diff --git a/004_image_stack_ram_based_reward_custom/__pycache__/street_fighter_custom_wrapper.cpython-38.pyc b/004_image_stack_ram_based_reward_custom/__pycache__/street_fighter_custom_wrapper.cpython-38.pyc deleted file mode 100644 index 859eef5..0000000 Binary files a/004_image_stack_ram_based_reward_custom/__pycache__/street_fighter_custom_wrapper.cpython-38.pyc and /dev/null differ diff --git a/004_image_stack_ram_based_reward_custom/logs/monitor.csv b/004_image_stack_ram_based_reward_custom/logs/monitor.csv deleted file mode 100644 index 137bced..0000000 --- a/004_image_stack_ram_based_reward_custom/logs/monitor.csv +++ /dev/null @@ -1,2047 +0,0 @@ -#{"t_start": 1680515263.2477837, "env_id": null} -r,l,t -0.19523,1437,6.158065 -0.515301,2178,12.733591 -0.634529,1375,16.361347 -0.434956,1856,22.400417 -0.501522,1312,25.952795 -0.625168,1210,30.836148 -0.458572,2566,37.943796 -0.351876,2734,57.698138 -0.438391,2093,64.435742 -0.560551,1632,68.687624 -0.353,2766,77.604214 -0.385311,1908,83.546733 -0.615739,956,86.49515 --0.126489,1632,92.323955 -0.344528,2451,99.244247 -0.546109,2006,105.640446 -0.205816,2114,112.294221 -0.361,2228,119.070559 -0.063959,1044,122.175435 --0.131312,1145,125.693627 -0.53285,1694,131.350782 -0.213564,1301,134.872645 --0.107708,1334,140.352893 -0.422398,1907,144.803949 -0.37097,2021,151.068017 --0.125282,1212,156.016458 -0.553221,1058,159.176978 -0.428607,1882,163.966119 -0.166701,1974,170.56537 -0.095926,1761,176.806112 -0.332661,1719,182.924983 -0.235783,1861,189.180695 -0.188014,1399,192.797684 -0.184866,1113,195.983856 -0.182883,971,198.910249 -0.519682,1859,205.101854 --0.092675,1103,208.582289 -0.012139,1399,212.352561 -0.252488,1761,218.047523 -0.193297,1857,224.25977 -0.208692,1949,230.906981 -0.333621,2097,237.512891 -0.337773,2379,244.75255 -0.2513,1880,251.02444 -0.118238,1465,254.738834 -0.143272,1599,260.233152 -0.115238,1035,263.322387 -0.222488,1903,269.358855 -0.151519,1236,272.746762 -0.330737,2823,281.849735 -0.147921,1557,286.12499 --0.082913,986,289.469522 -0.172711,1425,295.147659 -0.200396,1914,300.300695 -0.115668,1525,306.026715 -0.328661,2302,312.809297 -0.439802,2048,319.077458 -0.113238,2099,325.299501 -0.474391,2093,331.803078 -0.26322,1875,337.829412 -0.31958,1782,344.011115 -0.304042,2600,351.556374 -0.459925,2169,358.451489 -0.3998,2410,367.434605 -0.181701,1662,371.541217 -0.491624,2159,379.708102 -0.397427,1538,383.485948 -0.31445,2858,392.260264 -0.547118,2070,398.407839 -0.511811,2341,405.493453 -0.549531,1588,411.42555 -0.205692,1546,415.700895 -0.5381,1899,422.417346 -0.251053,2578,431.415421 -0.612009,1386,435.04311 -0.43306,2288,441.672518 -0.508798,1455,446.981311 -0.259453,1552,450.913679 -0.04349,1699,456.589592 -0.524278,1131,460.000105 -0.277589,1934,466.343967 -0.007862,971,469.754009 -0.117344,1503,473.722137 --0.219034,1166,477.240383 -0.015139,932,480.426492 -0.737164,939,483.609485 -0.711382,799,486.526034 -0.212714,1166,490.162396 -0.2813,1660,496.028137 -0.326661,1619,500.114207 -0.159701,1386,505.355108 --0.071708,875,506.670864 -0.090959,1632,512.384051 -0.390612,2145,519.090096 -0.306258,1475,524.835735 -0.637869,1551,529.168142 -0.148495,1816,535.591778 -0.158515,1398,539.720874 --0.348,734,542.705121 --0.317,1255,546.595661 --0.349,1100,549.926533 -0.119519,1733,555.513649 -0.000139,1527,559.493445 --0.348,1476,564.903809 -0.246965,2563,571.899967 -0.006402,1444,577.138756 -0.183515,1366,580.770298 -0.093538,1366,584.71654 --0.006942,1820,591.182403 --0.345,1551,596.844327 --0.167979,1610,601.199943 --0.344,1215,606.500184 --0.127189,1283,610.206978 -0.17023,1879,616.21545 --0.08845,1104,619.447153 --0.115312,1691,623.682969 --0.351,1703,629.398786 -0.046971,1393,633.026876 -0.654291,1020,636.088574 -0.296042,1474,641.88836 -0.207589,1393,645.986554 -0.171515,859,649.180724 -0.161692,1004,652.591506 --0.047345,1118,656.059297 -0.439674,1816,662.452899 --0.119719,695,665.224286 -0.215357,1689,669.57638 -0.133807,1206,672.997355 -0.554569,1141,676.219561 -0.143711,1061,681.136019 -0.612138,1053,684.297927 -0.142124,1360,687.912632 -0.35594,1303,691.454805 -0.61183,1122,694.705117 -0.348773,1638,700.282369 -0.260138,1118,703.69381 -0.25022,1459,707.834751 --0.136189,697,710.506485 --0.092708,656,713.368481 -0.512038,1350,717.456492 -0.215936,1185,721.207569 -0.790766,763,724.188263 --0.10633,949,727.460279 -0.500264,1197,730.916387 -0.154322,1561,736.378494 -0.084305,2713,743.596596 -0.288042,2210,749.929475 -0.271667,1939,755.80146 --0.034282,1310,761.071845 -0.10565,2669,769.011494 -0.665054,1081,772.349292 -0.63155,967,775.723073 -0.268453,2127,861.25144 --0.055274,1297,864.678903 -0.353421,3485,875.956086 -0.193866,2294,882.891786 -0.05049,1756,889.056097 --0.170979,1113,892.521465 -0.392633,2891,902.21622 -0.201564,2048,909.130561 --0.344,1215,912.500934 -0.346908,2427,919.333871 -0.124238,2442,927.647662 -0.430553,2160,934.037483 -0.568745,1695,938.161916 --0.119719,1924,944.71899 -0.413274,2635,954.097798 -0.397897,2141,960.963854 -0.429475,2720,970.295653 -0.443202,1759,974.55729 -0.645459,1489,979.827667 -0.106703,2176,986.089545 -0.185866,2401,993.050671 -0.258843,1696,998.988194 -0.318404,2209,1006.034883 -0.41305,3116,1016.445231 -0.339808,2304,1023.746192 -0.204883,1337,1029.279184 --0.012942,949,1032.342279 -0.47771,1950,1038.691317 -0.337773,1660,1042.72301 -0.354908,2174,1049.116896 -0.034518,1050,1052.316773 -0.212564,1974,1058.462567 -0.393509,1766,1064.790257 --0.35,805,1067.635236 -0.291153,1923,1073.914248 --0.300704,888,1075.434971 -0.344843,1183,1080.467153 -0.185059,1053,1083.905945 -0.039737,1199,1087.433287 -0.32958,1561,1091.687403 --0.088675,799,1094.410797 -0.083305,1172,1097.669537 -0.195297,1281,1102.680112 --0.11433,1210,1106.012133 -0.092668,1121,1109.231067 -0.067305,1096,1112.45206 -0.005402,1543,1116.243362 -0.218167,1378,1121.801496 -0.13565,1146,1125.317314 -0.445466,1546,1129.722465 -0.136807,1713,1135.968982 -0.034887,1681,1142.138187 --0.35,1345,1146.098068 --0.167979,1559,1150.017407 -0.038887,2163,1157.891188 --0.343,719,1158.930604 --0.003357,1401,1164.087668 --0.135189,1181,1167.377803 -0.230488,1911,1173.445371 -0.04749,1768,1177.539036 --0.076591,1939,1183.735026 --0.119189,1125,1187.273913 --0.063307,1855,1193.385057 -0.01055,1850,1199.738269 --0.092118,1783,1205.542241 --0.02251,1551,1209.611933 -0.611484,1124,1212.831633 --0.053913,1365,1257.246516 -0.092668,1575,1261.672053 --0.06606,1667,1267.971838 -0.113322,1713,1274.018948 -0.267378,1772,1278.298563 --0.34,860,1281.19556 -0.35397,1934,1287.302738 --0.125489,1623,1293.081073 --0.103312,760,1294.226408 -0.07287,1550,1299.920285 -0.133059,1015,1303.459678 --0.229111,807,1306.304986 -0.06687,1324,1310.216691 --0.06685,1158,1313.787076 -0.014225,1988,1320.335264 --0.237557,1135,1323.923253 -0.177277,920,1327.124238 -0.125926,1330,1330.766256 -0.279863,1644,1336.298713 -0.06187,1378,1339.90693 --0.292704,1093,1343.077613 --0.006942,889,1345.916135 --0.344,776,1348.635816 -0.120238,1094,1351.759519 -0.033136,1439,1355.401 -0.475082,1500,1360.853333 --0.05906,1527,1365.095499 -0.024305,1436,1370.650706 -0.227488,2269,1377.845103 -0.2593,1690,1384.237552 --0.153979,802,1385.820739 --0.155979,1520,1391.439341 -0.018518,2532,1398.59189 -0.412744,2411,1407.03341 --0.050675,815,1409.792042 -0.151124,2447,1416.783543 -0.100028,2969,1453.420833 --0.191557,749,1455.987653 -0.169124,2371,1462.494703 -0.136314,2130,1468.679571 --0.209034,1199,1472.010032 -0.209297,2017,1478.133822 -0.284863,2671,1487.710338 -0.060421,1620,1492.245922 -0.197714,2107,1499.292209 -0.225589,2161,1506.251105 --0.229301,918,1509.325238 -0.140519,1811,1515.233434 --0.339,1453,1520.525162 -0.196557,1642,1524.52582 --0.097133,1540,1529.974743 --0.351,1278,1533.503356 --0.208126,1153,1536.863022 -0.051971,1182,1540.376669 --0.06406,1599,1546.170679 -0.116238,1560,1550.229015 --0.003598,1490,1555.756008 --0.111312,855,1558.675586 -0.126314,1832,1563.295238 --0.35,1120,1566.929199 -0.055994,1710,1572.540122 -0.383589,2607,1581.04937 --0.154159,1645,1585.038229 --0.113719,819,1587.84268 -0.130807,1366,1591.416821 -0.137314,1313,1596.737995 --0.297,698,1597.786206 --0.194892,1224,1603.085769 -0.156322,7895,1627.861944 -0.163883,7513,1651.858899 -0.30845,3148,1661.703385 --0.015771,6835,1683.042569 -0.347876,2796,1692.217295 -0.102703,1947,1698.087837 -0.302308,2414,1704.675275 -0.195297,7623,1729.387191 -0.655668,1418,1733.751585 -0.089139,1707,1740.039815 --0.078603,1359,1744.177454 -0.487497,1597,1750.177523 -0.325098,1528,1753.965558 --0.170979,1154,1757.263989 -0.096668,1793,1763.023611 -0.4838,1753,1768.853634 -0.314404,2207,1775.428243 --0.040422,1819,1781.620307 -0.18123,1396,1785.539181 -0.029862,917,1788.71071 -0.463826,1825,1794.955051 -0.538331,1247,1798.604486 -0.257453,2063,1805.454289 -0.145495,1867,1811.581209 -0.484778,1621,1815.630368 -0.139314,1024,1818.82353 --0.087861,934,1821.742221 --0.148677,667,1824.269265 -0.014881,1068,1827.488811 -0.051484,1290,1830.936901 -0.605624,1089,1834.120461 -0.509868,1424,1839.431168 -0.111368,771,1840.782043 --0.001598,976,1844.13509 -0.077538,1599,1850.156449 -0.513584,1488,1854.556118 -0.007139,971,1857.910368 -0.033881,857,1861.096752 -0.469259,1789,1867.344983 -0.592102,1198,1870.875237 -0.194297,1165,1874.116925 -0.311308,1661,1879.699814 -0.35197,1415,1883.317267 -0.03255,953,1886.222523 --0.11133,834,1889.035276 -0.203816,1370,1892.819859 -0.011225,850,1895.886622 -0.200432,1353,1901.392485 -0.276799,1341,1905.13913 -0.012225,1168,1908.593209 -0.151272,1301,1912.287305 -0.188157,1447,1917.79455 -0.105023,1204,1921.299136 -0.083139,1292,1924.903875 -0.37697,2042,1931.232042 --0.089708,882,1934.122911 -0.244965,1544,1937.943445 -0.414081,2320,1946.069438 --0.208034,679,1947.042175 -0.447108,1636,1952.50968 --0.256389,772,1955.200019 --0.211029,857,1958.030758 --0.044298,1058,1961.324808 -0.319538,1501,1965.475011 --0.118489,939,1968.789795 --0.141111,807,1971.751039 -0.338538,1243,1975.536555 -0.120792,1359,1979.473296 -0.200863,1974,1985.968439 --0.173791,619,1988.612457 -0.427553,2118,1995.086241 -0.117028,1333,1998.80877 --0.346,1115,2002.186974 -0.531946,1542,2007.851241 --0.014295,1005,2011.074259 -0.097495,2041,2017.472274 -0.687268,1091,2020.768461 -0.498429,1884,2027.204569 -0.25022,3266,2037.528166 -0.520224,1909,2043.977005 -0.329737,1994,2050.595116 -0.501063,2084,2056.844635 -0.225384,1834,2062.8128 -0.052971,2058,2069.282586 -0.435135,2240,2076.121193 -0.457179,2495,2083.235508 -0.635026,1162,2086.889832 -0.717344,963,2090.244895 -0.602459,1489,2096.052326 -0.6952,1155,2099.615784 -0.428253,2402,2107.121103 -0.272,2086,2113.674139 -0.351876,2131,2120.222419 -0.289984,1965,2126.823019 --0.069307,793,2129.66934 --0.244557,802,2132.53505 --0.006138,828,2135.333235 --0.140121,967,2138.506217 -0.137792,1251,2142.089 -0.034737,1114,2145.5387 -0.326404,1204,2149.103445 -0.094368,1307,2152.843631 -0.528632,1258,2158.06034 -0.205432,1399,2161.957318 -0.315308,1354,2165.642179 --0.029295,993,2168.819197 -0.159322,904,2172.02226 --0.351,643,2174.630611 --0.04785,775,2175.833546 -0.122344,1205,2180.995522 -0.122238,1090,2184.240072 --0.161791,734,2185.333263 --0.056307,681,2188.065522 --0.082274,967,2191.122065 --0.220288,690,2193.761276 --0.286704,627,2194.751048 -0.03932,737,2197.503807 -0.085538,860,2200.60533 -0.11065,933,2203.703801 -0.279863,1149,2207.215951 -0.687173,886,2210.298792 -0.126314,1243,2214.004173 -0.036887,748,2216.829189 --0.11133,1037,2220.229309 --0.002972,1033,2223.378472 -0.35597,1768,2228.107189 --0.059674,1375,2233.456574 -0.293206,1206,2236.896558 --0.337,1252,2240.377609 -0.025518,1555,2245.776022 -0.037136,1341,2249.390244 --0.352,1311,2252.85374 -0.575432,1279,2257.928503 -0.420331,1498,2261.944631 -0.504647,1587,2267.729225 --0.348,1403,2271.508476 --0.349,1353,2275.237856 -0.115238,1267,2278.851226 --0.274416,1111,2283.686707 --0.120719,1511,2287.573651 -0.547995,1302,2291.117469 --0.295452,1227,2296.017473 --0.288704,1080,2299.180702 --0.294704,827,2300.431997 -0.265598,1621,2306.026564 -0.168515,1691,2311.735467 --0.149677,934,2314.787672 --0.352,1120,2318.100249 -0.067421,1736,2322.57612 -0.064421,1447,2328.246228 -0.617912,1394,2332.105186 -0.06287,2284,2339.001438 -0.378632,2311,2347.540457 -0.456259,1789,2351.846385 -0.123057,2070,2358.245325 -0.454913,2086,2364.53026 -0.228277,1957,2370.620599 -0.437388,2699,2379.421379 -0.423075,2827,2389.261088 -0.540823,1402,2393.273911 -0.360116,1645,2399.271965 -0.515053,1982,2405.830998 -0.652625,1360,2409.624835 -0.451607,1882,2415.672627 -0.194866,2414,2422.739834 --0.144121,2417,2429.647982 -0.434744,2888,2438.692997 -0.305308,2275,2447.180055 -0.451535,1697,2451.691131 -0.36597,2685,2460.792165 -0.565904,1762,2466.928705 -0.401682,2430,2474.079058 -0.693398,1142,2477.451829 -0.296153,2286,2483.914983 -0.471276,1897,2489.859246 --0.102133,2544,2498.480558 -0.281924,3162,2508.298685 -0.126314,3250,2518.200438 -0.590095,1400,2522.064434 -0.40156,2296,2528.932363 -0.063484,2784,2537.964735 --0.082913,1084,2541.065702 -0.237965,2263,2547.63395 -0.51688,1526,2553.192864 -0.256378,2145,2559.771576 --0.339,1403,2563.756909 --0.162979,1475,2569.340636 -0.291734,1906,2575.597026 -0.242965,1899,2581.990884 -0.194432,2069,2588.556953 -0.121519,1817,2592.86339 -0.141138,2368,2601.154252 -0.192014,1750,2605.458728 --0.055531,1888,2611.732713 -0.260453,1991,2618.190382 --0.014771,1681,2624.12154 -0.176396,1903,2630.400622 --0.246389,1147,2633.858814 -0.151792,1794,2639.934074 -0.324661,1867,2644.572418 -0.115238,2231,2652.856388 --0.139121,1226,2656.260673 --0.059674,1529,2660.022514 -0.039971,1059,2663.096704 --0.000357,1188,2666.386111 --0.147159,1067,2669.574053 -0.192297,943,2672.458737 -0.222488,1917,2678.399758 -0.428981,1935,2685.00839 -0.31445,1804,2691.304879 -0.241965,1656,2697.560014 -0.031737,1523,2701.772791 -0.44284,2833,2711.319422 -0.206564,1650,2715.386133 -0.127564,2087,2721.601892 -0.17323,1564,2727.023172 -0.161314,1232,2730.340679 -0.497543,1434,2735.662864 -0.455735,1724,2739.962049 -0.156124,1668,2746.015464 --0.028422,932,2749.184219 --0.001876,1194,2752.851671 -0.253688,1442,2757.124867 -0.263527,1175,2760.693759 -0.190866,1458,2766.377079 -0.304357,1314,2770.119318 -0.422967,2258,2776.608667 -0.504753,1440,2782.113143 --0.073591,805,2784.937071 --0.238288,773,2786.063277 --0.012406,1245,2791.055039 --0.128489,844,2792.326206 -0.513919,1559,2797.644229 -0.027518,1016,2800.987561 -0.268783,1689,2807.365137 -0.35294,2058,2814.253692 --0.011502,1387,2818.460335 -0.226488,1246,2822.291502 -0.11265,1239,2826.085949 --0.193557,693,2828.781463 --0.271113,632,2831.303579 --0.023282,832,2832.554826 -0.042437,1301,2837.682731 -0.305404,1488,2841.604492 -0.500698,1705,2847.330455 --0.011345,851,2850.180883 -0.236053,2036,2856.466957 --0.139268,864,2859.30354 -0.322153,1743,2863.914776 -0.510107,1740,2870.072052 --0.048531,970,2873.28235 --0.177791,1207,2877.031291 -0.312495,2397,2884.425658 -0.350843,2364,2892.88654 --0.184304,1328,2896.377923 -0.452793,1973,2902.579938 -0.293984,1348,2906.090774 --0.013623,751,2908.778114 -0.4758,1753,2914.48339 -0.31545,1682,2918.672555 -0.675359,1166,2922.307965 -0.329538,1887,2928.983038 -0.35094,1505,2934.774523 -0.57838,1148,2938.479162 --0.028531,985,2941.782721 -0.627229,1287,2945.639266 -0.045971,1123,2949.057375 -0.203816,1847,2954.91042 -0.466914,1656,2960.479946 -0.393068,2196,2966.781787 -0.35597,2504,2973.60168 -0.067305,2019,2979.933225 -0.241816,2031,2986.60401 -0.33758,1633,2992.632631 -0.369808,2546,3000.190516 -0.2613,2593,3009.412855 -0.069728,1418,3013.025114 -0.063484,1443,3018.213574 -0.583209,1216,3021.53969 -0.194277,1326,3025.111205 -0.110936,1430,3028.796881 -0.520925,2169,3036.724009 -0.313098,2427,3044.000988 -0.125948,1360,3048.09879 -0.322621,1831,3054.561651 -0.462529,1807,3061.111567 --0.344,1495,3065.496917 -0.206816,1705,3071.320697 -0.364725,2102,3077.597301 --0.046531,1364,3081.150166 -0.398621,2740,3089.972838 --0.333,987,3092.994737 --0.17435,1615,3098.481955 -0.35594,3177,3108.769684 --0.17835,1285,3112.589507 --0.352,2091,3119.323831 -0.201297,1513,3123.609362 --0.144111,1670,3129.480162 --0.098603,1338,3133.017705 --0.190113,1023,3136.056146 --0.208288,1689,3141.585299 --0.080913,1277,3144.967193 --0.154979,2097,3151.174063 -0.439069,2241,3157.54627 -0.122792,1294,3163.002219 --0.337,1547,3167.45009 -0.231688,1561,3173.375393 -0.017881,1528,3177.827719 -0.262688,1156,3181.549437 -0.281984,2516,3190.784662 -0.564675,1433,3194.42578 --0.229113,1417,3199.68172 --0.083913,1341,3203.253879 -0.125314,1345,3206.806545 -0.223488,2277,3213.423938 --0.120489,1348,3218.658591 --0.082913,1365,3222.61344 --0.34,597,3225.13959 --0.092118,972,3228.477257 --0.349,975,3231.55606 --0.024295,1952,3238.119529 --0.15044,883,3239.546431 -0.359773,2149,3246.355235 -0.034737,1512,3251.800153 -0.446564,2280,3258.244445 --0.35,863,3261.114645 -0.234688,2823,3269.886382 -0.114948,1969,3276.003557 -0.315495,2570,3283.490263 -0.210816,1853,3289.932563 -0.098368,1715,3296.336874 -0.278924,2516,3304.138137 --0.308,317,3304.769348 -0.328308,2001,3311.275757 -0.287734,2643,3320.057507 -0.177557,1682,3325.831429 -0.037855,1500,3329.56628 -0.150921,1793,3335.320864 -0.225297,1551,3339.28311 -0.009855,1872,3345.590387 -0.633049,1217,3349.292682 -0.099421,1076,3352.617174 -0.118238,2373,3361.131613 -0.50238,1466,3365.125313 --0.140111,1581,3370.752714 --0.316,545,3371.558929 --0.171979,1207,3374.865713 --0.013771,1511,3380.299099 -0.708798,1044,3383.453904 -0.183866,1737,3389.120378 --0.300704,807,3390.265381 --0.016771,1557,3395.646373 --0.230113,1728,3401.786225 --0.352,926,3404.976938 -0.105538,1664,3409.589694 -0.038518,1626,3415.68873 --0.15335,1208,3419.251427 --0.171979,1461,3423.486032 -0.305308,2071,3429.916502 -0.333357,1735,3435.67414 -0.232783,1747,3441.44432 --0.080274,1353,3445.062459 --0.081274,1108,3448.199685 -0.173396,2286,3454.768259 --0.038345,1321,3459.907258 -0.143792,1439,3464.064329 -0.318153,2117,3471.082403 --0.229113,784,3474.053053 -0.014862,964,3477.279507 -0.266378,1872,3483.78151 -0.247404,1506,3488.044053 --0.084274,1378,3493.261812 -0.36694,1573,3497.150517 -0.155495,1302,3500.618355 -0.052994,1288,3505.596302 -0.599909,1139,3508.824994 --0.000598,980,3511.804973 -0.006862,1077,3514.949461 --0.339,646,3515.886644 -0.119792,1256,3521.020645 --0.224288,571,3522.069886 -0.305206,1568,3527.818827 --0.218034,934,3531.152563 -0.432715,1734,3535.807103 -0.107926,577,3538.442038 --0.242923,852,3541.440731 -0.307153,1484,3545.700565 -0.177557,1879,3551.837416 --0.343,1472,3555.720024 -0.334737,2089,3562.051807 --0.15135,789,3564.884984 -0.337808,2260,3571.442088 -0.347876,1378,3576.664911 -0.353908,1637,3580.931627 --0.148268,1047,3584.207389 -0.44747,1941,3590.635359 -0.39994,2258,3597.524659 -0.215863,1750,3603.597916 --0.343,809,3606.507513 -0.583607,1411,3610.35376 -0.537735,1519,3615.79419 -0.243816,1386,3619.366106 -0.341876,2115,3625.580215 -0.175396,2014,3631.675213 -0.503246,1523,3637.081958 --0.010138,884,3639.977059 -0.512399,2382,3647.285137 -0.089926,1198,3650.987665 -0.000887,829,3654.052321 -0.023136,1352,3658.099741 -0.059421,1121,3661.608147 -0.471299,1979,3668.386918 --0.220923,738,3671.042192 --0.277416,1457,3674.802297 --0.345,1397,3679.963904 --0.343,986,3683.039049 --0.112719,2047,3689.220487 -0.172396,2039,3695.388716 --0.115,1049,3698.542931 --0.140111,1991,3704.842278 --0.082913,1470,3709.022272 -0.499119,1682,3714.848963 --0.069591,1705,3719.415927 --0.17335,1217,3724.658821 --0.107489,825,3726.189549 --0.037295,1519,3731.586523 --0.051674,1490,3735.39761 --0.268632,1636,3740.910265 -0.088023,1425,3744.496333 -0.338808,2793,3753.175724 --0.17435,1284,3756.63737 -0.492551,1632,3762.657962 --0.001138,1108,3766.223657 --0.034295,1765,3772.504371 -0.718076,783,3773.979744 -0.125314,1295,3779.611264 --0.155677,991,3783.012228 -0.580041,1180,3786.850374 -0.194515,1176,3790.523458 -0.06649,954,3793.553183 -0.060971,1146,3796.84827 -0.046887,1233,3800.295167 --0.341,1393,3805.447176 -0.218357,1266,3808.851801 --0.004357,1019,3811.894235 -0.127564,2373,3818.640186 -0.533984,1889,3825.274294 --0.35,1189,3828.830425 -0.06287,1964,3835.4508 -0.192866,1896,3841.940026 --0.15544,2002,3848.532753 --0.084274,1082,3851.686799 --0.088274,1155,3854.994491 -0.109948,2601,3863.464798 --0.129489,1210,3866.816376 --0.341,1011,3869.86583 --0.085274,1079,3872.982919 -0.45966,2232,3879.504321 -0.158921,1463,3883.872256 -0.358773,1925,3890.510958 --0.291704,656,3893.280232 -0.243965,2445,3901.238082 -0.200297,2432,3910.450869 -0.36194,2939,3919.460565 -0.075139,2916,3927.094302 -0.128564,2117,3935.037429 --0.11533,1606,3939.164108 -0.241965,2715,3948.560927 -0.11665,2095,3955.413003 -0.206692,1615,3960.066627 -0.37897,1749,3966.30495 -0.285799,2546,3974.766552 -0.173396,1683,3978.838822 -0.642726,1039,3981.896389 -0.584229,1287,3985.363463 -0.382624,2159,3993.313566 -0.256453,2423,4000.115316 -0.053437,1543,4004.543534 -0.467788,1914,4011.188746 -0.276378,1445,4016.994166 -0.310308,1895,4023.664815 -0.331737,1781,4028.496334 -0.528688,1403,4033.597858 -0.267527,2141,4039.780754 -0.216167,2034,4045.811713 -0.586264,1662,4049.781416 -0.38494,2743,4058.601798 -0.540469,1427,4062.616107 -0.415879,2060,4069.292865 -0.078728,2315,4077.892129 -0.121792,1758,4082.579987 -0.348808,1962,4088.91525 -0.077538,3420,4100.187304 -0.107124,2944,4109.122356 -0.627523,1118,4112.372732 --0.058307,3121,4122.038049 -0.263453,3215,4132.637727 -0.091368,2126,4139.800949 -0.092023,2628,4149.231755 -0.135124,1977,4153.945537 --0.326,2254,4162.173186 -0.272378,3024,4171.674757 -0.360661,2468,4178.411371 -0.250138,2734,4187.781152 --0.168677,2953,4197.581732 -0.122519,2988,4205.939325 --0.019623,2874,4214.808701 -0.028136,2100,4221.03255 -0.243053,2926,4230.009484 -0.278799,2021,4236.103949 -0.022136,2324,4243.396444 -0.070305,2280,4252.153447 -0.138272,1848,4256.855669 -0.01655,1946,4263.384491 -0.302153,2972,4272.531811 -0.275863,2486,4281.078846 -0.582089,1484,4284.818163 -0.303042,3449,4296.260442 --0.09733,1037,4299.400427 -0.293098,1531,4303.582474 -0.289924,1155,4307.088681 -0.011855,719,4309.788829 --0.030406,1113,4313.327255 --0.033531,840,4316.193095 -0.515871,1387,4320.181714 -0.237688,1224,4324.063946 -0.041971,1073,4327.614148 -0.024855,853,4330.48459 --0.343,602,4332.915373 --0.136189,960,4335.865295 -0.472231,1779,4340.069151 -0.582238,1015,4343.209347 -0.316357,793,4345.914411 -0.35,2062,4352.030387 -0.107948,1450,4357.337312 -0.056959,1026,4360.542578 -0.102926,775,4361.881787 -0.570102,1198,4367.306204 -0.26022,1311,4371.251237 -0.080926,1113,4374.803058 --0.057674,976,4378.258809 -0.024225,993,4381.609133 --0.009406,1086,4385.15683 -0.091368,927,4388.395686 -0.098028,1555,4392.267024 --0.062675,699,4394.850562 -0.222488,3345,4404.539643 --0.349,1355,4409.71288 --0.339,782,4410.90106 --0.255958,1157,4415.738795 -0.51739,1798,4420.049739 -0.029518,1110,4423.513936 -0.229384,3315,4435.338314 -0.602729,1188,4438.806216 -0.01255,1300,4442.455612 --0.061674,1969,4448.963027 --0.009138,2008,4455.003041 --0.13944,935,4457.869851 -0.143711,1370,4461.445308 -0.547135,3644,4473.043081 -0.043971,1217,4476.369048 --0.322,838,4479.229374 -0.601368,1215,4482.945704 --0.05885,1226,4486.804984 --0.068307,1335,4490.725798 -0.03432,1499,4496.622129 -0.45594,1722,4503.001523 --0.345,464,4503.876885 --0.084675,1210,4507.723686 --0.169677,988,4510.870716 --0.137121,629,4513.433221 -0.06687,1365,4516.965324 -0.172314,1654,4522.595638 -0.065728,992,4525.609026 -0.166883,1816,4529.901157 -0.307357,1786,4535.635861 --0.147489,533,4538.05758 -0.260053,1234,4541.791729 -0.48753,1726,4547.805227 -0.07187,1160,4551.417017 -0.155124,1151,4555.163406 -0.182701,1157,4558.76853 -0.442519,2026,4565.444977 -0.335661,1831,4571.528058 --0.102708,602,4572.412058 -0.134564,1605,4577.990885 -0.186396,1227,4581.417635 -0.127238,1146,4584.699157 -0.152432,2323,4592.871074 -0.442751,1194,4596.214182 --0.349,505,4596.968276 -0.052994,1077,4600.354687 -0.075421,1487,4606.417712 --0.080913,1568,4610.765579 -0.217277,2081,4617.724814 -0.36,3390,4630.20541 -0.229384,3320,4639.850678 -0.63153,1003,4643.032104 -0.134057,1269,4646.524737 -0.033737,1433,4650.19557 --0.001357,1118,4654.93996 -0.023881,1039,4658.119172 -0.242153,1625,4662.429227 -0.314357,1499,4668.294024 --0.162677,1630,4672.560985 -0.158124,2192,4679.436545 -0.232589,1705,4685.43347 -0.505538,2397,4692.441133 --0.088274,1050,4695.57734 --0.294452,1524,4700.914611 -0.302357,2650,4707.987097 -0.146924,1612,4713.487637 -0.538094,1566,4718.920379 -0.232564,1895,4723.806137 -0.474347,1547,4729.751319 -0.322357,1338,4733.839597 -0.556109,1583,4739.783026 -0.161124,1502,4744.106295 --0.049345,1109,4747.727468 -0.198432,1450,4753.107336 -0.157807,1779,4757.26502 -0.178783,1554,4762.725338 -0.427677,2024,4768.967131 -0.301042,3067,4778.25025 -0.343876,2706,4787.59367 -0.508911,1803,4792.24572 -0.309258,1854,4798.4222 -0.382401,1757,4804.503742 -0.213167,2570,4811.662571 --0.081913,1022,4814.718168 --0.183791,1181,4819.629143 -0.033136,1743,4823.761681 --0.148111,1382,4828.93657 --0.342,936,4830.329538 --0.35,811,4833.109017 --0.225288,1028,4836.310459 --0.190557,942,4839.450267 --0.14735,990,4842.822691 --0.122719,1050,4846.313598 --0.348,1008,4849.708977 --0.126312,770,4852.710364 -0.089057,1150,4856.474129 --0.255557,914,4859.662224 -0.073728,1194,4863.471691 --0.336,789,4866.549375 --0.018771,1456,4870.605457 --0.345,1060,4873.815956 --0.344,576,4876.247538 -0.200432,1698,4881.887199 --0.35,1197,4885.314188 --0.001598,2016,4891.558918 -0.161272,1298,4895.047681 --0.143979,886,4897.995451 -0.161515,1337,4901.939455 --0.041675,755,4904.764251 --0.006771,1373,4908.78973 -0.03332,1014,4912.075023 -0.329928,3120,4922.47082 -0.451788,2215,4929.251211 -0.246138,2117,4935.597492 -0.556559,1265,4940.617594 -0.015229,1317,4944.124383 -0.33197,2480,4950.951009 -0.446108,1627,4956.539521 -0.113344,2560,4965.952591 -0.543089,1508,4970.130159 -0.443137,2110,4977.393052 -0.144043,1976,4984.05484 -0.208936,1746,4990.474055 -0.479386,2315,4997.185249 -0.651049,1217,5000.619446 -0.46602,1731,5006.397124 --0.022623,1482,5010.276958 -0.348484,2250,5016.935491 -0.150124,1914,5023.409482 --0.060674,2172,5030.437284 -0.103703,2142,5038.790777 -0.05449,1952,5043.603817 -0.035887,1662,5049.392589 -0.119519,2212,5055.852248 -0.487878,1585,5061.384028 -0.565473,1412,5065.045184 -0.433203,2318,5073.577682 --0.028337,1420,5078.811265 --0.344,1513,5082.68572 -0.46533,1355,5088.259898 -0.649847,1303,5092.252929 -0.337773,1496,5096.432387 -0.454186,2056,5103.344823 -0.04332,2148,5110.317121 -0.235688,2003,5116.542571 -0.197866,2427,5124.808918 -0.456213,1769,5130.577841 -0.633023,1461,5134.270043 -0.251138,3800,5146.810488 -0.003855,3173,5156.515974 -0.066043,2000,5163.071823 -0.177297,1850,5167.678393 --0.081708,2320,5175.919214 -0.172396,2657,5183.013928 -0.436837,2324,5191.158984 -0.246053,2385,5197.767512 -0.134028,2452,5205.347904 -0.114238,1706,5211.622996 -0.633832,1231,5215.307814 -0.35097,8183,5241.836862 -0.052484,1563,5247.295573 -0.277863,1678,5251.421053 --0.347,868,5254.312518 -0.095703,1388,5259.4826 --0.235288,961,5262.566366 -0.04949,2371,5269.91487 -0.284799,1671,5274.450185 -0.190557,1562,5280.412756 --0.231389,1509,5284.568798 -0.624338,1004,5287.815119 --0.101708,1507,5293.229229 -0.445113,1378,5296.868172 -0.141792,1340,5301.986547 -0.365808,1978,5307.96617 -0.311495,1932,5312.380959 --0.34,990,5315.416383 -0.462549,2013,5321.715591 -0.470668,1456,5327.471761 --0.076133,1828,5334.058954 -0.234783,1516,5338.380817 --0.16344,1211,5342.226767 -0.00855,2547,5351.701293 --0.097603,974,5354.72539 -0.468324,2207,5361.158746 --0.15644,1302,5364.720943 --0.289704,1129,5368.058847 -0.345876,1982,5374.211908 -0.333773,2062,5380.403269 --0.165677,1201,5383.887744 --0.090603,1539,5389.677858 --0.115312,1452,5393.813883 -0.072305,1336,5399.16584 -0.223488,1957,5404.410425 -0.28522,1319,5409.64714 -0.053959,1454,5413.574143 -0.313357,2331,5420.10354 -0.254688,1774,5425.868834 -0.287042,1899,5431.8196 --0.305704,833,5434.562989 -0.007643,1257,5437.963905 --0.236557,1738,5444.041103 --0.342,846,5447.189602 --0.089118,1629,5451.649841 -0.273734,1427,5457.502013 -0.001377,1446,5461.660393 -0.183714,1718,5467.846429 -0.029881,1520,5471.943972 --0.348,883,5474.79476 --0.344,1405,5478.446155 -0.163883,2169,5484.679308 --0.155979,1071,5489.325063 --0.344,1315,5492.84808 --0.180892,1114,5496.049621 --0.168979,1149,5499.358802 -0.329495,1622,5504.890898 -0.209816,1447,5508.935915 -0.124314,2245,5515.931125 -0.25122,1569,5521.639646 --0.352,1326,5525.41189 --0.247923,1546,5531.185856 -0.021881,1561,5535.062219 -0.048437,1627,5540.574497 -0.268527,2047,5546.653633 -0.62441,1458,5550.391278 -0.175396,1441,5554.089336 -0.181557,1824,5559.906384 -0.100368,1608,5565.732669 -0.152272,1288,5569.830205 -0.244053,2201,5577.081988 -0.426455,1965,5583.899012 -0.559722,1479,5589.855785 -0.273734,1854,5594.169427 -0.728385,933,5597.016069 -0.300206,1905,5602.922627 -0.269527,1706,5608.621586 --0.021502,1775,5614.383343 -0.284042,2316,5621.013254 -0.273667,2118,5627.808437 -0.108948,1377,5631.948876 -0.189157,1777,5638.117679 -0.226167,2277,5645.33524 -0.111238,1827,5651.563409 -0.298984,1735,5657.263985 -0.295206,1876,5663.18263 --0.237288,1518,5666.924691 -0.212692,1840,5672.686523 -0.351737,3236,5682.351998 -0.25422,3225,5692.922391 -0.2563,2129,5699.847957 -0.064994,1857,5706.378307 -0.115948,1695,5712.485779 --0.225029,995,5715.507817 -0.608865,1175,5718.824531 -0.201564,1510,5722.678394 -0.324153,2170,5729.11362 --0.119719,975,5732.188314 -0.113948,2162,5738.653415 -0.252138,2095,5745.403173 -0.388498,2297,5754.166664 -0.236876,2534,5761.839545 -0.541865,1675,5767.990386 -0.354908,1952,5774.219398 --0.100298,965,5777.181948 --0.119,1107,5780.424902 --0.238288,1557,5784.401842 --0.341,951,5787.374677 -0.223277,1256,5790.893337 -0.167059,1658,5796.536301 -0.469868,1470,5800.250466 -0.208816,2130,5808.846785 -0.058959,1471,5813.043015 --0.116312,1203,5816.751998 -0.072421,2155,5823.944074 --0.097133,1308,5829.629675 --0.028337,1148,5833.070222 -0.596338,1004,5836.111869 -0.153124,1887,5842.126812 --0.15644,836,5843.376813 -0.027737,2205,5849.906301 -0.292863,2113,5857.717624 --0.343,555,5858.537487 -0.193157,1485,5864.28233 -0.290098,1976,5869.197867 -0.151138,1511,5874.913371 --0.050531,776,5877.794555 --0.104312,514,5878.666167 --0.016771,1076,5882.286914 -0.214936,1932,5888.820822 -0.12065,986,5892.042545 -0.245384,1394,5895.700425 -0.309,1638,5901.286556 --0.006771,1279,5904.78494 --0.015422,1042,5907.948572 -0.234384,1570,5913.406626 --0.033295,921,5916.339752 -0.516463,1227,5919.733629 -0.055959,1561,5924.19836 --0.35,557,5926.894445 --0.138189,1063,5930.482134 -0.247053,2249,5937.994894 --0.196892,1324,5943.553428 -0.074305,935,5945.37597 --0.086274,1245,5950.9072 -0.070421,7492,5973.094405 -0.195157,1480,5976.891176 -0.146495,1181,5981.796896 -0.451652,2395,5989.174185 -0.198014,2390,5996.509364 --0.13044,1540,6002.370263 -0.16923,2656,6010.234923 -0.007855,3165,6019.7185 -0.286734,3149,6030.614329 -0.377325,3140,6039.839199 -0.429135,2638,6047.883652 -0.351564,2280,6055.188777 -0.445829,2128,6062.36235 --0.025298,1636,6068.537771 -0.141238,1577,6074.141933 --0.080913,2043,6080.372906 -0.31958,7121,6102.188617 -0.529012,1408,6106.241162 -0.336808,2866,6115.522102 -0.029518,1970,6122.184685 -0.289042,2568,6129.684911 -0.310357,3490,6141.224181 -0.343843,2604,6148.205766 -0.334917,2481,6156.544557 -0.277598,3575,6167.373222 -0.394474,2568,6176.643057 -0.465817,2276,6183.830182 -0.344166,2554,6191.403542 -0.397813,2502,6199.971796 -0.303258,3375,6209.791496 -0.096368,2534,6216.677556 -0.24922,2740,6225.640627 -0.374588,2814,6234.710389 --0.032771,2233,6241.685884 -0.31858,2962,6251.55284 -0.472535,1697,6257.153012 -0.35097,2352,6263.787839 -0.373852,3511,6273.761007 --0.352,829,6276.560491 -0.098926,1009,6279.650259 -0.486574,2064,6286.437614 -0.311357,1477,6292.225999 --0.341,670,6293.46533 --0.044531,895,6296.666902 --0.336,892,6299.846632 -0.089305,938,6303.058818 --0.073118,1492,6307.241227 -0.325538,1650,6313.058896 -0.318357,1429,6316.849548 -0.234688,2234,6324.885667 -0.431146,1720,6329.054803 -0.014023,1702,6334.842205 --0.327,651,6337.634974 -0.458709,2011,6344.099353 -0.397297,1820,6348.988579 -0.489816,1733,6355.250047 --0.147159,1064,6358.663886 -0.060437,1631,6364.557702 -0.5251,1750,6369.238692 -0.00955,1443,6374.598927 -0.092302,3259,6384.296524 -0.30945,1895,6390.245358 -0.338843,2274,6396.780075 -0.104344,2609,6405.906445 -0.189014,2605,6413.838614 -0.489705,1962,6420.686162 -0.151043,2051,6427.65946 -0.432204,2030,6434.263956 -0.026139,1256,6437.68719 -0.655058,1144,6440.956564 -0.541457,1580,6446.468524 -0.270453,2126,6452.855658 -0.503722,1479,6456.652216 -0.464781,2887,6466.161268 -0.377565,1562,6472.150282 -0.36197,1537,6476.384704 --0.063274,937,6479.56561 --0.002502,909,6482.523817 --0.088603,1093,6485.898084 -0.021518,1530,6491.604765 --0.038913,813,6492.783138 --0.077913,1130,6496.073145 -0.463053,1982,6502.188851 -0.564461,1505,6507.592048 -0.360908,2358,6514.331911 -0.33645,2239,6520.904118 --0.047422,677,6523.655755 -0.298153,2189,6530.829952 --0.079591,1433,6536.497303 -0.148314,1272,6540.428329 -0.097368,1150,6543.945122 -0.547043,1721,6550.246143 -0.192014,1407,6553.891604 -0.49635,2003,6560.156629 -0.076421,1249,6563.576739 -0.592103,1760,6569.341666 --0.017771,1326,6572.877005 -0.150272,3104,6582.269182 -0.329495,2445,6591.093794 -0.295892,3826,6601.948863 --0.067482,1650,6607.867417 -0.565975,2154,6614.304911 -0.295206,3417,6624.173096 -0.598965,1845,6630.09135 -0.464646,2838,6638.889792 -0.324751,2915,6648.599843 -0.172515,2597,6656.481103 -0.359843,2665,6666.107239 -0.450413,2162,6672.819482 --0.07106,2865,6681.971034 -0.603872,810,6684.721881 -0.636322,1052,6687.815156 -0.627133,1075,6690.944474 -0.087538,1612,6694.970953 -0.143711,1930,6701.164314 -0.221053,3053,6711.196565 -0.043887,1747,6717.278919 -0.291098,2581,6725.042861 -0.192866,2549,6733.723555 --0.296704,1529,6737.594664 -0.071139,1494,6742.867958 --0.352,1306,6746.272062 -0.193297,1574,6751.694504 -0.199432,2401,6758.373966 -0.008402,1408,6762.281101 --0.334,1214,6767.613314 --0.106719,1163,6771.35154 -0.594101,1268,6775.188399 --0.343,1054,6778.793913 -0.479674,1816,6785.172569 --0.05385,2434,6792.826478 --0.34,862,6795.691527 --0.077913,747,6798.600601 --0.347,1097,6801.823327 -0.126238,2024,6808.056642 --0.335,697,6809.125969 -0.01655,1412,6814.514986 -0.200692,1661,6818.732883 -0.434825,2142,6827.10932 --0.129312,584,6828.132037 -0.190322,894,6831.254365 -0.331737,2224,6838.150245 -0.329621,2767,6847.371639 -0.122057,1456,6851.338668 -0.176059,1274,6856.438951 --0.193159,847,6857.703573 --0.141121,1531,6863.144211 -0.253488,1144,6866.426025 --0.022406,849,6869.371567 --0.230113,1195,6872.695554 -0.187014,1909,6878.739926 -0.095139,1856,6885.017663 --0.117,788,6886.374966 -0.257453,1445,6892.043072 -0.149807,1545,6896.542332 -0.423924,1924,6903.069518 -0.305699,1175,6906.786506 -0.349908,2237,6915.146006 -0.753574,559,6915.985007 -0.506082,1500,6921.341305 -0.483918,1732,6925.645544 -0.150921,918,6928.635748 -0.382988,1550,6934.107512 -0.155322,1580,6938.047634 --0.044345,1224,6941.680169 -0.154272,1209,6946.892132 -0.033225,1210,6950.502258 -0.243773,1886,6956.868342 -0.276667,1500,6961.018618 -0.250783,1491,6965.095321 -0.067484,1143,6970.147074 -0.191059,1323,6973.640304 -0.152404,1318,6977.159902 -0.232783,1968,6983.21078 --0.110719,765,6985.961497 -0.06587,2748,6994.77563 -0.012225,2724,7002.175253 -0.45809,3051,7012.288314 -0.039887,2928,7022.021594 -0.390462,2923,7031.668286 --0.041282,2718,7040.374459 -0.375572,3099,7049.693112 --0.247923,2430,7056.456709 --0.16044,2112,7063.000013 -0.261053,2563,7072.4312 -0.121057,2610,7080.457869 -0.415628,2525,7089.888759 --0.012502,766,7091.021937 --0.030337,1025,7094.078752 -0.086728,799,7096.835955 -0.813619,682,7099.422627 -0.166883,1165,7102.722572 --0.005942,1093,7105.990694 --0.337,763,7108.714064 -0.023881,1098,7111.959539 -0.336699,1179,7115.302588 --0.091118,754,7118.009159 -0.302258,1265,7121.52588 -0.026881,851,7124.612368 -0.264153,1395,7128.825383 --0.027282,1002,7132.283046 --0.35,658,7135.001756 -0.097023,997,7138.365637 -0.731126,543,7139.373637 -0.253688,1083,7143.007174 --0.261958,875,7146.018109 --0.010138,722,7148.921973 -0.137043,1143,7152.590885 -0.205816,1285,7156.048967 --0.260452,807,7158.821968 -0.253042,1405,7162.689427 -0.623587,1056,7165.834158 -0.222053,1113,7169.12726 -0.10565,1108,7174.105973 -0.312357,1375,7177.751518 -0.157564,783,7180.487637 -0.190059,892,7183.732581 --0.139111,699,7184.957763 -0.129519,1231,7188.630695 --0.004138,909,7191.749587 --0.047422,800,7194.758445 -0.221167,2222,7201.689299 -0.35494,3531,7214.07029 -0.060959,2557,7220.994854 -0.293206,3772,7232.801884 -0.03055,2564,7239.710421 --0.103,1760,7245.756227 -0.107344,2829,7255.530724 -0.119238,1996,7262.154307 -0.538182,2137,7269.298527 -0.338843,2836,7278.39509 -0.344737,3144,7287.794695 -0.126314,2827,7295.27331 -0.191322,1744,7301.041757 -0.144564,1472,7306.695998 -0.384373,3400,7317.233634 -0.023136,2158,7323.840893 --0.001942,1586,7329.729916 -0.072305,3493,7339.554313 -0.303258,2527,7346.327104 -0.17023,2356,7354.443623 -0.084668,2710,7361.760124 --0.127489,2255,7370.328627 -0.011139,2276,7377.624908 -0.200432,6621,7397.793312 -0.512662,1631,7403.37194 -0.350538,2727,7412.132349 -0.17123,2034,7418.292473 -0.056484,2350,7425.38721 --0.047422,1429,7429.624414 -0.058959,1903,7436.474757 --0.130189,1255,7440.379282 -0.25322,1468,7446.113152 -0.058484,1427,7450.228447 --0.072675,2059,7456.305244 --0.139121,1593,7461.770935 --0.144111,1549,7465.595454 -0.095023,1913,7471.528526 --0.158304,1740,7477.192059 --0.076274,1547,7481.303122 -0.072728,1652,7487.459523 --0.055531,2317,7494.864194 --0.133189,1557,7500.672775 --0.35,1349,7504.76235 -0.410069,2536,7513.770541 -0.261378,1300,7517.380375 -0.108302,1309,7520.896391 -0.32158,2354,7527.602602 -0.015855,1217,7532.682105 -0.246053,1958,7537.16981 -0.288598,1784,7543.24433 --0.109708,704,7546.147681 --0.057531,1190,7549.766725 --0.118312,684,7552.473243 -0.34894,2661,7560.312189 -0.047136,951,7563.593174 -0.25122,1426,7569.417938 -0.209936,1229,7572.80815 -0.144711,1515,7576.603079 -0.079538,2018,7582.712487 --0.108121,1135,7586.016139 -0.186866,1101,7589.156592 -0.306404,2336,7597.462422 --0.077591,1419,7601.106096 -0.708106,1000,7604.441884 -0.08487,806,7607.3616 --0.058913,1170,7610.942386 -0.545498,2065,7617.722328 -0.079028,933,7621.004918 -0.181167,1648,7627.113026 -0.135564,1625,7631.367309 -0.378571,2432,7639.725504 --0.022623,1210,7643.100652 -0.343808,2505,7649.989471 -0.515078,1833,7655.788805 -0.497518,1883,7661.915326 -0.447311,1768,7667.960258 -0.658211,1149,7671.319555 -0.53464,922,7674.506827 --0.206389,636,7675.551201 -0.433769,2562,7684.741263 -0.425258,2150,7691.491993 -0.502401,1670,7695.467297 -0.495924,1365,7700.634034 --0.067307,1146,7703.889017 -0.440007,2273,7710.440969 --0.054531,1036,7713.543747 --0.001357,1278,7716.936149 -0.204396,1563,7722.533118 --0.05906,1478,7726.726277 -0.018225,1524,7732.554766 --0.032295,1194,7736.346183 -0.013225,1182,7740.021631 --0.015623,1875,7746.449881 --0.006771,1582,7750.774651 --0.10733,1350,7755.990352 -0.06587,1896,7761.956896 -0.083538,2104,7768.282504 -0.004139,1376,7771.931926 --0.117111,1147,7775.204176 --0.05806,1158,7778.501034 -0.023518,2194,7785.637445 -0.051484,1608,7791.68095 -0.183866,2464,7799.553043 --0.023406,1567,7805.429028 --0.065133,1337,7809.536716 -0.053959,1706,7815.334217 -0.233692,1646,7820.852117 -0.534401,1757,7824.992982 -0.164515,1914,7830.859568 -0.370113,2990,7839.956648 -0.413189,2224,7847.056374 -0.161322,1923,7853.340841 -0.306734,1485,7859.098086 -0.324621,2472,7866.756829 -0.137519,2591,7874.230381 -0.41523,1853,7880.250185 -0.463541,2132,7886.78198 --0.003357,1260,7891.960317 -0.35397,1501,7895.784774 -0.476808,1985,7901.971638 -0.470541,1894,7908.461114 -0.267527,2032,7914.970028 -0.359955,1959,7921.549664 -0.367876,2935,7931.495661 -0.358557,3166,7940.975351 -0.480572,2379,7947.641581 --0.078913,1868,7953.591977 -0.410962,3653,7964.56509 -0.045971,2515,7973.834343 -0.596147,1407,7978.048554 -0.531273,2164,7984.986622 -0.328258,2720,7994.094134 -0.680593,1078,7997.371024 -0.112028,1726,8003.061945 -0.232924,2077,8009.333768 -0.502541,2608,8016.310991 -0.238688,2130,8022.748544 -0.314206,1934,8029.20437 -0.44481,1937,8035.558279 -0.159495,1861,8041.818151 -0.338773,2838,8051.303128 -0.331098,1922,8057.398742 --0.020531,829,8058.594579 --0.131312,874,8061.487954 -0.52718,1349,8066.631847 --0.33,724,8067.693624 -0.381905,1742,8073.359874 -0.163701,1782,8079.123339 -0.456697,1658,8083.386266 -0.499251,1377,8088.706672 -0.172124,1904,8095.206384 --0.321,560,8096.134335 -0.464888,2184,8102.962576 -0.237965,1919,8109.403981 -0.057421,1183,8112.763895 -0.238965,1783,8118.678681 -0.386462,2923,8127.725682 --0.058531,2083,8134.137103 -0.01055,1904,8140.136525 -0.093926,2366,8147.1555 -0.349943,3654,8159.899681 -0.364663,3840,8170.989666 -0.290098,2930,8179.991883 -0.321621,2830,8188.844911 --0.05406,11559,8225.918204 -0.603443,1107,8229.649346 --0.301704,810,8232.527807 -0.724379,786,8235.294538 -0.203984,1237,8238.810967 --0.029406,1370,8244.228987 --0.341,778,8245.370353 --0.055531,1085,8248.573262 --0.202034,936,8251.580722 -0.2783,1649,8257.332073 -0.130807,1417,8261.13381 -0.503515,1529,8266.93986 -0.185432,1342,8270.850161 -0.259527,1679,8276.879414 --0.072307,1538,8281.176495 --0.055674,1078,8284.563461 --0.007138,687,8287.513818 -0.544778,1200,8291.040457 -0.134043,923,8293.924237 -0.090495,903,8296.812253 -0.054484,1088,8299.980766 -0.327699,1439,8303.649385 -0.643709,912,8306.646952 -0.050484,737,8309.294598 -0.506468,1481,8313.087323 -0.240488,919,8315.994892 -0.25422,1119,8319.171668 -0.257453,1180,8324.532991 --0.302704,811,8325.943463 -0.422094,2097,8333.053019 -0.539215,1483,8338.894663 -0.25122,2493,8346.61376 -0.174396,1810,8352.837762 -0.717612,927,8355.947262 -0.224053,2098,8362.270691 -0.329699,1849,8368.495738 -0.299734,2517,8375.830219 -0.188157,2438,8384.493001 -0.460652,1677,8388.89849 -0.126519,1801,8394.893211 -0.421109,2006,8401.531183 -0.197014,1875,8407.728225 -0.213936,2019,8414.495124 -0.35197,1476,8418.265205 -0.10465,1867,8424.231416 -0.591953,1243,8427.776566 -0.275863,2188,8434.240082 -0.417483,2161,8442.946673 -0.628528,1214,8446.605994 -0.257495,1993,8453.119108 -0.130807,2155,8459.968418 -0.193866,1545,8464.27452 -0.161322,989,8467.584927 -0.649726,1039,8471.042084 -0.542644,1271,8476.231449 -0.211936,1685,8480.332281 -0.546629,1893,8486.307214 -0.479452,1895,8492.474297 -0.144495,1615,8496.669073 -0.184396,1689,8502.519696 -0.199564,1523,8508.337996 -0.259783,1755,8512.957785 -0.205564,1867,8519.519014 -0.283984,2112,8526.337322 -0.147495,1380,8532.107956 -0.348737,1942,8536.640707 -0.242053,2025,8543.054471 -0.127564,2004,8549.139486 --0.025295,1617,8554.637595 -0.349908,2094,8561.074543 --0.086133,1553,8565.472458 --0.339,914,8568.83683 -0.114519,1826,8575.231667 -0.06787,1849,8581.676151 --0.16244,1157,8585.454049 -0.553786,1257,8589.422538 --0.326,795,8592.277899 -0.582831,1494,8597.657163 -0.020881,2515,8604.613717 -0.270667,2478,8611.518872 --0.106133,980,8614.673984 -0.547204,1414,8619.936675 -0.471542,1952,8626.644103 -0.493786,1880,8633.224904 --0.004357,1231,8636.870582 -0.2513,1757,8641.54044 -0.281984,1937,8648.088308 -0.023518,1952,8654.170644 -0.492187,1672,8659.861657 -0.383541,2608,8666.809605 -0.234876,2179,8674.806142 -0.348,1836,8679.083841 -0.026136,2828,8689.138344 -0.605413,1079,8692.619756 -0.182714,1761,8698.957198 -0.171124,1137,8702.54288 --0.351,765,8705.59548 -0.335808,2219,8712.344451 -0.181883,2100,8718.583604 -0.115519,2059,8724.814011 -0.321538,1750,8730.734331 -0.338661,1543,8734.707125 -0.416575,2414,8743.285412 -0.34845,1446,8747.150629 -0.172059,2449,8754.378422 -0.211053,2726,8763.510882 --0.037295,2243,8770.185641 -0.244138,2556,8778.795629 -0.239783,2397,8785.534515 -0.24922,1740,8791.403489 -0.506152,1532,8795.226704 -0.260167,2310,8801.964056 -0.129314,2211,8812.433811 -0.406917,2687,8820.630056 -0.478317,1451,8826.725393 --0.032282,2511,8834.220695 -0.469924,2938,8844.261599 -0.147711,2435,8851.760725 -0.408414,1873,8858.232635 -0.256453,2547,8867.82813 -0.286053,1331,8871.926818 -0.677024,882,8875.137198 -0.35097,3352,8886.021838 -0.109948,1698,8892.375193 -0.119519,1793,8898.687383 -0.071728,1779,8903.264689 -0.613803,1704,8909.470993 -0.399355,2655,8918.834705 -0.476413,1221,8922.514926 -0.342843,1987,8929.583241 -0.640779,1225,8933.491396 -0.390733,3160,8944.188872 -0.488396,2472,8952.061294 -0.347908,2544,8961.281587 -0.385776,2325,8968.468217 -0.505427,1538,8974.333568 -0.294206,2628,8981.988766 -0.175059,1428,8987.722642 --0.079591,1610,8992.030082 -0.286042,1447,8997.917967 --0.075307,1544,9002.104958 -0.099028,1792,9008.533449 -0.507176,1248,9012.271259 -0.30845,2891,9022.162931 -0.112703,1008,9025.470801 --0.05885,1123,9028.955804 -0.420321,2222,9035.914469 -0.280799,2364,9043.188725 -0.383811,2483,9052.792629 --0.174719,1659,9057.287931 --0.025295,1109,9062.613318 --0.34,707,9063.808647 --0.276452,1194,9067.611562 -0.33158,2339,9076.513098 -0.103344,1380,9080.365199 --0.014771,1378,9084.255263 --0.036295,1550,9090.209013 --0.34,900,9093.348933 -0.065421,1592,9097.578418 --0.042298,800,9100.55485 --0.058531,1762,9106.767682 -0.098305,996,9110.020326 -0.138272,1382,9113.900784 --0.080274,1218,9117.574631 --0.101133,1172,9121.204749 --0.137189,1398,9126.929999 --0.022406,1132,9130.498577 --0.344,1392,9134.381 -0.154921,1736,9140.591604 -0.115948,1958,9147.099252 --0.025337,1794,9153.484286 -0.146921,2080,9160.152147 -0.014881,1254,9164.110757 -0.268527,1784,9170.84759 --0.016332,1597,9175.403139 --0.116,1600,9181.687542 -0.069421,1430,9186.081166 --0.000406,777,9189.259108 -0.091023,1079,9192.838141 -0.695665,879,9195.979869 -0.539001,1423,9200.037938 -0.633109,1242,9204.101888 -0.535865,1263,9209.722444 -0.184714,1385,9213.714225 -0.211053,1297,9217.505085 -0.06187,905,9220.945875 -0.128519,1511,9227.183677 -0.252138,1390,9231.4105 -0.622848,1212,9235.378855 -0.095368,781,9238.518782 -0.187557,937,9241.778562 -0.586692,1164,9245.560947 --0.327,602,9248.298558 -0.21258,1213,9252.224421 -0.599183,1294,9255.956561 --0.177791,947,9259.121361 --0.139189,681,9261.945591 -0.137043,912,9265.156599 -0.148711,935,9266.619707 -0.114396,1106,9271.92098 -0.065994,935,9273.405191 -0.364843,1559,9279.282578 -0.067959,846,9282.381462 --0.138189,560,9283.350982 --0.228113,771,9286.519524 --0.058531,715,9289.523735 -0.133807,1008,9293.160452 -0.219277,1227,9297.103878 --0.249923,1684,9303.617581 --0.275322,1057,9306.95552 --0.351,886,9310.198537 --0.081603,1302,9313.810947 --0.351,900,9316.827981 -0.437326,2135,9323.297344 -0.44337,2177,9329.868601 -0.2903,1963,9337.323388 -0.344908,2270,9344.731814 --0.097603,1460,9348.781978 --0.128312,1741,9355.078686 -0.187014,1143,9358.634718 -0.125792,1263,9362.347845 -0.17023,2491,9371.53837 -0.196157,2347,9378.654622 -0.204692,1498,9384.383464 -0.453452,1895,9390.926672 -0.281799,2845,9398.893615 -0.402094,1566,9404.958967 --0.014623,1264,9408.994035 --0.053531,1211,9412.756188 --0.18806,1265,9416.704011 --0.017406,846,9419.802929 --0.141111,1020,9423.24905 --0.005563,1336,9429.043645 -0.01555,1706,9433.467349 --0.178791,1379,9439.055954 -0.124519,1450,9443.037458 -0.004663,988,9446.276842 --0.011771,1493,9450.351884 -0.076139,1350,9455.93089 -0.094368,1536,9460.066689 -0.113948,1776,9466.383154 --0.270704,857,9469.48643 -0.065959,1536,9473.65579 -0.528152,1532,9479.538274 --0.035422,930,9482.770559 -0.028136,1088,9486.269268 --0.249791,927,9489.445099 -0.315,1699,9493.873626 --0.260322,1137,9499.080485 --0.178268,928,9500.558508 -0.138692,1514,9506.42015 -0.095668,1654,9512.489796 -0.346737,1585,9516.800315 -0.27822,1501,9522.785475 -0.5472,1155,9526.565085 -0.44691,1534,9530.914695 -0.557215,1483,9536.932656 -0.434508,1465,9541.271383 -0.058437,1429,9545.526352 -0.447791,1612,9551.77328 -0.324042,1702,9558.054865 -0.40716,2255,9565.183127 -0.499139,2404,9572.512318 -0.293153,2057,9579.348116 -0.333341,2192,9586.764838 -0.31545,2051,9594.015859 -0.55202,1731,9600.621291 -0.095023,2198,9607.942578 -0.663778,1200,9611.916975 -0.02055,1632,9618.296708 -0.440234,1875,9624.44946 -0.426777,1639,9629.278634 -0.283984,2024,9637.483425 -0.413804,1743,9645.405545 -0.345808,2085,9653.713054 -0.697528,1171,9657.456864 --0.345,1068,9661.693827 -0.328308,1700,9669.01629 --0.15344,1588,9676.622054 -0.495501,1756,9682.320488 --0.161979,1176,9685.742069 -0.238876,1979,9692.253916 --0.338,822,9695.262573 -0.321538,2469,9704.072829 --0.142708,1614,9708.190741 -0.357737,2257,9715.061541 -0.03132,1490,9720.929062 --0.281311,1685,9725.182852 -0.233783,1880,9731.279319 --0.129312,1163,9734.64942 -0.335661,2309,9742.98312 --0.193301,733,9744.126235 -0.146042,1392,9750.04841 --0.136121,1048,9754.096798 --0.345,1237,9758.905269 -0.176396,1728,9766.727719 -0.228488,1507,9772.096863 -0.185714,1392,9777.204087 -0.053959,1630,9784.584174 -0.090437,862,9788.443965 --0.296704,1282,9792.834872 --0.119312,683,9795.404369 -0.03432,1110,9798.657723 -0.204432,1012,9801.761656 -0.163124,1978,9808.425494 -0.050994,1434,9813.323866 -0.162883,1215,9817.987822 -0.011225,1830,9825.921638 -0.219053,1720,9833.577734 -0.09187,1699,9841.476802 --0.069118,762,9843.097113 -0.003855,1478,9850.427651 -0.077139,1420,9855.642607 -0.162948,1355,9860.861471 --0.06106,1792,9868.367412 -0.432716,2326,9875.015212 --0.009771,936,9877.942922 -0.511512,1554,9883.724778 -0.599472,1035,9887.213377 -0.476603,1745,9893.608616 -0.10465,1477,9897.810396 -0.281863,1300,9901.70241 -0.187714,873,9905.139867 -0.107948,1479,9912.431255 -0.191297,1523,9917.753748 --0.348,879,9921.66522 -0.31858,1346,9926.534055 --0.35,616,9929.852669 --0.349,567,9931.138176 -0.141495,1146,9937.756367 --0.127312,848,9939.583571 -0.619711,1251,9946.225687 -0.271453,1556,9951.575055 -0.356908,1686,9959.27784 -0.331661,1266,9964.014715 -0.052519,1265,9968.794289 -0.336773,1953,9975.054784 --0.333,837,9977.938066 -0.436685,2294,9984.548091 -0.175557,1814,9990.524363 --0.352,1725,9996.197741 --0.277416,1667,10000.33215 --0.35,1447,10006.903015 -0.025136,1643,10012.386861 --0.351,1525,10019.757132 --0.343,1344,10024.833764 -0.046994,1989,10033.252281 -0.35497,2603,10044.794616 --0.136121,1829,10050.613914 --0.055531,1523,10057.826907 --0.067307,1374,10062.718791 -0.002402,2429,10074.011074 --0.332,1519,10079.206482 --0.168677,1281,10083.94434 -0.014225,1335,10090.812446 --0.079675,1903,10096.920312 --0.06685,1805,10104.158103 --0.300704,1561,10109.578006 --0.172979,1469,10113.228468 -0.034737,2008,10119.274612 -0.646045,1115,10122.7493 -0.262598,1848,10129.164333 -0.478335,1841,10135.587393 -0.536683,1561,10139.908014 --0.163677,726,10142.769332 -0.40535,2418,10150.081842 -0.259453,2021,10156.558774 --0.024502,1262,10161.650701 --0.042282,930,10164.707554 --0.049422,765,10165.845477 -0.285984,1404,10171.378414 -0.478016,1438,10175.118942 --0.313,766,10178.008039 -0.084302,1097,10187.005437 -0.345538,2239,10194.005328 -0.01955,909,10197.09613 -0.046994,1351,10201.01025 -0.454276,1897,10207.311392 -0.229014,1328,10210.97305 -0.31958,1703,10216.841009 -0.57048,1019,10220.015394 -0.01055,1076,10223.267362 -0.454079,1673,10229.224617 -0.426439,2176,10235.881055 -0.504598,2025,10242.103011 -0.681846,1033,10245.416895 -0.290153,2290,10252.698996 -0.2853,1265,10256.500966 -0.359876,2733,10265.964206 -0.07187,1951,10272.560488 -0.621971,1712,10278.407147 --0.161677,2194,10285.101516 --0.001357,1902,10291.125623 -0.342876,2593,10298.111219 -0.35497,3606,10310.776561 -0.193124,1386,10314.76463 -0.31645,3071,10324.817897 -0.489152,2018,10331.390096 -0.072728,1138,10334.66247 --0.352,579,10337.176966 --0.334,641,10338.189691 -0.299863,1493,10343.754897 --0.345,581,10344.642584 -0.433352,1320,10350.075285 --0.342,801,10351.285367 -0.34994,1299,10356.509296 -0.127564,1273,10360.113587 -0.412065,1791,10366.618155 -0.24645,1354,10370.621154 -0.35097,1387,10374.629982 --0.138677,870,10377.735433 -0.562832,1231,10381.300071 -0.022881,1333,10386.794741 --0.083913,1163,10390.323088 -0.007139,927,10393.45161 -0.039518,665,10394.463485 -0.307308,999,10397.754746 --0.123719,638,10400.412601 -0.484186,1591,10404.46817 -0.569722,1002,10407.661551 -0.134043,1557,10413.324012 --0.134312,545,10415.781434 -0.156322,1121,10419.204554 -0.01455,979,10422.382061 -0.066437,924,10423.817133 --0.002357,796,10426.622307 -0.264527,1252,10430.354993 -0.584003,1121,10435.470129 -0.453838,2260,10442.383041 -0.189014,2199,10449.152822 -0.54835,1652,10454.854498 -0.186816,3044,10464.207938 -0.610485,1473,10468.065901 -0.190866,2543,10475.032645 -0.274863,1978,10481.529024 --0.00313,2312,10490.405779 -0.253053,3101,10500.643087 -0.086668,1320,10504.452186 -0.127057,2842,10513.918492 --0.125489,1423,10517.857187 -0.064518,1640,10523.572568 -0.270734,2602,10530.794524 -0.323495,2244,10537.276643 -0.206816,1583,10542.842922 -0.41763,2378,10550.11211 --0.35,606,10552.69151 -0.022518,1068,10555.988159 -0.326,1634,10561.652667 -0.583874,1151,10565.08183 -0.220384,1877,10569.635858 -0.081538,2719,10578.877268 -0.157124,1615,10584.58867 -0.144711,1845,10590.556854 --0.334,663,10591.575933 --0.130312,1057,10594.887073 -0.193297,1386,10600.366652 -0.128564,2321,10607.725653 -0.401928,2621,10615.475762 -0.131807,1689,10621.783959 -0.244589,1183,10625.438225 -0.520613,1353,10631.057469 -0.442329,1778,10635.187839 -0.220277,1299,10640.34815 --0.058913,1052,10643.551044 -0.098028,1568,10647.635385 --0.15335,1111,10650.961933 -0.129792,1253,10654.429516 --0.004138,1333,10659.690359 --0.352,1417,10663.713793 -0.154124,1553,10669.594352 -0.149272,1851,10674.349936 -0.209692,1967,10680.893208 -0.073139,2017,10687.633584 --0.347,844,10690.511572 --0.189304,1169,10693.899713 --0.163979,1521,10699.355731 -0.004855,2441,10706.058564 --0.226557,1412,10711.258245 -0.227167,1891,10715.588298 --0.034345,1272,10720.606355 --0.082913,1419,10724.831479 -0.015881,1417,10728.992351 -0.072959,1328,10734.525931 -0.289042,1573,10739.018857 -0.315495,2413,10748.048215 -0.443156,1663,10752.562618 -0.286042,1790,10758.726717 -0.31145,2105,10765.544843 --0.115312,1065,10768.829353 -0.588874,1151,10772.312763 -0.422452,1895,10778.390475 -0.200564,1803,10784.553664 -0.022518,1441,10788.536764 -0.305404,2135,10795.176641 -0.291098,1712,10801.079039 --0.305704,1283,10804.730947 --0.14944,947,10807.776403 -0.280734,2066,10814.203199 --0.069274,1327,10817.920161 -0.744418,812,10820.756027 -0.323404,1689,10826.589612 -0.677377,904,10829.528356 --0.006942,1464,10833.373283 --0.144121,1662,10839.13562 -0.431998,2289,10846.012632 -0.037437,1729,10851.974735 -0.287598,1575,10856.452862 -0.018792,1290,10862.043998 -0.524103,1801,10866.565504 -0.710544,861,10869.647034 -0.166322,1677,10875.551189 -0.076538,1364,10879.345465 -0.427678,2247,10885.972412 -0.296098,1552,10891.505085 -0.31545,2158,10898.003943 --0.290452,1631,10902.211606 --0.112489,1278,10907.556134 -0.389786,1880,10913.81234 -0.285378,1240,10917.258223 -0.196157,1847,10923.792352 --0.034295,1376,10927.547058 -0.146495,1880,10933.650134 -0.399362,2677,10940.818152 --0.113,1163,10945.882157 diff --git a/004_image_stack_ram_based_reward_custom/__pycache__/custom_cnn.cpython-38.pyc b/004_rgb_stack_ram_based_reward_custom/__pycache__/custom_cnn.cpython-38.pyc similarity index 100% rename from 004_image_stack_ram_based_reward_custom/__pycache__/custom_cnn.cpython-38.pyc rename to 004_rgb_stack_ram_based_reward_custom/__pycache__/custom_cnn.cpython-38.pyc diff --git a/004_rgb_stack_ram_based_reward_custom/__pycache__/street_fighter_custom_wrapper.cpython-38.pyc b/004_rgb_stack_ram_based_reward_custom/__pycache__/street_fighter_custom_wrapper.cpython-38.pyc new file mode 100644 index 0000000..92e8160 Binary files /dev/null and b/004_rgb_stack_ram_based_reward_custom/__pycache__/street_fighter_custom_wrapper.cpython-38.pyc differ diff --git a/004_image_stack_ram_based_reward_custom/check_reward.py b/004_rgb_stack_ram_based_reward_custom/check_reward.py similarity index 100% rename from 004_image_stack_ram_based_reward_custom/check_reward.py rename to 004_rgb_stack_ram_based_reward_custom/check_reward.py diff --git a/004_image_stack_ram_based_reward_custom/custom_cnn.py b/004_rgb_stack_ram_based_reward_custom/custom_cnn.py similarity index 100% rename from 004_image_stack_ram_based_reward_custom/custom_cnn.py rename to 004_rgb_stack_ram_based_reward_custom/custom_cnn.py diff --git a/004_image_stack_ram_based_reward_custom/evaluate.py b/004_rgb_stack_ram_based_reward_custom/evaluate.py similarity index 100% rename from 004_image_stack_ram_based_reward_custom/evaluate.py rename to 004_rgb_stack_ram_based_reward_custom/evaluate.py diff --git a/004_image_stack_ram_based_reward_custom/logs/PPO_1/events.out.tfevents.1680427238.DESKTOP-9E17TO7.27420.0 b/004_rgb_stack_ram_based_reward_custom/logs/PPO_1/events.out.tfevents.1680427238.DESKTOP-9E17TO7.27420.0 similarity index 100% rename from 004_image_stack_ram_based_reward_custom/logs/PPO_1/events.out.tfevents.1680427238.DESKTOP-9E17TO7.27420.0 rename to 004_rgb_stack_ram_based_reward_custom/logs/PPO_1/events.out.tfevents.1680427238.DESKTOP-9E17TO7.27420.0 diff --git a/004_image_stack_ram_based_reward_custom/logs/PPO_10/events.out.tfevents.1680505905.DESKTOP-9E17TO7.28664.0 b/004_rgb_stack_ram_based_reward_custom/logs/PPO_10/events.out.tfevents.1680505905.DESKTOP-9E17TO7.28664.0 similarity index 100% rename from 004_image_stack_ram_based_reward_custom/logs/PPO_10/events.out.tfevents.1680505905.DESKTOP-9E17TO7.28664.0 rename to 004_rgb_stack_ram_based_reward_custom/logs/PPO_10/events.out.tfevents.1680505905.DESKTOP-9E17TO7.28664.0 diff --git a/004_image_stack_ram_based_reward_custom/logs/PPO_11/events.out.tfevents.1680509256.DESKTOP-9E17TO7.5124.0 b/004_rgb_stack_ram_based_reward_custom/logs/PPO_11/events.out.tfevents.1680509256.DESKTOP-9E17TO7.5124.0 similarity index 100% rename from 004_image_stack_ram_based_reward_custom/logs/PPO_11/events.out.tfevents.1680509256.DESKTOP-9E17TO7.5124.0 rename to 004_rgb_stack_ram_based_reward_custom/logs/PPO_11/events.out.tfevents.1680509256.DESKTOP-9E17TO7.5124.0 diff --git a/004_image_stack_ram_based_reward_custom/logs/PPO_12/events.out.tfevents.1680515264.DESKTOP-9E17TO7.29580.0 b/004_rgb_stack_ram_based_reward_custom/logs/PPO_12/events.out.tfevents.1680515264.DESKTOP-9E17TO7.29580.0 similarity index 51% rename from 004_image_stack_ram_based_reward_custom/logs/PPO_12/events.out.tfevents.1680515264.DESKTOP-9E17TO7.29580.0 rename to 004_rgb_stack_ram_based_reward_custom/logs/PPO_12/events.out.tfevents.1680515264.DESKTOP-9E17TO7.29580.0 index beda370..3a3cbb6 100644 Binary files a/004_image_stack_ram_based_reward_custom/logs/PPO_12/events.out.tfevents.1680515264.DESKTOP-9E17TO7.29580.0 and b/004_rgb_stack_ram_based_reward_custom/logs/PPO_12/events.out.tfevents.1680515264.DESKTOP-9E17TO7.29580.0 differ diff --git a/004_rgb_stack_ram_based_reward_custom/logs/PPO_13/events.out.tfevents.1680536443.DESKTOP-9E17TO7.28860.0 b/004_rgb_stack_ram_based_reward_custom/logs/PPO_13/events.out.tfevents.1680536443.DESKTOP-9E17TO7.28860.0 new file mode 100644 index 0000000..12dabb9 Binary files /dev/null and b/004_rgb_stack_ram_based_reward_custom/logs/PPO_13/events.out.tfevents.1680536443.DESKTOP-9E17TO7.28860.0 differ diff --git a/004_rgb_stack_ram_based_reward_custom/logs/PPO_14/events.out.tfevents.1680569566.DESKTOP-9E17TO7.27436.0 b/004_rgb_stack_ram_based_reward_custom/logs/PPO_14/events.out.tfevents.1680569566.DESKTOP-9E17TO7.27436.0 new file mode 100644 index 0000000..6955c54 Binary files /dev/null and b/004_rgb_stack_ram_based_reward_custom/logs/PPO_14/events.out.tfevents.1680569566.DESKTOP-9E17TO7.27436.0 differ diff --git a/004_rgb_stack_ram_based_reward_custom/logs/PPO_15/events.out.tfevents.1680569667.DESKTOP-9E17TO7.1708.0 b/004_rgb_stack_ram_based_reward_custom/logs/PPO_15/events.out.tfevents.1680569667.DESKTOP-9E17TO7.1708.0 new file mode 100644 index 0000000..b880717 Binary files /dev/null and b/004_rgb_stack_ram_based_reward_custom/logs/PPO_15/events.out.tfevents.1680569667.DESKTOP-9E17TO7.1708.0 differ diff --git a/004_rgb_stack_ram_based_reward_custom/logs/PPO_16/events.out.tfevents.1680571727.DESKTOP-9E17TO7.35332.0 b/004_rgb_stack_ram_based_reward_custom/logs/PPO_16/events.out.tfevents.1680571727.DESKTOP-9E17TO7.35332.0 new file mode 100644 index 0000000..23d3b6a Binary files /dev/null and b/004_rgb_stack_ram_based_reward_custom/logs/PPO_16/events.out.tfevents.1680571727.DESKTOP-9E17TO7.35332.0 differ diff --git a/004_rgb_stack_ram_based_reward_custom/logs/PPO_17/events.out.tfevents.1680571830.DESKTOP-9E17TO7.33956.0 b/004_rgb_stack_ram_based_reward_custom/logs/PPO_17/events.out.tfevents.1680571830.DESKTOP-9E17TO7.33956.0 new file mode 100644 index 0000000..d563a48 Binary files /dev/null and b/004_rgb_stack_ram_based_reward_custom/logs/PPO_17/events.out.tfevents.1680571830.DESKTOP-9E17TO7.33956.0 differ diff --git a/004_rgb_stack_ram_based_reward_custom/logs/PPO_18/events.out.tfevents.1680576745.DESKTOP-9E17TO7.27264.0 b/004_rgb_stack_ram_based_reward_custom/logs/PPO_18/events.out.tfevents.1680576745.DESKTOP-9E17TO7.27264.0 new file mode 100644 index 0000000..f3b2cb0 Binary files /dev/null and b/004_rgb_stack_ram_based_reward_custom/logs/PPO_18/events.out.tfevents.1680576745.DESKTOP-9E17TO7.27264.0 differ diff --git a/004_rgb_stack_ram_based_reward_custom/logs/PPO_19/events.out.tfevents.1680577003.DESKTOP-9E17TO7.26744.0 b/004_rgb_stack_ram_based_reward_custom/logs/PPO_19/events.out.tfevents.1680577003.DESKTOP-9E17TO7.26744.0 new file mode 100644 index 0000000..7566224 Binary files /dev/null and b/004_rgb_stack_ram_based_reward_custom/logs/PPO_19/events.out.tfevents.1680577003.DESKTOP-9E17TO7.26744.0 differ diff --git a/004_image_stack_ram_based_reward_custom/logs/PPO_2/events.out.tfevents.1680442574.DESKTOP-9E17TO7.8472.0 b/004_rgb_stack_ram_based_reward_custom/logs/PPO_2/events.out.tfevents.1680442574.DESKTOP-9E17TO7.8472.0 similarity index 100% rename from 004_image_stack_ram_based_reward_custom/logs/PPO_2/events.out.tfevents.1680442574.DESKTOP-9E17TO7.8472.0 rename to 004_rgb_stack_ram_based_reward_custom/logs/PPO_2/events.out.tfevents.1680442574.DESKTOP-9E17TO7.8472.0 diff --git a/004_rgb_stack_ram_based_reward_custom/logs/PPO_20/events.out.tfevents.1680577202.DESKTOP-9E17TO7.31172.0 b/004_rgb_stack_ram_based_reward_custom/logs/PPO_20/events.out.tfevents.1680577202.DESKTOP-9E17TO7.31172.0 new file mode 100644 index 0000000..68b3e7b Binary files /dev/null and b/004_rgb_stack_ram_based_reward_custom/logs/PPO_20/events.out.tfevents.1680577202.DESKTOP-9E17TO7.31172.0 differ diff --git a/004_image_stack_ram_based_reward_custom/logs/PPO_3/events.out.tfevents.1680450538.DESKTOP-9E17TO7.4520.0 b/004_rgb_stack_ram_based_reward_custom/logs/PPO_3/events.out.tfevents.1680450538.DESKTOP-9E17TO7.4520.0 similarity index 100% rename from 004_image_stack_ram_based_reward_custom/logs/PPO_3/events.out.tfevents.1680450538.DESKTOP-9E17TO7.4520.0 rename to 004_rgb_stack_ram_based_reward_custom/logs/PPO_3/events.out.tfevents.1680450538.DESKTOP-9E17TO7.4520.0 diff --git a/004_image_stack_ram_based_reward_custom/logs/PPO_4/events.out.tfevents.1680494082.DESKTOP-9E17TO7.1808.0 b/004_rgb_stack_ram_based_reward_custom/logs/PPO_4/events.out.tfevents.1680494082.DESKTOP-9E17TO7.1808.0 similarity index 100% rename from 004_image_stack_ram_based_reward_custom/logs/PPO_4/events.out.tfevents.1680494082.DESKTOP-9E17TO7.1808.0 rename to 004_rgb_stack_ram_based_reward_custom/logs/PPO_4/events.out.tfevents.1680494082.DESKTOP-9E17TO7.1808.0 diff --git a/004_image_stack_ram_based_reward_custom/logs/PPO_5/events.out.tfevents.1680501562.DESKTOP-9E17TO7.12740.0 b/004_rgb_stack_ram_based_reward_custom/logs/PPO_5/events.out.tfevents.1680501562.DESKTOP-9E17TO7.12740.0 similarity index 100% rename from 004_image_stack_ram_based_reward_custom/logs/PPO_5/events.out.tfevents.1680501562.DESKTOP-9E17TO7.12740.0 rename to 004_rgb_stack_ram_based_reward_custom/logs/PPO_5/events.out.tfevents.1680501562.DESKTOP-9E17TO7.12740.0 diff --git a/004_image_stack_ram_based_reward_custom/logs/PPO_6/events.out.tfevents.1680502870.DESKTOP-9E17TO7.21800.0 b/004_rgb_stack_ram_based_reward_custom/logs/PPO_6/events.out.tfevents.1680502870.DESKTOP-9E17TO7.21800.0 similarity index 100% rename from 004_image_stack_ram_based_reward_custom/logs/PPO_6/events.out.tfevents.1680502870.DESKTOP-9E17TO7.21800.0 rename to 004_rgb_stack_ram_based_reward_custom/logs/PPO_6/events.out.tfevents.1680502870.DESKTOP-9E17TO7.21800.0 diff --git a/004_image_stack_ram_based_reward_custom/logs/PPO_7/events.out.tfevents.1680503637.DESKTOP-9E17TO7.30508.0 b/004_rgb_stack_ram_based_reward_custom/logs/PPO_7/events.out.tfevents.1680503637.DESKTOP-9E17TO7.30508.0 similarity index 100% rename from 004_image_stack_ram_based_reward_custom/logs/PPO_7/events.out.tfevents.1680503637.DESKTOP-9E17TO7.30508.0 rename to 004_rgb_stack_ram_based_reward_custom/logs/PPO_7/events.out.tfevents.1680503637.DESKTOP-9E17TO7.30508.0 diff --git a/004_image_stack_ram_based_reward_custom/logs/PPO_8/events.out.tfevents.1680504617.DESKTOP-9E17TO7.5124.0 b/004_rgb_stack_ram_based_reward_custom/logs/PPO_8/events.out.tfevents.1680504617.DESKTOP-9E17TO7.5124.0 similarity index 100% rename from 004_image_stack_ram_based_reward_custom/logs/PPO_8/events.out.tfevents.1680504617.DESKTOP-9E17TO7.5124.0 rename to 004_rgb_stack_ram_based_reward_custom/logs/PPO_8/events.out.tfevents.1680504617.DESKTOP-9E17TO7.5124.0 diff --git a/004_image_stack_ram_based_reward_custom/logs/PPO_9/events.out.tfevents.1680505010.DESKTOP-9E17TO7.28200.0 b/004_rgb_stack_ram_based_reward_custom/logs/PPO_9/events.out.tfevents.1680505010.DESKTOP-9E17TO7.28200.0 similarity index 100% rename from 004_image_stack_ram_based_reward_custom/logs/PPO_9/events.out.tfevents.1680505010.DESKTOP-9E17TO7.28200.0 rename to 004_rgb_stack_ram_based_reward_custom/logs/PPO_9/events.out.tfevents.1680505010.DESKTOP-9E17TO7.28200.0 diff --git a/004_rgb_stack_ram_based_reward_custom/logs/monitor.csv b/004_rgb_stack_ram_based_reward_custom/logs/monitor.csv new file mode 100644 index 0000000..a444c1c --- /dev/null +++ b/004_rgb_stack_ram_based_reward_custom/logs/monitor.csv @@ -0,0 +1,2922 @@ +#{"t_start": 1680577201.635132, "env_id": null} +r,l,t +0.517049,1217,4.197745 +0.718659,1034,5.697015 +0.618338,748,6.920976 +0.480607,1411,9.425264 +0.487443,1624,12.316793 +0.16923,2073,15.984169 +0.34258,1988,29.735386 +0.307404,2128,34.113894 +0.524784,1366,37.005667 +0.284527,1923,41.069882 +0.043028,1063,53.345574 +0.456394,1530,55.709616 +-0.079274,2504,60.153251 +0.569831,1494,62.781357 +0.295153,1845,66.016562 +0.311404,1939,79.237397 +0.543399,1068,80.982861 +-0.162677,1011,82.850329 +0.260527,1576,85.499347 +0.163883,2707,90.098924 +-0.335,608,101.49608 +0.340495,1861,104.601814 +0.174495,1408,107.310611 +0.046994,1533,110.352843 +0.069305,2787,115.455173 +-0.011942,1166,127.408902 +0.499113,1378,129.512156 +0.468216,1944,133.221178 +0.300206,2136,136.880262 +-0.344,1445,139.528157 +0.089139,1491,152.573515 +0.006139,2694,157.800156 +-0.099708,945,159.721347 +0.586689,1848,163.487041 +-0.026295,1594,166.756116 +0.506054,1081,178.466649 +0.301206,3167,183.724507 +-0.042041,1392,186.136086 +0.620239,1191,188.003523 +-0.018771,1034,189.842154 +0.595406,1266,202.535173 +0.293206,1813,205.857839 +0.347119,1682,208.87808 +0.233384,2106,213.138132 +0.188014,1279,215.807527 +0.200059,1448,228.892726 +-0.018345,659,230.07427 +0.239692,1111,232.197562 +0.281799,2605,236.718053 +0.104668,1507,239.450644 +0.27322,1849,253.36409 +0.090668,1241,255.256439 +0.478542,1952,258.672869 +-0.169979,1664,261.62492 +0.299153,1220,264.074272 +0.124792,1887,278.159782 +0.250589,1136,280.31614 +0.538724,1667,283.608424 +0.089668,1711,286.762413 +0.32445,1695,290.064136 +0.624183,1294,292.631576 +0.293863,1936,306.038916 +0.338773,1972,309.321796 +0.36397,2187,313.234781 +0.503678,2247,317.215487 +-0.000357,2161,331.330989 +0.452734,1238,333.788888 +-0.106133,1626,337.132599 +-0.216034,985,338.865824 +0.161515,3399,355.226085 +-0.116,2254,358.878617 +0.501585,1605,361.789395 +0.328621,3888,378.812001 +-0.074591,913,380.164083 +0.298206,1783,383.305446 +0.446521,2219,387.991029 +-0.134121,3595,405.279121 +-0.117,1443,408.022504 +-0.168791,942,409.988892 +-0.224029,1772,413.428313 +0.294153,1672,416.457088 +0.26522,2361,430.924273 +0.20223,1430,433.152574 +0.287734,1133,435.142847 +0.270598,1926,438.43171 +0.089668,1101,440.363197 +0.514545,1678,443.515344 +0.623748,966,455.497985 +0.485577,2104,459.426568 +-0.078591,1487,462.335821 +0.344908,2090,466.208006 +-0.132189,1399,468.915935 +-0.003598,1087,480.788554 +0.485356,1788,483.709647 +0.222488,1858,486.957328 +0.549706,1495,489.471737 +0.000643,1848,492.822415 +0.106028,1624,505.528778 +0.578957,1493,508.407739 +0.514865,1868,512.069174 +0.149564,3076,518.237521 +-0.173979,1524,531.511799 +0.016881,1215,533.421235 +-0.129121,1454,536.000591 +0.268667,1291,538.397302 +0.328661,1721,541.359965 +-0.034282,1324,543.621083 +0.697327,862,555.025303 +0.467793,1973,558.097428 +0.182866,2541,562.734306 +0.34258,1726,565.776165 +0.606865,1263,568.015717 +0.259378,2220,581.871493 +0.4237,1754,585.491933 +-0.307,1002,587.361678 +0.286863,1453,590.413698 +-0.119121,888,592.263954 +0.462474,2452,606.312788 +-0.042282,1510,608.795432 +0.190014,2038,612.515585 +0.378009,3704,629.1838 +0.451541,2132,633.512194 +0.525965,1845,637.666425 +0.138564,1516,640.932325 +0.406721,2216,655.691414 +-0.063913,1548,658.055518 +-0.095603,1211,660.056268 +0.038887,1566,662.82468 +0.115948,998,664.607762 +0.587913,1038,666.470588 +-0.295704,1136,668.545947 +-0.179791,978,680.210357 +0.554894,1462,682.649643 +0.353002,2305,687.172473 +0.094368,1475,690.03423 +-0.115307,1185,692.387845 +0.198297,1996,706.399954 +-0.328,1190,708.545261 +0.523058,1844,712.304445 +0.366737,2019,715.915618 +0.194866,1366,718.318925 +0.162883,2454,732.494276 +0.11165,1628,735.144053 +0.490156,1663,738.171277 +0.536354,2252,742.291923 +0.534632,1258,744.942447 +0.188866,1361,757.586746 +-0.131189,883,759.444167 +0.234688,2769,765.222721 +0.005855,1719,768.971338 +-0.352,868,770.872081 +0.143807,2426,784.931937 +-0.201126,1042,786.663939 +0.271734,3956,793.732086 +-0.047422,1110,795.714514 +0.166515,1701,808.730186 +-0.042345,2098,812.635902 +0.218692,2204,816.881681 +0.473438,1679,820.287576 +0.251277,1421,832.597006 +0.296206,2662,836.921959 +-0.282452,1080,838.926415 +0.608946,1372,841.399305 +-0.096603,1625,844.313953 +0.011229,873,845.899704 +0.042437,2567,859.961862 +0.052881,1062,861.871103 +0.17023,1789,865.537169 +0.473116,1645,868.75522 +-0.002598,1236,881.533493 +0.656529,1285,883.755705 +0.656593,1135,886.040097 +0.115926,1325,888.757288 +0.073139,1861,891.982671 +0.271688,1427,894.546751 +0.265527,2483,908.601468 +0.587294,1203,910.521064 +0.074139,2208,914.356361 +0.054028,1338,916.747551 +0.267589,1288,919.007836 +0.339808,3410,935.546451 +0.189866,1923,939.541233 +-0.05885,1996,943.498307 +0.557613,1735,957.088509 +0.159515,2073,960.151983 +0.006139,1289,962.402541 +0.280863,1924,965.854637 +0.287734,1548,968.598337 +0.166322,1091,970.601129 +0.250965,1793,983.901333 +-0.026531,834,985.547697 +0.03432,771,987.149429 +0.320249,2301,991.662403 +0.091305,1077,994.018633 +0.097368,2272,1009.052309 +0.545904,1762,1012.40333 +0.626447,1450,1014.982267 +-0.032337,1593,1017.827964 +-0.300704,750,1019.184178 +0.049994,1279,1021.458406 +0.301308,1356,1033.917027 +0.249138,2427,1037.848335 +0.137668,869,1039.38535 +0.506963,1485,1042.13165 +0.202692,2760,1047.422625 +0.155238,1555,1060.4589 +0.2663,1841,1063.770452 +0.115344,1335,1066.083339 +0.443217,1980,1069.424038 +0.101344,1917,1082.64571 +-0.346,549,1083.47471 +0.133564,1898,1086.523313 +0.370094,1566,1089.352961 +0.343808,2894,1094.413141 +-0.275311,1456,1107.304505 +0.192157,1318,1109.842693 +0.415823,2392,1114.612055 +0.332661,1964,1118.565267 +0.626411,1435,1121.476385 +0.198014,1919,1134.639159 +0.153124,3363,1140.437105 +0.2553,2295,1144.468176 +-0.196892,1112,1156.343038 +-0.037282,1829,1159.099632 +0.297042,1486,1161.778086 +0.332773,2313,1166.282692 +-0.026674,849,1167.997369 +0.050887,1080,1170.121202 +0.401191,3250,1186.058415 +0.086668,2165,1190.292452 +-0.166791,873,1191.943745 +0.484011,1702,1194.956042 +0.533264,1662,1207.570214 +0.050484,2626,1211.830542 +-0.079591,1045,1213.700701 +0.328621,2033,1217.296271 +0.204297,1578,1220.197963 +0.355204,2030,1233.879502 +0.04132,1496,1236.952504 +0.39197,1530,1240.242026 +0.542046,1329,1242.991131 +0.614623,987,1244.749607 +0.535446,2610,1259.20615 +0.473012,1408,1261.564657 +0.268688,2317,1265.578211 +0.04232,1664,1268.541401 +0.272453,1540,1281.077117 +0.31245,2152,1284.517913 +0.175059,845,1285.983095 +0.460399,2148,1289.782252 +0.241692,1095,1291.818747 +0.172936,1206,1294.058157 +0.334876,2110,1308.016009 +0.066994,1421,1310.996342 +0.343876,2458,1315.602011 +0.504294,1799,1318.634603 +0.054994,1436,1331.223175 +-0.263029,1425,1333.425537 +0.299863,1860,1336.742243 +-0.065307,1375,1339.044389 +0.33158,1456,1341.527798 +0.230564,1700,1354.812804 +0.058959,1696,1358.063308 +0.096023,1195,1360.609915 +0.630082,1492,1363.755704 +0.06687,1130,1366.207886 +0.152921,1765,1369.92651 +-0.076274,1093,1382.145246 +0.265924,2344,1385.92067 +0.134043,1755,1389.065155 +0.178714,1911,1392.399507 +0.430605,3005,1407.695479 +0.160863,1287,1410.1343 +0.48531,2016,1414.125035 +-0.162979,777,1415.684446 +0.318495,2039,1419.826862 +-0.022623,2781,1434.375624 +0.081959,2108,1437.976454 +0.162883,1550,1440.79004 +0.642485,1473,1443.406625 +0.127519,1842,1456.60033 +-0.074307,2093,1459.903941 +-0.002502,766,1461.406044 +0.105028,2526,1465.960363 +0.448146,1720,1469.288478 +0.37171,2944,1485.09294 +0.07349,1269,1487.469816 +-0.096708,925,1489.138378 +0.339821,2712,1493.994532 +0.419114,2596,1508.234438 +0.383629,3569,1514.539212 +0.352843,2431,1518.708483 +0.283984,1880,1531.719801 +0.180557,1667,1534.493291 +0.27322,1592,1537.494778 +0.262589,1302,1540.000464 +-0.122312,858,1541.554193 +0.37704,2460,1555.694603 +0.065926,1061,1557.380853 +0.240453,1686,1560.42136 +0.368968,2882,1565.59237 +0.388363,2080,1579.375758 +0.222297,1584,1581.902641 +0.35194,2156,1586.338705 +0.046971,1516,1589.559577 +-0.159677,1451,1592.667793 +0.192014,1611,1605.699015 +0.018518,1462,1608.486207 +0.157495,1024,1610.629872 +0.183714,2428,1615.104727 +-0.019623,1238,1617.232158 +0.454386,1942,1631.077039 +0.51215,1843,1634.331611 +0.078538,2465,1638.807387 +0.280924,1903,1642.356457 +0.280799,1958,1656.199961 +-0.101708,2510,1661.044022 +0.186714,1657,1664.481668 +-0.327,953,1666.387907 +0.256453,2569,1681.618977 +0.079139,836,1682.910543 +0.033737,2056,1686.377845 +-0.030406,1582,1689.239351 +0.07387,1289,1691.555386 +0.587231,1399,1694.050566 +0.001229,1131,1706.178 +0.434494,1929,1710.053185 +-0.034531,1208,1712.714838 +0.12865,1486,1715.928693 +0.078322,1380,1718.846731 +-0.142121,729,1720.433371 +-0.151677,1170,1733.046053 +-0.06806,1060,1734.614807 +0.385413,2844,1739.537926 +-0.100133,1552,1742.342462 +0.326495,1607,1745.146732 +0.302153,2239,1758.789045 +0.522401,1757,1761.803304 +0.166711,2856,1767.304286 +0.428716,2172,1771.677312 +-0.019623,1521,1784.479616 +0.260527,1966,1788.217453 +-0.119121,1074,1790.315712 +0.418528,2234,1794.520691 +0.517865,1263,1796.808059 +0.423456,1497,1809.422982 +-0.06006,1405,1811.81329 +0.160043,866,1813.366522 +0.585228,924,1815.029728 +0.277799,2779,1820.015805 +0.337404,2235,1834.103305 +0.46081,1937,1838.122495 +0.377994,2708,1843.626238 +-0.116719,1698,1847.148929 +0.045971,1155,1859.23671 +0.104344,1827,1862.143899 +-0.022295,680,1863.353439 +0.545887,1638,1866.3297 +0.185701,1653,1869.275571 +0.11265,1485,1872.003617 +0.484004,2242,1886.079721 +0.625981,1087,1888.322062 +0.279453,1843,1892.071028 +0.443652,1677,1895.357448 +0.344567,3572,1911.828596 +-0.256113,1043,1913.722027 +-0.071118,1227,1915.95661 +0.354908,2706,1920.812183 +0.240661,1316,1933.252254 +0.411623,2295,1936.724112 +-0.128337,1163,1938.761327 +0.282734,1626,1941.709326 +0.141057,2562,1947.12301 +0.190014,1767,1960.872575 +0.007855,1911,1964.506522 +0.523547,1537,1967.58492 +-0.083675,1705,1971.174932 +-0.204133,1771,1974.646778 +-0.351,1054,1986.497205 +-0.031337,2010,1989.983832 +0.719901,892,1991.616587 +0.234783,2343,1995.864636 +0.008594,1236,1998.122689 +0.130807,1746,2011.670501 +0.032887,2675,2017.085942 +-0.085274,1028,2019.367159 +0.53739,1572,2022.83379 +0.101344,1813,2026.051991 +0.609131,1609,2039.102567 +-0.315,1027,2040.921465 +0.228589,1624,2043.744258 +-0.067913,961,2045.419406 +0.344908,1684,2048.49276 +0.201322,2302,2062.915653 +0.003402,1394,2065.74916 +0.086302,886,2067.628501 +-0.084118,1766,2071.222687 +0.31345,1469,2074.389017 +0.671012,985,2076.589793 +0.121138,1758,2090.152525 +0.42729,1955,2093.724972 +-0.305704,951,2095.45047 +0.187014,1318,2097.778453 +0.150272,1525,2100.503914 +0.446624,1806,2113.71487 +0.446157,1993,2116.77129 +0.004139,1072,2118.667526 +0.49025,1886,2122.153946 +0.598946,1542,2125.144452 +0.063971,1398,2138.020052 +0.330661,1778,2140.932757 +0.558311,1768,2144.421883 +0.069971,2188,2148.617844 +-0.148979,1788,2151.95126 +0.589794,981,2163.773309 +-0.016337,1376,2165.83596 +-0.045298,1108,2167.725242 +0.362,2007,2171.246443 +-0.173791,1680,2174.165155 +0.028881,1445,2176.698017 +-0.082913,3017,2192.476497 +0.345876,1844,2196.53253 +0.376806,3192,2203.095655 +0.293924,1855,2216.368481 +0.327699,3420,2222.261474 +-0.075307,2010,2225.809767 +0.233589,1539,2238.681336 +0.426096,1922,2241.848257 +0.129238,1234,2244.127803 +0.414922,2213,2248.036653 +-0.023406,1240,2250.408203 +0.385072,2019,2264.503533 +0.526612,1596,2267.373233 +-0.014623,2459,2271.999529 +0.311042,2257,2276.050834 +0.561781,1847,2289.217858 +0.262527,2794,2293.786923 +0.06087,1519,2296.479167 +0.504211,1565,2299.294601 +-0.16335,1103,2301.262299 +-0.011771,956,2313.200801 +-0.156979,1365,2315.79994 +0.213059,1674,2319.165963 +0.342843,2181,2323.744536 +0.395166,2554,2339.300573 +0.323621,1817,2342.085472 +0.265308,2035,2345.730402 +0.162701,1656,2348.623318 +0.449228,2680,2363.403447 +0.35458,1538,2366.069551 +0.385283,2985,2372.093914 +-0.11133,1356,2374.94153 +0.344876,1280,2377.623858 +0.123368,1562,2391.239372 +-0.093861,856,2392.580549 +-0.026345,1206,2394.589562 +0.126519,2712,2399.423821 +0.311404,1872,2402.714003 +0.674096,1223,2415.077911 +0.249432,1166,2416.885843 +0.334699,2050,2420.401709 +0.048971,2029,2424.055109 +-0.123489,1358,2426.732783 +0.110344,1864,2440.750642 +0.602264,994,2442.468789 +0.31145,1680,2445.431804 +-0.079675,1074,2447.502147 +0.321621,1774,2450.841537 +0.018518,2750,2466.283256 +0.518064,1364,2468.394793 +0.300308,1773,2471.59765 +0.549016,1771,2474.749989 +0.386879,2832,2490.343248 +0.230589,2449,2494.661968 +-0.346,798,2496.259646 +0.349908,2988,2502.155276 +-0.204288,874,2503.919753 +0.149711,1235,2516.824644 +-0.343,588,2517.710077 +-0.005771,918,2519.245964 +0.165043,2482,2523.789843 +0.073959,971,2525.358779 +0.35345,1833,2528.81362 +0.144519,1530,2541.740274 +0.454994,2708,2546.725961 +-0.05985,2143,2550.940264 +-0.339,776,2552.449121 +-0.231113,1405,2555.207192 +0.139043,1285,2567.930768 +0.51738,1466,2570.779982 +-0.210923,1239,2572.927544 +0.554547,1537,2575.539801 +0.495146,1720,2578.386769 +0.324495,1405,2580.783971 +0.299984,2199,2594.455703 +0.311042,1998,2597.732284 +0.190866,3325,2603.475126 +-0.017771,1642,2616.58541 +0.25522,980,2618.160689 +0.326538,2050,2621.792263 +0.115519,1448,2624.659331 +0.027136,2506,2629.057435 +0.256589,2110,2642.698715 +0.288863,1768,2645.827699 +0.592461,1505,2648.521291 +0.096703,1954,2651.966565 +0.312206,1422,2664.625984 +0.309308,2112,2668.500269 +-0.085675,1633,2671.749722 +0.264453,1728,2675.335461 +-0.289322,1495,2678.445879 +-0.119,1492,2691.509205 +0.173322,1290,2693.488836 +0.333773,2938,2698.521325 +-0.16635,1093,2700.477738 +0.442957,2046,2704.091802 +0.194014,1869,2717.285679 +0.558491,1442,2719.698094 +0.593133,1204,2721.865341 +0.335404,1826,2725.737214 +0.406751,2915,2741.880271 +-0.351,1027,2743.653612 +0.172701,1639,2747.037151 +0.016881,1686,2750.604649 +0.199297,1417,2753.349496 +0.44047,2014,2767.527768 +0.301378,1227,2769.379543 +0.538204,1097,2771.334439 +-0.034337,2993,2776.785366 +0.461815,1804,2779.983258 +0.480743,2246,2794.56974 +0.327699,2018,2798.469186 +0.266688,3313,2805.094635 +0.028136,1629,2819.115683 +-0.117,1204,2821.025994 +0.554894,1337,2823.412227 +0.518712,1264,2825.716955 +0.43997,2599,2830.377576 +-0.141159,1521,2833.096709 +0.245688,1232,2845.839997 +0.11665,1766,2848.985284 +0.269667,2386,2853.329457 +0.496591,2000,2856.865831 +0.030225,1274,2869.77051 +0.333661,2577,2873.825197 +0.097703,1877,2877.263138 +0.159515,1357,2879.722015 +0.023136,2201,2894.295985 +0.234876,1356,2896.386444 +0.350876,2596,2900.997768 +-0.226113,1288,2903.428473 +0.156921,1307,2905.972358 +0.359876,1673,2919.646978 +0.556401,1670,2922.63608 +0.418368,1522,2925.8081 +0.046887,955,2927.783651 +0.198432,2829,2933.34941 +-0.10733,1057,2945.771723 +0.00855,843,2947.06393 +0.239783,1467,2949.53713 +0.212053,972,2951.27236 +0.103344,1780,2954.428923 +0.005139,1212,2956.53546 +0.638759,971,2958.256633 +0.55437,1178,2970.50473 +0.175059,2365,2974.496685 +0.614099,1445,2976.944443 +0.458237,1932,2980.286818 +0.31445,1873,2984.08166 +0.015881,1782,2997.032735 +-0.04685,1223,2999.028894 +0.444093,3182,3004.723579 +0.088023,832,3006.204974 +0.026402,1599,3019.097346 +0.127314,2018,3022.100507 +0.162711,1223,3024.505361 +0.088023,2978,3030.639644 +0.123519,1697,3034.164786 +0.043518,1805,3047.617391 +0.358094,2459,3052.560912 +0.420136,1910,3056.05119 +-0.041345,1963,3059.419827 +0.53904,1601,3073.118302 +0.430422,2066,3076.685719 +0.011229,589,3077.746171 +0.399891,2034,3081.523004 +0.037887,2010,3085.300681 +0.485244,1608,3098.770297 +0.145272,1757,3102.212645 +0.00755,925,3103.996978 +0.420624,2361,3108.827554 +0.146495,1154,3111.246821 +0.598089,1508,3123.897512 +-0.080675,1943,3127.086717 +0.102883,1732,3130.148192 +0.318538,2591,3134.779728 +0.582485,843,3136.297686 +0.053344,2244,3150.577753 +0.00755,924,3152.349729 +-0.157677,763,3153.806087 +0.423408,2120,3158.167295 +0.25222,2693,3173.302648 +0.431179,1710,3176.097391 +0.201714,1650,3179.040316 +0.372333,3489,3185.168276 +0.071139,1579,3198.205351 +0.443574,1579,3200.783503 +0.419858,2229,3205.227598 +0.204014,1149,3207.493357 +0.542083,2405,3212.331338 +-0.023502,1354,3225.084554 +0.181557,1119,3227.239697 +0.487607,2694,3232.797788 +0.450674,1816,3236.006609 +0.342808,2554,3250.397506 +0.289598,1539,3252.894104 +0.047994,2632,3257.519733 +0.118238,1883,3260.860341 +0.219167,2021,3274.654415 +0.322538,1819,3278.298883 +-0.115312,837,3280.093309 +0.015855,2771,3286.160651 +0.180557,1536,3289.494348 +0.246138,1107,3301.393602 +-0.069913,2329,3305.434199 +0.511254,1267,3307.743342 +0.220384,1862,3311.031099 +0.429357,2107,3324.964787 +0.047994,1854,3328.286734 +-0.325,983,3330.278497 +0.1633,1037,3332.369675 +-0.14144,1323,3334.980964 +0.536481,1292,3337.623722 +0.428707,2811,3352.592231 +-0.15335,1155,3354.517582 +0.192059,1685,3357.538119 +0.418784,2690,3362.327307 +0.027643,1076,3364.239087 +0.328699,1523,3376.691196 +0.230488,1170,3378.59568 +0.412613,6653,3401.701221 +0.075538,2247,3406.280903 +0.303357,1470,3409.364725 +0.124238,1341,3412.090083 +0.202297,1086,3414.044569 +0.443484,2250,3428.357185 +0.241866,1398,3430.635945 +-0.015771,974,3432.441625 +-0.002762,2961,3437.897976 +0.014881,1924,3451.468931 +-0.128489,1158,3453.557917 +0.185921,1519,3456.684968 +0.088668,2552,3461.873984 +-0.291704,1366,3464.744207 +-0.346,715,3466.138297 +0.077971,2575,3480.903273 +0.615734,1238,3483.133842 +0.265876,2056,3486.784507 +-0.145111,1006,3488.549701 +0.228453,1138,3490.620362 +0.395243,2513,3505.536063 +0.124314,906,3507.386506 +0.503555,1940,3511.591748 +0.397136,1910,3515.540182 +0.322116,2905,3531.240425 +0.059421,1553,3534.0352 +0.07687,1777,3537.234268 +-0.139677,1360,3539.706557 +-0.351,634,3540.856447 +0.400419,2870,3555.382201 +-0.054531,1242,3557.406936 +0.181714,1762,3560.596427 +0.520888,2184,3564.809576 +0.287863,1589,3567.976794 +0.411679,1795,3581.310363 +0.461182,2137,3585.133143 +0.348808,2567,3589.888143 +-0.102708,1732,3593.040859 +0.06449,931,3605.446166 +-0.006357,1516,3608.084385 +0.466181,1335,3610.531368 +0.437679,2524,3615.141456 +0.16923,1820,3618.519041 +0.31745,1600,3631.98568 +0.120238,2833,3637.529701 +0.58188,1526,3640.425426 +0.627168,905,3642.304157 +0.332773,2659,3657.574463 +0.241053,2132,3661.177543 +0.194308,2289,3665.183023 +0.343876,1963,3668.675365 +0.394036,1781,3681.667229 +0.197564,1674,3684.781171 +0.340843,1974,3688.745667 +0.178322,1037,3690.793039 +0.120519,1485,3693.861755 +0.296258,2964,3709.354905 +0.219053,3083,3715.20176 +0.129314,1503,3717.920407 +0.247384,1194,3720.062287 +0.282984,2015,3733.310145 +-0.271416,1397,3735.75352 +0.007855,1055,3737.642923 +0.249053,1523,3740.365684 +0.216167,1441,3743.189146 +0.488965,1878,3757.341944 +-0.120307,1297,3760.038365 +-0.305704,1048,3762.26034 +0.32345,2565,3767.828368 +0.017377,2044,3772.200619 +0.592762,1066,3784.176366 +0.139043,1659,3786.692372 +0.080484,1244,3788.869951 +0.057421,2383,3792.986466 +0.144711,1490,3795.552131 +0.260378,2677,3810.680256 +0.449758,1676,3814.016233 +0.244053,3768,3821.702024 +0.453546,1976,3835.926695 +0.082926,1318,3838.175236 +0.397191,3250,3843.929012 +0.2543,2545,3848.477242 +0.395341,1581,3861.434993 +0.096703,1522,3864.427095 +0.229488,3029,3870.174987 +-0.258311,1419,3872.814797 +0.050994,1356,3885.557415 +0.275404,2598,3890.912425 +0.26522,1341,3893.420756 +0.329661,3431,3899.484797 +-0.142121,857,3911.621974 +0.216053,1306,3913.651248 +0.413124,1468,3916.222517 +0.379908,1835,3919.566852 +0.538565,1562,3922.346249 +0.31245,2099,3937.120746 +-0.023337,1496,3939.618645 +-0.160979,1285,3942.013447 +0.252053,1322,3944.458127 +0.463252,1467,3947.219932 +0.559847,1303,3949.556774 +0.370843,2447,3964.171834 +-0.077119,840,3965.687034 +0.547061,1322,3968.151467 +0.287984,2781,3973.207351 +0.426329,1564,3986.831929 +0.351908,2204,3991.042756 +0.296734,2255,3995.832325 +0.515986,2461,4000.899323 +-0.015623,1433,4013.432708 +0.57494,1199,4015.296159 +0.109948,2506,4019.679604 +0.711427,756,4020.907788 +0.215053,2193,4024.61404 +0.079887,1133,4026.527553 +-0.073274,642,4037.709735 +0.206564,1619,4040.26093 +0.123057,1891,4043.806616 +0.477957,1493,4046.59718 +0.455727,2062,4050.583661 +0.38646,2434,4065.214826 +0.120519,1613,4068.128651 +0.265667,2346,4072.446939 +0.347908,1684,4075.635914 +0.195297,1730,4089.03788 +0.063519,2341,4093.206476 +-0.35,968,4095.06289 +0.006229,1436,4097.561573 +0.270527,2008,4101.133155 +0.127564,2054,4115.499609 +0.280984,2398,4120.495973 +0.533023,1461,4123.658516 +0.2583,2976,4140.611064 +0.261378,1907,4143.764421 +-0.192892,1773,4146.647187 +0.077538,1418,4149.010275 +0.338808,1423,4151.513877 +-0.167979,1305,4164.436902 +-0.054274,1467,4166.992661 +0.288098,1694,4170.031768 +-0.083913,2607,4174.725516 +0.38497,1436,4177.222701 +0.457507,1571,4190.381765 +0.171322,1295,4192.603075 +0.266598,2644,4197.380269 +-0.092675,1669,4200.35753 +0.484512,1736,4203.487614 +0.518927,1454,4216.107152 +-0.346,1013,4217.864686 +0.153322,2624,4222.66226 +0.318404,2260,4227.191908 +-0.088274,1255,4239.325507 +0.391407,3630,4246.384824 +0.160701,1375,4249.088653 +0.49839,2015,4253.036724 +0.531306,1539,4265.830832 +0.714007,779,4267.012068 +-0.120719,1381,4269.449985 +0.49081,1937,4272.968551 +0.494156,1557,4275.775202 +0.107948,1057,4277.676138 +0.31858,3105,4293.47657 +-0.030406,1732,4296.632987 +-0.305704,609,4297.66792 +0.311917,2500,4301.97754 +0.332661,1373,4315.395096 +0.611971,1712,4318.025201 +0.336808,1983,4321.451942 +0.117028,2548,4325.99611 +0.096368,2239,4340.759369 +0.195432,1477,4343.226582 +-0.34,976,4345.27853 +0.006862,1011,4347.490334 +0.484069,2241,4351.994669 +0.191014,1180,4354.381337 +0.039518,872,4366.604358 +0.2573,2726,4371.964284 +0.289984,1448,4374.586446 +0.287924,1966,4378.139769 +0.146921,1371,4380.569952 +0.369162,2775,4395.149874 +-0.017502,1565,4397.915225 +0.278734,1732,4401.043009 +0.574871,1387,4403.693187 +0.01155,773,4405.269862 +0.42984,2833,4420.750005 +0.068305,1456,4423.543226 +0.554372,1661,4426.955329 +0.323621,2985,4443.015009 +0.03532,1419,4445.112666 +0.31958,3348,4451.050633 +0.298258,2514,4455.478846 +0.644101,1268,4467.555605 +0.119238,1629,4470.53871 +-0.223029,1203,4473.057653 +0.044437,2052,4477.377669 +0.336773,1246,4479.960291 +0.217167,2648,4494.645586 +0.127564,1766,4497.580592 +0.291098,1750,4500.605548 +0.432393,2348,4504.744511 +0.518515,1529,4517.710911 +0.008855,1586,4520.169405 +0.318308,1854,4523.737699 +0.276863,3864,4531.821831 +0.345498,2297,4546.224688 +-0.10033,1146,4548.589459 +-0.16444,1677,4552.133506 +0.517697,1117,4554.183811 +0.333773,2895,4569.470328 +-0.018623,1807,4572.221904 +0.089538,1092,4574.148315 +0.562379,1286,4576.427659 +0.11865,2730,4581.275724 +0.266378,2207,4595.9391 +0.513273,1573,4599.179106 +0.459213,2368,4604.073374 +0.145495,1917,4608.213484 +-0.101708,1200,4619.492355 +0.230357,2254,4623.094901 +0.206157,1056,4624.983539 +0.368148,3544,4631.313379 +0.29158,1976,4644.790927 +0.193297,2129,4648.61295 +0.577004,1761,4651.991928 +0.084926,1745,4655.07078 +0.433509,2313,4669.417703 +0.338808,2347,4673.260444 +0.523865,1868,4676.521547 +-0.34,1171,4678.572252 +0.211564,1482,4681.186594 +0.345666,1622,4694.384964 +0.188014,1528,4696.894012 +0.384355,3074,4702.351996 +0.284042,1488,4705.144606 +0.339661,1789,4717.174365 +0.181059,2543,4721.874423 +0.329788,1961,4725.942109 +0.302924,2138,4730.215126 +0.462,2197,4744.351657 +0.577103,1516,4746.757353 +0.183557,1704,4749.771902 +-0.061307,1077,4751.67638 +-0.033295,1473,4754.294526 +-0.040531,1129,4756.279705 +0.439353,2332,4769.352796 +0.147921,1204,4771.428102 +0.231688,1641,4774.344765 +0.573159,1086,4776.254653 +0.245965,1776,4779.335071 +0.259453,2062,4792.282692 +0.574735,1277,4794.451838 +0.460146,1720,4797.451733 +0.018225,1347,4799.814037 +-0.352,1063,4801.696535 +0.071728,2411,4815.774208 +0.35794,1783,4818.763068 +0.435183,2681,4823.714797 +0.038737,1064,4825.973247 +0.269783,1217,4828.588959 +0.403717,2466,4843.528282 +0.217167,2539,4848.572614 +-0.125489,741,4850.165821 +-0.006502,1101,4852.390916 +0.401647,2173,4866.641586 +0.17023,2449,4870.889034 +-0.178791,1014,4872.771907 +0.388409,2769,4877.719404 +0.266053,1593,4889.022253 +0.184866,2768,4894.111789 +0.038737,1784,4897.808517 +0.244138,1685,4901.326184 +0.392722,4037,4916.912364 +-0.069307,1273,4919.252524 +0.31245,1020,4921.065582 +-0.087274,1313,4923.40004 +0.34794,2115,4935.910914 +0.066437,1394,4938.026082 +0.064421,1450,4940.541564 +-0.092118,1839,4944.017459 +0.459017,1610,4947.204214 +0.232488,2449,4962.271618 +0.014225,1686,4965.330042 +0.282598,2067,4969.392696 +0.366918,2733,4974.560895 +0.348266,2238,4988.765178 +0.621858,1518,4991.350373 +-0.293,652,4992.504137 +0.564321,1341,4994.867596 +0.098703,1685,4997.851759 +0.38394,1384,5000.321062 +0.088668,2089,5012.233753 +0.149965,1736,5015.243485 +0.267667,2661,5020.0047 +-0.079591,1352,5022.377927 +0.305308,1508,5034.659078 +0.459473,2330,5038.487221 +-0.015482,1653,5041.402164 +0.289734,2172,5045.245586 +0.393457,2869,5060.509645 +0.377852,3090,5066.091547 +-0.007357,1909,5069.683319 +0.469116,2752,5084.253348 +-0.204126,1583,5087.342705 +0.401584,1488,5090.19998 +0.140495,2075,5093.963196 +0.144238,1871,5097.234549 +0.561832,1231,5109.532004 +0.533897,1647,5112.328274 +0.604206,1321,5114.7007 +-0.007771,1054,5116.569934 +0.329699,2153,5120.377327 +0.059737,1600,5132.353727 +0.04649,1655,5134.870817 +0.162883,1628,5137.711502 +0.479483,1688,5140.645602 +0.458273,1573,5143.399826 +0.31245,3122,5156.887451 +-0.338,1166,5158.930248 +0.282378,1943,5162.355516 +0.466372,1966,5165.810489 +0.107028,1638,5178.399437 +0.547949,1269,5180.487773 +0.068728,1534,5183.50508 +0.063421,1975,5187.839742 +0.325661,2441,5192.996066 +0.331,1698,5205.999404 +0.681492,998,5208.108148 +0.456585,1504,5211.40914 +0.375615,3522,5217.903103 +-0.230489,1088,5229.379755 +0.525147,1407,5231.640963 +0.147921,2499,5236.113914 +0.111948,1726,5239.326159 +0.299843,1876,5242.929714 +0.576438,1679,5256.290934 +0.681794,1128,5258.48149 +0.186014,2043,5262.69497 +0.680673,1061,5264.712597 +-0.103133,1397,5267.427774 +0.552955,1006,5269.521294 +0.242053,1838,5282.064671 +0.164883,1530,5284.744186 +-0.166979,1004,5286.540367 +0.453605,2506,5290.978835 +0.107948,2115,5304.166853 +0.018881,2111,5308.274678 +-0.042282,1062,5310.424582 +-0.074307,2282,5314.856733 +-0.347,1269,5317.382905 +-0.088675,1247,5327.999151 +0.5005,1861,5331.400772 +0.026136,792,5332.880433 +0.156495,2145,5336.758297 +-0.096111,764,5338.10648 +0.228488,1351,5340.53004 +0.220936,2406,5353.391245 +0.309308,1823,5356.631445 +0.289042,1869,5359.970147 +0.156515,1937,5363.448688 +0.431613,1838,5375.065204 +-0.343,1303,5377.17247 +-0.071675,1799,5380.388104 +-0.071591,1308,5382.701322 +-0.053674,1054,5384.566694 +0.271734,2313,5397.068552 +0.119714,1606,5399.562567 +0.561251,1137,5401.559482 +0.190557,2167,5405.369481 +0.06987,2199,5409.237328 +0.221816,1017,5420.493035 +0.193297,1826,5423.602174 +0.272527,2036,5427.545245 +0.315042,1454,5430.471569 +0.339737,2462,5435.58556 +0.506204,1097,5447.464615 +0.2503,1372,5450.003095 +0.287042,3010,5455.572614 +-0.075138,1218,5457.701756 +0.578726,1039,5459.546917 +0.540965,1845,5471.02935 +0.148711,1641,5473.806719 +0.445471,1606,5476.666393 +0.36997,2321,5480.828865 +0.276799,2816,5494.335584 +-0.091118,1621,5497.126024 +-0.065307,1339,5499.468426 +0.06287,2659,5504.167647 +-0.230113,1047,5506.007979 +0.350908,3630,5521.286579 +-0.141111,1028,5523.085752 +0.595517,1084,5524.998905 +-0.276452,1554,5527.733416 +0.36794,2040,5539.426089 +0.144711,2260,5543.490969 +0.24722,1645,5547.033273 +0.445805,2375,5552.120684 +-0.352,1442,5563.382871 +0.166059,1813,5566.944431 +-0.079913,1425,5570.03862 +0.24558,1140,5572.425459 +0.332,2559,5577.205451 +-0.030674,957,5588.49499 +0.265384,1293,5590.55944 +0.284984,2823,5595.584345 +0.340737,2056,5599.368881 +0.35097,2729,5614.634789 +0.553955,1693,5617.957062 +0.385755,3470,5625.039283 +-0.352,1987,5628.948931 +0.451061,1322,5639.748078 +-0.115489,1329,5641.932741 +-0.188892,889,5643.5241 +0.382776,3125,5649.045943 +-0.024406,995,5650.803131 +0.268453,1338,5660.513128 +0.476232,2334,5664.550374 +0.166515,2172,5668.872092 +0.338843,1502,5671.816281 +0.617668,1418,5674.725692 +0.446344,2700,5686.755045 +-0.352,1051,5688.955713 +0.476551,1632,5692.312028 +0.184808,2693,5697.168406 +0.770879,878,5706.97525 +0.515227,1864,5709.942855 +-0.007406,1139,5711.961675 +0.225167,1231,5714.170429 +0.550607,1765,5717.318918 +0.223053,1847,5728.98117 +0.040437,1801,5731.900561 +0.506897,1647,5734.812639 +-0.174979,2293,5738.839533 +-0.302704,1197,5740.973668 +0.441301,1748,5753.807257 +0.315357,2186,5757.386476 +0.017881,1334,5759.744002 +0.262598,2357,5763.883091 +-0.137121,1030,5765.691533 +0.664369,839,5776.904888 +0.815836,697,5777.964326 +0.2573,1529,5780.426506 +0.569569,1141,5782.546003 +0.392399,2611,5787.588568 +0.341737,1942,5801.414761 +-0.114312,1218,5803.611826 +-0.196892,679,5804.951482 +0.35197,2592,5810.111129 +0.61209,1092,5812.182504 +0.46431,2016,5815.700436 +-0.025406,1342,5825.199494 +0.216167,1445,5827.543425 +0.352751,2342,5831.649974 +0.398663,2467,5836.02834 +0.41213,2440,5850.244528 +0.448949,2008,5853.685133 +0.06087,1636,5856.507263 +0.144711,2005,5859.969546 +0.12365,1709,5871.207072 +0.107028,2294,5874.918445 +0.094538,1065,5876.803103 +0.135043,2152,5880.581838 +-0.140133,1631,5883.451867 +0.285984,1918,5893.959902 +0.324621,2978,5899.092842 +-0.14435,621,5900.184016 +0.268667,2247,5904.560549 +0.561331,1625,5918.391512 +0.36397,2426,5923.540213 +0.151948,2036,5927.88639 +0.243488,1914,5932.122768 +-0.026298,1683,5945.285044 +0.535923,1576,5948.011166 +0.280863,2920,5953.39467 +-0.338,1177,5955.475512 +0.059959,1338,5957.859462 +0.059959,2540,5971.090229 +0.206297,1719,5974.51493 +0.048994,1393,5977.476973 +0.62508,1138,5979.935469 +0.434856,2445,5993.650002 +-0.05806,1952,5996.727158 +0.513422,1383,5999.184758 +0.521614,2090,6002.881242 +0.304357,1559,6005.682428 +0.349,2261,6018.032757 +-0.239557,1130,6020.020205 +0.121057,1588,6022.987099 +0.039887,2340,6027.854963 +0.10665,2593,6041.855981 +0.335495,2435,6046.538609 +0.354056,2211,6051.052491 +0.331737,2801,6064.571059 +-0.062913,1566,6066.93821 +0.4381,1750,6070.057516 +0.307098,1731,6073.148724 +0.103368,998,6074.947307 +0.48331,2401,6088.265462 +0.056484,1124,6090.072394 +0.228734,1433,6092.624084 +0.254378,3018,6098.03242 +-0.011771,1411,6100.554129 +0.079538,1334,6111.650276 +0.230936,2313,6115.525668 +0.077396,3088,6120.898147 +-0.094118,1400,6123.357377 +0.380876,1234,6135.218689 +0.2563,1612,6137.670399 +0.136807,1018,6139.478037 +0.355,1888,6142.898259 +0.001402,1410,6145.603923 +0.217277,1500,6148.606701 +0.107344,1894,6160.6239 +0.546504,1872,6164.474691 +0.384817,2541,6169.676749 +0.623937,1224,6172.150446 +0.459135,1981,6183.453457 +-0.023502,2003,6186.778843 +-0.349,944,6188.448983 +0.276378,1908,6191.839935 +0.213936,1265,6194.09234 +0.354843,2125,6206.641749 +-0.345,910,6207.995272 +0.335808,1975,6211.444905 +-0.011138,1712,6214.444348 +0.268527,1659,6217.350007 +0.381981,1935,6229.274232 +0.00755,1245,6231.263516 +0.357908,2486,6235.57687 +0.800292,607,6236.637045 +-0.240159,680,6237.83282 +0.020518,1836,6241.061044 +0.354661,1368,6250.627343 +-0.124489,1359,6252.786581 +-0.005563,1003,6254.534726 +0.388908,1578,6257.320213 +0.562971,1712,6260.322883 +-0.126489,927,6262.040829 +0.361908,1361,6272.410426 +0.341,2637,6277.913105 +0.02932,3020,6284.385326 +-0.088274,1475,6287.601372 +0.210432,1344,6298.613386 +-0.143121,2677,6303.505003 +0.03032,1032,6305.355768 +0.34794,2691,6310.412497 +-0.234288,1146,6320.613801 +0.117948,1518,6323.090142 +0.380922,5632,6334.667171 +0.254053,3183,6350.637298 +-0.351,847,6352.35003 +0.426452,1829,6355.634529 +0.025737,2006,6359.175629 +-0.174979,1234,6370.057668 +0.596005,901,6371.396053 +0.187714,2618,6375.860892 +0.705763,1007,6377.66005 +0.060421,2542,6382.247993 +-0.039298,1338,6393.414657 +0.076421,844,6394.902855 +0.356978,3186,6401.168182 +-0.044422,916,6402.934534 +0.712665,755,6404.422778 +0.627147,1407,6407.150984 +0.559147,1407,6418.238197 +-0.005138,1531,6420.689427 +-0.288704,1567,6423.476016 +0.596909,1139,6425.502312 +0.135792,1635,6428.440646 +0.182272,1795,6441.304642 +0.118519,1810,6444.139367 +0.228488,1748,6447.26205 +-0.152159,2010,6450.861468 +0.512485,1361,6453.282278 +0.116014,1816,6464.549895 +0.366773,1932,6467.66128 +0.247138,2265,6471.657797 +-0.114,1701,6474.645837 +0.219384,1490,6485.213444 +0.269598,3597,6491.036559 +-0.338,765,6492.392044 +0.389487,1797,6495.569369 +0.071139,1704,6498.605778 +0.363808,1363,6509.834892 +0.46019,2209,6514.217419 +0.198297,2217,6518.660847 +0.272734,1458,6521.613402 +0.001643,1015,6523.651886 +0.568957,1493,6534.577386 +-0.337,1354,6536.863307 +0.501732,1826,6540.1307 +0.218432,1931,6543.553186 +0.456712,1264,6545.802535 +0.119302,2229,6556.925388 +0.095484,1061,6558.754535 +0.233432,1237,6560.966398 +0.450716,2543,6565.4594 +0.652338,1085,6567.369732 +0.337737,1980,6578.196645 +0.06687,1381,6580.568659 +0.40817,2534,6584.998724 +0.094538,1551,6587.697395 +0.06087,1513,6597.733136 +0.04432,2196,6601.209486 +0.350843,1303,6603.512593 +0.019225,1789,6606.676736 +0.000402,1032,6608.499131 +0.207936,1741,6620.777417 +0.483836,1902,6623.874829 +0.505013,1683,6627.349088 +0.296258,2261,6632.02513 +0.025136,1320,6634.762475 +0.49074,2761,6648.679099 +0.202297,1934,6652.563253 +0.640726,1039,6654.611301 +0.286984,2217,6658.979798 +0.209564,977,6660.856167 +-0.083,1769,6673.042912 +0.152314,1526,6675.689763 +0.425657,1123,6677.835921 +0.519198,2270,6682.073246 +0.129564,2169,6693.787507 +0.520201,1749,6697.092691 +0.227384,1199,6699.664034 +0.385043,2640,6705.017179 +0.333773,3279,6719.604632 +0.175404,1156,6721.517793 +0.474615,1916,6724.898614 +0.280984,1329,6727.275743 +0.502231,1399,6729.754195 +-0.16835,1021,6731.563595 +0.602529,1285,6741.63754 +0.596897,1351,6744.128868 +0.237876,1587,6747.392246 +0.427355,2655,6752.728917 +-0.12344,826,6754.261457 +0.331737,2547,6767.449071 +-0.162979,1219,6769.937567 +-0.321,533,6771.066935 +0.000139,1753,6774.364775 +0.324624,2159,6778.245504 +0.327924,2228,6789.630458 +-0.013942,1502,6792.284771 +0.003862,992,6794.059916 +0.426676,2670,6798.812255 +0.022136,1240,6801.002483 +0.120792,1949,6812.948023 +0.595731,1219,6815.10654 +0.139344,1928,6818.496139 +0.221384,2479,6822.868837 +0.237876,1453,6834.031494 +0.044437,1028,6835.584743 +0.492478,1259,6837.794888 +0.149711,1948,6841.236649 +0.04449,1230,6843.402107 +0.559361,1160,6845.467265 +0.644793,931,6847.11182 +0.260453,2471,6859.122791 +0.331699,2250,6863.154297 +0.360737,2034,6867.069803 +0.087668,2901,6880.141649 +0.449751,1926,6883.935927 +0.256589,1163,6886.114214 +0.528213,1507,6889.100909 +-0.096133,905,6890.8624 +0.46168,3519,6906.324951 +-0.047345,1656,6909.249183 +0.333773,1522,6911.964724 +0.519264,1662,6914.897093 +-0.002771,2313,6924.999158 +0.346808,1187,6926.797394 +0.542528,1171,6928.843764 +0.159124,2086,6932.430343 +0.118538,1247,6934.596071 +0.438706,1544,6944.615683 +-0.004357,1211,6946.389284 +0.369908,1313,6948.543084 +0.016862,1880,6951.832058 +-0.055674,1115,6953.792286 +0.163701,1480,6956.405749 +0.443193,2876,6970.217024 +0.165322,1953,6973.636559 +0.60936,1443,6976.187794 +0.017377,1136,6978.199566 +0.526545,1828,6987.689406 +-0.268311,1202,6989.810658 +0.358737,2151,6993.789759 +-0.038282,1338,6996.580963 +0.265378,1362,6999.562317 +0.156515,1997,7003.534036 +0.093792,1225,7014.237441 +0.547398,1142,7016.244937 +0.331699,1628,7019.212252 +-0.043345,2119,7023.030178 +0.120277,1108,7025.070471 +0.052484,1557,7036.492245 +0.633159,1086,7038.178464 +0.099028,2098,7042.058818 +0.059959,931,7043.979286 +0.423622,1963,7048.082655 +0.173396,1318,7050.748327 +-0.075913,2756,7063.2837 +0.084926,1500,7065.793396 +0.205564,1304,7068.271248 +0.620143,1301,7070.930889 +0.421352,1320,7073.39726 +0.333699,2561,7085.880557 +0.49791,1534,7088.596009 +0.324308,2913,7093.671641 +-0.155979,1027,7095.484269 +0.094538,1052,7105.88198 +0.131564,1535,7108.575342 +0.306357,1566,7111.613508 +0.333,1913,7115.60619 +-0.112111,1115,7117.886056 +-0.002357,947,7119.820412 +-0.001357,2397,7132.457483 +0.147921,2355,7136.690277 +0.349773,1626,7139.611022 +0.369869,1551,7142.396141 +0.411082,4011,7156.12724 +-0.022406,2045,7159.780309 +0.181557,1272,7162.048722 +0.092023,2585,7171.795853 +0.600308,782,7172.994076 +0.194866,2947,7178.197026 +0.019881,1902,7181.543987 +0.32945,1687,7191.129688 +0.490688,1403,7193.229833 +-0.133312,860,7194.678977 +0.224384,1504,7197.334544 +0.610529,1285,7199.599688 +0.003855,1914,7202.931126 +0.163701,1318,7210.590449 +0.625176,1120,7212.267056 +0.32658,2840,7217.075402 +-0.336,527,7218.013662 +0.419613,2248,7222.021529 +0.058421,1250,7233.894068 +0.149711,1582,7236.707806 +0.073728,2036,7240.789187 +0.211816,1334,7243.428157 +0.308404,2005,7247.240264 +0.445549,2013,7258.294855 +0.324661,2762,7262.941391 +0.150711,1393,7265.389817 +-0.233288,1019,7267.189384 +-0.050422,1752,7270.275742 +0.274863,1438,7280.31065 +0.135043,2342,7284.196279 +-0.050531,1082,7286.086689 +-0.038345,729,7287.368852 +0.155807,1102,7289.313344 +0.041971,1368,7291.712614 +0.513465,2092,7303.416231 +-0.049913,1467,7305.963981 +0.348908,2640,7310.525627 +-0.040345,1540,7313.210202 +0.227816,1793,7324.066992 +0.194157,1845,7327.05333 +0.007498,1111,7329.005999 +0.356737,2033,7332.582627 +0.197404,1688,7335.55603 +0.187014,1549,7344.772915 +0.537574,1579,7347.797234 +0.645264,994,7349.690316 +0.098703,1614,7352.974819 +0.370773,2158,7357.491013 +0.481779,2603,7370.110183 +0.039437,1546,7372.995535 +0.173701,1175,7375.167747 +-0.051531,2335,7379.362247 +0.330699,1582,7382.274702 +0.130792,2315,7392.389535 +-0.018502,1487,7395.157013 +0.339621,1630,7398.237583 +0.545607,1765,7401.399233 +0.220936,2191,7413.178224 +0.279924,2109,7417.406596 +0.468029,2007,7421.527184 +-0.004357,1857,7425.353533 +-0.301704,1234,7435.54792 +0.59209,1092,7437.196462 +0.199564,2274,7441.132653 +0.244138,1542,7443.873356 +0.157124,3651,7459.17986 +-0.100133,1334,7461.185028 +-0.002623,1013,7463.022321 +0.280667,1866,7466.771132 +0.330737,1831,7470.533624 +0.280863,2606,7483.349977 +-0.007502,1037,7485.244636 +0.641487,1246,7487.611802 +-0.294704,1380,7490.163149 +0.191297,1567,7493.080536 +-0.220029,1147,7495.140725 +0.214936,1645,7505.03067 +0.522901,2127,7508.560071 +-0.019623,1306,7510.879269 +-0.100603,777,7512.293832 +0.411633,2891,7517.438737 +-0.168677,987,7526.729983 +0.341651,2103,7530.214734 +0.112344,1270,7532.456724 +0.465004,2242,7536.399935 +0.094703,1957,7546.851645 +0.054484,1261,7548.748793 +-0.343,1749,7551.652623 +0.071139,1268,7553.918087 +0.07249,1477,7556.521232 +-0.009771,1496,7559.166676 +0.156124,1797,7572.124595 +0.290495,1898,7575.246228 +0.433956,1856,7578.501643 +0.373904,1611,7581.363549 +0.36957,2312,7594.747508 +0.31445,7805,7617.190256 +0.35694,1995,7620.238398 +0.280984,2522,7624.705847 +0.286863,1744,7627.812766 +0.039971,864,7629.344907 +0.147043,2162,7641.356321 +-0.086312,1101,7643.033901 +0.076994,1602,7645.860751 +0.413018,2598,7650.436273 +0.134043,1555,7653.203942 +0.166059,1817,7664.752404 +0.296598,1808,7667.845779 +-0.051422,2249,7671.710402 +0.044437,1485,7674.297329 +0.30945,2275,7686.378906 +0.172564,1778,7689.341958 +0.242876,1088,7691.270181 +0.394642,2918,7696.422093 +0.13165,1076,7698.32552 +0.012225,1219,7708.342746 +0.322849,3226,7714.945584 +0.120238,1410,7717.728536 +0.201866,1820,7721.408023 +0.17123,1697,7733.182156 +0.564703,1744,7736.114539 +0.228589,3112,7741.942473 +0.150124,1396,7744.535145 +0.453803,2061,7756.664759 +0.020518,596,7757.645964 +0.446598,2025,7761.362458 +-0.201557,1052,7763.403185 +0.180043,1478,7766.296 +0.214014,1557,7769.470257 +0.279453,1443,7780.2297 +0.299984,1491,7783.28638 +0.049994,1097,7785.598807 +0.143043,2126,7789.763713 +0.04949,1484,7792.655095 +-0.293704,1244,7804.464879 +0.153711,1894,7807.549021 +0.60383,1122,7809.532394 +0.523868,1713,7812.56984 +0.019881,1144,7814.579601 +0.088538,1538,7817.322093 +0.342876,2282,7827.74924 +0.19323,2253,7832.266148 +0.366852,3090,7838.472618 +0.437504,2105,7850.022149 +0.279924,6901,7862.176339 +0.153322,2679,7875.448996 +0.244589,1825,7878.684507 +0.150921,1532,7881.392834 +0.346699,1342,7883.780617 +0.259053,2365,7897.139854 +0.492394,1530,7899.699772 +0.027225,950,7901.422047 +0.689338,1085,7903.516388 +0.206936,1346,7906.149257 +0.482072,1888,7917.234696 +-0.098603,1257,7919.348946 +0.295612,2145,7923.078647 +0.230688,2071,7926.670381 +0.463841,1783,7929.795833 +0.221384,2184,7942.076662 +0.272799,1367,7944.626495 +0.490875,1972,7948.097615 +0.134043,1348,7950.777195 +0.589375,1313,7953.68177 +0.579996,1469,7962.632235 +0.146043,1379,7965.209774 +0.12265,1357,7968.068073 +0.342308,1792,7971.898058 +0.316538,3131,7983.944885 +-0.150677,1444,7986.158794 +0.550877,1409,7988.567759 +-0.032295,1665,7991.548761 +0.414878,2307,7995.708487 +0.422274,2350,8008.062042 +-0.018298,1144,8010.088736 +-0.127312,638,8011.364899 +0.486682,2430,8015.998312 +0.502463,1977,8019.886385 +0.337661,1767,8031.221078 +0.026792,1255,8033.509747 +0.357876,2300,8037.97978 +-0.337,1238,8040.582061 +0.207564,1226,8043.251213 +0.401274,2350,8056.315314 +0.653875,1082,8058.081065 +0.499137,2110,8061.8316 +0.166322,1304,8064.613441 +-0.108312,754,8066.22611 +0.499457,1580,8069.56499 +0.581131,1281,8078.614867 +0.453838,2260,8083.223761 +0.511732,1826,8087.077639 +0.364627,2975,8093.194842 +-0.072591,2015,8103.597917 +0.247688,1504,8106.26106 +0.44664,1939,8109.697333 +0.492894,1462,8112.300116 +0.133807,1700,8122.066475 +-0.022674,1352,8124.438131 +0.25222,1450,8127.452214 +0.350843,2395,8132.340122 +0.177396,1863,8136.122112 +0.519616,1668,8147.812651 +0.403318,1863,8151.333838 +-0.136111,5964,8167.438596 +-0.269311,1154,8169.183741 +0.415152,1532,8171.91385 +-0.17835,1662,8174.83352 +0.021855,1135,8176.849742 +0.458504,1872,8180.176968 +-0.010942,1958,8189.40132 +0.210053,1341,8191.868331 +-0.11133,1938,8196.056411 +-0.342,663,8197.524734 +0.581399,1068,8199.882417 +0.378786,1880,8211.810326 +0.192876,2357,8215.502232 +-0.17135,1423,8217.888787 +0.647045,1115,8219.900934 +0.617041,1180,8222.036277 +0.076421,945,8223.789985 +0.561226,1515,8234.118647 +-0.035282,1474,8236.423437 +0.347737,1380,8238.930537 +0.096703,2464,8243.552922 +0.131314,2633,8256.241729 +0.294598,1942,8259.428576 +0.476116,1701,8262.481401 +0.433422,6798,8282.182358 +-0.344,1137,8284.127371 +-0.33,911,8285.66013 +0.130948,1708,8288.583485 +0.098728,935,8290.209753 +0.123057,2057,8302.358507 +0.34894,1623,8305.35205 +0.157515,1428,8308.238146 +0.377194,3326,8314.419437 +0.164883,1837,8326.548213 +0.263598,1788,8330.000619 +0.09887,1085,8331.940397 +0.067959,2713,8336.436118 +0.120344,1904,8347.856903 +0.237965,2027,8351.231393 +-0.292452,1368,8353.488536 +0.04449,1009,8355.365971 +0.135043,3684,8368.107972 +0.238965,2138,8371.619724 +-0.10933,1182,8373.720532 +0.58875,1345,8375.95191 +-0.049591,761,8377.249852 +0.300984,2303,8381.514687 +0.111703,1323,8391.641486 +0.407137,2110,8395.281657 +-0.338,1352,8397.807526 +0.135043,1239,8400.097105 +0.098668,1758,8403.370271 +0.473427,1538,8413.310983 +0.209308,3979,8420.406042 +-0.052598,1496,8423.355721 +0.136314,1303,8425.990712 +0.229277,2142,8437.934357 +0.68148,1019,8440.009242 +0.763766,763,8441.621146 +0.445744,2411,8446.480658 +0.468598,2025,8450.59562 +0.183734,1880,8461.674065 +0.107344,1375,8464.117558 +-0.16444,1691,8467.253384 +0.715562,972,8469.054396 +0.364301,2178,8473.040421 +0.2773,1018,8482.933142 +0.141043,1455,8485.586039 +0.120519,3139,8491.814103 +-0.038345,1503,8494.780315 +0.507932,2462,8507.851944 +0.289799,1738,8511.204425 +0.231384,2685,8515.98304 +-0.116719,1264,8518.218637 +-0.074307,751,8519.568353 +0.426047,1946,8532.643013 +0.335773,1605,8535.405686 +0.567347,1025,8537.276985 +0.018518,1636,8540.249322 +-0.048531,749,8541.655753 +0.396616,2764,8554.676614 +0.158322,1263,8557.110952 +0.068728,1981,8561.245594 +0.196866,2221,8565.724818 +0.268053,1997,8577.617746 +0.102703,2054,8580.906054 +-0.061357,888,8582.509757 +0.188598,1634,8585.49031 +0.544625,1325,8587.768993 +0.345876,2320,8599.939638 +0.158564,1838,8602.811094 +0.06187,1358,8605.266401 +0.649748,888,8606.894196 +0.414386,1942,8610.47541 +0.491014,1823,8613.665443 +0.47191,2444,8625.869553 +0.312863,1916,8629.302743 +-0.040579,948,8630.863533 +-0.292704,667,8632.11473 +0.450343,2163,8636.164019 +0.204692,1389,8645.447841 +0.148807,1168,8647.467027 +0.062518,1004,8649.374209 +-0.033531,1084,8651.348517 +0.333,2746,8656.48746 +0.151124,2391,8668.175914 +0.373737,2402,8672.801165 +0.211816,2304,8677.237346 +0.740168,672,8678.488041 +0.088139,1309,8680.974988 +0.46635,1119,8690.899557 +0.082703,2776,8695.645997 +0.63875,1338,8698.015929 +-0.303704,1689,8701.10751 +0.017701,1254,8703.113837 +0.138272,1785,8712.855822 +0.701352,968,8714.583866 +0.093302,2198,8718.509076 +0.468076,1994,8722.110509 +0.061994,1200,8724.30217 +-0.054422,1426,8734.757489 +0.091368,1557,8737.408883 +0.498228,1143,8739.578382 +-0.129312,1519,8742.31447 +0.352876,1694,8745.453032 +0.513341,2383,8756.909145 +0.034737,1734,8759.833919 +0.292098,1723,8762.953758 +0.709147,1229,8765.165498 +0.197014,1641,8768.094694 +0.482613,1353,8778.133179 +0.379808,1481,8780.410279 +-0.013771,2470,8785.335945 +0.074538,1977,8788.885363 +0.32997,1914,8799.444044 +-0.16344,1431,8802.155739 +0.127948,885,8803.914527 +0.165711,2291,8808.609909 +0.057437,1084,8810.913424 +0.31245,1501,8813.769237 +0.63741,1458,8824.264844 +0.281863,2095,8827.931068 +0.568186,1540,8830.839395 +0.329737,1863,8834.120565 +-0.053422,1843,8837.502804 +-0.055598,1327,8847.987683 +0.129519,2122,8851.922098 +0.165883,1626,8855.231655 +-0.114719,822,8856.873699 +0.118792,1816,8860.586776 +-0.097133,1414,8870.834271 +0.130314,1306,8873.327536 +-0.003357,1899,8877.031946 +0.040518,1221,8879.436333 +0.190157,1358,8882.153703 +0.320621,1626,8894.168331 +-0.06485,2908,8898.966831 +-0.122312,1389,8901.479764 +0.128589,1405,8903.919749 +0.205816,1966,8907.793886 +0.06349,779,8916.883828 +0.133703,1838,8920.307807 +0.06587,1488,8923.106181 +-0.021295,1097,8925.178818 +0.469969,1792,8928.866879 +0.32558,1406,8931.718391 +0.232783,2345,8942.3298 +0.302734,1703,8945.364009 +0.458905,1742,8948.267579 +0.039887,1835,8951.454716 +0.098703,1212,8961.220659 +0.412776,1794,8964.314937 +0.17223,1237,8966.534346 +0.356495,2496,8970.831345 +0.142272,1570,8973.860969 +0.124238,1123,8983.392293 +0.359346,2511,8987.632172 +0.100668,2177,8991.319565 +0.550231,1399,8993.775236 +0.257876,1761,9004.399796 +0.32958,2320,9008.12297 +-0.146111,1632,9010.902579 +0.206564,1077,9012.853203 +-0.038295,1575,9015.729539 +0.025881,852,9017.320415 +0.321538,2677,9030.410477 +-0.159304,732,9031.790938 +0.477482,1989,9035.665267 +0.466788,2215,9039.54087 +0.084668,1316,9049.75986 +0.368843,1955,9053.237629 +0.643219,1114,9055.070383 +0.443737,3427,9061.010133 +-0.133189,1539,9071.188991 +0.297799,2039,9074.501121 +0.415501,2281,9078.419091 +0.067421,1196,9080.441749 +0.291098,2154,9084.129509 +-0.335,822,9094.551785 +-0.113,651,9095.595245 +0.34794,3042,9100.890313 +0.2773,1501,9103.698038 +0.142807,1287,9105.957294 +0.256453,1881,9117.250156 +0.283984,2563,9121.678177 +0.248053,2811,9126.720673 +0.296206,1956,9130.266326 +0.259453,2022,9141.120713 +0.051437,1110,9143.330673 +0.210396,1645,9146.730944 +-0.198113,718,9148.229935 +0.351908,1909,9152.039731 +0.578276,1897,9164.812202 +-0.013771,1614,9168.041463 +0.345908,1785,9171.828296 +0.110344,1511,9174.670415 +0.345138,2932,9186.63406 +-0.343,1024,9188.308363 +0.033887,1356,9190.615061 +0.453076,1994,9194.164009 +0.071421,835,9195.623343 +0.336737,2760,9208.321634 +0.140519,1455,9210.814377 +-0.346,689,9212.191357 +0.087302,2517,9217.247436 +-0.002598,1151,9219.572499 +0.656876,1181,9221.835491 +0.245876,2026,9233.371123 +-0.094708,2027,9236.755767 +-0.144111,1331,9239.154052 +-0.352,773,9240.554862 +0.109948,2593,9245.034832 +-0.136189,779,9254.906669 +0.440356,1788,9257.781384 +-0.150708,1427,9260.368567 +0.272453,1761,9263.735309 +0.493887,2580,9268.939722 +0.038881,1808,9279.886125 +0.260378,1360,9282.522836 +0.405089,1508,9285.484175 +0.036437,1592,9288.528034 +-0.290452,1548,9291.226944 +0.643229,1444,9301.923541 +0.334308,2347,9305.705862 +0.077728,1221,9307.813226 +0.38465,2063,9311.293517 +0.113238,1794,9314.099529 +0.017855,753,9322.884709 +0.383909,2996,9327.863525 +0.375843,2173,9331.735982 +0.50402,1731,9334.661946 +0.518013,1683,9343.458728 +0.153322,2567,9347.796996 +-0.347,1349,9350.111223 +0.109703,1047,9351.977408 +-0.130312,1499,9354.646743 +0.041887,1253,9364.446671 +0.353661,2100,9367.818543 +0.057057,1203,9369.907284 +-0.212034,710,9371.150438 +0.346781,2522,9375.522085 +0.17423,2147,9386.641239 +0.441186,2056,9390.696454 +0.437633,1725,9394.276013 +0.297206,2058,9398.531579 +-0.168979,1845,9409.781114 +-0.120312,800,9411.185282 +0.289527,1577,9413.975908 +0.275598,1147,9415.999314 +0.177557,2387,9420.284158 +0.078538,1548,9422.979949 +-0.076591,1101,9432.383817 +-0.020337,2416,9436.393287 +0.324661,2137,9440.127095 +0.274799,2438,9444.57234 +0.026881,1403,9455.320291 +0.514776,2325,9459.395845 +0.32458,1757,9462.746337 +0.454971,1983,9466.723492 +-0.014623,2042,9477.858083 +0.098668,1027,9479.657089 +0.353876,2470,9483.930959 +-0.043298,1219,9486.023138 +0.761148,840,9487.709532 +0.298258,3160,9500.352803 +0.59675,1345,9502.809506 +0.42319,2123,9507.173715 +-0.219034,1047,9509.336451 +0.398416,2549,9522.324429 +-0.126489,2025,9526.072962 +-0.10933,1128,9528.336511 +0.35497,2060,9532.558137 +-0.35,736,9533.821861 +0.511107,1740,9536.906298 +-0.163557,970,9545.833778 +-0.137189,1207,9547.720047 +0.194297,2333,9551.832018 +-0.258958,1470,9554.402473 +0.450879,2060,9557.949726 +0.440677,2024,9569.311219 +0.135564,3863,9576.703141 +0.183396,2087,9580.722652 +0.003855,1219,9591.234405 +0.086668,1879,9594.357503 +0.645972,1205,9596.611461 +0.166883,2025,9600.266646 +0.027538,1152,9602.178303 +0.278734,1424,9610.181482 +0.581745,1695,9612.919173 +0.129564,1777,9615.942271 +0.327699,2663,9620.530271 +0.454956,1856,9632.504136 +0.132807,3274,9638.551205 +-0.099133,1765,9642.248612 +0.218277,1746,9645.52302 +0.414425,2569,9657.954671 +-0.075913,1064,9659.776392 +0.095703,2732,9664.91761 +0.180396,1328,9667.052203 +-0.123189,991,9668.595342 +0.578071,1592,9679.174341 +0.11565,1245,9681.165087 +0.420538,1964,9685.033589 +0.567362,1172,9687.412434 +0.193157,2168,9691.496991 +0.198297,2151,9701.907513 +0.204564,1442,9704.358821 +-0.047345,1640,9707.213523 +0.282924,1213,9709.165138 +0.38797,2226,9713.170699 +-0.258557,1229,9721.896516 +0.2943,1888,9725.138147 +0.542124,1969,9728.672368 +0.124057,1659,9731.640822 +0.548572,1220,9733.908381 +0.47235,2003,9744.462693 +0.160515,2011,9748.229258 +0.213258,2257,9752.434151 +0.214692,1355,9755.013235 +-0.208029,2557,9769.178354 +0.026225,813,9770.639828 +0.35194,2976,9775.696006 +-0.051674,1859,9778.960003 +-0.073591,1301,9788.847042 +0.522294,2419,9792.716207 +0.150272,2451,9797.048397 +0.484868,1470,9799.655884 +0.36497,1659,9802.591823 +0.239965,3207,9814.848597 +0.348908,2763,9819.524661 +-0.011138,1167,9821.41103 +0.362908,1878,9833.047296 +0.2633,1263,9834.992573 +0.240277,3033,9840.557445 +0.044971,1196,9842.770134 +-0.349,722,9844.10345 +0.691607,1346,9854.175542 +0.310357,2213,9857.671027 +0.307357,2184,9861.653766 +-0.072307,1479,9864.495914 +0.389951,2856,9878.304597 +-0.074307,1588,9881.176909 +0.140272,1156,9883.380525 +0.042887,1977,9886.908329 +0.141314,1156,9889.243961 +0.338647,2627,9900.606829 +-0.334,879,9901.973877 +0.495103,1476,9904.690512 +-0.007138,1991,9908.127279 +0.312863,1977,9911.707533 +0.270598,1677,9922.082793 +0.249589,1886,9925.524313 +0.093297,2540,9930.443056 +0.019518,1431,9932.911497 +0.470504,1872,9943.136702 +0.344908,1756,9946.082084 +-0.161791,746,9947.551959 +-0.343,1262,9950.003475 +-0.106719,793,9951.518679 +0.258453,1469,9953.985413 +0.151866,2111,9963.465653 +0.25222,2075,9966.82961 +0.613218,1069,9968.679375 +0.194432,1799,9971.800267 +0.345808,3332,9984.770246 +-0.236288,1371,9987.087485 +0.55325,1886,9990.647342 +-0.15544,978,9992.35765 +0.132314,1373,9994.902237 +0.500112,2044,9998.881866 +0.020881,1454,10008.794942 +-0.125312,836,10010.360163 +0.050484,1922,10013.701446 +0.35597,1903,10016.878677 +0.239984,1684,10019.932678 +-0.014771,1238,10030.321814 +0.366999,3600,10036.203431 +0.280984,1983,10039.46559 +0.060959,632,10040.633528 +0.343843,2903,10052.060497 +0.595674,1072,10053.874556 +0.392792,3158,10059.058246 +-0.347,1120,10061.008887 +-0.127282,537,10061.842498 +0.676338,1085,10072.253417 +-0.06485,1026,10073.887005 +0.434793,1973,10077.406372 +0.35097,2277,10081.515659 +0.504871,1387,10083.955902 +0.074139,1969,10095.081594 +0.264808,1377,10097.331285 +0.221432,1798,10100.404739 +0.068421,1260,10102.7672 +0.040314,2431,10107.299191 +0.01055,1475,10117.667168 +0.276799,1547,10120.424035 +0.400501,3314,10126.40115 +0.180495,2801,10140.322155 +0.675164,939,10141.78511 +0.2683,1640,10144.699945 +0.450218,2658,10149.03178 +-0.116719,1549,10151.715897 +0.301308,2045,10162.743061 +0.140043,1693,10165.709048 +0.557082,1315,10168.094985 +0.42166,2232,10171.853419 +-0.343,1252,10174.164246 +-0.164677,1543,10183.607786 +0.251053,2575,10187.833342 +0.337773,1528,10190.420082 +0.359876,2203,10194.29446 +0.35397,2433,10206.419595 +0.329661,2423,10210.477388 +-0.339,1189,10212.47315 +0.036225,1144,10214.277272 +-0.037282,2110,10226.64331 +0.576171,1261,10228.698817 +0.594146,1385,10231.194628 +0.05249,1568,10234.149308 +0.019855,881,10235.740253 +0.414064,2304,10240.345546 +0.192297,2777,10253.821067 +0.505227,1548,10256.52836 +0.546698,1705,10259.466419 +0.057959,1846,10262.624149 +-0.17735,1433,10272.212941 +-0.147111,991,10273.843781 +0.193297,2530,10278.433178 +0.204564,1245,10280.705439 +0.418816,1733,10284.092378 +0.661478,894,10285.751436 +0.11565,1277,10295.408706 +0.518486,1906,10298.93816 +-0.05785,1608,10302.1594 +0.286042,1775,10305.777169 +0.471259,1789,10309.360621 +0.271453,2414,10319.43704 +-0.108189,1119,10321.414473 +-0.169791,1048,10323.215568 +0.420107,2801,10327.864136 +0.043881,731,10329.141004 +0.179714,1790,10339.838488 +-0.104337,952,10341.424159 +0.251965,1635,10344.735387 +0.488053,1982,10348.902754 +0.416565,1562,10352.187501 +0.039437,2742,10361.549078 +0.176059,1559,10364.568593 +0.575279,1436,10367.102521 +-0.329,898,10368.781111 +0.034737,1282,10371.205323 +-0.103708,2111,10381.158518 +0.139453,973,10382.691387 +0.511813,2035,10385.994529 +-0.17935,986,10387.624857 +0.342308,1694,10390.606626 +0.043971,1686,10400.30414 +0.494803,1704,10403.080223 +0.407389,2794,10408.194494 +0.223277,1623,10411.116706 +0.115519,2712,10424.269996 +-0.352,957,10425.894699 +0.127057,1242,10427.957629 +-0.334,946,10429.622519 +0.285924,1465,10432.023849 +-0.314,1577,10434.957134 +0.051402,684,10436.188935 +0.225589,1732,10446.385203 +0.017057,2657,10451.187888 +0.67183,1283,10453.315394 +0.560079,1673,10456.319612 +0.306737,1594,10467.095873 +0.573541,1894,10470.26766 +0.36594,2377,10474.720028 +0.562464,1340,10477.260144 +0.218277,2035,10489.066787 +0.168883,1469,10491.6285 +0.314008,2964,10496.972207 +0.070728,1052,10498.867065 +0.116238,1461,10501.476841 +0.03632,1966,10511.997003 +0.003402,2657,10516.33407 +0.023136,1623,10519.227562 +0.508595,1480,10521.891819 +0.102028,2266,10532.4263 +-0.029298,1151,10534.174652 +0.2503,1635,10537.097217 +0.155711,2215,10541.056003 +0.54077,1324,10543.431729 +0.260527,2600,10555.63675 +0.061959,1200,10557.695863 +-0.343,624,10558.85611 +0.343398,1907,10562.446159 +0.35297,1793,10565.732546 +0.162883,2631,10577.197989 +0.060484,1205,10579.207356 +0.060302,2410,10583.650231 +-0.04685,1748,10586.990611 +0.202692,1815,10598.410469 +0.216053,2190,10602.197764 +0.597282,1280,10604.798105 +0.031058,1543,10607.837699 +-0.100531,1217,10610.181533 +-0.080913,1007,10612.186581 +0.222488,2191,10622.590539 +0.410202,1821,10625.845889 +0.31245,2986,10631.318249 +0.365538,1430,10634.010499 +0.489069,2241,10645.636752 +0.013402,1023,10647.727174 +0.021518,814,10649.443626 +0.249138,1480,10652.545871 +0.276734,1700,10655.961075 +0.19923,2929,10669.270331 +0.172238,1412,10672.013908 +0.324495,1463,10674.709072 +0.200059,1486,10677.364382 +-0.138189,1514,10680.11229 +0.391627,2279,10691.69023 +0.298984,1817,10694.885029 +0.379074,2497,10699.017141 +-0.11433,1752,10702.037703 +0.07265,960,10709.887229 +0.405629,1893,10713.231489 +0.676451,880,10714.930818 +0.366901,3420,10721.798628 +0.063971,1792,10731.572087 +-0.061119,751,10732.816664 +0.35294,3274,10738.268082 +0.032136,1420,10740.681185 +0.020402,1591,10743.605837 +0.451216,1944,10754.884974 +0.380974,3762,10761.200225 +-0.344,1326,10763.660666 +-0.058674,902,10765.353382 +0.348876,2179,10777.10603 +0.187701,1270,10779.425294 +-0.077,2446,10784.143875 +0.092668,1526,10787.076309 +-0.231288,840,10788.698398 +0.400682,2430,10799.558647 +-0.328,1230,10801.512359 +0.443958,1971,10805.043468 +0.426111,2336,10809.24182 +0.146272,3154,10822.305503 +-0.103133,1818,10825.899068 +0.423661,1904,10829.615477 +0.434612,1472,10832.37642 +0.208432,1056,10834.464316 +0.102344,2799,10847.266097 +-0.040298,1815,10850.435234 +0.341843,2172,10854.462027 +-0.034337,2514,10865.433918 +0.127564,2047,10868.833709 +0.199432,1562,10871.642126 +0.108322,1200,10873.778845 +0.332773,3599,10886.415703 +0.35997,3582,10892.910657 +0.328357,2595,10897.885117 +0.285042,2456,10910.313621 +-0.092118,918,10911.928074 +0.417957,2830,10917.260508 +0.004643,1149,10919.399558 +0.591152,1532,10922.180254 +-0.088274,2216,10932.982335 +0.46771,1974,10936.553141 +0.35097,2608,10941.399004 +-0.039422,1041,10943.414992 +0.312153,2166,10954.638997 +-0.001357,1993,10958.472471 +0.188157,1701,10961.751858 +0.102028,2462,10966.529071 +-0.056531,941,10975.012793 +0.33158,3428,10981.036284 +0.25522,1148,10983.068489 +0.223488,1475,10985.77863 +0.384856,2445,10998.600623 +0.137564,2272,11002.443486 +0.410493,3276,11008.94277 +0.153043,1175,11011.39827 +0.398951,2856,11022.081847 +0.203816,1642,11025.355074 +0.499486,1906,11029.175069 +-0.103942,1208,11031.526912 +0.259527,1379,11041.645468 +0.180714,3219,11046.971392 +0.078538,1332,11049.407801 +0.557311,1125,11051.44258 +0.544942,950,11053.122494 +-0.000598,1922,11064.203356 +0.300308,1713,11067.351991 +0.512568,1650,11070.529855 +-0.025502,2539,11075.848726 +0.059484,1710,11079.591656 +0.186515,1744,11089.154963 +0.287863,2415,11093.826416 +0.139564,1071,11095.74976 +0.201692,2798,11100.509148 +-0.129312,1167,11109.414138 +0.319308,1798,11112.529638 +0.529757,2129,11115.781666 +-0.060591,1346,11117.966991 +0.34794,2568,11129.673085 +0.606706,1495,11132.409595 +-0.097118,1818,11135.828788 +-0.17335,1181,11138.145358 +-0.124121,653,11139.38714 +0.089668,1811,11142.772055 +0.297098,1305,11152.940018 +-0.070591,2450,11157.177275 +-0.012771,884,11158.794026 +0.35345,1985,11162.417194 +0.639773,1077,11164.447964 +-0.112,1152,11166.3871 +0.360773,2286,11177.585776 +0.124519,1735,11180.701394 +0.356473,2330,11185.258196 +-0.125189,1095,11187.550638 +0.36397,1574,11196.845843 +0.333464,3240,11203.347306 +0.236661,1849,11207.272479 +0.268734,2661,11217.912494 +-0.163791,735,11218.982891 +0.35497,1826,11222.024497 +0.206621,2921,11227.130038 +0.176883,2002,11230.472795 +0.220297,1164,11239.904847 +0.097668,1718,11242.776412 +0.434169,2704,11247.699614 +0.020518,1591,11250.279845 +0.112238,1570,11259.804964 +0.072139,2394,11263.879802 +-0.024282,765,11265.311665 +0.334737,3009,11270.420165 +-0.257288,917,11271.990076 +-0.215034,964,11281.070038 +0.616335,1327,11283.010364 +0.173396,1767,11286.063886 +0.600265,1241,11288.308774 +0.090668,1304,11290.671958 +0.397381,2871,11301.428409 +0.17223,2067,11305.178473 +-0.054422,1301,11307.815484 +0.440034,2045,11311.885715 +0.002139,940,11313.828194 +0.188157,1753,11324.569204 +-0.06685,1192,11326.646474 +0.615109,1242,11329.06005 +0.030136,2786,11334.447653 +0.156124,1236,11336.796908 +0.256138,2000,11347.282847 +0.311495,2535,11351.57019 +0.632264,994,11353.203997 +0.25222,1721,11356.2124 +0.108344,1193,11358.342978 +-0.339,1606,11369.680328 +0.462031,1533,11372.420016 +0.465131,2575,11377.525922 +-0.034674,1104,11379.501035 +0.352876,1294,11381.824198 +0.348908,2406,11392.695729 +0.377773,2046,11396.301296 +0.007402,1294,11398.701474 +0.594146,1005,11400.481446 +-0.025502,3207,11413.375827 +-0.194892,1268,11415.343725 +0.057421,1034,11417.176333 +0.44134,2054,11420.880057 +0.188157,1263,11423.330508 +0.154322,2210,11435.245347 +0.182701,1449,11438.030351 +0.148564,1252,11440.560193 +0.509116,2555,11445.771514 +0.10665,1927,11449.70236 +0.35897,2457,11460.49737 +0.546588,1298,11462.737797 +0.212053,3156,11468.311088 +-0.113719,1101,11470.207185 +0.504509,1669,11480.476648 +0.309308,1897,11483.733127 +0.319538,1879,11487.171888 +0.422807,3424,11493.706881 +0.137807,1846,11503.531202 +0.182714,1687,11506.71217 +0.24822,2710,11511.7201 +0.485613,1520,11514.440348 +0.228488,2189,11525.83628 +0.391131,2575,11530.4343 +0.555591,1860,11533.431775 +0.283924,1997,11537.047672 +-0.04885,1038,11546.36938 +0.318924,3054,11552.107449 +-0.020623,887,11553.790279 +0.397533,2766,11558.752633 +-0.149111,1251,11566.620613 +-0.043531,1403,11568.907902 +0.393957,2780,11573.876048 +0.35694,1749,11577.031051 +0.36097,2170,11587.522318 +-0.195892,1153,11589.343722 +0.264453,3250,11594.665376 +-0.021623,2139,11598.559254 +0.04632,1346,11608.213701 +0.054994,2763,11612.651501 +0.548907,1358,11615.099149 +0.232688,2683,11619.935306 +0.124519,1502,11630.302389 +0.296153,1976,11633.581596 +0.363475,2528,11638.19909 +0.606042,1150,11640.339662 +0.646406,1266,11642.655485 +0.303308,2075,11653.317964 +-0.114719,1457,11655.902424 +0.179714,1895,11659.321227 +0.580325,1699,11662.445344 +-0.071307,1980,11666.28756 +0.305404,1661,11676.324558 +0.335808,2490,11681.198347 +0.065421,1480,11684.018789 +-0.028422,1031,11686.038281 +0.496417,2053,11696.214577 +0.185014,2135,11699.781308 +-0.027406,1920,11703.402203 +0.471428,1840,11706.809631 +0.136043,2498,11717.947471 +0.100028,1537,11720.204137 +-0.273452,839,11721.656344 +0.243053,2743,11727.197622 +0.520807,1373,11729.976591 +0.348,2332,11742.886791 +0.010737,1009,11744.688666 +0.470535,1697,11748.051589 +0.361621,1861,11751.458681 +0.132807,1709,11754.631094 +0.530103,1476,11764.210589 +-0.35,1661,11766.958378 +0.025737,2374,11771.17046 +-0.344,1985,11774.678908 +0.263965,1665,11784.099909 +0.308404,1779,11787.282447 +-0.099708,735,11788.837795 +0.181714,2526,11794.019974 +0.043057,1190,11796.073377 +0.360773,1618,11799.381305 +0.276043,2880,11812.032792 +0.110028,2356,11816.237362 +0.153057,1375,11818.570563 +0.10387,1404,11821.035964 +0.185557,2479,11832.967946 +0.344876,1905,11836.344506 +0.190714,1236,11838.593555 +0.108703,2620,11843.082093 +0.086668,1110,11852.571383 +0.112238,2114,11856.256054 +0.187714,1989,11859.870684 +0.108368,1156,11861.968294 +0.189883,2915,11873.527056 +0.237589,2211,11877.284479 +0.247688,1064,11879.233381 +0.496756,2023,11882.948039 +0.44724,3212,11896.851472 +0.165515,1741,11899.721111 +0.021518,1706,11902.910565 +0.121057,2220,11907.283634 +0.259965,967,11909.318411 +0.325304,3014,11921.33438 +0.039807,1259,11923.781504 +0.033887,1507,11926.749343 +0.618811,1206,11929.125632 +-0.118,915,11930.985663 +0.381389,2491,11941.920807 +0.297667,2140,11945.607014 +0.303357,2934,11950.555707 +0.167883,1829,11960.037031 +0.476219,1635,11962.754394 +-0.198126,1030,11964.626813 +-0.081598,662,11965.835375 +0.194014,2715,11970.518757 +-0.234557,981,11972.275544 +0.179322,1047,11979.99211 +0.592016,1438,11982.201701 +0.133057,1703,11985.023917 +0.2503,2102,11988.549428 +0.076728,1379,11990.979251 +0.361908,2527,12001.806273 +-0.014942,1495,12004.411178 +-0.142159,1192,12006.605227 +0.54039,1572,12009.519017 +0.285799,1281,12011.932612 +0.265588,2814,12024.709899 +-0.049674,1183,12026.922678 +0.195157,1926,12030.750524 +-0.014502,2828,12036.341151 +0.149711,1496,12048.50516 +0.201557,1622,12051.772057 +0.339538,1833,12055.399855 +0.197714,2271,12059.391931 +-0.164677,1447,12062.06947 +-0.144121,789,12072.260509 +0.122057,2981,12077.466156 +0.354908,1418,12079.943836 +0.130807,1674,12083.146271 +-0.074307,1280,12085.489782 +0.325621,1890,12095.110331 +0.406329,1634,12098.205701 +0.339699,2530,12103.545997 +0.521108,1549,12106.829483 +0.380876,2129,12117.164052 +0.058421,2058,12120.60195 +-0.166979,1165,12122.669249 +0.345773,2110,12126.437458 +0.247138,2002,12137.376311 +0.149921,1180,12139.288849 +0.511693,2584,12143.894711 +-0.176791,1136,12145.915404 +0.352908,1664,12148.821738 +-0.127312,1849,12158.788048 +0.544936,1316,12161.208335 +0.599211,1149,12163.480914 +0.35494,2043,12167.800256 +0.408811,2341,12172.588739 +-0.019531,1417,12181.758382 +-0.010623,901,12183.123086 +0.046994,1838,12186.223301 +0.24922,1410,12188.689362 +-0.033295,6476,12206.695807 +0.220277,1790,12210.356376 +0.368737,1656,12213.762468 +0.33258,2100,12226.236943 +0.11165,1151,12228.210854 +0.196557,1375,12230.870347 +0.014402,1405,12233.479885 +0.237589,2188,12237.292816 +0.032518,1411,12239.757466 +0.003139,843,12245.497187 +0.289098,1788,12248.251231 +0.690836,701,12249.521677 +-0.010942,2091,12253.388282 +-0.004531,769,12254.649559 +0.335737,1704,12257.606098 +0.460558,1716,12267.345191 +0.146495,2823,12272.648272 +0.340808,2130,12276.785089 +0.415096,2256,12288.407387 +0.423517,2265,12292.218828 +0.012139,2429,12296.478313 +0.466108,1636,12299.307127 +-0.007357,2840,12310.885858 +0.226488,1550,12313.514926 +-0.15644,1869,12316.860898 +0.191297,2374,12321.080671 +0.473585,1504,12329.808443 +0.294042,2730,12334.617777 +0.35394,1773,12338.151054 +0.530154,1600,12341.33215 +0.281734,1669,12344.484882 +-0.018623,2669,12355.968832 +-0.043298,1455,12358.607538 +0.045437,1359,12361.087024 +0.024518,2221,12365.031051 +0.336808,1590,12374.929744 +0.401413,2844,12379.971104 +-0.168979,895,12381.567335 +-0.141118,1007,12383.502693 +0.466657,2763,12394.474389 +0.304308,3021,12400.070276 +0.450339,1885,12403.734742 +0.331661,1706,12406.922611 +0.443513,2346,12417.884653 +0.058421,1537,12420.572038 +0.326699,2037,12424.354507 +0.012225,1494,12427.190407 +0.316843,1769,12430.432585 +0.459217,1980,12441.580724 +0.084302,1658,12444.772436 +0.030136,1328,12447.391031 +0.213053,2623,12452.322304 +0.156322,2651,12464.79359 +0.546558,1095,12466.985305 +0.494955,1693,12470.458755 +0.45089,1984,12474.116551 +0.021518,1764,12481.574703 +0.044881,1490,12483.930649 +0.56698,1517,12486.457962 +0.098703,1074,12488.380903 +0.377747,2376,12492.476789 +0.167059,1382,12494.814553 +0.175883,1709,12505.426899 +0.48871,1974,12509.439215 +0.065305,2749,12515.069207 +0.598338,1413,12517.907981 +0.319308,1561,12527.510527 +0.412043,2963,12533.431036 +0.237688,2082,12537.094276 +-0.145159,985,12538.849253 +-0.352,915,12540.42227 +0.548338,1413,12551.438693 +0.555971,1712,12554.28417 +0.057421,1492,12556.909615 +0.248965,1287,12559.084435 +0.133057,2030,12562.599952 +0.182557,2086,12571.734623 +0.600739,1140,12573.76572 +0.474249,1719,12577.260436 +0.098028,2158,12581.278322 +-0.34,911,12582.964917 +-0.17935,758,12591.648659 +0.083728,2347,12595.187435 +0.197297,1468,12597.813368 +0.566869,1551,12600.573978 +-0.189121,818,12602.011191 +0.34894,1684,12605.059255 +0.336773,2699,12615.858099 +-0.15244,1453,12618.416328 +0.508008,1211,12620.573919 +0.185564,1227,12622.882768 +0.179714,2686,12634.549245 +-0.352,1699,12637.997405 +0.27822,2328,12643.043996 +0.506907,1703,12646.618186 +0.524753,1440,12649.546765 +0.424355,3074,12661.951985 +0.054495,1412,12664.428463 +0.109703,1634,12667.322875 +0.184557,1963,12670.817373 +0.36094,2045,12681.204391 +0.17423,1885,12684.668755 +0.661558,1095,12687.001753 +0.558279,1436,12689.880133 +-0.348,1763,12693.514589 +0.069959,1342,12702.416846 +0.565615,1916,12706.048756 +0.136043,1199,12708.464097 +0.256138,2488,12713.119035 +-0.083274,1099,12715.074707 +0.499522,1312,12721.807044 +0.409809,2245,12725.591002 +0.022136,2963,12730.557955 +0.507014,1823,12733.823798 +0.391876,2141,12744.229817 +0.452504,1872,12748.081621 +-0.172979,1335,12750.877581 +0.144495,1928,12754.727622 +-0.006138,2438,12767.195338 +0.286667,1066,12769.171604 +0.438189,2043,12773.204572 +-0.237288,1258,12775.417634 +0.025737,924,12776.96836 +0.472955,1693,12780.084968 +-0.213029,688,12786.360498 +0.436583,1796,12789.373413 +0.475529,1807,12792.577061 +0.091023,2558,12796.827285 +-0.17335,1789,12806.782225 +-0.141121,823,12808.299596 +-0.136189,1151,12810.536013 +0.472204,1363,12813.330404 +0.145711,2886,12819.403967 +0.136807,1220,12821.991144 +0.064484,1189,12828.777686 +0.335699,2610,12833.893653 +-0.34,1196,12836.333507 +0.187866,2286,12840.320549 +0.005498,1114,12842.24802 +0.510362,2028,12852.582951 +-0.048674,2041,12856.004997 +0.337699,1801,12858.948646 +-0.113,1090,12860.952338 +0.060959,1217,12863.263725 +0.144711,2402,12875.25526 +0.040887,1362,12877.865718 +0.632148,840,12879.598276 +0.390355,3139,12885.964625 +0.610335,1327,12896.341556 +0.550996,1469,12898.775395 +0.245138,1530,12901.518811 +0.339808,3190,12906.908965 +0.022881,1342,12913.873905 +0.055437,1238,12915.752716 +0.095368,2109,12919.458337 +0.163701,1148,12921.414466 +0.285924,1986,12924.912404 +0.123519,1240,12927.170517 +-0.126489,868,12935.317512 +0.479879,2463,12939.379808 +-0.050531,1399,12941.829139 +0.36694,2215,12945.597245 +0.349808,2037,12956.763387 +0.260378,2228,12960.283095 +-0.344,1615,12962.845628 +0.411794,1949,12966.292834 +0.31045,2180,12977.729393 +0.274863,1814,12980.651107 +0.330699,2778,12985.990405 +0.067305,1492,12988.78881 +0.209404,1251,12991.134897 +0.506698,1604,13000.524442 +-0.006357,1678,13003.7018 +0.278598,2658,13009.231046 +-0.309083,939,13011.091246 +0.299308,2246,13021.531714 +0.101344,2334,13025.242044 +0.553109,1308,13027.56888 +0.441244,2773,13032.243541 +0.155384,1844,13043.178944 +0.211042,2308,13046.870349 +-0.142121,888,13048.441746 +0.115368,1276,13050.739007 +-0.127489,2550,13055.286203 +0.246138,2539,13065.878541 +0.409917,2113,13069.65346 +0.179714,2221,13073.458408 +0.049737,1868,13076.768219 +-0.298452,1877,13086.16073 +0.33458,1369,13088.613862 +-0.005357,2804,13093.526341 +-0.119719,830,13095.06557 +0.300308,1882,13104.851973 +0.229564,1949,13108.311931 +0.124701,1354,13110.979242 +0.340773,3094,13117.106066 +-0.050422,1559,13127.826093 +0.472301,1748,13130.717713 +0.028136,1353,13133.240613 +0.286984,3118,13138.635716 +0.310404,2657,13150.206966 +0.595368,1522,13152.860848 +0.329699,3003,13158.260285 +0.00955,1066,13160.053886 +0.328621,2330,13172.37113 +-0.348,900,13173.936116 +0.490108,1636,13177.209379 +0.34894,2325,13181.92139 +0.190396,1861,13185.299352 +0.620914,1193,13192.984011 +0.437553,2629,13197.754781 +0.274527,2610,13202.554555 +-0.054422,1920,13205.972645 +-0.084913,1187,13214.51346 +0.071139,2859,13219.198346 +0.419801,1560,13221.809218 +0.210059,1687,13225.204559 +0.383409,1862,13235.946911 +0.640322,1052,13237.97929 +-0.091118,1614,13240.873532 +0.443702,1915,13244.360033 +0.387162,3452,13250.906798 +0.366699,2050,13261.246553 +0.373977,3086,13266.628433 +-0.232113,1393,13269.106846 +0.12323,1409,13271.514508 +0.302042,1479,13280.752177 +0.568183,1294,13283.05332 +0.176883,2232,13286.917649 +0.022518,1496,13289.643117 +0.530784,1366,13292.091463 +-0.01668,2937,13303.432084 +0.071305,1018,13305.279186 +0.28997,2724,13310.028094 +0.347737,1768,13313.208855 +0.639892,1344,13319.748844 +0.006855,1564,13322.188918 +0.095668,1225,13324.361195 +0.345,1801,13327.577665 +0.472427,1538,13330.159488 +0.047881,1651,13341.377127 +0.013225,991,13343.03387 +0.258453,1812,13346.528923 +0.469787,1648,13350.035323 +-0.150304,1023,13352.169777 +0.079139,2064,13356.251092 +0.648204,1429,13366.875804 +0.365939,3025,13372.853746 +0.006862,1325,13375.165512 +0.227384,1990,13378.427999 +0.342876,2242,13389.442696 +0.197564,1201,13391.568037 +0.235297,1125,13393.566602 +0.051887,1512,13395.958004 +0.557229,1287,13398.298949 +0.511386,1942,13409.599979 +0.124314,1605,13412.244839 +0.340808,2629,13416.827312 +0.041971,1575,13419.681983 +0.116238,2081,13429.905994 +-0.12,1614,13432.494546 +0.201692,1350,13434.895632 +0.034737,1183,13437.013202 +0.684381,978,13438.777001 +0.016643,2415,13442.923205 +-0.125111,1110,13450.66434 +0.398594,2233,13454.730518 +0.286799,2005,13458.229562 +0.269598,2370,13462.348489 +0.203396,1478,13472.987632 +0.341308,1513,13475.766177 +0.184714,1948,13479.609052 +-0.007357,1729,13483.051712 +0.126792,1286,13485.568843 +0.249661,2154,13495.525727 +-0.134312,669,13496.60114 +0.343876,2604,13501.378678 +-0.008771,1029,13503.226975 +-0.05985,1051,13505.232678 +0.245488,3122,13518.214072 +0.624562,972,13519.948566 +0.467871,2340,13524.550762 +0.474875,1879,13528.267074 +0.122057,2666,13539.874019 +-0.122719,1198,13542.167489 +0.313404,2123,13546.352592 +-0.15344,1008,13548.416001 +-0.127189,577,13549.613902 +0.35697,2611,13561.186213 +0.213557,713,13562.260005 +0.113238,1736,13565.301626 +0.57204,1601,13568.217721 +0.085302,2939,13573.526189 +0.135807,1693,13583.431731 +0.510917,1772,13586.778188 +0.45289,1984,13590.66091 +-0.182892,1371,13593.457196 +0.342661,1840,13597.216324 +0.05532,1196,13607.007356 +0.568003,1121,13608.97696 +0.318357,2521,13613.777064 +0.011855,940,13615.43863 +0.233488,1483,13618.115767 +0.415717,2466,13628.162335 +0.343808,1709,13631.08551 +0.584244,1608,13634.021003 +0.096668,1535,13636.554459 +0.106028,2350,13647.604141 +-0.024502,2007,13650.799988 +-0.333,890,13652.465175 +-0.047531,2725,13656.962313 +-0.138189,659,13658.181191 +0.339967,3296,13670.576363 +-0.180791,1061,13672.411742 +0.282734,1350,13674.706909 +-0.118502,2213,13678.406096 +0.197564,3053,13691.402873 +0.026225,1434,13693.863806 +0.489866,1250,13695.99508 +0.08349,1288,13698.203598 +-0.321,1320,13700.429555 +0.329621,1685,13703.359193 +-0.232557,1298,13713.300883 +0.606523,1118,13715.171852 +0.053484,2363,13719.785289 +0.09349,1452,13722.608447 +0.359737,1744,13725.928463 +0.63853,1003,13734.332461 +0.019225,1646,13737.076798 +0.028136,2524,13741.668353 +-0.087675,895,13743.232597 +0.374908,2064,13746.932971 +0.007229,1155,13754.971577 +0.201157,1212,13756.93639 +0.353908,2406,13761.307093 +0.06587,1085,13763.298836 +0.341843,2378,13767.563742 +0.031377,1204,13776.349993 +0.197124,1392,13778.659508 +-0.346,1903,13781.976151 +0.161515,2251,13785.807302 +0.482506,2363,13797.66421 +0.460678,2247,13801.365208 +0.475836,1902,13804.894989 +0.097926,1875,13808.011342 +0.099421,866,13809.599816 +-0.108708,1940,13819.531449 +0.094305,1113,13821.371849 +0.273231,2875,13827.032968 +0.010855,1008,13828.783715 +0.468207,1491,13831.850867 +0.576108,1822,13843.008588 +0.327951,2642,13848.095176 +0.228167,1791,13851.548902 +0.190157,2243,13855.023417 +0.300871,2340,13865.134434 +-0.352,1631,13868.135422 +-0.126121,1092,13870.079495 +-0.351,1023,13871.903042 +0.176557,986,13873.667902 +0.380591,3350,13885.934326 +0.01555,1034,13888.021364 +0.088305,950,13889.917151 +0.486216,2553,13895.088575 +0.207816,3143,13908.853539 +0.371773,1858,13912.35979 +-0.027295,1026,13914.458586 +0.353808,1903,13918.233277 +0.156515,1681,13921.509578 +-0.134312,631,13927.084236 +-0.04885,1505,13929.471706 +0.535585,1504,13932.09573 +0.166322,2423,13936.496748 +-0.05906,1482,13938.945118 +0.161515,1355,13948.109291 +0.681535,1177,13950.1486 +0.577892,1344,13952.833004 +0.562907,1703,13956.19964 +0.051971,1513,13959.241045 +0.5887,1754,13962.745448 +-0.345,1199,13971.41597 +0.281734,1704,13974.264141 +0.139272,2369,13978.39576 +0.344843,1778,13981.339519 +0.269598,2204,13991.660098 +0.416516,2547,13995.950529 +0.497758,1676,13998.908149 +0.346843,3144,14004.4728 +0.364908,2114,14015.961803 +0.439135,2638,14020.663598 +-0.086274,1417,14023.07335 +0.365268,2874,14034.994134 +-0.119,1893,14038.287338 +-0.025502,810,14039.742217 +0.508041,1180,14041.694137 +0.647913,1038,14043.607857 +0.464803,1704,14046.521755 +-0.017295,1318,14055.698865 +0.35097,1675,14058.421014 +-0.349,2186,14062.324913 +0.226589,1595,14065.409827 +0.44358,1817,14068.805811 +0.48692,1824,14079.27806 +0.221384,1982,14082.744003 +-0.339,1499,14085.674424 +0.077421,1862,14088.888933 +0.255378,1689,14097.90815 +0.328699,1226,14099.837378 +0.224384,2474,14104.076283 +-0.097603,998,14105.839232 +0.03832,914,14107.485172 +0.244488,1781,14110.675967 +0.351,2431,14120.292452 +-0.014771,1094,14122.248672 +0.350908,1909,14125.688015 +0.339843,3331,14138.896275 +0.063421,1769,14141.698705 +-0.113489,1072,14143.671387 +0.116238,1921,14147.114321 +0.510472,1354,14149.419276 +0.255378,2437,14159.194096 +-0.006942,1634,14161.784609 +-0.155677,935,14163.240078 +0.693159,1026,14164.830545 +0.573481,1292,14167.125355 +0.422747,2293,14171.310482 +-0.11333,1497,14180.352993 +0.380881,2622,14185.078288 +-0.013942,2046,14189.160861 +0.049437,1034,14191.282097 +0.112703,1383,14193.755724 +0.516503,1397,14203.871927 +0.384,3374,14210.65889 +0.244138,1520,14213.461159 +0.027136,1111,14215.382435 +0.35497,3218,14228.921837 +0.395975,2620,14233.58507 +0.457766,1359,14236.081581 +0.487023,1655,14239.106046 +0.206936,3242,14251.639601 +0.111432,1285,14254.33004 +-0.062913,1276,14256.976364 +-0.149268,1026,14259.110661 +0.070484,913,14260.918533 +0.185866,2869,14271.338564 +-0.018502,1418,14273.930645 +0.119028,1392,14276.375671 +0.472457,2869,14281.358383 +0.026136,1662,14290.379261 +0.323661,2705,14295.010204 +0.095368,1417,14297.620254 +0.06287,1772,14300.565428 +0.050994,1525,14309.718914 +0.173711,1558,14312.459345 +0.31145,2646,14317.731812 +0.119948,1184,14320.050819 +0.004855,2053,14324.262593 +-0.014674,1540,14333.344691 +0.115519,1218,14335.421119 +0.227167,1547,14338.256114 +-0.089675,1361,14340.469392 +0.319,1339,14342.884171 +0.281863,2133,14353.309089 +0.419832,2521,14357.519367 +-0.11533,1625,14360.416643 +0.226692,1537,14363.302642 +0.34894,2601,14375.63607 +0.275799,1383,14378.08126 +0.218167,2775,14383.277673 +0.193157,1321,14385.820879 +0.07587,847,14387.595169 +0.482878,1948,14396.832592 +0.588079,1288,14398.997225 +0.663146,1103,14400.983336 +-0.02413,921,14402.622267 +0.184714,3048,14408.584748 +0.34894,2586,14419.347341 +0.24922,2159,14423.277756 +-0.111312,1626,14426.758277 +-0.123312,969,14428.892769 +0.504513,2346,14440.114188 +0.048971,1728,14443.376375 +0.487317,1451,14446.337762 +0.473122,1730,14449.920064 +0.091668,2209,14454.115231 +0.517331,1498,14463.041074 +0.241783,1885,14466.088192 +0.031136,1596,14468.918597 +-0.047345,1785,14472.031466 +-0.000516,1393,14474.472964 +0.312495,2930,14485.000945 +0.005139,1004,14486.791008 +0.085302,2367,14490.806831 +-0.094133,1732,14493.973295 +0.284042,1848,14504.278667 +-0.118719,1563,14506.928619 +0.234783,2999,14511.851023 +0.600712,1264,14514.163608 +0.437419,2251,14525.074047 +0.272453,2300,14528.89555 +0.115519,2167,14532.707258 +0.41744,1633,14535.688889 +0.320538,2567,14545.708786 +0.097023,1087,14547.829097 +0.316538,2487,14552.813538 +-0.065113,1315,14555.433518 +0.049994,1203,14557.890195 +0.409277,2572,14569.518979 +0.012139,1278,14572.075978 +0.236277,1895,14575.469777 +0.603907,1703,14578.58982 diff --git a/004_image_stack_ram_based_reward_custom/street_fighter_custom_wrapper.py b/004_rgb_stack_ram_based_reward_custom/street_fighter_custom_wrapper.py similarity index 80% rename from 004_image_stack_ram_based_reward_custom/street_fighter_custom_wrapper.py rename to 004_rgb_stack_ram_based_reward_custom/street_fighter_custom_wrapper.py index b1f8ac3..2ff12aa 100644 --- a/004_image_stack_ram_based_reward_custom/street_fighter_custom_wrapper.py +++ b/004_rgb_stack_ram_based_reward_custom/street_fighter_custom_wrapper.py @@ -9,6 +9,21 @@ class StreetFighterCustomWrapper(gym.Wrapper): def __init__(self, env, testing=False): super(StreetFighterCustomWrapper, self).__init__(env) self.env = env + self.state_stages = [ + "Champion.Level1.RyuVsGuile", + "Champion.Level2.RyuVsKen", + "Champion.Level3.RyuVsChunLi", + "Champion.Level4.RyuVsZangief", + "Champion.Level5.RyuVsDhalsim", + "Champion.Level6.RyuVsRyu", + "Champion.Level7.RyuVsEHonda", + "Champion.Level8.RyuVsBlanka", + "Champion.Level9.RyuVsBalrog", + "Champion.Level10.RyuVsVega", + "Champion.Level11.RyuVsSagat", + "Champion.Level12.RyuVsBison" + ] + self.current_stage = 0 # Use a deque to store the last 4 frames self.num_frames = 3 @@ -37,7 +52,10 @@ class StreetFighterCustomWrapper(gym.Wrapper): return stacked_image def reset(self): + self.env.unwrapped.load_state(self.state_stages[self.current_stage]) + self.current_stage = (self.current_stage + 1) % len(self.state_stages) observation = self.env.reset() + self.prev_player_health = self.full_hp self.prev_oppont_health = self.full_hp @@ -53,8 +71,8 @@ class StreetFighterCustomWrapper(gym.Wrapper): def step(self, action): obs, _reward, _done, info = self.env.step(action) - curr_player_health = info['health'] - curr_oppont_health = info['enemy_health'] + curr_player_health = info['agent_hp'] + curr_oppont_health = info['enemy_hp'] self.total_timesteps += 1 diff --git a/004_image_stack_ram_based_reward_custom/test.py b/004_rgb_stack_ram_based_reward_custom/test.py similarity index 75% rename from 004_image_stack_ram_based_reward_custom/test.py rename to 004_rgb_stack_ram_based_reward_custom/test.py index 06df259..66664aa 100644 --- a/004_image_stack_ram_based_reward_custom/test.py +++ b/004_rgb_stack_ram_based_reward_custom/test.py @@ -50,25 +50,28 @@ state_stages = [ # # Add other stages as necessary # ] -env = make_env(game, state_stages[11])() +env = make_env(game, state_stages[0])() model = PPO( "CnnPolicy", env, verbose=1 ) -model_path = r"trained_models_ryu_level_1_time_reward_small_random/ppo_ryu_2600000_steps" +model_path = r"trained_models_ryu_level_1_time_reward_small_loop_continue/ppo_ryu_5000000_steps.zip" model.load(model_path) # Average reward for optuna/trial_1_best_model: -82.3 # Average reward for optuna/trial_9_best_model: 36.7 | -86.23 # Average reward for trained_models/ppo_chunli_5376000_steps: -77.8 +# Level_1 Average reward for trained_models_ryu_level_1_time_reward_small_random/ppo_ryu_4200000_steps: 0.35772262101207986 Winning rate: 0.5666666666666667 +# Level_2 Average reward for trained_models_ryu_level_1_time_reward_small_random/ppo_ryu_4200000_steps: 0.18094390738868166 Winning rate: 0.16666666666666666 -obs = env.reset() +# obs = env.reset() done = False -num_episodes = 30 +num_episodes = 12 episode_reward_sum = 0 +num_victory = 0 for _ in range(num_episodes): done = False obs = env.reset() @@ -81,11 +84,15 @@ for _ in range(num_episodes): if reward != 0: total_reward += reward - print("Reward: {}, playerHP: {}, enemyHP:{}".format(reward, info['health'], info['enemy_health'])) + print("Reward: {}, playerHP: {}, enemyHP:{}".format(reward, info['agent_hp'], info['enemy_hp'])) env.render() # time.sleep(0.005) + if info['enemy_hp'] < 0: + print("Victory!") + num_victory += 1 print("Total reward: {}".format(total_reward)) episode_reward_sum += total_reward -# env.close() -# print("Average reward for {}: {}".format(model_path, episode_reward_sum/num_episodes)) \ No newline at end of file +env.close() +print("Winning rate: {}".format(1.0 * num_victory / num_episodes)) +print("Average reward for {}: {}".format(model_path, episode_reward_sum/num_episodes)) \ No newline at end of file diff --git a/004_image_stack_ram_based_reward_custom/train.py b/004_rgb_stack_ram_based_reward_custom/train.py similarity index 73% rename from 004_image_stack_ram_based_reward_custom/train.py rename to 004_rgb_stack_ram_based_reward_custom/train.py index fa06234..433ccec 100644 --- a/004_image_stack_ram_based_reward_custom/train.py +++ b/004_rgb_stack_ram_based_reward_custom/train.py @@ -12,33 +12,32 @@ from street_fighter_custom_wrapper import StreetFighterCustomWrapper LOG_DIR = 'logs' os.makedirs(LOG_DIR, exist_ok=True) -class RandomOpponentChangeCallback(BaseCallback): - def __init__(self, stages, opponent_interval, verbose=0): - super(RandomOpponentChangeCallback, self).__init__(verbose) - self.stages = stages - self.opponent_interval = opponent_interval +# class RandomOpponentChangeCallback(BaseCallback): +# def __init__(self, stages, opponent_interval, verbose=0): +# super(RandomOpponentChangeCallback, self).__init__(verbose) +# self.stages = stages +# self.opponent_interval = opponent_interval - def _on_step(self) -> bool: - if self.n_calls % self.opponent_interval == 0: - new_state = random.choice(self.stages) - print("\nCurrent state:", new_state) - self.training_env.env_method("load_state", new_state, indices=None) - return True +# def _on_step(self) -> bool: +# if self.n_calls % self.opponent_interval == 0: +# new_state = random.choice(self.stages) +# print("\nCurrent state:", new_state) +# self.training_env.env_method("load_state", new_state, indices=None) +# return True # class StageIncreaseCallback(BaseCallback): -# def __init__(self, stages, stage_interval, save_dir, verbose=0): +# def __init__(self, stages, stage_interval, verbose=0): # super(StageIncreaseCallback, self).__init__(verbose) # self.stages = stages # self.stage_interval = stage_interval -# self.save_dir = save_dir # self.current_stage = 0 # def _on_step(self) -> bool: -# if self.n_calls % self.stage_interval == 0 and self.current_stage < len(self.stages) - 1: +# if self.n_calls % self.stage_interval == 0: # self.current_stage += 1 -# new_state = self.stages[self.current_stage] +# new_state = self.stages[self.current_stage % len(self.stages)] +# print("\nCurrent state:", new_state) # self.training_env.env_method("load_state", new_state, indices=None) -# self.model.save(os.path.join(self.save_dir, f"ppo_chunli_stage_{self.current_stage}.zip")) # return True def make_env(game, state): @@ -116,30 +115,34 @@ def main(): env, device="cuda", verbose=1, - n_steps=1024, - batch_size=64, - learning_rate=1e-4, + n_steps=8192, + batch_size=128, + learning_rate=1e-5, + target_kl=0.03, tensorboard_log="logs" ) # Set the save directory - save_dir = "trained_models_ryu_level_1_time_reward_small_random" + save_dir = "trained_models_ryu_level_1_time_reward_small_loop_continue" os.makedirs(save_dir, exist_ok=True) # Load the model from file - model_path = "trained_models_ryu_level_1_time_reward_small_continue/ppo_ryu_400000_steps.zip" + model_path = "trained_models_ryu_level_1_time_reward_small_loop/ppo_ryu_1200000_steps.zip" # Load model and modify the learning rate and entropy coefficient - # custom_objects = { - # "learning_rate": 0.0002 - # } - model = PPO.load(model_path, env=env, device="cuda")#, custom_objects=custom_objects) + custom_objects = { + "learning_rate": 1e-5, + "target_kl": 0.03, + } + model = PPO.load(model_path, env=env, device="cuda", custom_objects=custom_objects) # Set up callbacks - opponent_interval = 32768 # stage_interval * num_envs = total_steps_per_stage + # opponent_interval = 32768 # stage_interval * num_envs = total_steps_per_stage + # stage_interval = 400000 checkpoint_interval = 200000 # checkpoint_interval * num_envs = total_steps_per_checkpoint (Every 80 rounds) checkpoint_callback = CheckpointCallback(save_freq=checkpoint_interval, save_path=save_dir, name_prefix="ppo_ryu") - stage_increase_callback = RandomOpponentChangeCallback(state_stages, opponent_interval, save_dir) + # stage_increase_callback = RandomOpponentChangeCallback(state_stages, opponent_interval) + # stage_increase_callback = StageIncreaseCallback(state_stages, stage_interval) # model_params = { # 'n_steps': 5, @@ -160,14 +163,14 @@ def main(): sys.stdout = log_file model.learn( - total_timesteps=int(10000000), # total_timesteps = stage_interval * num_envs * num_stages (1120 rounds) - callback=[checkpoint_callback, stage_increase_callback] + total_timesteps=int(20000000), # total_timesteps = stage_interval * num_envs * num_stages (1120 rounds) + callback=[checkpoint_callback]#, stage_increase_callback] ) env.close() # Restore stdout sys.stdout = original_stdout - + # Save the final model model.save(os.path.join(save_dir, "ppo_sf2_ryu_final.zip")) diff --git a/004_rgb_stack_ram_based_reward_custom/trained_models_ryu_level_1_time_reward_small_loop/training_log.txt b/004_rgb_stack_ram_based_reward_custom/trained_models_ryu_level_1_time_reward_small_loop/training_log.txt new file mode 100644 index 0000000..0a732b5 --- /dev/null +++ b/004_rgb_stack_ram_based_reward_custom/trained_models_ryu_level_1_time_reward_small_loop/training_log.txt @@ -0,0 +1,4085 @@ +Logging to logs\PPO_17 +--------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.167 | +| time/ | | +| fps | 506 | +| iterations | 1 | +| time_elapsed | 16 | +| total_timesteps | 8192 | +--------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2e+03 | +| ep_rew_mean | 0.128 | +| time/ | | +| fps | 412 | +| iterations | 2 | +| time_elapsed | 39 | +| total_timesteps | 16384 | +| train/ | | +| approx_kl | 0.0233551 | +| clip_fraction | 0.172 | +| clip_range | 0.2 | +| entropy_loss | -8.31 | +| explained_variance | -0.481 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 10 | +| policy_gradient_loss | -0.0467 | +| value_loss | 0.0125 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.213 | +| time/ | | +| fps | 385 | +| iterations | 3 | +| time_elapsed | 63 | +| total_timesteps | 24576 | +| train/ | | +| approx_kl | 0.039828487 | +| clip_fraction | 0.339 | +| clip_range | 0.2 | +| entropy_loss | -8.3 | +| explained_variance | -0.842 | +| learning_rate | 0.0001 | +| loss | -0.122 | +| n_updates | 20 | +| policy_gradient_loss | -0.0795 | +| value_loss | 0.00306 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.81e+03 | +| ep_rew_mean | 0.227 | +| time/ | | +| fps | 376 | +| iterations | 4 | +| time_elapsed | 87 | +| total_timesteps | 32768 | +| train/ | | +| approx_kl | 0.052003123 | +| clip_fraction | 0.44 | +| clip_range | 0.2 | +| entropy_loss | -8.28 | +| explained_variance | -1.14 | +| learning_rate | 0.0001 | +| loss | -0.143 | +| n_updates | 30 | +| policy_gradient_loss | -0.0948 | +| value_loss | 0.00271 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.213 | +| time/ | | +| fps | 369 | +| iterations | 5 | +| time_elapsed | 110 | +| total_timesteps | 40960 | +| train/ | | +| approx_kl | 0.049883284 | +| clip_fraction | 0.423 | +| clip_range | 0.2 | +| entropy_loss | -8.25 | +| explained_variance | -0.609 | +| learning_rate | 0.0001 | +| loss | -0.121 | +| n_updates | 40 | +| policy_gradient_loss | -0.0851 | +| value_loss | 0.00191 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.227 | +| time/ | | +| fps | 357 | +| iterations | 6 | +| time_elapsed | 137 | +| total_timesteps | 49152 | +| train/ | | +| approx_kl | 0.05796663 | +| clip_fraction | 0.477 | +| clip_range | 0.2 | +| entropy_loss | -8.26 | +| explained_variance | -1.27 | +| learning_rate | 0.0001 | +| loss | -0.133 | +| n_updates | 50 | +| policy_gradient_loss | -0.0948 | +| value_loss | 0.00159 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.78e+03 | +| ep_rew_mean | 0.245 | +| time/ | | +| fps | 355 | +| iterations | 7 | +| time_elapsed | 161 | +| total_timesteps | 57344 | +| train/ | | +| approx_kl | 0.070097305 | +| clip_fraction | 0.513 | +| clip_range | 0.2 | +| entropy_loss | -8.24 | +| explained_variance | -1.08 | +| learning_rate | 0.0001 | +| loss | -0.124 | +| n_updates | 60 | +| policy_gradient_loss | -0.101 | +| value_loss | 0.00132 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.8e+03 | +| ep_rew_mean | 0.238 | +| time/ | | +| fps | 349 | +| iterations | 8 | +| time_elapsed | 187 | +| total_timesteps | 65536 | +| train/ | | +| approx_kl | 0.06797121 | +| clip_fraction | 0.5 | +| clip_range | 0.2 | +| entropy_loss | -8.23 | +| explained_variance | -1.54 | +| learning_rate | 0.0001 | +| loss | -0.128 | +| n_updates | 70 | +| policy_gradient_loss | -0.0956 | +| value_loss | 0.000931 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.8e+03 | +| ep_rew_mean | 0.248 | +| time/ | | +| fps | 348 | +| iterations | 9 | +| time_elapsed | 211 | +| total_timesteps | 73728 | +| train/ | | +| approx_kl | 0.07762927 | +| clip_fraction | 0.535 | +| clip_range | 0.2 | +| entropy_loss | -8.2 | +| explained_variance | -1.37 | +| learning_rate | 0.0001 | +| loss | -0.129 | +| n_updates | 80 | +| policy_gradient_loss | -0.101 | +| value_loss | 0.000775 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.81e+03 | +| ep_rew_mean | 0.246 | +| time/ | | +| fps | 346 | +| iterations | 10 | +| time_elapsed | 236 | +| total_timesteps | 81920 | +| train/ | | +| approx_kl | 0.071543425 | +| clip_fraction | 0.516 | +| clip_range | 0.2 | +| entropy_loss | -8.18 | +| explained_variance | -0.732 | +| learning_rate | 0.0001 | +| loss | -0.124 | +| n_updates | 90 | +| policy_gradient_loss | -0.0917 | +| value_loss | 0.000555 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.239 | +| time/ | | +| fps | 344 | +| iterations | 11 | +| time_elapsed | 261 | +| total_timesteps | 90112 | +| train/ | | +| approx_kl | 0.085165806 | +| clip_fraction | 0.539 | +| clip_range | 0.2 | +| entropy_loss | -8.2 | +| explained_variance | -0.661 | +| learning_rate | 0.0001 | +| loss | -0.144 | +| n_updates | 100 | +| policy_gradient_loss | -0.101 | +| value_loss | 0.000395 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.8e+03 | +| ep_rew_mean | 0.239 | +| time/ | | +| fps | 344 | +| iterations | 12 | +| time_elapsed | 285 | +| total_timesteps | 98304 | +| train/ | | +| approx_kl | 0.08736507 | +| clip_fraction | 0.551 | +| clip_range | 0.2 | +| entropy_loss | -8.13 | +| explained_variance | -0.644 | +| learning_rate | 0.0001 | +| loss | -0.132 | +| n_updates | 110 | +| policy_gradient_loss | -0.0937 | +| value_loss | 0.0003 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.8e+03 | +| ep_rew_mean | 0.239 | +| time/ | | +| fps | 344 | +| iterations | 13 | +| time_elapsed | 309 | +| total_timesteps | 106496 | +| train/ | | +| approx_kl | 0.092018105 | +| clip_fraction | 0.55 | +| clip_range | 0.2 | +| entropy_loss | -8.11 | +| explained_variance | -0.0294 | +| learning_rate | 0.0001 | +| loss | -0.121 | +| n_updates | 120 | +| policy_gradient_loss | -0.0863 | +| value_loss | 0.000298 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.81e+03 | +| ep_rew_mean | 0.249 | +| time/ | | +| fps | 343 | +| iterations | 14 | +| time_elapsed | 334 | +| total_timesteps | 114688 | +| train/ | | +| approx_kl | 0.10196912 | +| clip_fraction | 0.573 | +| clip_range | 0.2 | +| entropy_loss | -8.11 | +| explained_variance | -0.256 | +| learning_rate | 0.0001 | +| loss | -0.122 | +| n_updates | 130 | +| policy_gradient_loss | -0.0903 | +| value_loss | 0.000182 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.81e+03 | +| ep_rew_mean | 0.244 | +| time/ | | +| fps | 342 | +| iterations | 15 | +| time_elapsed | 358 | +| total_timesteps | 122880 | +| train/ | | +| approx_kl | 0.09918235 | +| clip_fraction | 0.558 | +| clip_range | 0.2 | +| entropy_loss | -8.08 | +| explained_variance | -0.101 | +| learning_rate | 0.0001 | +| loss | -0.1 | +| n_updates | 140 | +| policy_gradient_loss | -0.0817 | +| value_loss | 0.000221 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.81e+03 | +| ep_rew_mean | 0.243 | +| time/ | | +| fps | 340 | +| iterations | 16 | +| time_elapsed | 384 | +| total_timesteps | 131072 | +| train/ | | +| approx_kl | 0.08725329 | +| clip_fraction | 0.545 | +| clip_range | 0.2 | +| entropy_loss | -8.12 | +| explained_variance | -0.134 | +| learning_rate | 0.0001 | +| loss | -0.112 | +| n_updates | 150 | +| policy_gradient_loss | -0.0817 | +| value_loss | 0.000147 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.81e+03 | +| ep_rew_mean | 0.248 | +| time/ | | +| fps | 340 | +| iterations | 17 | +| time_elapsed | 408 | +| total_timesteps | 139264 | +| train/ | | +| approx_kl | 0.10089743 | +| clip_fraction | 0.557 | +| clip_range | 0.2 | +| entropy_loss | -8.11 | +| explained_variance | -0.111 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 160 | +| policy_gradient_loss | -0.0817 | +| value_loss | 0.00017 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.246 | +| time/ | | +| fps | 339 | +| iterations | 18 | +| time_elapsed | 434 | +| total_timesteps | 147456 | +| train/ | | +| approx_kl | 0.10161966 | +| clip_fraction | 0.559 | +| clip_range | 0.2 | +| entropy_loss | -8.1 | +| explained_variance | -0.0495 | +| learning_rate | 0.0001 | +| loss | -0.0993 | +| n_updates | 170 | +| policy_gradient_loss | -0.0802 | +| value_loss | 0.000216 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.82e+03 | +| ep_rew_mean | 0.247 | +| time/ | | +| fps | 338 | +| iterations | 19 | +| time_elapsed | 459 | +| total_timesteps | 155648 | +| train/ | | +| approx_kl | 0.09544012 | +| clip_fraction | 0.551 | +| clip_range | 0.2 | +| entropy_loss | -8.14 | +| explained_variance | -0.116 | +| learning_rate | 0.0001 | +| loss | -0.127 | +| n_updates | 180 | +| policy_gradient_loss | -0.0831 | +| value_loss | 0.000143 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.252 | +| time/ | | +| fps | 338 | +| iterations | 20 | +| time_elapsed | 484 | +| total_timesteps | 163840 | +| train/ | | +| approx_kl | 0.11530705 | +| clip_fraction | 0.591 | +| clip_range | 0.2 | +| entropy_loss | -8.09 | +| explained_variance | -0.0865 | +| learning_rate | 0.0001 | +| loss | -0.0872 | +| n_updates | 190 | +| policy_gradient_loss | -0.0827 | +| value_loss | 0.000195 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.247 | +| time/ | | +| fps | 336 | +| iterations | 21 | +| time_elapsed | 510 | +| total_timesteps | 172032 | +| train/ | | +| approx_kl | 0.096661106 | +| clip_fraction | 0.568 | +| clip_range | 0.2 | +| entropy_loss | -8.08 | +| explained_variance | -0.0365 | +| learning_rate | 0.0001 | +| loss | -0.0995 | +| n_updates | 200 | +| policy_gradient_loss | -0.081 | +| value_loss | 0.000167 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.8e+03 | +| ep_rew_mean | 0.24 | +| time/ | | +| fps | 335 | +| iterations | 22 | +| time_elapsed | 536 | +| total_timesteps | 180224 | +| train/ | | +| approx_kl | 0.10808745 | +| clip_fraction | 0.569 | +| clip_range | 0.2 | +| entropy_loss | -8.11 | +| explained_variance | -0.0931 | +| learning_rate | 0.0001 | +| loss | -0.115 | +| n_updates | 210 | +| policy_gradient_loss | -0.0835 | +| value_loss | 0.000135 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.78e+03 | +| ep_rew_mean | 0.24 | +| time/ | | +| fps | 334 | +| iterations | 23 | +| time_elapsed | 563 | +| total_timesteps | 188416 | +| train/ | | +| approx_kl | 0.10340094 | +| clip_fraction | 0.556 | +| clip_range | 0.2 | +| entropy_loss | -8.05 | +| explained_variance | -0.0686 | +| learning_rate | 0.0001 | +| loss | -0.107 | +| n_updates | 220 | +| policy_gradient_loss | -0.0712 | +| value_loss | 0.000276 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.25 | +| time/ | | +| fps | 335 | +| iterations | 24 | +| time_elapsed | 586 | +| total_timesteps | 196608 | +| train/ | | +| approx_kl | 0.119622864 | +| clip_fraction | 0.583 | +| clip_range | 0.2 | +| entropy_loss | -8.02 | +| explained_variance | -0.201 | +| learning_rate | 0.0001 | +| loss | -0.112 | +| n_updates | 230 | +| policy_gradient_loss | -0.086 | +| value_loss | 0.0002 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.81e+03 | +| ep_rew_mean | 0.239 | +| time/ | | +| fps | 334 | +| iterations | 25 | +| time_elapsed | 612 | +| total_timesteps | 204800 | +| train/ | | +| approx_kl | 0.123282276 | +| clip_fraction | 0.606 | +| clip_range | 0.2 | +| entropy_loss | -8.03 | +| explained_variance | -0.221 | +| learning_rate | 0.0001 | +| loss | -0.107 | +| n_updates | 240 | +| policy_gradient_loss | -0.0869 | +| value_loss | 0.00018 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.78e+03 | +| ep_rew_mean | 0.233 | +| time/ | | +| fps | 334 | +| iterations | 26 | +| time_elapsed | 636 | +| total_timesteps | 212992 | +| train/ | | +| approx_kl | 0.108209915 | +| clip_fraction | 0.584 | +| clip_range | 0.2 | +| entropy_loss | -8.06 | +| explained_variance | -0.176 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 250 | +| policy_gradient_loss | -0.0827 | +| value_loss | 0.000131 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.246 | +| time/ | | +| fps | 334 | +| iterations | 27 | +| time_elapsed | 660 | +| total_timesteps | 221184 | +| train/ | | +| approx_kl | 0.107802525 | +| clip_fraction | 0.579 | +| clip_range | 0.2 | +| entropy_loss | -8.08 | +| explained_variance | -0.144 | +| learning_rate | 0.0001 | +| loss | -0.097 | +| n_updates | 260 | +| policy_gradient_loss | -0.0757 | +| value_loss | 0.000193 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.227 | +| time/ | | +| fps | 334 | +| iterations | 28 | +| time_elapsed | 685 | +| total_timesteps | 229376 | +| train/ | | +| approx_kl | 0.112481356 | +| clip_fraction | 0.582 | +| clip_range | 0.2 | +| entropy_loss | -8.08 | +| explained_variance | -0.0883 | +| learning_rate | 0.0001 | +| loss | -0.111 | +| n_updates | 270 | +| policy_gradient_loss | -0.0858 | +| value_loss | 0.000197 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.215 | +| time/ | | +| fps | 334 | +| iterations | 29 | +| time_elapsed | 710 | +| total_timesteps | 237568 | +| train/ | | +| approx_kl | 0.12023298 | +| clip_fraction | 0.6 | +| clip_range | 0.2 | +| entropy_loss | -8.03 | +| explained_variance | -0.139 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 280 | +| policy_gradient_loss | -0.0833 | +| value_loss | 0.000218 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.221 | +| time/ | | +| fps | 333 | +| iterations | 30 | +| time_elapsed | 737 | +| total_timesteps | 245760 | +| train/ | | +| approx_kl | 0.10121855 | +| clip_fraction | 0.565 | +| clip_range | 0.2 | +| entropy_loss | -8.09 | +| explained_variance | -0.128 | +| learning_rate | 0.0001 | +| loss | -0.119 | +| n_updates | 290 | +| policy_gradient_loss | -0.0819 | +| value_loss | 0.000151 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.22 | +| time/ | | +| fps | 333 | +| iterations | 31 | +| time_elapsed | 761 | +| total_timesteps | 253952 | +| train/ | | +| approx_kl | 0.10692425 | +| clip_fraction | 0.573 | +| clip_range | 0.2 | +| entropy_loss | -8.06 | +| explained_variance | -0.179 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 300 | +| policy_gradient_loss | -0.082 | +| value_loss | 0.000132 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.226 | +| time/ | | +| fps | 333 | +| iterations | 32 | +| time_elapsed | 787 | +| total_timesteps | 262144 | +| train/ | | +| approx_kl | 0.10510109 | +| clip_fraction | 0.56 | +| clip_range | 0.2 | +| entropy_loss | -8.08 | +| explained_variance | -0.0864 | +| learning_rate | 0.0001 | +| loss | -0.0936 | +| n_updates | 310 | +| policy_gradient_loss | -0.0728 | +| value_loss | 0.000243 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.222 | +| time/ | | +| fps | 333 | +| iterations | 33 | +| time_elapsed | 811 | +| total_timesteps | 270336 | +| train/ | | +| approx_kl | 0.11695571 | +| clip_fraction | 0.59 | +| clip_range | 0.2 | +| entropy_loss | -8.07 | +| explained_variance | -0.177 | +| learning_rate | 0.0001 | +| loss | -0.122 | +| n_updates | 320 | +| policy_gradient_loss | -0.092 | +| value_loss | 0.000161 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.22 | +| time/ | | +| fps | 332 | +| iterations | 34 | +| time_elapsed | 836 | +| total_timesteps | 278528 | +| train/ | | +| approx_kl | 0.118134014 | +| clip_fraction | 0.576 | +| clip_range | 0.2 | +| entropy_loss | -8.04 | +| explained_variance | -0.0744 | +| learning_rate | 0.0001 | +| loss | -0.106 | +| n_updates | 330 | +| policy_gradient_loss | -0.0807 | +| value_loss | 0.000187 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.214 | +| time/ | | +| fps | 332 | +| iterations | 35 | +| time_elapsed | 863 | +| total_timesteps | 286720 | +| train/ | | +| approx_kl | 0.13625988 | +| clip_fraction | 0.617 | +| clip_range | 0.2 | +| entropy_loss | -8.02 | +| explained_variance | -0.128 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 340 | +| policy_gradient_loss | -0.0893 | +| value_loss | 0.000161 | +---------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.214 | +| time/ | | +| fps | 332 | +| iterations | 36 | +| time_elapsed | 888 | +| total_timesteps | 294912 | +| train/ | | +| approx_kl | 0.1347452 | +| clip_fraction | 0.6 | +| clip_range | 0.2 | +| entropy_loss | -8.06 | +| explained_variance | -0.123 | +| learning_rate | 0.0001 | +| loss | -0.105 | +| n_updates | 350 | +| policy_gradient_loss | -0.0848 | +| value_loss | 0.000171 | +--------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.207 | +| time/ | | +| fps | 330 | +| iterations | 37 | +| time_elapsed | 916 | +| total_timesteps | 303104 | +| train/ | | +| approx_kl | 0.14947379 | +| clip_fraction | 0.637 | +| clip_range | 0.2 | +| entropy_loss | -8 | +| explained_variance | -0.195 | +| learning_rate | 0.0001 | +| loss | -0.106 | +| n_updates | 360 | +| policy_gradient_loss | -0.0916 | +| value_loss | 0.000148 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.203 | +| time/ | | +| fps | 331 | +| iterations | 38 | +| time_elapsed | 940 | +| total_timesteps | 311296 | +| train/ | | +| approx_kl | 0.12558436 | +| clip_fraction | 0.597 | +| clip_range | 0.2 | +| entropy_loss | -8.01 | +| explained_variance | -0.0606 | +| learning_rate | 0.0001 | +| loss | -0.0927 | +| n_updates | 370 | +| policy_gradient_loss | -0.0787 | +| value_loss | 0.000179 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.195 | +| time/ | | +| fps | 330 | +| iterations | 39 | +| time_elapsed | 965 | +| total_timesteps | 319488 | +| train/ | | +| approx_kl | 0.13759162 | +| clip_fraction | 0.622 | +| clip_range | 0.2 | +| entropy_loss | -7.99 | +| explained_variance | -0.16 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 380 | +| policy_gradient_loss | -0.0907 | +| value_loss | 0.000148 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.186 | +| time/ | | +| fps | 330 | +| iterations | 40 | +| time_elapsed | 991 | +| total_timesteps | 327680 | +| train/ | | +| approx_kl | 0.13663715 | +| clip_fraction | 0.605 | +| clip_range | 0.2 | +| entropy_loss | -7.97 | +| explained_variance | -0.0873 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 390 | +| policy_gradient_loss | -0.0824 | +| value_loss | 0.000219 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.65e+03 | +| ep_rew_mean | 0.196 | +| time/ | | +| fps | 330 | +| iterations | 41 | +| time_elapsed | 1015 | +| total_timesteps | 335872 | +| train/ | | +| approx_kl | 0.13338977 | +| clip_fraction | 0.615 | +| clip_range | 0.2 | +| entropy_loss | -7.93 | +| explained_variance | -0.19 | +| learning_rate | 0.0001 | +| loss | -0.128 | +| n_updates | 400 | +| policy_gradient_loss | -0.0921 | +| value_loss | 0.00013 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | 0.206 | +| time/ | | +| fps | 330 | +| iterations | 42 | +| time_elapsed | 1039 | +| total_timesteps | 344064 | +| train/ | | +| approx_kl | 0.12986794 | +| clip_fraction | 0.603 | +| clip_range | 0.2 | +| entropy_loss | -7.96 | +| explained_variance | -0.0432 | +| learning_rate | 0.0001 | +| loss | -0.109 | +| n_updates | 410 | +| policy_gradient_loss | -0.0777 | +| value_loss | 0.000359 | +---------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.213 | +| time/ | | +| fps | 330 | +| iterations | 43 | +| time_elapsed | 1064 | +| total_timesteps | 352256 | +| train/ | | +| approx_kl | 0.146621 | +| clip_fraction | 0.625 | +| clip_range | 0.2 | +| entropy_loss | -7.96 | +| explained_variance | -0.208 | +| learning_rate | 0.0001 | +| loss | -0.135 | +| n_updates | 420 | +| policy_gradient_loss | -0.0951 | +| value_loss | 0.000224 | +-------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.218 | +| time/ | | +| fps | 330 | +| iterations | 44 | +| time_elapsed | 1090 | +| total_timesteps | 360448 | +| train/ | | +| approx_kl | 0.14493753 | +| clip_fraction | 0.63 | +| clip_range | 0.2 | +| entropy_loss | -7.96 | +| explained_variance | -0.196 | +| learning_rate | 0.0001 | +| loss | -0.117 | +| n_updates | 430 | +| policy_gradient_loss | -0.0863 | +| value_loss | 0.000181 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.222 | +| time/ | | +| fps | 330 | +| iterations | 45 | +| time_elapsed | 1115 | +| total_timesteps | 368640 | +| train/ | | +| approx_kl | 0.12921694 | +| clip_fraction | 0.61 | +| clip_range | 0.2 | +| entropy_loss | -7.96 | +| explained_variance | -0.0731 | +| learning_rate | 0.0001 | +| loss | -0.114 | +| n_updates | 440 | +| policy_gradient_loss | -0.0845 | +| value_loss | 0.000234 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.232 | +| time/ | | +| fps | 330 | +| iterations | 46 | +| time_elapsed | 1139 | +| total_timesteps | 376832 | +| train/ | | +| approx_kl | 0.11812104 | +| clip_fraction | 0.591 | +| clip_range | 0.2 | +| entropy_loss | -8 | +| explained_variance | -0.13 | +| learning_rate | 0.0001 | +| loss | -0.122 | +| n_updates | 450 | +| policy_gradient_loss | -0.0878 | +| value_loss | 0.000181 | +---------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.234 | +| time/ | | +| fps | 330 | +| iterations | 47 | +| time_elapsed | 1164 | +| total_timesteps | 385024 | +| train/ | | +| approx_kl | 0.158959 | +| clip_fraction | 0.64 | +| clip_range | 0.2 | +| entropy_loss | -7.95 | +| explained_variance | -0.0855 | +| learning_rate | 0.0001 | +| loss | -0.132 | +| n_updates | 460 | +| policy_gradient_loss | -0.0899 | +| value_loss | 0.000217 | +-------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.22 | +| time/ | | +| fps | 330 | +| iterations | 48 | +| time_elapsed | 1188 | +| total_timesteps | 393216 | +| train/ | | +| approx_kl | 0.14679159 | +| clip_fraction | 0.621 | +| clip_range | 0.2 | +| entropy_loss | -7.94 | +| explained_variance | -0.132 | +| learning_rate | 0.0001 | +| loss | -0.128 | +| n_updates | 470 | +| policy_gradient_loss | -0.0897 | +| value_loss | 0.000189 | +---------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.229 | +| time/ | | +| fps | 330 | +| iterations | 49 | +| time_elapsed | 1215 | +| total_timesteps | 401408 | +| train/ | | +| approx_kl | 0.14383 | +| clip_fraction | 0.621 | +| clip_range | 0.2 | +| entropy_loss | -7.93 | +| explained_variance | -0.168 | +| learning_rate | 0.0001 | +| loss | -0.115 | +| n_updates | 480 | +| policy_gradient_loss | -0.0879 | +| value_loss | 0.000118 | +-------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.229 | +| time/ | | +| fps | 330 | +| iterations | 50 | +| time_elapsed | 1240 | +| total_timesteps | 409600 | +| train/ | | +| approx_kl | 0.15739234 | +| clip_fraction | 0.629 | +| clip_range | 0.2 | +| entropy_loss | -7.91 | +| explained_variance | -0.156 | +| learning_rate | 0.0001 | +| loss | -0.1 | +| n_updates | 490 | +| policy_gradient_loss | -0.0837 | +| value_loss | 0.000151 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.229 | +| time/ | | +| fps | 329 | +| iterations | 51 | +| time_elapsed | 1267 | +| total_timesteps | 417792 | +| train/ | | +| approx_kl | 0.15298745 | +| clip_fraction | 0.632 | +| clip_range | 0.2 | +| entropy_loss | -7.86 | +| explained_variance | -0.146 | +| learning_rate | 0.0001 | +| loss | -0.108 | +| n_updates | 500 | +| policy_gradient_loss | -0.0839 | +| value_loss | 0.000146 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.223 | +| time/ | | +| fps | 329 | +| iterations | 52 | +| time_elapsed | 1292 | +| total_timesteps | 425984 | +| train/ | | +| approx_kl | 0.17114481 | +| clip_fraction | 0.639 | +| clip_range | 0.2 | +| entropy_loss | -7.88 | +| explained_variance | -0.089 | +| learning_rate | 0.0001 | +| loss | -0.119 | +| n_updates | 510 | +| policy_gradient_loss | -0.087 | +| value_loss | 0.000182 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.218 | +| time/ | | +| fps | 329 | +| iterations | 53 | +| time_elapsed | 1316 | +| total_timesteps | 434176 | +| train/ | | +| approx_kl | 0.14141671 | +| clip_fraction | 0.613 | +| clip_range | 0.2 | +| entropy_loss | -7.95 | +| explained_variance | -0.163 | +| learning_rate | 0.0001 | +| loss | -0.0924 | +| n_updates | 520 | +| policy_gradient_loss | -0.0818 | +| value_loss | 0.000161 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.228 | +| time/ | | +| fps | 329 | +| iterations | 54 | +| time_elapsed | 1343 | +| total_timesteps | 442368 | +| train/ | | +| approx_kl | 0.13799667 | +| clip_fraction | 0.62 | +| clip_range | 0.2 | +| entropy_loss | -7.94 | +| explained_variance | -0.158 | +| learning_rate | 0.0001 | +| loss | -0.0983 | +| n_updates | 530 | +| policy_gradient_loss | -0.0813 | +| value_loss | 0.000171 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.238 | +| time/ | | +| fps | 329 | +| iterations | 55 | +| time_elapsed | 1367 | +| total_timesteps | 450560 | +| train/ | | +| approx_kl | 0.16143854 | +| clip_fraction | 0.641 | +| clip_range | 0.2 | +| entropy_loss | -7.88 | +| explained_variance | -0.102 | +| learning_rate | 0.0001 | +| loss | -0.116 | +| n_updates | 540 | +| policy_gradient_loss | -0.0861 | +| value_loss | 0.000243 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.233 | +| time/ | | +| fps | 329 | +| iterations | 56 | +| time_elapsed | 1393 | +| total_timesteps | 458752 | +| train/ | | +| approx_kl | 0.15157114 | +| clip_fraction | 0.628 | +| clip_range | 0.2 | +| entropy_loss | -7.9 | +| explained_variance | -0.0335 | +| learning_rate | 0.0001 | +| loss | -0.115 | +| n_updates | 550 | +| policy_gradient_loss | -0.0839 | +| value_loss | 0.000276 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.236 | +| time/ | | +| fps | 329 | +| iterations | 57 | +| time_elapsed | 1417 | +| total_timesteps | 466944 | +| train/ | | +| approx_kl | 0.16653106 | +| clip_fraction | 0.649 | +| clip_range | 0.2 | +| entropy_loss | -7.84 | +| explained_variance | -0.128 | +| learning_rate | 0.0001 | +| loss | -0.132 | +| n_updates | 560 | +| policy_gradient_loss | -0.089 | +| value_loss | 0.000197 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.249 | +| time/ | | +| fps | 329 | +| iterations | 58 | +| time_elapsed | 1442 | +| total_timesteps | 475136 | +| train/ | | +| approx_kl | 0.13777554 | +| clip_fraction | 0.614 | +| clip_range | 0.2 | +| entropy_loss | -7.93 | +| explained_variance | -0.000303 | +| learning_rate | 0.0001 | +| loss | -0.106 | +| n_updates | 570 | +| policy_gradient_loss | -0.082 | +| value_loss | 0.000207 | +---------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.265 | +| time/ | | +| fps | 329 | +| iterations | 59 | +| time_elapsed | 1468 | +| total_timesteps | 483328 | +| train/ | | +| approx_kl | 0.1691464 | +| clip_fraction | 0.647 | +| clip_range | 0.2 | +| entropy_loss | -7.9 | +| explained_variance | -0.105 | +| learning_rate | 0.0001 | +| loss | -0.107 | +| n_updates | 580 | +| policy_gradient_loss | -0.0907 | +| value_loss | 0.000215 | +--------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.272 | +| time/ | | +| fps | 329 | +| iterations | 60 | +| time_elapsed | 1491 | +| total_timesteps | 491520 | +| train/ | | +| approx_kl | 0.16887665 | +| clip_fraction | 0.653 | +| clip_range | 0.2 | +| entropy_loss | -7.83 | +| explained_variance | -0.135 | +| learning_rate | 0.0001 | +| loss | -0.107 | +| n_updates | 590 | +| policy_gradient_loss | -0.0888 | +| value_loss | 0.000238 | +---------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.271 | +| time/ | | +| fps | 329 | +| iterations | 61 | +| time_elapsed | 1516 | +| total_timesteps | 499712 | +| train/ | | +| approx_kl | 0.1684309 | +| clip_fraction | 0.652 | +| clip_range | 0.2 | +| entropy_loss | -7.89 | +| explained_variance | -0.212 | +| learning_rate | 0.0001 | +| loss | -0.108 | +| n_updates | 600 | +| policy_gradient_loss | -0.0925 | +| value_loss | 0.000152 | +--------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.272 | +| time/ | | +| fps | 329 | +| iterations | 62 | +| time_elapsed | 1540 | +| total_timesteps | 507904 | +| train/ | | +| approx_kl | 0.17604174 | +| clip_fraction | 0.657 | +| clip_range | 0.2 | +| entropy_loss | -7.84 | +| explained_variance | -0.151 | +| learning_rate | 0.0001 | +| loss | -0.112 | +| n_updates | 610 | +| policy_gradient_loss | -0.09 | +| value_loss | 0.000174 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.271 | +| time/ | | +| fps | 329 | +| iterations | 63 | +| time_elapsed | 1567 | +| total_timesteps | 516096 | +| train/ | | +| approx_kl | 0.16294369 | +| clip_fraction | 0.629 | +| clip_range | 0.2 | +| entropy_loss | -7.88 | +| explained_variance | -0.0733 | +| learning_rate | 0.0001 | +| loss | -0.123 | +| n_updates | 620 | +| policy_gradient_loss | -0.0852 | +| value_loss | 0.000176 | +---------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.78e+03 | +| ep_rew_mean | 0.255 | +| time/ | | +| fps | 329 | +| iterations | 64 | +| time_elapsed | 1592 | +| total_timesteps | 524288 | +| train/ | | +| approx_kl | 0.1955277 | +| clip_fraction | 0.659 | +| clip_range | 0.2 | +| entropy_loss | -7.83 | +| explained_variance | -0.0586 | +| learning_rate | 0.0001 | +| loss | -0.122 | +| n_updates | 630 | +| policy_gradient_loss | -0.0864 | +| value_loss | 0.000193 | +--------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.259 | +| time/ | | +| fps | 329 | +| iterations | 65 | +| time_elapsed | 1617 | +| total_timesteps | 532480 | +| train/ | | +| approx_kl | 0.19380729 | +| clip_fraction | 0.663 | +| clip_range | 0.2 | +| entropy_loss | -7.77 | +| explained_variance | -0.202 | +| learning_rate | 0.0001 | +| loss | -0.112 | +| n_updates | 640 | +| policy_gradient_loss | -0.0921 | +| value_loss | 0.000149 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.259 | +| time/ | | +| fps | 328 | +| iterations | 66 | +| time_elapsed | 1644 | +| total_timesteps | 540672 | +| train/ | | +| approx_kl | 0.17698011 | +| clip_fraction | 0.647 | +| clip_range | 0.2 | +| entropy_loss | -7.84 | +| explained_variance | -0.0683 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 650 | +| policy_gradient_loss | -0.0877 | +| value_loss | 0.000232 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.259 | +| time/ | | +| fps | 328 | +| iterations | 67 | +| time_elapsed | 1668 | +| total_timesteps | 548864 | +| train/ | | +| approx_kl | 0.17084396 | +| clip_fraction | 0.651 | +| clip_range | 0.2 | +| entropy_loss | -7.85 | +| explained_variance | -0.223 | +| learning_rate | 0.0001 | +| loss | -0.129 | +| n_updates | 660 | +| policy_gradient_loss | -0.095 | +| value_loss | 0.000201 | +---------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.78e+03 | +| ep_rew_mean | 0.255 | +| time/ | | +| fps | 328 | +| iterations | 68 | +| time_elapsed | 1695 | +| total_timesteps | 557056 | +| train/ | | +| approx_kl | 0.1717097 | +| clip_fraction | 0.648 | +| clip_range | 0.2 | +| entropy_loss | -7.85 | +| explained_variance | -0.22 | +| learning_rate | 0.0001 | +| loss | -0.114 | +| n_updates | 670 | +| policy_gradient_loss | -0.0871 | +| value_loss | 0.000179 | +--------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.78e+03 | +| ep_rew_mean | 0.252 | +| time/ | | +| fps | 328 | +| iterations | 69 | +| time_elapsed | 1719 | +| total_timesteps | 565248 | +| train/ | | +| approx_kl | 0.17255518 | +| clip_fraction | 0.649 | +| clip_range | 0.2 | +| entropy_loss | -7.87 | +| explained_variance | -0.171 | +| learning_rate | 0.0001 | +| loss | -0.106 | +| n_updates | 680 | +| policy_gradient_loss | -0.089 | +| value_loss | 0.000126 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.78e+03 | +| ep_rew_mean | 0.254 | +| time/ | | +| fps | 328 | +| iterations | 70 | +| time_elapsed | 1744 | +| total_timesteps | 573440 | +| train/ | | +| approx_kl | 0.18114299 | +| clip_fraction | 0.652 | +| clip_range | 0.2 | +| entropy_loss | -7.83 | +| explained_variance | -0.0566 | +| learning_rate | 0.0001 | +| loss | -0.12 | +| n_updates | 690 | +| policy_gradient_loss | -0.0885 | +| value_loss | 0.000177 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.78e+03 | +| ep_rew_mean | 0.258 | +| time/ | | +| fps | 328 | +| iterations | 71 | +| time_elapsed | 1769 | +| total_timesteps | 581632 | +| train/ | | +| approx_kl | 0.15088078 | +| clip_fraction | 0.636 | +| clip_range | 0.2 | +| entropy_loss | -7.96 | +| explained_variance | -0.18 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 700 | +| policy_gradient_loss | -0.0904 | +| value_loss | 0.000127 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.264 | +| time/ | | +| fps | 328 | +| iterations | 72 | +| time_elapsed | 1793 | +| total_timesteps | 589824 | +| train/ | | +| approx_kl | 0.16075188 | +| clip_fraction | 0.636 | +| clip_range | 0.2 | +| entropy_loss | -7.88 | +| explained_variance | -0.14 | +| learning_rate | 0.0001 | +| loss | -0.0992 | +| n_updates | 710 | +| policy_gradient_loss | -0.0869 | +| value_loss | 0.000166 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.263 | +| time/ | | +| fps | 328 | +| iterations | 73 | +| time_elapsed | 1820 | +| total_timesteps | 598016 | +| train/ | | +| approx_kl | 0.16291288 | +| clip_fraction | 0.649 | +| clip_range | 0.2 | +| entropy_loss | -7.81 | +| explained_variance | -0.087 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 720 | +| policy_gradient_loss | -0.0861 | +| value_loss | 0.000172 | +---------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.8e+03 | +| ep_rew_mean | 0.258 | +| time/ | | +| fps | 328 | +| iterations | 74 | +| time_elapsed | 1844 | +| total_timesteps | 606208 | +| train/ | | +| approx_kl | 0.1486624 | +| clip_fraction | 0.623 | +| clip_range | 0.2 | +| entropy_loss | -7.87 | +| explained_variance | -0.164 | +| learning_rate | 0.0001 | +| loss | -0.0875 | +| n_updates | 730 | +| policy_gradient_loss | -0.0855 | +| value_loss | 0.000191 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.267 | +| time/ | | +| fps | 328 | +| iterations | 75 | +| time_elapsed | 1870 | +| total_timesteps | 614400 | +| train/ | | +| approx_kl | 0.1650352 | +| clip_fraction | 0.643 | +| clip_range | 0.2 | +| entropy_loss | -7.83 | +| explained_variance | -0.103 | +| learning_rate | 0.0001 | +| loss | -0.122 | +| n_updates | 740 | +| policy_gradient_loss | -0.0818 | +| value_loss | 0.000234 | +--------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.277 | +| time/ | | +| fps | 328 | +| iterations | 76 | +| time_elapsed | 1894 | +| total_timesteps | 622592 | +| train/ | | +| approx_kl | 0.19676343 | +| clip_fraction | 0.662 | +| clip_range | 0.2 | +| entropy_loss | -7.82 | +| explained_variance | -0.111 | +| learning_rate | 0.0001 | +| loss | -0.114 | +| n_updates | 750 | +| policy_gradient_loss | -0.0883 | +| value_loss | 0.000284 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.78e+03 | +| ep_rew_mean | 0.272 | +| time/ | | +| fps | 328 | +| iterations | 77 | +| time_elapsed | 1919 | +| total_timesteps | 630784 | +| train/ | | +| approx_kl | 0.15633823 | +| clip_fraction | 0.626 | +| clip_range | 0.2 | +| entropy_loss | -7.84 | +| explained_variance | 0.00948 | +| learning_rate | 0.0001 | +| loss | -0.112 | +| n_updates | 760 | +| policy_gradient_loss | -0.0894 | +| value_loss | 0.000286 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.78e+03 | +| ep_rew_mean | 0.271 | +| time/ | | +| fps | 328 | +| iterations | 78 | +| time_elapsed | 1945 | +| total_timesteps | 638976 | +| train/ | | +| approx_kl | 0.19217956 | +| clip_fraction | 0.658 | +| clip_range | 0.2 | +| entropy_loss | -7.8 | +| explained_variance | -0.102 | +| learning_rate | 0.0001 | +| loss | -0.126 | +| n_updates | 770 | +| policy_gradient_loss | -0.0887 | +| value_loss | 0.000278 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.266 | +| time/ | | +| fps | 328 | +| iterations | 79 | +| time_elapsed | 1969 | +| total_timesteps | 647168 | +| train/ | | +| approx_kl | 0.19068094 | +| clip_fraction | 0.664 | +| clip_range | 0.2 | +| entropy_loss | -7.83 | +| explained_variance | -0.188 | +| learning_rate | 0.0001 | +| loss | -0.119 | +| n_updates | 780 | +| policy_gradient_loss | -0.0959 | +| value_loss | 0.000234 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.26 | +| time/ | | +| fps | 328 | +| iterations | 80 | +| time_elapsed | 1996 | +| total_timesteps | 655360 | +| train/ | | +| approx_kl | 0.18527758 | +| clip_fraction | 0.65 | +| clip_range | 0.2 | +| entropy_loss | -7.8 | +| explained_variance | -0.203 | +| learning_rate | 0.0001 | +| loss | -0.11 | +| n_updates | 790 | +| policy_gradient_loss | -0.0913 | +| value_loss | 0.000171 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.78e+03 | +| ep_rew_mean | 0.263 | +| time/ | | +| fps | 328 | +| iterations | 81 | +| time_elapsed | 2019 | +| total_timesteps | 663552 | +| train/ | | +| approx_kl | 0.17044926 | +| clip_fraction | 0.643 | +| clip_range | 0.2 | +| entropy_loss | -7.78 | +| explained_variance | -0.124 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 800 | +| policy_gradient_loss | -0.0854 | +| value_loss | 0.000204 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.263 | +| time/ | | +| fps | 328 | +| iterations | 82 | +| time_elapsed | 2045 | +| total_timesteps | 671744 | +| train/ | | +| approx_kl | 0.18568517 | +| clip_fraction | 0.659 | +| clip_range | 0.2 | +| entropy_loss | -7.78 | +| explained_variance | -0.0454 | +| learning_rate | 0.0001 | +| loss | -0.105 | +| n_updates | 810 | +| policy_gradient_loss | -0.0884 | +| value_loss | 0.000199 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.78e+03 | +| ep_rew_mean | 0.266 | +| time/ | | +| fps | 328 | +| iterations | 83 | +| time_elapsed | 2069 | +| total_timesteps | 679936 | +| train/ | | +| approx_kl | 0.18056011 | +| clip_fraction | 0.649 | +| clip_range | 0.2 | +| entropy_loss | -7.82 | +| explained_variance | 0.0228 | +| learning_rate | 0.0001 | +| loss | -0.115 | +| n_updates | 820 | +| policy_gradient_loss | -0.0878 | +| value_loss | 0.000179 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.78e+03 | +| ep_rew_mean | 0.258 | +| time/ | | +| fps | 328 | +| iterations | 84 | +| time_elapsed | 2094 | +| total_timesteps | 688128 | +| train/ | | +| approx_kl | 0.16859269 | +| clip_fraction | 0.639 | +| clip_range | 0.2 | +| entropy_loss | -7.8 | +| explained_variance | -0.108 | +| learning_rate | 0.0001 | +| loss | -0.122 | +| n_updates | 830 | +| policy_gradient_loss | -0.0893 | +| value_loss | 0.000197 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.257 | +| time/ | | +| fps | 328 | +| iterations | 85 | +| time_elapsed | 2119 | +| total_timesteps | 696320 | +| train/ | | +| approx_kl | 0.17766786 | +| clip_fraction | 0.653 | +| clip_range | 0.2 | +| entropy_loss | -7.84 | +| explained_variance | -0.0689 | +| learning_rate | 0.0001 | +| loss | -0.13 | +| n_updates | 840 | +| policy_gradient_loss | -0.0882 | +| value_loss | 0.000177 | +---------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.261 | +| time/ | | +| fps | 328 | +| iterations | 86 | +| time_elapsed | 2144 | +| total_timesteps | 704512 | +| train/ | | +| approx_kl | 0.1845145 | +| clip_fraction | 0.664 | +| clip_range | 0.2 | +| entropy_loss | -7.76 | +| explained_variance | -0.169 | +| learning_rate | 0.0001 | +| loss | -0.109 | +| n_updates | 850 | +| policy_gradient_loss | -0.0915 | +| value_loss | 0.000195 | +--------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.256 | +| time/ | | +| fps | 328 | +| iterations | 87 | +| time_elapsed | 2170 | +| total_timesteps | 712704 | +| train/ | | +| approx_kl | 0.18166707 | +| clip_fraction | 0.656 | +| clip_range | 0.2 | +| entropy_loss | -7.84 | +| explained_variance | -0.0554 | +| learning_rate | 0.0001 | +| loss | -0.12 | +| n_updates | 860 | +| policy_gradient_loss | -0.0864 | +| value_loss | 0.000173 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.257 | +| time/ | | +| fps | 328 | +| iterations | 88 | +| time_elapsed | 2194 | +| total_timesteps | 720896 | +| train/ | | +| approx_kl | 0.21389326 | +| clip_fraction | 0.677 | +| clip_range | 0.2 | +| entropy_loss | -7.81 | +| explained_variance | -0.167 | +| learning_rate | 0.0001 | +| loss | -0.11 | +| n_updates | 870 | +| policy_gradient_loss | -0.0937 | +| value_loss | 0.000153 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.258 | +| time/ | | +| fps | 328 | +| iterations | 89 | +| time_elapsed | 2218 | +| total_timesteps | 729088 | +| train/ | | +| approx_kl | 0.16689664 | +| clip_fraction | 0.641 | +| clip_range | 0.2 | +| entropy_loss | -7.86 | +| explained_variance | -0.0931 | +| learning_rate | 0.0001 | +| loss | -0.11 | +| n_updates | 880 | +| policy_gradient_loss | -0.0839 | +| value_loss | 0.000256 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.262 | +| time/ | | +| fps | 328 | +| iterations | 90 | +| time_elapsed | 2242 | +| total_timesteps | 737280 | +| train/ | | +| approx_kl | 0.16718942 | +| clip_fraction | 0.654 | +| clip_range | 0.2 | +| entropy_loss | -7.86 | +| explained_variance | -0.221 | +| learning_rate | 0.0001 | +| loss | -0.123 | +| n_updates | 890 | +| policy_gradient_loss | -0.094 | +| value_loss | 0.000147 | +---------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.258 | +| time/ | | +| fps | 328 | +| iterations | 91 | +| time_elapsed | 2267 | +| total_timesteps | 745472 | +| train/ | | +| approx_kl | 0.1912153 | +| clip_fraction | 0.667 | +| clip_range | 0.2 | +| entropy_loss | -7.75 | +| explained_variance | -0.196 | +| learning_rate | 0.0001 | +| loss | -0.113 | +| n_updates | 900 | +| policy_gradient_loss | -0.088 | +| value_loss | 0.000163 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.253 | +| time/ | | +| fps | 328 | +| iterations | 92 | +| time_elapsed | 2294 | +| total_timesteps | 753664 | +| train/ | | +| approx_kl | 0.1694367 | +| clip_fraction | 0.64 | +| clip_range | 0.2 | +| entropy_loss | -7.87 | +| explained_variance | -0.112 | +| learning_rate | 0.0001 | +| loss | -0.0953 | +| n_updates | 910 | +| policy_gradient_loss | -0.081 | +| value_loss | 0.000239 | +--------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.253 | +| time/ | | +| fps | 328 | +| iterations | 93 | +| time_elapsed | 2319 | +| total_timesteps | 761856 | +| train/ | | +| approx_kl | 0.19499661 | +| clip_fraction | 0.67 | +| clip_range | 0.2 | +| entropy_loss | -7.85 | +| explained_variance | -0.212 | +| learning_rate | 0.0001 | +| loss | -0.088 | +| n_updates | 920 | +| policy_gradient_loss | -0.0918 | +| value_loss | 0.000185 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.248 | +| time/ | | +| fps | 328 | +| iterations | 94 | +| time_elapsed | 2345 | +| total_timesteps | 770048 | +| train/ | | +| approx_kl | 0.16961744 | +| clip_fraction | 0.643 | +| clip_range | 0.2 | +| entropy_loss | -7.85 | +| explained_variance | -0.127 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 930 | +| policy_gradient_loss | -0.0886 | +| value_loss | 0.000186 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.24 | +| time/ | | +| fps | 328 | +| iterations | 95 | +| time_elapsed | 2371 | +| total_timesteps | 778240 | +| train/ | | +| approx_kl | 0.15027705 | +| clip_fraction | 0.636 | +| clip_range | 0.2 | +| entropy_loss | -7.83 | +| explained_variance | -0.224 | +| learning_rate | 0.0001 | +| loss | -0.0951 | +| n_updates | 940 | +| policy_gradient_loss | -0.0913 | +| value_loss | 0.000116 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.232 | +| time/ | | +| fps | 328 | +| iterations | 96 | +| time_elapsed | 2396 | +| total_timesteps | 786432 | +| train/ | | +| approx_kl | 0.22312313 | +| clip_fraction | 0.676 | +| clip_range | 0.2 | +| entropy_loss | -7.81 | +| explained_variance | -0.143 | +| learning_rate | 0.0001 | +| loss | -0.141 | +| n_updates | 950 | +| policy_gradient_loss | -0.0913 | +| value_loss | 0.000132 | +---------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.212 | +| time/ | | +| fps | 328 | +| iterations | 97 | +| time_elapsed | 2421 | +| total_timesteps | 794624 | +| train/ | | +| approx_kl | 0.1740413 | +| clip_fraction | 0.654 | +| clip_range | 0.2 | +| entropy_loss | -7.86 | +| explained_variance | -0.103 | +| learning_rate | 0.0001 | +| loss | -0.137 | +| n_updates | 960 | +| policy_gradient_loss | -0.0877 | +| value_loss | 0.000135 | +--------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.205 | +| time/ | | +| fps | 328 | +| iterations | 98 | +| time_elapsed | 2446 | +| total_timesteps | 802816 | +| train/ | | +| approx_kl | 0.19709359 | +| clip_fraction | 0.655 | +| clip_range | 0.2 | +| entropy_loss | -7.78 | +| explained_variance | -0.042 | +| learning_rate | 0.0001 | +| loss | -0.123 | +| n_updates | 970 | +| policy_gradient_loss | -0.0818 | +| value_loss | 0.000202 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.215 | +| time/ | | +| fps | 328 | +| iterations | 99 | +| time_elapsed | 2471 | +| total_timesteps | 811008 | +| train/ | | +| approx_kl | 0.19038029 | +| clip_fraction | 0.665 | +| clip_range | 0.2 | +| entropy_loss | -7.79 | +| explained_variance | -0.273 | +| learning_rate | 0.0001 | +| loss | -0.135 | +| n_updates | 980 | +| policy_gradient_loss | -0.0947 | +| value_loss | 0.00016 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.212 | +| time/ | | +| fps | 328 | +| iterations | 100 | +| time_elapsed | 2497 | +| total_timesteps | 819200 | +| train/ | | +| approx_kl | 0.18045267 | +| clip_fraction | 0.658 | +| clip_range | 0.2 | +| entropy_loss | -7.74 | +| explained_variance | -0.158 | +| learning_rate | 0.0001 | +| loss | -0.0954 | +| n_updates | 990 | +| policy_gradient_loss | -0.0921 | +| value_loss | 0.000139 | +---------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.219 | +| time/ | | +| fps | 328 | +| iterations | 101 | +| time_elapsed | 2522 | +| total_timesteps | 827392 | +| train/ | | +| approx_kl | 0.1898045 | +| clip_fraction | 0.65 | +| clip_range | 0.2 | +| entropy_loss | -7.82 | +| explained_variance | -0.12 | +| learning_rate | 0.0001 | +| loss | -0.118 | +| n_updates | 1000 | +| policy_gradient_loss | -0.0878 | +| value_loss | 0.000144 | +--------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.82e+03 | +| ep_rew_mean | 0.218 | +| time/ | | +| fps | 327 | +| iterations | 102 | +| time_elapsed | 2548 | +| total_timesteps | 835584 | +| train/ | | +| approx_kl | 0.21912768 | +| clip_fraction | 0.67 | +| clip_range | 0.2 | +| entropy_loss | -7.79 | +| explained_variance | -0.211 | +| learning_rate | 0.0001 | +| loss | -0.0981 | +| n_updates | 1010 | +| policy_gradient_loss | -0.0879 | +| value_loss | 0.000143 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.8e+03 | +| ep_rew_mean | 0.211 | +| time/ | | +| fps | 327 | +| iterations | 103 | +| time_elapsed | 2573 | +| total_timesteps | 843776 | +| train/ | | +| approx_kl | 0.21182102 | +| clip_fraction | 0.666 | +| clip_range | 0.2 | +| entropy_loss | -7.79 | +| explained_variance | -0.219 | +| learning_rate | 0.0001 | +| loss | -0.126 | +| n_updates | 1020 | +| policy_gradient_loss | -0.0898 | +| value_loss | 0.000169 | +---------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.8e+03 | +| ep_rew_mean | 0.219 | +| time/ | | +| fps | 327 | +| iterations | 104 | +| time_elapsed | 2598 | +| total_timesteps | 851968 | +| train/ | | +| approx_kl | 0.209546 | +| clip_fraction | 0.661 | +| clip_range | 0.2 | +| entropy_loss | -7.77 | +| explained_variance | -0.0714 | +| learning_rate | 0.0001 | +| loss | -0.114 | +| n_updates | 1030 | +| policy_gradient_loss | -0.0866 | +| value_loss | 0.000201 | +-------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.219 | +| time/ | | +| fps | 327 | +| iterations | 105 | +| time_elapsed | 2622 | +| total_timesteps | 860160 | +| train/ | | +| approx_kl | 0.19882202 | +| clip_fraction | 0.675 | +| clip_range | 0.2 | +| entropy_loss | -7.77 | +| explained_variance | -0.128 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 1040 | +| policy_gradient_loss | -0.0935 | +| value_loss | 0.000221 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.78e+03 | +| ep_rew_mean | 0.225 | +| time/ | | +| fps | 327 | +| iterations | 106 | +| time_elapsed | 2649 | +| total_timesteps | 868352 | +| train/ | | +| approx_kl | 0.18524104 | +| clip_fraction | 0.657 | +| clip_range | 0.2 | +| entropy_loss | -7.84 | +| explained_variance | -0.119 | +| learning_rate | 0.0001 | +| loss | -0.112 | +| n_updates | 1050 | +| policy_gradient_loss | -0.0903 | +| value_loss | 0.000232 | +---------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.8e+03 | +| ep_rew_mean | 0.229 | +| time/ | | +| fps | 327 | +| iterations | 107 | +| time_elapsed | 2674 | +| total_timesteps | 876544 | +| train/ | | +| approx_kl | 0.2398526 | +| clip_fraction | 0.688 | +| clip_range | 0.2 | +| entropy_loss | -7.74 | +| explained_variance | -0.173 | +| learning_rate | 0.0001 | +| loss | -0.129 | +| n_updates | 1060 | +| policy_gradient_loss | -0.1 | +| value_loss | 0.000221 | +--------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.22 | +| time/ | | +| fps | 327 | +| iterations | 108 | +| time_elapsed | 2699 | +| total_timesteps | 884736 | +| train/ | | +| approx_kl | 0.22406499 | +| clip_fraction | 0.685 | +| clip_range | 0.2 | +| entropy_loss | -7.8 | +| explained_variance | -0.191 | +| learning_rate | 0.0001 | +| loss | -0.132 | +| n_updates | 1070 | +| policy_gradient_loss | -0.0971 | +| value_loss | 0.000139 | +---------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.81e+03 | +| ep_rew_mean | 0.223 | +| time/ | | +| fps | 327 | +| iterations | 109 | +| time_elapsed | 2725 | +| total_timesteps | 892928 | +| train/ | | +| approx_kl | 0.2099807 | +| clip_fraction | 0.671 | +| clip_range | 0.2 | +| entropy_loss | -7.82 | +| explained_variance | -0.0304 | +| learning_rate | 0.0001 | +| loss | -0.105 | +| n_updates | 1080 | +| policy_gradient_loss | -0.0865 | +| value_loss | 0.000183 | +--------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.225 | +| time/ | | +| fps | 327 | +| iterations | 110 | +| time_elapsed | 2750 | +| total_timesteps | 901120 | +| train/ | | +| approx_kl | 0.18864596 | +| clip_fraction | 0.655 | +| clip_range | 0.2 | +| entropy_loss | -7.81 | +| explained_variance | -0.093 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 1090 | +| policy_gradient_loss | -0.0909 | +| value_loss | 0.000122 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.8e+03 | +| ep_rew_mean | 0.213 | +| time/ | | +| fps | 327 | +| iterations | 111 | +| time_elapsed | 2776 | +| total_timesteps | 909312 | +| train/ | | +| approx_kl | 0.16975819 | +| clip_fraction | 0.646 | +| clip_range | 0.2 | +| entropy_loss | -7.79 | +| explained_variance | -0.0162 | +| learning_rate | 0.0001 | +| loss | -0.0948 | +| n_updates | 1100 | +| policy_gradient_loss | -0.0838 | +| value_loss | 0.000166 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.215 | +| time/ | | +| fps | 327 | +| iterations | 112 | +| time_elapsed | 2801 | +| total_timesteps | 917504 | +| train/ | | +| approx_kl | 0.22776508 | +| clip_fraction | 0.696 | +| clip_range | 0.2 | +| entropy_loss | -7.7 | +| explained_variance | -0.186 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 1110 | +| policy_gradient_loss | -0.0922 | +| value_loss | 0.000222 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.214 | +| time/ | | +| fps | 327 | +| iterations | 113 | +| time_elapsed | 2826 | +| total_timesteps | 925696 | +| train/ | | +| approx_kl | 0.20033897 | +| clip_fraction | 0.676 | +| clip_range | 0.2 | +| entropy_loss | -7.81 | +| explained_variance | -0.13 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 1120 | +| policy_gradient_loss | -0.0948 | +| value_loss | 0.000187 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.82e+03 | +| ep_rew_mean | 0.229 | +| time/ | | +| fps | 327 | +| iterations | 114 | +| time_elapsed | 2851 | +| total_timesteps | 933888 | +| train/ | | +| approx_kl | 0.21014345 | +| clip_fraction | 0.678 | +| clip_range | 0.2 | +| entropy_loss | -7.83 | +| explained_variance | -0.191 | +| learning_rate | 0.0001 | +| loss | -0.132 | +| n_updates | 1130 | +| policy_gradient_loss | -0.0961 | +| value_loss | 0.000153 | +---------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.229 | +| time/ | | +| fps | 327 | +| iterations | 115 | +| time_elapsed | 2876 | +| total_timesteps | 942080 | +| train/ | | +| approx_kl | 0.1852269 | +| clip_fraction | 0.655 | +| clip_range | 0.2 | +| entropy_loss | -7.76 | +| explained_variance | -0.125 | +| learning_rate | 0.0001 | +| loss | -0.117 | +| n_updates | 1140 | +| policy_gradient_loss | -0.0842 | +| value_loss | 0.000139 | +--------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.226 | +| time/ | | +| fps | 327 | +| iterations | 116 | +| time_elapsed | 2902 | +| total_timesteps | 950272 | +| train/ | | +| approx_kl | 0.20463315 | +| clip_fraction | 0.68 | +| clip_range | 0.2 | +| entropy_loss | -7.83 | +| explained_variance | -0.182 | +| learning_rate | 0.0001 | +| loss | -0.126 | +| n_updates | 1150 | +| policy_gradient_loss | -0.0904 | +| value_loss | 0.000149 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.82e+03 | +| ep_rew_mean | 0.229 | +| time/ | | +| fps | 327 | +| iterations | 117 | +| time_elapsed | 2927 | +| total_timesteps | 958464 | +| train/ | | +| approx_kl | 0.19244146 | +| clip_fraction | 0.664 | +| clip_range | 0.2 | +| entropy_loss | -7.84 | +| explained_variance | -0.154 | +| learning_rate | 0.0001 | +| loss | -0.124 | +| n_updates | 1160 | +| policy_gradient_loss | -0.0924 | +| value_loss | 0.00011 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.219 | +| time/ | | +| fps | 327 | +| iterations | 118 | +| time_elapsed | 2952 | +| total_timesteps | 966656 | +| train/ | | +| approx_kl | 0.18285955 | +| clip_fraction | 0.653 | +| clip_range | 0.2 | +| entropy_loss | -7.79 | +| explained_variance | -0.092 | +| learning_rate | 0.0001 | +| loss | -0.111 | +| n_updates | 1170 | +| policy_gradient_loss | -0.0829 | +| value_loss | 0.000184 | +---------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.8e+03 | +| ep_rew_mean | 0.234 | +| time/ | | +| fps | 327 | +| iterations | 119 | +| time_elapsed | 2977 | +| total_timesteps | 974848 | +| train/ | | +| approx_kl | 0.2017031 | +| clip_fraction | 0.666 | +| clip_range | 0.2 | +| entropy_loss | -7.83 | +| explained_variance | -0.164 | +| learning_rate | 0.0001 | +| loss | -0.114 | +| n_updates | 1180 | +| policy_gradient_loss | -0.0907 | +| value_loss | 0.000155 | +--------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.82e+03 | +| ep_rew_mean | 0.235 | +| time/ | | +| fps | 327 | +| iterations | 120 | +| time_elapsed | 3002 | +| total_timesteps | 983040 | +| train/ | | +| approx_kl | 0.19539812 | +| clip_fraction | 0.661 | +| clip_range | 0.2 | +| entropy_loss | -7.8 | +| explained_variance | -0.105 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 1190 | +| policy_gradient_loss | -0.0891 | +| value_loss | 0.000169 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.78e+03 | +| ep_rew_mean | 0.231 | +| time/ | | +| fps | 327 | +| iterations | 121 | +| time_elapsed | 3028 | +| total_timesteps | 991232 | +| train/ | | +| approx_kl | 0.18791303 | +| clip_fraction | 0.67 | +| clip_range | 0.2 | +| entropy_loss | -7.82 | +| explained_variance | -0.193 | +| learning_rate | 0.0001 | +| loss | -0.118 | +| n_updates | 1200 | +| policy_gradient_loss | -0.0926 | +| value_loss | 0.000174 | +---------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.227 | +| time/ | | +| fps | 327 | +| iterations | 122 | +| time_elapsed | 3053 | +| total_timesteps | 999424 | +| train/ | | +| approx_kl | 0.1955392 | +| clip_fraction | 0.649 | +| clip_range | 0.2 | +| entropy_loss | -7.82 | +| explained_variance | -0.151 | +| learning_rate | 0.0001 | +| loss | -0.123 | +| n_updates | 1210 | +| policy_gradient_loss | -0.0834 | +| value_loss | 0.000227 | +--------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.229 | +| time/ | | +| fps | 327 | +| iterations | 123 | +| time_elapsed | 3080 | +| total_timesteps | 1007616 | +| train/ | | +| approx_kl | 0.20574816 | +| clip_fraction | 0.677 | +| clip_range | 0.2 | +| entropy_loss | -7.82 | +| explained_variance | -0.125 | +| learning_rate | 0.0001 | +| loss | -0.134 | +| n_updates | 1220 | +| policy_gradient_loss | -0.1 | +| value_loss | 0.000135 | +---------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.227 | +| time/ | | +| fps | 327 | +| iterations | 124 | +| time_elapsed | 3104 | +| total_timesteps | 1015808 | +| train/ | | +| approx_kl | 0.198515 | +| clip_fraction | 0.673 | +| clip_range | 0.2 | +| entropy_loss | -7.85 | +| explained_variance | -0.127 | +| learning_rate | 0.0001 | +| loss | -0.114 | +| n_updates | 1230 | +| policy_gradient_loss | -0.091 | +| value_loss | 0.000165 | +-------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.226 | +| time/ | | +| fps | 327 | +| iterations | 125 | +| time_elapsed | 3130 | +| total_timesteps | 1024000 | +| train/ | | +| approx_kl | 0.22398344 | +| clip_fraction | 0.69 | +| clip_range | 0.2 | +| entropy_loss | -7.77 | +| explained_variance | -0.163 | +| learning_rate | 0.0001 | +| loss | -0.118 | +| n_updates | 1240 | +| policy_gradient_loss | -0.0951 | +| value_loss | 0.000183 | +---------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.216 | +| time/ | | +| fps | 327 | +| iterations | 126 | +| time_elapsed | 3154 | +| total_timesteps | 1032192 | +| train/ | | +| approx_kl | 0.1910915 | +| clip_fraction | 0.654 | +| clip_range | 0.2 | +| entropy_loss | -7.73 | +| explained_variance | -0.0233 | +| learning_rate | 0.0001 | +| loss | -0.111 | +| n_updates | 1250 | +| policy_gradient_loss | -0.0887 | +| value_loss | 0.000226 | +--------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.219 | +| time/ | | +| fps | 327 | +| iterations | 127 | +| time_elapsed | 3179 | +| total_timesteps | 1040384 | +| train/ | | +| approx_kl | 0.20730115 | +| clip_fraction | 0.687 | +| clip_range | 0.2 | +| entropy_loss | -7.82 | +| explained_variance | -0.0941 | +| learning_rate | 0.0001 | +| loss | -0.117 | +| n_updates | 1260 | +| policy_gradient_loss | -0.0946 | +| value_loss | 0.000168 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.204 | +| time/ | | +| fps | 327 | +| iterations | 128 | +| time_elapsed | 3204 | +| total_timesteps | 1048576 | +| train/ | | +| approx_kl | 0.20378564 | +| clip_fraction | 0.663 | +| clip_range | 0.2 | +| entropy_loss | -7.78 | +| explained_variance | -0.158 | +| learning_rate | 0.0001 | +| loss | -0.118 | +| n_updates | 1270 | +| policy_gradient_loss | -0.0913 | +| value_loss | 0.00019 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.208 | +| time/ | | +| fps | 327 | +| iterations | 129 | +| time_elapsed | 3228 | +| total_timesteps | 1056768 | +| train/ | | +| approx_kl | 0.18443106 | +| clip_fraction | 0.645 | +| clip_range | 0.2 | +| entropy_loss | -7.82 | +| explained_variance | -0.239 | +| learning_rate | 0.0001 | +| loss | -0.107 | +| n_updates | 1280 | +| policy_gradient_loss | -0.0834 | +| value_loss | 0.000184 | +---------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.207 | +| time/ | | +| fps | 327 | +| iterations | 130 | +| time_elapsed | 3255 | +| total_timesteps | 1064960 | +| train/ | | +| approx_kl | 0.2105402 | +| clip_fraction | 0.685 | +| clip_range | 0.2 | +| entropy_loss | -7.79 | +| explained_variance | -0.0469 | +| learning_rate | 0.0001 | +| loss | -0.111 | +| n_updates | 1290 | +| policy_gradient_loss | -0.0924 | +| value_loss | 0.000234 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.2 | +| time/ | | +| fps | 327 | +| iterations | 131 | +| time_elapsed | 3280 | +| total_timesteps | 1073152 | +| train/ | | +| approx_kl | 0.2282112 | +| clip_fraction | 0.689 | +| clip_range | 0.2 | +| entropy_loss | -7.78 | +| explained_variance | -0.175 | +| learning_rate | 0.0001 | +| loss | -0.13 | +| n_updates | 1300 | +| policy_gradient_loss | -0.0972 | +| value_loss | 0.000178 | +--------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.201 | +| time/ | | +| fps | 327 | +| iterations | 132 | +| time_elapsed | 3305 | +| total_timesteps | 1081344 | +| train/ | | +| approx_kl | 0.24279466 | +| clip_fraction | 0.695 | +| clip_range | 0.2 | +| entropy_loss | -7.73 | +| explained_variance | -0.168 | +| learning_rate | 0.0001 | +| loss | -0.122 | +| n_updates | 1310 | +| policy_gradient_loss | -0.0988 | +| value_loss | 0.000155 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.201 | +| time/ | | +| fps | 327 | +| iterations | 133 | +| time_elapsed | 3330 | +| total_timesteps | 1089536 | +| train/ | | +| approx_kl | 0.19334699 | +| clip_fraction | 0.662 | +| clip_range | 0.2 | +| entropy_loss | -7.85 | +| explained_variance | -0.0743 | +| learning_rate | 0.0001 | +| loss | -0.127 | +| n_updates | 1320 | +| policy_gradient_loss | -0.0849 | +| value_loss | 0.000198 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.209 | +| time/ | | +| fps | 327 | +| iterations | 134 | +| time_elapsed | 3355 | +| total_timesteps | 1097728 | +| train/ | | +| approx_kl | 0.21402234 | +| clip_fraction | 0.675 | +| clip_range | 0.2 | +| entropy_loss | -7.83 | +| explained_variance | -0.169 | +| learning_rate | 0.0001 | +| loss | -0.113 | +| n_updates | 1330 | +| policy_gradient_loss | -0.0914 | +| value_loss | 0.000168 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.216 | +| time/ | | +| fps | 326 | +| iterations | 135 | +| time_elapsed | 3382 | +| total_timesteps | 1105920 | +| train/ | | +| approx_kl | 0.23198593 | +| clip_fraction | 0.689 | +| clip_range | 0.2 | +| entropy_loss | -7.73 | +| explained_variance | -0.0972 | +| learning_rate | 0.0001 | +| loss | -0.121 | +| n_updates | 1340 | +| policy_gradient_loss | -0.0931 | +| value_loss | 0.00024 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.215 | +| time/ | | +| fps | 327 | +| iterations | 136 | +| time_elapsed | 3406 | +| total_timesteps | 1114112 | +| train/ | | +| approx_kl | 0.22086786 | +| clip_fraction | 0.685 | +| clip_range | 0.2 | +| entropy_loss | -7.75 | +| explained_variance | -0.203 | +| learning_rate | 0.0001 | +| loss | -0.114 | +| n_updates | 1350 | +| policy_gradient_loss | -0.0936 | +| value_loss | 0.000191 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.226 | +| time/ | | +| fps | 326 | +| iterations | 137 | +| time_elapsed | 3432 | +| total_timesteps | 1122304 | +| train/ | | +| approx_kl | 0.24573462 | +| clip_fraction | 0.692 | +| clip_range | 0.2 | +| entropy_loss | -7.73 | +| explained_variance | -0.19 | +| learning_rate | 0.0001 | +| loss | -0.107 | +| n_updates | 1360 | +| policy_gradient_loss | -0.0921 | +| value_loss | 0.000236 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.226 | +| time/ | | +| fps | 327 | +| iterations | 138 | +| time_elapsed | 3456 | +| total_timesteps | 1130496 | +| train/ | | +| approx_kl | 0.21591774 | +| clip_fraction | 0.679 | +| clip_range | 0.2 | +| entropy_loss | -7.81 | +| explained_variance | -0.239 | +| learning_rate | 0.0001 | +| loss | -0.0844 | +| n_updates | 1370 | +| policy_gradient_loss | -0.0936 | +| value_loss | 0.000241 | +---------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.252 | +| time/ | | +| fps | 326 | +| iterations | 139 | +| time_elapsed | 3482 | +| total_timesteps | 1138688 | +| train/ | | +| approx_kl | 0.1889649 | +| clip_fraction | 0.669 | +| clip_range | 0.2 | +| entropy_loss | -7.78 | +| explained_variance | -0.119 | +| learning_rate | 0.0001 | +| loss | -0.119 | +| n_updates | 1380 | +| policy_gradient_loss | -0.0943 | +| value_loss | 0.000191 | +--------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.251 | +| time/ | | +| fps | 326 | +| iterations | 140 | +| time_elapsed | 3508 | +| total_timesteps | 1146880 | +| train/ | | +| approx_kl | 0.22649357 | +| clip_fraction | 0.694 | +| clip_range | 0.2 | +| entropy_loss | -7.75 | +| explained_variance | -0.154 | +| learning_rate | 0.0001 | +| loss | -0.114 | +| n_updates | 1390 | +| policy_gradient_loss | -0.0904 | +| value_loss | 0.000308 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | 0.251 | +| time/ | | +| fps | 326 | +| iterations | 141 | +| time_elapsed | 3533 | +| total_timesteps | 1155072 | +| train/ | | +| approx_kl | 0.21444023 | +| clip_fraction | 0.685 | +| clip_range | 0.2 | +| entropy_loss | -7.75 | +| explained_variance | -0.207 | +| learning_rate | 0.0001 | +| loss | -0.135 | +| n_updates | 1400 | +| policy_gradient_loss | -0.101 | +| value_loss | 0.000134 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.251 | +| time/ | | +| fps | 326 | +| iterations | 142 | +| time_elapsed | 3559 | +| total_timesteps | 1163264 | +| train/ | | +| approx_kl | 0.22134043 | +| clip_fraction | 0.674 | +| clip_range | 0.2 | +| entropy_loss | -7.71 | +| explained_variance | -0.165 | +| learning_rate | 0.0001 | +| loss | -0.107 | +| n_updates | 1410 | +| policy_gradient_loss | -0.09 | +| value_loss | 0.000183 | +---------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | 0.243 | +| time/ | | +| fps | 326 | +| iterations | 143 | +| time_elapsed | 3583 | +| total_timesteps | 1171456 | +| train/ | | +| approx_kl | 0.2133061 | +| clip_fraction | 0.674 | +| clip_range | 0.2 | +| entropy_loss | -7.8 | +| explained_variance | -0.174 | +| learning_rate | 0.0001 | +| loss | -0.116 | +| n_updates | 1420 | +| policy_gradient_loss | -0.0945 | +| value_loss | 0.000145 | +--------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.251 | +| time/ | | +| fps | 326 | +| iterations | 144 | +| time_elapsed | 3610 | +| total_timesteps | 1179648 | +| train/ | | +| approx_kl | 0.21563664 | +| clip_fraction | 0.677 | +| clip_range | 0.2 | +| entropy_loss | -7.84 | +| explained_variance | -0.202 | +| learning_rate | 0.0001 | +| loss | -0.107 | +| n_updates | 1430 | +| policy_gradient_loss | -0.092 | +| value_loss | 0.00015 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.253 | +| time/ | | +| fps | 326 | +| iterations | 145 | +| time_elapsed | 3635 | +| total_timesteps | 1187840 | +| train/ | | +| approx_kl | 0.24229789 | +| clip_fraction | 0.693 | +| clip_range | 0.2 | +| entropy_loss | -7.75 | +| explained_variance | -0.0742 | +| learning_rate | 0.0001 | +| loss | -0.116 | +| n_updates | 1440 | +| policy_gradient_loss | -0.0929 | +| value_loss | 0.000198 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.247 | +| time/ | | +| fps | 326 | +| iterations | 146 | +| time_elapsed | 3659 | +| total_timesteps | 1196032 | +| train/ | | +| approx_kl | 0.20989811 | +| clip_fraction | 0.679 | +| clip_range | 0.2 | +| entropy_loss | -7.79 | +| explained_variance | -0.127 | +| learning_rate | 0.0001 | +| loss | -0.106 | +| n_updates | 1450 | +| policy_gradient_loss | -0.0929 | +| value_loss | 0.000157 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.254 | +| time/ | | +| fps | 326 | +| iterations | 147 | +| time_elapsed | 3685 | +| total_timesteps | 1204224 | +| train/ | | +| approx_kl | 0.22965737 | +| clip_fraction | 0.683 | +| clip_range | 0.2 | +| entropy_loss | -7.75 | +| explained_variance | -0.137 | +| learning_rate | 0.0001 | +| loss | -0.106 | +| n_updates | 1460 | +| policy_gradient_loss | -0.0929 | +| value_loss | 0.000207 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.64e+03 | +| ep_rew_mean | 0.255 | +| time/ | | +| fps | 326 | +| iterations | 148 | +| time_elapsed | 3710 | +| total_timesteps | 1212416 | +| train/ | | +| approx_kl | 0.21099903 | +| clip_fraction | 0.68 | +| clip_range | 0.2 | +| entropy_loss | -7.83 | +| explained_variance | -0.107 | +| learning_rate | 0.0001 | +| loss | -0.118 | +| n_updates | 1470 | +| policy_gradient_loss | -0.0954 | +| value_loss | 0.000247 | +---------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.266 | +| time/ | | +| fps | 326 | +| iterations | 149 | +| time_elapsed | 3736 | +| total_timesteps | 1220608 | +| train/ | | +| approx_kl | 0.2328108 | +| clip_fraction | 0.69 | +| clip_range | 0.2 | +| entropy_loss | -7.78 | +| explained_variance | -0.135 | +| learning_rate | 0.0001 | +| loss | -0.113 | +| n_updates | 1480 | +| policy_gradient_loss | -0.0941 | +| value_loss | 0.00022 | +--------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.266 | +| time/ | | +| fps | 326 | +| iterations | 150 | +| time_elapsed | 3760 | +| total_timesteps | 1228800 | +| train/ | | +| approx_kl | 0.19640857 | +| clip_fraction | 0.665 | +| clip_range | 0.2 | +| entropy_loss | -7.84 | +| explained_variance | -0.164 | +| learning_rate | 0.0001 | +| loss | -0.125 | +| n_updates | 1490 | +| policy_gradient_loss | -0.0945 | +| value_loss | 0.000183 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.27 | +| time/ | | +| fps | 326 | +| iterations | 151 | +| time_elapsed | 3788 | +| total_timesteps | 1236992 | +| train/ | | +| approx_kl | 0.20808157 | +| clip_fraction | 0.675 | +| clip_range | 0.2 | +| entropy_loss | -7.83 | +| explained_variance | -0.22 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 1500 | +| policy_gradient_loss | -0.0923 | +| value_loss | 0.000153 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.283 | +| time/ | | +| fps | 326 | +| iterations | 152 | +| time_elapsed | 3814 | +| total_timesteps | 1245184 | +| train/ | | +| approx_kl | 0.26937294 | +| clip_fraction | 0.714 | +| clip_range | 0.2 | +| entropy_loss | -7.75 | +| explained_variance | -0.188 | +| learning_rate | 0.0001 | +| loss | -0.128 | +| n_updates | 1510 | +| policy_gradient_loss | -0.094 | +| value_loss | 0.000165 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.281 | +| time/ | | +| fps | 326 | +| iterations | 153 | +| time_elapsed | 3840 | +| total_timesteps | 1253376 | +| train/ | | +| approx_kl | 0.20888075 | +| clip_fraction | 0.673 | +| clip_range | 0.2 | +| entropy_loss | -7.84 | +| explained_variance | -0.145 | +| learning_rate | 0.0001 | +| loss | -0.117 | +| n_updates | 1520 | +| policy_gradient_loss | -0.0914 | +| value_loss | 0.000238 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.276 | +| time/ | | +| fps | 326 | +| iterations | 154 | +| time_elapsed | 3864 | +| total_timesteps | 1261568 | +| train/ | | +| approx_kl | 0.22639939 | +| clip_fraction | 0.691 | +| clip_range | 0.2 | +| entropy_loss | -7.83 | +| explained_variance | -0.132 | +| learning_rate | 0.0001 | +| loss | -0.108 | +| n_updates | 1530 | +| policy_gradient_loss | -0.0948 | +| value_loss | 0.000164 | +---------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.261 | +| time/ | | +| fps | 326 | +| iterations | 155 | +| time_elapsed | 3889 | +| total_timesteps | 1269760 | +| train/ | | +| approx_kl | 0.254834 | +| clip_fraction | 0.695 | +| clip_range | 0.2 | +| entropy_loss | -7.75 | +| explained_variance | -0.265 | +| learning_rate | 0.0001 | +| loss | -0.121 | +| n_updates | 1540 | +| policy_gradient_loss | -0.0973 | +| value_loss | 0.000188 | +-------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.264 | +| time/ | | +| fps | 326 | +| iterations | 156 | +| time_elapsed | 3913 | +| total_timesteps | 1277952 | +| train/ | | +| approx_kl | 0.21159756 | +| clip_fraction | 0.667 | +| clip_range | 0.2 | +| entropy_loss | -7.78 | +| explained_variance | -0.162 | +| learning_rate | 0.0001 | +| loss | -0.0929 | +| n_updates | 1550 | +| policy_gradient_loss | -0.0879 | +| value_loss | 0.000175 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.267 | +| time/ | | +| fps | 326 | +| iterations | 157 | +| time_elapsed | 3938 | +| total_timesteps | 1286144 | +| train/ | | +| approx_kl | 0.26367444 | +| clip_fraction | 0.704 | +| clip_range | 0.2 | +| entropy_loss | -7.7 | +| explained_variance | -0.197 | +| learning_rate | 0.0001 | +| loss | -0.116 | +| n_updates | 1560 | +| policy_gradient_loss | -0.0962 | +| value_loss | 0.000253 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.259 | +| time/ | | +| fps | 326 | +| iterations | 158 | +| time_elapsed | 3964 | +| total_timesteps | 1294336 | +| train/ | | +| approx_kl | 0.23841424 | +| clip_fraction | 0.696 | +| clip_range | 0.2 | +| entropy_loss | -7.8 | +| explained_variance | -0.222 | +| learning_rate | 0.0001 | +| loss | -0.132 | +| n_updates | 1570 | +| policy_gradient_loss | -0.0953 | +| value_loss | 0.000155 | +---------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.261 | +| time/ | | +| fps | 326 | +| iterations | 159 | +| time_elapsed | 3989 | +| total_timesteps | 1302528 | +| train/ | | +| approx_kl | 0.269823 | +| clip_fraction | 0.711 | +| clip_range | 0.2 | +| entropy_loss | -7.74 | +| explained_variance | -0.174 | +| learning_rate | 0.0001 | +| loss | -0.107 | +| n_updates | 1580 | +| policy_gradient_loss | -0.0963 | +| value_loss | 0.00018 | +-------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.258 | +| time/ | | +| fps | 326 | +| iterations | 160 | +| time_elapsed | 4013 | +| total_timesteps | 1310720 | +| train/ | | +| approx_kl | 0.23514143 | +| clip_fraction | 0.691 | +| clip_range | 0.2 | +| entropy_loss | -7.79 | +| explained_variance | -0.139 | +| learning_rate | 0.0001 | +| loss | -0.126 | +| n_updates | 1590 | +| policy_gradient_loss | -0.0921 | +| value_loss | 0.000139 | +---------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.248 | +| time/ | | +| fps | 326 | +| iterations | 161 | +| time_elapsed | 4037 | +| total_timesteps | 1318912 | +| train/ | | +| approx_kl | 0.2568788 | +| clip_fraction | 0.704 | +| clip_range | 0.2 | +| entropy_loss | -7.71 | +| explained_variance | -0.189 | +| learning_rate | 0.0001 | +| loss | -0.122 | +| n_updates | 1600 | +| policy_gradient_loss | -0.0934 | +| value_loss | 0.000138 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.253 | +| time/ | | +| fps | 326 | +| iterations | 162 | +| time_elapsed | 4061 | +| total_timesteps | 1327104 | +| train/ | | +| approx_kl | 0.2576354 | +| clip_fraction | 0.702 | +| clip_range | 0.2 | +| entropy_loss | -7.68 | +| explained_variance | -0.0996 | +| learning_rate | 0.0001 | +| loss | -0.11 | +| n_updates | 1610 | +| policy_gradient_loss | -0.0897 | +| value_loss | 0.000167 | +--------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.255 | +| time/ | | +| fps | 326 | +| iterations | 163 | +| time_elapsed | 4087 | +| total_timesteps | 1335296 | +| train/ | | +| approx_kl | 0.24636266 | +| clip_fraction | 0.691 | +| clip_range | 0.2 | +| entropy_loss | -7.7 | +| explained_variance | -0.126 | +| learning_rate | 0.0001 | +| loss | -0.111 | +| n_updates | 1620 | +| policy_gradient_loss | -0.0899 | +| value_loss | 0.000185 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.257 | +| time/ | | +| fps | 326 | +| iterations | 164 | +| time_elapsed | 4111 | +| total_timesteps | 1343488 | +| train/ | | +| approx_kl | 0.25216055 | +| clip_fraction | 0.695 | +| clip_range | 0.2 | +| entropy_loss | -7.65 | +| explained_variance | -0.25 | +| learning_rate | 0.0001 | +| loss | -0.124 | +| n_updates | 1630 | +| policy_gradient_loss | -0.0939 | +| value_loss | 0.000132 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.257 | +| time/ | | +| fps | 326 | +| iterations | 165 | +| time_elapsed | 4136 | +| total_timesteps | 1351680 | +| train/ | | +| approx_kl | 0.26191318 | +| clip_fraction | 0.697 | +| clip_range | 0.2 | +| entropy_loss | -7.66 | +| explained_variance | -0.0729 | +| learning_rate | 0.0001 | +| loss | -0.0903 | +| n_updates | 1640 | +| policy_gradient_loss | -0.0823 | +| value_loss | 0.00032 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.252 | +| time/ | | +| fps | 326 | +| iterations | 166 | +| time_elapsed | 4162 | +| total_timesteps | 1359872 | +| train/ | | +| approx_kl | 0.23675543 | +| clip_fraction | 0.696 | +| clip_range | 0.2 | +| entropy_loss | -7.79 | +| explained_variance | -0.186 | +| learning_rate | 0.0001 | +| loss | -0.114 | +| n_updates | 1650 | +| policy_gradient_loss | -0.0972 | +| value_loss | 0.000183 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.241 | +| time/ | | +| fps | 326 | +| iterations | 167 | +| time_elapsed | 4186 | +| total_timesteps | 1368064 | +| train/ | | +| approx_kl | 0.23261267 | +| clip_fraction | 0.698 | +| clip_range | 0.2 | +| entropy_loss | -7.73 | +| explained_variance | -0.125 | +| learning_rate | 0.0001 | +| loss | -0.114 | +| n_updates | 1660 | +| policy_gradient_loss | -0.0953 | +| value_loss | 0.0002 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.78e+03 | +| ep_rew_mean | 0.246 | +| time/ | | +| fps | 326 | +| iterations | 168 | +| time_elapsed | 4212 | +| total_timesteps | 1376256 | +| train/ | | +| approx_kl | 0.27211517 | +| clip_fraction | 0.71 | +| clip_range | 0.2 | +| entropy_loss | -7.67 | +| explained_variance | -0.181 | +| learning_rate | 0.0001 | +| loss | -0.124 | +| n_updates | 1670 | +| policy_gradient_loss | -0.098 | +| value_loss | 0.000174 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.8e+03 | +| ep_rew_mean | 0.241 | +| time/ | | +| fps | 326 | +| iterations | 169 | +| time_elapsed | 4237 | +| total_timesteps | 1384448 | +| train/ | | +| approx_kl | 0.24067077 | +| clip_fraction | 0.7 | +| clip_range | 0.2 | +| entropy_loss | -7.76 | +| explained_variance | -0.153 | +| learning_rate | 0.0001 | +| loss | -0.116 | +| n_updates | 1680 | +| policy_gradient_loss | -0.0966 | +| value_loss | 0.000176 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.82e+03 | +| ep_rew_mean | 0.246 | +| time/ | | +| fps | 326 | +| iterations | 170 | +| time_elapsed | 4261 | +| total_timesteps | 1392640 | +| train/ | | +| approx_kl | 0.23019451 | +| clip_fraction | 0.697 | +| clip_range | 0.2 | +| entropy_loss | -7.75 | +| explained_variance | -0.211 | +| learning_rate | 0.0001 | +| loss | -0.122 | +| n_updates | 1690 | +| policy_gradient_loss | -0.0939 | +| value_loss | 0.000136 | +---------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.82e+03 | +| ep_rew_mean | 0.242 | +| time/ | | +| fps | 326 | +| iterations | 171 | +| time_elapsed | 4287 | +| total_timesteps | 1400832 | +| train/ | | +| approx_kl | 0.2635875 | +| clip_fraction | 0.708 | +| clip_range | 0.2 | +| entropy_loss | -7.72 | +| explained_variance | -0.105 | +| learning_rate | 0.0001 | +| loss | -0.117 | +| n_updates | 1700 | +| policy_gradient_loss | -0.0941 | +| value_loss | 0.000169 | +--------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.82e+03 | +| ep_rew_mean | 0.234 | +| time/ | | +| fps | 326 | +| iterations | 172 | +| time_elapsed | 4312 | +| total_timesteps | 1409024 | +| train/ | | +| approx_kl | 0.25533813 | +| clip_fraction | 0.7 | +| clip_range | 0.2 | +| entropy_loss | -7.78 | +| explained_variance | -0.13 | +| learning_rate | 0.0001 | +| loss | -0.106 | +| n_updates | 1710 | +| policy_gradient_loss | -0.0931 | +| value_loss | 0.0002 | +---------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.231 | +| time/ | | +| fps | 326 | +| iterations | 173 | +| time_elapsed | 4338 | +| total_timesteps | 1417216 | +| train/ | | +| approx_kl | 0.2746632 | +| clip_fraction | 0.702 | +| clip_range | 0.2 | +| entropy_loss | -7.65 | +| explained_variance | -0.203 | +| learning_rate | 0.0001 | +| loss | -0.112 | +| n_updates | 1720 | +| policy_gradient_loss | -0.0953 | +| value_loss | 0.000171 | +--------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.8e+03 | +| ep_rew_mean | 0.223 | +| time/ | | +| fps | 326 | +| iterations | 174 | +| time_elapsed | 4362 | +| total_timesteps | 1425408 | +| train/ | | +| approx_kl | 0.25628483 | +| clip_fraction | 0.7 | +| clip_range | 0.2 | +| entropy_loss | -7.79 | +| explained_variance | -0.133 | +| learning_rate | 0.0001 | +| loss | -0.108 | +| n_updates | 1730 | +| policy_gradient_loss | -0.0948 | +| value_loss | 0.000175 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.82e+03 | +| ep_rew_mean | 0.219 | +| time/ | | +| fps | 326 | +| iterations | 175 | +| time_elapsed | 4386 | +| total_timesteps | 1433600 | +| train/ | | +| approx_kl | 0.24186687 | +| clip_fraction | 0.697 | +| clip_range | 0.2 | +| entropy_loss | -7.73 | +| explained_variance | -0.155 | +| learning_rate | 0.0001 | +| loss | -0.107 | +| n_updates | 1740 | +| policy_gradient_loss | -0.0962 | +| value_loss | 0.000125 | +---------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.228 | +| time/ | | +| fps | 326 | +| iterations | 176 | +| time_elapsed | 4411 | +| total_timesteps | 1441792 | +| train/ | | +| approx_kl | 0.2774456 | +| clip_fraction | 0.711 | +| clip_range | 0.2 | +| entropy_loss | -7.64 | +| explained_variance | -0.195 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 1750 | +| policy_gradient_loss | -0.0923 | +| value_loss | 0.000135 | +--------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.82e+03 | +| ep_rew_mean | 0.218 | +| time/ | | +| fps | 326 | +| iterations | 177 | +| time_elapsed | 4437 | +| total_timesteps | 1449984 | +| train/ | | +| approx_kl | 0.24052301 | +| clip_fraction | 0.694 | +| clip_range | 0.2 | +| entropy_loss | -7.71 | +| explained_variance | -0.0652 | +| learning_rate | 0.0001 | +| loss | -0.109 | +| n_updates | 1760 | +| policy_gradient_loss | -0.091 | +| value_loss | 0.000213 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.81e+03 | +| ep_rew_mean | 0.22 | +| time/ | | +| fps | 326 | +| iterations | 178 | +| time_elapsed | 4463 | +| total_timesteps | 1458176 | +| train/ | | +| approx_kl | 0.27771735 | +| clip_fraction | 0.709 | +| clip_range | 0.2 | +| entropy_loss | -7.68 | +| explained_variance | -0.195 | +| learning_rate | 0.0001 | +| loss | -0.128 | +| n_updates | 1770 | +| policy_gradient_loss | -0.0967 | +| value_loss | 0.000186 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.82e+03 | +| ep_rew_mean | 0.218 | +| time/ | | +| fps | 326 | +| iterations | 179 | +| time_elapsed | 4487 | +| total_timesteps | 1466368 | +| train/ | | +| approx_kl | 0.25509328 | +| clip_fraction | 0.698 | +| clip_range | 0.2 | +| entropy_loss | -7.72 | +| explained_variance | -0.141 | +| learning_rate | 0.0001 | +| loss | -0.107 | +| n_updates | 1780 | +| policy_gradient_loss | -0.0935 | +| value_loss | 0.000244 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.82e+03 | +| ep_rew_mean | 0.217 | +| time/ | | +| fps | 326 | +| iterations | 180 | +| time_elapsed | 4513 | +| total_timesteps | 1474560 | +| train/ | | +| approx_kl | 0.24361119 | +| clip_fraction | 0.697 | +| clip_range | 0.2 | +| entropy_loss | -7.7 | +| explained_variance | -0.189 | +| learning_rate | 0.0001 | +| loss | -0.0978 | +| n_updates | 1790 | +| policy_gradient_loss | -0.0948 | +| value_loss | 0.000165 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.221 | +| time/ | | +| fps | 326 | +| iterations | 181 | +| time_elapsed | 4537 | +| total_timesteps | 1482752 | +| train/ | | +| approx_kl | 0.26752913 | +| clip_fraction | 0.707 | +| clip_range | 0.2 | +| entropy_loss | -7.58 | +| explained_variance | -0.192 | +| learning_rate | 0.0001 | +| loss | -0.106 | +| n_updates | 1800 | +| policy_gradient_loss | -0.0933 | +| value_loss | 0.000165 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.81e+03 | +| ep_rew_mean | 0.211 | +| time/ | | +| fps | 326 | +| iterations | 182 | +| time_elapsed | 4563 | +| total_timesteps | 1490944 | +| train/ | | +| approx_kl | 0.24171938 | +| clip_fraction | 0.702 | +| clip_range | 0.2 | +| entropy_loss | -7.74 | +| explained_variance | -0.132 | +| learning_rate | 0.0001 | +| loss | -0.123 | +| n_updates | 1810 | +| policy_gradient_loss | -0.0947 | +| value_loss | 0.000145 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.214 | +| time/ | | +| fps | 326 | +| iterations | 183 | +| time_elapsed | 4588 | +| total_timesteps | 1499136 | +| train/ | | +| approx_kl | 0.24162316 | +| clip_fraction | 0.685 | +| clip_range | 0.2 | +| entropy_loss | -7.73 | +| explained_variance | -0.164 | +| learning_rate | 0.0001 | +| loss | -0.098 | +| n_updates | 1820 | +| policy_gradient_loss | -0.0888 | +| value_loss | 0.000163 | +---------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.8e+03 | +| ep_rew_mean | 0.207 | +| time/ | | +| fps | 326 | +| iterations | 184 | +| time_elapsed | 4613 | +| total_timesteps | 1507328 | +| train/ | | +| approx_kl | 0.2549442 | +| clip_fraction | 0.696 | +| clip_range | 0.2 | +| entropy_loss | -7.74 | +| explained_variance | -0.146 | +| learning_rate | 0.0001 | +| loss | -0.122 | +| n_updates | 1830 | +| policy_gradient_loss | -0.0915 | +| value_loss | 0.000168 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.208 | +| time/ | | +| fps | 326 | +| iterations | 185 | +| time_elapsed | 4638 | +| total_timesteps | 1515520 | +| train/ | | +| approx_kl | 0.2799434 | +| clip_fraction | 0.709 | +| clip_range | 0.2 | +| entropy_loss | -7.69 | +| explained_variance | -0.239 | +| learning_rate | 0.0001 | +| loss | -0.117 | +| n_updates | 1840 | +| policy_gradient_loss | -0.0949 | +| value_loss | 0.000137 | +--------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.201 | +| time/ | | +| fps | 326 | +| iterations | 186 | +| time_elapsed | 4663 | +| total_timesteps | 1523712 | +| train/ | | +| approx_kl | 0.27717438 | +| clip_fraction | 0.709 | +| clip_range | 0.2 | +| entropy_loss | -7.64 | +| explained_variance | -0.106 | +| learning_rate | 0.0001 | +| loss | -0.0861 | +| n_updates | 1850 | +| policy_gradient_loss | -0.0865 | +| value_loss | 0.000258 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.192 | +| time/ | | +| fps | 326 | +| iterations | 187 | +| time_elapsed | 4688 | +| total_timesteps | 1531904 | +| train/ | | +| approx_kl | 0.23951724 | +| clip_fraction | 0.703 | +| clip_range | 0.2 | +| entropy_loss | -7.73 | +| explained_variance | -0.246 | +| learning_rate | 0.0001 | +| loss | -0.107 | +| n_updates | 1860 | +| policy_gradient_loss | -0.0983 | +| value_loss | 0.000138 | +---------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.196 | +| time/ | | +| fps | 326 | +| iterations | 188 | +| time_elapsed | 4712 | +| total_timesteps | 1540096 | +| train/ | | +| approx_kl | 0.2695293 | +| clip_fraction | 0.7 | +| clip_range | 0.2 | +| entropy_loss | -7.7 | +| explained_variance | -0.232 | +| learning_rate | 0.0001 | +| loss | -0.111 | +| n_updates | 1870 | +| policy_gradient_loss | -0.0889 | +| value_loss | 0.000132 | +--------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.194 | +| time/ | | +| fps | 326 | +| iterations | 189 | +| time_elapsed | 4736 | +| total_timesteps | 1548288 | +| train/ | | +| approx_kl | 0.24947795 | +| clip_fraction | 0.695 | +| clip_range | 0.2 | +| entropy_loss | -7.6 | +| explained_variance | -0.134 | +| learning_rate | 0.0001 | +| loss | -0.109 | +| n_updates | 1880 | +| policy_gradient_loss | -0.0892 | +| value_loss | 0.000192 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.187 | +| time/ | | +| fps | 326 | +| iterations | 190 | +| time_elapsed | 4760 | +| total_timesteps | 1556480 | +| train/ | | +| approx_kl | 0.24628925 | +| clip_fraction | 0.704 | +| clip_range | 0.2 | +| entropy_loss | -7.69 | +| explained_variance | -0.127 | +| learning_rate | 0.0001 | +| loss | -0.119 | +| n_updates | 1890 | +| policy_gradient_loss | -0.0951 | +| value_loss | 0.000151 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.188 | +| time/ | | +| fps | 326 | +| iterations | 191 | +| time_elapsed | 4785 | +| total_timesteps | 1564672 | +| train/ | | +| approx_kl | 0.28343973 | +| clip_fraction | 0.72 | +| clip_range | 0.2 | +| entropy_loss | -7.63 | +| explained_variance | -0.0832 | +| learning_rate | 0.0001 | +| loss | -0.125 | +| n_updates | 1900 | +| policy_gradient_loss | -0.096 | +| value_loss | 0.000142 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.192 | +| time/ | | +| fps | 326 | +| iterations | 192 | +| time_elapsed | 4811 | +| total_timesteps | 1572864 | +| train/ | | +| approx_kl | 0.26376498 | +| clip_fraction | 0.709 | +| clip_range | 0.2 | +| entropy_loss | -7.74 | +| explained_variance | -0.185 | +| learning_rate | 0.0001 | +| loss | -0.123 | +| n_updates | 1910 | +| policy_gradient_loss | -0.0923 | +| value_loss | 0.000174 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.205 | +| time/ | | +| fps | 326 | +| iterations | 193 | +| time_elapsed | 4835 | +| total_timesteps | 1581056 | +| train/ | | +| approx_kl | 0.24122767 | +| clip_fraction | 0.698 | +| clip_range | 0.2 | +| entropy_loss | -7.76 | +| explained_variance | -0.169 | +| learning_rate | 0.0001 | +| loss | -0.106 | +| n_updates | 1920 | +| policy_gradient_loss | -0.0922 | +| value_loss | 0.000192 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.207 | +| time/ | | +| fps | 326 | +| iterations | 194 | +| time_elapsed | 4861 | +| total_timesteps | 1589248 | +| train/ | | +| approx_kl | 0.32758117 | +| clip_fraction | 0.726 | +| clip_range | 0.2 | +| entropy_loss | -7.62 | +| explained_variance | -0.292 | +| learning_rate | 0.0001 | +| loss | -0.119 | +| n_updates | 1930 | +| policy_gradient_loss | -0.0977 | +| value_loss | 0.000212 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.204 | +| time/ | | +| fps | 326 | +| iterations | 195 | +| time_elapsed | 4886 | +| total_timesteps | 1597440 | +| train/ | | +| approx_kl | 0.26719236 | +| clip_fraction | 0.705 | +| clip_range | 0.2 | +| entropy_loss | -7.73 | +| explained_variance | -0.159 | +| learning_rate | 0.0001 | +| loss | -0.125 | +| n_updates | 1940 | +| policy_gradient_loss | -0.0978 | +| value_loss | 0.000175 | +---------------------------------------- diff --git a/004_rgb_stack_ram_based_reward_custom/trained_models_ryu_level_1_time_reward_small_loop_continue/training_log.txt b/004_rgb_stack_ram_based_reward_custom/trained_models_ryu_level_1_time_reward_small_loop_continue/training_log.txt new file mode 100644 index 0000000..7770c5f --- /dev/null +++ b/004_rgb_stack_ram_based_reward_custom/trained_models_ryu_level_1_time_reward_small_loop_continue/training_log.txt @@ -0,0 +1,13619 @@ +Logging to logs\PPO_20 +--------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.499 | +| time/ | | +| fps | 542 | +| iterations | 1 | +| time_elapsed | 15 | +| total_timesteps | 8192 | +--------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.55e+03 | +| ep_rew_mean | 0.445 | +| time/ | | +| fps | 391 | +| iterations | 2 | +| time_elapsed | 41 | +| total_timesteps | 16384 | +| train/ | | +| approx_kl | 0.01515416 | +| clip_fraction | 0.139 | +| clip_range | 0.2 | +| entropy_loss | -7.83 | +| explained_variance | -0.106 | +| learning_rate | 1e-05 | +| loss | -0.0999 | +| n_updates | 1470 | +| policy_gradient_loss | -0.0622 | +| value_loss | 0.000445 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 372 | +| iterations | 3 | +| time_elapsed | 66 | +| total_timesteps | 24576 | +| train/ | | +| approx_kl | 0.016019773 | +| clip_fraction | 0.157 | +| clip_range | 0.2 | +| entropy_loss | -7.72 | +| explained_variance | -0.12 | +| learning_rate | 1e-05 | +| loss | -0.108 | +| n_updates | 1480 | +| policy_gradient_loss | -0.0678 | +| value_loss | 0.000266 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.61e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 364 | +| iterations | 4 | +| time_elapsed | 89 | +| total_timesteps | 32768 | +| train/ | | +| approx_kl | 0.015514909 | +| clip_fraction | 0.144 | +| clip_range | 0.2 | +| entropy_loss | -7.79 | +| explained_variance | -0.109 | +| learning_rate | 1e-05 | +| loss | -0.0901 | +| n_updates | 1490 | +| policy_gradient_loss | -0.0644 | +| value_loss | 0.000239 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.62e+03 | +| ep_rew_mean | 0.286 | +| time/ | | +| fps | 355 | +| iterations | 5 | +| time_elapsed | 115 | +| total_timesteps | 40960 | +| train/ | | +| approx_kl | 0.015337075 | +| clip_fraction | 0.139 | +| clip_range | 0.2 | +| entropy_loss | -7.79 | +| explained_variance | -0.0478 | +| learning_rate | 1e-05 | +| loss | -0.095 | +| n_updates | 1500 | +| policy_gradient_loss | -0.0626 | +| value_loss | 0.000198 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.62e+03 | +| ep_rew_mean | 0.269 | +| time/ | | +| fps | 351 | +| iterations | 6 | +| time_elapsed | 139 | +| total_timesteps | 49152 | +| train/ | | +| approx_kl | 0.01568208 | +| clip_fraction | 0.149 | +| clip_range | 0.2 | +| entropy_loss | -7.76 | +| explained_variance | -0.116 | +| learning_rate | 1e-05 | +| loss | -0.105 | +| n_updates | 1510 | +| policy_gradient_loss | -0.0608 | +| value_loss | 0.000205 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.63e+03 | +| ep_rew_mean | 0.246 | +| time/ | | +| fps | 345 | +| iterations | 7 | +| time_elapsed | 166 | +| total_timesteps | 57344 | +| train/ | | +| approx_kl | 0.015016765 | +| clip_fraction | 0.135 | +| clip_range | 0.2 | +| entropy_loss | -7.7 | +| explained_variance | -0.0203 | +| learning_rate | 1e-05 | +| loss | -0.0673 | +| n_updates | 1520 | +| policy_gradient_loss | -0.0589 | +| value_loss | 0.000226 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.62e+03 | +| ep_rew_mean | 0.25 | +| time/ | | +| fps | 345 | +| iterations | 8 | +| time_elapsed | 189 | +| total_timesteps | 65536 | +| train/ | | +| approx_kl | 0.017718825 | +| clip_fraction | 0.177 | +| clip_range | 0.2 | +| entropy_loss | -7.7 | +| explained_variance | -0.0685 | +| learning_rate | 1e-05 | +| loss | -0.101 | +| n_updates | 1530 | +| policy_gradient_loss | -0.066 | +| value_loss | 0.000161 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.62e+03 | +| ep_rew_mean | 0.259 | +| time/ | | +| fps | 341 | +| iterations | 9 | +| time_elapsed | 216 | +| total_timesteps | 73728 | +| train/ | | +| approx_kl | 0.015239941 | +| clip_fraction | 0.128 | +| clip_range | 0.2 | +| entropy_loss | -7.76 | +| explained_variance | 0.0104 | +| learning_rate | 1e-05 | +| loss | -0.0756 | +| n_updates | 1540 | +| policy_gradient_loss | -0.0577 | +| value_loss | 0.000267 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.61e+03 | +| ep_rew_mean | 0.249 | +| time/ | | +| fps | 339 | +| iterations | 10 | +| time_elapsed | 241 | +| total_timesteps | 81920 | +| train/ | | +| approx_kl | 0.0154467765 | +| clip_fraction | 0.138 | +| clip_range | 0.2 | +| entropy_loss | -7.71 | +| explained_variance | -0.0296 | +| learning_rate | 1e-05 | +| loss | -0.0817 | +| n_updates | 1550 | +| policy_gradient_loss | -0.0609 | +| value_loss | 0.000269 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.61e+03 | +| ep_rew_mean | 0.244 | +| time/ | | +| fps | 337 | +| iterations | 11 | +| time_elapsed | 266 | +| total_timesteps | 90112 | +| train/ | | +| approx_kl | 0.016432464 | +| clip_fraction | 0.152 | +| clip_range | 0.2 | +| entropy_loss | -7.74 | +| explained_variance | -0.0981 | +| learning_rate | 1e-05 | +| loss | -0.0863 | +| n_updates | 1560 | +| policy_gradient_loss | -0.0622 | +| value_loss | 0.000192 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | 0.252 | +| time/ | | +| fps | 335 | +| iterations | 12 | +| time_elapsed | 292 | +| total_timesteps | 98304 | +| train/ | | +| approx_kl | 0.01573594 | +| clip_fraction | 0.146 | +| clip_range | 0.2 | +| entropy_loss | -7.68 | +| explained_variance | -0.0147 | +| learning_rate | 1e-05 | +| loss | -0.0945 | +| n_updates | 1570 | +| policy_gradient_loss | -0.0625 | +| value_loss | 0.000178 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.63e+03 | +| ep_rew_mean | 0.26 | +| time/ | | +| fps | 336 | +| iterations | 13 | +| time_elapsed | 316 | +| total_timesteps | 106496 | +| train/ | | +| approx_kl | 0.018119466 | +| clip_fraction | 0.166 | +| clip_range | 0.2 | +| entropy_loss | -7.59 | +| explained_variance | -0.0752 | +| learning_rate | 1e-05 | +| loss | -0.106 | +| n_updates | 1580 | +| policy_gradient_loss | -0.0652 | +| value_loss | 0.000243 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.62e+03 | +| ep_rew_mean | 0.246 | +| time/ | | +| fps | 334 | +| iterations | 14 | +| time_elapsed | 342 | +| total_timesteps | 114688 | +| train/ | | +| approx_kl | 0.01718713 | +| clip_fraction | 0.158 | +| clip_range | 0.2 | +| entropy_loss | -7.63 | +| explained_variance | -0.0575 | +| learning_rate | 1e-05 | +| loss | -0.0939 | +| n_updates | 1590 | +| policy_gradient_loss | -0.0645 | +| value_loss | 0.000191 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | 0.244 | +| time/ | | +| fps | 334 | +| iterations | 15 | +| time_elapsed | 367 | +| total_timesteps | 122880 | +| train/ | | +| approx_kl | 0.018409822 | +| clip_fraction | 0.182 | +| clip_range | 0.2 | +| entropy_loss | -7.59 | +| explained_variance | -0.0869 | +| learning_rate | 1e-05 | +| loss | -0.113 | +| n_updates | 1600 | +| policy_gradient_loss | -0.0656 | +| value_loss | 0.000149 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.244 | +| time/ | | +| fps | 333 | +| iterations | 16 | +| time_elapsed | 393 | +| total_timesteps | 131072 | +| train/ | | +| approx_kl | 0.01640669 | +| clip_fraction | 0.154 | +| clip_range | 0.2 | +| entropy_loss | -7.69 | +| explained_variance | -0.166 | +| learning_rate | 1e-05 | +| loss | -0.0971 | +| n_updates | 1610 | +| policy_gradient_loss | -0.0598 | +| value_loss | 0.000117 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.225 | +| time/ | | +| fps | 332 | +| iterations | 17 | +| time_elapsed | 418 | +| total_timesteps | 139264 | +| train/ | | +| approx_kl | 0.017656447 | +| clip_fraction | 0.173 | +| clip_range | 0.2 | +| entropy_loss | -7.61 | +| explained_variance | -0.0837 | +| learning_rate | 1e-05 | +| loss | -0.085 | +| n_updates | 1620 | +| policy_gradient_loss | -0.0626 | +| value_loss | 0.000125 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.228 | +| time/ | | +| fps | 332 | +| iterations | 18 | +| time_elapsed | 442 | +| total_timesteps | 147456 | +| train/ | | +| approx_kl | 0.018764675 | +| clip_fraction | 0.183 | +| clip_range | 0.2 | +| entropy_loss | -7.5 | +| explained_variance | -0.0982 | +| learning_rate | 1e-05 | +| loss | -0.0997 | +| n_updates | 1630 | +| policy_gradient_loss | -0.0619 | +| value_loss | 0.000141 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.229 | +| time/ | | +| fps | 332 | +| iterations | 19 | +| time_elapsed | 468 | +| total_timesteps | 155648 | +| train/ | | +| approx_kl | 0.016829763 | +| clip_fraction | 0.146 | +| clip_range | 0.2 | +| entropy_loss | -7.54 | +| explained_variance | -0.0392 | +| learning_rate | 1e-05 | +| loss | -0.101 | +| n_updates | 1640 | +| policy_gradient_loss | -0.0624 | +| value_loss | 0.000236 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.23 | +| time/ | | +| fps | 332 | +| iterations | 20 | +| time_elapsed | 492 | +| total_timesteps | 163840 | +| train/ | | +| approx_kl | 0.017447889 | +| clip_fraction | 0.159 | +| clip_range | 0.2 | +| entropy_loss | -7.59 | +| explained_variance | -0.0356 | +| learning_rate | 1e-05 | +| loss | -0.0784 | +| n_updates | 1650 | +| policy_gradient_loss | -0.0598 | +| value_loss | 0.000254 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.232 | +| time/ | | +| fps | 331 | +| iterations | 21 | +| time_elapsed | 518 | +| total_timesteps | 172032 | +| train/ | | +| approx_kl | 0.019144129 | +| clip_fraction | 0.192 | +| clip_range | 0.2 | +| entropy_loss | -7.51 | +| explained_variance | -0.00336 | +| learning_rate | 1e-05 | +| loss | -0.113 | +| n_updates | 1660 | +| policy_gradient_loss | -0.07 | +| value_loss | 0.000213 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.206 | +| time/ | | +| fps | 331 | +| iterations | 22 | +| time_elapsed | 543 | +| total_timesteps | 180224 | +| train/ | | +| approx_kl | 0.019225769 | +| clip_fraction | 0.182 | +| clip_range | 0.2 | +| entropy_loss | -7.56 | +| explained_variance | -0.0524 | +| learning_rate | 1e-05 | +| loss | -0.0949 | +| n_updates | 1670 | +| policy_gradient_loss | -0.0664 | +| value_loss | 0.000182 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.213 | +| time/ | | +| fps | 332 | +| iterations | 23 | +| time_elapsed | 567 | +| total_timesteps | 188416 | +| train/ | | +| approx_kl | 0.018439146 | +| clip_fraction | 0.181 | +| clip_range | 0.2 | +| entropy_loss | -7.45 | +| explained_variance | 0.0549 | +| learning_rate | 1e-05 | +| loss | -0.11 | +| n_updates | 1680 | +| policy_gradient_loss | -0.066 | +| value_loss | 0.00021 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.202 | +| time/ | | +| fps | 331 | +| iterations | 24 | +| time_elapsed | 593 | +| total_timesteps | 196608 | +| train/ | | +| approx_kl | 0.017801572 | +| clip_fraction | 0.16 | +| clip_range | 0.2 | +| entropy_loss | -7.54 | +| explained_variance | -0.00446 | +| learning_rate | 1e-05 | +| loss | -0.109 | +| n_updates | 1690 | +| policy_gradient_loss | -0.0627 | +| value_loss | 0.000288 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.206 | +| time/ | | +| fps | 331 | +| iterations | 25 | +| time_elapsed | 617 | +| total_timesteps | 204800 | +| train/ | | +| approx_kl | 0.019647507 | +| clip_fraction | 0.198 | +| clip_range | 0.2 | +| entropy_loss | -7.48 | +| explained_variance | -0.00516 | +| learning_rate | 1e-05 | +| loss | -0.107 | +| n_updates | 1700 | +| policy_gradient_loss | -0.0662 | +| value_loss | 0.000231 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.218 | +| time/ | | +| fps | 330 | +| iterations | 26 | +| time_elapsed | 644 | +| total_timesteps | 212992 | +| train/ | | +| approx_kl | 0.019909011 | +| clip_fraction | 0.205 | +| clip_range | 0.2 | +| entropy_loss | -7.6 | +| explained_variance | -0.157 | +| learning_rate | 1e-05 | +| loss | -0.102 | +| n_updates | 1710 | +| policy_gradient_loss | -0.0685 | +| value_loss | 0.000131 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.214 | +| time/ | | +| fps | 330 | +| iterations | 27 | +| time_elapsed | 668 | +| total_timesteps | 221184 | +| train/ | | +| approx_kl | 0.018789908 | +| clip_fraction | 0.176 | +| clip_range | 0.2 | +| entropy_loss | -7.44 | +| explained_variance | -0.0513 | +| learning_rate | 1e-05 | +| loss | -0.0914 | +| n_updates | 1720 | +| policy_gradient_loss | -0.0646 | +| value_loss | 0.000178 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.212 | +| time/ | | +| fps | 330 | +| iterations | 28 | +| time_elapsed | 694 | +| total_timesteps | 229376 | +| train/ | | +| approx_kl | 0.018710822 | +| clip_fraction | 0.188 | +| clip_range | 0.2 | +| entropy_loss | -7.45 | +| explained_variance | 0.00949 | +| learning_rate | 1e-05 | +| loss | -0.0921 | +| n_updates | 1730 | +| policy_gradient_loss | -0.063 | +| value_loss | 0.000214 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.207 | +| time/ | | +| fps | 330 | +| iterations | 29 | +| time_elapsed | 719 | +| total_timesteps | 237568 | +| train/ | | +| approx_kl | 0.018554809 | +| clip_fraction | 0.182 | +| clip_range | 0.2 | +| entropy_loss | -7.41 | +| explained_variance | -0.0768 | +| learning_rate | 1e-05 | +| loss | -0.0997 | +| n_updates | 1740 | +| policy_gradient_loss | -0.0652 | +| value_loss | 0.000217 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.213 | +| time/ | | +| fps | 330 | +| iterations | 30 | +| time_elapsed | 744 | +| total_timesteps | 245760 | +| train/ | | +| approx_kl | 0.021522496 | +| clip_fraction | 0.207 | +| clip_range | 0.2 | +| entropy_loss | -7.46 | +| explained_variance | -0.0737 | +| learning_rate | 1e-05 | +| loss | -0.0971 | +| n_updates | 1750 | +| policy_gradient_loss | -0.0669 | +| value_loss | 0.000254 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.203 | +| time/ | | +| fps | 329 | +| iterations | 31 | +| time_elapsed | 771 | +| total_timesteps | 253952 | +| train/ | | +| approx_kl | 0.019515544 | +| clip_fraction | 0.193 | +| clip_range | 0.2 | +| entropy_loss | -7.47 | +| explained_variance | -0.031 | +| learning_rate | 1e-05 | +| loss | -0.0847 | +| n_updates | 1760 | +| policy_gradient_loss | -0.066 | +| value_loss | 0.000217 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.198 | +| time/ | | +| fps | 329 | +| iterations | 32 | +| time_elapsed | 795 | +| total_timesteps | 262144 | +| train/ | | +| approx_kl | 0.019901346 | +| clip_fraction | 0.204 | +| clip_range | 0.2 | +| entropy_loss | -7.44 | +| explained_variance | -0.122 | +| learning_rate | 1e-05 | +| loss | -0.0622 | +| n_updates | 1770 | +| policy_gradient_loss | -0.064 | +| value_loss | 0.000178 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.196 | +| time/ | | +| fps | 329 | +| iterations | 33 | +| time_elapsed | 820 | +| total_timesteps | 270336 | +| train/ | | +| approx_kl | 0.021802973 | +| clip_fraction | 0.23 | +| clip_range | 0.2 | +| entropy_loss | -7.27 | +| explained_variance | -0.165 | +| learning_rate | 1e-05 | +| loss | -0.0942 | +| n_updates | 1780 | +| policy_gradient_loss | -0.0703 | +| value_loss | 0.000124 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.179 | +| time/ | | +| fps | 329 | +| iterations | 34 | +| time_elapsed | 845 | +| total_timesteps | 278528 | +| train/ | | +| approx_kl | 0.020376727 | +| clip_fraction | 0.195 | +| clip_range | 0.2 | +| entropy_loss | -7.37 | +| explained_variance | -0.0682 | +| learning_rate | 1e-05 | +| loss | -0.0845 | +| n_updates | 1790 | +| policy_gradient_loss | -0.0654 | +| value_loss | 0.000158 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.185 | +| time/ | | +| fps | 329 | +| iterations | 35 | +| time_elapsed | 869 | +| total_timesteps | 286720 | +| train/ | | +| approx_kl | 0.019020554 | +| clip_fraction | 0.185 | +| clip_range | 0.2 | +| entropy_loss | -7.4 | +| explained_variance | -0.0489 | +| learning_rate | 1e-05 | +| loss | -0.0951 | +| n_updates | 1800 | +| policy_gradient_loss | -0.0632 | +| value_loss | 0.000187 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.192 | +| time/ | | +| fps | 329 | +| iterations | 36 | +| time_elapsed | 895 | +| total_timesteps | 294912 | +| train/ | | +| approx_kl | 0.02128502 | +| clip_fraction | 0.213 | +| clip_range | 0.2 | +| entropy_loss | -7.39 | +| explained_variance | -0.0917 | +| learning_rate | 1e-05 | +| loss | -0.084 | +| n_updates | 1810 | +| policy_gradient_loss | -0.0659 | +| value_loss | 0.000167 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | 0.207 | +| time/ | | +| fps | 329 | +| iterations | 37 | +| time_elapsed | 919 | +| total_timesteps | 303104 | +| train/ | | +| approx_kl | 0.021538049 | +| clip_fraction | 0.196 | +| clip_range | 0.2 | +| entropy_loss | -7.39 | +| explained_variance | 0.0143 | +| learning_rate | 1e-05 | +| loss | -0.0938 | +| n_updates | 1820 | +| policy_gradient_loss | -0.0658 | +| value_loss | 0.000256 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.204 | +| time/ | | +| fps | 329 | +| iterations | 38 | +| time_elapsed | 945 | +| total_timesteps | 311296 | +| train/ | | +| approx_kl | 0.022143919 | +| clip_fraction | 0.226 | +| clip_range | 0.2 | +| entropy_loss | -7.31 | +| explained_variance | -0.186 | +| learning_rate | 1e-05 | +| loss | -0.0844 | +| n_updates | 1830 | +| policy_gradient_loss | -0.0705 | +| value_loss | 0.000222 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.196 | +| time/ | | +| fps | 329 | +| iterations | 39 | +| time_elapsed | 969 | +| total_timesteps | 319488 | +| train/ | | +| approx_kl | 0.020683533 | +| clip_fraction | 0.196 | +| clip_range | 0.2 | +| entropy_loss | -7.4 | +| explained_variance | -0.1 | +| learning_rate | 1e-05 | +| loss | -0.0985 | +| n_updates | 1840 | +| policy_gradient_loss | -0.0664 | +| value_loss | 0.00014 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.196 | +| time/ | | +| fps | 328 | +| iterations | 40 | +| time_elapsed | 996 | +| total_timesteps | 327680 | +| train/ | | +| approx_kl | 0.021390148 | +| clip_fraction | 0.212 | +| clip_range | 0.2 | +| entropy_loss | -7.32 | +| explained_variance | -0.0182 | +| learning_rate | 1e-05 | +| loss | -0.0831 | +| n_updates | 1850 | +| policy_gradient_loss | -0.0683 | +| value_loss | 0.000199 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.186 | +| time/ | | +| fps | 328 | +| iterations | 41 | +| time_elapsed | 1021 | +| total_timesteps | 335872 | +| train/ | | +| approx_kl | 0.022304796 | +| clip_fraction | 0.22 | +| clip_range | 0.2 | +| entropy_loss | -7.37 | +| explained_variance | -0.0989 | +| learning_rate | 1e-05 | +| loss | -0.0836 | +| n_updates | 1860 | +| policy_gradient_loss | -0.0695 | +| value_loss | 0.000179 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.199 | +| time/ | | +| fps | 328 | +| iterations | 42 | +| time_elapsed | 1046 | +| total_timesteps | 344064 | +| train/ | | +| approx_kl | 0.020759406 | +| clip_fraction | 0.201 | +| clip_range | 0.2 | +| entropy_loss | -7.32 | +| explained_variance | -0.0265 | +| learning_rate | 1e-05 | +| loss | -0.0809 | +| n_updates | 1870 | +| policy_gradient_loss | -0.0665 | +| value_loss | 0.00022 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.194 | +| time/ | | +| fps | 328 | +| iterations | 43 | +| time_elapsed | 1070 | +| total_timesteps | 352256 | +| train/ | | +| approx_kl | 0.022563342 | +| clip_fraction | 0.223 | +| clip_range | 0.2 | +| entropy_loss | -7.33 | +| explained_variance | -0.104 | +| learning_rate | 1e-05 | +| loss | -0.1 | +| n_updates | 1880 | +| policy_gradient_loss | -0.0696 | +| value_loss | 0.000186 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.182 | +| time/ | | +| fps | 329 | +| iterations | 44 | +| time_elapsed | 1094 | +| total_timesteps | 360448 | +| train/ | | +| approx_kl | 0.020293225 | +| clip_fraction | 0.197 | +| clip_range | 0.2 | +| entropy_loss | -7.29 | +| explained_variance | -0.129 | +| learning_rate | 1e-05 | +| loss | -0.0918 | +| n_updates | 1890 | +| policy_gradient_loss | -0.0662 | +| value_loss | 0.000178 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.192 | +| time/ | | +| fps | 328 | +| iterations | 45 | +| time_elapsed | 1121 | +| total_timesteps | 368640 | +| train/ | | +| approx_kl | 0.023733145 | +| clip_fraction | 0.238 | +| clip_range | 0.2 | +| entropy_loss | -7.22 | +| explained_variance | -0.102 | +| learning_rate | 1e-05 | +| loss | -0.0987 | +| n_updates | 1900 | +| policy_gradient_loss | -0.0712 | +| value_loss | 0.000161 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.188 | +| time/ | | +| fps | 329 | +| iterations | 46 | +| time_elapsed | 1145 | +| total_timesteps | 376832 | +| train/ | | +| approx_kl | 0.021918137 | +| clip_fraction | 0.213 | +| clip_range | 0.2 | +| entropy_loss | -7.32 | +| explained_variance | -0.0299 | +| learning_rate | 1e-05 | +| loss | -0.0947 | +| n_updates | 1910 | +| policy_gradient_loss | -0.0674 | +| value_loss | 0.00022 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.183 | +| time/ | | +| fps | 328 | +| iterations | 47 | +| time_elapsed | 1170 | +| total_timesteps | 385024 | +| train/ | | +| approx_kl | 0.02211531 | +| clip_fraction | 0.234 | +| clip_range | 0.2 | +| entropy_loss | -7.3 | +| explained_variance | -0.139 | +| learning_rate | 1e-05 | +| loss | -0.103 | +| n_updates | 1920 | +| policy_gradient_loss | -0.0741 | +| value_loss | 0.000101 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.188 | +| time/ | | +| fps | 328 | +| iterations | 48 | +| time_elapsed | 1195 | +| total_timesteps | 393216 | +| train/ | | +| approx_kl | 0.022546507 | +| clip_fraction | 0.227 | +| clip_range | 0.2 | +| entropy_loss | -6.98 | +| explained_variance | -0.051 | +| learning_rate | 1e-05 | +| loss | -0.102 | +| n_updates | 1930 | +| policy_gradient_loss | -0.0692 | +| value_loss | 0.000177 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.188 | +| time/ | | +| fps | 329 | +| iterations | 49 | +| time_elapsed | 1219 | +| total_timesteps | 401408 | +| train/ | | +| approx_kl | 0.021896563 | +| clip_fraction | 0.211 | +| clip_range | 0.2 | +| entropy_loss | -7.31 | +| explained_variance | -0.125 | +| learning_rate | 1e-05 | +| loss | -0.104 | +| n_updates | 1940 | +| policy_gradient_loss | -0.0659 | +| value_loss | 0.000141 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.198 | +| time/ | | +| fps | 328 | +| iterations | 50 | +| time_elapsed | 1245 | +| total_timesteps | 409600 | +| train/ | | +| approx_kl | 0.020979375 | +| clip_fraction | 0.208 | +| clip_range | 0.2 | +| entropy_loss | -7.23 | +| explained_variance | -0.0212 | +| learning_rate | 1e-05 | +| loss | -0.0881 | +| n_updates | 1950 | +| policy_gradient_loss | -0.065 | +| value_loss | 0.000174 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.195 | +| time/ | | +| fps | 329 | +| iterations | 51 | +| time_elapsed | 1269 | +| total_timesteps | 417792 | +| train/ | | +| approx_kl | 0.022992343 | +| clip_fraction | 0.22 | +| clip_range | 0.2 | +| entropy_loss | -7.13 | +| explained_variance | -0.0644 | +| learning_rate | 1e-05 | +| loss | -0.0988 | +| n_updates | 1960 | +| policy_gradient_loss | -0.0684 | +| value_loss | 0.000275 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.21 | +| time/ | | +| fps | 329 | +| iterations | 52 | +| time_elapsed | 1293 | +| total_timesteps | 425984 | +| train/ | | +| approx_kl | 0.022395756 | +| clip_fraction | 0.226 | +| clip_range | 0.2 | +| entropy_loss | -7.21 | +| explained_variance | -0.0879 | +| learning_rate | 1e-05 | +| loss | -0.0981 | +| n_updates | 1970 | +| policy_gradient_loss | -0.07 | +| value_loss | 0.000184 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.221 | +| time/ | | +| fps | 329 | +| iterations | 53 | +| time_elapsed | 1318 | +| total_timesteps | 434176 | +| train/ | | +| approx_kl | 0.024155218 | +| clip_fraction | 0.244 | +| clip_range | 0.2 | +| entropy_loss | -7.17 | +| explained_variance | -0.104 | +| learning_rate | 1e-05 | +| loss | -0.0887 | +| n_updates | 1980 | +| policy_gradient_loss | -0.0729 | +| value_loss | 0.000215 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.212 | +| time/ | | +| fps | 329 | +| iterations | 54 | +| time_elapsed | 1343 | +| total_timesteps | 442368 | +| train/ | | +| approx_kl | 0.02208085 | +| clip_fraction | 0.217 | +| clip_range | 0.2 | +| entropy_loss | -7.19 | +| explained_variance | -0.0388 | +| learning_rate | 1e-05 | +| loss | -0.105 | +| n_updates | 1990 | +| policy_gradient_loss | -0.0684 | +| value_loss | 0.000181 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.221 | +| time/ | | +| fps | 328 | +| iterations | 55 | +| time_elapsed | 1370 | +| total_timesteps | 450560 | +| train/ | | +| approx_kl | 0.024053633 | +| clip_fraction | 0.237 | +| clip_range | 0.2 | +| entropy_loss | -7.16 | +| explained_variance | -0.137 | +| learning_rate | 1e-05 | +| loss | -0.096 | +| n_updates | 2000 | +| policy_gradient_loss | -0.0712 | +| value_loss | 0.000155 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.213 | +| time/ | | +| fps | 329 | +| iterations | 56 | +| time_elapsed | 1394 | +| total_timesteps | 458752 | +| train/ | | +| approx_kl | 0.023889687 | +| clip_fraction | 0.241 | +| clip_range | 0.2 | +| entropy_loss | -7.24 | +| explained_variance | -0.102 | +| learning_rate | 1e-05 | +| loss | -0.0952 | +| n_updates | 2010 | +| policy_gradient_loss | -0.0704 | +| value_loss | 0.000193 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.212 | +| time/ | | +| fps | 328 | +| iterations | 57 | +| time_elapsed | 1420 | +| total_timesteps | 466944 | +| train/ | | +| approx_kl | 0.023665758 | +| clip_fraction | 0.237 | +| clip_range | 0.2 | +| entropy_loss | -7.24 | +| explained_variance | -0.11 | +| learning_rate | 1e-05 | +| loss | -0.1 | +| n_updates | 2020 | +| policy_gradient_loss | -0.0697 | +| value_loss | 0.000151 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.211 | +| time/ | | +| fps | 329 | +| iterations | 58 | +| time_elapsed | 1444 | +| total_timesteps | 475136 | +| train/ | | +| approx_kl | 0.024316259 | +| clip_fraction | 0.242 | +| clip_range | 0.2 | +| entropy_loss | -7 | +| explained_variance | -0.0297 | +| learning_rate | 1e-05 | +| loss | -0.0962 | +| n_updates | 2030 | +| policy_gradient_loss | -0.0707 | +| value_loss | 0.000189 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.205 | +| time/ | | +| fps | 329 | +| iterations | 59 | +| time_elapsed | 1468 | +| total_timesteps | 483328 | +| train/ | | +| approx_kl | 0.023950368 | +| clip_fraction | 0.244 | +| clip_range | 0.2 | +| entropy_loss | -7.19 | +| explained_variance | -0.103 | +| learning_rate | 1e-05 | +| loss | -0.113 | +| n_updates | 2040 | +| policy_gradient_loss | -0.0716 | +| value_loss | 0.000154 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.204 | +| time/ | | +| fps | 329 | +| iterations | 60 | +| time_elapsed | 1493 | +| total_timesteps | 491520 | +| train/ | | +| approx_kl | 0.024130128 | +| clip_fraction | 0.241 | +| clip_range | 0.2 | +| entropy_loss | -7.15 | +| explained_variance | -0.0373 | +| learning_rate | 1e-05 | +| loss | -0.121 | +| n_updates | 2050 | +| policy_gradient_loss | -0.0688 | +| value_loss | 0.000152 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.213 | +| time/ | | +| fps | 329 | +| iterations | 61 | +| time_elapsed | 1517 | +| total_timesteps | 499712 | +| train/ | | +| approx_kl | 0.024628261 | +| clip_fraction | 0.25 | +| clip_range | 0.2 | +| entropy_loss | -7.2 | +| explained_variance | -0.117 | +| learning_rate | 1e-05 | +| loss | -0.105 | +| n_updates | 2060 | +| policy_gradient_loss | -0.0723 | +| value_loss | 0.000132 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.205 | +| time/ | | +| fps | 329 | +| iterations | 62 | +| time_elapsed | 1542 | +| total_timesteps | 507904 | +| train/ | | +| approx_kl | 0.026172826 | +| clip_fraction | 0.255 | +| clip_range | 0.2 | +| entropy_loss | -7.17 | +| explained_variance | -0.0801 | +| learning_rate | 1e-05 | +| loss | -0.0938 | +| n_updates | 2070 | +| policy_gradient_loss | -0.071 | +| value_loss | 0.000124 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.78e+03 | +| ep_rew_mean | 0.216 | +| time/ | | +| fps | 329 | +| iterations | 63 | +| time_elapsed | 1566 | +| total_timesteps | 516096 | +| train/ | | +| approx_kl | 0.025000596 | +| clip_fraction | 0.245 | +| clip_range | 0.2 | +| entropy_loss | -7.18 | +| explained_variance | -0.0402 | +| learning_rate | 1e-05 | +| loss | -0.0937 | +| n_updates | 2080 | +| policy_gradient_loss | -0.0699 | +| value_loss | 0.000164 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.78e+03 | +| ep_rew_mean | 0.212 | +| time/ | | +| fps | 329 | +| iterations | 64 | +| time_elapsed | 1592 | +| total_timesteps | 524288 | +| train/ | | +| approx_kl | 0.024162417 | +| clip_fraction | 0.245 | +| clip_range | 0.2 | +| entropy_loss | -7.04 | +| explained_variance | -0.0149 | +| learning_rate | 1e-05 | +| loss | -0.1 | +| n_updates | 2090 | +| policy_gradient_loss | -0.0707 | +| value_loss | 0.000161 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.78e+03 | +| ep_rew_mean | 0.211 | +| time/ | | +| fps | 329 | +| iterations | 65 | +| time_elapsed | 1617 | +| total_timesteps | 532480 | +| train/ | | +| approx_kl | 0.02347017 | +| clip_fraction | 0.234 | +| clip_range | 0.2 | +| entropy_loss | -7 | +| explained_variance | -0.054 | +| learning_rate | 1e-05 | +| loss | -0.108 | +| n_updates | 2100 | +| policy_gradient_loss | -0.0697 | +| value_loss | 0.000156 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.219 | +| time/ | | +| fps | 329 | +| iterations | 66 | +| time_elapsed | 1643 | +| total_timesteps | 540672 | +| train/ | | +| approx_kl | 0.024840454 | +| clip_fraction | 0.256 | +| clip_range | 0.2 | +| entropy_loss | -7.07 | +| explained_variance | -0.106 | +| learning_rate | 1e-05 | +| loss | -0.0963 | +| n_updates | 2110 | +| policy_gradient_loss | -0.0726 | +| value_loss | 0.00015 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.203 | +| time/ | | +| fps | 328 | +| iterations | 67 | +| time_elapsed | 1669 | +| total_timesteps | 548864 | +| train/ | | +| approx_kl | 0.023055967 | +| clip_fraction | 0.237 | +| clip_range | 0.2 | +| entropy_loss | -7.1 | +| explained_variance | 0.0217 | +| learning_rate | 1e-05 | +| loss | -0.0934 | +| n_updates | 2120 | +| policy_gradient_loss | -0.0661 | +| value_loss | 0.000193 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.207 | +| time/ | | +| fps | 328 | +| iterations | 68 | +| time_elapsed | 1694 | +| total_timesteps | 557056 | +| train/ | | +| approx_kl | 0.023825029 | +| clip_fraction | 0.247 | +| clip_range | 0.2 | +| entropy_loss | -7.12 | +| explained_variance | -0.0596 | +| learning_rate | 1e-05 | +| loss | -0.0879 | +| n_updates | 2130 | +| policy_gradient_loss | -0.0675 | +| value_loss | 0.000141 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.205 | +| time/ | | +| fps | 328 | +| iterations | 69 | +| time_elapsed | 1721 | +| total_timesteps | 565248 | +| train/ | | +| approx_kl | 0.02659879 | +| clip_fraction | 0.262 | +| clip_range | 0.2 | +| entropy_loss | -7 | +| explained_variance | -0.0687 | +| learning_rate | 1e-05 | +| loss | -0.113 | +| n_updates | 2140 | +| policy_gradient_loss | -0.072 | +| value_loss | 0.000183 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.195 | +| time/ | | +| fps | 328 | +| iterations | 70 | +| time_elapsed | 1745 | +| total_timesteps | 573440 | +| train/ | | +| approx_kl | 0.025512012 | +| clip_fraction | 0.267 | +| clip_range | 0.2 | +| entropy_loss | -7.07 | +| explained_variance | -0.0898 | +| learning_rate | 1e-05 | +| loss | -0.104 | +| n_updates | 2150 | +| policy_gradient_loss | -0.0746 | +| value_loss | 0.000141 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.2 | +| time/ | | +| fps | 328 | +| iterations | 71 | +| time_elapsed | 1770 | +| total_timesteps | 581632 | +| train/ | | +| approx_kl | 0.026720982 | +| clip_fraction | 0.27 | +| clip_range | 0.2 | +| entropy_loss | -6.98 | +| explained_variance | -0.0354 | +| learning_rate | 1e-05 | +| loss | -0.106 | +| n_updates | 2160 | +| policy_gradient_loss | -0.0725 | +| value_loss | 0.000181 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.186 | +| time/ | | +| fps | 328 | +| iterations | 72 | +| time_elapsed | 1796 | +| total_timesteps | 589824 | +| train/ | | +| approx_kl | 0.024995409 | +| clip_fraction | 0.242 | +| clip_range | 0.2 | +| entropy_loss | -7.1 | +| explained_variance | -0.021 | +| learning_rate | 1e-05 | +| loss | -0.102 | +| n_updates | 2170 | +| policy_gradient_loss | -0.0697 | +| value_loss | 0.000165 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.187 | +| time/ | | +| fps | 328 | +| iterations | 73 | +| time_elapsed | 1820 | +| total_timesteps | 598016 | +| train/ | | +| approx_kl | 0.02750969 | +| clip_fraction | 0.272 | +| clip_range | 0.2 | +| entropy_loss | -7.02 | +| explained_variance | -0.0845 | +| learning_rate | 1e-05 | +| loss | -0.114 | +| n_updates | 2180 | +| policy_gradient_loss | -0.0723 | +| value_loss | 0.000196 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.189 | +| time/ | | +| fps | 328 | +| iterations | 74 | +| time_elapsed | 1847 | +| total_timesteps | 606208 | +| train/ | | +| approx_kl | 0.025137216 | +| clip_fraction | 0.247 | +| clip_range | 0.2 | +| entropy_loss | -6.99 | +| explained_variance | -0.0826 | +| learning_rate | 1e-05 | +| loss | -0.107 | +| n_updates | 2190 | +| policy_gradient_loss | -0.0701 | +| value_loss | 0.000207 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.19 | +| time/ | | +| fps | 328 | +| iterations | 75 | +| time_elapsed | 1871 | +| total_timesteps | 614400 | +| train/ | | +| approx_kl | 0.023783617 | +| clip_fraction | 0.246 | +| clip_range | 0.2 | +| entropy_loss | -6.9 | +| explained_variance | -0.0522 | +| learning_rate | 1e-05 | +| loss | -0.0897 | +| n_updates | 2200 | +| policy_gradient_loss | -0.0719 | +| value_loss | 0.000155 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.202 | +| time/ | | +| fps | 328 | +| iterations | 76 | +| time_elapsed | 1897 | +| total_timesteps | 622592 | +| train/ | | +| approx_kl | 0.027604949 | +| clip_fraction | 0.276 | +| clip_range | 0.2 | +| entropy_loss | -6.93 | +| explained_variance | -0.025 | +| learning_rate | 1e-05 | +| loss | -0.108 | +| n_updates | 2210 | +| policy_gradient_loss | -0.0743 | +| value_loss | 0.000196 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.78e+03 | +| ep_rew_mean | 0.198 | +| time/ | | +| fps | 328 | +| iterations | 77 | +| time_elapsed | 1922 | +| total_timesteps | 630784 | +| train/ | | +| approx_kl | 0.026740989 | +| clip_fraction | 0.254 | +| clip_range | 0.2 | +| entropy_loss | -6.99 | +| explained_variance | -0.00878 | +| learning_rate | 1e-05 | +| loss | -0.0872 | +| n_updates | 2220 | +| policy_gradient_loss | -0.071 | +| value_loss | 0.000274 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.195 | +| time/ | | +| fps | 328 | +| iterations | 78 | +| time_elapsed | 1947 | +| total_timesteps | 638976 | +| train/ | | +| approx_kl | 0.028936466 | +| clip_fraction | 0.295 | +| clip_range | 0.2 | +| entropy_loss | -7.07 | +| explained_variance | -0.155 | +| learning_rate | 1e-05 | +| loss | -0.0938 | +| n_updates | 2230 | +| policy_gradient_loss | -0.0791 | +| value_loss | 0.000117 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.193 | +| time/ | | +| fps | 327 | +| iterations | 79 | +| time_elapsed | 1973 | +| total_timesteps | 647168 | +| train/ | | +| approx_kl | 0.027257314 | +| clip_fraction | 0.271 | +| clip_range | 0.2 | +| entropy_loss | -7.05 | +| explained_variance | -0.0611 | +| learning_rate | 1e-05 | +| loss | -0.111 | +| n_updates | 2240 | +| policy_gradient_loss | -0.0746 | +| value_loss | 0.000149 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.19 | +| time/ | | +| fps | 327 | +| iterations | 80 | +| time_elapsed | 1998 | +| total_timesteps | 655360 | +| train/ | | +| approx_kl | 0.027558876 | +| clip_fraction | 0.277 | +| clip_range | 0.2 | +| entropy_loss | -6.95 | +| explained_variance | -0.0342 | +| learning_rate | 1e-05 | +| loss | -0.0995 | +| n_updates | 2250 | +| policy_gradient_loss | -0.0757 | +| value_loss | 0.000115 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.188 | +| time/ | | +| fps | 327 | +| iterations | 81 | +| time_elapsed | 2025 | +| total_timesteps | 663552 | +| train/ | | +| approx_kl | 0.02662745 | +| clip_fraction | 0.257 | +| clip_range | 0.2 | +| entropy_loss | -6.87 | +| explained_variance | 0.0118 | +| learning_rate | 1e-05 | +| loss | -0.104 | +| n_updates | 2260 | +| policy_gradient_loss | -0.0676 | +| value_loss | 0.000193 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.178 | +| time/ | | +| fps | 327 | +| iterations | 82 | +| time_elapsed | 2049 | +| total_timesteps | 671744 | +| train/ | | +| approx_kl | 0.027315453 | +| clip_fraction | 0.271 | +| clip_range | 0.2 | +| entropy_loss | -7.03 | +| explained_variance | -0.101 | +| learning_rate | 1e-05 | +| loss | -0.0979 | +| n_updates | 2270 | +| policy_gradient_loss | -0.0759 | +| value_loss | 0.000165 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.18 | +| time/ | | +| fps | 327 | +| iterations | 83 | +| time_elapsed | 2077 | +| total_timesteps | 679936 | +| train/ | | +| approx_kl | 0.026290985 | +| clip_fraction | 0.262 | +| clip_range | 0.2 | +| entropy_loss | -6.92 | +| explained_variance | 0.056 | +| learning_rate | 1e-05 | +| loss | -0.0861 | +| n_updates | 2280 | +| policy_gradient_loss | -0.0717 | +| value_loss | 0.000219 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | 0.17 | +| time/ | | +| fps | 327 | +| iterations | 84 | +| time_elapsed | 2101 | +| total_timesteps | 688128 | +| train/ | | +| approx_kl | 0.026773749 | +| clip_fraction | 0.257 | +| clip_range | 0.2 | +| entropy_loss | -6.92 | +| explained_variance | 0.0112 | +| learning_rate | 1e-05 | +| loss | -0.108 | +| n_updates | 2290 | +| policy_gradient_loss | -0.0705 | +| value_loss | 0.000237 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.187 | +| time/ | | +| fps | 327 | +| iterations | 85 | +| time_elapsed | 2126 | +| total_timesteps | 696320 | +| train/ | | +| approx_kl | 0.029155396 | +| clip_fraction | 0.296 | +| clip_range | 0.2 | +| entropy_loss | -6.94 | +| explained_variance | -0.00692 | +| learning_rate | 1e-05 | +| loss | -0.1 | +| n_updates | 2300 | +| policy_gradient_loss | -0.076 | +| value_loss | 0.000188 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | 0.184 | +| time/ | | +| fps | 327 | +| iterations | 86 | +| time_elapsed | 2151 | +| total_timesteps | 704512 | +| train/ | | +| approx_kl | 0.025808152 | +| clip_fraction | 0.257 | +| clip_range | 0.2 | +| entropy_loss | -6.74 | +| explained_variance | -0.135 | +| learning_rate | 1e-05 | +| loss | -0.111 | +| n_updates | 2310 | +| policy_gradient_loss | -0.0722 | +| value_loss | 0.000224 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.63e+03 | +| ep_rew_mean | 0.186 | +| time/ | | +| fps | 327 | +| iterations | 87 | +| time_elapsed | 2175 | +| total_timesteps | 712704 | +| train/ | | +| approx_kl | 0.028605167 | +| clip_fraction | 0.284 | +| clip_range | 0.2 | +| entropy_loss | -6.84 | +| explained_variance | -0.0712 | +| learning_rate | 1e-05 | +| loss | -0.103 | +| n_updates | 2320 | +| policy_gradient_loss | -0.0768 | +| value_loss | 0.000147 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.191 | +| time/ | | +| fps | 327 | +| iterations | 88 | +| time_elapsed | 2202 | +| total_timesteps | 720896 | +| train/ | | +| approx_kl | 0.028366437 | +| clip_fraction | 0.293 | +| clip_range | 0.2 | +| entropy_loss | -6.93 | +| explained_variance | -0.0666 | +| learning_rate | 1e-05 | +| loss | -0.108 | +| n_updates | 2330 | +| policy_gradient_loss | -0.0757 | +| value_loss | 0.000185 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.19 | +| time/ | | +| fps | 327 | +| iterations | 89 | +| time_elapsed | 2226 | +| total_timesteps | 729088 | +| train/ | | +| approx_kl | 0.02839619 | +| clip_fraction | 0.286 | +| clip_range | 0.2 | +| entropy_loss | -6.9 | +| explained_variance | -0.0862 | +| learning_rate | 1e-05 | +| loss | -0.1 | +| n_updates | 2340 | +| policy_gradient_loss | -0.0782 | +| value_loss | 0.000119 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.197 | +| time/ | | +| fps | 327 | +| iterations | 90 | +| time_elapsed | 2251 | +| total_timesteps | 737280 | +| train/ | | +| approx_kl | 0.028138794 | +| clip_fraction | 0.277 | +| clip_range | 0.2 | +| entropy_loss | -6.96 | +| explained_variance | -0.0291 | +| learning_rate | 1e-05 | +| loss | -0.109 | +| n_updates | 2350 | +| policy_gradient_loss | -0.0722 | +| value_loss | 0.00012 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.209 | +| time/ | | +| fps | 327 | +| iterations | 91 | +| time_elapsed | 2276 | +| total_timesteps | 745472 | +| train/ | | +| approx_kl | 0.030626347 | +| clip_fraction | 0.294 | +| clip_range | 0.2 | +| entropy_loss | -6.91 | +| explained_variance | -0.0656 | +| learning_rate | 1e-05 | +| loss | -0.102 | +| n_updates | 2360 | +| policy_gradient_loss | -0.0736 | +| value_loss | 0.00019 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.203 | +| time/ | | +| fps | 327 | +| iterations | 92 | +| time_elapsed | 2301 | +| total_timesteps | 753664 | +| train/ | | +| approx_kl | 0.028051782 | +| clip_fraction | 0.287 | +| clip_range | 0.2 | +| entropy_loss | -6.86 | +| explained_variance | -0.15 | +| learning_rate | 1e-05 | +| loss | -0.113 | +| n_updates | 2370 | +| policy_gradient_loss | -0.077 | +| value_loss | 0.000177 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.202 | +| time/ | | +| fps | 327 | +| iterations | 93 | +| time_elapsed | 2327 | +| total_timesteps | 761856 | +| train/ | | +| approx_kl | 0.027255952 | +| clip_fraction | 0.261 | +| clip_range | 0.2 | +| entropy_loss | -6.91 | +| explained_variance | -0.0349 | +| learning_rate | 1e-05 | +| loss | -0.0887 | +| n_updates | 2380 | +| policy_gradient_loss | -0.0707 | +| value_loss | 0.000176 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.203 | +| time/ | | +| fps | 327 | +| iterations | 94 | +| time_elapsed | 2352 | +| total_timesteps | 770048 | +| train/ | | +| approx_kl | 0.028648807 | +| clip_fraction | 0.283 | +| clip_range | 0.2 | +| entropy_loss | -6.93 | +| explained_variance | -0.0601 | +| learning_rate | 1e-05 | +| loss | -0.101 | +| n_updates | 2390 | +| policy_gradient_loss | -0.073 | +| value_loss | 0.000169 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.197 | +| time/ | | +| fps | 327 | +| iterations | 95 | +| time_elapsed | 2378 | +| total_timesteps | 778240 | +| train/ | | +| approx_kl | 0.027264237 | +| clip_fraction | 0.267 | +| clip_range | 0.2 | +| entropy_loss | -6.77 | +| explained_variance | -0.0837 | +| learning_rate | 1e-05 | +| loss | -0.113 | +| n_updates | 2400 | +| policy_gradient_loss | -0.0717 | +| value_loss | 0.000166 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.196 | +| time/ | | +| fps | 327 | +| iterations | 96 | +| time_elapsed | 2403 | +| total_timesteps | 786432 | +| train/ | | +| approx_kl | 0.029162262 | +| clip_fraction | 0.286 | +| clip_range | 0.2 | +| entropy_loss | -6.92 | +| explained_variance | -0.0486 | +| learning_rate | 1e-05 | +| loss | -0.107 | +| n_updates | 2410 | +| policy_gradient_loss | -0.0754 | +| value_loss | 0.000161 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.191 | +| time/ | | +| fps | 327 | +| iterations | 97 | +| time_elapsed | 2428 | +| total_timesteps | 794624 | +| train/ | | +| approx_kl | 0.027706789 | +| clip_fraction | 0.274 | +| clip_range | 0.2 | +| entropy_loss | -6.95 | +| explained_variance | -0.117 | +| learning_rate | 1e-05 | +| loss | -0.0989 | +| n_updates | 2420 | +| policy_gradient_loss | -0.0739 | +| value_loss | 0.00018 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.195 | +| time/ | | +| fps | 327 | +| iterations | 98 | +| time_elapsed | 2453 | +| total_timesteps | 802816 | +| train/ | | +| approx_kl | 0.027352247 | +| clip_fraction | 0.272 | +| clip_range | 0.2 | +| entropy_loss | -6.88 | +| explained_variance | -0.0239 | +| learning_rate | 1e-05 | +| loss | -0.0922 | +| n_updates | 2430 | +| policy_gradient_loss | -0.0694 | +| value_loss | 0.000174 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.201 | +| time/ | | +| fps | 327 | +| iterations | 99 | +| time_elapsed | 2478 | +| total_timesteps | 811008 | +| train/ | | +| approx_kl | 0.030165147 | +| clip_fraction | 0.288 | +| clip_range | 0.2 | +| entropy_loss | -6.85 | +| explained_variance | -0.0119 | +| learning_rate | 1e-05 | +| loss | -0.102 | +| n_updates | 2440 | +| policy_gradient_loss | -0.0732 | +| value_loss | 0.000196 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.197 | +| time/ | | +| fps | 327 | +| iterations | 100 | +| time_elapsed | 2504 | +| total_timesteps | 819200 | +| train/ | | +| approx_kl | 0.029321907 | +| clip_fraction | 0.28 | +| clip_range | 0.2 | +| entropy_loss | -6.79 | +| explained_variance | -0.0395 | +| learning_rate | 1e-05 | +| loss | -0.109 | +| n_updates | 2450 | +| policy_gradient_loss | -0.0735 | +| value_loss | 0.000224 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.197 | +| time/ | | +| fps | 327 | +| iterations | 101 | +| time_elapsed | 2529 | +| total_timesteps | 827392 | +| train/ | | +| approx_kl | 0.027969323 | +| clip_fraction | 0.278 | +| clip_range | 0.2 | +| entropy_loss | -6.91 | +| explained_variance | -0.178 | +| learning_rate | 1e-05 | +| loss | -0.0956 | +| n_updates | 2460 | +| policy_gradient_loss | -0.0705 | +| value_loss | 0.000168 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.19 | +| time/ | | +| fps | 326 | +| iterations | 102 | +| time_elapsed | 2555 | +| total_timesteps | 835584 | +| train/ | | +| approx_kl | 0.030471638 | +| clip_fraction | 0.3 | +| clip_range | 0.2 | +| entropy_loss | -6.93 | +| explained_variance | -0.0627 | +| learning_rate | 1e-05 | +| loss | -0.0962 | +| n_updates | 2470 | +| policy_gradient_loss | -0.0743 | +| value_loss | 0.000208 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.198 | +| time/ | | +| fps | 327 | +| iterations | 103 | +| time_elapsed | 2580 | +| total_timesteps | 843776 | +| train/ | | +| approx_kl | 0.025988178 | +| clip_fraction | 0.287 | +| clip_range | 0.2 | +| entropy_loss | -6.81 | +| explained_variance | 0.102 | +| learning_rate | 1e-05 | +| loss | -0.0986 | +| n_updates | 2480 | +| policy_gradient_loss | -0.0736 | +| value_loss | 0.000129 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.206 | +| time/ | | +| fps | 327 | +| iterations | 104 | +| time_elapsed | 2604 | +| total_timesteps | 851968 | +| train/ | | +| approx_kl | 0.027657364 | +| clip_fraction | 0.271 | +| clip_range | 0.2 | +| entropy_loss | -6.73 | +| explained_variance | -0.0237 | +| learning_rate | 1e-05 | +| loss | -0.102 | +| n_updates | 2490 | +| policy_gradient_loss | -0.0709 | +| value_loss | 0.000273 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.201 | +| time/ | | +| fps | 327 | +| iterations | 105 | +| time_elapsed | 2628 | +| total_timesteps | 860160 | +| train/ | | +| approx_kl | 0.029009344 | +| clip_fraction | 0.302 | +| clip_range | 0.2 | +| entropy_loss | -6.74 | +| explained_variance | -0.226 | +| learning_rate | 1e-05 | +| loss | -0.121 | +| n_updates | 2500 | +| policy_gradient_loss | -0.0784 | +| value_loss | 0.000138 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.201 | +| time/ | | +| fps | 327 | +| iterations | 106 | +| time_elapsed | 2653 | +| total_timesteps | 868352 | +| train/ | | +| approx_kl | 0.02937651 | +| clip_fraction | 0.293 | +| clip_range | 0.2 | +| entropy_loss | -6.73 | +| explained_variance | -0.109 | +| learning_rate | 1e-05 | +| loss | -0.0975 | +| n_updates | 2510 | +| policy_gradient_loss | -0.0735 | +| value_loss | 0.000155 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.191 | +| time/ | | +| fps | 327 | +| iterations | 107 | +| time_elapsed | 2679 | +| total_timesteps | 876544 | +| train/ | | +| approx_kl | 0.02913464 | +| clip_fraction | 0.276 | +| clip_range | 0.2 | +| entropy_loss | -6.94 | +| explained_variance | -0.0631 | +| learning_rate | 1e-05 | +| loss | -0.0878 | +| n_updates | 2520 | +| policy_gradient_loss | -0.072 | +| value_loss | 0.000211 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.78e+03 | +| ep_rew_mean | 0.187 | +| time/ | | +| fps | 327 | +| iterations | 108 | +| time_elapsed | 2703 | +| total_timesteps | 884736 | +| train/ | | +| approx_kl | 0.027747024 | +| clip_fraction | 0.282 | +| clip_range | 0.2 | +| entropy_loss | -6.81 | +| explained_variance | -0.069 | +| learning_rate | 1e-05 | +| loss | -0.101 | +| n_updates | 2530 | +| policy_gradient_loss | -0.0741 | +| value_loss | 0.000148 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.78e+03 | +| ep_rew_mean | 0.202 | +| time/ | | +| fps | 327 | +| iterations | 109 | +| time_elapsed | 2729 | +| total_timesteps | 892928 | +| train/ | | +| approx_kl | 0.031071194 | +| clip_fraction | 0.318 | +| clip_range | 0.2 | +| entropy_loss | -6.73 | +| explained_variance | -0.0434 | +| learning_rate | 1e-05 | +| loss | -0.102 | +| n_updates | 2540 | +| policy_gradient_loss | -0.0753 | +| value_loss | 0.000158 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.194 | +| time/ | | +| fps | 327 | +| iterations | 110 | +| time_elapsed | 2755 | +| total_timesteps | 901120 | +| train/ | | +| approx_kl | 0.027999472 | +| clip_fraction | 0.272 | +| clip_range | 0.2 | +| entropy_loss | -6.75 | +| explained_variance | -0.0611 | +| learning_rate | 1e-05 | +| loss | -0.0814 | +| n_updates | 2550 | +| policy_gradient_loss | -0.0709 | +| value_loss | 0.000222 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.2 | +| time/ | | +| fps | 327 | +| iterations | 111 | +| time_elapsed | 2780 | +| total_timesteps | 909312 | +| train/ | | +| approx_kl | 0.027230646 | +| clip_fraction | 0.285 | +| clip_range | 0.2 | +| entropy_loss | -6.54 | +| explained_variance | -0.132 | +| learning_rate | 1e-05 | +| loss | -0.0891 | +| n_updates | 2560 | +| policy_gradient_loss | -0.0723 | +| value_loss | 0.000181 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.202 | +| time/ | | +| fps | 326 | +| iterations | 112 | +| time_elapsed | 2807 | +| total_timesteps | 917504 | +| train/ | | +| approx_kl | 0.030129144 | +| clip_fraction | 0.295 | +| clip_range | 0.2 | +| entropy_loss | -6.91 | +| explained_variance | -0.0463 | +| learning_rate | 1e-05 | +| loss | -0.114 | +| n_updates | 2570 | +| policy_gradient_loss | -0.0721 | +| value_loss | 0.000195 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.198 | +| time/ | | +| fps | 326 | +| iterations | 113 | +| time_elapsed | 2832 | +| total_timesteps | 925696 | +| train/ | | +| approx_kl | 0.03108217 | +| clip_fraction | 0.315 | +| clip_range | 0.2 | +| entropy_loss | -6.74 | +| explained_variance | -0.107 | +| learning_rate | 1e-05 | +| loss | -0.115 | +| n_updates | 2580 | +| policy_gradient_loss | -0.0766 | +| value_loss | 0.000176 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.21 | +| time/ | | +| fps | 326 | +| iterations | 114 | +| time_elapsed | 2857 | +| total_timesteps | 933888 | +| train/ | | +| approx_kl | 0.030777764 | +| clip_fraction | 0.294 | +| clip_range | 0.2 | +| entropy_loss | -6.74 | +| explained_variance | -0.086 | +| learning_rate | 1e-05 | +| loss | -0.0943 | +| n_updates | 2590 | +| policy_gradient_loss | -0.0709 | +| value_loss | 0.000237 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.203 | +| time/ | | +| fps | 326 | +| iterations | 115 | +| time_elapsed | 2882 | +| total_timesteps | 942080 | +| train/ | | +| approx_kl | 0.029392902 | +| clip_fraction | 0.289 | +| clip_range | 0.2 | +| entropy_loss | -6.82 | +| explained_variance | -0.125 | +| learning_rate | 1e-05 | +| loss | -0.092 | +| n_updates | 2600 | +| policy_gradient_loss | -0.0752 | +| value_loss | 0.000195 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.196 | +| time/ | | +| fps | 326 | +| iterations | 116 | +| time_elapsed | 2907 | +| total_timesteps | 950272 | +| train/ | | +| approx_kl | 0.028991774 | +| clip_fraction | 0.293 | +| clip_range | 0.2 | +| entropy_loss | -6.68 | +| explained_variance | -0.0925 | +| learning_rate | 1e-05 | +| loss | -0.11 | +| n_updates | 2610 | +| policy_gradient_loss | -0.0725 | +| value_loss | 0.000145 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.207 | +| time/ | | +| fps | 326 | +| iterations | 117 | +| time_elapsed | 2934 | +| total_timesteps | 958464 | +| train/ | | +| approx_kl | 0.030781427 | +| clip_fraction | 0.298 | +| clip_range | 0.2 | +| entropy_loss | -6.66 | +| explained_variance | -0.0302 | +| learning_rate | 1e-05 | +| loss | -0.106 | +| n_updates | 2620 | +| policy_gradient_loss | -0.0736 | +| value_loss | 0.000179 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.202 | +| time/ | | +| fps | 326 | +| iterations | 118 | +| time_elapsed | 2958 | +| total_timesteps | 966656 | +| train/ | | +| approx_kl | 0.030820765 | +| clip_fraction | 0.302 | +| clip_range | 0.2 | +| entropy_loss | -6.55 | +| explained_variance | -0.0677 | +| learning_rate | 1e-05 | +| loss | -0.104 | +| n_updates | 2630 | +| policy_gradient_loss | -0.0758 | +| value_loss | 0.000188 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.212 | +| time/ | | +| fps | 326 | +| iterations | 119 | +| time_elapsed | 2983 | +| total_timesteps | 974848 | +| train/ | | +| approx_kl | 0.031689454 | +| clip_fraction | 0.306 | +| clip_range | 0.2 | +| entropy_loss | -6.72 | +| explained_variance | -0.086 | +| learning_rate | 1e-05 | +| loss | -0.0957 | +| n_updates | 2640 | +| policy_gradient_loss | -0.0738 | +| value_loss | 0.000267 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.199 | +| time/ | | +| fps | 326 | +| iterations | 120 | +| time_elapsed | 3007 | +| total_timesteps | 983040 | +| train/ | | +| approx_kl | 0.031562798 | +| clip_fraction | 0.301 | +| clip_range | 0.2 | +| entropy_loss | -6.63 | +| explained_variance | -0.0433 | +| learning_rate | 1e-05 | +| loss | -0.103 | +| n_updates | 2650 | +| policy_gradient_loss | -0.0757 | +| value_loss | 0.000241 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.203 | +| time/ | | +| fps | 326 | +| iterations | 121 | +| time_elapsed | 3033 | +| total_timesteps | 991232 | +| train/ | | +| approx_kl | 0.029139122 | +| clip_fraction | 0.302 | +| clip_range | 0.2 | +| entropy_loss | -6.62 | +| explained_variance | -0.219 | +| learning_rate | 1e-05 | +| loss | -0.106 | +| n_updates | 2660 | +| policy_gradient_loss | -0.0776 | +| value_loss | 0.000147 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.211 | +| time/ | | +| fps | 326 | +| iterations | 122 | +| time_elapsed | 3058 | +| total_timesteps | 999424 | +| train/ | | +| approx_kl | 0.029234827 | +| clip_fraction | 0.286 | +| clip_range | 0.2 | +| entropy_loss | -6.78 | +| explained_variance | -0.0397 | +| learning_rate | 1e-05 | +| loss | -0.105 | +| n_updates | 2670 | +| policy_gradient_loss | -0.0716 | +| value_loss | 0.000138 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.22 | +| time/ | | +| fps | 326 | +| iterations | 123 | +| time_elapsed | 3084 | +| total_timesteps | 1007616 | +| train/ | | +| approx_kl | 0.03228468 | +| clip_fraction | 0.316 | +| clip_range | 0.2 | +| entropy_loss | -6.71 | +| explained_variance | -0.0574 | +| learning_rate | 1e-05 | +| loss | -0.109 | +| n_updates | 2680 | +| policy_gradient_loss | -0.0791 | +| value_loss | 0.000124 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.224 | +| time/ | | +| fps | 326 | +| iterations | 124 | +| time_elapsed | 3111 | +| total_timesteps | 1015808 | +| train/ | | +| approx_kl | 0.031846367 | +| clip_fraction | 0.304 | +| clip_range | 0.2 | +| entropy_loss | -6.67 | +| explained_variance | -0.107 | +| learning_rate | 1e-05 | +| loss | -0.101 | +| n_updates | 2690 | +| policy_gradient_loss | -0.0758 | +| value_loss | 0.000219 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.223 | +| time/ | | +| fps | 326 | +| iterations | 125 | +| time_elapsed | 3135 | +| total_timesteps | 1024000 | +| train/ | | +| approx_kl | 0.03248063 | +| clip_fraction | 0.317 | +| clip_range | 0.2 | +| entropy_loss | -6.68 | +| explained_variance | -0.111 | +| learning_rate | 1e-05 | +| loss | -0.115 | +| n_updates | 2700 | +| policy_gradient_loss | -0.079 | +| value_loss | 0.000177 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.22 | +| time/ | | +| fps | 326 | +| iterations | 126 | +| time_elapsed | 3161 | +| total_timesteps | 1032192 | +| train/ | | +| approx_kl | 0.030748092 | +| clip_fraction | 0.292 | +| clip_range | 0.2 | +| entropy_loss | -6.7 | +| explained_variance | -0.0115 | +| learning_rate | 1e-05 | +| loss | -0.11 | +| n_updates | 2710 | +| policy_gradient_loss | -0.0704 | +| value_loss | 0.000217 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.221 | +| time/ | | +| fps | 326 | +| iterations | 127 | +| time_elapsed | 3185 | +| total_timesteps | 1040384 | +| train/ | | +| approx_kl | 0.032510377 | +| clip_fraction | 0.314 | +| clip_range | 0.2 | +| entropy_loss | -6.65 | +| explained_variance | -0.163 | +| learning_rate | 1e-05 | +| loss | -0.118 | +| n_updates | 2720 | +| policy_gradient_loss | -0.0759 | +| value_loss | 0.000183 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.229 | +| time/ | | +| fps | 326 | +| iterations | 128 | +| time_elapsed | 3211 | +| total_timesteps | 1048576 | +| train/ | | +| approx_kl | 0.029900994 | +| clip_fraction | 0.308 | +| clip_range | 0.2 | +| entropy_loss | -6.56 | +| explained_variance | -0.0722 | +| learning_rate | 1e-05 | +| loss | -0.121 | +| n_updates | 2730 | +| policy_gradient_loss | -0.0725 | +| value_loss | 0.000182 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.239 | +| time/ | | +| fps | 326 | +| iterations | 129 | +| time_elapsed | 3237 | +| total_timesteps | 1056768 | +| train/ | | +| approx_kl | 0.03209553 | +| clip_fraction | 0.305 | +| clip_range | 0.2 | +| entropy_loss | -6.64 | +| explained_variance | -0.0691 | +| learning_rate | 1e-05 | +| loss | -0.0848 | +| n_updates | 2740 | +| policy_gradient_loss | -0.0732 | +| value_loss | 0.000207 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.236 | +| time/ | | +| fps | 326 | +| iterations | 130 | +| time_elapsed | 3261 | +| total_timesteps | 1064960 | +| train/ | | +| approx_kl | 0.029885024 | +| clip_fraction | 0.303 | +| clip_range | 0.2 | +| entropy_loss | -6.73 | +| explained_variance | -0.0631 | +| learning_rate | 1e-05 | +| loss | -0.109 | +| n_updates | 2750 | +| policy_gradient_loss | -0.0757 | +| value_loss | 0.000174 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.231 | +| time/ | | +| fps | 326 | +| iterations | 131 | +| time_elapsed | 3288 | +| total_timesteps | 1073152 | +| train/ | | +| approx_kl | 0.032808863 | +| clip_fraction | 0.327 | +| clip_range | 0.2 | +| entropy_loss | -6.66 | +| explained_variance | -0.0701 | +| learning_rate | 1e-05 | +| loss | -0.0996 | +| n_updates | 2760 | +| policy_gradient_loss | -0.0779 | +| value_loss | 0.000132 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.231 | +| time/ | | +| fps | 326 | +| iterations | 132 | +| time_elapsed | 3313 | +| total_timesteps | 1081344 | +| train/ | | +| approx_kl | 0.033111222 | +| clip_fraction | 0.317 | +| clip_range | 0.2 | +| entropy_loss | -6.64 | +| explained_variance | -0.0546 | +| learning_rate | 1e-05 | +| loss | -0.0967 | +| n_updates | 2770 | +| policy_gradient_loss | -0.0751 | +| value_loss | 0.000161 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.217 | +| time/ | | +| fps | 326 | +| iterations | 133 | +| time_elapsed | 3339 | +| total_timesteps | 1089536 | +| train/ | | +| approx_kl | 0.030845106 | +| clip_fraction | 0.296 | +| clip_range | 0.2 | +| entropy_loss | -6.55 | +| explained_variance | -0.0653 | +| learning_rate | 1e-05 | +| loss | -0.101 | +| n_updates | 2780 | +| policy_gradient_loss | -0.0733 | +| value_loss | 0.000212 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.212 | +| time/ | | +| fps | 326 | +| iterations | 134 | +| time_elapsed | 3363 | +| total_timesteps | 1097728 | +| train/ | | +| approx_kl | 0.030438457 | +| clip_fraction | 0.307 | +| clip_range | 0.2 | +| entropy_loss | -6.61 | +| explained_variance | -0.0723 | +| learning_rate | 1e-05 | +| loss | -0.103 | +| n_updates | 2790 | +| policy_gradient_loss | -0.071 | +| value_loss | 0.000233 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.217 | +| time/ | | +| fps | 326 | +| iterations | 135 | +| time_elapsed | 3388 | +| total_timesteps | 1105920 | +| train/ | | +| approx_kl | 0.03325868 | +| clip_fraction | 0.325 | +| clip_range | 0.2 | +| entropy_loss | -6.74 | +| explained_variance | -0.184 | +| learning_rate | 1e-05 | +| loss | -0.118 | +| n_updates | 2800 | +| policy_gradient_loss | -0.079 | +| value_loss | 0.000159 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.215 | +| time/ | | +| fps | 326 | +| iterations | 136 | +| time_elapsed | 3414 | +| total_timesteps | 1114112 | +| train/ | | +| approx_kl | 0.028465614 | +| clip_fraction | 0.299 | +| clip_range | 0.2 | +| entropy_loss | -6.37 | +| explained_variance | 0.0571 | +| learning_rate | 1e-05 | +| loss | -0.0929 | +| n_updates | 2810 | +| policy_gradient_loss | -0.0629 | +| value_loss | 0.000292 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.217 | +| time/ | | +| fps | 326 | +| iterations | 137 | +| time_elapsed | 3439 | +| total_timesteps | 1122304 | +| train/ | | +| approx_kl | 0.03070428 | +| clip_fraction | 0.308 | +| clip_range | 0.2 | +| entropy_loss | -6.62 | +| explained_variance | -0.0138 | +| learning_rate | 1e-05 | +| loss | -0.107 | +| n_updates | 2820 | +| policy_gradient_loss | -0.0775 | +| value_loss | 0.00017 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.196 | +| time/ | | +| fps | 326 | +| iterations | 138 | +| time_elapsed | 3466 | +| total_timesteps | 1130496 | +| train/ | | +| approx_kl | 0.032442547 | +| clip_fraction | 0.31 | +| clip_range | 0.2 | +| entropy_loss | -6.76 | +| explained_variance | -0.0724 | +| learning_rate | 1e-05 | +| loss | -0.118 | +| n_updates | 2830 | +| policy_gradient_loss | -0.0742 | +| value_loss | 0.00014 | +----------------------------------------- +Early stopping at step 9 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.203 | +| time/ | | +| fps | 326 | +| iterations | 139 | +| time_elapsed | 3490 | +| total_timesteps | 1138688 | +| train/ | | +| approx_kl | 0.03434139 | +| clip_fraction | 0.326 | +| clip_range | 0.2 | +| entropy_loss | -6.52 | +| explained_variance | -0.0425 | +| learning_rate | 1e-05 | +| loss | -0.095 | +| n_updates | 2840 | +| policy_gradient_loss | -0.0761 | +| value_loss | 0.000147 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.207 | +| time/ | | +| fps | 326 | +| iterations | 140 | +| time_elapsed | 3517 | +| total_timesteps | 1146880 | +| train/ | | +| approx_kl | 0.032933764 | +| clip_fraction | 0.327 | +| clip_range | 0.2 | +| entropy_loss | -6.4 | +| explained_variance | -0.0356 | +| learning_rate | 1e-05 | +| loss | -0.101 | +| n_updates | 2850 | +| policy_gradient_loss | -0.0757 | +| value_loss | 0.000188 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.186 | +| time/ | | +| fps | 326 | +| iterations | 141 | +| time_elapsed | 3542 | +| total_timesteps | 1155072 | +| train/ | | +| approx_kl | 0.03285028 | +| clip_fraction | 0.316 | +| clip_range | 0.2 | +| entropy_loss | -6.64 | +| explained_variance | -0.00417 | +| learning_rate | 1e-05 | +| loss | -0.107 | +| n_updates | 2860 | +| policy_gradient_loss | -0.0753 | +| value_loss | 0.000181 | +---------------------------------------- +Early stopping at step 9 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.8e+03 | +| ep_rew_mean | 0.194 | +| time/ | | +| fps | 326 | +| iterations | 142 | +| time_elapsed | 3567 | +| total_timesteps | 1163264 | +| train/ | | +| approx_kl | 0.03411108 | +| clip_fraction | 0.316 | +| clip_range | 0.2 | +| entropy_loss | -6.54 | +| explained_variance | -0.275 | +| learning_rate | 1e-05 | +| loss | -0.107 | +| n_updates | 2870 | +| policy_gradient_loss | -0.0769 | +| value_loss | 0.000141 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.8e+03 | +| ep_rew_mean | 0.2 | +| time/ | | +| fps | 326 | +| iterations | 143 | +| time_elapsed | 3592 | +| total_timesteps | 1171456 | +| train/ | | +| approx_kl | 0.033133425 | +| clip_fraction | 0.32 | +| clip_range | 0.2 | +| entropy_loss | -6.55 | +| explained_variance | -0.077 | +| learning_rate | 1e-05 | +| loss | -0.1 | +| n_updates | 2880 | +| policy_gradient_loss | -0.0752 | +| value_loss | 0.000149 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.198 | +| time/ | | +| fps | 326 | +| iterations | 144 | +| time_elapsed | 3617 | +| total_timesteps | 1179648 | +| train/ | | +| approx_kl | 0.032359906 | +| clip_fraction | 0.31 | +| clip_range | 0.2 | +| entropy_loss | -6.44 | +| explained_variance | -0.119 | +| learning_rate | 1e-05 | +| loss | -0.109 | +| n_updates | 2890 | +| policy_gradient_loss | -0.0748 | +| value_loss | 0.000144 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.206 | +| time/ | | +| fps | 325 | +| iterations | 145 | +| time_elapsed | 3644 | +| total_timesteps | 1187840 | +| train/ | | +| approx_kl | 0.034890193 | +| clip_fraction | 0.336 | +| clip_range | 0.2 | +| entropy_loss | -6.56 | +| explained_variance | -0.0799 | +| learning_rate | 1e-05 | +| loss | -0.0964 | +| n_updates | 2900 | +| policy_gradient_loss | -0.0781 | +| value_loss | 0.000221 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.81e+03 | +| ep_rew_mean | 0.206 | +| time/ | | +| fps | 325 | +| iterations | 146 | +| time_elapsed | 3668 | +| total_timesteps | 1196032 | +| train/ | | +| approx_kl | 0.031107485 | +| clip_fraction | 0.3 | +| clip_range | 0.2 | +| entropy_loss | -6.52 | +| explained_variance | -0.189 | +| learning_rate | 1e-05 | +| loss | -0.105 | +| n_updates | 2910 | +| policy_gradient_loss | -0.0719 | +| value_loss | 0.000226 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.8e+03 | +| ep_rew_mean | 0.208 | +| time/ | | +| fps | 325 | +| iterations | 147 | +| time_elapsed | 3694 | +| total_timesteps | 1204224 | +| train/ | | +| approx_kl | 0.032152005 | +| clip_fraction | 0.309 | +| clip_range | 0.2 | +| entropy_loss | -6.52 | +| explained_variance | -0.101 | +| learning_rate | 1e-05 | +| loss | -0.113 | +| n_updates | 2920 | +| policy_gradient_loss | -0.0729 | +| value_loss | 0.000182 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.212 | +| time/ | | +| fps | 325 | +| iterations | 148 | +| time_elapsed | 3719 | +| total_timesteps | 1212416 | +| train/ | | +| approx_kl | 0.033708118 | +| clip_fraction | 0.324 | +| clip_range | 0.2 | +| entropy_loss | -6.53 | +| explained_variance | -0.045 | +| learning_rate | 1e-05 | +| loss | -0.0995 | +| n_updates | 2930 | +| policy_gradient_loss | -0.0757 | +| value_loss | 0.000198 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.8e+03 | +| ep_rew_mean | 0.2 | +| time/ | | +| fps | 325 | +| iterations | 149 | +| time_elapsed | 3744 | +| total_timesteps | 1220608 | +| train/ | | +| approx_kl | 0.03398321 | +| clip_fraction | 0.332 | +| clip_range | 0.2 | +| entropy_loss | -6.52 | +| explained_variance | -0.148 | +| learning_rate | 1e-05 | +| loss | -0.102 | +| n_updates | 2940 | +| policy_gradient_loss | -0.077 | +| value_loss | 0.000145 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.8e+03 | +| ep_rew_mean | 0.187 | +| time/ | | +| fps | 325 | +| iterations | 150 | +| time_elapsed | 3772 | +| total_timesteps | 1228800 | +| train/ | | +| approx_kl | 0.032763116 | +| clip_fraction | 0.317 | +| clip_range | 0.2 | +| entropy_loss | -6.5 | +| explained_variance | -0.0496 | +| learning_rate | 1e-05 | +| loss | -0.106 | +| n_updates | 2950 | +| policy_gradient_loss | -0.0725 | +| value_loss | 0.000182 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.78e+03 | +| ep_rew_mean | 0.183 | +| time/ | | +| fps | 325 | +| iterations | 151 | +| time_elapsed | 3795 | +| total_timesteps | 1236992 | +| train/ | | +| approx_kl | 0.033449538 | +| clip_fraction | 0.329 | +| clip_range | 0.2 | +| entropy_loss | -6.6 | +| explained_variance | -0.14 | +| learning_rate | 1e-05 | +| loss | -0.112 | +| n_updates | 2960 | +| policy_gradient_loss | -0.0761 | +| value_loss | 0.000166 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.8e+03 | +| ep_rew_mean | 0.188 | +| time/ | | +| fps | 325 | +| iterations | 152 | +| time_elapsed | 3822 | +| total_timesteps | 1245184 | +| train/ | | +| approx_kl | 0.03459966 | +| clip_fraction | 0.328 | +| clip_range | 0.2 | +| entropy_loss | -6.57 | +| explained_variance | -0.0728 | +| learning_rate | 1e-05 | +| loss | -0.106 | +| n_updates | 2970 | +| policy_gradient_loss | -0.0777 | +| value_loss | 0.000151 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.82e+03 | +| ep_rew_mean | 0.195 | +| time/ | | +| fps | 325 | +| iterations | 153 | +| time_elapsed | 3847 | +| total_timesteps | 1253376 | +| train/ | | +| approx_kl | 0.035707712 | +| clip_fraction | 0.35 | +| clip_range | 0.2 | +| entropy_loss | -6.53 | +| explained_variance | -0.181 | +| learning_rate | 1e-05 | +| loss | -0.103 | +| n_updates | 2980 | +| policy_gradient_loss | -0.08 | +| value_loss | 0.000164 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.191 | +| time/ | | +| fps | 325 | +| iterations | 154 | +| time_elapsed | 3873 | +| total_timesteps | 1261568 | +| train/ | | +| approx_kl | 0.03071127 | +| clip_fraction | 0.291 | +| clip_range | 0.2 | +| entropy_loss | -6.62 | +| explained_variance | -0.126 | +| learning_rate | 1e-05 | +| loss | -0.101 | +| n_updates | 2990 | +| policy_gradient_loss | -0.0704 | +| value_loss | 0.000133 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.197 | +| time/ | | +| fps | 325 | +| iterations | 155 | +| time_elapsed | 3898 | +| total_timesteps | 1269760 | +| train/ | | +| approx_kl | 0.033001166 | +| clip_fraction | 0.317 | +| clip_range | 0.2 | +| entropy_loss | -6.33 | +| explained_variance | -0.0595 | +| learning_rate | 1e-05 | +| loss | -0.0873 | +| n_updates | 3000 | +| policy_gradient_loss | -0.0737 | +| value_loss | 0.000139 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.202 | +| time/ | | +| fps | 325 | +| iterations | 156 | +| time_elapsed | 3923 | +| total_timesteps | 1277952 | +| train/ | | +| approx_kl | 0.037322953 | +| clip_fraction | 0.351 | +| clip_range | 0.2 | +| entropy_loss | -6.53 | +| explained_variance | -0.118 | +| learning_rate | 1e-05 | +| loss | -0.112 | +| n_updates | 3010 | +| policy_gradient_loss | -0.0764 | +| value_loss | 0.000136 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.2 | +| time/ | | +| fps | 325 | +| iterations | 157 | +| time_elapsed | 3949 | +| total_timesteps | 1286144 | +| train/ | | +| approx_kl | 0.03257921 | +| clip_fraction | 0.308 | +| clip_range | 0.2 | +| entropy_loss | -6.39 | +| explained_variance | -0.0389 | +| learning_rate | 1e-05 | +| loss | -0.0918 | +| n_updates | 3020 | +| policy_gradient_loss | -0.075 | +| value_loss | 0.000224 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.8e+03 | +| ep_rew_mean | 0.205 | +| time/ | | +| fps | 325 | +| iterations | 158 | +| time_elapsed | 3974 | +| total_timesteps | 1294336 | +| train/ | | +| approx_kl | 0.032728054 | +| clip_fraction | 0.312 | +| clip_range | 0.2 | +| entropy_loss | -6.43 | +| explained_variance | -0.0696 | +| learning_rate | 1e-05 | +| loss | -0.0912 | +| n_updates | 3030 | +| policy_gradient_loss | -0.0757 | +| value_loss | 0.000204 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.81e+03 | +| ep_rew_mean | 0.214 | +| time/ | | +| fps | 325 | +| iterations | 159 | +| time_elapsed | 4001 | +| total_timesteps | 1302528 | +| train/ | | +| approx_kl | 0.032797147 | +| clip_fraction | 0.322 | +| clip_range | 0.2 | +| entropy_loss | -6.5 | +| explained_variance | -0.0106 | +| learning_rate | 1e-05 | +| loss | -0.099 | +| n_updates | 3040 | +| policy_gradient_loss | -0.072 | +| value_loss | 0.000221 | +----------------------------------------- +Early stopping at step 9 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.81e+03 | +| ep_rew_mean | 0.235 | +| time/ | | +| fps | 325 | +| iterations | 160 | +| time_elapsed | 4025 | +| total_timesteps | 1310720 | +| train/ | | +| approx_kl | 0.035665188 | +| clip_fraction | 0.336 | +| clip_range | 0.2 | +| entropy_loss | -6.45 | +| explained_variance | -0.0454 | +| learning_rate | 1e-05 | +| loss | -0.118 | +| n_updates | 3050 | +| policy_gradient_loss | -0.0794 | +| value_loss | 0.000166 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.8e+03 | +| ep_rew_mean | 0.237 | +| time/ | | +| fps | 325 | +| iterations | 161 | +| time_elapsed | 4050 | +| total_timesteps | 1318912 | +| train/ | | +| approx_kl | 0.034532305 | +| clip_fraction | 0.314 | +| clip_range | 0.2 | +| entropy_loss | -6.56 | +| explained_variance | -0.00779 | +| learning_rate | 1e-05 | +| loss | -0.104 | +| n_updates | 3060 | +| policy_gradient_loss | -0.0709 | +| value_loss | 0.000266 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.81e+03 | +| ep_rew_mean | 0.234 | +| time/ | | +| fps | 325 | +| iterations | 162 | +| time_elapsed | 4075 | +| total_timesteps | 1327104 | +| train/ | | +| approx_kl | 0.034062438 | +| clip_fraction | 0.338 | +| clip_range | 0.2 | +| entropy_loss | -6.45 | +| explained_variance | -0.0989 | +| learning_rate | 1e-05 | +| loss | -0.0989 | +| n_updates | 3070 | +| policy_gradient_loss | -0.0805 | +| value_loss | 0.000223 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.82e+03 | +| ep_rew_mean | 0.236 | +| time/ | | +| fps | 325 | +| iterations | 163 | +| time_elapsed | 4100 | +| total_timesteps | 1335296 | +| train/ | | +| approx_kl | 0.032870576 | +| clip_fraction | 0.326 | +| clip_range | 0.2 | +| entropy_loss | -6.47 | +| explained_variance | -0.0891 | +| learning_rate | 1e-05 | +| loss | -0.109 | +| n_updates | 3080 | +| policy_gradient_loss | -0.0775 | +| value_loss | 0.000177 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.82e+03 | +| ep_rew_mean | 0.24 | +| time/ | | +| fps | 325 | +| iterations | 164 | +| time_elapsed | 4128 | +| total_timesteps | 1343488 | +| train/ | | +| approx_kl | 0.03415974 | +| clip_fraction | 0.336 | +| clip_range | 0.2 | +| entropy_loss | -6.38 | +| explained_variance | -0.104 | +| learning_rate | 1e-05 | +| loss | -0.0968 | +| n_updates | 3090 | +| policy_gradient_loss | -0.0742 | +| value_loss | 0.000168 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.81e+03 | +| ep_rew_mean | 0.227 | +| time/ | | +| fps | 325 | +| iterations | 165 | +| time_elapsed | 4152 | +| total_timesteps | 1351680 | +| train/ | | +| approx_kl | 0.03576445 | +| clip_fraction | 0.348 | +| clip_range | 0.2 | +| entropy_loss | -6.23 | +| explained_variance | -0.16 | +| learning_rate | 1e-05 | +| loss | -0.106 | +| n_updates | 3100 | +| policy_gradient_loss | -0.0785 | +| value_loss | 0.000159 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.81e+03 | +| ep_rew_mean | 0.222 | +| time/ | | +| fps | 325 | +| iterations | 166 | +| time_elapsed | 4177 | +| total_timesteps | 1359872 | +| train/ | | +| approx_kl | 0.034567766 | +| clip_fraction | 0.329 | +| clip_range | 0.2 | +| entropy_loss | -6.44 | +| explained_variance | -0.0594 | +| learning_rate | 1e-05 | +| loss | -0.0926 | +| n_updates | 3110 | +| policy_gradient_loss | -0.0745 | +| value_loss | 0.00015 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.82e+03 | +| ep_rew_mean | 0.217 | +| time/ | | +| fps | 325 | +| iterations | 167 | +| time_elapsed | 4202 | +| total_timesteps | 1368064 | +| train/ | | +| approx_kl | 0.033078857 | +| clip_fraction | 0.319 | +| clip_range | 0.2 | +| entropy_loss | -6.54 | +| explained_variance | -0.0469 | +| learning_rate | 1e-05 | +| loss | -0.0907 | +| n_updates | 3120 | +| policy_gradient_loss | -0.0705 | +| value_loss | 0.00017 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.8e+03 | +| ep_rew_mean | 0.212 | +| time/ | | +| fps | 325 | +| iterations | 168 | +| time_elapsed | 4228 | +| total_timesteps | 1376256 | +| train/ | | +| approx_kl | 0.034428895 | +| clip_fraction | 0.339 | +| clip_range | 0.2 | +| entropy_loss | -6.37 | +| explained_variance | -0.0303 | +| learning_rate | 1e-05 | +| loss | -0.113 | +| n_updates | 3130 | +| policy_gradient_loss | -0.0788 | +| value_loss | 0.00015 | +----------------------------------------- +Early stopping at step 9 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.82e+03 | +| ep_rew_mean | 0.211 | +| time/ | | +| fps | 325 | +| iterations | 169 | +| time_elapsed | 4253 | +| total_timesteps | 1384448 | +| train/ | | +| approx_kl | 0.036727812 | +| clip_fraction | 0.324 | +| clip_range | 0.2 | +| entropy_loss | -6.48 | +| explained_variance | -0.0631 | +| learning_rate | 1e-05 | +| loss | -0.0953 | +| n_updates | 3140 | +| policy_gradient_loss | -0.0733 | +| value_loss | 0.000179 | +----------------------------------------- +Early stopping at step 9 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.78e+03 | +| ep_rew_mean | 0.22 | +| time/ | | +| fps | 325 | +| iterations | 170 | +| time_elapsed | 4278 | +| total_timesteps | 1392640 | +| train/ | | +| approx_kl | 0.036516808 | +| clip_fraction | 0.32 | +| clip_range | 0.2 | +| entropy_loss | -6.54 | +| explained_variance | -0.0503 | +| learning_rate | 1e-05 | +| loss | -0.0955 | +| n_updates | 3150 | +| policy_gradient_loss | -0.0755 | +| value_loss | 0.000183 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.8e+03 | +| ep_rew_mean | 0.221 | +| time/ | | +| fps | 325 | +| iterations | 171 | +| time_elapsed | 4303 | +| total_timesteps | 1400832 | +| train/ | | +| approx_kl | 0.033371743 | +| clip_fraction | 0.313 | +| clip_range | 0.2 | +| entropy_loss | -6.46 | +| explained_variance | 0.0597 | +| learning_rate | 1e-05 | +| loss | -0.106 | +| n_updates | 3160 | +| policy_gradient_loss | -0.0718 | +| value_loss | 0.000302 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.81e+03 | +| ep_rew_mean | 0.231 | +| time/ | | +| fps | 325 | +| iterations | 172 | +| time_elapsed | 4328 | +| total_timesteps | 1409024 | +| train/ | | +| approx_kl | 0.0340155 | +| clip_fraction | 0.339 | +| clip_range | 0.2 | +| entropy_loss | -6.43 | +| explained_variance | -0.147 | +| learning_rate | 1e-05 | +| loss | -0.114 | +| n_updates | 3170 | +| policy_gradient_loss | -0.0782 | +| value_loss | 0.000185 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.8e+03 | +| ep_rew_mean | 0.227 | +| time/ | | +| fps | 325 | +| iterations | 173 | +| time_elapsed | 4355 | +| total_timesteps | 1417216 | +| train/ | | +| approx_kl | 0.035656422 | +| clip_fraction | 0.342 | +| clip_range | 0.2 | +| entropy_loss | -6.39 | +| explained_variance | -0.119 | +| learning_rate | 1e-05 | +| loss | -0.1 | +| n_updates | 3180 | +| policy_gradient_loss | -0.0786 | +| value_loss | 0.000162 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.222 | +| time/ | | +| fps | 325 | +| iterations | 174 | +| time_elapsed | 4380 | +| total_timesteps | 1425408 | +| train/ | | +| approx_kl | 0.035448257 | +| clip_fraction | 0.328 | +| clip_range | 0.2 | +| entropy_loss | -6.33 | +| explained_variance | -0.0836 | +| learning_rate | 1e-05 | +| loss | -0.115 | +| n_updates | 3190 | +| policy_gradient_loss | -0.073 | +| value_loss | 0.000198 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.221 | +| time/ | | +| fps | 325 | +| iterations | 175 | +| time_elapsed | 4405 | +| total_timesteps | 1433600 | +| train/ | | +| approx_kl | 0.032862417 | +| clip_fraction | 0.312 | +| clip_range | 0.2 | +| entropy_loss | -6.37 | +| explained_variance | -0.0403 | +| learning_rate | 1e-05 | +| loss | -0.104 | +| n_updates | 3200 | +| policy_gradient_loss | -0.0749 | +| value_loss | 0.000193 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.231 | +| time/ | | +| fps | 325 | +| iterations | 176 | +| time_elapsed | 4431 | +| total_timesteps | 1441792 | +| train/ | | +| approx_kl | 0.036565352 | +| clip_fraction | 0.348 | +| clip_range | 0.2 | +| entropy_loss | -6.4 | +| explained_variance | -0.0264 | +| learning_rate | 1e-05 | +| loss | -0.109 | +| n_updates | 3210 | +| policy_gradient_loss | -0.0801 | +| value_loss | 0.000186 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.234 | +| time/ | | +| fps | 325 | +| iterations | 177 | +| time_elapsed | 4455 | +| total_timesteps | 1449984 | +| train/ | | +| approx_kl | 0.03555518 | +| clip_fraction | 0.337 | +| clip_range | 0.2 | +| entropy_loss | -6.52 | +| explained_variance | -0.0837 | +| learning_rate | 1e-05 | +| loss | -0.0996 | +| n_updates | 3220 | +| policy_gradient_loss | -0.076 | +| value_loss | 0.000173 | +---------------------------------------- +Early stopping at step 9 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.227 | +| time/ | | +| fps | 325 | +| iterations | 178 | +| time_elapsed | 4482 | +| total_timesteps | 1458176 | +| train/ | | +| approx_kl | 0.037863918 | +| clip_fraction | 0.337 | +| clip_range | 0.2 | +| entropy_loss | -6.26 | +| explained_variance | -0.197 | +| learning_rate | 1e-05 | +| loss | -0.0997 | +| n_updates | 3230 | +| policy_gradient_loss | -0.0801 | +| value_loss | 0.000132 | +----------------------------------------- +Early stopping at step 9 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.226 | +| time/ | | +| fps | 325 | +| iterations | 179 | +| time_elapsed | 4505 | +| total_timesteps | 1466368 | +| train/ | | +| approx_kl | 0.037821755 | +| clip_fraction | 0.318 | +| clip_range | 0.2 | +| entropy_loss | -6.52 | +| explained_variance | -0.0688 | +| learning_rate | 1e-05 | +| loss | -0.0892 | +| n_updates | 3240 | +| policy_gradient_loss | -0.0698 | +| value_loss | 0.00019 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.81e+03 | +| ep_rew_mean | 0.226 | +| time/ | | +| fps | 325 | +| iterations | 180 | +| time_elapsed | 4531 | +| total_timesteps | 1474560 | +| train/ | | +| approx_kl | 0.034453236 | +| clip_fraction | 0.327 | +| clip_range | 0.2 | +| entropy_loss | -6.45 | +| explained_variance | -0.125 | +| learning_rate | 1e-05 | +| loss | -0.0978 | +| n_updates | 3250 | +| policy_gradient_loss | -0.0771 | +| value_loss | 0.000177 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.216 | +| time/ | | +| fps | 325 | +| iterations | 181 | +| time_elapsed | 4557 | +| total_timesteps | 1482752 | +| train/ | | +| approx_kl | 0.03391707 | +| clip_fraction | 0.329 | +| clip_range | 0.2 | +| entropy_loss | -6.32 | +| explained_variance | -0.00846 | +| learning_rate | 1e-05 | +| loss | -0.101 | +| n_updates | 3260 | +| policy_gradient_loss | -0.0725 | +| value_loss | 0.000158 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.8e+03 | +| ep_rew_mean | 0.211 | +| time/ | | +| fps | 325 | +| iterations | 182 | +| time_elapsed | 4582 | +| total_timesteps | 1490944 | +| train/ | | +| approx_kl | 0.03418552 | +| clip_fraction | 0.34 | +| clip_range | 0.2 | +| entropy_loss | -6.26 | +| explained_variance | -0.104 | +| learning_rate | 1e-05 | +| loss | -0.118 | +| n_updates | 3270 | +| policy_gradient_loss | -0.076 | +| value_loss | 0.000204 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.222 | +| time/ | | +| fps | 325 | +| iterations | 183 | +| time_elapsed | 4609 | +| total_timesteps | 1499136 | +| train/ | | +| approx_kl | 0.03157659 | +| clip_fraction | 0.314 | +| clip_range | 0.2 | +| entropy_loss | -6.55 | +| explained_variance | -0.131 | +| learning_rate | 1e-05 | +| loss | -0.0773 | +| n_updates | 3280 | +| policy_gradient_loss | -0.0713 | +| value_loss | 0.000164 | +---------------------------------------- +Early stopping at step 8 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.214 | +| time/ | | +| fps | 325 | +| iterations | 184 | +| time_elapsed | 4632 | +| total_timesteps | 1507328 | +| train/ | | +| approx_kl | 0.032797612 | +| clip_fraction | 0.284 | +| clip_range | 0.2 | +| entropy_loss | -6.42 | +| explained_variance | -0.038 | +| learning_rate | 1e-05 | +| loss | -0.103 | +| n_updates | 3290 | +| policy_gradient_loss | -0.0685 | +| value_loss | 0.000177 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.217 | +| time/ | | +| fps | 325 | +| iterations | 185 | +| time_elapsed | 4657 | +| total_timesteps | 1515520 | +| train/ | | +| approx_kl | 0.03667748 | +| clip_fraction | 0.35 | +| clip_range | 0.2 | +| entropy_loss | -6.53 | +| explained_variance | -0.101 | +| learning_rate | 1e-05 | +| loss | -0.103 | +| n_updates | 3300 | +| policy_gradient_loss | -0.0792 | +| value_loss | 0.00015 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.225 | +| time/ | | +| fps | 325 | +| iterations | 186 | +| time_elapsed | 4681 | +| total_timesteps | 1523712 | +| train/ | | +| approx_kl | 0.037562028 | +| clip_fraction | 0.344 | +| clip_range | 0.2 | +| entropy_loss | -6.49 | +| explained_variance | -0.0654 | +| learning_rate | 1e-05 | +| loss | -0.0941 | +| n_updates | 3310 | +| policy_gradient_loss | -0.076 | +| value_loss | 0.000164 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.229 | +| time/ | | +| fps | 325 | +| iterations | 187 | +| time_elapsed | 4706 | +| total_timesteps | 1531904 | +| train/ | | +| approx_kl | 0.03479833 | +| clip_fraction | 0.337 | +| clip_range | 0.2 | +| entropy_loss | -6.39 | +| explained_variance | -0.0691 | +| learning_rate | 1e-05 | +| loss | -0.124 | +| n_updates | 3320 | +| policy_gradient_loss | -0.0736 | +| value_loss | 0.000191 | +---------------------------------------- +Early stopping at step 8 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.238 | +| time/ | | +| fps | 325 | +| iterations | 188 | +| time_elapsed | 4731 | +| total_timesteps | 1540096 | +| train/ | | +| approx_kl | 0.036690593 | +| clip_fraction | 0.308 | +| clip_range | 0.2 | +| entropy_loss | -6.4 | +| explained_variance | -0.11 | +| learning_rate | 1e-05 | +| loss | -0.12 | +| n_updates | 3330 | +| policy_gradient_loss | -0.0762 | +| value_loss | 0.000189 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.235 | +| time/ | | +| fps | 325 | +| iterations | 189 | +| time_elapsed | 4755 | +| total_timesteps | 1548288 | +| train/ | | +| approx_kl | 0.034374308 | +| clip_fraction | 0.328 | +| clip_range | 0.2 | +| entropy_loss | -6.44 | +| explained_variance | -0.0374 | +| learning_rate | 1e-05 | +| loss | -0.107 | +| n_updates | 3340 | +| policy_gradient_loss | -0.0735 | +| value_loss | 0.000151 | +----------------------------------------- +Early stopping at step 9 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.244 | +| time/ | | +| fps | 325 | +| iterations | 190 | +| time_elapsed | 4778 | +| total_timesteps | 1556480 | +| train/ | | +| approx_kl | 0.035594422 | +| clip_fraction | 0.32 | +| clip_range | 0.2 | +| entropy_loss | -6.4 | +| explained_variance | 0.00875 | +| learning_rate | 1e-05 | +| loss | -0.12 | +| n_updates | 3350 | +| policy_gradient_loss | -0.0761 | +| value_loss | 0.000163 | +----------------------------------------- +Early stopping at step 9 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.8e+03 | +| ep_rew_mean | 0.241 | +| time/ | | +| fps | 325 | +| iterations | 191 | +| time_elapsed | 4802 | +| total_timesteps | 1564672 | +| train/ | | +| approx_kl | 0.036643587 | +| clip_fraction | 0.325 | +| clip_range | 0.2 | +| entropy_loss | -6.42 | +| explained_variance | -0.0631 | +| learning_rate | 1e-05 | +| loss | -0.11 | +| n_updates | 3360 | +| policy_gradient_loss | -0.075 | +| value_loss | 0.000223 | +----------------------------------------- +Early stopping at step 9 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.82e+03 | +| ep_rew_mean | 0.231 | +| time/ | | +| fps | 325 | +| iterations | 192 | +| time_elapsed | 4827 | +| total_timesteps | 1572864 | +| train/ | | +| approx_kl | 0.03622193 | +| clip_fraction | 0.322 | +| clip_range | 0.2 | +| entropy_loss | -6.41 | +| explained_variance | -0.0608 | +| learning_rate | 1e-05 | +| loss | -0.104 | +| n_updates | 3370 | +| policy_gradient_loss | -0.0743 | +| value_loss | 0.000258 | +---------------------------------------- +Early stopping at step 9 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.235 | +| time/ | | +| fps | 325 | +| iterations | 193 | +| time_elapsed | 4853 | +| total_timesteps | 1581056 | +| train/ | | +| approx_kl | 0.03668083 | +| clip_fraction | 0.36 | +| clip_range | 0.2 | +| entropy_loss | -6.24 | +| explained_variance | -0.145 | +| learning_rate | 1e-05 | +| loss | -0.127 | +| n_updates | 3380 | +| policy_gradient_loss | -0.0824 | +| value_loss | 0.000151 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.227 | +| time/ | | +| fps | 325 | +| iterations | 194 | +| time_elapsed | 4878 | +| total_timesteps | 1589248 | +| train/ | | +| approx_kl | 0.033487737 | +| clip_fraction | 0.319 | +| clip_range | 0.2 | +| entropy_loss | -6.41 | +| explained_variance | -0.0279 | +| learning_rate | 1e-05 | +| loss | -0.123 | +| n_updates | 3390 | +| policy_gradient_loss | -0.0748 | +| value_loss | 0.000148 | +----------------------------------------- +Early stopping at step 8 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.234 | +| time/ | | +| fps | 325 | +| iterations | 195 | +| time_elapsed | 4903 | +| total_timesteps | 1597440 | +| train/ | | +| approx_kl | 0.035880595 | +| clip_fraction | 0.29 | +| clip_range | 0.2 | +| entropy_loss | -6.45 | +| explained_variance | -0.103 | +| learning_rate | 1e-05 | +| loss | -0.0957 | +| n_updates | 3400 | +| policy_gradient_loss | -0.0708 | +| value_loss | 0.000146 | +----------------------------------------- +Early stopping at step 8 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.232 | +| time/ | | +| fps | 325 | +| iterations | 196 | +| time_elapsed | 4926 | +| total_timesteps | 1605632 | +| train/ | | +| approx_kl | 0.038451854 | +| clip_fraction | 0.296 | +| clip_range | 0.2 | +| entropy_loss | -6.44 | +| explained_variance | -0.0958 | +| learning_rate | 1e-05 | +| loss | -0.109 | +| n_updates | 3410 | +| policy_gradient_loss | -0.0702 | +| value_loss | 0.000138 | +----------------------------------------- +Early stopping at step 8 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.227 | +| time/ | | +| fps | 326 | +| iterations | 197 | +| time_elapsed | 4949 | +| total_timesteps | 1613824 | +| train/ | | +| approx_kl | 0.035047356 | +| clip_fraction | 0.301 | +| clip_range | 0.2 | +| entropy_loss | -6.28 | +| explained_variance | -0.117 | +| learning_rate | 1e-05 | +| loss | -0.107 | +| n_updates | 3420 | +| policy_gradient_loss | -0.0724 | +| value_loss | 0.000137 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.227 | +| time/ | | +| fps | 326 | +| iterations | 198 | +| time_elapsed | 4975 | +| total_timesteps | 1622016 | +| train/ | | +| approx_kl | 0.03700445 | +| clip_fraction | 0.344 | +| clip_range | 0.2 | +| entropy_loss | -6.36 | +| explained_variance | -0.0643 | +| learning_rate | 1e-05 | +| loss | -0.0909 | +| n_updates | 3430 | +| policy_gradient_loss | -0.0755 | +| value_loss | 0.000138 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.227 | +| time/ | | +| fps | 326 | +| iterations | 199 | +| time_elapsed | 5000 | +| total_timesteps | 1630208 | +| train/ | | +| approx_kl | 0.03566097 | +| clip_fraction | 0.334 | +| clip_range | 0.2 | +| entropy_loss | -6.48 | +| explained_variance | -0.101 | +| learning_rate | 1e-05 | +| loss | -0.0849 | +| n_updates | 3440 | +| policy_gradient_loss | -0.0761 | +| value_loss | 0.000155 | +---------------------------------------- +Early stopping at step 8 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.223 | +| time/ | | +| fps | 326 | +| iterations | 200 | +| time_elapsed | 5022 | +| total_timesteps | 1638400 | +| train/ | | +| approx_kl | 0.03385992 | +| clip_fraction | 0.279 | +| clip_range | 0.2 | +| entropy_loss | -6.22 | +| explained_variance | -0.0746 | +| learning_rate | 1e-05 | +| loss | -0.105 | +| n_updates | 3450 | +| policy_gradient_loss | -0.0658 | +| value_loss | 0.000252 | +---------------------------------------- +Early stopping at step 9 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.226 | +| time/ | | +| fps | 326 | +| iterations | 201 | +| time_elapsed | 5046 | +| total_timesteps | 1646592 | +| train/ | | +| approx_kl | 0.04114793 | +| clip_fraction | 0.347 | +| clip_range | 0.2 | +| entropy_loss | -6.22 | +| explained_variance | -0.224 | +| learning_rate | 1e-05 | +| loss | -0.114 | +| n_updates | 3460 | +| policy_gradient_loss | -0.0819 | +| value_loss | 0.000132 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.222 | +| time/ | | +| fps | 326 | +| iterations | 202 | +| time_elapsed | 5071 | +| total_timesteps | 1654784 | +| train/ | | +| approx_kl | 0.03512036 | +| clip_fraction | 0.33 | +| clip_range | 0.2 | +| entropy_loss | -6.36 | +| explained_variance | -0.128 | +| learning_rate | 1e-05 | +| loss | -0.106 | +| n_updates | 3470 | +| policy_gradient_loss | -0.0733 | +| value_loss | 0.00014 | +---------------------------------------- +Early stopping at step 9 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.223 | +| time/ | | +| fps | 326 | +| iterations | 203 | +| time_elapsed | 5096 | +| total_timesteps | 1662976 | +| train/ | | +| approx_kl | 0.040669423 | +| clip_fraction | 0.322 | +| clip_range | 0.2 | +| entropy_loss | -6.23 | +| explained_variance | -0.125 | +| learning_rate | 1e-05 | +| loss | -0.107 | +| n_updates | 3480 | +| policy_gradient_loss | -0.073 | +| value_loss | 0.000113 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.235 | +| time/ | | +| fps | 326 | +| iterations | 204 | +| time_elapsed | 5120 | +| total_timesteps | 1671168 | +| train/ | | +| approx_kl | 0.034691453 | +| clip_fraction | 0.327 | +| clip_range | 0.2 | +| entropy_loss | -6.21 | +| explained_variance | -0.0897 | +| learning_rate | 1e-05 | +| loss | -0.0909 | +| n_updates | 3490 | +| policy_gradient_loss | -0.0694 | +| value_loss | 0.000156 | +----------------------------------------- +Early stopping at step 9 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.82e+03 | +| ep_rew_mean | 0.228 | +| time/ | | +| fps | 326 | +| iterations | 205 | +| time_elapsed | 5144 | +| total_timesteps | 1679360 | +| train/ | | +| approx_kl | 0.038953245 | +| clip_fraction | 0.311 | +| clip_range | 0.2 | +| entropy_loss | -6.2 | +| explained_variance | -0.0717 | +| learning_rate | 1e-05 | +| loss | -0.11 | +| n_updates | 3500 | +| policy_gradient_loss | -0.0727 | +| value_loss | 0.000242 | +----------------------------------------- +Early stopping at step 8 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.23 | +| time/ | | +| fps | 326 | +| iterations | 206 | +| time_elapsed | 5166 | +| total_timesteps | 1687552 | +| train/ | | +| approx_kl | 0.037756693 | +| clip_fraction | 0.311 | +| clip_range | 0.2 | +| entropy_loss | -6.34 | +| explained_variance | -0.0407 | +| learning_rate | 1e-05 | +| loss | -0.11 | +| n_updates | 3510 | +| policy_gradient_loss | -0.0747 | +| value_loss | 0.00021 | +----------------------------------------- +Early stopping at step 9 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.82e+03 | +| ep_rew_mean | 0.226 | +| time/ | | +| fps | 326 | +| iterations | 207 | +| time_elapsed | 5192 | +| total_timesteps | 1695744 | +| train/ | | +| approx_kl | 0.03777697 | +| clip_fraction | 0.31 | +| clip_range | 0.2 | +| entropy_loss | -6.31 | +| explained_variance | -0.115 | +| learning_rate | 1e-05 | +| loss | -0.121 | +| n_updates | 3520 | +| policy_gradient_loss | -0.0695 | +| value_loss | 0.00021 | +---------------------------------------- +Early stopping at step 9 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.82e+03 | +| ep_rew_mean | 0.235 | +| time/ | | +| fps | 326 | +| iterations | 208 | +| time_elapsed | 5218 | +| total_timesteps | 1703936 | +| train/ | | +| approx_kl | 0.03934103 | +| clip_fraction | 0.322 | +| clip_range | 0.2 | +| entropy_loss | -6.29 | +| explained_variance | -0.0654 | +| learning_rate | 1e-05 | +| loss | -0.104 | +| n_updates | 3530 | +| policy_gradient_loss | -0.0723 | +| value_loss | 0.000203 | +---------------------------------------- +Early stopping at step 9 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.81e+03 | +| ep_rew_mean | 0.23 | +| time/ | | +| fps | 326 | +| iterations | 209 | +| time_elapsed | 5242 | +| total_timesteps | 1712128 | +| train/ | | +| approx_kl | 0.036865685 | +| clip_fraction | 0.322 | +| clip_range | 0.2 | +| entropy_loss | -6.19 | +| explained_variance | -0.0578 | +| learning_rate | 1e-05 | +| loss | -0.118 | +| n_updates | 3540 | +| policy_gradient_loss | -0.0716 | +| value_loss | 0.000222 | +----------------------------------------- +Early stopping at step 9 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.234 | +| time/ | | +| fps | 326 | +| iterations | 210 | +| time_elapsed | 5268 | +| total_timesteps | 1720320 | +| train/ | | +| approx_kl | 0.038554084 | +| clip_fraction | 0.351 | +| clip_range | 0.2 | +| entropy_loss | -6.32 | +| explained_variance | -0.0849 | +| learning_rate | 1e-05 | +| loss | -0.111 | +| n_updates | 3550 | +| policy_gradient_loss | -0.0773 | +| value_loss | 0.000192 | +----------------------------------------- +Early stopping at step 9 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.24 | +| time/ | | +| fps | 326 | +| iterations | 211 | +| time_elapsed | 5292 | +| total_timesteps | 1728512 | +| train/ | | +| approx_kl | 0.038461953 | +| clip_fraction | 0.311 | +| clip_range | 0.2 | +| entropy_loss | -6.33 | +| explained_variance | -0.0722 | +| learning_rate | 1e-05 | +| loss | -0.102 | +| n_updates | 3560 | +| policy_gradient_loss | -0.0705 | +| value_loss | 0.000343 | +----------------------------------------- +Early stopping at step 9 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.8e+03 | +| ep_rew_mean | 0.22 | +| time/ | | +| fps | 326 | +| iterations | 212 | +| time_elapsed | 5318 | +| total_timesteps | 1736704 | +| train/ | | +| approx_kl | 0.038678665 | +| clip_fraction | 0.331 | +| clip_range | 0.2 | +| entropy_loss | -6.31 | +| explained_variance | -0.0793 | +| learning_rate | 1e-05 | +| loss | -0.113 | +| n_updates | 3570 | +| policy_gradient_loss | -0.0757 | +| value_loss | 0.000166 | +----------------------------------------- +Early stopping at step 8 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.78e+03 | +| ep_rew_mean | 0.217 | +| time/ | | +| fps | 326 | +| iterations | 213 | +| time_elapsed | 5341 | +| total_timesteps | 1744896 | +| train/ | | +| approx_kl | 0.03843149 | +| clip_fraction | 0.319 | +| clip_range | 0.2 | +| entropy_loss | -6.15 | +| explained_variance | -0.246 | +| learning_rate | 1e-05 | +| loss | -0.108 | +| n_updates | 3580 | +| policy_gradient_loss | -0.0778 | +| value_loss | 0.000116 | +---------------------------------------- +Early stopping at step 8 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.216 | +| time/ | | +| fps | 326 | +| iterations | 214 | +| time_elapsed | 5364 | +| total_timesteps | 1753088 | +| train/ | | +| approx_kl | 0.03654509 | +| clip_fraction | 0.317 | +| clip_range | 0.2 | +| entropy_loss | -6.28 | +| explained_variance | -0.082 | +| learning_rate | 1e-05 | +| loss | -0.103 | +| n_updates | 3590 | +| policy_gradient_loss | -0.0727 | +| value_loss | 0.000189 | +---------------------------------------- +Early stopping at step 8 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.206 | +| time/ | | +| fps | 326 | +| iterations | 215 | +| time_elapsed | 5387 | +| total_timesteps | 1761280 | +| train/ | | +| approx_kl | 0.03921295 | +| clip_fraction | 0.322 | +| clip_range | 0.2 | +| entropy_loss | -6.32 | +| explained_variance | -0.0968 | +| learning_rate | 1e-05 | +| loss | -0.106 | +| n_updates | 3600 | +| policy_gradient_loss | -0.076 | +| value_loss | 0.000167 | +---------------------------------------- +Early stopping at step 8 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.21 | +| time/ | | +| fps | 327 | +| iterations | 216 | +| time_elapsed | 5409 | +| total_timesteps | 1769472 | +| train/ | | +| approx_kl | 0.04364893 | +| clip_fraction | 0.308 | +| clip_range | 0.2 | +| entropy_loss | -6.21 | +| explained_variance | -0.0826 | +| learning_rate | 1e-05 | +| loss | -0.105 | +| n_updates | 3610 | +| policy_gradient_loss | -0.0704 | +| value_loss | 0.000164 | +---------------------------------------- +Early stopping at step 9 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.214 | +| time/ | | +| fps | 327 | +| iterations | 217 | +| time_elapsed | 5434 | +| total_timesteps | 1777664 | +| train/ | | +| approx_kl | 0.043177813 | +| clip_fraction | 0.312 | +| clip_range | 0.2 | +| entropy_loss | -6.37 | +| explained_variance | -0.0797 | +| learning_rate | 1e-05 | +| loss | -0.103 | +| n_updates | 3620 | +| policy_gradient_loss | -0.0706 | +| value_loss | 0.000175 | +----------------------------------------- +Early stopping at step 9 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.227 | +| time/ | | +| fps | 327 | +| iterations | 218 | +| time_elapsed | 5459 | +| total_timesteps | 1785856 | +| train/ | | +| approx_kl | 0.038538877 | +| clip_fraction | 0.337 | +| clip_range | 0.2 | +| entropy_loss | -6.21 | +| explained_variance | -0.0109 | +| learning_rate | 1e-05 | +| loss | -0.12 | +| n_updates | 3630 | +| policy_gradient_loss | -0.0764 | +| value_loss | 0.000177 | +----------------------------------------- +Early stopping at step 8 due to reaching max kl: 0.05 +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.232 | +| time/ | | +| fps | 327 | +| iterations | 219 | +| time_elapsed | 5482 | +| total_timesteps | 1794048 | +| train/ | | +| approx_kl | 0.0403127 | +| clip_fraction | 0.308 | +| clip_range | 0.2 | +| entropy_loss | -6.26 | +| explained_variance | -0.0381 | +| learning_rate | 1e-05 | +| loss | -0.107 | +| n_updates | 3640 | +| policy_gradient_loss | -0.0707 | +| value_loss | 0.000271 | +--------------------------------------- +Early stopping at step 8 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.215 | +| time/ | | +| fps | 327 | +| iterations | 220 | +| time_elapsed | 5505 | +| total_timesteps | 1802240 | +| train/ | | +| approx_kl | 0.03475095 | +| clip_fraction | 0.31 | +| clip_range | 0.2 | +| entropy_loss | -6.07 | +| explained_variance | 0.0801 | +| learning_rate | 1e-05 | +| loss | -0.106 | +| n_updates | 3650 | +| policy_gradient_loss | -0.0719 | +| value_loss | 0.000194 | +---------------------------------------- +Early stopping at step 9 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.213 | +| time/ | | +| fps | 327 | +| iterations | 221 | +| time_elapsed | 5528 | +| total_timesteps | 1810432 | +| train/ | | +| approx_kl | 0.046823706 | +| clip_fraction | 0.346 | +| clip_range | 0.2 | +| entropy_loss | -6.27 | +| explained_variance | -0.0955 | +| learning_rate | 1e-05 | +| loss | -0.123 | +| n_updates | 3660 | +| policy_gradient_loss | -0.0773 | +| value_loss | 0.000118 | +----------------------------------------- +Early stopping at step 8 due to reaching max kl: 0.06 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.216 | +| time/ | | +| fps | 327 | +| iterations | 222 | +| time_elapsed | 5552 | +| total_timesteps | 1818624 | +| train/ | | +| approx_kl | 0.041945163 | +| clip_fraction | 0.309 | +| clip_range | 0.2 | +| entropy_loss | -6.4 | +| explained_variance | -0.0827 | +| learning_rate | 1e-05 | +| loss | -0.101 | +| n_updates | 3670 | +| policy_gradient_loss | -0.0667 | +| value_loss | 0.000176 | +----------------------------------------- +Early stopping at step 8 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.208 | +| time/ | | +| fps | 327 | +| iterations | 223 | +| time_elapsed | 5577 | +| total_timesteps | 1826816 | +| train/ | | +| approx_kl | 0.04049235 | +| clip_fraction | 0.315 | +| clip_range | 0.2 | +| entropy_loss | -6.12 | +| explained_variance | -0.0966 | +| learning_rate | 1e-05 | +| loss | -0.133 | +| n_updates | 3680 | +| policy_gradient_loss | -0.0748 | +| value_loss | 0.000149 | +---------------------------------------- +Early stopping at step 9 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.209 | +| time/ | | +| fps | 327 | +| iterations | 224 | +| time_elapsed | 5601 | +| total_timesteps | 1835008 | +| train/ | | +| approx_kl | 0.04226905 | +| clip_fraction | 0.322 | +| clip_range | 0.2 | +| entropy_loss | -6.08 | +| explained_variance | -0.0853 | +| learning_rate | 1e-05 | +| loss | -0.116 | +| n_updates | 3690 | +| policy_gradient_loss | -0.0709 | +| value_loss | 0.000187 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.2 | +| time/ | | +| fps | 327 | +| iterations | 225 | +| time_elapsed | 5628 | +| total_timesteps | 1843200 | +| train/ | | +| approx_kl | 0.036874358 | +| clip_fraction | 0.344 | +| clip_range | 0.2 | +| entropy_loss | -6.28 | +| explained_variance | -0.143 | +| learning_rate | 1e-05 | +| loss | -0.107 | +| n_updates | 3700 | +| policy_gradient_loss | -0.076 | +| value_loss | 0.000179 | +----------------------------------------- +Early stopping at step 8 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.199 | +| time/ | | +| fps | 327 | +| iterations | 226 | +| time_elapsed | 5650 | +| total_timesteps | 1851392 | +| train/ | | +| approx_kl | 0.037619434 | +| clip_fraction | 0.317 | +| clip_range | 0.2 | +| entropy_loss | -6.17 | +| explained_variance | 0.0462 | +| learning_rate | 1e-05 | +| loss | -0.0771 | +| n_updates | 3710 | +| policy_gradient_loss | -0.0698 | +| value_loss | 0.00012 | +----------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.206 | +| time/ | | +| fps | 327 | +| iterations | 227 | +| time_elapsed | 5673 | +| total_timesteps | 1859584 | +| train/ | | +| approx_kl | 0.034392316 | +| clip_fraction | 0.296 | +| clip_range | 0.2 | +| entropy_loss | -6.13 | +| explained_variance | -0.123 | +| learning_rate | 1e-05 | +| loss | -0.0994 | +| n_updates | 3720 | +| policy_gradient_loss | -0.0699 | +| value_loss | 0.000182 | +----------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.201 | +| time/ | | +| fps | 327 | +| iterations | 228 | +| time_elapsed | 5696 | +| total_timesteps | 1867776 | +| train/ | | +| approx_kl | 0.049803548 | +| clip_fraction | 0.266 | +| clip_range | 0.2 | +| entropy_loss | -6.17 | +| explained_variance | -0.0422 | +| learning_rate | 1e-05 | +| loss | -0.112 | +| n_updates | 3730 | +| policy_gradient_loss | -0.067 | +| value_loss | 0.000231 | +----------------------------------------- +Early stopping at step 8 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.203 | +| time/ | | +| fps | 328 | +| iterations | 229 | +| time_elapsed | 5718 | +| total_timesteps | 1875968 | +| train/ | | +| approx_kl | 0.040501714 | +| clip_fraction | 0.293 | +| clip_range | 0.2 | +| entropy_loss | -6.15 | +| explained_variance | -0.0527 | +| learning_rate | 1e-05 | +| loss | -0.099 | +| n_updates | 3740 | +| policy_gradient_loss | -0.0688 | +| value_loss | 0.000174 | +----------------------------------------- +Early stopping at step 8 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.197 | +| time/ | | +| fps | 328 | +| iterations | 230 | +| time_elapsed | 5741 | +| total_timesteps | 1884160 | +| train/ | | +| approx_kl | 0.03705427 | +| clip_fraction | 0.304 | +| clip_range | 0.2 | +| entropy_loss | -6.28 | +| explained_variance | -0.0521 | +| learning_rate | 1e-05 | +| loss | -0.118 | +| n_updates | 3750 | +| policy_gradient_loss | -0.0706 | +| value_loss | 0.000299 | +---------------------------------------- +Early stopping at step 9 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.182 | +| time/ | | +| fps | 328 | +| iterations | 231 | +| time_elapsed | 5765 | +| total_timesteps | 1892352 | +| train/ | | +| approx_kl | 0.037775215 | +| clip_fraction | 0.345 | +| clip_range | 0.2 | +| entropy_loss | -6.06 | +| explained_variance | -0.104 | +| learning_rate | 1e-05 | +| loss | -0.11 | +| n_updates | 3760 | +| policy_gradient_loss | -0.0754 | +| value_loss | 0.000156 | +----------------------------------------- +Early stopping at step 9 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.202 | +| time/ | | +| fps | 328 | +| iterations | 232 | +| time_elapsed | 5790 | +| total_timesteps | 1900544 | +| train/ | | +| approx_kl | 0.038835492 | +| clip_fraction | 0.335 | +| clip_range | 0.2 | +| entropy_loss | -6.17 | +| explained_variance | -0.019 | +| learning_rate | 1e-05 | +| loss | -0.107 | +| n_updates | 3770 | +| policy_gradient_loss | -0.0729 | +| value_loss | 0.000181 | +----------------------------------------- +Early stopping at step 9 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.215 | +| time/ | | +| fps | 328 | +| iterations | 233 | +| time_elapsed | 5815 | +| total_timesteps | 1908736 | +| train/ | | +| approx_kl | 0.036624793 | +| clip_fraction | 0.324 | +| clip_range | 0.2 | +| entropy_loss | -5.96 | +| explained_variance | -0.0161 | +| learning_rate | 1e-05 | +| loss | -0.115 | +| n_updates | 3780 | +| policy_gradient_loss | -0.0679 | +| value_loss | 0.000384 | +----------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.219 | +| time/ | | +| fps | 328 | +| iterations | 234 | +| time_elapsed | 5836 | +| total_timesteps | 1916928 | +| train/ | | +| approx_kl | 0.036928628 | +| clip_fraction | 0.299 | +| clip_range | 0.2 | +| entropy_loss | -6.23 | +| explained_variance | -0.208 | +| learning_rate | 1e-05 | +| loss | -0.117 | +| n_updates | 3790 | +| policy_gradient_loss | -0.0737 | +| value_loss | 0.000227 | +----------------------------------------- +Early stopping at step 9 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.223 | +| time/ | | +| fps | 328 | +| iterations | 235 | +| time_elapsed | 5860 | +| total_timesteps | 1925120 | +| train/ | | +| approx_kl | 0.038759217 | +| clip_fraction | 0.357 | +| clip_range | 0.2 | +| entropy_loss | -6.3 | +| explained_variance | 0.0483 | +| learning_rate | 1e-05 | +| loss | -0.103 | +| n_updates | 3800 | +| policy_gradient_loss | -0.0789 | +| value_loss | 0.000162 | +----------------------------------------- +Early stopping at step 8 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.221 | +| time/ | | +| fps | 328 | +| iterations | 236 | +| time_elapsed | 5883 | +| total_timesteps | 1933312 | +| train/ | | +| approx_kl | 0.041059677 | +| clip_fraction | 0.312 | +| clip_range | 0.2 | +| entropy_loss | -6.06 | +| explained_variance | -0.205 | +| learning_rate | 1e-05 | +| loss | -0.111 | +| n_updates | 3810 | +| policy_gradient_loss | -0.0741 | +| value_loss | 0.000141 | +----------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.226 | +| time/ | | +| fps | 328 | +| iterations | 237 | +| time_elapsed | 5905 | +| total_timesteps | 1941504 | +| train/ | | +| approx_kl | 0.033873126 | +| clip_fraction | 0.28 | +| clip_range | 0.2 | +| entropy_loss | -6.07 | +| explained_variance | -0.139 | +| learning_rate | 1e-05 | +| loss | -0.109 | +| n_updates | 3820 | +| policy_gradient_loss | -0.0658 | +| value_loss | 0.000126 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.229 | +| time/ | | +| fps | 328 | +| iterations | 238 | +| time_elapsed | 5933 | +| total_timesteps | 1949696 | +| train/ | | +| approx_kl | 0.037151553 | +| clip_fraction | 0.34 | +| clip_range | 0.2 | +| entropy_loss | -6.01 | +| explained_variance | -0.0163 | +| learning_rate | 1e-05 | +| loss | -0.116 | +| n_updates | 3830 | +| policy_gradient_loss | -0.0732 | +| value_loss | 0.000178 | +----------------------------------------- +Early stopping at step 9 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.218 | +| time/ | | +| fps | 328 | +| iterations | 239 | +| time_elapsed | 5957 | +| total_timesteps | 1957888 | +| train/ | | +| approx_kl | 0.036308706 | +| clip_fraction | 0.354 | +| clip_range | 0.2 | +| entropy_loss | -6.15 | +| explained_variance | -0.0382 | +| learning_rate | 1e-05 | +| loss | -0.115 | +| n_updates | 3840 | +| policy_gradient_loss | -0.0778 | +| value_loss | 0.000121 | +----------------------------------------- +Early stopping at step 8 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.217 | +| time/ | | +| fps | 328 | +| iterations | 240 | +| time_elapsed | 5983 | +| total_timesteps | 1966080 | +| train/ | | +| approx_kl | 0.04451049 | +| clip_fraction | 0.328 | +| clip_range | 0.2 | +| entropy_loss | -6.11 | +| explained_variance | -0.0891 | +| learning_rate | 1e-05 | +| loss | -0.104 | +| n_updates | 3850 | +| policy_gradient_loss | -0.0705 | +| value_loss | 0.000169 | +---------------------------------------- +Early stopping at step 8 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.78e+03 | +| ep_rew_mean | 0.216 | +| time/ | | +| fps | 328 | +| iterations | 241 | +| time_elapsed | 6005 | +| total_timesteps | 1974272 | +| train/ | | +| approx_kl | 0.034856487 | +| clip_fraction | 0.307 | +| clip_range | 0.2 | +| entropy_loss | -6.15 | +| explained_variance | -0.0479 | +| learning_rate | 1e-05 | +| loss | -0.0966 | +| n_updates | 3860 | +| policy_gradient_loss | -0.0645 | +| value_loss | 0.000211 | +----------------------------------------- +Early stopping at step 8 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.222 | +| time/ | | +| fps | 328 | +| iterations | 242 | +| time_elapsed | 6029 | +| total_timesteps | 1982464 | +| train/ | | +| approx_kl | 0.038087957 | +| clip_fraction | 0.31 | +| clip_range | 0.2 | +| entropy_loss | -6.13 | +| explained_variance | -0.0868 | +| learning_rate | 1e-05 | +| loss | -0.108 | +| n_updates | 3870 | +| policy_gradient_loss | -0.072 | +| value_loss | 0.000222 | +----------------------------------------- +Early stopping at step 8 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.8e+03 | +| ep_rew_mean | 0.222 | +| time/ | | +| fps | 328 | +| iterations | 243 | +| time_elapsed | 6054 | +| total_timesteps | 1990656 | +| train/ | | +| approx_kl | 0.03718848 | +| clip_fraction | 0.357 | +| clip_range | 0.2 | +| entropy_loss | -6.15 | +| explained_variance | -0.167 | +| learning_rate | 1e-05 | +| loss | -0.116 | +| n_updates | 3880 | +| policy_gradient_loss | -0.0773 | +| value_loss | 0.000127 | +---------------------------------------- +Early stopping at step 8 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.224 | +| time/ | | +| fps | 328 | +| iterations | 244 | +| time_elapsed | 6077 | +| total_timesteps | 1998848 | +| train/ | | +| approx_kl | 0.04642535 | +| clip_fraction | 0.298 | +| clip_range | 0.2 | +| entropy_loss | -6.01 | +| explained_variance | -0.0621 | +| learning_rate | 1e-05 | +| loss | -0.104 | +| n_updates | 3890 | +| policy_gradient_loss | -0.0676 | +| value_loss | 0.000151 | +---------------------------------------- +Early stopping at step 8 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.8e+03 | +| ep_rew_mean | 0.231 | +| time/ | | +| fps | 328 | +| iterations | 245 | +| time_elapsed | 6100 | +| total_timesteps | 2007040 | +| train/ | | +| approx_kl | 0.037075393 | +| clip_fraction | 0.316 | +| clip_range | 0.2 | +| entropy_loss | -6.3 | +| explained_variance | -0.104 | +| learning_rate | 1e-05 | +| loss | -0.0951 | +| n_updates | 3900 | +| policy_gradient_loss | -0.0705 | +| value_loss | 0.000189 | +----------------------------------------- +Early stopping at step 8 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.81e+03 | +| ep_rew_mean | 0.225 | +| time/ | | +| fps | 329 | +| iterations | 246 | +| time_elapsed | 6123 | +| total_timesteps | 2015232 | +| train/ | | +| approx_kl | 0.037093796 | +| clip_fraction | 0.322 | +| clip_range | 0.2 | +| entropy_loss | -6.19 | +| explained_variance | -0.0812 | +| learning_rate | 1e-05 | +| loss | -0.0832 | +| n_updates | 3910 | +| policy_gradient_loss | -0.073 | +| value_loss | 0.000158 | +----------------------------------------- +Early stopping at step 9 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.226 | +| time/ | | +| fps | 329 | +| iterations | 247 | +| time_elapsed | 6148 | +| total_timesteps | 2023424 | +| train/ | | +| approx_kl | 0.039001867 | +| clip_fraction | 0.344 | +| clip_range | 0.2 | +| entropy_loss | -6.12 | +| explained_variance | -0.118 | +| learning_rate | 1e-05 | +| loss | -0.107 | +| n_updates | 3920 | +| policy_gradient_loss | -0.0746 | +| value_loss | 0.000114 | +----------------------------------------- +Early stopping at step 8 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.238 | +| time/ | | +| fps | 329 | +| iterations | 248 | +| time_elapsed | 6172 | +| total_timesteps | 2031616 | +| train/ | | +| approx_kl | 0.036917813 | +| clip_fraction | 0.313 | +| clip_range | 0.2 | +| entropy_loss | -6.14 | +| explained_variance | -0.0475 | +| learning_rate | 1e-05 | +| loss | -0.117 | +| n_updates | 3930 | +| policy_gradient_loss | -0.0722 | +| value_loss | 0.000214 | +----------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.223 | +| time/ | | +| fps | 329 | +| iterations | 249 | +| time_elapsed | 6194 | +| total_timesteps | 2039808 | +| train/ | | +| approx_kl | 0.03481173 | +| clip_fraction | 0.304 | +| clip_range | 0.2 | +| entropy_loss | -6.17 | +| explained_variance | -0.074 | +| learning_rate | 1e-05 | +| loss | -0.117 | +| n_updates | 3940 | +| policy_gradient_loss | -0.0709 | +| value_loss | 0.000221 | +---------------------------------------- +Early stopping at step 8 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.214 | +| time/ | | +| fps | 329 | +| iterations | 250 | +| time_elapsed | 6217 | +| total_timesteps | 2048000 | +| train/ | | +| approx_kl | 0.03601272 | +| clip_fraction | 0.321 | +| clip_range | 0.2 | +| entropy_loss | -6.21 | +| explained_variance | 0.0677 | +| learning_rate | 1e-05 | +| loss | -0.0968 | +| n_updates | 3950 | +| policy_gradient_loss | -0.071 | +| value_loss | 0.000203 | +---------------------------------------- +Early stopping at step 8 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.211 | +| time/ | | +| fps | 329 | +| iterations | 251 | +| time_elapsed | 6240 | +| total_timesteps | 2056192 | +| train/ | | +| approx_kl | 0.03730731 | +| clip_fraction | 0.313 | +| clip_range | 0.2 | +| entropy_loss | -6.09 | +| explained_variance | -0.059 | +| learning_rate | 1e-05 | +| loss | -0.105 | +| n_updates | 3960 | +| policy_gradient_loss | -0.0711 | +| value_loss | 0.000186 | +---------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.216 | +| time/ | | +| fps | 329 | +| iterations | 252 | +| time_elapsed | 6262 | +| total_timesteps | 2064384 | +| train/ | | +| approx_kl | 0.036965206 | +| clip_fraction | 0.286 | +| clip_range | 0.2 | +| entropy_loss | -6 | +| explained_variance | -0.0486 | +| learning_rate | 1e-05 | +| loss | -0.11 | +| n_updates | 3970 | +| policy_gradient_loss | -0.0642 | +| value_loss | 0.000276 | +----------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.207 | +| time/ | | +| fps | 329 | +| iterations | 253 | +| time_elapsed | 6286 | +| total_timesteps | 2072576 | +| train/ | | +| approx_kl | 0.034978997 | +| clip_fraction | 0.288 | +| clip_range | 0.2 | +| entropy_loss | -6.14 | +| explained_variance | -0.169 | +| learning_rate | 1e-05 | +| loss | -0.0967 | +| n_updates | 3980 | +| policy_gradient_loss | -0.0694 | +| value_loss | 0.000255 | +----------------------------------------- +Early stopping at step 8 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.78e+03 | +| ep_rew_mean | 0.199 | +| time/ | | +| fps | 329 | +| iterations | 254 | +| time_elapsed | 6310 | +| total_timesteps | 2080768 | +| train/ | | +| approx_kl | 0.035087377 | +| clip_fraction | 0.32 | +| clip_range | 0.2 | +| entropy_loss | -5.98 | +| explained_variance | -0.122 | +| learning_rate | 1e-05 | +| loss | -0.105 | +| n_updates | 3990 | +| policy_gradient_loss | -0.0756 | +| value_loss | 0.00012 | +----------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.82e+03 | +| ep_rew_mean | 0.194 | +| time/ | | +| fps | 329 | +| iterations | 255 | +| time_elapsed | 6334 | +| total_timesteps | 2088960 | +| train/ | | +| approx_kl | 0.03319447 | +| clip_fraction | 0.306 | +| clip_range | 0.2 | +| entropy_loss | -6 | +| explained_variance | -0.0837 | +| learning_rate | 1e-05 | +| loss | -0.097 | +| n_updates | 4000 | +| policy_gradient_loss | -0.0656 | +| value_loss | 0.000156 | +---------------------------------------- +Early stopping at step 9 due to reaching max kl: 0.05 +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.188 | +| time/ | | +| fps | 329 | +| iterations | 256 | +| time_elapsed | 6359 | +| total_timesteps | 2097152 | +| train/ | | +| approx_kl | 0.0374194 | +| clip_fraction | 0.339 | +| clip_range | 0.2 | +| entropy_loss | -6.26 | +| explained_variance | -0.0137 | +| learning_rate | 1e-05 | +| loss | -0.0989 | +| n_updates | 4010 | +| policy_gradient_loss | -0.0602 | +| value_loss | 0.000277 | +--------------------------------------- +Early stopping at step 8 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.81e+03 | +| ep_rew_mean | 0.187 | +| time/ | | +| fps | 329 | +| iterations | 257 | +| time_elapsed | 6382 | +| total_timesteps | 2105344 | +| train/ | | +| approx_kl | 0.03695973 | +| clip_fraction | 0.329 | +| clip_range | 0.2 | +| entropy_loss | -6.06 | +| explained_variance | -0.099 | +| learning_rate | 1e-05 | +| loss | -0.1 | +| n_updates | 4020 | +| policy_gradient_loss | -0.0729 | +| value_loss | 0.000147 | +---------------------------------------- +Early stopping at step 8 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.78e+03 | +| ep_rew_mean | 0.198 | +| time/ | | +| fps | 329 | +| iterations | 258 | +| time_elapsed | 6407 | +| total_timesteps | 2113536 | +| train/ | | +| approx_kl | 0.037142485 | +| clip_fraction | 0.316 | +| clip_range | 0.2 | +| entropy_loss | -6.04 | +| explained_variance | -0.0732 | +| learning_rate | 1e-05 | +| loss | -0.115 | +| n_updates | 4030 | +| policy_gradient_loss | -0.0676 | +| value_loss | 0.000228 | +----------------------------------------- +Early stopping at step 8 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.194 | +| time/ | | +| fps | 329 | +| iterations | 259 | +| time_elapsed | 6429 | +| total_timesteps | 2121728 | +| train/ | | +| approx_kl | 0.036751542 | +| clip_fraction | 0.318 | +| clip_range | 0.2 | +| entropy_loss | -6.18 | +| explained_variance | -0.066 | +| learning_rate | 1e-05 | +| loss | -0.104 | +| n_updates | 4040 | +| policy_gradient_loss | -0.0701 | +| value_loss | 0.000263 | +----------------------------------------- +Early stopping at step 9 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.191 | +| time/ | | +| fps | 330 | +| iterations | 260 | +| time_elapsed | 6453 | +| total_timesteps | 2129920 | +| train/ | | +| approx_kl | 0.039027855 | +| clip_fraction | 0.343 | +| clip_range | 0.2 | +| entropy_loss | -6.1 | +| explained_variance | 0.0129 | +| learning_rate | 1e-05 | +| loss | -0.126 | +| n_updates | 4050 | +| policy_gradient_loss | -0.0733 | +| value_loss | 0.000252 | +----------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.197 | +| time/ | | +| fps | 330 | +| iterations | 261 | +| time_elapsed | 6476 | +| total_timesteps | 2138112 | +| train/ | | +| approx_kl | 0.03629962 | +| clip_fraction | 0.317 | +| clip_range | 0.2 | +| entropy_loss | -6.17 | +| explained_variance | -0.224 | +| learning_rate | 1e-05 | +| loss | -0.119 | +| n_updates | 4060 | +| policy_gradient_loss | -0.0724 | +| value_loss | 0.000179 | +---------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.188 | +| time/ | | +| fps | 330 | +| iterations | 262 | +| time_elapsed | 6497 | +| total_timesteps | 2146304 | +| train/ | | +| approx_kl | 0.035928216 | +| clip_fraction | 0.302 | +| clip_range | 0.2 | +| entropy_loss | -6.1 | +| explained_variance | -0.125 | +| learning_rate | 1e-05 | +| loss | -0.0975 | +| n_updates | 4070 | +| policy_gradient_loss | -0.0707 | +| value_loss | 0.000144 | +----------------------------------------- +Early stopping at step 8 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.19 | +| time/ | | +| fps | 330 | +| iterations | 263 | +| time_elapsed | 6522 | +| total_timesteps | 2154496 | +| train/ | | +| approx_kl | 0.036663916 | +| clip_fraction | 0.32 | +| clip_range | 0.2 | +| entropy_loss | -6.13 | +| explained_variance | -0.104 | +| learning_rate | 1e-05 | +| loss | -0.0945 | +| n_updates | 4080 | +| policy_gradient_loss | -0.0675 | +| value_loss | 0.000137 | +----------------------------------------- +Early stopping at step 8 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.193 | +| time/ | | +| fps | 330 | +| iterations | 264 | +| time_elapsed | 6545 | +| total_timesteps | 2162688 | +| train/ | | +| approx_kl | 0.043685485 | +| clip_fraction | 0.312 | +| clip_range | 0.2 | +| entropy_loss | -6.11 | +| explained_variance | -0.0511 | +| learning_rate | 1e-05 | +| loss | -0.106 | +| n_updates | 4090 | +| policy_gradient_loss | -0.0688 | +| value_loss | 0.000205 | +----------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.195 | +| time/ | | +| fps | 330 | +| iterations | 265 | +| time_elapsed | 6567 | +| total_timesteps | 2170880 | +| train/ | | +| approx_kl | 0.03525881 | +| clip_fraction | 0.279 | +| clip_range | 0.2 | +| entropy_loss | -6.09 | +| explained_variance | -0.0483 | +| learning_rate | 1e-05 | +| loss | -0.101 | +| n_updates | 4100 | +| policy_gradient_loss | -0.0656 | +| value_loss | 0.000243 | +---------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.199 | +| time/ | | +| fps | 330 | +| iterations | 266 | +| time_elapsed | 6588 | +| total_timesteps | 2179072 | +| train/ | | +| approx_kl | 0.036899734 | +| clip_fraction | 0.291 | +| clip_range | 0.2 | +| entropy_loss | -6.16 | +| explained_variance | -0.0613 | +| learning_rate | 1e-05 | +| loss | -0.105 | +| n_updates | 4110 | +| policy_gradient_loss | -0.0655 | +| value_loss | 0.000218 | +----------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.197 | +| time/ | | +| fps | 330 | +| iterations | 267 | +| time_elapsed | 6610 | +| total_timesteps | 2187264 | +| train/ | | +| approx_kl | 0.037352633 | +| clip_fraction | 0.3 | +| clip_range | 0.2 | +| entropy_loss | -6.04 | +| explained_variance | 0.0529 | +| learning_rate | 1e-05 | +| loss | -0.11 | +| n_updates | 4120 | +| policy_gradient_loss | -0.0695 | +| value_loss | 0.000179 | +----------------------------------------- +Early stopping at step 8 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.203 | +| time/ | | +| fps | 330 | +| iterations | 268 | +| time_elapsed | 6635 | +| total_timesteps | 2195456 | +| train/ | | +| approx_kl | 0.038238283 | +| clip_fraction | 0.343 | +| clip_range | 0.2 | +| entropy_loss | -6 | +| explained_variance | -0.0228 | +| learning_rate | 1e-05 | +| loss | -0.112 | +| n_updates | 4130 | +| policy_gradient_loss | -0.0768 | +| value_loss | 0.000169 | +----------------------------------------- +Early stopping at step 8 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.2 | +| time/ | | +| fps | 330 | +| iterations | 269 | +| time_elapsed | 6660 | +| total_timesteps | 2203648 | +| train/ | | +| approx_kl | 0.04111334 | +| clip_fraction | 0.325 | +| clip_range | 0.2 | +| entropy_loss | -6.05 | +| explained_variance | 0.00963 | +| learning_rate | 1e-05 | +| loss | -0.108 | +| n_updates | 4140 | +| policy_gradient_loss | -0.0725 | +| value_loss | 0.000166 | +---------------------------------------- +Early stopping at step 8 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.209 | +| time/ | | +| fps | 330 | +| iterations | 270 | +| time_elapsed | 6684 | +| total_timesteps | 2211840 | +| train/ | | +| approx_kl | 0.037383795 | +| clip_fraction | 0.33 | +| clip_range | 0.2 | +| entropy_loss | -6.03 | +| explained_variance | -0.0112 | +| learning_rate | 1e-05 | +| loss | -0.109 | +| n_updates | 4150 | +| policy_gradient_loss | -0.0738 | +| value_loss | 0.000222 | +----------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.218 | +| time/ | | +| fps | 330 | +| iterations | 271 | +| time_elapsed | 6708 | +| total_timesteps | 2220032 | +| train/ | | +| approx_kl | 0.03879832 | +| clip_fraction | 0.28 | +| clip_range | 0.2 | +| entropy_loss | -6.18 | +| explained_variance | 0.00367 | +| learning_rate | 1e-05 | +| loss | -0.0999 | +| n_updates | 4160 | +| policy_gradient_loss | -0.0657 | +| value_loss | 0.000219 | +---------------------------------------- +Early stopping at step 8 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.218 | +| time/ | | +| fps | 331 | +| iterations | 272 | +| time_elapsed | 6730 | +| total_timesteps | 2228224 | +| train/ | | +| approx_kl | 0.044845775 | +| clip_fraction | 0.334 | +| clip_range | 0.2 | +| entropy_loss | -6.04 | +| explained_variance | -0.0679 | +| learning_rate | 1e-05 | +| loss | -0.117 | +| n_updates | 4170 | +| policy_gradient_loss | -0.0755 | +| value_loss | 0.000184 | +----------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.229 | +| time/ | | +| fps | 331 | +| iterations | 273 | +| time_elapsed | 6754 | +| total_timesteps | 2236416 | +| train/ | | +| approx_kl | 0.0339118 | +| clip_fraction | 0.293 | +| clip_range | 0.2 | +| entropy_loss | -6.21 | +| explained_variance | -0.0971 | +| learning_rate | 1e-05 | +| loss | -0.0989 | +| n_updates | 4180 | +| policy_gradient_loss | -0.0673 | +| value_loss | 0.000239 | +--------------------------------------- +Early stopping at step 8 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.219 | +| time/ | | +| fps | 331 | +| iterations | 274 | +| time_elapsed | 6778 | +| total_timesteps | 2244608 | +| train/ | | +| approx_kl | 0.03670116 | +| clip_fraction | 0.32 | +| clip_range | 0.2 | +| entropy_loss | -5.9 | +| explained_variance | -0.138 | +| learning_rate | 1e-05 | +| loss | -0.112 | +| n_updates | 4190 | +| policy_gradient_loss | -0.0674 | +| value_loss | 0.000236 | +---------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.223 | +| time/ | | +| fps | 331 | +| iterations | 275 | +| time_elapsed | 6800 | +| total_timesteps | 2252800 | +| train/ | | +| approx_kl | 0.037629664 | +| clip_fraction | 0.291 | +| clip_range | 0.2 | +| entropy_loss | -6.05 | +| explained_variance | -0.144 | +| learning_rate | 1e-05 | +| loss | -0.105 | +| n_updates | 4200 | +| policy_gradient_loss | -0.0661 | +| value_loss | 0.000195 | +----------------------------------------- +Early stopping at step 8 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.229 | +| time/ | | +| fps | 331 | +| iterations | 276 | +| time_elapsed | 6823 | +| total_timesteps | 2260992 | +| train/ | | +| approx_kl | 0.037273463 | +| clip_fraction | 0.318 | +| clip_range | 0.2 | +| entropy_loss | -6.02 | +| explained_variance | -0.0991 | +| learning_rate | 1e-05 | +| loss | -0.106 | +| n_updates | 4210 | +| policy_gradient_loss | -0.0722 | +| value_loss | 0.000132 | +----------------------------------------- +Early stopping at step 8 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.237 | +| time/ | | +| fps | 331 | +| iterations | 277 | +| time_elapsed | 6846 | +| total_timesteps | 2269184 | +| train/ | | +| approx_kl | 0.03548952 | +| clip_fraction | 0.294 | +| clip_range | 0.2 | +| entropy_loss | -6.08 | +| explained_variance | 0.00495 | +| learning_rate | 1e-05 | +| loss | -0.11 | +| n_updates | 4220 | +| policy_gradient_loss | -0.065 | +| value_loss | 0.00017 | +---------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.245 | +| time/ | | +| fps | 331 | +| iterations | 278 | +| time_elapsed | 6868 | +| total_timesteps | 2277376 | +| train/ | | +| approx_kl | 0.03499383 | +| clip_fraction | 0.287 | +| clip_range | 0.2 | +| entropy_loss | -6.13 | +| explained_variance | -0.0331 | +| learning_rate | 1e-05 | +| loss | -0.107 | +| n_updates | 4230 | +| policy_gradient_loss | -0.065 | +| value_loss | 0.000356 | +---------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.235 | +| time/ | | +| fps | 331 | +| iterations | 279 | +| time_elapsed | 6892 | +| total_timesteps | 2285568 | +| train/ | | +| approx_kl | 0.03692056 | +| clip_fraction | 0.313 | +| clip_range | 0.2 | +| entropy_loss | -6.16 | +| explained_variance | -0.115 | +| learning_rate | 1e-05 | +| loss | -0.121 | +| n_updates | 4240 | +| policy_gradient_loss | -0.0754 | +| value_loss | 0.000147 | +---------------------------------------- +Early stopping at step 9 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.244 | +| time/ | | +| fps | 331 | +| iterations | 280 | +| time_elapsed | 6915 | +| total_timesteps | 2293760 | +| train/ | | +| approx_kl | 0.041215982 | +| clip_fraction | 0.321 | +| clip_range | 0.2 | +| entropy_loss | -6.05 | +| explained_variance | -0.0565 | +| learning_rate | 1e-05 | +| loss | -0.117 | +| n_updates | 4250 | +| policy_gradient_loss | -0.0676 | +| value_loss | 0.000217 | +----------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.246 | +| time/ | | +| fps | 331 | +| iterations | 281 | +| time_elapsed | 6935 | +| total_timesteps | 2301952 | +| train/ | | +| approx_kl | 0.037398983 | +| clip_fraction | 0.265 | +| clip_range | 0.2 | +| entropy_loss | -6.04 | +| explained_variance | -0.0197 | +| learning_rate | 1e-05 | +| loss | -0.104 | +| n_updates | 4260 | +| policy_gradient_loss | -0.0618 | +| value_loss | 0.000169 | +----------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.245 | +| time/ | | +| fps | 332 | +| iterations | 282 | +| time_elapsed | 6956 | +| total_timesteps | 2310144 | +| train/ | | +| approx_kl | 0.045792483 | +| clip_fraction | 0.281 | +| clip_range | 0.2 | +| entropy_loss | -5.92 | +| explained_variance | -0.0741 | +| learning_rate | 1e-05 | +| loss | -0.102 | +| n_updates | 4270 | +| policy_gradient_loss | -0.0629 | +| value_loss | 0.000205 | +----------------------------------------- +Early stopping at step 8 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.252 | +| time/ | | +| fps | 332 | +| iterations | 283 | +| time_elapsed | 6980 | +| total_timesteps | 2318336 | +| train/ | | +| approx_kl | 0.03639487 | +| clip_fraction | 0.323 | +| clip_range | 0.2 | +| entropy_loss | -6.07 | +| explained_variance | -0.0246 | +| learning_rate | 1e-05 | +| loss | -0.109 | +| n_updates | 4280 | +| policy_gradient_loss | -0.0701 | +| value_loss | 0.000193 | +---------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.25 | +| time/ | | +| fps | 332 | +| iterations | 284 | +| time_elapsed | 7002 | +| total_timesteps | 2326528 | +| train/ | | +| approx_kl | 0.034554124 | +| clip_fraction | 0.27 | +| clip_range | 0.2 | +| entropy_loss | -6.14 | +| explained_variance | -0.0884 | +| learning_rate | 1e-05 | +| loss | -0.085 | +| n_updates | 4290 | +| policy_gradient_loss | -0.0614 | +| value_loss | 0.000233 | +----------------------------------------- +Early stopping at step 8 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.247 | +| time/ | | +| fps | 332 | +| iterations | 285 | +| time_elapsed | 7025 | +| total_timesteps | 2334720 | +| train/ | | +| approx_kl | 0.036932755 | +| clip_fraction | 0.324 | +| clip_range | 0.2 | +| entropy_loss | -6.16 | +| explained_variance | -0.0216 | +| learning_rate | 1e-05 | +| loss | -0.103 | +| n_updates | 4300 | +| policy_gradient_loss | -0.072 | +| value_loss | 0.000177 | +----------------------------------------- +Early stopping at step 8 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | 0.24 | +| time/ | | +| fps | 332 | +| iterations | 286 | +| time_elapsed | 7050 | +| total_timesteps | 2342912 | +| train/ | | +| approx_kl | 0.037813026 | +| clip_fraction | 0.308 | +| clip_range | 0.2 | +| entropy_loss | -6.1 | +| explained_variance | -0.0753 | +| learning_rate | 1e-05 | +| loss | -0.0855 | +| n_updates | 4310 | +| policy_gradient_loss | -0.0681 | +| value_loss | 0.000198 | +----------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | 0.247 | +| time/ | | +| fps | 332 | +| iterations | 287 | +| time_elapsed | 7072 | +| total_timesteps | 2351104 | +| train/ | | +| approx_kl | 0.034867156 | +| clip_fraction | 0.302 | +| clip_range | 0.2 | +| entropy_loss | -6.16 | +| explained_variance | -0.0227 | +| learning_rate | 1e-05 | +| loss | -0.109 | +| n_updates | 4320 | +| policy_gradient_loss | -0.0699 | +| value_loss | 0.000214 | +----------------------------------------- +Early stopping at step 8 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.245 | +| time/ | | +| fps | 332 | +| iterations | 288 | +| time_elapsed | 7095 | +| total_timesteps | 2359296 | +| train/ | | +| approx_kl | 0.041730203 | +| clip_fraction | 0.312 | +| clip_range | 0.2 | +| entropy_loss | -6 | +| explained_variance | -0.0867 | +| learning_rate | 1e-05 | +| loss | -0.107 | +| n_updates | 4330 | +| policy_gradient_loss | -0.0682 | +| value_loss | 0.000228 | +----------------------------------------- +Early stopping at step 8 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.65e+03 | +| ep_rew_mean | 0.233 | +| time/ | | +| fps | 332 | +| iterations | 289 | +| time_elapsed | 7119 | +| total_timesteps | 2367488 | +| train/ | | +| approx_kl | 0.03919076 | +| clip_fraction | 0.341 | +| clip_range | 0.2 | +| entropy_loss | -6 | +| explained_variance | -0.0976 | +| learning_rate | 1e-05 | +| loss | -0.116 | +| n_updates | 4340 | +| policy_gradient_loss | -0.0753 | +| value_loss | 0.000166 | +---------------------------------------- +Early stopping at step 8 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.235 | +| time/ | | +| fps | 332 | +| iterations | 290 | +| time_elapsed | 7142 | +| total_timesteps | 2375680 | +| train/ | | +| approx_kl | 0.039418772 | +| clip_fraction | 0.328 | +| clip_range | 0.2 | +| entropy_loss | -5.95 | +| explained_variance | -0.121 | +| learning_rate | 1e-05 | +| loss | -0.104 | +| n_updates | 4350 | +| policy_gradient_loss | -0.0691 | +| value_loss | 0.000198 | +----------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.229 | +| time/ | | +| fps | 332 | +| iterations | 291 | +| time_elapsed | 7163 | +| total_timesteps | 2383872 | +| train/ | | +| approx_kl | 0.034435105 | +| clip_fraction | 0.279 | +| clip_range | 0.2 | +| entropy_loss | -6.12 | +| explained_variance | -0.0746 | +| learning_rate | 1e-05 | +| loss | -0.102 | +| n_updates | 4360 | +| policy_gradient_loss | -0.0652 | +| value_loss | 0.000179 | +----------------------------------------- +Early stopping at step 5 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.226 | +| time/ | | +| fps | 333 | +| iterations | 292 | +| time_elapsed | 7183 | +| total_timesteps | 2392064 | +| train/ | | +| approx_kl | 0.034044504 | +| clip_fraction | 0.227 | +| clip_range | 0.2 | +| entropy_loss | -5.96 | +| explained_variance | -0.102 | +| learning_rate | 1e-05 | +| loss | -0.1 | +| n_updates | 4370 | +| policy_gradient_loss | -0.0544 | +| value_loss | 0.00012 | +----------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.219 | +| time/ | | +| fps | 333 | +| iterations | 293 | +| time_elapsed | 7203 | +| total_timesteps | 2400256 | +| train/ | | +| approx_kl | 0.03291393 | +| clip_fraction | 0.242 | +| clip_range | 0.2 | +| entropy_loss | -6.05 | +| explained_variance | -0.0153 | +| learning_rate | 1e-05 | +| loss | -0.0859 | +| n_updates | 4380 | +| policy_gradient_loss | -0.0557 | +| value_loss | 0.00017 | +---------------------------------------- +Early stopping at step 5 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.224 | +| time/ | | +| fps | 333 | +| iterations | 294 | +| time_elapsed | 7223 | +| total_timesteps | 2408448 | +| train/ | | +| approx_kl | 0.030309057 | +| clip_fraction | 0.214 | +| clip_range | 0.2 | +| entropy_loss | -5.81 | +| explained_variance | -0.0788 | +| learning_rate | 1e-05 | +| loss | -0.0919 | +| n_updates | 4390 | +| policy_gradient_loss | -0.0507 | +| value_loss | 0.000251 | +----------------------------------------- +Early stopping at step 9 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.228 | +| time/ | | +| fps | 333 | +| iterations | 295 | +| time_elapsed | 7248 | +| total_timesteps | 2416640 | +| train/ | | +| approx_kl | 0.038788766 | +| clip_fraction | 0.309 | +| clip_range | 0.2 | +| entropy_loss | -5.89 | +| explained_variance | -0.0573 | +| learning_rate | 1e-05 | +| loss | -0.0789 | +| n_updates | 4400 | +| policy_gradient_loss | -0.0651 | +| value_loss | 0.000235 | +----------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.223 | +| time/ | | +| fps | 333 | +| iterations | 296 | +| time_elapsed | 7270 | +| total_timesteps | 2424832 | +| train/ | | +| approx_kl | 0.038912743 | +| clip_fraction | 0.288 | +| clip_range | 0.2 | +| entropy_loss | -5.86 | +| explained_variance | -0.128 | +| learning_rate | 1e-05 | +| loss | -0.11 | +| n_updates | 4410 | +| policy_gradient_loss | -0.0678 | +| value_loss | 0.000196 | +----------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.215 | +| time/ | | +| fps | 333 | +| iterations | 297 | +| time_elapsed | 7291 | +| total_timesteps | 2433024 | +| train/ | | +| approx_kl | 0.03768293 | +| clip_fraction | 0.304 | +| clip_range | 0.2 | +| entropy_loss | -6.08 | +| explained_variance | 0.0163 | +| learning_rate | 1e-05 | +| loss | -0.0926 | +| n_updates | 4420 | +| policy_gradient_loss | -0.0676 | +| value_loss | 0.000148 | +---------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.208 | +| time/ | | +| fps | 333 | +| iterations | 298 | +| time_elapsed | 7314 | +| total_timesteps | 2441216 | +| train/ | | +| approx_kl | 0.036217682 | +| clip_fraction | 0.315 | +| clip_range | 0.2 | +| entropy_loss | -6.06 | +| explained_variance | -0.0085 | +| learning_rate | 1e-05 | +| loss | -0.0907 | +| n_updates | 4430 | +| policy_gradient_loss | -0.0702 | +| value_loss | 0.000165 | +----------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.203 | +| time/ | | +| fps | 333 | +| iterations | 299 | +| time_elapsed | 7335 | +| total_timesteps | 2449408 | +| train/ | | +| approx_kl | 0.03459088 | +| clip_fraction | 0.298 | +| clip_range | 0.2 | +| entropy_loss | -5.89 | +| explained_variance | -0.151 | +| learning_rate | 1e-05 | +| loss | -0.107 | +| n_updates | 4440 | +| policy_gradient_loss | -0.0691 | +| value_loss | 0.000119 | +---------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | 0.21 | +| time/ | | +| fps | 333 | +| iterations | 300 | +| time_elapsed | 7358 | +| total_timesteps | 2457600 | +| train/ | | +| approx_kl | 0.03584879 | +| clip_fraction | 0.252 | +| clip_range | 0.2 | +| entropy_loss | -6.05 | +| explained_variance | -0.072 | +| learning_rate | 1e-05 | +| loss | -0.1 | +| n_updates | 4450 | +| policy_gradient_loss | -0.0585 | +| value_loss | 0.00019 | +---------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | 0.204 | +| time/ | | +| fps | 334 | +| iterations | 301 | +| time_elapsed | 7381 | +| total_timesteps | 2465792 | +| train/ | | +| approx_kl | 0.033569597 | +| clip_fraction | 0.287 | +| clip_range | 0.2 | +| entropy_loss | -6 | +| explained_variance | -0.0651 | +| learning_rate | 1e-05 | +| loss | -0.0932 | +| n_updates | 4460 | +| policy_gradient_loss | -0.0632 | +| value_loss | 0.000267 | +----------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.205 | +| time/ | | +| fps | 334 | +| iterations | 302 | +| time_elapsed | 7402 | +| total_timesteps | 2473984 | +| train/ | | +| approx_kl | 0.045434076 | +| clip_fraction | 0.262 | +| clip_range | 0.2 | +| entropy_loss | -6.02 | +| explained_variance | -0.0784 | +| learning_rate | 1e-05 | +| loss | -0.106 | +| n_updates | 4470 | +| policy_gradient_loss | -0.0663 | +| value_loss | 0.000137 | +----------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.208 | +| time/ | | +| fps | 334 | +| iterations | 303 | +| time_elapsed | 7426 | +| total_timesteps | 2482176 | +| train/ | | +| approx_kl | 0.03577978 | +| clip_fraction | 0.289 | +| clip_range | 0.2 | +| entropy_loss | -5.99 | +| explained_variance | -0.0431 | +| learning_rate | 1e-05 | +| loss | -0.12 | +| n_updates | 4480 | +| policy_gradient_loss | -0.0652 | +| value_loss | 0.000167 | +---------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.203 | +| time/ | | +| fps | 334 | +| iterations | 304 | +| time_elapsed | 7448 | +| total_timesteps | 2490368 | +| train/ | | +| approx_kl | 0.034813154 | +| clip_fraction | 0.295 | +| clip_range | 0.2 | +| entropy_loss | -5.97 | +| explained_variance | -0.101 | +| learning_rate | 1e-05 | +| loss | -0.105 | +| n_updates | 4490 | +| policy_gradient_loss | -0.0674 | +| value_loss | 0.000134 | +----------------------------------------- +Early stopping at step 8 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.205 | +| time/ | | +| fps | 334 | +| iterations | 305 | +| time_elapsed | 7472 | +| total_timesteps | 2498560 | +| train/ | | +| approx_kl | 0.038340963 | +| clip_fraction | 0.32 | +| clip_range | 0.2 | +| entropy_loss | -5.94 | +| explained_variance | -0.0812 | +| learning_rate | 1e-05 | +| loss | -0.101 | +| n_updates | 4500 | +| policy_gradient_loss | -0.0661 | +| value_loss | 0.000194 | +----------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.199 | +| time/ | | +| fps | 334 | +| iterations | 306 | +| time_elapsed | 7495 | +| total_timesteps | 2506752 | +| train/ | | +| approx_kl | 0.033074073 | +| clip_fraction | 0.293 | +| clip_range | 0.2 | +| entropy_loss | -6.03 | +| explained_variance | -0.0324 | +| learning_rate | 1e-05 | +| loss | -0.115 | +| n_updates | 4510 | +| policy_gradient_loss | -0.0642 | +| value_loss | 0.000164 | +----------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.196 | +| time/ | | +| fps | 334 | +| iterations | 307 | +| time_elapsed | 7516 | +| total_timesteps | 2514944 | +| train/ | | +| approx_kl | 0.0339262 | +| clip_fraction | 0.281 | +| clip_range | 0.2 | +| entropy_loss | -6.04 | +| explained_variance | -0.0233 | +| learning_rate | 1e-05 | +| loss | -0.104 | +| n_updates | 4520 | +| policy_gradient_loss | -0.0636 | +| value_loss | 0.000202 | +--------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.195 | +| time/ | | +| fps | 334 | +| iterations | 308 | +| time_elapsed | 7538 | +| total_timesteps | 2523136 | +| train/ | | +| approx_kl | 0.038311966 | +| clip_fraction | 0.3 | +| clip_range | 0.2 | +| entropy_loss | -6 | +| explained_variance | -0.113 | +| learning_rate | 1e-05 | +| loss | -0.0918 | +| n_updates | 4530 | +| policy_gradient_loss | -0.0651 | +| value_loss | 0.000188 | +----------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.179 | +| time/ | | +| fps | 334 | +| iterations | 309 | +| time_elapsed | 7559 | +| total_timesteps | 2531328 | +| train/ | | +| approx_kl | 0.03465773 | +| clip_fraction | 0.279 | +| clip_range | 0.2 | +| entropy_loss | -5.89 | +| explained_variance | -0.109 | +| learning_rate | 1e-05 | +| loss | -0.0869 | +| n_updates | 4540 | +| policy_gradient_loss | -0.0636 | +| value_loss | 0.00018 | +---------------------------------------- +Early stopping at step 9 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.185 | +| time/ | | +| fps | 334 | +| iterations | 310 | +| time_elapsed | 7583 | +| total_timesteps | 2539520 | +| train/ | | +| approx_kl | 0.03973619 | +| clip_fraction | 0.352 | +| clip_range | 0.2 | +| entropy_loss | -5.97 | +| explained_variance | -0.027 | +| learning_rate | 1e-05 | +| loss | -0.084 | +| n_updates | 4550 | +| policy_gradient_loss | -0.0715 | +| value_loss | 0.000131 | +---------------------------------------- +Early stopping at step 8 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.189 | +| time/ | | +| fps | 334 | +| iterations | 311 | +| time_elapsed | 7608 | +| total_timesteps | 2547712 | +| train/ | | +| approx_kl | 0.037793778 | +| clip_fraction | 0.327 | +| clip_range | 0.2 | +| entropy_loss | -5.88 | +| explained_variance | -0.149 | +| learning_rate | 1e-05 | +| loss | -0.117 | +| n_updates | 4560 | +| policy_gradient_loss | -0.0713 | +| value_loss | 0.000217 | +----------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.189 | +| time/ | | +| fps | 334 | +| iterations | 312 | +| time_elapsed | 7630 | +| total_timesteps | 2555904 | +| train/ | | +| approx_kl | 0.0366598 | +| clip_fraction | 0.32 | +| clip_range | 0.2 | +| entropy_loss | -5.62 | +| explained_variance | 0.0976 | +| learning_rate | 1e-05 | +| loss | -0.0952 | +| n_updates | 4570 | +| policy_gradient_loss | -0.0599 | +| value_loss | 0.000224 | +--------------------------------------- +Early stopping at step 8 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.185 | +| time/ | | +| fps | 335 | +| iterations | 313 | +| time_elapsed | 7652 | +| total_timesteps | 2564096 | +| train/ | | +| approx_kl | 0.04291981 | +| clip_fraction | 0.32 | +| clip_range | 0.2 | +| entropy_loss | -6.11 | +| explained_variance | -0.113 | +| learning_rate | 1e-05 | +| loss | -0.107 | +| n_updates | 4580 | +| policy_gradient_loss | -0.0729 | +| value_loss | 0.00017 | +---------------------------------------- +Early stopping at step 8 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.183 | +| time/ | | +| fps | 335 | +| iterations | 314 | +| time_elapsed | 7675 | +| total_timesteps | 2572288 | +| train/ | | +| approx_kl | 0.038217865 | +| clip_fraction | 0.321 | +| clip_range | 0.2 | +| entropy_loss | -6 | +| explained_variance | -0.166 | +| learning_rate | 1e-05 | +| loss | -0.115 | +| n_updates | 4590 | +| policy_gradient_loss | -0.066 | +| value_loss | 0.000162 | +----------------------------------------- +Early stopping at step 8 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.179 | +| time/ | | +| fps | 335 | +| iterations | 315 | +| time_elapsed | 7697 | +| total_timesteps | 2580480 | +| train/ | | +| approx_kl | 0.041331332 | +| clip_fraction | 0.326 | +| clip_range | 0.2 | +| entropy_loss | -5.73 | +| explained_variance | -0.0382 | +| learning_rate | 1e-05 | +| loss | -0.112 | +| n_updates | 4600 | +| policy_gradient_loss | -0.0703 | +| value_loss | 0.000146 | +----------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.8e+03 | +| ep_rew_mean | 0.181 | +| time/ | | +| fps | 335 | +| iterations | 316 | +| time_elapsed | 7721 | +| total_timesteps | 2588672 | +| train/ | | +| approx_kl | 0.037958853 | +| clip_fraction | 0.311 | +| clip_range | 0.2 | +| entropy_loss | -5.88 | +| explained_variance | -0.0706 | +| learning_rate | 1e-05 | +| loss | -0.0998 | +| n_updates | 4610 | +| policy_gradient_loss | -0.0669 | +| value_loss | 0.000157 | +----------------------------------------- +Early stopping at step 8 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.81e+03 | +| ep_rew_mean | 0.185 | +| time/ | | +| fps | 335 | +| iterations | 317 | +| time_elapsed | 7744 | +| total_timesteps | 2596864 | +| train/ | | +| approx_kl | 0.037441455 | +| clip_fraction | 0.324 | +| clip_range | 0.2 | +| entropy_loss | -5.98 | +| explained_variance | -0.0483 | +| learning_rate | 1e-05 | +| loss | -0.117 | +| n_updates | 4620 | +| policy_gradient_loss | -0.0704 | +| value_loss | 0.000136 | +----------------------------------------- +Early stopping at step 8 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.187 | +| time/ | | +| fps | 335 | +| iterations | 318 | +| time_elapsed | 7768 | +| total_timesteps | 2605056 | +| train/ | | +| approx_kl | 0.036432464 | +| clip_fraction | 0.297 | +| clip_range | 0.2 | +| entropy_loss | -6.04 | +| explained_variance | -0.112 | +| learning_rate | 1e-05 | +| loss | -0.103 | +| n_updates | 4630 | +| policy_gradient_loss | -0.0656 | +| value_loss | 0.000153 | +----------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.8e+03 | +| ep_rew_mean | 0.192 | +| time/ | | +| fps | 335 | +| iterations | 319 | +| time_elapsed | 7793 | +| total_timesteps | 2613248 | +| train/ | | +| approx_kl | 0.034574565 | +| clip_fraction | 0.303 | +| clip_range | 0.2 | +| entropy_loss | -5.86 | +| explained_variance | -0.127 | +| learning_rate | 1e-05 | +| loss | -0.116 | +| n_updates | 4640 | +| policy_gradient_loss | -0.0686 | +| value_loss | 0.000189 | +----------------------------------------- +Early stopping at step 9 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.191 | +| time/ | | +| fps | 335 | +| iterations | 320 | +| time_elapsed | 7816 | +| total_timesteps | 2621440 | +| train/ | | +| approx_kl | 0.041225363 | +| clip_fraction | 0.355 | +| clip_range | 0.2 | +| entropy_loss | -5.97 | +| explained_variance | 0.00217 | +| learning_rate | 1e-05 | +| loss | -0.117 | +| n_updates | 4650 | +| policy_gradient_loss | -0.0723 | +| value_loss | 0.000176 | +----------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.8e+03 | +| ep_rew_mean | 0.195 | +| time/ | | +| fps | 335 | +| iterations | 321 | +| time_elapsed | 7839 | +| total_timesteps | 2629632 | +| train/ | | +| approx_kl | 0.035862014 | +| clip_fraction | 0.261 | +| clip_range | 0.2 | +| entropy_loss | -6.04 | +| explained_variance | -0.0422 | +| learning_rate | 1e-05 | +| loss | -0.097 | +| n_updates | 4660 | +| policy_gradient_loss | -0.0604 | +| value_loss | 0.000254 | +----------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.195 | +| time/ | | +| fps | 335 | +| iterations | 322 | +| time_elapsed | 7861 | +| total_timesteps | 2637824 | +| train/ | | +| approx_kl | 0.035096735 | +| clip_fraction | 0.31 | +| clip_range | 0.2 | +| entropy_loss | -5.93 | +| explained_variance | -0.194 | +| learning_rate | 1e-05 | +| loss | -0.104 | +| n_updates | 4670 | +| policy_gradient_loss | -0.0723 | +| value_loss | 0.000134 | +----------------------------------------- +Early stopping at step 8 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.188 | +| time/ | | +| fps | 335 | +| iterations | 323 | +| time_elapsed | 7884 | +| total_timesteps | 2646016 | +| train/ | | +| approx_kl | 0.036083627 | +| clip_fraction | 0.344 | +| clip_range | 0.2 | +| entropy_loss | -5.63 | +| explained_variance | -0.0367 | +| learning_rate | 1e-05 | +| loss | -0.095 | +| n_updates | 4680 | +| policy_gradient_loss | -0.0602 | +| value_loss | 0.000208 | +----------------------------------------- +Early stopping at step 8 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.198 | +| time/ | | +| fps | 335 | +| iterations | 324 | +| time_elapsed | 7908 | +| total_timesteps | 2654208 | +| train/ | | +| approx_kl | 0.041364178 | +| clip_fraction | 0.311 | +| clip_range | 0.2 | +| entropy_loss | -5.99 | +| explained_variance | -0.0987 | +| learning_rate | 1e-05 | +| loss | -0.101 | +| n_updates | 4690 | +| policy_gradient_loss | -0.0702 | +| value_loss | 0.000162 | +----------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.198 | +| time/ | | +| fps | 335 | +| iterations | 325 | +| time_elapsed | 7930 | +| total_timesteps | 2662400 | +| train/ | | +| approx_kl | 0.04628277 | +| clip_fraction | 0.292 | +| clip_range | 0.2 | +| entropy_loss | -5.83 | +| explained_variance | -0.0336 | +| learning_rate | 1e-05 | +| loss | -0.105 | +| n_updates | 4700 | +| policy_gradient_loss | -0.065 | +| value_loss | 0.000261 | +---------------------------------------- +Early stopping at step 8 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.206 | +| time/ | | +| fps | 335 | +| iterations | 326 | +| time_elapsed | 7954 | +| total_timesteps | 2670592 | +| train/ | | +| approx_kl | 0.03654798 | +| clip_fraction | 0.309 | +| clip_range | 0.2 | +| entropy_loss | -5.87 | +| explained_variance | -0.13 | +| learning_rate | 1e-05 | +| loss | -0.0921 | +| n_updates | 4710 | +| policy_gradient_loss | -0.0678 | +| value_loss | 0.000178 | +---------------------------------------- +Early stopping at step 5 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.82e+03 | +| ep_rew_mean | 0.215 | +| time/ | | +| fps | 335 | +| iterations | 327 | +| time_elapsed | 7976 | +| total_timesteps | 2678784 | +| train/ | | +| approx_kl | 0.030889269 | +| clip_fraction | 0.252 | +| clip_range | 0.2 | +| entropy_loss | -6.02 | +| explained_variance | 0.0384 | +| learning_rate | 1e-05 | +| loss | -0.0951 | +| n_updates | 4720 | +| policy_gradient_loss | -0.0613 | +| value_loss | 0.000259 | +----------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.211 | +| time/ | | +| fps | 335 | +| iterations | 328 | +| time_elapsed | 7997 | +| total_timesteps | 2686976 | +| train/ | | +| approx_kl | 0.036675286 | +| clip_fraction | 0.28 | +| clip_range | 0.2 | +| entropy_loss | -5.89 | +| explained_variance | -0.0639 | +| learning_rate | 1e-05 | +| loss | -0.106 | +| n_updates | 4730 | +| policy_gradient_loss | -0.0625 | +| value_loss | 0.000187 | +----------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.219 | +| time/ | | +| fps | 336 | +| iterations | 329 | +| time_elapsed | 8020 | +| total_timesteps | 2695168 | +| train/ | | +| approx_kl | 0.036311924 | +| clip_fraction | 0.303 | +| clip_range | 0.2 | +| entropy_loss | -6.01 | +| explained_variance | -0.138 | +| learning_rate | 1e-05 | +| loss | -0.109 | +| n_updates | 4740 | +| policy_gradient_loss | -0.0689 | +| value_loss | 0.000203 | +----------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.22 | +| time/ | | +| fps | 336 | +| iterations | 330 | +| time_elapsed | 8045 | +| total_timesteps | 2703360 | +| train/ | | +| approx_kl | 0.035581384 | +| clip_fraction | 0.305 | +| clip_range | 0.2 | +| entropy_loss | -6.05 | +| explained_variance | -0.108 | +| learning_rate | 1e-05 | +| loss | -0.0998 | +| n_updates | 4750 | +| policy_gradient_loss | -0.0666 | +| value_loss | 0.000183 | +----------------------------------------- +Early stopping at step 8 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.237 | +| time/ | | +| fps | 336 | +| iterations | 331 | +| time_elapsed | 8069 | +| total_timesteps | 2711552 | +| train/ | | +| approx_kl | 0.040048674 | +| clip_fraction | 0.321 | +| clip_range | 0.2 | +| entropy_loss | -5.96 | +| explained_variance | -0.162 | +| learning_rate | 1e-05 | +| loss | -0.0997 | +| n_updates | 4760 | +| policy_gradient_loss | -0.069 | +| value_loss | 0.000182 | +----------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.251 | +| time/ | | +| fps | 336 | +| iterations | 332 | +| time_elapsed | 8092 | +| total_timesteps | 2719744 | +| train/ | | +| approx_kl | 0.034863144 | +| clip_fraction | 0.254 | +| clip_range | 0.2 | +| entropy_loss | -6.12 | +| explained_variance | -0.112 | +| learning_rate | 1e-05 | +| loss | -0.103 | +| n_updates | 4770 | +| policy_gradient_loss | -0.0604 | +| value_loss | 0.000265 | +----------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.247 | +| time/ | | +| fps | 336 | +| iterations | 333 | +| time_elapsed | 8113 | +| total_timesteps | 2727936 | +| train/ | | +| approx_kl | 0.03755074 | +| clip_fraction | 0.303 | +| clip_range | 0.2 | +| entropy_loss | -5.73 | +| explained_variance | -0.0606 | +| learning_rate | 1e-05 | +| loss | -0.0988 | +| n_updates | 4780 | +| policy_gradient_loss | -0.0643 | +| value_loss | 0.000191 | +---------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.78e+03 | +| ep_rew_mean | 0.245 | +| time/ | | +| fps | 336 | +| iterations | 334 | +| time_elapsed | 8136 | +| total_timesteps | 2736128 | +| train/ | | +| approx_kl | 0.033561315 | +| clip_fraction | 0.274 | +| clip_range | 0.2 | +| entropy_loss | -6.07 | +| explained_variance | -0.0469 | +| learning_rate | 1e-05 | +| loss | -0.0965 | +| n_updates | 4790 | +| policy_gradient_loss | -0.0645 | +| value_loss | 0.000236 | +----------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.254 | +| time/ | | +| fps | 336 | +| iterations | 335 | +| time_elapsed | 8159 | +| total_timesteps | 2744320 | +| train/ | | +| approx_kl | 0.03447613 | +| clip_fraction | 0.305 | +| clip_range | 0.2 | +| entropy_loss | -6.03 | +| explained_variance | -0.0291 | +| learning_rate | 1e-05 | +| loss | -0.103 | +| n_updates | 4800 | +| policy_gradient_loss | -0.0654 | +| value_loss | 0.000175 | +---------------------------------------- +Early stopping at step 5 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.81e+03 | +| ep_rew_mean | 0.247 | +| time/ | | +| fps | 336 | +| iterations | 336 | +| time_elapsed | 8179 | +| total_timesteps | 2752512 | +| train/ | | +| approx_kl | 0.03299238 | +| clip_fraction | 0.272 | +| clip_range | 0.2 | +| entropy_loss | -5.84 | +| explained_variance | -0.0892 | +| learning_rate | 1e-05 | +| loss | -0.0863 | +| n_updates | 4810 | +| policy_gradient_loss | -0.0528 | +| value_loss | 0.000209 | +---------------------------------------- +Early stopping at step 5 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.238 | +| time/ | | +| fps | 336 | +| iterations | 337 | +| time_elapsed | 8202 | +| total_timesteps | 2760704 | +| train/ | | +| approx_kl | 0.028585656 | +| clip_fraction | 0.238 | +| clip_range | 0.2 | +| entropy_loss | -5.99 | +| explained_variance | -0.109 | +| learning_rate | 1e-05 | +| loss | -0.0946 | +| n_updates | 4820 | +| policy_gradient_loss | -0.0561 | +| value_loss | 0.000209 | +----------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.242 | +| time/ | | +| fps | 336 | +| iterations | 338 | +| time_elapsed | 8224 | +| total_timesteps | 2768896 | +| train/ | | +| approx_kl | 0.03436874 | +| clip_fraction | 0.292 | +| clip_range | 0.2 | +| entropy_loss | -5.93 | +| explained_variance | -0.0188 | +| learning_rate | 1e-05 | +| loss | -0.0901 | +| n_updates | 4830 | +| policy_gradient_loss | -0.06 | +| value_loss | 0.000218 | +---------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.243 | +| time/ | | +| fps | 336 | +| iterations | 339 | +| time_elapsed | 8247 | +| total_timesteps | 2777088 | +| train/ | | +| approx_kl | 0.036480214 | +| clip_fraction | 0.286 | +| clip_range | 0.2 | +| entropy_loss | -5.87 | +| explained_variance | -0.0522 | +| learning_rate | 1e-05 | +| loss | -0.109 | +| n_updates | 4840 | +| policy_gradient_loss | -0.0635 | +| value_loss | 0.000246 | +----------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.78e+03 | +| ep_rew_mean | 0.248 | +| time/ | | +| fps | 336 | +| iterations | 340 | +| time_elapsed | 8269 | +| total_timesteps | 2785280 | +| train/ | | +| approx_kl | 0.031197041 | +| clip_fraction | 0.274 | +| clip_range | 0.2 | +| entropy_loss | -5.9 | +| explained_variance | -0.034 | +| learning_rate | 1e-05 | +| loss | -0.101 | +| n_updates | 4850 | +| policy_gradient_loss | -0.0619 | +| value_loss | 0.00016 | +----------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.82e+03 | +| ep_rew_mean | 0.238 | +| time/ | | +| fps | 336 | +| iterations | 341 | +| time_elapsed | 8290 | +| total_timesteps | 2793472 | +| train/ | | +| approx_kl | 0.036701106 | +| clip_fraction | 0.318 | +| clip_range | 0.2 | +| entropy_loss | -5.86 | +| explained_variance | -0.11 | +| learning_rate | 1e-05 | +| loss | -0.0981 | +| n_updates | 4860 | +| policy_gradient_loss | -0.0678 | +| value_loss | 0.000117 | +----------------------------------------- +Early stopping at step 8 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.243 | +| time/ | | +| fps | 336 | +| iterations | 342 | +| time_elapsed | 8314 | +| total_timesteps | 2801664 | +| train/ | | +| approx_kl | 0.03880985 | +| clip_fraction | 0.315 | +| clip_range | 0.2 | +| entropy_loss | -5.95 | +| explained_variance | 0.181 | +| learning_rate | 1e-05 | +| loss | -0.101 | +| n_updates | 4870 | +| policy_gradient_loss | -0.0636 | +| value_loss | 0.000194 | +---------------------------------------- +Early stopping at step 8 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.239 | +| time/ | | +| fps | 336 | +| iterations | 343 | +| time_elapsed | 8338 | +| total_timesteps | 2809856 | +| train/ | | +| approx_kl | 0.039101165 | +| clip_fraction | 0.321 | +| clip_range | 0.2 | +| entropy_loss | -6.1 | +| explained_variance | -0.169 | +| learning_rate | 1e-05 | +| loss | -0.113 | +| n_updates | 4880 | +| policy_gradient_loss | -0.0689 | +| value_loss | 0.000157 | +----------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.227 | +| time/ | | +| fps | 337 | +| iterations | 344 | +| time_elapsed | 8359 | +| total_timesteps | 2818048 | +| train/ | | +| approx_kl | 0.034949034 | +| clip_fraction | 0.31 | +| clip_range | 0.2 | +| entropy_loss | -5.86 | +| explained_variance | -0.0539 | +| learning_rate | 1e-05 | +| loss | -0.12 | +| n_updates | 4890 | +| policy_gradient_loss | -0.0687 | +| value_loss | 0.000104 | +----------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.222 | +| time/ | | +| fps | 337 | +| iterations | 345 | +| time_elapsed | 8380 | +| total_timesteps | 2826240 | +| train/ | | +| approx_kl | 0.035765387 | +| clip_fraction | 0.28 | +| clip_range | 0.2 | +| entropy_loss | -5.88 | +| explained_variance | -0.0328 | +| learning_rate | 1e-05 | +| loss | -0.0861 | +| n_updates | 4900 | +| policy_gradient_loss | -0.0579 | +| value_loss | 0.00014 | +----------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.78e+03 | +| ep_rew_mean | 0.213 | +| time/ | | +| fps | 337 | +| iterations | 346 | +| time_elapsed | 8403 | +| total_timesteps | 2834432 | +| train/ | | +| approx_kl | 0.03517039 | +| clip_fraction | 0.297 | +| clip_range | 0.2 | +| entropy_loss | -5.81 | +| explained_variance | -0.0641 | +| learning_rate | 1e-05 | +| loss | -0.1 | +| n_updates | 4910 | +| policy_gradient_loss | -0.0659 | +| value_loss | 0.00019 | +---------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.78e+03 | +| ep_rew_mean | 0.208 | +| time/ | | +| fps | 337 | +| iterations | 347 | +| time_elapsed | 8425 | +| total_timesteps | 2842624 | +| train/ | | +| approx_kl | 0.03348704 | +| clip_fraction | 0.289 | +| clip_range | 0.2 | +| entropy_loss | -5.96 | +| explained_variance | -0.1 | +| learning_rate | 1e-05 | +| loss | -0.107 | +| n_updates | 4920 | +| policy_gradient_loss | -0.0655 | +| value_loss | 0.000176 | +---------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.213 | +| time/ | | +| fps | 337 | +| iterations | 348 | +| time_elapsed | 8450 | +| total_timesteps | 2850816 | +| train/ | | +| approx_kl | 0.038939476 | +| clip_fraction | 0.31 | +| clip_range | 0.2 | +| entropy_loss | -5.99 | +| explained_variance | -0.113 | +| learning_rate | 1e-05 | +| loss | -0.101 | +| n_updates | 4930 | +| policy_gradient_loss | -0.0673 | +| value_loss | 0.000146 | +----------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.78e+03 | +| ep_rew_mean | 0.218 | +| time/ | | +| fps | 337 | +| iterations | 349 | +| time_elapsed | 8472 | +| total_timesteps | 2859008 | +| train/ | | +| approx_kl | 0.03530786 | +| clip_fraction | 0.291 | +| clip_range | 0.2 | +| entropy_loss | -5.92 | +| explained_variance | -0.0275 | +| learning_rate | 1e-05 | +| loss | -0.0981 | +| n_updates | 4940 | +| policy_gradient_loss | -0.0625 | +| value_loss | 0.000301 | +---------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.78e+03 | +| ep_rew_mean | 0.209 | +| time/ | | +| fps | 337 | +| iterations | 350 | +| time_elapsed | 8496 | +| total_timesteps | 2867200 | +| train/ | | +| approx_kl | 0.036767192 | +| clip_fraction | 0.304 | +| clip_range | 0.2 | +| entropy_loss | -6.01 | +| explained_variance | -0.05 | +| learning_rate | 1e-05 | +| loss | -0.106 | +| n_updates | 4950 | +| policy_gradient_loss | -0.0704 | +| value_loss | 0.000217 | +----------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.206 | +| time/ | | +| fps | 337 | +| iterations | 351 | +| time_elapsed | 8519 | +| total_timesteps | 2875392 | +| train/ | | +| approx_kl | 0.03462816 | +| clip_fraction | 0.319 | +| clip_range | 0.2 | +| entropy_loss | -6.01 | +| explained_variance | -0.0326 | +| learning_rate | 1e-05 | +| loss | -0.11 | +| n_updates | 4960 | +| policy_gradient_loss | -0.0735 | +| value_loss | 0.000133 | +---------------------------------------- +Early stopping at step 9 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.212 | +| time/ | | +| fps | 337 | +| iterations | 352 | +| time_elapsed | 8544 | +| total_timesteps | 2883584 | +| train/ | | +| approx_kl | 0.039988656 | +| clip_fraction | 0.34 | +| clip_range | 0.2 | +| entropy_loss | -5.81 | +| explained_variance | -0.0255 | +| learning_rate | 1e-05 | +| loss | -0.116 | +| n_updates | 4970 | +| policy_gradient_loss | -0.0701 | +| value_loss | 0.000147 | +----------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.8e+03 | +| ep_rew_mean | 0.208 | +| time/ | | +| fps | 337 | +| iterations | 353 | +| time_elapsed | 8568 | +| total_timesteps | 2891776 | +| train/ | | +| approx_kl | 0.034158826 | +| clip_fraction | 0.295 | +| clip_range | 0.2 | +| entropy_loss | -5.88 | +| explained_variance | -0.0365 | +| learning_rate | 1e-05 | +| loss | -0.0848 | +| n_updates | 4980 | +| policy_gradient_loss | -0.064 | +| value_loss | 0.000197 | +----------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.78e+03 | +| ep_rew_mean | 0.195 | +| time/ | | +| fps | 337 | +| iterations | 354 | +| time_elapsed | 8590 | +| total_timesteps | 2899968 | +| train/ | | +| approx_kl | 0.03758976 | +| clip_fraction | 0.303 | +| clip_range | 0.2 | +| entropy_loss | -5.82 | +| explained_variance | -0.12 | +| learning_rate | 1e-05 | +| loss | -0.1 | +| n_updates | 4990 | +| policy_gradient_loss | -0.0681 | +| value_loss | 0.000152 | +---------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.78e+03 | +| ep_rew_mean | 0.204 | +| time/ | | +| fps | 337 | +| iterations | 355 | +| time_elapsed | 8613 | +| total_timesteps | 2908160 | +| train/ | | +| approx_kl | 0.03884941 | +| clip_fraction | 0.297 | +| clip_range | 0.2 | +| entropy_loss | -5.96 | +| explained_variance | -0.0419 | +| learning_rate | 1e-05 | +| loss | -0.088 | +| n_updates | 5000 | +| policy_gradient_loss | -0.0635 | +| value_loss | 0.000193 | +---------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.196 | +| time/ | | +| fps | 337 | +| iterations | 356 | +| time_elapsed | 8635 | +| total_timesteps | 2916352 | +| train/ | | +| approx_kl | 0.035172183 | +| clip_fraction | 0.289 | +| clip_range | 0.2 | +| entropy_loss | -5.9 | +| explained_variance | -0.0893 | +| learning_rate | 1e-05 | +| loss | -0.0982 | +| n_updates | 5010 | +| policy_gradient_loss | -0.0625 | +| value_loss | 0.000271 | +----------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.204 | +| time/ | | +| fps | 337 | +| iterations | 357 | +| time_elapsed | 8657 | +| total_timesteps | 2924544 | +| train/ | | +| approx_kl | 0.03557063 | +| clip_fraction | 0.277 | +| clip_range | 0.2 | +| entropy_loss | -5.91 | +| explained_variance | -0.122 | +| learning_rate | 1e-05 | +| loss | -0.105 | +| n_updates | 5020 | +| policy_gradient_loss | -0.0611 | +| value_loss | 0.000188 | +---------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.218 | +| time/ | | +| fps | 337 | +| iterations | 358 | +| time_elapsed | 8680 | +| total_timesteps | 2932736 | +| train/ | | +| approx_kl | 0.036148123 | +| clip_fraction | 0.296 | +| clip_range | 0.2 | +| entropy_loss | -5.92 | +| explained_variance | -0.0329 | +| learning_rate | 1e-05 | +| loss | -0.109 | +| n_updates | 5030 | +| policy_gradient_loss | -0.0678 | +| value_loss | 0.000166 | +----------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.211 | +| time/ | | +| fps | 337 | +| iterations | 359 | +| time_elapsed | 8702 | +| total_timesteps | 2940928 | +| train/ | | +| approx_kl | 0.037392933 | +| clip_fraction | 0.305 | +| clip_range | 0.2 | +| entropy_loss | -6.06 | +| explained_variance | -0.0188 | +| learning_rate | 1e-05 | +| loss | -0.0779 | +| n_updates | 5040 | +| policy_gradient_loss | -0.064 | +| value_loss | 0.000198 | +----------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.21 | +| time/ | | +| fps | 338 | +| iterations | 360 | +| time_elapsed | 8723 | +| total_timesteps | 2949120 | +| train/ | | +| approx_kl | 0.034755263 | +| clip_fraction | 0.27 | +| clip_range | 0.2 | +| entropy_loss | -5.98 | +| explained_variance | -0.0832 | +| learning_rate | 1e-05 | +| loss | -0.0793 | +| n_updates | 5050 | +| policy_gradient_loss | -0.0606 | +| value_loss | 0.000218 | +----------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.203 | +| time/ | | +| fps | 338 | +| iterations | 361 | +| time_elapsed | 8746 | +| total_timesteps | 2957312 | +| train/ | | +| approx_kl | 0.037755147 | +| clip_fraction | 0.321 | +| clip_range | 0.2 | +| entropy_loss | -5.96 | +| explained_variance | -0.142 | +| learning_rate | 1e-05 | +| loss | -0.111 | +| n_updates | 5060 | +| policy_gradient_loss | -0.0717 | +| value_loss | 0.000234 | +----------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.223 | +| time/ | | +| fps | 338 | +| iterations | 362 | +| time_elapsed | 8768 | +| total_timesteps | 2965504 | +| train/ | | +| approx_kl | 0.04004607 | +| clip_fraction | 0.303 | +| clip_range | 0.2 | +| entropy_loss | -6 | +| explained_variance | -0.0599 | +| learning_rate | 1e-05 | +| loss | -0.0892 | +| n_updates | 5070 | +| policy_gradient_loss | -0.0703 | +| value_loss | 0.000189 | +---------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.222 | +| time/ | | +| fps | 338 | +| iterations | 363 | +| time_elapsed | 8790 | +| total_timesteps | 2973696 | +| train/ | | +| approx_kl | 0.03567712 | +| clip_fraction | 0.316 | +| clip_range | 0.2 | +| entropy_loss | -6.11 | +| explained_variance | -0.00498 | +| learning_rate | 1e-05 | +| loss | -0.104 | +| n_updates | 5080 | +| policy_gradient_loss | -0.0668 | +| value_loss | 0.000219 | +---------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.226 | +| time/ | | +| fps | 338 | +| iterations | 364 | +| time_elapsed | 8813 | +| total_timesteps | 2981888 | +| train/ | | +| approx_kl | 0.0368034 | +| clip_fraction | 0.283 | +| clip_range | 0.2 | +| entropy_loss | -5.98 | +| explained_variance | -0.134 | +| learning_rate | 1e-05 | +| loss | -0.101 | +| n_updates | 5090 | +| policy_gradient_loss | -0.0654 | +| value_loss | 0.000157 | +--------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.234 | +| time/ | | +| fps | 338 | +| iterations | 365 | +| time_elapsed | 8836 | +| total_timesteps | 2990080 | +| train/ | | +| approx_kl | 0.034843624 | +| clip_fraction | 0.307 | +| clip_range | 0.2 | +| entropy_loss | -5.89 | +| explained_variance | -0.0696 | +| learning_rate | 1e-05 | +| loss | -0.1 | +| n_updates | 5100 | +| policy_gradient_loss | -0.0663 | +| value_loss | 0.000177 | +----------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.232 | +| time/ | | +| fps | 338 | +| iterations | 366 | +| time_elapsed | 8860 | +| total_timesteps | 2998272 | +| train/ | | +| approx_kl | 0.0367546 | +| clip_fraction | 0.313 | +| clip_range | 0.2 | +| entropy_loss | -6.01 | +| explained_variance | -0.043 | +| learning_rate | 1e-05 | +| loss | -0.107 | +| n_updates | 5110 | +| policy_gradient_loss | -0.0676 | +| value_loss | 0.00021 | +--------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.64e+03 | +| ep_rew_mean | 0.226 | +| time/ | | +| fps | 338 | +| iterations | 367 | +| time_elapsed | 8883 | +| total_timesteps | 3006464 | +| train/ | | +| approx_kl | 0.040459823 | +| clip_fraction | 0.296 | +| clip_range | 0.2 | +| entropy_loss | -6.04 | +| explained_variance | -0.158 | +| learning_rate | 1e-05 | +| loss | -0.0859 | +| n_updates | 5120 | +| policy_gradient_loss | -0.0687 | +| value_loss | 0.000142 | +----------------------------------------- +Early stopping at step 8 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | 0.208 | +| time/ | | +| fps | 338 | +| iterations | 368 | +| time_elapsed | 8907 | +| total_timesteps | 3014656 | +| train/ | | +| approx_kl | 0.046167746 | +| clip_fraction | 0.314 | +| clip_range | 0.2 | +| entropy_loss | -5.95 | +| explained_variance | -0.118 | +| learning_rate | 1e-05 | +| loss | -0.101 | +| n_updates | 5130 | +| policy_gradient_loss | -0.0673 | +| value_loss | 0.000178 | +----------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.64e+03 | +| ep_rew_mean | 0.202 | +| time/ | | +| fps | 338 | +| iterations | 369 | +| time_elapsed | 8931 | +| total_timesteps | 3022848 | +| train/ | | +| approx_kl | 0.037372753 | +| clip_fraction | 0.299 | +| clip_range | 0.2 | +| entropy_loss | -5.89 | +| explained_variance | -0.169 | +| learning_rate | 1e-05 | +| loss | -0.109 | +| n_updates | 5140 | +| policy_gradient_loss | -0.0635 | +| value_loss | 0.000137 | +----------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.65e+03 | +| ep_rew_mean | 0.207 | +| time/ | | +| fps | 338 | +| iterations | 370 | +| time_elapsed | 8951 | +| total_timesteps | 3031040 | +| train/ | | +| approx_kl | 0.03693919 | +| clip_fraction | 0.261 | +| clip_range | 0.2 | +| entropy_loss | -5.96 | +| explained_variance | -0.0792 | +| learning_rate | 1e-05 | +| loss | -0.102 | +| n_updates | 5150 | +| policy_gradient_loss | -0.0576 | +| value_loss | 0.000171 | +---------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.64e+03 | +| ep_rew_mean | 0.211 | +| time/ | | +| fps | 338 | +| iterations | 371 | +| time_elapsed | 8973 | +| total_timesteps | 3039232 | +| train/ | | +| approx_kl | 0.03637837 | +| clip_fraction | 0.298 | +| clip_range | 0.2 | +| entropy_loss | -6.03 | +| explained_variance | -0.0349 | +| learning_rate | 1e-05 | +| loss | -0.0953 | +| n_updates | 5160 | +| policy_gradient_loss | -0.0644 | +| value_loss | 0.000164 | +---------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.65e+03 | +| ep_rew_mean | 0.209 | +| time/ | | +| fps | 338 | +| iterations | 372 | +| time_elapsed | 8995 | +| total_timesteps | 3047424 | +| train/ | | +| approx_kl | 0.040128697 | +| clip_fraction | 0.289 | +| clip_range | 0.2 | +| entropy_loss | -5.99 | +| explained_variance | -0.000378 | +| learning_rate | 1e-05 | +| loss | -0.113 | +| n_updates | 5170 | +| policy_gradient_loss | -0.0662 | +| value_loss | 0.000194 | +----------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.63e+03 | +| ep_rew_mean | 0.205 | +| time/ | | +| fps | 338 | +| iterations | 373 | +| time_elapsed | 9017 | +| total_timesteps | 3055616 | +| train/ | | +| approx_kl | 0.040461775 | +| clip_fraction | 0.293 | +| clip_range | 0.2 | +| entropy_loss | -5.92 | +| explained_variance | -0.12 | +| learning_rate | 1e-05 | +| loss | -0.111 | +| n_updates | 5180 | +| policy_gradient_loss | -0.0648 | +| value_loss | 0.00019 | +----------------------------------------- +Early stopping at step 8 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.65e+03 | +| ep_rew_mean | 0.208 | +| time/ | | +| fps | 338 | +| iterations | 374 | +| time_elapsed | 9040 | +| total_timesteps | 3063808 | +| train/ | | +| approx_kl | 0.04095398 | +| clip_fraction | 0.328 | +| clip_range | 0.2 | +| entropy_loss | -6.1 | +| explained_variance | -0.027 | +| learning_rate | 1e-05 | +| loss | -0.0986 | +| n_updates | 5190 | +| policy_gradient_loss | -0.0713 | +| value_loss | 0.000154 | +---------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | 0.211 | +| time/ | | +| fps | 338 | +| iterations | 375 | +| time_elapsed | 9062 | +| total_timesteps | 3072000 | +| train/ | | +| approx_kl | 0.035835665 | +| clip_fraction | 0.299 | +| clip_range | 0.2 | +| entropy_loss | -5.93 | +| explained_variance | -0.0476 | +| learning_rate | 1e-05 | +| loss | -0.108 | +| n_updates | 5200 | +| policy_gradient_loss | -0.0663 | +| value_loss | 0.000191 | +----------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | 0.204 | +| time/ | | +| fps | 339 | +| iterations | 376 | +| time_elapsed | 9084 | +| total_timesteps | 3080192 | +| train/ | | +| approx_kl | 0.03850752 | +| clip_fraction | 0.296 | +| clip_range | 0.2 | +| entropy_loss | -5.96 | +| explained_variance | -0.121 | +| learning_rate | 1e-05 | +| loss | -0.0887 | +| n_updates | 5210 | +| policy_gradient_loss | -0.0637 | +| value_loss | 0.000207 | +---------------------------------------- +Early stopping at step 8 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.202 | +| time/ | | +| fps | 339 | +| iterations | 377 | +| time_elapsed | 9107 | +| total_timesteps | 3088384 | +| train/ | | +| approx_kl | 0.04491949 | +| clip_fraction | 0.327 | +| clip_range | 0.2 | +| entropy_loss | -5.82 | +| explained_variance | -0.0427 | +| learning_rate | 1e-05 | +| loss | -0.107 | +| n_updates | 5220 | +| policy_gradient_loss | -0.0709 | +| value_loss | 0.000168 | +---------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.204 | +| time/ | | +| fps | 339 | +| iterations | 378 | +| time_elapsed | 9129 | +| total_timesteps | 3096576 | +| train/ | | +| approx_kl | 0.03632611 | +| clip_fraction | 0.295 | +| clip_range | 0.2 | +| entropy_loss | -6.03 | +| explained_variance | -0.0711 | +| learning_rate | 1e-05 | +| loss | -0.101 | +| n_updates | 5230 | +| policy_gradient_loss | -0.0657 | +| value_loss | 0.000216 | +---------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.195 | +| time/ | | +| fps | 339 | +| iterations | 379 | +| time_elapsed | 9153 | +| total_timesteps | 3104768 | +| train/ | | +| approx_kl | 0.04925427 | +| clip_fraction | 0.306 | +| clip_range | 0.2 | +| entropy_loss | -6.14 | +| explained_variance | -0.0925 | +| learning_rate | 1e-05 | +| loss | -0.11 | +| n_updates | 5240 | +| policy_gradient_loss | -0.07 | +| value_loss | 0.000133 | +---------------------------------------- +Early stopping at step 8 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.2 | +| time/ | | +| fps | 339 | +| iterations | 380 | +| time_elapsed | 9178 | +| total_timesteps | 3112960 | +| train/ | | +| approx_kl | 0.037450977 | +| clip_fraction | 0.329 | +| clip_range | 0.2 | +| entropy_loss | -5.99 | +| explained_variance | -0.0217 | +| learning_rate | 1e-05 | +| loss | -0.102 | +| n_updates | 5250 | +| policy_gradient_loss | -0.066 | +| value_loss | 0.000231 | +----------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.193 | +| time/ | | +| fps | 339 | +| iterations | 381 | +| time_elapsed | 9199 | +| total_timesteps | 3121152 | +| train/ | | +| approx_kl | 0.03398097 | +| clip_fraction | 0.302 | +| clip_range | 0.2 | +| entropy_loss | -5.95 | +| explained_variance | -0.114 | +| learning_rate | 1e-05 | +| loss | -0.108 | +| n_updates | 5260 | +| policy_gradient_loss | -0.067 | +| value_loss | 0.000152 | +---------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.188 | +| time/ | | +| fps | 339 | +| iterations | 382 | +| time_elapsed | 9222 | +| total_timesteps | 3129344 | +| train/ | | +| approx_kl | 0.036579203 | +| clip_fraction | 0.304 | +| clip_range | 0.2 | +| entropy_loss | -6.05 | +| explained_variance | -0.0673 | +| learning_rate | 1e-05 | +| loss | -0.111 | +| n_updates | 5270 | +| policy_gradient_loss | -0.0651 | +| value_loss | 0.000196 | +----------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.165 | +| time/ | | +| fps | 339 | +| iterations | 383 | +| time_elapsed | 9244 | +| total_timesteps | 3137536 | +| train/ | | +| approx_kl | 0.0325909 | +| clip_fraction | 0.285 | +| clip_range | 0.2 | +| entropy_loss | -6.03 | +| explained_variance | -0.0235 | +| learning_rate | 1e-05 | +| loss | -0.0866 | +| n_updates | 5280 | +| policy_gradient_loss | -0.0581 | +| value_loss | 0.000197 | +--------------------------------------- +Early stopping at step 8 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.171 | +| time/ | | +| fps | 339 | +| iterations | 384 | +| time_elapsed | 9268 | +| total_timesteps | 3145728 | +| train/ | | +| approx_kl | 0.04238839 | +| clip_fraction | 0.34 | +| clip_range | 0.2 | +| entropy_loss | -5.87 | +| explained_variance | -0.137 | +| learning_rate | 1e-05 | +| loss | -0.0925 | +| n_updates | 5290 | +| policy_gradient_loss | -0.0738 | +| value_loss | 0.000126 | +---------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.161 | +| time/ | | +| fps | 339 | +| iterations | 385 | +| time_elapsed | 9291 | +| total_timesteps | 3153920 | +| train/ | | +| approx_kl | 0.036432553 | +| clip_fraction | 0.29 | +| clip_range | 0.2 | +| entropy_loss | -5.84 | +| explained_variance | -0.0814 | +| learning_rate | 1e-05 | +| loss | -0.118 | +| n_updates | 5300 | +| policy_gradient_loss | -0.0639 | +| value_loss | 0.000204 | +----------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.167 | +| time/ | | +| fps | 339 | +| iterations | 386 | +| time_elapsed | 9313 | +| total_timesteps | 3162112 | +| train/ | | +| approx_kl | 0.035191253 | +| clip_fraction | 0.311 | +| clip_range | 0.2 | +| entropy_loss | -5.84 | +| explained_variance | -0.114 | +| learning_rate | 1e-05 | +| loss | -0.114 | +| n_updates | 5310 | +| policy_gradient_loss | -0.0653 | +| value_loss | 0.000168 | +----------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.179 | +| time/ | | +| fps | 339 | +| iterations | 387 | +| time_elapsed | 9334 | +| total_timesteps | 3170304 | +| train/ | | +| approx_kl | 0.033129558 | +| clip_fraction | 0.297 | +| clip_range | 0.2 | +| entropy_loss | -5.99 | +| explained_variance | 0.0478 | +| learning_rate | 1e-05 | +| loss | -0.105 | +| n_updates | 5320 | +| policy_gradient_loss | -0.0662 | +| value_loss | 0.000163 | +----------------------------------------- +Early stopping at step 5 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.176 | +| time/ | | +| fps | 339 | +| iterations | 388 | +| time_elapsed | 9354 | +| total_timesteps | 3178496 | +| train/ | | +| approx_kl | 0.031340968 | +| clip_fraction | 0.253 | +| clip_range | 0.2 | +| entropy_loss | -6 | +| explained_variance | -0.0507 | +| learning_rate | 1e-05 | +| loss | -0.101 | +| n_updates | 5330 | +| policy_gradient_loss | -0.0585 | +| value_loss | 0.000196 | +----------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.179 | +| time/ | | +| fps | 339 | +| iterations | 389 | +| time_elapsed | 9376 | +| total_timesteps | 3186688 | +| train/ | | +| approx_kl | 0.038332038 | +| clip_fraction | 0.299 | +| clip_range | 0.2 | +| entropy_loss | -5.98 | +| explained_variance | -0.0966 | +| learning_rate | 1e-05 | +| loss | -0.121 | +| n_updates | 5340 | +| policy_gradient_loss | -0.0653 | +| value_loss | 0.000161 | +----------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.186 | +| time/ | | +| fps | 339 | +| iterations | 390 | +| time_elapsed | 9400 | +| total_timesteps | 3194880 | +| train/ | | +| approx_kl | 0.03840238 | +| clip_fraction | 0.293 | +| clip_range | 0.2 | +| entropy_loss | -6.07 | +| explained_variance | -0.0848 | +| learning_rate | 1e-05 | +| loss | -0.0891 | +| n_updates | 5350 | +| policy_gradient_loss | -0.066 | +| value_loss | 0.000184 | +---------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.177 | +| time/ | | +| fps | 339 | +| iterations | 391 | +| time_elapsed | 9422 | +| total_timesteps | 3203072 | +| train/ | | +| approx_kl | 0.03736275 | +| clip_fraction | 0.302 | +| clip_range | 0.2 | +| entropy_loss | -5.9 | +| explained_variance | 0.00519 | +| learning_rate | 1e-05 | +| loss | -0.102 | +| n_updates | 5360 | +| policy_gradient_loss | -0.0691 | +| value_loss | 0.00016 | +---------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.171 | +| time/ | | +| fps | 340 | +| iterations | 392 | +| time_elapsed | 9443 | +| total_timesteps | 3211264 | +| train/ | | +| approx_kl | 0.035909675 | +| clip_fraction | 0.3 | +| clip_range | 0.2 | +| entropy_loss | -5.97 | +| explained_variance | -0.0272 | +| learning_rate | 1e-05 | +| loss | -0.108 | +| n_updates | 5370 | +| policy_gradient_loss | -0.0674 | +| value_loss | 0.000169 | +----------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.173 | +| time/ | | +| fps | 340 | +| iterations | 393 | +| time_elapsed | 9467 | +| total_timesteps | 3219456 | +| train/ | | +| approx_kl | 0.03636317 | +| clip_fraction | 0.323 | +| clip_range | 0.2 | +| entropy_loss | -5.92 | +| explained_variance | -0.131 | +| learning_rate | 1e-05 | +| loss | -0.101 | +| n_updates | 5380 | +| policy_gradient_loss | -0.0702 | +| value_loss | 0.000138 | +---------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.179 | +| time/ | | +| fps | 340 | +| iterations | 394 | +| time_elapsed | 9489 | +| total_timesteps | 3227648 | +| train/ | | +| approx_kl | 0.047757737 | +| clip_fraction | 0.295 | +| clip_range | 0.2 | +| entropy_loss | -5.99 | +| explained_variance | -0.0552 | +| learning_rate | 1e-05 | +| loss | -0.113 | +| n_updates | 5390 | +| policy_gradient_loss | -0.0657 | +| value_loss | 0.000152 | +----------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.183 | +| time/ | | +| fps | 340 | +| iterations | 395 | +| time_elapsed | 9512 | +| total_timesteps | 3235840 | +| train/ | | +| approx_kl | 0.04472901 | +| clip_fraction | 0.3 | +| clip_range | 0.2 | +| entropy_loss | -6.01 | +| explained_variance | -0.0195 | +| learning_rate | 1e-05 | +| loss | -0.105 | +| n_updates | 5400 | +| policy_gradient_loss | -0.0657 | +| value_loss | 0.000205 | +---------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.171 | +| time/ | | +| fps | 340 | +| iterations | 396 | +| time_elapsed | 9535 | +| total_timesteps | 3244032 | +| train/ | | +| approx_kl | 0.038061023 | +| clip_fraction | 0.31 | +| clip_range | 0.2 | +| entropy_loss | -5.73 | +| explained_variance | -0.0163 | +| learning_rate | 1e-05 | +| loss | -0.0974 | +| n_updates | 5410 | +| policy_gradient_loss | -0.0633 | +| value_loss | 0.000232 | +----------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.165 | +| time/ | | +| fps | 340 | +| iterations | 397 | +| time_elapsed | 9557 | +| total_timesteps | 3252224 | +| train/ | | +| approx_kl | 0.035273176 | +| clip_fraction | 0.293 | +| clip_range | 0.2 | +| entropy_loss | -6.1 | +| explained_variance | -0.0761 | +| learning_rate | 1e-05 | +| loss | -0.0977 | +| n_updates | 5420 | +| policy_gradient_loss | -0.0667 | +| value_loss | 0.000201 | +----------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.167 | +| time/ | | +| fps | 340 | +| iterations | 398 | +| time_elapsed | 9580 | +| total_timesteps | 3260416 | +| train/ | | +| approx_kl | 0.03651804 | +| clip_fraction | 0.306 | +| clip_range | 0.2 | +| entropy_loss | -5.88 | +| explained_variance | -0.0912 | +| learning_rate | 1e-05 | +| loss | -0.105 | +| n_updates | 5430 | +| policy_gradient_loss | -0.0686 | +| value_loss | 0.000149 | +---------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.164 | +| time/ | | +| fps | 340 | +| iterations | 399 | +| time_elapsed | 9603 | +| total_timesteps | 3268608 | +| train/ | | +| approx_kl | 0.03678411 | +| clip_fraction | 0.323 | +| clip_range | 0.2 | +| entropy_loss | -5.86 | +| explained_variance | -0.136 | +| learning_rate | 1e-05 | +| loss | -0.109 | +| n_updates | 5440 | +| policy_gradient_loss | -0.0709 | +| value_loss | 0.000123 | +---------------------------------------- +Early stopping at step 5 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.174 | +| time/ | | +| fps | 340 | +| iterations | 400 | +| time_elapsed | 9622 | +| total_timesteps | 3276800 | +| train/ | | +| approx_kl | 0.03446927 | +| clip_fraction | 0.227 | +| clip_range | 0.2 | +| entropy_loss | -5.92 | +| explained_variance | 0.00295 | +| learning_rate | 1e-05 | +| loss | -0.0966 | +| n_updates | 5450 | +| policy_gradient_loss | -0.0525 | +| value_loss | 0.00022 | +---------------------------------------- +Early stopping at step 8 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.168 | +| time/ | | +| fps | 340 | +| iterations | 401 | +| time_elapsed | 9647 | +| total_timesteps | 3284992 | +| train/ | | +| approx_kl | 0.039839994 | +| clip_fraction | 0.326 | +| clip_range | 0.2 | +| entropy_loss | -5.87 | +| explained_variance | -0.0883 | +| learning_rate | 1e-05 | +| loss | -0.0902 | +| n_updates | 5460 | +| policy_gradient_loss | -0.0674 | +| value_loss | 0.000206 | +----------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.167 | +| time/ | | +| fps | 340 | +| iterations | 402 | +| time_elapsed | 9668 | +| total_timesteps | 3293184 | +| train/ | | +| approx_kl | 0.03560899 | +| clip_fraction | 0.291 | +| clip_range | 0.2 | +| entropy_loss | -6.07 | +| explained_variance | -0.0943 | +| learning_rate | 1e-05 | +| loss | -0.0974 | +| n_updates | 5470 | +| policy_gradient_loss | -0.0642 | +| value_loss | 0.000125 | +---------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.183 | +| time/ | | +| fps | 340 | +| iterations | 403 | +| time_elapsed | 9691 | +| total_timesteps | 3301376 | +| train/ | | +| approx_kl | 0.03787953 | +| clip_fraction | 0.316 | +| clip_range | 0.2 | +| entropy_loss | -6 | +| explained_variance | -0.0936 | +| learning_rate | 1e-05 | +| loss | -0.0994 | +| n_updates | 5480 | +| policy_gradient_loss | -0.065 | +| value_loss | 0.000153 | +---------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.187 | +| time/ | | +| fps | 340 | +| iterations | 404 | +| time_elapsed | 9712 | +| total_timesteps | 3309568 | +| train/ | | +| approx_kl | 0.035315305 | +| clip_fraction | 0.279 | +| clip_range | 0.2 | +| entropy_loss | -5.86 | +| explained_variance | -0.0398 | +| learning_rate | 1e-05 | +| loss | -0.117 | +| n_updates | 5490 | +| policy_gradient_loss | -0.0635 | +| value_loss | 0.000223 | +----------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.2 | +| time/ | | +| fps | 340 | +| iterations | 405 | +| time_elapsed | 9733 | +| total_timesteps | 3317760 | +| train/ | | +| approx_kl | 0.034752112 | +| clip_fraction | 0.27 | +| clip_range | 0.2 | +| entropy_loss | -5.93 | +| explained_variance | -0.121 | +| learning_rate | 1e-05 | +| loss | -0.104 | +| n_updates | 5500 | +| policy_gradient_loss | -0.061 | +| value_loss | 0.00017 | +----------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.06 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.2 | +| time/ | | +| fps | 340 | +| iterations | 406 | +| time_elapsed | 9756 | +| total_timesteps | 3325952 | +| train/ | | +| approx_kl | 0.03246415 | +| clip_fraction | 0.273 | +| clip_range | 0.2 | +| entropy_loss | -5.88 | +| explained_variance | -0.0434 | +| learning_rate | 1e-05 | +| loss | -0.0832 | +| n_updates | 5510 | +| policy_gradient_loss | -0.0578 | +| value_loss | 0.000237 | +---------------------------------------- +Early stopping at step 8 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.78e+03 | +| ep_rew_mean | 0.193 | +| time/ | | +| fps | 340 | +| iterations | 407 | +| time_elapsed | 9779 | +| total_timesteps | 3334144 | +| train/ | | +| approx_kl | 0.037464295 | +| clip_fraction | 0.339 | +| clip_range | 0.2 | +| entropy_loss | -6.17 | +| explained_variance | 0.0381 | +| learning_rate | 1e-05 | +| loss | -0.122 | +| n_updates | 5520 | +| policy_gradient_loss | -0.0717 | +| value_loss | 0.000156 | +----------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.199 | +| time/ | | +| fps | 340 | +| iterations | 408 | +| time_elapsed | 9801 | +| total_timesteps | 3342336 | +| train/ | | +| approx_kl | 0.03641179 | +| clip_fraction | 0.298 | +| clip_range | 0.2 | +| entropy_loss | -5.83 | +| explained_variance | -0.0857 | +| learning_rate | 1e-05 | +| loss | -0.11 | +| n_updates | 5530 | +| policy_gradient_loss | -0.0632 | +| value_loss | 0.000116 | +---------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.8e+03 | +| ep_rew_mean | 0.192 | +| time/ | | +| fps | 341 | +| iterations | 409 | +| time_elapsed | 9822 | +| total_timesteps | 3350528 | +| train/ | | +| approx_kl | 0.035663974 | +| clip_fraction | 0.279 | +| clip_range | 0.2 | +| entropy_loss | -5.99 | +| explained_variance | 0.0119 | +| learning_rate | 1e-05 | +| loss | -0.0829 | +| n_updates | 5540 | +| policy_gradient_loss | -0.0585 | +| value_loss | 0.000191 | +----------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.8e+03 | +| ep_rew_mean | 0.194 | +| time/ | | +| fps | 341 | +| iterations | 410 | +| time_elapsed | 9845 | +| total_timesteps | 3358720 | +| train/ | | +| approx_kl | 0.036520142 | +| clip_fraction | 0.322 | +| clip_range | 0.2 | +| entropy_loss | -6.13 | +| explained_variance | -0.00979 | +| learning_rate | 1e-05 | +| loss | -0.0931 | +| n_updates | 5550 | +| policy_gradient_loss | -0.0631 | +| value_loss | 0.000173 | +----------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.06 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.82e+03 | +| ep_rew_mean | 0.204 | +| time/ | | +| fps | 341 | +| iterations | 411 | +| time_elapsed | 9867 | +| total_timesteps | 3366912 | +| train/ | | +| approx_kl | 0.03987334 | +| clip_fraction | 0.305 | +| clip_range | 0.2 | +| entropy_loss | -5.88 | +| explained_variance | -0.037 | +| learning_rate | 1e-05 | +| loss | -0.0964 | +| n_updates | 5560 | +| policy_gradient_loss | -0.0648 | +| value_loss | 0.000196 | +---------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.8e+03 | +| ep_rew_mean | 0.194 | +| time/ | | +| fps | 341 | +| iterations | 412 | +| time_elapsed | 9891 | +| total_timesteps | 3375104 | +| train/ | | +| approx_kl | 0.037579946 | +| clip_fraction | 0.323 | +| clip_range | 0.2 | +| entropy_loss | -5.79 | +| explained_variance | -0.0385 | +| learning_rate | 1e-05 | +| loss | -0.0922 | +| n_updates | 5570 | +| policy_gradient_loss | -0.0681 | +| value_loss | 0.000152 | +----------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.81e+03 | +| ep_rew_mean | 0.197 | +| time/ | | +| fps | 341 | +| iterations | 413 | +| time_elapsed | 9912 | +| total_timesteps | 3383296 | +| train/ | | +| approx_kl | 0.031588443 | +| clip_fraction | 0.245 | +| clip_range | 0.2 | +| entropy_loss | -6.04 | +| explained_variance | -0.0731 | +| learning_rate | 1e-05 | +| loss | -0.113 | +| n_updates | 5580 | +| policy_gradient_loss | -0.0586 | +| value_loss | 0.000185 | +----------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.81e+03 | +| ep_rew_mean | 0.201 | +| time/ | | +| fps | 341 | +| iterations | 414 | +| time_elapsed | 9934 | +| total_timesteps | 3391488 | +| train/ | | +| approx_kl | 0.04529704 | +| clip_fraction | 0.292 | +| clip_range | 0.2 | +| entropy_loss | -5.91 | +| explained_variance | -0.0955 | +| learning_rate | 1e-05 | +| loss | -0.0939 | +| n_updates | 5590 | +| policy_gradient_loss | -0.0584 | +| value_loss | 0.000201 | +---------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.189 | +| time/ | | +| fps | 341 | +| iterations | 415 | +| time_elapsed | 9956 | +| total_timesteps | 3399680 | +| train/ | | +| approx_kl | 0.03546366 | +| clip_fraction | 0.274 | +| clip_range | 0.2 | +| entropy_loss | -6.08 | +| explained_variance | -0.135 | +| learning_rate | 1e-05 | +| loss | -0.105 | +| n_updates | 5600 | +| policy_gradient_loss | -0.0632 | +| value_loss | 0.000153 | +---------------------------------------- +Early stopping at step 5 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.19 | +| time/ | | +| fps | 341 | +| iterations | 416 | +| time_elapsed | 9975 | +| total_timesteps | 3407872 | +| train/ | | +| approx_kl | 0.03069415 | +| clip_fraction | 0.232 | +| clip_range | 0.2 | +| entropy_loss | -6.05 | +| explained_variance | -0.0468 | +| learning_rate | 1e-05 | +| loss | -0.0792 | +| n_updates | 5610 | +| policy_gradient_loss | -0.0533 | +| value_loss | 0.000206 | +---------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.78e+03 | +| ep_rew_mean | 0.187 | +| time/ | | +| fps | 341 | +| iterations | 417 | +| time_elapsed | 9998 | +| total_timesteps | 3416064 | +| train/ | | +| approx_kl | 0.0410811 | +| clip_fraction | 0.318 | +| clip_range | 0.2 | +| entropy_loss | -5.73 | +| explained_variance | -0.12 | +| learning_rate | 1e-05 | +| loss | -0.0994 | +| n_updates | 5620 | +| policy_gradient_loss | -0.0656 | +| value_loss | 0.000227 | +--------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.19 | +| time/ | | +| fps | 341 | +| iterations | 418 | +| time_elapsed | 10019 | +| total_timesteps | 3424256 | +| train/ | | +| approx_kl | 0.034248322 | +| clip_fraction | 0.29 | +| clip_range | 0.2 | +| entropy_loss | -5.98 | +| explained_variance | -0.102 | +| learning_rate | 1e-05 | +| loss | -0.0971 | +| n_updates | 5630 | +| policy_gradient_loss | -0.0617 | +| value_loss | 0.000181 | +----------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.195 | +| time/ | | +| fps | 341 | +| iterations | 419 | +| time_elapsed | 10041 | +| total_timesteps | 3432448 | +| train/ | | +| approx_kl | 0.03544284 | +| clip_fraction | 0.301 | +| clip_range | 0.2 | +| entropy_loss | -6.04 | +| explained_variance | -0.0344 | +| learning_rate | 1e-05 | +| loss | -0.0933 | +| n_updates | 5640 | +| policy_gradient_loss | -0.0662 | +| value_loss | 0.000169 | +---------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.195 | +| time/ | | +| fps | 341 | +| iterations | 420 | +| time_elapsed | 10061 | +| total_timesteps | 3440640 | +| train/ | | +| approx_kl | 0.033876378 | +| clip_fraction | 0.271 | +| clip_range | 0.2 | +| entropy_loss | -6.01 | +| explained_variance | -0.0242 | +| learning_rate | 1e-05 | +| loss | -0.0899 | +| n_updates | 5650 | +| policy_gradient_loss | -0.0598 | +| value_loss | 0.000171 | +----------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.06 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.197 | +| time/ | | +| fps | 341 | +| iterations | 421 | +| time_elapsed | 10084 | +| total_timesteps | 3448832 | +| train/ | | +| approx_kl | 0.038334675 | +| clip_fraction | 0.323 | +| clip_range | 0.2 | +| entropy_loss | -5.95 | +| explained_variance | -0.0168 | +| learning_rate | 1e-05 | +| loss | -0.0892 | +| n_updates | 5660 | +| policy_gradient_loss | -0.0641 | +| value_loss | 0.000206 | +----------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.194 | +| time/ | | +| fps | 342 | +| iterations | 422 | +| time_elapsed | 10107 | +| total_timesteps | 3457024 | +| train/ | | +| approx_kl | 0.038121775 | +| clip_fraction | 0.303 | +| clip_range | 0.2 | +| entropy_loss | -5.82 | +| explained_variance | -0.105 | +| learning_rate | 1e-05 | +| loss | -0.111 | +| n_updates | 5670 | +| policy_gradient_loss | -0.0693 | +| value_loss | 0.000242 | +----------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.196 | +| time/ | | +| fps | 342 | +| iterations | 423 | +| time_elapsed | 10129 | +| total_timesteps | 3465216 | +| train/ | | +| approx_kl | 0.03758856 | +| clip_fraction | 0.306 | +| clip_range | 0.2 | +| entropy_loss | -6.06 | +| explained_variance | -0.205 | +| learning_rate | 1e-05 | +| loss | -0.123 | +| n_updates | 5680 | +| policy_gradient_loss | -0.0724 | +| value_loss | 0.000131 | +---------------------------------------- +Early stopping at step 8 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.202 | +| time/ | | +| fps | 342 | +| iterations | 424 | +| time_elapsed | 10152 | +| total_timesteps | 3473408 | +| train/ | | +| approx_kl | 0.03577784 | +| clip_fraction | 0.31 | +| clip_range | 0.2 | +| entropy_loss | -5.95 | +| explained_variance | 0.00535 | +| learning_rate | 1e-05 | +| loss | -0.108 | +| n_updates | 5690 | +| policy_gradient_loss | -0.065 | +| value_loss | 0.000149 | +---------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.197 | +| time/ | | +| fps | 342 | +| iterations | 425 | +| time_elapsed | 10174 | +| total_timesteps | 3481600 | +| train/ | | +| approx_kl | 0.032055076 | +| clip_fraction | 0.275 | +| clip_range | 0.2 | +| entropy_loss | -5.93 | +| explained_variance | -0.00915 | +| learning_rate | 1e-05 | +| loss | -0.0932 | +| n_updates | 5700 | +| policy_gradient_loss | -0.0575 | +| value_loss | 0.000219 | +----------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.78e+03 | +| ep_rew_mean | 0.201 | +| time/ | | +| fps | 342 | +| iterations | 426 | +| time_elapsed | 10195 | +| total_timesteps | 3489792 | +| train/ | | +| approx_kl | 0.03573284 | +| clip_fraction | 0.286 | +| clip_range | 0.2 | +| entropy_loss | -5.96 | +| explained_variance | -0.0831 | +| learning_rate | 1e-05 | +| loss | -0.0996 | +| n_updates | 5710 | +| policy_gradient_loss | -0.0622 | +| value_loss | 0.000228 | +---------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.19 | +| time/ | | +| fps | 342 | +| iterations | 427 | +| time_elapsed | 10216 | +| total_timesteps | 3497984 | +| train/ | | +| approx_kl | 0.038702816 | +| clip_fraction | 0.307 | +| clip_range | 0.2 | +| entropy_loss | -5.93 | +| explained_variance | -0.0466 | +| learning_rate | 1e-05 | +| loss | -0.1 | +| n_updates | 5720 | +| policy_gradient_loss | -0.0666 | +| value_loss | 0.000195 | +----------------------------------------- +Early stopping at step 8 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.197 | +| time/ | | +| fps | 342 | +| iterations | 428 | +| time_elapsed | 10240 | +| total_timesteps | 3506176 | +| train/ | | +| approx_kl | 0.039249938 | +| clip_fraction | 0.33 | +| clip_range | 0.2 | +| entropy_loss | -6.05 | +| explained_variance | -0.163 | +| learning_rate | 1e-05 | +| loss | -0.0867 | +| n_updates | 5730 | +| policy_gradient_loss | -0.0681 | +| value_loss | 0.000133 | +----------------------------------------- +Early stopping at step 8 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.202 | +| time/ | | +| fps | 342 | +| iterations | 429 | +| time_elapsed | 10263 | +| total_timesteps | 3514368 | +| train/ | | +| approx_kl | 0.042318523 | +| clip_fraction | 0.323 | +| clip_range | 0.2 | +| entropy_loss | -5.91 | +| explained_variance | -0.0331 | +| learning_rate | 1e-05 | +| loss | -0.114 | +| n_updates | 5740 | +| policy_gradient_loss | -0.068 | +| value_loss | 0.000236 | +----------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.198 | +| time/ | | +| fps | 342 | +| iterations | 430 | +| time_elapsed | 10285 | +| total_timesteps | 3522560 | +| train/ | | +| approx_kl | 0.0361939 | +| clip_fraction | 0.304 | +| clip_range | 0.2 | +| entropy_loss | -5.85 | +| explained_variance | -0.0696 | +| learning_rate | 1e-05 | +| loss | -0.0855 | +| n_updates | 5750 | +| policy_gradient_loss | -0.0671 | +| value_loss | 0.000164 | +--------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.206 | +| time/ | | +| fps | 342 | +| iterations | 431 | +| time_elapsed | 10308 | +| total_timesteps | 3530752 | +| train/ | | +| approx_kl | 0.047709063 | +| clip_fraction | 0.288 | +| clip_range | 0.2 | +| entropy_loss | -6.02 | +| explained_variance | -0.0276 | +| learning_rate | 1e-05 | +| loss | -0.0931 | +| n_updates | 5760 | +| policy_gradient_loss | -0.0637 | +| value_loss | 0.00025 | +----------------------------------------- +Early stopping at step 5 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.194 | +| time/ | | +| fps | 342 | +| iterations | 432 | +| time_elapsed | 10328 | +| total_timesteps | 3538944 | +| train/ | | +| approx_kl | 0.03107907 | +| clip_fraction | 0.266 | +| clip_range | 0.2 | +| entropy_loss | -5.82 | +| explained_variance | -0.0328 | +| learning_rate | 1e-05 | +| loss | -0.0946 | +| n_updates | 5770 | +| policy_gradient_loss | -0.0604 | +| value_loss | 0.00023 | +---------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.201 | +| time/ | | +| fps | 342 | +| iterations | 433 | +| time_elapsed | 10352 | +| total_timesteps | 3547136 | +| train/ | | +| approx_kl | 0.036264673 | +| clip_fraction | 0.317 | +| clip_range | 0.2 | +| entropy_loss | -5.93 | +| explained_variance | -0.0479 | +| learning_rate | 1e-05 | +| loss | -0.103 | +| n_updates | 5780 | +| policy_gradient_loss | -0.0683 | +| value_loss | 0.000142 | +----------------------------------------- +Early stopping at step 4 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.198 | +| time/ | | +| fps | 342 | +| iterations | 434 | +| time_elapsed | 10371 | +| total_timesteps | 3555328 | +| train/ | | +| approx_kl | 0.02811438 | +| clip_fraction | 0.196 | +| clip_range | 0.2 | +| entropy_loss | -5.93 | +| explained_variance | -0.0371 | +| learning_rate | 1e-05 | +| loss | -0.0832 | +| n_updates | 5790 | +| policy_gradient_loss | -0.0465 | +| value_loss | 0.00023 | +---------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.194 | +| time/ | | +| fps | 342 | +| iterations | 435 | +| time_elapsed | 10391 | +| total_timesteps | 3563520 | +| train/ | | +| approx_kl | 0.034738723 | +| clip_fraction | 0.27 | +| clip_range | 0.2 | +| entropy_loss | -6.03 | +| explained_variance | -0.146 | +| learning_rate | 1e-05 | +| loss | -0.102 | +| n_updates | 5800 | +| policy_gradient_loss | -0.0589 | +| value_loss | 0.00015 | +----------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.209 | +| time/ | | +| fps | 343 | +| iterations | 436 | +| time_elapsed | 10412 | +| total_timesteps | 3571712 | +| train/ | | +| approx_kl | 0.03502604 | +| clip_fraction | 0.291 | +| clip_range | 0.2 | +| entropy_loss | -5.91 | +| explained_variance | -0.0288 | +| learning_rate | 1e-05 | +| loss | -0.105 | +| n_updates | 5810 | +| policy_gradient_loss | -0.0628 | +| value_loss | 0.000182 | +---------------------------------------- +Early stopping at step 8 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.186 | +| time/ | | +| fps | 343 | +| iterations | 437 | +| time_elapsed | 10435 | +| total_timesteps | 3579904 | +| train/ | | +| approx_kl | 0.040826537 | +| clip_fraction | 0.332 | +| clip_range | 0.2 | +| entropy_loss | -5.91 | +| explained_variance | -0.103 | +| learning_rate | 1e-05 | +| loss | -0.113 | +| n_updates | 5820 | +| policy_gradient_loss | -0.0701 | +| value_loss | 0.000149 | +----------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.196 | +| time/ | | +| fps | 343 | +| iterations | 438 | +| time_elapsed | 10457 | +| total_timesteps | 3588096 | +| train/ | | +| approx_kl | 0.039323226 | +| clip_fraction | 0.311 | +| clip_range | 0.2 | +| entropy_loss | -5.94 | +| explained_variance | -0.0388 | +| learning_rate | 1e-05 | +| loss | -0.11 | +| n_updates | 5830 | +| policy_gradient_loss | -0.0636 | +| value_loss | 0.0002 | +----------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.208 | +| time/ | | +| fps | 343 | +| iterations | 439 | +| time_elapsed | 10480 | +| total_timesteps | 3596288 | +| train/ | | +| approx_kl | 0.03640859 | +| clip_fraction | 0.308 | +| clip_range | 0.2 | +| entropy_loss | -5.86 | +| explained_variance | -0.0686 | +| learning_rate | 1e-05 | +| loss | -0.0999 | +| n_updates | 5840 | +| policy_gradient_loss | -0.0667 | +| value_loss | 0.000213 | +---------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.207 | +| time/ | | +| fps | 343 | +| iterations | 440 | +| time_elapsed | 10502 | +| total_timesteps | 3604480 | +| train/ | | +| approx_kl | 0.03823511 | +| clip_fraction | 0.289 | +| clip_range | 0.2 | +| entropy_loss | -5.98 | +| explained_variance | -0.0204 | +| learning_rate | 1e-05 | +| loss | -0.102 | +| n_updates | 5850 | +| policy_gradient_loss | -0.0674 | +| value_loss | 0.000211 | +---------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.208 | +| time/ | | +| fps | 343 | +| iterations | 441 | +| time_elapsed | 10523 | +| total_timesteps | 3612672 | +| train/ | | +| approx_kl | 0.035731696 | +| clip_fraction | 0.313 | +| clip_range | 0.2 | +| entropy_loss | -5.76 | +| explained_variance | -0.0485 | +| learning_rate | 1e-05 | +| loss | -0.105 | +| n_updates | 5860 | +| policy_gradient_loss | -0.0668 | +| value_loss | 0.000167 | +----------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.199 | +| time/ | | +| fps | 343 | +| iterations | 442 | +| time_elapsed | 10544 | +| total_timesteps | 3620864 | +| train/ | | +| approx_kl | 0.03383276 | +| clip_fraction | 0.272 | +| clip_range | 0.2 | +| entropy_loss | -5.85 | +| explained_variance | 0.0151 | +| learning_rate | 1e-05 | +| loss | -0.101 | +| n_updates | 5870 | +| policy_gradient_loss | -0.058 | +| value_loss | 0.00014 | +---------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.199 | +| time/ | | +| fps | 343 | +| iterations | 443 | +| time_elapsed | 10567 | +| total_timesteps | 3629056 | +| train/ | | +| approx_kl | 0.03833392 | +| clip_fraction | 0.296 | +| clip_range | 0.2 | +| entropy_loss | -5.92 | +| explained_variance | -0.0307 | +| learning_rate | 1e-05 | +| loss | -0.106 | +| n_updates | 5880 | +| policy_gradient_loss | -0.0633 | +| value_loss | 0.000193 | +---------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.192 | +| time/ | | +| fps | 343 | +| iterations | 444 | +| time_elapsed | 10589 | +| total_timesteps | 3637248 | +| train/ | | +| approx_kl | 0.03361411 | +| clip_fraction | 0.287 | +| clip_range | 0.2 | +| entropy_loss | -5.91 | +| explained_variance | -0.0383 | +| learning_rate | 1e-05 | +| loss | -0.103 | +| n_updates | 5890 | +| policy_gradient_loss | -0.0591 | +| value_loss | 0.000204 | +---------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.184 | +| time/ | | +| fps | 343 | +| iterations | 445 | +| time_elapsed | 10612 | +| total_timesteps | 3645440 | +| train/ | | +| approx_kl | 0.037749745 | +| clip_fraction | 0.317 | +| clip_range | 0.2 | +| entropy_loss | -5.85 | +| explained_variance | -0.00636 | +| learning_rate | 1e-05 | +| loss | -0.0848 | +| n_updates | 5900 | +| policy_gradient_loss | -0.0675 | +| value_loss | 0.000129 | +----------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.192 | +| time/ | | +| fps | 343 | +| iterations | 446 | +| time_elapsed | 10633 | +| total_timesteps | 3653632 | +| train/ | | +| approx_kl | 0.0370719 | +| clip_fraction | 0.283 | +| clip_range | 0.2 | +| entropy_loss | -5.95 | +| explained_variance | 0.00643 | +| learning_rate | 1e-05 | +| loss | -0.1 | +| n_updates | 5910 | +| policy_gradient_loss | -0.0618 | +| value_loss | 0.000189 | +--------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.187 | +| time/ | | +| fps | 343 | +| iterations | 447 | +| time_elapsed | 10657 | +| total_timesteps | 3661824 | +| train/ | | +| approx_kl | 0.039156154 | +| clip_fraction | 0.307 | +| clip_range | 0.2 | +| entropy_loss | -5.95 | +| explained_variance | -0.138 | +| learning_rate | 1e-05 | +| loss | -0.1 | +| n_updates | 5920 | +| policy_gradient_loss | -0.0663 | +| value_loss | 0.000161 | +----------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.186 | +| time/ | | +| fps | 343 | +| iterations | 448 | +| time_elapsed | 10680 | +| total_timesteps | 3670016 | +| train/ | | +| approx_kl | 0.036686555 | +| clip_fraction | 0.31 | +| clip_range | 0.2 | +| entropy_loss | -5.91 | +| explained_variance | -0.0356 | +| learning_rate | 1e-05 | +| loss | -0.112 | +| n_updates | 5930 | +| policy_gradient_loss | -0.0647 | +| value_loss | 0.000194 | +----------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.189 | +| time/ | | +| fps | 343 | +| iterations | 449 | +| time_elapsed | 10702 | +| total_timesteps | 3678208 | +| train/ | | +| approx_kl | 0.0369815 | +| clip_fraction | 0.31 | +| clip_range | 0.2 | +| entropy_loss | -5.96 | +| explained_variance | -0.179 | +| learning_rate | 1e-05 | +| loss | -0.101 | +| n_updates | 5940 | +| policy_gradient_loss | -0.0652 | +| value_loss | 0.000159 | +--------------------------------------- +Early stopping at step 5 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.194 | +| time/ | | +| fps | 343 | +| iterations | 450 | +| time_elapsed | 10723 | +| total_timesteps | 3686400 | +| train/ | | +| approx_kl | 0.033135407 | +| clip_fraction | 0.258 | +| clip_range | 0.2 | +| entropy_loss | -5.82 | +| explained_variance | -0.1 | +| learning_rate | 1e-05 | +| loss | -0.113 | +| n_updates | 5950 | +| policy_gradient_loss | -0.0595 | +| value_loss | 0.000154 | +----------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.185 | +| time/ | | +| fps | 343 | +| iterations | 451 | +| time_elapsed | 10744 | +| total_timesteps | 3694592 | +| train/ | | +| approx_kl | 0.038079735 | +| clip_fraction | 0.275 | +| clip_range | 0.2 | +| entropy_loss | -6.03 | +| explained_variance | -0.0418 | +| learning_rate | 1e-05 | +| loss | -0.0837 | +| n_updates | 5960 | +| policy_gradient_loss | -0.0615 | +| value_loss | 0.000184 | +----------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.181 | +| time/ | | +| fps | 343 | +| iterations | 452 | +| time_elapsed | 10766 | +| total_timesteps | 3702784 | +| train/ | | +| approx_kl | 0.0359037 | +| clip_fraction | 0.297 | +| clip_range | 0.2 | +| entropy_loss | -5.91 | +| explained_variance | -0.138 | +| learning_rate | 1e-05 | +| loss | -0.108 | +| n_updates | 5970 | +| policy_gradient_loss | -0.0627 | +| value_loss | 0.000171 | +--------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.175 | +| time/ | | +| fps | 343 | +| iterations | 453 | +| time_elapsed | 10790 | +| total_timesteps | 3710976 | +| train/ | | +| approx_kl | 0.03712887 | +| clip_fraction | 0.3 | +| clip_range | 0.2 | +| entropy_loss | -5.94 | +| explained_variance | -0.091 | +| learning_rate | 1e-05 | +| loss | -0.0832 | +| n_updates | 5980 | +| policy_gradient_loss | -0.06 | +| value_loss | 0.000171 | +---------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.181 | +| time/ | | +| fps | 344 | +| iterations | 454 | +| time_elapsed | 10810 | +| total_timesteps | 3719168 | +| train/ | | +| approx_kl | 0.03472683 | +| clip_fraction | 0.285 | +| clip_range | 0.2 | +| entropy_loss | -5.92 | +| explained_variance | -0.0558 | +| learning_rate | 1e-05 | +| loss | -0.0988 | +| n_updates | 5990 | +| policy_gradient_loss | -0.063 | +| value_loss | 0.000153 | +---------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.175 | +| time/ | | +| fps | 344 | +| iterations | 455 | +| time_elapsed | 10833 | +| total_timesteps | 3727360 | +| train/ | | +| approx_kl | 0.034337785 | +| clip_fraction | 0.302 | +| clip_range | 0.2 | +| entropy_loss | -5.9 | +| explained_variance | -0.0699 | +| learning_rate | 1e-05 | +| loss | -0.0799 | +| n_updates | 6000 | +| policy_gradient_loss | -0.0634 | +| value_loss | 0.000141 | +----------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.183 | +| time/ | | +| fps | 344 | +| iterations | 456 | +| time_elapsed | 10856 | +| total_timesteps | 3735552 | +| train/ | | +| approx_kl | 0.037471797 | +| clip_fraction | 0.305 | +| clip_range | 0.2 | +| entropy_loss | -5.89 | +| explained_variance | -0.0336 | +| learning_rate | 1e-05 | +| loss | -0.095 | +| n_updates | 6010 | +| policy_gradient_loss | -0.064 | +| value_loss | 0.000164 | +----------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.179 | +| time/ | | +| fps | 344 | +| iterations | 457 | +| time_elapsed | 10877 | +| total_timesteps | 3743744 | +| train/ | | +| approx_kl | 0.032627713 | +| clip_fraction | 0.281 | +| clip_range | 0.2 | +| entropy_loss | -5.96 | +| explained_variance | -0.182 | +| learning_rate | 1e-05 | +| loss | -0.0988 | +| n_updates | 6020 | +| policy_gradient_loss | -0.0612 | +| value_loss | 0.000121 | +----------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.82e+03 | +| ep_rew_mean | 0.18 | +| time/ | | +| fps | 344 | +| iterations | 458 | +| time_elapsed | 10898 | +| total_timesteps | 3751936 | +| train/ | | +| approx_kl | 0.035887174 | +| clip_fraction | 0.279 | +| clip_range | 0.2 | +| entropy_loss | -5.93 | +| explained_variance | -0.0589 | +| learning_rate | 1e-05 | +| loss | -0.1 | +| n_updates | 6030 | +| policy_gradient_loss | -0.0566 | +| value_loss | 0.00015 | +----------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.194 | +| time/ | | +| fps | 344 | +| iterations | 459 | +| time_elapsed | 10921 | +| total_timesteps | 3760128 | +| train/ | | +| approx_kl | 0.03634392 | +| clip_fraction | 0.31 | +| clip_range | 0.2 | +| entropy_loss | -6.13 | +| explained_variance | -0.0954 | +| learning_rate | 1e-05 | +| loss | -0.0853 | +| n_updates | 6040 | +| policy_gradient_loss | -0.0632 | +| value_loss | 0.000104 | +---------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.198 | +| time/ | | +| fps | 344 | +| iterations | 460 | +| time_elapsed | 10943 | +| total_timesteps | 3768320 | +| train/ | | +| approx_kl | 0.033260826 | +| clip_fraction | 0.29 | +| clip_range | 0.2 | +| entropy_loss | -5.8 | +| explained_variance | -0.0424 | +| learning_rate | 1e-05 | +| loss | -0.0988 | +| n_updates | 6050 | +| policy_gradient_loss | -0.0597 | +| value_loss | 0.000189 | +----------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.189 | +| time/ | | +| fps | 344 | +| iterations | 461 | +| time_elapsed | 10966 | +| total_timesteps | 3776512 | +| train/ | | +| approx_kl | 0.03423908 | +| clip_fraction | 0.291 | +| clip_range | 0.2 | +| entropy_loss | -5.74 | +| explained_variance | -0.139 | +| learning_rate | 1e-05 | +| loss | -0.106 | +| n_updates | 6060 | +| policy_gradient_loss | -0.0645 | +| value_loss | 0.000165 | +---------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.179 | +| time/ | | +| fps | 344 | +| iterations | 462 | +| time_elapsed | 10987 | +| total_timesteps | 3784704 | +| train/ | | +| approx_kl | 0.03363544 | +| clip_fraction | 0.269 | +| clip_range | 0.2 | +| entropy_loss | -6.08 | +| explained_variance | -0.148 | +| learning_rate | 1e-05 | +| loss | -0.106 | +| n_updates | 6070 | +| policy_gradient_loss | -0.0602 | +| value_loss | 0.000123 | +---------------------------------------- +Early stopping at step 8 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.89e+03 | +| ep_rew_mean | 0.183 | +| time/ | | +| fps | 344 | +| iterations | 463 | +| time_elapsed | 11011 | +| total_timesteps | 3792896 | +| train/ | | +| approx_kl | 0.039866723 | +| clip_fraction | 0.318 | +| clip_range | 0.2 | +| entropy_loss | -6.01 | +| explained_variance | -0.0393 | +| learning_rate | 1e-05 | +| loss | -0.0918 | +| n_updates | 6080 | +| policy_gradient_loss | -0.0627 | +| value_loss | 0.000147 | +----------------------------------------- +Early stopping at step 5 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.89e+03 | +| ep_rew_mean | 0.188 | +| time/ | | +| fps | 344 | +| iterations | 464 | +| time_elapsed | 11032 | +| total_timesteps | 3801088 | +| train/ | | +| approx_kl | 0.03675319 | +| clip_fraction | 0.252 | +| clip_range | 0.2 | +| entropy_loss | -5.84 | +| explained_variance | -0.0748 | +| learning_rate | 1e-05 | +| loss | -0.109 | +| n_updates | 6090 | +| policy_gradient_loss | -0.0539 | +| value_loss | 0.000185 | +---------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.194 | +| time/ | | +| fps | 344 | +| iterations | 465 | +| time_elapsed | 11054 | +| total_timesteps | 3809280 | +| train/ | | +| approx_kl | 0.03773135 | +| clip_fraction | 0.296 | +| clip_range | 0.2 | +| entropy_loss | -5.98 | +| explained_variance | -0.0541 | +| learning_rate | 1e-05 | +| loss | -0.102 | +| n_updates | 6100 | +| policy_gradient_loss | -0.0606 | +| value_loss | 0.000211 | +---------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.9e+03 | +| ep_rew_mean | 0.195 | +| time/ | | +| fps | 344 | +| iterations | 466 | +| time_elapsed | 11078 | +| total_timesteps | 3817472 | +| train/ | | +| approx_kl | 0.04699885 | +| clip_fraction | 0.31 | +| clip_range | 0.2 | +| entropy_loss | -5.94 | +| explained_variance | -0.122 | +| learning_rate | 1e-05 | +| loss | -0.108 | +| n_updates | 6110 | +| policy_gradient_loss | -0.0635 | +| value_loss | 0.000234 | +---------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.9e+03 | +| ep_rew_mean | 0.201 | +| time/ | | +| fps | 344 | +| iterations | 467 | +| time_elapsed | 11099 | +| total_timesteps | 3825664 | +| train/ | | +| approx_kl | 0.03889063 | +| clip_fraction | 0.298 | +| clip_range | 0.2 | +| entropy_loss | -5.88 | +| explained_variance | -0.0942 | +| learning_rate | 1e-05 | +| loss | -0.122 | +| n_updates | 6120 | +| policy_gradient_loss | -0.0674 | +| value_loss | 0.000149 | +---------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.89e+03 | +| ep_rew_mean | 0.197 | +| time/ | | +| fps | 344 | +| iterations | 468 | +| time_elapsed | 11120 | +| total_timesteps | 3833856 | +| train/ | | +| approx_kl | 0.033813052 | +| clip_fraction | 0.287 | +| clip_range | 0.2 | +| entropy_loss | -5.84 | +| explained_variance | -0.0986 | +| learning_rate | 1e-05 | +| loss | -0.094 | +| n_updates | 6130 | +| policy_gradient_loss | -0.0611 | +| value_loss | 0.000157 | +----------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.193 | +| time/ | | +| fps | 344 | +| iterations | 469 | +| time_elapsed | 11143 | +| total_timesteps | 3842048 | +| train/ | | +| approx_kl | 0.03504477 | +| clip_fraction | 0.283 | +| clip_range | 0.2 | +| entropy_loss | -6.03 | +| explained_variance | -0.0665 | +| learning_rate | 1e-05 | +| loss | -0.102 | +| n_updates | 6140 | +| policy_gradient_loss | -0.0627 | +| value_loss | 0.000176 | +---------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.191 | +| time/ | | +| fps | 344 | +| iterations | 470 | +| time_elapsed | 11165 | +| total_timesteps | 3850240 | +| train/ | | +| approx_kl | 0.038565706 | +| clip_fraction | 0.315 | +| clip_range | 0.2 | +| entropy_loss | -5.96 | +| explained_variance | -0.0673 | +| learning_rate | 1e-05 | +| loss | -0.104 | +| n_updates | 6150 | +| policy_gradient_loss | -0.0659 | +| value_loss | 0.000165 | +----------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.193 | +| time/ | | +| fps | 344 | +| iterations | 471 | +| time_elapsed | 11188 | +| total_timesteps | 3858432 | +| train/ | | +| approx_kl | 0.03747919 | +| clip_fraction | 0.295 | +| clip_range | 0.2 | +| entropy_loss | -5.87 | +| explained_variance | -0.0439 | +| learning_rate | 1e-05 | +| loss | -0.0964 | +| n_updates | 6160 | +| policy_gradient_loss | -0.0626 | +| value_loss | 0.000204 | +---------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.191 | +| time/ | | +| fps | 344 | +| iterations | 472 | +| time_elapsed | 11211 | +| total_timesteps | 3866624 | +| train/ | | +| approx_kl | 0.040243816 | +| clip_fraction | 0.271 | +| clip_range | 0.2 | +| entropy_loss | -5.73 | +| explained_variance | -0.195 | +| learning_rate | 1e-05 | +| loss | -0.0932 | +| n_updates | 6170 | +| policy_gradient_loss | -0.0591 | +| value_loss | 0.000178 | +----------------------------------------- +Early stopping at step 4 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.9e+03 | +| ep_rew_mean | 0.186 | +| time/ | | +| fps | 345 | +| iterations | 473 | +| time_elapsed | 11230 | +| total_timesteps | 3874816 | +| train/ | | +| approx_kl | 0.02925313 | +| clip_fraction | 0.246 | +| clip_range | 0.2 | +| entropy_loss | -5.93 | +| explained_variance | -0.079 | +| learning_rate | 1e-05 | +| loss | -0.103 | +| n_updates | 6180 | +| policy_gradient_loss | -0.0583 | +| value_loss | 0.000143 | +---------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.9e+03 | +| ep_rew_mean | 0.189 | +| time/ | | +| fps | 345 | +| iterations | 474 | +| time_elapsed | 11251 | +| total_timesteps | 3883008 | +| train/ | | +| approx_kl | 0.035933826 | +| clip_fraction | 0.29 | +| clip_range | 0.2 | +| entropy_loss | -5.88 | +| explained_variance | -0.0558 | +| learning_rate | 1e-05 | +| loss | -0.101 | +| n_updates | 6190 | +| policy_gradient_loss | -0.0587 | +| value_loss | 0.00015 | +----------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.89e+03 | +| ep_rew_mean | 0.187 | +| time/ | | +| fps | 345 | +| iterations | 475 | +| time_elapsed | 11272 | +| total_timesteps | 3891200 | +| train/ | | +| approx_kl | 0.03717289 | +| clip_fraction | 0.283 | +| clip_range | 0.2 | +| entropy_loss | -5.9 | +| explained_variance | -0.0894 | +| learning_rate | 1e-05 | +| loss | -0.0936 | +| n_updates | 6200 | +| policy_gradient_loss | -0.0632 | +| value_loss | 0.000147 | +---------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.197 | +| time/ | | +| fps | 345 | +| iterations | 476 | +| time_elapsed | 11293 | +| total_timesteps | 3899392 | +| train/ | | +| approx_kl | 0.034574647 | +| clip_fraction | 0.297 | +| clip_range | 0.2 | +| entropy_loss | -5.94 | +| explained_variance | -0.123 | +| learning_rate | 1e-05 | +| loss | -0.0855 | +| n_updates | 6210 | +| policy_gradient_loss | -0.0667 | +| value_loss | 0.000125 | +----------------------------------------- +Early stopping at step 5 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.195 | +| time/ | | +| fps | 345 | +| iterations | 477 | +| time_elapsed | 11315 | +| total_timesteps | 3907584 | +| train/ | | +| approx_kl | 0.033426937 | +| clip_fraction | 0.26 | +| clip_range | 0.2 | +| entropy_loss | -5.69 | +| explained_variance | -0.0509 | +| learning_rate | 1e-05 | +| loss | -0.0789 | +| n_updates | 6220 | +| policy_gradient_loss | -0.0496 | +| value_loss | 0.00026 | +----------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.194 | +| time/ | | +| fps | 345 | +| iterations | 478 | +| time_elapsed | 11338 | +| total_timesteps | 3915776 | +| train/ | | +| approx_kl | 0.035407014 | +| clip_fraction | 0.286 | +| clip_range | 0.2 | +| entropy_loss | -6.01 | +| explained_variance | -0.0798 | +| learning_rate | 1e-05 | +| loss | -0.117 | +| n_updates | 6230 | +| policy_gradient_loss | -0.0663 | +| value_loss | 0.000164 | +----------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.204 | +| time/ | | +| fps | 345 | +| iterations | 479 | +| time_elapsed | 11359 | +| total_timesteps | 3923968 | +| train/ | | +| approx_kl | 0.03457465 | +| clip_fraction | 0.261 | +| clip_range | 0.2 | +| entropy_loss | -5.97 | +| explained_variance | -0.0883 | +| learning_rate | 1e-05 | +| loss | -0.0762 | +| n_updates | 6240 | +| policy_gradient_loss | -0.0563 | +| value_loss | 0.000198 | +---------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.199 | +| time/ | | +| fps | 345 | +| iterations | 480 | +| time_elapsed | 11383 | +| total_timesteps | 3932160 | +| train/ | | +| approx_kl | 0.036188636 | +| clip_fraction | 0.322 | +| clip_range | 0.2 | +| entropy_loss | -5.83 | +| explained_variance | -0.0685 | +| learning_rate | 1e-05 | +| loss | -0.0963 | +| n_updates | 6250 | +| policy_gradient_loss | -0.0661 | +| value_loss | 0.000192 | +----------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.78e+03 | +| ep_rew_mean | 0.203 | +| time/ | | +| fps | 345 | +| iterations | 481 | +| time_elapsed | 11403 | +| total_timesteps | 3940352 | +| train/ | | +| approx_kl | 0.038585037 | +| clip_fraction | 0.283 | +| clip_range | 0.2 | +| entropy_loss | -5.89 | +| explained_variance | -0.159 | +| learning_rate | 1e-05 | +| loss | -0.0842 | +| n_updates | 6260 | +| policy_gradient_loss | -0.0603 | +| value_loss | 0.000235 | +----------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.197 | +| time/ | | +| fps | 345 | +| iterations | 482 | +| time_elapsed | 11426 | +| total_timesteps | 3948544 | +| train/ | | +| approx_kl | 0.033984162 | +| clip_fraction | 0.31 | +| clip_range | 0.2 | +| entropy_loss | -5.79 | +| explained_variance | -0.109 | +| learning_rate | 1e-05 | +| loss | -0.104 | +| n_updates | 6270 | +| policy_gradient_loss | -0.0648 | +| value_loss | 0.00017 | +----------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.203 | +| time/ | | +| fps | 345 | +| iterations | 483 | +| time_elapsed | 11450 | +| total_timesteps | 3956736 | +| train/ | | +| approx_kl | 0.039888013 | +| clip_fraction | 0.307 | +| clip_range | 0.2 | +| entropy_loss | -5.74 | +| explained_variance | -0.0447 | +| learning_rate | 1e-05 | +| loss | -0.0918 | +| n_updates | 6280 | +| policy_gradient_loss | -0.0659 | +| value_loss | 0.000167 | +----------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.203 | +| time/ | | +| fps | 345 | +| iterations | 484 | +| time_elapsed | 11470 | +| total_timesteps | 3964928 | +| train/ | | +| approx_kl | 0.03485775 | +| clip_fraction | 0.287 | +| clip_range | 0.2 | +| entropy_loss | -5.87 | +| explained_variance | -0.0978 | +| learning_rate | 1e-05 | +| loss | -0.114 | +| n_updates | 6290 | +| policy_gradient_loss | -0.0602 | +| value_loss | 0.000164 | +---------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.207 | +| time/ | | +| fps | 345 | +| iterations | 485 | +| time_elapsed | 11493 | +| total_timesteps | 3973120 | +| train/ | | +| approx_kl | 0.03773351 | +| clip_fraction | 0.311 | +| clip_range | 0.2 | +| entropy_loss | -5.69 | +| explained_variance | -0.0158 | +| learning_rate | 1e-05 | +| loss | -0.0933 | +| n_updates | 6300 | +| policy_gradient_loss | -0.0638 | +| value_loss | 0.000182 | +---------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.209 | +| time/ | | +| fps | 345 | +| iterations | 486 | +| time_elapsed | 11514 | +| total_timesteps | 3981312 | +| train/ | | +| approx_kl | 0.037471868 | +| clip_fraction | 0.272 | +| clip_range | 0.2 | +| entropy_loss | -5.8 | +| explained_variance | -0.154 | +| learning_rate | 1e-05 | +| loss | -0.0935 | +| n_updates | 6310 | +| policy_gradient_loss | -0.0599 | +| value_loss | 0.000171 | +----------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.212 | +| time/ | | +| fps | 345 | +| iterations | 487 | +| time_elapsed | 11536 | +| total_timesteps | 3989504 | +| train/ | | +| approx_kl | 0.03770376 | +| clip_fraction | 0.308 | +| clip_range | 0.2 | +| entropy_loss | -5.92 | +| explained_variance | -0.0701 | +| learning_rate | 1e-05 | +| loss | -0.107 | +| n_updates | 6320 | +| policy_gradient_loss | -0.0644 | +| value_loss | 0.000175 | +---------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.8e+03 | +| ep_rew_mean | 0.21 | +| time/ | | +| fps | 345 | +| iterations | 488 | +| time_elapsed | 11559 | +| total_timesteps | 3997696 | +| train/ | | +| approx_kl | 0.03903682 | +| clip_fraction | 0.32 | +| clip_range | 0.2 | +| entropy_loss | -5.74 | +| explained_variance | -0.0318 | +| learning_rate | 1e-05 | +| loss | -0.118 | +| n_updates | 6330 | +| policy_gradient_loss | -0.0664 | +| value_loss | 0.000174 | +---------------------------------------- +Early stopping at step 5 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.207 | +| time/ | | +| fps | 345 | +| iterations | 489 | +| time_elapsed | 11579 | +| total_timesteps | 4005888 | +| train/ | | +| approx_kl | 0.031445846 | +| clip_fraction | 0.257 | +| clip_range | 0.2 | +| entropy_loss | -5.75 | +| explained_variance | -0.105 | +| learning_rate | 1e-05 | +| loss | -0.0825 | +| n_updates | 6340 | +| policy_gradient_loss | -0.0552 | +| value_loss | 0.000145 | +----------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.81e+03 | +| ep_rew_mean | 0.204 | +| time/ | | +| fps | 346 | +| iterations | 490 | +| time_elapsed | 11599 | +| total_timesteps | 4014080 | +| train/ | | +| approx_kl | 0.03514891 | +| clip_fraction | 0.277 | +| clip_range | 0.2 | +| entropy_loss | -5.77 | +| explained_variance | -0.0241 | +| learning_rate | 1e-05 | +| loss | -0.117 | +| n_updates | 6350 | +| policy_gradient_loss | -0.0595 | +| value_loss | 0.000161 | +---------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.82e+03 | +| ep_rew_mean | 0.206 | +| time/ | | +| fps | 346 | +| iterations | 491 | +| time_elapsed | 11621 | +| total_timesteps | 4022272 | +| train/ | | +| approx_kl | 0.03481791 | +| clip_fraction | 0.301 | +| clip_range | 0.2 | +| entropy_loss | -5.77 | +| explained_variance | -0.0477 | +| learning_rate | 1e-05 | +| loss | -0.0881 | +| n_updates | 6360 | +| policy_gradient_loss | -0.0614 | +| value_loss | 0.000116 | +---------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.225 | +| time/ | | +| fps | 346 | +| iterations | 492 | +| time_elapsed | 11643 | +| total_timesteps | 4030464 | +| train/ | | +| approx_kl | 0.04471199 | +| clip_fraction | 0.315 | +| clip_range | 0.2 | +| entropy_loss | -5.8 | +| explained_variance | -0.117 | +| learning_rate | 1e-05 | +| loss | -0.113 | +| n_updates | 6370 | +| policy_gradient_loss | -0.0658 | +| value_loss | 0.000153 | +---------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.22 | +| time/ | | +| fps | 346 | +| iterations | 493 | +| time_elapsed | 11665 | +| total_timesteps | 4038656 | +| train/ | | +| approx_kl | 0.036991037 | +| clip_fraction | 0.296 | +| clip_range | 0.2 | +| entropy_loss | -5.84 | +| explained_variance | -0.0429 | +| learning_rate | 1e-05 | +| loss | -0.108 | +| n_updates | 6380 | +| policy_gradient_loss | -0.0611 | +| value_loss | 0.000268 | +----------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.218 | +| time/ | | +| fps | 346 | +| iterations | 494 | +| time_elapsed | 11688 | +| total_timesteps | 4046848 | +| train/ | | +| approx_kl | 0.03468462 | +| clip_fraction | 0.286 | +| clip_range | 0.2 | +| entropy_loss | -5.95 | +| explained_variance | -0.13 | +| learning_rate | 1e-05 | +| loss | -0.1 | +| n_updates | 6390 | +| policy_gradient_loss | -0.0642 | +| value_loss | 0.000155 | +---------------------------------------- +Early stopping at step 5 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.222 | +| time/ | | +| fps | 346 | +| iterations | 495 | +| time_elapsed | 11709 | +| total_timesteps | 4055040 | +| train/ | | +| approx_kl | 0.03222477 | +| clip_fraction | 0.273 | +| clip_range | 0.2 | +| entropy_loss | -5.87 | +| explained_variance | -0.0823 | +| learning_rate | 1e-05 | +| loss | -0.08 | +| n_updates | 6400 | +| policy_gradient_loss | -0.0561 | +| value_loss | 0.000188 | +---------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.82e+03 | +| ep_rew_mean | 0.218 | +| time/ | | +| fps | 346 | +| iterations | 496 | +| time_elapsed | 11731 | +| total_timesteps | 4063232 | +| train/ | | +| approx_kl | 0.036779094 | +| clip_fraction | 0.305 | +| clip_range | 0.2 | +| entropy_loss | -5.79 | +| explained_variance | -0.0591 | +| learning_rate | 1e-05 | +| loss | -0.0925 | +| n_updates | 6410 | +| policy_gradient_loss | -0.0622 | +| value_loss | 0.000169 | +----------------------------------------- +Early stopping at step 8 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.81e+03 | +| ep_rew_mean | 0.226 | +| time/ | | +| fps | 346 | +| iterations | 497 | +| time_elapsed | 11754 | +| total_timesteps | 4071424 | +| train/ | | +| approx_kl | 0.042729422 | +| clip_fraction | 0.324 | +| clip_range | 0.2 | +| entropy_loss | -5.84 | +| explained_variance | -0.158 | +| learning_rate | 1e-05 | +| loss | -0.108 | +| n_updates | 6420 | +| policy_gradient_loss | -0.064 | +| value_loss | 0.000185 | +----------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.221 | +| time/ | | +| fps | 346 | +| iterations | 498 | +| time_elapsed | 11776 | +| total_timesteps | 4079616 | +| train/ | | +| approx_kl | 0.034251466 | +| clip_fraction | 0.286 | +| clip_range | 0.2 | +| entropy_loss | -5.82 | +| explained_variance | -0.0551 | +| learning_rate | 1e-05 | +| loss | -0.0941 | +| n_updates | 6430 | +| policy_gradient_loss | -0.0582 | +| value_loss | 0.000198 | +----------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.82e+03 | +| ep_rew_mean | 0.215 | +| time/ | | +| fps | 346 | +| iterations | 499 | +| time_elapsed | 11798 | +| total_timesteps | 4087808 | +| train/ | | +| approx_kl | 0.037206236 | +| clip_fraction | 0.282 | +| clip_range | 0.2 | +| entropy_loss | -5.93 | +| explained_variance | -0.0884 | +| learning_rate | 1e-05 | +| loss | -0.0999 | +| n_updates | 6440 | +| policy_gradient_loss | -0.0562 | +| value_loss | 0.000163 | +----------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.214 | +| time/ | | +| fps | 346 | +| iterations | 500 | +| time_elapsed | 11820 | +| total_timesteps | 4096000 | +| train/ | | +| approx_kl | 0.040443316 | +| clip_fraction | 0.332 | +| clip_range | 0.2 | +| entropy_loss | -5.8 | +| explained_variance | -0.112 | +| learning_rate | 1e-05 | +| loss | -0.11 | +| n_updates | 6450 | +| policy_gradient_loss | -0.0709 | +| value_loss | 0.000171 | +----------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.215 | +| time/ | | +| fps | 346 | +| iterations | 501 | +| time_elapsed | 11842 | +| total_timesteps | 4104192 | +| train/ | | +| approx_kl | 0.03893515 | +| clip_fraction | 0.31 | +| clip_range | 0.2 | +| entropy_loss | -5.75 | +| explained_variance | -0.0316 | +| learning_rate | 1e-05 | +| loss | -0.103 | +| n_updates | 6460 | +| policy_gradient_loss | -0.0643 | +| value_loss | 0.000142 | +---------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.214 | +| time/ | | +| fps | 346 | +| iterations | 502 | +| time_elapsed | 11864 | +| total_timesteps | 4112384 | +| train/ | | +| approx_kl | 0.045732275 | +| clip_fraction | 0.295 | +| clip_range | 0.2 | +| entropy_loss | -5.85 | +| explained_variance | 0.0134 | +| learning_rate | 1e-05 | +| loss | -0.102 | +| n_updates | 6470 | +| policy_gradient_loss | -0.0606 | +| value_loss | 0.000147 | +----------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.213 | +| time/ | | +| fps | 346 | +| iterations | 503 | +| time_elapsed | 11885 | +| total_timesteps | 4120576 | +| train/ | | +| approx_kl | 0.03491245 | +| clip_fraction | 0.273 | +| clip_range | 0.2 | +| entropy_loss | -5.81 | +| explained_variance | -0.115 | +| learning_rate | 1e-05 | +| loss | -0.0924 | +| n_updates | 6480 | +| policy_gradient_loss | -0.059 | +| value_loss | 0.000141 | +---------------------------------------- +Early stopping at step 8 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.21 | +| time/ | | +| fps | 346 | +| iterations | 504 | +| time_elapsed | 11909 | +| total_timesteps | 4128768 | +| train/ | | +| approx_kl | 0.040733196 | +| clip_fraction | 0.33 | +| clip_range | 0.2 | +| entropy_loss | -5.81 | +| explained_variance | -0.0602 | +| learning_rate | 1e-05 | +| loss | -0.112 | +| n_updates | 6490 | +| policy_gradient_loss | -0.0646 | +| value_loss | 0.000174 | +----------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.06 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.213 | +| time/ | | +| fps | 346 | +| iterations | 505 | +| time_elapsed | 11931 | +| total_timesteps | 4136960 | +| train/ | | +| approx_kl | 0.036839623 | +| clip_fraction | 0.271 | +| clip_range | 0.2 | +| entropy_loss | -5.97 | +| explained_variance | -0.149 | +| learning_rate | 1e-05 | +| loss | -0.0899 | +| n_updates | 6500 | +| policy_gradient_loss | -0.0609 | +| value_loss | 0.000187 | +----------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.9e+03 | +| ep_rew_mean | 0.214 | +| time/ | | +| fps | 346 | +| iterations | 506 | +| time_elapsed | 11951 | +| total_timesteps | 4145152 | +| train/ | | +| approx_kl | 0.0362993 | +| clip_fraction | 0.292 | +| clip_range | 0.2 | +| entropy_loss | -5.9 | +| explained_variance | -0.0127 | +| learning_rate | 1e-05 | +| loss | -0.101 | +| n_updates | 6510 | +| policy_gradient_loss | -0.0615 | +| value_loss | 0.000207 | +--------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.201 | +| time/ | | +| fps | 346 | +| iterations | 507 | +| time_elapsed | 11972 | +| total_timesteps | 4153344 | +| train/ | | +| approx_kl | 0.03697148 | +| clip_fraction | 0.3 | +| clip_range | 0.2 | +| entropy_loss | -5.89 | +| explained_variance | -0.0302 | +| learning_rate | 1e-05 | +| loss | -0.0983 | +| n_updates | 6520 | +| policy_gradient_loss | -0.0663 | +| value_loss | 0.000129 | +---------------------------------------- +Early stopping at step 5 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.2 | +| time/ | | +| fps | 347 | +| iterations | 508 | +| time_elapsed | 11992 | +| total_timesteps | 4161536 | +| train/ | | +| approx_kl | 0.032749403 | +| clip_fraction | 0.256 | +| clip_range | 0.2 | +| entropy_loss | -5.94 | +| explained_variance | -0.107 | +| learning_rate | 1e-05 | +| loss | -0.0987 | +| n_updates | 6530 | +| policy_gradient_loss | -0.0553 | +| value_loss | 0.000164 | +----------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.81e+03 | +| ep_rew_mean | 0.191 | +| time/ | | +| fps | 347 | +| iterations | 509 | +| time_elapsed | 12013 | +| total_timesteps | 4169728 | +| train/ | | +| approx_kl | 0.03759933 | +| clip_fraction | 0.284 | +| clip_range | 0.2 | +| entropy_loss | -5.79 | +| explained_variance | -0.0323 | +| learning_rate | 1e-05 | +| loss | -0.107 | +| n_updates | 6540 | +| policy_gradient_loss | -0.0606 | +| value_loss | 0.000209 | +---------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.19 | +| time/ | | +| fps | 347 | +| iterations | 510 | +| time_elapsed | 12036 | +| total_timesteps | 4177920 | +| train/ | | +| approx_kl | 0.03770424 | +| clip_fraction | 0.306 | +| clip_range | 0.2 | +| entropy_loss | -5.93 | +| explained_variance | -0.0835 | +| learning_rate | 1e-05 | +| loss | -0.0985 | +| n_updates | 6550 | +| policy_gradient_loss | -0.0657 | +| value_loss | 0.000196 | +---------------------------------------- +Early stopping at step 8 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.82e+03 | +| ep_rew_mean | 0.187 | +| time/ | | +| fps | 347 | +| iterations | 511 | +| time_elapsed | 12061 | +| total_timesteps | 4186112 | +| train/ | | +| approx_kl | 0.037222084 | +| clip_fraction | 0.329 | +| clip_range | 0.2 | +| entropy_loss | -5.92 | +| explained_variance | -0.108 | +| learning_rate | 1e-05 | +| loss | -0.123 | +| n_updates | 6560 | +| policy_gradient_loss | -0.0677 | +| value_loss | 0.000131 | +----------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.8e+03 | +| ep_rew_mean | 0.187 | +| time/ | | +| fps | 347 | +| iterations | 512 | +| time_elapsed | 12084 | +| total_timesteps | 4194304 | +| train/ | | +| approx_kl | 0.035949048 | +| clip_fraction | 0.326 | +| clip_range | 0.2 | +| entropy_loss | -5.88 | +| explained_variance | -0.114 | +| learning_rate | 1e-05 | +| loss | -0.0917 | +| n_updates | 6570 | +| policy_gradient_loss | -0.0638 | +| value_loss | 0.000137 | +----------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.193 | +| time/ | | +| fps | 347 | +| iterations | 513 | +| time_elapsed | 12107 | +| total_timesteps | 4202496 | +| train/ | | +| approx_kl | 0.04737454 | +| clip_fraction | 0.268 | +| clip_range | 0.2 | +| entropy_loss | -5.94 | +| explained_variance | -0.145 | +| learning_rate | 1e-05 | +| loss | -0.11 | +| n_updates | 6580 | +| policy_gradient_loss | -0.0571 | +| value_loss | 0.000135 | +---------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.8e+03 | +| ep_rew_mean | 0.18 | +| time/ | | +| fps | 347 | +| iterations | 514 | +| time_elapsed | 12128 | +| total_timesteps | 4210688 | +| train/ | | +| approx_kl | 0.036024645 | +| clip_fraction | 0.286 | +| clip_range | 0.2 | +| entropy_loss | -5.86 | +| explained_variance | 0.00918 | +| learning_rate | 1e-05 | +| loss | -0.107 | +| n_updates | 6590 | +| policy_gradient_loss | -0.0615 | +| value_loss | 0.00019 | +----------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.182 | +| time/ | | +| fps | 347 | +| iterations | 515 | +| time_elapsed | 12150 | +| total_timesteps | 4218880 | +| train/ | | +| approx_kl | 0.0367581 | +| clip_fraction | 0.301 | +| clip_range | 0.2 | +| entropy_loss | -5.93 | +| explained_variance | -0.0655 | +| learning_rate | 1e-05 | +| loss | -0.103 | +| n_updates | 6600 | +| policy_gradient_loss | -0.0606 | +| value_loss | 0.000153 | +--------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.188 | +| time/ | | +| fps | 347 | +| iterations | 516 | +| time_elapsed | 12172 | +| total_timesteps | 4227072 | +| train/ | | +| approx_kl | 0.044120558 | +| clip_fraction | 0.293 | +| clip_range | 0.2 | +| entropy_loss | -5.91 | +| explained_variance | -0.0485 | +| learning_rate | 1e-05 | +| loss | -0.0877 | +| n_updates | 6610 | +| policy_gradient_loss | -0.0608 | +| value_loss | 0.000149 | +----------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.183 | +| time/ | | +| fps | 347 | +| iterations | 517 | +| time_elapsed | 12193 | +| total_timesteps | 4235264 | +| train/ | | +| approx_kl | 0.036905624 | +| clip_fraction | 0.287 | +| clip_range | 0.2 | +| entropy_loss | -5.82 | +| explained_variance | -0.0524 | +| learning_rate | 1e-05 | +| loss | -0.0763 | +| n_updates | 6620 | +| policy_gradient_loss | -0.0577 | +| value_loss | 0.000255 | +----------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.81e+03 | +| ep_rew_mean | 0.188 | +| time/ | | +| fps | 347 | +| iterations | 518 | +| time_elapsed | 12216 | +| total_timesteps | 4243456 | +| train/ | | +| approx_kl | 0.03816925 | +| clip_fraction | 0.288 | +| clip_range | 0.2 | +| entropy_loss | -5.94 | +| explained_variance | -0.0841 | +| learning_rate | 1e-05 | +| loss | -0.0965 | +| n_updates | 6630 | +| policy_gradient_loss | -0.0627 | +| value_loss | 0.000159 | +---------------------------------------- +Early stopping at step 8 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.81e+03 | +| ep_rew_mean | 0.179 | +| time/ | | +| fps | 347 | +| iterations | 519 | +| time_elapsed | 12239 | +| total_timesteps | 4251648 | +| train/ | | +| approx_kl | 0.03664714 | +| clip_fraction | 0.32 | +| clip_range | 0.2 | +| entropy_loss | -5.95 | +| explained_variance | -0.00869 | +| learning_rate | 1e-05 | +| loss | -0.0866 | +| n_updates | 6640 | +| policy_gradient_loss | -0.0565 | +| value_loss | 0.000287 | +---------------------------------------- +Early stopping at step 4 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.78e+03 | +| ep_rew_mean | 0.187 | +| time/ | | +| fps | 347 | +| iterations | 520 | +| time_elapsed | 12257 | +| total_timesteps | 4259840 | +| train/ | | +| approx_kl | 0.03125521 | +| clip_fraction | 0.226 | +| clip_range | 0.2 | +| entropy_loss | -5.86 | +| explained_variance | -0.225 | +| learning_rate | 1e-05 | +| loss | -0.0788 | +| n_updates | 6650 | +| policy_gradient_loss | -0.0531 | +| value_loss | 0.000185 | +---------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.8e+03 | +| ep_rew_mean | 0.196 | +| time/ | | +| fps | 347 | +| iterations | 521 | +| time_elapsed | 12279 | +| total_timesteps | 4268032 | +| train/ | | +| approx_kl | 0.039127897 | +| clip_fraction | 0.265 | +| clip_range | 0.2 | +| entropy_loss | -5.94 | +| explained_variance | -0.0501 | +| learning_rate | 1e-05 | +| loss | -0.0913 | +| n_updates | 6660 | +| policy_gradient_loss | -0.0587 | +| value_loss | 0.000239 | +----------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.8e+03 | +| ep_rew_mean | 0.2 | +| time/ | | +| fps | 347 | +| iterations | 522 | +| time_elapsed | 12301 | +| total_timesteps | 4276224 | +| train/ | | +| approx_kl | 0.039454877 | +| clip_fraction | 0.322 | +| clip_range | 0.2 | +| entropy_loss | -5.77 | +| explained_variance | -0.011 | +| learning_rate | 1e-05 | +| loss | -0.0981 | +| n_updates | 6670 | +| policy_gradient_loss | -0.0689 | +| value_loss | 0.000185 | +----------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.82e+03 | +| ep_rew_mean | 0.194 | +| time/ | | +| fps | 347 | +| iterations | 523 | +| time_elapsed | 12322 | +| total_timesteps | 4284416 | +| train/ | | +| approx_kl | 0.034197606 | +| clip_fraction | 0.281 | +| clip_range | 0.2 | +| entropy_loss | -5.96 | +| explained_variance | -0.157 | +| learning_rate | 1e-05 | +| loss | -0.105 | +| n_updates | 6680 | +| policy_gradient_loss | -0.0619 | +| value_loss | 0.000152 | +----------------------------------------- +Early stopping at step 5 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.82e+03 | +| ep_rew_mean | 0.207 | +| time/ | | +| fps | 347 | +| iterations | 524 | +| time_elapsed | 12343 | +| total_timesteps | 4292608 | +| train/ | | +| approx_kl | 0.031831644 | +| clip_fraction | 0.28 | +| clip_range | 0.2 | +| entropy_loss | -5.83 | +| explained_variance | 0.0247 | +| learning_rate | 1e-05 | +| loss | -0.0941 | +| n_updates | 6690 | +| policy_gradient_loss | -0.0576 | +| value_loss | 0.000151 | +----------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.82e+03 | +| ep_rew_mean | 0.196 | +| time/ | | +| fps | 347 | +| iterations | 525 | +| time_elapsed | 12365 | +| total_timesteps | 4300800 | +| train/ | | +| approx_kl | 0.035696488 | +| clip_fraction | 0.303 | +| clip_range | 0.2 | +| entropy_loss | -5.79 | +| explained_variance | 0.044 | +| learning_rate | 1e-05 | +| loss | -0.1 | +| n_updates | 6700 | +| policy_gradient_loss | -0.0648 | +| value_loss | 0.00019 | +----------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.193 | +| time/ | | +| fps | 347 | +| iterations | 526 | +| time_elapsed | 12387 | +| total_timesteps | 4308992 | +| train/ | | +| approx_kl | 0.03594896 | +| clip_fraction | 0.305 | +| clip_range | 0.2 | +| entropy_loss | -5.92 | +| explained_variance | -0.0759 | +| learning_rate | 1e-05 | +| loss | -0.0736 | +| n_updates | 6710 | +| policy_gradient_loss | -0.0631 | +| value_loss | 0.000128 | +---------------------------------------- +Early stopping at step 5 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.82e+03 | +| ep_rew_mean | 0.201 | +| time/ | | +| fps | 347 | +| iterations | 527 | +| time_elapsed | 12408 | +| total_timesteps | 4317184 | +| train/ | | +| approx_kl | 0.03438462 | +| clip_fraction | 0.252 | +| clip_range | 0.2 | +| entropy_loss | -5.95 | +| explained_variance | -0.106 | +| learning_rate | 1e-05 | +| loss | -0.0946 | +| n_updates | 6720 | +| policy_gradient_loss | -0.0545 | +| value_loss | 0.000139 | +---------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.81e+03 | +| ep_rew_mean | 0.198 | +| time/ | | +| fps | 347 | +| iterations | 528 | +| time_elapsed | 12429 | +| total_timesteps | 4325376 | +| train/ | | +| approx_kl | 0.03831674 | +| clip_fraction | 0.279 | +| clip_range | 0.2 | +| entropy_loss | -5.72 | +| explained_variance | -0.0637 | +| learning_rate | 1e-05 | +| loss | -0.107 | +| n_updates | 6730 | +| policy_gradient_loss | -0.0571 | +| value_loss | 0.000227 | +---------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.202 | +| time/ | | +| fps | 347 | +| iterations | 529 | +| time_elapsed | 12453 | +| total_timesteps | 4333568 | +| train/ | | +| approx_kl | 0.036123652 | +| clip_fraction | 0.301 | +| clip_range | 0.2 | +| entropy_loss | -5.88 | +| explained_variance | -0.0922 | +| learning_rate | 1e-05 | +| loss | -0.106 | +| n_updates | 6740 | +| policy_gradient_loss | -0.0655 | +| value_loss | 0.000168 | +----------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.212 | +| time/ | | +| fps | 348 | +| iterations | 530 | +| time_elapsed | 12476 | +| total_timesteps | 4341760 | +| train/ | | +| approx_kl | 0.046745013 | +| clip_fraction | 0.305 | +| clip_range | 0.2 | +| entropy_loss | -5.99 | +| explained_variance | -0.0783 | +| learning_rate | 1e-05 | +| loss | -0.0977 | +| n_updates | 6750 | +| policy_gradient_loss | -0.0628 | +| value_loss | 0.000144 | +----------------------------------------- +Early stopping at step 4 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.218 | +| time/ | | +| fps | 348 | +| iterations | 531 | +| time_elapsed | 12494 | +| total_timesteps | 4349952 | +| train/ | | +| approx_kl | 0.031984188 | +| clip_fraction | 0.207 | +| clip_range | 0.2 | +| entropy_loss | -5.89 | +| explained_variance | -0.049 | +| learning_rate | 1e-05 | +| loss | -0.0715 | +| n_updates | 6760 | +| policy_gradient_loss | -0.0445 | +| value_loss | 0.000231 | +----------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.221 | +| time/ | | +| fps | 348 | +| iterations | 532 | +| time_elapsed | 12518 | +| total_timesteps | 4358144 | +| train/ | | +| approx_kl | 0.037799172 | +| clip_fraction | 0.311 | +| clip_range | 0.2 | +| entropy_loss | -5.89 | +| explained_variance | -0.13 | +| learning_rate | 1e-05 | +| loss | -0.105 | +| n_updates | 6770 | +| policy_gradient_loss | -0.0638 | +| value_loss | 0.00019 | +----------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.217 | +| time/ | | +| fps | 348 | +| iterations | 533 | +| time_elapsed | 12539 | +| total_timesteps | 4366336 | +| train/ | | +| approx_kl | 0.035690174 | +| clip_fraction | 0.287 | +| clip_range | 0.2 | +| entropy_loss | -5.85 | +| explained_variance | -0.00866 | +| learning_rate | 1e-05 | +| loss | -0.0909 | +| n_updates | 6780 | +| policy_gradient_loss | -0.0557 | +| value_loss | 0.000193 | +----------------------------------------- +Early stopping at step 8 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.228 | +| time/ | | +| fps | 348 | +| iterations | 534 | +| time_elapsed | 12562 | +| total_timesteps | 4374528 | +| train/ | | +| approx_kl | 0.038933408 | +| clip_fraction | 0.336 | +| clip_range | 0.2 | +| entropy_loss | -5.97 | +| explained_variance | 0.019 | +| learning_rate | 1e-05 | +| loss | -0.0936 | +| n_updates | 6790 | +| policy_gradient_loss | -0.066 | +| value_loss | 0.000185 | +----------------------------------------- +Early stopping at step 5 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.82e+03 | +| ep_rew_mean | 0.227 | +| time/ | | +| fps | 348 | +| iterations | 535 | +| time_elapsed | 12583 | +| total_timesteps | 4382720 | +| train/ | | +| approx_kl | 0.03391295 | +| clip_fraction | 0.264 | +| clip_range | 0.2 | +| entropy_loss | -5.96 | +| explained_variance | -0.112 | +| learning_rate | 1e-05 | +| loss | -0.105 | +| n_updates | 6800 | +| policy_gradient_loss | -0.0585 | +| value_loss | 0.000236 | +---------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.8e+03 | +| ep_rew_mean | 0.222 | +| time/ | | +| fps | 348 | +| iterations | 536 | +| time_elapsed | 12604 | +| total_timesteps | 4390912 | +| train/ | | +| approx_kl | 0.03422355 | +| clip_fraction | 0.293 | +| clip_range | 0.2 | +| entropy_loss | -5.99 | +| explained_variance | -0.107 | +| learning_rate | 1e-05 | +| loss | -0.0859 | +| n_updates | 6810 | +| policy_gradient_loss | -0.0621 | +| value_loss | 0.00022 | +---------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.8e+03 | +| ep_rew_mean | 0.222 | +| time/ | | +| fps | 348 | +| iterations | 537 | +| time_elapsed | 12625 | +| total_timesteps | 4399104 | +| train/ | | +| approx_kl | 0.03712635 | +| clip_fraction | 0.277 | +| clip_range | 0.2 | +| entropy_loss | -5.9 | +| explained_variance | 0.0499 | +| learning_rate | 1e-05 | +| loss | -0.11 | +| n_updates | 6820 | +| policy_gradient_loss | -0.0622 | +| value_loss | 0.000193 | +---------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.81e+03 | +| ep_rew_mean | 0.216 | +| time/ | | +| fps | 348 | +| iterations | 538 | +| time_elapsed | 12648 | +| total_timesteps | 4407296 | +| train/ | | +| approx_kl | 0.03720688 | +| clip_fraction | 0.272 | +| clip_range | 0.2 | +| entropy_loss | -5.85 | +| explained_variance | 0.0414 | +| learning_rate | 1e-05 | +| loss | -0.102 | +| n_updates | 6830 | +| policy_gradient_loss | -0.0565 | +| value_loss | 0.000191 | +---------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.221 | +| time/ | | +| fps | 348 | +| iterations | 539 | +| time_elapsed | 12670 | +| total_timesteps | 4415488 | +| train/ | | +| approx_kl | 0.037637595 | +| clip_fraction | 0.306 | +| clip_range | 0.2 | +| entropy_loss | -6.02 | +| explained_variance | -0.0209 | +| learning_rate | 1e-05 | +| loss | -0.101 | +| n_updates | 6840 | +| policy_gradient_loss | -0.0611 | +| value_loss | 0.000209 | +----------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.78e+03 | +| ep_rew_mean | 0.225 | +| time/ | | +| fps | 348 | +| iterations | 540 | +| time_elapsed | 12693 | +| total_timesteps | 4423680 | +| train/ | | +| approx_kl | 0.039644845 | +| clip_fraction | 0.32 | +| clip_range | 0.2 | +| entropy_loss | -5.89 | +| explained_variance | -0.0939 | +| learning_rate | 1e-05 | +| loss | -0.125 | +| n_updates | 6850 | +| policy_gradient_loss | -0.0646 | +| value_loss | 0.000145 | +----------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.229 | +| time/ | | +| fps | 348 | +| iterations | 541 | +| time_elapsed | 12714 | +| total_timesteps | 4431872 | +| train/ | | +| approx_kl | 0.034694314 | +| clip_fraction | 0.263 | +| clip_range | 0.2 | +| entropy_loss | -5.97 | +| explained_variance | -0.0277 | +| learning_rate | 1e-05 | +| loss | -0.0965 | +| n_updates | 6860 | +| policy_gradient_loss | -0.0567 | +| value_loss | 0.000256 | +----------------------------------------- +Early stopping at step 4 due to reaching max kl: 0.05 +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.82e+03 | +| ep_rew_mean | 0.234 | +| time/ | | +| fps | 348 | +| iterations | 542 | +| time_elapsed | 12733 | +| total_timesteps | 4440064 | +| train/ | | +| approx_kl | 0.0302 | +| clip_fraction | 0.216 | +| clip_range | 0.2 | +| entropy_loss | -5.77 | +| explained_variance | -0.0991 | +| learning_rate | 1e-05 | +| loss | -0.0974 | +| n_updates | 6870 | +| policy_gradient_loss | -0.0505 | +| value_loss | 0.00018 | +-------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.81e+03 | +| ep_rew_mean | 0.229 | +| time/ | | +| fps | 348 | +| iterations | 543 | +| time_elapsed | 12756 | +| total_timesteps | 4448256 | +| train/ | | +| approx_kl | 0.04318103 | +| clip_fraction | 0.279 | +| clip_range | 0.2 | +| entropy_loss | -5.86 | +| explained_variance | -0.0738 | +| learning_rate | 1e-05 | +| loss | -0.0967 | +| n_updates | 6880 | +| policy_gradient_loss | -0.0578 | +| value_loss | 0.000193 | +---------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.224 | +| time/ | | +| fps | 348 | +| iterations | 544 | +| time_elapsed | 12779 | +| total_timesteps | 4456448 | +| train/ | | +| approx_kl | 0.035154495 | +| clip_fraction | 0.293 | +| clip_range | 0.2 | +| entropy_loss | -5.9 | +| explained_variance | -0.0792 | +| learning_rate | 1e-05 | +| loss | -0.108 | +| n_updates | 6890 | +| policy_gradient_loss | -0.0609 | +| value_loss | 0.000144 | +----------------------------------------- +Early stopping at step 4 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.224 | +| time/ | | +| fps | 348 | +| iterations | 545 | +| time_elapsed | 12798 | +| total_timesteps | 4464640 | +| train/ | | +| approx_kl | 0.029628424 | +| clip_fraction | 0.24 | +| clip_range | 0.2 | +| entropy_loss | -5.98 | +| explained_variance | -0.0404 | +| learning_rate | 1e-05 | +| loss | -0.0943 | +| n_updates | 6900 | +| policy_gradient_loss | -0.0541 | +| value_loss | 0.000204 | +----------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.215 | +| time/ | | +| fps | 348 | +| iterations | 546 | +| time_elapsed | 12821 | +| total_timesteps | 4472832 | +| train/ | | +| approx_kl | 0.03529534 | +| clip_fraction | 0.276 | +| clip_range | 0.2 | +| entropy_loss | -5.86 | +| explained_variance | 0.0256 | +| learning_rate | 1e-05 | +| loss | -0.0783 | +| n_updates | 6910 | +| policy_gradient_loss | -0.0594 | +| value_loss | 0.000154 | +---------------------------------------- +Early stopping at step 4 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.213 | +| time/ | | +| fps | 348 | +| iterations | 547 | +| time_elapsed | 12841 | +| total_timesteps | 4481024 | +| train/ | | +| approx_kl | 0.02724374 | +| clip_fraction | 0.206 | +| clip_range | 0.2 | +| entropy_loss | -6.05 | +| explained_variance | -0.0675 | +| learning_rate | 1e-05 | +| loss | -0.0726 | +| n_updates | 6920 | +| policy_gradient_loss | -0.0445 | +| value_loss | 0.000184 | +---------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.201 | +| time/ | | +| fps | 349 | +| iterations | 548 | +| time_elapsed | 12862 | +| total_timesteps | 4489216 | +| train/ | | +| approx_kl | 0.034250397 | +| clip_fraction | 0.296 | +| clip_range | 0.2 | +| entropy_loss | -5.89 | +| explained_variance | 0.0394 | +| learning_rate | 1e-05 | +| loss | -0.0847 | +| n_updates | 6930 | +| policy_gradient_loss | -0.0606 | +| value_loss | 0.000153 | +----------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.206 | +| time/ | | +| fps | 349 | +| iterations | 549 | +| time_elapsed | 12886 | +| total_timesteps | 4497408 | +| train/ | | +| approx_kl | 0.03836695 | +| clip_fraction | 0.3 | +| clip_range | 0.2 | +| entropy_loss | -6.01 | +| explained_variance | -0.0607 | +| learning_rate | 1e-05 | +| loss | -0.103 | +| n_updates | 6940 | +| policy_gradient_loss | -0.0627 | +| value_loss | 0.000158 | +---------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.215 | +| time/ | | +| fps | 349 | +| iterations | 550 | +| time_elapsed | 12908 | +| total_timesteps | 4505600 | +| train/ | | +| approx_kl | 0.03405632 | +| clip_fraction | 0.303 | +| clip_range | 0.2 | +| entropy_loss | -6.03 | +| explained_variance | -0.094 | +| learning_rate | 1e-05 | +| loss | -0.112 | +| n_updates | 6950 | +| policy_gradient_loss | -0.0594 | +| value_loss | 0.000223 | +---------------------------------------- +Early stopping at step 4 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.206 | +| time/ | | +| fps | 349 | +| iterations | 551 | +| time_elapsed | 12926 | +| total_timesteps | 4513792 | +| train/ | | +| approx_kl | 0.028957853 | +| clip_fraction | 0.207 | +| clip_range | 0.2 | +| entropy_loss | -5.93 | +| explained_variance | -0.0257 | +| learning_rate | 1e-05 | +| loss | -0.08 | +| n_updates | 6960 | +| policy_gradient_loss | -0.0485 | +| value_loss | 0.000233 | +----------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.2 | +| time/ | | +| fps | 349 | +| iterations | 552 | +| time_elapsed | 12947 | +| total_timesteps | 4521984 | +| train/ | | +| approx_kl | 0.03619219 | +| clip_fraction | 0.289 | +| clip_range | 0.2 | +| entropy_loss | -5.87 | +| explained_variance | -0.106 | +| learning_rate | 1e-05 | +| loss | -0.109 | +| n_updates | 6970 | +| policy_gradient_loss | -0.064 | +| value_loss | 0.000162 | +---------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.194 | +| time/ | | +| fps | 349 | +| iterations | 553 | +| time_elapsed | 12968 | +| total_timesteps | 4530176 | +| train/ | | +| approx_kl | 0.036546268 | +| clip_fraction | 0.303 | +| clip_range | 0.2 | +| entropy_loss | -5.82 | +| explained_variance | -0.00165 | +| learning_rate | 1e-05 | +| loss | -0.0891 | +| n_updates | 6980 | +| policy_gradient_loss | -0.0631 | +| value_loss | 0.000161 | +----------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.201 | +| time/ | | +| fps | 349 | +| iterations | 554 | +| time_elapsed | 12991 | +| total_timesteps | 4538368 | +| train/ | | +| approx_kl | 0.038536105 | +| clip_fraction | 0.303 | +| clip_range | 0.2 | +| entropy_loss | -5.94 | +| explained_variance | -0.0724 | +| learning_rate | 1e-05 | +| loss | -0.0916 | +| n_updates | 6990 | +| policy_gradient_loss | -0.0594 | +| value_loss | 0.000164 | +----------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.192 | +| time/ | | +| fps | 349 | +| iterations | 555 | +| time_elapsed | 13013 | +| total_timesteps | 4546560 | +| train/ | | +| approx_kl | 0.037542112 | +| clip_fraction | 0.307 | +| clip_range | 0.2 | +| entropy_loss | -5.84 | +| explained_variance | -0.123 | +| learning_rate | 1e-05 | +| loss | -0.1 | +| n_updates | 7000 | +| policy_gradient_loss | -0.0629 | +| value_loss | 0.000201 | +----------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.192 | +| time/ | | +| fps | 349 | +| iterations | 556 | +| time_elapsed | 13033 | +| total_timesteps | 4554752 | +| train/ | | +| approx_kl | 0.033887487 | +| clip_fraction | 0.292 | +| clip_range | 0.2 | +| entropy_loss | -5.75 | +| explained_variance | -0.115 | +| learning_rate | 1e-05 | +| loss | -0.086 | +| n_updates | 7010 | +| policy_gradient_loss | -0.06 | +| value_loss | 0.000172 | +----------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.195 | +| time/ | | +| fps | 349 | +| iterations | 557 | +| time_elapsed | 13055 | +| total_timesteps | 4562944 | +| train/ | | +| approx_kl | 0.041763347 | +| clip_fraction | 0.31 | +| clip_range | 0.2 | +| entropy_loss | -6.05 | +| explained_variance | -0.0555 | +| learning_rate | 1e-05 | +| loss | -0.102 | +| n_updates | 7020 | +| policy_gradient_loss | -0.065 | +| value_loss | 0.000169 | +----------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.78e+03 | +| ep_rew_mean | 0.193 | +| time/ | | +| fps | 349 | +| iterations | 558 | +| time_elapsed | 13076 | +| total_timesteps | 4571136 | +| train/ | | +| approx_kl | 0.035343334 | +| clip_fraction | 0.27 | +| clip_range | 0.2 | +| entropy_loss | -5.95 | +| explained_variance | -0.136 | +| learning_rate | 1e-05 | +| loss | -0.0917 | +| n_updates | 7030 | +| policy_gradient_loss | -0.0572 | +| value_loss | 0.000156 | +----------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.78e+03 | +| ep_rew_mean | 0.185 | +| time/ | | +| fps | 349 | +| iterations | 559 | +| time_elapsed | 13096 | +| total_timesteps | 4579328 | +| train/ | | +| approx_kl | 0.042336814 | +| clip_fraction | 0.293 | +| clip_range | 0.2 | +| entropy_loss | -5.86 | +| explained_variance | -0.0956 | +| learning_rate | 1e-05 | +| loss | -0.109 | +| n_updates | 7040 | +| policy_gradient_loss | -0.0598 | +| value_loss | 0.000141 | +----------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.186 | +| time/ | | +| fps | 349 | +| iterations | 560 | +| time_elapsed | 13119 | +| total_timesteps | 4587520 | +| train/ | | +| approx_kl | 0.040626638 | +| clip_fraction | 0.256 | +| clip_range | 0.2 | +| entropy_loss | -5.96 | +| explained_variance | 0.0156 | +| learning_rate | 1e-05 | +| loss | -0.0865 | +| n_updates | 7050 | +| policy_gradient_loss | -0.0563 | +| value_loss | 0.000152 | +----------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.185 | +| time/ | | +| fps | 349 | +| iterations | 561 | +| time_elapsed | 13140 | +| total_timesteps | 4595712 | +| train/ | | +| approx_kl | 0.036438067 | +| clip_fraction | 0.299 | +| clip_range | 0.2 | +| entropy_loss | -5.95 | +| explained_variance | -0.162 | +| learning_rate | 1e-05 | +| loss | -0.102 | +| n_updates | 7060 | +| policy_gradient_loss | -0.063 | +| value_loss | 0.000136 | +----------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.8e+03 | +| ep_rew_mean | 0.18 | +| time/ | | +| fps | 349 | +| iterations | 562 | +| time_elapsed | 13162 | +| total_timesteps | 4603904 | +| train/ | | +| approx_kl | 0.03478945 | +| clip_fraction | 0.298 | +| clip_range | 0.2 | +| entropy_loss | -5.79 | +| explained_variance | -0.103 | +| learning_rate | 1e-05 | +| loss | -0.103 | +| n_updates | 7070 | +| policy_gradient_loss | -0.0639 | +| value_loss | 0.000143 | +---------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.81e+03 | +| ep_rew_mean | 0.183 | +| time/ | | +| fps | 349 | +| iterations | 563 | +| time_elapsed | 13186 | +| total_timesteps | 4612096 | +| train/ | | +| approx_kl | 0.040729005 | +| clip_fraction | 0.314 | +| clip_range | 0.2 | +| entropy_loss | -6.05 | +| explained_variance | -0.0632 | +| learning_rate | 1e-05 | +| loss | -0.112 | +| n_updates | 7080 | +| policy_gradient_loss | -0.0652 | +| value_loss | 0.000165 | +----------------------------------------- +Early stopping at step 4 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.82e+03 | +| ep_rew_mean | 0.188 | +| time/ | | +| fps | 349 | +| iterations | 564 | +| time_elapsed | 13206 | +| total_timesteps | 4620288 | +| train/ | | +| approx_kl | 0.027750289 | +| clip_fraction | 0.229 | +| clip_range | 0.2 | +| entropy_loss | -5.85 | +| explained_variance | -0.099 | +| learning_rate | 1e-05 | +| loss | -0.0812 | +| n_updates | 7090 | +| policy_gradient_loss | -0.0475 | +| value_loss | 0.00022 | +----------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.82e+03 | +| ep_rew_mean | 0.182 | +| time/ | | +| fps | 349 | +| iterations | 565 | +| time_elapsed | 13227 | +| total_timesteps | 4628480 | +| train/ | | +| approx_kl | 0.03435795 | +| clip_fraction | 0.276 | +| clip_range | 0.2 | +| entropy_loss | -5.83 | +| explained_variance | 0.0291 | +| learning_rate | 1e-05 | +| loss | -0.108 | +| n_updates | 7100 | +| policy_gradient_loss | -0.0581 | +| value_loss | 0.000145 | +---------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.194 | +| time/ | | +| fps | 349 | +| iterations | 566 | +| time_elapsed | 13249 | +| total_timesteps | 4636672 | +| train/ | | +| approx_kl | 0.035992865 | +| clip_fraction | 0.285 | +| clip_range | 0.2 | +| entropy_loss | -6.01 | +| explained_variance | -0.1 | +| learning_rate | 1e-05 | +| loss | -0.0897 | +| n_updates | 7110 | +| policy_gradient_loss | -0.0621 | +| value_loss | 0.000161 | +----------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.193 | +| time/ | | +| fps | 350 | +| iterations | 567 | +| time_elapsed | 13270 | +| total_timesteps | 4644864 | +| train/ | | +| approx_kl | 0.036568623 | +| clip_fraction | 0.292 | +| clip_range | 0.2 | +| entropy_loss | -5.96 | +| explained_variance | -0.0605 | +| learning_rate | 1e-05 | +| loss | -0.0922 | +| n_updates | 7120 | +| policy_gradient_loss | -0.06 | +| value_loss | 0.000218 | +----------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.207 | +| time/ | | +| fps | 350 | +| iterations | 568 | +| time_elapsed | 13292 | +| total_timesteps | 4653056 | +| train/ | | +| approx_kl | 0.041547596 | +| clip_fraction | 0.283 | +| clip_range | 0.2 | +| entropy_loss | -5.9 | +| explained_variance | -0.0928 | +| learning_rate | 1e-05 | +| loss | -0.113 | +| n_updates | 7130 | +| policy_gradient_loss | -0.0582 | +| value_loss | 0.000143 | +----------------------------------------- +Early stopping at step 5 due to reaching max kl: 0.05 +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.206 | +| time/ | | +| fps | 350 | +| iterations | 569 | +| time_elapsed | 13312 | +| total_timesteps | 4661248 | +| train/ | | +| approx_kl | 0.0323131 | +| clip_fraction | 0.266 | +| clip_range | 0.2 | +| entropy_loss | -5.96 | +| explained_variance | -0.0233 | +| learning_rate | 1e-05 | +| loss | -0.0789 | +| n_updates | 7140 | +| policy_gradient_loss | -0.0557 | +| value_loss | 0.000233 | +--------------------------------------- +Early stopping at step 4 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.215 | +| time/ | | +| fps | 350 | +| iterations | 570 | +| time_elapsed | 13331 | +| total_timesteps | 4669440 | +| train/ | | +| approx_kl | 0.028266534 | +| clip_fraction | 0.216 | +| clip_range | 0.2 | +| entropy_loss | -5.72 | +| explained_variance | -0.0601 | +| learning_rate | 1e-05 | +| loss | -0.0906 | +| n_updates | 7150 | +| policy_gradient_loss | -0.0459 | +| value_loss | 0.000172 | +----------------------------------------- +Early stopping at step 8 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.218 | +| time/ | | +| fps | 350 | +| iterations | 571 | +| time_elapsed | 13355 | +| total_timesteps | 4677632 | +| train/ | | +| approx_kl | 0.03735585 | +| clip_fraction | 0.329 | +| clip_range | 0.2 | +| entropy_loss | -5.87 | +| explained_variance | 0.0505 | +| learning_rate | 1e-05 | +| loss | -0.11 | +| n_updates | 7160 | +| policy_gradient_loss | -0.0652 | +| value_loss | 0.000181 | +---------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.208 | +| time/ | | +| fps | 350 | +| iterations | 572 | +| time_elapsed | 13378 | +| total_timesteps | 4685824 | +| train/ | | +| approx_kl | 0.037394196 | +| clip_fraction | 0.336 | +| clip_range | 0.2 | +| entropy_loss | -5.77 | +| explained_variance | -0.0612 | +| learning_rate | 1e-05 | +| loss | -0.108 | +| n_updates | 7170 | +| policy_gradient_loss | -0.0694 | +| value_loss | 0.000156 | +----------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.215 | +| time/ | | +| fps | 350 | +| iterations | 573 | +| time_elapsed | 13399 | +| total_timesteps | 4694016 | +| train/ | | +| approx_kl | 0.03548644 | +| clip_fraction | 0.304 | +| clip_range | 0.2 | +| entropy_loss | -5.94 | +| explained_variance | -0.0564 | +| learning_rate | 1e-05 | +| loss | -0.0971 | +| n_updates | 7180 | +| policy_gradient_loss | -0.0629 | +| value_loss | 0.000159 | +---------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.22 | +| time/ | | +| fps | 350 | +| iterations | 574 | +| time_elapsed | 13421 | +| total_timesteps | 4702208 | +| train/ | | +| approx_kl | 0.035852958 | +| clip_fraction | 0.31 | +| clip_range | 0.2 | +| entropy_loss | -5.95 | +| explained_variance | 0.00475 | +| learning_rate | 1e-05 | +| loss | -0.098 | +| n_updates | 7190 | +| policy_gradient_loss | -0.0661 | +| value_loss | 0.000202 | +----------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.219 | +| time/ | | +| fps | 350 | +| iterations | 575 | +| time_elapsed | 13442 | +| total_timesteps | 4710400 | +| train/ | | +| approx_kl | 0.040056467 | +| clip_fraction | 0.297 | +| clip_range | 0.2 | +| entropy_loss | -5.78 | +| explained_variance | -0.142 | +| learning_rate | 1e-05 | +| loss | -0.106 | +| n_updates | 7200 | +| policy_gradient_loss | -0.0621 | +| value_loss | 0.000151 | +----------------------------------------- +Early stopping at step 5 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.214 | +| time/ | | +| fps | 350 | +| iterations | 576 | +| time_elapsed | 13462 | +| total_timesteps | 4718592 | +| train/ | | +| approx_kl | 0.031606555 | +| clip_fraction | 0.239 | +| clip_range | 0.2 | +| entropy_loss | -5.84 | +| explained_variance | -0.0585 | +| learning_rate | 1e-05 | +| loss | -0.0823 | +| n_updates | 7210 | +| policy_gradient_loss | -0.0529 | +| value_loss | 0.000173 | +----------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.82e+03 | +| ep_rew_mean | 0.212 | +| time/ | | +| fps | 350 | +| iterations | 577 | +| time_elapsed | 13486 | +| total_timesteps | 4726784 | +| train/ | | +| approx_kl | 0.03855902 | +| clip_fraction | 0.321 | +| clip_range | 0.2 | +| entropy_loss | -5.79 | +| explained_variance | -0.021 | +| learning_rate | 1e-05 | +| loss | -0.0997 | +| n_updates | 7220 | +| policy_gradient_loss | -0.0651 | +| value_loss | 0.000178 | +---------------------------------------- +Early stopping at step 5 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.8e+03 | +| ep_rew_mean | 0.205 | +| time/ | | +| fps | 350 | +| iterations | 578 | +| time_elapsed | 13507 | +| total_timesteps | 4734976 | +| train/ | | +| approx_kl | 0.030262763 | +| clip_fraction | 0.262 | +| clip_range | 0.2 | +| entropy_loss | -5.93 | +| explained_variance | -0.0511 | +| learning_rate | 1e-05 | +| loss | -0.111 | +| n_updates | 7230 | +| policy_gradient_loss | -0.0586 | +| value_loss | 0.000155 | +----------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.82e+03 | +| ep_rew_mean | 0.22 | +| time/ | | +| fps | 350 | +| iterations | 579 | +| time_elapsed | 13530 | +| total_timesteps | 4743168 | +| train/ | | +| approx_kl | 0.03511805 | +| clip_fraction | 0.319 | +| clip_range | 0.2 | +| entropy_loss | -5.86 | +| explained_variance | -0.00638 | +| learning_rate | 1e-05 | +| loss | -0.0884 | +| n_updates | 7240 | +| policy_gradient_loss | -0.0615 | +| value_loss | 0.000159 | +---------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.78e+03 | +| ep_rew_mean | 0.213 | +| time/ | | +| fps | 350 | +| iterations | 580 | +| time_elapsed | 13552 | +| total_timesteps | 4751360 | +| train/ | | +| approx_kl | 0.035261262 | +| clip_fraction | 0.27 | +| clip_range | 0.2 | +| entropy_loss | -5.78 | +| explained_variance | -0.00105 | +| learning_rate | 1e-05 | +| loss | -0.108 | +| n_updates | 7250 | +| policy_gradient_loss | -0.0587 | +| value_loss | 0.000221 | +----------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.224 | +| time/ | | +| fps | 350 | +| iterations | 581 | +| time_elapsed | 13573 | +| total_timesteps | 4759552 | +| train/ | | +| approx_kl | 0.037027594 | +| clip_fraction | 0.29 | +| clip_range | 0.2 | +| entropy_loss | -5.82 | +| explained_variance | -0.0224 | +| learning_rate | 1e-05 | +| loss | -0.103 | +| n_updates | 7260 | +| policy_gradient_loss | -0.0658 | +| value_loss | 0.000157 | +----------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.78e+03 | +| ep_rew_mean | 0.225 | +| time/ | | +| fps | 350 | +| iterations | 582 | +| time_elapsed | 13596 | +| total_timesteps | 4767744 | +| train/ | | +| approx_kl | 0.033465285 | +| clip_fraction | 0.282 | +| clip_range | 0.2 | +| entropy_loss | -5.84 | +| explained_variance | -0.0416 | +| learning_rate | 1e-05 | +| loss | -0.102 | +| n_updates | 7270 | +| policy_gradient_loss | -0.0609 | +| value_loss | 0.000167 | +----------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.222 | +| time/ | | +| fps | 350 | +| iterations | 583 | +| time_elapsed | 13619 | +| total_timesteps | 4775936 | +| train/ | | +| approx_kl | 0.038969554 | +| clip_fraction | 0.294 | +| clip_range | 0.2 | +| entropy_loss | -5.84 | +| explained_variance | -0.0735 | +| learning_rate | 1e-05 | +| loss | -0.108 | +| n_updates | 7280 | +| policy_gradient_loss | -0.0612 | +| value_loss | 0.000197 | +----------------------------------------- +Early stopping at step 5 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.231 | +| time/ | | +| fps | 350 | +| iterations | 584 | +| time_elapsed | 13639 | +| total_timesteps | 4784128 | +| train/ | | +| approx_kl | 0.032491706 | +| clip_fraction | 0.26 | +| clip_range | 0.2 | +| entropy_loss | -5.86 | +| explained_variance | -0.108 | +| learning_rate | 1e-05 | +| loss | -0.0942 | +| n_updates | 7290 | +| policy_gradient_loss | -0.0543 | +| value_loss | 0.000226 | +----------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.208 | +| time/ | | +| fps | 350 | +| iterations | 585 | +| time_elapsed | 13660 | +| total_timesteps | 4792320 | +| train/ | | +| approx_kl | 0.03476615 | +| clip_fraction | 0.298 | +| clip_range | 0.2 | +| entropy_loss | -5.7 | +| explained_variance | -0.0968 | +| learning_rate | 1e-05 | +| loss | -0.11 | +| n_updates | 7300 | +| policy_gradient_loss | -0.062 | +| value_loss | 0.000184 | +---------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.208 | +| time/ | | +| fps | 350 | +| iterations | 586 | +| time_elapsed | 13681 | +| total_timesteps | 4800512 | +| train/ | | +| approx_kl | 0.037137542 | +| clip_fraction | 0.284 | +| clip_range | 0.2 | +| entropy_loss | -6.05 | +| explained_variance | -0.101 | +| learning_rate | 1e-05 | +| loss | -0.0964 | +| n_updates | 7310 | +| policy_gradient_loss | -0.0637 | +| value_loss | 0.000119 | +----------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.196 | +| time/ | | +| fps | 350 | +| iterations | 587 | +| time_elapsed | 13702 | +| total_timesteps | 4808704 | +| train/ | | +| approx_kl | 0.036682963 | +| clip_fraction | 0.3 | +| clip_range | 0.2 | +| entropy_loss | -6.06 | +| explained_variance | -0.125 | +| learning_rate | 1e-05 | +| loss | -0.0935 | +| n_updates | 7320 | +| policy_gradient_loss | -0.0601 | +| value_loss | 0.000121 | +----------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.196 | +| time/ | | +| fps | 350 | +| iterations | 588 | +| time_elapsed | 13725 | +| total_timesteps | 4816896 | +| train/ | | +| approx_kl | 0.039626427 | +| clip_fraction | 0.298 | +| clip_range | 0.2 | +| entropy_loss | -5.9 | +| explained_variance | -0.108 | +| learning_rate | 1e-05 | +| loss | -0.0998 | +| n_updates | 7330 | +| policy_gradient_loss | -0.0596 | +| value_loss | 0.000176 | +----------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.193 | +| time/ | | +| fps | 351 | +| iterations | 589 | +| time_elapsed | 13746 | +| total_timesteps | 4825088 | +| train/ | | +| approx_kl | 0.035272382 | +| clip_fraction | 0.278 | +| clip_range | 0.2 | +| entropy_loss | -5.96 | +| explained_variance | -0.208 | +| learning_rate | 1e-05 | +| loss | -0.0878 | +| n_updates | 7340 | +| policy_gradient_loss | -0.0585 | +| value_loss | 0.000198 | +----------------------------------------- +Early stopping at step 5 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.189 | +| time/ | | +| fps | 351 | +| iterations | 590 | +| time_elapsed | 13767 | +| total_timesteps | 4833280 | +| train/ | | +| approx_kl | 0.031567298 | +| clip_fraction | 0.274 | +| clip_range | 0.2 | +| entropy_loss | -5.6 | +| explained_variance | 0.00999 | +| learning_rate | 1e-05 | +| loss | -0.0756 | +| n_updates | 7350 | +| policy_gradient_loss | -0.0545 | +| value_loss | 0.000191 | +----------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.18 | +| time/ | | +| fps | 351 | +| iterations | 591 | +| time_elapsed | 13787 | +| total_timesteps | 4841472 | +| train/ | | +| approx_kl | 0.03786836 | +| clip_fraction | 0.282 | +| clip_range | 0.2 | +| entropy_loss | -6.01 | +| explained_variance | -0.142 | +| learning_rate | 1e-05 | +| loss | -0.0928 | +| n_updates | 7360 | +| policy_gradient_loss | -0.0613 | +| value_loss | 0.000173 | +---------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.189 | +| time/ | | +| fps | 351 | +| iterations | 592 | +| time_elapsed | 13809 | +| total_timesteps | 4849664 | +| train/ | | +| approx_kl | 0.036420222 | +| clip_fraction | 0.312 | +| clip_range | 0.2 | +| entropy_loss | -5.86 | +| explained_variance | -0.0363 | +| learning_rate | 1e-05 | +| loss | -0.0891 | +| n_updates | 7370 | +| policy_gradient_loss | -0.0595 | +| value_loss | 0.000172 | +----------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.181 | +| time/ | | +| fps | 351 | +| iterations | 593 | +| time_elapsed | 13831 | +| total_timesteps | 4857856 | +| train/ | | +| approx_kl | 0.03525548 | +| clip_fraction | 0.265 | +| clip_range | 0.2 | +| entropy_loss | -5.9 | +| explained_variance | -0.0779 | +| learning_rate | 1e-05 | +| loss | -0.116 | +| n_updates | 7380 | +| policy_gradient_loss | -0.0583 | +| value_loss | 0.000164 | +---------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.183 | +| time/ | | +| fps | 351 | +| iterations | 594 | +| time_elapsed | 13854 | +| total_timesteps | 4866048 | +| train/ | | +| approx_kl | 0.045972794 | +| clip_fraction | 0.32 | +| clip_range | 0.2 | +| entropy_loss | -5.79 | +| explained_variance | -0.0487 | +| learning_rate | 1e-05 | +| loss | -0.0901 | +| n_updates | 7390 | +| policy_gradient_loss | -0.0612 | +| value_loss | 0.000189 | +----------------------------------------- +Early stopping at step 5 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.168 | +| time/ | | +| fps | 351 | +| iterations | 595 | +| time_elapsed | 13875 | +| total_timesteps | 4874240 | +| train/ | | +| approx_kl | 0.03247024 | +| clip_fraction | 0.278 | +| clip_range | 0.2 | +| entropy_loss | -5.83 | +| explained_variance | -0.0455 | +| learning_rate | 1e-05 | +| loss | -0.0847 | +| n_updates | 7400 | +| policy_gradient_loss | -0.0591 | +| value_loss | 0.000158 | +---------------------------------------- +Early stopping at step 5 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.17 | +| time/ | | +| fps | 351 | +| iterations | 596 | +| time_elapsed | 13897 | +| total_timesteps | 4882432 | +| train/ | | +| approx_kl | 0.031495083 | +| clip_fraction | 0.272 | +| clip_range | 0.2 | +| entropy_loss | -5.87 | +| explained_variance | -0.0321 | +| learning_rate | 1e-05 | +| loss | -0.09 | +| n_updates | 7410 | +| policy_gradient_loss | -0.0529 | +| value_loss | 0.000175 | +----------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.172 | +| time/ | | +| fps | 351 | +| iterations | 597 | +| time_elapsed | 13920 | +| total_timesteps | 4890624 | +| train/ | | +| approx_kl | 0.038796432 | +| clip_fraction | 0.309 | +| clip_range | 0.2 | +| entropy_loss | -5.7 | +| explained_variance | -0.127 | +| learning_rate | 1e-05 | +| loss | -0.108 | +| n_updates | 7420 | +| policy_gradient_loss | -0.0625 | +| value_loss | 0.000133 | +----------------------------------------- +Early stopping at step 4 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.168 | +| time/ | | +| fps | 351 | +| iterations | 598 | +| time_elapsed | 13939 | +| total_timesteps | 4898816 | +| train/ | | +| approx_kl | 0.02923264 | +| clip_fraction | 0.23 | +| clip_range | 0.2 | +| entropy_loss | -5.75 | +| explained_variance | -0.083 | +| learning_rate | 1e-05 | +| loss | -0.0925 | +| n_updates | 7430 | +| policy_gradient_loss | -0.0452 | +| value_loss | 0.000191 | +---------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.188 | +| time/ | | +| fps | 351 | +| iterations | 599 | +| time_elapsed | 13962 | +| total_timesteps | 4907008 | +| train/ | | +| approx_kl | 0.03739206 | +| clip_fraction | 0.298 | +| clip_range | 0.2 | +| entropy_loss | -5.92 | +| explained_variance | -0.103 | +| learning_rate | 1e-05 | +| loss | -0.103 | +| n_updates | 7440 | +| policy_gradient_loss | -0.061 | +| value_loss | 0.000155 | +---------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.176 | +| time/ | | +| fps | 351 | +| iterations | 600 | +| time_elapsed | 13982 | +| total_timesteps | 4915200 | +| train/ | | +| approx_kl | 0.034353524 | +| clip_fraction | 0.278 | +| clip_range | 0.2 | +| entropy_loss | -5.46 | +| explained_variance | -0.0724 | +| learning_rate | 1e-05 | +| loss | -0.11 | +| n_updates | 7450 | +| policy_gradient_loss | -0.0578 | +| value_loss | 0.000276 | +----------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.192 | +| time/ | | +| fps | 351 | +| iterations | 601 | +| time_elapsed | 14003 | +| total_timesteps | 4923392 | +| train/ | | +| approx_kl | 0.038023155 | +| clip_fraction | 0.271 | +| clip_range | 0.2 | +| entropy_loss | -5.97 | +| explained_variance | -0.0495 | +| learning_rate | 1e-05 | +| loss | -0.0813 | +| n_updates | 7460 | +| policy_gradient_loss | -0.0606 | +| value_loss | 0.000189 | +----------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.192 | +| time/ | | +| fps | 351 | +| iterations | 602 | +| time_elapsed | 14025 | +| total_timesteps | 4931584 | +| train/ | | +| approx_kl | 0.038119305 | +| clip_fraction | 0.304 | +| clip_range | 0.2 | +| entropy_loss | -6.01 | +| explained_variance | -0.067 | +| learning_rate | 1e-05 | +| loss | -0.0964 | +| n_updates | 7470 | +| policy_gradient_loss | -0.0612 | +| value_loss | 0.000183 | +----------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.195 | +| time/ | | +| fps | 351 | +| iterations | 603 | +| time_elapsed | 14046 | +| total_timesteps | 4939776 | +| train/ | | +| approx_kl | 0.036077105 | +| clip_fraction | 0.3 | +| clip_range | 0.2 | +| entropy_loss | -5.56 | +| explained_variance | -0.0544 | +| learning_rate | 1e-05 | +| loss | -0.109 | +| n_updates | 7480 | +| policy_gradient_loss | -0.0606 | +| value_loss | 0.000156 | +----------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.188 | +| time/ | | +| fps | 351 | +| iterations | 604 | +| time_elapsed | 14068 | +| total_timesteps | 4947968 | +| train/ | | +| approx_kl | 0.035020456 | +| clip_fraction | 0.282 | +| clip_range | 0.2 | +| entropy_loss | -5.83 | +| explained_variance | -0.0127 | +| learning_rate | 1e-05 | +| loss | -0.108 | +| n_updates | 7490 | +| policy_gradient_loss | -0.0608 | +| value_loss | 0.000241 | +----------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.177 | +| time/ | | +| fps | 351 | +| iterations | 605 | +| time_elapsed | 14090 | +| total_timesteps | 4956160 | +| train/ | | +| approx_kl | 0.034234174 | +| clip_fraction | 0.305 | +| clip_range | 0.2 | +| entropy_loss | -5.65 | +| explained_variance | -0.0336 | +| learning_rate | 1e-05 | +| loss | -0.105 | +| n_updates | 7500 | +| policy_gradient_loss | -0.0635 | +| value_loss | 0.000201 | +----------------------------------------- +Early stopping at step 5 due to reaching max kl: 0.06 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.19 | +| time/ | | +| fps | 351 | +| iterations | 606 | +| time_elapsed | 14110 | +| total_timesteps | 4964352 | +| train/ | | +| approx_kl | 0.03145513 | +| clip_fraction | 0.256 | +| clip_range | 0.2 | +| entropy_loss | -5.86 | +| explained_variance | 0.0179 | +| learning_rate | 1e-05 | +| loss | -0.099 | +| n_updates | 7510 | +| policy_gradient_loss | -0.0529 | +| value_loss | 0.000173 | +---------------------------------------- +Early stopping at step 5 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.193 | +| time/ | | +| fps | 351 | +| iterations | 607 | +| time_elapsed | 14130 | +| total_timesteps | 4972544 | +| train/ | | +| approx_kl | 0.035093546 | +| clip_fraction | 0.253 | +| clip_range | 0.2 | +| entropy_loss | -5.82 | +| explained_variance | 0.00275 | +| learning_rate | 1e-05 | +| loss | -0.0934 | +| n_updates | 7520 | +| policy_gradient_loss | -0.0592 | +| value_loss | 0.000176 | +----------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.195 | +| time/ | | +| fps | 351 | +| iterations | 608 | +| time_elapsed | 14151 | +| total_timesteps | 4980736 | +| train/ | | +| approx_kl | 0.035109498 | +| clip_fraction | 0.311 | +| clip_range | 0.2 | +| entropy_loss | -5.59 | +| explained_variance | -0.0611 | +| learning_rate | 1e-05 | +| loss | -0.084 | +| n_updates | 7530 | +| policy_gradient_loss | -0.0598 | +| value_loss | 0.000166 | +----------------------------------------- +Early stopping at step 5 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.208 | +| time/ | | +| fps | 352 | +| iterations | 609 | +| time_elapsed | 14171 | +| total_timesteps | 4988928 | +| train/ | | +| approx_kl | 0.033068717 | +| clip_fraction | 0.273 | +| clip_range | 0.2 | +| entropy_loss | -5.82 | +| explained_variance | -0.016 | +| learning_rate | 1e-05 | +| loss | -0.088 | +| n_updates | 7540 | +| policy_gradient_loss | -0.0555 | +| value_loss | 0.00018 | +----------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.202 | +| time/ | | +| fps | 352 | +| iterations | 610 | +| time_elapsed | 14192 | +| total_timesteps | 4997120 | +| train/ | | +| approx_kl | 0.033282492 | +| clip_fraction | 0.281 | +| clip_range | 0.2 | +| entropy_loss | -5.77 | +| explained_variance | -0.00967 | +| learning_rate | 1e-05 | +| loss | -0.0932 | +| n_updates | 7550 | +| policy_gradient_loss | -0.0538 | +| value_loss | 0.000278 | +----------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.205 | +| time/ | | +| fps | 352 | +| iterations | 611 | +| time_elapsed | 14216 | +| total_timesteps | 5005312 | +| train/ | | +| approx_kl | 0.034570385 | +| clip_fraction | 0.305 | +| clip_range | 0.2 | +| entropy_loss | -5.86 | +| explained_variance | -0.0622 | +| learning_rate | 1e-05 | +| loss | -0.11 | +| n_updates | 7560 | +| policy_gradient_loss | -0.0656 | +| value_loss | 0.000148 | +----------------------------------------- +Early stopping at step 7 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.78e+03 | +| ep_rew_mean | 0.215 | +| time/ | | +| fps | 352 | +| iterations | 612 | +| time_elapsed | 14238 | +| total_timesteps | 5013504 | +| train/ | | +| approx_kl | 0.03757929 | +| clip_fraction | 0.316 | +| clip_range | 0.2 | +| entropy_loss | -5.79 | +| explained_variance | 0.0188 | +| learning_rate | 1e-05 | +| loss | -0.108 | +| n_updates | 7570 | +| policy_gradient_loss | -0.0642 | +| value_loss | 0.00018 | +---------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.205 | +| time/ | | +| fps | 352 | +| iterations | 613 | +| time_elapsed | 14261 | +| total_timesteps | 5021696 | +| train/ | | +| approx_kl | 0.046588574 | +| clip_fraction | 0.293 | +| clip_range | 0.2 | +| entropy_loss | -5.77 | +| explained_variance | 0.0368 | +| learning_rate | 1e-05 | +| loss | -0.106 | +| n_updates | 7580 | +| policy_gradient_loss | -0.0612 | +| value_loss | 0.000208 | +----------------------------------------- +Early stopping at step 4 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.78e+03 | +| ep_rew_mean | 0.211 | +| time/ | | +| fps | 352 | +| iterations | 614 | +| time_elapsed | 14280 | +| total_timesteps | 5029888 | +| train/ | | +| approx_kl | 0.02765539 | +| clip_fraction | 0.245 | +| clip_range | 0.2 | +| entropy_loss | -5.8 | +| explained_variance | -0.0338 | +| learning_rate | 1e-05 | +| loss | -0.0904 | +| n_updates | 7590 | +| policy_gradient_loss | -0.0536 | +| value_loss | 0.000155 | +---------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.78e+03 | +| ep_rew_mean | 0.202 | +| time/ | | +| fps | 352 | +| iterations | 615 | +| time_elapsed | 14301 | +| total_timesteps | 5038080 | +| train/ | | +| approx_kl | 0.038189325 | +| clip_fraction | 0.301 | +| clip_range | 0.2 | +| entropy_loss | -5.91 | +| explained_variance | -0.133 | +| learning_rate | 1e-05 | +| loss | -0.101 | +| n_updates | 7600 | +| policy_gradient_loss | -0.0596 | +| value_loss | 0.000117 | +----------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.202 | +| time/ | | +| fps | 352 | +| iterations | 616 | +| time_elapsed | 14323 | +| total_timesteps | 5046272 | +| train/ | | +| approx_kl | 0.041053735 | +| clip_fraction | 0.287 | +| clip_range | 0.2 | +| entropy_loss | -5.77 | +| explained_variance | -0.0819 | +| learning_rate | 1e-05 | +| loss | -0.0913 | +| n_updates | 7610 | +| policy_gradient_loss | -0.0625 | +| value_loss | 0.000125 | +----------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.207 | +| time/ | | +| fps | 352 | +| iterations | 617 | +| time_elapsed | 14344 | +| total_timesteps | 5054464 | +| train/ | | +| approx_kl | 0.035959724 | +| clip_fraction | 0.273 | +| clip_range | 0.2 | +| entropy_loss | -5.86 | +| explained_variance | 0.13 | +| learning_rate | 1e-05 | +| loss | -0.0949 | +| n_updates | 7620 | +| policy_gradient_loss | -0.0593 | +| value_loss | 0.000129 | +----------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.203 | +| time/ | | +| fps | 352 | +| iterations | 618 | +| time_elapsed | 14365 | +| total_timesteps | 5062656 | +| train/ | | +| approx_kl | 0.03419258 | +| clip_fraction | 0.296 | +| clip_range | 0.2 | +| entropy_loss | -5.85 | +| explained_variance | -0.0157 | +| learning_rate | 1e-05 | +| loss | -0.0972 | +| n_updates | 7630 | +| policy_gradient_loss | -0.0607 | +| value_loss | 0.000184 | +---------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.211 | +| time/ | | +| fps | 352 | +| iterations | 619 | +| time_elapsed | 14388 | +| total_timesteps | 5070848 | +| train/ | | +| approx_kl | 0.033920072 | +| clip_fraction | 0.298 | +| clip_range | 0.2 | +| entropy_loss | -5.81 | +| explained_variance | -0.112 | +| learning_rate | 1e-05 | +| loss | -0.106 | +| n_updates | 7640 | +| policy_gradient_loss | -0.0638 | +| value_loss | 0.000135 | +----------------------------------------- +Early stopping at step 5 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.78e+03 | +| ep_rew_mean | 0.215 | +| time/ | | +| fps | 352 | +| iterations | 620 | +| time_elapsed | 14409 | +| total_timesteps | 5079040 | +| train/ | | +| approx_kl | 0.033736087 | +| clip_fraction | 0.265 | +| clip_range | 0.2 | +| entropy_loss | -5.6 | +| explained_variance | -0.0637 | +| learning_rate | 1e-05 | +| loss | -0.0906 | +| n_updates | 7650 | +| policy_gradient_loss | -0.0507 | +| value_loss | 0.000202 | +----------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.201 | +| time/ | | +| fps | 352 | +| iterations | 621 | +| time_elapsed | 14431 | +| total_timesteps | 5087232 | +| train/ | | +| approx_kl | 0.041054226 | +| clip_fraction | 0.286 | +| clip_range | 0.2 | +| entropy_loss | -5.7 | +| explained_variance | -0.0697 | +| learning_rate | 1e-05 | +| loss | -0.0851 | +| n_updates | 7660 | +| policy_gradient_loss | -0.0559 | +| value_loss | 0.000216 | +----------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.21 | +| time/ | | +| fps | 352 | +| iterations | 622 | +| time_elapsed | 14453 | +| total_timesteps | 5095424 | +| train/ | | +| approx_kl | 0.038532622 | +| clip_fraction | 0.286 | +| clip_range | 0.2 | +| entropy_loss | -5.93 | +| explained_variance | -0.12 | +| learning_rate | 1e-05 | +| loss | -0.108 | +| n_updates | 7670 | +| policy_gradient_loss | -0.063 | +| value_loss | 0.000149 | +----------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.197 | +| time/ | | +| fps | 352 | +| iterations | 623 | +| time_elapsed | 14474 | +| total_timesteps | 5103616 | +| train/ | | +| approx_kl | 0.040282883 | +| clip_fraction | 0.283 | +| clip_range | 0.2 | +| entropy_loss | -5.81 | +| explained_variance | -0.0162 | +| learning_rate | 1e-05 | +| loss | -0.0876 | +| n_updates | 7680 | +| policy_gradient_loss | -0.0579 | +| value_loss | 0.000175 | +----------------------------------------- +Early stopping at step 5 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.199 | +| time/ | | +| fps | 352 | +| iterations | 624 | +| time_elapsed | 14494 | +| total_timesteps | 5111808 | +| train/ | | +| approx_kl | 0.034726243 | +| clip_fraction | 0.265 | +| clip_range | 0.2 | +| entropy_loss | -5.75 | +| explained_variance | -0.0719 | +| learning_rate | 1e-05 | +| loss | -0.0956 | +| n_updates | 7690 | +| policy_gradient_loss | -0.0572 | +| value_loss | 0.000158 | +----------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.78e+03 | +| ep_rew_mean | 0.193 | +| time/ | | +| fps | 352 | +| iterations | 625 | +| time_elapsed | 14515 | +| total_timesteps | 5120000 | +| train/ | | +| approx_kl | 0.040160514 | +| clip_fraction | 0.296 | +| clip_range | 0.2 | +| entropy_loss | -5.87 | +| explained_variance | -0.155 | +| learning_rate | 1e-05 | +| loss | -0.0901 | +| n_updates | 7700 | +| policy_gradient_loss | -0.0633 | +| value_loss | 0.000138 | +----------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.199 | +| time/ | | +| fps | 352 | +| iterations | 626 | +| time_elapsed | 14536 | +| total_timesteps | 5128192 | +| train/ | | +| approx_kl | 0.035126433 | +| clip_fraction | 0.297 | +| clip_range | 0.2 | +| entropy_loss | -5.69 | +| explained_variance | -0.0271 | +| learning_rate | 1e-05 | +| loss | -0.0962 | +| n_updates | 7710 | +| policy_gradient_loss | -0.0597 | +| value_loss | 0.000175 | +----------------------------------------- +Early stopping at step 5 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.199 | +| time/ | | +| fps | 352 | +| iterations | 627 | +| time_elapsed | 14558 | +| total_timesteps | 5136384 | +| train/ | | +| approx_kl | 0.034940407 | +| clip_fraction | 0.253 | +| clip_range | 0.2 | +| entropy_loss | -5.88 | +| explained_variance | -0.049 | +| learning_rate | 1e-05 | +| loss | -0.0931 | +| n_updates | 7720 | +| policy_gradient_loss | -0.0534 | +| value_loss | 0.000168 | +----------------------------------------- +Early stopping at step 6 due to reaching max kl: 0.05 +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.81e+03 | +| ep_rew_mean | 0.206 | +| time/ | | +| fps | 352 | +| iterations | 628 | +| time_elapsed | 14579 | +| total_timesteps | 5144576 | +| train/ | | +| approx_kl | 0.037215568 | +| clip_fraction | 0.298 | +| clip_range | 0.2 | +| entropy_loss | -5.81 | +| explained_variance | -0.089 | +| learning_rate | 1e-05 | +| loss | -0.106 | +| n_updates | 7730 | +| policy_gradient_loss | -0.0617 | +| value_loss | 0.000153 | +----------------------------------------- diff --git a/004_rgb_stack_ram_based_reward_custom/trained_models_ryu_level_1_time_reward_small_random_continue/training_log.txt b/004_rgb_stack_ram_based_reward_custom/trained_models_ryu_level_1_time_reward_small_random_continue/training_log.txt new file mode 100644 index 0000000..8211e2d --- /dev/null +++ b/004_rgb_stack_ram_based_reward_custom/trained_models_ryu_level_1_time_reward_small_random_continue/training_log.txt @@ -0,0 +1,208819 @@ +Logging to logs\PPO_13 +----------------------------- +| time/ | | +| fps | 323 | +| iterations | 1 | +| time_elapsed | 3 | +| total_timesteps | 1024 | +----------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.89e+03 | +| ep_rew_mean | -0.0819 | +| time/ | | +| fps | 308 | +| iterations | 2 | +| time_elapsed | 6 | +| total_timesteps | 2048 | +| train/ | | +| approx_kl | 1.7311502 | +| clip_fraction | 0.546 | +| clip_range | 0.2 | +| entropy_loss | -0.518 | +| explained_variance | -0.739 | +| learning_rate | 0.0001 | +| loss | -0.0576 | +| n_updates | 60540 | +| policy_gradient_loss | -0.0591 | +| value_loss | 0.000286 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.89e+03 | +| ep_rew_mean | -0.0819 | +| time/ | | +| fps | 306 | +| iterations | 3 | +| time_elapsed | 10 | +| total_timesteps | 3072 | +| train/ | | +| approx_kl | 1.7776582 | +| clip_fraction | 0.505 | +| clip_range | 0.2 | +| entropy_loss | -0.457 | +| explained_variance | -2.29 | +| learning_rate | 0.0001 | +| loss | -0.0858 | +| n_updates | 60550 | +| policy_gradient_loss | -0.0674 | +| value_loss | 0.000131 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.82e+03 | +| ep_rew_mean | 0.187 | +| time/ | | +| fps | 309 | +| iterations | 4 | +| time_elapsed | 13 | +| total_timesteps | 4096 | +| train/ | | +| approx_kl | 1.9877899 | +| clip_fraction | 0.476 | +| clip_range | 0.2 | +| entropy_loss | -0.36 | +| explained_variance | -1.25 | +| learning_rate | 0.0001 | +| loss | -0.0829 | +| n_updates | 60560 | +| policy_gradient_loss | -0.0663 | +| value_loss | 0.000543 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.82e+03 | +| ep_rew_mean | 0.187 | +| time/ | | +| fps | 311 | +| iterations | 5 | +| time_elapsed | 16 | +| total_timesteps | 5120 | +| train/ | | +| approx_kl | 2.5217834 | +| clip_fraction | 0.496 | +| clip_range | 0.2 | +| entropy_loss | -0.462 | +| explained_variance | -0.841 | +| learning_rate | 0.0001 | +| loss | -0.0853 | +| n_updates | 60570 | +| policy_gradient_loss | -0.06 | +| value_loss | 0.00032 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.82e+03 | +| ep_rew_mean | 0.187 | +| time/ | | +| fps | 313 | +| iterations | 6 | +| time_elapsed | 19 | +| total_timesteps | 6144 | +| train/ | | +| approx_kl | 1.2413561 | +| clip_fraction | 0.435 | +| clip_range | 0.2 | +| entropy_loss | -0.355 | +| explained_variance | -1.94 | +| learning_rate | 0.0001 | +| loss | -0.0842 | +| n_updates | 60580 | +| policy_gradient_loss | -0.0568 | +| value_loss | 0.000215 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.06e+03 | +| ep_rew_mean | 0.26 | +| time/ | | +| fps | 314 | +| iterations | 7 | +| time_elapsed | 22 | +| total_timesteps | 7168 | +| train/ | | +| approx_kl | 1.5624533 | +| clip_fraction | 0.492 | +| clip_range | 0.2 | +| entropy_loss | -0.483 | +| explained_variance | -0.287 | +| learning_rate | 0.0001 | +| loss | -0.0246 | +| n_updates | 60590 | +| policy_gradient_loss | -0.0589 | +| value_loss | 0.000508 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.03e+03 | +| ep_rew_mean | 0.247 | +| time/ | | +| fps | 314 | +| iterations | 8 | +| time_elapsed | 26 | +| total_timesteps | 8192 | +| train/ | | +| approx_kl | 1.5707165 | +| clip_fraction | 0.505 | +| clip_range | 0.2 | +| entropy_loss | -0.483 | +| explained_variance | -1.81 | +| learning_rate | 0.0001 | +| loss | -0.0561 | +| n_updates | 60600 | +| policy_gradient_loss | -0.0535 | +| value_loss | 0.000438 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.03e+03 | +| ep_rew_mean | 0.247 | +| time/ | | +| fps | 313 | +| iterations | 9 | +| time_elapsed | 29 | +| total_timesteps | 9216 | +| train/ | | +| approx_kl | 2.192265 | +| clip_fraction | 0.499 | +| clip_range | 0.2 | +| entropy_loss | -0.418 | +| explained_variance | -0.977 | +| learning_rate | 0.0001 | +| loss | -0.0631 | +| n_updates | 60610 | +| policy_gradient_loss | -0.0622 | +| value_loss | 0.000595 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.97e+03 | +| ep_rew_mean | 0.304 | +| time/ | | +| fps | 311 | +| iterations | 10 | +| time_elapsed | 32 | +| total_timesteps | 10240 | +| train/ | | +| approx_kl | 2.9311686 | +| clip_fraction | 0.476 | +| clip_range | 0.2 | +| entropy_loss | -0.425 | +| explained_variance | -1.93 | +| learning_rate | 0.0001 | +| loss | -0.0961 | +| n_updates | 60620 | +| policy_gradient_loss | -0.0569 | +| value_loss | 0.000551 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.97e+03 | +| ep_rew_mean | 0.304 | +| time/ | | +| fps | 312 | +| iterations | 11 | +| time_elapsed | 36 | +| total_timesteps | 11264 | +| train/ | | +| approx_kl | 2.3376176 | +| clip_fraction | 0.514 | +| clip_range | 0.2 | +| entropy_loss | -0.432 | +| explained_variance | -0.655 | +| learning_rate | 0.0001 | +| loss | -0.1 | +| n_updates | 60630 | +| policy_gradient_loss | -0.0558 | +| value_loss | 0.000475 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.97e+03 | +| ep_rew_mean | 0.304 | +| time/ | | +| fps | 312 | +| iterations | 12 | +| time_elapsed | 39 | +| total_timesteps | 12288 | +| train/ | | +| approx_kl | 1.6648946 | +| clip_fraction | 0.49 | +| clip_range | 0.2 | +| entropy_loss | -0.42 | +| explained_variance | -1.63 | +| learning_rate | 0.0001 | +| loss | -0.0566 | +| n_updates | 60640 | +| policy_gradient_loss | -0.0635 | +| value_loss | 0.000423 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.07e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 312 | +| iterations | 13 | +| time_elapsed | 42 | +| total_timesteps | 13312 | +| train/ | | +| approx_kl | 1.6497533 | +| clip_fraction | 0.518 | +| clip_range | 0.2 | +| entropy_loss | -0.444 | +| explained_variance | -1.47 | +| learning_rate | 0.0001 | +| loss | -0.0978 | +| n_updates | 60650 | +| policy_gradient_loss | -0.0671 | +| value_loss | 0.000553 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.04e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 311 | +| iterations | 14 | +| time_elapsed | 46 | +| total_timesteps | 14336 | +| train/ | | +| approx_kl | 1.4611773 | +| clip_fraction | 0.472 | +| clip_range | 0.2 | +| entropy_loss | -0.443 | +| explained_variance | -3.72 | +| learning_rate | 0.0001 | +| loss | -0.0356 | +| n_updates | 60660 | +| policy_gradient_loss | -0.0483 | +| value_loss | 0.000184 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.04e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 311 | +| iterations | 15 | +| time_elapsed | 49 | +| total_timesteps | 15360 | +| train/ | | +| approx_kl | 1.3469869 | +| clip_fraction | 0.494 | +| clip_range | 0.2 | +| entropy_loss | -0.5 | +| explained_variance | -0.463 | +| learning_rate | 0.0001 | +| loss | -0.0997 | +| n_updates | 60670 | +| policy_gradient_loss | -0.0605 | +| value_loss | 0.000433 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.04e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 311 | +| iterations | 16 | +| time_elapsed | 52 | +| total_timesteps | 16384 | +| train/ | | +| approx_kl | 2.0747125 | +| clip_fraction | 0.482 | +| clip_range | 0.2 | +| entropy_loss | -0.39 | +| explained_variance | -1.3 | +| learning_rate | 0.0001 | +| loss | -0.0909 | +| n_updates | 60680 | +| policy_gradient_loss | -0.0565 | +| value_loss | 0.000515 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.06e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 312 | +| iterations | 17 | +| time_elapsed | 55 | +| total_timesteps | 17408 | +| train/ | | +| approx_kl | 2.300259 | +| clip_fraction | 0.46 | +| clip_range | 0.2 | +| entropy_loss | -0.353 | +| explained_variance | -5.12 | +| learning_rate | 0.0001 | +| loss | -0.0827 | +| n_updates | 60690 | +| policy_gradient_loss | -0.0685 | +| value_loss | 0.000409 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.04e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 313 | +| iterations | 18 | +| time_elapsed | 58 | +| total_timesteps | 18432 | +| train/ | | +| approx_kl | 1.5878639 | +| clip_fraction | 0.5 | +| clip_range | 0.2 | +| entropy_loss | -0.468 | +| explained_variance | -1.18 | +| learning_rate | 0.0001 | +| loss | -0.125 | +| n_updates | 60700 | +| policy_gradient_loss | -0.0701 | +| value_loss | 0.000256 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.04e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 312 | +| iterations | 19 | +| time_elapsed | 62 | +| total_timesteps | 19456 | +| train/ | | +| approx_kl | 1.6519537 | +| clip_fraction | 0.533 | +| clip_range | 0.2 | +| entropy_loss | -0.618 | +| explained_variance | -0.669 | +| learning_rate | 0.0001 | +| loss | -0.105 | +| n_updates | 60710 | +| policy_gradient_loss | -0.0663 | +| value_loss | 0.000499 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.01e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 312 | +| iterations | 20 | +| time_elapsed | 65 | +| total_timesteps | 20480 | +| train/ | | +| approx_kl | 1.7801784 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.44 | +| explained_variance | -1.32 | +| learning_rate | 0.0001 | +| loss | -0.0716 | +| n_updates | 60720 | +| policy_gradient_loss | -0.0443 | +| value_loss | 0.000422 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.01e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 312 | +| iterations | 21 | +| time_elapsed | 68 | +| total_timesteps | 21504 | +| train/ | | +| approx_kl | 1.9348958 | +| clip_fraction | 0.496 | +| clip_range | 0.2 | +| entropy_loss | -0.441 | +| explained_variance | -0.237 | +| learning_rate | 0.0001 | +| loss | -0.0713 | +| n_updates | 60730 | +| policy_gradient_loss | -0.0511 | +| value_loss | 0.000483 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.01e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 311 | +| iterations | 22 | +| time_elapsed | 72 | +| total_timesteps | 22528 | +| train/ | | +| approx_kl | 1.5786375 | +| clip_fraction | 0.474 | +| clip_range | 0.2 | +| entropy_loss | -0.432 | +| explained_variance | -1.41 | +| learning_rate | 0.0001 | +| loss | -0.112 | +| n_updates | 60740 | +| policy_gradient_loss | -0.0674 | +| value_loss | 0.00049 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.06e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 310 | +| iterations | 23 | +| time_elapsed | 75 | +| total_timesteps | 23552 | +| train/ | | +| approx_kl | 1.2974563 | +| clip_fraction | 0.453 | +| clip_range | 0.2 | +| entropy_loss | -0.416 | +| explained_variance | -2.57 | +| learning_rate | 0.0001 | +| loss | -0.077 | +| n_updates | 60750 | +| policy_gradient_loss | -0.0599 | +| value_loss | 0.000355 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.06e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 310 | +| iterations | 24 | +| time_elapsed | 79 | +| total_timesteps | 24576 | +| train/ | | +| approx_kl | 1.9828597 | +| clip_fraction | 0.45 | +| clip_range | 0.2 | +| entropy_loss | -0.36 | +| explained_variance | -1.4 | +| learning_rate | 0.0001 | +| loss | -0.0652 | +| n_updates | 60760 | +| policy_gradient_loss | -0.0604 | +| value_loss | 0.000599 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.06e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 310 | +| iterations | 25 | +| time_elapsed | 82 | +| total_timesteps | 25600 | +| train/ | | +| approx_kl | 1.6003879 | +| clip_fraction | 0.492 | +| clip_range | 0.2 | +| entropy_loss | -0.497 | +| explained_variance | -1.6 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 60770 | +| policy_gradient_loss | -0.067 | +| value_loss | 0.000596 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.06e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 310 | +| iterations | 26 | +| time_elapsed | 85 | +| total_timesteps | 26624 | +| train/ | | +| approx_kl | 1.8489563 | +| clip_fraction | 0.486 | +| clip_range | 0.2 | +| entropy_loss | -0.449 | +| explained_variance | -2.64 | +| learning_rate | 0.0001 | +| loss | -0.0938 | +| n_updates | 60780 | +| policy_gradient_loss | -0.0607 | +| value_loss | 0.000217 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.1e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 310 | +| iterations | 27 | +| time_elapsed | 88 | +| total_timesteps | 27648 | +| train/ | | +| approx_kl | 1.504662 | +| clip_fraction | 0.486 | +| clip_range | 0.2 | +| entropy_loss | -0.505 | +| explained_variance | -5.1 | +| learning_rate | 0.0001 | +| loss | -0.0979 | +| n_updates | 60790 | +| policy_gradient_loss | -0.0643 | +| value_loss | 0.00014 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.1e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 310 | +| iterations | 28 | +| time_elapsed | 92 | +| total_timesteps | 28672 | +| train/ | | +| approx_kl | 1.6301541 | +| clip_fraction | 0.468 | +| clip_range | 0.2 | +| entropy_loss | -0.44 | +| explained_variance | -0.634 | +| learning_rate | 0.0001 | +| loss | -0.0859 | +| n_updates | 60800 | +| policy_gradient_loss | -0.057 | +| value_loss | 0.000545 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.1e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 310 | +| iterations | 29 | +| time_elapsed | 95 | +| total_timesteps | 29696 | +| train/ | | +| approx_kl | 1.9214245 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.407 | +| explained_variance | -2.17 | +| learning_rate | 0.0001 | +| loss | -0.0721 | +| n_updates | 60810 | +| policy_gradient_loss | -0.0593 | +| value_loss | 0.000356 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.12e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 311 | +| iterations | 30 | +| time_elapsed | 98 | +| total_timesteps | 30720 | +| train/ | | +| approx_kl | 2.8619342 | +| clip_fraction | 0.495 | +| clip_range | 0.2 | +| entropy_loss | -0.487 | +| explained_variance | -0.71 | +| learning_rate | 0.0001 | +| loss | -0.0732 | +| n_updates | 60820 | +| policy_gradient_loss | -0.0558 | +| value_loss | 0.000529 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.06e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 311 | +| iterations | 31 | +| time_elapsed | 102 | +| total_timesteps | 31744 | +| train/ | | +| approx_kl | 1.3643384 | +| clip_fraction | 0.513 | +| clip_range | 0.2 | +| entropy_loss | -0.502 | +| explained_variance | -0.38 | +| learning_rate | 0.0001 | +| loss | -0.0516 | +| n_updates | 60830 | +| policy_gradient_loss | -0.0552 | +| value_loss | 0.000552 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.06e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 311 | +| iterations | 32 | +| time_elapsed | 105 | +| total_timesteps | 32768 | +| train/ | | +| approx_kl | 4.1749177 | +| clip_fraction | 0.458 | +| clip_range | 0.2 | +| entropy_loss | -0.375 | +| explained_variance | -0.495 | +| learning_rate | 0.0001 | +| loss | -0.0835 | +| n_updates | 60840 | +| policy_gradient_loss | -0.052 | +| value_loss | 0.00052 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.07e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 310 | +| iterations | 33 | +| time_elapsed | 108 | +| total_timesteps | 33792 | +| train/ | | +| approx_kl | 1.6803333 | +| clip_fraction | 0.497 | +| clip_range | 0.2 | +| entropy_loss | -0.42 | +| explained_variance | -0.936 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 60850 | +| policy_gradient_loss | -0.0687 | +| value_loss | 0.000578 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.03e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 309 | +| iterations | 34 | +| time_elapsed | 112 | +| total_timesteps | 34816 | +| train/ | | +| approx_kl | 1.8828642 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.392 | +| explained_variance | -1.02 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 60860 | +| policy_gradient_loss | -0.0676 | +| value_loss | 0.000632 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.99e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 309 | +| iterations | 35 | +| time_elapsed | 115 | +| total_timesteps | 35840 | +| train/ | | +| approx_kl | 2.1697845 | +| clip_fraction | 0.515 | +| clip_range | 0.2 | +| entropy_loss | -0.536 | +| explained_variance | -1.08 | +| learning_rate | 0.0001 | +| loss | -0.0783 | +| n_updates | 60870 | +| policy_gradient_loss | -0.0624 | +| value_loss | 0.000465 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.99e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 309 | +| iterations | 36 | +| time_elapsed | 119 | +| total_timesteps | 36864 | +| train/ | | +| approx_kl | 2.8276145 | +| clip_fraction | 0.518 | +| clip_range | 0.2 | +| entropy_loss | -0.448 | +| explained_variance | -1.76 | +| learning_rate | 0.0001 | +| loss | -0.0849 | +| n_updates | 60880 | +| policy_gradient_loss | -0.0606 | +| value_loss | 0.000336 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.97e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 309 | +| iterations | 37 | +| time_elapsed | 122 | +| total_timesteps | 37888 | +| train/ | | +| approx_kl | 1.7537458 | +| clip_fraction | 0.514 | +| clip_range | 0.2 | +| entropy_loss | -0.463 | +| explained_variance | -0.856 | +| learning_rate | 0.0001 | +| loss | -0.0625 | +| n_updates | 60890 | +| policy_gradient_loss | -0.06 | +| value_loss | 0.000477 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.97e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 308 | +| iterations | 38 | +| time_elapsed | 126 | +| total_timesteps | 38912 | +| train/ | | +| approx_kl | 1.3888268 | +| clip_fraction | 0.496 | +| clip_range | 0.2 | +| entropy_loss | -0.487 | +| explained_variance | -2.87 | +| learning_rate | 0.0001 | +| loss | -0.0846 | +| n_updates | 60900 | +| policy_gradient_loss | -0.0617 | +| value_loss | 0.00031 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.99e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 308 | +| iterations | 39 | +| time_elapsed | 129 | +| total_timesteps | 39936 | +| train/ | | +| approx_kl | 2.2796712 | +| clip_fraction | 0.496 | +| clip_range | 0.2 | +| entropy_loss | -0.379 | +| explained_variance | -1.25 | +| learning_rate | 0.0001 | +| loss | -0.0954 | +| n_updates | 60910 | +| policy_gradient_loss | -0.0597 | +| value_loss | 0.000547 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.99e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 309 | +| iterations | 40 | +| time_elapsed | 132 | +| total_timesteps | 40960 | +| train/ | | +| approx_kl | 1.452177 | +| clip_fraction | 0.523 | +| clip_range | 0.2 | +| entropy_loss | -0.547 | +| explained_variance | -3.79 | +| learning_rate | 0.0001 | +| loss | -0.0999 | +| n_updates | 60920 | +| policy_gradient_loss | -0.0682 | +| value_loss | 0.0002 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.99e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 309 | +| iterations | 41 | +| time_elapsed | 135 | +| total_timesteps | 41984 | +| train/ | | +| approx_kl | 1.4080222 | +| clip_fraction | 0.511 | +| clip_range | 0.2 | +| entropy_loss | -0.494 | +| explained_variance | -1.69 | +| learning_rate | 0.0001 | +| loss | -0.0841 | +| n_updates | 60930 | +| policy_gradient_loss | -0.0587 | +| value_loss | 0.000172 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.03e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 309 | +| iterations | 42 | +| time_elapsed | 138 | +| total_timesteps | 43008 | +| train/ | | +| approx_kl | 1.7915142 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.379 | +| explained_variance | -0.786 | +| learning_rate | 0.0001 | +| loss | -0.0846 | +| n_updates | 60940 | +| policy_gradient_loss | -0.065 | +| value_loss | 0.000579 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.03e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 310 | +| iterations | 43 | +| time_elapsed | 141 | +| total_timesteps | 44032 | +| train/ | | +| approx_kl | 1.8960822 | +| clip_fraction | 0.476 | +| clip_range | 0.2 | +| entropy_loss | -0.456 | +| explained_variance | -2.49 | +| learning_rate | 0.0001 | +| loss | -0.0973 | +| n_updates | 60950 | +| policy_gradient_loss | -0.0586 | +| value_loss | 0.000388 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.02e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 310 | +| iterations | 44 | +| time_elapsed | 145 | +| total_timesteps | 45056 | +| train/ | | +| approx_kl | 1.1823668 | +| clip_fraction | 0.502 | +| clip_range | 0.2 | +| entropy_loss | -0.493 | +| explained_variance | -1.83 | +| learning_rate | 0.0001 | +| loss | -0.0697 | +| n_updates | 60960 | +| policy_gradient_loss | -0.0642 | +| value_loss | 0.000191 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.98e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 310 | +| iterations | 45 | +| time_elapsed | 148 | +| total_timesteps | 46080 | +| train/ | | +| approx_kl | 1.1802037 | +| clip_fraction | 0.446 | +| clip_range | 0.2 | +| entropy_loss | -0.505 | +| explained_variance | -0.21 | +| learning_rate | 0.0001 | +| loss | -0.0592 | +| n_updates | 60970 | +| policy_gradient_loss | -0.0481 | +| value_loss | 0.00012 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.98e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 310 | +| iterations | 46 | +| time_elapsed | 151 | +| total_timesteps | 47104 | +| train/ | | +| approx_kl | 2.83764 | +| clip_fraction | 0.531 | +| clip_range | 0.2 | +| entropy_loss | -0.424 | +| explained_variance | -0.252 | +| learning_rate | 0.0001 | +| loss | -0.0854 | +| n_updates | 60980 | +| policy_gradient_loss | -0.0596 | +| value_loss | 0.000939 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.97e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 311 | +| iterations | 47 | +| time_elapsed | 154 | +| total_timesteps | 48128 | +| train/ | | +| approx_kl | 2.5625358 | +| clip_fraction | 0.484 | +| clip_range | 0.2 | +| entropy_loss | -0.419 | +| explained_variance | -1.99 | +| learning_rate | 0.0001 | +| loss | -0.0812 | +| n_updates | 60990 | +| policy_gradient_loss | -0.058 | +| value_loss | 0.000651 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.95e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 311 | +| iterations | 48 | +| time_elapsed | 157 | +| total_timesteps | 49152 | +| train/ | | +| approx_kl | 1.3189045 | +| clip_fraction | 0.482 | +| clip_range | 0.2 | +| entropy_loss | -0.433 | +| explained_variance | -2.74 | +| learning_rate | 0.0001 | +| loss | -0.0667 | +| n_updates | 61000 | +| policy_gradient_loss | -0.0648 | +| value_loss | 0.00041 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.95e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 311 | +| iterations | 49 | +| time_elapsed | 161 | +| total_timesteps | 50176 | +| train/ | | +| approx_kl | 1.5028002 | +| clip_fraction | 0.484 | +| clip_range | 0.2 | +| entropy_loss | -0.441 | +| explained_variance | -0.827 | +| learning_rate | 0.0001 | +| loss | -0.0792 | +| n_updates | 61010 | +| policy_gradient_loss | -0.0556 | +| value_loss | 0.00056 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.95e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 311 | +| iterations | 50 | +| time_elapsed | 164 | +| total_timesteps | 51200 | +| train/ | | +| approx_kl | 2.4161665 | +| clip_fraction | 0.497 | +| clip_range | 0.2 | +| entropy_loss | -0.442 | +| explained_variance | -3 | +| learning_rate | 0.0001 | +| loss | -0.0681 | +| n_updates | 61020 | +| policy_gradient_loss | -0.0636 | +| value_loss | 0.000446 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.98e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 311 | +| iterations | 51 | +| time_elapsed | 167 | +| total_timesteps | 52224 | +| train/ | | +| approx_kl | 1.5371432 | +| clip_fraction | 0.463 | +| clip_range | 0.2 | +| entropy_loss | -0.524 | +| explained_variance | -3 | +| learning_rate | 0.0001 | +| loss | -0.0967 | +| n_updates | 61030 | +| policy_gradient_loss | -0.0618 | +| value_loss | 0.000534 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.97e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 311 | +| iterations | 52 | +| time_elapsed | 170 | +| total_timesteps | 53248 | +| train/ | | +| approx_kl | 1.76951 | +| clip_fraction | 0.504 | +| clip_range | 0.2 | +| entropy_loss | -0.447 | +| explained_variance | -1.43 | +| learning_rate | 0.0001 | +| loss | -0.105 | +| n_updates | 61040 | +| policy_gradient_loss | -0.0591 | +| value_loss | 0.000517 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.97e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 311 | +| iterations | 53 | +| time_elapsed | 174 | +| total_timesteps | 54272 | +| train/ | | +| approx_kl | 1.5439987 | +| clip_fraction | 0.515 | +| clip_range | 0.2 | +| entropy_loss | -0.512 | +| explained_variance | -0.601 | +| learning_rate | 0.0001 | +| loss | -0.0694 | +| n_updates | 61050 | +| policy_gradient_loss | -0.0574 | +| value_loss | 0.000355 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.95e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 310 | +| iterations | 54 | +| time_elapsed | 177 | +| total_timesteps | 55296 | +| train/ | | +| approx_kl | 1.8297842 | +| clip_fraction | 0.503 | +| clip_range | 0.2 | +| entropy_loss | -0.431 | +| explained_variance | -2.18 | +| learning_rate | 0.0001 | +| loss | -0.0433 | +| n_updates | 61060 | +| policy_gradient_loss | -0.0648 | +| value_loss | 0.000502 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.95e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 310 | +| iterations | 55 | +| time_elapsed | 181 | +| total_timesteps | 56320 | +| train/ | | +| approx_kl | 2.6044598 | +| clip_fraction | 0.518 | +| clip_range | 0.2 | +| entropy_loss | -0.521 | +| explained_variance | -0.452 | +| learning_rate | 0.0001 | +| loss | -0.0771 | +| n_updates | 61070 | +| policy_gradient_loss | -0.0604 | +| value_loss | 0.00049 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.96e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 310 | +| iterations | 56 | +| time_elapsed | 184 | +| total_timesteps | 57344 | +| train/ | | +| approx_kl | 1.9317738 | +| clip_fraction | 0.511 | +| clip_range | 0.2 | +| entropy_loss | -0.472 | +| explained_variance | -2.51 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 61080 | +| policy_gradient_loss | -0.0737 | +| value_loss | 0.0006 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.96e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 310 | +| iterations | 57 | +| time_elapsed | 188 | +| total_timesteps | 58368 | +| train/ | | +| approx_kl | 1.7658124 | +| clip_fraction | 0.5 | +| clip_range | 0.2 | +| entropy_loss | -0.441 | +| explained_variance | -2.55 | +| learning_rate | 0.0001 | +| loss | -0.0799 | +| n_updates | 61090 | +| policy_gradient_loss | -0.0601 | +| value_loss | 0.000395 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.97e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 310 | +| iterations | 58 | +| time_elapsed | 191 | +| total_timesteps | 59392 | +| train/ | | +| approx_kl | 1.5546687 | +| clip_fraction | 0.511 | +| clip_range | 0.2 | +| entropy_loss | -0.504 | +| explained_variance | -0.892 | +| learning_rate | 0.0001 | +| loss | -0.0781 | +| n_updates | 61100 | +| policy_gradient_loss | -0.0694 | +| value_loss | 0.000568 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.97e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 311 | +| iterations | 59 | +| time_elapsed | 194 | +| total_timesteps | 60416 | +| train/ | | +| approx_kl | 2.12842 | +| clip_fraction | 0.463 | +| clip_range | 0.2 | +| entropy_loss | -0.435 | +| explained_variance | -2.31 | +| learning_rate | 0.0001 | +| loss | -0.0588 | +| n_updates | 61110 | +| policy_gradient_loss | -0.0647 | +| value_loss | 0.00063 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.97e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 311 | +| iterations | 60 | +| time_elapsed | 197 | +| total_timesteps | 61440 | +| train/ | | +| approx_kl | 1.796809 | +| clip_fraction | 0.532 | +| clip_range | 0.2 | +| entropy_loss | -0.481 | +| explained_variance | -0.797 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 61120 | +| policy_gradient_loss | -0.0721 | +| value_loss | 0.000526 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.95e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 311 | +| iterations | 61 | +| time_elapsed | 200 | +| total_timesteps | 62464 | +| train/ | | +| approx_kl | 1.9742922 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.471 | +| explained_variance | -1.17 | +| learning_rate | 0.0001 | +| loss | -0.0864 | +| n_updates | 61130 | +| policy_gradient_loss | -0.0598 | +| value_loss | 0.000545 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.95e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 311 | +| iterations | 62 | +| time_elapsed | 203 | +| total_timesteps | 63488 | +| train/ | | +| approx_kl | 1.1803893 | +| clip_fraction | 0.508 | +| clip_range | 0.2 | +| entropy_loss | -0.513 | +| explained_variance | -0.621 | +| learning_rate | 0.0001 | +| loss | -0.0829 | +| n_updates | 61140 | +| policy_gradient_loss | -0.066 | +| value_loss | 0.000712 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.95e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 312 | +| iterations | 63 | +| time_elapsed | 206 | +| total_timesteps | 64512 | +| train/ | | +| approx_kl | 1.7401277 | +| clip_fraction | 0.516 | +| clip_range | 0.2 | +| entropy_loss | -0.486 | +| explained_variance | -1.21 | +| learning_rate | 0.0001 | +| loss | -0.0911 | +| n_updates | 61150 | +| policy_gradient_loss | -0.067 | +| value_loss | 0.000579 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.95e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 312 | +| iterations | 64 | +| time_elapsed | 209 | +| total_timesteps | 65536 | +| train/ | | +| approx_kl | 2.095352 | +| clip_fraction | 0.507 | +| clip_range | 0.2 | +| entropy_loss | -0.446 | +| explained_variance | -1.1 | +| learning_rate | 0.0001 | +| loss | -0.0888 | +| n_updates | 61160 | +| policy_gradient_loss | -0.0633 | +| value_loss | 0.000837 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.95e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 312 | +| iterations | 65 | +| time_elapsed | 212 | +| total_timesteps | 66560 | +| train/ | | +| approx_kl | 1.2082384 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.457 | +| explained_variance | -3.05 | +| learning_rate | 0.0001 | +| loss | -0.0673 | +| n_updates | 61170 | +| policy_gradient_loss | -0.0662 | +| value_loss | 0.000279 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.98e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 312 | +| iterations | 66 | +| time_elapsed | 215 | +| total_timesteps | 67584 | +| train/ | | +| approx_kl | 3.208849 | +| clip_fraction | 0.534 | +| clip_range | 0.2 | +| entropy_loss | -0.557 | +| explained_variance | -0.985 | +| learning_rate | 0.0001 | +| loss | -0.0661 | +| n_updates | 61180 | +| policy_gradient_loss | -0.071 | +| value_loss | 0.00025 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.98e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 313 | +| iterations | 67 | +| time_elapsed | 219 | +| total_timesteps | 68608 | +| train/ | | +| approx_kl | 1.8093916 | +| clip_fraction | 0.508 | +| clip_range | 0.2 | +| entropy_loss | -0.53 | +| explained_variance | -0.644 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 61190 | +| policy_gradient_loss | -0.0682 | +| value_loss | 0.000711 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.96e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 313 | +| iterations | 68 | +| time_elapsed | 222 | +| total_timesteps | 69632 | +| train/ | | +| approx_kl | 1.7759354 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.463 | +| explained_variance | -1.28 | +| learning_rate | 0.0001 | +| loss | -0.0719 | +| n_updates | 61200 | +| policy_gradient_loss | -0.0564 | +| value_loss | 0.000597 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.96e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 312 | +| iterations | 69 | +| time_elapsed | 225 | +| total_timesteps | 70656 | +| train/ | | +| approx_kl | 1.4087964 | +| clip_fraction | 0.518 | +| clip_range | 0.2 | +| entropy_loss | -0.578 | +| explained_variance | -0.96 | +| learning_rate | 0.0001 | +| loss | -0.0903 | +| n_updates | 61210 | +| policy_gradient_loss | -0.0714 | +| value_loss | 0.000397 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.96e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 312 | +| iterations | 70 | +| time_elapsed | 229 | +| total_timesteps | 71680 | +| train/ | | +| approx_kl | 1.532946 | +| clip_fraction | 0.499 | +| clip_range | 0.2 | +| entropy_loss | -0.563 | +| explained_variance | -0.919 | +| learning_rate | 0.0001 | +| loss | -0.0968 | +| n_updates | 61220 | +| policy_gradient_loss | -0.0585 | +| value_loss | 0.000427 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.95e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 312 | +| iterations | 71 | +| time_elapsed | 232 | +| total_timesteps | 72704 | +| train/ | | +| approx_kl | 1.3848667 | +| clip_fraction | 0.5 | +| clip_range | 0.2 | +| entropy_loss | -0.476 | +| explained_variance | -0.764 | +| learning_rate | 0.0001 | +| loss | -0.0985 | +| n_updates | 61230 | +| policy_gradient_loss | -0.071 | +| value_loss | 0.000816 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.95e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 312 | +| iterations | 72 | +| time_elapsed | 235 | +| total_timesteps | 73728 | +| train/ | | +| approx_kl | 1.8494357 | +| clip_fraction | 0.511 | +| clip_range | 0.2 | +| entropy_loss | -0.498 | +| explained_variance | -1.42 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 61240 | +| policy_gradient_loss | -0.0692 | +| value_loss | 0.000405 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.95e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 312 | +| iterations | 73 | +| time_elapsed | 239 | +| total_timesteps | 74752 | +| train/ | | +| approx_kl | 1.7077079 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.464 | +| explained_variance | -1.56 | +| learning_rate | 0.0001 | +| loss | -0.0976 | +| n_updates | 61250 | +| policy_gradient_loss | -0.0727 | +| value_loss | 0.000454 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.95e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 311 | +| iterations | 74 | +| time_elapsed | 242 | +| total_timesteps | 75776 | +| train/ | | +| approx_kl | 1.3445895 | +| clip_fraction | 0.493 | +| clip_range | 0.2 | +| entropy_loss | -0.478 | +| explained_variance | -0.949 | +| learning_rate | 0.0001 | +| loss | -0.0431 | +| n_updates | 61260 | +| policy_gradient_loss | -0.0664 | +| value_loss | 0.000489 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.96e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 311 | +| iterations | 75 | +| time_elapsed | 246 | +| total_timesteps | 76800 | +| train/ | | +| approx_kl | 1.8408852 | +| clip_fraction | 0.519 | +| clip_range | 0.2 | +| entropy_loss | -0.538 | +| explained_variance | -0.785 | +| learning_rate | 0.0001 | +| loss | -0.0963 | +| n_updates | 61270 | +| policy_gradient_loss | -0.0608 | +| value_loss | 0.000409 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.96e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 311 | +| iterations | 76 | +| time_elapsed | 249 | +| total_timesteps | 77824 | +| train/ | | +| approx_kl | 1.3425887 | +| clip_fraction | 0.492 | +| clip_range | 0.2 | +| entropy_loss | -0.53 | +| explained_variance | -0.595 | +| learning_rate | 0.0001 | +| loss | -0.0846 | +| n_updates | 61280 | +| policy_gradient_loss | -0.0582 | +| value_loss | 0.000164 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.95e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 311 | +| iterations | 77 | +| time_elapsed | 253 | +| total_timesteps | 78848 | +| train/ | | +| approx_kl | 1.4747338 | +| clip_fraction | 0.512 | +| clip_range | 0.2 | +| entropy_loss | -0.502 | +| explained_variance | -4 | +| learning_rate | 0.0001 | +| loss | -0.0992 | +| n_updates | 61290 | +| policy_gradient_loss | -0.0726 | +| value_loss | 0.000158 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.95e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 311 | +| iterations | 78 | +| time_elapsed | 256 | +| total_timesteps | 79872 | +| train/ | | +| approx_kl | 1.6268996 | +| clip_fraction | 0.474 | +| clip_range | 0.2 | +| entropy_loss | -0.539 | +| explained_variance | -1.21 | +| learning_rate | 0.0001 | +| loss | -0.055 | +| n_updates | 61300 | +| policy_gradient_loss | -0.0583 | +| value_loss | 0.000459 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.96e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 311 | +| iterations | 79 | +| time_elapsed | 259 | +| total_timesteps | 80896 | +| train/ | | +| approx_kl | 1.1267136 | +| clip_fraction | 0.537 | +| clip_range | 0.2 | +| entropy_loss | -0.712 | +| explained_variance | -0.313 | +| learning_rate | 0.0001 | +| loss | -0.0826 | +| n_updates | 61310 | +| policy_gradient_loss | -0.0641 | +| value_loss | 0.000473 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.96e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 312 | +| iterations | 80 | +| time_elapsed | 262 | +| total_timesteps | 81920 | +| train/ | | +| approx_kl | 0.9900164 | +| clip_fraction | 0.49 | +| clip_range | 0.2 | +| entropy_loss | -0.549 | +| explained_variance | -0.883 | +| learning_rate | 0.0001 | +| loss | -0.076 | +| n_updates | 61320 | +| policy_gradient_loss | -0.0647 | +| value_loss | 0.000733 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.97e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 312 | +| iterations | 81 | +| time_elapsed | 265 | +| total_timesteps | 82944 | +| train/ | | +| approx_kl | 1.2784488 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.543 | +| explained_variance | -6.82 | +| learning_rate | 0.0001 | +| loss | -0.0761 | +| n_updates | 61330 | +| policy_gradient_loss | -0.0656 | +| value_loss | 0.000362 | +--------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.95e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 312 | +| iterations | 82 | +| time_elapsed | 268 | +| total_timesteps | 83968 | +| train/ | | +| approx_kl | 0.95692396 | +| clip_fraction | 0.495 | +| clip_range | 0.2 | +| entropy_loss | -0.546 | +| explained_variance | -5.28 | +| learning_rate | 0.0001 | +| loss | -0.108 | +| n_updates | 61340 | +| policy_gradient_loss | -0.0625 | +| value_loss | 0.000346 | +---------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.93e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 312 | +| iterations | 83 | +| time_elapsed | 272 | +| total_timesteps | 84992 | +| train/ | | +| approx_kl | 1.5917959 | +| clip_fraction | 0.529 | +| clip_range | 0.2 | +| entropy_loss | -0.564 | +| explained_variance | -0.389 | +| learning_rate | 0.0001 | +| loss | -0.0533 | +| n_updates | 61350 | +| policy_gradient_loss | -0.0647 | +| value_loss | 0.000738 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.93e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 312 | +| iterations | 84 | +| time_elapsed | 275 | +| total_timesteps | 86016 | +| train/ | | +| approx_kl | 1.6318542 | +| clip_fraction | 0.5 | +| clip_range | 0.2 | +| entropy_loss | -0.58 | +| explained_variance | -0.41 | +| learning_rate | 0.0001 | +| loss | -0.0939 | +| n_updates | 61360 | +| policy_gradient_loss | -0.0686 | +| value_loss | 0.000978 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.91e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 312 | +| iterations | 85 | +| time_elapsed | 278 | +| total_timesteps | 87040 | +| train/ | | +| approx_kl | 1.2089365 | +| clip_fraction | 0.47 | +| clip_range | 0.2 | +| entropy_loss | -0.477 | +| explained_variance | -1.75 | +| learning_rate | 0.0001 | +| loss | -0.0915 | +| n_updates | 61370 | +| policy_gradient_loss | -0.0679 | +| value_loss | 0.00105 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.91e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 312 | +| iterations | 86 | +| time_elapsed | 281 | +| total_timesteps | 88064 | +| train/ | | +| approx_kl | 1.5222851 | +| clip_fraction | 0.521 | +| clip_range | 0.2 | +| entropy_loss | -0.605 | +| explained_variance | -1.35 | +| learning_rate | 0.0001 | +| loss | -0.0927 | +| n_updates | 61380 | +| policy_gradient_loss | -0.0687 | +| value_loss | 0.000525 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.92e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 312 | +| iterations | 87 | +| time_elapsed | 285 | +| total_timesteps | 89088 | +| train/ | | +| approx_kl | 1.6046965 | +| clip_fraction | 0.515 | +| clip_range | 0.2 | +| entropy_loss | -0.545 | +| explained_variance | -1.14 | +| learning_rate | 0.0001 | +| loss | -0.0969 | +| n_updates | 61390 | +| policy_gradient_loss | -0.071 | +| value_loss | 0.000509 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.91e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 311 | +| iterations | 88 | +| time_elapsed | 288 | +| total_timesteps | 90112 | +| train/ | | +| approx_kl | 1.3549314 | +| clip_fraction | 0.521 | +| clip_range | 0.2 | +| entropy_loss | -0.578 | +| explained_variance | -2.03 | +| learning_rate | 0.0001 | +| loss | -0.0965 | +| n_updates | 61400 | +| policy_gradient_loss | -0.0627 | +| value_loss | 0.000246 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.91e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 311 | +| iterations | 89 | +| time_elapsed | 292 | +| total_timesteps | 91136 | +| train/ | | +| approx_kl | 1.3737867 | +| clip_fraction | 0.529 | +| clip_range | 0.2 | +| entropy_loss | -0.57 | +| explained_variance | -0.564 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 61410 | +| policy_gradient_loss | -0.0705 | +| value_loss | 0.000549 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.9e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 311 | +| iterations | 90 | +| time_elapsed | 295 | +| total_timesteps | 92160 | +| train/ | | +| approx_kl | 1.6841245 | +| clip_fraction | 0.496 | +| clip_range | 0.2 | +| entropy_loss | -0.482 | +| explained_variance | -1.48 | +| learning_rate | 0.0001 | +| loss | -0.0925 | +| n_updates | 61420 | +| policy_gradient_loss | -0.0628 | +| value_loss | 0.000503 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.9e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 311 | +| iterations | 91 | +| time_elapsed | 299 | +| total_timesteps | 93184 | +| train/ | | +| approx_kl | 1.9350884 | +| clip_fraction | 0.479 | +| clip_range | 0.2 | +| entropy_loss | -0.497 | +| explained_variance | -0.866 | +| learning_rate | 0.0001 | +| loss | -0.0567 | +| n_updates | 61430 | +| policy_gradient_loss | -0.0368 | +| value_loss | 0.000296 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.91e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 310 | +| iterations | 92 | +| time_elapsed | 302 | +| total_timesteps | 94208 | +| train/ | | +| approx_kl | 2.8683677 | +| clip_fraction | 0.486 | +| clip_range | 0.2 | +| entropy_loss | -0.401 | +| explained_variance | -0.328 | +| learning_rate | 0.0001 | +| loss | -0.0943 | +| n_updates | 61440 | +| policy_gradient_loss | -0.0707 | +| value_loss | 0.000704 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.91e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 310 | +| iterations | 93 | +| time_elapsed | 306 | +| total_timesteps | 95232 | +| train/ | | +| approx_kl | 1.8583369 | +| clip_fraction | 0.504 | +| clip_range | 0.2 | +| entropy_loss | -0.503 | +| explained_variance | -1.04 | +| learning_rate | 0.0001 | +| loss | -0.0656 | +| n_updates | 61450 | +| policy_gradient_loss | -0.0615 | +| value_loss | 0.000474 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.91e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 310 | +| iterations | 94 | +| time_elapsed | 309 | +| total_timesteps | 96256 | +| train/ | | +| approx_kl | 1.0132525 | +| clip_fraction | 0.511 | +| clip_range | 0.2 | +| entropy_loss | -0.587 | +| explained_variance | -2.09 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 61460 | +| policy_gradient_loss | -0.0588 | +| value_loss | 0.000336 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.91e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 310 | +| iterations | 95 | +| time_elapsed | 312 | +| total_timesteps | 97280 | +| train/ | | +| approx_kl | 1.088555 | +| clip_fraction | 0.477 | +| clip_range | 0.2 | +| entropy_loss | -0.518 | +| explained_variance | -1.34 | +| learning_rate | 0.0001 | +| loss | -0.0951 | +| n_updates | 61470 | +| policy_gradient_loss | -0.059 | +| value_loss | 0.000422 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.92e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 311 | +| iterations | 96 | +| time_elapsed | 315 | +| total_timesteps | 98304 | +| train/ | | +| approx_kl | 1.8404878 | +| clip_fraction | 0.496 | +| clip_range | 0.2 | +| entropy_loss | -0.43 | +| explained_variance | -0.924 | +| learning_rate | 0.0001 | +| loss | -0.0569 | +| n_updates | 61480 | +| policy_gradient_loss | -0.0661 | +| value_loss | 0.000703 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.92e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 311 | +| iterations | 97 | +| time_elapsed | 319 | +| total_timesteps | 99328 | +| train/ | | +| approx_kl | 2.0784028 | +| clip_fraction | 0.506 | +| clip_range | 0.2 | +| entropy_loss | -0.517 | +| explained_variance | -1.55 | +| learning_rate | 0.0001 | +| loss | -0.0749 | +| n_updates | 61490 | +| policy_gradient_loss | -0.0545 | +| value_loss | 0.00068 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.91e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 311 | +| iterations | 98 | +| time_elapsed | 322 | +| total_timesteps | 100352 | +| train/ | | +| approx_kl | 1.9000444 | +| clip_fraction | 0.518 | +| clip_range | 0.2 | +| entropy_loss | -0.505 | +| explained_variance | -4.91 | +| learning_rate | 0.0001 | +| loss | -0.0808 | +| n_updates | 61500 | +| policy_gradient_loss | -0.0658 | +| value_loss | 0.000294 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.91e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 311 | +| iterations | 99 | +| time_elapsed | 325 | +| total_timesteps | 101376 | +| train/ | | +| approx_kl | 2.7779183 | +| clip_fraction | 0.563 | +| clip_range | 0.2 | +| entropy_loss | -0.491 | +| explained_variance | -0.795 | +| learning_rate | 0.0001 | +| loss | -0.0861 | +| n_updates | 61510 | +| policy_gradient_loss | -0.0679 | +| value_loss | 0.000386 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.93e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 311 | +| iterations | 100 | +| time_elapsed | 328 | +| total_timesteps | 102400 | +| train/ | | +| approx_kl | 1.3231187 | +| clip_fraction | 0.518 | +| clip_range | 0.2 | +| entropy_loss | -0.572 | +| explained_variance | -4.22 | +| learning_rate | 0.0001 | +| loss | -0.118 | +| n_updates | 61520 | +| policy_gradient_loss | -0.0684 | +| value_loss | 0.000439 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.93e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 312 | +| iterations | 101 | +| time_elapsed | 331 | +| total_timesteps | 103424 | +| train/ | | +| approx_kl | 1.1351614 | +| clip_fraction | 0.492 | +| clip_range | 0.2 | +| entropy_loss | -0.599 | +| explained_variance | -1.86 | +| learning_rate | 0.0001 | +| loss | -0.079 | +| n_updates | 61530 | +| policy_gradient_loss | -0.0625 | +| value_loss | 0.000288 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.93e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 312 | +| iterations | 102 | +| time_elapsed | 334 | +| total_timesteps | 104448 | +| train/ | | +| approx_kl | 1.4344678 | +| clip_fraction | 0.537 | +| clip_range | 0.2 | +| entropy_loss | -0.561 | +| explained_variance | -0.568 | +| learning_rate | 0.0001 | +| loss | -0.0978 | +| n_updates | 61540 | +| policy_gradient_loss | -0.065 | +| value_loss | 0.00021 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.93e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 312 | +| iterations | 103 | +| time_elapsed | 337 | +| total_timesteps | 105472 | +| train/ | | +| approx_kl | 3.327394 | +| clip_fraction | 0.505 | +| clip_range | 0.2 | +| entropy_loss | -0.475 | +| explained_variance | -0.912 | +| learning_rate | 0.0001 | +| loss | -0.12 | +| n_updates | 61550 | +| policy_gradient_loss | -0.0674 | +| value_loss | 0.000396 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.92e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 312 | +| iterations | 104 | +| time_elapsed | 340 | +| total_timesteps | 106496 | +| train/ | | +| approx_kl | 1.4421798 | +| clip_fraction | 0.458 | +| clip_range | 0.2 | +| entropy_loss | -0.429 | +| explained_variance | -1.33 | +| learning_rate | 0.0001 | +| loss | -0.0836 | +| n_updates | 61560 | +| policy_gradient_loss | -0.0601 | +| value_loss | 0.000654 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.92e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 312 | +| iterations | 105 | +| time_elapsed | 344 | +| total_timesteps | 107520 | +| train/ | | +| approx_kl | 1.6579039 | +| clip_fraction | 0.449 | +| clip_range | 0.2 | +| entropy_loss | -0.389 | +| explained_variance | -3.97 | +| learning_rate | 0.0001 | +| loss | -0.0803 | +| n_updates | 61570 | +| policy_gradient_loss | -0.0614 | +| value_loss | 0.000345 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.92e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 312 | +| iterations | 106 | +| time_elapsed | 347 | +| total_timesteps | 108544 | +| train/ | | +| approx_kl | 2.129111 | +| clip_fraction | 0.507 | +| clip_range | 0.2 | +| entropy_loss | -0.447 | +| explained_variance | -0.541 | +| learning_rate | 0.0001 | +| loss | -0.0902 | +| n_updates | 61580 | +| policy_gradient_loss | -0.063 | +| value_loss | 0.000821 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.92e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 311 | +| iterations | 107 | +| time_elapsed | 351 | +| total_timesteps | 109568 | +| train/ | | +| approx_kl | 1.6481483 | +| clip_fraction | 0.494 | +| clip_range | 0.2 | +| entropy_loss | -0.44 | +| explained_variance | -2.77 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 61590 | +| policy_gradient_loss | -0.0741 | +| value_loss | 0.000457 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.93e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 311 | +| iterations | 108 | +| time_elapsed | 354 | +| total_timesteps | 110592 | +| train/ | | +| approx_kl | 1.6480682 | +| clip_fraction | 0.458 | +| clip_range | 0.2 | +| entropy_loss | -0.382 | +| explained_variance | -1.53 | +| learning_rate | 0.0001 | +| loss | -0.089 | +| n_updates | 61600 | +| policy_gradient_loss | -0.0562 | +| value_loss | 0.000479 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.92e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 311 | +| iterations | 109 | +| time_elapsed | 357 | +| total_timesteps | 111616 | +| train/ | | +| approx_kl | 1.7265146 | +| clip_fraction | 0.498 | +| clip_range | 0.2 | +| entropy_loss | -0.434 | +| explained_variance | -0.886 | +| learning_rate | 0.0001 | +| loss | -0.0765 | +| n_updates | 61610 | +| policy_gradient_loss | -0.0608 | +| value_loss | 0.000254 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.92e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 311 | +| iterations | 110 | +| time_elapsed | 361 | +| total_timesteps | 112640 | +| train/ | | +| approx_kl | 1.3687999 | +| clip_fraction | 0.482 | +| clip_range | 0.2 | +| entropy_loss | -0.484 | +| explained_variance | -1.7 | +| learning_rate | 0.0001 | +| loss | -0.0989 | +| n_updates | 61620 | +| policy_gradient_loss | -0.0705 | +| value_loss | 0.000482 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.91e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 311 | +| iterations | 111 | +| time_elapsed | 364 | +| total_timesteps | 113664 | +| train/ | | +| approx_kl | 1.6394086 | +| clip_fraction | 0.506 | +| clip_range | 0.2 | +| entropy_loss | -0.444 | +| explained_variance | -1.43 | +| learning_rate | 0.0001 | +| loss | -0.0772 | +| n_updates | 61630 | +| policy_gradient_loss | -0.0682 | +| value_loss | 0.000598 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.91e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 311 | +| iterations | 112 | +| time_elapsed | 368 | +| total_timesteps | 114688 | +| train/ | | +| approx_kl | 1.209552 | +| clip_fraction | 0.463 | +| clip_range | 0.2 | +| entropy_loss | -0.43 | +| explained_variance | -1.56 | +| learning_rate | 0.0001 | +| loss | -0.0793 | +| n_updates | 61640 | +| policy_gradient_loss | -0.0546 | +| value_loss | 0.000432 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.91e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 311 | +| iterations | 113 | +| time_elapsed | 371 | +| total_timesteps | 115712 | +| train/ | | +| approx_kl | 1.0906423 | +| clip_fraction | 0.464 | +| clip_range | 0.2 | +| entropy_loss | -0.516 | +| explained_variance | -2.8 | +| learning_rate | 0.0001 | +| loss | -0.0748 | +| n_updates | 61650 | +| policy_gradient_loss | -0.0544 | +| value_loss | 0.000388 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.91e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 311 | +| iterations | 114 | +| time_elapsed | 374 | +| total_timesteps | 116736 | +| train/ | | +| approx_kl | 1.6220332 | +| clip_fraction | 0.501 | +| clip_range | 0.2 | +| entropy_loss | -0.437 | +| explained_variance | -1.14 | +| learning_rate | 0.0001 | +| loss | -0.0613 | +| n_updates | 61660 | +| policy_gradient_loss | -0.0601 | +| value_loss | 0.000518 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.91e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 312 | +| iterations | 115 | +| time_elapsed | 377 | +| total_timesteps | 117760 | +| train/ | | +| approx_kl | 1.736095 | +| clip_fraction | 0.461 | +| clip_range | 0.2 | +| entropy_loss | -0.413 | +| explained_variance | -0.592 | +| learning_rate | 0.0001 | +| loss | -0.095 | +| n_updates | 61670 | +| policy_gradient_loss | -0.0639 | +| value_loss | 0.00104 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.91e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 312 | +| iterations | 116 | +| time_elapsed | 380 | +| total_timesteps | 118784 | +| train/ | | +| approx_kl | 2.4589636 | +| clip_fraction | 0.513 | +| clip_range | 0.2 | +| entropy_loss | -0.432 | +| explained_variance | -1.73 | +| learning_rate | 0.0001 | +| loss | -0.0998 | +| n_updates | 61680 | +| policy_gradient_loss | -0.0743 | +| value_loss | 0.000769 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.92e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 312 | +| iterations | 117 | +| time_elapsed | 383 | +| total_timesteps | 119808 | +| train/ | | +| approx_kl | 2.11278 | +| clip_fraction | 0.482 | +| clip_range | 0.2 | +| entropy_loss | -0.453 | +| explained_variance | -3.85 | +| learning_rate | 0.0001 | +| loss | -0.0854 | +| n_updates | 61690 | +| policy_gradient_loss | -0.0654 | +| value_loss | 0.000421 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.92e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 312 | +| iterations | 118 | +| time_elapsed | 386 | +| total_timesteps | 120832 | +| train/ | | +| approx_kl | 3.2765508 | +| clip_fraction | 0.436 | +| clip_range | 0.2 | +| entropy_loss | -0.38 | +| explained_variance | -7.74 | +| learning_rate | 0.0001 | +| loss | -0.0748 | +| n_updates | 61700 | +| policy_gradient_loss | -0.0571 | +| value_loss | 0.000301 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.93e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 312 | +| iterations | 119 | +| time_elapsed | 389 | +| total_timesteps | 121856 | +| train/ | | +| approx_kl | 1.5033191 | +| clip_fraction | 0.512 | +| clip_range | 0.2 | +| entropy_loss | -0.527 | +| explained_variance | -0.51 | +| learning_rate | 0.0001 | +| loss | -0.0833 | +| n_updates | 61710 | +| policy_gradient_loss | -0.0555 | +| value_loss | 0.000652 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.93e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 312 | +| iterations | 120 | +| time_elapsed | 393 | +| total_timesteps | 122880 | +| train/ | | +| approx_kl | 1.7355694 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.558 | +| explained_variance | -0.271 | +| learning_rate | 0.0001 | +| loss | -0.0775 | +| n_updates | 61720 | +| policy_gradient_loss | -0.0513 | +| value_loss | 0.000302 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.93e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 312 | +| iterations | 121 | +| time_elapsed | 396 | +| total_timesteps | 123904 | +| train/ | | +| approx_kl | 1.6828952 | +| clip_fraction | 0.496 | +| clip_range | 0.2 | +| entropy_loss | -0.459 | +| explained_variance | -1.05 | +| learning_rate | 0.0001 | +| loss | -0.0966 | +| n_updates | 61730 | +| policy_gradient_loss | -0.054 | +| value_loss | 0.000469 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.93e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 312 | +| iterations | 122 | +| time_elapsed | 399 | +| total_timesteps | 124928 | +| train/ | | +| approx_kl | 1.3481891 | +| clip_fraction | 0.463 | +| clip_range | 0.2 | +| entropy_loss | -0.442 | +| explained_variance | -1.59 | +| learning_rate | 0.0001 | +| loss | -0.0753 | +| n_updates | 61740 | +| policy_gradient_loss | -0.0589 | +| value_loss | 0.000466 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.93e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 312 | +| iterations | 123 | +| time_elapsed | 403 | +| total_timesteps | 125952 | +| train/ | | +| approx_kl | 1.8716009 | +| clip_fraction | 0.517 | +| clip_range | 0.2 | +| entropy_loss | -0.529 | +| explained_variance | -2.16 | +| learning_rate | 0.0001 | +| loss | -0.0741 | +| n_updates | 61750 | +| policy_gradient_loss | -0.0661 | +| value_loss | 0.000391 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.94e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 312 | +| iterations | 124 | +| time_elapsed | 406 | +| total_timesteps | 126976 | +| train/ | | +| approx_kl | 1.5188603 | +| clip_fraction | 0.53 | +| clip_range | 0.2 | +| entropy_loss | -0.582 | +| explained_variance | -0.577 | +| learning_rate | 0.0001 | +| loss | -0.091 | +| n_updates | 61760 | +| policy_gradient_loss | -0.0725 | +| value_loss | 0.000624 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.94e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 312 | +| iterations | 125 | +| time_elapsed | 409 | +| total_timesteps | 128000 | +| train/ | | +| approx_kl | 1.4086642 | +| clip_fraction | 0.504 | +| clip_range | 0.2 | +| entropy_loss | -0.616 | +| explained_variance | -1.1 | +| learning_rate | 0.0001 | +| loss | -0.111 | +| n_updates | 61770 | +| policy_gradient_loss | -0.0699 | +| value_loss | 0.000444 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.94e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 312 | +| iterations | 126 | +| time_elapsed | 413 | +| total_timesteps | 129024 | +| train/ | | +| approx_kl | 1.9666632 | +| clip_fraction | 0.512 | +| clip_range | 0.2 | +| entropy_loss | -0.407 | +| explained_variance | -1.36 | +| learning_rate | 0.0001 | +| loss | -0.0991 | +| n_updates | 61780 | +| policy_gradient_loss | -0.0696 | +| value_loss | 0.000713 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.94e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 312 | +| iterations | 127 | +| time_elapsed | 416 | +| total_timesteps | 130048 | +| train/ | | +| approx_kl | 1.9326179 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.444 | +| explained_variance | -1.16 | +| learning_rate | 0.0001 | +| loss | -0.0778 | +| n_updates | 61790 | +| policy_gradient_loss | -0.0682 | +| value_loss | 0.000506 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.95e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 312 | +| iterations | 128 | +| time_elapsed | 419 | +| total_timesteps | 131072 | +| train/ | | +| approx_kl | 1.683131 | +| clip_fraction | 0.518 | +| clip_range | 0.2 | +| entropy_loss | -0.478 | +| explained_variance | -1.25 | +| learning_rate | 0.0001 | +| loss | -0.0857 | +| n_updates | 61800 | +| policy_gradient_loss | -0.0588 | +| value_loss | 0.00031 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.95e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 312 | +| iterations | 129 | +| time_elapsed | 422 | +| total_timesteps | 132096 | +| train/ | | +| approx_kl | 1.71979 | +| clip_fraction | 0.466 | +| clip_range | 0.2 | +| entropy_loss | -0.464 | +| explained_variance | -1.43 | +| learning_rate | 0.0001 | +| loss | -0.0931 | +| n_updates | 61810 | +| policy_gradient_loss | -0.0602 | +| value_loss | 0.000273 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.94e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 312 | +| iterations | 130 | +| time_elapsed | 426 | +| total_timesteps | 133120 | +| train/ | | +| approx_kl | 1.815695 | +| clip_fraction | 0.498 | +| clip_range | 0.2 | +| entropy_loss | -0.44 | +| explained_variance | -1.23 | +| learning_rate | 0.0001 | +| loss | -0.108 | +| n_updates | 61820 | +| policy_gradient_loss | -0.0683 | +| value_loss | 0.000384 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.94e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 312 | +| iterations | 131 | +| time_elapsed | 429 | +| total_timesteps | 134144 | +| train/ | | +| approx_kl | 1.4204416 | +| clip_fraction | 0.449 | +| clip_range | 0.2 | +| entropy_loss | -0.409 | +| explained_variance | -1.95 | +| learning_rate | 0.0001 | +| loss | -0.0781 | +| n_updates | 61830 | +| policy_gradient_loss | -0.0556 | +| value_loss | 0.000629 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.95e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 312 | +| iterations | 132 | +| time_elapsed | 432 | +| total_timesteps | 135168 | +| train/ | | +| approx_kl | 1.9612577 | +| clip_fraction | 0.479 | +| clip_range | 0.2 | +| entropy_loss | -0.396 | +| explained_variance | -3.19 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 61840 | +| policy_gradient_loss | -0.0678 | +| value_loss | 0.000345 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.95e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 312 | +| iterations | 133 | +| time_elapsed | 435 | +| total_timesteps | 136192 | +| train/ | | +| approx_kl | 1.5303665 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.468 | +| explained_variance | -0.716 | +| learning_rate | 0.0001 | +| loss | -0.0861 | +| n_updates | 61850 | +| policy_gradient_loss | -0.0542 | +| value_loss | 0.000495 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.95e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 312 | +| iterations | 134 | +| time_elapsed | 438 | +| total_timesteps | 137216 | +| train/ | | +| approx_kl | 1.4657753 | +| clip_fraction | 0.484 | +| clip_range | 0.2 | +| entropy_loss | -0.506 | +| explained_variance | -2.13 | +| learning_rate | 0.0001 | +| loss | -0.0859 | +| n_updates | 61860 | +| policy_gradient_loss | -0.0629 | +| value_loss | 0.00047 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.94e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 312 | +| iterations | 135 | +| time_elapsed | 441 | +| total_timesteps | 138240 | +| train/ | | +| approx_kl | 1.8326538 | +| clip_fraction | 0.476 | +| clip_range | 0.2 | +| entropy_loss | -0.393 | +| explained_variance | -1.6 | +| learning_rate | 0.0001 | +| loss | -0.0581 | +| n_updates | 61870 | +| policy_gradient_loss | -0.0612 | +| value_loss | 0.000536 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.93e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 313 | +| iterations | 136 | +| time_elapsed | 444 | +| total_timesteps | 139264 | +| train/ | | +| approx_kl | 1.6774082 | +| clip_fraction | 0.511 | +| clip_range | 0.2 | +| entropy_loss | -0.464 | +| explained_variance | -1.44 | +| learning_rate | 0.0001 | +| loss | -0.0934 | +| n_updates | 61880 | +| policy_gradient_loss | -0.0649 | +| value_loss | 0.000802 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.93e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 313 | +| iterations | 137 | +| time_elapsed | 447 | +| total_timesteps | 140288 | +| train/ | | +| approx_kl | 1.6015013 | +| clip_fraction | 0.485 | +| clip_range | 0.2 | +| entropy_loss | -0.473 | +| explained_variance | -0.709 | +| learning_rate | 0.0001 | +| loss | -0.0885 | +| n_updates | 61890 | +| policy_gradient_loss | -0.0629 | +| value_loss | 0.000862 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.93e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 313 | +| iterations | 138 | +| time_elapsed | 451 | +| total_timesteps | 141312 | +| train/ | | +| approx_kl | 1.570045 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.474 | +| explained_variance | -6.63 | +| learning_rate | 0.0001 | +| loss | -0.086 | +| n_updates | 61900 | +| policy_gradient_loss | -0.0658 | +| value_loss | 0.000523 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.93e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 313 | +| iterations | 139 | +| time_elapsed | 454 | +| total_timesteps | 142336 | +| train/ | | +| approx_kl | 1.9651239 | +| clip_fraction | 0.484 | +| clip_range | 0.2 | +| entropy_loss | -0.406 | +| explained_variance | -1.04 | +| learning_rate | 0.0001 | +| loss | -0.093 | +| n_updates | 61910 | +| policy_gradient_loss | -0.0668 | +| value_loss | 0.000412 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.93e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 313 | +| iterations | 140 | +| time_elapsed | 457 | +| total_timesteps | 143360 | +| train/ | | +| approx_kl | 1.2214177 | +| clip_fraction | 0.474 | +| clip_range | 0.2 | +| entropy_loss | -0.481 | +| explained_variance | -0.483 | +| learning_rate | 0.0001 | +| loss | -0.0834 | +| n_updates | 61920 | +| policy_gradient_loss | -0.0626 | +| value_loss | 0.000542 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.93e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 313 | +| iterations | 141 | +| time_elapsed | 460 | +| total_timesteps | 144384 | +| train/ | | +| approx_kl | 1.8585805 | +| clip_fraction | 0.463 | +| clip_range | 0.2 | +| entropy_loss | -0.388 | +| explained_variance | -1.81 | +| learning_rate | 0.0001 | +| loss | -0.0755 | +| n_updates | 61930 | +| policy_gradient_loss | -0.061 | +| value_loss | 0.000455 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.93e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 313 | +| iterations | 142 | +| time_elapsed | 463 | +| total_timesteps | 145408 | +| train/ | | +| approx_kl | 1.3475428 | +| clip_fraction | 0.515 | +| clip_range | 0.2 | +| entropy_loss | -0.535 | +| explained_variance | -0.938 | +| learning_rate | 0.0001 | +| loss | -0.0811 | +| n_updates | 61940 | +| policy_gradient_loss | -0.0688 | +| value_loss | 0.000348 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.92e+03 | +| ep_rew_mean | 0.386 | +| time/ | | +| fps | 313 | +| iterations | 143 | +| time_elapsed | 467 | +| total_timesteps | 146432 | +| train/ | | +| approx_kl | 1.5383301 | +| clip_fraction | 0.514 | +| clip_range | 0.2 | +| entropy_loss | -0.551 | +| explained_variance | -0.333 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 61950 | +| policy_gradient_loss | -0.0696 | +| value_loss | 0.000475 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.91e+03 | +| ep_rew_mean | 0.389 | +| time/ | | +| fps | 313 | +| iterations | 144 | +| time_elapsed | 470 | +| total_timesteps | 147456 | +| train/ | | +| approx_kl | 1.6034629 | +| clip_fraction | 0.49 | +| clip_range | 0.2 | +| entropy_loss | -0.506 | +| explained_variance | -0.416 | +| learning_rate | 0.0001 | +| loss | -0.0653 | +| n_updates | 61960 | +| policy_gradient_loss | -0.0623 | +| value_loss | 0.000596 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.9e+03 | +| ep_rew_mean | 0.393 | +| time/ | | +| fps | 313 | +| iterations | 145 | +| time_elapsed | 474 | +| total_timesteps | 148480 | +| train/ | | +| approx_kl | 2.7389956 | +| clip_fraction | 0.5 | +| clip_range | 0.2 | +| entropy_loss | -0.472 | +| explained_variance | -0.56 | +| learning_rate | 0.0001 | +| loss | -0.0759 | +| n_updates | 61970 | +| policy_gradient_loss | -0.0639 | +| value_loss | 0.000659 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.9e+03 | +| ep_rew_mean | 0.393 | +| time/ | | +| fps | 313 | +| iterations | 146 | +| time_elapsed | 477 | +| total_timesteps | 149504 | +| train/ | | +| approx_kl | 1.2516875 | +| clip_fraction | 0.509 | +| clip_range | 0.2 | +| entropy_loss | -0.533 | +| explained_variance | -0.128 | +| learning_rate | 0.0001 | +| loss | -0.0757 | +| n_updates | 61980 | +| policy_gradient_loss | -0.0596 | +| value_loss | 0.000833 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.9e+03 | +| ep_rew_mean | 0.393 | +| time/ | | +| fps | 313 | +| iterations | 147 | +| time_elapsed | 480 | +| total_timesteps | 150528 | +| train/ | | +| approx_kl | 1.1739042 | +| clip_fraction | 0.523 | +| clip_range | 0.2 | +| entropy_loss | -0.565 | +| explained_variance | -1.3 | +| learning_rate | 0.0001 | +| loss | -0.0901 | +| n_updates | 61990 | +| policy_gradient_loss | -0.0779 | +| value_loss | 0.000586 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.9e+03 | +| ep_rew_mean | 0.393 | +| time/ | | +| fps | 312 | +| iterations | 148 | +| time_elapsed | 484 | +| total_timesteps | 151552 | +| train/ | | +| approx_kl | 10.327805 | +| clip_fraction | 0.531 | +| clip_range | 0.2 | +| entropy_loss | -0.471 | +| explained_variance | -2.65 | +| learning_rate | 0.0001 | +| loss | -0.0851 | +| n_updates | 62000 | +| policy_gradient_loss | -0.0687 | +| value_loss | 0.000261 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.9e+03 | +| ep_rew_mean | 0.394 | +| time/ | | +| fps | 312 | +| iterations | 149 | +| time_elapsed | 487 | +| total_timesteps | 152576 | +| train/ | | +| approx_kl | 1.2310567 | +| clip_fraction | 0.432 | +| clip_range | 0.2 | +| entropy_loss | -0.433 | +| explained_variance | -2.24 | +| learning_rate | 0.0001 | +| loss | -0.0673 | +| n_updates | 62010 | +| policy_gradient_loss | -0.0608 | +| value_loss | 0.000255 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.9e+03 | +| ep_rew_mean | 0.394 | +| time/ | | +| fps | 312 | +| iterations | 150 | +| time_elapsed | 490 | +| total_timesteps | 153600 | +| train/ | | +| approx_kl | 1.391287 | +| clip_fraction | 0.494 | +| clip_range | 0.2 | +| entropy_loss | -0.522 | +| explained_variance | -0.587 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 62020 | +| policy_gradient_loss | -0.063 | +| value_loss | 0.000639 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.9e+03 | +| ep_rew_mean | 0.397 | +| time/ | | +| fps | 312 | +| iterations | 151 | +| time_elapsed | 494 | +| total_timesteps | 154624 | +| train/ | | +| approx_kl | 2.7720213 | +| clip_fraction | 0.504 | +| clip_range | 0.2 | +| entropy_loss | -0.545 | +| explained_variance | -1.1 | +| learning_rate | 0.0001 | +| loss | -0.0829 | +| n_updates | 62030 | +| policy_gradient_loss | -0.0695 | +| value_loss | 0.000637 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.89e+03 | +| ep_rew_mean | 0.4 | +| time/ | | +| fps | 312 | +| iterations | 152 | +| time_elapsed | 497 | +| total_timesteps | 155648 | +| train/ | | +| approx_kl | 1.4196482 | +| clip_fraction | 0.498 | +| clip_range | 0.2 | +| entropy_loss | -0.516 | +| explained_variance | -1.06 | +| learning_rate | 0.0001 | +| loss | -0.0958 | +| n_updates | 62040 | +| policy_gradient_loss | -0.0701 | +| value_loss | 0.000828 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.89e+03 | +| ep_rew_mean | 0.4 | +| time/ | | +| fps | 313 | +| iterations | 153 | +| time_elapsed | 500 | +| total_timesteps | 156672 | +| train/ | | +| approx_kl | 1.4129362 | +| clip_fraction | 0.49 | +| clip_range | 0.2 | +| entropy_loss | -0.502 | +| explained_variance | -0.935 | +| learning_rate | 0.0001 | +| loss | -0.109 | +| n_updates | 62050 | +| policy_gradient_loss | -0.0648 | +| value_loss | 0.000856 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.89e+03 | +| ep_rew_mean | 0.4 | +| time/ | | +| fps | 313 | +| iterations | 154 | +| time_elapsed | 503 | +| total_timesteps | 157696 | +| train/ | | +| approx_kl | 1.3168782 | +| clip_fraction | 0.501 | +| clip_range | 0.2 | +| entropy_loss | -0.602 | +| explained_variance | -1.98 | +| learning_rate | 0.0001 | +| loss | -0.0346 | +| n_updates | 62060 | +| policy_gradient_loss | -0.071 | +| value_loss | 0.000663 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.89e+03 | +| ep_rew_mean | 0.4 | +| time/ | | +| fps | 313 | +| iterations | 155 | +| time_elapsed | 506 | +| total_timesteps | 158720 | +| train/ | | +| approx_kl | 1.1843734 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.595 | +| explained_variance | -1.41 | +| learning_rate | 0.0001 | +| loss | -0.0905 | +| n_updates | 62070 | +| policy_gradient_loss | -0.0638 | +| value_loss | 0.000601 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.89e+03 | +| ep_rew_mean | 0.4 | +| time/ | | +| fps | 313 | +| iterations | 156 | +| time_elapsed | 509 | +| total_timesteps | 159744 | +| train/ | | +| approx_kl | 1.5607178 | +| clip_fraction | 0.526 | +| clip_range | 0.2 | +| entropy_loss | -0.635 | +| explained_variance | -1.4 | +| learning_rate | 0.0001 | +| loss | -0.107 | +| n_updates | 62080 | +| policy_gradient_loss | -0.0653 | +| value_loss | 0.000603 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.89e+03 | +| ep_rew_mean | 0.4 | +| time/ | | +| fps | 313 | +| iterations | 157 | +| time_elapsed | 512 | +| total_timesteps | 160768 | +| train/ | | +| approx_kl | 1.2841483 | +| clip_fraction | 0.435 | +| clip_range | 0.2 | +| entropy_loss | -0.421 | +| explained_variance | -2.9 | +| learning_rate | 0.0001 | +| loss | -0.0889 | +| n_updates | 62090 | +| policy_gradient_loss | -0.0547 | +| value_loss | 0.000298 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.9e+03 | +| ep_rew_mean | 0.4 | +| time/ | | +| fps | 313 | +| iterations | 158 | +| time_elapsed | 516 | +| total_timesteps | 161792 | +| train/ | | +| approx_kl | 1.7017853 | +| clip_fraction | 0.5 | +| clip_range | 0.2 | +| entropy_loss | -0.454 | +| explained_variance | -1.26 | +| learning_rate | 0.0001 | +| loss | -0.0936 | +| n_updates | 62100 | +| policy_gradient_loss | -0.0651 | +| value_loss | 0.000419 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.9e+03 | +| ep_rew_mean | 0.4 | +| time/ | | +| fps | 313 | +| iterations | 159 | +| time_elapsed | 519 | +| total_timesteps | 162816 | +| train/ | | +| approx_kl | 1.3282013 | +| clip_fraction | 0.505 | +| clip_range | 0.2 | +| entropy_loss | -0.56 | +| explained_variance | -1.15 | +| learning_rate | 0.0001 | +| loss | -0.0878 | +| n_updates | 62110 | +| policy_gradient_loss | -0.0647 | +| value_loss | 0.000285 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.9e+03 | +| ep_rew_mean | 0.402 | +| time/ | | +| fps | 313 | +| iterations | 160 | +| time_elapsed | 522 | +| total_timesteps | 163840 | +| train/ | | +| approx_kl | 1.4131587 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.602 | +| explained_variance | -0.227 | +| learning_rate | 0.0001 | +| loss | -0.0496 | +| n_updates | 62120 | +| policy_gradient_loss | -0.0467 | +| value_loss | 0.00023 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.9e+03 | +| ep_rew_mean | 0.402 | +| time/ | | +| fps | 313 | +| iterations | 161 | +| time_elapsed | 525 | +| total_timesteps | 164864 | +| train/ | | +| approx_kl | 1.328328 | +| clip_fraction | 0.489 | +| clip_range | 0.2 | +| entropy_loss | -0.557 | +| explained_variance | -0.266 | +| learning_rate | 0.0001 | +| loss | -0.0905 | +| n_updates | 62130 | +| policy_gradient_loss | -0.0598 | +| value_loss | 0.000397 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.9e+03 | +| ep_rew_mean | 0.403 | +| time/ | | +| fps | 313 | +| iterations | 162 | +| time_elapsed | 528 | +| total_timesteps | 165888 | +| train/ | | +| approx_kl | 1.6786977 | +| clip_fraction | 0.49 | +| clip_range | 0.2 | +| entropy_loss | -0.482 | +| explained_variance | -2.97 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 62140 | +| policy_gradient_loss | -0.0665 | +| value_loss | 0.00052 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.89e+03 | +| ep_rew_mean | 0.405 | +| time/ | | +| fps | 313 | +| iterations | 163 | +| time_elapsed | 532 | +| total_timesteps | 166912 | +| train/ | | +| approx_kl | 2.7459831 | +| clip_fraction | 0.514 | +| clip_range | 0.2 | +| entropy_loss | -0.484 | +| explained_variance | -0.551 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 62150 | +| policy_gradient_loss | -0.0409 | +| value_loss | 0.000441 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.408 | +| time/ | | +| fps | 313 | +| iterations | 164 | +| time_elapsed | 535 | +| total_timesteps | 167936 | +| train/ | | +| approx_kl | 1.6290259 | +| clip_fraction | 0.509 | +| clip_range | 0.2 | +| entropy_loss | -0.484 | +| explained_variance | -0.708 | +| learning_rate | 0.0001 | +| loss | -0.0925 | +| n_updates | 62160 | +| policy_gradient_loss | -0.0721 | +| value_loss | 0.000904 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.408 | +| time/ | | +| fps | 313 | +| iterations | 165 | +| time_elapsed | 538 | +| total_timesteps | 168960 | +| train/ | | +| approx_kl | 1.2442849 | +| clip_fraction | 0.503 | +| clip_range | 0.2 | +| entropy_loss | -0.486 | +| explained_variance | -0.797 | +| learning_rate | 0.0001 | +| loss | -0.0678 | +| n_updates | 62170 | +| policy_gradient_loss | -0.0581 | +| value_loss | 0.000883 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.404 | +| time/ | | +| fps | 313 | +| iterations | 166 | +| time_elapsed | 541 | +| total_timesteps | 169984 | +| train/ | | +| approx_kl | 1.9231628 | +| clip_fraction | 0.491 | +| clip_range | 0.2 | +| entropy_loss | -0.457 | +| explained_variance | -4.2 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 62180 | +| policy_gradient_loss | -0.0636 | +| value_loss | 0.000501 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.404 | +| time/ | | +| fps | 313 | +| iterations | 167 | +| time_elapsed | 545 | +| total_timesteps | 171008 | +| train/ | | +| approx_kl | 1.171691 | +| clip_fraction | 0.465 | +| clip_range | 0.2 | +| entropy_loss | -0.486 | +| explained_variance | -1.13 | +| learning_rate | 0.0001 | +| loss | -0.0814 | +| n_updates | 62190 | +| policy_gradient_loss | -0.0588 | +| value_loss | 0.000537 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.404 | +| time/ | | +| fps | 313 | +| iterations | 168 | +| time_elapsed | 548 | +| total_timesteps | 172032 | +| train/ | | +| approx_kl | 1.5355248 | +| clip_fraction | 0.557 | +| clip_range | 0.2 | +| entropy_loss | -0.569 | +| explained_variance | -0.687 | +| learning_rate | 0.0001 | +| loss | -0.12 | +| n_updates | 62200 | +| policy_gradient_loss | -0.0717 | +| value_loss | 0.000565 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.406 | +| time/ | | +| fps | 313 | +| iterations | 169 | +| time_elapsed | 551 | +| total_timesteps | 173056 | +| train/ | | +| approx_kl | 1.2073833 | +| clip_fraction | 0.512 | +| clip_range | 0.2 | +| entropy_loss | -0.566 | +| explained_variance | -1.37 | +| learning_rate | 0.0001 | +| loss | -0.0826 | +| n_updates | 62210 | +| policy_gradient_loss | -0.0671 | +| value_loss | 0.000276 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.406 | +| time/ | | +| fps | 313 | +| iterations | 170 | +| time_elapsed | 554 | +| total_timesteps | 174080 | +| train/ | | +| approx_kl | 1.8281617 | +| clip_fraction | 0.51 | +| clip_range | 0.2 | +| entropy_loss | -0.535 | +| explained_variance | -0.879 | +| learning_rate | 0.0001 | +| loss | -0.0724 | +| n_updates | 62220 | +| policy_gradient_loss | -0.0575 | +| value_loss | 0.00051 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.406 | +| time/ | | +| fps | 313 | +| iterations | 171 | +| time_elapsed | 557 | +| total_timesteps | 175104 | +| train/ | | +| approx_kl | 1.4080815 | +| clip_fraction | 0.454 | +| clip_range | 0.2 | +| entropy_loss | -0.457 | +| explained_variance | -2.23 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 62230 | +| policy_gradient_loss | -0.0644 | +| value_loss | 0.000404 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.4 | +| time/ | | +| fps | 313 | +| iterations | 172 | +| time_elapsed | 561 | +| total_timesteps | 176128 | +| train/ | | +| approx_kl | 1.4735042 | +| clip_fraction | 0.493 | +| clip_range | 0.2 | +| entropy_loss | -0.475 | +| explained_variance | -4.11 | +| learning_rate | 0.0001 | +| loss | -0.0879 | +| n_updates | 62240 | +| policy_gradient_loss | -0.063 | +| value_loss | 0.000306 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.4 | +| time/ | | +| fps | 314 | +| iterations | 173 | +| time_elapsed | 564 | +| total_timesteps | 177152 | +| train/ | | +| approx_kl | 1.5811138 | +| clip_fraction | 0.491 | +| clip_range | 0.2 | +| entropy_loss | -0.504 | +| explained_variance | -0.4 | +| learning_rate | 0.0001 | +| loss | -0.0796 | +| n_updates | 62250 | +| policy_gradient_loss | -0.066 | +| value_loss | 0.00035 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.9e+03 | +| ep_rew_mean | 0.399 | +| time/ | | +| fps | 314 | +| iterations | 174 | +| time_elapsed | 567 | +| total_timesteps | 178176 | +| train/ | | +| approx_kl | 1.4231967 | +| clip_fraction | 0.489 | +| clip_range | 0.2 | +| entropy_loss | -0.485 | +| explained_variance | -3.31 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 62260 | +| policy_gradient_loss | -0.0629 | +| value_loss | 0.000543 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.9e+03 | +| ep_rew_mean | 0.399 | +| time/ | | +| fps | 314 | +| iterations | 175 | +| time_elapsed | 570 | +| total_timesteps | 179200 | +| train/ | | +| approx_kl | 2.4249876 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.444 | +| explained_variance | -1.41 | +| learning_rate | 0.0001 | +| loss | -0.0891 | +| n_updates | 62270 | +| policy_gradient_loss | -0.0644 | +| value_loss | 0.000434 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.89e+03 | +| ep_rew_mean | 0.401 | +| time/ | | +| fps | 314 | +| iterations | 176 | +| time_elapsed | 573 | +| total_timesteps | 180224 | +| train/ | | +| approx_kl | 1.4260437 | +| clip_fraction | 0.493 | +| clip_range | 0.2 | +| entropy_loss | -0.489 | +| explained_variance | -0.779 | +| learning_rate | 0.0001 | +| loss | -0.0966 | +| n_updates | 62280 | +| policy_gradient_loss | -0.0614 | +| value_loss | 0.000496 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.89e+03 | +| ep_rew_mean | 0.402 | +| time/ | | +| fps | 314 | +| iterations | 177 | +| time_elapsed | 576 | +| total_timesteps | 181248 | +| train/ | | +| approx_kl | 1.5583361 | +| clip_fraction | 0.527 | +| clip_range | 0.2 | +| entropy_loss | -0.501 | +| explained_variance | -0.894 | +| learning_rate | 0.0001 | +| loss | -0.11 | +| n_updates | 62290 | +| policy_gradient_loss | -0.068 | +| value_loss | 0.000729 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.405 | +| time/ | | +| fps | 314 | +| iterations | 178 | +| time_elapsed | 580 | +| total_timesteps | 182272 | +| train/ | | +| approx_kl | 1.1842606 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.484 | +| explained_variance | -0.582 | +| learning_rate | 0.0001 | +| loss | -0.0972 | +| n_updates | 62300 | +| policy_gradient_loss | -0.0614 | +| value_loss | 0.00049 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.405 | +| time/ | | +| fps | 314 | +| iterations | 179 | +| time_elapsed | 583 | +| total_timesteps | 183296 | +| train/ | | +| approx_kl | 2.6635702 | +| clip_fraction | 0.502 | +| clip_range | 0.2 | +| entropy_loss | -0.47 | +| explained_variance | -0.334 | +| learning_rate | 0.0001 | +| loss | -0.0946 | +| n_updates | 62310 | +| policy_gradient_loss | -0.064 | +| value_loss | 0.000782 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.403 | +| time/ | | +| fps | 314 | +| iterations | 180 | +| time_elapsed | 586 | +| total_timesteps | 184320 | +| train/ | | +| approx_kl | 2.0077906 | +| clip_fraction | 0.491 | +| clip_range | 0.2 | +| entropy_loss | -0.419 | +| explained_variance | -0.331 | +| learning_rate | 0.0001 | +| loss | -0.0759 | +| n_updates | 62320 | +| policy_gradient_loss | -0.0679 | +| value_loss | 0.000642 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.403 | +| time/ | | +| fps | 314 | +| iterations | 181 | +| time_elapsed | 590 | +| total_timesteps | 185344 | +| train/ | | +| approx_kl | 1.4689989 | +| clip_fraction | 0.493 | +| clip_range | 0.2 | +| entropy_loss | -0.47 | +| explained_variance | -0.976 | +| learning_rate | 0.0001 | +| loss | -0.0794 | +| n_updates | 62330 | +| policy_gradient_loss | -0.0656 | +| value_loss | 0.000488 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.403 | +| time/ | | +| fps | 313 | +| iterations | 182 | +| time_elapsed | 593 | +| total_timesteps | 186368 | +| train/ | | +| approx_kl | 1.4888334 | +| clip_fraction | 0.488 | +| clip_range | 0.2 | +| entropy_loss | -0.555 | +| explained_variance | -3.27 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 62340 | +| policy_gradient_loss | -0.0647 | +| value_loss | 0.000223 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.403 | +| time/ | | +| fps | 313 | +| iterations | 183 | +| time_elapsed | 597 | +| total_timesteps | 187392 | +| train/ | | +| approx_kl | 1.7309545 | +| clip_fraction | 0.459 | +| clip_range | 0.2 | +| entropy_loss | -0.462 | +| explained_variance | -0.838 | +| learning_rate | 0.0001 | +| loss | -0.0519 | +| n_updates | 62350 | +| policy_gradient_loss | -0.0544 | +| value_loss | 0.000263 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.403 | +| time/ | | +| fps | 313 | +| iterations | 184 | +| time_elapsed | 600 | +| total_timesteps | 188416 | +| train/ | | +| approx_kl | 1.4042141 | +| clip_fraction | 0.437 | +| clip_range | 0.2 | +| entropy_loss | -0.387 | +| explained_variance | -0.927 | +| learning_rate | 0.0001 | +| loss | -0.0947 | +| n_updates | 62360 | +| policy_gradient_loss | -0.0555 | +| value_loss | 0.000467 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.403 | +| time/ | | +| fps | 313 | +| iterations | 185 | +| time_elapsed | 603 | +| total_timesteps | 189440 | +| train/ | | +| approx_kl | 1.8196827 | +| clip_fraction | 0.488 | +| clip_range | 0.2 | +| entropy_loss | -0.398 | +| explained_variance | -1.89 | +| learning_rate | 0.0001 | +| loss | -0.0761 | +| n_updates | 62370 | +| policy_gradient_loss | -0.0501 | +| value_loss | 0.000582 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.409 | +| time/ | | +| fps | 313 | +| iterations | 186 | +| time_elapsed | 607 | +| total_timesteps | 190464 | +| train/ | | +| approx_kl | 1.7359579 | +| clip_fraction | 0.515 | +| clip_range | 0.2 | +| entropy_loss | -0.529 | +| explained_variance | -1.81 | +| learning_rate | 0.0001 | +| loss | -0.114 | +| n_updates | 62380 | +| policy_gradient_loss | -0.068 | +| value_loss | 0.00022 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.409 | +| time/ | | +| fps | 313 | +| iterations | 187 | +| time_elapsed | 610 | +| total_timesteps | 191488 | +| train/ | | +| approx_kl | 1.2292316 | +| clip_fraction | 0.489 | +| clip_range | 0.2 | +| entropy_loss | -0.558 | +| explained_variance | -0.288 | +| learning_rate | 0.0001 | +| loss | -0.0751 | +| n_updates | 62390 | +| policy_gradient_loss | -0.0549 | +| value_loss | 0.000552 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.89e+03 | +| ep_rew_mean | 0.409 | +| time/ | | +| fps | 313 | +| iterations | 188 | +| time_elapsed | 613 | +| total_timesteps | 192512 | +| train/ | | +| approx_kl | 1.8032582 | +| clip_fraction | 0.491 | +| clip_range | 0.2 | +| entropy_loss | -0.457 | +| explained_variance | -2.07 | +| learning_rate | 0.0001 | +| loss | -0.11 | +| n_updates | 62400 | +| policy_gradient_loss | -0.0691 | +| value_loss | 0.00046 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.89e+03 | +| ep_rew_mean | 0.409 | +| time/ | | +| fps | 313 | +| iterations | 189 | +| time_elapsed | 616 | +| total_timesteps | 193536 | +| train/ | | +| approx_kl | 1.3502748 | +| clip_fraction | 0.47 | +| clip_range | 0.2 | +| entropy_loss | -0.517 | +| explained_variance | -0.889 | +| learning_rate | 0.0001 | +| loss | -0.0781 | +| n_updates | 62410 | +| policy_gradient_loss | -0.0468 | +| value_loss | 0.000447 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.409 | +| time/ | | +| fps | 313 | +| iterations | 190 | +| time_elapsed | 619 | +| total_timesteps | 194560 | +| train/ | | +| approx_kl | 1.7905002 | +| clip_fraction | 0.497 | +| clip_range | 0.2 | +| entropy_loss | -0.476 | +| explained_variance | -1.78 | +| learning_rate | 0.0001 | +| loss | -0.0798 | +| n_updates | 62420 | +| policy_gradient_loss | -0.0691 | +| value_loss | 0.000487 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.409 | +| time/ | | +| fps | 313 | +| iterations | 191 | +| time_elapsed | 623 | +| total_timesteps | 195584 | +| train/ | | +| approx_kl | 1.3177085 | +| clip_fraction | 0.45 | +| clip_range | 0.2 | +| entropy_loss | -0.543 | +| explained_variance | -1.52 | +| learning_rate | 0.0001 | +| loss | -0.0629 | +| n_updates | 62430 | +| policy_gradient_loss | -0.0594 | +| value_loss | 0.000343 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.411 | +| time/ | | +| fps | 314 | +| iterations | 192 | +| time_elapsed | 626 | +| total_timesteps | 196608 | +| train/ | | +| approx_kl | 1.7684648 | +| clip_fraction | 0.486 | +| clip_range | 0.2 | +| entropy_loss | -0.455 | +| explained_variance | -3.25 | +| learning_rate | 0.0001 | +| loss | -0.0966 | +| n_updates | 62440 | +| policy_gradient_loss | -0.0682 | +| value_loss | 0.000331 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.411 | +| time/ | | +| fps | 313 | +| iterations | 193 | +| time_elapsed | 629 | +| total_timesteps | 197632 | +| train/ | | +| approx_kl | 1.7019458 | +| clip_fraction | 0.535 | +| clip_range | 0.2 | +| entropy_loss | -0.541 | +| explained_variance | -1.23 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 62450 | +| policy_gradient_loss | -0.0657 | +| value_loss | 0.00045 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.413 | +| time/ | | +| fps | 314 | +| iterations | 194 | +| time_elapsed | 632 | +| total_timesteps | 198656 | +| train/ | | +| approx_kl | 1.5601954 | +| clip_fraction | 0.503 | +| clip_range | 0.2 | +| entropy_loss | -0.513 | +| explained_variance | -0.652 | +| learning_rate | 0.0001 | +| loss | -0.11 | +| n_updates | 62460 | +| policy_gradient_loss | -0.07 | +| value_loss | 0.000705 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.414 | +| time/ | | +| fps | 314 | +| iterations | 195 | +| time_elapsed | 635 | +| total_timesteps | 199680 | +| train/ | | +| approx_kl | 1.4535134 | +| clip_fraction | 0.516 | +| clip_range | 0.2 | +| entropy_loss | -0.573 | +| explained_variance | -1.12 | +| learning_rate | 0.0001 | +| loss | -0.0766 | +| n_updates | 62470 | +| policy_gradient_loss | -0.0647 | +| value_loss | 0.000648 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.414 | +| time/ | | +| fps | 314 | +| iterations | 196 | +| time_elapsed | 638 | +| total_timesteps | 200704 | +| train/ | | +| approx_kl | 1.902439 | +| clip_fraction | 0.459 | +| clip_range | 0.2 | +| entropy_loss | -0.487 | +| explained_variance | -2.1 | +| learning_rate | 0.0001 | +| loss | -0.0451 | +| n_updates | 62480 | +| policy_gradient_loss | -0.0515 | +| value_loss | 0.000543 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.415 | +| time/ | | +| fps | 314 | +| iterations | 197 | +| time_elapsed | 642 | +| total_timesteps | 201728 | +| train/ | | +| approx_kl | 1.58075 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.513 | +| explained_variance | -1.65 | +| learning_rate | 0.0001 | +| loss | -0.0793 | +| n_updates | 62490 | +| policy_gradient_loss | -0.0711 | +| value_loss | 0.000457 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.415 | +| time/ | | +| fps | 314 | +| iterations | 198 | +| time_elapsed | 645 | +| total_timesteps | 202752 | +| train/ | | +| approx_kl | 1.3627045 | +| clip_fraction | 0.504 | +| clip_range | 0.2 | +| entropy_loss | -0.525 | +| explained_variance | -2.02 | +| learning_rate | 0.0001 | +| loss | -0.119 | +| n_updates | 62500 | +| policy_gradient_loss | -0.07 | +| value_loss | 0.000604 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.415 | +| time/ | | +| fps | 314 | +| iterations | 199 | +| time_elapsed | 648 | +| total_timesteps | 203776 | +| train/ | | +| approx_kl | 1.7162912 | +| clip_fraction | 0.5 | +| clip_range | 0.2 | +| entropy_loss | -0.517 | +| explained_variance | -0.914 | +| learning_rate | 0.0001 | +| loss | -0.0907 | +| n_updates | 62510 | +| policy_gradient_loss | -0.0617 | +| value_loss | 0.00059 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.418 | +| time/ | | +| fps | 313 | +| iterations | 200 | +| time_elapsed | 652 | +| total_timesteps | 204800 | +| train/ | | +| approx_kl | 1.2678041 | +| clip_fraction | 0.486 | +| clip_range | 0.2 | +| entropy_loss | -0.521 | +| explained_variance | -1.69 | +| learning_rate | 0.0001 | +| loss | -0.0646 | +| n_updates | 62520 | +| policy_gradient_loss | -0.0665 | +| value_loss | 0.000457 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.418 | +| time/ | | +| fps | 314 | +| iterations | 201 | +| time_elapsed | 655 | +| total_timesteps | 205824 | +| train/ | | +| approx_kl | 2.4622545 | +| clip_fraction | 0.472 | +| clip_range | 0.2 | +| entropy_loss | -0.457 | +| explained_variance | -2.17 | +| learning_rate | 0.0001 | +| loss | -0.0743 | +| n_updates | 62530 | +| policy_gradient_loss | -0.0699 | +| value_loss | 0.000321 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.417 | +| time/ | | +| fps | 313 | +| iterations | 202 | +| time_elapsed | 658 | +| total_timesteps | 206848 | +| train/ | | +| approx_kl | 1.3017278 | +| clip_fraction | 0.456 | +| clip_range | 0.2 | +| entropy_loss | -0.55 | +| explained_variance | -1 | +| learning_rate | 0.0001 | +| loss | -0.0829 | +| n_updates | 62540 | +| policy_gradient_loss | -0.059 | +| value_loss | 0.000557 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.417 | +| time/ | | +| fps | 313 | +| iterations | 203 | +| time_elapsed | 662 | +| total_timesteps | 207872 | +| train/ | | +| approx_kl | 1.4733262 | +| clip_fraction | 0.509 | +| clip_range | 0.2 | +| entropy_loss | -0.499 | +| explained_variance | -2.07 | +| learning_rate | 0.0001 | +| loss | -0.0715 | +| n_updates | 62550 | +| policy_gradient_loss | -0.0691 | +| value_loss | 0.00029 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.421 | +| time/ | | +| fps | 313 | +| iterations | 204 | +| time_elapsed | 665 | +| total_timesteps | 208896 | +| train/ | | +| approx_kl | 1.4883969 | +| clip_fraction | 0.507 | +| clip_range | 0.2 | +| entropy_loss | -0.485 | +| explained_variance | -0.731 | +| learning_rate | 0.0001 | +| loss | -0.0789 | +| n_updates | 62560 | +| policy_gradient_loss | -0.0674 | +| value_loss | 0.000762 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.422 | +| time/ | | +| fps | 313 | +| iterations | 205 | +| time_elapsed | 669 | +| total_timesteps | 209920 | +| train/ | | +| approx_kl | 1.6321554 | +| clip_fraction | 0.504 | +| clip_range | 0.2 | +| entropy_loss | -0.531 | +| explained_variance | -1.6 | +| learning_rate | 0.0001 | +| loss | -0.0873 | +| n_updates | 62570 | +| policy_gradient_loss | -0.0567 | +| value_loss | 0.000577 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.422 | +| time/ | | +| fps | 313 | +| iterations | 206 | +| time_elapsed | 672 | +| total_timesteps | 210944 | +| train/ | | +| approx_kl | 1.8764002 | +| clip_fraction | 0.538 | +| clip_range | 0.2 | +| entropy_loss | -0.538 | +| explained_variance | -0.983 | +| learning_rate | 0.0001 | +| loss | -0.0992 | +| n_updates | 62580 | +| policy_gradient_loss | -0.0757 | +| value_loss | 0.000805 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.422 | +| time/ | | +| fps | 313 | +| iterations | 207 | +| time_elapsed | 675 | +| total_timesteps | 211968 | +| train/ | | +| approx_kl | 1.6150913 | +| clip_fraction | 0.505 | +| clip_range | 0.2 | +| entropy_loss | -0.467 | +| explained_variance | -3.64 | +| learning_rate | 0.0001 | +| loss | -0.106 | +| n_updates | 62590 | +| policy_gradient_loss | -0.0738 | +| value_loss | 0.00051 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.422 | +| time/ | | +| fps | 314 | +| iterations | 208 | +| time_elapsed | 678 | +| total_timesteps | 212992 | +| train/ | | +| approx_kl | 7.485099 | +| clip_fraction | 0.492 | +| clip_range | 0.2 | +| entropy_loss | -0.473 | +| explained_variance | -2.15 | +| learning_rate | 0.0001 | +| loss | -0.106 | +| n_updates | 62600 | +| policy_gradient_loss | -0.0571 | +| value_loss | 0.00021 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.42 | +| time/ | | +| fps | 314 | +| iterations | 209 | +| time_elapsed | 681 | +| total_timesteps | 214016 | +| train/ | | +| approx_kl | 1.327753 | +| clip_fraction | 0.47 | +| clip_range | 0.2 | +| entropy_loss | -0.463 | +| explained_variance | -0.467 | +| learning_rate | 0.0001 | +| loss | -0.0569 | +| n_updates | 62610 | +| policy_gradient_loss | -0.0505 | +| value_loss | 0.000421 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.419 | +| time/ | | +| fps | 314 | +| iterations | 210 | +| time_elapsed | 684 | +| total_timesteps | 215040 | +| train/ | | +| approx_kl | 1.3299649 | +| clip_fraction | 0.494 | +| clip_range | 0.2 | +| entropy_loss | -0.546 | +| explained_variance | -1.05 | +| learning_rate | 0.0001 | +| loss | -0.0772 | +| n_updates | 62620 | +| policy_gradient_loss | -0.063 | +| value_loss | 0.000207 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.419 | +| time/ | | +| fps | 314 | +| iterations | 211 | +| time_elapsed | 687 | +| total_timesteps | 216064 | +| train/ | | +| approx_kl | 2.0314066 | +| clip_fraction | 0.504 | +| clip_range | 0.2 | +| entropy_loss | -0.504 | +| explained_variance | -0.218 | +| learning_rate | 0.0001 | +| loss | -0.105 | +| n_updates | 62630 | +| policy_gradient_loss | -0.0664 | +| value_loss | 0.000643 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.421 | +| time/ | | +| fps | 314 | +| iterations | 212 | +| time_elapsed | 690 | +| total_timesteps | 217088 | +| train/ | | +| approx_kl | 1.4977175 | +| clip_fraction | 0.497 | +| clip_range | 0.2 | +| entropy_loss | -0.489 | +| explained_variance | -1.93 | +| learning_rate | 0.0001 | +| loss | -0.0939 | +| n_updates | 62640 | +| policy_gradient_loss | -0.0749 | +| value_loss | 0.00104 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.421 | +| time/ | | +| fps | 314 | +| iterations | 213 | +| time_elapsed | 693 | +| total_timesteps | 218112 | +| train/ | | +| approx_kl | 1.4894416 | +| clip_fraction | 0.503 | +| clip_range | 0.2 | +| entropy_loss | -0.512 | +| explained_variance | -1.03 | +| learning_rate | 0.0001 | +| loss | -0.0728 | +| n_updates | 62650 | +| policy_gradient_loss | -0.064 | +| value_loss | 0.000382 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.418 | +| time/ | | +| fps | 314 | +| iterations | 214 | +| time_elapsed | 696 | +| total_timesteps | 219136 | +| train/ | | +| approx_kl | 2.065938 | +| clip_fraction | 0.503 | +| clip_range | 0.2 | +| entropy_loss | -0.435 | +| explained_variance | -1.46 | +| learning_rate | 0.0001 | +| loss | -0.0854 | +| n_updates | 62660 | +| policy_gradient_loss | -0.0707 | +| value_loss | 0.000674 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.423 | +| time/ | | +| fps | 314 | +| iterations | 215 | +| time_elapsed | 700 | +| total_timesteps | 220160 | +| train/ | | +| approx_kl | 2.2066295 | +| clip_fraction | 0.51 | +| clip_range | 0.2 | +| entropy_loss | -0.495 | +| explained_variance | -1.21 | +| learning_rate | 0.0001 | +| loss | -0.0873 | +| n_updates | 62670 | +| policy_gradient_loss | -0.0679 | +| value_loss | 0.000408 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.423 | +| time/ | | +| fps | 314 | +| iterations | 216 | +| time_elapsed | 703 | +| total_timesteps | 221184 | +| train/ | | +| approx_kl | 1.7549976 | +| clip_fraction | 0.503 | +| clip_range | 0.2 | +| entropy_loss | -0.471 | +| explained_variance | -0.883 | +| learning_rate | 0.0001 | +| loss | -0.0864 | +| n_updates | 62680 | +| policy_gradient_loss | -0.0727 | +| value_loss | 0.000812 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.423 | +| time/ | | +| fps | 314 | +| iterations | 217 | +| time_elapsed | 707 | +| total_timesteps | 222208 | +| train/ | | +| approx_kl | 1.3325232 | +| clip_fraction | 0.502 | +| clip_range | 0.2 | +| entropy_loss | -0.549 | +| explained_variance | -1.35 | +| learning_rate | 0.0001 | +| loss | -0.047 | +| n_updates | 62690 | +| policy_gradient_loss | -0.0662 | +| value_loss | 0.00042 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.422 | +| time/ | | +| fps | 314 | +| iterations | 218 | +| time_elapsed | 710 | +| total_timesteps | 223232 | +| train/ | | +| approx_kl | 1.3686328 | +| clip_fraction | 0.527 | +| clip_range | 0.2 | +| entropy_loss | -0.581 | +| explained_variance | -0.625 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 62700 | +| policy_gradient_loss | -0.0724 | +| value_loss | 0.000228 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.422 | +| time/ | | +| fps | 314 | +| iterations | 219 | +| time_elapsed | 713 | +| total_timesteps | 224256 | +| train/ | | +| approx_kl | 1.2643106 | +| clip_fraction | 0.513 | +| clip_range | 0.2 | +| entropy_loss | -0.565 | +| explained_variance | -2.95 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 62710 | +| policy_gradient_loss | -0.0689 | +| value_loss | 0.000226 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.421 | +| time/ | | +| fps | 314 | +| iterations | 220 | +| time_elapsed | 717 | +| total_timesteps | 225280 | +| train/ | | +| approx_kl | 1.2647462 | +| clip_fraction | 0.502 | +| clip_range | 0.2 | +| entropy_loss | -0.57 | +| explained_variance | -1.53 | +| learning_rate | 0.0001 | +| loss | -0.0989 | +| n_updates | 62720 | +| policy_gradient_loss | -0.0675 | +| value_loss | 0.000233 | +--------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.421 | +| time/ | | +| fps | 314 | +| iterations | 221 | +| time_elapsed | 720 | +| total_timesteps | 226304 | +| train/ | | +| approx_kl | 0.95901895 | +| clip_fraction | 0.509 | +| clip_range | 0.2 | +| entropy_loss | -0.591 | +| explained_variance | -2.12 | +| learning_rate | 0.0001 | +| loss | -0.116 | +| n_updates | 62730 | +| policy_gradient_loss | -0.0677 | +| value_loss | 0.000272 | +---------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.419 | +| time/ | | +| fps | 313 | +| iterations | 222 | +| time_elapsed | 724 | +| total_timesteps | 227328 | +| train/ | | +| approx_kl | 1.4514283 | +| clip_fraction | 0.513 | +| clip_range | 0.2 | +| entropy_loss | -0.497 | +| explained_variance | -1.2 | +| learning_rate | 0.0001 | +| loss | -0.0797 | +| n_updates | 62740 | +| policy_gradient_loss | -0.07 | +| value_loss | 0.000717 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.427 | +| time/ | | +| fps | 313 | +| iterations | 223 | +| time_elapsed | 727 | +| total_timesteps | 228352 | +| train/ | | +| approx_kl | 1.9747969 | +| clip_fraction | 0.501 | +| clip_range | 0.2 | +| entropy_loss | -0.524 | +| explained_variance | -2.47 | +| learning_rate | 0.0001 | +| loss | -0.0901 | +| n_updates | 62750 | +| policy_gradient_loss | -0.0633 | +| value_loss | 0.000607 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.427 | +| time/ | | +| fps | 313 | +| iterations | 224 | +| time_elapsed | 730 | +| total_timesteps | 229376 | +| train/ | | +| approx_kl | 1.466629 | +| clip_fraction | 0.5 | +| clip_range | 0.2 | +| entropy_loss | -0.537 | +| explained_variance | -0.228 | +| learning_rate | 0.0001 | +| loss | -0.1 | +| n_updates | 62760 | +| policy_gradient_loss | -0.0663 | +| value_loss | 0.000938 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.427 | +| time/ | | +| fps | 313 | +| iterations | 225 | +| time_elapsed | 733 | +| total_timesteps | 230400 | +| train/ | | +| approx_kl | 1.3341403 | +| clip_fraction | 0.525 | +| clip_range | 0.2 | +| entropy_loss | -0.601 | +| explained_variance | -0.715 | +| learning_rate | 0.0001 | +| loss | -0.0785 | +| n_updates | 62770 | +| policy_gradient_loss | -0.0664 | +| value_loss | 0.00111 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.428 | +| time/ | | +| fps | 313 | +| iterations | 226 | +| time_elapsed | 737 | +| total_timesteps | 231424 | +| train/ | | +| approx_kl | 2.138743 | +| clip_fraction | 0.504 | +| clip_range | 0.2 | +| entropy_loss | -0.517 | +| explained_variance | -1.46 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 62780 | +| policy_gradient_loss | -0.0734 | +| value_loss | 0.000794 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.428 | +| time/ | | +| fps | 313 | +| iterations | 227 | +| time_elapsed | 740 | +| total_timesteps | 232448 | +| train/ | | +| approx_kl | 1.4389315 | +| clip_fraction | 0.51 | +| clip_range | 0.2 | +| entropy_loss | -0.558 | +| explained_variance | -2.13 | +| learning_rate | 0.0001 | +| loss | -0.0933 | +| n_updates | 62790 | +| policy_gradient_loss | -0.0715 | +| value_loss | 0.000458 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.428 | +| time/ | | +| fps | 314 | +| iterations | 228 | +| time_elapsed | 743 | +| total_timesteps | 233472 | +| train/ | | +| approx_kl | 1.7707894 | +| clip_fraction | 0.49 | +| clip_range | 0.2 | +| entropy_loss | -0.505 | +| explained_variance | -1.46 | +| learning_rate | 0.0001 | +| loss | -0.0995 | +| n_updates | 62800 | +| policy_gradient_loss | -0.0673 | +| value_loss | 0.000776 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.428 | +| time/ | | +| fps | 314 | +| iterations | 229 | +| time_elapsed | 746 | +| total_timesteps | 234496 | +| train/ | | +| approx_kl | 1.7637224 | +| clip_fraction | 0.548 | +| clip_range | 0.2 | +| entropy_loss | -0.647 | +| explained_variance | -1.49 | +| learning_rate | 0.0001 | +| loss | -0.088 | +| n_updates | 62810 | +| policy_gradient_loss | -0.0749 | +| value_loss | 0.000313 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.428 | +| time/ | | +| fps | 314 | +| iterations | 230 | +| time_elapsed | 749 | +| total_timesteps | 235520 | +| train/ | | +| approx_kl | 1.6142564 | +| clip_fraction | 0.534 | +| clip_range | 0.2 | +| entropy_loss | -0.546 | +| explained_variance | -11.2 | +| learning_rate | 0.0001 | +| loss | -0.0805 | +| n_updates | 62820 | +| policy_gradient_loss | -0.0771 | +| value_loss | 0.0002 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.428 | +| time/ | | +| fps | 314 | +| iterations | 231 | +| time_elapsed | 752 | +| total_timesteps | 236544 | +| train/ | | +| approx_kl | 7.576496 | +| clip_fraction | 0.527 | +| clip_range | 0.2 | +| entropy_loss | -0.627 | +| explained_variance | -0.838 | +| learning_rate | 0.0001 | +| loss | -0.0909 | +| n_updates | 62830 | +| policy_gradient_loss | -0.0691 | +| value_loss | 0.000299 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.428 | +| time/ | | +| fps | 314 | +| iterations | 232 | +| time_elapsed | 756 | +| total_timesteps | 237568 | +| train/ | | +| approx_kl | 1.3686472 | +| clip_fraction | 0.498 | +| clip_range | 0.2 | +| entropy_loss | -0.538 | +| explained_variance | -1.57 | +| learning_rate | 0.0001 | +| loss | -0.0756 | +| n_updates | 62840 | +| policy_gradient_loss | -0.0719 | +| value_loss | 0.000405 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.425 | +| time/ | | +| fps | 314 | +| iterations | 233 | +| time_elapsed | 759 | +| total_timesteps | 238592 | +| train/ | | +| approx_kl | 2.375751 | +| clip_fraction | 0.561 | +| clip_range | 0.2 | +| entropy_loss | -0.592 | +| explained_variance | -1.55 | +| learning_rate | 0.0001 | +| loss | -0.105 | +| n_updates | 62850 | +| policy_gradient_loss | -0.078 | +| value_loss | 0.000536 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.425 | +| time/ | | +| fps | 314 | +| iterations | 234 | +| time_elapsed | 762 | +| total_timesteps | 239616 | +| train/ | | +| approx_kl | 1.5198817 | +| clip_fraction | 0.532 | +| clip_range | 0.2 | +| entropy_loss | -0.596 | +| explained_variance | -0.944 | +| learning_rate | 0.0001 | +| loss | -0.069 | +| n_updates | 62860 | +| policy_gradient_loss | -0.0699 | +| value_loss | 0.000391 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.425 | +| time/ | | +| fps | 314 | +| iterations | 235 | +| time_elapsed | 766 | +| total_timesteps | 240640 | +| train/ | | +| approx_kl | 1.6236422 | +| clip_fraction | 0.51 | +| clip_range | 0.2 | +| entropy_loss | -0.547 | +| explained_variance | -1.05 | +| learning_rate | 0.0001 | +| loss | -0.0838 | +| n_updates | 62870 | +| policy_gradient_loss | -0.073 | +| value_loss | 0.000514 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.431 | +| time/ | | +| fps | 313 | +| iterations | 236 | +| time_elapsed | 769 | +| total_timesteps | 241664 | +| train/ | | +| approx_kl | 1.1675856 | +| clip_fraction | 0.503 | +| clip_range | 0.2 | +| entropy_loss | -0.634 | +| explained_variance | -0.812 | +| learning_rate | 0.0001 | +| loss | -0.0735 | +| n_updates | 62880 | +| policy_gradient_loss | -0.0657 | +| value_loss | 0.00052 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.432 | +| time/ | | +| fps | 313 | +| iterations | 237 | +| time_elapsed | 772 | +| total_timesteps | 242688 | +| train/ | | +| approx_kl | 1.1636451 | +| clip_fraction | 0.527 | +| clip_range | 0.2 | +| entropy_loss | -0.632 | +| explained_variance | -0.658 | +| learning_rate | 0.0001 | +| loss | -0.0743 | +| n_updates | 62890 | +| policy_gradient_loss | -0.0746 | +| value_loss | 0.00103 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.432 | +| time/ | | +| fps | 313 | +| iterations | 238 | +| time_elapsed | 776 | +| total_timesteps | 243712 | +| train/ | | +| approx_kl | 2.2509346 | +| clip_fraction | 0.494 | +| clip_range | 0.2 | +| entropy_loss | -0.547 | +| explained_variance | -2.52 | +| learning_rate | 0.0001 | +| loss | -0.105 | +| n_updates | 62900 | +| policy_gradient_loss | -0.0739 | +| value_loss | 0.000663 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.432 | +| time/ | | +| fps | 313 | +| iterations | 239 | +| time_elapsed | 779 | +| total_timesteps | 244736 | +| train/ | | +| approx_kl | 1.4391901 | +| clip_fraction | 0.493 | +| clip_range | 0.2 | +| entropy_loss | -0.582 | +| explained_variance | -1.12 | +| learning_rate | 0.0001 | +| loss | -0.0878 | +| n_updates | 62910 | +| policy_gradient_loss | -0.0694 | +| value_loss | 0.000329 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.432 | +| time/ | | +| fps | 313 | +| iterations | 240 | +| time_elapsed | 783 | +| total_timesteps | 245760 | +| train/ | | +| approx_kl | 1.3268564 | +| clip_fraction | 0.491 | +| clip_range | 0.2 | +| entropy_loss | -0.564 | +| explained_variance | -0.717 | +| learning_rate | 0.0001 | +| loss | -0.0746 | +| n_updates | 62920 | +| policy_gradient_loss | -0.0665 | +| value_loss | 0.000354 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.429 | +| time/ | | +| fps | 313 | +| iterations | 241 | +| time_elapsed | 786 | +| total_timesteps | 246784 | +| train/ | | +| approx_kl | 1.4619589 | +| clip_fraction | 0.527 | +| clip_range | 0.2 | +| entropy_loss | -0.581 | +| explained_variance | -2.33 | +| learning_rate | 0.0001 | +| loss | -0.0996 | +| n_updates | 62930 | +| policy_gradient_loss | -0.0714 | +| value_loss | 0.000277 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.429 | +| time/ | | +| fps | 313 | +| iterations | 242 | +| time_elapsed | 789 | +| total_timesteps | 247808 | +| train/ | | +| approx_kl | 1.5727606 | +| clip_fraction | 0.491 | +| clip_range | 0.2 | +| entropy_loss | -0.607 | +| explained_variance | -2.37 | +| learning_rate | 0.0001 | +| loss | -0.107 | +| n_updates | 62940 | +| policy_gradient_loss | -0.0647 | +| value_loss | 0.000341 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.429 | +| time/ | | +| fps | 313 | +| iterations | 243 | +| time_elapsed | 793 | +| total_timesteps | 248832 | +| train/ | | +| approx_kl | 1.7627432 | +| clip_fraction | 0.489 | +| clip_range | 0.2 | +| entropy_loss | -0.471 | +| explained_variance | -1.87 | +| learning_rate | 0.0001 | +| loss | -0.071 | +| n_updates | 62950 | +| policy_gradient_loss | -0.0738 | +| value_loss | 0.000352 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.428 | +| time/ | | +| fps | 313 | +| iterations | 244 | +| time_elapsed | 796 | +| total_timesteps | 249856 | +| train/ | | +| approx_kl | 1.6225772 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.506 | +| explained_variance | -0.701 | +| learning_rate | 0.0001 | +| loss | -0.0943 | +| n_updates | 62960 | +| policy_gradient_loss | -0.0666 | +| value_loss | 0.000871 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.432 | +| time/ | | +| fps | 313 | +| iterations | 245 | +| time_elapsed | 799 | +| total_timesteps | 250880 | +| train/ | | +| approx_kl | 3.017615 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.478 | +| explained_variance | -1.49 | +| learning_rate | 0.0001 | +| loss | -0.0809 | +| n_updates | 62970 | +| policy_gradient_loss | -0.0694 | +| value_loss | 0.000657 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.432 | +| time/ | | +| fps | 313 | +| iterations | 246 | +| time_elapsed | 802 | +| total_timesteps | 251904 | +| train/ | | +| approx_kl | 2.5642462 | +| clip_fraction | 0.49 | +| clip_range | 0.2 | +| entropy_loss | -0.433 | +| explained_variance | -0.669 | +| learning_rate | 0.0001 | +| loss | -0.0817 | +| n_updates | 62980 | +| policy_gradient_loss | -0.0599 | +| value_loss | 0.000492 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.43 | +| time/ | | +| fps | 313 | +| iterations | 247 | +| time_elapsed | 805 | +| total_timesteps | 252928 | +| train/ | | +| approx_kl | 1.4302049 | +| clip_fraction | 0.503 | +| clip_range | 0.2 | +| entropy_loss | -0.498 | +| explained_variance | -8.75 | +| learning_rate | 0.0001 | +| loss | -0.111 | +| n_updates | 62990 | +| policy_gradient_loss | -0.0706 | +| value_loss | 0.000298 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.43 | +| time/ | | +| fps | 314 | +| iterations | 248 | +| time_elapsed | 808 | +| total_timesteps | 253952 | +| train/ | | +| approx_kl | 1.474335 | +| clip_fraction | 0.484 | +| clip_range | 0.2 | +| entropy_loss | -0.513 | +| explained_variance | -0.864 | +| learning_rate | 0.0001 | +| loss | -0.0841 | +| n_updates | 63000 | +| policy_gradient_loss | -0.0659 | +| value_loss | 0.000328 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.43 | +| time/ | | +| fps | 314 | +| iterations | 249 | +| time_elapsed | 811 | +| total_timesteps | 254976 | +| train/ | | +| approx_kl | 4.2956767 | +| clip_fraction | 0.492 | +| clip_range | 0.2 | +| entropy_loss | -0.446 | +| explained_variance | -2.14 | +| learning_rate | 0.0001 | +| loss | -0.107 | +| n_updates | 63010 | +| policy_gradient_loss | -0.0657 | +| value_loss | 0.000381 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.429 | +| time/ | | +| fps | 314 | +| iterations | 250 | +| time_elapsed | 814 | +| total_timesteps | 256000 | +| train/ | | +| approx_kl | 1.5831587 | +| clip_fraction | 0.46 | +| clip_range | 0.2 | +| entropy_loss | -0.508 | +| explained_variance | -1.26 | +| learning_rate | 0.0001 | +| loss | -0.0824 | +| n_updates | 63020 | +| policy_gradient_loss | -0.0517 | +| value_loss | 0.000595 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.43 | +| time/ | | +| fps | 314 | +| iterations | 251 | +| time_elapsed | 818 | +| total_timesteps | 257024 | +| train/ | | +| approx_kl | 1.5409033 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.459 | +| explained_variance | -4.61 | +| learning_rate | 0.0001 | +| loss | -0.0886 | +| n_updates | 63030 | +| policy_gradient_loss | -0.0636 | +| value_loss | 0.000396 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.43 | +| time/ | | +| fps | 314 | +| iterations | 252 | +| time_elapsed | 821 | +| total_timesteps | 258048 | +| train/ | | +| approx_kl | 1.9039006 | +| clip_fraction | 0.513 | +| clip_range | 0.2 | +| entropy_loss | -0.498 | +| explained_variance | -0.448 | +| learning_rate | 0.0001 | +| loss | -0.0446 | +| n_updates | 63040 | +| policy_gradient_loss | -0.0647 | +| value_loss | 0.000651 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.43 | +| time/ | | +| fps | 313 | +| iterations | 253 | +| time_elapsed | 825 | +| total_timesteps | 259072 | +| train/ | | +| approx_kl | 1.3845516 | +| clip_fraction | 0.485 | +| clip_range | 0.2 | +| entropy_loss | -0.479 | +| explained_variance | -3.51 | +| learning_rate | 0.0001 | +| loss | -0.105 | +| n_updates | 63050 | +| policy_gradient_loss | -0.0635 | +| value_loss | 0.000641 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.43 | +| time/ | | +| fps | 313 | +| iterations | 254 | +| time_elapsed | 828 | +| total_timesteps | 260096 | +| train/ | | +| approx_kl | 1.8558788 | +| clip_fraction | 0.486 | +| clip_range | 0.2 | +| entropy_loss | -0.433 | +| explained_variance | -1.15 | +| learning_rate | 0.0001 | +| loss | -0.0269 | +| n_updates | 63060 | +| policy_gradient_loss | -0.0582 | +| value_loss | 0.000438 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.43 | +| time/ | | +| fps | 313 | +| iterations | 255 | +| time_elapsed | 832 | +| total_timesteps | 261120 | +| train/ | | +| approx_kl | 1.5846572 | +| clip_fraction | 0.498 | +| clip_range | 0.2 | +| entropy_loss | -0.541 | +| explained_variance | -2.9 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 63070 | +| policy_gradient_loss | -0.0622 | +| value_loss | 0.000387 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.43 | +| time/ | | +| fps | 313 | +| iterations | 256 | +| time_elapsed | 835 | +| total_timesteps | 262144 | +| train/ | | +| approx_kl | 1.7300256 | +| clip_fraction | 0.499 | +| clip_range | 0.2 | +| entropy_loss | -0.533 | +| explained_variance | -0.985 | +| learning_rate | 0.0001 | +| loss | -0.082 | +| n_updates | 63080 | +| policy_gradient_loss | -0.0625 | +| value_loss | 0.000313 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.428 | +| time/ | | +| fps | 313 | +| iterations | 257 | +| time_elapsed | 838 | +| total_timesteps | 263168 | +| train/ | | +| approx_kl | 1.4771233 | +| clip_fraction | 0.491 | +| clip_range | 0.2 | +| entropy_loss | -0.551 | +| explained_variance | -1.25 | +| learning_rate | 0.0001 | +| loss | -0.0742 | +| n_updates | 63090 | +| policy_gradient_loss | -0.065 | +| value_loss | 0.000234 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.428 | +| time/ | | +| fps | 313 | +| iterations | 258 | +| time_elapsed | 842 | +| total_timesteps | 264192 | +| train/ | | +| approx_kl | 1.3940356 | +| clip_fraction | 0.477 | +| clip_range | 0.2 | +| entropy_loss | -0.57 | +| explained_variance | -1.23 | +| learning_rate | 0.0001 | +| loss | -0.0831 | +| n_updates | 63100 | +| policy_gradient_loss | -0.0557 | +| value_loss | 0.00042 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.432 | +| time/ | | +| fps | 313 | +| iterations | 259 | +| time_elapsed | 845 | +| total_timesteps | 265216 | +| train/ | | +| approx_kl | 1.8319519 | +| clip_fraction | 0.468 | +| clip_range | 0.2 | +| entropy_loss | -0.381 | +| explained_variance | -2.33 | +| learning_rate | 0.0001 | +| loss | -0.0854 | +| n_updates | 63110 | +| policy_gradient_loss | -0.0642 | +| value_loss | 0.000694 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.432 | +| time/ | | +| fps | 313 | +| iterations | 260 | +| time_elapsed | 849 | +| total_timesteps | 266240 | +| train/ | | +| approx_kl | 2.2845712 | +| clip_fraction | 0.455 | +| clip_range | 0.2 | +| entropy_loss | -0.487 | +| explained_variance | -3.52 | +| learning_rate | 0.0001 | +| loss | -0.0873 | +| n_updates | 63120 | +| policy_gradient_loss | -0.0518 | +| value_loss | 0.00036 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.43 | +| time/ | | +| fps | 313 | +| iterations | 261 | +| time_elapsed | 852 | +| total_timesteps | 267264 | +| train/ | | +| approx_kl | 1.2801368 | +| clip_fraction | 0.499 | +| clip_range | 0.2 | +| entropy_loss | -0.547 | +| explained_variance | -1.31 | +| learning_rate | 0.0001 | +| loss | -0.0963 | +| n_updates | 63130 | +| policy_gradient_loss | -0.0586 | +| value_loss | 0.000191 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.436 | +| time/ | | +| fps | 313 | +| iterations | 262 | +| time_elapsed | 855 | +| total_timesteps | 268288 | +| train/ | | +| approx_kl | 1.6841195 | +| clip_fraction | 0.486 | +| clip_range | 0.2 | +| entropy_loss | -0.429 | +| explained_variance | -0.565 | +| learning_rate | 0.0001 | +| loss | -0.0999 | +| n_updates | 63140 | +| policy_gradient_loss | -0.0621 | +| value_loss | 0.00088 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.436 | +| time/ | | +| fps | 313 | +| iterations | 263 | +| time_elapsed | 858 | +| total_timesteps | 269312 | +| train/ | | +| approx_kl | 4.525818 | +| clip_fraction | 0.482 | +| clip_range | 0.2 | +| entropy_loss | -0.474 | +| explained_variance | -0.775 | +| learning_rate | 0.0001 | +| loss | -0.0798 | +| n_updates | 63150 | +| policy_gradient_loss | -0.061 | +| value_loss | 0.000864 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.434 | +| time/ | | +| fps | 313 | +| iterations | 264 | +| time_elapsed | 862 | +| total_timesteps | 270336 | +| train/ | | +| approx_kl | 2.4921758 | +| clip_fraction | 0.5 | +| clip_range | 0.2 | +| entropy_loss | -0.446 | +| explained_variance | -3.77 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 63160 | +| policy_gradient_loss | -0.0721 | +| value_loss | 0.000475 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.434 | +| time/ | | +| fps | 313 | +| iterations | 265 | +| time_elapsed | 865 | +| total_timesteps | 271360 | +| train/ | | +| approx_kl | 1.6294286 | +| clip_fraction | 0.49 | +| clip_range | 0.2 | +| entropy_loss | -0.439 | +| explained_variance | -0.954 | +| learning_rate | 0.0001 | +| loss | -0.0704 | +| n_updates | 63170 | +| policy_gradient_loss | -0.0684 | +| value_loss | 0.000793 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.433 | +| time/ | | +| fps | 313 | +| iterations | 266 | +| time_elapsed | 868 | +| total_timesteps | 272384 | +| train/ | | +| approx_kl | 1.4112974 | +| clip_fraction | 0.485 | +| clip_range | 0.2 | +| entropy_loss | -0.475 | +| explained_variance | -1.77 | +| learning_rate | 0.0001 | +| loss | -0.111 | +| n_updates | 63180 | +| policy_gradient_loss | -0.0715 | +| value_loss | 0.000683 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.434 | +| time/ | | +| fps | 313 | +| iterations | 267 | +| time_elapsed | 871 | +| total_timesteps | 273408 | +| train/ | | +| approx_kl | 1.8196015 | +| clip_fraction | 0.489 | +| clip_range | 0.2 | +| entropy_loss | -0.499 | +| explained_variance | -0.495 | +| learning_rate | 0.0001 | +| loss | -0.0593 | +| n_updates | 63190 | +| policy_gradient_loss | -0.0565 | +| value_loss | 0.000677 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.434 | +| time/ | | +| fps | 313 | +| iterations | 268 | +| time_elapsed | 874 | +| total_timesteps | 274432 | +| train/ | | +| approx_kl | 1.4026589 | +| clip_fraction | 0.506 | +| clip_range | 0.2 | +| entropy_loss | -0.515 | +| explained_variance | -1.12 | +| learning_rate | 0.0001 | +| loss | -0.0806 | +| n_updates | 63200 | +| policy_gradient_loss | -0.0675 | +| value_loss | 0.000736 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.433 | +| time/ | | +| fps | 313 | +| iterations | 269 | +| time_elapsed | 878 | +| total_timesteps | 275456 | +| train/ | | +| approx_kl | 1.313307 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.5 | +| explained_variance | -2.58 | +| learning_rate | 0.0001 | +| loss | -0.0884 | +| n_updates | 63210 | +| policy_gradient_loss | -0.0671 | +| value_loss | 0.000286 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.433 | +| time/ | | +| fps | 313 | +| iterations | 270 | +| time_elapsed | 881 | +| total_timesteps | 276480 | +| train/ | | +| approx_kl | 1.4112453 | +| clip_fraction | 0.469 | +| clip_range | 0.2 | +| entropy_loss | -0.484 | +| explained_variance | -1.61 | +| learning_rate | 0.0001 | +| loss | -0.0762 | +| n_updates | 63220 | +| policy_gradient_loss | -0.0607 | +| value_loss | 0.000428 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.429 | +| time/ | | +| fps | 313 | +| iterations | 271 | +| time_elapsed | 884 | +| total_timesteps | 277504 | +| train/ | | +| approx_kl | 2.0113835 | +| clip_fraction | 0.495 | +| clip_range | 0.2 | +| entropy_loss | -0.414 | +| explained_variance | -1.94 | +| learning_rate | 0.0001 | +| loss | -0.0585 | +| n_updates | 63230 | +| policy_gradient_loss | -0.0673 | +| value_loss | 0.000448 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.431 | +| time/ | | +| fps | 313 | +| iterations | 272 | +| time_elapsed | 887 | +| total_timesteps | 278528 | +| train/ | | +| approx_kl | 1.5213246 | +| clip_fraction | 0.446 | +| clip_range | 0.2 | +| entropy_loss | -0.396 | +| explained_variance | -0.345 | +| learning_rate | 0.0001 | +| loss | -0.0838 | +| n_updates | 63240 | +| policy_gradient_loss | -0.057 | +| value_loss | 0.000558 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.435 | +| time/ | | +| fps | 313 | +| iterations | 273 | +| time_elapsed | 891 | +| total_timesteps | 279552 | +| train/ | | +| approx_kl | 1.4854913 | +| clip_fraction | 0.522 | +| clip_range | 0.2 | +| entropy_loss | -0.571 | +| explained_variance | -0.16 | +| learning_rate | 0.0001 | +| loss | -0.1 | +| n_updates | 63250 | +| policy_gradient_loss | -0.0548 | +| value_loss | 0.000652 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.436 | +| time/ | | +| fps | 313 | +| iterations | 274 | +| time_elapsed | 894 | +| total_timesteps | 280576 | +| train/ | | +| approx_kl | 1.7432904 | +| clip_fraction | 0.499 | +| clip_range | 0.2 | +| entropy_loss | -0.542 | +| explained_variance | -0.5 | +| learning_rate | 0.0001 | +| loss | -0.089 | +| n_updates | 63260 | +| policy_gradient_loss | -0.0662 | +| value_loss | 0.000521 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.436 | +| time/ | | +| fps | 313 | +| iterations | 275 | +| time_elapsed | 897 | +| total_timesteps | 281600 | +| train/ | | +| approx_kl | 1.8151146 | +| clip_fraction | 0.416 | +| clip_range | 0.2 | +| entropy_loss | -0.372 | +| explained_variance | -0.325 | +| learning_rate | 0.0001 | +| loss | -0.0966 | +| n_updates | 63270 | +| policy_gradient_loss | -0.0542 | +| value_loss | 0.00105 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.434 | +| time/ | | +| fps | 313 | +| iterations | 276 | +| time_elapsed | 901 | +| total_timesteps | 282624 | +| train/ | | +| approx_kl | 2.4724913 | +| clip_fraction | 0.453 | +| clip_range | 0.2 | +| entropy_loss | -0.367 | +| explained_variance | -2.85 | +| learning_rate | 0.0001 | +| loss | -0.0742 | +| n_updates | 63280 | +| policy_gradient_loss | -0.0686 | +| value_loss | 0.000714 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.434 | +| time/ | | +| fps | 313 | +| iterations | 277 | +| time_elapsed | 904 | +| total_timesteps | 283648 | +| train/ | | +| approx_kl | 1.4352196 | +| clip_fraction | 0.46 | +| clip_range | 0.2 | +| entropy_loss | -0.422 | +| explained_variance | -1.59 | +| learning_rate | 0.0001 | +| loss | -0.0681 | +| n_updates | 63290 | +| policy_gradient_loss | -0.0604 | +| value_loss | 0.000538 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.432 | +| time/ | | +| fps | 313 | +| iterations | 278 | +| time_elapsed | 907 | +| total_timesteps | 284672 | +| train/ | | +| approx_kl | 1.5407804 | +| clip_fraction | 0.465 | +| clip_range | 0.2 | +| entropy_loss | -0.411 | +| explained_variance | -0.841 | +| learning_rate | 0.0001 | +| loss | -0.064 | +| n_updates | 63300 | +| policy_gradient_loss | -0.0642 | +| value_loss | 0.000492 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.439 | +| time/ | | +| fps | 313 | +| iterations | 279 | +| time_elapsed | 910 | +| total_timesteps | 285696 | +| train/ | | +| approx_kl | 1.8666096 | +| clip_fraction | 0.477 | +| clip_range | 0.2 | +| entropy_loss | -0.468 | +| explained_variance | -1.56 | +| learning_rate | 0.0001 | +| loss | -0.00795 | +| n_updates | 63310 | +| policy_gradient_loss | -0.056 | +| value_loss | 0.000355 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.439 | +| time/ | | +| fps | 313 | +| iterations | 280 | +| time_elapsed | 913 | +| total_timesteps | 286720 | +| train/ | | +| approx_kl | 1.7430506 | +| clip_fraction | 0.472 | +| clip_range | 0.2 | +| entropy_loss | -0.429 | +| explained_variance | -0.808 | +| learning_rate | 0.0001 | +| loss | -0.0739 | +| n_updates | 63320 | +| policy_gradient_loss | -0.0567 | +| value_loss | 0.000595 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.43 | +| time/ | | +| fps | 313 | +| iterations | 281 | +| time_elapsed | 916 | +| total_timesteps | 287744 | +| train/ | | +| approx_kl | 1.683388 | +| clip_fraction | 0.467 | +| clip_range | 0.2 | +| entropy_loss | -0.387 | +| explained_variance | -7.59 | +| learning_rate | 0.0001 | +| loss | -0.111 | +| n_updates | 63330 | +| policy_gradient_loss | -0.0692 | +| value_loss | 0.000493 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.43 | +| time/ | | +| fps | 313 | +| iterations | 282 | +| time_elapsed | 919 | +| total_timesteps | 288768 | +| train/ | | +| approx_kl | 1.2761304 | +| clip_fraction | 0.428 | +| clip_range | 0.2 | +| entropy_loss | -0.369 | +| explained_variance | -1.54 | +| learning_rate | 0.0001 | +| loss | -0.0602 | +| n_updates | 63340 | +| policy_gradient_loss | -0.0589 | +| value_loss | 0.000643 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.43 | +| time/ | | +| fps | 313 | +| iterations | 283 | +| time_elapsed | 923 | +| total_timesteps | 289792 | +| train/ | | +| approx_kl | 1.5725667 | +| clip_fraction | 0.482 | +| clip_range | 0.2 | +| entropy_loss | -0.391 | +| explained_variance | -3.58 | +| learning_rate | 0.0001 | +| loss | -0.0948 | +| n_updates | 63350 | +| policy_gradient_loss | -0.0592 | +| value_loss | 0.000718 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.431 | +| time/ | | +| fps | 314 | +| iterations | 284 | +| time_elapsed | 926 | +| total_timesteps | 290816 | +| train/ | | +| approx_kl | 1.3592398 | +| clip_fraction | 0.494 | +| clip_range | 0.2 | +| entropy_loss | -0.462 | +| explained_variance | -2.3 | +| learning_rate | 0.0001 | +| loss | -0.0868 | +| n_updates | 63360 | +| policy_gradient_loss | -0.0646 | +| value_loss | 0.000456 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.431 | +| time/ | | +| fps | 314 | +| iterations | 285 | +| time_elapsed | 929 | +| total_timesteps | 291840 | +| train/ | | +| approx_kl | 1.6977253 | +| clip_fraction | 0.464 | +| clip_range | 0.2 | +| entropy_loss | -0.425 | +| explained_variance | -1.33 | +| learning_rate | 0.0001 | +| loss | -0.0759 | +| n_updates | 63370 | +| policy_gradient_loss | -0.0557 | +| value_loss | 0.000636 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.43 | +| time/ | | +| fps | 314 | +| iterations | 286 | +| time_elapsed | 932 | +| total_timesteps | 292864 | +| train/ | | +| approx_kl | 1.5846984 | +| clip_fraction | 0.431 | +| clip_range | 0.2 | +| entropy_loss | -0.364 | +| explained_variance | -1.55 | +| learning_rate | 0.0001 | +| loss | -0.0872 | +| n_updates | 63380 | +| policy_gradient_loss | -0.064 | +| value_loss | 0.000514 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.43 | +| time/ | | +| fps | 314 | +| iterations | 287 | +| time_elapsed | 935 | +| total_timesteps | 293888 | +| train/ | | +| approx_kl | 1.928215 | +| clip_fraction | 0.454 | +| clip_range | 0.2 | +| entropy_loss | -0.419 | +| explained_variance | -1.3 | +| learning_rate | 0.0001 | +| loss | -0.105 | +| n_updates | 63390 | +| policy_gradient_loss | -0.0651 | +| value_loss | 0.000538 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.431 | +| time/ | | +| fps | 314 | +| iterations | 288 | +| time_elapsed | 938 | +| total_timesteps | 294912 | +| train/ | | +| approx_kl | 2.1605248 | +| clip_fraction | 0.512 | +| clip_range | 0.2 | +| entropy_loss | -0.452 | +| explained_variance | -1.53 | +| learning_rate | 0.0001 | +| loss | -0.0813 | +| n_updates | 63400 | +| policy_gradient_loss | -0.0696 | +| value_loss | 0.0004 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.431 | +| time/ | | +| fps | 314 | +| iterations | 289 | +| time_elapsed | 941 | +| total_timesteps | 295936 | +| train/ | | +| approx_kl | 1.8659589 | +| clip_fraction | 0.453 | +| clip_range | 0.2 | +| entropy_loss | -0.382 | +| explained_variance | -1.84 | +| learning_rate | 0.0001 | +| loss | -0.0557 | +| n_updates | 63410 | +| policy_gradient_loss | -0.0569 | +| value_loss | 0.000517 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.432 | +| time/ | | +| fps | 314 | +| iterations | 290 | +| time_elapsed | 945 | +| total_timesteps | 296960 | +| train/ | | +| approx_kl | 1.7688541 | +| clip_fraction | 0.465 | +| clip_range | 0.2 | +| entropy_loss | -0.346 | +| explained_variance | -1.83 | +| learning_rate | 0.0001 | +| loss | -0.0832 | +| n_updates | 63420 | +| policy_gradient_loss | -0.0702 | +| value_loss | 0.000719 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.432 | +| time/ | | +| fps | 314 | +| iterations | 291 | +| time_elapsed | 948 | +| total_timesteps | 297984 | +| train/ | | +| approx_kl | 1.5425444 | +| clip_fraction | 0.422 | +| clip_range | 0.2 | +| entropy_loss | -0.333 | +| explained_variance | -1.7 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 63430 | +| policy_gradient_loss | -0.062 | +| value_loss | 0.000434 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.432 | +| time/ | | +| fps | 314 | +| iterations | 292 | +| time_elapsed | 952 | +| total_timesteps | 299008 | +| train/ | | +| approx_kl | 1.9720466 | +| clip_fraction | 0.453 | +| clip_range | 0.2 | +| entropy_loss | -0.374 | +| explained_variance | -0.122 | +| learning_rate | 0.0001 | +| loss | -0.0703 | +| n_updates | 63440 | +| policy_gradient_loss | -0.0591 | +| value_loss | 0.000508 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.432 | +| time/ | | +| fps | 313 | +| iterations | 293 | +| time_elapsed | 955 | +| total_timesteps | 300032 | +| train/ | | +| approx_kl | 1.6808664 | +| clip_fraction | 0.446 | +| clip_range | 0.2 | +| entropy_loss | -0.354 | +| explained_variance | -6.59 | +| learning_rate | 0.0001 | +| loss | -0.0934 | +| n_updates | 63450 | +| policy_gradient_loss | -0.0604 | +| value_loss | 0.00059 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.432 | +| time/ | | +| fps | 313 | +| iterations | 294 | +| time_elapsed | 958 | +| total_timesteps | 301056 | +| train/ | | +| approx_kl | 2.3503876 | +| clip_fraction | 0.439 | +| clip_range | 0.2 | +| entropy_loss | -0.351 | +| explained_variance | -1.04 | +| learning_rate | 0.0001 | +| loss | -0.0133 | +| n_updates | 63460 | +| policy_gradient_loss | -0.0529 | +| value_loss | 0.000405 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.43 | +| time/ | | +| fps | 313 | +| iterations | 295 | +| time_elapsed | 962 | +| total_timesteps | 302080 | +| train/ | | +| approx_kl | 1.8577924 | +| clip_fraction | 0.461 | +| clip_range | 0.2 | +| entropy_loss | -0.422 | +| explained_variance | -6.01 | +| learning_rate | 0.0001 | +| loss | -0.0589 | +| n_updates | 63470 | +| policy_gradient_loss | -0.0605 | +| value_loss | 0.000196 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.422 | +| time/ | | +| fps | 313 | +| iterations | 296 | +| time_elapsed | 966 | +| total_timesteps | 303104 | +| train/ | | +| approx_kl | 2.3671303 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.389 | +| explained_variance | -1.41 | +| learning_rate | 0.0001 | +| loss | -0.0748 | +| n_updates | 63480 | +| policy_gradient_loss | -0.0534 | +| value_loss | 0.000314 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.422 | +| time/ | | +| fps | 313 | +| iterations | 297 | +| time_elapsed | 969 | +| total_timesteps | 304128 | +| train/ | | +| approx_kl | 1.7353965 | +| clip_fraction | 0.44 | +| clip_range | 0.2 | +| entropy_loss | -0.364 | +| explained_variance | -2.42 | +| learning_rate | 0.0001 | +| loss | -0.0959 | +| n_updates | 63490 | +| policy_gradient_loss | -0.0656 | +| value_loss | 0.000304 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.419 | +| time/ | | +| fps | 313 | +| iterations | 298 | +| time_elapsed | 972 | +| total_timesteps | 305152 | +| train/ | | +| approx_kl | 1.7493837 | +| clip_fraction | 0.486 | +| clip_range | 0.2 | +| entropy_loss | -0.413 | +| explained_variance | -0.594 | +| learning_rate | 0.0001 | +| loss | -0.0622 | +| n_updates | 63500 | +| policy_gradient_loss | -0.051 | +| value_loss | 0.000437 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.419 | +| time/ | | +| fps | 313 | +| iterations | 299 | +| time_elapsed | 975 | +| total_timesteps | 306176 | +| train/ | | +| approx_kl | 1.3088558 | +| clip_fraction | 0.456 | +| clip_range | 0.2 | +| entropy_loss | -0.428 | +| explained_variance | -4.99 | +| learning_rate | 0.0001 | +| loss | -0.0853 | +| n_updates | 63510 | +| policy_gradient_loss | -0.0711 | +| value_loss | 0.000491 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.419 | +| time/ | | +| fps | 313 | +| iterations | 300 | +| time_elapsed | 978 | +| total_timesteps | 307200 | +| train/ | | +| approx_kl | 1.3299497 | +| clip_fraction | 0.488 | +| clip_range | 0.2 | +| entropy_loss | -0.466 | +| explained_variance | -1.35 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 63520 | +| policy_gradient_loss | -0.067 | +| value_loss | 0.00041 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.419 | +| time/ | | +| fps | 313 | +| iterations | 301 | +| time_elapsed | 981 | +| total_timesteps | 308224 | +| train/ | | +| approx_kl | 1.7476948 | +| clip_fraction | 0.466 | +| clip_range | 0.2 | +| entropy_loss | -0.398 | +| explained_variance | -1.84 | +| learning_rate | 0.0001 | +| loss | -0.0706 | +| n_updates | 63530 | +| policy_gradient_loss | -0.0587 | +| value_loss | 0.000446 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.419 | +| time/ | | +| fps | 313 | +| iterations | 302 | +| time_elapsed | 985 | +| total_timesteps | 309248 | +| train/ | | +| approx_kl | 1.446482 | +| clip_fraction | 0.434 | +| clip_range | 0.2 | +| entropy_loss | -0.361 | +| explained_variance | -3.52 | +| learning_rate | 0.0001 | +| loss | -0.0166 | +| n_updates | 63540 | +| policy_gradient_loss | -0.0515 | +| value_loss | 0.000492 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.419 | +| time/ | | +| fps | 313 | +| iterations | 303 | +| time_elapsed | 988 | +| total_timesteps | 310272 | +| train/ | | +| approx_kl | 1.439476 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.427 | +| explained_variance | -1.95 | +| learning_rate | 0.0001 | +| loss | -0.0858 | +| n_updates | 63550 | +| policy_gradient_loss | -0.0631 | +| value_loss | 0.000401 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.419 | +| time/ | | +| fps | 314 | +| iterations | 304 | +| time_elapsed | 991 | +| total_timesteps | 311296 | +| train/ | | +| approx_kl | 1.7288774 | +| clip_fraction | 0.473 | +| clip_range | 0.2 | +| entropy_loss | -0.369 | +| explained_variance | -1.67 | +| learning_rate | 0.0001 | +| loss | -0.0902 | +| n_updates | 63560 | +| policy_gradient_loss | -0.0629 | +| value_loss | 0.000742 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.419 | +| time/ | | +| fps | 314 | +| iterations | 305 | +| time_elapsed | 994 | +| total_timesteps | 312320 | +| train/ | | +| approx_kl | 2.0949905 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.365 | +| explained_variance | -1.79 | +| learning_rate | 0.0001 | +| loss | -0.0584 | +| n_updates | 63570 | +| policy_gradient_loss | -0.0651 | +| value_loss | 0.000403 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.419 | +| time/ | | +| fps | 314 | +| iterations | 306 | +| time_elapsed | 997 | +| total_timesteps | 313344 | +| train/ | | +| approx_kl | 1.7045407 | +| clip_fraction | 0.469 | +| clip_range | 0.2 | +| entropy_loss | -0.388 | +| explained_variance | -0.802 | +| learning_rate | 0.0001 | +| loss | -0.0989 | +| n_updates | 63580 | +| policy_gradient_loss | -0.0698 | +| value_loss | 0.000517 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.418 | +| time/ | | +| fps | 314 | +| iterations | 307 | +| time_elapsed | 1001 | +| total_timesteps | 314368 | +| train/ | | +| approx_kl | 2.0757778 | +| clip_fraction | 0.51 | +| clip_range | 0.2 | +| entropy_loss | -0.474 | +| explained_variance | -2.63 | +| learning_rate | 0.0001 | +| loss | -0.0843 | +| n_updates | 63590 | +| policy_gradient_loss | -0.0694 | +| value_loss | 0.00033 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.418 | +| time/ | | +| fps | 314 | +| iterations | 308 | +| time_elapsed | 1004 | +| total_timesteps | 315392 | +| train/ | | +| approx_kl | 1.6374636 | +| clip_fraction | 0.479 | +| clip_range | 0.2 | +| entropy_loss | -0.464 | +| explained_variance | -0.96 | +| learning_rate | 0.0001 | +| loss | -0.073 | +| n_updates | 63600 | +| policy_gradient_loss | -0.062 | +| value_loss | 0.000271 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.417 | +| time/ | | +| fps | 313 | +| iterations | 309 | +| time_elapsed | 1007 | +| total_timesteps | 316416 | +| train/ | | +| approx_kl | 2.188281 | +| clip_fraction | 0.455 | +| clip_range | 0.2 | +| entropy_loss | -0.45 | +| explained_variance | -1.03 | +| learning_rate | 0.0001 | +| loss | -0.0629 | +| n_updates | 63610 | +| policy_gradient_loss | -0.0579 | +| value_loss | 0.000408 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.423 | +| time/ | | +| fps | 313 | +| iterations | 310 | +| time_elapsed | 1011 | +| total_timesteps | 317440 | +| train/ | | +| approx_kl | 1.6735126 | +| clip_fraction | 0.492 | +| clip_range | 0.2 | +| entropy_loss | -0.485 | +| explained_variance | -2.44 | +| learning_rate | 0.0001 | +| loss | -0.062 | +| n_updates | 63620 | +| policy_gradient_loss | -0.0632 | +| value_loss | 0.000549 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.423 | +| time/ | | +| fps | 313 | +| iterations | 311 | +| time_elapsed | 1014 | +| total_timesteps | 318464 | +| train/ | | +| approx_kl | 1.6301131 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.472 | +| explained_variance | -0.626 | +| learning_rate | 0.0001 | +| loss | -0.0629 | +| n_updates | 63630 | +| policy_gradient_loss | -0.0619 | +| value_loss | 0.000621 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.425 | +| time/ | | +| fps | 313 | +| iterations | 312 | +| time_elapsed | 1017 | +| total_timesteps | 319488 | +| train/ | | +| approx_kl | 1.3105476 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.474 | +| explained_variance | -1.57 | +| learning_rate | 0.0001 | +| loss | -0.0638 | +| n_updates | 63640 | +| policy_gradient_loss | -0.0668 | +| value_loss | 0.00062 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.425 | +| time/ | | +| fps | 313 | +| iterations | 313 | +| time_elapsed | 1021 | +| total_timesteps | 320512 | +| train/ | | +| approx_kl | 2.1817307 | +| clip_fraction | 0.458 | +| clip_range | 0.2 | +| entropy_loss | -0.398 | +| explained_variance | -1.54 | +| learning_rate | 0.0001 | +| loss | -0.0752 | +| n_updates | 63650 | +| policy_gradient_loss | -0.0593 | +| value_loss | 0.000663 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.425 | +| time/ | | +| fps | 313 | +| iterations | 314 | +| time_elapsed | 1024 | +| total_timesteps | 321536 | +| train/ | | +| approx_kl | 1.3925021 | +| clip_fraction | 0.5 | +| clip_range | 0.2 | +| entropy_loss | -0.512 | +| explained_variance | -2.25 | +| learning_rate | 0.0001 | +| loss | -0.111 | +| n_updates | 63660 | +| policy_gradient_loss | -0.0636 | +| value_loss | 0.000415 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.426 | +| time/ | | +| fps | 313 | +| iterations | 315 | +| time_elapsed | 1027 | +| total_timesteps | 322560 | +| train/ | | +| approx_kl | 3.3699965 | +| clip_fraction | 0.458 | +| clip_range | 0.2 | +| entropy_loss | -0.37 | +| explained_variance | -1.96 | +| learning_rate | 0.0001 | +| loss | -0.0862 | +| n_updates | 63670 | +| policy_gradient_loss | -0.0647 | +| value_loss | 0.00041 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.426 | +| time/ | | +| fps | 313 | +| iterations | 316 | +| time_elapsed | 1031 | +| total_timesteps | 323584 | +| train/ | | +| approx_kl | 2.1037917 | +| clip_fraction | 0.454 | +| clip_range | 0.2 | +| entropy_loss | -0.409 | +| explained_variance | -5.55 | +| learning_rate | 0.0001 | +| loss | -0.0594 | +| n_updates | 63680 | +| policy_gradient_loss | -0.0594 | +| value_loss | 0.000296 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.421 | +| time/ | | +| fps | 313 | +| iterations | 317 | +| time_elapsed | 1034 | +| total_timesteps | 324608 | +| train/ | | +| approx_kl | 2.119739 | +| clip_fraction | 0.448 | +| clip_range | 0.2 | +| entropy_loss | -0.378 | +| explained_variance | -1.55 | +| learning_rate | 0.0001 | +| loss | -0.0884 | +| n_updates | 63690 | +| policy_gradient_loss | -0.0596 | +| value_loss | 0.000355 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.421 | +| time/ | | +| fps | 313 | +| iterations | 318 | +| time_elapsed | 1037 | +| total_timesteps | 325632 | +| train/ | | +| approx_kl | 1.7291256 | +| clip_fraction | 0.45 | +| clip_range | 0.2 | +| entropy_loss | -0.377 | +| explained_variance | -0.82 | +| learning_rate | 0.0001 | +| loss | -0.0916 | +| n_updates | 63700 | +| policy_gradient_loss | -0.0604 | +| value_loss | 0.000513 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.421 | +| time/ | | +| fps | 313 | +| iterations | 319 | +| time_elapsed | 1040 | +| total_timesteps | 326656 | +| train/ | | +| approx_kl | 1.8692992 | +| clip_fraction | 0.468 | +| clip_range | 0.2 | +| entropy_loss | -0.429 | +| explained_variance | -8.86 | +| learning_rate | 0.0001 | +| loss | -0.068 | +| n_updates | 63710 | +| policy_gradient_loss | -0.0647 | +| value_loss | 0.000297 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.89e+03 | +| ep_rew_mean | 0.419 | +| time/ | | +| fps | 314 | +| iterations | 320 | +| time_elapsed | 1043 | +| total_timesteps | 327680 | +| train/ | | +| approx_kl | 1.7427151 | +| clip_fraction | 0.454 | +| clip_range | 0.2 | +| entropy_loss | -0.352 | +| explained_variance | -0.468 | +| learning_rate | 0.0001 | +| loss | -0.062 | +| n_updates | 63720 | +| policy_gradient_loss | -0.059 | +| value_loss | 0.000564 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.89e+03 | +| ep_rew_mean | 0.419 | +| time/ | | +| fps | 314 | +| iterations | 321 | +| time_elapsed | 1046 | +| total_timesteps | 328704 | +| train/ | | +| approx_kl | 1.8223634 | +| clip_fraction | 0.444 | +| clip_range | 0.2 | +| entropy_loss | -0.344 | +| explained_variance | -1.32 | +| learning_rate | 0.0001 | +| loss | -0.0551 | +| n_updates | 63730 | +| policy_gradient_loss | -0.051 | +| value_loss | 0.000553 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.89e+03 | +| ep_rew_mean | 0.419 | +| time/ | | +| fps | 314 | +| iterations | 322 | +| time_elapsed | 1049 | +| total_timesteps | 329728 | +| train/ | | +| approx_kl | 1.4168142 | +| clip_fraction | 0.459 | +| clip_range | 0.2 | +| entropy_loss | -0.405 | +| explained_variance | -0.589 | +| learning_rate | 0.0001 | +| loss | -0.0886 | +| n_updates | 63740 | +| policy_gradient_loss | -0.0538 | +| value_loss | 0.000897 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.89e+03 | +| ep_rew_mean | 0.423 | +| time/ | | +| fps | 314 | +| iterations | 323 | +| time_elapsed | 1052 | +| total_timesteps | 330752 | +| train/ | | +| approx_kl | 1.8832718 | +| clip_fraction | 0.468 | +| clip_range | 0.2 | +| entropy_loss | -0.347 | +| explained_variance | -5.95 | +| learning_rate | 0.0001 | +| loss | -0.0884 | +| n_updates | 63750 | +| policy_gradient_loss | -0.067 | +| value_loss | 0.000852 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.89e+03 | +| ep_rew_mean | 0.423 | +| time/ | | +| fps | 314 | +| iterations | 324 | +| time_elapsed | 1055 | +| total_timesteps | 331776 | +| train/ | | +| approx_kl | 1.3480241 | +| clip_fraction | 0.436 | +| clip_range | 0.2 | +| entropy_loss | -0.411 | +| explained_variance | -1.95 | +| learning_rate | 0.0001 | +| loss | -0.0796 | +| n_updates | 63760 | +| policy_gradient_loss | -0.0588 | +| value_loss | 0.00031 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.89e+03 | +| ep_rew_mean | 0.42 | +| time/ | | +| fps | 314 | +| iterations | 325 | +| time_elapsed | 1058 | +| total_timesteps | 332800 | +| train/ | | +| approx_kl | 1.1551882 | +| clip_fraction | 0.47 | +| clip_range | 0.2 | +| entropy_loss | -0.46 | +| explained_variance | -0.658 | +| learning_rate | 0.0001 | +| loss | -0.0582 | +| n_updates | 63770 | +| policy_gradient_loss | -0.0539 | +| value_loss | 0.000323 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.89e+03 | +| ep_rew_mean | 0.42 | +| time/ | | +| fps | 314 | +| iterations | 326 | +| time_elapsed | 1062 | +| total_timesteps | 333824 | +| train/ | | +| approx_kl | 1.681217 | +| clip_fraction | 0.459 | +| clip_range | 0.2 | +| entropy_loss | -0.391 | +| explained_variance | -4.13 | +| learning_rate | 0.0001 | +| loss | -0.0393 | +| n_updates | 63780 | +| policy_gradient_loss | -0.0569 | +| value_loss | 0.000538 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.89e+03 | +| ep_rew_mean | 0.411 | +| time/ | | +| fps | 314 | +| iterations | 327 | +| time_elapsed | 1065 | +| total_timesteps | 334848 | +| train/ | | +| approx_kl | 1.4482296 | +| clip_fraction | 0.488 | +| clip_range | 0.2 | +| entropy_loss | -0.466 | +| explained_variance | -5.91 | +| learning_rate | 0.0001 | +| loss | -0.0788 | +| n_updates | 63790 | +| policy_gradient_loss | -0.0618 | +| value_loss | 0.000398 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.89e+03 | +| ep_rew_mean | 0.411 | +| time/ | | +| fps | 314 | +| iterations | 328 | +| time_elapsed | 1069 | +| total_timesteps | 335872 | +| train/ | | +| approx_kl | 1.2727785 | +| clip_fraction | 0.454 | +| clip_range | 0.2 | +| entropy_loss | -0.398 | +| explained_variance | -0.332 | +| learning_rate | 0.0001 | +| loss | -0.0711 | +| n_updates | 63800 | +| policy_gradient_loss | -0.0611 | +| value_loss | 0.000535 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.89e+03 | +| ep_rew_mean | 0.411 | +| time/ | | +| fps | 314 | +| iterations | 329 | +| time_elapsed | 1072 | +| total_timesteps | 336896 | +| train/ | | +| approx_kl | 1.6166143 | +| clip_fraction | 0.489 | +| clip_range | 0.2 | +| entropy_loss | -0.437 | +| explained_variance | -1.83 | +| learning_rate | 0.0001 | +| loss | -0.0952 | +| n_updates | 63810 | +| policy_gradient_loss | -0.0623 | +| value_loss | 0.000433 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.91e+03 | +| ep_rew_mean | 0.408 | +| time/ | | +| fps | 314 | +| iterations | 330 | +| time_elapsed | 1076 | +| total_timesteps | 337920 | +| train/ | | +| approx_kl | 1.9962986 | +| clip_fraction | 0.507 | +| clip_range | 0.2 | +| entropy_loss | -0.423 | +| explained_variance | -2.51 | +| learning_rate | 0.0001 | +| loss | -0.0915 | +| n_updates | 63820 | +| policy_gradient_loss | -0.0734 | +| value_loss | 0.000574 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.91e+03 | +| ep_rew_mean | 0.409 | +| time/ | | +| fps | 313 | +| iterations | 331 | +| time_elapsed | 1079 | +| total_timesteps | 338944 | +| train/ | | +| approx_kl | 1.6576093 | +| clip_fraction | 0.477 | +| clip_range | 0.2 | +| entropy_loss | -0.406 | +| explained_variance | -0.835 | +| learning_rate | 0.0001 | +| loss | -0.084 | +| n_updates | 63830 | +| policy_gradient_loss | -0.0688 | +| value_loss | 0.00067 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.91e+03 | +| ep_rew_mean | 0.409 | +| time/ | | +| fps | 313 | +| iterations | 332 | +| time_elapsed | 1083 | +| total_timesteps | 339968 | +| train/ | | +| approx_kl | 1.6201127 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.421 | +| explained_variance | -0.464 | +| learning_rate | 0.0001 | +| loss | -0.0782 | +| n_updates | 63840 | +| policy_gradient_loss | -0.0579 | +| value_loss | 0.000846 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.92e+03 | +| ep_rew_mean | 0.404 | +| time/ | | +| fps | 313 | +| iterations | 333 | +| time_elapsed | 1086 | +| total_timesteps | 340992 | +| train/ | | +| approx_kl | 2.2263622 | +| clip_fraction | 0.478 | +| clip_range | 0.2 | +| entropy_loss | -0.436 | +| explained_variance | -1.18 | +| learning_rate | 0.0001 | +| loss | -0.0734 | +| n_updates | 63850 | +| policy_gradient_loss | -0.0564 | +| value_loss | 0.000515 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.92e+03 | +| ep_rew_mean | 0.406 | +| time/ | | +| fps | 313 | +| iterations | 334 | +| time_elapsed | 1090 | +| total_timesteps | 342016 | +| train/ | | +| approx_kl | 1.6034806 | +| clip_fraction | 0.454 | +| clip_range | 0.2 | +| entropy_loss | -0.399 | +| explained_variance | -2.37 | +| learning_rate | 0.0001 | +| loss | -0.09 | +| n_updates | 63860 | +| policy_gradient_loss | -0.056 | +| value_loss | 0.000388 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.92e+03 | +| ep_rew_mean | 0.406 | +| time/ | | +| fps | 313 | +| iterations | 335 | +| time_elapsed | 1093 | +| total_timesteps | 343040 | +| train/ | | +| approx_kl | 2.018146 | +| clip_fraction | 0.465 | +| clip_range | 0.2 | +| entropy_loss | -0.377 | +| explained_variance | -0.49 | +| learning_rate | 0.0001 | +| loss | -0.0852 | +| n_updates | 63870 | +| policy_gradient_loss | -0.0583 | +| value_loss | 0.000844 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.92e+03 | +| ep_rew_mean | 0.401 | +| time/ | | +| fps | 313 | +| iterations | 336 | +| time_elapsed | 1096 | +| total_timesteps | 344064 | +| train/ | | +| approx_kl | 1.4990492 | +| clip_fraction | 0.413 | +| clip_range | 0.2 | +| entropy_loss | -0.302 | +| explained_variance | -0.72 | +| learning_rate | 0.0001 | +| loss | -0.0889 | +| n_updates | 63880 | +| policy_gradient_loss | -0.0574 | +| value_loss | 0.000691 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.92e+03 | +| ep_rew_mean | 0.401 | +| time/ | | +| fps | 313 | +| iterations | 337 | +| time_elapsed | 1099 | +| total_timesteps | 345088 | +| train/ | | +| approx_kl | 2.0321379 | +| clip_fraction | 0.448 | +| clip_range | 0.2 | +| entropy_loss | -0.347 | +| explained_variance | -6.56 | +| learning_rate | 0.0001 | +| loss | -0.0837 | +| n_updates | 63890 | +| policy_gradient_loss | -0.0584 | +| value_loss | 0.000469 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.92e+03 | +| ep_rew_mean | 0.401 | +| time/ | | +| fps | 313 | +| iterations | 338 | +| time_elapsed | 1102 | +| total_timesteps | 346112 | +| train/ | | +| approx_kl | 1.5713103 | +| clip_fraction | 0.478 | +| clip_range | 0.2 | +| entropy_loss | -0.425 | +| explained_variance | -0.819 | +| learning_rate | 0.0001 | +| loss | -0.0604 | +| n_updates | 63900 | +| policy_gradient_loss | -0.0603 | +| value_loss | 0.000667 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.93e+03 | +| ep_rew_mean | 0.398 | +| time/ | | +| fps | 313 | +| iterations | 339 | +| time_elapsed | 1105 | +| total_timesteps | 347136 | +| train/ | | +| approx_kl | 1.8891594 | +| clip_fraction | 0.512 | +| clip_range | 0.2 | +| entropy_loss | -0.491 | +| explained_variance | -1.35 | +| learning_rate | 0.0001 | +| loss | -0.0748 | +| n_updates | 63910 | +| policy_gradient_loss | -0.0608 | +| value_loss | 0.000497 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.93e+03 | +| ep_rew_mean | 0.397 | +| time/ | | +| fps | 313 | +| iterations | 340 | +| time_elapsed | 1108 | +| total_timesteps | 348160 | +| train/ | | +| approx_kl | 5.906361 | +| clip_fraction | 0.465 | +| clip_range | 0.2 | +| entropy_loss | -0.346 | +| explained_variance | -1.48 | +| learning_rate | 0.0001 | +| loss | -0.0869 | +| n_updates | 63920 | +| policy_gradient_loss | -0.0625 | +| value_loss | 0.00089 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.93e+03 | +| ep_rew_mean | 0.397 | +| time/ | | +| fps | 314 | +| iterations | 341 | +| time_elapsed | 1112 | +| total_timesteps | 349184 | +| train/ | | +| approx_kl | 2.1149616 | +| clip_fraction | 0.461 | +| clip_range | 0.2 | +| entropy_loss | -0.365 | +| explained_variance | -2.84 | +| learning_rate | 0.0001 | +| loss | -0.0916 | +| n_updates | 63930 | +| policy_gradient_loss | -0.0666 | +| value_loss | 0.000588 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.93e+03 | +| ep_rew_mean | 0.399 | +| time/ | | +| fps | 314 | +| iterations | 342 | +| time_elapsed | 1115 | +| total_timesteps | 350208 | +| train/ | | +| approx_kl | 2.2755527 | +| clip_fraction | 0.494 | +| clip_range | 0.2 | +| entropy_loss | -0.36 | +| explained_variance | -1.02 | +| learning_rate | 0.0001 | +| loss | -0.0882 | +| n_updates | 63940 | +| policy_gradient_loss | -0.0674 | +| value_loss | 0.000464 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.93e+03 | +| ep_rew_mean | 0.399 | +| time/ | | +| fps | 314 | +| iterations | 343 | +| time_elapsed | 1118 | +| total_timesteps | 351232 | +| train/ | | +| approx_kl | 2.1784053 | +| clip_fraction | 0.482 | +| clip_range | 0.2 | +| entropy_loss | -0.423 | +| explained_variance | -0.457 | +| learning_rate | 0.0001 | +| loss | -0.0623 | +| n_updates | 63950 | +| policy_gradient_loss | -0.0464 | +| value_loss | 0.00049 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.93e+03 | +| ep_rew_mean | 0.399 | +| time/ | | +| fps | 314 | +| iterations | 344 | +| time_elapsed | 1121 | +| total_timesteps | 352256 | +| train/ | | +| approx_kl | 1.5249907 | +| clip_fraction | 0.451 | +| clip_range | 0.2 | +| entropy_loss | -0.394 | +| explained_variance | -1.62 | +| learning_rate | 0.0001 | +| loss | -0.0885 | +| n_updates | 63960 | +| policy_gradient_loss | -0.0629 | +| value_loss | 0.000742 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.91e+03 | +| ep_rew_mean | 0.402 | +| time/ | | +| fps | 314 | +| iterations | 345 | +| time_elapsed | 1125 | +| total_timesteps | 353280 | +| train/ | | +| approx_kl | 1.4128735 | +| clip_fraction | 0.463 | +| clip_range | 0.2 | +| entropy_loss | -0.42 | +| explained_variance | -1.81 | +| learning_rate | 0.0001 | +| loss | -0.0765 | +| n_updates | 63970 | +| policy_gradient_loss | -0.056 | +| value_loss | 0.00059 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.91e+03 | +| ep_rew_mean | 0.402 | +| time/ | | +| fps | 314 | +| iterations | 346 | +| time_elapsed | 1128 | +| total_timesteps | 354304 | +| train/ | | +| approx_kl | 1.800601 | +| clip_fraction | 0.497 | +| clip_range | 0.2 | +| entropy_loss | -0.431 | +| explained_variance | -0.174 | +| learning_rate | 0.0001 | +| loss | -0.0806 | +| n_updates | 63980 | +| policy_gradient_loss | -0.0519 | +| value_loss | 0.000782 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.91e+03 | +| ep_rew_mean | 0.402 | +| time/ | | +| fps | 314 | +| iterations | 347 | +| time_elapsed | 1131 | +| total_timesteps | 355328 | +| train/ | | +| approx_kl | 2.0462272 | +| clip_fraction | 0.443 | +| clip_range | 0.2 | +| entropy_loss | -0.326 | +| explained_variance | -2.16 | +| learning_rate | 0.0001 | +| loss | -0.0558 | +| n_updates | 63990 | +| policy_gradient_loss | -0.053 | +| value_loss | 0.000865 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.92e+03 | +| ep_rew_mean | 0.401 | +| time/ | | +| fps | 313 | +| iterations | 348 | +| time_elapsed | 1134 | +| total_timesteps | 356352 | +| train/ | | +| approx_kl | 1.8379474 | +| clip_fraction | 0.449 | +| clip_range | 0.2 | +| entropy_loss | -0.366 | +| explained_variance | -3.16 | +| learning_rate | 0.0001 | +| loss | -0.093 | +| n_updates | 64000 | +| policy_gradient_loss | -0.063 | +| value_loss | 0.000529 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.92e+03 | +| ep_rew_mean | 0.401 | +| time/ | | +| fps | 313 | +| iterations | 349 | +| time_elapsed | 1138 | +| total_timesteps | 357376 | +| train/ | | +| approx_kl | 1.8005983 | +| clip_fraction | 0.453 | +| clip_range | 0.2 | +| entropy_loss | -0.367 | +| explained_variance | -0.952 | +| learning_rate | 0.0001 | +| loss | -0.0768 | +| n_updates | 64010 | +| policy_gradient_loss | -0.059 | +| value_loss | 0.000508 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.92e+03 | +| ep_rew_mean | 0.402 | +| time/ | | +| fps | 313 | +| iterations | 350 | +| time_elapsed | 1141 | +| total_timesteps | 358400 | +| train/ | | +| approx_kl | 2.0521767 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.388 | +| explained_variance | -1.76 | +| learning_rate | 0.0001 | +| loss | -0.0575 | +| n_updates | 64020 | +| policy_gradient_loss | -0.0627 | +| value_loss | 0.000801 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.93e+03 | +| ep_rew_mean | 0.402 | +| time/ | | +| fps | 313 | +| iterations | 351 | +| time_elapsed | 1144 | +| total_timesteps | 359424 | +| train/ | | +| approx_kl | 1.5026027 | +| clip_fraction | 0.464 | +| clip_range | 0.2 | +| entropy_loss | -0.383 | +| explained_variance | -2.09 | +| learning_rate | 0.0001 | +| loss | -0.0904 | +| n_updates | 64030 | +| policy_gradient_loss | -0.0629 | +| value_loss | 0.000567 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.93e+03 | +| ep_rew_mean | 0.402 | +| time/ | | +| fps | 313 | +| iterations | 352 | +| time_elapsed | 1148 | +| total_timesteps | 360448 | +| train/ | | +| approx_kl | 14.775136 | +| clip_fraction | 0.449 | +| clip_range | 0.2 | +| entropy_loss | -0.41 | +| explained_variance | -0.81 | +| learning_rate | 0.0001 | +| loss | -0.0634 | +| n_updates | 64040 | +| policy_gradient_loss | -0.0529 | +| value_loss | 0.000648 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.93e+03 | +| ep_rew_mean | 0.402 | +| time/ | | +| fps | 313 | +| iterations | 353 | +| time_elapsed | 1151 | +| total_timesteps | 361472 | +| train/ | | +| approx_kl | 2.0273795 | +| clip_fraction | 0.477 | +| clip_range | 0.2 | +| entropy_loss | -0.422 | +| explained_variance | -0.747 | +| learning_rate | 0.0001 | +| loss | -0.0911 | +| n_updates | 64050 | +| policy_gradient_loss | -0.059 | +| value_loss | 0.000609 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.93e+03 | +| ep_rew_mean | 0.407 | +| time/ | | +| fps | 313 | +| iterations | 354 | +| time_elapsed | 1154 | +| total_timesteps | 362496 | +| train/ | | +| approx_kl | 2.4043891 | +| clip_fraction | 0.476 | +| clip_range | 0.2 | +| entropy_loss | -0.422 | +| explained_variance | -1.63 | +| learning_rate | 0.0001 | +| loss | -0.0867 | +| n_updates | 64060 | +| policy_gradient_loss | -0.0643 | +| value_loss | 0.000938 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.93e+03 | +| ep_rew_mean | 0.407 | +| time/ | | +| fps | 314 | +| iterations | 355 | +| time_elapsed | 1157 | +| total_timesteps | 363520 | +| train/ | | +| approx_kl | 2.1650243 | +| clip_fraction | 0.46 | +| clip_range | 0.2 | +| entropy_loss | -0.359 | +| explained_variance | -5.04 | +| learning_rate | 0.0001 | +| loss | -0.0724 | +| n_updates | 64070 | +| policy_gradient_loss | -0.0642 | +| value_loss | 0.00054 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.93e+03 | +| ep_rew_mean | 0.408 | +| time/ | | +| fps | 314 | +| iterations | 356 | +| time_elapsed | 1160 | +| total_timesteps | 364544 | +| train/ | | +| approx_kl | 1.5840597 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.441 | +| explained_variance | -1.63 | +| learning_rate | 0.0001 | +| loss | -0.0764 | +| n_updates | 64080 | +| policy_gradient_loss | -0.0682 | +| value_loss | 0.000579 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.93e+03 | +| ep_rew_mean | 0.408 | +| time/ | | +| fps | 314 | +| iterations | 357 | +| time_elapsed | 1163 | +| total_timesteps | 365568 | +| train/ | | +| approx_kl | 2.2564654 | +| clip_fraction | 0.452 | +| clip_range | 0.2 | +| entropy_loss | -0.354 | +| explained_variance | -0.638 | +| learning_rate | 0.0001 | +| loss | -0.0634 | +| n_updates | 64090 | +| policy_gradient_loss | -0.0484 | +| value_loss | 0.000677 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.93e+03 | +| ep_rew_mean | 0.408 | +| time/ | | +| fps | 314 | +| iterations | 358 | +| time_elapsed | 1167 | +| total_timesteps | 366592 | +| train/ | | +| approx_kl | 2.5029874 | +| clip_fraction | 0.472 | +| clip_range | 0.2 | +| entropy_loss | -0.356 | +| explained_variance | -1.78 | +| learning_rate | 0.0001 | +| loss | -0.0546 | +| n_updates | 64100 | +| policy_gradient_loss | -0.0665 | +| value_loss | 0.000719 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.94e+03 | +| ep_rew_mean | 0.407 | +| time/ | | +| fps | 314 | +| iterations | 359 | +| time_elapsed | 1170 | +| total_timesteps | 367616 | +| train/ | | +| approx_kl | 3.4821143 | +| clip_fraction | 0.425 | +| clip_range | 0.2 | +| entropy_loss | -0.286 | +| explained_variance | -2.35 | +| learning_rate | 0.0001 | +| loss | -0.0854 | +| n_updates | 64110 | +| policy_gradient_loss | -0.0641 | +| value_loss | 0.000532 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.94e+03 | +| ep_rew_mean | 0.407 | +| time/ | | +| fps | 314 | +| iterations | 360 | +| time_elapsed | 1173 | +| total_timesteps | 368640 | +| train/ | | +| approx_kl | 1.7867892 | +| clip_fraction | 0.454 | +| clip_range | 0.2 | +| entropy_loss | -0.373 | +| explained_variance | -8.32 | +| learning_rate | 0.0001 | +| loss | -0.076 | +| n_updates | 64120 | +| policy_gradient_loss | -0.0615 | +| value_loss | 0.00035 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.94e+03 | +| ep_rew_mean | 0.411 | +| time/ | | +| fps | 314 | +| iterations | 361 | +| time_elapsed | 1176 | +| total_timesteps | 369664 | +| train/ | | +| approx_kl | 1.7488923 | +| clip_fraction | 0.512 | +| clip_range | 0.2 | +| entropy_loss | -0.447 | +| explained_variance | -0.563 | +| learning_rate | 0.0001 | +| loss | -0.0863 | +| n_updates | 64130 | +| policy_gradient_loss | -0.0633 | +| value_loss | 0.000591 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.94e+03 | +| ep_rew_mean | 0.411 | +| time/ | | +| fps | 314 | +| iterations | 362 | +| time_elapsed | 1179 | +| total_timesteps | 370688 | +| train/ | | +| approx_kl | 1.9248058 | +| clip_fraction | 0.415 | +| clip_range | 0.2 | +| entropy_loss | -0.309 | +| explained_variance | -3.14 | +| learning_rate | 0.0001 | +| loss | -0.0857 | +| n_updates | 64140 | +| policy_gradient_loss | -0.0475 | +| value_loss | 0.000427 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.93e+03 | +| ep_rew_mean | 0.414 | +| time/ | | +| fps | 314 | +| iterations | 363 | +| time_elapsed | 1182 | +| total_timesteps | 371712 | +| train/ | | +| approx_kl | 1.776987 | +| clip_fraction | 0.488 | +| clip_range | 0.2 | +| entropy_loss | -0.43 | +| explained_variance | -0.457 | +| learning_rate | 0.0001 | +| loss | -0.0801 | +| n_updates | 64150 | +| policy_gradient_loss | -0.0598 | +| value_loss | 0.000737 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.93e+03 | +| ep_rew_mean | 0.414 | +| time/ | | +| fps | 314 | +| iterations | 364 | +| time_elapsed | 1186 | +| total_timesteps | 372736 | +| train/ | | +| approx_kl | 2.01378 | +| clip_fraction | 0.49 | +| clip_range | 0.2 | +| entropy_loss | -0.422 | +| explained_variance | -0.608 | +| learning_rate | 0.0001 | +| loss | -0.0958 | +| n_updates | 64160 | +| policy_gradient_loss | -0.0678 | +| value_loss | 0.00048 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.94e+03 | +| ep_rew_mean | 0.412 | +| time/ | | +| fps | 314 | +| iterations | 365 | +| time_elapsed | 1189 | +| total_timesteps | 373760 | +| train/ | | +| approx_kl | 1.4891474 | +| clip_fraction | 0.488 | +| clip_range | 0.2 | +| entropy_loss | -0.447 | +| explained_variance | -2.45 | +| learning_rate | 0.0001 | +| loss | -0.073 | +| n_updates | 64170 | +| policy_gradient_loss | -0.0636 | +| value_loss | 0.000559 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.94e+03 | +| ep_rew_mean | 0.412 | +| time/ | | +| fps | 314 | +| iterations | 366 | +| time_elapsed | 1193 | +| total_timesteps | 374784 | +| train/ | | +| approx_kl | 2.1148436 | +| clip_fraction | 0.46 | +| clip_range | 0.2 | +| entropy_loss | -0.358 | +| explained_variance | -3.04 | +| learning_rate | 0.0001 | +| loss | -0.0885 | +| n_updates | 64180 | +| policy_gradient_loss | -0.0664 | +| value_loss | 0.000437 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.94e+03 | +| ep_rew_mean | 0.411 | +| time/ | | +| fps | 314 | +| iterations | 367 | +| time_elapsed | 1196 | +| total_timesteps | 375808 | +| train/ | | +| approx_kl | 2.020561 | +| clip_fraction | 0.473 | +| clip_range | 0.2 | +| entropy_loss | -0.433 | +| explained_variance | -1.96 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 64190 | +| policy_gradient_loss | -0.0624 | +| value_loss | 0.000492 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.94e+03 | +| ep_rew_mean | 0.411 | +| time/ | | +| fps | 314 | +| iterations | 368 | +| time_elapsed | 1200 | +| total_timesteps | 376832 | +| train/ | | +| approx_kl | 1.8836304 | +| clip_fraction | 0.484 | +| clip_range | 0.2 | +| entropy_loss | -0.466 | +| explained_variance | -0.28 | +| learning_rate | 0.0001 | +| loss | -0.0884 | +| n_updates | 64200 | +| policy_gradient_loss | -0.066 | +| value_loss | 0.00044 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.95e+03 | +| ep_rew_mean | 0.409 | +| time/ | | +| fps | 313 | +| iterations | 369 | +| time_elapsed | 1203 | +| total_timesteps | 377856 | +| train/ | | +| approx_kl | 1.5289679 | +| clip_fraction | 0.477 | +| clip_range | 0.2 | +| entropy_loss | -0.514 | +| explained_variance | -1.49 | +| learning_rate | 0.0001 | +| loss | -0.0835 | +| n_updates | 64210 | +| policy_gradient_loss | -0.0644 | +| value_loss | 0.000409 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.95e+03 | +| ep_rew_mean | 0.409 | +| time/ | | +| fps | 313 | +| iterations | 370 | +| time_elapsed | 1206 | +| total_timesteps | 378880 | +| train/ | | +| approx_kl | 2.3485112 | +| clip_fraction | 0.496 | +| clip_range | 0.2 | +| entropy_loss | -0.43 | +| explained_variance | -0.865 | +| learning_rate | 0.0001 | +| loss | -0.0722 | +| n_updates | 64220 | +| policy_gradient_loss | -0.0608 | +| value_loss | 0.000555 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.95e+03 | +| ep_rew_mean | 0.409 | +| time/ | | +| fps | 313 | +| iterations | 371 | +| time_elapsed | 1210 | +| total_timesteps | 379904 | +| train/ | | +| approx_kl | 1.9936737 | +| clip_fraction | 0.508 | +| clip_range | 0.2 | +| entropy_loss | -0.529 | +| explained_variance | -2.04 | +| learning_rate | 0.0001 | +| loss | -0.0804 | +| n_updates | 64230 | +| policy_gradient_loss | -0.0639 | +| value_loss | 0.000642 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.94e+03 | +| ep_rew_mean | 0.405 | +| time/ | | +| fps | 313 | +| iterations | 372 | +| time_elapsed | 1213 | +| total_timesteps | 380928 | +| train/ | | +| approx_kl | 1.6629803 | +| clip_fraction | 0.486 | +| clip_range | 0.2 | +| entropy_loss | -0.462 | +| explained_variance | -1.43 | +| learning_rate | 0.0001 | +| loss | -0.0697 | +| n_updates | 64240 | +| policy_gradient_loss | -0.0664 | +| value_loss | 0.000589 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.94e+03 | +| ep_rew_mean | 0.405 | +| time/ | | +| fps | 313 | +| iterations | 373 | +| time_elapsed | 1216 | +| total_timesteps | 381952 | +| train/ | | +| approx_kl | 1.6758053 | +| clip_fraction | 0.482 | +| clip_range | 0.2 | +| entropy_loss | -0.47 | +| explained_variance | -1.85 | +| learning_rate | 0.0001 | +| loss | -0.0841 | +| n_updates | 64250 | +| policy_gradient_loss | -0.0524 | +| value_loss | 0.000563 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.94e+03 | +| ep_rew_mean | 0.404 | +| time/ | | +| fps | 313 | +| iterations | 374 | +| time_elapsed | 1219 | +| total_timesteps | 382976 | +| train/ | | +| approx_kl | 1.4064845 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.507 | +| explained_variance | -2.72 | +| learning_rate | 0.0001 | +| loss | -0.0921 | +| n_updates | 64260 | +| policy_gradient_loss | -0.0637 | +| value_loss | 0.000402 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.93e+03 | +| ep_rew_mean | 0.405 | +| time/ | | +| fps | 314 | +| iterations | 375 | +| time_elapsed | 1222 | +| total_timesteps | 384000 | +| train/ | | +| approx_kl | 1.9649181 | +| clip_fraction | 0.503 | +| clip_range | 0.2 | +| entropy_loss | -0.47 | +| explained_variance | -0.716 | +| learning_rate | 0.0001 | +| loss | -0.0924 | +| n_updates | 64270 | +| policy_gradient_loss | -0.071 | +| value_loss | 0.000395 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.93e+03 | +| ep_rew_mean | 0.405 | +| time/ | | +| fps | 314 | +| iterations | 376 | +| time_elapsed | 1225 | +| total_timesteps | 385024 | +| train/ | | +| approx_kl | 1.7271904 | +| clip_fraction | 0.496 | +| clip_range | 0.2 | +| entropy_loss | -0.425 | +| explained_variance | -0.782 | +| learning_rate | 0.0001 | +| loss | -0.0949 | +| n_updates | 64280 | +| policy_gradient_loss | -0.0644 | +| value_loss | 0.000659 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.93e+03 | +| ep_rew_mean | 0.405 | +| time/ | | +| fps | 314 | +| iterations | 377 | +| time_elapsed | 1229 | +| total_timesteps | 386048 | +| train/ | | +| approx_kl | 1.5217957 | +| clip_fraction | 0.486 | +| clip_range | 0.2 | +| entropy_loss | -0.46 | +| explained_variance | -4 | +| learning_rate | 0.0001 | +| loss | -0.0923 | +| n_updates | 64290 | +| policy_gradient_loss | -0.0672 | +| value_loss | 0.000615 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.93e+03 | +| ep_rew_mean | 0.405 | +| time/ | | +| fps | 314 | +| iterations | 378 | +| time_elapsed | 1232 | +| total_timesteps | 387072 | +| train/ | | +| approx_kl | 1.8088237 | +| clip_fraction | 0.523 | +| clip_range | 0.2 | +| entropy_loss | -0.507 | +| explained_variance | -0.123 | +| learning_rate | 0.0001 | +| loss | -0.0885 | +| n_updates | 64300 | +| policy_gradient_loss | -0.0601 | +| value_loss | 0.000307 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.93e+03 | +| ep_rew_mean | 0.406 | +| time/ | | +| fps | 314 | +| iterations | 379 | +| time_elapsed | 1235 | +| total_timesteps | 388096 | +| train/ | | +| approx_kl | 2.0016131 | +| clip_fraction | 0.509 | +| clip_range | 0.2 | +| entropy_loss | -0.466 | +| explained_variance | -0.927 | +| learning_rate | 0.0001 | +| loss | -0.1 | +| n_updates | 64310 | +| policy_gradient_loss | -0.0746 | +| value_loss | 0.000629 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.93e+03 | +| ep_rew_mean | 0.406 | +| time/ | | +| fps | 314 | +| iterations | 380 | +| time_elapsed | 1238 | +| total_timesteps | 389120 | +| train/ | | +| approx_kl | 1.7858942 | +| clip_fraction | 0.498 | +| clip_range | 0.2 | +| entropy_loss | -0.423 | +| explained_variance | -1.47 | +| learning_rate | 0.0001 | +| loss | -0.0878 | +| n_updates | 64320 | +| policy_gradient_loss | -0.0696 | +| value_loss | 0.000668 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.93e+03 | +| ep_rew_mean | 0.403 | +| time/ | | +| fps | 314 | +| iterations | 381 | +| time_elapsed | 1241 | +| total_timesteps | 390144 | +| train/ | | +| approx_kl | 1.8219497 | +| clip_fraction | 0.482 | +| clip_range | 0.2 | +| entropy_loss | -0.391 | +| explained_variance | -1.66 | +| learning_rate | 0.0001 | +| loss | -0.091 | +| n_updates | 64330 | +| policy_gradient_loss | -0.0603 | +| value_loss | 0.000415 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.93e+03 | +| ep_rew_mean | 0.403 | +| time/ | | +| fps | 314 | +| iterations | 382 | +| time_elapsed | 1244 | +| total_timesteps | 391168 | +| train/ | | +| approx_kl | 1.6760724 | +| clip_fraction | 0.47 | +| clip_range | 0.2 | +| entropy_loss | -0.487 | +| explained_variance | -3.61 | +| learning_rate | 0.0001 | +| loss | -0.063 | +| n_updates | 64340 | +| policy_gradient_loss | -0.0629 | +| value_loss | 0.000266 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.94e+03 | +| ep_rew_mean | 0.401 | +| time/ | | +| fps | 314 | +| iterations | 383 | +| time_elapsed | 1248 | +| total_timesteps | 392192 | +| train/ | | +| approx_kl | 1.8066931 | +| clip_fraction | 0.534 | +| clip_range | 0.2 | +| entropy_loss | -0.517 | +| explained_variance | -0.462 | +| learning_rate | 0.0001 | +| loss | -0.1 | +| n_updates | 64350 | +| policy_gradient_loss | -0.0648 | +| value_loss | 0.000393 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.94e+03 | +| ep_rew_mean | 0.401 | +| time/ | | +| fps | 314 | +| iterations | 384 | +| time_elapsed | 1251 | +| total_timesteps | 393216 | +| train/ | | +| approx_kl | 1.7039499 | +| clip_fraction | 0.493 | +| clip_range | 0.2 | +| entropy_loss | -0.463 | +| explained_variance | -1.44 | +| learning_rate | 0.0001 | +| loss | -0.0799 | +| n_updates | 64360 | +| policy_gradient_loss | -0.0636 | +| value_loss | 0.000451 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.95e+03 | +| ep_rew_mean | 0.397 | +| time/ | | +| fps | 314 | +| iterations | 385 | +| time_elapsed | 1254 | +| total_timesteps | 394240 | +| train/ | | +| approx_kl | 1.985139 | +| clip_fraction | 0.482 | +| clip_range | 0.2 | +| entropy_loss | -0.416 | +| explained_variance | -2.5 | +| learning_rate | 0.0001 | +| loss | -0.0727 | +| n_updates | 64370 | +| policy_gradient_loss | -0.0613 | +| value_loss | 0.000578 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.95e+03 | +| ep_rew_mean | 0.397 | +| time/ | | +| fps | 314 | +| iterations | 386 | +| time_elapsed | 1258 | +| total_timesteps | 395264 | +| train/ | | +| approx_kl | 2.876234 | +| clip_fraction | 0.504 | +| clip_range | 0.2 | +| entropy_loss | -0.428 | +| explained_variance | -1.2 | +| learning_rate | 0.0001 | +| loss | -0.0928 | +| n_updates | 64380 | +| policy_gradient_loss | -0.0655 | +| value_loss | 0.000236 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.95e+03 | +| ep_rew_mean | 0.396 | +| time/ | | +| fps | 314 | +| iterations | 387 | +| time_elapsed | 1261 | +| total_timesteps | 396288 | +| train/ | | +| approx_kl | 1.4576786 | +| clip_fraction | 0.504 | +| clip_range | 0.2 | +| entropy_loss | -0.488 | +| explained_variance | -1.19 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 64390 | +| policy_gradient_loss | -0.0671 | +| value_loss | 0.000589 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.95e+03 | +| ep_rew_mean | 0.396 | +| time/ | | +| fps | 314 | +| iterations | 388 | +| time_elapsed | 1264 | +| total_timesteps | 397312 | +| train/ | | +| approx_kl | 1.8553383 | +| clip_fraction | 0.494 | +| clip_range | 0.2 | +| entropy_loss | -0.427 | +| explained_variance | -2.65 | +| learning_rate | 0.0001 | +| loss | -0.0895 | +| n_updates | 64400 | +| policy_gradient_loss | -0.0673 | +| value_loss | 0.000732 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.95e+03 | +| ep_rew_mean | 0.396 | +| time/ | | +| fps | 314 | +| iterations | 389 | +| time_elapsed | 1267 | +| total_timesteps | 398336 | +| train/ | | +| approx_kl | 1.5896786 | +| clip_fraction | 0.485 | +| clip_range | 0.2 | +| entropy_loss | -0.482 | +| explained_variance | -1.36 | +| learning_rate | 0.0001 | +| loss | -0.096 | +| n_updates | 64410 | +| policy_gradient_loss | -0.0609 | +| value_loss | 0.000457 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.96e+03 | +| ep_rew_mean | 0.394 | +| time/ | | +| fps | 314 | +| iterations | 390 | +| time_elapsed | 1271 | +| total_timesteps | 399360 | +| train/ | | +| approx_kl | 1.7125092 | +| clip_fraction | 0.509 | +| clip_range | 0.2 | +| entropy_loss | -0.537 | +| explained_variance | -10.3 | +| learning_rate | 0.0001 | +| loss | -0.0945 | +| n_updates | 64420 | +| policy_gradient_loss | -0.0707 | +| value_loss | 0.000187 | +--------------------------------------- + +Current state: Champion.Level2.RyuVsKen +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.95e+03 | +| ep_rew_mean | 0.398 | +| time/ | | +| fps | 314 | +| iterations | 391 | +| time_elapsed | 1274 | +| total_timesteps | 400384 | +| train/ | | +| approx_kl | 1.8932314 | +| clip_fraction | 0.532 | +| clip_range | 0.2 | +| entropy_loss | -0.477 | +| explained_variance | -0.293 | +| learning_rate | 0.0001 | +| loss | -0.105 | +| n_updates | 64430 | +| policy_gradient_loss | -0.0673 | +| value_loss | 0.000645 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.95e+03 | +| ep_rew_mean | 0.396 | +| time/ | | +| fps | 314 | +| iterations | 392 | +| time_elapsed | 1277 | +| total_timesteps | 401408 | +| train/ | | +| approx_kl | 2.0059464 | +| clip_fraction | 0.523 | +| clip_range | 0.2 | +| entropy_loss | -0.469 | +| explained_variance | -0.511 | +| learning_rate | 0.0001 | +| loss | -0.0696 | +| n_updates | 64440 | +| policy_gradient_loss | -0.0579 | +| value_loss | 0.000846 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.95e+03 | +| ep_rew_mean | 0.396 | +| time/ | | +| fps | 314 | +| iterations | 393 | +| time_elapsed | 1280 | +| total_timesteps | 402432 | +| train/ | | +| approx_kl | 1.9460074 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.399 | +| explained_variance | -2.42 | +| learning_rate | 0.0001 | +| loss | -0.107 | +| n_updates | 64450 | +| policy_gradient_loss | -0.0656 | +| value_loss | 0.000753 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.94e+03 | +| ep_rew_mean | 0.396 | +| time/ | | +| fps | 314 | +| iterations | 394 | +| time_elapsed | 1283 | +| total_timesteps | 403456 | +| train/ | | +| approx_kl | 2.2416964 | +| clip_fraction | 0.498 | +| clip_range | 0.2 | +| entropy_loss | -0.462 | +| explained_variance | -0.843 | +| learning_rate | 0.0001 | +| loss | -0.0994 | +| n_updates | 64460 | +| policy_gradient_loss | -0.0732 | +| value_loss | 0.000572 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.94e+03 | +| ep_rew_mean | 0.392 | +| time/ | | +| fps | 314 | +| iterations | 395 | +| time_elapsed | 1286 | +| total_timesteps | 404480 | +| train/ | | +| approx_kl | 2.6703086 | +| clip_fraction | 0.51 | +| clip_range | 0.2 | +| entropy_loss | -0.444 | +| explained_variance | -0.892 | +| learning_rate | 0.0001 | +| loss | -0.0973 | +| n_updates | 64470 | +| policy_gradient_loss | -0.0686 | +| value_loss | 0.00062 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.93e+03 | +| ep_rew_mean | 0.387 | +| time/ | | +| fps | 314 | +| iterations | 396 | +| time_elapsed | 1289 | +| total_timesteps | 405504 | +| train/ | | +| approx_kl | 2.0243087 | +| clip_fraction | 0.454 | +| clip_range | 0.2 | +| entropy_loss | -0.342 | +| explained_variance | -2.81 | +| learning_rate | 0.0001 | +| loss | -0.0705 | +| n_updates | 64480 | +| policy_gradient_loss | -0.0621 | +| value_loss | 0.000389 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.93e+03 | +| ep_rew_mean | 0.384 | +| time/ | | +| fps | 314 | +| iterations | 397 | +| time_elapsed | 1292 | +| total_timesteps | 406528 | +| train/ | | +| approx_kl | 2.389278 | +| clip_fraction | 0.458 | +| clip_range | 0.2 | +| entropy_loss | -0.358 | +| explained_variance | -0.257 | +| learning_rate | 0.0001 | +| loss | -0.083 | +| n_updates | 64490 | +| policy_gradient_loss | -0.0618 | +| value_loss | 0.000596 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.93e+03 | +| ep_rew_mean | 0.384 | +| time/ | | +| fps | 314 | +| iterations | 398 | +| time_elapsed | 1296 | +| total_timesteps | 407552 | +| train/ | | +| approx_kl | 2.0128238 | +| clip_fraction | 0.457 | +| clip_range | 0.2 | +| entropy_loss | -0.331 | +| explained_variance | -0.378 | +| learning_rate | 0.0001 | +| loss | -0.0701 | +| n_updates | 64500 | +| policy_gradient_loss | -0.0634 | +| value_loss | 0.000688 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.93e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 314 | +| iterations | 399 | +| time_elapsed | 1299 | +| total_timesteps | 408576 | +| train/ | | +| approx_kl | 1.6114583 | +| clip_fraction | 0.474 | +| clip_range | 0.2 | +| entropy_loss | -0.398 | +| explained_variance | -2.03 | +| learning_rate | 0.0001 | +| loss | -0.107 | +| n_updates | 64510 | +| policy_gradient_loss | -0.0672 | +| value_loss | 0.000536 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.93e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 314 | +| iterations | 400 | +| time_elapsed | 1302 | +| total_timesteps | 409600 | +| train/ | | +| approx_kl | 1.7267416 | +| clip_fraction | 0.394 | +| clip_range | 0.2 | +| entropy_loss | -0.3 | +| explained_variance | -0.851 | +| learning_rate | 0.0001 | +| loss | -0.0749 | +| n_updates | 64520 | +| policy_gradient_loss | -0.0534 | +| value_loss | 0.000572 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.94e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 314 | +| iterations | 401 | +| time_elapsed | 1305 | +| total_timesteps | 410624 | +| train/ | | +| approx_kl | 2.8690646 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.374 | +| explained_variance | -1.33 | +| learning_rate | 0.0001 | +| loss | -0.0848 | +| n_updates | 64530 | +| policy_gradient_loss | -0.0662 | +| value_loss | 0.000477 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.93e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 314 | +| iterations | 402 | +| time_elapsed | 1309 | +| total_timesteps | 411648 | +| train/ | | +| approx_kl | 2.0241632 | +| clip_fraction | 0.505 | +| clip_range | 0.2 | +| entropy_loss | -0.439 | +| explained_variance | -1.43 | +| learning_rate | 0.0001 | +| loss | -0.0912 | +| n_updates | 64540 | +| policy_gradient_loss | -0.0588 | +| value_loss | 0.000459 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.93e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 314 | +| iterations | 403 | +| time_elapsed | 1312 | +| total_timesteps | 412672 | +| train/ | | +| approx_kl | 1.9212523 | +| clip_fraction | 0.488 | +| clip_range | 0.2 | +| entropy_loss | -0.454 | +| explained_variance | -0.877 | +| learning_rate | 0.0001 | +| loss | -0.0945 | +| n_updates | 64550 | +| policy_gradient_loss | -0.0616 | +| value_loss | 0.00068 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.93e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 314 | +| iterations | 404 | +| time_elapsed | 1316 | +| total_timesteps | 413696 | +| train/ | | +| approx_kl | 2.241074 | +| clip_fraction | 0.443 | +| clip_range | 0.2 | +| entropy_loss | -0.35 | +| explained_variance | -1.31 | +| learning_rate | 0.0001 | +| loss | -0.072 | +| n_updates | 64560 | +| policy_gradient_loss | -0.058 | +| value_loss | 0.000425 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.92e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 314 | +| iterations | 405 | +| time_elapsed | 1319 | +| total_timesteps | 414720 | +| train/ | | +| approx_kl | 1.800976 | +| clip_fraction | 0.485 | +| clip_range | 0.2 | +| entropy_loss | -0.477 | +| explained_variance | -1.12 | +| learning_rate | 0.0001 | +| loss | -0.0737 | +| n_updates | 64570 | +| policy_gradient_loss | -0.0621 | +| value_loss | 0.000316 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.92e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 314 | +| iterations | 406 | +| time_elapsed | 1322 | +| total_timesteps | 415744 | +| train/ | | +| approx_kl | 1.5984144 | +| clip_fraction | 0.492 | +| clip_range | 0.2 | +| entropy_loss | -0.485 | +| explained_variance | -0.658 | +| learning_rate | 0.0001 | +| loss | -0.0744 | +| n_updates | 64580 | +| policy_gradient_loss | -0.0651 | +| value_loss | 0.000265 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.92e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 314 | +| iterations | 407 | +| time_elapsed | 1326 | +| total_timesteps | 416768 | +| train/ | | +| approx_kl | 3.2817087 | +| clip_fraction | 0.491 | +| clip_range | 0.2 | +| entropy_loss | -0.453 | +| explained_variance | -2.06 | +| learning_rate | 0.0001 | +| loss | -0.087 | +| n_updates | 64590 | +| policy_gradient_loss | -0.0739 | +| value_loss | 0.000411 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.92e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 314 | +| iterations | 408 | +| time_elapsed | 1329 | +| total_timesteps | 417792 | +| train/ | | +| approx_kl | 1.6745505 | +| clip_fraction | 0.534 | +| clip_range | 0.2 | +| entropy_loss | -0.497 | +| explained_variance | -1.71 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 64600 | +| policy_gradient_loss | -0.0705 | +| value_loss | 0.000314 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.92e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 314 | +| iterations | 409 | +| time_elapsed | 1332 | +| total_timesteps | 418816 | +| train/ | | +| approx_kl | 3.9073114 | +| clip_fraction | 0.464 | +| clip_range | 0.2 | +| entropy_loss | -0.439 | +| explained_variance | -0.16 | +| learning_rate | 0.0001 | +| loss | -0.0939 | +| n_updates | 64610 | +| policy_gradient_loss | -0.0568 | +| value_loss | 0.000387 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.92e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 314 | +| iterations | 410 | +| time_elapsed | 1335 | +| total_timesteps | 419840 | +| train/ | | +| approx_kl | 1.8963509 | +| clip_fraction | 0.479 | +| clip_range | 0.2 | +| entropy_loss | -0.415 | +| explained_variance | -3.74 | +| learning_rate | 0.0001 | +| loss | -0.088 | +| n_updates | 64620 | +| policy_gradient_loss | -0.0613 | +| value_loss | 0.000712 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.92e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 314 | +| iterations | 411 | +| time_elapsed | 1339 | +| total_timesteps | 420864 | +| train/ | | +| approx_kl | 2.0341842 | +| clip_fraction | 0.443 | +| clip_range | 0.2 | +| entropy_loss | -0.392 | +| explained_variance | -1.21 | +| learning_rate | 0.0001 | +| loss | -0.0751 | +| n_updates | 64630 | +| policy_gradient_loss | -0.0598 | +| value_loss | 0.000601 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.93e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 314 | +| iterations | 412 | +| time_elapsed | 1342 | +| total_timesteps | 421888 | +| train/ | | +| approx_kl | 1.7254064 | +| clip_fraction | 0.501 | +| clip_range | 0.2 | +| entropy_loss | -0.467 | +| explained_variance | -2.16 | +| learning_rate | 0.0001 | +| loss | -0.0907 | +| n_updates | 64640 | +| policy_gradient_loss | -0.067 | +| value_loss | 0.000487 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.94e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 314 | +| iterations | 413 | +| time_elapsed | 1345 | +| total_timesteps | 422912 | +| train/ | | +| approx_kl | 1.8397007 | +| clip_fraction | 0.466 | +| clip_range | 0.2 | +| entropy_loss | -0.388 | +| explained_variance | -0.525 | +| learning_rate | 0.0001 | +| loss | -0.0677 | +| n_updates | 64650 | +| policy_gradient_loss | -0.0605 | +| value_loss | 0.000517 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.94e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 314 | +| iterations | 414 | +| time_elapsed | 1348 | +| total_timesteps | 423936 | +| train/ | | +| approx_kl | 1.8433113 | +| clip_fraction | 0.453 | +| clip_range | 0.2 | +| entropy_loss | -0.35 | +| explained_variance | -2.15 | +| learning_rate | 0.0001 | +| loss | -0.0588 | +| n_updates | 64660 | +| policy_gradient_loss | -0.061 | +| value_loss | 0.000502 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.94e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 314 | +| iterations | 415 | +| time_elapsed | 1351 | +| total_timesteps | 424960 | +| train/ | | +| approx_kl | 1.9536766 | +| clip_fraction | 0.478 | +| clip_range | 0.2 | +| entropy_loss | -0.395 | +| explained_variance | -1.11 | +| learning_rate | 0.0001 | +| loss | -0.0734 | +| n_updates | 64670 | +| policy_gradient_loss | -0.0603 | +| value_loss | 0.000379 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.94e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 314 | +| iterations | 416 | +| time_elapsed | 1354 | +| total_timesteps | 425984 | +| train/ | | +| approx_kl | 2.0243077 | +| clip_fraction | 0.446 | +| clip_range | 0.2 | +| entropy_loss | -0.369 | +| explained_variance | -0.914 | +| learning_rate | 0.0001 | +| loss | -0.0812 | +| n_updates | 64680 | +| policy_gradient_loss | -0.0576 | +| value_loss | 0.00036 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.91e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 314 | +| iterations | 417 | +| time_elapsed | 1358 | +| total_timesteps | 427008 | +| train/ | | +| approx_kl | 1.925879 | +| clip_fraction | 0.442 | +| clip_range | 0.2 | +| entropy_loss | -0.328 | +| explained_variance | -3.72 | +| learning_rate | 0.0001 | +| loss | -0.0895 | +| n_updates | 64690 | +| policy_gradient_loss | -0.0657 | +| value_loss | 0.000364 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.91e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 314 | +| iterations | 418 | +| time_elapsed | 1361 | +| total_timesteps | 428032 | +| train/ | | +| approx_kl | 1.8520908 | +| clip_fraction | 0.397 | +| clip_range | 0.2 | +| entropy_loss | -0.295 | +| explained_variance | -0.0944 | +| learning_rate | 0.0001 | +| loss | -0.0755 | +| n_updates | 64700 | +| policy_gradient_loss | -0.0412 | +| value_loss | 0.000631 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.91e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 314 | +| iterations | 419 | +| time_elapsed | 1364 | +| total_timesteps | 429056 | +| train/ | | +| approx_kl | 1.8908422 | +| clip_fraction | 0.457 | +| clip_range | 0.2 | +| entropy_loss | -0.406 | +| explained_variance | -4.05 | +| learning_rate | 0.0001 | +| loss | -0.0759 | +| n_updates | 64710 | +| policy_gradient_loss | -0.0692 | +| value_loss | 0.000466 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.91e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 314 | +| iterations | 420 | +| time_elapsed | 1368 | +| total_timesteps | 430080 | +| train/ | | +| approx_kl | 1.8180102 | +| clip_fraction | 0.452 | +| clip_range | 0.2 | +| entropy_loss | -0.37 | +| explained_variance | -0.673 | +| learning_rate | 0.0001 | +| loss | -0.0884 | +| n_updates | 64720 | +| policy_gradient_loss | -0.0607 | +| value_loss | 0.000478 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.91e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 314 | +| iterations | 421 | +| time_elapsed | 1371 | +| total_timesteps | 431104 | +| train/ | | +| approx_kl | 6.4263773 | +| clip_fraction | 0.453 | +| clip_range | 0.2 | +| entropy_loss | -0.377 | +| explained_variance | -3.03 | +| learning_rate | 0.0001 | +| loss | -0.0733 | +| n_updates | 64730 | +| policy_gradient_loss | -0.000838 | +| value_loss | 0.000406 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.91e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 314 | +| iterations | 422 | +| time_elapsed | 1375 | +| total_timesteps | 432128 | +| train/ | | +| approx_kl | 1.3475163 | +| clip_fraction | 0.464 | +| clip_range | 0.2 | +| entropy_loss | -0.474 | +| explained_variance | -0.568 | +| learning_rate | 0.0001 | +| loss | -0.0887 | +| n_updates | 64740 | +| policy_gradient_loss | -0.0538 | +| value_loss | 0.000281 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.91e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 314 | +| iterations | 423 | +| time_elapsed | 1378 | +| total_timesteps | 433152 | +| train/ | | +| approx_kl | 2.0170488 | +| clip_fraction | 0.437 | +| clip_range | 0.2 | +| entropy_loss | -0.336 | +| explained_variance | -1.53 | +| learning_rate | 0.0001 | +| loss | -0.07 | +| n_updates | 64750 | +| policy_gradient_loss | -0.0615 | +| value_loss | 0.000564 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.91e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 314 | +| iterations | 424 | +| time_elapsed | 1381 | +| total_timesteps | 434176 | +| train/ | | +| approx_kl | 1.6390789 | +| clip_fraction | 0.513 | +| clip_range | 0.2 | +| entropy_loss | -0.509 | +| explained_variance | -0.928 | +| learning_rate | 0.0001 | +| loss | -0.092 | +| n_updates | 64760 | +| policy_gradient_loss | -0.0643 | +| value_loss | 0.000538 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.91e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 314 | +| iterations | 425 | +| time_elapsed | 1385 | +| total_timesteps | 435200 | +| train/ | | +| approx_kl | 1.655461 | +| clip_fraction | 0.454 | +| clip_range | 0.2 | +| entropy_loss | -0.378 | +| explained_variance | -1.4 | +| learning_rate | 0.0001 | +| loss | -0.0724 | +| n_updates | 64770 | +| policy_gradient_loss | -0.0649 | +| value_loss | 0.000565 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.91e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 314 | +| iterations | 426 | +| time_elapsed | 1388 | +| total_timesteps | 436224 | +| train/ | | +| approx_kl | 1.886131 | +| clip_fraction | 0.472 | +| clip_range | 0.2 | +| entropy_loss | -0.385 | +| explained_variance | -1.71 | +| learning_rate | 0.0001 | +| loss | -0.0576 | +| n_updates | 64780 | +| policy_gradient_loss | -0.0644 | +| value_loss | 0.000361 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.9e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 314 | +| iterations | 427 | +| time_elapsed | 1392 | +| total_timesteps | 437248 | +| train/ | | +| approx_kl | 2.195229 | +| clip_fraction | 0.453 | +| clip_range | 0.2 | +| entropy_loss | -0.375 | +| explained_variance | -0.736 | +| learning_rate | 0.0001 | +| loss | -0.0805 | +| n_updates | 64790 | +| policy_gradient_loss | -0.0634 | +| value_loss | 0.000538 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.89e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 314 | +| iterations | 428 | +| time_elapsed | 1395 | +| total_timesteps | 438272 | +| train/ | | +| approx_kl | 1.7567856 | +| clip_fraction | 0.467 | +| clip_range | 0.2 | +| entropy_loss | -0.434 | +| explained_variance | -1.23 | +| learning_rate | 0.0001 | +| loss | -0.0897 | +| n_updates | 64800 | +| policy_gradient_loss | -0.0662 | +| value_loss | 0.000539 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.89e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 314 | +| iterations | 429 | +| time_elapsed | 1398 | +| total_timesteps | 439296 | +| train/ | | +| approx_kl | 1.5778351 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.473 | +| explained_variance | -0.244 | +| learning_rate | 0.0001 | +| loss | -0.0945 | +| n_updates | 64810 | +| policy_gradient_loss | -0.0658 | +| value_loss | 0.000652 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.89e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 314 | +| iterations | 430 | +| time_elapsed | 1401 | +| total_timesteps | 440320 | +| train/ | | +| approx_kl | 1.8968529 | +| clip_fraction | 0.473 | +| clip_range | 0.2 | +| entropy_loss | -0.361 | +| explained_variance | -1.86 | +| learning_rate | 0.0001 | +| loss | -0.0965 | +| n_updates | 64820 | +| policy_gradient_loss | -0.0675 | +| value_loss | 0.000624 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 314 | +| iterations | 431 | +| time_elapsed | 1404 | +| total_timesteps | 441344 | +| train/ | | +| approx_kl | 1.7906685 | +| clip_fraction | 0.464 | +| clip_range | 0.2 | +| entropy_loss | -0.407 | +| explained_variance | -1.27 | +| learning_rate | 0.0001 | +| loss | -0.0988 | +| n_updates | 64830 | +| policy_gradient_loss | -0.0662 | +| value_loss | 0.000576 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 314 | +| iterations | 432 | +| time_elapsed | 1407 | +| total_timesteps | 442368 | +| train/ | | +| approx_kl | 2.2024555 | +| clip_fraction | 0.445 | +| clip_range | 0.2 | +| entropy_loss | -0.39 | +| explained_variance | -0.674 | +| learning_rate | 0.0001 | +| loss | -0.0775 | +| n_updates | 64840 | +| policy_gradient_loss | -0.0585 | +| value_loss | 0.000768 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 314 | +| iterations | 433 | +| time_elapsed | 1410 | +| total_timesteps | 443392 | +| train/ | | +| approx_kl | 1.919905 | +| clip_fraction | 0.44 | +| clip_range | 0.2 | +| entropy_loss | -0.288 | +| explained_variance | -0.0639 | +| learning_rate | 0.0001 | +| loss | -0.0907 | +| n_updates | 64850 | +| policy_gradient_loss | -0.0677 | +| value_loss | 0.000578 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 314 | +| iterations | 434 | +| time_elapsed | 1413 | +| total_timesteps | 444416 | +| train/ | | +| approx_kl | 2.1727543 | +| clip_fraction | 0.441 | +| clip_range | 0.2 | +| entropy_loss | -0.314 | +| explained_variance | -1.46 | +| learning_rate | 0.0001 | +| loss | -0.089 | +| n_updates | 64860 | +| policy_gradient_loss | -0.0618 | +| value_loss | 0.000484 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 314 | +| iterations | 435 | +| time_elapsed | 1417 | +| total_timesteps | 445440 | +| train/ | | +| approx_kl | 1.901705 | +| clip_fraction | 0.493 | +| clip_range | 0.2 | +| entropy_loss | -0.425 | +| explained_variance | -1.83 | +| learning_rate | 0.0001 | +| loss | -0.0922 | +| n_updates | 64870 | +| policy_gradient_loss | -0.0691 | +| value_loss | 0.000215 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 314 | +| iterations | 436 | +| time_elapsed | 1420 | +| total_timesteps | 446464 | +| train/ | | +| approx_kl | 2.1333847 | +| clip_fraction | 0.447 | +| clip_range | 0.2 | +| entropy_loss | -0.348 | +| explained_variance | -0.767 | +| learning_rate | 0.0001 | +| loss | -0.0833 | +| n_updates | 64880 | +| policy_gradient_loss | -0.0571 | +| value_loss | 0.000378 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 314 | +| iterations | 437 | +| time_elapsed | 1423 | +| total_timesteps | 447488 | +| train/ | | +| approx_kl | 1.8142686 | +| clip_fraction | 0.454 | +| clip_range | 0.2 | +| entropy_loss | -0.329 | +| explained_variance | -0.53 | +| learning_rate | 0.0001 | +| loss | -0.0964 | +| n_updates | 64890 | +| policy_gradient_loss | -0.061 | +| value_loss | 0.000675 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 314 | +| iterations | 438 | +| time_elapsed | 1427 | +| total_timesteps | 448512 | +| train/ | | +| approx_kl | 1.9051287 | +| clip_fraction | 0.425 | +| clip_range | 0.2 | +| entropy_loss | -0.315 | +| explained_variance | -3.05 | +| learning_rate | 0.0001 | +| loss | -0.0713 | +| n_updates | 64900 | +| policy_gradient_loss | -0.0622 | +| value_loss | 0.000468 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 314 | +| iterations | 439 | +| time_elapsed | 1430 | +| total_timesteps | 449536 | +| train/ | | +| approx_kl | 1.6915233 | +| clip_fraction | 0.413 | +| clip_range | 0.2 | +| entropy_loss | -0.29 | +| explained_variance | -1.48 | +| learning_rate | 0.0001 | +| loss | -0.0752 | +| n_updates | 64910 | +| policy_gradient_loss | -0.0494 | +| value_loss | 0.000393 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 314 | +| iterations | 440 | +| time_elapsed | 1434 | +| total_timesteps | 450560 | +| train/ | | +| approx_kl | 1.6643674 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.385 | +| explained_variance | -1.18 | +| learning_rate | 0.0001 | +| loss | -0.087 | +| n_updates | 64920 | +| policy_gradient_loss | -0.0693 | +| value_loss | 0.000451 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 314 | +| iterations | 441 | +| time_elapsed | 1437 | +| total_timesteps | 451584 | +| train/ | | +| approx_kl | 1.6654401 | +| clip_fraction | 0.445 | +| clip_range | 0.2 | +| entropy_loss | -0.337 | +| explained_variance | -1.87 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 64930 | +| policy_gradient_loss | -0.0621 | +| value_loss | 0.000447 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 313 | +| iterations | 442 | +| time_elapsed | 1441 | +| total_timesteps | 452608 | +| train/ | | +| approx_kl | 2.518581 | +| clip_fraction | 0.456 | +| clip_range | 0.2 | +| entropy_loss | -0.365 | +| explained_variance | -0.457 | +| learning_rate | 0.0001 | +| loss | -0.1 | +| n_updates | 64940 | +| policy_gradient_loss | -0.0606 | +| value_loss | 0.000516 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 313 | +| iterations | 443 | +| time_elapsed | 1445 | +| total_timesteps | 453632 | +| train/ | | +| approx_kl | 1.79268 | +| clip_fraction | 0.454 | +| clip_range | 0.2 | +| entropy_loss | -0.404 | +| explained_variance | -0.189 | +| learning_rate | 0.0001 | +| loss | -0.072 | +| n_updates | 64950 | +| policy_gradient_loss | -0.0634 | +| value_loss | 0.000846 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 313 | +| iterations | 444 | +| time_elapsed | 1448 | +| total_timesteps | 454656 | +| train/ | | +| approx_kl | 2.4733407 | +| clip_fraction | 0.524 | +| clip_range | 0.2 | +| entropy_loss | -0.496 | +| explained_variance | -2.29 | +| learning_rate | 0.0001 | +| loss | -0.0904 | +| n_updates | 64960 | +| policy_gradient_loss | -0.0727 | +| value_loss | 0.000553 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 313 | +| iterations | 445 | +| time_elapsed | 1451 | +| total_timesteps | 455680 | +| train/ | | +| approx_kl | 1.708167 | +| clip_fraction | 0.449 | +| clip_range | 0.2 | +| entropy_loss | -0.382 | +| explained_variance | -0.739 | +| learning_rate | 0.0001 | +| loss | -0.0894 | +| n_updates | 64970 | +| policy_gradient_loss | -0.0591 | +| value_loss | 0.000725 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 313 | +| iterations | 446 | +| time_elapsed | 1454 | +| total_timesteps | 456704 | +| train/ | | +| approx_kl | 2.3070505 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.448 | +| explained_variance | -1.31 | +| learning_rate | 0.0001 | +| loss | -0.0724 | +| n_updates | 64980 | +| policy_gradient_loss | -0.0678 | +| value_loss | 0.000382 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 313 | +| iterations | 447 | +| time_elapsed | 1457 | +| total_timesteps | 457728 | +| train/ | | +| approx_kl | 2.6024203 | +| clip_fraction | 0.509 | +| clip_range | 0.2 | +| entropy_loss | -0.423 | +| explained_variance | -0.444 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 64990 | +| policy_gradient_loss | -0.0628 | +| value_loss | 0.000474 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 313 | +| iterations | 448 | +| time_elapsed | 1461 | +| total_timesteps | 458752 | +| train/ | | +| approx_kl | 2.0758078 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.385 | +| explained_variance | -1.47 | +| learning_rate | 0.0001 | +| loss | -0.108 | +| n_updates | 65000 | +| policy_gradient_loss | -0.0632 | +| value_loss | 0.000541 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 314 | +| iterations | 449 | +| time_elapsed | 1464 | +| total_timesteps | 459776 | +| train/ | | +| approx_kl | 1.8114256 | +| clip_fraction | 0.443 | +| clip_range | 0.2 | +| entropy_loss | -0.338 | +| explained_variance | -0.738 | +| learning_rate | 0.0001 | +| loss | -0.105 | +| n_updates | 65010 | +| policy_gradient_loss | -0.064 | +| value_loss | 0.00074 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 314 | +| iterations | 450 | +| time_elapsed | 1467 | +| total_timesteps | 460800 | +| train/ | | +| approx_kl | 1.4533372 | +| clip_fraction | 0.407 | +| clip_range | 0.2 | +| entropy_loss | -0.283 | +| explained_variance | -0.557 | +| learning_rate | 0.0001 | +| loss | -0.0656 | +| n_updates | 65020 | +| policy_gradient_loss | -0.0506 | +| value_loss | 0.000645 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 314 | +| iterations | 451 | +| time_elapsed | 1470 | +| total_timesteps | 461824 | +| train/ | | +| approx_kl | 1.5734931 | +| clip_fraction | 0.469 | +| clip_range | 0.2 | +| entropy_loss | -0.414 | +| explained_variance | -1.94 | +| learning_rate | 0.0001 | +| loss | -0.0825 | +| n_updates | 65030 | +| policy_gradient_loss | -0.0615 | +| value_loss | 0.000306 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 314 | +| iterations | 452 | +| time_elapsed | 1473 | +| total_timesteps | 462848 | +| train/ | | +| approx_kl | 1.9491041 | +| clip_fraction | 0.476 | +| clip_range | 0.2 | +| entropy_loss | -0.448 | +| explained_variance | -1.45 | +| learning_rate | 0.0001 | +| loss | -0.0765 | +| n_updates | 65040 | +| policy_gradient_loss | -0.0643 | +| value_loss | 0.000326 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 314 | +| iterations | 453 | +| time_elapsed | 1477 | +| total_timesteps | 463872 | +| train/ | | +| approx_kl | 1.8793886 | +| clip_fraction | 0.456 | +| clip_range | 0.2 | +| entropy_loss | -0.349 | +| explained_variance | -1.11 | +| learning_rate | 0.0001 | +| loss | -0.0697 | +| n_updates | 65050 | +| policy_gradient_loss | -0.0573 | +| value_loss | 0.000509 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 314 | +| iterations | 454 | +| time_elapsed | 1480 | +| total_timesteps | 464896 | +| train/ | | +| approx_kl | 1.7272539 | +| clip_fraction | 0.417 | +| clip_range | 0.2 | +| entropy_loss | -0.319 | +| explained_variance | -0.454 | +| learning_rate | 0.0001 | +| loss | -0.0718 | +| n_updates | 65060 | +| policy_gradient_loss | -0.0556 | +| value_loss | 0.000559 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 314 | +| iterations | 455 | +| time_elapsed | 1483 | +| total_timesteps | 465920 | +| train/ | | +| approx_kl | 1.713577 | +| clip_fraction | 0.434 | +| clip_range | 0.2 | +| entropy_loss | -0.333 | +| explained_variance | -4.08 | +| learning_rate | 0.0001 | +| loss | -0.0735 | +| n_updates | 65070 | +| policy_gradient_loss | -0.0574 | +| value_loss | 0.000308 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 314 | +| iterations | 456 | +| time_elapsed | 1486 | +| total_timesteps | 466944 | +| train/ | | +| approx_kl | 2.440782 | +| clip_fraction | 0.407 | +| clip_range | 0.2 | +| entropy_loss | -0.296 | +| explained_variance | -0.111 | +| learning_rate | 0.0001 | +| loss | -0.0687 | +| n_updates | 65080 | +| policy_gradient_loss | -0.0412 | +| value_loss | 0.000524 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 314 | +| iterations | 457 | +| time_elapsed | 1490 | +| total_timesteps | 467968 | +| train/ | | +| approx_kl | 1.889776 | +| clip_fraction | 0.493 | +| clip_range | 0.2 | +| entropy_loss | -0.444 | +| explained_variance | -1.66 | +| learning_rate | 0.0001 | +| loss | -0.0849 | +| n_updates | 65090 | +| policy_gradient_loss | -0.0669 | +| value_loss | 0.000685 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 313 | +| iterations | 458 | +| time_elapsed | 1493 | +| total_timesteps | 468992 | +| train/ | | +| approx_kl | 2.2614794 | +| clip_fraction | 0.484 | +| clip_range | 0.2 | +| entropy_loss | -0.485 | +| explained_variance | -1 | +| learning_rate | 0.0001 | +| loss | -0.069 | +| n_updates | 65100 | +| policy_gradient_loss | -0.0594 | +| value_loss | 0.000465 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 313 | +| iterations | 459 | +| time_elapsed | 1497 | +| total_timesteps | 470016 | +| train/ | | +| approx_kl | 1.7236227 | +| clip_fraction | 0.482 | +| clip_range | 0.2 | +| entropy_loss | -0.383 | +| explained_variance | -2.33 | +| learning_rate | 0.0001 | +| loss | -0.0745 | +| n_updates | 65110 | +| policy_gradient_loss | -0.0621 | +| value_loss | 0.000427 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 313 | +| iterations | 460 | +| time_elapsed | 1500 | +| total_timesteps | 471040 | +| train/ | | +| approx_kl | 1.9120449 | +| clip_fraction | 0.445 | +| clip_range | 0.2 | +| entropy_loss | -0.355 | +| explained_variance | -0.776 | +| learning_rate | 0.0001 | +| loss | -0.0866 | +| n_updates | 65120 | +| policy_gradient_loss | -0.0598 | +| value_loss | 0.000618 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 313 | +| iterations | 461 | +| time_elapsed | 1503 | +| total_timesteps | 472064 | +| train/ | | +| approx_kl | 1.5636405 | +| clip_fraction | 0.392 | +| clip_range | 0.2 | +| entropy_loss | -0.319 | +| explained_variance | -1.07 | +| learning_rate | 0.0001 | +| loss | -0.0732 | +| n_updates | 65130 | +| policy_gradient_loss | -0.0537 | +| value_loss | 0.000701 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 313 | +| iterations | 462 | +| time_elapsed | 1507 | +| total_timesteps | 473088 | +| train/ | | +| approx_kl | 1.9269354 | +| clip_fraction | 0.412 | +| clip_range | 0.2 | +| entropy_loss | -0.321 | +| explained_variance | -0.273 | +| learning_rate | 0.0001 | +| loss | -0.0633 | +| n_updates | 65140 | +| policy_gradient_loss | -0.0524 | +| value_loss | 0.000444 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 313 | +| iterations | 463 | +| time_elapsed | 1510 | +| total_timesteps | 474112 | +| train/ | | +| approx_kl | 2.4413264 | +| clip_fraction | 0.426 | +| clip_range | 0.2 | +| entropy_loss | -0.283 | +| explained_variance | -2.67 | +| learning_rate | 0.0001 | +| loss | -0.0775 | +| n_updates | 65150 | +| policy_gradient_loss | -0.0546 | +| value_loss | 0.000659 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 313 | +| iterations | 464 | +| time_elapsed | 1513 | +| total_timesteps | 475136 | +| train/ | | +| approx_kl | 1.9391732 | +| clip_fraction | 0.457 | +| clip_range | 0.2 | +| entropy_loss | -0.436 | +| explained_variance | -0.353 | +| learning_rate | 0.0001 | +| loss | -0.0625 | +| n_updates | 65160 | +| policy_gradient_loss | -0.0474 | +| value_loss | 0.000217 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 313 | +| iterations | 465 | +| time_elapsed | 1517 | +| total_timesteps | 476160 | +| train/ | | +| approx_kl | 2.169254 | +| clip_fraction | 0.492 | +| clip_range | 0.2 | +| entropy_loss | -0.461 | +| explained_variance | -1.34 | +| learning_rate | 0.0001 | +| loss | -0.0998 | +| n_updates | 65170 | +| policy_gradient_loss | -0.0662 | +| value_loss | 0.000306 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 313 | +| iterations | 466 | +| time_elapsed | 1520 | +| total_timesteps | 477184 | +| train/ | | +| approx_kl | 1.6773192 | +| clip_fraction | 0.489 | +| clip_range | 0.2 | +| entropy_loss | -0.457 | +| explained_variance | -0.506 | +| learning_rate | 0.0001 | +| loss | -0.084 | +| n_updates | 65180 | +| policy_gradient_loss | -0.0555 | +| value_loss | 0.000378 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 313 | +| iterations | 467 | +| time_elapsed | 1523 | +| total_timesteps | 478208 | +| train/ | | +| approx_kl | 2.5393264 | +| clip_fraction | 0.49 | +| clip_range | 0.2 | +| entropy_loss | -0.451 | +| explained_variance | -0.8 | +| learning_rate | 0.0001 | +| loss | -0.0738 | +| n_updates | 65190 | +| policy_gradient_loss | -0.0589 | +| value_loss | 0.000433 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 313 | +| iterations | 468 | +| time_elapsed | 1526 | +| total_timesteps | 479232 | +| train/ | | +| approx_kl | 1.769432 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.443 | +| explained_variance | -0.943 | +| learning_rate | 0.0001 | +| loss | -0.0748 | +| n_updates | 65200 | +| policy_gradient_loss | -0.0614 | +| value_loss | 0.000499 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 313 | +| iterations | 469 | +| time_elapsed | 1530 | +| total_timesteps | 480256 | +| train/ | | +| approx_kl | 2.5167232 | +| clip_fraction | 0.501 | +| clip_range | 0.2 | +| entropy_loss | -0.431 | +| explained_variance | -2.71 | +| learning_rate | 0.0001 | +| loss | -0.0776 | +| n_updates | 65210 | +| policy_gradient_loss | -0.0774 | +| value_loss | 0.000478 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.82e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 313 | +| iterations | 470 | +| time_elapsed | 1533 | +| total_timesteps | 481280 | +| train/ | | +| approx_kl | 2.039703 | +| clip_fraction | 0.445 | +| clip_range | 0.2 | +| entropy_loss | -0.391 | +| explained_variance | -0.579 | +| learning_rate | 0.0001 | +| loss | -0.0953 | +| n_updates | 65220 | +| policy_gradient_loss | -0.0578 | +| value_loss | 0.000449 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.81e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 313 | +| iterations | 471 | +| time_elapsed | 1536 | +| total_timesteps | 482304 | +| train/ | | +| approx_kl | 1.8291582 | +| clip_fraction | 0.425 | +| clip_range | 0.2 | +| entropy_loss | -0.37 | +| explained_variance | -0.0642 | +| learning_rate | 0.0001 | +| loss | -0.0757 | +| n_updates | 65230 | +| policy_gradient_loss | -0.0591 | +| value_loss | 0.000506 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.8e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 313 | +| iterations | 472 | +| time_elapsed | 1540 | +| total_timesteps | 483328 | +| train/ | | +| approx_kl | 1.737644 | +| clip_fraction | 0.469 | +| clip_range | 0.2 | +| entropy_loss | -0.416 | +| explained_variance | -1.77 | +| learning_rate | 0.0001 | +| loss | -0.0878 | +| n_updates | 65240 | +| policy_gradient_loss | -0.0659 | +| value_loss | 0.000333 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.8e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 313 | +| iterations | 473 | +| time_elapsed | 1543 | +| total_timesteps | 484352 | +| train/ | | +| approx_kl | 2.128304 | +| clip_fraction | 0.456 | +| clip_range | 0.2 | +| entropy_loss | -0.348 | +| explained_variance | -0.183 | +| learning_rate | 0.0001 | +| loss | -0.0603 | +| n_updates | 65250 | +| policy_gradient_loss | -0.0514 | +| value_loss | 0.000563 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.8e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 313 | +| iterations | 474 | +| time_elapsed | 1546 | +| total_timesteps | 485376 | +| train/ | | +| approx_kl | 2.7813525 | +| clip_fraction | 0.457 | +| clip_range | 0.2 | +| entropy_loss | -0.378 | +| explained_variance | -1.79 | +| learning_rate | 0.0001 | +| loss | -0.0699 | +| n_updates | 65260 | +| policy_gradient_loss | -0.0683 | +| value_loss | 0.000575 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.8e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 313 | +| iterations | 475 | +| time_elapsed | 1550 | +| total_timesteps | 486400 | +| train/ | | +| approx_kl | 2.7122657 | +| clip_fraction | 0.482 | +| clip_range | 0.2 | +| entropy_loss | -0.415 | +| explained_variance | -0.398 | +| learning_rate | 0.0001 | +| loss | -0.0977 | +| n_updates | 65270 | +| policy_gradient_loss | -0.0691 | +| value_loss | 0.000527 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 313 | +| iterations | 476 | +| time_elapsed | 1554 | +| total_timesteps | 487424 | +| train/ | | +| approx_kl | 2.190526 | +| clip_fraction | 0.513 | +| clip_range | 0.2 | +| entropy_loss | -0.45 | +| explained_variance | -2.52 | +| learning_rate | 0.0001 | +| loss | -0.0837 | +| n_updates | 65280 | +| policy_gradient_loss | -0.0626 | +| value_loss | 0.000437 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 313 | +| iterations | 477 | +| time_elapsed | 1557 | +| total_timesteps | 488448 | +| train/ | | +| approx_kl | 1.8711151 | +| clip_fraction | 0.499 | +| clip_range | 0.2 | +| entropy_loss | -0.458 | +| explained_variance | -0.982 | +| learning_rate | 0.0001 | +| loss | -0.108 | +| n_updates | 65290 | +| policy_gradient_loss | -0.0681 | +| value_loss | 0.00048 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 313 | +| iterations | 478 | +| time_elapsed | 1560 | +| total_timesteps | 489472 | +| train/ | | +| approx_kl | 1.7925869 | +| clip_fraction | 0.478 | +| clip_range | 0.2 | +| entropy_loss | -0.419 | +| explained_variance | -2.2 | +| learning_rate | 0.0001 | +| loss | -0.0882 | +| n_updates | 65300 | +| policy_gradient_loss | -0.067 | +| value_loss | 0.000377 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 313 | +| iterations | 479 | +| time_elapsed | 1564 | +| total_timesteps | 490496 | +| train/ | | +| approx_kl | 1.7044238 | +| clip_fraction | 0.462 | +| clip_range | 0.2 | +| entropy_loss | -0.429 | +| explained_variance | -0.66 | +| learning_rate | 0.0001 | +| loss | -0.0764 | +| n_updates | 65310 | +| policy_gradient_loss | -0.0556 | +| value_loss | 0.000676 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 313 | +| iterations | 480 | +| time_elapsed | 1567 | +| total_timesteps | 491520 | +| train/ | | +| approx_kl | 1.6880765 | +| clip_fraction | 0.45 | +| clip_range | 0.2 | +| entropy_loss | -0.375 | +| explained_variance | -1.78 | +| learning_rate | 0.0001 | +| loss | -0.0486 | +| n_updates | 65320 | +| policy_gradient_loss | -0.0599 | +| value_loss | 0.000363 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 313 | +| iterations | 481 | +| time_elapsed | 1571 | +| total_timesteps | 492544 | +| train/ | | +| approx_kl | 2.0334144 | +| clip_fraction | 0.489 | +| clip_range | 0.2 | +| entropy_loss | -0.386 | +| explained_variance | -1.01 | +| learning_rate | 0.0001 | +| loss | -0.00387 | +| n_updates | 65330 | +| policy_gradient_loss | -0.0433 | +| value_loss | 0.000534 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 313 | +| iterations | 482 | +| time_elapsed | 1574 | +| total_timesteps | 493568 | +| train/ | | +| approx_kl | 2.605669 | +| clip_fraction | 0.453 | +| clip_range | 0.2 | +| entropy_loss | -0.357 | +| explained_variance | -1.77 | +| learning_rate | 0.0001 | +| loss | -0.0886 | +| n_updates | 65340 | +| policy_gradient_loss | -0.0619 | +| value_loss | 0.000328 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 313 | +| iterations | 483 | +| time_elapsed | 1577 | +| total_timesteps | 494592 | +| train/ | | +| approx_kl | 1.7524936 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.409 | +| explained_variance | -0.472 | +| learning_rate | 0.0001 | +| loss | -0.0809 | +| n_updates | 65350 | +| policy_gradient_loss | -0.0648 | +| value_loss | 0.000302 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 313 | +| iterations | 484 | +| time_elapsed | 1580 | +| total_timesteps | 495616 | +| train/ | | +| approx_kl | 2.1631308 | +| clip_fraction | 0.472 | +| clip_range | 0.2 | +| entropy_loss | -0.392 | +| explained_variance | -0.792 | +| learning_rate | 0.0001 | +| loss | -0.0962 | +| n_updates | 65360 | +| policy_gradient_loss | -0.0671 | +| value_loss | 0.000843 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 313 | +| iterations | 485 | +| time_elapsed | 1584 | +| total_timesteps | 496640 | +| train/ | | +| approx_kl | 2.8676867 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.394 | +| explained_variance | -2.04 | +| learning_rate | 0.0001 | +| loss | -0.0865 | +| n_updates | 65370 | +| policy_gradient_loss | -0.0714 | +| value_loss | 0.000349 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 313 | +| iterations | 486 | +| time_elapsed | 1587 | +| total_timesteps | 497664 | +| train/ | | +| approx_kl | 1.8125575 | +| clip_fraction | 0.462 | +| clip_range | 0.2 | +| entropy_loss | -0.379 | +| explained_variance | -1.65 | +| learning_rate | 0.0001 | +| loss | -0.0787 | +| n_updates | 65380 | +| policy_gradient_loss | -0.0574 | +| value_loss | 0.000556 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 313 | +| iterations | 487 | +| time_elapsed | 1590 | +| total_timesteps | 498688 | +| train/ | | +| approx_kl | 1.5680789 | +| clip_fraction | 0.506 | +| clip_range | 0.2 | +| entropy_loss | -0.523 | +| explained_variance | -0.949 | +| learning_rate | 0.0001 | +| loss | -0.0988 | +| n_updates | 65390 | +| policy_gradient_loss | -0.0633 | +| value_loss | 0.000193 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.304 | +| time/ | | +| fps | 313 | +| iterations | 488 | +| time_elapsed | 1593 | +| total_timesteps | 499712 | +| train/ | | +| approx_kl | 1.2061 | +| clip_fraction | 0.529 | +| clip_range | 0.2 | +| entropy_loss | -0.599 | +| explained_variance | -0.817 | +| learning_rate | 0.0001 | +| loss | -0.0852 | +| n_updates | 65400 | +| policy_gradient_loss | -0.0628 | +| value_loss | 0.000287 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.304 | +| time/ | | +| fps | 313 | +| iterations | 489 | +| time_elapsed | 1597 | +| total_timesteps | 500736 | +| train/ | | +| approx_kl | 1.79331 | +| clip_fraction | 0.463 | +| clip_range | 0.2 | +| entropy_loss | -0.418 | +| explained_variance | -1.14 | +| learning_rate | 0.0001 | +| loss | -0.0742 | +| n_updates | 65410 | +| policy_gradient_loss | -0.065 | +| value_loss | 0.000425 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.304 | +| time/ | | +| fps | 313 | +| iterations | 490 | +| time_elapsed | 1600 | +| total_timesteps | 501760 | +| train/ | | +| approx_kl | 1.7634228 | +| clip_fraction | 0.485 | +| clip_range | 0.2 | +| entropy_loss | -0.445 | +| explained_variance | -1.31 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 65420 | +| policy_gradient_loss | -0.0655 | +| value_loss | 0.00037 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 313 | +| iterations | 491 | +| time_elapsed | 1603 | +| total_timesteps | 502784 | +| train/ | | +| approx_kl | 1.9659967 | +| clip_fraction | 0.489 | +| clip_range | 0.2 | +| entropy_loss | -0.381 | +| explained_variance | -1.4 | +| learning_rate | 0.0001 | +| loss | -0.0813 | +| n_updates | 65430 | +| policy_gradient_loss | -0.064 | +| value_loss | 0.000367 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 313 | +| iterations | 492 | +| time_elapsed | 1607 | +| total_timesteps | 503808 | +| train/ | | +| approx_kl | 2.2260191 | +| clip_fraction | 0.509 | +| clip_range | 0.2 | +| entropy_loss | -0.578 | +| explained_variance | -1 | +| learning_rate | 0.0001 | +| loss | -0.107 | +| n_updates | 65440 | +| policy_gradient_loss | -0.0691 | +| value_loss | 0.000309 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.298 | +| time/ | | +| fps | 313 | +| iterations | 493 | +| time_elapsed | 1610 | +| total_timesteps | 504832 | +| train/ | | +| approx_kl | 1.6294117 | +| clip_fraction | 0.552 | +| clip_range | 0.2 | +| entropy_loss | -0.635 | +| explained_variance | -1.36 | +| learning_rate | 0.0001 | +| loss | -0.078 | +| n_updates | 65450 | +| policy_gradient_loss | -0.0722 | +| value_loss | 0.000266 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.298 | +| time/ | | +| fps | 313 | +| iterations | 494 | +| time_elapsed | 1613 | +| total_timesteps | 505856 | +| train/ | | +| approx_kl | 2.5956361 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.461 | +| explained_variance | -1.09 | +| learning_rate | 0.0001 | +| loss | -0.0929 | +| n_updates | 65460 | +| policy_gradient_loss | -0.0672 | +| value_loss | 0.000302 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.295 | +| time/ | | +| fps | 313 | +| iterations | 495 | +| time_elapsed | 1617 | +| total_timesteps | 506880 | +| train/ | | +| approx_kl | 2.3713546 | +| clip_fraction | 0.498 | +| clip_range | 0.2 | +| entropy_loss | -0.428 | +| explained_variance | -4.1 | +| learning_rate | 0.0001 | +| loss | -0.121 | +| n_updates | 65470 | +| policy_gradient_loss | -0.0736 | +| value_loss | 0.000413 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.295 | +| time/ | | +| fps | 313 | +| iterations | 496 | +| time_elapsed | 1620 | +| total_timesteps | 507904 | +| train/ | | +| approx_kl | 2.0506015 | +| clip_fraction | 0.503 | +| clip_range | 0.2 | +| entropy_loss | -0.451 | +| explained_variance | -1.45 | +| learning_rate | 0.0001 | +| loss | -0.0953 | +| n_updates | 65480 | +| policy_gradient_loss | -0.0741 | +| value_loss | 0.000441 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.295 | +| time/ | | +| fps | 313 | +| iterations | 497 | +| time_elapsed | 1623 | +| total_timesteps | 508928 | +| train/ | | +| approx_kl | 1.8638434 | +| clip_fraction | 0.478 | +| clip_range | 0.2 | +| entropy_loss | -0.405 | +| explained_variance | -0.711 | +| learning_rate | 0.0001 | +| loss | -0.073 | +| n_updates | 65490 | +| policy_gradient_loss | -0.0661 | +| value_loss | 0.000437 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.3 | +| time/ | | +| fps | 313 | +| iterations | 498 | +| time_elapsed | 1627 | +| total_timesteps | 509952 | +| train/ | | +| approx_kl | 2.0449538 | +| clip_fraction | 0.45 | +| clip_range | 0.2 | +| entropy_loss | -0.361 | +| explained_variance | -1.4 | +| learning_rate | 0.0001 | +| loss | -0.0607 | +| n_updates | 65500 | +| policy_gradient_loss | -0.0609 | +| value_loss | 0.000559 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.3 | +| time/ | | +| fps | 313 | +| iterations | 499 | +| time_elapsed | 1630 | +| total_timesteps | 510976 | +| train/ | | +| approx_kl | 2.029393 | +| clip_fraction | 0.378 | +| clip_range | 0.2 | +| entropy_loss | -0.285 | +| explained_variance | -0.649 | +| learning_rate | 0.0001 | +| loss | -0.072 | +| n_updates | 65510 | +| policy_gradient_loss | -0.0551 | +| value_loss | 0.000472 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 313 | +| iterations | 500 | +| time_elapsed | 1633 | +| total_timesteps | 512000 | +| train/ | | +| approx_kl | 1.9429939 | +| clip_fraction | 0.474 | +| clip_range | 0.2 | +| entropy_loss | -0.404 | +| explained_variance | -0.471 | +| learning_rate | 0.0001 | +| loss | -0.0957 | +| n_updates | 65520 | +| policy_gradient_loss | -0.0601 | +| value_loss | 0.000369 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 313 | +| iterations | 501 | +| time_elapsed | 1636 | +| total_timesteps | 513024 | +| train/ | | +| approx_kl | 1.6990714 | +| clip_fraction | 0.449 | +| clip_range | 0.2 | +| entropy_loss | -0.403 | +| explained_variance | -0.935 | +| learning_rate | 0.0001 | +| loss | -0.093 | +| n_updates | 65530 | +| policy_gradient_loss | -0.0596 | +| value_loss | 0.000469 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.294 | +| time/ | | +| fps | 313 | +| iterations | 502 | +| time_elapsed | 1640 | +| total_timesteps | 514048 | +| train/ | | +| approx_kl | 4.064236 | +| clip_fraction | 0.491 | +| clip_range | 0.2 | +| entropy_loss | -0.43 | +| explained_variance | -1.88 | +| learning_rate | 0.0001 | +| loss | -0.0852 | +| n_updates | 65540 | +| policy_gradient_loss | -0.0677 | +| value_loss | 0.000472 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.294 | +| time/ | | +| fps | 313 | +| iterations | 503 | +| time_elapsed | 1643 | +| total_timesteps | 515072 | +| train/ | | +| approx_kl | 1.7459731 | +| clip_fraction | 0.489 | +| clip_range | 0.2 | +| entropy_loss | -0.427 | +| explained_variance | -2.17 | +| learning_rate | 0.0001 | +| loss | -0.0717 | +| n_updates | 65550 | +| policy_gradient_loss | -0.0623 | +| value_loss | 0.000524 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.294 | +| time/ | | +| fps | 313 | +| iterations | 504 | +| time_elapsed | 1646 | +| total_timesteps | 516096 | +| train/ | | +| approx_kl | 1.6052883 | +| clip_fraction | 0.51 | +| clip_range | 0.2 | +| entropy_loss | -0.438 | +| explained_variance | -1.9 | +| learning_rate | 0.0001 | +| loss | 0.0247 | +| n_updates | 65560 | +| policy_gradient_loss | -0.0699 | +| value_loss | 0.000373 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.294 | +| time/ | | +| fps | 313 | +| iterations | 505 | +| time_elapsed | 1649 | +| total_timesteps | 517120 | +| train/ | | +| approx_kl | 1.7421887 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.414 | +| explained_variance | -1.2 | +| learning_rate | 0.0001 | +| loss | -0.0618 | +| n_updates | 65570 | +| policy_gradient_loss | -0.0547 | +| value_loss | 0.000347 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.294 | +| time/ | | +| fps | 313 | +| iterations | 506 | +| time_elapsed | 1653 | +| total_timesteps | 518144 | +| train/ | | +| approx_kl | 1.6968832 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.454 | +| explained_variance | -1.59 | +| learning_rate | 0.0001 | +| loss | -0.0776 | +| n_updates | 65580 | +| policy_gradient_loss | -0.0585 | +| value_loss | 0.000341 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.291 | +| time/ | | +| fps | 313 | +| iterations | 507 | +| time_elapsed | 1656 | +| total_timesteps | 519168 | +| train/ | | +| approx_kl | 5.156244 | +| clip_fraction | 0.458 | +| clip_range | 0.2 | +| entropy_loss | -0.347 | +| explained_variance | -0.51 | +| learning_rate | 0.0001 | +| loss | -0.0533 | +| n_updates | 65590 | +| policy_gradient_loss | -0.0526 | +| value_loss | 0.000365 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.292 | +| time/ | | +| fps | 313 | +| iterations | 508 | +| time_elapsed | 1659 | +| total_timesteps | 520192 | +| train/ | | +| approx_kl | 1.9587145 | +| clip_fraction | 0.479 | +| clip_range | 0.2 | +| entropy_loss | -0.363 | +| explained_variance | -2.19 | +| learning_rate | 0.0001 | +| loss | -0.0815 | +| n_updates | 65600 | +| policy_gradient_loss | -0.069 | +| value_loss | 0.000381 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.292 | +| time/ | | +| fps | 313 | +| iterations | 509 | +| time_elapsed | 1663 | +| total_timesteps | 521216 | +| train/ | | +| approx_kl | 1.4651421 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.421 | +| explained_variance | -0.937 | +| learning_rate | 0.0001 | +| loss | -0.0997 | +| n_updates | 65610 | +| policy_gradient_loss | -0.069 | +| value_loss | 0.000571 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.29 | +| time/ | | +| fps | 313 | +| iterations | 510 | +| time_elapsed | 1666 | +| total_timesteps | 522240 | +| train/ | | +| approx_kl | 2.039702 | +| clip_fraction | 0.472 | +| clip_range | 0.2 | +| entropy_loss | -0.366 | +| explained_variance | -2.18 | +| learning_rate | 0.0001 | +| loss | -0.0844 | +| n_updates | 65620 | +| policy_gradient_loss | -0.065 | +| value_loss | 0.000419 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.29 | +| time/ | | +| fps | 313 | +| iterations | 511 | +| time_elapsed | 1669 | +| total_timesteps | 523264 | +| train/ | | +| approx_kl | 24.76382 | +| clip_fraction | 0.452 | +| clip_range | 0.2 | +| entropy_loss | -0.408 | +| explained_variance | -0.681 | +| learning_rate | 0.0001 | +| loss | -0.0878 | +| n_updates | 65630 | +| policy_gradient_loss | -0.059 | +| value_loss | 0.000415 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.288 | +| time/ | | +| fps | 313 | +| iterations | 512 | +| time_elapsed | 1673 | +| total_timesteps | 524288 | +| train/ | | +| approx_kl | 2.1710215 | +| clip_fraction | 0.488 | +| clip_range | 0.2 | +| entropy_loss | -0.543 | +| explained_variance | -1.03 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 65640 | +| policy_gradient_loss | -0.0711 | +| value_loss | 0.000335 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.288 | +| time/ | | +| fps | 313 | +| iterations | 513 | +| time_elapsed | 1676 | +| total_timesteps | 525312 | +| train/ | | +| approx_kl | 2.706367 | +| clip_fraction | 0.456 | +| clip_range | 0.2 | +| entropy_loss | -0.346 | +| explained_variance | -0.515 | +| learning_rate | 0.0001 | +| loss | -0.0893 | +| n_updates | 65650 | +| policy_gradient_loss | -0.0634 | +| value_loss | 0.000641 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.284 | +| time/ | | +| fps | 313 | +| iterations | 514 | +| time_elapsed | 1680 | +| total_timesteps | 526336 | +| train/ | | +| approx_kl | 2.5392878 | +| clip_fraction | 0.463 | +| clip_range | 0.2 | +| entropy_loss | -0.351 | +| explained_variance | -1.85 | +| learning_rate | 0.0001 | +| loss | -0.106 | +| n_updates | 65660 | +| policy_gradient_loss | -0.069 | +| value_loss | 0.000418 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.284 | +| time/ | | +| fps | 313 | +| iterations | 515 | +| time_elapsed | 1683 | +| total_timesteps | 527360 | +| train/ | | +| approx_kl | 1.7076007 | +| clip_fraction | 0.392 | +| clip_range | 0.2 | +| entropy_loss | -0.303 | +| explained_variance | -4.7 | +| learning_rate | 0.0001 | +| loss | -0.0862 | +| n_updates | 65670 | +| policy_gradient_loss | -0.0611 | +| value_loss | 0.000474 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.284 | +| time/ | | +| fps | 313 | +| iterations | 516 | +| time_elapsed | 1686 | +| total_timesteps | 528384 | +| train/ | | +| approx_kl | 2.3165927 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.367 | +| explained_variance | -0.776 | +| learning_rate | 0.0001 | +| loss | -0.0453 | +| n_updates | 65680 | +| policy_gradient_loss | -0.0582 | +| value_loss | 0.000527 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.284 | +| time/ | | +| fps | 313 | +| iterations | 517 | +| time_elapsed | 1690 | +| total_timesteps | 529408 | +| train/ | | +| approx_kl | 4.2261534 | +| clip_fraction | 0.5 | +| clip_range | 0.2 | +| entropy_loss | -0.431 | +| explained_variance | -1.15 | +| learning_rate | 0.0001 | +| loss | -0.106 | +| n_updates | 65690 | +| policy_gradient_loss | -0.0694 | +| value_loss | 0.000404 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.284 | +| time/ | | +| fps | 313 | +| iterations | 518 | +| time_elapsed | 1693 | +| total_timesteps | 530432 | +| train/ | | +| approx_kl | 2.376241 | +| clip_fraction | 0.45 | +| clip_range | 0.2 | +| entropy_loss | -0.35 | +| explained_variance | -0.873 | +| learning_rate | 0.0001 | +| loss | -0.038 | +| n_updates | 65700 | +| policy_gradient_loss | -0.0556 | +| value_loss | 0.000414 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.78e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 313 | +| iterations | 519 | +| time_elapsed | 1696 | +| total_timesteps | 531456 | +| train/ | | +| approx_kl | 1.8735198 | +| clip_fraction | 0.522 | +| clip_range | 0.2 | +| entropy_loss | -0.455 | +| explained_variance | -1.75 | +| learning_rate | 0.0001 | +| loss | -0.114 | +| n_updates | 65710 | +| policy_gradient_loss | -0.0744 | +| value_loss | 0.000358 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.276 | +| time/ | | +| fps | 313 | +| iterations | 520 | +| time_elapsed | 1699 | +| total_timesteps | 532480 | +| train/ | | +| approx_kl | 2.5083938 | +| clip_fraction | 0.503 | +| clip_range | 0.2 | +| entropy_loss | -0.446 | +| explained_variance | -1.23 | +| learning_rate | 0.0001 | +| loss | -0.0896 | +| n_updates | 65720 | +| policy_gradient_loss | -0.0644 | +| value_loss | 0.000648 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.276 | +| time/ | | +| fps | 313 | +| iterations | 521 | +| time_elapsed | 1702 | +| total_timesteps | 533504 | +| train/ | | +| approx_kl | 2.2504795 | +| clip_fraction | 0.469 | +| clip_range | 0.2 | +| entropy_loss | -0.413 | +| explained_variance | -1.7 | +| learning_rate | 0.0001 | +| loss | -0.0864 | +| n_updates | 65730 | +| policy_gradient_loss | -0.0644 | +| value_loss | 0.000458 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 313 | +| iterations | 522 | +| time_elapsed | 1706 | +| total_timesteps | 534528 | +| train/ | | +| approx_kl | 2.5531888 | +| clip_fraction | 0.447 | +| clip_range | 0.2 | +| entropy_loss | -0.361 | +| explained_variance | -1.73 | +| learning_rate | 0.0001 | +| loss | -0.0798 | +| n_updates | 65740 | +| policy_gradient_loss | -0.0569 | +| value_loss | 0.000482 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 313 | +| iterations | 523 | +| time_elapsed | 1709 | +| total_timesteps | 535552 | +| train/ | | +| approx_kl | 2.1495872 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.437 | +| explained_variance | -0.876 | +| learning_rate | 0.0001 | +| loss | -0.09 | +| n_updates | 65750 | +| policy_gradient_loss | -0.0685 | +| value_loss | 0.000422 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.271 | +| time/ | | +| fps | 313 | +| iterations | 524 | +| time_elapsed | 1712 | +| total_timesteps | 536576 | +| train/ | | +| approx_kl | 1.897861 | +| clip_fraction | 0.466 | +| clip_range | 0.2 | +| entropy_loss | -0.394 | +| explained_variance | -1.32 | +| learning_rate | 0.0001 | +| loss | -0.0745 | +| n_updates | 65760 | +| policy_gradient_loss | -0.0619 | +| value_loss | 0.000541 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.271 | +| time/ | | +| fps | 313 | +| iterations | 525 | +| time_elapsed | 1715 | +| total_timesteps | 537600 | +| train/ | | +| approx_kl | 1.6853731 | +| clip_fraction | 0.464 | +| clip_range | 0.2 | +| entropy_loss | -0.396 | +| explained_variance | -1.2 | +| learning_rate | 0.0001 | +| loss | -0.0893 | +| n_updates | 65770 | +| policy_gradient_loss | -0.0636 | +| value_loss | 0.000587 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.266 | +| time/ | | +| fps | 313 | +| iterations | 526 | +| time_elapsed | 1719 | +| total_timesteps | 538624 | +| train/ | | +| approx_kl | 1.9435511 | +| clip_fraction | 0.472 | +| clip_range | 0.2 | +| entropy_loss | -0.418 | +| explained_variance | -1.46 | +| learning_rate | 0.0001 | +| loss | -0.0734 | +| n_updates | 65780 | +| policy_gradient_loss | -0.0647 | +| value_loss | 0.000209 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.266 | +| time/ | | +| fps | 313 | +| iterations | 527 | +| time_elapsed | 1722 | +| total_timesteps | 539648 | +| train/ | | +| approx_kl | 1.8289505 | +| clip_fraction | 0.486 | +| clip_range | 0.2 | +| entropy_loss | -0.477 | +| explained_variance | -0.675 | +| learning_rate | 0.0001 | +| loss | -0.0657 | +| n_updates | 65790 | +| policy_gradient_loss | -0.0581 | +| value_loss | 0.000458 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.78e+03 | +| ep_rew_mean | 0.264 | +| time/ | | +| fps | 313 | +| iterations | 528 | +| time_elapsed | 1725 | +| total_timesteps | 540672 | +| train/ | | +| approx_kl | 1.9385554 | +| clip_fraction | 0.455 | +| clip_range | 0.2 | +| entropy_loss | -0.393 | +| explained_variance | -2.44 | +| learning_rate | 0.0001 | +| loss | -0.0759 | +| n_updates | 65800 | +| policy_gradient_loss | -0.0677 | +| value_loss | 0.000372 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.26 | +| time/ | | +| fps | 313 | +| iterations | 529 | +| time_elapsed | 1729 | +| total_timesteps | 541696 | +| train/ | | +| approx_kl | 2.0201735 | +| clip_fraction | 0.451 | +| clip_range | 0.2 | +| entropy_loss | -0.337 | +| explained_variance | -0.754 | +| learning_rate | 0.0001 | +| loss | -0.0963 | +| n_updates | 65810 | +| policy_gradient_loss | -0.0636 | +| value_loss | 0.000454 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.26 | +| time/ | | +| fps | 313 | +| iterations | 530 | +| time_elapsed | 1732 | +| total_timesteps | 542720 | +| train/ | | +| approx_kl | 1.9138175 | +| clip_fraction | 0.431 | +| clip_range | 0.2 | +| entropy_loss | -0.335 | +| explained_variance | -1.12 | +| learning_rate | 0.0001 | +| loss | -0.111 | +| n_updates | 65820 | +| policy_gradient_loss | -0.0574 | +| value_loss | 0.000379 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.258 | +| time/ | | +| fps | 313 | +| iterations | 531 | +| time_elapsed | 1736 | +| total_timesteps | 543744 | +| train/ | | +| approx_kl | 1.9210222 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.362 | +| explained_variance | -1.87 | +| learning_rate | 0.0001 | +| loss | -0.0917 | +| n_updates | 65830 | +| policy_gradient_loss | -0.0689 | +| value_loss | 0.000373 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.257 | +| time/ | | +| fps | 313 | +| iterations | 532 | +| time_elapsed | 1739 | +| total_timesteps | 544768 | +| train/ | | +| approx_kl | 1.8878556 | +| clip_fraction | 0.448 | +| clip_range | 0.2 | +| entropy_loss | -0.349 | +| explained_variance | -1.74 | +| learning_rate | 0.0001 | +| loss | -0.0693 | +| n_updates | 65840 | +| policy_gradient_loss | -0.0632 | +| value_loss | 0.000558 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.257 | +| time/ | | +| fps | 313 | +| iterations | 533 | +| time_elapsed | 1743 | +| total_timesteps | 545792 | +| train/ | | +| approx_kl | 1.4666749 | +| clip_fraction | 0.484 | +| clip_range | 0.2 | +| entropy_loss | -0.469 | +| explained_variance | -1.87 | +| learning_rate | 0.0001 | +| loss | -0.0799 | +| n_updates | 65850 | +| policy_gradient_loss | -0.0614 | +| value_loss | 0.000654 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.253 | +| time/ | | +| fps | 313 | +| iterations | 534 | +| time_elapsed | 1746 | +| total_timesteps | 546816 | +| train/ | | +| approx_kl | 1.9140519 | +| clip_fraction | 0.474 | +| clip_range | 0.2 | +| entropy_loss | -0.441 | +| explained_variance | -0.624 | +| learning_rate | 0.0001 | +| loss | -0.0794 | +| n_updates | 65860 | +| policy_gradient_loss | -0.0537 | +| value_loss | 0.00035 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.249 | +| time/ | | +| fps | 313 | +| iterations | 535 | +| time_elapsed | 1750 | +| total_timesteps | 547840 | +| train/ | | +| approx_kl | 2.647917 | +| clip_fraction | 0.519 | +| clip_range | 0.2 | +| entropy_loss | -0.408 | +| explained_variance | -0.825 | +| learning_rate | 0.0001 | +| loss | -0.0811 | +| n_updates | 65870 | +| policy_gradient_loss | -0.0621 | +| value_loss | 0.000406 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.249 | +| time/ | | +| fps | 313 | +| iterations | 536 | +| time_elapsed | 1753 | +| total_timesteps | 548864 | +| train/ | | +| approx_kl | 2.3146634 | +| clip_fraction | 0.436 | +| clip_range | 0.2 | +| entropy_loss | -0.32 | +| explained_variance | -1.69 | +| learning_rate | 0.0001 | +| loss | -0.0778 | +| n_updates | 65880 | +| policy_gradient_loss | -0.0623 | +| value_loss | 0.000359 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.251 | +| time/ | | +| fps | 313 | +| iterations | 537 | +| time_elapsed | 1756 | +| total_timesteps | 549888 | +| train/ | | +| approx_kl | 2.2519262 | +| clip_fraction | 0.435 | +| clip_range | 0.2 | +| entropy_loss | -0.31 | +| explained_variance | -1.21 | +| learning_rate | 0.0001 | +| loss | -0.0704 | +| n_updates | 65890 | +| policy_gradient_loss | -0.0662 | +| value_loss | 0.000476 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.251 | +| time/ | | +| fps | 313 | +| iterations | 538 | +| time_elapsed | 1760 | +| total_timesteps | 550912 | +| train/ | | +| approx_kl | 2.5892835 | +| clip_fraction | 0.522 | +| clip_range | 0.2 | +| entropy_loss | -0.417 | +| explained_variance | -0.9 | +| learning_rate | 0.0001 | +| loss | -0.0756 | +| n_updates | 65900 | +| policy_gradient_loss | -0.0631 | +| value_loss | 0.00054 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.252 | +| time/ | | +| fps | 312 | +| iterations | 539 | +| time_elapsed | 1763 | +| total_timesteps | 551936 | +| train/ | | +| approx_kl | 2.1352706 | +| clip_fraction | 0.451 | +| clip_range | 0.2 | +| entropy_loss | -0.396 | +| explained_variance | -1.03 | +| learning_rate | 0.0001 | +| loss | -0.0716 | +| n_updates | 65910 | +| policy_gradient_loss | -0.0632 | +| value_loss | 0.000424 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.245 | +| time/ | | +| fps | 312 | +| iterations | 540 | +| time_elapsed | 1766 | +| total_timesteps | 552960 | +| train/ | | +| approx_kl | 2.3606129 | +| clip_fraction | 0.491 | +| clip_range | 0.2 | +| entropy_loss | -0.481 | +| explained_variance | -1.71 | +| learning_rate | 0.0001 | +| loss | -0.0795 | +| n_updates | 65920 | +| policy_gradient_loss | -0.0658 | +| value_loss | 0.000351 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.246 | +| time/ | | +| fps | 312 | +| iterations | 541 | +| time_elapsed | 1769 | +| total_timesteps | 553984 | +| train/ | | +| approx_kl | 2.1706457 | +| clip_fraction | 0.445 | +| clip_range | 0.2 | +| entropy_loss | -0.387 | +| explained_variance | -0.539 | +| learning_rate | 0.0001 | +| loss | -0.0762 | +| n_updates | 65930 | +| policy_gradient_loss | -0.0613 | +| value_loss | 0.000741 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.243 | +| time/ | | +| fps | 312 | +| iterations | 542 | +| time_elapsed | 1773 | +| total_timesteps | 555008 | +| train/ | | +| approx_kl | 1.669882 | +| clip_fraction | 0.472 | +| clip_range | 0.2 | +| entropy_loss | -0.394 | +| explained_variance | -2.73 | +| learning_rate | 0.0001 | +| loss | -0.108 | +| n_updates | 65940 | +| policy_gradient_loss | -0.0682 | +| value_loss | 0.000258 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.236 | +| time/ | | +| fps | 312 | +| iterations | 543 | +| time_elapsed | 1776 | +| total_timesteps | 556032 | +| train/ | | +| approx_kl | 2.1076744 | +| clip_fraction | 0.478 | +| clip_range | 0.2 | +| entropy_loss | -0.397 | +| explained_variance | -0.381 | +| learning_rate | 0.0001 | +| loss | -0.0725 | +| n_updates | 65950 | +| policy_gradient_loss | -0.0612 | +| value_loss | 0.000404 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.233 | +| time/ | | +| fps | 312 | +| iterations | 544 | +| time_elapsed | 1779 | +| total_timesteps | 557056 | +| train/ | | +| approx_kl | 2.4148717 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.413 | +| explained_variance | -0.485 | +| learning_rate | 0.0001 | +| loss | -0.0849 | +| n_updates | 65960 | +| policy_gradient_loss | -0.0691 | +| value_loss | 0.00043 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.233 | +| time/ | | +| fps | 312 | +| iterations | 545 | +| time_elapsed | 1783 | +| total_timesteps | 558080 | +| train/ | | +| approx_kl | 2.0273871 | +| clip_fraction | 0.443 | +| clip_range | 0.2 | +| entropy_loss | -0.359 | +| explained_variance | -0.88 | +| learning_rate | 0.0001 | +| loss | -0.0579 | +| n_updates | 65970 | +| policy_gradient_loss | -0.0549 | +| value_loss | 0.000569 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.23 | +| time/ | | +| fps | 312 | +| iterations | 546 | +| time_elapsed | 1786 | +| total_timesteps | 559104 | +| train/ | | +| approx_kl | 1.5755482 | +| clip_fraction | 0.503 | +| clip_range | 0.2 | +| entropy_loss | -0.596 | +| explained_variance | -2.5 | +| learning_rate | 0.0001 | +| loss | -0.1 | +| n_updates | 65980 | +| policy_gradient_loss | -0.0689 | +| value_loss | 0.000283 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.23 | +| time/ | | +| fps | 312 | +| iterations | 547 | +| time_elapsed | 1789 | +| total_timesteps | 560128 | +| train/ | | +| approx_kl | 1.9550304 | +| clip_fraction | 0.469 | +| clip_range | 0.2 | +| entropy_loss | -0.391 | +| explained_variance | -1.12 | +| learning_rate | 0.0001 | +| loss | -0.0757 | +| n_updates | 65990 | +| policy_gradient_loss | -0.0661 | +| value_loss | 0.000534 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.23 | +| time/ | | +| fps | 312 | +| iterations | 548 | +| time_elapsed | 1793 | +| total_timesteps | 561152 | +| train/ | | +| approx_kl | 2.7628627 | +| clip_fraction | 0.514 | +| clip_range | 0.2 | +| entropy_loss | -0.448 | +| explained_variance | -1.59 | +| learning_rate | 0.0001 | +| loss | -0.0988 | +| n_updates | 66000 | +| policy_gradient_loss | -0.0752 | +| value_loss | 0.000687 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.231 | +| time/ | | +| fps | 312 | +| iterations | 549 | +| time_elapsed | 1796 | +| total_timesteps | 562176 | +| train/ | | +| approx_kl | 1.8523586 | +| clip_fraction | 0.515 | +| clip_range | 0.2 | +| entropy_loss | -0.482 | +| explained_variance | -1.96 | +| learning_rate | 0.0001 | +| loss | -0.0973 | +| n_updates | 66010 | +| policy_gradient_loss | -0.0707 | +| value_loss | 0.00029 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.228 | +| time/ | | +| fps | 312 | +| iterations | 550 | +| time_elapsed | 1800 | +| total_timesteps | 563200 | +| train/ | | +| approx_kl | 1.8467976 | +| clip_fraction | 0.502 | +| clip_range | 0.2 | +| entropy_loss | -0.443 | +| explained_variance | -1.1 | +| learning_rate | 0.0001 | +| loss | -0.0779 | +| n_updates | 66020 | +| policy_gradient_loss | -0.0654 | +| value_loss | 0.000473 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.229 | +| time/ | | +| fps | 312 | +| iterations | 551 | +| time_elapsed | 1804 | +| total_timesteps | 564224 | +| train/ | | +| approx_kl | 2.0163317 | +| clip_fraction | 0.492 | +| clip_range | 0.2 | +| entropy_loss | -0.437 | +| explained_variance | -0.653 | +| learning_rate | 0.0001 | +| loss | -0.0718 | +| n_updates | 66030 | +| policy_gradient_loss | -0.0656 | +| value_loss | 0.000601 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.229 | +| time/ | | +| fps | 312 | +| iterations | 552 | +| time_elapsed | 1807 | +| total_timesteps | 565248 | +| train/ | | +| approx_kl | 1.6186609 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.441 | +| explained_variance | -1.74 | +| learning_rate | 0.0001 | +| loss | -0.0848 | +| n_updates | 66040 | +| policy_gradient_loss | -0.0625 | +| value_loss | 0.000395 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.229 | +| time/ | | +| fps | 312 | +| iterations | 553 | +| time_elapsed | 1810 | +| total_timesteps | 566272 | +| train/ | | +| approx_kl | 1.7927482 | +| clip_fraction | 0.501 | +| clip_range | 0.2 | +| entropy_loss | -0.432 | +| explained_variance | -1.03 | +| learning_rate | 0.0001 | +| loss | -0.115 | +| n_updates | 66050 | +| policy_gradient_loss | -0.0702 | +| value_loss | 0.000475 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.225 | +| time/ | | +| fps | 312 | +| iterations | 554 | +| time_elapsed | 1814 | +| total_timesteps | 567296 | +| train/ | | +| approx_kl | 1.7911525 | +| clip_fraction | 0.457 | +| clip_range | 0.2 | +| entropy_loss | -0.433 | +| explained_variance | -0.635 | +| learning_rate | 0.0001 | +| loss | -0.0899 | +| n_updates | 66060 | +| policy_gradient_loss | -0.0627 | +| value_loss | 0.000291 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.217 | +| time/ | | +| fps | 312 | +| iterations | 555 | +| time_elapsed | 1817 | +| total_timesteps | 568320 | +| train/ | | +| approx_kl | 2.3818367 | +| clip_fraction | 0.444 | +| clip_range | 0.2 | +| entropy_loss | -0.385 | +| explained_variance | 0.122 | +| learning_rate | 0.0001 | +| loss | -0.0835 | +| n_updates | 66070 | +| policy_gradient_loss | -0.0671 | +| value_loss | 0.000281 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.213 | +| time/ | | +| fps | 312 | +| iterations | 556 | +| time_elapsed | 1820 | +| total_timesteps | 569344 | +| train/ | | +| approx_kl | 1.7897776 | +| clip_fraction | 0.49 | +| clip_range | 0.2 | +| entropy_loss | -0.464 | +| explained_variance | -0.901 | +| learning_rate | 0.0001 | +| loss | -0.0531 | +| n_updates | 66080 | +| policy_gradient_loss | -0.0693 | +| value_loss | 0.000333 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.214 | +| time/ | | +| fps | 312 | +| iterations | 557 | +| time_elapsed | 1823 | +| total_timesteps | 570368 | +| train/ | | +| approx_kl | 1.901622 | +| clip_fraction | 0.459 | +| clip_range | 0.2 | +| entropy_loss | -0.483 | +| explained_variance | 0.106 | +| learning_rate | 0.0001 | +| loss | -0.0931 | +| n_updates | 66090 | +| policy_gradient_loss | -0.059 | +| value_loss | 0.000431 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.213 | +| time/ | | +| fps | 312 | +| iterations | 558 | +| time_elapsed | 1826 | +| total_timesteps | 571392 | +| train/ | | +| approx_kl | 162.84909 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.408 | +| explained_variance | -0.69 | +| learning_rate | 0.0001 | +| loss | -0.082 | +| n_updates | 66100 | +| policy_gradient_loss | -0.0642 | +| value_loss | 0.000746 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.213 | +| time/ | | +| fps | 312 | +| iterations | 559 | +| time_elapsed | 1830 | +| total_timesteps | 572416 | +| train/ | | +| approx_kl | 1.7889061 | +| clip_fraction | 0.508 | +| clip_range | 0.2 | +| entropy_loss | -0.51 | +| explained_variance | -1.34 | +| learning_rate | 0.0001 | +| loss | -0.113 | +| n_updates | 66110 | +| policy_gradient_loss | -0.0676 | +| value_loss | 0.000389 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.226 | +| time/ | | +| fps | 312 | +| iterations | 560 | +| time_elapsed | 1833 | +| total_timesteps | 573440 | +| train/ | | +| approx_kl | 1.8362033 | +| clip_fraction | 0.496 | +| clip_range | 0.2 | +| entropy_loss | -0.468 | +| explained_variance | -1.05 | +| learning_rate | 0.0001 | +| loss | -0.0766 | +| n_updates | 66120 | +| policy_gradient_loss | -0.0674 | +| value_loss | 0.000513 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.226 | +| time/ | | +| fps | 312 | +| iterations | 561 | +| time_elapsed | 1836 | +| total_timesteps | 574464 | +| train/ | | +| approx_kl | 1.7145903 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.518 | +| explained_variance | -0.134 | +| learning_rate | 0.0001 | +| loss | -0.086 | +| n_updates | 66130 | +| policy_gradient_loss | -0.0586 | +| value_loss | 0.00114 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.225 | +| time/ | | +| fps | 312 | +| iterations | 562 | +| time_elapsed | 1839 | +| total_timesteps | 575488 | +| train/ | | +| approx_kl | 1.5258585 | +| clip_fraction | 0.488 | +| clip_range | 0.2 | +| entropy_loss | -0.46 | +| explained_variance | -3.03 | +| learning_rate | 0.0001 | +| loss | -0.0909 | +| n_updates | 66140 | +| policy_gradient_loss | -0.0703 | +| value_loss | 0.000696 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.225 | +| time/ | | +| fps | 312 | +| iterations | 563 | +| time_elapsed | 1842 | +| total_timesteps | 576512 | +| train/ | | +| approx_kl | 1.8838317 | +| clip_fraction | 0.49 | +| clip_range | 0.2 | +| entropy_loss | -0.425 | +| explained_variance | -2.3 | +| learning_rate | 0.0001 | +| loss | -0.075 | +| n_updates | 66150 | +| policy_gradient_loss | -0.0644 | +| value_loss | 0.000358 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.227 | +| time/ | | +| fps | 312 | +| iterations | 564 | +| time_elapsed | 1846 | +| total_timesteps | 577536 | +| train/ | | +| approx_kl | 3.2388425 | +| clip_fraction | 0.518 | +| clip_range | 0.2 | +| entropy_loss | -0.527 | +| explained_variance | -1.06 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 66160 | +| policy_gradient_loss | -0.0753 | +| value_loss | 0.000318 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.227 | +| time/ | | +| fps | 312 | +| iterations | 565 | +| time_elapsed | 1849 | +| total_timesteps | 578560 | +| train/ | | +| approx_kl | 1.756858 | +| clip_fraction | 0.479 | +| clip_range | 0.2 | +| entropy_loss | -0.394 | +| explained_variance | -0.91 | +| learning_rate | 0.0001 | +| loss | -0.117 | +| n_updates | 66170 | +| policy_gradient_loss | -0.0699 | +| value_loss | 0.0005 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.227 | +| time/ | | +| fps | 312 | +| iterations | 566 | +| time_elapsed | 1852 | +| total_timesteps | 579584 | +| train/ | | +| approx_kl | 1.8205078 | +| clip_fraction | 0.449 | +| clip_range | 0.2 | +| entropy_loss | -0.393 | +| explained_variance | -4.74 | +| learning_rate | 0.0001 | +| loss | -0.0746 | +| n_updates | 66180 | +| policy_gradient_loss | -0.0628 | +| value_loss | 0.000282 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.225 | +| time/ | | +| fps | 312 | +| iterations | 567 | +| time_elapsed | 1855 | +| total_timesteps | 580608 | +| train/ | | +| approx_kl | 2.5845623 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.393 | +| explained_variance | -1.03 | +| learning_rate | 0.0001 | +| loss | -0.0884 | +| n_updates | 66190 | +| policy_gradient_loss | -0.0715 | +| value_loss | 0.000375 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.225 | +| time/ | | +| fps | 312 | +| iterations | 568 | +| time_elapsed | 1859 | +| total_timesteps | 581632 | +| train/ | | +| approx_kl | 1.9520617 | +| clip_fraction | 0.467 | +| clip_range | 0.2 | +| entropy_loss | -0.437 | +| explained_variance | -0.908 | +| learning_rate | 0.0001 | +| loss | -0.0894 | +| n_updates | 66200 | +| policy_gradient_loss | -0.0633 | +| value_loss | 0.000252 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.225 | +| time/ | | +| fps | 312 | +| iterations | 569 | +| time_elapsed | 1862 | +| total_timesteps | 582656 | +| train/ | | +| approx_kl | 2.7482922 | +| clip_fraction | 0.492 | +| clip_range | 0.2 | +| entropy_loss | -0.437 | +| explained_variance | -1.83 | +| learning_rate | 0.0001 | +| loss | -0.0847 | +| n_updates | 66210 | +| policy_gradient_loss | -0.071 | +| value_loss | 0.000342 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.229 | +| time/ | | +| fps | 312 | +| iterations | 570 | +| time_elapsed | 1865 | +| total_timesteps | 583680 | +| train/ | | +| approx_kl | 1.8245726 | +| clip_fraction | 0.476 | +| clip_range | 0.2 | +| entropy_loss | -0.433 | +| explained_variance | -1.21 | +| learning_rate | 0.0001 | +| loss | -0.0763 | +| n_updates | 66220 | +| policy_gradient_loss | -0.0544 | +| value_loss | 0.000543 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.229 | +| time/ | | +| fps | 312 | +| iterations | 571 | +| time_elapsed | 1869 | +| total_timesteps | 584704 | +| train/ | | +| approx_kl | 1.7467239 | +| clip_fraction | 0.512 | +| clip_range | 0.2 | +| entropy_loss | -0.496 | +| explained_variance | -0.644 | +| learning_rate | 0.0001 | +| loss | -0.0776 | +| n_updates | 66230 | +| policy_gradient_loss | -0.0711 | +| value_loss | 0.000748 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.229 | +| time/ | | +| fps | 312 | +| iterations | 572 | +| time_elapsed | 1872 | +| total_timesteps | 585728 | +| train/ | | +| approx_kl | 1.7160046 | +| clip_fraction | 0.571 | +| clip_range | 0.2 | +| entropy_loss | -0.641 | +| explained_variance | -1.96 | +| learning_rate | 0.0001 | +| loss | -0.09 | +| n_updates | 66240 | +| policy_gradient_loss | -0.0731 | +| value_loss | 0.000414 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.229 | +| time/ | | +| fps | 312 | +| iterations | 573 | +| time_elapsed | 1875 | +| total_timesteps | 586752 | +| train/ | | +| approx_kl | 2.0991492 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.458 | +| explained_variance | -1.42 | +| learning_rate | 0.0001 | +| loss | -0.0994 | +| n_updates | 66250 | +| policy_gradient_loss | -0.0661 | +| value_loss | 0.000591 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.23 | +| time/ | | +| fps | 312 | +| iterations | 574 | +| time_elapsed | 1878 | +| total_timesteps | 587776 | +| train/ | | +| approx_kl | 1.7891223 | +| clip_fraction | 0.504 | +| clip_range | 0.2 | +| entropy_loss | -0.445 | +| explained_variance | -2 | +| learning_rate | 0.0001 | +| loss | -0.0737 | +| n_updates | 66260 | +| policy_gradient_loss | -0.0745 | +| value_loss | 0.000579 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.226 | +| time/ | | +| fps | 312 | +| iterations | 575 | +| time_elapsed | 1882 | +| total_timesteps | 588800 | +| train/ | | +| approx_kl | 1.6342196 | +| clip_fraction | 0.469 | +| clip_range | 0.2 | +| entropy_loss | -0.443 | +| explained_variance | -1.02 | +| learning_rate | 0.0001 | +| loss | -0.0809 | +| n_updates | 66270 | +| policy_gradient_loss | -0.0554 | +| value_loss | 0.000703 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.226 | +| time/ | | +| fps | 312 | +| iterations | 576 | +| time_elapsed | 1885 | +| total_timesteps | 589824 | +| train/ | | +| approx_kl | 1.7167002 | +| clip_fraction | 0.457 | +| clip_range | 0.2 | +| entropy_loss | -0.393 | +| explained_variance | -0.962 | +| learning_rate | 0.0001 | +| loss | -0.08 | +| n_updates | 66280 | +| policy_gradient_loss | -0.0642 | +| value_loss | 0.000522 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | 0.224 | +| time/ | | +| fps | 312 | +| iterations | 577 | +| time_elapsed | 1888 | +| total_timesteps | 590848 | +| train/ | | +| approx_kl | 1.588861 | +| clip_fraction | 0.516 | +| clip_range | 0.2 | +| entropy_loss | -0.493 | +| explained_variance | -1.74 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 66290 | +| policy_gradient_loss | -0.0747 | +| value_loss | 0.0005 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | 0.224 | +| time/ | | +| fps | 312 | +| iterations | 578 | +| time_elapsed | 1891 | +| total_timesteps | 591872 | +| train/ | | +| approx_kl | 1.7450304 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.41 | +| explained_variance | -0.333 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 66300 | +| policy_gradient_loss | -0.0664 | +| value_loss | 0.000434 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | 0.226 | +| time/ | | +| fps | 312 | +| iterations | 579 | +| time_elapsed | 1895 | +| total_timesteps | 592896 | +| train/ | | +| approx_kl | 1.5812291 | +| clip_fraction | 0.533 | +| clip_range | 0.2 | +| entropy_loss | -0.504 | +| explained_variance | -1.31 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 66310 | +| policy_gradient_loss | -0.0744 | +| value_loss | 0.000427 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.225 | +| time/ | | +| fps | 312 | +| iterations | 580 | +| time_elapsed | 1898 | +| total_timesteps | 593920 | +| train/ | | +| approx_kl | 1.8338456 | +| clip_fraction | 0.52 | +| clip_range | 0.2 | +| entropy_loss | -0.501 | +| explained_variance | -1.18 | +| learning_rate | 0.0001 | +| loss | -0.0755 | +| n_updates | 66320 | +| policy_gradient_loss | -0.0732 | +| value_loss | 0.000465 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | 0.224 | +| time/ | | +| fps | 312 | +| iterations | 581 | +| time_elapsed | 1901 | +| total_timesteps | 594944 | +| train/ | | +| approx_kl | 2.0205562 | +| clip_fraction | 0.486 | +| clip_range | 0.2 | +| entropy_loss | -0.459 | +| explained_variance | -2.78 | +| learning_rate | 0.0001 | +| loss | -0.0804 | +| n_updates | 66330 | +| policy_gradient_loss | -0.0683 | +| value_loss | 0.000342 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | 0.224 | +| time/ | | +| fps | 312 | +| iterations | 582 | +| time_elapsed | 1904 | +| total_timesteps | 595968 | +| train/ | | +| approx_kl | 1.4041548 | +| clip_fraction | 0.468 | +| clip_range | 0.2 | +| entropy_loss | -0.444 | +| explained_variance | -1.14 | +| learning_rate | 0.0001 | +| loss | -0.067 | +| n_updates | 66340 | +| policy_gradient_loss | -0.0622 | +| value_loss | 0.000454 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.65e+03 | +| ep_rew_mean | 0.221 | +| time/ | | +| fps | 312 | +| iterations | 583 | +| time_elapsed | 1908 | +| total_timesteps | 596992 | +| train/ | | +| approx_kl | 1.5079627 | +| clip_fraction | 0.495 | +| clip_range | 0.2 | +| entropy_loss | -0.496 | +| explained_variance | -2.11 | +| learning_rate | 0.0001 | +| loss | -0.0923 | +| n_updates | 66350 | +| policy_gradient_loss | -0.0686 | +| value_loss | 0.00034 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.65e+03 | +| ep_rew_mean | 0.221 | +| time/ | | +| fps | 312 | +| iterations | 584 | +| time_elapsed | 1911 | +| total_timesteps | 598016 | +| train/ | | +| approx_kl | 2.4041848 | +| clip_fraction | 0.498 | +| clip_range | 0.2 | +| entropy_loss | -0.483 | +| explained_variance | -1.07 | +| learning_rate | 0.0001 | +| loss | -0.0936 | +| n_updates | 66360 | +| policy_gradient_loss | -0.0616 | +| value_loss | 0.000481 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | 0.217 | +| time/ | | +| fps | 312 | +| iterations | 585 | +| time_elapsed | 1915 | +| total_timesteps | 599040 | +| train/ | | +| approx_kl | 2.4970949 | +| clip_fraction | 0.509 | +| clip_range | 0.2 | +| entropy_loss | -0.487 | +| explained_variance | -0.834 | +| learning_rate | 0.0001 | +| loss | -0.0863 | +| n_updates | 66370 | +| policy_gradient_loss | -0.0662 | +| value_loss | 0.000717 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.65e+03 | +| ep_rew_mean | 0.216 | +| time/ | | +| fps | 312 | +| iterations | 586 | +| time_elapsed | 1918 | +| total_timesteps | 600064 | +| train/ | | +| approx_kl | 1.7803984 | +| clip_fraction | 0.526 | +| clip_range | 0.2 | +| entropy_loss | -0.467 | +| explained_variance | -3.03 | +| learning_rate | 0.0001 | +| loss | -0.105 | +| n_updates | 66380 | +| policy_gradient_loss | -0.0767 | +| value_loss | 0.000305 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.65e+03 | +| ep_rew_mean | 0.216 | +| time/ | | +| fps | 312 | +| iterations | 587 | +| time_elapsed | 1922 | +| total_timesteps | 601088 | +| train/ | | +| approx_kl | 1.4879464 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.471 | +| explained_variance | -0.619 | +| learning_rate | 0.0001 | +| loss | -0.112 | +| n_updates | 66390 | +| policy_gradient_loss | -0.0697 | +| value_loss | 0.000257 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.65e+03 | +| ep_rew_mean | 0.215 | +| time/ | | +| fps | 312 | +| iterations | 588 | +| time_elapsed | 1925 | +| total_timesteps | 602112 | +| train/ | | +| approx_kl | 1.2946005 | +| clip_fraction | 0.473 | +| clip_range | 0.2 | +| entropy_loss | -0.452 | +| explained_variance | -1.11 | +| learning_rate | 0.0001 | +| loss | -0.0892 | +| n_updates | 66400 | +| policy_gradient_loss | -0.0643 | +| value_loss | 0.000443 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.65e+03 | +| ep_rew_mean | 0.215 | +| time/ | | +| fps | 312 | +| iterations | 589 | +| time_elapsed | 1929 | +| total_timesteps | 603136 | +| train/ | | +| approx_kl | 1.8093703 | +| clip_fraction | 0.468 | +| clip_range | 0.2 | +| entropy_loss | -0.413 | +| explained_variance | -0.651 | +| learning_rate | 0.0001 | +| loss | -0.0861 | +| n_updates | 66410 | +| policy_gradient_loss | -0.0641 | +| value_loss | 0.000382 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.65e+03 | +| ep_rew_mean | 0.212 | +| time/ | | +| fps | 312 | +| iterations | 590 | +| time_elapsed | 1932 | +| total_timesteps | 604160 | +| train/ | | +| approx_kl | 1.757275 | +| clip_fraction | 0.519 | +| clip_range | 0.2 | +| entropy_loss | -0.552 | +| explained_variance | -1.72 | +| learning_rate | 0.0001 | +| loss | -0.0942 | +| n_updates | 66420 | +| policy_gradient_loss | -0.0742 | +| value_loss | 0.000378 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.65e+03 | +| ep_rew_mean | 0.212 | +| time/ | | +| fps | 312 | +| iterations | 591 | +| time_elapsed | 1935 | +| total_timesteps | 605184 | +| train/ | | +| approx_kl | 2.344267 | +| clip_fraction | 0.459 | +| clip_range | 0.2 | +| entropy_loss | -0.41 | +| explained_variance | -0.876 | +| learning_rate | 0.0001 | +| loss | -0.0601 | +| n_updates | 66430 | +| policy_gradient_loss | -0.0604 | +| value_loss | 0.000442 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.65e+03 | +| ep_rew_mean | 0.21 | +| time/ | | +| fps | 312 | +| iterations | 592 | +| time_elapsed | 1938 | +| total_timesteps | 606208 | +| train/ | | +| approx_kl | 2.4010375 | +| clip_fraction | 0.476 | +| clip_range | 0.2 | +| entropy_loss | -0.454 | +| explained_variance | -1.7 | +| learning_rate | 0.0001 | +| loss | -0.0884 | +| n_updates | 66440 | +| policy_gradient_loss | -0.0708 | +| value_loss | 0.000539 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.65e+03 | +| ep_rew_mean | 0.209 | +| time/ | | +| fps | 312 | +| iterations | 593 | +| time_elapsed | 1942 | +| total_timesteps | 607232 | +| train/ | | +| approx_kl | 3.5078459 | +| clip_fraction | 0.452 | +| clip_range | 0.2 | +| entropy_loss | -0.427 | +| explained_variance | -1.22 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 66450 | +| policy_gradient_loss | -0.0597 | +| value_loss | 0.000279 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.65e+03 | +| ep_rew_mean | 0.208 | +| time/ | | +| fps | 312 | +| iterations | 594 | +| time_elapsed | 1945 | +| total_timesteps | 608256 | +| train/ | | +| approx_kl | 1.7156262 | +| clip_fraction | 0.454 | +| clip_range | 0.2 | +| entropy_loss | -0.399 | +| explained_variance | -1.14 | +| learning_rate | 0.0001 | +| loss | -0.0591 | +| n_updates | 66460 | +| policy_gradient_loss | -0.0621 | +| value_loss | 0.00037 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.64e+03 | +| ep_rew_mean | 0.211 | +| time/ | | +| fps | 312 | +| iterations | 595 | +| time_elapsed | 1948 | +| total_timesteps | 609280 | +| train/ | | +| approx_kl | 2.056221 | +| clip_fraction | 0.448 | +| clip_range | 0.2 | +| entropy_loss | -0.388 | +| explained_variance | -0.568 | +| learning_rate | 0.0001 | +| loss | -0.0901 | +| n_updates | 66470 | +| policy_gradient_loss | -0.0638 | +| value_loss | 0.000323 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.63e+03 | +| ep_rew_mean | 0.208 | +| time/ | | +| fps | 312 | +| iterations | 596 | +| time_elapsed | 1951 | +| total_timesteps | 610304 | +| train/ | | +| approx_kl | 1.5773816 | +| clip_fraction | 0.446 | +| clip_range | 0.2 | +| entropy_loss | -0.449 | +| explained_variance | -0.759 | +| learning_rate | 0.0001 | +| loss | -0.0846 | +| n_updates | 66480 | +| policy_gradient_loss | -0.0605 | +| value_loss | 0.000445 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.63e+03 | +| ep_rew_mean | 0.208 | +| time/ | | +| fps | 312 | +| iterations | 597 | +| time_elapsed | 1955 | +| total_timesteps | 611328 | +| train/ | | +| approx_kl | 1.9150696 | +| clip_fraction | 0.457 | +| clip_range | 0.2 | +| entropy_loss | -0.434 | +| explained_variance | -1.05 | +| learning_rate | 0.0001 | +| loss | -0.058 | +| n_updates | 66490 | +| policy_gradient_loss | -0.0658 | +| value_loss | 0.000503 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.64e+03 | +| ep_rew_mean | 0.209 | +| time/ | | +| fps | 312 | +| iterations | 598 | +| time_elapsed | 1958 | +| total_timesteps | 612352 | +| train/ | | +| approx_kl | 1.5627236 | +| clip_fraction | 0.522 | +| clip_range | 0.2 | +| entropy_loss | -0.63 | +| explained_variance | -2.98 | +| learning_rate | 0.0001 | +| loss | -0.0881 | +| n_updates | 66500 | +| policy_gradient_loss | -0.0741 | +| value_loss | 0.000158 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.64e+03 | +| ep_rew_mean | 0.21 | +| time/ | | +| fps | 312 | +| iterations | 599 | +| time_elapsed | 1961 | +| total_timesteps | 613376 | +| train/ | | +| approx_kl | 1.7493031 | +| clip_fraction | 0.529 | +| clip_range | 0.2 | +| entropy_loss | -0.611 | +| explained_variance | -0.35 | +| learning_rate | 0.0001 | +| loss | -0.0707 | +| n_updates | 66510 | +| policy_gradient_loss | -0.0618 | +| value_loss | 0.00026 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.64e+03 | +| ep_rew_mean | 0.21 | +| time/ | | +| fps | 312 | +| iterations | 600 | +| time_elapsed | 1964 | +| total_timesteps | 614400 | +| train/ | | +| approx_kl | 1.9617449 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.396 | +| explained_variance | -0.445 | +| learning_rate | 0.0001 | +| loss | -0.068 | +| n_updates | 66520 | +| policy_gradient_loss | -0.0659 | +| value_loss | 0.000466 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.64e+03 | +| ep_rew_mean | 0.21 | +| time/ | | +| fps | 312 | +| iterations | 601 | +| time_elapsed | 1967 | +| total_timesteps | 615424 | +| train/ | | +| approx_kl | 1.8054183 | +| clip_fraction | 0.518 | +| clip_range | 0.2 | +| entropy_loss | -0.504 | +| explained_variance | -1.65 | +| learning_rate | 0.0001 | +| loss | -0.0676 | +| n_updates | 66530 | +| policy_gradient_loss | -0.0716 | +| value_loss | 0.000792 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.65e+03 | +| ep_rew_mean | 0.209 | +| time/ | | +| fps | 312 | +| iterations | 602 | +| time_elapsed | 1971 | +| total_timesteps | 616448 | +| train/ | | +| approx_kl | 1.6837454 | +| clip_fraction | 0.499 | +| clip_range | 0.2 | +| entropy_loss | -0.486 | +| explained_variance | -9.55 | +| learning_rate | 0.0001 | +| loss | -0.0842 | +| n_updates | 66540 | +| policy_gradient_loss | -0.0673 | +| value_loss | 0.000281 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.65e+03 | +| ep_rew_mean | 0.209 | +| time/ | | +| fps | 312 | +| iterations | 603 | +| time_elapsed | 1974 | +| total_timesteps | 617472 | +| train/ | | +| approx_kl | 1.7516463 | +| clip_fraction | 0.482 | +| clip_range | 0.2 | +| entropy_loss | -0.483 | +| explained_variance | -1.02 | +| learning_rate | 0.0001 | +| loss | -0.09 | +| n_updates | 66550 | +| policy_gradient_loss | -0.0626 | +| value_loss | 0.000269 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.65e+03 | +| ep_rew_mean | 0.205 | +| time/ | | +| fps | 312 | +| iterations | 604 | +| time_elapsed | 1977 | +| total_timesteps | 618496 | +| train/ | | +| approx_kl | 1.8262227 | +| clip_fraction | 0.485 | +| clip_range | 0.2 | +| entropy_loss | -0.421 | +| explained_variance | -0.765 | +| learning_rate | 0.0001 | +| loss | -0.0772 | +| n_updates | 66560 | +| policy_gradient_loss | -0.0635 | +| value_loss | 0.00043 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.65e+03 | +| ep_rew_mean | 0.199 | +| time/ | | +| fps | 312 | +| iterations | 605 | +| time_elapsed | 1981 | +| total_timesteps | 619520 | +| train/ | | +| approx_kl | 1.8841114 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.39 | +| explained_variance | -1.66 | +| learning_rate | 0.0001 | +| loss | -0.0834 | +| n_updates | 66570 | +| policy_gradient_loss | -0.0669 | +| value_loss | 0.000437 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.64e+03 | +| ep_rew_mean | 0.202 | +| time/ | | +| fps | 312 | +| iterations | 606 | +| time_elapsed | 1984 | +| total_timesteps | 620544 | +| train/ | | +| approx_kl | 2.2106354 | +| clip_fraction | 0.44 | +| clip_range | 0.2 | +| entropy_loss | -0.359 | +| explained_variance | -1.74 | +| learning_rate | 0.0001 | +| loss | -0.0889 | +| n_updates | 66580 | +| policy_gradient_loss | -0.0604 | +| value_loss | 0.000309 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.64e+03 | +| ep_rew_mean | 0.202 | +| time/ | | +| fps | 312 | +| iterations | 607 | +| time_elapsed | 1987 | +| total_timesteps | 621568 | +| train/ | | +| approx_kl | 2.455033 | +| clip_fraction | 0.476 | +| clip_range | 0.2 | +| entropy_loss | -0.431 | +| explained_variance | -0.141 | +| learning_rate | 0.0001 | +| loss | -0.0899 | +| n_updates | 66590 | +| policy_gradient_loss | -0.0617 | +| value_loss | 0.000893 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.64e+03 | +| ep_rew_mean | 0.2 | +| time/ | | +| fps | 312 | +| iterations | 608 | +| time_elapsed | 1991 | +| total_timesteps | 622592 | +| train/ | | +| approx_kl | 2.05198 | +| clip_fraction | 0.506 | +| clip_range | 0.2 | +| entropy_loss | -0.472 | +| explained_variance | -2.62 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 66600 | +| policy_gradient_loss | -0.0732 | +| value_loss | 0.000611 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.64e+03 | +| ep_rew_mean | 0.2 | +| time/ | | +| fps | 312 | +| iterations | 609 | +| time_elapsed | 1994 | +| total_timesteps | 623616 | +| train/ | | +| approx_kl | 2.0447373 | +| clip_fraction | 0.477 | +| clip_range | 0.2 | +| entropy_loss | -0.458 | +| explained_variance | -0.927 | +| learning_rate | 0.0001 | +| loss | -0.0986 | +| n_updates | 66610 | +| policy_gradient_loss | -0.0651 | +| value_loss | 0.000429 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.65e+03 | +| ep_rew_mean | 0.2 | +| time/ | | +| fps | 312 | +| iterations | 610 | +| time_elapsed | 1997 | +| total_timesteps | 624640 | +| train/ | | +| approx_kl | 1.8766549 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.415 | +| explained_variance | -1.33 | +| learning_rate | 0.0001 | +| loss | -0.0927 | +| n_updates | 66620 | +| policy_gradient_loss | -0.068 | +| value_loss | 0.000482 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.65e+03 | +| ep_rew_mean | 0.2 | +| time/ | | +| fps | 312 | +| iterations | 611 | +| time_elapsed | 2000 | +| total_timesteps | 625664 | +| train/ | | +| approx_kl | 2.3799171 | +| clip_fraction | 0.504 | +| clip_range | 0.2 | +| entropy_loss | -0.44 | +| explained_variance | -1.14 | +| learning_rate | 0.0001 | +| loss | -0.112 | +| n_updates | 66630 | +| policy_gradient_loss | -0.0722 | +| value_loss | 0.000717 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.65e+03 | +| ep_rew_mean | 0.199 | +| time/ | | +| fps | 312 | +| iterations | 612 | +| time_elapsed | 2003 | +| total_timesteps | 626688 | +| train/ | | +| approx_kl | 1.4333358 | +| clip_fraction | 0.5 | +| clip_range | 0.2 | +| entropy_loss | -0.451 | +| explained_variance | -1.09 | +| learning_rate | 0.0001 | +| loss | -0.0855 | +| n_updates | 66640 | +| policy_gradient_loss | -0.0662 | +| value_loss | 0.000644 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.65e+03 | +| ep_rew_mean | 0.199 | +| time/ | | +| fps | 312 | +| iterations | 613 | +| time_elapsed | 2007 | +| total_timesteps | 627712 | +| train/ | | +| approx_kl | 2.4696088 | +| clip_fraction | 0.551 | +| clip_range | 0.2 | +| entropy_loss | -0.579 | +| explained_variance | -0.668 | +| learning_rate | 0.0001 | +| loss | -0.0989 | +| n_updates | 66650 | +| policy_gradient_loss | -0.0677 | +| value_loss | 0.000269 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.65e+03 | +| ep_rew_mean | 0.202 | +| time/ | | +| fps | 312 | +| iterations | 614 | +| time_elapsed | 2010 | +| total_timesteps | 628736 | +| train/ | | +| approx_kl | 1.9422716 | +| clip_fraction | 0.476 | +| clip_range | 0.2 | +| entropy_loss | -0.371 | +| explained_variance | -1.77 | +| learning_rate | 0.0001 | +| loss | -0.0899 | +| n_updates | 66660 | +| policy_gradient_loss | -0.0453 | +| value_loss | 0.000501 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.65e+03 | +| ep_rew_mean | 0.202 | +| time/ | | +| fps | 312 | +| iterations | 615 | +| time_elapsed | 2013 | +| total_timesteps | 629760 | +| train/ | | +| approx_kl | 1.689615 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.395 | +| explained_variance | -1 | +| learning_rate | 0.0001 | +| loss | -0.0948 | +| n_updates | 66670 | +| policy_gradient_loss | -0.0663 | +| value_loss | 0.000551 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.65e+03 | +| ep_rew_mean | 0.204 | +| time/ | | +| fps | 312 | +| iterations | 616 | +| time_elapsed | 2017 | +| total_timesteps | 630784 | +| train/ | | +| approx_kl | 1.9159777 | +| clip_fraction | 0.459 | +| clip_range | 0.2 | +| entropy_loss | -0.349 | +| explained_variance | -2.5 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 66680 | +| policy_gradient_loss | -0.0642 | +| value_loss | 0.000488 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | 0.205 | +| time/ | | +| fps | 312 | +| iterations | 617 | +| time_elapsed | 2020 | +| total_timesteps | 631808 | +| train/ | | +| approx_kl | 1.8877201 | +| clip_fraction | 0.509 | +| clip_range | 0.2 | +| entropy_loss | -0.522 | +| explained_variance | -0.285 | +| learning_rate | 0.0001 | +| loss | -0.0742 | +| n_updates | 66690 | +| policy_gradient_loss | -0.0646 | +| value_loss | 0.000399 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | 0.205 | +| time/ | | +| fps | 312 | +| iterations | 618 | +| time_elapsed | 2023 | +| total_timesteps | 632832 | +| train/ | | +| approx_kl | 1.6697133 | +| clip_fraction | 0.5 | +| clip_range | 0.2 | +| entropy_loss | -0.465 | +| explained_variance | -0.315 | +| learning_rate | 0.0001 | +| loss | -0.0644 | +| n_updates | 66700 | +| policy_gradient_loss | -0.0684 | +| value_loss | 0.000359 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | 0.205 | +| time/ | | +| fps | 312 | +| iterations | 619 | +| time_elapsed | 2027 | +| total_timesteps | 633856 | +| train/ | | +| approx_kl | 2.30221 | +| clip_fraction | 0.503 | +| clip_range | 0.2 | +| entropy_loss | -0.439 | +| explained_variance | -2.27 | +| learning_rate | 0.0001 | +| loss | -0.0849 | +| n_updates | 66710 | +| policy_gradient_loss | -0.0684 | +| value_loss | 0.000245 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.204 | +| time/ | | +| fps | 312 | +| iterations | 620 | +| time_elapsed | 2030 | +| total_timesteps | 634880 | +| train/ | | +| approx_kl | 1.9361868 | +| clip_fraction | 0.454 | +| clip_range | 0.2 | +| entropy_loss | -0.332 | +| explained_variance | -7.24 | +| learning_rate | 0.0001 | +| loss | -0.0886 | +| n_updates | 66720 | +| policy_gradient_loss | -0.0711 | +| value_loss | 0.000215 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.204 | +| time/ | | +| fps | 312 | +| iterations | 621 | +| time_elapsed | 2034 | +| total_timesteps | 635904 | +| train/ | | +| approx_kl | 2.8065343 | +| clip_fraction | 0.494 | +| clip_range | 0.2 | +| entropy_loss | -0.49 | +| explained_variance | -0.428 | +| learning_rate | 0.0001 | +| loss | -0.0831 | +| n_updates | 66730 | +| policy_gradient_loss | -0.0548 | +| value_loss | 0.0003 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.204 | +| time/ | | +| fps | 312 | +| iterations | 622 | +| time_elapsed | 2037 | +| total_timesteps | 636928 | +| train/ | | +| approx_kl | 2.0469253 | +| clip_fraction | 0.505 | +| clip_range | 0.2 | +| entropy_loss | -0.492 | +| explained_variance | -1.34 | +| learning_rate | 0.0001 | +| loss | -0.113 | +| n_updates | 66740 | +| policy_gradient_loss | -0.0698 | +| value_loss | 0.000401 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.204 | +| time/ | | +| fps | 312 | +| iterations | 623 | +| time_elapsed | 2041 | +| total_timesteps | 637952 | +| train/ | | +| approx_kl | 2.2165241 | +| clip_fraction | 0.462 | +| clip_range | 0.2 | +| entropy_loss | -0.418 | +| explained_variance | -1.14 | +| learning_rate | 0.0001 | +| loss | -0.077 | +| n_updates | 66750 | +| policy_gradient_loss | -0.0589 | +| value_loss | 0.00045 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.205 | +| time/ | | +| fps | 312 | +| iterations | 624 | +| time_elapsed | 2044 | +| total_timesteps | 638976 | +| train/ | | +| approx_kl | 2.03971 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.417 | +| explained_variance | -3.43 | +| learning_rate | 0.0001 | +| loss | -0.0998 | +| n_updates | 66760 | +| policy_gradient_loss | -0.0675 | +| value_loss | 0.000588 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.205 | +| time/ | | +| fps | 312 | +| iterations | 625 | +| time_elapsed | 2048 | +| total_timesteps | 640000 | +| train/ | | +| approx_kl | 2.0120082 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.393 | +| explained_variance | -1.01 | +| learning_rate | 0.0001 | +| loss | -0.074 | +| n_updates | 66770 | +| policy_gradient_loss | -0.0667 | +| value_loss | 0.000423 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.21 | +| time/ | | +| fps | 312 | +| iterations | 626 | +| time_elapsed | 2051 | +| total_timesteps | 641024 | +| train/ | | +| approx_kl | 1.5104129 | +| clip_fraction | 0.503 | +| clip_range | 0.2 | +| entropy_loss | -0.486 | +| explained_variance | -0.64 | +| learning_rate | 0.0001 | +| loss | -0.0641 | +| n_updates | 66780 | +| policy_gradient_loss | -0.0645 | +| value_loss | 0.00069 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.213 | +| time/ | | +| fps | 312 | +| iterations | 627 | +| time_elapsed | 2054 | +| total_timesteps | 642048 | +| train/ | | +| approx_kl | 1.9146813 | +| clip_fraction | 0.514 | +| clip_range | 0.2 | +| entropy_loss | -0.549 | +| explained_variance | -1.21 | +| learning_rate | 0.0001 | +| loss | -0.0643 | +| n_updates | 66790 | +| policy_gradient_loss | -0.0637 | +| value_loss | 0.00066 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.213 | +| time/ | | +| fps | 312 | +| iterations | 628 | +| time_elapsed | 2057 | +| total_timesteps | 643072 | +| train/ | | +| approx_kl | 2.086305 | +| clip_fraction | 0.496 | +| clip_range | 0.2 | +| entropy_loss | -0.413 | +| explained_variance | -1.38 | +| learning_rate | 0.0001 | +| loss | -0.0605 | +| n_updates | 66800 | +| policy_gradient_loss | -0.0646 | +| value_loss | 0.000512 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.214 | +| time/ | | +| fps | 312 | +| iterations | 629 | +| time_elapsed | 2061 | +| total_timesteps | 644096 | +| train/ | | +| approx_kl | 1.7218964 | +| clip_fraction | 0.499 | +| clip_range | 0.2 | +| entropy_loss | -0.512 | +| explained_variance | -2.33 | +| learning_rate | 0.0001 | +| loss | -0.0768 | +| n_updates | 66810 | +| policy_gradient_loss | -0.0637 | +| value_loss | 0.00059 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.214 | +| time/ | | +| fps | 312 | +| iterations | 630 | +| time_elapsed | 2064 | +| total_timesteps | 645120 | +| train/ | | +| approx_kl | 2.2861252 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.385 | +| explained_variance | -1.28 | +| learning_rate | 0.0001 | +| loss | -0.0903 | +| n_updates | 66820 | +| policy_gradient_loss | -0.0703 | +| value_loss | 0.000366 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.211 | +| time/ | | +| fps | 312 | +| iterations | 631 | +| time_elapsed | 2067 | +| total_timesteps | 646144 | +| train/ | | +| approx_kl | 2.5953963 | +| clip_fraction | 0.486 | +| clip_range | 0.2 | +| entropy_loss | -0.393 | +| explained_variance | -0.594 | +| learning_rate | 0.0001 | +| loss | -0.0908 | +| n_updates | 66830 | +| policy_gradient_loss | -0.0631 | +| value_loss | 0.000303 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.211 | +| time/ | | +| fps | 312 | +| iterations | 632 | +| time_elapsed | 2070 | +| total_timesteps | 647168 | +| train/ | | +| approx_kl | 1.8613765 | +| clip_fraction | 0.479 | +| clip_range | 0.2 | +| entropy_loss | -0.441 | +| explained_variance | -1.88 | +| learning_rate | 0.0001 | +| loss | -0.0786 | +| n_updates | 66840 | +| policy_gradient_loss | -0.0616 | +| value_loss | 0.000168 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.207 | +| time/ | | +| fps | 312 | +| iterations | 633 | +| time_elapsed | 2074 | +| total_timesteps | 648192 | +| train/ | | +| approx_kl | 2.0986073 | +| clip_fraction | 0.515 | +| clip_range | 0.2 | +| entropy_loss | -0.439 | +| explained_variance | -0.808 | +| learning_rate | 0.0001 | +| loss | -0.0988 | +| n_updates | 66850 | +| policy_gradient_loss | -0.0701 | +| value_loss | 0.000287 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.205 | +| time/ | | +| fps | 312 | +| iterations | 634 | +| time_elapsed | 2077 | +| total_timesteps | 649216 | +| train/ | | +| approx_kl | 1.6802619 | +| clip_fraction | 0.464 | +| clip_range | 0.2 | +| entropy_loss | -0.36 | +| explained_variance | -1.25 | +| learning_rate | 0.0001 | +| loss | -0.0922 | +| n_updates | 66860 | +| policy_gradient_loss | -0.0648 | +| value_loss | 0.000525 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.204 | +| time/ | | +| fps | 312 | +| iterations | 635 | +| time_elapsed | 2080 | +| total_timesteps | 650240 | +| train/ | | +| approx_kl | 1.8239298 | +| clip_fraction | 0.457 | +| clip_range | 0.2 | +| entropy_loss | -0.392 | +| explained_variance | -0.471 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 66870 | +| policy_gradient_loss | -0.0673 | +| value_loss | 0.000337 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.204 | +| time/ | | +| fps | 312 | +| iterations | 636 | +| time_elapsed | 2084 | +| total_timesteps | 651264 | +| train/ | | +| approx_kl | 1.4426918 | +| clip_fraction | 0.439 | +| clip_range | 0.2 | +| entropy_loss | -0.367 | +| explained_variance | -1.71 | +| learning_rate | 0.0001 | +| loss | -0.0858 | +| n_updates | 66880 | +| policy_gradient_loss | -0.0657 | +| value_loss | 0.000313 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.209 | +| time/ | | +| fps | 312 | +| iterations | 637 | +| time_elapsed | 2087 | +| total_timesteps | 652288 | +| train/ | | +| approx_kl | 2.2100072 | +| clip_fraction | 0.504 | +| clip_range | 0.2 | +| entropy_loss | -0.478 | +| explained_variance | -0.553 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 66890 | +| policy_gradient_loss | -0.0689 | +| value_loss | 0.000485 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.209 | +| time/ | | +| fps | 312 | +| iterations | 638 | +| time_elapsed | 2091 | +| total_timesteps | 653312 | +| train/ | | +| approx_kl | 3.3200593 | +| clip_fraction | 0.468 | +| clip_range | 0.2 | +| entropy_loss | -0.413 | +| explained_variance | -0.931 | +| learning_rate | 0.0001 | +| loss | -0.061 | +| n_updates | 66900 | +| policy_gradient_loss | -0.0625 | +| value_loss | 0.000329 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.208 | +| time/ | | +| fps | 312 | +| iterations | 639 | +| time_elapsed | 2094 | +| total_timesteps | 654336 | +| train/ | | +| approx_kl | 1.8961852 | +| clip_fraction | 0.522 | +| clip_range | 0.2 | +| entropy_loss | -0.546 | +| explained_variance | -0.581 | +| learning_rate | 0.0001 | +| loss | -0.116 | +| n_updates | 66910 | +| policy_gradient_loss | -0.0684 | +| value_loss | 0.000238 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.208 | +| time/ | | +| fps | 312 | +| iterations | 640 | +| time_elapsed | 2097 | +| total_timesteps | 655360 | +| train/ | | +| approx_kl | 2.0417032 | +| clip_fraction | 0.467 | +| clip_range | 0.2 | +| entropy_loss | -0.393 | +| explained_variance | -0.597 | +| learning_rate | 0.0001 | +| loss | -0.0711 | +| n_updates | 66920 | +| policy_gradient_loss | -0.0675 | +| value_loss | 0.000347 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.208 | +| time/ | | +| fps | 312 | +| iterations | 641 | +| time_elapsed | 2101 | +| total_timesteps | 656384 | +| train/ | | +| approx_kl | 1.5582736 | +| clip_fraction | 0.496 | +| clip_range | 0.2 | +| entropy_loss | -0.48 | +| explained_variance | -0.864 | +| learning_rate | 0.0001 | +| loss | -0.0851 | +| n_updates | 66930 | +| policy_gradient_loss | -0.0647 | +| value_loss | 0.000439 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.207 | +| time/ | | +| fps | 312 | +| iterations | 642 | +| time_elapsed | 2104 | +| total_timesteps | 657408 | +| train/ | | +| approx_kl | 1.8887491 | +| clip_fraction | 0.462 | +| clip_range | 0.2 | +| entropy_loss | -0.37 | +| explained_variance | -1.52 | +| learning_rate | 0.0001 | +| loss | -0.106 | +| n_updates | 66940 | +| policy_gradient_loss | -0.0706 | +| value_loss | 0.000547 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.207 | +| time/ | | +| fps | 312 | +| iterations | 643 | +| time_elapsed | 2108 | +| total_timesteps | 658432 | +| train/ | | +| approx_kl | 1.839718 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.391 | +| explained_variance | -0.717 | +| learning_rate | 0.0001 | +| loss | -0.075 | +| n_updates | 66950 | +| policy_gradient_loss | -0.0687 | +| value_loss | 0.000594 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.207 | +| time/ | | +| fps | 312 | +| iterations | 644 | +| time_elapsed | 2111 | +| total_timesteps | 659456 | +| train/ | | +| approx_kl | 1.7744069 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.42 | +| explained_variance | -3.08 | +| learning_rate | 0.0001 | +| loss | -0.0927 | +| n_updates | 66960 | +| policy_gradient_loss | -0.0688 | +| value_loss | 0.000369 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.206 | +| time/ | | +| fps | 312 | +| iterations | 645 | +| time_elapsed | 2114 | +| total_timesteps | 660480 | +| train/ | | +| approx_kl | 1.7468804 | +| clip_fraction | 0.465 | +| clip_range | 0.2 | +| entropy_loss | -0.402 | +| explained_variance | -1.67 | +| learning_rate | 0.0001 | +| loss | -0.0698 | +| n_updates | 66970 | +| policy_gradient_loss | -0.0617 | +| value_loss | 0.000376 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.206 | +| time/ | | +| fps | 312 | +| iterations | 646 | +| time_elapsed | 2117 | +| total_timesteps | 661504 | +| train/ | | +| approx_kl | 1.5143065 | +| clip_fraction | 0.485 | +| clip_range | 0.2 | +| entropy_loss | -0.409 | +| explained_variance | -0.838 | +| learning_rate | 0.0001 | +| loss | -0.074 | +| n_updates | 66980 | +| policy_gradient_loss | -0.067 | +| value_loss | 0.000459 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.206 | +| time/ | | +| fps | 312 | +| iterations | 647 | +| time_elapsed | 2120 | +| total_timesteps | 662528 | +| train/ | | +| approx_kl | 1.7601995 | +| clip_fraction | 0.508 | +| clip_range | 0.2 | +| entropy_loss | -0.47 | +| explained_variance | -1.01 | +| learning_rate | 0.0001 | +| loss | -0.0702 | +| n_updates | 66990 | +| policy_gradient_loss | -0.0636 | +| value_loss | 0.000376 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.206 | +| time/ | | +| fps | 312 | +| iterations | 648 | +| time_elapsed | 2124 | +| total_timesteps | 663552 | +| train/ | | +| approx_kl | 1.1671305 | +| clip_fraction | 0.452 | +| clip_range | 0.2 | +| entropy_loss | -0.384 | +| explained_variance | -2.38 | +| learning_rate | 0.0001 | +| loss | -0.0651 | +| n_updates | 67000 | +| policy_gradient_loss | -0.0557 | +| value_loss | 0.000203 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.204 | +| time/ | | +| fps | 312 | +| iterations | 649 | +| time_elapsed | 2127 | +| total_timesteps | 664576 | +| train/ | | +| approx_kl | 1.9181087 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.423 | +| explained_variance | -0.33 | +| learning_rate | 0.0001 | +| loss | -0.0665 | +| n_updates | 67010 | +| policy_gradient_loss | -0.0697 | +| value_loss | 0.000436 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.204 | +| time/ | | +| fps | 312 | +| iterations | 650 | +| time_elapsed | 2130 | +| total_timesteps | 665600 | +| train/ | | +| approx_kl | 2.148868 | +| clip_fraction | 0.486 | +| clip_range | 0.2 | +| entropy_loss | -0.454 | +| explained_variance | -0.709 | +| learning_rate | 0.0001 | +| loss | -0.0786 | +| n_updates | 67020 | +| policy_gradient_loss | -0.0726 | +| value_loss | 0.000474 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.205 | +| time/ | | +| fps | 312 | +| iterations | 651 | +| time_elapsed | 2133 | +| total_timesteps | 666624 | +| train/ | | +| approx_kl | 4.230478 | +| clip_fraction | 0.502 | +| clip_range | 0.2 | +| entropy_loss | -0.461 | +| explained_variance | -1.21 | +| learning_rate | 0.0001 | +| loss | -0.0896 | +| n_updates | 67030 | +| policy_gradient_loss | -0.0719 | +| value_loss | 0.00051 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.205 | +| time/ | | +| fps | 312 | +| iterations | 652 | +| time_elapsed | 2136 | +| total_timesteps | 667648 | +| train/ | | +| approx_kl | 1.5357882 | +| clip_fraction | 0.506 | +| clip_range | 0.2 | +| entropy_loss | -0.49 | +| explained_variance | -1.77 | +| learning_rate | 0.0001 | +| loss | -0.0965 | +| n_updates | 67040 | +| policy_gradient_loss | -0.0708 | +| value_loss | 0.000361 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.203 | +| time/ | | +| fps | 312 | +| iterations | 653 | +| time_elapsed | 2139 | +| total_timesteps | 668672 | +| train/ | | +| approx_kl | 2.4530492 | +| clip_fraction | 0.53 | +| clip_range | 0.2 | +| entropy_loss | -0.485 | +| explained_variance | -1.88 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 67050 | +| policy_gradient_loss | -0.0765 | +| value_loss | 0.000349 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.203 | +| time/ | | +| fps | 312 | +| iterations | 654 | +| time_elapsed | 2143 | +| total_timesteps | 669696 | +| train/ | | +| approx_kl | 1.9302071 | +| clip_fraction | 0.503 | +| clip_range | 0.2 | +| entropy_loss | -0.434 | +| explained_variance | -4.32 | +| learning_rate | 0.0001 | +| loss | -0.0844 | +| n_updates | 67060 | +| policy_gradient_loss | -0.0653 | +| value_loss | 0.000383 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.202 | +| time/ | | +| fps | 312 | +| iterations | 655 | +| time_elapsed | 2146 | +| total_timesteps | 670720 | +| train/ | | +| approx_kl | 1.7350585 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.442 | +| explained_variance | -0.732 | +| learning_rate | 0.0001 | +| loss | -0.0698 | +| n_updates | 67070 | +| policy_gradient_loss | -0.0634 | +| value_loss | 0.000339 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.202 | +| time/ | | +| fps | 312 | +| iterations | 656 | +| time_elapsed | 2150 | +| total_timesteps | 671744 | +| train/ | | +| approx_kl | 1.7182469 | +| clip_fraction | 0.517 | +| clip_range | 0.2 | +| entropy_loss | -0.496 | +| explained_variance | -0.94 | +| learning_rate | 0.0001 | +| loss | -0.0868 | +| n_updates | 67080 | +| policy_gradient_loss | -0.0713 | +| value_loss | 0.000325 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.202 | +| time/ | | +| fps | 312 | +| iterations | 657 | +| time_elapsed | 2153 | +| total_timesteps | 672768 | +| train/ | | +| approx_kl | 1.6796939 | +| clip_fraction | 0.485 | +| clip_range | 0.2 | +| entropy_loss | -0.475 | +| explained_variance | -1.05 | +| learning_rate | 0.0001 | +| loss | -0.096 | +| n_updates | 67090 | +| policy_gradient_loss | -0.0635 | +| value_loss | 0.000326 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.2 | +| time/ | | +| fps | 312 | +| iterations | 658 | +| time_elapsed | 2157 | +| total_timesteps | 673792 | +| train/ | | +| approx_kl | 1.6894913 | +| clip_fraction | 0.488 | +| clip_range | 0.2 | +| entropy_loss | -0.483 | +| explained_variance | -3.35 | +| learning_rate | 0.0001 | +| loss | -0.0857 | +| n_updates | 67100 | +| policy_gradient_loss | -0.0695 | +| value_loss | 0.000261 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.199 | +| time/ | | +| fps | 312 | +| iterations | 659 | +| time_elapsed | 2160 | +| total_timesteps | 674816 | +| train/ | | +| approx_kl | 1.8347352 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.411 | +| explained_variance | -1.05 | +| learning_rate | 0.0001 | +| loss | -0.0855 | +| n_updates | 67110 | +| policy_gradient_loss | -0.0673 | +| value_loss | 0.000515 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.203 | +| time/ | | +| fps | 312 | +| iterations | 660 | +| time_elapsed | 2164 | +| total_timesteps | 675840 | +| train/ | | +| approx_kl | 1.4524655 | +| clip_fraction | 0.482 | +| clip_range | 0.2 | +| entropy_loss | -0.516 | +| explained_variance | -0.682 | +| learning_rate | 0.0001 | +| loss | -0.107 | +| n_updates | 67120 | +| policy_gradient_loss | -0.07 | +| value_loss | 0.000324 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.203 | +| time/ | | +| fps | 312 | +| iterations | 661 | +| time_elapsed | 2167 | +| total_timesteps | 676864 | +| train/ | | +| approx_kl | 1.316788 | +| clip_fraction | 0.472 | +| clip_range | 0.2 | +| entropy_loss | -0.656 | +| explained_variance | -0.192 | +| learning_rate | 0.0001 | +| loss | -0.0931 | +| n_updates | 67130 | +| policy_gradient_loss | -0.0521 | +| value_loss | 0.000511 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.202 | +| time/ | | +| fps | 312 | +| iterations | 662 | +| time_elapsed | 2170 | +| total_timesteps | 677888 | +| train/ | | +| approx_kl | 1.6818202 | +| clip_fraction | 0.496 | +| clip_range | 0.2 | +| entropy_loss | -0.522 | +| explained_variance | -2.46 | +| learning_rate | 0.0001 | +| loss | -0.0934 | +| n_updates | 67140 | +| policy_gradient_loss | -0.0691 | +| value_loss | 0.00028 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.197 | +| time/ | | +| fps | 312 | +| iterations | 663 | +| time_elapsed | 2174 | +| total_timesteps | 678912 | +| train/ | | +| approx_kl | 1.4038174 | +| clip_fraction | 0.486 | +| clip_range | 0.2 | +| entropy_loss | -0.467 | +| explained_variance | -3.47 | +| learning_rate | 0.0001 | +| loss | -0.0675 | +| n_updates | 67150 | +| policy_gradient_loss | -0.0684 | +| value_loss | 0.000162 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.197 | +| time/ | | +| fps | 312 | +| iterations | 664 | +| time_elapsed | 2177 | +| total_timesteps | 679936 | +| train/ | | +| approx_kl | 2.0448542 | +| clip_fraction | 0.496 | +| clip_range | 0.2 | +| entropy_loss | -0.443 | +| explained_variance | -0.886 | +| learning_rate | 0.0001 | +| loss | -0.0964 | +| n_updates | 67160 | +| policy_gradient_loss | -0.0663 | +| value_loss | 0.000272 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.197 | +| time/ | | +| fps | 312 | +| iterations | 665 | +| time_elapsed | 2180 | +| total_timesteps | 680960 | +| train/ | | +| approx_kl | 1.6578515 | +| clip_fraction | 0.504 | +| clip_range | 0.2 | +| entropy_loss | -0.466 | +| explained_variance | -2.02 | +| learning_rate | 0.0001 | +| loss | -0.0882 | +| n_updates | 67170 | +| policy_gradient_loss | -0.0736 | +| value_loss | 0.000245 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.196 | +| time/ | | +| fps | 312 | +| iterations | 666 | +| time_elapsed | 2183 | +| total_timesteps | 681984 | +| train/ | | +| approx_kl | 1.8925772 | +| clip_fraction | 0.519 | +| clip_range | 0.2 | +| entropy_loss | -0.541 | +| explained_variance | -2.03 | +| learning_rate | 0.0001 | +| loss | -0.0913 | +| n_updates | 67180 | +| policy_gradient_loss | -0.0744 | +| value_loss | 0.000336 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.196 | +| time/ | | +| fps | 312 | +| iterations | 667 | +| time_elapsed | 2187 | +| total_timesteps | 683008 | +| train/ | | +| approx_kl | 1.6901257 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.467 | +| explained_variance | -0.983 | +| learning_rate | 0.0001 | +| loss | -0.0928 | +| n_updates | 67190 | +| policy_gradient_loss | -0.0652 | +| value_loss | 0.000363 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.197 | +| time/ | | +| fps | 312 | +| iterations | 668 | +| time_elapsed | 2190 | +| total_timesteps | 684032 | +| train/ | | +| approx_kl | 2.0283422 | +| clip_fraction | 0.542 | +| clip_range | 0.2 | +| entropy_loss | -0.516 | +| explained_variance | -1.63 | +| learning_rate | 0.0001 | +| loss | -0.09 | +| n_updates | 67200 | +| policy_gradient_loss | -0.077 | +| value_loss | 0.000369 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | 0.194 | +| time/ | | +| fps | 312 | +| iterations | 669 | +| time_elapsed | 2194 | +| total_timesteps | 685056 | +| train/ | | +| approx_kl | 1.9725868 | +| clip_fraction | 0.504 | +| clip_range | 0.2 | +| entropy_loss | -0.475 | +| explained_variance | -4.98 | +| learning_rate | 0.0001 | +| loss | -0.0733 | +| n_updates | 67210 | +| policy_gradient_loss | -0.0756 | +| value_loss | 0.000309 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | 0.194 | +| time/ | | +| fps | 312 | +| iterations | 670 | +| time_elapsed | 2197 | +| total_timesteps | 686080 | +| train/ | | +| approx_kl | 2.5597386 | +| clip_fraction | 0.486 | +| clip_range | 0.2 | +| entropy_loss | -0.468 | +| explained_variance | -0.439 | +| learning_rate | 0.0001 | +| loss | -0.0975 | +| n_updates | 67220 | +| policy_gradient_loss | -0.0646 | +| value_loss | 0.000432 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.199 | +| time/ | | +| fps | 312 | +| iterations | 671 | +| time_elapsed | 2200 | +| total_timesteps | 687104 | +| train/ | | +| approx_kl | 2.2307584 | +| clip_fraction | 0.555 | +| clip_range | 0.2 | +| entropy_loss | -0.672 | +| explained_variance | -1.9 | +| learning_rate | 0.0001 | +| loss | -0.0707 | +| n_updates | 67230 | +| policy_gradient_loss | -0.0709 | +| value_loss | 0.000621 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | 0.201 | +| time/ | | +| fps | 312 | +| iterations | 672 | +| time_elapsed | 2204 | +| total_timesteps | 688128 | +| train/ | | +| approx_kl | 2.1741893 | +| clip_fraction | 0.531 | +| clip_range | 0.2 | +| entropy_loss | -0.548 | +| explained_variance | -0.432 | +| learning_rate | 0.0001 | +| loss | -0.0681 | +| n_updates | 67240 | +| policy_gradient_loss | -0.074 | +| value_loss | 0.000727 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.65e+03 | +| ep_rew_mean | 0.2 | +| time/ | | +| fps | 312 | +| iterations | 673 | +| time_elapsed | 2207 | +| total_timesteps | 689152 | +| train/ | | +| approx_kl | 1.9003589 | +| clip_fraction | 0.529 | +| clip_range | 0.2 | +| entropy_loss | -0.551 | +| explained_variance | -1.28 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 67250 | +| policy_gradient_loss | -0.0762 | +| value_loss | 0.000612 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.64e+03 | +| ep_rew_mean | 0.199 | +| time/ | | +| fps | 312 | +| iterations | 674 | +| time_elapsed | 2210 | +| total_timesteps | 690176 | +| train/ | | +| approx_kl | 2.0909529 | +| clip_fraction | 0.507 | +| clip_range | 0.2 | +| entropy_loss | -0.574 | +| explained_variance | -1.52 | +| learning_rate | 0.0001 | +| loss | -0.0787 | +| n_updates | 67260 | +| policy_gradient_loss | -0.0654 | +| value_loss | 0.000386 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.64e+03 | +| ep_rew_mean | 0.199 | +| time/ | | +| fps | 312 | +| iterations | 675 | +| time_elapsed | 2214 | +| total_timesteps | 691200 | +| train/ | | +| approx_kl | 1.8730031 | +| clip_fraction | 0.509 | +| clip_range | 0.2 | +| entropy_loss | -0.484 | +| explained_variance | -0.637 | +| learning_rate | 0.0001 | +| loss | -0.0982 | +| n_updates | 67270 | +| policy_gradient_loss | -0.0691 | +| value_loss | 0.000382 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.64e+03 | +| ep_rew_mean | 0.196 | +| time/ | | +| fps | 312 | +| iterations | 676 | +| time_elapsed | 2217 | +| total_timesteps | 692224 | +| train/ | | +| approx_kl | 1.9513317 | +| clip_fraction | 0.546 | +| clip_range | 0.2 | +| entropy_loss | -0.558 | +| explained_variance | -2.95 | +| learning_rate | 0.0001 | +| loss | -0.0895 | +| n_updates | 67280 | +| policy_gradient_loss | -0.0742 | +| value_loss | 0.000288 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.64e+03 | +| ep_rew_mean | 0.196 | +| time/ | | +| fps | 312 | +| iterations | 677 | +| time_elapsed | 2220 | +| total_timesteps | 693248 | +| train/ | | +| approx_kl | 2.475583 | +| clip_fraction | 0.532 | +| clip_range | 0.2 | +| entropy_loss | -0.5 | +| explained_variance | -2.49 | +| learning_rate | 0.0001 | +| loss | -0.131 | +| n_updates | 67290 | +| policy_gradient_loss | -0.0772 | +| value_loss | 0.000248 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.63e+03 | +| ep_rew_mean | 0.199 | +| time/ | | +| fps | 312 | +| iterations | 678 | +| time_elapsed | 2224 | +| total_timesteps | 694272 | +| train/ | | +| approx_kl | 1.5454397 | +| clip_fraction | 0.516 | +| clip_range | 0.2 | +| entropy_loss | -0.526 | +| explained_variance | -0.208 | +| learning_rate | 0.0001 | +| loss | -0.0946 | +| n_updates | 67300 | +| policy_gradient_loss | -0.0676 | +| value_loss | 0.000672 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.63e+03 | +| ep_rew_mean | 0.199 | +| time/ | | +| fps | 312 | +| iterations | 679 | +| time_elapsed | 2227 | +| total_timesteps | 695296 | +| train/ | | +| approx_kl | 2.4392347 | +| clip_fraction | 0.473 | +| clip_range | 0.2 | +| entropy_loss | -0.412 | +| explained_variance | -0.477 | +| learning_rate | 0.0001 | +| loss | -0.0706 | +| n_updates | 67310 | +| policy_gradient_loss | -0.067 | +| value_loss | 0.000592 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.63e+03 | +| ep_rew_mean | 0.199 | +| time/ | | +| fps | 312 | +| iterations | 680 | +| time_elapsed | 2230 | +| total_timesteps | 696320 | +| train/ | | +| approx_kl | 1.6654005 | +| clip_fraction | 0.516 | +| clip_range | 0.2 | +| entropy_loss | -0.486 | +| explained_variance | -3.43 | +| learning_rate | 0.0001 | +| loss | -0.11 | +| n_updates | 67320 | +| policy_gradient_loss | -0.0701 | +| value_loss | 0.000357 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.62e+03 | +| ep_rew_mean | 0.197 | +| time/ | | +| fps | 312 | +| iterations | 681 | +| time_elapsed | 2233 | +| total_timesteps | 697344 | +| train/ | | +| approx_kl | 1.4272373 | +| clip_fraction | 0.49 | +| clip_range | 0.2 | +| entropy_loss | -0.541 | +| explained_variance | -0.357 | +| learning_rate | 0.0001 | +| loss | -0.0863 | +| n_updates | 67330 | +| policy_gradient_loss | -0.0638 | +| value_loss | 0.000389 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.62e+03 | +| ep_rew_mean | 0.197 | +| time/ | | +| fps | 312 | +| iterations | 682 | +| time_elapsed | 2236 | +| total_timesteps | 698368 | +| train/ | | +| approx_kl | 1.8063394 | +| clip_fraction | 0.46 | +| clip_range | 0.2 | +| entropy_loss | -0.416 | +| explained_variance | -0.809 | +| learning_rate | 0.0001 | +| loss | -0.093 | +| n_updates | 67340 | +| policy_gradient_loss | -0.0659 | +| value_loss | 0.000297 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.62e+03 | +| ep_rew_mean | 0.197 | +| time/ | | +| fps | 312 | +| iterations | 683 | +| time_elapsed | 2240 | +| total_timesteps | 699392 | +| train/ | | +| approx_kl | 1.7653601 | +| clip_fraction | 0.478 | +| clip_range | 0.2 | +| entropy_loss | -0.43 | +| explained_variance | -4.88 | +| learning_rate | 0.0001 | +| loss | -0.105 | +| n_updates | 67350 | +| policy_gradient_loss | -0.0735 | +| value_loss | 0.000225 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.64e+03 | +| ep_rew_mean | 0.198 | +| time/ | | +| fps | 312 | +| iterations | 684 | +| time_elapsed | 2243 | +| total_timesteps | 700416 | +| train/ | | +| approx_kl | 2.0216417 | +| clip_fraction | 0.507 | +| clip_range | 0.2 | +| entropy_loss | -0.426 | +| explained_variance | -1.05 | +| learning_rate | 0.0001 | +| loss | -0.096 | +| n_updates | 67360 | +| policy_gradient_loss | -0.0673 | +| value_loss | 0.000282 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.64e+03 | +| ep_rew_mean | 0.198 | +| time/ | | +| fps | 312 | +| iterations | 685 | +| time_elapsed | 2246 | +| total_timesteps | 701440 | +| train/ | | +| approx_kl | 2.0996392 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.445 | +| explained_variance | -0.493 | +| learning_rate | 0.0001 | +| loss | -0.0965 | +| n_updates | 67370 | +| policy_gradient_loss | -0.0652 | +| value_loss | 0.000563 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.64e+03 | +| ep_rew_mean | 0.201 | +| time/ | | +| fps | 312 | +| iterations | 686 | +| time_elapsed | 2249 | +| total_timesteps | 702464 | +| train/ | | +| approx_kl | 1.73948 | +| clip_fraction | 0.489 | +| clip_range | 0.2 | +| entropy_loss | -0.432 | +| explained_variance | -2.07 | +| learning_rate | 0.0001 | +| loss | -0.0864 | +| n_updates | 67380 | +| policy_gradient_loss | -0.0737 | +| value_loss | 0.000359 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.63e+03 | +| ep_rew_mean | 0.202 | +| time/ | | +| fps | 312 | +| iterations | 687 | +| time_elapsed | 2252 | +| total_timesteps | 703488 | +| train/ | | +| approx_kl | 1.2590251 | +| clip_fraction | 0.461 | +| clip_range | 0.2 | +| entropy_loss | -0.469 | +| explained_variance | -0.549 | +| learning_rate | 0.0001 | +| loss | -0.0986 | +| n_updates | 67390 | +| policy_gradient_loss | -0.0678 | +| value_loss | 0.000492 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.63e+03 | +| ep_rew_mean | 0.207 | +| time/ | | +| fps | 312 | +| iterations | 688 | +| time_elapsed | 2256 | +| total_timesteps | 704512 | +| train/ | | +| approx_kl | 1.5568812 | +| clip_fraction | 0.519 | +| clip_range | 0.2 | +| entropy_loss | -0.487 | +| explained_variance | -0.467 | +| learning_rate | 0.0001 | +| loss | -0.108 | +| n_updates | 67400 | +| policy_gradient_loss | -0.0766 | +| value_loss | 0.000522 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.63e+03 | +| ep_rew_mean | 0.207 | +| time/ | | +| fps | 312 | +| iterations | 689 | +| time_elapsed | 2259 | +| total_timesteps | 705536 | +| train/ | | +| approx_kl | 1.4624002 | +| clip_fraction | 0.488 | +| clip_range | 0.2 | +| entropy_loss | -0.498 | +| explained_variance | -0.157 | +| learning_rate | 0.0001 | +| loss | -0.0912 | +| n_updates | 67410 | +| policy_gradient_loss | -0.0689 | +| value_loss | 0.000724 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.63e+03 | +| ep_rew_mean | 0.207 | +| time/ | | +| fps | 312 | +| iterations | 690 | +| time_elapsed | 2262 | +| total_timesteps | 706560 | +| train/ | | +| approx_kl | 1.4263855 | +| clip_fraction | 0.501 | +| clip_range | 0.2 | +| entropy_loss | -0.527 | +| explained_variance | -3.92 | +| learning_rate | 0.0001 | +| loss | -0.107 | +| n_updates | 67420 | +| policy_gradient_loss | -0.0764 | +| value_loss | 0.000353 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.64e+03 | +| ep_rew_mean | 0.21 | +| time/ | | +| fps | 312 | +| iterations | 691 | +| time_elapsed | 2266 | +| total_timesteps | 707584 | +| train/ | | +| approx_kl | 1.4621518 | +| clip_fraction | 0.528 | +| clip_range | 0.2 | +| entropy_loss | -0.587 | +| explained_variance | -1.68 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 67430 | +| policy_gradient_loss | -0.0699 | +| value_loss | 0.000258 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.64e+03 | +| ep_rew_mean | 0.21 | +| time/ | | +| fps | 312 | +| iterations | 692 | +| time_elapsed | 2269 | +| total_timesteps | 708608 | +| train/ | | +| approx_kl | 2.3373609 | +| clip_fraction | 0.499 | +| clip_range | 0.2 | +| entropy_loss | -0.407 | +| explained_variance | -1.41 | +| learning_rate | 0.0001 | +| loss | -0.0689 | +| n_updates | 67440 | +| policy_gradient_loss | -0.0692 | +| value_loss | 0.000485 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.64e+03 | +| ep_rew_mean | 0.21 | +| time/ | | +| fps | 312 | +| iterations | 693 | +| time_elapsed | 2273 | +| total_timesteps | 709632 | +| train/ | | +| approx_kl | 1.7806184 | +| clip_fraction | 0.476 | +| clip_range | 0.2 | +| entropy_loss | -0.422 | +| explained_variance | -0.934 | +| learning_rate | 0.0001 | +| loss | -0.0638 | +| n_updates | 67450 | +| policy_gradient_loss | -0.0604 | +| value_loss | 0.000331 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.64e+03 | +| ep_rew_mean | 0.21 | +| time/ | | +| fps | 312 | +| iterations | 694 | +| time_elapsed | 2276 | +| total_timesteps | 710656 | +| train/ | | +| approx_kl | 2.0279741 | +| clip_fraction | 0.517 | +| clip_range | 0.2 | +| entropy_loss | -0.483 | +| explained_variance | -2.18 | +| learning_rate | 0.0001 | +| loss | -0.0827 | +| n_updates | 67460 | +| policy_gradient_loss | -0.0721 | +| value_loss | 0.000281 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.65e+03 | +| ep_rew_mean | 0.208 | +| time/ | | +| fps | 312 | +| iterations | 695 | +| time_elapsed | 2280 | +| total_timesteps | 711680 | +| train/ | | +| approx_kl | 4.382779 | +| clip_fraction | 0.54 | +| clip_range | 0.2 | +| entropy_loss | -0.541 | +| explained_variance | -1.91 | +| learning_rate | 0.0001 | +| loss | -0.0869 | +| n_updates | 67470 | +| policy_gradient_loss | -0.0788 | +| value_loss | 0.000221 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.65e+03 | +| ep_rew_mean | 0.208 | +| time/ | | +| fps | 312 | +| iterations | 696 | +| time_elapsed | 2283 | +| total_timesteps | 712704 | +| train/ | | +| approx_kl | 1.7542601 | +| clip_fraction | 0.511 | +| clip_range | 0.2 | +| entropy_loss | -0.504 | +| explained_variance | -0.665 | +| learning_rate | 0.0001 | +| loss | -0.0737 | +| n_updates | 67480 | +| policy_gradient_loss | -0.0703 | +| value_loss | 0.000288 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.65e+03 | +| ep_rew_mean | 0.208 | +| time/ | | +| fps | 312 | +| iterations | 697 | +| time_elapsed | 2287 | +| total_timesteps | 713728 | +| train/ | | +| approx_kl | 1.5328178 | +| clip_fraction | 0.524 | +| clip_range | 0.2 | +| entropy_loss | -0.537 | +| explained_variance | -4.12 | +| learning_rate | 0.0001 | +| loss | -0.119 | +| n_updates | 67490 | +| policy_gradient_loss | -0.0697 | +| value_loss | 0.000328 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.64e+03 | +| ep_rew_mean | 0.209 | +| time/ | | +| fps | 312 | +| iterations | 698 | +| time_elapsed | 2290 | +| total_timesteps | 714752 | +| train/ | | +| approx_kl | 2.0103662 | +| clip_fraction | 0.523 | +| clip_range | 0.2 | +| entropy_loss | -0.503 | +| explained_variance | -0.555 | +| learning_rate | 0.0001 | +| loss | -0.109 | +| n_updates | 67500 | +| policy_gradient_loss | -0.0623 | +| value_loss | 0.000428 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.64e+03 | +| ep_rew_mean | 0.209 | +| time/ | | +| fps | 312 | +| iterations | 699 | +| time_elapsed | 2293 | +| total_timesteps | 715776 | +| train/ | | +| approx_kl | 1.7858102 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.456 | +| explained_variance | -0.913 | +| learning_rate | 0.0001 | +| loss | -0.0883 | +| n_updates | 67510 | +| policy_gradient_loss | -0.0698 | +| value_loss | 0.000568 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.65e+03 | +| ep_rew_mean | 0.207 | +| time/ | | +| fps | 312 | +| iterations | 700 | +| time_elapsed | 2297 | +| total_timesteps | 716800 | +| train/ | | +| approx_kl | 1.5550928 | +| clip_fraction | 0.531 | +| clip_range | 0.2 | +| entropy_loss | -0.575 | +| explained_variance | -0.863 | +| learning_rate | 0.0001 | +| loss | -0.108 | +| n_updates | 67520 | +| policy_gradient_loss | -0.0814 | +| value_loss | 0.000393 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | 0.213 | +| time/ | | +| fps | 312 | +| iterations | 701 | +| time_elapsed | 2300 | +| total_timesteps | 717824 | +| train/ | | +| approx_kl | 2.1942828 | +| clip_fraction | 0.513 | +| clip_range | 0.2 | +| entropy_loss | -0.504 | +| explained_variance | -0.993 | +| learning_rate | 0.0001 | +| loss | -0.108 | +| n_updates | 67530 | +| policy_gradient_loss | -0.075 | +| value_loss | 0.000317 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | 0.213 | +| time/ | | +| fps | 312 | +| iterations | 702 | +| time_elapsed | 2303 | +| total_timesteps | 718848 | +| train/ | | +| approx_kl | 5.6331935 | +| clip_fraction | 0.484 | +| clip_range | 0.2 | +| entropy_loss | -0.446 | +| explained_variance | -0.768 | +| learning_rate | 0.0001 | +| loss | -0.105 | +| n_updates | 67540 | +| policy_gradient_loss | -0.0651 | +| value_loss | 0.000542 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | 0.212 | +| time/ | | +| fps | 312 | +| iterations | 703 | +| time_elapsed | 2306 | +| total_timesteps | 719872 | +| train/ | | +| approx_kl | 2.3482018 | +| clip_fraction | 0.545 | +| clip_range | 0.2 | +| entropy_loss | -0.493 | +| explained_variance | -1.23 | +| learning_rate | 0.0001 | +| loss | -0.105 | +| n_updates | 67550 | +| policy_gradient_loss | -0.0772 | +| value_loss | 0.000328 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | 0.217 | +| time/ | | +| fps | 312 | +| iterations | 704 | +| time_elapsed | 2309 | +| total_timesteps | 720896 | +| train/ | | +| approx_kl | 1.879949 | +| clip_fraction | 0.529 | +| clip_range | 0.2 | +| entropy_loss | -0.498 | +| explained_variance | -0.818 | +| learning_rate | 0.0001 | +| loss | -0.0912 | +| n_updates | 67560 | +| policy_gradient_loss | -0.0729 | +| value_loss | 0.00033 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | 0.217 | +| time/ | | +| fps | 312 | +| iterations | 705 | +| time_elapsed | 2313 | +| total_timesteps | 721920 | +| train/ | | +| approx_kl | 3.171409 | +| clip_fraction | 0.508 | +| clip_range | 0.2 | +| entropy_loss | -0.517 | +| explained_variance | -0.526 | +| learning_rate | 0.0001 | +| loss | -0.0585 | +| n_updates | 67570 | +| policy_gradient_loss | -0.0671 | +| value_loss | 0.000332 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.218 | +| time/ | | +| fps | 312 | +| iterations | 706 | +| time_elapsed | 2316 | +| total_timesteps | 722944 | +| train/ | | +| approx_kl | 1.82726 | +| clip_fraction | 0.488 | +| clip_range | 0.2 | +| entropy_loss | -0.485 | +| explained_variance | -1.44 | +| learning_rate | 0.0001 | +| loss | -0.09 | +| n_updates | 67580 | +| policy_gradient_loss | -0.0682 | +| value_loss | 0.000579 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.213 | +| time/ | | +| fps | 312 | +| iterations | 707 | +| time_elapsed | 2319 | +| total_timesteps | 723968 | +| train/ | | +| approx_kl | 2.0790558 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.4 | +| explained_variance | -6.02 | +| learning_rate | 0.0001 | +| loss | -0.0797 | +| n_updates | 67590 | +| policy_gradient_loss | -0.0675 | +| value_loss | 0.000327 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.213 | +| time/ | | +| fps | 312 | +| iterations | 708 | +| time_elapsed | 2322 | +| total_timesteps | 724992 | +| train/ | | +| approx_kl | 1.787321 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.435 | +| explained_variance | -0.472 | +| learning_rate | 0.0001 | +| loss | -0.0866 | +| n_updates | 67600 | +| policy_gradient_loss | -0.0649 | +| value_loss | 0.000601 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.213 | +| time/ | | +| fps | 312 | +| iterations | 709 | +| time_elapsed | 2326 | +| total_timesteps | 726016 | +| train/ | | +| approx_kl | 3.2147326 | +| clip_fraction | 0.489 | +| clip_range | 0.2 | +| entropy_loss | -0.452 | +| explained_variance | -5.08 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 67610 | +| policy_gradient_loss | -0.0724 | +| value_loss | 0.000255 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.21 | +| time/ | | +| fps | 312 | +| iterations | 710 | +| time_elapsed | 2329 | +| total_timesteps | 727040 | +| train/ | | +| approx_kl | 2.1441138 | +| clip_fraction | 0.506 | +| clip_range | 0.2 | +| entropy_loss | -0.489 | +| explained_variance | -1.8 | +| learning_rate | 0.0001 | +| loss | -0.0802 | +| n_updates | 67620 | +| policy_gradient_loss | -0.0618 | +| value_loss | 8.08e-05 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.21 | +| time/ | | +| fps | 312 | +| iterations | 711 | +| time_elapsed | 2332 | +| total_timesteps | 728064 | +| train/ | | +| approx_kl | 2.1130705 | +| clip_fraction | 0.478 | +| clip_range | 0.2 | +| entropy_loss | -0.419 | +| explained_variance | -0.637 | +| learning_rate | 0.0001 | +| loss | -0.0913 | +| n_updates | 67630 | +| policy_gradient_loss | -0.0641 | +| value_loss | 0.000255 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.212 | +| time/ | | +| fps | 312 | +| iterations | 712 | +| time_elapsed | 2336 | +| total_timesteps | 729088 | +| train/ | | +| approx_kl | 1.786689 | +| clip_fraction | 0.532 | +| clip_range | 0.2 | +| entropy_loss | -0.585 | +| explained_variance | -0.934 | +| learning_rate | 0.0001 | +| loss | -0.11 | +| n_updates | 67640 | +| policy_gradient_loss | -0.067 | +| value_loss | 0.000554 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.212 | +| time/ | | +| fps | 312 | +| iterations | 713 | +| time_elapsed | 2339 | +| total_timesteps | 730112 | +| train/ | | +| approx_kl | 1.6989682 | +| clip_fraction | 0.512 | +| clip_range | 0.2 | +| entropy_loss | -0.528 | +| explained_variance | -1.4 | +| learning_rate | 0.0001 | +| loss | -0.0782 | +| n_updates | 67650 | +| policy_gradient_loss | -0.0725 | +| value_loss | 0.000559 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.215 | +| time/ | | +| fps | 312 | +| iterations | 714 | +| time_elapsed | 2342 | +| total_timesteps | 731136 | +| train/ | | +| approx_kl | 1.8104885 | +| clip_fraction | 0.527 | +| clip_range | 0.2 | +| entropy_loss | -0.505 | +| explained_variance | -1.2 | +| learning_rate | 0.0001 | +| loss | -0.11 | +| n_updates | 67660 | +| policy_gradient_loss | -0.0709 | +| value_loss | 0.000561 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.215 | +| time/ | | +| fps | 312 | +| iterations | 715 | +| time_elapsed | 2345 | +| total_timesteps | 732160 | +| train/ | | +| approx_kl | 1.8669388 | +| clip_fraction | 0.495 | +| clip_range | 0.2 | +| entropy_loss | -0.46 | +| explained_variance | -0.77 | +| learning_rate | 0.0001 | +| loss | -0.0748 | +| n_updates | 67670 | +| policy_gradient_loss | -0.0733 | +| value_loss | 0.000543 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.216 | +| time/ | | +| fps | 312 | +| iterations | 716 | +| time_elapsed | 2349 | +| total_timesteps | 733184 | +| train/ | | +| approx_kl | 1.4857273 | +| clip_fraction | 0.49 | +| clip_range | 0.2 | +| entropy_loss | -0.441 | +| explained_variance | -5.05 | +| learning_rate | 0.0001 | +| loss | -0.0886 | +| n_updates | 67680 | +| policy_gradient_loss | -0.0717 | +| value_loss | 0.000232 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.216 | +| time/ | | +| fps | 312 | +| iterations | 717 | +| time_elapsed | 2352 | +| total_timesteps | 734208 | +| train/ | | +| approx_kl | 2.0167866 | +| clip_fraction | 0.516 | +| clip_range | 0.2 | +| entropy_loss | -0.494 | +| explained_variance | -0.394 | +| learning_rate | 0.0001 | +| loss | -0.107 | +| n_updates | 67690 | +| policy_gradient_loss | -0.0649 | +| value_loss | 0.000526 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.214 | +| time/ | | +| fps | 312 | +| iterations | 718 | +| time_elapsed | 2355 | +| total_timesteps | 735232 | +| train/ | | +| approx_kl | 1.6603607 | +| clip_fraction | 0.494 | +| clip_range | 0.2 | +| entropy_loss | -0.405 | +| explained_variance | -4.68 | +| learning_rate | 0.0001 | +| loss | -0.094 | +| n_updates | 67700 | +| policy_gradient_loss | -0.0682 | +| value_loss | 0.00024 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.217 | +| time/ | | +| fps | 312 | +| iterations | 719 | +| time_elapsed | 2358 | +| total_timesteps | 736256 | +| train/ | | +| approx_kl | 1.784738 | +| clip_fraction | 0.541 | +| clip_range | 0.2 | +| entropy_loss | -0.576 | +| explained_variance | -0.538 | +| learning_rate | 0.0001 | +| loss | -0.0917 | +| n_updates | 67710 | +| policy_gradient_loss | -0.0615 | +| value_loss | 0.000262 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.217 | +| time/ | | +| fps | 312 | +| iterations | 720 | +| time_elapsed | 2362 | +| total_timesteps | 737280 | +| train/ | | +| approx_kl | 2.0649962 | +| clip_fraction | 0.505 | +| clip_range | 0.2 | +| entropy_loss | -0.551 | +| explained_variance | -0.514 | +| learning_rate | 0.0001 | +| loss | -0.091 | +| n_updates | 67720 | +| policy_gradient_loss | -0.0679 | +| value_loss | 0.000393 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.218 | +| time/ | | +| fps | 312 | +| iterations | 721 | +| time_elapsed | 2365 | +| total_timesteps | 738304 | +| train/ | | +| approx_kl | 1.8053808 | +| clip_fraction | 0.507 | +| clip_range | 0.2 | +| entropy_loss | -0.507 | +| explained_variance | -2.08 | +| learning_rate | 0.0001 | +| loss | -0.0736 | +| n_updates | 67730 | +| policy_gradient_loss | -0.0652 | +| value_loss | 0.000261 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.221 | +| time/ | | +| fps | 312 | +| iterations | 722 | +| time_elapsed | 2368 | +| total_timesteps | 739328 | +| train/ | | +| approx_kl | 1.6635647 | +| clip_fraction | 0.476 | +| clip_range | 0.2 | +| entropy_loss | -0.44 | +| explained_variance | -0.628 | +| learning_rate | 0.0001 | +| loss | -0.0873 | +| n_updates | 67740 | +| policy_gradient_loss | -0.0656 | +| value_loss | 0.000258 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.221 | +| time/ | | +| fps | 312 | +| iterations | 723 | +| time_elapsed | 2371 | +| total_timesteps | 740352 | +| train/ | | +| approx_kl | 1.8990426 | +| clip_fraction | 0.493 | +| clip_range | 0.2 | +| entropy_loss | -0.427 | +| explained_variance | -0.271 | +| learning_rate | 0.0001 | +| loss | -0.0632 | +| n_updates | 67750 | +| policy_gradient_loss | -0.0594 | +| value_loss | 0.000262 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.219 | +| time/ | | +| fps | 312 | +| iterations | 724 | +| time_elapsed | 2375 | +| total_timesteps | 741376 | +| train/ | | +| approx_kl | 2.0930526 | +| clip_fraction | 0.489 | +| clip_range | 0.2 | +| entropy_loss | -0.432 | +| explained_variance | -0.987 | +| learning_rate | 0.0001 | +| loss | -0.0993 | +| n_updates | 67760 | +| policy_gradient_loss | -0.0707 | +| value_loss | 0.00047 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.219 | +| time/ | | +| fps | 312 | +| iterations | 725 | +| time_elapsed | 2378 | +| total_timesteps | 742400 | +| train/ | | +| approx_kl | 1.988797 | +| clip_fraction | 0.478 | +| clip_range | 0.2 | +| entropy_loss | -0.425 | +| explained_variance | -1.08 | +| learning_rate | 0.0001 | +| loss | -0.0795 | +| n_updates | 67770 | +| policy_gradient_loss | -0.0681 | +| value_loss | 0.00049 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.219 | +| time/ | | +| fps | 312 | +| iterations | 726 | +| time_elapsed | 2381 | +| total_timesteps | 743424 | +| train/ | | +| approx_kl | 1.7421231 | +| clip_fraction | 0.513 | +| clip_range | 0.2 | +| entropy_loss | -0.508 | +| explained_variance | -4.81 | +| learning_rate | 0.0001 | +| loss | -0.0839 | +| n_updates | 67780 | +| policy_gradient_loss | -0.0719 | +| value_loss | 0.00024 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.219 | +| time/ | | +| fps | 312 | +| iterations | 727 | +| time_elapsed | 2385 | +| total_timesteps | 744448 | +| train/ | | +| approx_kl | 13.334466 | +| clip_fraction | 0.512 | +| clip_range | 0.2 | +| entropy_loss | -0.523 | +| explained_variance | -2.95 | +| learning_rate | 0.0001 | +| loss | -0.117 | +| n_updates | 67790 | +| policy_gradient_loss | -0.0746 | +| value_loss | 0.000119 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.219 | +| time/ | | +| fps | 312 | +| iterations | 728 | +| time_elapsed | 2388 | +| total_timesteps | 745472 | +| train/ | | +| approx_kl | 2.6715012 | +| clip_fraction | 0.498 | +| clip_range | 0.2 | +| entropy_loss | -0.452 | +| explained_variance | -0.319 | +| learning_rate | 0.0001 | +| loss | -0.0789 | +| n_updates | 67800 | +| policy_gradient_loss | -0.0581 | +| value_loss | 0.000333 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.221 | +| time/ | | +| fps | 312 | +| iterations | 729 | +| time_elapsed | 2392 | +| total_timesteps | 746496 | +| train/ | | +| approx_kl | 1.4563463 | +| clip_fraction | 0.53 | +| clip_range | 0.2 | +| entropy_loss | -0.594 | +| explained_variance | -1.67 | +| learning_rate | 0.0001 | +| loss | -0.0943 | +| n_updates | 67810 | +| policy_gradient_loss | -0.0735 | +| value_loss | 0.000214 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.221 | +| time/ | | +| fps | 312 | +| iterations | 730 | +| time_elapsed | 2395 | +| total_timesteps | 747520 | +| train/ | | +| approx_kl | 2.0648746 | +| clip_fraction | 0.492 | +| clip_range | 0.2 | +| entropy_loss | -0.404 | +| explained_variance | -1.79 | +| learning_rate | 0.0001 | +| loss | -0.0691 | +| n_updates | 67820 | +| policy_gradient_loss | -0.066 | +| value_loss | 0.000505 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.214 | +| time/ | | +| fps | 311 | +| iterations | 731 | +| time_elapsed | 2399 | +| total_timesteps | 748544 | +| train/ | | +| approx_kl | 2.08308 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.379 | +| explained_variance | -1.24 | +| learning_rate | 0.0001 | +| loss | -0.0968 | +| n_updates | 67830 | +| policy_gradient_loss | -0.0653 | +| value_loss | 0.000465 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.214 | +| time/ | | +| fps | 311 | +| iterations | 732 | +| time_elapsed | 2403 | +| total_timesteps | 749568 | +| train/ | | +| approx_kl | 1.9917753 | +| clip_fraction | 0.478 | +| clip_range | 0.2 | +| entropy_loss | -0.46 | +| explained_variance | -1 | +| learning_rate | 0.0001 | +| loss | -0.086 | +| n_updates | 67840 | +| policy_gradient_loss | -0.0585 | +| value_loss | 0.000322 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.212 | +| time/ | | +| fps | 311 | +| iterations | 733 | +| time_elapsed | 2406 | +| total_timesteps | 750592 | +| train/ | | +| approx_kl | 2.4651423 | +| clip_fraction | 0.508 | +| clip_range | 0.2 | +| entropy_loss | -0.442 | +| explained_variance | -2.67 | +| learning_rate | 0.0001 | +| loss | -0.111 | +| n_updates | 67850 | +| policy_gradient_loss | -0.0743 | +| value_loss | 0.000284 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.209 | +| time/ | | +| fps | 311 | +| iterations | 734 | +| time_elapsed | 2409 | +| total_timesteps | 751616 | +| train/ | | +| approx_kl | 1.8154052 | +| clip_fraction | 0.473 | +| clip_range | 0.2 | +| entropy_loss | -0.4 | +| explained_variance | -0.963 | +| learning_rate | 0.0001 | +| loss | -0.0805 | +| n_updates | 67860 | +| policy_gradient_loss | -0.0589 | +| value_loss | 0.000382 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.209 | +| time/ | | +| fps | 311 | +| iterations | 735 | +| time_elapsed | 2413 | +| total_timesteps | 752640 | +| train/ | | +| approx_kl | 1.5635322 | +| clip_fraction | 0.472 | +| clip_range | 0.2 | +| entropy_loss | -0.411 | +| explained_variance | -0.818 | +| learning_rate | 0.0001 | +| loss | -0.109 | +| n_updates | 67870 | +| policy_gradient_loss | -0.072 | +| value_loss | 0.000526 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.209 | +| time/ | | +| fps | 311 | +| iterations | 736 | +| time_elapsed | 2416 | +| total_timesteps | 753664 | +| train/ | | +| approx_kl | 2.4625168 | +| clip_fraction | 0.451 | +| clip_range | 0.2 | +| entropy_loss | -0.336 | +| explained_variance | -2.34 | +| learning_rate | 0.0001 | +| loss | -0.0863 | +| n_updates | 67880 | +| policy_gradient_loss | -0.0672 | +| value_loss | 0.000611 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.209 | +| time/ | | +| fps | 311 | +| iterations | 737 | +| time_elapsed | 2419 | +| total_timesteps | 754688 | +| train/ | | +| approx_kl | 2.4986925 | +| clip_fraction | 0.425 | +| clip_range | 0.2 | +| entropy_loss | -0.33 | +| explained_variance | -0.433 | +| learning_rate | 0.0001 | +| loss | -0.0909 | +| n_updates | 67890 | +| policy_gradient_loss | -0.0624 | +| value_loss | 0.000411 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.208 | +| time/ | | +| fps | 311 | +| iterations | 738 | +| time_elapsed | 2423 | +| total_timesteps | 755712 | +| train/ | | +| approx_kl | 1.5048184 | +| clip_fraction | 0.461 | +| clip_range | 0.2 | +| entropy_loss | -0.38 | +| explained_variance | -7.36 | +| learning_rate | 0.0001 | +| loss | -0.116 | +| n_updates | 67900 | +| policy_gradient_loss | -0.0663 | +| value_loss | 0.000196 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.208 | +| time/ | | +| fps | 311 | +| iterations | 739 | +| time_elapsed | 2426 | +| total_timesteps | 756736 | +| train/ | | +| approx_kl | 1.2930847 | +| clip_fraction | 0.445 | +| clip_range | 0.2 | +| entropy_loss | -0.369 | +| explained_variance | -0.66 | +| learning_rate | 0.0001 | +| loss | -0.0504 | +| n_updates | 67910 | +| policy_gradient_loss | -0.0566 | +| value_loss | 0.000175 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.206 | +| time/ | | +| fps | 311 | +| iterations | 740 | +| time_elapsed | 2429 | +| total_timesteps | 757760 | +| train/ | | +| approx_kl | 2.5914493 | +| clip_fraction | 0.466 | +| clip_range | 0.2 | +| entropy_loss | -0.43 | +| explained_variance | -0.627 | +| learning_rate | 0.0001 | +| loss | -0.058 | +| n_updates | 67920 | +| policy_gradient_loss | -0.058 | +| value_loss | 0.000234 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.207 | +| time/ | | +| fps | 311 | +| iterations | 741 | +| time_elapsed | 2433 | +| total_timesteps | 758784 | +| train/ | | +| approx_kl | 1.6680617 | +| clip_fraction | 0.443 | +| clip_range | 0.2 | +| entropy_loss | -0.395 | +| explained_variance | -0.19 | +| learning_rate | 0.0001 | +| loss | -0.0976 | +| n_updates | 67930 | +| policy_gradient_loss | -0.0575 | +| value_loss | 0.000472 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.207 | +| time/ | | +| fps | 311 | +| iterations | 742 | +| time_elapsed | 2436 | +| total_timesteps | 759808 | +| train/ | | +| approx_kl | 2.1342816 | +| clip_fraction | 0.497 | +| clip_range | 0.2 | +| entropy_loss | -0.468 | +| explained_variance | -0.174 | +| learning_rate | 0.0001 | +| loss | -0.0921 | +| n_updates | 67940 | +| policy_gradient_loss | -0.0655 | +| value_loss | 0.000813 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.207 | +| time/ | | +| fps | 311 | +| iterations | 743 | +| time_elapsed | 2439 | +| total_timesteps | 760832 | +| train/ | | +| approx_kl | 1.69033 | +| clip_fraction | 0.488 | +| clip_range | 0.2 | +| entropy_loss | -0.45 | +| explained_variance | -1.06 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 67950 | +| policy_gradient_loss | -0.0656 | +| value_loss | 0.00038 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.205 | +| time/ | | +| fps | 311 | +| iterations | 744 | +| time_elapsed | 2442 | +| total_timesteps | 761856 | +| train/ | | +| approx_kl | 5.538511 | +| clip_fraction | 0.453 | +| clip_range | 0.2 | +| entropy_loss | -0.373 | +| explained_variance | -4.33 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 67960 | +| policy_gradient_loss | -0.0683 | +| value_loss | 0.000263 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.205 | +| time/ | | +| fps | 311 | +| iterations | 745 | +| time_elapsed | 2446 | +| total_timesteps | 762880 | +| train/ | | +| approx_kl | 1.7914553 | +| clip_fraction | 0.45 | +| clip_range | 0.2 | +| entropy_loss | -0.367 | +| explained_variance | -1.29 | +| learning_rate | 0.0001 | +| loss | -0.0612 | +| n_updates | 67970 | +| policy_gradient_loss | -0.0602 | +| value_loss | 0.000291 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.206 | +| time/ | | +| fps | 311 | +| iterations | 746 | +| time_elapsed | 2449 | +| total_timesteps | 763904 | +| train/ | | +| approx_kl | 2.2156112 | +| clip_fraction | 0.516 | +| clip_range | 0.2 | +| entropy_loss | -0.429 | +| explained_variance | -0.978 | +| learning_rate | 0.0001 | +| loss | -0.0853 | +| n_updates | 67980 | +| policy_gradient_loss | -0.0676 | +| value_loss | 0.000499 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.204 | +| time/ | | +| fps | 311 | +| iterations | 747 | +| time_elapsed | 2453 | +| total_timesteps | 764928 | +| train/ | | +| approx_kl | 2.6977398 | +| clip_fraction | 0.433 | +| clip_range | 0.2 | +| entropy_loss | -0.342 | +| explained_variance | -0.585 | +| learning_rate | 0.0001 | +| loss | -0.0798 | +| n_updates | 67990 | +| policy_gradient_loss | -0.0631 | +| value_loss | 0.000563 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.204 | +| time/ | | +| fps | 311 | +| iterations | 748 | +| time_elapsed | 2456 | +| total_timesteps | 765952 | +| train/ | | +| approx_kl | 2.552396 | +| clip_fraction | 0.447 | +| clip_range | 0.2 | +| entropy_loss | -0.354 | +| explained_variance | -0.973 | +| learning_rate | 0.0001 | +| loss | -0.0866 | +| n_updates | 68000 | +| policy_gradient_loss | -0.0643 | +| value_loss | 0.000602 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.209 | +| time/ | | +| fps | 311 | +| iterations | 749 | +| time_elapsed | 2459 | +| total_timesteps | 766976 | +| train/ | | +| approx_kl | 1.6336087 | +| clip_fraction | 0.451 | +| clip_range | 0.2 | +| entropy_loss | -0.347 | +| explained_variance | -1.18 | +| learning_rate | 0.0001 | +| loss | -0.0884 | +| n_updates | 68010 | +| policy_gradient_loss | -0.0597 | +| value_loss | 0.000522 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.206 | +| time/ | | +| fps | 311 | +| iterations | 750 | +| time_elapsed | 2463 | +| total_timesteps | 768000 | +| train/ | | +| approx_kl | 1.7296765 | +| clip_fraction | 0.443 | +| clip_range | 0.2 | +| entropy_loss | -0.353 | +| explained_variance | -0.956 | +| learning_rate | 0.0001 | +| loss | -0.0899 | +| n_updates | 68020 | +| policy_gradient_loss | -0.0624 | +| value_loss | 0.000391 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.206 | +| time/ | | +| fps | 311 | +| iterations | 751 | +| time_elapsed | 2466 | +| total_timesteps | 769024 | +| train/ | | +| approx_kl | 1.9936831 | +| clip_fraction | 0.47 | +| clip_range | 0.2 | +| entropy_loss | -0.431 | +| explained_variance | -0.556 | +| learning_rate | 0.0001 | +| loss | -0.0826 | +| n_updates | 68030 | +| policy_gradient_loss | -0.0676 | +| value_loss | 0.000359 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.206 | +| time/ | | +| fps | 311 | +| iterations | 752 | +| time_elapsed | 2470 | +| total_timesteps | 770048 | +| train/ | | +| approx_kl | 1.8823355 | +| clip_fraction | 0.474 | +| clip_range | 0.2 | +| entropy_loss | -0.447 | +| explained_variance | -0.26 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 68040 | +| policy_gradient_loss | -0.0606 | +| value_loss | 0.000404 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.206 | +| time/ | | +| fps | 311 | +| iterations | 753 | +| time_elapsed | 2473 | +| total_timesteps | 771072 | +| train/ | | +| approx_kl | 1.7629178 | +| clip_fraction | 0.541 | +| clip_range | 0.2 | +| entropy_loss | -0.554 | +| explained_variance | -1.4 | +| learning_rate | 0.0001 | +| loss | -0.0755 | +| n_updates | 68050 | +| policy_gradient_loss | -0.0719 | +| value_loss | 0.000277 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.208 | +| time/ | | +| fps | 311 | +| iterations | 754 | +| time_elapsed | 2476 | +| total_timesteps | 772096 | +| train/ | | +| approx_kl | 1.7973454 | +| clip_fraction | 0.452 | +| clip_range | 0.2 | +| entropy_loss | -0.406 | +| explained_variance | -1.33 | +| learning_rate | 0.0001 | +| loss | -0.0815 | +| n_updates | 68060 | +| policy_gradient_loss | -0.0622 | +| value_loss | 0.000487 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.211 | +| time/ | | +| fps | 311 | +| iterations | 755 | +| time_elapsed | 2479 | +| total_timesteps | 773120 | +| train/ | | +| approx_kl | 1.8570759 | +| clip_fraction | 0.457 | +| clip_range | 0.2 | +| entropy_loss | -0.403 | +| explained_variance | -0.335 | +| learning_rate | 0.0001 | +| loss | -0.0672 | +| n_updates | 68070 | +| policy_gradient_loss | -0.0529 | +| value_loss | 0.000436 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.211 | +| time/ | | +| fps | 311 | +| iterations | 756 | +| time_elapsed | 2482 | +| total_timesteps | 774144 | +| train/ | | +| approx_kl | 2.6003318 | +| clip_fraction | 0.517 | +| clip_range | 0.2 | +| entropy_loss | -0.533 | +| explained_variance | -1.09 | +| learning_rate | 0.0001 | +| loss | -0.0747 | +| n_updates | 68080 | +| policy_gradient_loss | -0.0649 | +| value_loss | 0.000416 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.212 | +| time/ | | +| fps | 311 | +| iterations | 757 | +| time_elapsed | 2486 | +| total_timesteps | 775168 | +| train/ | | +| approx_kl | 1.8831747 | +| clip_fraction | 0.489 | +| clip_range | 0.2 | +| entropy_loss | -0.418 | +| explained_variance | -0.83 | +| learning_rate | 0.0001 | +| loss | -0.0787 | +| n_updates | 68090 | +| policy_gradient_loss | -0.0587 | +| value_loss | 0.000392 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.214 | +| time/ | | +| fps | 311 | +| iterations | 758 | +| time_elapsed | 2489 | +| total_timesteps | 776192 | +| train/ | | +| approx_kl | 3.1490135 | +| clip_fraction | 0.508 | +| clip_range | 0.2 | +| entropy_loss | -0.405 | +| explained_variance | -0.87 | +| learning_rate | 0.0001 | +| loss | -0.0987 | +| n_updates | 68100 | +| policy_gradient_loss | -0.0666 | +| value_loss | 0.000368 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.214 | +| time/ | | +| fps | 311 | +| iterations | 759 | +| time_elapsed | 2492 | +| total_timesteps | 777216 | +| train/ | | +| approx_kl | 2.2426775 | +| clip_fraction | 0.472 | +| clip_range | 0.2 | +| entropy_loss | -0.422 | +| explained_variance | -0.233 | +| learning_rate | 0.0001 | +| loss | -0.0871 | +| n_updates | 68110 | +| policy_gradient_loss | -0.0684 | +| value_loss | 0.000436 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.78e+03 | +| ep_rew_mean | 0.218 | +| time/ | | +| fps | 311 | +| iterations | 760 | +| time_elapsed | 2495 | +| total_timesteps | 778240 | +| train/ | | +| approx_kl | 1.9235339 | +| clip_fraction | 0.519 | +| clip_range | 0.2 | +| entropy_loss | -0.418 | +| explained_variance | -1.44 | +| learning_rate | 0.0001 | +| loss | -0.0919 | +| n_updates | 68120 | +| policy_gradient_loss | -0.0756 | +| value_loss | 0.000346 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.78e+03 | +| ep_rew_mean | 0.218 | +| time/ | | +| fps | 311 | +| iterations | 761 | +| time_elapsed | 2499 | +| total_timesteps | 779264 | +| train/ | | +| approx_kl | 1.9546554 | +| clip_fraction | 0.499 | +| clip_range | 0.2 | +| entropy_loss | -0.395 | +| explained_variance | -1.34 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 68130 | +| policy_gradient_loss | -0.0764 | +| value_loss | 0.000268 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.78e+03 | +| ep_rew_mean | 0.214 | +| time/ | | +| fps | 311 | +| iterations | 762 | +| time_elapsed | 2502 | +| total_timesteps | 780288 | +| train/ | | +| approx_kl | 1.9610066 | +| clip_fraction | 0.501 | +| clip_range | 0.2 | +| entropy_loss | -0.418 | +| explained_variance | -3.28 | +| learning_rate | 0.0001 | +| loss | -0.107 | +| n_updates | 68140 | +| policy_gradient_loss | -0.0724 | +| value_loss | 0.000367 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.218 | +| time/ | | +| fps | 311 | +| iterations | 763 | +| time_elapsed | 2505 | +| total_timesteps | 781312 | +| train/ | | +| approx_kl | 2.8869917 | +| clip_fraction | 0.501 | +| clip_range | 0.2 | +| entropy_loss | -0.439 | +| explained_variance | -0.483 | +| learning_rate | 0.0001 | +| loss | -0.0908 | +| n_updates | 68150 | +| policy_gradient_loss | -0.0639 | +| value_loss | 0.000539 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.218 | +| time/ | | +| fps | 311 | +| iterations | 764 | +| time_elapsed | 2509 | +| total_timesteps | 782336 | +| train/ | | +| approx_kl | 1.9774301 | +| clip_fraction | 0.501 | +| clip_range | 0.2 | +| entropy_loss | -0.44 | +| explained_variance | -1.12 | +| learning_rate | 0.0001 | +| loss | -0.0947 | +| n_updates | 68160 | +| policy_gradient_loss | -0.0663 | +| value_loss | 0.000421 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.218 | +| time/ | | +| fps | 311 | +| iterations | 765 | +| time_elapsed | 2512 | +| total_timesteps | 783360 | +| train/ | | +| approx_kl | 1.8508384 | +| clip_fraction | 0.492 | +| clip_range | 0.2 | +| entropy_loss | -0.466 | +| explained_variance | -5.18 | +| learning_rate | 0.0001 | +| loss | -0.0613 | +| n_updates | 68170 | +| policy_gradient_loss | -0.0678 | +| value_loss | 0.000374 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.78e+03 | +| ep_rew_mean | 0.221 | +| time/ | | +| fps | 311 | +| iterations | 766 | +| time_elapsed | 2515 | +| total_timesteps | 784384 | +| train/ | | +| approx_kl | 2.1737707 | +| clip_fraction | 0.532 | +| clip_range | 0.2 | +| entropy_loss | -0.505 | +| explained_variance | -0.992 | +| learning_rate | 0.0001 | +| loss | -0.0839 | +| n_updates | 68180 | +| policy_gradient_loss | -0.0748 | +| value_loss | 0.00039 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.78e+03 | +| ep_rew_mean | 0.221 | +| time/ | | +| fps | 311 | +| iterations | 767 | +| time_elapsed | 2519 | +| total_timesteps | 785408 | +| train/ | | +| approx_kl | 1.5805126 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.507 | +| explained_variance | -1.04 | +| learning_rate | 0.0001 | +| loss | -0.0626 | +| n_updates | 68190 | +| policy_gradient_loss | -0.0625 | +| value_loss | 0.000511 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.8e+03 | +| ep_rew_mean | 0.223 | +| time/ | | +| fps | 311 | +| iterations | 768 | +| time_elapsed | 2522 | +| total_timesteps | 786432 | +| train/ | | +| approx_kl | 1.2672566 | +| clip_fraction | 0.515 | +| clip_range | 0.2 | +| entropy_loss | -0.53 | +| explained_variance | -3.94 | +| learning_rate | 0.0001 | +| loss | -0.105 | +| n_updates | 68200 | +| policy_gradient_loss | -0.0693 | +| value_loss | 0.000193 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.8e+03 | +| ep_rew_mean | 0.223 | +| time/ | | +| fps | 311 | +| iterations | 769 | +| time_elapsed | 2526 | +| total_timesteps | 787456 | +| train/ | | +| approx_kl | 1.872271 | +| clip_fraction | 0.484 | +| clip_range | 0.2 | +| entropy_loss | -0.496 | +| explained_variance | -0.666 | +| learning_rate | 0.0001 | +| loss | -0.0585 | +| n_updates | 68210 | +| policy_gradient_loss | -0.0533 | +| value_loss | 0.000305 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.8e+03 | +| ep_rew_mean | 0.227 | +| time/ | | +| fps | 311 | +| iterations | 770 | +| time_elapsed | 2529 | +| total_timesteps | 788480 | +| train/ | | +| approx_kl | 2.284326 | +| clip_fraction | 0.498 | +| clip_range | 0.2 | +| entropy_loss | -0.42 | +| explained_variance | -1.34 | +| learning_rate | 0.0001 | +| loss | -0.0964 | +| n_updates | 68220 | +| policy_gradient_loss | -0.075 | +| value_loss | 0.000488 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.8e+03 | +| ep_rew_mean | 0.227 | +| time/ | | +| fps | 311 | +| iterations | 771 | +| time_elapsed | 2533 | +| total_timesteps | 789504 | +| train/ | | +| approx_kl | 2.207707 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.518 | +| explained_variance | -0.52 | +| learning_rate | 0.0001 | +| loss | -0.0741 | +| n_updates | 68230 | +| policy_gradient_loss | -0.0639 | +| value_loss | 0.000781 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.81e+03 | +| ep_rew_mean | 0.231 | +| time/ | | +| fps | 311 | +| iterations | 772 | +| time_elapsed | 2536 | +| total_timesteps | 790528 | +| train/ | | +| approx_kl | 1.8801453 | +| clip_fraction | 0.496 | +| clip_range | 0.2 | +| entropy_loss | -0.462 | +| explained_variance | -0.209 | +| learning_rate | 0.0001 | +| loss | -0.089 | +| n_updates | 68240 | +| policy_gradient_loss | -0.0619 | +| value_loss | 0.000695 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.81e+03 | +| ep_rew_mean | 0.231 | +| time/ | | +| fps | 311 | +| iterations | 773 | +| time_elapsed | 2539 | +| total_timesteps | 791552 | +| train/ | | +| approx_kl | 2.005004 | +| clip_fraction | 0.474 | +| clip_range | 0.2 | +| entropy_loss | -0.397 | +| explained_variance | -1.3 | +| learning_rate | 0.0001 | +| loss | -0.0746 | +| n_updates | 68250 | +| policy_gradient_loss | -0.062 | +| value_loss | 0.000575 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.8e+03 | +| ep_rew_mean | 0.23 | +| time/ | | +| fps | 311 | +| iterations | 774 | +| time_elapsed | 2542 | +| total_timesteps | 792576 | +| train/ | | +| approx_kl | 1.9226894 | +| clip_fraction | 0.498 | +| clip_range | 0.2 | +| entropy_loss | -0.39 | +| explained_variance | -1.9 | +| learning_rate | 0.0001 | +| loss | -0.0963 | +| n_updates | 68260 | +| policy_gradient_loss | -0.0749 | +| value_loss | 0.000509 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.8e+03 | +| ep_rew_mean | 0.231 | +| time/ | | +| fps | 311 | +| iterations | 775 | +| time_elapsed | 2546 | +| total_timesteps | 793600 | +| train/ | | +| approx_kl | 1.6055398 | +| clip_fraction | 0.467 | +| clip_range | 0.2 | +| entropy_loss | -0.406 | +| explained_variance | -0.279 | +| learning_rate | 0.0001 | +| loss | -0.0874 | +| n_updates | 68270 | +| policy_gradient_loss | -0.0705 | +| value_loss | 0.000601 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.8e+03 | +| ep_rew_mean | 0.231 | +| time/ | | +| fps | 311 | +| iterations | 776 | +| time_elapsed | 2549 | +| total_timesteps | 794624 | +| train/ | | +| approx_kl | 2.3811455 | +| clip_fraction | 0.461 | +| clip_range | 0.2 | +| entropy_loss | -0.411 | +| explained_variance | -2.8 | +| learning_rate | 0.0001 | +| loss | -0.0937 | +| n_updates | 68280 | +| policy_gradient_loss | -0.0655 | +| value_loss | 0.000568 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.23 | +| time/ | | +| fps | 311 | +| iterations | 777 | +| time_elapsed | 2552 | +| total_timesteps | 795648 | +| train/ | | +| approx_kl | 2.3275018 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.389 | +| explained_variance | -2.76 | +| learning_rate | 0.0001 | +| loss | -0.0947 | +| n_updates | 68290 | +| policy_gradient_loss | -0.0699 | +| value_loss | 0.00043 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.23 | +| time/ | | +| fps | 311 | +| iterations | 778 | +| time_elapsed | 2556 | +| total_timesteps | 796672 | +| train/ | | +| approx_kl | 1.6115932 | +| clip_fraction | 0.457 | +| clip_range | 0.2 | +| entropy_loss | -0.389 | +| explained_variance | -0.414 | +| learning_rate | 0.0001 | +| loss | -0.0765 | +| n_updates | 68300 | +| policy_gradient_loss | -0.0491 | +| value_loss | 0.000235 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.8e+03 | +| ep_rew_mean | 0.228 | +| time/ | | +| fps | 311 | +| iterations | 779 | +| time_elapsed | 2559 | +| total_timesteps | 797696 | +| train/ | | +| approx_kl | 1.7041531 | +| clip_fraction | 0.505 | +| clip_range | 0.2 | +| entropy_loss | -0.497 | +| explained_variance | -7.82 | +| learning_rate | 0.0001 | +| loss | -0.094 | +| n_updates | 68310 | +| policy_gradient_loss | -0.0702 | +| value_loss | 0.000107 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.8e+03 | +| ep_rew_mean | 0.228 | +| time/ | | +| fps | 311 | +| iterations | 780 | +| time_elapsed | 2562 | +| total_timesteps | 798720 | +| train/ | | +| approx_kl | 2.0575747 | +| clip_fraction | 0.46 | +| clip_range | 0.2 | +| entropy_loss | -0.399 | +| explained_variance | -1.96 | +| learning_rate | 0.0001 | +| loss | -0.119 | +| n_updates | 68320 | +| policy_gradient_loss | -0.0723 | +| value_loss | 0.000244 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.8e+03 | +| ep_rew_mean | 0.23 | +| time/ | | +| fps | 311 | +| iterations | 781 | +| time_elapsed | 2566 | +| total_timesteps | 799744 | +| train/ | | +| approx_kl | 1.4415885 | +| clip_fraction | 0.502 | +| clip_range | 0.2 | +| entropy_loss | -0.468 | +| explained_variance | -0.453 | +| learning_rate | 0.0001 | +| loss | -0.0974 | +| n_updates | 68330 | +| policy_gradient_loss | -0.0671 | +| value_loss | 0.000337 | +--------------------------------------- + +Current state: Champion.Level3.RyuVsChunLi +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.8e+03 | +| ep_rew_mean | 0.23 | +| time/ | | +| fps | 311 | +| iterations | 782 | +| time_elapsed | 2569 | +| total_timesteps | 800768 | +| train/ | | +| approx_kl | 2.0084736 | +| clip_fraction | 0.485 | +| clip_range | 0.2 | +| entropy_loss | -0.448 | +| explained_variance | -2.03 | +| learning_rate | 0.0001 | +| loss | -0.0807 | +| n_updates | 68340 | +| policy_gradient_loss | -0.0682 | +| value_loss | 0.000431 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.81e+03 | +| ep_rew_mean | 0.222 | +| time/ | | +| fps | 311 | +| iterations | 783 | +| time_elapsed | 2572 | +| total_timesteps | 801792 | +| train/ | | +| approx_kl | 2.1031592 | +| clip_fraction | 0.484 | +| clip_range | 0.2 | +| entropy_loss | -0.412 | +| explained_variance | -1.77 | +| learning_rate | 0.0001 | +| loss | -0.0873 | +| n_updates | 68350 | +| policy_gradient_loss | -0.0684 | +| value_loss | 0.000393 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.81e+03 | +| ep_rew_mean | 0.222 | +| time/ | | +| fps | 311 | +| iterations | 784 | +| time_elapsed | 2576 | +| total_timesteps | 802816 | +| train/ | | +| approx_kl | 2.4043484 | +| clip_fraction | 0.492 | +| clip_range | 0.2 | +| entropy_loss | -0.384 | +| explained_variance | -1.72 | +| learning_rate | 0.0001 | +| loss | -0.0922 | +| n_updates | 68360 | +| policy_gradient_loss | -0.0679 | +| value_loss | 0.000455 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.81e+03 | +| ep_rew_mean | 0.226 | +| time/ | | +| fps | 311 | +| iterations | 785 | +| time_elapsed | 2579 | +| total_timesteps | 803840 | +| train/ | | +| approx_kl | 3.3490074 | +| clip_fraction | 0.459 | +| clip_range | 0.2 | +| entropy_loss | -0.311 | +| explained_variance | -2.54 | +| learning_rate | 0.0001 | +| loss | -0.0885 | +| n_updates | 68370 | +| policy_gradient_loss | -0.0698 | +| value_loss | 0.000982 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.8e+03 | +| ep_rew_mean | 0.228 | +| time/ | | +| fps | 311 | +| iterations | 786 | +| time_elapsed | 2582 | +| total_timesteps | 804864 | +| train/ | | +| approx_kl | 2.56311 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.347 | +| explained_variance | -1.81 | +| learning_rate | 0.0001 | +| loss | -0.117 | +| n_updates | 68380 | +| policy_gradient_loss | -0.0706 | +| value_loss | 0.00079 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.8e+03 | +| ep_rew_mean | 0.228 | +| time/ | | +| fps | 311 | +| iterations | 787 | +| time_elapsed | 2586 | +| total_timesteps | 805888 | +| train/ | | +| approx_kl | 2.3094854 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.342 | +| explained_variance | -1.48 | +| learning_rate | 0.0001 | +| loss | -0.0923 | +| n_updates | 68390 | +| policy_gradient_loss | -0.0725 | +| value_loss | 0.000658 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.8e+03 | +| ep_rew_mean | 0.231 | +| time/ | | +| fps | 311 | +| iterations | 788 | +| time_elapsed | 2589 | +| total_timesteps | 806912 | +| train/ | | +| approx_kl | 2.6771274 | +| clip_fraction | 0.468 | +| clip_range | 0.2 | +| entropy_loss | -0.306 | +| explained_variance | -1.15 | +| learning_rate | 0.0001 | +| loss | -0.0702 | +| n_updates | 68400 | +| policy_gradient_loss | -0.0663 | +| value_loss | 0.000795 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.227 | +| time/ | | +| fps | 311 | +| iterations | 789 | +| time_elapsed | 2592 | +| total_timesteps | 807936 | +| train/ | | +| approx_kl | 2.4780617 | +| clip_fraction | 0.436 | +| clip_range | 0.2 | +| entropy_loss | -0.295 | +| explained_variance | -1.66 | +| learning_rate | 0.0001 | +| loss | -0.0913 | +| n_updates | 68410 | +| policy_gradient_loss | -0.067 | +| value_loss | 0.000703 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.227 | +| time/ | | +| fps | 311 | +| iterations | 790 | +| time_elapsed | 2595 | +| total_timesteps | 808960 | +| train/ | | +| approx_kl | 4.1709647 | +| clip_fraction | 0.489 | +| clip_range | 0.2 | +| entropy_loss | -0.383 | +| explained_variance | -1.97 | +| learning_rate | 0.0001 | +| loss | -0.0929 | +| n_updates | 68420 | +| policy_gradient_loss | -0.0587 | +| value_loss | 0.000473 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.223 | +| time/ | | +| fps | 311 | +| iterations | 791 | +| time_elapsed | 2599 | +| total_timesteps | 809984 | +| train/ | | +| approx_kl | 3.2612767 | +| clip_fraction | 0.462 | +| clip_range | 0.2 | +| entropy_loss | -0.321 | +| explained_variance | -3.27 | +| learning_rate | 0.0001 | +| loss | -0.0883 | +| n_updates | 68430 | +| policy_gradient_loss | -0.0656 | +| value_loss | 0.000524 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.227 | +| time/ | | +| fps | 311 | +| iterations | 792 | +| time_elapsed | 2602 | +| total_timesteps | 811008 | +| train/ | | +| approx_kl | 3.2188587 | +| clip_fraction | 0.498 | +| clip_range | 0.2 | +| entropy_loss | -0.375 | +| explained_variance | -0.992 | +| learning_rate | 0.0001 | +| loss | -0.0577 | +| n_updates | 68440 | +| policy_gradient_loss | -0.0652 | +| value_loss | 0.00055 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.227 | +| time/ | | +| fps | 311 | +| iterations | 793 | +| time_elapsed | 2605 | +| total_timesteps | 812032 | +| train/ | | +| approx_kl | 3.752379 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.313 | +| explained_variance | -0.914 | +| learning_rate | 0.0001 | +| loss | -0.0971 | +| n_updates | 68450 | +| policy_gradient_loss | -0.0666 | +| value_loss | 0.000574 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.78e+03 | +| ep_rew_mean | 0.228 | +| time/ | | +| fps | 311 | +| iterations | 794 | +| time_elapsed | 2609 | +| total_timesteps | 813056 | +| train/ | | +| approx_kl | 2.6579664 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.33 | +| explained_variance | -1.69 | +| learning_rate | 0.0001 | +| loss | -0.0872 | +| n_updates | 68460 | +| policy_gradient_loss | -0.068 | +| value_loss | 0.000544 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.78e+03 | +| ep_rew_mean | 0.228 | +| time/ | | +| fps | 311 | +| iterations | 795 | +| time_elapsed | 2612 | +| total_timesteps | 814080 | +| train/ | | +| approx_kl | 2.0520728 | +| clip_fraction | 0.44 | +| clip_range | 0.2 | +| entropy_loss | -0.316 | +| explained_variance | -1.06 | +| learning_rate | 0.0001 | +| loss | -0.0776 | +| n_updates | 68470 | +| policy_gradient_loss | -0.0636 | +| value_loss | 0.000631 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.78e+03 | +| ep_rew_mean | 0.228 | +| time/ | | +| fps | 311 | +| iterations | 796 | +| time_elapsed | 2615 | +| total_timesteps | 815104 | +| train/ | | +| approx_kl | 2.1829863 | +| clip_fraction | 0.451 | +| clip_range | 0.2 | +| entropy_loss | -0.311 | +| explained_variance | -1.74 | +| learning_rate | 0.0001 | +| loss | -0.0949 | +| n_updates | 68480 | +| policy_gradient_loss | -0.0631 | +| value_loss | 0.000776 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.78e+03 | +| ep_rew_mean | 0.228 | +| time/ | | +| fps | 311 | +| iterations | 797 | +| time_elapsed | 2618 | +| total_timesteps | 816128 | +| train/ | | +| approx_kl | 2.3681452 | +| clip_fraction | 0.446 | +| clip_range | 0.2 | +| entropy_loss | -0.281 | +| explained_variance | -3.06 | +| learning_rate | 0.0001 | +| loss | -0.0732 | +| n_updates | 68490 | +| policy_gradient_loss | -0.0636 | +| value_loss | 0.000421 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.229 | +| time/ | | +| fps | 311 | +| iterations | 798 | +| time_elapsed | 2622 | +| total_timesteps | 817152 | +| train/ | | +| approx_kl | 2.5186183 | +| clip_fraction | 0.477 | +| clip_range | 0.2 | +| entropy_loss | -0.434 | +| explained_variance | -0.926 | +| learning_rate | 0.0001 | +| loss | 0.144 | +| n_updates | 68500 | +| policy_gradient_loss | -0.0635 | +| value_loss | 0.000499 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.229 | +| time/ | | +| fps | 311 | +| iterations | 799 | +| time_elapsed | 2625 | +| total_timesteps | 818176 | +| train/ | | +| approx_kl | 2.5656185 | +| clip_fraction | 0.438 | +| clip_range | 0.2 | +| entropy_loss | -0.281 | +| explained_variance | -2.26 | +| learning_rate | 0.0001 | +| loss | -0.0974 | +| n_updates | 68510 | +| policy_gradient_loss | -0.0658 | +| value_loss | 0.00069 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.229 | +| time/ | | +| fps | 311 | +| iterations | 800 | +| time_elapsed | 2629 | +| total_timesteps | 819200 | +| train/ | | +| approx_kl | 2.3912425 | +| clip_fraction | 0.428 | +| clip_range | 0.2 | +| entropy_loss | -0.284 | +| explained_variance | -1.96 | +| learning_rate | 0.0001 | +| loss | -0.0866 | +| n_updates | 68520 | +| policy_gradient_loss | -0.0627 | +| value_loss | 0.000581 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.78e+03 | +| ep_rew_mean | 0.226 | +| time/ | | +| fps | 311 | +| iterations | 801 | +| time_elapsed | 2632 | +| total_timesteps | 820224 | +| train/ | | +| approx_kl | 2.765368 | +| clip_fraction | 0.441 | +| clip_range | 0.2 | +| entropy_loss | -0.299 | +| explained_variance | -3.03 | +| learning_rate | 0.0001 | +| loss | -0.0977 | +| n_updates | 68530 | +| policy_gradient_loss | -0.0684 | +| value_loss | 0.000532 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.78e+03 | +| ep_rew_mean | 0.226 | +| time/ | | +| fps | 311 | +| iterations | 802 | +| time_elapsed | 2636 | +| total_timesteps | 821248 | +| train/ | | +| approx_kl | 2.2312243 | +| clip_fraction | 0.453 | +| clip_range | 0.2 | +| entropy_loss | -0.324 | +| explained_variance | -1.14 | +| learning_rate | 0.0001 | +| loss | -0.0843 | +| n_updates | 68540 | +| policy_gradient_loss | -0.0665 | +| value_loss | 0.000663 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.78e+03 | +| ep_rew_mean | 0.226 | +| time/ | | +| fps | 311 | +| iterations | 803 | +| time_elapsed | 2639 | +| total_timesteps | 822272 | +| train/ | | +| approx_kl | 4.6659527 | +| clip_fraction | 0.463 | +| clip_range | 0.2 | +| entropy_loss | -0.327 | +| explained_variance | -2.25 | +| learning_rate | 0.0001 | +| loss | -0.0962 | +| n_updates | 68550 | +| policy_gradient_loss | -0.0675 | +| value_loss | 0.00059 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.228 | +| time/ | | +| fps | 311 | +| iterations | 804 | +| time_elapsed | 2642 | +| total_timesteps | 823296 | +| train/ | | +| approx_kl | 2.3712418 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.367 | +| explained_variance | -1.14 | +| learning_rate | 0.0001 | +| loss | -0.0691 | +| n_updates | 68560 | +| policy_gradient_loss | -0.0599 | +| value_loss | 0.000356 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.78e+03 | +| ep_rew_mean | 0.228 | +| time/ | | +| fps | 311 | +| iterations | 805 | +| time_elapsed | 2646 | +| total_timesteps | 824320 | +| train/ | | +| approx_kl | 3.0368402 | +| clip_fraction | 0.469 | +| clip_range | 0.2 | +| entropy_loss | -0.333 | +| explained_variance | -1.14 | +| learning_rate | 0.0001 | +| loss | -0.0704 | +| n_updates | 68570 | +| policy_gradient_loss | -0.0667 | +| value_loss | 0.000426 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.78e+03 | +| ep_rew_mean | 0.228 | +| time/ | | +| fps | 311 | +| iterations | 806 | +| time_elapsed | 2650 | +| total_timesteps | 825344 | +| train/ | | +| approx_kl | 2.4688773 | +| clip_fraction | 0.457 | +| clip_range | 0.2 | +| entropy_loss | -0.348 | +| explained_variance | -0.682 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 68580 | +| policy_gradient_loss | -0.066 | +| value_loss | 0.000455 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.78e+03 | +| ep_rew_mean | 0.231 | +| time/ | | +| fps | 311 | +| iterations | 807 | +| time_elapsed | 2653 | +| total_timesteps | 826368 | +| train/ | | +| approx_kl | 2.283585 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.311 | +| explained_variance | -3.47 | +| learning_rate | 0.0001 | +| loss | -0.0946 | +| n_updates | 68590 | +| policy_gradient_loss | -0.0705 | +| value_loss | 0.000513 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.78e+03 | +| ep_rew_mean | 0.231 | +| time/ | | +| fps | 311 | +| iterations | 808 | +| time_elapsed | 2656 | +| total_timesteps | 827392 | +| train/ | | +| approx_kl | 2.9925935 | +| clip_fraction | 0.459 | +| clip_range | 0.2 | +| entropy_loss | -0.315 | +| explained_variance | -1.22 | +| learning_rate | 0.0001 | +| loss | -0.0754 | +| n_updates | 68600 | +| policy_gradient_loss | -0.0647 | +| value_loss | 0.000549 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.235 | +| time/ | | +| fps | 311 | +| iterations | 809 | +| time_elapsed | 2659 | +| total_timesteps | 828416 | +| train/ | | +| approx_kl | 2.2782552 | +| clip_fraction | 0.443 | +| clip_range | 0.2 | +| entropy_loss | -0.295 | +| explained_variance | -5.23 | +| learning_rate | 0.0001 | +| loss | -0.0946 | +| n_updates | 68610 | +| policy_gradient_loss | -0.0673 | +| value_loss | 0.000607 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.235 | +| time/ | | +| fps | 311 | +| iterations | 810 | +| time_elapsed | 2663 | +| total_timesteps | 829440 | +| train/ | | +| approx_kl | 2.5175521 | +| clip_fraction | 0.457 | +| clip_range | 0.2 | +| entropy_loss | -0.333 | +| explained_variance | -1.01 | +| learning_rate | 0.0001 | +| loss | -0.0777 | +| n_updates | 68620 | +| policy_gradient_loss | -0.0593 | +| value_loss | 0.000639 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.238 | +| time/ | | +| fps | 311 | +| iterations | 811 | +| time_elapsed | 2666 | +| total_timesteps | 830464 | +| train/ | | +| approx_kl | 2.6754842 | +| clip_fraction | 0.46 | +| clip_range | 0.2 | +| entropy_loss | -0.275 | +| explained_variance | -2.82 | +| learning_rate | 0.0001 | +| loss | -0.0677 | +| n_updates | 68630 | +| policy_gradient_loss | -0.0654 | +| value_loss | 0.000612 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.238 | +| time/ | | +| fps | 311 | +| iterations | 812 | +| time_elapsed | 2669 | +| total_timesteps | 831488 | +| train/ | | +| approx_kl | 2.1509247 | +| clip_fraction | 0.443 | +| clip_range | 0.2 | +| entropy_loss | -0.288 | +| explained_variance | -4.25 | +| learning_rate | 0.0001 | +| loss | -0.0744 | +| n_updates | 68640 | +| policy_gradient_loss | -0.0649 | +| value_loss | 0.000482 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.239 | +| time/ | | +| fps | 311 | +| iterations | 813 | +| time_elapsed | 2672 | +| total_timesteps | 832512 | +| train/ | | +| approx_kl | 2.439484 | +| clip_fraction | 0.489 | +| clip_range | 0.2 | +| entropy_loss | -0.39 | +| explained_variance | -0.616 | +| learning_rate | 0.0001 | +| loss | -0.0735 | +| n_updates | 68650 | +| policy_gradient_loss | -0.064 | +| value_loss | 0.000299 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.236 | +| time/ | | +| fps | 311 | +| iterations | 814 | +| time_elapsed | 2676 | +| total_timesteps | 833536 | +| train/ | | +| approx_kl | 8.281949 | +| clip_fraction | 0.453 | +| clip_range | 0.2 | +| entropy_loss | -0.317 | +| explained_variance | -0.812 | +| learning_rate | 0.0001 | +| loss | -0.0745 | +| n_updates | 68660 | +| policy_gradient_loss | -0.0592 | +| value_loss | 0.000392 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.236 | +| time/ | | +| fps | 311 | +| iterations | 815 | +| time_elapsed | 2679 | +| total_timesteps | 834560 | +| train/ | | +| approx_kl | 2.3616767 | +| clip_fraction | 0.436 | +| clip_range | 0.2 | +| entropy_loss | -0.289 | +| explained_variance | -1.9 | +| learning_rate | 0.0001 | +| loss | -0.0768 | +| n_updates | 68670 | +| policy_gradient_loss | -0.0619 | +| value_loss | 0.000531 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.239 | +| time/ | | +| fps | 311 | +| iterations | 816 | +| time_elapsed | 2682 | +| total_timesteps | 835584 | +| train/ | | +| approx_kl | 2.6872473 | +| clip_fraction | 0.44 | +| clip_range | 0.2 | +| entropy_loss | -0.282 | +| explained_variance | -1.64 | +| learning_rate | 0.0001 | +| loss | -0.116 | +| n_updates | 68680 | +| policy_gradient_loss | -0.0638 | +| value_loss | 0.000419 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.239 | +| time/ | | +| fps | 311 | +| iterations | 817 | +| time_elapsed | 2686 | +| total_timesteps | 836608 | +| train/ | | +| approx_kl | 2.4006858 | +| clip_fraction | 0.452 | +| clip_range | 0.2 | +| entropy_loss | -0.285 | +| explained_variance | -0.801 | +| learning_rate | 0.0001 | +| loss | -0.0958 | +| n_updates | 68690 | +| policy_gradient_loss | -0.0661 | +| value_loss | 0.000536 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.239 | +| time/ | | +| fps | 311 | +| iterations | 818 | +| time_elapsed | 2689 | +| total_timesteps | 837632 | +| train/ | | +| approx_kl | 2.2574434 | +| clip_fraction | 0.458 | +| clip_range | 0.2 | +| entropy_loss | -0.324 | +| explained_variance | -1.2 | +| learning_rate | 0.0001 | +| loss | -0.0894 | +| n_updates | 68700 | +| policy_gradient_loss | -0.0676 | +| value_loss | 0.000544 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.234 | +| time/ | | +| fps | 311 | +| iterations | 819 | +| time_elapsed | 2693 | +| total_timesteps | 838656 | +| train/ | | +| approx_kl | 2.208754 | +| clip_fraction | 0.484 | +| clip_range | 0.2 | +| entropy_loss | -0.419 | +| explained_variance | -9.57 | +| learning_rate | 0.0001 | +| loss | -0.0991 | +| n_updates | 68710 | +| policy_gradient_loss | -0.0681 | +| value_loss | 0.000618 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.236 | +| time/ | | +| fps | 311 | +| iterations | 820 | +| time_elapsed | 2696 | +| total_timesteps | 839680 | +| train/ | | +| approx_kl | 2.2633882 | +| clip_fraction | 0.514 | +| clip_range | 0.2 | +| entropy_loss | -0.416 | +| explained_variance | -0.953 | +| learning_rate | 0.0001 | +| loss | -0.0683 | +| n_updates | 68720 | +| policy_gradient_loss | -0.0685 | +| value_loss | 0.000678 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.236 | +| time/ | | +| fps | 311 | +| iterations | 821 | +| time_elapsed | 2699 | +| total_timesteps | 840704 | +| train/ | | +| approx_kl | 2.083425 | +| clip_fraction | 0.455 | +| clip_range | 0.2 | +| entropy_loss | -0.33 | +| explained_variance | -3.12 | +| learning_rate | 0.0001 | +| loss | -0.0858 | +| n_updates | 68730 | +| policy_gradient_loss | -0.0708 | +| value_loss | 0.000599 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.239 | +| time/ | | +| fps | 311 | +| iterations | 822 | +| time_elapsed | 2703 | +| total_timesteps | 841728 | +| train/ | | +| approx_kl | 1.9719012 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.351 | +| explained_variance | -1.37 | +| learning_rate | 0.0001 | +| loss | -0.0888 | +| n_updates | 68740 | +| policy_gradient_loss | -0.0709 | +| value_loss | 0.000665 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.239 | +| time/ | | +| fps | 311 | +| iterations | 823 | +| time_elapsed | 2706 | +| total_timesteps | 842752 | +| train/ | | +| approx_kl | 2.8027246 | +| clip_fraction | 0.478 | +| clip_range | 0.2 | +| entropy_loss | -0.363 | +| explained_variance | -1.97 | +| learning_rate | 0.0001 | +| loss | -0.0589 | +| n_updates | 68750 | +| policy_gradient_loss | -0.071 | +| value_loss | 0.000573 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.239 | +| time/ | | +| fps | 311 | +| iterations | 824 | +| time_elapsed | 2709 | +| total_timesteps | 843776 | +| train/ | | +| approx_kl | 3.999599 | +| clip_fraction | 0.489 | +| clip_range | 0.2 | +| entropy_loss | -0.434 | +| explained_variance | -1.09 | +| learning_rate | 0.0001 | +| loss | -0.075 | +| n_updates | 68760 | +| policy_gradient_loss | -0.0681 | +| value_loss | 0.000448 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.8e+03 | +| ep_rew_mean | 0.24 | +| time/ | | +| fps | 311 | +| iterations | 825 | +| time_elapsed | 2713 | +| total_timesteps | 844800 | +| train/ | | +| approx_kl | 2.747841 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.379 | +| explained_variance | -5.21 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 68770 | +| policy_gradient_loss | -0.0724 | +| value_loss | 0.000307 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.8e+03 | +| ep_rew_mean | 0.24 | +| time/ | | +| fps | 311 | +| iterations | 826 | +| time_elapsed | 2716 | +| total_timesteps | 845824 | +| train/ | | +| approx_kl | 2.4644613 | +| clip_fraction | 0.477 | +| clip_range | 0.2 | +| entropy_loss | -0.343 | +| explained_variance | -1.05 | +| learning_rate | 0.0001 | +| loss | -0.095 | +| n_updates | 68780 | +| policy_gradient_loss | -0.0655 | +| value_loss | 0.00043 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.8e+03 | +| ep_rew_mean | 0.242 | +| time/ | | +| fps | 311 | +| iterations | 827 | +| time_elapsed | 2719 | +| total_timesteps | 846848 | +| train/ | | +| approx_kl | 2.4908586 | +| clip_fraction | 0.492 | +| clip_range | 0.2 | +| entropy_loss | -0.372 | +| explained_variance | -0.886 | +| learning_rate | 0.0001 | +| loss | -0.111 | +| n_updates | 68790 | +| policy_gradient_loss | -0.0691 | +| value_loss | 0.000364 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.8e+03 | +| ep_rew_mean | 0.242 | +| time/ | | +| fps | 311 | +| iterations | 828 | +| time_elapsed | 2723 | +| total_timesteps | 847872 | +| train/ | | +| approx_kl | 2.25873 | +| clip_fraction | 0.511 | +| clip_range | 0.2 | +| entropy_loss | -0.433 | +| explained_variance | -3.35 | +| learning_rate | 0.0001 | +| loss | -0.105 | +| n_updates | 68800 | +| policy_gradient_loss | -0.0766 | +| value_loss | 0.000277 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.247 | +| time/ | | +| fps | 311 | +| iterations | 829 | +| time_elapsed | 2726 | +| total_timesteps | 848896 | +| train/ | | +| approx_kl | 1.7001821 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.421 | +| explained_variance | -0.411 | +| learning_rate | 0.0001 | +| loss | -0.0908 | +| n_updates | 68810 | +| policy_gradient_loss | -0.06 | +| value_loss | 0.000378 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.247 | +| time/ | | +| fps | 311 | +| iterations | 830 | +| time_elapsed | 2729 | +| total_timesteps | 849920 | +| train/ | | +| approx_kl | 2.5296443 | +| clip_fraction | 0.493 | +| clip_range | 0.2 | +| entropy_loss | -0.36 | +| explained_variance | -0.836 | +| learning_rate | 0.0001 | +| loss | -0.0974 | +| n_updates | 68820 | +| policy_gradient_loss | -0.0683 | +| value_loss | 0.000529 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.247 | +| time/ | | +| fps | 311 | +| iterations | 831 | +| time_elapsed | 2732 | +| total_timesteps | 850944 | +| train/ | | +| approx_kl | 1.922072 | +| clip_fraction | 0.473 | +| clip_range | 0.2 | +| entropy_loss | -0.375 | +| explained_variance | -2.55 | +| learning_rate | 0.0001 | +| loss | -0.0974 | +| n_updates | 68830 | +| policy_gradient_loss | -0.0716 | +| value_loss | 0.000668 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.245 | +| time/ | | +| fps | 311 | +| iterations | 832 | +| time_elapsed | 2735 | +| total_timesteps | 851968 | +| train/ | | +| approx_kl | 2.2371674 | +| clip_fraction | 0.502 | +| clip_range | 0.2 | +| entropy_loss | -0.373 | +| explained_variance | -2.93 | +| learning_rate | 0.0001 | +| loss | -0.0651 | +| n_updates | 68840 | +| policy_gradient_loss | -0.0723 | +| value_loss | 0.000288 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.245 | +| time/ | | +| fps | 311 | +| iterations | 833 | +| time_elapsed | 2739 | +| total_timesteps | 852992 | +| train/ | | +| approx_kl | 3.2085168 | +| clip_fraction | 0.474 | +| clip_range | 0.2 | +| entropy_loss | -0.34 | +| explained_variance | -3.13 | +| learning_rate | 0.0001 | +| loss | -0.106 | +| n_updates | 68850 | +| policy_gradient_loss | -0.0744 | +| value_loss | 0.000262 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.246 | +| time/ | | +| fps | 311 | +| iterations | 834 | +| time_elapsed | 2742 | +| total_timesteps | 854016 | +| train/ | | +| approx_kl | 2.5547328 | +| clip_fraction | 0.472 | +| clip_range | 0.2 | +| entropy_loss | -0.353 | +| explained_variance | -0.964 | +| learning_rate | 0.0001 | +| loss | -0.0934 | +| n_updates | 68860 | +| policy_gradient_loss | -0.0711 | +| value_loss | 0.000281 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.246 | +| time/ | | +| fps | 311 | +| iterations | 835 | +| time_elapsed | 2746 | +| total_timesteps | 855040 | +| train/ | | +| approx_kl | 1.939417 | +| clip_fraction | 0.445 | +| clip_range | 0.2 | +| entropy_loss | -0.311 | +| explained_variance | -2.63 | +| learning_rate | 0.0001 | +| loss | -0.0844 | +| n_updates | 68870 | +| policy_gradient_loss | -0.0627 | +| value_loss | 0.000366 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.8e+03 | +| ep_rew_mean | 0.243 | +| time/ | | +| fps | 311 | +| iterations | 836 | +| time_elapsed | 2749 | +| total_timesteps | 856064 | +| train/ | | +| approx_kl | 2.9084673 | +| clip_fraction | 0.516 | +| clip_range | 0.2 | +| entropy_loss | -0.43 | +| explained_variance | -0.536 | +| learning_rate | 0.0001 | +| loss | -0.0939 | +| n_updates | 68880 | +| policy_gradient_loss | -0.0581 | +| value_loss | 0.000393 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.8e+03 | +| ep_rew_mean | 0.244 | +| time/ | | +| fps | 311 | +| iterations | 837 | +| time_elapsed | 2753 | +| total_timesteps | 857088 | +| train/ | | +| approx_kl | 2.177975 | +| clip_fraction | 0.501 | +| clip_range | 0.2 | +| entropy_loss | -0.411 | +| explained_variance | -2.04 | +| learning_rate | 0.0001 | +| loss | -0.0817 | +| n_updates | 68890 | +| policy_gradient_loss | -0.0757 | +| value_loss | 0.000396 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.8e+03 | +| ep_rew_mean | 0.244 | +| time/ | | +| fps | 311 | +| iterations | 838 | +| time_elapsed | 2756 | +| total_timesteps | 858112 | +| train/ | | +| approx_kl | 2.7374508 | +| clip_fraction | 0.474 | +| clip_range | 0.2 | +| entropy_loss | -0.386 | +| explained_variance | -2.67 | +| learning_rate | 0.0001 | +| loss | -0.0835 | +| n_updates | 68900 | +| policy_gradient_loss | -0.0689 | +| value_loss | 0.000421 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.8e+03 | +| ep_rew_mean | 0.244 | +| time/ | | +| fps | 311 | +| iterations | 839 | +| time_elapsed | 2760 | +| total_timesteps | 859136 | +| train/ | | +| approx_kl | 2.172096 | +| clip_fraction | 0.463 | +| clip_range | 0.2 | +| entropy_loss | -0.384 | +| explained_variance | -1.41 | +| learning_rate | 0.0001 | +| loss | -0.083 | +| n_updates | 68910 | +| policy_gradient_loss | -0.0658 | +| value_loss | 0.000532 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.81e+03 | +| ep_rew_mean | 0.249 | +| time/ | | +| fps | 311 | +| iterations | 840 | +| time_elapsed | 2763 | +| total_timesteps | 860160 | +| train/ | | +| approx_kl | 3.6543458 | +| clip_fraction | 0.51 | +| clip_range | 0.2 | +| entropy_loss | -0.436 | +| explained_variance | -1.34 | +| learning_rate | 0.0001 | +| loss | -0.0955 | +| n_updates | 68920 | +| policy_gradient_loss | -0.0751 | +| value_loss | 0.000468 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.8e+03 | +| ep_rew_mean | 0.249 | +| time/ | | +| fps | 311 | +| iterations | 841 | +| time_elapsed | 2767 | +| total_timesteps | 861184 | +| train/ | | +| approx_kl | 1.7430079 | +| clip_fraction | 0.433 | +| clip_range | 0.2 | +| entropy_loss | -0.355 | +| explained_variance | -3.22 | +| learning_rate | 0.0001 | +| loss | -0.0887 | +| n_updates | 68930 | +| policy_gradient_loss | -0.0609 | +| value_loss | 0.00113 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.8e+03 | +| ep_rew_mean | 0.249 | +| time/ | | +| fps | 311 | +| iterations | 842 | +| time_elapsed | 2770 | +| total_timesteps | 862208 | +| train/ | | +| approx_kl | 1.5629362 | +| clip_fraction | 0.495 | +| clip_range | 0.2 | +| entropy_loss | -0.43 | +| explained_variance | -2.49 | +| learning_rate | 0.0001 | +| loss | -0.0983 | +| n_updates | 68940 | +| policy_gradient_loss | -0.07 | +| value_loss | 0.000558 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.8e+03 | +| ep_rew_mean | 0.246 | +| time/ | | +| fps | 311 | +| iterations | 843 | +| time_elapsed | 2774 | +| total_timesteps | 863232 | +| train/ | | +| approx_kl | 2.1872778 | +| clip_fraction | 0.438 | +| clip_range | 0.2 | +| entropy_loss | -0.305 | +| explained_variance | -1.17 | +| learning_rate | 0.0001 | +| loss | -0.0882 | +| n_updates | 68950 | +| policy_gradient_loss | -0.0645 | +| value_loss | 0.00022 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.8e+03 | +| ep_rew_mean | 0.246 | +| time/ | | +| fps | 311 | +| iterations | 844 | +| time_elapsed | 2777 | +| total_timesteps | 864256 | +| train/ | | +| approx_kl | 2.0064096 | +| clip_fraction | 0.478 | +| clip_range | 0.2 | +| entropy_loss | -0.358 | +| explained_variance | -1.2 | +| learning_rate | 0.0001 | +| loss | -0.0951 | +| n_updates | 68960 | +| policy_gradient_loss | -0.0692 | +| value_loss | 0.00031 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.8e+03 | +| ep_rew_mean | 0.248 | +| time/ | | +| fps | 311 | +| iterations | 845 | +| time_elapsed | 2780 | +| total_timesteps | 865280 | +| train/ | | +| approx_kl | 3.130147 | +| clip_fraction | 0.446 | +| clip_range | 0.2 | +| entropy_loss | -0.321 | +| explained_variance | -1.98 | +| learning_rate | 0.0001 | +| loss | -0.111 | +| n_updates | 68970 | +| policy_gradient_loss | -0.0596 | +| value_loss | 0.000311 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.8e+03 | +| ep_rew_mean | 0.248 | +| time/ | | +| fps | 311 | +| iterations | 846 | +| time_elapsed | 2783 | +| total_timesteps | 866304 | +| train/ | | +| approx_kl | 3.1370678 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.374 | +| explained_variance | -1.05 | +| learning_rate | 0.0001 | +| loss | -0.0965 | +| n_updates | 68980 | +| policy_gradient_loss | -0.065 | +| value_loss | 0.000351 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.8e+03 | +| ep_rew_mean | 0.248 | +| time/ | | +| fps | 311 | +| iterations | 847 | +| time_elapsed | 2786 | +| total_timesteps | 867328 | +| train/ | | +| approx_kl | 2.4722066 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.382 | +| explained_variance | -2.55 | +| learning_rate | 0.0001 | +| loss | -0.0738 | +| n_updates | 68990 | +| policy_gradient_loss | -0.0647 | +| value_loss | 0.000323 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.81e+03 | +| ep_rew_mean | 0.245 | +| time/ | | +| fps | 311 | +| iterations | 848 | +| time_elapsed | 2790 | +| total_timesteps | 868352 | +| train/ | | +| approx_kl | 2.4634612 | +| clip_fraction | 0.484 | +| clip_range | 0.2 | +| entropy_loss | -0.356 | +| explained_variance | -1.81 | +| learning_rate | 0.0001 | +| loss | -0.106 | +| n_updates | 69000 | +| policy_gradient_loss | -0.0682 | +| value_loss | 0.000313 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.82e+03 | +| ep_rew_mean | 0.243 | +| time/ | | +| fps | 311 | +| iterations | 849 | +| time_elapsed | 2793 | +| total_timesteps | 869376 | +| train/ | | +| approx_kl | 2.1161382 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.385 | +| explained_variance | -1.29 | +| learning_rate | 0.0001 | +| loss | -0.0798 | +| n_updates | 69010 | +| policy_gradient_loss | -0.0685 | +| value_loss | 0.000395 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.82e+03 | +| ep_rew_mean | 0.243 | +| time/ | | +| fps | 311 | +| iterations | 850 | +| time_elapsed | 2796 | +| total_timesteps | 870400 | +| train/ | | +| approx_kl | 2.1101923 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.397 | +| explained_variance | -0.979 | +| learning_rate | 0.0001 | +| loss | -0.0774 | +| n_updates | 69020 | +| policy_gradient_loss | -0.0635 | +| value_loss | 0.00038 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.82e+03 | +| ep_rew_mean | 0.245 | +| time/ | | +| fps | 311 | +| iterations | 851 | +| time_elapsed | 2799 | +| total_timesteps | 871424 | +| train/ | | +| approx_kl | 1.6201913 | +| clip_fraction | 0.517 | +| clip_range | 0.2 | +| entropy_loss | -0.449 | +| explained_variance | -0.967 | +| learning_rate | 0.0001 | +| loss | -0.11 | +| n_updates | 69030 | +| policy_gradient_loss | -0.0701 | +| value_loss | 0.000591 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.82e+03 | +| ep_rew_mean | 0.245 | +| time/ | | +| fps | 311 | +| iterations | 852 | +| time_elapsed | 2803 | +| total_timesteps | 872448 | +| train/ | | +| approx_kl | 2.0742297 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.374 | +| explained_variance | -2.92 | +| learning_rate | 0.0001 | +| loss | -0.061 | +| n_updates | 69040 | +| policy_gradient_loss | -0.0704 | +| value_loss | 0.00047 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.246 | +| time/ | | +| fps | 311 | +| iterations | 853 | +| time_elapsed | 2806 | +| total_timesteps | 873472 | +| train/ | | +| approx_kl | 11.86647 | +| clip_fraction | 0.523 | +| clip_range | 0.2 | +| entropy_loss | -0.444 | +| explained_variance | -1.01 | +| learning_rate | 0.0001 | +| loss | -0.0562 | +| n_updates | 69050 | +| policy_gradient_loss | -0.069 | +| value_loss | 0.000413 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.246 | +| time/ | | +| fps | 311 | +| iterations | 854 | +| time_elapsed | 2810 | +| total_timesteps | 874496 | +| train/ | | +| approx_kl | 2.0317712 | +| clip_fraction | 0.507 | +| clip_range | 0.2 | +| entropy_loss | -0.404 | +| explained_variance | -3.11 | +| learning_rate | 0.0001 | +| loss | -0.0971 | +| n_updates | 69060 | +| policy_gradient_loss | -0.0766 | +| value_loss | 0.000315 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.25 | +| time/ | | +| fps | 311 | +| iterations | 855 | +| time_elapsed | 2813 | +| total_timesteps | 875520 | +| train/ | | +| approx_kl | 2.0100827 | +| clip_fraction | 0.492 | +| clip_range | 0.2 | +| entropy_loss | -0.38 | +| explained_variance | -0.386 | +| learning_rate | 0.0001 | +| loss | -0.086 | +| n_updates | 69070 | +| policy_gradient_loss | -0.0699 | +| value_loss | 0.000911 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.25 | +| time/ | | +| fps | 311 | +| iterations | 856 | +| time_elapsed | 2817 | +| total_timesteps | 876544 | +| train/ | | +| approx_kl | 1.6938491 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.377 | +| explained_variance | -1.36 | +| learning_rate | 0.0001 | +| loss | -0.1 | +| n_updates | 69080 | +| policy_gradient_loss | -0.0689 | +| value_loss | 0.000424 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.248 | +| time/ | | +| fps | 311 | +| iterations | 857 | +| time_elapsed | 2820 | +| total_timesteps | 877568 | +| train/ | | +| approx_kl | 2.3139887 | +| clip_fraction | 0.514 | +| clip_range | 0.2 | +| entropy_loss | -0.405 | +| explained_variance | -0.855 | +| learning_rate | 0.0001 | +| loss | -0.115 | +| n_updates | 69090 | +| policy_gradient_loss | -0.0702 | +| value_loss | 0.00051 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.253 | +| time/ | | +| fps | 311 | +| iterations | 858 | +| time_elapsed | 2823 | +| total_timesteps | 878592 | +| train/ | | +| approx_kl | 2.5143492 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.392 | +| explained_variance | -1.27 | +| learning_rate | 0.0001 | +| loss | -0.064 | +| n_updates | 69100 | +| policy_gradient_loss | -0.0704 | +| value_loss | 0.000526 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.251 | +| time/ | | +| fps | 311 | +| iterations | 859 | +| time_elapsed | 2827 | +| total_timesteps | 879616 | +| train/ | | +| approx_kl | 1.8590477 | +| clip_fraction | 0.492 | +| clip_range | 0.2 | +| entropy_loss | -0.43 | +| explained_variance | -0.607 | +| learning_rate | 0.0001 | +| loss | 0.0276 | +| n_updates | 69110 | +| policy_gradient_loss | -0.0702 | +| value_loss | 0.000728 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.251 | +| time/ | | +| fps | 311 | +| iterations | 860 | +| time_elapsed | 2830 | +| total_timesteps | 880640 | +| train/ | | +| approx_kl | 2.635927 | +| clip_fraction | 0.511 | +| clip_range | 0.2 | +| entropy_loss | -0.423 | +| explained_variance | -0.933 | +| learning_rate | 0.0001 | +| loss | -0.098 | +| n_updates | 69120 | +| policy_gradient_loss | -0.0729 | +| value_loss | 0.000555 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.82e+03 | +| ep_rew_mean | 0.248 | +| time/ | | +| fps | 311 | +| iterations | 861 | +| time_elapsed | 2833 | +| total_timesteps | 881664 | +| train/ | | +| approx_kl | 2.3899875 | +| clip_fraction | 0.473 | +| clip_range | 0.2 | +| entropy_loss | -0.353 | +| explained_variance | -2.74 | +| learning_rate | 0.0001 | +| loss | -0.0801 | +| n_updates | 69130 | +| policy_gradient_loss | -0.0693 | +| value_loss | 0.000431 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.82e+03 | +| ep_rew_mean | 0.248 | +| time/ | | +| fps | 311 | +| iterations | 862 | +| time_elapsed | 2836 | +| total_timesteps | 882688 | +| train/ | | +| approx_kl | 2.060249 | +| clip_fraction | 0.49 | +| clip_range | 0.2 | +| entropy_loss | -0.4 | +| explained_variance | -1.99 | +| learning_rate | 0.0001 | +| loss | -0.0854 | +| n_updates | 69140 | +| policy_gradient_loss | -0.075 | +| value_loss | 0.000374 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.82e+03 | +| ep_rew_mean | 0.248 | +| time/ | | +| fps | 311 | +| iterations | 863 | +| time_elapsed | 2840 | +| total_timesteps | 883712 | +| train/ | | +| approx_kl | 2.0867033 | +| clip_fraction | 0.51 | +| clip_range | 0.2 | +| entropy_loss | -0.404 | +| explained_variance | -0.623 | +| learning_rate | 0.0001 | +| loss | -0.0707 | +| n_updates | 69150 | +| policy_gradient_loss | -0.0703 | +| value_loss | 0.00081 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.82e+03 | +| ep_rew_mean | 0.248 | +| time/ | | +| fps | 311 | +| iterations | 864 | +| time_elapsed | 2843 | +| total_timesteps | 884736 | +| train/ | | +| approx_kl | 1.842118 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.459 | +| explained_variance | -2.93 | +| learning_rate | 0.0001 | +| loss | -0.0834 | +| n_updates | 69160 | +| policy_gradient_loss | -0.0729 | +| value_loss | 0.000321 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.82e+03 | +| ep_rew_mean | 0.247 | +| time/ | | +| fps | 311 | +| iterations | 865 | +| time_elapsed | 2846 | +| total_timesteps | 885760 | +| train/ | | +| approx_kl | 2.9723115 | +| clip_fraction | 0.542 | +| clip_range | 0.2 | +| entropy_loss | -0.447 | +| explained_variance | -0.485 | +| learning_rate | 0.0001 | +| loss | -0.0974 | +| n_updates | 69170 | +| policy_gradient_loss | -0.069 | +| value_loss | 0.000403 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.82e+03 | +| ep_rew_mean | 0.247 | +| time/ | | +| fps | 311 | +| iterations | 866 | +| time_elapsed | 2849 | +| total_timesteps | 886784 | +| train/ | | +| approx_kl | 2.0087137 | +| clip_fraction | 0.488 | +| clip_range | 0.2 | +| entropy_loss | -0.401 | +| explained_variance | -1.63 | +| learning_rate | 0.0001 | +| loss | -0.0898 | +| n_updates | 69180 | +| policy_gradient_loss | -0.0693 | +| value_loss | 0.000368 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.245 | +| time/ | | +| fps | 311 | +| iterations | 867 | +| time_elapsed | 2853 | +| total_timesteps | 887808 | +| train/ | | +| approx_kl | 1.98194 | +| clip_fraction | 0.528 | +| clip_range | 0.2 | +| entropy_loss | -0.446 | +| explained_variance | -1.01 | +| learning_rate | 0.0001 | +| loss | -0.081 | +| n_updates | 69190 | +| policy_gradient_loss | -0.0701 | +| value_loss | 0.000467 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.245 | +| time/ | | +| fps | 311 | +| iterations | 868 | +| time_elapsed | 2856 | +| total_timesteps | 888832 | +| train/ | | +| approx_kl | 2.034787 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.381 | +| explained_variance | -1.74 | +| learning_rate | 0.0001 | +| loss | -0.00163 | +| n_updates | 69200 | +| policy_gradient_loss | -0.0718 | +| value_loss | 0.000637 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.82e+03 | +| ep_rew_mean | 0.246 | +| time/ | | +| fps | 311 | +| iterations | 869 | +| time_elapsed | 2859 | +| total_timesteps | 889856 | +| train/ | | +| approx_kl | 1.9719733 | +| clip_fraction | 0.526 | +| clip_range | 0.2 | +| entropy_loss | -0.439 | +| explained_variance | -1.53 | +| learning_rate | 0.0001 | +| loss | -0.0766 | +| n_updates | 69210 | +| policy_gradient_loss | -0.0732 | +| value_loss | 0.000605 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.82e+03 | +| ep_rew_mean | 0.246 | +| time/ | | +| fps | 311 | +| iterations | 870 | +| time_elapsed | 2862 | +| total_timesteps | 890880 | +| train/ | | +| approx_kl | 2.233311 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.394 | +| explained_variance | -0.585 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 69220 | +| policy_gradient_loss | -0.069 | +| value_loss | 0.000539 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.246 | +| time/ | | +| fps | 311 | +| iterations | 871 | +| time_elapsed | 2866 | +| total_timesteps | 891904 | +| train/ | | +| approx_kl | 2.0706115 | +| clip_fraction | 0.522 | +| clip_range | 0.2 | +| entropy_loss | -0.466 | +| explained_variance | -5.27 | +| learning_rate | 0.0001 | +| loss | -0.112 | +| n_updates | 69230 | +| policy_gradient_loss | -0.0751 | +| value_loss | 0.00029 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.246 | +| time/ | | +| fps | 311 | +| iterations | 872 | +| time_elapsed | 2869 | +| total_timesteps | 892928 | +| train/ | | +| approx_kl | 2.3797712 | +| clip_fraction | 0.505 | +| clip_range | 0.2 | +| entropy_loss | -0.432 | +| explained_variance | -1.64 | +| learning_rate | 0.0001 | +| loss | -0.00805 | +| n_updates | 69240 | +| policy_gradient_loss | -0.0731 | +| value_loss | 0.000372 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.25 | +| time/ | | +| fps | 311 | +| iterations | 873 | +| time_elapsed | 2873 | +| total_timesteps | 893952 | +| train/ | | +| approx_kl | 1.9253933 | +| clip_fraction | 0.541 | +| clip_range | 0.2 | +| entropy_loss | -0.507 | +| explained_variance | -1.8 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 69250 | +| policy_gradient_loss | -0.0762 | +| value_loss | 0.0003 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.25 | +| time/ | | +| fps | 311 | +| iterations | 874 | +| time_elapsed | 2876 | +| total_timesteps | 894976 | +| train/ | | +| approx_kl | 2.6142886 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.392 | +| explained_variance | -1.12 | +| learning_rate | 0.0001 | +| loss | -0.108 | +| n_updates | 69260 | +| policy_gradient_loss | -0.0663 | +| value_loss | 0.000406 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.25 | +| time/ | | +| fps | 311 | +| iterations | 875 | +| time_elapsed | 2880 | +| total_timesteps | 896000 | +| train/ | | +| approx_kl | 2.168797 | +| clip_fraction | 0.499 | +| clip_range | 0.2 | +| entropy_loss | -0.408 | +| explained_variance | -1.21 | +| learning_rate | 0.0001 | +| loss | -0.105 | +| n_updates | 69270 | +| policy_gradient_loss | -0.0722 | +| value_loss | 0.000489 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.25 | +| time/ | | +| fps | 311 | +| iterations | 876 | +| time_elapsed | 2883 | +| total_timesteps | 897024 | +| train/ | | +| approx_kl | 1.9448166 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.368 | +| explained_variance | -2.47 | +| learning_rate | 0.0001 | +| loss | -0.0679 | +| n_updates | 69280 | +| policy_gradient_loss | -0.0654 | +| value_loss | 0.000423 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.246 | +| time/ | | +| fps | 311 | +| iterations | 877 | +| time_elapsed | 2887 | +| total_timesteps | 898048 | +| train/ | | +| approx_kl | 2.103795 | +| clip_fraction | 0.474 | +| clip_range | 0.2 | +| entropy_loss | -0.386 | +| explained_variance | -2.57 | +| learning_rate | 0.0001 | +| loss | -0.11 | +| n_updates | 69290 | +| policy_gradient_loss | -0.0697 | +| value_loss | 0.000452 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.246 | +| time/ | | +| fps | 311 | +| iterations | 878 | +| time_elapsed | 2890 | +| total_timesteps | 899072 | +| train/ | | +| approx_kl | 2.4245553 | +| clip_fraction | 0.467 | +| clip_range | 0.2 | +| entropy_loss | -0.353 | +| explained_variance | -1.67 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 69300 | +| policy_gradient_loss | -0.0707 | +| value_loss | 0.000542 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.246 | +| time/ | | +| fps | 311 | +| iterations | 879 | +| time_elapsed | 2893 | +| total_timesteps | 900096 | +| train/ | | +| approx_kl | 2.1351674 | +| clip_fraction | 0.489 | +| clip_range | 0.2 | +| entropy_loss | -0.399 | +| explained_variance | -2.41 | +| learning_rate | 0.0001 | +| loss | -0.0882 | +| n_updates | 69310 | +| policy_gradient_loss | -0.0703 | +| value_loss | 0.000504 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.246 | +| time/ | | +| fps | 311 | +| iterations | 880 | +| time_elapsed | 2896 | +| total_timesteps | 901120 | +| train/ | | +| approx_kl | 2.396597 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.391 | +| explained_variance | -2.89 | +| learning_rate | 0.0001 | +| loss | -0.0892 | +| n_updates | 69320 | +| policy_gradient_loss | -0.0701 | +| value_loss | 0.000403 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.249 | +| time/ | | +| fps | 311 | +| iterations | 881 | +| time_elapsed | 2900 | +| total_timesteps | 902144 | +| train/ | | +| approx_kl | 1.8884487 | +| clip_fraction | 0.535 | +| clip_range | 0.2 | +| entropy_loss | -0.509 | +| explained_variance | -2.75 | +| learning_rate | 0.0001 | +| loss | -0.0992 | +| n_updates | 69330 | +| policy_gradient_loss | -0.0737 | +| value_loss | 0.000269 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.249 | +| time/ | | +| fps | 311 | +| iterations | 882 | +| time_elapsed | 2903 | +| total_timesteps | 903168 | +| train/ | | +| approx_kl | 2.1443167 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.4 | +| explained_variance | -1.03 | +| learning_rate | 0.0001 | +| loss | -0.0935 | +| n_updates | 69340 | +| policy_gradient_loss | -0.072 | +| value_loss | 0.000508 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.249 | +| time/ | | +| fps | 311 | +| iterations | 883 | +| time_elapsed | 2906 | +| total_timesteps | 904192 | +| train/ | | +| approx_kl | 4.2462397 | +| clip_fraction | 0.492 | +| clip_range | 0.2 | +| entropy_loss | -0.358 | +| explained_variance | -3.71 | +| learning_rate | 0.0001 | +| loss | -0.108 | +| n_updates | 69350 | +| policy_gradient_loss | -0.0788 | +| value_loss | 0.000622 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.252 | +| time/ | | +| fps | 311 | +| iterations | 884 | +| time_elapsed | 2909 | +| total_timesteps | 905216 | +| train/ | | +| approx_kl | 1.7508041 | +| clip_fraction | 0.529 | +| clip_range | 0.2 | +| entropy_loss | -0.489 | +| explained_variance | -1.88 | +| learning_rate | 0.0001 | +| loss | -0.0486 | +| n_updates | 69360 | +| policy_gradient_loss | -0.0695 | +| value_loss | 0.000779 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.252 | +| time/ | | +| fps | 311 | +| iterations | 885 | +| time_elapsed | 2912 | +| total_timesteps | 906240 | +| train/ | | +| approx_kl | 1.7447829 | +| clip_fraction | 0.458 | +| clip_range | 0.2 | +| entropy_loss | -0.394 | +| explained_variance | -0.998 | +| learning_rate | 0.0001 | +| loss | -0.0374 | +| n_updates | 69370 | +| policy_gradient_loss | -0.0646 | +| value_loss | 0.000595 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.253 | +| time/ | | +| fps | 311 | +| iterations | 886 | +| time_elapsed | 2916 | +| total_timesteps | 907264 | +| train/ | | +| approx_kl | 2.236538 | +| clip_fraction | 0.484 | +| clip_range | 0.2 | +| entropy_loss | -0.392 | +| explained_variance | -1.75 | +| learning_rate | 0.0001 | +| loss | -0.0947 | +| n_updates | 69380 | +| policy_gradient_loss | -0.0765 | +| value_loss | 0.000609 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.255 | +| time/ | | +| fps | 311 | +| iterations | 887 | +| time_elapsed | 2919 | +| total_timesteps | 908288 | +| train/ | | +| approx_kl | 2.4594812 | +| clip_fraction | 0.505 | +| clip_range | 0.2 | +| entropy_loss | -0.407 | +| explained_variance | -1.42 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 69390 | +| policy_gradient_loss | -0.0756 | +| value_loss | 0.000431 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.255 | +| time/ | | +| fps | 311 | +| iterations | 888 | +| time_elapsed | 2922 | +| total_timesteps | 909312 | +| train/ | | +| approx_kl | 2.2528274 | +| clip_fraction | 0.466 | +| clip_range | 0.2 | +| entropy_loss | -0.38 | +| explained_variance | -1.36 | +| learning_rate | 0.0001 | +| loss | -0.0939 | +| n_updates | 69400 | +| policy_gradient_loss | -0.0699 | +| value_loss | 0.000673 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.255 | +| time/ | | +| fps | 311 | +| iterations | 889 | +| time_elapsed | 2926 | +| total_timesteps | 910336 | +| train/ | | +| approx_kl | 2.4343395 | +| clip_fraction | 0.494 | +| clip_range | 0.2 | +| entropy_loss | -0.392 | +| explained_variance | -1.09 | +| learning_rate | 0.0001 | +| loss | -0.0924 | +| n_updates | 69410 | +| policy_gradient_loss | -0.0746 | +| value_loss | 0.000705 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.262 | +| time/ | | +| fps | 311 | +| iterations | 890 | +| time_elapsed | 2929 | +| total_timesteps | 911360 | +| train/ | | +| approx_kl | 1.8610923 | +| clip_fraction | 0.491 | +| clip_range | 0.2 | +| entropy_loss | -0.444 | +| explained_variance | -2.9 | +| learning_rate | 0.0001 | +| loss | -0.0887 | +| n_updates | 69420 | +| policy_gradient_loss | -0.0781 | +| value_loss | 0.000482 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.261 | +| time/ | | +| fps | 311 | +| iterations | 891 | +| time_elapsed | 2933 | +| total_timesteps | 912384 | +| train/ | | +| approx_kl | 2.8936348 | +| clip_fraction | 0.484 | +| clip_range | 0.2 | +| entropy_loss | -0.375 | +| explained_variance | -1.76 | +| learning_rate | 0.0001 | +| loss | -0.0827 | +| n_updates | 69430 | +| policy_gradient_loss | -0.0679 | +| value_loss | 0.000357 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.261 | +| time/ | | +| fps | 311 | +| iterations | 892 | +| time_elapsed | 2936 | +| total_timesteps | 913408 | +| train/ | | +| approx_kl | 2.0652144 | +| clip_fraction | 0.436 | +| clip_range | 0.2 | +| entropy_loss | -0.326 | +| explained_variance | -3.4 | +| learning_rate | 0.0001 | +| loss | -0.0785 | +| n_updates | 69440 | +| policy_gradient_loss | -0.0667 | +| value_loss | 0.000357 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.259 | +| time/ | | +| fps | 311 | +| iterations | 893 | +| time_elapsed | 2940 | +| total_timesteps | 914432 | +| train/ | | +| approx_kl | 6.858472 | +| clip_fraction | 0.479 | +| clip_range | 0.2 | +| entropy_loss | -0.377 | +| explained_variance | -0.902 | +| learning_rate | 0.0001 | +| loss | -0.0745 | +| n_updates | 69450 | +| policy_gradient_loss | -0.0622 | +| value_loss | 0.000412 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.259 | +| time/ | | +| fps | 311 | +| iterations | 894 | +| time_elapsed | 2943 | +| total_timesteps | 915456 | +| train/ | | +| approx_kl | 2.066699 | +| clip_fraction | 0.477 | +| clip_range | 0.2 | +| entropy_loss | -0.351 | +| explained_variance | -2.12 | +| learning_rate | 0.0001 | +| loss | -0.0881 | +| n_updates | 69460 | +| policy_gradient_loss | -0.0674 | +| value_loss | 0.000395 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.259 | +| time/ | | +| fps | 310 | +| iterations | 895 | +| time_elapsed | 2947 | +| total_timesteps | 916480 | +| train/ | | +| approx_kl | 2.9815373 | +| clip_fraction | 0.494 | +| clip_range | 0.2 | +| entropy_loss | -0.376 | +| explained_variance | -1.11 | +| learning_rate | 0.0001 | +| loss | -0.0994 | +| n_updates | 69470 | +| policy_gradient_loss | -0.0687 | +| value_loss | 0.000491 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.255 | +| time/ | | +| fps | 310 | +| iterations | 896 | +| time_elapsed | 2950 | +| total_timesteps | 917504 | +| train/ | | +| approx_kl | 2.1274676 | +| clip_fraction | 0.495 | +| clip_range | 0.2 | +| entropy_loss | -0.436 | +| explained_variance | -4.03 | +| learning_rate | 0.0001 | +| loss | -0.0924 | +| n_updates | 69480 | +| policy_gradient_loss | -0.069 | +| value_loss | 0.000406 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.257 | +| time/ | | +| fps | 310 | +| iterations | 897 | +| time_elapsed | 2953 | +| total_timesteps | 918528 | +| train/ | | +| approx_kl | 2.514594 | +| clip_fraction | 0.501 | +| clip_range | 0.2 | +| entropy_loss | -0.44 | +| explained_variance | -0.987 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 69490 | +| policy_gradient_loss | -0.0593 | +| value_loss | 0.000329 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.257 | +| time/ | | +| fps | 310 | +| iterations | 898 | +| time_elapsed | 2956 | +| total_timesteps | 919552 | +| train/ | | +| approx_kl | 1.7616408 | +| clip_fraction | 0.495 | +| clip_range | 0.2 | +| entropy_loss | -0.414 | +| explained_variance | -0.652 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 69500 | +| policy_gradient_loss | -0.0702 | +| value_loss | 0.000529 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.259 | +| time/ | | +| fps | 311 | +| iterations | 899 | +| time_elapsed | 2960 | +| total_timesteps | 920576 | +| train/ | | +| approx_kl | 2.2512689 | +| clip_fraction | 0.511 | +| clip_range | 0.2 | +| entropy_loss | -0.424 | +| explained_variance | -2.06 | +| learning_rate | 0.0001 | +| loss | -0.0972 | +| n_updates | 69510 | +| policy_gradient_loss | -0.0763 | +| value_loss | 0.000819 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.259 | +| time/ | | +| fps | 311 | +| iterations | 900 | +| time_elapsed | 2963 | +| total_timesteps | 921600 | +| train/ | | +| approx_kl | 2.1281052 | +| clip_fraction | 0.476 | +| clip_range | 0.2 | +| entropy_loss | -0.401 | +| explained_variance | -2.25 | +| learning_rate | 0.0001 | +| loss | -0.0847 | +| n_updates | 69520 | +| policy_gradient_loss | -0.0712 | +| value_loss | 0.000509 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.259 | +| time/ | | +| fps | 311 | +| iterations | 901 | +| time_elapsed | 2966 | +| total_timesteps | 922624 | +| train/ | | +| approx_kl | 1.9886636 | +| clip_fraction | 0.501 | +| clip_range | 0.2 | +| entropy_loss | -0.388 | +| explained_variance | -1.05 | +| learning_rate | 0.0001 | +| loss | -0.0582 | +| n_updates | 69530 | +| policy_gradient_loss | -0.0693 | +| value_loss | 0.00047 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.259 | +| time/ | | +| fps | 311 | +| iterations | 902 | +| time_elapsed | 2969 | +| total_timesteps | 923648 | +| train/ | | +| approx_kl | 1.8621452 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.407 | +| explained_variance | -1.83 | +| learning_rate | 0.0001 | +| loss | -0.0872 | +| n_updates | 69540 | +| policy_gradient_loss | -0.0674 | +| value_loss | 0.000273 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.259 | +| time/ | | +| fps | 311 | +| iterations | 903 | +| time_elapsed | 2972 | +| total_timesteps | 924672 | +| train/ | | +| approx_kl | 2.1401973 | +| clip_fraction | 0.472 | +| clip_range | 0.2 | +| entropy_loss | -0.33 | +| explained_variance | -2 | +| learning_rate | 0.0001 | +| loss | -0.0964 | +| n_updates | 69550 | +| policy_gradient_loss | -0.068 | +| value_loss | 0.000429 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.261 | +| time/ | | +| fps | 311 | +| iterations | 904 | +| time_elapsed | 2976 | +| total_timesteps | 925696 | +| train/ | | +| approx_kl | 2.3586998 | +| clip_fraction | 0.513 | +| clip_range | 0.2 | +| entropy_loss | -0.442 | +| explained_variance | -1.44 | +| learning_rate | 0.0001 | +| loss | -0.123 | +| n_updates | 69560 | +| policy_gradient_loss | -0.0764 | +| value_loss | 0.000389 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.261 | +| time/ | | +| fps | 311 | +| iterations | 905 | +| time_elapsed | 2979 | +| total_timesteps | 926720 | +| train/ | | +| approx_kl | 2.691413 | +| clip_fraction | 0.499 | +| clip_range | 0.2 | +| entropy_loss | -0.406 | +| explained_variance | -1.19 | +| learning_rate | 0.0001 | +| loss | -0.0948 | +| n_updates | 69570 | +| policy_gradient_loss | -0.0731 | +| value_loss | 0.000402 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.264 | +| time/ | | +| fps | 311 | +| iterations | 906 | +| time_elapsed | 2982 | +| total_timesteps | 927744 | +| train/ | | +| approx_kl | 1.9003655 | +| clip_fraction | 0.493 | +| clip_range | 0.2 | +| entropy_loss | -0.403 | +| explained_variance | -1.81 | +| learning_rate | 0.0001 | +| loss | -0.0703 | +| n_updates | 69580 | +| policy_gradient_loss | -0.0726 | +| value_loss | 0.000517 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.264 | +| time/ | | +| fps | 311 | +| iterations | 907 | +| time_elapsed | 2986 | +| total_timesteps | 928768 | +| train/ | | +| approx_kl | 2.003161 | +| clip_fraction | 0.499 | +| clip_range | 0.2 | +| entropy_loss | -0.418 | +| explained_variance | -0.929 | +| learning_rate | 0.0001 | +| loss | -0.0872 | +| n_updates | 69590 | +| policy_gradient_loss | -0.0713 | +| value_loss | 0.000657 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.264 | +| time/ | | +| fps | 310 | +| iterations | 908 | +| time_elapsed | 2989 | +| total_timesteps | 929792 | +| train/ | | +| approx_kl | 1.4940124 | +| clip_fraction | 0.484 | +| clip_range | 0.2 | +| entropy_loss | -0.459 | +| explained_variance | -1.8 | +| learning_rate | 0.0001 | +| loss | -0.0742 | +| n_updates | 69600 | +| policy_gradient_loss | -0.07 | +| value_loss | 0.000289 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.266 | +| time/ | | +| fps | 310 | +| iterations | 909 | +| time_elapsed | 2993 | +| total_timesteps | 930816 | +| train/ | | +| approx_kl | 1.8579466 | +| clip_fraction | 0.513 | +| clip_range | 0.2 | +| entropy_loss | -0.457 | +| explained_variance | -0.224 | +| learning_rate | 0.0001 | +| loss | -0.0787 | +| n_updates | 69610 | +| policy_gradient_loss | -0.0664 | +| value_loss | 0.000621 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.263 | +| time/ | | +| fps | 310 | +| iterations | 910 | +| time_elapsed | 2996 | +| total_timesteps | 931840 | +| train/ | | +| approx_kl | 1.6813715 | +| clip_fraction | 0.493 | +| clip_range | 0.2 | +| entropy_loss | -0.432 | +| explained_variance | -3.91 | +| learning_rate | 0.0001 | +| loss | -0.0915 | +| n_updates | 69620 | +| policy_gradient_loss | -0.0651 | +| value_loss | 0.000353 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.263 | +| time/ | | +| fps | 310 | +| iterations | 911 | +| time_elapsed | 3000 | +| total_timesteps | 932864 | +| train/ | | +| approx_kl | 2.2723794 | +| clip_fraction | 0.5 | +| clip_range | 0.2 | +| entropy_loss | -0.394 | +| explained_variance | -1.13 | +| learning_rate | 0.0001 | +| loss | -0.0827 | +| n_updates | 69630 | +| policy_gradient_loss | -0.0731 | +| value_loss | 0.000319 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.263 | +| time/ | | +| fps | 310 | +| iterations | 912 | +| time_elapsed | 3003 | +| total_timesteps | 933888 | +| train/ | | +| approx_kl | 2.1006012 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.383 | +| explained_variance | -7.34 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 69640 | +| policy_gradient_loss | -0.0745 | +| value_loss | 0.000391 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.266 | +| time/ | | +| fps | 310 | +| iterations | 913 | +| time_elapsed | 3007 | +| total_timesteps | 934912 | +| train/ | | +| approx_kl | 1.9517088 | +| clip_fraction | 0.538 | +| clip_range | 0.2 | +| entropy_loss | -0.497 | +| explained_variance | -0.844 | +| learning_rate | 0.0001 | +| loss | -0.0903 | +| n_updates | 69650 | +| policy_gradient_loss | -0.07 | +| value_loss | 0.000632 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.266 | +| time/ | | +| fps | 310 | +| iterations | 914 | +| time_elapsed | 3010 | +| total_timesteps | 935936 | +| train/ | | +| approx_kl | 2.2732067 | +| clip_fraction | 0.494 | +| clip_range | 0.2 | +| entropy_loss | -0.378 | +| explained_variance | -5.32 | +| learning_rate | 0.0001 | +| loss | -0.109 | +| n_updates | 69660 | +| policy_gradient_loss | -0.0747 | +| value_loss | 0.000363 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.266 | +| time/ | | +| fps | 310 | +| iterations | 915 | +| time_elapsed | 3013 | +| total_timesteps | 936960 | +| train/ | | +| approx_kl | 1.7121136 | +| clip_fraction | 0.536 | +| clip_range | 0.2 | +| entropy_loss | -0.524 | +| explained_variance | -0.52 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 69670 | +| policy_gradient_loss | -0.0684 | +| value_loss | 0.000513 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.268 | +| time/ | | +| fps | 310 | +| iterations | 916 | +| time_elapsed | 3017 | +| total_timesteps | 937984 | +| train/ | | +| approx_kl | 3.0645983 | +| clip_fraction | 0.506 | +| clip_range | 0.2 | +| entropy_loss | -0.426 | +| explained_variance | -3.51 | +| learning_rate | 0.0001 | +| loss | -0.0771 | +| n_updates | 69680 | +| policy_gradient_loss | -0.0749 | +| value_loss | 0.000475 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.268 | +| time/ | | +| fps | 310 | +| iterations | 917 | +| time_elapsed | 3020 | +| total_timesteps | 939008 | +| train/ | | +| approx_kl | 2.1189432 | +| clip_fraction | 0.506 | +| clip_range | 0.2 | +| entropy_loss | -0.408 | +| explained_variance | -1.56 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 69690 | +| policy_gradient_loss | -0.0716 | +| value_loss | 0.000373 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.269 | +| time/ | | +| fps | 310 | +| iterations | 918 | +| time_elapsed | 3023 | +| total_timesteps | 940032 | +| train/ | | +| approx_kl | 2.9847665 | +| clip_fraction | 0.509 | +| clip_range | 0.2 | +| entropy_loss | -0.422 | +| explained_variance | -0.499 | +| learning_rate | 0.0001 | +| loss | -0.0879 | +| n_updates | 69700 | +| policy_gradient_loss | -0.0605 | +| value_loss | 0.000329 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.269 | +| time/ | | +| fps | 310 | +| iterations | 919 | +| time_elapsed | 3026 | +| total_timesteps | 941056 | +| train/ | | +| approx_kl | 1.714783 | +| clip_fraction | 0.478 | +| clip_range | 0.2 | +| entropy_loss | -0.406 | +| explained_variance | -2.29 | +| learning_rate | 0.0001 | +| loss | -0.0873 | +| n_updates | 69710 | +| policy_gradient_loss | -0.0667 | +| value_loss | 0.000324 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.269 | +| time/ | | +| fps | 310 | +| iterations | 920 | +| time_elapsed | 3029 | +| total_timesteps | 942080 | +| train/ | | +| approx_kl | 3.326964 | +| clip_fraction | 0.509 | +| clip_range | 0.2 | +| entropy_loss | -0.41 | +| explained_variance | -3.76 | +| learning_rate | 0.0001 | +| loss | -0.0694 | +| n_updates | 69720 | +| policy_gradient_loss | -0.0751 | +| value_loss | 0.000331 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.89e+03 | +| ep_rew_mean | 0.272 | +| time/ | | +| fps | 310 | +| iterations | 921 | +| time_elapsed | 3033 | +| total_timesteps | 943104 | +| train/ | | +| approx_kl | 10.140717 | +| clip_fraction | 0.495 | +| clip_range | 0.2 | +| entropy_loss | -0.419 | +| explained_variance | -1.34 | +| learning_rate | 0.0001 | +| loss | -0.089 | +| n_updates | 69730 | +| policy_gradient_loss | -0.0734 | +| value_loss | 0.000476 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.276 | +| time/ | | +| fps | 310 | +| iterations | 922 | +| time_elapsed | 3036 | +| total_timesteps | 944128 | +| train/ | | +| approx_kl | 2.2887554 | +| clip_fraction | 0.509 | +| clip_range | 0.2 | +| entropy_loss | -0.43 | +| explained_variance | -1.08 | +| learning_rate | 0.0001 | +| loss | -0.0905 | +| n_updates | 69740 | +| policy_gradient_loss | -0.0712 | +| value_loss | 0.000517 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.276 | +| time/ | | +| fps | 310 | +| iterations | 923 | +| time_elapsed | 3039 | +| total_timesteps | 945152 | +| train/ | | +| approx_kl | 2.1658757 | +| clip_fraction | 0.496 | +| clip_range | 0.2 | +| entropy_loss | -0.423 | +| explained_variance | -1.51 | +| learning_rate | 0.0001 | +| loss | -0.109 | +| n_updates | 69750 | +| policy_gradient_loss | -0.0689 | +| value_loss | 0.000388 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.276 | +| time/ | | +| fps | 310 | +| iterations | 924 | +| time_elapsed | 3042 | +| total_timesteps | 946176 | +| train/ | | +| approx_kl | 2.1721783 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.424 | +| explained_variance | -4.14 | +| learning_rate | 0.0001 | +| loss | -0.0742 | +| n_updates | 69760 | +| policy_gradient_loss | -0.0692 | +| value_loss | 0.000378 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.273 | +| time/ | | +| fps | 310 | +| iterations | 925 | +| time_elapsed | 3046 | +| total_timesteps | 947200 | +| train/ | | +| approx_kl | 2.0342822 | +| clip_fraction | 0.468 | +| clip_range | 0.2 | +| entropy_loss | -0.385 | +| explained_variance | -0.64 | +| learning_rate | 0.0001 | +| loss | -0.093 | +| n_updates | 69770 | +| policy_gradient_loss | -0.0651 | +| value_loss | 0.000496 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.273 | +| time/ | | +| fps | 310 | +| iterations | 926 | +| time_elapsed | 3049 | +| total_timesteps | 948224 | +| train/ | | +| approx_kl | 2.4492273 | +| clip_fraction | 0.512 | +| clip_range | 0.2 | +| entropy_loss | -0.456 | +| explained_variance | -2.34 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 69780 | +| policy_gradient_loss | -0.0732 | +| value_loss | 0.000495 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 310 | +| iterations | 927 | +| time_elapsed | 3053 | +| total_timesteps | 949248 | +| train/ | | +| approx_kl | 1.4408293 | +| clip_fraction | 0.494 | +| clip_range | 0.2 | +| entropy_loss | -0.473 | +| explained_variance | -1.38 | +| learning_rate | 0.0001 | +| loss | -0.0936 | +| n_updates | 69790 | +| policy_gradient_loss | -0.0729 | +| value_loss | 0.000641 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 310 | +| iterations | 928 | +| time_elapsed | 3056 | +| total_timesteps | 950272 | +| train/ | | +| approx_kl | 2.1561024 | +| clip_fraction | 0.486 | +| clip_range | 0.2 | +| entropy_loss | -0.381 | +| explained_variance | -1.37 | +| learning_rate | 0.0001 | +| loss | -0.0929 | +| n_updates | 69800 | +| policy_gradient_loss | -0.0723 | +| value_loss | 0.00045 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.277 | +| time/ | | +| fps | 310 | +| iterations | 929 | +| time_elapsed | 3060 | +| total_timesteps | 951296 | +| train/ | | +| approx_kl | 2.1248994 | +| clip_fraction | 0.514 | +| clip_range | 0.2 | +| entropy_loss | -0.434 | +| explained_variance | -0.957 | +| learning_rate | 0.0001 | +| loss | -0.094 | +| n_updates | 69810 | +| policy_gradient_loss | -0.0751 | +| value_loss | 0.000471 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.276 | +| time/ | | +| fps | 310 | +| iterations | 930 | +| time_elapsed | 3063 | +| total_timesteps | 952320 | +| train/ | | +| approx_kl | 2.2068374 | +| clip_fraction | 0.504 | +| clip_range | 0.2 | +| entropy_loss | -0.413 | +| explained_variance | -0.683 | +| learning_rate | 0.0001 | +| loss | -0.0848 | +| n_updates | 69820 | +| policy_gradient_loss | -0.0737 | +| value_loss | 0.000395 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.276 | +| time/ | | +| fps | 310 | +| iterations | 931 | +| time_elapsed | 3066 | +| total_timesteps | 953344 | +| train/ | | +| approx_kl | 2.397881 | +| clip_fraction | 0.484 | +| clip_range | 0.2 | +| entropy_loss | -0.402 | +| explained_variance | -1.72 | +| learning_rate | 0.0001 | +| loss | -0.109 | +| n_updates | 69830 | +| policy_gradient_loss | -0.0713 | +| value_loss | 0.000431 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.276 | +| time/ | | +| fps | 310 | +| iterations | 932 | +| time_elapsed | 3069 | +| total_timesteps | 954368 | +| train/ | | +| approx_kl | 2.048777 | +| clip_fraction | 0.473 | +| clip_range | 0.2 | +| entropy_loss | -0.4 | +| explained_variance | -1.38 | +| learning_rate | 0.0001 | +| loss | -0.0711 | +| n_updates | 69840 | +| policy_gradient_loss | -0.0702 | +| value_loss | 0.000412 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.276 | +| time/ | | +| fps | 310 | +| iterations | 933 | +| time_elapsed | 3073 | +| total_timesteps | 955392 | +| train/ | | +| approx_kl | 1.9087061 | +| clip_fraction | 0.468 | +| clip_range | 0.2 | +| entropy_loss | -0.364 | +| explained_variance | -1.81 | +| learning_rate | 0.0001 | +| loss | -0.0998 | +| n_updates | 69850 | +| policy_gradient_loss | -0.0703 | +| value_loss | 0.000469 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.277 | +| time/ | | +| fps | 310 | +| iterations | 934 | +| time_elapsed | 3076 | +| total_timesteps | 956416 | +| train/ | | +| approx_kl | 2.5082216 | +| clip_fraction | 0.489 | +| clip_range | 0.2 | +| entropy_loss | -0.376 | +| explained_variance | -0.798 | +| learning_rate | 0.0001 | +| loss | -0.0927 | +| n_updates | 69860 | +| policy_gradient_loss | -0.07 | +| value_loss | 0.000502 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.278 | +| time/ | | +| fps | 310 | +| iterations | 935 | +| time_elapsed | 3079 | +| total_timesteps | 957440 | +| train/ | | +| approx_kl | 2.3192885 | +| clip_fraction | 0.467 | +| clip_range | 0.2 | +| entropy_loss | -0.397 | +| explained_variance | -0.957 | +| learning_rate | 0.0001 | +| loss | -0.0858 | +| n_updates | 69870 | +| policy_gradient_loss | -0.0656 | +| value_loss | 0.000826 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.277 | +| time/ | | +| fps | 310 | +| iterations | 936 | +| time_elapsed | 3082 | +| total_timesteps | 958464 | +| train/ | | +| approx_kl | 2.0921814 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.354 | +| explained_variance | -4.98 | +| learning_rate | 0.0001 | +| loss | -0.0848 | +| n_updates | 69880 | +| policy_gradient_loss | -0.0747 | +| value_loss | 0.000505 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.276 | +| time/ | | +| fps | 310 | +| iterations | 937 | +| time_elapsed | 3085 | +| total_timesteps | 959488 | +| train/ | | +| approx_kl | 2.1260784 | +| clip_fraction | 0.51 | +| clip_range | 0.2 | +| entropy_loss | -0.408 | +| explained_variance | -0.757 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 69890 | +| policy_gradient_loss | -0.0706 | +| value_loss | 0.000426 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.276 | +| time/ | | +| fps | 310 | +| iterations | 938 | +| time_elapsed | 3088 | +| total_timesteps | 960512 | +| train/ | | +| approx_kl | 2.019035 | +| clip_fraction | 0.499 | +| clip_range | 0.2 | +| entropy_loss | -0.412 | +| explained_variance | -2.61 | +| learning_rate | 0.0001 | +| loss | -0.0684 | +| n_updates | 69900 | +| policy_gradient_loss | -0.0731 | +| value_loss | 0.000317 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.277 | +| time/ | | +| fps | 310 | +| iterations | 939 | +| time_elapsed | 3092 | +| total_timesteps | 961536 | +| train/ | | +| approx_kl | 2.0641532 | +| clip_fraction | 0.494 | +| clip_range | 0.2 | +| entropy_loss | -0.371 | +| explained_variance | -2.06 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 69910 | +| policy_gradient_loss | -0.0677 | +| value_loss | 0.000323 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.277 | +| time/ | | +| fps | 310 | +| iterations | 940 | +| time_elapsed | 3095 | +| total_timesteps | 962560 | +| train/ | | +| approx_kl | 7.1136637 | +| clip_fraction | 0.474 | +| clip_range | 0.2 | +| entropy_loss | -0.394 | +| explained_variance | -0.825 | +| learning_rate | 0.0001 | +| loss | -0.0838 | +| n_updates | 69920 | +| policy_gradient_loss | -0.0666 | +| value_loss | 0.000282 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.271 | +| time/ | | +| fps | 310 | +| iterations | 941 | +| time_elapsed | 3098 | +| total_timesteps | 963584 | +| train/ | | +| approx_kl | 2.0900326 | +| clip_fraction | 0.522 | +| clip_range | 0.2 | +| entropy_loss | -0.4 | +| explained_variance | -0.973 | +| learning_rate | 0.0001 | +| loss | -0.0791 | +| n_updates | 69930 | +| policy_gradient_loss | -0.0636 | +| value_loss | 0.000518 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.271 | +| time/ | | +| fps | 310 | +| iterations | 942 | +| time_elapsed | 3101 | +| total_timesteps | 964608 | +| train/ | | +| approx_kl | 2.0926666 | +| clip_fraction | 0.454 | +| clip_range | 0.2 | +| entropy_loss | -0.331 | +| explained_variance | -2.04 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 69940 | +| policy_gradient_loss | -0.0699 | +| value_loss | 0.000423 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.277 | +| time/ | | +| fps | 310 | +| iterations | 943 | +| time_elapsed | 3105 | +| total_timesteps | 965632 | +| train/ | | +| approx_kl | 2.3547466 | +| clip_fraction | 0.489 | +| clip_range | 0.2 | +| entropy_loss | -0.395 | +| explained_variance | -0.687 | +| learning_rate | 0.0001 | +| loss | -0.0676 | +| n_updates | 69950 | +| policy_gradient_loss | -0.0691 | +| value_loss | 0.000493 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.277 | +| time/ | | +| fps | 310 | +| iterations | 944 | +| time_elapsed | 3109 | +| total_timesteps | 966656 | +| train/ | | +| approx_kl | 2.071288 | +| clip_fraction | 0.479 | +| clip_range | 0.2 | +| entropy_loss | -0.419 | +| explained_variance | -1.32 | +| learning_rate | 0.0001 | +| loss | -0.0915 | +| n_updates | 69960 | +| policy_gradient_loss | -0.0671 | +| value_loss | 0.000283 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 310 | +| iterations | 945 | +| time_elapsed | 3112 | +| total_timesteps | 967680 | +| train/ | | +| approx_kl | 2.3370175 | +| clip_fraction | 0.485 | +| clip_range | 0.2 | +| entropy_loss | -0.402 | +| explained_variance | -1.12 | +| learning_rate | 0.0001 | +| loss | -0.106 | +| n_updates | 69970 | +| policy_gradient_loss | -0.0654 | +| value_loss | 0.000465 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 310 | +| iterations | 946 | +| time_elapsed | 3115 | +| total_timesteps | 968704 | +| train/ | | +| approx_kl | 2.3024545 | +| clip_fraction | 0.512 | +| clip_range | 0.2 | +| entropy_loss | -0.48 | +| explained_variance | -1.45 | +| learning_rate | 0.0001 | +| loss | -0.0704 | +| n_updates | 69980 | +| policy_gradient_loss | -0.07 | +| value_loss | 0.000419 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 310 | +| iterations | 947 | +| time_elapsed | 3119 | +| total_timesteps | 969728 | +| train/ | | +| approx_kl | 2.3417647 | +| clip_fraction | 0.484 | +| clip_range | 0.2 | +| entropy_loss | -0.422 | +| explained_variance | -2.17 | +| learning_rate | 0.0001 | +| loss | -0.0872 | +| n_updates | 69990 | +| policy_gradient_loss | -0.062 | +| value_loss | 0.000567 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 310 | +| iterations | 948 | +| time_elapsed | 3122 | +| total_timesteps | 970752 | +| train/ | | +| approx_kl | 2.149447 | +| clip_fraction | 0.495 | +| clip_range | 0.2 | +| entropy_loss | -0.41 | +| explained_variance | -3.47 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 70000 | +| policy_gradient_loss | -0.0702 | +| value_loss | 0.0004 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 310 | +| iterations | 949 | +| time_elapsed | 3126 | +| total_timesteps | 971776 | +| train/ | | +| approx_kl | 2.1684496 | +| clip_fraction | 0.496 | +| clip_range | 0.2 | +| entropy_loss | -0.377 | +| explained_variance | -2.53 | +| learning_rate | 0.0001 | +| loss | -0.096 | +| n_updates | 70010 | +| policy_gradient_loss | -0.0757 | +| value_loss | 0.000274 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.276 | +| time/ | | +| fps | 310 | +| iterations | 950 | +| time_elapsed | 3129 | +| total_timesteps | 972800 | +| train/ | | +| approx_kl | 1.966908 | +| clip_fraction | 0.51 | +| clip_range | 0.2 | +| entropy_loss | -0.434 | +| explained_variance | -1.5 | +| learning_rate | 0.0001 | +| loss | -0.0729 | +| n_updates | 70020 | +| policy_gradient_loss | -0.0698 | +| value_loss | 0.000298 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.276 | +| time/ | | +| fps | 310 | +| iterations | 951 | +| time_elapsed | 3132 | +| total_timesteps | 973824 | +| train/ | | +| approx_kl | 1.7816561 | +| clip_fraction | 0.485 | +| clip_range | 0.2 | +| entropy_loss | -0.4 | +| explained_variance | -0.727 | +| learning_rate | 0.0001 | +| loss | -0.0798 | +| n_updates | 70030 | +| policy_gradient_loss | -0.0704 | +| value_loss | 0.000776 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.276 | +| time/ | | +| fps | 310 | +| iterations | 952 | +| time_elapsed | 3136 | +| total_timesteps | 974848 | +| train/ | | +| approx_kl | 1.8740007 | +| clip_fraction | 0.499 | +| clip_range | 0.2 | +| entropy_loss | -0.482 | +| explained_variance | -1.61 | +| learning_rate | 0.0001 | +| loss | -0.0856 | +| n_updates | 70040 | +| policy_gradient_loss | -0.0741 | +| value_loss | 0.000508 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.276 | +| time/ | | +| fps | 310 | +| iterations | 953 | +| time_elapsed | 3139 | +| total_timesteps | 975872 | +| train/ | | +| approx_kl | 1.7057827 | +| clip_fraction | 0.459 | +| clip_range | 0.2 | +| entropy_loss | -0.362 | +| explained_variance | -1.93 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 70050 | +| policy_gradient_loss | -0.0708 | +| value_loss | 0.00041 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.271 | +| time/ | | +| fps | 310 | +| iterations | 954 | +| time_elapsed | 3142 | +| total_timesteps | 976896 | +| train/ | | +| approx_kl | 2.5050735 | +| clip_fraction | 0.49 | +| clip_range | 0.2 | +| entropy_loss | -0.39 | +| explained_variance | -3.54 | +| learning_rate | 0.0001 | +| loss | -0.0883 | +| n_updates | 70060 | +| policy_gradient_loss | -0.0653 | +| value_loss | 0.000541 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.271 | +| time/ | | +| fps | 310 | +| iterations | 955 | +| time_elapsed | 3145 | +| total_timesteps | 977920 | +| train/ | | +| approx_kl | 2.2360852 | +| clip_fraction | 0.5 | +| clip_range | 0.2 | +| entropy_loss | -0.41 | +| explained_variance | -0.39 | +| learning_rate | 0.0001 | +| loss | -0.0863 | +| n_updates | 70070 | +| policy_gradient_loss | -0.0704 | +| value_loss | 0.000541 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.274 | +| time/ | | +| fps | 310 | +| iterations | 956 | +| time_elapsed | 3149 | +| total_timesteps | 978944 | +| train/ | | +| approx_kl | 2.4920132 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.402 | +| explained_variance | -2.01 | +| learning_rate | 0.0001 | +| loss | -0.072 | +| n_updates | 70080 | +| policy_gradient_loss | -0.0639 | +| value_loss | 0.000639 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 310 | +| iterations | 957 | +| time_elapsed | 3152 | +| total_timesteps | 979968 | +| train/ | | +| approx_kl | 1.9029229 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.36 | +| explained_variance | -3.58 | +| learning_rate | 0.0001 | +| loss | -0.0987 | +| n_updates | 70090 | +| policy_gradient_loss | -0.07 | +| value_loss | 0.00052 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 310 | +| iterations | 958 | +| time_elapsed | 3155 | +| total_timesteps | 980992 | +| train/ | | +| approx_kl | 1.9105437 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.358 | +| explained_variance | -0.611 | +| learning_rate | 0.0001 | +| loss | -0.0599 | +| n_updates | 70100 | +| policy_gradient_loss | -0.067 | +| value_loss | 0.000601 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.272 | +| time/ | | +| fps | 310 | +| iterations | 959 | +| time_elapsed | 3158 | +| total_timesteps | 982016 | +| train/ | | +| approx_kl | 2.333155 | +| clip_fraction | 0.485 | +| clip_range | 0.2 | +| entropy_loss | -0.403 | +| explained_variance | -3 | +| learning_rate | 0.0001 | +| loss | -0.0312 | +| n_updates | 70110 | +| policy_gradient_loss | -0.0689 | +| value_loss | 0.000471 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.272 | +| time/ | | +| fps | 310 | +| iterations | 960 | +| time_elapsed | 3162 | +| total_timesteps | 983040 | +| train/ | | +| approx_kl | 2.0283432 | +| clip_fraction | 0.508 | +| clip_range | 0.2 | +| entropy_loss | -0.457 | +| explained_variance | -0.337 | +| learning_rate | 0.0001 | +| loss | -0.0658 | +| n_updates | 70120 | +| policy_gradient_loss | -0.0674 | +| value_loss | 0.000451 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.89e+03 | +| ep_rew_mean | 0.277 | +| time/ | | +| fps | 310 | +| iterations | 961 | +| time_elapsed | 3165 | +| total_timesteps | 984064 | +| train/ | | +| approx_kl | 2.4090896 | +| clip_fraction | 0.491 | +| clip_range | 0.2 | +| entropy_loss | -0.335 | +| explained_variance | -3.38 | +| learning_rate | 0.0001 | +| loss | -0.0546 | +| n_updates | 70130 | +| policy_gradient_loss | -0.0735 | +| value_loss | 0.000451 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.89e+03 | +| ep_rew_mean | 0.277 | +| time/ | | +| fps | 310 | +| iterations | 962 | +| time_elapsed | 3169 | +| total_timesteps | 985088 | +| train/ | | +| approx_kl | 2.113202 | +| clip_fraction | 0.466 | +| clip_range | 0.2 | +| entropy_loss | -0.332 | +| explained_variance | -0.887 | +| learning_rate | 0.0001 | +| loss | -0.064 | +| n_updates | 70140 | +| policy_gradient_loss | -0.0639 | +| value_loss | 0.000448 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.28 | +| time/ | | +| fps | 310 | +| iterations | 963 | +| time_elapsed | 3172 | +| total_timesteps | 986112 | +| train/ | | +| approx_kl | 4.165428 | +| clip_fraction | 0.489 | +| clip_range | 0.2 | +| entropy_loss | -0.369 | +| explained_variance | -1.25 | +| learning_rate | 0.0001 | +| loss | -0.0636 | +| n_updates | 70150 | +| policy_gradient_loss | -0.0645 | +| value_loss | 0.000594 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.281 | +| time/ | | +| fps | 310 | +| iterations | 964 | +| time_elapsed | 3175 | +| total_timesteps | 987136 | +| train/ | | +| approx_kl | 3.1498895 | +| clip_fraction | 0.499 | +| clip_range | 0.2 | +| entropy_loss | -0.408 | +| explained_variance | -1.6 | +| learning_rate | 0.0001 | +| loss | -0.0695 | +| n_updates | 70160 | +| policy_gradient_loss | -0.0696 | +| value_loss | 0.000449 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.281 | +| time/ | | +| fps | 310 | +| iterations | 965 | +| time_elapsed | 3179 | +| total_timesteps | 988160 | +| train/ | | +| approx_kl | 1.8816822 | +| clip_fraction | 0.47 | +| clip_range | 0.2 | +| entropy_loss | -0.38 | +| explained_variance | -0.976 | +| learning_rate | 0.0001 | +| loss | -0.1 | +| n_updates | 70170 | +| policy_gradient_loss | -0.0668 | +| value_loss | 0.000426 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.281 | +| time/ | | +| fps | 310 | +| iterations | 966 | +| time_elapsed | 3182 | +| total_timesteps | 989184 | +| train/ | | +| approx_kl | 2.5557103 | +| clip_fraction | 0.465 | +| clip_range | 0.2 | +| entropy_loss | -0.317 | +| explained_variance | -2.32 | +| learning_rate | 0.0001 | +| loss | 0.101 | +| n_updates | 70180 | +| policy_gradient_loss | -0.0695 | +| value_loss | 0.000548 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.286 | +| time/ | | +| fps | 310 | +| iterations | 967 | +| time_elapsed | 3186 | +| total_timesteps | 990208 | +| train/ | | +| approx_kl | 2.402278 | +| clip_fraction | 0.464 | +| clip_range | 0.2 | +| entropy_loss | -0.333 | +| explained_variance | -1.8 | +| learning_rate | 0.0001 | +| loss | -0.112 | +| n_updates | 70190 | +| policy_gradient_loss | -0.0674 | +| value_loss | 0.000525 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.286 | +| time/ | | +| fps | 310 | +| iterations | 968 | +| time_elapsed | 3189 | +| total_timesteps | 991232 | +| train/ | | +| approx_kl | 2.2682886 | +| clip_fraction | 0.477 | +| clip_range | 0.2 | +| entropy_loss | -0.362 | +| explained_variance | -0.749 | +| learning_rate | 0.0001 | +| loss | -0.0931 | +| n_updates | 70200 | +| policy_gradient_loss | -0.066 | +| value_loss | 0.000525 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.286 | +| time/ | | +| fps | 310 | +| iterations | 969 | +| time_elapsed | 3192 | +| total_timesteps | 992256 | +| train/ | | +| approx_kl | 2.2898293 | +| clip_fraction | 0.474 | +| clip_range | 0.2 | +| entropy_loss | -0.389 | +| explained_variance | -0.721 | +| learning_rate | 0.0001 | +| loss | -0.0801 | +| n_updates | 70210 | +| policy_gradient_loss | -0.0621 | +| value_loss | 0.000604 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.283 | +| time/ | | +| fps | 310 | +| iterations | 970 | +| time_elapsed | 3196 | +| total_timesteps | 993280 | +| train/ | | +| approx_kl | 3.114067 | +| clip_fraction | 0.465 | +| clip_range | 0.2 | +| entropy_loss | -0.328 | +| explained_variance | -2.13 | +| learning_rate | 0.0001 | +| loss | -0.0857 | +| n_updates | 70220 | +| policy_gradient_loss | -0.0704 | +| value_loss | 0.000484 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.283 | +| time/ | | +| fps | 310 | +| iterations | 971 | +| time_elapsed | 3199 | +| total_timesteps | 994304 | +| train/ | | +| approx_kl | 2.7711148 | +| clip_fraction | 0.448 | +| clip_range | 0.2 | +| entropy_loss | -0.302 | +| explained_variance | -0.969 | +| learning_rate | 0.0001 | +| loss | -0.0704 | +| n_updates | 70230 | +| policy_gradient_loss | -0.0652 | +| value_loss | 0.00045 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.28 | +| time/ | | +| fps | 310 | +| iterations | 972 | +| time_elapsed | 3202 | +| total_timesteps | 995328 | +| train/ | | +| approx_kl | 2.8681955 | +| clip_fraction | 0.452 | +| clip_range | 0.2 | +| entropy_loss | -0.352 | +| explained_variance | -1.22 | +| learning_rate | 0.0001 | +| loss | -0.0714 | +| n_updates | 70240 | +| policy_gradient_loss | -0.0644 | +| value_loss | 0.000426 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.89e+03 | +| ep_rew_mean | 0.281 | +| time/ | | +| fps | 310 | +| iterations | 973 | +| time_elapsed | 3205 | +| total_timesteps | 996352 | +| train/ | | +| approx_kl | 2.6955044 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.371 | +| explained_variance | -2.72 | +| learning_rate | 0.0001 | +| loss | -0.0941 | +| n_updates | 70250 | +| policy_gradient_loss | -0.0645 | +| value_loss | 0.00054 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.89e+03 | +| ep_rew_mean | 0.281 | +| time/ | | +| fps | 310 | +| iterations | 974 | +| time_elapsed | 3208 | +| total_timesteps | 997376 | +| train/ | | +| approx_kl | 2.3943353 | +| clip_fraction | 0.473 | +| clip_range | 0.2 | +| entropy_loss | -0.347 | +| explained_variance | -1.58 | +| learning_rate | 0.0001 | +| loss | -0.0833 | +| n_updates | 70260 | +| policy_gradient_loss | -0.0716 | +| value_loss | 0.000599 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.89e+03 | +| ep_rew_mean | 0.284 | +| time/ | | +| fps | 310 | +| iterations | 975 | +| time_elapsed | 3211 | +| total_timesteps | 998400 | +| train/ | | +| approx_kl | 3.195523 | +| clip_fraction | 0.469 | +| clip_range | 0.2 | +| entropy_loss | -0.329 | +| explained_variance | -2.09 | +| learning_rate | 0.0001 | +| loss | -0.095 | +| n_updates | 70270 | +| policy_gradient_loss | -0.0669 | +| value_loss | 0.000559 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.89e+03 | +| ep_rew_mean | 0.284 | +| time/ | | +| fps | 310 | +| iterations | 976 | +| time_elapsed | 3215 | +| total_timesteps | 999424 | +| train/ | | +| approx_kl | 4.32976 | +| clip_fraction | 0.464 | +| clip_range | 0.2 | +| entropy_loss | -0.371 | +| explained_variance | -1.36 | +| learning_rate | 0.0001 | +| loss | -0.0735 | +| n_updates | 70280 | +| policy_gradient_loss | -0.0654 | +| value_loss | 0.000526 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.89e+03 | +| ep_rew_mean | 0.283 | +| time/ | | +| fps | 310 | +| iterations | 977 | +| time_elapsed | 3218 | +| total_timesteps | 1000448 | +| train/ | | +| approx_kl | 2.0841503 | +| clip_fraction | 0.474 | +| clip_range | 0.2 | +| entropy_loss | -0.372 | +| explained_variance | -2.47 | +| learning_rate | 0.0001 | +| loss | -0.086 | +| n_updates | 70290 | +| policy_gradient_loss | -0.0647 | +| value_loss | 0.000495 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.89e+03 | +| ep_rew_mean | 0.283 | +| time/ | | +| fps | 310 | +| iterations | 978 | +| time_elapsed | 3221 | +| total_timesteps | 1001472 | +| train/ | | +| approx_kl | 2.561767 | +| clip_fraction | 0.455 | +| clip_range | 0.2 | +| entropy_loss | -0.312 | +| explained_variance | -1.73 | +| learning_rate | 0.0001 | +| loss | -0.0574 | +| n_updates | 70300 | +| policy_gradient_loss | -0.0684 | +| value_loss | 0.00041 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.9e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 310 | +| iterations | 979 | +| time_elapsed | 3225 | +| total_timesteps | 1002496 | +| train/ | | +| approx_kl | 2.3072915 | +| clip_fraction | 0.482 | +| clip_range | 0.2 | +| entropy_loss | -0.361 | +| explained_variance | -2.27 | +| learning_rate | 0.0001 | +| loss | -0.0988 | +| n_updates | 70310 | +| policy_gradient_loss | -0.07 | +| value_loss | 0.00052 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.9e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 310 | +| iterations | 980 | +| time_elapsed | 3228 | +| total_timesteps | 1003520 | +| train/ | | +| approx_kl | 2.5495276 | +| clip_fraction | 0.46 | +| clip_range | 0.2 | +| entropy_loss | -0.334 | +| explained_variance | -0.961 | +| learning_rate | 0.0001 | +| loss | -0.0869 | +| n_updates | 70320 | +| policy_gradient_loss | -0.0602 | +| value_loss | 0.000358 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.89e+03 | +| ep_rew_mean | 0.281 | +| time/ | | +| fps | 310 | +| iterations | 981 | +| time_elapsed | 3232 | +| total_timesteps | 1004544 | +| train/ | | +| approx_kl | 2.1833458 | +| clip_fraction | 0.47 | +| clip_range | 0.2 | +| entropy_loss | -0.352 | +| explained_variance | -1.05 | +| learning_rate | 0.0001 | +| loss | -0.0938 | +| n_updates | 70330 | +| policy_gradient_loss | -0.064 | +| value_loss | 0.000596 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.89e+03 | +| ep_rew_mean | 0.281 | +| time/ | | +| fps | 310 | +| iterations | 982 | +| time_elapsed | 3235 | +| total_timesteps | 1005568 | +| train/ | | +| approx_kl | 2.5399776 | +| clip_fraction | 0.478 | +| clip_range | 0.2 | +| entropy_loss | -0.331 | +| explained_variance | -1.9 | +| learning_rate | 0.0001 | +| loss | -0.105 | +| n_updates | 70340 | +| policy_gradient_loss | -0.0674 | +| value_loss | 0.000566 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.89e+03 | +| ep_rew_mean | 0.283 | +| time/ | | +| fps | 310 | +| iterations | 983 | +| time_elapsed | 3239 | +| total_timesteps | 1006592 | +| train/ | | +| approx_kl | 2.171154 | +| clip_fraction | 0.484 | +| clip_range | 0.2 | +| entropy_loss | -0.37 | +| explained_variance | -2.26 | +| learning_rate | 0.0001 | +| loss | -0.0626 | +| n_updates | 70350 | +| policy_gradient_loss | -0.0669 | +| value_loss | 0.000418 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.89e+03 | +| ep_rew_mean | 0.283 | +| time/ | | +| fps | 310 | +| iterations | 984 | +| time_elapsed | 3242 | +| total_timesteps | 1007616 | +| train/ | | +| approx_kl | 2.5416634 | +| clip_fraction | 0.435 | +| clip_range | 0.2 | +| entropy_loss | -0.286 | +| explained_variance | -1.26 | +| learning_rate | 0.0001 | +| loss | -0.0754 | +| n_updates | 70360 | +| policy_gradient_loss | -0.0615 | +| value_loss | 0.000491 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.89e+03 | +| ep_rew_mean | 0.283 | +| time/ | | +| fps | 310 | +| iterations | 985 | +| time_elapsed | 3246 | +| total_timesteps | 1008640 | +| train/ | | +| approx_kl | 2.4389725 | +| clip_fraction | 0.459 | +| clip_range | 0.2 | +| entropy_loss | -0.329 | +| explained_variance | -1.13 | +| learning_rate | 0.0001 | +| loss | -0.0828 | +| n_updates | 70370 | +| policy_gradient_loss | -0.0711 | +| value_loss | 0.000815 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.89e+03 | +| ep_rew_mean | 0.281 | +| time/ | | +| fps | 310 | +| iterations | 986 | +| time_elapsed | 3249 | +| total_timesteps | 1009664 | +| train/ | | +| approx_kl | 18.131897 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.3 | +| explained_variance | -1.54 | +| learning_rate | 0.0001 | +| loss | -0.0876 | +| n_updates | 70380 | +| policy_gradient_loss | -0.0682 | +| value_loss | 0.000654 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.89e+03 | +| ep_rew_mean | 0.281 | +| time/ | | +| fps | 310 | +| iterations | 987 | +| time_elapsed | 3252 | +| total_timesteps | 1010688 | +| train/ | | +| approx_kl | 3.2188568 | +| clip_fraction | 0.469 | +| clip_range | 0.2 | +| entropy_loss | -0.341 | +| explained_variance | -2.58 | +| learning_rate | 0.0001 | +| loss | -0.0903 | +| n_updates | 70390 | +| policy_gradient_loss | -0.065 | +| value_loss | 0.000342 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.89e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 310 | +| iterations | 988 | +| time_elapsed | 3256 | +| total_timesteps | 1011712 | +| train/ | | +| approx_kl | 2.1970758 | +| clip_fraction | 0.449 | +| clip_range | 0.2 | +| entropy_loss | -0.299 | +| explained_variance | -1.78 | +| learning_rate | 0.0001 | +| loss | -0.0742 | +| n_updates | 70400 | +| policy_gradient_loss | -0.0629 | +| value_loss | 0.000433 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.89e+03 | +| ep_rew_mean | 0.284 | +| time/ | | +| fps | 310 | +| iterations | 989 | +| time_elapsed | 3259 | +| total_timesteps | 1012736 | +| train/ | | +| approx_kl | 2.4136815 | +| clip_fraction | 0.461 | +| clip_range | 0.2 | +| entropy_loss | -0.329 | +| explained_variance | -1.73 | +| learning_rate | 0.0001 | +| loss | -0.0911 | +| n_updates | 70410 | +| policy_gradient_loss | -0.0649 | +| value_loss | 0.000721 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.89e+03 | +| ep_rew_mean | 0.284 | +| time/ | | +| fps | 310 | +| iterations | 990 | +| time_elapsed | 3262 | +| total_timesteps | 1013760 | +| train/ | | +| approx_kl | 2.9956079 | +| clip_fraction | 0.502 | +| clip_range | 0.2 | +| entropy_loss | -0.421 | +| explained_variance | -1.29 | +| learning_rate | 0.0001 | +| loss | -0.0945 | +| n_updates | 70420 | +| policy_gradient_loss | -0.0697 | +| value_loss | 0.000629 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.89e+03 | +| ep_rew_mean | 0.284 | +| time/ | | +| fps | 310 | +| iterations | 991 | +| time_elapsed | 3265 | +| total_timesteps | 1014784 | +| train/ | | +| approx_kl | 2.5830643 | +| clip_fraction | 0.479 | +| clip_range | 0.2 | +| entropy_loss | -0.382 | +| explained_variance | -2.22 | +| learning_rate | 0.0001 | +| loss | -0.0928 | +| n_updates | 70430 | +| policy_gradient_loss | -0.0679 | +| value_loss | 0.000463 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.89e+03 | +| ep_rew_mean | 0.283 | +| time/ | | +| fps | 310 | +| iterations | 992 | +| time_elapsed | 3268 | +| total_timesteps | 1015808 | +| train/ | | +| approx_kl | 2.6450758 | +| clip_fraction | 0.455 | +| clip_range | 0.2 | +| entropy_loss | -0.3 | +| explained_variance | -1.63 | +| learning_rate | 0.0001 | +| loss | -0.0836 | +| n_updates | 70440 | +| policy_gradient_loss | -0.0683 | +| value_loss | 0.000378 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.89e+03 | +| ep_rew_mean | 0.284 | +| time/ | | +| fps | 310 | +| iterations | 993 | +| time_elapsed | 3272 | +| total_timesteps | 1016832 | +| train/ | | +| approx_kl | 2.6565542 | +| clip_fraction | 0.485 | +| clip_range | 0.2 | +| entropy_loss | -0.346 | +| explained_variance | -0.578 | +| learning_rate | 0.0001 | +| loss | -0.0828 | +| n_updates | 70450 | +| policy_gradient_loss | -0.0646 | +| value_loss | 0.000446 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 310 | +| iterations | 994 | +| time_elapsed | 3275 | +| total_timesteps | 1017856 | +| train/ | | +| approx_kl | 2.0995097 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.366 | +| explained_variance | -0.903 | +| learning_rate | 0.0001 | +| loss | -0.0854 | +| n_updates | 70460 | +| policy_gradient_loss | -0.0652 | +| value_loss | 0.000356 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 310 | +| iterations | 995 | +| time_elapsed | 3278 | +| total_timesteps | 1018880 | +| train/ | | +| approx_kl | 2.1493106 | +| clip_fraction | 0.439 | +| clip_range | 0.2 | +| entropy_loss | -0.297 | +| explained_variance | -0.749 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 70470 | +| policy_gradient_loss | -0.0654 | +| value_loss | 0.000409 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.283 | +| time/ | | +| fps | 310 | +| iterations | 996 | +| time_elapsed | 3282 | +| total_timesteps | 1019904 | +| train/ | | +| approx_kl | 2.507985 | +| clip_fraction | 0.47 | +| clip_range | 0.2 | +| entropy_loss | -0.375 | +| explained_variance | -1.56 | +| learning_rate | 0.0001 | +| loss | -0.0699 | +| n_updates | 70480 | +| policy_gradient_loss | -0.0639 | +| value_loss | 0.000604 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.283 | +| time/ | | +| fps | 310 | +| iterations | 997 | +| time_elapsed | 3285 | +| total_timesteps | 1020928 | +| train/ | | +| approx_kl | 2.6269379 | +| clip_fraction | 0.464 | +| clip_range | 0.2 | +| entropy_loss | -0.323 | +| explained_variance | -7.38 | +| learning_rate | 0.0001 | +| loss | -0.0957 | +| n_updates | 70490 | +| policy_gradient_loss | -0.0692 | +| value_loss | 0.000526 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.283 | +| time/ | | +| fps | 310 | +| iterations | 998 | +| time_elapsed | 3288 | +| total_timesteps | 1021952 | +| train/ | | +| approx_kl | 2.494872 | +| clip_fraction | 0.449 | +| clip_range | 0.2 | +| entropy_loss | -0.314 | +| explained_variance | -0.898 | +| learning_rate | 0.0001 | +| loss | -0.0764 | +| n_updates | 70500 | +| policy_gradient_loss | -0.0572 | +| value_loss | 0.00049 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.89e+03 | +| ep_rew_mean | 0.285 | +| time/ | | +| fps | 310 | +| iterations | 999 | +| time_elapsed | 3292 | +| total_timesteps | 1022976 | +| train/ | | +| approx_kl | 2.5226488 | +| clip_fraction | 0.472 | +| clip_range | 0.2 | +| entropy_loss | -0.341 | +| explained_variance | -1.29 | +| learning_rate | 0.0001 | +| loss | -0.0833 | +| n_updates | 70510 | +| policy_gradient_loss | -0.0618 | +| value_loss | 0.000411 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.283 | +| time/ | | +| fps | 310 | +| iterations | 1000 | +| time_elapsed | 3295 | +| total_timesteps | 1024000 | +| train/ | | +| approx_kl | 2.2272863 | +| clip_fraction | 0.447 | +| clip_range | 0.2 | +| entropy_loss | -0.311 | +| explained_variance | -0.823 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 70520 | +| policy_gradient_loss | -0.063 | +| value_loss | 0.000612 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.278 | +| time/ | | +| fps | 310 | +| iterations | 1001 | +| time_elapsed | 3299 | +| total_timesteps | 1025024 | +| train/ | | +| approx_kl | 2.2716475 | +| clip_fraction | 0.433 | +| clip_range | 0.2 | +| entropy_loss | -0.343 | +| explained_variance | -2.95 | +| learning_rate | 0.0001 | +| loss | -0.0957 | +| n_updates | 70530 | +| policy_gradient_loss | -0.0659 | +| value_loss | 0.000463 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.278 | +| time/ | | +| fps | 310 | +| iterations | 1002 | +| time_elapsed | 3302 | +| total_timesteps | 1026048 | +| train/ | | +| approx_kl | 2.2102594 | +| clip_fraction | 0.434 | +| clip_range | 0.2 | +| entropy_loss | -0.289 | +| explained_variance | -0.817 | +| learning_rate | 0.0001 | +| loss | -0.0789 | +| n_updates | 70540 | +| policy_gradient_loss | -0.0613 | +| value_loss | 0.000591 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.89e+03 | +| ep_rew_mean | 0.283 | +| time/ | | +| fps | 310 | +| iterations | 1003 | +| time_elapsed | 3305 | +| total_timesteps | 1027072 | +| train/ | | +| approx_kl | 2.556622 | +| clip_fraction | 0.477 | +| clip_range | 0.2 | +| entropy_loss | -0.4 | +| explained_variance | -0.944 | +| learning_rate | 0.0001 | +| loss | -0.0809 | +| n_updates | 70550 | +| policy_gradient_loss | -0.0644 | +| value_loss | 0.000477 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.89e+03 | +| ep_rew_mean | 0.283 | +| time/ | | +| fps | 310 | +| iterations | 1004 | +| time_elapsed | 3309 | +| total_timesteps | 1028096 | +| train/ | | +| approx_kl | 2.383161 | +| clip_fraction | 0.448 | +| clip_range | 0.2 | +| entropy_loss | -0.341 | +| explained_variance | -0.753 | +| learning_rate | 0.0001 | +| loss | -0.0807 | +| n_updates | 70560 | +| policy_gradient_loss | -0.0518 | +| value_loss | 0.000549 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.89e+03 | +| ep_rew_mean | 0.284 | +| time/ | | +| fps | 310 | +| iterations | 1005 | +| time_elapsed | 3312 | +| total_timesteps | 1029120 | +| train/ | | +| approx_kl | 2.5364873 | +| clip_fraction | 0.493 | +| clip_range | 0.2 | +| entropy_loss | -0.351 | +| explained_variance | -2.43 | +| learning_rate | 0.0001 | +| loss | -0.0935 | +| n_updates | 70570 | +| policy_gradient_loss | -0.0691 | +| value_loss | 0.000566 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.89e+03 | +| ep_rew_mean | 0.283 | +| time/ | | +| fps | 310 | +| iterations | 1006 | +| time_elapsed | 3315 | +| total_timesteps | 1030144 | +| train/ | | +| approx_kl | 2.6128607 | +| clip_fraction | 0.442 | +| clip_range | 0.2 | +| entropy_loss | -0.313 | +| explained_variance | -0.844 | +| learning_rate | 0.0001 | +| loss | -0.0897 | +| n_updates | 70580 | +| policy_gradient_loss | -0.0581 | +| value_loss | 0.000558 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.89e+03 | +| ep_rew_mean | 0.283 | +| time/ | | +| fps | 310 | +| iterations | 1007 | +| time_elapsed | 3318 | +| total_timesteps | 1031168 | +| train/ | | +| approx_kl | 1.8451315 | +| clip_fraction | 0.464 | +| clip_range | 0.2 | +| entropy_loss | -0.362 | +| explained_variance | -0.882 | +| learning_rate | 0.0001 | +| loss | -0.0957 | +| n_updates | 70590 | +| policy_gradient_loss | -0.0652 | +| value_loss | 0.000588 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.89e+03 | +| ep_rew_mean | 0.283 | +| time/ | | +| fps | 310 | +| iterations | 1008 | +| time_elapsed | 3322 | +| total_timesteps | 1032192 | +| train/ | | +| approx_kl | 3.1523855 | +| clip_fraction | 0.461 | +| clip_range | 0.2 | +| entropy_loss | -0.331 | +| explained_variance | -2.21 | +| learning_rate | 0.0001 | +| loss | -0.0877 | +| n_updates | 70600 | +| policy_gradient_loss | -0.0678 | +| value_loss | 0.000511 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.89e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 310 | +| iterations | 1009 | +| time_elapsed | 3325 | +| total_timesteps | 1033216 | +| train/ | | +| approx_kl | 2.2738032 | +| clip_fraction | 0.422 | +| clip_range | 0.2 | +| entropy_loss | -0.268 | +| explained_variance | -2.7 | +| learning_rate | 0.0001 | +| loss | -0.0594 | +| n_updates | 70610 | +| policy_gradient_loss | -0.0514 | +| value_loss | 0.000445 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.89e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 310 | +| iterations | 1010 | +| time_elapsed | 3328 | +| total_timesteps | 1034240 | +| train/ | | +| approx_kl | 2.5525265 | +| clip_fraction | 0.407 | +| clip_range | 0.2 | +| entropy_loss | -0.256 | +| explained_variance | -2.45 | +| learning_rate | 0.0001 | +| loss | -0.0778 | +| n_updates | 70620 | +| policy_gradient_loss | -0.0637 | +| value_loss | 0.000381 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.89e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 310 | +| iterations | 1011 | +| time_elapsed | 3331 | +| total_timesteps | 1035264 | +| train/ | | +| approx_kl | 2.668038 | +| clip_fraction | 0.484 | +| clip_range | 0.2 | +| entropy_loss | -0.302 | +| explained_variance | -1.1 | +| learning_rate | 0.0001 | +| loss | -0.0766 | +| n_updates | 70630 | +| policy_gradient_loss | -0.0635 | +| value_loss | 0.000501 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.89e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 310 | +| iterations | 1012 | +| time_elapsed | 3334 | +| total_timesteps | 1036288 | +| train/ | | +| approx_kl | 2.389536 | +| clip_fraction | 0.44 | +| clip_range | 0.2 | +| entropy_loss | -0.304 | +| explained_variance | -3.61 | +| learning_rate | 0.0001 | +| loss | -0.0532 | +| n_updates | 70640 | +| policy_gradient_loss | -0.061 | +| value_loss | 0.000376 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.277 | +| time/ | | +| fps | 310 | +| iterations | 1013 | +| time_elapsed | 3337 | +| total_timesteps | 1037312 | +| train/ | | +| approx_kl | 3.0127244 | +| clip_fraction | 0.451 | +| clip_range | 0.2 | +| entropy_loss | -0.297 | +| explained_variance | -3.43 | +| learning_rate | 0.0001 | +| loss | -0.0884 | +| n_updates | 70650 | +| policy_gradient_loss | -0.0669 | +| value_loss | 0.000302 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 310 | +| iterations | 1014 | +| time_elapsed | 3341 | +| total_timesteps | 1038336 | +| train/ | | +| approx_kl | 1.9953601 | +| clip_fraction | 0.459 | +| clip_range | 0.2 | +| entropy_loss | -0.356 | +| explained_variance | -0.68 | +| learning_rate | 0.0001 | +| loss | -0.0748 | +| n_updates | 70660 | +| policy_gradient_loss | -0.0585 | +| value_loss | 0.00065 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 310 | +| iterations | 1015 | +| time_elapsed | 3344 | +| total_timesteps | 1039360 | +| train/ | | +| approx_kl | 2.874873 | +| clip_fraction | 0.46 | +| clip_range | 0.2 | +| entropy_loss | -0.296 | +| explained_variance | -4.9 | +| learning_rate | 0.0001 | +| loss | -0.0826 | +| n_updates | 70670 | +| policy_gradient_loss | -0.0674 | +| value_loss | 0.000535 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 310 | +| iterations | 1016 | +| time_elapsed | 3348 | +| total_timesteps | 1040384 | +| train/ | | +| approx_kl | 2.0777636 | +| clip_fraction | 0.444 | +| clip_range | 0.2 | +| entropy_loss | -0.316 | +| explained_variance | -0.695 | +| learning_rate | 0.0001 | +| loss | -0.091 | +| n_updates | 70680 | +| policy_gradient_loss | -0.0646 | +| value_loss | 0.00048 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.284 | +| time/ | | +| fps | 310 | +| iterations | 1017 | +| time_elapsed | 3351 | +| total_timesteps | 1041408 | +| train/ | | +| approx_kl | 2.2362487 | +| clip_fraction | 0.485 | +| clip_range | 0.2 | +| entropy_loss | -0.37 | +| explained_variance | -1.19 | +| learning_rate | 0.0001 | +| loss | -0.046 | +| n_updates | 70690 | +| policy_gradient_loss | -0.0654 | +| value_loss | 0.000336 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.284 | +| time/ | | +| fps | 310 | +| iterations | 1018 | +| time_elapsed | 3355 | +| total_timesteps | 1042432 | +| train/ | | +| approx_kl | 2.4359517 | +| clip_fraction | 0.495 | +| clip_range | 0.2 | +| entropy_loss | -0.367 | +| explained_variance | -0.328 | +| learning_rate | 0.0001 | +| loss | -0.0858 | +| n_updates | 70700 | +| policy_gradient_loss | -0.0669 | +| value_loss | 0.000608 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.286 | +| time/ | | +| fps | 310 | +| iterations | 1019 | +| time_elapsed | 3358 | +| total_timesteps | 1043456 | +| train/ | | +| approx_kl | 3.7984934 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.343 | +| explained_variance | -2.16 | +| learning_rate | 0.0001 | +| loss | -0.0937 | +| n_updates | 70710 | +| policy_gradient_loss | -0.0641 | +| value_loss | 0.000723 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.286 | +| time/ | | +| fps | 310 | +| iterations | 1020 | +| time_elapsed | 3362 | +| total_timesteps | 1044480 | +| train/ | | +| approx_kl | 2.4335952 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.382 | +| explained_variance | -0.678 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 70720 | +| policy_gradient_loss | -0.0622 | +| value_loss | 0.000463 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.286 | +| time/ | | +| fps | 310 | +| iterations | 1021 | +| time_elapsed | 3365 | +| total_timesteps | 1045504 | +| train/ | | +| approx_kl | 1.6472427 | +| clip_fraction | 0.451 | +| clip_range | 0.2 | +| entropy_loss | -0.368 | +| explained_variance | -1.11 | +| learning_rate | 0.0001 | +| loss | -0.0879 | +| n_updates | 70730 | +| policy_gradient_loss | -0.059 | +| value_loss | 0.000624 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.286 | +| time/ | | +| fps | 310 | +| iterations | 1022 | +| time_elapsed | 3369 | +| total_timesteps | 1046528 | +| train/ | | +| approx_kl | 2.4422944 | +| clip_fraction | 0.479 | +| clip_range | 0.2 | +| entropy_loss | -0.323 | +| explained_variance | -6.51 | +| learning_rate | 0.0001 | +| loss | -0.0966 | +| n_updates | 70740 | +| policy_gradient_loss | -0.0696 | +| value_loss | 0.00034 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.291 | +| time/ | | +| fps | 310 | +| iterations | 1023 | +| time_elapsed | 3372 | +| total_timesteps | 1047552 | +| train/ | | +| approx_kl | 2.6657352 | +| clip_fraction | 0.505 | +| clip_range | 0.2 | +| entropy_loss | -0.366 | +| explained_variance | -0.919 | +| learning_rate | 0.0001 | +| loss | -0.0634 | +| n_updates | 70750 | +| policy_gradient_loss | -0.0675 | +| value_loss | 0.000297 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.291 | +| time/ | | +| fps | 310 | +| iterations | 1024 | +| time_elapsed | 3375 | +| total_timesteps | 1048576 | +| train/ | | +| approx_kl | 1.7238348 | +| clip_fraction | 0.474 | +| clip_range | 0.2 | +| entropy_loss | -0.431 | +| explained_variance | -0.23 | +| learning_rate | 0.0001 | +| loss | -0.0632 | +| n_updates | 70760 | +| policy_gradient_loss | -0.0542 | +| value_loss | 0.000784 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.291 | +| time/ | | +| fps | 310 | +| iterations | 1025 | +| time_elapsed | 3378 | +| total_timesteps | 1049600 | +| train/ | | +| approx_kl | 2.0288167 | +| clip_fraction | 0.463 | +| clip_range | 0.2 | +| entropy_loss | -0.367 | +| explained_variance | -2.01 | +| learning_rate | 0.0001 | +| loss | -0.109 | +| n_updates | 70770 | +| policy_gradient_loss | -0.0686 | +| value_loss | 0.000567 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.294 | +| time/ | | +| fps | 310 | +| iterations | 1026 | +| time_elapsed | 3382 | +| total_timesteps | 1050624 | +| train/ | | +| approx_kl | 2.1846375 | +| clip_fraction | 0.447 | +| clip_range | 0.2 | +| entropy_loss | -0.353 | +| explained_variance | -1.25 | +| learning_rate | 0.0001 | +| loss | -0.078 | +| n_updates | 70780 | +| policy_gradient_loss | -0.0682 | +| value_loss | 0.00035 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.294 | +| time/ | | +| fps | 310 | +| iterations | 1027 | +| time_elapsed | 3385 | +| total_timesteps | 1051648 | +| train/ | | +| approx_kl | 4.1845875 | +| clip_fraction | 0.44 | +| clip_range | 0.2 | +| entropy_loss | -0.316 | +| explained_variance | -0.897 | +| learning_rate | 0.0001 | +| loss | -0.079 | +| n_updates | 70790 | +| policy_gradient_loss | -0.0561 | +| value_loss | 0.000439 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.297 | +| time/ | | +| fps | 310 | +| iterations | 1028 | +| time_elapsed | 3388 | +| total_timesteps | 1052672 | +| train/ | | +| approx_kl | 2.3234344 | +| clip_fraction | 0.446 | +| clip_range | 0.2 | +| entropy_loss | -0.33 | +| explained_variance | -1.71 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 70800 | +| policy_gradient_loss | -0.065 | +| value_loss | 0.000544 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 310 | +| iterations | 1029 | +| time_elapsed | 3391 | +| total_timesteps | 1053696 | +| train/ | | +| approx_kl | 3.5967755 | +| clip_fraction | 0.486 | +| clip_range | 0.2 | +| entropy_loss | -0.332 | +| explained_variance | -2.18 | +| learning_rate | 0.0001 | +| loss | -0.0942 | +| n_updates | 70810 | +| policy_gradient_loss | -0.07 | +| value_loss | 0.000357 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 310 | +| iterations | 1030 | +| time_elapsed | 3394 | +| total_timesteps | 1054720 | +| train/ | | +| approx_kl | 2.2584658 | +| clip_fraction | 0.457 | +| clip_range | 0.2 | +| entropy_loss | -0.319 | +| explained_variance | -0.821 | +| learning_rate | 0.0001 | +| loss | -0.0681 | +| n_updates | 70820 | +| policy_gradient_loss | -0.0575 | +| value_loss | 0.000544 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 310 | +| iterations | 1031 | +| time_elapsed | 3398 | +| total_timesteps | 1055744 | +| train/ | | +| approx_kl | 2.0236158 | +| clip_fraction | 0.472 | +| clip_range | 0.2 | +| entropy_loss | -0.361 | +| explained_variance | -2.39 | +| learning_rate | 0.0001 | +| loss | -0.075 | +| n_updates | 70830 | +| policy_gradient_loss | -0.0654 | +| value_loss | 0.00053 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 310 | +| iterations | 1032 | +| time_elapsed | 3401 | +| total_timesteps | 1056768 | +| train/ | | +| approx_kl | 2.2861443 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.325 | +| explained_variance | -1.21 | +| learning_rate | 0.0001 | +| loss | -0.0984 | +| n_updates | 70840 | +| policy_gradient_loss | -0.0678 | +| value_loss | 0.00059 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 310 | +| iterations | 1033 | +| time_elapsed | 3405 | +| total_timesteps | 1057792 | +| train/ | | +| approx_kl | 3.1390586 | +| clip_fraction | 0.472 | +| clip_range | 0.2 | +| entropy_loss | -0.382 | +| explained_variance | -0.927 | +| learning_rate | 0.0001 | +| loss | -0.0889 | +| n_updates | 70850 | +| policy_gradient_loss | -0.0585 | +| value_loss | 0.000562 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 310 | +| iterations | 1034 | +| time_elapsed | 3408 | +| total_timesteps | 1058816 | +| train/ | | +| approx_kl | 1.9465711 | +| clip_fraction | 0.446 | +| clip_range | 0.2 | +| entropy_loss | -0.341 | +| explained_variance | -2.39 | +| learning_rate | 0.0001 | +| loss | -0.0694 | +| n_updates | 70860 | +| policy_gradient_loss | -0.0607 | +| value_loss | 0.000532 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 310 | +| iterations | 1035 | +| time_elapsed | 3411 | +| total_timesteps | 1059840 | +| train/ | | +| approx_kl | 2.242001 | +| clip_fraction | 0.441 | +| clip_range | 0.2 | +| entropy_loss | -0.291 | +| explained_variance | -4.3 | +| learning_rate | 0.0001 | +| loss | -0.0928 | +| n_updates | 70870 | +| policy_gradient_loss | -0.0662 | +| value_loss | 0.000666 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 310 | +| iterations | 1036 | +| time_elapsed | 3415 | +| total_timesteps | 1060864 | +| train/ | | +| approx_kl | 1.8956414 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.375 | +| explained_variance | -1.54 | +| learning_rate | 0.0001 | +| loss | -0.115 | +| n_updates | 70880 | +| policy_gradient_loss | -0.0707 | +| value_loss | 0.00037 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 310 | +| iterations | 1037 | +| time_elapsed | 3418 | +| total_timesteps | 1061888 | +| train/ | | +| approx_kl | 1.8641933 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.363 | +| explained_variance | -5.08 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 70890 | +| policy_gradient_loss | -0.0712 | +| value_loss | 0.000278 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 310 | +| iterations | 1038 | +| time_elapsed | 3421 | +| total_timesteps | 1062912 | +| train/ | | +| approx_kl | 2.872657 | +| clip_fraction | 0.47 | +| clip_range | 0.2 | +| entropy_loss | -0.34 | +| explained_variance | -1.27 | +| learning_rate | 0.0001 | +| loss | -0.0724 | +| n_updates | 70900 | +| policy_gradient_loss | -0.0531 | +| value_loss | 0.000314 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 310 | +| iterations | 1039 | +| time_elapsed | 3425 | +| total_timesteps | 1063936 | +| train/ | | +| approx_kl | 2.241956 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.324 | +| explained_variance | -1.14 | +| learning_rate | 0.0001 | +| loss | -0.0888 | +| n_updates | 70910 | +| policy_gradient_loss | -0.0696 | +| value_loss | 0.000622 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.298 | +| time/ | | +| fps | 310 | +| iterations | 1040 | +| time_elapsed | 3428 | +| total_timesteps | 1064960 | +| train/ | | +| approx_kl | 2.873096 | +| clip_fraction | 0.431 | +| clip_range | 0.2 | +| entropy_loss | -0.299 | +| explained_variance | -2.34 | +| learning_rate | 0.0001 | +| loss | -0.0998 | +| n_updates | 70920 | +| policy_gradient_loss | -0.0632 | +| value_loss | 0.000412 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.298 | +| time/ | | +| fps | 310 | +| iterations | 1041 | +| time_elapsed | 3431 | +| total_timesteps | 1065984 | +| train/ | | +| approx_kl | 2.8950608 | +| clip_fraction | 0.449 | +| clip_range | 0.2 | +| entropy_loss | -0.291 | +| explained_variance | -0.543 | +| learning_rate | 0.0001 | +| loss | -0.0844 | +| n_updates | 70930 | +| policy_gradient_loss | -0.0659 | +| value_loss | 0.000632 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.294 | +| time/ | | +| fps | 310 | +| iterations | 1042 | +| time_elapsed | 3434 | +| total_timesteps | 1067008 | +| train/ | | +| approx_kl | 2.7078683 | +| clip_fraction | 0.458 | +| clip_range | 0.2 | +| entropy_loss | -0.305 | +| explained_variance | -2.41 | +| learning_rate | 0.0001 | +| loss | -0.0885 | +| n_updates | 70940 | +| policy_gradient_loss | -0.0662 | +| value_loss | 0.000453 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.294 | +| time/ | | +| fps | 310 | +| iterations | 1043 | +| time_elapsed | 3438 | +| total_timesteps | 1068032 | +| train/ | | +| approx_kl | 2.9374309 | +| clip_fraction | 0.454 | +| clip_range | 0.2 | +| entropy_loss | -0.335 | +| explained_variance | -1.57 | +| learning_rate | 0.0001 | +| loss | -0.0717 | +| n_updates | 70950 | +| policy_gradient_loss | -0.0595 | +| value_loss | 0.000354 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.294 | +| time/ | | +| fps | 310 | +| iterations | 1044 | +| time_elapsed | 3441 | +| total_timesteps | 1069056 | +| train/ | | +| approx_kl | 2.2262812 | +| clip_fraction | 0.463 | +| clip_range | 0.2 | +| entropy_loss | -0.334 | +| explained_variance | -2.47 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 70960 | +| policy_gradient_loss | -0.07 | +| value_loss | 0.000904 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.9e+03 | +| ep_rew_mean | 0.295 | +| time/ | | +| fps | 310 | +| iterations | 1045 | +| time_elapsed | 3444 | +| total_timesteps | 1070080 | +| train/ | | +| approx_kl | 2.273109 | +| clip_fraction | 0.493 | +| clip_range | 0.2 | +| entropy_loss | -0.339 | +| explained_variance | -1.31 | +| learning_rate | 0.0001 | +| loss | -0.097 | +| n_updates | 70970 | +| policy_gradient_loss | -0.0719 | +| value_loss | 0.000886 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.89e+03 | +| ep_rew_mean | 0.297 | +| time/ | | +| fps | 310 | +| iterations | 1046 | +| time_elapsed | 3447 | +| total_timesteps | 1071104 | +| train/ | | +| approx_kl | 2.2983236 | +| clip_fraction | 0.465 | +| clip_range | 0.2 | +| entropy_loss | -0.353 | +| explained_variance | -1.5 | +| learning_rate | 0.0001 | +| loss | -0.0847 | +| n_updates | 70980 | +| policy_gradient_loss | -0.0596 | +| value_loss | 0.000629 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.89e+03 | +| ep_rew_mean | 0.297 | +| time/ | | +| fps | 310 | +| iterations | 1047 | +| time_elapsed | 3450 | +| total_timesteps | 1072128 | +| train/ | | +| approx_kl | 2.2729235 | +| clip_fraction | 0.453 | +| clip_range | 0.2 | +| entropy_loss | -0.31 | +| explained_variance | -1.91 | +| learning_rate | 0.0001 | +| loss | -0.106 | +| n_updates | 70990 | +| policy_gradient_loss | -0.0686 | +| value_loss | 0.000565 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.9e+03 | +| ep_rew_mean | 0.297 | +| time/ | | +| fps | 310 | +| iterations | 1048 | +| time_elapsed | 3454 | +| total_timesteps | 1073152 | +| train/ | | +| approx_kl | 2.1050475 | +| clip_fraction | 0.474 | +| clip_range | 0.2 | +| entropy_loss | -0.376 | +| explained_variance | -2.98 | +| learning_rate | 0.0001 | +| loss | -0.0914 | +| n_updates | 71000 | +| policy_gradient_loss | -0.066 | +| value_loss | 0.000343 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.9e+03 | +| ep_rew_mean | 0.297 | +| time/ | | +| fps | 310 | +| iterations | 1049 | +| time_elapsed | 3457 | +| total_timesteps | 1074176 | +| train/ | | +| approx_kl | 2.7808924 | +| clip_fraction | 0.468 | +| clip_range | 0.2 | +| entropy_loss | -0.346 | +| explained_variance | -0.713 | +| learning_rate | 0.0001 | +| loss | -0.0872 | +| n_updates | 71010 | +| policy_gradient_loss | -0.065 | +| value_loss | 0.000588 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.89e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 310 | +| iterations | 1050 | +| time_elapsed | 3460 | +| total_timesteps | 1075200 | +| train/ | | +| approx_kl | 2.5219464 | +| clip_fraction | 0.5 | +| clip_range | 0.2 | +| entropy_loss | -0.373 | +| explained_variance | -1.82 | +| learning_rate | 0.0001 | +| loss | -0.0987 | +| n_updates | 71020 | +| policy_gradient_loss | -0.0758 | +| value_loss | 0.000557 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.89e+03 | +| ep_rew_mean | 0.295 | +| time/ | | +| fps | 310 | +| iterations | 1051 | +| time_elapsed | 3464 | +| total_timesteps | 1076224 | +| train/ | | +| approx_kl | 1.842998 | +| clip_fraction | 0.437 | +| clip_range | 0.2 | +| entropy_loss | -0.339 | +| explained_variance | -1 | +| learning_rate | 0.0001 | +| loss | -0.0748 | +| n_updates | 71030 | +| policy_gradient_loss | -0.0591 | +| value_loss | 0.000555 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.89e+03 | +| ep_rew_mean | 0.295 | +| time/ | | +| fps | 310 | +| iterations | 1052 | +| time_elapsed | 3467 | +| total_timesteps | 1077248 | +| train/ | | +| approx_kl | 2.444707 | +| clip_fraction | 0.449 | +| clip_range | 0.2 | +| entropy_loss | -0.318 | +| explained_variance | -2.22 | +| learning_rate | 0.0001 | +| loss | -0.0652 | +| n_updates | 71040 | +| policy_gradient_loss | -0.0664 | +| value_loss | 0.000485 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.89e+03 | +| ep_rew_mean | 0.295 | +| time/ | | +| fps | 310 | +| iterations | 1053 | +| time_elapsed | 3471 | +| total_timesteps | 1078272 | +| train/ | | +| approx_kl | 1.9548483 | +| clip_fraction | 0.461 | +| clip_range | 0.2 | +| entropy_loss | -0.361 | +| explained_variance | -1.12 | +| learning_rate | 0.0001 | +| loss | -0.0815 | +| n_updates | 71050 | +| policy_gradient_loss | -0.064 | +| value_loss | 0.000571 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.89e+03 | +| ep_rew_mean | 0.295 | +| time/ | | +| fps | 310 | +| iterations | 1054 | +| time_elapsed | 3474 | +| total_timesteps | 1079296 | +| train/ | | +| approx_kl | 2.3259983 | +| clip_fraction | 0.46 | +| clip_range | 0.2 | +| entropy_loss | -0.329 | +| explained_variance | -0.64 | +| learning_rate | 0.0001 | +| loss | -0.0724 | +| n_updates | 71060 | +| policy_gradient_loss | -0.0658 | +| value_loss | 0.000483 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.89e+03 | +| ep_rew_mean | 0.295 | +| time/ | | +| fps | 310 | +| iterations | 1055 | +| time_elapsed | 3478 | +| total_timesteps | 1080320 | +| train/ | | +| approx_kl | 2.6035645 | +| clip_fraction | 0.474 | +| clip_range | 0.2 | +| entropy_loss | -0.303 | +| explained_variance | -3.92 | +| learning_rate | 0.0001 | +| loss | -0.0821 | +| n_updates | 71070 | +| policy_gradient_loss | -0.0655 | +| value_loss | 0.000546 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.89e+03 | +| ep_rew_mean | 0.294 | +| time/ | | +| fps | 310 | +| iterations | 1056 | +| time_elapsed | 3481 | +| total_timesteps | 1081344 | +| train/ | | +| approx_kl | 2.4288135 | +| clip_fraction | 0.479 | +| clip_range | 0.2 | +| entropy_loss | -0.318 | +| explained_variance | -3.93 | +| learning_rate | 0.0001 | +| loss | -0.0873 | +| n_updates | 71080 | +| policy_gradient_loss | -0.0672 | +| value_loss | 0.000563 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.297 | +| time/ | | +| fps | 310 | +| iterations | 1057 | +| time_elapsed | 3485 | +| total_timesteps | 1082368 | +| train/ | | +| approx_kl | 37.890167 | +| clip_fraction | 0.505 | +| clip_range | 0.2 | +| entropy_loss | -0.387 | +| explained_variance | -0.522 | +| learning_rate | 0.0001 | +| loss | -0.097 | +| n_updates | 71090 | +| policy_gradient_loss | -0.0611 | +| value_loss | 0.000476 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.297 | +| time/ | | +| fps | 310 | +| iterations | 1058 | +| time_elapsed | 3488 | +| total_timesteps | 1083392 | +| train/ | | +| approx_kl | 2.3993225 | +| clip_fraction | 0.461 | +| clip_range | 0.2 | +| entropy_loss | -0.322 | +| explained_variance | -1.1 | +| learning_rate | 0.0001 | +| loss | -0.0768 | +| n_updates | 71100 | +| policy_gradient_loss | -0.0641 | +| value_loss | 0.000616 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.298 | +| time/ | | +| fps | 310 | +| iterations | 1059 | +| time_elapsed | 3492 | +| total_timesteps | 1084416 | +| train/ | | +| approx_kl | 2.2120767 | +| clip_fraction | 0.47 | +| clip_range | 0.2 | +| entropy_loss | -0.331 | +| explained_variance | -2.55 | +| learning_rate | 0.0001 | +| loss | -0.0879 | +| n_updates | 71110 | +| policy_gradient_loss | -0.0719 | +| value_loss | 0.000413 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.302 | +| time/ | | +| fps | 310 | +| iterations | 1060 | +| time_elapsed | 3495 | +| total_timesteps | 1085440 | +| train/ | | +| approx_kl | 1.9834721 | +| clip_fraction | 0.47 | +| clip_range | 0.2 | +| entropy_loss | -0.345 | +| explained_variance | -0.867 | +| learning_rate | 0.0001 | +| loss | -0.0852 | +| n_updates | 71120 | +| policy_gradient_loss | -0.0636 | +| value_loss | 0.000456 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.302 | +| time/ | | +| fps | 310 | +| iterations | 1061 | +| time_elapsed | 3498 | +| total_timesteps | 1086464 | +| train/ | | +| approx_kl | 1.8246282 | +| clip_fraction | 0.515 | +| clip_range | 0.2 | +| entropy_loss | -0.413 | +| explained_variance | -0.743 | +| learning_rate | 0.0001 | +| loss | -0.0776 | +| n_updates | 71130 | +| policy_gradient_loss | -0.0647 | +| value_loss | 0.000787 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.302 | +| time/ | | +| fps | 310 | +| iterations | 1062 | +| time_elapsed | 3501 | +| total_timesteps | 1087488 | +| train/ | | +| approx_kl | 2.514327 | +| clip_fraction | 0.484 | +| clip_range | 0.2 | +| entropy_loss | -0.341 | +| explained_variance | -4.04 | +| learning_rate | 0.0001 | +| loss | -0.0842 | +| n_updates | 71140 | +| policy_gradient_loss | -0.07 | +| value_loss | 0.000707 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.3 | +| time/ | | +| fps | 310 | +| iterations | 1063 | +| time_elapsed | 3504 | +| total_timesteps | 1088512 | +| train/ | | +| approx_kl | 2.8801637 | +| clip_fraction | 0.463 | +| clip_range | 0.2 | +| entropy_loss | -0.324 | +| explained_variance | -1.6 | +| learning_rate | 0.0001 | +| loss | -0.0792 | +| n_updates | 71150 | +| policy_gradient_loss | -0.067 | +| value_loss | 0.000449 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.3 | +| time/ | | +| fps | 310 | +| iterations | 1064 | +| time_elapsed | 3508 | +| total_timesteps | 1089536 | +| train/ | | +| approx_kl | 2.326652 | +| clip_fraction | 0.474 | +| clip_range | 0.2 | +| entropy_loss | -0.342 | +| explained_variance | -1.66 | +| learning_rate | 0.0001 | +| loss | -0.0849 | +| n_updates | 71160 | +| policy_gradient_loss | -0.0589 | +| value_loss | 0.000386 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 310 | +| iterations | 1065 | +| time_elapsed | 3511 | +| total_timesteps | 1090560 | +| train/ | | +| approx_kl | 2.8986053 | +| clip_fraction | 0.492 | +| clip_range | 0.2 | +| entropy_loss | -0.381 | +| explained_variance | -2.64 | +| learning_rate | 0.0001 | +| loss | -0.0862 | +| n_updates | 71170 | +| policy_gradient_loss | -0.0656 | +| value_loss | 0.000324 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 310 | +| iterations | 1066 | +| time_elapsed | 3514 | +| total_timesteps | 1091584 | +| train/ | | +| approx_kl | 3.9294188 | +| clip_fraction | 0.468 | +| clip_range | 0.2 | +| entropy_loss | -0.356 | +| explained_variance | -1.23 | +| learning_rate | 0.0001 | +| loss | -0.113 | +| n_updates | 71180 | +| policy_gradient_loss | -0.0643 | +| value_loss | 0.000403 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.3 | +| time/ | | +| fps | 310 | +| iterations | 1067 | +| time_elapsed | 3517 | +| total_timesteps | 1092608 | +| train/ | | +| approx_kl | 3.440074 | +| clip_fraction | 0.523 | +| clip_range | 0.2 | +| entropy_loss | -0.407 | +| explained_variance | -1.32 | +| learning_rate | 0.0001 | +| loss | -0.109 | +| n_updates | 71190 | +| policy_gradient_loss | -0.0724 | +| value_loss | 0.000364 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.3 | +| time/ | | +| fps | 310 | +| iterations | 1068 | +| time_elapsed | 3521 | +| total_timesteps | 1093632 | +| train/ | | +| approx_kl | 1.8750942 | +| clip_fraction | 0.486 | +| clip_range | 0.2 | +| entropy_loss | -0.392 | +| explained_variance | -0.615 | +| learning_rate | 0.0001 | +| loss | -0.108 | +| n_updates | 71200 | +| policy_gradient_loss | -0.0691 | +| value_loss | 0.000451 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 310 | +| iterations | 1069 | +| time_elapsed | 3524 | +| total_timesteps | 1094656 | +| train/ | | +| approx_kl | 2.94279 | +| clip_fraction | 0.469 | +| clip_range | 0.2 | +| entropy_loss | -0.359 | +| explained_variance | -9.43 | +| learning_rate | 0.0001 | +| loss | -0.09 | +| n_updates | 71210 | +| policy_gradient_loss | -0.0713 | +| value_loss | 0.00037 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 310 | +| iterations | 1070 | +| time_elapsed | 3527 | +| total_timesteps | 1095680 | +| train/ | | +| approx_kl | 1.9539133 | +| clip_fraction | 0.432 | +| clip_range | 0.2 | +| entropy_loss | -0.33 | +| explained_variance | -1.19 | +| learning_rate | 0.0001 | +| loss | -0.0683 | +| n_updates | 71220 | +| policy_gradient_loss | -0.0617 | +| value_loss | 0.000527 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.297 | +| time/ | | +| fps | 310 | +| iterations | 1071 | +| time_elapsed | 3531 | +| total_timesteps | 1096704 | +| train/ | | +| approx_kl | 2.916946 | +| clip_fraction | 0.46 | +| clip_range | 0.2 | +| entropy_loss | -0.308 | +| explained_variance | -1.96 | +| learning_rate | 0.0001 | +| loss | -0.0921 | +| n_updates | 71230 | +| policy_gradient_loss | -0.0715 | +| value_loss | 0.00065 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.297 | +| time/ | | +| fps | 310 | +| iterations | 1072 | +| time_elapsed | 3534 | +| total_timesteps | 1097728 | +| train/ | | +| approx_kl | 2.680472 | +| clip_fraction | 0.499 | +| clip_range | 0.2 | +| entropy_loss | -0.353 | +| explained_variance | -1.16 | +| learning_rate | 0.0001 | +| loss | -0.0742 | +| n_updates | 71240 | +| policy_gradient_loss | -0.0717 | +| value_loss | 0.000735 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.298 | +| time/ | | +| fps | 310 | +| iterations | 1073 | +| time_elapsed | 3538 | +| total_timesteps | 1098752 | +| train/ | | +| approx_kl | 2.275601 | +| clip_fraction | 0.484 | +| clip_range | 0.2 | +| entropy_loss | -0.317 | +| explained_variance | -3.97 | +| learning_rate | 0.0001 | +| loss | -0.0996 | +| n_updates | 71250 | +| policy_gradient_loss | -0.0703 | +| value_loss | 0.000493 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 310 | +| iterations | 1074 | +| time_elapsed | 3541 | +| total_timesteps | 1099776 | +| train/ | | +| approx_kl | 2.5351696 | +| clip_fraction | 0.444 | +| clip_range | 0.2 | +| entropy_loss | -0.311 | +| explained_variance | -1.28 | +| learning_rate | 0.0001 | +| loss | -0.0853 | +| n_updates | 71260 | +| policy_gradient_loss | -0.0602 | +| value_loss | 0.000466 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 310 | +| iterations | 1075 | +| time_elapsed | 3544 | +| total_timesteps | 1100800 | +| train/ | | +| approx_kl | 2.5727167 | +| clip_fraction | 0.486 | +| clip_range | 0.2 | +| entropy_loss | -0.343 | +| explained_variance | -0.673 | +| learning_rate | 0.0001 | +| loss | -0.0761 | +| n_updates | 71270 | +| policy_gradient_loss | -0.0674 | +| value_loss | 0.000737 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.304 | +| time/ | | +| fps | 310 | +| iterations | 1076 | +| time_elapsed | 3548 | +| total_timesteps | 1101824 | +| train/ | | +| approx_kl | 2.034247 | +| clip_fraction | 0.444 | +| clip_range | 0.2 | +| entropy_loss | -0.335 | +| explained_variance | -2.84 | +| learning_rate | 0.0001 | +| loss | -0.0805 | +| n_updates | 71280 | +| policy_gradient_loss | -0.0664 | +| value_loss | 0.000657 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.304 | +| time/ | | +| fps | 310 | +| iterations | 1077 | +| time_elapsed | 3551 | +| total_timesteps | 1102848 | +| train/ | | +| approx_kl | 2.5713882 | +| clip_fraction | 0.465 | +| clip_range | 0.2 | +| entropy_loss | -0.349 | +| explained_variance | -2.37 | +| learning_rate | 0.0001 | +| loss | -0.0837 | +| n_updates | 71290 | +| policy_gradient_loss | -0.067 | +| value_loss | 0.000407 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.306 | +| time/ | | +| fps | 310 | +| iterations | 1078 | +| time_elapsed | 3554 | +| total_timesteps | 1103872 | +| train/ | | +| approx_kl | 3.9824486 | +| clip_fraction | 0.504 | +| clip_range | 0.2 | +| entropy_loss | -0.378 | +| explained_variance | -0.949 | +| learning_rate | 0.0001 | +| loss | -0.0927 | +| n_updates | 71300 | +| policy_gradient_loss | -0.0715 | +| value_loss | 0.000465 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.306 | +| time/ | | +| fps | 310 | +| iterations | 1079 | +| time_elapsed | 3557 | +| total_timesteps | 1104896 | +| train/ | | +| approx_kl | 2.3639636 | +| clip_fraction | 0.465 | +| clip_range | 0.2 | +| entropy_loss | -0.345 | +| explained_variance | -1.5 | +| learning_rate | 0.0001 | +| loss | -0.0914 | +| n_updates | 71310 | +| policy_gradient_loss | -0.0672 | +| value_loss | 0.000656 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.306 | +| time/ | | +| fps | 310 | +| iterations | 1080 | +| time_elapsed | 3560 | +| total_timesteps | 1105920 | +| train/ | | +| approx_kl | 2.6370692 | +| clip_fraction | 0.456 | +| clip_range | 0.2 | +| entropy_loss | -0.354 | +| explained_variance | -0.973 | +| learning_rate | 0.0001 | +| loss | -0.0484 | +| n_updates | 71320 | +| policy_gradient_loss | -0.0653 | +| value_loss | 0.000869 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 310 | +| iterations | 1081 | +| time_elapsed | 3564 | +| total_timesteps | 1106944 | +| train/ | | +| approx_kl | 2.2128549 | +| clip_fraction | 0.455 | +| clip_range | 0.2 | +| entropy_loss | -0.309 | +| explained_variance | -1.84 | +| learning_rate | 0.0001 | +| loss | -0.0771 | +| n_updates | 71330 | +| policy_gradient_loss | -0.068 | +| value_loss | 0.0006 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 310 | +| iterations | 1082 | +| time_elapsed | 3567 | +| total_timesteps | 1107968 | +| train/ | | +| approx_kl | 1.9423808 | +| clip_fraction | 0.484 | +| clip_range | 0.2 | +| entropy_loss | -0.386 | +| explained_variance | -1.17 | +| learning_rate | 0.0001 | +| loss | -0.0577 | +| n_updates | 71340 | +| policy_gradient_loss | -0.0582 | +| value_loss | 0.000509 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 310 | +| iterations | 1083 | +| time_elapsed | 3570 | +| total_timesteps | 1108992 | +| train/ | | +| approx_kl | 2.897096 | +| clip_fraction | 0.478 | +| clip_range | 0.2 | +| entropy_loss | -0.349 | +| explained_variance | -4.92 | +| learning_rate | 0.0001 | +| loss | -0.0878 | +| n_updates | 71350 | +| policy_gradient_loss | -0.0688 | +| value_loss | 0.000444 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 310 | +| iterations | 1084 | +| time_elapsed | 3573 | +| total_timesteps | 1110016 | +| train/ | | +| approx_kl | 2.2169704 | +| clip_fraction | 0.494 | +| clip_range | 0.2 | +| entropy_loss | -0.408 | +| explained_variance | -0.37 | +| learning_rate | 0.0001 | +| loss | -0.0842 | +| n_updates | 71360 | +| policy_gradient_loss | -0.0614 | +| value_loss | 0.000391 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 310 | +| iterations | 1085 | +| time_elapsed | 3576 | +| total_timesteps | 1111040 | +| train/ | | +| approx_kl | 2.6298583 | +| clip_fraction | 0.464 | +| clip_range | 0.2 | +| entropy_loss | -0.332 | +| explained_variance | -2.79 | +| learning_rate | 0.0001 | +| loss | -0.0771 | +| n_updates | 71370 | +| policy_gradient_loss | -0.0661 | +| value_loss | 0.000477 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 310 | +| iterations | 1086 | +| time_elapsed | 3579 | +| total_timesteps | 1112064 | +| train/ | | +| approx_kl | 2.3799 | +| clip_fraction | 0.448 | +| clip_range | 0.2 | +| entropy_loss | -0.331 | +| explained_variance | -1.3 | +| learning_rate | 0.0001 | +| loss | -0.0976 | +| n_updates | 71380 | +| policy_gradient_loss | -0.0633 | +| value_loss | 0.000509 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 310 | +| iterations | 1087 | +| time_elapsed | 3583 | +| total_timesteps | 1113088 | +| train/ | | +| approx_kl | 2.0660267 | +| clip_fraction | 0.513 | +| clip_range | 0.2 | +| entropy_loss | -0.436 | +| explained_variance | -3.49 | +| learning_rate | 0.0001 | +| loss | -0.0955 | +| n_updates | 71390 | +| policy_gradient_loss | -0.0683 | +| value_loss | 0.000639 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 310 | +| iterations | 1088 | +| time_elapsed | 3586 | +| total_timesteps | 1114112 | +| train/ | | +| approx_kl | 2.5837443 | +| clip_fraction | 0.44 | +| clip_range | 0.2 | +| entropy_loss | -0.322 | +| explained_variance | -1.46 | +| learning_rate | 0.0001 | +| loss | -0.0793 | +| n_updates | 71400 | +| policy_gradient_loss | -0.0646 | +| value_loss | 0.000512 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 310 | +| iterations | 1089 | +| time_elapsed | 3590 | +| total_timesteps | 1115136 | +| train/ | | +| approx_kl | 3.2700183 | +| clip_fraction | 0.516 | +| clip_range | 0.2 | +| entropy_loss | -0.396 | +| explained_variance | -0.558 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 71410 | +| policy_gradient_loss | -0.0598 | +| value_loss | 0.000818 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 310 | +| iterations | 1090 | +| time_elapsed | 3593 | +| total_timesteps | 1116160 | +| train/ | | +| approx_kl | 2.0422277 | +| clip_fraction | 0.482 | +| clip_range | 0.2 | +| entropy_loss | -0.416 | +| explained_variance | -1.25 | +| learning_rate | 0.0001 | +| loss | -0.0168 | +| n_updates | 71420 | +| policy_gradient_loss | -0.0653 | +| value_loss | 0.000824 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 310 | +| iterations | 1091 | +| time_elapsed | 3597 | +| total_timesteps | 1117184 | +| train/ | | +| approx_kl | 2.3221233 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.426 | +| explained_variance | -2.12 | +| learning_rate | 0.0001 | +| loss | -0.0783 | +| n_updates | 71430 | +| policy_gradient_loss | -0.0696 | +| value_loss | 0.000614 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 310 | +| iterations | 1092 | +| time_elapsed | 3600 | +| total_timesteps | 1118208 | +| train/ | | +| approx_kl | 2.4277706 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.327 | +| explained_variance | -1.99 | +| learning_rate | 0.0001 | +| loss | -0.0946 | +| n_updates | 71440 | +| policy_gradient_loss | -0.0665 | +| value_loss | 0.0005 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 310 | +| iterations | 1093 | +| time_elapsed | 3604 | +| total_timesteps | 1119232 | +| train/ | | +| approx_kl | 2.3182263 | +| clip_fraction | 0.464 | +| clip_range | 0.2 | +| entropy_loss | -0.338 | +| explained_variance | -0.594 | +| learning_rate | 0.0001 | +| loss | -0.0908 | +| n_updates | 71450 | +| policy_gradient_loss | -0.0666 | +| value_loss | 0.000568 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 310 | +| iterations | 1094 | +| time_elapsed | 3607 | +| total_timesteps | 1120256 | +| train/ | | +| approx_kl | 3.9309537 | +| clip_fraction | 0.466 | +| clip_range | 0.2 | +| entropy_loss | -0.328 | +| explained_variance | -3.3 | +| learning_rate | 0.0001 | +| loss | -0.114 | +| n_updates | 71460 | +| policy_gradient_loss | -0.0745 | +| value_loss | 0.000583 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 310 | +| iterations | 1095 | +| time_elapsed | 3610 | +| total_timesteps | 1121280 | +| train/ | | +| approx_kl | 2.091602 | +| clip_fraction | 0.468 | +| clip_range | 0.2 | +| entropy_loss | -0.338 | +| explained_variance | -0.954 | +| learning_rate | 0.0001 | +| loss | -0.0892 | +| n_updates | 71470 | +| policy_gradient_loss | -0.0668 | +| value_loss | 0.000485 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.82e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 310 | +| iterations | 1096 | +| time_elapsed | 3613 | +| total_timesteps | 1122304 | +| train/ | | +| approx_kl | 2.4908972 | +| clip_fraction | 0.464 | +| clip_range | 0.2 | +| entropy_loss | -0.334 | +| explained_variance | -2.7 | +| learning_rate | 0.0001 | +| loss | -0.092 | +| n_updates | 71480 | +| policy_gradient_loss | -0.0695 | +| value_loss | 0.00051 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.81e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 310 | +| iterations | 1097 | +| time_elapsed | 3617 | +| total_timesteps | 1123328 | +| train/ | | +| approx_kl | 2.1370182 | +| clip_fraction | 0.452 | +| clip_range | 0.2 | +| entropy_loss | -0.331 | +| explained_variance | -1.21 | +| learning_rate | 0.0001 | +| loss | -0.0796 | +| n_updates | 71490 | +| policy_gradient_loss | -0.0588 | +| value_loss | 0.000468 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.81e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 310 | +| iterations | 1098 | +| time_elapsed | 3620 | +| total_timesteps | 1124352 | +| train/ | | +| approx_kl | 1.9667568 | +| clip_fraction | 0.456 | +| clip_range | 0.2 | +| entropy_loss | -0.355 | +| explained_variance | -0.935 | +| learning_rate | 0.0001 | +| loss | -0.0851 | +| n_updates | 71500 | +| policy_gradient_loss | -0.0668 | +| value_loss | 0.000419 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.81e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 310 | +| iterations | 1099 | +| time_elapsed | 3623 | +| total_timesteps | 1125376 | +| train/ | | +| approx_kl | 2.2910385 | +| clip_fraction | 0.445 | +| clip_range | 0.2 | +| entropy_loss | -0.338 | +| explained_variance | -3.04 | +| learning_rate | 0.0001 | +| loss | 0.0437 | +| n_updates | 71510 | +| policy_gradient_loss | -0.065 | +| value_loss | 0.000673 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.82e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 310 | +| iterations | 1100 | +| time_elapsed | 3626 | +| total_timesteps | 1126400 | +| train/ | | +| approx_kl | 2.640242 | +| clip_fraction | 0.486 | +| clip_range | 0.2 | +| entropy_loss | -0.349 | +| explained_variance | -2.73 | +| learning_rate | 0.0001 | +| loss | -0.108 | +| n_updates | 71520 | +| policy_gradient_loss | -0.0725 | +| value_loss | 0.000356 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.82e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 310 | +| iterations | 1101 | +| time_elapsed | 3630 | +| total_timesteps | 1127424 | +| train/ | | +| approx_kl | 2.4819946 | +| clip_fraction | 0.452 | +| clip_range | 0.2 | +| entropy_loss | -0.341 | +| explained_variance | -1.26 | +| learning_rate | 0.0001 | +| loss | -0.111 | +| n_updates | 71530 | +| policy_gradient_loss | -0.0692 | +| value_loss | 0.000431 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.82e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 310 | +| iterations | 1102 | +| time_elapsed | 3633 | +| total_timesteps | 1128448 | +| train/ | | +| approx_kl | 2.3779616 | +| clip_fraction | 0.491 | +| clip_range | 0.2 | +| entropy_loss | -0.386 | +| explained_variance | -1.6 | +| learning_rate | 0.0001 | +| loss | -0.0978 | +| n_updates | 71540 | +| policy_gradient_loss | -0.0712 | +| value_loss | 0.000413 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 310 | +| iterations | 1103 | +| time_elapsed | 3636 | +| total_timesteps | 1129472 | +| train/ | | +| approx_kl | 2.2994645 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.355 | +| explained_variance | -7.62 | +| learning_rate | 0.0001 | +| loss | -0.105 | +| n_updates | 71550 | +| policy_gradient_loss | -0.0756 | +| value_loss | 0.000394 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 310 | +| iterations | 1104 | +| time_elapsed | 3639 | +| total_timesteps | 1130496 | +| train/ | | +| approx_kl | 4.135197 | +| clip_fraction | 0.496 | +| clip_range | 0.2 | +| entropy_loss | -0.419 | +| explained_variance | -1.26 | +| learning_rate | 0.0001 | +| loss | -0.109 | +| n_updates | 71560 | +| policy_gradient_loss | -0.072 | +| value_loss | 0.000387 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 310 | +| iterations | 1105 | +| time_elapsed | 3642 | +| total_timesteps | 1131520 | +| train/ | | +| approx_kl | 2.33146 | +| clip_fraction | 0.503 | +| clip_range | 0.2 | +| entropy_loss | -0.389 | +| explained_variance | -5.06 | +| learning_rate | 0.0001 | +| loss | -0.106 | +| n_updates | 71570 | +| policy_gradient_loss | -0.0717 | +| value_loss | 0.000286 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 310 | +| iterations | 1106 | +| time_elapsed | 3646 | +| total_timesteps | 1132544 | +| train/ | | +| approx_kl | 2.274624 | +| clip_fraction | 0.472 | +| clip_range | 0.2 | +| entropy_loss | -0.351 | +| explained_variance | -1.32 | +| learning_rate | 0.0001 | +| loss | -0.096 | +| n_updates | 71580 | +| policy_gradient_loss | -0.0719 | +| value_loss | 0.000485 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 310 | +| iterations | 1107 | +| time_elapsed | 3649 | +| total_timesteps | 1133568 | +| train/ | | +| approx_kl | 2.4859416 | +| clip_fraction | 0.522 | +| clip_range | 0.2 | +| entropy_loss | -0.462 | +| explained_variance | -1.25 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 71590 | +| policy_gradient_loss | -0.0738 | +| value_loss | 0.000432 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 310 | +| iterations | 1108 | +| time_elapsed | 3653 | +| total_timesteps | 1134592 | +| train/ | | +| approx_kl | 2.758679 | +| clip_fraction | 0.454 | +| clip_range | 0.2 | +| entropy_loss | -0.39 | +| explained_variance | -1.31 | +| learning_rate | 0.0001 | +| loss | -0.0752 | +| n_updates | 71600 | +| policy_gradient_loss | -0.0624 | +| value_loss | 0.00043 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 310 | +| iterations | 1109 | +| time_elapsed | 3656 | +| total_timesteps | 1135616 | +| train/ | | +| approx_kl | 1.8917992 | +| clip_fraction | 0.496 | +| clip_range | 0.2 | +| entropy_loss | -0.386 | +| explained_variance | -1.28 | +| learning_rate | 0.0001 | +| loss | -0.0891 | +| n_updates | 71610 | +| policy_gradient_loss | -0.0733 | +| value_loss | 0.000527 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 310 | +| iterations | 1110 | +| time_elapsed | 3659 | +| total_timesteps | 1136640 | +| train/ | | +| approx_kl | 2.234106 | +| clip_fraction | 0.446 | +| clip_range | 0.2 | +| entropy_loss | -0.339 | +| explained_variance | -1.5 | +| learning_rate | 0.0001 | +| loss | -0.091 | +| n_updates | 71620 | +| policy_gradient_loss | -0.0656 | +| value_loss | 0.000498 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 310 | +| iterations | 1111 | +| time_elapsed | 3663 | +| total_timesteps | 1137664 | +| train/ | | +| approx_kl | 1.8865321 | +| clip_fraction | 0.469 | +| clip_range | 0.2 | +| entropy_loss | -0.376 | +| explained_variance | -2.01 | +| learning_rate | 0.0001 | +| loss | -0.0902 | +| n_updates | 71630 | +| policy_gradient_loss | -0.0672 | +| value_loss | 0.000373 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 310 | +| iterations | 1112 | +| time_elapsed | 3666 | +| total_timesteps | 1138688 | +| train/ | | +| approx_kl | 3.5964847 | +| clip_fraction | 0.499 | +| clip_range | 0.2 | +| entropy_loss | -0.421 | +| explained_variance | -0.714 | +| learning_rate | 0.0001 | +| loss | -0.0795 | +| n_updates | 71640 | +| policy_gradient_loss | -0.0683 | +| value_loss | 0.000579 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 310 | +| iterations | 1113 | +| time_elapsed | 3669 | +| total_timesteps | 1139712 | +| train/ | | +| approx_kl | 4.8989434 | +| clip_fraction | 0.497 | +| clip_range | 0.2 | +| entropy_loss | -0.417 | +| explained_variance | -7.92 | +| learning_rate | 0.0001 | +| loss | -0.0879 | +| n_updates | 71650 | +| policy_gradient_loss | -0.0782 | +| value_loss | 0.000501 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 310 | +| iterations | 1114 | +| time_elapsed | 3672 | +| total_timesteps | 1140736 | +| train/ | | +| approx_kl | 2.5465872 | +| clip_fraction | 0.477 | +| clip_range | 0.2 | +| entropy_loss | -0.389 | +| explained_variance | -2.69 | +| learning_rate | 0.0001 | +| loss | -0.0844 | +| n_updates | 71660 | +| policy_gradient_loss | -0.0606 | +| value_loss | 0.000226 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 310 | +| iterations | 1115 | +| time_elapsed | 3676 | +| total_timesteps | 1141760 | +| train/ | | +| approx_kl | 2.105359 | +| clip_fraction | 0.5 | +| clip_range | 0.2 | +| entropy_loss | -0.426 | +| explained_variance | -0.878 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 71670 | +| policy_gradient_loss | -0.0672 | +| value_loss | 0.000502 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 310 | +| iterations | 1116 | +| time_elapsed | 3679 | +| total_timesteps | 1142784 | +| train/ | | +| approx_kl | 2.1140323 | +| clip_fraction | 0.455 | +| clip_range | 0.2 | +| entropy_loss | -0.364 | +| explained_variance | -2.65 | +| learning_rate | 0.0001 | +| loss | -0.082 | +| n_updates | 71680 | +| policy_gradient_loss | -0.07 | +| value_loss | 0.000373 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 310 | +| iterations | 1117 | +| time_elapsed | 3682 | +| total_timesteps | 1143808 | +| train/ | | +| approx_kl | 2.1082506 | +| clip_fraction | 0.527 | +| clip_range | 0.2 | +| entropy_loss | -0.481 | +| explained_variance | -0.671 | +| learning_rate | 0.0001 | +| loss | -0.107 | +| n_updates | 71690 | +| policy_gradient_loss | -0.0753 | +| value_loss | 0.000489 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 310 | +| iterations | 1118 | +| time_elapsed | 3685 | +| total_timesteps | 1144832 | +| train/ | | +| approx_kl | 2.6114893 | +| clip_fraction | 0.522 | +| clip_range | 0.2 | +| entropy_loss | -0.421 | +| explained_variance | -1.4 | +| learning_rate | 0.0001 | +| loss | -0.107 | +| n_updates | 71700 | +| policy_gradient_loss | -0.0724 | +| value_loss | 0.000569 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 310 | +| iterations | 1119 | +| time_elapsed | 3688 | +| total_timesteps | 1145856 | +| train/ | | +| approx_kl | 1.833044 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.421 | +| explained_variance | -1.34 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 71710 | +| policy_gradient_loss | -0.0692 | +| value_loss | 0.000585 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 310 | +| iterations | 1120 | +| time_elapsed | 3691 | +| total_timesteps | 1146880 | +| train/ | | +| approx_kl | 2.1633677 | +| clip_fraction | 0.486 | +| clip_range | 0.2 | +| entropy_loss | -0.361 | +| explained_variance | -1.09 | +| learning_rate | 0.0001 | +| loss | -0.0849 | +| n_updates | 71720 | +| policy_gradient_loss | -0.0648 | +| value_loss | 0.000654 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 310 | +| iterations | 1121 | +| time_elapsed | 3694 | +| total_timesteps | 1147904 | +| train/ | | +| approx_kl | 1.8618858 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.389 | +| explained_variance | -2.4 | +| learning_rate | 0.0001 | +| loss | -0.0766 | +| n_updates | 71730 | +| policy_gradient_loss | -0.0728 | +| value_loss | 0.000563 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 310 | +| iterations | 1122 | +| time_elapsed | 3698 | +| total_timesteps | 1148928 | +| train/ | | +| approx_kl | 2.0815685 | +| clip_fraction | 0.464 | +| clip_range | 0.2 | +| entropy_loss | -0.357 | +| explained_variance | -0.956 | +| learning_rate | 0.0001 | +| loss | -0.0751 | +| n_updates | 71740 | +| policy_gradient_loss | -0.0743 | +| value_loss | 0.000466 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 310 | +| iterations | 1123 | +| time_elapsed | 3701 | +| total_timesteps | 1149952 | +| train/ | | +| approx_kl | 5.595582 | +| clip_fraction | 0.461 | +| clip_range | 0.2 | +| entropy_loss | -0.343 | +| explained_variance | -1.93 | +| learning_rate | 0.0001 | +| loss | -0.0773 | +| n_updates | 71750 | +| policy_gradient_loss | -0.0663 | +| value_loss | 0.000668 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 310 | +| iterations | 1124 | +| time_elapsed | 3705 | +| total_timesteps | 1150976 | +| train/ | | +| approx_kl | 2.4689493 | +| clip_fraction | 0.451 | +| clip_range | 0.2 | +| entropy_loss | -0.346 | +| explained_variance | -1.73 | +| learning_rate | 0.0001 | +| loss | -0.0873 | +| n_updates | 71760 | +| policy_gradient_loss | -0.0652 | +| value_loss | 0.000396 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 310 | +| iterations | 1125 | +| time_elapsed | 3708 | +| total_timesteps | 1152000 | +| train/ | | +| approx_kl | 2.063533 | +| clip_fraction | 0.498 | +| clip_range | 0.2 | +| entropy_loss | -0.392 | +| explained_variance | -2.06 | +| learning_rate | 0.0001 | +| loss | -0.109 | +| n_updates | 71770 | +| policy_gradient_loss | -0.0738 | +| value_loss | 0.000284 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 310 | +| iterations | 1126 | +| time_elapsed | 3712 | +| total_timesteps | 1153024 | +| train/ | | +| approx_kl | 2.2607834 | +| clip_fraction | 0.504 | +| clip_range | 0.2 | +| entropy_loss | -0.368 | +| explained_variance | -0.483 | +| learning_rate | 0.0001 | +| loss | -0.074 | +| n_updates | 71780 | +| policy_gradient_loss | -0.0718 | +| value_loss | 0.000511 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 310 | +| iterations | 1127 | +| time_elapsed | 3715 | +| total_timesteps | 1154048 | +| train/ | | +| approx_kl | 2.2164793 | +| clip_fraction | 0.5 | +| clip_range | 0.2 | +| entropy_loss | -0.371 | +| explained_variance | -1.51 | +| learning_rate | 0.0001 | +| loss | -0.0954 | +| n_updates | 71790 | +| policy_gradient_loss | -0.0681 | +| value_loss | 0.000482 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 310 | +| iterations | 1128 | +| time_elapsed | 3719 | +| total_timesteps | 1155072 | +| train/ | | +| approx_kl | 2.1831317 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.398 | +| explained_variance | -1.63 | +| learning_rate | 0.0001 | +| loss | -0.0799 | +| n_updates | 71800 | +| policy_gradient_loss | -0.0576 | +| value_loss | 0.000417 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 310 | +| iterations | 1129 | +| time_elapsed | 3722 | +| total_timesteps | 1156096 | +| train/ | | +| approx_kl | 2.0436873 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.398 | +| explained_variance | -2.38 | +| learning_rate | 0.0001 | +| loss | -0.113 | +| n_updates | 71810 | +| policy_gradient_loss | -0.0663 | +| value_loss | 0.000302 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 310 | +| iterations | 1130 | +| time_elapsed | 3726 | +| total_timesteps | 1157120 | +| train/ | | +| approx_kl | 29.878576 | +| clip_fraction | 0.477 | +| clip_range | 0.2 | +| entropy_loss | -0.402 | +| explained_variance | -0.627 | +| learning_rate | 0.0001 | +| loss | -0.0724 | +| n_updates | 71820 | +| policy_gradient_loss | -0.0633 | +| value_loss | 0.000514 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 310 | +| iterations | 1131 | +| time_elapsed | 3730 | +| total_timesteps | 1158144 | +| train/ | | +| approx_kl | 2.1049955 | +| clip_fraction | 0.463 | +| clip_range | 0.2 | +| entropy_loss | -0.333 | +| explained_variance | -1.72 | +| learning_rate | 0.0001 | +| loss | -0.0598 | +| n_updates | 71830 | +| policy_gradient_loss | -0.0647 | +| value_loss | 0.000665 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 310 | +| iterations | 1132 | +| time_elapsed | 3733 | +| total_timesteps | 1159168 | +| train/ | | +| approx_kl | 2.38838 | +| clip_fraction | 0.509 | +| clip_range | 0.2 | +| entropy_loss | -0.396 | +| explained_variance | -0.812 | +| learning_rate | 0.0001 | +| loss | -0.0702 | +| n_updates | 71840 | +| policy_gradient_loss | -0.068 | +| value_loss | 0.000689 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 310 | +| iterations | 1133 | +| time_elapsed | 3736 | +| total_timesteps | 1160192 | +| train/ | | +| approx_kl | 2.3778539 | +| clip_fraction | 0.474 | +| clip_range | 0.2 | +| entropy_loss | -0.334 | +| explained_variance | -2.75 | +| learning_rate | 0.0001 | +| loss | -0.0802 | +| n_updates | 71850 | +| policy_gradient_loss | -0.0632 | +| value_loss | 0.000497 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 310 | +| iterations | 1134 | +| time_elapsed | 3739 | +| total_timesteps | 1161216 | +| train/ | | +| approx_kl | 1.8722115 | +| clip_fraction | 0.495 | +| clip_range | 0.2 | +| entropy_loss | -0.38 | +| explained_variance | -0.947 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 71860 | +| policy_gradient_loss | -0.0723 | +| value_loss | 0.000552 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 310 | +| iterations | 1135 | +| time_elapsed | 3742 | +| total_timesteps | 1162240 | +| train/ | | +| approx_kl | 2.277894 | +| clip_fraction | 0.484 | +| clip_range | 0.2 | +| entropy_loss | -0.37 | +| explained_variance | -1.76 | +| learning_rate | 0.0001 | +| loss | -0.0722 | +| n_updates | 71870 | +| policy_gradient_loss | -0.0709 | +| value_loss | 0.000619 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 310 | +| iterations | 1136 | +| time_elapsed | 3745 | +| total_timesteps | 1163264 | +| train/ | | +| approx_kl | 2.030767 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.347 | +| explained_variance | -0.55 | +| learning_rate | 0.0001 | +| loss | -0.107 | +| n_updates | 71880 | +| policy_gradient_loss | -0.0636 | +| value_loss | 0.000808 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 310 | +| iterations | 1137 | +| time_elapsed | 3749 | +| total_timesteps | 1164288 | +| train/ | | +| approx_kl | 2.826232 | +| clip_fraction | 0.495 | +| clip_range | 0.2 | +| entropy_loss | -0.389 | +| explained_variance | -1.34 | +| learning_rate | 0.0001 | +| loss | -0.0968 | +| n_updates | 71890 | +| policy_gradient_loss | -0.073 | +| value_loss | 0.000598 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 310 | +| iterations | 1138 | +| time_elapsed | 3752 | +| total_timesteps | 1165312 | +| train/ | | +| approx_kl | 4.992343 | +| clip_fraction | 0.451 | +| clip_range | 0.2 | +| entropy_loss | -0.317 | +| explained_variance | -2.03 | +| learning_rate | 0.0001 | +| loss | -0.0736 | +| n_updates | 71900 | +| policy_gradient_loss | -0.0681 | +| value_loss | 0.000721 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 310 | +| iterations | 1139 | +| time_elapsed | 3755 | +| total_timesteps | 1166336 | +| train/ | | +| approx_kl | 2.2924116 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.373 | +| explained_variance | -0.546 | +| learning_rate | 0.0001 | +| loss | -0.0994 | +| n_updates | 71910 | +| policy_gradient_loss | -0.0673 | +| value_loss | 0.000664 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 310 | +| iterations | 1140 | +| time_elapsed | 3758 | +| total_timesteps | 1167360 | +| train/ | | +| approx_kl | 2.030113 | +| clip_fraction | 0.462 | +| clip_range | 0.2 | +| entropy_loss | -0.347 | +| explained_variance | -3.67 | +| learning_rate | 0.0001 | +| loss | -0.0987 | +| n_updates | 71920 | +| policy_gradient_loss | -0.0731 | +| value_loss | 0.000706 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 310 | +| iterations | 1141 | +| time_elapsed | 3761 | +| total_timesteps | 1168384 | +| train/ | | +| approx_kl | 2.9834394 | +| clip_fraction | 0.474 | +| clip_range | 0.2 | +| entropy_loss | -0.332 | +| explained_variance | -1.05 | +| learning_rate | 0.0001 | +| loss | -0.0915 | +| n_updates | 71930 | +| policy_gradient_loss | -0.0726 | +| value_loss | 0.000668 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 310 | +| iterations | 1142 | +| time_elapsed | 3765 | +| total_timesteps | 1169408 | +| train/ | | +| approx_kl | 2.1406815 | +| clip_fraction | 0.479 | +| clip_range | 0.2 | +| entropy_loss | -0.363 | +| explained_variance | -2.27 | +| learning_rate | 0.0001 | +| loss | -0.088 | +| n_updates | 71940 | +| policy_gradient_loss | -0.0758 | +| value_loss | 0.000596 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 310 | +| iterations | 1143 | +| time_elapsed | 3768 | +| total_timesteps | 1170432 | +| train/ | | +| approx_kl | 2.3493946 | +| clip_fraction | 0.495 | +| clip_range | 0.2 | +| entropy_loss | -0.41 | +| explained_variance | -2.47 | +| learning_rate | 0.0001 | +| loss | -0.0897 | +| n_updates | 71950 | +| policy_gradient_loss | -0.0716 | +| value_loss | 0.00047 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 310 | +| iterations | 1144 | +| time_elapsed | 3771 | +| total_timesteps | 1171456 | +| train/ | | +| approx_kl | 2.7116597 | +| clip_fraction | 0.489 | +| clip_range | 0.2 | +| entropy_loss | -0.344 | +| explained_variance | -1.18 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 71960 | +| policy_gradient_loss | -0.075 | +| value_loss | 0.00064 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 310 | +| iterations | 1145 | +| time_elapsed | 3775 | +| total_timesteps | 1172480 | +| train/ | | +| approx_kl | 2.9082193 | +| clip_fraction | 0.486 | +| clip_range | 0.2 | +| entropy_loss | -0.35 | +| explained_variance | -1.53 | +| learning_rate | 0.0001 | +| loss | -0.0941 | +| n_updates | 71970 | +| policy_gradient_loss | -0.0691 | +| value_loss | 0.00064 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 310 | +| iterations | 1146 | +| time_elapsed | 3778 | +| total_timesteps | 1173504 | +| train/ | | +| approx_kl | 2.3524733 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.336 | +| explained_variance | -1.24 | +| learning_rate | 0.0001 | +| loss | -0.0999 | +| n_updates | 71980 | +| policy_gradient_loss | -0.0699 | +| value_loss | 0.000472 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 310 | +| iterations | 1147 | +| time_elapsed | 3782 | +| total_timesteps | 1174528 | +| train/ | | +| approx_kl | 2.2762628 | +| clip_fraction | 0.495 | +| clip_range | 0.2 | +| entropy_loss | -0.381 | +| explained_variance | -0.774 | +| learning_rate | 0.0001 | +| loss | -0.0941 | +| n_updates | 71990 | +| policy_gradient_loss | -0.0695 | +| value_loss | 0.00055 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 310 | +| iterations | 1148 | +| time_elapsed | 3785 | +| total_timesteps | 1175552 | +| train/ | | +| approx_kl | 2.1936677 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.402 | +| explained_variance | -1.64 | +| learning_rate | 0.0001 | +| loss | -0.0846 | +| n_updates | 72000 | +| policy_gradient_loss | -0.0678 | +| value_loss | 0.000506 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 310 | +| iterations | 1149 | +| time_elapsed | 3788 | +| total_timesteps | 1176576 | +| train/ | | +| approx_kl | 2.236851 | +| clip_fraction | 0.492 | +| clip_range | 0.2 | +| entropy_loss | -0.345 | +| explained_variance | -1.3 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 72010 | +| policy_gradient_loss | -0.0763 | +| value_loss | 0.000511 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 310 | +| iterations | 1150 | +| time_elapsed | 3791 | +| total_timesteps | 1177600 | +| train/ | | +| approx_kl | 2.3544245 | +| clip_fraction | 0.478 | +| clip_range | 0.2 | +| entropy_loss | -0.358 | +| explained_variance | -1.47 | +| learning_rate | 0.0001 | +| loss | -0.0844 | +| n_updates | 72020 | +| policy_gradient_loss | -0.0679 | +| value_loss | 0.000438 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 310 | +| iterations | 1151 | +| time_elapsed | 3795 | +| total_timesteps | 1178624 | +| train/ | | +| approx_kl | 13.551728 | +| clip_fraction | 0.46 | +| clip_range | 0.2 | +| entropy_loss | -0.318 | +| explained_variance | -2.15 | +| learning_rate | 0.0001 | +| loss | -0.078 | +| n_updates | 72030 | +| policy_gradient_loss | -0.0675 | +| value_loss | 0.000668 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 310 | +| iterations | 1152 | +| time_elapsed | 3798 | +| total_timesteps | 1179648 | +| train/ | | +| approx_kl | 2.227716 | +| clip_fraction | 0.472 | +| clip_range | 0.2 | +| entropy_loss | -0.342 | +| explained_variance | -9.87 | +| learning_rate | 0.0001 | +| loss | -0.107 | +| n_updates | 72040 | +| policy_gradient_loss | -0.0712 | +| value_loss | 0.000186 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 310 | +| iterations | 1153 | +| time_elapsed | 3801 | +| total_timesteps | 1180672 | +| train/ | | +| approx_kl | 4.5639844 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.363 | +| explained_variance | -0.716 | +| learning_rate | 0.0001 | +| loss | -0.0825 | +| n_updates | 72050 | +| policy_gradient_loss | -0.0613 | +| value_loss | 0.000261 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 310 | +| iterations | 1154 | +| time_elapsed | 3804 | +| total_timesteps | 1181696 | +| train/ | | +| approx_kl | 3.124446 | +| clip_fraction | 0.463 | +| clip_range | 0.2 | +| entropy_loss | -0.353 | +| explained_variance | -2.09 | +| learning_rate | 0.0001 | +| loss | -0.11 | +| n_updates | 72060 | +| policy_gradient_loss | -0.0634 | +| value_loss | 0.000392 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 310 | +| iterations | 1155 | +| time_elapsed | 3807 | +| total_timesteps | 1182720 | +| train/ | | +| approx_kl | 2.385446 | +| clip_fraction | 0.506 | +| clip_range | 0.2 | +| entropy_loss | -0.42 | +| explained_variance | -0.682 | +| learning_rate | 0.0001 | +| loss | -0.0878 | +| n_updates | 72070 | +| policy_gradient_loss | -0.0708 | +| value_loss | 0.000451 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 310 | +| iterations | 1156 | +| time_elapsed | 3810 | +| total_timesteps | 1183744 | +| train/ | | +| approx_kl | 3.4134283 | +| clip_fraction | 0.47 | +| clip_range | 0.2 | +| entropy_loss | -0.342 | +| explained_variance | -0.341 | +| learning_rate | 0.0001 | +| loss | -0.0823 | +| n_updates | 72080 | +| policy_gradient_loss | -0.0615 | +| value_loss | 0.000882 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 310 | +| iterations | 1157 | +| time_elapsed | 3813 | +| total_timesteps | 1184768 | +| train/ | | +| approx_kl | 1.8549 | +| clip_fraction | 0.464 | +| clip_range | 0.2 | +| entropy_loss | -0.375 | +| explained_variance | -1.77 | +| learning_rate | 0.0001 | +| loss | -0.0839 | +| n_updates | 72090 | +| policy_gradient_loss | -0.0665 | +| value_loss | 0.000553 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 310 | +| iterations | 1158 | +| time_elapsed | 3817 | +| total_timesteps | 1185792 | +| train/ | | +| approx_kl | 2.5052075 | +| clip_fraction | 0.479 | +| clip_range | 0.2 | +| entropy_loss | -0.369 | +| explained_variance | -1.48 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 72100 | +| policy_gradient_loss | -0.0672 | +| value_loss | 0.000675 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 310 | +| iterations | 1159 | +| time_elapsed | 3820 | +| total_timesteps | 1186816 | +| train/ | | +| approx_kl | 2.1322699 | +| clip_fraction | 0.409 | +| clip_range | 0.2 | +| entropy_loss | -0.282 | +| explained_variance | -2.09 | +| learning_rate | 0.0001 | +| loss | -0.0759 | +| n_updates | 72110 | +| policy_gradient_loss | -0.0672 | +| value_loss | 0.000611 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 310 | +| iterations | 1160 | +| time_elapsed | 3823 | +| total_timesteps | 1187840 | +| train/ | | +| approx_kl | 2.3011293 | +| clip_fraction | 0.497 | +| clip_range | 0.2 | +| entropy_loss | -0.386 | +| explained_variance | -1.83 | +| learning_rate | 0.0001 | +| loss | -0.0827 | +| n_updates | 72120 | +| policy_gradient_loss | -0.0717 | +| value_loss | 0.000578 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 310 | +| iterations | 1161 | +| time_elapsed | 3827 | +| total_timesteps | 1188864 | +| train/ | | +| approx_kl | 2.995079 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.377 | +| explained_variance | -1.54 | +| learning_rate | 0.0001 | +| loss | -0.0969 | +| n_updates | 72130 | +| policy_gradient_loss | -0.0712 | +| value_loss | 0.000334 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 310 | +| iterations | 1162 | +| time_elapsed | 3831 | +| total_timesteps | 1189888 | +| train/ | | +| approx_kl | 2.3110826 | +| clip_fraction | 0.457 | +| clip_range | 0.2 | +| entropy_loss | -0.334 | +| explained_variance | -1.81 | +| learning_rate | 0.0001 | +| loss | -0.0862 | +| n_updates | 72140 | +| policy_gradient_loss | -0.0702 | +| value_loss | 0.000434 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 310 | +| iterations | 1163 | +| time_elapsed | 3834 | +| total_timesteps | 1190912 | +| train/ | | +| approx_kl | 2.30031 | +| clip_fraction | 0.503 | +| clip_range | 0.2 | +| entropy_loss | -0.393 | +| explained_variance | -1.86 | +| learning_rate | 0.0001 | +| loss | -0.0997 | +| n_updates | 72150 | +| policy_gradient_loss | -0.0678 | +| value_loss | 0.000353 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 310 | +| iterations | 1164 | +| time_elapsed | 3838 | +| total_timesteps | 1191936 | +| train/ | | +| approx_kl | 2.1876001 | +| clip_fraction | 0.476 | +| clip_range | 0.2 | +| entropy_loss | -0.388 | +| explained_variance | -2.21 | +| learning_rate | 0.0001 | +| loss | -0.0849 | +| n_updates | 72160 | +| policy_gradient_loss | -0.0677 | +| value_loss | 0.000458 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 310 | +| iterations | 1165 | +| time_elapsed | 3842 | +| total_timesteps | 1192960 | +| train/ | | +| approx_kl | 5.208439 | +| clip_fraction | 0.463 | +| clip_range | 0.2 | +| entropy_loss | -0.353 | +| explained_variance | -4.09 | +| learning_rate | 0.0001 | +| loss | -0.097 | +| n_updates | 72170 | +| policy_gradient_loss | -0.0715 | +| value_loss | 0.00047 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 310 | +| iterations | 1166 | +| time_elapsed | 3845 | +| total_timesteps | 1193984 | +| train/ | | +| approx_kl | 2.386118 | +| clip_fraction | 0.457 | +| clip_range | 0.2 | +| entropy_loss | -0.337 | +| explained_variance | -1.18 | +| learning_rate | 0.0001 | +| loss | -0.0919 | +| n_updates | 72180 | +| policy_gradient_loss | -0.0633 | +| value_loss | 0.000519 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 310 | +| iterations | 1167 | +| time_elapsed | 3849 | +| total_timesteps | 1195008 | +| train/ | | +| approx_kl | 2.4520707 | +| clip_fraction | 0.463 | +| clip_range | 0.2 | +| entropy_loss | -0.303 | +| explained_variance | -1.52 | +| learning_rate | 0.0001 | +| loss | -0.0888 | +| n_updates | 72190 | +| policy_gradient_loss | -0.0709 | +| value_loss | 0.000705 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 310 | +| iterations | 1168 | +| time_elapsed | 3852 | +| total_timesteps | 1196032 | +| train/ | | +| approx_kl | 2.3315217 | +| clip_fraction | 0.45 | +| clip_range | 0.2 | +| entropy_loss | -0.331 | +| explained_variance | -2.11 | +| learning_rate | 0.0001 | +| loss | -0.0811 | +| n_updates | 72200 | +| policy_gradient_loss | -0.0633 | +| value_loss | 0.000571 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 310 | +| iterations | 1169 | +| time_elapsed | 3855 | +| total_timesteps | 1197056 | +| train/ | | +| approx_kl | 2.2489634 | +| clip_fraction | 0.498 | +| clip_range | 0.2 | +| entropy_loss | -0.374 | +| explained_variance | -3.43 | +| learning_rate | 0.0001 | +| loss | -0.0953 | +| n_updates | 72210 | +| policy_gradient_loss | -0.0723 | +| value_loss | 0.000383 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 310 | +| iterations | 1170 | +| time_elapsed | 3858 | +| total_timesteps | 1198080 | +| train/ | | +| approx_kl | 2.253502 | +| clip_fraction | 0.458 | +| clip_range | 0.2 | +| entropy_loss | -0.359 | +| explained_variance | -1.24 | +| learning_rate | 0.0001 | +| loss | -0.0998 | +| n_updates | 72220 | +| policy_gradient_loss | -0.0641 | +| value_loss | 0.000383 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 310 | +| iterations | 1171 | +| time_elapsed | 3861 | +| total_timesteps | 1199104 | +| train/ | | +| approx_kl | 2.420652 | +| clip_fraction | 0.457 | +| clip_range | 0.2 | +| entropy_loss | -0.341 | +| explained_variance | -1.23 | +| learning_rate | 0.0001 | +| loss | -0.0998 | +| n_updates | 72230 | +| policy_gradient_loss | -0.0692 | +| value_loss | 0.000748 | +-------------------------------------- + +Current state: Champion.Level4.RyuVsZangief +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 310 | +| iterations | 1172 | +| time_elapsed | 3865 | +| total_timesteps | 1200128 | +| train/ | | +| approx_kl | 2.4810758 | +| clip_fraction | 0.495 | +| clip_range | 0.2 | +| entropy_loss | -0.389 | +| explained_variance | -2.99 | +| learning_rate | 0.0001 | +| loss | -0.0794 | +| n_updates | 72240 | +| policy_gradient_loss | -0.0727 | +| value_loss | 0.000636 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 310 | +| iterations | 1173 | +| time_elapsed | 3868 | +| total_timesteps | 1201152 | +| train/ | | +| approx_kl | 1.9230494 | +| clip_fraction | 0.477 | +| clip_range | 0.2 | +| entropy_loss | -0.413 | +| explained_variance | -0.659 | +| learning_rate | 0.0001 | +| loss | -0.0943 | +| n_updates | 72250 | +| policy_gradient_loss | -0.065 | +| value_loss | 0.000395 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 310 | +| iterations | 1174 | +| time_elapsed | 3871 | +| total_timesteps | 1202176 | +| train/ | | +| approx_kl | 1.6495962 | +| clip_fraction | 0.531 | +| clip_range | 0.2 | +| entropy_loss | -0.477 | +| explained_variance | -2.24 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 72260 | +| policy_gradient_loss | -0.0771 | +| value_loss | 0.000344 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 310 | +| iterations | 1175 | +| time_elapsed | 3874 | +| total_timesteps | 1203200 | +| train/ | | +| approx_kl | 2.5533352 | +| clip_fraction | 0.563 | +| clip_range | 0.2 | +| entropy_loss | -0.536 | +| explained_variance | -0.624 | +| learning_rate | 0.0001 | +| loss | -0.0184 | +| n_updates | 72270 | +| policy_gradient_loss | -0.0631 | +| value_loss | 0.00029 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 310 | +| iterations | 1176 | +| time_elapsed | 3877 | +| total_timesteps | 1204224 | +| train/ | | +| approx_kl | 1.8842044 | +| clip_fraction | 0.587 | +| clip_range | 0.2 | +| entropy_loss | -0.632 | +| explained_variance | -0.377 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 72280 | +| policy_gradient_loss | -0.0665 | +| value_loss | 0.000247 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 310 | +| iterations | 1177 | +| time_elapsed | 3881 | +| total_timesteps | 1205248 | +| train/ | | +| approx_kl | 2.2183871 | +| clip_fraction | 0.535 | +| clip_range | 0.2 | +| entropy_loss | -0.583 | +| explained_variance | -0.446 | +| learning_rate | 0.0001 | +| loss | -0.0756 | +| n_updates | 72290 | +| policy_gradient_loss | -0.056 | +| value_loss | 0.000245 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 310 | +| iterations | 1178 | +| time_elapsed | 3884 | +| total_timesteps | 1206272 | +| train/ | | +| approx_kl | 1.3304188 | +| clip_fraction | 0.545 | +| clip_range | 0.2 | +| entropy_loss | -0.594 | +| explained_variance | -0.664 | +| learning_rate | 0.0001 | +| loss | -0.105 | +| n_updates | 72300 | +| policy_gradient_loss | -0.0727 | +| value_loss | 0.00017 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 310 | +| iterations | 1179 | +| time_elapsed | 3888 | +| total_timesteps | 1207296 | +| train/ | | +| approx_kl | 1.9702661 | +| clip_fraction | 0.577 | +| clip_range | 0.2 | +| entropy_loss | -0.589 | +| explained_variance | -0.432 | +| learning_rate | 0.0001 | +| loss | -0.12 | +| n_updates | 72310 | +| policy_gradient_loss | -0.0771 | +| value_loss | 0.00026 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 310 | +| iterations | 1180 | +| time_elapsed | 3891 | +| total_timesteps | 1208320 | +| train/ | | +| approx_kl | 1.8900626 | +| clip_fraction | 0.538 | +| clip_range | 0.2 | +| entropy_loss | -0.485 | +| explained_variance | -3.61 | +| learning_rate | 0.0001 | +| loss | -0.122 | +| n_updates | 72320 | +| policy_gradient_loss | -0.0762 | +| value_loss | 0.000196 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 310 | +| iterations | 1181 | +| time_elapsed | 3894 | +| total_timesteps | 1209344 | +| train/ | | +| approx_kl | 2.3945847 | +| clip_fraction | 0.505 | +| clip_range | 0.2 | +| entropy_loss | -0.57 | +| explained_variance | -0.255 | +| learning_rate | 0.0001 | +| loss | 0.0746 | +| n_updates | 72330 | +| policy_gradient_loss | -0.0668 | +| value_loss | 0.000202 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 310 | +| iterations | 1182 | +| time_elapsed | 3898 | +| total_timesteps | 1210368 | +| train/ | | +| approx_kl | 1.7022176 | +| clip_fraction | 0.497 | +| clip_range | 0.2 | +| entropy_loss | -0.573 | +| explained_variance | -0.752 | +| learning_rate | 0.0001 | +| loss | -0.0853 | +| n_updates | 72340 | +| policy_gradient_loss | -0.0674 | +| value_loss | 0.00037 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 310 | +| iterations | 1183 | +| time_elapsed | 3901 | +| total_timesteps | 1211392 | +| train/ | | +| approx_kl | 1.3065214 | +| clip_fraction | 0.49 | +| clip_range | 0.2 | +| entropy_loss | -0.517 | +| explained_variance | -1.14 | +| learning_rate | 0.0001 | +| loss | -0.0721 | +| n_updates | 72350 | +| policy_gradient_loss | -0.0495 | +| value_loss | 0.000236 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 310 | +| iterations | 1184 | +| time_elapsed | 3905 | +| total_timesteps | 1212416 | +| train/ | | +| approx_kl | 1.4855962 | +| clip_fraction | 0.528 | +| clip_range | 0.2 | +| entropy_loss | -0.539 | +| explained_variance | -0.449 | +| learning_rate | 0.0001 | +| loss | -0.0907 | +| n_updates | 72360 | +| policy_gradient_loss | -0.0553 | +| value_loss | 0.000107 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 310 | +| iterations | 1185 | +| time_elapsed | 3908 | +| total_timesteps | 1213440 | +| train/ | | +| approx_kl | 1.2556963 | +| clip_fraction | 0.499 | +| clip_range | 0.2 | +| entropy_loss | -0.672 | +| explained_variance | -0.307 | +| learning_rate | 0.0001 | +| loss | -0.117 | +| n_updates | 72370 | +| policy_gradient_loss | -0.0589 | +| value_loss | 0.000125 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 310 | +| iterations | 1186 | +| time_elapsed | 3911 | +| total_timesteps | 1214464 | +| train/ | | +| approx_kl | 3.30238 | +| clip_fraction | 0.544 | +| clip_range | 0.2 | +| entropy_loss | -0.436 | +| explained_variance | -0.671 | +| learning_rate | 0.0001 | +| loss | -0.077 | +| n_updates | 72380 | +| policy_gradient_loss | -0.0678 | +| value_loss | 0.000531 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.82e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 310 | +| iterations | 1187 | +| time_elapsed | 3914 | +| total_timesteps | 1215488 | +| train/ | | +| approx_kl | 1.4880509 | +| clip_fraction | 0.547 | +| clip_range | 0.2 | +| entropy_loss | -0.612 | +| explained_variance | -2.89 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 72390 | +| policy_gradient_loss | -0.0644 | +| value_loss | 0.000353 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.81e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 310 | +| iterations | 1188 | +| time_elapsed | 3917 | +| total_timesteps | 1216512 | +| train/ | | +| approx_kl | 1.1782842 | +| clip_fraction | 0.524 | +| clip_range | 0.2 | +| entropy_loss | -0.581 | +| explained_variance | -0.422 | +| learning_rate | 0.0001 | +| loss | -0.0722 | +| n_updates | 72400 | +| policy_gradient_loss | -0.0638 | +| value_loss | 0.000262 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.81e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 310 | +| iterations | 1189 | +| time_elapsed | 3921 | +| total_timesteps | 1217536 | +| train/ | | +| approx_kl | 2.2195122 | +| clip_fraction | 0.592 | +| clip_range | 0.2 | +| entropy_loss | -0.553 | +| explained_variance | 0.21 | +| learning_rate | 0.0001 | +| loss | -0.0627 | +| n_updates | 72410 | +| policy_gradient_loss | -0.0559 | +| value_loss | 0.000453 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.81e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 310 | +| iterations | 1190 | +| time_elapsed | 3924 | +| total_timesteps | 1218560 | +| train/ | | +| approx_kl | 1.747304 | +| clip_fraction | 0.523 | +| clip_range | 0.2 | +| entropy_loss | -0.542 | +| explained_variance | -0.86 | +| learning_rate | 0.0001 | +| loss | -0.0381 | +| n_updates | 72420 | +| policy_gradient_loss | -0.0646 | +| value_loss | 0.000465 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.81e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 310 | +| iterations | 1191 | +| time_elapsed | 3927 | +| total_timesteps | 1219584 | +| train/ | | +| approx_kl | 2.64247 | +| clip_fraction | 0.555 | +| clip_range | 0.2 | +| entropy_loss | -0.49 | +| explained_variance | -2.25 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 72430 | +| policy_gradient_loss | -0.0766 | +| value_loss | 0.000816 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.81e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 310 | +| iterations | 1192 | +| time_elapsed | 3930 | +| total_timesteps | 1220608 | +| train/ | | +| approx_kl | 2.438186 | +| clip_fraction | 0.492 | +| clip_range | 0.2 | +| entropy_loss | -0.414 | +| explained_variance | -1.17 | +| learning_rate | 0.0001 | +| loss | -0.0927 | +| n_updates | 72440 | +| policy_gradient_loss | -0.0646 | +| value_loss | 0.000513 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.81e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 310 | +| iterations | 1193 | +| time_elapsed | 3933 | +| total_timesteps | 1221632 | +| train/ | | +| approx_kl | 2.33629 | +| clip_fraction | 0.53 | +| clip_range | 0.2 | +| entropy_loss | -0.52 | +| explained_variance | -1.13 | +| learning_rate | 0.0001 | +| loss | -0.116 | +| n_updates | 72450 | +| policy_gradient_loss | -0.0828 | +| value_loss | 0.000452 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.81e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 310 | +| iterations | 1194 | +| time_elapsed | 3936 | +| total_timesteps | 1222656 | +| train/ | | +| approx_kl | 2.4497023 | +| clip_fraction | 0.504 | +| clip_range | 0.2 | +| entropy_loss | -0.432 | +| explained_variance | -2.07 | +| learning_rate | 0.0001 | +| loss | -0.0867 | +| n_updates | 72460 | +| policy_gradient_loss | -0.076 | +| value_loss | 0.000491 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.82e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 310 | +| iterations | 1195 | +| time_elapsed | 3939 | +| total_timesteps | 1223680 | +| train/ | | +| approx_kl | 2.9437242 | +| clip_fraction | 0.571 | +| clip_range | 0.2 | +| entropy_loss | -0.488 | +| explained_variance | -0.771 | +| learning_rate | 0.0001 | +| loss | -0.0765 | +| n_updates | 72470 | +| policy_gradient_loss | -0.0667 | +| value_loss | 0.000587 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.82e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 310 | +| iterations | 1196 | +| time_elapsed | 3943 | +| total_timesteps | 1224704 | +| train/ | | +| approx_kl | 2.009482 | +| clip_fraction | 0.512 | +| clip_range | 0.2 | +| entropy_loss | -0.413 | +| explained_variance | -1 | +| learning_rate | 0.0001 | +| loss | -0.0904 | +| n_updates | 72480 | +| policy_gradient_loss | -0.0714 | +| value_loss | 0.000332 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.81e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 310 | +| iterations | 1197 | +| time_elapsed | 3946 | +| total_timesteps | 1225728 | +| train/ | | +| approx_kl | 2.4244323 | +| clip_fraction | 0.484 | +| clip_range | 0.2 | +| entropy_loss | -0.344 | +| explained_variance | -1.96 | +| learning_rate | 0.0001 | +| loss | -0.0941 | +| n_updates | 72490 | +| policy_gradient_loss | -0.0643 | +| value_loss | 0.000307 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.81e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 310 | +| iterations | 1198 | +| time_elapsed | 3950 | +| total_timesteps | 1226752 | +| train/ | | +| approx_kl | 2.1991146 | +| clip_fraction | 0.451 | +| clip_range | 0.2 | +| entropy_loss | -0.452 | +| explained_variance | -0.196 | +| learning_rate | 0.0001 | +| loss | -0.0881 | +| n_updates | 72500 | +| policy_gradient_loss | -0.0652 | +| value_loss | 0.000264 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.8e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 310 | +| iterations | 1199 | +| time_elapsed | 3953 | +| total_timesteps | 1227776 | +| train/ | | +| approx_kl | 1.6019447 | +| clip_fraction | 0.518 | +| clip_range | 0.2 | +| entropy_loss | -0.53 | +| explained_variance | -1.06 | +| learning_rate | 0.0001 | +| loss | -0.0349 | +| n_updates | 72510 | +| policy_gradient_loss | -0.066 | +| value_loss | 0.000178 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.81e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 310 | +| iterations | 1200 | +| time_elapsed | 3957 | +| total_timesteps | 1228800 | +| train/ | | +| approx_kl | 1.2416582 | +| clip_fraction | 0.46 | +| clip_range | 0.2 | +| entropy_loss | -0.476 | +| explained_variance | -0.0858 | +| learning_rate | 0.0001 | +| loss | -0.0909 | +| n_updates | 72520 | +| policy_gradient_loss | -0.0499 | +| value_loss | 0.000123 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.8e+03 | +| ep_rew_mean | 0.293 | +| time/ | | +| fps | 310 | +| iterations | 1201 | +| time_elapsed | 3961 | +| total_timesteps | 1229824 | +| train/ | | +| approx_kl | 1.6575277 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.475 | +| explained_variance | -0.318 | +| learning_rate | 0.0001 | +| loss | -0.0938 | +| n_updates | 72530 | +| policy_gradient_loss | -0.0601 | +| value_loss | 0.000172 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.29 | +| time/ | | +| fps | 310 | +| iterations | 1202 | +| time_elapsed | 3964 | +| total_timesteps | 1230848 | +| train/ | | +| approx_kl | 2.5890574 | +| clip_fraction | 0.494 | +| clip_range | 0.2 | +| entropy_loss | -0.454 | +| explained_variance | -0.673 | +| learning_rate | 0.0001 | +| loss | -0.0831 | +| n_updates | 72540 | +| policy_gradient_loss | -0.0631 | +| value_loss | 0.000382 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.29 | +| time/ | | +| fps | 310 | +| iterations | 1203 | +| time_elapsed | 3968 | +| total_timesteps | 1231872 | +| train/ | | +| approx_kl | 1.6104449 | +| clip_fraction | 0.505 | +| clip_range | 0.2 | +| entropy_loss | -0.479 | +| explained_variance | -1.02 | +| learning_rate | 0.0001 | +| loss | -0.0681 | +| n_updates | 72550 | +| policy_gradient_loss | -0.0689 | +| value_loss | 0.000544 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.284 | +| time/ | | +| fps | 310 | +| iterations | 1204 | +| time_elapsed | 3971 | +| total_timesteps | 1232896 | +| train/ | | +| approx_kl | 2.0237103 | +| clip_fraction | 0.486 | +| clip_range | 0.2 | +| entropy_loss | -0.503 | +| explained_variance | -1.7 | +| learning_rate | 0.0001 | +| loss | -0.0967 | +| n_updates | 72560 | +| policy_gradient_loss | -0.0634 | +| value_loss | 0.0003 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.78e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 310 | +| iterations | 1205 | +| time_elapsed | 3974 | +| total_timesteps | 1233920 | +| train/ | | +| approx_kl | 1.630011 | +| clip_fraction | 0.501 | +| clip_range | 0.2 | +| entropy_loss | -0.487 | +| explained_variance | -2.91 | +| learning_rate | 0.0001 | +| loss | -0.0471 | +| n_updates | 72570 | +| policy_gradient_loss | -0.0707 | +| value_loss | 0.000432 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.276 | +| time/ | | +| fps | 310 | +| iterations | 1206 | +| time_elapsed | 3977 | +| total_timesteps | 1234944 | +| train/ | | +| approx_kl | 2.1180775 | +| clip_fraction | 0.518 | +| clip_range | 0.2 | +| entropy_loss | -0.448 | +| explained_variance | -1.96 | +| learning_rate | 0.0001 | +| loss | -0.0928 | +| n_updates | 72580 | +| policy_gradient_loss | -0.0669 | +| value_loss | 0.000705 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.276 | +| time/ | | +| fps | 310 | +| iterations | 1207 | +| time_elapsed | 3980 | +| total_timesteps | 1235968 | +| train/ | | +| approx_kl | 1.3640747 | +| clip_fraction | 0.453 | +| clip_range | 0.2 | +| entropy_loss | -0.526 | +| explained_variance | -0.997 | +| learning_rate | 0.0001 | +| loss | -0.0503 | +| n_updates | 72590 | +| policy_gradient_loss | -0.0582 | +| value_loss | 0.000261 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 310 | +| iterations | 1208 | +| time_elapsed | 3983 | +| total_timesteps | 1236992 | +| train/ | | +| approx_kl | 2.11216 | +| clip_fraction | 0.509 | +| clip_range | 0.2 | +| entropy_loss | -0.43 | +| explained_variance | -3.06 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 72600 | +| policy_gradient_loss | -0.072 | +| value_loss | 0.00049 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.272 | +| time/ | | +| fps | 310 | +| iterations | 1209 | +| time_elapsed | 3987 | +| total_timesteps | 1238016 | +| train/ | | +| approx_kl | 2.1946225 | +| clip_fraction | 0.521 | +| clip_range | 0.2 | +| entropy_loss | -0.467 | +| explained_variance | -1.28 | +| learning_rate | 0.0001 | +| loss | -0.0834 | +| n_updates | 72610 | +| policy_gradient_loss | -0.0715 | +| value_loss | 0.000806 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.273 | +| time/ | | +| fps | 310 | +| iterations | 1210 | +| time_elapsed | 3990 | +| total_timesteps | 1239040 | +| train/ | | +| approx_kl | 2.3992949 | +| clip_fraction | 0.489 | +| clip_range | 0.2 | +| entropy_loss | -0.447 | +| explained_variance | -1.51 | +| learning_rate | 0.0001 | +| loss | -0.095 | +| n_updates | 72620 | +| policy_gradient_loss | -0.0635 | +| value_loss | 0.000387 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.273 | +| time/ | | +| fps | 310 | +| iterations | 1211 | +| time_elapsed | 3993 | +| total_timesteps | 1240064 | +| train/ | | +| approx_kl | 2.0270452 | +| clip_fraction | 0.55 | +| clip_range | 0.2 | +| entropy_loss | -0.533 | +| explained_variance | -1.4 | +| learning_rate | 0.0001 | +| loss | -0.0963 | +| n_updates | 72630 | +| policy_gradient_loss | -0.0751 | +| value_loss | 0.000273 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.273 | +| time/ | | +| fps | 310 | +| iterations | 1212 | +| time_elapsed | 3996 | +| total_timesteps | 1241088 | +| train/ | | +| approx_kl | 2.062029 | +| clip_fraction | 0.53 | +| clip_range | 0.2 | +| entropy_loss | -0.49 | +| explained_variance | -0.492 | +| learning_rate | 0.0001 | +| loss | -0.114 | +| n_updates | 72640 | +| policy_gradient_loss | -0.0796 | +| value_loss | 0.00037 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 310 | +| iterations | 1213 | +| time_elapsed | 4000 | +| total_timesteps | 1242112 | +| train/ | | +| approx_kl | 2.1140594 | +| clip_fraction | 0.519 | +| clip_range | 0.2 | +| entropy_loss | -0.508 | +| explained_variance | -3.86 | +| learning_rate | 0.0001 | +| loss | -0.0916 | +| n_updates | 72650 | +| policy_gradient_loss | -0.0706 | +| value_loss | 0.000349 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.272 | +| time/ | | +| fps | 310 | +| iterations | 1214 | +| time_elapsed | 4003 | +| total_timesteps | 1243136 | +| train/ | | +| approx_kl | 2.2198772 | +| clip_fraction | 0.543 | +| clip_range | 0.2 | +| entropy_loss | -0.525 | +| explained_variance | -0.723 | +| learning_rate | 0.0001 | +| loss | -0.0772 | +| n_updates | 72660 | +| policy_gradient_loss | -0.0676 | +| value_loss | 0.000331 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.271 | +| time/ | | +| fps | 310 | +| iterations | 1215 | +| time_elapsed | 4006 | +| total_timesteps | 1244160 | +| train/ | | +| approx_kl | 19.455109 | +| clip_fraction | 0.532 | +| clip_range | 0.2 | +| entropy_loss | -0.525 | +| explained_variance | -2.72 | +| learning_rate | 0.0001 | +| loss | -0.0923 | +| n_updates | 72670 | +| policy_gradient_loss | -0.074 | +| value_loss | 0.000257 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.271 | +| time/ | | +| fps | 310 | +| iterations | 1216 | +| time_elapsed | 4010 | +| total_timesteps | 1245184 | +| train/ | | +| approx_kl | 1.6973872 | +| clip_fraction | 0.489 | +| clip_range | 0.2 | +| entropy_loss | -0.618 | +| explained_variance | -0.661 | +| learning_rate | 0.0001 | +| loss | -0.0787 | +| n_updates | 72680 | +| policy_gradient_loss | -0.0579 | +| value_loss | 0.000264 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.269 | +| time/ | | +| fps | 310 | +| iterations | 1217 | +| time_elapsed | 4013 | +| total_timesteps | 1246208 | +| train/ | | +| approx_kl | 1.8057982 | +| clip_fraction | 0.519 | +| clip_range | 0.2 | +| entropy_loss | -0.459 | +| explained_variance | -0.893 | +| learning_rate | 0.0001 | +| loss | -0.0858 | +| n_updates | 72690 | +| policy_gradient_loss | -0.0722 | +| value_loss | 0.000514 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.269 | +| time/ | | +| fps | 310 | +| iterations | 1218 | +| time_elapsed | 4016 | +| total_timesteps | 1247232 | +| train/ | | +| approx_kl | 2.2812865 | +| clip_fraction | 0.495 | +| clip_range | 0.2 | +| entropy_loss | -0.391 | +| explained_variance | -1.18 | +| learning_rate | 0.0001 | +| loss | -0.0837 | +| n_updates | 72700 | +| policy_gradient_loss | -0.0683 | +| value_loss | 0.000602 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.265 | +| time/ | | +| fps | 310 | +| iterations | 1219 | +| time_elapsed | 4020 | +| total_timesteps | 1248256 | +| train/ | | +| approx_kl | 2.3269153 | +| clip_fraction | 0.54 | +| clip_range | 0.2 | +| entropy_loss | -0.472 | +| explained_variance | -2.2 | +| learning_rate | 0.0001 | +| loss | -0.107 | +| n_updates | 72710 | +| policy_gradient_loss | -0.0576 | +| value_loss | 0.000209 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.265 | +| time/ | | +| fps | 310 | +| iterations | 1220 | +| time_elapsed | 4023 | +| total_timesteps | 1249280 | +| train/ | | +| approx_kl | 1.8033786 | +| clip_fraction | 0.479 | +| clip_range | 0.2 | +| entropy_loss | -0.358 | +| explained_variance | -1.37 | +| learning_rate | 0.0001 | +| loss | -0.0829 | +| n_updates | 72720 | +| policy_gradient_loss | -0.0687 | +| value_loss | 0.00048 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.262 | +| time/ | | +| fps | 310 | +| iterations | 1221 | +| time_elapsed | 4026 | +| total_timesteps | 1250304 | +| train/ | | +| approx_kl | 1.5792742 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.459 | +| explained_variance | -0.239 | +| learning_rate | 0.0001 | +| loss | -0.108 | +| n_updates | 72730 | +| policy_gradient_loss | -0.0519 | +| value_loss | 0.000195 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.261 | +| time/ | | +| fps | 310 | +| iterations | 1222 | +| time_elapsed | 4030 | +| total_timesteps | 1251328 | +| train/ | | +| approx_kl | 2.0337586 | +| clip_fraction | 0.489 | +| clip_range | 0.2 | +| entropy_loss | -0.453 | +| explained_variance | -0.967 | +| learning_rate | 0.0001 | +| loss | -0.0985 | +| n_updates | 72740 | +| policy_gradient_loss | -0.062 | +| value_loss | 0.000327 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.261 | +| time/ | | +| fps | 310 | +| iterations | 1223 | +| time_elapsed | 4033 | +| total_timesteps | 1252352 | +| train/ | | +| approx_kl | 1.4380405 | +| clip_fraction | 0.522 | +| clip_range | 0.2 | +| entropy_loss | -0.519 | +| explained_variance | -1.37 | +| learning_rate | 0.0001 | +| loss | -0.065 | +| n_updates | 72750 | +| policy_gradient_loss | -0.0584 | +| value_loss | 0.000333 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.261 | +| time/ | | +| fps | 310 | +| iterations | 1224 | +| time_elapsed | 4036 | +| total_timesteps | 1253376 | +| train/ | | +| approx_kl | 1.2160546 | +| clip_fraction | 0.512 | +| clip_range | 0.2 | +| entropy_loss | -0.566 | +| explained_variance | -1.16 | +| learning_rate | 0.0001 | +| loss | -0.0804 | +| n_updates | 72760 | +| policy_gradient_loss | -0.0665 | +| value_loss | 0.00035 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.257 | +| time/ | | +| fps | 310 | +| iterations | 1225 | +| time_elapsed | 4039 | +| total_timesteps | 1254400 | +| train/ | | +| approx_kl | 1.8719077 | +| clip_fraction | 0.518 | +| clip_range | 0.2 | +| entropy_loss | -0.509 | +| explained_variance | -1.87 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 72770 | +| policy_gradient_loss | -0.0721 | +| value_loss | 0.00027 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.257 | +| time/ | | +| fps | 310 | +| iterations | 1226 | +| time_elapsed | 4043 | +| total_timesteps | 1255424 | +| train/ | | +| approx_kl | 2.0592859 | +| clip_fraction | 0.5 | +| clip_range | 0.2 | +| entropy_loss | -0.419 | +| explained_variance | -0.914 | +| learning_rate | 0.0001 | +| loss | -0.0708 | +| n_updates | 72780 | +| policy_gradient_loss | -0.0663 | +| value_loss | 0.00041 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.258 | +| time/ | | +| fps | 310 | +| iterations | 1227 | +| time_elapsed | 4046 | +| total_timesteps | 1256448 | +| train/ | | +| approx_kl | 1.9380946 | +| clip_fraction | 0.505 | +| clip_range | 0.2 | +| entropy_loss | -0.404 | +| explained_variance | -1.63 | +| learning_rate | 0.0001 | +| loss | -0.106 | +| n_updates | 72790 | +| policy_gradient_loss | -0.0633 | +| value_loss | 0.000481 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.258 | +| time/ | | +| fps | 310 | +| iterations | 1228 | +| time_elapsed | 4049 | +| total_timesteps | 1257472 | +| train/ | | +| approx_kl | 1.8365203 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.408 | +| explained_variance | -3.55 | +| learning_rate | 0.0001 | +| loss | -0.0986 | +| n_updates | 72800 | +| policy_gradient_loss | -0.0659 | +| value_loss | 0.000298 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.252 | +| time/ | | +| fps | 310 | +| iterations | 1229 | +| time_elapsed | 4052 | +| total_timesteps | 1258496 | +| train/ | | +| approx_kl | 1.5617427 | +| clip_fraction | 0.532 | +| clip_range | 0.2 | +| entropy_loss | -0.55 | +| explained_variance | -0.893 | +| learning_rate | 0.0001 | +| loss | -0.11 | +| n_updates | 72810 | +| policy_gradient_loss | -0.0605 | +| value_loss | 0.000343 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.25 | +| time/ | | +| fps | 310 | +| iterations | 1230 | +| time_elapsed | 4055 | +| total_timesteps | 1259520 | +| train/ | | +| approx_kl | 1.9556894 | +| clip_fraction | 0.473 | +| clip_range | 0.2 | +| entropy_loss | -0.388 | +| explained_variance | -1.14 | +| learning_rate | 0.0001 | +| loss | -0.083 | +| n_updates | 72820 | +| policy_gradient_loss | -0.0576 | +| value_loss | 0.000387 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.253 | +| time/ | | +| fps | 310 | +| iterations | 1231 | +| time_elapsed | 4058 | +| total_timesteps | 1260544 | +| train/ | | +| approx_kl | 4.3510337 | +| clip_fraction | 0.58 | +| clip_range | 0.2 | +| entropy_loss | -0.414 | +| explained_variance | -1.96 | +| learning_rate | 0.0001 | +| loss | -0.0688 | +| n_updates | 72830 | +| policy_gradient_loss | -0.0517 | +| value_loss | 0.000458 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.253 | +| time/ | | +| fps | 310 | +| iterations | 1232 | +| time_elapsed | 4062 | +| total_timesteps | 1261568 | +| train/ | | +| approx_kl | 3.0727115 | +| clip_fraction | 0.494 | +| clip_range | 0.2 | +| entropy_loss | -0.411 | +| explained_variance | -0.32 | +| learning_rate | 0.0001 | +| loss | -0.0519 | +| n_updates | 72840 | +| policy_gradient_loss | -0.0563 | +| value_loss | 0.000735 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.253 | +| time/ | | +| fps | 310 | +| iterations | 1233 | +| time_elapsed | 4065 | +| total_timesteps | 1262592 | +| train/ | | +| approx_kl | 1.7294886 | +| clip_fraction | 0.55 | +| clip_range | 0.2 | +| entropy_loss | -0.513 | +| explained_variance | -4.42 | +| learning_rate | 0.0001 | +| loss | -0.116 | +| n_updates | 72850 | +| policy_gradient_loss | -0.0746 | +| value_loss | 0.00043 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.252 | +| time/ | | +| fps | 310 | +| iterations | 1234 | +| time_elapsed | 4069 | +| total_timesteps | 1263616 | +| train/ | | +| approx_kl | 2.250535 | +| clip_fraction | 0.533 | +| clip_range | 0.2 | +| entropy_loss | -0.485 | +| explained_variance | -2.19 | +| learning_rate | 0.0001 | +| loss | -0.0857 | +| n_updates | 72860 | +| policy_gradient_loss | -0.0716 | +| value_loss | 0.000296 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.252 | +| time/ | | +| fps | 310 | +| iterations | 1235 | +| time_elapsed | 4073 | +| total_timesteps | 1264640 | +| train/ | | +| approx_kl | 2.292348 | +| clip_fraction | 0.534 | +| clip_range | 0.2 | +| entropy_loss | -0.466 | +| explained_variance | -1.83 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 72870 | +| policy_gradient_loss | -0.0696 | +| value_loss | 0.000334 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.255 | +| time/ | | +| fps | 310 | +| iterations | 1236 | +| time_elapsed | 4076 | +| total_timesteps | 1265664 | +| train/ | | +| approx_kl | 2.1322088 | +| clip_fraction | 0.534 | +| clip_range | 0.2 | +| entropy_loss | -0.489 | +| explained_variance | -0.817 | +| learning_rate | 0.0001 | +| loss | -0.112 | +| n_updates | 72880 | +| policy_gradient_loss | -0.0743 | +| value_loss | 0.000307 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.255 | +| time/ | | +| fps | 310 | +| iterations | 1237 | +| time_elapsed | 4080 | +| total_timesteps | 1266688 | +| train/ | | +| approx_kl | 2.4874277 | +| clip_fraction | 0.52 | +| clip_range | 0.2 | +| entropy_loss | -0.419 | +| explained_variance | -1.22 | +| learning_rate | 0.0001 | +| loss | -0.107 | +| n_updates | 72890 | +| policy_gradient_loss | -0.0717 | +| value_loss | 0.000437 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.255 | +| time/ | | +| fps | 310 | +| iterations | 1238 | +| time_elapsed | 4083 | +| total_timesteps | 1267712 | +| train/ | | +| approx_kl | 1.8968384 | +| clip_fraction | 0.554 | +| clip_range | 0.2 | +| entropy_loss | -0.523 | +| explained_variance | -1.11 | +| learning_rate | 0.0001 | +| loss | -0.109 | +| n_updates | 72900 | +| policy_gradient_loss | -0.0706 | +| value_loss | 0.000232 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.255 | +| time/ | | +| fps | 310 | +| iterations | 1239 | +| time_elapsed | 4087 | +| total_timesteps | 1268736 | +| train/ | | +| approx_kl | 1.8095987 | +| clip_fraction | 0.509 | +| clip_range | 0.2 | +| entropy_loss | -0.466 | +| explained_variance | -1.96 | +| learning_rate | 0.0001 | +| loss | -0.0728 | +| n_updates | 72910 | +| policy_gradient_loss | -0.0623 | +| value_loss | 0.000257 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.253 | +| time/ | | +| fps | 310 | +| iterations | 1240 | +| time_elapsed | 4090 | +| total_timesteps | 1269760 | +| train/ | | +| approx_kl | 2.3802261 | +| clip_fraction | 0.496 | +| clip_range | 0.2 | +| entropy_loss | -0.459 | +| explained_variance | -1.15 | +| learning_rate | 0.0001 | +| loss | -0.0998 | +| n_updates | 72920 | +| policy_gradient_loss | -0.0648 | +| value_loss | 0.000466 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.247 | +| time/ | | +| fps | 310 | +| iterations | 1241 | +| time_elapsed | 4093 | +| total_timesteps | 1270784 | +| train/ | | +| approx_kl | 1.497223 | +| clip_fraction | 0.518 | +| clip_range | 0.2 | +| entropy_loss | -0.505 | +| explained_variance | -1.18 | +| learning_rate | 0.0001 | +| loss | -0.0944 | +| n_updates | 72930 | +| policy_gradient_loss | -0.0646 | +| value_loss | 0.000215 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.247 | +| time/ | | +| fps | 310 | +| iterations | 1242 | +| time_elapsed | 4096 | +| total_timesteps | 1271808 | +| train/ | | +| approx_kl | 2.1169953 | +| clip_fraction | 0.522 | +| clip_range | 0.2 | +| entropy_loss | -0.478 | +| explained_variance | -0.508 | +| learning_rate | 0.0001 | +| loss | -0.0937 | +| n_updates | 72940 | +| policy_gradient_loss | -0.0678 | +| value_loss | 0.000504 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.249 | +| time/ | | +| fps | 310 | +| iterations | 1243 | +| time_elapsed | 4100 | +| total_timesteps | 1272832 | +| train/ | | +| approx_kl | 1.8165255 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.352 | +| explained_variance | -0.231 | +| learning_rate | 0.0001 | +| loss | -0.0928 | +| n_updates | 72950 | +| policy_gradient_loss | -0.0594 | +| value_loss | 0.000472 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.249 | +| time/ | | +| fps | 310 | +| iterations | 1244 | +| time_elapsed | 4103 | +| total_timesteps | 1273856 | +| train/ | | +| approx_kl | 2.6249878 | +| clip_fraction | 0.519 | +| clip_range | 0.2 | +| entropy_loss | -0.442 | +| explained_variance | -3.94 | +| learning_rate | 0.0001 | +| loss | -0.112 | +| n_updates | 72960 | +| policy_gradient_loss | -0.0654 | +| value_loss | 0.000376 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.249 | +| time/ | | +| fps | 310 | +| iterations | 1245 | +| time_elapsed | 4106 | +| total_timesteps | 1274880 | +| train/ | | +| approx_kl | 2.4741735 | +| clip_fraction | 0.55 | +| clip_range | 0.2 | +| entropy_loss | -0.514 | +| explained_variance | -1.69 | +| learning_rate | 0.0001 | +| loss | -0.106 | +| n_updates | 72970 | +| policy_gradient_loss | -0.0719 | +| value_loss | 0.000838 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.249 | +| time/ | | +| fps | 310 | +| iterations | 1246 | +| time_elapsed | 4109 | +| total_timesteps | 1275904 | +| train/ | | +| approx_kl | 2.068995 | +| clip_fraction | 0.52 | +| clip_range | 0.2 | +| entropy_loss | -0.455 | +| explained_variance | -3 | +| learning_rate | 0.0001 | +| loss | -0.0996 | +| n_updates | 72980 | +| policy_gradient_loss | -0.078 | +| value_loss | 0.000601 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.247 | +| time/ | | +| fps | 310 | +| iterations | 1247 | +| time_elapsed | 4112 | +| total_timesteps | 1276928 | +| train/ | | +| approx_kl | 2.2019682 | +| clip_fraction | 0.549 | +| clip_range | 0.2 | +| entropy_loss | -0.477 | +| explained_variance | -0.753 | +| learning_rate | 0.0001 | +| loss | -0.0973 | +| n_updates | 72990 | +| policy_gradient_loss | -0.0685 | +| value_loss | 0.000409 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.247 | +| time/ | | +| fps | 310 | +| iterations | 1248 | +| time_elapsed | 4115 | +| total_timesteps | 1277952 | +| train/ | | +| approx_kl | 2.4904323 | +| clip_fraction | 0.533 | +| clip_range | 0.2 | +| entropy_loss | -0.491 | +| explained_variance | -1.77 | +| learning_rate | 0.0001 | +| loss | -0.0703 | +| n_updates | 73000 | +| policy_gradient_loss | -0.0673 | +| value_loss | 0.000274 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.244 | +| time/ | | +| fps | 310 | +| iterations | 1249 | +| time_elapsed | 4119 | +| total_timesteps | 1278976 | +| train/ | | +| approx_kl | 1.4812368 | +| clip_fraction | 0.508 | +| clip_range | 0.2 | +| entropy_loss | -0.58 | +| explained_variance | -0.507 | +| learning_rate | 0.0001 | +| loss | -0.0992 | +| n_updates | 73010 | +| policy_gradient_loss | -0.0624 | +| value_loss | 0.000175 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.244 | +| time/ | | +| fps | 310 | +| iterations | 1250 | +| time_elapsed | 4122 | +| total_timesteps | 1280000 | +| train/ | | +| approx_kl | 1.9877088 | +| clip_fraction | 0.525 | +| clip_range | 0.2 | +| entropy_loss | -0.505 | +| explained_variance | -1.43 | +| learning_rate | 0.0001 | +| loss | -0.0671 | +| n_updates | 73020 | +| policy_gradient_loss | -0.0568 | +| value_loss | 0.000209 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.243 | +| time/ | | +| fps | 310 | +| iterations | 1251 | +| time_elapsed | 4125 | +| total_timesteps | 1281024 | +| train/ | | +| approx_kl | 2.5136037 | +| clip_fraction | 0.528 | +| clip_range | 0.2 | +| entropy_loss | -0.473 | +| explained_variance | -0.617 | +| learning_rate | 0.0001 | +| loss | -0.0833 | +| n_updates | 73030 | +| policy_gradient_loss | -0.0538 | +| value_loss | 0.000513 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.243 | +| time/ | | +| fps | 310 | +| iterations | 1252 | +| time_elapsed | 4129 | +| total_timesteps | 1282048 | +| train/ | | +| approx_kl | 1.8152039 | +| clip_fraction | 0.52 | +| clip_range | 0.2 | +| entropy_loss | -0.515 | +| explained_variance | -2.01 | +| learning_rate | 0.0001 | +| loss | -0.0837 | +| n_updates | 73040 | +| policy_gradient_loss | -0.0693 | +| value_loss | 0.000519 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.244 | +| time/ | | +| fps | 310 | +| iterations | 1253 | +| time_elapsed | 4132 | +| total_timesteps | 1283072 | +| train/ | | +| approx_kl | 3.1361246 | +| clip_fraction | 0.53 | +| clip_range | 0.2 | +| entropy_loss | -0.538 | +| explained_variance | -1.59 | +| learning_rate | 0.0001 | +| loss | -0.0976 | +| n_updates | 73050 | +| policy_gradient_loss | -0.0762 | +| value_loss | 0.000285 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.241 | +| time/ | | +| fps | 310 | +| iterations | 1254 | +| time_elapsed | 4136 | +| total_timesteps | 1284096 | +| train/ | | +| approx_kl | 2.22689 | +| clip_fraction | 0.504 | +| clip_range | 0.2 | +| entropy_loss | -0.483 | +| explained_variance | -1.65 | +| learning_rate | 0.0001 | +| loss | -0.0842 | +| n_updates | 73060 | +| policy_gradient_loss | -0.0684 | +| value_loss | 0.000141 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.241 | +| time/ | | +| fps | 310 | +| iterations | 1255 | +| time_elapsed | 4139 | +| total_timesteps | 1285120 | +| train/ | | +| approx_kl | 1.3060627 | +| clip_fraction | 0.491 | +| clip_range | 0.2 | +| entropy_loss | -0.504 | +| explained_variance | -1.27 | +| learning_rate | 0.0001 | +| loss | -0.0838 | +| n_updates | 73070 | +| policy_gradient_loss | -0.0639 | +| value_loss | 0.000186 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.238 | +| time/ | | +| fps | 310 | +| iterations | 1256 | +| time_elapsed | 4142 | +| total_timesteps | 1286144 | +| train/ | | +| approx_kl | 2.1533284 | +| clip_fraction | 0.555 | +| clip_range | 0.2 | +| entropy_loss | -0.468 | +| explained_variance | -0.679 | +| learning_rate | 0.0001 | +| loss | -0.0828 | +| n_updates | 73080 | +| policy_gradient_loss | -0.0676 | +| value_loss | 0.000383 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.233 | +| time/ | | +| fps | 310 | +| iterations | 1257 | +| time_elapsed | 4146 | +| total_timesteps | 1287168 | +| train/ | | +| approx_kl | 1.7343985 | +| clip_fraction | 0.473 | +| clip_range | 0.2 | +| entropy_loss | -0.439 | +| explained_variance | -1.52 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 73090 | +| policy_gradient_loss | -0.0648 | +| value_loss | 0.000333 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.233 | +| time/ | | +| fps | 310 | +| iterations | 1258 | +| time_elapsed | 4149 | +| total_timesteps | 1288192 | +| train/ | | +| approx_kl | 2.198923 | +| clip_fraction | 0.515 | +| clip_range | 0.2 | +| entropy_loss | -0.473 | +| explained_variance | -0.293 | +| learning_rate | 0.0001 | +| loss | -0.085 | +| n_updates | 73100 | +| policy_gradient_loss | -0.0666 | +| value_loss | 0.000403 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.23 | +| time/ | | +| fps | 310 | +| iterations | 1259 | +| time_elapsed | 4152 | +| total_timesteps | 1289216 | +| train/ | | +| approx_kl | 2.6080923 | +| clip_fraction | 0.522 | +| clip_range | 0.2 | +| entropy_loss | -0.409 | +| explained_variance | -1.38 | +| learning_rate | 0.0001 | +| loss | -0.0962 | +| n_updates | 73110 | +| policy_gradient_loss | -0.0732 | +| value_loss | 0.000503 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.23 | +| time/ | | +| fps | 310 | +| iterations | 1260 | +| time_elapsed | 4155 | +| total_timesteps | 1290240 | +| train/ | | +| approx_kl | 3.1342854 | +| clip_fraction | 0.536 | +| clip_range | 0.2 | +| entropy_loss | -0.498 | +| explained_variance | -0.835 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 73120 | +| policy_gradient_loss | -0.0752 | +| value_loss | 0.00043 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.23 | +| time/ | | +| fps | 310 | +| iterations | 1261 | +| time_elapsed | 4159 | +| total_timesteps | 1291264 | +| train/ | | +| approx_kl | 1.8075413 | +| clip_fraction | 0.542 | +| clip_range | 0.2 | +| entropy_loss | -0.562 | +| explained_variance | -1.4 | +| learning_rate | 0.0001 | +| loss | -0.094 | +| n_updates | 73130 | +| policy_gradient_loss | -0.0759 | +| value_loss | 0.000393 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.23 | +| time/ | | +| fps | 310 | +| iterations | 1262 | +| time_elapsed | 4162 | +| total_timesteps | 1292288 | +| train/ | | +| approx_kl | 1.8731303 | +| clip_fraction | 0.533 | +| clip_range | 0.2 | +| entropy_loss | -0.518 | +| explained_variance | -0.615 | +| learning_rate | 0.0001 | +| loss | -0.111 | +| n_updates | 73140 | +| policy_gradient_loss | -0.0739 | +| value_loss | 0.000341 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.229 | +| time/ | | +| fps | 310 | +| iterations | 1263 | +| time_elapsed | 4165 | +| total_timesteps | 1293312 | +| train/ | | +| approx_kl | 1.4858786 | +| clip_fraction | 0.507 | +| clip_range | 0.2 | +| entropy_loss | -0.504 | +| explained_variance | -0.643 | +| learning_rate | 0.0001 | +| loss | -0.0717 | +| n_updates | 73150 | +| policy_gradient_loss | -0.0633 | +| value_loss | 0.000344 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.229 | +| time/ | | +| fps | 310 | +| iterations | 1264 | +| time_elapsed | 4168 | +| total_timesteps | 1294336 | +| train/ | | +| approx_kl | 1.9978371 | +| clip_fraction | 0.507 | +| clip_range | 0.2 | +| entropy_loss | -0.427 | +| explained_variance | -1.57 | +| learning_rate | 0.0001 | +| loss | -0.0889 | +| n_updates | 73160 | +| policy_gradient_loss | -0.0721 | +| value_loss | 0.000497 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.231 | +| time/ | | +| fps | 310 | +| iterations | 1265 | +| time_elapsed | 4171 | +| total_timesteps | 1295360 | +| train/ | | +| approx_kl | 1.7793884 | +| clip_fraction | 0.498 | +| clip_range | 0.2 | +| entropy_loss | -0.49 | +| explained_variance | -1.8 | +| learning_rate | 0.0001 | +| loss | -0.0798 | +| n_updates | 73170 | +| policy_gradient_loss | -0.0719 | +| value_loss | 0.000494 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.231 | +| time/ | | +| fps | 310 | +| iterations | 1266 | +| time_elapsed | 4174 | +| total_timesteps | 1296384 | +| train/ | | +| approx_kl | 2.27028 | +| clip_fraction | 0.515 | +| clip_range | 0.2 | +| entropy_loss | -0.44 | +| explained_variance | -1.1 | +| learning_rate | 0.0001 | +| loss | -0.0972 | +| n_updates | 73180 | +| policy_gradient_loss | -0.0741 | +| value_loss | 0.000597 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.231 | +| time/ | | +| fps | 310 | +| iterations | 1267 | +| time_elapsed | 4178 | +| total_timesteps | 1297408 | +| train/ | | +| approx_kl | 1.7633424 | +| clip_fraction | 0.5 | +| clip_range | 0.2 | +| entropy_loss | -0.409 | +| explained_variance | -1.97 | +| learning_rate | 0.0001 | +| loss | -0.105 | +| n_updates | 73190 | +| policy_gradient_loss | -0.0663 | +| value_loss | 0.000467 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.231 | +| time/ | | +| fps | 310 | +| iterations | 1268 | +| time_elapsed | 4181 | +| total_timesteps | 1298432 | +| train/ | | +| approx_kl | 1.9734495 | +| clip_fraction | 0.493 | +| clip_range | 0.2 | +| entropy_loss | -0.391 | +| explained_variance | -1.22 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 73200 | +| policy_gradient_loss | -0.0645 | +| value_loss | 0.000474 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.234 | +| time/ | | +| fps | 310 | +| iterations | 1269 | +| time_elapsed | 4185 | +| total_timesteps | 1299456 | +| train/ | | +| approx_kl | 2.139376 | +| clip_fraction | 0.516 | +| clip_range | 0.2 | +| entropy_loss | -0.456 | +| explained_variance | -1.43 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 73210 | +| policy_gradient_loss | -0.0595 | +| value_loss | 0.000466 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.231 | +| time/ | | +| fps | 310 | +| iterations | 1270 | +| time_elapsed | 4188 | +| total_timesteps | 1300480 | +| train/ | | +| approx_kl | 1.7110926 | +| clip_fraction | 0.514 | +| clip_range | 0.2 | +| entropy_loss | -0.486 | +| explained_variance | -1.22 | +| learning_rate | 0.0001 | +| loss | -0.112 | +| n_updates | 73220 | +| policy_gradient_loss | -0.063 | +| value_loss | 0.000308 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.228 | +| time/ | | +| fps | 310 | +| iterations | 1271 | +| time_elapsed | 4192 | +| total_timesteps | 1301504 | +| train/ | | +| approx_kl | 1.8464752 | +| clip_fraction | 0.495 | +| clip_range | 0.2 | +| entropy_loss | -0.454 | +| explained_variance | -0.9 | +| learning_rate | 0.0001 | +| loss | -0.08 | +| n_updates | 73230 | +| policy_gradient_loss | -0.0608 | +| value_loss | 0.00051 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.228 | +| time/ | | +| fps | 310 | +| iterations | 1272 | +| time_elapsed | 4195 | +| total_timesteps | 1302528 | +| train/ | | +| approx_kl | 2.016498 | +| clip_fraction | 0.536 | +| clip_range | 0.2 | +| entropy_loss | -0.473 | +| explained_variance | -1.41 | +| learning_rate | 0.0001 | +| loss | -0.0928 | +| n_updates | 73240 | +| policy_gradient_loss | -0.0686 | +| value_loss | 0.000396 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.226 | +| time/ | | +| fps | 310 | +| iterations | 1273 | +| time_elapsed | 4199 | +| total_timesteps | 1303552 | +| train/ | | +| approx_kl | 2.2275379 | +| clip_fraction | 0.499 | +| clip_range | 0.2 | +| entropy_loss | -0.395 | +| explained_variance | -1.31 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 73250 | +| policy_gradient_loss | -0.0625 | +| value_loss | 0.000342 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.226 | +| time/ | | +| fps | 310 | +| iterations | 1274 | +| time_elapsed | 4203 | +| total_timesteps | 1304576 | +| train/ | | +| approx_kl | 1.7244275 | +| clip_fraction | 0.491 | +| clip_range | 0.2 | +| entropy_loss | -0.425 | +| explained_variance | -0.703 | +| learning_rate | 0.0001 | +| loss | -0.08 | +| n_updates | 73260 | +| policy_gradient_loss | -0.068 | +| value_loss | 0.000348 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.226 | +| time/ | | +| fps | 310 | +| iterations | 1275 | +| time_elapsed | 4206 | +| total_timesteps | 1305600 | +| train/ | | +| approx_kl | 2.0845342 | +| clip_fraction | 0.504 | +| clip_range | 0.2 | +| entropy_loss | -0.405 | +| explained_variance | -1.18 | +| learning_rate | 0.0001 | +| loss | -0.0887 | +| n_updates | 73270 | +| policy_gradient_loss | -0.0628 | +| value_loss | 0.000585 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.226 | +| time/ | | +| fps | 310 | +| iterations | 1276 | +| time_elapsed | 4210 | +| total_timesteps | 1306624 | +| train/ | | +| approx_kl | 2.4061508 | +| clip_fraction | 0.51 | +| clip_range | 0.2 | +| entropy_loss | -0.422 | +| explained_variance | -1.36 | +| learning_rate | 0.0001 | +| loss | -0.0444 | +| n_updates | 73280 | +| policy_gradient_loss | -0.0555 | +| value_loss | 0.000293 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.225 | +| time/ | | +| fps | 310 | +| iterations | 1277 | +| time_elapsed | 4213 | +| total_timesteps | 1307648 | +| train/ | | +| approx_kl | 3.3574188 | +| clip_fraction | 0.528 | +| clip_range | 0.2 | +| entropy_loss | -0.45 | +| explained_variance | -0.614 | +| learning_rate | 0.0001 | +| loss | -0.0858 | +| n_updates | 73290 | +| policy_gradient_loss | -0.0706 | +| value_loss | 0.000307 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.225 | +| time/ | | +| fps | 310 | +| iterations | 1278 | +| time_elapsed | 4216 | +| total_timesteps | 1308672 | +| train/ | | +| approx_kl | 2.2834442 | +| clip_fraction | 0.496 | +| clip_range | 0.2 | +| entropy_loss | -0.478 | +| explained_variance | -2.17 | +| learning_rate | 0.0001 | +| loss | -0.0994 | +| n_updates | 73300 | +| policy_gradient_loss | -0.0732 | +| value_loss | 0.000388 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.224 | +| time/ | | +| fps | 310 | +| iterations | 1279 | +| time_elapsed | 4219 | +| total_timesteps | 1309696 | +| train/ | | +| approx_kl | 2.3084836 | +| clip_fraction | 0.523 | +| clip_range | 0.2 | +| entropy_loss | -0.5 | +| explained_variance | -1.16 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 73310 | +| policy_gradient_loss | -0.0714 | +| value_loss | 0.000274 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.224 | +| time/ | | +| fps | 310 | +| iterations | 1280 | +| time_elapsed | 4222 | +| total_timesteps | 1310720 | +| train/ | | +| approx_kl | 1.6413765 | +| clip_fraction | 0.533 | +| clip_range | 0.2 | +| entropy_loss | -0.51 | +| explained_variance | -2.84 | +| learning_rate | 0.0001 | +| loss | -0.0829 | +| n_updates | 73320 | +| policy_gradient_loss | -0.0736 | +| value_loss | 0.000169 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.221 | +| time/ | | +| fps | 310 | +| iterations | 1281 | +| time_elapsed | 4226 | +| total_timesteps | 1311744 | +| train/ | | +| approx_kl | 1.8013856 | +| clip_fraction | 0.518 | +| clip_range | 0.2 | +| entropy_loss | -0.51 | +| explained_variance | -1.47 | +| learning_rate | 0.0001 | +| loss | -0.106 | +| n_updates | 73330 | +| policy_gradient_loss | -0.0747 | +| value_loss | 0.000179 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.22 | +| time/ | | +| fps | 310 | +| iterations | 1282 | +| time_elapsed | 4229 | +| total_timesteps | 1312768 | +| train/ | | +| approx_kl | 1.774829 | +| clip_fraction | 0.496 | +| clip_range | 0.2 | +| entropy_loss | -0.427 | +| explained_variance | -0.985 | +| learning_rate | 0.0001 | +| loss | -0.0941 | +| n_updates | 73340 | +| policy_gradient_loss | -0.0611 | +| value_loss | 0.000545 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.22 | +| time/ | | +| fps | 310 | +| iterations | 1283 | +| time_elapsed | 4232 | +| total_timesteps | 1313792 | +| train/ | | +| approx_kl | 2.352487 | +| clip_fraction | 0.517 | +| clip_range | 0.2 | +| entropy_loss | -0.402 | +| explained_variance | -4.41 | +| learning_rate | 0.0001 | +| loss | -0.111 | +| n_updates | 73350 | +| policy_gradient_loss | -0.0743 | +| value_loss | 0.000576 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.22 | +| time/ | | +| fps | 310 | +| iterations | 1284 | +| time_elapsed | 4235 | +| total_timesteps | 1314816 | +| train/ | | +| approx_kl | 2.0096383 | +| clip_fraction | 0.558 | +| clip_range | 0.2 | +| entropy_loss | -0.549 | +| explained_variance | -1.88 | +| learning_rate | 0.0001 | +| loss | -0.0973 | +| n_updates | 73360 | +| policy_gradient_loss | -0.0758 | +| value_loss | 0.000465 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.221 | +| time/ | | +| fps | 310 | +| iterations | 1285 | +| time_elapsed | 4238 | +| total_timesteps | 1315840 | +| train/ | | +| approx_kl | 2.0453558 | +| clip_fraction | 0.505 | +| clip_range | 0.2 | +| entropy_loss | -0.423 | +| explained_variance | -2.07 | +| learning_rate | 0.0001 | +| loss | -0.0654 | +| n_updates | 73370 | +| policy_gradient_loss | -0.0653 | +| value_loss | 0.000323 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.218 | +| time/ | | +| fps | 310 | +| iterations | 1286 | +| time_elapsed | 4242 | +| total_timesteps | 1316864 | +| train/ | | +| approx_kl | 2.5801842 | +| clip_fraction | 0.534 | +| clip_range | 0.2 | +| entropy_loss | -0.394 | +| explained_variance | -2.23 | +| learning_rate | 0.0001 | +| loss | -0.094 | +| n_updates | 73380 | +| policy_gradient_loss | -0.0733 | +| value_loss | 0.000541 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.218 | +| time/ | | +| fps | 310 | +| iterations | 1287 | +| time_elapsed | 4245 | +| total_timesteps | 1317888 | +| train/ | | +| approx_kl | 2.6348512 | +| clip_fraction | 0.552 | +| clip_range | 0.2 | +| entropy_loss | -0.459 | +| explained_variance | -2.2 | +| learning_rate | 0.0001 | +| loss | -0.105 | +| n_updates | 73390 | +| policy_gradient_loss | -0.0619 | +| value_loss | 0.000349 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.22 | +| time/ | | +| fps | 310 | +| iterations | 1288 | +| time_elapsed | 4249 | +| total_timesteps | 1318912 | +| train/ | | +| approx_kl | 2.1611688 | +| clip_fraction | 0.518 | +| clip_range | 0.2 | +| entropy_loss | -0.462 | +| explained_variance | -1.12 | +| learning_rate | 0.0001 | +| loss | -0.0952 | +| n_updates | 73400 | +| policy_gradient_loss | -0.0724 | +| value_loss | 0.000577 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.22 | +| time/ | | +| fps | 310 | +| iterations | 1289 | +| time_elapsed | 4252 | +| total_timesteps | 1319936 | +| train/ | | +| approx_kl | 2.956747 | +| clip_fraction | 0.507 | +| clip_range | 0.2 | +| entropy_loss | -0.459 | +| explained_variance | -1.08 | +| learning_rate | 0.0001 | +| loss | -0.105 | +| n_updates | 73410 | +| policy_gradient_loss | -0.073 | +| value_loss | 0.00053 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.22 | +| time/ | | +| fps | 310 | +| iterations | 1290 | +| time_elapsed | 4256 | +| total_timesteps | 1320960 | +| train/ | | +| approx_kl | 2.079868 | +| clip_fraction | 0.507 | +| clip_range | 0.2 | +| entropy_loss | -0.414 | +| explained_variance | -0.845 | +| learning_rate | 0.0001 | +| loss | -0.0965 | +| n_updates | 73420 | +| policy_gradient_loss | -0.0703 | +| value_loss | 0.000384 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.22 | +| time/ | | +| fps | 310 | +| iterations | 1291 | +| time_elapsed | 4259 | +| total_timesteps | 1321984 | +| train/ | | +| approx_kl | 2.1027634 | +| clip_fraction | 0.53 | +| clip_range | 0.2 | +| entropy_loss | -0.417 | +| explained_variance | -1.59 | +| learning_rate | 0.0001 | +| loss | -0.0927 | +| n_updates | 73430 | +| policy_gradient_loss | -0.0671 | +| value_loss | 0.000561 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.22 | +| time/ | | +| fps | 310 | +| iterations | 1292 | +| time_elapsed | 4263 | +| total_timesteps | 1323008 | +| train/ | | +| approx_kl | 1.8845968 | +| clip_fraction | 0.527 | +| clip_range | 0.2 | +| entropy_loss | -0.441 | +| explained_variance | -1.18 | +| learning_rate | 0.0001 | +| loss | -0.113 | +| n_updates | 73440 | +| policy_gradient_loss | -0.0763 | +| value_loss | 0.000423 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.217 | +| time/ | | +| fps | 310 | +| iterations | 1293 | +| time_elapsed | 4266 | +| total_timesteps | 1324032 | +| train/ | | +| approx_kl | 2.1762102 | +| clip_fraction | 0.528 | +| clip_range | 0.2 | +| entropy_loss | -0.445 | +| explained_variance | -3.07 | +| learning_rate | 0.0001 | +| loss | -0.0954 | +| n_updates | 73450 | +| policy_gradient_loss | -0.0749 | +| value_loss | 0.000488 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.217 | +| time/ | | +| fps | 310 | +| iterations | 1294 | +| time_elapsed | 4270 | +| total_timesteps | 1325056 | +| train/ | | +| approx_kl | 2.5502965 | +| clip_fraction | 0.535 | +| clip_range | 0.2 | +| entropy_loss | -0.461 | +| explained_variance | -1.58 | +| learning_rate | 0.0001 | +| loss | -0.108 | +| n_updates | 73460 | +| policy_gradient_loss | -0.0631 | +| value_loss | 0.000311 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.212 | +| time/ | | +| fps | 310 | +| iterations | 1295 | +| time_elapsed | 4273 | +| total_timesteps | 1326080 | +| train/ | | +| approx_kl | 3.6518817 | +| clip_fraction | 0.523 | +| clip_range | 0.2 | +| entropy_loss | -0.422 | +| explained_variance | -1.02 | +| learning_rate | 0.0001 | +| loss | 0.0157 | +| n_updates | 73470 | +| policy_gradient_loss | -0.0496 | +| value_loss | 0.000399 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.213 | +| time/ | | +| fps | 310 | +| iterations | 1296 | +| time_elapsed | 4276 | +| total_timesteps | 1327104 | +| train/ | | +| approx_kl | 2.2137623 | +| clip_fraction | 0.543 | +| clip_range | 0.2 | +| entropy_loss | -0.502 | +| explained_variance | -1.9 | +| learning_rate | 0.0001 | +| loss | -0.094 | +| n_updates | 73480 | +| policy_gradient_loss | -0.0681 | +| value_loss | 0.000646 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.213 | +| time/ | | +| fps | 310 | +| iterations | 1297 | +| time_elapsed | 4279 | +| total_timesteps | 1328128 | +| train/ | | +| approx_kl | 1.9496758 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.429 | +| explained_variance | -3.82 | +| learning_rate | 0.0001 | +| loss | -0.0774 | +| n_updates | 73490 | +| policy_gradient_loss | -0.0647 | +| value_loss | 0.000362 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.215 | +| time/ | | +| fps | 310 | +| iterations | 1298 | +| time_elapsed | 4282 | +| total_timesteps | 1329152 | +| train/ | | +| approx_kl | 5.4372263 | +| clip_fraction | 0.495 | +| clip_range | 0.2 | +| entropy_loss | -0.407 | +| explained_variance | -1.04 | +| learning_rate | 0.0001 | +| loss | -0.0876 | +| n_updates | 73500 | +| policy_gradient_loss | -0.0649 | +| value_loss | 0.000586 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.215 | +| time/ | | +| fps | 310 | +| iterations | 1299 | +| time_elapsed | 4285 | +| total_timesteps | 1330176 | +| train/ | | +| approx_kl | 2.6835184 | +| clip_fraction | 0.484 | +| clip_range | 0.2 | +| entropy_loss | -0.453 | +| explained_variance | -1.81 | +| learning_rate | 0.0001 | +| loss | -0.0727 | +| n_updates | 73510 | +| policy_gradient_loss | -0.0572 | +| value_loss | 0.000445 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.213 | +| time/ | | +| fps | 310 | +| iterations | 1300 | +| time_elapsed | 4288 | +| total_timesteps | 1331200 | +| train/ | | +| approx_kl | 2.2623653 | +| clip_fraction | 0.55 | +| clip_range | 0.2 | +| entropy_loss | -0.462 | +| explained_variance | -1.63 | +| learning_rate | 0.0001 | +| loss | -0.0984 | +| n_updates | 73520 | +| policy_gradient_loss | -0.071 | +| value_loss | 0.000347 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.213 | +| time/ | | +| fps | 310 | +| iterations | 1301 | +| time_elapsed | 4292 | +| total_timesteps | 1332224 | +| train/ | | +| approx_kl | 1.674742 | +| clip_fraction | 0.495 | +| clip_range | 0.2 | +| entropy_loss | -0.473 | +| explained_variance | -0.231 | +| learning_rate | 0.0001 | +| loss | -0.0934 | +| n_updates | 73530 | +| policy_gradient_loss | -0.0669 | +| value_loss | 0.000546 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.215 | +| time/ | | +| fps | 310 | +| iterations | 1302 | +| time_elapsed | 4295 | +| total_timesteps | 1333248 | +| train/ | | +| approx_kl | 2.1727412 | +| clip_fraction | 0.518 | +| clip_range | 0.2 | +| entropy_loss | -0.469 | +| explained_variance | -3.81 | +| learning_rate | 0.0001 | +| loss | -0.108 | +| n_updates | 73540 | +| policy_gradient_loss | -0.0636 | +| value_loss | 0.000325 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.215 | +| time/ | | +| fps | 310 | +| iterations | 1303 | +| time_elapsed | 4298 | +| total_timesteps | 1334272 | +| train/ | | +| approx_kl | 3.8948627 | +| clip_fraction | 0.529 | +| clip_range | 0.2 | +| entropy_loss | -0.44 | +| explained_variance | -0.569 | +| learning_rate | 0.0001 | +| loss | -0.0908 | +| n_updates | 73550 | +| policy_gradient_loss | -0.0626 | +| value_loss | 0.000429 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.214 | +| time/ | | +| fps | 310 | +| iterations | 1304 | +| time_elapsed | 4301 | +| total_timesteps | 1335296 | +| train/ | | +| approx_kl | 1.4489061 | +| clip_fraction | 0.467 | +| clip_range | 0.2 | +| entropy_loss | -0.41 | +| explained_variance | -1.16 | +| learning_rate | 0.0001 | +| loss | -0.0731 | +| n_updates | 73560 | +| policy_gradient_loss | -0.0581 | +| value_loss | 0.000302 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.214 | +| time/ | | +| fps | 310 | +| iterations | 1305 | +| time_elapsed | 4305 | +| total_timesteps | 1336320 | +| train/ | | +| approx_kl | 2.209735 | +| clip_fraction | 0.53 | +| clip_range | 0.2 | +| entropy_loss | -0.498 | +| explained_variance | -2.08 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 73570 | +| policy_gradient_loss | -0.0753 | +| value_loss | 0.00044 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.216 | +| time/ | | +| fps | 310 | +| iterations | 1306 | +| time_elapsed | 4308 | +| total_timesteps | 1337344 | +| train/ | | +| approx_kl | 1.5824848 | +| clip_fraction | 0.53 | +| clip_range | 0.2 | +| entropy_loss | -0.552 | +| explained_variance | -1.13 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 73580 | +| policy_gradient_loss | -0.0593 | +| value_loss | 0.000217 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.216 | +| time/ | | +| fps | 310 | +| iterations | 1307 | +| time_elapsed | 4312 | +| total_timesteps | 1338368 | +| train/ | | +| approx_kl | 1.8940178 | +| clip_fraction | 0.523 | +| clip_range | 0.2 | +| entropy_loss | -0.495 | +| explained_variance | -1.08 | +| learning_rate | 0.0001 | +| loss | -0.105 | +| n_updates | 73590 | +| policy_gradient_loss | -0.0711 | +| value_loss | 0.000312 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.218 | +| time/ | | +| fps | 310 | +| iterations | 1308 | +| time_elapsed | 4315 | +| total_timesteps | 1339392 | +| train/ | | +| approx_kl | 1.583914 | +| clip_fraction | 0.519 | +| clip_range | 0.2 | +| entropy_loss | -0.468 | +| explained_variance | -1.13 | +| learning_rate | 0.0001 | +| loss | -0.0971 | +| n_updates | 73600 | +| policy_gradient_loss | -0.0638 | +| value_loss | 0.000329 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.216 | +| time/ | | +| fps | 310 | +| iterations | 1309 | +| time_elapsed | 4319 | +| total_timesteps | 1340416 | +| train/ | | +| approx_kl | 2.081037 | +| clip_fraction | 0.495 | +| clip_range | 0.2 | +| entropy_loss | -0.404 | +| explained_variance | -0.681 | +| learning_rate | 0.0001 | +| loss | -0.0815 | +| n_updates | 73610 | +| policy_gradient_loss | -0.071 | +| value_loss | 0.000329 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.216 | +| time/ | | +| fps | 310 | +| iterations | 1310 | +| time_elapsed | 4322 | +| total_timesteps | 1341440 | +| train/ | | +| approx_kl | 1.8933965 | +| clip_fraction | 0.499 | +| clip_range | 0.2 | +| entropy_loss | -0.434 | +| explained_variance | -1.51 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 73620 | +| policy_gradient_loss | -0.0654 | +| value_loss | 0.000396 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.22 | +| time/ | | +| fps | 310 | +| iterations | 1311 | +| time_elapsed | 4326 | +| total_timesteps | 1342464 | +| train/ | | +| approx_kl | 2.0024414 | +| clip_fraction | 0.531 | +| clip_range | 0.2 | +| entropy_loss | -0.514 | +| explained_variance | -0.892 | +| learning_rate | 0.0001 | +| loss | -0.1 | +| n_updates | 73630 | +| policy_gradient_loss | -0.0798 | +| value_loss | 0.000464 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.22 | +| time/ | | +| fps | 310 | +| iterations | 1312 | +| time_elapsed | 4329 | +| total_timesteps | 1343488 | +| train/ | | +| approx_kl | 2.1367717 | +| clip_fraction | 0.503 | +| clip_range | 0.2 | +| entropy_loss | -0.398 | +| explained_variance | -1.55 | +| learning_rate | 0.0001 | +| loss | -0.108 | +| n_updates | 73640 | +| policy_gradient_loss | -0.0676 | +| value_loss | 0.000619 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.216 | +| time/ | | +| fps | 310 | +| iterations | 1313 | +| time_elapsed | 4332 | +| total_timesteps | 1344512 | +| train/ | | +| approx_kl | 14.630033 | +| clip_fraction | 0.556 | +| clip_range | 0.2 | +| entropy_loss | -0.517 | +| explained_variance | -0.893 | +| learning_rate | 0.0001 | +| loss | -0.0796 | +| n_updates | 73650 | +| policy_gradient_loss | -0.0634 | +| value_loss | 0.000283 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.211 | +| time/ | | +| fps | 310 | +| iterations | 1314 | +| time_elapsed | 4336 | +| total_timesteps | 1345536 | +| train/ | | +| approx_kl | 1.5679442 | +| clip_fraction | 0.539 | +| clip_range | 0.2 | +| entropy_loss | -0.529 | +| explained_variance | -1.02 | +| learning_rate | 0.0001 | +| loss | -0.118 | +| n_updates | 73660 | +| policy_gradient_loss | -0.071 | +| value_loss | 0.000227 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.211 | +| time/ | | +| fps | 310 | +| iterations | 1315 | +| time_elapsed | 4339 | +| total_timesteps | 1346560 | +| train/ | | +| approx_kl | 3.5585222 | +| clip_fraction | 0.532 | +| clip_range | 0.2 | +| entropy_loss | -0.549 | +| explained_variance | -2 | +| learning_rate | 0.0001 | +| loss | -0.065 | +| n_updates | 73670 | +| policy_gradient_loss | -0.053 | +| value_loss | 0.000258 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.211 | +| time/ | | +| fps | 310 | +| iterations | 1316 | +| time_elapsed | 4342 | +| total_timesteps | 1347584 | +| train/ | | +| approx_kl | 3.1279619 | +| clip_fraction | 0.541 | +| clip_range | 0.2 | +| entropy_loss | -0.448 | +| explained_variance | -0.792 | +| learning_rate | 0.0001 | +| loss | -0.0938 | +| n_updates | 73680 | +| policy_gradient_loss | -0.0673 | +| value_loss | 0.000367 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.211 | +| time/ | | +| fps | 310 | +| iterations | 1317 | +| time_elapsed | 4345 | +| total_timesteps | 1348608 | +| train/ | | +| approx_kl | 2.047062 | +| clip_fraction | 0.528 | +| clip_range | 0.2 | +| entropy_loss | -0.48 | +| explained_variance | -1.59 | +| learning_rate | 0.0001 | +| loss | -0.0979 | +| n_updates | 73690 | +| policy_gradient_loss | -0.0717 | +| value_loss | 0.000878 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.21 | +| time/ | | +| fps | 310 | +| iterations | 1318 | +| time_elapsed | 4348 | +| total_timesteps | 1349632 | +| train/ | | +| approx_kl | 1.7233309 | +| clip_fraction | 0.505 | +| clip_range | 0.2 | +| entropy_loss | -0.475 | +| explained_variance | -0.995 | +| learning_rate | 0.0001 | +| loss | -0.0901 | +| n_updates | 73700 | +| policy_gradient_loss | -0.0748 | +| value_loss | 0.000528 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.204 | +| time/ | | +| fps | 310 | +| iterations | 1319 | +| time_elapsed | 4351 | +| total_timesteps | 1350656 | +| train/ | | +| approx_kl | 2.0315309 | +| clip_fraction | 0.518 | +| clip_range | 0.2 | +| entropy_loss | -0.48 | +| explained_variance | -0.702 | +| learning_rate | 0.0001 | +| loss | -0.108 | +| n_updates | 73710 | +| policy_gradient_loss | -0.0652 | +| value_loss | 0.000557 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.204 | +| time/ | | +| fps | 310 | +| iterations | 1320 | +| time_elapsed | 4355 | +| total_timesteps | 1351680 | +| train/ | | +| approx_kl | 1.9213665 | +| clip_fraction | 0.52 | +| clip_range | 0.2 | +| entropy_loss | -0.49 | +| explained_variance | -2.9 | +| learning_rate | 0.0001 | +| loss | -0.0824 | +| n_updates | 73720 | +| policy_gradient_loss | -0.0701 | +| value_loss | 0.000455 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.204 | +| time/ | | +| fps | 310 | +| iterations | 1321 | +| time_elapsed | 4358 | +| total_timesteps | 1352704 | +| train/ | | +| approx_kl | 1.6699471 | +| clip_fraction | 0.507 | +| clip_range | 0.2 | +| entropy_loss | -0.453 | +| explained_variance | -1.78 | +| learning_rate | 0.0001 | +| loss | -0.109 | +| n_updates | 73730 | +| policy_gradient_loss | -0.0682 | +| value_loss | 0.000439 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.205 | +| time/ | | +| fps | 310 | +| iterations | 1322 | +| time_elapsed | 4361 | +| total_timesteps | 1353728 | +| train/ | | +| approx_kl | 2.0277638 | +| clip_fraction | 0.54 | +| clip_range | 0.2 | +| entropy_loss | -0.469 | +| explained_variance | -3.68 | +| learning_rate | 0.0001 | +| loss | 0.000977 | +| n_updates | 73740 | +| policy_gradient_loss | -0.0732 | +| value_loss | 0.000225 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.202 | +| time/ | | +| fps | 310 | +| iterations | 1323 | +| time_elapsed | 4365 | +| total_timesteps | 1354752 | +| train/ | | +| approx_kl | 6.5859823 | +| clip_fraction | 0.527 | +| clip_range | 0.2 | +| entropy_loss | -0.55 | +| explained_variance | -0.914 | +| learning_rate | 0.0001 | +| loss | -0.091 | +| n_updates | 73750 | +| policy_gradient_loss | -0.0633 | +| value_loss | 0.000201 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.202 | +| time/ | | +| fps | 310 | +| iterations | 1324 | +| time_elapsed | 4368 | +| total_timesteps | 1355776 | +| train/ | | +| approx_kl | 1.9681145 | +| clip_fraction | 0.512 | +| clip_range | 0.2 | +| entropy_loss | -0.423 | +| explained_variance | -1.43 | +| learning_rate | 0.0001 | +| loss | -0.0643 | +| n_updates | 73760 | +| policy_gradient_loss | -0.0605 | +| value_loss | 0.000317 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.204 | +| time/ | | +| fps | 310 | +| iterations | 1325 | +| time_elapsed | 4371 | +| total_timesteps | 1356800 | +| train/ | | +| approx_kl | 2.0987546 | +| clip_fraction | 0.519 | +| clip_range | 0.2 | +| entropy_loss | -0.472 | +| explained_variance | -1.16 | +| learning_rate | 0.0001 | +| loss | -0.121 | +| n_updates | 73770 | +| policy_gradient_loss | -0.0684 | +| value_loss | 0.000535 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.204 | +| time/ | | +| fps | 310 | +| iterations | 1326 | +| time_elapsed | 4375 | +| total_timesteps | 1357824 | +| train/ | | +| approx_kl | 1.9395676 | +| clip_fraction | 0.522 | +| clip_range | 0.2 | +| entropy_loss | -0.434 | +| explained_variance | -0.962 | +| learning_rate | 0.0001 | +| loss | -0.075 | +| n_updates | 73780 | +| policy_gradient_loss | -0.0672 | +| value_loss | 0.000825 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.205 | +| time/ | | +| fps | 310 | +| iterations | 1327 | +| time_elapsed | 4378 | +| total_timesteps | 1358848 | +| train/ | | +| approx_kl | 2.1745992 | +| clip_fraction | 0.525 | +| clip_range | 0.2 | +| entropy_loss | -0.448 | +| explained_variance | -4.26 | +| learning_rate | 0.0001 | +| loss | -0.0812 | +| n_updates | 73790 | +| policy_gradient_loss | -0.0666 | +| value_loss | 0.000497 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.205 | +| time/ | | +| fps | 310 | +| iterations | 1328 | +| time_elapsed | 4382 | +| total_timesteps | 1359872 | +| train/ | | +| approx_kl | 2.6361341 | +| clip_fraction | 0.507 | +| clip_range | 0.2 | +| entropy_loss | -0.435 | +| explained_variance | -1.74 | +| learning_rate | 0.0001 | +| loss | -0.0967 | +| n_updates | 73800 | +| policy_gradient_loss | -0.074 | +| value_loss | 0.000352 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.205 | +| time/ | | +| fps | 310 | +| iterations | 1329 | +| time_elapsed | 4385 | +| total_timesteps | 1360896 | +| train/ | | +| approx_kl | 1.6621883 | +| clip_fraction | 0.506 | +| clip_range | 0.2 | +| entropy_loss | -0.465 | +| explained_variance | -0.923 | +| learning_rate | 0.0001 | +| loss | -0.0846 | +| n_updates | 73810 | +| policy_gradient_loss | -0.0762 | +| value_loss | 0.000566 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.204 | +| time/ | | +| fps | 310 | +| iterations | 1330 | +| time_elapsed | 4388 | +| total_timesteps | 1361920 | +| train/ | | +| approx_kl | 2.5163918 | +| clip_fraction | 0.575 | +| clip_range | 0.2 | +| entropy_loss | -0.564 | +| explained_variance | -2.14 | +| learning_rate | 0.0001 | +| loss | -0.0961 | +| n_updates | 73820 | +| policy_gradient_loss | -0.0659 | +| value_loss | 0.000356 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.204 | +| time/ | | +| fps | 310 | +| iterations | 1331 | +| time_elapsed | 4391 | +| total_timesteps | 1362944 | +| train/ | | +| approx_kl | 2.966876 | +| clip_fraction | 0.501 | +| clip_range | 0.2 | +| entropy_loss | -0.439 | +| explained_variance | -0.883 | +| learning_rate | 0.0001 | +| loss | -0.0823 | +| n_updates | 73830 | +| policy_gradient_loss | -0.0679 | +| value_loss | 0.000296 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | 0.207 | +| time/ | | +| fps | 310 | +| iterations | 1332 | +| time_elapsed | 4395 | +| total_timesteps | 1363968 | +| train/ | | +| approx_kl | 2.045199 | +| clip_fraction | 0.515 | +| clip_range | 0.2 | +| entropy_loss | -0.459 | +| explained_variance | -1.03 | +| learning_rate | 0.0001 | +| loss | -0.0726 | +| n_updates | 73840 | +| policy_gradient_loss | -0.0694 | +| value_loss | 0.000323 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | 0.207 | +| time/ | | +| fps | 310 | +| iterations | 1333 | +| time_elapsed | 4398 | +| total_timesteps | 1364992 | +| train/ | | +| approx_kl | 2.1324973 | +| clip_fraction | 0.58 | +| clip_range | 0.2 | +| entropy_loss | -0.531 | +| explained_variance | -0.782 | +| learning_rate | 0.0001 | +| loss | -0.0994 | +| n_updates | 73850 | +| policy_gradient_loss | -0.0774 | +| value_loss | 0.000283 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | 0.204 | +| time/ | | +| fps | 310 | +| iterations | 1334 | +| time_elapsed | 4401 | +| total_timesteps | 1366016 | +| train/ | | +| approx_kl | 1.9370662 | +| clip_fraction | 0.537 | +| clip_range | 0.2 | +| entropy_loss | -0.502 | +| explained_variance | -2 | +| learning_rate | 0.0001 | +| loss | -0.0775 | +| n_updates | 73860 | +| policy_gradient_loss | -0.0629 | +| value_loss | 0.000383 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | 0.204 | +| time/ | | +| fps | 310 | +| iterations | 1335 | +| time_elapsed | 4404 | +| total_timesteps | 1367040 | +| train/ | | +| approx_kl | 1.9596515 | +| clip_fraction | 0.515 | +| clip_range | 0.2 | +| entropy_loss | -0.468 | +| explained_variance | -2.27 | +| learning_rate | 0.0001 | +| loss | -0.0775 | +| n_updates | 73870 | +| policy_gradient_loss | -0.0748 | +| value_loss | 0.000421 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.204 | +| time/ | | +| fps | 310 | +| iterations | 1336 | +| time_elapsed | 4407 | +| total_timesteps | 1368064 | +| train/ | | +| approx_kl | 2.276091 | +| clip_fraction | 0.512 | +| clip_range | 0.2 | +| entropy_loss | -0.426 | +| explained_variance | -3.39 | +| learning_rate | 0.0001 | +| loss | -0.0822 | +| n_updates | 73880 | +| policy_gradient_loss | -0.0674 | +| value_loss | 0.000616 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.204 | +| time/ | | +| fps | 310 | +| iterations | 1337 | +| time_elapsed | 4411 | +| total_timesteps | 1369088 | +| train/ | | +| approx_kl | 2.6390169 | +| clip_fraction | 0.506 | +| clip_range | 0.2 | +| entropy_loss | -0.447 | +| explained_variance | -2.07 | +| learning_rate | 0.0001 | +| loss | -0.0954 | +| n_updates | 73890 | +| policy_gradient_loss | -0.0624 | +| value_loss | 0.000677 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.205 | +| time/ | | +| fps | 310 | +| iterations | 1338 | +| time_elapsed | 4414 | +| total_timesteps | 1370112 | +| train/ | | +| approx_kl | 2.1851888 | +| clip_fraction | 0.537 | +| clip_range | 0.2 | +| entropy_loss | -0.523 | +| explained_variance | -1.24 | +| learning_rate | 0.0001 | +| loss | -0.115 | +| n_updates | 73900 | +| policy_gradient_loss | -0.0759 | +| value_loss | 0.000355 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.203 | +| time/ | | +| fps | 310 | +| iterations | 1339 | +| time_elapsed | 4417 | +| total_timesteps | 1371136 | +| train/ | | +| approx_kl | 2.0114632 | +| clip_fraction | 0.491 | +| clip_range | 0.2 | +| entropy_loss | -0.456 | +| explained_variance | -1.69 | +| learning_rate | 0.0001 | +| loss | -0.0778 | +| n_updates | 73910 | +| policy_gradient_loss | -0.0676 | +| value_loss | 0.000167 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.201 | +| time/ | | +| fps | 310 | +| iterations | 1340 | +| time_elapsed | 4420 | +| total_timesteps | 1372160 | +| train/ | | +| approx_kl | 2.442737 | +| clip_fraction | 0.517 | +| clip_range | 0.2 | +| entropy_loss | -0.468 | +| explained_variance | -0.766 | +| learning_rate | 0.0001 | +| loss | -0.0742 | +| n_updates | 73920 | +| policy_gradient_loss | -0.057 | +| value_loss | 0.000184 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.65e+03 | +| ep_rew_mean | 0.194 | +| time/ | | +| fps | 310 | +| iterations | 1341 | +| time_elapsed | 4424 | +| total_timesteps | 1373184 | +| train/ | | +| approx_kl | 1.6817997 | +| clip_fraction | 0.473 | +| clip_range | 0.2 | +| entropy_loss | -0.427 | +| explained_variance | -1.64 | +| learning_rate | 0.0001 | +| loss | -0.0827 | +| n_updates | 73930 | +| policy_gradient_loss | -0.0655 | +| value_loss | 0.00031 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.65e+03 | +| ep_rew_mean | 0.194 | +| time/ | | +| fps | 310 | +| iterations | 1342 | +| time_elapsed | 4427 | +| total_timesteps | 1374208 | +| train/ | | +| approx_kl | 1.4120057 | +| clip_fraction | 0.497 | +| clip_range | 0.2 | +| entropy_loss | -0.494 | +| explained_variance | -0.712 | +| learning_rate | 0.0001 | +| loss | -0.081 | +| n_updates | 73940 | +| policy_gradient_loss | -0.0642 | +| value_loss | 0.000378 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | 0.194 | +| time/ | | +| fps | 310 | +| iterations | 1343 | +| time_elapsed | 4431 | +| total_timesteps | 1375232 | +| train/ | | +| approx_kl | 2.087143 | +| clip_fraction | 0.504 | +| clip_range | 0.2 | +| entropy_loss | -0.408 | +| explained_variance | -2.08 | +| learning_rate | 0.0001 | +| loss | -0.0782 | +| n_updates | 73950 | +| policy_gradient_loss | -0.0569 | +| value_loss | 0.000375 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | 0.194 | +| time/ | | +| fps | 310 | +| iterations | 1344 | +| time_elapsed | 4434 | +| total_timesteps | 1376256 | +| train/ | | +| approx_kl | 1.6089389 | +| clip_fraction | 0.497 | +| clip_range | 0.2 | +| entropy_loss | -0.443 | +| explained_variance | -1.41 | +| learning_rate | 0.0001 | +| loss | -0.0946 | +| n_updates | 73960 | +| policy_gradient_loss | -0.0718 | +| value_loss | 0.000484 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.2 | +| time/ | | +| fps | 310 | +| iterations | 1345 | +| time_elapsed | 4437 | +| total_timesteps | 1377280 | +| train/ | | +| approx_kl | 2.226209 | +| clip_fraction | 0.518 | +| clip_range | 0.2 | +| entropy_loss | -0.474 | +| explained_variance | -2.5 | +| learning_rate | 0.0001 | +| loss | -0.072 | +| n_updates | 73970 | +| policy_gradient_loss | -0.0746 | +| value_loss | 0.000817 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.203 | +| time/ | | +| fps | 310 | +| iterations | 1346 | +| time_elapsed | 4441 | +| total_timesteps | 1378304 | +| train/ | | +| approx_kl | 1.5922666 | +| clip_fraction | 0.5 | +| clip_range | 0.2 | +| entropy_loss | -0.481 | +| explained_variance | -1.43 | +| learning_rate | 0.0001 | +| loss | -0.108 | +| n_updates | 73980 | +| policy_gradient_loss | -0.0697 | +| value_loss | 0.000358 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.203 | +| time/ | | +| fps | 310 | +| iterations | 1347 | +| time_elapsed | 4444 | +| total_timesteps | 1379328 | +| train/ | | +| approx_kl | 1.5502994 | +| clip_fraction | 0.525 | +| clip_range | 0.2 | +| entropy_loss | -0.479 | +| explained_variance | -0.638 | +| learning_rate | 0.0001 | +| loss | -0.0961 | +| n_updates | 73990 | +| policy_gradient_loss | -0.0687 | +| value_loss | 0.000476 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.204 | +| time/ | | +| fps | 310 | +| iterations | 1348 | +| time_elapsed | 4448 | +| total_timesteps | 1380352 | +| train/ | | +| approx_kl | 1.3134031 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.526 | +| explained_variance | -1.48 | +| learning_rate | 0.0001 | +| loss | -0.0911 | +| n_updates | 74000 | +| policy_gradient_loss | -0.07 | +| value_loss | 0.000433 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.204 | +| time/ | | +| fps | 310 | +| iterations | 1349 | +| time_elapsed | 4451 | +| total_timesteps | 1381376 | +| train/ | | +| approx_kl | 1.3526766 | +| clip_fraction | 0.512 | +| clip_range | 0.2 | +| entropy_loss | -0.548 | +| explained_variance | -5.16 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 74010 | +| policy_gradient_loss | -0.0673 | +| value_loss | 0.000389 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.203 | +| time/ | | +| fps | 310 | +| iterations | 1350 | +| time_elapsed | 4454 | +| total_timesteps | 1382400 | +| train/ | | +| approx_kl | 1.1565977 | +| clip_fraction | 0.495 | +| clip_range | 0.2 | +| entropy_loss | -0.492 | +| explained_variance | -1.2 | +| learning_rate | 0.0001 | +| loss | -0.0695 | +| n_updates | 74020 | +| policy_gradient_loss | -0.0674 | +| value_loss | 0.000352 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.203 | +| time/ | | +| fps | 310 | +| iterations | 1351 | +| time_elapsed | 4457 | +| total_timesteps | 1383424 | +| train/ | | +| approx_kl | 2.1918745 | +| clip_fraction | 0.537 | +| clip_range | 0.2 | +| entropy_loss | -0.469 | +| explained_variance | -1.16 | +| learning_rate | 0.0001 | +| loss | -0.0871 | +| n_updates | 74030 | +| policy_gradient_loss | -0.0628 | +| value_loss | 0.000578 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.201 | +| time/ | | +| fps | 310 | +| iterations | 1352 | +| time_elapsed | 4460 | +| total_timesteps | 1384448 | +| train/ | | +| approx_kl | 1.7279103 | +| clip_fraction | 0.573 | +| clip_range | 0.2 | +| entropy_loss | -0.561 | +| explained_variance | -2.56 | +| learning_rate | 0.0001 | +| loss | -0.0862 | +| n_updates | 74040 | +| policy_gradient_loss | -0.057 | +| value_loss | 0.00068 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.203 | +| time/ | | +| fps | 310 | +| iterations | 1353 | +| time_elapsed | 4463 | +| total_timesteps | 1385472 | +| train/ | | +| approx_kl | 1.238361 | +| clip_fraction | 0.499 | +| clip_range | 0.2 | +| entropy_loss | -0.564 | +| explained_variance | -1.54 | +| learning_rate | 0.0001 | +| loss | -0.0893 | +| n_updates | 74050 | +| policy_gradient_loss | -0.0591 | +| value_loss | 0.000249 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.203 | +| time/ | | +| fps | 310 | +| iterations | 1354 | +| time_elapsed | 4466 | +| total_timesteps | 1386496 | +| train/ | | +| approx_kl | 1.445123 | +| clip_fraction | 0.49 | +| clip_range | 0.2 | +| entropy_loss | -0.494 | +| explained_variance | -1.16 | +| learning_rate | 0.0001 | +| loss | -0.0818 | +| n_updates | 74060 | +| policy_gradient_loss | -0.0706 | +| value_loss | 0.000276 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.203 | +| time/ | | +| fps | 310 | +| iterations | 1355 | +| time_elapsed | 4470 | +| total_timesteps | 1387520 | +| train/ | | +| approx_kl | 1.7137353 | +| clip_fraction | 0.493 | +| clip_range | 0.2 | +| entropy_loss | -0.51 | +| explained_variance | -1.04 | +| learning_rate | 0.0001 | +| loss | -0.0932 | +| n_updates | 74070 | +| policy_gradient_loss | -0.0645 | +| value_loss | 0.00043 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.206 | +| time/ | | +| fps | 310 | +| iterations | 1356 | +| time_elapsed | 4473 | +| total_timesteps | 1388544 | +| train/ | | +| approx_kl | 2.4888384 | +| clip_fraction | 0.536 | +| clip_range | 0.2 | +| entropy_loss | -0.44 | +| explained_variance | -1.97 | +| learning_rate | 0.0001 | +| loss | -0.0976 | +| n_updates | 74080 | +| policy_gradient_loss | -0.0771 | +| value_loss | 0.000535 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.206 | +| time/ | | +| fps | 310 | +| iterations | 1357 | +| time_elapsed | 4476 | +| total_timesteps | 1389568 | +| train/ | | +| approx_kl | 2.097807 | +| clip_fraction | 0.51 | +| clip_range | 0.2 | +| entropy_loss | -0.434 | +| explained_variance | -0.706 | +| learning_rate | 0.0001 | +| loss | -0.117 | +| n_updates | 74090 | +| policy_gradient_loss | -0.0667 | +| value_loss | 0.000722 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.204 | +| time/ | | +| fps | 310 | +| iterations | 1358 | +| time_elapsed | 4479 | +| total_timesteps | 1390592 | +| train/ | | +| approx_kl | 1.8101192 | +| clip_fraction | 0.464 | +| clip_range | 0.2 | +| entropy_loss | -0.383 | +| explained_variance | -10.8 | +| learning_rate | 0.0001 | +| loss | -0.0902 | +| n_updates | 74100 | +| policy_gradient_loss | -0.0671 | +| value_loss | 0.000415 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.202 | +| time/ | | +| fps | 310 | +| iterations | 1359 | +| time_elapsed | 4482 | +| total_timesteps | 1391616 | +| train/ | | +| approx_kl | 2.1939664 | +| clip_fraction | 0.524 | +| clip_range | 0.2 | +| entropy_loss | -0.42 | +| explained_variance | -0.677 | +| learning_rate | 0.0001 | +| loss | -0.0596 | +| n_updates | 74110 | +| policy_gradient_loss | -0.0625 | +| value_loss | 0.000349 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.202 | +| time/ | | +| fps | 310 | +| iterations | 1360 | +| time_elapsed | 4486 | +| total_timesteps | 1392640 | +| train/ | | +| approx_kl | 1.4071105 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.496 | +| explained_variance | -1.21 | +| learning_rate | 0.0001 | +| loss | -0.0845 | +| n_updates | 74120 | +| policy_gradient_loss | -0.0593 | +| value_loss | 0.000302 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.204 | +| time/ | | +| fps | 310 | +| iterations | 1361 | +| time_elapsed | 4489 | +| total_timesteps | 1393664 | +| train/ | | +| approx_kl | 1.9592928 | +| clip_fraction | 0.496 | +| clip_range | 0.2 | +| entropy_loss | -0.545 | +| explained_variance | -0.731 | +| learning_rate | 0.0001 | +| loss | -0.1 | +| n_updates | 74130 | +| policy_gradient_loss | -0.0657 | +| value_loss | 0.000275 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.205 | +| time/ | | +| fps | 310 | +| iterations | 1362 | +| time_elapsed | 4493 | +| total_timesteps | 1394688 | +| train/ | | +| approx_kl | 1.4994385 | +| clip_fraction | 0.493 | +| clip_range | 0.2 | +| entropy_loss | -0.504 | +| explained_variance | -0.801 | +| learning_rate | 0.0001 | +| loss | -0.079 | +| n_updates | 74140 | +| policy_gradient_loss | -0.073 | +| value_loss | 0.000461 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.205 | +| time/ | | +| fps | 310 | +| iterations | 1363 | +| time_elapsed | 4496 | +| total_timesteps | 1395712 | +| train/ | | +| approx_kl | 1.4667051 | +| clip_fraction | 0.543 | +| clip_range | 0.2 | +| entropy_loss | -0.581 | +| explained_variance | -1.74 | +| learning_rate | 0.0001 | +| loss | -0.0774 | +| n_updates | 74150 | +| policy_gradient_loss | -0.0666 | +| value_loss | 0.000195 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.208 | +| time/ | | +| fps | 310 | +| iterations | 1364 | +| time_elapsed | 4499 | +| total_timesteps | 1396736 | +| train/ | | +| approx_kl | 1.5919976 | +| clip_fraction | 0.518 | +| clip_range | 0.2 | +| entropy_loss | -0.559 | +| explained_variance | -0.59 | +| learning_rate | 0.0001 | +| loss | -0.0782 | +| n_updates | 74160 | +| policy_gradient_loss | -0.0677 | +| value_loss | 0.000322 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.208 | +| time/ | | +| fps | 310 | +| iterations | 1365 | +| time_elapsed | 4503 | +| total_timesteps | 1397760 | +| train/ | | +| approx_kl | 1.6683356 | +| clip_fraction | 0.477 | +| clip_range | 0.2 | +| entropy_loss | -0.448 | +| explained_variance | -3.12 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 74170 | +| policy_gradient_loss | -0.0689 | +| value_loss | 0.000339 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.212 | +| time/ | | +| fps | 310 | +| iterations | 1366 | +| time_elapsed | 4506 | +| total_timesteps | 1398784 | +| train/ | | +| approx_kl | 5.3959837 | +| clip_fraction | 0.523 | +| clip_range | 0.2 | +| entropy_loss | -0.559 | +| explained_variance | -1.07 | +| learning_rate | 0.0001 | +| loss | -0.0805 | +| n_updates | 74180 | +| policy_gradient_loss | -0.065 | +| value_loss | 0.000505 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.21 | +| time/ | | +| fps | 310 | +| iterations | 1367 | +| time_elapsed | 4509 | +| total_timesteps | 1399808 | +| train/ | | +| approx_kl | 1.7638345 | +| clip_fraction | 0.49 | +| clip_range | 0.2 | +| entropy_loss | -0.493 | +| explained_variance | -1.13 | +| learning_rate | 0.0001 | +| loss | -0.0922 | +| n_updates | 74190 | +| policy_gradient_loss | -0.0672 | +| value_loss | 0.000274 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.21 | +| time/ | | +| fps | 310 | +| iterations | 1368 | +| time_elapsed | 4513 | +| total_timesteps | 1400832 | +| train/ | | +| approx_kl | 2.0084364 | +| clip_fraction | 0.489 | +| clip_range | 0.2 | +| entropy_loss | -0.411 | +| explained_variance | -1.57 | +| learning_rate | 0.0001 | +| loss | -0.1 | +| n_updates | 74200 | +| policy_gradient_loss | -0.0673 | +| value_loss | 0.000812 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.214 | +| time/ | | +| fps | 310 | +| iterations | 1369 | +| time_elapsed | 4516 | +| total_timesteps | 1401856 | +| train/ | | +| approx_kl | 1.8455478 | +| clip_fraction | 0.514 | +| clip_range | 0.2 | +| entropy_loss | -0.475 | +| explained_variance | -2.8 | +| learning_rate | 0.0001 | +| loss | -0.0925 | +| n_updates | 74210 | +| policy_gradient_loss | -0.0731 | +| value_loss | 0.000396 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.214 | +| time/ | | +| fps | 310 | +| iterations | 1370 | +| time_elapsed | 4519 | +| total_timesteps | 1402880 | +| train/ | | +| approx_kl | 2.628254 | +| clip_fraction | 0.504 | +| clip_range | 0.2 | +| entropy_loss | -0.394 | +| explained_variance | -0.844 | +| learning_rate | 0.0001 | +| loss | -0.0991 | +| n_updates | 74220 | +| policy_gradient_loss | -0.0679 | +| value_loss | 0.000521 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.216 | +| time/ | | +| fps | 310 | +| iterations | 1371 | +| time_elapsed | 4522 | +| total_timesteps | 1403904 | +| train/ | | +| approx_kl | 1.6807482 | +| clip_fraction | 0.473 | +| clip_range | 0.2 | +| entropy_loss | -0.421 | +| explained_variance | -1.04 | +| learning_rate | 0.0001 | +| loss | -0.0924 | +| n_updates | 74230 | +| policy_gradient_loss | -0.0683 | +| value_loss | 0.000513 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.22 | +| time/ | | +| fps | 310 | +| iterations | 1372 | +| time_elapsed | 4525 | +| total_timesteps | 1404928 | +| train/ | | +| approx_kl | 1.5938382 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.49 | +| explained_variance | -0.794 | +| learning_rate | 0.0001 | +| loss | -0.0809 | +| n_updates | 74240 | +| policy_gradient_loss | -0.0647 | +| value_loss | 0.000707 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.22 | +| time/ | | +| fps | 310 | +| iterations | 1373 | +| time_elapsed | 4529 | +| total_timesteps | 1405952 | +| train/ | | +| approx_kl | 1.5092907 | +| clip_fraction | 0.493 | +| clip_range | 0.2 | +| entropy_loss | -0.445 | +| explained_variance | -0.836 | +| learning_rate | 0.0001 | +| loss | -0.0716 | +| n_updates | 74250 | +| policy_gradient_loss | -0.0608 | +| value_loss | 0.000534 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.22 | +| time/ | | +| fps | 310 | +| iterations | 1374 | +| time_elapsed | 4532 | +| total_timesteps | 1406976 | +| train/ | | +| approx_kl | 2.6109424 | +| clip_fraction | 0.53 | +| clip_range | 0.2 | +| entropy_loss | -0.375 | +| explained_variance | -1.8 | +| learning_rate | 0.0001 | +| loss | -0.0744 | +| n_updates | 74260 | +| policy_gradient_loss | -0.0705 | +| value_loss | 0.000748 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.223 | +| time/ | | +| fps | 310 | +| iterations | 1375 | +| time_elapsed | 4535 | +| total_timesteps | 1408000 | +| train/ | | +| approx_kl | 2.0929108 | +| clip_fraction | 0.494 | +| clip_range | 0.2 | +| entropy_loss | -0.422 | +| explained_variance | -1.82 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 74270 | +| policy_gradient_loss | -0.0651 | +| value_loss | 0.000509 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.223 | +| time/ | | +| fps | 310 | +| iterations | 1376 | +| time_elapsed | 4538 | +| total_timesteps | 1409024 | +| train/ | | +| approx_kl | 1.7879846 | +| clip_fraction | 0.546 | +| clip_range | 0.2 | +| entropy_loss | -0.527 | +| explained_variance | -1.15 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 74280 | +| policy_gradient_loss | -0.0712 | +| value_loss | 0.000383 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.226 | +| time/ | | +| fps | 310 | +| iterations | 1377 | +| time_elapsed | 4542 | +| total_timesteps | 1410048 | +| train/ | | +| approx_kl | 2.3123202 | +| clip_fraction | 0.539 | +| clip_range | 0.2 | +| entropy_loss | -0.446 | +| explained_variance | -2.41 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 74290 | +| policy_gradient_loss | -0.0711 | +| value_loss | 0.000466 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.226 | +| time/ | | +| fps | 310 | +| iterations | 1378 | +| time_elapsed | 4545 | +| total_timesteps | 1411072 | +| train/ | | +| approx_kl | 2.0367217 | +| clip_fraction | 0.547 | +| clip_range | 0.2 | +| entropy_loss | -0.493 | +| explained_variance | -0.758 | +| learning_rate | 0.0001 | +| loss | -0.107 | +| n_updates | 74300 | +| policy_gradient_loss | -0.0753 | +| value_loss | 0.000311 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.224 | +| time/ | | +| fps | 310 | +| iterations | 1379 | +| time_elapsed | 4549 | +| total_timesteps | 1412096 | +| train/ | | +| approx_kl | 2.3895628 | +| clip_fraction | 0.553 | +| clip_range | 0.2 | +| entropy_loss | -0.501 | +| explained_variance | -4.02 | +| learning_rate | 0.0001 | +| loss | -0.0938 | +| n_updates | 74310 | +| policy_gradient_loss | -0.07 | +| value_loss | 0.000214 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.22 | +| time/ | | +| fps | 310 | +| iterations | 1380 | +| time_elapsed | 4552 | +| total_timesteps | 1413120 | +| train/ | | +| approx_kl | 1.4215134 | +| clip_fraction | 0.523 | +| clip_range | 0.2 | +| entropy_loss | -0.595 | +| explained_variance | -1.46 | +| learning_rate | 0.0001 | +| loss | -0.0941 | +| n_updates | 74320 | +| policy_gradient_loss | -0.0675 | +| value_loss | 0.000233 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.22 | +| time/ | | +| fps | 310 | +| iterations | 1381 | +| time_elapsed | 4556 | +| total_timesteps | 1414144 | +| train/ | | +| approx_kl | 21.914532 | +| clip_fraction | 0.538 | +| clip_range | 0.2 | +| entropy_loss | -0.54 | +| explained_variance | -1.28 | +| learning_rate | 0.0001 | +| loss | -0.0765 | +| n_updates | 74330 | +| policy_gradient_loss | -0.0669 | +| value_loss | 0.000794 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.222 | +| time/ | | +| fps | 310 | +| iterations | 1382 | +| time_elapsed | 4559 | +| total_timesteps | 1415168 | +| train/ | | +| approx_kl | 1.7991791 | +| clip_fraction | 0.529 | +| clip_range | 0.2 | +| entropy_loss | -0.53 | +| explained_variance | -4.55 | +| learning_rate | 0.0001 | +| loss | -0.0972 | +| n_updates | 74340 | +| policy_gradient_loss | -0.0714 | +| value_loss | 0.000248 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.222 | +| time/ | | +| fps | 310 | +| iterations | 1383 | +| time_elapsed | 4563 | +| total_timesteps | 1416192 | +| train/ | | +| approx_kl | 1.897383 | +| clip_fraction | 0.517 | +| clip_range | 0.2 | +| entropy_loss | -0.465 | +| explained_variance | -2.22 | +| learning_rate | 0.0001 | +| loss | -0.105 | +| n_updates | 74350 | +| policy_gradient_loss | -0.0725 | +| value_loss | 0.000207 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.222 | +| time/ | | +| fps | 310 | +| iterations | 1384 | +| time_elapsed | 4567 | +| total_timesteps | 1417216 | +| train/ | | +| approx_kl | 2.196766 | +| clip_fraction | 0.545 | +| clip_range | 0.2 | +| entropy_loss | -0.506 | +| explained_variance | -1.78 | +| learning_rate | 0.0001 | +| loss | -0.0864 | +| n_updates | 74360 | +| policy_gradient_loss | -0.0664 | +| value_loss | 0.000724 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.225 | +| time/ | | +| fps | 310 | +| iterations | 1385 | +| time_elapsed | 4570 | +| total_timesteps | 1418240 | +| train/ | | +| approx_kl | 1.5669034 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.439 | +| explained_variance | -1.59 | +| learning_rate | 0.0001 | +| loss | -0.066 | +| n_updates | 74370 | +| policy_gradient_loss | -0.0549 | +| value_loss | 0.000427 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.222 | +| time/ | | +| fps | 310 | +| iterations | 1386 | +| time_elapsed | 4573 | +| total_timesteps | 1419264 | +| train/ | | +| approx_kl | 1.639761 | +| clip_fraction | 0.515 | +| clip_range | 0.2 | +| entropy_loss | -0.476 | +| explained_variance | -1.96 | +| learning_rate | 0.0001 | +| loss | -0.0848 | +| n_updates | 74380 | +| policy_gradient_loss | -0.0638 | +| value_loss | 0.000187 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.222 | +| time/ | | +| fps | 310 | +| iterations | 1387 | +| time_elapsed | 4576 | +| total_timesteps | 1420288 | +| train/ | | +| approx_kl | 1.4528863 | +| clip_fraction | 0.472 | +| clip_range | 0.2 | +| entropy_loss | -0.459 | +| explained_variance | -0.787 | +| learning_rate | 0.0001 | +| loss | -0.0826 | +| n_updates | 74390 | +| policy_gradient_loss | -0.062 | +| value_loss | 0.000284 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.223 | +| time/ | | +| fps | 310 | +| iterations | 1388 | +| time_elapsed | 4580 | +| total_timesteps | 1421312 | +| train/ | | +| approx_kl | 1.7788447 | +| clip_fraction | 0.498 | +| clip_range | 0.2 | +| entropy_loss | -0.55 | +| explained_variance | -1.03 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 74400 | +| policy_gradient_loss | -0.0641 | +| value_loss | 0.000392 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.229 | +| time/ | | +| fps | 310 | +| iterations | 1389 | +| time_elapsed | 4583 | +| total_timesteps | 1422336 | +| train/ | | +| approx_kl | 2.204398 | +| clip_fraction | 0.509 | +| clip_range | 0.2 | +| entropy_loss | -0.451 | +| explained_variance | -1.22 | +| learning_rate | 0.0001 | +| loss | -0.0825 | +| n_updates | 74410 | +| policy_gradient_loss | -0.074 | +| value_loss | 0.000581 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.229 | +| time/ | | +| fps | 310 | +| iterations | 1390 | +| time_elapsed | 4586 | +| total_timesteps | 1423360 | +| train/ | | +| approx_kl | 2.2134194 | +| clip_fraction | 0.474 | +| clip_range | 0.2 | +| entropy_loss | -0.413 | +| explained_variance | -3.33 | +| learning_rate | 0.0001 | +| loss | -0.076 | +| n_updates | 74420 | +| policy_gradient_loss | -0.0633 | +| value_loss | 0.000533 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.232 | +| time/ | | +| fps | 310 | +| iterations | 1391 | +| time_elapsed | 4589 | +| total_timesteps | 1424384 | +| train/ | | +| approx_kl | 1.7240627 | +| clip_fraction | 0.51 | +| clip_range | 0.2 | +| entropy_loss | -0.469 | +| explained_variance | -0.647 | +| learning_rate | 0.0001 | +| loss | -0.0956 | +| n_updates | 74430 | +| policy_gradient_loss | -0.0728 | +| value_loss | 0.000464 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.237 | +| time/ | | +| fps | 310 | +| iterations | 1392 | +| time_elapsed | 4592 | +| total_timesteps | 1425408 | +| train/ | | +| approx_kl | 3.002133 | +| clip_fraction | 0.509 | +| clip_range | 0.2 | +| entropy_loss | -0.471 | +| explained_variance | -0.515 | +| learning_rate | 0.0001 | +| loss | -0.0827 | +| n_updates | 74440 | +| policy_gradient_loss | -0.0738 | +| value_loss | 0.00108 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.237 | +| time/ | | +| fps | 310 | +| iterations | 1393 | +| time_elapsed | 4595 | +| total_timesteps | 1426432 | +| train/ | | +| approx_kl | 1.9777422 | +| clip_fraction | 0.514 | +| clip_range | 0.2 | +| entropy_loss | -0.445 | +| explained_variance | -1.79 | +| learning_rate | 0.0001 | +| loss | -0.0827 | +| n_updates | 74450 | +| policy_gradient_loss | -0.0591 | +| value_loss | 0.00083 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.238 | +| time/ | | +| fps | 310 | +| iterations | 1394 | +| time_elapsed | 4599 | +| total_timesteps | 1427456 | +| train/ | | +| approx_kl | 1.654149 | +| clip_fraction | 0.54 | +| clip_range | 0.2 | +| entropy_loss | -0.525 | +| explained_variance | -2.78 | +| learning_rate | 0.0001 | +| loss | -0.0968 | +| n_updates | 74460 | +| policy_gradient_loss | -0.0766 | +| value_loss | 0.000532 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.238 | +| time/ | | +| fps | 310 | +| iterations | 1395 | +| time_elapsed | 4602 | +| total_timesteps | 1428480 | +| train/ | | +| approx_kl | 1.7961614 | +| clip_fraction | 0.545 | +| clip_range | 0.2 | +| entropy_loss | -0.5 | +| explained_variance | -1.66 | +| learning_rate | 0.0001 | +| loss | -0.099 | +| n_updates | 74470 | +| policy_gradient_loss | -0.0661 | +| value_loss | 0.000283 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.233 | +| time/ | | +| fps | 310 | +| iterations | 1396 | +| time_elapsed | 4605 | +| total_timesteps | 1429504 | +| train/ | | +| approx_kl | 1.8317943 | +| clip_fraction | 0.484 | +| clip_range | 0.2 | +| entropy_loss | -0.475 | +| explained_variance | -1.8 | +| learning_rate | 0.0001 | +| loss | -0.0773 | +| n_updates | 74480 | +| policy_gradient_loss | -0.0669 | +| value_loss | 0.000194 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.233 | +| time/ | | +| fps | 310 | +| iterations | 1397 | +| time_elapsed | 4609 | +| total_timesteps | 1430528 | +| train/ | | +| approx_kl | 2.1275127 | +| clip_fraction | 0.464 | +| clip_range | 0.2 | +| entropy_loss | -0.412 | +| explained_variance | -0.674 | +| learning_rate | 0.0001 | +| loss | -0.084 | +| n_updates | 74490 | +| policy_gradient_loss | -0.0638 | +| value_loss | 0.000611 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.236 | +| time/ | | +| fps | 310 | +| iterations | 1398 | +| time_elapsed | 4612 | +| total_timesteps | 1431552 | +| train/ | | +| approx_kl | 1.9427307 | +| clip_fraction | 0.511 | +| clip_range | 0.2 | +| entropy_loss | -0.413 | +| explained_variance | -1.43 | +| learning_rate | 0.0001 | +| loss | -0.105 | +| n_updates | 74500 | +| policy_gradient_loss | -0.0718 | +| value_loss | 0.000656 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.235 | +| time/ | | +| fps | 310 | +| iterations | 1399 | +| time_elapsed | 4616 | +| total_timesteps | 1432576 | +| train/ | | +| approx_kl | 2.1513467 | +| clip_fraction | 0.539 | +| clip_range | 0.2 | +| entropy_loss | -0.49 | +| explained_variance | -1.19 | +| learning_rate | 0.0001 | +| loss | -0.0749 | +| n_updates | 74510 | +| policy_gradient_loss | -0.0662 | +| value_loss | 0.000426 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.235 | +| time/ | | +| fps | 310 | +| iterations | 1400 | +| time_elapsed | 4619 | +| total_timesteps | 1433600 | +| train/ | | +| approx_kl | 1.3029668 | +| clip_fraction | 0.424 | +| clip_range | 0.2 | +| entropy_loss | -0.402 | +| explained_variance | -0.507 | +| learning_rate | 0.0001 | +| loss | -0.0671 | +| n_updates | 74520 | +| policy_gradient_loss | -0.0563 | +| value_loss | 0.000253 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.231 | +| time/ | | +| fps | 310 | +| iterations | 1401 | +| time_elapsed | 4623 | +| total_timesteps | 1434624 | +| train/ | | +| approx_kl | 2.5463672 | +| clip_fraction | 0.517 | +| clip_range | 0.2 | +| entropy_loss | -0.463 | +| explained_variance | -2.01 | +| learning_rate | 0.0001 | +| loss | -0.136 | +| n_updates | 74530 | +| policy_gradient_loss | -0.0732 | +| value_loss | 0.000346 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.227 | +| time/ | | +| fps | 310 | +| iterations | 1402 | +| time_elapsed | 4626 | +| total_timesteps | 1435648 | +| train/ | | +| approx_kl | 1.9400632 | +| clip_fraction | 0.468 | +| clip_range | 0.2 | +| entropy_loss | -0.422 | +| explained_variance | -1.67 | +| learning_rate | 0.0001 | +| loss | -0.0669 | +| n_updates | 74540 | +| policy_gradient_loss | -0.0557 | +| value_loss | 0.000254 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.223 | +| time/ | | +| fps | 310 | +| iterations | 1403 | +| time_elapsed | 4629 | +| total_timesteps | 1436672 | +| train/ | | +| approx_kl | 2.0685523 | +| clip_fraction | 0.512 | +| clip_range | 0.2 | +| entropy_loss | -0.489 | +| explained_variance | -0.353 | +| learning_rate | 0.0001 | +| loss | -0.0773 | +| n_updates | 74550 | +| policy_gradient_loss | -0.0659 | +| value_loss | 0.000444 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.223 | +| time/ | | +| fps | 310 | +| iterations | 1404 | +| time_elapsed | 4632 | +| total_timesteps | 1437696 | +| train/ | | +| approx_kl | 2.305808 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.414 | +| explained_variance | -3.64 | +| learning_rate | 0.0001 | +| loss | -0.0783 | +| n_updates | 74560 | +| policy_gradient_loss | -0.0642 | +| value_loss | 0.000557 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.223 | +| time/ | | +| fps | 310 | +| iterations | 1405 | +| time_elapsed | 4636 | +| total_timesteps | 1438720 | +| train/ | | +| approx_kl | 1.8073733 | +| clip_fraction | 0.49 | +| clip_range | 0.2 | +| entropy_loss | -0.446 | +| explained_variance | -1.09 | +| learning_rate | 0.0001 | +| loss | -0.0952 | +| n_updates | 74570 | +| policy_gradient_loss | -0.072 | +| value_loss | 0.000619 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.223 | +| time/ | | +| fps | 310 | +| iterations | 1406 | +| time_elapsed | 4639 | +| total_timesteps | 1439744 | +| train/ | | +| approx_kl | 2.2224193 | +| clip_fraction | 0.516 | +| clip_range | 0.2 | +| entropy_loss | -0.475 | +| explained_variance | -1.21 | +| learning_rate | 0.0001 | +| loss | -0.0917 | +| n_updates | 74580 | +| policy_gradient_loss | -0.0635 | +| value_loss | 0.0004 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.222 | +| time/ | | +| fps | 310 | +| iterations | 1407 | +| time_elapsed | 4642 | +| total_timesteps | 1440768 | +| train/ | | +| approx_kl | 1.6666062 | +| clip_fraction | 0.515 | +| clip_range | 0.2 | +| entropy_loss | -0.489 | +| explained_variance | -1.49 | +| learning_rate | 0.0001 | +| loss | -0.0243 | +| n_updates | 74590 | +| policy_gradient_loss | -0.065 | +| value_loss | 0.000468 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.224 | +| time/ | | +| fps | 310 | +| iterations | 1408 | +| time_elapsed | 4645 | +| total_timesteps | 1441792 | +| train/ | | +| approx_kl | 1.6146026 | +| clip_fraction | 0.495 | +| clip_range | 0.2 | +| entropy_loss | -0.478 | +| explained_variance | -1.64 | +| learning_rate | 0.0001 | +| loss | -0.0955 | +| n_updates | 74600 | +| policy_gradient_loss | -0.0673 | +| value_loss | 0.000319 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.224 | +| time/ | | +| fps | 310 | +| iterations | 1409 | +| time_elapsed | 4648 | +| total_timesteps | 1442816 | +| train/ | | +| approx_kl | 1.5139724 | +| clip_fraction | 0.486 | +| clip_range | 0.2 | +| entropy_loss | -0.465 | +| explained_variance | -1.13 | +| learning_rate | 0.0001 | +| loss | -0.0841 | +| n_updates | 74610 | +| policy_gradient_loss | -0.0669 | +| value_loss | 0.000469 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.224 | +| time/ | | +| fps | 310 | +| iterations | 1410 | +| time_elapsed | 4651 | +| total_timesteps | 1443840 | +| train/ | | +| approx_kl | 2.7286072 | +| clip_fraction | 0.549 | +| clip_range | 0.2 | +| entropy_loss | -0.453 | +| explained_variance | -1.45 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 74620 | +| policy_gradient_loss | -0.077 | +| value_loss | 0.000541 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.225 | +| time/ | | +| fps | 310 | +| iterations | 1411 | +| time_elapsed | 4654 | +| total_timesteps | 1444864 | +| train/ | | +| approx_kl | 2.7104273 | +| clip_fraction | 0.511 | +| clip_range | 0.2 | +| entropy_loss | -0.423 | +| explained_variance | -0.972 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 74630 | +| policy_gradient_loss | -0.0637 | +| value_loss | 0.00103 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.223 | +| time/ | | +| fps | 310 | +| iterations | 1412 | +| time_elapsed | 4658 | +| total_timesteps | 1445888 | +| train/ | | +| approx_kl | 3.4815283 | +| clip_fraction | 0.494 | +| clip_range | 0.2 | +| entropy_loss | -0.434 | +| explained_variance | -1.31 | +| learning_rate | 0.0001 | +| loss | -0.0731 | +| n_updates | 74640 | +| policy_gradient_loss | -0.0499 | +| value_loss | 0.000481 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.223 | +| time/ | | +| fps | 310 | +| iterations | 1413 | +| time_elapsed | 4661 | +| total_timesteps | 1446912 | +| train/ | | +| approx_kl | 1.8425881 | +| clip_fraction | 0.473 | +| clip_range | 0.2 | +| entropy_loss | -0.48 | +| explained_variance | -1.69 | +| learning_rate | 0.0001 | +| loss | -0.0799 | +| n_updates | 74650 | +| policy_gradient_loss | -0.0651 | +| value_loss | 0.000519 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.221 | +| time/ | | +| fps | 310 | +| iterations | 1414 | +| time_elapsed | 4664 | +| total_timesteps | 1447936 | +| train/ | | +| approx_kl | 1.6038754 | +| clip_fraction | 0.451 | +| clip_range | 0.2 | +| entropy_loss | -0.439 | +| explained_variance | -2.55 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 74660 | +| policy_gradient_loss | -0.0675 | +| value_loss | 0.000454 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.221 | +| time/ | | +| fps | 310 | +| iterations | 1415 | +| time_elapsed | 4668 | +| total_timesteps | 1448960 | +| train/ | | +| approx_kl | 1.8775495 | +| clip_fraction | 0.478 | +| clip_range | 0.2 | +| entropy_loss | -0.373 | +| explained_variance | -1.15 | +| learning_rate | 0.0001 | +| loss | -0.0427 | +| n_updates | 74670 | +| policy_gradient_loss | -0.0541 | +| value_loss | 0.00083 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.221 | +| time/ | | +| fps | 310 | +| iterations | 1416 | +| time_elapsed | 4671 | +| total_timesteps | 1449984 | +| train/ | | +| approx_kl | 1.871002 | +| clip_fraction | 0.474 | +| clip_range | 0.2 | +| entropy_loss | -0.429 | +| explained_variance | -1.79 | +| learning_rate | 0.0001 | +| loss | -0.076 | +| n_updates | 74680 | +| policy_gradient_loss | -0.0668 | +| value_loss | 0.000466 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.221 | +| time/ | | +| fps | 310 | +| iterations | 1417 | +| time_elapsed | 4675 | +| total_timesteps | 1451008 | +| train/ | | +| approx_kl | 1.6659194 | +| clip_fraction | 0.477 | +| clip_range | 0.2 | +| entropy_loss | -0.419 | +| explained_variance | -1.02 | +| learning_rate | 0.0001 | +| loss | -0.0819 | +| n_updates | 74690 | +| policy_gradient_loss | -0.0639 | +| value_loss | 0.000587 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.223 | +| time/ | | +| fps | 310 | +| iterations | 1418 | +| time_elapsed | 4678 | +| total_timesteps | 1452032 | +| train/ | | +| approx_kl | 1.8108639 | +| clip_fraction | 0.52 | +| clip_range | 0.2 | +| entropy_loss | -0.45 | +| explained_variance | -3.14 | +| learning_rate | 0.0001 | +| loss | -0.0765 | +| n_updates | 74700 | +| policy_gradient_loss | -0.0662 | +| value_loss | 0.000312 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.223 | +| time/ | | +| fps | 310 | +| iterations | 1419 | +| time_elapsed | 4682 | +| total_timesteps | 1453056 | +| train/ | | +| approx_kl | 2.766017 | +| clip_fraction | 0.506 | +| clip_range | 0.2 | +| entropy_loss | -0.441 | +| explained_variance | -0.202 | +| learning_rate | 0.0001 | +| loss | -0.0933 | +| n_updates | 74710 | +| policy_gradient_loss | -0.0666 | +| value_loss | 0.000475 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.224 | +| time/ | | +| fps | 310 | +| iterations | 1420 | +| time_elapsed | 4685 | +| total_timesteps | 1454080 | +| train/ | | +| approx_kl | 3.0571449 | +| clip_fraction | 0.51 | +| clip_range | 0.2 | +| entropy_loss | -0.375 | +| explained_variance | -2.14 | +| learning_rate | 0.0001 | +| loss | -0.097 | +| n_updates | 74720 | +| policy_gradient_loss | -0.0691 | +| value_loss | 0.000606 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.224 | +| time/ | | +| fps | 310 | +| iterations | 1421 | +| time_elapsed | 4689 | +| total_timesteps | 1455104 | +| train/ | | +| approx_kl | 1.7651565 | +| clip_fraction | 0.489 | +| clip_range | 0.2 | +| entropy_loss | -0.452 | +| explained_variance | -3.3 | +| learning_rate | 0.0001 | +| loss | -0.0899 | +| n_updates | 74730 | +| policy_gradient_loss | -0.0679 | +| value_loss | 0.00024 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.226 | +| time/ | | +| fps | 310 | +| iterations | 1422 | +| time_elapsed | 4692 | +| total_timesteps | 1456128 | +| train/ | | +| approx_kl | 2.1968982 | +| clip_fraction | 0.589 | +| clip_range | 0.2 | +| entropy_loss | -0.553 | +| explained_variance | -0.299 | +| learning_rate | 0.0001 | +| loss | -0.0947 | +| n_updates | 74740 | +| policy_gradient_loss | -0.0527 | +| value_loss | 0.000458 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.226 | +| time/ | | +| fps | 310 | +| iterations | 1423 | +| time_elapsed | 4695 | +| total_timesteps | 1457152 | +| train/ | | +| approx_kl | 2.099162 | +| clip_fraction | 0.485 | +| clip_range | 0.2 | +| entropy_loss | -0.379 | +| explained_variance | -1.68 | +| learning_rate | 0.0001 | +| loss | -0.115 | +| n_updates | 74750 | +| policy_gradient_loss | -0.0701 | +| value_loss | 0.000467 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.226 | +| time/ | | +| fps | 310 | +| iterations | 1424 | +| time_elapsed | 4698 | +| total_timesteps | 1458176 | +| train/ | | +| approx_kl | 1.8355377 | +| clip_fraction | 0.52 | +| clip_range | 0.2 | +| entropy_loss | -0.465 | +| explained_variance | -1.87 | +| learning_rate | 0.0001 | +| loss | -0.0843 | +| n_updates | 74760 | +| policy_gradient_loss | -0.0606 | +| value_loss | 0.000476 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.225 | +| time/ | | +| fps | 310 | +| iterations | 1425 | +| time_elapsed | 4702 | +| total_timesteps | 1459200 | +| train/ | | +| approx_kl | 2.9862332 | +| clip_fraction | 0.514 | +| clip_range | 0.2 | +| entropy_loss | -0.42 | +| explained_variance | -3.01 | +| learning_rate | 0.0001 | +| loss | -0.117 | +| n_updates | 74770 | +| policy_gradient_loss | -0.0537 | +| value_loss | 0.00045 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.225 | +| time/ | | +| fps | 310 | +| iterations | 1426 | +| time_elapsed | 4705 | +| total_timesteps | 1460224 | +| train/ | | +| approx_kl | 2.231005 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.392 | +| explained_variance | -2.2 | +| learning_rate | 0.0001 | +| loss | -0.0866 | +| n_updates | 74780 | +| policy_gradient_loss | -0.0703 | +| value_loss | 0.000592 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.224 | +| time/ | | +| fps | 310 | +| iterations | 1427 | +| time_elapsed | 4708 | +| total_timesteps | 1461248 | +| train/ | | +| approx_kl | 1.5574322 | +| clip_fraction | 0.485 | +| clip_range | 0.2 | +| entropy_loss | -0.471 | +| explained_variance | -0.422 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 74790 | +| policy_gradient_loss | -0.0678 | +| value_loss | 0.000459 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.231 | +| time/ | | +| fps | 310 | +| iterations | 1428 | +| time_elapsed | 4711 | +| total_timesteps | 1462272 | +| train/ | | +| approx_kl | 2.1612985 | +| clip_fraction | 0.506 | +| clip_range | 0.2 | +| entropy_loss | -0.446 | +| explained_variance | -3.46 | +| learning_rate | 0.0001 | +| loss | -0.124 | +| n_updates | 74800 | +| policy_gradient_loss | -0.0702 | +| value_loss | 0.000376 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.231 | +| time/ | | +| fps | 310 | +| iterations | 1429 | +| time_elapsed | 4714 | +| total_timesteps | 1463296 | +| train/ | | +| approx_kl | 2.440611 | +| clip_fraction | 0.5 | +| clip_range | 0.2 | +| entropy_loss | -0.399 | +| explained_variance | -0.798 | +| learning_rate | 0.0001 | +| loss | -0.0927 | +| n_updates | 74810 | +| policy_gradient_loss | -0.0593 | +| value_loss | 0.000875 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.226 | +| time/ | | +| fps | 310 | +| iterations | 1430 | +| time_elapsed | 4717 | +| total_timesteps | 1464320 | +| train/ | | +| approx_kl | 1.9561068 | +| clip_fraction | 0.477 | +| clip_range | 0.2 | +| entropy_loss | -0.433 | +| explained_variance | -2.66 | +| learning_rate | 0.0001 | +| loss | -0.0756 | +| n_updates | 74820 | +| policy_gradient_loss | -0.0525 | +| value_loss | 0.000482 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.226 | +| time/ | | +| fps | 310 | +| iterations | 1431 | +| time_elapsed | 4721 | +| total_timesteps | 1465344 | +| train/ | | +| approx_kl | 1.5305512 | +| clip_fraction | 0.455 | +| clip_range | 0.2 | +| entropy_loss | -0.428 | +| explained_variance | -1.17 | +| learning_rate | 0.0001 | +| loss | -0.098 | +| n_updates | 74830 | +| policy_gradient_loss | -0.0544 | +| value_loss | 0.000358 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.226 | +| time/ | | +| fps | 310 | +| iterations | 1432 | +| time_elapsed | 4724 | +| total_timesteps | 1466368 | +| train/ | | +| approx_kl | 2.5478582 | +| clip_fraction | 0.5 | +| clip_range | 0.2 | +| entropy_loss | -0.476 | +| explained_variance | -1.41 | +| learning_rate | 0.0001 | +| loss | -0.086 | +| n_updates | 74840 | +| policy_gradient_loss | -0.0644 | +| value_loss | 0.00029 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.226 | +| time/ | | +| fps | 310 | +| iterations | 1433 | +| time_elapsed | 4727 | +| total_timesteps | 1467392 | +| train/ | | +| approx_kl | 2.446921 | +| clip_fraction | 0.482 | +| clip_range | 0.2 | +| entropy_loss | -0.395 | +| explained_variance | -0.978 | +| learning_rate | 0.0001 | +| loss | -0.075 | +| n_updates | 74850 | +| policy_gradient_loss | -0.0706 | +| value_loss | 0.000576 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.224 | +| time/ | | +| fps | 310 | +| iterations | 1434 | +| time_elapsed | 4731 | +| total_timesteps | 1468416 | +| train/ | | +| approx_kl | 21.575006 | +| clip_fraction | 0.532 | +| clip_range | 0.2 | +| entropy_loss | -0.453 | +| explained_variance | -2.05 | +| learning_rate | 0.0001 | +| loss | -0.0835 | +| n_updates | 74860 | +| policy_gradient_loss | -0.0655 | +| value_loss | 0.000592 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.224 | +| time/ | | +| fps | 310 | +| iterations | 1435 | +| time_elapsed | 4734 | +| total_timesteps | 1469440 | +| train/ | | +| approx_kl | 2.0008683 | +| clip_fraction | 0.461 | +| clip_range | 0.2 | +| entropy_loss | -0.368 | +| explained_variance | -2.29 | +| learning_rate | 0.0001 | +| loss | -0.0885 | +| n_updates | 74870 | +| policy_gradient_loss | -0.0647 | +| value_loss | 0.000554 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.226 | +| time/ | | +| fps | 310 | +| iterations | 1436 | +| time_elapsed | 4738 | +| total_timesteps | 1470464 | +| train/ | | +| approx_kl | 1.7268873 | +| clip_fraction | 0.499 | +| clip_range | 0.2 | +| entropy_loss | -0.41 | +| explained_variance | -1.85 | +| learning_rate | 0.0001 | +| loss | -0.0921 | +| n_updates | 74880 | +| policy_gradient_loss | -0.0754 | +| value_loss | 0.000488 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.226 | +| time/ | | +| fps | 310 | +| iterations | 1437 | +| time_elapsed | 4741 | +| total_timesteps | 1471488 | +| train/ | | +| approx_kl | 1.5744586 | +| clip_fraction | 0.447 | +| clip_range | 0.2 | +| entropy_loss | -0.377 | +| explained_variance | -1.44 | +| learning_rate | 0.0001 | +| loss | -0.0671 | +| n_updates | 74890 | +| policy_gradient_loss | -0.0615 | +| value_loss | 0.000287 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.226 | +| time/ | | +| fps | 310 | +| iterations | 1438 | +| time_elapsed | 4744 | +| total_timesteps | 1472512 | +| train/ | | +| approx_kl | 1.7930851 | +| clip_fraction | 0.534 | +| clip_range | 0.2 | +| entropy_loss | -0.496 | +| explained_variance | -1.69 | +| learning_rate | 0.0001 | +| loss | -0.107 | +| n_updates | 74900 | +| policy_gradient_loss | -0.0721 | +| value_loss | 0.000231 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.228 | +| time/ | | +| fps | 310 | +| iterations | 1439 | +| time_elapsed | 4748 | +| total_timesteps | 1473536 | +| train/ | | +| approx_kl | 2.7424252 | +| clip_fraction | 0.503 | +| clip_range | 0.2 | +| entropy_loss | -0.437 | +| explained_variance | -2.02 | +| learning_rate | 0.0001 | +| loss | 0.197 | +| n_updates | 74910 | +| policy_gradient_loss | -0.0594 | +| value_loss | 0.000321 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.228 | +| time/ | | +| fps | 310 | +| iterations | 1440 | +| time_elapsed | 4751 | +| total_timesteps | 1474560 | +| train/ | | +| approx_kl | 2.0269945 | +| clip_fraction | 0.491 | +| clip_range | 0.2 | +| entropy_loss | -0.44 | +| explained_variance | -0.708 | +| learning_rate | 0.0001 | +| loss | -0.0759 | +| n_updates | 74920 | +| policy_gradient_loss | -0.0594 | +| value_loss | 0.000515 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.228 | +| time/ | | +| fps | 310 | +| iterations | 1441 | +| time_elapsed | 4754 | +| total_timesteps | 1475584 | +| train/ | | +| approx_kl | 1.4654822 | +| clip_fraction | 0.494 | +| clip_range | 0.2 | +| entropy_loss | -0.421 | +| explained_variance | -1.46 | +| learning_rate | 0.0001 | +| loss | -0.0764 | +| n_updates | 74930 | +| policy_gradient_loss | -0.0564 | +| value_loss | 0.000527 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.225 | +| time/ | | +| fps | 310 | +| iterations | 1442 | +| time_elapsed | 4757 | +| total_timesteps | 1476608 | +| train/ | | +| approx_kl | 1.5233836 | +| clip_fraction | 0.492 | +| clip_range | 0.2 | +| entropy_loss | -0.45 | +| explained_variance | -1.3 | +| learning_rate | 0.0001 | +| loss | -0.0376 | +| n_updates | 74940 | +| policy_gradient_loss | -0.0665 | +| value_loss | 0.000305 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.222 | +| time/ | | +| fps | 310 | +| iterations | 1443 | +| time_elapsed | 4761 | +| total_timesteps | 1477632 | +| train/ | | +| approx_kl | 2.2047873 | +| clip_fraction | 0.49 | +| clip_range | 0.2 | +| entropy_loss | -0.4 | +| explained_variance | -1.66 | +| learning_rate | 0.0001 | +| loss | -0.0864 | +| n_updates | 74950 | +| policy_gradient_loss | -0.0712 | +| value_loss | 0.00034 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.226 | +| time/ | | +| fps | 310 | +| iterations | 1444 | +| time_elapsed | 4764 | +| total_timesteps | 1478656 | +| train/ | | +| approx_kl | 3.8211622 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.351 | +| explained_variance | -0.902 | +| learning_rate | 0.0001 | +| loss | -0.0631 | +| n_updates | 74960 | +| policy_gradient_loss | -0.0647 | +| value_loss | 0.000575 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.227 | +| time/ | | +| fps | 310 | +| iterations | 1445 | +| time_elapsed | 4767 | +| total_timesteps | 1479680 | +| train/ | | +| approx_kl | 2.572941 | +| clip_fraction | 0.503 | +| clip_range | 0.2 | +| entropy_loss | -0.358 | +| explained_variance | -1.4 | +| learning_rate | 0.0001 | +| loss | -0.0659 | +| n_updates | 74970 | +| policy_gradient_loss | -0.0595 | +| value_loss | 0.000655 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.221 | +| time/ | | +| fps | 310 | +| iterations | 1446 | +| time_elapsed | 4770 | +| total_timesteps | 1480704 | +| train/ | | +| approx_kl | 1.7752222 | +| clip_fraction | 0.468 | +| clip_range | 0.2 | +| entropy_loss | -0.464 | +| explained_variance | -2.06 | +| learning_rate | 0.0001 | +| loss | -0.0525 | +| n_updates | 74980 | +| policy_gradient_loss | -0.0537 | +| value_loss | 0.000348 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.221 | +| time/ | | +| fps | 310 | +| iterations | 1447 | +| time_elapsed | 4773 | +| total_timesteps | 1481728 | +| train/ | | +| approx_kl | 1.6642203 | +| clip_fraction | 0.461 | +| clip_range | 0.2 | +| entropy_loss | -0.383 | +| explained_variance | -0.54 | +| learning_rate | 0.0001 | +| loss | -0.112 | +| n_updates | 74990 | +| policy_gradient_loss | -0.0599 | +| value_loss | 0.000467 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.217 | +| time/ | | +| fps | 310 | +| iterations | 1448 | +| time_elapsed | 4776 | +| total_timesteps | 1482752 | +| train/ | | +| approx_kl | 1.6405511 | +| clip_fraction | 0.501 | +| clip_range | 0.2 | +| entropy_loss | -0.454 | +| explained_variance | -1.87 | +| learning_rate | 0.0001 | +| loss | -0.105 | +| n_updates | 75000 | +| policy_gradient_loss | -0.0653 | +| value_loss | 0.000414 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.217 | +| time/ | | +| fps | 310 | +| iterations | 1449 | +| time_elapsed | 4779 | +| total_timesteps | 1483776 | +| train/ | | +| approx_kl | 1.9947889 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.468 | +| explained_variance | -0.996 | +| learning_rate | 0.0001 | +| loss | -0.0852 | +| n_updates | 75010 | +| policy_gradient_loss | -0.0701 | +| value_loss | 0.000455 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.217 | +| time/ | | +| fps | 310 | +| iterations | 1450 | +| time_elapsed | 4783 | +| total_timesteps | 1484800 | +| train/ | | +| approx_kl | 1.9873929 | +| clip_fraction | 0.468 | +| clip_range | 0.2 | +| entropy_loss | -0.413 | +| explained_variance | -2.37 | +| learning_rate | 0.0001 | +| loss | -0.0832 | +| n_updates | 75020 | +| policy_gradient_loss | -0.0594 | +| value_loss | 0.000314 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | 0.214 | +| time/ | | +| fps | 310 | +| iterations | 1451 | +| time_elapsed | 4786 | +| total_timesteps | 1485824 | +| train/ | | +| approx_kl | 3.0411227 | +| clip_fraction | 0.531 | +| clip_range | 0.2 | +| entropy_loss | -0.38 | +| explained_variance | -1.58 | +| learning_rate | 0.0001 | +| loss | -0.0745 | +| n_updates | 75030 | +| policy_gradient_loss | -0.0662 | +| value_loss | 0.000606 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | 0.214 | +| time/ | | +| fps | 310 | +| iterations | 1452 | +| time_elapsed | 4790 | +| total_timesteps | 1486848 | +| train/ | | +| approx_kl | 2.4616003 | +| clip_fraction | 0.498 | +| clip_range | 0.2 | +| entropy_loss | -0.432 | +| explained_variance | -2.49 | +| learning_rate | 0.0001 | +| loss | -0.068 | +| n_updates | 75040 | +| policy_gradient_loss | -0.068 | +| value_loss | 0.000576 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.64e+03 | +| ep_rew_mean | 0.207 | +| time/ | | +| fps | 310 | +| iterations | 1453 | +| time_elapsed | 4793 | +| total_timesteps | 1487872 | +| train/ | | +| approx_kl | 1.6186684 | +| clip_fraction | 0.478 | +| clip_range | 0.2 | +| entropy_loss | -0.435 | +| explained_variance | -2.74 | +| learning_rate | 0.0001 | +| loss | -0.0677 | +| n_updates | 75050 | +| policy_gradient_loss | -0.0616 | +| value_loss | 0.000452 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.65e+03 | +| ep_rew_mean | 0.213 | +| time/ | | +| fps | 310 | +| iterations | 1454 | +| time_elapsed | 4796 | +| total_timesteps | 1488896 | +| train/ | | +| approx_kl | 2.090546 | +| clip_fraction | 0.491 | +| clip_range | 0.2 | +| entropy_loss | -0.43 | +| explained_variance | -0.657 | +| learning_rate | 0.0001 | +| loss | -0.0704 | +| n_updates | 75060 | +| policy_gradient_loss | -0.0567 | +| value_loss | 0.000958 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.65e+03 | +| ep_rew_mean | 0.213 | +| time/ | | +| fps | 310 | +| iterations | 1455 | +| time_elapsed | 4800 | +| total_timesteps | 1489920 | +| train/ | | +| approx_kl | 9.39641 | +| clip_fraction | 0.518 | +| clip_range | 0.2 | +| entropy_loss | -0.38 | +| explained_variance | -4.66 | +| learning_rate | 0.0001 | +| loss | -0.0777 | +| n_updates | 75070 | +| policy_gradient_loss | -0.0667 | +| value_loss | 0.000605 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.65e+03 | +| ep_rew_mean | 0.217 | +| time/ | | +| fps | 310 | +| iterations | 1456 | +| time_elapsed | 4803 | +| total_timesteps | 1490944 | +| train/ | | +| approx_kl | 2.0296183 | +| clip_fraction | 0.508 | +| clip_range | 0.2 | +| entropy_loss | -0.489 | +| explained_variance | -2.24 | +| learning_rate | 0.0001 | +| loss | -0.0978 | +| n_updates | 75080 | +| policy_gradient_loss | -0.0669 | +| value_loss | 0.000365 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.65e+03 | +| ep_rew_mean | 0.218 | +| time/ | | +| fps | 310 | +| iterations | 1457 | +| time_elapsed | 4807 | +| total_timesteps | 1491968 | +| train/ | | +| approx_kl | 2.450567 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.345 | +| explained_variance | -0.794 | +| learning_rate | 0.0001 | +| loss | -0.0777 | +| n_updates | 75090 | +| policy_gradient_loss | -0.0631 | +| value_loss | 0.000722 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.65e+03 | +| ep_rew_mean | 0.218 | +| time/ | | +| fps | 310 | +| iterations | 1458 | +| time_elapsed | 4810 | +| total_timesteps | 1492992 | +| train/ | | +| approx_kl | 2.4277375 | +| clip_fraction | 0.565 | +| clip_range | 0.2 | +| entropy_loss | -0.505 | +| explained_variance | -2.93 | +| learning_rate | 0.0001 | +| loss | -0.0252 | +| n_updates | 75100 | +| policy_gradient_loss | -0.0657 | +| value_loss | 0.000368 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.64e+03 | +| ep_rew_mean | 0.216 | +| time/ | | +| fps | 310 | +| iterations | 1459 | +| time_elapsed | 4813 | +| total_timesteps | 1494016 | +| train/ | | +| approx_kl | 2.114518 | +| clip_fraction | 0.5 | +| clip_range | 0.2 | +| entropy_loss | -0.451 | +| explained_variance | -1.9 | +| learning_rate | 0.0001 | +| loss | -0.0852 | +| n_updates | 75110 | +| policy_gradient_loss | -0.0657 | +| value_loss | 0.000401 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.64e+03 | +| ep_rew_mean | 0.213 | +| time/ | | +| fps | 310 | +| iterations | 1460 | +| time_elapsed | 4816 | +| total_timesteps | 1495040 | +| train/ | | +| approx_kl | 1.7145305 | +| clip_fraction | 0.512 | +| clip_range | 0.2 | +| entropy_loss | -0.456 | +| explained_variance | -0.846 | +| learning_rate | 0.0001 | +| loss | -0.0297 | +| n_updates | 75120 | +| policy_gradient_loss | -0.0657 | +| value_loss | 0.000384 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.64e+03 | +| ep_rew_mean | 0.213 | +| time/ | | +| fps | 310 | +| iterations | 1461 | +| time_elapsed | 4820 | +| total_timesteps | 1496064 | +| train/ | | +| approx_kl | 1.7415959 | +| clip_fraction | 0.486 | +| clip_range | 0.2 | +| entropy_loss | -0.408 | +| explained_variance | -1.02 | +| learning_rate | 0.0001 | +| loss | -0.12 | +| n_updates | 75130 | +| policy_gradient_loss | -0.0658 | +| value_loss | 0.000299 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.62e+03 | +| ep_rew_mean | 0.206 | +| time/ | | +| fps | 310 | +| iterations | 1462 | +| time_elapsed | 4823 | +| total_timesteps | 1497088 | +| train/ | | +| approx_kl | 3.4178324 | +| clip_fraction | 0.563 | +| clip_range | 0.2 | +| entropy_loss | -0.458 | +| explained_variance | -0.407 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 75140 | +| policy_gradient_loss | -0.0674 | +| value_loss | 0.000345 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.61e+03 | +| ep_rew_mean | 0.2 | +| time/ | | +| fps | 310 | +| iterations | 1463 | +| time_elapsed | 4826 | +| total_timesteps | 1498112 | +| train/ | | +| approx_kl | 1.9410563 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.387 | +| explained_variance | -0.703 | +| learning_rate | 0.0001 | +| loss | -0.0597 | +| n_updates | 75150 | +| policy_gradient_loss | -0.0492 | +| value_loss | 0.000528 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.61e+03 | +| ep_rew_mean | 0.2 | +| time/ | | +| fps | 310 | +| iterations | 1464 | +| time_elapsed | 4829 | +| total_timesteps | 1499136 | +| train/ | | +| approx_kl | 2.800013 | +| clip_fraction | 0.494 | +| clip_range | 0.2 | +| entropy_loss | -0.405 | +| explained_variance | -1.22 | +| learning_rate | 0.0001 | +| loss | -0.0867 | +| n_updates | 75160 | +| policy_gradient_loss | -0.062 | +| value_loss | 0.000366 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.61e+03 | +| ep_rew_mean | 0.2 | +| time/ | | +| fps | 310 | +| iterations | 1465 | +| time_elapsed | 4832 | +| total_timesteps | 1500160 | +| train/ | | +| approx_kl | 2.591209 | +| clip_fraction | 0.517 | +| clip_range | 0.2 | +| entropy_loss | -0.459 | +| explained_variance | -0.808 | +| learning_rate | 0.0001 | +| loss | -0.0805 | +| n_updates | 75170 | +| policy_gradient_loss | -0.0631 | +| value_loss | 0.000436 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.62e+03 | +| ep_rew_mean | 0.199 | +| time/ | | +| fps | 310 | +| iterations | 1466 | +| time_elapsed | 4835 | +| total_timesteps | 1501184 | +| train/ | | +| approx_kl | 2.4936628 | +| clip_fraction | 0.485 | +| clip_range | 0.2 | +| entropy_loss | -0.373 | +| explained_variance | -5.11 | +| learning_rate | 0.0001 | +| loss | -0.0877 | +| n_updates | 75180 | +| policy_gradient_loss | -0.0683 | +| value_loss | 0.000662 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.62e+03 | +| ep_rew_mean | 0.199 | +| time/ | | +| fps | 310 | +| iterations | 1467 | +| time_elapsed | 4839 | +| total_timesteps | 1502208 | +| train/ | | +| approx_kl | 2.154959 | +| clip_fraction | 0.521 | +| clip_range | 0.2 | +| entropy_loss | -0.44 | +| explained_variance | -1.23 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 75190 | +| policy_gradient_loss | -0.0637 | +| value_loss | 0.000644 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.62e+03 | +| ep_rew_mean | 0.203 | +| time/ | | +| fps | 310 | +| iterations | 1468 | +| time_elapsed | 4842 | +| total_timesteps | 1503232 | +| train/ | | +| approx_kl | 2.0711293 | +| clip_fraction | 0.513 | +| clip_range | 0.2 | +| entropy_loss | -0.372 | +| explained_variance | -1.34 | +| learning_rate | 0.0001 | +| loss | -0.0832 | +| n_updates | 75200 | +| policy_gradient_loss | -0.0681 | +| value_loss | 0.000473 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.62e+03 | +| ep_rew_mean | 0.203 | +| time/ | | +| fps | 310 | +| iterations | 1469 | +| time_elapsed | 4845 | +| total_timesteps | 1504256 | +| train/ | | +| approx_kl | 2.2693865 | +| clip_fraction | 0.505 | +| clip_range | 0.2 | +| entropy_loss | -0.419 | +| explained_variance | -0.868 | +| learning_rate | 0.0001 | +| loss | -0.0448 | +| n_updates | 75210 | +| policy_gradient_loss | -0.0586 | +| value_loss | 0.000477 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.62e+03 | +| ep_rew_mean | 0.2 | +| time/ | | +| fps | 310 | +| iterations | 1470 | +| time_elapsed | 4849 | +| total_timesteps | 1505280 | +| train/ | | +| approx_kl | 2.2138774 | +| clip_fraction | 0.542 | +| clip_range | 0.2 | +| entropy_loss | -0.527 | +| explained_variance | -3.38 | +| learning_rate | 0.0001 | +| loss | -0.0749 | +| n_updates | 75220 | +| policy_gradient_loss | -0.0627 | +| value_loss | 0.000481 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.62e+03 | +| ep_rew_mean | 0.2 | +| time/ | | +| fps | 310 | +| iterations | 1471 | +| time_elapsed | 4852 | +| total_timesteps | 1506304 | +| train/ | | +| approx_kl | 6.254488 | +| clip_fraction | 0.469 | +| clip_range | 0.2 | +| entropy_loss | -0.392 | +| explained_variance | -1.41 | +| learning_rate | 0.0001 | +| loss | -0.0914 | +| n_updates | 75230 | +| policy_gradient_loss | -0.0582 | +| value_loss | 0.000355 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.62e+03 | +| ep_rew_mean | 0.2 | +| time/ | | +| fps | 310 | +| iterations | 1472 | +| time_elapsed | 4855 | +| total_timesteps | 1507328 | +| train/ | | +| approx_kl | 1.9279463 | +| clip_fraction | 0.495 | +| clip_range | 0.2 | +| entropy_loss | -0.406 | +| explained_variance | -0.864 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 75240 | +| policy_gradient_loss | -0.0675 | +| value_loss | 0.000466 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.62e+03 | +| ep_rew_mean | 0.203 | +| time/ | | +| fps | 310 | +| iterations | 1473 | +| time_elapsed | 4859 | +| total_timesteps | 1508352 | +| train/ | | +| approx_kl | 2.134445 | +| clip_fraction | 0.513 | +| clip_range | 0.2 | +| entropy_loss | -0.498 | +| explained_variance | -1.02 | +| learning_rate | 0.0001 | +| loss | -0.0905 | +| n_updates | 75250 | +| policy_gradient_loss | -0.0624 | +| value_loss | 0.000319 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.62e+03 | +| ep_rew_mean | 0.2 | +| time/ | | +| fps | 310 | +| iterations | 1474 | +| time_elapsed | 4862 | +| total_timesteps | 1509376 | +| train/ | | +| approx_kl | 1.8886139 | +| clip_fraction | 0.519 | +| clip_range | 0.2 | +| entropy_loss | -0.465 | +| explained_variance | -1.26 | +| learning_rate | 0.0001 | +| loss | -0.0928 | +| n_updates | 75260 | +| policy_gradient_loss | -0.0658 | +| value_loss | 0.000292 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.62e+03 | +| ep_rew_mean | 0.2 | +| time/ | | +| fps | 310 | +| iterations | 1475 | +| time_elapsed | 4865 | +| total_timesteps | 1510400 | +| train/ | | +| approx_kl | 2.068147 | +| clip_fraction | 0.507 | +| clip_range | 0.2 | +| entropy_loss | -0.45 | +| explained_variance | -2.31 | +| learning_rate | 0.0001 | +| loss | -0.085 | +| n_updates | 75270 | +| policy_gradient_loss | -0.0515 | +| value_loss | 0.000488 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.61e+03 | +| ep_rew_mean | 0.198 | +| time/ | | +| fps | 310 | +| iterations | 1476 | +| time_elapsed | 4869 | +| total_timesteps | 1511424 | +| train/ | | +| approx_kl | 2.2146292 | +| clip_fraction | 0.511 | +| clip_range | 0.2 | +| entropy_loss | -0.435 | +| explained_variance | -1.83 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 75280 | +| policy_gradient_loss | -0.0732 | +| value_loss | 0.000562 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | 0.196 | +| time/ | | +| fps | 310 | +| iterations | 1477 | +| time_elapsed | 4872 | +| total_timesteps | 1512448 | +| train/ | | +| approx_kl | 1.4916035 | +| clip_fraction | 0.517 | +| clip_range | 0.2 | +| entropy_loss | -0.55 | +| explained_variance | -0.821 | +| learning_rate | 0.0001 | +| loss | -0.0534 | +| n_updates | 75290 | +| policy_gradient_loss | -0.0619 | +| value_loss | 0.000469 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | 0.196 | +| time/ | | +| fps | 310 | +| iterations | 1478 | +| time_elapsed | 4875 | +| total_timesteps | 1513472 | +| train/ | | +| approx_kl | 1.625674 | +| clip_fraction | 0.549 | +| clip_range | 0.2 | +| entropy_loss | -0.558 | +| explained_variance | -1.54 | +| learning_rate | 0.0001 | +| loss | -0.0747 | +| n_updates | 75300 | +| policy_gradient_loss | -0.0717 | +| value_loss | 0.000345 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | 0.196 | +| time/ | | +| fps | 310 | +| iterations | 1479 | +| time_elapsed | 4878 | +| total_timesteps | 1514496 | +| train/ | | +| approx_kl | 1.9404192 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.41 | +| explained_variance | -2.48 | +| learning_rate | 0.0001 | +| loss | -0.0488 | +| n_updates | 75310 | +| policy_gradient_loss | -0.0504 | +| value_loss | 0.0004 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | 0.197 | +| time/ | | +| fps | 310 | +| iterations | 1480 | +| time_elapsed | 4881 | +| total_timesteps | 1515520 | +| train/ | | +| approx_kl | 2.0503492 | +| clip_fraction | 0.536 | +| clip_range | 0.2 | +| entropy_loss | -0.506 | +| explained_variance | -3.82 | +| learning_rate | 0.0001 | +| loss | -0.109 | +| n_updates | 75320 | +| policy_gradient_loss | -0.0741 | +| value_loss | 0.000726 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | 0.194 | +| time/ | | +| fps | 310 | +| iterations | 1481 | +| time_elapsed | 4885 | +| total_timesteps | 1516544 | +| train/ | | +| approx_kl | 2.4624293 | +| clip_fraction | 0.551 | +| clip_range | 0.2 | +| entropy_loss | -0.498 | +| explained_variance | -2.26 | +| learning_rate | 0.0001 | +| loss | -0.0703 | +| n_updates | 75330 | +| policy_gradient_loss | -0.0678 | +| value_loss | 0.000715 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.58e+03 | +| ep_rew_mean | 0.187 | +| time/ | | +| fps | 310 | +| iterations | 1482 | +| time_elapsed | 4888 | +| total_timesteps | 1517568 | +| train/ | | +| approx_kl | 1.4477171 | +| clip_fraction | 0.528 | +| clip_range | 0.2 | +| entropy_loss | -0.582 | +| explained_variance | -1.02 | +| learning_rate | 0.0001 | +| loss | -0.107 | +| n_updates | 75340 | +| policy_gradient_loss | -0.0714 | +| value_loss | 0.000428 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.57e+03 | +| ep_rew_mean | 0.184 | +| time/ | | +| fps | 310 | +| iterations | 1483 | +| time_elapsed | 4891 | +| total_timesteps | 1518592 | +| train/ | | +| approx_kl | 1.4601107 | +| clip_fraction | 0.526 | +| clip_range | 0.2 | +| entropy_loss | -0.623 | +| explained_variance | -0.886 | +| learning_rate | 0.0001 | +| loss | -0.0842 | +| n_updates | 75350 | +| policy_gradient_loss | -0.0603 | +| value_loss | 0.000513 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.57e+03 | +| ep_rew_mean | 0.184 | +| time/ | | +| fps | 310 | +| iterations | 1484 | +| time_elapsed | 4894 | +| total_timesteps | 1519616 | +| train/ | | +| approx_kl | 1.7217048 | +| clip_fraction | 0.528 | +| clip_range | 0.2 | +| entropy_loss | -0.615 | +| explained_variance | -1.06 | +| learning_rate | 0.0001 | +| loss | -0.119 | +| n_updates | 75360 | +| policy_gradient_loss | -0.0772 | +| value_loss | 0.000455 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.57e+03 | +| ep_rew_mean | 0.182 | +| time/ | | +| fps | 310 | +| iterations | 1485 | +| time_elapsed | 4897 | +| total_timesteps | 1520640 | +| train/ | | +| approx_kl | 1.9136777 | +| clip_fraction | 0.554 | +| clip_range | 0.2 | +| entropy_loss | -0.504 | +| explained_variance | -1.01 | +| learning_rate | 0.0001 | +| loss | -0.0729 | +| n_updates | 75370 | +| policy_gradient_loss | -0.0768 | +| value_loss | 0.000431 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.57e+03 | +| ep_rew_mean | 0.182 | +| time/ | | +| fps | 310 | +| iterations | 1486 | +| time_elapsed | 4901 | +| total_timesteps | 1521664 | +| train/ | | +| approx_kl | 1.8160437 | +| clip_fraction | 0.516 | +| clip_range | 0.2 | +| entropy_loss | -0.471 | +| explained_variance | -1.94 | +| learning_rate | 0.0001 | +| loss | -0.107 | +| n_updates | 75380 | +| policy_gradient_loss | -0.0662 | +| value_loss | 0.000488 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.57e+03 | +| ep_rew_mean | 0.183 | +| time/ | | +| fps | 310 | +| iterations | 1487 | +| time_elapsed | 4904 | +| total_timesteps | 1522688 | +| train/ | | +| approx_kl | 2.6342273 | +| clip_fraction | 0.507 | +| clip_range | 0.2 | +| entropy_loss | -0.546 | +| explained_variance | -1.04 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 75390 | +| policy_gradient_loss | -0.0665 | +| value_loss | 0.000685 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.57e+03 | +| ep_rew_mean | 0.183 | +| time/ | | +| fps | 310 | +| iterations | 1488 | +| time_elapsed | 4908 | +| total_timesteps | 1523712 | +| train/ | | +| approx_kl | 1.6284876 | +| clip_fraction | 0.533 | +| clip_range | 0.2 | +| entropy_loss | -0.622 | +| explained_variance | -0.968 | +| learning_rate | 0.0001 | +| loss | -0.114 | +| n_updates | 75400 | +| policy_gradient_loss | -0.0708 | +| value_loss | 0.000632 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.58e+03 | +| ep_rew_mean | 0.188 | +| time/ | | +| fps | 310 | +| iterations | 1489 | +| time_elapsed | 4911 | +| total_timesteps | 1524736 | +| train/ | | +| approx_kl | 1.548993 | +| clip_fraction | 0.54 | +| clip_range | 0.2 | +| entropy_loss | -0.634 | +| explained_variance | -2.41 | +| learning_rate | 0.0001 | +| loss | -0.13 | +| n_updates | 75410 | +| policy_gradient_loss | -0.0753 | +| value_loss | 0.000526 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.58e+03 | +| ep_rew_mean | 0.186 | +| time/ | | +| fps | 310 | +| iterations | 1490 | +| time_elapsed | 4915 | +| total_timesteps | 1525760 | +| train/ | | +| approx_kl | 1.5853 | +| clip_fraction | 0.53 | +| clip_range | 0.2 | +| entropy_loss | -0.555 | +| explained_variance | -2.42 | +| learning_rate | 0.0001 | +| loss | -0.0573 | +| n_updates | 75420 | +| policy_gradient_loss | -0.0571 | +| value_loss | 0.000246 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.57e+03 | +| ep_rew_mean | 0.182 | +| time/ | | +| fps | 310 | +| iterations | 1491 | +| time_elapsed | 4918 | +| total_timesteps | 1526784 | +| train/ | | +| approx_kl | 2.052286 | +| clip_fraction | 0.536 | +| clip_range | 0.2 | +| entropy_loss | -0.604 | +| explained_variance | -1.76 | +| learning_rate | 0.0001 | +| loss | -0.12 | +| n_updates | 75430 | +| policy_gradient_loss | -0.0674 | +| value_loss | 0.000439 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.57e+03 | +| ep_rew_mean | 0.182 | +| time/ | | +| fps | 310 | +| iterations | 1492 | +| time_elapsed | 4922 | +| total_timesteps | 1527808 | +| train/ | | +| approx_kl | 1.4369054 | +| clip_fraction | 0.5 | +| clip_range | 0.2 | +| entropy_loss | -0.615 | +| explained_variance | -0.964 | +| learning_rate | 0.0001 | +| loss | -0.0638 | +| n_updates | 75440 | +| policy_gradient_loss | -0.0672 | +| value_loss | 0.000343 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.57e+03 | +| ep_rew_mean | 0.182 | +| time/ | | +| fps | 310 | +| iterations | 1493 | +| time_elapsed | 4925 | +| total_timesteps | 1528832 | +| train/ | | +| approx_kl | 1.1119816 | +| clip_fraction | 0.501 | +| clip_range | 0.2 | +| entropy_loss | -0.698 | +| explained_variance | -1.12 | +| learning_rate | 0.0001 | +| loss | -0.0817 | +| n_updates | 75450 | +| policy_gradient_loss | -0.0685 | +| value_loss | 0.000204 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.58e+03 | +| ep_rew_mean | 0.185 | +| time/ | | +| fps | 310 | +| iterations | 1494 | +| time_elapsed | 4929 | +| total_timesteps | 1529856 | +| train/ | | +| approx_kl | 1.940289 | +| clip_fraction | 0.508 | +| clip_range | 0.2 | +| entropy_loss | -0.511 | +| explained_variance | -0.829 | +| learning_rate | 0.0001 | +| loss | -0.0892 | +| n_updates | 75460 | +| policy_gradient_loss | -0.068 | +| value_loss | 0.000609 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.58e+03 | +| ep_rew_mean | 0.185 | +| time/ | | +| fps | 310 | +| iterations | 1495 | +| time_elapsed | 4932 | +| total_timesteps | 1530880 | +| train/ | | +| approx_kl | 1.7357106 | +| clip_fraction | 0.479 | +| clip_range | 0.2 | +| entropy_loss | -0.45 | +| explained_variance | -2.56 | +| learning_rate | 0.0001 | +| loss | -0.0663 | +| n_updates | 75470 | +| policy_gradient_loss | -0.0623 | +| value_loss | 0.000794 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.58e+03 | +| ep_rew_mean | 0.185 | +| time/ | | +| fps | 310 | +| iterations | 1496 | +| time_elapsed | 4935 | +| total_timesteps | 1531904 | +| train/ | | +| approx_kl | 2.53302 | +| clip_fraction | 0.497 | +| clip_range | 0.2 | +| entropy_loss | -0.455 | +| explained_variance | -2 | +| learning_rate | 0.0001 | +| loss | -0.068 | +| n_updates | 75480 | +| policy_gradient_loss | -0.0573 | +| value_loss | 0.000705 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | 0.192 | +| time/ | | +| fps | 310 | +| iterations | 1497 | +| time_elapsed | 4938 | +| total_timesteps | 1532928 | +| train/ | | +| approx_kl | 2.2155771 | +| clip_fraction | 0.532 | +| clip_range | 0.2 | +| entropy_loss | -0.49 | +| explained_variance | -1.55 | +| learning_rate | 0.0001 | +| loss | -0.1 | +| n_updates | 75490 | +| policy_gradient_loss | -0.07 | +| value_loss | 0.000584 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | 0.191 | +| time/ | | +| fps | 310 | +| iterations | 1498 | +| time_elapsed | 4941 | +| total_timesteps | 1533952 | +| train/ | | +| approx_kl | 1.8864961 | +| clip_fraction | 0.511 | +| clip_range | 0.2 | +| entropy_loss | -0.516 | +| explained_variance | -2.53 | +| learning_rate | 0.0001 | +| loss | -0.0884 | +| n_updates | 75500 | +| policy_gradient_loss | -0.0739 | +| value_loss | 0.000444 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | 0.191 | +| time/ | | +| fps | 310 | +| iterations | 1499 | +| time_elapsed | 4945 | +| total_timesteps | 1534976 | +| train/ | | +| approx_kl | 1.5958354 | +| clip_fraction | 0.524 | +| clip_range | 0.2 | +| entropy_loss | -0.581 | +| explained_variance | -1.04 | +| learning_rate | 0.0001 | +| loss | -0.0857 | +| n_updates | 75510 | +| policy_gradient_loss | -0.0696 | +| value_loss | 0.000385 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.58e+03 | +| ep_rew_mean | 0.188 | +| time/ | | +| fps | 310 | +| iterations | 1500 | +| time_elapsed | 4948 | +| total_timesteps | 1536000 | +| train/ | | +| approx_kl | 1.461945 | +| clip_fraction | 0.534 | +| clip_range | 0.2 | +| entropy_loss | -0.646 | +| explained_variance | -0.998 | +| learning_rate | 0.0001 | +| loss | -0.0714 | +| n_updates | 75520 | +| policy_gradient_loss | -0.062 | +| value_loss | 0.000414 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.58e+03 | +| ep_rew_mean | 0.188 | +| time/ | | +| fps | 310 | +| iterations | 1501 | +| time_elapsed | 4951 | +| total_timesteps | 1537024 | +| train/ | | +| approx_kl | 2.310751 | +| clip_fraction | 0.524 | +| clip_range | 0.2 | +| entropy_loss | -0.555 | +| explained_variance | -2.36 | +| learning_rate | 0.0001 | +| loss | -0.119 | +| n_updates | 75530 | +| policy_gradient_loss | -0.0746 | +| value_loss | 0.000304 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | 0.191 | +| time/ | | +| fps | 310 | +| iterations | 1502 | +| time_elapsed | 4954 | +| total_timesteps | 1538048 | +| train/ | | +| approx_kl | 1.9838594 | +| clip_fraction | 0.536 | +| clip_range | 0.2 | +| entropy_loss | -0.5 | +| explained_variance | -0.672 | +| learning_rate | 0.0001 | +| loss | -0.107 | +| n_updates | 75540 | +| policy_gradient_loss | -0.0718 | +| value_loss | 0.000501 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | 0.184 | +| time/ | | +| fps | 310 | +| iterations | 1503 | +| time_elapsed | 4957 | +| total_timesteps | 1539072 | +| train/ | | +| approx_kl | 1.6479352 | +| clip_fraction | 0.499 | +| clip_range | 0.2 | +| entropy_loss | -0.476 | +| explained_variance | -6.66 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 75550 | +| policy_gradient_loss | -0.0723 | +| value_loss | 0.000673 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | 0.187 | +| time/ | | +| fps | 310 | +| iterations | 1504 | +| time_elapsed | 4960 | +| total_timesteps | 1540096 | +| train/ | | +| approx_kl | 2.1092887 | +| clip_fraction | 0.501 | +| clip_range | 0.2 | +| entropy_loss | -0.613 | +| explained_variance | -0.971 | +| learning_rate | 0.0001 | +| loss | -0.0931 | +| n_updates | 75560 | +| policy_gradient_loss | -0.0633 | +| value_loss | 0.00056 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | 0.187 | +| time/ | | +| fps | 310 | +| iterations | 1505 | +| time_elapsed | 4964 | +| total_timesteps | 1541120 | +| train/ | | +| approx_kl | 2.0221603 | +| clip_fraction | 0.53 | +| clip_range | 0.2 | +| entropy_loss | -0.68 | +| explained_variance | -2.46 | +| learning_rate | 0.0001 | +| loss | -0.0787 | +| n_updates | 75570 | +| policy_gradient_loss | -0.0705 | +| value_loss | 0.000413 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | 0.192 | +| time/ | | +| fps | 310 | +| iterations | 1506 | +| time_elapsed | 4967 | +| total_timesteps | 1542144 | +| train/ | | +| approx_kl | 3.1697803 | +| clip_fraction | 0.505 | +| clip_range | 0.2 | +| entropy_loss | -0.42 | +| explained_variance | -1.3 | +| learning_rate | 0.0001 | +| loss | -0.0912 | +| n_updates | 75580 | +| policy_gradient_loss | -0.0693 | +| value_loss | 0.000785 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | 0.192 | +| time/ | | +| fps | 310 | +| iterations | 1507 | +| time_elapsed | 4971 | +| total_timesteps | 1543168 | +| train/ | | +| approx_kl | 2.1316042 | +| clip_fraction | 0.492 | +| clip_range | 0.2 | +| entropy_loss | -0.489 | +| explained_variance | -1.93 | +| learning_rate | 0.0001 | +| loss | -0.0711 | +| n_updates | 75590 | +| policy_gradient_loss | -0.0667 | +| value_loss | 0.000729 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | 0.189 | +| time/ | | +| fps | 310 | +| iterations | 1508 | +| time_elapsed | 4974 | +| total_timesteps | 1544192 | +| train/ | | +| approx_kl | 1.6069154 | +| clip_fraction | 0.54 | +| clip_range | 0.2 | +| entropy_loss | -0.683 | +| explained_variance | -2.64 | +| learning_rate | 0.0001 | +| loss | -0.092 | +| n_updates | 75600 | +| policy_gradient_loss | -0.0638 | +| value_loss | 0.000301 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | 0.189 | +| time/ | | +| fps | 310 | +| iterations | 1509 | +| time_elapsed | 4978 | +| total_timesteps | 1545216 | +| train/ | | +| approx_kl | 1.9796938 | +| clip_fraction | 0.511 | +| clip_range | 0.2 | +| entropy_loss | -0.451 | +| explained_variance | -0.934 | +| learning_rate | 0.0001 | +| loss | -0.0812 | +| n_updates | 75610 | +| policy_gradient_loss | -0.067 | +| value_loss | 0.000535 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | 0.193 | +| time/ | | +| fps | 310 | +| iterations | 1510 | +| time_elapsed | 4981 | +| total_timesteps | 1546240 | +| train/ | | +| approx_kl | 1.8726133 | +| clip_fraction | 0.531 | +| clip_range | 0.2 | +| entropy_loss | -0.487 | +| explained_variance | -1.57 | +| learning_rate | 0.0001 | +| loss | -0.062 | +| n_updates | 75620 | +| policy_gradient_loss | -0.0712 | +| value_loss | 0.000476 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | 0.193 | +| time/ | | +| fps | 310 | +| iterations | 1511 | +| time_elapsed | 4984 | +| total_timesteps | 1547264 | +| train/ | | +| approx_kl | 1.6283714 | +| clip_fraction | 0.521 | +| clip_range | 0.2 | +| entropy_loss | -0.551 | +| explained_variance | -1.87 | +| learning_rate | 0.0001 | +| loss | -0.0823 | +| n_updates | 75630 | +| policy_gradient_loss | -0.0655 | +| value_loss | 0.000237 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.61e+03 | +| ep_rew_mean | 0.195 | +| time/ | | +| fps | 310 | +| iterations | 1512 | +| time_elapsed | 4988 | +| total_timesteps | 1548288 | +| train/ | | +| approx_kl | 2.3211546 | +| clip_fraction | 0.53 | +| clip_range | 0.2 | +| entropy_loss | -0.484 | +| explained_variance | -0.984 | +| learning_rate | 0.0001 | +| loss | -0.0974 | +| n_updates | 75640 | +| policy_gradient_loss | -0.0654 | +| value_loss | 0.000471 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.61e+03 | +| ep_rew_mean | 0.19 | +| time/ | | +| fps | 310 | +| iterations | 1513 | +| time_elapsed | 4991 | +| total_timesteps | 1549312 | +| train/ | | +| approx_kl | 1.8774385 | +| clip_fraction | 0.548 | +| clip_range | 0.2 | +| entropy_loss | -0.532 | +| explained_variance | -1.49 | +| learning_rate | 0.0001 | +| loss | -0.0841 | +| n_updates | 75650 | +| policy_gradient_loss | -0.0656 | +| value_loss | 0.000608 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.61e+03 | +| ep_rew_mean | 0.19 | +| time/ | | +| fps | 310 | +| iterations | 1514 | +| time_elapsed | 4994 | +| total_timesteps | 1550336 | +| train/ | | +| approx_kl | 1.7982104 | +| clip_fraction | 0.544 | +| clip_range | 0.2 | +| entropy_loss | -0.531 | +| explained_variance | -2.32 | +| learning_rate | 0.0001 | +| loss | -0.0769 | +| n_updates | 75660 | +| policy_gradient_loss | -0.0761 | +| value_loss | 0.000604 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | 0.186 | +| time/ | | +| fps | 310 | +| iterations | 1515 | +| time_elapsed | 4997 | +| total_timesteps | 1551360 | +| train/ | | +| approx_kl | 1.7976446 | +| clip_fraction | 0.525 | +| clip_range | 0.2 | +| entropy_loss | -0.503 | +| explained_variance | -2.61 | +| learning_rate | 0.0001 | +| loss | -0.0826 | +| n_updates | 75670 | +| policy_gradient_loss | -0.0754 | +| value_loss | 0.00049 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | 0.189 | +| time/ | | +| fps | 310 | +| iterations | 1516 | +| time_elapsed | 5000 | +| total_timesteps | 1552384 | +| train/ | | +| approx_kl | 1.779556 | +| clip_fraction | 0.524 | +| clip_range | 0.2 | +| entropy_loss | -0.541 | +| explained_variance | -2.98 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 75680 | +| policy_gradient_loss | -0.0685 | +| value_loss | 0.000451 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | 0.187 | +| time/ | | +| fps | 310 | +| iterations | 1517 | +| time_elapsed | 5004 | +| total_timesteps | 1553408 | +| train/ | | +| approx_kl | 2.6347733 | +| clip_fraction | 0.518 | +| clip_range | 0.2 | +| entropy_loss | -0.552 | +| explained_variance | -2.82 | +| learning_rate | 0.0001 | +| loss | -0.0798 | +| n_updates | 75690 | +| policy_gradient_loss | -0.0681 | +| value_loss | 0.000454 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | 0.187 | +| time/ | | +| fps | 310 | +| iterations | 1518 | +| time_elapsed | 5007 | +| total_timesteps | 1554432 | +| train/ | | +| approx_kl | 2.260248 | +| clip_fraction | 0.501 | +| clip_range | 0.2 | +| entropy_loss | -0.47 | +| explained_variance | -0.938 | +| learning_rate | 0.0001 | +| loss | -0.0987 | +| n_updates | 75700 | +| policy_gradient_loss | -0.0566 | +| value_loss | 0.000598 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.61e+03 | +| ep_rew_mean | 0.193 | +| time/ | | +| fps | 310 | +| iterations | 1519 | +| time_elapsed | 5010 | +| total_timesteps | 1555456 | +| train/ | | +| approx_kl | 1.8473209 | +| clip_fraction | 0.505 | +| clip_range | 0.2 | +| entropy_loss | -0.551 | +| explained_variance | -2.3 | +| learning_rate | 0.0001 | +| loss | -0.0901 | +| n_updates | 75710 | +| policy_gradient_loss | -0.067 | +| value_loss | 0.000481 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | 0.19 | +| time/ | | +| fps | 310 | +| iterations | 1520 | +| time_elapsed | 5013 | +| total_timesteps | 1556480 | +| train/ | | +| approx_kl | 2.0085201 | +| clip_fraction | 0.495 | +| clip_range | 0.2 | +| entropy_loss | -0.492 | +| explained_variance | -0.856 | +| learning_rate | 0.0001 | +| loss | -0.0797 | +| n_updates | 75720 | +| policy_gradient_loss | -0.0639 | +| value_loss | 0.00071 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | 0.19 | +| time/ | | +| fps | 310 | +| iterations | 1521 | +| time_elapsed | 5016 | +| total_timesteps | 1557504 | +| train/ | | +| approx_kl | 1.8097694 | +| clip_fraction | 0.537 | +| clip_range | 0.2 | +| entropy_loss | -0.623 | +| explained_variance | -1.09 | +| learning_rate | 0.0001 | +| loss | -0.0852 | +| n_updates | 75730 | +| policy_gradient_loss | -0.0692 | +| value_loss | 0.0003 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | 0.189 | +| time/ | | +| fps | 310 | +| iterations | 1522 | +| time_elapsed | 5019 | +| total_timesteps | 1558528 | +| train/ | | +| approx_kl | 1.4972425 | +| clip_fraction | 0.541 | +| clip_range | 0.2 | +| entropy_loss | -0.615 | +| explained_variance | -1.07 | +| learning_rate | 0.0001 | +| loss | -0.086 | +| n_updates | 75740 | +| policy_gradient_loss | -0.0736 | +| value_loss | 0.000218 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | 0.194 | +| time/ | | +| fps | 310 | +| iterations | 1523 | +| time_elapsed | 5023 | +| total_timesteps | 1559552 | +| train/ | | +| approx_kl | 1.768239 | +| clip_fraction | 0.534 | +| clip_range | 0.2 | +| entropy_loss | -0.567 | +| explained_variance | -0.622 | +| learning_rate | 0.0001 | +| loss | -0.107 | +| n_updates | 75750 | +| policy_gradient_loss | -0.0733 | +| value_loss | 0.000397 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | 0.194 | +| time/ | | +| fps | 310 | +| iterations | 1524 | +| time_elapsed | 5026 | +| total_timesteps | 1560576 | +| train/ | | +| approx_kl | 1.8144047 | +| clip_fraction | 0.499 | +| clip_range | 0.2 | +| entropy_loss | -0.514 | +| explained_variance | -1.14 | +| learning_rate | 0.0001 | +| loss | -0.0843 | +| n_updates | 75760 | +| policy_gradient_loss | -0.0663 | +| value_loss | 0.000922 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | 0.19 | +| time/ | | +| fps | 310 | +| iterations | 1525 | +| time_elapsed | 5030 | +| total_timesteps | 1561600 | +| train/ | | +| approx_kl | 1.9101627 | +| clip_fraction | 0.515 | +| clip_range | 0.2 | +| entropy_loss | -0.44 | +| explained_variance | -2.49 | +| learning_rate | 0.0001 | +| loss | -0.0813 | +| n_updates | 75770 | +| policy_gradient_loss | -0.0705 | +| value_loss | 0.000821 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | 0.19 | +| time/ | | +| fps | 310 | +| iterations | 1526 | +| time_elapsed | 5033 | +| total_timesteps | 1562624 | +| train/ | | +| approx_kl | 2.582208 | +| clip_fraction | 0.465 | +| clip_range | 0.2 | +| entropy_loss | -0.423 | +| explained_variance | -2.87 | +| learning_rate | 0.0001 | +| loss | -0.0688 | +| n_updates | 75780 | +| policy_gradient_loss | -0.0577 | +| value_loss | 0.000831 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | 0.189 | +| time/ | | +| fps | 310 | +| iterations | 1527 | +| time_elapsed | 5037 | +| total_timesteps | 1563648 | +| train/ | | +| approx_kl | 1.948884 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.494 | +| explained_variance | -2.52 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 75790 | +| policy_gradient_loss | -0.0678 | +| value_loss | 0.000723 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.57e+03 | +| ep_rew_mean | 0.191 | +| time/ | | +| fps | 310 | +| iterations | 1528 | +| time_elapsed | 5040 | +| total_timesteps | 1564672 | +| train/ | | +| approx_kl | 2.3618097 | +| clip_fraction | 0.485 | +| clip_range | 0.2 | +| entropy_loss | -0.459 | +| explained_variance | -1.74 | +| learning_rate | 0.0001 | +| loss | -0.0667 | +| n_updates | 75800 | +| policy_gradient_loss | -0.0628 | +| value_loss | 0.00061 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.56e+03 | +| ep_rew_mean | 0.19 | +| time/ | | +| fps | 310 | +| iterations | 1529 | +| time_elapsed | 5044 | +| total_timesteps | 1565696 | +| train/ | | +| approx_kl | 1.8053733 | +| clip_fraction | 0.507 | +| clip_range | 0.2 | +| entropy_loss | -0.489 | +| explained_variance | -1.37 | +| learning_rate | 0.0001 | +| loss | -0.0728 | +| n_updates | 75810 | +| policy_gradient_loss | -0.0647 | +| value_loss | 0.000615 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.56e+03 | +| ep_rew_mean | 0.19 | +| time/ | | +| fps | 310 | +| iterations | 1530 | +| time_elapsed | 5047 | +| total_timesteps | 1566720 | +| train/ | | +| approx_kl | 2.5529149 | +| clip_fraction | 0.488 | +| clip_range | 0.2 | +| entropy_loss | -0.387 | +| explained_variance | -2.27 | +| learning_rate | 0.0001 | +| loss | -0.09 | +| n_updates | 75820 | +| policy_gradient_loss | -0.066 | +| value_loss | 0.000816 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.56e+03 | +| ep_rew_mean | 0.191 | +| time/ | | +| fps | 310 | +| iterations | 1531 | +| time_elapsed | 5050 | +| total_timesteps | 1567744 | +| train/ | | +| approx_kl | 1.9700625 | +| clip_fraction | 0.461 | +| clip_range | 0.2 | +| entropy_loss | -0.393 | +| explained_variance | -1.62 | +| learning_rate | 0.0001 | +| loss | -0.0882 | +| n_updates | 75830 | +| policy_gradient_loss | -0.0583 | +| value_loss | 0.000737 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.56e+03 | +| ep_rew_mean | 0.195 | +| time/ | | +| fps | 310 | +| iterations | 1532 | +| time_elapsed | 5054 | +| total_timesteps | 1568768 | +| train/ | | +| approx_kl | 4.9689064 | +| clip_fraction | 0.526 | +| clip_range | 0.2 | +| entropy_loss | -0.44 | +| explained_variance | -0.689 | +| learning_rate | 0.0001 | +| loss | -0.0931 | +| n_updates | 75840 | +| policy_gradient_loss | -0.072 | +| value_loss | 0.000311 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.56e+03 | +| ep_rew_mean | 0.195 | +| time/ | | +| fps | 310 | +| iterations | 1533 | +| time_elapsed | 5057 | +| total_timesteps | 1569792 | +| train/ | | +| approx_kl | 3.0842233 | +| clip_fraction | 0.553 | +| clip_range | 0.2 | +| entropy_loss | -0.479 | +| explained_variance | -0.97 | +| learning_rate | 0.0001 | +| loss | -0.115 | +| n_updates | 75850 | +| policy_gradient_loss | -0.0615 | +| value_loss | 0.000333 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.55e+03 | +| ep_rew_mean | 0.192 | +| time/ | | +| fps | 310 | +| iterations | 1534 | +| time_elapsed | 5060 | +| total_timesteps | 1570816 | +| train/ | | +| approx_kl | 2.1858978 | +| clip_fraction | 0.551 | +| clip_range | 0.2 | +| entropy_loss | -0.506 | +| explained_variance | -1.01 | +| learning_rate | 0.0001 | +| loss | -0.0464 | +| n_updates | 75860 | +| policy_gradient_loss | -0.0746 | +| value_loss | 0.000311 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.54e+03 | +| ep_rew_mean | 0.187 | +| time/ | | +| fps | 310 | +| iterations | 1535 | +| time_elapsed | 5063 | +| total_timesteps | 1571840 | +| train/ | | +| approx_kl | 1.5536091 | +| clip_fraction | 0.512 | +| clip_range | 0.2 | +| entropy_loss | -0.555 | +| explained_variance | -2.12 | +| learning_rate | 0.0001 | +| loss | -0.0961 | +| n_updates | 75870 | +| policy_gradient_loss | -0.0724 | +| value_loss | 0.000409 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.54e+03 | +| ep_rew_mean | 0.189 | +| time/ | | +| fps | 310 | +| iterations | 1536 | +| time_elapsed | 5066 | +| total_timesteps | 1572864 | +| train/ | | +| approx_kl | 1.412492 | +| clip_fraction | 0.539 | +| clip_range | 0.2 | +| entropy_loss | -0.708 | +| explained_variance | -0.592 | +| learning_rate | 0.0001 | +| loss | -0.1 | +| n_updates | 75880 | +| policy_gradient_loss | -0.0664 | +| value_loss | 0.000403 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.54e+03 | +| ep_rew_mean | 0.189 | +| time/ | | +| fps | 310 | +| iterations | 1537 | +| time_elapsed | 5070 | +| total_timesteps | 1573888 | +| train/ | | +| approx_kl | 1.6550449 | +| clip_fraction | 0.526 | +| clip_range | 0.2 | +| entropy_loss | -0.49 | +| explained_variance | -2.38 | +| learning_rate | 0.0001 | +| loss | -0.0847 | +| n_updates | 75890 | +| policy_gradient_loss | -0.0735 | +| value_loss | 0.000614 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.54e+03 | +| ep_rew_mean | 0.189 | +| time/ | | +| fps | 310 | +| iterations | 1538 | +| time_elapsed | 5073 | +| total_timesteps | 1574912 | +| train/ | | +| approx_kl | 2.5889509 | +| clip_fraction | 0.532 | +| clip_range | 0.2 | +| entropy_loss | -0.506 | +| explained_variance | -1.18 | +| learning_rate | 0.0001 | +| loss | -0.0805 | +| n_updates | 75900 | +| policy_gradient_loss | -0.0658 | +| value_loss | 0.000458 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.54e+03 | +| ep_rew_mean | 0.189 | +| time/ | | +| fps | 310 | +| iterations | 1539 | +| time_elapsed | 5076 | +| total_timesteps | 1575936 | +| train/ | | +| approx_kl | 1.5236145 | +| clip_fraction | 0.504 | +| clip_range | 0.2 | +| entropy_loss | -0.526 | +| explained_variance | -1.23 | +| learning_rate | 0.0001 | +| loss | -0.0626 | +| n_updates | 75910 | +| policy_gradient_loss | -0.0663 | +| value_loss | 0.000258 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.54e+03 | +| ep_rew_mean | 0.186 | +| time/ | | +| fps | 310 | +| iterations | 1540 | +| time_elapsed | 5079 | +| total_timesteps | 1576960 | +| train/ | | +| approx_kl | 2.3945732 | +| clip_fraction | 0.555 | +| clip_range | 0.2 | +| entropy_loss | -0.53 | +| explained_variance | -1.19 | +| learning_rate | 0.0001 | +| loss | 0.0331 | +| n_updates | 75920 | +| policy_gradient_loss | -0.0644 | +| value_loss | 0.000614 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.54e+03 | +| ep_rew_mean | 0.179 | +| time/ | | +| fps | 310 | +| iterations | 1541 | +| time_elapsed | 5083 | +| total_timesteps | 1577984 | +| train/ | | +| approx_kl | 2.056706 | +| clip_fraction | 0.498 | +| clip_range | 0.2 | +| entropy_loss | -0.47 | +| explained_variance | -4.66 | +| learning_rate | 0.0001 | +| loss | -0.0937 | +| n_updates | 75930 | +| policy_gradient_loss | -0.0563 | +| value_loss | 0.000783 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.54e+03 | +| ep_rew_mean | 0.178 | +| time/ | | +| fps | 310 | +| iterations | 1542 | +| time_elapsed | 5086 | +| total_timesteps | 1579008 | +| train/ | | +| approx_kl | 1.9013628 | +| clip_fraction | 0.514 | +| clip_range | 0.2 | +| entropy_loss | -0.503 | +| explained_variance | -1 | +| learning_rate | 0.0001 | +| loss | -0.0831 | +| n_updates | 75940 | +| policy_gradient_loss | -0.0652 | +| value_loss | 0.000656 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.54e+03 | +| ep_rew_mean | 0.178 | +| time/ | | +| fps | 310 | +| iterations | 1543 | +| time_elapsed | 5089 | +| total_timesteps | 1580032 | +| train/ | | +| approx_kl | 1.6781452 | +| clip_fraction | 0.535 | +| clip_range | 0.2 | +| entropy_loss | -0.585 | +| explained_variance | -1.15 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 75950 | +| policy_gradient_loss | -0.0637 | +| value_loss | 0.000641 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.53e+03 | +| ep_rew_mean | 0.18 | +| time/ | | +| fps | 310 | +| iterations | 1544 | +| time_elapsed | 5093 | +| total_timesteps | 1581056 | +| train/ | | +| approx_kl | 2.0449457 | +| clip_fraction | 0.529 | +| clip_range | 0.2 | +| entropy_loss | -0.545 | +| explained_variance | -2.91 | +| learning_rate | 0.0001 | +| loss | -0.0842 | +| n_updates | 75960 | +| policy_gradient_loss | -0.072 | +| value_loss | 0.000509 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.53e+03 | +| ep_rew_mean | 0.187 | +| time/ | | +| fps | 310 | +| iterations | 1545 | +| time_elapsed | 5096 | +| total_timesteps | 1582080 | +| train/ | | +| approx_kl | 2.1708865 | +| clip_fraction | 0.491 | +| clip_range | 0.2 | +| entropy_loss | -0.458 | +| explained_variance | -0.615 | +| learning_rate | 0.0001 | +| loss | -0.0673 | +| n_updates | 75970 | +| policy_gradient_loss | -0.0584 | +| value_loss | 0.000685 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.53e+03 | +| ep_rew_mean | 0.187 | +| time/ | | +| fps | 310 | +| iterations | 1546 | +| time_elapsed | 5099 | +| total_timesteps | 1583104 | +| train/ | | +| approx_kl | 2.1490104 | +| clip_fraction | 0.525 | +| clip_range | 0.2 | +| entropy_loss | -0.474 | +| explained_variance | -1.19 | +| learning_rate | 0.0001 | +| loss | -0.0998 | +| n_updates | 75980 | +| policy_gradient_loss | -0.0704 | +| value_loss | 0.000551 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.53e+03 | +| ep_rew_mean | 0.184 | +| time/ | | +| fps | 310 | +| iterations | 1547 | +| time_elapsed | 5103 | +| total_timesteps | 1584128 | +| train/ | | +| approx_kl | 2.4728408 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.49 | +| explained_variance | -2.53 | +| learning_rate | 0.0001 | +| loss | -0.0885 | +| n_updates | 75990 | +| policy_gradient_loss | -0.0643 | +| value_loss | 0.000394 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.53e+03 | +| ep_rew_mean | 0.184 | +| time/ | | +| fps | 310 | +| iterations | 1548 | +| time_elapsed | 5106 | +| total_timesteps | 1585152 | +| train/ | | +| approx_kl | 3.9488306 | +| clip_fraction | 0.513 | +| clip_range | 0.2 | +| entropy_loss | -0.563 | +| explained_variance | -0.949 | +| learning_rate | 0.0001 | +| loss | -0.0653 | +| n_updates | 76000 | +| policy_gradient_loss | -0.0579 | +| value_loss | 0.000259 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.53e+03 | +| ep_rew_mean | 0.184 | +| time/ | | +| fps | 310 | +| iterations | 1549 | +| time_elapsed | 5110 | +| total_timesteps | 1586176 | +| train/ | | +| approx_kl | 1.6944938 | +| clip_fraction | 0.472 | +| clip_range | 0.2 | +| entropy_loss | -0.481 | +| explained_variance | -1.75 | +| learning_rate | 0.0001 | +| loss | -0.0735 | +| n_updates | 76010 | +| policy_gradient_loss | -0.0674 | +| value_loss | 0.000395 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.54e+03 | +| ep_rew_mean | 0.188 | +| time/ | | +| fps | 310 | +| iterations | 1550 | +| time_elapsed | 5113 | +| total_timesteps | 1587200 | +| train/ | | +| approx_kl | 2.596046 | +| clip_fraction | 0.515 | +| clip_range | 0.2 | +| entropy_loss | -0.444 | +| explained_variance | -5.88 | +| learning_rate | 0.0001 | +| loss | -0.0907 | +| n_updates | 76020 | +| policy_gradient_loss | -0.0749 | +| value_loss | 0.000388 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.54e+03 | +| ep_rew_mean | 0.19 | +| time/ | | +| fps | 310 | +| iterations | 1551 | +| time_elapsed | 5116 | +| total_timesteps | 1588224 | +| train/ | | +| approx_kl | 2.5848927 | +| clip_fraction | 0.496 | +| clip_range | 0.2 | +| entropy_loss | -0.468 | +| explained_variance | -1.51 | +| learning_rate | 0.0001 | +| loss | -0.0821 | +| n_updates | 76030 | +| policy_gradient_loss | -0.0597 | +| value_loss | 0.000349 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.54e+03 | +| ep_rew_mean | 0.192 | +| time/ | | +| fps | 310 | +| iterations | 1552 | +| time_elapsed | 5120 | +| total_timesteps | 1589248 | +| train/ | | +| approx_kl | 1.9655914 | +| clip_fraction | 0.478 | +| clip_range | 0.2 | +| entropy_loss | -0.424 | +| explained_variance | -1.08 | +| learning_rate | 0.0001 | +| loss | -0.0903 | +| n_updates | 76040 | +| policy_gradient_loss | -0.0594 | +| value_loss | 0.000391 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.54e+03 | +| ep_rew_mean | 0.192 | +| time/ | | +| fps | 310 | +| iterations | 1553 | +| time_elapsed | 5123 | +| total_timesteps | 1590272 | +| train/ | | +| approx_kl | 1.9311087 | +| clip_fraction | 0.519 | +| clip_range | 0.2 | +| entropy_loss | -0.469 | +| explained_variance | -1.02 | +| learning_rate | 0.0001 | +| loss | -0.0891 | +| n_updates | 76050 | +| policy_gradient_loss | -0.0672 | +| value_loss | 0.000263 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.55e+03 | +| ep_rew_mean | 0.196 | +| time/ | | +| fps | 310 | +| iterations | 1554 | +| time_elapsed | 5126 | +| total_timesteps | 1591296 | +| train/ | | +| approx_kl | 1.988617 | +| clip_fraction | 0.512 | +| clip_range | 0.2 | +| entropy_loss | -0.471 | +| explained_variance | -1.48 | +| learning_rate | 0.0001 | +| loss | -0.0762 | +| n_updates | 76060 | +| policy_gradient_loss | -0.0726 | +| value_loss | 0.000619 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.55e+03 | +| ep_rew_mean | 0.196 | +| time/ | | +| fps | 310 | +| iterations | 1555 | +| time_elapsed | 5129 | +| total_timesteps | 1592320 | +| train/ | | +| approx_kl | 1.5423789 | +| clip_fraction | 0.482 | +| clip_range | 0.2 | +| entropy_loss | -0.48 | +| explained_variance | -0.996 | +| learning_rate | 0.0001 | +| loss | -0.0892 | +| n_updates | 76070 | +| policy_gradient_loss | -0.0607 | +| value_loss | 0.000682 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.55e+03 | +| ep_rew_mean | 0.195 | +| time/ | | +| fps | 310 | +| iterations | 1556 | +| time_elapsed | 5132 | +| total_timesteps | 1593344 | +| train/ | | +| approx_kl | 1.5828395 | +| clip_fraction | 0.492 | +| clip_range | 0.2 | +| entropy_loss | -0.513 | +| explained_variance | -2.09 | +| learning_rate | 0.0001 | +| loss | -0.0856 | +| n_updates | 76080 | +| policy_gradient_loss | -0.0598 | +| value_loss | 0.000595 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.55e+03 | +| ep_rew_mean | 0.195 | +| time/ | | +| fps | 310 | +| iterations | 1557 | +| time_elapsed | 5136 | +| total_timesteps | 1594368 | +| train/ | | +| approx_kl | 1.590801 | +| clip_fraction | 0.485 | +| clip_range | 0.2 | +| entropy_loss | -0.521 | +| explained_variance | -1.34 | +| learning_rate | 0.0001 | +| loss | -0.0882 | +| n_updates | 76090 | +| policy_gradient_loss | -0.0564 | +| value_loss | 0.000383 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.55e+03 | +| ep_rew_mean | 0.198 | +| time/ | | +| fps | 310 | +| iterations | 1558 | +| time_elapsed | 5139 | +| total_timesteps | 1595392 | +| train/ | | +| approx_kl | 1.1260853 | +| clip_fraction | 0.484 | +| clip_range | 0.2 | +| entropy_loss | -0.582 | +| explained_variance | -2.74 | +| learning_rate | 0.0001 | +| loss | -0.0718 | +| n_updates | 76100 | +| policy_gradient_loss | -0.055 | +| value_loss | 0.000779 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.55e+03 | +| ep_rew_mean | 0.198 | +| time/ | | +| fps | 310 | +| iterations | 1559 | +| time_elapsed | 5142 | +| total_timesteps | 1596416 | +| train/ | | +| approx_kl | 1.6765326 | +| clip_fraction | 0.463 | +| clip_range | 0.2 | +| entropy_loss | -0.436 | +| explained_variance | -1.39 | +| learning_rate | 0.0001 | +| loss | -0.0574 | +| n_updates | 76110 | +| policy_gradient_loss | -0.0608 | +| value_loss | 0.000654 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.55e+03 | +| ep_rew_mean | 0.202 | +| time/ | | +| fps | 310 | +| iterations | 1560 | +| time_elapsed | 5146 | +| total_timesteps | 1597440 | +| train/ | | +| approx_kl | 1.667803 | +| clip_fraction | 0.506 | +| clip_range | 0.2 | +| entropy_loss | -0.529 | +| explained_variance | -1.76 | +| learning_rate | 0.0001 | +| loss | -0.0667 | +| n_updates | 76120 | +| policy_gradient_loss | -0.0706 | +| value_loss | 0.000418 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.55e+03 | +| ep_rew_mean | 0.202 | +| time/ | | +| fps | 310 | +| iterations | 1561 | +| time_elapsed | 5150 | +| total_timesteps | 1598464 | +| train/ | | +| approx_kl | 1.6812258 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.567 | +| explained_variance | -1.36 | +| learning_rate | 0.0001 | +| loss | -0.0578 | +| n_updates | 76130 | +| policy_gradient_loss | -0.0594 | +| value_loss | 0.000489 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.56e+03 | +| ep_rew_mean | 0.205 | +| time/ | | +| fps | 310 | +| iterations | 1562 | +| time_elapsed | 5153 | +| total_timesteps | 1599488 | +| train/ | | +| approx_kl | 1.8200881 | +| clip_fraction | 0.554 | +| clip_range | 0.2 | +| entropy_loss | -0.592 | +| explained_variance | -1.14 | +| learning_rate | 0.0001 | +| loss | -0.0581 | +| n_updates | 76140 | +| policy_gradient_loss | -0.0732 | +| value_loss | 0.00044 | +--------------------------------------- + +Current state: Champion.Level5.RyuVsDhalsim +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.56e+03 | +| ep_rew_mean | 0.205 | +| time/ | | +| fps | 310 | +| iterations | 1563 | +| time_elapsed | 5156 | +| total_timesteps | 1600512 | +| train/ | | +| approx_kl | 1.8582954 | +| clip_fraction | 0.464 | +| clip_range | 0.2 | +| entropy_loss | -0.505 | +| explained_variance | -0.779 | +| learning_rate | 0.0001 | +| loss | -0.0973 | +| n_updates | 76150 | +| policy_gradient_loss | -0.0609 | +| value_loss | 0.000629 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.57e+03 | +| ep_rew_mean | 0.203 | +| time/ | | +| fps | 310 | +| iterations | 1564 | +| time_elapsed | 5160 | +| total_timesteps | 1601536 | +| train/ | | +| approx_kl | 2.3079739 | +| clip_fraction | 0.516 | +| clip_range | 0.2 | +| entropy_loss | -0.507 | +| explained_variance | -6.6 | +| learning_rate | 0.0001 | +| loss | -0.0993 | +| n_updates | 76160 | +| policy_gradient_loss | -0.0612 | +| value_loss | 0.000624 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.57e+03 | +| ep_rew_mean | 0.203 | +| time/ | | +| fps | 310 | +| iterations | 1565 | +| time_elapsed | 5163 | +| total_timesteps | 1602560 | +| train/ | | +| approx_kl | 2.7511861 | +| clip_fraction | 0.486 | +| clip_range | 0.2 | +| entropy_loss | -0.464 | +| explained_variance | -1.47 | +| learning_rate | 0.0001 | +| loss | -0.114 | +| n_updates | 76170 | +| policy_gradient_loss | -0.0591 | +| value_loss | 0.000723 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.57e+03 | +| ep_rew_mean | 0.203 | +| time/ | | +| fps | 310 | +| iterations | 1566 | +| time_elapsed | 5167 | +| total_timesteps | 1603584 | +| train/ | | +| approx_kl | 3.4642625 | +| clip_fraction | 0.446 | +| clip_range | 0.2 | +| entropy_loss | -0.224 | +| explained_variance | -4.46 | +| learning_rate | 0.0001 | +| loss | -0.0404 | +| n_updates | 76180 | +| policy_gradient_loss | -0.0549 | +| value_loss | 0.000551 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.58e+03 | +| ep_rew_mean | 0.203 | +| time/ | | +| fps | 310 | +| iterations | 1567 | +| time_elapsed | 5170 | +| total_timesteps | 1604608 | +| train/ | | +| approx_kl | 3.440405 | +| clip_fraction | 0.502 | +| clip_range | 0.2 | +| entropy_loss | -0.275 | +| explained_variance | -0.26 | +| learning_rate | 0.0001 | +| loss | -0.0818 | +| n_updates | 76190 | +| policy_gradient_loss | -0.0359 | +| value_loss | 0.000499 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | 0.202 | +| time/ | | +| fps | 310 | +| iterations | 1568 | +| time_elapsed | 5173 | +| total_timesteps | 1605632 | +| train/ | | +| approx_kl | 4.0519304 | +| clip_fraction | 0.502 | +| clip_range | 0.2 | +| entropy_loss | -0.277 | +| explained_variance | -1.33 | +| learning_rate | 0.0001 | +| loss | -0.0988 | +| n_updates | 76200 | +| policy_gradient_loss | -0.0554 | +| value_loss | 0.000645 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | 0.202 | +| time/ | | +| fps | 310 | +| iterations | 1569 | +| time_elapsed | 5176 | +| total_timesteps | 1606656 | +| train/ | | +| approx_kl | 3.4474993 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.286 | +| explained_variance | -2.96 | +| learning_rate | 0.0001 | +| loss | -0.0109 | +| n_updates | 76210 | +| policy_gradient_loss | -0.0431 | +| value_loss | 0.000422 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | 0.202 | +| time/ | | +| fps | 310 | +| iterations | 1570 | +| time_elapsed | 5180 | +| total_timesteps | 1607680 | +| train/ | | +| approx_kl | 4.124818 | +| clip_fraction | 0.464 | +| clip_range | 0.2 | +| entropy_loss | -0.251 | +| explained_variance | -3.52 | +| learning_rate | 0.0001 | +| loss | -0.0426 | +| n_updates | 76220 | +| policy_gradient_loss | -0.0415 | +| value_loss | 0.000345 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | 0.2 | +| time/ | | +| fps | 310 | +| iterations | 1571 | +| time_elapsed | 5183 | +| total_timesteps | 1608704 | +| train/ | | +| approx_kl | 1.678284 | +| clip_fraction | 0.519 | +| clip_range | 0.2 | +| entropy_loss | -0.44 | +| explained_variance | -1.11 | +| learning_rate | 0.0001 | +| loss | -0.0984 | +| n_updates | 76230 | +| policy_gradient_loss | -0.0321 | +| value_loss | 0.000403 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | 0.2 | +| time/ | | +| fps | 310 | +| iterations | 1572 | +| time_elapsed | 5186 | +| total_timesteps | 1609728 | +| train/ | | +| approx_kl | 2.4043016 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.28 | +| explained_variance | -0.581 | +| learning_rate | 0.0001 | +| loss | -0.068 | +| n_updates | 76240 | +| policy_gradient_loss | -0.0512 | +| value_loss | 0.000379 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.61e+03 | +| ep_rew_mean | 0.202 | +| time/ | | +| fps | 310 | +| iterations | 1573 | +| time_elapsed | 5189 | +| total_timesteps | 1610752 | +| train/ | | +| approx_kl | 2.626277 | +| clip_fraction | 0.476 | +| clip_range | 0.2 | +| entropy_loss | -0.328 | +| explained_variance | -1.27 | +| learning_rate | 0.0001 | +| loss | -0.0621 | +| n_updates | 76250 | +| policy_gradient_loss | -0.0582 | +| value_loss | 0.000451 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.61e+03 | +| ep_rew_mean | 0.202 | +| time/ | | +| fps | 310 | +| iterations | 1574 | +| time_elapsed | 5192 | +| total_timesteps | 1611776 | +| train/ | | +| approx_kl | 3.89632 | +| clip_fraction | 0.484 | +| clip_range | 0.2 | +| entropy_loss | -0.273 | +| explained_variance | -0.349 | +| learning_rate | 0.0001 | +| loss | -0.0782 | +| n_updates | 76260 | +| policy_gradient_loss | -0.051 | +| value_loss | 0.000775 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.61e+03 | +| ep_rew_mean | 0.202 | +| time/ | | +| fps | 310 | +| iterations | 1575 | +| time_elapsed | 5195 | +| total_timesteps | 1612800 | +| train/ | | +| approx_kl | 3.1475801 | +| clip_fraction | 0.444 | +| clip_range | 0.2 | +| entropy_loss | -0.286 | +| explained_variance | -1.39 | +| learning_rate | 0.0001 | +| loss | -0.0741 | +| n_updates | 76270 | +| policy_gradient_loss | -0.0565 | +| value_loss | 0.000612 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.62e+03 | +| ep_rew_mean | 0.201 | +| time/ | | +| fps | 310 | +| iterations | 1576 | +| time_elapsed | 5199 | +| total_timesteps | 1613824 | +| train/ | | +| approx_kl | 1.5627339 | +| clip_fraction | 0.479 | +| clip_range | 0.2 | +| entropy_loss | -0.389 | +| explained_variance | -2.38 | +| learning_rate | 0.0001 | +| loss | -0.0505 | +| n_updates | 76280 | +| policy_gradient_loss | -0.0508 | +| value_loss | 0.00024 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.62e+03 | +| ep_rew_mean | 0.201 | +| time/ | | +| fps | 310 | +| iterations | 1577 | +| time_elapsed | 5202 | +| total_timesteps | 1614848 | +| train/ | | +| approx_kl | 2.201776 | +| clip_fraction | 0.491 | +| clip_range | 0.2 | +| entropy_loss | -0.344 | +| explained_variance | -0.409 | +| learning_rate | 0.0001 | +| loss | -0.0817 | +| n_updates | 76290 | +| policy_gradient_loss | -0.0484 | +| value_loss | 0.000327 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.62e+03 | +| ep_rew_mean | 0.201 | +| time/ | | +| fps | 310 | +| iterations | 1578 | +| time_elapsed | 5205 | +| total_timesteps | 1615872 | +| train/ | | +| approx_kl | 3.693033 | +| clip_fraction | 0.476 | +| clip_range | 0.2 | +| entropy_loss | -0.248 | +| explained_variance | -1.97 | +| learning_rate | 0.0001 | +| loss | -0.0908 | +| n_updates | 76300 | +| policy_gradient_loss | -0.0534 | +| value_loss | 0.000546 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.62e+03 | +| ep_rew_mean | 0.2 | +| time/ | | +| fps | 310 | +| iterations | 1579 | +| time_elapsed | 5208 | +| total_timesteps | 1616896 | +| train/ | | +| approx_kl | 2.9175386 | +| clip_fraction | 0.43 | +| clip_range | 0.2 | +| entropy_loss | -0.243 | +| explained_variance | -1.49 | +| learning_rate | 0.0001 | +| loss | -0.0637 | +| n_updates | 76310 | +| policy_gradient_loss | -0.0451 | +| value_loss | 0.000487 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.62e+03 | +| ep_rew_mean | 0.2 | +| time/ | | +| fps | 310 | +| iterations | 1580 | +| time_elapsed | 5212 | +| total_timesteps | 1617920 | +| train/ | | +| approx_kl | 2.462045 | +| clip_fraction | 0.445 | +| clip_range | 0.2 | +| entropy_loss | -0.261 | +| explained_variance | -3.29 | +| learning_rate | 0.0001 | +| loss | -0.0697 | +| n_updates | 76320 | +| policy_gradient_loss | -0.05 | +| value_loss | 0.000421 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.63e+03 | +| ep_rew_mean | 0.201 | +| time/ | | +| fps | 310 | +| iterations | 1581 | +| time_elapsed | 5215 | +| total_timesteps | 1618944 | +| train/ | | +| approx_kl | 3.1012769 | +| clip_fraction | 0.46 | +| clip_range | 0.2 | +| entropy_loss | -0.278 | +| explained_variance | -0.337 | +| learning_rate | 0.0001 | +| loss | -0.0584 | +| n_updates | 76330 | +| policy_gradient_loss | -0.0463 | +| value_loss | 0.00071 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.63e+03 | +| ep_rew_mean | 0.208 | +| time/ | | +| fps | 310 | +| iterations | 1582 | +| time_elapsed | 5218 | +| total_timesteps | 1619968 | +| train/ | | +| approx_kl | 3.5704772 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.284 | +| explained_variance | -0.0069 | +| learning_rate | 0.0001 | +| loss | -0.0635 | +| n_updates | 76340 | +| policy_gradient_loss | -0.0446 | +| value_loss | 0.000525 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.63e+03 | +| ep_rew_mean | 0.208 | +| time/ | | +| fps | 310 | +| iterations | 1583 | +| time_elapsed | 5222 | +| total_timesteps | 1620992 | +| train/ | | +| approx_kl | 2.4392707 | +| clip_fraction | 0.497 | +| clip_range | 0.2 | +| entropy_loss | -0.368 | +| explained_variance | -0.0627 | +| learning_rate | 0.0001 | +| loss | -0.0882 | +| n_updates | 76350 | +| policy_gradient_loss | -0.0517 | +| value_loss | 0.00081 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.63e+03 | +| ep_rew_mean | 0.208 | +| time/ | | +| fps | 310 | +| iterations | 1584 | +| time_elapsed | 5225 | +| total_timesteps | 1622016 | +| train/ | | +| approx_kl | 2.9584923 | +| clip_fraction | 0.451 | +| clip_range | 0.2 | +| entropy_loss | -0.236 | +| explained_variance | -1.06 | +| learning_rate | 0.0001 | +| loss | -0.0869 | +| n_updates | 76360 | +| policy_gradient_loss | -0.0554 | +| value_loss | 0.000664 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.64e+03 | +| ep_rew_mean | 0.204 | +| time/ | | +| fps | 310 | +| iterations | 1585 | +| time_elapsed | 5228 | +| total_timesteps | 1623040 | +| train/ | | +| approx_kl | 2.7382264 | +| clip_fraction | 0.46 | +| clip_range | 0.2 | +| entropy_loss | -0.287 | +| explained_variance | -3.96 | +| learning_rate | 0.0001 | +| loss | -0.0703 | +| n_updates | 76370 | +| policy_gradient_loss | -0.0374 | +| value_loss | 0.00033 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.64e+03 | +| ep_rew_mean | 0.204 | +| time/ | | +| fps | 310 | +| iterations | 1586 | +| time_elapsed | 5231 | +| total_timesteps | 1624064 | +| train/ | | +| approx_kl | 1.4820137 | +| clip_fraction | 0.435 | +| clip_range | 0.2 | +| entropy_loss | -0.362 | +| explained_variance | -0.513 | +| learning_rate | 0.0001 | +| loss | -0.0584 | +| n_updates | 76380 | +| policy_gradient_loss | -0.0398 | +| value_loss | 0.000348 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.64e+03 | +| ep_rew_mean | 0.204 | +| time/ | | +| fps | 310 | +| iterations | 1587 | +| time_elapsed | 5234 | +| total_timesteps | 1625088 | +| train/ | | +| approx_kl | 3.7220018 | +| clip_fraction | 0.492 | +| clip_range | 0.2 | +| entropy_loss | -0.331 | +| explained_variance | -1.51 | +| learning_rate | 0.0001 | +| loss | 0.0308 | +| n_updates | 76390 | +| policy_gradient_loss | -0.0506 | +| value_loss | 0.000806 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.64e+03 | +| ep_rew_mean | 0.204 | +| time/ | | +| fps | 310 | +| iterations | 1588 | +| time_elapsed | 5238 | +| total_timesteps | 1626112 | +| train/ | | +| approx_kl | 3.2713199 | +| clip_fraction | 0.516 | +| clip_range | 0.2 | +| entropy_loss | -0.326 | +| explained_variance | -1.19 | +| learning_rate | 0.0001 | +| loss | -0.0896 | +| n_updates | 76400 | +| policy_gradient_loss | -0.0486 | +| value_loss | 0.000419 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.64e+03 | +| ep_rew_mean | 0.204 | +| time/ | | +| fps | 310 | +| iterations | 1589 | +| time_elapsed | 5241 | +| total_timesteps | 1627136 | +| train/ | | +| approx_kl | 2.6491008 | +| clip_fraction | 0.458 | +| clip_range | 0.2 | +| entropy_loss | -0.285 | +| explained_variance | -0.43 | +| learning_rate | 0.0001 | +| loss | -0.0747 | +| n_updates | 76410 | +| policy_gradient_loss | -0.0514 | +| value_loss | 0.000584 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.65e+03 | +| ep_rew_mean | 0.2 | +| time/ | | +| fps | 310 | +| iterations | 1590 | +| time_elapsed | 5244 | +| total_timesteps | 1628160 | +| train/ | | +| approx_kl | 1.9050108 | +| clip_fraction | 0.49 | +| clip_range | 0.2 | +| entropy_loss | -0.385 | +| explained_variance | -0.925 | +| learning_rate | 0.0001 | +| loss | -0.0639 | +| n_updates | 76420 | +| policy_gradient_loss | -0.0456 | +| value_loss | 0.000357 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.65e+03 | +| ep_rew_mean | 0.2 | +| time/ | | +| fps | 310 | +| iterations | 1591 | +| time_elapsed | 5247 | +| total_timesteps | 1629184 | +| train/ | | +| approx_kl | 2.819471 | +| clip_fraction | 0.467 | +| clip_range | 0.2 | +| entropy_loss | -0.303 | +| explained_variance | -3.45 | +| learning_rate | 0.0001 | +| loss | -0.0853 | +| n_updates | 76430 | +| policy_gradient_loss | -0.0539 | +| value_loss | 0.000232 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | 0.201 | +| time/ | | +| fps | 310 | +| iterations | 1592 | +| time_elapsed | 5250 | +| total_timesteps | 1630208 | +| train/ | | +| approx_kl | 3.060614 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.315 | +| explained_variance | -0.541 | +| learning_rate | 0.0001 | +| loss | -0.089 | +| n_updates | 76440 | +| policy_gradient_loss | -0.0562 | +| value_loss | 0.000596 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | 0.201 | +| time/ | | +| fps | 310 | +| iterations | 1593 | +| time_elapsed | 5253 | +| total_timesteps | 1631232 | +| train/ | | +| approx_kl | 6.780851 | +| clip_fraction | 0.511 | +| clip_range | 0.2 | +| entropy_loss | -0.274 | +| explained_variance | -0.117 | +| learning_rate | 0.0001 | +| loss | -0.0502 | +| n_updates | 76450 | +| policy_gradient_loss | -0.0404 | +| value_loss | 0.000686 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | 0.201 | +| time/ | | +| fps | 310 | +| iterations | 1594 | +| time_elapsed | 5256 | +| total_timesteps | 1632256 | +| train/ | | +| approx_kl | 2.8745975 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.313 | +| explained_variance | -1.03 | +| learning_rate | 0.0001 | +| loss | -0.0858 | +| n_updates | 76460 | +| policy_gradient_loss | -0.0575 | +| value_loss | 0.000585 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | 0.201 | +| time/ | | +| fps | 310 | +| iterations | 1595 | +| time_elapsed | 5259 | +| total_timesteps | 1633280 | +| train/ | | +| approx_kl | 2.019504 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.339 | +| explained_variance | -2.33 | +| learning_rate | 0.0001 | +| loss | -0.0918 | +| n_updates | 76470 | +| policy_gradient_loss | -0.0637 | +| value_loss | 0.000973 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | 0.199 | +| time/ | | +| fps | 310 | +| iterations | 1596 | +| time_elapsed | 5263 | +| total_timesteps | 1634304 | +| train/ | | +| approx_kl | 1.6753178 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.367 | +| explained_variance | -1.01 | +| learning_rate | 0.0001 | +| loss | -0.056 | +| n_updates | 76480 | +| policy_gradient_loss | -0.0539 | +| value_loss | 0.000323 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | 0.199 | +| time/ | | +| fps | 310 | +| iterations | 1597 | +| time_elapsed | 5266 | +| total_timesteps | 1635328 | +| train/ | | +| approx_kl | 7.9974465 | +| clip_fraction | 0.493 | +| clip_range | 0.2 | +| entropy_loss | -0.338 | +| explained_variance | -1.37 | +| learning_rate | 0.0001 | +| loss | -0.081 | +| n_updates | 76490 | +| policy_gradient_loss | -0.0585 | +| value_loss | 0.000495 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | 0.196 | +| time/ | | +| fps | 310 | +| iterations | 1598 | +| time_elapsed | 5270 | +| total_timesteps | 1636352 | +| train/ | | +| approx_kl | 3.1395998 | +| clip_fraction | 0.477 | +| clip_range | 0.2 | +| entropy_loss | -0.282 | +| explained_variance | -0.93 | +| learning_rate | 0.0001 | +| loss | -0.0816 | +| n_updates | 76500 | +| policy_gradient_loss | -0.0396 | +| value_loss | 0.000592 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | 0.196 | +| time/ | | +| fps | 310 | +| iterations | 1599 | +| time_elapsed | 5273 | +| total_timesteps | 1637376 | +| train/ | | +| approx_kl | 3.2121167 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.311 | +| explained_variance | -1.71 | +| learning_rate | 0.0001 | +| loss | -0.0684 | +| n_updates | 76510 | +| policy_gradient_loss | -0.0483 | +| value_loss | 0.000434 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | 0.194 | +| time/ | | +| fps | 310 | +| iterations | 1600 | +| time_elapsed | 5277 | +| total_timesteps | 1638400 | +| train/ | | +| approx_kl | 2.5379496 | +| clip_fraction | 0.482 | +| clip_range | 0.2 | +| entropy_loss | -0.334 | +| explained_variance | -4.38 | +| learning_rate | 0.0001 | +| loss | -0.1 | +| n_updates | 76520 | +| policy_gradient_loss | -0.0569 | +| value_loss | 0.000258 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | 0.194 | +| time/ | | +| fps | 310 | +| iterations | 1601 | +| time_elapsed | 5280 | +| total_timesteps | 1639424 | +| train/ | | +| approx_kl | 2.6592128 | +| clip_fraction | 0.453 | +| clip_range | 0.2 | +| entropy_loss | -0.388 | +| explained_variance | -1.59 | +| learning_rate | 0.0001 | +| loss | -0.0628 | +| n_updates | 76530 | +| policy_gradient_loss | -0.0497 | +| value_loss | 0.000208 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | 0.194 | +| time/ | | +| fps | 310 | +| iterations | 1602 | +| time_elapsed | 5284 | +| total_timesteps | 1640448 | +| train/ | | +| approx_kl | 3.0773864 | +| clip_fraction | 0.507 | +| clip_range | 0.2 | +| entropy_loss | -0.362 | +| explained_variance | -0.696 | +| learning_rate | 0.0001 | +| loss | -0.109 | +| n_updates | 76540 | +| policy_gradient_loss | -0.0535 | +| value_loss | 0.00052 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | 0.195 | +| time/ | | +| fps | 310 | +| iterations | 1603 | +| time_elapsed | 5287 | +| total_timesteps | 1641472 | +| train/ | | +| approx_kl | 3.4767962 | +| clip_fraction | 0.466 | +| clip_range | 0.2 | +| entropy_loss | -0.381 | +| explained_variance | -1.39 | +| learning_rate | 0.0001 | +| loss | -0.0775 | +| n_updates | 76550 | +| policy_gradient_loss | -0.0521 | +| value_loss | 0.000392 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | 0.195 | +| time/ | | +| fps | 310 | +| iterations | 1604 | +| time_elapsed | 5290 | +| total_timesteps | 1642496 | +| train/ | | +| approx_kl | 2.8943627 | +| clip_fraction | 0.472 | +| clip_range | 0.2 | +| entropy_loss | -0.301 | +| explained_variance | -0.813 | +| learning_rate | 0.0001 | +| loss | -0.0875 | +| n_updates | 76560 | +| policy_gradient_loss | -0.0638 | +| value_loss | 0.000556 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.192 | +| time/ | | +| fps | 310 | +| iterations | 1605 | +| time_elapsed | 5293 | +| total_timesteps | 1643520 | +| train/ | | +| approx_kl | 2.0107508 | +| clip_fraction | 0.49 | +| clip_range | 0.2 | +| entropy_loss | -0.38 | +| explained_variance | -4.26 | +| learning_rate | 0.0001 | +| loss | -0.061 | +| n_updates | 76570 | +| policy_gradient_loss | -0.0571 | +| value_loss | 0.000301 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.192 | +| time/ | | +| fps | 310 | +| iterations | 1606 | +| time_elapsed | 5297 | +| total_timesteps | 1644544 | +| train/ | | +| approx_kl | 2.734806 | +| clip_fraction | 0.472 | +| clip_range | 0.2 | +| entropy_loss | -0.319 | +| explained_variance | -1.3 | +| learning_rate | 0.0001 | +| loss | -0.0712 | +| n_updates | 76580 | +| policy_gradient_loss | -0.0593 | +| value_loss | 0.000358 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.197 | +| time/ | | +| fps | 310 | +| iterations | 1607 | +| time_elapsed | 5300 | +| total_timesteps | 1645568 | +| train/ | | +| approx_kl | 2.6102183 | +| clip_fraction | 0.464 | +| clip_range | 0.2 | +| entropy_loss | -0.303 | +| explained_variance | -0.658 | +| learning_rate | 0.0001 | +| loss | -0.0549 | +| n_updates | 76590 | +| policy_gradient_loss | -0.0503 | +| value_loss | 0.000645 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.197 | +| time/ | | +| fps | 310 | +| iterations | 1608 | +| time_elapsed | 5303 | +| total_timesteps | 1646592 | +| train/ | | +| approx_kl | 2.1309383 | +| clip_fraction | 0.469 | +| clip_range | 0.2 | +| entropy_loss | -0.358 | +| explained_variance | -3.4 | +| learning_rate | 0.0001 | +| loss | -0.0441 | +| n_updates | 76600 | +| policy_gradient_loss | -0.0577 | +| value_loss | 0.000893 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.193 | +| time/ | | +| fps | 310 | +| iterations | 1609 | +| time_elapsed | 5306 | +| total_timesteps | 1647616 | +| train/ | | +| approx_kl | 2.3858263 | +| clip_fraction | 0.457 | +| clip_range | 0.2 | +| entropy_loss | -0.31 | +| explained_variance | -1.58 | +| learning_rate | 0.0001 | +| loss | -0.0968 | +| n_updates | 76610 | +| policy_gradient_loss | -0.0564 | +| value_loss | 0.000432 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.193 | +| time/ | | +| fps | 310 | +| iterations | 1610 | +| time_elapsed | 5309 | +| total_timesteps | 1648640 | +| train/ | | +| approx_kl | 3.023538 | +| clip_fraction | 0.472 | +| clip_range | 0.2 | +| entropy_loss | -0.303 | +| explained_variance | -1.54 | +| learning_rate | 0.0001 | +| loss | -0.0859 | +| n_updates | 76620 | +| policy_gradient_loss | -0.0558 | +| value_loss | 0.000746 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.192 | +| time/ | | +| fps | 310 | +| iterations | 1611 | +| time_elapsed | 5313 | +| total_timesteps | 1649664 | +| train/ | | +| approx_kl | 3.6596074 | +| clip_fraction | 0.498 | +| clip_range | 0.2 | +| entropy_loss | -0.395 | +| explained_variance | -2.5 | +| learning_rate | 0.0001 | +| loss | -0.111 | +| n_updates | 76630 | +| policy_gradient_loss | -0.0506 | +| value_loss | 0.00028 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.192 | +| time/ | | +| fps | 310 | +| iterations | 1612 | +| time_elapsed | 5316 | +| total_timesteps | 1650688 | +| train/ | | +| approx_kl | 2.246096 | +| clip_fraction | 0.484 | +| clip_range | 0.2 | +| entropy_loss | -0.373 | +| explained_variance | -0.403 | +| learning_rate | 0.0001 | +| loss | -0.0575 | +| n_updates | 76640 | +| policy_gradient_loss | -0.0463 | +| value_loss | 0.000431 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.192 | +| time/ | | +| fps | 310 | +| iterations | 1613 | +| time_elapsed | 5319 | +| total_timesteps | 1651712 | +| train/ | | +| approx_kl | 2.1429 | +| clip_fraction | 0.461 | +| clip_range | 0.2 | +| entropy_loss | -0.308 | +| explained_variance | -5.05 | +| learning_rate | 0.0001 | +| loss | -0.0775 | +| n_updates | 76650 | +| policy_gradient_loss | -0.0616 | +| value_loss | 0.000547 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.197 | +| time/ | | +| fps | 310 | +| iterations | 1614 | +| time_elapsed | 5322 | +| total_timesteps | 1652736 | +| train/ | | +| approx_kl | 1.9707431 | +| clip_fraction | 0.473 | +| clip_range | 0.2 | +| entropy_loss | -0.388 | +| explained_variance | -2.25 | +| learning_rate | 0.0001 | +| loss | -0.114 | +| n_updates | 76660 | +| policy_gradient_loss | -0.0592 | +| value_loss | 0.000259 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.197 | +| time/ | | +| fps | 310 | +| iterations | 1615 | +| time_elapsed | 5326 | +| total_timesteps | 1653760 | +| train/ | | +| approx_kl | 3.140859 | +| clip_fraction | 0.506 | +| clip_range | 0.2 | +| entropy_loss | -0.4 | +| explained_variance | -0.604 | +| learning_rate | 0.0001 | +| loss | -0.0368 | +| n_updates | 76670 | +| policy_gradient_loss | -0.047 | +| value_loss | 0.00037 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.2 | +| time/ | | +| fps | 310 | +| iterations | 1616 | +| time_elapsed | 5329 | +| total_timesteps | 1654784 | +| train/ | | +| approx_kl | 2.4827795 | +| clip_fraction | 0.496 | +| clip_range | 0.2 | +| entropy_loss | -0.392 | +| explained_variance | -1.02 | +| learning_rate | 0.0001 | +| loss | -0.0862 | +| n_updates | 76680 | +| policy_gradient_loss | -0.0605 | +| value_loss | 0.000254 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.2 | +| time/ | | +| fps | 310 | +| iterations | 1617 | +| time_elapsed | 5333 | +| total_timesteps | 1655808 | +| train/ | | +| approx_kl | 3.027091 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.337 | +| explained_variance | -0.788 | +| learning_rate | 0.0001 | +| loss | -0.0635 | +| n_updates | 76690 | +| policy_gradient_loss | -0.0534 | +| value_loss | 0.000572 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.2 | +| time/ | | +| fps | 310 | +| iterations | 1618 | +| time_elapsed | 5336 | +| total_timesteps | 1656832 | +| train/ | | +| approx_kl | 2.6463988 | +| clip_fraction | 0.485 | +| clip_range | 0.2 | +| entropy_loss | -0.328 | +| explained_variance | -1.4 | +| learning_rate | 0.0001 | +| loss | -0.0763 | +| n_updates | 76700 | +| policy_gradient_loss | -0.0567 | +| value_loss | 0.000375 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.2 | +| time/ | | +| fps | 310 | +| iterations | 1619 | +| time_elapsed | 5340 | +| total_timesteps | 1657856 | +| train/ | | +| approx_kl | 2.3423402 | +| clip_fraction | 0.49 | +| clip_range | 0.2 | +| entropy_loss | -0.366 | +| explained_variance | -0.454 | +| learning_rate | 0.0001 | +| loss | -0.0756 | +| n_updates | 76710 | +| policy_gradient_loss | -0.0453 | +| value_loss | 0.000819 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.2 | +| time/ | | +| fps | 310 | +| iterations | 1620 | +| time_elapsed | 5343 | +| total_timesteps | 1658880 | +| train/ | | +| approx_kl | 1.7454354 | +| clip_fraction | 0.453 | +| clip_range | 0.2 | +| entropy_loss | -0.305 | +| explained_variance | -1.67 | +| learning_rate | 0.0001 | +| loss | -0.096 | +| n_updates | 76720 | +| policy_gradient_loss | -0.0617 | +| value_loss | 0.000365 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.196 | +| time/ | | +| fps | 310 | +| iterations | 1621 | +| time_elapsed | 5346 | +| total_timesteps | 1659904 | +| train/ | | +| approx_kl | 2.1750686 | +| clip_fraction | 0.498 | +| clip_range | 0.2 | +| entropy_loss | -0.328 | +| explained_variance | -1.53 | +| learning_rate | 0.0001 | +| loss | -0.0359 | +| n_updates | 76730 | +| policy_gradient_loss | -0.0518 | +| value_loss | 0.000422 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.196 | +| time/ | | +| fps | 310 | +| iterations | 1622 | +| time_elapsed | 5350 | +| total_timesteps | 1660928 | +| train/ | | +| approx_kl | 2.1161475 | +| clip_fraction | 0.466 | +| clip_range | 0.2 | +| entropy_loss | -0.341 | +| explained_variance | -1.3 | +| learning_rate | 0.0001 | +| loss | -0.0476 | +| n_updates | 76740 | +| policy_gradient_loss | -0.0557 | +| value_loss | 0.000195 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.196 | +| time/ | | +| fps | 310 | +| iterations | 1623 | +| time_elapsed | 5353 | +| total_timesteps | 1661952 | +| train/ | | +| approx_kl | 2.7052062 | +| clip_fraction | 0.565 | +| clip_range | 0.2 | +| entropy_loss | -0.449 | +| explained_variance | -0.314 | +| learning_rate | 0.0001 | +| loss | -0.0742 | +| n_updates | 76750 | +| policy_gradient_loss | -0.028 | +| value_loss | 0.000394 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.202 | +| time/ | | +| fps | 310 | +| iterations | 1624 | +| time_elapsed | 5356 | +| total_timesteps | 1662976 | +| train/ | | +| approx_kl | 1.3531976 | +| clip_fraction | 0.416 | +| clip_range | 0.2 | +| entropy_loss | -0.375 | +| explained_variance | -0.654 | +| learning_rate | 0.0001 | +| loss | -0.0667 | +| n_updates | 76760 | +| policy_gradient_loss | -0.0513 | +| value_loss | 0.000259 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.197 | +| time/ | | +| fps | 310 | +| iterations | 1625 | +| time_elapsed | 5359 | +| total_timesteps | 1664000 | +| train/ | | +| approx_kl | 1.9029691 | +| clip_fraction | 0.465 | +| clip_range | 0.2 | +| entropy_loss | -0.382 | +| explained_variance | -0.969 | +| learning_rate | 0.0001 | +| loss | -0.0661 | +| n_updates | 76770 | +| policy_gradient_loss | -0.0595 | +| value_loss | 0.000334 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.197 | +| time/ | | +| fps | 310 | +| iterations | 1626 | +| time_elapsed | 5362 | +| total_timesteps | 1665024 | +| train/ | | +| approx_kl | 2.4527872 | +| clip_fraction | 0.45 | +| clip_range | 0.2 | +| entropy_loss | -0.31 | +| explained_variance | -1.21 | +| learning_rate | 0.0001 | +| loss | -0.0648 | +| n_updates | 76780 | +| policy_gradient_loss | -0.0557 | +| value_loss | 0.000518 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.195 | +| time/ | | +| fps | 310 | +| iterations | 1627 | +| time_elapsed | 5365 | +| total_timesteps | 1666048 | +| train/ | | +| approx_kl | 2.5844164 | +| clip_fraction | 0.499 | +| clip_range | 0.2 | +| entropy_loss | -0.343 | +| explained_variance | -0.827 | +| learning_rate | 0.0001 | +| loss | -0.0695 | +| n_updates | 76790 | +| policy_gradient_loss | -0.0568 | +| value_loss | 0.000651 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.195 | +| time/ | | +| fps | 310 | +| iterations | 1628 | +| time_elapsed | 5369 | +| total_timesteps | 1667072 | +| train/ | | +| approx_kl | 2.726691 | +| clip_fraction | 0.49 | +| clip_range | 0.2 | +| entropy_loss | -0.37 | +| explained_variance | -1.23 | +| learning_rate | 0.0001 | +| loss | -0.0988 | +| n_updates | 76800 | +| policy_gradient_loss | -0.0602 | +| value_loss | 0.000839 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.195 | +| time/ | | +| fps | 310 | +| iterations | 1629 | +| time_elapsed | 5372 | +| total_timesteps | 1668096 | +| train/ | | +| approx_kl | 2.6215591 | +| clip_fraction | 0.49 | +| clip_range | 0.2 | +| entropy_loss | -0.331 | +| explained_variance | -1.25 | +| learning_rate | 0.0001 | +| loss | -0.0924 | +| n_updates | 76810 | +| policy_gradient_loss | -0.0696 | +| value_loss | 0.000617 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.195 | +| time/ | | +| fps | 310 | +| iterations | 1630 | +| time_elapsed | 5375 | +| total_timesteps | 1669120 | +| train/ | | +| approx_kl | 2.5830073 | +| clip_fraction | 0.502 | +| clip_range | 0.2 | +| entropy_loss | -0.353 | +| explained_variance | -3 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 76820 | +| policy_gradient_loss | -0.0594 | +| value_loss | 0.0004 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.195 | +| time/ | | +| fps | 310 | +| iterations | 1631 | +| time_elapsed | 5378 | +| total_timesteps | 1670144 | +| train/ | | +| approx_kl | 1.8224959 | +| clip_fraction | 0.461 | +| clip_range | 0.2 | +| entropy_loss | -0.336 | +| explained_variance | -1.76 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 76830 | +| policy_gradient_loss | -0.0587 | +| value_loss | 0.000408 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.195 | +| time/ | | +| fps | 310 | +| iterations | 1632 | +| time_elapsed | 5381 | +| total_timesteps | 1671168 | +| train/ | | +| approx_kl | 1.5333797 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.347 | +| explained_variance | -0.223 | +| learning_rate | 0.0001 | +| loss | -0.093 | +| n_updates | 76840 | +| policy_gradient_loss | -0.0436 | +| value_loss | 0.000556 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.78e+03 | +| ep_rew_mean | 0.198 | +| time/ | | +| fps | 310 | +| iterations | 1633 | +| time_elapsed | 5385 | +| total_timesteps | 1672192 | +| train/ | | +| approx_kl | 2.7830257 | +| clip_fraction | 0.514 | +| clip_range | 0.2 | +| entropy_loss | -0.4 | +| explained_variance | -2.63 | +| learning_rate | 0.0001 | +| loss | -0.0855 | +| n_updates | 76850 | +| policy_gradient_loss | -0.0652 | +| value_loss | 0.000426 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.78e+03 | +| ep_rew_mean | 0.198 | +| time/ | | +| fps | 310 | +| iterations | 1634 | +| time_elapsed | 5388 | +| total_timesteps | 1673216 | +| train/ | | +| approx_kl | 3.300696 | +| clip_fraction | 0.522 | +| clip_range | 0.2 | +| entropy_loss | -0.448 | +| explained_variance | -1.06 | +| learning_rate | 0.0001 | +| loss | -0.0695 | +| n_updates | 76860 | +| policy_gradient_loss | -0.0562 | +| value_loss | 0.000406 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.8e+03 | +| ep_rew_mean | 0.196 | +| time/ | | +| fps | 310 | +| iterations | 1635 | +| time_elapsed | 5392 | +| total_timesteps | 1674240 | +| train/ | | +| approx_kl | 2.414784 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.346 | +| explained_variance | -2.1 | +| learning_rate | 0.0001 | +| loss | -0.0916 | +| n_updates | 76870 | +| policy_gradient_loss | -0.0649 | +| value_loss | 0.000467 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.8e+03 | +| ep_rew_mean | 0.196 | +| time/ | | +| fps | 310 | +| iterations | 1636 | +| time_elapsed | 5395 | +| total_timesteps | 1675264 | +| train/ | | +| approx_kl | 2.1958032 | +| clip_fraction | 0.513 | +| clip_range | 0.2 | +| entropy_loss | -0.542 | +| explained_variance | -1.25 | +| learning_rate | 0.0001 | +| loss | -0.0547 | +| n_updates | 76880 | +| policy_gradient_loss | -0.062 | +| value_loss | 0.000246 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.8e+03 | +| ep_rew_mean | 0.196 | +| time/ | | +| fps | 310 | +| iterations | 1637 | +| time_elapsed | 5399 | +| total_timesteps | 1676288 | +| train/ | | +| approx_kl | 2.9007049 | +| clip_fraction | 0.511 | +| clip_range | 0.2 | +| entropy_loss | -0.373 | +| explained_variance | -0.318 | +| learning_rate | 0.0001 | +| loss | -0.0714 | +| n_updates | 76890 | +| policy_gradient_loss | -0.0473 | +| value_loss | 0.000431 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.8e+03 | +| ep_rew_mean | 0.194 | +| time/ | | +| fps | 310 | +| iterations | 1638 | +| time_elapsed | 5402 | +| total_timesteps | 1677312 | +| train/ | | +| approx_kl | 2.4688401 | +| clip_fraction | 0.495 | +| clip_range | 0.2 | +| entropy_loss | -0.338 | +| explained_variance | -2.47 | +| learning_rate | 0.0001 | +| loss | -0.0705 | +| n_updates | 76900 | +| policy_gradient_loss | -0.045 | +| value_loss | 0.000319 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.8e+03 | +| ep_rew_mean | 0.194 | +| time/ | | +| fps | 310 | +| iterations | 1639 | +| time_elapsed | 5406 | +| total_timesteps | 1678336 | +| train/ | | +| approx_kl | 34.927822 | +| clip_fraction | 0.494 | +| clip_range | 0.2 | +| entropy_loss | -0.356 | +| explained_variance | -2.56 | +| learning_rate | 0.0001 | +| loss | -0.0935 | +| n_updates | 76910 | +| policy_gradient_loss | -0.065 | +| value_loss | 0.000227 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.82e+03 | +| ep_rew_mean | 0.2 | +| time/ | | +| fps | 310 | +| iterations | 1640 | +| time_elapsed | 5409 | +| total_timesteps | 1679360 | +| train/ | | +| approx_kl | 2.7206905 | +| clip_fraction | 0.496 | +| clip_range | 0.2 | +| entropy_loss | -0.356 | +| explained_variance | -0.85 | +| learning_rate | 0.0001 | +| loss | -0.0804 | +| n_updates | 76920 | +| policy_gradient_loss | -0.0566 | +| value_loss | 0.000559 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.82e+03 | +| ep_rew_mean | 0.2 | +| time/ | | +| fps | 310 | +| iterations | 1641 | +| time_elapsed | 5412 | +| total_timesteps | 1680384 | +| train/ | | +| approx_kl | 2.2898116 | +| clip_fraction | 0.479 | +| clip_range | 0.2 | +| entropy_loss | -0.319 | +| explained_variance | -1.7 | +| learning_rate | 0.0001 | +| loss | -0.0771 | +| n_updates | 76930 | +| policy_gradient_loss | -0.0552 | +| value_loss | 0.000423 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.82e+03 | +| ep_rew_mean | 0.2 | +| time/ | | +| fps | 310 | +| iterations | 1642 | +| time_elapsed | 5416 | +| total_timesteps | 1681408 | +| train/ | | +| approx_kl | 2.7975364 | +| clip_fraction | 0.472 | +| clip_range | 0.2 | +| entropy_loss | -0.339 | +| explained_variance | -0.905 | +| learning_rate | 0.0001 | +| loss | -0.0303 | +| n_updates | 76940 | +| policy_gradient_loss | -0.0449 | +| value_loss | 0.000408 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.205 | +| time/ | | +| fps | 310 | +| iterations | 1643 | +| time_elapsed | 5419 | +| total_timesteps | 1682432 | +| train/ | | +| approx_kl | 1.8105824 | +| clip_fraction | 0.438 | +| clip_range | 0.2 | +| entropy_loss | -0.335 | +| explained_variance | -0.948 | +| learning_rate | 0.0001 | +| loss | -0.087 | +| n_updates | 76950 | +| policy_gradient_loss | -0.0495 | +| value_loss | 0.000217 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.205 | +| time/ | | +| fps | 310 | +| iterations | 1644 | +| time_elapsed | 5422 | +| total_timesteps | 1683456 | +| train/ | | +| approx_kl | 2.2519422 | +| clip_fraction | 0.468 | +| clip_range | 0.2 | +| entropy_loss | -0.328 | +| explained_variance | -1.65 | +| learning_rate | 0.0001 | +| loss | -0.069 | +| n_updates | 76960 | +| policy_gradient_loss | -0.0564 | +| value_loss | 0.00036 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.199 | +| time/ | | +| fps | 310 | +| iterations | 1645 | +| time_elapsed | 5425 | +| total_timesteps | 1684480 | +| train/ | | +| approx_kl | 2.0643415 | +| clip_fraction | 0.514 | +| clip_range | 0.2 | +| entropy_loss | -0.448 | +| explained_variance | -2.71 | +| learning_rate | 0.0001 | +| loss | -0.0825 | +| n_updates | 76970 | +| policy_gradient_loss | -0.0571 | +| value_loss | 0.000363 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.199 | +| time/ | | +| fps | 310 | +| iterations | 1646 | +| time_elapsed | 5428 | +| total_timesteps | 1685504 | +| train/ | | +| approx_kl | 1.8637246 | +| clip_fraction | 0.426 | +| clip_range | 0.2 | +| entropy_loss | -0.332 | +| explained_variance | -0.709 | +| learning_rate | 0.0001 | +| loss | -0.0841 | +| n_updates | 76980 | +| policy_gradient_loss | -0.0526 | +| value_loss | 0.000217 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.197 | +| time/ | | +| fps | 310 | +| iterations | 1647 | +| time_elapsed | 5431 | +| total_timesteps | 1686528 | +| train/ | | +| approx_kl | 2.2303863 | +| clip_fraction | 0.468 | +| clip_range | 0.2 | +| entropy_loss | -0.35 | +| explained_variance | -0.627 | +| learning_rate | 0.0001 | +| loss | -0.0881 | +| n_updates | 76990 | +| policy_gradient_loss | -0.0535 | +| value_loss | 0.000268 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.197 | +| time/ | | +| fps | 310 | +| iterations | 1648 | +| time_elapsed | 5435 | +| total_timesteps | 1687552 | +| train/ | | +| approx_kl | 1.5338861 | +| clip_fraction | 0.461 | +| clip_range | 0.2 | +| entropy_loss | -0.387 | +| explained_variance | -0.36 | +| learning_rate | 0.0001 | +| loss | -0.0652 | +| n_updates | 77000 | +| policy_gradient_loss | -0.0468 | +| value_loss | 0.000494 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.192 | +| time/ | | +| fps | 310 | +| iterations | 1649 | +| time_elapsed | 5438 | +| total_timesteps | 1688576 | +| train/ | | +| approx_kl | 7.80762 | +| clip_fraction | 0.493 | +| clip_range | 0.2 | +| entropy_loss | -0.372 | +| explained_variance | -2.28 | +| learning_rate | 0.0001 | +| loss | -0.0882 | +| n_updates | 77010 | +| policy_gradient_loss | -0.0678 | +| value_loss | 0.000441 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.192 | +| time/ | | +| fps | 310 | +| iterations | 1650 | +| time_elapsed | 5441 | +| total_timesteps | 1689600 | +| train/ | | +| approx_kl | 2.2512152 | +| clip_fraction | 0.496 | +| clip_range | 0.2 | +| entropy_loss | -0.375 | +| explained_variance | -1.2 | +| learning_rate | 0.0001 | +| loss | -0.0415 | +| n_updates | 77020 | +| policy_gradient_loss | -0.0528 | +| value_loss | 0.000276 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.192 | +| time/ | | +| fps | 310 | +| iterations | 1651 | +| time_elapsed | 5444 | +| total_timesteps | 1690624 | +| train/ | | +| approx_kl | 2.5352354 | +| clip_fraction | 0.517 | +| clip_range | 0.2 | +| entropy_loss | -0.373 | +| explained_variance | -2.69 | +| learning_rate | 0.0001 | +| loss | -0.0835 | +| n_updates | 77030 | +| policy_gradient_loss | -0.0582 | +| value_loss | 0.000317 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.192 | +| time/ | | +| fps | 310 | +| iterations | 1652 | +| time_elapsed | 5447 | +| total_timesteps | 1691648 | +| train/ | | +| approx_kl | 2.2033727 | +| clip_fraction | 0.469 | +| clip_range | 0.2 | +| entropy_loss | -0.325 | +| explained_variance | -0.863 | +| learning_rate | 0.0001 | +| loss | -0.079 | +| n_updates | 77040 | +| policy_gradient_loss | -0.0594 | +| value_loss | 0.000574 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.192 | +| time/ | | +| fps | 310 | +| iterations | 1653 | +| time_elapsed | 5451 | +| total_timesteps | 1692672 | +| train/ | | +| approx_kl | 2.1237092 | +| clip_fraction | 0.447 | +| clip_range | 0.2 | +| entropy_loss | -0.351 | +| explained_variance | -7.95 | +| learning_rate | 0.0001 | +| loss | -0.0601 | +| n_updates | 77050 | +| policy_gradient_loss | -0.0353 | +| value_loss | 0.000138 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.192 | +| time/ | | +| fps | 310 | +| iterations | 1654 | +| time_elapsed | 5454 | +| total_timesteps | 1693696 | +| train/ | | +| approx_kl | 1.4933609 | +| clip_fraction | 0.455 | +| clip_range | 0.2 | +| entropy_loss | -0.511 | +| explained_variance | -0.432 | +| learning_rate | 0.0001 | +| loss | -0.0599 | +| n_updates | 77060 | +| policy_gradient_loss | -0.0271 | +| value_loss | 0.00105 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.192 | +| time/ | | +| fps | 310 | +| iterations | 1655 | +| time_elapsed | 5458 | +| total_timesteps | 1694720 | +| train/ | | +| approx_kl | 2.5106544 | +| clip_fraction | 0.463 | +| clip_range | 0.2 | +| entropy_loss | -0.332 | +| explained_variance | -3.04 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 77070 | +| policy_gradient_loss | -0.0606 | +| value_loss | 0.000461 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.89e+03 | +| ep_rew_mean | 0.194 | +| time/ | | +| fps | 310 | +| iterations | 1656 | +| time_elapsed | 5461 | +| total_timesteps | 1695744 | +| train/ | | +| approx_kl | 2.4010952 | +| clip_fraction | 0.489 | +| clip_range | 0.2 | +| entropy_loss | -0.382 | +| explained_variance | -1.39 | +| learning_rate | 0.0001 | +| loss | -0.0852 | +| n_updates | 77080 | +| policy_gradient_loss | -0.0524 | +| value_loss | 0.000606 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.89e+03 | +| ep_rew_mean | 0.194 | +| time/ | | +| fps | 310 | +| iterations | 1657 | +| time_elapsed | 5464 | +| total_timesteps | 1696768 | +| train/ | | +| approx_kl | 2.033948 | +| clip_fraction | 0.515 | +| clip_range | 0.2 | +| entropy_loss | -0.403 | +| explained_variance | -0.873 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 77090 | +| policy_gradient_loss | -0.0662 | +| value_loss | 0.000528 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.9e+03 | +| ep_rew_mean | 0.192 | +| time/ | | +| fps | 310 | +| iterations | 1658 | +| time_elapsed | 5468 | +| total_timesteps | 1697792 | +| train/ | | +| approx_kl | 2.2220395 | +| clip_fraction | 0.556 | +| clip_range | 0.2 | +| entropy_loss | -0.543 | +| explained_variance | -3.49 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 77100 | +| policy_gradient_loss | -0.068 | +| value_loss | 0.000371 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.9e+03 | +| ep_rew_mean | 0.192 | +| time/ | | +| fps | 310 | +| iterations | 1659 | +| time_elapsed | 5471 | +| total_timesteps | 1698816 | +| train/ | | +| approx_kl | 1.8545967 | +| clip_fraction | 0.446 | +| clip_range | 0.2 | +| entropy_loss | -0.326 | +| explained_variance | -3.67 | +| learning_rate | 0.0001 | +| loss | -0.1 | +| n_updates | 77110 | +| policy_gradient_loss | -0.0611 | +| value_loss | 0.000208 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.91e+03 | +| ep_rew_mean | 0.193 | +| time/ | | +| fps | 310 | +| iterations | 1660 | +| time_elapsed | 5474 | +| total_timesteps | 1699840 | +| train/ | | +| approx_kl | 12.478692 | +| clip_fraction | 0.494 | +| clip_range | 0.2 | +| entropy_loss | -0.408 | +| explained_variance | -1.25 | +| learning_rate | 0.0001 | +| loss | -0.0874 | +| n_updates | 77120 | +| policy_gradient_loss | -0.0697 | +| value_loss | 0.000214 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.91e+03 | +| ep_rew_mean | 0.193 | +| time/ | | +| fps | 310 | +| iterations | 1661 | +| time_elapsed | 5477 | +| total_timesteps | 1700864 | +| train/ | | +| approx_kl | 2.173467 | +| clip_fraction | 0.468 | +| clip_range | 0.2 | +| entropy_loss | -0.36 | +| explained_variance | -0.866 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 77130 | +| policy_gradient_loss | -0.0536 | +| value_loss | 0.000394 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.91e+03 | +| ep_rew_mean | 0.193 | +| time/ | | +| fps | 310 | +| iterations | 1662 | +| time_elapsed | 5480 | +| total_timesteps | 1701888 | +| train/ | | +| approx_kl | 2.4674573 | +| clip_fraction | 0.543 | +| clip_range | 0.2 | +| entropy_loss | -0.469 | +| explained_variance | -1.08 | +| learning_rate | 0.0001 | +| loss | -0.0945 | +| n_updates | 77140 | +| policy_gradient_loss | -0.0657 | +| value_loss | 0.000664 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.92e+03 | +| ep_rew_mean | 0.192 | +| time/ | | +| fps | 310 | +| iterations | 1663 | +| time_elapsed | 5483 | +| total_timesteps | 1702912 | +| train/ | | +| approx_kl | 1.82296 | +| clip_fraction | 0.5 | +| clip_range | 0.2 | +| entropy_loss | -0.417 | +| explained_variance | -1.15 | +| learning_rate | 0.0001 | +| loss | -0.106 | +| n_updates | 77150 | +| policy_gradient_loss | -0.0667 | +| value_loss | 0.000621 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.92e+03 | +| ep_rew_mean | 0.192 | +| time/ | | +| fps | 310 | +| iterations | 1664 | +| time_elapsed | 5487 | +| total_timesteps | 1703936 | +| train/ | | +| approx_kl | 1.9527547 | +| clip_fraction | 0.463 | +| clip_range | 0.2 | +| entropy_loss | -0.336 | +| explained_variance | -1.82 | +| learning_rate | 0.0001 | +| loss | -0.0744 | +| n_updates | 77160 | +| policy_gradient_loss | -0.0493 | +| value_loss | 0.000517 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.93e+03 | +| ep_rew_mean | 0.193 | +| time/ | | +| fps | 310 | +| iterations | 1665 | +| time_elapsed | 5490 | +| total_timesteps | 1704960 | +| train/ | | +| approx_kl | 2.101993 | +| clip_fraction | 0.503 | +| clip_range | 0.2 | +| entropy_loss | -0.403 | +| explained_variance | -1.13 | +| learning_rate | 0.0001 | +| loss | -0.0685 | +| n_updates | 77170 | +| policy_gradient_loss | -0.0634 | +| value_loss | 0.000345 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.93e+03 | +| ep_rew_mean | 0.193 | +| time/ | | +| fps | 310 | +| iterations | 1666 | +| time_elapsed | 5493 | +| total_timesteps | 1705984 | +| train/ | | +| approx_kl | 3.0502796 | +| clip_fraction | 0.509 | +| clip_range | 0.2 | +| entropy_loss | -0.381 | +| explained_variance | -1.17 | +| learning_rate | 0.0001 | +| loss | -0.0786 | +| n_updates | 77180 | +| policy_gradient_loss | -0.0577 | +| value_loss | 0.00044 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.94e+03 | +| ep_rew_mean | 0.196 | +| time/ | | +| fps | 310 | +| iterations | 1667 | +| time_elapsed | 5496 | +| total_timesteps | 1707008 | +| train/ | | +| approx_kl | 2.5702248 | +| clip_fraction | 0.494 | +| clip_range | 0.2 | +| entropy_loss | -0.432 | +| explained_variance | -1.51 | +| learning_rate | 0.0001 | +| loss | -0.0799 | +| n_updates | 77190 | +| policy_gradient_loss | -0.06 | +| value_loss | 0.000342 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.94e+03 | +| ep_rew_mean | 0.196 | +| time/ | | +| fps | 310 | +| iterations | 1668 | +| time_elapsed | 5499 | +| total_timesteps | 1708032 | +| train/ | | +| approx_kl | 2.6528566 | +| clip_fraction | 0.522 | +| clip_range | 0.2 | +| entropy_loss | -0.367 | +| explained_variance | -0.342 | +| learning_rate | 0.0001 | +| loss | -0.0708 | +| n_updates | 77200 | +| policy_gradient_loss | -0.057 | +| value_loss | 0.000452 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.94e+03 | +| ep_rew_mean | 0.196 | +| time/ | | +| fps | 310 | +| iterations | 1669 | +| time_elapsed | 5503 | +| total_timesteps | 1709056 | +| train/ | | +| approx_kl | 1.5472527 | +| clip_fraction | 0.484 | +| clip_range | 0.2 | +| entropy_loss | -0.44 | +| explained_variance | -1.21 | +| learning_rate | 0.0001 | +| loss | -0.0704 | +| n_updates | 77210 | +| policy_gradient_loss | -0.0567 | +| value_loss | 0.000427 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.94e+03 | +| ep_rew_mean | 0.196 | +| time/ | | +| fps | 310 | +| iterations | 1670 | +| time_elapsed | 5506 | +| total_timesteps | 1710080 | +| train/ | | +| approx_kl | 1.296831 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.479 | +| explained_variance | -0.69 | +| learning_rate | 0.0001 | +| loss | -0.0889 | +| n_updates | 77220 | +| policy_gradient_loss | -0.0602 | +| value_loss | 0.000114 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.95e+03 | +| ep_rew_mean | 0.194 | +| time/ | | +| fps | 310 | +| iterations | 1671 | +| time_elapsed | 5510 | +| total_timesteps | 1711104 | +| train/ | | +| approx_kl | 2.359016 | +| clip_fraction | 0.488 | +| clip_range | 0.2 | +| entropy_loss | -0.375 | +| explained_variance | -2.88 | +| learning_rate | 0.0001 | +| loss | -0.0837 | +| n_updates | 77230 | +| policy_gradient_loss | -0.056 | +| value_loss | 0.000291 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.95e+03 | +| ep_rew_mean | 0.194 | +| time/ | | +| fps | 310 | +| iterations | 1672 | +| time_elapsed | 5513 | +| total_timesteps | 1712128 | +| train/ | | +| approx_kl | 1.5367419 | +| clip_fraction | 0.493 | +| clip_range | 0.2 | +| entropy_loss | -0.436 | +| explained_variance | -1.43 | +| learning_rate | 0.0001 | +| loss | -0.0746 | +| n_updates | 77240 | +| policy_gradient_loss | -0.0494 | +| value_loss | 0.000138 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.95e+03 | +| ep_rew_mean | 0.194 | +| time/ | | +| fps | 310 | +| iterations | 1673 | +| time_elapsed | 5517 | +| total_timesteps | 1713152 | +| train/ | | +| approx_kl | 2.0750985 | +| clip_fraction | 0.485 | +| clip_range | 0.2 | +| entropy_loss | -0.37 | +| explained_variance | -1.85 | +| learning_rate | 0.0001 | +| loss | -0.116 | +| n_updates | 77250 | +| policy_gradient_loss | -0.0703 | +| value_loss | 0.000175 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.97e+03 | +| ep_rew_mean | 0.192 | +| time/ | | +| fps | 310 | +| iterations | 1674 | +| time_elapsed | 5520 | +| total_timesteps | 1714176 | +| train/ | | +| approx_kl | 1.7618333 | +| clip_fraction | 0.518 | +| clip_range | 0.2 | +| entropy_loss | -0.458 | +| explained_variance | -1.63 | +| learning_rate | 0.0001 | +| loss | -0.0427 | +| n_updates | 77260 | +| policy_gradient_loss | -0.0631 | +| value_loss | 0.000124 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.97e+03 | +| ep_rew_mean | 0.192 | +| time/ | | +| fps | 310 | +| iterations | 1675 | +| time_elapsed | 5523 | +| total_timesteps | 1715200 | +| train/ | | +| approx_kl | 2.0282552 | +| clip_fraction | 0.506 | +| clip_range | 0.2 | +| entropy_loss | -0.394 | +| explained_variance | -0.874 | +| learning_rate | 0.0001 | +| loss | -0.0705 | +| n_updates | 77270 | +| policy_gradient_loss | -0.0665 | +| value_loss | 0.000801 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.99e+03 | +| ep_rew_mean | 0.197 | +| time/ | | +| fps | 310 | +| iterations | 1676 | +| time_elapsed | 5527 | +| total_timesteps | 1716224 | +| train/ | | +| approx_kl | 2.3532398 | +| clip_fraction | 0.494 | +| clip_range | 0.2 | +| entropy_loss | -0.483 | +| explained_variance | -3.16 | +| learning_rate | 0.0001 | +| loss | -0.0774 | +| n_updates | 77280 | +| policy_gradient_loss | -0.0702 | +| value_loss | 0.000485 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.99e+03 | +| ep_rew_mean | 0.197 | +| time/ | | +| fps | 310 | +| iterations | 1677 | +| time_elapsed | 5530 | +| total_timesteps | 1717248 | +| train/ | | +| approx_kl | 3.8971334 | +| clip_fraction | 0.51 | +| clip_range | 0.2 | +| entropy_loss | -0.385 | +| explained_variance | -2.12 | +| learning_rate | 0.0001 | +| loss | -0.0951 | +| n_updates | 77290 | +| policy_gradient_loss | -0.0643 | +| value_loss | 0.000515 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2e+03 | +| ep_rew_mean | 0.199 | +| time/ | | +| fps | 310 | +| iterations | 1678 | +| time_elapsed | 5533 | +| total_timesteps | 1718272 | +| train/ | | +| approx_kl | 2.3760052 | +| clip_fraction | 0.476 | +| clip_range | 0.2 | +| entropy_loss | -0.389 | +| explained_variance | -1.72 | +| learning_rate | 0.0001 | +| loss | -0.0398 | +| n_updates | 77300 | +| policy_gradient_loss | -0.0536 | +| value_loss | 0.000294 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2e+03 | +| ep_rew_mean | 0.199 | +| time/ | | +| fps | 310 | +| iterations | 1679 | +| time_elapsed | 5537 | +| total_timesteps | 1719296 | +| train/ | | +| approx_kl | 2.3275814 | +| clip_fraction | 0.451 | +| clip_range | 0.2 | +| entropy_loss | -0.315 | +| explained_variance | -1.37 | +| learning_rate | 0.0001 | +| loss | -0.0831 | +| n_updates | 77310 | +| policy_gradient_loss | -0.0647 | +| value_loss | 0.000754 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2e+03 | +| ep_rew_mean | 0.199 | +| time/ | | +| fps | 310 | +| iterations | 1680 | +| time_elapsed | 5540 | +| total_timesteps | 1720320 | +| train/ | | +| approx_kl | 1.6287205 | +| clip_fraction | 0.512 | +| clip_range | 0.2 | +| entropy_loss | -0.481 | +| explained_variance | -0.265 | +| learning_rate | 0.0001 | +| loss | -0.075 | +| n_updates | 77320 | +| policy_gradient_loss | -0.0681 | +| value_loss | 0.000506 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2e+03 | +| ep_rew_mean | 0.199 | +| time/ | | +| fps | 310 | +| iterations | 1681 | +| time_elapsed | 5543 | +| total_timesteps | 1721344 | +| train/ | | +| approx_kl | 2.4131997 | +| clip_fraction | 0.525 | +| clip_range | 0.2 | +| entropy_loss | -0.388 | +| explained_variance | -1.54 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 77330 | +| policy_gradient_loss | -0.0576 | +| value_loss | 0.000705 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2e+03 | +| ep_rew_mean | 0.201 | +| time/ | | +| fps | 310 | +| iterations | 1682 | +| time_elapsed | 5546 | +| total_timesteps | 1722368 | +| train/ | | +| approx_kl | 2.3088286 | +| clip_fraction | 0.516 | +| clip_range | 0.2 | +| entropy_loss | -0.462 | +| explained_variance | -1.18 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 77340 | +| policy_gradient_loss | -0.0618 | +| value_loss | 0.00029 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2e+03 | +| ep_rew_mean | 0.201 | +| time/ | | +| fps | 310 | +| iterations | 1683 | +| time_elapsed | 5549 | +| total_timesteps | 1723392 | +| train/ | | +| approx_kl | 1.904487 | +| clip_fraction | 0.542 | +| clip_range | 0.2 | +| entropy_loss | -0.496 | +| explained_variance | -0.282 | +| learning_rate | 0.0001 | +| loss | -0.0762 | +| n_updates | 77350 | +| policy_gradient_loss | -0.0652 | +| value_loss | 0.00069 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2e+03 | +| ep_rew_mean | 0.201 | +| time/ | | +| fps | 310 | +| iterations | 1684 | +| time_elapsed | 5552 | +| total_timesteps | 1724416 | +| train/ | | +| approx_kl | 2.3514936 | +| clip_fraction | 0.511 | +| clip_range | 0.2 | +| entropy_loss | -0.391 | +| explained_variance | -2.72 | +| learning_rate | 0.0001 | +| loss | -0.085 | +| n_updates | 77360 | +| policy_gradient_loss | -0.0675 | +| value_loss | 0.000385 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.01e+03 | +| ep_rew_mean | 0.197 | +| time/ | | +| fps | 310 | +| iterations | 1685 | +| time_elapsed | 5555 | +| total_timesteps | 1725440 | +| train/ | | +| approx_kl | 5.898565 | +| clip_fraction | 0.501 | +| clip_range | 0.2 | +| entropy_loss | -0.389 | +| explained_variance | -0.689 | +| learning_rate | 0.0001 | +| loss | -0.107 | +| n_updates | 77370 | +| policy_gradient_loss | -0.0574 | +| value_loss | 0.000229 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.01e+03 | +| ep_rew_mean | 0.197 | +| time/ | | +| fps | 310 | +| iterations | 1686 | +| time_elapsed | 5559 | +| total_timesteps | 1726464 | +| train/ | | +| approx_kl | 3.0308118 | +| clip_fraction | 0.506 | +| clip_range | 0.2 | +| entropy_loss | -0.39 | +| explained_variance | -1.42 | +| learning_rate | 0.0001 | +| loss | -0.0614 | +| n_updates | 77380 | +| policy_gradient_loss | -0.0561 | +| value_loss | 0.000291 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.01e+03 | +| ep_rew_mean | 0.195 | +| time/ | | +| fps | 310 | +| iterations | 1687 | +| time_elapsed | 5562 | +| total_timesteps | 1727488 | +| train/ | | +| approx_kl | 2.6498857 | +| clip_fraction | 0.525 | +| clip_range | 0.2 | +| entropy_loss | -0.371 | +| explained_variance | -3.75 | +| learning_rate | 0.0001 | +| loss | -0.0866 | +| n_updates | 77390 | +| policy_gradient_loss | -0.064 | +| value_loss | 0.000384 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.01e+03 | +| ep_rew_mean | 0.195 | +| time/ | | +| fps | 310 | +| iterations | 1688 | +| time_elapsed | 5565 | +| total_timesteps | 1728512 | +| train/ | | +| approx_kl | 1.863108 | +| clip_fraction | 0.51 | +| clip_range | 0.2 | +| entropy_loss | -0.462 | +| explained_variance | -0.605 | +| learning_rate | 0.0001 | +| loss | -0.089 | +| n_updates | 77400 | +| policy_gradient_loss | -0.0643 | +| value_loss | 0.000675 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.02e+03 | +| ep_rew_mean | 0.196 | +| time/ | | +| fps | 310 | +| iterations | 1689 | +| time_elapsed | 5569 | +| total_timesteps | 1729536 | +| train/ | | +| approx_kl | 2.316661 | +| clip_fraction | 0.486 | +| clip_range | 0.2 | +| entropy_loss | -0.392 | +| explained_variance | -1.75 | +| learning_rate | 0.0001 | +| loss | -0.113 | +| n_updates | 77410 | +| policy_gradient_loss | -0.0631 | +| value_loss | 0.000367 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.02e+03 | +| ep_rew_mean | 0.196 | +| time/ | | +| fps | 310 | +| iterations | 1690 | +| time_elapsed | 5572 | +| total_timesteps | 1730560 | +| train/ | | +| approx_kl | 2.3737817 | +| clip_fraction | 0.496 | +| clip_range | 0.2 | +| entropy_loss | -0.39 | +| explained_variance | -1.19 | +| learning_rate | 0.0001 | +| loss | -0.0826 | +| n_updates | 77420 | +| policy_gradient_loss | -0.0673 | +| value_loss | 0.000465 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.02e+03 | +| ep_rew_mean | 0.196 | +| time/ | | +| fps | 310 | +| iterations | 1691 | +| time_elapsed | 5575 | +| total_timesteps | 1731584 | +| train/ | | +| approx_kl | 2.0009522 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.373 | +| explained_variance | -2.25 | +| learning_rate | 0.0001 | +| loss | -0.0862 | +| n_updates | 77430 | +| policy_gradient_loss | -0.0656 | +| value_loss | 0.000459 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.02e+03 | +| ep_rew_mean | 0.196 | +| time/ | | +| fps | 310 | +| iterations | 1692 | +| time_elapsed | 5579 | +| total_timesteps | 1732608 | +| train/ | | +| approx_kl | 2.5476913 | +| clip_fraction | 0.478 | +| clip_range | 0.2 | +| entropy_loss | -0.314 | +| explained_variance | -0.56 | +| learning_rate | 0.0001 | +| loss | -0.0656 | +| n_updates | 77440 | +| policy_gradient_loss | -0.0539 | +| value_loss | 0.000652 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.03e+03 | +| ep_rew_mean | 0.196 | +| time/ | | +| fps | 310 | +| iterations | 1693 | +| time_elapsed | 5582 | +| total_timesteps | 1733632 | +| train/ | | +| approx_kl | 2.6188624 | +| clip_fraction | 0.473 | +| clip_range | 0.2 | +| entropy_loss | -0.358 | +| explained_variance | -3.72 | +| learning_rate | 0.0001 | +| loss | -0.0965 | +| n_updates | 77450 | +| policy_gradient_loss | -0.0653 | +| value_loss | 0.000508 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.03e+03 | +| ep_rew_mean | 0.196 | +| time/ | | +| fps | 310 | +| iterations | 1694 | +| time_elapsed | 5585 | +| total_timesteps | 1734656 | +| train/ | | +| approx_kl | 2.7746668 | +| clip_fraction | 0.473 | +| clip_range | 0.2 | +| entropy_loss | -0.341 | +| explained_variance | -3.46 | +| learning_rate | 0.0001 | +| loss | -0.1 | +| n_updates | 77460 | +| policy_gradient_loss | -0.0588 | +| value_loss | 0.000339 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.03e+03 | +| ep_rew_mean | 0.193 | +| time/ | | +| fps | 310 | +| iterations | 1695 | +| time_elapsed | 5588 | +| total_timesteps | 1735680 | +| train/ | | +| approx_kl | 2.4636712 | +| clip_fraction | 0.521 | +| clip_range | 0.2 | +| entropy_loss | -0.389 | +| explained_variance | -1.39 | +| learning_rate | 0.0001 | +| loss | -0.0881 | +| n_updates | 77470 | +| policy_gradient_loss | -0.0666 | +| value_loss | 0.000389 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.03e+03 | +| ep_rew_mean | 0.193 | +| time/ | | +| fps | 310 | +| iterations | 1696 | +| time_elapsed | 5592 | +| total_timesteps | 1736704 | +| train/ | | +| approx_kl | 1.9926075 | +| clip_fraction | 0.488 | +| clip_range | 0.2 | +| entropy_loss | -0.388 | +| explained_variance | -3.12 | +| learning_rate | 0.0001 | +| loss | -0.0906 | +| n_updates | 77480 | +| policy_gradient_loss | -0.0637 | +| value_loss | 0.000255 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.03e+03 | +| ep_rew_mean | 0.193 | +| time/ | | +| fps | 310 | +| iterations | 1697 | +| time_elapsed | 5595 | +| total_timesteps | 1737728 | +| train/ | | +| approx_kl | 2.1075346 | +| clip_fraction | 0.493 | +| clip_range | 0.2 | +| entropy_loss | -0.366 | +| explained_variance | -0.875 | +| learning_rate | 0.0001 | +| loss | -0.0874 | +| n_updates | 77490 | +| policy_gradient_loss | -0.0581 | +| value_loss | 0.000585 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.04e+03 | +| ep_rew_mean | 0.193 | +| time/ | | +| fps | 310 | +| iterations | 1698 | +| time_elapsed | 5598 | +| total_timesteps | 1738752 | +| train/ | | +| approx_kl | 2.7109504 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.326 | +| explained_variance | -1.79 | +| learning_rate | 0.0001 | +| loss | -0.0399 | +| n_updates | 77500 | +| policy_gradient_loss | -0.0548 | +| value_loss | 0.00041 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.04e+03 | +| ep_rew_mean | 0.193 | +| time/ | | +| fps | 310 | +| iterations | 1699 | +| time_elapsed | 5601 | +| total_timesteps | 1739776 | +| train/ | | +| approx_kl | 1.915671 | +| clip_fraction | 0.509 | +| clip_range | 0.2 | +| entropy_loss | -0.436 | +| explained_variance | -2.27 | +| learning_rate | 0.0001 | +| loss | -0.08 | +| n_updates | 77510 | +| policy_gradient_loss | -0.0502 | +| value_loss | 0.000121 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.05e+03 | +| ep_rew_mean | 0.192 | +| time/ | | +| fps | 310 | +| iterations | 1700 | +| time_elapsed | 5604 | +| total_timesteps | 1740800 | +| train/ | | +| approx_kl | 2.4152393 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.361 | +| explained_variance | -0.975 | +| learning_rate | 0.0001 | +| loss | -0.097 | +| n_updates | 77520 | +| policy_gradient_loss | -0.0573 | +| value_loss | 0.000409 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.05e+03 | +| ep_rew_mean | 0.192 | +| time/ | | +| fps | 310 | +| iterations | 1701 | +| time_elapsed | 5607 | +| total_timesteps | 1741824 | +| train/ | | +| approx_kl | 2.124495 | +| clip_fraction | 0.452 | +| clip_range | 0.2 | +| entropy_loss | -0.359 | +| explained_variance | -4.85 | +| learning_rate | 0.0001 | +| loss | -0.0704 | +| n_updates | 77530 | +| policy_gradient_loss | -0.0533 | +| value_loss | 0.000879 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.05e+03 | +| ep_rew_mean | 0.192 | +| time/ | | +| fps | 310 | +| iterations | 1702 | +| time_elapsed | 5610 | +| total_timesteps | 1742848 | +| train/ | | +| approx_kl | 2.151116 | +| clip_fraction | 0.444 | +| clip_range | 0.2 | +| entropy_loss | -0.324 | +| explained_variance | -3.52 | +| learning_rate | 0.0001 | +| loss | -0.0877 | +| n_updates | 77540 | +| policy_gradient_loss | -0.062 | +| value_loss | 0.000482 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.06e+03 | +| ep_rew_mean | 0.191 | +| time/ | | +| fps | 310 | +| iterations | 1703 | +| time_elapsed | 5614 | +| total_timesteps | 1743872 | +| train/ | | +| approx_kl | 2.2985072 | +| clip_fraction | 0.478 | +| clip_range | 0.2 | +| entropy_loss | -0.359 | +| explained_variance | -0.842 | +| learning_rate | 0.0001 | +| loss | -0.0815 | +| n_updates | 77550 | +| policy_gradient_loss | -0.0506 | +| value_loss | 0.0004 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.06e+03 | +| ep_rew_mean | 0.191 | +| time/ | | +| fps | 310 | +| iterations | 1704 | +| time_elapsed | 5617 | +| total_timesteps | 1744896 | +| train/ | | +| approx_kl | 3.5799122 | +| clip_fraction | 0.449 | +| clip_range | 0.2 | +| entropy_loss | -0.287 | +| explained_variance | -1.98 | +| learning_rate | 0.0001 | +| loss | -0.0904 | +| n_updates | 77560 | +| policy_gradient_loss | -0.0636 | +| value_loss | 0.000478 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.07e+03 | +| ep_rew_mean | 0.199 | +| time/ | | +| fps | 310 | +| iterations | 1705 | +| time_elapsed | 5620 | +| total_timesteps | 1745920 | +| train/ | | +| approx_kl | 4.5376244 | +| clip_fraction | 0.502 | +| clip_range | 0.2 | +| entropy_loss | -0.371 | +| explained_variance | -0.648 | +| learning_rate | 0.0001 | +| loss | -0.0614 | +| n_updates | 77570 | +| policy_gradient_loss | -0.0595 | +| value_loss | 0.000605 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.07e+03 | +| ep_rew_mean | 0.199 | +| time/ | | +| fps | 310 | +| iterations | 1706 | +| time_elapsed | 5624 | +| total_timesteps | 1746944 | +| train/ | | +| approx_kl | 2.3232136 | +| clip_fraction | 0.466 | +| clip_range | 0.2 | +| entropy_loss | -0.331 | +| explained_variance | -2.15 | +| learning_rate | 0.0001 | +| loss | -0.0705 | +| n_updates | 77580 | +| policy_gradient_loss | -0.0614 | +| value_loss | 0.000505 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.07e+03 | +| ep_rew_mean | 0.197 | +| time/ | | +| fps | 310 | +| iterations | 1707 | +| time_elapsed | 5627 | +| total_timesteps | 1747968 | +| train/ | | +| approx_kl | 2.2223122 | +| clip_fraction | 0.496 | +| clip_range | 0.2 | +| entropy_loss | -0.346 | +| explained_variance | -1.21 | +| learning_rate | 0.0001 | +| loss | -0.0494 | +| n_updates | 77590 | +| policy_gradient_loss | -0.0625 | +| value_loss | 0.000526 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.07e+03 | +| ep_rew_mean | 0.197 | +| time/ | | +| fps | 310 | +| iterations | 1708 | +| time_elapsed | 5631 | +| total_timesteps | 1748992 | +| train/ | | +| approx_kl | 2.589231 | +| clip_fraction | 0.514 | +| clip_range | 0.2 | +| entropy_loss | -0.378 | +| explained_variance | -2.19 | +| learning_rate | 0.0001 | +| loss | -0.0812 | +| n_updates | 77600 | +| policy_gradient_loss | -0.0618 | +| value_loss | 0.000351 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.07e+03 | +| ep_rew_mean | 0.197 | +| time/ | | +| fps | 310 | +| iterations | 1709 | +| time_elapsed | 5634 | +| total_timesteps | 1750016 | +| train/ | | +| approx_kl | 2.6950965 | +| clip_fraction | 0.551 | +| clip_range | 0.2 | +| entropy_loss | -0.458 | +| explained_variance | -1.05 | +| learning_rate | 0.0001 | +| loss | -0.0562 | +| n_updates | 77610 | +| policy_gradient_loss | -0.0495 | +| value_loss | 0.00034 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.09e+03 | +| ep_rew_mean | 0.193 | +| time/ | | +| fps | 310 | +| iterations | 1710 | +| time_elapsed | 5637 | +| total_timesteps | 1751040 | +| train/ | | +| approx_kl | 2.5249777 | +| clip_fraction | 0.511 | +| clip_range | 0.2 | +| entropy_loss | -0.336 | +| explained_variance | -2 | +| learning_rate | 0.0001 | +| loss | -0.0798 | +| n_updates | 77620 | +| policy_gradient_loss | -0.0662 | +| value_loss | 0.000213 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.09e+03 | +| ep_rew_mean | 0.193 | +| time/ | | +| fps | 310 | +| iterations | 1711 | +| time_elapsed | 5641 | +| total_timesteps | 1752064 | +| train/ | | +| approx_kl | 2.0912406 | +| clip_fraction | 0.484 | +| clip_range | 0.2 | +| entropy_loss | -0.357 | +| explained_variance | -0.808 | +| learning_rate | 0.0001 | +| loss | -0.0919 | +| n_updates | 77630 | +| policy_gradient_loss | -0.0579 | +| value_loss | 0.00058 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.09e+03 | +| ep_rew_mean | 0.196 | +| time/ | | +| fps | 310 | +| iterations | 1712 | +| time_elapsed | 5644 | +| total_timesteps | 1753088 | +| train/ | | +| approx_kl | 2.3182135 | +| clip_fraction | 0.439 | +| clip_range | 0.2 | +| entropy_loss | -0.338 | +| explained_variance | -0.668 | +| learning_rate | 0.0001 | +| loss | -0.069 | +| n_updates | 77640 | +| policy_gradient_loss | -0.0419 | +| value_loss | 0.000542 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.09e+03 | +| ep_rew_mean | 0.196 | +| time/ | | +| fps | 310 | +| iterations | 1713 | +| time_elapsed | 5648 | +| total_timesteps | 1754112 | +| train/ | | +| approx_kl | 1.7247052 | +| clip_fraction | 0.439 | +| clip_range | 0.2 | +| entropy_loss | -0.34 | +| explained_variance | -2.82 | +| learning_rate | 0.0001 | +| loss | -0.0615 | +| n_updates | 77650 | +| policy_gradient_loss | -0.0528 | +| value_loss | 0.000304 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.09e+03 | +| ep_rew_mean | 0.196 | +| time/ | | +| fps | 310 | +| iterations | 1714 | +| time_elapsed | 5651 | +| total_timesteps | 1755136 | +| train/ | | +| approx_kl | 2.0526295 | +| clip_fraction | 0.515 | +| clip_range | 0.2 | +| entropy_loss | -0.388 | +| explained_variance | -0.357 | +| learning_rate | 0.0001 | +| loss | -0.0992 | +| n_updates | 77660 | +| policy_gradient_loss | -0.058 | +| value_loss | 0.000696 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.1e+03 | +| ep_rew_mean | 0.196 | +| time/ | | +| fps | 310 | +| iterations | 1715 | +| time_elapsed | 5654 | +| total_timesteps | 1756160 | +| train/ | | +| approx_kl | 1.7759987 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.415 | +| explained_variance | -7.19 | +| learning_rate | 0.0001 | +| loss | -0.0892 | +| n_updates | 77670 | +| policy_gradient_loss | -0.0513 | +| value_loss | 0.000285 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.1e+03 | +| ep_rew_mean | 0.196 | +| time/ | | +| fps | 310 | +| iterations | 1716 | +| time_elapsed | 5657 | +| total_timesteps | 1757184 | +| train/ | | +| approx_kl | 1.955335 | +| clip_fraction | 0.503 | +| clip_range | 0.2 | +| entropy_loss | -0.4 | +| explained_variance | -1.58 | +| learning_rate | 0.0001 | +| loss | -0.0729 | +| n_updates | 77680 | +| policy_gradient_loss | -0.0621 | +| value_loss | 0.000502 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.1e+03 | +| ep_rew_mean | 0.194 | +| time/ | | +| fps | 310 | +| iterations | 1717 | +| time_elapsed | 5661 | +| total_timesteps | 1758208 | +| train/ | | +| approx_kl | 1.3439577 | +| clip_fraction | 0.455 | +| clip_range | 0.2 | +| entropy_loss | -0.432 | +| explained_variance | -0.418 | +| learning_rate | 0.0001 | +| loss | -0.0415 | +| n_updates | 77690 | +| policy_gradient_loss | -0.0527 | +| value_loss | 0.000375 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.1e+03 | +| ep_rew_mean | 0.194 | +| time/ | | +| fps | 310 | +| iterations | 1718 | +| time_elapsed | 5664 | +| total_timesteps | 1759232 | +| train/ | | +| approx_kl | 2.211803 | +| clip_fraction | 0.467 | +| clip_range | 0.2 | +| entropy_loss | -0.384 | +| explained_variance | -0.931 | +| learning_rate | 0.0001 | +| loss | -0.0898 | +| n_updates | 77700 | +| policy_gradient_loss | -0.0531 | +| value_loss | 0.00051 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.11e+03 | +| ep_rew_mean | 0.196 | +| time/ | | +| fps | 310 | +| iterations | 1719 | +| time_elapsed | 5667 | +| total_timesteps | 1760256 | +| train/ | | +| approx_kl | 2.874403 | +| clip_fraction | 0.484 | +| clip_range | 0.2 | +| entropy_loss | -0.373 | +| explained_variance | -0.707 | +| learning_rate | 0.0001 | +| loss | -0.0601 | +| n_updates | 77710 | +| policy_gradient_loss | -0.0524 | +| value_loss | 0.000563 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.11e+03 | +| ep_rew_mean | 0.196 | +| time/ | | +| fps | 310 | +| iterations | 1720 | +| time_elapsed | 5670 | +| total_timesteps | 1761280 | +| train/ | | +| approx_kl | 2.2951298 | +| clip_fraction | 0.464 | +| clip_range | 0.2 | +| entropy_loss | -0.312 | +| explained_variance | -0.555 | +| learning_rate | 0.0001 | +| loss | -0.0971 | +| n_updates | 77720 | +| policy_gradient_loss | -0.0598 | +| value_loss | 0.000286 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.12e+03 | +| ep_rew_mean | 0.196 | +| time/ | | +| fps | 310 | +| iterations | 1721 | +| time_elapsed | 5673 | +| total_timesteps | 1762304 | +| train/ | | +| approx_kl | 3.151942 | +| clip_fraction | 0.504 | +| clip_range | 0.2 | +| entropy_loss | -0.345 | +| explained_variance | -0.962 | +| learning_rate | 0.0001 | +| loss | -0.108 | +| n_updates | 77730 | +| policy_gradient_loss | -0.0536 | +| value_loss | 0.00046 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.12e+03 | +| ep_rew_mean | 0.196 | +| time/ | | +| fps | 310 | +| iterations | 1722 | +| time_elapsed | 5676 | +| total_timesteps | 1763328 | +| train/ | | +| approx_kl | 2.0219414 | +| clip_fraction | 0.505 | +| clip_range | 0.2 | +| entropy_loss | -0.426 | +| explained_variance | -1.15 | +| learning_rate | 0.0001 | +| loss | -0.0561 | +| n_updates | 77740 | +| policy_gradient_loss | -0.0631 | +| value_loss | 0.000562 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.12e+03 | +| ep_rew_mean | 0.196 | +| time/ | | +| fps | 310 | +| iterations | 1723 | +| time_elapsed | 5679 | +| total_timesteps | 1764352 | +| train/ | | +| approx_kl | 1.8426781 | +| clip_fraction | 0.492 | +| clip_range | 0.2 | +| entropy_loss | -0.413 | +| explained_variance | -4.07 | +| learning_rate | 0.0001 | +| loss | -0.0773 | +| n_updates | 77750 | +| policy_gradient_loss | -0.064 | +| value_loss | 0.000312 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.12e+03 | +| ep_rew_mean | 0.196 | +| time/ | | +| fps | 310 | +| iterations | 1724 | +| time_elapsed | 5683 | +| total_timesteps | 1765376 | +| train/ | | +| approx_kl | 2.5557342 | +| clip_fraction | 0.51 | +| clip_range | 0.2 | +| entropy_loss | -0.354 | +| explained_variance | -0.803 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 77760 | +| policy_gradient_loss | -0.0587 | +| value_loss | 0.000505 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.14e+03 | +| ep_rew_mean | 0.199 | +| time/ | | +| fps | 310 | +| iterations | 1725 | +| time_elapsed | 5686 | +| total_timesteps | 1766400 | +| train/ | | +| approx_kl | 1.8214458 | +| clip_fraction | 0.506 | +| clip_range | 0.2 | +| entropy_loss | -0.421 | +| explained_variance | -3.86 | +| learning_rate | 0.0001 | +| loss | -0.0837 | +| n_updates | 77770 | +| policy_gradient_loss | -0.0535 | +| value_loss | 0.000238 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.14e+03 | +| ep_rew_mean | 0.199 | +| time/ | | +| fps | 310 | +| iterations | 1726 | +| time_elapsed | 5690 | +| total_timesteps | 1767424 | +| train/ | | +| approx_kl | 2.360721 | +| clip_fraction | 0.469 | +| clip_range | 0.2 | +| entropy_loss | -0.347 | +| explained_variance | -1.96 | +| learning_rate | 0.0001 | +| loss | -0.095 | +| n_updates | 77780 | +| policy_gradient_loss | -0.0596 | +| value_loss | 0.000524 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.14e+03 | +| ep_rew_mean | 0.199 | +| time/ | | +| fps | 310 | +| iterations | 1727 | +| time_elapsed | 5693 | +| total_timesteps | 1768448 | +| train/ | | +| approx_kl | 1.4971008 | +| clip_fraction | 0.486 | +| clip_range | 0.2 | +| entropy_loss | -0.447 | +| explained_variance | -2.39 | +| learning_rate | 0.0001 | +| loss | -0.0634 | +| n_updates | 77790 | +| policy_gradient_loss | -0.0561 | +| value_loss | 0.000529 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.16e+03 | +| ep_rew_mean | 0.202 | +| time/ | | +| fps | 310 | +| iterations | 1728 | +| time_elapsed | 5696 | +| total_timesteps | 1769472 | +| train/ | | +| approx_kl | 2.2586746 | +| clip_fraction | 0.495 | +| clip_range | 0.2 | +| entropy_loss | -0.362 | +| explained_variance | -0.0334 | +| learning_rate | 0.0001 | +| loss | -0.0858 | +| n_updates | 77800 | +| policy_gradient_loss | -0.0491 | +| value_loss | 0.000129 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.16e+03 | +| ep_rew_mean | 0.202 | +| time/ | | +| fps | 310 | +| iterations | 1729 | +| time_elapsed | 5700 | +| total_timesteps | 1770496 | +| train/ | | +| approx_kl | 2.4676597 | +| clip_fraction | 0.504 | +| clip_range | 0.2 | +| entropy_loss | -0.373 | +| explained_variance | -0.292 | +| learning_rate | 0.0001 | +| loss | -0.0837 | +| n_updates | 77810 | +| policy_gradient_loss | -0.0598 | +| value_loss | 0.000594 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.16e+03 | +| ep_rew_mean | 0.202 | +| time/ | | +| fps | 310 | +| iterations | 1730 | +| time_elapsed | 5703 | +| total_timesteps | 1771520 | +| train/ | | +| approx_kl | 2.0246682 | +| clip_fraction | 0.528 | +| clip_range | 0.2 | +| entropy_loss | -0.48 | +| explained_variance | -1.33 | +| learning_rate | 0.0001 | +| loss | -0.069 | +| n_updates | 77820 | +| policy_gradient_loss | -0.0655 | +| value_loss | 0.000545 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.17e+03 | +| ep_rew_mean | 0.2 | +| time/ | | +| fps | 310 | +| iterations | 1731 | +| time_elapsed | 5707 | +| total_timesteps | 1772544 | +| train/ | | +| approx_kl | 1.2624596 | +| clip_fraction | 0.494 | +| clip_range | 0.2 | +| entropy_loss | -0.57 | +| explained_variance | -2.34 | +| learning_rate | 0.0001 | +| loss | -0.109 | +| n_updates | 77830 | +| policy_gradient_loss | -0.0634 | +| value_loss | 0.000129 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.17e+03 | +| ep_rew_mean | 0.203 | +| time/ | | +| fps | 310 | +| iterations | 1732 | +| time_elapsed | 5710 | +| total_timesteps | 1773568 | +| train/ | | +| approx_kl | 2.0540853 | +| clip_fraction | 0.525 | +| clip_range | 0.2 | +| entropy_loss | -0.46 | +| explained_variance | -0.702 | +| learning_rate | 0.0001 | +| loss | -0.0594 | +| n_updates | 77840 | +| policy_gradient_loss | -0.0598 | +| value_loss | 0.000424 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.17e+03 | +| ep_rew_mean | 0.203 | +| time/ | | +| fps | 310 | +| iterations | 1733 | +| time_elapsed | 5713 | +| total_timesteps | 1774592 | +| train/ | | +| approx_kl | 2.1007774 | +| clip_fraction | 0.516 | +| clip_range | 0.2 | +| entropy_loss | -0.438 | +| explained_variance | -0.811 | +| learning_rate | 0.0001 | +| loss | -0.117 | +| n_updates | 77850 | +| policy_gradient_loss | -0.0599 | +| value_loss | 0.000405 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.17e+03 | +| ep_rew_mean | 0.203 | +| time/ | | +| fps | 310 | +| iterations | 1734 | +| time_elapsed | 5716 | +| total_timesteps | 1775616 | +| train/ | | +| approx_kl | 2.4156735 | +| clip_fraction | 0.526 | +| clip_range | 0.2 | +| entropy_loss | -0.422 | +| explained_variance | -2.65 | +| learning_rate | 0.0001 | +| loss | -0.0969 | +| n_updates | 77860 | +| policy_gradient_loss | -0.063 | +| value_loss | 0.000604 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.18e+03 | +| ep_rew_mean | 0.205 | +| time/ | | +| fps | 310 | +| iterations | 1735 | +| time_elapsed | 5719 | +| total_timesteps | 1776640 | +| train/ | | +| approx_kl | 2.527193 | +| clip_fraction | 0.496 | +| clip_range | 0.2 | +| entropy_loss | -0.398 | +| explained_variance | -1.2 | +| learning_rate | 0.0001 | +| loss | -0.0802 | +| n_updates | 77870 | +| policy_gradient_loss | -0.054 | +| value_loss | 0.000844 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.18e+03 | +| ep_rew_mean | 0.202 | +| time/ | | +| fps | 310 | +| iterations | 1736 | +| time_elapsed | 5722 | +| total_timesteps | 1777664 | +| train/ | | +| approx_kl | 2.121194 | +| clip_fraction | 0.504 | +| clip_range | 0.2 | +| entropy_loss | -0.401 | +| explained_variance | -1.71 | +| learning_rate | 0.0001 | +| loss | -0.11 | +| n_updates | 77880 | +| policy_gradient_loss | -0.065 | +| value_loss | 0.000602 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.18e+03 | +| ep_rew_mean | 0.202 | +| time/ | | +| fps | 310 | +| iterations | 1737 | +| time_elapsed | 5725 | +| total_timesteps | 1778688 | +| train/ | | +| approx_kl | 2.098957 | +| clip_fraction | 0.477 | +| clip_range | 0.2 | +| entropy_loss | -0.379 | +| explained_variance | -3.53 | +| learning_rate | 0.0001 | +| loss | -0.0908 | +| n_updates | 77890 | +| policy_gradient_loss | -0.0604 | +| value_loss | 0.000259 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.18e+03 | +| ep_rew_mean | 0.202 | +| time/ | | +| fps | 310 | +| iterations | 1738 | +| time_elapsed | 5728 | +| total_timesteps | 1779712 | +| train/ | | +| approx_kl | 2.295507 | +| clip_fraction | 0.468 | +| clip_range | 0.2 | +| entropy_loss | -0.334 | +| explained_variance | -2.87 | +| learning_rate | 0.0001 | +| loss | -0.0764 | +| n_updates | 77900 | +| policy_gradient_loss | -0.06 | +| value_loss | 0.000293 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.18e+03 | +| ep_rew_mean | 0.202 | +| time/ | | +| fps | 310 | +| iterations | 1739 | +| time_elapsed | 5732 | +| total_timesteps | 1780736 | +| train/ | | +| approx_kl | 2.481998 | +| clip_fraction | 0.46 | +| clip_range | 0.2 | +| entropy_loss | -0.319 | +| explained_variance | -1.95 | +| learning_rate | 0.0001 | +| loss | -0.0776 | +| n_updates | 77910 | +| policy_gradient_loss | -0.0634 | +| value_loss | 0.00052 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.18e+03 | +| ep_rew_mean | 0.202 | +| time/ | | +| fps | 310 | +| iterations | 1740 | +| time_elapsed | 5735 | +| total_timesteps | 1781760 | +| train/ | | +| approx_kl | 2.2460995 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.334 | +| explained_variance | -3.93 | +| learning_rate | 0.0001 | +| loss | -0.0804 | +| n_updates | 77920 | +| policy_gradient_loss | -0.0675 | +| value_loss | 0.00048 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.18e+03 | +| ep_rew_mean | 0.202 | +| time/ | | +| fps | 310 | +| iterations | 1741 | +| time_elapsed | 5738 | +| total_timesteps | 1782784 | +| train/ | | +| approx_kl | 2.6224103 | +| clip_fraction | 0.493 | +| clip_range | 0.2 | +| entropy_loss | -0.43 | +| explained_variance | -4.03 | +| learning_rate | 0.0001 | +| loss | -0.079 | +| n_updates | 77930 | +| policy_gradient_loss | -0.0574 | +| value_loss | 0.000218 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.18e+03 | +| ep_rew_mean | 0.202 | +| time/ | | +| fps | 310 | +| iterations | 1742 | +| time_elapsed | 5741 | +| total_timesteps | 1783808 | +| train/ | | +| approx_kl | 1.3828603 | +| clip_fraction | 0.476 | +| clip_range | 0.2 | +| entropy_loss | -0.614 | +| explained_variance | -0.452 | +| learning_rate | 0.0001 | +| loss | -0.0557 | +| n_updates | 77940 | +| policy_gradient_loss | -0.0469 | +| value_loss | 0.000257 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.18e+03 | +| ep_rew_mean | 0.202 | +| time/ | | +| fps | 310 | +| iterations | 1743 | +| time_elapsed | 5745 | +| total_timesteps | 1784832 | +| train/ | | +| approx_kl | 2.4930754 | +| clip_fraction | 0.512 | +| clip_range | 0.2 | +| entropy_loss | -0.409 | +| explained_variance | -1.22 | +| learning_rate | 0.0001 | +| loss | -0.109 | +| n_updates | 77950 | +| policy_gradient_loss | -0.0602 | +| value_loss | 0.000339 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.24e+03 | +| ep_rew_mean | 0.196 | +| time/ | | +| fps | 310 | +| iterations | 1744 | +| time_elapsed | 5748 | +| total_timesteps | 1785856 | +| train/ | | +| approx_kl | 2.3495364 | +| clip_fraction | 0.476 | +| clip_range | 0.2 | +| entropy_loss | -0.34 | +| explained_variance | -1.87 | +| learning_rate | 0.0001 | +| loss | -0.0873 | +| n_updates | 77960 | +| policy_gradient_loss | -0.0615 | +| value_loss | 0.000552 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.25e+03 | +| ep_rew_mean | 0.2 | +| time/ | | +| fps | 310 | +| iterations | 1745 | +| time_elapsed | 5752 | +| total_timesteps | 1786880 | +| train/ | | +| approx_kl | 2.2192564 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.359 | +| explained_variance | -2.06 | +| learning_rate | 0.0001 | +| loss | -0.0703 | +| n_updates | 77970 | +| policy_gradient_loss | -0.067 | +| value_loss | 0.000475 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.25e+03 | +| ep_rew_mean | 0.2 | +| time/ | | +| fps | 310 | +| iterations | 1746 | +| time_elapsed | 5755 | +| total_timesteps | 1787904 | +| train/ | | +| approx_kl | 3.5913155 | +| clip_fraction | 0.51 | +| clip_range | 0.2 | +| entropy_loss | -0.377 | +| explained_variance | -1.69 | +| learning_rate | 0.0001 | +| loss | -0.0904 | +| n_updates | 77980 | +| policy_gradient_loss | -0.0586 | +| value_loss | 0.000507 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.25e+03 | +| ep_rew_mean | 0.2 | +| time/ | | +| fps | 310 | +| iterations | 1747 | +| time_elapsed | 5758 | +| total_timesteps | 1788928 | +| train/ | | +| approx_kl | 2.181838 | +| clip_fraction | 0.5 | +| clip_range | 0.2 | +| entropy_loss | -0.468 | +| explained_variance | -0.743 | +| learning_rate | 0.0001 | +| loss | -0.0661 | +| n_updates | 77990 | +| policy_gradient_loss | -0.049 | +| value_loss | 0.000443 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.27e+03 | +| ep_rew_mean | 0.203 | +| time/ | | +| fps | 310 | +| iterations | 1748 | +| time_elapsed | 5762 | +| total_timesteps | 1789952 | +| train/ | | +| approx_kl | 2.2532642 | +| clip_fraction | 0.508 | +| clip_range | 0.2 | +| entropy_loss | -0.388 | +| explained_variance | -0.891 | +| learning_rate | 0.0001 | +| loss | -0.08 | +| n_updates | 78000 | +| policy_gradient_loss | -0.0655 | +| value_loss | 0.000437 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.27e+03 | +| ep_rew_mean | 0.203 | +| time/ | | +| fps | 310 | +| iterations | 1749 | +| time_elapsed | 5765 | +| total_timesteps | 1790976 | +| train/ | | +| approx_kl | 2.5218675 | +| clip_fraction | 0.515 | +| clip_range | 0.2 | +| entropy_loss | -0.367 | +| explained_variance | -1.27 | +| learning_rate | 0.0001 | +| loss | -0.11 | +| n_updates | 78010 | +| policy_gradient_loss | -0.068 | +| value_loss | 0.00067 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.27e+03 | +| ep_rew_mean | 0.203 | +| time/ | | +| fps | 310 | +| iterations | 1750 | +| time_elapsed | 5769 | +| total_timesteps | 1792000 | +| train/ | | +| approx_kl | 2.3542013 | +| clip_fraction | 0.5 | +| clip_range | 0.2 | +| entropy_loss | -0.382 | +| explained_variance | -2.68 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 78020 | +| policy_gradient_loss | -0.0506 | +| value_loss | 0.000207 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.28e+03 | +| ep_rew_mean | 0.198 | +| time/ | | +| fps | 310 | +| iterations | 1751 | +| time_elapsed | 5772 | +| total_timesteps | 1793024 | +| train/ | | +| approx_kl | 3.1475625 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.364 | +| explained_variance | -2.01 | +| learning_rate | 0.0001 | +| loss | -0.083 | +| n_updates | 78030 | +| policy_gradient_loss | -0.0597 | +| value_loss | 0.000215 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.28e+03 | +| ep_rew_mean | 0.198 | +| time/ | | +| fps | 310 | +| iterations | 1752 | +| time_elapsed | 5775 | +| total_timesteps | 1794048 | +| train/ | | +| approx_kl | 2.0221481 | +| clip_fraction | 0.491 | +| clip_range | 0.2 | +| entropy_loss | -0.364 | +| explained_variance | -2.12 | +| learning_rate | 0.0001 | +| loss | -0.109 | +| n_updates | 78040 | +| policy_gradient_loss | -0.0643 | +| value_loss | 0.000321 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.29e+03 | +| ep_rew_mean | 0.197 | +| time/ | | +| fps | 310 | +| iterations | 1753 | +| time_elapsed | 5778 | +| total_timesteps | 1795072 | +| train/ | | +| approx_kl | 2.6053698 | +| clip_fraction | 0.503 | +| clip_range | 0.2 | +| entropy_loss | -0.379 | +| explained_variance | -2.47 | +| learning_rate | 0.0001 | +| loss | -0.0895 | +| n_updates | 78050 | +| policy_gradient_loss | -0.0492 | +| value_loss | 0.000365 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.29e+03 | +| ep_rew_mean | 0.197 | +| time/ | | +| fps | 310 | +| iterations | 1754 | +| time_elapsed | 5781 | +| total_timesteps | 1796096 | +| train/ | | +| approx_kl | 1.770901 | +| clip_fraction | 0.488 | +| clip_range | 0.2 | +| entropy_loss | -0.383 | +| explained_variance | -1.09 | +| learning_rate | 0.0001 | +| loss | -0.1 | +| n_updates | 78060 | +| policy_gradient_loss | -0.0627 | +| value_loss | 0.000738 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.3e+03 | +| ep_rew_mean | 0.197 | +| time/ | | +| fps | 310 | +| iterations | 1755 | +| time_elapsed | 5785 | +| total_timesteps | 1797120 | +| train/ | | +| approx_kl | 3.6968827 | +| clip_fraction | 0.485 | +| clip_range | 0.2 | +| entropy_loss | -0.397 | +| explained_variance | -1.04 | +| learning_rate | 0.0001 | +| loss | -0.0732 | +| n_updates | 78070 | +| policy_gradient_loss | -0.0636 | +| value_loss | 0.000604 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.3e+03 | +| ep_rew_mean | 0.197 | +| time/ | | +| fps | 310 | +| iterations | 1756 | +| time_elapsed | 5788 | +| total_timesteps | 1798144 | +| train/ | | +| approx_kl | 1.9079434 | +| clip_fraction | 0.517 | +| clip_range | 0.2 | +| entropy_loss | -0.419 | +| explained_variance | -0.649 | +| learning_rate | 0.0001 | +| loss | -0.092 | +| n_updates | 78080 | +| policy_gradient_loss | -0.0586 | +| value_loss | 0.000586 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.3e+03 | +| ep_rew_mean | 0.197 | +| time/ | | +| fps | 310 | +| iterations | 1757 | +| time_elapsed | 5791 | +| total_timesteps | 1799168 | +| train/ | | +| approx_kl | 5.0167866 | +| clip_fraction | 0.492 | +| clip_range | 0.2 | +| entropy_loss | -0.341 | +| explained_variance | -3.15 | +| learning_rate | 0.0001 | +| loss | -0.0649 | +| n_updates | 78090 | +| policy_gradient_loss | -0.0592 | +| value_loss | 0.000425 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.31e+03 | +| ep_rew_mean | 0.196 | +| time/ | | +| fps | 310 | +| iterations | 1758 | +| time_elapsed | 5794 | +| total_timesteps | 1800192 | +| train/ | | +| approx_kl | 2.9726887 | +| clip_fraction | 0.511 | +| clip_range | 0.2 | +| entropy_loss | -0.387 | +| explained_variance | -0.343 | +| learning_rate | 0.0001 | +| loss | -0.0826 | +| n_updates | 78100 | +| policy_gradient_loss | -0.0643 | +| value_loss | 0.000564 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.31e+03 | +| ep_rew_mean | 0.196 | +| time/ | | +| fps | 310 | +| iterations | 1759 | +| time_elapsed | 5797 | +| total_timesteps | 1801216 | +| train/ | | +| approx_kl | 2.138334 | +| clip_fraction | 0.473 | +| clip_range | 0.2 | +| entropy_loss | -0.33 | +| explained_variance | -4.81 | +| learning_rate | 0.0001 | +| loss | -0.0927 | +| n_updates | 78110 | +| policy_gradient_loss | -0.0528 | +| value_loss | 0.000518 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.32e+03 | +| ep_rew_mean | 0.195 | +| time/ | | +| fps | 310 | +| iterations | 1760 | +| time_elapsed | 5801 | +| total_timesteps | 1802240 | +| train/ | | +| approx_kl | 2.604521 | +| clip_fraction | 0.498 | +| clip_range | 0.2 | +| entropy_loss | -0.373 | +| explained_variance | -1.29 | +| learning_rate | 0.0001 | +| loss | -0.0865 | +| n_updates | 78120 | +| policy_gradient_loss | -0.0637 | +| value_loss | 0.00042 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.32e+03 | +| ep_rew_mean | 0.195 | +| time/ | | +| fps | 310 | +| iterations | 1761 | +| time_elapsed | 5804 | +| total_timesteps | 1803264 | +| train/ | | +| approx_kl | 1.4797789 | +| clip_fraction | 0.507 | +| clip_range | 0.2 | +| entropy_loss | -0.479 | +| explained_variance | -1.23 | +| learning_rate | 0.0001 | +| loss | -0.0944 | +| n_updates | 78130 | +| policy_gradient_loss | -0.0539 | +| value_loss | 0.000406 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.33e+03 | +| ep_rew_mean | 0.197 | +| time/ | | +| fps | 310 | +| iterations | 1762 | +| time_elapsed | 5807 | +| total_timesteps | 1804288 | +| train/ | | +| approx_kl | 2.5454183 | +| clip_fraction | 0.465 | +| clip_range | 0.2 | +| entropy_loss | -0.367 | +| explained_variance | -1.97 | +| learning_rate | 0.0001 | +| loss | -0.076 | +| n_updates | 78140 | +| policy_gradient_loss | -0.0658 | +| value_loss | 0.000297 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.33e+03 | +| ep_rew_mean | 0.197 | +| time/ | | +| fps | 310 | +| iterations | 1763 | +| time_elapsed | 5811 | +| total_timesteps | 1805312 | +| train/ | | +| approx_kl | 1.9240328 | +| clip_fraction | 0.498 | +| clip_range | 0.2 | +| entropy_loss | -0.459 | +| explained_variance | -8.12 | +| learning_rate | 0.0001 | +| loss | -0.0891 | +| n_updates | 78150 | +| policy_gradient_loss | -0.0616 | +| value_loss | 0.00033 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.33e+03 | +| ep_rew_mean | 0.197 | +| time/ | | +| fps | 310 | +| iterations | 1764 | +| time_elapsed | 5814 | +| total_timesteps | 1806336 | +| train/ | | +| approx_kl | 2.0847857 | +| clip_fraction | 0.49 | +| clip_range | 0.2 | +| entropy_loss | -0.429 | +| explained_variance | -5.79 | +| learning_rate | 0.0001 | +| loss | -0.0974 | +| n_updates | 78160 | +| policy_gradient_loss | -0.0593 | +| value_loss | 0.000403 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.35e+03 | +| ep_rew_mean | 0.196 | +| time/ | | +| fps | 310 | +| iterations | 1765 | +| time_elapsed | 5817 | +| total_timesteps | 1807360 | +| train/ | | +| approx_kl | 2.5448165 | +| clip_fraction | 0.465 | +| clip_range | 0.2 | +| entropy_loss | -0.325 | +| explained_variance | -0.982 | +| learning_rate | 0.0001 | +| loss | -0.0738 | +| n_updates | 78170 | +| policy_gradient_loss | -0.0416 | +| value_loss | 0.000238 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.35e+03 | +| ep_rew_mean | 0.196 | +| time/ | | +| fps | 310 | +| iterations | 1766 | +| time_elapsed | 5821 | +| total_timesteps | 1808384 | +| train/ | | +| approx_kl | 1.4815812 | +| clip_fraction | 0.476 | +| clip_range | 0.2 | +| entropy_loss | -0.419 | +| explained_variance | -0.706 | +| learning_rate | 0.0001 | +| loss | -0.0698 | +| n_updates | 78180 | +| policy_gradient_loss | -0.0617 | +| value_loss | 0.00038 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.35e+03 | +| ep_rew_mean | 0.196 | +| time/ | | +| fps | 310 | +| iterations | 1767 | +| time_elapsed | 5824 | +| total_timesteps | 1809408 | +| train/ | | +| approx_kl | 2.7916431 | +| clip_fraction | 0.509 | +| clip_range | 0.2 | +| entropy_loss | -0.376 | +| explained_variance | -1.7 | +| learning_rate | 0.0001 | +| loss | -0.0976 | +| n_updates | 78190 | +| policy_gradient_loss | -0.0592 | +| value_loss | 0.000681 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.36e+03 | +| ep_rew_mean | 0.195 | +| time/ | | +| fps | 310 | +| iterations | 1768 | +| time_elapsed | 5828 | +| total_timesteps | 1810432 | +| train/ | | +| approx_kl | 2.773363 | +| clip_fraction | 0.509 | +| clip_range | 0.2 | +| entropy_loss | -0.397 | +| explained_variance | -3 | +| learning_rate | 0.0001 | +| loss | -0.0894 | +| n_updates | 78200 | +| policy_gradient_loss | -0.0655 | +| value_loss | 0.000371 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.36e+03 | +| ep_rew_mean | 0.195 | +| time/ | | +| fps | 310 | +| iterations | 1769 | +| time_elapsed | 5831 | +| total_timesteps | 1811456 | +| train/ | | +| approx_kl | 1.7722163 | +| clip_fraction | 0.516 | +| clip_range | 0.2 | +| entropy_loss | -0.472 | +| explained_variance | -1.68 | +| learning_rate | 0.0001 | +| loss | -0.107 | +| n_updates | 78210 | +| policy_gradient_loss | -0.0643 | +| value_loss | 0.000194 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.35e+03 | +| ep_rew_mean | 0.19 | +| time/ | | +| fps | 310 | +| iterations | 1770 | +| time_elapsed | 5834 | +| total_timesteps | 1812480 | +| train/ | | +| approx_kl | 2.1494663 | +| clip_fraction | 0.474 | +| clip_range | 0.2 | +| entropy_loss | -0.354 | +| explained_variance | -4.34 | +| learning_rate | 0.0001 | +| loss | -0.0695 | +| n_updates | 78220 | +| policy_gradient_loss | -0.0598 | +| value_loss | 0.000262 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.35e+03 | +| ep_rew_mean | 0.19 | +| time/ | | +| fps | 310 | +| iterations | 1771 | +| time_elapsed | 5837 | +| total_timesteps | 1813504 | +| train/ | | +| approx_kl | 3.6781163 | +| clip_fraction | 0.469 | +| clip_range | 0.2 | +| entropy_loss | -0.323 | +| explained_variance | -0.623 | +| learning_rate | 0.0001 | +| loss | -0.0924 | +| n_updates | 78230 | +| policy_gradient_loss | -0.0582 | +| value_loss | 0.000414 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.36e+03 | +| ep_rew_mean | 0.198 | +| time/ | | +| fps | 310 | +| iterations | 1772 | +| time_elapsed | 5841 | +| total_timesteps | 1814528 | +| train/ | | +| approx_kl | 9.066462 | +| clip_fraction | 0.511 | +| clip_range | 0.2 | +| entropy_loss | -0.427 | +| explained_variance | -1.2 | +| learning_rate | 0.0001 | +| loss | -0.064 | +| n_updates | 78240 | +| policy_gradient_loss | -0.0664 | +| value_loss | 0.000682 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.36e+03 | +| ep_rew_mean | 0.198 | +| time/ | | +| fps | 310 | +| iterations | 1773 | +| time_elapsed | 5844 | +| total_timesteps | 1815552 | +| train/ | | +| approx_kl | 2.6746445 | +| clip_fraction | 0.459 | +| clip_range | 0.2 | +| entropy_loss | -0.318 | +| explained_variance | -1.11 | +| learning_rate | 0.0001 | +| loss | -0.0828 | +| n_updates | 78250 | +| policy_gradient_loss | -0.0425 | +| value_loss | 0.000513 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.36e+03 | +| ep_rew_mean | 0.198 | +| time/ | | +| fps | 310 | +| iterations | 1774 | +| time_elapsed | 5847 | +| total_timesteps | 1816576 | +| train/ | | +| approx_kl | 2.5634668 | +| clip_fraction | 0.519 | +| clip_range | 0.2 | +| entropy_loss | -0.373 | +| explained_variance | -1.99 | +| learning_rate | 0.0001 | +| loss | -0.0988 | +| n_updates | 78260 | +| policy_gradient_loss | -0.0635 | +| value_loss | 0.000455 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.38e+03 | +| ep_rew_mean | 0.197 | +| time/ | | +| fps | 310 | +| iterations | 1775 | +| time_elapsed | 5850 | +| total_timesteps | 1817600 | +| train/ | | +| approx_kl | 2.366011 | +| clip_fraction | 0.489 | +| clip_range | 0.2 | +| entropy_loss | -0.377 | +| explained_variance | -2.19 | +| learning_rate | 0.0001 | +| loss | -0.0917 | +| n_updates | 78270 | +| policy_gradient_loss | -0.0682 | +| value_loss | 0.000315 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.38e+03 | +| ep_rew_mean | 0.197 | +| time/ | | +| fps | 310 | +| iterations | 1776 | +| time_elapsed | 5853 | +| total_timesteps | 1818624 | +| train/ | | +| approx_kl | 2.5139482 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.387 | +| explained_variance | -1.24 | +| learning_rate | 0.0001 | +| loss | -0.094 | +| n_updates | 78280 | +| policy_gradient_loss | -0.0276 | +| value_loss | 0.000439 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.38e+03 | +| ep_rew_mean | 0.197 | +| time/ | | +| fps | 310 | +| iterations | 1777 | +| time_elapsed | 5856 | +| total_timesteps | 1819648 | +| train/ | | +| approx_kl | 1.8221245 | +| clip_fraction | 0.511 | +| clip_range | 0.2 | +| entropy_loss | -0.447 | +| explained_variance | -0.315 | +| learning_rate | 0.0001 | +| loss | -0.0721 | +| n_updates | 78290 | +| policy_gradient_loss | -0.0582 | +| value_loss | 0.000533 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.38e+03 | +| ep_rew_mean | 0.19 | +| time/ | | +| fps | 310 | +| iterations | 1778 | +| time_elapsed | 5859 | +| total_timesteps | 1820672 | +| train/ | | +| approx_kl | 2.449989 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.379 | +| explained_variance | -4.56 | +| learning_rate | 0.0001 | +| loss | -0.0708 | +| n_updates | 78300 | +| policy_gradient_loss | -0.0596 | +| value_loss | 0.000555 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.38e+03 | +| ep_rew_mean | 0.19 | +| time/ | | +| fps | 310 | +| iterations | 1779 | +| time_elapsed | 5863 | +| total_timesteps | 1821696 | +| train/ | | +| approx_kl | 2.6751475 | +| clip_fraction | 0.47 | +| clip_range | 0.2 | +| entropy_loss | -0.335 | +| explained_variance | -1.07 | +| learning_rate | 0.0001 | +| loss | -0.0909 | +| n_updates | 78310 | +| policy_gradient_loss | -0.0517 | +| value_loss | 0.000432 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.38e+03 | +| ep_rew_mean | 0.19 | +| time/ | | +| fps | 310 | +| iterations | 1780 | +| time_elapsed | 5866 | +| total_timesteps | 1822720 | +| train/ | | +| approx_kl | 4.26021 | +| clip_fraction | 0.521 | +| clip_range | 0.2 | +| entropy_loss | -0.41 | +| explained_variance | -4.71 | +| learning_rate | 0.0001 | +| loss | -0.0827 | +| n_updates | 78320 | +| policy_gradient_loss | -0.0676 | +| value_loss | 0.000387 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.38e+03 | +| ep_rew_mean | 0.19 | +| time/ | | +| fps | 310 | +| iterations | 1781 | +| time_elapsed | 5870 | +| total_timesteps | 1823744 | +| train/ | | +| approx_kl | 2.3084478 | +| clip_fraction | 0.522 | +| clip_range | 0.2 | +| entropy_loss | -0.419 | +| explained_variance | -0.815 | +| learning_rate | 0.0001 | +| loss | -0.0959 | +| n_updates | 78330 | +| policy_gradient_loss | -0.0577 | +| value_loss | 0.000514 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.38e+03 | +| ep_rew_mean | 0.19 | +| time/ | | +| fps | 310 | +| iterations | 1782 | +| time_elapsed | 5873 | +| total_timesteps | 1824768 | +| train/ | | +| approx_kl | 1.5993955 | +| clip_fraction | 0.52 | +| clip_range | 0.2 | +| entropy_loss | -0.497 | +| explained_variance | -2.11 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 78340 | +| policy_gradient_loss | -0.062 | +| value_loss | 0.000239 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.38e+03 | +| ep_rew_mean | 0.19 | +| time/ | | +| fps | 310 | +| iterations | 1783 | +| time_elapsed | 5877 | +| total_timesteps | 1825792 | +| train/ | | +| approx_kl | 1.9238186 | +| clip_fraction | 0.525 | +| clip_range | 0.2 | +| entropy_loss | -0.377 | +| explained_variance | -9.61 | +| learning_rate | 0.0001 | +| loss | -0.0563 | +| n_updates | 78350 | +| policy_gradient_loss | -0.038 | +| value_loss | 0.000114 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.43e+03 | +| ep_rew_mean | 0.189 | +| time/ | | +| fps | 310 | +| iterations | 1784 | +| time_elapsed | 5880 | +| total_timesteps | 1826816 | +| train/ | | +| approx_kl | 1.5102005 | +| clip_fraction | 0.43 | +| clip_range | 0.2 | +| entropy_loss | -0.593 | +| explained_variance | -0.141 | +| learning_rate | 0.0001 | +| loss | -0.0632 | +| n_updates | 78360 | +| policy_gradient_loss | -0.0477 | +| value_loss | 0.00078 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.43e+03 | +| ep_rew_mean | 0.189 | +| time/ | | +| fps | 310 | +| iterations | 1785 | +| time_elapsed | 5884 | +| total_timesteps | 1827840 | +| train/ | | +| approx_kl | 1.3858452 | +| clip_fraction | 0.515 | +| clip_range | 0.2 | +| entropy_loss | -0.525 | +| explained_variance | -1.89 | +| learning_rate | 0.0001 | +| loss | -0.0996 | +| n_updates | 78370 | +| policy_gradient_loss | -0.0666 | +| value_loss | 0.000382 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.43e+03 | +| ep_rew_mean | 0.189 | +| time/ | | +| fps | 310 | +| iterations | 1786 | +| time_elapsed | 5887 | +| total_timesteps | 1828864 | +| train/ | | +| approx_kl | 5.061593 | +| clip_fraction | 0.517 | +| clip_range | 0.2 | +| entropy_loss | -0.372 | +| explained_variance | -2.52 | +| learning_rate | 0.0001 | +| loss | -0.0682 | +| n_updates | 78380 | +| policy_gradient_loss | -0.0563 | +| value_loss | 0.000332 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.43e+03 | +| ep_rew_mean | 0.189 | +| time/ | | +| fps | 310 | +| iterations | 1787 | +| time_elapsed | 5890 | +| total_timesteps | 1829888 | +| train/ | | +| approx_kl | 2.5989962 | +| clip_fraction | 0.495 | +| clip_range | 0.2 | +| entropy_loss | -0.394 | +| explained_variance | -1.01 | +| learning_rate | 0.0001 | +| loss | -0.0814 | +| n_updates | 78390 | +| policy_gradient_loss | -0.0564 | +| value_loss | 0.000428 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.43e+03 | +| ep_rew_mean | 0.189 | +| time/ | | +| fps | 310 | +| iterations | 1788 | +| time_elapsed | 5894 | +| total_timesteps | 1830912 | +| train/ | | +| approx_kl | 2.1282094 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.378 | +| explained_variance | -0.854 | +| learning_rate | 0.0001 | +| loss | -0.0737 | +| n_updates | 78400 | +| policy_gradient_loss | -0.0635 | +| value_loss | 0.000577 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.43e+03 | +| ep_rew_mean | 0.187 | +| time/ | | +| fps | 310 | +| iterations | 1789 | +| time_elapsed | 5897 | +| total_timesteps | 1831936 | +| train/ | | +| approx_kl | 1.5009776 | +| clip_fraction | 0.524 | +| clip_range | 0.2 | +| entropy_loss | -0.483 | +| explained_variance | -1.15 | +| learning_rate | 0.0001 | +| loss | -0.0726 | +| n_updates | 78410 | +| policy_gradient_loss | -0.0644 | +| value_loss | 0.000562 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.43e+03 | +| ep_rew_mean | 0.187 | +| time/ | | +| fps | 310 | +| iterations | 1790 | +| time_elapsed | 5900 | +| total_timesteps | 1832960 | +| train/ | | +| approx_kl | 2.5679822 | +| clip_fraction | 0.491 | +| clip_range | 0.2 | +| entropy_loss | -0.391 | +| explained_variance | -0.894 | +| learning_rate | 0.0001 | +| loss | -0.0636 | +| n_updates | 78420 | +| policy_gradient_loss | -0.0659 | +| value_loss | 0.000604 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.44e+03 | +| ep_rew_mean | 0.191 | +| time/ | | +| fps | 310 | +| iterations | 1791 | +| time_elapsed | 5903 | +| total_timesteps | 1833984 | +| train/ | | +| approx_kl | 2.138018 | +| clip_fraction | 0.498 | +| clip_range | 0.2 | +| entropy_loss | -0.428 | +| explained_variance | -0.637 | +| learning_rate | 0.0001 | +| loss | -0.0687 | +| n_updates | 78430 | +| policy_gradient_loss | -0.0654 | +| value_loss | 0.000394 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.44e+03 | +| ep_rew_mean | 0.191 | +| time/ | | +| fps | 310 | +| iterations | 1792 | +| time_elapsed | 5906 | +| total_timesteps | 1835008 | +| train/ | | +| approx_kl | 1.9660714 | +| clip_fraction | 0.484 | +| clip_range | 0.2 | +| entropy_loss | -0.419 | +| explained_variance | -0.945 | +| learning_rate | 0.0001 | +| loss | -0.0858 | +| n_updates | 78440 | +| policy_gradient_loss | -0.0648 | +| value_loss | 0.000328 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.45e+03 | +| ep_rew_mean | 0.192 | +| time/ | | +| fps | 310 | +| iterations | 1793 | +| time_elapsed | 5910 | +| total_timesteps | 1836032 | +| train/ | | +| approx_kl | 2.5459685 | +| clip_fraction | 0.51 | +| clip_range | 0.2 | +| entropy_loss | -0.38 | +| explained_variance | -1.78 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 78450 | +| policy_gradient_loss | -0.066 | +| value_loss | 0.000584 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.45e+03 | +| ep_rew_mean | 0.192 | +| time/ | | +| fps | 310 | +| iterations | 1794 | +| time_elapsed | 5913 | +| total_timesteps | 1837056 | +| train/ | | +| approx_kl | 2.0869675 | +| clip_fraction | 0.44 | +| clip_range | 0.2 | +| entropy_loss | -0.339 | +| explained_variance | -1.27 | +| learning_rate | 0.0001 | +| loss | -0.0963 | +| n_updates | 78460 | +| policy_gradient_loss | -0.0637 | +| value_loss | 0.00058 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.45e+03 | +| ep_rew_mean | 0.194 | +| time/ | | +| fps | 310 | +| iterations | 1795 | +| time_elapsed | 5916 | +| total_timesteps | 1838080 | +| train/ | | +| approx_kl | 2.3478703 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.375 | +| explained_variance | -1.65 | +| learning_rate | 0.0001 | +| loss | -0.0847 | +| n_updates | 78470 | +| policy_gradient_loss | -0.068 | +| value_loss | 0.00055 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.45e+03 | +| ep_rew_mean | 0.194 | +| time/ | | +| fps | 310 | +| iterations | 1796 | +| time_elapsed | 5919 | +| total_timesteps | 1839104 | +| train/ | | +| approx_kl | 2.1484687 | +| clip_fraction | 0.497 | +| clip_range | 0.2 | +| entropy_loss | -0.414 | +| explained_variance | -0.826 | +| learning_rate | 0.0001 | +| loss | -0.0833 | +| n_updates | 78480 | +| policy_gradient_loss | -0.0629 | +| value_loss | 0.000468 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.45e+03 | +| ep_rew_mean | 0.19 | +| time/ | | +| fps | 310 | +| iterations | 1797 | +| time_elapsed | 5923 | +| total_timesteps | 1840128 | +| train/ | | +| approx_kl | 2.9563882 | +| clip_fraction | 0.461 | +| clip_range | 0.2 | +| entropy_loss | -0.307 | +| explained_variance | -10.7 | +| learning_rate | 0.0001 | +| loss | -0.107 | +| n_updates | 78490 | +| policy_gradient_loss | -0.0657 | +| value_loss | 0.000568 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.45e+03 | +| ep_rew_mean | 0.19 | +| time/ | | +| fps | 310 | +| iterations | 1798 | +| time_elapsed | 5926 | +| total_timesteps | 1841152 | +| train/ | | +| approx_kl | 2.5406318 | +| clip_fraction | 0.503 | +| clip_range | 0.2 | +| entropy_loss | -0.364 | +| explained_variance | -0.662 | +| learning_rate | 0.0001 | +| loss | -0.0817 | +| n_updates | 78500 | +| policy_gradient_loss | -0.0585 | +| value_loss | 0.000461 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.45e+03 | +| ep_rew_mean | 0.19 | +| time/ | | +| fps | 310 | +| iterations | 1799 | +| time_elapsed | 5929 | +| total_timesteps | 1842176 | +| train/ | | +| approx_kl | 1.7001762 | +| clip_fraction | 0.526 | +| clip_range | 0.2 | +| entropy_loss | -0.43 | +| explained_variance | -1.24 | +| learning_rate | 0.0001 | +| loss | -0.0917 | +| n_updates | 78510 | +| policy_gradient_loss | -0.0603 | +| value_loss | 0.000363 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.45e+03 | +| ep_rew_mean | 0.187 | +| time/ | | +| fps | 310 | +| iterations | 1800 | +| time_elapsed | 5932 | +| total_timesteps | 1843200 | +| train/ | | +| approx_kl | 1.5616374 | +| clip_fraction | 0.496 | +| clip_range | 0.2 | +| entropy_loss | -0.447 | +| explained_variance | -0.904 | +| learning_rate | 0.0001 | +| loss | -0.0648 | +| n_updates | 78520 | +| policy_gradient_loss | -0.0581 | +| value_loss | 0.000297 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.46e+03 | +| ep_rew_mean | 0.18 | +| time/ | | +| fps | 310 | +| iterations | 1801 | +| time_elapsed | 5936 | +| total_timesteps | 1844224 | +| train/ | | +| approx_kl | 4.5712266 | +| clip_fraction | 0.488 | +| clip_range | 0.2 | +| entropy_loss | -0.371 | +| explained_variance | -2.3 | +| learning_rate | 0.0001 | +| loss | -0.0922 | +| n_updates | 78530 | +| policy_gradient_loss | -0.0643 | +| value_loss | 0.000277 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.46e+03 | +| ep_rew_mean | 0.18 | +| time/ | | +| fps | 310 | +| iterations | 1802 | +| time_elapsed | 5939 | +| total_timesteps | 1845248 | +| train/ | | +| approx_kl | 1.7404221 | +| clip_fraction | 0.514 | +| clip_range | 0.2 | +| entropy_loss | -0.528 | +| explained_variance | -0.166 | +| learning_rate | 0.0001 | +| loss | -0.0962 | +| n_updates | 78540 | +| policy_gradient_loss | -0.053 | +| value_loss | 0.000281 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.45e+03 | +| ep_rew_mean | 0.18 | +| time/ | | +| fps | 310 | +| iterations | 1803 | +| time_elapsed | 5942 | +| total_timesteps | 1846272 | +| train/ | | +| approx_kl | 2.4214044 | +| clip_fraction | 0.534 | +| clip_range | 0.2 | +| entropy_loss | -0.441 | +| explained_variance | -1.9 | +| learning_rate | 0.0001 | +| loss | -0.0819 | +| n_updates | 78550 | +| policy_gradient_loss | -0.0649 | +| value_loss | 0.000238 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.45e+03 | +| ep_rew_mean | 0.18 | +| time/ | | +| fps | 310 | +| iterations | 1804 | +| time_elapsed | 5946 | +| total_timesteps | 1847296 | +| train/ | | +| approx_kl | 2.1369 | +| clip_fraction | 0.514 | +| clip_range | 0.2 | +| entropy_loss | -0.422 | +| explained_variance | -0.491 | +| learning_rate | 0.0001 | +| loss | -0.0952 | +| n_updates | 78560 | +| policy_gradient_loss | -0.0567 | +| value_loss | 0.000466 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.45e+03 | +| ep_rew_mean | 0.18 | +| time/ | | +| fps | 310 | +| iterations | 1805 | +| time_elapsed | 5949 | +| total_timesteps | 1848320 | +| train/ | | +| approx_kl | 2.3852158 | +| clip_fraction | 0.482 | +| clip_range | 0.2 | +| entropy_loss | -0.382 | +| explained_variance | -1.57 | +| learning_rate | 0.0001 | +| loss | -0.089 | +| n_updates | 78570 | +| policy_gradient_loss | -0.0623 | +| value_loss | 0.000745 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.45e+03 | +| ep_rew_mean | 0.183 | +| time/ | | +| fps | 310 | +| iterations | 1806 | +| time_elapsed | 5952 | +| total_timesteps | 1849344 | +| train/ | | +| approx_kl | 9.198111 | +| clip_fraction | 0.502 | +| clip_range | 0.2 | +| entropy_loss | -0.428 | +| explained_variance | -1.43 | +| learning_rate | 0.0001 | +| loss | -0.0654 | +| n_updates | 78580 | +| policy_gradient_loss | -0.0583 | +| value_loss | 0.000545 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.45e+03 | +| ep_rew_mean | 0.183 | +| time/ | | +| fps | 310 | +| iterations | 1807 | +| time_elapsed | 5955 | +| total_timesteps | 1850368 | +| train/ | | +| approx_kl | 2.9596887 | +| clip_fraction | 0.528 | +| clip_range | 0.2 | +| entropy_loss | -0.474 | +| explained_variance | -0.966 | +| learning_rate | 0.0001 | +| loss | -0.0794 | +| n_updates | 78590 | +| policy_gradient_loss | -0.063 | +| value_loss | 0.000662 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.46e+03 | +| ep_rew_mean | 0.186 | +| time/ | | +| fps | 310 | +| iterations | 1808 | +| time_elapsed | 5958 | +| total_timesteps | 1851392 | +| train/ | | +| approx_kl | 1.807142 | +| clip_fraction | 0.478 | +| clip_range | 0.2 | +| entropy_loss | -0.405 | +| explained_variance | -2.62 | +| learning_rate | 0.0001 | +| loss | -0.0912 | +| n_updates | 78600 | +| policy_gradient_loss | -0.0555 | +| value_loss | 0.000361 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.46e+03 | +| ep_rew_mean | 0.186 | +| time/ | | +| fps | 310 | +| iterations | 1809 | +| time_elapsed | 5962 | +| total_timesteps | 1852416 | +| train/ | | +| approx_kl | 2.5840397 | +| clip_fraction | 0.474 | +| clip_range | 0.2 | +| entropy_loss | -0.339 | +| explained_variance | -1.62 | +| learning_rate | 0.0001 | +| loss | -0.091 | +| n_updates | 78610 | +| policy_gradient_loss | -0.0623 | +| value_loss | 0.000462 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.46e+03 | +| ep_rew_mean | 0.186 | +| time/ | | +| fps | 310 | +| iterations | 1810 | +| time_elapsed | 5965 | +| total_timesteps | 1853440 | +| train/ | | +| approx_kl | 4.5097594 | +| clip_fraction | 0.514 | +| clip_range | 0.2 | +| entropy_loss | -0.412 | +| explained_variance | -0.0827 | +| learning_rate | 0.0001 | +| loss | -0.0898 | +| n_updates | 78620 | +| policy_gradient_loss | -0.0625 | +| value_loss | 0.000454 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.46e+03 | +| ep_rew_mean | 0.19 | +| time/ | | +| fps | 310 | +| iterations | 1811 | +| time_elapsed | 5968 | +| total_timesteps | 1854464 | +| train/ | | +| approx_kl | 2.3530686 | +| clip_fraction | 0.468 | +| clip_range | 0.2 | +| entropy_loss | -0.342 | +| explained_variance | -2.7 | +| learning_rate | 0.0001 | +| loss | -0.0597 | +| n_updates | 78630 | +| policy_gradient_loss | -0.0563 | +| value_loss | 0.000432 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.46e+03 | +| ep_rew_mean | 0.19 | +| time/ | | +| fps | 310 | +| iterations | 1812 | +| time_elapsed | 5971 | +| total_timesteps | 1855488 | +| train/ | | +| approx_kl | 1.8366446 | +| clip_fraction | 0.505 | +| clip_range | 0.2 | +| entropy_loss | -0.429 | +| explained_variance | -0.835 | +| learning_rate | 0.0001 | +| loss | -0.12 | +| n_updates | 78640 | +| policy_gradient_loss | -0.0674 | +| value_loss | 0.000259 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.46e+03 | +| ep_rew_mean | 0.19 | +| time/ | | +| fps | 310 | +| iterations | 1813 | +| time_elapsed | 5974 | +| total_timesteps | 1856512 | +| train/ | | +| approx_kl | 2.189166 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.341 | +| explained_variance | -0.467 | +| learning_rate | 0.0001 | +| loss | -0.0811 | +| n_updates | 78650 | +| policy_gradient_loss | -0.0633 | +| value_loss | 0.000345 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.46e+03 | +| ep_rew_mean | 0.188 | +| time/ | | +| fps | 310 | +| iterations | 1814 | +| time_elapsed | 5977 | +| total_timesteps | 1857536 | +| train/ | | +| approx_kl | 1.645227 | +| clip_fraction | 0.49 | +| clip_range | 0.2 | +| entropy_loss | -0.414 | +| explained_variance | -0.905 | +| learning_rate | 0.0001 | +| loss | -0.0665 | +| n_updates | 78660 | +| policy_gradient_loss | -0.062 | +| value_loss | 0.000385 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.46e+03 | +| ep_rew_mean | 0.188 | +| time/ | | +| fps | 310 | +| iterations | 1815 | +| time_elapsed | 5980 | +| total_timesteps | 1858560 | +| train/ | | +| approx_kl | 2.1201692 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.412 | +| explained_variance | -0.715 | +| learning_rate | 0.0001 | +| loss | -0.0672 | +| n_updates | 78670 | +| policy_gradient_loss | -0.0631 | +| value_loss | 0.00047 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.46e+03 | +| ep_rew_mean | 0.188 | +| time/ | | +| fps | 310 | +| iterations | 1816 | +| time_elapsed | 5984 | +| total_timesteps | 1859584 | +| train/ | | +| approx_kl | 1.9024427 | +| clip_fraction | 0.515 | +| clip_range | 0.2 | +| entropy_loss | -0.439 | +| explained_variance | -2.04 | +| learning_rate | 0.0001 | +| loss | -0.0893 | +| n_updates | 78680 | +| policy_gradient_loss | -0.0679 | +| value_loss | 0.000341 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.46e+03 | +| ep_rew_mean | 0.188 | +| time/ | | +| fps | 310 | +| iterations | 1817 | +| time_elapsed | 5987 | +| total_timesteps | 1860608 | +| train/ | | +| approx_kl | 1.9995173 | +| clip_fraction | 0.525 | +| clip_range | 0.2 | +| entropy_loss | -0.465 | +| explained_variance | -2.97 | +| learning_rate | 0.0001 | +| loss | -0.0736 | +| n_updates | 78690 | +| policy_gradient_loss | -0.0524 | +| value_loss | 0.000103 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.46e+03 | +| ep_rew_mean | 0.188 | +| time/ | | +| fps | 310 | +| iterations | 1818 | +| time_elapsed | 5991 | +| total_timesteps | 1861632 | +| train/ | | +| approx_kl | 1.4302957 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.457 | +| explained_variance | -3.81 | +| learning_rate | 0.0001 | +| loss | -0.0591 | +| n_updates | 78700 | +| policy_gradient_loss | -0.0616 | +| value_loss | 8.55e-05 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.46e+03 | +| ep_rew_mean | 0.188 | +| time/ | | +| fps | 310 | +| iterations | 1819 | +| time_elapsed | 5995 | +| total_timesteps | 1862656 | +| train/ | | +| approx_kl | 0.7861792 | +| clip_fraction | 0.464 | +| clip_range | 0.2 | +| entropy_loss | -0.729 | +| explained_variance | 0.0643 | +| learning_rate | 0.0001 | +| loss | -0.0435 | +| n_updates | 78710 | +| policy_gradient_loss | -0.0235 | +| value_loss | 0.00116 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.46e+03 | +| ep_rew_mean | 0.188 | +| time/ | | +| fps | 310 | +| iterations | 1820 | +| time_elapsed | 5998 | +| total_timesteps | 1863680 | +| train/ | | +| approx_kl | 2.528697 | +| clip_fraction | 0.506 | +| clip_range | 0.2 | +| entropy_loss | -0.387 | +| explained_variance | -3.34 | +| learning_rate | 0.0001 | +| loss | -0.0963 | +| n_updates | 78720 | +| policy_gradient_loss | -0.0515 | +| value_loss | 0.00042 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.46e+03 | +| ep_rew_mean | 0.188 | +| time/ | | +| fps | 310 | +| iterations | 1821 | +| time_elapsed | 6001 | +| total_timesteps | 1864704 | +| train/ | | +| approx_kl | 2.694601 | +| clip_fraction | 0.51 | +| clip_range | 0.2 | +| entropy_loss | -0.419 | +| explained_variance | -1.06 | +| learning_rate | 0.0001 | +| loss | -0.0979 | +| n_updates | 78730 | +| policy_gradient_loss | -0.0639 | +| value_loss | 0.000463 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.46e+03 | +| ep_rew_mean | 0.188 | +| time/ | | +| fps | 310 | +| iterations | 1822 | +| time_elapsed | 6005 | +| total_timesteps | 1865728 | +| train/ | | +| approx_kl | 2.3211884 | +| clip_fraction | 0.459 | +| clip_range | 0.2 | +| entropy_loss | -0.386 | +| explained_variance | -1.4 | +| learning_rate | 0.0001 | +| loss | -0.0832 | +| n_updates | 78740 | +| policy_gradient_loss | -0.0601 | +| value_loss | 0.000752 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.46e+03 | +| ep_rew_mean | 0.188 | +| time/ | | +| fps | 310 | +| iterations | 1823 | +| time_elapsed | 6008 | +| total_timesteps | 1866752 | +| train/ | | +| approx_kl | 1.6428146 | +| clip_fraction | 0.476 | +| clip_range | 0.2 | +| entropy_loss | -0.379 | +| explained_variance | -0.325 | +| learning_rate | 0.0001 | +| loss | -0.0551 | +| n_updates | 78750 | +| policy_gradient_loss | -0.0582 | +| value_loss | 0.000366 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.46e+03 | +| ep_rew_mean | 0.188 | +| time/ | | +| fps | 310 | +| iterations | 1824 | +| time_elapsed | 6012 | +| total_timesteps | 1867776 | +| train/ | | +| approx_kl | 1.3527639 | +| clip_fraction | 0.428 | +| clip_range | 0.2 | +| entropy_loss | -0.567 | +| explained_variance | -0.0405 | +| learning_rate | 0.0001 | +| loss | -0.0769 | +| n_updates | 78760 | +| policy_gradient_loss | -0.0508 | +| value_loss | 0.00069 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.46e+03 | +| ep_rew_mean | 0.188 | +| time/ | | +| fps | 310 | +| iterations | 1825 | +| time_elapsed | 6015 | +| total_timesteps | 1868800 | +| train/ | | +| approx_kl | 1.756525 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.411 | +| explained_variance | -1.14 | +| learning_rate | 0.0001 | +| loss | -0.0653 | +| n_updates | 78770 | +| policy_gradient_loss | -0.0668 | +| value_loss | 0.000661 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.46e+03 | +| ep_rew_mean | 0.188 | +| time/ | | +| fps | 310 | +| iterations | 1826 | +| time_elapsed | 6018 | +| total_timesteps | 1869824 | +| train/ | | +| approx_kl | 2.0845811 | +| clip_fraction | 0.517 | +| clip_range | 0.2 | +| entropy_loss | -0.475 | +| explained_variance | -1.44 | +| learning_rate | 0.0001 | +| loss | -0.0772 | +| n_updates | 78780 | +| policy_gradient_loss | -0.0686 | +| value_loss | 0.000385 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.46e+03 | +| ep_rew_mean | 0.188 | +| time/ | | +| fps | 310 | +| iterations | 1827 | +| time_elapsed | 6021 | +| total_timesteps | 1870848 | +| train/ | | +| approx_kl | 2.3056285 | +| clip_fraction | 0.507 | +| clip_range | 0.2 | +| entropy_loss | -0.403 | +| explained_variance | -0.717 | +| learning_rate | 0.0001 | +| loss | -0.0897 | +| n_updates | 78790 | +| policy_gradient_loss | -0.0641 | +| value_loss | 0.000296 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.46e+03 | +| ep_rew_mean | 0.188 | +| time/ | | +| fps | 310 | +| iterations | 1828 | +| time_elapsed | 6024 | +| total_timesteps | 1871872 | +| train/ | | +| approx_kl | 2.5997276 | +| clip_fraction | 0.556 | +| clip_range | 0.2 | +| entropy_loss | -0.776 | +| explained_variance | -0.19 | +| learning_rate | 0.0001 | +| loss | -0.0714 | +| n_updates | 78800 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000144 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.46e+03 | +| ep_rew_mean | 0.188 | +| time/ | | +| fps | 310 | +| iterations | 1829 | +| time_elapsed | 6027 | +| total_timesteps | 1872896 | +| train/ | | +| approx_kl | 1.9700637 | +| clip_fraction | 0.458 | +| clip_range | 0.2 | +| entropy_loss | -0.828 | +| explained_variance | -1.1 | +| learning_rate | 0.0001 | +| loss | -0.0677 | +| n_updates | 78810 | +| policy_gradient_loss | -0.022 | +| value_loss | 0.000114 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.46e+03 | +| ep_rew_mean | 0.188 | +| time/ | | +| fps | 310 | +| iterations | 1830 | +| time_elapsed | 6031 | +| total_timesteps | 1873920 | +| train/ | | +| approx_kl | 24.364613 | +| clip_fraction | 0.812 | +| clip_range | 0.2 | +| entropy_loss | -1.31 | +| explained_variance | -8.23 | +| learning_rate | 0.0001 | +| loss | -0.0622 | +| n_updates | 78820 | +| policy_gradient_loss | -0.0231 | +| value_loss | 0.00115 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.61e+03 | +| ep_rew_mean | 0.191 | +| time/ | | +| fps | 310 | +| iterations | 1831 | +| time_elapsed | 6034 | +| total_timesteps | 1874944 | +| train/ | | +| approx_kl | 1.7821898 | +| clip_fraction | 0.537 | +| clip_range | 0.2 | +| entropy_loss | -0.933 | +| explained_variance | -0.127 | +| learning_rate | 0.0001 | +| loss | -0.0996 | +| n_updates | 78830 | +| policy_gradient_loss | -0.0535 | +| value_loss | 0.00252 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.61e+03 | +| ep_rew_mean | 0.191 | +| time/ | | +| fps | 310 | +| iterations | 1832 | +| time_elapsed | 6037 | +| total_timesteps | 1875968 | +| train/ | | +| approx_kl | 3.170116 | +| clip_fraction | 0.484 | +| clip_range | 0.2 | +| entropy_loss | -0.436 | +| explained_variance | -1.22 | +| learning_rate | 0.0001 | +| loss | -0.11 | +| n_updates | 78840 | +| policy_gradient_loss | -0.0663 | +| value_loss | 0.001 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.6e+03 | +| ep_rew_mean | 0.19 | +| time/ | | +| fps | 310 | +| iterations | 1833 | +| time_elapsed | 6040 | +| total_timesteps | 1876992 | +| train/ | | +| approx_kl | 1.9280322 | +| clip_fraction | 0.488 | +| clip_range | 0.2 | +| entropy_loss | -0.452 | +| explained_variance | -1.03 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 78850 | +| policy_gradient_loss | -0.0674 | +| value_loss | 0.000425 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.6e+03 | +| ep_rew_mean | 0.19 | +| time/ | | +| fps | 310 | +| iterations | 1834 | +| time_elapsed | 6044 | +| total_timesteps | 1878016 | +| train/ | | +| approx_kl | 3.1064687 | +| clip_fraction | 0.494 | +| clip_range | 0.2 | +| entropy_loss | -0.346 | +| explained_variance | -4.82 | +| learning_rate | 0.0001 | +| loss | -0.0618 | +| n_updates | 78860 | +| policy_gradient_loss | -0.0588 | +| value_loss | 0.000342 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.6e+03 | +| ep_rew_mean | 0.184 | +| time/ | | +| fps | 310 | +| iterations | 1835 | +| time_elapsed | 6047 | +| total_timesteps | 1879040 | +| train/ | | +| approx_kl | 1.6546893 | +| clip_fraction | 0.515 | +| clip_range | 0.2 | +| entropy_loss | -0.45 | +| explained_variance | -3.59 | +| learning_rate | 0.0001 | +| loss | -0.0952 | +| n_updates | 78870 | +| policy_gradient_loss | -0.0726 | +| value_loss | 0.000257 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.6e+03 | +| ep_rew_mean | 0.184 | +| time/ | | +| fps | 310 | +| iterations | 1836 | +| time_elapsed | 6050 | +| total_timesteps | 1880064 | +| train/ | | +| approx_kl | 1.6159148 | +| clip_fraction | 0.49 | +| clip_range | 0.2 | +| entropy_loss | -0.426 | +| explained_variance | -1.24 | +| learning_rate | 0.0001 | +| loss | -0.0898 | +| n_updates | 78880 | +| policy_gradient_loss | -0.0629 | +| value_loss | 0.000818 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.61e+03 | +| ep_rew_mean | 0.181 | +| time/ | | +| fps | 310 | +| iterations | 1837 | +| time_elapsed | 6054 | +| total_timesteps | 1881088 | +| train/ | | +| approx_kl | 2.5978785 | +| clip_fraction | 0.496 | +| clip_range | 0.2 | +| entropy_loss | -0.471 | +| explained_variance | -1.06 | +| learning_rate | 0.0001 | +| loss | -0.0761 | +| n_updates | 78890 | +| policy_gradient_loss | -0.0607 | +| value_loss | 0.000311 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.59e+03 | +| ep_rew_mean | 0.181 | +| time/ | | +| fps | 310 | +| iterations | 1838 | +| time_elapsed | 6057 | +| total_timesteps | 1882112 | +| train/ | | +| approx_kl | 2.2604518 | +| clip_fraction | 0.507 | +| clip_range | 0.2 | +| entropy_loss | -0.428 | +| explained_variance | -0.948 | +| learning_rate | 0.0001 | +| loss | -0.123 | +| n_updates | 78900 | +| policy_gradient_loss | -0.0613 | +| value_loss | 0.000459 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.59e+03 | +| ep_rew_mean | 0.181 | +| time/ | | +| fps | 310 | +| iterations | 1839 | +| time_elapsed | 6061 | +| total_timesteps | 1883136 | +| train/ | | +| approx_kl | 2.079114 | +| clip_fraction | 0.501 | +| clip_range | 0.2 | +| entropy_loss | -0.424 | +| explained_variance | -1.49 | +| learning_rate | 0.0001 | +| loss | -0.0834 | +| n_updates | 78910 | +| policy_gradient_loss | -0.0676 | +| value_loss | 0.000393 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.59e+03 | +| ep_rew_mean | 0.181 | +| time/ | | +| fps | 310 | +| iterations | 1840 | +| time_elapsed | 6064 | +| total_timesteps | 1884160 | +| train/ | | +| approx_kl | 4.343845 | +| clip_fraction | 0.532 | +| clip_range | 0.2 | +| entropy_loss | -0.38 | +| explained_variance | -1.69 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 78920 | +| policy_gradient_loss | -0.0681 | +| value_loss | 0.000636 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.59e+03 | +| ep_rew_mean | 0.178 | +| time/ | | +| fps | 310 | +| iterations | 1841 | +| time_elapsed | 6067 | +| total_timesteps | 1885184 | +| train/ | | +| approx_kl | 1.9530201 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.442 | +| explained_variance | -3.64 | +| learning_rate | 0.0001 | +| loss | -0.0888 | +| n_updates | 78930 | +| policy_gradient_loss | -0.0573 | +| value_loss | 0.00026 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.59e+03 | +| ep_rew_mean | 0.178 | +| time/ | | +| fps | 310 | +| iterations | 1842 | +| time_elapsed | 6071 | +| total_timesteps | 1886208 | +| train/ | | +| approx_kl | 2.2842078 | +| clip_fraction | 0.491 | +| clip_range | 0.2 | +| entropy_loss | -0.413 | +| explained_variance | -3.89 | +| learning_rate | 0.0001 | +| loss | -0.105 | +| n_updates | 78940 | +| policy_gradient_loss | -0.0654 | +| value_loss | 0.00031 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.6e+03 | +| ep_rew_mean | 0.177 | +| time/ | | +| fps | 310 | +| iterations | 1843 | +| time_elapsed | 6074 | +| total_timesteps | 1887232 | +| train/ | | +| approx_kl | 1.9545457 | +| clip_fraction | 0.536 | +| clip_range | 0.2 | +| entropy_loss | -0.418 | +| explained_variance | -1.71 | +| learning_rate | 0.0001 | +| loss | -0.106 | +| n_updates | 78950 | +| policy_gradient_loss | -0.069 | +| value_loss | 0.000449 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.6e+03 | +| ep_rew_mean | 0.177 | +| time/ | | +| fps | 310 | +| iterations | 1844 | +| time_elapsed | 6077 | +| total_timesteps | 1888256 | +| train/ | | +| approx_kl | 2.2591202 | +| clip_fraction | 0.493 | +| clip_range | 0.2 | +| entropy_loss | -0.406 | +| explained_variance | -1.77 | +| learning_rate | 0.0001 | +| loss | -0.0855 | +| n_updates | 78960 | +| policy_gradient_loss | -0.0611 | +| value_loss | 0.000578 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.6e+03 | +| ep_rew_mean | 0.177 | +| time/ | | +| fps | 310 | +| iterations | 1845 | +| time_elapsed | 6080 | +| total_timesteps | 1889280 | +| train/ | | +| approx_kl | 2.2961836 | +| clip_fraction | 0.502 | +| clip_range | 0.2 | +| entropy_loss | -0.394 | +| explained_variance | -1.15 | +| learning_rate | 0.0001 | +| loss | -0.0889 | +| n_updates | 78970 | +| policy_gradient_loss | -0.0614 | +| value_loss | 0.000385 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.6e+03 | +| ep_rew_mean | 0.175 | +| time/ | | +| fps | 310 | +| iterations | 1846 | +| time_elapsed | 6083 | +| total_timesteps | 1890304 | +| train/ | | +| approx_kl | 2.7502594 | +| clip_fraction | 0.521 | +| clip_range | 0.2 | +| entropy_loss | -0.465 | +| explained_variance | -4.83 | +| learning_rate | 0.0001 | +| loss | -0.098 | +| n_updates | 78980 | +| policy_gradient_loss | -0.0653 | +| value_loss | 0.000239 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.6e+03 | +| ep_rew_mean | 0.175 | +| time/ | | +| fps | 310 | +| iterations | 1847 | +| time_elapsed | 6086 | +| total_timesteps | 1891328 | +| train/ | | +| approx_kl | 2.0393436 | +| clip_fraction | 0.52 | +| clip_range | 0.2 | +| entropy_loss | -0.472 | +| explained_variance | -1.53 | +| learning_rate | 0.0001 | +| loss | -0.0773 | +| n_updates | 78990 | +| policy_gradient_loss | -0.0695 | +| value_loss | 0.000426 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.6e+03 | +| ep_rew_mean | 0.174 | +| time/ | | +| fps | 310 | +| iterations | 1848 | +| time_elapsed | 6090 | +| total_timesteps | 1892352 | +| train/ | | +| approx_kl | 2.526534 | +| clip_fraction | 0.55 | +| clip_range | 0.2 | +| entropy_loss | -0.483 | +| explained_variance | -3.04 | +| learning_rate | 0.0001 | +| loss | -0.072 | +| n_updates | 79000 | +| policy_gradient_loss | -0.0584 | +| value_loss | 0.000317 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.6e+03 | +| ep_rew_mean | 0.173 | +| time/ | | +| fps | 310 | +| iterations | 1849 | +| time_elapsed | 6093 | +| total_timesteps | 1893376 | +| train/ | | +| approx_kl | 2.6465588 | +| clip_fraction | 0.534 | +| clip_range | 0.2 | +| entropy_loss | -0.458 | +| explained_variance | -1.51 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 79010 | +| policy_gradient_loss | -0.0705 | +| value_loss | 0.000199 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.6e+03 | +| ep_rew_mean | 0.173 | +| time/ | | +| fps | 310 | +| iterations | 1850 | +| time_elapsed | 6096 | +| total_timesteps | 1894400 | +| train/ | | +| approx_kl | 1.8253021 | +| clip_fraction | 0.526 | +| clip_range | 0.2 | +| entropy_loss | -0.483 | +| explained_variance | -0.854 | +| learning_rate | 0.0001 | +| loss | -0.0715 | +| n_updates | 79020 | +| policy_gradient_loss | -0.0728 | +| value_loss | 0.000244 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.59e+03 | +| ep_rew_mean | 0.177 | +| time/ | | +| fps | 310 | +| iterations | 1851 | +| time_elapsed | 6099 | +| total_timesteps | 1895424 | +| train/ | | +| approx_kl | 2.944334 | +| clip_fraction | 0.536 | +| clip_range | 0.2 | +| entropy_loss | -0.413 | +| explained_variance | -0.826 | +| learning_rate | 0.0001 | +| loss | -0.0733 | +| n_updates | 79030 | +| policy_gradient_loss | -0.0629 | +| value_loss | 0.000509 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.58e+03 | +| ep_rew_mean | 0.178 | +| time/ | | +| fps | 310 | +| iterations | 1852 | +| time_elapsed | 6102 | +| total_timesteps | 1896448 | +| train/ | | +| approx_kl | 2.1218538 | +| clip_fraction | 0.532 | +| clip_range | 0.2 | +| entropy_loss | -0.476 | +| explained_variance | -2.35 | +| learning_rate | 0.0001 | +| loss | -0.0757 | +| n_updates | 79040 | +| policy_gradient_loss | -0.0644 | +| value_loss | 0.0004 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.58e+03 | +| ep_rew_mean | 0.178 | +| time/ | | +| fps | 310 | +| iterations | 1853 | +| time_elapsed | 6106 | +| total_timesteps | 1897472 | +| train/ | | +| approx_kl | 2.2486782 | +| clip_fraction | 0.523 | +| clip_range | 0.2 | +| entropy_loss | -0.505 | +| explained_variance | -0.724 | +| learning_rate | 0.0001 | +| loss | -0.114 | +| n_updates | 79050 | +| policy_gradient_loss | -0.0658 | +| value_loss | 0.000463 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.58e+03 | +| ep_rew_mean | 0.178 | +| time/ | | +| fps | 310 | +| iterations | 1854 | +| time_elapsed | 6109 | +| total_timesteps | 1898496 | +| train/ | | +| approx_kl | 2.469789 | +| clip_fraction | 0.523 | +| clip_range | 0.2 | +| entropy_loss | -0.446 | +| explained_variance | -1.15 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 79060 | +| policy_gradient_loss | -0.0729 | +| value_loss | 0.000471 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.58e+03 | +| ep_rew_mean | 0.178 | +| time/ | | +| fps | 310 | +| iterations | 1855 | +| time_elapsed | 6113 | +| total_timesteps | 1899520 | +| train/ | | +| approx_kl | 2.067422 | +| clip_fraction | 0.56 | +| clip_range | 0.2 | +| entropy_loss | -0.571 | +| explained_variance | -2.61 | +| learning_rate | 0.0001 | +| loss | -0.1 | +| n_updates | 79070 | +| policy_gradient_loss | -0.052 | +| value_loss | 0.000728 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.59e+03 | +| ep_rew_mean | 0.177 | +| time/ | | +| fps | 310 | +| iterations | 1856 | +| time_elapsed | 6116 | +| total_timesteps | 1900544 | +| train/ | | +| approx_kl | 2.0073602 | +| clip_fraction | 0.539 | +| clip_range | 0.2 | +| entropy_loss | -0.463 | +| explained_variance | -3.37 | +| learning_rate | 0.0001 | +| loss | -0.0759 | +| n_updates | 79080 | +| policy_gradient_loss | -0.0704 | +| value_loss | 0.000436 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.59e+03 | +| ep_rew_mean | 0.179 | +| time/ | | +| fps | 310 | +| iterations | 1857 | +| time_elapsed | 6120 | +| total_timesteps | 1901568 | +| train/ | | +| approx_kl | 1.7471681 | +| clip_fraction | 0.519 | +| clip_range | 0.2 | +| entropy_loss | -0.469 | +| explained_variance | -1.54 | +| learning_rate | 0.0001 | +| loss | -0.0936 | +| n_updates | 79090 | +| policy_gradient_loss | -0.071 | +| value_loss | 0.000307 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.59e+03 | +| ep_rew_mean | 0.179 | +| time/ | | +| fps | 310 | +| iterations | 1858 | +| time_elapsed | 6123 | +| total_timesteps | 1902592 | +| train/ | | +| approx_kl | 2.2514021 | +| clip_fraction | 0.493 | +| clip_range | 0.2 | +| entropy_loss | -0.405 | +| explained_variance | -2.05 | +| learning_rate | 0.0001 | +| loss | -0.11 | +| n_updates | 79100 | +| policy_gradient_loss | -0.0714 | +| value_loss | 0.000474 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.59e+03 | +| ep_rew_mean | 0.176 | +| time/ | | +| fps | 310 | +| iterations | 1859 | +| time_elapsed | 6127 | +| total_timesteps | 1903616 | +| train/ | | +| approx_kl | 1.9322526 | +| clip_fraction | 0.509 | +| clip_range | 0.2 | +| entropy_loss | -0.489 | +| explained_variance | -0.685 | +| learning_rate | 0.0001 | +| loss | -0.0535 | +| n_updates | 79110 | +| policy_gradient_loss | -0.0571 | +| value_loss | 0.00033 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.59e+03 | +| ep_rew_mean | 0.176 | +| time/ | | +| fps | 310 | +| iterations | 1860 | +| time_elapsed | 6130 | +| total_timesteps | 1904640 | +| train/ | | +| approx_kl | 2.4223156 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.44 | +| explained_variance | -1.88 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 79120 | +| policy_gradient_loss | -0.0668 | +| value_loss | 0.000381 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.58e+03 | +| ep_rew_mean | 0.178 | +| time/ | | +| fps | 310 | +| iterations | 1861 | +| time_elapsed | 6133 | +| total_timesteps | 1905664 | +| train/ | | +| approx_kl | 1.8791871 | +| clip_fraction | 0.53 | +| clip_range | 0.2 | +| entropy_loss | -0.475 | +| explained_variance | -0.212 | +| learning_rate | 0.0001 | +| loss | -0.0918 | +| n_updates | 79130 | +| policy_gradient_loss | -0.0677 | +| value_loss | 0.00038 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.58e+03 | +| ep_rew_mean | 0.178 | +| time/ | | +| fps | 310 | +| iterations | 1862 | +| time_elapsed | 6136 | +| total_timesteps | 1906688 | +| train/ | | +| approx_kl | 1.8813429 | +| clip_fraction | 0.537 | +| clip_range | 0.2 | +| entropy_loss | -0.5 | +| explained_variance | -1.74 | +| learning_rate | 0.0001 | +| loss | -0.116 | +| n_updates | 79140 | +| policy_gradient_loss | -0.0757 | +| value_loss | 0.000296 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.58e+03 | +| ep_rew_mean | 0.176 | +| time/ | | +| fps | 310 | +| iterations | 1863 | +| time_elapsed | 6140 | +| total_timesteps | 1907712 | +| train/ | | +| approx_kl | 2.6588068 | +| clip_fraction | 0.505 | +| clip_range | 0.2 | +| entropy_loss | -0.433 | +| explained_variance | -2.64 | +| learning_rate | 0.0001 | +| loss | -0.0766 | +| n_updates | 79150 | +| policy_gradient_loss | -0.066 | +| value_loss | 0.000357 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.58e+03 | +| ep_rew_mean | 0.176 | +| time/ | | +| fps | 310 | +| iterations | 1864 | +| time_elapsed | 6143 | +| total_timesteps | 1908736 | +| train/ | | +| approx_kl | 2.0321352 | +| clip_fraction | 0.5 | +| clip_range | 0.2 | +| entropy_loss | -0.419 | +| explained_variance | -0.596 | +| learning_rate | 0.0001 | +| loss | -0.0415 | +| n_updates | 79160 | +| policy_gradient_loss | -0.0587 | +| value_loss | 0.00033 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.57e+03 | +| ep_rew_mean | 0.176 | +| time/ | | +| fps | 310 | +| iterations | 1865 | +| time_elapsed | 6146 | +| total_timesteps | 1909760 | +| train/ | | +| approx_kl | 2.0155325 | +| clip_fraction | 0.548 | +| clip_range | 0.2 | +| entropy_loss | -0.483 | +| explained_variance | -0.961 | +| learning_rate | 0.0001 | +| loss | -0.0808 | +| n_updates | 79170 | +| policy_gradient_loss | -0.0659 | +| value_loss | 0.000682 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.57e+03 | +| ep_rew_mean | 0.176 | +| time/ | | +| fps | 310 | +| iterations | 1866 | +| time_elapsed | 6149 | +| total_timesteps | 1910784 | +| train/ | | +| approx_kl | 2.5780497 | +| clip_fraction | 0.535 | +| clip_range | 0.2 | +| entropy_loss | -0.454 | +| explained_variance | -1.81 | +| learning_rate | 0.0001 | +| loss | -0.118 | +| n_updates | 79180 | +| policy_gradient_loss | -0.0697 | +| value_loss | 0.000733 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.57e+03 | +| ep_rew_mean | 0.176 | +| time/ | | +| fps | 310 | +| iterations | 1867 | +| time_elapsed | 6152 | +| total_timesteps | 1911808 | +| train/ | | +| approx_kl | 1.606883 | +| clip_fraction | 0.537 | +| clip_range | 0.2 | +| entropy_loss | -0.568 | +| explained_variance | -2.12 | +| learning_rate | 0.0001 | +| loss | -0.0833 | +| n_updates | 79190 | +| policy_gradient_loss | -0.0695 | +| value_loss | 0.000334 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.57e+03 | +| ep_rew_mean | 0.176 | +| time/ | | +| fps | 310 | +| iterations | 1868 | +| time_elapsed | 6155 | +| total_timesteps | 1912832 | +| train/ | | +| approx_kl | 2.2666426 | +| clip_fraction | 0.542 | +| clip_range | 0.2 | +| entropy_loss | -0.464 | +| explained_variance | -0.941 | +| learning_rate | 0.0001 | +| loss | -0.0882 | +| n_updates | 79200 | +| policy_gradient_loss | -0.0718 | +| value_loss | 0.000444 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.58e+03 | +| ep_rew_mean | 0.18 | +| time/ | | +| fps | 310 | +| iterations | 1869 | +| time_elapsed | 6159 | +| total_timesteps | 1913856 | +| train/ | | +| approx_kl | 2.421842 | +| clip_fraction | 0.534 | +| clip_range | 0.2 | +| entropy_loss | -0.459 | +| explained_variance | -2.13 | +| learning_rate | 0.0001 | +| loss | -0.0844 | +| n_updates | 79210 | +| policy_gradient_loss | -0.0704 | +| value_loss | 0.000403 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.58e+03 | +| ep_rew_mean | 0.18 | +| time/ | | +| fps | 310 | +| iterations | 1870 | +| time_elapsed | 6162 | +| total_timesteps | 1914880 | +| train/ | | +| approx_kl | 2.041402 | +| clip_fraction | 0.498 | +| clip_range | 0.2 | +| entropy_loss | -0.376 | +| explained_variance | -6.97 | +| learning_rate | 0.0001 | +| loss | -0.105 | +| n_updates | 79220 | +| policy_gradient_loss | -0.0692 | +| value_loss | 0.000383 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.58e+03 | +| ep_rew_mean | 0.182 | +| time/ | | +| fps | 310 | +| iterations | 1871 | +| time_elapsed | 6165 | +| total_timesteps | 1915904 | +| train/ | | +| approx_kl | 1.5774169 | +| clip_fraction | 0.519 | +| clip_range | 0.2 | +| entropy_loss | -0.545 | +| explained_variance | -0.56 | +| learning_rate | 0.0001 | +| loss | -0.0998 | +| n_updates | 79230 | +| policy_gradient_loss | -0.0576 | +| value_loss | 0.000268 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.58e+03 | +| ep_rew_mean | 0.182 | +| time/ | | +| fps | 310 | +| iterations | 1872 | +| time_elapsed | 6169 | +| total_timesteps | 1916928 | +| train/ | | +| approx_kl | 1.7973663 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.464 | +| explained_variance | -0.635 | +| learning_rate | 0.0001 | +| loss | -0.0752 | +| n_updates | 79240 | +| policy_gradient_loss | -0.0566 | +| value_loss | 0.000677 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.58e+03 | +| ep_rew_mean | 0.182 | +| time/ | | +| fps | 310 | +| iterations | 1873 | +| time_elapsed | 6172 | +| total_timesteps | 1917952 | +| train/ | | +| approx_kl | 1.6688788 | +| clip_fraction | 0.515 | +| clip_range | 0.2 | +| entropy_loss | -0.431 | +| explained_variance | -3.54 | +| learning_rate | 0.0001 | +| loss | -0.0906 | +| n_updates | 79250 | +| policy_gradient_loss | -0.071 | +| value_loss | 0.00063 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.58e+03 | +| ep_rew_mean | 0.182 | +| time/ | | +| fps | 310 | +| iterations | 1874 | +| time_elapsed | 6175 | +| total_timesteps | 1918976 | +| train/ | | +| approx_kl | 5.453751 | +| clip_fraction | 0.532 | +| clip_range | 0.2 | +| entropy_loss | -0.475 | +| explained_variance | -1.89 | +| learning_rate | 0.0001 | +| loss | -0.0741 | +| n_updates | 79260 | +| policy_gradient_loss | -0.0708 | +| value_loss | 0.000292 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.6e+03 | +| ep_rew_mean | 0.186 | +| time/ | | +| fps | 310 | +| iterations | 1875 | +| time_elapsed | 6179 | +| total_timesteps | 1920000 | +| train/ | | +| approx_kl | 2.366693 | +| clip_fraction | 0.488 | +| clip_range | 0.2 | +| entropy_loss | -0.469 | +| explained_variance | -2.47 | +| learning_rate | 0.0001 | +| loss | -0.0327 | +| n_updates | 79270 | +| policy_gradient_loss | -0.0563 | +| value_loss | 0.000274 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.6e+03 | +| ep_rew_mean | 0.186 | +| time/ | | +| fps | 310 | +| iterations | 1876 | +| time_elapsed | 6182 | +| total_timesteps | 1921024 | +| train/ | | +| approx_kl | 2.021597 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.397 | +| explained_variance | -1.44 | +| learning_rate | 0.0001 | +| loss | -0.0498 | +| n_updates | 79280 | +| policy_gradient_loss | -0.0596 | +| value_loss | 0.000342 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.59e+03 | +| ep_rew_mean | 0.183 | +| time/ | | +| fps | 310 | +| iterations | 1877 | +| time_elapsed | 6185 | +| total_timesteps | 1922048 | +| train/ | | +| approx_kl | 1.8018534 | +| clip_fraction | 0.504 | +| clip_range | 0.2 | +| entropy_loss | -0.458 | +| explained_variance | -3.23 | +| learning_rate | 0.0001 | +| loss | -0.0841 | +| n_updates | 79290 | +| policy_gradient_loss | -0.0662 | +| value_loss | 0.000169 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.59e+03 | +| ep_rew_mean | 0.183 | +| time/ | | +| fps | 310 | +| iterations | 1878 | +| time_elapsed | 6189 | +| total_timesteps | 1923072 | +| train/ | | +| approx_kl | 2.5332665 | +| clip_fraction | 0.516 | +| clip_range | 0.2 | +| entropy_loss | -0.503 | +| explained_variance | -0.475 | +| learning_rate | 0.0001 | +| loss | -0.0736 | +| n_updates | 79300 | +| policy_gradient_loss | -0.059 | +| value_loss | 0.00018 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.59e+03 | +| ep_rew_mean | 0.183 | +| time/ | | +| fps | 310 | +| iterations | 1879 | +| time_elapsed | 6192 | +| total_timesteps | 1924096 | +| train/ | | +| approx_kl | 2.0379472 | +| clip_fraction | 0.472 | +| clip_range | 0.2 | +| entropy_loss | -0.458 | +| explained_variance | -2.6 | +| learning_rate | 0.0001 | +| loss | -0.085 | +| n_updates | 79310 | +| policy_gradient_loss | -0.0627 | +| value_loss | 0.000246 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.59e+03 | +| ep_rew_mean | 0.183 | +| time/ | | +| fps | 310 | +| iterations | 1880 | +| time_elapsed | 6195 | +| total_timesteps | 1925120 | +| train/ | | +| approx_kl | 2.4308734 | +| clip_fraction | 0.502 | +| clip_range | 0.2 | +| entropy_loss | -0.395 | +| explained_variance | -0.457 | +| learning_rate | 0.0001 | +| loss | -0.0982 | +| n_updates | 79320 | +| policy_gradient_loss | -0.0617 | +| value_loss | 0.000514 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.6e+03 | +| ep_rew_mean | 0.181 | +| time/ | | +| fps | 310 | +| iterations | 1881 | +| time_elapsed | 6198 | +| total_timesteps | 1926144 | +| train/ | | +| approx_kl | 1.6872687 | +| clip_fraction | 0.502 | +| clip_range | 0.2 | +| entropy_loss | -0.434 | +| explained_variance | -2.51 | +| learning_rate | 0.0001 | +| loss | -0.113 | +| n_updates | 79330 | +| policy_gradient_loss | -0.0592 | +| value_loss | 0.000287 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.6e+03 | +| ep_rew_mean | 0.181 | +| time/ | | +| fps | 310 | +| iterations | 1882 | +| time_elapsed | 6201 | +| total_timesteps | 1927168 | +| train/ | | +| approx_kl | 2.3502886 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.399 | +| explained_variance | -0.663 | +| learning_rate | 0.0001 | +| loss | -0.109 | +| n_updates | 79340 | +| policy_gradient_loss | -0.055 | +| value_loss | 0.00034 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.6e+03 | +| ep_rew_mean | 0.181 | +| time/ | | +| fps | 310 | +| iterations | 1883 | +| time_elapsed | 6205 | +| total_timesteps | 1928192 | +| train/ | | +| approx_kl | 2.656623 | +| clip_fraction | 0.523 | +| clip_range | 0.2 | +| entropy_loss | -0.399 | +| explained_variance | -0.656 | +| learning_rate | 0.0001 | +| loss | -0.0939 | +| n_updates | 79350 | +| policy_gradient_loss | -0.0646 | +| value_loss | 0.000445 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.6e+03 | +| ep_rew_mean | 0.183 | +| time/ | | +| fps | 310 | +| iterations | 1884 | +| time_elapsed | 6208 | +| total_timesteps | 1929216 | +| train/ | | +| approx_kl | 1.653653 | +| clip_fraction | 0.467 | +| clip_range | 0.2 | +| entropy_loss | -0.395 | +| explained_variance | -1.37 | +| learning_rate | 0.0001 | +| loss | -0.0852 | +| n_updates | 79360 | +| policy_gradient_loss | -0.0718 | +| value_loss | 0.000354 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.6e+03 | +| ep_rew_mean | 0.183 | +| time/ | | +| fps | 310 | +| iterations | 1885 | +| time_elapsed | 6211 | +| total_timesteps | 1930240 | +| train/ | | +| approx_kl | 2.5716426 | +| clip_fraction | 0.504 | +| clip_range | 0.2 | +| entropy_loss | -0.372 | +| explained_variance | -3.21 | +| learning_rate | 0.0001 | +| loss | -0.0832 | +| n_updates | 79370 | +| policy_gradient_loss | -0.0678 | +| value_loss | 0.000769 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.59e+03 | +| ep_rew_mean | 0.181 | +| time/ | | +| fps | 310 | +| iterations | 1886 | +| time_elapsed | 6214 | +| total_timesteps | 1931264 | +| train/ | | +| approx_kl | 2.836206 | +| clip_fraction | 0.515 | +| clip_range | 0.2 | +| entropy_loss | -0.404 | +| explained_variance | -1.2 | +| learning_rate | 0.0001 | +| loss | -0.0859 | +| n_updates | 79380 | +| policy_gradient_loss | -0.0697 | +| value_loss | 0.000572 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.59e+03 | +| ep_rew_mean | 0.181 | +| time/ | | +| fps | 310 | +| iterations | 1887 | +| time_elapsed | 6217 | +| total_timesteps | 1932288 | +| train/ | | +| approx_kl | 9.17802 | +| clip_fraction | 0.491 | +| clip_range | 0.2 | +| entropy_loss | -0.407 | +| explained_variance | -3.23 | +| learning_rate | 0.0001 | +| loss | -0.0763 | +| n_updates | 79390 | +| policy_gradient_loss | -0.0647 | +| value_loss | 0.000201 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.58e+03 | +| ep_rew_mean | 0.18 | +| time/ | | +| fps | 310 | +| iterations | 1888 | +| time_elapsed | 6221 | +| total_timesteps | 1933312 | +| train/ | | +| approx_kl | 2.4760914 | +| clip_fraction | 0.535 | +| clip_range | 0.2 | +| entropy_loss | -0.5 | +| explained_variance | -0.868 | +| learning_rate | 0.0001 | +| loss | -0.0771 | +| n_updates | 79400 | +| policy_gradient_loss | -0.068 | +| value_loss | 8.7e-05 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.58e+03 | +| ep_rew_mean | 0.18 | +| time/ | | +| fps | 310 | +| iterations | 1889 | +| time_elapsed | 6224 | +| total_timesteps | 1934336 | +| train/ | | +| approx_kl | 2.112329 | +| clip_fraction | 0.543 | +| clip_range | 0.2 | +| entropy_loss | -0.45 | +| explained_variance | -0.371 | +| learning_rate | 0.0001 | +| loss | -0.0428 | +| n_updates | 79410 | +| policy_gradient_loss | -0.0624 | +| value_loss | 0.000496 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.58e+03 | +| ep_rew_mean | 0.18 | +| time/ | | +| fps | 310 | +| iterations | 1890 | +| time_elapsed | 6228 | +| total_timesteps | 1935360 | +| train/ | | +| approx_kl | 2.3536463 | +| clip_fraction | 0.546 | +| clip_range | 0.2 | +| entropy_loss | -0.488 | +| explained_variance | -2.95 | +| learning_rate | 0.0001 | +| loss | -0.0915 | +| n_updates | 79420 | +| policy_gradient_loss | -0.0745 | +| value_loss | 0.000289 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.59e+03 | +| ep_rew_mean | 0.179 | +| time/ | | +| fps | 310 | +| iterations | 1891 | +| time_elapsed | 6231 | +| total_timesteps | 1936384 | +| train/ | | +| approx_kl | 2.236107 | +| clip_fraction | 0.535 | +| clip_range | 0.2 | +| entropy_loss | -0.444 | +| explained_variance | -4.78 | +| learning_rate | 0.0001 | +| loss | -0.0986 | +| n_updates | 79430 | +| policy_gradient_loss | -0.0729 | +| value_loss | 0.000206 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.59e+03 | +| ep_rew_mean | 0.179 | +| time/ | | +| fps | 310 | +| iterations | 1892 | +| time_elapsed | 6235 | +| total_timesteps | 1937408 | +| train/ | | +| approx_kl | 3.087907 | +| clip_fraction | 0.525 | +| clip_range | 0.2 | +| entropy_loss | -0.437 | +| explained_variance | -1.39 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 79440 | +| policy_gradient_loss | -0.065 | +| value_loss | 0.000294 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.59e+03 | +| ep_rew_mean | 0.179 | +| time/ | | +| fps | 310 | +| iterations | 1893 | +| time_elapsed | 6238 | +| total_timesteps | 1938432 | +| train/ | | +| approx_kl | 2.1343625 | +| clip_fraction | 0.553 | +| clip_range | 0.2 | +| entropy_loss | -0.501 | +| explained_variance | -1.17 | +| learning_rate | 0.0001 | +| loss | -0.0999 | +| n_updates | 79450 | +| policy_gradient_loss | -0.0617 | +| value_loss | 0.000251 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.6e+03 | +| ep_rew_mean | 0.177 | +| time/ | | +| fps | 310 | +| iterations | 1894 | +| time_elapsed | 6242 | +| total_timesteps | 1939456 | +| train/ | | +| approx_kl | 2.364478 | +| clip_fraction | 0.525 | +| clip_range | 0.2 | +| entropy_loss | -0.478 | +| explained_variance | -3.74 | +| learning_rate | 0.0001 | +| loss | -0.0953 | +| n_updates | 79460 | +| policy_gradient_loss | -0.0735 | +| value_loss | 0.000216 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.6e+03 | +| ep_rew_mean | 0.177 | +| time/ | | +| fps | 310 | +| iterations | 1895 | +| time_elapsed | 6245 | +| total_timesteps | 1940480 | +| train/ | | +| approx_kl | 2.0261443 | +| clip_fraction | 0.537 | +| clip_range | 0.2 | +| entropy_loss | -0.491 | +| explained_variance | -2.64 | +| learning_rate | 0.0001 | +| loss | -0.0905 | +| n_updates | 79470 | +| policy_gradient_loss | -0.0746 | +| value_loss | 0.000451 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.59e+03 | +| ep_rew_mean | 0.171 | +| time/ | | +| fps | 310 | +| iterations | 1896 | +| time_elapsed | 6249 | +| total_timesteps | 1941504 | +| train/ | | +| approx_kl | 1.5727236 | +| clip_fraction | 0.518 | +| clip_range | 0.2 | +| entropy_loss | -0.528 | +| explained_variance | -2.88 | +| learning_rate | 0.0001 | +| loss | -0.0135 | +| n_updates | 79480 | +| policy_gradient_loss | -0.067 | +| value_loss | 0.000623 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.59e+03 | +| ep_rew_mean | 0.171 | +| time/ | | +| fps | 310 | +| iterations | 1897 | +| time_elapsed | 6252 | +| total_timesteps | 1942528 | +| train/ | | +| approx_kl | 4.235613 | +| clip_fraction | 0.559 | +| clip_range | 0.2 | +| entropy_loss | -0.604 | +| explained_variance | -0.723 | +| learning_rate | 0.0001 | +| loss | -0.0935 | +| n_updates | 79490 | +| policy_gradient_loss | -0.0651 | +| value_loss | 0.000276 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.6e+03 | +| ep_rew_mean | 0.176 | +| time/ | | +| fps | 310 | +| iterations | 1898 | +| time_elapsed | 6255 | +| total_timesteps | 1943552 | +| train/ | | +| approx_kl | 1.5196939 | +| clip_fraction | 0.535 | +| clip_range | 0.2 | +| entropy_loss | -0.529 | +| explained_variance | -0.861 | +| learning_rate | 0.0001 | +| loss | -0.0586 | +| n_updates | 79500 | +| policy_gradient_loss | -0.0624 | +| value_loss | 0.000387 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.6e+03 | +| ep_rew_mean | 0.176 | +| time/ | | +| fps | 310 | +| iterations | 1899 | +| time_elapsed | 6258 | +| total_timesteps | 1944576 | +| train/ | | +| approx_kl | 2.7198129 | +| clip_fraction | 0.528 | +| clip_range | 0.2 | +| entropy_loss | -0.478 | +| explained_variance | -0.899 | +| learning_rate | 0.0001 | +| loss | -0.11 | +| n_updates | 79510 | +| policy_gradient_loss | -0.0676 | +| value_loss | 0.000409 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.6e+03 | +| ep_rew_mean | 0.176 | +| time/ | | +| fps | 310 | +| iterations | 1900 | +| time_elapsed | 6261 | +| total_timesteps | 1945600 | +| train/ | | +| approx_kl | 1.8700864 | +| clip_fraction | 0.547 | +| clip_range | 0.2 | +| entropy_loss | -0.532 | +| explained_variance | -1.54 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 79520 | +| policy_gradient_loss | -0.0727 | +| value_loss | 0.000342 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.6e+03 | +| ep_rew_mean | 0.174 | +| time/ | | +| fps | 310 | +| iterations | 1901 | +| time_elapsed | 6264 | +| total_timesteps | 1946624 | +| train/ | | +| approx_kl | 1.9416033 | +| clip_fraction | 0.514 | +| clip_range | 0.2 | +| entropy_loss | -0.469 | +| explained_variance | -2.28 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 79530 | +| policy_gradient_loss | -0.0714 | +| value_loss | 0.000259 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.6e+03 | +| ep_rew_mean | 0.174 | +| time/ | | +| fps | 310 | +| iterations | 1902 | +| time_elapsed | 6268 | +| total_timesteps | 1947648 | +| train/ | | +| approx_kl | 2.602583 | +| clip_fraction | 0.555 | +| clip_range | 0.2 | +| entropy_loss | -0.544 | +| explained_variance | -5.29 | +| learning_rate | 0.0001 | +| loss | -0.11 | +| n_updates | 79540 | +| policy_gradient_loss | -0.0777 | +| value_loss | 0.000186 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.6e+03 | +| ep_rew_mean | 0.174 | +| time/ | | +| fps | 310 | +| iterations | 1903 | +| time_elapsed | 6271 | +| total_timesteps | 1948672 | +| train/ | | +| approx_kl | 3.7404845 | +| clip_fraction | 0.556 | +| clip_range | 0.2 | +| entropy_loss | -0.503 | +| explained_variance | -0.382 | +| learning_rate | 0.0001 | +| loss | -0.0694 | +| n_updates | 79550 | +| policy_gradient_loss | -0.0602 | +| value_loss | 0.000343 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.62e+03 | +| ep_rew_mean | 0.178 | +| time/ | | +| fps | 310 | +| iterations | 1904 | +| time_elapsed | 6274 | +| total_timesteps | 1949696 | +| train/ | | +| approx_kl | 1.5652964 | +| clip_fraction | 0.509 | +| clip_range | 0.2 | +| entropy_loss | -0.494 | +| explained_variance | -3.7 | +| learning_rate | 0.0001 | +| loss | -0.0875 | +| n_updates | 79560 | +| policy_gradient_loss | -0.0726 | +| value_loss | 0.000273 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.62e+03 | +| ep_rew_mean | 0.178 | +| time/ | | +| fps | 310 | +| iterations | 1905 | +| time_elapsed | 6277 | +| total_timesteps | 1950720 | +| train/ | | +| approx_kl | 1.6856918 | +| clip_fraction | 0.529 | +| clip_range | 0.2 | +| entropy_loss | -0.593 | +| explained_variance | -1.21 | +| learning_rate | 0.0001 | +| loss | -0.0888 | +| n_updates | 79570 | +| policy_gradient_loss | -0.0641 | +| value_loss | 0.000344 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.56e+03 | +| ep_rew_mean | 0.178 | +| time/ | | +| fps | 310 | +| iterations | 1906 | +| time_elapsed | 6280 | +| total_timesteps | 1951744 | +| train/ | | +| approx_kl | 1.9866608 | +| clip_fraction | 0.563 | +| clip_range | 0.2 | +| entropy_loss | -0.586 | +| explained_variance | -0.101 | +| learning_rate | 0.0001 | +| loss | -0.0819 | +| n_updates | 79580 | +| policy_gradient_loss | -0.0677 | +| value_loss | 0.000287 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.55e+03 | +| ep_rew_mean | 0.177 | +| time/ | | +| fps | 310 | +| iterations | 1907 | +| time_elapsed | 6284 | +| total_timesteps | 1952768 | +| train/ | | +| approx_kl | 2.140829 | +| clip_fraction | 0.545 | +| clip_range | 0.2 | +| entropy_loss | -0.519 | +| explained_variance | -1.82 | +| learning_rate | 0.0001 | +| loss | -0.0924 | +| n_updates | 79590 | +| policy_gradient_loss | -0.0667 | +| value_loss | 0.000444 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.55e+03 | +| ep_rew_mean | 0.177 | +| time/ | | +| fps | 310 | +| iterations | 1908 | +| time_elapsed | 6287 | +| total_timesteps | 1953792 | +| train/ | | +| approx_kl | 2.4339042 | +| clip_fraction | 0.518 | +| clip_range | 0.2 | +| entropy_loss | -0.455 | +| explained_variance | -0.445 | +| learning_rate | 0.0001 | +| loss | -0.0886 | +| n_updates | 79600 | +| policy_gradient_loss | -0.0623 | +| value_loss | 0.00037 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.55e+03 | +| ep_rew_mean | 0.177 | +| time/ | | +| fps | 310 | +| iterations | 1909 | +| time_elapsed | 6290 | +| total_timesteps | 1954816 | +| train/ | | +| approx_kl | 2.687819 | +| clip_fraction | 0.531 | +| clip_range | 0.2 | +| entropy_loss | -0.523 | +| explained_variance | -1.76 | +| learning_rate | 0.0001 | +| loss | -0.0795 | +| n_updates | 79610 | +| policy_gradient_loss | -0.0654 | +| value_loss | 0.000347 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.56e+03 | +| ep_rew_mean | 0.179 | +| time/ | | +| fps | 310 | +| iterations | 1910 | +| time_elapsed | 6294 | +| total_timesteps | 1955840 | +| train/ | | +| approx_kl | 3.588749 | +| clip_fraction | 0.55 | +| clip_range | 0.2 | +| entropy_loss | -0.533 | +| explained_variance | -5.7 | +| learning_rate | 0.0001 | +| loss | -0.0824 | +| n_updates | 79620 | +| policy_gradient_loss | -0.082 | +| value_loss | 0.000394 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.56e+03 | +| ep_rew_mean | 0.179 | +| time/ | | +| fps | 310 | +| iterations | 1911 | +| time_elapsed | 6297 | +| total_timesteps | 1956864 | +| train/ | | +| approx_kl | 1.7782817 | +| clip_fraction | 0.51 | +| clip_range | 0.2 | +| entropy_loss | -0.499 | +| explained_variance | -0.803 | +| learning_rate | 0.0001 | +| loss | -0.0879 | +| n_updates | 79630 | +| policy_gradient_loss | -0.0498 | +| value_loss | 0.000434 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.55e+03 | +| ep_rew_mean | 0.176 | +| time/ | | +| fps | 310 | +| iterations | 1912 | +| time_elapsed | 6300 | +| total_timesteps | 1957888 | +| train/ | | +| approx_kl | 1.1944685 | +| clip_fraction | 0.549 | +| clip_range | 0.2 | +| entropy_loss | -0.697 | +| explained_variance | -1.04 | +| learning_rate | 0.0001 | +| loss | -0.106 | +| n_updates | 79640 | +| policy_gradient_loss | -0.0627 | +| value_loss | 0.000244 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.55e+03 | +| ep_rew_mean | 0.176 | +| time/ | | +| fps | 310 | +| iterations | 1913 | +| time_elapsed | 6304 | +| total_timesteps | 1958912 | +| train/ | | +| approx_kl | 1.3811579 | +| clip_fraction | 0.512 | +| clip_range | 0.2 | +| entropy_loss | -0.518 | +| explained_variance | -2.4 | +| learning_rate | 0.0001 | +| loss | -0.0684 | +| n_updates | 79650 | +| policy_gradient_loss | -0.0632 | +| value_loss | 0.000232 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.55e+03 | +| ep_rew_mean | 0.176 | +| time/ | | +| fps | 310 | +| iterations | 1914 | +| time_elapsed | 6307 | +| total_timesteps | 1959936 | +| train/ | | +| approx_kl | 2.2796009 | +| clip_fraction | 0.584 | +| clip_range | 0.2 | +| entropy_loss | -0.555 | +| explained_variance | -1.77 | +| learning_rate | 0.0001 | +| loss | -0.0852 | +| n_updates | 79660 | +| policy_gradient_loss | -0.0716 | +| value_loss | 0.000264 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.57e+03 | +| ep_rew_mean | 0.181 | +| time/ | | +| fps | 310 | +| iterations | 1915 | +| time_elapsed | 6310 | +| total_timesteps | 1960960 | +| train/ | | +| approx_kl | 1.9675455 | +| clip_fraction | 0.581 | +| clip_range | 0.2 | +| entropy_loss | -0.543 | +| explained_variance | -5.37 | +| learning_rate | 0.0001 | +| loss | -0.0994 | +| n_updates | 79670 | +| policy_gradient_loss | -0.0694 | +| value_loss | 0.000242 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.57e+03 | +| ep_rew_mean | 0.181 | +| time/ | | +| fps | 310 | +| iterations | 1916 | +| time_elapsed | 6313 | +| total_timesteps | 1961984 | +| train/ | | +| approx_kl | 1.7981889 | +| clip_fraction | 0.541 | +| clip_range | 0.2 | +| entropy_loss | -0.501 | +| explained_variance | -0.565 | +| learning_rate | 0.0001 | +| loss | -0.0944 | +| n_updates | 79680 | +| policy_gradient_loss | -0.0711 | +| value_loss | 0.00031 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.57e+03 | +| ep_rew_mean | 0.181 | +| time/ | | +| fps | 310 | +| iterations | 1917 | +| time_elapsed | 6317 | +| total_timesteps | 1963008 | +| train/ | | +| approx_kl | 1.7173129 | +| clip_fraction | 0.531 | +| clip_range | 0.2 | +| entropy_loss | -0.459 | +| explained_variance | -2.01 | +| learning_rate | 0.0001 | +| loss | -0.0953 | +| n_updates | 79690 | +| policy_gradient_loss | -0.0663 | +| value_loss | 0.00043 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.57e+03 | +| ep_rew_mean | 0.181 | +| time/ | | +| fps | 310 | +| iterations | 1918 | +| time_elapsed | 6320 | +| total_timesteps | 1964032 | +| train/ | | +| approx_kl | 2.4164343 | +| clip_fraction | 0.539 | +| clip_range | 0.2 | +| entropy_loss | -0.519 | +| explained_variance | -0.789 | +| learning_rate | 0.0001 | +| loss | -0.0778 | +| n_updates | 79700 | +| policy_gradient_loss | -0.0706 | +| value_loss | 0.000663 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.57e+03 | +| ep_rew_mean | 0.181 | +| time/ | | +| fps | 310 | +| iterations | 1919 | +| time_elapsed | 6323 | +| total_timesteps | 1965056 | +| train/ | | +| approx_kl | 2.24992 | +| clip_fraction | 0.525 | +| clip_range | 0.2 | +| entropy_loss | -0.437 | +| explained_variance | -4.83 | +| learning_rate | 0.0001 | +| loss | -0.108 | +| n_updates | 79710 | +| policy_gradient_loss | -0.0717 | +| value_loss | 0.000445 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.57e+03 | +| ep_rew_mean | 0.181 | +| time/ | | +| fps | 310 | +| iterations | 1920 | +| time_elapsed | 6326 | +| total_timesteps | 1966080 | +| train/ | | +| approx_kl | 2.529017 | +| clip_fraction | 0.568 | +| clip_range | 0.2 | +| entropy_loss | -0.552 | +| explained_variance | -3.22 | +| learning_rate | 0.0001 | +| loss | -0.097 | +| n_updates | 79720 | +| policy_gradient_loss | -0.0745 | +| value_loss | 0.000236 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.58e+03 | +| ep_rew_mean | 0.181 | +| time/ | | +| fps | 310 | +| iterations | 1921 | +| time_elapsed | 6329 | +| total_timesteps | 1967104 | +| train/ | | +| approx_kl | 1.7804427 | +| clip_fraction | 0.542 | +| clip_range | 0.2 | +| entropy_loss | -0.586 | +| explained_variance | -0.614 | +| learning_rate | 0.0001 | +| loss | -0.0944 | +| n_updates | 79730 | +| policy_gradient_loss | -0.0729 | +| value_loss | 0.000491 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.58e+03 | +| ep_rew_mean | 0.181 | +| time/ | | +| fps | 310 | +| iterations | 1922 | +| time_elapsed | 6332 | +| total_timesteps | 1968128 | +| train/ | | +| approx_kl | 1.8800311 | +| clip_fraction | 0.525 | +| clip_range | 0.2 | +| entropy_loss | -0.579 | +| explained_variance | -13.1 | +| learning_rate | 0.0001 | +| loss | -0.105 | +| n_updates | 79740 | +| policy_gradient_loss | -0.0769 | +| value_loss | 0.000215 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.58e+03 | +| ep_rew_mean | 0.182 | +| time/ | | +| fps | 310 | +| iterations | 1923 | +| time_elapsed | 6335 | +| total_timesteps | 1969152 | +| train/ | | +| approx_kl | 3.0897162 | +| clip_fraction | 0.557 | +| clip_range | 0.2 | +| entropy_loss | -0.573 | +| explained_variance | -0.117 | +| learning_rate | 0.0001 | +| loss | -0.0909 | +| n_updates | 79750 | +| policy_gradient_loss | -0.0697 | +| value_loss | 0.000401 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.58e+03 | +| ep_rew_mean | 0.182 | +| time/ | | +| fps | 310 | +| iterations | 1924 | +| time_elapsed | 6339 | +| total_timesteps | 1970176 | +| train/ | | +| approx_kl | 2.2621303 | +| clip_fraction | 0.522 | +| clip_range | 0.2 | +| entropy_loss | -0.525 | +| explained_variance | -3.41 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 79760 | +| policy_gradient_loss | -0.065 | +| value_loss | 0.000242 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.58e+03 | +| ep_rew_mean | 0.182 | +| time/ | | +| fps | 310 | +| iterations | 1925 | +| time_elapsed | 6342 | +| total_timesteps | 1971200 | +| train/ | | +| approx_kl | 2.140899 | +| clip_fraction | 0.556 | +| clip_range | 0.2 | +| entropy_loss | -0.512 | +| explained_variance | -1 | +| learning_rate | 0.0001 | +| loss | -0.109 | +| n_updates | 79770 | +| policy_gradient_loss | -0.0714 | +| value_loss | 0.00062 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.58e+03 | +| ep_rew_mean | 0.185 | +| time/ | | +| fps | 310 | +| iterations | 1926 | +| time_elapsed | 6346 | +| total_timesteps | 1972224 | +| train/ | | +| approx_kl | 2.1139562 | +| clip_fraction | 0.533 | +| clip_range | 0.2 | +| entropy_loss | -0.495 | +| explained_variance | -1.85 | +| learning_rate | 0.0001 | +| loss | -0.0425 | +| n_updates | 79780 | +| policy_gradient_loss | -0.0655 | +| value_loss | 0.000465 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.58e+03 | +| ep_rew_mean | 0.185 | +| time/ | | +| fps | 310 | +| iterations | 1927 | +| time_elapsed | 6349 | +| total_timesteps | 1973248 | +| train/ | | +| approx_kl | 2.2781644 | +| clip_fraction | 0.554 | +| clip_range | 0.2 | +| entropy_loss | -0.485 | +| explained_variance | -1.54 | +| learning_rate | 0.0001 | +| loss | -0.105 | +| n_updates | 79790 | +| policy_gradient_loss | -0.0699 | +| value_loss | 0.000836 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.58e+03 | +| ep_rew_mean | 0.185 | +| time/ | | +| fps | 310 | +| iterations | 1928 | +| time_elapsed | 6353 | +| total_timesteps | 1974272 | +| train/ | | +| approx_kl | 1.7615983 | +| clip_fraction | 0.551 | +| clip_range | 0.2 | +| entropy_loss | -0.573 | +| explained_variance | -1.02 | +| learning_rate | 0.0001 | +| loss | -0.0823 | +| n_updates | 79800 | +| policy_gradient_loss | -0.0616 | +| value_loss | 0.000599 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.58e+03 | +| ep_rew_mean | 0.187 | +| time/ | | +| fps | 310 | +| iterations | 1929 | +| time_elapsed | 6356 | +| total_timesteps | 1975296 | +| train/ | | +| approx_kl | 2.2912211 | +| clip_fraction | 0.534 | +| clip_range | 0.2 | +| entropy_loss | -0.469 | +| explained_variance | -4.91 | +| learning_rate | 0.0001 | +| loss | -0.0959 | +| n_updates | 79810 | +| policy_gradient_loss | -0.0718 | +| value_loss | 0.000265 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.58e+03 | +| ep_rew_mean | 0.187 | +| time/ | | +| fps | 310 | +| iterations | 1930 | +| time_elapsed | 6360 | +| total_timesteps | 1976320 | +| train/ | | +| approx_kl | 2.3001475 | +| clip_fraction | 0.523 | +| clip_range | 0.2 | +| entropy_loss | -0.406 | +| explained_variance | -2.29 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 79820 | +| policy_gradient_loss | -0.0759 | +| value_loss | 0.000226 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.59e+03 | +| ep_rew_mean | 0.187 | +| time/ | | +| fps | 310 | +| iterations | 1931 | +| time_elapsed | 6364 | +| total_timesteps | 1977344 | +| train/ | | +| approx_kl | 2.4779043 | +| clip_fraction | 0.521 | +| clip_range | 0.2 | +| entropy_loss | -0.426 | +| explained_variance | -0.31 | +| learning_rate | 0.0001 | +| loss | -0.0911 | +| n_updates | 79830 | +| policy_gradient_loss | -0.0634 | +| value_loss | 0.000487 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.59e+03 | +| ep_rew_mean | 0.187 | +| time/ | | +| fps | 310 | +| iterations | 1932 | +| time_elapsed | 6367 | +| total_timesteps | 1978368 | +| train/ | | +| approx_kl | 2.8808162 | +| clip_fraction | 0.531 | +| clip_range | 0.2 | +| entropy_loss | -0.465 | +| explained_variance | -2.01 | +| learning_rate | 0.0001 | +| loss | -0.0849 | +| n_updates | 79840 | +| policy_gradient_loss | -0.071 | +| value_loss | 0.000474 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.59e+03 | +| ep_rew_mean | 0.187 | +| time/ | | +| fps | 310 | +| iterations | 1933 | +| time_elapsed | 6370 | +| total_timesteps | 1979392 | +| train/ | | +| approx_kl | 1.9177938 | +| clip_fraction | 0.537 | +| clip_range | 0.2 | +| entropy_loss | -0.503 | +| explained_variance | -0.952 | +| learning_rate | 0.0001 | +| loss | -0.0764 | +| n_updates | 79850 | +| policy_gradient_loss | -0.075 | +| value_loss | 0.000305 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.59e+03 | +| ep_rew_mean | 0.189 | +| time/ | | +| fps | 310 | +| iterations | 1934 | +| time_elapsed | 6374 | +| total_timesteps | 1980416 | +| train/ | | +| approx_kl | 2.2132382 | +| clip_fraction | 0.534 | +| clip_range | 0.2 | +| entropy_loss | -0.452 | +| explained_variance | -1.43 | +| learning_rate | 0.0001 | +| loss | -0.0725 | +| n_updates | 79860 | +| policy_gradient_loss | -0.0681 | +| value_loss | 0.000357 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.59e+03 | +| ep_rew_mean | 0.189 | +| time/ | | +| fps | 310 | +| iterations | 1935 | +| time_elapsed | 6377 | +| total_timesteps | 1981440 | +| train/ | | +| approx_kl | 2.0259914 | +| clip_fraction | 0.517 | +| clip_range | 0.2 | +| entropy_loss | -0.444 | +| explained_variance | -1.14 | +| learning_rate | 0.0001 | +| loss | -0.00365 | +| n_updates | 79870 | +| policy_gradient_loss | -0.0548 | +| value_loss | 0.000467 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.6e+03 | +| ep_rew_mean | 0.187 | +| time/ | | +| fps | 310 | +| iterations | 1936 | +| time_elapsed | 6380 | +| total_timesteps | 1982464 | +| train/ | | +| approx_kl | 2.3287442 | +| clip_fraction | 0.533 | +| clip_range | 0.2 | +| entropy_loss | -0.467 | +| explained_variance | -1.5 | +| learning_rate | 0.0001 | +| loss | -0.109 | +| n_updates | 79880 | +| policy_gradient_loss | -0.06 | +| value_loss | 0.000597 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.6e+03 | +| ep_rew_mean | 0.187 | +| time/ | | +| fps | 310 | +| iterations | 1937 | +| time_elapsed | 6383 | +| total_timesteps | 1983488 | +| train/ | | +| approx_kl | 2.1150131 | +| clip_fraction | 0.514 | +| clip_range | 0.2 | +| entropy_loss | -0.456 | +| explained_variance | -1.79 | +| learning_rate | 0.0001 | +| loss | -0.044 | +| n_updates | 79890 | +| policy_gradient_loss | -0.058 | +| value_loss | 0.00077 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.59e+03 | +| ep_rew_mean | 0.187 | +| time/ | | +| fps | 310 | +| iterations | 1938 | +| time_elapsed | 6386 | +| total_timesteps | 1984512 | +| train/ | | +| approx_kl | 2.1959462 | +| clip_fraction | 0.527 | +| clip_range | 0.2 | +| entropy_loss | -0.426 | +| explained_variance | -6.35 | +| learning_rate | 0.0001 | +| loss | -0.0933 | +| n_updates | 79900 | +| policy_gradient_loss | -0.071 | +| value_loss | 0.00048 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.59e+03 | +| ep_rew_mean | 0.187 | +| time/ | | +| fps | 310 | +| iterations | 1939 | +| time_elapsed | 6390 | +| total_timesteps | 1985536 | +| train/ | | +| approx_kl | 2.0868511 | +| clip_fraction | 0.496 | +| clip_range | 0.2 | +| entropy_loss | -0.536 | +| explained_variance | -0.401 | +| learning_rate | 0.0001 | +| loss | -0.0752 | +| n_updates | 79910 | +| policy_gradient_loss | -0.0663 | +| value_loss | 0.00033 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.59e+03 | +| ep_rew_mean | 0.192 | +| time/ | | +| fps | 310 | +| iterations | 1940 | +| time_elapsed | 6393 | +| total_timesteps | 1986560 | +| train/ | | +| approx_kl | 2.6646714 | +| clip_fraction | 0.526 | +| clip_range | 0.2 | +| entropy_loss | -0.397 | +| explained_variance | -1.15 | +| learning_rate | 0.0001 | +| loss | -0.0827 | +| n_updates | 79920 | +| policy_gradient_loss | -0.0687 | +| value_loss | 0.000311 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.59e+03 | +| ep_rew_mean | 0.192 | +| time/ | | +| fps | 310 | +| iterations | 1941 | +| time_elapsed | 6396 | +| total_timesteps | 1987584 | +| train/ | | +| approx_kl | 2.3602736 | +| clip_fraction | 0.533 | +| clip_range | 0.2 | +| entropy_loss | -0.48 | +| explained_variance | -1.66 | +| learning_rate | 0.0001 | +| loss | -0.0607 | +| n_updates | 79930 | +| policy_gradient_loss | -0.0608 | +| value_loss | 0.000485 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.59e+03 | +| ep_rew_mean | 0.195 | +| time/ | | +| fps | 310 | +| iterations | 1942 | +| time_elapsed | 6399 | +| total_timesteps | 1988608 | +| train/ | | +| approx_kl | 2.057013 | +| clip_fraction | 0.509 | +| clip_range | 0.2 | +| entropy_loss | -0.439 | +| explained_variance | -2.69 | +| learning_rate | 0.0001 | +| loss | -0.0901 | +| n_updates | 79940 | +| policy_gradient_loss | -0.068 | +| value_loss | 0.000467 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.59e+03 | +| ep_rew_mean | 0.194 | +| time/ | | +| fps | 310 | +| iterations | 1943 | +| time_elapsed | 6403 | +| total_timesteps | 1989632 | +| train/ | | +| approx_kl | 1.7343733 | +| clip_fraction | 0.518 | +| clip_range | 0.2 | +| entropy_loss | -0.477 | +| explained_variance | -3.08 | +| learning_rate | 0.0001 | +| loss | -0.11 | +| n_updates | 79950 | +| policy_gradient_loss | -0.067 | +| value_loss | 0.000358 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.59e+03 | +| ep_rew_mean | 0.194 | +| time/ | | +| fps | 310 | +| iterations | 1944 | +| time_elapsed | 6406 | +| total_timesteps | 1990656 | +| train/ | | +| approx_kl | 2.8168993 | +| clip_fraction | 0.492 | +| clip_range | 0.2 | +| entropy_loss | -0.419 | +| explained_variance | -1.34 | +| learning_rate | 0.0001 | +| loss | -0.115 | +| n_updates | 79960 | +| policy_gradient_loss | -0.0642 | +| value_loss | 0.000237 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.59e+03 | +| ep_rew_mean | 0.195 | +| time/ | | +| fps | 310 | +| iterations | 1945 | +| time_elapsed | 6409 | +| total_timesteps | 1991680 | +| train/ | | +| approx_kl | 2.0796657 | +| clip_fraction | 0.504 | +| clip_range | 0.2 | +| entropy_loss | -0.447 | +| explained_variance | -0.622 | +| learning_rate | 0.0001 | +| loss | -0.0827 | +| n_updates | 79970 | +| policy_gradient_loss | -0.0625 | +| value_loss | 0.000389 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.59e+03 | +| ep_rew_mean | 0.195 | +| time/ | | +| fps | 310 | +| iterations | 1946 | +| time_elapsed | 6413 | +| total_timesteps | 1992704 | +| train/ | | +| approx_kl | 2.1222088 | +| clip_fraction | 0.529 | +| clip_range | 0.2 | +| entropy_loss | -0.421 | +| explained_variance | -0.919 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 79980 | +| policy_gradient_loss | -0.0689 | +| value_loss | 0.00041 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.59e+03 | +| ep_rew_mean | 0.195 | +| time/ | | +| fps | 310 | +| iterations | 1947 | +| time_elapsed | 6416 | +| total_timesteps | 1993728 | +| train/ | | +| approx_kl | 1.9023938 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.442 | +| explained_variance | -4.65 | +| learning_rate | 0.0001 | +| loss | -0.0912 | +| n_updates | 79990 | +| policy_gradient_loss | -0.0684 | +| value_loss | 0.000262 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.59e+03 | +| ep_rew_mean | 0.195 | +| time/ | | +| fps | 310 | +| iterations | 1948 | +| time_elapsed | 6420 | +| total_timesteps | 1994752 | +| train/ | | +| approx_kl | 1.7745525 | +| clip_fraction | 0.479 | +| clip_range | 0.2 | +| entropy_loss | -0.416 | +| explained_variance | -1.81 | +| learning_rate | 0.0001 | +| loss | -0.057 | +| n_updates | 80000 | +| policy_gradient_loss | -0.0609 | +| value_loss | 0.000419 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.59e+03 | +| ep_rew_mean | 0.195 | +| time/ | | +| fps | 310 | +| iterations | 1949 | +| time_elapsed | 6423 | +| total_timesteps | 1995776 | +| train/ | | +| approx_kl | 2.1626205 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.37 | +| explained_variance | -1.18 | +| learning_rate | 0.0001 | +| loss | -0.0906 | +| n_updates | 80010 | +| policy_gradient_loss | -0.0675 | +| value_loss | 0.000627 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.59e+03 | +| ep_rew_mean | 0.195 | +| time/ | | +| fps | 310 | +| iterations | 1950 | +| time_elapsed | 6427 | +| total_timesteps | 1996800 | +| train/ | | +| approx_kl | 1.5747371 | +| clip_fraction | 0.534 | +| clip_range | 0.2 | +| entropy_loss | -0.552 | +| explained_variance | -1.05 | +| learning_rate | 0.0001 | +| loss | -0.0938 | +| n_updates | 80020 | +| policy_gradient_loss | -0.069 | +| value_loss | 0.000297 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.59e+03 | +| ep_rew_mean | 0.195 | +| time/ | | +| fps | 310 | +| iterations | 1951 | +| time_elapsed | 6430 | +| total_timesteps | 1997824 | +| train/ | | +| approx_kl | 1.6040006 | +| clip_fraction | 0.497 | +| clip_range | 0.2 | +| entropy_loss | -0.651 | +| explained_variance | -0.171 | +| learning_rate | 0.0001 | +| loss | -0.0387 | +| n_updates | 80030 | +| policy_gradient_loss | -0.0371 | +| value_loss | 0.000941 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.59e+03 | +| ep_rew_mean | 0.195 | +| time/ | | +| fps | 310 | +| iterations | 1952 | +| time_elapsed | 6433 | +| total_timesteps | 1998848 | +| train/ | | +| approx_kl | 3.8298683 | +| clip_fraction | 0.528 | +| clip_range | 0.2 | +| entropy_loss | -0.445 | +| explained_variance | -3.52 | +| learning_rate | 0.0001 | +| loss | -0.0882 | +| n_updates | 80040 | +| policy_gradient_loss | -0.0649 | +| value_loss | 0.000672 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.64e+03 | +| ep_rew_mean | 0.196 | +| time/ | | +| fps | 310 | +| iterations | 1953 | +| time_elapsed | 6436 | +| total_timesteps | 1999872 | +| train/ | | +| approx_kl | 2.272878 | +| clip_fraction | 0.535 | +| clip_range | 0.2 | +| entropy_loss | -0.437 | +| explained_variance | -1.44 | +| learning_rate | 0.0001 | +| loss | -0.116 | +| n_updates | 80050 | +| policy_gradient_loss | -0.0599 | +| value_loss | 0.000567 | +-------------------------------------- + +Current state: Champion.Level6.RyuVsRyu +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.63e+03 | +| ep_rew_mean | 0.196 | +| time/ | | +| fps | 310 | +| iterations | 1954 | +| time_elapsed | 6439 | +| total_timesteps | 2000896 | +| train/ | | +| approx_kl | 1.7932973 | +| clip_fraction | 0.484 | +| clip_range | 0.2 | +| entropy_loss | -0.41 | +| explained_variance | -3.81 | +| learning_rate | 0.0001 | +| loss | -0.0891 | +| n_updates | 80060 | +| policy_gradient_loss | -0.0622 | +| value_loss | 0.000283 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.63e+03 | +| ep_rew_mean | 0.196 | +| time/ | | +| fps | 310 | +| iterations | 1955 | +| time_elapsed | 6443 | +| total_timesteps | 2001920 | +| train/ | | +| approx_kl | 2.0726712 | +| clip_fraction | 0.545 | +| clip_range | 0.2 | +| entropy_loss | -0.541 | +| explained_variance | -0.444 | +| learning_rate | 0.0001 | +| loss | -0.0694 | +| n_updates | 80070 | +| policy_gradient_loss | -0.0628 | +| value_loss | 0.000554 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.62e+03 | +| ep_rew_mean | 0.193 | +| time/ | | +| fps | 310 | +| iterations | 1956 | +| time_elapsed | 6446 | +| total_timesteps | 2002944 | +| train/ | | +| approx_kl | 2.6082387 | +| clip_fraction | 0.517 | +| clip_range | 0.2 | +| entropy_loss | -0.594 | +| explained_variance | -8.92 | +| learning_rate | 0.0001 | +| loss | -0.0755 | +| n_updates | 80080 | +| policy_gradient_loss | -0.0706 | +| value_loss | 0.000939 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.62e+03 | +| ep_rew_mean | 0.193 | +| time/ | | +| fps | 310 | +| iterations | 1957 | +| time_elapsed | 6449 | +| total_timesteps | 2003968 | +| train/ | | +| approx_kl | 1.9268177 | +| clip_fraction | 0.496 | +| clip_range | 0.2 | +| entropy_loss | -0.537 | +| explained_variance | -3.24 | +| learning_rate | 0.0001 | +| loss | -0.0551 | +| n_updates | 80090 | +| policy_gradient_loss | -0.0654 | +| value_loss | 0.00132 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.61e+03 | +| ep_rew_mean | 0.19 | +| time/ | | +| fps | 310 | +| iterations | 1958 | +| time_elapsed | 6452 | +| total_timesteps | 2004992 | +| train/ | | +| approx_kl | 1.6541767 | +| clip_fraction | 0.518 | +| clip_range | 0.2 | +| entropy_loss | -0.594 | +| explained_variance | -2.97 | +| learning_rate | 0.0001 | +| loss | -0.0507 | +| n_updates | 80100 | +| policy_gradient_loss | -0.0632 | +| value_loss | 0.00107 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.6e+03 | +| ep_rew_mean | 0.184 | +| time/ | | +| fps | 310 | +| iterations | 1959 | +| time_elapsed | 6455 | +| total_timesteps | 2006016 | +| train/ | | +| approx_kl | 1.3783591 | +| clip_fraction | 0.513 | +| clip_range | 0.2 | +| entropy_loss | -0.638 | +| explained_variance | -5.9 | +| learning_rate | 0.0001 | +| loss | -0.109 | +| n_updates | 80110 | +| policy_gradient_loss | -0.0698 | +| value_loss | 0.000444 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.6e+03 | +| ep_rew_mean | 0.18 | +| time/ | | +| fps | 310 | +| iterations | 1960 | +| time_elapsed | 6458 | +| total_timesteps | 2007040 | +| train/ | | +| approx_kl | 1.5389798 | +| clip_fraction | 0.461 | +| clip_range | 0.2 | +| entropy_loss | -0.494 | +| explained_variance | -2.8 | +| learning_rate | 0.0001 | +| loss | -0.0513 | +| n_updates | 80120 | +| policy_gradient_loss | -0.0573 | +| value_loss | 0.000621 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.58e+03 | +| ep_rew_mean | 0.176 | +| time/ | | +| fps | 310 | +| iterations | 1961 | +| time_elapsed | 6462 | +| total_timesteps | 2008064 | +| train/ | | +| approx_kl | 1.3756583 | +| clip_fraction | 0.45 | +| clip_range | 0.2 | +| entropy_loss | -0.464 | +| explained_variance | -2.17 | +| learning_rate | 0.0001 | +| loss | -0.0537 | +| n_updates | 80130 | +| policy_gradient_loss | -0.0471 | +| value_loss | 0.000465 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.58e+03 | +| ep_rew_mean | 0.176 | +| time/ | | +| fps | 310 | +| iterations | 1962 | +| time_elapsed | 6465 | +| total_timesteps | 2009088 | +| train/ | | +| approx_kl | 1.3878314 | +| clip_fraction | 0.461 | +| clip_range | 0.2 | +| entropy_loss | -0.45 | +| explained_variance | -1.07 | +| learning_rate | 0.0001 | +| loss | -0.0962 | +| n_updates | 80140 | +| policy_gradient_loss | -0.0555 | +| value_loss | 0.000547 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.57e+03 | +| ep_rew_mean | 0.171 | +| time/ | | +| fps | 310 | +| iterations | 1963 | +| time_elapsed | 6469 | +| total_timesteps | 2010112 | +| train/ | | +| approx_kl | 1.1994183 | +| clip_fraction | 0.494 | +| clip_range | 0.2 | +| entropy_loss | -0.529 | +| explained_variance | -2.47 | +| learning_rate | 0.0001 | +| loss | -0.063 | +| n_updates | 80150 | +| policy_gradient_loss | -0.0597 | +| value_loss | 0.000496 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.56e+03 | +| ep_rew_mean | 0.164 | +| time/ | | +| fps | 310 | +| iterations | 1964 | +| time_elapsed | 6472 | +| total_timesteps | 2011136 | +| train/ | | +| approx_kl | 1.3366826 | +| clip_fraction | 0.491 | +| clip_range | 0.2 | +| entropy_loss | -0.49 | +| explained_variance | -5.83 | +| learning_rate | 0.0001 | +| loss | -0.0948 | +| n_updates | 80160 | +| policy_gradient_loss | -0.0683 | +| value_loss | 0.000494 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.56e+03 | +| ep_rew_mean | 0.164 | +| time/ | | +| fps | 310 | +| iterations | 1965 | +| time_elapsed | 6476 | +| total_timesteps | 2012160 | +| train/ | | +| approx_kl | 1.3396235 | +| clip_fraction | 0.489 | +| clip_range | 0.2 | +| entropy_loss | -0.518 | +| explained_variance | -0.694 | +| learning_rate | 0.0001 | +| loss | -0.0803 | +| n_updates | 80170 | +| policy_gradient_loss | -0.0573 | +| value_loss | 0.000551 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.55e+03 | +| ep_rew_mean | 0.158 | +| time/ | | +| fps | 310 | +| iterations | 1966 | +| time_elapsed | 6479 | +| total_timesteps | 2013184 | +| train/ | | +| approx_kl | 1.2620751 | +| clip_fraction | 0.527 | +| clip_range | 0.2 | +| entropy_loss | -0.621 | +| explained_variance | -7.48 | +| learning_rate | 0.0001 | +| loss | -0.0652 | +| n_updates | 80180 | +| policy_gradient_loss | -0.0671 | +| value_loss | 0.00052 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.54e+03 | +| ep_rew_mean | 0.156 | +| time/ | | +| fps | 310 | +| iterations | 1967 | +| time_elapsed | 6483 | +| total_timesteps | 2014208 | +| train/ | | +| approx_kl | 1.4246237 | +| clip_fraction | 0.494 | +| clip_range | 0.2 | +| entropy_loss | -0.552 | +| explained_variance | -4.88 | +| learning_rate | 0.0001 | +| loss | -0.064 | +| n_updates | 80190 | +| policy_gradient_loss | -0.0579 | +| value_loss | 0.000628 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.54e+03 | +| ep_rew_mean | 0.156 | +| time/ | | +| fps | 310 | +| iterations | 1968 | +| time_elapsed | 6486 | +| total_timesteps | 2015232 | +| train/ | | +| approx_kl | 1.3831172 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.569 | +| explained_variance | -3.43 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 80200 | +| policy_gradient_loss | -0.0597 | +| value_loss | 0.000554 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.54e+03 | +| ep_rew_mean | 0.156 | +| time/ | | +| fps | 310 | +| iterations | 1969 | +| time_elapsed | 6490 | +| total_timesteps | 2016256 | +| train/ | | +| approx_kl | 1.6793869 | +| clip_fraction | 0.516 | +| clip_range | 0.2 | +| entropy_loss | -0.534 | +| explained_variance | -2.58 | +| learning_rate | 0.0001 | +| loss | -0.0869 | +| n_updates | 80210 | +| policy_gradient_loss | -0.0641 | +| value_loss | 0.000486 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.54e+03 | +| ep_rew_mean | 0.158 | +| time/ | | +| fps | 310 | +| iterations | 1970 | +| time_elapsed | 6493 | +| total_timesteps | 2017280 | +| train/ | | +| approx_kl | 1.7252314 | +| clip_fraction | 0.545 | +| clip_range | 0.2 | +| entropy_loss | -0.694 | +| explained_variance | -2.75 | +| learning_rate | 0.0001 | +| loss | -0.0862 | +| n_updates | 80220 | +| policy_gradient_loss | -0.0641 | +| value_loss | 0.00071 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.52e+03 | +| ep_rew_mean | 0.151 | +| time/ | | +| fps | 310 | +| iterations | 1971 | +| time_elapsed | 6496 | +| total_timesteps | 2018304 | +| train/ | | +| approx_kl | 1.110959 | +| clip_fraction | 0.492 | +| clip_range | 0.2 | +| entropy_loss | -0.61 | +| explained_variance | -3.68 | +| learning_rate | 0.0001 | +| loss | -0.0884 | +| n_updates | 80230 | +| policy_gradient_loss | -0.0614 | +| value_loss | 0.000492 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.52e+03 | +| ep_rew_mean | 0.151 | +| time/ | | +| fps | 310 | +| iterations | 1972 | +| time_elapsed | 6499 | +| total_timesteps | 2019328 | +| train/ | | +| approx_kl | 1.8846458 | +| clip_fraction | 0.454 | +| clip_range | 0.2 | +| entropy_loss | -0.463 | +| explained_variance | -1.02 | +| learning_rate | 0.0001 | +| loss | -0.0612 | +| n_updates | 80240 | +| policy_gradient_loss | -0.0574 | +| value_loss | 0.000436 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.51e+03 | +| ep_rew_mean | 0.145 | +| time/ | | +| fps | 310 | +| iterations | 1973 | +| time_elapsed | 6502 | +| total_timesteps | 2020352 | +| train/ | | +| approx_kl | 1.2689114 | +| clip_fraction | 0.503 | +| clip_range | 0.2 | +| entropy_loss | -0.558 | +| explained_variance | -4.06 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 80250 | +| policy_gradient_loss | -0.0692 | +| value_loss | 0.000424 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.51e+03 | +| ep_rew_mean | 0.145 | +| time/ | | +| fps | 310 | +| iterations | 1974 | +| time_elapsed | 6506 | +| total_timesteps | 2021376 | +| train/ | | +| approx_kl | 1.3639015 | +| clip_fraction | 0.562 | +| clip_range | 0.2 | +| entropy_loss | -0.773 | +| explained_variance | -0.499 | +| learning_rate | 0.0001 | +| loss | -0.109 | +| n_updates | 80260 | +| policy_gradient_loss | -0.0709 | +| value_loss | 0.000563 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.5e+03 | +| ep_rew_mean | 0.146 | +| time/ | | +| fps | 310 | +| iterations | 1975 | +| time_elapsed | 6509 | +| total_timesteps | 2022400 | +| train/ | | +| approx_kl | 2.2125268 | +| clip_fraction | 0.521 | +| clip_range | 0.2 | +| entropy_loss | -0.527 | +| explained_variance | -1.92 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 80270 | +| policy_gradient_loss | -0.0734 | +| value_loss | 0.000538 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.5e+03 | +| ep_rew_mean | 0.146 | +| time/ | | +| fps | 310 | +| iterations | 1976 | +| time_elapsed | 6512 | +| total_timesteps | 2023424 | +| train/ | | +| approx_kl | 1.4825948 | +| clip_fraction | 0.464 | +| clip_range | 0.2 | +| entropy_loss | -0.484 | +| explained_variance | -2.8 | +| learning_rate | 0.0001 | +| loss | -0.067 | +| n_updates | 80280 | +| policy_gradient_loss | -0.06 | +| value_loss | 0.000385 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.5e+03 | +| ep_rew_mean | 0.139 | +| time/ | | +| fps | 310 | +| iterations | 1977 | +| time_elapsed | 6515 | +| total_timesteps | 2024448 | +| train/ | | +| approx_kl | 2.8018067 | +| clip_fraction | 0.5 | +| clip_range | 0.2 | +| entropy_loss | -0.527 | +| explained_variance | -4.92 | +| learning_rate | 0.0001 | +| loss | -0.0716 | +| n_updates | 80290 | +| policy_gradient_loss | -0.0542 | +| value_loss | 0.000197 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.5e+03 | +| ep_rew_mean | 0.134 | +| time/ | | +| fps | 310 | +| iterations | 1978 | +| time_elapsed | 6518 | +| total_timesteps | 2025472 | +| train/ | | +| approx_kl | 1.2877314 | +| clip_fraction | 0.492 | +| clip_range | 0.2 | +| entropy_loss | -0.495 | +| explained_variance | -1.2 | +| learning_rate | 0.0001 | +| loss | -0.086 | +| n_updates | 80300 | +| policy_gradient_loss | -0.0635 | +| value_loss | 0.000464 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.49e+03 | +| ep_rew_mean | 0.13 | +| time/ | | +| fps | 310 | +| iterations | 1979 | +| time_elapsed | 6522 | +| total_timesteps | 2026496 | +| train/ | | +| approx_kl | 1.2688339 | +| clip_fraction | 0.445 | +| clip_range | 0.2 | +| entropy_loss | -0.436 | +| explained_variance | -1.7 | +| learning_rate | 0.0001 | +| loss | -0.0344 | +| n_updates | 80310 | +| policy_gradient_loss | -0.0582 | +| value_loss | 0.000368 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.49e+03 | +| ep_rew_mean | 0.13 | +| time/ | | +| fps | 310 | +| iterations | 1980 | +| time_elapsed | 6525 | +| total_timesteps | 2027520 | +| train/ | | +| approx_kl | 1.3342162 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.478 | +| explained_variance | -4.43 | +| learning_rate | 0.0001 | +| loss | -0.0976 | +| n_updates | 80320 | +| policy_gradient_loss | -0.0566 | +| value_loss | 0.000578 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.42e+03 | +| ep_rew_mean | 0.128 | +| time/ | | +| fps | 310 | +| iterations | 1981 | +| time_elapsed | 6529 | +| total_timesteps | 2028544 | +| train/ | | +| approx_kl | 1.1531323 | +| clip_fraction | 0.452 | +| clip_range | 0.2 | +| entropy_loss | -0.488 | +| explained_variance | -4.81 | +| learning_rate | 0.0001 | +| loss | -0.0755 | +| n_updates | 80330 | +| policy_gradient_loss | -0.0521 | +| value_loss | 0.00065 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.43e+03 | +| ep_rew_mean | 0.125 | +| time/ | | +| fps | 310 | +| iterations | 1982 | +| time_elapsed | 6532 | +| total_timesteps | 2029568 | +| train/ | | +| approx_kl | 1.7303064 | +| clip_fraction | 0.503 | +| clip_range | 0.2 | +| entropy_loss | -0.599 | +| explained_variance | -6.05 | +| learning_rate | 0.0001 | +| loss | -0.0611 | +| n_updates | 80340 | +| policy_gradient_loss | -0.0583 | +| value_loss | 0.000559 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.43e+03 | +| ep_rew_mean | 0.125 | +| time/ | | +| fps | 310 | +| iterations | 1983 | +| time_elapsed | 6535 | +| total_timesteps | 2030592 | +| train/ | | +| approx_kl | 1.5637798 | +| clip_fraction | 0.521 | +| clip_range | 0.2 | +| entropy_loss | -0.618 | +| explained_variance | -2.59 | +| learning_rate | 0.0001 | +| loss | -0.0486 | +| n_updates | 80350 | +| policy_gradient_loss | -0.0676 | +| value_loss | 0.000454 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.42e+03 | +| ep_rew_mean | 0.122 | +| time/ | | +| fps | 310 | +| iterations | 1984 | +| time_elapsed | 6538 | +| total_timesteps | 2031616 | +| train/ | | +| approx_kl | 1.7232099 | +| clip_fraction | 0.524 | +| clip_range | 0.2 | +| entropy_loss | -0.588 | +| explained_variance | -2.79 | +| learning_rate | 0.0001 | +| loss | -0.0679 | +| n_updates | 80360 | +| policy_gradient_loss | -0.0634 | +| value_loss | 0.000664 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.42e+03 | +| ep_rew_mean | 0.122 | +| time/ | | +| fps | 310 | +| iterations | 1985 | +| time_elapsed | 6542 | +| total_timesteps | 2032640 | +| train/ | | +| approx_kl | 1.5569216 | +| clip_fraction | 0.51 | +| clip_range | 0.2 | +| entropy_loss | -0.53 | +| explained_variance | -8.18 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 80370 | +| policy_gradient_loss | -0.0721 | +| value_loss | 0.00059 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.41e+03 | +| ep_rew_mean | 0.121 | +| time/ | | +| fps | 310 | +| iterations | 1986 | +| time_elapsed | 6545 | +| total_timesteps | 2033664 | +| train/ | | +| approx_kl | 1.4180038 | +| clip_fraction | 0.445 | +| clip_range | 0.2 | +| entropy_loss | -0.414 | +| explained_variance | -5.74 | +| learning_rate | 0.0001 | +| loss | -0.0905 | +| n_updates | 80380 | +| policy_gradient_loss | -0.0577 | +| value_loss | 0.000348 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.4e+03 | +| ep_rew_mean | 0.118 | +| time/ | | +| fps | 310 | +| iterations | 1987 | +| time_elapsed | 6549 | +| total_timesteps | 2034688 | +| train/ | | +| approx_kl | 1.7587807 | +| clip_fraction | 0.501 | +| clip_range | 0.2 | +| entropy_loss | -0.513 | +| explained_variance | -2.11 | +| learning_rate | 0.0001 | +| loss | -0.0838 | +| n_updates | 80390 | +| policy_gradient_loss | -0.0583 | +| value_loss | 0.000573 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.4e+03 | +| ep_rew_mean | 0.118 | +| time/ | | +| fps | 310 | +| iterations | 1988 | +| time_elapsed | 6552 | +| total_timesteps | 2035712 | +| train/ | | +| approx_kl | 1.3887787 | +| clip_fraction | 0.473 | +| clip_range | 0.2 | +| entropy_loss | -0.485 | +| explained_variance | -2.85 | +| learning_rate | 0.0001 | +| loss | -0.0599 | +| n_updates | 80400 | +| policy_gradient_loss | -0.0577 | +| value_loss | 0.000397 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.39e+03 | +| ep_rew_mean | 0.116 | +| time/ | | +| fps | 310 | +| iterations | 1989 | +| time_elapsed | 6555 | +| total_timesteps | 2036736 | +| train/ | | +| approx_kl | 1.2634149 | +| clip_fraction | 0.522 | +| clip_range | 0.2 | +| entropy_loss | -0.636 | +| explained_variance | -1.03 | +| learning_rate | 0.0001 | +| loss | -0.0927 | +| n_updates | 80410 | +| policy_gradient_loss | -0.0649 | +| value_loss | 0.000396 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.38e+03 | +| ep_rew_mean | 0.117 | +| time/ | | +| fps | 310 | +| iterations | 1990 | +| time_elapsed | 6558 | +| total_timesteps | 2037760 | +| train/ | | +| approx_kl | 1.61762 | +| clip_fraction | 0.479 | +| clip_range | 0.2 | +| entropy_loss | -0.484 | +| explained_variance | -3.63 | +| learning_rate | 0.0001 | +| loss | -0.0868 | +| n_updates | 80420 | +| policy_gradient_loss | -0.0615 | +| value_loss | 0.000404 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.38e+03 | +| ep_rew_mean | 0.117 | +| time/ | | +| fps | 310 | +| iterations | 1991 | +| time_elapsed | 6561 | +| total_timesteps | 2038784 | +| train/ | | +| approx_kl | 1.5045707 | +| clip_fraction | 0.443 | +| clip_range | 0.2 | +| entropy_loss | -0.456 | +| explained_variance | -2.11 | +| learning_rate | 0.0001 | +| loss | -0.0877 | +| n_updates | 80430 | +| policy_gradient_loss | -0.0562 | +| value_loss | 0.000582 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.37e+03 | +| ep_rew_mean | 0.118 | +| time/ | | +| fps | 310 | +| iterations | 1992 | +| time_elapsed | 6564 | +| total_timesteps | 2039808 | +| train/ | | +| approx_kl | 2.3100572 | +| clip_fraction | 0.509 | +| clip_range | 0.2 | +| entropy_loss | -0.55 | +| explained_variance | -3.75 | +| learning_rate | 0.0001 | +| loss | -0.0771 | +| n_updates | 80440 | +| policy_gradient_loss | -0.0692 | +| value_loss | 0.000518 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.37e+03 | +| ep_rew_mean | 0.118 | +| time/ | | +| fps | 310 | +| iterations | 1993 | +| time_elapsed | 6568 | +| total_timesteps | 2040832 | +| train/ | | +| approx_kl | 1.7758352 | +| clip_fraction | 0.486 | +| clip_range | 0.2 | +| entropy_loss | -0.466 | +| explained_variance | -0.942 | +| learning_rate | 0.0001 | +| loss | -0.092 | +| n_updates | 80450 | +| policy_gradient_loss | -0.0622 | +| value_loss | 0.000815 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.37e+03 | +| ep_rew_mean | 0.119 | +| time/ | | +| fps | 310 | +| iterations | 1994 | +| time_elapsed | 6571 | +| total_timesteps | 2041856 | +| train/ | | +| approx_kl | 4.144164 | +| clip_fraction | 0.504 | +| clip_range | 0.2 | +| entropy_loss | -0.475 | +| explained_variance | -2.77 | +| learning_rate | 0.0001 | +| loss | -0.0984 | +| n_updates | 80460 | +| policy_gradient_loss | -0.0678 | +| value_loss | 0.000604 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.37e+03 | +| ep_rew_mean | 0.119 | +| time/ | | +| fps | 310 | +| iterations | 1995 | +| time_elapsed | 6574 | +| total_timesteps | 2042880 | +| train/ | | +| approx_kl | 1.5908526 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.448 | +| explained_variance | -3.39 | +| learning_rate | 0.0001 | +| loss | -0.0725 | +| n_updates | 80470 | +| policy_gradient_loss | -0.0609 | +| value_loss | 0.000516 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.36e+03 | +| ep_rew_mean | 0.122 | +| time/ | | +| fps | 310 | +| iterations | 1996 | +| time_elapsed | 6577 | +| total_timesteps | 2043904 | +| train/ | | +| approx_kl | 1.8685819 | +| clip_fraction | 0.522 | +| clip_range | 0.2 | +| entropy_loss | -0.594 | +| explained_variance | -2.7 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 80480 | +| policy_gradient_loss | -0.0674 | +| value_loss | 0.000416 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.36e+03 | +| ep_rew_mean | 0.122 | +| time/ | | +| fps | 310 | +| iterations | 1997 | +| time_elapsed | 6580 | +| total_timesteps | 2044928 | +| train/ | | +| approx_kl | 1.4377066 | +| clip_fraction | 0.513 | +| clip_range | 0.2 | +| entropy_loss | -0.564 | +| explained_variance | -1.93 | +| learning_rate | 0.0001 | +| loss | -0.0924 | +| n_updates | 80490 | +| policy_gradient_loss | -0.0698 | +| value_loss | 0.0004 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.35e+03 | +| ep_rew_mean | 0.117 | +| time/ | | +| fps | 310 | +| iterations | 1998 | +| time_elapsed | 6584 | +| total_timesteps | 2045952 | +| train/ | | +| approx_kl | 1.8517565 | +| clip_fraction | 0.474 | +| clip_range | 0.2 | +| entropy_loss | -0.481 | +| explained_variance | -2.4 | +| learning_rate | 0.0001 | +| loss | -0.0979 | +| n_updates | 80500 | +| policy_gradient_loss | -0.0601 | +| value_loss | 0.000353 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.34e+03 | +| ep_rew_mean | 0.118 | +| time/ | | +| fps | 310 | +| iterations | 1999 | +| time_elapsed | 6587 | +| total_timesteps | 2046976 | +| train/ | | +| approx_kl | 1.4138067 | +| clip_fraction | 0.528 | +| clip_range | 0.2 | +| entropy_loss | -0.625 | +| explained_variance | -0.559 | +| learning_rate | 0.0001 | +| loss | -0.0943 | +| n_updates | 80510 | +| policy_gradient_loss | -0.0564 | +| value_loss | 0.000239 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.34e+03 | +| ep_rew_mean | 0.118 | +| time/ | | +| fps | 310 | +| iterations | 2000 | +| time_elapsed | 6591 | +| total_timesteps | 2048000 | +| train/ | | +| approx_kl | 1.5501313 | +| clip_fraction | 0.494 | +| clip_range | 0.2 | +| entropy_loss | -0.482 | +| explained_variance | -0.829 | +| learning_rate | 0.0001 | +| loss | -0.0916 | +| n_updates | 80520 | +| policy_gradient_loss | -0.0687 | +| value_loss | 0.000647 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.34e+03 | +| ep_rew_mean | 0.114 | +| time/ | | +| fps | 310 | +| iterations | 2001 | +| time_elapsed | 6594 | +| total_timesteps | 2049024 | +| train/ | | +| approx_kl | 1.4397104 | +| clip_fraction | 0.516 | +| clip_range | 0.2 | +| entropy_loss | -0.612 | +| explained_variance | -4.26 | +| learning_rate | 0.0001 | +| loss | -0.0825 | +| n_updates | 80530 | +| policy_gradient_loss | -0.0782 | +| value_loss | 0.000592 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.33e+03 | +| ep_rew_mean | 0.108 | +| time/ | | +| fps | 310 | +| iterations | 2002 | +| time_elapsed | 6598 | +| total_timesteps | 2050048 | +| train/ | | +| approx_kl | 2.4182901 | +| clip_fraction | 0.472 | +| clip_range | 0.2 | +| entropy_loss | -0.469 | +| explained_variance | -2.94 | +| learning_rate | 0.0001 | +| loss | -0.0626 | +| n_updates | 80540 | +| policy_gradient_loss | -0.0589 | +| value_loss | 0.000762 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.33e+03 | +| ep_rew_mean | 0.108 | +| time/ | | +| fps | 310 | +| iterations | 2003 | +| time_elapsed | 6601 | +| total_timesteps | 2051072 | +| train/ | | +| approx_kl | 2.564087 | +| clip_fraction | 0.469 | +| clip_range | 0.2 | +| entropy_loss | -0.449 | +| explained_variance | -4.18 | +| learning_rate | 0.0001 | +| loss | -0.0565 | +| n_updates | 80550 | +| policy_gradient_loss | -0.0609 | +| value_loss | 0.000588 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.33e+03 | +| ep_rew_mean | 0.0993 | +| time/ | | +| fps | 310 | +| iterations | 2004 | +| time_elapsed | 6605 | +| total_timesteps | 2052096 | +| train/ | | +| approx_kl | 1.5434835 | +| clip_fraction | 0.513 | +| clip_range | 0.2 | +| entropy_loss | -0.524 | +| explained_variance | -6.86 | +| learning_rate | 0.0001 | +| loss | -0.0933 | +| n_updates | 80560 | +| policy_gradient_loss | -0.0684 | +| value_loss | 0.000691 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.33e+03 | +| ep_rew_mean | 0.0968 | +| time/ | | +| fps | 310 | +| iterations | 2005 | +| time_elapsed | 6608 | +| total_timesteps | 2053120 | +| train/ | | +| approx_kl | 1.4036582 | +| clip_fraction | 0.463 | +| clip_range | 0.2 | +| entropy_loss | -0.558 | +| explained_variance | -1.73 | +| learning_rate | 0.0001 | +| loss | -0.0787 | +| n_updates | 80570 | +| policy_gradient_loss | -0.056 | +| value_loss | 0.000387 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.33e+03 | +| ep_rew_mean | 0.0968 | +| time/ | | +| fps | 310 | +| iterations | 2006 | +| time_elapsed | 6612 | +| total_timesteps | 2054144 | +| train/ | | +| approx_kl | 11.469612 | +| clip_fraction | 0.465 | +| clip_range | 0.2 | +| entropy_loss | -0.459 | +| explained_variance | -1.02 | +| learning_rate | 0.0001 | +| loss | -0.084 | +| n_updates | 80580 | +| policy_gradient_loss | -0.0681 | +| value_loss | 0.000522 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.28e+03 | +| ep_rew_mean | 0.0972 | +| time/ | | +| fps | 310 | +| iterations | 2007 | +| time_elapsed | 6615 | +| total_timesteps | 2055168 | +| train/ | | +| approx_kl | 1.5036583 | +| clip_fraction | 0.541 | +| clip_range | 0.2 | +| entropy_loss | -0.591 | +| explained_variance | -5.47 | +| learning_rate | 0.0001 | +| loss | -0.0903 | +| n_updates | 80590 | +| policy_gradient_loss | -0.0675 | +| value_loss | 0.000292 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.28e+03 | +| ep_rew_mean | 0.0972 | +| time/ | | +| fps | 310 | +| iterations | 2008 | +| time_elapsed | 6618 | +| total_timesteps | 2056192 | +| train/ | | +| approx_kl | 1.0159374 | +| clip_fraction | 0.465 | +| clip_range | 0.2 | +| entropy_loss | -0.569 | +| explained_variance | -6.36 | +| learning_rate | 0.0001 | +| loss | -0.0772 | +| n_updates | 80600 | +| policy_gradient_loss | -0.0498 | +| value_loss | 0.00103 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.27e+03 | +| ep_rew_mean | 0.0951 | +| time/ | | +| fps | 310 | +| iterations | 2009 | +| time_elapsed | 6621 | +| total_timesteps | 2057216 | +| train/ | | +| approx_kl | 1.8194481 | +| clip_fraction | 0.528 | +| clip_range | 0.2 | +| entropy_loss | -0.592 | +| explained_variance | -2.06 | +| learning_rate | 0.0001 | +| loss | -0.1 | +| n_updates | 80610 | +| policy_gradient_loss | -0.0727 | +| value_loss | 0.000425 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.27e+03 | +| ep_rew_mean | 0.0951 | +| time/ | | +| fps | 310 | +| iterations | 2010 | +| time_elapsed | 6624 | +| total_timesteps | 2058240 | +| train/ | | +| approx_kl | 2.2631555 | +| clip_fraction | 0.49 | +| clip_range | 0.2 | +| entropy_loss | -0.456 | +| explained_variance | -4.78 | +| learning_rate | 0.0001 | +| loss | -0.0632 | +| n_updates | 80620 | +| policy_gradient_loss | -0.0653 | +| value_loss | 0.000463 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.27e+03 | +| ep_rew_mean | 0.0911 | +| time/ | | +| fps | 310 | +| iterations | 2011 | +| time_elapsed | 6627 | +| total_timesteps | 2059264 | +| train/ | | +| approx_kl | 1.6886991 | +| clip_fraction | 0.515 | +| clip_range | 0.2 | +| entropy_loss | -0.518 | +| explained_variance | -6.66 | +| learning_rate | 0.0001 | +| loss | -0.109 | +| n_updates | 80630 | +| policy_gradient_loss | -0.0708 | +| value_loss | 0.0003 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.27e+03 | +| ep_rew_mean | 0.0834 | +| time/ | | +| fps | 310 | +| iterations | 2012 | +| time_elapsed | 6631 | +| total_timesteps | 2060288 | +| train/ | | +| approx_kl | 1.5752558 | +| clip_fraction | 0.451 | +| clip_range | 0.2 | +| entropy_loss | -0.493 | +| explained_variance | -2.65 | +| learning_rate | 0.0001 | +| loss | -0.0833 | +| n_updates | 80640 | +| policy_gradient_loss | -0.0586 | +| value_loss | 0.00028 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.27e+03 | +| ep_rew_mean | 0.0834 | +| time/ | | +| fps | 310 | +| iterations | 2013 | +| time_elapsed | 6634 | +| total_timesteps | 2061312 | +| train/ | | +| approx_kl | 1.524333 | +| clip_fraction | 0.439 | +| clip_range | 0.2 | +| entropy_loss | -0.415 | +| explained_variance | -0.765 | +| learning_rate | 0.0001 | +| loss | -0.0814 | +| n_updates | 80650 | +| policy_gradient_loss | -0.0578 | +| value_loss | 0.000519 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.26e+03 | +| ep_rew_mean | 0.0785 | +| time/ | | +| fps | 310 | +| iterations | 2014 | +| time_elapsed | 6637 | +| total_timesteps | 2062336 | +| train/ | | +| approx_kl | 1.6425745 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.496 | +| explained_variance | -3.06 | +| learning_rate | 0.0001 | +| loss | -0.0907 | +| n_updates | 80660 | +| policy_gradient_loss | -0.0769 | +| value_loss | 0.000566 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.25e+03 | +| ep_rew_mean | 0.0709 | +| time/ | | +| fps | 310 | +| iterations | 2015 | +| time_elapsed | 6640 | +| total_timesteps | 2063360 | +| train/ | | +| approx_kl | 1.3833766 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.44 | +| explained_variance | -2.61 | +| learning_rate | 0.0001 | +| loss | -0.0668 | +| n_updates | 80670 | +| policy_gradient_loss | -0.0605 | +| value_loss | 0.000518 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.25e+03 | +| ep_rew_mean | 0.0709 | +| time/ | | +| fps | 310 | +| iterations | 2016 | +| time_elapsed | 6644 | +| total_timesteps | 2064384 | +| train/ | | +| approx_kl | 1.7854767 | +| clip_fraction | 0.47 | +| clip_range | 0.2 | +| entropy_loss | -0.399 | +| explained_variance | -1.03 | +| learning_rate | 0.0001 | +| loss | -0.0947 | +| n_updates | 80680 | +| policy_gradient_loss | -0.0602 | +| value_loss | 0.00075 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.25e+03 | +| ep_rew_mean | 0.0721 | +| time/ | | +| fps | 310 | +| iterations | 2017 | +| time_elapsed | 6647 | +| total_timesteps | 2065408 | +| train/ | | +| approx_kl | 1.9238245 | +| clip_fraction | 0.503 | +| clip_range | 0.2 | +| entropy_loss | -0.439 | +| explained_variance | -3.06 | +| learning_rate | 0.0001 | +| loss | -0.106 | +| n_updates | 80690 | +| policy_gradient_loss | -0.0611 | +| value_loss | 0.00137 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.25e+03 | +| ep_rew_mean | 0.0721 | +| time/ | | +| fps | 310 | +| iterations | 2018 | +| time_elapsed | 6650 | +| total_timesteps | 2066432 | +| train/ | | +| approx_kl | 1.8618819 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.486 | +| explained_variance | -3.37 | +| learning_rate | 0.0001 | +| loss | -0.0967 | +| n_updates | 80700 | +| policy_gradient_loss | -0.071 | +| value_loss | 0.000612 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.25e+03 | +| ep_rew_mean | 0.0724 | +| time/ | | +| fps | 310 | +| iterations | 2019 | +| time_elapsed | 6654 | +| total_timesteps | 2067456 | +| train/ | | +| approx_kl | 1.3847599 | +| clip_fraction | 0.446 | +| clip_range | 0.2 | +| entropy_loss | -0.41 | +| explained_variance | -0.611 | +| learning_rate | 0.0001 | +| loss | -0.0808 | +| n_updates | 80710 | +| policy_gradient_loss | -0.0456 | +| value_loss | 0.000301 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.24e+03 | +| ep_rew_mean | 0.0724 | +| time/ | | +| fps | 310 | +| iterations | 2020 | +| time_elapsed | 6657 | +| total_timesteps | 2068480 | +| train/ | | +| approx_kl | 1.5737797 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.41 | +| explained_variance | -1.69 | +| learning_rate | 0.0001 | +| loss | -0.093 | +| n_updates | 80720 | +| policy_gradient_loss | -0.047 | +| value_loss | 0.000293 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.24e+03 | +| ep_rew_mean | 0.0724 | +| time/ | | +| fps | 310 | +| iterations | 2021 | +| time_elapsed | 6660 | +| total_timesteps | 2069504 | +| train/ | | +| approx_kl | 1.8821788 | +| clip_fraction | 0.446 | +| clip_range | 0.2 | +| entropy_loss | -0.375 | +| explained_variance | -0.853 | +| learning_rate | 0.0001 | +| loss | -0.0693 | +| n_updates | 80730 | +| policy_gradient_loss | -0.0652 | +| value_loss | 0.000614 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.24e+03 | +| ep_rew_mean | 0.0711 | +| time/ | | +| fps | 310 | +| iterations | 2022 | +| time_elapsed | 6664 | +| total_timesteps | 2070528 | +| train/ | | +| approx_kl | 2.0024354 | +| clip_fraction | 0.472 | +| clip_range | 0.2 | +| entropy_loss | -0.421 | +| explained_variance | -3.36 | +| learning_rate | 0.0001 | +| loss | -0.0616 | +| n_updates | 80740 | +| policy_gradient_loss | -0.0679 | +| value_loss | 0.000504 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.24e+03 | +| ep_rew_mean | 0.0711 | +| time/ | | +| fps | 310 | +| iterations | 2023 | +| time_elapsed | 6667 | +| total_timesteps | 2071552 | +| train/ | | +| approx_kl | 1.8497534 | +| clip_fraction | 0.477 | +| clip_range | 0.2 | +| entropy_loss | -0.478 | +| explained_variance | -1.05 | +| learning_rate | 0.0001 | +| loss | -0.0997 | +| n_updates | 80750 | +| policy_gradient_loss | -0.0614 | +| value_loss | 0.000528 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.24e+03 | +| ep_rew_mean | 0.0705 | +| time/ | | +| fps | 310 | +| iterations | 2024 | +| time_elapsed | 6670 | +| total_timesteps | 2072576 | +| train/ | | +| approx_kl | 1.4196036 | +| clip_fraction | 0.456 | +| clip_range | 0.2 | +| entropy_loss | -0.403 | +| explained_variance | -2.51 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 80760 | +| policy_gradient_loss | -0.066 | +| value_loss | 0.000493 | +--------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 2.22e+03 | +| ep_rew_mean | 0.0675 | +| time/ | | +| fps | 310 | +| iterations | 2025 | +| time_elapsed | 6673 | +| total_timesteps | 2073600 | +| train/ | | +| approx_kl | 10.8728485 | +| clip_fraction | 0.493 | +| clip_range | 0.2 | +| entropy_loss | -0.515 | +| explained_variance | -0.763 | +| learning_rate | 0.0001 | +| loss | -0.0912 | +| n_updates | 80770 | +| policy_gradient_loss | -0.0603 | +| value_loss | 0.000301 | +---------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.22e+03 | +| ep_rew_mean | 0.0675 | +| time/ | | +| fps | 310 | +| iterations | 2026 | +| time_elapsed | 6676 | +| total_timesteps | 2074624 | +| train/ | | +| approx_kl | 1.3883204 | +| clip_fraction | 0.489 | +| clip_range | 0.2 | +| entropy_loss | -0.475 | +| explained_variance | -1.5 | +| learning_rate | 0.0001 | +| loss | -0.0895 | +| n_updates | 80780 | +| policy_gradient_loss | -0.0698 | +| value_loss | 0.000468 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.21e+03 | +| ep_rew_mean | 0.0612 | +| time/ | | +| fps | 310 | +| iterations | 2027 | +| time_elapsed | 6680 | +| total_timesteps | 2075648 | +| train/ | | +| approx_kl | 1.7980046 | +| clip_fraction | 0.493 | +| clip_range | 0.2 | +| entropy_loss | -0.476 | +| explained_variance | -4.16 | +| learning_rate | 0.0001 | +| loss | -0.106 | +| n_updates | 80790 | +| policy_gradient_loss | -0.0678 | +| value_loss | 0.000415 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.2e+03 | +| ep_rew_mean | 0.0592 | +| time/ | | +| fps | 310 | +| iterations | 2028 | +| time_elapsed | 6683 | +| total_timesteps | 2076672 | +| train/ | | +| approx_kl | 2.4651039 | +| clip_fraction | 0.439 | +| clip_range | 0.2 | +| entropy_loss | -0.458 | +| explained_variance | -1.38 | +| learning_rate | 0.0001 | +| loss | -0.0565 | +| n_updates | 80800 | +| policy_gradient_loss | -0.0593 | +| value_loss | 0.000551 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.03e+03 | +| ep_rew_mean | 0.0558 | +| time/ | | +| fps | 310 | +| iterations | 2029 | +| time_elapsed | 6686 | +| total_timesteps | 2077696 | +| train/ | | +| approx_kl | 5.1112437 | +| clip_fraction | 0.484 | +| clip_range | 0.2 | +| entropy_loss | -0.483 | +| explained_variance | -6.35 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 80810 | +| policy_gradient_loss | -0.0678 | +| value_loss | 0.000583 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.03e+03 | +| ep_rew_mean | 0.0558 | +| time/ | | +| fps | 310 | +| iterations | 2030 | +| time_elapsed | 6689 | +| total_timesteps | 2078720 | +| train/ | | +| approx_kl | 1.693351 | +| clip_fraction | 0.492 | +| clip_range | 0.2 | +| entropy_loss | -0.496 | +| explained_variance | -0.835 | +| learning_rate | 0.0001 | +| loss | -0.0899 | +| n_updates | 80820 | +| policy_gradient_loss | -0.063 | +| value_loss | 0.000409 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.03e+03 | +| ep_rew_mean | 0.0513 | +| time/ | | +| fps | 310 | +| iterations | 2031 | +| time_elapsed | 6692 | +| total_timesteps | 2079744 | +| train/ | | +| approx_kl | 1.7815166 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.495 | +| explained_variance | -5.11 | +| learning_rate | 0.0001 | +| loss | -0.0889 | +| n_updates | 80830 | +| policy_gradient_loss | -0.0613 | +| value_loss | 0.000364 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.02e+03 | +| ep_rew_mean | 0.0503 | +| time/ | | +| fps | 310 | +| iterations | 2032 | +| time_elapsed | 6695 | +| total_timesteps | 2080768 | +| train/ | | +| approx_kl | 2.34378 | +| clip_fraction | 0.479 | +| clip_range | 0.2 | +| entropy_loss | -0.488 | +| explained_variance | -1.56 | +| learning_rate | 0.0001 | +| loss | -0.0691 | +| n_updates | 80840 | +| policy_gradient_loss | -0.0519 | +| value_loss | 0.000642 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.02e+03 | +| ep_rew_mean | 0.0503 | +| time/ | | +| fps | 310 | +| iterations | 2033 | +| time_elapsed | 6698 | +| total_timesteps | 2081792 | +| train/ | | +| approx_kl | 1.7524108 | +| clip_fraction | 0.553 | +| clip_range | 0.2 | +| entropy_loss | -0.758 | +| explained_variance | -2.07 | +| learning_rate | 0.0001 | +| loss | -0.0753 | +| n_updates | 80850 | +| policy_gradient_loss | -0.0554 | +| value_loss | 0.000252 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.02e+03 | +| ep_rew_mean | 0.0469 | +| time/ | | +| fps | 310 | +| iterations | 2034 | +| time_elapsed | 6702 | +| total_timesteps | 2082816 | +| train/ | | +| approx_kl | 1.2904862 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.51 | +| explained_variance | -2.72 | +| learning_rate | 0.0001 | +| loss | -0.0839 | +| n_updates | 80860 | +| policy_gradient_loss | -0.0623 | +| value_loss | 0.00031 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.02e+03 | +| ep_rew_mean | 0.0448 | +| time/ | | +| fps | 310 | +| iterations | 2035 | +| time_elapsed | 6706 | +| total_timesteps | 2083840 | +| train/ | | +| approx_kl | 1.7787694 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.43 | +| explained_variance | -1.22 | +| learning_rate | 0.0001 | +| loss | -0.0814 | +| n_updates | 80870 | +| policy_gradient_loss | -0.0576 | +| value_loss | 0.000352 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.01e+03 | +| ep_rew_mean | 0.0415 | +| time/ | | +| fps | 310 | +| iterations | 2036 | +| time_elapsed | 6709 | +| total_timesteps | 2084864 | +| train/ | | +| approx_kl | 2.1284626 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.46 | +| explained_variance | -1.35 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 80880 | +| policy_gradient_loss | -0.0578 | +| value_loss | 0.000568 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.01e+03 | +| ep_rew_mean | 0.0415 | +| time/ | | +| fps | 310 | +| iterations | 2037 | +| time_elapsed | 6713 | +| total_timesteps | 2085888 | +| train/ | | +| approx_kl | 2.4694266 | +| clip_fraction | 0.443 | +| clip_range | 0.2 | +| entropy_loss | -0.438 | +| explained_variance | -0.844 | +| learning_rate | 0.0001 | +| loss | -0.116 | +| n_updates | 80890 | +| policy_gradient_loss | -0.0603 | +| value_loss | 0.00045 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2e+03 | +| ep_rew_mean | 0.0365 | +| time/ | | +| fps | 310 | +| iterations | 2038 | +| time_elapsed | 6716 | +| total_timesteps | 2086912 | +| train/ | | +| approx_kl | 1.9785933 | +| clip_fraction | 0.521 | +| clip_range | 0.2 | +| entropy_loss | -0.545 | +| explained_variance | -5.88 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 80900 | +| policy_gradient_loss | -0.0699 | +| value_loss | 0.000425 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2e+03 | +| ep_rew_mean | 0.0365 | +| time/ | | +| fps | 310 | +| iterations | 2039 | +| time_elapsed | 6720 | +| total_timesteps | 2087936 | +| train/ | | +| approx_kl | 1.3181021 | +| clip_fraction | 0.444 | +| clip_range | 0.2 | +| entropy_loss | -0.549 | +| explained_variance | -0.916 | +| learning_rate | 0.0001 | +| loss | -0.0583 | +| n_updates | 80910 | +| policy_gradient_loss | -0.054 | +| value_loss | 0.0007 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.98e+03 | +| ep_rew_mean | 0.0358 | +| time/ | | +| fps | 310 | +| iterations | 2040 | +| time_elapsed | 6723 | +| total_timesteps | 2088960 | +| train/ | | +| approx_kl | 1.4707154 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.451 | +| explained_variance | -3.56 | +| learning_rate | 0.0001 | +| loss | -0.0885 | +| n_updates | 80920 | +| policy_gradient_loss | -0.061 | +| value_loss | 0.000355 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.98e+03 | +| ep_rew_mean | 0.0334 | +| time/ | | +| fps | 310 | +| iterations | 2041 | +| time_elapsed | 6727 | +| total_timesteps | 2089984 | +| train/ | | +| approx_kl | 2.3016794 | +| clip_fraction | 0.482 | +| clip_range | 0.2 | +| entropy_loss | -0.47 | +| explained_variance | -2.31 | +| learning_rate | 0.0001 | +| loss | -0.0765 | +| n_updates | 80930 | +| policy_gradient_loss | -0.0658 | +| value_loss | 0.000637 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.97e+03 | +| ep_rew_mean | 0.0302 | +| time/ | | +| fps | 310 | +| iterations | 2042 | +| time_elapsed | 6730 | +| total_timesteps | 2091008 | +| train/ | | +| approx_kl | 2.0231702 | +| clip_fraction | 0.461 | +| clip_range | 0.2 | +| entropy_loss | -0.421 | +| explained_variance | -2.93 | +| learning_rate | 0.0001 | +| loss | -0.0836 | +| n_updates | 80940 | +| policy_gradient_loss | -0.0606 | +| value_loss | 0.000722 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.97e+03 | +| ep_rew_mean | 0.025 | +| time/ | | +| fps | 310 | +| iterations | 2043 | +| time_elapsed | 6733 | +| total_timesteps | 2092032 | +| train/ | | +| approx_kl | 2.307739 | +| clip_fraction | 0.478 | +| clip_range | 0.2 | +| entropy_loss | -0.427 | +| explained_variance | -1.14 | +| learning_rate | 0.0001 | +| loss | -0.0726 | +| n_updates | 80950 | +| policy_gradient_loss | -0.058 | +| value_loss | 0.000578 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.97e+03 | +| ep_rew_mean | 0.025 | +| time/ | | +| fps | 310 | +| iterations | 2044 | +| time_elapsed | 6736 | +| total_timesteps | 2093056 | +| train/ | | +| approx_kl | 1.5313029 | +| clip_fraction | 0.465 | +| clip_range | 0.2 | +| entropy_loss | -0.459 | +| explained_variance | -2.98 | +| learning_rate | 0.0001 | +| loss | -0.0435 | +| n_updates | 80960 | +| policy_gradient_loss | -0.0624 | +| value_loss | 0.000388 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.97e+03 | +| ep_rew_mean | 0.0237 | +| time/ | | +| fps | 310 | +| iterations | 2045 | +| time_elapsed | 6740 | +| total_timesteps | 2094080 | +| train/ | | +| approx_kl | 1.6963034 | +| clip_fraction | 0.511 | +| clip_range | 0.2 | +| entropy_loss | -0.58 | +| explained_variance | -1.21 | +| learning_rate | 0.0001 | +| loss | -0.0737 | +| n_updates | 80970 | +| policy_gradient_loss | -0.0615 | +| value_loss | 0.000518 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.97e+03 | +| ep_rew_mean | 0.0237 | +| time/ | | +| fps | 310 | +| iterations | 2046 | +| time_elapsed | 6743 | +| total_timesteps | 2095104 | +| train/ | | +| approx_kl | 1.831243 | +| clip_fraction | 0.428 | +| clip_range | 0.2 | +| entropy_loss | -0.34 | +| explained_variance | -2.93 | +| learning_rate | 0.0001 | +| loss | -0.0848 | +| n_updates | 80980 | +| policy_gradient_loss | -0.0658 | +| value_loss | 0.000578 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.96e+03 | +| ep_rew_mean | 0.0224 | +| time/ | | +| fps | 310 | +| iterations | 2047 | +| time_elapsed | 6746 | +| total_timesteps | 2096128 | +| train/ | | +| approx_kl | 1.710615 | +| clip_fraction | 0.509 | +| clip_range | 0.2 | +| entropy_loss | -0.608 | +| explained_variance | -2.84 | +| learning_rate | 0.0001 | +| loss | -0.0847 | +| n_updates | 80990 | +| policy_gradient_loss | -0.0631 | +| value_loss | 0.000676 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.95e+03 | +| ep_rew_mean | 0.0182 | +| time/ | | +| fps | 310 | +| iterations | 2048 | +| time_elapsed | 6749 | +| total_timesteps | 2097152 | +| train/ | | +| approx_kl | 1.3719883 | +| clip_fraction | 0.47 | +| clip_range | 0.2 | +| entropy_loss | -0.472 | +| explained_variance | -4.25 | +| learning_rate | 0.0001 | +| loss | -0.0908 | +| n_updates | 81000 | +| policy_gradient_loss | -0.0674 | +| value_loss | 0.000437 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.95e+03 | +| ep_rew_mean | 0.0138 | +| time/ | | +| fps | 310 | +| iterations | 2049 | +| time_elapsed | 6752 | +| total_timesteps | 2098176 | +| train/ | | +| approx_kl | 1.4536297 | +| clip_fraction | 0.43 | +| clip_range | 0.2 | +| entropy_loss | -0.381 | +| explained_variance | -0.84 | +| learning_rate | 0.0001 | +| loss | -0.088 | +| n_updates | 81010 | +| policy_gradient_loss | -0.0586 | +| value_loss | 0.00075 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.95e+03 | +| ep_rew_mean | 0.0138 | +| time/ | | +| fps | 310 | +| iterations | 2050 | +| time_elapsed | 6755 | +| total_timesteps | 2099200 | +| train/ | | +| approx_kl | 1.8096719 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.454 | +| explained_variance | -0.918 | +| learning_rate | 0.0001 | +| loss | -0.0962 | +| n_updates | 81020 | +| policy_gradient_loss | -0.0689 | +| value_loss | 0.000514 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.94e+03 | +| ep_rew_mean | 0.00587 | +| time/ | | +| fps | 310 | +| iterations | 2051 | +| time_elapsed | 6759 | +| total_timesteps | 2100224 | +| train/ | | +| approx_kl | 1.9348431 | +| clip_fraction | 0.479 | +| clip_range | 0.2 | +| entropy_loss | -0.483 | +| explained_variance | -11.4 | +| learning_rate | 0.0001 | +| loss | -0.117 | +| n_updates | 81030 | +| policy_gradient_loss | -0.0685 | +| value_loss | 0.000524 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.94e+03 | +| ep_rew_mean | 0.00916 | +| time/ | | +| fps | 310 | +| iterations | 2052 | +| time_elapsed | 6762 | +| total_timesteps | 2101248 | +| train/ | | +| approx_kl | 1.7436675 | +| clip_fraction | 0.451 | +| clip_range | 0.2 | +| entropy_loss | -0.409 | +| explained_variance | -0.608 | +| learning_rate | 0.0001 | +| loss | -0.0549 | +| n_updates | 81040 | +| policy_gradient_loss | -0.0576 | +| value_loss | 0.000599 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.93e+03 | +| ep_rew_mean | 0.00685 | +| time/ | | +| fps | 310 | +| iterations | 2053 | +| time_elapsed | 6765 | +| total_timesteps | 2102272 | +| train/ | | +| approx_kl | 1.9873548 | +| clip_fraction | 0.502 | +| clip_range | 0.2 | +| entropy_loss | -0.515 | +| explained_variance | -2.15 | +| learning_rate | 0.0001 | +| loss | -0.0887 | +| n_updates | 81050 | +| policy_gradient_loss | -0.0734 | +| value_loss | 0.000597 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.93e+03 | +| ep_rew_mean | 0.00685 | +| time/ | | +| fps | 310 | +| iterations | 2054 | +| time_elapsed | 6769 | +| total_timesteps | 2103296 | +| train/ | | +| approx_kl | 1.5584589 | +| clip_fraction | 0.464 | +| clip_range | 0.2 | +| entropy_loss | -0.46 | +| explained_variance | -1.92 | +| learning_rate | 0.0001 | +| loss | -0.109 | +| n_updates | 81060 | +| policy_gradient_loss | -0.0593 | +| value_loss | 0.000559 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.93e+03 | +| ep_rew_mean | 0.00685 | +| time/ | | +| fps | 310 | +| iterations | 2055 | +| time_elapsed | 6772 | +| total_timesteps | 2104320 | +| train/ | | +| approx_kl | 1.9878445 | +| clip_fraction | 0.453 | +| clip_range | 0.2 | +| entropy_loss | -0.418 | +| explained_variance | -1.23 | +| learning_rate | 0.0001 | +| loss | -0.107 | +| n_updates | 81070 | +| policy_gradient_loss | -0.0641 | +| value_loss | 0.000343 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.93e+03 | +| ep_rew_mean | 0.00466 | +| time/ | | +| fps | 310 | +| iterations | 2056 | +| time_elapsed | 6776 | +| total_timesteps | 2105344 | +| train/ | | +| approx_kl | 1.3213061 | +| clip_fraction | 0.44 | +| clip_range | 0.2 | +| entropy_loss | -0.41 | +| explained_variance | -2.56 | +| learning_rate | 0.0001 | +| loss | -0.0998 | +| n_updates | 81080 | +| policy_gradient_loss | -0.0546 | +| value_loss | 0.000544 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.92e+03 | +| ep_rew_mean | -0.00116 | +| time/ | | +| fps | 310 | +| iterations | 2057 | +| time_elapsed | 6779 | +| total_timesteps | 2106368 | +| train/ | | +| approx_kl | 2.0981073 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.411 | +| explained_variance | -1.65 | +| learning_rate | 0.0001 | +| loss | -0.0774 | +| n_updates | 81090 | +| policy_gradient_loss | -0.0608 | +| value_loss | 0.000595 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.92e+03 | +| ep_rew_mean | -0.0093 | +| time/ | | +| fps | 310 | +| iterations | 2058 | +| time_elapsed | 6783 | +| total_timesteps | 2107392 | +| train/ | | +| approx_kl | 1.7314801 | +| clip_fraction | 0.466 | +| clip_range | 0.2 | +| entropy_loss | -0.432 | +| explained_variance | -0.947 | +| learning_rate | 0.0001 | +| loss | -0.116 | +| n_updates | 81100 | +| policy_gradient_loss | -0.0715 | +| value_loss | 0.000755 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.89e+03 | +| ep_rew_mean | -0.0134 | +| time/ | | +| fps | 310 | +| iterations | 2059 | +| time_elapsed | 6786 | +| total_timesteps | 2108416 | +| train/ | | +| approx_kl | 1.785397 | +| clip_fraction | 0.439 | +| clip_range | 0.2 | +| entropy_loss | -0.401 | +| explained_variance | -1.95 | +| learning_rate | 0.0001 | +| loss | -0.0767 | +| n_updates | 81110 | +| policy_gradient_loss | -0.0553 | +| value_loss | 0.000904 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.89e+03 | +| ep_rew_mean | -0.0134 | +| time/ | | +| fps | 310 | +| iterations | 2060 | +| time_elapsed | 6790 | +| total_timesteps | 2109440 | +| train/ | | +| approx_kl | 1.6139706 | +| clip_fraction | 0.488 | +| clip_range | 0.2 | +| entropy_loss | -0.517 | +| explained_variance | -2.28 | +| learning_rate | 0.0001 | +| loss | -0.113 | +| n_updates | 81120 | +| policy_gradient_loss | -0.0622 | +| value_loss | 0.000543 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.89e+03 | +| ep_rew_mean | -0.0143 | +| time/ | | +| fps | 310 | +| iterations | 2061 | +| time_elapsed | 6793 | +| total_timesteps | 2110464 | +| train/ | | +| approx_kl | 1.6398251 | +| clip_fraction | 0.446 | +| clip_range | 0.2 | +| entropy_loss | -0.401 | +| explained_variance | -3.42 | +| learning_rate | 0.0001 | +| loss | -0.0863 | +| n_updates | 81130 | +| policy_gradient_loss | -0.0574 | +| value_loss | 0.000316 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.89e+03 | +| ep_rew_mean | -0.0143 | +| time/ | | +| fps | 310 | +| iterations | 2062 | +| time_elapsed | 6796 | +| total_timesteps | 2111488 | +| train/ | | +| approx_kl | 1.9372091 | +| clip_fraction | 0.447 | +| clip_range | 0.2 | +| entropy_loss | -0.371 | +| explained_variance | -2.69 | +| learning_rate | 0.0001 | +| loss | -0.07 | +| n_updates | 81140 | +| policy_gradient_loss | -0.0544 | +| value_loss | 0.000508 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.89e+03 | +| ep_rew_mean | -0.0155 | +| time/ | | +| fps | 310 | +| iterations | 2063 | +| time_elapsed | 6799 | +| total_timesteps | 2112512 | +| train/ | | +| approx_kl | 1.2964017 | +| clip_fraction | 0.459 | +| clip_range | 0.2 | +| entropy_loss | -0.437 | +| explained_variance | -1.39 | +| learning_rate | 0.0001 | +| loss | -0.0703 | +| n_updates | 81150 | +| policy_gradient_loss | -0.063 | +| value_loss | 0.000351 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | -0.0162 | +| time/ | | +| fps | 310 | +| iterations | 2064 | +| time_elapsed | 6802 | +| total_timesteps | 2113536 | +| train/ | | +| approx_kl | 2.003476 | +| clip_fraction | 0.47 | +| clip_range | 0.2 | +| entropy_loss | -0.421 | +| explained_variance | -1.13 | +| learning_rate | 0.0001 | +| loss | -0.0666 | +| n_updates | 81160 | +| policy_gradient_loss | -0.0601 | +| value_loss | 0.000971 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | -0.0162 | +| time/ | | +| fps | 310 | +| iterations | 2065 | +| time_elapsed | 6805 | +| total_timesteps | 2114560 | +| train/ | | +| approx_kl | 1.7078135 | +| clip_fraction | 0.501 | +| clip_range | 0.2 | +| entropy_loss | -0.488 | +| explained_variance | -6.39 | +| learning_rate | 0.0001 | +| loss | -0.0811 | +| n_updates | 81170 | +| policy_gradient_loss | -0.0716 | +| value_loss | 0.000571 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | -0.018 | +| time/ | | +| fps | 310 | +| iterations | 2066 | +| time_elapsed | 6809 | +| total_timesteps | 2115584 | +| train/ | | +| approx_kl | 2.1931849 | +| clip_fraction | 0.46 | +| clip_range | 0.2 | +| entropy_loss | -0.414 | +| explained_variance | -5.42 | +| learning_rate | 0.0001 | +| loss | -0.063 | +| n_updates | 81180 | +| policy_gradient_loss | -0.0645 | +| value_loss | 0.000692 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | -0.018 | +| time/ | | +| fps | 310 | +| iterations | 2067 | +| time_elapsed | 6812 | +| total_timesteps | 2116608 | +| train/ | | +| approx_kl | 1.4103125 | +| clip_fraction | 0.462 | +| clip_range | 0.2 | +| entropy_loss | -0.427 | +| explained_variance | -1.11 | +| learning_rate | 0.0001 | +| loss | -0.0681 | +| n_updates | 81190 | +| policy_gradient_loss | -0.0543 | +| value_loss | 0.00061 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | -0.0228 | +| time/ | | +| fps | 310 | +| iterations | 2068 | +| time_elapsed | 6815 | +| total_timesteps | 2117632 | +| train/ | | +| approx_kl | 1.7969453 | +| clip_fraction | 0.486 | +| clip_range | 0.2 | +| entropy_loss | -0.41 | +| explained_variance | -7.35 | +| learning_rate | 0.0001 | +| loss | -0.0817 | +| n_updates | 81200 | +| policy_gradient_loss | -0.0664 | +| value_loss | 0.000421 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | -0.0228 | +| time/ | | +| fps | 310 | +| iterations | 2069 | +| time_elapsed | 6818 | +| total_timesteps | 2118656 | +| train/ | | +| approx_kl | 1.6705425 | +| clip_fraction | 0.435 | +| clip_range | 0.2 | +| entropy_loss | -0.471 | +| explained_variance | -0.853 | +| learning_rate | 0.0001 | +| loss | -0.0811 | +| n_updates | 81210 | +| policy_gradient_loss | -0.0576 | +| value_loss | 0.00068 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | -0.0206 | +| time/ | | +| fps | 310 | +| iterations | 2070 | +| time_elapsed | 6821 | +| total_timesteps | 2119680 | +| train/ | | +| approx_kl | 1.7461207 | +| clip_fraction | 0.488 | +| clip_range | 0.2 | +| entropy_loss | -0.47 | +| explained_variance | -4.95 | +| learning_rate | 0.0001 | +| loss | -0.0641 | +| n_updates | 81220 | +| policy_gradient_loss | -0.0587 | +| value_loss | 0.000647 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | -0.0256 | +| time/ | | +| fps | 310 | +| iterations | 2071 | +| time_elapsed | 6825 | +| total_timesteps | 2120704 | +| train/ | | +| approx_kl | 1.7440271 | +| clip_fraction | 0.434 | +| clip_range | 0.2 | +| entropy_loss | -0.337 | +| explained_variance | -1.26 | +| learning_rate | 0.0001 | +| loss | -0.0903 | +| n_updates | 81230 | +| policy_gradient_loss | -0.0568 | +| value_loss | 0.000756 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | -0.0256 | +| time/ | | +| fps | 310 | +| iterations | 2072 | +| time_elapsed | 6828 | +| total_timesteps | 2121728 | +| train/ | | +| approx_kl | 1.4268332 | +| clip_fraction | 0.446 | +| clip_range | 0.2 | +| entropy_loss | -0.426 | +| explained_variance | -1.59 | +| learning_rate | 0.0001 | +| loss | -0.0712 | +| n_updates | 81240 | +| policy_gradient_loss | -0.0548 | +| value_loss | 0.000691 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | -0.0295 | +| time/ | | +| fps | 310 | +| iterations | 2073 | +| time_elapsed | 6832 | +| total_timesteps | 2122752 | +| train/ | | +| approx_kl | 1.4522176 | +| clip_fraction | 0.534 | +| clip_range | 0.2 | +| entropy_loss | -0.643 | +| explained_variance | -8.32 | +| learning_rate | 0.0001 | +| loss | -0.112 | +| n_updates | 81250 | +| policy_gradient_loss | -0.0727 | +| value_loss | 0.000441 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | -0.0295 | +| time/ | | +| fps | 310 | +| iterations | 2074 | +| time_elapsed | 6835 | +| total_timesteps | 2123776 | +| train/ | | +| approx_kl | 1.7530336 | +| clip_fraction | 0.467 | +| clip_range | 0.2 | +| entropy_loss | -0.423 | +| explained_variance | -0.777 | +| learning_rate | 0.0001 | +| loss | -0.0725 | +| n_updates | 81260 | +| policy_gradient_loss | -0.0618 | +| value_loss | 0.000522 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | -0.03 | +| time/ | | +| fps | 310 | +| iterations | 2075 | +| time_elapsed | 6839 | +| total_timesteps | 2124800 | +| train/ | | +| approx_kl | 3.0689728 | +| clip_fraction | 0.505 | +| clip_range | 0.2 | +| entropy_loss | -0.457 | +| explained_variance | -2.5 | +| learning_rate | 0.0001 | +| loss | -0.0888 | +| n_updates | 81270 | +| policy_gradient_loss | -0.068 | +| value_loss | 0.000604 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | -0.0348 | +| time/ | | +| fps | 310 | +| iterations | 2076 | +| time_elapsed | 6842 | +| total_timesteps | 2125824 | +| train/ | | +| approx_kl | 1.8421674 | +| clip_fraction | 0.459 | +| clip_range | 0.2 | +| entropy_loss | -0.433 | +| explained_variance | -2.29 | +| learning_rate | 0.0001 | +| loss | -0.0697 | +| n_updates | 81280 | +| policy_gradient_loss | -0.0535 | +| value_loss | 0.000331 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | -0.0348 | +| time/ | | +| fps | 310 | +| iterations | 2077 | +| time_elapsed | 6846 | +| total_timesteps | 2126848 | +| train/ | | +| approx_kl | 1.5952946 | +| clip_fraction | 0.479 | +| clip_range | 0.2 | +| entropy_loss | -0.422 | +| explained_variance | -2.07 | +| learning_rate | 0.0001 | +| loss | -0.0852 | +| n_updates | 81290 | +| policy_gradient_loss | -0.063 | +| value_loss | 0.000566 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.81e+03 | +| ep_rew_mean | -0.0367 | +| time/ | | +| fps | 310 | +| iterations | 2078 | +| time_elapsed | 6849 | +| total_timesteps | 2127872 | +| train/ | | +| approx_kl | 1.4934819 | +| clip_fraction | 0.488 | +| clip_range | 0.2 | +| entropy_loss | -0.512 | +| explained_variance | -6.52 | +| learning_rate | 0.0001 | +| loss | -0.0922 | +| n_updates | 81300 | +| policy_gradient_loss | -0.0607 | +| value_loss | 0.000625 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.81e+03 | +| ep_rew_mean | -0.0367 | +| time/ | | +| fps | 310 | +| iterations | 2079 | +| time_elapsed | 6853 | +| total_timesteps | 2128896 | +| train/ | | +| approx_kl | 1.7826285 | +| clip_fraction | 0.467 | +| clip_range | 0.2 | +| entropy_loss | -0.42 | +| explained_variance | -3.05 | +| learning_rate | 0.0001 | +| loss | -0.0906 | +| n_updates | 81310 | +| policy_gradient_loss | -0.063 | +| value_loss | 0.000385 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | -0.0394 | +| time/ | | +| fps | 310 | +| iterations | 2080 | +| time_elapsed | 6856 | +| total_timesteps | 2129920 | +| train/ | | +| approx_kl | 1.6648419 | +| clip_fraction | 0.505 | +| clip_range | 0.2 | +| entropy_loss | -0.428 | +| explained_variance | -1.93 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 81320 | +| policy_gradient_loss | -0.077 | +| value_loss | 0.000378 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.8e+03 | +| ep_rew_mean | -0.0432 | +| time/ | | +| fps | 310 | +| iterations | 2081 | +| time_elapsed | 6859 | +| total_timesteps | 2130944 | +| train/ | | +| approx_kl | 1.6570902 | +| clip_fraction | 0.464 | +| clip_range | 0.2 | +| entropy_loss | -0.406 | +| explained_variance | -1.47 | +| learning_rate | 0.0001 | +| loss | -0.0841 | +| n_updates | 81330 | +| policy_gradient_loss | -0.0611 | +| value_loss | 0.000561 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.8e+03 | +| ep_rew_mean | -0.0432 | +| time/ | | +| fps | 310 | +| iterations | 2082 | +| time_elapsed | 6862 | +| total_timesteps | 2131968 | +| train/ | | +| approx_kl | 2.0005794 | +| clip_fraction | 0.451 | +| clip_range | 0.2 | +| entropy_loss | -0.356 | +| explained_variance | -2.34 | +| learning_rate | 0.0001 | +| loss | -0.0944 | +| n_updates | 81340 | +| policy_gradient_loss | -0.0634 | +| value_loss | 0.000506 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | -0.0371 | +| time/ | | +| fps | 310 | +| iterations | 2083 | +| time_elapsed | 6866 | +| total_timesteps | 2132992 | +| train/ | | +| approx_kl | 2.8097568 | +| clip_fraction | 0.509 | +| clip_range | 0.2 | +| entropy_loss | -0.488 | +| explained_variance | -2.9 | +| learning_rate | 0.0001 | +| loss | -0.0983 | +| n_updates | 81350 | +| policy_gradient_loss | -0.0577 | +| value_loss | 0.000556 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | -0.0371 | +| time/ | | +| fps | 310 | +| iterations | 2084 | +| time_elapsed | 6869 | +| total_timesteps | 2134016 | +| train/ | | +| approx_kl | 1.9352987 | +| clip_fraction | 0.501 | +| clip_range | 0.2 | +| entropy_loss | -0.421 | +| explained_variance | -0.397 | +| learning_rate | 0.0001 | +| loss | -0.056 | +| n_updates | 81360 | +| policy_gradient_loss | -0.0576 | +| value_loss | 0.00143 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | -0.0366 | +| time/ | | +| fps | 310 | +| iterations | 2085 | +| time_elapsed | 6872 | +| total_timesteps | 2135040 | +| train/ | | +| approx_kl | 26.140787 | +| clip_fraction | 0.5 | +| clip_range | 0.2 | +| entropy_loss | -0.444 | +| explained_variance | -1.95 | +| learning_rate | 0.0001 | +| loss | -0.112 | +| n_updates | 81370 | +| policy_gradient_loss | -0.0715 | +| value_loss | 0.000834 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | -0.0383 | +| time/ | | +| fps | 310 | +| iterations | 2086 | +| time_elapsed | 6875 | +| total_timesteps | 2136064 | +| train/ | | +| approx_kl | 1.7935879 | +| clip_fraction | 0.508 | +| clip_range | 0.2 | +| entropy_loss | -0.502 | +| explained_variance | -3.07 | +| learning_rate | 0.0001 | +| loss | -0.0797 | +| n_updates | 81380 | +| policy_gradient_loss | -0.0665 | +| value_loss | 0.000462 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | -0.0383 | +| time/ | | +| fps | 310 | +| iterations | 2087 | +| time_elapsed | 6878 | +| total_timesteps | 2137088 | +| train/ | | +| approx_kl | 2.0107508 | +| clip_fraction | 0.461 | +| clip_range | 0.2 | +| entropy_loss | -0.374 | +| explained_variance | -4.16 | +| learning_rate | 0.0001 | +| loss | -0.0866 | +| n_updates | 81390 | +| policy_gradient_loss | -0.0662 | +| value_loss | 0.000459 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | -0.0447 | +| time/ | | +| fps | 310 | +| iterations | 2088 | +| time_elapsed | 6882 | +| total_timesteps | 2138112 | +| train/ | | +| approx_kl | 1.9764992 | +| clip_fraction | 0.491 | +| clip_range | 0.2 | +| entropy_loss | -0.418 | +| explained_variance | -5.73 | +| learning_rate | 0.0001 | +| loss | -0.0817 | +| n_updates | 81400 | +| policy_gradient_loss | -0.0724 | +| value_loss | 0.000267 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | -0.0447 | +| time/ | | +| fps | 310 | +| iterations | 2089 | +| time_elapsed | 6885 | +| total_timesteps | 2139136 | +| train/ | | +| approx_kl | 1.887328 | +| clip_fraction | 0.486 | +| clip_range | 0.2 | +| entropy_loss | -0.458 | +| explained_variance | -2 | +| learning_rate | 0.0001 | +| loss | -0.0992 | +| n_updates | 81410 | +| policy_gradient_loss | -0.0632 | +| value_loss | 0.000385 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | -0.0455 | +| time/ | | +| fps | 310 | +| iterations | 2090 | +| time_elapsed | 6888 | +| total_timesteps | 2140160 | +| train/ | | +| approx_kl | 2.9815524 | +| clip_fraction | 0.501 | +| clip_range | 0.2 | +| entropy_loss | -0.592 | +| explained_variance | -0.739 | +| learning_rate | 0.0001 | +| loss | -0.0732 | +| n_updates | 81420 | +| policy_gradient_loss | -0.0627 | +| value_loss | 0.00067 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | -0.0482 | +| time/ | | +| fps | 310 | +| iterations | 2091 | +| time_elapsed | 6892 | +| total_timesteps | 2141184 | +| train/ | | +| approx_kl | 1.6138904 | +| clip_fraction | 0.447 | +| clip_range | 0.2 | +| entropy_loss | -0.355 | +| explained_variance | -6.12 | +| learning_rate | 0.0001 | +| loss | -0.0753 | +| n_updates | 81430 | +| policy_gradient_loss | -0.0582 | +| value_loss | 0.00069 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | -0.0505 | +| time/ | | +| fps | 310 | +| iterations | 2092 | +| time_elapsed | 6895 | +| total_timesteps | 2142208 | +| train/ | | +| approx_kl | 2.015572 | +| clip_fraction | 0.461 | +| clip_range | 0.2 | +| entropy_loss | -0.469 | +| explained_variance | -2.45 | +| learning_rate | 0.0001 | +| loss | -0.0729 | +| n_updates | 81440 | +| policy_gradient_loss | -0.0605 | +| value_loss | 0.000574 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | -0.0505 | +| time/ | | +| fps | 310 | +| iterations | 2093 | +| time_elapsed | 6898 | +| total_timesteps | 2143232 | +| train/ | | +| approx_kl | 1.7764058 | +| clip_fraction | 0.476 | +| clip_range | 0.2 | +| entropy_loss | -0.422 | +| explained_variance | -2.36 | +| learning_rate | 0.0001 | +| loss | -0.096 | +| n_updates | 81450 | +| policy_gradient_loss | -0.0603 | +| value_loss | 0.000316 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | -0.0505 | +| time/ | | +| fps | 310 | +| iterations | 2094 | +| time_elapsed | 6902 | +| total_timesteps | 2144256 | +| train/ | | +| approx_kl | 1.9993618 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.385 | +| explained_variance | -2.98 | +| learning_rate | 0.0001 | +| loss | -0.0736 | +| n_updates | 81460 | +| policy_gradient_loss | -0.0624 | +| value_loss | 0.000455 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | -0.056 | +| time/ | | +| fps | 310 | +| iterations | 2095 | +| time_elapsed | 6905 | +| total_timesteps | 2145280 | +| train/ | | +| approx_kl | 1.6533318 | +| clip_fraction | 0.445 | +| clip_range | 0.2 | +| entropy_loss | -0.382 | +| explained_variance | -3.93 | +| learning_rate | 0.0001 | +| loss | -0.0573 | +| n_updates | 81470 | +| policy_gradient_loss | -0.0601 | +| value_loss | 0.000392 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | -0.056 | +| time/ | | +| fps | 310 | +| iterations | 2096 | +| time_elapsed | 6909 | +| total_timesteps | 2146304 | +| train/ | | +| approx_kl | 1.2479542 | +| clip_fraction | 0.477 | +| clip_range | 0.2 | +| entropy_loss | -0.487 | +| explained_variance | -3.05 | +| learning_rate | 0.0001 | +| loss | -0.0858 | +| n_updates | 81480 | +| policy_gradient_loss | -0.0659 | +| value_loss | 0.000431 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | -0.0567 | +| time/ | | +| fps | 310 | +| iterations | 2097 | +| time_elapsed | 6912 | +| total_timesteps | 2147328 | +| train/ | | +| approx_kl | 1.6923375 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.406 | +| explained_variance | -0.758 | +| learning_rate | 0.0001 | +| loss | -0.0914 | +| n_updates | 81490 | +| policy_gradient_loss | -0.0647 | +| value_loss | 0.000721 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | -0.064 | +| time/ | | +| fps | 310 | +| iterations | 2098 | +| time_elapsed | 6915 | +| total_timesteps | 2148352 | +| train/ | | +| approx_kl | 1.7380786 | +| clip_fraction | 0.446 | +| clip_range | 0.2 | +| entropy_loss | -0.442 | +| explained_variance | -3.86 | +| learning_rate | 0.0001 | +| loss | -0.0577 | +| n_updates | 81500 | +| policy_gradient_loss | -0.0609 | +| value_loss | 0.000668 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | -0.07 | +| time/ | | +| fps | 310 | +| iterations | 2099 | +| time_elapsed | 6919 | +| total_timesteps | 2149376 | +| train/ | | +| approx_kl | 1.7326908 | +| clip_fraction | 0.469 | +| clip_range | 0.2 | +| entropy_loss | -0.417 | +| explained_variance | -0.249 | +| learning_rate | 0.0001 | +| loss | -0.105 | +| n_updates | 81510 | +| policy_gradient_loss | -0.0614 | +| value_loss | 0.000545 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | -0.0713 | +| time/ | | +| fps | 310 | +| iterations | 2100 | +| time_elapsed | 6922 | +| total_timesteps | 2150400 | +| train/ | | +| approx_kl | 1.585463 | +| clip_fraction | 0.444 | +| clip_range | 0.2 | +| entropy_loss | -0.43 | +| explained_variance | -1.6 | +| learning_rate | 0.0001 | +| loss | -0.0657 | +| n_updates | 81520 | +| policy_gradient_loss | -0.0581 | +| value_loss | 0.000571 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | -0.0713 | +| time/ | | +| fps | 310 | +| iterations | 2101 | +| time_elapsed | 6925 | +| total_timesteps | 2151424 | +| train/ | | +| approx_kl | 1.4513602 | +| clip_fraction | 0.466 | +| clip_range | 0.2 | +| entropy_loss | -0.406 | +| explained_variance | -0.513 | +| learning_rate | 0.0001 | +| loss | -0.0888 | +| n_updates | 81530 | +| policy_gradient_loss | -0.0572 | +| value_loss | 0.000423 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | -0.076 | +| time/ | | +| fps | 310 | +| iterations | 2102 | +| time_elapsed | 6928 | +| total_timesteps | 2152448 | +| train/ | | +| approx_kl | 1.67448 | +| clip_fraction | 0.488 | +| clip_range | 0.2 | +| entropy_loss | -0.461 | +| explained_variance | -1.56 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 81540 | +| policy_gradient_loss | -0.0616 | +| value_loss | 0.000447 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.65e+03 | +| ep_rew_mean | -0.0808 | +| time/ | | +| fps | 310 | +| iterations | 2103 | +| time_elapsed | 6931 | +| total_timesteps | 2153472 | +| train/ | | +| approx_kl | 3.1575584 | +| clip_fraction | 0.508 | +| clip_range | 0.2 | +| entropy_loss | -0.489 | +| explained_variance | -3.98 | +| learning_rate | 0.0001 | +| loss | -0.0817 | +| n_updates | 81550 | +| policy_gradient_loss | -0.0694 | +| value_loss | 0.00042 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.65e+03 | +| ep_rew_mean | -0.0808 | +| time/ | | +| fps | 310 | +| iterations | 2104 | +| time_elapsed | 6935 | +| total_timesteps | 2154496 | +| train/ | | +| approx_kl | 1.5490909 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.419 | +| explained_variance | -2.61 | +| learning_rate | 0.0001 | +| loss | -0.0908 | +| n_updates | 81560 | +| policy_gradient_loss | -0.0691 | +| value_loss | 0.000653 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.65e+03 | +| ep_rew_mean | -0.0778 | +| time/ | | +| fps | 310 | +| iterations | 2105 | +| time_elapsed | 6938 | +| total_timesteps | 2155520 | +| train/ | | +| approx_kl | 1.6292179 | +| clip_fraction | 0.455 | +| clip_range | 0.2 | +| entropy_loss | -0.404 | +| explained_variance | -4.46 | +| learning_rate | 0.0001 | +| loss | -0.0991 | +| n_updates | 81570 | +| policy_gradient_loss | -0.0652 | +| value_loss | 0.000695 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.65e+03 | +| ep_rew_mean | -0.0833 | +| time/ | | +| fps | 310 | +| iterations | 2106 | +| time_elapsed | 6941 | +| total_timesteps | 2156544 | +| train/ | | +| approx_kl | 1.6614767 | +| clip_fraction | 0.431 | +| clip_range | 0.2 | +| entropy_loss | -0.311 | +| explained_variance | -2.45 | +| learning_rate | 0.0001 | +| loss | -0.0882 | +| n_updates | 81580 | +| policy_gradient_loss | -0.0557 | +| value_loss | 0.000617 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.58e+03 | +| ep_rew_mean | -0.0871 | +| time/ | | +| fps | 310 | +| iterations | 2107 | +| time_elapsed | 6945 | +| total_timesteps | 2157568 | +| train/ | | +| approx_kl | 1.7638823 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.441 | +| explained_variance | -3.36 | +| learning_rate | 0.0001 | +| loss | -0.0851 | +| n_updates | 81590 | +| policy_gradient_loss | -0.0588 | +| value_loss | 0.000435 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.57e+03 | +| ep_rew_mean | -0.0915 | +| time/ | | +| fps | 310 | +| iterations | 2108 | +| time_elapsed | 6948 | +| total_timesteps | 2158592 | +| train/ | | +| approx_kl | 2.9623713 | +| clip_fraction | 0.479 | +| clip_range | 0.2 | +| entropy_loss | -0.42 | +| explained_variance | -0.684 | +| learning_rate | 0.0001 | +| loss | -0.0669 | +| n_updates | 81600 | +| policy_gradient_loss | -0.0589 | +| value_loss | 0.000462 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.57e+03 | +| ep_rew_mean | -0.0915 | +| time/ | | +| fps | 310 | +| iterations | 2109 | +| time_elapsed | 6952 | +| total_timesteps | 2159616 | +| train/ | | +| approx_kl | 1.4786878 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.451 | +| explained_variance | -0.621 | +| learning_rate | 0.0001 | +| loss | -0.0772 | +| n_updates | 81610 | +| policy_gradient_loss | -0.0639 | +| value_loss | 0.000449 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.57e+03 | +| ep_rew_mean | -0.0914 | +| time/ | | +| fps | 310 | +| iterations | 2110 | +| time_elapsed | 6955 | +| total_timesteps | 2160640 | +| train/ | | +| approx_kl | 1.7508787 | +| clip_fraction | 0.449 | +| clip_range | 0.2 | +| entropy_loss | -0.392 | +| explained_variance | -5.17 | +| learning_rate | 0.0001 | +| loss | -0.0629 | +| n_updates | 81620 | +| policy_gradient_loss | -0.0522 | +| value_loss | 0.000488 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.57e+03 | +| ep_rew_mean | -0.0949 | +| time/ | | +| fps | 310 | +| iterations | 2111 | +| time_elapsed | 6959 | +| total_timesteps | 2161664 | +| train/ | | +| approx_kl | 1.3248913 | +| clip_fraction | 0.505 | +| clip_range | 0.2 | +| entropy_loss | -0.554 | +| explained_variance | -1.75 | +| learning_rate | 0.0001 | +| loss | -0.0887 | +| n_updates | 81630 | +| policy_gradient_loss | -0.063 | +| value_loss | 0.000415 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.57e+03 | +| ep_rew_mean | -0.0964 | +| time/ | | +| fps | 310 | +| iterations | 2112 | +| time_elapsed | 6962 | +| total_timesteps | 2162688 | +| train/ | | +| approx_kl | 2.130198 | +| clip_fraction | 0.489 | +| clip_range | 0.2 | +| entropy_loss | -0.441 | +| explained_variance | -1.58 | +| learning_rate | 0.0001 | +| loss | -0.0871 | +| n_updates | 81640 | +| policy_gradient_loss | -0.0633 | +| value_loss | 0.000441 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.57e+03 | +| ep_rew_mean | -0.0964 | +| time/ | | +| fps | 310 | +| iterations | 2113 | +| time_elapsed | 6966 | +| total_timesteps | 2163712 | +| train/ | | +| approx_kl | 2.4103875 | +| clip_fraction | 0.459 | +| clip_range | 0.2 | +| entropy_loss | -0.464 | +| explained_variance | -1.49 | +| learning_rate | 0.0001 | +| loss | -0.0824 | +| n_updates | 81650 | +| policy_gradient_loss | -0.0512 | +| value_loss | 0.00086 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.57e+03 | +| ep_rew_mean | -0.0947 | +| time/ | | +| fps | 310 | +| iterations | 2114 | +| time_elapsed | 6969 | +| total_timesteps | 2164736 | +| train/ | | +| approx_kl | 1.6317823 | +| clip_fraction | 0.468 | +| clip_range | 0.2 | +| entropy_loss | -0.406 | +| explained_variance | -5.77 | +| learning_rate | 0.0001 | +| loss | -0.0824 | +| n_updates | 81660 | +| policy_gradient_loss | -0.0693 | +| value_loss | 0.000432 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.57e+03 | +| ep_rew_mean | -0.0927 | +| time/ | | +| fps | 310 | +| iterations | 2115 | +| time_elapsed | 6973 | +| total_timesteps | 2165760 | +| train/ | | +| approx_kl | 2.67382 | +| clip_fraction | 0.446 | +| clip_range | 0.2 | +| entropy_loss | -0.418 | +| explained_variance | -1.89 | +| learning_rate | 0.0001 | +| loss | -0.0809 | +| n_updates | 81670 | +| policy_gradient_loss | -0.0607 | +| value_loss | 0.000579 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.57e+03 | +| ep_rew_mean | -0.0859 | +| time/ | | +| fps | 310 | +| iterations | 2116 | +| time_elapsed | 6976 | +| total_timesteps | 2166784 | +| train/ | | +| approx_kl | 2.4956179 | +| clip_fraction | 0.478 | +| clip_range | 0.2 | +| entropy_loss | -0.431 | +| explained_variance | -2.75 | +| learning_rate | 0.0001 | +| loss | -0.0641 | +| n_updates | 81680 | +| policy_gradient_loss | -0.0646 | +| value_loss | 0.00042 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.57e+03 | +| ep_rew_mean | -0.0859 | +| time/ | | +| fps | 310 | +| iterations | 2117 | +| time_elapsed | 6979 | +| total_timesteps | 2167808 | +| train/ | | +| approx_kl | 1.6862785 | +| clip_fraction | 0.505 | +| clip_range | 0.2 | +| entropy_loss | -0.493 | +| explained_variance | -0.747 | +| learning_rate | 0.0001 | +| loss | -0.0866 | +| n_updates | 81690 | +| policy_gradient_loss | -0.0664 | +| value_loss | 0.000633 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.57e+03 | +| ep_rew_mean | -0.086 | +| time/ | | +| fps | 310 | +| iterations | 2118 | +| time_elapsed | 6982 | +| total_timesteps | 2168832 | +| train/ | | +| approx_kl | 1.6821411 | +| clip_fraction | 0.501 | +| clip_range | 0.2 | +| entropy_loss | -0.531 | +| explained_variance | -8.67 | +| learning_rate | 0.0001 | +| loss | -0.078 | +| n_updates | 81700 | +| policy_gradient_loss | -0.0663 | +| value_loss | 0.000315 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.57e+03 | +| ep_rew_mean | -0.0876 | +| time/ | | +| fps | 310 | +| iterations | 2119 | +| time_elapsed | 6985 | +| total_timesteps | 2169856 | +| train/ | | +| approx_kl | 1.3228911 | +| clip_fraction | 0.462 | +| clip_range | 0.2 | +| entropy_loss | -0.422 | +| explained_variance | -0.653 | +| learning_rate | 0.0001 | +| loss | -0.0979 | +| n_updates | 81710 | +| policy_gradient_loss | -0.057 | +| value_loss | 0.000526 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.57e+03 | +| ep_rew_mean | -0.0876 | +| time/ | | +| fps | 310 | +| iterations | 2120 | +| time_elapsed | 6989 | +| total_timesteps | 2170880 | +| train/ | | +| approx_kl | 1.6990361 | +| clip_fraction | 0.47 | +| clip_range | 0.2 | +| entropy_loss | -0.413 | +| explained_variance | -1.27 | +| learning_rate | 0.0001 | +| loss | -0.0616 | +| n_updates | 81720 | +| policy_gradient_loss | -0.0613 | +| value_loss | 0.000623 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.57e+03 | +| ep_rew_mean | -0.0856 | +| time/ | | +| fps | 310 | +| iterations | 2121 | +| time_elapsed | 6992 | +| total_timesteps | 2171904 | +| train/ | | +| approx_kl | 1.7684207 | +| clip_fraction | 0.46 | +| clip_range | 0.2 | +| entropy_loss | -0.426 | +| explained_variance | -4.66 | +| learning_rate | 0.0001 | +| loss | -0.112 | +| n_updates | 81730 | +| policy_gradient_loss | -0.0517 | +| value_loss | 0.000487 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.57e+03 | +| ep_rew_mean | -0.0856 | +| time/ | | +| fps | 310 | +| iterations | 2122 | +| time_elapsed | 6995 | +| total_timesteps | 2172928 | +| train/ | | +| approx_kl | 1.6913383 | +| clip_fraction | 0.49 | +| clip_range | 0.2 | +| entropy_loss | -0.494 | +| explained_variance | -1.5 | +| learning_rate | 0.0001 | +| loss | -0.0328 | +| n_updates | 81740 | +| policy_gradient_loss | -0.0487 | +| value_loss | 0.000519 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.57e+03 | +| ep_rew_mean | -0.0847 | +| time/ | | +| fps | 310 | +| iterations | 2123 | +| time_elapsed | 6998 | +| total_timesteps | 2173952 | +| train/ | | +| approx_kl | 2.1670063 | +| clip_fraction | 0.514 | +| clip_range | 0.2 | +| entropy_loss | -0.443 | +| explained_variance | -1.57 | +| learning_rate | 0.0001 | +| loss | -0.108 | +| n_updates | 81750 | +| policy_gradient_loss | -0.0685 | +| value_loss | 0.000611 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.57e+03 | +| ep_rew_mean | -0.0833 | +| time/ | | +| fps | 310 | +| iterations | 2124 | +| time_elapsed | 7001 | +| total_timesteps | 2174976 | +| train/ | | +| approx_kl | 2.063755 | +| clip_fraction | 0.465 | +| clip_range | 0.2 | +| entropy_loss | -0.427 | +| explained_variance | -3.46 | +| learning_rate | 0.0001 | +| loss | -0.0901 | +| n_updates | 81760 | +| policy_gradient_loss | -0.0665 | +| value_loss | 0.000478 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.57e+03 | +| ep_rew_mean | -0.0833 | +| time/ | | +| fps | 310 | +| iterations | 2125 | +| time_elapsed | 7005 | +| total_timesteps | 2176000 | +| train/ | | +| approx_kl | 1.737262 | +| clip_fraction | 0.482 | +| clip_range | 0.2 | +| entropy_loss | -0.43 | +| explained_variance | -5.38 | +| learning_rate | 0.0001 | +| loss | -0.077 | +| n_updates | 81770 | +| policy_gradient_loss | -0.0681 | +| value_loss | 0.000514 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.57e+03 | +| ep_rew_mean | -0.081 | +| time/ | | +| fps | 310 | +| iterations | 2126 | +| time_elapsed | 7008 | +| total_timesteps | 2177024 | +| train/ | | +| approx_kl | 2.009592 | +| clip_fraction | 0.465 | +| clip_range | 0.2 | +| entropy_loss | -0.435 | +| explained_variance | -1.62 | +| learning_rate | 0.0001 | +| loss | -0.0551 | +| n_updates | 81780 | +| policy_gradient_loss | -0.0593 | +| value_loss | 0.000431 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.56e+03 | +| ep_rew_mean | -0.0885 | +| time/ | | +| fps | 310 | +| iterations | 2127 | +| time_elapsed | 7011 | +| total_timesteps | 2178048 | +| train/ | | +| approx_kl | 1.5878212 | +| clip_fraction | 0.465 | +| clip_range | 0.2 | +| entropy_loss | -0.412 | +| explained_variance | -4.39 | +| learning_rate | 0.0001 | +| loss | -0.0479 | +| n_updates | 81790 | +| policy_gradient_loss | -0.0609 | +| value_loss | 0.000454 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.56e+03 | +| ep_rew_mean | -0.0896 | +| time/ | | +| fps | 310 | +| iterations | 2128 | +| time_elapsed | 7014 | +| total_timesteps | 2179072 | +| train/ | | +| approx_kl | 1.8194795 | +| clip_fraction | 0.466 | +| clip_range | 0.2 | +| entropy_loss | -0.433 | +| explained_variance | -1.24 | +| learning_rate | 0.0001 | +| loss | -0.0749 | +| n_updates | 81800 | +| policy_gradient_loss | -0.0608 | +| value_loss | 0.000632 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.56e+03 | +| ep_rew_mean | -0.0896 | +| time/ | | +| fps | 310 | +| iterations | 2129 | +| time_elapsed | 7018 | +| total_timesteps | 2180096 | +| train/ | | +| approx_kl | 1.4969635 | +| clip_fraction | 0.476 | +| clip_range | 0.2 | +| entropy_loss | -0.533 | +| explained_variance | -1.12 | +| learning_rate | 0.0001 | +| loss | -0.0684 | +| n_updates | 81810 | +| policy_gradient_loss | -0.06 | +| value_loss | 0.000583 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.56e+03 | +| ep_rew_mean | -0.0864 | +| time/ | | +| fps | 310 | +| iterations | 2130 | +| time_elapsed | 7021 | +| total_timesteps | 2181120 | +| train/ | | +| approx_kl | 3.1986156 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.402 | +| explained_variance | -4.14 | +| learning_rate | 0.0001 | +| loss | -0.0859 | +| n_updates | 81820 | +| policy_gradient_loss | -0.0635 | +| value_loss | 0.000663 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.56e+03 | +| ep_rew_mean | -0.0864 | +| time/ | | +| fps | 310 | +| iterations | 2131 | +| time_elapsed | 7025 | +| total_timesteps | 2182144 | +| train/ | | +| approx_kl | 3.547579 | +| clip_fraction | 0.489 | +| clip_range | 0.2 | +| entropy_loss | -0.529 | +| explained_variance | -9.67 | +| learning_rate | 0.0001 | +| loss | -0.105 | +| n_updates | 81830 | +| policy_gradient_loss | -0.0713 | +| value_loss | 0.000321 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.56e+03 | +| ep_rew_mean | -0.0887 | +| time/ | | +| fps | 310 | +| iterations | 2132 | +| time_elapsed | 7028 | +| total_timesteps | 2183168 | +| train/ | | +| approx_kl | 1.4741362 | +| clip_fraction | 0.477 | +| clip_range | 0.2 | +| entropy_loss | -0.473 | +| explained_variance | -4.1 | +| learning_rate | 0.0001 | +| loss | -0.0957 | +| n_updates | 81840 | +| policy_gradient_loss | -0.066 | +| value_loss | 0.000339 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.56e+03 | +| ep_rew_mean | -0.0887 | +| time/ | | +| fps | 310 | +| iterations | 2133 | +| time_elapsed | 7031 | +| total_timesteps | 2184192 | +| train/ | | +| approx_kl | 1.8704832 | +| clip_fraction | 0.459 | +| clip_range | 0.2 | +| entropy_loss | -0.387 | +| explained_variance | -0.898 | +| learning_rate | 0.0001 | +| loss | -0.0841 | +| n_updates | 81850 | +| policy_gradient_loss | -0.0537 | +| value_loss | 0.000756 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.57e+03 | +| ep_rew_mean | -0.0855 | +| time/ | | +| fps | 310 | +| iterations | 2134 | +| time_elapsed | 7034 | +| total_timesteps | 2185216 | +| train/ | | +| approx_kl | 1.8048483 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.42 | +| explained_variance | -7.36 | +| learning_rate | 0.0001 | +| loss | -0.0863 | +| n_updates | 81860 | +| policy_gradient_loss | -0.0703 | +| value_loss | 0.000816 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.57e+03 | +| ep_rew_mean | -0.0855 | +| time/ | | +| fps | 310 | +| iterations | 2135 | +| time_elapsed | 7037 | +| total_timesteps | 2186240 | +| train/ | | +| approx_kl | 3.2301424 | +| clip_fraction | 0.455 | +| clip_range | 0.2 | +| entropy_loss | -0.395 | +| explained_variance | -4.2 | +| learning_rate | 0.0001 | +| loss | -0.0818 | +| n_updates | 81870 | +| policy_gradient_loss | -0.0588 | +| value_loss | 0.000656 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.58e+03 | +| ep_rew_mean | -0.08 | +| time/ | | +| fps | 310 | +| iterations | 2136 | +| time_elapsed | 7040 | +| total_timesteps | 2187264 | +| train/ | | +| approx_kl | 1.7126757 | +| clip_fraction | 0.494 | +| clip_range | 0.2 | +| entropy_loss | -0.46 | +| explained_variance | -2 | +| learning_rate | 0.0001 | +| loss | -0.0808 | +| n_updates | 81880 | +| policy_gradient_loss | -0.0589 | +| value_loss | 0.000651 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.57e+03 | +| ep_rew_mean | -0.0826 | +| time/ | | +| fps | 310 | +| iterations | 2137 | +| time_elapsed | 7044 | +| total_timesteps | 2188288 | +| train/ | | +| approx_kl | 1.8617038 | +| clip_fraction | 0.499 | +| clip_range | 0.2 | +| entropy_loss | -0.442 | +| explained_variance | -6.24 | +| learning_rate | 0.0001 | +| loss | -0.0773 | +| n_updates | 81890 | +| policy_gradient_loss | -0.0741 | +| value_loss | 0.000383 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.57e+03 | +| ep_rew_mean | -0.0826 | +| time/ | | +| fps | 310 | +| iterations | 2138 | +| time_elapsed | 7047 | +| total_timesteps | 2189312 | +| train/ | | +| approx_kl | 1.7429235 | +| clip_fraction | 0.434 | +| clip_range | 0.2 | +| entropy_loss | -0.358 | +| explained_variance | -1.45 | +| learning_rate | 0.0001 | +| loss | -0.0829 | +| n_updates | 81900 | +| policy_gradient_loss | -0.065 | +| value_loss | 0.000766 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.57e+03 | +| ep_rew_mean | -0.0837 | +| time/ | | +| fps | 310 | +| iterations | 2139 | +| time_elapsed | 7050 | +| total_timesteps | 2190336 | +| train/ | | +| approx_kl | 1.7789943 | +| clip_fraction | 0.445 | +| clip_range | 0.2 | +| entropy_loss | -0.385 | +| explained_variance | -3.78 | +| learning_rate | 0.0001 | +| loss | -0.0711 | +| n_updates | 81910 | +| policy_gradient_loss | -0.0589 | +| value_loss | 0.000472 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.57e+03 | +| ep_rew_mean | -0.0837 | +| time/ | | +| fps | 310 | +| iterations | 2140 | +| time_elapsed | 7053 | +| total_timesteps | 2191360 | +| train/ | | +| approx_kl | 2.148478 | +| clip_fraction | 0.453 | +| clip_range | 0.2 | +| entropy_loss | -0.417 | +| explained_variance | -1.6 | +| learning_rate | 0.0001 | +| loss | -0.0678 | +| n_updates | 81920 | +| policy_gradient_loss | -0.059 | +| value_loss | 0.000417 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.57e+03 | +| ep_rew_mean | -0.0804 | +| time/ | | +| fps | 310 | +| iterations | 2141 | +| time_elapsed | 7056 | +| total_timesteps | 2192384 | +| train/ | | +| approx_kl | 1.7514676 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.403 | +| explained_variance | -5.26 | +| learning_rate | 0.0001 | +| loss | -0.0641 | +| n_updates | 81930 | +| policy_gradient_loss | -0.0631 | +| value_loss | 0.000577 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.57e+03 | +| ep_rew_mean | -0.0811 | +| time/ | | +| fps | 310 | +| iterations | 2142 | +| time_elapsed | 7059 | +| total_timesteps | 2193408 | +| train/ | | +| approx_kl | 1.7717643 | +| clip_fraction | 0.397 | +| clip_range | 0.2 | +| entropy_loss | -0.32 | +| explained_variance | -3.3 | +| learning_rate | 0.0001 | +| loss | -0.0621 | +| n_updates | 81940 | +| policy_gradient_loss | -0.056 | +| value_loss | 0.000558 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.57e+03 | +| ep_rew_mean | -0.0811 | +| time/ | | +| fps | 310 | +| iterations | 2143 | +| time_elapsed | 7063 | +| total_timesteps | 2194432 | +| train/ | | +| approx_kl | 2.0703473 | +| clip_fraction | 0.426 | +| clip_range | 0.2 | +| entropy_loss | -0.357 | +| explained_variance | -5.55 | +| learning_rate | 0.0001 | +| loss | -0.107 | +| n_updates | 81950 | +| policy_gradient_loss | -0.0645 | +| value_loss | 0.000595 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.57e+03 | +| ep_rew_mean | -0.0852 | +| time/ | | +| fps | 310 | +| iterations | 2144 | +| time_elapsed | 7067 | +| total_timesteps | 2195456 | +| train/ | | +| approx_kl | 1.4912753 | +| clip_fraction | 0.411 | +| clip_range | 0.2 | +| entropy_loss | -0.334 | +| explained_variance | -2.76 | +| learning_rate | 0.0001 | +| loss | -0.0785 | +| n_updates | 81960 | +| policy_gradient_loss | -0.047 | +| value_loss | 0.000564 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.57e+03 | +| ep_rew_mean | -0.0859 | +| time/ | | +| fps | 310 | +| iterations | 2145 | +| time_elapsed | 7070 | +| total_timesteps | 2196480 | +| train/ | | +| approx_kl | 1.9945729 | +| clip_fraction | 0.46 | +| clip_range | 0.2 | +| entropy_loss | -0.34 | +| explained_variance | -1.41 | +| learning_rate | 0.0001 | +| loss | -0.0822 | +| n_updates | 81970 | +| policy_gradient_loss | -0.0637 | +| value_loss | 0.000529 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.57e+03 | +| ep_rew_mean | -0.0859 | +| time/ | | +| fps | 310 | +| iterations | 2146 | +| time_elapsed | 7074 | +| total_timesteps | 2197504 | +| train/ | | +| approx_kl | 1.9016879 | +| clip_fraction | 0.438 | +| clip_range | 0.2 | +| entropy_loss | -0.366 | +| explained_variance | -3.64 | +| learning_rate | 0.0001 | +| loss | -0.0697 | +| n_updates | 81980 | +| policy_gradient_loss | -0.0658 | +| value_loss | 0.000549 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.57e+03 | +| ep_rew_mean | -0.0891 | +| time/ | | +| fps | 310 | +| iterations | 2147 | +| time_elapsed | 7077 | +| total_timesteps | 2198528 | +| train/ | | +| approx_kl | 1.9699214 | +| clip_fraction | 0.459 | +| clip_range | 0.2 | +| entropy_loss | -0.362 | +| explained_variance | -2.94 | +| learning_rate | 0.0001 | +| loss | -0.0657 | +| n_updates | 81990 | +| policy_gradient_loss | -0.0617 | +| value_loss | 0.000726 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.57e+03 | +| ep_rew_mean | -0.0891 | +| time/ | | +| fps | 310 | +| iterations | 2148 | +| time_elapsed | 7081 | +| total_timesteps | 2199552 | +| train/ | | +| approx_kl | 2.1544528 | +| clip_fraction | 0.479 | +| clip_range | 0.2 | +| entropy_loss | -0.406 | +| explained_variance | -2.52 | +| learning_rate | 0.0001 | +| loss | -0.086 | +| n_updates | 82000 | +| policy_gradient_loss | -0.0635 | +| value_loss | 0.000818 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.57e+03 | +| ep_rew_mean | -0.0888 | +| time/ | | +| fps | 310 | +| iterations | 2149 | +| time_elapsed | 7084 | +| total_timesteps | 2200576 | +| train/ | | +| approx_kl | 2.1832523 | +| clip_fraction | 0.476 | +| clip_range | 0.2 | +| entropy_loss | -0.416 | +| explained_variance | -10.8 | +| learning_rate | 0.0001 | +| loss | -0.084 | +| n_updates | 82010 | +| policy_gradient_loss | -0.0615 | +| value_loss | 0.000445 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.56e+03 | +| ep_rew_mean | -0.0887 | +| time/ | | +| fps | 310 | +| iterations | 2150 | +| time_elapsed | 7088 | +| total_timesteps | 2201600 | +| train/ | | +| approx_kl | 1.6733122 | +| clip_fraction | 0.464 | +| clip_range | 0.2 | +| entropy_loss | -0.406 | +| explained_variance | -1.04 | +| learning_rate | 0.0001 | +| loss | -0.0712 | +| n_updates | 82020 | +| policy_gradient_loss | -0.054 | +| value_loss | 0.000784 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.56e+03 | +| ep_rew_mean | -0.0887 | +| time/ | | +| fps | 310 | +| iterations | 2151 | +| time_elapsed | 7091 | +| total_timesteps | 2202624 | +| train/ | | +| approx_kl | 1.7904253 | +| clip_fraction | 0.449 | +| clip_range | 0.2 | +| entropy_loss | -0.367 | +| explained_variance | -6.75 | +| learning_rate | 0.0001 | +| loss | -0.0842 | +| n_updates | 82030 | +| policy_gradient_loss | -0.0582 | +| value_loss | 0.000646 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.57e+03 | +| ep_rew_mean | -0.087 | +| time/ | | +| fps | 310 | +| iterations | 2152 | +| time_elapsed | 7094 | +| total_timesteps | 2203648 | +| train/ | | +| approx_kl | 2.566813 | +| clip_fraction | 0.46 | +| clip_range | 0.2 | +| entropy_loss | -0.383 | +| explained_variance | -1.64 | +| learning_rate | 0.0001 | +| loss | -0.0822 | +| n_updates | 82040 | +| policy_gradient_loss | -0.0612 | +| value_loss | 0.000376 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.57e+03 | +| ep_rew_mean | -0.087 | +| time/ | | +| fps | 310 | +| iterations | 2153 | +| time_elapsed | 7098 | +| total_timesteps | 2204672 | +| train/ | | +| approx_kl | 2.0453072 | +| clip_fraction | 0.442 | +| clip_range | 0.2 | +| entropy_loss | -0.308 | +| explained_variance | -4.39 | +| learning_rate | 0.0001 | +| loss | -0.0691 | +| n_updates | 82050 | +| policy_gradient_loss | -0.062 | +| value_loss | 0.000583 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.57e+03 | +| ep_rew_mean | -0.0875 | +| time/ | | +| fps | 310 | +| iterations | 2154 | +| time_elapsed | 7101 | +| total_timesteps | 2205696 | +| train/ | | +| approx_kl | 1.9837323 | +| clip_fraction | 0.455 | +| clip_range | 0.2 | +| entropy_loss | -0.368 | +| explained_variance | -6.6 | +| learning_rate | 0.0001 | +| loss | -0.0906 | +| n_updates | 82060 | +| policy_gradient_loss | -0.062 | +| value_loss | 0.000259 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.56e+03 | +| ep_rew_mean | -0.0886 | +| time/ | | +| fps | 310 | +| iterations | 2155 | +| time_elapsed | 7104 | +| total_timesteps | 2206720 | +| train/ | | +| approx_kl | 2.025941 | +| clip_fraction | 0.448 | +| clip_range | 0.2 | +| entropy_loss | -0.316 | +| explained_variance | -1.12 | +| learning_rate | 0.0001 | +| loss | -0.0824 | +| n_updates | 82070 | +| policy_gradient_loss | -0.0576 | +| value_loss | 0.000647 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.56e+03 | +| ep_rew_mean | -0.0886 | +| time/ | | +| fps | 310 | +| iterations | 2156 | +| time_elapsed | 7107 | +| total_timesteps | 2207744 | +| train/ | | +| approx_kl | 1.5056348 | +| clip_fraction | 0.397 | +| clip_range | 0.2 | +| entropy_loss | -0.33 | +| explained_variance | -0.942 | +| learning_rate | 0.0001 | +| loss | -0.0784 | +| n_updates | 82080 | +| policy_gradient_loss | -0.0585 | +| value_loss | 0.000533 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.56e+03 | +| ep_rew_mean | -0.0856 | +| time/ | | +| fps | 310 | +| iterations | 2157 | +| time_elapsed | 7110 | +| total_timesteps | 2208768 | +| train/ | | +| approx_kl | 15.032631 | +| clip_fraction | 0.449 | +| clip_range | 0.2 | +| entropy_loss | -0.446 | +| explained_variance | -0.717 | +| learning_rate | 0.0001 | +| loss | -0.081 | +| n_updates | 82090 | +| policy_gradient_loss | -0.0581 | +| value_loss | 0.000771 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.56e+03 | +| ep_rew_mean | -0.0856 | +| time/ | | +| fps | 310 | +| iterations | 2158 | +| time_elapsed | 7113 | +| total_timesteps | 2209792 | +| train/ | | +| approx_kl | 2.2574391 | +| clip_fraction | 0.462 | +| clip_range | 0.2 | +| entropy_loss | -0.332 | +| explained_variance | -3.01 | +| learning_rate | 0.0001 | +| loss | -0.0834 | +| n_updates | 82100 | +| policy_gradient_loss | -0.0568 | +| value_loss | 0.000478 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.56e+03 | +| ep_rew_mean | -0.0871 | +| time/ | | +| fps | 310 | +| iterations | 2159 | +| time_elapsed | 7117 | +| total_timesteps | 2210816 | +| train/ | | +| approx_kl | 1.70997 | +| clip_fraction | 0.458 | +| clip_range | 0.2 | +| entropy_loss | -0.362 | +| explained_variance | -2.59 | +| learning_rate | 0.0001 | +| loss | -0.0924 | +| n_updates | 82110 | +| policy_gradient_loss | -0.0599 | +| value_loss | 0.000413 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.56e+03 | +| ep_rew_mean | -0.0871 | +| time/ | | +| fps | 310 | +| iterations | 2160 | +| time_elapsed | 7120 | +| total_timesteps | 2211840 | +| train/ | | +| approx_kl | 1.9971862 | +| clip_fraction | 0.442 | +| clip_range | 0.2 | +| entropy_loss | -0.346 | +| explained_variance | -2.38 | +| learning_rate | 0.0001 | +| loss | -0.0605 | +| n_updates | 82120 | +| policy_gradient_loss | -0.0569 | +| value_loss | 0.000255 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.56e+03 | +| ep_rew_mean | -0.0873 | +| time/ | | +| fps | 310 | +| iterations | 2161 | +| time_elapsed | 7123 | +| total_timesteps | 2212864 | +| train/ | | +| approx_kl | 2.0458994 | +| clip_fraction | 0.473 | +| clip_range | 0.2 | +| entropy_loss | -0.391 | +| explained_variance | -6.55 | +| learning_rate | 0.0001 | +| loss | -0.0416 | +| n_updates | 82130 | +| policy_gradient_loss | -0.0464 | +| value_loss | 0.000467 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.56e+03 | +| ep_rew_mean | -0.0881 | +| time/ | | +| fps | 310 | +| iterations | 2162 | +| time_elapsed | 7127 | +| total_timesteps | 2213888 | +| train/ | | +| approx_kl | 2.3314188 | +| clip_fraction | 0.455 | +| clip_range | 0.2 | +| entropy_loss | -0.344 | +| explained_variance | -2.12 | +| learning_rate | 0.0001 | +| loss | -0.0918 | +| n_updates | 82140 | +| policy_gradient_loss | -0.0562 | +| value_loss | 0.000692 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.56e+03 | +| ep_rew_mean | -0.0881 | +| time/ | | +| fps | 310 | +| iterations | 2163 | +| time_elapsed | 7130 | +| total_timesteps | 2214912 | +| train/ | | +| approx_kl | 2.098511 | +| clip_fraction | 0.437 | +| clip_range | 0.2 | +| entropy_loss | -0.348 | +| explained_variance | -3.12 | +| learning_rate | 0.0001 | +| loss | -0.0968 | +| n_updates | 82150 | +| policy_gradient_loss | -0.0606 | +| value_loss | 0.00065 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.56e+03 | +| ep_rew_mean | -0.0869 | +| time/ | | +| fps | 310 | +| iterations | 2164 | +| time_elapsed | 7134 | +| total_timesteps | 2215936 | +| train/ | | +| approx_kl | 1.7674434 | +| clip_fraction | 0.466 | +| clip_range | 0.2 | +| entropy_loss | -0.379 | +| explained_variance | -2.89 | +| learning_rate | 0.0001 | +| loss | -0.0908 | +| n_updates | 82160 | +| policy_gradient_loss | -0.0598 | +| value_loss | 0.000503 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.55e+03 | +| ep_rew_mean | -0.0909 | +| time/ | | +| fps | 310 | +| iterations | 2165 | +| time_elapsed | 7137 | +| total_timesteps | 2216960 | +| train/ | | +| approx_kl | 2.0687056 | +| clip_fraction | 0.432 | +| clip_range | 0.2 | +| entropy_loss | -0.348 | +| explained_variance | -3.81 | +| learning_rate | 0.0001 | +| loss | -0.0929 | +| n_updates | 82170 | +| policy_gradient_loss | -0.0618 | +| value_loss | 0.000895 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.55e+03 | +| ep_rew_mean | -0.0909 | +| time/ | | +| fps | 310 | +| iterations | 2166 | +| time_elapsed | 7141 | +| total_timesteps | 2217984 | +| train/ | | +| approx_kl | 1.7155514 | +| clip_fraction | 0.41 | +| clip_range | 0.2 | +| entropy_loss | -0.351 | +| explained_variance | -1.73 | +| learning_rate | 0.0001 | +| loss | -0.0662 | +| n_updates | 82180 | +| policy_gradient_loss | -0.0523 | +| value_loss | 0.000574 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.54e+03 | +| ep_rew_mean | -0.0939 | +| time/ | | +| fps | 310 | +| iterations | 2167 | +| time_elapsed | 7144 | +| total_timesteps | 2219008 | +| train/ | | +| approx_kl | 1.8552287 | +| clip_fraction | 0.418 | +| clip_range | 0.2 | +| entropy_loss | -0.317 | +| explained_variance | -2.74 | +| learning_rate | 0.0001 | +| loss | -0.085 | +| n_updates | 82190 | +| policy_gradient_loss | -0.0542 | +| value_loss | 0.000731 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.54e+03 | +| ep_rew_mean | -0.0939 | +| time/ | | +| fps | 310 | +| iterations | 2168 | +| time_elapsed | 7148 | +| total_timesteps | 2220032 | +| train/ | | +| approx_kl | 1.8638117 | +| clip_fraction | 0.392 | +| clip_range | 0.2 | +| entropy_loss | -0.283 | +| explained_variance | -1.55 | +| learning_rate | 0.0001 | +| loss | -0.0904 | +| n_updates | 82200 | +| policy_gradient_loss | -0.0533 | +| value_loss | 0.000779 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.53e+03 | +| ep_rew_mean | -0.0975 | +| time/ | | +| fps | 310 | +| iterations | 2169 | +| time_elapsed | 7151 | +| total_timesteps | 2221056 | +| train/ | | +| approx_kl | 1.8357003 | +| clip_fraction | 0.431 | +| clip_range | 0.2 | +| entropy_loss | -0.318 | +| explained_variance | -3.29 | +| learning_rate | 0.0001 | +| loss | -0.087 | +| n_updates | 82210 | +| policy_gradient_loss | -0.0609 | +| value_loss | 0.00062 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.54e+03 | +| ep_rew_mean | -0.0964 | +| time/ | | +| fps | 310 | +| iterations | 2170 | +| time_elapsed | 7154 | +| total_timesteps | 2222080 | +| train/ | | +| approx_kl | 1.7618241 | +| clip_fraction | 0.474 | +| clip_range | 0.2 | +| entropy_loss | -0.37 | +| explained_variance | -5.76 | +| learning_rate | 0.0001 | +| loss | -0.0969 | +| n_updates | 82220 | +| policy_gradient_loss | -0.0635 | +| value_loss | 0.000329 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.54e+03 | +| ep_rew_mean | -0.0964 | +| time/ | | +| fps | 310 | +| iterations | 2171 | +| time_elapsed | 7157 | +| total_timesteps | 2223104 | +| train/ | | +| approx_kl | 1.7758894 | +| clip_fraction | 0.436 | +| clip_range | 0.2 | +| entropy_loss | -0.324 | +| explained_variance | -1.27 | +| learning_rate | 0.0001 | +| loss | -0.0738 | +| n_updates | 82230 | +| policy_gradient_loss | -0.0582 | +| value_loss | 0.00048 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.54e+03 | +| ep_rew_mean | -0.101 | +| time/ | | +| fps | 310 | +| iterations | 2172 | +| time_elapsed | 7160 | +| total_timesteps | 2224128 | +| train/ | | +| approx_kl | 1.7739927 | +| clip_fraction | 0.478 | +| clip_range | 0.2 | +| entropy_loss | -0.442 | +| explained_variance | -10.3 | +| learning_rate | 0.0001 | +| loss | -0.0744 | +| n_updates | 82240 | +| policy_gradient_loss | -0.0638 | +| value_loss | 0.000415 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.53e+03 | +| ep_rew_mean | -0.106 | +| time/ | | +| fps | 310 | +| iterations | 2173 | +| time_elapsed | 7163 | +| total_timesteps | 2225152 | +| train/ | | +| approx_kl | 2.0623846 | +| clip_fraction | 0.425 | +| clip_range | 0.2 | +| entropy_loss | -0.369 | +| explained_variance | -1.35 | +| learning_rate | 0.0001 | +| loss | -0.0689 | +| n_updates | 82250 | +| policy_gradient_loss | -0.0536 | +| value_loss | 0.000647 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.53e+03 | +| ep_rew_mean | -0.106 | +| time/ | | +| fps | 310 | +| iterations | 2174 | +| time_elapsed | 7167 | +| total_timesteps | 2226176 | +| train/ | | +| approx_kl | 2.0088005 | +| clip_fraction | 0.435 | +| clip_range | 0.2 | +| entropy_loss | -0.321 | +| explained_variance | -2.56 | +| learning_rate | 0.0001 | +| loss | -0.0798 | +| n_updates | 82260 | +| policy_gradient_loss | -0.0622 | +| value_loss | 0.000535 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.54e+03 | +| ep_rew_mean | -0.103 | +| time/ | | +| fps | 310 | +| iterations | 2175 | +| time_elapsed | 7170 | +| total_timesteps | 2227200 | +| train/ | | +| approx_kl | 1.8351965 | +| clip_fraction | 0.443 | +| clip_range | 0.2 | +| entropy_loss | -0.37 | +| explained_variance | -1.2 | +| learning_rate | 0.0001 | +| loss | -0.0792 | +| n_updates | 82270 | +| policy_gradient_loss | -0.0563 | +| value_loss | 0.000698 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.54e+03 | +| ep_rew_mean | -0.103 | +| time/ | | +| fps | 310 | +| iterations | 2176 | +| time_elapsed | 7173 | +| total_timesteps | 2228224 | +| train/ | | +| approx_kl | 2.250017 | +| clip_fraction | 0.421 | +| clip_range | 0.2 | +| entropy_loss | -0.314 | +| explained_variance | -1.35 | +| learning_rate | 0.0001 | +| loss | -0.0767 | +| n_updates | 82280 | +| policy_gradient_loss | -0.0557 | +| value_loss | 0.000549 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.54e+03 | +| ep_rew_mean | -0.105 | +| time/ | | +| fps | 310 | +| iterations | 2177 | +| time_elapsed | 7176 | +| total_timesteps | 2229248 | +| train/ | | +| approx_kl | 2.9400868 | +| clip_fraction | 0.469 | +| clip_range | 0.2 | +| entropy_loss | -0.465 | +| explained_variance | -3.63 | +| learning_rate | 0.0001 | +| loss | -0.0803 | +| n_updates | 82290 | +| policy_gradient_loss | -0.0666 | +| value_loss | 0.000253 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.54e+03 | +| ep_rew_mean | -0.105 | +| time/ | | +| fps | 310 | +| iterations | 2178 | +| time_elapsed | 7179 | +| total_timesteps | 2230272 | +| train/ | | +| approx_kl | 1.9121661 | +| clip_fraction | 0.423 | +| clip_range | 0.2 | +| entropy_loss | -0.313 | +| explained_variance | -0.756 | +| learning_rate | 0.0001 | +| loss | -0.0406 | +| n_updates | 82300 | +| policy_gradient_loss | -0.0419 | +| value_loss | 0.000693 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.54e+03 | +| ep_rew_mean | -0.105 | +| time/ | | +| fps | 310 | +| iterations | 2179 | +| time_elapsed | 7183 | +| total_timesteps | 2231296 | +| train/ | | +| approx_kl | 2.0282383 | +| clip_fraction | 0.432 | +| clip_range | 0.2 | +| entropy_loss | -0.31 | +| explained_variance | -2.47 | +| learning_rate | 0.0001 | +| loss | -0.0853 | +| n_updates | 82310 | +| policy_gradient_loss | -0.0598 | +| value_loss | 0.000634 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.54e+03 | +| ep_rew_mean | -0.109 | +| time/ | | +| fps | 310 | +| iterations | 2180 | +| time_elapsed | 7186 | +| total_timesteps | 2232320 | +| train/ | | +| approx_kl | 2.3835952 | +| clip_fraction | 0.45 | +| clip_range | 0.2 | +| entropy_loss | -0.4 | +| explained_variance | -5.06 | +| learning_rate | 0.0001 | +| loss | -0.0852 | +| n_updates | 82320 | +| policy_gradient_loss | -0.0605 | +| value_loss | 0.000541 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.54e+03 | +| ep_rew_mean | -0.106 | +| time/ | | +| fps | 310 | +| iterations | 2181 | +| time_elapsed | 7189 | +| total_timesteps | 2233344 | +| train/ | | +| approx_kl | 2.136564 | +| clip_fraction | 0.393 | +| clip_range | 0.2 | +| entropy_loss | -0.261 | +| explained_variance | -0.695 | +| learning_rate | 0.0001 | +| loss | -0.0735 | +| n_updates | 82330 | +| policy_gradient_loss | -0.057 | +| value_loss | 0.000866 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.53e+03 | +| ep_rew_mean | -0.107 | +| time/ | | +| fps | 310 | +| iterations | 2182 | +| time_elapsed | 7193 | +| total_timesteps | 2234368 | +| train/ | | +| approx_kl | 2.0902953 | +| clip_fraction | 0.404 | +| clip_range | 0.2 | +| entropy_loss | -0.302 | +| explained_variance | -1.65 | +| learning_rate | 0.0001 | +| loss | -0.0658 | +| n_updates | 82340 | +| policy_gradient_loss | -0.0544 | +| value_loss | 0.000747 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.53e+03 | +| ep_rew_mean | -0.107 | +| time/ | | +| fps | 310 | +| iterations | 2183 | +| time_elapsed | 7196 | +| total_timesteps | 2235392 | +| train/ | | +| approx_kl | 1.235298 | +| clip_fraction | 0.419 | +| clip_range | 0.2 | +| entropy_loss | -0.437 | +| explained_variance | -0.854 | +| learning_rate | 0.0001 | +| loss | -0.0512 | +| n_updates | 82350 | +| policy_gradient_loss | -0.0531 | +| value_loss | 0.000604 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.54e+03 | +| ep_rew_mean | -0.108 | +| time/ | | +| fps | 310 | +| iterations | 2184 | +| time_elapsed | 7200 | +| total_timesteps | 2236416 | +| train/ | | +| approx_kl | 2.2451677 | +| clip_fraction | 0.466 | +| clip_range | 0.2 | +| entropy_loss | -0.405 | +| explained_variance | -2.87 | +| learning_rate | 0.0001 | +| loss | -0.108 | +| n_updates | 82360 | +| policy_gradient_loss | -0.0666 | +| value_loss | 0.000559 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.54e+03 | +| ep_rew_mean | -0.11 | +| time/ | | +| fps | 310 | +| iterations | 2185 | +| time_elapsed | 7203 | +| total_timesteps | 2237440 | +| train/ | | +| approx_kl | 2.3616538 | +| clip_fraction | 0.426 | +| clip_range | 0.2 | +| entropy_loss | -0.34 | +| explained_variance | -5.75 | +| learning_rate | 0.0001 | +| loss | -0.0828 | +| n_updates | 82370 | +| policy_gradient_loss | -0.0595 | +| value_loss | 0.000355 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.54e+03 | +| ep_rew_mean | -0.11 | +| time/ | | +| fps | 310 | +| iterations | 2186 | +| time_elapsed | 7207 | +| total_timesteps | 2238464 | +| train/ | | +| approx_kl | 1.4715552 | +| clip_fraction | 0.408 | +| clip_range | 0.2 | +| entropy_loss | -0.353 | +| explained_variance | -1 | +| learning_rate | 0.0001 | +| loss | -0.0537 | +| n_updates | 82380 | +| policy_gradient_loss | -0.054 | +| value_loss | 0.000642 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.54e+03 | +| ep_rew_mean | -0.106 | +| time/ | | +| fps | 310 | +| iterations | 2187 | +| time_elapsed | 7210 | +| total_timesteps | 2239488 | +| train/ | | +| approx_kl | 1.9821388 | +| clip_fraction | 0.407 | +| clip_range | 0.2 | +| entropy_loss | -0.302 | +| explained_variance | -3.58 | +| learning_rate | 0.0001 | +| loss | -0.0581 | +| n_updates | 82390 | +| policy_gradient_loss | -0.0552 | +| value_loss | 0.000735 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.53e+03 | +| ep_rew_mean | -0.106 | +| time/ | | +| fps | 310 | +| iterations | 2188 | +| time_elapsed | 7213 | +| total_timesteps | 2240512 | +| train/ | | +| approx_kl | 7.5316343 | +| clip_fraction | 0.437 | +| clip_range | 0.2 | +| entropy_loss | -0.36 | +| explained_variance | -4.95 | +| learning_rate | 0.0001 | +| loss | -0.0947 | +| n_updates | 82400 | +| policy_gradient_loss | -0.062 | +| value_loss | 0.000656 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.53e+03 | +| ep_rew_mean | -0.108 | +| time/ | | +| fps | 310 | +| iterations | 2189 | +| time_elapsed | 7217 | +| total_timesteps | 2241536 | +| train/ | | +| approx_kl | 3.0567393 | +| clip_fraction | 0.406 | +| clip_range | 0.2 | +| entropy_loss | -0.328 | +| explained_variance | -2.28 | +| learning_rate | 0.0001 | +| loss | -0.0552 | +| n_updates | 82410 | +| policy_gradient_loss | -0.0317 | +| value_loss | 0.000521 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.53e+03 | +| ep_rew_mean | -0.108 | +| time/ | | +| fps | 310 | +| iterations | 2190 | +| time_elapsed | 7220 | +| total_timesteps | 2242560 | +| train/ | | +| approx_kl | 1.695703 | +| clip_fraction | 0.39 | +| clip_range | 0.2 | +| entropy_loss | -0.334 | +| explained_variance | -1.24 | +| learning_rate | 0.0001 | +| loss | -0.0703 | +| n_updates | 82420 | +| policy_gradient_loss | -0.0527 | +| value_loss | 0.000511 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.53e+03 | +| ep_rew_mean | -0.108 | +| time/ | | +| fps | 310 | +| iterations | 2191 | +| time_elapsed | 7223 | +| total_timesteps | 2243584 | +| train/ | | +| approx_kl | 2.254467 | +| clip_fraction | 0.486 | +| clip_range | 0.2 | +| entropy_loss | -0.442 | +| explained_variance | -0.703 | +| learning_rate | 0.0001 | +| loss | -0.0906 | +| n_updates | 82430 | +| policy_gradient_loss | -0.0567 | +| value_loss | 0.000608 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.54e+03 | +| ep_rew_mean | -0.105 | +| time/ | | +| fps | 310 | +| iterations | 2192 | +| time_elapsed | 7226 | +| total_timesteps | 2244608 | +| train/ | | +| approx_kl | 1.7004886 | +| clip_fraction | 0.428 | +| clip_range | 0.2 | +| entropy_loss | -0.329 | +| explained_variance | -13.3 | +| learning_rate | 0.0001 | +| loss | -0.0913 | +| n_updates | 82440 | +| policy_gradient_loss | -0.0558 | +| value_loss | 0.000534 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.54e+03 | +| ep_rew_mean | -0.105 | +| time/ | | +| fps | 310 | +| iterations | 2193 | +| time_elapsed | 7229 | +| total_timesteps | 2245632 | +| train/ | | +| approx_kl | 2.3641608 | +| clip_fraction | 0.425 | +| clip_range | 0.2 | +| entropy_loss | -0.325 | +| explained_variance | -1.07 | +| learning_rate | 0.0001 | +| loss | -0.0788 | +| n_updates | 82450 | +| policy_gradient_loss | -0.0582 | +| value_loss | 0.000776 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.55e+03 | +| ep_rew_mean | -0.101 | +| time/ | | +| fps | 310 | +| iterations | 2194 | +| time_elapsed | 7233 | +| total_timesteps | 2246656 | +| train/ | | +| approx_kl | 1.7225479 | +| clip_fraction | 0.47 | +| clip_range | 0.2 | +| entropy_loss | -0.394 | +| explained_variance | -2.5 | +| learning_rate | 0.0001 | +| loss | -0.0863 | +| n_updates | 82460 | +| policy_gradient_loss | -0.0634 | +| value_loss | 0.000369 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.55e+03 | +| ep_rew_mean | -0.103 | +| time/ | | +| fps | 310 | +| iterations | 2195 | +| time_elapsed | 7236 | +| total_timesteps | 2247680 | +| train/ | | +| approx_kl | 2.75524 | +| clip_fraction | 0.442 | +| clip_range | 0.2 | +| entropy_loss | -0.371 | +| explained_variance | -6.18 | +| learning_rate | 0.0001 | +| loss | -0.0595 | +| n_updates | 82470 | +| policy_gradient_loss | -0.0587 | +| value_loss | 0.000444 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.55e+03 | +| ep_rew_mean | -0.105 | +| time/ | | +| fps | 310 | +| iterations | 2196 | +| time_elapsed | 7239 | +| total_timesteps | 2248704 | +| train/ | | +| approx_kl | 2.4003084 | +| clip_fraction | 0.425 | +| clip_range | 0.2 | +| entropy_loss | -0.33 | +| explained_variance | -1.3 | +| learning_rate | 0.0001 | +| loss | -0.0633 | +| n_updates | 82480 | +| policy_gradient_loss | -0.0494 | +| value_loss | 0.000765 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.54e+03 | +| ep_rew_mean | -0.109 | +| time/ | | +| fps | 310 | +| iterations | 2197 | +| time_elapsed | 7242 | +| total_timesteps | 2249728 | +| train/ | | +| approx_kl | 1.6892797 | +| clip_fraction | 0.437 | +| clip_range | 0.2 | +| entropy_loss | -0.37 | +| explained_variance | -5.46 | +| learning_rate | 0.0001 | +| loss | -0.0696 | +| n_updates | 82490 | +| policy_gradient_loss | -0.0605 | +| value_loss | 0.000944 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.54e+03 | +| ep_rew_mean | -0.109 | +| time/ | | +| fps | 310 | +| iterations | 2198 | +| time_elapsed | 7246 | +| total_timesteps | 2250752 | +| train/ | | +| approx_kl | 1.8717937 | +| clip_fraction | 0.401 | +| clip_range | 0.2 | +| entropy_loss | -0.312 | +| explained_variance | -4.16 | +| learning_rate | 0.0001 | +| loss | -0.0675 | +| n_updates | 82500 | +| policy_gradient_loss | -0.0524 | +| value_loss | 0.000654 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.55e+03 | +| ep_rew_mean | -0.105 | +| time/ | | +| fps | 310 | +| iterations | 2199 | +| time_elapsed | 7249 | +| total_timesteps | 2251776 | +| train/ | | +| approx_kl | 1.9623868 | +| clip_fraction | 0.437 | +| clip_range | 0.2 | +| entropy_loss | -0.391 | +| explained_variance | -2.53 | +| learning_rate | 0.0001 | +| loss | -0.0892 | +| n_updates | 82510 | +| policy_gradient_loss | -0.0583 | +| value_loss | 0.000462 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.54e+03 | +| ep_rew_mean | -0.105 | +| time/ | | +| fps | 310 | +| iterations | 2200 | +| time_elapsed | 7252 | +| total_timesteps | 2252800 | +| train/ | | +| approx_kl | 2.5638123 | +| clip_fraction | 0.447 | +| clip_range | 0.2 | +| entropy_loss | -0.356 | +| explained_variance | -3.88 | +| learning_rate | 0.0001 | +| loss | -0.0654 | +| n_updates | 82520 | +| policy_gradient_loss | -0.0587 | +| value_loss | 0.000426 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.54e+03 | +| ep_rew_mean | -0.102 | +| time/ | | +| fps | 310 | +| iterations | 2201 | +| time_elapsed | 7256 | +| total_timesteps | 2253824 | +| train/ | | +| approx_kl | 1.6037419 | +| clip_fraction | 0.416 | +| clip_range | 0.2 | +| entropy_loss | -0.332 | +| explained_variance | -0.696 | +| learning_rate | 0.0001 | +| loss | -0.0733 | +| n_updates | 82530 | +| policy_gradient_loss | -0.0544 | +| value_loss | 0.000443 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.54e+03 | +| ep_rew_mean | -0.102 | +| time/ | | +| fps | 310 | +| iterations | 2202 | +| time_elapsed | 7259 | +| total_timesteps | 2254848 | +| train/ | | +| approx_kl | 1.7954466 | +| clip_fraction | 0.4 | +| clip_range | 0.2 | +| entropy_loss | -0.303 | +| explained_variance | -2.71 | +| learning_rate | 0.0001 | +| loss | -0.0793 | +| n_updates | 82540 | +| policy_gradient_loss | -0.0579 | +| value_loss | 0.000516 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.54e+03 | +| ep_rew_mean | -0.102 | +| time/ | | +| fps | 310 | +| iterations | 2203 | +| time_elapsed | 7263 | +| total_timesteps | 2255872 | +| train/ | | +| approx_kl | 1.5855597 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.419 | +| explained_variance | -5.97 | +| learning_rate | 0.0001 | +| loss | -0.0783 | +| n_updates | 82550 | +| policy_gradient_loss | -0.0607 | +| value_loss | 0.000428 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.56e+03 | +| ep_rew_mean | -0.102 | +| time/ | | +| fps | 310 | +| iterations | 2204 | +| time_elapsed | 7266 | +| total_timesteps | 2256896 | +| train/ | | +| approx_kl | 1.6856806 | +| clip_fraction | 0.401 | +| clip_range | 0.2 | +| entropy_loss | -0.312 | +| explained_variance | -2.08 | +| learning_rate | 0.0001 | +| loss | -0.0852 | +| n_updates | 82560 | +| policy_gradient_loss | -0.0529 | +| value_loss | 0.000452 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.56e+03 | +| ep_rew_mean | -0.104 | +| time/ | | +| fps | 310 | +| iterations | 2205 | +| time_elapsed | 7269 | +| total_timesteps | 2257920 | +| train/ | | +| approx_kl | 1.7994155 | +| clip_fraction | 0.411 | +| clip_range | 0.2 | +| entropy_loss | -0.292 | +| explained_variance | -1.34 | +| learning_rate | 0.0001 | +| loss | -0.0738 | +| n_updates | 82570 | +| policy_gradient_loss | -0.0569 | +| value_loss | 0.000725 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.56e+03 | +| ep_rew_mean | -0.104 | +| time/ | | +| fps | 310 | +| iterations | 2206 | +| time_elapsed | 7273 | +| total_timesteps | 2258944 | +| train/ | | +| approx_kl | 1.7180336 | +| clip_fraction | 0.435 | +| clip_range | 0.2 | +| entropy_loss | -0.337 | +| explained_variance | -2.68 | +| learning_rate | 0.0001 | +| loss | -0.0748 | +| n_updates | 82580 | +| policy_gradient_loss | -0.0601 | +| value_loss | 0.00071 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.55e+03 | +| ep_rew_mean | -0.108 | +| time/ | | +| fps | 310 | +| iterations | 2207 | +| time_elapsed | 7276 | +| total_timesteps | 2259968 | +| train/ | | +| approx_kl | 2.1261475 | +| clip_fraction | 0.417 | +| clip_range | 0.2 | +| entropy_loss | -0.319 | +| explained_variance | -6.58 | +| learning_rate | 0.0001 | +| loss | -0.0757 | +| n_updates | 82590 | +| policy_gradient_loss | -0.0573 | +| value_loss | 0.000513 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.55e+03 | +| ep_rew_mean | -0.108 | +| time/ | | +| fps | 310 | +| iterations | 2208 | +| time_elapsed | 7279 | +| total_timesteps | 2260992 | +| train/ | | +| approx_kl | 1.6660466 | +| clip_fraction | 0.415 | +| clip_range | 0.2 | +| entropy_loss | -0.335 | +| explained_variance | -0.685 | +| learning_rate | 0.0001 | +| loss | -0.0548 | +| n_updates | 82600 | +| policy_gradient_loss | -0.0613 | +| value_loss | 0.000689 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.55e+03 | +| ep_rew_mean | -0.105 | +| time/ | | +| fps | 310 | +| iterations | 2209 | +| time_elapsed | 7282 | +| total_timesteps | 2262016 | +| train/ | | +| approx_kl | 1.8192487 | +| clip_fraction | 0.466 | +| clip_range | 0.2 | +| entropy_loss | -0.366 | +| explained_variance | -3.23 | +| learning_rate | 0.0001 | +| loss | -0.0878 | +| n_updates | 82610 | +| policy_gradient_loss | -0.0629 | +| value_loss | 0.000677 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.55e+03 | +| ep_rew_mean | -0.105 | +| time/ | | +| fps | 310 | +| iterations | 2210 | +| time_elapsed | 7285 | +| total_timesteps | 2263040 | +| train/ | | +| approx_kl | 1.6980537 | +| clip_fraction | 0.453 | +| clip_range | 0.2 | +| entropy_loss | -0.394 | +| explained_variance | -1.04 | +| learning_rate | 0.0001 | +| loss | -0.12 | +| n_updates | 82620 | +| policy_gradient_loss | -0.0598 | +| value_loss | 0.000509 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.56e+03 | +| ep_rew_mean | -0.0999 | +| time/ | | +| fps | 310 | +| iterations | 2211 | +| time_elapsed | 7288 | +| total_timesteps | 2264064 | +| train/ | | +| approx_kl | 1.8195843 | +| clip_fraction | 0.44 | +| clip_range | 0.2 | +| entropy_loss | -0.343 | +| explained_variance | -1.94 | +| learning_rate | 0.0001 | +| loss | -0.0708 | +| n_updates | 82630 | +| policy_gradient_loss | -0.0566 | +| value_loss | 0.000547 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.56e+03 | +| ep_rew_mean | -0.0996 | +| time/ | | +| fps | 310 | +| iterations | 2212 | +| time_elapsed | 7292 | +| total_timesteps | 2265088 | +| train/ | | +| approx_kl | 1.860543 | +| clip_fraction | 0.422 | +| clip_range | 0.2 | +| entropy_loss | -0.341 | +| explained_variance | -2.8 | +| learning_rate | 0.0001 | +| loss | -0.0853 | +| n_updates | 82640 | +| policy_gradient_loss | -0.059 | +| value_loss | 0.000339 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.56e+03 | +| ep_rew_mean | -0.0996 | +| time/ | | +| fps | 310 | +| iterations | 2213 | +| time_elapsed | 7295 | +| total_timesteps | 2266112 | +| train/ | | +| approx_kl | 2.1247773 | +| clip_fraction | 0.403 | +| clip_range | 0.2 | +| entropy_loss | -0.287 | +| explained_variance | -2.13 | +| learning_rate | 0.0001 | +| loss | -0.0783 | +| n_updates | 82650 | +| policy_gradient_loss | -0.0596 | +| value_loss | 0.000465 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.56e+03 | +| ep_rew_mean | -0.0982 | +| time/ | | +| fps | 310 | +| iterations | 2214 | +| time_elapsed | 7298 | +| total_timesteps | 2267136 | +| train/ | | +| approx_kl | 1.9494227 | +| clip_fraction | 0.434 | +| clip_range | 0.2 | +| entropy_loss | -0.34 | +| explained_variance | -3.53 | +| learning_rate | 0.0001 | +| loss | -0.0895 | +| n_updates | 82660 | +| policy_gradient_loss | -0.0617 | +| value_loss | 0.000733 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.56e+03 | +| ep_rew_mean | -0.0975 | +| time/ | | +| fps | 310 | +| iterations | 2215 | +| time_elapsed | 7302 | +| total_timesteps | 2268160 | +| train/ | | +| approx_kl | 1.8416235 | +| clip_fraction | 0.419 | +| clip_range | 0.2 | +| entropy_loss | -0.321 | +| explained_variance | -1.48 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 82670 | +| policy_gradient_loss | -0.0595 | +| value_loss | 0.000767 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.56e+03 | +| ep_rew_mean | -0.0975 | +| time/ | | +| fps | 310 | +| iterations | 2216 | +| time_elapsed | 7305 | +| total_timesteps | 2269184 | +| train/ | | +| approx_kl | 1.59799 | +| clip_fraction | 0.433 | +| clip_range | 0.2 | +| entropy_loss | -0.335 | +| explained_variance | -1.49 | +| learning_rate | 0.0001 | +| loss | -0.0611 | +| n_updates | 82680 | +| policy_gradient_loss | -0.0557 | +| value_loss | 0.000692 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.56e+03 | +| ep_rew_mean | -0.0944 | +| time/ | | +| fps | 310 | +| iterations | 2217 | +| time_elapsed | 7308 | +| total_timesteps | 2270208 | +| train/ | | +| approx_kl | 1.7638018 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.417 | +| explained_variance | -0.554 | +| learning_rate | 0.0001 | +| loss | -0.0821 | +| n_updates | 82690 | +| policy_gradient_loss | -0.0495 | +| value_loss | 0.000737 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.56e+03 | +| ep_rew_mean | -0.0963 | +| time/ | | +| fps | 310 | +| iterations | 2218 | +| time_elapsed | 7312 | +| total_timesteps | 2271232 | +| train/ | | +| approx_kl | 4.599678 | +| clip_fraction | 0.454 | +| clip_range | 0.2 | +| entropy_loss | -0.387 | +| explained_variance | -3.44 | +| learning_rate | 0.0001 | +| loss | -0.0909 | +| n_updates | 82700 | +| policy_gradient_loss | -0.0548 | +| value_loss | 0.000532 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.56e+03 | +| ep_rew_mean | -0.0963 | +| time/ | | +| fps | 310 | +| iterations | 2219 | +| time_elapsed | 7315 | +| total_timesteps | 2272256 | +| train/ | | +| approx_kl | 1.616617 | +| clip_fraction | 0.436 | +| clip_range | 0.2 | +| entropy_loss | -0.364 | +| explained_variance | -1.9 | +| learning_rate | 0.0001 | +| loss | -0.119 | +| n_updates | 82710 | +| policy_gradient_loss | -0.0573 | +| value_loss | 0.000392 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.56e+03 | +| ep_rew_mean | -0.0919 | +| time/ | | +| fps | 310 | +| iterations | 2220 | +| time_elapsed | 7319 | +| total_timesteps | 2273280 | +| train/ | | +| approx_kl | 1.9773144 | +| clip_fraction | 0.442 | +| clip_range | 0.2 | +| entropy_loss | -0.371 | +| explained_variance | -1.78 | +| learning_rate | 0.0001 | +| loss | -0.0897 | +| n_updates | 82720 | +| policy_gradient_loss | -0.0566 | +| value_loss | 0.000452 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.55e+03 | +| ep_rew_mean | -0.0953 | +| time/ | | +| fps | 310 | +| iterations | 2221 | +| time_elapsed | 7322 | +| total_timesteps | 2274304 | +| train/ | | +| approx_kl | 1.8257208 | +| clip_fraction | 0.443 | +| clip_range | 0.2 | +| entropy_loss | -0.336 | +| explained_variance | -5.26 | +| learning_rate | 0.0001 | +| loss | -0.0845 | +| n_updates | 82730 | +| policy_gradient_loss | -0.0619 | +| value_loss | 0.000712 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.55e+03 | +| ep_rew_mean | -0.0953 | +| time/ | | +| fps | 310 | +| iterations | 2222 | +| time_elapsed | 7325 | +| total_timesteps | 2275328 | +| train/ | | +| approx_kl | 2.7745633 | +| clip_fraction | 0.434 | +| clip_range | 0.2 | +| entropy_loss | -0.387 | +| explained_variance | -1.72 | +| learning_rate | 0.0001 | +| loss | -0.0617 | +| n_updates | 82740 | +| policy_gradient_loss | -0.0563 | +| value_loss | 0.000572 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.55e+03 | +| ep_rew_mean | -0.0953 | +| time/ | | +| fps | 310 | +| iterations | 2223 | +| time_elapsed | 7329 | +| total_timesteps | 2276352 | +| train/ | | +| approx_kl | 2.6424556 | +| clip_fraction | 0.482 | +| clip_range | 0.2 | +| entropy_loss | -0.444 | +| explained_variance | -5.28 | +| learning_rate | 0.0001 | +| loss | -0.0676 | +| n_updates | 82750 | +| policy_gradient_loss | -0.0599 | +| value_loss | 0.000361 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.55e+03 | +| ep_rew_mean | -0.0949 | +| time/ | | +| fps | 310 | +| iterations | 2224 | +| time_elapsed | 7332 | +| total_timesteps | 2277376 | +| train/ | | +| approx_kl | 2.360199 | +| clip_fraction | 0.414 | +| clip_range | 0.2 | +| entropy_loss | -0.294 | +| explained_variance | -0.91 | +| learning_rate | 0.0001 | +| loss | -0.0865 | +| n_updates | 82760 | +| policy_gradient_loss | -0.057 | +| value_loss | 0.000667 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.55e+03 | +| ep_rew_mean | -0.0949 | +| time/ | | +| fps | 310 | +| iterations | 2225 | +| time_elapsed | 7335 | +| total_timesteps | 2278400 | +| train/ | | +| approx_kl | 3.7619054 | +| clip_fraction | 0.457 | +| clip_range | 0.2 | +| entropy_loss | -0.332 | +| explained_variance | -2.97 | +| learning_rate | 0.0001 | +| loss | -0.0681 | +| n_updates | 82770 | +| policy_gradient_loss | -0.0551 | +| value_loss | 0.000633 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.54e+03 | +| ep_rew_mean | -0.0962 | +| time/ | | +| fps | 310 | +| iterations | 2226 | +| time_elapsed | 7339 | +| total_timesteps | 2279424 | +| train/ | | +| approx_kl | 1.6430545 | +| clip_fraction | 0.427 | +| clip_range | 0.2 | +| entropy_loss | -0.336 | +| explained_variance | -3.18 | +| learning_rate | 0.0001 | +| loss | -0.0826 | +| n_updates | 82780 | +| policy_gradient_loss | -0.0521 | +| value_loss | 0.000591 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.54e+03 | +| ep_rew_mean | -0.098 | +| time/ | | +| fps | 310 | +| iterations | 2227 | +| time_elapsed | 7342 | +| total_timesteps | 2280448 | +| train/ | | +| approx_kl | 1.8942139 | +| clip_fraction | 0.409 | +| clip_range | 0.2 | +| entropy_loss | -0.313 | +| explained_variance | -0.874 | +| learning_rate | 0.0001 | +| loss | -0.0554 | +| n_updates | 82790 | +| policy_gradient_loss | -0.0553 | +| value_loss | 0.000695 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.53e+03 | +| ep_rew_mean | -0.1 | +| time/ | | +| fps | 310 | +| iterations | 2228 | +| time_elapsed | 7345 | +| total_timesteps | 2281472 | +| train/ | | +| approx_kl | 1.6238029 | +| clip_fraction | 0.408 | +| clip_range | 0.2 | +| entropy_loss | -0.324 | +| explained_variance | -2.55 | +| learning_rate | 0.0001 | +| loss | -0.0622 | +| n_updates | 82800 | +| policy_gradient_loss | -0.0524 | +| value_loss | 0.000702 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.53e+03 | +| ep_rew_mean | -0.102 | +| time/ | | +| fps | 310 | +| iterations | 2229 | +| time_elapsed | 7348 | +| total_timesteps | 2282496 | +| train/ | | +| approx_kl | 1.6584442 | +| clip_fraction | 0.4 | +| clip_range | 0.2 | +| entropy_loss | -0.309 | +| explained_variance | -1.85 | +| learning_rate | 0.0001 | +| loss | -0.0345 | +| n_updates | 82810 | +| policy_gradient_loss | -0.0499 | +| value_loss | 0.000846 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.52e+03 | +| ep_rew_mean | -0.105 | +| time/ | | +| fps | 310 | +| iterations | 2230 | +| time_elapsed | 7352 | +| total_timesteps | 2283520 | +| train/ | | +| approx_kl | 1.8108647 | +| clip_fraction | 0.432 | +| clip_range | 0.2 | +| entropy_loss | -0.36 | +| explained_variance | -2.41 | +| learning_rate | 0.0001 | +| loss | -0.0661 | +| n_updates | 82820 | +| policy_gradient_loss | -0.0541 | +| value_loss | 0.000775 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.52e+03 | +| ep_rew_mean | -0.105 | +| time/ | | +| fps | 310 | +| iterations | 2231 | +| time_elapsed | 7355 | +| total_timesteps | 2284544 | +| train/ | | +| approx_kl | 4.700872 | +| clip_fraction | 0.434 | +| clip_range | 0.2 | +| entropy_loss | -0.337 | +| explained_variance | -2.61 | +| learning_rate | 0.0001 | +| loss | -0.0758 | +| n_updates | 82830 | +| policy_gradient_loss | -0.0602 | +| value_loss | 0.000804 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.52e+03 | +| ep_rew_mean | -0.105 | +| time/ | | +| fps | 310 | +| iterations | 2232 | +| time_elapsed | 7358 | +| total_timesteps | 2285568 | +| train/ | | +| approx_kl | 1.6502385 | +| clip_fraction | 0.465 | +| clip_range | 0.2 | +| entropy_loss | -0.406 | +| explained_variance | -2.16 | +| learning_rate | 0.0001 | +| loss | -0.0551 | +| n_updates | 82840 | +| policy_gradient_loss | -0.0574 | +| value_loss | 0.000438 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.54e+03 | +| ep_rew_mean | -0.1 | +| time/ | | +| fps | 310 | +| iterations | 2233 | +| time_elapsed | 7361 | +| total_timesteps | 2286592 | +| train/ | | +| approx_kl | 1.965929 | +| clip_fraction | 0.411 | +| clip_range | 0.2 | +| entropy_loss | -0.324 | +| explained_variance | -0.92 | +| learning_rate | 0.0001 | +| loss | -0.0823 | +| n_updates | 82850 | +| policy_gradient_loss | -0.0572 | +| value_loss | 0.000433 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.54e+03 | +| ep_rew_mean | -0.1 | +| time/ | | +| fps | 310 | +| iterations | 2234 | +| time_elapsed | 7364 | +| total_timesteps | 2287616 | +| train/ | | +| approx_kl | 3.4393244 | +| clip_fraction | 0.424 | +| clip_range | 0.2 | +| entropy_loss | -0.323 | +| explained_variance | -4.37 | +| learning_rate | 0.0001 | +| loss | -0.0799 | +| n_updates | 82860 | +| policy_gradient_loss | -0.0583 | +| value_loss | 0.000478 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.55e+03 | +| ep_rew_mean | -0.109 | +| time/ | | +| fps | 310 | +| iterations | 2235 | +| time_elapsed | 7368 | +| total_timesteps | 2288640 | +| train/ | | +| approx_kl | 3.923893 | +| clip_fraction | 0.438 | +| clip_range | 0.2 | +| entropy_loss | -0.345 | +| explained_variance | -4.5 | +| learning_rate | 0.0001 | +| loss | -0.0873 | +| n_updates | 82870 | +| policy_gradient_loss | -0.0581 | +| value_loss | 0.0006 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.55e+03 | +| ep_rew_mean | -0.109 | +| time/ | | +| fps | 310 | +| iterations | 2236 | +| time_elapsed | 7371 | +| total_timesteps | 2289664 | +| train/ | | +| approx_kl | 2.8450515 | +| clip_fraction | 0.41 | +| clip_range | 0.2 | +| entropy_loss | -0.319 | +| explained_variance | -1.48 | +| learning_rate | 0.0001 | +| loss | -0.0572 | +| n_updates | 82880 | +| policy_gradient_loss | -0.0486 | +| value_loss | 0.000565 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.56e+03 | +| ep_rew_mean | -0.112 | +| time/ | | +| fps | 310 | +| iterations | 2237 | +| time_elapsed | 7374 | +| total_timesteps | 2290688 | +| train/ | | +| approx_kl | 2.2300382 | +| clip_fraction | 0.486 | +| clip_range | 0.2 | +| entropy_loss | -0.421 | +| explained_variance | -4.58 | +| learning_rate | 0.0001 | +| loss | -0.0853 | +| n_updates | 82890 | +| policy_gradient_loss | -0.065 | +| value_loss | 0.000602 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.55e+03 | +| ep_rew_mean | -0.115 | +| time/ | | +| fps | 310 | +| iterations | 2238 | +| time_elapsed | 7377 | +| total_timesteps | 2291712 | +| train/ | | +| approx_kl | 1.5944206 | +| clip_fraction | 0.444 | +| clip_range | 0.2 | +| entropy_loss | -0.408 | +| explained_variance | -2.08 | +| learning_rate | 0.0001 | +| loss | -0.0583 | +| n_updates | 82900 | +| policy_gradient_loss | -0.0547 | +| value_loss | 0.00054 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.55e+03 | +| ep_rew_mean | -0.115 | +| time/ | | +| fps | 310 | +| iterations | 2239 | +| time_elapsed | 7381 | +| total_timesteps | 2292736 | +| train/ | | +| approx_kl | 1.6603327 | +| clip_fraction | 0.375 | +| clip_range | 0.2 | +| entropy_loss | -0.258 | +| explained_variance | -4.73 | +| learning_rate | 0.0001 | +| loss | -0.0635 | +| n_updates | 82910 | +| policy_gradient_loss | -0.0544 | +| value_loss | 0.000531 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.55e+03 | +| ep_rew_mean | -0.116 | +| time/ | | +| fps | 310 | +| iterations | 2240 | +| time_elapsed | 7384 | +| total_timesteps | 2293760 | +| train/ | | +| approx_kl | 1.7929689 | +| clip_fraction | 0.414 | +| clip_range | 0.2 | +| entropy_loss | -0.283 | +| explained_variance | -10.4 | +| learning_rate | 0.0001 | +| loss | -0.0681 | +| n_updates | 82920 | +| policy_gradient_loss | -0.0519 | +| value_loss | 0.000762 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.55e+03 | +| ep_rew_mean | -0.12 | +| time/ | | +| fps | 310 | +| iterations | 2241 | +| time_elapsed | 7388 | +| total_timesteps | 2294784 | +| train/ | | +| approx_kl | 1.5825169 | +| clip_fraction | 0.412 | +| clip_range | 0.2 | +| entropy_loss | -0.32 | +| explained_variance | -1.73 | +| learning_rate | 0.0001 | +| loss | -0.0546 | +| n_updates | 82930 | +| policy_gradient_loss | -0.0561 | +| value_loss | 0.000607 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.55e+03 | +| ep_rew_mean | -0.121 | +| time/ | | +| fps | 310 | +| iterations | 2242 | +| time_elapsed | 7391 | +| total_timesteps | 2295808 | +| train/ | | +| approx_kl | 1.5543653 | +| clip_fraction | 0.42 | +| clip_range | 0.2 | +| entropy_loss | -0.313 | +| explained_variance | -1.02 | +| learning_rate | 0.0001 | +| loss | -0.0635 | +| n_updates | 82940 | +| policy_gradient_loss | -0.0578 | +| value_loss | 0.000617 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.55e+03 | +| ep_rew_mean | -0.121 | +| time/ | | +| fps | 310 | +| iterations | 2243 | +| time_elapsed | 7394 | +| total_timesteps | 2296832 | +| train/ | | +| approx_kl | 1.7227397 | +| clip_fraction | 0.425 | +| clip_range | 0.2 | +| entropy_loss | -0.34 | +| explained_variance | -2.93 | +| learning_rate | 0.0001 | +| loss | -0.0554 | +| n_updates | 82950 | +| policy_gradient_loss | -0.059 | +| value_loss | 0.000674 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.55e+03 | +| ep_rew_mean | -0.121 | +| time/ | | +| fps | 310 | +| iterations | 2244 | +| time_elapsed | 7397 | +| total_timesteps | 2297856 | +| train/ | | +| approx_kl | 1.7789257 | +| clip_fraction | 0.431 | +| clip_range | 0.2 | +| entropy_loss | -0.327 | +| explained_variance | -3.96 | +| learning_rate | 0.0001 | +| loss | -0.0695 | +| n_updates | 82960 | +| policy_gradient_loss | -0.0582 | +| value_loss | 0.000626 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.56e+03 | +| ep_rew_mean | -0.118 | +| time/ | | +| fps | 310 | +| iterations | 2245 | +| time_elapsed | 7400 | +| total_timesteps | 2298880 | +| train/ | | +| approx_kl | 1.7559106 | +| clip_fraction | 0.485 | +| clip_range | 0.2 | +| entropy_loss | -0.397 | +| explained_variance | -1.85 | +| learning_rate | 0.0001 | +| loss | -0.0914 | +| n_updates | 82970 | +| policy_gradient_loss | -0.0601 | +| value_loss | 0.000578 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.55e+03 | +| ep_rew_mean | -0.117 | +| time/ | | +| fps | 310 | +| iterations | 2246 | +| time_elapsed | 7404 | +| total_timesteps | 2299904 | +| train/ | | +| approx_kl | 2.4511092 | +| clip_fraction | 0.426 | +| clip_range | 0.2 | +| entropy_loss | -0.267 | +| explained_variance | -3.91 | +| learning_rate | 0.0001 | +| loss | -0.0719 | +| n_updates | 82980 | +| policy_gradient_loss | -0.0557 | +| value_loss | 0.000755 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.55e+03 | +| ep_rew_mean | -0.117 | +| time/ | | +| fps | 310 | +| iterations | 2247 | +| time_elapsed | 7407 | +| total_timesteps | 2300928 | +| train/ | | +| approx_kl | 1.9269329 | +| clip_fraction | 0.397 | +| clip_range | 0.2 | +| entropy_loss | -0.289 | +| explained_variance | -2.36 | +| learning_rate | 0.0001 | +| loss | -0.0273 | +| n_updates | 82990 | +| policy_gradient_loss | -0.0488 | +| value_loss | 0.000661 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.54e+03 | +| ep_rew_mean | -0.121 | +| time/ | | +| fps | 310 | +| iterations | 2248 | +| time_elapsed | 7410 | +| total_timesteps | 2301952 | +| train/ | | +| approx_kl | 1.8381836 | +| clip_fraction | 0.415 | +| clip_range | 0.2 | +| entropy_loss | -0.368 | +| explained_variance | -3.72 | +| learning_rate | 0.0001 | +| loss | -0.0634 | +| n_updates | 83000 | +| policy_gradient_loss | -0.0482 | +| value_loss | 0.000559 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.55e+03 | +| ep_rew_mean | -0.122 | +| time/ | | +| fps | 310 | +| iterations | 2249 | +| time_elapsed | 7413 | +| total_timesteps | 2302976 | +| train/ | | +| approx_kl | 3.0270913 | +| clip_fraction | 0.445 | +| clip_range | 0.2 | +| entropy_loss | -0.376 | +| explained_variance | -1.52 | +| learning_rate | 0.0001 | +| loss | -0.0998 | +| n_updates | 83010 | +| policy_gradient_loss | -0.0564 | +| value_loss | 0.000502 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.55e+03 | +| ep_rew_mean | -0.121 | +| time/ | | +| fps | 310 | +| iterations | 2250 | +| time_elapsed | 7416 | +| total_timesteps | 2304000 | +| train/ | | +| approx_kl | 1.9998262 | +| clip_fraction | 0.431 | +| clip_range | 0.2 | +| entropy_loss | -0.325 | +| explained_variance | -1.69 | +| learning_rate | 0.0001 | +| loss | -0.0726 | +| n_updates | 83020 | +| policy_gradient_loss | -0.0621 | +| value_loss | 0.000766 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.55e+03 | +| ep_rew_mean | -0.121 | +| time/ | | +| fps | 310 | +| iterations | 2251 | +| time_elapsed | 7419 | +| total_timesteps | 2305024 | +| train/ | | +| approx_kl | 1.8723785 | +| clip_fraction | 0.401 | +| clip_range | 0.2 | +| entropy_loss | -0.288 | +| explained_variance | -2.69 | +| learning_rate | 0.0001 | +| loss | -0.079 | +| n_updates | 83030 | +| policy_gradient_loss | -0.0532 | +| value_loss | 0.000679 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.56e+03 | +| ep_rew_mean | -0.118 | +| time/ | | +| fps | 310 | +| iterations | 2252 | +| time_elapsed | 7423 | +| total_timesteps | 2306048 | +| train/ | | +| approx_kl | 2.2176104 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.414 | +| explained_variance | -2.82 | +| learning_rate | 0.0001 | +| loss | -0.0828 | +| n_updates | 83040 | +| policy_gradient_loss | -0.0642 | +| value_loss | 0.000675 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.56e+03 | +| ep_rew_mean | -0.118 | +| time/ | | +| fps | 310 | +| iterations | 2253 | +| time_elapsed | 7426 | +| total_timesteps | 2307072 | +| train/ | | +| approx_kl | 1.9531448 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.42 | +| explained_variance | -5.78 | +| learning_rate | 0.0001 | +| loss | -0.0785 | +| n_updates | 83050 | +| policy_gradient_loss | -0.0589 | +| value_loss | 0.000503 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.56e+03 | +| ep_rew_mean | -0.116 | +| time/ | | +| fps | 310 | +| iterations | 2254 | +| time_elapsed | 7430 | +| total_timesteps | 2308096 | +| train/ | | +| approx_kl | 1.9199204 | +| clip_fraction | 0.436 | +| clip_range | 0.2 | +| entropy_loss | -0.32 | +| explained_variance | -1.19 | +| learning_rate | 0.0001 | +| loss | -0.0808 | +| n_updates | 83060 | +| policy_gradient_loss | -0.0538 | +| value_loss | 0.00057 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.56e+03 | +| ep_rew_mean | -0.11 | +| time/ | | +| fps | 310 | +| iterations | 2255 | +| time_elapsed | 7433 | +| total_timesteps | 2309120 | +| train/ | | +| approx_kl | 2.5175543 | +| clip_fraction | 0.469 | +| clip_range | 0.2 | +| entropy_loss | -0.373 | +| explained_variance | -1.61 | +| learning_rate | 0.0001 | +| loss | -0.0732 | +| n_updates | 83070 | +| policy_gradient_loss | -0.0599 | +| value_loss | 0.000835 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.56e+03 | +| ep_rew_mean | -0.11 | +| time/ | | +| fps | 310 | +| iterations | 2256 | +| time_elapsed | 7437 | +| total_timesteps | 2310144 | +| train/ | | +| approx_kl | 5.5645647 | +| clip_fraction | 0.442 | +| clip_range | 0.2 | +| entropy_loss | -0.33 | +| explained_variance | -1.51 | +| learning_rate | 0.0001 | +| loss | -0.116 | +| n_updates | 83080 | +| policy_gradient_loss | -0.0618 | +| value_loss | 0.000823 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.56e+03 | +| ep_rew_mean | -0.11 | +| time/ | | +| fps | 310 | +| iterations | 2257 | +| time_elapsed | 7441 | +| total_timesteps | 2311168 | +| train/ | | +| approx_kl | 2.2677782 | +| clip_fraction | 0.446 | +| clip_range | 0.2 | +| entropy_loss | -0.348 | +| explained_variance | -7.94 | +| learning_rate | 0.0001 | +| loss | -0.0705 | +| n_updates | 83090 | +| policy_gradient_loss | -0.06 | +| value_loss | 0.00047 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.56e+03 | +| ep_rew_mean | -0.11 | +| time/ | | +| fps | 310 | +| iterations | 2258 | +| time_elapsed | 7444 | +| total_timesteps | 2312192 | +| train/ | | +| approx_kl | 2.0080843 | +| clip_fraction | 0.46 | +| clip_range | 0.2 | +| entropy_loss | -0.384 | +| explained_variance | -2.81 | +| learning_rate | 0.0001 | +| loss | -0.094 | +| n_updates | 83100 | +| policy_gradient_loss | -0.0543 | +| value_loss | 0.000599 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.56e+03 | +| ep_rew_mean | -0.112 | +| time/ | | +| fps | 310 | +| iterations | 2259 | +| time_elapsed | 7448 | +| total_timesteps | 2313216 | +| train/ | | +| approx_kl | 1.6482241 | +| clip_fraction | 0.472 | +| clip_range | 0.2 | +| entropy_loss | -0.357 | +| explained_variance | -6.92 | +| learning_rate | 0.0001 | +| loss | -0.0773 | +| n_updates | 83110 | +| policy_gradient_loss | -0.06 | +| value_loss | 0.00055 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.56e+03 | +| ep_rew_mean | -0.112 | +| time/ | | +| fps | 310 | +| iterations | 2260 | +| time_elapsed | 7451 | +| total_timesteps | 2314240 | +| train/ | | +| approx_kl | 1.5809183 | +| clip_fraction | 0.424 | +| clip_range | 0.2 | +| entropy_loss | -0.413 | +| explained_variance | -1.32 | +| learning_rate | 0.0001 | +| loss | -0.0677 | +| n_updates | 83120 | +| policy_gradient_loss | -0.047 | +| value_loss | 0.000729 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.57e+03 | +| ep_rew_mean | -0.109 | +| time/ | | +| fps | 310 | +| iterations | 2261 | +| time_elapsed | 7454 | +| total_timesteps | 2315264 | +| train/ | | +| approx_kl | 2.0604649 | +| clip_fraction | 0.463 | +| clip_range | 0.2 | +| entropy_loss | -0.353 | +| explained_variance | -6.23 | +| learning_rate | 0.0001 | +| loss | -0.0732 | +| n_updates | 83130 | +| policy_gradient_loss | -0.0646 | +| value_loss | 0.00055 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.58e+03 | +| ep_rew_mean | -0.109 | +| time/ | | +| fps | 310 | +| iterations | 2262 | +| time_elapsed | 7457 | +| total_timesteps | 2316288 | +| train/ | | +| approx_kl | 2.0059865 | +| clip_fraction | 0.42 | +| clip_range | 0.2 | +| entropy_loss | -0.296 | +| explained_variance | -6.78 | +| learning_rate | 0.0001 | +| loss | -0.0868 | +| n_updates | 83140 | +| policy_gradient_loss | -0.056 | +| value_loss | 0.000465 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.58e+03 | +| ep_rew_mean | -0.109 | +| time/ | | +| fps | 310 | +| iterations | 2263 | +| time_elapsed | 7460 | +| total_timesteps | 2317312 | +| train/ | | +| approx_kl | 2.2152634 | +| clip_fraction | 0.43 | +| clip_range | 0.2 | +| entropy_loss | -0.405 | +| explained_variance | -0.979 | +| learning_rate | 0.0001 | +| loss | -0.0723 | +| n_updates | 83150 | +| policy_gradient_loss | -0.051 | +| value_loss | 0.000705 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.58e+03 | +| ep_rew_mean | -0.107 | +| time/ | | +| fps | 310 | +| iterations | 2264 | +| time_elapsed | 7464 | +| total_timesteps | 2318336 | +| train/ | | +| approx_kl | 1.6615973 | +| clip_fraction | 0.434 | +| clip_range | 0.2 | +| entropy_loss | -0.341 | +| explained_variance | -2.64 | +| learning_rate | 0.0001 | +| loss | -0.0955 | +| n_updates | 83160 | +| policy_gradient_loss | -0.0565 | +| value_loss | 0.000645 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.58e+03 | +| ep_rew_mean | -0.103 | +| time/ | | +| fps | 310 | +| iterations | 2265 | +| time_elapsed | 7467 | +| total_timesteps | 2319360 | +| train/ | | +| approx_kl | 1.8629743 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.427 | +| explained_variance | -2.94 | +| learning_rate | 0.0001 | +| loss | -0.0817 | +| n_updates | 83170 | +| policy_gradient_loss | -0.062 | +| value_loss | 0.000405 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.58e+03 | +| ep_rew_mean | -0.103 | +| time/ | | +| fps | 310 | +| iterations | 2266 | +| time_elapsed | 7470 | +| total_timesteps | 2320384 | +| train/ | | +| approx_kl | 1.8050194 | +| clip_fraction | 0.486 | +| clip_range | 0.2 | +| entropy_loss | -0.361 | +| explained_variance | -1.8 | +| learning_rate | 0.0001 | +| loss | -0.0848 | +| n_updates | 83180 | +| policy_gradient_loss | -0.0617 | +| value_loss | 0.000848 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | -0.101 | +| time/ | | +| fps | 310 | +| iterations | 2267 | +| time_elapsed | 7473 | +| total_timesteps | 2321408 | +| train/ | | +| approx_kl | 1.9802654 | +| clip_fraction | 0.445 | +| clip_range | 0.2 | +| entropy_loss | -0.356 | +| explained_variance | -3.38 | +| learning_rate | 0.0001 | +| loss | -0.0844 | +| n_updates | 83190 | +| policy_gradient_loss | -0.0571 | +| value_loss | 0.000614 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | -0.101 | +| time/ | | +| fps | 310 | +| iterations | 2268 | +| time_elapsed | 7476 | +| total_timesteps | 2322432 | +| train/ | | +| approx_kl | 1.765142 | +| clip_fraction | 0.436 | +| clip_range | 0.2 | +| entropy_loss | -0.329 | +| explained_variance | -2.29 | +| learning_rate | 0.0001 | +| loss | -0.0885 | +| n_updates | 83200 | +| policy_gradient_loss | -0.0558 | +| value_loss | 0.000502 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | -0.103 | +| time/ | | +| fps | 310 | +| iterations | 2269 | +| time_elapsed | 7479 | +| total_timesteps | 2323456 | +| train/ | | +| approx_kl | 4.9732027 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.447 | +| explained_variance | -5.28 | +| learning_rate | 0.0001 | +| loss | -0.0995 | +| n_updates | 83210 | +| policy_gradient_loss | -0.0627 | +| value_loss | 0.000505 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | -0.103 | +| time/ | | +| fps | 310 | +| iterations | 2270 | +| time_elapsed | 7483 | +| total_timesteps | 2324480 | +| train/ | | +| approx_kl | 1.7748609 | +| clip_fraction | 0.437 | +| clip_range | 0.2 | +| entropy_loss | -0.356 | +| explained_variance | -1.15 | +| learning_rate | 0.0001 | +| loss | -0.0767 | +| n_updates | 83220 | +| policy_gradient_loss | -0.0553 | +| value_loss | 0.000791 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | -0.1 | +| time/ | | +| fps | 310 | +| iterations | 2271 | +| time_elapsed | 7486 | +| total_timesteps | 2325504 | +| train/ | | +| approx_kl | 2.442307 | +| clip_fraction | 0.459 | +| clip_range | 0.2 | +| entropy_loss | -0.423 | +| explained_variance | -2.97 | +| learning_rate | 0.0001 | +| loss | -0.0857 | +| n_updates | 83230 | +| policy_gradient_loss | -0.0642 | +| value_loss | 0.00111 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | -0.1 | +| time/ | | +| fps | 310 | +| iterations | 2272 | +| time_elapsed | 7490 | +| total_timesteps | 2326528 | +| train/ | | +| approx_kl | 1.7502457 | +| clip_fraction | 0.458 | +| clip_range | 0.2 | +| entropy_loss | -0.402 | +| explained_variance | -2.33 | +| learning_rate | 0.0001 | +| loss | -0.0855 | +| n_updates | 83240 | +| policy_gradient_loss | -0.0466 | +| value_loss | 0.000416 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | -0.0998 | +| time/ | | +| fps | 310 | +| iterations | 2273 | +| time_elapsed | 7493 | +| total_timesteps | 2327552 | +| train/ | | +| approx_kl | 1.9779885 | +| clip_fraction | 0.508 | +| clip_range | 0.2 | +| entropy_loss | -0.494 | +| explained_variance | -0.653 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 83250 | +| policy_gradient_loss | -0.0622 | +| value_loss | 0.000353 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | -0.0998 | +| time/ | | +| fps | 310 | +| iterations | 2274 | +| time_elapsed | 7497 | +| total_timesteps | 2328576 | +| train/ | | +| approx_kl | 1.853518 | +| clip_fraction | 0.441 | +| clip_range | 0.2 | +| entropy_loss | -0.316 | +| explained_variance | -2.53 | +| learning_rate | 0.0001 | +| loss | -0.0949 | +| n_updates | 83260 | +| policy_gradient_loss | -0.0607 | +| value_loss | 0.000521 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.61e+03 | +| ep_rew_mean | -0.0945 | +| time/ | | +| fps | 310 | +| iterations | 2275 | +| time_elapsed | 7500 | +| total_timesteps | 2329600 | +| train/ | | +| approx_kl | 1.9793293 | +| clip_fraction | 0.456 | +| clip_range | 0.2 | +| entropy_loss | -0.361 | +| explained_variance | -2.21 | +| learning_rate | 0.0001 | +| loss | -0.0751 | +| n_updates | 83270 | +| policy_gradient_loss | -0.0643 | +| value_loss | 0.000537 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.61e+03 | +| ep_rew_mean | -0.0914 | +| time/ | | +| fps | 310 | +| iterations | 2276 | +| time_elapsed | 7503 | +| total_timesteps | 2330624 | +| train/ | | +| approx_kl | 1.695222 | +| clip_fraction | 0.421 | +| clip_range | 0.2 | +| entropy_loss | -0.31 | +| explained_variance | -3.89 | +| learning_rate | 0.0001 | +| loss | -0.0784 | +| n_updates | 83280 | +| policy_gradient_loss | -0.0597 | +| value_loss | 0.000548 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | -0.0959 | +| time/ | | +| fps | 310 | +| iterations | 2277 | +| time_elapsed | 7507 | +| total_timesteps | 2331648 | +| train/ | | +| approx_kl | 2.0444999 | +| clip_fraction | 0.436 | +| clip_range | 0.2 | +| entropy_loss | -0.322 | +| explained_variance | -1.93 | +| learning_rate | 0.0001 | +| loss | -0.0786 | +| n_updates | 83290 | +| policy_gradient_loss | -0.0613 | +| value_loss | 0.000604 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | -0.0959 | +| time/ | | +| fps | 310 | +| iterations | 2278 | +| time_elapsed | 7510 | +| total_timesteps | 2332672 | +| train/ | | +| approx_kl | 2.0529964 | +| clip_fraction | 0.414 | +| clip_range | 0.2 | +| entropy_loss | -0.269 | +| explained_variance | -1.11 | +| learning_rate | 0.0001 | +| loss | -0.0771 | +| n_updates | 83300 | +| policy_gradient_loss | -0.0524 | +| value_loss | 0.0008 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | -0.0991 | +| time/ | | +| fps | 310 | +| iterations | 2279 | +| time_elapsed | 7513 | +| total_timesteps | 2333696 | +| train/ | | +| approx_kl | 2.6157126 | +| clip_fraction | 0.448 | +| clip_range | 0.2 | +| entropy_loss | -0.345 | +| explained_variance | -2.21 | +| learning_rate | 0.0001 | +| loss | -0.0729 | +| n_updates | 83310 | +| policy_gradient_loss | -0.0657 | +| value_loss | 0.000485 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | -0.0991 | +| time/ | | +| fps | 310 | +| iterations | 2280 | +| time_elapsed | 7516 | +| total_timesteps | 2334720 | +| train/ | | +| approx_kl | 2.529486 | +| clip_fraction | 0.429 | +| clip_range | 0.2 | +| entropy_loss | -0.335 | +| explained_variance | -3.9 | +| learning_rate | 0.0001 | +| loss | -0.0772 | +| n_updates | 83320 | +| policy_gradient_loss | -0.0627 | +| value_loss | 0.000505 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | -0.101 | +| time/ | | +| fps | 310 | +| iterations | 2281 | +| time_elapsed | 7519 | +| total_timesteps | 2335744 | +| train/ | | +| approx_kl | 1.883637 | +| clip_fraction | 0.436 | +| clip_range | 0.2 | +| entropy_loss | -0.389 | +| explained_variance | -2.93 | +| learning_rate | 0.0001 | +| loss | -0.0695 | +| n_updates | 83330 | +| policy_gradient_loss | -0.0597 | +| value_loss | 0.000457 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | -0.101 | +| time/ | | +| fps | 310 | +| iterations | 2282 | +| time_elapsed | 7523 | +| total_timesteps | 2336768 | +| train/ | | +| approx_kl | 1.625613 | +| clip_fraction | 0.375 | +| clip_range | 0.2 | +| entropy_loss | -0.308 | +| explained_variance | -0.912 | +| learning_rate | 0.0001 | +| loss | -0.0522 | +| n_updates | 83340 | +| policy_gradient_loss | -0.0464 | +| value_loss | 0.000581 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | -0.101 | +| time/ | | +| fps | 310 | +| iterations | 2283 | +| time_elapsed | 7526 | +| total_timesteps | 2337792 | +| train/ | | +| approx_kl | 1.8823504 | +| clip_fraction | 0.41 | +| clip_range | 0.2 | +| entropy_loss | -0.335 | +| explained_variance | -3.61 | +| learning_rate | 0.0001 | +| loss | -0.0543 | +| n_updates | 83350 | +| policy_gradient_loss | -0.051 | +| value_loss | 0.000677 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | -0.098 | +| time/ | | +| fps | 310 | +| iterations | 2284 | +| time_elapsed | 7529 | +| total_timesteps | 2338816 | +| train/ | | +| approx_kl | 2.2290823 | +| clip_fraction | 0.426 | +| clip_range | 0.2 | +| entropy_loss | -0.31 | +| explained_variance | -1.46 | +| learning_rate | 0.0001 | +| loss | -0.0653 | +| n_updates | 83360 | +| policy_gradient_loss | -0.0632 | +| value_loss | 0.000702 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | -0.098 | +| time/ | | +| fps | 310 | +| iterations | 2285 | +| time_elapsed | 7532 | +| total_timesteps | 2339840 | +| train/ | | +| approx_kl | 2.4724143 | +| clip_fraction | 0.431 | +| clip_range | 0.2 | +| entropy_loss | -0.319 | +| explained_variance | -2.38 | +| learning_rate | 0.0001 | +| loss | -0.0675 | +| n_updates | 83370 | +| policy_gradient_loss | -0.0574 | +| value_loss | 0.000647 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.61e+03 | +| ep_rew_mean | -0.0935 | +| time/ | | +| fps | 310 | +| iterations | 2286 | +| time_elapsed | 7536 | +| total_timesteps | 2340864 | +| train/ | | +| approx_kl | 1.9305401 | +| clip_fraction | 0.462 | +| clip_range | 0.2 | +| entropy_loss | -0.418 | +| explained_variance | -5.84 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 83380 | +| policy_gradient_loss | -0.0664 | +| value_loss | 0.000505 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | -0.0957 | +| time/ | | +| fps | 310 | +| iterations | 2287 | +| time_elapsed | 7539 | +| total_timesteps | 2341888 | +| train/ | | +| approx_kl | 1.6572933 | +| clip_fraction | 0.41 | +| clip_range | 0.2 | +| entropy_loss | -0.337 | +| explained_variance | -7.47 | +| learning_rate | 0.0001 | +| loss | -0.0751 | +| n_updates | 83390 | +| policy_gradient_loss | -0.0533 | +| value_loss | 0.000352 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | -0.0959 | +| time/ | | +| fps | 310 | +| iterations | 2288 | +| time_elapsed | 7542 | +| total_timesteps | 2342912 | +| train/ | | +| approx_kl | 1.8355547 | +| clip_fraction | 0.406 | +| clip_range | 0.2 | +| entropy_loss | -0.285 | +| explained_variance | -1.37 | +| learning_rate | 0.0001 | +| loss | -0.0595 | +| n_updates | 83400 | +| policy_gradient_loss | -0.054 | +| value_loss | 0.00045 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | -0.101 | +| time/ | | +| fps | 310 | +| iterations | 2289 | +| time_elapsed | 7546 | +| total_timesteps | 2343936 | +| train/ | | +| approx_kl | 1.6115346 | +| clip_fraction | 0.414 | +| clip_range | 0.2 | +| entropy_loss | -0.324 | +| explained_variance | -0.834 | +| learning_rate | 0.0001 | +| loss | -0.0622 | +| n_updates | 83410 | +| policy_gradient_loss | -0.0568 | +| value_loss | 0.000766 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | -0.101 | +| time/ | | +| fps | 310 | +| iterations | 2290 | +| time_elapsed | 7549 | +| total_timesteps | 2344960 | +| train/ | | +| approx_kl | 2.3631735 | +| clip_fraction | 0.443 | +| clip_range | 0.2 | +| entropy_loss | -0.314 | +| explained_variance | -1.98 | +| learning_rate | 0.0001 | +| loss | -0.059 | +| n_updates | 83420 | +| policy_gradient_loss | -0.0493 | +| value_loss | 0.000885 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | -0.106 | +| time/ | | +| fps | 310 | +| iterations | 2291 | +| time_elapsed | 7553 | +| total_timesteps | 2345984 | +| train/ | | +| approx_kl | 1.6893076 | +| clip_fraction | 0.441 | +| clip_range | 0.2 | +| entropy_loss | -0.356 | +| explained_variance | -3.9 | +| learning_rate | 0.0001 | +| loss | -0.0763 | +| n_updates | 83430 | +| policy_gradient_loss | -0.0643 | +| value_loss | 0.00083 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | -0.106 | +| time/ | | +| fps | 310 | +| iterations | 2292 | +| time_elapsed | 7556 | +| total_timesteps | 2347008 | +| train/ | | +| approx_kl | 2.3759458 | +| clip_fraction | 0.411 | +| clip_range | 0.2 | +| entropy_loss | -0.345 | +| explained_variance | -2.16 | +| learning_rate | 0.0001 | +| loss | -0.0852 | +| n_updates | 83440 | +| policy_gradient_loss | -0.0568 | +| value_loss | 0.000537 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | -0.101 | +| time/ | | +| fps | 310 | +| iterations | 2293 | +| time_elapsed | 7559 | +| total_timesteps | 2348032 | +| train/ | | +| approx_kl | 2.0490208 | +| clip_fraction | 0.469 | +| clip_range | 0.2 | +| entropy_loss | -0.419 | +| explained_variance | -2.5 | +| learning_rate | 0.0001 | +| loss | -0.086 | +| n_updates | 83450 | +| policy_gradient_loss | -0.0645 | +| value_loss | 0.000755 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | -0.101 | +| time/ | | +| fps | 310 | +| iterations | 2294 | +| time_elapsed | 7563 | +| total_timesteps | 2349056 | +| train/ | | +| approx_kl | 1.7210981 | +| clip_fraction | 0.411 | +| clip_range | 0.2 | +| entropy_loss | -0.32 | +| explained_variance | -4.34 | +| learning_rate | 0.0001 | +| loss | -0.0624 | +| n_updates | 83460 | +| policy_gradient_loss | -0.0551 | +| value_loss | 0.000695 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | -0.101 | +| time/ | | +| fps | 310 | +| iterations | 2295 | +| time_elapsed | 7566 | +| total_timesteps | 2350080 | +| train/ | | +| approx_kl | 1.9550309 | +| clip_fraction | 0.445 | +| clip_range | 0.2 | +| entropy_loss | -0.365 | +| explained_variance | -1.13 | +| learning_rate | 0.0001 | +| loss | -0.0865 | +| n_updates | 83470 | +| policy_gradient_loss | -0.057 | +| value_loss | 0.000476 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | -0.0973 | +| time/ | | +| fps | 310 | +| iterations | 2296 | +| time_elapsed | 7570 | +| total_timesteps | 2351104 | +| train/ | | +| approx_kl | 1.6376104 | +| clip_fraction | 0.446 | +| clip_range | 0.2 | +| entropy_loss | -0.339 | +| explained_variance | -1.56 | +| learning_rate | 0.0001 | +| loss | -0.0906 | +| n_updates | 83480 | +| policy_gradient_loss | -0.0627 | +| value_loss | 0.000543 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | -0.099 | +| time/ | | +| fps | 310 | +| iterations | 2297 | +| time_elapsed | 7573 | +| total_timesteps | 2352128 | +| train/ | | +| approx_kl | 2.167192 | +| clip_fraction | 0.399 | +| clip_range | 0.2 | +| entropy_loss | -0.351 | +| explained_variance | -3.24 | +| learning_rate | 0.0001 | +| loss | -0.0697 | +| n_updates | 83490 | +| policy_gradient_loss | -0.0519 | +| value_loss | 0.000925 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | -0.102 | +| time/ | | +| fps | 310 | +| iterations | 2298 | +| time_elapsed | 7576 | +| total_timesteps | 2353152 | +| train/ | | +| approx_kl | 2.0821042 | +| clip_fraction | 0.421 | +| clip_range | 0.2 | +| entropy_loss | -0.3 | +| explained_variance | -4.58 | +| learning_rate | 0.0001 | +| loss | -0.0848 | +| n_updates | 83500 | +| policy_gradient_loss | -0.064 | +| value_loss | 0.00051 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | -0.0991 | +| time/ | | +| fps | 310 | +| iterations | 2299 | +| time_elapsed | 7579 | +| total_timesteps | 2354176 | +| train/ | | +| approx_kl | 1.7805924 | +| clip_fraction | 0.414 | +| clip_range | 0.2 | +| entropy_loss | -0.351 | +| explained_variance | -0.81 | +| learning_rate | 0.0001 | +| loss | -0.0551 | +| n_updates | 83510 | +| policy_gradient_loss | -0.0387 | +| value_loss | 0.000617 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | -0.0991 | +| time/ | | +| fps | 310 | +| iterations | 2300 | +| time_elapsed | 7582 | +| total_timesteps | 2355200 | +| train/ | | +| approx_kl | 43.774952 | +| clip_fraction | 0.409 | +| clip_range | 0.2 | +| entropy_loss | -0.31 | +| explained_variance | -2.32 | +| learning_rate | 0.0001 | +| loss | -0.0453 | +| n_updates | 83520 | +| policy_gradient_loss | -0.0469 | +| value_loss | 0.000951 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | -0.0987 | +| time/ | | +| fps | 310 | +| iterations | 2301 | +| time_elapsed | 7586 | +| total_timesteps | 2356224 | +| train/ | | +| approx_kl | 2.003455 | +| clip_fraction | 0.438 | +| clip_range | 0.2 | +| entropy_loss | -0.32 | +| explained_variance | -3.65 | +| learning_rate | 0.0001 | +| loss | -0.0611 | +| n_updates | 83530 | +| policy_gradient_loss | -0.0574 | +| value_loss | 0.000553 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | -0.0987 | +| time/ | | +| fps | 310 | +| iterations | 2302 | +| time_elapsed | 7589 | +| total_timesteps | 2357248 | +| train/ | | +| approx_kl | 7.201186 | +| clip_fraction | 0.391 | +| clip_range | 0.2 | +| entropy_loss | -0.263 | +| explained_variance | -3.62 | +| learning_rate | 0.0001 | +| loss | -0.0575 | +| n_updates | 83540 | +| policy_gradient_loss | -0.0565 | +| value_loss | 0.000617 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | -0.0963 | +| time/ | | +| fps | 310 | +| iterations | 2303 | +| time_elapsed | 7592 | +| total_timesteps | 2358272 | +| train/ | | +| approx_kl | 2.254489 | +| clip_fraction | 0.447 | +| clip_range | 0.2 | +| entropy_loss | -0.336 | +| explained_variance | -0.961 | +| learning_rate | 0.0001 | +| loss | -0.0961 | +| n_updates | 83550 | +| policy_gradient_loss | -0.0604 | +| value_loss | 0.000717 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | -0.0963 | +| time/ | | +| fps | 310 | +| iterations | 2304 | +| time_elapsed | 7595 | +| total_timesteps | 2359296 | +| train/ | | +| approx_kl | 1.9100089 | +| clip_fraction | 0.391 | +| clip_range | 0.2 | +| entropy_loss | -0.249 | +| explained_variance | -7.52 | +| learning_rate | 0.0001 | +| loss | -0.0818 | +| n_updates | 83560 | +| policy_gradient_loss | -0.0556 | +| value_loss | 0.000566 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | -0.102 | +| time/ | | +| fps | 310 | +| iterations | 2305 | +| time_elapsed | 7599 | +| total_timesteps | 2360320 | +| train/ | | +| approx_kl | 2.0943217 | +| clip_fraction | 0.427 | +| clip_range | 0.2 | +| entropy_loss | -0.3 | +| explained_variance | -3.87 | +| learning_rate | 0.0001 | +| loss | -0.094 | +| n_updates | 83570 | +| policy_gradient_loss | -0.0571 | +| value_loss | 0.000594 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | -0.0997 | +| time/ | | +| fps | 310 | +| iterations | 2306 | +| time_elapsed | 7602 | +| total_timesteps | 2361344 | +| train/ | | +| approx_kl | 2.59084 | +| clip_fraction | 0.42 | +| clip_range | 0.2 | +| entropy_loss | -0.276 | +| explained_variance | -0.884 | +| learning_rate | 0.0001 | +| loss | -0.0741 | +| n_updates | 83580 | +| policy_gradient_loss | -0.0542 | +| value_loss | 0.00098 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | -0.102 | +| time/ | | +| fps | 310 | +| iterations | 2307 | +| time_elapsed | 7605 | +| total_timesteps | 2362368 | +| train/ | | +| approx_kl | 2.0072803 | +| clip_fraction | 0.436 | +| clip_range | 0.2 | +| entropy_loss | -0.299 | +| explained_variance | -7.05 | +| learning_rate | 0.0001 | +| loss | -0.0738 | +| n_updates | 83590 | +| policy_gradient_loss | -0.055 | +| value_loss | 0.000535 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | -0.102 | +| time/ | | +| fps | 310 | +| iterations | 2308 | +| time_elapsed | 7609 | +| total_timesteps | 2363392 | +| train/ | | +| approx_kl | 1.8111445 | +| clip_fraction | 0.436 | +| clip_range | 0.2 | +| entropy_loss | -0.343 | +| explained_variance | -2.38 | +| learning_rate | 0.0001 | +| loss | -0.0747 | +| n_updates | 83600 | +| policy_gradient_loss | -0.0548 | +| value_loss | 0.000301 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.58e+03 | +| ep_rew_mean | -0.103 | +| time/ | | +| fps | 310 | +| iterations | 2309 | +| time_elapsed | 7612 | +| total_timesteps | 2364416 | +| train/ | | +| approx_kl | 2.8547938 | +| clip_fraction | 0.431 | +| clip_range | 0.2 | +| entropy_loss | -0.312 | +| explained_variance | -3.19 | +| learning_rate | 0.0001 | +| loss | -0.0358 | +| n_updates | 83610 | +| policy_gradient_loss | -0.0612 | +| value_loss | 0.00064 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | -0.101 | +| time/ | | +| fps | 310 | +| iterations | 2310 | +| time_elapsed | 7615 | +| total_timesteps | 2365440 | +| train/ | | +| approx_kl | 2.3885407 | +| clip_fraction | 0.431 | +| clip_range | 0.2 | +| entropy_loss | -0.307 | +| explained_variance | -1.36 | +| learning_rate | 0.0001 | +| loss | -0.0719 | +| n_updates | 83620 | +| policy_gradient_loss | -0.0552 | +| value_loss | 0.000678 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | -0.101 | +| time/ | | +| fps | 310 | +| iterations | 2311 | +| time_elapsed | 7619 | +| total_timesteps | 2366464 | +| train/ | | +| approx_kl | 2.0437984 | +| clip_fraction | 0.41 | +| clip_range | 0.2 | +| entropy_loss | -0.315 | +| explained_variance | -1.46 | +| learning_rate | 0.0001 | +| loss | -0.0834 | +| n_updates | 83630 | +| policy_gradient_loss | -0.043 | +| value_loss | 0.000318 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | -0.101 | +| time/ | | +| fps | 310 | +| iterations | 2312 | +| time_elapsed | 7622 | +| total_timesteps | 2367488 | +| train/ | | +| approx_kl | 2.1500337 | +| clip_fraction | 0.378 | +| clip_range | 0.2 | +| entropy_loss | -0.233 | +| explained_variance | -0.451 | +| learning_rate | 0.0001 | +| loss | -0.0576 | +| n_updates | 83640 | +| policy_gradient_loss | -0.0394 | +| value_loss | 0.000839 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | -0.104 | +| time/ | | +| fps | 310 | +| iterations | 2313 | +| time_elapsed | 7626 | +| total_timesteps | 2368512 | +| train/ | | +| approx_kl | 1.6421814 | +| clip_fraction | 0.424 | +| clip_range | 0.2 | +| entropy_loss | -0.345 | +| explained_variance | -5.86 | +| learning_rate | 0.0001 | +| loss | -0.0768 | +| n_updates | 83650 | +| policy_gradient_loss | -0.059 | +| value_loss | 0.000578 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | -0.103 | +| time/ | | +| fps | 310 | +| iterations | 2314 | +| time_elapsed | 7629 | +| total_timesteps | 2369536 | +| train/ | | +| approx_kl | 1.6524701 | +| clip_fraction | 0.392 | +| clip_range | 0.2 | +| entropy_loss | -0.29 | +| explained_variance | -2.01 | +| learning_rate | 0.0001 | +| loss | -0.0545 | +| n_updates | 83660 | +| policy_gradient_loss | -0.046 | +| value_loss | 0.00061 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.58e+03 | +| ep_rew_mean | -0.106 | +| time/ | | +| fps | 310 | +| iterations | 2315 | +| time_elapsed | 7632 | +| total_timesteps | 2370560 | +| train/ | | +| approx_kl | 1.6843207 | +| clip_fraction | 0.393 | +| clip_range | 0.2 | +| entropy_loss | -0.277 | +| explained_variance | -2.51 | +| learning_rate | 0.0001 | +| loss | -0.0667 | +| n_updates | 83670 | +| policy_gradient_loss | -0.057 | +| value_loss | 0.000564 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.58e+03 | +| ep_rew_mean | -0.106 | +| time/ | | +| fps | 310 | +| iterations | 2316 | +| time_elapsed | 7635 | +| total_timesteps | 2371584 | +| train/ | | +| approx_kl | 2.8988533 | +| clip_fraction | 0.405 | +| clip_range | 0.2 | +| entropy_loss | -0.327 | +| explained_variance | -0.858 | +| learning_rate | 0.0001 | +| loss | -0.0767 | +| n_updates | 83680 | +| policy_gradient_loss | -0.0578 | +| value_loss | 0.000704 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.58e+03 | +| ep_rew_mean | -0.103 | +| time/ | | +| fps | 310 | +| iterations | 2317 | +| time_elapsed | 7639 | +| total_timesteps | 2372608 | +| train/ | | +| approx_kl | 2.481194 | +| clip_fraction | 0.466 | +| clip_range | 0.2 | +| entropy_loss | -0.364 | +| explained_variance | -3.3 | +| learning_rate | 0.0001 | +| loss | -0.081 | +| n_updates | 83690 | +| policy_gradient_loss | -0.0652 | +| value_loss | 0.000772 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.58e+03 | +| ep_rew_mean | -0.103 | +| time/ | | +| fps | 310 | +| iterations | 2318 | +| time_elapsed | 7642 | +| total_timesteps | 2373632 | +| train/ | | +| approx_kl | 1.6079348 | +| clip_fraction | 0.416 | +| clip_range | 0.2 | +| entropy_loss | -0.306 | +| explained_variance | -3.97 | +| learning_rate | 0.0001 | +| loss | -0.0653 | +| n_updates | 83700 | +| policy_gradient_loss | -0.0527 | +| value_loss | 0.000525 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.58e+03 | +| ep_rew_mean | -0.1 | +| time/ | | +| fps | 310 | +| iterations | 2319 | +| time_elapsed | 7645 | +| total_timesteps | 2374656 | +| train/ | | +| approx_kl | 1.8228633 | +| clip_fraction | 0.466 | +| clip_range | 0.2 | +| entropy_loss | -0.397 | +| explained_variance | -2.25 | +| learning_rate | 0.0001 | +| loss | -0.0783 | +| n_updates | 83710 | +| policy_gradient_loss | -0.0587 | +| value_loss | 0.000676 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.58e+03 | +| ep_rew_mean | -0.1 | +| time/ | | +| fps | 310 | +| iterations | 2320 | +| time_elapsed | 7648 | +| total_timesteps | 2375680 | +| train/ | | +| approx_kl | 2.4055293 | +| clip_fraction | 0.419 | +| clip_range | 0.2 | +| entropy_loss | -0.261 | +| explained_variance | -7.28 | +| learning_rate | 0.0001 | +| loss | -0.0702 | +| n_updates | 83720 | +| policy_gradient_loss | -0.0602 | +| value_loss | 0.000378 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | -0.0936 | +| time/ | | +| fps | 310 | +| iterations | 2321 | +| time_elapsed | 7651 | +| total_timesteps | 2376704 | +| train/ | | +| approx_kl | 1.9388727 | +| clip_fraction | 0.477 | +| clip_range | 0.2 | +| entropy_loss | -0.394 | +| explained_variance | -0.589 | +| learning_rate | 0.0001 | +| loss | -0.0959 | +| n_updates | 83730 | +| policy_gradient_loss | -0.0552 | +| value_loss | 0.000804 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | -0.0962 | +| time/ | | +| fps | 310 | +| iterations | 2322 | +| time_elapsed | 7654 | +| total_timesteps | 2377728 | +| train/ | | +| approx_kl | 65.241005 | +| clip_fraction | 0.41 | +| clip_range | 0.2 | +| entropy_loss | -0.306 | +| explained_variance | -6.71 | +| learning_rate | 0.0001 | +| loss | -0.0607 | +| n_updates | 83740 | +| policy_gradient_loss | -0.0522 | +| value_loss | 0.000612 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | -0.0962 | +| time/ | | +| fps | 310 | +| iterations | 2323 | +| time_elapsed | 7657 | +| total_timesteps | 2378752 | +| train/ | | +| approx_kl | 1.537642 | +| clip_fraction | 0.358 | +| clip_range | 0.2 | +| entropy_loss | -0.254 | +| explained_variance | -1.38 | +| learning_rate | 0.0001 | +| loss | -0.0681 | +| n_updates | 83750 | +| policy_gradient_loss | -0.0424 | +| value_loss | 0.000642 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | -0.0962 | +| time/ | | +| fps | 310 | +| iterations | 2324 | +| time_elapsed | 7661 | +| total_timesteps | 2379776 | +| train/ | | +| approx_kl | 2.1814528 | +| clip_fraction | 0.454 | +| clip_range | 0.2 | +| entropy_loss | -0.32 | +| explained_variance | -7 | +| learning_rate | 0.0001 | +| loss | -0.0889 | +| n_updates | 83760 | +| policy_gradient_loss | -0.0575 | +| value_loss | 0.000495 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | -0.0983 | +| time/ | | +| fps | 310 | +| iterations | 2325 | +| time_elapsed | 7664 | +| total_timesteps | 2380800 | +| train/ | | +| approx_kl | 3.6856248 | +| clip_fraction | 0.361 | +| clip_range | 0.2 | +| entropy_loss | -0.244 | +| explained_variance | -1.1 | +| learning_rate | 0.0001 | +| loss | -0.062 | +| n_updates | 83770 | +| policy_gradient_loss | -0.0447 | +| value_loss | 0.000626 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | -0.101 | +| time/ | | +| fps | 310 | +| iterations | 2326 | +| time_elapsed | 7668 | +| total_timesteps | 2381824 | +| train/ | | +| approx_kl | 1.6001933 | +| clip_fraction | 0.372 | +| clip_range | 0.2 | +| entropy_loss | -0.262 | +| explained_variance | -1.28 | +| learning_rate | 0.0001 | +| loss | -0.0658 | +| n_updates | 83780 | +| policy_gradient_loss | -0.05 | +| value_loss | 0.000776 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | -0.0996 | +| time/ | | +| fps | 310 | +| iterations | 2327 | +| time_elapsed | 7671 | +| total_timesteps | 2382848 | +| train/ | | +| approx_kl | 1.588474 | +| clip_fraction | 0.401 | +| clip_range | 0.2 | +| entropy_loss | -0.277 | +| explained_variance | -0.619 | +| learning_rate | 0.0001 | +| loss | -0.0655 | +| n_updates | 83790 | +| policy_gradient_loss | -0.0523 | +| value_loss | 0.000962 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | -0.0996 | +| time/ | | +| fps | 310 | +| iterations | 2328 | +| time_elapsed | 7675 | +| total_timesteps | 2383872 | +| train/ | | +| approx_kl | 2.1793127 | +| clip_fraction | 0.38 | +| clip_range | 0.2 | +| entropy_loss | -0.252 | +| explained_variance | -2.37 | +| learning_rate | 0.0001 | +| loss | -0.0762 | +| n_updates | 83800 | +| policy_gradient_loss | -0.0537 | +| value_loss | 0.000632 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | -0.0988 | +| time/ | | +| fps | 310 | +| iterations | 2329 | +| time_elapsed | 7678 | +| total_timesteps | 2384896 | +| train/ | | +| approx_kl | 2.1039505 | +| clip_fraction | 0.458 | +| clip_range | 0.2 | +| entropy_loss | -0.293 | +| explained_variance | -2.82 | +| learning_rate | 0.0001 | +| loss | -0.0645 | +| n_updates | 83810 | +| policy_gradient_loss | -0.058 | +| value_loss | 0.00095 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | -0.1 | +| time/ | | +| fps | 310 | +| iterations | 2330 | +| time_elapsed | 7681 | +| total_timesteps | 2385920 | +| train/ | | +| approx_kl | 3.9384713 | +| clip_fraction | 0.443 | +| clip_range | 0.2 | +| entropy_loss | -0.343 | +| explained_variance | -2.82 | +| learning_rate | 0.0001 | +| loss | -0.0782 | +| n_updates | 83820 | +| policy_gradient_loss | -0.0548 | +| value_loss | 0.000531 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | -0.1 | +| time/ | | +| fps | 310 | +| iterations | 2331 | +| time_elapsed | 7685 | +| total_timesteps | 2386944 | +| train/ | | +| approx_kl | 2.084742 | +| clip_fraction | 0.462 | +| clip_range | 0.2 | +| entropy_loss | -0.357 | +| explained_variance | -2.24 | +| learning_rate | 0.0001 | +| loss | -0.099 | +| n_updates | 83830 | +| policy_gradient_loss | -0.0556 | +| value_loss | 0.000422 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | -0.1 | +| time/ | | +| fps | 310 | +| iterations | 2332 | +| time_elapsed | 7688 | +| total_timesteps | 2387968 | +| train/ | | +| approx_kl | 2.0552084 | +| clip_fraction | 0.425 | +| clip_range | 0.2 | +| entropy_loss | -0.348 | +| explained_variance | -5.84 | +| learning_rate | 0.0001 | +| loss | -0.0804 | +| n_updates | 83840 | +| policy_gradient_loss | -0.058 | +| value_loss | 0.000568 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.58e+03 | +| ep_rew_mean | -0.101 | +| time/ | | +| fps | 310 | +| iterations | 2333 | +| time_elapsed | 7691 | +| total_timesteps | 2388992 | +| train/ | | +| approx_kl | 2.0669706 | +| clip_fraction | 0.415 | +| clip_range | 0.2 | +| entropy_loss | -0.305 | +| explained_variance | -1.51 | +| learning_rate | 0.0001 | +| loss | -0.0801 | +| n_updates | 83850 | +| policy_gradient_loss | -0.0562 | +| value_loss | 0.000774 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.58e+03 | +| ep_rew_mean | -0.101 | +| time/ | | +| fps | 310 | +| iterations | 2334 | +| time_elapsed | 7695 | +| total_timesteps | 2390016 | +| train/ | | +| approx_kl | 1.8603628 | +| clip_fraction | 0.417 | +| clip_range | 0.2 | +| entropy_loss | -0.324 | +| explained_variance | -4.53 | +| learning_rate | 0.0001 | +| loss | -0.0809 | +| n_updates | 83860 | +| policy_gradient_loss | -0.0585 | +| value_loss | 0.000577 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | -0.0971 | +| time/ | | +| fps | 310 | +| iterations | 2335 | +| time_elapsed | 7698 | +| total_timesteps | 2391040 | +| train/ | | +| approx_kl | 2.310162 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.337 | +| explained_variance | -1.6 | +| learning_rate | 0.0001 | +| loss | -0.0808 | +| n_updates | 83870 | +| policy_gradient_loss | -0.0575 | +| value_loss | 0.000512 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | -0.0971 | +| time/ | | +| fps | 310 | +| iterations | 2336 | +| time_elapsed | 7701 | +| total_timesteps | 2392064 | +| train/ | | +| approx_kl | 1.5352316 | +| clip_fraction | 0.433 | +| clip_range | 0.2 | +| entropy_loss | -0.338 | +| explained_variance | -7.06 | +| learning_rate | 0.0001 | +| loss | -0.068 | +| n_updates | 83880 | +| policy_gradient_loss | -0.0624 | +| value_loss | 0.000414 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | -0.0986 | +| time/ | | +| fps | 310 | +| iterations | 2337 | +| time_elapsed | 7704 | +| total_timesteps | 2393088 | +| train/ | | +| approx_kl | 1.7072947 | +| clip_fraction | 0.443 | +| clip_range | 0.2 | +| entropy_loss | -0.402 | +| explained_variance | -3.91 | +| learning_rate | 0.0001 | +| loss | -0.0753 | +| n_updates | 83890 | +| policy_gradient_loss | -0.0603 | +| value_loss | 0.000361 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | -0.0986 | +| time/ | | +| fps | 310 | +| iterations | 2338 | +| time_elapsed | 7708 | +| total_timesteps | 2394112 | +| train/ | | +| approx_kl | 1.7875437 | +| clip_fraction | 0.372 | +| clip_range | 0.2 | +| entropy_loss | -0.26 | +| explained_variance | -2.24 | +| learning_rate | 0.0001 | +| loss | -0.0653 | +| n_updates | 83900 | +| policy_gradient_loss | -0.0528 | +| value_loss | 0.000554 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | -0.0986 | +| time/ | | +| fps | 310 | +| iterations | 2339 | +| time_elapsed | 7711 | +| total_timesteps | 2395136 | +| train/ | | +| approx_kl | 1.9393321 | +| clip_fraction | 0.424 | +| clip_range | 0.2 | +| entropy_loss | -0.333 | +| explained_variance | -1.14 | +| learning_rate | 0.0001 | +| loss | -0.0365 | +| n_updates | 83910 | +| policy_gradient_loss | -0.0442 | +| value_loss | 0.000522 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | -0.0973 | +| time/ | | +| fps | 310 | +| iterations | 2340 | +| time_elapsed | 7714 | +| total_timesteps | 2396160 | +| train/ | | +| approx_kl | 2.290973 | +| clip_fraction | 0.456 | +| clip_range | 0.2 | +| entropy_loss | -0.334 | +| explained_variance | -1.51 | +| learning_rate | 0.0001 | +| loss | -0.0809 | +| n_updates | 83920 | +| policy_gradient_loss | -0.0629 | +| value_loss | 0.000809 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | -0.0884 | +| time/ | | +| fps | 310 | +| iterations | 2341 | +| time_elapsed | 7717 | +| total_timesteps | 2397184 | +| train/ | | +| approx_kl | 1.8137505 | +| clip_fraction | 0.427 | +| clip_range | 0.2 | +| entropy_loss | -0.344 | +| explained_variance | -1.53 | +| learning_rate | 0.0001 | +| loss | -0.0511 | +| n_updates | 83930 | +| policy_gradient_loss | -0.0605 | +| value_loss | 0.000666 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | -0.0884 | +| time/ | | +| fps | 310 | +| iterations | 2342 | +| time_elapsed | 7720 | +| total_timesteps | 2398208 | +| train/ | | +| approx_kl | 1.6325517 | +| clip_fraction | 0.418 | +| clip_range | 0.2 | +| entropy_loss | -0.334 | +| explained_variance | -0.622 | +| learning_rate | 0.0001 | +| loss | -0.0767 | +| n_updates | 83940 | +| policy_gradient_loss | -0.0585 | +| value_loss | 0.000599 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | -0.0924 | +| time/ | | +| fps | 310 | +| iterations | 2343 | +| time_elapsed | 7724 | +| total_timesteps | 2399232 | +| train/ | | +| approx_kl | 1.6541271 | +| clip_fraction | 0.428 | +| clip_range | 0.2 | +| entropy_loss | -0.353 | +| explained_variance | -5.65 | +| learning_rate | 0.0001 | +| loss | -0.0776 | +| n_updates | 83950 | +| policy_gradient_loss | -0.057 | +| value_loss | 0.000409 | +--------------------------------------- + +Current state: Champion.Level7.RyuVsEHonda +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | -0.0924 | +| time/ | | +| fps | 310 | +| iterations | 2344 | +| time_elapsed | 7727 | +| total_timesteps | 2400256 | +| train/ | | +| approx_kl | 3.754396 | +| clip_fraction | 0.379 | +| clip_range | 0.2 | +| entropy_loss | -0.287 | +| explained_variance | -0.764 | +| learning_rate | 0.0001 | +| loss | -0.0614 | +| n_updates | 83960 | +| policy_gradient_loss | -0.0468 | +| value_loss | 0.00052 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | -0.0924 | +| time/ | | +| fps | 310 | +| iterations | 2345 | +| time_elapsed | 7730 | +| total_timesteps | 2401280 | +| train/ | | +| approx_kl | 2.3834827 | +| clip_fraction | 0.377 | +| clip_range | 0.2 | +| entropy_loss | -0.254 | +| explained_variance | -1.2 | +| learning_rate | 0.0001 | +| loss | -0.0677 | +| n_updates | 83970 | +| policy_gradient_loss | -0.0493 | +| value_loss | 0.000993 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.61e+03 | +| ep_rew_mean | -0.0876 | +| time/ | | +| fps | 310 | +| iterations | 2346 | +| time_elapsed | 7734 | +| total_timesteps | 2402304 | +| train/ | | +| approx_kl | 1.6481426 | +| clip_fraction | 0.463 | +| clip_range | 0.2 | +| entropy_loss | -0.372 | +| explained_variance | -1.78 | +| learning_rate | 0.0001 | +| loss | -0.0741 | +| n_updates | 83980 | +| policy_gradient_loss | -0.0639 | +| value_loss | 0.00064 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.61e+03 | +| ep_rew_mean | -0.0876 | +| time/ | | +| fps | 310 | +| iterations | 2347 | +| time_elapsed | 7737 | +| total_timesteps | 2403328 | +| train/ | | +| approx_kl | 2.1099405 | +| clip_fraction | 0.452 | +| clip_range | 0.2 | +| entropy_loss | -0.376 | +| explained_variance | -1.97 | +| learning_rate | 0.0001 | +| loss | -0.0652 | +| n_updates | 83990 | +| policy_gradient_loss | -0.0597 | +| value_loss | 0.000703 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | -0.0852 | +| time/ | | +| fps | 310 | +| iterations | 2348 | +| time_elapsed | 7740 | +| total_timesteps | 2404352 | +| train/ | | +| approx_kl | 2.3033838 | +| clip_fraction | 0.456 | +| clip_range | 0.2 | +| entropy_loss | -0.294 | +| explained_variance | -1.9 | +| learning_rate | 0.0001 | +| loss | -0.063 | +| n_updates | 84000 | +| policy_gradient_loss | -0.0623 | +| value_loss | 0.000553 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | -0.0852 | +| time/ | | +| fps | 310 | +| iterations | 2349 | +| time_elapsed | 7744 | +| total_timesteps | 2405376 | +| train/ | | +| approx_kl | 2.5719967 | +| clip_fraction | 0.438 | +| clip_range | 0.2 | +| entropy_loss | -0.328 | +| explained_variance | -1.39 | +| learning_rate | 0.0001 | +| loss | -0.0569 | +| n_updates | 84010 | +| policy_gradient_loss | -0.0475 | +| value_loss | 0.000471 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | -0.0849 | +| time/ | | +| fps | 310 | +| iterations | 2350 | +| time_elapsed | 7747 | +| total_timesteps | 2406400 | +| train/ | | +| approx_kl | 2.1012309 | +| clip_fraction | 0.365 | +| clip_range | 0.2 | +| entropy_loss | -0.219 | +| explained_variance | -2.42 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 84020 | +| policy_gradient_loss | -0.0505 | +| value_loss | 0.000628 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | -0.0849 | +| time/ | | +| fps | 310 | +| iterations | 2351 | +| time_elapsed | 7750 | +| total_timesteps | 2407424 | +| train/ | | +| approx_kl | 2.672487 | +| clip_fraction | 0.492 | +| clip_range | 0.2 | +| entropy_loss | -0.366 | +| explained_variance | -1.4 | +| learning_rate | 0.0001 | +| loss | -0.0722 | +| n_updates | 84030 | +| policy_gradient_loss | -0.0546 | +| value_loss | 0.000307 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.61e+03 | +| ep_rew_mean | -0.076 | +| time/ | | +| fps | 310 | +| iterations | 2352 | +| time_elapsed | 7754 | +| total_timesteps | 2408448 | +| train/ | | +| approx_kl | 5.944882 | +| clip_fraction | 0.452 | +| clip_range | 0.2 | +| entropy_loss | -0.304 | +| explained_variance | -1.11 | +| learning_rate | 0.0001 | +| loss | -0.0788 | +| n_updates | 84040 | +| policy_gradient_loss | -0.0589 | +| value_loss | 0.000638 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.61e+03 | +| ep_rew_mean | -0.076 | +| time/ | | +| fps | 310 | +| iterations | 2353 | +| time_elapsed | 7757 | +| total_timesteps | 2409472 | +| train/ | | +| approx_kl | 2.2304971 | +| clip_fraction | 0.452 | +| clip_range | 0.2 | +| entropy_loss | -0.33 | +| explained_variance | -1.77 | +| learning_rate | 0.0001 | +| loss | -0.0957 | +| n_updates | 84050 | +| policy_gradient_loss | -0.0618 | +| value_loss | 0.000416 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.62e+03 | +| ep_rew_mean | -0.0728 | +| time/ | | +| fps | 310 | +| iterations | 2354 | +| time_elapsed | 7760 | +| total_timesteps | 2410496 | +| train/ | | +| approx_kl | 2.4868295 | +| clip_fraction | 0.449 | +| clip_range | 0.2 | +| entropy_loss | -0.296 | +| explained_variance | -1.77 | +| learning_rate | 0.0001 | +| loss | -0.085 | +| n_updates | 84060 | +| policy_gradient_loss | -0.0613 | +| value_loss | 0.000554 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.61e+03 | +| ep_rew_mean | -0.074 | +| time/ | | +| fps | 310 | +| iterations | 2355 | +| time_elapsed | 7763 | +| total_timesteps | 2411520 | +| train/ | | +| approx_kl | 2.9747062 | +| clip_fraction | 0.371 | +| clip_range | 0.2 | +| entropy_loss | -0.236 | +| explained_variance | -2.29 | +| learning_rate | 0.0001 | +| loss | -0.065 | +| n_updates | 84070 | +| policy_gradient_loss | -0.0569 | +| value_loss | 0.000432 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.61e+03 | +| ep_rew_mean | -0.074 | +| time/ | | +| fps | 310 | +| iterations | 2356 | +| time_elapsed | 7766 | +| total_timesteps | 2412544 | +| train/ | | +| approx_kl | 1.9298794 | +| clip_fraction | 0.333 | +| clip_range | 0.2 | +| entropy_loss | -0.22 | +| explained_variance | -0.418 | +| learning_rate | 0.0001 | +| loss | -0.0527 | +| n_updates | 84080 | +| policy_gradient_loss | -0.0471 | +| value_loss | 0.000687 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.62e+03 | +| ep_rew_mean | -0.0714 | +| time/ | | +| fps | 310 | +| iterations | 2357 | +| time_elapsed | 7769 | +| total_timesteps | 2413568 | +| train/ | | +| approx_kl | 2.0179179 | +| clip_fraction | 0.41 | +| clip_range | 0.2 | +| entropy_loss | -0.268 | +| explained_variance | -2.62 | +| learning_rate | 0.0001 | +| loss | -0.0846 | +| n_updates | 84090 | +| policy_gradient_loss | -0.0596 | +| value_loss | 0.000699 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.62e+03 | +| ep_rew_mean | -0.0695 | +| time/ | | +| fps | 310 | +| iterations | 2358 | +| time_elapsed | 7772 | +| total_timesteps | 2414592 | +| train/ | | +| approx_kl | 2.1188602 | +| clip_fraction | 0.428 | +| clip_range | 0.2 | +| entropy_loss | -0.288 | +| explained_variance | -1.35 | +| learning_rate | 0.0001 | +| loss | -0.0548 | +| n_updates | 84100 | +| policy_gradient_loss | -0.056 | +| value_loss | 0.000549 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.61e+03 | +| ep_rew_mean | -0.0724 | +| time/ | | +| fps | 310 | +| iterations | 2359 | +| time_elapsed | 7776 | +| total_timesteps | 2415616 | +| train/ | | +| approx_kl | 1.9175291 | +| clip_fraction | 0.424 | +| clip_range | 0.2 | +| entropy_loss | -0.284 | +| explained_variance | -3.31 | +| learning_rate | 0.0001 | +| loss | -0.072 | +| n_updates | 84110 | +| policy_gradient_loss | -0.0575 | +| value_loss | 0.000465 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | -0.0732 | +| time/ | | +| fps | 310 | +| iterations | 2360 | +| time_elapsed | 7779 | +| total_timesteps | 2416640 | +| train/ | | +| approx_kl | 1.9735825 | +| clip_fraction | 0.404 | +| clip_range | 0.2 | +| entropy_loss | -0.29 | +| explained_variance | -0.941 | +| learning_rate | 0.0001 | +| loss | -0.0748 | +| n_updates | 84120 | +| policy_gradient_loss | -0.0554 | +| value_loss | 0.000716 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | -0.0732 | +| time/ | | +| fps | 310 | +| iterations | 2361 | +| time_elapsed | 7782 | +| total_timesteps | 2417664 | +| train/ | | +| approx_kl | 2.0414574 | +| clip_fraction | 0.415 | +| clip_range | 0.2 | +| entropy_loss | -0.29 | +| explained_variance | -6.68 | +| learning_rate | 0.0001 | +| loss | -0.0631 | +| n_updates | 84130 | +| policy_gradient_loss | -0.0554 | +| value_loss | 0.000632 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | -0.0732 | +| time/ | | +| fps | 310 | +| iterations | 2362 | +| time_elapsed | 7786 | +| total_timesteps | 2418688 | +| train/ | | +| approx_kl | 1.9443634 | +| clip_fraction | 0.446 | +| clip_range | 0.2 | +| entropy_loss | -0.334 | +| explained_variance | -0.811 | +| learning_rate | 0.0001 | +| loss | -0.0581 | +| n_updates | 84140 | +| policy_gradient_loss | -0.0498 | +| value_loss | 0.000434 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.61e+03 | +| ep_rew_mean | -0.0668 | +| time/ | | +| fps | 310 | +| iterations | 2363 | +| time_elapsed | 7789 | +| total_timesteps | 2419712 | +| train/ | | +| approx_kl | 1.7324287 | +| clip_fraction | 0.432 | +| clip_range | 0.2 | +| entropy_loss | -0.306 | +| explained_variance | -7.09 | +| learning_rate | 0.0001 | +| loss | -0.0882 | +| n_updates | 84150 | +| policy_gradient_loss | -0.0581 | +| value_loss | 0.000219 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.61e+03 | +| ep_rew_mean | -0.0668 | +| time/ | | +| fps | 310 | +| iterations | 2364 | +| time_elapsed | 7793 | +| total_timesteps | 2420736 | +| train/ | | +| approx_kl | 2.2526796 | +| clip_fraction | 0.434 | +| clip_range | 0.2 | +| entropy_loss | -0.327 | +| explained_variance | -1.7 | +| learning_rate | 0.0001 | +| loss | -0.0912 | +| n_updates | 84160 | +| policy_gradient_loss | -0.055 | +| value_loss | 0.000371 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.61e+03 | +| ep_rew_mean | -0.0615 | +| time/ | | +| fps | 310 | +| iterations | 2365 | +| time_elapsed | 7796 | +| total_timesteps | 2421760 | +| train/ | | +| approx_kl | 2.3094387 | +| clip_fraction | 0.411 | +| clip_range | 0.2 | +| entropy_loss | -0.273 | +| explained_variance | -1.03 | +| learning_rate | 0.0001 | +| loss | -0.0698 | +| n_updates | 84170 | +| policy_gradient_loss | -0.0559 | +| value_loss | 0.000589 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.61e+03 | +| ep_rew_mean | -0.0655 | +| time/ | | +| fps | 310 | +| iterations | 2366 | +| time_elapsed | 7799 | +| total_timesteps | 2422784 | +| train/ | | +| approx_kl | 2.323957 | +| clip_fraction | 0.422 | +| clip_range | 0.2 | +| entropy_loss | -0.31 | +| explained_variance | -7.73 | +| learning_rate | 0.0001 | +| loss | -0.0971 | +| n_updates | 84180 | +| policy_gradient_loss | -0.059 | +| value_loss | 0.000387 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.61e+03 | +| ep_rew_mean | -0.0655 | +| time/ | | +| fps | 310 | +| iterations | 2367 | +| time_elapsed | 7803 | +| total_timesteps | 2423808 | +| train/ | | +| approx_kl | 1.3856261 | +| clip_fraction | 0.38 | +| clip_range | 0.2 | +| entropy_loss | -0.268 | +| explained_variance | -0.558 | +| learning_rate | 0.0001 | +| loss | -0.0687 | +| n_updates | 84190 | +| policy_gradient_loss | -0.0509 | +| value_loss | 0.000637 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | -0.0658 | +| time/ | | +| fps | 310 | +| iterations | 2368 | +| time_elapsed | 7806 | +| total_timesteps | 2424832 | +| train/ | | +| approx_kl | 1.5683025 | +| clip_fraction | 0.414 | +| clip_range | 0.2 | +| entropy_loss | -0.311 | +| explained_variance | -2.6 | +| learning_rate | 0.0001 | +| loss | -0.083 | +| n_updates | 84200 | +| policy_gradient_loss | -0.059 | +| value_loss | 0.000532 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.61e+03 | +| ep_rew_mean | -0.0611 | +| time/ | | +| fps | 310 | +| iterations | 2369 | +| time_elapsed | 7810 | +| total_timesteps | 2425856 | +| train/ | | +| approx_kl | 1.9154886 | +| clip_fraction | 0.411 | +| clip_range | 0.2 | +| entropy_loss | -0.288 | +| explained_variance | -1.19 | +| learning_rate | 0.0001 | +| loss | -0.0766 | +| n_updates | 84210 | +| policy_gradient_loss | -0.0561 | +| value_loss | 0.000649 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.61e+03 | +| ep_rew_mean | -0.0611 | +| time/ | | +| fps | 310 | +| iterations | 2370 | +| time_elapsed | 7813 | +| total_timesteps | 2426880 | +| train/ | | +| approx_kl | 1.8907871 | +| clip_fraction | 0.452 | +| clip_range | 0.2 | +| entropy_loss | -0.305 | +| explained_variance | -0.968 | +| learning_rate | 0.0001 | +| loss | -0.0689 | +| n_updates | 84220 | +| policy_gradient_loss | -0.0634 | +| value_loss | 0.000802 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.61e+03 | +| ep_rew_mean | -0.0611 | +| time/ | | +| fps | 310 | +| iterations | 2371 | +| time_elapsed | 7816 | +| total_timesteps | 2427904 | +| train/ | | +| approx_kl | 3.132008 | +| clip_fraction | 0.444 | +| clip_range | 0.2 | +| entropy_loss | -0.346 | +| explained_variance | -2.03 | +| learning_rate | 0.0001 | +| loss | -0.0823 | +| n_updates | 84230 | +| policy_gradient_loss | -0.0562 | +| value_loss | 0.000575 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.62e+03 | +| ep_rew_mean | -0.0578 | +| time/ | | +| fps | 310 | +| iterations | 2372 | +| time_elapsed | 7819 | +| total_timesteps | 2428928 | +| train/ | | +| approx_kl | 1.7427316 | +| clip_fraction | 0.436 | +| clip_range | 0.2 | +| entropy_loss | -0.33 | +| explained_variance | -9.89 | +| learning_rate | 0.0001 | +| loss | -0.0835 | +| n_updates | 84240 | +| policy_gradient_loss | -0.0525 | +| value_loss | 0.000222 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.62e+03 | +| ep_rew_mean | -0.0588 | +| time/ | | +| fps | 310 | +| iterations | 2373 | +| time_elapsed | 7823 | +| total_timesteps | 2429952 | +| train/ | | +| approx_kl | 2.5334773 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.385 | +| explained_variance | -1.68 | +| learning_rate | 0.0001 | +| loss | -0.106 | +| n_updates | 84250 | +| policy_gradient_loss | -0.0647 | +| value_loss | 0.000332 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.61e+03 | +| ep_rew_mean | -0.0648 | +| time/ | | +| fps | 310 | +| iterations | 2374 | +| time_elapsed | 7826 | +| total_timesteps | 2430976 | +| train/ | | +| approx_kl | 1.3558095 | +| clip_fraction | 0.406 | +| clip_range | 0.2 | +| entropy_loss | -0.292 | +| explained_variance | -3.06 | +| learning_rate | 0.0001 | +| loss | -0.056 | +| n_updates | 84260 | +| policy_gradient_loss | -0.0549 | +| value_loss | 0.000592 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | -0.0683 | +| time/ | | +| fps | 310 | +| iterations | 2375 | +| time_elapsed | 7829 | +| total_timesteps | 2432000 | +| train/ | | +| approx_kl | 1.6577613 | +| clip_fraction | 0.4 | +| clip_range | 0.2 | +| entropy_loss | -0.28 | +| explained_variance | -1.6 | +| learning_rate | 0.0001 | +| loss | -0.0743 | +| n_updates | 84270 | +| policy_gradient_loss | -0.0554 | +| value_loss | 0.00041 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | -0.0708 | +| time/ | | +| fps | 310 | +| iterations | 2376 | +| time_elapsed | 7832 | +| total_timesteps | 2433024 | +| train/ | | +| approx_kl | 2.0584846 | +| clip_fraction | 0.415 | +| clip_range | 0.2 | +| entropy_loss | -0.304 | +| explained_variance | -0.529 | +| learning_rate | 0.0001 | +| loss | -0.0717 | +| n_updates | 84280 | +| policy_gradient_loss | -0.0461 | +| value_loss | 0.000483 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | -0.0715 | +| time/ | | +| fps | 310 | +| iterations | 2377 | +| time_elapsed | 7835 | +| total_timesteps | 2434048 | +| train/ | | +| approx_kl | 1.7231957 | +| clip_fraction | 0.445 | +| clip_range | 0.2 | +| entropy_loss | -0.365 | +| explained_variance | -3.26 | +| learning_rate | 0.0001 | +| loss | -0.0632 | +| n_updates | 84290 | +| policy_gradient_loss | -0.0601 | +| value_loss | 0.000658 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | -0.0715 | +| time/ | | +| fps | 310 | +| iterations | 2378 | +| time_elapsed | 7839 | +| total_timesteps | 2435072 | +| train/ | | +| approx_kl | 1.812769 | +| clip_fraction | 0.435 | +| clip_range | 0.2 | +| entropy_loss | -0.331 | +| explained_variance | -1.34 | +| learning_rate | 0.0001 | +| loss | -0.0845 | +| n_updates | 84300 | +| policy_gradient_loss | -0.0597 | +| value_loss | 0.000607 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | -0.0665 | +| time/ | | +| fps | 310 | +| iterations | 2379 | +| time_elapsed | 7842 | +| total_timesteps | 2436096 | +| train/ | | +| approx_kl | 1.9832158 | +| clip_fraction | 0.472 | +| clip_range | 0.2 | +| entropy_loss | -0.4 | +| explained_variance | -2.56 | +| learning_rate | 0.0001 | +| loss | -0.0807 | +| n_updates | 84310 | +| policy_gradient_loss | -0.0635 | +| value_loss | 0.000349 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | -0.0643 | +| time/ | | +| fps | 310 | +| iterations | 2380 | +| time_elapsed | 7845 | +| total_timesteps | 2437120 | +| train/ | | +| approx_kl | 1.8266778 | +| clip_fraction | 0.437 | +| clip_range | 0.2 | +| entropy_loss | -0.355 | +| explained_variance | -1.32 | +| learning_rate | 0.0001 | +| loss | -0.0777 | +| n_updates | 84320 | +| policy_gradient_loss | -0.0667 | +| value_loss | 0.000841 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | -0.0623 | +| time/ | | +| fps | 310 | +| iterations | 2381 | +| time_elapsed | 7849 | +| total_timesteps | 2438144 | +| train/ | | +| approx_kl | 2.094802 | +| clip_fraction | 0.466 | +| clip_range | 0.2 | +| entropy_loss | -0.341 | +| explained_variance | -1.69 | +| learning_rate | 0.0001 | +| loss | -0.0465 | +| n_updates | 84330 | +| policy_gradient_loss | -0.0623 | +| value_loss | 0.000446 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | -0.0623 | +| time/ | | +| fps | 310 | +| iterations | 2382 | +| time_elapsed | 7852 | +| total_timesteps | 2439168 | +| train/ | | +| approx_kl | 1.6337403 | +| clip_fraction | 0.44 | +| clip_range | 0.2 | +| entropy_loss | -0.35 | +| explained_variance | -1.59 | +| learning_rate | 0.0001 | +| loss | -0.0641 | +| n_updates | 84340 | +| policy_gradient_loss | -0.0599 | +| value_loss | 0.000449 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | -0.0596 | +| time/ | | +| fps | 310 | +| iterations | 2383 | +| time_elapsed | 7856 | +| total_timesteps | 2440192 | +| train/ | | +| approx_kl | 1.8950524 | +| clip_fraction | 0.439 | +| clip_range | 0.2 | +| entropy_loss | -0.331 | +| explained_variance | -3.35 | +| learning_rate | 0.0001 | +| loss | -0.076 | +| n_updates | 84350 | +| policy_gradient_loss | -0.0606 | +| value_loss | 0.000382 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | -0.0554 | +| time/ | | +| fps | 310 | +| iterations | 2384 | +| time_elapsed | 7859 | +| total_timesteps | 2441216 | +| train/ | | +| approx_kl | 3.3400233 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.388 | +| explained_variance | -0.85 | +| learning_rate | 0.0001 | +| loss | -0.089 | +| n_updates | 84360 | +| policy_gradient_loss | -0.0576 | +| value_loss | 0.000545 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | -0.0554 | +| time/ | | +| fps | 310 | +| iterations | 2385 | +| time_elapsed | 7863 | +| total_timesteps | 2442240 | +| train/ | | +| approx_kl | 1.8550496 | +| clip_fraction | 0.433 | +| clip_range | 0.2 | +| entropy_loss | -0.313 | +| explained_variance | -3.17 | +| learning_rate | 0.0001 | +| loss | -0.0659 | +| n_updates | 84370 | +| policy_gradient_loss | -0.0594 | +| value_loss | 0.000849 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.61e+03 | +| ep_rew_mean | -0.049 | +| time/ | | +| fps | 310 | +| iterations | 2386 | +| time_elapsed | 7866 | +| total_timesteps | 2443264 | +| train/ | | +| approx_kl | 2.0821548 | +| clip_fraction | 0.46 | +| clip_range | 0.2 | +| entropy_loss | -0.348 | +| explained_variance | -0.94 | +| learning_rate | 0.0001 | +| loss | -0.0804 | +| n_updates | 84380 | +| policy_gradient_loss | -0.0582 | +| value_loss | 0.000371 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.61e+03 | +| ep_rew_mean | -0.0468 | +| time/ | | +| fps | 310 | +| iterations | 2387 | +| time_elapsed | 7870 | +| total_timesteps | 2444288 | +| train/ | | +| approx_kl | 2.010057 | +| clip_fraction | 0.503 | +| clip_range | 0.2 | +| entropy_loss | -0.396 | +| explained_variance | -0.648 | +| learning_rate | 0.0001 | +| loss | -0.0809 | +| n_updates | 84390 | +| policy_gradient_loss | -0.0574 | +| value_loss | 0.000385 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | -0.0533 | +| time/ | | +| fps | 310 | +| iterations | 2388 | +| time_elapsed | 7873 | +| total_timesteps | 2445312 | +| train/ | | +| approx_kl | 2.0046725 | +| clip_fraction | 0.461 | +| clip_range | 0.2 | +| entropy_loss | -0.357 | +| explained_variance | -3.23 | +| learning_rate | 0.0001 | +| loss | -0.0545 | +| n_updates | 84400 | +| policy_gradient_loss | -0.0633 | +| value_loss | 0.000364 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.58e+03 | +| ep_rew_mean | -0.0523 | +| time/ | | +| fps | 310 | +| iterations | 2389 | +| time_elapsed | 7876 | +| total_timesteps | 2446336 | +| train/ | | +| approx_kl | 1.488265 | +| clip_fraction | 0.472 | +| clip_range | 0.2 | +| entropy_loss | -0.441 | +| explained_variance | -0.647 | +| learning_rate | 0.0001 | +| loss | -0.0717 | +| n_updates | 84410 | +| policy_gradient_loss | -0.0587 | +| value_loss | 0.000407 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.57e+03 | +| ep_rew_mean | -0.0516 | +| time/ | | +| fps | 310 | +| iterations | 2390 | +| time_elapsed | 7879 | +| total_timesteps | 2447360 | +| train/ | | +| approx_kl | 2.6018872 | +| clip_fraction | 0.465 | +| clip_range | 0.2 | +| entropy_loss | -0.389 | +| explained_variance | -3.18 | +| learning_rate | 0.0001 | +| loss | -0.0832 | +| n_updates | 84420 | +| policy_gradient_loss | -0.0661 | +| value_loss | 0.000438 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.57e+03 | +| ep_rew_mean | -0.0515 | +| time/ | | +| fps | 310 | +| iterations | 2391 | +| time_elapsed | 7882 | +| total_timesteps | 2448384 | +| train/ | | +| approx_kl | 1.7541429 | +| clip_fraction | 0.44 | +| clip_range | 0.2 | +| entropy_loss | -0.356 | +| explained_variance | -3.1 | +| learning_rate | 0.0001 | +| loss | -0.0821 | +| n_updates | 84430 | +| policy_gradient_loss | -0.0581 | +| value_loss | 0.00057 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.57e+03 | +| ep_rew_mean | -0.0515 | +| time/ | | +| fps | 310 | +| iterations | 2392 | +| time_elapsed | 7885 | +| total_timesteps | 2449408 | +| train/ | | +| approx_kl | 1.8121136 | +| clip_fraction | 0.444 | +| clip_range | 0.2 | +| entropy_loss | -0.346 | +| explained_variance | -1.98 | +| learning_rate | 0.0001 | +| loss | -0.0594 | +| n_updates | 84440 | +| policy_gradient_loss | -0.0597 | +| value_loss | 0.00055 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.57e+03 | +| ep_rew_mean | -0.0515 | +| time/ | | +| fps | 310 | +| iterations | 2393 | +| time_elapsed | 7888 | +| total_timesteps | 2450432 | +| train/ | | +| approx_kl | 1.8915395 | +| clip_fraction | 0.47 | +| clip_range | 0.2 | +| entropy_loss | -0.395 | +| explained_variance | -2.1 | +| learning_rate | 0.0001 | +| loss | -0.0683 | +| n_updates | 84450 | +| policy_gradient_loss | -0.0656 | +| value_loss | 0.00043 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.57e+03 | +| ep_rew_mean | -0.0448 | +| time/ | | +| fps | 310 | +| iterations | 2394 | +| time_elapsed | 7892 | +| total_timesteps | 2451456 | +| train/ | | +| approx_kl | 1.8661225 | +| clip_fraction | 0.449 | +| clip_range | 0.2 | +| entropy_loss | -0.349 | +| explained_variance | -1.56 | +| learning_rate | 0.0001 | +| loss | -0.0804 | +| n_updates | 84460 | +| policy_gradient_loss | -0.058 | +| value_loss | 0.000437 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.57e+03 | +| ep_rew_mean | -0.0461 | +| time/ | | +| fps | 310 | +| iterations | 2395 | +| time_elapsed | 7895 | +| total_timesteps | 2452480 | +| train/ | | +| approx_kl | 1.4847033 | +| clip_fraction | 0.431 | +| clip_range | 0.2 | +| entropy_loss | -0.381 | +| explained_variance | -2.11 | +| learning_rate | 0.0001 | +| loss | -0.0638 | +| n_updates | 84470 | +| policy_gradient_loss | -0.0581 | +| value_loss | 0.000418 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.57e+03 | +| ep_rew_mean | -0.0461 | +| time/ | | +| fps | 310 | +| iterations | 2396 | +| time_elapsed | 7898 | +| total_timesteps | 2453504 | +| train/ | | +| approx_kl | 1.3527733 | +| clip_fraction | 0.425 | +| clip_range | 0.2 | +| entropy_loss | -0.373 | +| explained_variance | -2.13 | +| learning_rate | 0.0001 | +| loss | -0.0639 | +| n_updates | 84480 | +| policy_gradient_loss | -0.0519 | +| value_loss | 0.000448 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.56e+03 | +| ep_rew_mean | -0.045 | +| time/ | | +| fps | 310 | +| iterations | 2397 | +| time_elapsed | 7901 | +| total_timesteps | 2454528 | +| train/ | | +| approx_kl | 5.3782935 | +| clip_fraction | 0.479 | +| clip_range | 0.2 | +| entropy_loss | -0.331 | +| explained_variance | -1.06 | +| learning_rate | 0.0001 | +| loss | -0.0864 | +| n_updates | 84490 | +| policy_gradient_loss | -0.0514 | +| value_loss | 0.000837 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.56e+03 | +| ep_rew_mean | -0.0377 | +| time/ | | +| fps | 310 | +| iterations | 2398 | +| time_elapsed | 7905 | +| total_timesteps | 2455552 | +| train/ | | +| approx_kl | 1.7913553 | +| clip_fraction | 0.439 | +| clip_range | 0.2 | +| entropy_loss | -0.33 | +| explained_variance | -1.35 | +| learning_rate | 0.0001 | +| loss | -0.0862 | +| n_updates | 84500 | +| policy_gradient_loss | -0.055 | +| value_loss | 0.000711 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.56e+03 | +| ep_rew_mean | -0.0377 | +| time/ | | +| fps | 310 | +| iterations | 2399 | +| time_elapsed | 7908 | +| total_timesteps | 2456576 | +| train/ | | +| approx_kl | 1.7417177 | +| clip_fraction | 0.476 | +| clip_range | 0.2 | +| entropy_loss | -0.352 | +| explained_variance | -0.56 | +| learning_rate | 0.0001 | +| loss | -0.0702 | +| n_updates | 84510 | +| policy_gradient_loss | -0.0616 | +| value_loss | 0.00103 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.56e+03 | +| ep_rew_mean | -0.031 | +| time/ | | +| fps | 310 | +| iterations | 2400 | +| time_elapsed | 7912 | +| total_timesteps | 2457600 | +| train/ | | +| approx_kl | 1.9043423 | +| clip_fraction | 0.453 | +| clip_range | 0.2 | +| entropy_loss | -0.352 | +| explained_variance | -1.89 | +| learning_rate | 0.0001 | +| loss | -0.0641 | +| n_updates | 84520 | +| policy_gradient_loss | -0.0643 | +| value_loss | 0.000852 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.56e+03 | +| ep_rew_mean | -0.031 | +| time/ | | +| fps | 310 | +| iterations | 2401 | +| time_elapsed | 7915 | +| total_timesteps | 2458624 | +| train/ | | +| approx_kl | 1.8260945 | +| clip_fraction | 0.465 | +| clip_range | 0.2 | +| entropy_loss | -0.419 | +| explained_variance | -1.4 | +| learning_rate | 0.0001 | +| loss | -0.097 | +| n_updates | 84530 | +| policy_gradient_loss | -0.0675 | +| value_loss | 0.00071 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.57e+03 | +| ep_rew_mean | -0.0239 | +| time/ | | +| fps | 310 | +| iterations | 2402 | +| time_elapsed | 7919 | +| total_timesteps | 2459648 | +| train/ | | +| approx_kl | 1.6965286 | +| clip_fraction | 0.437 | +| clip_range | 0.2 | +| entropy_loss | -0.353 | +| explained_variance | -2.73 | +| learning_rate | 0.0001 | +| loss | -0.0791 | +| n_updates | 84540 | +| policy_gradient_loss | -0.0626 | +| value_loss | 0.000456 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.56e+03 | +| ep_rew_mean | -0.0224 | +| time/ | | +| fps | 310 | +| iterations | 2403 | +| time_elapsed | 7922 | +| total_timesteps | 2460672 | +| train/ | | +| approx_kl | 1.8485626 | +| clip_fraction | 0.413 | +| clip_range | 0.2 | +| entropy_loss | -0.295 | +| explained_variance | -5 | +| learning_rate | 0.0001 | +| loss | -0.0895 | +| n_updates | 84550 | +| policy_gradient_loss | -0.0549 | +| value_loss | 0.000459 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.56e+03 | +| ep_rew_mean | -0.0238 | +| time/ | | +| fps | 310 | +| iterations | 2404 | +| time_elapsed | 7926 | +| total_timesteps | 2461696 | +| train/ | | +| approx_kl | 2.5244303 | +| clip_fraction | 0.421 | +| clip_range | 0.2 | +| entropy_loss | -0.314 | +| explained_variance | -1.83 | +| learning_rate | 0.0001 | +| loss | -0.105 | +| n_updates | 84560 | +| policy_gradient_loss | -0.0608 | +| value_loss | 0.00039 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.55e+03 | +| ep_rew_mean | -0.0182 | +| time/ | | +| fps | 310 | +| iterations | 2405 | +| time_elapsed | 7929 | +| total_timesteps | 2462720 | +| train/ | | +| approx_kl | 2.286921 | +| clip_fraction | 0.434 | +| clip_range | 0.2 | +| entropy_loss | -0.299 | +| explained_variance | -1.17 | +| learning_rate | 0.0001 | +| loss | -0.0676 | +| n_updates | 84570 | +| policy_gradient_loss | -0.0618 | +| value_loss | 0.000689 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.55e+03 | +| ep_rew_mean | -0.0182 | +| time/ | | +| fps | 310 | +| iterations | 2406 | +| time_elapsed | 7932 | +| total_timesteps | 2463744 | +| train/ | | +| approx_kl | 1.9441268 | +| clip_fraction | 0.468 | +| clip_range | 0.2 | +| entropy_loss | -0.346 | +| explained_variance | -1.31 | +| learning_rate | 0.0001 | +| loss | -0.0944 | +| n_updates | 84580 | +| policy_gradient_loss | -0.0603 | +| value_loss | 0.000725 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.55e+03 | +| ep_rew_mean | -0.0196 | +| time/ | | +| fps | 310 | +| iterations | 2407 | +| time_elapsed | 7935 | +| total_timesteps | 2464768 | +| train/ | | +| approx_kl | 1.7129948 | +| clip_fraction | 0.473 | +| clip_range | 0.2 | +| entropy_loss | -0.387 | +| explained_variance | -1.71 | +| learning_rate | 0.0001 | +| loss | -0.105 | +| n_updates | 84590 | +| policy_gradient_loss | -0.0598 | +| value_loss | 0.000498 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.55e+03 | +| ep_rew_mean | -0.0196 | +| time/ | | +| fps | 310 | +| iterations | 2408 | +| time_elapsed | 7939 | +| total_timesteps | 2465792 | +| train/ | | +| approx_kl | 1.6737165 | +| clip_fraction | 0.479 | +| clip_range | 0.2 | +| entropy_loss | -0.341 | +| explained_variance | -3.72 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 84600 | +| policy_gradient_loss | -0.0662 | +| value_loss | 0.000435 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.55e+03 | +| ep_rew_mean | -0.0196 | +| time/ | | +| fps | 310 | +| iterations | 2409 | +| time_elapsed | 7942 | +| total_timesteps | 2466816 | +| train/ | | +| approx_kl | 1.9259305 | +| clip_fraction | 0.45 | +| clip_range | 0.2 | +| entropy_loss | -0.351 | +| explained_variance | -2.11 | +| learning_rate | 0.0001 | +| loss | -0.0714 | +| n_updates | 84610 | +| policy_gradient_loss | -0.0634 | +| value_loss | 0.00065 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.56e+03 | +| ep_rew_mean | -0.0165 | +| time/ | | +| fps | 310 | +| iterations | 2410 | +| time_elapsed | 7945 | +| total_timesteps | 2467840 | +| train/ | | +| approx_kl | 4.15518 | +| clip_fraction | 0.466 | +| clip_range | 0.2 | +| entropy_loss | -0.332 | +| explained_variance | -0.604 | +| learning_rate | 0.0001 | +| loss | -0.079 | +| n_updates | 84620 | +| policy_gradient_loss | -0.0641 | +| value_loss | 0.000604 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.56e+03 | +| ep_rew_mean | -0.0165 | +| time/ | | +| fps | 310 | +| iterations | 2411 | +| time_elapsed | 7948 | +| total_timesteps | 2468864 | +| train/ | | +| approx_kl | 1.8360004 | +| clip_fraction | 0.512 | +| clip_range | 0.2 | +| entropy_loss | -0.474 | +| explained_variance | -2.38 | +| learning_rate | 0.0001 | +| loss | -0.0877 | +| n_updates | 84630 | +| policy_gradient_loss | -0.0591 | +| value_loss | 0.000283 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.57e+03 | +| ep_rew_mean | -0.0138 | +| time/ | | +| fps | 310 | +| iterations | 2412 | +| time_elapsed | 7951 | +| total_timesteps | 2469888 | +| train/ | | +| approx_kl | 1.8093092 | +| clip_fraction | 0.428 | +| clip_range | 0.2 | +| entropy_loss | -0.339 | +| explained_variance | -2.61 | +| learning_rate | 0.0001 | +| loss | -0.0804 | +| n_updates | 84640 | +| policy_gradient_loss | -0.0624 | +| value_loss | 0.000393 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.56e+03 | +| ep_rew_mean | -0.0161 | +| time/ | | +| fps | 310 | +| iterations | 2413 | +| time_elapsed | 7955 | +| total_timesteps | 2470912 | +| train/ | | +| approx_kl | 1.875243 | +| clip_fraction | 0.46 | +| clip_range | 0.2 | +| entropy_loss | -0.338 | +| explained_variance | -2.87 | +| learning_rate | 0.0001 | +| loss | -0.072 | +| n_updates | 84650 | +| policy_gradient_loss | -0.0554 | +| value_loss | 0.000398 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.56e+03 | +| ep_rew_mean | -0.00693 | +| time/ | | +| fps | 310 | +| iterations | 2414 | +| time_elapsed | 7958 | +| total_timesteps | 2471936 | +| train/ | | +| approx_kl | 1.781512 | +| clip_fraction | 0.457 | +| clip_range | 0.2 | +| entropy_loss | -0.381 | +| explained_variance | -1.18 | +| learning_rate | 0.0001 | +| loss | -0.0903 | +| n_updates | 84660 | +| policy_gradient_loss | -0.0581 | +| value_loss | 0.000351 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.56e+03 | +| ep_rew_mean | -0.00693 | +| time/ | | +| fps | 310 | +| iterations | 2415 | +| time_elapsed | 7961 | +| total_timesteps | 2472960 | +| train/ | | +| approx_kl | 1.7576406 | +| clip_fraction | 0.448 | +| clip_range | 0.2 | +| entropy_loss | -0.375 | +| explained_variance | -0.512 | +| learning_rate | 0.0001 | +| loss | -0.0879 | +| n_updates | 84670 | +| policy_gradient_loss | -0.058 | +| value_loss | 0.000561 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.56e+03 | +| ep_rew_mean | -0.00295 | +| time/ | | +| fps | 310 | +| iterations | 2416 | +| time_elapsed | 7965 | +| total_timesteps | 2473984 | +| train/ | | +| approx_kl | 1.4555383 | +| clip_fraction | 0.452 | +| clip_range | 0.2 | +| entropy_loss | -0.384 | +| explained_variance | -1.34 | +| learning_rate | 0.0001 | +| loss | -0.0675 | +| n_updates | 84680 | +| policy_gradient_loss | -0.0607 | +| value_loss | 0.000417 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.55e+03 | +| ep_rew_mean | -0.00663 | +| time/ | | +| fps | 310 | +| iterations | 2417 | +| time_elapsed | 7968 | +| total_timesteps | 2475008 | +| train/ | | +| approx_kl | 2.4333441 | +| clip_fraction | 0.469 | +| clip_range | 0.2 | +| entropy_loss | -0.358 | +| explained_variance | -2.04 | +| learning_rate | 0.0001 | +| loss | -0.0826 | +| n_updates | 84690 | +| policy_gradient_loss | -0.0569 | +| value_loss | 0.000595 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.55e+03 | +| ep_rew_mean | -0.00663 | +| time/ | | +| fps | 310 | +| iterations | 2418 | +| time_elapsed | 7971 | +| total_timesteps | 2476032 | +| train/ | | +| approx_kl | 1.5906199 | +| clip_fraction | 0.426 | +| clip_range | 0.2 | +| entropy_loss | -0.365 | +| explained_variance | -1.25 | +| learning_rate | 0.0001 | +| loss | -0.0816 | +| n_updates | 84700 | +| policy_gradient_loss | -0.0502 | +| value_loss | 0.000606 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.56e+03 | +| ep_rew_mean | -0.0025 | +| time/ | | +| fps | 310 | +| iterations | 2419 | +| time_elapsed | 7975 | +| total_timesteps | 2477056 | +| train/ | | +| approx_kl | 1.7302492 | +| clip_fraction | 0.461 | +| clip_range | 0.2 | +| entropy_loss | -0.363 | +| explained_variance | -1.78 | +| learning_rate | 0.0001 | +| loss | -0.0582 | +| n_updates | 84710 | +| policy_gradient_loss | -0.059 | +| value_loss | 0.000569 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.55e+03 | +| ep_rew_mean | -0.000291 | +| time/ | | +| fps | 310 | +| iterations | 2420 | +| time_elapsed | 7978 | +| total_timesteps | 2478080 | +| train/ | | +| approx_kl | 2.156479 | +| clip_fraction | 0.432 | +| clip_range | 0.2 | +| entropy_loss | -0.36 | +| explained_variance | -3.16 | +| learning_rate | 0.0001 | +| loss | -0.0539 | +| n_updates | 84720 | +| policy_gradient_loss | -0.0647 | +| value_loss | 0.000468 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.54e+03 | +| ep_rew_mean | -0.000853 | +| time/ | | +| fps | 310 | +| iterations | 2421 | +| time_elapsed | 7981 | +| total_timesteps | 2479104 | +| train/ | | +| approx_kl | 2.01752 | +| clip_fraction | 0.428 | +| clip_range | 0.2 | +| entropy_loss | -0.33 | +| explained_variance | -2.07 | +| learning_rate | 0.0001 | +| loss | -0.0926 | +| n_updates | 84730 | +| policy_gradient_loss | -0.0581 | +| value_loss | 0.00045 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.54e+03 | +| ep_rew_mean | -0.000853 | +| time/ | | +| fps | 310 | +| iterations | 2422 | +| time_elapsed | 7985 | +| total_timesteps | 2480128 | +| train/ | | +| approx_kl | 2.2422142 | +| clip_fraction | 0.416 | +| clip_range | 0.2 | +| entropy_loss | -0.325 | +| explained_variance | -0.655 | +| learning_rate | 0.0001 | +| loss | -0.0793 | +| n_updates | 84740 | +| policy_gradient_loss | -0.054 | +| value_loss | 0.000485 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.54e+03 | +| ep_rew_mean | -0.00389 | +| time/ | | +| fps | 310 | +| iterations | 2423 | +| time_elapsed | 7988 | +| total_timesteps | 2481152 | +| train/ | | +| approx_kl | 1.8543174 | +| clip_fraction | 0.461 | +| clip_range | 0.2 | +| entropy_loss | -0.356 | +| explained_variance | -1.94 | +| learning_rate | 0.0001 | +| loss | -0.105 | +| n_updates | 84750 | +| policy_gradient_loss | -0.0674 | +| value_loss | 0.000821 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.54e+03 | +| ep_rew_mean | -0.00389 | +| time/ | | +| fps | 310 | +| iterations | 2424 | +| time_elapsed | 7991 | +| total_timesteps | 2482176 | +| train/ | | +| approx_kl | 1.7361484 | +| clip_fraction | 0.458 | +| clip_range | 0.2 | +| entropy_loss | -0.332 | +| explained_variance | -4.2 | +| learning_rate | 0.0001 | +| loss | -0.0868 | +| n_updates | 84760 | +| policy_gradient_loss | -0.0567 | +| value_loss | 0.00087 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.53e+03 | +| ep_rew_mean | -0.00305 | +| time/ | | +| fps | 310 | +| iterations | 2425 | +| time_elapsed | 7995 | +| total_timesteps | 2483200 | +| train/ | | +| approx_kl | 2.2165048 | +| clip_fraction | 0.47 | +| clip_range | 0.2 | +| entropy_loss | -0.362 | +| explained_variance | -1.32 | +| learning_rate | 0.0001 | +| loss | -0.0787 | +| n_updates | 84770 | +| policy_gradient_loss | -0.068 | +| value_loss | 0.000601 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.53e+03 | +| ep_rew_mean | -0.00305 | +| time/ | | +| fps | 310 | +| iterations | 2426 | +| time_elapsed | 7998 | +| total_timesteps | 2484224 | +| train/ | | +| approx_kl | 2.2148132 | +| clip_fraction | 0.456 | +| clip_range | 0.2 | +| entropy_loss | -0.359 | +| explained_variance | -1.45 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 84780 | +| policy_gradient_loss | -0.0668 | +| value_loss | 0.000798 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.54e+03 | +| ep_rew_mean | 0.000788 | +| time/ | | +| fps | 310 | +| iterations | 2427 | +| time_elapsed | 8001 | +| total_timesteps | 2485248 | +| train/ | | +| approx_kl | 2.3560944 | +| clip_fraction | 0.468 | +| clip_range | 0.2 | +| entropy_loss | -0.379 | +| explained_variance | -5.84 | +| learning_rate | 0.0001 | +| loss | -0.087 | +| n_updates | 84790 | +| policy_gradient_loss | -0.061 | +| value_loss | 0.000536 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.54e+03 | +| ep_rew_mean | 0.000788 | +| time/ | | +| fps | 310 | +| iterations | 2428 | +| time_elapsed | 8004 | +| total_timesteps | 2486272 | +| train/ | | +| approx_kl | 2.070775 | +| clip_fraction | 0.47 | +| clip_range | 0.2 | +| entropy_loss | -0.437 | +| explained_variance | -1.2 | +| learning_rate | 0.0001 | +| loss | -0.0445 | +| n_updates | 84800 | +| policy_gradient_loss | -0.0632 | +| value_loss | 0.000702 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.54e+03 | +| ep_rew_mean | 0.00158 | +| time/ | | +| fps | 310 | +| iterations | 2429 | +| time_elapsed | 8007 | +| total_timesteps | 2487296 | +| train/ | | +| approx_kl | 1.9219277 | +| clip_fraction | 0.46 | +| clip_range | 0.2 | +| entropy_loss | -0.355 | +| explained_variance | -2.19 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 84810 | +| policy_gradient_loss | -0.0666 | +| value_loss | 0.000373 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.54e+03 | +| ep_rew_mean | 0.00158 | +| time/ | | +| fps | 310 | +| iterations | 2430 | +| time_elapsed | 8010 | +| total_timesteps | 2488320 | +| train/ | | +| approx_kl | 2.8504167 | +| clip_fraction | 0.469 | +| clip_range | 0.2 | +| entropy_loss | -0.383 | +| explained_variance | -1.2 | +| learning_rate | 0.0001 | +| loss | -0.0425 | +| n_updates | 84820 | +| policy_gradient_loss | -0.052 | +| value_loss | 0.000486 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.53e+03 | +| ep_rew_mean | 0.00416 | +| time/ | | +| fps | 310 | +| iterations | 2431 | +| time_elapsed | 8013 | +| total_timesteps | 2489344 | +| train/ | | +| approx_kl | 1.6684088 | +| clip_fraction | 0.452 | +| clip_range | 0.2 | +| entropy_loss | -0.367 | +| explained_variance | -2.78 | +| learning_rate | 0.0001 | +| loss | -0.0921 | +| n_updates | 84830 | +| policy_gradient_loss | -0.0661 | +| value_loss | 0.000552 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.53e+03 | +| ep_rew_mean | 0.00422 | +| time/ | | +| fps | 310 | +| iterations | 2432 | +| time_elapsed | 8017 | +| total_timesteps | 2490368 | +| train/ | | +| approx_kl | 1.7103922 | +| clip_fraction | 0.439 | +| clip_range | 0.2 | +| entropy_loss | -0.332 | +| explained_variance | -2.47 | +| learning_rate | 0.0001 | +| loss | -0.0567 | +| n_updates | 84840 | +| policy_gradient_loss | -0.0556 | +| value_loss | 0.000539 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.53e+03 | +| ep_rew_mean | 0.00422 | +| time/ | | +| fps | 310 | +| iterations | 2433 | +| time_elapsed | 8020 | +| total_timesteps | 2491392 | +| train/ | | +| approx_kl | 2.529758 | +| clip_fraction | 0.453 | +| clip_range | 0.2 | +| entropy_loss | -0.342 | +| explained_variance | -4.26 | +| learning_rate | 0.0001 | +| loss | -0.0594 | +| n_updates | 84850 | +| policy_gradient_loss | -0.0642 | +| value_loss | 0.000561 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.54e+03 | +| ep_rew_mean | 0.00653 | +| time/ | | +| fps | 310 | +| iterations | 2434 | +| time_elapsed | 8023 | +| total_timesteps | 2492416 | +| train/ | | +| approx_kl | 2.152207 | +| clip_fraction | 0.478 | +| clip_range | 0.2 | +| entropy_loss | -0.407 | +| explained_variance | -1.89 | +| learning_rate | 0.0001 | +| loss | -0.0757 | +| n_updates | 84860 | +| policy_gradient_loss | -0.0642 | +| value_loss | 0.000441 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.53e+03 | +| ep_rew_mean | 0.00406 | +| time/ | | +| fps | 310 | +| iterations | 2435 | +| time_elapsed | 8027 | +| total_timesteps | 2493440 | +| train/ | | +| approx_kl | 2.0001369 | +| clip_fraction | 0.465 | +| clip_range | 0.2 | +| entropy_loss | -0.38 | +| explained_variance | -2.19 | +| learning_rate | 0.0001 | +| loss | -0.0624 | +| n_updates | 84870 | +| policy_gradient_loss | -0.0667 | +| value_loss | 0.000491 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.52e+03 | +| ep_rew_mean | 0.00294 | +| time/ | | +| fps | 310 | +| iterations | 2436 | +| time_elapsed | 8030 | +| total_timesteps | 2494464 | +| train/ | | +| approx_kl | 1.4654778 | +| clip_fraction | 0.435 | +| clip_range | 0.2 | +| entropy_loss | -0.379 | +| explained_variance | -1.77 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 84880 | +| policy_gradient_loss | -0.0625 | +| value_loss | 0.000381 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.52e+03 | +| ep_rew_mean | 0.00294 | +| time/ | | +| fps | 310 | +| iterations | 2437 | +| time_elapsed | 8034 | +| total_timesteps | 2495488 | +| train/ | | +| approx_kl | 1.6297724 | +| clip_fraction | 0.407 | +| clip_range | 0.2 | +| entropy_loss | -0.342 | +| explained_variance | -0.976 | +| learning_rate | 0.0001 | +| loss | -0.0869 | +| n_updates | 84890 | +| policy_gradient_loss | -0.0605 | +| value_loss | 0.000601 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.53e+03 | +| ep_rew_mean | 0.00976 | +| time/ | | +| fps | 310 | +| iterations | 2438 | +| time_elapsed | 8037 | +| total_timesteps | 2496512 | +| train/ | | +| approx_kl | 1.9197255 | +| clip_fraction | 0.447 | +| clip_range | 0.2 | +| entropy_loss | -0.336 | +| explained_variance | -1.55 | +| learning_rate | 0.0001 | +| loss | -0.0703 | +| n_updates | 84900 | +| policy_gradient_loss | -0.0619 | +| value_loss | 0.000452 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.53e+03 | +| ep_rew_mean | 0.00976 | +| time/ | | +| fps | 310 | +| iterations | 2439 | +| time_elapsed | 8041 | +| total_timesteps | 2497536 | +| train/ | | +| approx_kl | 2.0786743 | +| clip_fraction | 0.447 | +| clip_range | 0.2 | +| entropy_loss | -0.363 | +| explained_variance | -2.14 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 84910 | +| policy_gradient_loss | -0.0565 | +| value_loss | 0.000541 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.54e+03 | +| ep_rew_mean | 0.0122 | +| time/ | | +| fps | 310 | +| iterations | 2440 | +| time_elapsed | 8044 | +| total_timesteps | 2498560 | +| train/ | | +| approx_kl | 1.4037812 | +| clip_fraction | 0.469 | +| clip_range | 0.2 | +| entropy_loss | -0.379 | +| explained_variance | -3.94 | +| learning_rate | 0.0001 | +| loss | -0.0802 | +| n_updates | 84920 | +| policy_gradient_loss | -0.0684 | +| value_loss | 0.000294 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.53e+03 | +| ep_rew_mean | 0.00955 | +| time/ | | +| fps | 310 | +| iterations | 2441 | +| time_elapsed | 8048 | +| total_timesteps | 2499584 | +| train/ | | +| approx_kl | 1.7195559 | +| clip_fraction | 0.438 | +| clip_range | 0.2 | +| entropy_loss | -0.325 | +| explained_variance | -1.54 | +| learning_rate | 0.0001 | +| loss | -0.0789 | +| n_updates | 84930 | +| policy_gradient_loss | -0.0626 | +| value_loss | 0.000347 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.52e+03 | +| ep_rew_mean | 0.00634 | +| time/ | | +| fps | 310 | +| iterations | 2442 | +| time_elapsed | 8051 | +| total_timesteps | 2500608 | +| train/ | | +| approx_kl | 2.5868182 | +| clip_fraction | 0.408 | +| clip_range | 0.2 | +| entropy_loss | -0.355 | +| explained_variance | -0.451 | +| learning_rate | 0.0001 | +| loss | -0.059 | +| n_updates | 84940 | +| policy_gradient_loss | -0.0534 | +| value_loss | 0.000432 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.51e+03 | +| ep_rew_mean | 0.00639 | +| time/ | | +| fps | 310 | +| iterations | 2443 | +| time_elapsed | 8054 | +| total_timesteps | 2501632 | +| train/ | | +| approx_kl | 1.7318954 | +| clip_fraction | 0.464 | +| clip_range | 0.2 | +| entropy_loss | -0.342 | +| explained_variance | -0.406 | +| learning_rate | 0.0001 | +| loss | -0.0769 | +| n_updates | 84950 | +| policy_gradient_loss | -0.0614 | +| value_loss | 0.000948 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.51e+03 | +| ep_rew_mean | 0.00639 | +| time/ | | +| fps | 310 | +| iterations | 2444 | +| time_elapsed | 8057 | +| total_timesteps | 2502656 | +| train/ | | +| approx_kl | 1.7243948 | +| clip_fraction | 0.442 | +| clip_range | 0.2 | +| entropy_loss | -0.327 | +| explained_variance | -3.18 | +| learning_rate | 0.0001 | +| loss | -0.0755 | +| n_updates | 84960 | +| policy_gradient_loss | -0.0659 | +| value_loss | 0.000659 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.52e+03 | +| ep_rew_mean | 0.00896 | +| time/ | | +| fps | 310 | +| iterations | 2445 | +| time_elapsed | 8061 | +| total_timesteps | 2503680 | +| train/ | | +| approx_kl | 1.9081967 | +| clip_fraction | 0.46 | +| clip_range | 0.2 | +| entropy_loss | -0.357 | +| explained_variance | -1.37 | +| learning_rate | 0.0001 | +| loss | -0.105 | +| n_updates | 84970 | +| policy_gradient_loss | -0.066 | +| value_loss | 0.000562 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.52e+03 | +| ep_rew_mean | 0.00896 | +| time/ | | +| fps | 310 | +| iterations | 2446 | +| time_elapsed | 8064 | +| total_timesteps | 2504704 | +| train/ | | +| approx_kl | 1.8484272 | +| clip_fraction | 0.468 | +| clip_range | 0.2 | +| entropy_loss | -0.364 | +| explained_variance | -2.58 | +| learning_rate | 0.0001 | +| loss | -0.086 | +| n_updates | 84980 | +| policy_gradient_loss | -0.067 | +| value_loss | 0.000543 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.53e+03 | +| ep_rew_mean | 0.0157 | +| time/ | | +| fps | 310 | +| iterations | 2447 | +| time_elapsed | 8067 | +| total_timesteps | 2505728 | +| train/ | | +| approx_kl | 2.281504 | +| clip_fraction | 0.478 | +| clip_range | 0.2 | +| entropy_loss | -0.432 | +| explained_variance | -0.994 | +| learning_rate | 0.0001 | +| loss | -0.0796 | +| n_updates | 84990 | +| policy_gradient_loss | -0.0701 | +| value_loss | 0.000493 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.53e+03 | +| ep_rew_mean | 0.0156 | +| time/ | | +| fps | 310 | +| iterations | 2448 | +| time_elapsed | 8070 | +| total_timesteps | 2506752 | +| train/ | | +| approx_kl | 1.9726465 | +| clip_fraction | 0.477 | +| clip_range | 0.2 | +| entropy_loss | -0.388 | +| explained_variance | -1.65 | +| learning_rate | 0.0001 | +| loss | -0.0895 | +| n_updates | 85000 | +| policy_gradient_loss | -0.0641 | +| value_loss | 0.000377 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.53e+03 | +| ep_rew_mean | 0.0156 | +| time/ | | +| fps | 310 | +| iterations | 2449 | +| time_elapsed | 8073 | +| total_timesteps | 2507776 | +| train/ | | +| approx_kl | 1.8379326 | +| clip_fraction | 0.44 | +| clip_range | 0.2 | +| entropy_loss | -0.383 | +| explained_variance | -2.11 | +| learning_rate | 0.0001 | +| loss | -0.0392 | +| n_updates | 85010 | +| policy_gradient_loss | -0.0543 | +| value_loss | 0.000647 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.53e+03 | +| ep_rew_mean | 0.0216 | +| time/ | | +| fps | 310 | +| iterations | 2450 | +| time_elapsed | 8076 | +| total_timesteps | 2508800 | +| train/ | | +| approx_kl | 3.5266404 | +| clip_fraction | 0.488 | +| clip_range | 0.2 | +| entropy_loss | -0.405 | +| explained_variance | -3.71 | +| learning_rate | 0.0001 | +| loss | -0.0728 | +| n_updates | 85020 | +| policy_gradient_loss | -0.0691 | +| value_loss | 0.000284 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.53e+03 | +| ep_rew_mean | 0.0216 | +| time/ | | +| fps | 310 | +| iterations | 2451 | +| time_elapsed | 8080 | +| total_timesteps | 2509824 | +| train/ | | +| approx_kl | 1.8805268 | +| clip_fraction | 0.463 | +| clip_range | 0.2 | +| entropy_loss | -0.36 | +| explained_variance | -0.9 | +| learning_rate | 0.0001 | +| loss | -0.0445 | +| n_updates | 85030 | +| policy_gradient_loss | -0.0596 | +| value_loss | 0.000471 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.52e+03 | +| ep_rew_mean | 0.0208 | +| time/ | | +| fps | 310 | +| iterations | 2452 | +| time_elapsed | 8083 | +| total_timesteps | 2510848 | +| train/ | | +| approx_kl | 1.8776902 | +| clip_fraction | 0.431 | +| clip_range | 0.2 | +| entropy_loss | -0.312 | +| explained_variance | -2.03 | +| learning_rate | 0.0001 | +| loss | -0.0786 | +| n_updates | 85040 | +| policy_gradient_loss | -0.0648 | +| value_loss | 0.000469 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.52e+03 | +| ep_rew_mean | 0.022 | +| time/ | | +| fps | 310 | +| iterations | 2453 | +| time_elapsed | 8086 | +| total_timesteps | 2511872 | +| train/ | | +| approx_kl | 1.9754453 | +| clip_fraction | 0.412 | +| clip_range | 0.2 | +| entropy_loss | -0.296 | +| explained_variance | -4.65 | +| learning_rate | 0.0001 | +| loss | -0.106 | +| n_updates | 85050 | +| policy_gradient_loss | -0.0638 | +| value_loss | 0.00044 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.52e+03 | +| ep_rew_mean | 0.0201 | +| time/ | | +| fps | 310 | +| iterations | 2454 | +| time_elapsed | 8090 | +| total_timesteps | 2512896 | +| train/ | | +| approx_kl | 1.7890383 | +| clip_fraction | 0.441 | +| clip_range | 0.2 | +| entropy_loss | -0.362 | +| explained_variance | -2.93 | +| learning_rate | 0.0001 | +| loss | -0.0835 | +| n_updates | 85060 | +| policy_gradient_loss | -0.0677 | +| value_loss | 0.000568 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.52e+03 | +| ep_rew_mean | 0.0212 | +| time/ | | +| fps | 310 | +| iterations | 2455 | +| time_elapsed | 8093 | +| total_timesteps | 2513920 | +| train/ | | +| approx_kl | 2.7212987 | +| clip_fraction | 0.428 | +| clip_range | 0.2 | +| entropy_loss | -0.354 | +| explained_variance | -1.49 | +| learning_rate | 0.0001 | +| loss | -0.087 | +| n_updates | 85070 | +| policy_gradient_loss | -0.0629 | +| value_loss | 0.000586 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.51e+03 | +| ep_rew_mean | 0.0191 | +| time/ | | +| fps | 310 | +| iterations | 2456 | +| time_elapsed | 8096 | +| total_timesteps | 2514944 | +| train/ | | +| approx_kl | 1.8178091 | +| clip_fraction | 0.441 | +| clip_range | 0.2 | +| entropy_loss | -0.339 | +| explained_variance | -2.54 | +| learning_rate | 0.0001 | +| loss | -0.07 | +| n_updates | 85080 | +| policy_gradient_loss | -0.0594 | +| value_loss | 0.000411 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.5e+03 | +| ep_rew_mean | 0.019 | +| time/ | | +| fps | 310 | +| iterations | 2457 | +| time_elapsed | 8100 | +| total_timesteps | 2515968 | +| train/ | | +| approx_kl | 1.4104031 | +| clip_fraction | 0.425 | +| clip_range | 0.2 | +| entropy_loss | -0.332 | +| explained_variance | -2.3 | +| learning_rate | 0.0001 | +| loss | -0.0337 | +| n_updates | 85090 | +| policy_gradient_loss | -0.0541 | +| value_loss | 0.000537 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.51e+03 | +| ep_rew_mean | 0.0237 | +| time/ | | +| fps | 310 | +| iterations | 2458 | +| time_elapsed | 8103 | +| total_timesteps | 2516992 | +| train/ | | +| approx_kl | 1.5295968 | +| clip_fraction | 0.404 | +| clip_range | 0.2 | +| entropy_loss | -0.301 | +| explained_variance | -3.24 | +| learning_rate | 0.0001 | +| loss | -0.0746 | +| n_updates | 85100 | +| policy_gradient_loss | -0.054 | +| value_loss | 0.000509 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.51e+03 | +| ep_rew_mean | 0.0237 | +| time/ | | +| fps | 310 | +| iterations | 2459 | +| time_elapsed | 8106 | +| total_timesteps | 2518016 | +| train/ | | +| approx_kl | 2.484724 | +| clip_fraction | 0.437 | +| clip_range | 0.2 | +| entropy_loss | -0.297 | +| explained_variance | -1.48 | +| learning_rate | 0.0001 | +| loss | -0.0895 | +| n_updates | 85110 | +| policy_gradient_loss | -0.0622 | +| value_loss | 0.00051 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.51e+03 | +| ep_rew_mean | 0.0237 | +| time/ | | +| fps | 310 | +| iterations | 2460 | +| time_elapsed | 8110 | +| total_timesteps | 2519040 | +| train/ | | +| approx_kl | 1.9885793 | +| clip_fraction | 0.473 | +| clip_range | 0.2 | +| entropy_loss | -0.412 | +| explained_variance | -1.67 | +| learning_rate | 0.0001 | +| loss | -0.0798 | +| n_updates | 85120 | +| policy_gradient_loss | -0.0683 | +| value_loss | 0.000351 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.52e+03 | +| ep_rew_mean | 0.0297 | +| time/ | | +| fps | 310 | +| iterations | 2461 | +| time_elapsed | 8113 | +| total_timesteps | 2520064 | +| train/ | | +| approx_kl | 1.8338283 | +| clip_fraction | 0.454 | +| clip_range | 0.2 | +| entropy_loss | -0.37 | +| explained_variance | -0.499 | +| learning_rate | 0.0001 | +| loss | -0.0924 | +| n_updates | 85130 | +| policy_gradient_loss | -0.0544 | +| value_loss | 0.00053 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.51e+03 | +| ep_rew_mean | 0.0334 | +| time/ | | +| fps | 310 | +| iterations | 2462 | +| time_elapsed | 8116 | +| total_timesteps | 2521088 | +| train/ | | +| approx_kl | 2.4259682 | +| clip_fraction | 0.44 | +| clip_range | 0.2 | +| entropy_loss | -0.343 | +| explained_variance | -0.983 | +| learning_rate | 0.0001 | +| loss | -0.0557 | +| n_updates | 85140 | +| policy_gradient_loss | -0.0526 | +| value_loss | 0.000547 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.51e+03 | +| ep_rew_mean | 0.0339 | +| time/ | | +| fps | 310 | +| iterations | 2463 | +| time_elapsed | 8119 | +| total_timesteps | 2522112 | +| train/ | | +| approx_kl | 1.6708076 | +| clip_fraction | 0.44 | +| clip_range | 0.2 | +| entropy_loss | -0.377 | +| explained_variance | -4.15 | +| learning_rate | 0.0001 | +| loss | -0.0749 | +| n_updates | 85150 | +| policy_gradient_loss | -0.0576 | +| value_loss | 0.000526 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.5e+03 | +| ep_rew_mean | 0.0327 | +| time/ | | +| fps | 310 | +| iterations | 2464 | +| time_elapsed | 8122 | +| total_timesteps | 2523136 | +| train/ | | +| approx_kl | 1.5953933 | +| clip_fraction | 0.435 | +| clip_range | 0.2 | +| entropy_loss | -0.375 | +| explained_variance | -0.194 | +| learning_rate | 0.0001 | +| loss | -0.0628 | +| n_updates | 85160 | +| policy_gradient_loss | -0.0555 | +| value_loss | 0.000462 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.5e+03 | +| ep_rew_mean | 0.03 | +| time/ | | +| fps | 310 | +| iterations | 2465 | +| time_elapsed | 8125 | +| total_timesteps | 2524160 | +| train/ | | +| approx_kl | 1.7465489 | +| clip_fraction | 0.447 | +| clip_range | 0.2 | +| entropy_loss | -0.385 | +| explained_variance | -2.5 | +| learning_rate | 0.0001 | +| loss | -0.0828 | +| n_updates | 85170 | +| policy_gradient_loss | -0.059 | +| value_loss | 0.000365 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.5e+03 | +| ep_rew_mean | 0.03 | +| time/ | | +| fps | 310 | +| iterations | 2466 | +| time_elapsed | 8128 | +| total_timesteps | 2525184 | +| train/ | | +| approx_kl | 1.6619774 | +| clip_fraction | 0.417 | +| clip_range | 0.2 | +| entropy_loss | -0.339 | +| explained_variance | -0.753 | +| learning_rate | 0.0001 | +| loss | -0.0524 | +| n_updates | 85180 | +| policy_gradient_loss | -0.0553 | +| value_loss | 0.000416 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.5e+03 | +| ep_rew_mean | 0.028 | +| time/ | | +| fps | 310 | +| iterations | 2467 | +| time_elapsed | 8132 | +| total_timesteps | 2526208 | +| train/ | | +| approx_kl | 2.2206483 | +| clip_fraction | 0.452 | +| clip_range | 0.2 | +| entropy_loss | -0.361 | +| explained_variance | -5.24 | +| learning_rate | 0.0001 | +| loss | -0.0918 | +| n_updates | 85190 | +| policy_gradient_loss | -0.0635 | +| value_loss | 0.000314 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.5e+03 | +| ep_rew_mean | 0.0301 | +| time/ | | +| fps | 310 | +| iterations | 2468 | +| time_elapsed | 8135 | +| total_timesteps | 2527232 | +| train/ | | +| approx_kl | 1.5479357 | +| clip_fraction | 0.442 | +| clip_range | 0.2 | +| entropy_loss | -0.34 | +| explained_variance | -1.26 | +| learning_rate | 0.0001 | +| loss | -0.0622 | +| n_updates | 85200 | +| policy_gradient_loss | -0.0631 | +| value_loss | 0.00036 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.49e+03 | +| ep_rew_mean | 0.0378 | +| time/ | | +| fps | 310 | +| iterations | 2469 | +| time_elapsed | 8138 | +| total_timesteps | 2528256 | +| train/ | | +| approx_kl | 1.4834146 | +| clip_fraction | 0.395 | +| clip_range | 0.2 | +| entropy_loss | -0.301 | +| explained_variance | -1.41 | +| learning_rate | 0.0001 | +| loss | -0.0615 | +| n_updates | 85210 | +| policy_gradient_loss | -0.0519 | +| value_loss | 0.00065 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.49e+03 | +| ep_rew_mean | 0.0378 | +| time/ | | +| fps | 310 | +| iterations | 2470 | +| time_elapsed | 8141 | +| total_timesteps | 2529280 | +| train/ | | +| approx_kl | 1.7373403 | +| clip_fraction | 0.449 | +| clip_range | 0.2 | +| entropy_loss | -0.381 | +| explained_variance | -0.429 | +| learning_rate | 0.0001 | +| loss | -0.0993 | +| n_updates | 85220 | +| policy_gradient_loss | -0.0645 | +| value_loss | 0.000898 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.5e+03 | +| ep_rew_mean | 0.043 | +| time/ | | +| fps | 310 | +| iterations | 2471 | +| time_elapsed | 8145 | +| total_timesteps | 2530304 | +| train/ | | +| approx_kl | 2.2155838 | +| clip_fraction | 0.467 | +| clip_range | 0.2 | +| entropy_loss | -0.377 | +| explained_variance | -1.85 | +| learning_rate | 0.0001 | +| loss | -0.0514 | +| n_updates | 85230 | +| policy_gradient_loss | -0.0627 | +| value_loss | 0.00093 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.5e+03 | +| ep_rew_mean | 0.043 | +| time/ | | +| fps | 310 | +| iterations | 2472 | +| time_elapsed | 8148 | +| total_timesteps | 2531328 | +| train/ | | +| approx_kl | 2.1511965 | +| clip_fraction | 0.427 | +| clip_range | 0.2 | +| entropy_loss | -0.327 | +| explained_variance | -4.85 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 85240 | +| policy_gradient_loss | -0.0609 | +| value_loss | 0.00039 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.51e+03 | +| ep_rew_mean | 0.0461 | +| time/ | | +| fps | 310 | +| iterations | 2473 | +| time_elapsed | 8152 | +| total_timesteps | 2532352 | +| train/ | | +| approx_kl | 1.8095526 | +| clip_fraction | 0.496 | +| clip_range | 0.2 | +| entropy_loss | -0.449 | +| explained_variance | -1.07 | +| learning_rate | 0.0001 | +| loss | -0.0612 | +| n_updates | 85250 | +| policy_gradient_loss | -0.0599 | +| value_loss | 0.000378 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.51e+03 | +| ep_rew_mean | 0.0461 | +| time/ | | +| fps | 310 | +| iterations | 2474 | +| time_elapsed | 8155 | +| total_timesteps | 2533376 | +| train/ | | +| approx_kl | 2.0129132 | +| clip_fraction | 0.44 | +| clip_range | 0.2 | +| entropy_loss | -0.352 | +| explained_variance | -1.77 | +| learning_rate | 0.0001 | +| loss | -0.0694 | +| n_updates | 85260 | +| policy_gradient_loss | -0.059 | +| value_loss | 0.00061 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.51e+03 | +| ep_rew_mean | 0.0503 | +| time/ | | +| fps | 310 | +| iterations | 2475 | +| time_elapsed | 8158 | +| total_timesteps | 2534400 | +| train/ | | +| approx_kl | 2.097122 | +| clip_fraction | 0.467 | +| clip_range | 0.2 | +| entropy_loss | -0.353 | +| explained_variance | -2.46 | +| learning_rate | 0.0001 | +| loss | -0.0791 | +| n_updates | 85270 | +| policy_gradient_loss | -0.0608 | +| value_loss | 0.00054 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.51e+03 | +| ep_rew_mean | 0.054 | +| time/ | | +| fps | 310 | +| iterations | 2476 | +| time_elapsed | 8162 | +| total_timesteps | 2535424 | +| train/ | | +| approx_kl | 2.0625377 | +| clip_fraction | 0.439 | +| clip_range | 0.2 | +| entropy_loss | -0.317 | +| explained_variance | -1.63 | +| learning_rate | 0.0001 | +| loss | -0.0748 | +| n_updates | 85280 | +| policy_gradient_loss | -0.0588 | +| value_loss | 0.000427 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.51e+03 | +| ep_rew_mean | 0.054 | +| time/ | | +| fps | 310 | +| iterations | 2477 | +| time_elapsed | 8165 | +| total_timesteps | 2536448 | +| train/ | | +| approx_kl | 2.4576292 | +| clip_fraction | 0.469 | +| clip_range | 0.2 | +| entropy_loss | -0.348 | +| explained_variance | -1.94 | +| learning_rate | 0.0001 | +| loss | -0.0581 | +| n_updates | 85290 | +| policy_gradient_loss | -0.0578 | +| value_loss | 0.000639 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.51e+03 | +| ep_rew_mean | 0.0554 | +| time/ | | +| fps | 310 | +| iterations | 2478 | +| time_elapsed | 8169 | +| total_timesteps | 2537472 | +| train/ | | +| approx_kl | 3.0710826 | +| clip_fraction | 0.453 | +| clip_range | 0.2 | +| entropy_loss | -0.351 | +| explained_variance | -4.73 | +| learning_rate | 0.0001 | +| loss | -0.0574 | +| n_updates | 85300 | +| policy_gradient_loss | -0.0642 | +| value_loss | 0.000406 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.51e+03 | +| ep_rew_mean | 0.0554 | +| time/ | | +| fps | 310 | +| iterations | 2479 | +| time_elapsed | 8172 | +| total_timesteps | 2538496 | +| train/ | | +| approx_kl | 1.7858632 | +| clip_fraction | 0.426 | +| clip_range | 0.2 | +| entropy_loss | -0.331 | +| explained_variance | -1.33 | +| learning_rate | 0.0001 | +| loss | -0.0869 | +| n_updates | 85310 | +| policy_gradient_loss | -0.0536 | +| value_loss | 0.000389 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.52e+03 | +| ep_rew_mean | 0.0611 | +| time/ | | +| fps | 310 | +| iterations | 2480 | +| time_elapsed | 8175 | +| total_timesteps | 2539520 | +| train/ | | +| approx_kl | 1.7134101 | +| clip_fraction | 0.446 | +| clip_range | 0.2 | +| entropy_loss | -0.346 | +| explained_variance | -2.23 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 85320 | +| policy_gradient_loss | -0.0631 | +| value_loss | 0.000546 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.52e+03 | +| ep_rew_mean | 0.0611 | +| time/ | | +| fps | 310 | +| iterations | 2481 | +| time_elapsed | 8179 | +| total_timesteps | 2540544 | +| train/ | | +| approx_kl | 1.6629839 | +| clip_fraction | 0.455 | +| clip_range | 0.2 | +| entropy_loss | -0.375 | +| explained_variance | -7.6 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 85330 | +| policy_gradient_loss | -0.0614 | +| value_loss | 0.000466 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.52e+03 | +| ep_rew_mean | 0.06 | +| time/ | | +| fps | 310 | +| iterations | 2482 | +| time_elapsed | 8182 | +| total_timesteps | 2541568 | +| train/ | | +| approx_kl | 1.6860261 | +| clip_fraction | 0.439 | +| clip_range | 0.2 | +| entropy_loss | -0.366 | +| explained_variance | -4.91 | +| learning_rate | 0.0001 | +| loss | -0.0926 | +| n_updates | 85340 | +| policy_gradient_loss | -0.0638 | +| value_loss | 0.000469 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.51e+03 | +| ep_rew_mean | 0.0606 | +| time/ | | +| fps | 310 | +| iterations | 2483 | +| time_elapsed | 8185 | +| total_timesteps | 2542592 | +| train/ | | +| approx_kl | 1.7140214 | +| clip_fraction | 0.456 | +| clip_range | 0.2 | +| entropy_loss | -0.384 | +| explained_variance | -0.185 | +| learning_rate | 0.0001 | +| loss | -0.083 | +| n_updates | 85350 | +| policy_gradient_loss | -0.0582 | +| value_loss | 0.000682 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.51e+03 | +| ep_rew_mean | 0.0628 | +| time/ | | +| fps | 310 | +| iterations | 2484 | +| time_elapsed | 8188 | +| total_timesteps | 2543616 | +| train/ | | +| approx_kl | 1.9074001 | +| clip_fraction | 0.476 | +| clip_range | 0.2 | +| entropy_loss | -0.413 | +| explained_variance | -1.61 | +| learning_rate | 0.0001 | +| loss | -0.114 | +| n_updates | 85360 | +| policy_gradient_loss | -0.0624 | +| value_loss | 0.000697 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.51e+03 | +| ep_rew_mean | 0.0677 | +| time/ | | +| fps | 310 | +| iterations | 2485 | +| time_elapsed | 8191 | +| total_timesteps | 2544640 | +| train/ | | +| approx_kl | 1.7334398 | +| clip_fraction | 0.453 | +| clip_range | 0.2 | +| entropy_loss | -0.393 | +| explained_variance | -0.163 | +| learning_rate | 0.0001 | +| loss | -0.0809 | +| n_updates | 85370 | +| policy_gradient_loss | -0.0588 | +| value_loss | 0.000562 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.51e+03 | +| ep_rew_mean | 0.0677 | +| time/ | | +| fps | 310 | +| iterations | 2486 | +| time_elapsed | 8195 | +| total_timesteps | 2545664 | +| train/ | | +| approx_kl | 2.002687 | +| clip_fraction | 0.468 | +| clip_range | 0.2 | +| entropy_loss | -0.365 | +| explained_variance | -2.17 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 85380 | +| policy_gradient_loss | -0.0643 | +| value_loss | 0.000647 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.49e+03 | +| ep_rew_mean | 0.0586 | +| time/ | | +| fps | 310 | +| iterations | 2487 | +| time_elapsed | 8198 | +| total_timesteps | 2546688 | +| train/ | | +| approx_kl | 1.812604 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.412 | +| explained_variance | -3.49 | +| learning_rate | 0.0001 | +| loss | -0.0926 | +| n_updates | 85390 | +| policy_gradient_loss | -0.064 | +| value_loss | 0.00051 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.48e+03 | +| ep_rew_mean | 0.0587 | +| time/ | | +| fps | 310 | +| iterations | 2488 | +| time_elapsed | 8201 | +| total_timesteps | 2547712 | +| train/ | | +| approx_kl | 1.9959136 | +| clip_fraction | 0.434 | +| clip_range | 0.2 | +| entropy_loss | -0.372 | +| explained_variance | -1.4 | +| learning_rate | 0.0001 | +| loss | -0.0778 | +| n_updates | 85400 | +| policy_gradient_loss | -0.0549 | +| value_loss | 0.000496 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.48e+03 | +| ep_rew_mean | 0.0587 | +| time/ | | +| fps | 310 | +| iterations | 2489 | +| time_elapsed | 8205 | +| total_timesteps | 2548736 | +| train/ | | +| approx_kl | 1.5158124 | +| clip_fraction | 0.447 | +| clip_range | 0.2 | +| entropy_loss | -0.417 | +| explained_variance | -0.499 | +| learning_rate | 0.0001 | +| loss | -0.073 | +| n_updates | 85410 | +| policy_gradient_loss | -0.0629 | +| value_loss | 0.000425 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.47e+03 | +| ep_rew_mean | 0.0557 | +| time/ | | +| fps | 310 | +| iterations | 2490 | +| time_elapsed | 8208 | +| total_timesteps | 2549760 | +| train/ | | +| approx_kl | 1.1801217 | +| clip_fraction | 0.455 | +| clip_range | 0.2 | +| entropy_loss | -0.479 | +| explained_variance | -0.759 | +| learning_rate | 0.0001 | +| loss | -0.0604 | +| n_updates | 85420 | +| policy_gradient_loss | -0.0404 | +| value_loss | 0.000578 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.46e+03 | +| ep_rew_mean | 0.053 | +| time/ | | +| fps | 310 | +| iterations | 2491 | +| time_elapsed | 8211 | +| total_timesteps | 2550784 | +| train/ | | +| approx_kl | 1.6159556 | +| clip_fraction | 0.454 | +| clip_range | 0.2 | +| entropy_loss | -0.411 | +| explained_variance | -6.56 | +| learning_rate | 0.0001 | +| loss | -0.0887 | +| n_updates | 85430 | +| policy_gradient_loss | -0.0638 | +| value_loss | 0.000427 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.46e+03 | +| ep_rew_mean | 0.053 | +| time/ | | +| fps | 310 | +| iterations | 2492 | +| time_elapsed | 8215 | +| total_timesteps | 2551808 | +| train/ | | +| approx_kl | 2.4659111 | +| clip_fraction | 0.494 | +| clip_range | 0.2 | +| entropy_loss | -0.418 | +| explained_variance | -0.625 | +| learning_rate | 0.0001 | +| loss | -0.0979 | +| n_updates | 85440 | +| policy_gradient_loss | -0.0605 | +| value_loss | 0.000653 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.47e+03 | +| ep_rew_mean | 0.0549 | +| time/ | | +| fps | 310 | +| iterations | 2493 | +| time_elapsed | 8218 | +| total_timesteps | 2552832 | +| train/ | | +| approx_kl | 2.095921 | +| clip_fraction | 0.459 | +| clip_range | 0.2 | +| entropy_loss | -0.34 | +| explained_variance | -5.82 | +| learning_rate | 0.0001 | +| loss | -0.0863 | +| n_updates | 85450 | +| policy_gradient_loss | -0.069 | +| value_loss | 0.000546 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.47e+03 | +| ep_rew_mean | 0.0549 | +| time/ | | +| fps | 310 | +| iterations | 2494 | +| time_elapsed | 8221 | +| total_timesteps | 2553856 | +| train/ | | +| approx_kl | 2.1786609 | +| clip_fraction | 0.467 | +| clip_range | 0.2 | +| entropy_loss | -0.429 | +| explained_variance | -0.856 | +| learning_rate | 0.0001 | +| loss | -0.0778 | +| n_updates | 85460 | +| policy_gradient_loss | -0.0632 | +| value_loss | 0.000522 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.47e+03 | +| ep_rew_mean | 0.0527 | +| time/ | | +| fps | 310 | +| iterations | 2495 | +| time_elapsed | 8225 | +| total_timesteps | 2554880 | +| train/ | | +| approx_kl | 1.784862 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.411 | +| explained_variance | -5.66 | +| learning_rate | 0.0001 | +| loss | -0.0885 | +| n_updates | 85470 | +| policy_gradient_loss | -0.0647 | +| value_loss | 0.000365 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.47e+03 | +| ep_rew_mean | 0.0527 | +| time/ | | +| fps | 310 | +| iterations | 2496 | +| time_elapsed | 8228 | +| total_timesteps | 2555904 | +| train/ | | +| approx_kl | 1.829465 | +| clip_fraction | 0.474 | +| clip_range | 0.2 | +| entropy_loss | -0.385 | +| explained_variance | -1.13 | +| learning_rate | 0.0001 | +| loss | -0.0373 | +| n_updates | 85480 | +| policy_gradient_loss | -0.064 | +| value_loss | 0.000482 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.47e+03 | +| ep_rew_mean | 0.0536 | +| time/ | | +| fps | 310 | +| iterations | 2497 | +| time_elapsed | 8232 | +| total_timesteps | 2556928 | +| train/ | | +| approx_kl | 1.6513433 | +| clip_fraction | 0.463 | +| clip_range | 0.2 | +| entropy_loss | -0.397 | +| explained_variance | -2.99 | +| learning_rate | 0.0001 | +| loss | -0.0844 | +| n_updates | 85490 | +| policy_gradient_loss | -0.0646 | +| value_loss | 0.000347 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.47e+03 | +| ep_rew_mean | 0.0536 | +| time/ | | +| fps | 310 | +| iterations | 2498 | +| time_elapsed | 8235 | +| total_timesteps | 2557952 | +| train/ | | +| approx_kl | 1.8241336 | +| clip_fraction | 0.437 | +| clip_range | 0.2 | +| entropy_loss | -0.339 | +| explained_variance | -1.68 | +| learning_rate | 0.0001 | +| loss | -0.08 | +| n_updates | 85500 | +| policy_gradient_loss | -0.0557 | +| value_loss | 0.000442 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.48e+03 | +| ep_rew_mean | 0.0593 | +| time/ | | +| fps | 310 | +| iterations | 2499 | +| time_elapsed | 8238 | +| total_timesteps | 2558976 | +| train/ | | +| approx_kl | 1.7757671 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.453 | +| explained_variance | -1.16 | +| learning_rate | 0.0001 | +| loss | -0.0887 | +| n_updates | 85510 | +| policy_gradient_loss | -0.0625 | +| value_loss | 0.000654 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.47e+03 | +| ep_rew_mean | 0.0524 | +| time/ | | +| fps | 310 | +| iterations | 2500 | +| time_elapsed | 8241 | +| total_timesteps | 2560000 | +| train/ | | +| approx_kl | 1.649752 | +| clip_fraction | 0.474 | +| clip_range | 0.2 | +| entropy_loss | -0.403 | +| explained_variance | -1.97 | +| learning_rate | 0.0001 | +| loss | -0.0529 | +| n_updates | 85520 | +| policy_gradient_loss | -0.0607 | +| value_loss | 0.000516 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.47e+03 | +| ep_rew_mean | 0.0524 | +| time/ | | +| fps | 310 | +| iterations | 2501 | +| time_elapsed | 8244 | +| total_timesteps | 2561024 | +| train/ | | +| approx_kl | 1.3568728 | +| clip_fraction | 0.457 | +| clip_range | 0.2 | +| entropy_loss | -0.407 | +| explained_variance | -1.74 | +| learning_rate | 0.0001 | +| loss | -0.0977 | +| n_updates | 85530 | +| policy_gradient_loss | -0.0592 | +| value_loss | 0.000646 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.47e+03 | +| ep_rew_mean | 0.0522 | +| time/ | | +| fps | 310 | +| iterations | 2502 | +| time_elapsed | 8247 | +| total_timesteps | 2562048 | +| train/ | | +| approx_kl | 1.9727664 | +| clip_fraction | 0.499 | +| clip_range | 0.2 | +| entropy_loss | -0.474 | +| explained_variance | -0.821 | +| learning_rate | 0.0001 | +| loss | -0.0879 | +| n_updates | 85540 | +| policy_gradient_loss | -0.0697 | +| value_loss | 0.000336 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.47e+03 | +| ep_rew_mean | 0.0522 | +| time/ | | +| fps | 310 | +| iterations | 2503 | +| time_elapsed | 8250 | +| total_timesteps | 2563072 | +| train/ | | +| approx_kl | 1.580493 | +| clip_fraction | 0.433 | +| clip_range | 0.2 | +| entropy_loss | -0.384 | +| explained_variance | -0.565 | +| learning_rate | 0.0001 | +| loss | -0.082 | +| n_updates | 85550 | +| policy_gradient_loss | -0.0558 | +| value_loss | 0.000457 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.48e+03 | +| ep_rew_mean | 0.0563 | +| time/ | | +| fps | 310 | +| iterations | 2504 | +| time_elapsed | 8254 | +| total_timesteps | 2564096 | +| train/ | | +| approx_kl | 1.8887517 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.402 | +| explained_variance | -1.16 | +| learning_rate | 0.0001 | +| loss | -0.0711 | +| n_updates | 85560 | +| policy_gradient_loss | -0.0684 | +| value_loss | 0.000348 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.48e+03 | +| ep_rew_mean | 0.0628 | +| time/ | | +| fps | 310 | +| iterations | 2505 | +| time_elapsed | 8257 | +| total_timesteps | 2565120 | +| train/ | | +| approx_kl | 1.3903008 | +| clip_fraction | 0.494 | +| clip_range | 0.2 | +| entropy_loss | -0.479 | +| explained_variance | -0.82 | +| learning_rate | 0.0001 | +| loss | -0.107 | +| n_updates | 85570 | +| policy_gradient_loss | -0.0679 | +| value_loss | 0.000587 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.47e+03 | +| ep_rew_mean | 0.0609 | +| time/ | | +| fps | 310 | +| iterations | 2506 | +| time_elapsed | 8260 | +| total_timesteps | 2566144 | +| train/ | | +| approx_kl | 1.7190924 | +| clip_fraction | 0.505 | +| clip_range | 0.2 | +| entropy_loss | -0.462 | +| explained_variance | -0.392 | +| learning_rate | 0.0001 | +| loss | -0.0959 | +| n_updates | 85580 | +| policy_gradient_loss | -0.0694 | +| value_loss | 0.000692 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.46e+03 | +| ep_rew_mean | 0.0574 | +| time/ | | +| fps | 310 | +| iterations | 2507 | +| time_elapsed | 8263 | +| total_timesteps | 2567168 | +| train/ | | +| approx_kl | 1.620061 | +| clip_fraction | 0.472 | +| clip_range | 0.2 | +| entropy_loss | -0.409 | +| explained_variance | -1.74 | +| learning_rate | 0.0001 | +| loss | -0.0619 | +| n_updates | 85590 | +| policy_gradient_loss | -0.0703 | +| value_loss | 0.00079 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.46e+03 | +| ep_rew_mean | 0.0574 | +| time/ | | +| fps | 310 | +| iterations | 2508 | +| time_elapsed | 8267 | +| total_timesteps | 2568192 | +| train/ | | +| approx_kl | 1.5399823 | +| clip_fraction | 0.421 | +| clip_range | 0.2 | +| entropy_loss | -0.362 | +| explained_variance | -2.3 | +| learning_rate | 0.0001 | +| loss | -0.0916 | +| n_updates | 85600 | +| policy_gradient_loss | -0.0623 | +| value_loss | 0.000614 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.47e+03 | +| ep_rew_mean | 0.0631 | +| time/ | | +| fps | 310 | +| iterations | 2509 | +| time_elapsed | 8270 | +| total_timesteps | 2569216 | +| train/ | | +| approx_kl | 1.845364 | +| clip_fraction | 0.46 | +| clip_range | 0.2 | +| entropy_loss | -0.402 | +| explained_variance | -1.46 | +| learning_rate | 0.0001 | +| loss | -0.065 | +| n_updates | 85610 | +| policy_gradient_loss | -0.0631 | +| value_loss | 0.000382 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.46e+03 | +| ep_rew_mean | 0.0621 | +| time/ | | +| fps | 310 | +| iterations | 2510 | +| time_elapsed | 8274 | +| total_timesteps | 2570240 | +| train/ | | +| approx_kl | 1.7582982 | +| clip_fraction | 0.446 | +| clip_range | 0.2 | +| entropy_loss | -0.361 | +| explained_variance | -1.05 | +| learning_rate | 0.0001 | +| loss | -0.0998 | +| n_updates | 85620 | +| policy_gradient_loss | -0.0615 | +| value_loss | 0.000458 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.46e+03 | +| ep_rew_mean | 0.0621 | +| time/ | | +| fps | 310 | +| iterations | 2511 | +| time_elapsed | 8277 | +| total_timesteps | 2571264 | +| train/ | | +| approx_kl | 1.3902289 | +| clip_fraction | 0.439 | +| clip_range | 0.2 | +| entropy_loss | -0.389 | +| explained_variance | -2.69 | +| learning_rate | 0.0001 | +| loss | -0.0744 | +| n_updates | 85630 | +| policy_gradient_loss | -0.0594 | +| value_loss | 0.000371 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.46e+03 | +| ep_rew_mean | 0.0583 | +| time/ | | +| fps | 310 | +| iterations | 2512 | +| time_elapsed | 8281 | +| total_timesteps | 2572288 | +| train/ | | +| approx_kl | 1.1795788 | +| clip_fraction | 0.442 | +| clip_range | 0.2 | +| entropy_loss | -0.415 | +| explained_variance | -6.03 | +| learning_rate | 0.0001 | +| loss | -0.0894 | +| n_updates | 85640 | +| policy_gradient_loss | -0.0621 | +| value_loss | 0.000132 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.44e+03 | +| ep_rew_mean | 0.0542 | +| time/ | | +| fps | 310 | +| iterations | 2513 | +| time_elapsed | 8284 | +| total_timesteps | 2573312 | +| train/ | | +| approx_kl | 1.8221399 | +| clip_fraction | 0.457 | +| clip_range | 0.2 | +| entropy_loss | -0.435 | +| explained_variance | -0.763 | +| learning_rate | 0.0001 | +| loss | -0.0835 | +| n_updates | 85650 | +| policy_gradient_loss | -0.0618 | +| value_loss | 0.000389 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.44e+03 | +| ep_rew_mean | 0.0561 | +| time/ | | +| fps | 310 | +| iterations | 2514 | +| time_elapsed | 8288 | +| total_timesteps | 2574336 | +| train/ | | +| approx_kl | 1.4019039 | +| clip_fraction | 0.446 | +| clip_range | 0.2 | +| entropy_loss | -0.396 | +| explained_variance | -1.58 | +| learning_rate | 0.0001 | +| loss | -0.0856 | +| n_updates | 85660 | +| policy_gradient_loss | -0.0572 | +| value_loss | 0.000423 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.44e+03 | +| ep_rew_mean | 0.0653 | +| time/ | | +| fps | 310 | +| iterations | 2515 | +| time_elapsed | 8291 | +| total_timesteps | 2575360 | +| train/ | | +| approx_kl | 1.8043296 | +| clip_fraction | 0.462 | +| clip_range | 0.2 | +| entropy_loss | -0.401 | +| explained_variance | -0.561 | +| learning_rate | 0.0001 | +| loss | -0.072 | +| n_updates | 85670 | +| policy_gradient_loss | -0.0626 | +| value_loss | 0.00086 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.44e+03 | +| ep_rew_mean | 0.0664 | +| time/ | | +| fps | 310 | +| iterations | 2516 | +| time_elapsed | 8294 | +| total_timesteps | 2576384 | +| train/ | | +| approx_kl | 1.7112484 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.4 | +| explained_variance | -1.05 | +| learning_rate | 0.0001 | +| loss | -0.0832 | +| n_updates | 85680 | +| policy_gradient_loss | -0.0663 | +| value_loss | 0.00102 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.44e+03 | +| ep_rew_mean | 0.0664 | +| time/ | | +| fps | 310 | +| iterations | 2517 | +| time_elapsed | 8298 | +| total_timesteps | 2577408 | +| train/ | | +| approx_kl | 1.656138 | +| clip_fraction | 0.468 | +| clip_range | 0.2 | +| entropy_loss | -0.382 | +| explained_variance | -3.15 | +| learning_rate | 0.0001 | +| loss | -0.0892 | +| n_updates | 85690 | +| policy_gradient_loss | -0.0653 | +| value_loss | 0.000522 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.45e+03 | +| ep_rew_mean | 0.0698 | +| time/ | | +| fps | 310 | +| iterations | 2518 | +| time_elapsed | 8301 | +| total_timesteps | 2578432 | +| train/ | | +| approx_kl | 1.1521237 | +| clip_fraction | 0.495 | +| clip_range | 0.2 | +| entropy_loss | -0.464 | +| explained_variance | -1.54 | +| learning_rate | 0.0001 | +| loss | -0.0728 | +| n_updates | 85700 | +| policy_gradient_loss | -0.0689 | +| value_loss | 0.000682 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.45e+03 | +| ep_rew_mean | 0.0698 | +| time/ | | +| fps | 310 | +| iterations | 2519 | +| time_elapsed | 8304 | +| total_timesteps | 2579456 | +| train/ | | +| approx_kl | 1.9552138 | +| clip_fraction | 0.498 | +| clip_range | 0.2 | +| entropy_loss | -0.431 | +| explained_variance | -2.44 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 85710 | +| policy_gradient_loss | -0.0703 | +| value_loss | 0.000478 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.46e+03 | +| ep_rew_mean | 0.0751 | +| time/ | | +| fps | 310 | +| iterations | 2520 | +| time_elapsed | 8307 | +| total_timesteps | 2580480 | +| train/ | | +| approx_kl | 1.8021735 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.379 | +| explained_variance | -2.79 | +| learning_rate | 0.0001 | +| loss | -0.0953 | +| n_updates | 85720 | +| policy_gradient_loss | -0.0766 | +| value_loss | 0.00041 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.46e+03 | +| ep_rew_mean | 0.0751 | +| time/ | | +| fps | 310 | +| iterations | 2521 | +| time_elapsed | 8310 | +| total_timesteps | 2581504 | +| train/ | | +| approx_kl | 2.4832528 | +| clip_fraction | 0.457 | +| clip_range | 0.2 | +| entropy_loss | -0.433 | +| explained_variance | -2.16 | +| learning_rate | 0.0001 | +| loss | -0.079 | +| n_updates | 85730 | +| policy_gradient_loss | -0.0668 | +| value_loss | 0.000388 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.46e+03 | +| ep_rew_mean | 0.078 | +| time/ | | +| fps | 310 | +| iterations | 2522 | +| time_elapsed | 8313 | +| total_timesteps | 2582528 | +| train/ | | +| approx_kl | 1.9961822 | +| clip_fraction | 0.46 | +| clip_range | 0.2 | +| entropy_loss | -0.374 | +| explained_variance | -2.42 | +| learning_rate | 0.0001 | +| loss | -0.0919 | +| n_updates | 85740 | +| policy_gradient_loss | -0.0594 | +| value_loss | 0.00034 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.47e+03 | +| ep_rew_mean | 0.0849 | +| time/ | | +| fps | 310 | +| iterations | 2523 | +| time_elapsed | 8317 | +| total_timesteps | 2583552 | +| train/ | | +| approx_kl | 1.7586946 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.433 | +| explained_variance | -0.545 | +| learning_rate | 0.0001 | +| loss | -0.079 | +| n_updates | 85750 | +| policy_gradient_loss | -0.0634 | +| value_loss | 0.000297 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.47e+03 | +| ep_rew_mean | 0.0849 | +| time/ | | +| fps | 310 | +| iterations | 2524 | +| time_elapsed | 8320 | +| total_timesteps | 2584576 | +| train/ | | +| approx_kl | 2.3742704 | +| clip_fraction | 0.499 | +| clip_range | 0.2 | +| entropy_loss | -0.481 | +| explained_variance | -0.323 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 85760 | +| policy_gradient_loss | -0.0679 | +| value_loss | 0.000461 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.48e+03 | +| ep_rew_mean | 0.0887 | +| time/ | | +| fps | 310 | +| iterations | 2525 | +| time_elapsed | 8323 | +| total_timesteps | 2585600 | +| train/ | | +| approx_kl | 1.5133271 | +| clip_fraction | 0.448 | +| clip_range | 0.2 | +| entropy_loss | -0.412 | +| explained_variance | -4.41 | +| learning_rate | 0.0001 | +| loss | -0.111 | +| n_updates | 85770 | +| policy_gradient_loss | -0.0651 | +| value_loss | 0.000486 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.48e+03 | +| ep_rew_mean | 0.0887 | +| time/ | | +| fps | 310 | +| iterations | 2526 | +| time_elapsed | 8327 | +| total_timesteps | 2586624 | +| train/ | | +| approx_kl | 1.6558435 | +| clip_fraction | 0.443 | +| clip_range | 0.2 | +| entropy_loss | -0.364 | +| explained_variance | -1.03 | +| learning_rate | 0.0001 | +| loss | -0.0994 | +| n_updates | 85780 | +| policy_gradient_loss | -0.0645 | +| value_loss | 0.000633 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.47e+03 | +| ep_rew_mean | 0.0908 | +| time/ | | +| fps | 310 | +| iterations | 2527 | +| time_elapsed | 8330 | +| total_timesteps | 2587648 | +| train/ | | +| approx_kl | 1.3756053 | +| clip_fraction | 0.451 | +| clip_range | 0.2 | +| entropy_loss | -0.418 | +| explained_variance | -0.925 | +| learning_rate | 0.0001 | +| loss | -0.0597 | +| n_updates | 85790 | +| policy_gradient_loss | -0.0656 | +| value_loss | 0.000702 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.47e+03 | +| ep_rew_mean | 0.0888 | +| time/ | | +| fps | 310 | +| iterations | 2528 | +| time_elapsed | 8333 | +| total_timesteps | 2588672 | +| train/ | | +| approx_kl | 1.410721 | +| clip_fraction | 0.466 | +| clip_range | 0.2 | +| entropy_loss | -0.427 | +| explained_variance | -4.09 | +| learning_rate | 0.0001 | +| loss | -0.0692 | +| n_updates | 85800 | +| policy_gradient_loss | -0.0649 | +| value_loss | 0.000425 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.47e+03 | +| ep_rew_mean | 0.0832 | +| time/ | | +| fps | 310 | +| iterations | 2529 | +| time_elapsed | 8337 | +| total_timesteps | 2589696 | +| train/ | | +| approx_kl | 1.8884315 | +| clip_fraction | 0.496 | +| clip_range | 0.2 | +| entropy_loss | -0.528 | +| explained_variance | -6.22 | +| learning_rate | 0.0001 | +| loss | -0.0706 | +| n_updates | 85810 | +| policy_gradient_loss | -0.0718 | +| value_loss | 0.000156 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.47e+03 | +| ep_rew_mean | 0.0832 | +| time/ | | +| fps | 310 | +| iterations | 2530 | +| time_elapsed | 8341 | +| total_timesteps | 2590720 | +| train/ | | +| approx_kl | 1.283698 | +| clip_fraction | 0.438 | +| clip_range | 0.2 | +| entropy_loss | -0.406 | +| explained_variance | -0.707 | +| learning_rate | 0.0001 | +| loss | -0.0698 | +| n_updates | 85820 | +| policy_gradient_loss | -0.0575 | +| value_loss | 0.000452 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.47e+03 | +| ep_rew_mean | 0.0832 | +| time/ | | +| fps | 310 | +| iterations | 2531 | +| time_elapsed | 8344 | +| total_timesteps | 2591744 | +| train/ | | +| approx_kl | 2.0742133 | +| clip_fraction | 0.466 | +| clip_range | 0.2 | +| entropy_loss | -0.369 | +| explained_variance | -2 | +| learning_rate | 0.0001 | +| loss | -0.11 | +| n_updates | 85830 | +| policy_gradient_loss | -0.0734 | +| value_loss | 0.000725 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.49e+03 | +| ep_rew_mean | 0.086 | +| time/ | | +| fps | 310 | +| iterations | 2532 | +| time_elapsed | 8347 | +| total_timesteps | 2592768 | +| train/ | | +| approx_kl | 1.7425244 | +| clip_fraction | 0.515 | +| clip_range | 0.2 | +| entropy_loss | -0.478 | +| explained_variance | -5.26 | +| learning_rate | 0.0001 | +| loss | -0.118 | +| n_updates | 85840 | +| policy_gradient_loss | -0.0777 | +| value_loss | 0.000323 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.48e+03 | +| ep_rew_mean | 0.088 | +| time/ | | +| fps | 310 | +| iterations | 2533 | +| time_elapsed | 8351 | +| total_timesteps | 2593792 | +| train/ | | +| approx_kl | 2.0296698 | +| clip_fraction | 0.456 | +| clip_range | 0.2 | +| entropy_loss | -0.359 | +| explained_variance | -0.716 | +| learning_rate | 0.0001 | +| loss | -0.0986 | +| n_updates | 85850 | +| policy_gradient_loss | -0.0624 | +| value_loss | 0.000318 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.49e+03 | +| ep_rew_mean | 0.087 | +| time/ | | +| fps | 310 | +| iterations | 2534 | +| time_elapsed | 8354 | +| total_timesteps | 2594816 | +| train/ | | +| approx_kl | 2.1739302 | +| clip_fraction | 0.443 | +| clip_range | 0.2 | +| entropy_loss | -0.407 | +| explained_variance | -0.93 | +| learning_rate | 0.0001 | +| loss | -0.0725 | +| n_updates | 85860 | +| policy_gradient_loss | -0.0542 | +| value_loss | 0.000526 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.49e+03 | +| ep_rew_mean | 0.0862 | +| time/ | | +| fps | 310 | +| iterations | 2535 | +| time_elapsed | 8357 | +| total_timesteps | 2595840 | +| train/ | | +| approx_kl | 1.482014 | +| clip_fraction | 0.468 | +| clip_range | 0.2 | +| entropy_loss | -0.394 | +| explained_variance | -3.6 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 85870 | +| policy_gradient_loss | -0.0645 | +| value_loss | 0.000433 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.48e+03 | +| ep_rew_mean | 0.0847 | +| time/ | | +| fps | 310 | +| iterations | 2536 | +| time_elapsed | 8360 | +| total_timesteps | 2596864 | +| train/ | | +| approx_kl | 1.7070653 | +| clip_fraction | 0.44 | +| clip_range | 0.2 | +| entropy_loss | -0.376 | +| explained_variance | -1.26 | +| learning_rate | 0.0001 | +| loss | -0.0944 | +| n_updates | 85880 | +| policy_gradient_loss | -0.0645 | +| value_loss | 0.000341 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.47e+03 | +| ep_rew_mean | 0.0843 | +| time/ | | +| fps | 310 | +| iterations | 2537 | +| time_elapsed | 8363 | +| total_timesteps | 2597888 | +| train/ | | +| approx_kl | 1.470505 | +| clip_fraction | 0.456 | +| clip_range | 0.2 | +| entropy_loss | -0.393 | +| explained_variance | -0.312 | +| learning_rate | 0.0001 | +| loss | -0.0707 | +| n_updates | 85890 | +| policy_gradient_loss | -0.0594 | +| value_loss | 0.000653 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.47e+03 | +| ep_rew_mean | 0.0859 | +| time/ | | +| fps | 310 | +| iterations | 2538 | +| time_elapsed | 8366 | +| total_timesteps | 2598912 | +| train/ | | +| approx_kl | 2.5200067 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.438 | +| explained_variance | -2.77 | +| learning_rate | 0.0001 | +| loss | -0.0861 | +| n_updates | 85900 | +| policy_gradient_loss | -0.059 | +| value_loss | 0.000505 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.47e+03 | +| ep_rew_mean | 0.0859 | +| time/ | | +| fps | 310 | +| iterations | 2539 | +| time_elapsed | 8370 | +| total_timesteps | 2599936 | +| train/ | | +| approx_kl | 1.2475072 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.442 | +| explained_variance | -3.27 | +| learning_rate | 0.0001 | +| loss | -0.0975 | +| n_updates | 85910 | +| policy_gradient_loss | -0.0693 | +| value_loss | 0.00047 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.49e+03 | +| ep_rew_mean | 0.0911 | +| time/ | | +| fps | 310 | +| iterations | 2540 | +| time_elapsed | 8373 | +| total_timesteps | 2600960 | +| train/ | | +| approx_kl | 1.6754315 | +| clip_fraction | 0.485 | +| clip_range | 0.2 | +| entropy_loss | -0.457 | +| explained_variance | -3.25 | +| learning_rate | 0.0001 | +| loss | -0.0772 | +| n_updates | 85920 | +| policy_gradient_loss | -0.0628 | +| value_loss | 0.000622 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.49e+03 | +| ep_rew_mean | 0.0911 | +| time/ | | +| fps | 310 | +| iterations | 2541 | +| time_elapsed | 8376 | +| total_timesteps | 2601984 | +| train/ | | +| approx_kl | 3.1306653 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.404 | +| explained_variance | -1.54 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 85930 | +| policy_gradient_loss | -0.0677 | +| value_loss | 0.000606 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.48e+03 | +| ep_rew_mean | 0.0889 | +| time/ | | +| fps | 310 | +| iterations | 2542 | +| time_elapsed | 8379 | +| total_timesteps | 2603008 | +| train/ | | +| approx_kl | 1.5094545 | +| clip_fraction | 0.45 | +| clip_range | 0.2 | +| entropy_loss | -0.408 | +| explained_variance | -2.18 | +| learning_rate | 0.0001 | +| loss | -0.0877 | +| n_updates | 85940 | +| policy_gradient_loss | -0.0615 | +| value_loss | 0.000501 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.48e+03 | +| ep_rew_mean | 0.0845 | +| time/ | | +| fps | 310 | +| iterations | 2543 | +| time_elapsed | 8383 | +| total_timesteps | 2604032 | +| train/ | | +| approx_kl | 1.7211475 | +| clip_fraction | 0.505 | +| clip_range | 0.2 | +| entropy_loss | -0.419 | +| explained_variance | -1.01 | +| learning_rate | 0.0001 | +| loss | -0.0826 | +| n_updates | 85950 | +| policy_gradient_loss | -0.0668 | +| value_loss | 0.00051 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.48e+03 | +| ep_rew_mean | 0.08 | +| time/ | | +| fps | 310 | +| iterations | 2544 | +| time_elapsed | 8386 | +| total_timesteps | 2605056 | +| train/ | | +| approx_kl | 1.8956654 | +| clip_fraction | 0.466 | +| clip_range | 0.2 | +| entropy_loss | -0.405 | +| explained_variance | -2.67 | +| learning_rate | 0.0001 | +| loss | -0.0532 | +| n_updates | 85960 | +| policy_gradient_loss | -0.0614 | +| value_loss | 0.000438 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.48e+03 | +| ep_rew_mean | 0.08 | +| time/ | | +| fps | 310 | +| iterations | 2545 | +| time_elapsed | 8390 | +| total_timesteps | 2606080 | +| train/ | | +| approx_kl | 1.7018414 | +| clip_fraction | 0.477 | +| clip_range | 0.2 | +| entropy_loss | -0.374 | +| explained_variance | -1.16 | +| learning_rate | 0.0001 | +| loss | -0.0816 | +| n_updates | 85970 | +| policy_gradient_loss | -0.0675 | +| value_loss | 0.000331 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.48e+03 | +| ep_rew_mean | 0.0808 | +| time/ | | +| fps | 310 | +| iterations | 2546 | +| time_elapsed | 8393 | +| total_timesteps | 2607104 | +| train/ | | +| approx_kl | 1.7086594 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.429 | +| explained_variance | -1.18 | +| learning_rate | 0.0001 | +| loss | -0.0948 | +| n_updates | 85980 | +| policy_gradient_loss | -0.066 | +| value_loss | 0.000415 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.48e+03 | +| ep_rew_mean | 0.0808 | +| time/ | | +| fps | 310 | +| iterations | 2547 | +| time_elapsed | 8397 | +| total_timesteps | 2608128 | +| train/ | | +| approx_kl | 1.4870498 | +| clip_fraction | 0.476 | +| clip_range | 0.2 | +| entropy_loss | -0.393 | +| explained_variance | -0.864 | +| learning_rate | 0.0001 | +| loss | -0.11 | +| n_updates | 85990 | +| policy_gradient_loss | -0.0655 | +| value_loss | 0.000545 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.48e+03 | +| ep_rew_mean | 0.0813 | +| time/ | | +| fps | 310 | +| iterations | 2548 | +| time_elapsed | 8400 | +| total_timesteps | 2609152 | +| train/ | | +| approx_kl | 1.5128925 | +| clip_fraction | 0.423 | +| clip_range | 0.2 | +| entropy_loss | -0.367 | +| explained_variance | -2.9 | +| learning_rate | 0.0001 | +| loss | -0.112 | +| n_updates | 86000 | +| policy_gradient_loss | -0.0573 | +| value_loss | 0.000644 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.48e+03 | +| ep_rew_mean | 0.0813 | +| time/ | | +| fps | 310 | +| iterations | 2549 | +| time_elapsed | 8404 | +| total_timesteps | 2610176 | +| train/ | | +| approx_kl | 1.6521015 | +| clip_fraction | 0.443 | +| clip_range | 0.2 | +| entropy_loss | -0.388 | +| explained_variance | -2.27 | +| learning_rate | 0.0001 | +| loss | -0.0686 | +| n_updates | 86010 | +| policy_gradient_loss | -0.0637 | +| value_loss | 0.000527 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.49e+03 | +| ep_rew_mean | 0.0821 | +| time/ | | +| fps | 310 | +| iterations | 2550 | +| time_elapsed | 8407 | +| total_timesteps | 2611200 | +| train/ | | +| approx_kl | 1.4506377 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.437 | +| explained_variance | -2.52 | +| learning_rate | 0.0001 | +| loss | -0.0751 | +| n_updates | 86020 | +| policy_gradient_loss | -0.0661 | +| value_loss | 0.000347 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.5e+03 | +| ep_rew_mean | 0.0776 | +| time/ | | +| fps | 310 | +| iterations | 2551 | +| time_elapsed | 8410 | +| total_timesteps | 2612224 | +| train/ | | +| approx_kl | 1.7900019 | +| clip_fraction | 0.464 | +| clip_range | 0.2 | +| entropy_loss | -0.391 | +| explained_variance | -0.929 | +| learning_rate | 0.0001 | +| loss | -0.0918 | +| n_updates | 86030 | +| policy_gradient_loss | -0.0671 | +| value_loss | 0.000361 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.5e+03 | +| ep_rew_mean | 0.0776 | +| time/ | | +| fps | 310 | +| iterations | 2552 | +| time_elapsed | 8414 | +| total_timesteps | 2613248 | +| train/ | | +| approx_kl | 1.537998 | +| clip_fraction | 0.448 | +| clip_range | 0.2 | +| entropy_loss | -0.352 | +| explained_variance | -0.717 | +| learning_rate | 0.0001 | +| loss | -0.0857 | +| n_updates | 86040 | +| policy_gradient_loss | -0.0635 | +| value_loss | 0.000596 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.49e+03 | +| ep_rew_mean | 0.0734 | +| time/ | | +| fps | 310 | +| iterations | 2553 | +| time_elapsed | 8417 | +| total_timesteps | 2614272 | +| train/ | | +| approx_kl | 1.7112284 | +| clip_fraction | 0.477 | +| clip_range | 0.2 | +| entropy_loss | -0.438 | +| explained_variance | -3.58 | +| learning_rate | 0.0001 | +| loss | -0.0679 | +| n_updates | 86050 | +| policy_gradient_loss | -0.0725 | +| value_loss | 0.000499 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.49e+03 | +| ep_rew_mean | 0.0734 | +| time/ | | +| fps | 310 | +| iterations | 2554 | +| time_elapsed | 8420 | +| total_timesteps | 2615296 | +| train/ | | +| approx_kl | 1.6542815 | +| clip_fraction | 0.463 | +| clip_range | 0.2 | +| entropy_loss | -0.436 | +| explained_variance | -0.625 | +| learning_rate | 0.0001 | +| loss | -0.0831 | +| n_updates | 86060 | +| policy_gradient_loss | -0.0636 | +| value_loss | 0.00052 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.49e+03 | +| ep_rew_mean | 0.0719 | +| time/ | | +| fps | 310 | +| iterations | 2555 | +| time_elapsed | 8423 | +| total_timesteps | 2616320 | +| train/ | | +| approx_kl | 1.3938118 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.484 | +| explained_variance | -3.19 | +| learning_rate | 0.0001 | +| loss | -0.0826 | +| n_updates | 86070 | +| policy_gradient_loss | -0.0683 | +| value_loss | 0.000288 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.49e+03 | +| ep_rew_mean | 0.0719 | +| time/ | | +| fps | 310 | +| iterations | 2556 | +| time_elapsed | 8426 | +| total_timesteps | 2617344 | +| train/ | | +| approx_kl | 1.630352 | +| clip_fraction | 0.43 | +| clip_range | 0.2 | +| entropy_loss | -0.359 | +| explained_variance | -1.82 | +| learning_rate | 0.0001 | +| loss | -0.0478 | +| n_updates | 86080 | +| policy_gradient_loss | -0.0623 | +| value_loss | 0.0005 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.49e+03 | +| ep_rew_mean | 0.0762 | +| time/ | | +| fps | 310 | +| iterations | 2557 | +| time_elapsed | 8429 | +| total_timesteps | 2618368 | +| train/ | | +| approx_kl | 1.6529927 | +| clip_fraction | 0.469 | +| clip_range | 0.2 | +| entropy_loss | -0.463 | +| explained_variance | -1.51 | +| learning_rate | 0.0001 | +| loss | -0.0963 | +| n_updates | 86090 | +| policy_gradient_loss | -0.0672 | +| value_loss | 0.000478 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.49e+03 | +| ep_rew_mean | 0.0787 | +| time/ | | +| fps | 310 | +| iterations | 2558 | +| time_elapsed | 8433 | +| total_timesteps | 2619392 | +| train/ | | +| approx_kl | 1.3415842 | +| clip_fraction | 0.469 | +| clip_range | 0.2 | +| entropy_loss | -0.425 | +| explained_variance | -4.76 | +| learning_rate | 0.0001 | +| loss | -0.0887 | +| n_updates | 86100 | +| policy_gradient_loss | -0.0647 | +| value_loss | 0.000574 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.49e+03 | +| ep_rew_mean | 0.0787 | +| time/ | | +| fps | 310 | +| iterations | 2559 | +| time_elapsed | 8436 | +| total_timesteps | 2620416 | +| train/ | | +| approx_kl | 2.1060905 | +| clip_fraction | 0.497 | +| clip_range | 0.2 | +| entropy_loss | -0.414 | +| explained_variance | -1.82 | +| learning_rate | 0.0001 | +| loss | -0.0724 | +| n_updates | 86110 | +| policy_gradient_loss | -0.0597 | +| value_loss | 0.00056 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.49e+03 | +| ep_rew_mean | 0.0777 | +| time/ | | +| fps | 310 | +| iterations | 2560 | +| time_elapsed | 8439 | +| total_timesteps | 2621440 | +| train/ | | +| approx_kl | 1.8745389 | +| clip_fraction | 0.542 | +| clip_range | 0.2 | +| entropy_loss | -0.518 | +| explained_variance | -1.39 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 86120 | +| policy_gradient_loss | -0.0726 | +| value_loss | 0.000383 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.49e+03 | +| ep_rew_mean | 0.0759 | +| time/ | | +| fps | 310 | +| iterations | 2561 | +| time_elapsed | 8442 | +| total_timesteps | 2622464 | +| train/ | | +| approx_kl | 1.884955 | +| clip_fraction | 0.47 | +| clip_range | 0.2 | +| entropy_loss | -0.37 | +| explained_variance | -1.71 | +| learning_rate | 0.0001 | +| loss | -0.0996 | +| n_updates | 86130 | +| policy_gradient_loss | -0.0671 | +| value_loss | 0.000442 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.49e+03 | +| ep_rew_mean | 0.0759 | +| time/ | | +| fps | 310 | +| iterations | 2562 | +| time_elapsed | 8446 | +| total_timesteps | 2623488 | +| train/ | | +| approx_kl | 1.7590115 | +| clip_fraction | 0.452 | +| clip_range | 0.2 | +| entropy_loss | -0.384 | +| explained_variance | -2.45 | +| learning_rate | 0.0001 | +| loss | -0.0701 | +| n_updates | 86140 | +| policy_gradient_loss | -0.0647 | +| value_loss | 0.000467 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.49e+03 | +| ep_rew_mean | 0.0759 | +| time/ | | +| fps | 310 | +| iterations | 2563 | +| time_elapsed | 8449 | +| total_timesteps | 2624512 | +| train/ | | +| approx_kl | 1.5289931 | +| clip_fraction | 0.469 | +| clip_range | 0.2 | +| entropy_loss | -0.383 | +| explained_variance | -1.39 | +| learning_rate | 0.0001 | +| loss | -0.114 | +| n_updates | 86150 | +| policy_gradient_loss | -0.0669 | +| value_loss | 0.000543 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.51e+03 | +| ep_rew_mean | 0.0825 | +| time/ | | +| fps | 310 | +| iterations | 2564 | +| time_elapsed | 8452 | +| total_timesteps | 2625536 | +| train/ | | +| approx_kl | 1.630047 | +| clip_fraction | 0.493 | +| clip_range | 0.2 | +| entropy_loss | -0.42 | +| explained_variance | -1.66 | +| learning_rate | 0.0001 | +| loss | -0.0857 | +| n_updates | 86160 | +| policy_gradient_loss | -0.0696 | +| value_loss | 0.000581 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.51e+03 | +| ep_rew_mean | 0.0825 | +| time/ | | +| fps | 310 | +| iterations | 2565 | +| time_elapsed | 8456 | +| total_timesteps | 2626560 | +| train/ | | +| approx_kl | 2.3474474 | +| clip_fraction | 0.477 | +| clip_range | 0.2 | +| entropy_loss | -0.426 | +| explained_variance | -3.81 | +| learning_rate | 0.0001 | +| loss | -0.0974 | +| n_updates | 86170 | +| policy_gradient_loss | -0.0649 | +| value_loss | 0.000258 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.51e+03 | +| ep_rew_mean | 0.0814 | +| time/ | | +| fps | 310 | +| iterations | 2566 | +| time_elapsed | 8459 | +| total_timesteps | 2627584 | +| train/ | | +| approx_kl | 1.578015 | +| clip_fraction | 0.466 | +| clip_range | 0.2 | +| entropy_loss | -0.457 | +| explained_variance | -6.45 | +| learning_rate | 0.0001 | +| loss | -0.1 | +| n_updates | 86180 | +| policy_gradient_loss | -0.0712 | +| value_loss | 0.000283 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.51e+03 | +| ep_rew_mean | 0.0814 | +| time/ | | +| fps | 310 | +| iterations | 2567 | +| time_elapsed | 8462 | +| total_timesteps | 2628608 | +| train/ | | +| approx_kl | 2.1984978 | +| clip_fraction | 0.464 | +| clip_range | 0.2 | +| entropy_loss | -0.407 | +| explained_variance | -0.776 | +| learning_rate | 0.0001 | +| loss | -0.0996 | +| n_updates | 86190 | +| policy_gradient_loss | -0.0616 | +| value_loss | 0.000397 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.51e+03 | +| ep_rew_mean | 0.0828 | +| time/ | | +| fps | 310 | +| iterations | 2568 | +| time_elapsed | 8466 | +| total_timesteps | 2629632 | +| train/ | | +| approx_kl | 1.8118408 | +| clip_fraction | 0.491 | +| clip_range | 0.2 | +| entropy_loss | -0.476 | +| explained_variance | -4.68 | +| learning_rate | 0.0001 | +| loss | -0.0962 | +| n_updates | 86200 | +| policy_gradient_loss | -0.0611 | +| value_loss | 0.000262 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.51e+03 | +| ep_rew_mean | 0.0828 | +| time/ | | +| fps | 310 | +| iterations | 2569 | +| time_elapsed | 8469 | +| total_timesteps | 2630656 | +| train/ | | +| approx_kl | 2.6101136 | +| clip_fraction | 0.453 | +| clip_range | 0.2 | +| entropy_loss | -0.369 | +| explained_variance | -1.44 | +| learning_rate | 0.0001 | +| loss | -0.0898 | +| n_updates | 86210 | +| policy_gradient_loss | -0.0628 | +| value_loss | 0.000229 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.51e+03 | +| ep_rew_mean | 0.0792 | +| time/ | | +| fps | 310 | +| iterations | 2570 | +| time_elapsed | 8472 | +| total_timesteps | 2631680 | +| train/ | | +| approx_kl | 1.584611 | +| clip_fraction | 0.491 | +| clip_range | 0.2 | +| entropy_loss | -0.422 | +| explained_variance | -0.839 | +| learning_rate | 0.0001 | +| loss | -0.0906 | +| n_updates | 86220 | +| policy_gradient_loss | -0.0687 | +| value_loss | 0.00061 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.51e+03 | +| ep_rew_mean | 0.0792 | +| time/ | | +| fps | 310 | +| iterations | 2571 | +| time_elapsed | 8475 | +| total_timesteps | 2632704 | +| train/ | | +| approx_kl | 1.4510052 | +| clip_fraction | 0.439 | +| clip_range | 0.2 | +| entropy_loss | -0.392 | +| explained_variance | -0.648 | +| learning_rate | 0.0001 | +| loss | -0.0344 | +| n_updates | 86230 | +| policy_gradient_loss | -0.0576 | +| value_loss | 0.000827 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.51e+03 | +| ep_rew_mean | 0.0792 | +| time/ | | +| fps | 310 | +| iterations | 2572 | +| time_elapsed | 8478 | +| total_timesteps | 2633728 | +| train/ | | +| approx_kl | 1.5435319 | +| clip_fraction | 0.482 | +| clip_range | 0.2 | +| entropy_loss | -0.415 | +| explained_variance | -2.14 | +| learning_rate | 0.0001 | +| loss | -0.0949 | +| n_updates | 86240 | +| policy_gradient_loss | -0.0615 | +| value_loss | 0.000351 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.52e+03 | +| ep_rew_mean | 0.0795 | +| time/ | | +| fps | 310 | +| iterations | 2573 | +| time_elapsed | 8482 | +| total_timesteps | 2634752 | +| train/ | | +| approx_kl | 1.7610809 | +| clip_fraction | 0.482 | +| clip_range | 0.2 | +| entropy_loss | -0.453 | +| explained_variance | -4.74 | +| learning_rate | 0.0001 | +| loss | -0.0905 | +| n_updates | 86250 | +| policy_gradient_loss | -0.0648 | +| value_loss | 0.000297 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.51e+03 | +| ep_rew_mean | 0.0787 | +| time/ | | +| fps | 310 | +| iterations | 2574 | +| time_elapsed | 8485 | +| total_timesteps | 2635776 | +| train/ | | +| approx_kl | 1.6989726 | +| clip_fraction | 0.434 | +| clip_range | 0.2 | +| entropy_loss | -0.341 | +| explained_variance | -2.24 | +| learning_rate | 0.0001 | +| loss | -0.0729 | +| n_updates | 86260 | +| policy_gradient_loss | -0.0608 | +| value_loss | 0.000643 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.51e+03 | +| ep_rew_mean | 0.0787 | +| time/ | | +| fps | 310 | +| iterations | 2575 | +| time_elapsed | 8488 | +| total_timesteps | 2636800 | +| train/ | | +| approx_kl | 1.8574617 | +| clip_fraction | 0.423 | +| clip_range | 0.2 | +| entropy_loss | -0.342 | +| explained_variance | -1.42 | +| learning_rate | 0.0001 | +| loss | -0.0847 | +| n_updates | 86270 | +| policy_gradient_loss | -0.057 | +| value_loss | 0.00068 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.51e+03 | +| ep_rew_mean | 0.0814 | +| time/ | | +| fps | 310 | +| iterations | 2576 | +| time_elapsed | 8491 | +| total_timesteps | 2637824 | +| train/ | | +| approx_kl | 3.4284432 | +| clip_fraction | 0.463 | +| clip_range | 0.2 | +| entropy_loss | -0.367 | +| explained_variance | -0.895 | +| learning_rate | 0.0001 | +| loss | -0.0784 | +| n_updates | 86280 | +| policy_gradient_loss | -0.0629 | +| value_loss | 0.000671 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.52e+03 | +| ep_rew_mean | 0.0884 | +| time/ | | +| fps | 310 | +| iterations | 2577 | +| time_elapsed | 8494 | +| total_timesteps | 2638848 | +| train/ | | +| approx_kl | 2.1426156 | +| clip_fraction | 0.448 | +| clip_range | 0.2 | +| entropy_loss | -0.374 | +| explained_variance | -1.77 | +| learning_rate | 0.0001 | +| loss | -0.0862 | +| n_updates | 86290 | +| policy_gradient_loss | -0.0552 | +| value_loss | 0.000613 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.52e+03 | +| ep_rew_mean | 0.0884 | +| time/ | | +| fps | 310 | +| iterations | 2578 | +| time_elapsed | 8498 | +| total_timesteps | 2639872 | +| train/ | | +| approx_kl | 1.9725263 | +| clip_fraction | 0.47 | +| clip_range | 0.2 | +| entropy_loss | -0.39 | +| explained_variance | -7.97 | +| learning_rate | 0.0001 | +| loss | -0.0868 | +| n_updates | 86300 | +| policy_gradient_loss | -0.0651 | +| value_loss | 0.000349 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.52e+03 | +| ep_rew_mean | 0.0884 | +| time/ | | +| fps | 310 | +| iterations | 2579 | +| time_elapsed | 8501 | +| total_timesteps | 2640896 | +| train/ | | +| approx_kl | 1.609701 | +| clip_fraction | 0.454 | +| clip_range | 0.2 | +| entropy_loss | -0.398 | +| explained_variance | -2.69 | +| learning_rate | 0.0001 | +| loss | -0.0875 | +| n_updates | 86310 | +| policy_gradient_loss | -0.063 | +| value_loss | 0.000229 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.52e+03 | +| ep_rew_mean | 0.0908 | +| time/ | | +| fps | 310 | +| iterations | 2580 | +| time_elapsed | 8504 | +| total_timesteps | 2641920 | +| train/ | | +| approx_kl | 1.6400363 | +| clip_fraction | 0.493 | +| clip_range | 0.2 | +| entropy_loss | -0.445 | +| explained_variance | -2.08 | +| learning_rate | 0.0001 | +| loss | -0.0996 | +| n_updates | 86320 | +| policy_gradient_loss | -0.0641 | +| value_loss | 0.000334 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.53e+03 | +| ep_rew_mean | 0.0918 | +| time/ | | +| fps | 310 | +| iterations | 2581 | +| time_elapsed | 8508 | +| total_timesteps | 2642944 | +| train/ | | +| approx_kl | 1.7483438 | +| clip_fraction | 0.47 | +| clip_range | 0.2 | +| entropy_loss | -0.442 | +| explained_variance | -0.745 | +| learning_rate | 0.0001 | +| loss | -0.081 | +| n_updates | 86330 | +| policy_gradient_loss | -0.0582 | +| value_loss | 0.000418 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.53e+03 | +| ep_rew_mean | 0.0918 | +| time/ | | +| fps | 310 | +| iterations | 2582 | +| time_elapsed | 8511 | +| total_timesteps | 2643968 | +| train/ | | +| approx_kl | 1.64094 | +| clip_fraction | 0.441 | +| clip_range | 0.2 | +| entropy_loss | -0.365 | +| explained_variance | -3.11 | +| learning_rate | 0.0001 | +| loss | -0.0949 | +| n_updates | 86340 | +| policy_gradient_loss | -0.0608 | +| value_loss | 0.000456 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.53e+03 | +| ep_rew_mean | 0.0926 | +| time/ | | +| fps | 310 | +| iterations | 2583 | +| time_elapsed | 8515 | +| total_timesteps | 2644992 | +| train/ | | +| approx_kl | 1.6969984 | +| clip_fraction | 0.46 | +| clip_range | 0.2 | +| entropy_loss | -0.393 | +| explained_variance | -2.88 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 86350 | +| policy_gradient_loss | -0.0654 | +| value_loss | 0.000433 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.53e+03 | +| ep_rew_mean | 0.0926 | +| time/ | | +| fps | 310 | +| iterations | 2584 | +| time_elapsed | 8518 | +| total_timesteps | 2646016 | +| train/ | | +| approx_kl | 1.9881401 | +| clip_fraction | 0.446 | +| clip_range | 0.2 | +| entropy_loss | -0.323 | +| explained_variance | -2.23 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 86360 | +| policy_gradient_loss | -0.065 | +| value_loss | 0.000545 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.53e+03 | +| ep_rew_mean | 0.0952 | +| time/ | | +| fps | 310 | +| iterations | 2585 | +| time_elapsed | 8521 | +| total_timesteps | 2647040 | +| train/ | | +| approx_kl | 1.4943697 | +| clip_fraction | 0.476 | +| clip_range | 0.2 | +| entropy_loss | -0.41 | +| explained_variance | -1.39 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 86370 | +| policy_gradient_loss | -0.0637 | +| value_loss | 0.000647 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.54e+03 | +| ep_rew_mean | 0.0975 | +| time/ | | +| fps | 310 | +| iterations | 2586 | +| time_elapsed | 8525 | +| total_timesteps | 2648064 | +| train/ | | +| approx_kl | 1.2833784 | +| clip_fraction | 0.472 | +| clip_range | 0.2 | +| entropy_loss | -0.408 | +| explained_variance | -3.92 | +| learning_rate | 0.0001 | +| loss | -0.0773 | +| n_updates | 86380 | +| policy_gradient_loss | -0.0625 | +| value_loss | 0.000459 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.53e+03 | +| ep_rew_mean | 0.0948 | +| time/ | | +| fps | 310 | +| iterations | 2587 | +| time_elapsed | 8528 | +| total_timesteps | 2649088 | +| train/ | | +| approx_kl | 1.4698526 | +| clip_fraction | 0.499 | +| clip_range | 0.2 | +| entropy_loss | -0.483 | +| explained_variance | -0.809 | +| learning_rate | 0.0001 | +| loss | -0.0743 | +| n_updates | 86390 | +| policy_gradient_loss | -0.0592 | +| value_loss | 0.00048 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.53e+03 | +| ep_rew_mean | 0.0948 | +| time/ | | +| fps | 310 | +| iterations | 2588 | +| time_elapsed | 8532 | +| total_timesteps | 2650112 | +| train/ | | +| approx_kl | 1.679544 | +| clip_fraction | 0.453 | +| clip_range | 0.2 | +| entropy_loss | -0.378 | +| explained_variance | -0.604 | +| learning_rate | 0.0001 | +| loss | -0.0728 | +| n_updates | 86400 | +| policy_gradient_loss | -0.0606 | +| value_loss | 0.000651 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.53e+03 | +| ep_rew_mean | 0.0993 | +| time/ | | +| fps | 310 | +| iterations | 2589 | +| time_elapsed | 8535 | +| total_timesteps | 2651136 | +| train/ | | +| approx_kl | 1.7926674 | +| clip_fraction | 0.468 | +| clip_range | 0.2 | +| entropy_loss | -0.391 | +| explained_variance | -3.24 | +| learning_rate | 0.0001 | +| loss | -0.0866 | +| n_updates | 86410 | +| policy_gradient_loss | -0.0511 | +| value_loss | 0.000906 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.53e+03 | +| ep_rew_mean | 0.0993 | +| time/ | | +| fps | 310 | +| iterations | 2590 | +| time_elapsed | 8538 | +| total_timesteps | 2652160 | +| train/ | | +| approx_kl | 3.1035776 | +| clip_fraction | 0.467 | +| clip_range | 0.2 | +| entropy_loss | -0.375 | +| explained_variance | -1.36 | +| learning_rate | 0.0001 | +| loss | -0.0816 | +| n_updates | 86420 | +| policy_gradient_loss | -0.066 | +| value_loss | 0.000637 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.54e+03 | +| ep_rew_mean | 0.106 | +| time/ | | +| fps | 310 | +| iterations | 2591 | +| time_elapsed | 8541 | +| total_timesteps | 2653184 | +| train/ | | +| approx_kl | 1.9969385 | +| clip_fraction | 0.47 | +| clip_range | 0.2 | +| entropy_loss | -0.408 | +| explained_variance | -3.12 | +| learning_rate | 0.0001 | +| loss | -0.0749 | +| n_updates | 86430 | +| policy_gradient_loss | -0.0713 | +| value_loss | 0.000432 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.54e+03 | +| ep_rew_mean | 0.11 | +| time/ | | +| fps | 310 | +| iterations | 2592 | +| time_elapsed | 8545 | +| total_timesteps | 2654208 | +| train/ | | +| approx_kl | 1.5945656 | +| clip_fraction | 0.462 | +| clip_range | 0.2 | +| entropy_loss | -0.399 | +| explained_variance | -0.946 | +| learning_rate | 0.0001 | +| loss | -0.0669 | +| n_updates | 86440 | +| policy_gradient_loss | -0.0579 | +| value_loss | 0.000799 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.54e+03 | +| ep_rew_mean | 0.107 | +| time/ | | +| fps | 310 | +| iterations | 2593 | +| time_elapsed | 8548 | +| total_timesteps | 2655232 | +| train/ | | +| approx_kl | 2.146017 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.378 | +| explained_variance | -4.89 | +| learning_rate | 0.0001 | +| loss | -0.0576 | +| n_updates | 86450 | +| policy_gradient_loss | -0.0698 | +| value_loss | 0.000565 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.54e+03 | +| ep_rew_mean | 0.107 | +| time/ | | +| fps | 310 | +| iterations | 2594 | +| time_elapsed | 8551 | +| total_timesteps | 2656256 | +| train/ | | +| approx_kl | 2.5564425 | +| clip_fraction | 0.416 | +| clip_range | 0.2 | +| entropy_loss | -0.311 | +| explained_variance | -2.05 | +| learning_rate | 0.0001 | +| loss | -0.053 | +| n_updates | 86460 | +| policy_gradient_loss | -0.0607 | +| value_loss | 0.000479 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.54e+03 | +| ep_rew_mean | 0.107 | +| time/ | | +| fps | 310 | +| iterations | 2595 | +| time_elapsed | 8554 | +| total_timesteps | 2657280 | +| train/ | | +| approx_kl | 2.1693697 | +| clip_fraction | 0.476 | +| clip_range | 0.2 | +| entropy_loss | -0.384 | +| explained_variance | -1.16 | +| learning_rate | 0.0001 | +| loss | -0.0634 | +| n_updates | 86470 | +| policy_gradient_loss | -0.0595 | +| value_loss | 0.000349 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.55e+03 | +| ep_rew_mean | 0.106 | +| time/ | | +| fps | 310 | +| iterations | 2596 | +| time_elapsed | 8557 | +| total_timesteps | 2658304 | +| train/ | | +| approx_kl | 1.7513162 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.414 | +| explained_variance | -1.67 | +| learning_rate | 0.0001 | +| loss | -0.106 | +| n_updates | 86480 | +| policy_gradient_loss | -0.0706 | +| value_loss | 0.000395 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.55e+03 | +| ep_rew_mean | 0.106 | +| time/ | | +| fps | 310 | +| iterations | 2597 | +| time_elapsed | 8561 | +| total_timesteps | 2659328 | +| train/ | | +| approx_kl | 2.1098475 | +| clip_fraction | 0.448 | +| clip_range | 0.2 | +| entropy_loss | -0.369 | +| explained_variance | -1.61 | +| learning_rate | 0.0001 | +| loss | -0.113 | +| n_updates | 86490 | +| policy_gradient_loss | -0.0664 | +| value_loss | 0.000478 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.55e+03 | +| ep_rew_mean | 0.103 | +| time/ | | +| fps | 310 | +| iterations | 2598 | +| time_elapsed | 8564 | +| total_timesteps | 2660352 | +| train/ | | +| approx_kl | 1.6643353 | +| clip_fraction | 0.491 | +| clip_range | 0.2 | +| entropy_loss | -0.487 | +| explained_variance | -10.9 | +| learning_rate | 0.0001 | +| loss | -0.099 | +| n_updates | 86500 | +| policy_gradient_loss | -0.0667 | +| value_loss | 0.000267 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.55e+03 | +| ep_rew_mean | 0.103 | +| time/ | | +| fps | 310 | +| iterations | 2599 | +| time_elapsed | 8568 | +| total_timesteps | 2661376 | +| train/ | | +| approx_kl | 3.553286 | +| clip_fraction | 0.465 | +| clip_range | 0.2 | +| entropy_loss | -0.376 | +| explained_variance | -1.71 | +| learning_rate | 0.0001 | +| loss | -0.0755 | +| n_updates | 86510 | +| policy_gradient_loss | -0.0693 | +| value_loss | 0.000395 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.55e+03 | +| ep_rew_mean | 0.103 | +| time/ | | +| fps | 310 | +| iterations | 2600 | +| time_elapsed | 8571 | +| total_timesteps | 2662400 | +| train/ | | +| approx_kl | 1.9641405 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.408 | +| explained_variance | -1.45 | +| learning_rate | 0.0001 | +| loss | -0.0876 | +| n_updates | 86520 | +| policy_gradient_loss | -0.0668 | +| value_loss | 0.000432 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.55e+03 | +| ep_rew_mean | 0.0958 | +| time/ | | +| fps | 310 | +| iterations | 2601 | +| time_elapsed | 8574 | +| total_timesteps | 2663424 | +| train/ | | +| approx_kl | 1.5408304 | +| clip_fraction | 0.479 | +| clip_range | 0.2 | +| entropy_loss | -0.378 | +| explained_variance | -2.22 | +| learning_rate | 0.0001 | +| loss | -0.0408 | +| n_updates | 86530 | +| policy_gradient_loss | -0.0629 | +| value_loss | 0.000441 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.54e+03 | +| ep_rew_mean | 0.0955 | +| time/ | | +| fps | 310 | +| iterations | 2602 | +| time_elapsed | 8578 | +| total_timesteps | 2664448 | +| train/ | | +| approx_kl | 1.5094652 | +| clip_fraction | 0.427 | +| clip_range | 0.2 | +| entropy_loss | -0.364 | +| explained_variance | -1.23 | +| learning_rate | 0.0001 | +| loss | -0.0952 | +| n_updates | 86540 | +| policy_gradient_loss | -0.0643 | +| value_loss | 0.00065 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.54e+03 | +| ep_rew_mean | 0.0955 | +| time/ | | +| fps | 310 | +| iterations | 2603 | +| time_elapsed | 8581 | +| total_timesteps | 2665472 | +| train/ | | +| approx_kl | 2.041136 | +| clip_fraction | 0.439 | +| clip_range | 0.2 | +| entropy_loss | -0.338 | +| explained_variance | -1.93 | +| learning_rate | 0.0001 | +| loss | -0.0876 | +| n_updates | 86550 | +| policy_gradient_loss | -0.0528 | +| value_loss | 0.000597 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.55e+03 | +| ep_rew_mean | 0.102 | +| time/ | | +| fps | 310 | +| iterations | 2604 | +| time_elapsed | 8585 | +| total_timesteps | 2666496 | +| train/ | | +| approx_kl | 2.5247498 | +| clip_fraction | 0.447 | +| clip_range | 0.2 | +| entropy_loss | -0.338 | +| explained_variance | -0.891 | +| learning_rate | 0.0001 | +| loss | -0.0708 | +| n_updates | 86560 | +| policy_gradient_loss | -0.0586 | +| value_loss | 0.000628 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.55e+03 | +| ep_rew_mean | 0.102 | +| time/ | | +| fps | 310 | +| iterations | 2605 | +| time_elapsed | 8588 | +| total_timesteps | 2667520 | +| train/ | | +| approx_kl | 4.1064677 | +| clip_fraction | 0.445 | +| clip_range | 0.2 | +| entropy_loss | -0.375 | +| explained_variance | -1.41 | +| learning_rate | 0.0001 | +| loss | -0.0713 | +| n_updates | 86570 | +| policy_gradient_loss | -0.0592 | +| value_loss | 0.000615 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.55e+03 | +| ep_rew_mean | 0.102 | +| time/ | | +| fps | 310 | +| iterations | 2606 | +| time_elapsed | 8591 | +| total_timesteps | 2668544 | +| train/ | | +| approx_kl | 1.6293921 | +| clip_fraction | 0.451 | +| clip_range | 0.2 | +| entropy_loss | -0.342 | +| explained_variance | -3.85 | +| learning_rate | 0.0001 | +| loss | -0.0846 | +| n_updates | 86580 | +| policy_gradient_loss | -0.0646 | +| value_loss | 0.000532 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.55e+03 | +| ep_rew_mean | 0.102 | +| time/ | | +| fps | 310 | +| iterations | 2607 | +| time_elapsed | 8595 | +| total_timesteps | 2669568 | +| train/ | | +| approx_kl | 1.6551919 | +| clip_fraction | 0.488 | +| clip_range | 0.2 | +| entropy_loss | -0.425 | +| explained_variance | -1.33 | +| learning_rate | 0.0001 | +| loss | -0.08 | +| n_updates | 86590 | +| policy_gradient_loss | -0.0722 | +| value_loss | 0.000611 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.56e+03 | +| ep_rew_mean | 0.107 | +| time/ | | +| fps | 310 | +| iterations | 2608 | +| time_elapsed | 8598 | +| total_timesteps | 2670592 | +| train/ | | +| approx_kl | 1.6119319 | +| clip_fraction | 0.476 | +| clip_range | 0.2 | +| entropy_loss | -0.398 | +| explained_variance | -2.73 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 86600 | +| policy_gradient_loss | -0.0673 | +| value_loss | 0.000429 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.56e+03 | +| ep_rew_mean | 0.107 | +| time/ | | +| fps | 310 | +| iterations | 2609 | +| time_elapsed | 8601 | +| total_timesteps | 2671616 | +| train/ | | +| approx_kl | 10.139338 | +| clip_fraction | 0.464 | +| clip_range | 0.2 | +| entropy_loss | -0.352 | +| explained_variance | -0.753 | +| learning_rate | 0.0001 | +| loss | -0.0858 | +| n_updates | 86610 | +| policy_gradient_loss | -0.0658 | +| value_loss | 0.000548 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.57e+03 | +| ep_rew_mean | 0.112 | +| time/ | | +| fps | 310 | +| iterations | 2610 | +| time_elapsed | 8604 | +| total_timesteps | 2672640 | +| train/ | | +| approx_kl | 1.8589485 | +| clip_fraction | 0.484 | +| clip_range | 0.2 | +| entropy_loss | -0.409 | +| explained_variance | -2.06 | +| learning_rate | 0.0001 | +| loss | -0.0801 | +| n_updates | 86620 | +| policy_gradient_loss | -0.0707 | +| value_loss | 0.000671 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.57e+03 | +| ep_rew_mean | 0.113 | +| time/ | | +| fps | 310 | +| iterations | 2611 | +| time_elapsed | 8607 | +| total_timesteps | 2673664 | +| train/ | | +| approx_kl | 2.1781845 | +| clip_fraction | 0.465 | +| clip_range | 0.2 | +| entropy_loss | -0.374 | +| explained_variance | -3.29 | +| learning_rate | 0.0001 | +| loss | -0.114 | +| n_updates | 86630 | +| policy_gradient_loss | -0.0676 | +| value_loss | 0.000539 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.58e+03 | +| ep_rew_mean | 0.114 | +| time/ | | +| fps | 310 | +| iterations | 2612 | +| time_elapsed | 8611 | +| total_timesteps | 2674688 | +| train/ | | +| approx_kl | 2.2339764 | +| clip_fraction | 0.472 | +| clip_range | 0.2 | +| entropy_loss | -0.393 | +| explained_variance | -0.929 | +| learning_rate | 0.0001 | +| loss | -0.0965 | +| n_updates | 86640 | +| policy_gradient_loss | -0.0682 | +| value_loss | 0.000525 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.58e+03 | +| ep_rew_mean | 0.114 | +| time/ | | +| fps | 310 | +| iterations | 2613 | +| time_elapsed | 8614 | +| total_timesteps | 2675712 | +| train/ | | +| approx_kl | 1.5403097 | +| clip_fraction | 0.421 | +| clip_range | 0.2 | +| entropy_loss | -0.335 | +| explained_variance | -0.952 | +| learning_rate | 0.0001 | +| loss | -0.0826 | +| n_updates | 86650 | +| policy_gradient_loss | -0.068 | +| value_loss | 0.000544 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.57e+03 | +| ep_rew_mean | 0.115 | +| time/ | | +| fps | 310 | +| iterations | 2614 | +| time_elapsed | 8617 | +| total_timesteps | 2676736 | +| train/ | | +| approx_kl | 1.6735954 | +| clip_fraction | 0.466 | +| clip_range | 0.2 | +| entropy_loss | -0.377 | +| explained_variance | -2.27 | +| learning_rate | 0.0001 | +| loss | -0.0938 | +| n_updates | 86660 | +| policy_gradient_loss | -0.0631 | +| value_loss | 0.000412 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.57e+03 | +| ep_rew_mean | 0.115 | +| time/ | | +| fps | 310 | +| iterations | 2615 | +| time_elapsed | 8620 | +| total_timesteps | 2677760 | +| train/ | | +| approx_kl | 1.7098811 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.468 | +| explained_variance | -0.776 | +| learning_rate | 0.0001 | +| loss | -0.085 | +| n_updates | 86670 | +| policy_gradient_loss | -0.0681 | +| value_loss | 0.000303 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.57e+03 | +| ep_rew_mean | 0.115 | +| time/ | | +| fps | 310 | +| iterations | 2616 | +| time_elapsed | 8624 | +| total_timesteps | 2678784 | +| train/ | | +| approx_kl | 7.569064 | +| clip_fraction | 0.489 | +| clip_range | 0.2 | +| entropy_loss | -0.429 | +| explained_variance | -0.757 | +| learning_rate | 0.0001 | +| loss | -0.0784 | +| n_updates | 86680 | +| policy_gradient_loss | -0.0669 | +| value_loss | 0.000468 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | 0.116 | +| time/ | | +| fps | 310 | +| iterations | 2617 | +| time_elapsed | 8627 | +| total_timesteps | 2679808 | +| train/ | | +| approx_kl | 1.9411887 | +| clip_fraction | 0.456 | +| clip_range | 0.2 | +| entropy_loss | -0.35 | +| explained_variance | -2.66 | +| learning_rate | 0.0001 | +| loss | -0.0655 | +| n_updates | 86690 | +| policy_gradient_loss | -0.0692 | +| value_loss | 0.000639 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | 0.116 | +| time/ | | +| fps | 310 | +| iterations | 2618 | +| time_elapsed | 8631 | +| total_timesteps | 2680832 | +| train/ | | +| approx_kl | 1.9154168 | +| clip_fraction | 0.464 | +| clip_range | 0.2 | +| entropy_loss | -0.347 | +| explained_variance | -4.55 | +| learning_rate | 0.0001 | +| loss | -0.0681 | +| n_updates | 86700 | +| policy_gradient_loss | -0.072 | +| value_loss | 0.000417 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | 0.12 | +| time/ | | +| fps | 310 | +| iterations | 2619 | +| time_elapsed | 8634 | +| total_timesteps | 2681856 | +| train/ | | +| approx_kl | 1.5084763 | +| clip_fraction | 0.457 | +| clip_range | 0.2 | +| entropy_loss | -0.469 | +| explained_variance | -3.19 | +| learning_rate | 0.0001 | +| loss | -0.11 | +| n_updates | 86710 | +| policy_gradient_loss | -0.0627 | +| value_loss | 0.000391 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.61e+03 | +| ep_rew_mean | 0.125 | +| time/ | | +| fps | 310 | +| iterations | 2620 | +| time_elapsed | 8638 | +| total_timesteps | 2682880 | +| train/ | | +| approx_kl | 1.7454288 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.379 | +| explained_variance | -0.506 | +| learning_rate | 0.0001 | +| loss | -0.089 | +| n_updates | 86720 | +| policy_gradient_loss | -0.0677 | +| value_loss | 0.000451 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | 0.124 | +| time/ | | +| fps | 310 | +| iterations | 2621 | +| time_elapsed | 8641 | +| total_timesteps | 2683904 | +| train/ | | +| approx_kl | 1.6791754 | +| clip_fraction | 0.462 | +| clip_range | 0.2 | +| entropy_loss | -0.346 | +| explained_variance | -0.374 | +| learning_rate | 0.0001 | +| loss | -0.0641 | +| n_updates | 86730 | +| policy_gradient_loss | -0.0619 | +| value_loss | 0.000493 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | 0.123 | +| time/ | | +| fps | 310 | +| iterations | 2622 | +| time_elapsed | 8645 | +| total_timesteps | 2684928 | +| train/ | | +| approx_kl | 1.7562792 | +| clip_fraction | 0.415 | +| clip_range | 0.2 | +| entropy_loss | -0.348 | +| explained_variance | -0.994 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 86740 | +| policy_gradient_loss | -0.0617 | +| value_loss | 0.000611 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | 0.123 | +| time/ | | +| fps | 310 | +| iterations | 2623 | +| time_elapsed | 8648 | +| total_timesteps | 2685952 | +| train/ | | +| approx_kl | 1.9013 | +| clip_fraction | 0.427 | +| clip_range | 0.2 | +| entropy_loss | -0.346 | +| explained_variance | -1.93 | +| learning_rate | 0.0001 | +| loss | -0.0984 | +| n_updates | 86750 | +| policy_gradient_loss | -0.0598 | +| value_loss | 0.000509 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | 0.127 | +| time/ | | +| fps | 310 | +| iterations | 2624 | +| time_elapsed | 8652 | +| total_timesteps | 2686976 | +| train/ | | +| approx_kl | 1.547892 | +| clip_fraction | 0.438 | +| clip_range | 0.2 | +| entropy_loss | -0.363 | +| explained_variance | -1.46 | +| learning_rate | 0.0001 | +| loss | -0.07 | +| n_updates | 86760 | +| policy_gradient_loss | -0.0563 | +| value_loss | 0.000361 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | 0.123 | +| time/ | | +| fps | 310 | +| iterations | 2625 | +| time_elapsed | 8655 | +| total_timesteps | 2688000 | +| train/ | | +| approx_kl | 1.7974505 | +| clip_fraction | 0.435 | +| clip_range | 0.2 | +| entropy_loss | -0.337 | +| explained_variance | -0.734 | +| learning_rate | 0.0001 | +| loss | -0.105 | +| n_updates | 86770 | +| policy_gradient_loss | -0.0625 | +| value_loss | 0.000515 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | 0.124 | +| time/ | | +| fps | 310 | +| iterations | 2626 | +| time_elapsed | 8658 | +| total_timesteps | 2689024 | +| train/ | | +| approx_kl | 1.6114607 | +| clip_fraction | 0.449 | +| clip_range | 0.2 | +| entropy_loss | -0.383 | +| explained_variance | -1.02 | +| learning_rate | 0.0001 | +| loss | -0.0378 | +| n_updates | 86780 | +| policy_gradient_loss | -0.0641 | +| value_loss | 0.000492 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | 0.124 | +| time/ | | +| fps | 310 | +| iterations | 2627 | +| time_elapsed | 8661 | +| total_timesteps | 2690048 | +| train/ | | +| approx_kl | 1.7486905 | +| clip_fraction | 0.446 | +| clip_range | 0.2 | +| entropy_loss | -0.405 | +| explained_variance | -1.86 | +| learning_rate | 0.0001 | +| loss | -0.0824 | +| n_updates | 86790 | +| policy_gradient_loss | -0.0585 | +| value_loss | 0.000509 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | 0.126 | +| time/ | | +| fps | 310 | +| iterations | 2628 | +| time_elapsed | 8664 | +| total_timesteps | 2691072 | +| train/ | | +| approx_kl | 1.3247848 | +| clip_fraction | 0.445 | +| clip_range | 0.2 | +| entropy_loss | -0.382 | +| explained_variance | -3.59 | +| learning_rate | 0.0001 | +| loss | -0.0858 | +| n_updates | 86800 | +| policy_gradient_loss | -0.0588 | +| value_loss | 0.000578 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.58e+03 | +| ep_rew_mean | 0.121 | +| time/ | | +| fps | 310 | +| iterations | 2629 | +| time_elapsed | 8668 | +| total_timesteps | 2692096 | +| train/ | | +| approx_kl | 1.621738 | +| clip_fraction | 0.446 | +| clip_range | 0.2 | +| entropy_loss | -0.372 | +| explained_variance | -1.96 | +| learning_rate | 0.0001 | +| loss | -0.0717 | +| n_updates | 86810 | +| policy_gradient_loss | -0.0611 | +| value_loss | 0.0007 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.58e+03 | +| ep_rew_mean | 0.121 | +| time/ | | +| fps | 310 | +| iterations | 2630 | +| time_elapsed | 8671 | +| total_timesteps | 2693120 | +| train/ | | +| approx_kl | 2.1020484 | +| clip_fraction | 0.423 | +| clip_range | 0.2 | +| entropy_loss | -0.319 | +| explained_variance | -1.89 | +| learning_rate | 0.0001 | +| loss | -0.0829 | +| n_updates | 86820 | +| policy_gradient_loss | -0.0628 | +| value_loss | 0.000666 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | 0.121 | +| time/ | | +| fps | 310 | +| iterations | 2631 | +| time_elapsed | 8674 | +| total_timesteps | 2694144 | +| train/ | | +| approx_kl | 1.58583 | +| clip_fraction | 0.452 | +| clip_range | 0.2 | +| entropy_loss | -0.365 | +| explained_variance | -2.03 | +| learning_rate | 0.0001 | +| loss | -0.0734 | +| n_updates | 86830 | +| policy_gradient_loss | -0.0514 | +| value_loss | 0.000551 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | 0.121 | +| time/ | | +| fps | 310 | +| iterations | 2632 | +| time_elapsed | 8677 | +| total_timesteps | 2695168 | +| train/ | | +| approx_kl | 1.379908 | +| clip_fraction | 0.451 | +| clip_range | 0.2 | +| entropy_loss | -0.381 | +| explained_variance | -4.54 | +| learning_rate | 0.0001 | +| loss | -0.0914 | +| n_updates | 86840 | +| policy_gradient_loss | -0.0664 | +| value_loss | 0.000315 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.58e+03 | +| ep_rew_mean | 0.12 | +| time/ | | +| fps | 310 | +| iterations | 2633 | +| time_elapsed | 8681 | +| total_timesteps | 2696192 | +| train/ | | +| approx_kl | 1.9885831 | +| clip_fraction | 0.46 | +| clip_range | 0.2 | +| entropy_loss | -0.411 | +| explained_variance | -1.18 | +| learning_rate | 0.0001 | +| loss | -0.105 | +| n_updates | 86850 | +| policy_gradient_loss | -0.0608 | +| value_loss | 0.000345 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.57e+03 | +| ep_rew_mean | 0.117 | +| time/ | | +| fps | 310 | +| iterations | 2634 | +| time_elapsed | 8684 | +| total_timesteps | 2697216 | +| train/ | | +| approx_kl | 2.4722383 | +| clip_fraction | 0.436 | +| clip_range | 0.2 | +| entropy_loss | -0.36 | +| explained_variance | -0.945 | +| learning_rate | 0.0001 | +| loss | -0.0576 | +| n_updates | 86860 | +| policy_gradient_loss | -0.0604 | +| value_loss | 0.000494 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.57e+03 | +| ep_rew_mean | 0.122 | +| time/ | | +| fps | 310 | +| iterations | 2635 | +| time_elapsed | 8687 | +| total_timesteps | 2698240 | +| train/ | | +| approx_kl | 2.0754018 | +| clip_fraction | 0.462 | +| clip_range | 0.2 | +| entropy_loss | -0.354 | +| explained_variance | -1.55 | +| learning_rate | 0.0001 | +| loss | -0.0791 | +| n_updates | 86870 | +| policy_gradient_loss | -0.0654 | +| value_loss | 0.000562 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.57e+03 | +| ep_rew_mean | 0.122 | +| time/ | | +| fps | 310 | +| iterations | 2636 | +| time_elapsed | 8691 | +| total_timesteps | 2699264 | +| train/ | | +| approx_kl | 1.908173 | +| clip_fraction | 0.45 | +| clip_range | 0.2 | +| entropy_loss | -0.347 | +| explained_variance | -3.19 | +| learning_rate | 0.0001 | +| loss | -0.0977 | +| n_updates | 86880 | +| policy_gradient_loss | -0.0622 | +| value_loss | 0.000527 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.58e+03 | +| ep_rew_mean | 0.12 | +| time/ | | +| fps | 310 | +| iterations | 2637 | +| time_elapsed | 8694 | +| total_timesteps | 2700288 | +| train/ | | +| approx_kl | 2.1306493 | +| clip_fraction | 0.456 | +| clip_range | 0.2 | +| entropy_loss | -0.395 | +| explained_variance | -2.39 | +| learning_rate | 0.0001 | +| loss | -0.0851 | +| n_updates | 86890 | +| policy_gradient_loss | -0.0678 | +| value_loss | 0.000378 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.58e+03 | +| ep_rew_mean | 0.12 | +| time/ | | +| fps | 310 | +| iterations | 2638 | +| time_elapsed | 8698 | +| total_timesteps | 2701312 | +| train/ | | +| approx_kl | 2.0395784 | +| clip_fraction | 0.469 | +| clip_range | 0.2 | +| entropy_loss | -0.375 | +| explained_variance | -1.31 | +| learning_rate | 0.0001 | +| loss | -0.0723 | +| n_updates | 86900 | +| policy_gradient_loss | -0.0565 | +| value_loss | 0.000484 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | 0.123 | +| time/ | | +| fps | 310 | +| iterations | 2639 | +| time_elapsed | 8701 | +| total_timesteps | 2702336 | +| train/ | | +| approx_kl | 2.1082397 | +| clip_fraction | 0.457 | +| clip_range | 0.2 | +| entropy_loss | -0.427 | +| explained_variance | -3.74 | +| learning_rate | 0.0001 | +| loss | -0.0987 | +| n_updates | 86910 | +| policy_gradient_loss | -0.0615 | +| value_loss | 0.00061 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | 0.123 | +| time/ | | +| fps | 310 | +| iterations | 2640 | +| time_elapsed | 8704 | +| total_timesteps | 2703360 | +| train/ | | +| approx_kl | 2.7530174 | +| clip_fraction | 0.518 | +| clip_range | 0.2 | +| entropy_loss | -0.392 | +| explained_variance | -2.18 | +| learning_rate | 0.0001 | +| loss | -0.0279 | +| n_updates | 86920 | +| policy_gradient_loss | -0.0534 | +| value_loss | 0.000463 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | 0.123 | +| time/ | | +| fps | 310 | +| iterations | 2641 | +| time_elapsed | 8708 | +| total_timesteps | 2704384 | +| train/ | | +| approx_kl | 1.6354587 | +| clip_fraction | 0.438 | +| clip_range | 0.2 | +| entropy_loss | -0.366 | +| explained_variance | -0.511 | +| learning_rate | 0.0001 | +| loss | -0.0459 | +| n_updates | 86930 | +| policy_gradient_loss | -0.0506 | +| value_loss | 0.000465 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | 0.125 | +| time/ | | +| fps | 310 | +| iterations | 2642 | +| time_elapsed | 8711 | +| total_timesteps | 2705408 | +| train/ | | +| approx_kl | 1.6750729 | +| clip_fraction | 0.464 | +| clip_range | 0.2 | +| entropy_loss | -0.375 | +| explained_variance | -3.45 | +| learning_rate | 0.0001 | +| loss | -0.0731 | +| n_updates | 86940 | +| policy_gradient_loss | -0.0629 | +| value_loss | 0.000388 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | 0.125 | +| time/ | | +| fps | 310 | +| iterations | 2643 | +| time_elapsed | 8714 | +| total_timesteps | 2706432 | +| train/ | | +| approx_kl | 1.66832 | +| clip_fraction | 0.468 | +| clip_range | 0.2 | +| entropy_loss | -0.404 | +| explained_variance | -1.47 | +| learning_rate | 0.0001 | +| loss | -0.0967 | +| n_updates | 86950 | +| policy_gradient_loss | -0.0664 | +| value_loss | 0.000624 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.61e+03 | +| ep_rew_mean | 0.132 | +| time/ | | +| fps | 310 | +| iterations | 2644 | +| time_elapsed | 8717 | +| total_timesteps | 2707456 | +| train/ | | +| approx_kl | 1.5808864 | +| clip_fraction | 0.437 | +| clip_range | 0.2 | +| entropy_loss | -0.356 | +| explained_variance | -1.47 | +| learning_rate | 0.0001 | +| loss | -0.0818 | +| n_updates | 86960 | +| policy_gradient_loss | -0.0641 | +| value_loss | 0.000597 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.61e+03 | +| ep_rew_mean | 0.132 | +| time/ | | +| fps | 310 | +| iterations | 2645 | +| time_elapsed | 8721 | +| total_timesteps | 2708480 | +| train/ | | +| approx_kl | 1.588631 | +| clip_fraction | 0.469 | +| clip_range | 0.2 | +| entropy_loss | -0.396 | +| explained_variance | -3.1 | +| learning_rate | 0.0001 | +| loss | -0.0758 | +| n_updates | 86970 | +| policy_gradient_loss | -0.0689 | +| value_loss | 0.000499 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.62e+03 | +| ep_rew_mean | 0.137 | +| time/ | | +| fps | 310 | +| iterations | 2646 | +| time_elapsed | 8724 | +| total_timesteps | 2709504 | +| train/ | | +| approx_kl | 1.447474 | +| clip_fraction | 0.497 | +| clip_range | 0.2 | +| entropy_loss | -0.498 | +| explained_variance | -1.75 | +| learning_rate | 0.0001 | +| loss | -0.0736 | +| n_updates | 86980 | +| policy_gradient_loss | -0.0654 | +| value_loss | 0.00055 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.62e+03 | +| ep_rew_mean | 0.139 | +| time/ | | +| fps | 310 | +| iterations | 2647 | +| time_elapsed | 8727 | +| total_timesteps | 2710528 | +| train/ | | +| approx_kl | 1.8415854 | +| clip_fraction | 0.468 | +| clip_range | 0.2 | +| entropy_loss | -0.388 | +| explained_variance | -5.54 | +| learning_rate | 0.0001 | +| loss | -0.105 | +| n_updates | 86990 | +| policy_gradient_loss | -0.064 | +| value_loss | 0.000564 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.62e+03 | +| ep_rew_mean | 0.139 | +| time/ | | +| fps | 310 | +| iterations | 2648 | +| time_elapsed | 8730 | +| total_timesteps | 2711552 | +| train/ | | +| approx_kl | 1.9432217 | +| clip_fraction | 0.465 | +| clip_range | 0.2 | +| entropy_loss | -0.421 | +| explained_variance | -1.21 | +| learning_rate | 0.0001 | +| loss | -0.076 | +| n_updates | 87000 | +| policy_gradient_loss | -0.0621 | +| value_loss | 0.000662 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.62e+03 | +| ep_rew_mean | 0.137 | +| time/ | | +| fps | 310 | +| iterations | 2649 | +| time_elapsed | 8733 | +| total_timesteps | 2712576 | +| train/ | | +| approx_kl | 1.5540323 | +| clip_fraction | 0.438 | +| clip_range | 0.2 | +| entropy_loss | -0.363 | +| explained_variance | -6.66 | +| learning_rate | 0.0001 | +| loss | -0.0886 | +| n_updates | 87010 | +| policy_gradient_loss | -0.0597 | +| value_loss | 0.000261 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.62e+03 | +| ep_rew_mean | 0.137 | +| time/ | | +| fps | 310 | +| iterations | 2650 | +| time_elapsed | 8736 | +| total_timesteps | 2713600 | +| train/ | | +| approx_kl | 4.7513022 | +| clip_fraction | 0.407 | +| clip_range | 0.2 | +| entropy_loss | -0.339 | +| explained_variance | -0.39 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 87020 | +| policy_gradient_loss | -0.0546 | +| value_loss | 0.000489 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.62e+03 | +| ep_rew_mean | 0.137 | +| time/ | | +| fps | 310 | +| iterations | 2651 | +| time_elapsed | 8740 | +| total_timesteps | 2714624 | +| train/ | | +| approx_kl | 1.4505138 | +| clip_fraction | 0.497 | +| clip_range | 0.2 | +| entropy_loss | -0.477 | +| explained_variance | -2.12 | +| learning_rate | 0.0001 | +| loss | -0.0823 | +| n_updates | 87030 | +| policy_gradient_loss | -0.0699 | +| value_loss | 0.000438 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.63e+03 | +| ep_rew_mean | 0.14 | +| time/ | | +| fps | 310 | +| iterations | 2652 | +| time_elapsed | 8743 | +| total_timesteps | 2715648 | +| train/ | | +| approx_kl | 1.6686459 | +| clip_fraction | 0.451 | +| clip_range | 0.2 | +| entropy_loss | -0.398 | +| explained_variance | -1.61 | +| learning_rate | 0.0001 | +| loss | -0.0959 | +| n_updates | 87040 | +| policy_gradient_loss | -0.0546 | +| value_loss | 0.000493 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.62e+03 | +| ep_rew_mean | 0.144 | +| time/ | | +| fps | 310 | +| iterations | 2653 | +| time_elapsed | 8747 | +| total_timesteps | 2716672 | +| train/ | | +| approx_kl | 1.7892345 | +| clip_fraction | 0.466 | +| clip_range | 0.2 | +| entropy_loss | -0.345 | +| explained_variance | -1.14 | +| learning_rate | 0.0001 | +| loss | -0.0972 | +| n_updates | 87050 | +| policy_gradient_loss | -0.0671 | +| value_loss | 0.000428 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.61e+03 | +| ep_rew_mean | 0.14 | +| time/ | | +| fps | 310 | +| iterations | 2654 | +| time_elapsed | 8750 | +| total_timesteps | 2717696 | +| train/ | | +| approx_kl | 1.6598263 | +| clip_fraction | 0.472 | +| clip_range | 0.2 | +| entropy_loss | -0.426 | +| explained_variance | -0.719 | +| learning_rate | 0.0001 | +| loss | -0.0131 | +| n_updates | 87060 | +| policy_gradient_loss | -0.053 | +| value_loss | 0.000586 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.61e+03 | +| ep_rew_mean | 0.14 | +| time/ | | +| fps | 310 | +| iterations | 2655 | +| time_elapsed | 8754 | +| total_timesteps | 2718720 | +| train/ | | +| approx_kl | 1.4968078 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.43 | +| explained_variance | -1.59 | +| learning_rate | 0.0001 | +| loss | -0.0949 | +| n_updates | 87070 | +| policy_gradient_loss | -0.0667 | +| value_loss | 0.000546 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | 0.139 | +| time/ | | +| fps | 310 | +| iterations | 2656 | +| time_elapsed | 8757 | +| total_timesteps | 2719744 | +| train/ | | +| approx_kl | 1.611424 | +| clip_fraction | 0.477 | +| clip_range | 0.2 | +| entropy_loss | -0.399 | +| explained_variance | -2.78 | +| learning_rate | 0.0001 | +| loss | -0.0897 | +| n_updates | 87080 | +| policy_gradient_loss | -0.0627 | +| value_loss | 0.000328 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | 0.139 | +| time/ | | +| fps | 310 | +| iterations | 2657 | +| time_elapsed | 8761 | +| total_timesteps | 2720768 | +| train/ | | +| approx_kl | 1.6161705 | +| clip_fraction | 0.497 | +| clip_range | 0.2 | +| entropy_loss | -0.474 | +| explained_variance | -1.04 | +| learning_rate | 0.0001 | +| loss | -0.0873 | +| n_updates | 87090 | +| policy_gradient_loss | -0.0564 | +| value_loss | 0.00042 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.61e+03 | +| ep_rew_mean | 0.146 | +| time/ | | +| fps | 310 | +| iterations | 2658 | +| time_elapsed | 8764 | +| total_timesteps | 2721792 | +| train/ | | +| approx_kl | 1.7882556 | +| clip_fraction | 0.458 | +| clip_range | 0.2 | +| entropy_loss | -0.365 | +| explained_variance | -2.28 | +| learning_rate | 0.0001 | +| loss | -0.0845 | +| n_updates | 87100 | +| policy_gradient_loss | -0.0646 | +| value_loss | 0.000564 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.61e+03 | +| ep_rew_mean | 0.145 | +| time/ | | +| fps | 310 | +| iterations | 2659 | +| time_elapsed | 8767 | +| total_timesteps | 2722816 | +| train/ | | +| approx_kl | 1.9499155 | +| clip_fraction | 0.458 | +| clip_range | 0.2 | +| entropy_loss | -0.356 | +| explained_variance | -8.12 | +| learning_rate | 0.0001 | +| loss | -0.0838 | +| n_updates | 87110 | +| policy_gradient_loss | -0.0686 | +| value_loss | 0.000429 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.61e+03 | +| ep_rew_mean | 0.143 | +| time/ | | +| fps | 310 | +| iterations | 2660 | +| time_elapsed | 8771 | +| total_timesteps | 2723840 | +| train/ | | +| approx_kl | 1.9145784 | +| clip_fraction | 0.443 | +| clip_range | 0.2 | +| entropy_loss | -0.367 | +| explained_variance | -2.11 | +| learning_rate | 0.0001 | +| loss | -0.0679 | +| n_updates | 87120 | +| policy_gradient_loss | -0.0627 | +| value_loss | 0.00063 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | 0.133 | +| time/ | | +| fps | 310 | +| iterations | 2661 | +| time_elapsed | 8774 | +| total_timesteps | 2724864 | +| train/ | | +| approx_kl | 2.0237613 | +| clip_fraction | 0.441 | +| clip_range | 0.2 | +| entropy_loss | -0.349 | +| explained_variance | -1.93 | +| learning_rate | 0.0001 | +| loss | -0.0914 | +| n_updates | 87130 | +| policy_gradient_loss | -0.0625 | +| value_loss | 0.000638 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | 0.133 | +| time/ | | +| fps | 310 | +| iterations | 2662 | +| time_elapsed | 8777 | +| total_timesteps | 2725888 | +| train/ | | +| approx_kl | 1.3745549 | +| clip_fraction | 0.433 | +| clip_range | 0.2 | +| entropy_loss | -0.392 | +| explained_variance | -0.921 | +| learning_rate | 0.0001 | +| loss | -0.0863 | +| n_updates | 87140 | +| policy_gradient_loss | -0.0596 | +| value_loss | 0.000514 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | 0.133 | +| time/ | | +| fps | 310 | +| iterations | 2663 | +| time_elapsed | 8780 | +| total_timesteps | 2726912 | +| train/ | | +| approx_kl | 1.8660488 | +| clip_fraction | 0.435 | +| clip_range | 0.2 | +| entropy_loss | -0.357 | +| explained_variance | -0.688 | +| learning_rate | 0.0001 | +| loss | -0.0864 | +| n_updates | 87150 | +| policy_gradient_loss | -0.0614 | +| value_loss | 0.000477 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.61e+03 | +| ep_rew_mean | 0.135 | +| time/ | | +| fps | 310 | +| iterations | 2664 | +| time_elapsed | 8783 | +| total_timesteps | 2727936 | +| train/ | | +| approx_kl | 3.0109096 | +| clip_fraction | 0.472 | +| clip_range | 0.2 | +| entropy_loss | -0.37 | +| explained_variance | -3.32 | +| learning_rate | 0.0001 | +| loss | -0.113 | +| n_updates | 87160 | +| policy_gradient_loss | -0.0721 | +| value_loss | 0.000445 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.61e+03 | +| ep_rew_mean | 0.14 | +| time/ | | +| fps | 310 | +| iterations | 2665 | +| time_elapsed | 8787 | +| total_timesteps | 2728960 | +| train/ | | +| approx_kl | 1.72559 | +| clip_fraction | 0.464 | +| clip_range | 0.2 | +| entropy_loss | -0.389 | +| explained_variance | -0.973 | +| learning_rate | 0.0001 | +| loss | -0.0867 | +| n_updates | 87170 | +| policy_gradient_loss | -0.0651 | +| value_loss | 0.000499 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.61e+03 | +| ep_rew_mean | 0.137 | +| time/ | | +| fps | 310 | +| iterations | 2666 | +| time_elapsed | 8790 | +| total_timesteps | 2729984 | +| train/ | | +| approx_kl | 1.958463 | +| clip_fraction | 0.467 | +| clip_range | 0.2 | +| entropy_loss | -0.375 | +| explained_variance | -2.96 | +| learning_rate | 0.0001 | +| loss | -0.106 | +| n_updates | 87180 | +| policy_gradient_loss | -0.0659 | +| value_loss | 0.000376 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.61e+03 | +| ep_rew_mean | 0.137 | +| time/ | | +| fps | 310 | +| iterations | 2667 | +| time_elapsed | 8793 | +| total_timesteps | 2731008 | +| train/ | | +| approx_kl | 1.4433048 | +| clip_fraction | 0.436 | +| clip_range | 0.2 | +| entropy_loss | -0.365 | +| explained_variance | -1.34 | +| learning_rate | 0.0001 | +| loss | -0.0941 | +| n_updates | 87190 | +| policy_gradient_loss | -0.0528 | +| value_loss | 0.000579 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.61e+03 | +| ep_rew_mean | 0.139 | +| time/ | | +| fps | 310 | +| iterations | 2668 | +| time_elapsed | 8796 | +| total_timesteps | 2732032 | +| train/ | | +| approx_kl | 1.7653894 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.395 | +| explained_variance | -1.29 | +| learning_rate | 0.0001 | +| loss | -0.0734 | +| n_updates | 87200 | +| policy_gradient_loss | -0.0686 | +| value_loss | 0.000494 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.61e+03 | +| ep_rew_mean | 0.139 | +| time/ | | +| fps | 310 | +| iterations | 2669 | +| time_elapsed | 8799 | +| total_timesteps | 2733056 | +| train/ | | +| approx_kl | 2.8306055 | +| clip_fraction | 0.449 | +| clip_range | 0.2 | +| entropy_loss | -0.388 | +| explained_variance | -3.69 | +| learning_rate | 0.0001 | +| loss | -0.0859 | +| n_updates | 87210 | +| policy_gradient_loss | -0.0651 | +| value_loss | 0.000492 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.61e+03 | +| ep_rew_mean | 0.144 | +| time/ | | +| fps | 310 | +| iterations | 2670 | +| time_elapsed | 8803 | +| total_timesteps | 2734080 | +| train/ | | +| approx_kl | 1.7514749 | +| clip_fraction | 0.496 | +| clip_range | 0.2 | +| entropy_loss | -0.459 | +| explained_variance | -1.31 | +| learning_rate | 0.0001 | +| loss | -0.106 | +| n_updates | 87220 | +| policy_gradient_loss | -0.0656 | +| value_loss | 0.000302 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.61e+03 | +| ep_rew_mean | 0.144 | +| time/ | | +| fps | 310 | +| iterations | 2671 | +| time_elapsed | 8806 | +| total_timesteps | 2735104 | +| train/ | | +| approx_kl | 1.6711917 | +| clip_fraction | 0.474 | +| clip_range | 0.2 | +| entropy_loss | -0.433 | +| explained_variance | -0.873 | +| learning_rate | 0.0001 | +| loss | -0.087 | +| n_updates | 87230 | +| policy_gradient_loss | -0.0635 | +| value_loss | 0.000413 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.62e+03 | +| ep_rew_mean | 0.146 | +| time/ | | +| fps | 310 | +| iterations | 2672 | +| time_elapsed | 8809 | +| total_timesteps | 2736128 | +| train/ | | +| approx_kl | 1.560349 | +| clip_fraction | 0.489 | +| clip_range | 0.2 | +| entropy_loss | -0.433 | +| explained_variance | -1.7 | +| learning_rate | 0.0001 | +| loss | -0.0911 | +| n_updates | 87240 | +| policy_gradient_loss | -0.0629 | +| value_loss | 0.000367 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.62e+03 | +| ep_rew_mean | 0.146 | +| time/ | | +| fps | 310 | +| iterations | 2673 | +| time_elapsed | 8813 | +| total_timesteps | 2737152 | +| train/ | | +| approx_kl | 3.1279058 | +| clip_fraction | 0.469 | +| clip_range | 0.2 | +| entropy_loss | -0.346 | +| explained_variance | -0.794 | +| learning_rate | 0.0001 | +| loss | -0.0758 | +| n_updates | 87250 | +| policy_gradient_loss | -0.0555 | +| value_loss | 0.00045 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.63e+03 | +| ep_rew_mean | 0.141 | +| time/ | | +| fps | 310 | +| iterations | 2674 | +| time_elapsed | 8816 | +| total_timesteps | 2738176 | +| train/ | | +| approx_kl | 1.7673054 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.386 | +| explained_variance | -2.79 | +| learning_rate | 0.0001 | +| loss | -0.105 | +| n_updates | 87260 | +| policy_gradient_loss | -0.0707 | +| value_loss | 0.000486 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.63e+03 | +| ep_rew_mean | 0.141 | +| time/ | | +| fps | 310 | +| iterations | 2675 | +| time_elapsed | 8819 | +| total_timesteps | 2739200 | +| train/ | | +| approx_kl | 1.6622705 | +| clip_fraction | 0.455 | +| clip_range | 0.2 | +| entropy_loss | -0.37 | +| explained_variance | -2.78 | +| learning_rate | 0.0001 | +| loss | -0.0979 | +| n_updates | 87270 | +| policy_gradient_loss | -0.0619 | +| value_loss | 0.00041 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.65e+03 | +| ep_rew_mean | 0.146 | +| time/ | | +| fps | 310 | +| iterations | 2676 | +| time_elapsed | 8823 | +| total_timesteps | 2740224 | +| train/ | | +| approx_kl | 1.6670084 | +| clip_fraction | 0.454 | +| clip_range | 0.2 | +| entropy_loss | -0.416 | +| explained_variance | -1.71 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 87280 | +| policy_gradient_loss | -0.0448 | +| value_loss | 0.000417 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.65e+03 | +| ep_rew_mean | 0.146 | +| time/ | | +| fps | 310 | +| iterations | 2677 | +| time_elapsed | 8826 | +| total_timesteps | 2741248 | +| train/ | | +| approx_kl | 1.4004012 | +| clip_fraction | 0.456 | +| clip_range | 0.2 | +| entropy_loss | -0.378 | +| explained_variance | -0.214 | +| learning_rate | 0.0001 | +| loss | -0.0805 | +| n_updates | 87290 | +| policy_gradient_loss | -0.0598 | +| value_loss | 0.000554 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.64e+03 | +| ep_rew_mean | 0.147 | +| time/ | | +| fps | 310 | +| iterations | 2678 | +| time_elapsed | 8829 | +| total_timesteps | 2742272 | +| train/ | | +| approx_kl | 1.601798 | +| clip_fraction | 0.446 | +| clip_range | 0.2 | +| entropy_loss | -0.393 | +| explained_variance | -1.22 | +| learning_rate | 0.0001 | +| loss | -0.0983 | +| n_updates | 87300 | +| policy_gradient_loss | -0.0664 | +| value_loss | 0.000536 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.63e+03 | +| ep_rew_mean | 0.144 | +| time/ | | +| fps | 310 | +| iterations | 2679 | +| time_elapsed | 8832 | +| total_timesteps | 2743296 | +| train/ | | +| approx_kl | 1.8203323 | +| clip_fraction | 0.446 | +| clip_range | 0.2 | +| entropy_loss | -0.389 | +| explained_variance | -1.09 | +| learning_rate | 0.0001 | +| loss | -0.0836 | +| n_updates | 87310 | +| policy_gradient_loss | -0.0662 | +| value_loss | 0.000441 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.63e+03 | +| ep_rew_mean | 0.144 | +| time/ | | +| fps | 310 | +| iterations | 2680 | +| time_elapsed | 8836 | +| total_timesteps | 2744320 | +| train/ | | +| approx_kl | 1.3983047 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.5 | +| explained_variance | -2.8 | +| learning_rate | 0.0001 | +| loss | -0.076 | +| n_updates | 87320 | +| policy_gradient_loss | -0.0593 | +| value_loss | 0.000364 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.62e+03 | +| ep_rew_mean | 0.144 | +| time/ | | +| fps | 310 | +| iterations | 2681 | +| time_elapsed | 8839 | +| total_timesteps | 2745344 | +| train/ | | +| approx_kl | 1.8405252 | +| clip_fraction | 0.467 | +| clip_range | 0.2 | +| entropy_loss | -0.37 | +| explained_variance | -0.699 | +| learning_rate | 0.0001 | +| loss | -0.085 | +| n_updates | 87330 | +| policy_gradient_loss | -0.0641 | +| value_loss | 0.000506 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.62e+03 | +| ep_rew_mean | 0.141 | +| time/ | | +| fps | 310 | +| iterations | 2682 | +| time_elapsed | 8842 | +| total_timesteps | 2746368 | +| train/ | | +| approx_kl | 1.5359782 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.455 | +| explained_variance | -1.79 | +| learning_rate | 0.0001 | +| loss | -0.077 | +| n_updates | 87340 | +| policy_gradient_loss | -0.0613 | +| value_loss | 0.000515 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.62e+03 | +| ep_rew_mean | 0.141 | +| time/ | | +| fps | 310 | +| iterations | 2683 | +| time_elapsed | 8845 | +| total_timesteps | 2747392 | +| train/ | | +| approx_kl | 1.4403871 | +| clip_fraction | 0.441 | +| clip_range | 0.2 | +| entropy_loss | -0.393 | +| explained_variance | -2.11 | +| learning_rate | 0.0001 | +| loss | -0.0891 | +| n_updates | 87350 | +| policy_gradient_loss | -0.0689 | +| value_loss | 0.000764 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.62e+03 | +| ep_rew_mean | 0.14 | +| time/ | | +| fps | 310 | +| iterations | 2684 | +| time_elapsed | 8848 | +| total_timesteps | 2748416 | +| train/ | | +| approx_kl | 2.0438676 | +| clip_fraction | 0.446 | +| clip_range | 0.2 | +| entropy_loss | -0.417 | +| explained_variance | -2.26 | +| learning_rate | 0.0001 | +| loss | -0.108 | +| n_updates | 87360 | +| policy_gradient_loss | -0.0675 | +| value_loss | 0.000373 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.62e+03 | +| ep_rew_mean | 0.137 | +| time/ | | +| fps | 310 | +| iterations | 2685 | +| time_elapsed | 8852 | +| total_timesteps | 2749440 | +| train/ | | +| approx_kl | 1.378397 | +| clip_fraction | 0.436 | +| clip_range | 0.2 | +| entropy_loss | -0.401 | +| explained_variance | -1.44 | +| learning_rate | 0.0001 | +| loss | -0.0896 | +| n_updates | 87370 | +| policy_gradient_loss | -0.0631 | +| value_loss | 0.000494 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.63e+03 | +| ep_rew_mean | 0.141 | +| time/ | | +| fps | 310 | +| iterations | 2686 | +| time_elapsed | 8855 | +| total_timesteps | 2750464 | +| train/ | | +| approx_kl | 2.0680275 | +| clip_fraction | 0.446 | +| clip_range | 0.2 | +| entropy_loss | -0.329 | +| explained_variance | -1.21 | +| learning_rate | 0.0001 | +| loss | -0.0903 | +| n_updates | 87380 | +| policy_gradient_loss | -0.0712 | +| value_loss | 0.000475 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.63e+03 | +| ep_rew_mean | 0.141 | +| time/ | | +| fps | 310 | +| iterations | 2687 | +| time_elapsed | 8858 | +| total_timesteps | 2751488 | +| train/ | | +| approx_kl | 1.9880245 | +| clip_fraction | 0.431 | +| clip_range | 0.2 | +| entropy_loss | -0.348 | +| explained_variance | -1.75 | +| learning_rate | 0.0001 | +| loss | -0.0966 | +| n_updates | 87390 | +| policy_gradient_loss | -0.0682 | +| value_loss | 0.000578 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.63e+03 | +| ep_rew_mean | 0.143 | +| time/ | | +| fps | 310 | +| iterations | 2688 | +| time_elapsed | 8861 | +| total_timesteps | 2752512 | +| train/ | | +| approx_kl | 1.6561177 | +| clip_fraction | 0.449 | +| clip_range | 0.2 | +| entropy_loss | -0.359 | +| explained_variance | -3.04 | +| learning_rate | 0.0001 | +| loss | -0.0889 | +| n_updates | 87400 | +| policy_gradient_loss | -0.0657 | +| value_loss | 0.000742 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.61e+03 | +| ep_rew_mean | 0.146 | +| time/ | | +| fps | 310 | +| iterations | 2689 | +| time_elapsed | 8865 | +| total_timesteps | 2753536 | +| train/ | | +| approx_kl | 1.6622713 | +| clip_fraction | 0.456 | +| clip_range | 0.2 | +| entropy_loss | -0.371 | +| explained_variance | -0.442 | +| learning_rate | 0.0001 | +| loss | -0.0856 | +| n_updates | 87410 | +| policy_gradient_loss | -0.0639 | +| value_loss | 0.000632 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.61e+03 | +| ep_rew_mean | 0.146 | +| time/ | | +| fps | 310 | +| iterations | 2690 | +| time_elapsed | 8868 | +| total_timesteps | 2754560 | +| train/ | | +| approx_kl | 1.6860057 | +| clip_fraction | 0.467 | +| clip_range | 0.2 | +| entropy_loss | -0.433 | +| explained_variance | -0.442 | +| learning_rate | 0.0001 | +| loss | -0.0825 | +| n_updates | 87420 | +| policy_gradient_loss | -0.0658 | +| value_loss | 0.000848 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.62e+03 | +| ep_rew_mean | 0.15 | +| time/ | | +| fps | 310 | +| iterations | 2691 | +| time_elapsed | 8872 | +| total_timesteps | 2755584 | +| train/ | | +| approx_kl | 1.9150534 | +| clip_fraction | 0.486 | +| clip_range | 0.2 | +| entropy_loss | -0.41 | +| explained_variance | -1.84 | +| learning_rate | 0.0001 | +| loss | -0.0884 | +| n_updates | 87430 | +| policy_gradient_loss | -0.0702 | +| value_loss | 0.000689 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.62e+03 | +| ep_rew_mean | 0.149 | +| time/ | | +| fps | 310 | +| iterations | 2692 | +| time_elapsed | 8875 | +| total_timesteps | 2756608 | +| train/ | | +| approx_kl | 1.7036508 | +| clip_fraction | 0.465 | +| clip_range | 0.2 | +| entropy_loss | -0.46 | +| explained_variance | -5.73 | +| learning_rate | 0.0001 | +| loss | -0.0869 | +| n_updates | 87440 | +| policy_gradient_loss | -0.0671 | +| value_loss | 0.000182 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.62e+03 | +| ep_rew_mean | 0.149 | +| time/ | | +| fps | 310 | +| iterations | 2693 | +| time_elapsed | 8879 | +| total_timesteps | 2757632 | +| train/ | | +| approx_kl | 1.4100506 | +| clip_fraction | 0.461 | +| clip_range | 0.2 | +| entropy_loss | -0.415 | +| explained_variance | -1.5 | +| learning_rate | 0.0001 | +| loss | -0.0883 | +| n_updates | 87450 | +| policy_gradient_loss | -0.0661 | +| value_loss | 0.000396 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.62e+03 | +| ep_rew_mean | 0.149 | +| time/ | | +| fps | 310 | +| iterations | 2694 | +| time_elapsed | 8882 | +| total_timesteps | 2758656 | +| train/ | | +| approx_kl | 1.8268023 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.473 | +| explained_variance | -1.72 | +| learning_rate | 0.0001 | +| loss | -0.0675 | +| n_updates | 87460 | +| policy_gradient_loss | -0.0561 | +| value_loss | 0.000528 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.64e+03 | +| ep_rew_mean | 0.156 | +| time/ | | +| fps | 310 | +| iterations | 2695 | +| time_elapsed | 8885 | +| total_timesteps | 2759680 | +| train/ | | +| approx_kl | 3.7283125 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.426 | +| explained_variance | -4.71 | +| learning_rate | 0.0001 | +| loss | -0.0845 | +| n_updates | 87470 | +| policy_gradient_loss | -0.0672 | +| value_loss | 0.000333 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.64e+03 | +| ep_rew_mean | 0.157 | +| time/ | | +| fps | 310 | +| iterations | 2696 | +| time_elapsed | 8889 | +| total_timesteps | 2760704 | +| train/ | | +| approx_kl | 1.5615737 | +| clip_fraction | 0.456 | +| clip_range | 0.2 | +| entropy_loss | -0.482 | +| explained_variance | -1.83 | +| learning_rate | 0.0001 | +| loss | -0.0843 | +| n_updates | 87480 | +| policy_gradient_loss | -0.0657 | +| value_loss | 0.000268 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.64e+03 | +| ep_rew_mean | 0.151 | +| time/ | | +| fps | 310 | +| iterations | 2697 | +| time_elapsed | 8892 | +| total_timesteps | 2761728 | +| train/ | | +| approx_kl | 1.3301162 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.484 | +| explained_variance | -1.36 | +| learning_rate | 0.0001 | +| loss | -0.0486 | +| n_updates | 87490 | +| policy_gradient_loss | -0.0607 | +| value_loss | 0.000193 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.63e+03 | +| ep_rew_mean | 0.151 | +| time/ | | +| fps | 310 | +| iterations | 2698 | +| time_elapsed | 8895 | +| total_timesteps | 2762752 | +| train/ | | +| approx_kl | 1.3003703 | +| clip_fraction | 0.46 | +| clip_range | 0.2 | +| entropy_loss | -0.448 | +| explained_variance | -0.264 | +| learning_rate | 0.0001 | +| loss | -0.0987 | +| n_updates | 87500 | +| policy_gradient_loss | -0.0586 | +| value_loss | 0.000459 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.63e+03 | +| ep_rew_mean | 0.151 | +| time/ | | +| fps | 310 | +| iterations | 2699 | +| time_elapsed | 8898 | +| total_timesteps | 2763776 | +| train/ | | +| approx_kl | 1.3628936 | +| clip_fraction | 0.512 | +| clip_range | 0.2 | +| entropy_loss | -0.569 | +| explained_variance | -2.16 | +| learning_rate | 0.0001 | +| loss | -0.109 | +| n_updates | 87510 | +| policy_gradient_loss | -0.0704 | +| value_loss | 0.000395 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.63e+03 | +| ep_rew_mean | 0.149 | +| time/ | | +| fps | 310 | +| iterations | 2700 | +| time_elapsed | 8901 | +| total_timesteps | 2764800 | +| train/ | | +| approx_kl | 1.284276 | +| clip_fraction | 0.49 | +| clip_range | 0.2 | +| entropy_loss | -0.539 | +| explained_variance | -1.33 | +| learning_rate | 0.0001 | +| loss | -0.0654 | +| n_updates | 87520 | +| policy_gradient_loss | -0.0648 | +| value_loss | 0.000558 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.64e+03 | +| ep_rew_mean | 0.151 | +| time/ | | +| fps | 310 | +| iterations | 2701 | +| time_elapsed | 8905 | +| total_timesteps | 2765824 | +| train/ | | +| approx_kl | 1.6874628 | +| clip_fraction | 0.504 | +| clip_range | 0.2 | +| entropy_loss | -0.44 | +| explained_variance | -1.67 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 87530 | +| policy_gradient_loss | -0.0741 | +| value_loss | 0.000539 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.64e+03 | +| ep_rew_mean | 0.151 | +| time/ | | +| fps | 310 | +| iterations | 2702 | +| time_elapsed | 8908 | +| total_timesteps | 2766848 | +| train/ | | +| approx_kl | 1.5326562 | +| clip_fraction | 0.437 | +| clip_range | 0.2 | +| entropy_loss | -0.38 | +| explained_variance | -2.25 | +| learning_rate | 0.0001 | +| loss | -0.0939 | +| n_updates | 87540 | +| policy_gradient_loss | -0.0648 | +| value_loss | 0.000276 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.64e+03 | +| ep_rew_mean | 0.153 | +| time/ | | +| fps | 310 | +| iterations | 2703 | +| time_elapsed | 8911 | +| total_timesteps | 2767872 | +| train/ | | +| approx_kl | 1.5416777 | +| clip_fraction | 0.496 | +| clip_range | 0.2 | +| entropy_loss | -0.457 | +| explained_variance | -0.779 | +| learning_rate | 0.0001 | +| loss | -0.0687 | +| n_updates | 87550 | +| policy_gradient_loss | -0.056 | +| value_loss | 0.000448 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.64e+03 | +| ep_rew_mean | 0.153 | +| time/ | | +| fps | 310 | +| iterations | 2704 | +| time_elapsed | 8914 | +| total_timesteps | 2768896 | +| train/ | | +| approx_kl | 1.7957716 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.403 | +| explained_variance | -2.14 | +| learning_rate | 0.0001 | +| loss | -0.0823 | +| n_updates | 87560 | +| policy_gradient_loss | -0.0657 | +| value_loss | 0.000363 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.64e+03 | +| ep_rew_mean | 0.154 | +| time/ | | +| fps | 310 | +| iterations | 2705 | +| time_elapsed | 8917 | +| total_timesteps | 2769920 | +| train/ | | +| approx_kl | 1.5827776 | +| clip_fraction | 0.502 | +| clip_range | 0.2 | +| entropy_loss | -0.484 | +| explained_variance | -0.895 | +| learning_rate | 0.0001 | +| loss | -0.0745 | +| n_updates | 87570 | +| policy_gradient_loss | -0.0589 | +| value_loss | 0.000375 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.64e+03 | +| ep_rew_mean | 0.15 | +| time/ | | +| fps | 310 | +| iterations | 2706 | +| time_elapsed | 8921 | +| total_timesteps | 2770944 | +| train/ | | +| approx_kl | 1.491303 | +| clip_fraction | 0.448 | +| clip_range | 0.2 | +| entropy_loss | -0.402 | +| explained_variance | -1.95 | +| learning_rate | 0.0001 | +| loss | -0.0873 | +| n_updates | 87580 | +| policy_gradient_loss | -0.0694 | +| value_loss | 0.000518 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.64e+03 | +| ep_rew_mean | 0.15 | +| time/ | | +| fps | 310 | +| iterations | 2707 | +| time_elapsed | 8924 | +| total_timesteps | 2771968 | +| train/ | | +| approx_kl | 1.6366405 | +| clip_fraction | 0.466 | +| clip_range | 0.2 | +| entropy_loss | -0.465 | +| explained_variance | -2.18 | +| learning_rate | 0.0001 | +| loss | -0.0941 | +| n_updates | 87590 | +| policy_gradient_loss | -0.0694 | +| value_loss | 0.000319 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.64e+03 | +| ep_rew_mean | 0.15 | +| time/ | | +| fps | 310 | +| iterations | 2708 | +| time_elapsed | 8928 | +| total_timesteps | 2772992 | +| train/ | | +| approx_kl | 2.0719597 | +| clip_fraction | 0.51 | +| clip_range | 0.2 | +| entropy_loss | -0.487 | +| explained_variance | -1.11 | +| learning_rate | 0.0001 | +| loss | -0.044 | +| n_updates | 87600 | +| policy_gradient_loss | -0.0693 | +| value_loss | 0.00043 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.65e+03 | +| ep_rew_mean | 0.155 | +| time/ | | +| fps | 310 | +| iterations | 2709 | +| time_elapsed | 8931 | +| total_timesteps | 2774016 | +| train/ | | +| approx_kl | 1.7819865 | +| clip_fraction | 0.503 | +| clip_range | 0.2 | +| entropy_loss | -0.494 | +| explained_variance | -4.76 | +| learning_rate | 0.0001 | +| loss | -0.0928 | +| n_updates | 87610 | +| policy_gradient_loss | -0.0749 | +| value_loss | 0.000337 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.64e+03 | +| ep_rew_mean | 0.154 | +| time/ | | +| fps | 310 | +| iterations | 2710 | +| time_elapsed | 8935 | +| total_timesteps | 2775040 | +| train/ | | +| approx_kl | 1.6301944 | +| clip_fraction | 0.521 | +| clip_range | 0.2 | +| entropy_loss | -0.562 | +| explained_variance | -1.86 | +| learning_rate | 0.0001 | +| loss | -0.0982 | +| n_updates | 87620 | +| policy_gradient_loss | -0.0679 | +| value_loss | 0.000463 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.64e+03 | +| ep_rew_mean | 0.154 | +| time/ | | +| fps | 310 | +| iterations | 2711 | +| time_elapsed | 8938 | +| total_timesteps | 2776064 | +| train/ | | +| approx_kl | 1.9748662 | +| clip_fraction | 0.496 | +| clip_range | 0.2 | +| entropy_loss | -0.461 | +| explained_variance | -0.979 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 87630 | +| policy_gradient_loss | -0.0656 | +| value_loss | 0.000369 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.65e+03 | +| ep_rew_mean | 0.155 | +| time/ | | +| fps | 310 | +| iterations | 2712 | +| time_elapsed | 8941 | +| total_timesteps | 2777088 | +| train/ | | +| approx_kl | 2.0735369 | +| clip_fraction | 0.516 | +| clip_range | 0.2 | +| entropy_loss | -0.531 | +| explained_variance | -1.45 | +| learning_rate | 0.0001 | +| loss | -0.0983 | +| n_updates | 87640 | +| policy_gradient_loss | -0.0737 | +| value_loss | 0.000394 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.64e+03 | +| ep_rew_mean | 0.157 | +| time/ | | +| fps | 310 | +| iterations | 2713 | +| time_elapsed | 8945 | +| total_timesteps | 2778112 | +| train/ | | +| approx_kl | 3.4029489 | +| clip_fraction | 0.51 | +| clip_range | 0.2 | +| entropy_loss | -0.508 | +| explained_variance | -1.71 | +| learning_rate | 0.0001 | +| loss | -0.0744 | +| n_updates | 87650 | +| policy_gradient_loss | -0.0668 | +| value_loss | 0.000508 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.64e+03 | +| ep_rew_mean | 0.157 | +| time/ | | +| fps | 310 | +| iterations | 2714 | +| time_elapsed | 8948 | +| total_timesteps | 2779136 | +| train/ | | +| approx_kl | 2.0624018 | +| clip_fraction | 0.501 | +| clip_range | 0.2 | +| entropy_loss | -0.477 | +| explained_variance | -0.884 | +| learning_rate | 0.0001 | +| loss | -0.0986 | +| n_updates | 87660 | +| policy_gradient_loss | -0.0706 | +| value_loss | 0.000621 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.62e+03 | +| ep_rew_mean | 0.155 | +| time/ | | +| fps | 310 | +| iterations | 2715 | +| time_elapsed | 8951 | +| total_timesteps | 2780160 | +| train/ | | +| approx_kl | 1.787327 | +| clip_fraction | 0.522 | +| clip_range | 0.2 | +| entropy_loss | -0.503 | +| explained_variance | -1.33 | +| learning_rate | 0.0001 | +| loss | -0.0818 | +| n_updates | 87670 | +| policy_gradient_loss | -0.0445 | +| value_loss | 0.000752 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.62e+03 | +| ep_rew_mean | 0.152 | +| time/ | | +| fps | 310 | +| iterations | 2716 | +| time_elapsed | 8955 | +| total_timesteps | 2781184 | +| train/ | | +| approx_kl | 1.8303628 | +| clip_fraction | 0.458 | +| clip_range | 0.2 | +| entropy_loss | -0.463 | +| explained_variance | -1.7 | +| learning_rate | 0.0001 | +| loss | -0.0634 | +| n_updates | 87680 | +| policy_gradient_loss | -0.0628 | +| value_loss | 0.000647 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.62e+03 | +| ep_rew_mean | 0.152 | +| time/ | | +| fps | 310 | +| iterations | 2717 | +| time_elapsed | 8958 | +| total_timesteps | 2782208 | +| train/ | | +| approx_kl | 1.5338919 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.445 | +| explained_variance | -1.61 | +| learning_rate | 0.0001 | +| loss | -0.0869 | +| n_updates | 87690 | +| policy_gradient_loss | -0.0696 | +| value_loss | 0.000473 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.61e+03 | +| ep_rew_mean | 0.15 | +| time/ | | +| fps | 310 | +| iterations | 2718 | +| time_elapsed | 8961 | +| total_timesteps | 2783232 | +| train/ | | +| approx_kl | 2.0057025 | +| clip_fraction | 0.479 | +| clip_range | 0.2 | +| entropy_loss | -0.41 | +| explained_variance | -0.586 | +| learning_rate | 0.0001 | +| loss | -0.117 | +| n_updates | 87700 | +| policy_gradient_loss | -0.0719 | +| value_loss | 0.000627 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.61e+03 | +| ep_rew_mean | 0.15 | +| time/ | | +| fps | 310 | +| iterations | 2719 | +| time_elapsed | 8964 | +| total_timesteps | 2784256 | +| train/ | | +| approx_kl | 1.569767 | +| clip_fraction | 0.478 | +| clip_range | 0.2 | +| entropy_loss | -0.484 | +| explained_variance | -9.17 | +| learning_rate | 0.0001 | +| loss | -0.109 | +| n_updates | 87710 | +| policy_gradient_loss | -0.0708 | +| value_loss | 0.000288 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.62e+03 | +| ep_rew_mean | 0.151 | +| time/ | | +| fps | 310 | +| iterations | 2720 | +| time_elapsed | 8967 | +| total_timesteps | 2785280 | +| train/ | | +| approx_kl | 1.3881441 | +| clip_fraction | 0.511 | +| clip_range | 0.2 | +| entropy_loss | -0.649 | +| explained_variance | -0.692 | +| learning_rate | 0.0001 | +| loss | -0.113 | +| n_updates | 87720 | +| policy_gradient_loss | -0.0683 | +| value_loss | 0.000202 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.61e+03 | +| ep_rew_mean | 0.147 | +| time/ | | +| fps | 310 | +| iterations | 2721 | +| time_elapsed | 8970 | +| total_timesteps | 2786304 | +| train/ | | +| approx_kl | 1.5603595 | +| clip_fraction | 0.464 | +| clip_range | 0.2 | +| entropy_loss | -0.456 | +| explained_variance | -1.5 | +| learning_rate | 0.0001 | +| loss | -0.0905 | +| n_updates | 87730 | +| policy_gradient_loss | -0.0692 | +| value_loss | 0.000331 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.61e+03 | +| ep_rew_mean | 0.147 | +| time/ | | +| fps | 310 | +| iterations | 2722 | +| time_elapsed | 8974 | +| total_timesteps | 2787328 | +| train/ | | +| approx_kl | 1.5031619 | +| clip_fraction | 0.458 | +| clip_range | 0.2 | +| entropy_loss | -0.408 | +| explained_variance | -1.51 | +| learning_rate | 0.0001 | +| loss | -0.0937 | +| n_updates | 87740 | +| policy_gradient_loss | -0.0661 | +| value_loss | 0.000577 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.61e+03 | +| ep_rew_mean | 0.147 | +| time/ | | +| fps | 310 | +| iterations | 2723 | +| time_elapsed | 8977 | +| total_timesteps | 2788352 | +| train/ | | +| approx_kl | 1.5696563 | +| clip_fraction | 0.462 | +| clip_range | 0.2 | +| entropy_loss | -0.411 | +| explained_variance | -1.63 | +| learning_rate | 0.0001 | +| loss | -0.0956 | +| n_updates | 87750 | +| policy_gradient_loss | -0.0637 | +| value_loss | 0.000519 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.61e+03 | +| ep_rew_mean | 0.148 | +| time/ | | +| fps | 310 | +| iterations | 2724 | +| time_elapsed | 8980 | +| total_timesteps | 2789376 | +| train/ | | +| approx_kl | 1.3982377 | +| clip_fraction | 0.478 | +| clip_range | 0.2 | +| entropy_loss | -0.406 | +| explained_variance | -7.65 | +| learning_rate | 0.0001 | +| loss | 0.0283 | +| n_updates | 87760 | +| policy_gradient_loss | -0.0711 | +| value_loss | 0.00035 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.61e+03 | +| ep_rew_mean | 0.149 | +| time/ | | +| fps | 310 | +| iterations | 2725 | +| time_elapsed | 8983 | +| total_timesteps | 2790400 | +| train/ | | +| approx_kl | 1.5263976 | +| clip_fraction | 0.485 | +| clip_range | 0.2 | +| entropy_loss | -0.471 | +| explained_variance | -0.784 | +| learning_rate | 0.0001 | +| loss | -0.1 | +| n_updates | 87770 | +| policy_gradient_loss | -0.0582 | +| value_loss | 0.000271 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | 0.145 | +| time/ | | +| fps | 310 | +| iterations | 2726 | +| time_elapsed | 8987 | +| total_timesteps | 2791424 | +| train/ | | +| approx_kl | 1.9062959 | +| clip_fraction | 0.462 | +| clip_range | 0.2 | +| entropy_loss | -0.445 | +| explained_variance | -1.91 | +| learning_rate | 0.0001 | +| loss | -0.0962 | +| n_updates | 87780 | +| policy_gradient_loss | -0.0731 | +| value_loss | 0.000357 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | 0.145 | +| time/ | | +| fps | 310 | +| iterations | 2727 | +| time_elapsed | 8990 | +| total_timesteps | 2792448 | +| train/ | | +| approx_kl | 1.578192 | +| clip_fraction | 0.472 | +| clip_range | 0.2 | +| entropy_loss | -0.47 | +| explained_variance | -0.375 | +| learning_rate | 0.0001 | +| loss | -0.11 | +| n_updates | 87790 | +| policy_gradient_loss | -0.0694 | +| value_loss | 0.000584 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.62e+03 | +| ep_rew_mean | 0.149 | +| time/ | | +| fps | 310 | +| iterations | 2728 | +| time_elapsed | 8994 | +| total_timesteps | 2793472 | +| train/ | | +| approx_kl | 1.3614324 | +| clip_fraction | 0.505 | +| clip_range | 0.2 | +| entropy_loss | -0.49 | +| explained_variance | -0.689 | +| learning_rate | 0.0001 | +| loss | -0.0951 | +| n_updates | 87800 | +| policy_gradient_loss | -0.0732 | +| value_loss | 0.000582 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | 0.148 | +| time/ | | +| fps | 310 | +| iterations | 2729 | +| time_elapsed | 8997 | +| total_timesteps | 2794496 | +| train/ | | +| approx_kl | 1.5931315 | +| clip_fraction | 0.496 | +| clip_range | 0.2 | +| entropy_loss | -0.469 | +| explained_variance | -1.94 | +| learning_rate | 0.0001 | +| loss | -0.079 | +| n_updates | 87810 | +| policy_gradient_loss | -0.0701 | +| value_loss | 0.00029 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | 0.148 | +| time/ | | +| fps | 310 | +| iterations | 2730 | +| time_elapsed | 9001 | +| total_timesteps | 2795520 | +| train/ | | +| approx_kl | 2.8611274 | +| clip_fraction | 0.514 | +| clip_range | 0.2 | +| entropy_loss | -0.412 | +| explained_variance | -0.603 | +| learning_rate | 0.0001 | +| loss | -0.0822 | +| n_updates | 87820 | +| policy_gradient_loss | -0.0591 | +| value_loss | 0.000363 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.61e+03 | +| ep_rew_mean | 0.147 | +| time/ | | +| fps | 310 | +| iterations | 2731 | +| time_elapsed | 9004 | +| total_timesteps | 2796544 | +| train/ | | +| approx_kl | 2.2183712 | +| clip_fraction | 0.495 | +| clip_range | 0.2 | +| entropy_loss | -0.504 | +| explained_variance | -0.935 | +| learning_rate | 0.0001 | +| loss | -0.108 | +| n_updates | 87830 | +| policy_gradient_loss | -0.0657 | +| value_loss | 0.000558 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | 0.144 | +| time/ | | +| fps | 310 | +| iterations | 2732 | +| time_elapsed | 9008 | +| total_timesteps | 2797568 | +| train/ | | +| approx_kl | 1.8751531 | +| clip_fraction | 0.493 | +| clip_range | 0.2 | +| entropy_loss | -0.477 | +| explained_variance | -2.21 | +| learning_rate | 0.0001 | +| loss | -0.0893 | +| n_updates | 87840 | +| policy_gradient_loss | -0.0671 | +| value_loss | 0.000491 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | 0.144 | +| time/ | | +| fps | 310 | +| iterations | 2733 | +| time_elapsed | 9011 | +| total_timesteps | 2798592 | +| train/ | | +| approx_kl | 1.7351794 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.41 | +| explained_variance | -1.6 | +| learning_rate | 0.0001 | +| loss | -0.0918 | +| n_updates | 87850 | +| policy_gradient_loss | -0.066 | +| value_loss | 0.000614 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | 0.144 | +| time/ | | +| fps | 310 | +| iterations | 2734 | +| time_elapsed | 9014 | +| total_timesteps | 2799616 | +| train/ | | +| approx_kl | 2.8518355 | +| clip_fraction | 0.568 | +| clip_range | 0.2 | +| entropy_loss | -0.515 | +| explained_variance | -2.25 | +| learning_rate | 0.0001 | +| loss | -0.0605 | +| n_updates | 87860 | +| policy_gradient_loss | -0.0702 | +| value_loss | 0.000357 | +--------------------------------------- + +Current state: Champion.Level8.RyuVsBlanka +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.61e+03 | +| ep_rew_mean | 0.144 | +| time/ | | +| fps | 310 | +| iterations | 2735 | +| time_elapsed | 9018 | +| total_timesteps | 2800640 | +| train/ | | +| approx_kl | 1.6533966 | +| clip_fraction | 0.452 | +| clip_range | 0.2 | +| entropy_loss | -0.395 | +| explained_variance | -2.17 | +| learning_rate | 0.0001 | +| loss | -0.071 | +| n_updates | 87870 | +| policy_gradient_loss | -0.0633 | +| value_loss | 0.000588 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | 0.142 | +| time/ | | +| fps | 310 | +| iterations | 2736 | +| time_elapsed | 9021 | +| total_timesteps | 2801664 | +| train/ | | +| approx_kl | 1.395165 | +| clip_fraction | 0.478 | +| clip_range | 0.2 | +| entropy_loss | -0.457 | +| explained_variance | -5.53 | +| learning_rate | 0.0001 | +| loss | -0.0735 | +| n_updates | 87880 | +| policy_gradient_loss | -0.0639 | +| value_loss | 0.000373 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | 0.142 | +| time/ | | +| fps | 310 | +| iterations | 2737 | +| time_elapsed | 9024 | +| total_timesteps | 2802688 | +| train/ | | +| approx_kl | 2.0642815 | +| clip_fraction | 0.466 | +| clip_range | 0.2 | +| entropy_loss | -0.386 | +| explained_variance | -1.85 | +| learning_rate | 0.0001 | +| loss | -0.107 | +| n_updates | 87890 | +| policy_gradient_loss | -0.0663 | +| value_loss | 0.000475 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | 0.142 | +| time/ | | +| fps | 310 | +| iterations | 2738 | +| time_elapsed | 9028 | +| total_timesteps | 2803712 | +| train/ | | +| approx_kl | 2.1150985 | +| clip_fraction | 0.465 | +| clip_range | 0.2 | +| entropy_loss | -0.331 | +| explained_variance | -1.82 | +| learning_rate | 0.0001 | +| loss | -0.0716 | +| n_updates | 87900 | +| policy_gradient_loss | -0.0624 | +| value_loss | 0.000802 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | 0.14 | +| time/ | | +| fps | 310 | +| iterations | 2739 | +| time_elapsed | 9031 | +| total_timesteps | 2804736 | +| train/ | | +| approx_kl | 2.1321087 | +| clip_fraction | 0.45 | +| clip_range | 0.2 | +| entropy_loss | -0.334 | +| explained_variance | -2.38 | +| learning_rate | 0.0001 | +| loss | -0.0998 | +| n_updates | 87910 | +| policy_gradient_loss | -0.0593 | +| value_loss | 0.000488 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | 0.14 | +| time/ | | +| fps | 310 | +| iterations | 2740 | +| time_elapsed | 9034 | +| total_timesteps | 2805760 | +| train/ | | +| approx_kl | 2.2151608 | +| clip_fraction | 0.424 | +| clip_range | 0.2 | +| entropy_loss | -0.3 | +| explained_variance | -3.2 | +| learning_rate | 0.0001 | +| loss | -0.0922 | +| n_updates | 87920 | +| policy_gradient_loss | -0.0589 | +| value_loss | 0.000399 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.61e+03 | +| ep_rew_mean | 0.139 | +| time/ | | +| fps | 310 | +| iterations | 2741 | +| time_elapsed | 9037 | +| total_timesteps | 2806784 | +| train/ | | +| approx_kl | 1.9460583 | +| clip_fraction | 0.479 | +| clip_range | 0.2 | +| entropy_loss | -0.369 | +| explained_variance | -1.49 | +| learning_rate | 0.0001 | +| loss | -0.0864 | +| n_updates | 87930 | +| policy_gradient_loss | -0.065 | +| value_loss | 0.000693 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.61e+03 | +| ep_rew_mean | 0.139 | +| time/ | | +| fps | 310 | +| iterations | 2742 | +| time_elapsed | 9040 | +| total_timesteps | 2807808 | +| train/ | | +| approx_kl | 3.4698718 | +| clip_fraction | 0.47 | +| clip_range | 0.2 | +| entropy_loss | -0.337 | +| explained_variance | -11.3 | +| learning_rate | 0.0001 | +| loss | -0.0705 | +| n_updates | 87940 | +| policy_gradient_loss | -0.0657 | +| value_loss | 0.000576 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | 0.137 | +| time/ | | +| fps | 310 | +| iterations | 2743 | +| time_elapsed | 9044 | +| total_timesteps | 2808832 | +| train/ | | +| approx_kl | 2.149028 | +| clip_fraction | 0.468 | +| clip_range | 0.2 | +| entropy_loss | -0.354 | +| explained_variance | -1.91 | +| learning_rate | 0.0001 | +| loss | -0.0856 | +| n_updates | 87950 | +| policy_gradient_loss | -0.0668 | +| value_loss | 0.000405 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | 0.137 | +| time/ | | +| fps | 310 | +| iterations | 2744 | +| time_elapsed | 9047 | +| total_timesteps | 2809856 | +| train/ | | +| approx_kl | 2.3060827 | +| clip_fraction | 0.468 | +| clip_range | 0.2 | +| entropy_loss | -0.357 | +| explained_variance | -1.11 | +| learning_rate | 0.0001 | +| loss | -0.0582 | +| n_updates | 87960 | +| policy_gradient_loss | -0.0648 | +| value_loss | 0.000512 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.62e+03 | +| ep_rew_mean | 0.141 | +| time/ | | +| fps | 310 | +| iterations | 2745 | +| time_elapsed | 9050 | +| total_timesteps | 2810880 | +| train/ | | +| approx_kl | 1.9805253 | +| clip_fraction | 0.469 | +| clip_range | 0.2 | +| entropy_loss | -0.413 | +| explained_variance | -3.14 | +| learning_rate | 0.0001 | +| loss | -0.0788 | +| n_updates | 87970 | +| policy_gradient_loss | -0.0629 | +| value_loss | 0.000561 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.62e+03 | +| ep_rew_mean | 0.141 | +| time/ | | +| fps | 310 | +| iterations | 2746 | +| time_elapsed | 9054 | +| total_timesteps | 2811904 | +| train/ | | +| approx_kl | 1.9158282 | +| clip_fraction | 0.482 | +| clip_range | 0.2 | +| entropy_loss | -0.396 | +| explained_variance | -3.59 | +| learning_rate | 0.0001 | +| loss | -0.0854 | +| n_updates | 87980 | +| policy_gradient_loss | -0.0669 | +| value_loss | 0.00035 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.62e+03 | +| ep_rew_mean | 0.139 | +| time/ | | +| fps | 310 | +| iterations | 2747 | +| time_elapsed | 9057 | +| total_timesteps | 2812928 | +| train/ | | +| approx_kl | 2.0211117 | +| clip_fraction | 0.477 | +| clip_range | 0.2 | +| entropy_loss | -0.413 | +| explained_variance | -2.27 | +| learning_rate | 0.0001 | +| loss | -0.0894 | +| n_updates | 87990 | +| policy_gradient_loss | -0.0623 | +| value_loss | 0.000425 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.61e+03 | +| ep_rew_mean | 0.132 | +| time/ | | +| fps | 310 | +| iterations | 2748 | +| time_elapsed | 9060 | +| total_timesteps | 2813952 | +| train/ | | +| approx_kl | 2.061129 | +| clip_fraction | 0.489 | +| clip_range | 0.2 | +| entropy_loss | -0.419 | +| explained_variance | -2.26 | +| learning_rate | 0.0001 | +| loss | -0.0917 | +| n_updates | 88000 | +| policy_gradient_loss | -0.0685 | +| value_loss | 0.000357 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.61e+03 | +| ep_rew_mean | 0.132 | +| time/ | | +| fps | 310 | +| iterations | 2749 | +| time_elapsed | 9064 | +| total_timesteps | 2814976 | +| train/ | | +| approx_kl | 1.8489051 | +| clip_fraction | 0.441 | +| clip_range | 0.2 | +| entropy_loss | -0.396 | +| explained_variance | -0.558 | +| learning_rate | 0.0001 | +| loss | -0.0696 | +| n_updates | 88010 | +| policy_gradient_loss | -0.0493 | +| value_loss | 0.000792 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.61e+03 | +| ep_rew_mean | 0.132 | +| time/ | | +| fps | 310 | +| iterations | 2750 | +| time_elapsed | 9068 | +| total_timesteps | 2816000 | +| train/ | | +| approx_kl | 1.9432039 | +| clip_fraction | 0.469 | +| clip_range | 0.2 | +| entropy_loss | -0.397 | +| explained_variance | -7.97 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 88020 | +| policy_gradient_loss | -0.07 | +| value_loss | 0.000321 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.63e+03 | +| ep_rew_mean | 0.131 | +| time/ | | +| fps | 310 | +| iterations | 2751 | +| time_elapsed | 9071 | +| total_timesteps | 2817024 | +| train/ | | +| approx_kl | 1.961936 | +| clip_fraction | 0.47 | +| clip_range | 0.2 | +| entropy_loss | -0.358 | +| explained_variance | -4.42 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 88030 | +| policy_gradient_loss | -0.0662 | +| value_loss | 0.00033 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.63e+03 | +| ep_rew_mean | 0.131 | +| time/ | | +| fps | 310 | +| iterations | 2752 | +| time_elapsed | 9074 | +| total_timesteps | 2818048 | +| train/ | | +| approx_kl | 1.9470415 | +| clip_fraction | 0.44 | +| clip_range | 0.2 | +| entropy_loss | -0.321 | +| explained_variance | -3.98 | +| learning_rate | 0.0001 | +| loss | -0.0738 | +| n_updates | 88040 | +| policy_gradient_loss | -0.0629 | +| value_loss | 0.000641 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.63e+03 | +| ep_rew_mean | 0.13 | +| time/ | | +| fps | 310 | +| iterations | 2753 | +| time_elapsed | 9077 | +| total_timesteps | 2819072 | +| train/ | | +| approx_kl | 1.8370278 | +| clip_fraction | 0.478 | +| clip_range | 0.2 | +| entropy_loss | -0.352 | +| explained_variance | -1.71 | +| learning_rate | 0.0001 | +| loss | -0.091 | +| n_updates | 88050 | +| policy_gradient_loss | -0.0655 | +| value_loss | 0.000513 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.62e+03 | +| ep_rew_mean | 0.125 | +| time/ | | +| fps | 310 | +| iterations | 2754 | +| time_elapsed | 9080 | +| total_timesteps | 2820096 | +| train/ | | +| approx_kl | 1.6195984 | +| clip_fraction | 0.458 | +| clip_range | 0.2 | +| entropy_loss | -0.386 | +| explained_variance | -3.93 | +| learning_rate | 0.0001 | +| loss | -0.0776 | +| n_updates | 88060 | +| policy_gradient_loss | -0.0636 | +| value_loss | 0.000408 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.62e+03 | +| ep_rew_mean | 0.125 | +| time/ | | +| fps | 310 | +| iterations | 2755 | +| time_elapsed | 9083 | +| total_timesteps | 2821120 | +| train/ | | +| approx_kl | 1.7268193 | +| clip_fraction | 0.465 | +| clip_range | 0.2 | +| entropy_loss | -0.369 | +| explained_variance | -0.549 | +| learning_rate | 0.0001 | +| loss | -0.0709 | +| n_updates | 88070 | +| policy_gradient_loss | -0.0512 | +| value_loss | 0.000567 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.62e+03 | +| ep_rew_mean | 0.125 | +| time/ | | +| fps | 310 | +| iterations | 2756 | +| time_elapsed | 9086 | +| total_timesteps | 2822144 | +| train/ | | +| approx_kl | 2.0467517 | +| clip_fraction | 0.489 | +| clip_range | 0.2 | +| entropy_loss | -0.381 | +| explained_variance | -2.36 | +| learning_rate | 0.0001 | +| loss | -0.0863 | +| n_updates | 88080 | +| policy_gradient_loss | -0.0759 | +| value_loss | 0.000428 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.62e+03 | +| ep_rew_mean | 0.125 | +| time/ | | +| fps | 310 | +| iterations | 2757 | +| time_elapsed | 9090 | +| total_timesteps | 2823168 | +| train/ | | +| approx_kl | 2.1513543 | +| clip_fraction | 0.488 | +| clip_range | 0.2 | +| entropy_loss | -0.417 | +| explained_variance | -8.37 | +| learning_rate | 0.0001 | +| loss | -0.0784 | +| n_updates | 88090 | +| policy_gradient_loss | -0.0608 | +| value_loss | 0.000326 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.62e+03 | +| ep_rew_mean | 0.125 | +| time/ | | +| fps | 310 | +| iterations | 2758 | +| time_elapsed | 9093 | +| total_timesteps | 2824192 | +| train/ | | +| approx_kl | 1.6247998 | +| clip_fraction | 0.465 | +| clip_range | 0.2 | +| entropy_loss | -0.381 | +| explained_variance | -2.63 | +| learning_rate | 0.0001 | +| loss | -0.0844 | +| n_updates | 88100 | +| policy_gradient_loss | -0.0652 | +| value_loss | 0.000477 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.62e+03 | +| ep_rew_mean | 0.123 | +| time/ | | +| fps | 310 | +| iterations | 2759 | +| time_elapsed | 9096 | +| total_timesteps | 2825216 | +| train/ | | +| approx_kl | 2.0728292 | +| clip_fraction | 0.478 | +| clip_range | 0.2 | +| entropy_loss | -0.395 | +| explained_variance | -2.83 | +| learning_rate | 0.0001 | +| loss | -0.0837 | +| n_updates | 88110 | +| policy_gradient_loss | -0.0551 | +| value_loss | 0.000377 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.62e+03 | +| ep_rew_mean | 0.123 | +| time/ | | +| fps | 310 | +| iterations | 2760 | +| time_elapsed | 9099 | +| total_timesteps | 2826240 | +| train/ | | +| approx_kl | 1.9993541 | +| clip_fraction | 0.427 | +| clip_range | 0.2 | +| entropy_loss | -0.319 | +| explained_variance | -1.56 | +| learning_rate | 0.0001 | +| loss | -0.0375 | +| n_updates | 88120 | +| policy_gradient_loss | -0.0493 | +| value_loss | 0.000534 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.62e+03 | +| ep_rew_mean | 0.123 | +| time/ | | +| fps | 310 | +| iterations | 2761 | +| time_elapsed | 9103 | +| total_timesteps | 2827264 | +| train/ | | +| approx_kl | 2.1450276 | +| clip_fraction | 0.472 | +| clip_range | 0.2 | +| entropy_loss | -0.396 | +| explained_variance | -2.77 | +| learning_rate | 0.0001 | +| loss | -0.0951 | +| n_updates | 88130 | +| policy_gradient_loss | -0.0646 | +| value_loss | 0.000514 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.65e+03 | +| ep_rew_mean | 0.127 | +| time/ | | +| fps | 310 | +| iterations | 2762 | +| time_elapsed | 9106 | +| total_timesteps | 2828288 | +| train/ | | +| approx_kl | 2.372758 | +| clip_fraction | 0.458 | +| clip_range | 0.2 | +| entropy_loss | -0.332 | +| explained_variance | -7.27 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 88140 | +| policy_gradient_loss | -0.0681 | +| value_loss | 0.000644 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.65e+03 | +| ep_rew_mean | 0.127 | +| time/ | | +| fps | 310 | +| iterations | 2763 | +| time_elapsed | 9110 | +| total_timesteps | 2829312 | +| train/ | | +| approx_kl | 2.5289311 | +| clip_fraction | 0.443 | +| clip_range | 0.2 | +| entropy_loss | -0.324 | +| explained_variance | -2.97 | +| learning_rate | 0.0001 | +| loss | -0.077 | +| n_updates | 88150 | +| policy_gradient_loss | -0.0592 | +| value_loss | 0.000546 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | 0.129 | +| time/ | | +| fps | 310 | +| iterations | 2764 | +| time_elapsed | 9113 | +| total_timesteps | 2830336 | +| train/ | | +| approx_kl | 2.21917 | +| clip_fraction | 0.508 | +| clip_range | 0.2 | +| entropy_loss | -0.397 | +| explained_variance | -1.08 | +| learning_rate | 0.0001 | +| loss | -0.0888 | +| n_updates | 88160 | +| policy_gradient_loss | -0.0678 | +| value_loss | 0.00056 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.65e+03 | +| ep_rew_mean | 0.13 | +| time/ | | +| fps | 310 | +| iterations | 2765 | +| time_elapsed | 9117 | +| total_timesteps | 2831360 | +| train/ | | +| approx_kl | 3.1772954 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.409 | +| explained_variance | -1.41 | +| learning_rate | 0.0001 | +| loss | -0.0577 | +| n_updates | 88170 | +| policy_gradient_loss | -0.0622 | +| value_loss | 0.000583 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.65e+03 | +| ep_rew_mean | 0.13 | +| time/ | | +| fps | 310 | +| iterations | 2766 | +| time_elapsed | 9120 | +| total_timesteps | 2832384 | +| train/ | | +| approx_kl | 2.5544028 | +| clip_fraction | 0.47 | +| clip_range | 0.2 | +| entropy_loss | -0.347 | +| explained_variance | -0.837 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 88180 | +| policy_gradient_loss | -0.0692 | +| value_loss | 0.000728 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.65e+03 | +| ep_rew_mean | 0.131 | +| time/ | | +| fps | 310 | +| iterations | 2767 | +| time_elapsed | 9124 | +| total_timesteps | 2833408 | +| train/ | | +| approx_kl | 2.9851093 | +| clip_fraction | 0.498 | +| clip_range | 0.2 | +| entropy_loss | -0.437 | +| explained_variance | -2.19 | +| learning_rate | 0.0001 | +| loss | -0.0917 | +| n_updates | 88190 | +| policy_gradient_loss | -0.0719 | +| value_loss | 0.00048 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.64e+03 | +| ep_rew_mean | 0.132 | +| time/ | | +| fps | 310 | +| iterations | 2768 | +| time_elapsed | 9127 | +| total_timesteps | 2834432 | +| train/ | | +| approx_kl | 2.2821383 | +| clip_fraction | 0.449 | +| clip_range | 0.2 | +| entropy_loss | -0.333 | +| explained_variance | -1.03 | +| learning_rate | 0.0001 | +| loss | -0.0833 | +| n_updates | 88200 | +| policy_gradient_loss | -0.0612 | +| value_loss | 0.000386 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.64e+03 | +| ep_rew_mean | 0.132 | +| time/ | | +| fps | 310 | +| iterations | 2769 | +| time_elapsed | 9130 | +| total_timesteps | 2835456 | +| train/ | | +| approx_kl | 2.040008 | +| clip_fraction | 0.506 | +| clip_range | 0.2 | +| entropy_loss | -0.442 | +| explained_variance | -0.79 | +| learning_rate | 0.0001 | +| loss | -0.0776 | +| n_updates | 88210 | +| policy_gradient_loss | -0.0623 | +| value_loss | 0.000588 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.64e+03 | +| ep_rew_mean | 0.129 | +| time/ | | +| fps | 310 | +| iterations | 2770 | +| time_elapsed | 9134 | +| total_timesteps | 2836480 | +| train/ | | +| approx_kl | 2.3112302 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.467 | +| explained_variance | -2.15 | +| learning_rate | 0.0001 | +| loss | -0.0648 | +| n_updates | 88220 | +| policy_gradient_loss | -0.0622 | +| value_loss | 0.000578 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.64e+03 | +| ep_rew_mean | 0.129 | +| time/ | | +| fps | 310 | +| iterations | 2771 | +| time_elapsed | 9137 | +| total_timesteps | 2837504 | +| train/ | | +| approx_kl | 1.9848614 | +| clip_fraction | 0.458 | +| clip_range | 0.2 | +| entropy_loss | -0.391 | +| explained_variance | -2.3 | +| learning_rate | 0.0001 | +| loss | -0.0944 | +| n_updates | 88230 | +| policy_gradient_loss | -0.0638 | +| value_loss | 0.000481 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.65e+03 | +| ep_rew_mean | 0.127 | +| time/ | | +| fps | 310 | +| iterations | 2772 | +| time_elapsed | 9140 | +| total_timesteps | 2838528 | +| train/ | | +| approx_kl | 1.8471236 | +| clip_fraction | 0.476 | +| clip_range | 0.2 | +| entropy_loss | -0.412 | +| explained_variance | -5.64 | +| learning_rate | 0.0001 | +| loss | -0.0659 | +| n_updates | 88240 | +| policy_gradient_loss | -0.0617 | +| value_loss | 0.000481 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.65e+03 | +| ep_rew_mean | 0.127 | +| time/ | | +| fps | 310 | +| iterations | 2773 | +| time_elapsed | 9143 | +| total_timesteps | 2839552 | +| train/ | | +| approx_kl | 1.7680277 | +| clip_fraction | 0.44 | +| clip_range | 0.2 | +| entropy_loss | -0.336 | +| explained_variance | -3.49 | +| learning_rate | 0.0001 | +| loss | -0.0807 | +| n_updates | 88250 | +| policy_gradient_loss | -0.0589 | +| value_loss | 0.000756 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | 0.124 | +| time/ | | +| fps | 310 | +| iterations | 2774 | +| time_elapsed | 9146 | +| total_timesteps | 2840576 | +| train/ | | +| approx_kl | 1.5029082 | +| clip_fraction | 0.497 | +| clip_range | 0.2 | +| entropy_loss | -0.428 | +| explained_variance | -2.76 | +| learning_rate | 0.0001 | +| loss | -0.107 | +| n_updates | 88260 | +| policy_gradient_loss | -0.0693 | +| value_loss | 0.000463 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | 0.124 | +| time/ | | +| fps | 310 | +| iterations | 2775 | +| time_elapsed | 9149 | +| total_timesteps | 2841600 | +| train/ | | +| approx_kl | 2.3473928 | +| clip_fraction | 0.473 | +| clip_range | 0.2 | +| entropy_loss | -0.371 | +| explained_variance | -5.32 | +| learning_rate | 0.0001 | +| loss | -0.11 | +| n_updates | 88270 | +| policy_gradient_loss | -0.0715 | +| value_loss | 0.00076 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | 0.124 | +| time/ | | +| fps | 310 | +| iterations | 2776 | +| time_elapsed | 9153 | +| total_timesteps | 2842624 | +| train/ | | +| approx_kl | 3.5832543 | +| clip_fraction | 0.504 | +| clip_range | 0.2 | +| entropy_loss | -0.369 | +| explained_variance | -0.957 | +| learning_rate | 0.0001 | +| loss | -0.0955 | +| n_updates | 88280 | +| policy_gradient_loss | -0.0663 | +| value_loss | 0.00042 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | 0.124 | +| time/ | | +| fps | 310 | +| iterations | 2777 | +| time_elapsed | 9156 | +| total_timesteps | 2843648 | +| train/ | | +| approx_kl | 2.1525383 | +| clip_fraction | 0.495 | +| clip_range | 0.2 | +| entropy_loss | -0.396 | +| explained_variance | -3.87 | +| learning_rate | 0.0001 | +| loss | -0.0914 | +| n_updates | 88290 | +| policy_gradient_loss | -0.0718 | +| value_loss | 0.000391 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | 0.124 | +| time/ | | +| fps | 310 | +| iterations | 2778 | +| time_elapsed | 9159 | +| total_timesteps | 2844672 | +| train/ | | +| approx_kl | 2.372446 | +| clip_fraction | 0.495 | +| clip_range | 0.2 | +| entropy_loss | -0.428 | +| explained_variance | -2.32 | +| learning_rate | 0.0001 | +| loss | -0.0798 | +| n_updates | 88300 | +| policy_gradient_loss | -0.0608 | +| value_loss | 0.000266 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | 0.12 | +| time/ | | +| fps | 310 | +| iterations | 2779 | +| time_elapsed | 9162 | +| total_timesteps | 2845696 | +| train/ | | +| approx_kl | 1.6341833 | +| clip_fraction | 0.479 | +| clip_range | 0.2 | +| entropy_loss | -0.421 | +| explained_variance | -3.42 | +| learning_rate | 0.0001 | +| loss | -0.0719 | +| n_updates | 88310 | +| policy_gradient_loss | -0.0639 | +| value_loss | 0.000376 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | 0.12 | +| time/ | | +| fps | 310 | +| iterations | 2780 | +| time_elapsed | 9166 | +| total_timesteps | 2846720 | +| train/ | | +| approx_kl | 1.8514886 | +| clip_fraction | 0.477 | +| clip_range | 0.2 | +| entropy_loss | -0.397 | +| explained_variance | -2.22 | +| learning_rate | 0.0001 | +| loss | -0.0805 | +| n_updates | 88320 | +| policy_gradient_loss | -0.0678 | +| value_loss | 0.000532 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | 0.12 | +| time/ | | +| fps | 310 | +| iterations | 2781 | +| time_elapsed | 9169 | +| total_timesteps | 2847744 | +| train/ | | +| approx_kl | 3.0513525 | +| clip_fraction | 0.469 | +| clip_range | 0.2 | +| entropy_loss | -0.333 | +| explained_variance | -1.88 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 88330 | +| policy_gradient_loss | -0.0628 | +| value_loss | 0.000595 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | 0.12 | +| time/ | | +| fps | 310 | +| iterations | 2782 | +| time_elapsed | 9172 | +| total_timesteps | 2848768 | +| train/ | | +| approx_kl | 3.0643585 | +| clip_fraction | 0.459 | +| clip_range | 0.2 | +| entropy_loss | -0.357 | +| explained_variance | -1.93 | +| learning_rate | 0.0001 | +| loss | -0.0855 | +| n_updates | 88340 | +| policy_gradient_loss | -0.0659 | +| value_loss | 0.000371 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | 0.12 | +| time/ | | +| fps | 310 | +| iterations | 2783 | +| time_elapsed | 9175 | +| total_timesteps | 2849792 | +| train/ | | +| approx_kl | 2.1551728 | +| clip_fraction | 0.482 | +| clip_range | 0.2 | +| entropy_loss | -0.397 | +| explained_variance | -4.5 | +| learning_rate | 0.0001 | +| loss | -0.0708 | +| n_updates | 88350 | +| policy_gradient_loss | -0.0661 | +| value_loss | 0.000349 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.118 | +| time/ | | +| fps | 310 | +| iterations | 2784 | +| time_elapsed | 9179 | +| total_timesteps | 2850816 | +| train/ | | +| approx_kl | 2.84025 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.377 | +| explained_variance | -1.27 | +| learning_rate | 0.0001 | +| loss | -0.0799 | +| n_updates | 88360 | +| policy_gradient_loss | -0.0683 | +| value_loss | 0.000395 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.119 | +| time/ | | +| fps | 310 | +| iterations | 2785 | +| time_elapsed | 9182 | +| total_timesteps | 2851840 | +| train/ | | +| approx_kl | 2.2984204 | +| clip_fraction | 0.499 | +| clip_range | 0.2 | +| entropy_loss | -0.431 | +| explained_variance | -1.34 | +| learning_rate | 0.0001 | +| loss | -0.0627 | +| n_updates | 88370 | +| policy_gradient_loss | -0.0571 | +| value_loss | 0.000313 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.119 | +| time/ | | +| fps | 310 | +| iterations | 2786 | +| time_elapsed | 9185 | +| total_timesteps | 2852864 | +| train/ | | +| approx_kl | 1.5973437 | +| clip_fraction | 0.436 | +| clip_range | 0.2 | +| entropy_loss | -0.373 | +| explained_variance | -2.21 | +| learning_rate | 0.0001 | +| loss | -0.0849 | +| n_updates | 88380 | +| policy_gradient_loss | -0.0635 | +| value_loss | 0.000382 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.119 | +| time/ | | +| fps | 310 | +| iterations | 2787 | +| time_elapsed | 9189 | +| total_timesteps | 2853888 | +| train/ | | +| approx_kl | 1.9149861 | +| clip_fraction | 0.468 | +| clip_range | 0.2 | +| entropy_loss | -0.381 | +| explained_variance | -1.95 | +| learning_rate | 0.0001 | +| loss | -0.0838 | +| n_updates | 88390 | +| policy_gradient_loss | -0.0671 | +| value_loss | 0.000701 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.115 | +| time/ | | +| fps | 310 | +| iterations | 2788 | +| time_elapsed | 9192 | +| total_timesteps | 2854912 | +| train/ | | +| approx_kl | 1.8849474 | +| clip_fraction | 0.428 | +| clip_range | 0.2 | +| entropy_loss | -0.318 | +| explained_variance | -2.2 | +| learning_rate | 0.0001 | +| loss | -0.0821 | +| n_updates | 88400 | +| policy_gradient_loss | -0.0531 | +| value_loss | 0.00057 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.115 | +| time/ | | +| fps | 310 | +| iterations | 2789 | +| time_elapsed | 9195 | +| total_timesteps | 2855936 | +| train/ | | +| approx_kl | 2.2860463 | +| clip_fraction | 0.463 | +| clip_range | 0.2 | +| entropy_loss | -0.381 | +| explained_variance | -0.97 | +| learning_rate | 0.0001 | +| loss | -0.079 | +| n_updates | 88410 | +| policy_gradient_loss | -0.0638 | +| value_loss | 0.000407 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.116 | +| time/ | | +| fps | 310 | +| iterations | 2790 | +| time_elapsed | 9198 | +| total_timesteps | 2856960 | +| train/ | | +| approx_kl | 2.0327468 | +| clip_fraction | 0.503 | +| clip_range | 0.2 | +| entropy_loss | -0.383 | +| explained_variance | -3.01 | +| learning_rate | 0.0001 | +| loss | -0.055 | +| n_updates | 88420 | +| policy_gradient_loss | -0.0705 | +| value_loss | 0.000778 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.115 | +| time/ | | +| fps | 310 | +| iterations | 2791 | +| time_elapsed | 9202 | +| total_timesteps | 2857984 | +| train/ | | +| approx_kl | 2.409614 | +| clip_fraction | 0.445 | +| clip_range | 0.2 | +| entropy_loss | -0.344 | +| explained_variance | -2.1 | +| learning_rate | 0.0001 | +| loss | -0.1 | +| n_updates | 88430 | +| policy_gradient_loss | -0.0649 | +| value_loss | 0.000555 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.115 | +| time/ | | +| fps | 310 | +| iterations | 2792 | +| time_elapsed | 9205 | +| total_timesteps | 2859008 | +| train/ | | +| approx_kl | 3.2933998 | +| clip_fraction | 0.494 | +| clip_range | 0.2 | +| entropy_loss | -0.419 | +| explained_variance | -2.48 | +| learning_rate | 0.0001 | +| loss | -0.0847 | +| n_updates | 88440 | +| policy_gradient_loss | -0.0725 | +| value_loss | 0.000358 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.116 | +| time/ | | +| fps | 310 | +| iterations | 2793 | +| time_elapsed | 9208 | +| total_timesteps | 2860032 | +| train/ | | +| approx_kl | 1.9054561 | +| clip_fraction | 0.491 | +| clip_range | 0.2 | +| entropy_loss | -0.404 | +| explained_variance | -1.03 | +| learning_rate | 0.0001 | +| loss | -0.0605 | +| n_updates | 88450 | +| policy_gradient_loss | -0.0608 | +| value_loss | 0.000672 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.123 | +| time/ | | +| fps | 310 | +| iterations | 2794 | +| time_elapsed | 9211 | +| total_timesteps | 2861056 | +| train/ | | +| approx_kl | 2.4295354 | +| clip_fraction | 0.46 | +| clip_range | 0.2 | +| entropy_loss | -0.374 | +| explained_variance | -2.87 | +| learning_rate | 0.0001 | +| loss | -0.0789 | +| n_updates | 88460 | +| policy_gradient_loss | -0.0608 | +| value_loss | 0.000728 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.123 | +| time/ | | +| fps | 310 | +| iterations | 2795 | +| time_elapsed | 9214 | +| total_timesteps | 2862080 | +| train/ | | +| approx_kl | 1.9492066 | +| clip_fraction | 0.479 | +| clip_range | 0.2 | +| entropy_loss | -0.414 | +| explained_variance | -0.376 | +| learning_rate | 0.0001 | +| loss | -0.0472 | +| n_updates | 88470 | +| policy_gradient_loss | -0.0594 | +| value_loss | 0.000973 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.122 | +| time/ | | +| fps | 310 | +| iterations | 2796 | +| time_elapsed | 9217 | +| total_timesteps | 2863104 | +| train/ | | +| approx_kl | 2.0434065 | +| clip_fraction | 0.468 | +| clip_range | 0.2 | +| entropy_loss | -0.334 | +| explained_variance | -1.77 | +| learning_rate | 0.0001 | +| loss | -0.0928 | +| n_updates | 88480 | +| policy_gradient_loss | -0.0667 | +| value_loss | 0.000856 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.118 | +| time/ | | +| fps | 310 | +| iterations | 2797 | +| time_elapsed | 9221 | +| total_timesteps | 2864128 | +| train/ | | +| approx_kl | 1.819197 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.396 | +| explained_variance | -6.8 | +| learning_rate | 0.0001 | +| loss | -0.0786 | +| n_updates | 88490 | +| policy_gradient_loss | -0.0621 | +| value_loss | 0.000353 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.117 | +| time/ | | +| fps | 310 | +| iterations | 2798 | +| time_elapsed | 9224 | +| total_timesteps | 2865152 | +| train/ | | +| approx_kl | 2.1096787 | +| clip_fraction | 0.422 | +| clip_range | 0.2 | +| entropy_loss | -0.38 | +| explained_variance | -0.307 | +| learning_rate | 0.0001 | +| loss | -0.0718 | +| n_updates | 88500 | +| policy_gradient_loss | -0.0499 | +| value_loss | 0.000442 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.117 | +| time/ | | +| fps | 310 | +| iterations | 2799 | +| time_elapsed | 9228 | +| total_timesteps | 2866176 | +| train/ | | +| approx_kl | 1.7526021 | +| clip_fraction | 0.451 | +| clip_range | 0.2 | +| entropy_loss | -0.334 | +| explained_variance | -2.06 | +| learning_rate | 0.0001 | +| loss | -0.0818 | +| n_updates | 88510 | +| policy_gradient_loss | -0.0572 | +| value_loss | 0.000409 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.117 | +| time/ | | +| fps | 310 | +| iterations | 2800 | +| time_elapsed | 9231 | +| total_timesteps | 2867200 | +| train/ | | +| approx_kl | 2.202273 | +| clip_fraction | 0.462 | +| clip_range | 0.2 | +| entropy_loss | -0.371 | +| explained_variance | -2.26 | +| learning_rate | 0.0001 | +| loss | -0.0892 | +| n_updates | 88520 | +| policy_gradient_loss | -0.0605 | +| value_loss | 0.000455 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.117 | +| time/ | | +| fps | 310 | +| iterations | 2801 | +| time_elapsed | 9235 | +| total_timesteps | 2868224 | +| train/ | | +| approx_kl | 2.3451223 | +| clip_fraction | 0.474 | +| clip_range | 0.2 | +| entropy_loss | -0.357 | +| explained_variance | -2.61 | +| learning_rate | 0.0001 | +| loss | -0.0966 | +| n_updates | 88530 | +| policy_gradient_loss | -0.0646 | +| value_loss | 0.000768 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.117 | +| time/ | | +| fps | 310 | +| iterations | 2802 | +| time_elapsed | 9238 | +| total_timesteps | 2869248 | +| train/ | | +| approx_kl | 2.7452826 | +| clip_fraction | 0.499 | +| clip_range | 0.2 | +| entropy_loss | -0.382 | +| explained_variance | -2.57 | +| learning_rate | 0.0001 | +| loss | -0.0657 | +| n_updates | 88540 | +| policy_gradient_loss | -0.0728 | +| value_loss | 0.000371 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.12 | +| time/ | | +| fps | 310 | +| iterations | 2803 | +| time_elapsed | 9242 | +| total_timesteps | 2870272 | +| train/ | | +| approx_kl | 2.3015342 | +| clip_fraction | 0.464 | +| clip_range | 0.2 | +| entropy_loss | -0.337 | +| explained_variance | -1.61 | +| learning_rate | 0.0001 | +| loss | -0.0923 | +| n_updates | 88550 | +| policy_gradient_loss | -0.0649 | +| value_loss | 0.000249 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.12 | +| time/ | | +| fps | 310 | +| iterations | 2804 | +| time_elapsed | 9245 | +| total_timesteps | 2871296 | +| train/ | | +| approx_kl | 2.6566684 | +| clip_fraction | 0.476 | +| clip_range | 0.2 | +| entropy_loss | -0.332 | +| explained_variance | -1.71 | +| learning_rate | 0.0001 | +| loss | -0.0626 | +| n_updates | 88560 | +| policy_gradient_loss | -0.0614 | +| value_loss | 0.000353 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.12 | +| time/ | | +| fps | 310 | +| iterations | 2805 | +| time_elapsed | 9249 | +| total_timesteps | 2872320 | +| train/ | | +| approx_kl | 1.9172434 | +| clip_fraction | 0.51 | +| clip_range | 0.2 | +| entropy_loss | -0.471 | +| explained_variance | -4.47 | +| learning_rate | 0.0001 | +| loss | -0.0818 | +| n_updates | 88570 | +| policy_gradient_loss | -0.0612 | +| value_loss | 0.00075 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.119 | +| time/ | | +| fps | 310 | +| iterations | 2806 | +| time_elapsed | 9252 | +| total_timesteps | 2873344 | +| train/ | | +| approx_kl | 1.685514 | +| clip_fraction | 0.439 | +| clip_range | 0.2 | +| entropy_loss | -0.348 | +| explained_variance | -2.46 | +| learning_rate | 0.0001 | +| loss | -0.0676 | +| n_updates | 88580 | +| policy_gradient_loss | -0.0616 | +| value_loss | 0.000772 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.119 | +| time/ | | +| fps | 310 | +| iterations | 2807 | +| time_elapsed | 9255 | +| total_timesteps | 2874368 | +| train/ | | +| approx_kl | 2.6681068 | +| clip_fraction | 0.465 | +| clip_range | 0.2 | +| entropy_loss | -0.364 | +| explained_variance | -2.94 | +| learning_rate | 0.0001 | +| loss | -0.0925 | +| n_updates | 88590 | +| policy_gradient_loss | -0.0687 | +| value_loss | 0.000392 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.123 | +| time/ | | +| fps | 310 | +| iterations | 2808 | +| time_elapsed | 9258 | +| total_timesteps | 2875392 | +| train/ | | +| approx_kl | 2.4164476 | +| clip_fraction | 0.527 | +| clip_range | 0.2 | +| entropy_loss | -0.469 | +| explained_variance | -0.75 | +| learning_rate | 0.0001 | +| loss | -0.114 | +| n_updates | 88600 | +| policy_gradient_loss | -0.0668 | +| value_loss | 0.000484 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.123 | +| time/ | | +| fps | 310 | +| iterations | 2809 | +| time_elapsed | 9261 | +| total_timesteps | 2876416 | +| train/ | | +| approx_kl | 3.7948418 | +| clip_fraction | 0.451 | +| clip_range | 0.2 | +| entropy_loss | -0.367 | +| explained_variance | -1.6 | +| learning_rate | 0.0001 | +| loss | -0.0976 | +| n_updates | 88610 | +| policy_gradient_loss | -0.0572 | +| value_loss | 0.000479 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.121 | +| time/ | | +| fps | 310 | +| iterations | 2810 | +| time_elapsed | 9265 | +| total_timesteps | 2877440 | +| train/ | | +| approx_kl | 1.9987051 | +| clip_fraction | 0.449 | +| clip_range | 0.2 | +| entropy_loss | -0.331 | +| explained_variance | -7.61 | +| learning_rate | 0.0001 | +| loss | -0.0611 | +| n_updates | 88620 | +| policy_gradient_loss | -0.0577 | +| value_loss | 0.000445 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.114 | +| time/ | | +| fps | 310 | +| iterations | 2811 | +| time_elapsed | 9268 | +| total_timesteps | 2878464 | +| train/ | | +| approx_kl | 1.802546 | +| clip_fraction | 0.422 | +| clip_range | 0.2 | +| entropy_loss | -0.337 | +| explained_variance | -5.95 | +| learning_rate | 0.0001 | +| loss | -0.0804 | +| n_updates | 88630 | +| policy_gradient_loss | -0.0632 | +| value_loss | 0.000394 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.114 | +| time/ | | +| fps | 310 | +| iterations | 2812 | +| time_elapsed | 9271 | +| total_timesteps | 2879488 | +| train/ | | +| approx_kl | 1.4240081 | +| clip_fraction | 0.429 | +| clip_range | 0.2 | +| entropy_loss | -0.322 | +| explained_variance | -0.538 | +| learning_rate | 0.0001 | +| loss | -0.0615 | +| n_updates | 88640 | +| policy_gradient_loss | -0.0519 | +| value_loss | 0.000441 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.112 | +| time/ | | +| fps | 310 | +| iterations | 2813 | +| time_elapsed | 9274 | +| total_timesteps | 2880512 | +| train/ | | +| approx_kl | 2.5965977 | +| clip_fraction | 0.448 | +| clip_range | 0.2 | +| entropy_loss | -0.276 | +| explained_variance | -3.97 | +| learning_rate | 0.0001 | +| loss | -0.0492 | +| n_updates | 88650 | +| policy_gradient_loss | -0.0528 | +| value_loss | 0.000359 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.112 | +| time/ | | +| fps | 310 | +| iterations | 2814 | +| time_elapsed | 9278 | +| total_timesteps | 2881536 | +| train/ | | +| approx_kl | 2.3002577 | +| clip_fraction | 0.455 | +| clip_range | 0.2 | +| entropy_loss | -0.34 | +| explained_variance | -2.13 | +| learning_rate | 0.0001 | +| loss | -0.0926 | +| n_updates | 88660 | +| policy_gradient_loss | -0.0563 | +| value_loss | 0.000475 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.112 | +| time/ | | +| fps | 310 | +| iterations | 2815 | +| time_elapsed | 9281 | +| total_timesteps | 2882560 | +| train/ | | +| approx_kl | 1.8023543 | +| clip_fraction | 0.464 | +| clip_range | 0.2 | +| entropy_loss | -0.362 | +| explained_variance | -2.31 | +| learning_rate | 0.0001 | +| loss | -0.0859 | +| n_updates | 88670 | +| policy_gradient_loss | -0.0617 | +| value_loss | 0.000404 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.117 | +| time/ | | +| fps | 310 | +| iterations | 2816 | +| time_elapsed | 9285 | +| total_timesteps | 2883584 | +| train/ | | +| approx_kl | 3.7395046 | +| clip_fraction | 0.501 | +| clip_range | 0.2 | +| entropy_loss | -0.347 | +| explained_variance | -1.51 | +| learning_rate | 0.0001 | +| loss | -0.0929 | +| n_updates | 88680 | +| policy_gradient_loss | -0.0608 | +| value_loss | 0.000641 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.111 | +| time/ | | +| fps | 310 | +| iterations | 2817 | +| time_elapsed | 9288 | +| total_timesteps | 2884608 | +| train/ | | +| approx_kl | 1.6448104 | +| clip_fraction | 0.454 | +| clip_range | 0.2 | +| entropy_loss | -0.326 | +| explained_variance | -5.21 | +| learning_rate | 0.0001 | +| loss | -0.0997 | +| n_updates | 88690 | +| policy_gradient_loss | -0.0625 | +| value_loss | 0.00062 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.111 | +| time/ | | +| fps | 310 | +| iterations | 2818 | +| time_elapsed | 9291 | +| total_timesteps | 2885632 | +| train/ | | +| approx_kl | 1.388973 | +| clip_fraction | 0.454 | +| clip_range | 0.2 | +| entropy_loss | -0.384 | +| explained_variance | -0.884 | +| learning_rate | 0.0001 | +| loss | -0.0912 | +| n_updates | 88700 | +| policy_gradient_loss | -0.0494 | +| value_loss | 0.000422 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.111 | +| time/ | | +| fps | 310 | +| iterations | 2819 | +| time_elapsed | 9295 | +| total_timesteps | 2886656 | +| train/ | | +| approx_kl | 2.1016445 | +| clip_fraction | 0.496 | +| clip_range | 0.2 | +| entropy_loss | -0.395 | +| explained_variance | -2.08 | +| learning_rate | 0.0001 | +| loss | -0.0874 | +| n_updates | 88710 | +| policy_gradient_loss | -0.0644 | +| value_loss | 0.000397 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.117 | +| time/ | | +| fps | 310 | +| iterations | 2820 | +| time_elapsed | 9298 | +| total_timesteps | 2887680 | +| train/ | | +| approx_kl | 1.7793825 | +| clip_fraction | 0.494 | +| clip_range | 0.2 | +| entropy_loss | -0.391 | +| explained_variance | -0.475 | +| learning_rate | 0.0001 | +| loss | -0.0952 | +| n_updates | 88720 | +| policy_gradient_loss | -0.0732 | +| value_loss | 0.000665 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.117 | +| time/ | | +| fps | 310 | +| iterations | 2821 | +| time_elapsed | 9302 | +| total_timesteps | 2888704 | +| train/ | | +| approx_kl | 1.7961632 | +| clip_fraction | 0.465 | +| clip_range | 0.2 | +| entropy_loss | -0.347 | +| explained_variance | -4.42 | +| learning_rate | 0.0001 | +| loss | -0.0854 | +| n_updates | 88730 | +| policy_gradient_loss | -0.0619 | +| value_loss | 0.000711 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.113 | +| time/ | | +| fps | 310 | +| iterations | 2822 | +| time_elapsed | 9305 | +| total_timesteps | 2889728 | +| train/ | | +| approx_kl | 2.1671436 | +| clip_fraction | 0.466 | +| clip_range | 0.2 | +| entropy_loss | -0.378 | +| explained_variance | -9.18 | +| learning_rate | 0.0001 | +| loss | -0.081 | +| n_updates | 88740 | +| policy_gradient_loss | -0.0701 | +| value_loss | 0.000484 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.113 | +| time/ | | +| fps | 310 | +| iterations | 2823 | +| time_elapsed | 9309 | +| total_timesteps | 2890752 | +| train/ | | +| approx_kl | 1.9805918 | +| clip_fraction | 0.491 | +| clip_range | 0.2 | +| entropy_loss | -0.376 | +| explained_variance | -1.46 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 88750 | +| policy_gradient_loss | -0.0643 | +| value_loss | 0.000481 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.106 | +| time/ | | +| fps | 310 | +| iterations | 2824 | +| time_elapsed | 9312 | +| total_timesteps | 2891776 | +| train/ | | +| approx_kl | 2.0765028 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.344 | +| explained_variance | -9.21 | +| learning_rate | 0.0001 | +| loss | -0.108 | +| n_updates | 88760 | +| policy_gradient_loss | -0.0718 | +| value_loss | 0.000445 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.106 | +| time/ | | +| fps | 310 | +| iterations | 2825 | +| time_elapsed | 9315 | +| total_timesteps | 2892800 | +| train/ | | +| approx_kl | 1.9711587 | +| clip_fraction | 0.473 | +| clip_range | 0.2 | +| entropy_loss | -0.359 | +| explained_variance | -9.09 | +| learning_rate | 0.0001 | +| loss | -0.0868 | +| n_updates | 88770 | +| policy_gradient_loss | -0.0651 | +| value_loss | 0.000395 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.103 | +| time/ | | +| fps | 310 | +| iterations | 2826 | +| time_elapsed | 9318 | +| total_timesteps | 2893824 | +| train/ | | +| approx_kl | 1.3412142 | +| clip_fraction | 0.454 | +| clip_range | 0.2 | +| entropy_loss | -0.424 | +| explained_variance | -3.62 | +| learning_rate | 0.0001 | +| loss | -0.076 | +| n_updates | 88780 | +| policy_gradient_loss | -0.0653 | +| value_loss | 0.000204 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.103 | +| time/ | | +| fps | 310 | +| iterations | 2827 | +| time_elapsed | 9321 | +| total_timesteps | 2894848 | +| train/ | | +| approx_kl | 1.6069168 | +| clip_fraction | 0.447 | +| clip_range | 0.2 | +| entropy_loss | -0.353 | +| explained_variance | -1.53 | +| learning_rate | 0.0001 | +| loss | -0.0712 | +| n_updates | 88790 | +| policy_gradient_loss | -0.0627 | +| value_loss | 0.000582 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.103 | +| time/ | | +| fps | 310 | +| iterations | 2828 | +| time_elapsed | 9324 | +| total_timesteps | 2895872 | +| train/ | | +| approx_kl | 2.599598 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.379 | +| explained_variance | -8 | +| learning_rate | 0.0001 | +| loss | -0.0812 | +| n_updates | 88800 | +| policy_gradient_loss | -0.0622 | +| value_loss | 0.000512 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.78e+03 | +| ep_rew_mean | 0.102 | +| time/ | | +| fps | 310 | +| iterations | 2829 | +| time_elapsed | 9327 | +| total_timesteps | 2896896 | +| train/ | | +| approx_kl | 2.6008005 | +| clip_fraction | 0.477 | +| clip_range | 0.2 | +| entropy_loss | -0.429 | +| explained_variance | -2.56 | +| learning_rate | 0.0001 | +| loss | -0.106 | +| n_updates | 88810 | +| policy_gradient_loss | -0.0606 | +| value_loss | 0.000466 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.78e+03 | +| ep_rew_mean | 0.102 | +| time/ | | +| fps | 310 | +| iterations | 2830 | +| time_elapsed | 9331 | +| total_timesteps | 2897920 | +| train/ | | +| approx_kl | 2.176783 | +| clip_fraction | 0.478 | +| clip_range | 0.2 | +| entropy_loss | -0.372 | +| explained_variance | -2.97 | +| learning_rate | 0.0001 | +| loss | -0.0709 | +| n_updates | 88820 | +| policy_gradient_loss | -0.0646 | +| value_loss | 0.000661 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.0974 | +| time/ | | +| fps | 310 | +| iterations | 2831 | +| time_elapsed | 9334 | +| total_timesteps | 2898944 | +| train/ | | +| approx_kl | 2.1697083 | +| clip_fraction | 0.514 | +| clip_range | 0.2 | +| entropy_loss | -0.38 | +| explained_variance | -3.66 | +| learning_rate | 0.0001 | +| loss | -0.0885 | +| n_updates | 88830 | +| policy_gradient_loss | -0.0715 | +| value_loss | 0.000372 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.105 | +| time/ | | +| fps | 310 | +| iterations | 2832 | +| time_elapsed | 9337 | +| total_timesteps | 2899968 | +| train/ | | +| approx_kl | 1.7706244 | +| clip_fraction | 0.444 | +| clip_range | 0.2 | +| entropy_loss | -0.333 | +| explained_variance | -0.837 | +| learning_rate | 0.0001 | +| loss | -0.0974 | +| n_updates | 88840 | +| policy_gradient_loss | -0.0626 | +| value_loss | 0.000471 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.105 | +| time/ | | +| fps | 310 | +| iterations | 2833 | +| time_elapsed | 9340 | +| total_timesteps | 2900992 | +| train/ | | +| approx_kl | 3.559694 | +| clip_fraction | 0.452 | +| clip_range | 0.2 | +| entropy_loss | -0.352 | +| explained_variance | -1.03 | +| learning_rate | 0.0001 | +| loss | -0.0786 | +| n_updates | 88850 | +| policy_gradient_loss | -0.0644 | +| value_loss | 0.000652 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.105 | +| time/ | | +| fps | 310 | +| iterations | 2834 | +| time_elapsed | 9344 | +| total_timesteps | 2902016 | +| train/ | | +| approx_kl | 2.2919283 | +| clip_fraction | 0.438 | +| clip_range | 0.2 | +| entropy_loss | -0.33 | +| explained_variance | -3.84 | +| learning_rate | 0.0001 | +| loss | -0.0662 | +| n_updates | 88860 | +| policy_gradient_loss | -0.0635 | +| value_loss | 0.000465 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.108 | +| time/ | | +| fps | 310 | +| iterations | 2835 | +| time_elapsed | 9347 | +| total_timesteps | 2903040 | +| train/ | | +| approx_kl | 1.7983863 | +| clip_fraction | 0.467 | +| clip_range | 0.2 | +| entropy_loss | -0.362 | +| explained_variance | -0.97 | +| learning_rate | 0.0001 | +| loss | -0.0884 | +| n_updates | 88870 | +| policy_gradient_loss | -0.065 | +| value_loss | 0.00061 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.117 | +| time/ | | +| fps | 310 | +| iterations | 2836 | +| time_elapsed | 9351 | +| total_timesteps | 2904064 | +| train/ | | +| approx_kl | 5.9017 | +| clip_fraction | 0.49 | +| clip_range | 0.2 | +| entropy_loss | -0.443 | +| explained_variance | -2.37 | +| learning_rate | 0.0001 | +| loss | -0.0994 | +| n_updates | 88880 | +| policy_gradient_loss | -0.0639 | +| value_loss | 0.000547 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.117 | +| time/ | | +| fps | 310 | +| iterations | 2837 | +| time_elapsed | 9354 | +| total_timesteps | 2905088 | +| train/ | | +| approx_kl | 1.7283924 | +| clip_fraction | 0.496 | +| clip_range | 0.2 | +| entropy_loss | -0.429 | +| explained_variance | -0.242 | +| learning_rate | 0.0001 | +| loss | -0.105 | +| n_updates | 88890 | +| policy_gradient_loss | -0.0678 | +| value_loss | 0.000759 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.117 | +| time/ | | +| fps | 310 | +| iterations | 2838 | +| time_elapsed | 9358 | +| total_timesteps | 2906112 | +| train/ | | +| approx_kl | 2.4891691 | +| clip_fraction | 0.448 | +| clip_range | 0.2 | +| entropy_loss | -0.318 | +| explained_variance | -1.73 | +| learning_rate | 0.0001 | +| loss | -0.0609 | +| n_updates | 88900 | +| policy_gradient_loss | -0.059 | +| value_loss | 0.00085 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.8e+03 | +| ep_rew_mean | 0.117 | +| time/ | | +| fps | 310 | +| iterations | 2839 | +| time_elapsed | 9361 | +| total_timesteps | 2907136 | +| train/ | | +| approx_kl | 1.892781 | +| clip_fraction | 0.455 | +| clip_range | 0.2 | +| entropy_loss | -0.356 | +| explained_variance | -5.95 | +| learning_rate | 0.0001 | +| loss | -0.0918 | +| n_updates | 88910 | +| policy_gradient_loss | -0.0634 | +| value_loss | 0.000537 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.8e+03 | +| ep_rew_mean | 0.117 | +| time/ | | +| fps | 310 | +| iterations | 2840 | +| time_elapsed | 9365 | +| total_timesteps | 2908160 | +| train/ | | +| approx_kl | 1.9654706 | +| clip_fraction | 0.448 | +| clip_range | 0.2 | +| entropy_loss | -0.334 | +| explained_variance | -5.67 | +| learning_rate | 0.0001 | +| loss | -0.0595 | +| n_updates | 88920 | +| policy_gradient_loss | -0.0621 | +| value_loss | 0.000252 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.8e+03 | +| ep_rew_mean | 0.117 | +| time/ | | +| fps | 310 | +| iterations | 2841 | +| time_elapsed | 9368 | +| total_timesteps | 2909184 | +| train/ | | +| approx_kl | 2.104094 | +| clip_fraction | 0.495 | +| clip_range | 0.2 | +| entropy_loss | -0.39 | +| explained_variance | -0.729 | +| learning_rate | 0.0001 | +| loss | -0.0971 | +| n_updates | 88930 | +| policy_gradient_loss | -0.0664 | +| value_loss | 0.00056 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.81e+03 | +| ep_rew_mean | 0.115 | +| time/ | | +| fps | 310 | +| iterations | 2842 | +| time_elapsed | 9371 | +| total_timesteps | 2910208 | +| train/ | | +| approx_kl | 2.0680249 | +| clip_fraction | 0.468 | +| clip_range | 0.2 | +| entropy_loss | -0.375 | +| explained_variance | -6.47 | +| learning_rate | 0.0001 | +| loss | -0.0796 | +| n_updates | 88940 | +| policy_gradient_loss | -0.0633 | +| value_loss | 0.000446 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.81e+03 | +| ep_rew_mean | 0.112 | +| time/ | | +| fps | 310 | +| iterations | 2843 | +| time_elapsed | 9375 | +| total_timesteps | 2911232 | +| train/ | | +| approx_kl | 1.9979633 | +| clip_fraction | 0.44 | +| clip_range | 0.2 | +| entropy_loss | -0.341 | +| explained_variance | -4.17 | +| learning_rate | 0.0001 | +| loss | -0.112 | +| n_updates | 88950 | +| policy_gradient_loss | -0.064 | +| value_loss | 0.000335 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.81e+03 | +| ep_rew_mean | 0.11 | +| time/ | | +| fps | 310 | +| iterations | 2844 | +| time_elapsed | 9378 | +| total_timesteps | 2912256 | +| train/ | | +| approx_kl | 2.069188 | +| clip_fraction | 0.443 | +| clip_range | 0.2 | +| entropy_loss | -0.405 | +| explained_variance | -0.646 | +| learning_rate | 0.0001 | +| loss | -0.063 | +| n_updates | 88960 | +| policy_gradient_loss | -0.0536 | +| value_loss | 0.000437 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.8e+03 | +| ep_rew_mean | 0.109 | +| time/ | | +| fps | 310 | +| iterations | 2845 | +| time_elapsed | 9381 | +| total_timesteps | 2913280 | +| train/ | | +| approx_kl | 1.8164238 | +| clip_fraction | 0.436 | +| clip_range | 0.2 | +| entropy_loss | -0.411 | +| explained_variance | -1.05 | +| learning_rate | 0.0001 | +| loss | -0.045 | +| n_updates | 88970 | +| policy_gradient_loss | -0.0523 | +| value_loss | 0.000514 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.8e+03 | +| ep_rew_mean | 0.109 | +| time/ | | +| fps | 310 | +| iterations | 2846 | +| time_elapsed | 9384 | +| total_timesteps | 2914304 | +| train/ | | +| approx_kl | 2.0769079 | +| clip_fraction | 0.394 | +| clip_range | 0.2 | +| entropy_loss | -0.312 | +| explained_variance | -0.596 | +| learning_rate | 0.0001 | +| loss | -0.0896 | +| n_updates | 88980 | +| policy_gradient_loss | -0.053 | +| value_loss | 0.000636 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.81e+03 | +| ep_rew_mean | 0.112 | +| time/ | | +| fps | 310 | +| iterations | 2847 | +| time_elapsed | 9388 | +| total_timesteps | 2915328 | +| train/ | | +| approx_kl | 1.4754493 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.479 | +| explained_variance | -3.93 | +| learning_rate | 0.0001 | +| loss | -0.0938 | +| n_updates | 88990 | +| policy_gradient_loss | -0.0685 | +| value_loss | 0.000305 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.81e+03 | +| ep_rew_mean | 0.112 | +| time/ | | +| fps | 310 | +| iterations | 2848 | +| time_elapsed | 9391 | +| total_timesteps | 2916352 | +| train/ | | +| approx_kl | 1.9222072 | +| clip_fraction | 0.429 | +| clip_range | 0.2 | +| entropy_loss | -0.304 | +| explained_variance | -1.08 | +| learning_rate | 0.0001 | +| loss | -0.0766 | +| n_updates | 89000 | +| policy_gradient_loss | -0.0585 | +| value_loss | 0.000659 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.81e+03 | +| ep_rew_mean | 0.113 | +| time/ | | +| fps | 310 | +| iterations | 2849 | +| time_elapsed | 9394 | +| total_timesteps | 2917376 | +| train/ | | +| approx_kl | 2.7347183 | +| clip_fraction | 0.46 | +| clip_range | 0.2 | +| entropy_loss | -0.357 | +| explained_variance | -2.3 | +| learning_rate | 0.0001 | +| loss | -0.0354 | +| n_updates | 89010 | +| policy_gradient_loss | -0.0545 | +| value_loss | 0.000662 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.81e+03 | +| ep_rew_mean | 0.113 | +| time/ | | +| fps | 310 | +| iterations | 2850 | +| time_elapsed | 9397 | +| total_timesteps | 2918400 | +| train/ | | +| approx_kl | 1.9503675 | +| clip_fraction | 0.413 | +| clip_range | 0.2 | +| entropy_loss | -0.283 | +| explained_variance | -8.11 | +| learning_rate | 0.0001 | +| loss | -0.0802 | +| n_updates | 89020 | +| policy_gradient_loss | -0.0599 | +| value_loss | 0.000518 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.81e+03 | +| ep_rew_mean | 0.111 | +| time/ | | +| fps | 310 | +| iterations | 2851 | +| time_elapsed | 9401 | +| total_timesteps | 2919424 | +| train/ | | +| approx_kl | 1.9542663 | +| clip_fraction | 0.492 | +| clip_range | 0.2 | +| entropy_loss | -0.408 | +| explained_variance | -4.36 | +| learning_rate | 0.0001 | +| loss | -0.0952 | +| n_updates | 89030 | +| policy_gradient_loss | -0.0705 | +| value_loss | 0.000388 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.81e+03 | +| ep_rew_mean | 0.111 | +| time/ | | +| fps | 310 | +| iterations | 2852 | +| time_elapsed | 9404 | +| total_timesteps | 2920448 | +| train/ | | +| approx_kl | 3.652411 | +| clip_fraction | 0.439 | +| clip_range | 0.2 | +| entropy_loss | -0.345 | +| explained_variance | -1.63 | +| learning_rate | 0.0001 | +| loss | -0.0824 | +| n_updates | 89040 | +| policy_gradient_loss | -0.0608 | +| value_loss | 0.000636 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.81e+03 | +| ep_rew_mean | 0.111 | +| time/ | | +| fps | 310 | +| iterations | 2853 | +| time_elapsed | 9408 | +| total_timesteps | 2921472 | +| train/ | | +| approx_kl | 2.3487642 | +| clip_fraction | 0.468 | +| clip_range | 0.2 | +| entropy_loss | -0.351 | +| explained_variance | -6.66 | +| learning_rate | 0.0001 | +| loss | -0.0835 | +| n_updates | 89050 | +| policy_gradient_loss | -0.0673 | +| value_loss | 0.000394 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.82e+03 | +| ep_rew_mean | 0.109 | +| time/ | | +| fps | 310 | +| iterations | 2854 | +| time_elapsed | 9411 | +| total_timesteps | 2922496 | +| train/ | | +| approx_kl | 2.017398 | +| clip_fraction | 0.469 | +| clip_range | 0.2 | +| entropy_loss | -0.351 | +| explained_variance | -1.81 | +| learning_rate | 0.0001 | +| loss | -0.0693 | +| n_updates | 89060 | +| policy_gradient_loss | -0.0599 | +| value_loss | 0.000497 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.82e+03 | +| ep_rew_mean | 0.106 | +| time/ | | +| fps | 310 | +| iterations | 2855 | +| time_elapsed | 9414 | +| total_timesteps | 2923520 | +| train/ | | +| approx_kl | 1.9790711 | +| clip_fraction | 0.469 | +| clip_range | 0.2 | +| entropy_loss | -0.355 | +| explained_variance | -4.02 | +| learning_rate | 0.0001 | +| loss | -0.0705 | +| n_updates | 89070 | +| policy_gradient_loss | -0.0588 | +| value_loss | 0.000458 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.82e+03 | +| ep_rew_mean | 0.106 | +| time/ | | +| fps | 310 | +| iterations | 2856 | +| time_elapsed | 9418 | +| total_timesteps | 2924544 | +| train/ | | +| approx_kl | 1.6347718 | +| clip_fraction | 0.464 | +| clip_range | 0.2 | +| entropy_loss | -0.429 | +| explained_variance | -2.38 | +| learning_rate | 0.0001 | +| loss | -0.0934 | +| n_updates | 89080 | +| policy_gradient_loss | -0.0617 | +| value_loss | 0.000233 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.82e+03 | +| ep_rew_mean | 0.106 | +| time/ | | +| fps | 310 | +| iterations | 2857 | +| time_elapsed | 9421 | +| total_timesteps | 2925568 | +| train/ | | +| approx_kl | 2.452228 | +| clip_fraction | 0.454 | +| clip_range | 0.2 | +| entropy_loss | -0.319 | +| explained_variance | -0.877 | +| learning_rate | 0.0001 | +| loss | -0.066 | +| n_updates | 89090 | +| policy_gradient_loss | -0.0587 | +| value_loss | 0.000539 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.105 | +| time/ | | +| fps | 310 | +| iterations | 2858 | +| time_elapsed | 9425 | +| total_timesteps | 2926592 | +| train/ | | +| approx_kl | 2.468244 | +| clip_fraction | 0.466 | +| clip_range | 0.2 | +| entropy_loss | -0.331 | +| explained_variance | -9.32 | +| learning_rate | 0.0001 | +| loss | -0.0916 | +| n_updates | 89100 | +| policy_gradient_loss | -0.063 | +| value_loss | 0.000784 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.105 | +| time/ | | +| fps | 310 | +| iterations | 2859 | +| time_elapsed | 9428 | +| total_timesteps | 2927616 | +| train/ | | +| approx_kl | 1.8136563 | +| clip_fraction | 0.451 | +| clip_range | 0.2 | +| entropy_loss | -0.331 | +| explained_variance | -3.13 | +| learning_rate | 0.0001 | +| loss | -0.0746 | +| n_updates | 89110 | +| policy_gradient_loss | -0.0655 | +| value_loss | 0.000582 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.1 | +| time/ | | +| fps | 310 | +| iterations | 2860 | +| time_elapsed | 9431 | +| total_timesteps | 2928640 | +| train/ | | +| approx_kl | 2.4521022 | +| clip_fraction | 0.468 | +| clip_range | 0.2 | +| entropy_loss | -0.39 | +| explained_variance | -1.3 | +| learning_rate | 0.0001 | +| loss | -0.0751 | +| n_updates | 89120 | +| policy_gradient_loss | -0.047 | +| value_loss | 0.000369 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.1 | +| time/ | | +| fps | 310 | +| iterations | 2861 | +| time_elapsed | 9434 | +| total_timesteps | 2929664 | +| train/ | | +| approx_kl | 2.0055497 | +| clip_fraction | 0.453 | +| clip_range | 0.2 | +| entropy_loss | -0.33 | +| explained_variance | -1.01 | +| learning_rate | 0.0001 | +| loss | -0.0803 | +| n_updates | 89130 | +| policy_gradient_loss | -0.0576 | +| value_loss | 0.000572 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.0953 | +| time/ | | +| fps | 310 | +| iterations | 2862 | +| time_elapsed | 9437 | +| total_timesteps | 2930688 | +| train/ | | +| approx_kl | 1.9641788 | +| clip_fraction | 0.441 | +| clip_range | 0.2 | +| entropy_loss | -0.332 | +| explained_variance | -4.66 | +| learning_rate | 0.0001 | +| loss | -0.0792 | +| n_updates | 89140 | +| policy_gradient_loss | -0.0669 | +| value_loss | 0.000511 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.0953 | +| time/ | | +| fps | 310 | +| iterations | 2863 | +| time_elapsed | 9441 | +| total_timesteps | 2931712 | +| train/ | | +| approx_kl | 1.6409231 | +| clip_fraction | 0.407 | +| clip_range | 0.2 | +| entropy_loss | -0.319 | +| explained_variance | -1.05 | +| learning_rate | 0.0001 | +| loss | -0.0721 | +| n_updates | 89150 | +| policy_gradient_loss | -0.0527 | +| value_loss | 0.000718 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.1 | +| time/ | | +| fps | 310 | +| iterations | 2864 | +| time_elapsed | 9444 | +| total_timesteps | 2932736 | +| train/ | | +| approx_kl | 1.9993993 | +| clip_fraction | 0.479 | +| clip_range | 0.2 | +| entropy_loss | -0.381 | +| explained_variance | -1.46 | +| learning_rate | 0.0001 | +| loss | -0.082 | +| n_updates | 89160 | +| policy_gradient_loss | -0.0611 | +| value_loss | 0.000899 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.094 | +| time/ | | +| fps | 310 | +| iterations | 2865 | +| time_elapsed | 9447 | +| total_timesteps | 2933760 | +| train/ | | +| approx_kl | 1.9160541 | +| clip_fraction | 0.45 | +| clip_range | 0.2 | +| entropy_loss | -0.35 | +| explained_variance | -2.79 | +| learning_rate | 0.0001 | +| loss | -0.0412 | +| n_updates | 89170 | +| policy_gradient_loss | -0.0543 | +| value_loss | 0.000685 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.094 | +| time/ | | +| fps | 310 | +| iterations | 2866 | +| time_elapsed | 9450 | +| total_timesteps | 2934784 | +| train/ | | +| approx_kl | 1.8656205 | +| clip_fraction | 0.435 | +| clip_range | 0.2 | +| entropy_loss | -0.362 | +| explained_variance | -1.43 | +| learning_rate | 0.0001 | +| loss | -0.0819 | +| n_updates | 89180 | +| policy_gradient_loss | -0.0572 | +| value_loss | 0.000735 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.095 | +| time/ | | +| fps | 310 | +| iterations | 2867 | +| time_elapsed | 9453 | +| total_timesteps | 2935808 | +| train/ | | +| approx_kl | 2.0431113 | +| clip_fraction | 0.466 | +| clip_range | 0.2 | +| entropy_loss | -0.384 | +| explained_variance | -8.25 | +| learning_rate | 0.0001 | +| loss | -0.0865 | +| n_updates | 89190 | +| policy_gradient_loss | -0.0662 | +| value_loss | 0.000528 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.095 | +| time/ | | +| fps | 310 | +| iterations | 2868 | +| time_elapsed | 9456 | +| total_timesteps | 2936832 | +| train/ | | +| approx_kl | 2.1086528 | +| clip_fraction | 0.429 | +| clip_range | 0.2 | +| entropy_loss | -0.304 | +| explained_variance | -1.66 | +| learning_rate | 0.0001 | +| loss | -0.0912 | +| n_updates | 89200 | +| policy_gradient_loss | -0.0609 | +| value_loss | 0.000742 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.0905 | +| time/ | | +| fps | 310 | +| iterations | 2869 | +| time_elapsed | 9460 | +| total_timesteps | 2937856 | +| train/ | | +| approx_kl | 2.729811 | +| clip_fraction | 0.464 | +| clip_range | 0.2 | +| entropy_loss | -0.325 | +| explained_variance | -0.976 | +| learning_rate | 0.0001 | +| loss | -0.0883 | +| n_updates | 89210 | +| policy_gradient_loss | -0.0619 | +| value_loss | 0.000665 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.0905 | +| time/ | | +| fps | 310 | +| iterations | 2870 | +| time_elapsed | 9463 | +| total_timesteps | 2938880 | +| train/ | | +| approx_kl | 2.010158 | +| clip_fraction | 0.426 | +| clip_range | 0.2 | +| entropy_loss | -0.316 | +| explained_variance | -2.3 | +| learning_rate | 0.0001 | +| loss | -0.0933 | +| n_updates | 89220 | +| policy_gradient_loss | -0.0593 | +| value_loss | 0.000824 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.0838 | +| time/ | | +| fps | 310 | +| iterations | 2871 | +| time_elapsed | 9467 | +| total_timesteps | 2939904 | +| train/ | | +| approx_kl | 1.8357427 | +| clip_fraction | 0.472 | +| clip_range | 0.2 | +| entropy_loss | -0.382 | +| explained_variance | -2.84 | +| learning_rate | 0.0001 | +| loss | -0.0993 | +| n_updates | 89230 | +| policy_gradient_loss | -0.0636 | +| value_loss | 0.000398 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.0838 | +| time/ | | +| fps | 310 | +| iterations | 2872 | +| time_elapsed | 9470 | +| total_timesteps | 2940928 | +| train/ | | +| approx_kl | 1.9685148 | +| clip_fraction | 0.456 | +| clip_range | 0.2 | +| entropy_loss | -0.387 | +| explained_variance | -0.344 | +| learning_rate | 0.0001 | +| loss | -0.0395 | +| n_updates | 89240 | +| policy_gradient_loss | -0.0607 | +| value_loss | 0.000719 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.0897 | +| time/ | | +| fps | 310 | +| iterations | 2873 | +| time_elapsed | 9474 | +| total_timesteps | 2941952 | +| train/ | | +| approx_kl | 19.389019 | +| clip_fraction | 0.432 | +| clip_range | 0.2 | +| entropy_loss | -0.298 | +| explained_variance | -3.45 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 89250 | +| policy_gradient_loss | -0.0577 | +| value_loss | 0.000931 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.0897 | +| time/ | | +| fps | 310 | +| iterations | 2874 | +| time_elapsed | 9477 | +| total_timesteps | 2942976 | +| train/ | | +| approx_kl | 2.1684074 | +| clip_fraction | 0.453 | +| clip_range | 0.2 | +| entropy_loss | -0.379 | +| explained_variance | -1.38 | +| learning_rate | 0.0001 | +| loss | -0.085 | +| n_updates | 89260 | +| policy_gradient_loss | -0.0592 | +| value_loss | 0.00053 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.0884 | +| time/ | | +| fps | 310 | +| iterations | 2875 | +| time_elapsed | 9481 | +| total_timesteps | 2944000 | +| train/ | | +| approx_kl | 2.0762548 | +| clip_fraction | 0.521 | +| clip_range | 0.2 | +| entropy_loss | -0.443 | +| explained_variance | -0.973 | +| learning_rate | 0.0001 | +| loss | -0.0874 | +| n_updates | 89270 | +| policy_gradient_loss | -0.0674 | +| value_loss | 0.000622 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.0883 | +| time/ | | +| fps | 310 | +| iterations | 2876 | +| time_elapsed | 9484 | +| total_timesteps | 2945024 | +| train/ | | +| approx_kl | 1.8776565 | +| clip_fraction | 0.446 | +| clip_range | 0.2 | +| entropy_loss | -0.349 | +| explained_variance | -4.88 | +| learning_rate | 0.0001 | +| loss | -0.0726 | +| n_updates | 89280 | +| policy_gradient_loss | -0.0622 | +| value_loss | 0.000664 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.0883 | +| time/ | | +| fps | 310 | +| iterations | 2877 | +| time_elapsed | 9488 | +| total_timesteps | 2946048 | +| train/ | | +| approx_kl | 2.069266 | +| clip_fraction | 0.436 | +| clip_range | 0.2 | +| entropy_loss | -0.307 | +| explained_variance | -2.37 | +| learning_rate | 0.0001 | +| loss | -0.0798 | +| n_updates | 89290 | +| policy_gradient_loss | -0.0659 | +| value_loss | 0.000474 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.0965 | +| time/ | | +| fps | 310 | +| iterations | 2878 | +| time_elapsed | 9491 | +| total_timesteps | 2947072 | +| train/ | | +| approx_kl | 2.020917 | +| clip_fraction | 0.486 | +| clip_range | 0.2 | +| entropy_loss | -0.345 | +| explained_variance | -0.935 | +| learning_rate | 0.0001 | +| loss | -0.0732 | +| n_updates | 89300 | +| policy_gradient_loss | -0.068 | +| value_loss | 0.000706 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.0944 | +| time/ | | +| fps | 310 | +| iterations | 2879 | +| time_elapsed | 9494 | +| total_timesteps | 2948096 | +| train/ | | +| approx_kl | 2.1927543 | +| clip_fraction | 0.482 | +| clip_range | 0.2 | +| entropy_loss | -0.342 | +| explained_variance | -1.99 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 89310 | +| policy_gradient_loss | -0.0623 | +| value_loss | 0.00057 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.0944 | +| time/ | | +| fps | 310 | +| iterations | 2880 | +| time_elapsed | 9497 | +| total_timesteps | 2949120 | +| train/ | | +| approx_kl | 2.052548 | +| clip_fraction | 0.427 | +| clip_range | 0.2 | +| entropy_loss | -0.338 | +| explained_variance | -1.33 | +| learning_rate | 0.0001 | +| loss | -0.0557 | +| n_updates | 89320 | +| policy_gradient_loss | -0.045 | +| value_loss | 0.000451 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.0944 | +| time/ | | +| fps | 310 | +| iterations | 2881 | +| time_elapsed | 9501 | +| total_timesteps | 2950144 | +| train/ | | +| approx_kl | 1.366045 | +| clip_fraction | 0.451 | +| clip_range | 0.2 | +| entropy_loss | -0.382 | +| explained_variance | -6.95 | +| learning_rate | 0.0001 | +| loss | -0.0895 | +| n_updates | 89330 | +| policy_gradient_loss | -0.0571 | +| value_loss | 0.000361 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.0944 | +| time/ | | +| fps | 310 | +| iterations | 2882 | +| time_elapsed | 9504 | +| total_timesteps | 2951168 | +| train/ | | +| approx_kl | 2.2634182 | +| clip_fraction | 0.451 | +| clip_range | 0.2 | +| entropy_loss | -0.345 | +| explained_variance | -2.24 | +| learning_rate | 0.0001 | +| loss | -0.0699 | +| n_updates | 89340 | +| policy_gradient_loss | -0.0665 | +| value_loss | 0.000418 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.0962 | +| time/ | | +| fps | 310 | +| iterations | 2883 | +| time_elapsed | 9507 | +| total_timesteps | 2952192 | +| train/ | | +| approx_kl | 2.8591087 | +| clip_fraction | 0.474 | +| clip_range | 0.2 | +| entropy_loss | -0.394 | +| explained_variance | -2.12 | +| learning_rate | 0.0001 | +| loss | -0.107 | +| n_updates | 89350 | +| policy_gradient_loss | -0.0644 | +| value_loss | 0.000316 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.0953 | +| time/ | | +| fps | 310 | +| iterations | 2884 | +| time_elapsed | 9510 | +| total_timesteps | 2953216 | +| train/ | | +| approx_kl | 2.5065212 | +| clip_fraction | 0.447 | +| clip_range | 0.2 | +| entropy_loss | -0.352 | +| explained_variance | -1.97 | +| learning_rate | 0.0001 | +| loss | -0.0801 | +| n_updates | 89360 | +| policy_gradient_loss | -0.0585 | +| value_loss | 0.000316 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.0953 | +| time/ | | +| fps | 310 | +| iterations | 2885 | +| time_elapsed | 9513 | +| total_timesteps | 2954240 | +| train/ | | +| approx_kl | 1.9737105 | +| clip_fraction | 0.477 | +| clip_range | 0.2 | +| entropy_loss | -0.384 | +| explained_variance | -0.44 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 89370 | +| policy_gradient_loss | -0.0596 | +| value_loss | 0.000742 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.095 | +| time/ | | +| fps | 310 | +| iterations | 2886 | +| time_elapsed | 9516 | +| total_timesteps | 2955264 | +| train/ | | +| approx_kl | 2.1061 | +| clip_fraction | 0.501 | +| clip_range | 0.2 | +| entropy_loss | -0.374 | +| explained_variance | -4.85 | +| learning_rate | 0.0001 | +| loss | -0.093 | +| n_updates | 89380 | +| policy_gradient_loss | -0.0747 | +| value_loss | 0.00043 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.095 | +| time/ | | +| fps | 310 | +| iterations | 2887 | +| time_elapsed | 9520 | +| total_timesteps | 2956288 | +| train/ | | +| approx_kl | 1.8695781 | +| clip_fraction | 0.45 | +| clip_range | 0.2 | +| entropy_loss | -0.344 | +| explained_variance | -1.71 | +| learning_rate | 0.0001 | +| loss | -0.0624 | +| n_updates | 89390 | +| policy_gradient_loss | -0.0589 | +| value_loss | 0.000801 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.0977 | +| time/ | | +| fps | 310 | +| iterations | 2888 | +| time_elapsed | 9523 | +| total_timesteps | 2957312 | +| train/ | | +| approx_kl | 2.0395515 | +| clip_fraction | 0.476 | +| clip_range | 0.2 | +| entropy_loss | -0.376 | +| explained_variance | -1.86 | +| learning_rate | 0.0001 | +| loss | -0.0869 | +| n_updates | 89400 | +| policy_gradient_loss | -0.0673 | +| value_loss | 0.000885 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.1 | +| time/ | | +| fps | 310 | +| iterations | 2889 | +| time_elapsed | 9526 | +| total_timesteps | 2958336 | +| train/ | | +| approx_kl | 6.77692 | +| clip_fraction | 0.465 | +| clip_range | 0.2 | +| entropy_loss | -0.373 | +| explained_variance | -2.34 | +| learning_rate | 0.0001 | +| loss | -0.096 | +| n_updates | 89410 | +| policy_gradient_loss | -0.0666 | +| value_loss | 0.000884 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.1 | +| time/ | | +| fps | 310 | +| iterations | 2890 | +| time_elapsed | 9529 | +| total_timesteps | 2959360 | +| train/ | | +| approx_kl | 2.4506958 | +| clip_fraction | 0.479 | +| clip_range | 0.2 | +| entropy_loss | -0.412 | +| explained_variance | -0.926 | +| learning_rate | 0.0001 | +| loss | -0.0566 | +| n_updates | 89420 | +| policy_gradient_loss | -0.053 | +| value_loss | 0.000544 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.1 | +| time/ | | +| fps | 310 | +| iterations | 2891 | +| time_elapsed | 9533 | +| total_timesteps | 2960384 | +| train/ | | +| approx_kl | 3.012917 | +| clip_fraction | 0.477 | +| clip_range | 0.2 | +| entropy_loss | -0.395 | +| explained_variance | -2.71 | +| learning_rate | 0.0001 | +| loss | -0.0674 | +| n_updates | 89430 | +| policy_gradient_loss | -0.0615 | +| value_loss | 0.000464 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.101 | +| time/ | | +| fps | 310 | +| iterations | 2892 | +| time_elapsed | 9536 | +| total_timesteps | 2961408 | +| train/ | | +| approx_kl | 2.130826 | +| clip_fraction | 0.46 | +| clip_range | 0.2 | +| entropy_loss | -0.361 | +| explained_variance | -1.13 | +| learning_rate | 0.0001 | +| loss | -0.091 | +| n_updates | 89440 | +| policy_gradient_loss | -0.0585 | +| value_loss | 0.000545 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.0963 | +| time/ | | +| fps | 310 | +| iterations | 2893 | +| time_elapsed | 9540 | +| total_timesteps | 2962432 | +| train/ | | +| approx_kl | 2.060135 | +| clip_fraction | 0.436 | +| clip_range | 0.2 | +| entropy_loss | -0.295 | +| explained_variance | -5.37 | +| learning_rate | 0.0001 | +| loss | -0.0673 | +| n_updates | 89450 | +| policy_gradient_loss | -0.0645 | +| value_loss | 0.000386 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.0924 | +| time/ | | +| fps | 310 | +| iterations | 2894 | +| time_elapsed | 9543 | +| total_timesteps | 2963456 | +| train/ | | +| approx_kl | 1.6967525 | +| clip_fraction | 0.438 | +| clip_range | 0.2 | +| entropy_loss | -0.321 | +| explained_variance | -1.2 | +| learning_rate | 0.0001 | +| loss | -0.0884 | +| n_updates | 89460 | +| policy_gradient_loss | -0.0572 | +| value_loss | 0.000952 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.0924 | +| time/ | | +| fps | 310 | +| iterations | 2895 | +| time_elapsed | 9547 | +| total_timesteps | 2964480 | +| train/ | | +| approx_kl | 1.7429307 | +| clip_fraction | 0.433 | +| clip_range | 0.2 | +| entropy_loss | -0.343 | +| explained_variance | -3.71 | +| learning_rate | 0.0001 | +| loss | -0.0958 | +| n_updates | 89470 | +| policy_gradient_loss | -0.0627 | +| value_loss | 0.000516 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.0944 | +| time/ | | +| fps | 310 | +| iterations | 2896 | +| time_elapsed | 9550 | +| total_timesteps | 2965504 | +| train/ | | +| approx_kl | 2.0299993 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.394 | +| explained_variance | -2.57 | +| learning_rate | 0.0001 | +| loss | -0.0897 | +| n_updates | 89480 | +| policy_gradient_loss | -0.068 | +| value_loss | 0.000378 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.0944 | +| time/ | | +| fps | 310 | +| iterations | 2897 | +| time_elapsed | 9553 | +| total_timesteps | 2966528 | +| train/ | | +| approx_kl | 2.181929 | +| clip_fraction | 0.458 | +| clip_range | 0.2 | +| entropy_loss | -0.33 | +| explained_variance | -2.34 | +| learning_rate | 0.0001 | +| loss | -0.0679 | +| n_updates | 89490 | +| policy_gradient_loss | -0.0613 | +| value_loss | 0.00077 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.0944 | +| time/ | | +| fps | 310 | +| iterations | 2898 | +| time_elapsed | 9556 | +| total_timesteps | 2967552 | +| train/ | | +| approx_kl | 2.257993 | +| clip_fraction | 0.448 | +| clip_range | 0.2 | +| entropy_loss | -0.332 | +| explained_variance | -3.36 | +| learning_rate | 0.0001 | +| loss | -0.0794 | +| n_updates | 89500 | +| policy_gradient_loss | -0.0596 | +| value_loss | 0.000498 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.0944 | +| time/ | | +| fps | 310 | +| iterations | 2899 | +| time_elapsed | 9559 | +| total_timesteps | 2968576 | +| train/ | | +| approx_kl | 2.0965796 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.345 | +| explained_variance | -3.17 | +| learning_rate | 0.0001 | +| loss | -0.0857 | +| n_updates | 89510 | +| policy_gradient_loss | -0.0676 | +| value_loss | 0.000412 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.9e+03 | +| ep_rew_mean | 0.0923 | +| time/ | | +| fps | 310 | +| iterations | 2900 | +| time_elapsed | 9563 | +| total_timesteps | 2969600 | +| train/ | | +| approx_kl | 2.2807937 | +| clip_fraction | 0.461 | +| clip_range | 0.2 | +| entropy_loss | -0.346 | +| explained_variance | -0.947 | +| learning_rate | 0.0001 | +| loss | -0.0785 | +| n_updates | 89520 | +| policy_gradient_loss | -0.0611 | +| value_loss | 0.000666 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.9e+03 | +| ep_rew_mean | 0.0923 | +| time/ | | +| fps | 310 | +| iterations | 2901 | +| time_elapsed | 9566 | +| total_timesteps | 2970624 | +| train/ | | +| approx_kl | 2.3574376 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.338 | +| explained_variance | -2.76 | +| learning_rate | 0.0001 | +| loss | -0.0408 | +| n_updates | 89530 | +| policy_gradient_loss | -0.0595 | +| value_loss | 0.000358 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.91e+03 | +| ep_rew_mean | 0.091 | +| time/ | | +| fps | 310 | +| iterations | 2902 | +| time_elapsed | 9569 | +| total_timesteps | 2971648 | +| train/ | | +| approx_kl | 1.7955813 | +| clip_fraction | 0.474 | +| clip_range | 0.2 | +| entropy_loss | -0.371 | +| explained_variance | -7.16 | +| learning_rate | 0.0001 | +| loss | -0.0958 | +| n_updates | 89540 | +| policy_gradient_loss | -0.0673 | +| value_loss | 0.000166 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.92e+03 | +| ep_rew_mean | 0.0938 | +| time/ | | +| fps | 310 | +| iterations | 2903 | +| time_elapsed | 9572 | +| total_timesteps | 2972672 | +| train/ | | +| approx_kl | 2.1162174 | +| clip_fraction | 0.447 | +| clip_range | 0.2 | +| entropy_loss | -0.336 | +| explained_variance | -1.21 | +| learning_rate | 0.0001 | +| loss | -0.0777 | +| n_updates | 89550 | +| policy_gradient_loss | -0.0669 | +| value_loss | 0.00052 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.92e+03 | +| ep_rew_mean | 0.0938 | +| time/ | | +| fps | 310 | +| iterations | 2904 | +| time_elapsed | 9575 | +| total_timesteps | 2973696 | +| train/ | | +| approx_kl | 3.240414 | +| clip_fraction | 0.488 | +| clip_range | 0.2 | +| entropy_loss | -0.452 | +| explained_variance | -1.36 | +| learning_rate | 0.0001 | +| loss | -0.0845 | +| n_updates | 89560 | +| policy_gradient_loss | -0.0619 | +| value_loss | 0.000473 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.91e+03 | +| ep_rew_mean | 0.0906 | +| time/ | | +| fps | 310 | +| iterations | 2905 | +| time_elapsed | 9578 | +| total_timesteps | 2974720 | +| train/ | | +| approx_kl | 2.9812016 | +| clip_fraction | 0.467 | +| clip_range | 0.2 | +| entropy_loss | -0.359 | +| explained_variance | -0.638 | +| learning_rate | 0.0001 | +| loss | -0.093 | +| n_updates | 89570 | +| policy_gradient_loss | -0.0637 | +| value_loss | 0.000539 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.91e+03 | +| ep_rew_mean | 0.0886 | +| time/ | | +| fps | 310 | +| iterations | 2906 | +| time_elapsed | 9582 | +| total_timesteps | 2975744 | +| train/ | | +| approx_kl | 1.9277295 | +| clip_fraction | 0.472 | +| clip_range | 0.2 | +| entropy_loss | -0.366 | +| explained_variance | -4.17 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 89580 | +| policy_gradient_loss | -0.0663 | +| value_loss | 0.000316 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.91e+03 | +| ep_rew_mean | 0.0886 | +| time/ | | +| fps | 310 | +| iterations | 2907 | +| time_elapsed | 9586 | +| total_timesteps | 2976768 | +| train/ | | +| approx_kl | 1.7316067 | +| clip_fraction | 0.476 | +| clip_range | 0.2 | +| entropy_loss | -0.417 | +| explained_variance | -1.55 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 89590 | +| policy_gradient_loss | -0.0626 | +| value_loss | 0.000303 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.91e+03 | +| ep_rew_mean | 0.0871 | +| time/ | | +| fps | 310 | +| iterations | 2908 | +| time_elapsed | 9589 | +| total_timesteps | 2977792 | +| train/ | | +| approx_kl | 2.608344 | +| clip_fraction | 0.463 | +| clip_range | 0.2 | +| entropy_loss | -0.338 | +| explained_variance | -3.75 | +| learning_rate | 0.0001 | +| loss | -0.0996 | +| n_updates | 89600 | +| policy_gradient_loss | -0.065 | +| value_loss | 0.00038 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.91e+03 | +| ep_rew_mean | 0.0871 | +| time/ | | +| fps | 310 | +| iterations | 2909 | +| time_elapsed | 9593 | +| total_timesteps | 2978816 | +| train/ | | +| approx_kl | 2.096977 | +| clip_fraction | 0.417 | +| clip_range | 0.2 | +| entropy_loss | -0.303 | +| explained_variance | -1.29 | +| learning_rate | 0.0001 | +| loss | -0.0545 | +| n_updates | 89610 | +| policy_gradient_loss | -0.0572 | +| value_loss | 0.000581 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.9e+03 | +| ep_rew_mean | 0.0859 | +| time/ | | +| fps | 310 | +| iterations | 2910 | +| time_elapsed | 9596 | +| total_timesteps | 2979840 | +| train/ | | +| approx_kl | 1.9194908 | +| clip_fraction | 0.458 | +| clip_range | 0.2 | +| entropy_loss | -0.353 | +| explained_variance | -1.04 | +| learning_rate | 0.0001 | +| loss | -0.0729 | +| n_updates | 89620 | +| policy_gradient_loss | -0.0659 | +| value_loss | 0.001 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.9e+03 | +| ep_rew_mean | 0.0858 | +| time/ | | +| fps | 310 | +| iterations | 2911 | +| time_elapsed | 9600 | +| total_timesteps | 2980864 | +| train/ | | +| approx_kl | 2.741894 | +| clip_fraction | 0.413 | +| clip_range | 0.2 | +| entropy_loss | -0.285 | +| explained_variance | -2.32 | +| learning_rate | 0.0001 | +| loss | -0.0723 | +| n_updates | 89630 | +| policy_gradient_loss | -0.0565 | +| value_loss | 0.000943 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.9e+03 | +| ep_rew_mean | 0.0858 | +| time/ | | +| fps | 310 | +| iterations | 2912 | +| time_elapsed | 9604 | +| total_timesteps | 2981888 | +| train/ | | +| approx_kl | 1.9968817 | +| clip_fraction | 0.442 | +| clip_range | 0.2 | +| entropy_loss | -0.371 | +| explained_variance | -1.71 | +| learning_rate | 0.0001 | +| loss | -0.0837 | +| n_updates | 89640 | +| policy_gradient_loss | -0.052 | +| value_loss | 0.000551 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.9e+03 | +| ep_rew_mean | 0.0858 | +| time/ | | +| fps | 310 | +| iterations | 2913 | +| time_elapsed | 9607 | +| total_timesteps | 2982912 | +| train/ | | +| approx_kl | 1.9761081 | +| clip_fraction | 0.458 | +| clip_range | 0.2 | +| entropy_loss | -0.375 | +| explained_variance | -2.44 | +| learning_rate | 0.0001 | +| loss | -0.0765 | +| n_updates | 89650 | +| policy_gradient_loss | -0.0562 | +| value_loss | 0.00028 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.92e+03 | +| ep_rew_mean | 0.09 | +| time/ | | +| fps | 310 | +| iterations | 2914 | +| time_elapsed | 9610 | +| total_timesteps | 2983936 | +| train/ | | +| approx_kl | 2.1536283 | +| clip_fraction | 0.458 | +| clip_range | 0.2 | +| entropy_loss | -0.311 | +| explained_variance | -4.01 | +| learning_rate | 0.0001 | +| loss | -0.0851 | +| n_updates | 89660 | +| policy_gradient_loss | -0.0647 | +| value_loss | 0.000508 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.92e+03 | +| ep_rew_mean | 0.09 | +| time/ | | +| fps | 310 | +| iterations | 2915 | +| time_elapsed | 9614 | +| total_timesteps | 2984960 | +| train/ | | +| approx_kl | 2.2136216 | +| clip_fraction | 0.429 | +| clip_range | 0.2 | +| entropy_loss | -0.329 | +| explained_variance | -1.83 | +| learning_rate | 0.0001 | +| loss | -0.0931 | +| n_updates | 89670 | +| policy_gradient_loss | -0.0568 | +| value_loss | 0.000334 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.92e+03 | +| ep_rew_mean | 0.0917 | +| time/ | | +| fps | 310 | +| iterations | 2916 | +| time_elapsed | 9617 | +| total_timesteps | 2985984 | +| train/ | | +| approx_kl | 2.1301634 | +| clip_fraction | 0.453 | +| clip_range | 0.2 | +| entropy_loss | -0.366 | +| explained_variance | -0.852 | +| learning_rate | 0.0001 | +| loss | -0.0813 | +| n_updates | 89680 | +| policy_gradient_loss | -0.0574 | +| value_loss | 0.000737 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.92e+03 | +| ep_rew_mean | 0.0917 | +| time/ | | +| fps | 310 | +| iterations | 2917 | +| time_elapsed | 9620 | +| total_timesteps | 2987008 | +| train/ | | +| approx_kl | 1.7822899 | +| clip_fraction | 0.489 | +| clip_range | 0.2 | +| entropy_loss | -0.401 | +| explained_variance | -2.58 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 89690 | +| policy_gradient_loss | -0.06 | +| value_loss | 0.000566 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.94e+03 | +| ep_rew_mean | 0.0946 | +| time/ | | +| fps | 310 | +| iterations | 2918 | +| time_elapsed | 9623 | +| total_timesteps | 2988032 | +| train/ | | +| approx_kl | 2.7299895 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.382 | +| explained_variance | -0.983 | +| learning_rate | 0.0001 | +| loss | -0.0817 | +| n_updates | 89700 | +| policy_gradient_loss | -0.0581 | +| value_loss | 0.000434 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.94e+03 | +| ep_rew_mean | 0.0946 | +| time/ | | +| fps | 310 | +| iterations | 2919 | +| time_elapsed | 9626 | +| total_timesteps | 2989056 | +| train/ | | +| approx_kl | 13.172029 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.378 | +| explained_variance | -2.94 | +| learning_rate | 0.0001 | +| loss | -0.1 | +| n_updates | 89710 | +| policy_gradient_loss | -0.0651 | +| value_loss | 0.000649 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.94e+03 | +| ep_rew_mean | 0.0946 | +| time/ | | +| fps | 310 | +| iterations | 2920 | +| time_elapsed | 9630 | +| total_timesteps | 2990080 | +| train/ | | +| approx_kl | 2.0578291 | +| clip_fraction | 0.458 | +| clip_range | 0.2 | +| entropy_loss | -0.349 | +| explained_variance | -4.2 | +| learning_rate | 0.0001 | +| loss | -0.0869 | +| n_updates | 89720 | +| policy_gradient_loss | -0.0672 | +| value_loss | 0.000497 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.94e+03 | +| ep_rew_mean | 0.0946 | +| time/ | | +| fps | 310 | +| iterations | 2921 | +| time_elapsed | 9633 | +| total_timesteps | 2991104 | +| train/ | | +| approx_kl | 2.1321082 | +| clip_fraction | 0.447 | +| clip_range | 0.2 | +| entropy_loss | -0.337 | +| explained_variance | -1.66 | +| learning_rate | 0.0001 | +| loss | -0.0857 | +| n_updates | 89730 | +| policy_gradient_loss | -0.0577 | +| value_loss | 0.000793 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.94e+03 | +| ep_rew_mean | 0.0985 | +| time/ | | +| fps | 310 | +| iterations | 2922 | +| time_elapsed | 9636 | +| total_timesteps | 2992128 | +| train/ | | +| approx_kl | 5.2559257 | +| clip_fraction | 0.492 | +| clip_range | 0.2 | +| entropy_loss | -0.367 | +| explained_variance | -1.98 | +| learning_rate | 0.0001 | +| loss | -0.0734 | +| n_updates | 89740 | +| policy_gradient_loss | -0.0668 | +| value_loss | 0.000658 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.93e+03 | +| ep_rew_mean | 0.0971 | +| time/ | | +| fps | 310 | +| iterations | 2923 | +| time_elapsed | 9639 | +| total_timesteps | 2993152 | +| train/ | | +| approx_kl | 3.1581237 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.411 | +| explained_variance | -1.07 | +| learning_rate | 0.0001 | +| loss | -0.0515 | +| n_updates | 89750 | +| policy_gradient_loss | -0.0658 | +| value_loss | 0.000536 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.93e+03 | +| ep_rew_mean | 0.0971 | +| time/ | | +| fps | 310 | +| iterations | 2924 | +| time_elapsed | 9643 | +| total_timesteps | 2994176 | +| train/ | | +| approx_kl | 1.7874011 | +| clip_fraction | 0.445 | +| clip_range | 0.2 | +| entropy_loss | -0.346 | +| explained_variance | -2.13 | +| learning_rate | 0.0001 | +| loss | -0.0935 | +| n_updates | 89760 | +| policy_gradient_loss | -0.0483 | +| value_loss | 0.000778 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.94e+03 | +| ep_rew_mean | 0.0946 | +| time/ | | +| fps | 310 | +| iterations | 2925 | +| time_elapsed | 9646 | +| total_timesteps | 2995200 | +| train/ | | +| approx_kl | 1.7661581 | +| clip_fraction | 0.474 | +| clip_range | 0.2 | +| entropy_loss | -0.374 | +| explained_variance | -6.48 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 89770 | +| policy_gradient_loss | -0.0584 | +| value_loss | 0.000258 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.94e+03 | +| ep_rew_mean | 0.0946 | +| time/ | | +| fps | 310 | +| iterations | 2926 | +| time_elapsed | 9650 | +| total_timesteps | 2996224 | +| train/ | | +| approx_kl | 1.7646989 | +| clip_fraction | 0.456 | +| clip_range | 0.2 | +| entropy_loss | -0.35 | +| explained_variance | -0.429 | +| learning_rate | 0.0001 | +| loss | -0.0599 | +| n_updates | 89780 | +| policy_gradient_loss | -0.0535 | +| value_loss | 0.000693 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.94e+03 | +| ep_rew_mean | 0.0946 | +| time/ | | +| fps | 310 | +| iterations | 2927 | +| time_elapsed | 9653 | +| total_timesteps | 2997248 | +| train/ | | +| approx_kl | 2.2179418 | +| clip_fraction | 0.493 | +| clip_range | 0.2 | +| entropy_loss | -0.376 | +| explained_variance | -12.3 | +| learning_rate | 0.0001 | +| loss | -0.0943 | +| n_updates | 89790 | +| policy_gradient_loss | -0.0613 | +| value_loss | 0.000366 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.95e+03 | +| ep_rew_mean | 0.0978 | +| time/ | | +| fps | 310 | +| iterations | 2928 | +| time_elapsed | 9657 | +| total_timesteps | 2998272 | +| train/ | | +| approx_kl | 2.1630454 | +| clip_fraction | 0.506 | +| clip_range | 0.2 | +| entropy_loss | -0.388 | +| explained_variance | -1.99 | +| learning_rate | 0.0001 | +| loss | -0.0542 | +| n_updates | 89800 | +| policy_gradient_loss | -0.0709 | +| value_loss | 0.000396 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.95e+03 | +| ep_rew_mean | 0.0978 | +| time/ | | +| fps | 310 | +| iterations | 2929 | +| time_elapsed | 9660 | +| total_timesteps | 2999296 | +| train/ | | +| approx_kl | 2.4517536 | +| clip_fraction | 0.457 | +| clip_range | 0.2 | +| entropy_loss | -0.354 | +| explained_variance | -1.24 | +| learning_rate | 0.0001 | +| loss | -0.0934 | +| n_updates | 89810 | +| policy_gradient_loss | -0.0629 | +| value_loss | 0.000357 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.96e+03 | +| ep_rew_mean | 0.0974 | +| time/ | | +| fps | 310 | +| iterations | 2930 | +| time_elapsed | 9664 | +| total_timesteps | 3000320 | +| train/ | | +| approx_kl | 1.9111294 | +| clip_fraction | 0.429 | +| clip_range | 0.2 | +| entropy_loss | -0.314 | +| explained_variance | -3.42 | +| learning_rate | 0.0001 | +| loss | -0.0858 | +| n_updates | 89820 | +| policy_gradient_loss | -0.061 | +| value_loss | 0.00072 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.95e+03 | +| ep_rew_mean | 0.0997 | +| time/ | | +| fps | 310 | +| iterations | 2931 | +| time_elapsed | 9667 | +| total_timesteps | 3001344 | +| train/ | | +| approx_kl | 2.2625527 | +| clip_fraction | 0.442 | +| clip_range | 0.2 | +| entropy_loss | -0.341 | +| explained_variance | -2.9 | +| learning_rate | 0.0001 | +| loss | -0.0735 | +| n_updates | 89830 | +| policy_gradient_loss | -0.0609 | +| value_loss | 0.000522 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.95e+03 | +| ep_rew_mean | 0.0997 | +| time/ | | +| fps | 310 | +| iterations | 2932 | +| time_elapsed | 9670 | +| total_timesteps | 3002368 | +| train/ | | +| approx_kl | 2.0887368 | +| clip_fraction | 0.463 | +| clip_range | 0.2 | +| entropy_loss | -0.337 | +| explained_variance | -1.65 | +| learning_rate | 0.0001 | +| loss | -0.0795 | +| n_updates | 89840 | +| policy_gradient_loss | -0.0611 | +| value_loss | 0.000709 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.95e+03 | +| ep_rew_mean | 0.101 | +| time/ | | +| fps | 310 | +| iterations | 2933 | +| time_elapsed | 9673 | +| total_timesteps | 3003392 | +| train/ | | +| approx_kl | 2.6371222 | +| clip_fraction | 0.465 | +| clip_range | 0.2 | +| entropy_loss | -0.356 | +| explained_variance | -2.09 | +| learning_rate | 0.0001 | +| loss | -0.0765 | +| n_updates | 89850 | +| policy_gradient_loss | -0.067 | +| value_loss | 0.000478 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.95e+03 | +| ep_rew_mean | 0.101 | +| time/ | | +| fps | 310 | +| iterations | 2934 | +| time_elapsed | 9677 | +| total_timesteps | 3004416 | +| train/ | | +| approx_kl | 1.7255161 | +| clip_fraction | 0.467 | +| clip_range | 0.2 | +| entropy_loss | -0.417 | +| explained_variance | -3.18 | +| learning_rate | 0.0001 | +| loss | -0.0996 | +| n_updates | 89860 | +| policy_gradient_loss | -0.0634 | +| value_loss | 0.000318 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.94e+03 | +| ep_rew_mean | 0.0958 | +| time/ | | +| fps | 310 | +| iterations | 2935 | +| time_elapsed | 9680 | +| total_timesteps | 3005440 | +| train/ | | +| approx_kl | 1.9108744 | +| clip_fraction | 0.449 | +| clip_range | 0.2 | +| entropy_loss | -0.324 | +| explained_variance | -0.847 | +| learning_rate | 0.0001 | +| loss | -0.0663 | +| n_updates | 89870 | +| policy_gradient_loss | -0.0554 | +| value_loss | 0.000409 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.94e+03 | +| ep_rew_mean | 0.0983 | +| time/ | | +| fps | 310 | +| iterations | 2936 | +| time_elapsed | 9683 | +| total_timesteps | 3006464 | +| train/ | | +| approx_kl | 2.208255 | +| clip_fraction | 0.436 | +| clip_range | 0.2 | +| entropy_loss | -0.313 | +| explained_variance | -3.36 | +| learning_rate | 0.0001 | +| loss | -0.0572 | +| n_updates | 89880 | +| policy_gradient_loss | -0.0592 | +| value_loss | 0.000563 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.94e+03 | +| ep_rew_mean | 0.0983 | +| time/ | | +| fps | 310 | +| iterations | 2937 | +| time_elapsed | 9686 | +| total_timesteps | 3007488 | +| train/ | | +| approx_kl | 2.0066 | +| clip_fraction | 0.446 | +| clip_range | 0.2 | +| entropy_loss | -0.356 | +| explained_variance | -0.543 | +| learning_rate | 0.0001 | +| loss | -0.0756 | +| n_updates | 89890 | +| policy_gradient_loss | -0.0632 | +| value_loss | 0.000655 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.95e+03 | +| ep_rew_mean | 0.102 | +| time/ | | +| fps | 310 | +| iterations | 2938 | +| time_elapsed | 9689 | +| total_timesteps | 3008512 | +| train/ | | +| approx_kl | 1.838277 | +| clip_fraction | 0.493 | +| clip_range | 0.2 | +| entropy_loss | -0.403 | +| explained_variance | -3.94 | +| learning_rate | 0.0001 | +| loss | -0.0716 | +| n_updates | 89900 | +| policy_gradient_loss | -0.0733 | +| value_loss | 0.000671 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.95e+03 | +| ep_rew_mean | 0.102 | +| time/ | | +| fps | 310 | +| iterations | 2939 | +| time_elapsed | 9693 | +| total_timesteps | 3009536 | +| train/ | | +| approx_kl | 2.3220654 | +| clip_fraction | 0.451 | +| clip_range | 0.2 | +| entropy_loss | -0.3 | +| explained_variance | -4.11 | +| learning_rate | 0.0001 | +| loss | -0.0894 | +| n_updates | 89910 | +| policy_gradient_loss | -0.0718 | +| value_loss | 0.000862 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.93e+03 | +| ep_rew_mean | 0.103 | +| time/ | | +| fps | 310 | +| iterations | 2940 | +| time_elapsed | 9696 | +| total_timesteps | 3010560 | +| train/ | | +| approx_kl | 2.2636752 | +| clip_fraction | 0.422 | +| clip_range | 0.2 | +| entropy_loss | -0.289 | +| explained_variance | -3.03 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 89920 | +| policy_gradient_loss | -0.0597 | +| value_loss | 0.000555 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.93e+03 | +| ep_rew_mean | 0.103 | +| time/ | | +| fps | 310 | +| iterations | 2941 | +| time_elapsed | 9699 | +| total_timesteps | 3011584 | +| train/ | | +| approx_kl | 2.0724776 | +| clip_fraction | 0.444 | +| clip_range | 0.2 | +| entropy_loss | -0.335 | +| explained_variance | -0.536 | +| learning_rate | 0.0001 | +| loss | -0.092 | +| n_updates | 89930 | +| policy_gradient_loss | -0.0634 | +| value_loss | 0.000514 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.94e+03 | +| ep_rew_mean | 0.11 | +| time/ | | +| fps | 310 | +| iterations | 2942 | +| time_elapsed | 9702 | +| total_timesteps | 3012608 | +| train/ | | +| approx_kl | 1.9459901 | +| clip_fraction | 0.427 | +| clip_range | 0.2 | +| entropy_loss | -0.291 | +| explained_variance | -1.96 | +| learning_rate | 0.0001 | +| loss | -0.0898 | +| n_updates | 89940 | +| policy_gradient_loss | -0.0616 | +| value_loss | 0.000878 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.94e+03 | +| ep_rew_mean | 0.11 | +| time/ | | +| fps | 310 | +| iterations | 2943 | +| time_elapsed | 9706 | +| total_timesteps | 3013632 | +| train/ | | +| approx_kl | 1.998948 | +| clip_fraction | 0.422 | +| clip_range | 0.2 | +| entropy_loss | -0.296 | +| explained_variance | -4.14 | +| learning_rate | 0.0001 | +| loss | -0.0645 | +| n_updates | 89950 | +| policy_gradient_loss | -0.0526 | +| value_loss | 0.000671 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.92e+03 | +| ep_rew_mean | 0.113 | +| time/ | | +| fps | 310 | +| iterations | 2944 | +| time_elapsed | 9709 | +| total_timesteps | 3014656 | +| train/ | | +| approx_kl | 1.7112722 | +| clip_fraction | 0.411 | +| clip_range | 0.2 | +| entropy_loss | -0.32 | +| explained_variance | -0.437 | +| learning_rate | 0.0001 | +| loss | -0.0606 | +| n_updates | 89960 | +| policy_gradient_loss | -0.0557 | +| value_loss | 0.000536 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.92e+03 | +| ep_rew_mean | 0.113 | +| time/ | | +| fps | 310 | +| iterations | 2945 | +| time_elapsed | 9713 | +| total_timesteps | 3015680 | +| train/ | | +| approx_kl | 1.8829701 | +| clip_fraction | 0.389 | +| clip_range | 0.2 | +| entropy_loss | -0.272 | +| explained_variance | -2.02 | +| learning_rate | 0.0001 | +| loss | -0.0591 | +| n_updates | 89970 | +| policy_gradient_loss | -0.0514 | +| value_loss | 0.000775 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.92e+03 | +| ep_rew_mean | 0.113 | +| time/ | | +| fps | 310 | +| iterations | 2946 | +| time_elapsed | 9716 | +| total_timesteps | 3016704 | +| train/ | | +| approx_kl | 2.2399588 | +| clip_fraction | 0.44 | +| clip_range | 0.2 | +| entropy_loss | -0.298 | +| explained_variance | -2.14 | +| learning_rate | 0.0001 | +| loss | -0.0715 | +| n_updates | 89980 | +| policy_gradient_loss | -0.0613 | +| value_loss | 0.000562 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.92e+03 | +| ep_rew_mean | 0.116 | +| time/ | | +| fps | 310 | +| iterations | 2947 | +| time_elapsed | 9720 | +| total_timesteps | 3017728 | +| train/ | | +| approx_kl | 3.0710373 | +| clip_fraction | 0.459 | +| clip_range | 0.2 | +| entropy_loss | -0.321 | +| explained_variance | -1.72 | +| learning_rate | 0.0001 | +| loss | -0.0998 | +| n_updates | 89990 | +| policy_gradient_loss | -0.0644 | +| value_loss | 0.00052 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.9e+03 | +| ep_rew_mean | 0.112 | +| time/ | | +| fps | 310 | +| iterations | 2948 | +| time_elapsed | 9723 | +| total_timesteps | 3018752 | +| train/ | | +| approx_kl | 1.9707212 | +| clip_fraction | 0.431 | +| clip_range | 0.2 | +| entropy_loss | -0.303 | +| explained_variance | -4.44 | +| learning_rate | 0.0001 | +| loss | -0.0931 | +| n_updates | 90000 | +| policy_gradient_loss | -0.0652 | +| value_loss | 0.00046 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.9e+03 | +| ep_rew_mean | 0.112 | +| time/ | | +| fps | 310 | +| iterations | 2949 | +| time_elapsed | 9727 | +| total_timesteps | 3019776 | +| train/ | | +| approx_kl | 2.2972212 | +| clip_fraction | 0.409 | +| clip_range | 0.2 | +| entropy_loss | -0.305 | +| explained_variance | -0.551 | +| learning_rate | 0.0001 | +| loss | -0.065 | +| n_updates | 90010 | +| policy_gradient_loss | -0.0574 | +| value_loss | 0.000607 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.9e+03 | +| ep_rew_mean | 0.112 | +| time/ | | +| fps | 310 | +| iterations | 2950 | +| time_elapsed | 9730 | +| total_timesteps | 3020800 | +| train/ | | +| approx_kl | 2.357708 | +| clip_fraction | 0.464 | +| clip_range | 0.2 | +| entropy_loss | -0.341 | +| explained_variance | -4.77 | +| learning_rate | 0.0001 | +| loss | -0.11 | +| n_updates | 90020 | +| policy_gradient_loss | -0.0666 | +| value_loss | 0.00073 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.91e+03 | +| ep_rew_mean | 0.113 | +| time/ | | +| fps | 310 | +| iterations | 2951 | +| time_elapsed | 9733 | +| total_timesteps | 3021824 | +| train/ | | +| approx_kl | 2.0505066 | +| clip_fraction | 0.457 | +| clip_range | 0.2 | +| entropy_loss | -0.325 | +| explained_variance | -3.25 | +| learning_rate | 0.0001 | +| loss | -0.0665 | +| n_updates | 90030 | +| policy_gradient_loss | -0.0598 | +| value_loss | 0.000522 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.91e+03 | +| ep_rew_mean | 0.113 | +| time/ | | +| fps | 310 | +| iterations | 2952 | +| time_elapsed | 9737 | +| total_timesteps | 3022848 | +| train/ | | +| approx_kl | 2.2810392 | +| clip_fraction | 0.44 | +| clip_range | 0.2 | +| entropy_loss | -0.316 | +| explained_variance | -4.59 | +| learning_rate | 0.0001 | +| loss | -0.0845 | +| n_updates | 90040 | +| policy_gradient_loss | -0.065 | +| value_loss | 0.000455 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.92e+03 | +| ep_rew_mean | 0.106 | +| time/ | | +| fps | 310 | +| iterations | 2953 | +| time_elapsed | 9740 | +| total_timesteps | 3023872 | +| train/ | | +| approx_kl | 2.5552309 | +| clip_fraction | 0.464 | +| clip_range | 0.2 | +| entropy_loss | -0.338 | +| explained_variance | -1.38 | +| learning_rate | 0.0001 | +| loss | -0.0924 | +| n_updates | 90050 | +| policy_gradient_loss | -0.0623 | +| value_loss | 0.000293 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.92e+03 | +| ep_rew_mean | 0.106 | +| time/ | | +| fps | 310 | +| iterations | 2954 | +| time_elapsed | 9743 | +| total_timesteps | 3024896 | +| train/ | | +| approx_kl | 2.1167178 | +| clip_fraction | 0.434 | +| clip_range | 0.2 | +| entropy_loss | -0.349 | +| explained_variance | -2.87 | +| learning_rate | 0.0001 | +| loss | -0.0752 | +| n_updates | 90060 | +| policy_gradient_loss | -0.0561 | +| value_loss | 0.000278 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.93e+03 | +| ep_rew_mean | 0.112 | +| time/ | | +| fps | 310 | +| iterations | 2955 | +| time_elapsed | 9746 | +| total_timesteps | 3025920 | +| train/ | | +| approx_kl | 2.1682243 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.376 | +| explained_variance | -0.836 | +| learning_rate | 0.0001 | +| loss | -0.0896 | +| n_updates | 90070 | +| policy_gradient_loss | -0.0594 | +| value_loss | 0.00103 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.93e+03 | +| ep_rew_mean | 0.112 | +| time/ | | +| fps | 310 | +| iterations | 2956 | +| time_elapsed | 9749 | +| total_timesteps | 3026944 | +| train/ | | +| approx_kl | 2.037391 | +| clip_fraction | 0.482 | +| clip_range | 0.2 | +| entropy_loss | -0.353 | +| explained_variance | -2.35 | +| learning_rate | 0.0001 | +| loss | -0.0723 | +| n_updates | 90080 | +| policy_gradient_loss | -0.0594 | +| value_loss | 0.000608 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.93e+03 | +| ep_rew_mean | 0.106 | +| time/ | | +| fps | 310 | +| iterations | 2957 | +| time_elapsed | 9753 | +| total_timesteps | 3027968 | +| train/ | | +| approx_kl | 2.3310795 | +| clip_fraction | 0.466 | +| clip_range | 0.2 | +| entropy_loss | -0.313 | +| explained_variance | -1.59 | +| learning_rate | 0.0001 | +| loss | -0.117 | +| n_updates | 90090 | +| policy_gradient_loss | -0.0594 | +| value_loss | 0.000557 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.93e+03 | +| ep_rew_mean | 0.106 | +| time/ | | +| fps | 310 | +| iterations | 2958 | +| time_elapsed | 9756 | +| total_timesteps | 3028992 | +| train/ | | +| approx_kl | 4.6603336 | +| clip_fraction | 0.484 | +| clip_range | 0.2 | +| entropy_loss | -0.385 | +| explained_variance | -1.58 | +| learning_rate | 0.0001 | +| loss | -0.0834 | +| n_updates | 90100 | +| policy_gradient_loss | -0.0654 | +| value_loss | 0.000352 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.94e+03 | +| ep_rew_mean | 0.111 | +| time/ | | +| fps | 310 | +| iterations | 2959 | +| time_elapsed | 9759 | +| total_timesteps | 3030016 | +| train/ | | +| approx_kl | 2.32883 | +| clip_fraction | 0.449 | +| clip_range | 0.2 | +| entropy_loss | -0.321 | +| explained_variance | -1.98 | +| learning_rate | 0.0001 | +| loss | -0.0728 | +| n_updates | 90110 | +| policy_gradient_loss | -0.0616 | +| value_loss | 0.000592 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.94e+03 | +| ep_rew_mean | 0.111 | +| time/ | | +| fps | 310 | +| iterations | 2960 | +| time_elapsed | 9763 | +| total_timesteps | 3031040 | +| train/ | | +| approx_kl | 2.5427547 | +| clip_fraction | 0.433 | +| clip_range | 0.2 | +| entropy_loss | -0.302 | +| explained_variance | -2.78 | +| learning_rate | 0.0001 | +| loss | -0.0574 | +| n_updates | 90120 | +| policy_gradient_loss | -0.0642 | +| value_loss | 0.000817 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.94e+03 | +| ep_rew_mean | 0.117 | +| time/ | | +| fps | 310 | +| iterations | 2961 | +| time_elapsed | 9766 | +| total_timesteps | 3032064 | +| train/ | | +| approx_kl | 2.9079635 | +| clip_fraction | 0.428 | +| clip_range | 0.2 | +| entropy_loss | -0.293 | +| explained_variance | -2.15 | +| learning_rate | 0.0001 | +| loss | -0.0901 | +| n_updates | 90130 | +| policy_gradient_loss | -0.0562 | +| value_loss | 0.000468 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.94e+03 | +| ep_rew_mean | 0.117 | +| time/ | | +| fps | 310 | +| iterations | 2962 | +| time_elapsed | 9769 | +| total_timesteps | 3033088 | +| train/ | | +| approx_kl | 2.0395694 | +| clip_fraction | 0.446 | +| clip_range | 0.2 | +| entropy_loss | -0.321 | +| explained_variance | -3.13 | +| learning_rate | 0.0001 | +| loss | -0.0812 | +| n_updates | 90140 | +| policy_gradient_loss | -0.0619 | +| value_loss | 0.000632 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.93e+03 | +| ep_rew_mean | 0.117 | +| time/ | | +| fps | 310 | +| iterations | 2963 | +| time_elapsed | 9773 | +| total_timesteps | 3034112 | +| train/ | | +| approx_kl | 2.983571 | +| clip_fraction | 0.446 | +| clip_range | 0.2 | +| entropy_loss | -0.335 | +| explained_variance | -4.09 | +| learning_rate | 0.0001 | +| loss | -0.0548 | +| n_updates | 90150 | +| policy_gradient_loss | -0.0606 | +| value_loss | 0.000377 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.93e+03 | +| ep_rew_mean | 0.117 | +| time/ | | +| fps | 310 | +| iterations | 2964 | +| time_elapsed | 9776 | +| total_timesteps | 3035136 | +| train/ | | +| approx_kl | 2.4100718 | +| clip_fraction | 0.405 | +| clip_range | 0.2 | +| entropy_loss | -0.276 | +| explained_variance | -3.13 | +| learning_rate | 0.0001 | +| loss | -0.0717 | +| n_updates | 90160 | +| policy_gradient_loss | -0.0593 | +| value_loss | 0.000308 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.93e+03 | +| ep_rew_mean | 0.117 | +| time/ | | +| fps | 310 | +| iterations | 2965 | +| time_elapsed | 9780 | +| total_timesteps | 3036160 | +| train/ | | +| approx_kl | 2.3810725 | +| clip_fraction | 0.482 | +| clip_range | 0.2 | +| entropy_loss | -0.355 | +| explained_variance | -1.32 | +| learning_rate | 0.0001 | +| loss | -0.087 | +| n_updates | 90170 | +| policy_gradient_loss | -0.0629 | +| value_loss | 0.000874 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.93e+03 | +| ep_rew_mean | 0.117 | +| time/ | | +| fps | 310 | +| iterations | 2966 | +| time_elapsed | 9783 | +| total_timesteps | 3037184 | +| train/ | | +| approx_kl | 2.2895865 | +| clip_fraction | 0.438 | +| clip_range | 0.2 | +| entropy_loss | -0.293 | +| explained_variance | -1.67 | +| learning_rate | 0.0001 | +| loss | -0.0784 | +| n_updates | 90180 | +| policy_gradient_loss | -0.06 | +| value_loss | 0.000546 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.92e+03 | +| ep_rew_mean | 0.119 | +| time/ | | +| fps | 310 | +| iterations | 2967 | +| time_elapsed | 9786 | +| total_timesteps | 3038208 | +| train/ | | +| approx_kl | 2.0012145 | +| clip_fraction | 0.472 | +| clip_range | 0.2 | +| entropy_loss | -0.34 | +| explained_variance | -2.57 | +| learning_rate | 0.0001 | +| loss | -0.0913 | +| n_updates | 90190 | +| policy_gradient_loss | -0.0622 | +| value_loss | 0.000586 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.92e+03 | +| ep_rew_mean | 0.119 | +| time/ | | +| fps | 310 | +| iterations | 2968 | +| time_elapsed | 9789 | +| total_timesteps | 3039232 | +| train/ | | +| approx_kl | 38.966087 | +| clip_fraction | 0.446 | +| clip_range | 0.2 | +| entropy_loss | -0.304 | +| explained_variance | -1.98 | +| learning_rate | 0.0001 | +| loss | -0.0918 | +| n_updates | 90200 | +| policy_gradient_loss | -0.0643 | +| value_loss | 0.000697 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.93e+03 | +| ep_rew_mean | 0.123 | +| time/ | | +| fps | 310 | +| iterations | 2969 | +| time_elapsed | 9793 | +| total_timesteps | 3040256 | +| train/ | | +| approx_kl | 1.9817823 | +| clip_fraction | 0.486 | +| clip_range | 0.2 | +| entropy_loss | -0.4 | +| explained_variance | -2.22 | +| learning_rate | 0.0001 | +| loss | -0.0842 | +| n_updates | 90210 | +| policy_gradient_loss | -0.0582 | +| value_loss | 0.000543 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.93e+03 | +| ep_rew_mean | 0.123 | +| time/ | | +| fps | 310 | +| iterations | 2970 | +| time_elapsed | 9796 | +| total_timesteps | 3041280 | +| train/ | | +| approx_kl | 2.4214702 | +| clip_fraction | 0.451 | +| clip_range | 0.2 | +| entropy_loss | -0.308 | +| explained_variance | -2.8 | +| learning_rate | 0.0001 | +| loss | -0.0881 | +| n_updates | 90220 | +| policy_gradient_loss | -0.0611 | +| value_loss | 0.000429 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.92e+03 | +| ep_rew_mean | 0.125 | +| time/ | | +| fps | 310 | +| iterations | 2971 | +| time_elapsed | 9799 | +| total_timesteps | 3042304 | +| train/ | | +| approx_kl | 2.8021946 | +| clip_fraction | 0.443 | +| clip_range | 0.2 | +| entropy_loss | -0.297 | +| explained_variance | -1.35 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 90230 | +| policy_gradient_loss | -0.0591 | +| value_loss | 0.000767 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.92e+03 | +| ep_rew_mean | 0.125 | +| time/ | | +| fps | 310 | +| iterations | 2972 | +| time_elapsed | 9802 | +| total_timesteps | 3043328 | +| train/ | | +| approx_kl | 2.267417 | +| clip_fraction | 0.421 | +| clip_range | 0.2 | +| entropy_loss | -0.303 | +| explained_variance | -1.62 | +| learning_rate | 0.0001 | +| loss | -0.0901 | +| n_updates | 90240 | +| policy_gradient_loss | -0.0622 | +| value_loss | 0.00054 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.92e+03 | +| ep_rew_mean | 0.125 | +| time/ | | +| fps | 310 | +| iterations | 2973 | +| time_elapsed | 9805 | +| total_timesteps | 3044352 | +| train/ | | +| approx_kl | 1.4205083 | +| clip_fraction | 0.419 | +| clip_range | 0.2 | +| entropy_loss | -0.366 | +| explained_variance | -8.16 | +| learning_rate | 0.0001 | +| loss | -0.0771 | +| n_updates | 90250 | +| policy_gradient_loss | -0.0522 | +| value_loss | 0.000404 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.93e+03 | +| ep_rew_mean | 0.13 | +| time/ | | +| fps | 310 | +| iterations | 2974 | +| time_elapsed | 9809 | +| total_timesteps | 3045376 | +| train/ | | +| approx_kl | 2.3860128 | +| clip_fraction | 0.469 | +| clip_range | 0.2 | +| entropy_loss | -0.316 | +| explained_variance | -0.819 | +| learning_rate | 0.0001 | +| loss | -0.0705 | +| n_updates | 90260 | +| policy_gradient_loss | -0.0607 | +| value_loss | 0.00045 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.93e+03 | +| ep_rew_mean | 0.13 | +| time/ | | +| fps | 310 | +| iterations | 2975 | +| time_elapsed | 9812 | +| total_timesteps | 3046400 | +| train/ | | +| approx_kl | 2.2414584 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.445 | +| explained_variance | -1.34 | +| learning_rate | 0.0001 | +| loss | -0.0884 | +| n_updates | 90270 | +| policy_gradient_loss | -0.0648 | +| value_loss | 0.000564 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.93e+03 | +| ep_rew_mean | 0.134 | +| time/ | | +| fps | 310 | +| iterations | 2976 | +| time_elapsed | 9815 | +| total_timesteps | 3047424 | +| train/ | | +| approx_kl | 95.715614 | +| clip_fraction | 0.464 | +| clip_range | 0.2 | +| entropy_loss | -0.382 | +| explained_variance | -2.44 | +| learning_rate | 0.0001 | +| loss | -0.0821 | +| n_updates | 90280 | +| policy_gradient_loss | -0.0603 | +| value_loss | 0.000533 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.94e+03 | +| ep_rew_mean | 0.137 | +| time/ | | +| fps | 310 | +| iterations | 2977 | +| time_elapsed | 9818 | +| total_timesteps | 3048448 | +| train/ | | +| approx_kl | 1.8262085 | +| clip_fraction | 0.478 | +| clip_range | 0.2 | +| entropy_loss | -0.378 | +| explained_variance | -1.56 | +| learning_rate | 0.0001 | +| loss | -0.0691 | +| n_updates | 90290 | +| policy_gradient_loss | -0.0623 | +| value_loss | 0.000686 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.94e+03 | +| ep_rew_mean | 0.137 | +| time/ | | +| fps | 310 | +| iterations | 2978 | +| time_elapsed | 9822 | +| total_timesteps | 3049472 | +| train/ | | +| approx_kl | 2.242774 | +| clip_fraction | 0.496 | +| clip_range | 0.2 | +| entropy_loss | -0.386 | +| explained_variance | -4.58 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 90300 | +| policy_gradient_loss | -0.0639 | +| value_loss | 0.000643 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.94e+03 | +| ep_rew_mean | 0.135 | +| time/ | | +| fps | 310 | +| iterations | 2979 | +| time_elapsed | 9825 | +| total_timesteps | 3050496 | +| train/ | | +| approx_kl | 2.0319672 | +| clip_fraction | 0.479 | +| clip_range | 0.2 | +| entropy_loss | -0.376 | +| explained_variance | -1.51 | +| learning_rate | 0.0001 | +| loss | -0.0957 | +| n_updates | 90310 | +| policy_gradient_loss | -0.0549 | +| value_loss | 0.000479 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.94e+03 | +| ep_rew_mean | 0.135 | +| time/ | | +| fps | 310 | +| iterations | 2980 | +| time_elapsed | 9829 | +| total_timesteps | 3051520 | +| train/ | | +| approx_kl | 2.4065447 | +| clip_fraction | 0.492 | +| clip_range | 0.2 | +| entropy_loss | -0.377 | +| explained_variance | -2.92 | +| learning_rate | 0.0001 | +| loss | -0.0892 | +| n_updates | 90320 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000745 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.94e+03 | +| ep_rew_mean | 0.137 | +| time/ | | +| fps | 310 | +| iterations | 2981 | +| time_elapsed | 9832 | +| total_timesteps | 3052544 | +| train/ | | +| approx_kl | 1.8003303 | +| clip_fraction | 0.464 | +| clip_range | 0.2 | +| entropy_loss | -0.369 | +| explained_variance | -1.24 | +| learning_rate | 0.0001 | +| loss | -0.0813 | +| n_updates | 90330 | +| policy_gradient_loss | -0.0634 | +| value_loss | 0.000642 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.94e+03 | +| ep_rew_mean | 0.137 | +| time/ | | +| fps | 310 | +| iterations | 2982 | +| time_elapsed | 9836 | +| total_timesteps | 3053568 | +| train/ | | +| approx_kl | 2.2072861 | +| clip_fraction | 0.509 | +| clip_range | 0.2 | +| entropy_loss | -0.382 | +| explained_variance | -4.49 | +| learning_rate | 0.0001 | +| loss | -0.1 | +| n_updates | 90340 | +| policy_gradient_loss | -0.0686 | +| value_loss | 0.000569 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.94e+03 | +| ep_rew_mean | 0.136 | +| time/ | | +| fps | 310 | +| iterations | 2983 | +| time_elapsed | 9839 | +| total_timesteps | 3054592 | +| train/ | | +| approx_kl | 3.4216099 | +| clip_fraction | 0.477 | +| clip_range | 0.2 | +| entropy_loss | -0.364 | +| explained_variance | -2.57 | +| learning_rate | 0.0001 | +| loss | -0.0956 | +| n_updates | 90350 | +| policy_gradient_loss | -0.0586 | +| value_loss | 0.000359 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.94e+03 | +| ep_rew_mean | 0.136 | +| time/ | | +| fps | 310 | +| iterations | 2984 | +| time_elapsed | 9843 | +| total_timesteps | 3055616 | +| train/ | | +| approx_kl | 2.028702 | +| clip_fraction | 0.477 | +| clip_range | 0.2 | +| entropy_loss | -0.371 | +| explained_variance | -1.7 | +| learning_rate | 0.0001 | +| loss | -0.0857 | +| n_updates | 90360 | +| policy_gradient_loss | -0.0645 | +| value_loss | 0.000416 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.94e+03 | +| ep_rew_mean | 0.136 | +| time/ | | +| fps | 310 | +| iterations | 2985 | +| time_elapsed | 9846 | +| total_timesteps | 3056640 | +| train/ | | +| approx_kl | 1.9062105 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.377 | +| explained_variance | -7.1 | +| learning_rate | 0.0001 | +| loss | -0.0926 | +| n_updates | 90370 | +| policy_gradient_loss | -0.0708 | +| value_loss | 0.000544 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.96e+03 | +| ep_rew_mean | 0.13 | +| time/ | | +| fps | 310 | +| iterations | 2986 | +| time_elapsed | 9849 | +| total_timesteps | 3057664 | +| train/ | | +| approx_kl | 1.9293362 | +| clip_fraction | 0.482 | +| clip_range | 0.2 | +| entropy_loss | -0.418 | +| explained_variance | -3.44 | +| learning_rate | 0.0001 | +| loss | -0.0938 | +| n_updates | 90380 | +| policy_gradient_loss | -0.0668 | +| value_loss | 0.000731 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.95e+03 | +| ep_rew_mean | 0.126 | +| time/ | | +| fps | 310 | +| iterations | 2987 | +| time_elapsed | 9853 | +| total_timesteps | 3058688 | +| train/ | | +| approx_kl | 4.527295 | +| clip_fraction | 0.458 | +| clip_range | 0.2 | +| entropy_loss | -0.348 | +| explained_variance | -5.21 | +| learning_rate | 0.0001 | +| loss | -0.0689 | +| n_updates | 90390 | +| policy_gradient_loss | -0.0637 | +| value_loss | 0.000531 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.95e+03 | +| ep_rew_mean | 0.129 | +| time/ | | +| fps | 310 | +| iterations | 2988 | +| time_elapsed | 9856 | +| total_timesteps | 3059712 | +| train/ | | +| approx_kl | 1.664865 | +| clip_fraction | 0.423 | +| clip_range | 0.2 | +| entropy_loss | -0.355 | +| explained_variance | -1.32 | +| learning_rate | 0.0001 | +| loss | -0.0883 | +| n_updates | 90400 | +| policy_gradient_loss | -0.0628 | +| value_loss | 0.000417 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.95e+03 | +| ep_rew_mean | 0.129 | +| time/ | | +| fps | 310 | +| iterations | 2989 | +| time_elapsed | 9859 | +| total_timesteps | 3060736 | +| train/ | | +| approx_kl | 1.9107214 | +| clip_fraction | 0.456 | +| clip_range | 0.2 | +| entropy_loss | -0.377 | +| explained_variance | -1.11 | +| learning_rate | 0.0001 | +| loss | -0.082 | +| n_updates | 90410 | +| policy_gradient_loss | -0.06 | +| value_loss | 0.00062 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.96e+03 | +| ep_rew_mean | 0.134 | +| time/ | | +| fps | 310 | +| iterations | 2990 | +| time_elapsed | 9862 | +| total_timesteps | 3061760 | +| train/ | | +| approx_kl | 2.600581 | +| clip_fraction | 0.469 | +| clip_range | 0.2 | +| entropy_loss | -0.427 | +| explained_variance | -0.968 | +| learning_rate | 0.0001 | +| loss | -0.0624 | +| n_updates | 90420 | +| policy_gradient_loss | -0.0644 | +| value_loss | 0.000728 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.95e+03 | +| ep_rew_mean | 0.132 | +| time/ | | +| fps | 310 | +| iterations | 2991 | +| time_elapsed | 9865 | +| total_timesteps | 3062784 | +| train/ | | +| approx_kl | 1.7494323 | +| clip_fraction | 0.429 | +| clip_range | 0.2 | +| entropy_loss | -0.305 | +| explained_variance | -1.2 | +| learning_rate | 0.0001 | +| loss | -0.0911 | +| n_updates | 90430 | +| policy_gradient_loss | -0.052 | +| value_loss | 0.000639 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.95e+03 | +| ep_rew_mean | 0.132 | +| time/ | | +| fps | 310 | +| iterations | 2992 | +| time_elapsed | 9868 | +| total_timesteps | 3063808 | +| train/ | | +| approx_kl | 1.9551439 | +| clip_fraction | 0.461 | +| clip_range | 0.2 | +| entropy_loss | -0.383 | +| explained_variance | -3.06 | +| learning_rate | 0.0001 | +| loss | -0.106 | +| n_updates | 90440 | +| policy_gradient_loss | -0.0658 | +| value_loss | 0.000483 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.95e+03 | +| ep_rew_mean | 0.132 | +| time/ | | +| fps | 310 | +| iterations | 2993 | +| time_elapsed | 9872 | +| total_timesteps | 3064832 | +| train/ | | +| approx_kl | 1.9804578 | +| clip_fraction | 0.465 | +| clip_range | 0.2 | +| entropy_loss | -0.379 | +| explained_variance | -0.511 | +| learning_rate | 0.0001 | +| loss | -0.0964 | +| n_updates | 90450 | +| policy_gradient_loss | -0.0625 | +| value_loss | 0.000701 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.95e+03 | +| ep_rew_mean | 0.132 | +| time/ | | +| fps | 310 | +| iterations | 2994 | +| time_elapsed | 9875 | +| total_timesteps | 3065856 | +| train/ | | +| approx_kl | 2.049542 | +| clip_fraction | 0.461 | +| clip_range | 0.2 | +| entropy_loss | -0.369 | +| explained_variance | -3.7 | +| learning_rate | 0.0001 | +| loss | -0.0954 | +| n_updates | 90460 | +| policy_gradient_loss | -0.0679 | +| value_loss | 0.000484 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.94e+03 | +| ep_rew_mean | 0.13 | +| time/ | | +| fps | 310 | +| iterations | 2995 | +| time_elapsed | 9878 | +| total_timesteps | 3066880 | +| train/ | | +| approx_kl | 1.9923348 | +| clip_fraction | 0.413 | +| clip_range | 0.2 | +| entropy_loss | -0.32 | +| explained_variance | -6.18 | +| learning_rate | 0.0001 | +| loss | -0.0997 | +| n_updates | 90470 | +| policy_gradient_loss | -0.0638 | +| value_loss | 0.000226 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.93e+03 | +| ep_rew_mean | 0.125 | +| time/ | | +| fps | 310 | +| iterations | 2996 | +| time_elapsed | 9881 | +| total_timesteps | 3067904 | +| train/ | | +| approx_kl | 2.3074877 | +| clip_fraction | 0.472 | +| clip_range | 0.2 | +| entropy_loss | -0.353 | +| explained_variance | -0.668 | +| learning_rate | 0.0001 | +| loss | -0.0802 | +| n_updates | 90480 | +| policy_gradient_loss | -0.0633 | +| value_loss | 0.000331 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.93e+03 | +| ep_rew_mean | 0.125 | +| time/ | | +| fps | 310 | +| iterations | 2997 | +| time_elapsed | 9885 | +| total_timesteps | 3068928 | +| train/ | | +| approx_kl | 1.7011077 | +| clip_fraction | 0.445 | +| clip_range | 0.2 | +| entropy_loss | -0.36 | +| explained_variance | -2.02 | +| learning_rate | 0.0001 | +| loss | -0.0795 | +| n_updates | 90490 | +| policy_gradient_loss | -0.0607 | +| value_loss | 0.000369 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.93e+03 | +| ep_rew_mean | 0.125 | +| time/ | | +| fps | 310 | +| iterations | 2998 | +| time_elapsed | 9888 | +| total_timesteps | 3069952 | +| train/ | | +| approx_kl | 2.0923848 | +| clip_fraction | 0.498 | +| clip_range | 0.2 | +| entropy_loss | -0.387 | +| explained_variance | -1.97 | +| learning_rate | 0.0001 | +| loss | -0.0758 | +| n_updates | 90500 | +| policy_gradient_loss | -0.0636 | +| value_loss | 0.000318 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.94e+03 | +| ep_rew_mean | 0.126 | +| time/ | | +| fps | 310 | +| iterations | 2999 | +| time_elapsed | 9892 | +| total_timesteps | 3070976 | +| train/ | | +| approx_kl | 2.233626 | +| clip_fraction | 0.489 | +| clip_range | 0.2 | +| entropy_loss | -0.391 | +| explained_variance | -3.51 | +| learning_rate | 0.0001 | +| loss | -0.0809 | +| n_updates | 90510 | +| policy_gradient_loss | -0.0628 | +| value_loss | 0.000387 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.94e+03 | +| ep_rew_mean | 0.126 | +| time/ | | +| fps | 310 | +| iterations | 3000 | +| time_elapsed | 9895 | +| total_timesteps | 3072000 | +| train/ | | +| approx_kl | 1.6350343 | +| clip_fraction | 0.463 | +| clip_range | 0.2 | +| entropy_loss | -0.374 | +| explained_variance | -1.86 | +| learning_rate | 0.0001 | +| loss | -0.091 | +| n_updates | 90520 | +| policy_gradient_loss | -0.0656 | +| value_loss | 0.000511 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.94e+03 | +| ep_rew_mean | 0.128 | +| time/ | | +| fps | 310 | +| iterations | 3001 | +| time_elapsed | 9899 | +| total_timesteps | 3073024 | +| train/ | | +| approx_kl | 2.166229 | +| clip_fraction | 0.46 | +| clip_range | 0.2 | +| entropy_loss | -0.364 | +| explained_variance | -5.34 | +| learning_rate | 0.0001 | +| loss | -0.0855 | +| n_updates | 90530 | +| policy_gradient_loss | -0.0609 | +| value_loss | 0.000614 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.94e+03 | +| ep_rew_mean | 0.128 | +| time/ | | +| fps | 310 | +| iterations | 3002 | +| time_elapsed | 9902 | +| total_timesteps | 3074048 | +| train/ | | +| approx_kl | 3.1634583 | +| clip_fraction | 0.476 | +| clip_range | 0.2 | +| entropy_loss | -0.33 | +| explained_variance | -0.926 | +| learning_rate | 0.0001 | +| loss | -0.0753 | +| n_updates | 90540 | +| policy_gradient_loss | -0.0608 | +| value_loss | 0.000506 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.94e+03 | +| ep_rew_mean | 0.131 | +| time/ | | +| fps | 310 | +| iterations | 3003 | +| time_elapsed | 9905 | +| total_timesteps | 3075072 | +| train/ | | +| approx_kl | 1.9402177 | +| clip_fraction | 0.457 | +| clip_range | 0.2 | +| entropy_loss | -0.355 | +| explained_variance | -4.17 | +| learning_rate | 0.0001 | +| loss | -0.0894 | +| n_updates | 90550 | +| policy_gradient_loss | -0.0672 | +| value_loss | 0.000528 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.94e+03 | +| ep_rew_mean | 0.131 | +| time/ | | +| fps | 310 | +| iterations | 3004 | +| time_elapsed | 9909 | +| total_timesteps | 3076096 | +| train/ | | +| approx_kl | 1.9731371 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.372 | +| explained_variance | -3.97 | +| learning_rate | 0.0001 | +| loss | -0.08 | +| n_updates | 90560 | +| policy_gradient_loss | -0.0603 | +| value_loss | 0.000488 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.93e+03 | +| ep_rew_mean | 0.13 | +| time/ | | +| fps | 310 | +| iterations | 3005 | +| time_elapsed | 9912 | +| total_timesteps | 3077120 | +| train/ | | +| approx_kl | 1.8114996 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.396 | +| explained_variance | -1.26 | +| learning_rate | 0.0001 | +| loss | -0.0949 | +| n_updates | 90570 | +| policy_gradient_loss | -0.0656 | +| value_loss | 0.000595 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.93e+03 | +| ep_rew_mean | 0.13 | +| time/ | | +| fps | 310 | +| iterations | 3006 | +| time_elapsed | 9915 | +| total_timesteps | 3078144 | +| train/ | | +| approx_kl | 1.4067345 | +| clip_fraction | 0.464 | +| clip_range | 0.2 | +| entropy_loss | -0.41 | +| explained_variance | -1.27 | +| learning_rate | 0.0001 | +| loss | -0.0771 | +| n_updates | 90580 | +| policy_gradient_loss | -0.0615 | +| value_loss | 0.000292 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.94e+03 | +| ep_rew_mean | 0.137 | +| time/ | | +| fps | 310 | +| iterations | 3007 | +| time_elapsed | 9918 | +| total_timesteps | 3079168 | +| train/ | | +| approx_kl | 2.0183244 | +| clip_fraction | 0.498 | +| clip_range | 0.2 | +| entropy_loss | -0.433 | +| explained_variance | -0.883 | +| learning_rate | 0.0001 | +| loss | -0.0871 | +| n_updates | 90590 | +| policy_gradient_loss | -0.0696 | +| value_loss | 0.00029 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.94e+03 | +| ep_rew_mean | 0.137 | +| time/ | | +| fps | 310 | +| iterations | 3008 | +| time_elapsed | 9921 | +| total_timesteps | 3080192 | +| train/ | | +| approx_kl | 1.6704155 | +| clip_fraction | 0.45 | +| clip_range | 0.2 | +| entropy_loss | -0.374 | +| explained_variance | -4.25 | +| learning_rate | 0.0001 | +| loss | -0.0977 | +| n_updates | 90600 | +| policy_gradient_loss | -0.0594 | +| value_loss | 0.000352 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.94e+03 | +| ep_rew_mean | 0.137 | +| time/ | | +| fps | 310 | +| iterations | 3009 | +| time_elapsed | 9924 | +| total_timesteps | 3081216 | +| train/ | | +| approx_kl | 2.4430757 | +| clip_fraction | 0.443 | +| clip_range | 0.2 | +| entropy_loss | -0.334 | +| explained_variance | -2 | +| learning_rate | 0.0001 | +| loss | -0.0712 | +| n_updates | 90610 | +| policy_gradient_loss | -0.0534 | +| value_loss | 0.00048 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.94e+03 | +| ep_rew_mean | 0.137 | +| time/ | | +| fps | 310 | +| iterations | 3010 | +| time_elapsed | 9927 | +| total_timesteps | 3082240 | +| train/ | | +| approx_kl | 2.4134285 | +| clip_fraction | 0.477 | +| clip_range | 0.2 | +| entropy_loss | -0.359 | +| explained_variance | -1.68 | +| learning_rate | 0.0001 | +| loss | -0.0763 | +| n_updates | 90620 | +| policy_gradient_loss | -0.0603 | +| value_loss | 0.000721 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.94e+03 | +| ep_rew_mean | 0.135 | +| time/ | | +| fps | 310 | +| iterations | 3011 | +| time_elapsed | 9931 | +| total_timesteps | 3083264 | +| train/ | | +| approx_kl | 2.060645 | +| clip_fraction | 0.482 | +| clip_range | 0.2 | +| entropy_loss | -0.363 | +| explained_variance | -6 | +| learning_rate | 0.0001 | +| loss | -0.0883 | +| n_updates | 90630 | +| policy_gradient_loss | -0.0691 | +| value_loss | 0.000732 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.94e+03 | +| ep_rew_mean | 0.135 | +| time/ | | +| fps | 310 | +| iterations | 3012 | +| time_elapsed | 9934 | +| total_timesteps | 3084288 | +| train/ | | +| approx_kl | 2.5368686 | +| clip_fraction | 0.467 | +| clip_range | 0.2 | +| entropy_loss | -0.427 | +| explained_variance | -1.2 | +| learning_rate | 0.0001 | +| loss | -0.0505 | +| n_updates | 90640 | +| policy_gradient_loss | -0.064 | +| value_loss | 0.000521 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.93e+03 | +| ep_rew_mean | 0.139 | +| time/ | | +| fps | 310 | +| iterations | 3013 | +| time_elapsed | 9937 | +| total_timesteps | 3085312 | +| train/ | | +| approx_kl | 1.7448124 | +| clip_fraction | 0.446 | +| clip_range | 0.2 | +| entropy_loss | -0.366 | +| explained_variance | -2.12 | +| learning_rate | 0.0001 | +| loss | -0.0767 | +| n_updates | 90650 | +| policy_gradient_loss | -0.0652 | +| value_loss | 0.000632 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.93e+03 | +| ep_rew_mean | 0.139 | +| time/ | | +| fps | 310 | +| iterations | 3014 | +| time_elapsed | 9940 | +| total_timesteps | 3086336 | +| train/ | | +| approx_kl | 2.4195309 | +| clip_fraction | 0.482 | +| clip_range | 0.2 | +| entropy_loss | -0.399 | +| explained_variance | -1.91 | +| learning_rate | 0.0001 | +| loss | -0.0909 | +| n_updates | 90660 | +| policy_gradient_loss | -0.0698 | +| value_loss | 0.000542 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.94e+03 | +| ep_rew_mean | 0.142 | +| time/ | | +| fps | 310 | +| iterations | 3015 | +| time_elapsed | 9944 | +| total_timesteps | 3087360 | +| train/ | | +| approx_kl | 1.8383272 | +| clip_fraction | 0.51 | +| clip_range | 0.2 | +| entropy_loss | -0.43 | +| explained_variance | -13.9 | +| learning_rate | 0.0001 | +| loss | -0.0928 | +| n_updates | 90670 | +| policy_gradient_loss | -0.0582 | +| value_loss | 0.000237 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.94e+03 | +| ep_rew_mean | 0.142 | +| time/ | | +| fps | 310 | +| iterations | 3016 | +| time_elapsed | 9947 | +| total_timesteps | 3088384 | +| train/ | | +| approx_kl | 1.9612727 | +| clip_fraction | 0.451 | +| clip_range | 0.2 | +| entropy_loss | -0.352 | +| explained_variance | -3.97 | +| learning_rate | 0.0001 | +| loss | -0.0821 | +| n_updates | 90680 | +| policy_gradient_loss | -0.0639 | +| value_loss | 0.000348 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.92e+03 | +| ep_rew_mean | 0.144 | +| time/ | | +| fps | 310 | +| iterations | 3017 | +| time_elapsed | 9951 | +| total_timesteps | 3089408 | +| train/ | | +| approx_kl | 2.2807875 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.387 | +| explained_variance | -0.83 | +| learning_rate | 0.0001 | +| loss | -0.0862 | +| n_updates | 90690 | +| policy_gradient_loss | -0.061 | +| value_loss | 0.000356 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.92e+03 | +| ep_rew_mean | 0.145 | +| time/ | | +| fps | 310 | +| iterations | 3018 | +| time_elapsed | 9955 | +| total_timesteps | 3090432 | +| train/ | | +| approx_kl | 3.1614316 | +| clip_fraction | 0.486 | +| clip_range | 0.2 | +| entropy_loss | -0.449 | +| explained_variance | -1.68 | +| learning_rate | 0.0001 | +| loss | -0.0999 | +| n_updates | 90700 | +| policy_gradient_loss | -0.0682 | +| value_loss | 0.000325 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.92e+03 | +| ep_rew_mean | 0.145 | +| time/ | | +| fps | 310 | +| iterations | 3019 | +| time_elapsed | 9958 | +| total_timesteps | 3091456 | +| train/ | | +| approx_kl | 1.3563719 | +| clip_fraction | 0.502 | +| clip_range | 0.2 | +| entropy_loss | -0.466 | +| explained_variance | -1.39 | +| learning_rate | 0.0001 | +| loss | -0.094 | +| n_updates | 90710 | +| policy_gradient_loss | -0.0656 | +| value_loss | 0.000297 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.92e+03 | +| ep_rew_mean | 0.139 | +| time/ | | +| fps | 310 | +| iterations | 3020 | +| time_elapsed | 9962 | +| total_timesteps | 3092480 | +| train/ | | +| approx_kl | 1.9066782 | +| clip_fraction | 0.473 | +| clip_range | 0.2 | +| entropy_loss | -0.382 | +| explained_variance | -3.25 | +| learning_rate | 0.0001 | +| loss | -0.0841 | +| n_updates | 90720 | +| policy_gradient_loss | -0.0689 | +| value_loss | 0.00037 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.92e+03 | +| ep_rew_mean | 0.139 | +| time/ | | +| fps | 310 | +| iterations | 3021 | +| time_elapsed | 9965 | +| total_timesteps | 3093504 | +| train/ | | +| approx_kl | 1.9613338 | +| clip_fraction | 0.459 | +| clip_range | 0.2 | +| entropy_loss | -0.367 | +| explained_variance | -1.35 | +| learning_rate | 0.0001 | +| loss | -0.0816 | +| n_updates | 90730 | +| policy_gradient_loss | -0.0558 | +| value_loss | 0.000377 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.92e+03 | +| ep_rew_mean | 0.139 | +| time/ | | +| fps | 310 | +| iterations | 3022 | +| time_elapsed | 9968 | +| total_timesteps | 3094528 | +| train/ | | +| approx_kl | 4.3573146 | +| clip_fraction | 0.479 | +| clip_range | 0.2 | +| entropy_loss | -0.373 | +| explained_variance | -1.22 | +| learning_rate | 0.0001 | +| loss | -0.0821 | +| n_updates | 90740 | +| policy_gradient_loss | -0.0605 | +| value_loss | 0.00058 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.92e+03 | +| ep_rew_mean | 0.141 | +| time/ | | +| fps | 310 | +| iterations | 3023 | +| time_elapsed | 9972 | +| total_timesteps | 3095552 | +| train/ | | +| approx_kl | 2.3842132 | +| clip_fraction | 0.438 | +| clip_range | 0.2 | +| entropy_loss | -0.325 | +| explained_variance | -3.05 | +| learning_rate | 0.0001 | +| loss | -0.0672 | +| n_updates | 90750 | +| policy_gradient_loss | -0.0651 | +| value_loss | 0.000545 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.92e+03 | +| ep_rew_mean | 0.136 | +| time/ | | +| fps | 310 | +| iterations | 3024 | +| time_elapsed | 9975 | +| total_timesteps | 3096576 | +| train/ | | +| approx_kl | 1.9976592 | +| clip_fraction | 0.478 | +| clip_range | 0.2 | +| entropy_loss | -0.394 | +| explained_variance | -1.51 | +| learning_rate | 0.0001 | +| loss | -0.115 | +| n_updates | 90760 | +| policy_gradient_loss | -0.0585 | +| value_loss | 0.000445 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.9e+03 | +| ep_rew_mean | 0.131 | +| time/ | | +| fps | 310 | +| iterations | 3025 | +| time_elapsed | 9978 | +| total_timesteps | 3097600 | +| train/ | | +| approx_kl | 1.6687214 | +| clip_fraction | 0.43 | +| clip_range | 0.2 | +| entropy_loss | -0.37 | +| explained_variance | -1.8 | +| learning_rate | 0.0001 | +| loss | -0.0529 | +| n_updates | 90770 | +| policy_gradient_loss | -0.0581 | +| value_loss | 0.000319 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.9e+03 | +| ep_rew_mean | 0.131 | +| time/ | | +| fps | 310 | +| iterations | 3026 | +| time_elapsed | 9981 | +| total_timesteps | 3098624 | +| train/ | | +| approx_kl | 2.1275187 | +| clip_fraction | 0.474 | +| clip_range | 0.2 | +| entropy_loss | -0.386 | +| explained_variance | -2.04 | +| learning_rate | 0.0001 | +| loss | -0.0875 | +| n_updates | 90780 | +| policy_gradient_loss | -0.0657 | +| value_loss | 0.000326 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.9e+03 | +| ep_rew_mean | 0.133 | +| time/ | | +| fps | 310 | +| iterations | 3027 | +| time_elapsed | 9984 | +| total_timesteps | 3099648 | +| train/ | | +| approx_kl | 2.0029926 | +| clip_fraction | 0.462 | +| clip_range | 0.2 | +| entropy_loss | -0.342 | +| explained_variance | -0.516 | +| learning_rate | 0.0001 | +| loss | -0.0581 | +| n_updates | 90790 | +| policy_gradient_loss | -0.0634 | +| value_loss | 0.000628 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.9e+03 | +| ep_rew_mean | 0.143 | +| time/ | | +| fps | 310 | +| iterations | 3028 | +| time_elapsed | 9988 | +| total_timesteps | 3100672 | +| train/ | | +| approx_kl | 2.232685 | +| clip_fraction | 0.447 | +| clip_range | 0.2 | +| entropy_loss | -0.343 | +| explained_variance | -1.5 | +| learning_rate | 0.0001 | +| loss | -0.0402 | +| n_updates | 90800 | +| policy_gradient_loss | -0.058 | +| value_loss | 0.000871 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.9e+03 | +| ep_rew_mean | 0.143 | +| time/ | | +| fps | 310 | +| iterations | 3029 | +| time_elapsed | 9991 | +| total_timesteps | 3101696 | +| train/ | | +| approx_kl | 1.6720748 | +| clip_fraction | 0.472 | +| clip_range | 0.2 | +| entropy_loss | -0.388 | +| explained_variance | -0.673 | +| learning_rate | 0.0001 | +| loss | -0.0904 | +| n_updates | 90810 | +| policy_gradient_loss | -0.0646 | +| value_loss | 0.00125 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.9e+03 | +| ep_rew_mean | 0.143 | +| time/ | | +| fps | 310 | +| iterations | 3030 | +| time_elapsed | 9994 | +| total_timesteps | 3102720 | +| train/ | | +| approx_kl | 2.0176952 | +| clip_fraction | 0.477 | +| clip_range | 0.2 | +| entropy_loss | -0.367 | +| explained_variance | -3.89 | +| learning_rate | 0.0001 | +| loss | -0.0845 | +| n_updates | 90820 | +| policy_gradient_loss | -0.0681 | +| value_loss | 0.000567 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.91e+03 | +| ep_rew_mean | 0.144 | +| time/ | | +| fps | 310 | +| iterations | 3031 | +| time_elapsed | 9997 | +| total_timesteps | 3103744 | +| train/ | | +| approx_kl | 2.0814774 | +| clip_fraction | 0.467 | +| clip_range | 0.2 | +| entropy_loss | -0.372 | +| explained_variance | -2.64 | +| learning_rate | 0.0001 | +| loss | -0.0927 | +| n_updates | 90830 | +| policy_gradient_loss | -0.0673 | +| value_loss | 0.000649 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.91e+03 | +| ep_rew_mean | 0.143 | +| time/ | | +| fps | 310 | +| iterations | 3032 | +| time_elapsed | 10001 | +| total_timesteps | 3104768 | +| train/ | | +| approx_kl | 2.0348954 | +| clip_fraction | 0.465 | +| clip_range | 0.2 | +| entropy_loss | -0.368 | +| explained_variance | -1.55 | +| learning_rate | 0.0001 | +| loss | -0.111 | +| n_updates | 90840 | +| policy_gradient_loss | -0.0677 | +| value_loss | 0.000464 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.91e+03 | +| ep_rew_mean | 0.143 | +| time/ | | +| fps | 310 | +| iterations | 3033 | +| time_elapsed | 10004 | +| total_timesteps | 3105792 | +| train/ | | +| approx_kl | 1.8506918 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.39 | +| explained_variance | -1.32 | +| learning_rate | 0.0001 | +| loss | -0.0664 | +| n_updates | 90850 | +| policy_gradient_loss | -0.0633 | +| value_loss | 0.000535 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.91e+03 | +| ep_rew_mean | 0.145 | +| time/ | | +| fps | 310 | +| iterations | 3034 | +| time_elapsed | 10007 | +| total_timesteps | 3106816 | +| train/ | | +| approx_kl | 2.01191 | +| clip_fraction | 0.472 | +| clip_range | 0.2 | +| entropy_loss | -0.365 | +| explained_variance | -1.89 | +| learning_rate | 0.0001 | +| loss | -0.0853 | +| n_updates | 90860 | +| policy_gradient_loss | -0.0655 | +| value_loss | 0.000661 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.91e+03 | +| ep_rew_mean | 0.145 | +| time/ | | +| fps | 310 | +| iterations | 3035 | +| time_elapsed | 10011 | +| total_timesteps | 3107840 | +| train/ | | +| approx_kl | 3.727869 | +| clip_fraction | 0.469 | +| clip_range | 0.2 | +| entropy_loss | -0.338 | +| explained_variance | -1.29 | +| learning_rate | 0.0001 | +| loss | -0.0904 | +| n_updates | 90870 | +| policy_gradient_loss | -0.06 | +| value_loss | 0.000537 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.91e+03 | +| ep_rew_mean | 0.14 | +| time/ | | +| fps | 310 | +| iterations | 3036 | +| time_elapsed | 10014 | +| total_timesteps | 3108864 | +| train/ | | +| approx_kl | 1.5828843 | +| clip_fraction | 0.466 | +| clip_range | 0.2 | +| entropy_loss | -0.38 | +| explained_variance | -3.13 | +| learning_rate | 0.0001 | +| loss | -0.0912 | +| n_updates | 90880 | +| policy_gradient_loss | -0.0631 | +| value_loss | 0.000365 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.9e+03 | +| ep_rew_mean | 0.14 | +| time/ | | +| fps | 310 | +| iterations | 3037 | +| time_elapsed | 10018 | +| total_timesteps | 3109888 | +| train/ | | +| approx_kl | 1.84862 | +| clip_fraction | 0.43 | +| clip_range | 0.2 | +| entropy_loss | -0.35 | +| explained_variance | -1.53 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 90890 | +| policy_gradient_loss | -0.0613 | +| value_loss | 0.000492 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.9e+03 | +| ep_rew_mean | 0.14 | +| time/ | | +| fps | 310 | +| iterations | 3038 | +| time_elapsed | 10021 | +| total_timesteps | 3110912 | +| train/ | | +| approx_kl | 2.7751546 | +| clip_fraction | 0.466 | +| clip_range | 0.2 | +| entropy_loss | -0.382 | +| explained_variance | -1.37 | +| learning_rate | 0.0001 | +| loss | -0.0986 | +| n_updates | 90900 | +| policy_gradient_loss | -0.0604 | +| value_loss | 0.000492 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.89e+03 | +| ep_rew_mean | 0.138 | +| time/ | | +| fps | 310 | +| iterations | 3039 | +| time_elapsed | 10025 | +| total_timesteps | 3111936 | +| train/ | | +| approx_kl | 1.8488269 | +| clip_fraction | 0.443 | +| clip_range | 0.2 | +| entropy_loss | -0.323 | +| explained_variance | -13 | +| learning_rate | 0.0001 | +| loss | -0.0762 | +| n_updates | 90910 | +| policy_gradient_loss | -0.0672 | +| value_loss | 0.000487 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.89e+03 | +| ep_rew_mean | 0.141 | +| time/ | | +| fps | 310 | +| iterations | 3040 | +| time_elapsed | 10028 | +| total_timesteps | 3112960 | +| train/ | | +| approx_kl | 2.4277842 | +| clip_fraction | 0.478 | +| clip_range | 0.2 | +| entropy_loss | -0.36 | +| explained_variance | -2.26 | +| learning_rate | 0.0001 | +| loss | -0.0767 | +| n_updates | 90920 | +| policy_gradient_loss | -0.0686 | +| value_loss | 0.000357 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.89e+03 | +| ep_rew_mean | 0.141 | +| time/ | | +| fps | 310 | +| iterations | 3041 | +| time_elapsed | 10031 | +| total_timesteps | 3113984 | +| train/ | | +| approx_kl | 2.0453598 | +| clip_fraction | 0.495 | +| clip_range | 0.2 | +| entropy_loss | -0.385 | +| explained_variance | -3.12 | +| learning_rate | 0.0001 | +| loss | -0.0912 | +| n_updates | 90930 | +| policy_gradient_loss | -0.0648 | +| value_loss | 0.000503 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.14 | +| time/ | | +| fps | 310 | +| iterations | 3042 | +| time_elapsed | 10034 | +| total_timesteps | 3115008 | +| train/ | | +| approx_kl | 1.829881 | +| clip_fraction | 0.474 | +| clip_range | 0.2 | +| entropy_loss | -0.367 | +| explained_variance | -2.58 | +| learning_rate | 0.0001 | +| loss | -0.093 | +| n_updates | 90940 | +| policy_gradient_loss | -0.0675 | +| value_loss | 0.000687 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.14 | +| time/ | | +| fps | 310 | +| iterations | 3043 | +| time_elapsed | 10038 | +| total_timesteps | 3116032 | +| train/ | | +| approx_kl | 2.3333564 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.392 | +| explained_variance | -2.25 | +| learning_rate | 0.0001 | +| loss | -0.115 | +| n_updates | 90950 | +| policy_gradient_loss | -0.0707 | +| value_loss | 0.000504 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.14 | +| time/ | | +| fps | 310 | +| iterations | 3044 | +| time_elapsed | 10041 | +| total_timesteps | 3117056 | +| train/ | | +| approx_kl | 2.4751482 | +| clip_fraction | 0.494 | +| clip_range | 0.2 | +| entropy_loss | -0.409 | +| explained_variance | -2.65 | +| learning_rate | 0.0001 | +| loss | -0.0845 | +| n_updates | 90960 | +| policy_gradient_loss | -0.0671 | +| value_loss | 0.000262 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.89e+03 | +| ep_rew_mean | 0.144 | +| time/ | | +| fps | 310 | +| iterations | 3045 | +| time_elapsed | 10044 | +| total_timesteps | 3118080 | +| train/ | | +| approx_kl | 1.8261604 | +| clip_fraction | 0.503 | +| clip_range | 0.2 | +| entropy_loss | -0.413 | +| explained_variance | -1.25 | +| learning_rate | 0.0001 | +| loss | -0.0904 | +| n_updates | 90970 | +| policy_gradient_loss | -0.0646 | +| value_loss | 0.000662 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.89e+03 | +| ep_rew_mean | 0.14 | +| time/ | | +| fps | 310 | +| iterations | 3046 | +| time_elapsed | 10047 | +| total_timesteps | 3119104 | +| train/ | | +| approx_kl | 1.5318377 | +| clip_fraction | 0.463 | +| clip_range | 0.2 | +| entropy_loss | -0.411 | +| explained_variance | -2.25 | +| learning_rate | 0.0001 | +| loss | -0.093 | +| n_updates | 90980 | +| policy_gradient_loss | -0.063 | +| value_loss | 0.000377 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.89e+03 | +| ep_rew_mean | 0.14 | +| time/ | | +| fps | 310 | +| iterations | 3047 | +| time_elapsed | 10050 | +| total_timesteps | 3120128 | +| train/ | | +| approx_kl | 2.3363607 | +| clip_fraction | 0.484 | +| clip_range | 0.2 | +| entropy_loss | -0.393 | +| explained_variance | -1.65 | +| learning_rate | 0.0001 | +| loss | -0.0862 | +| n_updates | 90990 | +| policy_gradient_loss | -0.0678 | +| value_loss | 0.000455 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.9e+03 | +| ep_rew_mean | 0.147 | +| time/ | | +| fps | 310 | +| iterations | 3048 | +| time_elapsed | 10053 | +| total_timesteps | 3121152 | +| train/ | | +| approx_kl | 1.9162816 | +| clip_fraction | 0.488 | +| clip_range | 0.2 | +| entropy_loss | -0.396 | +| explained_variance | -1.86 | +| learning_rate | 0.0001 | +| loss | -0.0894 | +| n_updates | 91000 | +| policy_gradient_loss | -0.0655 | +| value_loss | 0.000493 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.9e+03 | +| ep_rew_mean | 0.147 | +| time/ | | +| fps | 310 | +| iterations | 3049 | +| time_elapsed | 10056 | +| total_timesteps | 3122176 | +| train/ | | +| approx_kl | 2.0119274 | +| clip_fraction | 0.444 | +| clip_range | 0.2 | +| entropy_loss | -0.363 | +| explained_variance | -0.893 | +| learning_rate | 0.0001 | +| loss | -0.0869 | +| n_updates | 91010 | +| policy_gradient_loss | -0.0555 | +| value_loss | 0.000605 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.9e+03 | +| ep_rew_mean | 0.147 | +| time/ | | +| fps | 310 | +| iterations | 3050 | +| time_elapsed | 10060 | +| total_timesteps | 3123200 | +| train/ | | +| approx_kl | 1.9539121 | +| clip_fraction | 0.47 | +| clip_range | 0.2 | +| entropy_loss | -0.352 | +| explained_variance | -2.68 | +| learning_rate | 0.0001 | +| loss | -0.0922 | +| n_updates | 91020 | +| policy_gradient_loss | -0.0582 | +| value_loss | 0.00101 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.9e+03 | +| ep_rew_mean | 0.151 | +| time/ | | +| fps | 310 | +| iterations | 3051 | +| time_elapsed | 10063 | +| total_timesteps | 3124224 | +| train/ | | +| approx_kl | 1.4533362 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.43 | +| explained_variance | -3.92 | +| learning_rate | 0.0001 | +| loss | -0.11 | +| n_updates | 91030 | +| policy_gradient_loss | -0.0662 | +| value_loss | 0.000782 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.9e+03 | +| ep_rew_mean | 0.151 | +| time/ | | +| fps | 310 | +| iterations | 3052 | +| time_elapsed | 10066 | +| total_timesteps | 3125248 | +| train/ | | +| approx_kl | 1.6495016 | +| clip_fraction | 0.478 | +| clip_range | 0.2 | +| entropy_loss | -0.396 | +| explained_variance | -1.75 | +| learning_rate | 0.0001 | +| loss | -0.0907 | +| n_updates | 91040 | +| policy_gradient_loss | -0.0668 | +| value_loss | 0.000583 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.9e+03 | +| ep_rew_mean | 0.155 | +| time/ | | +| fps | 310 | +| iterations | 3053 | +| time_elapsed | 10070 | +| total_timesteps | 3126272 | +| train/ | | +| approx_kl | 1.8794798 | +| clip_fraction | 0.496 | +| clip_range | 0.2 | +| entropy_loss | -0.45 | +| explained_variance | -0.554 | +| learning_rate | 0.0001 | +| loss | -0.0523 | +| n_updates | 91050 | +| policy_gradient_loss | -0.0564 | +| value_loss | 0.000607 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.89e+03 | +| ep_rew_mean | 0.153 | +| time/ | | +| fps | 310 | +| iterations | 3054 | +| time_elapsed | 10073 | +| total_timesteps | 3127296 | +| train/ | | +| approx_kl | 3.2176087 | +| clip_fraction | 0.503 | +| clip_range | 0.2 | +| entropy_loss | -0.416 | +| explained_variance | -1.72 | +| learning_rate | 0.0001 | +| loss | -0.0708 | +| n_updates | 91060 | +| policy_gradient_loss | -0.0609 | +| value_loss | 0.000583 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.89e+03 | +| ep_rew_mean | 0.153 | +| time/ | | +| fps | 310 | +| iterations | 3055 | +| time_elapsed | 10077 | +| total_timesteps | 3128320 | +| train/ | | +| approx_kl | 1.8887787 | +| clip_fraction | 0.464 | +| clip_range | 0.2 | +| entropy_loss | -0.364 | +| explained_variance | -2.35 | +| learning_rate | 0.0001 | +| loss | -0.093 | +| n_updates | 91070 | +| policy_gradient_loss | -0.0684 | +| value_loss | 0.000329 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.89e+03 | +| ep_rew_mean | 0.161 | +| time/ | | +| fps | 310 | +| iterations | 3056 | +| time_elapsed | 10080 | +| total_timesteps | 3129344 | +| train/ | | +| approx_kl | 1.5875242 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.418 | +| explained_variance | -1.46 | +| learning_rate | 0.0001 | +| loss | -0.114 | +| n_updates | 91080 | +| policy_gradient_loss | -0.0583 | +| value_loss | 0.000483 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.89e+03 | +| ep_rew_mean | 0.161 | +| time/ | | +| fps | 310 | +| iterations | 3057 | +| time_elapsed | 10084 | +| total_timesteps | 3130368 | +| train/ | | +| approx_kl | 1.8899817 | +| clip_fraction | 0.467 | +| clip_range | 0.2 | +| entropy_loss | -0.415 | +| explained_variance | -0.882 | +| learning_rate | 0.0001 | +| loss | -0.0819 | +| n_updates | 91090 | +| policy_gradient_loss | -0.0569 | +| value_loss | 0.000465 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.89e+03 | +| ep_rew_mean | 0.16 | +| time/ | | +| fps | 310 | +| iterations | 3058 | +| time_elapsed | 10087 | +| total_timesteps | 3131392 | +| train/ | | +| approx_kl | 2.011204 | +| clip_fraction | 0.488 | +| clip_range | 0.2 | +| entropy_loss | -0.451 | +| explained_variance | -2.18 | +| learning_rate | 0.0001 | +| loss | -0.0742 | +| n_updates | 91100 | +| policy_gradient_loss | -0.0658 | +| value_loss | 0.000492 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.157 | +| time/ | | +| fps | 310 | +| iterations | 3059 | +| time_elapsed | 10090 | +| total_timesteps | 3132416 | +| train/ | | +| approx_kl | 1.9422772 | +| clip_fraction | 0.446 | +| clip_range | 0.2 | +| entropy_loss | -0.341 | +| explained_variance | -1.47 | +| learning_rate | 0.0001 | +| loss | -0.0788 | +| n_updates | 91110 | +| policy_gradient_loss | -0.0666 | +| value_loss | 0.000652 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.155 | +| time/ | | +| fps | 310 | +| iterations | 3060 | +| time_elapsed | 10094 | +| total_timesteps | 3133440 | +| train/ | | +| approx_kl | 2.1672146 | +| clip_fraction | 0.461 | +| clip_range | 0.2 | +| entropy_loss | -0.372 | +| explained_variance | -7.4 | +| learning_rate | 0.0001 | +| loss | -0.0785 | +| n_updates | 91120 | +| policy_gradient_loss | -0.0676 | +| value_loss | 0.000567 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.155 | +| time/ | | +| fps | 310 | +| iterations | 3061 | +| time_elapsed | 10097 | +| total_timesteps | 3134464 | +| train/ | | +| approx_kl | 1.7440741 | +| clip_fraction | 0.441 | +| clip_range | 0.2 | +| entropy_loss | -0.417 | +| explained_variance | -1.07 | +| learning_rate | 0.0001 | +| loss | 0.0127 | +| n_updates | 91130 | +| policy_gradient_loss | -0.0572 | +| value_loss | 0.000523 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.155 | +| time/ | | +| fps | 310 | +| iterations | 3062 | +| time_elapsed | 10100 | +| total_timesteps | 3135488 | +| train/ | | +| approx_kl | 1.995215 | +| clip_fraction | 0.495 | +| clip_range | 0.2 | +| entropy_loss | -0.423 | +| explained_variance | -3.59 | +| learning_rate | 0.0001 | +| loss | -0.0731 | +| n_updates | 91140 | +| policy_gradient_loss | -0.0702 | +| value_loss | 0.000287 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.89e+03 | +| ep_rew_mean | 0.151 | +| time/ | | +| fps | 310 | +| iterations | 3063 | +| time_elapsed | 10103 | +| total_timesteps | 3136512 | +| train/ | | +| approx_kl | 1.5073414 | +| clip_fraction | 0.46 | +| clip_range | 0.2 | +| entropy_loss | -0.389 | +| explained_variance | -1.53 | +| learning_rate | 0.0001 | +| loss | -0.0995 | +| n_updates | 91150 | +| policy_gradient_loss | -0.0641 | +| value_loss | 0.000632 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.89e+03 | +| ep_rew_mean | 0.151 | +| time/ | | +| fps | 310 | +| iterations | 3064 | +| time_elapsed | 10106 | +| total_timesteps | 3137536 | +| train/ | | +| approx_kl | 2.4575074 | +| clip_fraction | 0.476 | +| clip_range | 0.2 | +| entropy_loss | -0.398 | +| explained_variance | -3 | +| learning_rate | 0.0001 | +| loss | -0.0689 | +| n_updates | 91160 | +| policy_gradient_loss | -0.0696 | +| value_loss | 0.000344 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.9e+03 | +| ep_rew_mean | 0.155 | +| time/ | | +| fps | 310 | +| iterations | 3065 | +| time_elapsed | 10110 | +| total_timesteps | 3138560 | +| train/ | | +| approx_kl | 1.9764211 | +| clip_fraction | 0.473 | +| clip_range | 0.2 | +| entropy_loss | -0.391 | +| explained_variance | -3.84 | +| learning_rate | 0.0001 | +| loss | -0.0694 | +| n_updates | 91170 | +| policy_gradient_loss | -0.065 | +| value_loss | 0.000476 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.9e+03 | +| ep_rew_mean | 0.155 | +| time/ | | +| fps | 310 | +| iterations | 3066 | +| time_elapsed | 10113 | +| total_timesteps | 3139584 | +| train/ | | +| approx_kl | 2.2913191 | +| clip_fraction | 0.456 | +| clip_range | 0.2 | +| entropy_loss | -0.398 | +| explained_variance | -1.06 | +| learning_rate | 0.0001 | +| loss | -0.0758 | +| n_updates | 91180 | +| policy_gradient_loss | -0.0581 | +| value_loss | 0.000584 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.15 | +| time/ | | +| fps | 310 | +| iterations | 3067 | +| time_elapsed | 10116 | +| total_timesteps | 3140608 | +| train/ | | +| approx_kl | 1.5989224 | +| clip_fraction | 0.479 | +| clip_range | 0.2 | +| entropy_loss | -0.44 | +| explained_variance | -2.6 | +| learning_rate | 0.0001 | +| loss | -0.117 | +| n_updates | 91190 | +| policy_gradient_loss | -0.0669 | +| value_loss | 0.000476 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.89e+03 | +| ep_rew_mean | 0.148 | +| time/ | | +| fps | 310 | +| iterations | 3068 | +| time_elapsed | 10119 | +| total_timesteps | 3141632 | +| train/ | | +| approx_kl | 5.11195 | +| clip_fraction | 0.43 | +| clip_range | 0.2 | +| entropy_loss | -0.34 | +| explained_variance | -0.74 | +| learning_rate | 0.0001 | +| loss | -0.109 | +| n_updates | 91200 | +| policy_gradient_loss | -0.0566 | +| value_loss | 0.000638 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.143 | +| time/ | | +| fps | 310 | +| iterations | 3069 | +| time_elapsed | 10123 | +| total_timesteps | 3142656 | +| train/ | | +| approx_kl | 5.010318 | +| clip_fraction | 0.473 | +| clip_range | 0.2 | +| entropy_loss | -0.388 | +| explained_variance | -1.39 | +| learning_rate | 0.0001 | +| loss | -0.0765 | +| n_updates | 91210 | +| policy_gradient_loss | -0.0611 | +| value_loss | 0.000378 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.143 | +| time/ | | +| fps | 310 | +| iterations | 3070 | +| time_elapsed | 10126 | +| total_timesteps | 3143680 | +| train/ | | +| approx_kl | 1.6644679 | +| clip_fraction | 0.468 | +| clip_range | 0.2 | +| entropy_loss | -0.357 | +| explained_variance | -1.42 | +| learning_rate | 0.0001 | +| loss | -0.109 | +| n_updates | 91220 | +| policy_gradient_loss | -0.0694 | +| value_loss | 0.000639 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.14 | +| time/ | | +| fps | 310 | +| iterations | 3071 | +| time_elapsed | 10130 | +| total_timesteps | 3144704 | +| train/ | | +| approx_kl | 2.292713 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.333 | +| explained_variance | -2.6 | +| learning_rate | 0.0001 | +| loss | -0.1 | +| n_updates | 91230 | +| policy_gradient_loss | -0.068 | +| value_loss | 0.000426 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.14 | +| time/ | | +| fps | 310 | +| iterations | 3072 | +| time_elapsed | 10133 | +| total_timesteps | 3145728 | +| train/ | | +| approx_kl | 2.3216147 | +| clip_fraction | 0.463 | +| clip_range | 0.2 | +| entropy_loss | -0.354 | +| explained_variance | -3.88 | +| learning_rate | 0.0001 | +| loss | -0.0322 | +| n_updates | 91240 | +| policy_gradient_loss | -0.061 | +| value_loss | 0.000619 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.142 | +| time/ | | +| fps | 310 | +| iterations | 3073 | +| time_elapsed | 10136 | +| total_timesteps | 3146752 | +| train/ | | +| approx_kl | 1.923756 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.374 | +| explained_variance | -1.07 | +| learning_rate | 0.0001 | +| loss | -0.0889 | +| n_updates | 91250 | +| policy_gradient_loss | -0.0639 | +| value_loss | 0.000611 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.142 | +| time/ | | +| fps | 310 | +| iterations | 3074 | +| time_elapsed | 10140 | +| total_timesteps | 3147776 | +| train/ | | +| approx_kl | 2.1196256 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.378 | +| explained_variance | -1.5 | +| learning_rate | 0.0001 | +| loss | -0.0961 | +| n_updates | 91260 | +| policy_gradient_loss | -0.0684 | +| value_loss | 0.000465 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.137 | +| time/ | | +| fps | 310 | +| iterations | 3075 | +| time_elapsed | 10143 | +| total_timesteps | 3148800 | +| train/ | | +| approx_kl | 1.7953446 | +| clip_fraction | 0.46 | +| clip_range | 0.2 | +| entropy_loss | -0.363 | +| explained_variance | -1.76 | +| learning_rate | 0.0001 | +| loss | -0.0479 | +| n_updates | 91270 | +| policy_gradient_loss | -0.0621 | +| value_loss | 0.000501 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.139 | +| time/ | | +| fps | 310 | +| iterations | 3076 | +| time_elapsed | 10147 | +| total_timesteps | 3149824 | +| train/ | | +| approx_kl | 1.7159201 | +| clip_fraction | 0.46 | +| clip_range | 0.2 | +| entropy_loss | -0.373 | +| explained_variance | -5.31 | +| learning_rate | 0.0001 | +| loss | -0.0902 | +| n_updates | 91280 | +| policy_gradient_loss | -0.0616 | +| value_loss | 0.000419 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.139 | +| time/ | | +| fps | 310 | +| iterations | 3077 | +| time_elapsed | 10150 | +| total_timesteps | 3150848 | +| train/ | | +| approx_kl | 2.2140946 | +| clip_fraction | 0.464 | +| clip_range | 0.2 | +| entropy_loss | -0.356 | +| explained_variance | -0.527 | +| learning_rate | 0.0001 | +| loss | -0.0824 | +| n_updates | 91290 | +| policy_gradient_loss | -0.0616 | +| value_loss | 0.000528 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.145 | +| time/ | | +| fps | 310 | +| iterations | 3078 | +| time_elapsed | 10153 | +| total_timesteps | 3151872 | +| train/ | | +| approx_kl | 2.6278133 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.363 | +| explained_variance | -3.41 | +| learning_rate | 0.0001 | +| loss | -0.0685 | +| n_updates | 91300 | +| policy_gradient_loss | -0.0684 | +| value_loss | 0.000633 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.145 | +| time/ | | +| fps | 310 | +| iterations | 3079 | +| time_elapsed | 10156 | +| total_timesteps | 3152896 | +| train/ | | +| approx_kl | 2.5341885 | +| clip_fraction | 0.46 | +| clip_range | 0.2 | +| entropy_loss | -0.351 | +| explained_variance | -4.63 | +| learning_rate | 0.0001 | +| loss | -0.0884 | +| n_updates | 91310 | +| policy_gradient_loss | -0.0645 | +| value_loss | 0.000596 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.145 | +| time/ | | +| fps | 310 | +| iterations | 3080 | +| time_elapsed | 10159 | +| total_timesteps | 3153920 | +| train/ | | +| approx_kl | 2.1205816 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.361 | +| explained_variance | -2.96 | +| learning_rate | 0.0001 | +| loss | -0.0848 | +| n_updates | 91320 | +| policy_gradient_loss | -0.0705 | +| value_loss | 0.000671 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.89e+03 | +| ep_rew_mean | 0.145 | +| time/ | | +| fps | 310 | +| iterations | 3081 | +| time_elapsed | 10163 | +| total_timesteps | 3154944 | +| train/ | | +| approx_kl | 2.1763792 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.334 | +| explained_variance | -0.812 | +| learning_rate | 0.0001 | +| loss | -0.0958 | +| n_updates | 91330 | +| policy_gradient_loss | -0.0681 | +| value_loss | 0.000557 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.14 | +| time/ | | +| fps | 310 | +| iterations | 3082 | +| time_elapsed | 10166 | +| total_timesteps | 3155968 | +| train/ | | +| approx_kl | 1.9759754 | +| clip_fraction | 0.453 | +| clip_range | 0.2 | +| entropy_loss | -0.355 | +| explained_variance | -3.48 | +| learning_rate | 0.0001 | +| loss | -0.0847 | +| n_updates | 91340 | +| policy_gradient_loss | -0.0645 | +| value_loss | 0.000936 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.14 | +| time/ | | +| fps | 310 | +| iterations | 3083 | +| time_elapsed | 10169 | +| total_timesteps | 3156992 | +| train/ | | +| approx_kl | 2.6810932 | +| clip_fraction | 0.459 | +| clip_range | 0.2 | +| entropy_loss | -0.391 | +| explained_variance | -3.35 | +| learning_rate | 0.0001 | +| loss | -0.0907 | +| n_updates | 91350 | +| policy_gradient_loss | -0.0624 | +| value_loss | 0.000414 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.142 | +| time/ | | +| fps | 310 | +| iterations | 3084 | +| time_elapsed | 10172 | +| total_timesteps | 3158016 | +| train/ | | +| approx_kl | 2.2278247 | +| clip_fraction | 0.477 | +| clip_range | 0.2 | +| entropy_loss | -0.363 | +| explained_variance | -1.85 | +| learning_rate | 0.0001 | +| loss | -0.0687 | +| n_updates | 91360 | +| policy_gradient_loss | -0.0662 | +| value_loss | 0.000488 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.141 | +| time/ | | +| fps | 310 | +| iterations | 3085 | +| time_elapsed | 10175 | +| total_timesteps | 3159040 | +| train/ | | +| approx_kl | 2.1366189 | +| clip_fraction | 0.461 | +| clip_range | 0.2 | +| entropy_loss | -0.315 | +| explained_variance | -1.01 | +| learning_rate | 0.0001 | +| loss | -0.0916 | +| n_updates | 91370 | +| policy_gradient_loss | -0.0601 | +| value_loss | 0.000635 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.141 | +| time/ | | +| fps | 310 | +| iterations | 3086 | +| time_elapsed | 10178 | +| total_timesteps | 3160064 | +| train/ | | +| approx_kl | 1.8576554 | +| clip_fraction | 0.465 | +| clip_range | 0.2 | +| entropy_loss | -0.352 | +| explained_variance | -7.19 | +| learning_rate | 0.0001 | +| loss | -0.0749 | +| n_updates | 91380 | +| policy_gradient_loss | -0.0509 | +| value_loss | 0.000478 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.139 | +| time/ | | +| fps | 310 | +| iterations | 3087 | +| time_elapsed | 10182 | +| total_timesteps | 3161088 | +| train/ | | +| approx_kl | 1.8501706 | +| clip_fraction | 0.466 | +| clip_range | 0.2 | +| entropy_loss | -0.386 | +| explained_variance | -5.34 | +| learning_rate | 0.0001 | +| loss | -0.0648 | +| n_updates | 91390 | +| policy_gradient_loss | -0.052 | +| value_loss | 0.000347 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.139 | +| time/ | | +| fps | 310 | +| iterations | 3088 | +| time_elapsed | 10185 | +| total_timesteps | 3162112 | +| train/ | | +| approx_kl | 1.675587 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.427 | +| explained_variance | -2.65 | +| learning_rate | 0.0001 | +| loss | -0.0524 | +| n_updates | 91400 | +| policy_gradient_loss | -0.0654 | +| value_loss | 0.000141 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.139 | +| time/ | | +| fps | 310 | +| iterations | 3089 | +| time_elapsed | 10189 | +| total_timesteps | 3163136 | +| train/ | | +| approx_kl | 2.9239955 | +| clip_fraction | 0.49 | +| clip_range | 0.2 | +| entropy_loss | -0.403 | +| explained_variance | -0.619 | +| learning_rate | 0.0001 | +| loss | -0.0868 | +| n_updates | 91410 | +| policy_gradient_loss | -0.064 | +| value_loss | 0.000446 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.143 | +| time/ | | +| fps | 310 | +| iterations | 3090 | +| time_elapsed | 10192 | +| total_timesteps | 3164160 | +| train/ | | +| approx_kl | 2.1076894 | +| clip_fraction | 0.433 | +| clip_range | 0.2 | +| entropy_loss | -0.314 | +| explained_variance | -2.35 | +| learning_rate | 0.0001 | +| loss | -0.0855 | +| n_updates | 91420 | +| policy_gradient_loss | -0.0627 | +| value_loss | 0.000943 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.148 | +| time/ | | +| fps | 310 | +| iterations | 3091 | +| time_elapsed | 10196 | +| total_timesteps | 3165184 | +| train/ | | +| approx_kl | 1.9641001 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.398 | +| explained_variance | -1.27 | +| learning_rate | 0.0001 | +| loss | -0.0839 | +| n_updates | 91430 | +| policy_gradient_loss | -0.0652 | +| value_loss | 0.000862 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.148 | +| time/ | | +| fps | 310 | +| iterations | 3092 | +| time_elapsed | 10199 | +| total_timesteps | 3166208 | +| train/ | | +| approx_kl | 2.0893464 | +| clip_fraction | 0.437 | +| clip_range | 0.2 | +| entropy_loss | -0.307 | +| explained_variance | -4.42 | +| learning_rate | 0.0001 | +| loss | -0.0608 | +| n_updates | 91440 | +| policy_gradient_loss | -0.0654 | +| value_loss | 0.000436 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.148 | +| time/ | | +| fps | 310 | +| iterations | 3093 | +| time_elapsed | 10203 | +| total_timesteps | 3167232 | +| train/ | | +| approx_kl | 2.1240711 | +| clip_fraction | 0.477 | +| clip_range | 0.2 | +| entropy_loss | -0.329 | +| explained_variance | -1.46 | +| learning_rate | 0.0001 | +| loss | -0.0761 | +| n_updates | 91450 | +| policy_gradient_loss | -0.0675 | +| value_loss | 0.00049 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.89e+03 | +| ep_rew_mean | 0.147 | +| time/ | | +| fps | 310 | +| iterations | 3094 | +| time_elapsed | 10206 | +| total_timesteps | 3168256 | +| train/ | | +| approx_kl | 2.07053 | +| clip_fraction | 0.469 | +| clip_range | 0.2 | +| entropy_loss | -0.362 | +| explained_variance | -6.64 | +| learning_rate | 0.0001 | +| loss | -0.0861 | +| n_updates | 91460 | +| policy_gradient_loss | -0.0669 | +| value_loss | 0.000269 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.89e+03 | +| ep_rew_mean | 0.147 | +| time/ | | +| fps | 310 | +| iterations | 3095 | +| time_elapsed | 10209 | +| total_timesteps | 3169280 | +| train/ | | +| approx_kl | 2.7114804 | +| clip_fraction | 0.466 | +| clip_range | 0.2 | +| entropy_loss | -0.361 | +| explained_variance | -1.52 | +| learning_rate | 0.0001 | +| loss | -0.0761 | +| n_updates | 91470 | +| policy_gradient_loss | -0.06 | +| value_loss | 0.000451 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.89e+03 | +| ep_rew_mean | 0.15 | +| time/ | | +| fps | 310 | +| iterations | 3096 | +| time_elapsed | 10213 | +| total_timesteps | 3170304 | +| train/ | | +| approx_kl | 2.1287727 | +| clip_fraction | 0.5 | +| clip_range | 0.2 | +| entropy_loss | -0.385 | +| explained_variance | -1.34 | +| learning_rate | 0.0001 | +| loss | -0.0906 | +| n_updates | 91480 | +| policy_gradient_loss | -0.0658 | +| value_loss | 0.000598 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.89e+03 | +| ep_rew_mean | 0.15 | +| time/ | | +| fps | 310 | +| iterations | 3097 | +| time_elapsed | 10216 | +| total_timesteps | 3171328 | +| train/ | | +| approx_kl | 3.2721937 | +| clip_fraction | 0.455 | +| clip_range | 0.2 | +| entropy_loss | -0.355 | +| explained_variance | -1.75 | +| learning_rate | 0.0001 | +| loss | -0.0728 | +| n_updates | 91490 | +| policy_gradient_loss | -0.0628 | +| value_loss | 0.000762 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.89e+03 | +| ep_rew_mean | 0.149 | +| time/ | | +| fps | 310 | +| iterations | 3098 | +| time_elapsed | 10219 | +| total_timesteps | 3172352 | +| train/ | | +| approx_kl | 1.985832 | +| clip_fraction | 0.474 | +| clip_range | 0.2 | +| entropy_loss | -0.373 | +| explained_variance | -2.32 | +| learning_rate | 0.0001 | +| loss | -0.0726 | +| n_updates | 91500 | +| policy_gradient_loss | -0.0537 | +| value_loss | 0.000614 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.89e+03 | +| ep_rew_mean | 0.149 | +| time/ | | +| fps | 310 | +| iterations | 3099 | +| time_elapsed | 10222 | +| total_timesteps | 3173376 | +| train/ | | +| approx_kl | 2.9053063 | +| clip_fraction | 0.46 | +| clip_range | 0.2 | +| entropy_loss | -0.34 | +| explained_variance | -3.81 | +| learning_rate | 0.0001 | +| loss | -0.0851 | +| n_updates | 91510 | +| policy_gradient_loss | -0.0662 | +| value_loss | 0.000536 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.146 | +| time/ | | +| fps | 310 | +| iterations | 3100 | +| time_elapsed | 10225 | +| total_timesteps | 3174400 | +| train/ | | +| approx_kl | 1.5862743 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.386 | +| explained_variance | -0.579 | +| learning_rate | 0.0001 | +| loss | -0.099 | +| n_updates | 91520 | +| policy_gradient_loss | -0.0619 | +| value_loss | 0.000682 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.146 | +| time/ | | +| fps | 310 | +| iterations | 3101 | +| time_elapsed | 10229 | +| total_timesteps | 3175424 | +| train/ | | +| approx_kl | 2.2238643 | +| clip_fraction | 0.453 | +| clip_range | 0.2 | +| entropy_loss | -0.325 | +| explained_variance | -9.62 | +| learning_rate | 0.0001 | +| loss | -0.0863 | +| n_updates | 91530 | +| policy_gradient_loss | -0.0702 | +| value_loss | 0.000547 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.146 | +| time/ | | +| fps | 310 | +| iterations | 3102 | +| time_elapsed | 10232 | +| total_timesteps | 3176448 | +| train/ | | +| approx_kl | 2.219808 | +| clip_fraction | 0.449 | +| clip_range | 0.2 | +| entropy_loss | -0.33 | +| explained_variance | -0.889 | +| learning_rate | 0.0001 | +| loss | -0.0708 | +| n_updates | 91540 | +| policy_gradient_loss | -0.0589 | +| value_loss | 0.000367 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.89e+03 | +| ep_rew_mean | 0.143 | +| time/ | | +| fps | 310 | +| iterations | 3103 | +| time_elapsed | 10235 | +| total_timesteps | 3177472 | +| train/ | | +| approx_kl | 2.2834795 | +| clip_fraction | 0.478 | +| clip_range | 0.2 | +| entropy_loss | -0.336 | +| explained_variance | -12.1 | +| learning_rate | 0.0001 | +| loss | -0.085 | +| n_updates | 91550 | +| policy_gradient_loss | -0.0687 | +| value_loss | 0.000222 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.89e+03 | +| ep_rew_mean | 0.143 | +| time/ | | +| fps | 310 | +| iterations | 3104 | +| time_elapsed | 10238 | +| total_timesteps | 3178496 | +| train/ | | +| approx_kl | 2.387457 | +| clip_fraction | 0.451 | +| clip_range | 0.2 | +| entropy_loss | -0.284 | +| explained_variance | -1.4 | +| learning_rate | 0.0001 | +| loss | -0.0783 | +| n_updates | 91560 | +| policy_gradient_loss | -0.0607 | +| value_loss | 0.00038 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.89e+03 | +| ep_rew_mean | 0.138 | +| time/ | | +| fps | 310 | +| iterations | 3105 | +| time_elapsed | 10242 | +| total_timesteps | 3179520 | +| train/ | | +| approx_kl | 2.2260296 | +| clip_fraction | 0.448 | +| clip_range | 0.2 | +| entropy_loss | -0.366 | +| explained_variance | -6.32 | +| learning_rate | 0.0001 | +| loss | -0.0393 | +| n_updates | 91570 | +| policy_gradient_loss | -0.0601 | +| value_loss | 0.0003 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.89e+03 | +| ep_rew_mean | 0.138 | +| time/ | | +| fps | 310 | +| iterations | 3106 | +| time_elapsed | 10245 | +| total_timesteps | 3180544 | +| train/ | | +| approx_kl | 1.7247636 | +| clip_fraction | 0.452 | +| clip_range | 0.2 | +| entropy_loss | -0.342 | +| explained_variance | -0.936 | +| learning_rate | 0.0001 | +| loss | -0.0603 | +| n_updates | 91580 | +| policy_gradient_loss | -0.052 | +| value_loss | 0.00037 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.9e+03 | +| ep_rew_mean | 0.136 | +| time/ | | +| fps | 310 | +| iterations | 3107 | +| time_elapsed | 10248 | +| total_timesteps | 3181568 | +| train/ | | +| approx_kl | 2.1655636 | +| clip_fraction | 0.47 | +| clip_range | 0.2 | +| entropy_loss | -0.337 | +| explained_variance | -0.713 | +| learning_rate | 0.0001 | +| loss | -0.0813 | +| n_updates | 91590 | +| policy_gradient_loss | -0.0633 | +| value_loss | 0.000632 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.9e+03 | +| ep_rew_mean | 0.136 | +| time/ | | +| fps | 310 | +| iterations | 3108 | +| time_elapsed | 10252 | +| total_timesteps | 3182592 | +| train/ | | +| approx_kl | 2.367883 | +| clip_fraction | 0.457 | +| clip_range | 0.2 | +| entropy_loss | -0.331 | +| explained_variance | -3.13 | +| learning_rate | 0.0001 | +| loss | -0.0524 | +| n_updates | 91600 | +| policy_gradient_loss | -0.0655 | +| value_loss | 0.000676 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.9e+03 | +| ep_rew_mean | 0.136 | +| time/ | | +| fps | 310 | +| iterations | 3109 | +| time_elapsed | 10255 | +| total_timesteps | 3183616 | +| train/ | | +| approx_kl | 1.759727 | +| clip_fraction | 0.412 | +| clip_range | 0.2 | +| entropy_loss | -0.251 | +| explained_variance | -4.38 | +| learning_rate | 0.0001 | +| loss | -0.0516 | +| n_updates | 91610 | +| policy_gradient_loss | -0.0612 | +| value_loss | 0.000365 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.91e+03 | +| ep_rew_mean | 0.137 | +| time/ | | +| fps | 310 | +| iterations | 3110 | +| time_elapsed | 10258 | +| total_timesteps | 3184640 | +| train/ | | +| approx_kl | 2.2993646 | +| clip_fraction | 0.476 | +| clip_range | 0.2 | +| entropy_loss | -0.347 | +| explained_variance | -2.34 | +| learning_rate | 0.0001 | +| loss | -0.066 | +| n_updates | 91620 | +| policy_gradient_loss | -0.0603 | +| value_loss | 0.000545 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.91e+03 | +| ep_rew_mean | 0.137 | +| time/ | | +| fps | 310 | +| iterations | 3111 | +| time_elapsed | 10262 | +| total_timesteps | 3185664 | +| train/ | | +| approx_kl | 2.2285244 | +| clip_fraction | 0.474 | +| clip_range | 0.2 | +| entropy_loss | -0.318 | +| explained_variance | -1.24 | +| learning_rate | 0.0001 | +| loss | -0.0852 | +| n_updates | 91630 | +| policy_gradient_loss | -0.061 | +| value_loss | 0.000832 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.92e+03 | +| ep_rew_mean | 0.144 | +| time/ | | +| fps | 310 | +| iterations | 3112 | +| time_elapsed | 10265 | +| total_timesteps | 3186688 | +| train/ | | +| approx_kl | 1.8835129 | +| clip_fraction | 0.447 | +| clip_range | 0.2 | +| entropy_loss | -0.344 | +| explained_variance | -2.31 | +| learning_rate | 0.0001 | +| loss | -0.0488 | +| n_updates | 91640 | +| policy_gradient_loss | -0.0585 | +| value_loss | 0.000585 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.92e+03 | +| ep_rew_mean | 0.144 | +| time/ | | +| fps | 310 | +| iterations | 3113 | +| time_elapsed | 10268 | +| total_timesteps | 3187712 | +| train/ | | +| approx_kl | 2.0985398 | +| clip_fraction | 0.41 | +| clip_range | 0.2 | +| entropy_loss | -0.249 | +| explained_variance | -1.89 | +| learning_rate | 0.0001 | +| loss | -0.0787 | +| n_updates | 91650 | +| policy_gradient_loss | -0.0558 | +| value_loss | 0.0008 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.9e+03 | +| ep_rew_mean | 0.138 | +| time/ | | +| fps | 310 | +| iterations | 3114 | +| time_elapsed | 10272 | +| total_timesteps | 3188736 | +| train/ | | +| approx_kl | 1.6055665 | +| clip_fraction | 0.433 | +| clip_range | 0.2 | +| entropy_loss | -0.357 | +| explained_variance | -4.27 | +| learning_rate | 0.0001 | +| loss | -0.0598 | +| n_updates | 91660 | +| policy_gradient_loss | -0.0568 | +| value_loss | 0.000371 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.9e+03 | +| ep_rew_mean | 0.138 | +| time/ | | +| fps | 310 | +| iterations | 3115 | +| time_elapsed | 10275 | +| total_timesteps | 3189760 | +| train/ | | +| approx_kl | 1.8620319 | +| clip_fraction | 0.446 | +| clip_range | 0.2 | +| entropy_loss | -0.354 | +| explained_variance | -0.315 | +| learning_rate | 0.0001 | +| loss | -0.0858 | +| n_updates | 91670 | +| policy_gradient_loss | -0.0495 | +| value_loss | 0.000525 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.9e+03 | +| ep_rew_mean | 0.143 | +| time/ | | +| fps | 310 | +| iterations | 3116 | +| time_elapsed | 10278 | +| total_timesteps | 3190784 | +| train/ | | +| approx_kl | 2.5191507 | +| clip_fraction | 0.476 | +| clip_range | 0.2 | +| entropy_loss | -0.306 | +| explained_variance | -2.95 | +| learning_rate | 0.0001 | +| loss | -0.0728 | +| n_updates | 91680 | +| policy_gradient_loss | -0.0654 | +| value_loss | 0.000568 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.9e+03 | +| ep_rew_mean | 0.143 | +| time/ | | +| fps | 310 | +| iterations | 3117 | +| time_elapsed | 10281 | +| total_timesteps | 3191808 | +| train/ | | +| approx_kl | 2.316573 | +| clip_fraction | 0.43 | +| clip_range | 0.2 | +| entropy_loss | -0.275 | +| explained_variance | -2.3 | +| learning_rate | 0.0001 | +| loss | -0.0584 | +| n_updates | 91690 | +| policy_gradient_loss | -0.0591 | +| value_loss | 0.000442 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.91e+03 | +| ep_rew_mean | 0.145 | +| time/ | | +| fps | 310 | +| iterations | 3118 | +| time_elapsed | 10284 | +| total_timesteps | 3192832 | +| train/ | | +| approx_kl | 2.02906 | +| clip_fraction | 0.496 | +| clip_range | 0.2 | +| entropy_loss | -0.354 | +| explained_variance | -0.897 | +| learning_rate | 0.0001 | +| loss | -0.0805 | +| n_updates | 91700 | +| policy_gradient_loss | -0.0663 | +| value_loss | 0.00071 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.91e+03 | +| ep_rew_mean | 0.145 | +| time/ | | +| fps | 310 | +| iterations | 3119 | +| time_elapsed | 10287 | +| total_timesteps | 3193856 | +| train/ | | +| approx_kl | 2.2670972 | +| clip_fraction | 0.445 | +| clip_range | 0.2 | +| entropy_loss | -0.293 | +| explained_variance | -3.34 | +| learning_rate | 0.0001 | +| loss | -0.0885 | +| n_updates | 91710 | +| policy_gradient_loss | -0.0584 | +| value_loss | 0.000683 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.91e+03 | +| ep_rew_mean | 0.145 | +| time/ | | +| fps | 310 | +| iterations | 3120 | +| time_elapsed | 10291 | +| total_timesteps | 3194880 | +| train/ | | +| approx_kl | 3.9655585 | +| clip_fraction | 0.418 | +| clip_range | 0.2 | +| entropy_loss | -0.299 | +| explained_variance | -6.9 | +| learning_rate | 0.0001 | +| loss | -0.0709 | +| n_updates | 91720 | +| policy_gradient_loss | -0.0572 | +| value_loss | 0.000379 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.93e+03 | +| ep_rew_mean | 0.149 | +| time/ | | +| fps | 310 | +| iterations | 3121 | +| time_elapsed | 10294 | +| total_timesteps | 3195904 | +| train/ | | +| approx_kl | 2.1152186 | +| clip_fraction | 0.461 | +| clip_range | 0.2 | +| entropy_loss | -0.347 | +| explained_variance | -0.649 | +| learning_rate | 0.0001 | +| loss | -0.0771 | +| n_updates | 91730 | +| policy_gradient_loss | -0.0544 | +| value_loss | 0.000453 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.93e+03 | +| ep_rew_mean | 0.149 | +| time/ | | +| fps | 310 | +| iterations | 3122 | +| time_elapsed | 10297 | +| total_timesteps | 3196928 | +| train/ | | +| approx_kl | 2.0418434 | +| clip_fraction | 0.44 | +| clip_range | 0.2 | +| entropy_loss | -0.298 | +| explained_variance | -1.73 | +| learning_rate | 0.0001 | +| loss | -0.0624 | +| n_updates | 91740 | +| policy_gradient_loss | -0.0589 | +| value_loss | 0.000335 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.93e+03 | +| ep_rew_mean | 0.149 | +| time/ | | +| fps | 310 | +| iterations | 3123 | +| time_elapsed | 10300 | +| total_timesteps | 3197952 | +| train/ | | +| approx_kl | 1.6585624 | +| clip_fraction | 0.463 | +| clip_range | 0.2 | +| entropy_loss | -0.353 | +| explained_variance | -1.74 | +| learning_rate | 0.0001 | +| loss | -0.0821 | +| n_updates | 91750 | +| policy_gradient_loss | -0.0636 | +| value_loss | 0.000332 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.93e+03 | +| ep_rew_mean | 0.151 | +| time/ | | +| fps | 310 | +| iterations | 3124 | +| time_elapsed | 10304 | +| total_timesteps | 3198976 | +| train/ | | +| approx_kl | 3.0756261 | +| clip_fraction | 0.451 | +| clip_range | 0.2 | +| entropy_loss | -0.369 | +| explained_variance | -1.21 | +| learning_rate | 0.0001 | +| loss | -0.0725 | +| n_updates | 91760 | +| policy_gradient_loss | -0.0547 | +| value_loss | 0.000711 | +--------------------------------------- + +Current state: Champion.Level9.RyuVsBalrog +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.93e+03 | +| ep_rew_mean | 0.151 | +| time/ | | +| fps | 310 | +| iterations | 3125 | +| time_elapsed | 10307 | +| total_timesteps | 3200000 | +| train/ | | +| approx_kl | 2.1819477 | +| clip_fraction | 0.454 | +| clip_range | 0.2 | +| entropy_loss | -0.304 | +| explained_variance | -2.35 | +| learning_rate | 0.0001 | +| loss | -0.0845 | +| n_updates | 91770 | +| policy_gradient_loss | -0.0564 | +| value_loss | 0.00048 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.93e+03 | +| ep_rew_mean | 0.151 | +| time/ | | +| fps | 310 | +| iterations | 3126 | +| time_elapsed | 10311 | +| total_timesteps | 3201024 | +| train/ | | +| approx_kl | 3.2995071 | +| clip_fraction | 0.436 | +| clip_range | 0.2 | +| entropy_loss | -0.294 | +| explained_variance | -1.27 | +| learning_rate | 0.0001 | +| loss | -0.108 | +| n_updates | 91780 | +| policy_gradient_loss | -0.0612 | +| value_loss | 0.000525 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.95e+03 | +| ep_rew_mean | 0.151 | +| time/ | | +| fps | 310 | +| iterations | 3127 | +| time_elapsed | 10314 | +| total_timesteps | 3202048 | +| train/ | | +| approx_kl | 2.27352 | +| clip_fraction | 0.461 | +| clip_range | 0.2 | +| entropy_loss | -0.301 | +| explained_variance | -1.6 | +| learning_rate | 0.0001 | +| loss | -0.0892 | +| n_updates | 91790 | +| policy_gradient_loss | -0.0637 | +| value_loss | 0.000572 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.94e+03 | +| ep_rew_mean | 0.15 | +| time/ | | +| fps | 310 | +| iterations | 3128 | +| time_elapsed | 10318 | +| total_timesteps | 3203072 | +| train/ | | +| approx_kl | 3.7718844 | +| clip_fraction | 0.448 | +| clip_range | 0.2 | +| entropy_loss | -0.247 | +| explained_variance | -4.81 | +| learning_rate | 0.0001 | +| loss | -0.0597 | +| n_updates | 91800 | +| policy_gradient_loss | -0.0592 | +| value_loss | 0.000589 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.94e+03 | +| ep_rew_mean | 0.148 | +| time/ | | +| fps | 310 | +| iterations | 3129 | +| time_elapsed | 10321 | +| total_timesteps | 3204096 | +| train/ | | +| approx_kl | 3.8996296 | +| clip_fraction | 0.426 | +| clip_range | 0.2 | +| entropy_loss | -0.222 | +| explained_variance | -1.85 | +| learning_rate | 0.0001 | +| loss | -0.0663 | +| n_updates | 91810 | +| policy_gradient_loss | -0.0467 | +| value_loss | 0.000568 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.94e+03 | +| ep_rew_mean | 0.148 | +| time/ | | +| fps | 310 | +| iterations | 3130 | +| time_elapsed | 10325 | +| total_timesteps | 3205120 | +| train/ | | +| approx_kl | 2.6500316 | +| clip_fraction | 0.446 | +| clip_range | 0.2 | +| entropy_loss | -0.262 | +| explained_variance | -1.5 | +| learning_rate | 0.0001 | +| loss | -0.0771 | +| n_updates | 91820 | +| policy_gradient_loss | -0.0522 | +| value_loss | 0.000386 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.94e+03 | +| ep_rew_mean | 0.144 | +| time/ | | +| fps | 310 | +| iterations | 3131 | +| time_elapsed | 10328 | +| total_timesteps | 3206144 | +| train/ | | +| approx_kl | 2.86053 | +| clip_fraction | 0.4 | +| clip_range | 0.2 | +| entropy_loss | -0.2 | +| explained_variance | -1.47 | +| learning_rate | 0.0001 | +| loss | -0.0739 | +| n_updates | 91830 | +| policy_gradient_loss | -0.0534 | +| value_loss | 0.000676 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.93e+03 | +| ep_rew_mean | 0.14 | +| time/ | | +| fps | 310 | +| iterations | 3132 | +| time_elapsed | 10331 | +| total_timesteps | 3207168 | +| train/ | | +| approx_kl | 2.636352 | +| clip_fraction | 0.408 | +| clip_range | 0.2 | +| entropy_loss | -0.236 | +| explained_variance | -5.38 | +| learning_rate | 0.0001 | +| loss | -0.0562 | +| n_updates | 91840 | +| policy_gradient_loss | -0.0519 | +| value_loss | 0.000556 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.93e+03 | +| ep_rew_mean | 0.145 | +| time/ | | +| fps | 310 | +| iterations | 3133 | +| time_elapsed | 10334 | +| total_timesteps | 3208192 | +| train/ | | +| approx_kl | 5.1571555 | +| clip_fraction | 0.433 | +| clip_range | 0.2 | +| entropy_loss | -0.237 | +| explained_variance | -0.872 | +| learning_rate | 0.0001 | +| loss | -0.0814 | +| n_updates | 91850 | +| policy_gradient_loss | -0.0631 | +| value_loss | 0.000674 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.92e+03 | +| ep_rew_mean | 0.143 | +| time/ | | +| fps | 310 | +| iterations | 3134 | +| time_elapsed | 10338 | +| total_timesteps | 3209216 | +| train/ | | +| approx_kl | 2.7719007 | +| clip_fraction | 0.435 | +| clip_range | 0.2 | +| entropy_loss | -0.212 | +| explained_variance | -1.93 | +| learning_rate | 0.0001 | +| loss | -0.0885 | +| n_updates | 91860 | +| policy_gradient_loss | -0.0523 | +| value_loss | 0.000691 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.92e+03 | +| ep_rew_mean | 0.143 | +| time/ | | +| fps | 310 | +| iterations | 3135 | +| time_elapsed | 10341 | +| total_timesteps | 3210240 | +| train/ | | +| approx_kl | 2.9053025 | +| clip_fraction | 0.406 | +| clip_range | 0.2 | +| entropy_loss | -0.22 | +| explained_variance | -1.86 | +| learning_rate | 0.0001 | +| loss | -0.0742 | +| n_updates | 91870 | +| policy_gradient_loss | -0.052 | +| value_loss | 0.000607 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.92e+03 | +| ep_rew_mean | 0.143 | +| time/ | | +| fps | 310 | +| iterations | 3136 | +| time_elapsed | 10344 | +| total_timesteps | 3211264 | +| train/ | | +| approx_kl | 2.416534 | +| clip_fraction | 0.379 | +| clip_range | 0.2 | +| entropy_loss | -0.199 | +| explained_variance | -5.98 | +| learning_rate | 0.0001 | +| loss | -0.0658 | +| n_updates | 91880 | +| policy_gradient_loss | -0.0441 | +| value_loss | 0.000566 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.9e+03 | +| ep_rew_mean | 0.142 | +| time/ | | +| fps | 310 | +| iterations | 3137 | +| time_elapsed | 10347 | +| total_timesteps | 3212288 | +| train/ | | +| approx_kl | 2.8164952 | +| clip_fraction | 0.417 | +| clip_range | 0.2 | +| entropy_loss | -0.244 | +| explained_variance | -0.219 | +| learning_rate | 0.0001 | +| loss | -0.0712 | +| n_updates | 91890 | +| policy_gradient_loss | -0.046 | +| value_loss | 0.000624 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.9e+03 | +| ep_rew_mean | 0.145 | +| time/ | | +| fps | 310 | +| iterations | 3138 | +| time_elapsed | 10350 | +| total_timesteps | 3213312 | +| train/ | | +| approx_kl | 3.0331397 | +| clip_fraction | 0.432 | +| clip_range | 0.2 | +| entropy_loss | -0.237 | +| explained_variance | -1.7 | +| learning_rate | 0.0001 | +| loss | -0.0861 | +| n_updates | 91900 | +| policy_gradient_loss | -0.0389 | +| value_loss | 0.000627 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.89e+03 | +| ep_rew_mean | 0.137 | +| time/ | | +| fps | 310 | +| iterations | 3139 | +| time_elapsed | 10354 | +| total_timesteps | 3214336 | +| train/ | | +| approx_kl | 3.002295 | +| clip_fraction | 0.435 | +| clip_range | 0.2 | +| entropy_loss | -0.243 | +| explained_variance | -1.95 | +| learning_rate | 0.0001 | +| loss | -0.0907 | +| n_updates | 91910 | +| policy_gradient_loss | -0.0551 | +| value_loss | 0.000543 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.14 | +| time/ | | +| fps | 310 | +| iterations | 3140 | +| time_elapsed | 10357 | +| total_timesteps | 3215360 | +| train/ | | +| approx_kl | 2.7851872 | +| clip_fraction | 0.439 | +| clip_range | 0.2 | +| entropy_loss | -0.268 | +| explained_variance | -0.991 | +| learning_rate | 0.0001 | +| loss | -0.0967 | +| n_updates | 91920 | +| policy_gradient_loss | -0.0594 | +| value_loss | 0.000661 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.137 | +| time/ | | +| fps | 310 | +| iterations | 3141 | +| time_elapsed | 10360 | +| total_timesteps | 3216384 | +| train/ | | +| approx_kl | 2.4494376 | +| clip_fraction | 0.408 | +| clip_range | 0.2 | +| entropy_loss | -0.231 | +| explained_variance | -3.79 | +| learning_rate | 0.0001 | +| loss | -0.0574 | +| n_updates | 91930 | +| policy_gradient_loss | -0.0542 | +| value_loss | 0.000639 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.137 | +| time/ | | +| fps | 310 | +| iterations | 3142 | +| time_elapsed | 10363 | +| total_timesteps | 3217408 | +| train/ | | +| approx_kl | 4.353686 | +| clip_fraction | 0.405 | +| clip_range | 0.2 | +| entropy_loss | -0.264 | +| explained_variance | -0.57 | +| learning_rate | 0.0001 | +| loss | -0.112 | +| n_updates | 91940 | +| policy_gradient_loss | -0.0406 | +| value_loss | 0.000688 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.137 | +| time/ | | +| fps | 310 | +| iterations | 3143 | +| time_elapsed | 10367 | +| total_timesteps | 3218432 | +| train/ | | +| approx_kl | 2.7105994 | +| clip_fraction | 0.433 | +| clip_range | 0.2 | +| entropy_loss | -0.242 | +| explained_variance | -1.21 | +| learning_rate | 0.0001 | +| loss | -0.0717 | +| n_updates | 91950 | +| policy_gradient_loss | -0.0529 | +| value_loss | 0.000438 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.137 | +| time/ | | +| fps | 310 | +| iterations | 3144 | +| time_elapsed | 10370 | +| total_timesteps | 3219456 | +| train/ | | +| approx_kl | 8.499312 | +| clip_fraction | 0.433 | +| clip_range | 0.2 | +| entropy_loss | -0.245 | +| explained_variance | -1.76 | +| learning_rate | 0.0001 | +| loss | -0.0731 | +| n_updates | 91960 | +| policy_gradient_loss | -0.0563 | +| value_loss | 0.000612 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.141 | +| time/ | | +| fps | 310 | +| iterations | 3145 | +| time_elapsed | 10374 | +| total_timesteps | 3220480 | +| train/ | | +| approx_kl | 3.756291 | +| clip_fraction | 0.428 | +| clip_range | 0.2 | +| entropy_loss | -0.244 | +| explained_variance | -1.93 | +| learning_rate | 0.0001 | +| loss | -0.0723 | +| n_updates | 91970 | +| policy_gradient_loss | -0.0466 | +| value_loss | 0.000576 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.136 | +| time/ | | +| fps | 310 | +| iterations | 3146 | +| time_elapsed | 10377 | +| total_timesteps | 3221504 | +| train/ | | +| approx_kl | 3.2541776 | +| clip_fraction | 0.422 | +| clip_range | 0.2 | +| entropy_loss | -0.232 | +| explained_variance | -0.905 | +| learning_rate | 0.0001 | +| loss | -0.0958 | +| n_updates | 91980 | +| policy_gradient_loss | -0.0526 | +| value_loss | 0.000781 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.136 | +| time/ | | +| fps | 310 | +| iterations | 3147 | +| time_elapsed | 10380 | +| total_timesteps | 3222528 | +| train/ | | +| approx_kl | 2.6986296 | +| clip_fraction | 0.415 | +| clip_range | 0.2 | +| entropy_loss | -0.247 | +| explained_variance | -2.76 | +| learning_rate | 0.0001 | +| loss | -0.0914 | +| n_updates | 91990 | +| policy_gradient_loss | -0.0568 | +| value_loss | 0.000592 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.136 | +| time/ | | +| fps | 310 | +| iterations | 3148 | +| time_elapsed | 10384 | +| total_timesteps | 3223552 | +| train/ | | +| approx_kl | 2.8448431 | +| clip_fraction | 0.397 | +| clip_range | 0.2 | +| entropy_loss | -0.2 | +| explained_variance | -2.55 | +| learning_rate | 0.0001 | +| loss | -0.0763 | +| n_updates | 92000 | +| policy_gradient_loss | -0.0513 | +| value_loss | 0.000791 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.134 | +| time/ | | +| fps | 310 | +| iterations | 3149 | +| time_elapsed | 10387 | +| total_timesteps | 3224576 | +| train/ | | +| approx_kl | 6.540847 | +| clip_fraction | 0.42 | +| clip_range | 0.2 | +| entropy_loss | -0.217 | +| explained_variance | -2.23 | +| learning_rate | 0.0001 | +| loss | -0.0793 | +| n_updates | 92010 | +| policy_gradient_loss | -0.0466 | +| value_loss | 0.000643 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.131 | +| time/ | | +| fps | 310 | +| iterations | 3150 | +| time_elapsed | 10390 | +| total_timesteps | 3225600 | +| train/ | | +| approx_kl | 2.3549743 | +| clip_fraction | 0.411 | +| clip_range | 0.2 | +| entropy_loss | -0.26 | +| explained_variance | -1.73 | +| learning_rate | 0.0001 | +| loss | -0.0885 | +| n_updates | 92020 | +| policy_gradient_loss | -0.0541 | +| value_loss | 0.000575 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.82e+03 | +| ep_rew_mean | 0.129 | +| time/ | | +| fps | 310 | +| iterations | 3151 | +| time_elapsed | 10394 | +| total_timesteps | 3226624 | +| train/ | | +| approx_kl | 2.5127811 | +| clip_fraction | 0.421 | +| clip_range | 0.2 | +| entropy_loss | -0.259 | +| explained_variance | -1.49 | +| learning_rate | 0.0001 | +| loss | -0.0742 | +| n_updates | 92030 | +| policy_gradient_loss | -0.0553 | +| value_loss | 0.000729 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.81e+03 | +| ep_rew_mean | 0.127 | +| time/ | | +| fps | 310 | +| iterations | 3152 | +| time_elapsed | 10397 | +| total_timesteps | 3227648 | +| train/ | | +| approx_kl | 2.7104936 | +| clip_fraction | 0.424 | +| clip_range | 0.2 | +| entropy_loss | -0.24 | +| explained_variance | -2.44 | +| learning_rate | 0.0001 | +| loss | -0.0883 | +| n_updates | 92040 | +| policy_gradient_loss | -0.0601 | +| value_loss | 0.000878 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.81e+03 | +| ep_rew_mean | 0.127 | +| time/ | | +| fps | 310 | +| iterations | 3153 | +| time_elapsed | 10400 | +| total_timesteps | 3228672 | +| train/ | | +| approx_kl | 4.0437346 | +| clip_fraction | 0.437 | +| clip_range | 0.2 | +| entropy_loss | -0.235 | +| explained_variance | -1.68 | +| learning_rate | 0.0001 | +| loss | -0.091 | +| n_updates | 92050 | +| policy_gradient_loss | -0.062 | +| value_loss | 0.000702 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.81e+03 | +| ep_rew_mean | 0.131 | +| time/ | | +| fps | 310 | +| iterations | 3154 | +| time_elapsed | 10403 | +| total_timesteps | 3229696 | +| train/ | | +| approx_kl | 2.9982276 | +| clip_fraction | 0.423 | +| clip_range | 0.2 | +| entropy_loss | -0.24 | +| explained_variance | -1.81 | +| learning_rate | 0.0001 | +| loss | -0.0896 | +| n_updates | 92060 | +| policy_gradient_loss | -0.053 | +| value_loss | 0.000633 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.81e+03 | +| ep_rew_mean | 0.136 | +| time/ | | +| fps | 310 | +| iterations | 3155 | +| time_elapsed | 10406 | +| total_timesteps | 3230720 | +| train/ | | +| approx_kl | 3.1690903 | +| clip_fraction | 0.436 | +| clip_range | 0.2 | +| entropy_loss | -0.227 | +| explained_variance | -1.18 | +| learning_rate | 0.0001 | +| loss | -0.0806 | +| n_updates | 92070 | +| policy_gradient_loss | -0.0477 | +| value_loss | 0.000791 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.81e+03 | +| ep_rew_mean | 0.136 | +| time/ | | +| fps | 310 | +| iterations | 3156 | +| time_elapsed | 10410 | +| total_timesteps | 3231744 | +| train/ | | +| approx_kl | 2.431994 | +| clip_fraction | 0.401 | +| clip_range | 0.2 | +| entropy_loss | -0.232 | +| explained_variance | -1.73 | +| learning_rate | 0.0001 | +| loss | -0.0651 | +| n_updates | 92080 | +| policy_gradient_loss | -0.0476 | +| value_loss | 0.000701 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.81e+03 | +| ep_rew_mean | 0.136 | +| time/ | | +| fps | 310 | +| iterations | 3157 | +| time_elapsed | 10413 | +| total_timesteps | 3232768 | +| train/ | | +| approx_kl | 2.983467 | +| clip_fraction | 0.413 | +| clip_range | 0.2 | +| entropy_loss | -0.226 | +| explained_variance | -1.17 | +| learning_rate | 0.0001 | +| loss | -0.0662 | +| n_updates | 92090 | +| policy_gradient_loss | -0.0542 | +| value_loss | 0.000747 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.136 | +| time/ | | +| fps | 310 | +| iterations | 3158 | +| time_elapsed | 10416 | +| total_timesteps | 3233792 | +| train/ | | +| approx_kl | 3.2958145 | +| clip_fraction | 0.422 | +| clip_range | 0.2 | +| entropy_loss | -0.24 | +| explained_variance | -1.22 | +| learning_rate | 0.0001 | +| loss | -0.066 | +| n_updates | 92100 | +| policy_gradient_loss | -0.0575 | +| value_loss | 0.000739 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.78e+03 | +| ep_rew_mean | 0.137 | +| time/ | | +| fps | 310 | +| iterations | 3159 | +| time_elapsed | 10419 | +| total_timesteps | 3234816 | +| train/ | | +| approx_kl | 3.0933952 | +| clip_fraction | 0.405 | +| clip_range | 0.2 | +| entropy_loss | -0.237 | +| explained_variance | -1.44 | +| learning_rate | 0.0001 | +| loss | -0.077 | +| n_updates | 92110 | +| policy_gradient_loss | -0.0481 | +| value_loss | 0.000685 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.78e+03 | +| ep_rew_mean | 0.137 | +| time/ | | +| fps | 310 | +| iterations | 3160 | +| time_elapsed | 10423 | +| total_timesteps | 3235840 | +| train/ | | +| approx_kl | 2.7127104 | +| clip_fraction | 0.421 | +| clip_range | 0.2 | +| entropy_loss | -0.259 | +| explained_variance | -0.829 | +| learning_rate | 0.0001 | +| loss | -0.0742 | +| n_updates | 92120 | +| policy_gradient_loss | -0.0556 | +| value_loss | 0.00066 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.78e+03 | +| ep_rew_mean | 0.15 | +| time/ | | +| fps | 310 | +| iterations | 3161 | +| time_elapsed | 10426 | +| total_timesteps | 3236864 | +| train/ | | +| approx_kl | 2.7987971 | +| clip_fraction | 0.403 | +| clip_range | 0.2 | +| entropy_loss | -0.233 | +| explained_variance | -2.01 | +| learning_rate | 0.0001 | +| loss | -0.0896 | +| n_updates | 92130 | +| policy_gradient_loss | -0.0557 | +| value_loss | 0.000643 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.78e+03 | +| ep_rew_mean | 0.15 | +| time/ | | +| fps | 310 | +| iterations | 3162 | +| time_elapsed | 10430 | +| total_timesteps | 3237888 | +| train/ | | +| approx_kl | 2.7471113 | +| clip_fraction | 0.456 | +| clip_range | 0.2 | +| entropy_loss | -0.278 | +| explained_variance | -0.842 | +| learning_rate | 0.0001 | +| loss | -0.078 | +| n_updates | 92140 | +| policy_gradient_loss | -0.0538 | +| value_loss | 0.00103 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.152 | +| time/ | | +| fps | 310 | +| iterations | 3163 | +| time_elapsed | 10433 | +| total_timesteps | 3238912 | +| train/ | | +| approx_kl | 2.259525 | +| clip_fraction | 0.4 | +| clip_range | 0.2 | +| entropy_loss | -0.228 | +| explained_variance | -2.65 | +| learning_rate | 0.0001 | +| loss | -0.0895 | +| n_updates | 92150 | +| policy_gradient_loss | -0.0566 | +| value_loss | 0.00114 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.78e+03 | +| ep_rew_mean | 0.153 | +| time/ | | +| fps | 310 | +| iterations | 3164 | +| time_elapsed | 10437 | +| total_timesteps | 3239936 | +| train/ | | +| approx_kl | 2.9210868 | +| clip_fraction | 0.419 | +| clip_range | 0.2 | +| entropy_loss | -0.243 | +| explained_variance | -1.26 | +| learning_rate | 0.0001 | +| loss | -0.0867 | +| n_updates | 92160 | +| policy_gradient_loss | -0.0558 | +| value_loss | 0.000874 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.78e+03 | +| ep_rew_mean | 0.153 | +| time/ | | +| fps | 310 | +| iterations | 3165 | +| time_elapsed | 10440 | +| total_timesteps | 3240960 | +| train/ | | +| approx_kl | 1.98668 | +| clip_fraction | 0.396 | +| clip_range | 0.2 | +| entropy_loss | -0.24 | +| explained_variance | -3.09 | +| learning_rate | 0.0001 | +| loss | -0.0818 | +| n_updates | 92170 | +| policy_gradient_loss | -0.0529 | +| value_loss | 0.000521 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.156 | +| time/ | | +| fps | 310 | +| iterations | 3166 | +| time_elapsed | 10444 | +| total_timesteps | 3241984 | +| train/ | | +| approx_kl | 2.898003 | +| clip_fraction | 0.411 | +| clip_range | 0.2 | +| entropy_loss | -0.221 | +| explained_variance | -1.2 | +| learning_rate | 0.0001 | +| loss | -0.0764 | +| n_updates | 92180 | +| policy_gradient_loss | -0.0516 | +| value_loss | 0.000753 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.157 | +| time/ | | +| fps | 310 | +| iterations | 3167 | +| time_elapsed | 10447 | +| total_timesteps | 3243008 | +| train/ | | +| approx_kl | 3.196695 | +| clip_fraction | 0.38 | +| clip_range | 0.2 | +| entropy_loss | -0.2 | +| explained_variance | -0.993 | +| learning_rate | 0.0001 | +| loss | -0.059 | +| n_updates | 92190 | +| policy_gradient_loss | -0.0504 | +| value_loss | 0.000856 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.157 | +| time/ | | +| fps | 310 | +| iterations | 3168 | +| time_elapsed | 10450 | +| total_timesteps | 3244032 | +| train/ | | +| approx_kl | 2.3391166 | +| clip_fraction | 0.388 | +| clip_range | 0.2 | +| entropy_loss | -0.213 | +| explained_variance | -2.28 | +| learning_rate | 0.0001 | +| loss | -0.0783 | +| n_updates | 92200 | +| policy_gradient_loss | -0.0489 | +| value_loss | 0.000537 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.159 | +| time/ | | +| fps | 310 | +| iterations | 3169 | +| time_elapsed | 10454 | +| total_timesteps | 3245056 | +| train/ | | +| approx_kl | 1.931227 | +| clip_fraction | 0.41 | +| clip_range | 0.2 | +| entropy_loss | -0.252 | +| explained_variance | -0.952 | +| learning_rate | 0.0001 | +| loss | -0.0652 | +| n_updates | 92210 | +| policy_gradient_loss | -0.0422 | +| value_loss | 0.000593 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.157 | +| time/ | | +| fps | 310 | +| iterations | 3170 | +| time_elapsed | 10457 | +| total_timesteps | 3246080 | +| train/ | | +| approx_kl | 2.4126842 | +| clip_fraction | 0.401 | +| clip_range | 0.2 | +| entropy_loss | -0.211 | +| explained_variance | -2.18 | +| learning_rate | 0.0001 | +| loss | -0.0797 | +| n_updates | 92220 | +| policy_gradient_loss | -0.0449 | +| value_loss | 0.000614 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.153 | +| time/ | | +| fps | 310 | +| iterations | 3171 | +| time_elapsed | 10460 | +| total_timesteps | 3247104 | +| train/ | | +| approx_kl | 2.721093 | +| clip_fraction | 0.383 | +| clip_range | 0.2 | +| entropy_loss | -0.197 | +| explained_variance | -1.09 | +| learning_rate | 0.0001 | +| loss | -0.0615 | +| n_updates | 92230 | +| policy_gradient_loss | -0.0515 | +| value_loss | 0.000704 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.153 | +| time/ | | +| fps | 310 | +| iterations | 3172 | +| time_elapsed | 10463 | +| total_timesteps | 3248128 | +| train/ | | +| approx_kl | 2.5876408 | +| clip_fraction | 0.367 | +| clip_range | 0.2 | +| entropy_loss | -0.2 | +| explained_variance | -1.74 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 92240 | +| policy_gradient_loss | -0.0558 | +| value_loss | 0.000861 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.155 | +| time/ | | +| fps | 310 | +| iterations | 3173 | +| time_elapsed | 10467 | +| total_timesteps | 3249152 | +| train/ | | +| approx_kl | 2.615743 | +| clip_fraction | 0.442 | +| clip_range | 0.2 | +| entropy_loss | -0.296 | +| explained_variance | -0.96 | +| learning_rate | 0.0001 | +| loss | -0.1 | +| n_updates | 92250 | +| policy_gradient_loss | -0.058 | +| value_loss | 0.00069 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.154 | +| time/ | | +| fps | 310 | +| iterations | 3174 | +| time_elapsed | 10470 | +| total_timesteps | 3250176 | +| train/ | | +| approx_kl | 3.6456456 | +| clip_fraction | 0.401 | +| clip_range | 0.2 | +| entropy_loss | -0.207 | +| explained_variance | -2.07 | +| learning_rate | 0.0001 | +| loss | -0.0852 | +| n_updates | 92260 | +| policy_gradient_loss | -0.0541 | +| value_loss | 0.000686 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.149 | +| time/ | | +| fps | 310 | +| iterations | 3175 | +| time_elapsed | 10473 | +| total_timesteps | 3251200 | +| train/ | | +| approx_kl | 8.746782 | +| clip_fraction | 0.385 | +| clip_range | 0.2 | +| entropy_loss | -0.218 | +| explained_variance | -2.5 | +| learning_rate | 0.0001 | +| loss | -0.0643 | +| n_updates | 92270 | +| policy_gradient_loss | -0.0239 | +| value_loss | 0.000672 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.149 | +| time/ | | +| fps | 310 | +| iterations | 3176 | +| time_elapsed | 10476 | +| total_timesteps | 3252224 | +| train/ | | +| approx_kl | 8.990642 | +| clip_fraction | 0.365 | +| clip_range | 0.2 | +| entropy_loss | -0.208 | +| explained_variance | -1.65 | +| learning_rate | 0.0001 | +| loss | -0.0943 | +| n_updates | 92280 | +| policy_gradient_loss | -0.0497 | +| value_loss | 0.000624 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.155 | +| time/ | | +| fps | 310 | +| iterations | 3177 | +| time_elapsed | 10479 | +| total_timesteps | 3253248 | +| train/ | | +| approx_kl | 2.2938044 | +| clip_fraction | 0.386 | +| clip_range | 0.2 | +| entropy_loss | -0.208 | +| explained_variance | -2.4 | +| learning_rate | 0.0001 | +| loss | -0.0972 | +| n_updates | 92290 | +| policy_gradient_loss | -0.045 | +| value_loss | 0.000572 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.152 | +| time/ | | +| fps | 310 | +| iterations | 3178 | +| time_elapsed | 10483 | +| total_timesteps | 3254272 | +| train/ | | +| approx_kl | 3.2154996 | +| clip_fraction | 0.442 | +| clip_range | 0.2 | +| entropy_loss | -0.23 | +| explained_variance | -1.27 | +| learning_rate | 0.0001 | +| loss | -0.0929 | +| n_updates | 92300 | +| policy_gradient_loss | -0.053 | +| value_loss | 0.000738 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.154 | +| time/ | | +| fps | 310 | +| iterations | 3179 | +| time_elapsed | 10486 | +| total_timesteps | 3255296 | +| train/ | | +| approx_kl | 2.2609506 | +| clip_fraction | 0.36 | +| clip_range | 0.2 | +| entropy_loss | -0.217 | +| explained_variance | -2.23 | +| learning_rate | 0.0001 | +| loss | -0.0678 | +| n_updates | 92310 | +| policy_gradient_loss | -0.0467 | +| value_loss | 0.000748 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.154 | +| time/ | | +| fps | 310 | +| iterations | 3180 | +| time_elapsed | 10490 | +| total_timesteps | 3256320 | +| train/ | | +| approx_kl | 1.6620158 | +| clip_fraction | 0.375 | +| clip_range | 0.2 | +| entropy_loss | -0.235 | +| explained_variance | -4.22 | +| learning_rate | 0.0001 | +| loss | -0.0841 | +| n_updates | 92320 | +| policy_gradient_loss | -0.0384 | +| value_loss | 0.00065 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.154 | +| time/ | | +| fps | 310 | +| iterations | 3181 | +| time_elapsed | 10493 | +| total_timesteps | 3257344 | +| train/ | | +| approx_kl | 2.2484212 | +| clip_fraction | 0.402 | +| clip_range | 0.2 | +| entropy_loss | -0.232 | +| explained_variance | -0.0894 | +| learning_rate | 0.0001 | +| loss | -0.076 | +| n_updates | 92330 | +| policy_gradient_loss | -0.0479 | +| value_loss | 0.000904 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.154 | +| time/ | | +| fps | 310 | +| iterations | 3182 | +| time_elapsed | 10497 | +| total_timesteps | 3258368 | +| train/ | | +| approx_kl | 2.1273584 | +| clip_fraction | 0.382 | +| clip_range | 0.2 | +| entropy_loss | -0.239 | +| explained_variance | -0.742 | +| learning_rate | 0.0001 | +| loss | -0.0367 | +| n_updates | 92340 | +| policy_gradient_loss | -0.0378 | +| value_loss | 0.00133 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.159 | +| time/ | | +| fps | 310 | +| iterations | 3183 | +| time_elapsed | 10500 | +| total_timesteps | 3259392 | +| train/ | | +| approx_kl | 3.1218295 | +| clip_fraction | 0.425 | +| clip_range | 0.2 | +| entropy_loss | -0.214 | +| explained_variance | -2.11 | +| learning_rate | 0.0001 | +| loss | -0.0862 | +| n_updates | 92350 | +| policy_gradient_loss | -0.0543 | +| value_loss | 0.000664 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.65e+03 | +| ep_rew_mean | 0.159 | +| time/ | | +| fps | 310 | +| iterations | 3184 | +| time_elapsed | 10504 | +| total_timesteps | 3260416 | +| train/ | | +| approx_kl | 2.5463123 | +| clip_fraction | 0.374 | +| clip_range | 0.2 | +| entropy_loss | -0.202 | +| explained_variance | -0.588 | +| learning_rate | 0.0001 | +| loss | -0.0455 | +| n_updates | 92360 | +| policy_gradient_loss | -0.051 | +| value_loss | 0.000961 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.65e+03 | +| ep_rew_mean | 0.159 | +| time/ | | +| fps | 310 | +| iterations | 3185 | +| time_elapsed | 10507 | +| total_timesteps | 3261440 | +| train/ | | +| approx_kl | 2.7612855 | +| clip_fraction | 0.418 | +| clip_range | 0.2 | +| entropy_loss | -0.239 | +| explained_variance | -2.06 | +| learning_rate | 0.0001 | +| loss | -0.0639 | +| n_updates | 92370 | +| policy_gradient_loss | -0.0504 | +| value_loss | 0.000538 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.65e+03 | +| ep_rew_mean | 0.159 | +| time/ | | +| fps | 310 | +| iterations | 3186 | +| time_elapsed | 10510 | +| total_timesteps | 3262464 | +| train/ | | +| approx_kl | 2.3096647 | +| clip_fraction | 0.431 | +| clip_range | 0.2 | +| entropy_loss | -0.268 | +| explained_variance | -1.45 | +| learning_rate | 0.0001 | +| loss | -0.0719 | +| n_updates | 92380 | +| policy_gradient_loss | -0.0427 | +| value_loss | 0.000604 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.64e+03 | +| ep_rew_mean | 0.162 | +| time/ | | +| fps | 310 | +| iterations | 3187 | +| time_elapsed | 10513 | +| total_timesteps | 3263488 | +| train/ | | +| approx_kl | 2.568768 | +| clip_fraction | 0.377 | +| clip_range | 0.2 | +| entropy_loss | -0.202 | +| explained_variance | -0.49 | +| learning_rate | 0.0001 | +| loss | -0.0744 | +| n_updates | 92390 | +| policy_gradient_loss | -0.0403 | +| value_loss | 0.000722 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.64e+03 | +| ep_rew_mean | 0.162 | +| time/ | | +| fps | 310 | +| iterations | 3188 | +| time_elapsed | 10517 | +| total_timesteps | 3264512 | +| train/ | | +| approx_kl | 2.61355 | +| clip_fraction | 0.428 | +| clip_range | 0.2 | +| entropy_loss | -0.233 | +| explained_variance | -0.625 | +| learning_rate | 0.0001 | +| loss | -0.0795 | +| n_updates | 92400 | +| policy_gradient_loss | -0.058 | +| value_loss | 0.00103 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.65e+03 | +| ep_rew_mean | 0.157 | +| time/ | | +| fps | 310 | +| iterations | 3189 | +| time_elapsed | 10520 | +| total_timesteps | 3265536 | +| train/ | | +| approx_kl | 2.9442 | +| clip_fraction | 0.42 | +| clip_range | 0.2 | +| entropy_loss | -0.225 | +| explained_variance | -2.91 | +| learning_rate | 0.0001 | +| loss | -0.06 | +| n_updates | 92410 | +| policy_gradient_loss | -0.0562 | +| value_loss | 0.000822 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.64e+03 | +| ep_rew_mean | 0.16 | +| time/ | | +| fps | 310 | +| iterations | 3190 | +| time_elapsed | 10523 | +| total_timesteps | 3266560 | +| train/ | | +| approx_kl | 3.7337458 | +| clip_fraction | 0.421 | +| clip_range | 0.2 | +| entropy_loss | -0.216 | +| explained_variance | -1.38 | +| learning_rate | 0.0001 | +| loss | -0.0808 | +| n_updates | 92420 | +| policy_gradient_loss | -0.0538 | +| value_loss | 0.000667 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.63e+03 | +| ep_rew_mean | 0.157 | +| time/ | | +| fps | 310 | +| iterations | 3191 | +| time_elapsed | 10526 | +| total_timesteps | 3267584 | +| train/ | | +| approx_kl | 2.5997162 | +| clip_fraction | 0.386 | +| clip_range | 0.2 | +| entropy_loss | -0.214 | +| explained_variance | -0.622 | +| learning_rate | 0.0001 | +| loss | -0.0644 | +| n_updates | 92430 | +| policy_gradient_loss | -0.0422 | +| value_loss | 0.00064 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.63e+03 | +| ep_rew_mean | 0.157 | +| time/ | | +| fps | 310 | +| iterations | 3192 | +| time_elapsed | 10529 | +| total_timesteps | 3268608 | +| train/ | | +| approx_kl | 2.5775871 | +| clip_fraction | 0.387 | +| clip_range | 0.2 | +| entropy_loss | -0.209 | +| explained_variance | -1.31 | +| learning_rate | 0.0001 | +| loss | -0.0848 | +| n_updates | 92440 | +| policy_gradient_loss | -0.0494 | +| value_loss | 0.000687 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.62e+03 | +| ep_rew_mean | 0.154 | +| time/ | | +| fps | 310 | +| iterations | 3193 | +| time_elapsed | 10533 | +| total_timesteps | 3269632 | +| train/ | | +| approx_kl | 2.7806013 | +| clip_fraction | 0.421 | +| clip_range | 0.2 | +| entropy_loss | -0.232 | +| explained_variance | -0.968 | +| learning_rate | 0.0001 | +| loss | -0.0988 | +| n_updates | 92450 | +| policy_gradient_loss | -0.0556 | +| value_loss | 0.000531 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.61e+03 | +| ep_rew_mean | 0.157 | +| time/ | | +| fps | 310 | +| iterations | 3194 | +| time_elapsed | 10536 | +| total_timesteps | 3270656 | +| train/ | | +| approx_kl | 1.9741826 | +| clip_fraction | 0.356 | +| clip_range | 0.2 | +| entropy_loss | -0.197 | +| explained_variance | -0.843 | +| learning_rate | 0.0001 | +| loss | -0.0573 | +| n_updates | 92460 | +| policy_gradient_loss | -0.0484 | +| value_loss | 0.000729 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | 0.163 | +| time/ | | +| fps | 310 | +| iterations | 3195 | +| time_elapsed | 10539 | +| total_timesteps | 3271680 | +| train/ | | +| approx_kl | 3.2104015 | +| clip_fraction | 0.403 | +| clip_range | 0.2 | +| entropy_loss | -0.185 | +| explained_variance | -1.29 | +| learning_rate | 0.0001 | +| loss | -0.0527 | +| n_updates | 92470 | +| policy_gradient_loss | -0.0378 | +| value_loss | 0.000769 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | 0.161 | +| time/ | | +| fps | 310 | +| iterations | 3196 | +| time_elapsed | 10542 | +| total_timesteps | 3272704 | +| train/ | | +| approx_kl | 2.7865467 | +| clip_fraction | 0.408 | +| clip_range | 0.2 | +| entropy_loss | -0.207 | +| explained_variance | -1.35 | +| learning_rate | 0.0001 | +| loss | -0.0893 | +| n_updates | 92480 | +| policy_gradient_loss | -0.0568 | +| value_loss | 0.000761 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | 0.161 | +| time/ | | +| fps | 310 | +| iterations | 3197 | +| time_elapsed | 10546 | +| total_timesteps | 3273728 | +| train/ | | +| approx_kl | 6.2231436 | +| clip_fraction | 0.398 | +| clip_range | 0.2 | +| entropy_loss | -0.204 | +| explained_variance | -2.35 | +| learning_rate | 0.0001 | +| loss | -0.105 | +| n_updates | 92490 | +| policy_gradient_loss | -0.0592 | +| value_loss | 0.000704 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | 0.163 | +| time/ | | +| fps | 310 | +| iterations | 3198 | +| time_elapsed | 10550 | +| total_timesteps | 3274752 | +| train/ | | +| approx_kl | 11.602729 | +| clip_fraction | 0.406 | +| clip_range | 0.2 | +| entropy_loss | -0.228 | +| explained_variance | -1.91 | +| learning_rate | 0.0001 | +| loss | -0.0739 | +| n_updates | 92500 | +| policy_gradient_loss | -0.0469 | +| value_loss | 0.000581 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.58e+03 | +| ep_rew_mean | 0.159 | +| time/ | | +| fps | 310 | +| iterations | 3199 | +| time_elapsed | 10553 | +| total_timesteps | 3275776 | +| train/ | | +| approx_kl | 2.981214 | +| clip_fraction | 0.395 | +| clip_range | 0.2 | +| entropy_loss | -0.211 | +| explained_variance | -2.61 | +| learning_rate | 0.0001 | +| loss | -0.0857 | +| n_updates | 92510 | +| policy_gradient_loss | -0.0553 | +| value_loss | 0.000373 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.58e+03 | +| ep_rew_mean | 0.166 | +| time/ | | +| fps | 310 | +| iterations | 3200 | +| time_elapsed | 10556 | +| total_timesteps | 3276800 | +| train/ | | +| approx_kl | 2.9168522 | +| clip_fraction | 0.418 | +| clip_range | 0.2 | +| entropy_loss | -0.232 | +| explained_variance | -0.945 | +| learning_rate | 0.0001 | +| loss | -0.0608 | +| n_updates | 92520 | +| policy_gradient_loss | -0.0549 | +| value_loss | 0.000517 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.58e+03 | +| ep_rew_mean | 0.166 | +| time/ | | +| fps | 310 | +| iterations | 3201 | +| time_elapsed | 10560 | +| total_timesteps | 3277824 | +| train/ | | +| approx_kl | 2.6650405 | +| clip_fraction | 0.398 | +| clip_range | 0.2 | +| entropy_loss | -0.248 | +| explained_variance | -1.12 | +| learning_rate | 0.0001 | +| loss | -0.0594 | +| n_updates | 92530 | +| policy_gradient_loss | -0.0488 | +| value_loss | 0.000533 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.58e+03 | +| ep_rew_mean | 0.167 | +| time/ | | +| fps | 310 | +| iterations | 3202 | +| time_elapsed | 10563 | +| total_timesteps | 3278848 | +| train/ | | +| approx_kl | 2.983222 | +| clip_fraction | 0.407 | +| clip_range | 0.2 | +| entropy_loss | -0.207 | +| explained_variance | -2.29 | +| learning_rate | 0.0001 | +| loss | -0.0733 | +| n_updates | 92540 | +| policy_gradient_loss | -0.0559 | +| value_loss | 0.000569 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.57e+03 | +| ep_rew_mean | 0.163 | +| time/ | | +| fps | 310 | +| iterations | 3203 | +| time_elapsed | 10567 | +| total_timesteps | 3279872 | +| train/ | | +| approx_kl | 2.3786862 | +| clip_fraction | 0.392 | +| clip_range | 0.2 | +| entropy_loss | -0.221 | +| explained_variance | -1.44 | +| learning_rate | 0.0001 | +| loss | -0.0815 | +| n_updates | 92550 | +| policy_gradient_loss | -0.0563 | +| value_loss | 0.000708 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.57e+03 | +| ep_rew_mean | 0.163 | +| time/ | | +| fps | 310 | +| iterations | 3204 | +| time_elapsed | 10570 | +| total_timesteps | 3280896 | +| train/ | | +| approx_kl | 1.9466889 | +| clip_fraction | 0.371 | +| clip_range | 0.2 | +| entropy_loss | -0.205 | +| explained_variance | -1.77 | +| learning_rate | 0.0001 | +| loss | -0.0851 | +| n_updates | 92560 | +| policy_gradient_loss | -0.0554 | +| value_loss | 0.000772 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.57e+03 | +| ep_rew_mean | 0.166 | +| time/ | | +| fps | 310 | +| iterations | 3205 | +| time_elapsed | 10573 | +| total_timesteps | 3281920 | +| train/ | | +| approx_kl | 2.7234635 | +| clip_fraction | 0.411 | +| clip_range | 0.2 | +| entropy_loss | -0.234 | +| explained_variance | -1.67 | +| learning_rate | 0.0001 | +| loss | -0.093 | +| n_updates | 92570 | +| policy_gradient_loss | -0.0447 | +| value_loss | 0.000654 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.57e+03 | +| ep_rew_mean | 0.166 | +| time/ | | +| fps | 310 | +| iterations | 3206 | +| time_elapsed | 10576 | +| total_timesteps | 3282944 | +| train/ | | +| approx_kl | 2.50197 | +| clip_fraction | 0.403 | +| clip_range | 0.2 | +| entropy_loss | -0.209 | +| explained_variance | -1.05 | +| learning_rate | 0.0001 | +| loss | -0.0877 | +| n_updates | 92580 | +| policy_gradient_loss | -0.0573 | +| value_loss | 0.000647 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.57e+03 | +| ep_rew_mean | 0.171 | +| time/ | | +| fps | 310 | +| iterations | 3207 | +| time_elapsed | 10580 | +| total_timesteps | 3283968 | +| train/ | | +| approx_kl | 2.665752 | +| clip_fraction | 0.43 | +| clip_range | 0.2 | +| entropy_loss | -0.23 | +| explained_variance | -1.02 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 92590 | +| policy_gradient_loss | -0.062 | +| value_loss | 0.000871 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.56e+03 | +| ep_rew_mean | 0.163 | +| time/ | | +| fps | 310 | +| iterations | 3208 | +| time_elapsed | 10583 | +| total_timesteps | 3284992 | +| train/ | | +| approx_kl | 2.253813 | +| clip_fraction | 0.385 | +| clip_range | 0.2 | +| entropy_loss | -0.225 | +| explained_variance | -1.02 | +| learning_rate | 0.0001 | +| loss | -0.0805 | +| n_updates | 92600 | +| policy_gradient_loss | -0.0525 | +| value_loss | 0.000532 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.56e+03 | +| ep_rew_mean | 0.163 | +| time/ | | +| fps | 310 | +| iterations | 3209 | +| time_elapsed | 10586 | +| total_timesteps | 3286016 | +| train/ | | +| approx_kl | 2.5904903 | +| clip_fraction | 0.389 | +| clip_range | 0.2 | +| entropy_loss | -0.213 | +| explained_variance | -0.942 | +| learning_rate | 0.0001 | +| loss | -0.0772 | +| n_updates | 92610 | +| policy_gradient_loss | -0.0528 | +| value_loss | 0.00077 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.56e+03 | +| ep_rew_mean | 0.165 | +| time/ | | +| fps | 310 | +| iterations | 3210 | +| time_elapsed | 10589 | +| total_timesteps | 3287040 | +| train/ | | +| approx_kl | 3.1111362 | +| clip_fraction | 0.436 | +| clip_range | 0.2 | +| entropy_loss | -0.234 | +| explained_variance | -2.56 | +| learning_rate | 0.0001 | +| loss | -0.0739 | +| n_updates | 92620 | +| policy_gradient_loss | -0.0589 | +| value_loss | 0.000539 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.56e+03 | +| ep_rew_mean | 0.165 | +| time/ | | +| fps | 310 | +| iterations | 3211 | +| time_elapsed | 10593 | +| total_timesteps | 3288064 | +| train/ | | +| approx_kl | 3.3029995 | +| clip_fraction | 0.414 | +| clip_range | 0.2 | +| entropy_loss | -0.218 | +| explained_variance | -1.41 | +| learning_rate | 0.0001 | +| loss | -0.0621 | +| n_updates | 92630 | +| policy_gradient_loss | -0.0576 | +| value_loss | 0.000769 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.56e+03 | +| ep_rew_mean | 0.168 | +| time/ | | +| fps | 310 | +| iterations | 3212 | +| time_elapsed | 10596 | +| total_timesteps | 3289088 | +| train/ | | +| approx_kl | 2.8215775 | +| clip_fraction | 0.407 | +| clip_range | 0.2 | +| entropy_loss | -0.239 | +| explained_variance | -2.32 | +| learning_rate | 0.0001 | +| loss | -0.0771 | +| n_updates | 92640 | +| policy_gradient_loss | -0.0536 | +| value_loss | 0.000662 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.57e+03 | +| ep_rew_mean | 0.176 | +| time/ | | +| fps | 310 | +| iterations | 3213 | +| time_elapsed | 10599 | +| total_timesteps | 3290112 | +| train/ | | +| approx_kl | 2.8412666 | +| clip_fraction | 0.411 | +| clip_range | 0.2 | +| entropy_loss | -0.245 | +| explained_variance | -0.973 | +| learning_rate | 0.0001 | +| loss | -0.0744 | +| n_updates | 92650 | +| policy_gradient_loss | -0.0568 | +| value_loss | 0.00076 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.55e+03 | +| ep_rew_mean | 0.175 | +| time/ | | +| fps | 310 | +| iterations | 3214 | +| time_elapsed | 10602 | +| total_timesteps | 3291136 | +| train/ | | +| approx_kl | 3.070578 | +| clip_fraction | 0.399 | +| clip_range | 0.2 | +| entropy_loss | -0.206 | +| explained_variance | -3.12 | +| learning_rate | 0.0001 | +| loss | -0.0736 | +| n_updates | 92660 | +| policy_gradient_loss | -0.0542 | +| value_loss | 0.000821 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.54e+03 | +| ep_rew_mean | 0.181 | +| time/ | | +| fps | 310 | +| iterations | 3215 | +| time_elapsed | 10606 | +| total_timesteps | 3292160 | +| train/ | | +| approx_kl | 2.3813257 | +| clip_fraction | 0.398 | +| clip_range | 0.2 | +| entropy_loss | -0.217 | +| explained_variance | -3.26 | +| learning_rate | 0.0001 | +| loss | -0.0686 | +| n_updates | 92670 | +| policy_gradient_loss | -0.0561 | +| value_loss | 0.000526 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.53e+03 | +| ep_rew_mean | 0.183 | +| time/ | | +| fps | 310 | +| iterations | 3216 | +| time_elapsed | 10609 | +| total_timesteps | 3293184 | +| train/ | | +| approx_kl | 2.631056 | +| clip_fraction | 0.428 | +| clip_range | 0.2 | +| entropy_loss | -0.229 | +| explained_variance | -0.454 | +| learning_rate | 0.0001 | +| loss | -0.113 | +| n_updates | 92680 | +| policy_gradient_loss | -0.0606 | +| value_loss | 0.000804 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.53e+03 | +| ep_rew_mean | 0.189 | +| time/ | | +| fps | 310 | +| iterations | 3217 | +| time_elapsed | 10612 | +| total_timesteps | 3294208 | +| train/ | | +| approx_kl | 2.6131406 | +| clip_fraction | 0.411 | +| clip_range | 0.2 | +| entropy_loss | -0.229 | +| explained_variance | -3.05 | +| learning_rate | 0.0001 | +| loss | -0.0768 | +| n_updates | 92690 | +| policy_gradient_loss | -0.0498 | +| value_loss | 0.000545 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.53e+03 | +| ep_rew_mean | 0.19 | +| time/ | | +| fps | 310 | +| iterations | 3218 | +| time_elapsed | 10616 | +| total_timesteps | 3295232 | +| train/ | | +| approx_kl | 3.0936263 | +| clip_fraction | 0.427 | +| clip_range | 0.2 | +| entropy_loss | -0.249 | +| explained_variance | -0.496 | +| learning_rate | 0.0001 | +| loss | -0.092 | +| n_updates | 92700 | +| policy_gradient_loss | -0.0511 | +| value_loss | 0.000769 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.52e+03 | +| ep_rew_mean | 0.187 | +| time/ | | +| fps | 310 | +| iterations | 3219 | +| time_elapsed | 10619 | +| total_timesteps | 3296256 | +| train/ | | +| approx_kl | 2.0230172 | +| clip_fraction | 0.412 | +| clip_range | 0.2 | +| entropy_loss | -0.255 | +| explained_variance | -5.24 | +| learning_rate | 0.0001 | +| loss | -0.0726 | +| n_updates | 92710 | +| policy_gradient_loss | -0.058 | +| value_loss | 0.000529 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.52e+03 | +| ep_rew_mean | 0.187 | +| time/ | | +| fps | 310 | +| iterations | 3220 | +| time_elapsed | 10623 | +| total_timesteps | 3297280 | +| train/ | | +| approx_kl | 1.7520854 | +| clip_fraction | 0.371 | +| clip_range | 0.2 | +| entropy_loss | -0.238 | +| explained_variance | -1.37 | +| learning_rate | 0.0001 | +| loss | -0.0529 | +| n_updates | 92720 | +| policy_gradient_loss | -0.0479 | +| value_loss | 0.000376 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.52e+03 | +| ep_rew_mean | 0.185 | +| time/ | | +| fps | 310 | +| iterations | 3221 | +| time_elapsed | 10626 | +| total_timesteps | 3298304 | +| train/ | | +| approx_kl | 2.0928993 | +| clip_fraction | 0.441 | +| clip_range | 0.2 | +| entropy_loss | -0.29 | +| explained_variance | -0.692 | +| learning_rate | 0.0001 | +| loss | -0.0818 | +| n_updates | 92730 | +| policy_gradient_loss | -0.053 | +| value_loss | 0.000623 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.52e+03 | +| ep_rew_mean | 0.185 | +| time/ | | +| fps | 310 | +| iterations | 3222 | +| time_elapsed | 10629 | +| total_timesteps | 3299328 | +| train/ | | +| approx_kl | 2.5268388 | +| clip_fraction | 0.401 | +| clip_range | 0.2 | +| entropy_loss | -0.231 | +| explained_variance | -1.41 | +| learning_rate | 0.0001 | +| loss | -0.0902 | +| n_updates | 92740 | +| policy_gradient_loss | -0.0565 | +| value_loss | 0.000568 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.52e+03 | +| ep_rew_mean | 0.188 | +| time/ | | +| fps | 310 | +| iterations | 3223 | +| time_elapsed | 10633 | +| total_timesteps | 3300352 | +| train/ | | +| approx_kl | 2.7279768 | +| clip_fraction | 0.424 | +| clip_range | 0.2 | +| entropy_loss | -0.241 | +| explained_variance | -4.31 | +| learning_rate | 0.0001 | +| loss | -0.0839 | +| n_updates | 92750 | +| policy_gradient_loss | -0.0594 | +| value_loss | 0.000509 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.52e+03 | +| ep_rew_mean | 0.192 | +| time/ | | +| fps | 310 | +| iterations | 3224 | +| time_elapsed | 10636 | +| total_timesteps | 3301376 | +| train/ | | +| approx_kl | 2.9086237 | +| clip_fraction | 0.411 | +| clip_range | 0.2 | +| entropy_loss | -0.23 | +| explained_variance | -1.35 | +| learning_rate | 0.0001 | +| loss | -0.0728 | +| n_updates | 92760 | +| policy_gradient_loss | -0.0522 | +| value_loss | 0.00056 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.51e+03 | +| ep_rew_mean | 0.19 | +| time/ | | +| fps | 310 | +| iterations | 3225 | +| time_elapsed | 10639 | +| total_timesteps | 3302400 | +| train/ | | +| approx_kl | 3.0029545 | +| clip_fraction | 0.419 | +| clip_range | 0.2 | +| entropy_loss | -0.227 | +| explained_variance | -0.99 | +| learning_rate | 0.0001 | +| loss | -0.0861 | +| n_updates | 92770 | +| policy_gradient_loss | -0.0573 | +| value_loss | 0.000562 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.51e+03 | +| ep_rew_mean | 0.19 | +| time/ | | +| fps | 310 | +| iterations | 3226 | +| time_elapsed | 10642 | +| total_timesteps | 3303424 | +| train/ | | +| approx_kl | 2.1192358 | +| clip_fraction | 0.397 | +| clip_range | 0.2 | +| entropy_loss | -0.253 | +| explained_variance | -0.367 | +| learning_rate | 0.0001 | +| loss | -0.0842 | +| n_updates | 92780 | +| policy_gradient_loss | -0.0502 | +| value_loss | 0.000813 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.5e+03 | +| ep_rew_mean | 0.193 | +| time/ | | +| fps | 310 | +| iterations | 3227 | +| time_elapsed | 10645 | +| total_timesteps | 3304448 | +| train/ | | +| approx_kl | 2.6830196 | +| clip_fraction | 0.435 | +| clip_range | 0.2 | +| entropy_loss | -0.259 | +| explained_variance | -2.81 | +| learning_rate | 0.0001 | +| loss | -0.0835 | +| n_updates | 92790 | +| policy_gradient_loss | -0.0629 | +| value_loss | 0.000509 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.49e+03 | +| ep_rew_mean | 0.194 | +| time/ | | +| fps | 310 | +| iterations | 3228 | +| time_elapsed | 10648 | +| total_timesteps | 3305472 | +| train/ | | +| approx_kl | 3.2475533 | +| clip_fraction | 0.464 | +| clip_range | 0.2 | +| entropy_loss | -0.289 | +| explained_variance | -1.28 | +| learning_rate | 0.0001 | +| loss | -0.0834 | +| n_updates | 92800 | +| policy_gradient_loss | -0.0562 | +| value_loss | 0.000565 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.49e+03 | +| ep_rew_mean | 0.191 | +| time/ | | +| fps | 310 | +| iterations | 3229 | +| time_elapsed | 10652 | +| total_timesteps | 3306496 | +| train/ | | +| approx_kl | 2.0185673 | +| clip_fraction | 0.409 | +| clip_range | 0.2 | +| entropy_loss | -0.262 | +| explained_variance | -4.18 | +| learning_rate | 0.0001 | +| loss | -0.0665 | +| n_updates | 92810 | +| policy_gradient_loss | -0.0547 | +| value_loss | 0.000504 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.48e+03 | +| ep_rew_mean | 0.188 | +| time/ | | +| fps | 310 | +| iterations | 3230 | +| time_elapsed | 10655 | +| total_timesteps | 3307520 | +| train/ | | +| approx_kl | 6.363045 | +| clip_fraction | 0.398 | +| clip_range | 0.2 | +| entropy_loss | -0.239 | +| explained_variance | -0.783 | +| learning_rate | 0.0001 | +| loss | -0.0793 | +| n_updates | 92820 | +| policy_gradient_loss | -0.0527 | +| value_loss | 0.000615 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.47e+03 | +| ep_rew_mean | 0.189 | +| time/ | | +| fps | 310 | +| iterations | 3231 | +| time_elapsed | 10658 | +| total_timesteps | 3308544 | +| train/ | | +| approx_kl | 2.625003 | +| clip_fraction | 0.399 | +| clip_range | 0.2 | +| entropy_loss | -0.243 | +| explained_variance | -0.683 | +| learning_rate | 0.0001 | +| loss | -0.078 | +| n_updates | 92830 | +| policy_gradient_loss | -0.0504 | +| value_loss | 0.000595 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.45e+03 | +| ep_rew_mean | 0.192 | +| time/ | | +| fps | 310 | +| iterations | 3232 | +| time_elapsed | 10662 | +| total_timesteps | 3309568 | +| train/ | | +| approx_kl | 2.5837367 | +| clip_fraction | 0.453 | +| clip_range | 0.2 | +| entropy_loss | -0.308 | +| explained_variance | -0.954 | +| learning_rate | 0.0001 | +| loss | -0.078 | +| n_updates | 92840 | +| policy_gradient_loss | -0.0586 | +| value_loss | 0.000629 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.45e+03 | +| ep_rew_mean | 0.187 | +| time/ | | +| fps | 310 | +| iterations | 3233 | +| time_elapsed | 10665 | +| total_timesteps | 3310592 | +| train/ | | +| approx_kl | 2.4731784 | +| clip_fraction | 0.419 | +| clip_range | 0.2 | +| entropy_loss | -0.254 | +| explained_variance | -1.15 | +| learning_rate | 0.0001 | +| loss | -0.0485 | +| n_updates | 92850 | +| policy_gradient_loss | -0.0524 | +| value_loss | 0.000954 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.44e+03 | +| ep_rew_mean | 0.186 | +| time/ | | +| fps | 310 | +| iterations | 3234 | +| time_elapsed | 10669 | +| total_timesteps | 3311616 | +| train/ | | +| approx_kl | 3.2709837 | +| clip_fraction | 0.463 | +| clip_range | 0.2 | +| entropy_loss | -0.27 | +| explained_variance | -1.16 | +| learning_rate | 0.0001 | +| loss | -0.0812 | +| n_updates | 92860 | +| policy_gradient_loss | -0.066 | +| value_loss | 0.000985 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.43e+03 | +| ep_rew_mean | 0.185 | +| time/ | | +| fps | 310 | +| iterations | 3235 | +| time_elapsed | 10672 | +| total_timesteps | 3312640 | +| train/ | | +| approx_kl | 2.587595 | +| clip_fraction | 0.403 | +| clip_range | 0.2 | +| entropy_loss | -0.24 | +| explained_variance | -1.41 | +| learning_rate | 0.0001 | +| loss | -0.0773 | +| n_updates | 92870 | +| policy_gradient_loss | -0.0549 | +| value_loss | 0.000749 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.43e+03 | +| ep_rew_mean | 0.185 | +| time/ | | +| fps | 310 | +| iterations | 3236 | +| time_elapsed | 10676 | +| total_timesteps | 3313664 | +| train/ | | +| approx_kl | 2.6576118 | +| clip_fraction | 0.441 | +| clip_range | 0.2 | +| entropy_loss | -0.256 | +| explained_variance | -2.61 | +| learning_rate | 0.0001 | +| loss | -0.0926 | +| n_updates | 92880 | +| policy_gradient_loss | -0.0601 | +| value_loss | 0.00044 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.185 | +| time/ | | +| fps | 310 | +| iterations | 3237 | +| time_elapsed | 10679 | +| total_timesteps | 3314688 | +| train/ | | +| approx_kl | 2.7690718 | +| clip_fraction | 0.449 | +| clip_range | 0.2 | +| entropy_loss | -0.267 | +| explained_variance | -1.15 | +| learning_rate | 0.0001 | +| loss | -0.0802 | +| n_updates | 92890 | +| policy_gradient_loss | -0.0501 | +| value_loss | 0.000433 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.185 | +| time/ | | +| fps | 310 | +| iterations | 3238 | +| time_elapsed | 10683 | +| total_timesteps | 3315712 | +| train/ | | +| approx_kl | 2.815254 | +| clip_fraction | 0.399 | +| clip_range | 0.2 | +| entropy_loss | -0.238 | +| explained_variance | -0.372 | +| learning_rate | 0.0001 | +| loss | -0.0169 | +| n_updates | 92900 | +| policy_gradient_loss | -0.0357 | +| value_loss | 0.000576 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.185 | +| time/ | | +| fps | 310 | +| iterations | 3239 | +| time_elapsed | 10686 | +| total_timesteps | 3316736 | +| train/ | | +| approx_kl | 2.0876489 | +| clip_fraction | 0.403 | +| clip_range | 0.2 | +| entropy_loss | -0.261 | +| explained_variance | -1.53 | +| learning_rate | 0.0001 | +| loss | -0.0607 | +| n_updates | 92910 | +| policy_gradient_loss | -0.052 | +| value_loss | 0.000701 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.188 | +| time/ | | +| fps | 310 | +| iterations | 3240 | +| time_elapsed | 10690 | +| total_timesteps | 3317760 | +| train/ | | +| approx_kl | 2.439724 | +| clip_fraction | 0.443 | +| clip_range | 0.2 | +| entropy_loss | -0.308 | +| explained_variance | -1.74 | +| learning_rate | 0.0001 | +| loss | -0.079 | +| n_updates | 92920 | +| policy_gradient_loss | -0.0543 | +| value_loss | 0.000382 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.185 | +| time/ | | +| fps | 310 | +| iterations | 3241 | +| time_elapsed | 10693 | +| total_timesteps | 3318784 | +| train/ | | +| approx_kl | 2.793469 | +| clip_fraction | 0.42 | +| clip_range | 0.2 | +| entropy_loss | -0.267 | +| explained_variance | -2.18 | +| learning_rate | 0.0001 | +| loss | -0.0908 | +| n_updates | 92930 | +| policy_gradient_loss | -0.0518 | +| value_loss | 0.000462 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.186 | +| time/ | | +| fps | 310 | +| iterations | 3242 | +| time_elapsed | 10696 | +| total_timesteps | 3319808 | +| train/ | | +| approx_kl | 2.292839 | +| clip_fraction | 0.387 | +| clip_range | 0.2 | +| entropy_loss | -0.231 | +| explained_variance | -1.78 | +| learning_rate | 0.0001 | +| loss | -0.0701 | +| n_updates | 92940 | +| policy_gradient_loss | -0.0552 | +| value_loss | 0.000971 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.18 | +| time/ | | +| fps | 310 | +| iterations | 3243 | +| time_elapsed | 10699 | +| total_timesteps | 3320832 | +| train/ | | +| approx_kl | 2.7997484 | +| clip_fraction | 0.418 | +| clip_range | 0.2 | +| entropy_loss | -0.225 | +| explained_variance | -1.82 | +| learning_rate | 0.0001 | +| loss | -0.0869 | +| n_updates | 92950 | +| policy_gradient_loss | -0.0508 | +| value_loss | 0.00058 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.18 | +| time/ | | +| fps | 310 | +| iterations | 3244 | +| time_elapsed | 10702 | +| total_timesteps | 3321856 | +| train/ | | +| approx_kl | 2.4046032 | +| clip_fraction | 0.412 | +| clip_range | 0.2 | +| entropy_loss | -0.266 | +| explained_variance | -1.99 | +| learning_rate | 0.0001 | +| loss | -0.0854 | +| n_updates | 92960 | +| policy_gradient_loss | -0.0588 | +| value_loss | 0.000435 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.188 | +| time/ | | +| fps | 310 | +| iterations | 3245 | +| time_elapsed | 10706 | +| total_timesteps | 3322880 | +| train/ | | +| approx_kl | 2.5355077 | +| clip_fraction | 0.436 | +| clip_range | 0.2 | +| entropy_loss | -0.282 | +| explained_variance | -1.22 | +| learning_rate | 0.0001 | +| loss | -0.0731 | +| n_updates | 92970 | +| policy_gradient_loss | -0.0559 | +| value_loss | 0.000503 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.184 | +| time/ | | +| fps | 310 | +| iterations | 3246 | +| time_elapsed | 10709 | +| total_timesteps | 3323904 | +| train/ | | +| approx_kl | 2.1077538 | +| clip_fraction | 0.423 | +| clip_range | 0.2 | +| entropy_loss | -0.246 | +| explained_variance | -1.29 | +| learning_rate | 0.0001 | +| loss | -0.0938 | +| n_updates | 92980 | +| policy_gradient_loss | -0.0587 | +| value_loss | 0.00057 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.184 | +| time/ | | +| fps | 310 | +| iterations | 3247 | +| time_elapsed | 10712 | +| total_timesteps | 3324928 | +| train/ | | +| approx_kl | 2.4332457 | +| clip_fraction | 0.414 | +| clip_range | 0.2 | +| entropy_loss | -0.261 | +| explained_variance | -2.8 | +| learning_rate | 0.0001 | +| loss | -0.0765 | +| n_updates | 92990 | +| policy_gradient_loss | -0.059 | +| value_loss | 0.000494 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.188 | +| time/ | | +| fps | 310 | +| iterations | 3248 | +| time_elapsed | 10715 | +| total_timesteps | 3325952 | +| train/ | | +| approx_kl | 2.89535 | +| clip_fraction | 0.464 | +| clip_range | 0.2 | +| entropy_loss | -0.282 | +| explained_variance | -1.27 | +| learning_rate | 0.0001 | +| loss | -0.0588 | +| n_updates | 93000 | +| policy_gradient_loss | -0.06 | +| value_loss | 0.0006 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.188 | +| time/ | | +| fps | 310 | +| iterations | 3249 | +| time_elapsed | 10718 | +| total_timesteps | 3326976 | +| train/ | | +| approx_kl | 3.264278 | +| clip_fraction | 0.454 | +| clip_range | 0.2 | +| entropy_loss | -0.262 | +| explained_variance | -0.353 | +| learning_rate | 0.0001 | +| loss | -0.0619 | +| n_updates | 93010 | +| policy_gradient_loss | -0.0593 | +| value_loss | 0.000883 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.189 | +| time/ | | +| fps | 310 | +| iterations | 3250 | +| time_elapsed | 10722 | +| total_timesteps | 3328000 | +| train/ | | +| approx_kl | 2.6965246 | +| clip_fraction | 0.454 | +| clip_range | 0.2 | +| entropy_loss | -0.286 | +| explained_variance | -1.42 | +| learning_rate | 0.0001 | +| loss | -0.0946 | +| n_updates | 93020 | +| policy_gradient_loss | -0.0642 | +| value_loss | 0.000746 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.187 | +| time/ | | +| fps | 310 | +| iterations | 3251 | +| time_elapsed | 10725 | +| total_timesteps | 3329024 | +| train/ | | +| approx_kl | 2.1622095 | +| clip_fraction | 0.434 | +| clip_range | 0.2 | +| entropy_loss | -0.259 | +| explained_variance | -2.1 | +| learning_rate | 0.0001 | +| loss | -0.0992 | +| n_updates | 93030 | +| policy_gradient_loss | -0.0633 | +| value_loss | 0.000663 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.187 | +| time/ | | +| fps | 310 | +| iterations | 3252 | +| time_elapsed | 10729 | +| total_timesteps | 3330048 | +| train/ | | +| approx_kl | 1.8872237 | +| clip_fraction | 0.404 | +| clip_range | 0.2 | +| entropy_loss | -0.243 | +| explained_variance | -0.456 | +| learning_rate | 0.0001 | +| loss | -0.0888 | +| n_updates | 93040 | +| policy_gradient_loss | -0.0468 | +| value_loss | 0.00082 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.189 | +| time/ | | +| fps | 310 | +| iterations | 3253 | +| time_elapsed | 10732 | +| total_timesteps | 3331072 | +| train/ | | +| approx_kl | 2.953113 | +| clip_fraction | 0.442 | +| clip_range | 0.2 | +| entropy_loss | -0.275 | +| explained_variance | -2.39 | +| learning_rate | 0.0001 | +| loss | -0.0888 | +| n_updates | 93050 | +| policy_gradient_loss | -0.0616 | +| value_loss | 0.000567 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.189 | +| time/ | | +| fps | 310 | +| iterations | 3254 | +| time_elapsed | 10736 | +| total_timesteps | 3332096 | +| train/ | | +| approx_kl | 4.7717166 | +| clip_fraction | 0.456 | +| clip_range | 0.2 | +| entropy_loss | -0.267 | +| explained_variance | -1.57 | +| learning_rate | 0.0001 | +| loss | -0.0978 | +| n_updates | 93060 | +| policy_gradient_loss | -0.0594 | +| value_loss | 0.00061 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.189 | +| time/ | | +| fps | 310 | +| iterations | 3255 | +| time_elapsed | 10739 | +| total_timesteps | 3333120 | +| train/ | | +| approx_kl | 2.5855327 | +| clip_fraction | 0.442 | +| clip_range | 0.2 | +| entropy_loss | -0.267 | +| explained_variance | -3.55 | +| learning_rate | 0.0001 | +| loss | -0.0649 | +| n_updates | 93070 | +| policy_gradient_loss | -0.0654 | +| value_loss | 0.00056 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.194 | +| time/ | | +| fps | 310 | +| iterations | 3256 | +| time_elapsed | 10743 | +| total_timesteps | 3334144 | +| train/ | | +| approx_kl | 2.9173355 | +| clip_fraction | 0.439 | +| clip_range | 0.2 | +| entropy_loss | -0.28 | +| explained_variance | -0.885 | +| learning_rate | 0.0001 | +| loss | -0.0674 | +| n_updates | 93080 | +| policy_gradient_loss | -0.0602 | +| value_loss | 0.000707 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.196 | +| time/ | | +| fps | 310 | +| iterations | 3257 | +| time_elapsed | 10746 | +| total_timesteps | 3335168 | +| train/ | | +| approx_kl | 2.428668 | +| clip_fraction | 0.431 | +| clip_range | 0.2 | +| entropy_loss | -0.27 | +| explained_variance | -0.527 | +| learning_rate | 0.0001 | +| loss | -0.0704 | +| n_updates | 93090 | +| policy_gradient_loss | -0.0593 | +| value_loss | 0.00102 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.198 | +| time/ | | +| fps | 310 | +| iterations | 3258 | +| time_elapsed | 10750 | +| total_timesteps | 3336192 | +| train/ | | +| approx_kl | 2.2458282 | +| clip_fraction | 0.423 | +| clip_range | 0.2 | +| entropy_loss | -0.253 | +| explained_variance | -2.63 | +| learning_rate | 0.0001 | +| loss | -0.0963 | +| n_updates | 93100 | +| policy_gradient_loss | -0.0625 | +| value_loss | 0.000563 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.197 | +| time/ | | +| fps | 310 | +| iterations | 3259 | +| time_elapsed | 10753 | +| total_timesteps | 3337216 | +| train/ | | +| approx_kl | 6.0307612 | +| clip_fraction | 0.384 | +| clip_range | 0.2 | +| entropy_loss | -0.228 | +| explained_variance | -1.52 | +| learning_rate | 0.0001 | +| loss | -0.0652 | +| n_updates | 93110 | +| policy_gradient_loss | -0.0563 | +| value_loss | 0.000542 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.197 | +| time/ | | +| fps | 310 | +| iterations | 3260 | +| time_elapsed | 10756 | +| total_timesteps | 3338240 | +| train/ | | +| approx_kl | 2.5216846 | +| clip_fraction | 0.412 | +| clip_range | 0.2 | +| entropy_loss | -0.249 | +| explained_variance | -1.11 | +| learning_rate | 0.0001 | +| loss | -0.0958 | +| n_updates | 93120 | +| policy_gradient_loss | -0.0568 | +| value_loss | 0.000634 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.2 | +| time/ | | +| fps | 310 | +| iterations | 3261 | +| time_elapsed | 10759 | +| total_timesteps | 3339264 | +| train/ | | +| approx_kl | 2.578414 | +| clip_fraction | 0.414 | +| clip_range | 0.2 | +| entropy_loss | -0.253 | +| explained_variance | -1.73 | +| learning_rate | 0.0001 | +| loss | -0.0771 | +| n_updates | 93130 | +| policy_gradient_loss | -0.0573 | +| value_loss | 0.000538 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.208 | +| time/ | | +| fps | 310 | +| iterations | 3262 | +| time_elapsed | 10762 | +| total_timesteps | 3340288 | +| train/ | | +| approx_kl | 3.146092 | +| clip_fraction | 0.43 | +| clip_range | 0.2 | +| entropy_loss | -0.248 | +| explained_variance | -0.223 | +| learning_rate | 0.0001 | +| loss | -0.0697 | +| n_updates | 93140 | +| policy_gradient_loss | -0.0577 | +| value_loss | 0.000636 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.208 | +| time/ | | +| fps | 310 | +| iterations | 3263 | +| time_elapsed | 10765 | +| total_timesteps | 3341312 | +| train/ | | +| approx_kl | 2.6529229 | +| clip_fraction | 0.429 | +| clip_range | 0.2 | +| entropy_loss | -0.235 | +| explained_variance | -1.57 | +| learning_rate | 0.0001 | +| loss | -0.0759 | +| n_updates | 93150 | +| policy_gradient_loss | -0.0552 | +| value_loss | 0.000606 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.207 | +| time/ | | +| fps | 310 | +| iterations | 3264 | +| time_elapsed | 10768 | +| total_timesteps | 3342336 | +| train/ | | +| approx_kl | 2.0930963 | +| clip_fraction | 0.429 | +| clip_range | 0.2 | +| entropy_loss | -0.28 | +| explained_variance | -2.39 | +| learning_rate | 0.0001 | +| loss | -0.0749 | +| n_updates | 93160 | +| policy_gradient_loss | -0.0557 | +| value_loss | 0.000552 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.208 | +| time/ | | +| fps | 310 | +| iterations | 3265 | +| time_elapsed | 10772 | +| total_timesteps | 3343360 | +| train/ | | +| approx_kl | 2.2892694 | +| clip_fraction | 0.41 | +| clip_range | 0.2 | +| entropy_loss | -0.262 | +| explained_variance | -1.38 | +| learning_rate | 0.0001 | +| loss | -0.0679 | +| n_updates | 93170 | +| policy_gradient_loss | -0.0555 | +| value_loss | 0.000561 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.208 | +| time/ | | +| fps | 310 | +| iterations | 3266 | +| time_elapsed | 10775 | +| total_timesteps | 3344384 | +| train/ | | +| approx_kl | 2.5137606 | +| clip_fraction | 0.435 | +| clip_range | 0.2 | +| entropy_loss | -0.269 | +| explained_variance | -0.626 | +| learning_rate | 0.0001 | +| loss | -0.0741 | +| n_updates | 93180 | +| policy_gradient_loss | -0.0595 | +| value_loss | 0.000602 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.206 | +| time/ | | +| fps | 310 | +| iterations | 3267 | +| time_elapsed | 10778 | +| total_timesteps | 3345408 | +| train/ | | +| approx_kl | 2.9050305 | +| clip_fraction | 0.444 | +| clip_range | 0.2 | +| entropy_loss | -0.295 | +| explained_variance | -2.82 | +| learning_rate | 0.0001 | +| loss | -0.0868 | +| n_updates | 93190 | +| policy_gradient_loss | -0.0637 | +| value_loss | 0.000594 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.207 | +| time/ | | +| fps | 310 | +| iterations | 3268 | +| time_elapsed | 10782 | +| total_timesteps | 3346432 | +| train/ | | +| approx_kl | 2.480733 | +| clip_fraction | 0.401 | +| clip_range | 0.2 | +| entropy_loss | -0.238 | +| explained_variance | -1.72 | +| learning_rate | 0.0001 | +| loss | -0.0931 | +| n_updates | 93200 | +| policy_gradient_loss | -0.0544 | +| value_loss | 0.000832 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.209 | +| time/ | | +| fps | 310 | +| iterations | 3269 | +| time_elapsed | 10785 | +| total_timesteps | 3347456 | +| train/ | | +| approx_kl | 2.282616 | +| clip_fraction | 0.389 | +| clip_range | 0.2 | +| entropy_loss | -0.23 | +| explained_variance | -1.55 | +| learning_rate | 0.0001 | +| loss | -0.0716 | +| n_updates | 93210 | +| policy_gradient_loss | -0.0466 | +| value_loss | 0.000863 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.21 | +| time/ | | +| fps | 310 | +| iterations | 3270 | +| time_elapsed | 10788 | +| total_timesteps | 3348480 | +| train/ | | +| approx_kl | 1.9046698 | +| clip_fraction | 0.382 | +| clip_range | 0.2 | +| entropy_loss | -0.242 | +| explained_variance | -1.68 | +| learning_rate | 0.0001 | +| loss | -0.0551 | +| n_updates | 93220 | +| policy_gradient_loss | -0.053 | +| value_loss | 0.000824 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.21 | +| time/ | | +| fps | 310 | +| iterations | 3271 | +| time_elapsed | 10792 | +| total_timesteps | 3349504 | +| train/ | | +| approx_kl | 2.0561686 | +| clip_fraction | 0.364 | +| clip_range | 0.2 | +| entropy_loss | -0.245 | +| explained_variance | -1.35 | +| learning_rate | 0.0001 | +| loss | -0.0777 | +| n_updates | 93230 | +| policy_gradient_loss | -0.0497 | +| value_loss | 0.000826 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.213 | +| time/ | | +| fps | 310 | +| iterations | 3272 | +| time_elapsed | 10796 | +| total_timesteps | 3350528 | +| train/ | | +| approx_kl | 3.1279774 | +| clip_fraction | 0.437 | +| clip_range | 0.2 | +| entropy_loss | -0.257 | +| explained_variance | -1.6 | +| learning_rate | 0.0001 | +| loss | -0.0798 | +| n_updates | 93240 | +| policy_gradient_loss | -0.0579 | +| value_loss | 0.000595 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.21 | +| time/ | | +| fps | 310 | +| iterations | 3273 | +| time_elapsed | 10799 | +| total_timesteps | 3351552 | +| train/ | | +| approx_kl | 2.1801991 | +| clip_fraction | 0.385 | +| clip_range | 0.2 | +| entropy_loss | -0.251 | +| explained_variance | -1.13 | +| learning_rate | 0.0001 | +| loss | -0.0566 | +| n_updates | 93250 | +| policy_gradient_loss | -0.0508 | +| value_loss | 0.000429 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.209 | +| time/ | | +| fps | 310 | +| iterations | 3274 | +| time_elapsed | 10803 | +| total_timesteps | 3352576 | +| train/ | | +| approx_kl | 2.0274138 | +| clip_fraction | 0.398 | +| clip_range | 0.2 | +| entropy_loss | -0.252 | +| explained_variance | -1.16 | +| learning_rate | 0.0001 | +| loss | -0.0915 | +| n_updates | 93260 | +| policy_gradient_loss | -0.0511 | +| value_loss | 0.000394 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.209 | +| time/ | | +| fps | 310 | +| iterations | 3275 | +| time_elapsed | 10806 | +| total_timesteps | 3353600 | +| train/ | | +| approx_kl | 2.746543 | +| clip_fraction | 0.41 | +| clip_range | 0.2 | +| entropy_loss | -0.241 | +| explained_variance | -0.751 | +| learning_rate | 0.0001 | +| loss | -0.0393 | +| n_updates | 93270 | +| policy_gradient_loss | -0.0509 | +| value_loss | 0.000468 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.212 | +| time/ | | +| fps | 310 | +| iterations | 3276 | +| time_elapsed | 10809 | +| total_timesteps | 3354624 | +| train/ | | +| approx_kl | 2.3428812 | +| clip_fraction | 0.381 | +| clip_range | 0.2 | +| entropy_loss | -0.235 | +| explained_variance | -0.866 | +| learning_rate | 0.0001 | +| loss | -0.0723 | +| n_updates | 93280 | +| policy_gradient_loss | -0.053 | +| value_loss | 0.000738 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.208 | +| time/ | | +| fps | 310 | +| iterations | 3277 | +| time_elapsed | 10813 | +| total_timesteps | 3355648 | +| train/ | | +| approx_kl | 2.3859224 | +| clip_fraction | 0.391 | +| clip_range | 0.2 | +| entropy_loss | -0.237 | +| explained_variance | -2.28 | +| learning_rate | 0.0001 | +| loss | -0.0565 | +| n_updates | 93290 | +| policy_gradient_loss | -0.052 | +| value_loss | 0.000652 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.207 | +| time/ | | +| fps | 310 | +| iterations | 3278 | +| time_elapsed | 10816 | +| total_timesteps | 3356672 | +| train/ | | +| approx_kl | 2.6395507 | +| clip_fraction | 0.403 | +| clip_range | 0.2 | +| entropy_loss | -0.253 | +| explained_variance | -1.77 | +| learning_rate | 0.0001 | +| loss | -0.0879 | +| n_updates | 93300 | +| policy_gradient_loss | -0.0491 | +| value_loss | 0.000587 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.207 | +| time/ | | +| fps | 310 | +| iterations | 3279 | +| time_elapsed | 10819 | +| total_timesteps | 3357696 | +| train/ | | +| approx_kl | 3.7412157 | +| clip_fraction | 0.403 | +| clip_range | 0.2 | +| entropy_loss | -0.219 | +| explained_variance | -0.76 | +| learning_rate | 0.0001 | +| loss | -0.0701 | +| n_updates | 93310 | +| policy_gradient_loss | -0.0593 | +| value_loss | 0.000674 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.204 | +| time/ | | +| fps | 310 | +| iterations | 3280 | +| time_elapsed | 10823 | +| total_timesteps | 3358720 | +| train/ | | +| approx_kl | 6.6608543 | +| clip_fraction | 0.426 | +| clip_range | 0.2 | +| entropy_loss | -0.256 | +| explained_variance | -1.35 | +| learning_rate | 0.0001 | +| loss | -0.0945 | +| n_updates | 93320 | +| policy_gradient_loss | -0.056 | +| value_loss | 0.000562 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.205 | +| time/ | | +| fps | 310 | +| iterations | 3281 | +| time_elapsed | 10826 | +| total_timesteps | 3359744 | +| train/ | | +| approx_kl | 2.3018217 | +| clip_fraction | 0.406 | +| clip_range | 0.2 | +| entropy_loss | -0.242 | +| explained_variance | -1.3 | +| learning_rate | 0.0001 | +| loss | -0.0799 | +| n_updates | 93330 | +| policy_gradient_loss | -0.0548 | +| value_loss | 0.000673 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.205 | +| time/ | | +| fps | 310 | +| iterations | 3282 | +| time_elapsed | 10829 | +| total_timesteps | 3360768 | +| train/ | | +| approx_kl | 2.5677338 | +| clip_fraction | 0.412 | +| clip_range | 0.2 | +| entropy_loss | -0.269 | +| explained_variance | -2.87 | +| learning_rate | 0.0001 | +| loss | -0.11 | +| n_updates | 93340 | +| policy_gradient_loss | -0.0502 | +| value_loss | 0.000528 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.207 | +| time/ | | +| fps | 310 | +| iterations | 3283 | +| time_elapsed | 10832 | +| total_timesteps | 3361792 | +| train/ | | +| approx_kl | 2.4395201 | +| clip_fraction | 0.411 | +| clip_range | 0.2 | +| entropy_loss | -0.256 | +| explained_variance | -1.71 | +| learning_rate | 0.0001 | +| loss | -0.0646 | +| n_updates | 93350 | +| policy_gradient_loss | -0.0568 | +| value_loss | 0.000643 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.201 | +| time/ | | +| fps | 310 | +| iterations | 3284 | +| time_elapsed | 10835 | +| total_timesteps | 3362816 | +| train/ | | +| approx_kl | 2.3484218 | +| clip_fraction | 0.407 | +| clip_range | 0.2 | +| entropy_loss | -0.225 | +| explained_variance | -3.14 | +| learning_rate | 0.0001 | +| loss | -0.0697 | +| n_updates | 93360 | +| policy_gradient_loss | -0.0579 | +| value_loss | 0.000496 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.193 | +| time/ | | +| fps | 310 | +| iterations | 3285 | +| time_elapsed | 10839 | +| total_timesteps | 3363840 | +| train/ | | +| approx_kl | 2.4925988 | +| clip_fraction | 0.405 | +| clip_range | 0.2 | +| entropy_loss | -0.255 | +| explained_variance | -0.763 | +| learning_rate | 0.0001 | +| loss | -0.0649 | +| n_updates | 93370 | +| policy_gradient_loss | -0.0524 | +| value_loss | 0.000603 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.195 | +| time/ | | +| fps | 310 | +| iterations | 3286 | +| time_elapsed | 10842 | +| total_timesteps | 3364864 | +| train/ | | +| approx_kl | 2.3413262 | +| clip_fraction | 0.384 | +| clip_range | 0.2 | +| entropy_loss | -0.208 | +| explained_variance | -1.04 | +| learning_rate | 0.0001 | +| loss | -0.0767 | +| n_updates | 93380 | +| policy_gradient_loss | -0.0456 | +| value_loss | 0.000709 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.195 | +| time/ | | +| fps | 310 | +| iterations | 3287 | +| time_elapsed | 10845 | +| total_timesteps | 3365888 | +| train/ | | +| approx_kl | 3.1207032 | +| clip_fraction | 0.409 | +| clip_range | 0.2 | +| entropy_loss | -0.236 | +| explained_variance | -0.639 | +| learning_rate | 0.0001 | +| loss | -0.0742 | +| n_updates | 93390 | +| policy_gradient_loss | -0.0541 | +| value_loss | 0.00102 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.198 | +| time/ | | +| fps | 310 | +| iterations | 3288 | +| time_elapsed | 10849 | +| total_timesteps | 3366912 | +| train/ | | +| approx_kl | 2.3818786 | +| clip_fraction | 0.439 | +| clip_range | 0.2 | +| entropy_loss | -0.267 | +| explained_variance | -2.62 | +| learning_rate | 0.0001 | +| loss | 0.155 | +| n_updates | 93400 | +| policy_gradient_loss | -0.0614 | +| value_loss | 0.000566 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.196 | +| time/ | | +| fps | 310 | +| iterations | 3289 | +| time_elapsed | 10852 | +| total_timesteps | 3367936 | +| train/ | | +| approx_kl | 2.452786 | +| clip_fraction | 0.429 | +| clip_range | 0.2 | +| entropy_loss | -0.286 | +| explained_variance | -1.84 | +| learning_rate | 0.0001 | +| loss | -0.0867 | +| n_updates | 93410 | +| policy_gradient_loss | -0.0586 | +| value_loss | 0.000438 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.196 | +| time/ | | +| fps | 310 | +| iterations | 3290 | +| time_elapsed | 10856 | +| total_timesteps | 3368960 | +| train/ | | +| approx_kl | 2.7384803 | +| clip_fraction | 0.396 | +| clip_range | 0.2 | +| entropy_loss | -0.225 | +| explained_variance | -1.66 | +| learning_rate | 0.0001 | +| loss | -0.0703 | +| n_updates | 93420 | +| policy_gradient_loss | -0.0576 | +| value_loss | 0.000586 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.194 | +| time/ | | +| fps | 310 | +| iterations | 3291 | +| time_elapsed | 10859 | +| total_timesteps | 3369984 | +| train/ | | +| approx_kl | 2.4358945 | +| clip_fraction | 0.436 | +| clip_range | 0.2 | +| entropy_loss | -0.287 | +| explained_variance | -2.72 | +| learning_rate | 0.0001 | +| loss | -0.0635 | +| n_updates | 93430 | +| policy_gradient_loss | -0.0525 | +| value_loss | 0.000621 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.191 | +| time/ | | +| fps | 310 | +| iterations | 3292 | +| time_elapsed | 10863 | +| total_timesteps | 3371008 | +| train/ | | +| approx_kl | 2.7191463 | +| clip_fraction | 0.427 | +| clip_range | 0.2 | +| entropy_loss | -0.265 | +| explained_variance | -1.82 | +| learning_rate | 0.0001 | +| loss | -0.0793 | +| n_updates | 93440 | +| policy_gradient_loss | -0.0526 | +| value_loss | 0.000484 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.197 | +| time/ | | +| fps | 310 | +| iterations | 3293 | +| time_elapsed | 10866 | +| total_timesteps | 3372032 | +| train/ | | +| approx_kl | 2.281879 | +| clip_fraction | 0.425 | +| clip_range | 0.2 | +| entropy_loss | -0.277 | +| explained_variance | -1.85 | +| learning_rate | 0.0001 | +| loss | -0.0857 | +| n_updates | 93450 | +| policy_gradient_loss | -0.0536 | +| value_loss | 0.000739 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.197 | +| time/ | | +| fps | 310 | +| iterations | 3294 | +| time_elapsed | 10869 | +| total_timesteps | 3373056 | +| train/ | | +| approx_kl | 2.5990834 | +| clip_fraction | 0.44 | +| clip_range | 0.2 | +| entropy_loss | -0.265 | +| explained_variance | -0.963 | +| learning_rate | 0.0001 | +| loss | -0.0652 | +| n_updates | 93460 | +| policy_gradient_loss | -0.0578 | +| value_loss | 0.00078 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.199 | +| time/ | | +| fps | 310 | +| iterations | 3295 | +| time_elapsed | 10873 | +| total_timesteps | 3374080 | +| train/ | | +| approx_kl | 2.350146 | +| clip_fraction | 0.448 | +| clip_range | 0.2 | +| entropy_loss | -0.286 | +| explained_variance | -2.07 | +| learning_rate | 0.0001 | +| loss | -0.0807 | +| n_updates | 93470 | +| policy_gradient_loss | -0.0579 | +| value_loss | 0.000658 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.196 | +| time/ | | +| fps | 310 | +| iterations | 3296 | +| time_elapsed | 10876 | +| total_timesteps | 3375104 | +| train/ | | +| approx_kl | 2.2338648 | +| clip_fraction | 0.408 | +| clip_range | 0.2 | +| entropy_loss | -0.268 | +| explained_variance | -0.432 | +| learning_rate | 0.0001 | +| loss | -0.0543 | +| n_updates | 93480 | +| policy_gradient_loss | -0.0492 | +| value_loss | 0.000742 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.193 | +| time/ | | +| fps | 310 | +| iterations | 3297 | +| time_elapsed | 10879 | +| total_timesteps | 3376128 | +| train/ | | +| approx_kl | 2.7729788 | +| clip_fraction | 0.419 | +| clip_range | 0.2 | +| entropy_loss | -0.237 | +| explained_variance | -1.51 | +| learning_rate | 0.0001 | +| loss | -0.0751 | +| n_updates | 93490 | +| policy_gradient_loss | -0.0568 | +| value_loss | 0.000769 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.202 | +| time/ | | +| fps | 310 | +| iterations | 3298 | +| time_elapsed | 10882 | +| total_timesteps | 3377152 | +| train/ | | +| approx_kl | 3.091611 | +| clip_fraction | 0.433 | +| clip_range | 0.2 | +| entropy_loss | -0.246 | +| explained_variance | -1.91 | +| learning_rate | 0.0001 | +| loss | -0.0945 | +| n_updates | 93500 | +| policy_gradient_loss | -0.0559 | +| value_loss | 0.000458 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.202 | +| time/ | | +| fps | 310 | +| iterations | 3299 | +| time_elapsed | 10885 | +| total_timesteps | 3378176 | +| train/ | | +| approx_kl | 2.5656276 | +| clip_fraction | 0.429 | +| clip_range | 0.2 | +| entropy_loss | -0.246 | +| explained_variance | -0.693 | +| learning_rate | 0.0001 | +| loss | -0.0528 | +| n_updates | 93510 | +| policy_gradient_loss | -0.0527 | +| value_loss | 0.000625 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.197 | +| time/ | | +| fps | 310 | +| iterations | 3300 | +| time_elapsed | 10888 | +| total_timesteps | 3379200 | +| train/ | | +| approx_kl | 2.190741 | +| clip_fraction | 0.438 | +| clip_range | 0.2 | +| entropy_loss | -0.268 | +| explained_variance | -3.45 | +| learning_rate | 0.0001 | +| loss | -0.0728 | +| n_updates | 93520 | +| policy_gradient_loss | -0.0613 | +| value_loss | 0.000597 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.197 | +| time/ | | +| fps | 310 | +| iterations | 3301 | +| time_elapsed | 10892 | +| total_timesteps | 3380224 | +| train/ | | +| approx_kl | 2.3685641 | +| clip_fraction | 0.421 | +| clip_range | 0.2 | +| entropy_loss | -0.258 | +| explained_variance | -2.91 | +| learning_rate | 0.0001 | +| loss | -0.0958 | +| n_updates | 93530 | +| policy_gradient_loss | -0.0606 | +| value_loss | 0.000602 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.2 | +| time/ | | +| fps | 310 | +| iterations | 3302 | +| time_elapsed | 10895 | +| total_timesteps | 3381248 | +| train/ | | +| approx_kl | 2.9557614 | +| clip_fraction | 0.441 | +| clip_range | 0.2 | +| entropy_loss | -0.256 | +| explained_variance | -1.21 | +| learning_rate | 0.0001 | +| loss | -0.0823 | +| n_updates | 93540 | +| policy_gradient_loss | -0.0534 | +| value_loss | 0.000548 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.2 | +| time/ | | +| fps | 310 | +| iterations | 3303 | +| time_elapsed | 10898 | +| total_timesteps | 3382272 | +| train/ | | +| approx_kl | 3.5469275 | +| clip_fraction | 0.432 | +| clip_range | 0.2 | +| entropy_loss | -0.263 | +| explained_variance | -0.765 | +| learning_rate | 0.0001 | +| loss | -0.0682 | +| n_updates | 93550 | +| policy_gradient_loss | -0.0593 | +| value_loss | 0.00058 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.198 | +| time/ | | +| fps | 310 | +| iterations | 3304 | +| time_elapsed | 10901 | +| total_timesteps | 3383296 | +| train/ | | +| approx_kl | 2.5143716 | +| clip_fraction | 0.402 | +| clip_range | 0.2 | +| entropy_loss | -0.231 | +| explained_variance | -3.22 | +| learning_rate | 0.0001 | +| loss | -0.0589 | +| n_updates | 93560 | +| policy_gradient_loss | -0.0596 | +| value_loss | 0.000549 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.2 | +| time/ | | +| fps | 310 | +| iterations | 3305 | +| time_elapsed | 10905 | +| total_timesteps | 3384320 | +| train/ | | +| approx_kl | 2.6316738 | +| clip_fraction | 0.427 | +| clip_range | 0.2 | +| entropy_loss | -0.248 | +| explained_variance | -1.42 | +| learning_rate | 0.0001 | +| loss | -0.073 | +| n_updates | 93570 | +| policy_gradient_loss | -0.0576 | +| value_loss | 0.000623 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.2 | +| time/ | | +| fps | 310 | +| iterations | 3306 | +| time_elapsed | 10908 | +| total_timesteps | 3385344 | +| train/ | | +| approx_kl | 2.1784139 | +| clip_fraction | 0.412 | +| clip_range | 0.2 | +| entropy_loss | -0.259 | +| explained_variance | -0.671 | +| learning_rate | 0.0001 | +| loss | -0.0649 | +| n_updates | 93580 | +| policy_gradient_loss | -0.0493 | +| value_loss | 0.000805 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.196 | +| time/ | | +| fps | 310 | +| iterations | 3307 | +| time_elapsed | 10912 | +| total_timesteps | 3386368 | +| train/ | | +| approx_kl | 2.74477 | +| clip_fraction | 0.421 | +| clip_range | 0.2 | +| entropy_loss | -0.225 | +| explained_variance | -1.24 | +| learning_rate | 0.0001 | +| loss | -0.0838 | +| n_updates | 93590 | +| policy_gradient_loss | -0.0577 | +| value_loss | 0.000826 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.205 | +| time/ | | +| fps | 310 | +| iterations | 3308 | +| time_elapsed | 10916 | +| total_timesteps | 3387392 | +| train/ | | +| approx_kl | 2.5677116 | +| clip_fraction | 0.401 | +| clip_range | 0.2 | +| entropy_loss | -0.238 | +| explained_variance | -2.88 | +| learning_rate | 0.0001 | +| loss | -0.0725 | +| n_updates | 93600 | +| policy_gradient_loss | -0.0538 | +| value_loss | 0.000485 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.205 | +| time/ | | +| fps | 310 | +| iterations | 3309 | +| time_elapsed | 10919 | +| total_timesteps | 3388416 | +| train/ | | +| approx_kl | 4.500454 | +| clip_fraction | 0.413 | +| clip_range | 0.2 | +| entropy_loss | -0.234 | +| explained_variance | -0.733 | +| learning_rate | 0.0001 | +| loss | -0.0831 | +| n_updates | 93610 | +| policy_gradient_loss | -0.0484 | +| value_loss | 0.000856 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.2 | +| time/ | | +| fps | 310 | +| iterations | 3310 | +| time_elapsed | 10923 | +| total_timesteps | 3389440 | +| train/ | | +| approx_kl | 2.2030323 | +| clip_fraction | 0.396 | +| clip_range | 0.2 | +| entropy_loss | -0.241 | +| explained_variance | -0.911 | +| learning_rate | 0.0001 | +| loss | -0.0562 | +| n_updates | 93620 | +| policy_gradient_loss | -0.0581 | +| value_loss | 0.000816 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.201 | +| time/ | | +| fps | 310 | +| iterations | 3311 | +| time_elapsed | 10926 | +| total_timesteps | 3390464 | +| train/ | | +| approx_kl | 2.4705853 | +| clip_fraction | 0.407 | +| clip_range | 0.2 | +| entropy_loss | -0.228 | +| explained_variance | -1.23 | +| learning_rate | 0.0001 | +| loss | -0.0709 | +| n_updates | 93630 | +| policy_gradient_loss | -0.0559 | +| value_loss | 0.000664 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.201 | +| time/ | | +| fps | 310 | +| iterations | 3312 | +| time_elapsed | 10930 | +| total_timesteps | 3391488 | +| train/ | | +| approx_kl | 2.6460102 | +| clip_fraction | 0.416 | +| clip_range | 0.2 | +| entropy_loss | -0.226 | +| explained_variance | -2.66 | +| learning_rate | 0.0001 | +| loss | -0.0922 | +| n_updates | 93640 | +| policy_gradient_loss | -0.0642 | +| value_loss | 0.000642 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.198 | +| time/ | | +| fps | 310 | +| iterations | 3313 | +| time_elapsed | 10933 | +| total_timesteps | 3392512 | +| train/ | | +| approx_kl | 2.238612 | +| clip_fraction | 0.414 | +| clip_range | 0.2 | +| entropy_loss | -0.255 | +| explained_variance | -1.14 | +| learning_rate | 0.0001 | +| loss | -0.0597 | +| n_updates | 93650 | +| policy_gradient_loss | -0.0494 | +| value_loss | 0.000555 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.201 | +| time/ | | +| fps | 310 | +| iterations | 3314 | +| time_elapsed | 10936 | +| total_timesteps | 3393536 | +| train/ | | +| approx_kl | 2.649282 | +| clip_fraction | 0.391 | +| clip_range | 0.2 | +| entropy_loss | -0.21 | +| explained_variance | -2.91 | +| learning_rate | 0.0001 | +| loss | -0.0694 | +| n_updates | 93660 | +| policy_gradient_loss | -0.0526 | +| value_loss | 0.000468 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.204 | +| time/ | | +| fps | 310 | +| iterations | 3315 | +| time_elapsed | 10940 | +| total_timesteps | 3394560 | +| train/ | | +| approx_kl | 2.598856 | +| clip_fraction | 0.407 | +| clip_range | 0.2 | +| entropy_loss | -0.221 | +| explained_variance | -1.41 | +| learning_rate | 0.0001 | +| loss | -0.075 | +| n_updates | 93670 | +| policy_gradient_loss | -0.0568 | +| value_loss | 0.000543 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.204 | +| time/ | | +| fps | 310 | +| iterations | 3316 | +| time_elapsed | 10943 | +| total_timesteps | 3395584 | +| train/ | | +| approx_kl | 3.0186896 | +| clip_fraction | 0.43 | +| clip_range | 0.2 | +| entropy_loss | -0.25 | +| explained_variance | -0.657 | +| learning_rate | 0.0001 | +| loss | -0.0323 | +| n_updates | 93680 | +| policy_gradient_loss | -0.0563 | +| value_loss | 0.000899 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.21 | +| time/ | | +| fps | 310 | +| iterations | 3317 | +| time_elapsed | 10946 | +| total_timesteps | 3396608 | +| train/ | | +| approx_kl | 2.4474146 | +| clip_fraction | 0.396 | +| clip_range | 0.2 | +| entropy_loss | -0.245 | +| explained_variance | -3.52 | +| learning_rate | 0.0001 | +| loss | -0.0757 | +| n_updates | 93690 | +| policy_gradient_loss | -0.0486 | +| value_loss | 0.000379 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.212 | +| time/ | | +| fps | 310 | +| iterations | 3318 | +| time_elapsed | 10949 | +| total_timesteps | 3397632 | +| train/ | | +| approx_kl | 3.427117 | +| clip_fraction | 0.412 | +| clip_range | 0.2 | +| entropy_loss | -0.229 | +| explained_variance | -0.977 | +| learning_rate | 0.0001 | +| loss | -0.0993 | +| n_updates | 93700 | +| policy_gradient_loss | -0.0583 | +| value_loss | 0.00043 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.212 | +| time/ | | +| fps | 310 | +| iterations | 3319 | +| time_elapsed | 10952 | +| total_timesteps | 3398656 | +| train/ | | +| approx_kl | 2.506619 | +| clip_fraction | 0.414 | +| clip_range | 0.2 | +| entropy_loss | -0.222 | +| explained_variance | -1.15 | +| learning_rate | 0.0001 | +| loss | -0.0792 | +| n_updates | 93710 | +| policy_gradient_loss | -0.0515 | +| value_loss | 0.000563 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.212 | +| time/ | | +| fps | 310 | +| iterations | 3320 | +| time_elapsed | 10956 | +| total_timesteps | 3399680 | +| train/ | | +| approx_kl | 2.287841 | +| clip_fraction | 0.451 | +| clip_range | 0.2 | +| entropy_loss | -0.281 | +| explained_variance | -0.956 | +| learning_rate | 0.0001 | +| loss | -0.0528 | +| n_updates | 93720 | +| policy_gradient_loss | -0.0534 | +| value_loss | 0.00075 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.216 | +| time/ | | +| fps | 310 | +| iterations | 3321 | +| time_elapsed | 10959 | +| total_timesteps | 3400704 | +| train/ | | +| approx_kl | 2.8262992 | +| clip_fraction | 0.396 | +| clip_range | 0.2 | +| entropy_loss | -0.215 | +| explained_variance | -1.83 | +| learning_rate | 0.0001 | +| loss | -0.0606 | +| n_updates | 93730 | +| policy_gradient_loss | -0.0578 | +| value_loss | 0.000844 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.216 | +| time/ | | +| fps | 310 | +| iterations | 3322 | +| time_elapsed | 10962 | +| total_timesteps | 3401728 | +| train/ | | +| approx_kl | 2.3863134 | +| clip_fraction | 0.41 | +| clip_range | 0.2 | +| entropy_loss | -0.228 | +| explained_variance | -1.65 | +| learning_rate | 0.0001 | +| loss | -0.067 | +| n_updates | 93740 | +| policy_gradient_loss | -0.0597 | +| value_loss | 0.000719 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.221 | +| time/ | | +| fps | 310 | +| iterations | 3323 | +| time_elapsed | 10966 | +| total_timesteps | 3402752 | +| train/ | | +| approx_kl | 2.852525 | +| clip_fraction | 0.458 | +| clip_range | 0.2 | +| entropy_loss | -0.265 | +| explained_variance | -0.982 | +| learning_rate | 0.0001 | +| loss | -0.123 | +| n_updates | 93750 | +| policy_gradient_loss | -0.0563 | +| value_loss | 0.000642 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.227 | +| time/ | | +| fps | 310 | +| iterations | 3324 | +| time_elapsed | 10969 | +| total_timesteps | 3403776 | +| train/ | | +| approx_kl | 2.3734767 | +| clip_fraction | 0.422 | +| clip_range | 0.2 | +| entropy_loss | -0.254 | +| explained_variance | -1.3 | +| learning_rate | 0.0001 | +| loss | -0.093 | +| n_updates | 93760 | +| policy_gradient_loss | -0.0612 | +| value_loss | 0.000841 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.228 | +| time/ | | +| fps | 310 | +| iterations | 3325 | +| time_elapsed | 10972 | +| total_timesteps | 3404800 | +| train/ | | +| approx_kl | 2.5063035 | +| clip_fraction | 0.412 | +| clip_range | 0.2 | +| entropy_loss | -0.246 | +| explained_variance | -0.629 | +| learning_rate | 0.0001 | +| loss | -0.0701 | +| n_updates | 93770 | +| policy_gradient_loss | -0.0574 | +| value_loss | 0.00101 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.224 | +| time/ | | +| fps | 310 | +| iterations | 3326 | +| time_elapsed | 10975 | +| total_timesteps | 3405824 | +| train/ | | +| approx_kl | 2.2895956 | +| clip_fraction | 0.405 | +| clip_range | 0.2 | +| entropy_loss | -0.255 | +| explained_variance | -0.674 | +| learning_rate | 0.0001 | +| loss | -0.0804 | +| n_updates | 93780 | +| policy_gradient_loss | -0.0566 | +| value_loss | 0.000788 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.224 | +| time/ | | +| fps | 310 | +| iterations | 3327 | +| time_elapsed | 10979 | +| total_timesteps | 3406848 | +| train/ | | +| approx_kl | 3.224255 | +| clip_fraction | 0.44 | +| clip_range | 0.2 | +| entropy_loss | -0.258 | +| explained_variance | -1.53 | +| learning_rate | 0.0001 | +| loss | -0.0674 | +| n_updates | 93790 | +| policy_gradient_loss | -0.0581 | +| value_loss | 0.000724 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.23 | +| time/ | | +| fps | 310 | +| iterations | 3328 | +| time_elapsed | 10982 | +| total_timesteps | 3407872 | +| train/ | | +| approx_kl | 2.3212924 | +| clip_fraction | 0.413 | +| clip_range | 0.2 | +| entropy_loss | -0.256 | +| explained_variance | -2.87 | +| learning_rate | 0.0001 | +| loss | -0.092 | +| n_updates | 93800 | +| policy_gradient_loss | -0.0576 | +| value_loss | 0.000584 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.229 | +| time/ | | +| fps | 310 | +| iterations | 3329 | +| time_elapsed | 10986 | +| total_timesteps | 3408896 | +| train/ | | +| approx_kl | 4.1215734 | +| clip_fraction | 0.416 | +| clip_range | 0.2 | +| entropy_loss | -0.235 | +| explained_variance | -1.04 | +| learning_rate | 0.0001 | +| loss | -0.0658 | +| n_updates | 93810 | +| policy_gradient_loss | -0.0572 | +| value_loss | 0.000518 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.222 | +| time/ | | +| fps | 310 | +| iterations | 3330 | +| time_elapsed | 10989 | +| total_timesteps | 3409920 | +| train/ | | +| approx_kl | 2.2815938 | +| clip_fraction | 0.422 | +| clip_range | 0.2 | +| entropy_loss | -0.254 | +| explained_variance | -2.03 | +| learning_rate | 0.0001 | +| loss | -0.067 | +| n_updates | 93820 | +| policy_gradient_loss | -0.0567 | +| value_loss | 0.000416 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.222 | +| time/ | | +| fps | 310 | +| iterations | 3331 | +| time_elapsed | 10992 | +| total_timesteps | 3410944 | +| train/ | | +| approx_kl | 27.592606 | +| clip_fraction | 0.412 | +| clip_range | 0.2 | +| entropy_loss | -0.258 | +| explained_variance | -0.643 | +| learning_rate | 0.0001 | +| loss | -0.0686 | +| n_updates | 93830 | +| policy_gradient_loss | -0.0498 | +| value_loss | 0.000504 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.222 | +| time/ | | +| fps | 310 | +| iterations | 3332 | +| time_elapsed | 10995 | +| total_timesteps | 3411968 | +| train/ | | +| approx_kl | 2.2994986 | +| clip_fraction | 0.374 | +| clip_range | 0.2 | +| entropy_loss | -0.207 | +| explained_variance | -0.953 | +| learning_rate | 0.0001 | +| loss | -0.0571 | +| n_updates | 93840 | +| policy_gradient_loss | -0.0505 | +| value_loss | 0.000695 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.228 | +| time/ | | +| fps | 310 | +| iterations | 3333 | +| time_elapsed | 10998 | +| total_timesteps | 3412992 | +| train/ | | +| approx_kl | 2.7810915 | +| clip_fraction | 0.431 | +| clip_range | 0.2 | +| entropy_loss | -0.266 | +| explained_variance | -1.09 | +| learning_rate | 0.0001 | +| loss | -0.0822 | +| n_updates | 93850 | +| policy_gradient_loss | -0.0477 | +| value_loss | 0.000574 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.229 | +| time/ | | +| fps | 310 | +| iterations | 3334 | +| time_elapsed | 11002 | +| total_timesteps | 3414016 | +| train/ | | +| approx_kl | 2.4302864 | +| clip_fraction | 0.407 | +| clip_range | 0.2 | +| entropy_loss | -0.229 | +| explained_variance | -1.07 | +| learning_rate | 0.0001 | +| loss | -0.0806 | +| n_updates | 93860 | +| policy_gradient_loss | -0.0538 | +| value_loss | 0.000676 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.228 | +| time/ | | +| fps | 310 | +| iterations | 3335 | +| time_elapsed | 11005 | +| total_timesteps | 3415040 | +| train/ | | +| approx_kl | 2.4236903 | +| clip_fraction | 0.392 | +| clip_range | 0.2 | +| entropy_loss | -0.208 | +| explained_variance | -0.856 | +| learning_rate | 0.0001 | +| loss | -0.0883 | +| n_updates | 93870 | +| policy_gradient_loss | -0.0589 | +| value_loss | 0.000916 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.224 | +| time/ | | +| fps | 310 | +| iterations | 3336 | +| time_elapsed | 11008 | +| total_timesteps | 3416064 | +| train/ | | +| approx_kl | 3.4474144 | +| clip_fraction | 0.433 | +| clip_range | 0.2 | +| entropy_loss | -0.255 | +| explained_variance | -2.9 | +| learning_rate | 0.0001 | +| loss | -0.0935 | +| n_updates | 93880 | +| policy_gradient_loss | -0.0622 | +| value_loss | 0.000516 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.224 | +| time/ | | +| fps | 310 | +| iterations | 3337 | +| time_elapsed | 11011 | +| total_timesteps | 3417088 | +| train/ | | +| approx_kl | 2.517744 | +| clip_fraction | 0.395 | +| clip_range | 0.2 | +| entropy_loss | -0.214 | +| explained_variance | -1.79 | +| learning_rate | 0.0001 | +| loss | -0.0585 | +| n_updates | 93890 | +| policy_gradient_loss | -0.061 | +| value_loss | 0.00048 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.218 | +| time/ | | +| fps | 310 | +| iterations | 3338 | +| time_elapsed | 11014 | +| total_timesteps | 3418112 | +| train/ | | +| approx_kl | 17.744358 | +| clip_fraction | 0.335 | +| clip_range | 0.2 | +| entropy_loss | -0.189 | +| explained_variance | -0.607 | +| learning_rate | 0.0001 | +| loss | -0.0775 | +| n_updates | 93900 | +| policy_gradient_loss | -0.0545 | +| value_loss | 0.000661 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.222 | +| time/ | | +| fps | 310 | +| iterations | 3339 | +| time_elapsed | 11018 | +| total_timesteps | 3419136 | +| train/ | | +| approx_kl | 1.8687282 | +| clip_fraction | 0.37 | +| clip_range | 0.2 | +| entropy_loss | -0.22 | +| explained_variance | -0.665 | +| learning_rate | 0.0001 | +| loss | -0.0836 | +| n_updates | 93910 | +| policy_gradient_loss | -0.0499 | +| value_loss | 0.00083 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.216 | +| time/ | | +| fps | 310 | +| iterations | 3340 | +| time_elapsed | 11021 | +| total_timesteps | 3420160 | +| train/ | | +| approx_kl | 2.1811073 | +| clip_fraction | 0.349 | +| clip_range | 0.2 | +| entropy_loss | -0.195 | +| explained_variance | -2.38 | +| learning_rate | 0.0001 | +| loss | -0.0745 | +| n_updates | 93920 | +| policy_gradient_loss | -0.0553 | +| value_loss | 0.000814 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.223 | +| time/ | | +| fps | 310 | +| iterations | 3341 | +| time_elapsed | 11025 | +| total_timesteps | 3421184 | +| train/ | | +| approx_kl | 2.2995496 | +| clip_fraction | 0.382 | +| clip_range | 0.2 | +| entropy_loss | -0.224 | +| explained_variance | -0.317 | +| learning_rate | 0.0001 | +| loss | -0.0882 | +| n_updates | 93930 | +| policy_gradient_loss | -0.0468 | +| value_loss | 0.000706 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.223 | +| time/ | | +| fps | 310 | +| iterations | 3342 | +| time_elapsed | 11028 | +| total_timesteps | 3422208 | +| train/ | | +| approx_kl | 2.7405589 | +| clip_fraction | 0.419 | +| clip_range | 0.2 | +| entropy_loss | -0.237 | +| explained_variance | -1.5 | +| learning_rate | 0.0001 | +| loss | -0.0748 | +| n_updates | 93940 | +| policy_gradient_loss | -0.0587 | +| value_loss | 0.000549 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.229 | +| time/ | | +| fps | 310 | +| iterations | 3343 | +| time_elapsed | 11032 | +| total_timesteps | 3423232 | +| train/ | | +| approx_kl | 2.0038404 | +| clip_fraction | 0.418 | +| clip_range | 0.2 | +| entropy_loss | -0.299 | +| explained_variance | -0.886 | +| learning_rate | 0.0001 | +| loss | -0.0626 | +| n_updates | 93950 | +| policy_gradient_loss | -0.0498 | +| value_loss | 0.00055 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.23 | +| time/ | | +| fps | 310 | +| iterations | 3344 | +| time_elapsed | 11035 | +| total_timesteps | 3424256 | +| train/ | | +| approx_kl | 2.2585163 | +| clip_fraction | 0.396 | +| clip_range | 0.2 | +| entropy_loss | -0.233 | +| explained_variance | -0.692 | +| learning_rate | 0.0001 | +| loss | -0.0903 | +| n_updates | 93960 | +| policy_gradient_loss | -0.0602 | +| value_loss | 0.000478 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.229 | +| time/ | | +| fps | 310 | +| iterations | 3345 | +| time_elapsed | 11039 | +| total_timesteps | 3425280 | +| train/ | | +| approx_kl | 2.2463517 | +| clip_fraction | 0.423 | +| clip_range | 0.2 | +| entropy_loss | -0.246 | +| explained_variance | -0.348 | +| learning_rate | 0.0001 | +| loss | -0.0771 | +| n_updates | 93970 | +| policy_gradient_loss | -0.0596 | +| value_loss | 0.000817 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.229 | +| time/ | | +| fps | 310 | +| iterations | 3346 | +| time_elapsed | 11042 | +| total_timesteps | 3426304 | +| train/ | | +| approx_kl | 2.2229455 | +| clip_fraction | 0.413 | +| clip_range | 0.2 | +| entropy_loss | -0.266 | +| explained_variance | -2.74 | +| learning_rate | 0.0001 | +| loss | -0.0589 | +| n_updates | 93980 | +| policy_gradient_loss | -0.0577 | +| value_loss | 0.000991 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.231 | +| time/ | | +| fps | 310 | +| iterations | 3347 | +| time_elapsed | 11046 | +| total_timesteps | 3427328 | +| train/ | | +| approx_kl | 2.9501452 | +| clip_fraction | 0.452 | +| clip_range | 0.2 | +| entropy_loss | -0.265 | +| explained_variance | -1.06 | +| learning_rate | 0.0001 | +| loss | -0.106 | +| n_updates | 93990 | +| policy_gradient_loss | -0.063 | +| value_loss | 0.000723 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.231 | +| time/ | | +| fps | 310 | +| iterations | 3348 | +| time_elapsed | 11049 | +| total_timesteps | 3428352 | +| train/ | | +| approx_kl | 2.2951484 | +| clip_fraction | 0.422 | +| clip_range | 0.2 | +| entropy_loss | -0.246 | +| explained_variance | -0.492 | +| learning_rate | 0.0001 | +| loss | -0.0657 | +| n_updates | 94000 | +| policy_gradient_loss | -0.0565 | +| value_loss | 0.000702 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.234 | +| time/ | | +| fps | 310 | +| iterations | 3349 | +| time_elapsed | 11053 | +| total_timesteps | 3429376 | +| train/ | | +| approx_kl | 2.7330084 | +| clip_fraction | 0.401 | +| clip_range | 0.2 | +| entropy_loss | -0.22 | +| explained_variance | -2.69 | +| learning_rate | 0.0001 | +| loss | -0.0941 | +| n_updates | 94010 | +| policy_gradient_loss | -0.0596 | +| value_loss | 0.000709 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.228 | +| time/ | | +| fps | 310 | +| iterations | 3350 | +| time_elapsed | 11056 | +| total_timesteps | 3430400 | +| train/ | | +| approx_kl | 2.8443456 | +| clip_fraction | 0.413 | +| clip_range | 0.2 | +| entropy_loss | -0.239 | +| explained_variance | -1.72 | +| learning_rate | 0.0001 | +| loss | -0.0629 | +| n_updates | 94020 | +| policy_gradient_loss | -0.0545 | +| value_loss | 0.000581 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.234 | +| time/ | | +| fps | 310 | +| iterations | 3351 | +| time_elapsed | 11059 | +| total_timesteps | 3431424 | +| train/ | | +| approx_kl | 2.3732643 | +| clip_fraction | 0.437 | +| clip_range | 0.2 | +| entropy_loss | -0.271 | +| explained_variance | -1.58 | +| learning_rate | 0.0001 | +| loss | -0.0411 | +| n_updates | 94030 | +| policy_gradient_loss | -0.0559 | +| value_loss | 0.000543 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.24 | +| time/ | | +| fps | 310 | +| iterations | 3352 | +| time_elapsed | 11062 | +| total_timesteps | 3432448 | +| train/ | | +| approx_kl | 2.6122904 | +| clip_fraction | 0.431 | +| clip_range | 0.2 | +| entropy_loss | -0.268 | +| explained_variance | -1.02 | +| learning_rate | 0.0001 | +| loss | -0.0892 | +| n_updates | 94040 | +| policy_gradient_loss | -0.0526 | +| value_loss | 0.000487 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.24 | +| time/ | | +| fps | 310 | +| iterations | 3353 | +| time_elapsed | 11065 | +| total_timesteps | 3433472 | +| train/ | | +| approx_kl | 1.9590997 | +| clip_fraction | 0.413 | +| clip_range | 0.2 | +| entropy_loss | -0.294 | +| explained_variance | -0.741 | +| learning_rate | 0.0001 | +| loss | -0.0546 | +| n_updates | 94050 | +| policy_gradient_loss | -0.0496 | +| value_loss | 0.0006 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.246 | +| time/ | | +| fps | 310 | +| iterations | 3354 | +| time_elapsed | 11069 | +| total_timesteps | 3434496 | +| train/ | | +| approx_kl | 2.1220217 | +| clip_fraction | 0.393 | +| clip_range | 0.2 | +| entropy_loss | -0.24 | +| explained_variance | -2.02 | +| learning_rate | 0.0001 | +| loss | -0.0696 | +| n_updates | 94060 | +| policy_gradient_loss | -0.0556 | +| value_loss | 0.00073 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.252 | +| time/ | | +| fps | 310 | +| iterations | 3355 | +| time_elapsed | 11072 | +| total_timesteps | 3435520 | +| train/ | | +| approx_kl | 3.183755 | +| clip_fraction | 0.371 | +| clip_range | 0.2 | +| entropy_loss | -0.23 | +| explained_variance | -0.646 | +| learning_rate | 0.0001 | +| loss | -0.0773 | +| n_updates | 94070 | +| policy_gradient_loss | -0.0559 | +| value_loss | 0.000579 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.251 | +| time/ | | +| fps | 310 | +| iterations | 3356 | +| time_elapsed | 11075 | +| total_timesteps | 3436544 | +| train/ | | +| approx_kl | 2.30301 | +| clip_fraction | 0.369 | +| clip_range | 0.2 | +| entropy_loss | -0.211 | +| explained_variance | -1 | +| learning_rate | 0.0001 | +| loss | -0.0875 | +| n_updates | 94080 | +| policy_gradient_loss | -0.0551 | +| value_loss | 0.000875 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.256 | +| time/ | | +| fps | 310 | +| iterations | 3357 | +| time_elapsed | 11078 | +| total_timesteps | 3437568 | +| train/ | | +| approx_kl | 2.902846 | +| clip_fraction | 0.371 | +| clip_range | 0.2 | +| entropy_loss | -0.212 | +| explained_variance | -2.52 | +| learning_rate | 0.0001 | +| loss | -0.0644 | +| n_updates | 94090 | +| policy_gradient_loss | -0.0562 | +| value_loss | 0.000776 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.257 | +| time/ | | +| fps | 310 | +| iterations | 3358 | +| time_elapsed | 11082 | +| total_timesteps | 3438592 | +| train/ | | +| approx_kl | 2.4129982 | +| clip_fraction | 0.421 | +| clip_range | 0.2 | +| entropy_loss | -0.262 | +| explained_variance | -2.8 | +| learning_rate | 0.0001 | +| loss | -0.0668 | +| n_updates | 94100 | +| policy_gradient_loss | -0.0634 | +| value_loss | 0.000617 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.259 | +| time/ | | +| fps | 310 | +| iterations | 3359 | +| time_elapsed | 11085 | +| total_timesteps | 3439616 | +| train/ | | +| approx_kl | 1.9079212 | +| clip_fraction | 0.394 | +| clip_range | 0.2 | +| entropy_loss | -0.282 | +| explained_variance | -2.29 | +| learning_rate | 0.0001 | +| loss | -0.0884 | +| n_updates | 94110 | +| policy_gradient_loss | -0.0454 | +| value_loss | 0.000459 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.26 | +| time/ | | +| fps | 310 | +| iterations | 3360 | +| time_elapsed | 11088 | +| total_timesteps | 3440640 | +| train/ | | +| approx_kl | 2.6226242 | +| clip_fraction | 0.411 | +| clip_range | 0.2 | +| entropy_loss | -0.236 | +| explained_variance | -0.676 | +| learning_rate | 0.0001 | +| loss | -0.0567 | +| n_updates | 94120 | +| policy_gradient_loss | -0.0512 | +| value_loss | 0.000755 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.261 | +| time/ | | +| fps | 310 | +| iterations | 3361 | +| time_elapsed | 11092 | +| total_timesteps | 3441664 | +| train/ | | +| approx_kl | 2.6699352 | +| clip_fraction | 0.43 | +| clip_range | 0.2 | +| entropy_loss | -0.262 | +| explained_variance | -1.34 | +| learning_rate | 0.0001 | +| loss | -0.0786 | +| n_updates | 94130 | +| policy_gradient_loss | -0.0601 | +| value_loss | 0.00074 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.261 | +| time/ | | +| fps | 310 | +| iterations | 3362 | +| time_elapsed | 11095 | +| total_timesteps | 3442688 | +| train/ | | +| approx_kl | 2.019073 | +| clip_fraction | 0.409 | +| clip_range | 0.2 | +| entropy_loss | -0.277 | +| explained_variance | -1.35 | +| learning_rate | 0.0001 | +| loss | -0.0822 | +| n_updates | 94140 | +| policy_gradient_loss | -0.0564 | +| value_loss | 0.000841 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.26 | +| time/ | | +| fps | 310 | +| iterations | 3363 | +| time_elapsed | 11099 | +| total_timesteps | 3443712 | +| train/ | | +| approx_kl | 2.9991336 | +| clip_fraction | 0.433 | +| clip_range | 0.2 | +| entropy_loss | -0.263 | +| explained_variance | -1.16 | +| learning_rate | 0.0001 | +| loss | -0.0931 | +| n_updates | 94150 | +| policy_gradient_loss | -0.0623 | +| value_loss | 0.000517 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.259 | +| time/ | | +| fps | 310 | +| iterations | 3364 | +| time_elapsed | 11102 | +| total_timesteps | 3444736 | +| train/ | | +| approx_kl | 2.8083727 | +| clip_fraction | 0.422 | +| clip_range | 0.2 | +| entropy_loss | -0.261 | +| explained_variance | -1.3 | +| learning_rate | 0.0001 | +| loss | -0.0627 | +| n_updates | 94160 | +| policy_gradient_loss | -0.0586 | +| value_loss | 0.000621 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.261 | +| time/ | | +| fps | 310 | +| iterations | 3365 | +| time_elapsed | 11106 | +| total_timesteps | 3445760 | +| train/ | | +| approx_kl | 2.824128 | +| clip_fraction | 0.439 | +| clip_range | 0.2 | +| entropy_loss | -0.246 | +| explained_variance | -1.75 | +| learning_rate | 0.0001 | +| loss | -0.058 | +| n_updates | 94170 | +| policy_gradient_loss | -0.0588 | +| value_loss | 0.000382 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.26 | +| time/ | | +| fps | 310 | +| iterations | 3366 | +| time_elapsed | 11109 | +| total_timesteps | 3446784 | +| train/ | | +| approx_kl | 2.8960934 | +| clip_fraction | 0.444 | +| clip_range | 0.2 | +| entropy_loss | -0.268 | +| explained_variance | -1.12 | +| learning_rate | 0.0001 | +| loss | -0.0781 | +| n_updates | 94180 | +| policy_gradient_loss | -0.0634 | +| value_loss | 0.000534 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.26 | +| time/ | | +| fps | 310 | +| iterations | 3367 | +| time_elapsed | 11112 | +| total_timesteps | 3447808 | +| train/ | | +| approx_kl | 2.930862 | +| clip_fraction | 0.391 | +| clip_range | 0.2 | +| entropy_loss | -0.223 | +| explained_variance | -1.96 | +| learning_rate | 0.0001 | +| loss | -0.0914 | +| n_updates | 94190 | +| policy_gradient_loss | -0.0598 | +| value_loss | 0.000493 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.264 | +| time/ | | +| fps | 310 | +| iterations | 3368 | +| time_elapsed | 11115 | +| total_timesteps | 3448832 | +| train/ | | +| approx_kl | 2.4297464 | +| clip_fraction | 0.419 | +| clip_range | 0.2 | +| entropy_loss | -0.265 | +| explained_variance | -0.484 | +| learning_rate | 0.0001 | +| loss | -0.0552 | +| n_updates | 94200 | +| policy_gradient_loss | -0.0616 | +| value_loss | 0.000595 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.263 | +| time/ | | +| fps | 310 | +| iterations | 3369 | +| time_elapsed | 11119 | +| total_timesteps | 3449856 | +| train/ | | +| approx_kl | 3.4016004 | +| clip_fraction | 0.413 | +| clip_range | 0.2 | +| entropy_loss | -0.248 | +| explained_variance | -0.309 | +| learning_rate | 0.0001 | +| loss | -0.0872 | +| n_updates | 94210 | +| policy_gradient_loss | -0.0601 | +| value_loss | 0.000708 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.263 | +| time/ | | +| fps | 310 | +| iterations | 3370 | +| time_elapsed | 11122 | +| total_timesteps | 3450880 | +| train/ | | +| approx_kl | 63.231876 | +| clip_fraction | 0.444 | +| clip_range | 0.2 | +| entropy_loss | -0.281 | +| explained_variance | -1.11 | +| learning_rate | 0.0001 | +| loss | -0.0668 | +| n_updates | 94220 | +| policy_gradient_loss | -0.0613 | +| value_loss | 0.000618 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.265 | +| time/ | | +| fps | 310 | +| iterations | 3371 | +| time_elapsed | 11125 | +| total_timesteps | 3451904 | +| train/ | | +| approx_kl | 2.8188865 | +| clip_fraction | 0.419 | +| clip_range | 0.2 | +| entropy_loss | -0.256 | +| explained_variance | -1.27 | +| learning_rate | 0.0001 | +| loss | -0.0711 | +| n_updates | 94230 | +| policy_gradient_loss | -0.0575 | +| value_loss | 0.000678 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.26 | +| time/ | | +| fps | 310 | +| iterations | 3372 | +| time_elapsed | 11128 | +| total_timesteps | 3452928 | +| train/ | | +| approx_kl | 2.2474122 | +| clip_fraction | 0.378 | +| clip_range | 0.2 | +| entropy_loss | -0.231 | +| explained_variance | -0.727 | +| learning_rate | 0.0001 | +| loss | -0.0869 | +| n_updates | 94240 | +| policy_gradient_loss | -0.0559 | +| value_loss | 0.000548 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.256 | +| time/ | | +| fps | 310 | +| iterations | 3373 | +| time_elapsed | 11131 | +| total_timesteps | 3453952 | +| train/ | | +| approx_kl | 2.362287 | +| clip_fraction | 0.411 | +| clip_range | 0.2 | +| entropy_loss | -0.257 | +| explained_variance | -0.945 | +| learning_rate | 0.0001 | +| loss | -0.0557 | +| n_updates | 94250 | +| policy_gradient_loss | -0.0517 | +| value_loss | 0.000579 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.256 | +| time/ | | +| fps | 310 | +| iterations | 3374 | +| time_elapsed | 11134 | +| total_timesteps | 3454976 | +| train/ | | +| approx_kl | 3.1569467 | +| clip_fraction | 0.376 | +| clip_range | 0.2 | +| entropy_loss | -0.199 | +| explained_variance | -1.37 | +| learning_rate | 0.0001 | +| loss | -0.0679 | +| n_updates | 94260 | +| policy_gradient_loss | -0.0535 | +| value_loss | 0.000669 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.256 | +| time/ | | +| fps | 310 | +| iterations | 3375 | +| time_elapsed | 11138 | +| total_timesteps | 3456000 | +| train/ | | +| approx_kl | 1.8403597 | +| clip_fraction | 0.394 | +| clip_range | 0.2 | +| entropy_loss | -0.28 | +| explained_variance | -1.73 | +| learning_rate | 0.0001 | +| loss | -0.0794 | +| n_updates | 94270 | +| policy_gradient_loss | -0.055 | +| value_loss | 0.000524 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.257 | +| time/ | | +| fps | 310 | +| iterations | 3376 | +| time_elapsed | 11141 | +| total_timesteps | 3457024 | +| train/ | | +| approx_kl | 20.931488 | +| clip_fraction | 0.405 | +| clip_range | 0.2 | +| entropy_loss | -0.252 | +| explained_variance | -0.503 | +| learning_rate | 0.0001 | +| loss | -0.0871 | +| n_updates | 94280 | +| policy_gradient_loss | -0.0515 | +| value_loss | 0.000542 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.262 | +| time/ | | +| fps | 310 | +| iterations | 3377 | +| time_elapsed | 11145 | +| total_timesteps | 3458048 | +| train/ | | +| approx_kl | 3.1643817 | +| clip_fraction | 0.37 | +| clip_range | 0.2 | +| entropy_loss | -0.249 | +| explained_variance | -0.545 | +| learning_rate | 0.0001 | +| loss | -0.0741 | +| n_updates | 94290 | +| policy_gradient_loss | -0.0452 | +| value_loss | 0.000766 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.266 | +| time/ | | +| fps | 310 | +| iterations | 3378 | +| time_elapsed | 11148 | +| total_timesteps | 3459072 | +| train/ | | +| approx_kl | 2.2433128 | +| clip_fraction | 0.381 | +| clip_range | 0.2 | +| entropy_loss | -0.227 | +| explained_variance | -2.8 | +| learning_rate | 0.0001 | +| loss | -0.0955 | +| n_updates | 94300 | +| policy_gradient_loss | -0.0558 | +| value_loss | 0.000648 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.266 | +| time/ | | +| fps | 310 | +| iterations | 3379 | +| time_elapsed | 11152 | +| total_timesteps | 3460096 | +| train/ | | +| approx_kl | 2.588922 | +| clip_fraction | 0.442 | +| clip_range | 0.2 | +| entropy_loss | -0.246 | +| explained_variance | -0.761 | +| learning_rate | 0.0001 | +| loss | -0.0874 | +| n_updates | 94310 | +| policy_gradient_loss | -0.0624 | +| value_loss | 0.000737 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.27 | +| time/ | | +| fps | 310 | +| iterations | 3380 | +| time_elapsed | 11155 | +| total_timesteps | 3461120 | +| train/ | | +| approx_kl | 2.6920214 | +| clip_fraction | 0.465 | +| clip_range | 0.2 | +| entropy_loss | -0.288 | +| explained_variance | -1.48 | +| learning_rate | 0.0001 | +| loss | -0.062 | +| n_updates | 94320 | +| policy_gradient_loss | -0.0612 | +| value_loss | 0.000487 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.274 | +| time/ | | +| fps | 310 | +| iterations | 3381 | +| time_elapsed | 11158 | +| total_timesteps | 3462144 | +| train/ | | +| approx_kl | 2.1012707 | +| clip_fraction | 0.422 | +| clip_range | 0.2 | +| entropy_loss | -0.279 | +| explained_variance | -1.69 | +| learning_rate | 0.0001 | +| loss | -0.083 | +| n_updates | 94330 | +| policy_gradient_loss | -0.0583 | +| value_loss | 0.000657 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.27 | +| time/ | | +| fps | 310 | +| iterations | 3382 | +| time_elapsed | 11162 | +| total_timesteps | 3463168 | +| train/ | | +| approx_kl | 2.087729 | +| clip_fraction | 0.408 | +| clip_range | 0.2 | +| entropy_loss | -0.236 | +| explained_variance | -2.28 | +| learning_rate | 0.0001 | +| loss | -0.0867 | +| n_updates | 94340 | +| policy_gradient_loss | -0.0607 | +| value_loss | 0.00068 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.27 | +| time/ | | +| fps | 310 | +| iterations | 3383 | +| time_elapsed | 11165 | +| total_timesteps | 3464192 | +| train/ | | +| approx_kl | 3.6225853 | +| clip_fraction | 0.422 | +| clip_range | 0.2 | +| entropy_loss | -0.24 | +| explained_variance | -0.637 | +| learning_rate | 0.0001 | +| loss | -0.0719 | +| n_updates | 94350 | +| policy_gradient_loss | -0.0553 | +| value_loss | 0.00077 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.269 | +| time/ | | +| fps | 310 | +| iterations | 3384 | +| time_elapsed | 11169 | +| total_timesteps | 3465216 | +| train/ | | +| approx_kl | 3.0653586 | +| clip_fraction | 0.463 | +| clip_range | 0.2 | +| entropy_loss | -0.308 | +| explained_variance | -1.21 | +| learning_rate | 0.0001 | +| loss | -0.0694 | +| n_updates | 94360 | +| policy_gradient_loss | -0.0636 | +| value_loss | 0.000514 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.272 | +| time/ | | +| fps | 310 | +| iterations | 3385 | +| time_elapsed | 11172 | +| total_timesteps | 3466240 | +| train/ | | +| approx_kl | 2.355617 | +| clip_fraction | 0.433 | +| clip_range | 0.2 | +| entropy_loss | -0.258 | +| explained_variance | -0.905 | +| learning_rate | 0.0001 | +| loss | -0.0975 | +| n_updates | 94370 | +| policy_gradient_loss | -0.0615 | +| value_loss | 0.000535 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.273 | +| time/ | | +| fps | 310 | +| iterations | 3386 | +| time_elapsed | 11175 | +| total_timesteps | 3467264 | +| train/ | | +| approx_kl | 2.0618677 | +| clip_fraction | 0.424 | +| clip_range | 0.2 | +| entropy_loss | -0.267 | +| explained_variance | -0.519 | +| learning_rate | 0.0001 | +| loss | -0.0843 | +| n_updates | 94380 | +| policy_gradient_loss | -0.0588 | +| value_loss | 0.000584 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.273 | +| time/ | | +| fps | 310 | +| iterations | 3387 | +| time_elapsed | 11179 | +| total_timesteps | 3468288 | +| train/ | | +| approx_kl | 2.361021 | +| clip_fraction | 0.403 | +| clip_range | 0.2 | +| entropy_loss | -0.254 | +| explained_variance | -1.14 | +| learning_rate | 0.0001 | +| loss | -0.0695 | +| n_updates | 94390 | +| policy_gradient_loss | -0.0562 | +| value_loss | 0.000672 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.271 | +| time/ | | +| fps | 310 | +| iterations | 3388 | +| time_elapsed | 11182 | +| total_timesteps | 3469312 | +| train/ | | +| approx_kl | 2.0991077 | +| clip_fraction | 0.448 | +| clip_range | 0.2 | +| entropy_loss | -0.309 | +| explained_variance | -2.25 | +| learning_rate | 0.0001 | +| loss | -0.0652 | +| n_updates | 94400 | +| policy_gradient_loss | -0.062 | +| value_loss | 0.000546 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.268 | +| time/ | | +| fps | 310 | +| iterations | 3389 | +| time_elapsed | 11185 | +| total_timesteps | 3470336 | +| train/ | | +| approx_kl | 1.9855983 | +| clip_fraction | 0.399 | +| clip_range | 0.2 | +| entropy_loss | -0.282 | +| explained_variance | -1.82 | +| learning_rate | 0.0001 | +| loss | -0.0593 | +| n_updates | 94410 | +| policy_gradient_loss | -0.0538 | +| value_loss | 0.000486 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.268 | +| time/ | | +| fps | 310 | +| iterations | 3390 | +| time_elapsed | 11188 | +| total_timesteps | 3471360 | +| train/ | | +| approx_kl | 1.9233141 | +| clip_fraction | 0.417 | +| clip_range | 0.2 | +| entropy_loss | -0.263 | +| explained_variance | -1 | +| learning_rate | 0.0001 | +| loss | -0.0773 | +| n_updates | 94420 | +| policy_gradient_loss | -0.048 | +| value_loss | 0.000704 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.269 | +| time/ | | +| fps | 310 | +| iterations | 3391 | +| time_elapsed | 11192 | +| total_timesteps | 3472384 | +| train/ | | +| approx_kl | 2.6797986 | +| clip_fraction | 0.447 | +| clip_range | 0.2 | +| entropy_loss | -0.295 | +| explained_variance | -1.34 | +| learning_rate | 0.0001 | +| loss | -0.0479 | +| n_updates | 94430 | +| policy_gradient_loss | -0.0526 | +| value_loss | 0.000665 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.272 | +| time/ | | +| fps | 310 | +| iterations | 3392 | +| time_elapsed | 11195 | +| total_timesteps | 3473408 | +| train/ | | +| approx_kl | 3.1278944 | +| clip_fraction | 0.403 | +| clip_range | 0.2 | +| entropy_loss | -0.25 | +| explained_variance | -2.55 | +| learning_rate | 0.0001 | +| loss | -0.0858 | +| n_updates | 94440 | +| policy_gradient_loss | -0.06 | +| value_loss | 0.000739 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.272 | +| time/ | | +| fps | 310 | +| iterations | 3393 | +| time_elapsed | 11198 | +| total_timesteps | 3474432 | +| train/ | | +| approx_kl | 2.493004 | +| clip_fraction | 0.418 | +| clip_range | 0.2 | +| entropy_loss | -0.244 | +| explained_variance | -1.46 | +| learning_rate | 0.0001 | +| loss | -0.0631 | +| n_updates | 94450 | +| policy_gradient_loss | -0.0629 | +| value_loss | 0.000747 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.272 | +| time/ | | +| fps | 310 | +| iterations | 3394 | +| time_elapsed | 11201 | +| total_timesteps | 3475456 | +| train/ | | +| approx_kl | 2.0467446 | +| clip_fraction | 0.453 | +| clip_range | 0.2 | +| entropy_loss | -0.329 | +| explained_variance | -2.29 | +| learning_rate | 0.0001 | +| loss | -0.0534 | +| n_updates | 94460 | +| policy_gradient_loss | -0.0595 | +| value_loss | 0.00045 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.265 | +| time/ | | +| fps | 310 | +| iterations | 3395 | +| time_elapsed | 11205 | +| total_timesteps | 3476480 | +| train/ | | +| approx_kl | 2.1192389 | +| clip_fraction | 0.445 | +| clip_range | 0.2 | +| entropy_loss | -0.281 | +| explained_variance | -1.92 | +| learning_rate | 0.0001 | +| loss | -0.106 | +| n_updates | 94470 | +| policy_gradient_loss | -0.0609 | +| value_loss | 0.000504 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.265 | +| time/ | | +| fps | 310 | +| iterations | 3396 | +| time_elapsed | 11208 | +| total_timesteps | 3477504 | +| train/ | | +| approx_kl | 2.020808 | +| clip_fraction | 0.389 | +| clip_range | 0.2 | +| entropy_loss | -0.276 | +| explained_variance | -1.13 | +| learning_rate | 0.0001 | +| loss | -0.0815 | +| n_updates | 94480 | +| policy_gradient_loss | -0.0516 | +| value_loss | 0.000544 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.265 | +| time/ | | +| fps | 310 | +| iterations | 3397 | +| time_elapsed | 11211 | +| total_timesteps | 3478528 | +| train/ | | +| approx_kl | 2.9072504 | +| clip_fraction | 0.439 | +| clip_range | 0.2 | +| entropy_loss | -0.281 | +| explained_variance | -2.41 | +| learning_rate | 0.0001 | +| loss | -0.107 | +| n_updates | 94490 | +| policy_gradient_loss | -0.055 | +| value_loss | 0.000331 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.263 | +| time/ | | +| fps | 310 | +| iterations | 3398 | +| time_elapsed | 11215 | +| total_timesteps | 3479552 | +| train/ | | +| approx_kl | 2.2625217 | +| clip_fraction | 0.415 | +| clip_range | 0.2 | +| entropy_loss | -0.27 | +| explained_variance | -0.457 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 94500 | +| policy_gradient_loss | -0.0559 | +| value_loss | 0.000474 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.259 | +| time/ | | +| fps | 310 | +| iterations | 3399 | +| time_elapsed | 11218 | +| total_timesteps | 3480576 | +| train/ | | +| approx_kl | 2.0360026 | +| clip_fraction | 0.429 | +| clip_range | 0.2 | +| entropy_loss | -0.3 | +| explained_variance | -2.34 | +| learning_rate | 0.0001 | +| loss | -0.0735 | +| n_updates | 94510 | +| policy_gradient_loss | -0.0559 | +| value_loss | 0.000592 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.26 | +| time/ | | +| fps | 310 | +| iterations | 3400 | +| time_elapsed | 11222 | +| total_timesteps | 3481600 | +| train/ | | +| approx_kl | 2.5399241 | +| clip_fraction | 0.395 | +| clip_range | 0.2 | +| entropy_loss | -0.269 | +| explained_variance | -2.37 | +| learning_rate | 0.0001 | +| loss | -0.0879 | +| n_updates | 94520 | +| policy_gradient_loss | -0.0497 | +| value_loss | 0.000635 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.26 | +| time/ | | +| fps | 310 | +| iterations | 3401 | +| time_elapsed | 11225 | +| total_timesteps | 3482624 | +| train/ | | +| approx_kl | 2.3526096 | +| clip_fraction | 0.393 | +| clip_range | 0.2 | +| entropy_loss | -0.283 | +| explained_variance | -0.991 | +| learning_rate | 0.0001 | +| loss | -0.0802 | +| n_updates | 94530 | +| policy_gradient_loss | -0.0511 | +| value_loss | 0.000407 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.259 | +| time/ | | +| fps | 310 | +| iterations | 3402 | +| time_elapsed | 11228 | +| total_timesteps | 3483648 | +| train/ | | +| approx_kl | 2.23528 | +| clip_fraction | 0.42 | +| clip_range | 0.2 | +| entropy_loss | -0.274 | +| explained_variance | -1.17 | +| learning_rate | 0.0001 | +| loss | -0.0667 | +| n_updates | 94540 | +| policy_gradient_loss | -0.058 | +| value_loss | 0.00049 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.256 | +| time/ | | +| fps | 310 | +| iterations | 3403 | +| time_elapsed | 11232 | +| total_timesteps | 3484672 | +| train/ | | +| approx_kl | 2.3561075 | +| clip_fraction | 0.407 | +| clip_range | 0.2 | +| entropy_loss | -0.254 | +| explained_variance | -2.39 | +| learning_rate | 0.0001 | +| loss | -0.0916 | +| n_updates | 94550 | +| policy_gradient_loss | -0.0577 | +| value_loss | 0.000698 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.256 | +| time/ | | +| fps | 310 | +| iterations | 3404 | +| time_elapsed | 11235 | +| total_timesteps | 3485696 | +| train/ | | +| approx_kl | 2.5360708 | +| clip_fraction | 0.417 | +| clip_range | 0.2 | +| entropy_loss | -0.262 | +| explained_variance | -2.07 | +| learning_rate | 0.0001 | +| loss | -0.0729 | +| n_updates | 94560 | +| policy_gradient_loss | -0.0533 | +| value_loss | 0.000621 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.259 | +| time/ | | +| fps | 310 | +| iterations | 3405 | +| time_elapsed | 11238 | +| total_timesteps | 3486720 | +| train/ | | +| approx_kl | 2.8306897 | +| clip_fraction | 0.42 | +| clip_range | 0.2 | +| entropy_loss | -0.239 | +| explained_variance | -1.41 | +| learning_rate | 0.0001 | +| loss | -0.0774 | +| n_updates | 94570 | +| policy_gradient_loss | -0.0608 | +| value_loss | 0.00092 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.259 | +| time/ | | +| fps | 310 | +| iterations | 3406 | +| time_elapsed | 11241 | +| total_timesteps | 3487744 | +| train/ | | +| approx_kl | 3.6528635 | +| clip_fraction | 0.441 | +| clip_range | 0.2 | +| entropy_loss | -0.263 | +| explained_variance | -0.581 | +| learning_rate | 0.0001 | +| loss | -0.0916 | +| n_updates | 94580 | +| policy_gradient_loss | -0.0562 | +| value_loss | 0.000644 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.262 | +| time/ | | +| fps | 310 | +| iterations | 3407 | +| time_elapsed | 11244 | +| total_timesteps | 3488768 | +| train/ | | +| approx_kl | 2.477319 | +| clip_fraction | 0.429 | +| clip_range | 0.2 | +| entropy_loss | -0.25 | +| explained_variance | -0.35 | +| learning_rate | 0.0001 | +| loss | -0.0733 | +| n_updates | 94590 | +| policy_gradient_loss | -0.0629 | +| value_loss | 0.000743 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.261 | +| time/ | | +| fps | 310 | +| iterations | 3408 | +| time_elapsed | 11247 | +| total_timesteps | 3489792 | +| train/ | | +| approx_kl | 2.6673412 | +| clip_fraction | 0.403 | +| clip_range | 0.2 | +| entropy_loss | -0.221 | +| explained_variance | -2.74 | +| learning_rate | 0.0001 | +| loss | -0.0737 | +| n_updates | 94600 | +| policy_gradient_loss | -0.0589 | +| value_loss | 0.000625 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.26 | +| time/ | | +| fps | 310 | +| iterations | 3409 | +| time_elapsed | 11250 | +| total_timesteps | 3490816 | +| train/ | | +| approx_kl | 2.6867683 | +| clip_fraction | 0.401 | +| clip_range | 0.2 | +| entropy_loss | -0.221 | +| explained_variance | -0.785 | +| learning_rate | 0.0001 | +| loss | -0.0778 | +| n_updates | 94610 | +| policy_gradient_loss | -0.0565 | +| value_loss | 0.000682 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.262 | +| time/ | | +| fps | 310 | +| iterations | 3410 | +| time_elapsed | 11254 | +| total_timesteps | 3491840 | +| train/ | | +| approx_kl | 2.4181376 | +| clip_fraction | 0.389 | +| clip_range | 0.2 | +| entropy_loss | -0.202 | +| explained_variance | -2.23 | +| learning_rate | 0.0001 | +| loss | -0.0277 | +| n_updates | 94620 | +| policy_gradient_loss | -0.0504 | +| value_loss | 0.000436 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.26 | +| time/ | | +| fps | 310 | +| iterations | 3411 | +| time_elapsed | 11257 | +| total_timesteps | 3492864 | +| train/ | | +| approx_kl | 1.6996796 | +| clip_fraction | 0.385 | +| clip_range | 0.2 | +| entropy_loss | -0.26 | +| explained_variance | -1.43 | +| learning_rate | 0.0001 | +| loss | -0.0211 | +| n_updates | 94630 | +| policy_gradient_loss | -0.0455 | +| value_loss | 0.00056 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.256 | +| time/ | | +| fps | 310 | +| iterations | 3412 | +| time_elapsed | 11260 | +| total_timesteps | 3493888 | +| train/ | | +| approx_kl | 2.1400545 | +| clip_fraction | 0.408 | +| clip_range | 0.2 | +| entropy_loss | -0.266 | +| explained_variance | -0.963 | +| learning_rate | 0.0001 | +| loss | -0.0799 | +| n_updates | 94640 | +| policy_gradient_loss | -0.0547 | +| value_loss | 0.000642 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.254 | +| time/ | | +| fps | 310 | +| iterations | 3413 | +| time_elapsed | 11264 | +| total_timesteps | 3494912 | +| train/ | | +| approx_kl | 2.5492866 | +| clip_fraction | 0.396 | +| clip_range | 0.2 | +| entropy_loss | -0.236 | +| explained_variance | -1.92 | +| learning_rate | 0.0001 | +| loss | -0.0721 | +| n_updates | 94650 | +| policy_gradient_loss | -0.0574 | +| value_loss | 0.000758 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.254 | +| time/ | | +| fps | 310 | +| iterations | 3414 | +| time_elapsed | 11267 | +| total_timesteps | 3495936 | +| train/ | | +| approx_kl | 2.9978454 | +| clip_fraction | 0.395 | +| clip_range | 0.2 | +| entropy_loss | -0.21 | +| explained_variance | -1.96 | +| learning_rate | 0.0001 | +| loss | -0.0899 | +| n_updates | 94660 | +| policy_gradient_loss | -0.0578 | +| value_loss | 0.000566 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.254 | +| time/ | | +| fps | 310 | +| iterations | 3415 | +| time_elapsed | 11270 | +| total_timesteps | 3496960 | +| train/ | | +| approx_kl | 1.8100669 | +| clip_fraction | 0.388 | +| clip_range | 0.2 | +| entropy_loss | -0.265 | +| explained_variance | -1.26 | +| learning_rate | 0.0001 | +| loss | -0.0682 | +| n_updates | 94670 | +| policy_gradient_loss | -0.0475 | +| value_loss | 0.000651 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.254 | +| time/ | | +| fps | 310 | +| iterations | 3416 | +| time_elapsed | 11274 | +| total_timesteps | 3497984 | +| train/ | | +| approx_kl | 2.589837 | +| clip_fraction | 0.375 | +| clip_range | 0.2 | +| entropy_loss | -0.239 | +| explained_variance | -1.3 | +| learning_rate | 0.0001 | +| loss | -0.0836 | +| n_updates | 94680 | +| policy_gradient_loss | -0.0555 | +| value_loss | 0.000511 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.254 | +| time/ | | +| fps | 310 | +| iterations | 3417 | +| time_elapsed | 11277 | +| total_timesteps | 3499008 | +| train/ | | +| approx_kl | 2.0996113 | +| clip_fraction | 0.379 | +| clip_range | 0.2 | +| entropy_loss | -0.232 | +| explained_variance | -1.3 | +| learning_rate | 0.0001 | +| loss | -0.0677 | +| n_updates | 94690 | +| policy_gradient_loss | -0.0378 | +| value_loss | 0.000356 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.257 | +| time/ | | +| fps | 310 | +| iterations | 3418 | +| time_elapsed | 11281 | +| total_timesteps | 3500032 | +| train/ | | +| approx_kl | 2.420494 | +| clip_fraction | 0.436 | +| clip_range | 0.2 | +| entropy_loss | -0.276 | +| explained_variance | -1.04 | +| learning_rate | 0.0001 | +| loss | -0.0624 | +| n_updates | 94700 | +| policy_gradient_loss | -0.0522 | +| value_loss | 0.000505 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.257 | +| time/ | | +| fps | 310 | +| iterations | 3419 | +| time_elapsed | 11284 | +| total_timesteps | 3501056 | +| train/ | | +| approx_kl | 4.030222 | +| clip_fraction | 0.397 | +| clip_range | 0.2 | +| entropy_loss | -0.269 | +| explained_variance | -1.31 | +| learning_rate | 0.0001 | +| loss | -0.065 | +| n_updates | 94710 | +| policy_gradient_loss | -0.0521 | +| value_loss | 0.000506 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.256 | +| time/ | | +| fps | 310 | +| iterations | 3420 | +| time_elapsed | 11288 | +| total_timesteps | 3502080 | +| train/ | | +| approx_kl | 2.750951 | +| clip_fraction | 0.42 | +| clip_range | 0.2 | +| entropy_loss | -0.237 | +| explained_variance | -0.931 | +| learning_rate | 0.0001 | +| loss | -0.0805 | +| n_updates | 94720 | +| policy_gradient_loss | -0.0567 | +| value_loss | 0.000526 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.261 | +| time/ | | +| fps | 310 | +| iterations | 3421 | +| time_elapsed | 11291 | +| total_timesteps | 3503104 | +| train/ | | +| approx_kl | 2.081159 | +| clip_fraction | 0.412 | +| clip_range | 0.2 | +| entropy_loss | -0.268 | +| explained_variance | -1.05 | +| learning_rate | 0.0001 | +| loss | -0.0827 | +| n_updates | 94730 | +| policy_gradient_loss | -0.055 | +| value_loss | 0.000933 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.267 | +| time/ | | +| fps | 310 | +| iterations | 3422 | +| time_elapsed | 11294 | +| total_timesteps | 3504128 | +| train/ | | +| approx_kl | 1.921915 | +| clip_fraction | 0.419 | +| clip_range | 0.2 | +| entropy_loss | -0.272 | +| explained_variance | -1.1 | +| learning_rate | 0.0001 | +| loss | -0.0804 | +| n_updates | 94740 | +| policy_gradient_loss | -0.0544 | +| value_loss | 0.000749 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.271 | +| time/ | | +| fps | 310 | +| iterations | 3423 | +| time_elapsed | 11298 | +| total_timesteps | 3505152 | +| train/ | | +| approx_kl | 2.1218522 | +| clip_fraction | 0.367 | +| clip_range | 0.2 | +| entropy_loss | -0.234 | +| explained_variance | -1.2 | +| learning_rate | 0.0001 | +| loss | -0.0759 | +| n_updates | 94750 | +| policy_gradient_loss | -0.0522 | +| value_loss | 0.00115 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.271 | +| time/ | | +| fps | 310 | +| iterations | 3424 | +| time_elapsed | 11301 | +| total_timesteps | 3506176 | +| train/ | | +| approx_kl | 2.7943149 | +| clip_fraction | 0.396 | +| clip_range | 0.2 | +| entropy_loss | -0.222 | +| explained_variance | -1.95 | +| learning_rate | 0.0001 | +| loss | -0.0714 | +| n_updates | 94760 | +| policy_gradient_loss | -0.0575 | +| value_loss | 0.000819 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.276 | +| time/ | | +| fps | 310 | +| iterations | 3425 | +| time_elapsed | 11304 | +| total_timesteps | 3507200 | +| train/ | | +| approx_kl | 2.7109816 | +| clip_fraction | 0.422 | +| clip_range | 0.2 | +| entropy_loss | -0.255 | +| explained_variance | -1.49 | +| learning_rate | 0.0001 | +| loss | -0.085 | +| n_updates | 94770 | +| policy_gradient_loss | -0.0633 | +| value_loss | 0.00066 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.276 | +| time/ | | +| fps | 310 | +| iterations | 3426 | +| time_elapsed | 11307 | +| total_timesteps | 3508224 | +| train/ | | +| approx_kl | 2.26537 | +| clip_fraction | 0.42 | +| clip_range | 0.2 | +| entropy_loss | -0.253 | +| explained_variance | -1.28 | +| learning_rate | 0.0001 | +| loss | -0.091 | +| n_updates | 94780 | +| policy_gradient_loss | -0.0513 | +| value_loss | 0.000726 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.276 | +| time/ | | +| fps | 310 | +| iterations | 3427 | +| time_elapsed | 11310 | +| total_timesteps | 3509248 | +| train/ | | +| approx_kl | 3.6110303 | +| clip_fraction | 0.438 | +| clip_range | 0.2 | +| entropy_loss | -0.258 | +| explained_variance | -1.35 | +| learning_rate | 0.0001 | +| loss | -0.0702 | +| n_updates | 94790 | +| policy_gradient_loss | -0.0593 | +| value_loss | 0.000507 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.278 | +| time/ | | +| fps | 310 | +| iterations | 3428 | +| time_elapsed | 11314 | +| total_timesteps | 3510272 | +| train/ | | +| approx_kl | 2.4332433 | +| clip_fraction | 0.414 | +| clip_range | 0.2 | +| entropy_loss | -0.26 | +| explained_variance | -0.936 | +| learning_rate | 0.0001 | +| loss | -0.0554 | +| n_updates | 94800 | +| policy_gradient_loss | -0.0555 | +| value_loss | 0.000596 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 310 | +| iterations | 3429 | +| time_elapsed | 11317 | +| total_timesteps | 3511296 | +| train/ | | +| approx_kl | 2.6369634 | +| clip_fraction | 0.421 | +| clip_range | 0.2 | +| entropy_loss | -0.233 | +| explained_variance | -0.886 | +| learning_rate | 0.0001 | +| loss | -0.0909 | +| n_updates | 94810 | +| policy_gradient_loss | -0.0615 | +| value_loss | 0.000606 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 310 | +| iterations | 3430 | +| time_elapsed | 11320 | +| total_timesteps | 3512320 | +| train/ | | +| approx_kl | 2.8913841 | +| clip_fraction | 0.398 | +| clip_range | 0.2 | +| entropy_loss | -0.217 | +| explained_variance | -3.07 | +| learning_rate | 0.0001 | +| loss | -0.0652 | +| n_updates | 94820 | +| policy_gradient_loss | -0.0586 | +| value_loss | 0.000888 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.28 | +| time/ | | +| fps | 310 | +| iterations | 3431 | +| time_elapsed | 11324 | +| total_timesteps | 3513344 | +| train/ | | +| approx_kl | 2.44082 | +| clip_fraction | 0.412 | +| clip_range | 0.2 | +| entropy_loss | -0.236 | +| explained_variance | -1.64 | +| learning_rate | 0.0001 | +| loss | -0.0558 | +| n_updates | 94830 | +| policy_gradient_loss | -0.0556 | +| value_loss | 0.000832 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.28 | +| time/ | | +| fps | 310 | +| iterations | 3432 | +| time_elapsed | 11327 | +| total_timesteps | 3514368 | +| train/ | | +| approx_kl | 2.8182073 | +| clip_fraction | 0.409 | +| clip_range | 0.2 | +| entropy_loss | -0.259 | +| explained_variance | -1.52 | +| learning_rate | 0.0001 | +| loss | -0.0828 | +| n_updates | 94840 | +| policy_gradient_loss | -0.0575 | +| value_loss | 0.000627 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.281 | +| time/ | | +| fps | 310 | +| iterations | 3433 | +| time_elapsed | 11330 | +| total_timesteps | 3515392 | +| train/ | | +| approx_kl | 3.5069728 | +| clip_fraction | 0.446 | +| clip_range | 0.2 | +| entropy_loss | -0.312 | +| explained_variance | -2.24 | +| learning_rate | 0.0001 | +| loss | -0.11 | +| n_updates | 94850 | +| policy_gradient_loss | -0.0563 | +| value_loss | 0.000488 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 310 | +| iterations | 3434 | +| time_elapsed | 11334 | +| total_timesteps | 3516416 | +| train/ | | +| approx_kl | 2.365312 | +| clip_fraction | 0.436 | +| clip_range | 0.2 | +| entropy_loss | -0.273 | +| explained_variance | -1.58 | +| learning_rate | 0.0001 | +| loss | -0.0889 | +| n_updates | 94860 | +| policy_gradient_loss | -0.0626 | +| value_loss | 0.000541 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 310 | +| iterations | 3435 | +| time_elapsed | 11337 | +| total_timesteps | 3517440 | +| train/ | | +| approx_kl | 2.4380085 | +| clip_fraction | 0.408 | +| clip_range | 0.2 | +| entropy_loss | -0.258 | +| explained_variance | -0.672 | +| learning_rate | 0.0001 | +| loss | -0.0382 | +| n_updates | 94870 | +| policy_gradient_loss | -0.0528 | +| value_loss | 0.000465 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 310 | +| iterations | 3436 | +| time_elapsed | 11340 | +| total_timesteps | 3518464 | +| train/ | | +| approx_kl | 2.34143 | +| clip_fraction | 0.414 | +| clip_range | 0.2 | +| entropy_loss | -0.251 | +| explained_variance | -1.18 | +| learning_rate | 0.0001 | +| loss | -0.0496 | +| n_updates | 94880 | +| policy_gradient_loss | -0.0608 | +| value_loss | 0.000847 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 310 | +| iterations | 3437 | +| time_elapsed | 11344 | +| total_timesteps | 3519488 | +| train/ | | +| approx_kl | 1.8537209 | +| clip_fraction | 0.369 | +| clip_range | 0.2 | +| entropy_loss | -0.219 | +| explained_variance | -1.21 | +| learning_rate | 0.0001 | +| loss | -0.078 | +| n_updates | 94890 | +| policy_gradient_loss | -0.0522 | +| value_loss | 0.000871 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.285 | +| time/ | | +| fps | 310 | +| iterations | 3438 | +| time_elapsed | 11347 | +| total_timesteps | 3520512 | +| train/ | | +| approx_kl | 1.708937 | +| clip_fraction | 0.41 | +| clip_range | 0.2 | +| entropy_loss | -0.277 | +| explained_variance | -1.92 | +| learning_rate | 0.0001 | +| loss | -0.0915 | +| n_updates | 94900 | +| policy_gradient_loss | -0.0569 | +| value_loss | 0.000688 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 310 | +| iterations | 3439 | +| time_elapsed | 11350 | +| total_timesteps | 3521536 | +| train/ | | +| approx_kl | 2.488854 | +| clip_fraction | 0.431 | +| clip_range | 0.2 | +| entropy_loss | -0.268 | +| explained_variance | -1.62 | +| learning_rate | 0.0001 | +| loss | -0.0873 | +| n_updates | 94910 | +| policy_gradient_loss | -0.0569 | +| value_loss | 0.000705 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 310 | +| iterations | 3440 | +| time_elapsed | 11353 | +| total_timesteps | 3522560 | +| train/ | | +| approx_kl | 2.2359874 | +| clip_fraction | 0.409 | +| clip_range | 0.2 | +| entropy_loss | -0.246 | +| explained_variance | -3.23 | +| learning_rate | 0.0001 | +| loss | -0.0787 | +| n_updates | 94920 | +| policy_gradient_loss | -0.0584 | +| value_loss | 0.000446 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 310 | +| iterations | 3441 | +| time_elapsed | 11357 | +| total_timesteps | 3523584 | +| train/ | | +| approx_kl | 3.2333949 | +| clip_fraction | 0.449 | +| clip_range | 0.2 | +| entropy_loss | -0.276 | +| explained_variance | -1.15 | +| learning_rate | 0.0001 | +| loss | -0.0796 | +| n_updates | 94930 | +| policy_gradient_loss | -0.0592 | +| value_loss | 0.000551 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.283 | +| time/ | | +| fps | 310 | +| iterations | 3442 | +| time_elapsed | 11360 | +| total_timesteps | 3524608 | +| train/ | | +| approx_kl | 2.0828583 | +| clip_fraction | 0.39 | +| clip_range | 0.2 | +| entropy_loss | -0.257 | +| explained_variance | -1.59 | +| learning_rate | 0.0001 | +| loss | -0.0724 | +| n_updates | 94940 | +| policy_gradient_loss | -0.0563 | +| value_loss | 0.000704 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.283 | +| time/ | | +| fps | 310 | +| iterations | 3443 | +| time_elapsed | 11363 | +| total_timesteps | 3525632 | +| train/ | | +| approx_kl | 2.2921767 | +| clip_fraction | 0.375 | +| clip_range | 0.2 | +| entropy_loss | -0.228 | +| explained_variance | -1.48 | +| learning_rate | 0.0001 | +| loss | -0.0588 | +| n_updates | 94950 | +| policy_gradient_loss | -0.0549 | +| value_loss | 0.000576 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.286 | +| time/ | | +| fps | 310 | +| iterations | 3444 | +| time_elapsed | 11366 | +| total_timesteps | 3526656 | +| train/ | | +| approx_kl | 2.460155 | +| clip_fraction | 0.418 | +| clip_range | 0.2 | +| entropy_loss | -0.248 | +| explained_variance | -1.12 | +| learning_rate | 0.0001 | +| loss | -0.0854 | +| n_updates | 94960 | +| policy_gradient_loss | -0.0543 | +| value_loss | 0.00068 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.289 | +| time/ | | +| fps | 310 | +| iterations | 3445 | +| time_elapsed | 11369 | +| total_timesteps | 3527680 | +| train/ | | +| approx_kl | 3.9524155 | +| clip_fraction | 0.382 | +| clip_range | 0.2 | +| entropy_loss | -0.246 | +| explained_variance | -0.799 | +| learning_rate | 0.0001 | +| loss | -0.0804 | +| n_updates | 94970 | +| policy_gradient_loss | -0.0543 | +| value_loss | 0.00067 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.289 | +| time/ | | +| fps | 310 | +| iterations | 3446 | +| time_elapsed | 11372 | +| total_timesteps | 3528704 | +| train/ | | +| approx_kl | 2.1513643 | +| clip_fraction | 0.4 | +| clip_range | 0.2 | +| entropy_loss | -0.262 | +| explained_variance | -1 | +| learning_rate | 0.0001 | +| loss | -0.0663 | +| n_updates | 94980 | +| policy_gradient_loss | -0.0532 | +| value_loss | 0.000631 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.289 | +| time/ | | +| fps | 310 | +| iterations | 3447 | +| time_elapsed | 11376 | +| total_timesteps | 3529728 | +| train/ | | +| approx_kl | 1.8696761 | +| clip_fraction | 0.388 | +| clip_range | 0.2 | +| entropy_loss | -0.241 | +| explained_variance | -0.551 | +| learning_rate | 0.0001 | +| loss | -0.0476 | +| n_updates | 94990 | +| policy_gradient_loss | -0.0514 | +| value_loss | 0.000927 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.289 | +| time/ | | +| fps | 310 | +| iterations | 3448 | +| time_elapsed | 11379 | +| total_timesteps | 3530752 | +| train/ | | +| approx_kl | 2.0909257 | +| clip_fraction | 0.403 | +| clip_range | 0.2 | +| entropy_loss | -0.245 | +| explained_variance | -2.35 | +| learning_rate | 0.0001 | +| loss | -0.0762 | +| n_updates | 95000 | +| policy_gradient_loss | -0.0603 | +| value_loss | 0.000672 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.287 | +| time/ | | +| fps | 310 | +| iterations | 3449 | +| time_elapsed | 11382 | +| total_timesteps | 3531776 | +| train/ | | +| approx_kl | 2.520704 | +| clip_fraction | 0.415 | +| clip_range | 0.2 | +| entropy_loss | -0.279 | +| explained_variance | -1.49 | +| learning_rate | 0.0001 | +| loss | -0.0717 | +| n_updates | 95010 | +| policy_gradient_loss | -0.0569 | +| value_loss | 0.000584 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.287 | +| time/ | | +| fps | 310 | +| iterations | 3450 | +| time_elapsed | 11386 | +| total_timesteps | 3532800 | +| train/ | | +| approx_kl | 2.4567213 | +| clip_fraction | 0.403 | +| clip_range | 0.2 | +| entropy_loss | -0.239 | +| explained_variance | -2.43 | +| learning_rate | 0.0001 | +| loss | -0.0849 | +| n_updates | 95020 | +| policy_gradient_loss | -0.0588 | +| value_loss | 0.000545 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.287 | +| time/ | | +| fps | 310 | +| iterations | 3451 | +| time_elapsed | 11390 | +| total_timesteps | 3533824 | +| train/ | | +| approx_kl | 3.0212018 | +| clip_fraction | 0.435 | +| clip_range | 0.2 | +| entropy_loss | -0.289 | +| explained_variance | -0.23 | +| learning_rate | 0.0001 | +| loss | -0.091 | +| n_updates | 95030 | +| policy_gradient_loss | -0.0566 | +| value_loss | 0.00057 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.287 | +| time/ | | +| fps | 310 | +| iterations | 3452 | +| time_elapsed | 11393 | +| total_timesteps | 3534848 | +| train/ | | +| approx_kl | 2.0159822 | +| clip_fraction | 0.367 | +| clip_range | 0.2 | +| entropy_loss | -0.235 | +| explained_variance | -1.11 | +| learning_rate | 0.0001 | +| loss | -0.0696 | +| n_updates | 95040 | +| policy_gradient_loss | -0.0447 | +| value_loss | 0.000684 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.284 | +| time/ | | +| fps | 310 | +| iterations | 3453 | +| time_elapsed | 11397 | +| total_timesteps | 3535872 | +| train/ | | +| approx_kl | 2.5150015 | +| clip_fraction | 0.441 | +| clip_range | 0.2 | +| entropy_loss | -0.254 | +| explained_variance | -1.59 | +| learning_rate | 0.0001 | +| loss | -0.0876 | +| n_updates | 95050 | +| policy_gradient_loss | -0.0608 | +| value_loss | 0.0007 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 310 | +| iterations | 3454 | +| time_elapsed | 11400 | +| total_timesteps | 3536896 | +| train/ | | +| approx_kl | 1.8886858 | +| clip_fraction | 0.401 | +| clip_range | 0.2 | +| entropy_loss | -0.248 | +| explained_variance | -1.9 | +| learning_rate | 0.0001 | +| loss | -0.0609 | +| n_updates | 95060 | +| policy_gradient_loss | -0.0531 | +| value_loss | 0.000412 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.278 | +| time/ | | +| fps | 310 | +| iterations | 3455 | +| time_elapsed | 11404 | +| total_timesteps | 3537920 | +| train/ | | +| approx_kl | 2.224666 | +| clip_fraction | 0.391 | +| clip_range | 0.2 | +| entropy_loss | -0.232 | +| explained_variance | -1.19 | +| learning_rate | 0.0001 | +| loss | -0.0601 | +| n_updates | 95070 | +| policy_gradient_loss | -0.0509 | +| value_loss | 0.000621 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.278 | +| time/ | | +| fps | 310 | +| iterations | 3456 | +| time_elapsed | 11408 | +| total_timesteps | 3538944 | +| train/ | | +| approx_kl | 2.2160466 | +| clip_fraction | 0.418 | +| clip_range | 0.2 | +| entropy_loss | -0.267 | +| explained_variance | -0.623 | +| learning_rate | 0.0001 | +| loss | -0.0805 | +| n_updates | 95080 | +| policy_gradient_loss | -0.0547 | +| value_loss | 0.000664 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.274 | +| time/ | | +| fps | 310 | +| iterations | 3457 | +| time_elapsed | 11411 | +| total_timesteps | 3539968 | +| train/ | | +| approx_kl | 1.8039628 | +| clip_fraction | 0.39 | +| clip_range | 0.2 | +| entropy_loss | -0.254 | +| explained_variance | -1.54 | +| learning_rate | 0.0001 | +| loss | -0.0703 | +| n_updates | 95090 | +| policy_gradient_loss | -0.0542 | +| value_loss | 0.000565 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.273 | +| time/ | | +| fps | 310 | +| iterations | 3458 | +| time_elapsed | 11414 | +| total_timesteps | 3540992 | +| train/ | | +| approx_kl | 1.8101642 | +| clip_fraction | 0.396 | +| clip_range | 0.2 | +| entropy_loss | -0.269 | +| explained_variance | -1.78 | +| learning_rate | 0.0001 | +| loss | -0.0666 | +| n_updates | 95100 | +| policy_gradient_loss | -0.0557 | +| value_loss | 0.000622 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.273 | +| time/ | | +| fps | 310 | +| iterations | 3459 | +| time_elapsed | 11417 | +| total_timesteps | 3542016 | +| train/ | | +| approx_kl | 2.3815432 | +| clip_fraction | 0.456 | +| clip_range | 0.2 | +| entropy_loss | -0.267 | +| explained_variance | -1.37 | +| learning_rate | 0.0001 | +| loss | -0.106 | +| n_updates | 95110 | +| policy_gradient_loss | -0.0619 | +| value_loss | 0.000794 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.28 | +| time/ | | +| fps | 310 | +| iterations | 3460 | +| time_elapsed | 11420 | +| total_timesteps | 3543040 | +| train/ | | +| approx_kl | 1.7521245 | +| clip_fraction | 0.418 | +| clip_range | 0.2 | +| entropy_loss | -0.289 | +| explained_variance | -1.23 | +| learning_rate | 0.0001 | +| loss | -0.0746 | +| n_updates | 95120 | +| policy_gradient_loss | -0.058 | +| value_loss | 0.000467 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.28 | +| time/ | | +| fps | 310 | +| iterations | 3461 | +| time_elapsed | 11423 | +| total_timesteps | 3544064 | +| train/ | | +| approx_kl | 2.4975522 | +| clip_fraction | 0.412 | +| clip_range | 0.2 | +| entropy_loss | -0.273 | +| explained_variance | -1.39 | +| learning_rate | 0.0001 | +| loss | -0.0798 | +| n_updates | 95130 | +| policy_gradient_loss | -0.0531 | +| value_loss | 0.000496 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.278 | +| time/ | | +| fps | 310 | +| iterations | 3462 | +| time_elapsed | 11427 | +| total_timesteps | 3545088 | +| train/ | | +| approx_kl | 2.9043689 | +| clip_fraction | 0.485 | +| clip_range | 0.2 | +| entropy_loss | -0.325 | +| explained_variance | -1.62 | +| learning_rate | 0.0001 | +| loss | -0.108 | +| n_updates | 95140 | +| policy_gradient_loss | -0.0675 | +| value_loss | 0.000567 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.277 | +| time/ | | +| fps | 310 | +| iterations | 3463 | +| time_elapsed | 11430 | +| total_timesteps | 3546112 | +| train/ | | +| approx_kl | 2.3858535 | +| clip_fraction | 0.415 | +| clip_range | 0.2 | +| entropy_loss | -0.226 | +| explained_variance | -2.59 | +| learning_rate | 0.0001 | +| loss | -0.0812 | +| n_updates | 95150 | +| policy_gradient_loss | -0.0685 | +| value_loss | 0.000693 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.274 | +| time/ | | +| fps | 310 | +| iterations | 3464 | +| time_elapsed | 11433 | +| total_timesteps | 3547136 | +| train/ | | +| approx_kl | 2.3421023 | +| clip_fraction | 0.397 | +| clip_range | 0.2 | +| entropy_loss | -0.252 | +| explained_variance | -1.82 | +| learning_rate | 0.0001 | +| loss | -0.0771 | +| n_updates | 95160 | +| policy_gradient_loss | -0.0533 | +| value_loss | 0.00047 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.274 | +| time/ | | +| fps | 310 | +| iterations | 3465 | +| time_elapsed | 11436 | +| total_timesteps | 3548160 | +| train/ | | +| approx_kl | 1.8496735 | +| clip_fraction | 0.394 | +| clip_range | 0.2 | +| entropy_loss | -0.266 | +| explained_variance | -0.8 | +| learning_rate | 0.0001 | +| loss | -0.0934 | +| n_updates | 95170 | +| policy_gradient_loss | -0.0452 | +| value_loss | 0.000566 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.277 | +| time/ | | +| fps | 310 | +| iterations | 3466 | +| time_elapsed | 11440 | +| total_timesteps | 3549184 | +| train/ | | +| approx_kl | 2.2522624 | +| clip_fraction | 0.4 | +| clip_range | 0.2 | +| entropy_loss | -0.253 | +| explained_variance | -0.837 | +| learning_rate | 0.0001 | +| loss | -0.0712 | +| n_updates | 95180 | +| policy_gradient_loss | -0.0552 | +| value_loss | 0.000567 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.278 | +| time/ | | +| fps | 310 | +| iterations | 3467 | +| time_elapsed | 11443 | +| total_timesteps | 3550208 | +| train/ | | +| approx_kl | 2.2169719 | +| clip_fraction | 0.376 | +| clip_range | 0.2 | +| entropy_loss | -0.224 | +| explained_variance | -0.568 | +| learning_rate | 0.0001 | +| loss | -0.0721 | +| n_updates | 95190 | +| policy_gradient_loss | -0.0566 | +| value_loss | 0.000677 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 310 | +| iterations | 3468 | +| time_elapsed | 11446 | +| total_timesteps | 3551232 | +| train/ | | +| approx_kl | 2.4627967 | +| clip_fraction | 0.413 | +| clip_range | 0.2 | +| entropy_loss | -0.276 | +| explained_variance | -1.32 | +| learning_rate | 0.0001 | +| loss | -0.0969 | +| n_updates | 95200 | +| policy_gradient_loss | -0.0578 | +| value_loss | 0.0008 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.285 | +| time/ | | +| fps | 310 | +| iterations | 3469 | +| time_elapsed | 11450 | +| total_timesteps | 3552256 | +| train/ | | +| approx_kl | 1.7824543 | +| clip_fraction | 0.419 | +| clip_range | 0.2 | +| entropy_loss | -0.298 | +| explained_variance | -1.51 | +| learning_rate | 0.0001 | +| loss | -0.0593 | +| n_updates | 95210 | +| policy_gradient_loss | -0.0537 | +| value_loss | 0.000653 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.285 | +| time/ | | +| fps | 310 | +| iterations | 3470 | +| time_elapsed | 11453 | +| total_timesteps | 3553280 | +| train/ | | +| approx_kl | 2.743065 | +| clip_fraction | 0.47 | +| clip_range | 0.2 | +| entropy_loss | -0.308 | +| explained_variance | -1.06 | +| learning_rate | 0.0001 | +| loss | -0.0808 | +| n_updates | 95220 | +| policy_gradient_loss | -0.0594 | +| value_loss | 0.000681 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.286 | +| time/ | | +| fps | 310 | +| iterations | 3471 | +| time_elapsed | 11457 | +| total_timesteps | 3554304 | +| train/ | | +| approx_kl | 1.8450494 | +| clip_fraction | 0.42 | +| clip_range | 0.2 | +| entropy_loss | -0.273 | +| explained_variance | -0.833 | +| learning_rate | 0.0001 | +| loss | -0.0821 | +| n_updates | 95230 | +| policy_gradient_loss | -0.0637 | +| value_loss | 0.000613 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.288 | +| time/ | | +| fps | 310 | +| iterations | 3472 | +| time_elapsed | 11460 | +| total_timesteps | 3555328 | +| train/ | | +| approx_kl | 2.187663 | +| clip_fraction | 0.41 | +| clip_range | 0.2 | +| entropy_loss | -0.25 | +| explained_variance | -1.62 | +| learning_rate | 0.0001 | +| loss | -0.0777 | +| n_updates | 95240 | +| policy_gradient_loss | -0.0509 | +| value_loss | 0.000441 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.288 | +| time/ | | +| fps | 310 | +| iterations | 3473 | +| time_elapsed | 11464 | +| total_timesteps | 3556352 | +| train/ | | +| approx_kl | 2.354189 | +| clip_fraction | 0.424 | +| clip_range | 0.2 | +| entropy_loss | -0.272 | +| explained_variance | -0.979 | +| learning_rate | 0.0001 | +| loss | -0.0765 | +| n_updates | 95250 | +| policy_gradient_loss | -0.0578 | +| value_loss | 0.000645 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.285 | +| time/ | | +| fps | 310 | +| iterations | 3474 | +| time_elapsed | 11467 | +| total_timesteps | 3557376 | +| train/ | | +| approx_kl | 2.530604 | +| clip_fraction | 0.445 | +| clip_range | 0.2 | +| entropy_loss | -0.312 | +| explained_variance | -1.21 | +| learning_rate | 0.0001 | +| loss | -0.0699 | +| n_updates | 95260 | +| policy_gradient_loss | -0.0572 | +| value_loss | 0.00057 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.283 | +| time/ | | +| fps | 310 | +| iterations | 3475 | +| time_elapsed | 11470 | +| total_timesteps | 3558400 | +| train/ | | +| approx_kl | 2.3801422 | +| clip_fraction | 0.413 | +| clip_range | 0.2 | +| entropy_loss | -0.274 | +| explained_variance | -1.91 | +| learning_rate | 0.0001 | +| loss | -0.0742 | +| n_updates | 95270 | +| policy_gradient_loss | -0.0537 | +| value_loss | 0.000484 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.28 | +| time/ | | +| fps | 310 | +| iterations | 3476 | +| time_elapsed | 11474 | +| total_timesteps | 3559424 | +| train/ | | +| approx_kl | 2.4709163 | +| clip_fraction | 0.419 | +| clip_range | 0.2 | +| entropy_loss | -0.274 | +| explained_variance | -1.75 | +| learning_rate | 0.0001 | +| loss | -0.0692 | +| n_updates | 95280 | +| policy_gradient_loss | -0.0585 | +| value_loss | 0.000511 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.28 | +| time/ | | +| fps | 310 | +| iterations | 3477 | +| time_elapsed | 11477 | +| total_timesteps | 3560448 | +| train/ | | +| approx_kl | 1.8321195 | +| clip_fraction | 0.385 | +| clip_range | 0.2 | +| entropy_loss | -0.252 | +| explained_variance | -2.49 | +| learning_rate | 0.0001 | +| loss | -0.0689 | +| n_updates | 95290 | +| policy_gradient_loss | -0.0541 | +| value_loss | 0.000611 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.277 | +| time/ | | +| fps | 310 | +| iterations | 3478 | +| time_elapsed | 11480 | +| total_timesteps | 3561472 | +| train/ | | +| approx_kl | 2.020968 | +| clip_fraction | 0.453 | +| clip_range | 0.2 | +| entropy_loss | -0.31 | +| explained_variance | -5.05 | +| learning_rate | 0.0001 | +| loss | -0.0981 | +| n_updates | 95300 | +| policy_gradient_loss | -0.0665 | +| value_loss | 0.000349 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.273 | +| time/ | | +| fps | 310 | +| iterations | 3479 | +| time_elapsed | 11483 | +| total_timesteps | 3562496 | +| train/ | | +| approx_kl | 1.8838423 | +| clip_fraction | 0.377 | +| clip_range | 0.2 | +| entropy_loss | -0.262 | +| explained_variance | -0.613 | +| learning_rate | 0.0001 | +| loss | -0.0941 | +| n_updates | 95310 | +| policy_gradient_loss | -0.0517 | +| value_loss | 0.000403 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.267 | +| time/ | | +| fps | 310 | +| iterations | 3480 | +| time_elapsed | 11486 | +| total_timesteps | 3563520 | +| train/ | | +| approx_kl | 2.6567464 | +| clip_fraction | 0.431 | +| clip_range | 0.2 | +| entropy_loss | -0.267 | +| explained_variance | -1.45 | +| learning_rate | 0.0001 | +| loss | -0.0627 | +| n_updates | 95320 | +| policy_gradient_loss | -0.0567 | +| value_loss | 0.000438 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.27 | +| time/ | | +| fps | 310 | +| iterations | 3481 | +| time_elapsed | 11489 | +| total_timesteps | 3564544 | +| train/ | | +| approx_kl | 2.0378582 | +| clip_fraction | 0.416 | +| clip_range | 0.2 | +| entropy_loss | -0.271 | +| explained_variance | -0.673 | +| learning_rate | 0.0001 | +| loss | -0.0768 | +| n_updates | 95330 | +| policy_gradient_loss | -0.0582 | +| value_loss | 0.000538 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.27 | +| time/ | | +| fps | 310 | +| iterations | 3482 | +| time_elapsed | 11493 | +| total_timesteps | 3565568 | +| train/ | | +| approx_kl | 1.7574319 | +| clip_fraction | 0.399 | +| clip_range | 0.2 | +| entropy_loss | -0.265 | +| explained_variance | -1.6 | +| learning_rate | 0.0001 | +| loss | -0.0684 | +| n_updates | 95340 | +| policy_gradient_loss | -0.00678 | +| value_loss | 0.000569 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.264 | +| time/ | | +| fps | 310 | +| iterations | 3483 | +| time_elapsed | 11496 | +| total_timesteps | 3566592 | +| train/ | | +| approx_kl | 2.3436437 | +| clip_fraction | 0.444 | +| clip_range | 0.2 | +| entropy_loss | -0.32 | +| explained_variance | -2.96 | +| learning_rate | 0.0001 | +| loss | -0.0695 | +| n_updates | 95350 | +| policy_gradient_loss | -0.061 | +| value_loss | 0.000293 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.267 | +| time/ | | +| fps | 310 | +| iterations | 3484 | +| time_elapsed | 11499 | +| total_timesteps | 3567616 | +| train/ | | +| approx_kl | 1.8020363 | +| clip_fraction | 0.416 | +| clip_range | 0.2 | +| entropy_loss | -0.302 | +| explained_variance | -0.622 | +| learning_rate | 0.0001 | +| loss | -0.0801 | +| n_updates | 95360 | +| policy_gradient_loss | -0.055 | +| value_loss | 0.000696 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.267 | +| time/ | | +| fps | 310 | +| iterations | 3485 | +| time_elapsed | 11503 | +| total_timesteps | 3568640 | +| train/ | | +| approx_kl | 1.9643451 | +| clip_fraction | 0.403 | +| clip_range | 0.2 | +| entropy_loss | -0.257 | +| explained_variance | -1.03 | +| learning_rate | 0.0001 | +| loss | -0.0775 | +| n_updates | 95370 | +| policy_gradient_loss | -0.0577 | +| value_loss | 0.000706 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.267 | +| time/ | | +| fps | 310 | +| iterations | 3486 | +| time_elapsed | 11506 | +| total_timesteps | 3569664 | +| train/ | | +| approx_kl | 1.9283993 | +| clip_fraction | 0.427 | +| clip_range | 0.2 | +| entropy_loss | -0.286 | +| explained_variance | -1.99 | +| learning_rate | 0.0001 | +| loss | -0.0938 | +| n_updates | 95380 | +| policy_gradient_loss | -0.0594 | +| value_loss | 0.000652 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.266 | +| time/ | | +| fps | 310 | +| iterations | 3487 | +| time_elapsed | 11510 | +| total_timesteps | 3570688 | +| train/ | | +| approx_kl | 2.0518234 | +| clip_fraction | 0.43 | +| clip_range | 0.2 | +| entropy_loss | -0.283 | +| explained_variance | -0.297 | +| learning_rate | 0.0001 | +| loss | -0.0802 | +| n_updates | 95390 | +| policy_gradient_loss | -0.0558 | +| value_loss | 0.00123 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.266 | +| time/ | | +| fps | 310 | +| iterations | 3488 | +| time_elapsed | 11513 | +| total_timesteps | 3571712 | +| train/ | | +| approx_kl | 2.2330027 | +| clip_fraction | 0.422 | +| clip_range | 0.2 | +| entropy_loss | -0.293 | +| explained_variance | -2.12 | +| learning_rate | 0.0001 | +| loss | -0.07 | +| n_updates | 95400 | +| policy_gradient_loss | -0.0601 | +| value_loss | 0.000776 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.266 | +| time/ | | +| fps | 310 | +| iterations | 3489 | +| time_elapsed | 11517 | +| total_timesteps | 3572736 | +| train/ | | +| approx_kl | 2.0040247 | +| clip_fraction | 0.433 | +| clip_range | 0.2 | +| entropy_loss | -0.31 | +| explained_variance | -4.25 | +| learning_rate | 0.0001 | +| loss | -0.064 | +| n_updates | 95410 | +| policy_gradient_loss | -0.0375 | +| value_loss | 0.000396 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.266 | +| time/ | | +| fps | 310 | +| iterations | 3490 | +| time_elapsed | 11520 | +| total_timesteps | 3573760 | +| train/ | | +| approx_kl | 3.8131886 | +| clip_fraction | 0.416 | +| clip_range | 0.2 | +| entropy_loss | -0.271 | +| explained_variance | -3.11 | +| learning_rate | 0.0001 | +| loss | -0.0758 | +| n_updates | 95420 | +| policy_gradient_loss | -0.058 | +| value_loss | 0.000686 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.27 | +| time/ | | +| fps | 310 | +| iterations | 3491 | +| time_elapsed | 11523 | +| total_timesteps | 3574784 | +| train/ | | +| approx_kl | 2.5110111 | +| clip_fraction | 0.449 | +| clip_range | 0.2 | +| entropy_loss | -0.287 | +| explained_variance | -2.51 | +| learning_rate | 0.0001 | +| loss | -0.0749 | +| n_updates | 95430 | +| policy_gradient_loss | -0.0616 | +| value_loss | 0.000521 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.266 | +| time/ | | +| fps | 310 | +| iterations | 3492 | +| time_elapsed | 11527 | +| total_timesteps | 3575808 | +| train/ | | +| approx_kl | 2.60047 | +| clip_fraction | 0.448 | +| clip_range | 0.2 | +| entropy_loss | -0.288 | +| explained_variance | -0.789 | +| learning_rate | 0.0001 | +| loss | -0.0968 | +| n_updates | 95440 | +| policy_gradient_loss | -0.0611 | +| value_loss | 0.000689 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.266 | +| time/ | | +| fps | 310 | +| iterations | 3493 | +| time_elapsed | 11530 | +| total_timesteps | 3576832 | +| train/ | | +| approx_kl | 2.614778 | +| clip_fraction | 0.426 | +| clip_range | 0.2 | +| entropy_loss | -0.257 | +| explained_variance | -5.81 | +| learning_rate | 0.0001 | +| loss | -0.0645 | +| n_updates | 95450 | +| policy_gradient_loss | -0.0621 | +| value_loss | 0.000427 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.262 | +| time/ | | +| fps | 310 | +| iterations | 3494 | +| time_elapsed | 11533 | +| total_timesteps | 3577856 | +| train/ | | +| approx_kl | 2.3972073 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.294 | +| explained_variance | -1.15 | +| learning_rate | 0.0001 | +| loss | -0.0845 | +| n_updates | 95460 | +| policy_gradient_loss | -0.06 | +| value_loss | 0.000533 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.262 | +| time/ | | +| fps | 310 | +| iterations | 3495 | +| time_elapsed | 11537 | +| total_timesteps | 3578880 | +| train/ | | +| approx_kl | 1.7394937 | +| clip_fraction | 0.376 | +| clip_range | 0.2 | +| entropy_loss | -0.247 | +| explained_variance | -0.93 | +| learning_rate | 0.0001 | +| loss | -0.054 | +| n_updates | 95470 | +| policy_gradient_loss | -0.0453 | +| value_loss | 0.000514 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.264 | +| time/ | | +| fps | 310 | +| iterations | 3496 | +| time_elapsed | 11540 | +| total_timesteps | 3579904 | +| train/ | | +| approx_kl | 2.6238637 | +| clip_fraction | 0.436 | +| clip_range | 0.2 | +| entropy_loss | -0.285 | +| explained_variance | -1.21 | +| learning_rate | 0.0001 | +| loss | -0.0679 | +| n_updates | 95480 | +| policy_gradient_loss | -0.0598 | +| value_loss | 0.000563 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.262 | +| time/ | | +| fps | 310 | +| iterations | 3497 | +| time_elapsed | 11543 | +| total_timesteps | 3580928 | +| train/ | | +| approx_kl | 1.6537331 | +| clip_fraction | 0.408 | +| clip_range | 0.2 | +| entropy_loss | -0.278 | +| explained_variance | -6.04 | +| learning_rate | 0.0001 | +| loss | -0.0532 | +| n_updates | 95490 | +| policy_gradient_loss | -0.0602 | +| value_loss | 0.000633 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.262 | +| time/ | | +| fps | 310 | +| iterations | 3498 | +| time_elapsed | 11546 | +| total_timesteps | 3581952 | +| train/ | | +| approx_kl | 1.6515504 | +| clip_fraction | 0.429 | +| clip_range | 0.2 | +| entropy_loss | -0.348 | +| explained_variance | -1.82 | +| learning_rate | 0.0001 | +| loss | -0.0673 | +| n_updates | 95500 | +| policy_gradient_loss | -0.0532 | +| value_loss | 0.000412 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.263 | +| time/ | | +| fps | 310 | +| iterations | 3499 | +| time_elapsed | 11549 | +| total_timesteps | 3582976 | +| train/ | | +| approx_kl | 1.8305757 | +| clip_fraction | 0.439 | +| clip_range | 0.2 | +| entropy_loss | -0.333 | +| explained_variance | -1.2 | +| learning_rate | 0.0001 | +| loss | -0.0781 | +| n_updates | 95510 | +| policy_gradient_loss | -0.0594 | +| value_loss | 0.000559 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.269 | +| time/ | | +| fps | 310 | +| iterations | 3500 | +| time_elapsed | 11553 | +| total_timesteps | 3584000 | +| train/ | | +| approx_kl | 17.319866 | +| clip_fraction | 0.429 | +| clip_range | 0.2 | +| entropy_loss | -0.271 | +| explained_variance | -1.42 | +| learning_rate | 0.0001 | +| loss | -0.0633 | +| n_updates | 95520 | +| policy_gradient_loss | -0.0638 | +| value_loss | 0.000864 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.268 | +| time/ | | +| fps | 310 | +| iterations | 3501 | +| time_elapsed | 11556 | +| total_timesteps | 3585024 | +| train/ | | +| approx_kl | 3.2412786 | +| clip_fraction | 0.438 | +| clip_range | 0.2 | +| entropy_loss | -0.27 | +| explained_variance | -1.08 | +| learning_rate | 0.0001 | +| loss | -0.0691 | +| n_updates | 95530 | +| policy_gradient_loss | -0.0587 | +| value_loss | 0.000917 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.267 | +| time/ | | +| fps | 310 | +| iterations | 3502 | +| time_elapsed | 11559 | +| total_timesteps | 3586048 | +| train/ | | +| approx_kl | 1.9625793 | +| clip_fraction | 0.409 | +| clip_range | 0.2 | +| entropy_loss | -0.285 | +| explained_variance | -1.09 | +| learning_rate | 0.0001 | +| loss | -0.0622 | +| n_updates | 95540 | +| policy_gradient_loss | -0.0571 | +| value_loss | 0.00079 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.266 | +| time/ | | +| fps | 310 | +| iterations | 3503 | +| time_elapsed | 11563 | +| total_timesteps | 3587072 | +| train/ | | +| approx_kl | 2.4693508 | +| clip_fraction | 0.436 | +| clip_range | 0.2 | +| entropy_loss | -0.305 | +| explained_variance | -1.19 | +| learning_rate | 0.0001 | +| loss | -0.0459 | +| n_updates | 95550 | +| policy_gradient_loss | -0.057 | +| value_loss | 0.000509 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.263 | +| time/ | | +| fps | 310 | +| iterations | 3504 | +| time_elapsed | 11566 | +| total_timesteps | 3588096 | +| train/ | | +| approx_kl | 2.2639565 | +| clip_fraction | 0.4 | +| clip_range | 0.2 | +| entropy_loss | -0.281 | +| explained_variance | -3.41 | +| learning_rate | 0.0001 | +| loss | -0.0751 | +| n_updates | 95560 | +| policy_gradient_loss | -0.0615 | +| value_loss | 0.000486 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.26 | +| time/ | | +| fps | 310 | +| iterations | 3505 | +| time_elapsed | 11569 | +| total_timesteps | 3589120 | +| train/ | | +| approx_kl | 1.5221171 | +| clip_fraction | 0.369 | +| clip_range | 0.2 | +| entropy_loss | -0.252 | +| explained_variance | -0.218 | +| learning_rate | 0.0001 | +| loss | -0.0745 | +| n_updates | 95570 | +| policy_gradient_loss | -0.0506 | +| value_loss | 0.00052 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.259 | +| time/ | | +| fps | 310 | +| iterations | 3506 | +| time_elapsed | 11573 | +| total_timesteps | 3590144 | +| train/ | | +| approx_kl | 2.172697 | +| clip_fraction | 0.399 | +| clip_range | 0.2 | +| entropy_loss | -0.257 | +| explained_variance | -1.35 | +| learning_rate | 0.0001 | +| loss | -0.0685 | +| n_updates | 95580 | +| policy_gradient_loss | -0.056 | +| value_loss | 0.000654 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.259 | +| time/ | | +| fps | 310 | +| iterations | 3507 | +| time_elapsed | 11576 | +| total_timesteps | 3591168 | +| train/ | | +| approx_kl | 2.0218852 | +| clip_fraction | 0.448 | +| clip_range | 0.2 | +| entropy_loss | -0.331 | +| explained_variance | -0.549 | +| learning_rate | 0.0001 | +| loss | -0.0881 | +| n_updates | 95590 | +| policy_gradient_loss | -0.0606 | +| value_loss | 0.000633 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.255 | +| time/ | | +| fps | 310 | +| iterations | 3508 | +| time_elapsed | 11580 | +| total_timesteps | 3592192 | +| train/ | | +| approx_kl | 1.9136487 | +| clip_fraction | 0.44 | +| clip_range | 0.2 | +| entropy_loss | -0.332 | +| explained_variance | -1.34 | +| learning_rate | 0.0001 | +| loss | -0.0873 | +| n_updates | 95600 | +| policy_gradient_loss | -0.0587 | +| value_loss | 0.000744 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.251 | +| time/ | | +| fps | 310 | +| iterations | 3509 | +| time_elapsed | 11583 | +| total_timesteps | 3593216 | +| train/ | | +| approx_kl | 2.5430722 | +| clip_fraction | 0.448 | +| clip_range | 0.2 | +| entropy_loss | -0.296 | +| explained_variance | -1.84 | +| learning_rate | 0.0001 | +| loss | -0.0961 | +| n_updates | 95610 | +| policy_gradient_loss | -0.068 | +| value_loss | 0.000491 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.245 | +| time/ | | +| fps | 310 | +| iterations | 3510 | +| time_elapsed | 11587 | +| total_timesteps | 3594240 | +| train/ | | +| approx_kl | 2.9082952 | +| clip_fraction | 0.436 | +| clip_range | 0.2 | +| entropy_loss | -0.314 | +| explained_variance | -1.03 | +| learning_rate | 0.0001 | +| loss | -0.078 | +| n_updates | 95620 | +| policy_gradient_loss | -0.0606 | +| value_loss | 0.000565 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.243 | +| time/ | | +| fps | 310 | +| iterations | 3511 | +| time_elapsed | 11590 | +| total_timesteps | 3595264 | +| train/ | | +| approx_kl | 3.3549953 | +| clip_fraction | 0.436 | +| clip_range | 0.2 | +| entropy_loss | -0.319 | +| explained_variance | -1.13 | +| learning_rate | 0.0001 | +| loss | -0.079 | +| n_updates | 95630 | +| policy_gradient_loss | -0.0567 | +| value_loss | 0.000504 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.243 | +| time/ | | +| fps | 310 | +| iterations | 3512 | +| time_elapsed | 11593 | +| total_timesteps | 3596288 | +| train/ | | +| approx_kl | 2.3432865 | +| clip_fraction | 0.467 | +| clip_range | 0.2 | +| entropy_loss | -0.332 | +| explained_variance | -1.23 | +| learning_rate | 0.0001 | +| loss | -0.0822 | +| n_updates | 95640 | +| policy_gradient_loss | -0.0705 | +| value_loss | 0.000791 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.243 | +| time/ | | +| fps | 310 | +| iterations | 3513 | +| time_elapsed | 11596 | +| total_timesteps | 3597312 | +| train/ | | +| approx_kl | 1.8693174 | +| clip_fraction | 0.424 | +| clip_range | 0.2 | +| entropy_loss | -0.323 | +| explained_variance | -2.06 | +| learning_rate | 0.0001 | +| loss | -0.0968 | +| n_updates | 95650 | +| policy_gradient_loss | -0.063 | +| value_loss | 0.000484 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.243 | +| time/ | | +| fps | 310 | +| iterations | 3514 | +| time_elapsed | 11599 | +| total_timesteps | 3598336 | +| train/ | | +| approx_kl | 2.681623 | +| clip_fraction | 0.439 | +| clip_range | 0.2 | +| entropy_loss | -0.314 | +| explained_variance | -0.993 | +| learning_rate | 0.0001 | +| loss | -0.0928 | +| n_updates | 95660 | +| policy_gradient_loss | -0.0561 | +| value_loss | 0.000608 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.246 | +| time/ | | +| fps | 310 | +| iterations | 3515 | +| time_elapsed | 11603 | +| total_timesteps | 3599360 | +| train/ | | +| approx_kl | 2.3672292 | +| clip_fraction | 0.443 | +| clip_range | 0.2 | +| entropy_loss | -0.332 | +| explained_variance | -1.71 | +| learning_rate | 0.0001 | +| loss | -0.11 | +| n_updates | 95670 | +| policy_gradient_loss | -0.0646 | +| value_loss | 0.00058 | +--------------------------------------- + +Current state: Champion.Level10.RyuVsVega +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.245 | +| time/ | | +| fps | 310 | +| iterations | 3516 | +| time_elapsed | 11606 | +| total_timesteps | 3600384 | +| train/ | | +| approx_kl | 1.7259052 | +| clip_fraction | 0.454 | +| clip_range | 0.2 | +| entropy_loss | -0.348 | +| explained_variance | -0.653 | +| learning_rate | 0.0001 | +| loss | -0.0853 | +| n_updates | 95680 | +| policy_gradient_loss | -0.0619 | +| value_loss | 0.000719 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.245 | +| time/ | | +| fps | 310 | +| iterations | 3517 | +| time_elapsed | 11609 | +| total_timesteps | 3601408 | +| train/ | | +| approx_kl | 2.2822623 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.349 | +| explained_variance | -1.73 | +| learning_rate | 0.0001 | +| loss | -0.0715 | +| n_updates | 95690 | +| policy_gradient_loss | -0.0672 | +| value_loss | 0.000732 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.247 | +| time/ | | +| fps | 310 | +| iterations | 3518 | +| time_elapsed | 11612 | +| total_timesteps | 3602432 | +| train/ | | +| approx_kl | 2.3145204 | +| clip_fraction | 0.447 | +| clip_range | 0.2 | +| entropy_loss | -0.329 | +| explained_variance | -1.28 | +| learning_rate | 0.0001 | +| loss | -0.0803 | +| n_updates | 95700 | +| policy_gradient_loss | -0.0621 | +| value_loss | 0.000851 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.248 | +| time/ | | +| fps | 310 | +| iterations | 3519 | +| time_elapsed | 11616 | +| total_timesteps | 3603456 | +| train/ | | +| approx_kl | 3.2662091 | +| clip_fraction | 0.497 | +| clip_range | 0.2 | +| entropy_loss | -0.332 | +| explained_variance | -3.34 | +| learning_rate | 0.0001 | +| loss | -0.0922 | +| n_updates | 95710 | +| policy_gradient_loss | -0.0692 | +| value_loss | 0.000604 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.248 | +| time/ | | +| fps | 310 | +| iterations | 3520 | +| time_elapsed | 11619 | +| total_timesteps | 3604480 | +| train/ | | +| approx_kl | 3.5041287 | +| clip_fraction | 0.472 | +| clip_range | 0.2 | +| entropy_loss | -0.334 | +| explained_variance | -1.26 | +| learning_rate | 0.0001 | +| loss | -0.0779 | +| n_updates | 95720 | +| policy_gradient_loss | -0.0588 | +| value_loss | 0.000645 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.248 | +| time/ | | +| fps | 310 | +| iterations | 3521 | +| time_elapsed | 11623 | +| total_timesteps | 3605504 | +| train/ | | +| approx_kl | 2.2779531 | +| clip_fraction | 0.51 | +| clip_range | 0.2 | +| entropy_loss | -0.366 | +| explained_variance | -2.27 | +| learning_rate | 0.0001 | +| loss | -0.0556 | +| n_updates | 95730 | +| policy_gradient_loss | -0.0625 | +| value_loss | 0.000556 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.247 | +| time/ | | +| fps | 310 | +| iterations | 3522 | +| time_elapsed | 11626 | +| total_timesteps | 3606528 | +| train/ | | +| approx_kl | 2.373774 | +| clip_fraction | 0.497 | +| clip_range | 0.2 | +| entropy_loss | -0.353 | +| explained_variance | -5.03 | +| learning_rate | 0.0001 | +| loss | -0.0928 | +| n_updates | 95740 | +| policy_gradient_loss | -0.0635 | +| value_loss | 0.000259 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.247 | +| time/ | | +| fps | 310 | +| iterations | 3523 | +| time_elapsed | 11629 | +| total_timesteps | 3607552 | +| train/ | | +| approx_kl | 2.3949587 | +| clip_fraction | 0.464 | +| clip_range | 0.2 | +| entropy_loss | -0.311 | +| explained_variance | -1.2 | +| learning_rate | 0.0001 | +| loss | -0.0727 | +| n_updates | 95750 | +| policy_gradient_loss | -0.0611 | +| value_loss | 0.000408 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.244 | +| time/ | | +| fps | 310 | +| iterations | 3524 | +| time_elapsed | 11633 | +| total_timesteps | 3608576 | +| train/ | | +| approx_kl | 2.4360685 | +| clip_fraction | 0.482 | +| clip_range | 0.2 | +| entropy_loss | -0.36 | +| explained_variance | -2.55 | +| learning_rate | 0.0001 | +| loss | -0.0832 | +| n_updates | 95760 | +| policy_gradient_loss | -0.0696 | +| value_loss | 0.000462 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.244 | +| time/ | | +| fps | 310 | +| iterations | 3525 | +| time_elapsed | 11637 | +| total_timesteps | 3609600 | +| train/ | | +| approx_kl | 2.1962001 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.341 | +| explained_variance | -1.53 | +| learning_rate | 0.0001 | +| loss | -0.0977 | +| n_updates | 95770 | +| policy_gradient_loss | -0.0681 | +| value_loss | 0.000557 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.243 | +| time/ | | +| fps | 310 | +| iterations | 3526 | +| time_elapsed | 11640 | +| total_timesteps | 3610624 | +| train/ | | +| approx_kl | 2.2672691 | +| clip_fraction | 0.493 | +| clip_range | 0.2 | +| entropy_loss | -0.317 | +| explained_variance | -6.14 | +| learning_rate | 0.0001 | +| loss | -0.108 | +| n_updates | 95780 | +| policy_gradient_loss | -0.0755 | +| value_loss | 0.00053 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.243 | +| time/ | | +| fps | 310 | +| iterations | 3527 | +| time_elapsed | 11644 | +| total_timesteps | 3611648 | +| train/ | | +| approx_kl | 2.4998727 | +| clip_fraction | 0.461 | +| clip_range | 0.2 | +| entropy_loss | -0.341 | +| explained_variance | -1.73 | +| learning_rate | 0.0001 | +| loss | -0.0518 | +| n_updates | 95790 | +| policy_gradient_loss | -0.0622 | +| value_loss | 0.000543 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.249 | +| time/ | | +| fps | 310 | +| iterations | 3528 | +| time_elapsed | 11647 | +| total_timesteps | 3612672 | +| train/ | | +| approx_kl | 2.266348 | +| clip_fraction | 0.485 | +| clip_range | 0.2 | +| entropy_loss | -0.345 | +| explained_variance | -1.18 | +| learning_rate | 0.0001 | +| loss | -0.0911 | +| n_updates | 95800 | +| policy_gradient_loss | -0.0613 | +| value_loss | 0.000557 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.249 | +| time/ | | +| fps | 310 | +| iterations | 3529 | +| time_elapsed | 11650 | +| total_timesteps | 3613696 | +| train/ | | +| approx_kl | 2.6842594 | +| clip_fraction | 0.473 | +| clip_range | 0.2 | +| entropy_loss | -0.327 | +| explained_variance | -2.56 | +| learning_rate | 0.0001 | +| loss | -0.0889 | +| n_updates | 95810 | +| policy_gradient_loss | -0.0704 | +| value_loss | 0.000696 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.253 | +| time/ | | +| fps | 310 | +| iterations | 3530 | +| time_elapsed | 11653 | +| total_timesteps | 3614720 | +| train/ | | +| approx_kl | 2.9521163 | +| clip_fraction | 0.506 | +| clip_range | 0.2 | +| entropy_loss | -0.388 | +| explained_variance | -1.18 | +| learning_rate | 0.0001 | +| loss | -0.0869 | +| n_updates | 95820 | +| policy_gradient_loss | -0.0664 | +| value_loss | 0.000593 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.253 | +| time/ | | +| fps | 310 | +| iterations | 3531 | +| time_elapsed | 11657 | +| total_timesteps | 3615744 | +| train/ | | +| approx_kl | 2.131497 | +| clip_fraction | 0.452 | +| clip_range | 0.2 | +| entropy_loss | -0.321 | +| explained_variance | -1.1 | +| learning_rate | 0.0001 | +| loss | -0.0765 | +| n_updates | 95830 | +| policy_gradient_loss | -0.0644 | +| value_loss | 0.000673 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.253 | +| time/ | | +| fps | 310 | +| iterations | 3532 | +| time_elapsed | 11660 | +| total_timesteps | 3616768 | +| train/ | | +| approx_kl | 2.4005616 | +| clip_fraction | 0.468 | +| clip_range | 0.2 | +| entropy_loss | -0.317 | +| explained_variance | -5.71 | +| learning_rate | 0.0001 | +| loss | -0.0885 | +| n_updates | 95840 | +| policy_gradient_loss | -0.0657 | +| value_loss | 0.000443 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.252 | +| time/ | | +| fps | 310 | +| iterations | 3533 | +| time_elapsed | 11663 | +| total_timesteps | 3617792 | +| train/ | | +| approx_kl | 2.288577 | +| clip_fraction | 0.461 | +| clip_range | 0.2 | +| entropy_loss | -0.355 | +| explained_variance | -3.61 | +| learning_rate | 0.0001 | +| loss | -0.107 | +| n_updates | 95850 | +| policy_gradient_loss | -0.0654 | +| value_loss | 0.000275 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.256 | +| time/ | | +| fps | 310 | +| iterations | 3534 | +| time_elapsed | 11666 | +| total_timesteps | 3618816 | +| train/ | | +| approx_kl | 2.591014 | +| clip_fraction | 0.468 | +| clip_range | 0.2 | +| entropy_loss | -0.342 | +| explained_variance | -1.09 | +| learning_rate | 0.0001 | +| loss | -0.0737 | +| n_updates | 95860 | +| policy_gradient_loss | -0.0606 | +| value_loss | 0.000392 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.256 | +| time/ | | +| fps | 310 | +| iterations | 3535 | +| time_elapsed | 11669 | +| total_timesteps | 3619840 | +| train/ | | +| approx_kl | 2.0161664 | +| clip_fraction | 0.446 | +| clip_range | 0.2 | +| entropy_loss | -0.322 | +| explained_variance | -0.258 | +| learning_rate | 0.0001 | +| loss | -0.0882 | +| n_updates | 95870 | +| policy_gradient_loss | -0.0622 | +| value_loss | 0.00077 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.258 | +| time/ | | +| fps | 310 | +| iterations | 3536 | +| time_elapsed | 11672 | +| total_timesteps | 3620864 | +| train/ | | +| approx_kl | 1.9986976 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.372 | +| explained_variance | -2.4 | +| learning_rate | 0.0001 | +| loss | -0.0247 | +| n_updates | 95880 | +| policy_gradient_loss | -0.0584 | +| value_loss | 0.000742 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.258 | +| time/ | | +| fps | 310 | +| iterations | 3537 | +| time_elapsed | 11676 | +| total_timesteps | 3621888 | +| train/ | | +| approx_kl | 5.788223 | +| clip_fraction | 0.466 | +| clip_range | 0.2 | +| entropy_loss | -0.344 | +| explained_variance | -2.08 | +| learning_rate | 0.0001 | +| loss | -0.094 | +| n_updates | 95890 | +| policy_gradient_loss | -0.0683 | +| value_loss | 0.000791 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.262 | +| time/ | | +| fps | 310 | +| iterations | 3538 | +| time_elapsed | 11679 | +| total_timesteps | 3622912 | +| train/ | | +| approx_kl | 3.521748 | +| clip_fraction | 0.482 | +| clip_range | 0.2 | +| entropy_loss | -0.355 | +| explained_variance | -3.6 | +| learning_rate | 0.0001 | +| loss | -0.106 | +| n_updates | 95900 | +| policy_gradient_loss | -0.0696 | +| value_loss | 0.00052 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.262 | +| time/ | | +| fps | 310 | +| iterations | 3539 | +| time_elapsed | 11682 | +| total_timesteps | 3623936 | +| train/ | | +| approx_kl | 2.0933774 | +| clip_fraction | 0.462 | +| clip_range | 0.2 | +| entropy_loss | -0.331 | +| explained_variance | -0.834 | +| learning_rate | 0.0001 | +| loss | -0.0861 | +| n_updates | 95910 | +| policy_gradient_loss | -0.0644 | +| value_loss | 0.000415 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.264 | +| time/ | | +| fps | 310 | +| iterations | 3540 | +| time_elapsed | 11686 | +| total_timesteps | 3624960 | +| train/ | | +| approx_kl | 2.0280051 | +| clip_fraction | 0.489 | +| clip_range | 0.2 | +| entropy_loss | -0.359 | +| explained_variance | -1.63 | +| learning_rate | 0.0001 | +| loss | -0.0896 | +| n_updates | 95920 | +| policy_gradient_loss | -0.0565 | +| value_loss | 0.000269 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.264 | +| time/ | | +| fps | 310 | +| iterations | 3541 | +| time_elapsed | 11689 | +| total_timesteps | 3625984 | +| train/ | | +| approx_kl | 2.0921822 | +| clip_fraction | 0.43 | +| clip_range | 0.2 | +| entropy_loss | -0.314 | +| explained_variance | -0.893 | +| learning_rate | 0.0001 | +| loss | -0.0851 | +| n_updates | 95930 | +| policy_gradient_loss | -0.0479 | +| value_loss | 0.000805 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.264 | +| time/ | | +| fps | 310 | +| iterations | 3542 | +| time_elapsed | 11692 | +| total_timesteps | 3627008 | +| train/ | | +| approx_kl | 2.2620134 | +| clip_fraction | 0.467 | +| clip_range | 0.2 | +| entropy_loss | -0.38 | +| explained_variance | -4.51 | +| learning_rate | 0.0001 | +| loss | -0.0766 | +| n_updates | 95940 | +| policy_gradient_loss | -0.0689 | +| value_loss | 0.000348 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.265 | +| time/ | | +| fps | 310 | +| iterations | 3543 | +| time_elapsed | 11696 | +| total_timesteps | 3628032 | +| train/ | | +| approx_kl | 3.8918614 | +| clip_fraction | 0.442 | +| clip_range | 0.2 | +| entropy_loss | -0.348 | +| explained_variance | -3.59 | +| learning_rate | 0.0001 | +| loss | -0.0687 | +| n_updates | 95950 | +| policy_gradient_loss | -0.0561 | +| value_loss | 0.000324 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.265 | +| time/ | | +| fps | 310 | +| iterations | 3544 | +| time_elapsed | 11699 | +| total_timesteps | 3629056 | +| train/ | | +| approx_kl | 2.6103644 | +| clip_fraction | 0.437 | +| clip_range | 0.2 | +| entropy_loss | -0.339 | +| explained_variance | -2.74 | +| learning_rate | 0.0001 | +| loss | -0.0741 | +| n_updates | 95960 | +| policy_gradient_loss | -0.0563 | +| value_loss | 0.000492 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.43e+03 | +| ep_rew_mean | 0.263 | +| time/ | | +| fps | 310 | +| iterations | 3545 | +| time_elapsed | 11702 | +| total_timesteps | 3630080 | +| train/ | | +| approx_kl | 1.7896485 | +| clip_fraction | 0.499 | +| clip_range | 0.2 | +| entropy_loss | -0.432 | +| explained_variance | -0.675 | +| learning_rate | 0.0001 | +| loss | -0.03 | +| n_updates | 95970 | +| policy_gradient_loss | -0.043 | +| value_loss | 0.000574 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.43e+03 | +| ep_rew_mean | 0.263 | +| time/ | | +| fps | 310 | +| iterations | 3546 | +| time_elapsed | 11706 | +| total_timesteps | 3631104 | +| train/ | | +| approx_kl | 2.5482936 | +| clip_fraction | 0.426 | +| clip_range | 0.2 | +| entropy_loss | -0.337 | +| explained_variance | -7.86 | +| learning_rate | 0.0001 | +| loss | -0.0633 | +| n_updates | 95980 | +| policy_gradient_loss | -0.0595 | +| value_loss | 0.000691 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.43e+03 | +| ep_rew_mean | 0.263 | +| time/ | | +| fps | 310 | +| iterations | 3547 | +| time_elapsed | 11709 | +| total_timesteps | 3632128 | +| train/ | | +| approx_kl | 2.651603 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.416 | +| explained_variance | -0.568 | +| learning_rate | 0.0001 | +| loss | -0.0818 | +| n_updates | 95990 | +| policy_gradient_loss | -0.0508 | +| value_loss | 0.000465 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.45e+03 | +| ep_rew_mean | 0.262 | +| time/ | | +| fps | 310 | +| iterations | 3548 | +| time_elapsed | 11712 | +| total_timesteps | 3633152 | +| train/ | | +| approx_kl | 2.323114 | +| clip_fraction | 0.474 | +| clip_range | 0.2 | +| entropy_loss | -0.353 | +| explained_variance | -2.37 | +| learning_rate | 0.0001 | +| loss | -0.0983 | +| n_updates | 96000 | +| policy_gradient_loss | -0.0553 | +| value_loss | 0.000275 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.45e+03 | +| ep_rew_mean | 0.262 | +| time/ | | +| fps | 310 | +| iterations | 3549 | +| time_elapsed | 11715 | +| total_timesteps | 3634176 | +| train/ | | +| approx_kl | 2.356927 | +| clip_fraction | 0.463 | +| clip_range | 0.2 | +| entropy_loss | -0.368 | +| explained_variance | -0.727 | +| learning_rate | 0.0001 | +| loss | -0.0889 | +| n_updates | 96010 | +| policy_gradient_loss | -0.0642 | +| value_loss | 0.000348 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.45e+03 | +| ep_rew_mean | 0.262 | +| time/ | | +| fps | 310 | +| iterations | 3550 | +| time_elapsed | 11718 | +| total_timesteps | 3635200 | +| train/ | | +| approx_kl | 1.7891967 | +| clip_fraction | 0.461 | +| clip_range | 0.2 | +| entropy_loss | -0.359 | +| explained_variance | -3.54 | +| learning_rate | 0.0001 | +| loss | -0.0642 | +| n_updates | 96020 | +| policy_gradient_loss | -0.0599 | +| value_loss | 0.000293 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.45e+03 | +| ep_rew_mean | 0.262 | +| time/ | | +| fps | 310 | +| iterations | 3551 | +| time_elapsed | 11722 | +| total_timesteps | 3636224 | +| train/ | | +| approx_kl | 2.1655118 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.362 | +| explained_variance | -0.528 | +| learning_rate | 0.0001 | +| loss | -0.0715 | +| n_updates | 96030 | +| policy_gradient_loss | -0.0569 | +| value_loss | 0.000537 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.47e+03 | +| ep_rew_mean | 0.264 | +| time/ | | +| fps | 310 | +| iterations | 3552 | +| time_elapsed | 11725 | +| total_timesteps | 3637248 | +| train/ | | +| approx_kl | 2.022017 | +| clip_fraction | 0.503 | +| clip_range | 0.2 | +| entropy_loss | -0.4 | +| explained_variance | -2.64 | +| learning_rate | 0.0001 | +| loss | -0.0864 | +| n_updates | 96040 | +| policy_gradient_loss | -0.072 | +| value_loss | 0.000478 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.47e+03 | +| ep_rew_mean | 0.264 | +| time/ | | +| fps | 310 | +| iterations | 3553 | +| time_elapsed | 11728 | +| total_timesteps | 3638272 | +| train/ | | +| approx_kl | 2.1504526 | +| clip_fraction | 0.482 | +| clip_range | 0.2 | +| entropy_loss | -0.411 | +| explained_variance | -2.73 | +| learning_rate | 0.0001 | +| loss | -0.0914 | +| n_updates | 96050 | +| policy_gradient_loss | -0.0621 | +| value_loss | 0.000509 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.47e+03 | +| ep_rew_mean | 0.264 | +| time/ | | +| fps | 310 | +| iterations | 3554 | +| time_elapsed | 11731 | +| total_timesteps | 3639296 | +| train/ | | +| approx_kl | 2.109304 | +| clip_fraction | 0.555 | +| clip_range | 0.2 | +| entropy_loss | -0.473 | +| explained_variance | -0.506 | +| learning_rate | 0.0001 | +| loss | -0.0757 | +| n_updates | 96060 | +| policy_gradient_loss | -0.0671 | +| value_loss | 0.000521 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.48e+03 | +| ep_rew_mean | 0.268 | +| time/ | | +| fps | 310 | +| iterations | 3555 | +| time_elapsed | 11734 | +| total_timesteps | 3640320 | +| train/ | | +| approx_kl | 1.5765457 | +| clip_fraction | 0.46 | +| clip_range | 0.2 | +| entropy_loss | -0.377 | +| explained_variance | -5.53 | +| learning_rate | 0.0001 | +| loss | -0.0707 | +| n_updates | 96070 | +| policy_gradient_loss | -0.0627 | +| value_loss | 0.000949 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.49e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 310 | +| iterations | 3556 | +| time_elapsed | 11737 | +| total_timesteps | 3641344 | +| train/ | | +| approx_kl | 1.9471866 | +| clip_fraction | 0.499 | +| clip_range | 0.2 | +| entropy_loss | -0.377 | +| explained_variance | -1 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 96080 | +| policy_gradient_loss | -0.0645 | +| value_loss | 0.000509 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.49e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 310 | +| iterations | 3557 | +| time_elapsed | 11741 | +| total_timesteps | 3642368 | +| train/ | | +| approx_kl | 1.8465976 | +| clip_fraction | 0.493 | +| clip_range | 0.2 | +| entropy_loss | -0.374 | +| explained_variance | -1.08 | +| learning_rate | 0.0001 | +| loss | -0.0857 | +| n_updates | 96090 | +| policy_gradient_loss | -0.072 | +| value_loss | 0.000558 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.49e+03 | +| ep_rew_mean | 0.273 | +| time/ | | +| fps | 310 | +| iterations | 3558 | +| time_elapsed | 11744 | +| total_timesteps | 3643392 | +| train/ | | +| approx_kl | 3.6176288 | +| clip_fraction | 0.521 | +| clip_range | 0.2 | +| entropy_loss | -0.43 | +| explained_variance | -2.44 | +| learning_rate | 0.0001 | +| loss | -0.105 | +| n_updates | 96100 | +| policy_gradient_loss | -0.067 | +| value_loss | 0.000456 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.49e+03 | +| ep_rew_mean | 0.271 | +| time/ | | +| fps | 310 | +| iterations | 3559 | +| time_elapsed | 11748 | +| total_timesteps | 3644416 | +| train/ | | +| approx_kl | 2.1546535 | +| clip_fraction | 0.489 | +| clip_range | 0.2 | +| entropy_loss | -0.378 | +| explained_variance | -1.97 | +| learning_rate | 0.0001 | +| loss | -0.105 | +| n_updates | 96110 | +| policy_gradient_loss | -0.07 | +| value_loss | 0.000332 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.49e+03 | +| ep_rew_mean | 0.271 | +| time/ | | +| fps | 310 | +| iterations | 3560 | +| time_elapsed | 11751 | +| total_timesteps | 3645440 | +| train/ | | +| approx_kl | 2.4898639 | +| clip_fraction | 0.474 | +| clip_range | 0.2 | +| entropy_loss | -0.365 | +| explained_variance | -1.34 | +| learning_rate | 0.0001 | +| loss | -0.0804 | +| n_updates | 96120 | +| policy_gradient_loss | -0.066 | +| value_loss | 0.000517 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.49e+03 | +| ep_rew_mean | 0.271 | +| time/ | | +| fps | 310 | +| iterations | 3561 | +| time_elapsed | 11755 | +| total_timesteps | 3646464 | +| train/ | | +| approx_kl | 2.0976746 | +| clip_fraction | 0.5 | +| clip_range | 0.2 | +| entropy_loss | -0.362 | +| explained_variance | -6.38 | +| learning_rate | 0.0001 | +| loss | -0.0956 | +| n_updates | 96130 | +| policy_gradient_loss | -0.0703 | +| value_loss | 0.000705 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.51e+03 | +| ep_rew_mean | 0.271 | +| time/ | | +| fps | 310 | +| iterations | 3562 | +| time_elapsed | 11758 | +| total_timesteps | 3647488 | +| train/ | | +| approx_kl | 2.1473765 | +| clip_fraction | 0.534 | +| clip_range | 0.2 | +| entropy_loss | -0.467 | +| explained_variance | -1.87 | +| learning_rate | 0.0001 | +| loss | -0.0871 | +| n_updates | 96140 | +| policy_gradient_loss | -0.0726 | +| value_loss | 0.000237 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.51e+03 | +| ep_rew_mean | 0.271 | +| time/ | | +| fps | 310 | +| iterations | 3563 | +| time_elapsed | 11762 | +| total_timesteps | 3648512 | +| train/ | | +| approx_kl | 4.8251977 | +| clip_fraction | 0.499 | +| clip_range | 0.2 | +| entropy_loss | -0.39 | +| explained_variance | -5.07 | +| learning_rate | 0.0001 | +| loss | -0.0854 | +| n_updates | 96150 | +| policy_gradient_loss | -0.0704 | +| value_loss | 0.000358 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.51e+03 | +| ep_rew_mean | 0.269 | +| time/ | | +| fps | 310 | +| iterations | 3564 | +| time_elapsed | 11765 | +| total_timesteps | 3649536 | +| train/ | | +| approx_kl | 2.3256888 | +| clip_fraction | 0.507 | +| clip_range | 0.2 | +| entropy_loss | -0.417 | +| explained_variance | -1.93 | +| learning_rate | 0.0001 | +| loss | -0.0724 | +| n_updates | 96160 | +| policy_gradient_loss | -0.0683 | +| value_loss | 0.000486 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.51e+03 | +| ep_rew_mean | 0.269 | +| time/ | | +| fps | 310 | +| iterations | 3565 | +| time_elapsed | 11769 | +| total_timesteps | 3650560 | +| train/ | | +| approx_kl | 1.8752398 | +| clip_fraction | 0.502 | +| clip_range | 0.2 | +| entropy_loss | -0.438 | +| explained_variance | -0.899 | +| learning_rate | 0.0001 | +| loss | -0.0941 | +| n_updates | 96170 | +| policy_gradient_loss | -0.0668 | +| value_loss | 0.000595 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.52e+03 | +| ep_rew_mean | 0.271 | +| time/ | | +| fps | 310 | +| iterations | 3566 | +| time_elapsed | 11772 | +| total_timesteps | 3651584 | +| train/ | | +| approx_kl | 1.9369365 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.403 | +| explained_variance | -2.51 | +| learning_rate | 0.0001 | +| loss | -0.0799 | +| n_updates | 96180 | +| policy_gradient_loss | -0.0644 | +| value_loss | 0.000709 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.52e+03 | +| ep_rew_mean | 0.271 | +| time/ | | +| fps | 310 | +| iterations | 3567 | +| time_elapsed | 11775 | +| total_timesteps | 3652608 | +| train/ | | +| approx_kl | 2.836444 | +| clip_fraction | 0.525 | +| clip_range | 0.2 | +| entropy_loss | -0.43 | +| explained_variance | -1.38 | +| learning_rate | 0.0001 | +| loss | -0.109 | +| n_updates | 96190 | +| policy_gradient_loss | -0.0743 | +| value_loss | 0.000586 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.52e+03 | +| ep_rew_mean | 0.272 | +| time/ | | +| fps | 310 | +| iterations | 3568 | +| time_elapsed | 11778 | +| total_timesteps | 3653632 | +| train/ | | +| approx_kl | 1.9448926 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.412 | +| explained_variance | -2.29 | +| learning_rate | 0.0001 | +| loss | -0.083 | +| n_updates | 96200 | +| policy_gradient_loss | -0.0685 | +| value_loss | 0.000425 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.52e+03 | +| ep_rew_mean | 0.27 | +| time/ | | +| fps | 310 | +| iterations | 3569 | +| time_elapsed | 11781 | +| total_timesteps | 3654656 | +| train/ | | +| approx_kl | 2.1398964 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.414 | +| explained_variance | -0.77 | +| learning_rate | 0.0001 | +| loss | -0.0662 | +| n_updates | 96210 | +| policy_gradient_loss | -0.0707 | +| value_loss | 0.000592 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.52e+03 | +| ep_rew_mean | 0.27 | +| time/ | | +| fps | 310 | +| iterations | 3570 | +| time_elapsed | 11785 | +| total_timesteps | 3655680 | +| train/ | | +| approx_kl | 3.5008385 | +| clip_fraction | 0.521 | +| clip_range | 0.2 | +| entropy_loss | -0.401 | +| explained_variance | -1.24 | +| learning_rate | 0.0001 | +| loss | -0.0911 | +| n_updates | 96220 | +| policy_gradient_loss | -0.0705 | +| value_loss | 0.000709 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.52e+03 | +| ep_rew_mean | 0.272 | +| time/ | | +| fps | 310 | +| iterations | 3571 | +| time_elapsed | 11788 | +| total_timesteps | 3656704 | +| train/ | | +| approx_kl | 2.3050752 | +| clip_fraction | 0.509 | +| clip_range | 0.2 | +| entropy_loss | -0.474 | +| explained_variance | -3.22 | +| learning_rate | 0.0001 | +| loss | -0.0502 | +| n_updates | 96230 | +| policy_gradient_loss | -0.0635 | +| value_loss | 0.000508 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.52e+03 | +| ep_rew_mean | 0.272 | +| time/ | | +| fps | 310 | +| iterations | 3572 | +| time_elapsed | 11791 | +| total_timesteps | 3657728 | +| train/ | | +| approx_kl | 2.2794886 | +| clip_fraction | 0.495 | +| clip_range | 0.2 | +| entropy_loss | -0.392 | +| explained_variance | -3.03 | +| learning_rate | 0.0001 | +| loss | -0.0719 | +| n_updates | 96240 | +| policy_gradient_loss | -0.0681 | +| value_loss | 0.000313 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.54e+03 | +| ep_rew_mean | 0.265 | +| time/ | | +| fps | 310 | +| iterations | 3573 | +| time_elapsed | 11794 | +| total_timesteps | 3658752 | +| train/ | | +| approx_kl | 1.9148642 | +| clip_fraction | 0.472 | +| clip_range | 0.2 | +| entropy_loss | -0.354 | +| explained_variance | -1.84 | +| learning_rate | 0.0001 | +| loss | -0.0206 | +| n_updates | 96250 | +| policy_gradient_loss | -0.0677 | +| value_loss | 0.000471 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.53e+03 | +| ep_rew_mean | 0.267 | +| time/ | | +| fps | 310 | +| iterations | 3574 | +| time_elapsed | 11798 | +| total_timesteps | 3659776 | +| train/ | | +| approx_kl | 1.482689 | +| clip_fraction | 0.461 | +| clip_range | 0.2 | +| entropy_loss | -0.402 | +| explained_variance | -2.79 | +| learning_rate | 0.0001 | +| loss | -0.1 | +| n_updates | 96260 | +| policy_gradient_loss | -0.0618 | +| value_loss | 0.00026 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.53e+03 | +| ep_rew_mean | 0.267 | +| time/ | | +| fps | 310 | +| iterations | 3575 | +| time_elapsed | 11801 | +| total_timesteps | 3660800 | +| train/ | | +| approx_kl | 1.6676531 | +| clip_fraction | 0.5 | +| clip_range | 0.2 | +| entropy_loss | -0.436 | +| explained_variance | -0.156 | +| learning_rate | 0.0001 | +| loss | -0.0676 | +| n_updates | 96270 | +| policy_gradient_loss | -0.0625 | +| value_loss | 0.00113 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.53e+03 | +| ep_rew_mean | 0.267 | +| time/ | | +| fps | 310 | +| iterations | 3576 | +| time_elapsed | 11804 | +| total_timesteps | 3661824 | +| train/ | | +| approx_kl | 2.040948 | +| clip_fraction | 0.465 | +| clip_range | 0.2 | +| entropy_loss | -0.415 | +| explained_variance | -5.25 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 96280 | +| policy_gradient_loss | -0.0725 | +| value_loss | 0.000506 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.54e+03 | +| ep_rew_mean | 0.264 | +| time/ | | +| fps | 310 | +| iterations | 3577 | +| time_elapsed | 11808 | +| total_timesteps | 3662848 | +| train/ | | +| approx_kl | 2.1836672 | +| clip_fraction | 0.508 | +| clip_range | 0.2 | +| entropy_loss | -0.404 | +| explained_variance | -3.66 | +| learning_rate | 0.0001 | +| loss | -0.0723 | +| n_updates | 96290 | +| policy_gradient_loss | -0.066 | +| value_loss | 0.000265 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.54e+03 | +| ep_rew_mean | 0.264 | +| time/ | | +| fps | 310 | +| iterations | 3578 | +| time_elapsed | 11811 | +| total_timesteps | 3663872 | +| train/ | | +| approx_kl | 1.6515908 | +| clip_fraction | 0.441 | +| clip_range | 0.2 | +| entropy_loss | -0.34 | +| explained_variance | -5.87 | +| learning_rate | 0.0001 | +| loss | -0.0985 | +| n_updates | 96300 | +| policy_gradient_loss | -0.0597 | +| value_loss | 0.000378 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.54e+03 | +| ep_rew_mean | 0.264 | +| time/ | | +| fps | 310 | +| iterations | 3579 | +| time_elapsed | 11815 | +| total_timesteps | 3664896 | +| train/ | | +| approx_kl | 1.9327568 | +| clip_fraction | 0.529 | +| clip_range | 0.2 | +| entropy_loss | -0.446 | +| explained_variance | -0.69 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 96310 | +| policy_gradient_loss | -0.0692 | +| value_loss | 0.000428 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.56e+03 | +| ep_rew_mean | 0.263 | +| time/ | | +| fps | 310 | +| iterations | 3580 | +| time_elapsed | 11818 | +| total_timesteps | 3665920 | +| train/ | | +| approx_kl | 2.5917735 | +| clip_fraction | 0.457 | +| clip_range | 0.2 | +| entropy_loss | -0.344 | +| explained_variance | -1.11 | +| learning_rate | 0.0001 | +| loss | -0.105 | +| n_updates | 96320 | +| policy_gradient_loss | -0.0601 | +| value_loss | 0.000394 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.55e+03 | +| ep_rew_mean | 0.256 | +| time/ | | +| fps | 310 | +| iterations | 3581 | +| time_elapsed | 11822 | +| total_timesteps | 3666944 | +| train/ | | +| approx_kl | 1.9806778 | +| clip_fraction | 0.465 | +| clip_range | 0.2 | +| entropy_loss | -0.347 | +| explained_variance | -3.74 | +| learning_rate | 0.0001 | +| loss | -0.071 | +| n_updates | 96330 | +| policy_gradient_loss | -0.0653 | +| value_loss | 0.000521 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.55e+03 | +| ep_rew_mean | 0.256 | +| time/ | | +| fps | 310 | +| iterations | 3582 | +| time_elapsed | 11825 | +| total_timesteps | 3667968 | +| train/ | | +| approx_kl | 2.6331763 | +| clip_fraction | 0.478 | +| clip_range | 0.2 | +| entropy_loss | -0.39 | +| explained_variance | -2.9 | +| learning_rate | 0.0001 | +| loss | -0.0661 | +| n_updates | 96340 | +| policy_gradient_loss | -0.069 | +| value_loss | 0.000634 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.55e+03 | +| ep_rew_mean | 0.256 | +| time/ | | +| fps | 310 | +| iterations | 3583 | +| time_elapsed | 11828 | +| total_timesteps | 3668992 | +| train/ | | +| approx_kl | 2.421623 | +| clip_fraction | 0.5 | +| clip_range | 0.2 | +| entropy_loss | -0.395 | +| explained_variance | -4.38 | +| learning_rate | 0.0001 | +| loss | -0.0769 | +| n_updates | 96350 | +| policy_gradient_loss | -0.0706 | +| value_loss | 0.000534 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.56e+03 | +| ep_rew_mean | 0.255 | +| time/ | | +| fps | 310 | +| iterations | 3584 | +| time_elapsed | 11832 | +| total_timesteps | 3670016 | +| train/ | | +| approx_kl | 1.6889292 | +| clip_fraction | 0.469 | +| clip_range | 0.2 | +| entropy_loss | -0.382 | +| explained_variance | -1.61 | +| learning_rate | 0.0001 | +| loss | -0.0615 | +| n_updates | 96360 | +| policy_gradient_loss | -0.0626 | +| value_loss | 0.000349 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.56e+03 | +| ep_rew_mean | 0.255 | +| time/ | | +| fps | 310 | +| iterations | 3585 | +| time_elapsed | 11835 | +| total_timesteps | 3671040 | +| train/ | | +| approx_kl | 2.121031 | +| clip_fraction | 0.493 | +| clip_range | 0.2 | +| entropy_loss | -0.383 | +| explained_variance | -1.12 | +| learning_rate | 0.0001 | +| loss | -0.113 | +| n_updates | 96370 | +| policy_gradient_loss | -0.0711 | +| value_loss | 0.000671 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.57e+03 | +| ep_rew_mean | 0.256 | +| time/ | | +| fps | 310 | +| iterations | 3586 | +| time_elapsed | 11838 | +| total_timesteps | 3672064 | +| train/ | | +| approx_kl | 2.1126833 | +| clip_fraction | 0.501 | +| clip_range | 0.2 | +| entropy_loss | -0.413 | +| explained_variance | -1.62 | +| learning_rate | 0.0001 | +| loss | -0.096 | +| n_updates | 96380 | +| policy_gradient_loss | -0.0662 | +| value_loss | 0.000411 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.57e+03 | +| ep_rew_mean | 0.256 | +| time/ | | +| fps | 310 | +| iterations | 3587 | +| time_elapsed | 11841 | +| total_timesteps | 3673088 | +| train/ | | +| approx_kl | 2.2597072 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.375 | +| explained_variance | -0.9 | +| learning_rate | 0.0001 | +| loss | -0.0681 | +| n_updates | 96390 | +| policy_gradient_loss | -0.064 | +| value_loss | 0.000385 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.58e+03 | +| ep_rew_mean | 0.261 | +| time/ | | +| fps | 310 | +| iterations | 3588 | +| time_elapsed | 11844 | +| total_timesteps | 3674112 | +| train/ | | +| approx_kl | 3.0443745 | +| clip_fraction | 0.499 | +| clip_range | 0.2 | +| entropy_loss | -0.39 | +| explained_variance | -1.28 | +| learning_rate | 0.0001 | +| loss | -0.0915 | +| n_updates | 96400 | +| policy_gradient_loss | -0.0635 | +| value_loss | 0.000648 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.58e+03 | +| ep_rew_mean | 0.261 | +| time/ | | +| fps | 310 | +| iterations | 3589 | +| time_elapsed | 11847 | +| total_timesteps | 3675136 | +| train/ | | +| approx_kl | 1.8441305 | +| clip_fraction | 0.499 | +| clip_range | 0.2 | +| entropy_loss | -0.418 | +| explained_variance | -2.27 | +| learning_rate | 0.0001 | +| loss | -0.0912 | +| n_updates | 96410 | +| policy_gradient_loss | -0.0734 | +| value_loss | 0.000377 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | 0.256 | +| time/ | | +| fps | 310 | +| iterations | 3590 | +| time_elapsed | 11851 | +| total_timesteps | 3676160 | +| train/ | | +| approx_kl | 2.228929 | +| clip_fraction | 0.504 | +| clip_range | 0.2 | +| entropy_loss | -0.373 | +| explained_variance | -3.03 | +| learning_rate | 0.0001 | +| loss | -0.0823 | +| n_updates | 96420 | +| policy_gradient_loss | -0.0698 | +| value_loss | 0.00046 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | 0.256 | +| time/ | | +| fps | 310 | +| iterations | 3591 | +| time_elapsed | 11854 | +| total_timesteps | 3677184 | +| train/ | | +| approx_kl | 2.3089187 | +| clip_fraction | 0.447 | +| clip_range | 0.2 | +| entropy_loss | -0.344 | +| explained_variance | -3.02 | +| learning_rate | 0.0001 | +| loss | -0.117 | +| n_updates | 96430 | +| policy_gradient_loss | -0.0692 | +| value_loss | 0.000267 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | 0.256 | +| time/ | | +| fps | 310 | +| iterations | 3592 | +| time_elapsed | 11857 | +| total_timesteps | 3678208 | +| train/ | | +| approx_kl | 2.1631877 | +| clip_fraction | 0.49 | +| clip_range | 0.2 | +| entropy_loss | -0.392 | +| explained_variance | -0.97 | +| learning_rate | 0.0001 | +| loss | -0.0897 | +| n_updates | 96440 | +| policy_gradient_loss | -0.0712 | +| value_loss | 0.000579 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.61e+03 | +| ep_rew_mean | 0.255 | +| time/ | | +| fps | 310 | +| iterations | 3593 | +| time_elapsed | 11860 | +| total_timesteps | 3679232 | +| train/ | | +| approx_kl | 2.4322448 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.369 | +| explained_variance | -3.35 | +| learning_rate | 0.0001 | +| loss | -0.105 | +| n_updates | 96450 | +| policy_gradient_loss | -0.0771 | +| value_loss | 0.000394 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.61e+03 | +| ep_rew_mean | 0.255 | +| time/ | | +| fps | 310 | +| iterations | 3594 | +| time_elapsed | 11864 | +| total_timesteps | 3680256 | +| train/ | | +| approx_kl | 2.2502108 | +| clip_fraction | 0.469 | +| clip_range | 0.2 | +| entropy_loss | -0.35 | +| explained_variance | -3.36 | +| learning_rate | 0.0001 | +| loss | -0.0986 | +| n_updates | 96460 | +| policy_gradient_loss | -0.0637 | +| value_loss | 0.000323 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.61e+03 | +| ep_rew_mean | 0.255 | +| time/ | | +| fps | 310 | +| iterations | 3595 | +| time_elapsed | 11867 | +| total_timesteps | 3681280 | +| train/ | | +| approx_kl | 2.566334 | +| clip_fraction | 0.499 | +| clip_range | 0.2 | +| entropy_loss | -0.378 | +| explained_variance | -2.69 | +| learning_rate | 0.0001 | +| loss | -0.0819 | +| n_updates | 96470 | +| policy_gradient_loss | -0.0722 | +| value_loss | 0.000358 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.62e+03 | +| ep_rew_mean | 0.253 | +| time/ | | +| fps | 310 | +| iterations | 3596 | +| time_elapsed | 11871 | +| total_timesteps | 3682304 | +| train/ | | +| approx_kl | 1.6876723 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.375 | +| explained_variance | -3.72 | +| learning_rate | 0.0001 | +| loss | -0.0871 | +| n_updates | 96480 | +| policy_gradient_loss | -0.0555 | +| value_loss | 0.000641 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.62e+03 | +| ep_rew_mean | 0.253 | +| time/ | | +| fps | 310 | +| iterations | 3597 | +| time_elapsed | 11874 | +| total_timesteps | 3683328 | +| train/ | | +| approx_kl | 2.2561526 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.395 | +| explained_variance | -2.97 | +| learning_rate | 0.0001 | +| loss | -0.0904 | +| n_updates | 96490 | +| policy_gradient_loss | -0.0601 | +| value_loss | 0.000631 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.63e+03 | +| ep_rew_mean | 0.251 | +| time/ | | +| fps | 310 | +| iterations | 3598 | +| time_elapsed | 11877 | +| total_timesteps | 3684352 | +| train/ | | +| approx_kl | 2.2988172 | +| clip_fraction | 0.51 | +| clip_range | 0.2 | +| entropy_loss | -0.413 | +| explained_variance | -1.82 | +| learning_rate | 0.0001 | +| loss | -0.0836 | +| n_updates | 96500 | +| policy_gradient_loss | -0.0674 | +| value_loss | 0.000428 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.62e+03 | +| ep_rew_mean | 0.257 | +| time/ | | +| fps | 310 | +| iterations | 3599 | +| time_elapsed | 11881 | +| total_timesteps | 3685376 | +| train/ | | +| approx_kl | 2.27361 | +| clip_fraction | 0.546 | +| clip_range | 0.2 | +| entropy_loss | -0.451 | +| explained_variance | -0.72 | +| learning_rate | 0.0001 | +| loss | -0.0985 | +| n_updates | 96510 | +| policy_gradient_loss | -0.0739 | +| value_loss | 0.000584 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.62e+03 | +| ep_rew_mean | 0.257 | +| time/ | | +| fps | 310 | +| iterations | 3600 | +| time_elapsed | 11885 | +| total_timesteps | 3686400 | +| train/ | | +| approx_kl | 1.8964128 | +| clip_fraction | 0.516 | +| clip_range | 0.2 | +| entropy_loss | -0.435 | +| explained_variance | -0.42 | +| learning_rate | 0.0001 | +| loss | -0.0538 | +| n_updates | 96520 | +| policy_gradient_loss | -0.0604 | +| value_loss | 0.000919 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.62e+03 | +| ep_rew_mean | 0.257 | +| time/ | | +| fps | 310 | +| iterations | 3601 | +| time_elapsed | 11888 | +| total_timesteps | 3687424 | +| train/ | | +| approx_kl | 2.7018073 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.385 | +| explained_variance | -2.48 | +| learning_rate | 0.0001 | +| loss | -0.056 | +| n_updates | 96530 | +| policy_gradient_loss | -0.0697 | +| value_loss | 0.000612 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.62e+03 | +| ep_rew_mean | 0.257 | +| time/ | | +| fps | 310 | +| iterations | 3602 | +| time_elapsed | 11891 | +| total_timesteps | 3688448 | +| train/ | | +| approx_kl | 2.134197 | +| clip_fraction | 0.449 | +| clip_range | 0.2 | +| entropy_loss | -0.342 | +| explained_variance | -2.42 | +| learning_rate | 0.0001 | +| loss | -0.0727 | +| n_updates | 96540 | +| policy_gradient_loss | -0.0656 | +| value_loss | 0.000739 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.62e+03 | +| ep_rew_mean | 0.257 | +| time/ | | +| fps | 310 | +| iterations | 3603 | +| time_elapsed | 11894 | +| total_timesteps | 3689472 | +| train/ | | +| approx_kl | 2.1838987 | +| clip_fraction | 0.5 | +| clip_range | 0.2 | +| entropy_loss | -0.364 | +| explained_variance | -1.79 | +| learning_rate | 0.0001 | +| loss | -0.0873 | +| n_updates | 96550 | +| policy_gradient_loss | -0.0707 | +| value_loss | 0.000452 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.64e+03 | +| ep_rew_mean | 0.256 | +| time/ | | +| fps | 310 | +| iterations | 3604 | +| time_elapsed | 11898 | +| total_timesteps | 3690496 | +| train/ | | +| approx_kl | 1.4981095 | +| clip_fraction | 0.463 | +| clip_range | 0.2 | +| entropy_loss | -0.377 | +| explained_variance | -3.84 | +| learning_rate | 0.0001 | +| loss | -0.0777 | +| n_updates | 96560 | +| policy_gradient_loss | -0.0686 | +| value_loss | 0.000327 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.64e+03 | +| ep_rew_mean | 0.256 | +| time/ | | +| fps | 310 | +| iterations | 3605 | +| time_elapsed | 11901 | +| total_timesteps | 3691520 | +| train/ | | +| approx_kl | 2.1820297 | +| clip_fraction | 0.51 | +| clip_range | 0.2 | +| entropy_loss | -0.435 | +| explained_variance | -1.12 | +| learning_rate | 0.0001 | +| loss | -0.0758 | +| n_updates | 96570 | +| policy_gradient_loss | -0.0631 | +| value_loss | 0.000349 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.65e+03 | +| ep_rew_mean | 0.256 | +| time/ | | +| fps | 310 | +| iterations | 3606 | +| time_elapsed | 11904 | +| total_timesteps | 3692544 | +| train/ | | +| approx_kl | 2.450582 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.346 | +| explained_variance | -1.46 | +| learning_rate | 0.0001 | +| loss | -0.0564 | +| n_updates | 96580 | +| policy_gradient_loss | -0.0593 | +| value_loss | 0.000398 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.65e+03 | +| ep_rew_mean | 0.256 | +| time/ | | +| fps | 310 | +| iterations | 3607 | +| time_elapsed | 11907 | +| total_timesteps | 3693568 | +| train/ | | +| approx_kl | 2.3766963 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.363 | +| explained_variance | -3.91 | +| learning_rate | 0.0001 | +| loss | -0.106 | +| n_updates | 96590 | +| policy_gradient_loss | -0.0712 | +| value_loss | 0.000386 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.65e+03 | +| ep_rew_mean | 0.256 | +| time/ | | +| fps | 310 | +| iterations | 3608 | +| time_elapsed | 11910 | +| total_timesteps | 3694592 | +| train/ | | +| approx_kl | 9.057508 | +| clip_fraction | 0.489 | +| clip_range | 0.2 | +| entropy_loss | -0.383 | +| explained_variance | -2.11 | +| learning_rate | 0.0001 | +| loss | -0.0304 | +| n_updates | 96600 | +| policy_gradient_loss | -0.0548 | +| value_loss | 0.000515 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.252 | +| time/ | | +| fps | 310 | +| iterations | 3609 | +| time_elapsed | 11914 | +| total_timesteps | 3695616 | +| train/ | | +| approx_kl | 1.8546805 | +| clip_fraction | 0.51 | +| clip_range | 0.2 | +| entropy_loss | -0.415 | +| explained_variance | -4.6 | +| learning_rate | 0.0001 | +| loss | -0.0979 | +| n_updates | 96610 | +| policy_gradient_loss | -0.0714 | +| value_loss | 0.000327 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.252 | +| time/ | | +| fps | 310 | +| iterations | 3610 | +| time_elapsed | 11917 | +| total_timesteps | 3696640 | +| train/ | | +| approx_kl | 2.139778 | +| clip_fraction | 0.532 | +| clip_range | 0.2 | +| entropy_loss | -0.424 | +| explained_variance | -1.2 | +| learning_rate | 0.0001 | +| loss | -0.0751 | +| n_updates | 96620 | +| policy_gradient_loss | -0.0658 | +| value_loss | 0.000316 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.252 | +| time/ | | +| fps | 310 | +| iterations | 3611 | +| time_elapsed | 11920 | +| total_timesteps | 3697664 | +| train/ | | +| approx_kl | 2.2804298 | +| clip_fraction | 0.517 | +| clip_range | 0.2 | +| entropy_loss | -0.4 | +| explained_variance | -3.91 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 96630 | +| policy_gradient_loss | -0.0706 | +| value_loss | 0.000643 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.25 | +| time/ | | +| fps | 310 | +| iterations | 3612 | +| time_elapsed | 11924 | +| total_timesteps | 3698688 | +| train/ | | +| approx_kl | 1.8331897 | +| clip_fraction | 0.482 | +| clip_range | 0.2 | +| entropy_loss | -0.387 | +| explained_variance | -7.38 | +| learning_rate | 0.0001 | +| loss | -0.083 | +| n_updates | 96640 | +| policy_gradient_loss | -0.059 | +| value_loss | 0.000259 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.25 | +| time/ | | +| fps | 310 | +| iterations | 3613 | +| time_elapsed | 11927 | +| total_timesteps | 3699712 | +| train/ | | +| approx_kl | 2.6078873 | +| clip_fraction | 0.494 | +| clip_range | 0.2 | +| entropy_loss | -0.394 | +| explained_variance | -1.47 | +| learning_rate | 0.0001 | +| loss | -0.0732 | +| n_updates | 96650 | +| policy_gradient_loss | -0.0644 | +| value_loss | 0.00068 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.25 | +| time/ | | +| fps | 310 | +| iterations | 3614 | +| time_elapsed | 11930 | +| total_timesteps | 3700736 | +| train/ | | +| approx_kl | 2.0162005 | +| clip_fraction | 0.451 | +| clip_range | 0.2 | +| entropy_loss | -0.36 | +| explained_variance | -3.13 | +| learning_rate | 0.0001 | +| loss | -0.0871 | +| n_updates | 96660 | +| policy_gradient_loss | -0.0658 | +| value_loss | 0.000512 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.25 | +| time/ | | +| fps | 310 | +| iterations | 3615 | +| time_elapsed | 11934 | +| total_timesteps | 3701760 | +| train/ | | +| approx_kl | 1.7032369 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.374 | +| explained_variance | -2.42 | +| learning_rate | 0.0001 | +| loss | -0.088 | +| n_updates | 96670 | +| policy_gradient_loss | -0.0665 | +| value_loss | 0.000276 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.247 | +| time/ | | +| fps | 310 | +| iterations | 3616 | +| time_elapsed | 11937 | +| total_timesteps | 3702784 | +| train/ | | +| approx_kl | 1.965368 | +| clip_fraction | 0.486 | +| clip_range | 0.2 | +| entropy_loss | -0.403 | +| explained_variance | -1.35 | +| learning_rate | 0.0001 | +| loss | -0.111 | +| n_updates | 96680 | +| policy_gradient_loss | -0.0663 | +| value_loss | 0.000418 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.247 | +| time/ | | +| fps | 310 | +| iterations | 3617 | +| time_elapsed | 11940 | +| total_timesteps | 3703808 | +| train/ | | +| approx_kl | 2.1477938 | +| clip_fraction | 0.515 | +| clip_range | 0.2 | +| entropy_loss | -0.461 | +| explained_variance | -1.69 | +| learning_rate | 0.0001 | +| loss | -0.0835 | +| n_updates | 96690 | +| policy_gradient_loss | -0.0645 | +| value_loss | 0.000401 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.247 | +| time/ | | +| fps | 310 | +| iterations | 3618 | +| time_elapsed | 11944 | +| total_timesteps | 3704832 | +| train/ | | +| approx_kl | 1.8917208 | +| clip_fraction | 0.51 | +| clip_range | 0.2 | +| entropy_loss | -0.436 | +| explained_variance | -1.47 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 96700 | +| policy_gradient_loss | -0.0693 | +| value_loss | 0.000411 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.245 | +| time/ | | +| fps | 310 | +| iterations | 3619 | +| time_elapsed | 11947 | +| total_timesteps | 3705856 | +| train/ | | +| approx_kl | 1.6519803 | +| clip_fraction | 0.476 | +| clip_range | 0.2 | +| entropy_loss | -0.425 | +| explained_variance | -1.48 | +| learning_rate | 0.0001 | +| loss | -0.0672 | +| n_updates | 96710 | +| policy_gradient_loss | -0.0619 | +| value_loss | 0.000421 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.245 | +| time/ | | +| fps | 310 | +| iterations | 3620 | +| time_elapsed | 11951 | +| total_timesteps | 3706880 | +| train/ | | +| approx_kl | 2.061674 | +| clip_fraction | 0.441 | +| clip_range | 0.2 | +| entropy_loss | -0.378 | +| explained_variance | -4.72 | +| learning_rate | 0.0001 | +| loss | -0.0992 | +| n_updates | 96720 | +| policy_gradient_loss | -0.0606 | +| value_loss | 0.00041 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.245 | +| time/ | | +| fps | 310 | +| iterations | 3621 | +| time_elapsed | 11954 | +| total_timesteps | 3707904 | +| train/ | | +| approx_kl | 2.1450648 | +| clip_fraction | 0.501 | +| clip_range | 0.2 | +| entropy_loss | -0.392 | +| explained_variance | -1.16 | +| learning_rate | 0.0001 | +| loss | -0.0904 | +| n_updates | 96730 | +| policy_gradient_loss | -0.0688 | +| value_loss | 0.000645 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.243 | +| time/ | | +| fps | 310 | +| iterations | 3622 | +| time_elapsed | 11957 | +| total_timesteps | 3708928 | +| train/ | | +| approx_kl | 2.2469049 | +| clip_fraction | 0.474 | +| clip_range | 0.2 | +| entropy_loss | -0.362 | +| explained_variance | -7.01 | +| learning_rate | 0.0001 | +| loss | -0.086 | +| n_updates | 96740 | +| policy_gradient_loss | -0.0678 | +| value_loss | 0.000519 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.243 | +| time/ | | +| fps | 310 | +| iterations | 3623 | +| time_elapsed | 11960 | +| total_timesteps | 3709952 | +| train/ | | +| approx_kl | 1.8826749 | +| clip_fraction | 0.454 | +| clip_range | 0.2 | +| entropy_loss | -0.354 | +| explained_variance | -8.16 | +| learning_rate | 0.0001 | +| loss | -0.0716 | +| n_updates | 96750 | +| policy_gradient_loss | -0.0631 | +| value_loss | 0.000257 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.242 | +| time/ | | +| fps | 310 | +| iterations | 3624 | +| time_elapsed | 11963 | +| total_timesteps | 3710976 | +| train/ | | +| approx_kl | 2.05976 | +| clip_fraction | 0.49 | +| clip_range | 0.2 | +| entropy_loss | -0.385 | +| explained_variance | -1.6 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 96760 | +| policy_gradient_loss | -0.0658 | +| value_loss | 0.000247 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.242 | +| time/ | | +| fps | 310 | +| iterations | 3625 | +| time_elapsed | 11966 | +| total_timesteps | 3712000 | +| train/ | | +| approx_kl | 1.6461997 | +| clip_fraction | 0.447 | +| clip_range | 0.2 | +| entropy_loss | -0.357 | +| explained_variance | -2.2 | +| learning_rate | 0.0001 | +| loss | -0.0875 | +| n_updates | 96770 | +| policy_gradient_loss | -0.0637 | +| value_loss | 0.000465 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.242 | +| time/ | | +| fps | 310 | +| iterations | 3626 | +| time_elapsed | 11970 | +| total_timesteps | 3713024 | +| train/ | | +| approx_kl | 2.0830874 | +| clip_fraction | 0.472 | +| clip_range | 0.2 | +| entropy_loss | -0.351 | +| explained_variance | -5.03 | +| learning_rate | 0.0001 | +| loss | -0.0938 | +| n_updates | 96780 | +| policy_gradient_loss | -0.0713 | +| value_loss | 0.000567 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.242 | +| time/ | | +| fps | 310 | +| iterations | 3627 | +| time_elapsed | 11973 | +| total_timesteps | 3714048 | +| train/ | | +| approx_kl | 1.6969662 | +| clip_fraction | 0.468 | +| clip_range | 0.2 | +| entropy_loss | -0.396 | +| explained_variance | -2.03 | +| learning_rate | 0.0001 | +| loss | -0.107 | +| n_updates | 96790 | +| policy_gradient_loss | -0.0647 | +| value_loss | 0.000365 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.24 | +| time/ | | +| fps | 310 | +| iterations | 3628 | +| time_elapsed | 11976 | +| total_timesteps | 3715072 | +| train/ | | +| approx_kl | 1.9797058 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.406 | +| explained_variance | -0.935 | +| learning_rate | 0.0001 | +| loss | -0.113 | +| n_updates | 96800 | +| policy_gradient_loss | -0.0552 | +| value_loss | 0.000696 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.24 | +| time/ | | +| fps | 310 | +| iterations | 3629 | +| time_elapsed | 11979 | +| total_timesteps | 3716096 | +| train/ | | +| approx_kl | 1.9162813 | +| clip_fraction | 0.435 | +| clip_range | 0.2 | +| entropy_loss | -0.353 | +| explained_variance | -1.42 | +| learning_rate | 0.0001 | +| loss | -0.0838 | +| n_updates | 96810 | +| policy_gradient_loss | -0.0563 | +| value_loss | 0.000646 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.78e+03 | +| ep_rew_mean | 0.242 | +| time/ | | +| fps | 310 | +| iterations | 3630 | +| time_elapsed | 11982 | +| total_timesteps | 3717120 | +| train/ | | +| approx_kl | 1.7695545 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.383 | +| explained_variance | -2.39 | +| learning_rate | 0.0001 | +| loss | -0.0996 | +| n_updates | 96820 | +| policy_gradient_loss | -0.0628 | +| value_loss | 0.000428 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.78e+03 | +| ep_rew_mean | 0.242 | +| time/ | | +| fps | 310 | +| iterations | 3631 | +| time_elapsed | 11986 | +| total_timesteps | 3718144 | +| train/ | | +| approx_kl | 2.1152713 | +| clip_fraction | 0.482 | +| clip_range | 0.2 | +| entropy_loss | -0.403 | +| explained_variance | -1.87 | +| learning_rate | 0.0001 | +| loss | -0.106 | +| n_updates | 96830 | +| policy_gradient_loss | -0.0735 | +| value_loss | 0.000462 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.247 | +| time/ | | +| fps | 310 | +| iterations | 3632 | +| time_elapsed | 11989 | +| total_timesteps | 3719168 | +| train/ | | +| approx_kl | 1.9776189 | +| clip_fraction | 0.546 | +| clip_range | 0.2 | +| entropy_loss | -0.498 | +| explained_variance | -1.61 | +| learning_rate | 0.0001 | +| loss | -0.0671 | +| n_updates | 96840 | +| policy_gradient_loss | -0.059 | +| value_loss | 0.000598 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.247 | +| time/ | | +| fps | 310 | +| iterations | 3633 | +| time_elapsed | 11993 | +| total_timesteps | 3720192 | +| train/ | | +| approx_kl | 2.0702305 | +| clip_fraction | 0.496 | +| clip_range | 0.2 | +| entropy_loss | -0.385 | +| explained_variance | -2.86 | +| learning_rate | 0.0001 | +| loss | -0.0877 | +| n_updates | 96850 | +| policy_gradient_loss | -0.0752 | +| value_loss | 0.000699 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.8e+03 | +| ep_rew_mean | 0.246 | +| time/ | | +| fps | 310 | +| iterations | 3634 | +| time_elapsed | 11997 | +| total_timesteps | 3721216 | +| train/ | | +| approx_kl | 2.1892285 | +| clip_fraction | 0.474 | +| clip_range | 0.2 | +| entropy_loss | -0.359 | +| explained_variance | -4.19 | +| learning_rate | 0.0001 | +| loss | -0.0902 | +| n_updates | 96860 | +| policy_gradient_loss | -0.0728 | +| value_loss | 0.000493 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.8e+03 | +| ep_rew_mean | 0.246 | +| time/ | | +| fps | 310 | +| iterations | 3635 | +| time_elapsed | 12000 | +| total_timesteps | 3722240 | +| train/ | | +| approx_kl | 1.7887777 | +| clip_fraction | 0.507 | +| clip_range | 0.2 | +| entropy_loss | -0.387 | +| explained_variance | -2.54 | +| learning_rate | 0.0001 | +| loss | -0.0764 | +| n_updates | 96870 | +| policy_gradient_loss | -0.0616 | +| value_loss | 0.000295 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.8e+03 | +| ep_rew_mean | 0.246 | +| time/ | | +| fps | 310 | +| iterations | 3636 | +| time_elapsed | 12004 | +| total_timesteps | 3723264 | +| train/ | | +| approx_kl | 2.0248928 | +| clip_fraction | 0.491 | +| clip_range | 0.2 | +| entropy_loss | -0.39 | +| explained_variance | -0.995 | +| learning_rate | 0.0001 | +| loss | -0.0888 | +| n_updates | 96880 | +| policy_gradient_loss | -0.0637 | +| value_loss | 0.000226 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.81e+03 | +| ep_rew_mean | 0.243 | +| time/ | | +| fps | 310 | +| iterations | 3637 | +| time_elapsed | 12007 | +| total_timesteps | 3724288 | +| train/ | | +| approx_kl | 1.9958951 | +| clip_fraction | 0.494 | +| clip_range | 0.2 | +| entropy_loss | -0.419 | +| explained_variance | -0.878 | +| learning_rate | 0.0001 | +| loss | -0.0863 | +| n_updates | 96890 | +| policy_gradient_loss | -0.066 | +| value_loss | 0.000335 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.81e+03 | +| ep_rew_mean | 0.243 | +| time/ | | +| fps | 310 | +| iterations | 3638 | +| time_elapsed | 12010 | +| total_timesteps | 3725312 | +| train/ | | +| approx_kl | 2.9105406 | +| clip_fraction | 0.478 | +| clip_range | 0.2 | +| entropy_loss | -0.418 | +| explained_variance | -1.75 | +| learning_rate | 0.0001 | +| loss | -0.0718 | +| n_updates | 96900 | +| policy_gradient_loss | -0.0679 | +| value_loss | 0.000399 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.81e+03 | +| ep_rew_mean | 0.24 | +| time/ | | +| fps | 310 | +| iterations | 3639 | +| time_elapsed | 12014 | +| total_timesteps | 3726336 | +| train/ | | +| approx_kl | 2.3506107 | +| clip_fraction | 0.512 | +| clip_range | 0.2 | +| entropy_loss | -0.39 | +| explained_variance | -1.64 | +| learning_rate | 0.0001 | +| loss | -0.0744 | +| n_updates | 96910 | +| policy_gradient_loss | -0.074 | +| value_loss | 0.000285 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.81e+03 | +| ep_rew_mean | 0.24 | +| time/ | | +| fps | 310 | +| iterations | 3640 | +| time_elapsed | 12017 | +| total_timesteps | 3727360 | +| train/ | | +| approx_kl | 2.4082918 | +| clip_fraction | 0.479 | +| clip_range | 0.2 | +| entropy_loss | -0.349 | +| explained_variance | -0.992 | +| learning_rate | 0.0001 | +| loss | -0.0865 | +| n_updates | 96920 | +| policy_gradient_loss | -0.0698 | +| value_loss | 0.000415 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.82e+03 | +| ep_rew_mean | 0.242 | +| time/ | | +| fps | 310 | +| iterations | 3641 | +| time_elapsed | 12020 | +| total_timesteps | 3728384 | +| train/ | | +| approx_kl | 2.4967785 | +| clip_fraction | 0.513 | +| clip_range | 0.2 | +| entropy_loss | -0.428 | +| explained_variance | -2.84 | +| learning_rate | 0.0001 | +| loss | -0.0822 | +| n_updates | 96930 | +| policy_gradient_loss | -0.0763 | +| value_loss | 0.000269 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.82e+03 | +| ep_rew_mean | 0.242 | +| time/ | | +| fps | 310 | +| iterations | 3642 | +| time_elapsed | 12023 | +| total_timesteps | 3729408 | +| train/ | | +| approx_kl | 1.9111106 | +| clip_fraction | 0.474 | +| clip_range | 0.2 | +| entropy_loss | -0.403 | +| explained_variance | -0.818 | +| learning_rate | 0.0001 | +| loss | -0.0796 | +| n_updates | 96940 | +| policy_gradient_loss | -0.0631 | +| value_loss | 0.000727 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.244 | +| time/ | | +| fps | 310 | +| iterations | 3643 | +| time_elapsed | 12026 | +| total_timesteps | 3730432 | +| train/ | | +| approx_kl | 1.6738819 | +| clip_fraction | 0.505 | +| clip_range | 0.2 | +| entropy_loss | -0.446 | +| explained_variance | -0.995 | +| learning_rate | 0.0001 | +| loss | -0.0985 | +| n_updates | 96950 | +| policy_gradient_loss | -0.0666 | +| value_loss | 0.000557 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.244 | +| time/ | | +| fps | 310 | +| iterations | 3644 | +| time_elapsed | 12029 | +| total_timesteps | 3731456 | +| train/ | | +| approx_kl | 4.4837556 | +| clip_fraction | 0.459 | +| clip_range | 0.2 | +| entropy_loss | -0.382 | +| explained_variance | -1.76 | +| learning_rate | 0.0001 | +| loss | -0.113 | +| n_updates | 96960 | +| policy_gradient_loss | -0.0685 | +| value_loss | 0.000573 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.243 | +| time/ | | +| fps | 310 | +| iterations | 3645 | +| time_elapsed | 12033 | +| total_timesteps | 3732480 | +| train/ | | +| approx_kl | 1.8201869 | +| clip_fraction | 0.468 | +| clip_range | 0.2 | +| entropy_loss | -0.368 | +| explained_variance | -1.33 | +| learning_rate | 0.0001 | +| loss | -0.109 | +| n_updates | 96970 | +| policy_gradient_loss | -0.0649 | +| value_loss | 0.000529 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.243 | +| time/ | | +| fps | 310 | +| iterations | 3646 | +| time_elapsed | 12036 | +| total_timesteps | 3733504 | +| train/ | | +| approx_kl | 1.8920727 | +| clip_fraction | 0.477 | +| clip_range | 0.2 | +| entropy_loss | -0.409 | +| explained_variance | -4.87 | +| learning_rate | 0.0001 | +| loss | -0.065 | +| n_updates | 96980 | +| policy_gradient_loss | -0.0658 | +| value_loss | 0.00031 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.243 | +| time/ | | +| fps | 310 | +| iterations | 3647 | +| time_elapsed | 12039 | +| total_timesteps | 3734528 | +| train/ | | +| approx_kl | 2.4820929 | +| clip_fraction | 0.46 | +| clip_range | 0.2 | +| entropy_loss | -0.329 | +| explained_variance | -1.82 | +| learning_rate | 0.0001 | +| loss | -0.0976 | +| n_updates | 96990 | +| policy_gradient_loss | -0.0661 | +| value_loss | 0.000376 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.243 | +| time/ | | +| fps | 310 | +| iterations | 3648 | +| time_elapsed | 12042 | +| total_timesteps | 3735552 | +| train/ | | +| approx_kl | 2.355688 | +| clip_fraction | 0.478 | +| clip_range | 0.2 | +| entropy_loss | -0.388 | +| explained_variance | -1.09 | +| learning_rate | 0.0001 | +| loss | -0.0905 | +| n_updates | 97000 | +| policy_gradient_loss | -0.0697 | +| value_loss | 0.000446 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.243 | +| time/ | | +| fps | 310 | +| iterations | 3649 | +| time_elapsed | 12045 | +| total_timesteps | 3736576 | +| train/ | | +| approx_kl | 1.98945 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.413 | +| explained_variance | -2.24 | +| learning_rate | 0.0001 | +| loss | -0.0819 | +| n_updates | 97010 | +| policy_gradient_loss | -0.0676 | +| value_loss | 0.000527 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.243 | +| time/ | | +| fps | 310 | +| iterations | 3650 | +| time_elapsed | 12049 | +| total_timesteps | 3737600 | +| train/ | | +| approx_kl | 2.032149 | +| clip_fraction | 0.536 | +| clip_range | 0.2 | +| entropy_loss | -0.506 | +| explained_variance | -4.14 | +| learning_rate | 0.0001 | +| loss | -0.106 | +| n_updates | 97020 | +| policy_gradient_loss | -0.0673 | +| value_loss | 0.000218 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.243 | +| time/ | | +| fps | 310 | +| iterations | 3651 | +| time_elapsed | 12052 | +| total_timesteps | 3738624 | +| train/ | | +| approx_kl | 1.761816 | +| clip_fraction | 0.494 | +| clip_range | 0.2 | +| entropy_loss | -0.406 | +| explained_variance | -0.751 | +| learning_rate | 0.0001 | +| loss | -0.0921 | +| n_updates | 97030 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000386 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.243 | +| time/ | | +| fps | 310 | +| iterations | 3652 | +| time_elapsed | 12055 | +| total_timesteps | 3739648 | +| train/ | | +| approx_kl | 2.0236926 | +| clip_fraction | 0.535 | +| clip_range | 0.2 | +| entropy_loss | -0.482 | +| explained_variance | -2.41 | +| learning_rate | 0.0001 | +| loss | -0.1 | +| n_updates | 97040 | +| policy_gradient_loss | -0.0781 | +| value_loss | 0.000412 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.24 | +| time/ | | +| fps | 310 | +| iterations | 3653 | +| time_elapsed | 12059 | +| total_timesteps | 3740672 | +| train/ | | +| approx_kl | 2.064173 | +| clip_fraction | 0.516 | +| clip_range | 0.2 | +| entropy_loss | -0.419 | +| explained_variance | -1.41 | +| learning_rate | 0.0001 | +| loss | -0.109 | +| n_updates | 97050 | +| policy_gradient_loss | -0.0694 | +| value_loss | 0.000372 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.24 | +| time/ | | +| fps | 310 | +| iterations | 3654 | +| time_elapsed | 12062 | +| total_timesteps | 3741696 | +| train/ | | +| approx_kl | 2.2258594 | +| clip_fraction | 0.469 | +| clip_range | 0.2 | +| entropy_loss | -0.373 | +| explained_variance | -2.21 | +| learning_rate | 0.0001 | +| loss | -0.097 | +| n_updates | 97060 | +| policy_gradient_loss | -0.0648 | +| value_loss | 0.000647 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.238 | +| time/ | | +| fps | 310 | +| iterations | 3655 | +| time_elapsed | 12066 | +| total_timesteps | 3742720 | +| train/ | | +| approx_kl | 1.8936884 | +| clip_fraction | 0.478 | +| clip_range | 0.2 | +| entropy_loss | -0.39 | +| explained_variance | -1.72 | +| learning_rate | 0.0001 | +| loss | -0.0987 | +| n_updates | 97070 | +| policy_gradient_loss | -0.0678 | +| value_loss | 0.000406 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.238 | +| time/ | | +| fps | 310 | +| iterations | 3656 | +| time_elapsed | 12069 | +| total_timesteps | 3743744 | +| train/ | | +| approx_kl | 2.2369313 | +| clip_fraction | 0.491 | +| clip_range | 0.2 | +| entropy_loss | -0.388 | +| explained_variance | -2.06 | +| learning_rate | 0.0001 | +| loss | -0.0836 | +| n_updates | 97080 | +| policy_gradient_loss | -0.0662 | +| value_loss | 0.000429 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.89e+03 | +| ep_rew_mean | 0.238 | +| time/ | | +| fps | 310 | +| iterations | 3657 | +| time_elapsed | 12072 | +| total_timesteps | 3744768 | +| train/ | | +| approx_kl | 1.9137063 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.414 | +| explained_variance | -2.55 | +| learning_rate | 0.0001 | +| loss | -0.0608 | +| n_updates | 97090 | +| policy_gradient_loss | -0.0657 | +| value_loss | 0.000386 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.89e+03 | +| ep_rew_mean | 0.238 | +| time/ | | +| fps | 310 | +| iterations | 3658 | +| time_elapsed | 12075 | +| total_timesteps | 3745792 | +| train/ | | +| approx_kl | 1.9001825 | +| clip_fraction | 0.495 | +| clip_range | 0.2 | +| entropy_loss | -0.387 | +| explained_variance | -4.93 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 97100 | +| policy_gradient_loss | -0.0668 | +| value_loss | 0.000239 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.89e+03 | +| ep_rew_mean | 0.238 | +| time/ | | +| fps | 310 | +| iterations | 3659 | +| time_elapsed | 12078 | +| total_timesteps | 3746816 | +| train/ | | +| approx_kl | 2.6201892 | +| clip_fraction | 0.517 | +| clip_range | 0.2 | +| entropy_loss | -0.387 | +| explained_variance | -1.43 | +| learning_rate | 0.0001 | +| loss | -0.0973 | +| n_updates | 97110 | +| policy_gradient_loss | -0.0671 | +| value_loss | 0.000342 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.91e+03 | +| ep_rew_mean | 0.235 | +| time/ | | +| fps | 310 | +| iterations | 3660 | +| time_elapsed | 12081 | +| total_timesteps | 3747840 | +| train/ | | +| approx_kl | 1.6251571 | +| clip_fraction | 0.448 | +| clip_range | 0.2 | +| entropy_loss | -0.382 | +| explained_variance | -5.41 | +| learning_rate | 0.0001 | +| loss | -0.0882 | +| n_updates | 97120 | +| policy_gradient_loss | -0.058 | +| value_loss | 0.000187 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.91e+03 | +| ep_rew_mean | 0.235 | +| time/ | | +| fps | 310 | +| iterations | 3661 | +| time_elapsed | 12085 | +| total_timesteps | 3748864 | +| train/ | | +| approx_kl | 1.7928908 | +| clip_fraction | 0.462 | +| clip_range | 0.2 | +| entropy_loss | -0.384 | +| explained_variance | -0.618 | +| learning_rate | 0.0001 | +| loss | -0.11 | +| n_updates | 97130 | +| policy_gradient_loss | -0.0581 | +| value_loss | 0.000649 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.92e+03 | +| ep_rew_mean | 0.236 | +| time/ | | +| fps | 310 | +| iterations | 3662 | +| time_elapsed | 12088 | +| total_timesteps | 3749888 | +| train/ | | +| approx_kl | 4.817507 | +| clip_fraction | 0.535 | +| clip_range | 0.2 | +| entropy_loss | -0.415 | +| explained_variance | -2.4 | +| learning_rate | 0.0001 | +| loss | -0.114 | +| n_updates | 97140 | +| policy_gradient_loss | -0.0756 | +| value_loss | 0.000563 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.92e+03 | +| ep_rew_mean | 0.236 | +| time/ | | +| fps | 310 | +| iterations | 3663 | +| time_elapsed | 12091 | +| total_timesteps | 3750912 | +| train/ | | +| approx_kl | 2.586805 | +| clip_fraction | 0.459 | +| clip_range | 0.2 | +| entropy_loss | -0.365 | +| explained_variance | -2.21 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 97150 | +| policy_gradient_loss | -0.0675 | +| value_loss | 0.000292 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.92e+03 | +| ep_rew_mean | 0.236 | +| time/ | | +| fps | 310 | +| iterations | 3664 | +| time_elapsed | 12094 | +| total_timesteps | 3751936 | +| train/ | | +| approx_kl | 2.3895469 | +| clip_fraction | 0.501 | +| clip_range | 0.2 | +| entropy_loss | -0.376 | +| explained_variance | -2.69 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 97160 | +| policy_gradient_loss | -0.0749 | +| value_loss | 0.00045 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.93e+03 | +| ep_rew_mean | 0.234 | +| time/ | | +| fps | 310 | +| iterations | 3665 | +| time_elapsed | 12097 | +| total_timesteps | 3752960 | +| train/ | | +| approx_kl | 2.9490833 | +| clip_fraction | 0.515 | +| clip_range | 0.2 | +| entropy_loss | -0.423 | +| explained_variance | -8.25 | +| learning_rate | 0.0001 | +| loss | -0.0808 | +| n_updates | 97170 | +| policy_gradient_loss | -0.0703 | +| value_loss | 0.000257 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.93e+03 | +| ep_rew_mean | 0.234 | +| time/ | | +| fps | 310 | +| iterations | 3666 | +| time_elapsed | 12101 | +| total_timesteps | 3753984 | +| train/ | | +| approx_kl | 1.6403493 | +| clip_fraction | 0.456 | +| clip_range | 0.2 | +| entropy_loss | -0.397 | +| explained_variance | -1.25 | +| learning_rate | 0.0001 | +| loss | -0.0846 | +| n_updates | 97180 | +| policy_gradient_loss | -0.0622 | +| value_loss | 0.000471 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.94e+03 | +| ep_rew_mean | 0.239 | +| time/ | | +| fps | 310 | +| iterations | 3667 | +| time_elapsed | 12104 | +| total_timesteps | 3755008 | +| train/ | | +| approx_kl | 1.9506737 | +| clip_fraction | 0.53 | +| clip_range | 0.2 | +| entropy_loss | -0.52 | +| explained_variance | -1.17 | +| learning_rate | 0.0001 | +| loss | -0.0866 | +| n_updates | 97190 | +| policy_gradient_loss | -0.0731 | +| value_loss | 0.000577 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.94e+03 | +| ep_rew_mean | 0.239 | +| time/ | | +| fps | 310 | +| iterations | 3668 | +| time_elapsed | 12108 | +| total_timesteps | 3756032 | +| train/ | | +| approx_kl | 1.6109529 | +| clip_fraction | 0.49 | +| clip_range | 0.2 | +| entropy_loss | -0.438 | +| explained_variance | -1.72 | +| learning_rate | 0.0001 | +| loss | -0.0813 | +| n_updates | 97200 | +| policy_gradient_loss | -0.0692 | +| value_loss | 0.000695 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.95e+03 | +| ep_rew_mean | 0.242 | +| time/ | | +| fps | 310 | +| iterations | 3669 | +| time_elapsed | 12112 | +| total_timesteps | 3757056 | +| train/ | | +| approx_kl | 1.974743 | +| clip_fraction | 0.506 | +| clip_range | 0.2 | +| entropy_loss | -0.461 | +| explained_variance | -1.39 | +| learning_rate | 0.0001 | +| loss | -0.0748 | +| n_updates | 97210 | +| policy_gradient_loss | -0.0628 | +| value_loss | 0.000611 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.95e+03 | +| ep_rew_mean | 0.242 | +| time/ | | +| fps | 310 | +| iterations | 3670 | +| time_elapsed | 12115 | +| total_timesteps | 3758080 | +| train/ | | +| approx_kl | 1.7095444 | +| clip_fraction | 0.507 | +| clip_range | 0.2 | +| entropy_loss | -0.416 | +| explained_variance | -1.85 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 97220 | +| policy_gradient_loss | -0.0763 | +| value_loss | 0.000492 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.96e+03 | +| ep_rew_mean | 0.248 | +| time/ | | +| fps | 310 | +| iterations | 3671 | +| time_elapsed | 12119 | +| total_timesteps | 3759104 | +| train/ | | +| approx_kl | 2.0577497 | +| clip_fraction | 0.488 | +| clip_range | 0.2 | +| entropy_loss | -0.362 | +| explained_variance | -2.05 | +| learning_rate | 0.0001 | +| loss | -0.0689 | +| n_updates | 97230 | +| policy_gradient_loss | -0.0616 | +| value_loss | 0.000771 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.96e+03 | +| ep_rew_mean | 0.248 | +| time/ | | +| fps | 310 | +| iterations | 3672 | +| time_elapsed | 12122 | +| total_timesteps | 3760128 | +| train/ | | +| approx_kl | 3.1085548 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.367 | +| explained_variance | -2.16 | +| learning_rate | 0.0001 | +| loss | -0.0998 | +| n_updates | 97240 | +| policy_gradient_loss | -0.0674 | +| value_loss | 0.000702 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.97e+03 | +| ep_rew_mean | 0.25 | +| time/ | | +| fps | 310 | +| iterations | 3673 | +| time_elapsed | 12126 | +| total_timesteps | 3761152 | +| train/ | | +| approx_kl | 1.8826593 | +| clip_fraction | 0.473 | +| clip_range | 0.2 | +| entropy_loss | -0.416 | +| explained_variance | -1.67 | +| learning_rate | 0.0001 | +| loss | -0.0775 | +| n_updates | 97250 | +| policy_gradient_loss | -0.0705 | +| value_loss | 0.000517 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.97e+03 | +| ep_rew_mean | 0.25 | +| time/ | | +| fps | 310 | +| iterations | 3674 | +| time_elapsed | 12129 | +| total_timesteps | 3762176 | +| train/ | | +| approx_kl | 1.6660846 | +| clip_fraction | 0.492 | +| clip_range | 0.2 | +| entropy_loss | -0.408 | +| explained_variance | -3.65 | +| learning_rate | 0.0001 | +| loss | -0.0763 | +| n_updates | 97260 | +| policy_gradient_loss | -0.0657 | +| value_loss | 0.000337 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.97e+03 | +| ep_rew_mean | 0.25 | +| time/ | | +| fps | 310 | +| iterations | 3675 | +| time_elapsed | 12133 | +| total_timesteps | 3763200 | +| train/ | | +| approx_kl | 2.377658 | +| clip_fraction | 0.493 | +| clip_range | 0.2 | +| entropy_loss | -0.39 | +| explained_variance | -0.651 | +| learning_rate | 0.0001 | +| loss | -0.0871 | +| n_updates | 97270 | +| policy_gradient_loss | -0.0658 | +| value_loss | 0.00063 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.98e+03 | +| ep_rew_mean | 0.251 | +| time/ | | +| fps | 310 | +| iterations | 3676 | +| time_elapsed | 12136 | +| total_timesteps | 3764224 | +| train/ | | +| approx_kl | 1.8819356 | +| clip_fraction | 0.461 | +| clip_range | 0.2 | +| entropy_loss | -0.363 | +| explained_variance | -7.72 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 97280 | +| policy_gradient_loss | -0.0675 | +| value_loss | 0.000353 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.98e+03 | +| ep_rew_mean | 0.251 | +| time/ | | +| fps | 310 | +| iterations | 3677 | +| time_elapsed | 12139 | +| total_timesteps | 3765248 | +| train/ | | +| approx_kl | 2.0686343 | +| clip_fraction | 0.466 | +| clip_range | 0.2 | +| entropy_loss | -0.356 | +| explained_variance | -2.08 | +| learning_rate | 0.0001 | +| loss | -0.0911 | +| n_updates | 97290 | +| policy_gradient_loss | -0.0623 | +| value_loss | 0.000385 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.98e+03 | +| ep_rew_mean | 0.245 | +| time/ | | +| fps | 310 | +| iterations | 3678 | +| time_elapsed | 12142 | +| total_timesteps | 3766272 | +| train/ | | +| approx_kl | 2.6658237 | +| clip_fraction | 0.465 | +| clip_range | 0.2 | +| entropy_loss | -0.359 | +| explained_variance | -1.89 | +| learning_rate | 0.0001 | +| loss | -0.0745 | +| n_updates | 97300 | +| policy_gradient_loss | -0.0689 | +| value_loss | 0.000357 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.98e+03 | +| ep_rew_mean | 0.245 | +| time/ | | +| fps | 310 | +| iterations | 3679 | +| time_elapsed | 12145 | +| total_timesteps | 3767296 | +| train/ | | +| approx_kl | 4.0428176 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.36 | +| explained_variance | -1.86 | +| learning_rate | 0.0001 | +| loss | -0.0994 | +| n_updates | 97310 | +| policy_gradient_loss | -0.0702 | +| value_loss | 0.000549 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.98e+03 | +| ep_rew_mean | 0.245 | +| time/ | | +| fps | 310 | +| iterations | 3680 | +| time_elapsed | 12148 | +| total_timesteps | 3768320 | +| train/ | | +| approx_kl | 2.1124167 | +| clip_fraction | 0.507 | +| clip_range | 0.2 | +| entropy_loss | -0.422 | +| explained_variance | -2.88 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 97320 | +| policy_gradient_loss | -0.0709 | +| value_loss | 0.000519 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2e+03 | +| ep_rew_mean | 0.245 | +| time/ | | +| fps | 310 | +| iterations | 3681 | +| time_elapsed | 12152 | +| total_timesteps | 3769344 | +| train/ | | +| approx_kl | 1.7808583 | +| clip_fraction | 0.47 | +| clip_range | 0.2 | +| entropy_loss | -0.384 | +| explained_variance | -6.4 | +| learning_rate | 0.0001 | +| loss | -0.0962 | +| n_updates | 97330 | +| policy_gradient_loss | -0.0633 | +| value_loss | 0.000191 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2e+03 | +| ep_rew_mean | 0.245 | +| time/ | | +| fps | 310 | +| iterations | 3682 | +| time_elapsed | 12155 | +| total_timesteps | 3770368 | +| train/ | | +| approx_kl | 1.9761394 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.378 | +| explained_variance | -2.5 | +| learning_rate | 0.0001 | +| loss | -0.096 | +| n_updates | 97340 | +| policy_gradient_loss | -0.0632 | +| value_loss | 0.000622 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.02e+03 | +| ep_rew_mean | 0.243 | +| time/ | | +| fps | 310 | +| iterations | 3683 | +| time_elapsed | 12158 | +| total_timesteps | 3771392 | +| train/ | | +| approx_kl | 2.4941978 | +| clip_fraction | 0.479 | +| clip_range | 0.2 | +| entropy_loss | -0.347 | +| explained_variance | -0.915 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 97350 | +| policy_gradient_loss | -0.0671 | +| value_loss | 0.000434 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.02e+03 | +| ep_rew_mean | 0.243 | +| time/ | | +| fps | 310 | +| iterations | 3684 | +| time_elapsed | 12162 | +| total_timesteps | 3772416 | +| train/ | | +| approx_kl | 2.6417046 | +| clip_fraction | 0.491 | +| clip_range | 0.2 | +| entropy_loss | -0.338 | +| explained_variance | -4.52 | +| learning_rate | 0.0001 | +| loss | -0.108 | +| n_updates | 97360 | +| policy_gradient_loss | -0.0705 | +| value_loss | 0.00042 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.03e+03 | +| ep_rew_mean | 0.24 | +| time/ | | +| fps | 310 | +| iterations | 3685 | +| time_elapsed | 12165 | +| total_timesteps | 3773440 | +| train/ | | +| approx_kl | 1.822051 | +| clip_fraction | 0.444 | +| clip_range | 0.2 | +| entropy_loss | -0.291 | +| explained_variance | -4.96 | +| learning_rate | 0.0001 | +| loss | -0.105 | +| n_updates | 97370 | +| policy_gradient_loss | -0.0713 | +| value_loss | 0.000484 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.03e+03 | +| ep_rew_mean | 0.24 | +| time/ | | +| fps | 310 | +| iterations | 3686 | +| time_elapsed | 12168 | +| total_timesteps | 3774464 | +| train/ | | +| approx_kl | 2.0212562 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.341 | +| explained_variance | -1.79 | +| learning_rate | 0.0001 | +| loss | -0.0675 | +| n_updates | 97380 | +| policy_gradient_loss | -0.0645 | +| value_loss | 0.000525 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.03e+03 | +| ep_rew_mean | 0.24 | +| time/ | | +| fps | 310 | +| iterations | 3687 | +| time_elapsed | 12172 | +| total_timesteps | 3775488 | +| train/ | | +| approx_kl | 2.3109457 | +| clip_fraction | 0.396 | +| clip_range | 0.2 | +| entropy_loss | -0.301 | +| explained_variance | -3.23 | +| learning_rate | 0.0001 | +| loss | -0.096 | +| n_updates | 97390 | +| policy_gradient_loss | -0.0643 | +| value_loss | 0.0005 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.04e+03 | +| ep_rew_mean | 0.239 | +| time/ | | +| fps | 310 | +| iterations | 3688 | +| time_elapsed | 12175 | +| total_timesteps | 3776512 | +| train/ | | +| approx_kl | 1.8163929 | +| clip_fraction | 0.447 | +| clip_range | 0.2 | +| entropy_loss | -0.35 | +| explained_variance | -1.39 | +| learning_rate | 0.0001 | +| loss | -0.0909 | +| n_updates | 97400 | +| policy_gradient_loss | -0.062 | +| value_loss | 0.000423 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.04e+03 | +| ep_rew_mean | 0.239 | +| time/ | | +| fps | 310 | +| iterations | 3689 | +| time_elapsed | 12178 | +| total_timesteps | 3777536 | +| train/ | | +| approx_kl | 3.0649958 | +| clip_fraction | 0.495 | +| clip_range | 0.2 | +| entropy_loss | -0.363 | +| explained_variance | -9.64 | +| learning_rate | 0.0001 | +| loss | -0.0747 | +| n_updates | 97410 | +| policy_gradient_loss | -0.0742 | +| value_loss | 0.000412 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.04e+03 | +| ep_rew_mean | 0.239 | +| time/ | | +| fps | 310 | +| iterations | 3690 | +| time_elapsed | 12182 | +| total_timesteps | 3778560 | +| train/ | | +| approx_kl | 1.8976331 | +| clip_fraction | 0.458 | +| clip_range | 0.2 | +| entropy_loss | -0.328 | +| explained_variance | -6.87 | +| learning_rate | 0.0001 | +| loss | -0.0919 | +| n_updates | 97420 | +| policy_gradient_loss | -0.074 | +| value_loss | 0.000299 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.05e+03 | +| ep_rew_mean | 0.233 | +| time/ | | +| fps | 310 | +| iterations | 3691 | +| time_elapsed | 12185 | +| total_timesteps | 3779584 | +| train/ | | +| approx_kl | 2.5681822 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.349 | +| explained_variance | -2.44 | +| learning_rate | 0.0001 | +| loss | -0.0635 | +| n_updates | 97430 | +| policy_gradient_loss | -0.0654 | +| value_loss | 0.000578 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.05e+03 | +| ep_rew_mean | 0.233 | +| time/ | | +| fps | 310 | +| iterations | 3692 | +| time_elapsed | 12189 | +| total_timesteps | 3780608 | +| train/ | | +| approx_kl | 2.1544719 | +| clip_fraction | 0.447 | +| clip_range | 0.2 | +| entropy_loss | -0.307 | +| explained_variance | -1.81 | +| learning_rate | 0.0001 | +| loss | -0.0753 | +| n_updates | 97440 | +| policy_gradient_loss | -0.0608 | +| value_loss | 0.000675 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.05e+03 | +| ep_rew_mean | 0.235 | +| time/ | | +| fps | 310 | +| iterations | 3693 | +| time_elapsed | 12192 | +| total_timesteps | 3781632 | +| train/ | | +| approx_kl | 2.3642378 | +| clip_fraction | 0.477 | +| clip_range | 0.2 | +| entropy_loss | -0.345 | +| explained_variance | -2.57 | +| learning_rate | 0.0001 | +| loss | -0.0965 | +| n_updates | 97450 | +| policy_gradient_loss | -0.066 | +| value_loss | 0.000573 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.05e+03 | +| ep_rew_mean | 0.235 | +| time/ | | +| fps | 310 | +| iterations | 3694 | +| time_elapsed | 12195 | +| total_timesteps | 3782656 | +| train/ | | +| approx_kl | 1.8229041 | +| clip_fraction | 0.446 | +| clip_range | 0.2 | +| entropy_loss | -0.335 | +| explained_variance | -0.865 | +| learning_rate | 0.0001 | +| loss | -0.0551 | +| n_updates | 97460 | +| policy_gradient_loss | -0.0625 | +| value_loss | 0.000509 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.06e+03 | +| ep_rew_mean | 0.237 | +| time/ | | +| fps | 310 | +| iterations | 3695 | +| time_elapsed | 12198 | +| total_timesteps | 3783680 | +| train/ | | +| approx_kl | 2.2583575 | +| clip_fraction | 0.506 | +| clip_range | 0.2 | +| entropy_loss | -0.369 | +| explained_variance | -0.743 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 97470 | +| policy_gradient_loss | -0.0778 | +| value_loss | 0.000501 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.06e+03 | +| ep_rew_mean | 0.237 | +| time/ | | +| fps | 310 | +| iterations | 3696 | +| time_elapsed | 12201 | +| total_timesteps | 3784704 | +| train/ | | +| approx_kl | 2.5590363 | +| clip_fraction | 0.46 | +| clip_range | 0.2 | +| entropy_loss | -0.334 | +| explained_variance | -2.01 | +| learning_rate | 0.0001 | +| loss | -0.0998 | +| n_updates | 97480 | +| policy_gradient_loss | -0.0642 | +| value_loss | 0.000631 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.06e+03 | +| ep_rew_mean | 0.237 | +| time/ | | +| fps | 310 | +| iterations | 3697 | +| time_elapsed | 12204 | +| total_timesteps | 3785728 | +| train/ | | +| approx_kl | 2.0935466 | +| clip_fraction | 0.452 | +| clip_range | 0.2 | +| entropy_loss | -0.374 | +| explained_variance | -5.05 | +| learning_rate | 0.0001 | +| loss | -0.0954 | +| n_updates | 97490 | +| policy_gradient_loss | -0.064 | +| value_loss | 0.000486 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.08e+03 | +| ep_rew_mean | 0.245 | +| time/ | | +| fps | 310 | +| iterations | 3698 | +| time_elapsed | 12208 | +| total_timesteps | 3786752 | +| train/ | | +| approx_kl | 1.6409042 | +| clip_fraction | 0.453 | +| clip_range | 0.2 | +| entropy_loss | -0.346 | +| explained_variance | -1.86 | +| learning_rate | 0.0001 | +| loss | 0.108 | +| n_updates | 97500 | +| policy_gradient_loss | -0.0589 | +| value_loss | 0.000459 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.08e+03 | +| ep_rew_mean | 0.245 | +| time/ | | +| fps | 310 | +| iterations | 3699 | +| time_elapsed | 12211 | +| total_timesteps | 3787776 | +| train/ | | +| approx_kl | 2.0998445 | +| clip_fraction | 0.498 | +| clip_range | 0.2 | +| entropy_loss | -0.366 | +| explained_variance | -1.03 | +| learning_rate | 0.0001 | +| loss | -0.114 | +| n_updates | 97510 | +| policy_gradient_loss | -0.0639 | +| value_loss | 0.000726 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.09e+03 | +| ep_rew_mean | 0.244 | +| time/ | | +| fps | 310 | +| iterations | 3700 | +| time_elapsed | 12214 | +| total_timesteps | 3788800 | +| train/ | | +| approx_kl | 2.388897 | +| clip_fraction | 0.503 | +| clip_range | 0.2 | +| entropy_loss | -0.382 | +| explained_variance | -4.04 | +| learning_rate | 0.0001 | +| loss | -0.077 | +| n_updates | 97520 | +| policy_gradient_loss | -0.0685 | +| value_loss | 0.000415 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.09e+03 | +| ep_rew_mean | 0.244 | +| time/ | | +| fps | 310 | +| iterations | 3701 | +| time_elapsed | 12217 | +| total_timesteps | 3789824 | +| train/ | | +| approx_kl | 3.0293193 | +| clip_fraction | 0.473 | +| clip_range | 0.2 | +| entropy_loss | -0.324 | +| explained_variance | -9.43 | +| learning_rate | 0.0001 | +| loss | -0.0739 | +| n_updates | 97530 | +| policy_gradient_loss | -0.0728 | +| value_loss | 0.000175 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.09e+03 | +| ep_rew_mean | 0.244 | +| time/ | | +| fps | 310 | +| iterations | 3702 | +| time_elapsed | 12221 | +| total_timesteps | 3790848 | +| train/ | | +| approx_kl | 2.5662413 | +| clip_fraction | 0.46 | +| clip_range | 0.2 | +| entropy_loss | -0.367 | +| explained_variance | -0.648 | +| learning_rate | 0.0001 | +| loss | -0.0978 | +| n_updates | 97540 | +| policy_gradient_loss | -0.0614 | +| value_loss | 0.000684 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.11e+03 | +| ep_rew_mean | 0.25 | +| time/ | | +| fps | 310 | +| iterations | 3703 | +| time_elapsed | 12224 | +| total_timesteps | 3791872 | +| train/ | | +| approx_kl | 2.0127308 | +| clip_fraction | 0.465 | +| clip_range | 0.2 | +| entropy_loss | -0.323 | +| explained_variance | -0.783 | +| learning_rate | 0.0001 | +| loss | -0.0913 | +| n_updates | 97550 | +| policy_gradient_loss | -0.0627 | +| value_loss | 0.000613 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.11e+03 | +| ep_rew_mean | 0.25 | +| time/ | | +| fps | 310 | +| iterations | 3704 | +| time_elapsed | 12227 | +| total_timesteps | 3792896 | +| train/ | | +| approx_kl | 2.469735 | +| clip_fraction | 0.434 | +| clip_range | 0.2 | +| entropy_loss | -0.28 | +| explained_variance | -5.62 | +| learning_rate | 0.0001 | +| loss | -0.069 | +| n_updates | 97560 | +| policy_gradient_loss | -0.0616 | +| value_loss | 0.000589 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.11e+03 | +| ep_rew_mean | 0.248 | +| time/ | | +| fps | 310 | +| iterations | 3705 | +| time_elapsed | 12231 | +| total_timesteps | 3793920 | +| train/ | | +| approx_kl | 2.2044692 | +| clip_fraction | 0.528 | +| clip_range | 0.2 | +| entropy_loss | -0.414 | +| explained_variance | -1.71 | +| learning_rate | 0.0001 | +| loss | -0.124 | +| n_updates | 97570 | +| policy_gradient_loss | -0.0685 | +| value_loss | 0.000273 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.11e+03 | +| ep_rew_mean | 0.248 | +| time/ | | +| fps | 310 | +| iterations | 3706 | +| time_elapsed | 12235 | +| total_timesteps | 3794944 | +| train/ | | +| approx_kl | 2.9531264 | +| clip_fraction | 0.419 | +| clip_range | 0.2 | +| entropy_loss | -0.284 | +| explained_variance | -6.23 | +| learning_rate | 0.0001 | +| loss | -0.0666 | +| n_updates | 97580 | +| policy_gradient_loss | -0.0569 | +| value_loss | 0.00045 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.11e+03 | +| ep_rew_mean | 0.248 | +| time/ | | +| fps | 310 | +| iterations | 3707 | +| time_elapsed | 12238 | +| total_timesteps | 3795968 | +| train/ | | +| approx_kl | 2.0725389 | +| clip_fraction | 0.484 | +| clip_range | 0.2 | +| entropy_loss | -0.395 | +| explained_variance | -0.358 | +| learning_rate | 0.0001 | +| loss | -0.0867 | +| n_updates | 97590 | +| policy_gradient_loss | -0.0614 | +| value_loss | 0.000447 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.13e+03 | +| ep_rew_mean | 0.245 | +| time/ | | +| fps | 310 | +| iterations | 3708 | +| time_elapsed | 12242 | +| total_timesteps | 3796992 | +| train/ | | +| approx_kl | 7.8871207 | +| clip_fraction | 0.478 | +| clip_range | 0.2 | +| entropy_loss | -0.347 | +| explained_variance | -1.52 | +| learning_rate | 0.0001 | +| loss | -0.0718 | +| n_updates | 97600 | +| policy_gradient_loss | -0.0672 | +| value_loss | 0.000468 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.13e+03 | +| ep_rew_mean | 0.245 | +| time/ | | +| fps | 310 | +| iterations | 3709 | +| time_elapsed | 12245 | +| total_timesteps | 3798016 | +| train/ | | +| approx_kl | 3.192058 | +| clip_fraction | 0.452 | +| clip_range | 0.2 | +| entropy_loss | -0.295 | +| explained_variance | -2.95 | +| learning_rate | 0.0001 | +| loss | -0.0957 | +| n_updates | 97610 | +| policy_gradient_loss | -0.0682 | +| value_loss | 0.000596 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.15e+03 | +| ep_rew_mean | 0.245 | +| time/ | | +| fps | 310 | +| iterations | 3710 | +| time_elapsed | 12248 | +| total_timesteps | 3799040 | +| train/ | | +| approx_kl | 2.4939523 | +| clip_fraction | 0.45 | +| clip_range | 0.2 | +| entropy_loss | -0.352 | +| explained_variance | -3.18 | +| learning_rate | 0.0001 | +| loss | -0.0564 | +| n_updates | 97620 | +| policy_gradient_loss | -0.0587 | +| value_loss | 0.000619 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.15e+03 | +| ep_rew_mean | 0.245 | +| time/ | | +| fps | 310 | +| iterations | 3711 | +| time_elapsed | 12252 | +| total_timesteps | 3800064 | +| train/ | | +| approx_kl | 2.553711 | +| clip_fraction | 0.464 | +| clip_range | 0.2 | +| entropy_loss | -0.329 | +| explained_variance | -1.21 | +| learning_rate | 0.0001 | +| loss | -0.0888 | +| n_updates | 97630 | +| policy_gradient_loss | -0.0639 | +| value_loss | 0.000567 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.16e+03 | +| ep_rew_mean | 0.246 | +| time/ | | +| fps | 310 | +| iterations | 3712 | +| time_elapsed | 12255 | +| total_timesteps | 3801088 | +| train/ | | +| approx_kl | 2.2663906 | +| clip_fraction | 0.497 | +| clip_range | 0.2 | +| entropy_loss | -0.357 | +| explained_variance | -1.69 | +| learning_rate | 0.0001 | +| loss | -0.0853 | +| n_updates | 97640 | +| policy_gradient_loss | -0.068 | +| value_loss | 0.000567 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.16e+03 | +| ep_rew_mean | 0.246 | +| time/ | | +| fps | 310 | +| iterations | 3713 | +| time_elapsed | 12258 | +| total_timesteps | 3802112 | +| train/ | | +| approx_kl | 2.4733763 | +| clip_fraction | 0.482 | +| clip_range | 0.2 | +| entropy_loss | -0.38 | +| explained_variance | -2.07 | +| learning_rate | 0.0001 | +| loss | -0.0782 | +| n_updates | 97650 | +| policy_gradient_loss | -0.0635 | +| value_loss | 0.000355 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.16e+03 | +| ep_rew_mean | 0.246 | +| time/ | | +| fps | 310 | +| iterations | 3714 | +| time_elapsed | 12262 | +| total_timesteps | 3803136 | +| train/ | | +| approx_kl | 1.8114189 | +| clip_fraction | 0.508 | +| clip_range | 0.2 | +| entropy_loss | -0.418 | +| explained_variance | -2.18 | +| learning_rate | 0.0001 | +| loss | -0.113 | +| n_updates | 97660 | +| policy_gradient_loss | -0.07 | +| value_loss | 0.000281 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.17e+03 | +| ep_rew_mean | 0.246 | +| time/ | | +| fps | 310 | +| iterations | 3715 | +| time_elapsed | 12265 | +| total_timesteps | 3804160 | +| train/ | | +| approx_kl | 2.3592286 | +| clip_fraction | 0.476 | +| clip_range | 0.2 | +| entropy_loss | -0.353 | +| explained_variance | -1.94 | +| learning_rate | 0.0001 | +| loss | -0.0939 | +| n_updates | 97670 | +| policy_gradient_loss | -0.0666 | +| value_loss | 0.00033 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.17e+03 | +| ep_rew_mean | 0.246 | +| time/ | | +| fps | 310 | +| iterations | 3716 | +| time_elapsed | 12268 | +| total_timesteps | 3805184 | +| train/ | | +| approx_kl | 1.8303387 | +| clip_fraction | 0.462 | +| clip_range | 0.2 | +| entropy_loss | -0.363 | +| explained_variance | -1.77 | +| learning_rate | 0.0001 | +| loss | -0.0824 | +| n_updates | 97680 | +| policy_gradient_loss | -0.0677 | +| value_loss | 0.000382 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.19e+03 | +| ep_rew_mean | 0.253 | +| time/ | | +| fps | 310 | +| iterations | 3717 | +| time_elapsed | 12271 | +| total_timesteps | 3806208 | +| train/ | | +| approx_kl | 2.333162 | +| clip_fraction | 0.492 | +| clip_range | 0.2 | +| entropy_loss | -0.382 | +| explained_variance | -1.91 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 97690 | +| policy_gradient_loss | -0.069 | +| value_loss | 0.000622 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.19e+03 | +| ep_rew_mean | 0.253 | +| time/ | | +| fps | 310 | +| iterations | 3718 | +| time_elapsed | 12274 | +| total_timesteps | 3807232 | +| train/ | | +| approx_kl | 1.9327625 | +| clip_fraction | 0.513 | +| clip_range | 0.2 | +| entropy_loss | -0.455 | +| explained_variance | -0.787 | +| learning_rate | 0.0001 | +| loss | -0.0787 | +| n_updates | 97700 | +| policy_gradient_loss | -0.0638 | +| value_loss | 0.000406 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.19e+03 | +| ep_rew_mean | 0.253 | +| time/ | | +| fps | 310 | +| iterations | 3719 | +| time_elapsed | 12278 | +| total_timesteps | 3808256 | +| train/ | | +| approx_kl | 1.9367107 | +| clip_fraction | 0.513 | +| clip_range | 0.2 | +| entropy_loss | -0.453 | +| explained_variance | -3.02 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 97710 | +| policy_gradient_loss | -0.0718 | +| value_loss | 0.000372 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.21e+03 | +| ep_rew_mean | 0.257 | +| time/ | | +| fps | 310 | +| iterations | 3720 | +| time_elapsed | 12281 | +| total_timesteps | 3809280 | +| train/ | | +| approx_kl | 1.6758231 | +| clip_fraction | 0.458 | +| clip_range | 0.2 | +| entropy_loss | -0.349 | +| explained_variance | -2.07 | +| learning_rate | 0.0001 | +| loss | -0.0956 | +| n_updates | 97720 | +| policy_gradient_loss | -0.067 | +| value_loss | 0.000176 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.21e+03 | +| ep_rew_mean | 0.257 | +| time/ | | +| fps | 310 | +| iterations | 3721 | +| time_elapsed | 12284 | +| total_timesteps | 3810304 | +| train/ | | +| approx_kl | 1.6269256 | +| clip_fraction | 0.466 | +| clip_range | 0.2 | +| entropy_loss | -0.363 | +| explained_variance | -0.683 | +| learning_rate | 0.0001 | +| loss | -0.0842 | +| n_updates | 97730 | +| policy_gradient_loss | -0.0564 | +| value_loss | 0.000541 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.21e+03 | +| ep_rew_mean | 0.257 | +| time/ | | +| fps | 310 | +| iterations | 3722 | +| time_elapsed | 12288 | +| total_timesteps | 3811328 | +| train/ | | +| approx_kl | 2.0274284 | +| clip_fraction | 0.496 | +| clip_range | 0.2 | +| entropy_loss | -0.37 | +| explained_variance | -2.44 | +| learning_rate | 0.0001 | +| loss | -0.106 | +| n_updates | 97740 | +| policy_gradient_loss | -0.0765 | +| value_loss | 0.000499 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.22e+03 | +| ep_rew_mean | 0.257 | +| time/ | | +| fps | 310 | +| iterations | 3723 | +| time_elapsed | 12291 | +| total_timesteps | 3812352 | +| train/ | | +| approx_kl | 1.9720938 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.371 | +| explained_variance | -2.22 | +| learning_rate | 0.0001 | +| loss | -0.1 | +| n_updates | 97750 | +| policy_gradient_loss | -0.07 | +| value_loss | 0.000397 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.22e+03 | +| ep_rew_mean | 0.257 | +| time/ | | +| fps | 310 | +| iterations | 3724 | +| time_elapsed | 12294 | +| total_timesteps | 3813376 | +| train/ | | +| approx_kl | 2.333 | +| clip_fraction | 0.478 | +| clip_range | 0.2 | +| entropy_loss | -0.359 | +| explained_variance | -2.63 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 97760 | +| policy_gradient_loss | -0.0639 | +| value_loss | 0.000618 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.23e+03 | +| ep_rew_mean | 0.256 | +| time/ | | +| fps | 310 | +| iterations | 3725 | +| time_elapsed | 12298 | +| total_timesteps | 3814400 | +| train/ | | +| approx_kl | 2.2488434 | +| clip_fraction | 0.457 | +| clip_range | 0.2 | +| entropy_loss | -0.341 | +| explained_variance | -1.39 | +| learning_rate | 0.0001 | +| loss | -0.113 | +| n_updates | 97770 | +| policy_gradient_loss | -0.0649 | +| value_loss | 0.000621 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.23e+03 | +| ep_rew_mean | 0.256 | +| time/ | | +| fps | 310 | +| iterations | 3726 | +| time_elapsed | 12301 | +| total_timesteps | 3815424 | +| train/ | | +| approx_kl | 2.044229 | +| clip_fraction | 0.452 | +| clip_range | 0.2 | +| entropy_loss | -0.341 | +| explained_variance | -2.14 | +| learning_rate | 0.0001 | +| loss | -0.125 | +| n_updates | 97780 | +| policy_gradient_loss | -0.0656 | +| value_loss | 0.000632 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.25e+03 | +| ep_rew_mean | 0.26 | +| time/ | | +| fps | 310 | +| iterations | 3727 | +| time_elapsed | 12305 | +| total_timesteps | 3816448 | +| train/ | | +| approx_kl | 2.584802 | +| clip_fraction | 0.466 | +| clip_range | 0.2 | +| entropy_loss | -0.343 | +| explained_variance | -2.38 | +| learning_rate | 0.0001 | +| loss | -0.113 | +| n_updates | 97790 | +| policy_gradient_loss | -0.0552 | +| value_loss | 0.000473 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.25e+03 | +| ep_rew_mean | 0.26 | +| time/ | | +| fps | 310 | +| iterations | 3728 | +| time_elapsed | 12308 | +| total_timesteps | 3817472 | +| train/ | | +| approx_kl | 1.8001708 | +| clip_fraction | 0.436 | +| clip_range | 0.2 | +| entropy_loss | -0.313 | +| explained_variance | -1.57 | +| learning_rate | 0.0001 | +| loss | -0.108 | +| n_updates | 97800 | +| policy_gradient_loss | -0.0657 | +| value_loss | 0.000327 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.26e+03 | +| ep_rew_mean | 0.257 | +| time/ | | +| fps | 310 | +| iterations | 3729 | +| time_elapsed | 12312 | +| total_timesteps | 3818496 | +| train/ | | +| approx_kl | 3.2687266 | +| clip_fraction | 0.417 | +| clip_range | 0.2 | +| entropy_loss | -0.311 | +| explained_variance | -2.58 | +| learning_rate | 0.0001 | +| loss | -0.0467 | +| n_updates | 97810 | +| policy_gradient_loss | -0.0569 | +| value_loss | 0.000467 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.26e+03 | +| ep_rew_mean | 0.257 | +| time/ | | +| fps | 310 | +| iterations | 3730 | +| time_elapsed | 12315 | +| total_timesteps | 3819520 | +| train/ | | +| approx_kl | 3.0622368 | +| clip_fraction | 0.494 | +| clip_range | 0.2 | +| entropy_loss | -0.367 | +| explained_variance | -1.4 | +| learning_rate | 0.0001 | +| loss | -0.0911 | +| n_updates | 97820 | +| policy_gradient_loss | -0.0725 | +| value_loss | 0.000481 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.27e+03 | +| ep_rew_mean | 0.26 | +| time/ | | +| fps | 310 | +| iterations | 3731 | +| time_elapsed | 12318 | +| total_timesteps | 3820544 | +| train/ | | +| approx_kl | 2.684854 | +| clip_fraction | 0.494 | +| clip_range | 0.2 | +| entropy_loss | -0.365 | +| explained_variance | -1.2 | +| learning_rate | 0.0001 | +| loss | -0.0654 | +| n_updates | 97830 | +| policy_gradient_loss | -0.0587 | +| value_loss | 0.0004 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.27e+03 | +| ep_rew_mean | 0.26 | +| time/ | | +| fps | 310 | +| iterations | 3732 | +| time_elapsed | 12321 | +| total_timesteps | 3821568 | +| train/ | | +| approx_kl | 1.5128973 | +| clip_fraction | 0.422 | +| clip_range | 0.2 | +| entropy_loss | -0.343 | +| explained_variance | -2.5 | +| learning_rate | 0.0001 | +| loss | -0.0766 | +| n_updates | 97840 | +| policy_gradient_loss | -0.0588 | +| value_loss | 0.00036 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.27e+03 | +| ep_rew_mean | 0.26 | +| time/ | | +| fps | 310 | +| iterations | 3733 | +| time_elapsed | 12324 | +| total_timesteps | 3822592 | +| train/ | | +| approx_kl | 4.754403 | +| clip_fraction | 0.42 | +| clip_range | 0.2 | +| entropy_loss | -0.301 | +| explained_variance | -1.39 | +| learning_rate | 0.0001 | +| loss | -0.0858 | +| n_updates | 97850 | +| policy_gradient_loss | -0.0627 | +| value_loss | 0.000649 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.29e+03 | +| ep_rew_mean | 0.262 | +| time/ | | +| fps | 310 | +| iterations | 3734 | +| time_elapsed | 12327 | +| total_timesteps | 3823616 | +| train/ | | +| approx_kl | 1.9940007 | +| clip_fraction | 0.427 | +| clip_range | 0.2 | +| entropy_loss | -0.3 | +| explained_variance | -8.91 | +| learning_rate | 0.0001 | +| loss | -0.093 | +| n_updates | 97860 | +| policy_gradient_loss | -0.0633 | +| value_loss | 0.000448 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.29e+03 | +| ep_rew_mean | 0.262 | +| time/ | | +| fps | 310 | +| iterations | 3735 | +| time_elapsed | 12331 | +| total_timesteps | 3824640 | +| train/ | | +| approx_kl | 4.9297957 | +| clip_fraction | 0.479 | +| clip_range | 0.2 | +| entropy_loss | -0.371 | +| explained_variance | -4.46 | +| learning_rate | 0.0001 | +| loss | -0.0832 | +| n_updates | 97870 | +| policy_gradient_loss | -0.068 | +| value_loss | 0.000467 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.29e+03 | +| ep_rew_mean | 0.26 | +| time/ | | +| fps | 310 | +| iterations | 3736 | +| time_elapsed | 12334 | +| total_timesteps | 3825664 | +| train/ | | +| approx_kl | 2.0331903 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.384 | +| explained_variance | -0.832 | +| learning_rate | 0.0001 | +| loss | -0.0819 | +| n_updates | 97880 | +| policy_gradient_loss | -0.0689 | +| value_loss | 0.000488 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.29e+03 | +| ep_rew_mean | 0.26 | +| time/ | | +| fps | 310 | +| iterations | 3737 | +| time_elapsed | 12337 | +| total_timesteps | 3826688 | +| train/ | | +| approx_kl | 2.210751 | +| clip_fraction | 0.447 | +| clip_range | 0.2 | +| entropy_loss | -0.31 | +| explained_variance | -1.32 | +| learning_rate | 0.0001 | +| loss | -0.0887 | +| n_updates | 97890 | +| policy_gradient_loss | -0.0651 | +| value_loss | 0.000925 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.29e+03 | +| ep_rew_mean | 0.26 | +| time/ | | +| fps | 310 | +| iterations | 3738 | +| time_elapsed | 12340 | +| total_timesteps | 3827712 | +| train/ | | +| approx_kl | 2.963099 | +| clip_fraction | 0.477 | +| clip_range | 0.2 | +| entropy_loss | -0.339 | +| explained_variance | -3.42 | +| learning_rate | 0.0001 | +| loss | -0.069 | +| n_updates | 97900 | +| policy_gradient_loss | -0.0698 | +| value_loss | 0.000382 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.3e+03 | +| ep_rew_mean | 0.261 | +| time/ | | +| fps | 310 | +| iterations | 3739 | +| time_elapsed | 12344 | +| total_timesteps | 3828736 | +| train/ | | +| approx_kl | 2.0257745 | +| clip_fraction | 0.467 | +| clip_range | 0.2 | +| entropy_loss | -0.328 | +| explained_variance | -1.37 | +| learning_rate | 0.0001 | +| loss | -0.11 | +| n_updates | 97910 | +| policy_gradient_loss | -0.0726 | +| value_loss | 0.000376 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.3e+03 | +| ep_rew_mean | 0.261 | +| time/ | | +| fps | 310 | +| iterations | 3740 | +| time_elapsed | 12347 | +| total_timesteps | 3829760 | +| train/ | | +| approx_kl | 1.9174347 | +| clip_fraction | 0.433 | +| clip_range | 0.2 | +| entropy_loss | -0.301 | +| explained_variance | -1.75 | +| learning_rate | 0.0001 | +| loss | -0.0924 | +| n_updates | 97920 | +| policy_gradient_loss | -0.0567 | +| value_loss | 0.000657 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.32e+03 | +| ep_rew_mean | 0.258 | +| time/ | | +| fps | 310 | +| iterations | 3741 | +| time_elapsed | 12351 | +| total_timesteps | 3830784 | +| train/ | | +| approx_kl | 3.224615 | +| clip_fraction | 0.473 | +| clip_range | 0.2 | +| entropy_loss | -0.349 | +| explained_variance | -3.54 | +| learning_rate | 0.0001 | +| loss | -0.0688 | +| n_updates | 97930 | +| policy_gradient_loss | -0.0636 | +| value_loss | 0.000423 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.32e+03 | +| ep_rew_mean | 0.258 | +| time/ | | +| fps | 310 | +| iterations | 3742 | +| time_elapsed | 12354 | +| total_timesteps | 3831808 | +| train/ | | +| approx_kl | 2.616857 | +| clip_fraction | 0.497 | +| clip_range | 0.2 | +| entropy_loss | -0.371 | +| explained_variance | -1.12 | +| learning_rate | 0.0001 | +| loss | -0.0889 | +| n_updates | 97940 | +| policy_gradient_loss | -0.0657 | +| value_loss | 0.000296 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.32e+03 | +| ep_rew_mean | 0.258 | +| time/ | | +| fps | 310 | +| iterations | 3743 | +| time_elapsed | 12357 | +| total_timesteps | 3832832 | +| train/ | | +| approx_kl | 1.9082453 | +| clip_fraction | 0.445 | +| clip_range | 0.2 | +| entropy_loss | -0.324 | +| explained_variance | -4.31 | +| learning_rate | 0.0001 | +| loss | -0.0832 | +| n_updates | 97950 | +| policy_gradient_loss | -0.061 | +| value_loss | 0.000845 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.32e+03 | +| ep_rew_mean | 0.258 | +| time/ | | +| fps | 310 | +| iterations | 3744 | +| time_elapsed | 12361 | +| total_timesteps | 3833856 | +| train/ | | +| approx_kl | 2.2407362 | +| clip_fraction | 0.452 | +| clip_range | 0.2 | +| entropy_loss | -0.313 | +| explained_variance | -2.68 | +| learning_rate | 0.0001 | +| loss | -0.0959 | +| n_updates | 97960 | +| policy_gradient_loss | -0.0684 | +| value_loss | 0.000758 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.34e+03 | +| ep_rew_mean | 0.26 | +| time/ | | +| fps | 310 | +| iterations | 3745 | +| time_elapsed | 12364 | +| total_timesteps | 3834880 | +| train/ | | +| approx_kl | 6.68082 | +| clip_fraction | 0.47 | +| clip_range | 0.2 | +| entropy_loss | -0.33 | +| explained_variance | -2.86 | +| learning_rate | 0.0001 | +| loss | -0.111 | +| n_updates | 97970 | +| policy_gradient_loss | -0.0665 | +| value_loss | 0.000346 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.34e+03 | +| ep_rew_mean | 0.253 | +| time/ | | +| fps | 310 | +| iterations | 3746 | +| time_elapsed | 12368 | +| total_timesteps | 3835904 | +| train/ | | +| approx_kl | 2.1405187 | +| clip_fraction | 0.394 | +| clip_range | 0.2 | +| entropy_loss | -0.271 | +| explained_variance | -3.88 | +| learning_rate | 0.0001 | +| loss | -0.0685 | +| n_updates | 97980 | +| policy_gradient_loss | -0.0562 | +| value_loss | 0.000411 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.34e+03 | +| ep_rew_mean | 0.253 | +| time/ | | +| fps | 310 | +| iterations | 3747 | +| time_elapsed | 12371 | +| total_timesteps | 3836928 | +| train/ | | +| approx_kl | 1.4475218 | +| clip_fraction | 0.368 | +| clip_range | 0.2 | +| entropy_loss | -0.257 | +| explained_variance | -2.52 | +| learning_rate | 0.0001 | +| loss | -0.0738 | +| n_updates | 97990 | +| policy_gradient_loss | -0.0515 | +| value_loss | 0.000876 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.34e+03 | +| ep_rew_mean | 0.253 | +| time/ | | +| fps | 310 | +| iterations | 3748 | +| time_elapsed | 12374 | +| total_timesteps | 3837952 | +| train/ | | +| approx_kl | 2.0033998 | +| clip_fraction | 0.442 | +| clip_range | 0.2 | +| entropy_loss | -0.298 | +| explained_variance | -1.9 | +| learning_rate | 0.0001 | +| loss | -0.0858 | +| n_updates | 98000 | +| policy_gradient_loss | -0.0558 | +| value_loss | 0.00056 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.35e+03 | +| ep_rew_mean | 0.253 | +| time/ | | +| fps | 310 | +| iterations | 3749 | +| time_elapsed | 12378 | +| total_timesteps | 3838976 | +| train/ | | +| approx_kl | 17.290306 | +| clip_fraction | 0.436 | +| clip_range | 0.2 | +| entropy_loss | -0.295 | +| explained_variance | -1.95 | +| learning_rate | 0.0001 | +| loss | -0.0973 | +| n_updates | 98010 | +| policy_gradient_loss | -0.0592 | +| value_loss | 0.000392 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.35e+03 | +| ep_rew_mean | 0.253 | +| time/ | | +| fps | 310 | +| iterations | 3750 | +| time_elapsed | 12381 | +| total_timesteps | 3840000 | +| train/ | | +| approx_kl | 1.5382383 | +| clip_fraction | 0.378 | +| clip_range | 0.2 | +| entropy_loss | -0.256 | +| explained_variance | -2.76 | +| learning_rate | 0.0001 | +| loss | -0.0951 | +| n_updates | 98020 | +| policy_gradient_loss | -0.054 | +| value_loss | 0.00042 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.35e+03 | +| ep_rew_mean | 0.254 | +| time/ | | +| fps | 310 | +| iterations | 3751 | +| time_elapsed | 12384 | +| total_timesteps | 3841024 | +| train/ | | +| approx_kl | 2.4722085 | +| clip_fraction | 0.467 | +| clip_range | 0.2 | +| entropy_loss | -0.334 | +| explained_variance | -0.654 | +| learning_rate | 0.0001 | +| loss | -0.0369 | +| n_updates | 98030 | +| policy_gradient_loss | -0.0576 | +| value_loss | 0.000561 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.35e+03 | +| ep_rew_mean | 0.254 | +| time/ | | +| fps | 310 | +| iterations | 3752 | +| time_elapsed | 12387 | +| total_timesteps | 3842048 | +| train/ | | +| approx_kl | 2.7391942 | +| clip_fraction | 0.429 | +| clip_range | 0.2 | +| entropy_loss | -0.332 | +| explained_variance | -2.57 | +| learning_rate | 0.0001 | +| loss | -0.0698 | +| n_updates | 98040 | +| policy_gradient_loss | -0.0463 | +| value_loss | 0.00073 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.35e+03 | +| ep_rew_mean | 0.254 | +| time/ | | +| fps | 310 | +| iterations | 3753 | +| time_elapsed | 12390 | +| total_timesteps | 3843072 | +| train/ | | +| approx_kl | 1.491913 | +| clip_fraction | 0.436 | +| clip_range | 0.2 | +| entropy_loss | -0.317 | +| explained_variance | -5.31 | +| learning_rate | 0.0001 | +| loss | -0.0844 | +| n_updates | 98050 | +| policy_gradient_loss | -0.0606 | +| value_loss | 0.000222 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.35e+03 | +| ep_rew_mean | 0.253 | +| time/ | | +| fps | 310 | +| iterations | 3754 | +| time_elapsed | 12394 | +| total_timesteps | 3844096 | +| train/ | | +| approx_kl | 1.6147022 | +| clip_fraction | 0.437 | +| clip_range | 0.2 | +| entropy_loss | -0.34 | +| explained_variance | -1.58 | +| learning_rate | 0.0001 | +| loss | -0.0751 | +| n_updates | 98060 | +| policy_gradient_loss | -0.058 | +| value_loss | 0.000368 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.35e+03 | +| ep_rew_mean | 0.253 | +| time/ | | +| fps | 310 | +| iterations | 3755 | +| time_elapsed | 12397 | +| total_timesteps | 3845120 | +| train/ | | +| approx_kl | 2.0533245 | +| clip_fraction | 0.395 | +| clip_range | 0.2 | +| entropy_loss | -0.272 | +| explained_variance | -4.96 | +| learning_rate | 0.0001 | +| loss | -0.069 | +| n_updates | 98070 | +| policy_gradient_loss | -0.0553 | +| value_loss | 0.000449 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.35e+03 | +| ep_rew_mean | 0.254 | +| time/ | | +| fps | 310 | +| iterations | 3756 | +| time_elapsed | 12400 | +| total_timesteps | 3846144 | +| train/ | | +| approx_kl | 3.168839 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.332 | +| explained_variance | -2.71 | +| learning_rate | 0.0001 | +| loss | -0.0756 | +| n_updates | 98080 | +| policy_gradient_loss | -0.0669 | +| value_loss | 0.000745 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.35e+03 | +| ep_rew_mean | 0.254 | +| time/ | | +| fps | 310 | +| iterations | 3757 | +| time_elapsed | 12403 | +| total_timesteps | 3847168 | +| train/ | | +| approx_kl | 2.356562 | +| clip_fraction | 0.43 | +| clip_range | 0.2 | +| entropy_loss | -0.323 | +| explained_variance | -2.56 | +| learning_rate | 0.0001 | +| loss | -0.0548 | +| n_updates | 98090 | +| policy_gradient_loss | -0.0602 | +| value_loss | 0.000683 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.35e+03 | +| ep_rew_mean | 0.252 | +| time/ | | +| fps | 310 | +| iterations | 3758 | +| time_elapsed | 12407 | +| total_timesteps | 3848192 | +| train/ | | +| approx_kl | 2.6826644 | +| clip_fraction | 0.434 | +| clip_range | 0.2 | +| entropy_loss | -0.311 | +| explained_variance | -3.19 | +| learning_rate | 0.0001 | +| loss | -0.0852 | +| n_updates | 98100 | +| policy_gradient_loss | -0.0598 | +| value_loss | 0.000481 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.35e+03 | +| ep_rew_mean | 0.252 | +| time/ | | +| fps | 310 | +| iterations | 3759 | +| time_elapsed | 12410 | +| total_timesteps | 3849216 | +| train/ | | +| approx_kl | 1.968499 | +| clip_fraction | 0.438 | +| clip_range | 0.2 | +| entropy_loss | -0.311 | +| explained_variance | -2.37 | +| learning_rate | 0.0001 | +| loss | -0.0809 | +| n_updates | 98110 | +| policy_gradient_loss | -0.064 | +| value_loss | 0.000466 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.35e+03 | +| ep_rew_mean | 0.252 | +| time/ | | +| fps | 310 | +| iterations | 3760 | +| time_elapsed | 12413 | +| total_timesteps | 3850240 | +| train/ | | +| approx_kl | 1.9638762 | +| clip_fraction | 0.452 | +| clip_range | 0.2 | +| entropy_loss | -0.314 | +| explained_variance | -4.08 | +| learning_rate | 0.0001 | +| loss | -0.105 | +| n_updates | 98120 | +| policy_gradient_loss | -0.0586 | +| value_loss | 0.00032 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.36e+03 | +| ep_rew_mean | 0.247 | +| time/ | | +| fps | 310 | +| iterations | 3761 | +| time_elapsed | 12416 | +| total_timesteps | 3851264 | +| train/ | | +| approx_kl | 1.4219768 | +| clip_fraction | 0.393 | +| clip_range | 0.2 | +| entropy_loss | -0.291 | +| explained_variance | -2.23 | +| learning_rate | 0.0001 | +| loss | -0.0754 | +| n_updates | 98130 | +| policy_gradient_loss | -0.0509 | +| value_loss | 0.000401 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.36e+03 | +| ep_rew_mean | 0.247 | +| time/ | | +| fps | 310 | +| iterations | 3762 | +| time_elapsed | 12420 | +| total_timesteps | 3852288 | +| train/ | | +| approx_kl | 1.6783247 | +| clip_fraction | 0.383 | +| clip_range | 0.2 | +| entropy_loss | -0.268 | +| explained_variance | -2.91 | +| learning_rate | 0.0001 | +| loss | -0.0931 | +| n_updates | 98140 | +| policy_gradient_loss | -0.0547 | +| value_loss | 0.00078 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.36e+03 | +| ep_rew_mean | 0.251 | +| time/ | | +| fps | 310 | +| iterations | 3763 | +| time_elapsed | 12423 | +| total_timesteps | 3853312 | +| train/ | | +| approx_kl | 1.7119956 | +| clip_fraction | 0.421 | +| clip_range | 0.2 | +| entropy_loss | -0.319 | +| explained_variance | -3.29 | +| learning_rate | 0.0001 | +| loss | -0.0776 | +| n_updates | 98150 | +| policy_gradient_loss | -0.0619 | +| value_loss | 0.000473 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.36e+03 | +| ep_rew_mean | 0.251 | +| time/ | | +| fps | 310 | +| iterations | 3764 | +| time_elapsed | 12426 | +| total_timesteps | 3854336 | +| train/ | | +| approx_kl | 3.8011281 | +| clip_fraction | 0.452 | +| clip_range | 0.2 | +| entropy_loss | -0.309 | +| explained_variance | -2.78 | +| learning_rate | 0.0001 | +| loss | -0.0752 | +| n_updates | 98160 | +| policy_gradient_loss | -0.0603 | +| value_loss | 0.000581 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.36e+03 | +| ep_rew_mean | 0.251 | +| time/ | | +| fps | 310 | +| iterations | 3765 | +| time_elapsed | 12430 | +| total_timesteps | 3855360 | +| train/ | | +| approx_kl | 3.1369398 | +| clip_fraction | 0.417 | +| clip_range | 0.2 | +| entropy_loss | -0.287 | +| explained_variance | -13 | +| learning_rate | 0.0001 | +| loss | -0.0952 | +| n_updates | 98170 | +| policy_gradient_loss | -0.0604 | +| value_loss | 0.000574 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.37e+03 | +| ep_rew_mean | 0.245 | +| time/ | | +| fps | 310 | +| iterations | 3766 | +| time_elapsed | 12433 | +| total_timesteps | 3856384 | +| train/ | | +| approx_kl | 1.8000742 | +| clip_fraction | 0.417 | +| clip_range | 0.2 | +| entropy_loss | -0.299 | +| explained_variance | -2.59 | +| learning_rate | 0.0001 | +| loss | -0.034 | +| n_updates | 98180 | +| policy_gradient_loss | -0.0565 | +| value_loss | 0.000324 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.37e+03 | +| ep_rew_mean | 0.245 | +| time/ | | +| fps | 310 | +| iterations | 3767 | +| time_elapsed | 12436 | +| total_timesteps | 3857408 | +| train/ | | +| approx_kl | 1.8971107 | +| clip_fraction | 0.401 | +| clip_range | 0.2 | +| entropy_loss | -0.293 | +| explained_variance | -2.05 | +| learning_rate | 0.0001 | +| loss | -0.085 | +| n_updates | 98190 | +| policy_gradient_loss | -0.0566 | +| value_loss | 0.000378 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.38e+03 | +| ep_rew_mean | 0.244 | +| time/ | | +| fps | 310 | +| iterations | 3768 | +| time_elapsed | 12439 | +| total_timesteps | 3858432 | +| train/ | | +| approx_kl | 2.3627663 | +| clip_fraction | 0.464 | +| clip_range | 0.2 | +| entropy_loss | -0.363 | +| explained_variance | -2.08 | +| learning_rate | 0.0001 | +| loss | -0.0799 | +| n_updates | 98200 | +| policy_gradient_loss | -0.0605 | +| value_loss | 0.000289 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.38e+03 | +| ep_rew_mean | 0.244 | +| time/ | | +| fps | 310 | +| iterations | 3769 | +| time_elapsed | 12442 | +| total_timesteps | 3859456 | +| train/ | | +| approx_kl | 1.4607396 | +| clip_fraction | 0.39 | +| clip_range | 0.2 | +| entropy_loss | -0.293 | +| explained_variance | -4.16 | +| learning_rate | 0.0001 | +| loss | -0.0519 | +| n_updates | 98210 | +| policy_gradient_loss | -0.0458 | +| value_loss | 0.000445 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.38e+03 | +| ep_rew_mean | 0.244 | +| time/ | | +| fps | 310 | +| iterations | 3770 | +| time_elapsed | 12445 | +| total_timesteps | 3860480 | +| train/ | | +| approx_kl | 1.9067249 | +| clip_fraction | 0.485 | +| clip_range | 0.2 | +| entropy_loss | -0.358 | +| explained_variance | -1.43 | +| learning_rate | 0.0001 | +| loss | -0.0771 | +| n_updates | 98220 | +| policy_gradient_loss | -0.0652 | +| value_loss | 0.000667 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.38e+03 | +| ep_rew_mean | 0.244 | +| time/ | | +| fps | 310 | +| iterations | 3771 | +| time_elapsed | 12448 | +| total_timesteps | 3861504 | +| train/ | | +| approx_kl | 4.540717 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.369 | +| explained_variance | -1.57 | +| learning_rate | 0.0001 | +| loss | -0.11 | +| n_updates | 98230 | +| policy_gradient_loss | -0.0697 | +| value_loss | 0.000476 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.39e+03 | +| ep_rew_mean | 0.243 | +| time/ | | +| fps | 310 | +| iterations | 3772 | +| time_elapsed | 12452 | +| total_timesteps | 3862528 | +| train/ | | +| approx_kl | 2.2021325 | +| clip_fraction | 0.495 | +| clip_range | 0.2 | +| entropy_loss | -0.348 | +| explained_variance | -5.22 | +| learning_rate | 0.0001 | +| loss | -0.0775 | +| n_updates | 98240 | +| policy_gradient_loss | -0.0675 | +| value_loss | 0.000246 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.39e+03 | +| ep_rew_mean | 0.243 | +| time/ | | +| fps | 310 | +| iterations | 3773 | +| time_elapsed | 12455 | +| total_timesteps | 3863552 | +| train/ | | +| approx_kl | 1.9548306 | +| clip_fraction | 0.467 | +| clip_range | 0.2 | +| entropy_loss | -0.348 | +| explained_variance | -0.855 | +| learning_rate | 0.0001 | +| loss | -0.0794 | +| n_updates | 98250 | +| policy_gradient_loss | -0.061 | +| value_loss | 0.000477 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.39e+03 | +| ep_rew_mean | 0.244 | +| time/ | | +| fps | 310 | +| iterations | 3774 | +| time_elapsed | 12458 | +| total_timesteps | 3864576 | +| train/ | | +| approx_kl | 2.2367404 | +| clip_fraction | 0.507 | +| clip_range | 0.2 | +| entropy_loss | -0.401 | +| explained_variance | -1.01 | +| learning_rate | 0.0001 | +| loss | -0.0712 | +| n_updates | 98260 | +| policy_gradient_loss | -0.0705 | +| value_loss | 0.000479 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.39e+03 | +| ep_rew_mean | 0.244 | +| time/ | | +| fps | 310 | +| iterations | 3775 | +| time_elapsed | 12461 | +| total_timesteps | 3865600 | +| train/ | | +| approx_kl | 1.7796538 | +| clip_fraction | 0.433 | +| clip_range | 0.2 | +| entropy_loss | -0.327 | +| explained_variance | -2.81 | +| learning_rate | 0.0001 | +| loss | -0.0682 | +| n_updates | 98270 | +| policy_gradient_loss | -0.0632 | +| value_loss | 0.000445 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.39e+03 | +| ep_rew_mean | 0.245 | +| time/ | | +| fps | 310 | +| iterations | 3776 | +| time_elapsed | 12465 | +| total_timesteps | 3866624 | +| train/ | | +| approx_kl | 1.774555 | +| clip_fraction | 0.47 | +| clip_range | 0.2 | +| entropy_loss | -0.372 | +| explained_variance | -2.3 | +| learning_rate | 0.0001 | +| loss | -0.0845 | +| n_updates | 98280 | +| policy_gradient_loss | -0.0597 | +| value_loss | 0.000647 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.39e+03 | +| ep_rew_mean | 0.245 | +| time/ | | +| fps | 310 | +| iterations | 3777 | +| time_elapsed | 12468 | +| total_timesteps | 3867648 | +| train/ | | +| approx_kl | 2.2256625 | +| clip_fraction | 0.45 | +| clip_range | 0.2 | +| entropy_loss | -0.351 | +| explained_variance | -7.71 | +| learning_rate | 0.0001 | +| loss | -0.09 | +| n_updates | 98290 | +| policy_gradient_loss | -0.0667 | +| value_loss | 0.000511 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.39e+03 | +| ep_rew_mean | 0.245 | +| time/ | | +| fps | 310 | +| iterations | 3778 | +| time_elapsed | 12472 | +| total_timesteps | 3868672 | +| train/ | | +| approx_kl | 2.1143615 | +| clip_fraction | 0.511 | +| clip_range | 0.2 | +| entropy_loss | -0.401 | +| explained_variance | -1.1 | +| learning_rate | 0.0001 | +| loss | -0.0961 | +| n_updates | 98300 | +| policy_gradient_loss | -0.0663 | +| value_loss | 0.000503 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.4e+03 | +| ep_rew_mean | 0.245 | +| time/ | | +| fps | 310 | +| iterations | 3779 | +| time_elapsed | 12475 | +| total_timesteps | 3869696 | +| train/ | | +| approx_kl | 3.174227 | +| clip_fraction | 0.464 | +| clip_range | 0.2 | +| entropy_loss | -0.379 | +| explained_variance | -3.11 | +| learning_rate | 0.0001 | +| loss | -0.112 | +| n_updates | 98310 | +| policy_gradient_loss | -0.0654 | +| value_loss | 0.00041 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.4e+03 | +| ep_rew_mean | 0.245 | +| time/ | | +| fps | 310 | +| iterations | 3780 | +| time_elapsed | 12478 | +| total_timesteps | 3870720 | +| train/ | | +| approx_kl | 2.0092928 | +| clip_fraction | 0.443 | +| clip_range | 0.2 | +| entropy_loss | -0.346 | +| explained_variance | -4.1 | +| learning_rate | 0.0001 | +| loss | -0.0555 | +| n_updates | 98320 | +| policy_gradient_loss | -0.0553 | +| value_loss | 0.000765 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.4e+03 | +| ep_rew_mean | 0.245 | +| time/ | | +| fps | 310 | +| iterations | 3781 | +| time_elapsed | 12482 | +| total_timesteps | 3871744 | +| train/ | | +| approx_kl | 2.1269457 | +| clip_fraction | 0.516 | +| clip_range | 0.2 | +| entropy_loss | -0.408 | +| explained_variance | -1.56 | +| learning_rate | 0.0001 | +| loss | -0.0427 | +| n_updates | 98330 | +| policy_gradient_loss | -0.0716 | +| value_loss | 0.000475 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.4e+03 | +| ep_rew_mean | 0.246 | +| time/ | | +| fps | 310 | +| iterations | 3782 | +| time_elapsed | 12485 | +| total_timesteps | 3872768 | +| train/ | | +| approx_kl | 2.1429982 | +| clip_fraction | 0.506 | +| clip_range | 0.2 | +| entropy_loss | -0.361 | +| explained_variance | -1.18 | +| learning_rate | 0.0001 | +| loss | -0.0774 | +| n_updates | 98340 | +| policy_gradient_loss | -0.0646 | +| value_loss | 0.000568 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.4e+03 | +| ep_rew_mean | 0.246 | +| time/ | | +| fps | 310 | +| iterations | 3783 | +| time_elapsed | 12489 | +| total_timesteps | 3873792 | +| train/ | | +| approx_kl | 2.0852053 | +| clip_fraction | 0.455 | +| clip_range | 0.2 | +| entropy_loss | -0.336 | +| explained_variance | -6.14 | +| learning_rate | 0.0001 | +| loss | -0.0781 | +| n_updates | 98350 | +| policy_gradient_loss | -0.0639 | +| value_loss | 0.000394 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.4e+03 | +| ep_rew_mean | 0.246 | +| time/ | | +| fps | 310 | +| iterations | 3784 | +| time_elapsed | 12492 | +| total_timesteps | 3874816 | +| train/ | | +| approx_kl | 1.8015865 | +| clip_fraction | 0.458 | +| clip_range | 0.2 | +| entropy_loss | -0.33 | +| explained_variance | -1.46 | +| learning_rate | 0.0001 | +| loss | -0.0917 | +| n_updates | 98360 | +| policy_gradient_loss | -0.062 | +| value_loss | 0.000495 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.41e+03 | +| ep_rew_mean | 0.246 | +| time/ | | +| fps | 310 | +| iterations | 3785 | +| time_elapsed | 12495 | +| total_timesteps | 3875840 | +| train/ | | +| approx_kl | 1.396624 | +| clip_fraction | 0.421 | +| clip_range | 0.2 | +| entropy_loss | -0.326 | +| explained_variance | -6.91 | +| learning_rate | 0.0001 | +| loss | -0.0893 | +| n_updates | 98370 | +| policy_gradient_loss | -0.0614 | +| value_loss | 0.000198 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.41e+03 | +| ep_rew_mean | 0.246 | +| time/ | | +| fps | 310 | +| iterations | 3786 | +| time_elapsed | 12498 | +| total_timesteps | 3876864 | +| train/ | | +| approx_kl | 2.0230622 | +| clip_fraction | 0.446 | +| clip_range | 0.2 | +| entropy_loss | -0.326 | +| explained_variance | -0.394 | +| learning_rate | 0.0001 | +| loss | -0.0475 | +| n_updates | 98380 | +| policy_gradient_loss | -0.0539 | +| value_loss | 0.000716 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.4e+03 | +| ep_rew_mean | 0.244 | +| time/ | | +| fps | 310 | +| iterations | 3787 | +| time_elapsed | 12502 | +| total_timesteps | 3877888 | +| train/ | | +| approx_kl | 1.7155263 | +| clip_fraction | 0.45 | +| clip_range | 0.2 | +| entropy_loss | -0.348 | +| explained_variance | -4.37 | +| learning_rate | 0.0001 | +| loss | -0.0849 | +| n_updates | 98390 | +| policy_gradient_loss | -0.0598 | +| value_loss | 0.000299 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.4e+03 | +| ep_rew_mean | 0.244 | +| time/ | | +| fps | 310 | +| iterations | 3788 | +| time_elapsed | 12505 | +| total_timesteps | 3878912 | +| train/ | | +| approx_kl | 1.3654059 | +| clip_fraction | 0.394 | +| clip_range | 0.2 | +| entropy_loss | -0.323 | +| explained_variance | -1.38 | +| learning_rate | 0.0001 | +| loss | -0.0599 | +| n_updates | 98400 | +| policy_gradient_loss | -0.0498 | +| value_loss | 0.000882 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.4e+03 | +| ep_rew_mean | 0.244 | +| time/ | | +| fps | 310 | +| iterations | 3789 | +| time_elapsed | 12508 | +| total_timesteps | 3879936 | +| train/ | | +| approx_kl | 1.538243 | +| clip_fraction | 0.428 | +| clip_range | 0.2 | +| entropy_loss | -0.349 | +| explained_variance | -5.1 | +| learning_rate | 0.0001 | +| loss | -0.0375 | +| n_updates | 98410 | +| policy_gradient_loss | -0.0568 | +| value_loss | 0.000444 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.41e+03 | +| ep_rew_mean | 0.241 | +| time/ | | +| fps | 310 | +| iterations | 3790 | +| time_elapsed | 12511 | +| total_timesteps | 3880960 | +| train/ | | +| approx_kl | 1.8553882 | +| clip_fraction | 0.482 | +| clip_range | 0.2 | +| entropy_loss | -0.371 | +| explained_variance | -8.49 | +| learning_rate | 0.0001 | +| loss | -0.0893 | +| n_updates | 98420 | +| policy_gradient_loss | -0.0683 | +| value_loss | 0.000213 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.41e+03 | +| ep_rew_mean | 0.241 | +| time/ | | +| fps | 310 | +| iterations | 3791 | +| time_elapsed | 12514 | +| total_timesteps | 3881984 | +| train/ | | +| approx_kl | 1.9056419 | +| clip_fraction | 0.449 | +| clip_range | 0.2 | +| entropy_loss | -0.334 | +| explained_variance | -2.1 | +| learning_rate | 0.0001 | +| loss | -0.0771 | +| n_updates | 98430 | +| policy_gradient_loss | -0.0553 | +| value_loss | 0.000321 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.42e+03 | +| ep_rew_mean | 0.236 | +| time/ | | +| fps | 310 | +| iterations | 3792 | +| time_elapsed | 12518 | +| total_timesteps | 3883008 | +| train/ | | +| approx_kl | 2.0382452 | +| clip_fraction | 0.485 | +| clip_range | 0.2 | +| entropy_loss | -0.399 | +| explained_variance | -2.13 | +| learning_rate | 0.0001 | +| loss | -0.0829 | +| n_updates | 98440 | +| policy_gradient_loss | -0.0698 | +| value_loss | 0.000461 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.42e+03 | +| ep_rew_mean | 0.236 | +| time/ | | +| fps | 310 | +| iterations | 3793 | +| time_elapsed | 12521 | +| total_timesteps | 3884032 | +| train/ | | +| approx_kl | 10.955961 | +| clip_fraction | 0.448 | +| clip_range | 0.2 | +| entropy_loss | -0.315 | +| explained_variance | -3.31 | +| learning_rate | 0.0001 | +| loss | -0.0925 | +| n_updates | 98450 | +| policy_gradient_loss | -0.0655 | +| value_loss | 0.000608 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.42e+03 | +| ep_rew_mean | 0.236 | +| time/ | | +| fps | 310 | +| iterations | 3794 | +| time_elapsed | 12525 | +| total_timesteps | 3885056 | +| train/ | | +| approx_kl | 1.6609678 | +| clip_fraction | 0.458 | +| clip_range | 0.2 | +| entropy_loss | -0.376 | +| explained_variance | -4.66 | +| learning_rate | 0.0001 | +| loss | -0.059 | +| n_updates | 98460 | +| policy_gradient_loss | -0.0604 | +| value_loss | 0.00076 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.43e+03 | +| ep_rew_mean | 0.239 | +| time/ | | +| fps | 310 | +| iterations | 3795 | +| time_elapsed | 12528 | +| total_timesteps | 3886080 | +| train/ | | +| approx_kl | 1.7636981 | +| clip_fraction | 0.451 | +| clip_range | 0.2 | +| entropy_loss | -0.355 | +| explained_variance | -2.38 | +| learning_rate | 0.0001 | +| loss | -0.082 | +| n_updates | 98470 | +| policy_gradient_loss | -0.058 | +| value_loss | 0.000386 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.43e+03 | +| ep_rew_mean | 0.239 | +| time/ | | +| fps | 310 | +| iterations | 3796 | +| time_elapsed | 12532 | +| total_timesteps | 3887104 | +| train/ | | +| approx_kl | 1.9586692 | +| clip_fraction | 0.418 | +| clip_range | 0.2 | +| entropy_loss | -0.317 | +| explained_variance | -8.69 | +| learning_rate | 0.0001 | +| loss | -0.0868 | +| n_updates | 98480 | +| policy_gradient_loss | -0.0585 | +| value_loss | 0.000345 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.43e+03 | +| ep_rew_mean | 0.239 | +| time/ | | +| fps | 310 | +| iterations | 3797 | +| time_elapsed | 12535 | +| total_timesteps | 3888128 | +| train/ | | +| approx_kl | 2.6041768 | +| clip_fraction | 0.492 | +| clip_range | 0.2 | +| entropy_loss | -0.352 | +| explained_variance | -4.2 | +| learning_rate | 0.0001 | +| loss | -0.095 | +| n_updates | 98490 | +| policy_gradient_loss | -0.0709 | +| value_loss | 0.000344 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.44e+03 | +| ep_rew_mean | 0.24 | +| time/ | | +| fps | 310 | +| iterations | 3798 | +| time_elapsed | 12539 | +| total_timesteps | 3889152 | +| train/ | | +| approx_kl | 8.213058 | +| clip_fraction | 0.458 | +| clip_range | 0.2 | +| entropy_loss | -0.337 | +| explained_variance | -0.833 | +| learning_rate | 0.0001 | +| loss | -0.106 | +| n_updates | 98500 | +| policy_gradient_loss | -0.0654 | +| value_loss | 0.000506 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.44e+03 | +| ep_rew_mean | 0.24 | +| time/ | | +| fps | 310 | +| iterations | 3799 | +| time_elapsed | 12543 | +| total_timesteps | 3890176 | +| train/ | | +| approx_kl | 2.5249734 | +| clip_fraction | 0.438 | +| clip_range | 0.2 | +| entropy_loss | -0.346 | +| explained_variance | -5.76 | +| learning_rate | 0.0001 | +| loss | -0.0943 | +| n_updates | 98510 | +| policy_gradient_loss | -0.0665 | +| value_loss | 0.000545 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.44e+03 | +| ep_rew_mean | 0.24 | +| time/ | | +| fps | 310 | +| iterations | 3800 | +| time_elapsed | 12546 | +| total_timesteps | 3891200 | +| train/ | | +| approx_kl | 1.9839492 | +| clip_fraction | 0.458 | +| clip_range | 0.2 | +| entropy_loss | -0.368 | +| explained_variance | -2.94 | +| learning_rate | 0.0001 | +| loss | -0.0839 | +| n_updates | 98520 | +| policy_gradient_loss | -0.0639 | +| value_loss | 0.000424 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.45e+03 | +| ep_rew_mean | 0.238 | +| time/ | | +| fps | 310 | +| iterations | 3801 | +| time_elapsed | 12549 | +| total_timesteps | 3892224 | +| train/ | | +| approx_kl | 2.3330967 | +| clip_fraction | 0.482 | +| clip_range | 0.2 | +| entropy_loss | -0.341 | +| explained_variance | -3.91 | +| learning_rate | 0.0001 | +| loss | -0.0918 | +| n_updates | 98530 | +| policy_gradient_loss | -0.0714 | +| value_loss | 0.000321 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.45e+03 | +| ep_rew_mean | 0.238 | +| time/ | | +| fps | 310 | +| iterations | 3802 | +| time_elapsed | 12553 | +| total_timesteps | 3893248 | +| train/ | | +| approx_kl | 2.2250226 | +| clip_fraction | 0.425 | +| clip_range | 0.2 | +| entropy_loss | -0.308 | +| explained_variance | -0.924 | +| learning_rate | 0.0001 | +| loss | -0.079 | +| n_updates | 98540 | +| policy_gradient_loss | -0.0604 | +| value_loss | 0.000761 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.45e+03 | +| ep_rew_mean | 0.243 | +| time/ | | +| fps | 310 | +| iterations | 3803 | +| time_elapsed | 12556 | +| total_timesteps | 3894272 | +| train/ | | +| approx_kl | 2.9893856 | +| clip_fraction | 0.497 | +| clip_range | 0.2 | +| entropy_loss | -0.341 | +| explained_variance | -2.01 | +| learning_rate | 0.0001 | +| loss | -0.0933 | +| n_updates | 98550 | +| policy_gradient_loss | -0.071 | +| value_loss | 0.000954 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.45e+03 | +| ep_rew_mean | 0.243 | +| time/ | | +| fps | 310 | +| iterations | 3804 | +| time_elapsed | 12559 | +| total_timesteps | 3895296 | +| train/ | | +| approx_kl | 1.9838303 | +| clip_fraction | 0.458 | +| clip_range | 0.2 | +| entropy_loss | -0.35 | +| explained_variance | -2.06 | +| learning_rate | 0.0001 | +| loss | -0.0988 | +| n_updates | 98560 | +| policy_gradient_loss | -0.0665 | +| value_loss | 0.000461 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.45e+03 | +| ep_rew_mean | 0.241 | +| time/ | | +| fps | 310 | +| iterations | 3805 | +| time_elapsed | 12562 | +| total_timesteps | 3896320 | +| train/ | | +| approx_kl | 2.0275233 | +| clip_fraction | 0.453 | +| clip_range | 0.2 | +| entropy_loss | -0.324 | +| explained_variance | -4.01 | +| learning_rate | 0.0001 | +| loss | -0.091 | +| n_updates | 98570 | +| policy_gradient_loss | -0.0665 | +| value_loss | 0.000702 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.45e+03 | +| ep_rew_mean | 0.241 | +| time/ | | +| fps | 310 | +| iterations | 3806 | +| time_elapsed | 12565 | +| total_timesteps | 3897344 | +| train/ | | +| approx_kl | 2.1582668 | +| clip_fraction | 0.448 | +| clip_range | 0.2 | +| entropy_loss | -0.322 | +| explained_variance | -1.93 | +| learning_rate | 0.0001 | +| loss | -0.076 | +| n_updates | 98580 | +| policy_gradient_loss | -0.0603 | +| value_loss | 0.000645 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.45e+03 | +| ep_rew_mean | 0.241 | +| time/ | | +| fps | 310 | +| iterations | 3807 | +| time_elapsed | 12568 | +| total_timesteps | 3898368 | +| train/ | | +| approx_kl | 2.157555 | +| clip_fraction | 0.47 | +| clip_range | 0.2 | +| entropy_loss | -0.336 | +| explained_variance | -1.35 | +| learning_rate | 0.0001 | +| loss | -0.0754 | +| n_updates | 98590 | +| policy_gradient_loss | -0.0655 | +| value_loss | 0.000589 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.45e+03 | +| ep_rew_mean | 0.241 | +| time/ | | +| fps | 310 | +| iterations | 3808 | +| time_elapsed | 12572 | +| total_timesteps | 3899392 | +| train/ | | +| approx_kl | 2.3086147 | +| clip_fraction | 0.463 | +| clip_range | 0.2 | +| entropy_loss | -0.354 | +| explained_variance | -2.45 | +| learning_rate | 0.0001 | +| loss | -0.108 | +| n_updates | 98600 | +| policy_gradient_loss | -0.0664 | +| value_loss | 0.000501 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.45e+03 | +| ep_rew_mean | 0.241 | +| time/ | | +| fps | 310 | +| iterations | 3809 | +| time_elapsed | 12575 | +| total_timesteps | 3900416 | +| train/ | | +| approx_kl | 3.5220408 | +| clip_fraction | 0.542 | +| clip_range | 0.2 | +| entropy_loss | -0.381 | +| explained_variance | -1.57 | +| learning_rate | 0.0001 | +| loss | -0.0876 | +| n_updates | 98610 | +| policy_gradient_loss | 0.0402 | +| value_loss | 0.000613 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.47e+03 | +| ep_rew_mean | 0.24 | +| time/ | | +| fps | 310 | +| iterations | 3810 | +| time_elapsed | 12578 | +| total_timesteps | 3901440 | +| train/ | | +| approx_kl | 2.2311969 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.33 | +| explained_variance | -3.23 | +| learning_rate | 0.0001 | +| loss | -0.1 | +| n_updates | 98620 | +| policy_gradient_loss | -0.0708 | +| value_loss | 0.000441 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.47e+03 | +| ep_rew_mean | 0.24 | +| time/ | | +| fps | 310 | +| iterations | 3811 | +| time_elapsed | 12581 | +| total_timesteps | 3902464 | +| train/ | | +| approx_kl | 1.9757426 | +| clip_fraction | 0.448 | +| clip_range | 0.2 | +| entropy_loss | -0.32 | +| explained_variance | -2.32 | +| learning_rate | 0.0001 | +| loss | -0.0812 | +| n_updates | 98630 | +| policy_gradient_loss | -0.0687 | +| value_loss | 0.000629 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.47e+03 | +| ep_rew_mean | 0.237 | +| time/ | | +| fps | 310 | +| iterations | 3812 | +| time_elapsed | 12585 | +| total_timesteps | 3903488 | +| train/ | | +| approx_kl | 2.3173318 | +| clip_fraction | 0.492 | +| clip_range | 0.2 | +| entropy_loss | -0.357 | +| explained_variance | -2.89 | +| learning_rate | 0.0001 | +| loss | -0.0975 | +| n_updates | 98640 | +| policy_gradient_loss | -0.0724 | +| value_loss | 0.000464 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.47e+03 | +| ep_rew_mean | 0.237 | +| time/ | | +| fps | 310 | +| iterations | 3813 | +| time_elapsed | 12588 | +| total_timesteps | 3904512 | +| train/ | | +| approx_kl | 2.2150035 | +| clip_fraction | 0.408 | +| clip_range | 0.2 | +| entropy_loss | -0.277 | +| explained_variance | -1.09 | +| learning_rate | 0.0001 | +| loss | -0.0562 | +| n_updates | 98650 | +| policy_gradient_loss | -0.049 | +| value_loss | 0.000378 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.46e+03 | +| ep_rew_mean | 0.24 | +| time/ | | +| fps | 310 | +| iterations | 3814 | +| time_elapsed | 12592 | +| total_timesteps | 3905536 | +| train/ | | +| approx_kl | 2.1678057 | +| clip_fraction | 0.467 | +| clip_range | 0.2 | +| entropy_loss | -0.383 | +| explained_variance | -1.72 | +| learning_rate | 0.0001 | +| loss | -0.0944 | +| n_updates | 98660 | +| policy_gradient_loss | -0.061 | +| value_loss | 0.000349 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.46e+03 | +| ep_rew_mean | 0.24 | +| time/ | | +| fps | 310 | +| iterations | 3815 | +| time_elapsed | 12595 | +| total_timesteps | 3906560 | +| train/ | | +| approx_kl | 1.8034432 | +| clip_fraction | 0.434 | +| clip_range | 0.2 | +| entropy_loss | -0.321 | +| explained_variance | -16.1 | +| learning_rate | 0.0001 | +| loss | -0.0958 | +| n_updates | 98670 | +| policy_gradient_loss | -0.0591 | +| value_loss | 0.0004 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.46e+03 | +| ep_rew_mean | 0.24 | +| time/ | | +| fps | 310 | +| iterations | 3816 | +| time_elapsed | 12599 | +| total_timesteps | 3907584 | +| train/ | | +| approx_kl | 2.1217644 | +| clip_fraction | 0.444 | +| clip_range | 0.2 | +| entropy_loss | -0.333 | +| explained_variance | -2.13 | +| learning_rate | 0.0001 | +| loss | -0.0884 | +| n_updates | 98680 | +| policy_gradient_loss | -0.0658 | +| value_loss | 0.000285 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.48e+03 | +| ep_rew_mean | 0.234 | +| time/ | | +| fps | 310 | +| iterations | 3817 | +| time_elapsed | 12602 | +| total_timesteps | 3908608 | +| train/ | | +| approx_kl | 1.9309118 | +| clip_fraction | 0.535 | +| clip_range | 0.2 | +| entropy_loss | -0.474 | +| explained_variance | -0.872 | +| learning_rate | 0.0001 | +| loss | -0.0837 | +| n_updates | 98690 | +| policy_gradient_loss | -0.0701 | +| value_loss | 0.000348 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.48e+03 | +| ep_rew_mean | 0.234 | +| time/ | | +| fps | 310 | +| iterations | 3818 | +| time_elapsed | 12605 | +| total_timesteps | 3909632 | +| train/ | | +| approx_kl | 2.7108753 | +| clip_fraction | 0.443 | +| clip_range | 0.2 | +| entropy_loss | -0.314 | +| explained_variance | -2.88 | +| learning_rate | 0.0001 | +| loss | -0.0866 | +| n_updates | 98700 | +| policy_gradient_loss | -0.0643 | +| value_loss | 0.000635 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.48e+03 | +| ep_rew_mean | 0.234 | +| time/ | | +| fps | 310 | +| iterations | 3819 | +| time_elapsed | 12609 | +| total_timesteps | 3910656 | +| train/ | | +| approx_kl | 1.9653723 | +| clip_fraction | 0.45 | +| clip_range | 0.2 | +| entropy_loss | -0.324 | +| explained_variance | -4.38 | +| learning_rate | 0.0001 | +| loss | -0.0901 | +| n_updates | 98710 | +| policy_gradient_loss | -0.0696 | +| value_loss | 0.00054 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.49e+03 | +| ep_rew_mean | 0.237 | +| time/ | | +| fps | 310 | +| iterations | 3820 | +| time_elapsed | 12612 | +| total_timesteps | 3911680 | +| train/ | | +| approx_kl | 2.278185 | +| clip_fraction | 0.47 | +| clip_range | 0.2 | +| entropy_loss | -0.324 | +| explained_variance | -1.32 | +| learning_rate | 0.0001 | +| loss | -0.071 | +| n_updates | 98720 | +| policy_gradient_loss | -0.0608 | +| value_loss | 0.000459 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.49e+03 | +| ep_rew_mean | 0.237 | +| time/ | | +| fps | 310 | +| iterations | 3821 | +| time_elapsed | 12615 | +| total_timesteps | 3912704 | +| train/ | | +| approx_kl | 2.1626616 | +| clip_fraction | 0.441 | +| clip_range | 0.2 | +| entropy_loss | -0.31 | +| explained_variance | -1.24 | +| learning_rate | 0.0001 | +| loss | -0.084 | +| n_updates | 98730 | +| policy_gradient_loss | -0.0678 | +| value_loss | 0.000646 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.49e+03 | +| ep_rew_mean | 0.237 | +| time/ | | +| fps | 310 | +| iterations | 3822 | +| time_elapsed | 12619 | +| total_timesteps | 3913728 | +| train/ | | +| approx_kl | 4.9039736 | +| clip_fraction | 0.473 | +| clip_range | 0.2 | +| entropy_loss | -0.332 | +| explained_variance | -2.3 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 98740 | +| policy_gradient_loss | -0.0706 | +| value_loss | 0.000608 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.49e+03 | +| ep_rew_mean | 0.237 | +| time/ | | +| fps | 310 | +| iterations | 3823 | +| time_elapsed | 12622 | +| total_timesteps | 3914752 | +| train/ | | +| approx_kl | 3.3672097 | +| clip_fraction | 0.455 | +| clip_range | 0.2 | +| entropy_loss | -0.319 | +| explained_variance | -3.75 | +| learning_rate | 0.0001 | +| loss | -0.0843 | +| n_updates | 98750 | +| policy_gradient_loss | -0.069 | +| value_loss | 0.00034 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.5e+03 | +| ep_rew_mean | 0.238 | +| time/ | | +| fps | 310 | +| iterations | 3824 | +| time_elapsed | 12625 | +| total_timesteps | 3915776 | +| train/ | | +| approx_kl | 1.8322471 | +| clip_fraction | 0.429 | +| clip_range | 0.2 | +| entropy_loss | -0.332 | +| explained_variance | -2.05 | +| learning_rate | 0.0001 | +| loss | -0.0742 | +| n_updates | 98760 | +| policy_gradient_loss | -0.0578 | +| value_loss | 0.000421 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.5e+03 | +| ep_rew_mean | 0.238 | +| time/ | | +| fps | 310 | +| iterations | 3825 | +| time_elapsed | 12628 | +| total_timesteps | 3916800 | +| train/ | | +| approx_kl | 2.090347 | +| clip_fraction | 0.455 | +| clip_range | 0.2 | +| entropy_loss | -0.352 | +| explained_variance | -5.37 | +| learning_rate | 0.0001 | +| loss | -0.0857 | +| n_updates | 98770 | +| policy_gradient_loss | -0.0678 | +| value_loss | 0.000351 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.51e+03 | +| ep_rew_mean | 0.242 | +| time/ | | +| fps | 310 | +| iterations | 3826 | +| time_elapsed | 12631 | +| total_timesteps | 3917824 | +| train/ | | +| approx_kl | 2.5347455 | +| clip_fraction | 0.468 | +| clip_range | 0.2 | +| entropy_loss | -0.337 | +| explained_variance | -0.852 | +| learning_rate | 0.0001 | +| loss | -0.0941 | +| n_updates | 98780 | +| policy_gradient_loss | -0.0714 | +| value_loss | 0.000483 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.51e+03 | +| ep_rew_mean | 0.242 | +| time/ | | +| fps | 310 | +| iterations | 3827 | +| time_elapsed | 12635 | +| total_timesteps | 3918848 | +| train/ | | +| approx_kl | 1.994993 | +| clip_fraction | 0.442 | +| clip_range | 0.2 | +| entropy_loss | -0.314 | +| explained_variance | -2.31 | +| learning_rate | 0.0001 | +| loss | -0.0938 | +| n_updates | 98790 | +| policy_gradient_loss | -0.0638 | +| value_loss | 0.000711 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.5e+03 | +| ep_rew_mean | 0.241 | +| time/ | | +| fps | 310 | +| iterations | 3828 | +| time_elapsed | 12638 | +| total_timesteps | 3919872 | +| train/ | | +| approx_kl | 2.2484202 | +| clip_fraction | 0.484 | +| clip_range | 0.2 | +| entropy_loss | -0.37 | +| explained_variance | -2.07 | +| learning_rate | 0.0001 | +| loss | -0.0872 | +| n_updates | 98800 | +| policy_gradient_loss | -0.0705 | +| value_loss | 0.000345 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.5e+03 | +| ep_rew_mean | 0.241 | +| time/ | | +| fps | 310 | +| iterations | 3829 | +| time_elapsed | 12641 | +| total_timesteps | 3920896 | +| train/ | | +| approx_kl | 1.8498954 | +| clip_fraction | 0.46 | +| clip_range | 0.2 | +| entropy_loss | -0.325 | +| explained_variance | -1.4 | +| learning_rate | 0.0001 | +| loss | -0.084 | +| n_updates | 98810 | +| policy_gradient_loss | -0.0594 | +| value_loss | 0.000484 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.5e+03 | +| ep_rew_mean | 0.241 | +| time/ | | +| fps | 310 | +| iterations | 3830 | +| time_elapsed | 12645 | +| total_timesteps | 3921920 | +| train/ | | +| approx_kl | 1.8945656 | +| clip_fraction | 0.479 | +| clip_range | 0.2 | +| entropy_loss | -0.374 | +| explained_variance | -2.42 | +| learning_rate | 0.0001 | +| loss | -0.0773 | +| n_updates | 98820 | +| policy_gradient_loss | -0.0644 | +| value_loss | 0.000432 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.5e+03 | +| ep_rew_mean | 0.241 | +| time/ | | +| fps | 310 | +| iterations | 3831 | +| time_elapsed | 12648 | +| total_timesteps | 3922944 | +| train/ | | +| approx_kl | 1.8397061 | +| clip_fraction | 0.443 | +| clip_range | 0.2 | +| entropy_loss | -0.337 | +| explained_variance | -0.958 | +| learning_rate | 0.0001 | +| loss | -0.0571 | +| n_updates | 98830 | +| policy_gradient_loss | -0.0606 | +| value_loss | 0.000676 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.49e+03 | +| ep_rew_mean | 0.238 | +| time/ | | +| fps | 310 | +| iterations | 3832 | +| time_elapsed | 12652 | +| total_timesteps | 3923968 | +| train/ | | +| approx_kl | 2.1924973 | +| clip_fraction | 0.449 | +| clip_range | 0.2 | +| entropy_loss | -0.32 | +| explained_variance | -2.67 | +| learning_rate | 0.0001 | +| loss | -0.0754 | +| n_updates | 98840 | +| policy_gradient_loss | -0.0623 | +| value_loss | 0.000508 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.49e+03 | +| ep_rew_mean | 0.238 | +| time/ | | +| fps | 310 | +| iterations | 3833 | +| time_elapsed | 12655 | +| total_timesteps | 3924992 | +| train/ | | +| approx_kl | 4.1205473 | +| clip_fraction | 0.422 | +| clip_range | 0.2 | +| entropy_loss | -0.296 | +| explained_variance | -1.11 | +| learning_rate | 0.0001 | +| loss | -0.0526 | +| n_updates | 98850 | +| policy_gradient_loss | -0.0591 | +| value_loss | 0.000652 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.49e+03 | +| ep_rew_mean | 0.238 | +| time/ | | +| fps | 310 | +| iterations | 3834 | +| time_elapsed | 12658 | +| total_timesteps | 3926016 | +| train/ | | +| approx_kl | 2.0212586 | +| clip_fraction | 0.467 | +| clip_range | 0.2 | +| entropy_loss | -0.329 | +| explained_variance | -3.39 | +| learning_rate | 0.0001 | +| loss | -0.0628 | +| n_updates | 98860 | +| policy_gradient_loss | -0.0717 | +| value_loss | 0.000701 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.51e+03 | +| ep_rew_mean | 0.239 | +| time/ | | +| fps | 310 | +| iterations | 3835 | +| time_elapsed | 12662 | +| total_timesteps | 3927040 | +| train/ | | +| approx_kl | 2.4952106 | +| clip_fraction | 0.441 | +| clip_range | 0.2 | +| entropy_loss | -0.299 | +| explained_variance | -2.4 | +| learning_rate | 0.0001 | +| loss | -0.0823 | +| n_updates | 98870 | +| policy_gradient_loss | -0.0549 | +| value_loss | 0.000232 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.51e+03 | +| ep_rew_mean | 0.239 | +| time/ | | +| fps | 310 | +| iterations | 3836 | +| time_elapsed | 12665 | +| total_timesteps | 3928064 | +| train/ | | +| approx_kl | 1.769149 | +| clip_fraction | 0.395 | +| clip_range | 0.2 | +| entropy_loss | -0.268 | +| explained_variance | -0.873 | +| learning_rate | 0.0001 | +| loss | -0.0521 | +| n_updates | 98880 | +| policy_gradient_loss | -0.052 | +| value_loss | 0.000361 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.5e+03 | +| ep_rew_mean | 0.243 | +| time/ | | +| fps | 310 | +| iterations | 3837 | +| time_elapsed | 12668 | +| total_timesteps | 3929088 | +| train/ | | +| approx_kl | 2.6812375 | +| clip_fraction | 0.459 | +| clip_range | 0.2 | +| entropy_loss | -0.331 | +| explained_variance | -0.951 | +| learning_rate | 0.0001 | +| loss | -0.0727 | +| n_updates | 98890 | +| policy_gradient_loss | -0.0524 | +| value_loss | 0.000494 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.5e+03 | +| ep_rew_mean | 0.243 | +| time/ | | +| fps | 310 | +| iterations | 3838 | +| time_elapsed | 12671 | +| total_timesteps | 3930112 | +| train/ | | +| approx_kl | 2.4201808 | +| clip_fraction | 0.448 | +| clip_range | 0.2 | +| entropy_loss | -0.298 | +| explained_variance | -0.909 | +| learning_rate | 0.0001 | +| loss | -0.0904 | +| n_updates | 98900 | +| policy_gradient_loss | -0.0658 | +| value_loss | 0.000505 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.5e+03 | +| ep_rew_mean | 0.243 | +| time/ | | +| fps | 310 | +| iterations | 3839 | +| time_elapsed | 12675 | +| total_timesteps | 3931136 | +| train/ | | +| approx_kl | 2.5265236 | +| clip_fraction | 0.44 | +| clip_range | 0.2 | +| entropy_loss | -0.284 | +| explained_variance | -2.93 | +| learning_rate | 0.0001 | +| loss | -0.0667 | +| n_updates | 98910 | +| policy_gradient_loss | -0.0636 | +| value_loss | 0.000504 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.5e+03 | +| ep_rew_mean | 0.243 | +| time/ | | +| fps | 310 | +| iterations | 3840 | +| time_elapsed | 12678 | +| total_timesteps | 3932160 | +| train/ | | +| approx_kl | 2.4275334 | +| clip_fraction | 0.462 | +| clip_range | 0.2 | +| entropy_loss | -0.315 | +| explained_variance | -4.19 | +| learning_rate | 0.0001 | +| loss | -0.0931 | +| n_updates | 98920 | +| policy_gradient_loss | -0.0688 | +| value_loss | 0.00039 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.51e+03 | +| ep_rew_mean | 0.244 | +| time/ | | +| fps | 310 | +| iterations | 3841 | +| time_elapsed | 12681 | +| total_timesteps | 3933184 | +| train/ | | +| approx_kl | 1.7557745 | +| clip_fraction | 0.461 | +| clip_range | 0.2 | +| entropy_loss | -0.323 | +| explained_variance | -0.988 | +| learning_rate | 0.0001 | +| loss | -0.091 | +| n_updates | 98930 | +| policy_gradient_loss | -0.0466 | +| value_loss | 0.000368 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.51e+03 | +| ep_rew_mean | 0.244 | +| time/ | | +| fps | 310 | +| iterations | 3842 | +| time_elapsed | 12684 | +| total_timesteps | 3934208 | +| train/ | | +| approx_kl | 2.3941798 | +| clip_fraction | 0.411 | +| clip_range | 0.2 | +| entropy_loss | -0.306 | +| explained_variance | -3 | +| learning_rate | 0.0001 | +| loss | -0.0942 | +| n_updates | 98940 | +| policy_gradient_loss | -0.0567 | +| value_loss | 0.000754 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.51e+03 | +| ep_rew_mean | 0.244 | +| time/ | | +| fps | 310 | +| iterations | 3843 | +| time_elapsed | 12688 | +| total_timesteps | 3935232 | +| train/ | | +| approx_kl | 1.8012233 | +| clip_fraction | 0.488 | +| clip_range | 0.2 | +| entropy_loss | -0.368 | +| explained_variance | -5.65 | +| learning_rate | 0.0001 | +| loss | -0.0792 | +| n_updates | 98950 | +| policy_gradient_loss | -0.0615 | +| value_loss | 0.000287 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.52e+03 | +| ep_rew_mean | 0.247 | +| time/ | | +| fps | 310 | +| iterations | 3844 | +| time_elapsed | 12691 | +| total_timesteps | 3936256 | +| train/ | | +| approx_kl | 1.8199979 | +| clip_fraction | 0.459 | +| clip_range | 0.2 | +| entropy_loss | -0.344 | +| explained_variance | -2.52 | +| learning_rate | 0.0001 | +| loss | -0.0892 | +| n_updates | 98960 | +| policy_gradient_loss | -0.0626 | +| value_loss | 0.000445 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.52e+03 | +| ep_rew_mean | 0.247 | +| time/ | | +| fps | 310 | +| iterations | 3845 | +| time_elapsed | 12694 | +| total_timesteps | 3937280 | +| train/ | | +| approx_kl | 2.1568916 | +| clip_fraction | 0.452 | +| clip_range | 0.2 | +| entropy_loss | -0.333 | +| explained_variance | -2.62 | +| learning_rate | 0.0001 | +| loss | -0.0611 | +| n_updates | 98970 | +| policy_gradient_loss | -0.0657 | +| value_loss | 0.000523 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.52e+03 | +| ep_rew_mean | 0.247 | +| time/ | | +| fps | 310 | +| iterations | 3846 | +| time_elapsed | 12697 | +| total_timesteps | 3938304 | +| train/ | | +| approx_kl | 3.4699867 | +| clip_fraction | 0.484 | +| clip_range | 0.2 | +| entropy_loss | -0.33 | +| explained_variance | -0.403 | +| learning_rate | 0.0001 | +| loss | -0.087 | +| n_updates | 98980 | +| policy_gradient_loss | -0.0712 | +| value_loss | 0.000601 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.54e+03 | +| ep_rew_mean | 0.244 | +| time/ | | +| fps | 310 | +| iterations | 3847 | +| time_elapsed | 12700 | +| total_timesteps | 3939328 | +| train/ | | +| approx_kl | 1.9175911 | +| clip_fraction | 0.435 | +| clip_range | 0.2 | +| entropy_loss | -0.328 | +| explained_variance | -9.87 | +| learning_rate | 0.0001 | +| loss | -0.0732 | +| n_updates | 98990 | +| policy_gradient_loss | -0.0528 | +| value_loss | 0.00058 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.54e+03 | +| ep_rew_mean | 0.244 | +| time/ | | +| fps | 310 | +| iterations | 3848 | +| time_elapsed | 12704 | +| total_timesteps | 3940352 | +| train/ | | +| approx_kl | 2.7015333 | +| clip_fraction | 0.452 | +| clip_range | 0.2 | +| entropy_loss | -0.312 | +| explained_variance | -2.63 | +| learning_rate | 0.0001 | +| loss | -0.0609 | +| n_updates | 99000 | +| policy_gradient_loss | -0.065 | +| value_loss | 0.00039 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.54e+03 | +| ep_rew_mean | 0.242 | +| time/ | | +| fps | 310 | +| iterations | 3849 | +| time_elapsed | 12707 | +| total_timesteps | 3941376 | +| train/ | | +| approx_kl | 2.541891 | +| clip_fraction | 0.469 | +| clip_range | 0.2 | +| entropy_loss | -0.342 | +| explained_variance | -1.73 | +| learning_rate | 0.0001 | +| loss | -0.0912 | +| n_updates | 99010 | +| policy_gradient_loss | -0.0689 | +| value_loss | 0.000446 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.54e+03 | +| ep_rew_mean | 0.242 | +| time/ | | +| fps | 310 | +| iterations | 3850 | +| time_elapsed | 12711 | +| total_timesteps | 3942400 | +| train/ | | +| approx_kl | 5.0283337 | +| clip_fraction | 0.434 | +| clip_range | 0.2 | +| entropy_loss | -0.317 | +| explained_variance | -2.57 | +| learning_rate | 0.0001 | +| loss | -0.0722 | +| n_updates | 99020 | +| policy_gradient_loss | -0.0633 | +| value_loss | 0.000645 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.54e+03 | +| ep_rew_mean | 0.242 | +| time/ | | +| fps | 310 | +| iterations | 3851 | +| time_elapsed | 12714 | +| total_timesteps | 3943424 | +| train/ | | +| approx_kl | 1.9872987 | +| clip_fraction | 0.451 | +| clip_range | 0.2 | +| entropy_loss | -0.371 | +| explained_variance | -1.11 | +| learning_rate | 0.0001 | +| loss | -0.076 | +| n_updates | 99030 | +| policy_gradient_loss | -0.0644 | +| value_loss | 0.000446 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.54e+03 | +| ep_rew_mean | 0.242 | +| time/ | | +| fps | 310 | +| iterations | 3852 | +| time_elapsed | 12718 | +| total_timesteps | 3944448 | +| train/ | | +| approx_kl | 1.5423051 | +| clip_fraction | 0.423 | +| clip_range | 0.2 | +| entropy_loss | -0.364 | +| explained_variance | -13.8 | +| learning_rate | 0.0001 | +| loss | -0.116 | +| n_updates | 99040 | +| policy_gradient_loss | -0.0625 | +| value_loss | 0.000168 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.54e+03 | +| ep_rew_mean | 0.242 | +| time/ | | +| fps | 310 | +| iterations | 3853 | +| time_elapsed | 12721 | +| total_timesteps | 3945472 | +| train/ | | +| approx_kl | 1.6314389 | +| clip_fraction | 0.407 | +| clip_range | 0.2 | +| entropy_loss | -0.29 | +| explained_variance | -5.29 | +| learning_rate | 0.0001 | +| loss | -0.0898 | +| n_updates | 99050 | +| policy_gradient_loss | -0.0585 | +| value_loss | 0.000765 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.54e+03 | +| ep_rew_mean | 0.24 | +| time/ | | +| fps | 310 | +| iterations | 3854 | +| time_elapsed | 12724 | +| total_timesteps | 3946496 | +| train/ | | +| approx_kl | 2.0816824 | +| clip_fraction | 0.45 | +| clip_range | 0.2 | +| entropy_loss | -0.321 | +| explained_variance | -1.34 | +| learning_rate | 0.0001 | +| loss | -0.0781 | +| n_updates | 99060 | +| policy_gradient_loss | -0.063 | +| value_loss | 0.000532 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.54e+03 | +| ep_rew_mean | 0.24 | +| time/ | | +| fps | 310 | +| iterations | 3855 | +| time_elapsed | 12728 | +| total_timesteps | 3947520 | +| train/ | | +| approx_kl | 2.031749 | +| clip_fraction | 0.43 | +| clip_range | 0.2 | +| entropy_loss | -0.305 | +| explained_variance | -2.36 | +| learning_rate | 0.0001 | +| loss | -0.0868 | +| n_updates | 99070 | +| policy_gradient_loss | -0.0627 | +| value_loss | 0.00091 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.54e+03 | +| ep_rew_mean | 0.24 | +| time/ | | +| fps | 310 | +| iterations | 3856 | +| time_elapsed | 12731 | +| total_timesteps | 3948544 | +| train/ | | +| approx_kl | 2.0530646 | +| clip_fraction | 0.468 | +| clip_range | 0.2 | +| entropy_loss | -0.353 | +| explained_variance | -2.81 | +| learning_rate | 0.0001 | +| loss | -0.0728 | +| n_updates | 99080 | +| policy_gradient_loss | -0.0599 | +| value_loss | 0.00051 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.54e+03 | +| ep_rew_mean | 0.241 | +| time/ | | +| fps | 310 | +| iterations | 3857 | +| time_elapsed | 12734 | +| total_timesteps | 3949568 | +| train/ | | +| approx_kl | 1.7837231 | +| clip_fraction | 0.463 | +| clip_range | 0.2 | +| entropy_loss | -0.352 | +| explained_variance | -1.31 | +| learning_rate | 0.0001 | +| loss | -0.0962 | +| n_updates | 99090 | +| policy_gradient_loss | -0.071 | +| value_loss | 0.000353 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.54e+03 | +| ep_rew_mean | 0.241 | +| time/ | | +| fps | 310 | +| iterations | 3858 | +| time_elapsed | 12738 | +| total_timesteps | 3950592 | +| train/ | | +| approx_kl | 1.970245 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.36 | +| explained_variance | -2.83 | +| learning_rate | 0.0001 | +| loss | -0.0771 | +| n_updates | 99100 | +| policy_gradient_loss | -0.0626 | +| value_loss | 0.000425 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.54e+03 | +| ep_rew_mean | 0.241 | +| time/ | | +| fps | 310 | +| iterations | 3859 | +| time_elapsed | 12741 | +| total_timesteps | 3951616 | +| train/ | | +| approx_kl | 1.8711984 | +| clip_fraction | 0.428 | +| clip_range | 0.2 | +| entropy_loss | -0.324 | +| explained_variance | -2.94 | +| learning_rate | 0.0001 | +| loss | -0.0649 | +| n_updates | 99110 | +| policy_gradient_loss | -0.0655 | +| value_loss | 0.000697 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.54e+03 | +| ep_rew_mean | 0.241 | +| time/ | | +| fps | 310 | +| iterations | 3860 | +| time_elapsed | 12744 | +| total_timesteps | 3952640 | +| train/ | | +| approx_kl | 1.7962061 | +| clip_fraction | 0.45 | +| clip_range | 0.2 | +| entropy_loss | -0.352 | +| explained_variance | -5.52 | +| learning_rate | 0.0001 | +| loss | -0.0717 | +| n_updates | 99120 | +| policy_gradient_loss | -0.0613 | +| value_loss | 0.000648 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.54e+03 | +| ep_rew_mean | 0.241 | +| time/ | | +| fps | 310 | +| iterations | 3861 | +| time_elapsed | 12747 | +| total_timesteps | 3953664 | +| train/ | | +| approx_kl | 1.897743 | +| clip_fraction | 0.463 | +| clip_range | 0.2 | +| entropy_loss | -0.385 | +| explained_variance | -7.49 | +| learning_rate | 0.0001 | +| loss | -0.0686 | +| n_updates | 99130 | +| policy_gradient_loss | -0.0583 | +| value_loss | 0.00059 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.54e+03 | +| ep_rew_mean | 0.241 | +| time/ | | +| fps | 310 | +| iterations | 3862 | +| time_elapsed | 12750 | +| total_timesteps | 3954688 | +| train/ | | +| approx_kl | 13.371383 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.372 | +| explained_variance | -1.04 | +| learning_rate | 0.0001 | +| loss | -0.077 | +| n_updates | 99140 | +| policy_gradient_loss | -0.0628 | +| value_loss | 0.000467 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.54e+03 | +| ep_rew_mean | 0.241 | +| time/ | | +| fps | 310 | +| iterations | 3863 | +| time_elapsed | 12754 | +| total_timesteps | 3955712 | +| train/ | | +| approx_kl | 1.9901803 | +| clip_fraction | 0.462 | +| clip_range | 0.2 | +| entropy_loss | -0.354 | +| explained_variance | -4.11 | +| learning_rate | 0.0001 | +| loss | -0.0415 | +| n_updates | 99150 | +| policy_gradient_loss | -0.0557 | +| value_loss | 0.000343 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.54e+03 | +| ep_rew_mean | 0.241 | +| time/ | | +| fps | 310 | +| iterations | 3864 | +| time_elapsed | 12757 | +| total_timesteps | 3956736 | +| train/ | | +| approx_kl | 2.0523512 | +| clip_fraction | 0.458 | +| clip_range | 0.2 | +| entropy_loss | -0.346 | +| explained_variance | -1.08 | +| learning_rate | 0.0001 | +| loss | -0.0778 | +| n_updates | 99160 | +| policy_gradient_loss | -0.0645 | +| value_loss | 0.000502 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.54e+03 | +| ep_rew_mean | 0.242 | +| time/ | | +| fps | 310 | +| iterations | 3865 | +| time_elapsed | 12760 | +| total_timesteps | 3957760 | +| train/ | | +| approx_kl | 1.5894712 | +| clip_fraction | 0.469 | +| clip_range | 0.2 | +| entropy_loss | -0.412 | +| explained_variance | -1.39 | +| learning_rate | 0.0001 | +| loss | -0.0715 | +| n_updates | 99170 | +| policy_gradient_loss | -0.0609 | +| value_loss | 0.000334 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.54e+03 | +| ep_rew_mean | 0.242 | +| time/ | | +| fps | 310 | +| iterations | 3866 | +| time_elapsed | 12763 | +| total_timesteps | 3958784 | +| train/ | | +| approx_kl | 2.4917886 | +| clip_fraction | 0.442 | +| clip_range | 0.2 | +| entropy_loss | -0.307 | +| explained_variance | -7.95 | +| learning_rate | 0.0001 | +| loss | -0.0866 | +| n_updates | 99180 | +| policy_gradient_loss | -0.0664 | +| value_loss | 0.000452 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.53e+03 | +| ep_rew_mean | 0.237 | +| time/ | | +| fps | 310 | +| iterations | 3867 | +| time_elapsed | 12767 | +| total_timesteps | 3959808 | +| train/ | | +| approx_kl | 2.2425995 | +| clip_fraction | 0.42 | +| clip_range | 0.2 | +| entropy_loss | -0.301 | +| explained_variance | -8.81 | +| learning_rate | 0.0001 | +| loss | -0.0751 | +| n_updates | 99190 | +| policy_gradient_loss | -0.0669 | +| value_loss | 0.000557 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.53e+03 | +| ep_rew_mean | 0.237 | +| time/ | | +| fps | 310 | +| iterations | 3868 | +| time_elapsed | 12770 | +| total_timesteps | 3960832 | +| train/ | | +| approx_kl | 2.0557332 | +| clip_fraction | 0.451 | +| clip_range | 0.2 | +| entropy_loss | -0.34 | +| explained_variance | -3.97 | +| learning_rate | 0.0001 | +| loss | -0.076 | +| n_updates | 99200 | +| policy_gradient_loss | -0.0627 | +| value_loss | 0.000543 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.53e+03 | +| ep_rew_mean | 0.237 | +| time/ | | +| fps | 310 | +| iterations | 3869 | +| time_elapsed | 12774 | +| total_timesteps | 3961856 | +| train/ | | +| approx_kl | 2.7305353 | +| clip_fraction | 0.461 | +| clip_range | 0.2 | +| entropy_loss | -0.361 | +| explained_variance | -4.3 | +| learning_rate | 0.0001 | +| loss | -0.0769 | +| n_updates | 99210 | +| policy_gradient_loss | -0.0617 | +| value_loss | 0.000352 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.53e+03 | +| ep_rew_mean | 0.237 | +| time/ | | +| fps | 310 | +| iterations | 3870 | +| time_elapsed | 12777 | +| total_timesteps | 3962880 | +| train/ | | +| approx_kl | 1.8577855 | +| clip_fraction | 0.466 | +| clip_range | 0.2 | +| entropy_loss | -0.405 | +| explained_variance | -3.14 | +| learning_rate | 0.0001 | +| loss | -0.095 | +| n_updates | 99220 | +| policy_gradient_loss | -0.0639 | +| value_loss | 0.000351 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.53e+03 | +| ep_rew_mean | 0.237 | +| time/ | | +| fps | 310 | +| iterations | 3871 | +| time_elapsed | 12780 | +| total_timesteps | 3963904 | +| train/ | | +| approx_kl | 2.4286942 | +| clip_fraction | 0.469 | +| clip_range | 0.2 | +| entropy_loss | -0.358 | +| explained_variance | -1.12 | +| learning_rate | 0.0001 | +| loss | -0.0708 | +| n_updates | 99230 | +| policy_gradient_loss | -0.0588 | +| value_loss | 0.000287 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.53e+03 | +| ep_rew_mean | 0.237 | +| time/ | | +| fps | 310 | +| iterations | 3872 | +| time_elapsed | 12784 | +| total_timesteps | 3964928 | +| train/ | | +| approx_kl | 2.5735302 | +| clip_fraction | 0.568 | +| clip_range | 0.2 | +| entropy_loss | -0.645 | +| explained_variance | -0.0424 | +| learning_rate | 0.0001 | +| loss | -0.034 | +| n_updates | 99240 | +| policy_gradient_loss | -0.0336 | +| value_loss | 0.000406 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.57e+03 | +| ep_rew_mean | 0.239 | +| time/ | | +| fps | 310 | +| iterations | 3873 | +| time_elapsed | 12787 | +| total_timesteps | 3965952 | +| train/ | | +| approx_kl | 2.5944107 | +| clip_fraction | 0.459 | +| clip_range | 0.2 | +| entropy_loss | -0.313 | +| explained_variance | -1.38 | +| learning_rate | 0.0001 | +| loss | -0.0866 | +| n_updates | 99250 | +| policy_gradient_loss | -0.0645 | +| value_loss | 0.000386 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.57e+03 | +| ep_rew_mean | 0.239 | +| time/ | | +| fps | 310 | +| iterations | 3874 | +| time_elapsed | 12790 | +| total_timesteps | 3966976 | +| train/ | | +| approx_kl | 2.1852129 | +| clip_fraction | 0.454 | +| clip_range | 0.2 | +| entropy_loss | -0.301 | +| explained_variance | -1.71 | +| learning_rate | 0.0001 | +| loss | -0.0911 | +| n_updates | 99260 | +| policy_gradient_loss | -0.0645 | +| value_loss | 0.000594 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.57e+03 | +| ep_rew_mean | 0.24 | +| time/ | | +| fps | 310 | +| iterations | 3875 | +| time_elapsed | 12793 | +| total_timesteps | 3968000 | +| train/ | | +| approx_kl | 1.7481248 | +| clip_fraction | 0.427 | +| clip_range | 0.2 | +| entropy_loss | -0.345 | +| explained_variance | -2.87 | +| learning_rate | 0.0001 | +| loss | -0.0549 | +| n_updates | 99270 | +| policy_gradient_loss | -0.0582 | +| value_loss | 0.000391 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.57e+03 | +| ep_rew_mean | 0.24 | +| time/ | | +| fps | 310 | +| iterations | 3876 | +| time_elapsed | 12797 | +| total_timesteps | 3969024 | +| train/ | | +| approx_kl | 2.0590432 | +| clip_fraction | 0.461 | +| clip_range | 0.2 | +| entropy_loss | -0.336 | +| explained_variance | -3.31 | +| learning_rate | 0.0001 | +| loss | -0.0821 | +| n_updates | 99280 | +| policy_gradient_loss | -0.0679 | +| value_loss | 0.000657 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.56e+03 | +| ep_rew_mean | 0.239 | +| time/ | | +| fps | 310 | +| iterations | 3877 | +| time_elapsed | 12800 | +| total_timesteps | 3970048 | +| train/ | | +| approx_kl | 1.9496694 | +| clip_fraction | 0.464 | +| clip_range | 0.2 | +| entropy_loss | -0.349 | +| explained_variance | -1.36 | +| learning_rate | 0.0001 | +| loss | -0.0416 | +| n_updates | 99290 | +| policy_gradient_loss | -0.0605 | +| value_loss | 0.00058 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.56e+03 | +| ep_rew_mean | 0.239 | +| time/ | | +| fps | 310 | +| iterations | 3878 | +| time_elapsed | 12803 | +| total_timesteps | 3971072 | +| train/ | | +| approx_kl | 2.3233695 | +| clip_fraction | 0.414 | +| clip_range | 0.2 | +| entropy_loss | -0.296 | +| explained_variance | -2.26 | +| learning_rate | 0.0001 | +| loss | -0.0674 | +| n_updates | 99300 | +| policy_gradient_loss | -0.0629 | +| value_loss | 0.000737 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.56e+03 | +| ep_rew_mean | 0.239 | +| time/ | | +| fps | 310 | +| iterations | 3879 | +| time_elapsed | 12806 | +| total_timesteps | 3972096 | +| train/ | | +| approx_kl | 2.1416898 | +| clip_fraction | 0.463 | +| clip_range | 0.2 | +| entropy_loss | -0.329 | +| explained_variance | -3.22 | +| learning_rate | 0.0001 | +| loss | -0.0766 | +| n_updates | 99310 | +| policy_gradient_loss | -0.0602 | +| value_loss | 0.000611 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.56e+03 | +| ep_rew_mean | 0.236 | +| time/ | | +| fps | 310 | +| iterations | 3880 | +| time_elapsed | 12809 | +| total_timesteps | 3973120 | +| train/ | | +| approx_kl | 2.0795364 | +| clip_fraction | 0.445 | +| clip_range | 0.2 | +| entropy_loss | -0.324 | +| explained_variance | -5.71 | +| learning_rate | 0.0001 | +| loss | -0.0912 | +| n_updates | 99320 | +| policy_gradient_loss | -0.0691 | +| value_loss | 0.000304 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.56e+03 | +| ep_rew_mean | 0.236 | +| time/ | | +| fps | 310 | +| iterations | 3881 | +| time_elapsed | 12813 | +| total_timesteps | 3974144 | +| train/ | | +| approx_kl | 2.2376285 | +| clip_fraction | 0.465 | +| clip_range | 0.2 | +| entropy_loss | -0.333 | +| explained_variance | -1.14 | +| learning_rate | 0.0001 | +| loss | -0.0719 | +| n_updates | 99330 | +| policy_gradient_loss | -0.064 | +| value_loss | 0.000408 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.57e+03 | +| ep_rew_mean | 0.231 | +| time/ | | +| fps | 310 | +| iterations | 3882 | +| time_elapsed | 12816 | +| total_timesteps | 3975168 | +| train/ | | +| approx_kl | 1.9075719 | +| clip_fraction | 0.437 | +| clip_range | 0.2 | +| entropy_loss | -0.333 | +| explained_variance | -2.68 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 99340 | +| policy_gradient_loss | -0.0557 | +| value_loss | 0.000719 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.57e+03 | +| ep_rew_mean | 0.231 | +| time/ | | +| fps | 310 | +| iterations | 3883 | +| time_elapsed | 12819 | +| total_timesteps | 3976192 | +| train/ | | +| approx_kl | 2.2646947 | +| clip_fraction | 0.45 | +| clip_range | 0.2 | +| entropy_loss | -0.299 | +| explained_variance | -3.19 | +| learning_rate | 0.0001 | +| loss | -0.0647 | +| n_updates | 99350 | +| policy_gradient_loss | -0.0698 | +| value_loss | 0.00046 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.57e+03 | +| ep_rew_mean | 0.231 | +| time/ | | +| fps | 310 | +| iterations | 3884 | +| time_elapsed | 12822 | +| total_timesteps | 3977216 | +| train/ | | +| approx_kl | 1.8389292 | +| clip_fraction | 0.501 | +| clip_range | 0.2 | +| entropy_loss | -0.374 | +| explained_variance | -1.86 | +| learning_rate | 0.0001 | +| loss | -0.0912 | +| n_updates | 99360 | +| policy_gradient_loss | -0.0618 | +| value_loss | 0.000613 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.56e+03 | +| ep_rew_mean | 0.233 | +| time/ | | +| fps | 310 | +| iterations | 3885 | +| time_elapsed | 12826 | +| total_timesteps | 3978240 | +| train/ | | +| approx_kl | 2.4934816 | +| clip_fraction | 0.496 | +| clip_range | 0.2 | +| entropy_loss | -0.354 | +| explained_variance | -2.8 | +| learning_rate | 0.0001 | +| loss | -0.0963 | +| n_updates | 99370 | +| policy_gradient_loss | -0.0669 | +| value_loss | 0.000462 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.55e+03 | +| ep_rew_mean | 0.236 | +| time/ | | +| fps | 310 | +| iterations | 3886 | +| time_elapsed | 12829 | +| total_timesteps | 3979264 | +| train/ | | +| approx_kl | 2.380734 | +| clip_fraction | 0.425 | +| clip_range | 0.2 | +| entropy_loss | -0.295 | +| explained_variance | -2.66 | +| learning_rate | 0.0001 | +| loss | -0.0964 | +| n_updates | 99380 | +| policy_gradient_loss | -0.0617 | +| value_loss | 0.00046 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.55e+03 | +| ep_rew_mean | 0.236 | +| time/ | | +| fps | 310 | +| iterations | 3887 | +| time_elapsed | 12833 | +| total_timesteps | 3980288 | +| train/ | | +| approx_kl | 2.6384058 | +| clip_fraction | 0.511 | +| clip_range | 0.2 | +| entropy_loss | -0.348 | +| explained_variance | -1.03 | +| learning_rate | 0.0001 | +| loss | -0.0751 | +| n_updates | 99390 | +| policy_gradient_loss | -0.0663 | +| value_loss | 0.000778 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.55e+03 | +| ep_rew_mean | 0.236 | +| time/ | | +| fps | 310 | +| iterations | 3888 | +| time_elapsed | 12836 | +| total_timesteps | 3981312 | +| train/ | | +| approx_kl | 2.0105662 | +| clip_fraction | 0.449 | +| clip_range | 0.2 | +| entropy_loss | -0.317 | +| explained_variance | -6.23 | +| learning_rate | 0.0001 | +| loss | 0.0143 | +| n_updates | 99400 | +| policy_gradient_loss | -0.0656 | +| value_loss | 0.000566 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.56e+03 | +| ep_rew_mean | 0.235 | +| time/ | | +| fps | 310 | +| iterations | 3889 | +| time_elapsed | 12840 | +| total_timesteps | 3982336 | +| train/ | | +| approx_kl | 1.9881166 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.347 | +| explained_variance | -5.57 | +| learning_rate | 0.0001 | +| loss | -0.0956 | +| n_updates | 99410 | +| policy_gradient_loss | -0.0684 | +| value_loss | 0.000331 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.56e+03 | +| ep_rew_mean | 0.235 | +| time/ | | +| fps | 310 | +| iterations | 3890 | +| time_elapsed | 12843 | +| total_timesteps | 3983360 | +| train/ | | +| approx_kl | 2.661329 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.365 | +| explained_variance | -1.26 | +| learning_rate | 0.0001 | +| loss | -0.0848 | +| n_updates | 99420 | +| policy_gradient_loss | -0.0568 | +| value_loss | 0.000588 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.56e+03 | +| ep_rew_mean | 0.235 | +| time/ | | +| fps | 310 | +| iterations | 3891 | +| time_elapsed | 12847 | +| total_timesteps | 3984384 | +| train/ | | +| approx_kl | 2.3258653 | +| clip_fraction | 0.465 | +| clip_range | 0.2 | +| entropy_loss | -0.343 | +| explained_variance | -3.23 | +| learning_rate | 0.0001 | +| loss | -0.0672 | +| n_updates | 99430 | +| policy_gradient_loss | -0.0663 | +| value_loss | 0.000616 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.57e+03 | +| ep_rew_mean | 0.234 | +| time/ | | +| fps | 310 | +| iterations | 3892 | +| time_elapsed | 12850 | +| total_timesteps | 3985408 | +| train/ | | +| approx_kl | 11.357177 | +| clip_fraction | 0.463 | +| clip_range | 0.2 | +| entropy_loss | -0.357 | +| explained_variance | -4.43 | +| learning_rate | 0.0001 | +| loss | -0.097 | +| n_updates | 99440 | +| policy_gradient_loss | -0.0651 | +| value_loss | 0.000562 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.57e+03 | +| ep_rew_mean | 0.234 | +| time/ | | +| fps | 310 | +| iterations | 3893 | +| time_elapsed | 12853 | +| total_timesteps | 3986432 | +| train/ | | +| approx_kl | 1.6991909 | +| clip_fraction | 0.464 | +| clip_range | 0.2 | +| entropy_loss | -0.369 | +| explained_variance | -1.45 | +| learning_rate | 0.0001 | +| loss | -0.0639 | +| n_updates | 99450 | +| policy_gradient_loss | -0.0557 | +| value_loss | 0.00039 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.58e+03 | +| ep_rew_mean | 0.23 | +| time/ | | +| fps | 310 | +| iterations | 3894 | +| time_elapsed | 12857 | +| total_timesteps | 3987456 | +| train/ | | +| approx_kl | 1.8160723 | +| clip_fraction | 0.482 | +| clip_range | 0.2 | +| entropy_loss | -0.4 | +| explained_variance | -4.16 | +| learning_rate | 0.0001 | +| loss | -0.114 | +| n_updates | 99460 | +| policy_gradient_loss | -0.0716 | +| value_loss | 0.000337 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.58e+03 | +| ep_rew_mean | 0.23 | +| time/ | | +| fps | 310 | +| iterations | 3895 | +| time_elapsed | 12860 | +| total_timesteps | 3988480 | +| train/ | | +| approx_kl | 2.2923656 | +| clip_fraction | 0.516 | +| clip_range | 0.2 | +| entropy_loss | -0.41 | +| explained_variance | -1.18 | +| learning_rate | 0.0001 | +| loss | -0.0805 | +| n_updates | 99470 | +| policy_gradient_loss | -0.0666 | +| value_loss | 0.000428 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.57e+03 | +| ep_rew_mean | 0.228 | +| time/ | | +| fps | 310 | +| iterations | 3896 | +| time_elapsed | 12863 | +| total_timesteps | 3989504 | +| train/ | | +| approx_kl | 2.526995 | +| clip_fraction | 0.473 | +| clip_range | 0.2 | +| entropy_loss | -0.349 | +| explained_variance | -4.51 | +| learning_rate | 0.0001 | +| loss | -0.0811 | +| n_updates | 99480 | +| policy_gradient_loss | -0.0681 | +| value_loss | 0.000471 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.57e+03 | +| ep_rew_mean | 0.228 | +| time/ | | +| fps | 310 | +| iterations | 3897 | +| time_elapsed | 12866 | +| total_timesteps | 3990528 | +| train/ | | +| approx_kl | 2.1450953 | +| clip_fraction | 0.472 | +| clip_range | 0.2 | +| entropy_loss | -0.374 | +| explained_variance | -2.34 | +| learning_rate | 0.0001 | +| loss | -0.0978 | +| n_updates | 99490 | +| policy_gradient_loss | -0.0706 | +| value_loss | 0.000522 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.57e+03 | +| ep_rew_mean | 0.228 | +| time/ | | +| fps | 310 | +| iterations | 3898 | +| time_elapsed | 12870 | +| total_timesteps | 3991552 | +| train/ | | +| approx_kl | 2.7726665 | +| clip_fraction | 0.497 | +| clip_range | 0.2 | +| entropy_loss | -0.376 | +| explained_variance | -6.78 | +| learning_rate | 0.0001 | +| loss | -0.093 | +| n_updates | 99500 | +| policy_gradient_loss | -0.0641 | +| value_loss | 0.000402 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.58e+03 | +| ep_rew_mean | 0.223 | +| time/ | | +| fps | 310 | +| iterations | 3899 | +| time_elapsed | 12873 | +| total_timesteps | 3992576 | +| train/ | | +| approx_kl | 2.541957 | +| clip_fraction | 0.488 | +| clip_range | 0.2 | +| entropy_loss | -0.39 | +| explained_variance | -3.79 | +| learning_rate | 0.0001 | +| loss | -0.096 | +| n_updates | 99510 | +| policy_gradient_loss | -0.0672 | +| value_loss | 0.000313 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.58e+03 | +| ep_rew_mean | 0.223 | +| time/ | | +| fps | 310 | +| iterations | 3900 | +| time_elapsed | 12876 | +| total_timesteps | 3993600 | +| train/ | | +| approx_kl | 1.9344127 | +| clip_fraction | 0.453 | +| clip_range | 0.2 | +| entropy_loss | -0.362 | +| explained_variance | -1.4 | +| learning_rate | 0.0001 | +| loss | -0.0886 | +| n_updates | 99520 | +| policy_gradient_loss | -0.0577 | +| value_loss | 0.00031 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.57e+03 | +| ep_rew_mean | 0.224 | +| time/ | | +| fps | 310 | +| iterations | 3901 | +| time_elapsed | 12879 | +| total_timesteps | 3994624 | +| train/ | | +| approx_kl | 1.9984417 | +| clip_fraction | 0.456 | +| clip_range | 0.2 | +| entropy_loss | -0.345 | +| explained_variance | -2.34 | +| learning_rate | 0.0001 | +| loss | -0.0714 | +| n_updates | 99530 | +| policy_gradient_loss | -0.0669 | +| value_loss | 0.000553 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.57e+03 | +| ep_rew_mean | 0.224 | +| time/ | | +| fps | 310 | +| iterations | 3902 | +| time_elapsed | 12883 | +| total_timesteps | 3995648 | +| train/ | | +| approx_kl | 1.8608065 | +| clip_fraction | 0.466 | +| clip_range | 0.2 | +| entropy_loss | -0.372 | +| explained_variance | -4.02 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 99540 | +| policy_gradient_loss | -0.0594 | +| value_loss | 0.000613 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.57e+03 | +| ep_rew_mean | 0.224 | +| time/ | | +| fps | 310 | +| iterations | 3903 | +| time_elapsed | 12886 | +| total_timesteps | 3996672 | +| train/ | | +| approx_kl | 2.2948356 | +| clip_fraction | 0.518 | +| clip_range | 0.2 | +| entropy_loss | -0.392 | +| explained_variance | -1.78 | +| learning_rate | 0.0001 | +| loss | -0.108 | +| n_updates | 99550 | +| policy_gradient_loss | -0.0711 | +| value_loss | 0.000467 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.57e+03 | +| ep_rew_mean | 0.225 | +| time/ | | +| fps | 310 | +| iterations | 3904 | +| time_elapsed | 12889 | +| total_timesteps | 3997696 | +| train/ | | +| approx_kl | 1.8945014 | +| clip_fraction | 0.514 | +| clip_range | 0.2 | +| entropy_loss | -0.437 | +| explained_variance | -1.81 | +| learning_rate | 0.0001 | +| loss | -0.0778 | +| n_updates | 99560 | +| policy_gradient_loss | -0.0795 | +| value_loss | 0.000257 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.57e+03 | +| ep_rew_mean | 0.225 | +| time/ | | +| fps | 310 | +| iterations | 3905 | +| time_elapsed | 12893 | +| total_timesteps | 3998720 | +| train/ | | +| approx_kl | 1.9223728 | +| clip_fraction | 0.477 | +| clip_range | 0.2 | +| entropy_loss | -0.352 | +| explained_variance | -1.82 | +| learning_rate | 0.0001 | +| loss | -0.0504 | +| n_updates | 99570 | +| policy_gradient_loss | -0.0609 | +| value_loss | 0.000755 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.58e+03 | +| ep_rew_mean | 0.228 | +| time/ | | +| fps | 310 | +| iterations | 3906 | +| time_elapsed | 12897 | +| total_timesteps | 3999744 | +| train/ | | +| approx_kl | 3.273931 | +| clip_fraction | 0.537 | +| clip_range | 0.2 | +| entropy_loss | -0.422 | +| explained_variance | -10.8 | +| learning_rate | 0.0001 | +| loss | -0.0806 | +| n_updates | 99580 | +| policy_gradient_loss | -0.0767 | +| value_loss | 0.000259 | +-------------------------------------- + +Current state: Champion.Level11.RyuVsSagat +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.58e+03 | +| ep_rew_mean | 0.228 | +| time/ | | +| fps | 310 | +| iterations | 3907 | +| time_elapsed | 12900 | +| total_timesteps | 4000768 | +| train/ | | +| approx_kl | 2.0807316 | +| clip_fraction | 0.458 | +| clip_range | 0.2 | +| entropy_loss | -0.329 | +| explained_variance | -0.513 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 99590 | +| policy_gradient_loss | -0.0567 | +| value_loss | 0.000575 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.57e+03 | +| ep_rew_mean | 0.229 | +| time/ | | +| fps | 310 | +| iterations | 3908 | +| time_elapsed | 12904 | +| total_timesteps | 4001792 | +| train/ | | +| approx_kl | 1.8297743 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.359 | +| explained_variance | -1.81 | +| learning_rate | 0.0001 | +| loss | -0.112 | +| n_updates | 99600 | +| policy_gradient_loss | -0.0695 | +| value_loss | 0.000547 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.57e+03 | +| ep_rew_mean | 0.229 | +| time/ | | +| fps | 310 | +| iterations | 3909 | +| time_elapsed | 12907 | +| total_timesteps | 4002816 | +| train/ | | +| approx_kl | 1.6180625 | +| clip_fraction | 0.506 | +| clip_range | 0.2 | +| entropy_loss | -0.515 | +| explained_variance | -1.42 | +| learning_rate | 0.0001 | +| loss | -0.0513 | +| n_updates | 99610 | +| policy_gradient_loss | -0.0656 | +| value_loss | 0.000378 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.56e+03 | +| ep_rew_mean | 0.23 | +| time/ | | +| fps | 310 | +| iterations | 3910 | +| time_elapsed | 12910 | +| total_timesteps | 4003840 | +| train/ | | +| approx_kl | 1.2200955 | +| clip_fraction | 0.566 | +| clip_range | 0.2 | +| entropy_loss | -0.733 | +| explained_variance | -1.2 | +| learning_rate | 0.0001 | +| loss | -0.109 | +| n_updates | 99620 | +| policy_gradient_loss | -0.0762 | +| value_loss | 0.000309 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.56e+03 | +| ep_rew_mean | 0.23 | +| time/ | | +| fps | 310 | +| iterations | 3911 | +| time_elapsed | 12914 | +| total_timesteps | 4004864 | +| train/ | | +| approx_kl | 1.1105102 | +| clip_fraction | 0.545 | +| clip_range | 0.2 | +| entropy_loss | -0.737 | +| explained_variance | -3.58 | +| learning_rate | 0.0001 | +| loss | -0.085 | +| n_updates | 99630 | +| policy_gradient_loss | -0.0819 | +| value_loss | 0.000159 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.55e+03 | +| ep_rew_mean | 0.224 | +| time/ | | +| fps | 310 | +| iterations | 3912 | +| time_elapsed | 12917 | +| total_timesteps | 4005888 | +| train/ | | +| approx_kl | 1.1644465 | +| clip_fraction | 0.5 | +| clip_range | 0.2 | +| entropy_loss | -0.618 | +| explained_variance | -1.25 | +| learning_rate | 0.0001 | +| loss | -0.0653 | +| n_updates | 99640 | +| policy_gradient_loss | -0.0753 | +| value_loss | 6.78e-05 | +--------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 2.54e+03 | +| ep_rew_mean | 0.223 | +| time/ | | +| fps | 310 | +| iterations | 3913 | +| time_elapsed | 12920 | +| total_timesteps | 4006912 | +| train/ | | +| approx_kl | 0.95667994 | +| clip_fraction | 0.503 | +| clip_range | 0.2 | +| entropy_loss | -0.704 | +| explained_variance | -0.204 | +| learning_rate | 0.0001 | +| loss | -0.061 | +| n_updates | 99650 | +| policy_gradient_loss | -0.0527 | +| value_loss | 0.000317 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 2.53e+03 | +| ep_rew_mean | 0.219 | +| time/ | | +| fps | 310 | +| iterations | 3914 | +| time_elapsed | 12923 | +| total_timesteps | 4007936 | +| train/ | | +| approx_kl | 0.84243834 | +| clip_fraction | 0.523 | +| clip_range | 0.2 | +| entropy_loss | -0.722 | +| explained_variance | -1.39 | +| learning_rate | 0.0001 | +| loss | -0.0765 | +| n_updates | 99660 | +| policy_gradient_loss | -0.0652 | +| value_loss | 0.000658 | +---------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.53e+03 | +| ep_rew_mean | 0.219 | +| time/ | | +| fps | 310 | +| iterations | 3915 | +| time_elapsed | 12926 | +| total_timesteps | 4008960 | +| train/ | | +| approx_kl | 0.9285501 | +| clip_fraction | 0.521 | +| clip_range | 0.2 | +| entropy_loss | -0.652 | +| explained_variance | -3.22 | +| learning_rate | 0.0001 | +| loss | -0.099 | +| n_updates | 99670 | +| policy_gradient_loss | -0.0751 | +| value_loss | 0.000355 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.52e+03 | +| ep_rew_mean | 0.213 | +| time/ | | +| fps | 310 | +| iterations | 3916 | +| time_elapsed | 12929 | +| total_timesteps | 4009984 | +| train/ | | +| approx_kl | 1.632627 | +| clip_fraction | 0.556 | +| clip_range | 0.2 | +| entropy_loss | -0.757 | +| explained_variance | -2.77 | +| learning_rate | 0.0001 | +| loss | -0.0371 | +| n_updates | 99680 | +| policy_gradient_loss | -0.0643 | +| value_loss | 0.000295 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.52e+03 | +| ep_rew_mean | 0.207 | +| time/ | | +| fps | 310 | +| iterations | 3917 | +| time_elapsed | 12932 | +| total_timesteps | 4011008 | +| train/ | | +| approx_kl | 0.8347266 | +| clip_fraction | 0.5 | +| clip_range | 0.2 | +| entropy_loss | -0.734 | +| explained_variance | -0.742 | +| learning_rate | 0.0001 | +| loss | -0.0754 | +| n_updates | 99690 | +| policy_gradient_loss | -0.0657 | +| value_loss | 0.000256 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.52e+03 | +| ep_rew_mean | 0.207 | +| time/ | | +| fps | 310 | +| iterations | 3918 | +| time_elapsed | 12936 | +| total_timesteps | 4012032 | +| train/ | | +| approx_kl | 1.2182751 | +| clip_fraction | 0.546 | +| clip_range | 0.2 | +| entropy_loss | -0.679 | +| explained_variance | -0.0559 | +| learning_rate | 0.0001 | +| loss | -0.116 | +| n_updates | 99700 | +| policy_gradient_loss | -0.0749 | +| value_loss | 0.000267 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.51e+03 | +| ep_rew_mean | 0.203 | +| time/ | | +| fps | 310 | +| iterations | 3919 | +| time_elapsed | 12939 | +| total_timesteps | 4013056 | +| train/ | | +| approx_kl | 1.019667 | +| clip_fraction | 0.512 | +| clip_range | 0.2 | +| entropy_loss | -0.689 | +| explained_variance | -0.533 | +| learning_rate | 0.0001 | +| loss | -0.0978 | +| n_updates | 99710 | +| policy_gradient_loss | -0.0703 | +| value_loss | 0.000359 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.5e+03 | +| ep_rew_mean | 0.197 | +| time/ | | +| fps | 310 | +| iterations | 3920 | +| time_elapsed | 12942 | +| total_timesteps | 4014080 | +| train/ | | +| approx_kl | 1.8065915 | +| clip_fraction | 0.541 | +| clip_range | 0.2 | +| entropy_loss | -0.681 | +| explained_variance | -2.06 | +| learning_rate | 0.0001 | +| loss | -0.0937 | +| n_updates | 99720 | +| policy_gradient_loss | -0.0769 | +| value_loss | 0.000219 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.49e+03 | +| ep_rew_mean | 0.198 | +| time/ | | +| fps | 310 | +| iterations | 3921 | +| time_elapsed | 12946 | +| total_timesteps | 4015104 | +| train/ | | +| approx_kl | 1.4617577 | +| clip_fraction | 0.535 | +| clip_range | 0.2 | +| entropy_loss | -0.695 | +| explained_variance | -0.546 | +| learning_rate | 0.0001 | +| loss | -0.0808 | +| n_updates | 99730 | +| policy_gradient_loss | -0.0727 | +| value_loss | 0.000358 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.48e+03 | +| ep_rew_mean | 0.198 | +| time/ | | +| fps | 310 | +| iterations | 3922 | +| time_elapsed | 12949 | +| total_timesteps | 4016128 | +| train/ | | +| approx_kl | 1.7132759 | +| clip_fraction | 0.532 | +| clip_range | 0.2 | +| entropy_loss | -0.65 | +| explained_variance | -3.17 | +| learning_rate | 0.0001 | +| loss | -0.111 | +| n_updates | 99740 | +| policy_gradient_loss | -0.078 | +| value_loss | 0.000311 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.48e+03 | +| ep_rew_mean | 0.198 | +| time/ | | +| fps | 310 | +| iterations | 3923 | +| time_elapsed | 12953 | +| total_timesteps | 4017152 | +| train/ | | +| approx_kl | 1.0756091 | +| clip_fraction | 0.551 | +| clip_range | 0.2 | +| entropy_loss | -0.749 | +| explained_variance | -0.332 | +| learning_rate | 0.0001 | +| loss | -0.0909 | +| n_updates | 99750 | +| policy_gradient_loss | -0.0747 | +| value_loss | 0.000435 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.45e+03 | +| ep_rew_mean | 0.19 | +| time/ | | +| fps | 310 | +| iterations | 3924 | +| time_elapsed | 12956 | +| total_timesteps | 4018176 | +| train/ | | +| approx_kl | 1.8917408 | +| clip_fraction | 0.558 | +| clip_range | 0.2 | +| entropy_loss | -0.577 | +| explained_variance | -6.76 | +| learning_rate | 0.0001 | +| loss | -0.095 | +| n_updates | 99760 | +| policy_gradient_loss | -0.0793 | +| value_loss | 0.000353 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.43e+03 | +| ep_rew_mean | 0.189 | +| time/ | | +| fps | 310 | +| iterations | 3925 | +| time_elapsed | 12959 | +| total_timesteps | 4019200 | +| train/ | | +| approx_kl | 1.265355 | +| clip_fraction | 0.523 | +| clip_range | 0.2 | +| entropy_loss | -0.746 | +| explained_variance | -1.31 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 99770 | +| policy_gradient_loss | -0.0771 | +| value_loss | 0.000206 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.43e+03 | +| ep_rew_mean | 0.189 | +| time/ | | +| fps | 310 | +| iterations | 3926 | +| time_elapsed | 12963 | +| total_timesteps | 4020224 | +| train/ | | +| approx_kl | 1.0973122 | +| clip_fraction | 0.509 | +| clip_range | 0.2 | +| entropy_loss | -0.627 | +| explained_variance | -1.1 | +| learning_rate | 0.0001 | +| loss | -0.107 | +| n_updates | 99780 | +| policy_gradient_loss | -0.0737 | +| value_loss | 0.000342 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.42e+03 | +| ep_rew_mean | 0.189 | +| time/ | | +| fps | 310 | +| iterations | 3927 | +| time_elapsed | 12966 | +| total_timesteps | 4021248 | +| train/ | | +| approx_kl | 1.2508569 | +| clip_fraction | 0.524 | +| clip_range | 0.2 | +| entropy_loss | -0.643 | +| explained_variance | -3.85 | +| learning_rate | 0.0001 | +| loss | -0.0881 | +| n_updates | 99790 | +| policy_gradient_loss | -0.0734 | +| value_loss | 0.000246 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.42e+03 | +| ep_rew_mean | 0.189 | +| time/ | | +| fps | 310 | +| iterations | 3928 | +| time_elapsed | 12970 | +| total_timesteps | 4022272 | +| train/ | | +| approx_kl | 1.280091 | +| clip_fraction | 0.504 | +| clip_range | 0.2 | +| entropy_loss | -0.669 | +| explained_variance | -0.524 | +| learning_rate | 0.0001 | +| loss | -0.061 | +| n_updates | 99800 | +| policy_gradient_loss | -0.0625 | +| value_loss | 0.000149 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.42e+03 | +| ep_rew_mean | 0.189 | +| time/ | | +| fps | 310 | +| iterations | 3929 | +| time_elapsed | 12973 | +| total_timesteps | 4023296 | +| train/ | | +| approx_kl | 1.4214165 | +| clip_fraction | 0.575 | +| clip_range | 0.2 | +| entropy_loss | -0.716 | +| explained_variance | -1.73 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 99810 | +| policy_gradient_loss | -0.0762 | +| value_loss | 0.000672 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.43e+03 | +| ep_rew_mean | 0.187 | +| time/ | | +| fps | 310 | +| iterations | 3930 | +| time_elapsed | 12976 | +| total_timesteps | 4024320 | +| train/ | | +| approx_kl | 2.3752909 | +| clip_fraction | 0.537 | +| clip_range | 0.2 | +| entropy_loss | -0.6 | +| explained_variance | -1.4 | +| learning_rate | 0.0001 | +| loss | -0.0985 | +| n_updates | 99820 | +| policy_gradient_loss | -0.0769 | +| value_loss | 0.000502 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.42e+03 | +| ep_rew_mean | 0.182 | +| time/ | | +| fps | 310 | +| iterations | 3931 | +| time_elapsed | 12979 | +| total_timesteps | 4025344 | +| train/ | | +| approx_kl | 1.3399134 | +| clip_fraction | 0.544 | +| clip_range | 0.2 | +| entropy_loss | -0.734 | +| explained_variance | -3.97 | +| learning_rate | 0.0001 | +| loss | -0.0845 | +| n_updates | 99830 | +| policy_gradient_loss | -0.0682 | +| value_loss | 0.000416 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.4e+03 | +| ep_rew_mean | 0.177 | +| time/ | | +| fps | 310 | +| iterations | 3932 | +| time_elapsed | 12983 | +| total_timesteps | 4026368 | +| train/ | | +| approx_kl | 1.2024534 | +| clip_fraction | 0.541 | +| clip_range | 0.2 | +| entropy_loss | -0.734 | +| explained_variance | -0.902 | +| learning_rate | 0.0001 | +| loss | -0.0918 | +| n_updates | 99840 | +| policy_gradient_loss | -0.0689 | +| value_loss | 0.000367 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.4e+03 | +| ep_rew_mean | 0.177 | +| time/ | | +| fps | 310 | +| iterations | 3933 | +| time_elapsed | 12986 | +| total_timesteps | 4027392 | +| train/ | | +| approx_kl | 1.0218421 | +| clip_fraction | 0.502 | +| clip_range | 0.2 | +| entropy_loss | -0.626 | +| explained_variance | -1.49 | +| learning_rate | 0.0001 | +| loss | -0.0985 | +| n_updates | 99850 | +| policy_gradient_loss | -0.0705 | +| value_loss | 0.000414 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.39e+03 | +| ep_rew_mean | 0.176 | +| time/ | | +| fps | 310 | +| iterations | 3934 | +| time_elapsed | 12989 | +| total_timesteps | 4028416 | +| train/ | | +| approx_kl | 1.658276 | +| clip_fraction | 0.568 | +| clip_range | 0.2 | +| entropy_loss | -0.64 | +| explained_variance | -1.64 | +| learning_rate | 0.0001 | +| loss | -0.109 | +| n_updates | 99860 | +| policy_gradient_loss | -0.0828 | +| value_loss | 0.000463 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.37e+03 | +| ep_rew_mean | 0.172 | +| time/ | | +| fps | 310 | +| iterations | 3935 | +| time_elapsed | 12992 | +| total_timesteps | 4029440 | +| train/ | | +| approx_kl | 1.1566567 | +| clip_fraction | 0.506 | +| clip_range | 0.2 | +| entropy_loss | -0.651 | +| explained_variance | -4.27 | +| learning_rate | 0.0001 | +| loss | -0.0954 | +| n_updates | 99870 | +| policy_gradient_loss | -0.0701 | +| value_loss | 0.000258 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.37e+03 | +| ep_rew_mean | 0.17 | +| time/ | | +| fps | 310 | +| iterations | 3936 | +| time_elapsed | 12996 | +| total_timesteps | 4030464 | +| train/ | | +| approx_kl | 1.2499586 | +| clip_fraction | 0.519 | +| clip_range | 0.2 | +| entropy_loss | -0.654 | +| explained_variance | -0.903 | +| learning_rate | 0.0001 | +| loss | -0.0912 | +| n_updates | 99880 | +| policy_gradient_loss | -0.0657 | +| value_loss | 0.000264 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.37e+03 | +| ep_rew_mean | 0.17 | +| time/ | | +| fps | 310 | +| iterations | 3937 | +| time_elapsed | 12999 | +| total_timesteps | 4031488 | +| train/ | | +| approx_kl | 1.410114 | +| clip_fraction | 0.528 | +| clip_range | 0.2 | +| entropy_loss | -0.716 | +| explained_variance | -2.38 | +| learning_rate | 0.0001 | +| loss | -0.121 | +| n_updates | 99890 | +| policy_gradient_loss | -0.0749 | +| value_loss | 0.000207 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.36e+03 | +| ep_rew_mean | 0.166 | +| time/ | | +| fps | 310 | +| iterations | 3938 | +| time_elapsed | 13002 | +| total_timesteps | 4032512 | +| train/ | | +| approx_kl | 1.3502512 | +| clip_fraction | 0.515 | +| clip_range | 0.2 | +| entropy_loss | -0.709 | +| explained_variance | -0.469 | +| learning_rate | 0.0001 | +| loss | -0.0988 | +| n_updates | 99900 | +| policy_gradient_loss | -0.0708 | +| value_loss | 0.000206 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.34e+03 | +| ep_rew_mean | 0.161 | +| time/ | | +| fps | 310 | +| iterations | 3939 | +| time_elapsed | 13006 | +| total_timesteps | 4033536 | +| train/ | | +| approx_kl | 1.4396838 | +| clip_fraction | 0.511 | +| clip_range | 0.2 | +| entropy_loss | -0.624 | +| explained_variance | -5.96 | +| learning_rate | 0.0001 | +| loss | -0.0685 | +| n_updates | 99910 | +| policy_gradient_loss | -0.0698 | +| value_loss | 0.0003 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.33e+03 | +| ep_rew_mean | 0.157 | +| time/ | | +| fps | 310 | +| iterations | 3940 | +| time_elapsed | 13009 | +| total_timesteps | 4034560 | +| train/ | | +| approx_kl | 1.425395 | +| clip_fraction | 0.527 | +| clip_range | 0.2 | +| entropy_loss | -0.605 | +| explained_variance | -0.467 | +| learning_rate | 0.0001 | +| loss | -0.117 | +| n_updates | 99920 | +| policy_gradient_loss | -0.0758 | +| value_loss | 0.000346 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.31e+03 | +| ep_rew_mean | 0.154 | +| time/ | | +| fps | 310 | +| iterations | 3941 | +| time_elapsed | 13012 | +| total_timesteps | 4035584 | +| train/ | | +| approx_kl | 1.2403009 | +| clip_fraction | 0.507 | +| clip_range | 0.2 | +| entropy_loss | -0.633 | +| explained_variance | -1.26 | +| learning_rate | 0.0001 | +| loss | -0.107 | +| n_updates | 99930 | +| policy_gradient_loss | -0.0751 | +| value_loss | 0.000369 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.3e+03 | +| ep_rew_mean | 0.151 | +| time/ | | +| fps | 310 | +| iterations | 3942 | +| time_elapsed | 13015 | +| total_timesteps | 4036608 | +| train/ | | +| approx_kl | 1.2967789 | +| clip_fraction | 0.547 | +| clip_range | 0.2 | +| entropy_loss | -0.693 | +| explained_variance | -0.775 | +| learning_rate | 0.0001 | +| loss | -0.115 | +| n_updates | 99940 | +| policy_gradient_loss | -0.0795 | +| value_loss | 0.00051 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.3e+03 | +| ep_rew_mean | 0.151 | +| time/ | | +| fps | 310 | +| iterations | 3943 | +| time_elapsed | 13019 | +| total_timesteps | 4037632 | +| train/ | | +| approx_kl | 1.152826 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.488 | +| explained_variance | -1.51 | +| learning_rate | 0.0001 | +| loss | -0.0846 | +| n_updates | 99950 | +| policy_gradient_loss | -0.0746 | +| value_loss | 0.000816 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.29e+03 | +| ep_rew_mean | 0.147 | +| time/ | | +| fps | 310 | +| iterations | 3944 | +| time_elapsed | 13022 | +| total_timesteps | 4038656 | +| train/ | | +| approx_kl | 1.5044563 | +| clip_fraction | 0.517 | +| clip_range | 0.2 | +| entropy_loss | -0.567 | +| explained_variance | -1.24 | +| learning_rate | 0.0001 | +| loss | -0.0147 | +| n_updates | 99960 | +| policy_gradient_loss | -0.0393 | +| value_loss | 0.00141 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.28e+03 | +| ep_rew_mean | 0.142 | +| time/ | | +| fps | 310 | +| iterations | 3945 | +| time_elapsed | 13026 | +| total_timesteps | 4039680 | +| train/ | | +| approx_kl | 1.2824883 | +| clip_fraction | 0.484 | +| clip_range | 0.2 | +| entropy_loss | -0.574 | +| explained_variance | -2.83 | +| learning_rate | 0.0001 | +| loss | -0.1 | +| n_updates | 99970 | +| policy_gradient_loss | -0.0632 | +| value_loss | 0.000467 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.27e+03 | +| ep_rew_mean | 0.137 | +| time/ | | +| fps | 310 | +| iterations | 3946 | +| time_elapsed | 13029 | +| total_timesteps | 4040704 | +| train/ | | +| approx_kl | 1.3587068 | +| clip_fraction | 0.503 | +| clip_range | 0.2 | +| entropy_loss | -0.636 | +| explained_variance | -1.16 | +| learning_rate | 0.0001 | +| loss | -0.0882 | +| n_updates | 99980 | +| policy_gradient_loss | -0.0686 | +| value_loss | 0.000346 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.27e+03 | +| ep_rew_mean | 0.137 | +| time/ | | +| fps | 310 | +| iterations | 3947 | +| time_elapsed | 13032 | +| total_timesteps | 4041728 | +| train/ | | +| approx_kl | 1.0837194 | +| clip_fraction | 0.473 | +| clip_range | 0.2 | +| entropy_loss | -0.536 | +| explained_variance | -0.877 | +| learning_rate | 0.0001 | +| loss | -0.0966 | +| n_updates | 99990 | +| policy_gradient_loss | -0.0682 | +| value_loss | 0.000398 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.26e+03 | +| ep_rew_mean | 0.136 | +| time/ | | +| fps | 310 | +| iterations | 3948 | +| time_elapsed | 13035 | +| total_timesteps | 4042752 | +| train/ | | +| approx_kl | 1.4766183 | +| clip_fraction | 0.511 | +| clip_range | 0.2 | +| entropy_loss | -0.571 | +| explained_variance | -0.477 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 100000 | +| policy_gradient_loss | -0.0768 | +| value_loss | 0.000296 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.25e+03 | +| ep_rew_mean | 0.138 | +| time/ | | +| fps | 310 | +| iterations | 3949 | +| time_elapsed | 13039 | +| total_timesteps | 4043776 | +| train/ | | +| approx_kl | 2.0837588 | +| clip_fraction | 0.528 | +| clip_range | 0.2 | +| entropy_loss | -0.571 | +| explained_variance | -1.8 | +| learning_rate | 0.0001 | +| loss | -0.0646 | +| n_updates | 100010 | +| policy_gradient_loss | -0.0763 | +| value_loss | 0.000476 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.24e+03 | +| ep_rew_mean | 0.137 | +| time/ | | +| fps | 310 | +| iterations | 3950 | +| time_elapsed | 13042 | +| total_timesteps | 4044800 | +| train/ | | +| approx_kl | 1.7055542 | +| clip_fraction | 0.53 | +| clip_range | 0.2 | +| entropy_loss | -0.612 | +| explained_variance | -0.925 | +| learning_rate | 0.0001 | +| loss | -0.0618 | +| n_updates | 100020 | +| policy_gradient_loss | -0.0734 | +| value_loss | 0.000328 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.23e+03 | +| ep_rew_mean | 0.132 | +| time/ | | +| fps | 310 | +| iterations | 3951 | +| time_elapsed | 13045 | +| total_timesteps | 4045824 | +| train/ | | +| approx_kl | 1.5666562 | +| clip_fraction | 0.518 | +| clip_range | 0.2 | +| entropy_loss | -0.593 | +| explained_variance | -0.684 | +| learning_rate | 0.0001 | +| loss | -0.081 | +| n_updates | 100030 | +| policy_gradient_loss | -0.0651 | +| value_loss | 0.000345 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.22e+03 | +| ep_rew_mean | 0.131 | +| time/ | | +| fps | 310 | +| iterations | 3952 | +| time_elapsed | 13048 | +| total_timesteps | 4046848 | +| train/ | | +| approx_kl | 1.2997863 | +| clip_fraction | 0.495 | +| clip_range | 0.2 | +| entropy_loss | -0.529 | +| explained_variance | -1.54 | +| learning_rate | 0.0001 | +| loss | -0.0646 | +| n_updates | 100040 | +| policy_gradient_loss | -0.0664 | +| value_loss | 0.000409 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.22e+03 | +| ep_rew_mean | 0.131 | +| time/ | | +| fps | 310 | +| iterations | 3953 | +| time_elapsed | 13051 | +| total_timesteps | 4047872 | +| train/ | | +| approx_kl | 2.1909022 | +| clip_fraction | 0.494 | +| clip_range | 0.2 | +| entropy_loss | -0.505 | +| explained_variance | -0.953 | +| learning_rate | 0.0001 | +| loss | -0.0631 | +| n_updates | 100050 | +| policy_gradient_loss | -0.0788 | +| value_loss | 0.000328 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.2e+03 | +| ep_rew_mean | 0.128 | +| time/ | | +| fps | 310 | +| iterations | 3954 | +| time_elapsed | 13054 | +| total_timesteps | 4048896 | +| train/ | | +| approx_kl | 1.5337573 | +| clip_fraction | 0.548 | +| clip_range | 0.2 | +| entropy_loss | -0.667 | +| explained_variance | -0.739 | +| learning_rate | 0.0001 | +| loss | -0.0931 | +| n_updates | 100060 | +| policy_gradient_loss | -0.0683 | +| value_loss | 0.000299 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.19e+03 | +| ep_rew_mean | 0.126 | +| time/ | | +| fps | 310 | +| iterations | 3955 | +| time_elapsed | 13058 | +| total_timesteps | 4049920 | +| train/ | | +| approx_kl | 1.5293385 | +| clip_fraction | 0.514 | +| clip_range | 0.2 | +| entropy_loss | -0.508 | +| explained_variance | -1.49 | +| learning_rate | 0.0001 | +| loss | -0.0824 | +| n_updates | 100070 | +| policy_gradient_loss | -0.0758 | +| value_loss | 0.000323 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.16e+03 | +| ep_rew_mean | 0.121 | +| time/ | | +| fps | 310 | +| iterations | 3956 | +| time_elapsed | 13061 | +| total_timesteps | 4050944 | +| train/ | | +| approx_kl | 1.5622272 | +| clip_fraction | 0.484 | +| clip_range | 0.2 | +| entropy_loss | -0.543 | +| explained_variance | -1.37 | +| learning_rate | 0.0001 | +| loss | -0.0854 | +| n_updates | 100080 | +| policy_gradient_loss | -0.0683 | +| value_loss | 0.000493 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.16e+03 | +| ep_rew_mean | 0.123 | +| time/ | | +| fps | 310 | +| iterations | 3957 | +| time_elapsed | 13065 | +| total_timesteps | 4051968 | +| train/ | | +| approx_kl | 1.4885064 | +| clip_fraction | 0.523 | +| clip_range | 0.2 | +| entropy_loss | -0.585 | +| explained_variance | -0.905 | +| learning_rate | 0.0001 | +| loss | -0.1 | +| n_updates | 100090 | +| policy_gradient_loss | -0.0774 | +| value_loss | 0.000445 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.15e+03 | +| ep_rew_mean | 0.119 | +| time/ | | +| fps | 310 | +| iterations | 3958 | +| time_elapsed | 13068 | +| total_timesteps | 4052992 | +| train/ | | +| approx_kl | 2.6533227 | +| clip_fraction | 0.537 | +| clip_range | 0.2 | +| entropy_loss | -0.648 | +| explained_variance | -2.35 | +| learning_rate | 0.0001 | +| loss | -0.107 | +| n_updates | 100100 | +| policy_gradient_loss | -0.0843 | +| value_loss | 0.000342 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.13e+03 | +| ep_rew_mean | 0.113 | +| time/ | | +| fps | 310 | +| iterations | 3959 | +| time_elapsed | 13072 | +| total_timesteps | 4054016 | +| train/ | | +| approx_kl | 1.5831671 | +| clip_fraction | 0.504 | +| clip_range | 0.2 | +| entropy_loss | -0.531 | +| explained_variance | -1.5 | +| learning_rate | 0.0001 | +| loss | -0.115 | +| n_updates | 100110 | +| policy_gradient_loss | -0.0737 | +| value_loss | 0.000248 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.11e+03 | +| ep_rew_mean | 0.11 | +| time/ | | +| fps | 310 | +| iterations | 3960 | +| time_elapsed | 13075 | +| total_timesteps | 4055040 | +| train/ | | +| approx_kl | 1.6166048 | +| clip_fraction | 0.495 | +| clip_range | 0.2 | +| entropy_loss | -0.539 | +| explained_variance | -0.853 | +| learning_rate | 0.0001 | +| loss | -0.107 | +| n_updates | 100120 | +| policy_gradient_loss | -0.0675 | +| value_loss | 0.000736 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.11e+03 | +| ep_rew_mean | 0.11 | +| time/ | | +| fps | 310 | +| iterations | 3961 | +| time_elapsed | 13078 | +| total_timesteps | 4056064 | +| train/ | | +| approx_kl | 2.093978 | +| clip_fraction | 0.533 | +| clip_range | 0.2 | +| entropy_loss | -0.54 | +| explained_variance | -1.6 | +| learning_rate | 0.0001 | +| loss | -0.0781 | +| n_updates | 100130 | +| policy_gradient_loss | -0.0748 | +| value_loss | 0.000586 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.09e+03 | +| ep_rew_mean | 0.108 | +| time/ | | +| fps | 310 | +| iterations | 3962 | +| time_elapsed | 13082 | +| total_timesteps | 4057088 | +| train/ | | +| approx_kl | 1.3145084 | +| clip_fraction | 0.5 | +| clip_range | 0.2 | +| entropy_loss | -0.536 | +| explained_variance | -2.96 | +| learning_rate | 0.0001 | +| loss | -0.123 | +| n_updates | 100140 | +| policy_gradient_loss | -0.0675 | +| value_loss | 0.000144 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.08e+03 | +| ep_rew_mean | 0.108 | +| time/ | | +| fps | 310 | +| iterations | 3963 | +| time_elapsed | 13085 | +| total_timesteps | 4058112 | +| train/ | | +| approx_kl | 1.3078692 | +| clip_fraction | 0.529 | +| clip_range | 0.2 | +| entropy_loss | -0.515 | +| explained_variance | -0.559 | +| learning_rate | 0.0001 | +| loss | -0.0784 | +| n_updates | 100150 | +| policy_gradient_loss | -0.0764 | +| value_loss | 0.000337 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.06e+03 | +| ep_rew_mean | 0.104 | +| time/ | | +| fps | 310 | +| iterations | 3964 | +| time_elapsed | 13089 | +| total_timesteps | 4059136 | +| train/ | | +| approx_kl | 1.3307291 | +| clip_fraction | 0.478 | +| clip_range | 0.2 | +| entropy_loss | -0.493 | +| explained_variance | -0.989 | +| learning_rate | 0.0001 | +| loss | -0.0891 | +| n_updates | 100160 | +| policy_gradient_loss | -0.0667 | +| value_loss | 0.000666 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.06e+03 | +| ep_rew_mean | 0.104 | +| time/ | | +| fps | 310 | +| iterations | 3965 | +| time_elapsed | 13092 | +| total_timesteps | 4060160 | +| train/ | | +| approx_kl | 1.8452196 | +| clip_fraction | 0.516 | +| clip_range | 0.2 | +| entropy_loss | -0.592 | +| explained_variance | -1.8 | +| learning_rate | 0.0001 | +| loss | -0.0905 | +| n_updates | 100170 | +| policy_gradient_loss | -0.0709 | +| value_loss | 0.000556 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.06e+03 | +| ep_rew_mean | 0.104 | +| time/ | | +| fps | 310 | +| iterations | 3966 | +| time_elapsed | 13095 | +| total_timesteps | 4061184 | +| train/ | | +| approx_kl | 1.4274659 | +| clip_fraction | 0.543 | +| clip_range | 0.2 | +| entropy_loss | -0.543 | +| explained_variance | -2.07 | +| learning_rate | 0.0001 | +| loss | -0.0935 | +| n_updates | 100180 | +| policy_gradient_loss | -0.0771 | +| value_loss | 0.00065 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.06e+03 | +| ep_rew_mean | 0.106 | +| time/ | | +| fps | 310 | +| iterations | 3967 | +| time_elapsed | 13098 | +| total_timesteps | 4062208 | +| train/ | | +| approx_kl | 545.12775 | +| clip_fraction | 0.489 | +| clip_range | 0.2 | +| entropy_loss | -0.522 | +| explained_variance | -1.28 | +| learning_rate | 0.0001 | +| loss | -0.0884 | +| n_updates | 100190 | +| policy_gradient_loss | -0.0682 | +| value_loss | 0.000338 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.06e+03 | +| ep_rew_mean | 0.106 | +| time/ | | +| fps | 310 | +| iterations | 3968 | +| time_elapsed | 13102 | +| total_timesteps | 4063232 | +| train/ | | +| approx_kl | 1.11697 | +| clip_fraction | 0.515 | +| clip_range | 0.2 | +| entropy_loss | -0.58 | +| explained_variance | -2.99 | +| learning_rate | 0.0001 | +| loss | -0.018 | +| n_updates | 100200 | +| policy_gradient_loss | -0.0707 | +| value_loss | 0.000649 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.05e+03 | +| ep_rew_mean | 0.104 | +| time/ | | +| fps | 310 | +| iterations | 3969 | +| time_elapsed | 13105 | +| total_timesteps | 4064256 | +| train/ | | +| approx_kl | 1.8673524 | +| clip_fraction | 0.532 | +| clip_range | 0.2 | +| entropy_loss | -0.551 | +| explained_variance | -2.26 | +| learning_rate | 0.0001 | +| loss | -0.0981 | +| n_updates | 100210 | +| policy_gradient_loss | -0.0781 | +| value_loss | 0.000444 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.03e+03 | +| ep_rew_mean | 0.102 | +| time/ | | +| fps | 310 | +| iterations | 3970 | +| time_elapsed | 13108 | +| total_timesteps | 4065280 | +| train/ | | +| approx_kl | 2.1411226 | +| clip_fraction | 0.519 | +| clip_range | 0.2 | +| entropy_loss | -0.568 | +| explained_variance | -0.473 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 100220 | +| policy_gradient_loss | -0.0764 | +| value_loss | 0.000379 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.02e+03 | +| ep_rew_mean | 0.0956 | +| time/ | | +| fps | 310 | +| iterations | 3971 | +| time_elapsed | 13111 | +| total_timesteps | 4066304 | +| train/ | | +| approx_kl | 1.9583998 | +| clip_fraction | 0.509 | +| clip_range | 0.2 | +| entropy_loss | -0.561 | +| explained_variance | -3.17 | +| learning_rate | 0.0001 | +| loss | -0.117 | +| n_updates | 100230 | +| policy_gradient_loss | -0.0779 | +| value_loss | 0.000412 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.01e+03 | +| ep_rew_mean | 0.0921 | +| time/ | | +| fps | 310 | +| iterations | 3972 | +| time_elapsed | 13114 | +| total_timesteps | 4067328 | +| train/ | | +| approx_kl | 1.4235909 | +| clip_fraction | 0.457 | +| clip_range | 0.2 | +| entropy_loss | -0.51 | +| explained_variance | -0.842 | +| learning_rate | 0.0001 | +| loss | -0.0815 | +| n_updates | 100240 | +| policy_gradient_loss | -0.0688 | +| value_loss | 0.000339 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.99e+03 | +| ep_rew_mean | 0.085 | +| time/ | | +| fps | 310 | +| iterations | 3973 | +| time_elapsed | 13118 | +| total_timesteps | 4068352 | +| train/ | | +| approx_kl | 1.9880068 | +| clip_fraction | 0.493 | +| clip_range | 0.2 | +| entropy_loss | -0.472 | +| explained_variance | -1.41 | +| learning_rate | 0.0001 | +| loss | -0.106 | +| n_updates | 100250 | +| policy_gradient_loss | -0.0679 | +| value_loss | 0.000475 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.99e+03 | +| ep_rew_mean | 0.085 | +| time/ | | +| fps | 310 | +| iterations | 3974 | +| time_elapsed | 13121 | +| total_timesteps | 4069376 | +| train/ | | +| approx_kl | 1.7609499 | +| clip_fraction | 0.486 | +| clip_range | 0.2 | +| entropy_loss | -0.547 | +| explained_variance | -1.88 | +| learning_rate | 0.0001 | +| loss | -0.113 | +| n_updates | 100260 | +| policy_gradient_loss | -0.0691 | +| value_loss | 0.000696 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.97e+03 | +| ep_rew_mean | 0.0807 | +| time/ | | +| fps | 310 | +| iterations | 3975 | +| time_elapsed | 13124 | +| total_timesteps | 4070400 | +| train/ | | +| approx_kl | 1.7400708 | +| clip_fraction | 0.539 | +| clip_range | 0.2 | +| entropy_loss | -0.614 | +| explained_variance | -2.68 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 100270 | +| policy_gradient_loss | -0.0739 | +| value_loss | 0.00028 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.95e+03 | +| ep_rew_mean | 0.0787 | +| time/ | | +| fps | 310 | +| iterations | 3976 | +| time_elapsed | 13128 | +| total_timesteps | 4071424 | +| train/ | | +| approx_kl | 1.429141 | +| clip_fraction | 0.497 | +| clip_range | 0.2 | +| entropy_loss | -0.502 | +| explained_variance | -2.15 | +| learning_rate | 0.0001 | +| loss | -0.0992 | +| n_updates | 100280 | +| policy_gradient_loss | -0.0674 | +| value_loss | 0.00026 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.95e+03 | +| ep_rew_mean | 0.079 | +| time/ | | +| fps | 310 | +| iterations | 3977 | +| time_elapsed | 13131 | +| total_timesteps | 4072448 | +| train/ | | +| approx_kl | 1.3580847 | +| clip_fraction | 0.509 | +| clip_range | 0.2 | +| entropy_loss | -0.53 | +| explained_variance | -1.55 | +| learning_rate | 0.0001 | +| loss | -0.0875 | +| n_updates | 100290 | +| policy_gradient_loss | -0.0725 | +| value_loss | 0.000276 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.95e+03 | +| ep_rew_mean | 0.079 | +| time/ | | +| fps | 310 | +| iterations | 3978 | +| time_elapsed | 13134 | +| total_timesteps | 4073472 | +| train/ | | +| approx_kl | 1.2823988 | +| clip_fraction | 0.489 | +| clip_range | 0.2 | +| entropy_loss | -0.496 | +| explained_variance | -1.19 | +| learning_rate | 0.0001 | +| loss | -0.0887 | +| n_updates | 100300 | +| policy_gradient_loss | -0.0685 | +| value_loss | 0.000464 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.93e+03 | +| ep_rew_mean | 0.079 | +| time/ | | +| fps | 310 | +| iterations | 3979 | +| time_elapsed | 13138 | +| total_timesteps | 4074496 | +| train/ | | +| approx_kl | 1.868327 | +| clip_fraction | 0.478 | +| clip_range | 0.2 | +| entropy_loss | -0.497 | +| explained_variance | -2.45 | +| learning_rate | 0.0001 | +| loss | -0.0897 | +| n_updates | 100310 | +| policy_gradient_loss | -0.0668 | +| value_loss | 0.000519 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.92e+03 | +| ep_rew_mean | 0.0768 | +| time/ | | +| fps | 310 | +| iterations | 3980 | +| time_elapsed | 13141 | +| total_timesteps | 4075520 | +| train/ | | +| approx_kl | 1.3668736 | +| clip_fraction | 0.459 | +| clip_range | 0.2 | +| entropy_loss | -0.489 | +| explained_variance | -2.95 | +| learning_rate | 0.0001 | +| loss | -0.0671 | +| n_updates | 100320 | +| policy_gradient_loss | -0.0599 | +| value_loss | 0.000365 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.9e+03 | +| ep_rew_mean | 0.0718 | +| time/ | | +| fps | 310 | +| iterations | 3981 | +| time_elapsed | 13144 | +| total_timesteps | 4076544 | +| train/ | | +| approx_kl | 1.031992 | +| clip_fraction | 0.504 | +| clip_range | 0.2 | +| entropy_loss | -0.646 | +| explained_variance | -0.789 | +| learning_rate | 0.0001 | +| loss | -0.108 | +| n_updates | 100330 | +| policy_gradient_loss | -0.0685 | +| value_loss | 0.000391 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.89e+03 | +| ep_rew_mean | 0.0672 | +| time/ | | +| fps | 310 | +| iterations | 3982 | +| time_elapsed | 13148 | +| total_timesteps | 4077568 | +| train/ | | +| approx_kl | 1.5287874 | +| clip_fraction | 0.492 | +| clip_range | 0.2 | +| entropy_loss | -0.566 | +| explained_variance | -1.36 | +| learning_rate | 0.0001 | +| loss | -0.0999 | +| n_updates | 100340 | +| policy_gradient_loss | -0.0716 | +| value_loss | 0.000165 | +--------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.0659 | +| time/ | | +| fps | 310 | +| iterations | 3983 | +| time_elapsed | 13151 | +| total_timesteps | 4078592 | +| train/ | | +| approx_kl | 0.88175493 | +| clip_fraction | 0.461 | +| clip_range | 0.2 | +| entropy_loss | -0.527 | +| explained_variance | -0.371 | +| learning_rate | 0.0001 | +| loss | -0.0766 | +| n_updates | 100350 | +| policy_gradient_loss | -0.0551 | +| value_loss | 0.000371 | +---------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.063 | +| time/ | | +| fps | 310 | +| iterations | 3984 | +| time_elapsed | 13154 | +| total_timesteps | 4079616 | +| train/ | | +| approx_kl | 1.2840428 | +| clip_fraction | 0.489 | +| clip_range | 0.2 | +| entropy_loss | -0.541 | +| explained_variance | -2.13 | +| learning_rate | 0.0001 | +| loss | -0.11 | +| n_updates | 100360 | +| policy_gradient_loss | -0.0692 | +| value_loss | 0.000808 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.0601 | +| time/ | | +| fps | 310 | +| iterations | 3985 | +| time_elapsed | 13157 | +| total_timesteps | 4080640 | +| train/ | | +| approx_kl | 1.2326375 | +| clip_fraction | 0.49 | +| clip_range | 0.2 | +| entropy_loss | -0.495 | +| explained_variance | -1.88 | +| learning_rate | 0.0001 | +| loss | -0.0918 | +| n_updates | 100370 | +| policy_gradient_loss | -0.0629 | +| value_loss | 0.00065 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.0536 | +| time/ | | +| fps | 310 | +| iterations | 3986 | +| time_elapsed | 13160 | +| total_timesteps | 4081664 | +| train/ | | +| approx_kl | 3.0171084 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.536 | +| explained_variance | -2.3 | +| learning_rate | 0.0001 | +| loss | -0.0773 | +| n_updates | 100380 | +| policy_gradient_loss | -0.0685 | +| value_loss | 0.000444 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.82e+03 | +| ep_rew_mean | 0.0484 | +| time/ | | +| fps | 310 | +| iterations | 3987 | +| time_elapsed | 13163 | +| total_timesteps | 4082688 | +| train/ | | +| approx_kl | 1.4617649 | +| clip_fraction | 0.478 | +| clip_range | 0.2 | +| entropy_loss | -0.507 | +| explained_variance | -1.77 | +| learning_rate | 0.0001 | +| loss | -0.0939 | +| n_updates | 100390 | +| policy_gradient_loss | -0.062 | +| value_loss | 0.000508 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.81e+03 | +| ep_rew_mean | 0.0475 | +| time/ | | +| fps | 310 | +| iterations | 3988 | +| time_elapsed | 13166 | +| total_timesteps | 4083712 | +| train/ | | +| approx_kl | 1.6953936 | +| clip_fraction | 0.494 | +| clip_range | 0.2 | +| entropy_loss | -0.484 | +| explained_variance | -1.14 | +| learning_rate | 0.0001 | +| loss | -0.0928 | +| n_updates | 100400 | +| policy_gradient_loss | -0.067 | +| value_loss | 0.000753 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.81e+03 | +| ep_rew_mean | 0.0475 | +| time/ | | +| fps | 310 | +| iterations | 3989 | +| time_elapsed | 13170 | +| total_timesteps | 4084736 | +| train/ | | +| approx_kl | 1.4953637 | +| clip_fraction | 0.485 | +| clip_range | 0.2 | +| entropy_loss | -0.508 | +| explained_variance | -4.47 | +| learning_rate | 0.0001 | +| loss | -0.0968 | +| n_updates | 100410 | +| policy_gradient_loss | -0.0714 | +| value_loss | 0.000344 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.8e+03 | +| ep_rew_mean | 0.0422 | +| time/ | | +| fps | 310 | +| iterations | 3990 | +| time_elapsed | 13173 | +| total_timesteps | 4085760 | +| train/ | | +| approx_kl | 1.4677517 | +| clip_fraction | 0.485 | +| clip_range | 0.2 | +| entropy_loss | -0.536 | +| explained_variance | -3.56 | +| learning_rate | 0.0001 | +| loss | -0.123 | +| n_updates | 100420 | +| policy_gradient_loss | -0.0718 | +| value_loss | 0.000155 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.0415 | +| time/ | | +| fps | 310 | +| iterations | 3991 | +| time_elapsed | 13176 | +| total_timesteps | 4086784 | +| train/ | | +| approx_kl | 3.5726938 | +| clip_fraction | 0.497 | +| clip_range | 0.2 | +| entropy_loss | -0.562 | +| explained_variance | -0.302 | +| learning_rate | 0.0001 | +| loss | -0.082 | +| n_updates | 100430 | +| policy_gradient_loss | -0.0597 | +| value_loss | 0.000525 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.0379 | +| time/ | | +| fps | 310 | +| iterations | 3992 | +| time_elapsed | 13179 | +| total_timesteps | 4087808 | +| train/ | | +| approx_kl | 1.4137466 | +| clip_fraction | 0.506 | +| clip_range | 0.2 | +| entropy_loss | -0.549 | +| explained_variance | -4.79 | +| learning_rate | 0.0001 | +| loss | -0.0626 | +| n_updates | 100440 | +| policy_gradient_loss | -0.0601 | +| value_loss | 0.000464 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.0336 | +| time/ | | +| fps | 310 | +| iterations | 3993 | +| time_elapsed | 13183 | +| total_timesteps | 4088832 | +| train/ | | +| approx_kl | 1.2253208 | +| clip_fraction | 0.499 | +| clip_range | 0.2 | +| entropy_loss | -0.515 | +| explained_variance | -1.21 | +| learning_rate | 0.0001 | +| loss | -0.0735 | +| n_updates | 100450 | +| policy_gradient_loss | -0.0689 | +| value_loss | 0.000515 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.0297 | +| time/ | | +| fps | 310 | +| iterations | 3994 | +| time_elapsed | 13186 | +| total_timesteps | 4089856 | +| train/ | | +| approx_kl | 2.2164445 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.406 | +| explained_variance | -2.66 | +| learning_rate | 0.0001 | +| loss | -0.0555 | +| n_updates | 100460 | +| policy_gradient_loss | -0.0614 | +| value_loss | 0.000363 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.0297 | +| time/ | | +| fps | 310 | +| iterations | 3995 | +| time_elapsed | 13190 | +| total_timesteps | 4090880 | +| train/ | | +| approx_kl | 1.3765556 | +| clip_fraction | 0.488 | +| clip_range | 0.2 | +| entropy_loss | -0.515 | +| explained_variance | -1.17 | +| learning_rate | 0.0001 | +| loss | -0.115 | +| n_updates | 100470 | +| policy_gradient_loss | -0.0632 | +| value_loss | 0.000395 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.0297 | +| time/ | | +| fps | 310 | +| iterations | 3996 | +| time_elapsed | 13193 | +| total_timesteps | 4091904 | +| train/ | | +| approx_kl | 2.5177755 | +| clip_fraction | 0.521 | +| clip_range | 0.2 | +| entropy_loss | -0.53 | +| explained_variance | -3.89 | +| learning_rate | 0.0001 | +| loss | -0.0806 | +| n_updates | 100480 | +| policy_gradient_loss | -0.0704 | +| value_loss | 0.000301 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.0251 | +| time/ | | +| fps | 310 | +| iterations | 3997 | +| time_elapsed | 13197 | +| total_timesteps | 4092928 | +| train/ | | +| approx_kl | 1.6805259 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.57 | +| explained_variance | -2.34 | +| learning_rate | 0.0001 | +| loss | -0.0904 | +| n_updates | 100490 | +| policy_gradient_loss | -0.0629 | +| value_loss | 0.000199 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.0251 | +| time/ | | +| fps | 310 | +| iterations | 3998 | +| time_elapsed | 13200 | +| total_timesteps | 4093952 | +| train/ | | +| approx_kl | 1.182044 | +| clip_fraction | 0.495 | +| clip_range | 0.2 | +| entropy_loss | -0.513 | +| explained_variance | -1.21 | +| learning_rate | 0.0001 | +| loss | -0.111 | +| n_updates | 100500 | +| policy_gradient_loss | -0.063 | +| value_loss | 0.000278 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.0243 | +| time/ | | +| fps | 310 | +| iterations | 3999 | +| time_elapsed | 13204 | +| total_timesteps | 4094976 | +| train/ | | +| approx_kl | 1.7884758 | +| clip_fraction | 0.528 | +| clip_range | 0.2 | +| entropy_loss | -0.591 | +| explained_variance | -0.898 | +| learning_rate | 0.0001 | +| loss | -0.113 | +| n_updates | 100510 | +| policy_gradient_loss | -0.0711 | +| value_loss | 0.000509 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.0243 | +| time/ | | +| fps | 310 | +| iterations | 4000 | +| time_elapsed | 13207 | +| total_timesteps | 4096000 | +| train/ | | +| approx_kl | 1.2782416 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.492 | +| explained_variance | -6.36 | +| learning_rate | 0.0001 | +| loss | -0.0677 | +| n_updates | 100520 | +| policy_gradient_loss | -0.0626 | +| value_loss | 0.000745 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.0223 | +| time/ | | +| fps | 310 | +| iterations | 4001 | +| time_elapsed | 13210 | +| total_timesteps | 4097024 | +| train/ | | +| approx_kl | 1.399431 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.575 | +| explained_variance | -1.26 | +| learning_rate | 0.0001 | +| loss | -0.0954 | +| n_updates | 100530 | +| policy_gradient_loss | -0.0658 | +| value_loss | 0.000299 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.0147 | +| time/ | | +| fps | 310 | +| iterations | 4002 | +| time_elapsed | 13214 | +| total_timesteps | 4098048 | +| train/ | | +| approx_kl | 2.2174716 | +| clip_fraction | 0.45 | +| clip_range | 0.2 | +| entropy_loss | -0.45 | +| explained_variance | -2.68 | +| learning_rate | 0.0001 | +| loss | -0.0962 | +| n_updates | 100540 | +| policy_gradient_loss | -0.0676 | +| value_loss | 0.00031 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | 0.0133 | +| time/ | | +| fps | 310 | +| iterations | 4003 | +| time_elapsed | 13217 | +| total_timesteps | 4099072 | +| train/ | | +| approx_kl | 1.5585722 | +| clip_fraction | 0.448 | +| clip_range | 0.2 | +| entropy_loss | -0.455 | +| explained_variance | -1.61 | +| learning_rate | 0.0001 | +| loss | -0.0773 | +| n_updates | 100550 | +| policy_gradient_loss | -0.0596 | +| value_loss | 0.00077 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.64e+03 | +| ep_rew_mean | 0.00808 | +| time/ | | +| fps | 310 | +| iterations | 4004 | +| time_elapsed | 13220 | +| total_timesteps | 4100096 | +| train/ | | +| approx_kl | 1.5610311 | +| clip_fraction | 0.461 | +| clip_range | 0.2 | +| entropy_loss | -0.501 | +| explained_variance | -4.92 | +| learning_rate | 0.0001 | +| loss | -0.0815 | +| n_updates | 100560 | +| policy_gradient_loss | -0.0602 | +| value_loss | 0.000603 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.62e+03 | +| ep_rew_mean | 0.00321 | +| time/ | | +| fps | 310 | +| iterations | 4005 | +| time_elapsed | 13223 | +| total_timesteps | 4101120 | +| train/ | | +| approx_kl | 1.4770908 | +| clip_fraction | 0.494 | +| clip_range | 0.2 | +| entropy_loss | -0.499 | +| explained_variance | -1.63 | +| learning_rate | 0.0001 | +| loss | -0.0998 | +| n_updates | 100570 | +| policy_gradient_loss | -0.0629 | +| value_loss | 0.00065 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.62e+03 | +| ep_rew_mean | 0.00321 | +| time/ | | +| fps | 310 | +| iterations | 4006 | +| time_elapsed | 13226 | +| total_timesteps | 4102144 | +| train/ | | +| approx_kl | 2.1211195 | +| clip_fraction | 0.499 | +| clip_range | 0.2 | +| entropy_loss | -0.383 | +| explained_variance | -1.42 | +| learning_rate | 0.0001 | +| loss | -0.0866 | +| n_updates | 100580 | +| policy_gradient_loss | -0.0729 | +| value_loss | 0.000487 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.62e+03 | +| ep_rew_mean | 0.00462 | +| time/ | | +| fps | 310 | +| iterations | 4007 | +| time_elapsed | 13230 | +| total_timesteps | 4103168 | +| train/ | | +| approx_kl | 24.591919 | +| clip_fraction | 0.506 | +| clip_range | 0.2 | +| entropy_loss | -0.476 | +| explained_variance | -0.887 | +| learning_rate | 0.0001 | +| loss | -0.0931 | +| n_updates | 100590 | +| policy_gradient_loss | -0.072 | +| value_loss | 0.000523 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.61e+03 | +| ep_rew_mean | 0.00315 | +| time/ | | +| fps | 310 | +| iterations | 4008 | +| time_elapsed | 13233 | +| total_timesteps | 4104192 | +| train/ | | +| approx_kl | 1.9410905 | +| clip_fraction | 0.485 | +| clip_range | 0.2 | +| entropy_loss | -0.431 | +| explained_variance | -2.74 | +| learning_rate | 0.0001 | +| loss | -0.0965 | +| n_updates | 100600 | +| policy_gradient_loss | -0.0756 | +| value_loss | 0.000543 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.61e+03 | +| ep_rew_mean | 0.00315 | +| time/ | | +| fps | 310 | +| iterations | 4009 | +| time_elapsed | 13236 | +| total_timesteps | 4105216 | +| train/ | | +| approx_kl | 2.1109996 | +| clip_fraction | 0.504 | +| clip_range | 0.2 | +| entropy_loss | -0.471 | +| explained_variance | -1.47 | +| learning_rate | 0.0001 | +| loss | -0.109 | +| n_updates | 100610 | +| policy_gradient_loss | -0.0706 | +| value_loss | 0.000404 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | 0.00235 | +| time/ | | +| fps | 310 | +| iterations | 4010 | +| time_elapsed | 13239 | +| total_timesteps | 4106240 | +| train/ | | +| approx_kl | 7.2515645 | +| clip_fraction | 0.515 | +| clip_range | 0.2 | +| entropy_loss | -0.476 | +| explained_variance | -0.779 | +| learning_rate | 0.0001 | +| loss | -0.0991 | +| n_updates | 100620 | +| policy_gradient_loss | -0.06 | +| value_loss | 0.000396 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | 0.00235 | +| time/ | | +| fps | 310 | +| iterations | 4011 | +| time_elapsed | 13243 | +| total_timesteps | 4107264 | +| train/ | | +| approx_kl | 1.6043054 | +| clip_fraction | 0.497 | +| clip_range | 0.2 | +| entropy_loss | -0.462 | +| explained_variance | -1.44 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 100630 | +| policy_gradient_loss | -0.0624 | +| value_loss | 0.000435 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | -0.000218 | +| time/ | | +| fps | 310 | +| iterations | 4012 | +| time_elapsed | 13247 | +| total_timesteps | 4108288 | +| train/ | | +| approx_kl | 1.8733615 | +| clip_fraction | 0.496 | +| clip_range | 0.2 | +| entropy_loss | -0.455 | +| explained_variance | -1.35 | +| learning_rate | 0.0001 | +| loss | -0.0608 | +| n_updates | 100640 | +| policy_gradient_loss | -0.0538 | +| value_loss | 0.000558 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.57e+03 | +| ep_rew_mean | -0.00238 | +| time/ | | +| fps | 310 | +| iterations | 4013 | +| time_elapsed | 13250 | +| total_timesteps | 4109312 | +| train/ | | +| approx_kl | 2.1302483 | +| clip_fraction | 0.509 | +| clip_range | 0.2 | +| entropy_loss | -0.483 | +| explained_variance | -1.04 | +| learning_rate | 0.0001 | +| loss | -0.0896 | +| n_updates | 100650 | +| policy_gradient_loss | -0.0706 | +| value_loss | 0.00043 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.55e+03 | +| ep_rew_mean | -0.00301 | +| time/ | | +| fps | 310 | +| iterations | 4014 | +| time_elapsed | 13254 | +| total_timesteps | 4110336 | +| train/ | | +| approx_kl | 1.8102343 | +| clip_fraction | 0.476 | +| clip_range | 0.2 | +| entropy_loss | -0.459 | +| explained_variance | -2.72 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 100660 | +| policy_gradient_loss | -0.0713 | +| value_loss | 0.000259 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.55e+03 | +| ep_rew_mean | -0.00301 | +| time/ | | +| fps | 310 | +| iterations | 4015 | +| time_elapsed | 13257 | +| total_timesteps | 4111360 | +| train/ | | +| approx_kl | 2.0502396 | +| clip_fraction | 0.496 | +| clip_range | 0.2 | +| entropy_loss | -0.472 | +| explained_variance | -0.553 | +| learning_rate | 0.0001 | +| loss | -0.0404 | +| n_updates | 100670 | +| policy_gradient_loss | -0.0545 | +| value_loss | 0.000401 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.55e+03 | +| ep_rew_mean | -0.00301 | +| time/ | | +| fps | 310 | +| iterations | 4016 | +| time_elapsed | 13261 | +| total_timesteps | 4112384 | +| train/ | | +| approx_kl | 1.5518718 | +| clip_fraction | 0.5 | +| clip_range | 0.2 | +| entropy_loss | -0.482 | +| explained_variance | -3.5 | +| learning_rate | 0.0001 | +| loss | -0.081 | +| n_updates | 100680 | +| policy_gradient_loss | -0.0664 | +| value_loss | 0.000501 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.56e+03 | +| ep_rew_mean | -0.00593 | +| time/ | | +| fps | 310 | +| iterations | 4017 | +| time_elapsed | 13264 | +| total_timesteps | 4113408 | +| train/ | | +| approx_kl | 1.5330324 | +| clip_fraction | 0.49 | +| clip_range | 0.2 | +| entropy_loss | -0.503 | +| explained_variance | -3.44 | +| learning_rate | 0.0001 | +| loss | -0.0968 | +| n_updates | 100690 | +| policy_gradient_loss | -0.0718 | +| value_loss | 0.000387 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.55e+03 | +| ep_rew_mean | -0.00528 | +| time/ | | +| fps | 310 | +| iterations | 4018 | +| time_elapsed | 13268 | +| total_timesteps | 4114432 | +| train/ | | +| approx_kl | 1.7967813 | +| clip_fraction | 0.466 | +| clip_range | 0.2 | +| entropy_loss | -0.441 | +| explained_variance | -1.89 | +| learning_rate | 0.0001 | +| loss | -0.073 | +| n_updates | 100700 | +| policy_gradient_loss | -0.0691 | +| value_loss | 0.000347 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.5e+03 | +| ep_rew_mean | -0.00836 | +| time/ | | +| fps | 310 | +| iterations | 4019 | +| time_elapsed | 13271 | +| total_timesteps | 4115456 | +| train/ | | +| approx_kl | 2.160317 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.433 | +| explained_variance | -1.11 | +| learning_rate | 0.0001 | +| loss | -0.0699 | +| n_updates | 100710 | +| policy_gradient_loss | -0.0648 | +| value_loss | 0.00056 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.5e+03 | +| ep_rew_mean | -0.00836 | +| time/ | | +| fps | 310 | +| iterations | 4020 | +| time_elapsed | 13274 | +| total_timesteps | 4116480 | +| train/ | | +| approx_kl | 1.7060443 | +| clip_fraction | 0.463 | +| clip_range | 0.2 | +| entropy_loss | -0.404 | +| explained_variance | -0.736 | +| learning_rate | 0.0001 | +| loss | -0.0784 | +| n_updates | 100720 | +| policy_gradient_loss | -0.0664 | +| value_loss | 0.000618 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.49e+03 | +| ep_rew_mean | -0.00861 | +| time/ | | +| fps | 310 | +| iterations | 4021 | +| time_elapsed | 13277 | +| total_timesteps | 4117504 | +| train/ | | +| approx_kl | 2.3858876 | +| clip_fraction | 0.5 | +| clip_range | 0.2 | +| entropy_loss | -0.428 | +| explained_variance | -2.21 | +| learning_rate | 0.0001 | +| loss | -0.0882 | +| n_updates | 100730 | +| policy_gradient_loss | -0.0679 | +| value_loss | 0.000529 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.49e+03 | +| ep_rew_mean | -0.0111 | +| time/ | | +| fps | 310 | +| iterations | 4022 | +| time_elapsed | 13281 | +| total_timesteps | 4118528 | +| train/ | | +| approx_kl | 1.5544657 | +| clip_fraction | 0.493 | +| clip_range | 0.2 | +| entropy_loss | -0.485 | +| explained_variance | -2.04 | +| learning_rate | 0.0001 | +| loss | -0.113 | +| n_updates | 100740 | +| policy_gradient_loss | -0.0641 | +| value_loss | 0.000473 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.49e+03 | +| ep_rew_mean | -0.0111 | +| time/ | | +| fps | 310 | +| iterations | 4023 | +| time_elapsed | 13284 | +| total_timesteps | 4119552 | +| train/ | | +| approx_kl | 1.9888955 | +| clip_fraction | 0.51 | +| clip_range | 0.2 | +| entropy_loss | -0.439 | +| explained_variance | -1.56 | +| learning_rate | 0.0001 | +| loss | -0.078 | +| n_updates | 100750 | +| policy_gradient_loss | -0.0706 | +| value_loss | 0.000464 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.47e+03 | +| ep_rew_mean | -0.0113 | +| time/ | | +| fps | 310 | +| iterations | 4024 | +| time_elapsed | 13287 | +| total_timesteps | 4120576 | +| train/ | | +| approx_kl | 1.9140725 | +| clip_fraction | 0.505 | +| clip_range | 0.2 | +| entropy_loss | -0.502 | +| explained_variance | -1.66 | +| learning_rate | 0.0001 | +| loss | -0.118 | +| n_updates | 100760 | +| policy_gradient_loss | -0.0672 | +| value_loss | 0.000294 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.46e+03 | +| ep_rew_mean | -0.0135 | +| time/ | | +| fps | 310 | +| iterations | 4025 | +| time_elapsed | 13290 | +| total_timesteps | 4121600 | +| train/ | | +| approx_kl | 1.4859979 | +| clip_fraction | 0.453 | +| clip_range | 0.2 | +| entropy_loss | -0.403 | +| explained_variance | -2.1 | +| learning_rate | 0.0001 | +| loss | -0.0953 | +| n_updates | 100770 | +| policy_gradient_loss | -0.0655 | +| value_loss | 0.000384 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.46e+03 | +| ep_rew_mean | -0.0135 | +| time/ | | +| fps | 310 | +| iterations | 4026 | +| time_elapsed | 13293 | +| total_timesteps | 4122624 | +| train/ | | +| approx_kl | 1.5743525 | +| clip_fraction | 0.476 | +| clip_range | 0.2 | +| entropy_loss | -0.442 | +| explained_variance | -0.768 | +| learning_rate | 0.0001 | +| loss | -0.0643 | +| n_updates | 100780 | +| policy_gradient_loss | -0.0703 | +| value_loss | 0.00028 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.46e+03 | +| ep_rew_mean | -0.0135 | +| time/ | | +| fps | 310 | +| iterations | 4027 | +| time_elapsed | 13296 | +| total_timesteps | 4123648 | +| train/ | | +| approx_kl | 1.9906259 | +| clip_fraction | 0.506 | +| clip_range | 0.2 | +| entropy_loss | -0.466 | +| explained_variance | -0.477 | +| learning_rate | 0.0001 | +| loss | -0.0897 | +| n_updates | 100790 | +| policy_gradient_loss | -0.0707 | +| value_loss | 0.000446 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.45e+03 | +| ep_rew_mean | -0.0214 | +| time/ | | +| fps | 310 | +| iterations | 4028 | +| time_elapsed | 13300 | +| total_timesteps | 4124672 | +| train/ | | +| approx_kl | 1.8987474 | +| clip_fraction | 0.514 | +| clip_range | 0.2 | +| entropy_loss | -0.527 | +| explained_variance | -2.12 | +| learning_rate | 0.0001 | +| loss | -0.1 | +| n_updates | 100800 | +| policy_gradient_loss | -0.0715 | +| value_loss | 0.000424 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.45e+03 | +| ep_rew_mean | -0.0214 | +| time/ | | +| fps | 310 | +| iterations | 4029 | +| time_elapsed | 13303 | +| total_timesteps | 4125696 | +| train/ | | +| approx_kl | 1.9206729 | +| clip_fraction | 0.452 | +| clip_range | 0.2 | +| entropy_loss | -0.402 | +| explained_variance | -0.628 | +| learning_rate | 0.0001 | +| loss | -0.0869 | +| n_updates | 100810 | +| policy_gradient_loss | -0.0605 | +| value_loss | 0.000387 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.45e+03 | +| ep_rew_mean | -0.0214 | +| time/ | | +| fps | 310 | +| iterations | 4030 | +| time_elapsed | 13307 | +| total_timesteps | 4126720 | +| train/ | | +| approx_kl | 1.8420763 | +| clip_fraction | 0.458 | +| clip_range | 0.2 | +| entropy_loss | -0.432 | +| explained_variance | -2.39 | +| learning_rate | 0.0001 | +| loss | -0.0733 | +| n_updates | 100820 | +| policy_gradient_loss | -0.0646 | +| value_loss | 0.000385 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.45e+03 | +| ep_rew_mean | -0.0205 | +| time/ | | +| fps | 310 | +| iterations | 4031 | +| time_elapsed | 13310 | +| total_timesteps | 4127744 | +| train/ | | +| approx_kl | 1.8323982 | +| clip_fraction | 0.494 | +| clip_range | 0.2 | +| entropy_loss | -0.438 | +| explained_variance | -2.95 | +| learning_rate | 0.0001 | +| loss | -0.0979 | +| n_updates | 100830 | +| policy_gradient_loss | -0.0769 | +| value_loss | 0.00032 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.43e+03 | +| ep_rew_mean | -0.0228 | +| time/ | | +| fps | 310 | +| iterations | 4032 | +| time_elapsed | 13314 | +| total_timesteps | 4128768 | +| train/ | | +| approx_kl | 1.9607809 | +| clip_fraction | 0.484 | +| clip_range | 0.2 | +| entropy_loss | -0.469 | +| explained_variance | -1.48 | +| learning_rate | 0.0001 | +| loss | -0.105 | +| n_updates | 100840 | +| policy_gradient_loss | -0.0694 | +| value_loss | 0.000382 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | -0.0263 | +| time/ | | +| fps | 310 | +| iterations | 4033 | +| time_elapsed | 13317 | +| total_timesteps | 4129792 | +| train/ | | +| approx_kl | 1.4608243 | +| clip_fraction | 0.477 | +| clip_range | 0.2 | +| entropy_loss | -0.425 | +| explained_variance | -2.89 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 100850 | +| policy_gradient_loss | -0.0706 | +| value_loss | 0.000366 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | -0.0272 | +| time/ | | +| fps | 310 | +| iterations | 4034 | +| time_elapsed | 13320 | +| total_timesteps | 4130816 | +| train/ | | +| approx_kl | 1.5255749 | +| clip_fraction | 0.463 | +| clip_range | 0.2 | +| entropy_loss | -0.448 | +| explained_variance | -1.67 | +| learning_rate | 0.0001 | +| loss | -0.0922 | +| n_updates | 100860 | +| policy_gradient_loss | -0.065 | +| value_loss | 0.000393 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | -0.0256 | +| time/ | | +| fps | 310 | +| iterations | 4035 | +| time_elapsed | 13324 | +| total_timesteps | 4131840 | +| train/ | | +| approx_kl | 1.7170901 | +| clip_fraction | 0.479 | +| clip_range | 0.2 | +| entropy_loss | -0.417 | +| explained_variance | -2.46 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 100870 | +| policy_gradient_loss | -0.0687 | +| value_loss | 0.00064 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | -0.0272 | +| time/ | | +| fps | 310 | +| iterations | 4036 | +| time_elapsed | 13328 | +| total_timesteps | 4132864 | +| train/ | | +| approx_kl | 2.100006 | +| clip_fraction | 0.522 | +| clip_range | 0.2 | +| entropy_loss | -0.438 | +| explained_variance | -2.65 | +| learning_rate | 0.0001 | +| loss | -0.0933 | +| n_updates | 100880 | +| policy_gradient_loss | -0.0731 | +| value_loss | 0.000583 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | -0.0314 | +| time/ | | +| fps | 310 | +| iterations | 4037 | +| time_elapsed | 13331 | +| total_timesteps | 4133888 | +| train/ | | +| approx_kl | 2.8510933 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.428 | +| explained_variance | -1.48 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 100890 | +| policy_gradient_loss | -0.0636 | +| value_loss | 0.000663 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | -0.0314 | +| time/ | | +| fps | 310 | +| iterations | 4038 | +| time_elapsed | 13334 | +| total_timesteps | 4134912 | +| train/ | | +| approx_kl | 1.8599682 | +| clip_fraction | 0.446 | +| clip_range | 0.2 | +| entropy_loss | -0.347 | +| explained_variance | -1.11 | +| learning_rate | 0.0001 | +| loss | -0.0932 | +| n_updates | 100900 | +| policy_gradient_loss | -0.0611 | +| value_loss | 0.000615 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | -0.0347 | +| time/ | | +| fps | 310 | +| iterations | 4039 | +| time_elapsed | 13337 | +| total_timesteps | 4135936 | +| train/ | | +| approx_kl | 2.293406 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.391 | +| explained_variance | -1.05 | +| learning_rate | 0.0001 | +| loss | -0.13 | +| n_updates | 100910 | +| policy_gradient_loss | -0.0654 | +| value_loss | 0.000649 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | -0.0351 | +| time/ | | +| fps | 310 | +| iterations | 4040 | +| time_elapsed | 13341 | +| total_timesteps | 4136960 | +| train/ | | +| approx_kl | 2.0745492 | +| clip_fraction | 0.458 | +| clip_range | 0.2 | +| entropy_loss | -0.386 | +| explained_variance | -1.79 | +| learning_rate | 0.0001 | +| loss | -0.0896 | +| n_updates | 100920 | +| policy_gradient_loss | -0.0666 | +| value_loss | 0.000449 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | -0.0342 | +| time/ | | +| fps | 310 | +| iterations | 4041 | +| time_elapsed | 13344 | +| total_timesteps | 4137984 | +| train/ | | +| approx_kl | 2.7427702 | +| clip_fraction | 0.488 | +| clip_range | 0.2 | +| entropy_loss | -0.394 | +| explained_variance | -1.13 | +| learning_rate | 0.0001 | +| loss | -0.0981 | +| n_updates | 100930 | +| policy_gradient_loss | -0.0686 | +| value_loss | 0.000676 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | -0.0341 | +| time/ | | +| fps | 310 | +| iterations | 4042 | +| time_elapsed | 13347 | +| total_timesteps | 4139008 | +| train/ | | +| approx_kl | 1.9497035 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.385 | +| explained_variance | -2.57 | +| learning_rate | 0.0001 | +| loss | -0.0847 | +| n_updates | 100940 | +| policy_gradient_loss | -0.0731 | +| value_loss | 0.000541 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | -0.0341 | +| time/ | | +| fps | 310 | +| iterations | 4043 | +| time_elapsed | 13350 | +| total_timesteps | 4140032 | +| train/ | | +| approx_kl | 3.292009 | +| clip_fraction | 0.498 | +| clip_range | 0.2 | +| entropy_loss | -0.428 | +| explained_variance | -1.63 | +| learning_rate | 0.0001 | +| loss | -0.0762 | +| n_updates | 100950 | +| policy_gradient_loss | -0.0523 | +| value_loss | 0.000379 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | -0.0341 | +| time/ | | +| fps | 310 | +| iterations | 4044 | +| time_elapsed | 13354 | +| total_timesteps | 4141056 | +| train/ | | +| approx_kl | 2.2378802 | +| clip_fraction | 0.528 | +| clip_range | 0.2 | +| entropy_loss | -0.434 | +| explained_variance | -2.7 | +| learning_rate | 0.0001 | +| loss | -0.118 | +| n_updates | 100960 | +| policy_gradient_loss | -0.0803 | +| value_loss | 0.000467 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | -0.0305 | +| time/ | | +| fps | 310 | +| iterations | 4045 | +| time_elapsed | 13357 | +| total_timesteps | 4142080 | +| train/ | | +| approx_kl | 1.7320119 | +| clip_fraction | 0.502 | +| clip_range | 0.2 | +| entropy_loss | -0.45 | +| explained_variance | -2.99 | +| learning_rate | 0.0001 | +| loss | -0.0973 | +| n_updates | 100970 | +| policy_gradient_loss | -0.0743 | +| value_loss | 0.00045 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | -0.0305 | +| time/ | | +| fps | 310 | +| iterations | 4046 | +| time_elapsed | 13360 | +| total_timesteps | 4143104 | +| train/ | | +| approx_kl | 2.5678444 | +| clip_fraction | 0.515 | +| clip_range | 0.2 | +| entropy_loss | -0.437 | +| explained_variance | -1.52 | +| learning_rate | 0.0001 | +| loss | -0.0497 | +| n_updates | 100980 | +| policy_gradient_loss | -0.049 | +| value_loss | 0.000328 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | -0.0277 | +| time/ | | +| fps | 310 | +| iterations | 4047 | +| time_elapsed | 13363 | +| total_timesteps | 4144128 | +| train/ | | +| approx_kl | 2.222929 | +| clip_fraction | 0.515 | +| clip_range | 0.2 | +| entropy_loss | -0.454 | +| explained_variance | -0.512 | +| learning_rate | 0.0001 | +| loss | -0.0729 | +| n_updates | 100990 | +| policy_gradient_loss | -0.0603 | +| value_loss | 0.000518 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | -0.0277 | +| time/ | | +| fps | 310 | +| iterations | 4048 | +| time_elapsed | 13367 | +| total_timesteps | 4145152 | +| train/ | | +| approx_kl | 1.5840452 | +| clip_fraction | 0.463 | +| clip_range | 0.2 | +| entropy_loss | -0.415 | +| explained_variance | -1.17 | +| learning_rate | 0.0001 | +| loss | -0.0804 | +| n_updates | 101000 | +| policy_gradient_loss | -0.0629 | +| value_loss | 0.000483 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | -0.0281 | +| time/ | | +| fps | 310 | +| iterations | 4049 | +| time_elapsed | 13370 | +| total_timesteps | 4146176 | +| train/ | | +| approx_kl | 1.404038 | +| clip_fraction | 0.491 | +| clip_range | 0.2 | +| entropy_loss | -0.477 | +| explained_variance | -0.762 | +| learning_rate | 0.0001 | +| loss | -0.0998 | +| n_updates | 101010 | +| policy_gradient_loss | -0.0624 | +| value_loss | 0.000246 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | -0.0225 | +| time/ | | +| fps | 310 | +| iterations | 4050 | +| time_elapsed | 13374 | +| total_timesteps | 4147200 | +| train/ | | +| approx_kl | 1.3862472 | +| clip_fraction | 0.476 | +| clip_range | 0.2 | +| entropy_loss | -0.457 | +| explained_variance | -0.89 | +| learning_rate | 0.0001 | +| loss | -0.0689 | +| n_updates | 101020 | +| policy_gradient_loss | -0.0616 | +| value_loss | 0.000505 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | -0.0258 | +| time/ | | +| fps | 310 | +| iterations | 4051 | +| time_elapsed | 13377 | +| total_timesteps | 4148224 | +| train/ | | +| approx_kl | 1.6245971 | +| clip_fraction | 0.53 | +| clip_range | 0.2 | +| entropy_loss | -0.519 | +| explained_variance | -1.5 | +| learning_rate | 0.0001 | +| loss | -0.0816 | +| n_updates | 101030 | +| policy_gradient_loss | -0.0632 | +| value_loss | 0.000602 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | -0.0258 | +| time/ | | +| fps | 310 | +| iterations | 4052 | +| time_elapsed | 13380 | +| total_timesteps | 4149248 | +| train/ | | +| approx_kl | 1.7228346 | +| clip_fraction | 0.461 | +| clip_range | 0.2 | +| entropy_loss | -0.383 | +| explained_variance | -1.25 | +| learning_rate | 0.0001 | +| loss | -0.082 | +| n_updates | 101040 | +| policy_gradient_loss | -0.0641 | +| value_loss | 0.000552 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | -0.0291 | +| time/ | | +| fps | 310 | +| iterations | 4053 | +| time_elapsed | 13384 | +| total_timesteps | 4150272 | +| train/ | | +| approx_kl | 6.4180746 | +| clip_fraction | 0.498 | +| clip_range | 0.2 | +| entropy_loss | -0.449 | +| explained_variance | -1.5 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 101050 | +| policy_gradient_loss | -0.0711 | +| value_loss | 0.000407 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | -0.0245 | +| time/ | | +| fps | 310 | +| iterations | 4054 | +| time_elapsed | 13387 | +| total_timesteps | 4151296 | +| train/ | | +| approx_kl | 1.8733441 | +| clip_fraction | 0.496 | +| clip_range | 0.2 | +| entropy_loss | -0.405 | +| explained_variance | -0.759 | +| learning_rate | 0.0001 | +| loss | -0.0965 | +| n_updates | 101060 | +| policy_gradient_loss | -0.0675 | +| value_loss | 0.000508 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | -0.0245 | +| time/ | | +| fps | 310 | +| iterations | 4055 | +| time_elapsed | 13390 | +| total_timesteps | 4152320 | +| train/ | | +| approx_kl | 1.784575 | +| clip_fraction | 0.486 | +| clip_range | 0.2 | +| entropy_loss | -0.463 | +| explained_variance | -6.39 | +| learning_rate | 0.0001 | +| loss | -0.0889 | +| n_updates | 101070 | +| policy_gradient_loss | -0.0679 | +| value_loss | 0.000283 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | -0.0234 | +| time/ | | +| fps | 310 | +| iterations | 4056 | +| time_elapsed | 13393 | +| total_timesteps | 4153344 | +| train/ | | +| approx_kl | 2.6005676 | +| clip_fraction | 0.476 | +| clip_range | 0.2 | +| entropy_loss | -0.414 | +| explained_variance | -1.09 | +| learning_rate | 0.0001 | +| loss | -0.0624 | +| n_updates | 101080 | +| policy_gradient_loss | -0.0613 | +| value_loss | 0.000441 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | -0.0232 | +| time/ | | +| fps | 310 | +| iterations | 4057 | +| time_elapsed | 13397 | +| total_timesteps | 4154368 | +| train/ | | +| approx_kl | 1.885962 | +| clip_fraction | 0.474 | +| clip_range | 0.2 | +| entropy_loss | -0.436 | +| explained_variance | -0.737 | +| learning_rate | 0.0001 | +| loss | -0.041 | +| n_updates | 101090 | +| policy_gradient_loss | -0.0615 | +| value_loss | 0.00044 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | -0.0222 | +| time/ | | +| fps | 310 | +| iterations | 4058 | +| time_elapsed | 13400 | +| total_timesteps | 4155392 | +| train/ | | +| approx_kl | 1.8763195 | +| clip_fraction | 0.498 | +| clip_range | 0.2 | +| entropy_loss | -0.428 | +| explained_variance | -2.11 | +| learning_rate | 0.0001 | +| loss | -0.127 | +| n_updates | 101100 | +| policy_gradient_loss | -0.0741 | +| value_loss | 0.000255 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | -0.027 | +| time/ | | +| fps | 310 | +| iterations | 4059 | +| time_elapsed | 13403 | +| total_timesteps | 4156416 | +| train/ | | +| approx_kl | 2.0076385 | +| clip_fraction | 0.488 | +| clip_range | 0.2 | +| entropy_loss | -0.48 | +| explained_variance | -1.05 | +| learning_rate | 0.0001 | +| loss | -0.0695 | +| n_updates | 101110 | +| policy_gradient_loss | -0.0692 | +| value_loss | 0.000376 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | -0.027 | +| time/ | | +| fps | 310 | +| iterations | 4060 | +| time_elapsed | 13406 | +| total_timesteps | 4157440 | +| train/ | | +| approx_kl | 1.651483 | +| clip_fraction | 0.464 | +| clip_range | 0.2 | +| entropy_loss | -0.48 | +| explained_variance | -0.921 | +| learning_rate | 0.0001 | +| loss | -0.0728 | +| n_updates | 101120 | +| policy_gradient_loss | -0.0655 | +| value_loss | 0.000542 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | -0.0254 | +| time/ | | +| fps | 310 | +| iterations | 4061 | +| time_elapsed | 13409 | +| total_timesteps | 4158464 | +| train/ | | +| approx_kl | 1.8615423 | +| clip_fraction | 0.493 | +| clip_range | 0.2 | +| entropy_loss | -0.41 | +| explained_variance | -1.68 | +| learning_rate | 0.0001 | +| loss | -0.0904 | +| n_updates | 101130 | +| policy_gradient_loss | -0.0702 | +| value_loss | 0.000518 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | -0.0228 | +| time/ | | +| fps | 310 | +| iterations | 4062 | +| time_elapsed | 13412 | +| total_timesteps | 4159488 | +| train/ | | +| approx_kl | 1.85046 | +| clip_fraction | 0.472 | +| clip_range | 0.2 | +| entropy_loss | -0.458 | +| explained_variance | -3.43 | +| learning_rate | 0.0001 | +| loss | -0.067 | +| n_updates | 101140 | +| policy_gradient_loss | -0.0698 | +| value_loss | 0.000416 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | -0.0242 | +| time/ | | +| fps | 310 | +| iterations | 4063 | +| time_elapsed | 13416 | +| total_timesteps | 4160512 | +| train/ | | +| approx_kl | 2.0062587 | +| clip_fraction | 0.497 | +| clip_range | 0.2 | +| entropy_loss | -0.421 | +| explained_variance | -0.805 | +| learning_rate | 0.0001 | +| loss | -0.0584 | +| n_updates | 101150 | +| policy_gradient_loss | -0.0667 | +| value_loss | 0.00052 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | -0.0242 | +| time/ | | +| fps | 310 | +| iterations | 4064 | +| time_elapsed | 13419 | +| total_timesteps | 4161536 | +| train/ | | +| approx_kl | 1.3907465 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.487 | +| explained_variance | -1.59 | +| learning_rate | 0.0001 | +| loss | -0.052 | +| n_updates | 101160 | +| policy_gradient_loss | -0.0635 | +| value_loss | 0.000495 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | -0.0257 | +| time/ | | +| fps | 310 | +| iterations | 4065 | +| time_elapsed | 13422 | +| total_timesteps | 4162560 | +| train/ | | +| approx_kl | 1.8650723 | +| clip_fraction | 0.477 | +| clip_range | 0.2 | +| entropy_loss | -0.438 | +| explained_variance | -2.04 | +| learning_rate | 0.0001 | +| loss | -0.0703 | +| n_updates | 101170 | +| policy_gradient_loss | -0.0651 | +| value_loss | 0.000598 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | -0.0257 | +| time/ | | +| fps | 310 | +| iterations | 4066 | +| time_elapsed | 13426 | +| total_timesteps | 4163584 | +| train/ | | +| approx_kl | 1.9316089 | +| clip_fraction | 0.518 | +| clip_range | 0.2 | +| entropy_loss | -0.458 | +| explained_variance | -0.657 | +| learning_rate | 0.0001 | +| loss | -0.0723 | +| n_updates | 101180 | +| policy_gradient_loss | -0.0691 | +| value_loss | 0.000495 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | -0.021 | +| time/ | | +| fps | 310 | +| iterations | 4067 | +| time_elapsed | 13429 | +| total_timesteps | 4164608 | +| train/ | | +| approx_kl | 1.7547495 | +| clip_fraction | 0.505 | +| clip_range | 0.2 | +| entropy_loss | -0.427 | +| explained_variance | -5.42 | +| learning_rate | 0.0001 | +| loss | -0.0962 | +| n_updates | 101190 | +| policy_gradient_loss | -0.0748 | +| value_loss | 0.000687 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | -0.021 | +| time/ | | +| fps | 310 | +| iterations | 4068 | +| time_elapsed | 13433 | +| total_timesteps | 4165632 | +| train/ | | +| approx_kl | 1.8709687 | +| clip_fraction | 0.511 | +| clip_range | 0.2 | +| entropy_loss | -0.479 | +| explained_variance | -2.54 | +| learning_rate | 0.0001 | +| loss | -0.106 | +| n_updates | 101200 | +| policy_gradient_loss | -0.0757 | +| value_loss | 0.000327 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | -0.0206 | +| time/ | | +| fps | 310 | +| iterations | 4069 | +| time_elapsed | 13436 | +| total_timesteps | 4166656 | +| train/ | | +| approx_kl | 2.1236253 | +| clip_fraction | 0.486 | +| clip_range | 0.2 | +| entropy_loss | -0.438 | +| explained_variance | -0.647 | +| learning_rate | 0.0001 | +| loss | -0.0926 | +| n_updates | 101210 | +| policy_gradient_loss | -0.0643 | +| value_loss | 0.000253 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | -0.0205 | +| time/ | | +| fps | 310 | +| iterations | 4070 | +| time_elapsed | 13440 | +| total_timesteps | 4167680 | +| train/ | | +| approx_kl | 2.2369323 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.415 | +| explained_variance | -4.64 | +| learning_rate | 0.0001 | +| loss | -0.0924 | +| n_updates | 101220 | +| policy_gradient_loss | -0.0743 | +| value_loss | 0.000303 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | -0.019 | +| time/ | | +| fps | 310 | +| iterations | 4071 | +| time_elapsed | 13443 | +| total_timesteps | 4168704 | +| train/ | | +| approx_kl | 1.6098993 | +| clip_fraction | 0.496 | +| clip_range | 0.2 | +| entropy_loss | -0.45 | +| explained_variance | -2.85 | +| learning_rate | 0.0001 | +| loss | -0.0756 | +| n_updates | 101230 | +| policy_gradient_loss | -0.0657 | +| value_loss | 0.000639 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | -0.019 | +| time/ | | +| fps | 310 | +| iterations | 4072 | +| time_elapsed | 13447 | +| total_timesteps | 4169728 | +| train/ | | +| approx_kl | 1.5556253 | +| clip_fraction | 0.49 | +| clip_range | 0.2 | +| entropy_loss | -0.456 | +| explained_variance | -1.26 | +| learning_rate | 0.0001 | +| loss | -0.0823 | +| n_updates | 101240 | +| policy_gradient_loss | -0.0682 | +| value_loss | 0.000445 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | -0.019 | +| time/ | | +| fps | 310 | +| iterations | 4073 | +| time_elapsed | 13450 | +| total_timesteps | 4170752 | +| train/ | | +| approx_kl | 1.7959745 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.47 | +| explained_variance | -2.48 | +| learning_rate | 0.0001 | +| loss | -0.0826 | +| n_updates | 101250 | +| policy_gradient_loss | -0.0644 | +| value_loss | 0.000341 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | -0.0188 | +| time/ | | +| fps | 310 | +| iterations | 4074 | +| time_elapsed | 13453 | +| total_timesteps | 4171776 | +| train/ | | +| approx_kl | 1.8317788 | +| clip_fraction | 0.474 | +| clip_range | 0.2 | +| entropy_loss | -0.403 | +| explained_variance | -1.83 | +| learning_rate | 0.0001 | +| loss | -0.106 | +| n_updates | 101260 | +| policy_gradient_loss | -0.0672 | +| value_loss | 0.000353 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | -0.0188 | +| time/ | | +| fps | 310 | +| iterations | 4075 | +| time_elapsed | 13457 | +| total_timesteps | 4172800 | +| train/ | | +| approx_kl | 1.7040801 | +| clip_fraction | 0.458 | +| clip_range | 0.2 | +| entropy_loss | -0.393 | +| explained_variance | -2.96 | +| learning_rate | 0.0001 | +| loss | -0.0848 | +| n_updates | 101270 | +| policy_gradient_loss | -0.0627 | +| value_loss | 0.000711 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | -0.0156 | +| time/ | | +| fps | 310 | +| iterations | 4076 | +| time_elapsed | 13460 | +| total_timesteps | 4173824 | +| train/ | | +| approx_kl | 1.9269662 | +| clip_fraction | 0.484 | +| clip_range | 0.2 | +| entropy_loss | -0.444 | +| explained_variance | -1.47 | +| learning_rate | 0.0001 | +| loss | -0.0905 | +| n_updates | 101280 | +| policy_gradient_loss | -0.0745 | +| value_loss | 0.000753 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | -0.0118 | +| time/ | | +| fps | 310 | +| iterations | 4077 | +| time_elapsed | 13463 | +| total_timesteps | 4174848 | +| train/ | | +| approx_kl | 1.915591 | +| clip_fraction | 0.485 | +| clip_range | 0.2 | +| entropy_loss | -0.391 | +| explained_variance | -3.74 | +| learning_rate | 0.0001 | +| loss | -0.0908 | +| n_updates | 101290 | +| policy_gradient_loss | -0.0734 | +| value_loss | 0.00045 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | -0.011 | +| time/ | | +| fps | 310 | +| iterations | 4078 | +| time_elapsed | 13466 | +| total_timesteps | 4175872 | +| train/ | | +| approx_kl | 2.0601125 | +| clip_fraction | 0.467 | +| clip_range | 0.2 | +| entropy_loss | -0.363 | +| explained_variance | -2.78 | +| learning_rate | 0.0001 | +| loss | -0.109 | +| n_updates | 101300 | +| policy_gradient_loss | -0.0692 | +| value_loss | 0.000568 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | -0.0129 | +| time/ | | +| fps | 310 | +| iterations | 4079 | +| time_elapsed | 13469 | +| total_timesteps | 4176896 | +| train/ | | +| approx_kl | 2.0380707 | +| clip_fraction | 0.451 | +| clip_range | 0.2 | +| entropy_loss | -0.41 | +| explained_variance | -1.42 | +| learning_rate | 0.0001 | +| loss | -0.0864 | +| n_updates | 101310 | +| policy_gradient_loss | -0.067 | +| value_loss | 0.000611 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | -0.0129 | +| time/ | | +| fps | 310 | +| iterations | 4080 | +| time_elapsed | 13472 | +| total_timesteps | 4177920 | +| train/ | | +| approx_kl | 1.6386187 | +| clip_fraction | 0.47 | +| clip_range | 0.2 | +| entropy_loss | -0.415 | +| explained_variance | -1.78 | +| learning_rate | 0.0001 | +| loss | -0.074 | +| n_updates | 101320 | +| policy_gradient_loss | -0.0667 | +| value_loss | 0.000554 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | -0.0125 | +| time/ | | +| fps | 310 | +| iterations | 4081 | +| time_elapsed | 13476 | +| total_timesteps | 4178944 | +| train/ | | +| approx_kl | 1.7937479 | +| clip_fraction | 0.458 | +| clip_range | 0.2 | +| entropy_loss | -0.387 | +| explained_variance | -0.918 | +| learning_rate | 0.0001 | +| loss | -0.0969 | +| n_updates | 101330 | +| policy_gradient_loss | -0.0661 | +| value_loss | 0.000569 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | -0.0125 | +| time/ | | +| fps | 310 | +| iterations | 4082 | +| time_elapsed | 13479 | +| total_timesteps | 4179968 | +| train/ | | +| approx_kl | 1.6848482 | +| clip_fraction | 0.474 | +| clip_range | 0.2 | +| entropy_loss | -0.454 | +| explained_variance | -1.19 | +| learning_rate | 0.0001 | +| loss | -0.0916 | +| n_updates | 101340 | +| policy_gradient_loss | -0.0667 | +| value_loss | 0.000633 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | -0.014 | +| time/ | | +| fps | 310 | +| iterations | 4083 | +| time_elapsed | 13482 | +| total_timesteps | 4180992 | +| train/ | | +| approx_kl | 1.8461565 | +| clip_fraction | 0.47 | +| clip_range | 0.2 | +| entropy_loss | -0.386 | +| explained_variance | -2.9 | +| learning_rate | 0.0001 | +| loss | -0.0926 | +| n_updates | 101350 | +| policy_gradient_loss | -0.0701 | +| value_loss | 0.000357 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | -0.0137 | +| time/ | | +| fps | 310 | +| iterations | 4084 | +| time_elapsed | 13486 | +| total_timesteps | 4182016 | +| train/ | | +| approx_kl | 2.1303878 | +| clip_fraction | 0.454 | +| clip_range | 0.2 | +| entropy_loss | -0.388 | +| explained_variance | -1 | +| learning_rate | 0.0001 | +| loss | -0.0604 | +| n_updates | 101360 | +| policy_gradient_loss | -0.0606 | +| value_loss | 0.000404 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | -0.0113 | +| time/ | | +| fps | 310 | +| iterations | 4085 | +| time_elapsed | 13489 | +| total_timesteps | 4183040 | +| train/ | | +| approx_kl | 5.5112743 | +| clip_fraction | 0.466 | +| clip_range | 0.2 | +| entropy_loss | -0.401 | +| explained_variance | -0.947 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 101370 | +| policy_gradient_loss | -0.0634 | +| value_loss | 0.000627 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | -0.0105 | +| time/ | | +| fps | 310 | +| iterations | 4086 | +| time_elapsed | 13492 | +| total_timesteps | 4184064 | +| train/ | | +| approx_kl | 1.9007545 | +| clip_fraction | 0.484 | +| clip_range | 0.2 | +| entropy_loss | -0.358 | +| explained_variance | -3.55 | +| learning_rate | 0.0001 | +| loss | -0.113 | +| n_updates | 101380 | +| policy_gradient_loss | -0.0734 | +| value_loss | 0.0006 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | -0.0105 | +| time/ | | +| fps | 310 | +| iterations | 4087 | +| time_elapsed | 13496 | +| total_timesteps | 4185088 | +| train/ | | +| approx_kl | 1.6052983 | +| clip_fraction | 0.463 | +| clip_range | 0.2 | +| entropy_loss | -0.361 | +| explained_variance | -2.7 | +| learning_rate | 0.0001 | +| loss | -0.0732 | +| n_updates | 101390 | +| policy_gradient_loss | -0.062 | +| value_loss | 0.000656 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | -0.01 | +| time/ | | +| fps | 310 | +| iterations | 4088 | +| time_elapsed | 13499 | +| total_timesteps | 4186112 | +| train/ | | +| approx_kl | 1.7803853 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.397 | +| explained_variance | -1.63 | +| learning_rate | 0.0001 | +| loss | -0.0752 | +| n_updates | 101400 | +| policy_gradient_loss | -0.0671 | +| value_loss | 0.0007 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | -0.01 | +| time/ | | +| fps | 310 | +| iterations | 4089 | +| time_elapsed | 13503 | +| total_timesteps | 4187136 | +| train/ | | +| approx_kl | 1.4437592 | +| clip_fraction | 0.47 | +| clip_range | 0.2 | +| entropy_loss | -0.433 | +| explained_variance | -2.89 | +| learning_rate | 0.0001 | +| loss | -0.0765 | +| n_updates | 101410 | +| policy_gradient_loss | -0.0624 | +| value_loss | 0.00053 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | -0.00729 | +| time/ | | +| fps | 310 | +| iterations | 4090 | +| time_elapsed | 13506 | +| total_timesteps | 4188160 | +| train/ | | +| approx_kl | 1.2804456 | +| clip_fraction | 0.462 | +| clip_range | 0.2 | +| entropy_loss | -0.405 | +| explained_variance | -1.49 | +| learning_rate | 0.0001 | +| loss | -0.0696 | +| n_updates | 101420 | +| policy_gradient_loss | -0.0576 | +| value_loss | 0.000376 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | -0.00671 | +| time/ | | +| fps | 310 | +| iterations | 4091 | +| time_elapsed | 13509 | +| total_timesteps | 4189184 | +| train/ | | +| approx_kl | 1.8188818 | +| clip_fraction | 0.515 | +| clip_range | 0.2 | +| entropy_loss | -0.456 | +| explained_variance | -1.8 | +| learning_rate | 0.0001 | +| loss | -0.0955 | +| n_updates | 101430 | +| policy_gradient_loss | -0.0693 | +| value_loss | 0.000759 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | -0.00671 | +| time/ | | +| fps | 310 | +| iterations | 4092 | +| time_elapsed | 13512 | +| total_timesteps | 4190208 | +| train/ | | +| approx_kl | 1.6503177 | +| clip_fraction | 0.438 | +| clip_range | 0.2 | +| entropy_loss | -0.382 | +| explained_variance | -0.52 | +| learning_rate | 0.0001 | +| loss | -0.0828 | +| n_updates | 101440 | +| policy_gradient_loss | -0.065 | +| value_loss | 0.00055 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | -0.00471 | +| time/ | | +| fps | 310 | +| iterations | 4093 | +| time_elapsed | 13516 | +| total_timesteps | 4191232 | +| train/ | | +| approx_kl | 2.101077 | +| clip_fraction | 0.537 | +| clip_range | 0.2 | +| entropy_loss | -0.518 | +| explained_variance | -1.75 | +| learning_rate | 0.0001 | +| loss | -0.0974 | +| n_updates | 101450 | +| policy_gradient_loss | -0.0709 | +| value_loss | 0.00047 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | -0.00344 | +| time/ | | +| fps | 310 | +| iterations | 4094 | +| time_elapsed | 13519 | +| total_timesteps | 4192256 | +| train/ | | +| approx_kl | 1.5342056 | +| clip_fraction | 0.433 | +| clip_range | 0.2 | +| entropy_loss | -0.397 | +| explained_variance | -1.65 | +| learning_rate | 0.0001 | +| loss | -0.0769 | +| n_updates | 101460 | +| policy_gradient_loss | -0.0616 | +| value_loss | 0.000625 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | -0.00446 | +| time/ | | +| fps | 310 | +| iterations | 4095 | +| time_elapsed | 13522 | +| total_timesteps | 4193280 | +| train/ | | +| approx_kl | 2.6654 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.411 | +| explained_variance | -1.68 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 101470 | +| policy_gradient_loss | -0.0589 | +| value_loss | 0.000381 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | -0.00446 | +| time/ | | +| fps | 310 | +| iterations | 4096 | +| time_elapsed | 13525 | +| total_timesteps | 4194304 | +| train/ | | +| approx_kl | 1.4388298 | +| clip_fraction | 0.449 | +| clip_range | 0.2 | +| entropy_loss | -0.421 | +| explained_variance | -1.7 | +| learning_rate | 0.0001 | +| loss | -0.0957 | +| n_updates | 101480 | +| policy_gradient_loss | -0.0582 | +| value_loss | 0.00056 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | -0.00302 | +| time/ | | +| fps | 310 | +| iterations | 4097 | +| time_elapsed | 13528 | +| total_timesteps | 4195328 | +| train/ | | +| approx_kl | 1.5069675 | +| clip_fraction | 0.478 | +| clip_range | 0.2 | +| entropy_loss | -0.455 | +| explained_variance | -0.286 | +| learning_rate | 0.0001 | +| loss | -0.0906 | +| n_updates | 101490 | +| policy_gradient_loss | -0.0605 | +| value_loss | 0.000647 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | -0.00473 | +| time/ | | +| fps | 310 | +| iterations | 4098 | +| time_elapsed | 13531 | +| total_timesteps | 4196352 | +| train/ | | +| approx_kl | 1.4541373 | +| clip_fraction | 0.442 | +| clip_range | 0.2 | +| entropy_loss | -0.391 | +| explained_variance | -3.56 | +| learning_rate | 0.0001 | +| loss | -0.0593 | +| n_updates | 101500 | +| policy_gradient_loss | -0.0575 | +| value_loss | 0.000427 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | -0.00473 | +| time/ | | +| fps | 310 | +| iterations | 4099 | +| time_elapsed | 13534 | +| total_timesteps | 4197376 | +| train/ | | +| approx_kl | 1.435076 | +| clip_fraction | 0.492 | +| clip_range | 0.2 | +| entropy_loss | -0.484 | +| explained_variance | -3.39 | +| learning_rate | 0.0001 | +| loss | -0.0723 | +| n_updates | 101510 | +| policy_gradient_loss | -0.057 | +| value_loss | 0.000598 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | -0.00472 | +| time/ | | +| fps | 310 | +| iterations | 4100 | +| time_elapsed | 13538 | +| total_timesteps | 4198400 | +| train/ | | +| approx_kl | 1.9143056 | +| clip_fraction | 0.495 | +| clip_range | 0.2 | +| entropy_loss | -0.412 | +| explained_variance | -1.99 | +| learning_rate | 0.0001 | +| loss | -0.0806 | +| n_updates | 101520 | +| policy_gradient_loss | -0.0663 | +| value_loss | 0.000687 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | -0.00444 | +| time/ | | +| fps | 310 | +| iterations | 4101 | +| time_elapsed | 13541 | +| total_timesteps | 4199424 | +| train/ | | +| approx_kl | 1.3875823 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.495 | +| explained_variance | -5.8 | +| learning_rate | 0.0001 | +| loss | -0.0929 | +| n_updates | 101530 | +| policy_gradient_loss | -0.0501 | +| value_loss | 0.000316 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | -0.00444 | +| time/ | | +| fps | 310 | +| iterations | 4102 | +| time_elapsed | 13545 | +| total_timesteps | 4200448 | +| train/ | | +| approx_kl | 2.487545 | +| clip_fraction | 0.479 | +| clip_range | 0.2 | +| entropy_loss | -0.458 | +| explained_variance | -0.863 | +| learning_rate | 0.0001 | +| loss | -0.0924 | +| n_updates | 101540 | +| policy_gradient_loss | -0.0565 | +| value_loss | 0.000389 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | -0.00683 | +| time/ | | +| fps | 310 | +| iterations | 4103 | +| time_elapsed | 13548 | +| total_timesteps | 4201472 | +| train/ | | +| approx_kl | 1.6370543 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.44 | +| explained_variance | -2.52 | +| learning_rate | 0.0001 | +| loss | -0.112 | +| n_updates | 101550 | +| policy_gradient_loss | -0.0694 | +| value_loss | 0.00074 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | -0.00589 | +| time/ | | +| fps | 310 | +| iterations | 4104 | +| time_elapsed | 13552 | +| total_timesteps | 4202496 | +| train/ | | +| approx_kl | 2.2798479 | +| clip_fraction | 0.492 | +| clip_range | 0.2 | +| entropy_loss | -0.451 | +| explained_variance | -1.8 | +| learning_rate | 0.0001 | +| loss | -0.0964 | +| n_updates | 101560 | +| policy_gradient_loss | -0.0648 | +| value_loss | 0.000529 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | -0.0108 | +| time/ | | +| fps | 310 | +| iterations | 4105 | +| time_elapsed | 13555 | +| total_timesteps | 4203520 | +| train/ | | +| approx_kl | 2.002337 | +| clip_fraction | 0.482 | +| clip_range | 0.2 | +| entropy_loss | -0.413 | +| explained_variance | -3.18 | +| learning_rate | 0.0001 | +| loss | -0.096 | +| n_updates | 101570 | +| policy_gradient_loss | -0.0735 | +| value_loss | 0.000526 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | -0.0108 | +| time/ | | +| fps | 310 | +| iterations | 4106 | +| time_elapsed | 13559 | +| total_timesteps | 4204544 | +| train/ | | +| approx_kl | 1.5892398 | +| clip_fraction | 0.451 | +| clip_range | 0.2 | +| entropy_loss | -0.406 | +| explained_variance | -1.09 | +| learning_rate | 0.0001 | +| loss | -0.0437 | +| n_updates | 101580 | +| policy_gradient_loss | -0.0482 | +| value_loss | 0.000272 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | -0.00848 | +| time/ | | +| fps | 310 | +| iterations | 4107 | +| time_elapsed | 13562 | +| total_timesteps | 4205568 | +| train/ | | +| approx_kl | 1.69381 | +| clip_fraction | 0.486 | +| clip_range | 0.2 | +| entropy_loss | -0.451 | +| explained_variance | -2.78 | +| learning_rate | 0.0001 | +| loss | -0.0821 | +| n_updates | 101590 | +| policy_gradient_loss | -0.0482 | +| value_loss | 0.000281 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | -0.00848 | +| time/ | | +| fps | 310 | +| iterations | 4108 | +| time_elapsed | 13565 | +| total_timesteps | 4206592 | +| train/ | | +| approx_kl | 1.9148698 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.424 | +| explained_variance | -2.79 | +| learning_rate | 0.0001 | +| loss | -0.0757 | +| n_updates | 101600 | +| policy_gradient_loss | -0.0649 | +| value_loss | 0.000418 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | -0.00869 | +| time/ | | +| fps | 310 | +| iterations | 4109 | +| time_elapsed | 13569 | +| total_timesteps | 4207616 | +| train/ | | +| approx_kl | 2.4317248 | +| clip_fraction | 0.484 | +| clip_range | 0.2 | +| entropy_loss | -0.401 | +| explained_variance | -1.49 | +| learning_rate | 0.0001 | +| loss | -0.0787 | +| n_updates | 101610 | +| policy_gradient_loss | -0.0667 | +| value_loss | 0.000554 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | -0.00869 | +| time/ | | +| fps | 310 | +| iterations | 4110 | +| time_elapsed | 13572 | +| total_timesteps | 4208640 | +| train/ | | +| approx_kl | 1.7431302 | +| clip_fraction | 0.509 | +| clip_range | 0.2 | +| entropy_loss | -0.468 | +| explained_variance | -0.971 | +| learning_rate | 0.0001 | +| loss | -0.0641 | +| n_updates | 101620 | +| policy_gradient_loss | -0.0689 | +| value_loss | 0.000696 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | -0.0049 | +| time/ | | +| fps | 310 | +| iterations | 4111 | +| time_elapsed | 13575 | +| total_timesteps | 4209664 | +| train/ | | +| approx_kl | 2.0371969 | +| clip_fraction | 0.478 | +| clip_range | 0.2 | +| entropy_loss | -0.467 | +| explained_variance | -5.35 | +| learning_rate | 0.0001 | +| loss | -0.0806 | +| n_updates | 101630 | +| policy_gradient_loss | -0.0687 | +| value_loss | 0.000274 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | -0.00729 | +| time/ | | +| fps | 310 | +| iterations | 4112 | +| time_elapsed | 13579 | +| total_timesteps | 4210688 | +| train/ | | +| approx_kl | 2.101216 | +| clip_fraction | 0.465 | +| clip_range | 0.2 | +| entropy_loss | -0.388 | +| explained_variance | -11.9 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 101640 | +| policy_gradient_loss | -0.0643 | +| value_loss | 0.000285 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | -0.00751 | +| time/ | | +| fps | 310 | +| iterations | 4113 | +| time_elapsed | 13582 | +| total_timesteps | 4211712 | +| train/ | | +| approx_kl | 1.5996673 | +| clip_fraction | 0.442 | +| clip_range | 0.2 | +| entropy_loss | -0.384 | +| explained_variance | -0.792 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 101650 | +| policy_gradient_loss | -0.0497 | +| value_loss | 0.000555 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | -0.00751 | +| time/ | | +| fps | 310 | +| iterations | 4114 | +| time_elapsed | 13585 | +| total_timesteps | 4212736 | +| train/ | | +| approx_kl | 2.035471 | +| clip_fraction | 0.45 | +| clip_range | 0.2 | +| entropy_loss | -0.371 | +| explained_variance | -2.12 | +| learning_rate | 0.0001 | +| loss | -0.079 | +| n_updates | 101660 | +| policy_gradient_loss | -0.0638 | +| value_loss | 0.000464 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | -0.00943 | +| time/ | | +| fps | 310 | +| iterations | 4115 | +| time_elapsed | 13588 | +| total_timesteps | 4213760 | +| train/ | | +| approx_kl | 1.6953626 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.468 | +| explained_variance | -2.17 | +| learning_rate | 0.0001 | +| loss | -0.0839 | +| n_updates | 101670 | +| policy_gradient_loss | -0.0565 | +| value_loss | 0.000362 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | -0.00818 | +| time/ | | +| fps | 310 | +| iterations | 4116 | +| time_elapsed | 13591 | +| total_timesteps | 4214784 | +| train/ | | +| approx_kl | 1.5817045 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.399 | +| explained_variance | -1.05 | +| learning_rate | 0.0001 | +| loss | -0.0944 | +| n_updates | 101680 | +| policy_gradient_loss | -0.0671 | +| value_loss | 0.000585 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | -0.00818 | +| time/ | | +| fps | 310 | +| iterations | 4117 | +| time_elapsed | 13595 | +| total_timesteps | 4215808 | +| train/ | | +| approx_kl | 2.4353433 | +| clip_fraction | 0.485 | +| clip_range | 0.2 | +| entropy_loss | -0.37 | +| explained_variance | -1.91 | +| learning_rate | 0.0001 | +| loss | -0.0466 | +| n_updates | 101690 | +| policy_gradient_loss | -0.0618 | +| value_loss | 0.000622 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | -0.00848 | +| time/ | | +| fps | 310 | +| iterations | 4118 | +| time_elapsed | 13598 | +| total_timesteps | 4216832 | +| train/ | | +| approx_kl | 1.9274422 | +| clip_fraction | 0.501 | +| clip_range | 0.2 | +| entropy_loss | -0.443 | +| explained_variance | -3.03 | +| learning_rate | 0.0001 | +| loss | -0.0963 | +| n_updates | 101700 | +| policy_gradient_loss | -0.0723 | +| value_loss | 0.000375 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | -0.00848 | +| time/ | | +| fps | 310 | +| iterations | 4119 | +| time_elapsed | 13601 | +| total_timesteps | 4217856 | +| train/ | | +| approx_kl | 2.838972 | +| clip_fraction | 0.433 | +| clip_range | 0.2 | +| entropy_loss | -0.332 | +| explained_variance | -0.639 | +| learning_rate | 0.0001 | +| loss | -0.0581 | +| n_updates | 101710 | +| policy_gradient_loss | -0.053 | +| value_loss | 0.00063 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | -0.00444 | +| time/ | | +| fps | 310 | +| iterations | 4120 | +| time_elapsed | 13605 | +| total_timesteps | 4218880 | +| train/ | | +| approx_kl | 1.5324576 | +| clip_fraction | 0.469 | +| clip_range | 0.2 | +| entropy_loss | -0.418 | +| explained_variance | -4.64 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 101720 | +| policy_gradient_loss | -0.0513 | +| value_loss | 0.00059 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | -0.00377 | +| time/ | | +| fps | 310 | +| iterations | 4121 | +| time_elapsed | 13608 | +| total_timesteps | 4219904 | +| train/ | | +| approx_kl | 1.7386957 | +| clip_fraction | 0.485 | +| clip_range | 0.2 | +| entropy_loss | -0.454 | +| explained_variance | -2.68 | +| learning_rate | 0.0001 | +| loss | -0.0772 | +| n_updates | 101730 | +| policy_gradient_loss | -0.0587 | +| value_loss | 0.000466 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | -0.00623 | +| time/ | | +| fps | 310 | +| iterations | 4122 | +| time_elapsed | 13612 | +| total_timesteps | 4220928 | +| train/ | | +| approx_kl | 2.2212725 | +| clip_fraction | 0.472 | +| clip_range | 0.2 | +| entropy_loss | -0.383 | +| explained_variance | -1.32 | +| learning_rate | 0.0001 | +| loss | -0.0541 | +| n_updates | 101740 | +| policy_gradient_loss | -0.063 | +| value_loss | 0.000514 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | -0.00623 | +| time/ | | +| fps | 310 | +| iterations | 4123 | +| time_elapsed | 13615 | +| total_timesteps | 4221952 | +| train/ | | +| approx_kl | 2.1601567 | +| clip_fraction | 0.468 | +| clip_range | 0.2 | +| entropy_loss | -0.365 | +| explained_variance | -2.86 | +| learning_rate | 0.0001 | +| loss | -0.0831 | +| n_updates | 101750 | +| policy_gradient_loss | -0.0619 | +| value_loss | 0.00071 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | -0.00623 | +| time/ | | +| fps | 310 | +| iterations | 4124 | +| time_elapsed | 13619 | +| total_timesteps | 4222976 | +| train/ | | +| approx_kl | 2.2338638 | +| clip_fraction | 0.504 | +| clip_range | 0.2 | +| entropy_loss | -0.421 | +| explained_variance | -1.92 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 101760 | +| policy_gradient_loss | -0.0688 | +| value_loss | 0.000451 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.43e+03 | +| ep_rew_mean | -0.00564 | +| time/ | | +| fps | 310 | +| iterations | 4125 | +| time_elapsed | 13622 | +| total_timesteps | 4224000 | +| train/ | | +| approx_kl | 2.7763162 | +| clip_fraction | 0.46 | +| clip_range | 0.2 | +| entropy_loss | -0.355 | +| explained_variance | -10.1 | +| learning_rate | 0.0001 | +| loss | -0.0648 | +| n_updates | 101770 | +| policy_gradient_loss | -0.0676 | +| value_loss | 0.000327 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.44e+03 | +| ep_rew_mean | -0.00322 | +| time/ | | +| fps | 310 | +| iterations | 4126 | +| time_elapsed | 13626 | +| total_timesteps | 4225024 | +| train/ | | +| approx_kl | 2.3641725 | +| clip_fraction | 0.458 | +| clip_range | 0.2 | +| entropy_loss | -0.373 | +| explained_variance | -1.1 | +| learning_rate | 0.0001 | +| loss | -0.0795 | +| n_updates | 101780 | +| policy_gradient_loss | -0.0492 | +| value_loss | 0.000405 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.44e+03 | +| ep_rew_mean | -0.00322 | +| time/ | | +| fps | 310 | +| iterations | 4127 | +| time_elapsed | 13629 | +| total_timesteps | 4226048 | +| train/ | | +| approx_kl | 1.7077663 | +| clip_fraction | 0.447 | +| clip_range | 0.2 | +| entropy_loss | -0.419 | +| explained_variance | -1.57 | +| learning_rate | 0.0001 | +| loss | -0.0758 | +| n_updates | 101790 | +| policy_gradient_loss | -0.056 | +| value_loss | 0.000304 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.43e+03 | +| ep_rew_mean | -0.00635 | +| time/ | | +| fps | 310 | +| iterations | 4128 | +| time_elapsed | 13633 | +| total_timesteps | 4227072 | +| train/ | | +| approx_kl | 2.7589438 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.344 | +| explained_variance | -5.21 | +| learning_rate | 0.0001 | +| loss | -0.0712 | +| n_updates | 101800 | +| policy_gradient_loss | -0.0697 | +| value_loss | 0.000658 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.43e+03 | +| ep_rew_mean | -0.00635 | +| time/ | | +| fps | 310 | +| iterations | 4129 | +| time_elapsed | 13636 | +| total_timesteps | 4228096 | +| train/ | | +| approx_kl | 1.8848729 | +| clip_fraction | 0.422 | +| clip_range | 0.2 | +| entropy_loss | -0.315 | +| explained_variance | -1.73 | +| learning_rate | 0.0001 | +| loss | -0.0568 | +| n_updates | 101810 | +| policy_gradient_loss | -0.0479 | +| value_loss | 0.000842 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.43e+03 | +| ep_rew_mean | -0.00201 | +| time/ | | +| fps | 310 | +| iterations | 4130 | +| time_elapsed | 13639 | +| total_timesteps | 4229120 | +| train/ | | +| approx_kl | 3.3638432 | +| clip_fraction | 0.448 | +| clip_range | 0.2 | +| entropy_loss | -0.398 | +| explained_variance | -1.84 | +| learning_rate | 0.0001 | +| loss | -0.0934 | +| n_updates | 101820 | +| policy_gradient_loss | -0.0612 | +| value_loss | 0.000573 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.43e+03 | +| ep_rew_mean | -0.00332 | +| time/ | | +| fps | 310 | +| iterations | 4131 | +| time_elapsed | 13642 | +| total_timesteps | 4230144 | +| train/ | | +| approx_kl | 2.2731056 | +| clip_fraction | 0.453 | +| clip_range | 0.2 | +| entropy_loss | -0.345 | +| explained_variance | -2.25 | +| learning_rate | 0.0001 | +| loss | -0.0741 | +| n_updates | 101830 | +| policy_gradient_loss | -0.0564 | +| value_loss | 0.000402 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.44e+03 | +| ep_rew_mean | -0.00289 | +| time/ | | +| fps | 310 | +| iterations | 4132 | +| time_elapsed | 13645 | +| total_timesteps | 4231168 | +| train/ | | +| approx_kl | 2.5088165 | +| clip_fraction | 0.443 | +| clip_range | 0.2 | +| entropy_loss | -0.353 | +| explained_variance | -1.04 | +| learning_rate | 0.0001 | +| loss | -0.0617 | +| n_updates | 101840 | +| policy_gradient_loss | -0.0617 | +| value_loss | 0.000525 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.44e+03 | +| ep_rew_mean | -0.00289 | +| time/ | | +| fps | 310 | +| iterations | 4133 | +| time_elapsed | 13648 | +| total_timesteps | 4232192 | +| train/ | | +| approx_kl | 1.5993125 | +| clip_fraction | 0.46 | +| clip_range | 0.2 | +| entropy_loss | -0.38 | +| explained_variance | -2.1 | +| learning_rate | 0.0001 | +| loss | -0.0829 | +| n_updates | 101850 | +| policy_gradient_loss | -0.0657 | +| value_loss | 0.000337 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.44e+03 | +| ep_rew_mean | -0.00188 | +| time/ | | +| fps | 310 | +| iterations | 4134 | +| time_elapsed | 13652 | +| total_timesteps | 4233216 | +| train/ | | +| approx_kl | 2.1464067 | +| clip_fraction | 0.449 | +| clip_range | 0.2 | +| entropy_loss | -0.351 | +| explained_variance | -1.38 | +| learning_rate | 0.0001 | +| loss | -0.0726 | +| n_updates | 101860 | +| policy_gradient_loss | -0.0613 | +| value_loss | 0.000639 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.44e+03 | +| ep_rew_mean | -0.000464 | +| time/ | | +| fps | 310 | +| iterations | 4135 | +| time_elapsed | 13655 | +| total_timesteps | 4234240 | +| train/ | | +| approx_kl | 1.8162804 | +| clip_fraction | 0.458 | +| clip_range | 0.2 | +| entropy_loss | -0.344 | +| explained_variance | -1.85 | +| learning_rate | 0.0001 | +| loss | -0.0928 | +| n_updates | 101870 | +| policy_gradient_loss | -0.0641 | +| value_loss | 0.000427 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.43e+03 | +| ep_rew_mean | -0.0029 | +| time/ | | +| fps | 310 | +| iterations | 4136 | +| time_elapsed | 13658 | +| total_timesteps | 4235264 | +| train/ | | +| approx_kl | 1.9164588 | +| clip_fraction | 0.446 | +| clip_range | 0.2 | +| entropy_loss | -0.342 | +| explained_variance | -0.715 | +| learning_rate | 0.0001 | +| loss | -0.106 | +| n_updates | 101880 | +| policy_gradient_loss | -0.0633 | +| value_loss | 0.000339 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.43e+03 | +| ep_rew_mean | -0.00287 | +| time/ | | +| fps | 310 | +| iterations | 4137 | +| time_elapsed | 13661 | +| total_timesteps | 4236288 | +| train/ | | +| approx_kl | 2.3736935 | +| clip_fraction | 0.473 | +| clip_range | 0.2 | +| entropy_loss | -0.358 | +| explained_variance | -0.509 | +| learning_rate | 0.0001 | +| loss | -0.0694 | +| n_updates | 101890 | +| policy_gradient_loss | -0.0643 | +| value_loss | 0.000426 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.43e+03 | +| ep_rew_mean | -0.00171 | +| time/ | | +| fps | 310 | +| iterations | 4138 | +| time_elapsed | 13665 | +| total_timesteps | 4237312 | +| train/ | | +| approx_kl | 2.7713819 | +| clip_fraction | 0.47 | +| clip_range | 0.2 | +| entropy_loss | -0.438 | +| explained_variance | -2.5 | +| learning_rate | 0.0001 | +| loss | -0.0855 | +| n_updates | 101900 | +| policy_gradient_loss | -0.0648 | +| value_loss | 0.000497 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.43e+03 | +| ep_rew_mean | -0.00171 | +| time/ | | +| fps | 310 | +| iterations | 4139 | +| time_elapsed | 13668 | +| total_timesteps | 4238336 | +| train/ | | +| approx_kl | 2.3886604 | +| clip_fraction | 0.497 | +| clip_range | 0.2 | +| entropy_loss | -0.455 | +| explained_variance | -1.53 | +| learning_rate | 0.0001 | +| loss | -0.0917 | +| n_updates | 101910 | +| policy_gradient_loss | -0.068 | +| value_loss | 0.000342 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | -0.0028 | +| time/ | | +| fps | 310 | +| iterations | 4140 | +| time_elapsed | 13672 | +| total_timesteps | 4239360 | +| train/ | | +| approx_kl | 1.4946482 | +| clip_fraction | 0.49 | +| clip_range | 0.2 | +| entropy_loss | -0.454 | +| explained_variance | -0.921 | +| learning_rate | 0.0001 | +| loss | -0.0931 | +| n_updates | 101920 | +| policy_gradient_loss | -0.0669 | +| value_loss | 0.000364 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.000589 | +| time/ | | +| fps | 310 | +| iterations | 4141 | +| time_elapsed | 13676 | +| total_timesteps | 4240384 | +| train/ | | +| approx_kl | 2.4166365 | +| clip_fraction | 0.478 | +| clip_range | 0.2 | +| entropy_loss | -0.412 | +| explained_variance | -1.54 | +| learning_rate | 0.0001 | +| loss | -0.0867 | +| n_updates | 101930 | +| policy_gradient_loss | -0.0634 | +| value_loss | 0.000715 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | -0.00236 | +| time/ | | +| fps | 310 | +| iterations | 4142 | +| time_elapsed | 13679 | +| total_timesteps | 4241408 | +| train/ | | +| approx_kl | 1.7114208 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.424 | +| explained_variance | -3.16 | +| learning_rate | 0.0001 | +| loss | -0.0804 | +| n_updates | 101940 | +| policy_gradient_loss | -0.0603 | +| value_loss | 0.000561 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | -0.00236 | +| time/ | | +| fps | 310 | +| iterations | 4143 | +| time_elapsed | 13683 | +| total_timesteps | 4242432 | +| train/ | | +| approx_kl | 2.0353465 | +| clip_fraction | 0.473 | +| clip_range | 0.2 | +| entropy_loss | -0.373 | +| explained_variance | -2.02 | +| learning_rate | 0.0001 | +| loss | -0.0752 | +| n_updates | 101950 | +| policy_gradient_loss | -0.0566 | +| value_loss | 0.000394 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.43e+03 | +| ep_rew_mean | -0.00123 | +| time/ | | +| fps | 310 | +| iterations | 4144 | +| time_elapsed | 13686 | +| total_timesteps | 4243456 | +| train/ | | +| approx_kl | 2.0238752 | +| clip_fraction | 0.49 | +| clip_range | 0.2 | +| entropy_loss | -0.428 | +| explained_variance | -1.29 | +| learning_rate | 0.0001 | +| loss | -0.0938 | +| n_updates | 101960 | +| policy_gradient_loss | -0.0513 | +| value_loss | 0.000346 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.44e+03 | +| ep_rew_mean | -0.0007 | +| time/ | | +| fps | 310 | +| iterations | 4145 | +| time_elapsed | 13690 | +| total_timesteps | 4244480 | +| train/ | | +| approx_kl | 2.076404 | +| clip_fraction | 0.504 | +| clip_range | 0.2 | +| entropy_loss | -0.442 | +| explained_variance | -0.749 | +| learning_rate | 0.0001 | +| loss | -0.072 | +| n_updates | 101970 | +| policy_gradient_loss | -0.0646 | +| value_loss | 0.000633 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.43e+03 | +| ep_rew_mean | -0.00233 | +| time/ | | +| fps | 310 | +| iterations | 4146 | +| time_elapsed | 13693 | +| total_timesteps | 4245504 | +| train/ | | +| approx_kl | 1.4531306 | +| clip_fraction | 0.453 | +| clip_range | 0.2 | +| entropy_loss | -0.45 | +| explained_variance | -1.92 | +| learning_rate | 0.0001 | +| loss | -0.0663 | +| n_updates | 101980 | +| policy_gradient_loss | -0.0593 | +| value_loss | 0.000582 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.43e+03 | +| ep_rew_mean | -0.00233 | +| time/ | | +| fps | 310 | +| iterations | 4147 | +| time_elapsed | 13696 | +| total_timesteps | 4246528 | +| train/ | | +| approx_kl | 2.279345 | +| clip_fraction | 0.478 | +| clip_range | 0.2 | +| entropy_loss | -0.431 | +| explained_variance | -2.64 | +| learning_rate | 0.0001 | +| loss | -0.105 | +| n_updates | 101990 | +| policy_gradient_loss | -0.0624 | +| value_loss | 0.000515 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.43e+03 | +| ep_rew_mean | -0.00494 | +| time/ | | +| fps | 310 | +| iterations | 4148 | +| time_elapsed | 13699 | +| total_timesteps | 4247552 | +| train/ | | +| approx_kl | 1.4270562 | +| clip_fraction | 0.467 | +| clip_range | 0.2 | +| entropy_loss | -0.457 | +| explained_variance | -0.929 | +| learning_rate | 0.0001 | +| loss | -0.0391 | +| n_updates | 102000 | +| policy_gradient_loss | -0.0495 | +| value_loss | 0.00056 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | -0.0105 | +| time/ | | +| fps | 310 | +| iterations | 4149 | +| time_elapsed | 13703 | +| total_timesteps | 4248576 | +| train/ | | +| approx_kl | 1.5530059 | +| clip_fraction | 0.461 | +| clip_range | 0.2 | +| entropy_loss | -0.408 | +| explained_variance | -2.91 | +| learning_rate | 0.0001 | +| loss | -0.0808 | +| n_updates | 102010 | +| policy_gradient_loss | -0.0537 | +| value_loss | 0.000529 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | -0.0104 | +| time/ | | +| fps | 310 | +| iterations | 4150 | +| time_elapsed | 13706 | +| total_timesteps | 4249600 | +| train/ | | +| approx_kl | 1.766445 | +| clip_fraction | 0.426 | +| clip_range | 0.2 | +| entropy_loss | -0.404 | +| explained_variance | -0.446 | +| learning_rate | 0.0001 | +| loss | -0.066 | +| n_updates | 102020 | +| policy_gradient_loss | -0.0519 | +| value_loss | 0.000842 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | -0.00903 | +| time/ | | +| fps | 310 | +| iterations | 4151 | +| time_elapsed | 13709 | +| total_timesteps | 4250624 | +| train/ | | +| approx_kl | 2.4208245 | +| clip_fraction | 0.484 | +| clip_range | 0.2 | +| entropy_loss | -0.452 | +| explained_variance | -4.33 | +| learning_rate | 0.0001 | +| loss | -0.0828 | +| n_updates | 102030 | +| policy_gradient_loss | -0.0645 | +| value_loss | 0.000375 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | -0.00903 | +| time/ | | +| fps | 310 | +| iterations | 4152 | +| time_elapsed | 13712 | +| total_timesteps | 4251648 | +| train/ | | +| approx_kl | 1.441963 | +| clip_fraction | 0.479 | +| clip_range | 0.2 | +| entropy_loss | -0.429 | +| explained_variance | -1.45 | +| learning_rate | 0.0001 | +| loss | -0.069 | +| n_updates | 102040 | +| policy_gradient_loss | -0.0651 | +| value_loss | 0.000433 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | -0.00839 | +| time/ | | +| fps | 310 | +| iterations | 4153 | +| time_elapsed | 13715 | +| total_timesteps | 4252672 | +| train/ | | +| approx_kl | 2.7834055 | +| clip_fraction | 0.538 | +| clip_range | 0.2 | +| entropy_loss | -0.473 | +| explained_variance | -0.803 | +| learning_rate | 0.0001 | +| loss | -0.0962 | +| n_updates | 102050 | +| policy_gradient_loss | -0.0679 | +| value_loss | 0.000333 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | -0.0121 | +| time/ | | +| fps | 310 | +| iterations | 4154 | +| time_elapsed | 13719 | +| total_timesteps | 4253696 | +| train/ | | +| approx_kl | 2.177238 | +| clip_fraction | 0.458 | +| clip_range | 0.2 | +| entropy_loss | -0.369 | +| explained_variance | -3.06 | +| learning_rate | 0.0001 | +| loss | -0.0947 | +| n_updates | 102060 | +| policy_gradient_loss | -0.0624 | +| value_loss | 0.000557 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | -0.00971 | +| time/ | | +| fps | 310 | +| iterations | 4155 | +| time_elapsed | 13722 | +| total_timesteps | 4254720 | +| train/ | | +| approx_kl | 1.5221782 | +| clip_fraction | 0.482 | +| clip_range | 0.2 | +| entropy_loss | -0.441 | +| explained_variance | -0.807 | +| learning_rate | 0.0001 | +| loss | -0.0773 | +| n_updates | 102070 | +| policy_gradient_loss | -0.0591 | +| value_loss | 0.000542 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | -0.00964 | +| time/ | | +| fps | 310 | +| iterations | 4156 | +| time_elapsed | 13725 | +| total_timesteps | 4255744 | +| train/ | | +| approx_kl | 2.2505054 | +| clip_fraction | 0.454 | +| clip_range | 0.2 | +| entropy_loss | -0.328 | +| explained_variance | -1.43 | +| learning_rate | 0.0001 | +| loss | -0.0933 | +| n_updates | 102080 | +| policy_gradient_loss | -0.0637 | +| value_loss | 0.000545 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | -0.00964 | +| time/ | | +| fps | 310 | +| iterations | 4157 | +| time_elapsed | 13729 | +| total_timesteps | 4256768 | +| train/ | | +| approx_kl | 2.1075351 | +| clip_fraction | 0.468 | +| clip_range | 0.2 | +| entropy_loss | -0.399 | +| explained_variance | -2.45 | +| learning_rate | 0.0001 | +| loss | -0.0801 | +| n_updates | 102090 | +| policy_gradient_loss | -0.0662 | +| value_loss | 0.000517 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | -0.0139 | +| time/ | | +| fps | 310 | +| iterations | 4158 | +| time_elapsed | 13732 | +| total_timesteps | 4257792 | +| train/ | | +| approx_kl | 2.2865987 | +| clip_fraction | 0.517 | +| clip_range | 0.2 | +| entropy_loss | -0.442 | +| explained_variance | -2.04 | +| learning_rate | 0.0001 | +| loss | -0.115 | +| n_updates | 102100 | +| policy_gradient_loss | -0.0653 | +| value_loss | 0.000488 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | -0.0139 | +| time/ | | +| fps | 310 | +| iterations | 4159 | +| time_elapsed | 13736 | +| total_timesteps | 4258816 | +| train/ | | +| approx_kl | 2.233702 | +| clip_fraction | 0.464 | +| clip_range | 0.2 | +| entropy_loss | -0.369 | +| explained_variance | -1.12 | +| learning_rate | 0.0001 | +| loss | -0.0948 | +| n_updates | 102110 | +| policy_gradient_loss | -0.0661 | +| value_loss | 0.000654 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | -0.0114 | +| time/ | | +| fps | 310 | +| iterations | 4160 | +| time_elapsed | 13739 | +| total_timesteps | 4259840 | +| train/ | | +| approx_kl | 2.7881098 | +| clip_fraction | 0.513 | +| clip_range | 0.2 | +| entropy_loss | -0.387 | +| explained_variance | -2.65 | +| learning_rate | 0.0001 | +| loss | -0.119 | +| n_updates | 102120 | +| policy_gradient_loss | -0.0723 | +| value_loss | 0.000492 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | -0.0111 | +| time/ | | +| fps | 310 | +| iterations | 4161 | +| time_elapsed | 13743 | +| total_timesteps | 4260864 | +| train/ | | +| approx_kl | 1.6808162 | +| clip_fraction | 0.478 | +| clip_range | 0.2 | +| entropy_loss | -0.444 | +| explained_variance | -3.27 | +| learning_rate | 0.0001 | +| loss | -0.0965 | +| n_updates | 102130 | +| policy_gradient_loss | -0.0646 | +| value_loss | 0.00024 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | -0.0111 | +| time/ | | +| fps | 310 | +| iterations | 4162 | +| time_elapsed | 13746 | +| total_timesteps | 4261888 | +| train/ | | +| approx_kl | 2.0070214 | +| clip_fraction | 0.491 | +| clip_range | 0.2 | +| entropy_loss | -0.382 | +| explained_variance | -1.84 | +| learning_rate | 0.0001 | +| loss | -0.094 | +| n_updates | 102140 | +| policy_gradient_loss | -0.0629 | +| value_loss | 0.00053 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | -0.0137 | +| time/ | | +| fps | 310 | +| iterations | 4163 | +| time_elapsed | 13749 | +| total_timesteps | 4262912 | +| train/ | | +| approx_kl | 2.130433 | +| clip_fraction | 0.496 | +| clip_range | 0.2 | +| entropy_loss | -0.386 | +| explained_variance | -2.55 | +| learning_rate | 0.0001 | +| loss | -0.105 | +| n_updates | 102150 | +| policy_gradient_loss | -0.0715 | +| value_loss | 0.000535 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | -0.0114 | +| time/ | | +| fps | 310 | +| iterations | 4164 | +| time_elapsed | 13752 | +| total_timesteps | 4263936 | +| train/ | | +| approx_kl | 1.6545975 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.437 | +| explained_variance | -1.22 | +| learning_rate | 0.0001 | +| loss | -0.0854 | +| n_updates | 102160 | +| policy_gradient_loss | -0.0584 | +| value_loss | 0.000292 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | -0.0134 | +| time/ | | +| fps | 310 | +| iterations | 4165 | +| time_elapsed | 13756 | +| total_timesteps | 4264960 | +| train/ | | +| approx_kl | 4.4378843 | +| clip_fraction | 0.462 | +| clip_range | 0.2 | +| entropy_loss | -0.37 | +| explained_variance | -1.08 | +| learning_rate | 0.0001 | +| loss | -0.0746 | +| n_updates | 102170 | +| policy_gradient_loss | -0.0695 | +| value_loss | 0.000519 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | -0.0134 | +| time/ | | +| fps | 310 | +| iterations | 4166 | +| time_elapsed | 13759 | +| total_timesteps | 4265984 | +| train/ | | +| approx_kl | 1.784978 | +| clip_fraction | 0.458 | +| clip_range | 0.2 | +| entropy_loss | -0.396 | +| explained_variance | -1.93 | +| learning_rate | 0.0001 | +| loss | -0.0794 | +| n_updates | 102180 | +| policy_gradient_loss | -0.0655 | +| value_loss | 0.000419 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | -0.0116 | +| time/ | | +| fps | 310 | +| iterations | 4167 | +| time_elapsed | 13762 | +| total_timesteps | 4267008 | +| train/ | | +| approx_kl | 1.6997925 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.35 | +| explained_variance | -3.12 | +| learning_rate | 0.0001 | +| loss | -0.0868 | +| n_updates | 102190 | +| policy_gradient_loss | -0.066 | +| value_loss | 0.000406 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | -0.0116 | +| time/ | | +| fps | 310 | +| iterations | 4168 | +| time_elapsed | 13765 | +| total_timesteps | 4268032 | +| train/ | | +| approx_kl | 2.0213594 | +| clip_fraction | 0.408 | +| clip_range | 0.2 | +| entropy_loss | -0.329 | +| explained_variance | -0.804 | +| learning_rate | 0.0001 | +| loss | -0.0707 | +| n_updates | 102200 | +| policy_gradient_loss | -0.059 | +| value_loss | 0.000546 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | -0.00932 | +| time/ | | +| fps | 310 | +| iterations | 4169 | +| time_elapsed | 13768 | +| total_timesteps | 4269056 | +| train/ | | +| approx_kl | 1.6701553 | +| clip_fraction | 0.454 | +| clip_range | 0.2 | +| entropy_loss | -0.368 | +| explained_variance | -3.82 | +| learning_rate | 0.0001 | +| loss | -0.0942 | +| n_updates | 102210 | +| policy_gradient_loss | -0.0649 | +| value_loss | 0.000397 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | -0.00932 | +| time/ | | +| fps | 310 | +| iterations | 4170 | +| time_elapsed | 13772 | +| total_timesteps | 4270080 | +| train/ | | +| approx_kl | 1.8329759 | +| clip_fraction | 0.438 | +| clip_range | 0.2 | +| entropy_loss | -0.348 | +| explained_variance | -1.16 | +| learning_rate | 0.0001 | +| loss | -0.0587 | +| n_updates | 102220 | +| policy_gradient_loss | -0.0586 | +| value_loss | 0.000484 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | -0.00713 | +| time/ | | +| fps | 310 | +| iterations | 4171 | +| time_elapsed | 13775 | +| total_timesteps | 4271104 | +| train/ | | +| approx_kl | 2.1145976 | +| clip_fraction | 0.456 | +| clip_range | 0.2 | +| entropy_loss | -0.374 | +| explained_variance | -1.6 | +| learning_rate | 0.0001 | +| loss | -0.0778 | +| n_updates | 102230 | +| policy_gradient_loss | -0.0613 | +| value_loss | 0.000688 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | -0.00713 | +| time/ | | +| fps | 310 | +| iterations | 4172 | +| time_elapsed | 13778 | +| total_timesteps | 4272128 | +| train/ | | +| approx_kl | 2.2074122 | +| clip_fraction | 0.442 | +| clip_range | 0.2 | +| entropy_loss | -0.322 | +| explained_variance | -2.79 | +| learning_rate | 0.0001 | +| loss | -0.0814 | +| n_updates | 102240 | +| policy_gradient_loss | -0.0677 | +| value_loss | 0.000669 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | -0.0063 | +| time/ | | +| fps | 310 | +| iterations | 4173 | +| time_elapsed | 13781 | +| total_timesteps | 4273152 | +| train/ | | +| approx_kl | 1.940558 | +| clip_fraction | 0.466 | +| clip_range | 0.2 | +| entropy_loss | -0.371 | +| explained_variance | -2.2 | +| learning_rate | 0.0001 | +| loss | -0.0778 | +| n_updates | 102250 | +| policy_gradient_loss | 0.0775 | +| value_loss | 0.000575 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | -0.00579 | +| time/ | | +| fps | 310 | +| iterations | 4174 | +| time_elapsed | 13785 | +| total_timesteps | 4274176 | +| train/ | | +| approx_kl | 2.7544172 | +| clip_fraction | 0.448 | +| clip_range | 0.2 | +| entropy_loss | -0.317 | +| explained_variance | -1.63 | +| learning_rate | 0.0001 | +| loss | -0.0876 | +| n_updates | 102260 | +| policy_gradient_loss | -0.0624 | +| value_loss | 0.000425 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | -0.00501 | +| time/ | | +| fps | 310 | +| iterations | 4175 | +| time_elapsed | 13788 | +| total_timesteps | 4275200 | +| train/ | | +| approx_kl | 1.9519861 | +| clip_fraction | 0.466 | +| clip_range | 0.2 | +| entropy_loss | -0.358 | +| explained_variance | -2.47 | +| learning_rate | 0.0001 | +| loss | -0.0695 | +| n_updates | 102270 | +| policy_gradient_loss | -0.0611 | +| value_loss | 0.000444 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | -0.00501 | +| time/ | | +| fps | 310 | +| iterations | 4176 | +| time_elapsed | 13792 | +| total_timesteps | 4276224 | +| train/ | | +| approx_kl | 1.9983065 | +| clip_fraction | 0.496 | +| clip_range | 0.2 | +| entropy_loss | -0.426 | +| explained_variance | -1.73 | +| learning_rate | 0.0001 | +| loss | -0.0856 | +| n_updates | 102280 | +| policy_gradient_loss | -0.0638 | +| value_loss | 0.000676 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | -0.00581 | +| time/ | | +| fps | 310 | +| iterations | 4177 | +| time_elapsed | 13796 | +| total_timesteps | 4277248 | +| train/ | | +| approx_kl | 2.736869 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.367 | +| explained_variance | -1.51 | +| learning_rate | 0.0001 | +| loss | -0.0971 | +| n_updates | 102290 | +| policy_gradient_loss | -0.0624 | +| value_loss | 0.000621 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | -0.00581 | +| time/ | | +| fps | 310 | +| iterations | 4178 | +| time_elapsed | 13799 | +| total_timesteps | 4278272 | +| train/ | | +| approx_kl | 2.1920452 | +| clip_fraction | 0.446 | +| clip_range | 0.2 | +| entropy_loss | -0.31 | +| explained_variance | -5.61 | +| learning_rate | 0.0001 | +| loss | -0.0963 | +| n_updates | 102300 | +| policy_gradient_loss | -0.0681 | +| value_loss | 0.000554 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.43e+03 | +| ep_rew_mean | -0.00528 | +| time/ | | +| fps | 310 | +| iterations | 4179 | +| time_elapsed | 13802 | +| total_timesteps | 4279296 | +| train/ | | +| approx_kl | 1.9909701 | +| clip_fraction | 0.45 | +| clip_range | 0.2 | +| entropy_loss | -0.342 | +| explained_variance | -1.2 | +| learning_rate | 0.0001 | +| loss | -0.0587 | +| n_updates | 102310 | +| policy_gradient_loss | -0.0536 | +| value_loss | 0.000415 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.43e+03 | +| ep_rew_mean | -0.00568 | +| time/ | | +| fps | 310 | +| iterations | 4180 | +| time_elapsed | 13806 | +| total_timesteps | 4280320 | +| train/ | | +| approx_kl | 2.052105 | +| clip_fraction | 0.473 | +| clip_range | 0.2 | +| entropy_loss | -0.347 | +| explained_variance | -1.75 | +| learning_rate | 0.0001 | +| loss | -0.0925 | +| n_updates | 102320 | +| policy_gradient_loss | -0.0669 | +| value_loss | 0.00067 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.43e+03 | +| ep_rew_mean | -0.00419 | +| time/ | | +| fps | 310 | +| iterations | 4181 | +| time_elapsed | 13809 | +| total_timesteps | 4281344 | +| train/ | | +| approx_kl | 2.3818798 | +| clip_fraction | 0.459 | +| clip_range | 0.2 | +| entropy_loss | -0.361 | +| explained_variance | -2.74 | +| learning_rate | 0.0001 | +| loss | -0.0848 | +| n_updates | 102330 | +| policy_gradient_loss | -0.0704 | +| value_loss | 0.000546 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.43e+03 | +| ep_rew_mean | -0.00763 | +| time/ | | +| fps | 310 | +| iterations | 4182 | +| time_elapsed | 13813 | +| total_timesteps | 4282368 | +| train/ | | +| approx_kl | 3.103324 | +| clip_fraction | 0.434 | +| clip_range | 0.2 | +| entropy_loss | -0.33 | +| explained_variance | -0.77 | +| learning_rate | 0.0001 | +| loss | 0.00196 | +| n_updates | 102340 | +| policy_gradient_loss | -0.0371 | +| value_loss | 0.000689 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.43e+03 | +| ep_rew_mean | -0.00763 | +| time/ | | +| fps | 310 | +| iterations | 4183 | +| time_elapsed | 13816 | +| total_timesteps | 4283392 | +| train/ | | +| approx_kl | 1.6159129 | +| clip_fraction | 0.452 | +| clip_range | 0.2 | +| entropy_loss | -0.376 | +| explained_variance | -1.45 | +| learning_rate | 0.0001 | +| loss | -0.0802 | +| n_updates | 102350 | +| policy_gradient_loss | -0.0512 | +| value_loss | 0.000537 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.43e+03 | +| ep_rew_mean | -0.00789 | +| time/ | | +| fps | 310 | +| iterations | 4184 | +| time_elapsed | 13819 | +| total_timesteps | 4284416 | +| train/ | | +| approx_kl | 2.1146357 | +| clip_fraction | 0.453 | +| clip_range | 0.2 | +| entropy_loss | -0.333 | +| explained_variance | -1.85 | +| learning_rate | 0.0001 | +| loss | -0.0938 | +| n_updates | 102360 | +| policy_gradient_loss | -0.0667 | +| value_loss | 0.000692 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.43e+03 | +| ep_rew_mean | -0.00392 | +| time/ | | +| fps | 310 | +| iterations | 4185 | +| time_elapsed | 13822 | +| total_timesteps | 4285440 | +| train/ | | +| approx_kl | 2.6595683 | +| clip_fraction | 0.47 | +| clip_range | 0.2 | +| entropy_loss | -0.344 | +| explained_variance | -1.81 | +| learning_rate | 0.0001 | +| loss | -0.0923 | +| n_updates | 102370 | +| policy_gradient_loss | -0.0628 | +| value_loss | 0.000512 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.43e+03 | +| ep_rew_mean | -0.00392 | +| time/ | | +| fps | 310 | +| iterations | 4186 | +| time_elapsed | 13825 | +| total_timesteps | 4286464 | +| train/ | | +| approx_kl | 2.0309453 | +| clip_fraction | 0.478 | +| clip_range | 0.2 | +| entropy_loss | -0.368 | +| explained_variance | -1.46 | +| learning_rate | 0.0001 | +| loss | -0.108 | +| n_updates | 102380 | +| policy_gradient_loss | -0.0615 | +| value_loss | 0.000405 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.43e+03 | +| ep_rew_mean | -0.00502 | +| time/ | | +| fps | 310 | +| iterations | 4187 | +| time_elapsed | 13828 | +| total_timesteps | 4287488 | +| train/ | | +| approx_kl | 3.7574878 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.399 | +| explained_variance | -0.412 | +| learning_rate | 0.0001 | +| loss | -0.0963 | +| n_updates | 102390 | +| policy_gradient_loss | -0.0645 | +| value_loss | 0.000569 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | -0.00403 | +| time/ | | +| fps | 310 | +| iterations | 4188 | +| time_elapsed | 13832 | +| total_timesteps | 4288512 | +| train/ | | +| approx_kl | 2.2812762 | +| clip_fraction | 0.479 | +| clip_range | 0.2 | +| entropy_loss | -0.432 | +| explained_variance | -2.72 | +| learning_rate | 0.0001 | +| loss | -0.0982 | +| n_updates | 102400 | +| policy_gradient_loss | -0.0609 | +| value_loss | 0.000348 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | -0.00403 | +| time/ | | +| fps | 310 | +| iterations | 4189 | +| time_elapsed | 13835 | +| total_timesteps | 4289536 | +| train/ | | +| approx_kl | 1.9498291 | +| clip_fraction | 0.457 | +| clip_range | 0.2 | +| entropy_loss | -0.355 | +| explained_variance | -1.19 | +| learning_rate | 0.0001 | +| loss | -0.0672 | +| n_updates | 102410 | +| policy_gradient_loss | -0.06 | +| value_loss | 0.00076 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.43e+03 | +| ep_rew_mean | -0.00254 | +| time/ | | +| fps | 310 | +| iterations | 4190 | +| time_elapsed | 13838 | +| total_timesteps | 4290560 | +| train/ | | +| approx_kl | 2.9785104 | +| clip_fraction | 0.486 | +| clip_range | 0.2 | +| entropy_loss | -0.364 | +| explained_variance | -1.77 | +| learning_rate | 0.0001 | +| loss | -0.0919 | +| n_updates | 102420 | +| policy_gradient_loss | -0.0621 | +| value_loss | 0.000646 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.43e+03 | +| ep_rew_mean | 0.000113 | +| time/ | | +| fps | 310 | +| iterations | 4191 | +| time_elapsed | 13841 | +| total_timesteps | 4291584 | +| train/ | | +| approx_kl | 2.1638432 | +| clip_fraction | 0.479 | +| clip_range | 0.2 | +| entropy_loss | -0.37 | +| explained_variance | -1.16 | +| learning_rate | 0.0001 | +| loss | -0.0826 | +| n_updates | 102430 | +| policy_gradient_loss | -0.0612 | +| value_loss | 0.000731 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.43e+03 | +| ep_rew_mean | 0.0025 | +| time/ | | +| fps | 310 | +| iterations | 4192 | +| time_elapsed | 13845 | +| total_timesteps | 4292608 | +| train/ | | +| approx_kl | 1.788012 | +| clip_fraction | 0.466 | +| clip_range | 0.2 | +| entropy_loss | -0.378 | +| explained_variance | -2.11 | +| learning_rate | 0.0001 | +| loss | -0.0685 | +| n_updates | 102440 | +| policy_gradient_loss | -0.0683 | +| value_loss | 0.000285 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.43e+03 | +| ep_rew_mean | 0.000614 | +| time/ | | +| fps | 310 | +| iterations | 4193 | +| time_elapsed | 13848 | +| total_timesteps | 4293632 | +| train/ | | +| approx_kl | 2.4918056 | +| clip_fraction | 0.45 | +| clip_range | 0.2 | +| entropy_loss | -0.34 | +| explained_variance | -5.89 | +| learning_rate | 0.0001 | +| loss | -0.091 | +| n_updates | 102450 | +| policy_gradient_loss | -0.0656 | +| value_loss | 0.000318 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.43e+03 | +| ep_rew_mean | 0.000614 | +| time/ | | +| fps | 310 | +| iterations | 4194 | +| time_elapsed | 13851 | +| total_timesteps | 4294656 | +| train/ | | +| approx_kl | 2.2069783 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.371 | +| explained_variance | -0.619 | +| learning_rate | 0.0001 | +| loss | -0.0717 | +| n_updates | 102460 | +| policy_gradient_loss | -0.0524 | +| value_loss | 0.000445 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.43e+03 | +| ep_rew_mean | 0.00141 | +| time/ | | +| fps | 310 | +| iterations | 4195 | +| time_elapsed | 13855 | +| total_timesteps | 4295680 | +| train/ | | +| approx_kl | 3.4494295 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.402 | +| explained_variance | -0.977 | +| learning_rate | 0.0001 | +| loss | -0.0728 | +| n_updates | 102470 | +| policy_gradient_loss | -0.058 | +| value_loss | 0.000411 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.000112 | +| time/ | | +| fps | 310 | +| iterations | 4196 | +| time_elapsed | 13858 | +| total_timesteps | 4296704 | +| train/ | | +| approx_kl | 1.8900867 | +| clip_fraction | 0.465 | +| clip_range | 0.2 | +| entropy_loss | -0.337 | +| explained_variance | -1.88 | +| learning_rate | 0.0001 | +| loss | -0.0772 | +| n_updates | 102480 | +| policy_gradient_loss | -0.0611 | +| value_loss | 0.000416 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | -0.000316 | +| time/ | | +| fps | 310 | +| iterations | 4197 | +| time_elapsed | 13861 | +| total_timesteps | 4297728 | +| train/ | | +| approx_kl | 2.188544 | +| clip_fraction | 0.463 | +| clip_range | 0.2 | +| entropy_loss | -0.376 | +| explained_variance | -1.26 | +| learning_rate | 0.0001 | +| loss | -0.0999 | +| n_updates | 102490 | +| policy_gradient_loss | -0.0578 | +| value_loss | 0.000577 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | -0.000316 | +| time/ | | +| fps | 310 | +| iterations | 4198 | +| time_elapsed | 13865 | +| total_timesteps | 4298752 | +| train/ | | +| approx_kl | 2.0801573 | +| clip_fraction | 0.449 | +| clip_range | 0.2 | +| entropy_loss | -0.301 | +| explained_variance | -2.15 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 102500 | +| policy_gradient_loss | -0.0643 | +| value_loss | 0.000554 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.43e+03 | +| ep_rew_mean | 0.00408 | +| time/ | | +| fps | 310 | +| iterations | 4199 | +| time_elapsed | 13868 | +| total_timesteps | 4299776 | +| train/ | | +| approx_kl | 1.9254806 | +| clip_fraction | 0.496 | +| clip_range | 0.2 | +| entropy_loss | -0.389 | +| explained_variance | -1.8 | +| learning_rate | 0.0001 | +| loss | -0.0449 | +| n_updates | 102510 | +| policy_gradient_loss | -0.063 | +| value_loss | 0.000867 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.43e+03 | +| ep_rew_mean | 0.00408 | +| time/ | | +| fps | 310 | +| iterations | 4200 | +| time_elapsed | 13871 | +| total_timesteps | 4300800 | +| train/ | | +| approx_kl | 2.646555 | +| clip_fraction | 0.495 | +| clip_range | 0.2 | +| entropy_loss | -0.377 | +| explained_variance | -1.24 | +| learning_rate | 0.0001 | +| loss | -0.0985 | +| n_updates | 102520 | +| policy_gradient_loss | -0.0668 | +| value_loss | 0.0006 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.43e+03 | +| ep_rew_mean | 0.00464 | +| time/ | | +| fps | 310 | +| iterations | 4201 | +| time_elapsed | 13874 | +| total_timesteps | 4301824 | +| train/ | | +| approx_kl | 1.9850566 | +| clip_fraction | 0.464 | +| clip_range | 0.2 | +| entropy_loss | -0.382 | +| explained_variance | -2.2 | +| learning_rate | 0.0001 | +| loss | -0.0829 | +| n_updates | 102530 | +| policy_gradient_loss | -0.0589 | +| value_loss | 0.000477 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.43e+03 | +| ep_rew_mean | 0.00426 | +| time/ | | +| fps | 310 | +| iterations | 4202 | +| time_elapsed | 13878 | +| total_timesteps | 4302848 | +| train/ | | +| approx_kl | 2.4770243 | +| clip_fraction | 0.469 | +| clip_range | 0.2 | +| entropy_loss | -0.325 | +| explained_variance | -1.15 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 102540 | +| policy_gradient_loss | -0.0604 | +| value_loss | 0.000595 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.43e+03 | +| ep_rew_mean | 0.00415 | +| time/ | | +| fps | 310 | +| iterations | 4203 | +| time_elapsed | 13881 | +| total_timesteps | 4303872 | +| train/ | | +| approx_kl | 3.0100725 | +| clip_fraction | 0.473 | +| clip_range | 0.2 | +| entropy_loss | -0.327 | +| explained_variance | -1.71 | +| learning_rate | 0.0001 | +| loss | -0.0906 | +| n_updates | 102550 | +| policy_gradient_loss | -0.0694 | +| value_loss | 0.000561 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.43e+03 | +| ep_rew_mean | 0.00418 | +| time/ | | +| fps | 310 | +| iterations | 4204 | +| time_elapsed | 13884 | +| total_timesteps | 4304896 | +| train/ | | +| approx_kl | 4.1953897 | +| clip_fraction | 0.493 | +| clip_range | 0.2 | +| entropy_loss | -0.453 | +| explained_variance | -2.43 | +| learning_rate | 0.0001 | +| loss | -0.0869 | +| n_updates | 102560 | +| policy_gradient_loss | -0.0543 | +| value_loss | 0.000306 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.43e+03 | +| ep_rew_mean | 0.00418 | +| time/ | | +| fps | 310 | +| iterations | 4205 | +| time_elapsed | 13887 | +| total_timesteps | 4305920 | +| train/ | | +| approx_kl | 1.9713162 | +| clip_fraction | 0.438 | +| clip_range | 0.2 | +| entropy_loss | -0.317 | +| explained_variance | -1.08 | +| learning_rate | 0.0001 | +| loss | -0.0967 | +| n_updates | 102570 | +| policy_gradient_loss | -0.0549 | +| value_loss | 0.000314 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.0017 | +| time/ | | +| fps | 310 | +| iterations | 4206 | +| time_elapsed | 13890 | +| total_timesteps | 4306944 | +| train/ | | +| approx_kl | 1.91953 | +| clip_fraction | 0.46 | +| clip_range | 0.2 | +| entropy_loss | -0.403 | +| explained_variance | -1.21 | +| learning_rate | 0.0001 | +| loss | -0.0902 | +| n_updates | 102580 | +| policy_gradient_loss | -0.0562 | +| value_loss | 0.000419 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.00215 | +| time/ | | +| fps | 310 | +| iterations | 4207 | +| time_elapsed | 13893 | +| total_timesteps | 4307968 | +| train/ | | +| approx_kl | 1.7718654 | +| clip_fraction | 0.454 | +| clip_range | 0.2 | +| entropy_loss | -0.405 | +| explained_variance | -1.22 | +| learning_rate | 0.0001 | +| loss | -0.0788 | +| n_updates | 102590 | +| policy_gradient_loss | -0.0634 | +| value_loss | 0.000504 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.00215 | +| time/ | | +| fps | 310 | +| iterations | 4208 | +| time_elapsed | 13896 | +| total_timesteps | 4308992 | +| train/ | | +| approx_kl | 3.7346988 | +| clip_fraction | 0.469 | +| clip_range | 0.2 | +| entropy_loss | -0.399 | +| explained_variance | -2.69 | +| learning_rate | 0.0001 | +| loss | -0.0881 | +| n_updates | 102600 | +| policy_gradient_loss | -0.0658 | +| value_loss | 0.000456 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.43e+03 | +| ep_rew_mean | 0.00262 | +| time/ | | +| fps | 310 | +| iterations | 4209 | +| time_elapsed | 13900 | +| total_timesteps | 4310016 | +| train/ | | +| approx_kl | 8.100611 | +| clip_fraction | 0.493 | +| clip_range | 0.2 | +| entropy_loss | -0.382 | +| explained_variance | -4.23 | +| learning_rate | 0.0001 | +| loss | -0.0715 | +| n_updates | 102610 | +| policy_gradient_loss | -0.0648 | +| value_loss | 0.000864 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.00336 | +| time/ | | +| fps | 310 | +| iterations | 4210 | +| time_elapsed | 13903 | +| total_timesteps | 4311040 | +| train/ | | +| approx_kl | 1.8163134 | +| clip_fraction | 0.453 | +| clip_range | 0.2 | +| entropy_loss | -0.384 | +| explained_variance | -1.64 | +| learning_rate | 0.0001 | +| loss | -0.0735 | +| n_updates | 102620 | +| policy_gradient_loss | -0.0653 | +| value_loss | 0.000544 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.00336 | +| time/ | | +| fps | 310 | +| iterations | 4211 | +| time_elapsed | 13907 | +| total_timesteps | 4312064 | +| train/ | | +| approx_kl | 2.8791513 | +| clip_fraction | 0.472 | +| clip_range | 0.2 | +| entropy_loss | -0.388 | +| explained_variance | -1.08 | +| learning_rate | 0.0001 | +| loss | -0.0977 | +| n_updates | 102630 | +| policy_gradient_loss | -0.0651 | +| value_loss | 0.000394 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.43e+03 | +| ep_rew_mean | 0.00413 | +| time/ | | +| fps | 310 | +| iterations | 4212 | +| time_elapsed | 13910 | +| total_timesteps | 4313088 | +| train/ | | +| approx_kl | 2.4223108 | +| clip_fraction | 0.49 | +| clip_range | 0.2 | +| entropy_loss | -0.41 | +| explained_variance | -2.97 | +| learning_rate | 0.0001 | +| loss | -0.0997 | +| n_updates | 102640 | +| policy_gradient_loss | -0.0613 | +| value_loss | 0.000527 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.43e+03 | +| ep_rew_mean | 0.00413 | +| time/ | | +| fps | 310 | +| iterations | 4213 | +| time_elapsed | 13914 | +| total_timesteps | 4314112 | +| train/ | | +| approx_kl | 1.9060382 | +| clip_fraction | 0.493 | +| clip_range | 0.2 | +| entropy_loss | -0.47 | +| explained_variance | -5.11 | +| learning_rate | 0.0001 | +| loss | -0.0662 | +| n_updates | 102650 | +| policy_gradient_loss | -0.0557 | +| value_loss | 0.000342 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.43e+03 | +| ep_rew_mean | 0.00416 | +| time/ | | +| fps | 310 | +| iterations | 4214 | +| time_elapsed | 13917 | +| total_timesteps | 4315136 | +| train/ | | +| approx_kl | 1.8398368 | +| clip_fraction | 0.502 | +| clip_range | 0.2 | +| entropy_loss | -0.431 | +| explained_variance | -0.365 | +| learning_rate | 0.0001 | +| loss | -0.06 | +| n_updates | 102660 | +| policy_gradient_loss | -0.065 | +| value_loss | 0.000356 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.43e+03 | +| ep_rew_mean | 0.00416 | +| time/ | | +| fps | 310 | +| iterations | 4215 | +| time_elapsed | 13921 | +| total_timesteps | 4316160 | +| train/ | | +| approx_kl | 1.9743686 | +| clip_fraction | 0.467 | +| clip_range | 0.2 | +| entropy_loss | -0.356 | +| explained_variance | -1.02 | +| learning_rate | 0.0001 | +| loss | -0.0656 | +| n_updates | 102670 | +| policy_gradient_loss | -0.0621 | +| value_loss | 0.000373 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.43e+03 | +| ep_rew_mean | 0.00309 | +| time/ | | +| fps | 310 | +| iterations | 4216 | +| time_elapsed | 13924 | +| total_timesteps | 4317184 | +| train/ | | +| approx_kl | 2.4205735 | +| clip_fraction | 0.465 | +| clip_range | 0.2 | +| entropy_loss | -0.338 | +| explained_variance | -1.33 | +| learning_rate | 0.0001 | +| loss | -0.00118 | +| n_updates | 102680 | +| policy_gradient_loss | -0.0101 | +| value_loss | 0.000749 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.43e+03 | +| ep_rew_mean | 0.00309 | +| time/ | | +| fps | 310 | +| iterations | 4217 | +| time_elapsed | 13928 | +| total_timesteps | 4318208 | +| train/ | | +| approx_kl | 2.4223206 | +| clip_fraction | 0.461 | +| clip_range | 0.2 | +| entropy_loss | -0.315 | +| explained_variance | -4.43 | +| learning_rate | 0.0001 | +| loss | -0.073 | +| n_updates | 102690 | +| policy_gradient_loss | -0.0547 | +| value_loss | 0.000458 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.44e+03 | +| ep_rew_mean | 0.00324 | +| time/ | | +| fps | 310 | +| iterations | 4218 | +| time_elapsed | 13931 | +| total_timesteps | 4319232 | +| train/ | | +| approx_kl | 1.7737937 | +| clip_fraction | 0.439 | +| clip_range | 0.2 | +| entropy_loss | -0.373 | +| explained_variance | -1.82 | +| learning_rate | 0.0001 | +| loss | -0.097 | +| n_updates | 102700 | +| policy_gradient_loss | -0.0622 | +| value_loss | 0.000579 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.44e+03 | +| ep_rew_mean | 0.00144 | +| time/ | | +| fps | 310 | +| iterations | 4219 | +| time_elapsed | 13934 | +| total_timesteps | 4320256 | +| train/ | | +| approx_kl | 2.2204394 | +| clip_fraction | 0.464 | +| clip_range | 0.2 | +| entropy_loss | -0.387 | +| explained_variance | -3.01 | +| learning_rate | 0.0001 | +| loss | -0.084 | +| n_updates | 102710 | +| policy_gradient_loss | -0.0603 | +| value_loss | 0.000454 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.44e+03 | +| ep_rew_mean | 0.0034 | +| time/ | | +| fps | 310 | +| iterations | 4220 | +| time_elapsed | 13937 | +| total_timesteps | 4321280 | +| train/ | | +| approx_kl | 2.8860188 | +| clip_fraction | 0.463 | +| clip_range | 0.2 | +| entropy_loss | -0.348 | +| explained_variance | -3.33 | +| learning_rate | 0.0001 | +| loss | -0.0614 | +| n_updates | 102720 | +| policy_gradient_loss | -0.0571 | +| value_loss | 0.000456 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.44e+03 | +| ep_rew_mean | 0.0034 | +| time/ | | +| fps | 310 | +| iterations | 4221 | +| time_elapsed | 13940 | +| total_timesteps | 4322304 | +| train/ | | +| approx_kl | 1.6385919 | +| clip_fraction | 0.446 | +| clip_range | 0.2 | +| entropy_loss | -0.365 | +| explained_variance | -0.788 | +| learning_rate | 0.0001 | +| loss | -0.0341 | +| n_updates | 102730 | +| policy_gradient_loss | -0.0599 | +| value_loss | 0.000559 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.44e+03 | +| ep_rew_mean | 0.00398 | +| time/ | | +| fps | 310 | +| iterations | 4222 | +| time_elapsed | 13943 | +| total_timesteps | 4323328 | +| train/ | | +| approx_kl | 2.0182776 | +| clip_fraction | 0.516 | +| clip_range | 0.2 | +| entropy_loss | -0.449 | +| explained_variance | -3.12 | +| learning_rate | 0.0001 | +| loss | -0.0849 | +| n_updates | 102740 | +| policy_gradient_loss | -0.0631 | +| value_loss | 0.000471 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.44e+03 | +| ep_rew_mean | 0.00409 | +| time/ | | +| fps | 310 | +| iterations | 4223 | +| time_elapsed | 13947 | +| total_timesteps | 4324352 | +| train/ | | +| approx_kl | 2.6157413 | +| clip_fraction | 0.467 | +| clip_range | 0.2 | +| entropy_loss | -0.371 | +| explained_variance | -2.79 | +| learning_rate | 0.0001 | +| loss | -0.0879 | +| n_updates | 102750 | +| policy_gradient_loss | -0.0634 | +| value_loss | 0.000525 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.44e+03 | +| ep_rew_mean | 0.00658 | +| time/ | | +| fps | 310 | +| iterations | 4224 | +| time_elapsed | 13950 | +| total_timesteps | 4325376 | +| train/ | | +| approx_kl | 2.1563897 | +| clip_fraction | 0.469 | +| clip_range | 0.2 | +| entropy_loss | -0.372 | +| explained_variance | -1.45 | +| learning_rate | 0.0001 | +| loss | -0.0891 | +| n_updates | 102760 | +| policy_gradient_loss | -0.0689 | +| value_loss | 0.000498 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.44e+03 | +| ep_rew_mean | 0.00658 | +| time/ | | +| fps | 310 | +| iterations | 4225 | +| time_elapsed | 13953 | +| total_timesteps | 4326400 | +| train/ | | +| approx_kl | 2.141602 | +| clip_fraction | 0.489 | +| clip_range | 0.2 | +| entropy_loss | -0.395 | +| explained_variance | -1.39 | +| learning_rate | 0.0001 | +| loss | -0.0887 | +| n_updates | 102770 | +| policy_gradient_loss | -0.0603 | +| value_loss | 0.000636 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.44e+03 | +| ep_rew_mean | 0.00539 | +| time/ | | +| fps | 310 | +| iterations | 4226 | +| time_elapsed | 13956 | +| total_timesteps | 4327424 | +| train/ | | +| approx_kl | 2.5191126 | +| clip_fraction | 0.477 | +| clip_range | 0.2 | +| entropy_loss | -0.352 | +| explained_variance | -2.79 | +| learning_rate | 0.0001 | +| loss | -0.0568 | +| n_updates | 102780 | +| policy_gradient_loss | -0.0668 | +| value_loss | 0.000307 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.44e+03 | +| ep_rew_mean | 0.00539 | +| time/ | | +| fps | 310 | +| iterations | 4227 | +| time_elapsed | 13959 | +| total_timesteps | 4328448 | +| train/ | | +| approx_kl | 2.0598269 | +| clip_fraction | 0.449 | +| clip_range | 0.2 | +| entropy_loss | -0.325 | +| explained_variance | -0.987 | +| learning_rate | 0.0001 | +| loss | -0.0791 | +| n_updates | 102790 | +| policy_gradient_loss | -0.0605 | +| value_loss | 0.000465 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.45e+03 | +| ep_rew_mean | 0.00581 | +| time/ | | +| fps | 310 | +| iterations | 4228 | +| time_elapsed | 13963 | +| total_timesteps | 4329472 | +| train/ | | +| approx_kl | 2.0384133 | +| clip_fraction | 0.496 | +| clip_range | 0.2 | +| entropy_loss | -0.393 | +| explained_variance | -0.285 | +| learning_rate | 0.0001 | +| loss | -0.0989 | +| n_updates | 102800 | +| policy_gradient_loss | -0.067 | +| value_loss | 0.000815 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.44e+03 | +| ep_rew_mean | 0.00745 | +| time/ | | +| fps | 310 | +| iterations | 4229 | +| time_elapsed | 13967 | +| total_timesteps | 4330496 | +| train/ | | +| approx_kl | 1.7270253 | +| clip_fraction | 0.463 | +| clip_range | 0.2 | +| entropy_loss | -0.355 | +| explained_variance | -0.593 | +| learning_rate | 0.0001 | +| loss | -0.0963 | +| n_updates | 102810 | +| policy_gradient_loss | -0.0643 | +| value_loss | 0.000769 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.44e+03 | +| ep_rew_mean | 0.00323 | +| time/ | | +| fps | 310 | +| iterations | 4230 | +| time_elapsed | 13970 | +| total_timesteps | 4331520 | +| train/ | | +| approx_kl | 2.1136298 | +| clip_fraction | 0.457 | +| clip_range | 0.2 | +| entropy_loss | -0.349 | +| explained_variance | -1.68 | +| learning_rate | 0.0001 | +| loss | -0.0598 | +| n_updates | 102820 | +| policy_gradient_loss | -0.0632 | +| value_loss | 0.000529 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.44e+03 | +| ep_rew_mean | 0.00323 | +| time/ | | +| fps | 310 | +| iterations | 4231 | +| time_elapsed | 13974 | +| total_timesteps | 4332544 | +| train/ | | +| approx_kl | 1.9071604 | +| clip_fraction | 0.421 | +| clip_range | 0.2 | +| entropy_loss | -0.325 | +| explained_variance | -1.98 | +| learning_rate | 0.0001 | +| loss | -0.0857 | +| n_updates | 102830 | +| policy_gradient_loss | -0.0599 | +| value_loss | 0.000473 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.44e+03 | +| ep_rew_mean | 0.0037 | +| time/ | | +| fps | 310 | +| iterations | 4232 | +| time_elapsed | 13977 | +| total_timesteps | 4333568 | +| train/ | | +| approx_kl | 4.094217 | +| clip_fraction | 0.512 | +| clip_range | 0.2 | +| entropy_loss | -0.417 | +| explained_variance | -2 | +| learning_rate | 0.0001 | +| loss | -0.0562 | +| n_updates | 102840 | +| policy_gradient_loss | -0.0612 | +| value_loss | 0.000284 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.44e+03 | +| ep_rew_mean | 0.0037 | +| time/ | | +| fps | 310 | +| iterations | 4233 | +| time_elapsed | 13981 | +| total_timesteps | 4334592 | +| train/ | | +| approx_kl | 2.4206095 | +| clip_fraction | 0.458 | +| clip_range | 0.2 | +| entropy_loss | -0.377 | +| explained_variance | -2.91 | +| learning_rate | 0.0001 | +| loss | -0.0933 | +| n_updates | 102850 | +| policy_gradient_loss | -0.0481 | +| value_loss | 0.000363 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.45e+03 | +| ep_rew_mean | 0.00105 | +| time/ | | +| fps | 310 | +| iterations | 4234 | +| time_elapsed | 13984 | +| total_timesteps | 4335616 | +| train/ | | +| approx_kl | 1.8586738 | +| clip_fraction | 0.478 | +| clip_range | 0.2 | +| entropy_loss | -0.406 | +| explained_variance | -2.1 | +| learning_rate | 0.0001 | +| loss | -0.094 | +| n_updates | 102860 | +| policy_gradient_loss | -0.0593 | +| value_loss | 0.000436 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.45e+03 | +| ep_rew_mean | 0.00105 | +| time/ | | +| fps | 310 | +| iterations | 4235 | +| time_elapsed | 13988 | +| total_timesteps | 4336640 | +| train/ | | +| approx_kl | 1.7322733 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.425 | +| explained_variance | -0.696 | +| learning_rate | 0.0001 | +| loss | -0.106 | +| n_updates | 102870 | +| policy_gradient_loss | -0.0613 | +| value_loss | 0.000665 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.46e+03 | +| ep_rew_mean | 0.00475 | +| time/ | | +| fps | 310 | +| iterations | 4236 | +| time_elapsed | 13991 | +| total_timesteps | 4337664 | +| train/ | | +| approx_kl | 1.7169409 | +| clip_fraction | 0.479 | +| clip_range | 0.2 | +| entropy_loss | -0.37 | +| explained_variance | -5.05 | +| learning_rate | 0.0001 | +| loss | -0.0854 | +| n_updates | 102880 | +| policy_gradient_loss | -0.0687 | +| value_loss | 0.00049 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.46e+03 | +| ep_rew_mean | 0.00475 | +| time/ | | +| fps | 310 | +| iterations | 4237 | +| time_elapsed | 13994 | +| total_timesteps | 4338688 | +| train/ | | +| approx_kl | 2.1294818 | +| clip_fraction | 0.468 | +| clip_range | 0.2 | +| entropy_loss | -0.358 | +| explained_variance | -3.3 | +| learning_rate | 0.0001 | +| loss | -0.0799 | +| n_updates | 102890 | +| policy_gradient_loss | -0.0725 | +| value_loss | 0.000274 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.46e+03 | +| ep_rew_mean | 0.00817 | +| time/ | | +| fps | 310 | +| iterations | 4238 | +| time_elapsed | 13997 | +| total_timesteps | 4339712 | +| train/ | | +| approx_kl | 1.9595883 | +| clip_fraction | 0.493 | +| clip_range | 0.2 | +| entropy_loss | -0.453 | +| explained_variance | -0.765 | +| learning_rate | 0.0001 | +| loss | -0.0702 | +| n_updates | 102900 | +| policy_gradient_loss | -0.0634 | +| value_loss | 0.000315 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.46e+03 | +| ep_rew_mean | 0.00817 | +| time/ | | +| fps | 310 | +| iterations | 4239 | +| time_elapsed | 14001 | +| total_timesteps | 4340736 | +| train/ | | +| approx_kl | 2.5112634 | +| clip_fraction | 0.468 | +| clip_range | 0.2 | +| entropy_loss | -0.372 | +| explained_variance | -2.95 | +| learning_rate | 0.0001 | +| loss | -0.0816 | +| n_updates | 102910 | +| policy_gradient_loss | -0.0578 | +| value_loss | 0.00029 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.46e+03 | +| ep_rew_mean | 0.0062 | +| time/ | | +| fps | 310 | +| iterations | 4240 | +| time_elapsed | 14004 | +| total_timesteps | 4341760 | +| train/ | | +| approx_kl | 4.88291 | +| clip_fraction | 0.439 | +| clip_range | 0.2 | +| entropy_loss | -0.334 | +| explained_variance | -4.53 | +| learning_rate | 0.0001 | +| loss | -0.0901 | +| n_updates | 102920 | +| policy_gradient_loss | -0.0577 | +| value_loss | 0.000291 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.47e+03 | +| ep_rew_mean | 0.00949 | +| time/ | | +| fps | 310 | +| iterations | 4241 | +| time_elapsed | 14007 | +| total_timesteps | 4342784 | +| train/ | | +| approx_kl | 1.9638695 | +| clip_fraction | 0.468 | +| clip_range | 0.2 | +| entropy_loss | -0.382 | +| explained_variance | -2.17 | +| learning_rate | 0.0001 | +| loss | -0.0552 | +| n_updates | 102930 | +| policy_gradient_loss | -0.0604 | +| value_loss | 0.000357 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.47e+03 | +| ep_rew_mean | 0.00949 | +| time/ | | +| fps | 310 | +| iterations | 4242 | +| time_elapsed | 14010 | +| total_timesteps | 4343808 | +| train/ | | +| approx_kl | 1.6671999 | +| clip_fraction | 0.498 | +| clip_range | 0.2 | +| entropy_loss | -0.429 | +| explained_variance | -1.06 | +| learning_rate | 0.0001 | +| loss | -0.0998 | +| n_updates | 102940 | +| policy_gradient_loss | -0.0716 | +| value_loss | 0.000576 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.46e+03 | +| ep_rew_mean | 0.00862 | +| time/ | | +| fps | 310 | +| iterations | 4243 | +| time_elapsed | 14013 | +| total_timesteps | 4344832 | +| train/ | | +| approx_kl | 2.3901353 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.357 | +| explained_variance | -1.9 | +| learning_rate | 0.0001 | +| loss | -0.0919 | +| n_updates | 102950 | +| policy_gradient_loss | -0.0594 | +| value_loss | 0.000709 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.46e+03 | +| ep_rew_mean | 0.0106 | +| time/ | | +| fps | 310 | +| iterations | 4244 | +| time_elapsed | 14016 | +| total_timesteps | 4345856 | +| train/ | | +| approx_kl | 2.1687794 | +| clip_fraction | 0.462 | +| clip_range | 0.2 | +| entropy_loss | -0.349 | +| explained_variance | -1.23 | +| learning_rate | 0.0001 | +| loss | -0.109 | +| n_updates | 102960 | +| policy_gradient_loss | -0.0674 | +| value_loss | 0.000551 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.46e+03 | +| ep_rew_mean | 0.0106 | +| time/ | | +| fps | 310 | +| iterations | 4245 | +| time_elapsed | 14019 | +| total_timesteps | 4346880 | +| train/ | | +| approx_kl | 2.4990523 | +| clip_fraction | 0.485 | +| clip_range | 0.2 | +| entropy_loss | -0.405 | +| explained_variance | -1.13 | +| learning_rate | 0.0001 | +| loss | -0.0973 | +| n_updates | 102970 | +| policy_gradient_loss | -0.07 | +| value_loss | 0.000732 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.46e+03 | +| ep_rew_mean | 0.0118 | +| time/ | | +| fps | 310 | +| iterations | 4246 | +| time_elapsed | 14023 | +| total_timesteps | 4347904 | +| train/ | | +| approx_kl | 2.4191585 | +| clip_fraction | 0.49 | +| clip_range | 0.2 | +| entropy_loss | -0.393 | +| explained_variance | -1.43 | +| learning_rate | 0.0001 | +| loss | -0.0852 | +| n_updates | 102980 | +| policy_gradient_loss | -0.0614 | +| value_loss | 0.000454 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.47e+03 | +| ep_rew_mean | 0.0158 | +| time/ | | +| fps | 310 | +| iterations | 4247 | +| time_elapsed | 14026 | +| total_timesteps | 4348928 | +| train/ | | +| approx_kl | 2.0874925 | +| clip_fraction | 0.503 | +| clip_range | 0.2 | +| entropy_loss | -0.407 | +| explained_variance | -1.54 | +| learning_rate | 0.0001 | +| loss | -0.0365 | +| n_updates | 102990 | +| policy_gradient_loss | -0.0661 | +| value_loss | 0.000469 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.47e+03 | +| ep_rew_mean | 0.0158 | +| time/ | | +| fps | 310 | +| iterations | 4248 | +| time_elapsed | 14030 | +| total_timesteps | 4349952 | +| train/ | | +| approx_kl | 1.9608898 | +| clip_fraction | 0.506 | +| clip_range | 0.2 | +| entropy_loss | -0.424 | +| explained_variance | -1.08 | +| learning_rate | 0.0001 | +| loss | -0.0682 | +| n_updates | 103000 | +| policy_gradient_loss | -0.0693 | +| value_loss | 0.000489 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.47e+03 | +| ep_rew_mean | 0.0218 | +| time/ | | +| fps | 310 | +| iterations | 4249 | +| time_elapsed | 14033 | +| total_timesteps | 4350976 | +| train/ | | +| approx_kl | 1.7582254 | +| clip_fraction | 0.496 | +| clip_range | 0.2 | +| entropy_loss | -0.381 | +| explained_variance | -0.533 | +| learning_rate | 0.0001 | +| loss | -0.0981 | +| n_updates | 103010 | +| policy_gradient_loss | -0.0714 | +| value_loss | 0.000713 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.46e+03 | +| ep_rew_mean | 0.0203 | +| time/ | | +| fps | 310 | +| iterations | 4250 | +| time_elapsed | 14037 | +| total_timesteps | 4352000 | +| train/ | | +| approx_kl | 1.7641499 | +| clip_fraction | 0.474 | +| clip_range | 0.2 | +| entropy_loss | -0.406 | +| explained_variance | -5.45 | +| learning_rate | 0.0001 | +| loss | -0.09 | +| n_updates | 103020 | +| policy_gradient_loss | -0.0593 | +| value_loss | 0.000382 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.46e+03 | +| ep_rew_mean | 0.0208 | +| time/ | | +| fps | 310 | +| iterations | 4251 | +| time_elapsed | 14040 | +| total_timesteps | 4353024 | +| train/ | | +| approx_kl | 1.97883 | +| clip_fraction | 0.503 | +| clip_range | 0.2 | +| entropy_loss | -0.447 | +| explained_variance | -0.531 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 103030 | +| policy_gradient_loss | -0.068 | +| value_loss | 0.000311 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.45e+03 | +| ep_rew_mean | 0.0191 | +| time/ | | +| fps | 310 | +| iterations | 4252 | +| time_elapsed | 14044 | +| total_timesteps | 4354048 | +| train/ | | +| approx_kl | 2.2311468 | +| clip_fraction | 0.488 | +| clip_range | 0.2 | +| entropy_loss | -0.45 | +| explained_variance | -4.21 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 103040 | +| policy_gradient_loss | -0.0685 | +| value_loss | 0.000292 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.45e+03 | +| ep_rew_mean | 0.0191 | +| time/ | | +| fps | 310 | +| iterations | 4253 | +| time_elapsed | 14047 | +| total_timesteps | 4355072 | +| train/ | | +| approx_kl | 1.9474808 | +| clip_fraction | 0.506 | +| clip_range | 0.2 | +| entropy_loss | -0.42 | +| explained_variance | -0.988 | +| learning_rate | 0.0001 | +| loss | -0.0668 | +| n_updates | 103050 | +| policy_gradient_loss | -0.0566 | +| value_loss | 0.000314 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.45e+03 | +| ep_rew_mean | 0.0213 | +| time/ | | +| fps | 310 | +| iterations | 4254 | +| time_elapsed | 14051 | +| total_timesteps | 4356096 | +| train/ | | +| approx_kl | 1.8567685 | +| clip_fraction | 0.464 | +| clip_range | 0.2 | +| entropy_loss | -0.359 | +| explained_variance | -2.55 | +| learning_rate | 0.0001 | +| loss | -0.0882 | +| n_updates | 103060 | +| policy_gradient_loss | -0.0636 | +| value_loss | 0.000472 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.45e+03 | +| ep_rew_mean | 0.0222 | +| time/ | | +| fps | 310 | +| iterations | 4255 | +| time_elapsed | 14054 | +| total_timesteps | 4357120 | +| train/ | | +| approx_kl | 2.0226748 | +| clip_fraction | 0.515 | +| clip_range | 0.2 | +| entropy_loss | -0.428 | +| explained_variance | -1.24 | +| learning_rate | 0.0001 | +| loss | -0.1 | +| n_updates | 103070 | +| policy_gradient_loss | -0.0673 | +| value_loss | 0.000534 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.45e+03 | +| ep_rew_mean | 0.0214 | +| time/ | | +| fps | 310 | +| iterations | 4256 | +| time_elapsed | 14057 | +| total_timesteps | 4358144 | +| train/ | | +| approx_kl | 2.6036792 | +| clip_fraction | 0.494 | +| clip_range | 0.2 | +| entropy_loss | -0.409 | +| explained_variance | -2.14 | +| learning_rate | 0.0001 | +| loss | -0.0771 | +| n_updates | 103080 | +| policy_gradient_loss | -0.0671 | +| value_loss | 0.000619 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.45e+03 | +| ep_rew_mean | 0.0214 | +| time/ | | +| fps | 310 | +| iterations | 4257 | +| time_elapsed | 14060 | +| total_timesteps | 4359168 | +| train/ | | +| approx_kl | 2.3329463 | +| clip_fraction | 0.476 | +| clip_range | 0.2 | +| entropy_loss | -0.425 | +| explained_variance | -3.47 | +| learning_rate | 0.0001 | +| loss | -0.0628 | +| n_updates | 103090 | +| policy_gradient_loss | -0.0691 | +| value_loss | 0.000481 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.46e+03 | +| ep_rew_mean | 0.0206 | +| time/ | | +| fps | 310 | +| iterations | 4258 | +| time_elapsed | 14063 | +| total_timesteps | 4360192 | +| train/ | | +| approx_kl | 2.561059 | +| clip_fraction | 0.491 | +| clip_range | 0.2 | +| entropy_loss | -0.369 | +| explained_variance | -1.2 | +| learning_rate | 0.0001 | +| loss | -0.0534 | +| n_updates | 103100 | +| policy_gradient_loss | -0.0565 | +| value_loss | 0.000429 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.46e+03 | +| ep_rew_mean | 0.0206 | +| time/ | | +| fps | 310 | +| iterations | 4259 | +| time_elapsed | 14067 | +| total_timesteps | 4361216 | +| train/ | | +| approx_kl | 1.4571474 | +| clip_fraction | 0.456 | +| clip_range | 0.2 | +| entropy_loss | -0.391 | +| explained_variance | -4.13 | +| learning_rate | 0.0001 | +| loss | -0.0784 | +| n_updates | 103110 | +| policy_gradient_loss | -0.0659 | +| value_loss | 0.000278 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.45e+03 | +| ep_rew_mean | 0.0208 | +| time/ | | +| fps | 310 | +| iterations | 4260 | +| time_elapsed | 14070 | +| total_timesteps | 4362240 | +| train/ | | +| approx_kl | 2.390205 | +| clip_fraction | 0.485 | +| clip_range | 0.2 | +| entropy_loss | -0.357 | +| explained_variance | -0.907 | +| learning_rate | 0.0001 | +| loss | -0.107 | +| n_updates | 103120 | +| policy_gradient_loss | -0.0623 | +| value_loss | 0.000374 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.46e+03 | +| ep_rew_mean | 0.0248 | +| time/ | | +| fps | 310 | +| iterations | 4261 | +| time_elapsed | 14073 | +| total_timesteps | 4363264 | +| train/ | | +| approx_kl | 2.7346096 | +| clip_fraction | 0.447 | +| clip_range | 0.2 | +| entropy_loss | -0.325 | +| explained_variance | -1.08 | +| learning_rate | 0.0001 | +| loss | -0.0609 | +| n_updates | 103130 | +| policy_gradient_loss | -0.0644 | +| value_loss | 0.000465 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.46e+03 | +| ep_rew_mean | 0.0248 | +| time/ | | +| fps | 310 | +| iterations | 4262 | +| time_elapsed | 14076 | +| total_timesteps | 4364288 | +| train/ | | +| approx_kl | 2.140129 | +| clip_fraction | 0.462 | +| clip_range | 0.2 | +| entropy_loss | -0.374 | +| explained_variance | -4.21 | +| learning_rate | 0.0001 | +| loss | -0.0901 | +| n_updates | 103140 | +| policy_gradient_loss | -0.0703 | +| value_loss | 0.000442 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.46e+03 | +| ep_rew_mean | 0.0253 | +| time/ | | +| fps | 310 | +| iterations | 4263 | +| time_elapsed | 14080 | +| total_timesteps | 4365312 | +| train/ | | +| approx_kl | 2.4176533 | +| clip_fraction | 0.484 | +| clip_range | 0.2 | +| entropy_loss | -0.387 | +| explained_variance | -1.65 | +| learning_rate | 0.0001 | +| loss | -0.0887 | +| n_updates | 103150 | +| policy_gradient_loss | -0.0554 | +| value_loss | 0.000736 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.46e+03 | +| ep_rew_mean | 0.0264 | +| time/ | | +| fps | 310 | +| iterations | 4264 | +| time_elapsed | 14083 | +| total_timesteps | 4366336 | +| train/ | | +| approx_kl | 2.167438 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.359 | +| explained_variance | -4.74 | +| learning_rate | 0.0001 | +| loss | -0.0781 | +| n_updates | 103160 | +| policy_gradient_loss | -0.0639 | +| value_loss | 0.000396 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.46e+03 | +| ep_rew_mean | 0.0264 | +| time/ | | +| fps | 310 | +| iterations | 4265 | +| time_elapsed | 14086 | +| total_timesteps | 4367360 | +| train/ | | +| approx_kl | 2.38308 | +| clip_fraction | 0.472 | +| clip_range | 0.2 | +| entropy_loss | -0.368 | +| explained_variance | -1.28 | +| learning_rate | 0.0001 | +| loss | -0.0973 | +| n_updates | 103170 | +| policy_gradient_loss | -0.0609 | +| value_loss | 0.000537 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.47e+03 | +| ep_rew_mean | 0.0263 | +| time/ | | +| fps | 310 | +| iterations | 4266 | +| time_elapsed | 14090 | +| total_timesteps | 4368384 | +| train/ | | +| approx_kl | 2.383361 | +| clip_fraction | 0.477 | +| clip_range | 0.2 | +| entropy_loss | -0.365 | +| explained_variance | -1.41 | +| learning_rate | 0.0001 | +| loss | -0.0928 | +| n_updates | 103180 | +| policy_gradient_loss | -0.0628 | +| value_loss | 0.00047 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.47e+03 | +| ep_rew_mean | 0.0263 | +| time/ | | +| fps | 310 | +| iterations | 4267 | +| time_elapsed | 14093 | +| total_timesteps | 4369408 | +| train/ | | +| approx_kl | 2.4251401 | +| clip_fraction | 0.461 | +| clip_range | 0.2 | +| entropy_loss | -0.354 | +| explained_variance | -1.96 | +| learning_rate | 0.0001 | +| loss | -0.0997 | +| n_updates | 103190 | +| policy_gradient_loss | -0.0729 | +| value_loss | 0.000471 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.47e+03 | +| ep_rew_mean | 0.0282 | +| time/ | | +| fps | 310 | +| iterations | 4268 | +| time_elapsed | 14096 | +| total_timesteps | 4370432 | +| train/ | | +| approx_kl | 2.0497456 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.361 | +| explained_variance | -1.29 | +| learning_rate | 0.0001 | +| loss | -0.106 | +| n_updates | 103200 | +| policy_gradient_loss | -0.0738 | +| value_loss | 0.000458 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.46e+03 | +| ep_rew_mean | 0.0266 | +| time/ | | +| fps | 310 | +| iterations | 4269 | +| time_elapsed | 14100 | +| total_timesteps | 4371456 | +| train/ | | +| approx_kl | 1.9851785 | +| clip_fraction | 0.452 | +| clip_range | 0.2 | +| entropy_loss | -0.327 | +| explained_variance | -3.86 | +| learning_rate | 0.0001 | +| loss | -0.0986 | +| n_updates | 103210 | +| policy_gradient_loss | -0.0706 | +| value_loss | 0.000538 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.46e+03 | +| ep_rew_mean | 0.0266 | +| time/ | | +| fps | 310 | +| iterations | 4270 | +| time_elapsed | 14103 | +| total_timesteps | 4372480 | +| train/ | | +| approx_kl | 1.9184858 | +| clip_fraction | 0.477 | +| clip_range | 0.2 | +| entropy_loss | -0.389 | +| explained_variance | -0.807 | +| learning_rate | 0.0001 | +| loss | -0.0596 | +| n_updates | 103220 | +| policy_gradient_loss | -0.0536 | +| value_loss | 0.000779 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.47e+03 | +| ep_rew_mean | 0.0272 | +| time/ | | +| fps | 310 | +| iterations | 4271 | +| time_elapsed | 14107 | +| total_timesteps | 4373504 | +| train/ | | +| approx_kl | 2.2611637 | +| clip_fraction | 0.461 | +| clip_range | 0.2 | +| entropy_loss | -0.339 | +| explained_variance | -4.89 | +| learning_rate | 0.0001 | +| loss | -0.0924 | +| n_updates | 103230 | +| policy_gradient_loss | -0.0623 | +| value_loss | 0.000593 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.47e+03 | +| ep_rew_mean | 0.0272 | +| time/ | | +| fps | 310 | +| iterations | 4272 | +| time_elapsed | 14110 | +| total_timesteps | 4374528 | +| train/ | | +| approx_kl | 2.0053725 | +| clip_fraction | 0.436 | +| clip_range | 0.2 | +| entropy_loss | -0.342 | +| explained_variance | -4.07 | +| learning_rate | 0.0001 | +| loss | -0.0879 | +| n_updates | 103240 | +| policy_gradient_loss | -0.0615 | +| value_loss | 0.000329 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.47e+03 | +| ep_rew_mean | 0.0269 | +| time/ | | +| fps | 310 | +| iterations | 4273 | +| time_elapsed | 14113 | +| total_timesteps | 4375552 | +| train/ | | +| approx_kl | 2.4750075 | +| clip_fraction | 0.445 | +| clip_range | 0.2 | +| entropy_loss | -0.342 | +| explained_variance | -0.912 | +| learning_rate | 0.0001 | +| loss | -0.0666 | +| n_updates | 103250 | +| policy_gradient_loss | -0.0565 | +| value_loss | 0.00066 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.47e+03 | +| ep_rew_mean | 0.0259 | +| time/ | | +| fps | 310 | +| iterations | 4274 | +| time_elapsed | 14116 | +| total_timesteps | 4376576 | +| train/ | | +| approx_kl | 5.5785036 | +| clip_fraction | 0.434 | +| clip_range | 0.2 | +| entropy_loss | -0.337 | +| explained_variance | -6.11 | +| learning_rate | 0.0001 | +| loss | -0.0735 | +| n_updates | 103260 | +| policy_gradient_loss | -0.0581 | +| value_loss | 0.000427 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.47e+03 | +| ep_rew_mean | 0.0259 | +| time/ | | +| fps | 310 | +| iterations | 4275 | +| time_elapsed | 14119 | +| total_timesteps | 4377600 | +| train/ | | +| approx_kl | 1.4974301 | +| clip_fraction | 0.433 | +| clip_range | 0.2 | +| entropy_loss | -0.365 | +| explained_variance | -1.39 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 103270 | +| policy_gradient_loss | -0.0591 | +| value_loss | 0.000352 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.47e+03 | +| ep_rew_mean | 0.0251 | +| time/ | | +| fps | 310 | +| iterations | 4276 | +| time_elapsed | 14123 | +| total_timesteps | 4378624 | +| train/ | | +| approx_kl | 2.308104 | +| clip_fraction | 0.45 | +| clip_range | 0.2 | +| entropy_loss | -0.299 | +| explained_variance | -2.01 | +| learning_rate | 0.0001 | +| loss | -0.0738 | +| n_updates | 103280 | +| policy_gradient_loss | -0.064 | +| value_loss | 0.000489 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.47e+03 | +| ep_rew_mean | 0.0251 | +| time/ | | +| fps | 310 | +| iterations | 4277 | +| time_elapsed | 14126 | +| total_timesteps | 4379648 | +| train/ | | +| approx_kl | 1.7301991 | +| clip_fraction | 0.447 | +| clip_range | 0.2 | +| entropy_loss | -0.36 | +| explained_variance | -3.75 | +| learning_rate | 0.0001 | +| loss | -0.0683 | +| n_updates | 103290 | +| policy_gradient_loss | -0.0495 | +| value_loss | 0.000414 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.47e+03 | +| ep_rew_mean | 0.0251 | +| time/ | | +| fps | 310 | +| iterations | 4278 | +| time_elapsed | 14129 | +| total_timesteps | 4380672 | +| train/ | | +| approx_kl | 1.9879997 | +| clip_fraction | 0.453 | +| clip_range | 0.2 | +| entropy_loss | -0.375 | +| explained_variance | -1.34 | +| learning_rate | 0.0001 | +| loss | -0.0796 | +| n_updates | 103300 | +| policy_gradient_loss | -0.0579 | +| value_loss | 0.000244 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.47e+03 | +| ep_rew_mean | 0.0262 | +| time/ | | +| fps | 310 | +| iterations | 4279 | +| time_elapsed | 14132 | +| total_timesteps | 4381696 | +| train/ | | +| approx_kl | 2.0506337 | +| clip_fraction | 0.508 | +| clip_range | 0.2 | +| entropy_loss | -0.416 | +| explained_variance | -0.488 | +| learning_rate | 0.0001 | +| loss | -0.0634 | +| n_updates | 103310 | +| policy_gradient_loss | -0.0583 | +| value_loss | 0.000545 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.47e+03 | +| ep_rew_mean | 0.0262 | +| time/ | | +| fps | 310 | +| iterations | 4280 | +| time_elapsed | 14135 | +| total_timesteps | 4382720 | +| train/ | | +| approx_kl | 1.9340686 | +| clip_fraction | 0.447 | +| clip_range | 0.2 | +| entropy_loss | -0.344 | +| explained_variance | -2.16 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 103320 | +| policy_gradient_loss | -0.0484 | +| value_loss | 0.000715 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.48e+03 | +| ep_rew_mean | 0.029 | +| time/ | | +| fps | 310 | +| iterations | 4281 | +| time_elapsed | 14138 | +| total_timesteps | 4383744 | +| train/ | | +| approx_kl | 2.4570386 | +| clip_fraction | 0.514 | +| clip_range | 0.2 | +| entropy_loss | -0.413 | +| explained_variance | -1.66 | +| learning_rate | 0.0001 | +| loss | -0.114 | +| n_updates | 103330 | +| policy_gradient_loss | -0.0683 | +| value_loss | 0.0006 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.49e+03 | +| ep_rew_mean | 0.0303 | +| time/ | | +| fps | 310 | +| iterations | 4282 | +| time_elapsed | 14142 | +| total_timesteps | 4384768 | +| train/ | | +| approx_kl | 1.7200621 | +| clip_fraction | 0.436 | +| clip_range | 0.2 | +| entropy_loss | -0.352 | +| explained_variance | -2.61 | +| learning_rate | 0.0001 | +| loss | -0.0653 | +| n_updates | 103340 | +| policy_gradient_loss | -0.059 | +| value_loss | 0.0009 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.48e+03 | +| ep_rew_mean | 0.0299 | +| time/ | | +| fps | 310 | +| iterations | 4283 | +| time_elapsed | 14145 | +| total_timesteps | 4385792 | +| train/ | | +| approx_kl | 1.6445827 | +| clip_fraction | 0.442 | +| clip_range | 0.2 | +| entropy_loss | -0.352 | +| explained_variance | -1.11 | +| learning_rate | 0.0001 | +| loss | -0.0632 | +| n_updates | 103350 | +| policy_gradient_loss | -0.0533 | +| value_loss | 0.000535 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.48e+03 | +| ep_rew_mean | 0.0299 | +| time/ | | +| fps | 310 | +| iterations | 4284 | +| time_elapsed | 14149 | +| total_timesteps | 4386816 | +| train/ | | +| approx_kl | 2.2442026 | +| clip_fraction | 0.476 | +| clip_range | 0.2 | +| entropy_loss | -0.388 | +| explained_variance | -2.21 | +| learning_rate | 0.0001 | +| loss | -0.0607 | +| n_updates | 103360 | +| policy_gradient_loss | -0.0608 | +| value_loss | 0.000451 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.49e+03 | +| ep_rew_mean | 0.0308 | +| time/ | | +| fps | 310 | +| iterations | 4285 | +| time_elapsed | 14152 | +| total_timesteps | 4387840 | +| train/ | | +| approx_kl | 2.5678272 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.378 | +| explained_variance | -2.15 | +| learning_rate | 0.0001 | +| loss | -0.0847 | +| n_updates | 103370 | +| policy_gradient_loss | -0.0649 | +| value_loss | 0.000587 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.49e+03 | +| ep_rew_mean | 0.0308 | +| time/ | | +| fps | 310 | +| iterations | 4286 | +| time_elapsed | 14156 | +| total_timesteps | 4388864 | +| train/ | | +| approx_kl | 1.7905996 | +| clip_fraction | 0.448 | +| clip_range | 0.2 | +| entropy_loss | -0.351 | +| explained_variance | -2.03 | +| learning_rate | 0.0001 | +| loss | -0.0945 | +| n_updates | 103380 | +| policy_gradient_loss | -0.0589 | +| value_loss | 0.000518 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.49e+03 | +| ep_rew_mean | 0.0308 | +| time/ | | +| fps | 310 | +| iterations | 4287 | +| time_elapsed | 14159 | +| total_timesteps | 4389888 | +| train/ | | +| approx_kl | 2.0692015 | +| clip_fraction | 0.478 | +| clip_range | 0.2 | +| entropy_loss | -0.397 | +| explained_variance | -1.57 | +| learning_rate | 0.0001 | +| loss | -0.0908 | +| n_updates | 103390 | +| policy_gradient_loss | -0.0632 | +| value_loss | 0.000443 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.49e+03 | +| ep_rew_mean | 0.0336 | +| time/ | | +| fps | 310 | +| iterations | 4288 | +| time_elapsed | 14163 | +| total_timesteps | 4390912 | +| train/ | | +| approx_kl | 2.1293354 | +| clip_fraction | 0.485 | +| clip_range | 0.2 | +| entropy_loss | -0.367 | +| explained_variance | -3.51 | +| learning_rate | 0.0001 | +| loss | -0.109 | +| n_updates | 103400 | +| policy_gradient_loss | -0.0653 | +| value_loss | 0.000325 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.49e+03 | +| ep_rew_mean | 0.0349 | +| time/ | | +| fps | 310 | +| iterations | 4289 | +| time_elapsed | 14166 | +| total_timesteps | 4391936 | +| train/ | | +| approx_kl | 2.921865 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.314 | +| explained_variance | -1.27 | +| learning_rate | 0.0001 | +| loss | -0.0608 | +| n_updates | 103410 | +| policy_gradient_loss | -0.0596 | +| value_loss | 0.000596 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.49e+03 | +| ep_rew_mean | 0.0317 | +| time/ | | +| fps | 310 | +| iterations | 4290 | +| time_elapsed | 14170 | +| total_timesteps | 4392960 | +| train/ | | +| approx_kl | 3.4959664 | +| clip_fraction | 0.444 | +| clip_range | 0.2 | +| entropy_loss | -0.295 | +| explained_variance | -2.52 | +| learning_rate | 0.0001 | +| loss | -0.0906 | +| n_updates | 103420 | +| policy_gradient_loss | -0.0666 | +| value_loss | 0.000831 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.48e+03 | +| ep_rew_mean | 0.0315 | +| time/ | | +| fps | 310 | +| iterations | 4291 | +| time_elapsed | 14173 | +| total_timesteps | 4393984 | +| train/ | | +| approx_kl | 2.006319 | +| clip_fraction | 0.445 | +| clip_range | 0.2 | +| entropy_loss | -0.32 | +| explained_variance | -0.984 | +| learning_rate | 0.0001 | +| loss | -0.107 | +| n_updates | 103430 | +| policy_gradient_loss | -0.0639 | +| value_loss | 0.000947 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.48e+03 | +| ep_rew_mean | 0.0323 | +| time/ | | +| fps | 310 | +| iterations | 4292 | +| time_elapsed | 14176 | +| total_timesteps | 4395008 | +| train/ | | +| approx_kl | 2.0204854 | +| clip_fraction | 0.461 | +| clip_range | 0.2 | +| entropy_loss | -0.348 | +| explained_variance | -1.63 | +| learning_rate | 0.0001 | +| loss | -0.0621 | +| n_updates | 103440 | +| policy_gradient_loss | -0.0596 | +| value_loss | 0.000714 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.48e+03 | +| ep_rew_mean | 0.0323 | +| time/ | | +| fps | 310 | +| iterations | 4293 | +| time_elapsed | 14179 | +| total_timesteps | 4396032 | +| train/ | | +| approx_kl | 2.4367793 | +| clip_fraction | 0.488 | +| clip_range | 0.2 | +| entropy_loss | -0.34 | +| explained_variance | -1.19 | +| learning_rate | 0.0001 | +| loss | -0.0934 | +| n_updates | 103450 | +| policy_gradient_loss | -0.0622 | +| value_loss | 0.000572 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.49e+03 | +| ep_rew_mean | 0.0345 | +| time/ | | +| fps | 310 | +| iterations | 4294 | +| time_elapsed | 14182 | +| total_timesteps | 4397056 | +| train/ | | +| approx_kl | 1.9952438 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.381 | +| explained_variance | -3.79 | +| learning_rate | 0.0001 | +| loss | -0.0751 | +| n_updates | 103460 | +| policy_gradient_loss | -0.0588 | +| value_loss | 0.000423 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.49e+03 | +| ep_rew_mean | 0.0317 | +| time/ | | +| fps | 310 | +| iterations | 4295 | +| time_elapsed | 14186 | +| total_timesteps | 4398080 | +| train/ | | +| approx_kl | 1.7478056 | +| clip_fraction | 0.44 | +| clip_range | 0.2 | +| entropy_loss | -0.352 | +| explained_variance | -1.78 | +| learning_rate | 0.0001 | +| loss | -0.0845 | +| n_updates | 103470 | +| policy_gradient_loss | -0.0313 | +| value_loss | 0.00033 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.49e+03 | +| ep_rew_mean | 0.0315 | +| time/ | | +| fps | 310 | +| iterations | 4296 | +| time_elapsed | 14189 | +| total_timesteps | 4399104 | +| train/ | | +| approx_kl | 1.8822134 | +| clip_fraction | 0.431 | +| clip_range | 0.2 | +| entropy_loss | -0.307 | +| explained_variance | -1.58 | +| learning_rate | 0.0001 | +| loss | -0.0478 | +| n_updates | 103480 | +| policy_gradient_loss | -0.054 | +| value_loss | 0.00036 | +--------------------------------------- + +Current state: Champion.Level12.RyuVsBison +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.49e+03 | +| ep_rew_mean | 0.0315 | +| time/ | | +| fps | 310 | +| iterations | 4297 | +| time_elapsed | 14192 | +| total_timesteps | 4400128 | +| train/ | | +| approx_kl | 2.158697 | +| clip_fraction | 0.465 | +| clip_range | 0.2 | +| entropy_loss | -0.39 | +| explained_variance | -1.75 | +| learning_rate | 0.0001 | +| loss | -0.0821 | +| n_updates | 103490 | +| policy_gradient_loss | -0.0586 | +| value_loss | 0.000574 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.49e+03 | +| ep_rew_mean | 0.0294 | +| time/ | | +| fps | 310 | +| iterations | 4298 | +| time_elapsed | 14195 | +| total_timesteps | 4401152 | +| train/ | | +| approx_kl | 3.0520296 | +| clip_fraction | 0.463 | +| clip_range | 0.2 | +| entropy_loss | -0.293 | +| explained_variance | -1.99 | +| learning_rate | 0.0001 | +| loss | -0.0939 | +| n_updates | 103500 | +| policy_gradient_loss | -0.0655 | +| value_loss | 0.000493 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.49e+03 | +| ep_rew_mean | 0.0294 | +| time/ | | +| fps | 310 | +| iterations | 4299 | +| time_elapsed | 14199 | +| total_timesteps | 4402176 | +| train/ | | +| approx_kl | 2.5631087 | +| clip_fraction | 0.445 | +| clip_range | 0.2 | +| entropy_loss | -0.291 | +| explained_variance | -3.15 | +| learning_rate | 0.0001 | +| loss | -0.0913 | +| n_updates | 103510 | +| policy_gradient_loss | -0.0581 | +| value_loss | 0.000616 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.49e+03 | +| ep_rew_mean | 0.0382 | +| time/ | | +| fps | 310 | +| iterations | 4300 | +| time_elapsed | 14202 | +| total_timesteps | 4403200 | +| train/ | | +| approx_kl | 3.0502014 | +| clip_fraction | 0.461 | +| clip_range | 0.2 | +| entropy_loss | -0.25 | +| explained_variance | -0.786 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 103520 | +| policy_gradient_loss | -0.0593 | +| value_loss | 0.000691 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.5e+03 | +| ep_rew_mean | 0.0416 | +| time/ | | +| fps | 310 | +| iterations | 4301 | +| time_elapsed | 14205 | +| total_timesteps | 4404224 | +| train/ | | +| approx_kl | 3.2566717 | +| clip_fraction | 0.43 | +| clip_range | 0.2 | +| entropy_loss | -0.229 | +| explained_variance | -1.93 | +| learning_rate | 0.0001 | +| loss | -0.07 | +| n_updates | 103530 | +| policy_gradient_loss | -0.0577 | +| value_loss | 0.000859 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.49e+03 | +| ep_rew_mean | 0.0429 | +| time/ | | +| fps | 310 | +| iterations | 4302 | +| time_elapsed | 14209 | +| total_timesteps | 4405248 | +| train/ | | +| approx_kl | 3.1475263 | +| clip_fraction | 0.428 | +| clip_range | 0.2 | +| entropy_loss | -0.218 | +| explained_variance | -1.26 | +| learning_rate | 0.0001 | +| loss | -0.0765 | +| n_updates | 103540 | +| policy_gradient_loss | -0.0627 | +| value_loss | 0.00103 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.49e+03 | +| ep_rew_mean | 0.0464 | +| time/ | | +| fps | 310 | +| iterations | 4303 | +| time_elapsed | 14212 | +| total_timesteps | 4406272 | +| train/ | | +| approx_kl | 4.158456 | +| clip_fraction | 0.403 | +| clip_range | 0.2 | +| entropy_loss | -0.207 | +| explained_variance | -2.51 | +| learning_rate | 0.0001 | +| loss | -0.0831 | +| n_updates | 103550 | +| policy_gradient_loss | -0.056 | +| value_loss | 0.000611 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.49e+03 | +| ep_rew_mean | 0.0464 | +| time/ | | +| fps | 310 | +| iterations | 4304 | +| time_elapsed | 14215 | +| total_timesteps | 4407296 | +| train/ | | +| approx_kl | 2.6743603 | +| clip_fraction | 0.4 | +| clip_range | 0.2 | +| entropy_loss | -0.23 | +| explained_variance | -0.777 | +| learning_rate | 0.0001 | +| loss | -0.0797 | +| n_updates | 103560 | +| policy_gradient_loss | -0.0496 | +| value_loss | 0.00066 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.5e+03 | +| ep_rew_mean | 0.0525 | +| time/ | | +| fps | 310 | +| iterations | 4305 | +| time_elapsed | 14219 | +| total_timesteps | 4408320 | +| train/ | | +| approx_kl | 2.6594336 | +| clip_fraction | 0.428 | +| clip_range | 0.2 | +| entropy_loss | -0.225 | +| explained_variance | -0.888 | +| learning_rate | 0.0001 | +| loss | -0.0903 | +| n_updates | 103570 | +| policy_gradient_loss | -0.0457 | +| value_loss | 0.000563 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.49e+03 | +| ep_rew_mean | 0.0507 | +| time/ | | +| fps | 310 | +| iterations | 4306 | +| time_elapsed | 14222 | +| total_timesteps | 4409344 | +| train/ | | +| approx_kl | 3.530409 | +| clip_fraction | 0.399 | +| clip_range | 0.2 | +| entropy_loss | -0.201 | +| explained_variance | -0.398 | +| learning_rate | 0.0001 | +| loss | -0.018 | +| n_updates | 103580 | +| policy_gradient_loss | -0.0399 | +| value_loss | 0.000522 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.49e+03 | +| ep_rew_mean | 0.0514 | +| time/ | | +| fps | 310 | +| iterations | 4307 | +| time_elapsed | 14225 | +| total_timesteps | 4410368 | +| train/ | | +| approx_kl | 2.9193158 | +| clip_fraction | 0.398 | +| clip_range | 0.2 | +| entropy_loss | -0.224 | +| explained_variance | -1.98 | +| learning_rate | 0.0001 | +| loss | -0.0661 | +| n_updates | 103590 | +| policy_gradient_loss | -0.052 | +| value_loss | 0.000612 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.49e+03 | +| ep_rew_mean | 0.0574 | +| time/ | | +| fps | 310 | +| iterations | 4308 | +| time_elapsed | 14229 | +| total_timesteps | 4411392 | +| train/ | | +| approx_kl | 3.0696626 | +| clip_fraction | 0.398 | +| clip_range | 0.2 | +| entropy_loss | -0.206 | +| explained_variance | -1.15 | +| learning_rate | 0.0001 | +| loss | -0.0802 | +| n_updates | 103600 | +| policy_gradient_loss | -0.0484 | +| value_loss | 0.000768 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.49e+03 | +| ep_rew_mean | 0.0638 | +| time/ | | +| fps | 310 | +| iterations | 4309 | +| time_elapsed | 14232 | +| total_timesteps | 4412416 | +| train/ | | +| approx_kl | 3.3055153 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.297 | +| explained_variance | -1.32 | +| learning_rate | 0.0001 | +| loss | -0.0927 | +| n_updates | 103610 | +| policy_gradient_loss | -0.0581 | +| value_loss | 0.000769 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.49e+03 | +| ep_rew_mean | 0.0638 | +| time/ | | +| fps | 310 | +| iterations | 4310 | +| time_elapsed | 14235 | +| total_timesteps | 4413440 | +| train/ | | +| approx_kl | 2.1216507 | +| clip_fraction | 0.45 | +| clip_range | 0.2 | +| entropy_loss | -0.352 | +| explained_variance | -0.464 | +| learning_rate | 0.0001 | +| loss | -0.0765 | +| n_updates | 103620 | +| policy_gradient_loss | -0.048 | +| value_loss | 0.000971 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.49e+03 | +| ep_rew_mean | 0.0704 | +| time/ | | +| fps | 310 | +| iterations | 4311 | +| time_elapsed | 14238 | +| total_timesteps | 4414464 | +| train/ | | +| approx_kl | 2.823704 | +| clip_fraction | 0.446 | +| clip_range | 0.2 | +| entropy_loss | -0.246 | +| explained_variance | -2.66 | +| learning_rate | 0.0001 | +| loss | -0.0864 | +| n_updates | 103630 | +| policy_gradient_loss | -0.0639 | +| value_loss | 0.000672 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.49e+03 | +| ep_rew_mean | 0.0704 | +| time/ | | +| fps | 310 | +| iterations | 4312 | +| time_elapsed | 14241 | +| total_timesteps | 4415488 | +| train/ | | +| approx_kl | 3.1612241 | +| clip_fraction | 0.422 | +| clip_range | 0.2 | +| entropy_loss | -0.232 | +| explained_variance | -1.04 | +| learning_rate | 0.0001 | +| loss | -0.0757 | +| n_updates | 103640 | +| policy_gradient_loss | -0.0533 | +| value_loss | 0.000831 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.49e+03 | +| ep_rew_mean | 0.074 | +| time/ | | +| fps | 310 | +| iterations | 4313 | +| time_elapsed | 14245 | +| total_timesteps | 4416512 | +| train/ | | +| approx_kl | 2.8665347 | +| clip_fraction | 0.443 | +| clip_range | 0.2 | +| entropy_loss | -0.252 | +| explained_variance | -2.22 | +| learning_rate | 0.0001 | +| loss | -0.0849 | +| n_updates | 103650 | +| policy_gradient_loss | -0.0637 | +| value_loss | 0.000721 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.48e+03 | +| ep_rew_mean | 0.0798 | +| time/ | | +| fps | 310 | +| iterations | 4314 | +| time_elapsed | 14248 | +| total_timesteps | 4417536 | +| train/ | | +| approx_kl | 3.1219342 | +| clip_fraction | 0.442 | +| clip_range | 0.2 | +| entropy_loss | -0.257 | +| explained_variance | -0.847 | +| learning_rate | 0.0001 | +| loss | -0.0578 | +| n_updates | 103660 | +| policy_gradient_loss | -0.0578 | +| value_loss | 0.000712 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.48e+03 | +| ep_rew_mean | 0.0817 | +| time/ | | +| fps | 310 | +| iterations | 4315 | +| time_elapsed | 14251 | +| total_timesteps | 4418560 | +| train/ | | +| approx_kl | 2.642686 | +| clip_fraction | 0.403 | +| clip_range | 0.2 | +| entropy_loss | -0.227 | +| explained_variance | -1.37 | +| learning_rate | 0.0001 | +| loss | -0.0551 | +| n_updates | 103670 | +| policy_gradient_loss | -0.0569 | +| value_loss | 0.000988 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.47e+03 | +| ep_rew_mean | 0.0843 | +| time/ | | +| fps | 310 | +| iterations | 4316 | +| time_elapsed | 14254 | +| total_timesteps | 4419584 | +| train/ | | +| approx_kl | 2.8187575 | +| clip_fraction | 0.413 | +| clip_range | 0.2 | +| entropy_loss | -0.219 | +| explained_variance | -1.38 | +| learning_rate | 0.0001 | +| loss | -0.0812 | +| n_updates | 103680 | +| policy_gradient_loss | -0.0421 | +| value_loss | 0.000745 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.47e+03 | +| ep_rew_mean | 0.0844 | +| time/ | | +| fps | 310 | +| iterations | 4317 | +| time_elapsed | 14257 | +| total_timesteps | 4420608 | +| train/ | | +| approx_kl | 2.2845016 | +| clip_fraction | 0.416 | +| clip_range | 0.2 | +| entropy_loss | -0.243 | +| explained_variance | -1.09 | +| learning_rate | 0.0001 | +| loss | -0.0574 | +| n_updates | 103690 | +| policy_gradient_loss | -0.0464 | +| value_loss | 0.000578 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.47e+03 | +| ep_rew_mean | 0.0844 | +| time/ | | +| fps | 310 | +| iterations | 4318 | +| time_elapsed | 14261 | +| total_timesteps | 4421632 | +| train/ | | +| approx_kl | 2.9001844 | +| clip_fraction | 0.432 | +| clip_range | 0.2 | +| entropy_loss | -0.216 | +| explained_variance | -3.18 | +| learning_rate | 0.0001 | +| loss | -0.0382 | +| n_updates | 103700 | +| policy_gradient_loss | -0.0474 | +| value_loss | 0.000527 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.47e+03 | +| ep_rew_mean | 0.0885 | +| time/ | | +| fps | 310 | +| iterations | 4319 | +| time_elapsed | 14264 | +| total_timesteps | 4422656 | +| train/ | | +| approx_kl | 2.7413783 | +| clip_fraction | 0.435 | +| clip_range | 0.2 | +| entropy_loss | -0.246 | +| explained_variance | -1.14 | +| learning_rate | 0.0001 | +| loss | -0.0646 | +| n_updates | 103710 | +| policy_gradient_loss | -0.0555 | +| value_loss | 0.000641 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.46e+03 | +| ep_rew_mean | 0.0927 | +| time/ | | +| fps | 310 | +| iterations | 4320 | +| time_elapsed | 14268 | +| total_timesteps | 4423680 | +| train/ | | +| approx_kl | 2.6613607 | +| clip_fraction | 0.391 | +| clip_range | 0.2 | +| entropy_loss | -0.2 | +| explained_variance | -1.77 | +| learning_rate | 0.0001 | +| loss | -0.0671 | +| n_updates | 103720 | +| policy_gradient_loss | -0.0567 | +| value_loss | 0.000753 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.46e+03 | +| ep_rew_mean | 0.0949 | +| time/ | | +| fps | 310 | +| iterations | 4321 | +| time_elapsed | 14271 | +| total_timesteps | 4424704 | +| train/ | | +| approx_kl | 2.4961314 | +| clip_fraction | 0.416 | +| clip_range | 0.2 | +| entropy_loss | -0.255 | +| explained_variance | -0.99 | +| learning_rate | 0.0001 | +| loss | -0.0876 | +| n_updates | 103730 | +| policy_gradient_loss | -0.0517 | +| value_loss | 0.000735 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.46e+03 | +| ep_rew_mean | 0.0949 | +| time/ | | +| fps | 310 | +| iterations | 4322 | +| time_elapsed | 14275 | +| total_timesteps | 4425728 | +| train/ | | +| approx_kl | 2.5227885 | +| clip_fraction | 0.402 | +| clip_range | 0.2 | +| entropy_loss | -0.21 | +| explained_variance | -2.1 | +| learning_rate | 0.0001 | +| loss | -0.0709 | +| n_updates | 103740 | +| policy_gradient_loss | -0.0625 | +| value_loss | 0.000884 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.46e+03 | +| ep_rew_mean | 0.0945 | +| time/ | | +| fps | 310 | +| iterations | 4323 | +| time_elapsed | 14278 | +| total_timesteps | 4426752 | +| train/ | | +| approx_kl | 3.265893 | +| clip_fraction | 0.425 | +| clip_range | 0.2 | +| entropy_loss | -0.255 | +| explained_variance | -2.04 | +| learning_rate | 0.0001 | +| loss | -0.0803 | +| n_updates | 103750 | +| policy_gradient_loss | -0.0536 | +| value_loss | 0.000613 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.46e+03 | +| ep_rew_mean | 0.0973 | +| time/ | | +| fps | 310 | +| iterations | 4324 | +| time_elapsed | 14282 | +| total_timesteps | 4427776 | +| train/ | | +| approx_kl | 2.7461114 | +| clip_fraction | 0.366 | +| clip_range | 0.2 | +| entropy_loss | -0.191 | +| explained_variance | -1.54 | +| learning_rate | 0.0001 | +| loss | -0.0583 | +| n_updates | 103760 | +| policy_gradient_loss | -0.052 | +| value_loss | 0.000703 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.46e+03 | +| ep_rew_mean | 0.0998 | +| time/ | | +| fps | 310 | +| iterations | 4325 | +| time_elapsed | 14285 | +| total_timesteps | 4428800 | +| train/ | | +| approx_kl | 2.7550511 | +| clip_fraction | 0.407 | +| clip_range | 0.2 | +| entropy_loss | -0.207 | +| explained_variance | -2.18 | +| learning_rate | 0.0001 | +| loss | -0.0728 | +| n_updates | 103770 | +| policy_gradient_loss | -0.0581 | +| value_loss | 0.000498 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.46e+03 | +| ep_rew_mean | 0.101 | +| time/ | | +| fps | 310 | +| iterations | 4326 | +| time_elapsed | 14289 | +| total_timesteps | 4429824 | +| train/ | | +| approx_kl | 2.9980922 | +| clip_fraction | 0.38 | +| clip_range | 0.2 | +| entropy_loss | -0.189 | +| explained_variance | -0.663 | +| learning_rate | 0.0001 | +| loss | -0.055 | +| n_updates | 103780 | +| policy_gradient_loss | -0.0526 | +| value_loss | 0.000942 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.45e+03 | +| ep_rew_mean | 0.0995 | +| time/ | | +| fps | 310 | +| iterations | 4327 | +| time_elapsed | 14292 | +| total_timesteps | 4430848 | +| train/ | | +| approx_kl | 3.0704644 | +| clip_fraction | 0.423 | +| clip_range | 0.2 | +| entropy_loss | -0.254 | +| explained_variance | -0.816 | +| learning_rate | 0.0001 | +| loss | -0.0817 | +| n_updates | 103790 | +| policy_gradient_loss | -0.0461 | +| value_loss | 0.000537 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.45e+03 | +| ep_rew_mean | 0.0989 | +| time/ | | +| fps | 310 | +| iterations | 4328 | +| time_elapsed | 14295 | +| total_timesteps | 4431872 | +| train/ | | +| approx_kl | 2.8723495 | +| clip_fraction | 0.409 | +| clip_range | 0.2 | +| entropy_loss | -0.218 | +| explained_variance | -1.65 | +| learning_rate | 0.0001 | +| loss | -0.0594 | +| n_updates | 103800 | +| policy_gradient_loss | -0.0543 | +| value_loss | 0.000676 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.45e+03 | +| ep_rew_mean | 0.0979 | +| time/ | | +| fps | 310 | +| iterations | 4329 | +| time_elapsed | 14299 | +| total_timesteps | 4432896 | +| train/ | | +| approx_kl | 2.7967896 | +| clip_fraction | 0.374 | +| clip_range | 0.2 | +| entropy_loss | -0.197 | +| explained_variance | -0.904 | +| learning_rate | 0.0001 | +| loss | -0.0501 | +| n_updates | 103810 | +| policy_gradient_loss | -0.0492 | +| value_loss | 0.000741 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.44e+03 | +| ep_rew_mean | 0.094 | +| time/ | | +| fps | 310 | +| iterations | 4330 | +| time_elapsed | 14302 | +| total_timesteps | 4433920 | +| train/ | | +| approx_kl | 3.3747158 | +| clip_fraction | 0.39 | +| clip_range | 0.2 | +| entropy_loss | -0.194 | +| explained_variance | -3.18 | +| learning_rate | 0.0001 | +| loss | -0.0613 | +| n_updates | 103820 | +| policy_gradient_loss | -0.0544 | +| value_loss | 0.000863 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.44e+03 | +| ep_rew_mean | 0.094 | +| time/ | | +| fps | 310 | +| iterations | 4331 | +| time_elapsed | 14305 | +| total_timesteps | 4434944 | +| train/ | | +| approx_kl | 2.7572498 | +| clip_fraction | 0.39 | +| clip_range | 0.2 | +| entropy_loss | -0.205 | +| explained_variance | -0.414 | +| learning_rate | 0.0001 | +| loss | -0.0854 | +| n_updates | 103830 | +| policy_gradient_loss | 0.0107 | +| value_loss | 0.00061 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.44e+03 | +| ep_rew_mean | 0.0951 | +| time/ | | +| fps | 310 | +| iterations | 4332 | +| time_elapsed | 14308 | +| total_timesteps | 4435968 | +| train/ | | +| approx_kl | 3.222947 | +| clip_fraction | 0.442 | +| clip_range | 0.2 | +| entropy_loss | -0.273 | +| explained_variance | -0.833 | +| learning_rate | 0.0001 | +| loss | -0.0556 | +| n_updates | 103840 | +| policy_gradient_loss | -0.0539 | +| value_loss | 0.000515 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.43e+03 | +| ep_rew_mean | 0.0933 | +| time/ | | +| fps | 310 | +| iterations | 4333 | +| time_elapsed | 14311 | +| total_timesteps | 4436992 | +| train/ | | +| approx_kl | 2.486698 | +| clip_fraction | 0.394 | +| clip_range | 0.2 | +| entropy_loss | -0.207 | +| explained_variance | -1.89 | +| learning_rate | 0.0001 | +| loss | -0.0775 | +| n_updates | 103850 | +| policy_gradient_loss | -0.0538 | +| value_loss | 0.00065 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.43e+03 | +| ep_rew_mean | 0.0933 | +| time/ | | +| fps | 310 | +| iterations | 4334 | +| time_elapsed | 14314 | +| total_timesteps | 4438016 | +| train/ | | +| approx_kl | 14.114234 | +| clip_fraction | 0.419 | +| clip_range | 0.2 | +| entropy_loss | -0.223 | +| explained_variance | -1.44 | +| learning_rate | 0.0001 | +| loss | -0.0597 | +| n_updates | 103860 | +| policy_gradient_loss | -0.0416 | +| value_loss | 0.000607 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.43e+03 | +| ep_rew_mean | 0.0984 | +| time/ | | +| fps | 310 | +| iterations | 4335 | +| time_elapsed | 14318 | +| total_timesteps | 4439040 | +| train/ | | +| approx_kl | 3.8505232 | +| clip_fraction | 0.45 | +| clip_range | 0.2 | +| entropy_loss | -0.263 | +| explained_variance | -1.94 | +| learning_rate | 0.0001 | +| loss | -0.0646 | +| n_updates | 103870 | +| policy_gradient_loss | -0.058 | +| value_loss | 0.00074 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.43e+03 | +| ep_rew_mean | 0.102 | +| time/ | | +| fps | 310 | +| iterations | 4336 | +| time_elapsed | 14321 | +| total_timesteps | 4440064 | +| train/ | | +| approx_kl | 3.2905853 | +| clip_fraction | 0.406 | +| clip_range | 0.2 | +| entropy_loss | -0.227 | +| explained_variance | -1.3 | +| learning_rate | 0.0001 | +| loss | -0.0829 | +| n_updates | 103880 | +| policy_gradient_loss | -0.0528 | +| value_loss | 0.000765 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.43e+03 | +| ep_rew_mean | 0.105 | +| time/ | | +| fps | 310 | +| iterations | 4337 | +| time_elapsed | 14325 | +| total_timesteps | 4441088 | +| train/ | | +| approx_kl | 3.1456509 | +| clip_fraction | 0.417 | +| clip_range | 0.2 | +| entropy_loss | -0.23 | +| explained_variance | -1.39 | +| learning_rate | 0.0001 | +| loss | -0.0732 | +| n_updates | 103890 | +| policy_gradient_loss | -0.058 | +| value_loss | 0.000612 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.43e+03 | +| ep_rew_mean | 0.103 | +| time/ | | +| fps | 310 | +| iterations | 4338 | +| time_elapsed | 14329 | +| total_timesteps | 4442112 | +| train/ | | +| approx_kl | 2.9080954 | +| clip_fraction | 0.411 | +| clip_range | 0.2 | +| entropy_loss | -0.204 | +| explained_variance | -2.46 | +| learning_rate | 0.0001 | +| loss | -0.0567 | +| n_updates | 103900 | +| policy_gradient_loss | -0.0597 | +| value_loss | 0.000761 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.106 | +| time/ | | +| fps | 309 | +| iterations | 4339 | +| time_elapsed | 14332 | +| total_timesteps | 4443136 | +| train/ | | +| approx_kl | 3.1105103 | +| clip_fraction | 0.409 | +| clip_range | 0.2 | +| entropy_loss | -0.213 | +| explained_variance | -0.809 | +| learning_rate | 0.0001 | +| loss | -0.0794 | +| n_updates | 103910 | +| policy_gradient_loss | -0.0333 | +| value_loss | 0.000523 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.106 | +| time/ | | +| fps | 309 | +| iterations | 4340 | +| time_elapsed | 14336 | +| total_timesteps | 4444160 | +| train/ | | +| approx_kl | 2.56624 | +| clip_fraction | 0.383 | +| clip_range | 0.2 | +| entropy_loss | -0.213 | +| explained_variance | -0.231 | +| learning_rate | 0.0001 | +| loss | -0.0537 | +| n_updates | 103920 | +| policy_gradient_loss | -0.0526 | +| value_loss | 0.000785 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.11 | +| time/ | | +| fps | 309 | +| iterations | 4341 | +| time_elapsed | 14340 | +| total_timesteps | 4445184 | +| train/ | | +| approx_kl | 2.6763153 | +| clip_fraction | 0.422 | +| clip_range | 0.2 | +| entropy_loss | -0.239 | +| explained_variance | -1.07 | +| learning_rate | 0.0001 | +| loss | -0.0819 | +| n_updates | 103930 | +| policy_gradient_loss | -0.0613 | +| value_loss | 0.000671 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.11 | +| time/ | | +| fps | 309 | +| iterations | 4342 | +| time_elapsed | 14343 | +| total_timesteps | 4446208 | +| train/ | | +| approx_kl | 3.0515203 | +| clip_fraction | 0.409 | +| clip_range | 0.2 | +| entropy_loss | -0.22 | +| explained_variance | -1.19 | +| learning_rate | 0.0001 | +| loss | -0.0467 | +| n_updates | 103940 | +| policy_gradient_loss | -0.0523 | +| value_loss | 0.000587 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.43e+03 | +| ep_rew_mean | 0.115 | +| time/ | | +| fps | 309 | +| iterations | 4343 | +| time_elapsed | 14347 | +| total_timesteps | 4447232 | +| train/ | | +| approx_kl | 2.3294291 | +| clip_fraction | 0.422 | +| clip_range | 0.2 | +| entropy_loss | -0.26 | +| explained_variance | -1.11 | +| learning_rate | 0.0001 | +| loss | -0.0561 | +| n_updates | 103950 | +| policy_gradient_loss | -0.0514 | +| value_loss | 0.000605 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.43e+03 | +| ep_rew_mean | 0.118 | +| time/ | | +| fps | 309 | +| iterations | 4344 | +| time_elapsed | 14350 | +| total_timesteps | 4448256 | +| train/ | | +| approx_kl | 2.774829 | +| clip_fraction | 0.401 | +| clip_range | 0.2 | +| entropy_loss | -0.226 | +| explained_variance | -2.25 | +| learning_rate | 0.0001 | +| loss | -0.0791 | +| n_updates | 103960 | +| policy_gradient_loss | -0.0527 | +| value_loss | 0.00069 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.124 | +| time/ | | +| fps | 309 | +| iterations | 4345 | +| time_elapsed | 14353 | +| total_timesteps | 4449280 | +| train/ | | +| approx_kl | 3.3079474 | +| clip_fraction | 0.37 | +| clip_range | 0.2 | +| entropy_loss | -0.213 | +| explained_variance | -1.23 | +| learning_rate | 0.0001 | +| loss | -0.0632 | +| n_updates | 103970 | +| policy_gradient_loss | -0.0445 | +| value_loss | 0.000665 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.129 | +| time/ | | +| fps | 309 | +| iterations | 4346 | +| time_elapsed | 14356 | +| total_timesteps | 4450304 | +| train/ | | +| approx_kl | 2.589294 | +| clip_fraction | 0.406 | +| clip_range | 0.2 | +| entropy_loss | -0.246 | +| explained_variance | -0.142 | +| learning_rate | 0.0001 | +| loss | -0.0925 | +| n_updates | 103980 | +| policy_gradient_loss | -0.0585 | +| value_loss | 0.00099 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.132 | +| time/ | | +| fps | 309 | +| iterations | 4347 | +| time_elapsed | 14360 | +| total_timesteps | 4451328 | +| train/ | | +| approx_kl | 3.2892563 | +| clip_fraction | 0.397 | +| clip_range | 0.2 | +| entropy_loss | -0.22 | +| explained_variance | -1.97 | +| learning_rate | 0.0001 | +| loss | -0.0686 | +| n_updates | 103990 | +| policy_gradient_loss | -0.0528 | +| value_loss | 0.000796 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.132 | +| time/ | | +| fps | 309 | +| iterations | 4348 | +| time_elapsed | 14363 | +| total_timesteps | 4452352 | +| train/ | | +| approx_kl | 2.341032 | +| clip_fraction | 0.399 | +| clip_range | 0.2 | +| entropy_loss | -0.229 | +| explained_variance | -2.75 | +| learning_rate | 0.0001 | +| loss | -0.0732 | +| n_updates | 104000 | +| policy_gradient_loss | -0.0555 | +| value_loss | 0.000799 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.133 | +| time/ | | +| fps | 309 | +| iterations | 4349 | +| time_elapsed | 14366 | +| total_timesteps | 4453376 | +| train/ | | +| approx_kl | 2.5016506 | +| clip_fraction | 0.401 | +| clip_range | 0.2 | +| entropy_loss | -0.227 | +| explained_variance | -1.5 | +| learning_rate | 0.0001 | +| loss | -0.0708 | +| n_updates | 104010 | +| policy_gradient_loss | -0.0431 | +| value_loss | 0.000635 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.135 | +| time/ | | +| fps | 309 | +| iterations | 4350 | +| time_elapsed | 14369 | +| total_timesteps | 4454400 | +| train/ | | +| approx_kl | 2.501267 | +| clip_fraction | 0.43 | +| clip_range | 0.2 | +| entropy_loss | -0.269 | +| explained_variance | -2.61 | +| learning_rate | 0.0001 | +| loss | -0.0806 | +| n_updates | 104020 | +| policy_gradient_loss | -0.0587 | +| value_loss | 0.000575 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.135 | +| time/ | | +| fps | 309 | +| iterations | 4351 | +| time_elapsed | 14372 | +| total_timesteps | 4455424 | +| train/ | | +| approx_kl | 2.6262116 | +| clip_fraction | 0.461 | +| clip_range | 0.2 | +| entropy_loss | -0.252 | +| explained_variance | -1.58 | +| learning_rate | 0.0001 | +| loss | -0.091 | +| n_updates | 104030 | +| policy_gradient_loss | -0.0552 | +| value_loss | 0.000503 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.135 | +| time/ | | +| fps | 309 | +| iterations | 4352 | +| time_elapsed | 14375 | +| total_timesteps | 4456448 | +| train/ | | +| approx_kl | 2.3025255 | +| clip_fraction | 0.414 | +| clip_range | 0.2 | +| entropy_loss | -0.242 | +| explained_variance | -2.01 | +| learning_rate | 0.0001 | +| loss | -0.0911 | +| n_updates | 104040 | +| policy_gradient_loss | -0.0484 | +| value_loss | 0.000368 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.137 | +| time/ | | +| fps | 309 | +| iterations | 4353 | +| time_elapsed | 14379 | +| total_timesteps | 4457472 | +| train/ | | +| approx_kl | 4.7511578 | +| clip_fraction | 0.446 | +| clip_range | 0.2 | +| entropy_loss | -0.241 | +| explained_variance | -0.804 | +| learning_rate | 0.0001 | +| loss | -0.0735 | +| n_updates | 104050 | +| policy_gradient_loss | -0.0619 | +| value_loss | 0.000736 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.137 | +| time/ | | +| fps | 309 | +| iterations | 4354 | +| time_elapsed | 14382 | +| total_timesteps | 4458496 | +| train/ | | +| approx_kl | 3.133791 | +| clip_fraction | 0.439 | +| clip_range | 0.2 | +| entropy_loss | -0.236 | +| explained_variance | -1.31 | +| learning_rate | 0.0001 | +| loss | -0.0729 | +| n_updates | 104060 | +| policy_gradient_loss | -0.0593 | +| value_loss | 0.000642 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.14 | +| time/ | | +| fps | 309 | +| iterations | 4355 | +| time_elapsed | 14386 | +| total_timesteps | 4459520 | +| train/ | | +| approx_kl | 2.8375688 | +| clip_fraction | 0.397 | +| clip_range | 0.2 | +| entropy_loss | -0.216 | +| explained_variance | -3.01 | +| learning_rate | 0.0001 | +| loss | -0.0641 | +| n_updates | 104070 | +| policy_gradient_loss | -0.0564 | +| value_loss | 0.000594 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.144 | +| time/ | | +| fps | 309 | +| iterations | 4356 | +| time_elapsed | 14389 | +| total_timesteps | 4460544 | +| train/ | | +| approx_kl | 2.6319041 | +| clip_fraction | 0.39 | +| clip_range | 0.2 | +| entropy_loss | -0.228 | +| explained_variance | -0.309 | +| learning_rate | 0.0001 | +| loss | -0.0601 | +| n_updates | 104080 | +| policy_gradient_loss | -0.0478 | +| value_loss | 0.000748 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.15 | +| time/ | | +| fps | 309 | +| iterations | 4357 | +| time_elapsed | 14393 | +| total_timesteps | 4461568 | +| train/ | | +| approx_kl | 2.9061518 | +| clip_fraction | 0.428 | +| clip_range | 0.2 | +| entropy_loss | -0.248 | +| explained_variance | -0.792 | +| learning_rate | 0.0001 | +| loss | -0.0912 | +| n_updates | 104090 | +| policy_gradient_loss | -0.0582 | +| value_loss | 0.000705 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.153 | +| time/ | | +| fps | 309 | +| iterations | 4358 | +| time_elapsed | 14396 | +| total_timesteps | 4462592 | +| train/ | | +| approx_kl | 2.8621335 | +| clip_fraction | 0.397 | +| clip_range | 0.2 | +| entropy_loss | -0.229 | +| explained_variance | -0.793 | +| learning_rate | 0.0001 | +| loss | -0.0653 | +| n_updates | 104100 | +| policy_gradient_loss | -0.0476 | +| value_loss | 0.000778 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.153 | +| time/ | | +| fps | 309 | +| iterations | 4359 | +| time_elapsed | 14400 | +| total_timesteps | 4463616 | +| train/ | | +| approx_kl | 6.716865 | +| clip_fraction | 0.358 | +| clip_range | 0.2 | +| entropy_loss | -0.221 | +| explained_variance | -1.1 | +| learning_rate | 0.0001 | +| loss | -0.0324 | +| n_updates | 104110 | +| policy_gradient_loss | -0.036 | +| value_loss | 0.000847 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.157 | +| time/ | | +| fps | 309 | +| iterations | 4360 | +| time_elapsed | 14403 | +| total_timesteps | 4464640 | +| train/ | | +| approx_kl | 2.5782516 | +| clip_fraction | 0.459 | +| clip_range | 0.2 | +| entropy_loss | -0.285 | +| explained_variance | -0.976 | +| learning_rate | 0.0001 | +| loss | -0.0733 | +| n_updates | 104120 | +| policy_gradient_loss | -0.066 | +| value_loss | 0.000711 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.158 | +| time/ | | +| fps | 309 | +| iterations | 4361 | +| time_elapsed | 14407 | +| total_timesteps | 4465664 | +| train/ | | +| approx_kl | 2.4707198 | +| clip_fraction | 0.388 | +| clip_range | 0.2 | +| entropy_loss | -0.211 | +| explained_variance | -0.877 | +| learning_rate | 0.0001 | +| loss | -0.066 | +| n_updates | 104130 | +| policy_gradient_loss | -0.0499 | +| value_loss | 0.000819 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.158 | +| time/ | | +| fps | 309 | +| iterations | 4362 | +| time_elapsed | 14410 | +| total_timesteps | 4466688 | +| train/ | | +| approx_kl | 2.95744 | +| clip_fraction | 0.428 | +| clip_range | 0.2 | +| entropy_loss | -0.233 | +| explained_variance | -2.35 | +| learning_rate | 0.0001 | +| loss | -0.0844 | +| n_updates | 104140 | +| policy_gradient_loss | -0.0599 | +| value_loss | 0.000628 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.161 | +| time/ | | +| fps | 309 | +| iterations | 4363 | +| time_elapsed | 14413 | +| total_timesteps | 4467712 | +| train/ | | +| approx_kl | 2.4907482 | +| clip_fraction | 0.376 | +| clip_range | 0.2 | +| entropy_loss | -0.202 | +| explained_variance | -1.5 | +| learning_rate | 0.0001 | +| loss | -0.0827 | +| n_updates | 104150 | +| policy_gradient_loss | -0.0513 | +| value_loss | 0.000778 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.161 | +| time/ | | +| fps | 309 | +| iterations | 4364 | +| time_elapsed | 14416 | +| total_timesteps | 4468736 | +| train/ | | +| approx_kl | 2.4666162 | +| clip_fraction | 0.403 | +| clip_range | 0.2 | +| entropy_loss | -0.232 | +| explained_variance | -0.978 | +| learning_rate | 0.0001 | +| loss | -0.0657 | +| n_updates | 104160 | +| policy_gradient_loss | -0.0496 | +| value_loss | 0.0006 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.167 | +| time/ | | +| fps | 309 | +| iterations | 4365 | +| time_elapsed | 14420 | +| total_timesteps | 4469760 | +| train/ | | +| approx_kl | 3.20407 | +| clip_fraction | 0.418 | +| clip_range | 0.2 | +| entropy_loss | -0.232 | +| explained_variance | -0.716 | +| learning_rate | 0.0001 | +| loss | -0.0833 | +| n_updates | 104170 | +| policy_gradient_loss | -0.0568 | +| value_loss | 0.000858 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.172 | +| time/ | | +| fps | 309 | +| iterations | 4366 | +| time_elapsed | 14423 | +| total_timesteps | 4470784 | +| train/ | | +| approx_kl | 2.8965096 | +| clip_fraction | 0.445 | +| clip_range | 0.2 | +| entropy_loss | -0.253 | +| explained_variance | -1.76 | +| learning_rate | 0.0001 | +| loss | -0.0761 | +| n_updates | 104180 | +| policy_gradient_loss | -0.0646 | +| value_loss | 0.000779 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.175 | +| time/ | | +| fps | 309 | +| iterations | 4367 | +| time_elapsed | 14426 | +| total_timesteps | 4471808 | +| train/ | | +| approx_kl | 2.5134788 | +| clip_fraction | 0.438 | +| clip_range | 0.2 | +| entropy_loss | -0.259 | +| explained_variance | -0.944 | +| learning_rate | 0.0001 | +| loss | -0.0701 | +| n_updates | 104190 | +| policy_gradient_loss | -0.0584 | +| value_loss | 0.000688 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.179 | +| time/ | | +| fps | 309 | +| iterations | 4368 | +| time_elapsed | 14429 | +| total_timesteps | 4472832 | +| train/ | | +| approx_kl | 2.2109547 | +| clip_fraction | 0.402 | +| clip_range | 0.2 | +| entropy_loss | -0.259 | +| explained_variance | -0.973 | +| learning_rate | 0.0001 | +| loss | -0.0967 | +| n_updates | 104200 | +| policy_gradient_loss | -0.0562 | +| value_loss | 0.000661 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.177 | +| time/ | | +| fps | 309 | +| iterations | 4369 | +| time_elapsed | 14432 | +| total_timesteps | 4473856 | +| train/ | | +| approx_kl | 2.7555618 | +| clip_fraction | 0.433 | +| clip_range | 0.2 | +| entropy_loss | -0.264 | +| explained_variance | -0.884 | +| learning_rate | 0.0001 | +| loss | -0.0614 | +| n_updates | 104210 | +| policy_gradient_loss | -0.06 | +| value_loss | 0.000905 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.177 | +| time/ | | +| fps | 309 | +| iterations | 4370 | +| time_elapsed | 14436 | +| total_timesteps | 4474880 | +| train/ | | +| approx_kl | 2.6777253 | +| clip_fraction | 0.422 | +| clip_range | 0.2 | +| entropy_loss | -0.251 | +| explained_variance | -2.08 | +| learning_rate | 0.0001 | +| loss | -0.0737 | +| n_updates | 104220 | +| policy_gradient_loss | -0.0503 | +| value_loss | 0.00066 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.184 | +| time/ | | +| fps | 309 | +| iterations | 4371 | +| time_elapsed | 14439 | +| total_timesteps | 4475904 | +| train/ | | +| approx_kl | 2.3942952 | +| clip_fraction | 0.444 | +| clip_range | 0.2 | +| entropy_loss | -0.266 | +| explained_variance | -2.19 | +| learning_rate | 0.0001 | +| loss | -0.0717 | +| n_updates | 104230 | +| policy_gradient_loss | -0.0622 | +| value_loss | 0.000632 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.184 | +| time/ | | +| fps | 309 | +| iterations | 4372 | +| time_elapsed | 14442 | +| total_timesteps | 4476928 | +| train/ | | +| approx_kl | 2.769355 | +| clip_fraction | 0.46 | +| clip_range | 0.2 | +| entropy_loss | -0.281 | +| explained_variance | -0.627 | +| learning_rate | 0.0001 | +| loss | -0.0882 | +| n_updates | 104240 | +| policy_gradient_loss | -0.066 | +| value_loss | 0.000624 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.185 | +| time/ | | +| fps | 309 | +| iterations | 4373 | +| time_elapsed | 14446 | +| total_timesteps | 4477952 | +| train/ | | +| approx_kl | 2.4939246 | +| clip_fraction | 0.416 | +| clip_range | 0.2 | +| entropy_loss | -0.246 | +| explained_variance | -1.82 | +| learning_rate | 0.0001 | +| loss | -0.0653 | +| n_updates | 104250 | +| policy_gradient_loss | -0.06 | +| value_loss | 0.000475 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.189 | +| time/ | | +| fps | 309 | +| iterations | 4374 | +| time_elapsed | 14449 | +| total_timesteps | 4478976 | +| train/ | | +| approx_kl | 2.6357853 | +| clip_fraction | 0.42 | +| clip_range | 0.2 | +| entropy_loss | -0.253 | +| explained_variance | -0.902 | +| learning_rate | 0.0001 | +| loss | -0.073 | +| n_updates | 104260 | +| policy_gradient_loss | -0.0521 | +| value_loss | 0.000523 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.189 | +| time/ | | +| fps | 309 | +| iterations | 4375 | +| time_elapsed | 14452 | +| total_timesteps | 4480000 | +| train/ | | +| approx_kl | 2.488594 | +| clip_fraction | 0.443 | +| clip_range | 0.2 | +| entropy_loss | -0.266 | +| explained_variance | -2.71 | +| learning_rate | 0.0001 | +| loss | -0.105 | +| n_updates | 104270 | +| policy_gradient_loss | -0.0602 | +| value_loss | 0.000399 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.191 | +| time/ | | +| fps | 309 | +| iterations | 4376 | +| time_elapsed | 14456 | +| total_timesteps | 4481024 | +| train/ | | +| approx_kl | 2.2228684 | +| clip_fraction | 0.446 | +| clip_range | 0.2 | +| entropy_loss | -0.288 | +| explained_variance | -1.07 | +| learning_rate | 0.0001 | +| loss | -0.0937 | +| n_updates | 104280 | +| policy_gradient_loss | -0.0604 | +| value_loss | 0.000819 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.194 | +| time/ | | +| fps | 309 | +| iterations | 4377 | +| time_elapsed | 14459 | +| total_timesteps | 4482048 | +| train/ | | +| approx_kl | 3.7001991 | +| clip_fraction | 0.44 | +| clip_range | 0.2 | +| entropy_loss | -0.262 | +| explained_variance | -1.33 | +| learning_rate | 0.0001 | +| loss | -0.0867 | +| n_updates | 104290 | +| policy_gradient_loss | -0.0566 | +| value_loss | 0.00074 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.189 | +| time/ | | +| fps | 309 | +| iterations | 4378 | +| time_elapsed | 14462 | +| total_timesteps | 4483072 | +| train/ | | +| approx_kl | 2.9170172 | +| clip_fraction | 0.442 | +| clip_range | 0.2 | +| entropy_loss | -0.257 | +| explained_variance | -3.66 | +| learning_rate | 0.0001 | +| loss | -0.0661 | +| n_updates | 104300 | +| policy_gradient_loss | -0.0624 | +| value_loss | 0.000465 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.189 | +| time/ | | +| fps | 309 | +| iterations | 4379 | +| time_elapsed | 14466 | +| total_timesteps | 4484096 | +| train/ | | +| approx_kl | 2.746769 | +| clip_fraction | 0.425 | +| clip_range | 0.2 | +| entropy_loss | -0.233 | +| explained_variance | -0.396 | +| learning_rate | 0.0001 | +| loss | -0.0861 | +| n_updates | 104310 | +| policy_gradient_loss | -0.0601 | +| value_loss | 0.000509 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.192 | +| time/ | | +| fps | 309 | +| iterations | 4380 | +| time_elapsed | 14469 | +| total_timesteps | 4485120 | +| train/ | | +| approx_kl | 2.9826002 | +| clip_fraction | 0.463 | +| clip_range | 0.2 | +| entropy_loss | -0.288 | +| explained_variance | -2.01 | +| learning_rate | 0.0001 | +| loss | -0.0732 | +| n_updates | 104320 | +| policy_gradient_loss | -0.0578 | +| value_loss | 0.000784 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.197 | +| time/ | | +| fps | 309 | +| iterations | 4381 | +| time_elapsed | 14472 | +| total_timesteps | 4486144 | +| train/ | | +| approx_kl | 2.6964712 | +| clip_fraction | 0.429 | +| clip_range | 0.2 | +| entropy_loss | -0.272 | +| explained_variance | -1.14 | +| learning_rate | 0.0001 | +| loss | -0.0743 | +| n_updates | 104330 | +| policy_gradient_loss | -0.0612 | +| value_loss | 0.000733 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.193 | +| time/ | | +| fps | 309 | +| iterations | 4382 | +| time_elapsed | 14475 | +| total_timesteps | 4487168 | +| train/ | | +| approx_kl | 2.5717325 | +| clip_fraction | 0.446 | +| clip_range | 0.2 | +| entropy_loss | -0.283 | +| explained_variance | -1.72 | +| learning_rate | 0.0001 | +| loss | -0.0781 | +| n_updates | 104340 | +| policy_gradient_loss | -0.056 | +| value_loss | 0.000471 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.193 | +| time/ | | +| fps | 309 | +| iterations | 4383 | +| time_elapsed | 14479 | +| total_timesteps | 4488192 | +| train/ | | +| approx_kl | 2.3714583 | +| clip_fraction | 0.393 | +| clip_range | 0.2 | +| entropy_loss | -0.252 | +| explained_variance | -0.223 | +| learning_rate | 0.0001 | +| loss | -0.064 | +| n_updates | 104350 | +| policy_gradient_loss | -0.0531 | +| value_loss | 0.000825 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.198 | +| time/ | | +| fps | 309 | +| iterations | 4384 | +| time_elapsed | 14482 | +| total_timesteps | 4489216 | +| train/ | | +| approx_kl | 2.3286347 | +| clip_fraction | 0.434 | +| clip_range | 0.2 | +| entropy_loss | -0.277 | +| explained_variance | -2.67 | +| learning_rate | 0.0001 | +| loss | -0.0873 | +| n_updates | 104360 | +| policy_gradient_loss | -0.06 | +| value_loss | 0.000645 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.198 | +| time/ | | +| fps | 309 | +| iterations | 4385 | +| time_elapsed | 14485 | +| total_timesteps | 4490240 | +| train/ | | +| approx_kl | 2.8745346 | +| clip_fraction | 0.458 | +| clip_range | 0.2 | +| entropy_loss | -0.307 | +| explained_variance | -0.961 | +| learning_rate | 0.0001 | +| loss | -0.0767 | +| n_updates | 104370 | +| policy_gradient_loss | -0.0405 | +| value_loss | 0.000447 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.199 | +| time/ | | +| fps | 309 | +| iterations | 4386 | +| time_elapsed | 14488 | +| total_timesteps | 4491264 | +| train/ | | +| approx_kl | 4.5258207 | +| clip_fraction | 0.47 | +| clip_range | 0.2 | +| entropy_loss | -0.306 | +| explained_variance | -1.44 | +| learning_rate | 0.0001 | +| loss | -0.0809 | +| n_updates | 104380 | +| policy_gradient_loss | -0.0615 | +| value_loss | 0.000547 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.2 | +| time/ | | +| fps | 309 | +| iterations | 4387 | +| time_elapsed | 14491 | +| total_timesteps | 4492288 | +| train/ | | +| approx_kl | 2.7031972 | +| clip_fraction | 0.379 | +| clip_range | 0.2 | +| entropy_loss | -0.205 | +| explained_variance | -1.94 | +| learning_rate | 0.0001 | +| loss | -0.0925 | +| n_updates | 104390 | +| policy_gradient_loss | -0.0426 | +| value_loss | 0.000486 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.2 | +| time/ | | +| fps | 309 | +| iterations | 4388 | +| time_elapsed | 14495 | +| total_timesteps | 4493312 | +| train/ | | +| approx_kl | 2.5485044 | +| clip_fraction | 0.415 | +| clip_range | 0.2 | +| entropy_loss | -0.251 | +| explained_variance | -2.13 | +| learning_rate | 0.0001 | +| loss | -0.0602 | +| n_updates | 104400 | +| policy_gradient_loss | -0.054 | +| value_loss | 0.000479 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.203 | +| time/ | | +| fps | 309 | +| iterations | 4389 | +| time_elapsed | 14498 | +| total_timesteps | 4494336 | +| train/ | | +| approx_kl | 3.2353125 | +| clip_fraction | 0.466 | +| clip_range | 0.2 | +| entropy_loss | -0.311 | +| explained_variance | -1.3 | +| learning_rate | 0.0001 | +| loss | -0.0882 | +| n_updates | 104410 | +| policy_gradient_loss | -0.0574 | +| value_loss | 0.000469 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.204 | +| time/ | | +| fps | 309 | +| iterations | 4390 | +| time_elapsed | 14501 | +| total_timesteps | 4495360 | +| train/ | | +| approx_kl | 2.2706685 | +| clip_fraction | 0.448 | +| clip_range | 0.2 | +| entropy_loss | -0.301 | +| explained_variance | -1.58 | +| learning_rate | 0.0001 | +| loss | -0.0825 | +| n_updates | 104420 | +| policy_gradient_loss | -0.0509 | +| value_loss | 0.000628 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.205 | +| time/ | | +| fps | 309 | +| iterations | 4391 | +| time_elapsed | 14505 | +| total_timesteps | 4496384 | +| train/ | | +| approx_kl | 2.3130312 | +| clip_fraction | 0.385 | +| clip_range | 0.2 | +| entropy_loss | -0.216 | +| explained_variance | -3.1 | +| learning_rate | 0.0001 | +| loss | -0.0797 | +| n_updates | 104430 | +| policy_gradient_loss | -0.0601 | +| value_loss | 0.000562 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.205 | +| time/ | | +| fps | 309 | +| iterations | 4392 | +| time_elapsed | 14508 | +| total_timesteps | 4497408 | +| train/ | | +| approx_kl | 2.883676 | +| clip_fraction | 0.447 | +| clip_range | 0.2 | +| entropy_loss | -0.304 | +| explained_variance | -1.11 | +| learning_rate | 0.0001 | +| loss | -0.0731 | +| n_updates | 104440 | +| policy_gradient_loss | -0.0592 | +| value_loss | 0.000501 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.206 | +| time/ | | +| fps | 309 | +| iterations | 4393 | +| time_elapsed | 14512 | +| total_timesteps | 4498432 | +| train/ | | +| approx_kl | 3.4736788 | +| clip_fraction | 0.452 | +| clip_range | 0.2 | +| entropy_loss | -0.278 | +| explained_variance | -0.985 | +| learning_rate | 0.0001 | +| loss | -0.0628 | +| n_updates | 104450 | +| policy_gradient_loss | -0.0668 | +| value_loss | 0.000655 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.211 | +| time/ | | +| fps | 309 | +| iterations | 4394 | +| time_elapsed | 14515 | +| total_timesteps | 4499456 | +| train/ | | +| approx_kl | 3.2642112 | +| clip_fraction | 0.423 | +| clip_range | 0.2 | +| entropy_loss | -0.244 | +| explained_variance | -1.58 | +| learning_rate | 0.0001 | +| loss | -0.083 | +| n_updates | 104460 | +| policy_gradient_loss | -0.0563 | +| value_loss | 0.000705 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.211 | +| time/ | | +| fps | 309 | +| iterations | 4395 | +| time_elapsed | 14519 | +| total_timesteps | 4500480 | +| train/ | | +| approx_kl | 3.574809 | +| clip_fraction | 0.474 | +| clip_range | 0.2 | +| entropy_loss | -0.317 | +| explained_variance | -0.755 | +| learning_rate | 0.0001 | +| loss | -0.0608 | +| n_updates | 104470 | +| policy_gradient_loss | -0.0697 | +| value_loss | 0.000774 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.216 | +| time/ | | +| fps | 309 | +| iterations | 4396 | +| time_elapsed | 14522 | +| total_timesteps | 4501504 | +| train/ | | +| approx_kl | 2.0369346 | +| clip_fraction | 0.447 | +| clip_range | 0.2 | +| entropy_loss | -0.289 | +| explained_variance | -3.06 | +| learning_rate | 0.0001 | +| loss | -0.0778 | +| n_updates | 104480 | +| policy_gradient_loss | -0.0645 | +| value_loss | 0.000628 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.214 | +| time/ | | +| fps | 309 | +| iterations | 4397 | +| time_elapsed | 14526 | +| total_timesteps | 4502528 | +| train/ | | +| approx_kl | 3.1303315 | +| clip_fraction | 0.467 | +| clip_range | 0.2 | +| entropy_loss | -0.32 | +| explained_variance | -1.11 | +| learning_rate | 0.0001 | +| loss | -0.0994 | +| n_updates | 104490 | +| policy_gradient_loss | -0.0661 | +| value_loss | 0.000469 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.214 | +| time/ | | +| fps | 309 | +| iterations | 4398 | +| time_elapsed | 14529 | +| total_timesteps | 4503552 | +| train/ | | +| approx_kl | 2.4751105 | +| clip_fraction | 0.426 | +| clip_range | 0.2 | +| entropy_loss | -0.283 | +| explained_variance | -1.36 | +| learning_rate | 0.0001 | +| loss | -0.0845 | +| n_updates | 104500 | +| policy_gradient_loss | -0.06 | +| value_loss | 0.000658 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.215 | +| time/ | | +| fps | 309 | +| iterations | 4399 | +| time_elapsed | 14532 | +| total_timesteps | 4504576 | +| train/ | | +| approx_kl | 2.5346584 | +| clip_fraction | 0.468 | +| clip_range | 0.2 | +| entropy_loss | -0.291 | +| explained_variance | -5.3 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 104510 | +| policy_gradient_loss | -0.0607 | +| value_loss | 0.000602 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.216 | +| time/ | | +| fps | 309 | +| iterations | 4400 | +| time_elapsed | 14536 | +| total_timesteps | 4505600 | +| train/ | | +| approx_kl | 2.2502975 | +| clip_fraction | 0.401 | +| clip_range | 0.2 | +| entropy_loss | -0.255 | +| explained_variance | -0.982 | +| learning_rate | 0.0001 | +| loss | -0.0623 | +| n_updates | 104520 | +| policy_gradient_loss | -0.0461 | +| value_loss | 0.000541 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.216 | +| time/ | | +| fps | 309 | +| iterations | 4401 | +| time_elapsed | 14539 | +| total_timesteps | 4506624 | +| train/ | | +| approx_kl | 4.286449 | +| clip_fraction | 0.374 | +| clip_range | 0.2 | +| entropy_loss | -0.227 | +| explained_variance | -0.796 | +| learning_rate | 0.0001 | +| loss | -0.0585 | +| n_updates | 104530 | +| policy_gradient_loss | -0.0484 | +| value_loss | 0.000686 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.216 | +| time/ | | +| fps | 309 | +| iterations | 4402 | +| time_elapsed | 14542 | +| total_timesteps | 4507648 | +| train/ | | +| approx_kl | 2.47854 | +| clip_fraction | 0.424 | +| clip_range | 0.2 | +| entropy_loss | -0.28 | +| explained_variance | -2.82 | +| learning_rate | 0.0001 | +| loss | -0.0622 | +| n_updates | 104540 | +| policy_gradient_loss | -0.0499 | +| value_loss | 0.000586 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.22 | +| time/ | | +| fps | 309 | +| iterations | 4403 | +| time_elapsed | 14545 | +| total_timesteps | 4508672 | +| train/ | | +| approx_kl | 2.1439466 | +| clip_fraction | 0.42 | +| clip_range | 0.2 | +| entropy_loss | -0.278 | +| explained_variance | -0.741 | +| learning_rate | 0.0001 | +| loss | -0.0538 | +| n_updates | 104550 | +| policy_gradient_loss | -0.0535 | +| value_loss | 0.000505 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.22 | +| time/ | | +| fps | 309 | +| iterations | 4404 | +| time_elapsed | 14548 | +| total_timesteps | 4509696 | +| train/ | | +| approx_kl | 1.9906702 | +| clip_fraction | 0.436 | +| clip_range | 0.2 | +| entropy_loss | -0.313 | +| explained_variance | -1.48 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 104560 | +| policy_gradient_loss | -0.0627 | +| value_loss | 0.000445 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.221 | +| time/ | | +| fps | 309 | +| iterations | 4405 | +| time_elapsed | 14551 | +| total_timesteps | 4510720 | +| train/ | | +| approx_kl | 2.274928 | +| clip_fraction | 0.409 | +| clip_range | 0.2 | +| entropy_loss | -0.267 | +| explained_variance | -6.57 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 104570 | +| policy_gradient_loss | -0.0621 | +| value_loss | 0.000523 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.22 | +| time/ | | +| fps | 309 | +| iterations | 4406 | +| time_elapsed | 14555 | +| total_timesteps | 4511744 | +| train/ | | +| approx_kl | 2.7183084 | +| clip_fraction | 0.448 | +| clip_range | 0.2 | +| entropy_loss | -0.277 | +| explained_variance | -1.23 | +| learning_rate | 0.0001 | +| loss | -0.0535 | +| n_updates | 104580 | +| policy_gradient_loss | -0.0567 | +| value_loss | 0.0007 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.221 | +| time/ | | +| fps | 309 | +| iterations | 4407 | +| time_elapsed | 14558 | +| total_timesteps | 4512768 | +| train/ | | +| approx_kl | 2.9205356 | +| clip_fraction | 0.442 | +| clip_range | 0.2 | +| entropy_loss | -0.288 | +| explained_variance | -1.85 | +| learning_rate | 0.0001 | +| loss | -0.0875 | +| n_updates | 104590 | +| policy_gradient_loss | -0.0636 | +| value_loss | 0.000432 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.225 | +| time/ | | +| fps | 309 | +| iterations | 4408 | +| time_elapsed | 14561 | +| total_timesteps | 4513792 | +| train/ | | +| approx_kl | 2.4485245 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.324 | +| explained_variance | -1.02 | +| learning_rate | 0.0001 | +| loss | -0.0695 | +| n_updates | 104600 | +| policy_gradient_loss | -0.0607 | +| value_loss | 0.000507 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.225 | +| time/ | | +| fps | 309 | +| iterations | 4409 | +| time_elapsed | 14565 | +| total_timesteps | 4514816 | +| train/ | | +| approx_kl | 2.4938915 | +| clip_fraction | 0.441 | +| clip_range | 0.2 | +| entropy_loss | -0.28 | +| explained_variance | -0.912 | +| learning_rate | 0.0001 | +| loss | -0.0806 | +| n_updates | 104610 | +| policy_gradient_loss | -0.0589 | +| value_loss | 0.000618 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.224 | +| time/ | | +| fps | 309 | +| iterations | 4410 | +| time_elapsed | 14568 | +| total_timesteps | 4515840 | +| train/ | | +| approx_kl | 2.6942768 | +| clip_fraction | 0.468 | +| clip_range | 0.2 | +| entropy_loss | -0.293 | +| explained_variance | -5.32 | +| learning_rate | 0.0001 | +| loss | -0.097 | +| n_updates | 104620 | +| policy_gradient_loss | -0.0695 | +| value_loss | 0.000429 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.225 | +| time/ | | +| fps | 309 | +| iterations | 4411 | +| time_elapsed | 14571 | +| total_timesteps | 4516864 | +| train/ | | +| approx_kl | 2.0594552 | +| clip_fraction | 0.404 | +| clip_range | 0.2 | +| entropy_loss | -0.263 | +| explained_variance | -1.23 | +| learning_rate | 0.0001 | +| loss | -0.0788 | +| n_updates | 104630 | +| policy_gradient_loss | -0.0536 | +| value_loss | 0.000537 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.228 | +| time/ | | +| fps | 309 | +| iterations | 4412 | +| time_elapsed | 14574 | +| total_timesteps | 4517888 | +| train/ | | +| approx_kl | 2.8090436 | +| clip_fraction | 0.46 | +| clip_range | 0.2 | +| entropy_loss | -0.306 | +| explained_variance | -0.13 | +| learning_rate | 0.0001 | +| loss | -0.0663 | +| n_updates | 104640 | +| policy_gradient_loss | -0.0642 | +| value_loss | 0.000545 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.227 | +| time/ | | +| fps | 309 | +| iterations | 4413 | +| time_elapsed | 14578 | +| total_timesteps | 4518912 | +| train/ | | +| approx_kl | 1.8209023 | +| clip_fraction | 0.4 | +| clip_range | 0.2 | +| entropy_loss | -0.282 | +| explained_variance | -0.405 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 104650 | +| policy_gradient_loss | -0.0567 | +| value_loss | 0.000718 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.227 | +| time/ | | +| fps | 309 | +| iterations | 4414 | +| time_elapsed | 14581 | +| total_timesteps | 4519936 | +| train/ | | +| approx_kl | 2.7443032 | +| clip_fraction | 0.4 | +| clip_range | 0.2 | +| entropy_loss | -0.255 | +| explained_variance | -0.326 | +| learning_rate | 0.0001 | +| loss | -0.0879 | +| n_updates | 104660 | +| policy_gradient_loss | -0.0596 | +| value_loss | 0.000602 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.231 | +| time/ | | +| fps | 309 | +| iterations | 4415 | +| time_elapsed | 14584 | +| total_timesteps | 4520960 | +| train/ | | +| approx_kl | 2.2814713 | +| clip_fraction | 0.474 | +| clip_range | 0.2 | +| entropy_loss | -0.316 | +| explained_variance | -1.62 | +| learning_rate | 0.0001 | +| loss | -0.0906 | +| n_updates | 104670 | +| policy_gradient_loss | -0.0691 | +| value_loss | 0.000643 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.231 | +| time/ | | +| fps | 309 | +| iterations | 4416 | +| time_elapsed | 14588 | +| total_timesteps | 4521984 | +| train/ | | +| approx_kl | 2.41182 | +| clip_fraction | 0.456 | +| clip_range | 0.2 | +| entropy_loss | -0.313 | +| explained_variance | -0.886 | +| learning_rate | 0.0001 | +| loss | -0.0456 | +| n_updates | 104680 | +| policy_gradient_loss | -0.0624 | +| value_loss | 0.000577 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.239 | +| time/ | | +| fps | 309 | +| iterations | 4417 | +| time_elapsed | 14591 | +| total_timesteps | 4523008 | +| train/ | | +| approx_kl | 2.10333 | +| clip_fraction | 0.443 | +| clip_range | 0.2 | +| entropy_loss | -0.323 | +| explained_variance | -0.993 | +| learning_rate | 0.0001 | +| loss | -0.0804 | +| n_updates | 104690 | +| policy_gradient_loss | -0.0644 | +| value_loss | 0.000391 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.239 | +| time/ | | +| fps | 309 | +| iterations | 4418 | +| time_elapsed | 14594 | +| total_timesteps | 4524032 | +| train/ | | +| approx_kl | 2.1294422 | +| clip_fraction | 0.419 | +| clip_range | 0.2 | +| entropy_loss | -0.281 | +| explained_variance | -0.569 | +| learning_rate | 0.0001 | +| loss | -0.0856 | +| n_updates | 104700 | +| policy_gradient_loss | -0.0506 | +| value_loss | 0.000666 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.239 | +| time/ | | +| fps | 309 | +| iterations | 4419 | +| time_elapsed | 14597 | +| total_timesteps | 4525056 | +| train/ | | +| approx_kl | 1.7693462 | +| clip_fraction | 0.389 | +| clip_range | 0.2 | +| entropy_loss | -0.253 | +| explained_variance | -0.438 | +| learning_rate | 0.0001 | +| loss | -0.0659 | +| n_updates | 104710 | +| policy_gradient_loss | -0.0599 | +| value_loss | 0.000442 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.243 | +| time/ | | +| fps | 309 | +| iterations | 4420 | +| time_elapsed | 14601 | +| total_timesteps | 4526080 | +| train/ | | +| approx_kl | 2.6629794 | +| clip_fraction | 0.438 | +| clip_range | 0.2 | +| entropy_loss | -0.272 | +| explained_variance | -0.504 | +| learning_rate | 0.0001 | +| loss | -0.0842 | +| n_updates | 104720 | +| policy_gradient_loss | -0.0633 | +| value_loss | 0.000704 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.249 | +| time/ | | +| fps | 309 | +| iterations | 4421 | +| time_elapsed | 14604 | +| total_timesteps | 4527104 | +| train/ | | +| approx_kl | 2.049274 | +| clip_fraction | 0.422 | +| clip_range | 0.2 | +| entropy_loss | -0.274 | +| explained_variance | -2.93 | +| learning_rate | 0.0001 | +| loss | -0.0822 | +| n_updates | 104730 | +| policy_gradient_loss | -0.0574 | +| value_loss | 0.000837 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.249 | +| time/ | | +| fps | 309 | +| iterations | 4422 | +| time_elapsed | 14607 | +| total_timesteps | 4528128 | +| train/ | | +| approx_kl | 1.9030559 | +| clip_fraction | 0.414 | +| clip_range | 0.2 | +| entropy_loss | -0.283 | +| explained_variance | -0.163 | +| learning_rate | 0.0001 | +| loss | -0.0831 | +| n_updates | 104740 | +| policy_gradient_loss | -0.055 | +| value_loss | 0.000667 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.252 | +| time/ | | +| fps | 309 | +| iterations | 4423 | +| time_elapsed | 14610 | +| total_timesteps | 4529152 | +| train/ | | +| approx_kl | 3.3367515 | +| clip_fraction | 0.462 | +| clip_range | 0.2 | +| entropy_loss | -0.278 | +| explained_variance | -2.74 | +| learning_rate | 0.0001 | +| loss | -0.0483 | +| n_updates | 104750 | +| policy_gradient_loss | -0.0619 | +| value_loss | 0.000447 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.255 | +| time/ | | +| fps | 309 | +| iterations | 4424 | +| time_elapsed | 14613 | +| total_timesteps | 4530176 | +| train/ | | +| approx_kl | 3.355089 | +| clip_fraction | 0.416 | +| clip_range | 0.2 | +| entropy_loss | -0.284 | +| explained_variance | -0.451 | +| learning_rate | 0.0001 | +| loss | -0.0537 | +| n_updates | 104760 | +| policy_gradient_loss | -0.0542 | +| value_loss | 0.000444 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.255 | +| time/ | | +| fps | 309 | +| iterations | 4425 | +| time_elapsed | 14617 | +| total_timesteps | 4531200 | +| train/ | | +| approx_kl | 2.1466184 | +| clip_fraction | 0.39 | +| clip_range | 0.2 | +| entropy_loss | -0.246 | +| explained_variance | -0.825 | +| learning_rate | 0.0001 | +| loss | -0.04 | +| n_updates | 104770 | +| policy_gradient_loss | -0.0572 | +| value_loss | 0.000552 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.258 | +| time/ | | +| fps | 309 | +| iterations | 4426 | +| time_elapsed | 14620 | +| total_timesteps | 4532224 | +| train/ | | +| approx_kl | 2.4398112 | +| clip_fraction | 0.474 | +| clip_range | 0.2 | +| entropy_loss | -0.326 | +| explained_variance | -2.27 | +| learning_rate | 0.0001 | +| loss | -0.1 | +| n_updates | 104780 | +| policy_gradient_loss | -0.072 | +| value_loss | 0.000691 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.258 | +| time/ | | +| fps | 309 | +| iterations | 4427 | +| time_elapsed | 14623 | +| total_timesteps | 4533248 | +| train/ | | +| approx_kl | 2.181434 | +| clip_fraction | 0.403 | +| clip_range | 0.2 | +| entropy_loss | -0.249 | +| explained_variance | -1.17 | +| learning_rate | 0.0001 | +| loss | -0.0842 | +| n_updates | 104790 | +| policy_gradient_loss | -0.0581 | +| value_loss | 0.000994 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.26 | +| time/ | | +| fps | 309 | +| iterations | 4428 | +| time_elapsed | 14627 | +| total_timesteps | 4534272 | +| train/ | | +| approx_kl | 1.9145374 | +| clip_fraction | 0.392 | +| clip_range | 0.2 | +| entropy_loss | -0.231 | +| explained_variance | -0.928 | +| learning_rate | 0.0001 | +| loss | -0.0694 | +| n_updates | 104800 | +| policy_gradient_loss | -0.0579 | +| value_loss | 0.00101 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.261 | +| time/ | | +| fps | 309 | +| iterations | 4429 | +| time_elapsed | 14630 | +| total_timesteps | 4535296 | +| train/ | | +| approx_kl | 2.212553 | +| clip_fraction | 0.38 | +| clip_range | 0.2 | +| entropy_loss | -0.235 | +| explained_variance | -0.703 | +| learning_rate | 0.0001 | +| loss | -0.0654 | +| n_updates | 104810 | +| policy_gradient_loss | -0.0593 | +| value_loss | 0.000857 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.26 | +| time/ | | +| fps | 309 | +| iterations | 4430 | +| time_elapsed | 14634 | +| total_timesteps | 4536320 | +| train/ | | +| approx_kl | 2.7536292 | +| clip_fraction | 0.428 | +| clip_range | 0.2 | +| entropy_loss | -0.271 | +| explained_variance | -2.79 | +| learning_rate | 0.0001 | +| loss | -0.0968 | +| n_updates | 104820 | +| policy_gradient_loss | -0.0651 | +| value_loss | 0.000774 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.259 | +| time/ | | +| fps | 309 | +| iterations | 4431 | +| time_elapsed | 14638 | +| total_timesteps | 4537344 | +| train/ | | +| approx_kl | 2.5004797 | +| clip_fraction | 0.478 | +| clip_range | 0.2 | +| entropy_loss | -0.299 | +| explained_variance | -0.718 | +| learning_rate | 0.0001 | +| loss | -0.105 | +| n_updates | 104830 | +| policy_gradient_loss | -0.0616 | +| value_loss | 0.000906 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.258 | +| time/ | | +| fps | 309 | +| iterations | 4432 | +| time_elapsed | 14641 | +| total_timesteps | 4538368 | +| train/ | | +| approx_kl | 3.1863194 | +| clip_fraction | 0.467 | +| clip_range | 0.2 | +| entropy_loss | -0.299 | +| explained_variance | -1.57 | +| learning_rate | 0.0001 | +| loss | -0.109 | +| n_updates | 104840 | +| policy_gradient_loss | -0.07 | +| value_loss | 0.000737 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.263 | +| time/ | | +| fps | 309 | +| iterations | 4433 | +| time_elapsed | 14645 | +| total_timesteps | 4539392 | +| train/ | | +| approx_kl | 2.264287 | +| clip_fraction | 0.434 | +| clip_range | 0.2 | +| entropy_loss | -0.293 | +| explained_variance | -1.42 | +| learning_rate | 0.0001 | +| loss | -0.0838 | +| n_updates | 104850 | +| policy_gradient_loss | -0.0589 | +| value_loss | 0.000496 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.263 | +| time/ | | +| fps | 309 | +| iterations | 4434 | +| time_elapsed | 14648 | +| total_timesteps | 4540416 | +| train/ | | +| approx_kl | 3.4108982 | +| clip_fraction | 0.454 | +| clip_range | 0.2 | +| entropy_loss | -0.3 | +| explained_variance | -0.638 | +| learning_rate | 0.0001 | +| loss | -0.0451 | +| n_updates | 104860 | +| policy_gradient_loss | -0.0633 | +| value_loss | 0.000633 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.258 | +| time/ | | +| fps | 309 | +| iterations | 4435 | +| time_elapsed | 14651 | +| total_timesteps | 4541440 | +| train/ | | +| approx_kl | 2.5387793 | +| clip_fraction | 0.437 | +| clip_range | 0.2 | +| entropy_loss | -0.26 | +| explained_variance | -3.89 | +| learning_rate | 0.0001 | +| loss | -0.0761 | +| n_updates | 104870 | +| policy_gradient_loss | -0.0624 | +| value_loss | 0.000647 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.255 | +| time/ | | +| fps | 309 | +| iterations | 4436 | +| time_elapsed | 14655 | +| total_timesteps | 4542464 | +| train/ | | +| approx_kl | 2.1556058 | +| clip_fraction | 0.417 | +| clip_range | 0.2 | +| entropy_loss | -0.278 | +| explained_variance | -0.987 | +| learning_rate | 0.0001 | +| loss | -0.0944 | +| n_updates | 104880 | +| policy_gradient_loss | -0.0521 | +| value_loss | 0.000605 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.252 | +| time/ | | +| fps | 309 | +| iterations | 4437 | +| time_elapsed | 14658 | +| total_timesteps | 4543488 | +| train/ | | +| approx_kl | 2.2547677 | +| clip_fraction | 0.407 | +| clip_range | 0.2 | +| entropy_loss | -0.249 | +| explained_variance | -0.42 | +| learning_rate | 0.0001 | +| loss | -0.0509 | +| n_updates | 104890 | +| policy_gradient_loss | -0.0579 | +| value_loss | 0.000732 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.252 | +| time/ | | +| fps | 309 | +| iterations | 4438 | +| time_elapsed | 14661 | +| total_timesteps | 4544512 | +| train/ | | +| approx_kl | 2.1145294 | +| clip_fraction | 0.416 | +| clip_range | 0.2 | +| entropy_loss | -0.265 | +| explained_variance | -3.39 | +| learning_rate | 0.0001 | +| loss | -0.0887 | +| n_updates | 104900 | +| policy_gradient_loss | -0.0516 | +| value_loss | 0.000494 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.251 | +| time/ | | +| fps | 309 | +| iterations | 4439 | +| time_elapsed | 14664 | +| total_timesteps | 4545536 | +| train/ | | +| approx_kl | 2.9235322 | +| clip_fraction | 0.413 | +| clip_range | 0.2 | +| entropy_loss | -0.278 | +| explained_variance | -0.298 | +| learning_rate | 0.0001 | +| loss | -0.0787 | +| n_updates | 104910 | +| policy_gradient_loss | -0.0431 | +| value_loss | 0.000839 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.251 | +| time/ | | +| fps | 309 | +| iterations | 4440 | +| time_elapsed | 14667 | +| total_timesteps | 4546560 | +| train/ | | +| approx_kl | 1.877008 | +| clip_fraction | 0.43 | +| clip_range | 0.2 | +| entropy_loss | -0.28 | +| explained_variance | -0.905 | +| learning_rate | 0.0001 | +| loss | -0.0571 | +| n_updates | 104920 | +| policy_gradient_loss | -0.053 | +| value_loss | 0.000518 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.253 | +| time/ | | +| fps | 309 | +| iterations | 4441 | +| time_elapsed | 14671 | +| total_timesteps | 4547584 | +| train/ | | +| approx_kl | 2.7833378 | +| clip_fraction | 0.479 | +| clip_range | 0.2 | +| entropy_loss | -0.316 | +| explained_variance | -0.768 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 104930 | +| policy_gradient_loss | -0.0668 | +| value_loss | 0.000683 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.248 | +| time/ | | +| fps | 309 | +| iterations | 4442 | +| time_elapsed | 14674 | +| total_timesteps | 4548608 | +| train/ | | +| approx_kl | 2.2501106 | +| clip_fraction | 0.432 | +| clip_range | 0.2 | +| entropy_loss | -0.309 | +| explained_variance | -0.384 | +| learning_rate | 0.0001 | +| loss | -0.0823 | +| n_updates | 104940 | +| policy_gradient_loss | -0.0608 | +| value_loss | 0.000553 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.248 | +| time/ | | +| fps | 309 | +| iterations | 4443 | +| time_elapsed | 14677 | +| total_timesteps | 4549632 | +| train/ | | +| approx_kl | 2.3187423 | +| clip_fraction | 0.424 | +| clip_range | 0.2 | +| entropy_loss | -0.276 | +| explained_variance | -0.989 | +| learning_rate | 0.0001 | +| loss | -0.066 | +| n_updates | 104950 | +| policy_gradient_loss | -0.0627 | +| value_loss | 0.000889 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.25 | +| time/ | | +| fps | 309 | +| iterations | 4444 | +| time_elapsed | 14681 | +| total_timesteps | 4550656 | +| train/ | | +| approx_kl | 2.179669 | +| clip_fraction | 0.425 | +| clip_range | 0.2 | +| entropy_loss | -0.267 | +| explained_variance | -4.74 | +| learning_rate | 0.0001 | +| loss | -0.0786 | +| n_updates | 104960 | +| policy_gradient_loss | -0.0622 | +| value_loss | 0.000962 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.25 | +| time/ | | +| fps | 309 | +| iterations | 4445 | +| time_elapsed | 14684 | +| total_timesteps | 4551680 | +| train/ | | +| approx_kl | 2.810934 | +| clip_fraction | 0.386 | +| clip_range | 0.2 | +| entropy_loss | -0.251 | +| explained_variance | -0.769 | +| learning_rate | 0.0001 | +| loss | -0.0747 | +| n_updates | 104970 | +| policy_gradient_loss | -0.0525 | +| value_loss | 0.000715 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.25 | +| time/ | | +| fps | 309 | +| iterations | 4446 | +| time_elapsed | 14688 | +| total_timesteps | 4552704 | +| train/ | | +| approx_kl | 2.7661848 | +| clip_fraction | 0.453 | +| clip_range | 0.2 | +| entropy_loss | -0.297 | +| explained_variance | -0.897 | +| learning_rate | 0.0001 | +| loss | -0.0728 | +| n_updates | 104980 | +| policy_gradient_loss | -0.0582 | +| value_loss | 0.000482 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.248 | +| time/ | | +| fps | 309 | +| iterations | 4447 | +| time_elapsed | 14691 | +| total_timesteps | 4553728 | +| train/ | | +| approx_kl | 2.0411167 | +| clip_fraction | 0.402 | +| clip_range | 0.2 | +| entropy_loss | -0.237 | +| explained_variance | -0.94 | +| learning_rate | 0.0001 | +| loss | -0.077 | +| n_updates | 104990 | +| policy_gradient_loss | -0.0554 | +| value_loss | 0.000584 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.251 | +| time/ | | +| fps | 309 | +| iterations | 4448 | +| time_elapsed | 14695 | +| total_timesteps | 4554752 | +| train/ | | +| approx_kl | 2.2234912 | +| clip_fraction | 0.429 | +| clip_range | 0.2 | +| entropy_loss | -0.275 | +| explained_variance | -1.66 | +| learning_rate | 0.0001 | +| loss | -0.0557 | +| n_updates | 105000 | +| policy_gradient_loss | -0.0564 | +| value_loss | 0.000587 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.251 | +| time/ | | +| fps | 309 | +| iterations | 4449 | +| time_elapsed | 14699 | +| total_timesteps | 4555776 | +| train/ | | +| approx_kl | 2.1359878 | +| clip_fraction | 0.418 | +| clip_range | 0.2 | +| entropy_loss | -0.277 | +| explained_variance | -0.545 | +| learning_rate | 0.0001 | +| loss | -0.0617 | +| n_updates | 105010 | +| policy_gradient_loss | -0.0536 | +| value_loss | 0.000557 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.251 | +| time/ | | +| fps | 309 | +| iterations | 4450 | +| time_elapsed | 14702 | +| total_timesteps | 4556800 | +| train/ | | +| approx_kl | 2.4389117 | +| clip_fraction | 0.401 | +| clip_range | 0.2 | +| entropy_loss | -0.263 | +| explained_variance | -1.34 | +| learning_rate | 0.0001 | +| loss | -0.0608 | +| n_updates | 105020 | +| policy_gradient_loss | -0.0548 | +| value_loss | 0.000534 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.253 | +| time/ | | +| fps | 309 | +| iterations | 4451 | +| time_elapsed | 14706 | +| total_timesteps | 4557824 | +| train/ | | +| approx_kl | 2.4119854 | +| clip_fraction | 0.422 | +| clip_range | 0.2 | +| entropy_loss | -0.255 | +| explained_variance | -0.681 | +| learning_rate | 0.0001 | +| loss | -0.0189 | +| n_updates | 105030 | +| policy_gradient_loss | -0.0565 | +| value_loss | 0.000529 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.258 | +| time/ | | +| fps | 309 | +| iterations | 4452 | +| time_elapsed | 14710 | +| total_timesteps | 4558848 | +| train/ | | +| approx_kl | 2.6127696 | +| clip_fraction | 0.401 | +| clip_range | 0.2 | +| entropy_loss | -0.252 | +| explained_variance | -0.994 | +| learning_rate | 0.0001 | +| loss | -0.071 | +| n_updates | 105040 | +| policy_gradient_loss | -0.0577 | +| value_loss | 0.000635 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.258 | +| time/ | | +| fps | 309 | +| iterations | 4453 | +| time_elapsed | 14713 | +| total_timesteps | 4559872 | +| train/ | | +| approx_kl | 1.9042623 | +| clip_fraction | 0.408 | +| clip_range | 0.2 | +| entropy_loss | -0.268 | +| explained_variance | -0.773 | +| learning_rate | 0.0001 | +| loss | -0.0691 | +| n_updates | 105050 | +| policy_gradient_loss | -0.0579 | +| value_loss | 0.000666 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.258 | +| time/ | | +| fps | 309 | +| iterations | 4454 | +| time_elapsed | 14716 | +| total_timesteps | 4560896 | +| train/ | | +| approx_kl | 1.6616151 | +| clip_fraction | 0.382 | +| clip_range | 0.2 | +| entropy_loss | -0.253 | +| explained_variance | -0.83 | +| learning_rate | 0.0001 | +| loss | -0.0973 | +| n_updates | 105060 | +| policy_gradient_loss | -0.0487 | +| value_loss | 0.000747 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.26 | +| time/ | | +| fps | 309 | +| iterations | 4455 | +| time_elapsed | 14719 | +| total_timesteps | 4561920 | +| train/ | | +| approx_kl | 2.551107 | +| clip_fraction | 0.464 | +| clip_range | 0.2 | +| entropy_loss | -0.298 | +| explained_variance | -1.92 | +| learning_rate | 0.0001 | +| loss | -0.0998 | +| n_updates | 105070 | +| policy_gradient_loss | -0.0665 | +| value_loss | 0.000634 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.264 | +| time/ | | +| fps | 309 | +| iterations | 4456 | +| time_elapsed | 14722 | +| total_timesteps | 4562944 | +| train/ | | +| approx_kl | 2.2071438 | +| clip_fraction | 0.37 | +| clip_range | 0.2 | +| entropy_loss | -0.217 | +| explained_variance | -1.23 | +| learning_rate | 0.0001 | +| loss | -0.0681 | +| n_updates | 105080 | +| policy_gradient_loss | -0.0532 | +| value_loss | 0.000657 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.264 | +| time/ | | +| fps | 309 | +| iterations | 4457 | +| time_elapsed | 14725 | +| total_timesteps | 4563968 | +| train/ | | +| approx_kl | 2.023901 | +| clip_fraction | 0.377 | +| clip_range | 0.2 | +| entropy_loss | -0.242 | +| explained_variance | -0.511 | +| learning_rate | 0.0001 | +| loss | -0.0779 | +| n_updates | 105090 | +| policy_gradient_loss | -0.0603 | +| value_loss | 0.000668 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.266 | +| time/ | | +| fps | 309 | +| iterations | 4458 | +| time_elapsed | 14729 | +| total_timesteps | 4564992 | +| train/ | | +| approx_kl | 2.0074375 | +| clip_fraction | 0.409 | +| clip_range | 0.2 | +| entropy_loss | -0.278 | +| explained_variance | -3.12 | +| learning_rate | 0.0001 | +| loss | -0.0773 | +| n_updates | 105100 | +| policy_gradient_loss | -0.057 | +| value_loss | 0.000451 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.272 | +| time/ | | +| fps | 309 | +| iterations | 4459 | +| time_elapsed | 14732 | +| total_timesteps | 4566016 | +| train/ | | +| approx_kl | 2.4669194 | +| clip_fraction | 0.427 | +| clip_range | 0.2 | +| entropy_loss | -0.258 | +| explained_variance | -0.688 | +| learning_rate | 0.0001 | +| loss | -0.0816 | +| n_updates | 105110 | +| policy_gradient_loss | -0.0596 | +| value_loss | 0.000594 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.271 | +| time/ | | +| fps | 309 | +| iterations | 4460 | +| time_elapsed | 14735 | +| total_timesteps | 4567040 | +| train/ | | +| approx_kl | 2.0252671 | +| clip_fraction | 0.405 | +| clip_range | 0.2 | +| entropy_loss | -0.279 | +| explained_variance | -0.435 | +| learning_rate | 0.0001 | +| loss | -0.0555 | +| n_updates | 105120 | +| policy_gradient_loss | -0.0566 | +| value_loss | 0.00073 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 309 | +| iterations | 4461 | +| time_elapsed | 14738 | +| total_timesteps | 4568064 | +| train/ | | +| approx_kl | 2.6684973 | +| clip_fraction | 0.441 | +| clip_range | 0.2 | +| entropy_loss | -0.295 | +| explained_variance | -0.664 | +| learning_rate | 0.0001 | +| loss | -0.0879 | +| n_updates | 105130 | +| policy_gradient_loss | -0.0598 | +| value_loss | 0.000817 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.281 | +| time/ | | +| fps | 309 | +| iterations | 4462 | +| time_elapsed | 14742 | +| total_timesteps | 4569088 | +| train/ | | +| approx_kl | 2.718916 | +| clip_fraction | 0.399 | +| clip_range | 0.2 | +| entropy_loss | -0.235 | +| explained_variance | -0.73 | +| learning_rate | 0.0001 | +| loss | -0.0776 | +| n_updates | 105140 | +| policy_gradient_loss | -0.0602 | +| value_loss | 0.000776 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.281 | +| time/ | | +| fps | 309 | +| iterations | 4463 | +| time_elapsed | 14745 | +| total_timesteps | 4570112 | +| train/ | | +| approx_kl | 1.9568274 | +| clip_fraction | 0.39 | +| clip_range | 0.2 | +| entropy_loss | -0.254 | +| explained_variance | -0.32 | +| learning_rate | 0.0001 | +| loss | -0.0718 | +| n_updates | 105150 | +| policy_gradient_loss | -0.0471 | +| value_loss | 0.000505 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 309 | +| iterations | 4464 | +| time_elapsed | 14749 | +| total_timesteps | 4571136 | +| train/ | | +| approx_kl | 1.9334636 | +| clip_fraction | 0.42 | +| clip_range | 0.2 | +| entropy_loss | -0.274 | +| explained_variance | -2.25 | +| learning_rate | 0.0001 | +| loss | -0.0565 | +| n_updates | 105160 | +| policy_gradient_loss | -0.0607 | +| value_loss | 0.000567 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 309 | +| iterations | 4465 | +| time_elapsed | 14752 | +| total_timesteps | 4572160 | +| train/ | | +| approx_kl | 2.0903544 | +| clip_fraction | 0.378 | +| clip_range | 0.2 | +| entropy_loss | -0.243 | +| explained_variance | -0.891 | +| learning_rate | 0.0001 | +| loss | -0.0799 | +| n_updates | 105170 | +| policy_gradient_loss | -0.0533 | +| value_loss | 0.000595 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.281 | +| time/ | | +| fps | 309 | +| iterations | 4466 | +| time_elapsed | 14756 | +| total_timesteps | 4573184 | +| train/ | | +| approx_kl | 2.3388417 | +| clip_fraction | 0.446 | +| clip_range | 0.2 | +| entropy_loss | -0.303 | +| explained_variance | -1.71 | +| learning_rate | 0.0001 | +| loss | -0.107 | +| n_updates | 105180 | +| policy_gradient_loss | -0.0615 | +| value_loss | 0.00046 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.28 | +| time/ | | +| fps | 309 | +| iterations | 4467 | +| time_elapsed | 14759 | +| total_timesteps | 4574208 | +| train/ | | +| approx_kl | 3.7543173 | +| clip_fraction | 0.395 | +| clip_range | 0.2 | +| entropy_loss | -0.223 | +| explained_variance | -1.13 | +| learning_rate | 0.0001 | +| loss | -0.0716 | +| n_updates | 105190 | +| policy_gradient_loss | -0.0547 | +| value_loss | 0.000701 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.28 | +| time/ | | +| fps | 309 | +| iterations | 4468 | +| time_elapsed | 14763 | +| total_timesteps | 4575232 | +| train/ | | +| approx_kl | 3.5580497 | +| clip_fraction | 0.385 | +| clip_range | 0.2 | +| entropy_loss | -0.225 | +| explained_variance | -0.953 | +| learning_rate | 0.0001 | +| loss | -0.0453 | +| n_updates | 105200 | +| policy_gradient_loss | -0.0557 | +| value_loss | 0.000529 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.284 | +| time/ | | +| fps | 309 | +| iterations | 4469 | +| time_elapsed | 14766 | +| total_timesteps | 4576256 | +| train/ | | +| approx_kl | 2.786312 | +| clip_fraction | 0.463 | +| clip_range | 0.2 | +| entropy_loss | -0.294 | +| explained_variance | -1.99 | +| learning_rate | 0.0001 | +| loss | -0.0682 | +| n_updates | 105210 | +| policy_gradient_loss | -0.0593 | +| value_loss | 0.000493 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.283 | +| time/ | | +| fps | 309 | +| iterations | 4470 | +| time_elapsed | 14770 | +| total_timesteps | 4577280 | +| train/ | | +| approx_kl | 3.4122567 | +| clip_fraction | 0.43 | +| clip_range | 0.2 | +| entropy_loss | -0.28 | +| explained_variance | -0.816 | +| learning_rate | 0.0001 | +| loss | -0.0575 | +| n_updates | 105220 | +| policy_gradient_loss | -0.0552 | +| value_loss | 0.000581 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.283 | +| time/ | | +| fps | 309 | +| iterations | 4471 | +| time_elapsed | 14773 | +| total_timesteps | 4578304 | +| train/ | | +| approx_kl | 2.5213594 | +| clip_fraction | 0.405 | +| clip_range | 0.2 | +| entropy_loss | -0.256 | +| explained_variance | -1.53 | +| learning_rate | 0.0001 | +| loss | -0.0959 | +| n_updates | 105230 | +| policy_gradient_loss | -0.0593 | +| value_loss | 0.000613 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.283 | +| time/ | | +| fps | 309 | +| iterations | 4472 | +| time_elapsed | 14776 | +| total_timesteps | 4579328 | +| train/ | | +| approx_kl | 2.360035 | +| clip_fraction | 0.41 | +| clip_range | 0.2 | +| entropy_loss | -0.263 | +| explained_variance | -1.96 | +| learning_rate | 0.0001 | +| loss | -0.0833 | +| n_updates | 105240 | +| policy_gradient_loss | -0.0591 | +| value_loss | 0.000672 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 309 | +| iterations | 4473 | +| time_elapsed | 14779 | +| total_timesteps | 4580352 | +| train/ | | +| approx_kl | 2.372908 | +| clip_fraction | 0.419 | +| clip_range | 0.2 | +| entropy_loss | -0.243 | +| explained_variance | -0.564 | +| learning_rate | 0.0001 | +| loss | -0.0681 | +| n_updates | 105250 | +| policy_gradient_loss | -0.0587 | +| value_loss | 0.0009 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 309 | +| iterations | 4474 | +| time_elapsed | 14783 | +| total_timesteps | 4581376 | +| train/ | | +| approx_kl | 3.4196 | +| clip_fraction | 0.406 | +| clip_range | 0.2 | +| entropy_loss | -0.249 | +| explained_variance | -0.982 | +| learning_rate | 0.0001 | +| loss | -0.0645 | +| n_updates | 105260 | +| policy_gradient_loss | -0.0631 | +| value_loss | 0.000882 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 309 | +| iterations | 4475 | +| time_elapsed | 14786 | +| total_timesteps | 4582400 | +| train/ | | +| approx_kl | 2.0552688 | +| clip_fraction | 0.382 | +| clip_range | 0.2 | +| entropy_loss | -0.255 | +| explained_variance | -0.485 | +| learning_rate | 0.0001 | +| loss | -0.0745 | +| n_updates | 105270 | +| policy_gradient_loss | -0.0509 | +| value_loss | 0.000683 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 309 | +| iterations | 4476 | +| time_elapsed | 14789 | +| total_timesteps | 4583424 | +| train/ | | +| approx_kl | 2.2655978 | +| clip_fraction | 0.402 | +| clip_range | 0.2 | +| entropy_loss | -0.27 | +| explained_variance | -0.0295 | +| learning_rate | 0.0001 | +| loss | -0.0932 | +| n_updates | 105280 | +| policy_gradient_loss | -0.0637 | +| value_loss | 0.000881 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 309 | +| iterations | 4477 | +| time_elapsed | 14792 | +| total_timesteps | 4584448 | +| train/ | | +| approx_kl | 4.5725474 | +| clip_fraction | 0.446 | +| clip_range | 0.2 | +| entropy_loss | -0.293 | +| explained_variance | -5.84 | +| learning_rate | 0.0001 | +| loss | -0.0891 | +| n_updates | 105290 | +| policy_gradient_loss | -0.0647 | +| value_loss | 0.000438 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 309 | +| iterations | 4478 | +| time_elapsed | 14796 | +| total_timesteps | 4585472 | +| train/ | | +| approx_kl | 2.0112474 | +| clip_fraction | 0.405 | +| clip_range | 0.2 | +| entropy_loss | -0.257 | +| explained_variance | -0.381 | +| learning_rate | 0.0001 | +| loss | -0.0631 | +| n_updates | 105300 | +| policy_gradient_loss | -0.046 | +| value_loss | 0.000596 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 309 | +| iterations | 4479 | +| time_elapsed | 14799 | +| total_timesteps | 4586496 | +| train/ | | +| approx_kl | 2.5090165 | +| clip_fraction | 0.426 | +| clip_range | 0.2 | +| entropy_loss | -0.27 | +| explained_variance | -1.23 | +| learning_rate | 0.0001 | +| loss | -0.097 | +| n_updates | 105310 | +| policy_gradient_loss | -0.0632 | +| value_loss | 0.00051 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.277 | +| time/ | | +| fps | 309 | +| iterations | 4480 | +| time_elapsed | 14802 | +| total_timesteps | 4587520 | +| train/ | | +| approx_kl | 2.5195322 | +| clip_fraction | 0.448 | +| clip_range | 0.2 | +| entropy_loss | -0.303 | +| explained_variance | -2.78 | +| learning_rate | 0.0001 | +| loss | -0.0707 | +| n_updates | 105320 | +| policy_gradient_loss | -0.0637 | +| value_loss | 0.000517 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.277 | +| time/ | | +| fps | 309 | +| iterations | 4481 | +| time_elapsed | 14806 | +| total_timesteps | 4588544 | +| train/ | | +| approx_kl | 2.4271033 | +| clip_fraction | 0.392 | +| clip_range | 0.2 | +| entropy_loss | -0.243 | +| explained_variance | -0.703 | +| learning_rate | 0.0001 | +| loss | -0.0763 | +| n_updates | 105330 | +| policy_gradient_loss | -0.0605 | +| value_loss | 0.000523 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.278 | +| time/ | | +| fps | 309 | +| iterations | 4482 | +| time_elapsed | 14809 | +| total_timesteps | 4589568 | +| train/ | | +| approx_kl | 1.6018188 | +| clip_fraction | 0.367 | +| clip_range | 0.2 | +| entropy_loss | -0.235 | +| explained_variance | -0.402 | +| learning_rate | 0.0001 | +| loss | -0.0533 | +| n_updates | 105340 | +| policy_gradient_loss | -0.0454 | +| value_loss | 0.000585 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.281 | +| time/ | | +| fps | 309 | +| iterations | 4483 | +| time_elapsed | 14813 | +| total_timesteps | 4590592 | +| train/ | | +| approx_kl | 2.1480553 | +| clip_fraction | 0.392 | +| clip_range | 0.2 | +| entropy_loss | -0.234 | +| explained_variance | -0.289 | +| learning_rate | 0.0001 | +| loss | -0.0802 | +| n_updates | 105350 | +| policy_gradient_loss | -0.0612 | +| value_loss | 0.000532 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.281 | +| time/ | | +| fps | 309 | +| iterations | 4484 | +| time_elapsed | 14816 | +| total_timesteps | 4591616 | +| train/ | | +| approx_kl | 2.3470387 | +| clip_fraction | 0.427 | +| clip_range | 0.2 | +| entropy_loss | -0.252 | +| explained_variance | -0.284 | +| learning_rate | 0.0001 | +| loss | -0.0846 | +| n_updates | 105360 | +| policy_gradient_loss | -0.0624 | +| value_loss | 0.000716 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 309 | +| iterations | 4485 | +| time_elapsed | 14819 | +| total_timesteps | 4592640 | +| train/ | | +| approx_kl | 8.178195 | +| clip_fraction | 0.459 | +| clip_range | 0.2 | +| entropy_loss | -0.296 | +| explained_variance | -4.33 | +| learning_rate | 0.0001 | +| loss | -0.0923 | +| n_updates | 105370 | +| policy_gradient_loss | -0.0582 | +| value_loss | 0.000558 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 309 | +| iterations | 4486 | +| time_elapsed | 14823 | +| total_timesteps | 4593664 | +| train/ | | +| approx_kl | 1.9426903 | +| clip_fraction | 0.387 | +| clip_range | 0.2 | +| entropy_loss | -0.259 | +| explained_variance | -0.611 | +| learning_rate | 0.0001 | +| loss | -0.0778 | +| n_updates | 105380 | +| policy_gradient_loss | -0.0509 | +| value_loss | 0.000605 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.28 | +| time/ | | +| fps | 309 | +| iterations | 4487 | +| time_elapsed | 14826 | +| total_timesteps | 4594688 | +| train/ | | +| approx_kl | 1.7169484 | +| clip_fraction | 0.39 | +| clip_range | 0.2 | +| entropy_loss | -0.266 | +| explained_variance | -1.37 | +| learning_rate | 0.0001 | +| loss | -0.0728 | +| n_updates | 105390 | +| policy_gradient_loss | -0.055 | +| value_loss | 0.00081 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 309 | +| iterations | 4488 | +| time_elapsed | 14830 | +| total_timesteps | 4595712 | +| train/ | | +| approx_kl | 1.596564 | +| clip_fraction | 0.284 | +| clip_range | 0.2 | +| entropy_loss | -0.181 | +| explained_variance | -0.107 | +| learning_rate | 0.0001 | +| loss | -0.0421 | +| n_updates | 105400 | +| policy_gradient_loss | -0.0443 | +| value_loss | 0.00107 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.28 | +| time/ | | +| fps | 309 | +| iterations | 4489 | +| time_elapsed | 14833 | +| total_timesteps | 4596736 | +| train/ | | +| approx_kl | 2.7300706 | +| clip_fraction | 0.363 | +| clip_range | 0.2 | +| entropy_loss | -0.23 | +| explained_variance | -1.86 | +| learning_rate | 0.0001 | +| loss | -0.0791 | +| n_updates | 105410 | +| policy_gradient_loss | -0.0527 | +| value_loss | 0.00058 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 309 | +| iterations | 4490 | +| time_elapsed | 14836 | +| total_timesteps | 4597760 | +| train/ | | +| approx_kl | 1.885646 | +| clip_fraction | 0.366 | +| clip_range | 0.2 | +| entropy_loss | -0.251 | +| explained_variance | 0.109 | +| learning_rate | 0.0001 | +| loss | -0.0513 | +| n_updates | 105420 | +| policy_gradient_loss | -0.0433 | +| value_loss | 0.000892 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 309 | +| iterations | 4491 | +| time_elapsed | 14839 | +| total_timesteps | 4598784 | +| train/ | | +| approx_kl | 2.1922889 | +| clip_fraction | 0.363 | +| clip_range | 0.2 | +| entropy_loss | -0.22 | +| explained_variance | -1.87 | +| learning_rate | 0.0001 | +| loss | -0.061 | +| n_updates | 105430 | +| policy_gradient_loss | -0.0531 | +| value_loss | 0.00103 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.278 | +| time/ | | +| fps | 309 | +| iterations | 4492 | +| time_elapsed | 14842 | +| total_timesteps | 4599808 | +| train/ | | +| approx_kl | 3.8406491 | +| clip_fraction | 0.443 | +| clip_range | 0.2 | +| entropy_loss | -0.311 | +| explained_variance | -1.41 | +| learning_rate | 0.0001 | +| loss | -0.0813 | +| n_updates | 105440 | +| policy_gradient_loss | -0.0572 | +| value_loss | 0.000602 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 309 | +| iterations | 4493 | +| time_elapsed | 14846 | +| total_timesteps | 4600832 | +| train/ | | +| approx_kl | 2.2521 | +| clip_fraction | 0.406 | +| clip_range | 0.2 | +| entropy_loss | -0.258 | +| explained_variance | -1.87 | +| learning_rate | 0.0001 | +| loss | -0.0534 | +| n_updates | 105450 | +| policy_gradient_loss | -0.0528 | +| value_loss | 0.00053 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 309 | +| iterations | 4494 | +| time_elapsed | 14849 | +| total_timesteps | 4601856 | +| train/ | | +| approx_kl | 1.9237007 | +| clip_fraction | 0.447 | +| clip_range | 0.2 | +| entropy_loss | -0.294 | +| explained_variance | -0.667 | +| learning_rate | 0.0001 | +| loss | -0.0975 | +| n_updates | 105460 | +| policy_gradient_loss | -0.0578 | +| value_loss | 0.000599 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 309 | +| iterations | 4495 | +| time_elapsed | 14852 | +| total_timesteps | 4602880 | +| train/ | | +| approx_kl | 6.8665853 | +| clip_fraction | 0.412 | +| clip_range | 0.2 | +| entropy_loss | -0.294 | +| explained_variance | -1.2 | +| learning_rate | 0.0001 | +| loss | -0.0914 | +| n_updates | 105470 | +| policy_gradient_loss | -0.054 | +| value_loss | 0.000615 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.276 | +| time/ | | +| fps | 309 | +| iterations | 4496 | +| time_elapsed | 14855 | +| total_timesteps | 4603904 | +| train/ | | +| approx_kl | 2.4946446 | +| clip_fraction | 0.426 | +| clip_range | 0.2 | +| entropy_loss | -0.285 | +| explained_variance | -4.24 | +| learning_rate | 0.0001 | +| loss | -0.0781 | +| n_updates | 105480 | +| policy_gradient_loss | -0.0665 | +| value_loss | 0.00039 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 309 | +| iterations | 4497 | +| time_elapsed | 14859 | +| total_timesteps | 4604928 | +| train/ | | +| approx_kl | 2.4185617 | +| clip_fraction | 0.419 | +| clip_range | 0.2 | +| entropy_loss | -0.27 | +| explained_variance | -0.853 | +| learning_rate | 0.0001 | +| loss | -0.0727 | +| n_updates | 105490 | +| policy_gradient_loss | -0.0595 | +| value_loss | 0.000532 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.273 | +| time/ | | +| fps | 309 | +| iterations | 4498 | +| time_elapsed | 14862 | +| total_timesteps | 4605952 | +| train/ | | +| approx_kl | 2.672334 | +| clip_fraction | 0.436 | +| clip_range | 0.2 | +| entropy_loss | -0.285 | +| explained_variance | -0.52 | +| learning_rate | 0.0001 | +| loss | -0.0861 | +| n_updates | 105500 | +| policy_gradient_loss | -0.059 | +| value_loss | 0.000907 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.278 | +| time/ | | +| fps | 309 | +| iterations | 4499 | +| time_elapsed | 14866 | +| total_timesteps | 4606976 | +| train/ | | +| approx_kl | 2.3693364 | +| clip_fraction | 0.431 | +| clip_range | 0.2 | +| entropy_loss | -0.3 | +| explained_variance | -0.488 | +| learning_rate | 0.0001 | +| loss | -0.0709 | +| n_updates | 105510 | +| policy_gradient_loss | -0.0593 | +| value_loss | 0.00071 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.278 | +| time/ | | +| fps | 309 | +| iterations | 4500 | +| time_elapsed | 14869 | +| total_timesteps | 4608000 | +| train/ | | +| approx_kl | 2.410985 | +| clip_fraction | 0.454 | +| clip_range | 0.2 | +| entropy_loss | -0.316 | +| explained_variance | -1.39 | +| learning_rate | 0.0001 | +| loss | -0.0714 | +| n_updates | 105520 | +| policy_gradient_loss | -0.0618 | +| value_loss | 0.000689 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.276 | +| time/ | | +| fps | 309 | +| iterations | 4501 | +| time_elapsed | 14873 | +| total_timesteps | 4609024 | +| train/ | | +| approx_kl | 2.711258 | +| clip_fraction | 0.389 | +| clip_range | 0.2 | +| entropy_loss | -0.248 | +| explained_variance | -0.655 | +| learning_rate | 0.0001 | +| loss | -0.0769 | +| n_updates | 105530 | +| policy_gradient_loss | -0.0517 | +| value_loss | 0.000632 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.276 | +| time/ | | +| fps | 309 | +| iterations | 4502 | +| time_elapsed | 14876 | +| total_timesteps | 4610048 | +| train/ | | +| approx_kl | 3.8067331 | +| clip_fraction | 0.407 | +| clip_range | 0.2 | +| entropy_loss | -0.263 | +| explained_variance | -0.982 | +| learning_rate | 0.0001 | +| loss | -0.0968 | +| n_updates | 105540 | +| policy_gradient_loss | -0.0616 | +| value_loss | 0.000567 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 309 | +| iterations | 4503 | +| time_elapsed | 14880 | +| total_timesteps | 4611072 | +| train/ | | +| approx_kl | 2.0274029 | +| clip_fraction | 0.43 | +| clip_range | 0.2 | +| entropy_loss | -0.297 | +| explained_variance | -1.83 | +| learning_rate | 0.0001 | +| loss | -0.0846 | +| n_updates | 105550 | +| policy_gradient_loss | -0.063 | +| value_loss | 0.000622 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.277 | +| time/ | | +| fps | 309 | +| iterations | 4504 | +| time_elapsed | 14883 | +| total_timesteps | 4612096 | +| train/ | | +| approx_kl | 2.0317476 | +| clip_fraction | 0.4 | +| clip_range | 0.2 | +| entropy_loss | -0.274 | +| explained_variance | -0.701 | +| learning_rate | 0.0001 | +| loss | -0.0543 | +| n_updates | 105560 | +| policy_gradient_loss | -0.0557 | +| value_loss | 0.000428 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.277 | +| time/ | | +| fps | 309 | +| iterations | 4505 | +| time_elapsed | 14886 | +| total_timesteps | 4613120 | +| train/ | | +| approx_kl | 2.2170606 | +| clip_fraction | 0.387 | +| clip_range | 0.2 | +| entropy_loss | -0.251 | +| explained_variance | -0.365 | +| learning_rate | 0.0001 | +| loss | -0.0781 | +| n_updates | 105570 | +| policy_gradient_loss | -0.0558 | +| value_loss | 0.000837 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.278 | +| time/ | | +| fps | 309 | +| iterations | 4506 | +| time_elapsed | 14890 | +| total_timesteps | 4614144 | +| train/ | | +| approx_kl | 2.392173 | +| clip_fraction | 0.396 | +| clip_range | 0.2 | +| entropy_loss | -0.258 | +| explained_variance | -1.04 | +| learning_rate | 0.0001 | +| loss | -0.0793 | +| n_updates | 105580 | +| policy_gradient_loss | -0.0636 | +| value_loss | 0.000888 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.276 | +| time/ | | +| fps | 309 | +| iterations | 4507 | +| time_elapsed | 14893 | +| total_timesteps | 4615168 | +| train/ | | +| approx_kl | 2.3335595 | +| clip_fraction | 0.414 | +| clip_range | 0.2 | +| entropy_loss | -0.26 | +| explained_variance | -0.866 | +| learning_rate | 0.0001 | +| loss | -0.0667 | +| n_updates | 105590 | +| policy_gradient_loss | -0.0585 | +| value_loss | 0.000522 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.274 | +| time/ | | +| fps | 309 | +| iterations | 4508 | +| time_elapsed | 14896 | +| total_timesteps | 4616192 | +| train/ | | +| approx_kl | 2.0534773 | +| clip_fraction | 0.432 | +| clip_range | 0.2 | +| entropy_loss | -0.293 | +| explained_variance | -0.267 | +| learning_rate | 0.0001 | +| loss | -0.0583 | +| n_updates | 105600 | +| policy_gradient_loss | -0.0589 | +| value_loss | 0.000444 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.274 | +| time/ | | +| fps | 309 | +| iterations | 4509 | +| time_elapsed | 14899 | +| total_timesteps | 4617216 | +| train/ | | +| approx_kl | 1.9582405 | +| clip_fraction | 0.418 | +| clip_range | 0.2 | +| entropy_loss | -0.275 | +| explained_variance | -0.373 | +| learning_rate | 0.0001 | +| loss | -0.0646 | +| n_updates | 105610 | +| policy_gradient_loss | -0.0571 | +| value_loss | 0.000629 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 309 | +| iterations | 4510 | +| time_elapsed | 14902 | +| total_timesteps | 4618240 | +| train/ | | +| approx_kl | 2.8601637 | +| clip_fraction | 0.464 | +| clip_range | 0.2 | +| entropy_loss | -0.322 | +| explained_variance | -2.48 | +| learning_rate | 0.0001 | +| loss | -0.11 | +| n_updates | 105620 | +| policy_gradient_loss | -0.0675 | +| value_loss | 0.000608 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 309 | +| iterations | 4511 | +| time_elapsed | 14906 | +| total_timesteps | 4619264 | +| train/ | | +| approx_kl | 2.2807407 | +| clip_fraction | 0.42 | +| clip_range | 0.2 | +| entropy_loss | -0.283 | +| explained_variance | -0.549 | +| learning_rate | 0.0001 | +| loss | -0.0778 | +| n_updates | 105630 | +| policy_gradient_loss | -0.0571 | +| value_loss | 0.000473 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.284 | +| time/ | | +| fps | 309 | +| iterations | 4512 | +| time_elapsed | 14909 | +| total_timesteps | 4620288 | +| train/ | | +| approx_kl | 2.0862803 | +| clip_fraction | 0.417 | +| clip_range | 0.2 | +| entropy_loss | -0.304 | +| explained_variance | -0.745 | +| learning_rate | 0.0001 | +| loss | -0.0693 | +| n_updates | 105640 | +| policy_gradient_loss | -0.0605 | +| value_loss | 0.000476 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.292 | +| time/ | | +| fps | 309 | +| iterations | 4513 | +| time_elapsed | 14912 | +| total_timesteps | 4621312 | +| train/ | | +| approx_kl | 2.0951746 | +| clip_fraction | 0.416 | +| clip_range | 0.2 | +| entropy_loss | -0.264 | +| explained_variance | -0.172 | +| learning_rate | 0.0001 | +| loss | -0.0556 | +| n_updates | 105650 | +| policy_gradient_loss | -0.0585 | +| value_loss | 0.000929 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 309 | +| iterations | 4514 | +| time_elapsed | 14915 | +| total_timesteps | 4622336 | +| train/ | | +| approx_kl | 2.2936926 | +| clip_fraction | 0.458 | +| clip_range | 0.2 | +| entropy_loss | -0.301 | +| explained_variance | -1.11 | +| learning_rate | 0.0001 | +| loss | -0.0664 | +| n_updates | 105660 | +| policy_gradient_loss | -0.0707 | +| value_loss | 0.000872 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 309 | +| iterations | 4515 | +| time_elapsed | 14919 | +| total_timesteps | 4623360 | +| train/ | | +| approx_kl | 2.811685 | +| clip_fraction | 0.408 | +| clip_range | 0.2 | +| entropy_loss | -0.258 | +| explained_variance | -1.09 | +| learning_rate | 0.0001 | +| loss | -0.0384 | +| n_updates | 105670 | +| policy_gradient_loss | -0.0589 | +| value_loss | 0.000893 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 309 | +| iterations | 4516 | +| time_elapsed | 14922 | +| total_timesteps | 4624384 | +| train/ | | +| approx_kl | 2.522706 | +| clip_fraction | 0.439 | +| clip_range | 0.2 | +| entropy_loss | -0.314 | +| explained_variance | -1.58 | +| learning_rate | 0.0001 | +| loss | -0.0915 | +| n_updates | 105680 | +| policy_gradient_loss | -0.0626 | +| value_loss | 0.000673 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.298 | +| time/ | | +| fps | 309 | +| iterations | 4517 | +| time_elapsed | 14925 | +| total_timesteps | 4625408 | +| train/ | | +| approx_kl | 2.2624998 | +| clip_fraction | 0.428 | +| clip_range | 0.2 | +| entropy_loss | -0.265 | +| explained_variance | -1.99 | +| learning_rate | 0.0001 | +| loss | -0.0896 | +| n_updates | 105690 | +| policy_gradient_loss | -0.0629 | +| value_loss | 0.000481 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 309 | +| iterations | 4518 | +| time_elapsed | 14929 | +| total_timesteps | 4626432 | +| train/ | | +| approx_kl | 2.3549194 | +| clip_fraction | 0.457 | +| clip_range | 0.2 | +| entropy_loss | -0.31 | +| explained_variance | -0.977 | +| learning_rate | 0.0001 | +| loss | -0.077 | +| n_updates | 105700 | +| policy_gradient_loss | -0.0641 | +| value_loss | 0.000817 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.306 | +| time/ | | +| fps | 309 | +| iterations | 4519 | +| time_elapsed | 14932 | +| total_timesteps | 4627456 | +| train/ | | +| approx_kl | 2.3559456 | +| clip_fraction | 0.45 | +| clip_range | 0.2 | +| entropy_loss | -0.327 | +| explained_variance | -0.335 | +| learning_rate | 0.0001 | +| loss | -0.0812 | +| n_updates | 105710 | +| policy_gradient_loss | -0.0623 | +| value_loss | 0.000718 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 309 | +| iterations | 4520 | +| time_elapsed | 14935 | +| total_timesteps | 4628480 | +| train/ | | +| approx_kl | 2.7683444 | +| clip_fraction | 0.424 | +| clip_range | 0.2 | +| entropy_loss | -0.299 | +| explained_variance | -0.643 | +| learning_rate | 0.0001 | +| loss | -0.0966 | +| n_updates | 105720 | +| policy_gradient_loss | -0.0603 | +| value_loss | 0.000708 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 309 | +| iterations | 4521 | +| time_elapsed | 14939 | +| total_timesteps | 4629504 | +| train/ | | +| approx_kl | 2.4689522 | +| clip_fraction | 0.439 | +| clip_range | 0.2 | +| entropy_loss | -0.29 | +| explained_variance | -0.34 | +| learning_rate | 0.0001 | +| loss | -0.0766 | +| n_updates | 105730 | +| policy_gradient_loss | -0.0646 | +| value_loss | 0.000956 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.302 | +| time/ | | +| fps | 309 | +| iterations | 4522 | +| time_elapsed | 14942 | +| total_timesteps | 4630528 | +| train/ | | +| approx_kl | 1.8009132 | +| clip_fraction | 0.476 | +| clip_range | 0.2 | +| entropy_loss | -0.348 | +| explained_variance | -3.21 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 105740 | +| policy_gradient_loss | -0.0665 | +| value_loss | 0.000843 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.302 | +| time/ | | +| fps | 309 | +| iterations | 4523 | +| time_elapsed | 14945 | +| total_timesteps | 4631552 | +| train/ | | +| approx_kl | 2.2038627 | +| clip_fraction | 0.351 | +| clip_range | 0.2 | +| entropy_loss | -0.227 | +| explained_variance | -0.159 | +| learning_rate | 0.0001 | +| loss | -0.0683 | +| n_updates | 105750 | +| policy_gradient_loss | -0.0379 | +| value_loss | 0.00043 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.306 | +| time/ | | +| fps | 309 | +| iterations | 4524 | +| time_elapsed | 14949 | +| total_timesteps | 4632576 | +| train/ | | +| approx_kl | 1.954253 | +| clip_fraction | 0.446 | +| clip_range | 0.2 | +| entropy_loss | -0.303 | +| explained_variance | -1.82 | +| learning_rate | 0.0001 | +| loss | -0.105 | +| n_updates | 105760 | +| policy_gradient_loss | -0.0586 | +| value_loss | 0.000471 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 309 | +| iterations | 4525 | +| time_elapsed | 14952 | +| total_timesteps | 4633600 | +| train/ | | +| approx_kl | 1.9369862 | +| clip_fraction | 0.42 | +| clip_range | 0.2 | +| entropy_loss | -0.342 | +| explained_variance | -0.657 | +| learning_rate | 0.0001 | +| loss | -0.0679 | +| n_updates | 105770 | +| policy_gradient_loss | -0.053 | +| value_loss | 0.000525 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 309 | +| iterations | 4526 | +| time_elapsed | 14955 | +| total_timesteps | 4634624 | +| train/ | | +| approx_kl | 2.0350873 | +| clip_fraction | 0.422 | +| clip_range | 0.2 | +| entropy_loss | -0.326 | +| explained_variance | 0.0203 | +| learning_rate | 0.0001 | +| loss | -0.058 | +| n_updates | 105780 | +| policy_gradient_loss | -0.0591 | +| value_loss | 0.000624 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 309 | +| iterations | 4527 | +| time_elapsed | 14958 | +| total_timesteps | 4635648 | +| train/ | | +| approx_kl | 1.6209242 | +| clip_fraction | 0.396 | +| clip_range | 0.2 | +| entropy_loss | -0.28 | +| explained_variance | -0.331 | +| learning_rate | 0.0001 | +| loss | -0.0625 | +| n_updates | 105790 | +| policy_gradient_loss | -0.0565 | +| value_loss | 0.000602 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 309 | +| iterations | 4528 | +| time_elapsed | 14961 | +| total_timesteps | 4636672 | +| train/ | | +| approx_kl | 1.6645432 | +| clip_fraction | 0.41 | +| clip_range | 0.2 | +| entropy_loss | -0.303 | +| explained_variance | -0.893 | +| learning_rate | 0.0001 | +| loss | -0.0706 | +| n_updates | 105800 | +| policy_gradient_loss | -0.052 | +| value_loss | 0.000694 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 309 | +| iterations | 4529 | +| time_elapsed | 14965 | +| total_timesteps | 4637696 | +| train/ | | +| approx_kl | 2.565936 | +| clip_fraction | 0.497 | +| clip_range | 0.2 | +| entropy_loss | -0.33 | +| explained_variance | -1.37 | +| learning_rate | 0.0001 | +| loss | -0.0908 | +| n_updates | 105810 | +| policy_gradient_loss | -0.0627 | +| value_loss | 0.000461 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 309 | +| iterations | 4530 | +| time_elapsed | 14968 | +| total_timesteps | 4638720 | +| train/ | | +| approx_kl | 2.014902 | +| clip_fraction | 0.414 | +| clip_range | 0.2 | +| entropy_loss | -0.279 | +| explained_variance | -0.822 | +| learning_rate | 0.0001 | +| loss | -0.0585 | +| n_updates | 105820 | +| policy_gradient_loss | -0.0569 | +| value_loss | 0.000574 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 309 | +| iterations | 4531 | +| time_elapsed | 14971 | +| total_timesteps | 4639744 | +| train/ | | +| approx_kl | 3.1991436 | +| clip_fraction | 0.47 | +| clip_range | 0.2 | +| entropy_loss | -0.302 | +| explained_variance | -0.0772 | +| learning_rate | 0.0001 | +| loss | -0.0965 | +| n_updates | 105830 | +| policy_gradient_loss | -0.0619 | +| value_loss | 0.000671 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 309 | +| iterations | 4532 | +| time_elapsed | 14974 | +| total_timesteps | 4640768 | +| train/ | | +| approx_kl | 2.6414912 | +| clip_fraction | 0.459 | +| clip_range | 0.2 | +| entropy_loss | -0.303 | +| explained_variance | -6.63 | +| learning_rate | 0.0001 | +| loss | -0.0848 | +| n_updates | 105840 | +| policy_gradient_loss | -0.0657 | +| value_loss | 0.000521 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 309 | +| iterations | 4533 | +| time_elapsed | 14977 | +| total_timesteps | 4641792 | +| train/ | | +| approx_kl | 2.2554584 | +| clip_fraction | 0.441 | +| clip_range | 0.2 | +| entropy_loss | -0.314 | +| explained_variance | -0.946 | +| learning_rate | 0.0001 | +| loss | -0.0539 | +| n_updates | 105850 | +| policy_gradient_loss | -0.0512 | +| value_loss | 0.000311 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 309 | +| iterations | 4534 | +| time_elapsed | 14981 | +| total_timesteps | 4642816 | +| train/ | | +| approx_kl | 3.1558628 | +| clip_fraction | 0.423 | +| clip_range | 0.2 | +| entropy_loss | -0.291 | +| explained_variance | -0.169 | +| learning_rate | 0.0001 | +| loss | -0.0862 | +| n_updates | 105860 | +| policy_gradient_loss | -0.0597 | +| value_loss | 0.000492 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 309 | +| iterations | 4535 | +| time_elapsed | 14984 | +| total_timesteps | 4643840 | +| train/ | | +| approx_kl | 1.7417529 | +| clip_fraction | 0.4 | +| clip_range | 0.2 | +| entropy_loss | -0.288 | +| explained_variance | -0.324 | +| learning_rate | 0.0001 | +| loss | -0.079 | +| n_updates | 105870 | +| policy_gradient_loss | -0.0533 | +| value_loss | 0.000683 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 309 | +| iterations | 4536 | +| time_elapsed | 14988 | +| total_timesteps | 4644864 | +| train/ | | +| approx_kl | 1.9478245 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.381 | +| explained_variance | -1.77 | +| learning_rate | 0.0001 | +| loss | -0.0995 | +| n_updates | 105880 | +| policy_gradient_loss | -0.07 | +| value_loss | 0.000414 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 309 | +| iterations | 4537 | +| time_elapsed | 14991 | +| total_timesteps | 4645888 | +| train/ | | +| approx_kl | 2.5995262 | +| clip_fraction | 0.416 | +| clip_range | 0.2 | +| entropy_loss | -0.3 | +| explained_variance | -0.811 | +| learning_rate | 0.0001 | +| loss | -0.0533 | +| n_updates | 105890 | +| policy_gradient_loss | -0.0573 | +| value_loss | 0.000511 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 309 | +| iterations | 4538 | +| time_elapsed | 14994 | +| total_timesteps | 4646912 | +| train/ | | +| approx_kl | 1.4696627 | +| clip_fraction | 0.425 | +| clip_range | 0.2 | +| entropy_loss | -0.319 | +| explained_variance | -0.465 | +| learning_rate | 0.0001 | +| loss | -0.0662 | +| n_updates | 105900 | +| policy_gradient_loss | -0.0607 | +| value_loss | 0.000599 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 309 | +| iterations | 4539 | +| time_elapsed | 14998 | +| total_timesteps | 4647936 | +| train/ | | +| approx_kl | 2.3436856 | +| clip_fraction | 0.409 | +| clip_range | 0.2 | +| entropy_loss | -0.274 | +| explained_variance | -1.33 | +| learning_rate | 0.0001 | +| loss | -0.0863 | +| n_updates | 105910 | +| policy_gradient_loss | -0.0543 | +| value_loss | 0.000474 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 309 | +| iterations | 4540 | +| time_elapsed | 15001 | +| total_timesteps | 4648960 | +| train/ | | +| approx_kl | 2.9132037 | +| clip_fraction | 0.415 | +| clip_range | 0.2 | +| entropy_loss | -0.254 | +| explained_variance | -0.403 | +| learning_rate | 0.0001 | +| loss | -0.0905 | +| n_updates | 105920 | +| policy_gradient_loss | -0.0514 | +| value_loss | 0.000672 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 309 | +| iterations | 4541 | +| time_elapsed | 15005 | +| total_timesteps | 4649984 | +| train/ | | +| approx_kl | 2.6390805 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.332 | +| explained_variance | -0.273 | +| learning_rate | 0.0001 | +| loss | -0.00488 | +| n_updates | 105930 | +| policy_gradient_loss | -0.0458 | +| value_loss | 0.000929 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 309 | +| iterations | 4542 | +| time_elapsed | 15008 | +| total_timesteps | 4651008 | +| train/ | | +| approx_kl | 2.143664 | +| clip_fraction | 0.431 | +| clip_range | 0.2 | +| entropy_loss | -0.305 | +| explained_variance | -1.1 | +| learning_rate | 0.0001 | +| loss | -0.0851 | +| n_updates | 105940 | +| policy_gradient_loss | -0.0598 | +| value_loss | 0.00103 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 309 | +| iterations | 4543 | +| time_elapsed | 15012 | +| total_timesteps | 4652032 | +| train/ | | +| approx_kl | 2.0885763 | +| clip_fraction | 0.405 | +| clip_range | 0.2 | +| entropy_loss | -0.303 | +| explained_variance | -0.588 | +| learning_rate | 0.0001 | +| loss | -0.0707 | +| n_updates | 105950 | +| policy_gradient_loss | -0.06 | +| value_loss | 0.000897 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 309 | +| iterations | 4544 | +| time_elapsed | 15015 | +| total_timesteps | 4653056 | +| train/ | | +| approx_kl | 3.2037735 | +| clip_fraction | 0.472 | +| clip_range | 0.2 | +| entropy_loss | -0.329 | +| explained_variance | -2.35 | +| learning_rate | 0.0001 | +| loss | -0.0932 | +| n_updates | 105960 | +| policy_gradient_loss | -0.0642 | +| value_loss | 0.000501 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 309 | +| iterations | 4545 | +| time_elapsed | 15019 | +| total_timesteps | 4654080 | +| train/ | | +| approx_kl | 2.4095428 | +| clip_fraction | 0.458 | +| clip_range | 0.2 | +| entropy_loss | -0.315 | +| explained_variance | -0.477 | +| learning_rate | 0.0001 | +| loss | -0.069 | +| n_updates | 105970 | +| policy_gradient_loss | -0.0595 | +| value_loss | 0.000474 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 309 | +| iterations | 4546 | +| time_elapsed | 15022 | +| total_timesteps | 4655104 | +| train/ | | +| approx_kl | 2.128002 | +| clip_fraction | 0.461 | +| clip_range | 0.2 | +| entropy_loss | -0.326 | +| explained_variance | -0.416 | +| learning_rate | 0.0001 | +| loss | -0.0877 | +| n_updates | 105980 | +| policy_gradient_loss | -0.0608 | +| value_loss | 0.000548 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 309 | +| iterations | 4547 | +| time_elapsed | 15025 | +| total_timesteps | 4656128 | +| train/ | | +| approx_kl | 2.4312184 | +| clip_fraction | 0.434 | +| clip_range | 0.2 | +| entropy_loss | -0.27 | +| explained_variance | -0.473 | +| learning_rate | 0.0001 | +| loss | -0.0653 | +| n_updates | 105990 | +| policy_gradient_loss | -0.0659 | +| value_loss | 0.000741 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 309 | +| iterations | 4548 | +| time_elapsed | 15028 | +| total_timesteps | 4657152 | +| train/ | | +| approx_kl | 2.8269029 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.323 | +| explained_variance | -0.327 | +| learning_rate | 0.0001 | +| loss | -0.0755 | +| n_updates | 106000 | +| policy_gradient_loss | -0.0683 | +| value_loss | 0.000614 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 309 | +| iterations | 4549 | +| time_elapsed | 15031 | +| total_timesteps | 4658176 | +| train/ | | +| approx_kl | 1.7732737 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.375 | +| explained_variance | -1.68 | +| learning_rate | 0.0001 | +| loss | -0.0799 | +| n_updates | 106010 | +| policy_gradient_loss | -0.0668 | +| value_loss | 0.000546 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 309 | +| iterations | 4550 | +| time_elapsed | 15035 | +| total_timesteps | 4659200 | +| train/ | | +| approx_kl | 2.0290818 | +| clip_fraction | 0.444 | +| clip_range | 0.2 | +| entropy_loss | -0.323 | +| explained_variance | -0.868 | +| learning_rate | 0.0001 | +| loss | -0.0722 | +| n_updates | 106020 | +| policy_gradient_loss | -0.062 | +| value_loss | 0.000587 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 309 | +| iterations | 4551 | +| time_elapsed | 15038 | +| total_timesteps | 4660224 | +| train/ | | +| approx_kl | 2.2549186 | +| clip_fraction | 0.415 | +| clip_range | 0.2 | +| entropy_loss | -0.298 | +| explained_variance | -0.537 | +| learning_rate | 0.0001 | +| loss | -0.0709 | +| n_updates | 106030 | +| policy_gradient_loss | -0.0608 | +| value_loss | 0.000486 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 309 | +| iterations | 4552 | +| time_elapsed | 15041 | +| total_timesteps | 4661248 | +| train/ | | +| approx_kl | 2.370605 | +| clip_fraction | 0.427 | +| clip_range | 0.2 | +| entropy_loss | -0.328 | +| explained_variance | -0.0734 | +| learning_rate | 0.0001 | +| loss | -0.0685 | +| n_updates | 106040 | +| policy_gradient_loss | -0.0542 | +| value_loss | 0.000708 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 309 | +| iterations | 4553 | +| time_elapsed | 15045 | +| total_timesteps | 4662272 | +| train/ | | +| approx_kl | 2.1422482 | +| clip_fraction | 0.441 | +| clip_range | 0.2 | +| entropy_loss | -0.328 | +| explained_variance | -0.491 | +| learning_rate | 0.0001 | +| loss | -0.0786 | +| n_updates | 106050 | +| policy_gradient_loss | -0.0647 | +| value_loss | 0.000624 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 309 | +| iterations | 4554 | +| time_elapsed | 15048 | +| total_timesteps | 4663296 | +| train/ | | +| approx_kl | 2.469061 | +| clip_fraction | 0.424 | +| clip_range | 0.2 | +| entropy_loss | -0.327 | +| explained_variance | -0.372 | +| learning_rate | 0.0001 | +| loss | -0.093 | +| n_updates | 106060 | +| policy_gradient_loss | -0.0689 | +| value_loss | 0.000649 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 309 | +| iterations | 4555 | +| time_elapsed | 15052 | +| total_timesteps | 4664320 | +| train/ | | +| approx_kl | 1.8025271 | +| clip_fraction | 0.444 | +| clip_range | 0.2 | +| entropy_loss | -0.341 | +| explained_variance | 0.0867 | +| learning_rate | 0.0001 | +| loss | -0.0985 | +| n_updates | 106070 | +| policy_gradient_loss | -0.063 | +| value_loss | 0.00089 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 309 | +| iterations | 4556 | +| time_elapsed | 15055 | +| total_timesteps | 4665344 | +| train/ | | +| approx_kl | 1.693866 | +| clip_fraction | 0.388 | +| clip_range | 0.2 | +| entropy_loss | -0.297 | +| explained_variance | -0.768 | +| learning_rate | 0.0001 | +| loss | -0.0829 | +| n_updates | 106080 | +| policy_gradient_loss | -0.0545 | +| value_loss | 0.000571 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 309 | +| iterations | 4557 | +| time_elapsed | 15059 | +| total_timesteps | 4666368 | +| train/ | | +| approx_kl | 1.9051623 | +| clip_fraction | 0.442 | +| clip_range | 0.2 | +| entropy_loss | -0.326 | +| explained_variance | -0.127 | +| learning_rate | 0.0001 | +| loss | -0.0715 | +| n_updates | 106090 | +| policy_gradient_loss | -0.0577 | +| value_loss | 0.000719 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 309 | +| iterations | 4558 | +| time_elapsed | 15062 | +| total_timesteps | 4667392 | +| train/ | | +| approx_kl | 2.527376 | +| clip_fraction | 0.496 | +| clip_range | 0.2 | +| entropy_loss | -0.363 | +| explained_variance | -1.45 | +| learning_rate | 0.0001 | +| loss | -0.0771 | +| n_updates | 106100 | +| policy_gradient_loss | -0.071 | +| value_loss | 0.00067 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 309 | +| iterations | 4559 | +| time_elapsed | 15066 | +| total_timesteps | 4668416 | +| train/ | | +| approx_kl | 2.8891263 | +| clip_fraction | 0.434 | +| clip_range | 0.2 | +| entropy_loss | -0.308 | +| explained_variance | -0.322 | +| learning_rate | 0.0001 | +| loss | -0.0791 | +| n_updates | 106110 | +| policy_gradient_loss | -0.0538 | +| value_loss | 0.000736 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 309 | +| iterations | 4560 | +| time_elapsed | 15070 | +| total_timesteps | 4669440 | +| train/ | | +| approx_kl | 1.8634729 | +| clip_fraction | 0.443 | +| clip_range | 0.2 | +| entropy_loss | -0.342 | +| explained_variance | -0.122 | +| learning_rate | 0.0001 | +| loss | -0.0667 | +| n_updates | 106120 | +| policy_gradient_loss | -0.0655 | +| value_loss | 0.000435 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 309 | +| iterations | 4561 | +| time_elapsed | 15073 | +| total_timesteps | 4670464 | +| train/ | | +| approx_kl | 2.355209 | +| clip_fraction | 0.497 | +| clip_range | 0.2 | +| entropy_loss | -0.387 | +| explained_variance | -1.33 | +| learning_rate | 0.0001 | +| loss | -0.0857 | +| n_updates | 106130 | +| policy_gradient_loss | -0.0677 | +| value_loss | 0.000619 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 309 | +| iterations | 4562 | +| time_elapsed | 15076 | +| total_timesteps | 4671488 | +| train/ | | +| approx_kl | 2.3718019 | +| clip_fraction | 0.452 | +| clip_range | 0.2 | +| entropy_loss | -0.339 | +| explained_variance | -0.471 | +| learning_rate | 0.0001 | +| loss | -0.0908 | +| n_updates | 106140 | +| policy_gradient_loss | -0.0644 | +| value_loss | 0.000596 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 309 | +| iterations | 4563 | +| time_elapsed | 15079 | +| total_timesteps | 4672512 | +| train/ | | +| approx_kl | 2.3883467 | +| clip_fraction | 0.437 | +| clip_range | 0.2 | +| entropy_loss | -0.297 | +| explained_variance | -0.366 | +| learning_rate | 0.0001 | +| loss | -0.0612 | +| n_updates | 106150 | +| policy_gradient_loss | -0.0655 | +| value_loss | 0.000807 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 309 | +| iterations | 4564 | +| time_elapsed | 15082 | +| total_timesteps | 4673536 | +| train/ | | +| approx_kl | 2.5152464 | +| clip_fraction | 0.45 | +| clip_range | 0.2 | +| entropy_loss | -0.331 | +| explained_variance | -0.412 | +| learning_rate | 0.0001 | +| loss | -0.0906 | +| n_updates | 106160 | +| policy_gradient_loss | -0.0646 | +| value_loss | 0.000727 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 309 | +| iterations | 4565 | +| time_elapsed | 15086 | +| total_timesteps | 4674560 | +| train/ | | +| approx_kl | 2.1209736 | +| clip_fraction | 0.474 | +| clip_range | 0.2 | +| entropy_loss | -0.359 | +| explained_variance | -5.47 | +| learning_rate | 0.0001 | +| loss | -0.0986 | +| n_updates | 106170 | +| policy_gradient_loss | -0.0685 | +| value_loss | 0.000614 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 309 | +| iterations | 4566 | +| time_elapsed | 15089 | +| total_timesteps | 4675584 | +| train/ | | +| approx_kl | 2.5447683 | +| clip_fraction | 0.47 | +| clip_range | 0.2 | +| entropy_loss | -0.363 | +| explained_variance | -0.0401 | +| learning_rate | 0.0001 | +| loss | -0.0596 | +| n_updates | 106180 | +| policy_gradient_loss | -0.0579 | +| value_loss | 0.000334 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 309 | +| iterations | 4567 | +| time_elapsed | 15092 | +| total_timesteps | 4676608 | +| train/ | | +| approx_kl | 2.0131586 | +| clip_fraction | 0.442 | +| clip_range | 0.2 | +| entropy_loss | -0.358 | +| explained_variance | -0.182 | +| learning_rate | 0.0001 | +| loss | -0.0934 | +| n_updates | 106190 | +| policy_gradient_loss | -0.058 | +| value_loss | 0.000519 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 309 | +| iterations | 4568 | +| time_elapsed | 15095 | +| total_timesteps | 4677632 | +| train/ | | +| approx_kl | 2.0411408 | +| clip_fraction | 0.461 | +| clip_range | 0.2 | +| entropy_loss | -0.329 | +| explained_variance | -0.432 | +| learning_rate | 0.0001 | +| loss | -0.0964 | +| n_updates | 106200 | +| policy_gradient_loss | -0.0693 | +| value_loss | 0.000789 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 309 | +| iterations | 4569 | +| time_elapsed | 15098 | +| total_timesteps | 4678656 | +| train/ | | +| approx_kl | 3.0201626 | +| clip_fraction | 0.448 | +| clip_range | 0.2 | +| entropy_loss | -0.322 | +| explained_variance | -0.133 | +| learning_rate | 0.0001 | +| loss | -0.0703 | +| n_updates | 106210 | +| policy_gradient_loss | -0.0585 | +| value_loss | 0.000788 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 309 | +| iterations | 4570 | +| time_elapsed | 15102 | +| total_timesteps | 4679680 | +| train/ | | +| approx_kl | 2.0978868 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.358 | +| explained_variance | -1.97 | +| learning_rate | 0.0001 | +| loss | -0.0766 | +| n_updates | 106220 | +| policy_gradient_loss | -0.06 | +| value_loss | 0.000523 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 309 | +| iterations | 4571 | +| time_elapsed | 15105 | +| total_timesteps | 4680704 | +| train/ | | +| approx_kl | 2.758089 | +| clip_fraction | 0.493 | +| clip_range | 0.2 | +| entropy_loss | -0.353 | +| explained_variance | -0.504 | +| learning_rate | 0.0001 | +| loss | -0.111 | +| n_updates | 106230 | +| policy_gradient_loss | -0.0636 | +| value_loss | 0.00059 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 309 | +| iterations | 4572 | +| time_elapsed | 15109 | +| total_timesteps | 4681728 | +| train/ | | +| approx_kl | 2.5283961 | +| clip_fraction | 0.447 | +| clip_range | 0.2 | +| entropy_loss | -0.33 | +| explained_variance | -0.697 | +| learning_rate | 0.0001 | +| loss | -0.0787 | +| n_updates | 106240 | +| policy_gradient_loss | -0.0592 | +| value_loss | 0.000757 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 309 | +| iterations | 4573 | +| time_elapsed | 15112 | +| total_timesteps | 4682752 | +| train/ | | +| approx_kl | 2.3901281 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.363 | +| explained_variance | -0.293 | +| learning_rate | 0.0001 | +| loss | -0.0749 | +| n_updates | 106250 | +| policy_gradient_loss | -0.0645 | +| value_loss | 0.000661 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 309 | +| iterations | 4574 | +| time_elapsed | 15115 | +| total_timesteps | 4683776 | +| train/ | | +| approx_kl | 2.6321511 | +| clip_fraction | 0.438 | +| clip_range | 0.2 | +| entropy_loss | -0.308 | +| explained_variance | -0.9 | +| learning_rate | 0.0001 | +| loss | -0.0772 | +| n_updates | 106260 | +| policy_gradient_loss | -0.0666 | +| value_loss | 0.000662 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 309 | +| iterations | 4575 | +| time_elapsed | 15119 | +| total_timesteps | 4684800 | +| train/ | | +| approx_kl | 2.4702106 | +| clip_fraction | 0.526 | +| clip_range | 0.2 | +| entropy_loss | -0.428 | +| explained_variance | -1.75 | +| learning_rate | 0.0001 | +| loss | -0.0838 | +| n_updates | 106270 | +| policy_gradient_loss | -0.0604 | +| value_loss | 0.000599 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 309 | +| iterations | 4576 | +| time_elapsed | 15122 | +| total_timesteps | 4685824 | +| train/ | | +| approx_kl | 1.7589114 | +| clip_fraction | 0.418 | +| clip_range | 0.2 | +| entropy_loss | -0.298 | +| explained_variance | -0.71 | +| learning_rate | 0.0001 | +| loss | -0.0627 | +| n_updates | 106280 | +| policy_gradient_loss | -0.0602 | +| value_loss | 0.000596 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 309 | +| iterations | 4577 | +| time_elapsed | 15126 | +| total_timesteps | 4686848 | +| train/ | | +| approx_kl | 1.9006364 | +| clip_fraction | 0.465 | +| clip_range | 0.2 | +| entropy_loss | -0.335 | +| explained_variance | -0.323 | +| learning_rate | 0.0001 | +| loss | -0.0712 | +| n_updates | 106290 | +| policy_gradient_loss | -0.0656 | +| value_loss | 0.000836 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 309 | +| iterations | 4578 | +| time_elapsed | 15129 | +| total_timesteps | 4687872 | +| train/ | | +| approx_kl | 1.62948 | +| clip_fraction | 0.366 | +| clip_range | 0.2 | +| entropy_loss | -0.257 | +| explained_variance | -0.211 | +| learning_rate | 0.0001 | +| loss | -0.0215 | +| n_updates | 106300 | +| policy_gradient_loss | -0.043 | +| value_loss | 0.000572 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 309 | +| iterations | 4579 | +| time_elapsed | 15132 | +| total_timesteps | 4688896 | +| train/ | | +| approx_kl | 1.8789101 | +| clip_fraction | 0.404 | +| clip_range | 0.2 | +| entropy_loss | -0.296 | +| explained_variance | -0.986 | +| learning_rate | 0.0001 | +| loss | -0.0767 | +| n_updates | 106310 | +| policy_gradient_loss | -0.0543 | +| value_loss | 0.000701 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 309 | +| iterations | 4580 | +| time_elapsed | 15136 | +| total_timesteps | 4689920 | +| train/ | | +| approx_kl | 2.805615 | +| clip_fraction | 0.458 | +| clip_range | 0.2 | +| entropy_loss | -0.345 | +| explained_variance | -0.216 | +| learning_rate | 0.0001 | +| loss | -0.088 | +| n_updates | 106320 | +| policy_gradient_loss | -0.0579 | +| value_loss | 0.000887 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 309 | +| iterations | 4581 | +| time_elapsed | 15139 | +| total_timesteps | 4690944 | +| train/ | | +| approx_kl | 2.2226865 | +| clip_fraction | 0.477 | +| clip_range | 0.2 | +| entropy_loss | -0.368 | +| explained_variance | -2.17 | +| learning_rate | 0.0001 | +| loss | -0.0873 | +| n_updates | 106330 | +| policy_gradient_loss | -0.0711 | +| value_loss | 0.000608 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 309 | +| iterations | 4582 | +| time_elapsed | 15142 | +| total_timesteps | 4691968 | +| train/ | | +| approx_kl | 1.900136 | +| clip_fraction | 0.451 | +| clip_range | 0.2 | +| entropy_loss | -0.36 | +| explained_variance | -0.378 | +| learning_rate | 0.0001 | +| loss | -0.0713 | +| n_updates | 106340 | +| policy_gradient_loss | -0.0593 | +| value_loss | 0.000465 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 309 | +| iterations | 4583 | +| time_elapsed | 15145 | +| total_timesteps | 4692992 | +| train/ | | +| approx_kl | 2.0497649 | +| clip_fraction | 0.466 | +| clip_range | 0.2 | +| entropy_loss | -0.338 | +| explained_variance | -0.593 | +| learning_rate | 0.0001 | +| loss | -0.082 | +| n_updates | 106350 | +| policy_gradient_loss | -0.0664 | +| value_loss | 0.000673 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 309 | +| iterations | 4584 | +| time_elapsed | 15149 | +| total_timesteps | 4694016 | +| train/ | | +| approx_kl | 2.3119907 | +| clip_fraction | 0.465 | +| clip_range | 0.2 | +| entropy_loss | -0.333 | +| explained_variance | -0.314 | +| learning_rate | 0.0001 | +| loss | -0.0634 | +| n_updates | 106360 | +| policy_gradient_loss | -0.0681 | +| value_loss | 0.000659 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 309 | +| iterations | 4585 | +| time_elapsed | 15152 | +| total_timesteps | 4695040 | +| train/ | | +| approx_kl | 2.0766048 | +| clip_fraction | 0.473 | +| clip_range | 0.2 | +| entropy_loss | -0.381 | +| explained_variance | -2.01 | +| learning_rate | 0.0001 | +| loss | -0.0779 | +| n_updates | 106370 | +| policy_gradient_loss | -0.0652 | +| value_loss | 0.000705 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 309 | +| iterations | 4586 | +| time_elapsed | 15155 | +| total_timesteps | 4696064 | +| train/ | | +| approx_kl | 1.9680157 | +| clip_fraction | 0.453 | +| clip_range | 0.2 | +| entropy_loss | -0.347 | +| explained_variance | -0.362 | +| learning_rate | 0.0001 | +| loss | -0.0863 | +| n_updates | 106380 | +| policy_gradient_loss | -0.057 | +| value_loss | 0.000628 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 309 | +| iterations | 4587 | +| time_elapsed | 15158 | +| total_timesteps | 4697088 | +| train/ | | +| approx_kl | 1.9110562 | +| clip_fraction | 0.459 | +| clip_range | 0.2 | +| entropy_loss | -0.325 | +| explained_variance | -0.285 | +| learning_rate | 0.0001 | +| loss | -0.0923 | +| n_updates | 106390 | +| policy_gradient_loss | -0.0575 | +| value_loss | 0.000478 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 309 | +| iterations | 4588 | +| time_elapsed | 15162 | +| total_timesteps | 4698112 | +| train/ | | +| approx_kl | 1.9575813 | +| clip_fraction | 0.467 | +| clip_range | 0.2 | +| entropy_loss | -0.366 | +| explained_variance | -2.45 | +| learning_rate | 0.0001 | +| loss | -0.106 | +| n_updates | 106400 | +| policy_gradient_loss | -0.0726 | +| value_loss | 0.000498 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 309 | +| iterations | 4589 | +| time_elapsed | 15165 | +| total_timesteps | 4699136 | +| train/ | | +| approx_kl | 2.3811698 | +| clip_fraction | 0.474 | +| clip_range | 0.2 | +| entropy_loss | -0.35 | +| explained_variance | -0.528 | +| learning_rate | 0.0001 | +| loss | -0.0962 | +| n_updates | 106410 | +| policy_gradient_loss | -0.0653 | +| value_loss | 0.000523 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 309 | +| iterations | 4590 | +| time_elapsed | 15168 | +| total_timesteps | 4700160 | +| train/ | | +| approx_kl | 2.2219992 | +| clip_fraction | 0.435 | +| clip_range | 0.2 | +| entropy_loss | -0.333 | +| explained_variance | -1.09 | +| learning_rate | 0.0001 | +| loss | -0.078 | +| n_updates | 106420 | +| policy_gradient_loss | -0.0604 | +| value_loss | 0.000676 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 309 | +| iterations | 4591 | +| time_elapsed | 15172 | +| total_timesteps | 4701184 | +| train/ | | +| approx_kl | 2.12387 | +| clip_fraction | 0.463 | +| clip_range | 0.2 | +| entropy_loss | -0.349 | +| explained_variance | -0.519 | +| learning_rate | 0.0001 | +| loss | -0.0989 | +| n_updates | 106430 | +| policy_gradient_loss | -0.0705 | +| value_loss | 0.000431 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 309 | +| iterations | 4592 | +| time_elapsed | 15175 | +| total_timesteps | 4702208 | +| train/ | | +| approx_kl | 2.1952589 | +| clip_fraction | 0.5 | +| clip_range | 0.2 | +| entropy_loss | -0.415 | +| explained_variance | -1.16 | +| learning_rate | 0.0001 | +| loss | -0.095 | +| n_updates | 106440 | +| policy_gradient_loss | -0.0713 | +| value_loss | 0.000415 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 309 | +| iterations | 4593 | +| time_elapsed | 15179 | +| total_timesteps | 4703232 | +| train/ | | +| approx_kl | 2.0501313 | +| clip_fraction | 0.477 | +| clip_range | 0.2 | +| entropy_loss | -0.36 | +| explained_variance | -0.974 | +| learning_rate | 0.0001 | +| loss | -0.0686 | +| n_updates | 106450 | +| policy_gradient_loss | -0.0514 | +| value_loss | 0.000575 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 309 | +| iterations | 4594 | +| time_elapsed | 15182 | +| total_timesteps | 4704256 | +| train/ | | +| approx_kl | 1.9931958 | +| clip_fraction | 0.429 | +| clip_range | 0.2 | +| entropy_loss | -0.349 | +| explained_variance | -0.518 | +| learning_rate | 0.0001 | +| loss | -0.0735 | +| n_updates | 106460 | +| policy_gradient_loss | -0.0601 | +| value_loss | 0.000459 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 309 | +| iterations | 4595 | +| time_elapsed | 15186 | +| total_timesteps | 4705280 | +| train/ | | +| approx_kl | 3.2598321 | +| clip_fraction | 0.478 | +| clip_range | 0.2 | +| entropy_loss | -0.337 | +| explained_variance | -0.843 | +| learning_rate | 0.0001 | +| loss | -0.0822 | +| n_updates | 106470 | +| policy_gradient_loss | -0.0716 | +| value_loss | 0.000445 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 309 | +| iterations | 4596 | +| time_elapsed | 15189 | +| total_timesteps | 4706304 | +| train/ | | +| approx_kl | 3.4179878 | +| clip_fraction | 0.484 | +| clip_range | 0.2 | +| entropy_loss | -0.372 | +| explained_variance | -1.25 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 106480 | +| policy_gradient_loss | -0.0658 | +| value_loss | 0.000398 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 309 | +| iterations | 4597 | +| time_elapsed | 15192 | +| total_timesteps | 4707328 | +| train/ | | +| approx_kl | 1.6580389 | +| clip_fraction | 0.457 | +| clip_range | 0.2 | +| entropy_loss | -0.38 | +| explained_variance | -0.315 | +| learning_rate | 0.0001 | +| loss | -0.0852 | +| n_updates | 106490 | +| policy_gradient_loss | -0.0508 | +| value_loss | 0.000426 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 309 | +| iterations | 4598 | +| time_elapsed | 15196 | +| total_timesteps | 4708352 | +| train/ | | +| approx_kl | 1.8382652 | +| clip_fraction | 0.465 | +| clip_range | 0.2 | +| entropy_loss | -0.369 | +| explained_variance | -0.275 | +| learning_rate | 0.0001 | +| loss | -0.0672 | +| n_updates | 106500 | +| policy_gradient_loss | -0.0672 | +| value_loss | 0.000551 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 309 | +| iterations | 4599 | +| time_elapsed | 15199 | +| total_timesteps | 4709376 | +| train/ | | +| approx_kl | 2.5790439 | +| clip_fraction | 0.478 | +| clip_range | 0.2 | +| entropy_loss | -0.36 | +| explained_variance | -2.74 | +| learning_rate | 0.0001 | +| loss | -0.0733 | +| n_updates | 106510 | +| policy_gradient_loss | -0.0732 | +| value_loss | 0.000578 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 309 | +| iterations | 4600 | +| time_elapsed | 15202 | +| total_timesteps | 4710400 | +| train/ | | +| approx_kl | 1.8144796 | +| clip_fraction | 0.438 | +| clip_range | 0.2 | +| entropy_loss | -0.346 | +| explained_variance | -0.925 | +| learning_rate | 0.0001 | +| loss | -0.0718 | +| n_updates | 106520 | +| policy_gradient_loss | -0.0564 | +| value_loss | 0.000488 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 309 | +| iterations | 4601 | +| time_elapsed | 15205 | +| total_timesteps | 4711424 | +| train/ | | +| approx_kl | 2.422504 | +| clip_fraction | 0.437 | +| clip_range | 0.2 | +| entropy_loss | -0.351 | +| explained_variance | -0.824 | +| learning_rate | 0.0001 | +| loss | -0.043 | +| n_updates | 106530 | +| policy_gradient_loss | -0.0643 | +| value_loss | 0.000397 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 309 | +| iterations | 4602 | +| time_elapsed | 15208 | +| total_timesteps | 4712448 | +| train/ | | +| approx_kl | 2.2430906 | +| clip_fraction | 0.533 | +| clip_range | 0.2 | +| entropy_loss | -0.415 | +| explained_variance | -2.34 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 106540 | +| policy_gradient_loss | -0.0737 | +| value_loss | 0.000442 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 309 | +| iterations | 4603 | +| time_elapsed | 15211 | +| total_timesteps | 4713472 | +| train/ | | +| approx_kl | 1.9731978 | +| clip_fraction | 0.45 | +| clip_range | 0.2 | +| entropy_loss | -0.382 | +| explained_variance | -0.292 | +| learning_rate | 0.0001 | +| loss | -0.0434 | +| n_updates | 106550 | +| policy_gradient_loss | -0.051 | +| value_loss | 0.000903 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 309 | +| iterations | 4604 | +| time_elapsed | 15215 | +| total_timesteps | 4714496 | +| train/ | | +| approx_kl | 1.9499693 | +| clip_fraction | 0.444 | +| clip_range | 0.2 | +| entropy_loss | -0.327 | +| explained_variance | -1.6 | +| learning_rate | 0.0001 | +| loss | -0.083 | +| n_updates | 106560 | +| policy_gradient_loss | -0.0655 | +| value_loss | 0.00076 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 309 | +| iterations | 4605 | +| time_elapsed | 15218 | +| total_timesteps | 4715520 | +| train/ | | +| approx_kl | 2.482099 | +| clip_fraction | 0.425 | +| clip_range | 0.2 | +| entropy_loss | -0.324 | +| explained_variance | -0.828 | +| learning_rate | 0.0001 | +| loss | -0.118 | +| n_updates | 106570 | +| policy_gradient_loss | -0.0606 | +| value_loss | 0.000662 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 309 | +| iterations | 4606 | +| time_elapsed | 15221 | +| total_timesteps | 4716544 | +| train/ | | +| approx_kl | 1.9160678 | +| clip_fraction | 0.418 | +| clip_range | 0.2 | +| entropy_loss | -0.316 | +| explained_variance | -0.604 | +| learning_rate | 0.0001 | +| loss | -0.0487 | +| n_updates | 106580 | +| policy_gradient_loss | -0.0576 | +| value_loss | 0.000461 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 309 | +| iterations | 4607 | +| time_elapsed | 15225 | +| total_timesteps | 4717568 | +| train/ | | +| approx_kl | 1.877486 | +| clip_fraction | 0.438 | +| clip_range | 0.2 | +| entropy_loss | -0.339 | +| explained_variance | -0.868 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 106590 | +| policy_gradient_loss | -0.0596 | +| value_loss | 0.000376 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 309 | +| iterations | 4608 | +| time_elapsed | 15228 | +| total_timesteps | 4718592 | +| train/ | | +| approx_kl | 1.9686191 | +| clip_fraction | 0.462 | +| clip_range | 0.2 | +| entropy_loss | -0.347 | +| explained_variance | -0.267 | +| learning_rate | 0.0001 | +| loss | -0.09 | +| n_updates | 106600 | +| policy_gradient_loss | -0.0648 | +| value_loss | 0.000627 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 309 | +| iterations | 4609 | +| time_elapsed | 15232 | +| total_timesteps | 4719616 | +| train/ | | +| approx_kl | 2.089189 | +| clip_fraction | 0.493 | +| clip_range | 0.2 | +| entropy_loss | -0.418 | +| explained_variance | -1.34 | +| learning_rate | 0.0001 | +| loss | -0.116 | +| n_updates | 106610 | +| policy_gradient_loss | -0.0756 | +| value_loss | 0.000627 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 309 | +| iterations | 4610 | +| time_elapsed | 15235 | +| total_timesteps | 4720640 | +| train/ | | +| approx_kl | 1.7341925 | +| clip_fraction | 0.453 | +| clip_range | 0.2 | +| entropy_loss | -0.37 | +| explained_variance | -0.196 | +| learning_rate | 0.0001 | +| loss | -0.0703 | +| n_updates | 106620 | +| policy_gradient_loss | -0.0573 | +| value_loss | 0.00064 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 309 | +| iterations | 4611 | +| time_elapsed | 15239 | +| total_timesteps | 4721664 | +| train/ | | +| approx_kl | 1.8411505 | +| clip_fraction | 0.412 | +| clip_range | 0.2 | +| entropy_loss | -0.33 | +| explained_variance | 0.26 | +| learning_rate | 0.0001 | +| loss | -0.0917 | +| n_updates | 106630 | +| policy_gradient_loss | -0.0573 | +| value_loss | 0.00039 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 309 | +| iterations | 4612 | +| time_elapsed | 15242 | +| total_timesteps | 4722688 | +| train/ | | +| approx_kl | 5.719039 | +| clip_fraction | 0.465 | +| clip_range | 0.2 | +| entropy_loss | -0.382 | +| explained_variance | -1.13 | +| learning_rate | 0.0001 | +| loss | -0.0932 | +| n_updates | 106640 | +| policy_gradient_loss | -0.0653 | +| value_loss | 0.0004 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 309 | +| iterations | 4613 | +| time_elapsed | 15246 | +| total_timesteps | 4723712 | +| train/ | | +| approx_kl | 2.0004528 | +| clip_fraction | 0.465 | +| clip_range | 0.2 | +| entropy_loss | -0.393 | +| explained_variance | -0.419 | +| learning_rate | 0.0001 | +| loss | -0.107 | +| n_updates | 106650 | +| policy_gradient_loss | -0.0636 | +| value_loss | 0.000618 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 309 | +| iterations | 4614 | +| time_elapsed | 15249 | +| total_timesteps | 4724736 | +| train/ | | +| approx_kl | 1.9442546 | +| clip_fraction | 0.499 | +| clip_range | 0.2 | +| entropy_loss | -0.397 | +| explained_variance | -4.77 | +| learning_rate | 0.0001 | +| loss | -0.115 | +| n_updates | 106660 | +| policy_gradient_loss | -0.0772 | +| value_loss | 0.000632 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 309 | +| iterations | 4615 | +| time_elapsed | 15252 | +| total_timesteps | 4725760 | +| train/ | | +| approx_kl | 1.5539691 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.399 | +| explained_variance | -1.17 | +| learning_rate | 0.0001 | +| loss | -0.0861 | +| n_updates | 106670 | +| policy_gradient_loss | -0.0541 | +| value_loss | 0.00053 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 309 | +| iterations | 4616 | +| time_elapsed | 15256 | +| total_timesteps | 4726784 | +| train/ | | +| approx_kl | 2.016509 | +| clip_fraction | 0.496 | +| clip_range | 0.2 | +| entropy_loss | -0.412 | +| explained_variance | -0.481 | +| learning_rate | 0.0001 | +| loss | -0.0702 | +| n_updates | 106680 | +| policy_gradient_loss | -0.0664 | +| value_loss | 0.000542 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 309 | +| iterations | 4617 | +| time_elapsed | 15259 | +| total_timesteps | 4727808 | +| train/ | | +| approx_kl | 2.1588607 | +| clip_fraction | 0.472 | +| clip_range | 0.2 | +| entropy_loss | -0.391 | +| explained_variance | -4.88 | +| learning_rate | 0.0001 | +| loss | -0.0958 | +| n_updates | 106690 | +| policy_gradient_loss | -0.0707 | +| value_loss | 0.000278 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 309 | +| iterations | 4618 | +| time_elapsed | 15262 | +| total_timesteps | 4728832 | +| train/ | | +| approx_kl | 2.0046902 | +| clip_fraction | 0.492 | +| clip_range | 0.2 | +| entropy_loss | -0.406 | +| explained_variance | -0.756 | +| learning_rate | 0.0001 | +| loss | -0.0885 | +| n_updates | 106700 | +| policy_gradient_loss | -0.0586 | +| value_loss | 0.000329 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 309 | +| iterations | 4619 | +| time_elapsed | 15265 | +| total_timesteps | 4729856 | +| train/ | | +| approx_kl | 1.5652297 | +| clip_fraction | 0.502 | +| clip_range | 0.2 | +| entropy_loss | -0.421 | +| explained_variance | -1.8 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 106710 | +| policy_gradient_loss | -0.069 | +| value_loss | 0.000439 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 309 | +| iterations | 4620 | +| time_elapsed | 15268 | +| total_timesteps | 4730880 | +| train/ | | +| approx_kl | 1.577896 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.428 | +| explained_variance | -0.495 | +| learning_rate | 0.0001 | +| loss | -0.0811 | +| n_updates | 106720 | +| policy_gradient_loss | -0.0644 | +| value_loss | 0.000481 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 309 | +| iterations | 4621 | +| time_elapsed | 15272 | +| total_timesteps | 4731904 | +| train/ | | +| approx_kl | 4.5791125 | +| clip_fraction | 0.5 | +| clip_range | 0.2 | +| entropy_loss | -0.416 | +| explained_variance | -0.467 | +| learning_rate | 0.0001 | +| loss | -0.084 | +| n_updates | 106730 | +| policy_gradient_loss | -0.0695 | +| value_loss | 0.000501 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 309 | +| iterations | 4622 | +| time_elapsed | 15275 | +| total_timesteps | 4732928 | +| train/ | | +| approx_kl | 1.9035543 | +| clip_fraction | 0.468 | +| clip_range | 0.2 | +| entropy_loss | -0.358 | +| explained_variance | -0.517 | +| learning_rate | 0.0001 | +| loss | -0.111 | +| n_updates | 106740 | +| policy_gradient_loss | -0.072 | +| value_loss | 0.000598 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 309 | +| iterations | 4623 | +| time_elapsed | 15278 | +| total_timesteps | 4733952 | +| train/ | | +| approx_kl | 2.1941557 | +| clip_fraction | 0.53 | +| clip_range | 0.2 | +| entropy_loss | -0.435 | +| explained_variance | -0.65 | +| learning_rate | 0.0001 | +| loss | -0.0761 | +| n_updates | 106750 | +| policy_gradient_loss | -0.0674 | +| value_loss | 0.000595 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 309 | +| iterations | 4624 | +| time_elapsed | 15281 | +| total_timesteps | 4734976 | +| train/ | | +| approx_kl | 2.1481106 | +| clip_fraction | 0.491 | +| clip_range | 0.2 | +| entropy_loss | -0.428 | +| explained_variance | -1.58 | +| learning_rate | 0.0001 | +| loss | -0.0939 | +| n_updates | 106760 | +| policy_gradient_loss | -0.0699 | +| value_loss | 0.000526 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 309 | +| iterations | 4625 | +| time_elapsed | 15285 | +| total_timesteps | 4736000 | +| train/ | | +| approx_kl | 1.8264928 | +| clip_fraction | 0.445 | +| clip_range | 0.2 | +| entropy_loss | -0.357 | +| explained_variance | -0.566 | +| learning_rate | 0.0001 | +| loss | -0.084 | +| n_updates | 106770 | +| policy_gradient_loss | -0.0592 | +| value_loss | 0.000813 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 309 | +| iterations | 4626 | +| time_elapsed | 15288 | +| total_timesteps | 4737024 | +| train/ | | +| approx_kl | 2.6215725 | +| clip_fraction | 0.474 | +| clip_range | 0.2 | +| entropy_loss | -0.36 | +| explained_variance | -0.47 | +| learning_rate | 0.0001 | +| loss | -0.0734 | +| n_updates | 106780 | +| policy_gradient_loss | -0.0555 | +| value_loss | 0.000934 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 309 | +| iterations | 4627 | +| time_elapsed | 15292 | +| total_timesteps | 4738048 | +| train/ | | +| approx_kl | 2.1386726 | +| clip_fraction | 0.469 | +| clip_range | 0.2 | +| entropy_loss | -0.383 | +| explained_variance | -0.498 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 106790 | +| policy_gradient_loss | -0.0671 | +| value_loss | 0.000509 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 309 | +| iterations | 4628 | +| time_elapsed | 15295 | +| total_timesteps | 4739072 | +| train/ | | +| approx_kl | 1.6204016 | +| clip_fraction | 0.434 | +| clip_range | 0.2 | +| entropy_loss | -0.348 | +| explained_variance | -0.741 | +| learning_rate | 0.0001 | +| loss | -0.0937 | +| n_updates | 106800 | +| policy_gradient_loss | -0.0674 | +| value_loss | 0.000453 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 309 | +| iterations | 4629 | +| time_elapsed | 15298 | +| total_timesteps | 4740096 | +| train/ | | +| approx_kl | 1.5526571 | +| clip_fraction | 0.456 | +| clip_range | 0.2 | +| entropy_loss | -0.399 | +| explained_variance | -0.953 | +| learning_rate | 0.0001 | +| loss | -0.0818 | +| n_updates | 106810 | +| policy_gradient_loss | -0.0587 | +| value_loss | 0.000276 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 309 | +| iterations | 4630 | +| time_elapsed | 15302 | +| total_timesteps | 4741120 | +| train/ | | +| approx_kl | 4.539941 | +| clip_fraction | 0.513 | +| clip_range | 0.2 | +| entropy_loss | -0.437 | +| explained_variance | -0.533 | +| learning_rate | 0.0001 | +| loss | -0.0967 | +| n_updates | 106820 | +| policy_gradient_loss | -0.0668 | +| value_loss | 0.000488 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 309 | +| iterations | 4631 | +| time_elapsed | 15305 | +| total_timesteps | 4742144 | +| train/ | | +| approx_kl | 1.9536389 | +| clip_fraction | 0.465 | +| clip_range | 0.2 | +| entropy_loss | -0.371 | +| explained_variance | -1.1 | +| learning_rate | 0.0001 | +| loss | -0.0972 | +| n_updates | 106830 | +| policy_gradient_loss | -0.0683 | +| value_loss | 0.000476 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 309 | +| iterations | 4632 | +| time_elapsed | 15309 | +| total_timesteps | 4743168 | +| train/ | | +| approx_kl | 2.1000233 | +| clip_fraction | 0.46 | +| clip_range | 0.2 | +| entropy_loss | -0.383 | +| explained_variance | -0.636 | +| learning_rate | 0.0001 | +| loss | -0.105 | +| n_updates | 106840 | +| policy_gradient_loss | -0.0735 | +| value_loss | 0.000361 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 309 | +| iterations | 4633 | +| time_elapsed | 15312 | +| total_timesteps | 4744192 | +| train/ | | +| approx_kl | 6.618824 | +| clip_fraction | 0.512 | +| clip_range | 0.2 | +| entropy_loss | -0.412 | +| explained_variance | -0.556 | +| learning_rate | 0.0001 | +| loss | -0.108 | +| n_updates | 106850 | +| policy_gradient_loss | -0.0712 | +| value_loss | 0.000423 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 309 | +| iterations | 4634 | +| time_elapsed | 15315 | +| total_timesteps | 4745216 | +| train/ | | +| approx_kl | 1.7886877 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.409 | +| explained_variance | -1.33 | +| learning_rate | 0.0001 | +| loss | -0.0728 | +| n_updates | 106860 | +| policy_gradient_loss | -0.0596 | +| value_loss | 0.000456 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 309 | +| iterations | 4635 | +| time_elapsed | 15318 | +| total_timesteps | 4746240 | +| train/ | | +| approx_kl | 1.7798862 | +| clip_fraction | 0.449 | +| clip_range | 0.2 | +| entropy_loss | -0.362 | +| explained_variance | -0.537 | +| learning_rate | 0.0001 | +| loss | -0.0824 | +| n_updates | 106870 | +| policy_gradient_loss | -0.0641 | +| value_loss | 0.000669 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 309 | +| iterations | 4636 | +| time_elapsed | 15321 | +| total_timesteps | 4747264 | +| train/ | | +| approx_kl | 1.9510772 | +| clip_fraction | 0.449 | +| clip_range | 0.2 | +| entropy_loss | -0.397 | +| explained_variance | -1.65 | +| learning_rate | 0.0001 | +| loss | -0.058 | +| n_updates | 106880 | +| policy_gradient_loss | -0.0656 | +| value_loss | 0.000547 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 309 | +| iterations | 4637 | +| time_elapsed | 15325 | +| total_timesteps | 4748288 | +| train/ | | +| approx_kl | 1.3911841 | +| clip_fraction | 0.474 | +| clip_range | 0.2 | +| entropy_loss | -0.408 | +| explained_variance | -1.58 | +| learning_rate | 0.0001 | +| loss | -0.0813 | +| n_updates | 106890 | +| policy_gradient_loss | -0.0695 | +| value_loss | 0.000456 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 309 | +| iterations | 4638 | +| time_elapsed | 15328 | +| total_timesteps | 4749312 | +| train/ | | +| approx_kl | 2.0661085 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.436 | +| explained_variance | -0.673 | +| learning_rate | 0.0001 | +| loss | -0.091 | +| n_updates | 106900 | +| policy_gradient_loss | -0.0686 | +| value_loss | 0.000505 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 309 | +| iterations | 4639 | +| time_elapsed | 15331 | +| total_timesteps | 4750336 | +| train/ | | +| approx_kl | 2.0985682 | +| clip_fraction | 0.507 | +| clip_range | 0.2 | +| entropy_loss | -0.466 | +| explained_variance | -2.25 | +| learning_rate | 0.0001 | +| loss | -0.0945 | +| n_updates | 106910 | +| policy_gradient_loss | -0.0756 | +| value_loss | 0.000345 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 309 | +| iterations | 4640 | +| time_elapsed | 15334 | +| total_timesteps | 4751360 | +| train/ | | +| approx_kl | 2.2958875 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.393 | +| explained_variance | -0.174 | +| learning_rate | 0.0001 | +| loss | -0.0849 | +| n_updates | 106920 | +| policy_gradient_loss | -0.0651 | +| value_loss | 0.000455 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 309 | +| iterations | 4641 | +| time_elapsed | 15337 | +| total_timesteps | 4752384 | +| train/ | | +| approx_kl | 3.9254851 | +| clip_fraction | 0.508 | +| clip_range | 0.2 | +| entropy_loss | -0.425 | +| explained_variance | -0.752 | +| learning_rate | 0.0001 | +| loss | -0.076 | +| n_updates | 106930 | +| policy_gradient_loss | -0.0623 | +| value_loss | 0.000586 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 309 | +| iterations | 4642 | +| time_elapsed | 15341 | +| total_timesteps | 4753408 | +| train/ | | +| approx_kl | 1.7358129 | +| clip_fraction | 0.453 | +| clip_range | 0.2 | +| entropy_loss | -0.402 | +| explained_variance | -0.858 | +| learning_rate | 0.0001 | +| loss | -0.0789 | +| n_updates | 106940 | +| policy_gradient_loss | -0.0613 | +| value_loss | 0.000865 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 309 | +| iterations | 4643 | +| time_elapsed | 15344 | +| total_timesteps | 4754432 | +| train/ | | +| approx_kl | 1.8461299 | +| clip_fraction | 0.491 | +| clip_range | 0.2 | +| entropy_loss | -0.419 | +| explained_variance | -0.962 | +| learning_rate | 0.0001 | +| loss | -0.0908 | +| n_updates | 106950 | +| policy_gradient_loss | -0.0699 | +| value_loss | 0.000799 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 309 | +| iterations | 4644 | +| time_elapsed | 15348 | +| total_timesteps | 4755456 | +| train/ | | +| approx_kl | 3.0773585 | +| clip_fraction | 0.473 | +| clip_range | 0.2 | +| entropy_loss | -0.4 | +| explained_variance | -1.56 | +| learning_rate | 0.0001 | +| loss | -0.0923 | +| n_updates | 106960 | +| policy_gradient_loss | -0.0655 | +| value_loss | 0.000723 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 309 | +| iterations | 4645 | +| time_elapsed | 15351 | +| total_timesteps | 4756480 | +| train/ | | +| approx_kl | 2.1146207 | +| clip_fraction | 0.496 | +| clip_range | 0.2 | +| entropy_loss | -0.442 | +| explained_variance | -2.22 | +| learning_rate | 0.0001 | +| loss | -0.0916 | +| n_updates | 106970 | +| policy_gradient_loss | -0.0696 | +| value_loss | 0.000442 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 309 | +| iterations | 4646 | +| time_elapsed | 15354 | +| total_timesteps | 4757504 | +| train/ | | +| approx_kl | 2.1218915 | +| clip_fraction | 0.485 | +| clip_range | 0.2 | +| entropy_loss | -0.406 | +| explained_variance | -0.52 | +| learning_rate | 0.0001 | +| loss | -0.0671 | +| n_updates | 106980 | +| policy_gradient_loss | -0.063 | +| value_loss | 0.000514 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 309 | +| iterations | 4647 | +| time_elapsed | 15358 | +| total_timesteps | 4758528 | +| train/ | | +| approx_kl | 1.9162383 | +| clip_fraction | 0.452 | +| clip_range | 0.2 | +| entropy_loss | -0.357 | +| explained_variance | -0.819 | +| learning_rate | 0.0001 | +| loss | -0.0817 | +| n_updates | 106990 | +| policy_gradient_loss | -0.0598 | +| value_loss | 0.000581 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 309 | +| iterations | 4648 | +| time_elapsed | 15361 | +| total_timesteps | 4759552 | +| train/ | | +| approx_kl | 1.9385262 | +| clip_fraction | 0.474 | +| clip_range | 0.2 | +| entropy_loss | -0.416 | +| explained_variance | -0.379 | +| learning_rate | 0.0001 | +| loss | -0.0717 | +| n_updates | 107000 | +| policy_gradient_loss | -0.065 | +| value_loss | 0.000581 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 309 | +| iterations | 4649 | +| time_elapsed | 15365 | +| total_timesteps | 4760576 | +| train/ | | +| approx_kl | 1.8386326 | +| clip_fraction | 0.491 | +| clip_range | 0.2 | +| entropy_loss | -0.401 | +| explained_variance | -2.03 | +| learning_rate | 0.0001 | +| loss | -0.0803 | +| n_updates | 107010 | +| policy_gradient_loss | -0.0704 | +| value_loss | 0.000547 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 309 | +| iterations | 4650 | +| time_elapsed | 15368 | +| total_timesteps | 4761600 | +| train/ | | +| approx_kl | 2.381619 | +| clip_fraction | 0.445 | +| clip_range | 0.2 | +| entropy_loss | -0.348 | +| explained_variance | -0.755 | +| learning_rate | 0.0001 | +| loss | -0.108 | +| n_updates | 107020 | +| policy_gradient_loss | -0.0594 | +| value_loss | 0.00049 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 309 | +| iterations | 4651 | +| time_elapsed | 15371 | +| total_timesteps | 4762624 | +| train/ | | +| approx_kl | 1.8445573 | +| clip_fraction | 0.441 | +| clip_range | 0.2 | +| entropy_loss | -0.352 | +| explained_variance | -0.371 | +| learning_rate | 0.0001 | +| loss | -0.0861 | +| n_updates | 107030 | +| policy_gradient_loss | -0.0659 | +| value_loss | 0.000636 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 309 | +| iterations | 4652 | +| time_elapsed | 15374 | +| total_timesteps | 4763648 | +| train/ | | +| approx_kl | 2.0535007 | +| clip_fraction | 0.434 | +| clip_range | 0.2 | +| entropy_loss | -0.314 | +| explained_variance | -0.25 | +| learning_rate | 0.0001 | +| loss | -0.0722 | +| n_updates | 107040 | +| policy_gradient_loss | -0.0639 | +| value_loss | 0.000626 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 309 | +| iterations | 4653 | +| time_elapsed | 15378 | +| total_timesteps | 4764672 | +| train/ | | +| approx_kl | 2.7104967 | +| clip_fraction | 0.489 | +| clip_range | 0.2 | +| entropy_loss | -0.372 | +| explained_variance | -0.464 | +| learning_rate | 0.0001 | +| loss | -0.107 | +| n_updates | 107050 | +| policy_gradient_loss | -0.0764 | +| value_loss | 0.000549 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 309 | +| iterations | 4654 | +| time_elapsed | 15381 | +| total_timesteps | 4765696 | +| train/ | | +| approx_kl | 1.7644033 | +| clip_fraction | 0.458 | +| clip_range | 0.2 | +| entropy_loss | -0.376 | +| explained_variance | -0.544 | +| learning_rate | 0.0001 | +| loss | -0.0767 | +| n_updates | 107060 | +| policy_gradient_loss | -0.0591 | +| value_loss | 0.000479 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 309 | +| iterations | 4655 | +| time_elapsed | 15384 | +| total_timesteps | 4766720 | +| train/ | | +| approx_kl | 2.1122236 | +| clip_fraction | 0.458 | +| clip_range | 0.2 | +| entropy_loss | -0.411 | +| explained_variance | -0.692 | +| learning_rate | 0.0001 | +| loss | -0.0886 | +| n_updates | 107070 | +| policy_gradient_loss | -0.0613 | +| value_loss | 0.000379 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 309 | +| iterations | 4656 | +| time_elapsed | 15387 | +| total_timesteps | 4767744 | +| train/ | | +| approx_kl | 1.9730041 | +| clip_fraction | 0.52 | +| clip_range | 0.2 | +| entropy_loss | -0.466 | +| explained_variance | -1.34 | +| learning_rate | 0.0001 | +| loss | -0.113 | +| n_updates | 107080 | +| policy_gradient_loss | -0.0672 | +| value_loss | 0.000247 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 309 | +| iterations | 4657 | +| time_elapsed | 15391 | +| total_timesteps | 4768768 | +| train/ | | +| approx_kl | 2.1211 | +| clip_fraction | 0.464 | +| clip_range | 0.2 | +| entropy_loss | -0.357 | +| explained_variance | 0.103 | +| learning_rate | 0.0001 | +| loss | -0.0885 | +| n_updates | 107090 | +| policy_gradient_loss | -0.0631 | +| value_loss | 0.000477 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 309 | +| iterations | 4658 | +| time_elapsed | 15394 | +| total_timesteps | 4769792 | +| train/ | | +| approx_kl | 1.8443204 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.345 | +| explained_variance | -1.27 | +| learning_rate | 0.0001 | +| loss | -0.1 | +| n_updates | 107100 | +| policy_gradient_loss | -0.0713 | +| value_loss | 0.00057 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 309 | +| iterations | 4659 | +| time_elapsed | 15397 | +| total_timesteps | 4770816 | +| train/ | | +| approx_kl | 2.0771918 | +| clip_fraction | 0.472 | +| clip_range | 0.2 | +| entropy_loss | -0.364 | +| explained_variance | -1.56 | +| learning_rate | 0.0001 | +| loss | -0.0881 | +| n_updates | 107110 | +| policy_gradient_loss | -0.0671 | +| value_loss | 0.000518 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 309 | +| iterations | 4660 | +| time_elapsed | 15400 | +| total_timesteps | 4771840 | +| train/ | | +| approx_kl | 2.435779 | +| clip_fraction | 0.459 | +| clip_range | 0.2 | +| entropy_loss | -0.333 | +| explained_variance | -0.797 | +| learning_rate | 0.0001 | +| loss | -0.0863 | +| n_updates | 107120 | +| policy_gradient_loss | -0.0654 | +| value_loss | 0.000487 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 309 | +| iterations | 4661 | +| time_elapsed | 15404 | +| total_timesteps | 4772864 | +| train/ | | +| approx_kl | 2.6027446 | +| clip_fraction | 0.519 | +| clip_range | 0.2 | +| entropy_loss | -0.483 | +| explained_variance | -1.6 | +| learning_rate | 0.0001 | +| loss | -0.0923 | +| n_updates | 107130 | +| policy_gradient_loss | -0.0756 | +| value_loss | 0.000404 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 309 | +| iterations | 4662 | +| time_elapsed | 15407 | +| total_timesteps | 4773888 | +| train/ | | +| approx_kl | 2.1078684 | +| clip_fraction | 0.495 | +| clip_range | 0.2 | +| entropy_loss | -0.387 | +| explained_variance | -0.431 | +| learning_rate | 0.0001 | +| loss | -0.0756 | +| n_updates | 107140 | +| policy_gradient_loss | -0.0638 | +| value_loss | 0.000464 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 309 | +| iterations | 4663 | +| time_elapsed | 15411 | +| total_timesteps | 4774912 | +| train/ | | +| approx_kl | 2.1302514 | +| clip_fraction | 0.433 | +| clip_range | 0.2 | +| entropy_loss | -0.336 | +| explained_variance | -0.176 | +| learning_rate | 0.0001 | +| loss | -0.0703 | +| n_updates | 107150 | +| policy_gradient_loss | -0.0568 | +| value_loss | 0.000589 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 309 | +| iterations | 4664 | +| time_elapsed | 15414 | +| total_timesteps | 4775936 | +| train/ | | +| approx_kl | 1.9725327 | +| clip_fraction | 0.525 | +| clip_range | 0.2 | +| entropy_loss | -0.441 | +| explained_variance | -1.51 | +| learning_rate | 0.0001 | +| loss | -0.074 | +| n_updates | 107160 | +| policy_gradient_loss | -0.0729 | +| value_loss | 0.000423 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 309 | +| iterations | 4665 | +| time_elapsed | 15418 | +| total_timesteps | 4776960 | +| train/ | | +| approx_kl | 2.1420856 | +| clip_fraction | 0.459 | +| clip_range | 0.2 | +| entropy_loss | -0.399 | +| explained_variance | -0.837 | +| learning_rate | 0.0001 | +| loss | -0.0809 | +| n_updates | 107170 | +| policy_gradient_loss | -0.0577 | +| value_loss | 0.000552 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 309 | +| iterations | 4666 | +| time_elapsed | 15421 | +| total_timesteps | 4777984 | +| train/ | | +| approx_kl | 1.708763 | +| clip_fraction | 0.465 | +| clip_range | 0.2 | +| entropy_loss | -0.439 | +| explained_variance | -0.517 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 107180 | +| policy_gradient_loss | -0.0642 | +| value_loss | 0.000894 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 309 | +| iterations | 4667 | +| time_elapsed | 15425 | +| total_timesteps | 4779008 | +| train/ | | +| approx_kl | 1.6396539 | +| clip_fraction | 0.437 | +| clip_range | 0.2 | +| entropy_loss | -0.359 | +| explained_variance | -1.49 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 107190 | +| policy_gradient_loss | -0.066 | +| value_loss | 0.000608 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 309 | +| iterations | 4668 | +| time_elapsed | 15428 | +| total_timesteps | 4780032 | +| train/ | | +| approx_kl | 1.72881 | +| clip_fraction | 0.444 | +| clip_range | 0.2 | +| entropy_loss | -0.357 | +| explained_variance | -0.367 | +| learning_rate | 0.0001 | +| loss | -0.0844 | +| n_updates | 107200 | +| policy_gradient_loss | -0.0644 | +| value_loss | 0.000776 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 309 | +| iterations | 4669 | +| time_elapsed | 15431 | +| total_timesteps | 4781056 | +| train/ | | +| approx_kl | 1.853235 | +| clip_fraction | 0.533 | +| clip_range | 0.2 | +| entropy_loss | -0.427 | +| explained_variance | -2.7 | +| learning_rate | 0.0001 | +| loss | -0.0901 | +| n_updates | 107210 | +| policy_gradient_loss | -0.0822 | +| value_loss | 0.00061 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 309 | +| iterations | 4670 | +| time_elapsed | 15434 | +| total_timesteps | 4782080 | +| train/ | | +| approx_kl | 1.982015 | +| clip_fraction | 0.452 | +| clip_range | 0.2 | +| entropy_loss | -0.377 | +| explained_variance | -1.36 | +| learning_rate | 0.0001 | +| loss | -0.0816 | +| n_updates | 107220 | +| policy_gradient_loss | -0.0675 | +| value_loss | 0.000465 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 309 | +| iterations | 4671 | +| time_elapsed | 15437 | +| total_timesteps | 4783104 | +| train/ | | +| approx_kl | 1.7707555 | +| clip_fraction | 0.434 | +| clip_range | 0.2 | +| entropy_loss | -0.354 | +| explained_variance | -0.216 | +| learning_rate | 0.0001 | +| loss | -0.0803 | +| n_updates | 107230 | +| policy_gradient_loss | -0.0621 | +| value_loss | 0.000532 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 309 | +| iterations | 4672 | +| time_elapsed | 15441 | +| total_timesteps | 4784128 | +| train/ | | +| approx_kl | 1.6846738 | +| clip_fraction | 0.464 | +| clip_range | 0.2 | +| entropy_loss | -0.395 | +| explained_variance | -2.54 | +| learning_rate | 0.0001 | +| loss | -0.0844 | +| n_updates | 107240 | +| policy_gradient_loss | -0.0638 | +| value_loss | 0.000589 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 309 | +| iterations | 4673 | +| time_elapsed | 15444 | +| total_timesteps | 4785152 | +| train/ | | +| approx_kl | 2.026762 | +| clip_fraction | 0.44 | +| clip_range | 0.2 | +| entropy_loss | -0.355 | +| explained_variance | -0.281 | +| learning_rate | 0.0001 | +| loss | -0.0754 | +| n_updates | 107250 | +| policy_gradient_loss | -0.0633 | +| value_loss | 0.000455 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 309 | +| iterations | 4674 | +| time_elapsed | 15447 | +| total_timesteps | 4786176 | +| train/ | | +| approx_kl | 1.3710229 | +| clip_fraction | 0.452 | +| clip_range | 0.2 | +| entropy_loss | -0.415 | +| explained_variance | -0.63 | +| learning_rate | 0.0001 | +| loss | -0.078 | +| n_updates | 107260 | +| policy_gradient_loss | -0.057 | +| value_loss | 0.000554 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 309 | +| iterations | 4675 | +| time_elapsed | 15450 | +| total_timesteps | 4787200 | +| train/ | | +| approx_kl | 1.7498983 | +| clip_fraction | 0.5 | +| clip_range | 0.2 | +| entropy_loss | -0.432 | +| explained_variance | -1.38 | +| learning_rate | 0.0001 | +| loss | -0.093 | +| n_updates | 107270 | +| policy_gradient_loss | -0.0714 | +| value_loss | 0.000661 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 309 | +| iterations | 4676 | +| time_elapsed | 15454 | +| total_timesteps | 4788224 | +| train/ | | +| approx_kl | 2.585906 | +| clip_fraction | 0.468 | +| clip_range | 0.2 | +| entropy_loss | -0.425 | +| explained_variance | -0.235 | +| learning_rate | 0.0001 | +| loss | -0.0515 | +| n_updates | 107280 | +| policy_gradient_loss | -0.0609 | +| value_loss | 0.000398 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 309 | +| iterations | 4677 | +| time_elapsed | 15457 | +| total_timesteps | 4789248 | +| train/ | | +| approx_kl | 1.9533734 | +| clip_fraction | 0.448 | +| clip_range | 0.2 | +| entropy_loss | -0.363 | +| explained_variance | -0.167 | +| learning_rate | 0.0001 | +| loss | -0.1 | +| n_updates | 107290 | +| policy_gradient_loss | -0.0695 | +| value_loss | 0.000616 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 309 | +| iterations | 4678 | +| time_elapsed | 15460 | +| total_timesteps | 4790272 | +| train/ | | +| approx_kl | 1.7564274 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.39 | +| explained_variance | -1.92 | +| learning_rate | 0.0001 | +| loss | -0.108 | +| n_updates | 107300 | +| policy_gradient_loss | -0.064 | +| value_loss | 0.000387 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 309 | +| iterations | 4679 | +| time_elapsed | 15464 | +| total_timesteps | 4791296 | +| train/ | | +| approx_kl | 2.0184412 | +| clip_fraction | 0.452 | +| clip_range | 0.2 | +| entropy_loss | -0.362 | +| explained_variance | -0.262 | +| learning_rate | 0.0001 | +| loss | -0.093 | +| n_updates | 107310 | +| policy_gradient_loss | -0.0672 | +| value_loss | 0.000544 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 309 | +| iterations | 4680 | +| time_elapsed | 15467 | +| total_timesteps | 4792320 | +| train/ | | +| approx_kl | 1.9700016 | +| clip_fraction | 0.422 | +| clip_range | 0.2 | +| entropy_loss | -0.316 | +| explained_variance | -0.257 | +| learning_rate | 0.0001 | +| loss | -0.0607 | +| n_updates | 107320 | +| policy_gradient_loss | -0.0574 | +| value_loss | 0.000645 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 309 | +| iterations | 4681 | +| time_elapsed | 15471 | +| total_timesteps | 4793344 | +| train/ | | +| approx_kl | 1.8137671 | +| clip_fraction | 0.445 | +| clip_range | 0.2 | +| entropy_loss | -0.361 | +| explained_variance | -0.662 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 107330 | +| policy_gradient_loss | -0.0639 | +| value_loss | 0.000682 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 309 | +| iterations | 4682 | +| time_elapsed | 15474 | +| total_timesteps | 4794368 | +| train/ | | +| approx_kl | 2.1605647 | +| clip_fraction | 0.489 | +| clip_range | 0.2 | +| entropy_loss | -0.394 | +| explained_variance | -0.814 | +| learning_rate | 0.0001 | +| loss | -0.118 | +| n_updates | 107340 | +| policy_gradient_loss | -0.0735 | +| value_loss | 0.000397 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 309 | +| iterations | 4683 | +| time_elapsed | 15478 | +| total_timesteps | 4795392 | +| train/ | | +| approx_kl | 1.8128709 | +| clip_fraction | 0.479 | +| clip_range | 0.2 | +| entropy_loss | -0.376 | +| explained_variance | -1.18 | +| learning_rate | 0.0001 | +| loss | -0.0866 | +| n_updates | 107350 | +| policy_gradient_loss | -0.0729 | +| value_loss | 0.000329 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 309 | +| iterations | 4684 | +| time_elapsed | 15481 | +| total_timesteps | 4796416 | +| train/ | | +| approx_kl | 2.983747 | +| clip_fraction | 0.505 | +| clip_range | 0.2 | +| entropy_loss | -0.45 | +| explained_variance | 0.0039 | +| learning_rate | 0.0001 | +| loss | -0.0579 | +| n_updates | 107360 | +| policy_gradient_loss | -0.0608 | +| value_loss | 0.000392 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 309 | +| iterations | 4685 | +| time_elapsed | 15485 | +| total_timesteps | 4797440 | +| train/ | | +| approx_kl | 2.2276382 | +| clip_fraction | 0.47 | +| clip_range | 0.2 | +| entropy_loss | -0.395 | +| explained_variance | -0.941 | +| learning_rate | 0.0001 | +| loss | -0.0635 | +| n_updates | 107370 | +| policy_gradient_loss | -0.0597 | +| value_loss | 0.000599 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 309 | +| iterations | 4686 | +| time_elapsed | 15488 | +| total_timesteps | 4798464 | +| train/ | | +| approx_kl | 3.3494167 | +| clip_fraction | 0.459 | +| clip_range | 0.2 | +| entropy_loss | -0.385 | +| explained_variance | -0.746 | +| learning_rate | 0.0001 | +| loss | -0.0853 | +| n_updates | 107380 | +| policy_gradient_loss | -0.0652 | +| value_loss | 0.00052 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 309 | +| iterations | 4687 | +| time_elapsed | 15491 | +| total_timesteps | 4799488 | +| train/ | | +| approx_kl | 1.9364972 | +| clip_fraction | 0.492 | +| clip_range | 0.2 | +| entropy_loss | -0.433 | +| explained_variance | -0.0597 | +| learning_rate | 0.0001 | +| loss | -0.0775 | +| n_updates | 107390 | +| policy_gradient_loss | -0.0665 | +| value_loss | 0.000786 | +--------------------------------------- + +Current state: Champion.Level1.RyuVsGuile +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 309 | +| iterations | 4688 | +| time_elapsed | 15495 | +| total_timesteps | 4800512 | +| train/ | | +| approx_kl | 3.0711515 | +| clip_fraction | 0.444 | +| clip_range | 0.2 | +| entropy_loss | -0.367 | +| explained_variance | -0.472 | +| learning_rate | 0.0001 | +| loss | -0.0809 | +| n_updates | 107400 | +| policy_gradient_loss | -0.0604 | +| value_loss | 0.0009 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 309 | +| iterations | 4689 | +| time_elapsed | 15498 | +| total_timesteps | 4801536 | +| train/ | | +| approx_kl | 1.7490134 | +| clip_fraction | 0.506 | +| clip_range | 0.2 | +| entropy_loss | -0.455 | +| explained_variance | -0.387 | +| learning_rate | 0.0001 | +| loss | -0.0717 | +| n_updates | 107410 | +| policy_gradient_loss | -0.0647 | +| value_loss | 0.00048 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 309 | +| iterations | 4690 | +| time_elapsed | 15501 | +| total_timesteps | 4802560 | +| train/ | | +| approx_kl | 2.2231019 | +| clip_fraction | 0.532 | +| clip_range | 0.2 | +| entropy_loss | -0.472 | +| explained_variance | -0.642 | +| learning_rate | 0.0001 | +| loss | -0.0788 | +| n_updates | 107420 | +| policy_gradient_loss | -0.0707 | +| value_loss | 0.000536 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 309 | +| iterations | 4691 | +| time_elapsed | 15504 | +| total_timesteps | 4803584 | +| train/ | | +| approx_kl | 1.6956983 | +| clip_fraction | 0.559 | +| clip_range | 0.2 | +| entropy_loss | -0.579 | +| explained_variance | -2.46 | +| learning_rate | 0.0001 | +| loss | -0.121 | +| n_updates | 107430 | +| policy_gradient_loss | -0.0782 | +| value_loss | 0.000331 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 309 | +| iterations | 4692 | +| time_elapsed | 15508 | +| total_timesteps | 4804608 | +| train/ | | +| approx_kl | 1.4381332 | +| clip_fraction | 0.543 | +| clip_range | 0.2 | +| entropy_loss | -0.607 | +| explained_variance | -0.644 | +| learning_rate | 0.0001 | +| loss | -0.0907 | +| n_updates | 107440 | +| policy_gradient_loss | -0.0679 | +| value_loss | 0.000239 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 309 | +| iterations | 4693 | +| time_elapsed | 15511 | +| total_timesteps | 4805632 | +| train/ | | +| approx_kl | 1.21639 | +| clip_fraction | 0.551 | +| clip_range | 0.2 | +| entropy_loss | -0.66 | +| explained_variance | -0.804 | +| learning_rate | 0.0001 | +| loss | -0.0935 | +| n_updates | 107450 | +| policy_gradient_loss | -0.0696 | +| value_loss | 0.000205 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 309 | +| iterations | 4694 | +| time_elapsed | 15514 | +| total_timesteps | 4806656 | +| train/ | | +| approx_kl | 1.584991 | +| clip_fraction | 0.565 | +| clip_range | 0.2 | +| entropy_loss | -0.594 | +| explained_variance | -0.786 | +| learning_rate | 0.0001 | +| loss | -0.0959 | +| n_updates | 107460 | +| policy_gradient_loss | -0.0768 | +| value_loss | 0.000301 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 309 | +| iterations | 4695 | +| time_elapsed | 15517 | +| total_timesteps | 4807680 | +| train/ | | +| approx_kl | 1.9644731 | +| clip_fraction | 0.513 | +| clip_range | 0.2 | +| entropy_loss | -0.477 | +| explained_variance | -1.56 | +| learning_rate | 0.0001 | +| loss | -0.111 | +| n_updates | 107470 | +| policy_gradient_loss | -0.0754 | +| value_loss | 0.000247 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 309 | +| iterations | 4696 | +| time_elapsed | 15520 | +| total_timesteps | 4808704 | +| train/ | | +| approx_kl | 1.500277 | +| clip_fraction | 0.552 | +| clip_range | 0.2 | +| entropy_loss | -0.66 | +| explained_variance | -0.22 | +| learning_rate | 0.0001 | +| loss | -0.0744 | +| n_updates | 107480 | +| policy_gradient_loss | -0.057 | +| value_loss | 0.000488 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 309 | +| iterations | 4697 | +| time_elapsed | 15524 | +| total_timesteps | 4809728 | +| train/ | | +| approx_kl | 2.4126763 | +| clip_fraction | 0.536 | +| clip_range | 0.2 | +| entropy_loss | -0.548 | +| explained_variance | -1.1 | +| learning_rate | 0.0001 | +| loss | -0.0619 | +| n_updates | 107490 | +| policy_gradient_loss | -0.074 | +| value_loss | 0.000615 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 309 | +| iterations | 4698 | +| time_elapsed | 15527 | +| total_timesteps | 4810752 | +| train/ | | +| approx_kl | 1.1831727 | +| clip_fraction | 0.506 | +| clip_range | 0.2 | +| entropy_loss | -0.538 | +| explained_variance | -3.03 | +| learning_rate | 0.0001 | +| loss | -0.108 | +| n_updates | 107500 | +| policy_gradient_loss | -0.0674 | +| value_loss | 0.000211 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 309 | +| iterations | 4699 | +| time_elapsed | 15531 | +| total_timesteps | 4811776 | +| train/ | | +| approx_kl | 1.7885101 | +| clip_fraction | 0.577 | +| clip_range | 0.2 | +| entropy_loss | -0.612 | +| explained_variance | -0.584 | +| learning_rate | 0.0001 | +| loss | -0.0915 | +| n_updates | 107510 | +| policy_gradient_loss | -0.0774 | +| value_loss | 0.000361 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 309 | +| iterations | 4700 | +| time_elapsed | 15534 | +| total_timesteps | 4812800 | +| train/ | | +| approx_kl | 1.2483652 | +| clip_fraction | 0.544 | +| clip_range | 0.2 | +| entropy_loss | -0.595 | +| explained_variance | -2.3 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 107520 | +| policy_gradient_loss | -0.0707 | +| value_loss | 0.000335 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 309 | +| iterations | 4701 | +| time_elapsed | 15538 | +| total_timesteps | 4813824 | +| train/ | | +| approx_kl | 1.8076401 | +| clip_fraction | 0.536 | +| clip_range | 0.2 | +| entropy_loss | -0.537 | +| explained_variance | -1.36 | +| learning_rate | 0.0001 | +| loss | -0.109 | +| n_updates | 107530 | +| policy_gradient_loss | -0.0766 | +| value_loss | 0.000368 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 309 | +| iterations | 4702 | +| time_elapsed | 15541 | +| total_timesteps | 4814848 | +| train/ | | +| approx_kl | 1.5947987 | +| clip_fraction | 0.54 | +| clip_range | 0.2 | +| entropy_loss | -0.518 | +| explained_variance | -0.216 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 107540 | +| policy_gradient_loss | -0.0707 | +| value_loss | 0.000491 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 309 | +| iterations | 4703 | +| time_elapsed | 15544 | +| total_timesteps | 4815872 | +| train/ | | +| approx_kl | 2.115901 | +| clip_fraction | 0.524 | +| clip_range | 0.2 | +| entropy_loss | -0.501 | +| explained_variance | -1.67 | +| learning_rate | 0.0001 | +| loss | -0.0928 | +| n_updates | 107550 | +| policy_gradient_loss | -0.0825 | +| value_loss | 0.000482 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 309 | +| iterations | 4704 | +| time_elapsed | 15548 | +| total_timesteps | 4816896 | +| train/ | | +| approx_kl | 1.569897 | +| clip_fraction | 0.532 | +| clip_range | 0.2 | +| entropy_loss | -0.532 | +| explained_variance | -1.34 | +| learning_rate | 0.0001 | +| loss | -0.0821 | +| n_updates | 107560 | +| policy_gradient_loss | -0.0765 | +| value_loss | 0.000369 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 309 | +| iterations | 4705 | +| time_elapsed | 15551 | +| total_timesteps | 4817920 | +| train/ | | +| approx_kl | 2.8442059 | +| clip_fraction | 0.527 | +| clip_range | 0.2 | +| entropy_loss | -0.482 | +| explained_variance | -0.785 | +| learning_rate | 0.0001 | +| loss | -0.105 | +| n_updates | 107570 | +| policy_gradient_loss | -0.0705 | +| value_loss | 0.000369 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 309 | +| iterations | 4706 | +| time_elapsed | 15554 | +| total_timesteps | 4818944 | +| train/ | | +| approx_kl | 1.7397194 | +| clip_fraction | 0.543 | +| clip_range | 0.2 | +| entropy_loss | -0.603 | +| explained_variance | -0.387 | +| learning_rate | 0.0001 | +| loss | -0.109 | +| n_updates | 107580 | +| policy_gradient_loss | -0.0754 | +| value_loss | 0.000448 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 309 | +| iterations | 4707 | +| time_elapsed | 15557 | +| total_timesteps | 4819968 | +| train/ | | +| approx_kl | 1.6739707 | +| clip_fraction | 0.534 | +| clip_range | 0.2 | +| entropy_loss | -0.582 | +| explained_variance | -1.09 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 107590 | +| policy_gradient_loss | -0.0658 | +| value_loss | 0.000404 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 309 | +| iterations | 4708 | +| time_elapsed | 15561 | +| total_timesteps | 4820992 | +| train/ | | +| approx_kl | 1.6171691 | +| clip_fraction | 0.55 | +| clip_range | 0.2 | +| entropy_loss | -0.607 | +| explained_variance | -1.92 | +| learning_rate | 0.0001 | +| loss | -0.099 | +| n_updates | 107600 | +| policy_gradient_loss | -0.0791 | +| value_loss | 0.000283 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 309 | +| iterations | 4709 | +| time_elapsed | 15564 | +| total_timesteps | 4822016 | +| train/ | | +| approx_kl | 1.4078803 | +| clip_fraction | 0.533 | +| clip_range | 0.2 | +| entropy_loss | -0.557 | +| explained_variance | -2.08 | +| learning_rate | 0.0001 | +| loss | -0.108 | +| n_updates | 107610 | +| policy_gradient_loss | -0.0824 | +| value_loss | 9.55e-05 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 309 | +| iterations | 4710 | +| time_elapsed | 15567 | +| total_timesteps | 4823040 | +| train/ | | +| approx_kl | 1.0415308 | +| clip_fraction | 0.468 | +| clip_range | 0.2 | +| entropy_loss | -0.566 | +| explained_variance | -1.59 | +| learning_rate | 0.0001 | +| loss | -0.0881 | +| n_updates | 107620 | +| policy_gradient_loss | -0.0647 | +| value_loss | 2.28e-05 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 309 | +| iterations | 4711 | +| time_elapsed | 15570 | +| total_timesteps | 4824064 | +| train/ | | +| approx_kl | 0.5911147 | +| clip_fraction | 0.455 | +| clip_range | 0.2 | +| entropy_loss | -0.979 | +| explained_variance | 0.00874 | +| learning_rate | 0.0001 | +| loss | -0.0384 | +| n_updates | 107630 | +| policy_gradient_loss | -0.0303 | +| value_loss | 0.00108 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 309 | +| iterations | 4712 | +| time_elapsed | 15573 | +| total_timesteps | 4825088 | +| train/ | | +| approx_kl | 3.7771058 | +| clip_fraction | 0.503 | +| clip_range | 0.2 | +| entropy_loss | -0.474 | +| explained_variance | -4.96 | +| learning_rate | 0.0001 | +| loss | -0.0901 | +| n_updates | 107640 | +| policy_gradient_loss | -0.0781 | +| value_loss | 0.000642 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 309 | +| iterations | 4713 | +| time_elapsed | 15576 | +| total_timesteps | 4826112 | +| train/ | | +| approx_kl | 1.7415626 | +| clip_fraction | 0.506 | +| clip_range | 0.2 | +| entropy_loss | -0.489 | +| explained_variance | -1.14 | +| learning_rate | 0.0001 | +| loss | -0.105 | +| n_updates | 107650 | +| policy_gradient_loss | -0.072 | +| value_loss | 0.000338 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 309 | +| iterations | 4714 | +| time_elapsed | 15579 | +| total_timesteps | 4827136 | +| train/ | | +| approx_kl | 1.8209611 | +| clip_fraction | 0.561 | +| clip_range | 0.2 | +| entropy_loss | -0.539 | +| explained_variance | -1.26 | +| learning_rate | 0.0001 | +| loss | -0.0661 | +| n_updates | 107660 | +| policy_gradient_loss | -0.0741 | +| value_loss | 0.000625 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 309 | +| iterations | 4715 | +| time_elapsed | 15583 | +| total_timesteps | 4828160 | +| train/ | | +| approx_kl | 1.5019536 | +| clip_fraction | 0.588 | +| clip_range | 0.2 | +| entropy_loss | -0.722 | +| explained_variance | -5.17 | +| learning_rate | 0.0001 | +| loss | -0.116 | +| n_updates | 107670 | +| policy_gradient_loss | -0.0714 | +| value_loss | 0.000388 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 309 | +| iterations | 4716 | +| time_elapsed | 15586 | +| total_timesteps | 4829184 | +| train/ | | +| approx_kl | 1.3531938 | +| clip_fraction | 0.464 | +| clip_range | 0.2 | +| entropy_loss | -0.423 | +| explained_variance | -2.92 | +| learning_rate | 0.0001 | +| loss | -0.0964 | +| n_updates | 107680 | +| policy_gradient_loss | -0.0643 | +| value_loss | 0.000202 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.43e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 309 | +| iterations | 4717 | +| time_elapsed | 15590 | +| total_timesteps | 4830208 | +| train/ | | +| approx_kl | 1.7918766 | +| clip_fraction | 0.518 | +| clip_range | 0.2 | +| entropy_loss | -0.544 | +| explained_variance | -0.961 | +| learning_rate | 0.0001 | +| loss | -0.111 | +| n_updates | 107690 | +| policy_gradient_loss | -0.0608 | +| value_loss | 0.000596 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.44e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 309 | +| iterations | 4718 | +| time_elapsed | 15593 | +| total_timesteps | 4831232 | +| train/ | | +| approx_kl | 2.2823853 | +| clip_fraction | 0.566 | +| clip_range | 0.2 | +| entropy_loss | -0.604 | +| explained_variance | -1.18 | +| learning_rate | 0.0001 | +| loss | -0.114 | +| n_updates | 107700 | +| policy_gradient_loss | -0.0779 | +| value_loss | 0.000401 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.44e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 309 | +| iterations | 4719 | +| time_elapsed | 15597 | +| total_timesteps | 4832256 | +| train/ | | +| approx_kl | 1.640415 | +| clip_fraction | 0.521 | +| clip_range | 0.2 | +| entropy_loss | -0.53 | +| explained_variance | -0.697 | +| learning_rate | 0.0001 | +| loss | -0.075 | +| n_updates | 107710 | +| policy_gradient_loss | -0.0666 | +| value_loss | 0.000515 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.44e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 309 | +| iterations | 4720 | +| time_elapsed | 15600 | +| total_timesteps | 4833280 | +| train/ | | +| approx_kl | 1.373945 | +| clip_fraction | 0.494 | +| clip_range | 0.2 | +| entropy_loss | -0.472 | +| explained_variance | -2.1 | +| learning_rate | 0.0001 | +| loss | -0.0752 | +| n_updates | 107720 | +| policy_gradient_loss | -0.0691 | +| value_loss | 0.000716 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.44e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 309 | +| iterations | 4721 | +| time_elapsed | 15604 | +| total_timesteps | 4834304 | +| train/ | | +| approx_kl | 1.6442666 | +| clip_fraction | 0.521 | +| clip_range | 0.2 | +| entropy_loss | -0.505 | +| explained_variance | -8.73 | +| learning_rate | 0.0001 | +| loss | -0.0993 | +| n_updates | 107730 | +| policy_gradient_loss | -0.0711 | +| value_loss | 0.00048 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.46e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 309 | +| iterations | 4722 | +| time_elapsed | 15607 | +| total_timesteps | 4835328 | +| train/ | | +| approx_kl | 1.7277359 | +| clip_fraction | 0.553 | +| clip_range | 0.2 | +| entropy_loss | -0.61 | +| explained_variance | -3.01 | +| learning_rate | 0.0001 | +| loss | -0.111 | +| n_updates | 107740 | +| policy_gradient_loss | -0.0779 | +| value_loss | 0.000252 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.46e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 309 | +| iterations | 4723 | +| time_elapsed | 15611 | +| total_timesteps | 4836352 | +| train/ | | +| approx_kl | 1.274058 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.448 | +| explained_variance | -0.892 | +| learning_rate | 0.0001 | +| loss | -0.0946 | +| n_updates | 107750 | +| policy_gradient_loss | -0.0687 | +| value_loss | 0.000366 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.47e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 309 | +| iterations | 4724 | +| time_elapsed | 15614 | +| total_timesteps | 4837376 | +| train/ | | +| approx_kl | 1.5246863 | +| clip_fraction | 0.546 | +| clip_range | 0.2 | +| entropy_loss | -0.527 | +| explained_variance | -1.85 | +| learning_rate | 0.0001 | +| loss | -0.0909 | +| n_updates | 107760 | +| policy_gradient_loss | -0.0752 | +| value_loss | 0.000185 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.46e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 309 | +| iterations | 4725 | +| time_elapsed | 15617 | +| total_timesteps | 4838400 | +| train/ | | +| approx_kl | 1.4055871 | +| clip_fraction | 0.545 | +| clip_range | 0.2 | +| entropy_loss | -0.546 | +| explained_variance | -0.302 | +| learning_rate | 0.0001 | +| loss | -0.113 | +| n_updates | 107770 | +| policy_gradient_loss | -0.0762 | +| value_loss | 0.000361 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.46e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 309 | +| iterations | 4726 | +| time_elapsed | 15620 | +| total_timesteps | 4839424 | +| train/ | | +| approx_kl | 1.9626935 | +| clip_fraction | 0.491 | +| clip_range | 0.2 | +| entropy_loss | -0.504 | +| explained_variance | -1.37 | +| learning_rate | 0.0001 | +| loss | -0.082 | +| n_updates | 107780 | +| policy_gradient_loss | -0.0678 | +| value_loss | 0.000284 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.47e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 309 | +| iterations | 4727 | +| time_elapsed | 15623 | +| total_timesteps | 4840448 | +| train/ | | +| approx_kl | 1.4970918 | +| clip_fraction | 0.518 | +| clip_range | 0.2 | +| entropy_loss | -0.543 | +| explained_variance | -1.6 | +| learning_rate | 0.0001 | +| loss | -0.0694 | +| n_updates | 107790 | +| policy_gradient_loss | -0.0737 | +| value_loss | 0.000249 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.47e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 309 | +| iterations | 4728 | +| time_elapsed | 15627 | +| total_timesteps | 4841472 | +| train/ | | +| approx_kl | 1.7887423 | +| clip_fraction | 0.529 | +| clip_range | 0.2 | +| entropy_loss | -0.519 | +| explained_variance | -0.29 | +| learning_rate | 0.0001 | +| loss | -0.0789 | +| n_updates | 107800 | +| policy_gradient_loss | -0.0684 | +| value_loss | 0.000437 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.48e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 309 | +| iterations | 4729 | +| time_elapsed | 15630 | +| total_timesteps | 4842496 | +| train/ | | +| approx_kl | 1.6047039 | +| clip_fraction | 0.529 | +| clip_range | 0.2 | +| entropy_loss | -0.583 | +| explained_variance | -1.48 | +| learning_rate | 0.0001 | +| loss | -0.0953 | +| n_updates | 107810 | +| policy_gradient_loss | -0.077 | +| value_loss | 0.000391 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.48e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 309 | +| iterations | 4730 | +| time_elapsed | 15633 | +| total_timesteps | 4843520 | +| train/ | | +| approx_kl | 1.339998 | +| clip_fraction | 0.508 | +| clip_range | 0.2 | +| entropy_loss | -0.517 | +| explained_variance | -0.439 | +| learning_rate | 0.0001 | +| loss | -0.0984 | +| n_updates | 107820 | +| policy_gradient_loss | -0.0668 | +| value_loss | 0.000457 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.49e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 309 | +| iterations | 4731 | +| time_elapsed | 15636 | +| total_timesteps | 4844544 | +| train/ | | +| approx_kl | 1.5776379 | +| clip_fraction | 0.524 | +| clip_range | 0.2 | +| entropy_loss | -0.56 | +| explained_variance | -5.16 | +| learning_rate | 0.0001 | +| loss | -0.115 | +| n_updates | 107830 | +| policy_gradient_loss | -0.0841 | +| value_loss | 0.000194 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.49e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 309 | +| iterations | 4732 | +| time_elapsed | 15639 | +| total_timesteps | 4845568 | +| train/ | | +| approx_kl | 1.4455997 | +| clip_fraction | 0.463 | +| clip_range | 0.2 | +| entropy_loss | -0.544 | +| explained_variance | -0.255 | +| learning_rate | 0.0001 | +| loss | -0.0704 | +| n_updates | 107840 | +| policy_gradient_loss | -0.0542 | +| value_loss | 0.000169 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.5e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 309 | +| iterations | 4733 | +| time_elapsed | 15643 | +| total_timesteps | 4846592 | +| train/ | | +| approx_kl | 1.4548323 | +| clip_fraction | 0.54 | +| clip_range | 0.2 | +| entropy_loss | -0.561 | +| explained_variance | -1.88 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 107850 | +| policy_gradient_loss | -0.0767 | +| value_loss | 0.000303 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.5e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 309 | +| iterations | 4734 | +| time_elapsed | 15646 | +| total_timesteps | 4847616 | +| train/ | | +| approx_kl | 1.3029537 | +| clip_fraction | 0.515 | +| clip_range | 0.2 | +| entropy_loss | -0.541 | +| explained_variance | -0.261 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 107860 | +| policy_gradient_loss | -0.0645 | +| value_loss | 0.000468 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.51e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 309 | +| iterations | 4735 | +| time_elapsed | 15649 | +| total_timesteps | 4848640 | +| train/ | | +| approx_kl | 1.7528578 | +| clip_fraction | 0.521 | +| clip_range | 0.2 | +| entropy_loss | -0.48 | +| explained_variance | -4.33 | +| learning_rate | 0.0001 | +| loss | -0.121 | +| n_updates | 107870 | +| policy_gradient_loss | -0.0821 | +| value_loss | 0.000556 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.51e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 309 | +| iterations | 4736 | +| time_elapsed | 15653 | +| total_timesteps | 4849664 | +| train/ | | +| approx_kl | 1.5706853 | +| clip_fraction | 0.521 | +| clip_range | 0.2 | +| entropy_loss | -0.545 | +| explained_variance | -0.292 | +| learning_rate | 0.0001 | +| loss | -0.115 | +| n_updates | 107880 | +| policy_gradient_loss | -0.0671 | +| value_loss | 0.000369 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.51e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 309 | +| iterations | 4737 | +| time_elapsed | 15656 | +| total_timesteps | 4850688 | +| train/ | | +| approx_kl | 2.9557452 | +| clip_fraction | 0.551 | +| clip_range | 0.2 | +| entropy_loss | -0.556 | +| explained_variance | -0.514 | +| learning_rate | 0.0001 | +| loss | -0.0882 | +| n_updates | 107890 | +| policy_gradient_loss | -0.0767 | +| value_loss | 0.000665 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.51e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 309 | +| iterations | 4738 | +| time_elapsed | 15659 | +| total_timesteps | 4851712 | +| train/ | | +| approx_kl | 1.3559382 | +| clip_fraction | 0.496 | +| clip_range | 0.2 | +| entropy_loss | -0.522 | +| explained_variance | -2.4 | +| learning_rate | 0.0001 | +| loss | -0.105 | +| n_updates | 107900 | +| policy_gradient_loss | -0.0747 | +| value_loss | 0.000375 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.51e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 309 | +| iterations | 4739 | +| time_elapsed | 15663 | +| total_timesteps | 4852736 | +| train/ | | +| approx_kl | 1.325057 | +| clip_fraction | 0.526 | +| clip_range | 0.2 | +| entropy_loss | -0.672 | +| explained_variance | -0.159 | +| learning_rate | 0.0001 | +| loss | -0.0999 | +| n_updates | 107910 | +| policy_gradient_loss | -0.0708 | +| value_loss | 0.000158 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.51e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 309 | +| iterations | 4740 | +| time_elapsed | 15666 | +| total_timesteps | 4853760 | +| train/ | | +| approx_kl | 2.5342278 | +| clip_fraction | 0.539 | +| clip_range | 0.2 | +| entropy_loss | -0.507 | +| explained_variance | -0.262 | +| learning_rate | 0.0001 | +| loss | -0.0566 | +| n_updates | 107920 | +| policy_gradient_loss | -0.0593 | +| value_loss | 0.00042 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.53e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 309 | +| iterations | 4741 | +| time_elapsed | 15669 | +| total_timesteps | 4854784 | +| train/ | | +| approx_kl | 1.6045811 | +| clip_fraction | 0.51 | +| clip_range | 0.2 | +| entropy_loss | -0.557 | +| explained_variance | -4.26 | +| learning_rate | 0.0001 | +| loss | -0.111 | +| n_updates | 107930 | +| policy_gradient_loss | -0.0776 | +| value_loss | 0.000222 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.53e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 309 | +| iterations | 4742 | +| time_elapsed | 15672 | +| total_timesteps | 4855808 | +| train/ | | +| approx_kl | 1.4038645 | +| clip_fraction | 0.503 | +| clip_range | 0.2 | +| entropy_loss | -0.568 | +| explained_variance | -2.55 | +| learning_rate | 0.0001 | +| loss | -0.0895 | +| n_updates | 107940 | +| policy_gradient_loss | -0.0695 | +| value_loss | 0.000149 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.54e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 309 | +| iterations | 4743 | +| time_elapsed | 15676 | +| total_timesteps | 4856832 | +| train/ | | +| approx_kl | 1.273077 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.515 | +| explained_variance | -0.759 | +| learning_rate | 0.0001 | +| loss | -0.0969 | +| n_updates | 107950 | +| policy_gradient_loss | -0.0711 | +| value_loss | 0.000368 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.54e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 309 | +| iterations | 4744 | +| time_elapsed | 15679 | +| total_timesteps | 4857856 | +| train/ | | +| approx_kl | 2.2344801 | +| clip_fraction | 0.527 | +| clip_range | 0.2 | +| entropy_loss | -0.535 | +| explained_variance | -0.919 | +| learning_rate | 0.0001 | +| loss | -0.0898 | +| n_updates | 107960 | +| policy_gradient_loss | -0.0715 | +| value_loss | 0.000522 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.54e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 309 | +| iterations | 4745 | +| time_elapsed | 15682 | +| total_timesteps | 4858880 | +| train/ | | +| approx_kl | 1.6824856 | +| clip_fraction | 0.525 | +| clip_range | 0.2 | +| entropy_loss | -0.484 | +| explained_variance | -2.26 | +| learning_rate | 0.0001 | +| loss | -0.0936 | +| n_updates | 107970 | +| policy_gradient_loss | -0.0809 | +| value_loss | 0.000486 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.55e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 309 | +| iterations | 4746 | +| time_elapsed | 15685 | +| total_timesteps | 4859904 | +| train/ | | +| approx_kl | 1.864198 | +| clip_fraction | 0.538 | +| clip_range | 0.2 | +| entropy_loss | -0.565 | +| explained_variance | -4.38 | +| learning_rate | 0.0001 | +| loss | -0.0912 | +| n_updates | 107980 | +| policy_gradient_loss | -0.079 | +| value_loss | 0.000366 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.55e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 309 | +| iterations | 4747 | +| time_elapsed | 15688 | +| total_timesteps | 4860928 | +| train/ | | +| approx_kl | 1.4501407 | +| clip_fraction | 0.498 | +| clip_range | 0.2 | +| entropy_loss | -0.478 | +| explained_variance | -1.13 | +| learning_rate | 0.0001 | +| loss | -0.109 | +| n_updates | 107990 | +| policy_gradient_loss | -0.0724 | +| value_loss | 0.000239 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.55e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 309 | +| iterations | 4748 | +| time_elapsed | 15691 | +| total_timesteps | 4861952 | +| train/ | | +| approx_kl | 1.9484006 | +| clip_fraction | 0.54 | +| clip_range | 0.2 | +| entropy_loss | -0.534 | +| explained_variance | -0.493 | +| learning_rate | 0.0001 | +| loss | -0.0915 | +| n_updates | 108000 | +| policy_gradient_loss | -0.071 | +| value_loss | 0.000359 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.56e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 309 | +| iterations | 4749 | +| time_elapsed | 15695 | +| total_timesteps | 4862976 | +| train/ | | +| approx_kl | 1.8140159 | +| clip_fraction | 0.525 | +| clip_range | 0.2 | +| entropy_loss | -0.535 | +| explained_variance | -4.18 | +| learning_rate | 0.0001 | +| loss | -0.0918 | +| n_updates | 108010 | +| policy_gradient_loss | -0.0787 | +| value_loss | 0.000257 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.56e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 309 | +| iterations | 4750 | +| time_elapsed | 15698 | +| total_timesteps | 4864000 | +| train/ | | +| approx_kl | 1.4355637 | +| clip_fraction | 0.545 | +| clip_range | 0.2 | +| entropy_loss | -0.538 | +| explained_variance | -0.583 | +| learning_rate | 0.0001 | +| loss | -0.0905 | +| n_updates | 108020 | +| policy_gradient_loss | -0.0652 | +| value_loss | 0.000363 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.58e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 309 | +| iterations | 4751 | +| time_elapsed | 15701 | +| total_timesteps | 4865024 | +| train/ | | +| approx_kl | 1.4774305 | +| clip_fraction | 0.522 | +| clip_range | 0.2 | +| entropy_loss | -0.548 | +| explained_variance | -1.46 | +| learning_rate | 0.0001 | +| loss | -0.109 | +| n_updates | 108030 | +| policy_gradient_loss | -0.0641 | +| value_loss | 0.000379 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.58e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 309 | +| iterations | 4752 | +| time_elapsed | 15704 | +| total_timesteps | 4866048 | +| train/ | | +| approx_kl | 1.8264617 | +| clip_fraction | 0.537 | +| clip_range | 0.2 | +| entropy_loss | -0.505 | +| explained_variance | -1.16 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 108040 | +| policy_gradient_loss | -0.0758 | +| value_loss | 0.00063 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.58e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 309 | +| iterations | 4753 | +| time_elapsed | 15708 | +| total_timesteps | 4867072 | +| train/ | | +| approx_kl | 1.9604443 | +| clip_fraction | 0.538 | +| clip_range | 0.2 | +| entropy_loss | -0.494 | +| explained_variance | -2.82 | +| learning_rate | 0.0001 | +| loss | -0.106 | +| n_updates | 108050 | +| policy_gradient_loss | -0.077 | +| value_loss | 0.000607 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.58e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 309 | +| iterations | 4754 | +| time_elapsed | 15711 | +| total_timesteps | 4868096 | +| train/ | | +| approx_kl | 3.068019 | +| clip_fraction | 0.522 | +| clip_range | 0.2 | +| entropy_loss | -0.536 | +| explained_variance | -0.573 | +| learning_rate | 0.0001 | +| loss | -0.0808 | +| n_updates | 108060 | +| policy_gradient_loss | -0.0665 | +| value_loss | 0.000478 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 309 | +| iterations | 4755 | +| time_elapsed | 15715 | +| total_timesteps | 4869120 | +| train/ | | +| approx_kl | 1.4310635 | +| clip_fraction | 0.503 | +| clip_range | 0.2 | +| entropy_loss | -0.538 | +| explained_variance | -3.17 | +| learning_rate | 0.0001 | +| loss | -0.0831 | +| n_updates | 108070 | +| policy_gradient_loss | -0.0734 | +| value_loss | 0.00033 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 309 | +| iterations | 4756 | +| time_elapsed | 15718 | +| total_timesteps | 4870144 | +| train/ | | +| approx_kl | 1.4397849 | +| clip_fraction | 0.503 | +| clip_range | 0.2 | +| entropy_loss | -0.488 | +| explained_variance | -1.21 | +| learning_rate | 0.0001 | +| loss | -0.0876 | +| n_updates | 108080 | +| policy_gradient_loss | -0.0684 | +| value_loss | 0.00033 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 309 | +| iterations | 4757 | +| time_elapsed | 15722 | +| total_timesteps | 4871168 | +| train/ | | +| approx_kl | 2.4276104 | +| clip_fraction | 0.515 | +| clip_range | 0.2 | +| entropy_loss | -0.6 | +| explained_variance | -0.481 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 108090 | +| policy_gradient_loss | -0.0681 | +| value_loss | 0.00036 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 309 | +| iterations | 4758 | +| time_elapsed | 15725 | +| total_timesteps | 4872192 | +| train/ | | +| approx_kl | 1.468895 | +| clip_fraction | 0.534 | +| clip_range | 0.2 | +| entropy_loss | -0.561 | +| explained_variance | -1.35 | +| learning_rate | 0.0001 | +| loss | -0.0709 | +| n_updates | 108100 | +| policy_gradient_loss | -0.0623 | +| value_loss | 0.000361 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 309 | +| iterations | 4759 | +| time_elapsed | 15728 | +| total_timesteps | 4873216 | +| train/ | | +| approx_kl | 2.019769 | +| clip_fraction | 0.535 | +| clip_range | 0.2 | +| entropy_loss | -0.478 | +| explained_variance | -0.293 | +| learning_rate | 0.0001 | +| loss | -0.114 | +| n_updates | 108110 | +| policy_gradient_loss | -0.0764 | +| value_loss | 0.000448 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 309 | +| iterations | 4760 | +| time_elapsed | 15732 | +| total_timesteps | 4874240 | +| train/ | | +| approx_kl | 1.3291115 | +| clip_fraction | 0.517 | +| clip_range | 0.2 | +| entropy_loss | -0.519 | +| explained_variance | -1.42 | +| learning_rate | 0.0001 | +| loss | -0.0733 | +| n_updates | 108120 | +| policy_gradient_loss | -0.0723 | +| value_loss | 0.000606 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.62e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 309 | +| iterations | 4761 | +| time_elapsed | 15735 | +| total_timesteps | 4875264 | +| train/ | | +| approx_kl | 2.0531363 | +| clip_fraction | 0.516 | +| clip_range | 0.2 | +| entropy_loss | -0.56 | +| explained_variance | -4.18 | +| learning_rate | 0.0001 | +| loss | -0.0971 | +| n_updates | 108130 | +| policy_gradient_loss | -0.0722 | +| value_loss | 0.000213 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.62e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 309 | +| iterations | 4762 | +| time_elapsed | 15738 | +| total_timesteps | 4876288 | +| train/ | | +| approx_kl | 1.8141874 | +| clip_fraction | 0.519 | +| clip_range | 0.2 | +| entropy_loss | -0.486 | +| explained_variance | -1.85 | +| learning_rate | 0.0001 | +| loss | -0.1 | +| n_updates | 108140 | +| policy_gradient_loss | -0.0735 | +| value_loss | 0.00029 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.62e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 309 | +| iterations | 4763 | +| time_elapsed | 15741 | +| total_timesteps | 4877312 | +| train/ | | +| approx_kl | 2.0923767 | +| clip_fraction | 0.544 | +| clip_range | 0.2 | +| entropy_loss | -0.534 | +| explained_variance | -2.68 | +| learning_rate | 0.0001 | +| loss | -0.0715 | +| n_updates | 108150 | +| policy_gradient_loss | -0.0617 | +| value_loss | 0.000188 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.63e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 309 | +| iterations | 4764 | +| time_elapsed | 15745 | +| total_timesteps | 4878336 | +| train/ | | +| approx_kl | 2.7296438 | +| clip_fraction | 0.523 | +| clip_range | 0.2 | +| entropy_loss | -0.523 | +| explained_variance | -2.69 | +| learning_rate | 0.0001 | +| loss | -0.0952 | +| n_updates | 108160 | +| policy_gradient_loss | -0.0757 | +| value_loss | 0.000146 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.63e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 309 | +| iterations | 4765 | +| time_elapsed | 15748 | +| total_timesteps | 4879360 | +| train/ | | +| approx_kl | 1.8581289 | +| clip_fraction | 0.52 | +| clip_range | 0.2 | +| entropy_loss | -0.501 | +| explained_variance | -1.1 | +| learning_rate | 0.0001 | +| loss | -0.0834 | +| n_updates | 108170 | +| policy_gradient_loss | -0.062 | +| value_loss | 0.000281 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.64e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 309 | +| iterations | 4766 | +| time_elapsed | 15751 | +| total_timesteps | 4880384 | +| train/ | | +| approx_kl | 1.612606 | +| clip_fraction | 0.51 | +| clip_range | 0.2 | +| entropy_loss | -0.557 | +| explained_variance | -3.86 | +| learning_rate | 0.0001 | +| loss | -0.0906 | +| n_updates | 108180 | +| policy_gradient_loss | -0.0717 | +| value_loss | 0.000323 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.64e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 309 | +| iterations | 4767 | +| time_elapsed | 15754 | +| total_timesteps | 4881408 | +| train/ | | +| approx_kl | 2.1104794 | +| clip_fraction | 0.509 | +| clip_range | 0.2 | +| entropy_loss | -0.498 | +| explained_variance | -1.77 | +| learning_rate | 0.0001 | +| loss | -0.105 | +| n_updates | 108190 | +| policy_gradient_loss | -0.0731 | +| value_loss | 0.000547 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.64e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 309 | +| iterations | 4768 | +| time_elapsed | 15757 | +| total_timesteps | 4882432 | +| train/ | | +| approx_kl | 1.4390926 | +| clip_fraction | 0.52 | +| clip_range | 0.2 | +| entropy_loss | -0.486 | +| explained_variance | -1.15 | +| learning_rate | 0.0001 | +| loss | -0.11 | +| n_updates | 108200 | +| policy_gradient_loss | -0.0753 | +| value_loss | 0.000325 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.64e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 309 | +| iterations | 4769 | +| time_elapsed | 15761 | +| total_timesteps | 4883456 | +| train/ | | +| approx_kl | 1.8723106 | +| clip_fraction | 0.478 | +| clip_range | 0.2 | +| entropy_loss | -0.395 | +| explained_variance | -1.31 | +| learning_rate | 0.0001 | +| loss | -0.0913 | +| n_updates | 108210 | +| policy_gradient_loss | -0.0705 | +| value_loss | 0.000378 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.65e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 309 | +| iterations | 4770 | +| time_elapsed | 15764 | +| total_timesteps | 4884480 | +| train/ | | +| approx_kl | 2.3357792 | +| clip_fraction | 0.539 | +| clip_range | 0.2 | +| entropy_loss | -0.504 | +| explained_variance | -0.409 | +| learning_rate | 0.0001 | +| loss | -0.0854 | +| n_updates | 108220 | +| policy_gradient_loss | -0.0678 | +| value_loss | 0.000702 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.65e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 309 | +| iterations | 4771 | +| time_elapsed | 15768 | +| total_timesteps | 4885504 | +| train/ | | +| approx_kl | 2.0309005 | +| clip_fraction | 0.552 | +| clip_range | 0.2 | +| entropy_loss | -0.489 | +| explained_variance | -1.14 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 108230 | +| policy_gradient_loss | -0.0756 | +| value_loss | 0.000639 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 309 | +| iterations | 4772 | +| time_elapsed | 15771 | +| total_timesteps | 4886528 | +| train/ | | +| approx_kl | 1.844674 | +| clip_fraction | 0.536 | +| clip_range | 0.2 | +| entropy_loss | -0.506 | +| explained_variance | -1.62 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 108240 | +| policy_gradient_loss | -0.0775 | +| value_loss | 0.000518 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 309 | +| iterations | 4773 | +| time_elapsed | 15774 | +| total_timesteps | 4887552 | +| train/ | | +| approx_kl | 1.6902053 | +| clip_fraction | 0.495 | +| clip_range | 0.2 | +| entropy_loss | -0.53 | +| explained_variance | -0.981 | +| learning_rate | 0.0001 | +| loss | -0.0909 | +| n_updates | 108250 | +| policy_gradient_loss | -0.0689 | +| value_loss | 0.000383 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 309 | +| iterations | 4774 | +| time_elapsed | 15778 | +| total_timesteps | 4888576 | +| train/ | | +| approx_kl | 2.2837057 | +| clip_fraction | 0.501 | +| clip_range | 0.2 | +| entropy_loss | -0.428 | +| explained_variance | -3.23 | +| learning_rate | 0.0001 | +| loss | 0.0272 | +| n_updates | 108260 | +| policy_gradient_loss | -0.0702 | +| value_loss | 0.000383 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 309 | +| iterations | 4775 | +| time_elapsed | 15781 | +| total_timesteps | 4889600 | +| train/ | | +| approx_kl | 1.4899484 | +| clip_fraction | 0.554 | +| clip_range | 0.2 | +| entropy_loss | -0.574 | +| explained_variance | -2.2 | +| learning_rate | 0.0001 | +| loss | -0.0742 | +| n_updates | 108270 | +| policy_gradient_loss | -0.0783 | +| value_loss | 0.000326 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 309 | +| iterations | 4776 | +| time_elapsed | 15785 | +| total_timesteps | 4890624 | +| train/ | | +| approx_kl | 1.7576897 | +| clip_fraction | 0.527 | +| clip_range | 0.2 | +| entropy_loss | -0.532 | +| explained_variance | -1.77 | +| learning_rate | 0.0001 | +| loss | -0.0839 | +| n_updates | 108280 | +| policy_gradient_loss | -0.0693 | +| value_loss | 0.000367 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 309 | +| iterations | 4777 | +| time_elapsed | 15788 | +| total_timesteps | 4891648 | +| train/ | | +| approx_kl | 1.7985196 | +| clip_fraction | 0.554 | +| clip_range | 0.2 | +| entropy_loss | -0.488 | +| explained_variance | -0.164 | +| learning_rate | 0.0001 | +| loss | -0.119 | +| n_updates | 108290 | +| policy_gradient_loss | -0.0662 | +| value_loss | 0.00058 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 309 | +| iterations | 4778 | +| time_elapsed | 15791 | +| total_timesteps | 4892672 | +| train/ | | +| approx_kl | 1.5681598 | +| clip_fraction | 0.507 | +| clip_range | 0.2 | +| entropy_loss | -0.446 | +| explained_variance | -1.28 | +| learning_rate | 0.0001 | +| loss | -0.0912 | +| n_updates | 108300 | +| policy_gradient_loss | -0.0761 | +| value_loss | 0.00081 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 309 | +| iterations | 4779 | +| time_elapsed | 15794 | +| total_timesteps | 4893696 | +| train/ | | +| approx_kl | 2.1690264 | +| clip_fraction | 0.502 | +| clip_range | 0.2 | +| entropy_loss | -0.448 | +| explained_variance | -2.67 | +| learning_rate | 0.0001 | +| loss | -0.106 | +| n_updates | 108310 | +| policy_gradient_loss | -0.069 | +| value_loss | 0.000341 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 309 | +| iterations | 4780 | +| time_elapsed | 15798 | +| total_timesteps | 4894720 | +| train/ | | +| approx_kl | 2.0298338 | +| clip_fraction | 0.533 | +| clip_range | 0.2 | +| entropy_loss | -0.474 | +| explained_variance | -0.765 | +| learning_rate | 0.0001 | +| loss | -0.0596 | +| n_updates | 108320 | +| policy_gradient_loss | -0.0632 | +| value_loss | 0.000402 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 309 | +| iterations | 4781 | +| time_elapsed | 15801 | +| total_timesteps | 4895744 | +| train/ | | +| approx_kl | 1.6961441 | +| clip_fraction | 0.505 | +| clip_range | 0.2 | +| entropy_loss | -0.456 | +| explained_variance | -2.07 | +| learning_rate | 0.0001 | +| loss | -0.112 | +| n_updates | 108330 | +| policy_gradient_loss | -0.0684 | +| value_loss | 0.000489 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 309 | +| iterations | 4782 | +| time_elapsed | 15804 | +| total_timesteps | 4896768 | +| train/ | | +| approx_kl | 1.9042037 | +| clip_fraction | 0.484 | +| clip_range | 0.2 | +| entropy_loss | -0.444 | +| explained_variance | -0.978 | +| learning_rate | 0.0001 | +| loss | -0.017 | +| n_updates | 108340 | +| policy_gradient_loss | -0.0561 | +| value_loss | 0.000335 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 309 | +| iterations | 4783 | +| time_elapsed | 15807 | +| total_timesteps | 4897792 | +| train/ | | +| approx_kl | 2.2506413 | +| clip_fraction | 0.498 | +| clip_range | 0.2 | +| entropy_loss | -0.513 | +| explained_variance | -0.652 | +| learning_rate | 0.0001 | +| loss | -0.0703 | +| n_updates | 108350 | +| policy_gradient_loss | -0.0731 | +| value_loss | 0.000291 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 309 | +| iterations | 4784 | +| time_elapsed | 15810 | +| total_timesteps | 4898816 | +| train/ | | +| approx_kl | 2.1278687 | +| clip_fraction | 0.514 | +| clip_range | 0.2 | +| entropy_loss | -0.488 | +| explained_variance | -1.49 | +| learning_rate | 0.0001 | +| loss | -0.0915 | +| n_updates | 108360 | +| policy_gradient_loss | -0.0699 | +| value_loss | 0.00026 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 309 | +| iterations | 4785 | +| time_elapsed | 15814 | +| total_timesteps | 4899840 | +| train/ | | +| approx_kl | 2.1658702 | +| clip_fraction | 0.519 | +| clip_range | 0.2 | +| entropy_loss | -0.53 | +| explained_variance | -0.976 | +| learning_rate | 0.0001 | +| loss | -0.099 | +| n_updates | 108370 | +| policy_gradient_loss | -0.0756 | +| value_loss | 0.000225 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 309 | +| iterations | 4786 | +| time_elapsed | 15817 | +| total_timesteps | 4900864 | +| train/ | | +| approx_kl | 1.8126209 | +| clip_fraction | 0.504 | +| clip_range | 0.2 | +| entropy_loss | -0.423 | +| explained_variance | -0.874 | +| learning_rate | 0.0001 | +| loss | -0.0657 | +| n_updates | 108380 | +| policy_gradient_loss | -0.0655 | +| value_loss | 0.000494 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 309 | +| iterations | 4787 | +| time_elapsed | 15820 | +| total_timesteps | 4901888 | +| train/ | | +| approx_kl | 2.1127195 | +| clip_fraction | 0.533 | +| clip_range | 0.2 | +| entropy_loss | -0.507 | +| explained_variance | -1.1 | +| learning_rate | 0.0001 | +| loss | -0.0925 | +| n_updates | 108390 | +| policy_gradient_loss | -0.0754 | +| value_loss | 0.00045 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 309 | +| iterations | 4788 | +| time_elapsed | 15823 | +| total_timesteps | 4902912 | +| train/ | | +| approx_kl | 1.274996 | +| clip_fraction | 0.505 | +| clip_range | 0.2 | +| entropy_loss | -0.546 | +| explained_variance | -0.54 | +| learning_rate | 0.0001 | +| loss | -0.0789 | +| n_updates | 108400 | +| policy_gradient_loss | -0.0678 | +| value_loss | 0.000309 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 309 | +| iterations | 4789 | +| time_elapsed | 15827 | +| total_timesteps | 4903936 | +| train/ | | +| approx_kl | 1.5998602 | +| clip_fraction | 0.519 | +| clip_range | 0.2 | +| entropy_loss | -0.499 | +| explained_variance | -0.794 | +| learning_rate | 0.0001 | +| loss | -0.0525 | +| n_updates | 108410 | +| policy_gradient_loss | -0.068 | +| value_loss | 0.000332 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 309 | +| iterations | 4790 | +| time_elapsed | 15830 | +| total_timesteps | 4904960 | +| train/ | | +| approx_kl | 1.9302404 | +| clip_fraction | 0.49 | +| clip_range | 0.2 | +| entropy_loss | -0.433 | +| explained_variance | -2.01 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 108420 | +| policy_gradient_loss | -0.0704 | +| value_loss | 0.000456 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 309 | +| iterations | 4791 | +| time_elapsed | 15834 | +| total_timesteps | 4905984 | +| train/ | | +| approx_kl | 1.7697728 | +| clip_fraction | 0.506 | +| clip_range | 0.2 | +| entropy_loss | -0.479 | +| explained_variance | -0.969 | +| learning_rate | 0.0001 | +| loss | -0.0837 | +| n_updates | 108430 | +| policy_gradient_loss | -0.0683 | +| value_loss | 0.000615 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 309 | +| iterations | 4792 | +| time_elapsed | 15837 | +| total_timesteps | 4907008 | +| train/ | | +| approx_kl | 1.2106998 | +| clip_fraction | 0.519 | +| clip_range | 0.2 | +| entropy_loss | -0.533 | +| explained_variance | -1.24 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 108440 | +| policy_gradient_loss | -0.0702 | +| value_loss | 0.000356 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 309 | +| iterations | 4793 | +| time_elapsed | 15841 | +| total_timesteps | 4908032 | +| train/ | | +| approx_kl | 1.1944447 | +| clip_fraction | 0.477 | +| clip_range | 0.2 | +| entropy_loss | -0.486 | +| explained_variance | -1.96 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 108450 | +| policy_gradient_loss | -0.0681 | +| value_loss | 0.000448 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 309 | +| iterations | 4794 | +| time_elapsed | 15844 | +| total_timesteps | 4909056 | +| train/ | | +| approx_kl | 1.7884533 | +| clip_fraction | 0.522 | +| clip_range | 0.2 | +| entropy_loss | -0.489 | +| explained_variance | -2.04 | +| learning_rate | 0.0001 | +| loss | -0.0895 | +| n_updates | 108460 | +| policy_gradient_loss | -0.0709 | +| value_loss | 0.000235 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 309 | +| iterations | 4795 | +| time_elapsed | 15848 | +| total_timesteps | 4910080 | +| train/ | | +| approx_kl | 1.6202025 | +| clip_fraction | 0.53 | +| clip_range | 0.2 | +| entropy_loss | -0.513 | +| explained_variance | -1.3 | +| learning_rate | 0.0001 | +| loss | -0.0829 | +| n_updates | 108470 | +| policy_gradient_loss | -0.0703 | +| value_loss | 0.000369 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 309 | +| iterations | 4796 | +| time_elapsed | 15851 | +| total_timesteps | 4911104 | +| train/ | | +| approx_kl | 1.4559264 | +| clip_fraction | 0.547 | +| clip_range | 0.2 | +| entropy_loss | -0.617 | +| explained_variance | -3.87 | +| learning_rate | 0.0001 | +| loss | -0.0821 | +| n_updates | 108480 | +| policy_gradient_loss | -0.0782 | +| value_loss | 0.000283 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 309 | +| iterations | 4797 | +| time_elapsed | 15854 | +| total_timesteps | 4912128 | +| train/ | | +| approx_kl | 1.9991379 | +| clip_fraction | 0.543 | +| clip_range | 0.2 | +| entropy_loss | -0.487 | +| explained_variance | -1.19 | +| learning_rate | 0.0001 | +| loss | -0.115 | +| n_updates | 108490 | +| policy_gradient_loss | -0.0797 | +| value_loss | 0.000366 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 309 | +| iterations | 4798 | +| time_elapsed | 15858 | +| total_timesteps | 4913152 | +| train/ | | +| approx_kl | 1.8104008 | +| clip_fraction | 0.515 | +| clip_range | 0.2 | +| entropy_loss | -0.444 | +| explained_variance | -2.74 | +| learning_rate | 0.0001 | +| loss | -0.0862 | +| n_updates | 108500 | +| policy_gradient_loss | -0.0692 | +| value_loss | 0.000291 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 309 | +| iterations | 4799 | +| time_elapsed | 15861 | +| total_timesteps | 4914176 | +| train/ | | +| approx_kl | 2.0702624 | +| clip_fraction | 0.508 | +| clip_range | 0.2 | +| entropy_loss | -0.441 | +| explained_variance | -0.911 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 108510 | +| policy_gradient_loss | -0.0679 | +| value_loss | 0.000427 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 309 | +| iterations | 4800 | +| time_elapsed | 15864 | +| total_timesteps | 4915200 | +| train/ | | +| approx_kl | 1.5927734 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.457 | +| explained_variance | -3.31 | +| learning_rate | 0.0001 | +| loss | -0.0928 | +| n_updates | 108520 | +| policy_gradient_loss | -0.0705 | +| value_loss | 0.000299 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.78e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 309 | +| iterations | 4801 | +| time_elapsed | 15867 | +| total_timesteps | 4916224 | +| train/ | | +| approx_kl | 6.159995 | +| clip_fraction | 0.507 | +| clip_range | 0.2 | +| entropy_loss | -0.448 | +| explained_variance | -7.89 | +| learning_rate | 0.0001 | +| loss | -0.086 | +| n_updates | 108530 | +| policy_gradient_loss | -0.0756 | +| value_loss | 0.000228 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.78e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 309 | +| iterations | 4802 | +| time_elapsed | 15870 | +| total_timesteps | 4917248 | +| train/ | | +| approx_kl | 1.8957849 | +| clip_fraction | 0.498 | +| clip_range | 0.2 | +| entropy_loss | -0.446 | +| explained_variance | -1.17 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 108540 | +| policy_gradient_loss | -0.0644 | +| value_loss | 0.000363 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 309 | +| iterations | 4803 | +| time_elapsed | 15874 | +| total_timesteps | 4918272 | +| train/ | | +| approx_kl | 2.2274299 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.407 | +| explained_variance | -0.662 | +| learning_rate | 0.0001 | +| loss | -0.0747 | +| n_updates | 108550 | +| policy_gradient_loss | -0.0717 | +| value_loss | 0.000401 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 309 | +| iterations | 4804 | +| time_elapsed | 15877 | +| total_timesteps | 4919296 | +| train/ | | +| approx_kl | 1.2564344 | +| clip_fraction | 0.502 | +| clip_range | 0.2 | +| entropy_loss | -0.457 | +| explained_variance | -0.296 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 108560 | +| policy_gradient_loss | -0.0614 | +| value_loss | 0.000438 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 309 | +| iterations | 4805 | +| time_elapsed | 15880 | +| total_timesteps | 4920320 | +| train/ | | +| approx_kl | 2.02607 | +| clip_fraction | 0.513 | +| clip_range | 0.2 | +| entropy_loss | -0.486 | +| explained_variance | -1.53 | +| learning_rate | 0.0001 | +| loss | -0.0978 | +| n_updates | 108570 | +| policy_gradient_loss | -0.0723 | +| value_loss | 0.000467 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 309 | +| iterations | 4806 | +| time_elapsed | 15883 | +| total_timesteps | 4921344 | +| train/ | | +| approx_kl | 2.8838432 | +| clip_fraction | 0.46 | +| clip_range | 0.2 | +| entropy_loss | -0.404 | +| explained_variance | -3.68 | +| learning_rate | 0.0001 | +| loss | -0.0905 | +| n_updates | 108580 | +| policy_gradient_loss | -0.066 | +| value_loss | 0.000334 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.8e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 309 | +| iterations | 4807 | +| time_elapsed | 15887 | +| total_timesteps | 4922368 | +| train/ | | +| approx_kl | 1.6759293 | +| clip_fraction | 0.517 | +| clip_range | 0.2 | +| entropy_loss | -0.496 | +| explained_variance | -0.996 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 108590 | +| policy_gradient_loss | -0.0694 | +| value_loss | 0.000455 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.8e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 309 | +| iterations | 4808 | +| time_elapsed | 15890 | +| total_timesteps | 4923392 | +| train/ | | +| approx_kl | 1.5137618 | +| clip_fraction | 0.488 | +| clip_range | 0.2 | +| entropy_loss | -0.464 | +| explained_variance | -4.87 | +| learning_rate | 0.0001 | +| loss | -0.0584 | +| n_updates | 108600 | +| policy_gradient_loss | -0.0719 | +| value_loss | 0.000362 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.8e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 309 | +| iterations | 4809 | +| time_elapsed | 15894 | +| total_timesteps | 4924416 | +| train/ | | +| approx_kl | 1.4188306 | +| clip_fraction | 0.447 | +| clip_range | 0.2 | +| entropy_loss | -0.403 | +| explained_variance | -2.56 | +| learning_rate | 0.0001 | +| loss | -0.0749 | +| n_updates | 108610 | +| policy_gradient_loss | -0.0693 | +| value_loss | 0.00014 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.81e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 309 | +| iterations | 4810 | +| time_elapsed | 15897 | +| total_timesteps | 4925440 | +| train/ | | +| approx_kl | 1.1640213 | +| clip_fraction | 0.489 | +| clip_range | 0.2 | +| entropy_loss | -0.466 | +| explained_variance | -0.513 | +| learning_rate | 0.0001 | +| loss | -0.0867 | +| n_updates | 108620 | +| policy_gradient_loss | -0.0571 | +| value_loss | 0.000372 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.81e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 309 | +| iterations | 4811 | +| time_elapsed | 15900 | +| total_timesteps | 4926464 | +| train/ | | +| approx_kl | 2.4016964 | +| clip_fraction | 0.526 | +| clip_range | 0.2 | +| entropy_loss | -0.426 | +| explained_variance | -0.588 | +| learning_rate | 0.0001 | +| loss | -0.0969 | +| n_updates | 108630 | +| policy_gradient_loss | -0.0662 | +| value_loss | 0.000457 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.82e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 309 | +| iterations | 4812 | +| time_elapsed | 15904 | +| total_timesteps | 4927488 | +| train/ | | +| approx_kl | 1.796416 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.378 | +| explained_variance | -1.12 | +| learning_rate | 0.0001 | +| loss | -0.0753 | +| n_updates | 108640 | +| policy_gradient_loss | -0.0708 | +| value_loss | 0.000656 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.82e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 309 | +| iterations | 4813 | +| time_elapsed | 15907 | +| total_timesteps | 4928512 | +| train/ | | +| approx_kl | 2.3605695 | +| clip_fraction | 0.47 | +| clip_range | 0.2 | +| entropy_loss | -0.392 | +| explained_variance | -2.64 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 108650 | +| policy_gradient_loss | -0.0648 | +| value_loss | 0.00043 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.82e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 309 | +| iterations | 4814 | +| time_elapsed | 15910 | +| total_timesteps | 4929536 | +| train/ | | +| approx_kl | 1.8653497 | +| clip_fraction | 0.474 | +| clip_range | 0.2 | +| entropy_loss | -0.418 | +| explained_variance | -3.93 | +| learning_rate | 0.0001 | +| loss | -0.108 | +| n_updates | 108660 | +| policy_gradient_loss | -0.0705 | +| value_loss | 0.000257 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 309 | +| iterations | 4815 | +| time_elapsed | 15913 | +| total_timesteps | 4930560 | +| train/ | | +| approx_kl | 8.115897 | +| clip_fraction | 0.523 | +| clip_range | 0.2 | +| entropy_loss | -0.481 | +| explained_variance | -0.396 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 108670 | +| policy_gradient_loss | -0.0697 | +| value_loss | 0.000375 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 309 | +| iterations | 4816 | +| time_elapsed | 15916 | +| total_timesteps | 4931584 | +| train/ | | +| approx_kl | 1.3068342 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.444 | +| explained_variance | -0.75 | +| learning_rate | 0.0001 | +| loss | -0.0807 | +| n_updates | 108680 | +| policy_gradient_loss | -0.0633 | +| value_loss | 0.000516 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 309 | +| iterations | 4817 | +| time_elapsed | 15920 | +| total_timesteps | 4932608 | +| train/ | | +| approx_kl | 1.8325411 | +| clip_fraction | 0.519 | +| clip_range | 0.2 | +| entropy_loss | -0.463 | +| explained_variance | -2.26 | +| learning_rate | 0.0001 | +| loss | -0.107 | +| n_updates | 108690 | +| policy_gradient_loss | -0.0706 | +| value_loss | 0.000524 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 309 | +| iterations | 4818 | +| time_elapsed | 15923 | +| total_timesteps | 4933632 | +| train/ | | +| approx_kl | 1.5729198 | +| clip_fraction | 0.486 | +| clip_range | 0.2 | +| entropy_loss | -0.402 | +| explained_variance | -1.14 | +| learning_rate | 0.0001 | +| loss | -0.0752 | +| n_updates | 108700 | +| policy_gradient_loss | -0.0726 | +| value_loss | 0.000365 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 309 | +| iterations | 4819 | +| time_elapsed | 15926 | +| total_timesteps | 4934656 | +| train/ | | +| approx_kl | 2.0252995 | +| clip_fraction | 0.496 | +| clip_range | 0.2 | +| entropy_loss | -0.464 | +| explained_variance | -3.69 | +| learning_rate | 0.0001 | +| loss | -0.123 | +| n_updates | 108710 | +| policy_gradient_loss | -0.0658 | +| value_loss | 0.00015 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 309 | +| iterations | 4820 | +| time_elapsed | 15929 | +| total_timesteps | 4935680 | +| train/ | | +| approx_kl | 2.0118656 | +| clip_fraction | 0.495 | +| clip_range | 0.2 | +| entropy_loss | -0.442 | +| explained_variance | -0.816 | +| learning_rate | 0.0001 | +| loss | -0.107 | +| n_updates | 108720 | +| policy_gradient_loss | -0.0677 | +| value_loss | 0.000243 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 309 | +| iterations | 4821 | +| time_elapsed | 15932 | +| total_timesteps | 4936704 | +| train/ | | +| approx_kl | 1.7318193 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.43 | +| explained_variance | -1.38 | +| learning_rate | 0.0001 | +| loss | -0.0957 | +| n_updates | 108730 | +| policy_gradient_loss | -0.0697 | +| value_loss | 0.00034 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 309 | +| iterations | 4822 | +| time_elapsed | 15936 | +| total_timesteps | 4937728 | +| train/ | | +| approx_kl | 1.3983228 | +| clip_fraction | 0.499 | +| clip_range | 0.2 | +| entropy_loss | -0.484 | +| explained_variance | -0.67 | +| learning_rate | 0.0001 | +| loss | -0.0319 | +| n_updates | 108740 | +| policy_gradient_loss | -0.0657 | +| value_loss | 0.000553 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 309 | +| iterations | 4823 | +| time_elapsed | 15939 | +| total_timesteps | 4938752 | +| train/ | | +| approx_kl | 2.3489017 | +| clip_fraction | 0.493 | +| clip_range | 0.2 | +| entropy_loss | -0.398 | +| explained_variance | -4.64 | +| learning_rate | 0.0001 | +| loss | -0.106 | +| n_updates | 108750 | +| policy_gradient_loss | -0.059 | +| value_loss | 0.000467 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 309 | +| iterations | 4824 | +| time_elapsed | 15942 | +| total_timesteps | 4939776 | +| train/ | | +| approx_kl | 1.921143 | +| clip_fraction | 0.507 | +| clip_range | 0.2 | +| entropy_loss | -0.409 | +| explained_variance | -1.07 | +| learning_rate | 0.0001 | +| loss | -0.0991 | +| n_updates | 108760 | +| policy_gradient_loss | -0.0727 | +| value_loss | 0.000474 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 309 | +| iterations | 4825 | +| time_elapsed | 15946 | +| total_timesteps | 4940800 | +| train/ | | +| approx_kl | 2.1034966 | +| clip_fraction | 0.523 | +| clip_range | 0.2 | +| entropy_loss | -0.51 | +| explained_variance | -2.48 | +| learning_rate | 0.0001 | +| loss | -0.0982 | +| n_updates | 108770 | +| policy_gradient_loss | -0.0702 | +| value_loss | 0.000311 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 309 | +| iterations | 4826 | +| time_elapsed | 15949 | +| total_timesteps | 4941824 | +| train/ | | +| approx_kl | 2.0245335 | +| clip_fraction | 0.494 | +| clip_range | 0.2 | +| entropy_loss | -0.408 | +| explained_variance | -1.29 | +| learning_rate | 0.0001 | +| loss | -0.0797 | +| n_updates | 108780 | +| policy_gradient_loss | -0.0612 | +| value_loss | 0.000653 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 309 | +| iterations | 4827 | +| time_elapsed | 15953 | +| total_timesteps | 4942848 | +| train/ | | +| approx_kl | 2.6795177 | +| clip_fraction | 0.52 | +| clip_range | 0.2 | +| entropy_loss | -0.427 | +| explained_variance | -1.66 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 108790 | +| policy_gradient_loss | -0.0754 | +| value_loss | 0.000409 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.91e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 309 | +| iterations | 4828 | +| time_elapsed | 15956 | +| total_timesteps | 4943872 | +| train/ | | +| approx_kl | 1.6408694 | +| clip_fraction | 0.516 | +| clip_range | 0.2 | +| entropy_loss | -0.56 | +| explained_variance | -5.35 | +| learning_rate | 0.0001 | +| loss | -0.0916 | +| n_updates | 108800 | +| policy_gradient_loss | -0.0693 | +| value_loss | 0.000208 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.91e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 309 | +| iterations | 4829 | +| time_elapsed | 15959 | +| total_timesteps | 4944896 | +| train/ | | +| approx_kl | 1.6766157 | +| clip_fraction | 0.474 | +| clip_range | 0.2 | +| entropy_loss | -0.424 | +| explained_variance | -0.928 | +| learning_rate | 0.0001 | +| loss | -0.0916 | +| n_updates | 108810 | +| policy_gradient_loss | -0.0563 | +| value_loss | 0.000209 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.91e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 309 | +| iterations | 4830 | +| time_elapsed | 15963 | +| total_timesteps | 4945920 | +| train/ | | +| approx_kl | 2.7887986 | +| clip_fraction | 0.508 | +| clip_range | 0.2 | +| entropy_loss | -0.472 | +| explained_variance | -1.13 | +| learning_rate | 0.0001 | +| loss | -0.0858 | +| n_updates | 108820 | +| policy_gradient_loss | -0.0703 | +| value_loss | 0.000467 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.92e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 309 | +| iterations | 4831 | +| time_elapsed | 15967 | +| total_timesteps | 4946944 | +| train/ | | +| approx_kl | 1.9020437 | +| clip_fraction | 0.531 | +| clip_range | 0.2 | +| entropy_loss | -0.482 | +| explained_variance | -2.49 | +| learning_rate | 0.0001 | +| loss | -0.0977 | +| n_updates | 108830 | +| policy_gradient_loss | -0.0804 | +| value_loss | 0.000482 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.92e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 309 | +| iterations | 4832 | +| time_elapsed | 15970 | +| total_timesteps | 4947968 | +| train/ | | +| approx_kl | 2.0545201 | +| clip_fraction | 0.494 | +| clip_range | 0.2 | +| entropy_loss | -0.432 | +| explained_variance | -6 | +| learning_rate | 0.0001 | +| loss | -0.09 | +| n_updates | 108840 | +| policy_gradient_loss | -0.0698 | +| value_loss | 0.000287 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.92e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 309 | +| iterations | 4833 | +| time_elapsed | 15973 | +| total_timesteps | 4948992 | +| train/ | | +| approx_kl | 2.0794268 | +| clip_fraction | 0.53 | +| clip_range | 0.2 | +| entropy_loss | -0.47 | +| explained_variance | -0.845 | +| learning_rate | 0.0001 | +| loss | -0.108 | +| n_updates | 108850 | +| policy_gradient_loss | -0.0709 | +| value_loss | 0.000409 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.92e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 309 | +| iterations | 4834 | +| time_elapsed | 15976 | +| total_timesteps | 4950016 | +| train/ | | +| approx_kl | 2.2123227 | +| clip_fraction | 0.477 | +| clip_range | 0.2 | +| entropy_loss | -0.397 | +| explained_variance | -0.493 | +| learning_rate | 0.0001 | +| loss | -0.0672 | +| n_updates | 108860 | +| policy_gradient_loss | -0.0661 | +| value_loss | 0.000509 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.92e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 309 | +| iterations | 4835 | +| time_elapsed | 15979 | +| total_timesteps | 4951040 | +| train/ | | +| approx_kl | 2.5426006 | +| clip_fraction | 0.524 | +| clip_range | 0.2 | +| entropy_loss | -0.425 | +| explained_variance | -5.72 | +| learning_rate | 0.0001 | +| loss | -0.0736 | +| n_updates | 108870 | +| policy_gradient_loss | -0.0709 | +| value_loss | 0.000315 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.95e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 309 | +| iterations | 4836 | +| time_elapsed | 15983 | +| total_timesteps | 4952064 | +| train/ | | +| approx_kl | 2.3684273 | +| clip_fraction | 0.538 | +| clip_range | 0.2 | +| entropy_loss | -0.484 | +| explained_variance | -1.14 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 108880 | +| policy_gradient_loss | -0.0754 | +| value_loss | 0.000291 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.95e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 309 | +| iterations | 4837 | +| time_elapsed | 15986 | +| total_timesteps | 4953088 | +| train/ | | +| approx_kl | 2.1265287 | +| clip_fraction | 0.491 | +| clip_range | 0.2 | +| entropy_loss | -0.434 | +| explained_variance | -2.31 | +| learning_rate | 0.0001 | +| loss | -0.0462 | +| n_updates | 108890 | +| policy_gradient_loss | -0.0606 | +| value_loss | 0.000258 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.96e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 309 | +| iterations | 4838 | +| time_elapsed | 15989 | +| total_timesteps | 4954112 | +| train/ | | +| approx_kl | 2.0965028 | +| clip_fraction | 0.492 | +| clip_range | 0.2 | +| entropy_loss | -0.426 | +| explained_variance | -1.05 | +| learning_rate | 0.0001 | +| loss | -0.0673 | +| n_updates | 108900 | +| policy_gradient_loss | -0.067 | +| value_loss | 0.000499 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.95e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 309 | +| iterations | 4839 | +| time_elapsed | 15992 | +| total_timesteps | 4955136 | +| train/ | | +| approx_kl | 1.7560959 | +| clip_fraction | 0.501 | +| clip_range | 0.2 | +| entropy_loss | -0.424 | +| explained_variance | -1.08 | +| learning_rate | 0.0001 | +| loss | -0.0696 | +| n_updates | 108910 | +| policy_gradient_loss | -0.07 | +| value_loss | 0.000431 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.95e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 309 | +| iterations | 4840 | +| time_elapsed | 15995 | +| total_timesteps | 4956160 | +| train/ | | +| approx_kl | 1.8781701 | +| clip_fraction | 0.5 | +| clip_range | 0.2 | +| entropy_loss | -0.423 | +| explained_variance | -0.612 | +| learning_rate | 0.0001 | +| loss | -0.0801 | +| n_updates | 108920 | +| policy_gradient_loss | -0.0537 | +| value_loss | 0.000766 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.96e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 309 | +| iterations | 4841 | +| time_elapsed | 15998 | +| total_timesteps | 4957184 | +| train/ | | +| approx_kl | 1.9821305 | +| clip_fraction | 0.495 | +| clip_range | 0.2 | +| entropy_loss | -0.377 | +| explained_variance | -6.9 | +| learning_rate | 0.0001 | +| loss | -0.089 | +| n_updates | 108930 | +| policy_gradient_loss | -0.0751 | +| value_loss | 0.000375 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.96e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 309 | +| iterations | 4842 | +| time_elapsed | 16002 | +| total_timesteps | 4958208 | +| train/ | | +| approx_kl | 2.2449946 | +| clip_fraction | 0.5 | +| clip_range | 0.2 | +| entropy_loss | -0.405 | +| explained_variance | -2.68 | +| learning_rate | 0.0001 | +| loss | -0.0704 | +| n_updates | 108940 | +| policy_gradient_loss | -0.0742 | +| value_loss | 0.000433 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.96e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 309 | +| iterations | 4843 | +| time_elapsed | 16005 | +| total_timesteps | 4959232 | +| train/ | | +| approx_kl | 2.6076455 | +| clip_fraction | 0.506 | +| clip_range | 0.2 | +| entropy_loss | -0.483 | +| explained_variance | -2.68 | +| learning_rate | 0.0001 | +| loss | -0.0897 | +| n_updates | 108950 | +| policy_gradient_loss | -0.0743 | +| value_loss | 0.0002 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.96e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 309 | +| iterations | 4844 | +| time_elapsed | 16009 | +| total_timesteps | 4960256 | +| train/ | | +| approx_kl | 2.0417986 | +| clip_fraction | 0.508 | +| clip_range | 0.2 | +| entropy_loss | -0.421 | +| explained_variance | -0.806 | +| learning_rate | 0.0001 | +| loss | -0.0536 | +| n_updates | 108960 | +| policy_gradient_loss | -0.069 | +| value_loss | 0.000496 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.96e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 309 | +| iterations | 4845 | +| time_elapsed | 16012 | +| total_timesteps | 4961280 | +| train/ | | +| approx_kl | 1.5713551 | +| clip_fraction | 0.491 | +| clip_range | 0.2 | +| entropy_loss | -0.431 | +| explained_variance | -8.86 | +| learning_rate | 0.0001 | +| loss | -0.0949 | +| n_updates | 108970 | +| policy_gradient_loss | -0.0754 | +| value_loss | 0.000309 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.96e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 309 | +| iterations | 4846 | +| time_elapsed | 16015 | +| total_timesteps | 4962304 | +| train/ | | +| approx_kl | 2.079954 | +| clip_fraction | 0.552 | +| clip_range | 0.2 | +| entropy_loss | -0.546 | +| explained_variance | -7.96 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 108980 | +| policy_gradient_loss | -0.0627 | +| value_loss | 0.000164 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.96e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 309 | +| iterations | 4847 | +| time_elapsed | 16019 | +| total_timesteps | 4963328 | +| train/ | | +| approx_kl | 1.1521455 | +| clip_fraction | 0.473 | +| clip_range | 0.2 | +| entropy_loss | -0.649 | +| explained_variance | -0.0519 | +| learning_rate | 0.0001 | +| loss | 0.0276 | +| n_updates | 108990 | +| policy_gradient_loss | -0.0391 | +| value_loss | 0.000824 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.01e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 309 | +| iterations | 4848 | +| time_elapsed | 16022 | +| total_timesteps | 4964352 | +| train/ | | +| approx_kl | 1.6342747 | +| clip_fraction | 0.517 | +| clip_range | 0.2 | +| entropy_loss | -0.443 | +| explained_variance | -3.72 | +| learning_rate | 0.0001 | +| loss | -0.0875 | +| n_updates | 109000 | +| policy_gradient_loss | -0.0603 | +| value_loss | 0.000771 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.02e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 309 | +| iterations | 4849 | +| time_elapsed | 16026 | +| total_timesteps | 4965376 | +| train/ | | +| approx_kl | 1.8340156 | +| clip_fraction | 0.478 | +| clip_range | 0.2 | +| entropy_loss | -0.432 | +| explained_variance | -1.67 | +| learning_rate | 0.0001 | +| loss | -0.118 | +| n_updates | 109010 | +| policy_gradient_loss | -0.0706 | +| value_loss | 0.000374 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.02e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 309 | +| iterations | 4850 | +| time_elapsed | 16029 | +| total_timesteps | 4966400 | +| train/ | | +| approx_kl | 1.2155664 | +| clip_fraction | 0.523 | +| clip_range | 0.2 | +| entropy_loss | -0.533 | +| explained_variance | -1.2 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 109020 | +| policy_gradient_loss | -0.0745 | +| value_loss | 0.000324 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.02e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 309 | +| iterations | 4851 | +| time_elapsed | 16032 | +| total_timesteps | 4967424 | +| train/ | | +| approx_kl | 1.4926754 | +| clip_fraction | 0.473 | +| clip_range | 0.2 | +| entropy_loss | -0.401 | +| explained_variance | -0.921 | +| learning_rate | 0.0001 | +| loss | -0.0741 | +| n_updates | 109030 | +| policy_gradient_loss | -0.0679 | +| value_loss | 0.000496 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.02e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 309 | +| iterations | 4852 | +| time_elapsed | 16035 | +| total_timesteps | 4968448 | +| train/ | | +| approx_kl | 2.4638815 | +| clip_fraction | 0.507 | +| clip_range | 0.2 | +| entropy_loss | -0.421 | +| explained_variance | -1.73 | +| learning_rate | 0.0001 | +| loss | -0.106 | +| n_updates | 109040 | +| policy_gradient_loss | -0.0759 | +| value_loss | 0.000568 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.02e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 309 | +| iterations | 4853 | +| time_elapsed | 16038 | +| total_timesteps | 4969472 | +| train/ | | +| approx_kl | 48.548916 | +| clip_fraction | 0.469 | +| clip_range | 0.2 | +| entropy_loss | -0.372 | +| explained_variance | -0.896 | +| learning_rate | 0.0001 | +| loss | -0.0798 | +| n_updates | 109050 | +| policy_gradient_loss | -0.0669 | +| value_loss | 0.000892 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.02e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 309 | +| iterations | 4854 | +| time_elapsed | 16042 | +| total_timesteps | 4970496 | +| train/ | | +| approx_kl | 1.7426639 | +| clip_fraction | 0.462 | +| clip_range | 0.2 | +| entropy_loss | -0.41 | +| explained_variance | -1.45 | +| learning_rate | 0.0001 | +| loss | -0.0961 | +| n_updates | 109060 | +| policy_gradient_loss | -0.0661 | +| value_loss | 0.000713 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.02e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 309 | +| iterations | 4855 | +| time_elapsed | 16045 | +| total_timesteps | 4971520 | +| train/ | | +| approx_kl | 1.726435 | +| clip_fraction | 0.489 | +| clip_range | 0.2 | +| entropy_loss | -0.474 | +| explained_variance | -1.19 | +| learning_rate | 0.0001 | +| loss | -0.0897 | +| n_updates | 109070 | +| policy_gradient_loss | -0.0662 | +| value_loss | 0.00049 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.02e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 309 | +| iterations | 4856 | +| time_elapsed | 16048 | +| total_timesteps | 4972544 | +| train/ | | +| approx_kl | 1.9651296 | +| clip_fraction | 0.514 | +| clip_range | 0.2 | +| entropy_loss | -0.463 | +| explained_variance | -1.4 | +| learning_rate | 0.0001 | +| loss | -0.087 | +| n_updates | 109080 | +| policy_gradient_loss | -0.0774 | +| value_loss | 0.000406 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.02e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 309 | +| iterations | 4857 | +| time_elapsed | 16051 | +| total_timesteps | 4973568 | +| train/ | | +| approx_kl | 2.0100305 | +| clip_fraction | 0.489 | +| clip_range | 0.2 | +| entropy_loss | -0.419 | +| explained_variance | -1.75 | +| learning_rate | 0.0001 | +| loss | -0.0876 | +| n_updates | 109090 | +| policy_gradient_loss | -0.051 | +| value_loss | 0.000387 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.04e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 309 | +| iterations | 4858 | +| time_elapsed | 16054 | +| total_timesteps | 4974592 | +| train/ | | +| approx_kl | 1.6804047 | +| clip_fraction | 0.512 | +| clip_range | 0.2 | +| entropy_loss | -0.454 | +| explained_variance | -5.9 | +| learning_rate | 0.0001 | +| loss | -0.107 | +| n_updates | 109100 | +| policy_gradient_loss | -0.0713 | +| value_loss | 0.00022 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.04e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 309 | +| iterations | 4859 | +| time_elapsed | 16057 | +| total_timesteps | 4975616 | +| train/ | | +| approx_kl | 1.7751824 | +| clip_fraction | 0.516 | +| clip_range | 0.2 | +| entropy_loss | -0.424 | +| explained_variance | -1.12 | +| learning_rate | 0.0001 | +| loss | -0.0712 | +| n_updates | 109110 | +| policy_gradient_loss | -0.0638 | +| value_loss | 0.000338 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.04e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 309 | +| iterations | 4860 | +| time_elapsed | 16061 | +| total_timesteps | 4976640 | +| train/ | | +| approx_kl | 1.4236621 | +| clip_fraction | 0.478 | +| clip_range | 0.2 | +| entropy_loss | -0.471 | +| explained_variance | -0.184 | +| learning_rate | 0.0001 | +| loss | -0.0988 | +| n_updates | 109120 | +| policy_gradient_loss | -0.0582 | +| value_loss | 0.000337 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.04e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 309 | +| iterations | 4861 | +| time_elapsed | 16064 | +| total_timesteps | 4977664 | +| train/ | | +| approx_kl | 2.6653526 | +| clip_fraction | 0.501 | +| clip_range | 0.2 | +| entropy_loss | -0.404 | +| explained_variance | -0.915 | +| learning_rate | 0.0001 | +| loss | -0.092 | +| n_updates | 109130 | +| policy_gradient_loss | -0.0688 | +| value_loss | 0.000548 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.05e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 309 | +| iterations | 4862 | +| time_elapsed | 16068 | +| total_timesteps | 4978688 | +| train/ | | +| approx_kl | 2.2099082 | +| clip_fraction | 0.513 | +| clip_range | 0.2 | +| entropy_loss | -0.427 | +| explained_variance | -5.51 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 109140 | +| policy_gradient_loss | -0.0754 | +| value_loss | 0.000309 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.05e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 309 | +| iterations | 4863 | +| time_elapsed | 16071 | +| total_timesteps | 4979712 | +| train/ | | +| approx_kl | 2.0018215 | +| clip_fraction | 0.492 | +| clip_range | 0.2 | +| entropy_loss | -0.417 | +| explained_variance | -1.86 | +| learning_rate | 0.0001 | +| loss | -0.0766 | +| n_updates | 109150 | +| policy_gradient_loss | -0.0701 | +| value_loss | 0.000238 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.05e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 309 | +| iterations | 4864 | +| time_elapsed | 16074 | +| total_timesteps | 4980736 | +| train/ | | +| approx_kl | 80.469955 | +| clip_fraction | 0.516 | +| clip_range | 0.2 | +| entropy_loss | -0.43 | +| explained_variance | -6.71 | +| learning_rate | 0.0001 | +| loss | -0.0766 | +| n_updates | 109160 | +| policy_gradient_loss | -0.0741 | +| value_loss | 0.00027 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.05e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 309 | +| iterations | 4865 | +| time_elapsed | 16078 | +| total_timesteps | 4981760 | +| train/ | | +| approx_kl | 1.6605406 | +| clip_fraction | 0.49 | +| clip_range | 0.2 | +| entropy_loss | -0.419 | +| explained_variance | -2.27 | +| learning_rate | 0.0001 | +| loss | -0.106 | +| n_updates | 109170 | +| policy_gradient_loss | -0.0729 | +| value_loss | 0.00056 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.05e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 309 | +| iterations | 4866 | +| time_elapsed | 16081 | +| total_timesteps | 4982784 | +| train/ | | +| approx_kl | 1.7916722 | +| clip_fraction | 0.457 | +| clip_range | 0.2 | +| entropy_loss | -0.424 | +| explained_variance | -1.73 | +| learning_rate | 0.0001 | +| loss | -0.0772 | +| n_updates | 109180 | +| policy_gradient_loss | -0.0649 | +| value_loss | 0.000276 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.07e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 309 | +| iterations | 4867 | +| time_elapsed | 16085 | +| total_timesteps | 4983808 | +| train/ | | +| approx_kl | 1.7850876 | +| clip_fraction | 0.518 | +| clip_range | 0.2 | +| entropy_loss | -0.457 | +| explained_variance | -4.64 | +| learning_rate | 0.0001 | +| loss | -0.105 | +| n_updates | 109190 | +| policy_gradient_loss | -0.0766 | +| value_loss | 0.000177 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.07e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 309 | +| iterations | 4868 | +| time_elapsed | 16088 | +| total_timesteps | 4984832 | +| train/ | | +| approx_kl | 2.417552 | +| clip_fraction | 0.528 | +| clip_range | 0.2 | +| entropy_loss | -0.444 | +| explained_variance | -0.289 | +| learning_rate | 0.0001 | +| loss | -0.0923 | +| n_updates | 109200 | +| policy_gradient_loss | -0.0655 | +| value_loss | 0.000264 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.07e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 309 | +| iterations | 4869 | +| time_elapsed | 16091 | +| total_timesteps | 4985856 | +| train/ | | +| approx_kl | 2.0180025 | +| clip_fraction | 0.484 | +| clip_range | 0.2 | +| entropy_loss | -0.4 | +| explained_variance | -1.61 | +| learning_rate | 0.0001 | +| loss | -0.0992 | +| n_updates | 109210 | +| policy_gradient_loss | -0.0719 | +| value_loss | 0.000549 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.07e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 309 | +| iterations | 4870 | +| time_elapsed | 16094 | +| total_timesteps | 4986880 | +| train/ | | +| approx_kl | 1.6743888 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.433 | +| explained_variance | -2.17 | +| learning_rate | 0.0001 | +| loss | -0.0961 | +| n_updates | 109220 | +| policy_gradient_loss | -0.0724 | +| value_loss | 0.000294 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.09e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 309 | +| iterations | 4871 | +| time_elapsed | 16098 | +| total_timesteps | 4987904 | +| train/ | | +| approx_kl | 1.8262582 | +| clip_fraction | 0.489 | +| clip_range | 0.2 | +| entropy_loss | -0.4 | +| explained_variance | -0.645 | +| learning_rate | 0.0001 | +| loss | -0.0771 | +| n_updates | 109230 | +| policy_gradient_loss | -0.0632 | +| value_loss | 0.000271 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.09e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 309 | +| iterations | 4872 | +| time_elapsed | 16101 | +| total_timesteps | 4988928 | +| train/ | | +| approx_kl | 1.4148153 | +| clip_fraction | 0.497 | +| clip_range | 0.2 | +| entropy_loss | -0.539 | +| explained_variance | -5.58 | +| learning_rate | 0.0001 | +| loss | -0.0903 | +| n_updates | 109240 | +| policy_gradient_loss | -0.0674 | +| value_loss | 0.00018 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.09e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 309 | +| iterations | 4873 | +| time_elapsed | 16104 | +| total_timesteps | 4989952 | +| train/ | | +| approx_kl | 1.8298395 | +| clip_fraction | 0.488 | +| clip_range | 0.2 | +| entropy_loss | -0.43 | +| explained_variance | -0.58 | +| learning_rate | 0.0001 | +| loss | -0.0659 | +| n_updates | 109250 | +| policy_gradient_loss | -0.0595 | +| value_loss | 0.000481 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.1e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 309 | +| iterations | 4874 | +| time_elapsed | 16107 | +| total_timesteps | 4990976 | +| train/ | | +| approx_kl | 1.6903088 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.427 | +| explained_variance | -2.47 | +| learning_rate | 0.0001 | +| loss | -0.085 | +| n_updates | 109260 | +| policy_gradient_loss | -0.0675 | +| value_loss | 0.000499 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.1e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 309 | +| iterations | 4875 | +| time_elapsed | 16110 | +| total_timesteps | 4992000 | +| train/ | | +| approx_kl | 7.980363 | +| clip_fraction | 0.532 | +| clip_range | 0.2 | +| entropy_loss | -0.481 | +| explained_variance | -1.03 | +| learning_rate | 0.0001 | +| loss | -0.109 | +| n_updates | 109270 | +| policy_gradient_loss | -0.0643 | +| value_loss | 0.000503 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.1e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 309 | +| iterations | 4876 | +| time_elapsed | 16114 | +| total_timesteps | 4993024 | +| train/ | | +| approx_kl | 3.8079472 | +| clip_fraction | 0.497 | +| clip_range | 0.2 | +| entropy_loss | -0.41 | +| explained_variance | -0.357 | +| learning_rate | 0.0001 | +| loss | -0.108 | +| n_updates | 109280 | +| policy_gradient_loss | -0.0649 | +| value_loss | 0.001 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.1e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 309 | +| iterations | 4877 | +| time_elapsed | 16117 | +| total_timesteps | 4994048 | +| train/ | | +| approx_kl | 1.9894652 | +| clip_fraction | 0.474 | +| clip_range | 0.2 | +| entropy_loss | -0.371 | +| explained_variance | -4.66 | +| learning_rate | 0.0001 | +| loss | -0.0645 | +| n_updates | 109290 | +| policy_gradient_loss | -0.07 | +| value_loss | 0.000776 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.1e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 309 | +| iterations | 4878 | +| time_elapsed | 16120 | +| total_timesteps | 4995072 | +| train/ | | +| approx_kl | 1.7756643 | +| clip_fraction | 0.514 | +| clip_range | 0.2 | +| entropy_loss | -0.456 | +| explained_variance | -2.77 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 109300 | +| policy_gradient_loss | -0.0729 | +| value_loss | 0.000301 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.1e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 309 | +| iterations | 4879 | +| time_elapsed | 16124 | +| total_timesteps | 4996096 | +| train/ | | +| approx_kl | 1.5110929 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.433 | +| explained_variance | -5.96 | +| learning_rate | 0.0001 | +| loss | -0.071 | +| n_updates | 109310 | +| policy_gradient_loss | -0.0639 | +| value_loss | 0.000221 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.1e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 309 | +| iterations | 4880 | +| time_elapsed | 16127 | +| total_timesteps | 4997120 | +| train/ | | +| approx_kl | 14.86447 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.427 | +| explained_variance | -0.794 | +| learning_rate | 0.0001 | +| loss | -0.111 | +| n_updates | 109320 | +| policy_gradient_loss | -0.0646 | +| value_loss | 0.000396 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.11e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 309 | +| iterations | 4881 | +| time_elapsed | 16130 | +| total_timesteps | 4998144 | +| train/ | | +| approx_kl | 1.7896445 | +| clip_fraction | 0.49 | +| clip_range | 0.2 | +| entropy_loss | -0.408 | +| explained_variance | -2.96 | +| learning_rate | 0.0001 | +| loss | -0.112 | +| n_updates | 109330 | +| policy_gradient_loss | -0.0713 | +| value_loss | 0.000421 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.11e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 309 | +| iterations | 4882 | +| time_elapsed | 16134 | +| total_timesteps | 4999168 | +| train/ | | +| approx_kl | 2.063311 | +| clip_fraction | 0.492 | +| clip_range | 0.2 | +| entropy_loss | -0.416 | +| explained_variance | -1.59 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 109340 | +| policy_gradient_loss | -0.0696 | +| value_loss | 0.000388 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.12e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 309 | +| iterations | 4883 | +| time_elapsed | 16137 | +| total_timesteps | 5000192 | +| train/ | | +| approx_kl | 2.3240366 | +| clip_fraction | 0.499 | +| clip_range | 0.2 | +| entropy_loss | -0.408 | +| explained_variance | -1.96 | +| learning_rate | 0.0001 | +| loss | -0.107 | +| n_updates | 109350 | +| policy_gradient_loss | -0.0714 | +| value_loss | 0.000427 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.12e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 309 | +| iterations | 4884 | +| time_elapsed | 16141 | +| total_timesteps | 5001216 | +| train/ | | +| approx_kl | 1.5746822 | +| clip_fraction | 0.519 | +| clip_range | 0.2 | +| entropy_loss | -0.442 | +| explained_variance | -1.27 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 109360 | +| policy_gradient_loss | -0.0699 | +| value_loss | 0.0003 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.12e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 309 | +| iterations | 4885 | +| time_elapsed | 16144 | +| total_timesteps | 5002240 | +| train/ | | +| approx_kl | 1.7774248 | +| clip_fraction | 0.498 | +| clip_range | 0.2 | +| entropy_loss | -0.416 | +| explained_variance | -1.16 | +| learning_rate | 0.0001 | +| loss | -0.107 | +| n_updates | 109370 | +| policy_gradient_loss | -0.0649 | +| value_loss | 0.000583 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.13e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 309 | +| iterations | 4886 | +| time_elapsed | 16148 | +| total_timesteps | 5003264 | +| train/ | | +| approx_kl | 1.2188253 | +| clip_fraction | 0.497 | +| clip_range | 0.2 | +| entropy_loss | -0.506 | +| explained_variance | -1.92 | +| learning_rate | 0.0001 | +| loss | -0.0887 | +| n_updates | 109380 | +| policy_gradient_loss | -0.0664 | +| value_loss | 0.000223 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.13e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 309 | +| iterations | 4887 | +| time_elapsed | 16151 | +| total_timesteps | 5004288 | +| train/ | | +| approx_kl | 1.6354587 | +| clip_fraction | 0.464 | +| clip_range | 0.2 | +| entropy_loss | -0.385 | +| explained_variance | -5.89 | +| learning_rate | 0.0001 | +| loss | -0.0913 | +| n_updates | 109390 | +| policy_gradient_loss | -0.0686 | +| value_loss | 0.000151 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.15e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 309 | +| iterations | 4888 | +| time_elapsed | 16154 | +| total_timesteps | 5005312 | +| train/ | | +| approx_kl | 1.627461 | +| clip_fraction | 0.482 | +| clip_range | 0.2 | +| entropy_loss | -0.396 | +| explained_variance | -2.14 | +| learning_rate | 0.0001 | +| loss | -0.0954 | +| n_updates | 109400 | +| policy_gradient_loss | -0.0671 | +| value_loss | 0.000331 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.15e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 309 | +| iterations | 4889 | +| time_elapsed | 16157 | +| total_timesteps | 5006336 | +| train/ | | +| approx_kl | 1.4551473 | +| clip_fraction | 0.488 | +| clip_range | 0.2 | +| entropy_loss | -0.438 | +| explained_variance | -1 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 109410 | +| policy_gradient_loss | -0.0697 | +| value_loss | 0.000486 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.15e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 309 | +| iterations | 4890 | +| time_elapsed | 16160 | +| total_timesteps | 5007360 | +| train/ | | +| approx_kl | 1.3371756 | +| clip_fraction | 0.486 | +| clip_range | 0.2 | +| entropy_loss | -0.387 | +| explained_variance | -4.32 | +| learning_rate | 0.0001 | +| loss | -0.0966 | +| n_updates | 109420 | +| policy_gradient_loss | -0.0712 | +| value_loss | 0.000346 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.16e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 309 | +| iterations | 4891 | +| time_elapsed | 16164 | +| total_timesteps | 5008384 | +| train/ | | +| approx_kl | 2.0775852 | +| clip_fraction | 0.504 | +| clip_range | 0.2 | +| entropy_loss | -0.406 | +| explained_variance | -2.83 | +| learning_rate | 0.0001 | +| loss | -0.108 | +| n_updates | 109430 | +| policy_gradient_loss | -0.0741 | +| value_loss | 0.000508 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.16e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 309 | +| iterations | 4892 | +| time_elapsed | 16167 | +| total_timesteps | 5009408 | +| train/ | | +| approx_kl | 3.004455 | +| clip_fraction | 0.52 | +| clip_range | 0.2 | +| entropy_loss | -0.433 | +| explained_variance | -0.877 | +| learning_rate | 0.0001 | +| loss | -0.0847 | +| n_updates | 109440 | +| policy_gradient_loss | -0.0751 | +| value_loss | 0.000399 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.16e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 309 | +| iterations | 4893 | +| time_elapsed | 16170 | +| total_timesteps | 5010432 | +| train/ | | +| approx_kl | 2.2307386 | +| clip_fraction | 0.478 | +| clip_range | 0.2 | +| entropy_loss | -0.497 | +| explained_variance | -3.29 | +| learning_rate | 0.0001 | +| loss | -0.079 | +| n_updates | 109450 | +| policy_gradient_loss | -0.0613 | +| value_loss | 0.00023 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.16e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 309 | +| iterations | 4894 | +| time_elapsed | 16173 | +| total_timesteps | 5011456 | +| train/ | | +| approx_kl | 1.7339822 | +| clip_fraction | 0.488 | +| clip_range | 0.2 | +| entropy_loss | -0.402 | +| explained_variance | -1.09 | +| learning_rate | 0.0001 | +| loss | -0.0889 | +| n_updates | 109460 | +| policy_gradient_loss | -0.0689 | +| value_loss | 0.000374 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.18e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 309 | +| iterations | 4895 | +| time_elapsed | 16176 | +| total_timesteps | 5012480 | +| train/ | | +| approx_kl | 1.7018946 | +| clip_fraction | 0.49 | +| clip_range | 0.2 | +| entropy_loss | -0.47 | +| explained_variance | -7.46 | +| learning_rate | 0.0001 | +| loss | -0.0884 | +| n_updates | 109470 | +| policy_gradient_loss | -0.0697 | +| value_loss | 0.000499 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.18e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 309 | +| iterations | 4896 | +| time_elapsed | 16179 | +| total_timesteps | 5013504 | +| train/ | | +| approx_kl | 2.3862495 | +| clip_fraction | 0.463 | +| clip_range | 0.2 | +| entropy_loss | -0.362 | +| explained_variance | -2.27 | +| learning_rate | 0.0001 | +| loss | -0.0873 | +| n_updates | 109480 | +| policy_gradient_loss | -0.0673 | +| value_loss | 0.00064 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.19e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 309 | +| iterations | 4897 | +| time_elapsed | 16183 | +| total_timesteps | 5014528 | +| train/ | | +| approx_kl | 1.7879182 | +| clip_fraction | 0.501 | +| clip_range | 0.2 | +| entropy_loss | -0.41 | +| explained_variance | -2.56 | +| learning_rate | 0.0001 | +| loss | -0.0844 | +| n_updates | 109490 | +| policy_gradient_loss | -0.0721 | +| value_loss | 0.000391 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.19e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 309 | +| iterations | 4898 | +| time_elapsed | 16186 | +| total_timesteps | 5015552 | +| train/ | | +| approx_kl | 2.0153868 | +| clip_fraction | 0.516 | +| clip_range | 0.2 | +| entropy_loss | -0.471 | +| explained_variance | -0.368 | +| learning_rate | 0.0001 | +| loss | -0.106 | +| n_updates | 109500 | +| policy_gradient_loss | -0.0646 | +| value_loss | 0.000348 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.19e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 309 | +| iterations | 4899 | +| time_elapsed | 16190 | +| total_timesteps | 5016576 | +| train/ | | +| approx_kl | 1.9726028 | +| clip_fraction | 0.49 | +| clip_range | 0.2 | +| entropy_loss | -0.389 | +| explained_variance | -3.24 | +| learning_rate | 0.0001 | +| loss | -0.0958 | +| n_updates | 109510 | +| policy_gradient_loss | -0.068 | +| value_loss | 0.000491 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.2e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 309 | +| iterations | 4900 | +| time_elapsed | 16193 | +| total_timesteps | 5017600 | +| train/ | | +| approx_kl | 1.6537434 | +| clip_fraction | 0.503 | +| clip_range | 0.2 | +| entropy_loss | -0.47 | +| explained_variance | -0.768 | +| learning_rate | 0.0001 | +| loss | -0.0922 | +| n_updates | 109520 | +| policy_gradient_loss | -0.0672 | +| value_loss | 0.000281 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.2e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 309 | +| iterations | 4901 | +| time_elapsed | 16197 | +| total_timesteps | 5018624 | +| train/ | | +| approx_kl | 1.3655516 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.458 | +| explained_variance | -1.54 | +| learning_rate | 0.0001 | +| loss | -0.0964 | +| n_updates | 109530 | +| policy_gradient_loss | -0.0635 | +| value_loss | 0.000221 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.21e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 309 | +| iterations | 4902 | +| time_elapsed | 16200 | +| total_timesteps | 5019648 | +| train/ | | +| approx_kl | 1.7575101 | +| clip_fraction | 0.508 | +| clip_range | 0.2 | +| entropy_loss | -0.451 | +| explained_variance | -0.481 | +| learning_rate | 0.0001 | +| loss | -0.0699 | +| n_updates | 109540 | +| policy_gradient_loss | -0.0646 | +| value_loss | 0.000367 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.21e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 309 | +| iterations | 4903 | +| time_elapsed | 16204 | +| total_timesteps | 5020672 | +| train/ | | +| approx_kl | 4.114299 | +| clip_fraction | 0.498 | +| clip_range | 0.2 | +| entropy_loss | -0.46 | +| explained_variance | -1.54 | +| learning_rate | 0.0001 | +| loss | -0.0865 | +| n_updates | 109550 | +| policy_gradient_loss | -0.0728 | +| value_loss | 0.000402 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.21e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 309 | +| iterations | 4904 | +| time_elapsed | 16207 | +| total_timesteps | 5021696 | +| train/ | | +| approx_kl | 1.4072587 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.439 | +| explained_variance | -2.29 | +| learning_rate | 0.0001 | +| loss | -0.0947 | +| n_updates | 109560 | +| policy_gradient_loss | -0.0676 | +| value_loss | 0.000407 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.23e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 309 | +| iterations | 4905 | +| time_elapsed | 16211 | +| total_timesteps | 5022720 | +| train/ | | +| approx_kl | 1.7429054 | +| clip_fraction | 0.508 | +| clip_range | 0.2 | +| entropy_loss | -0.421 | +| explained_variance | -1.39 | +| learning_rate | 0.0001 | +| loss | -0.123 | +| n_updates | 109570 | +| policy_gradient_loss | -0.0737 | +| value_loss | 0.000485 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.23e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 309 | +| iterations | 4906 | +| time_elapsed | 16214 | +| total_timesteps | 5023744 | +| train/ | | +| approx_kl | 1.864331 | +| clip_fraction | 0.489 | +| clip_range | 0.2 | +| entropy_loss | -0.416 | +| explained_variance | -0.877 | +| learning_rate | 0.0001 | +| loss | -0.0873 | +| n_updates | 109580 | +| policy_gradient_loss | -0.0699 | +| value_loss | 0.000497 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.23e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 309 | +| iterations | 4907 | +| time_elapsed | 16217 | +| total_timesteps | 5024768 | +| train/ | | +| approx_kl | 2.1799452 | +| clip_fraction | 0.53 | +| clip_range | 0.2 | +| entropy_loss | -0.441 | +| explained_variance | -2.83 | +| learning_rate | 0.0001 | +| loss | -0.117 | +| n_updates | 109590 | +| policy_gradient_loss | -0.0775 | +| value_loss | 0.000474 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.25e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 309 | +| iterations | 4908 | +| time_elapsed | 16220 | +| total_timesteps | 5025792 | +| train/ | | +| approx_kl | 1.6588577 | +| clip_fraction | 0.501 | +| clip_range | 0.2 | +| entropy_loss | -0.45 | +| explained_variance | -3.86 | +| learning_rate | 0.0001 | +| loss | -0.112 | +| n_updates | 109600 | +| policy_gradient_loss | -0.0688 | +| value_loss | 0.000233 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.25e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 309 | +| iterations | 4909 | +| time_elapsed | 16224 | +| total_timesteps | 5026816 | +| train/ | | +| approx_kl | 1.6266863 | +| clip_fraction | 0.484 | +| clip_range | 0.2 | +| entropy_loss | -0.42 | +| explained_variance | -6.08 | +| learning_rate | 0.0001 | +| loss | -0.107 | +| n_updates | 109610 | +| policy_gradient_loss | -0.0682 | +| value_loss | 0.000304 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.26e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 309 | +| iterations | 4910 | +| time_elapsed | 16227 | +| total_timesteps | 5027840 | +| train/ | | +| approx_kl | 1.763177 | +| clip_fraction | 0.509 | +| clip_range | 0.2 | +| entropy_loss | -0.4 | +| explained_variance | -0.956 | +| learning_rate | 0.0001 | +| loss | -0.106 | +| n_updates | 109620 | +| policy_gradient_loss | -0.0759 | +| value_loss | 0.000612 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.26e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 309 | +| iterations | 4911 | +| time_elapsed | 16230 | +| total_timesteps | 5028864 | +| train/ | | +| approx_kl | 1.8336111 | +| clip_fraction | 0.508 | +| clip_range | 0.2 | +| entropy_loss | -0.432 | +| explained_variance | -0.959 | +| learning_rate | 0.0001 | +| loss | -0.0743 | +| n_updates | 109630 | +| policy_gradient_loss | -0.0731 | +| value_loss | 0.000467 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.26e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 309 | +| iterations | 4912 | +| time_elapsed | 16233 | +| total_timesteps | 5029888 | +| train/ | | +| approx_kl | 3.3381999 | +| clip_fraction | 0.507 | +| clip_range | 0.2 | +| entropy_loss | -0.433 | +| explained_variance | -9.26 | +| learning_rate | 0.0001 | +| loss | -0.0933 | +| n_updates | 109640 | +| policy_gradient_loss | -0.0626 | +| value_loss | 0.000329 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.27e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 309 | +| iterations | 4913 | +| time_elapsed | 16236 | +| total_timesteps | 5030912 | +| train/ | | +| approx_kl | 3.3816974 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.441 | +| explained_variance | -1.77 | +| learning_rate | 0.0001 | +| loss | -0.0905 | +| n_updates | 109650 | +| policy_gradient_loss | -0.0679 | +| value_loss | 0.000283 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.27e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 309 | +| iterations | 4914 | +| time_elapsed | 16240 | +| total_timesteps | 5031936 | +| train/ | | +| approx_kl | 1.757258 | +| clip_fraction | 0.492 | +| clip_range | 0.2 | +| entropy_loss | -0.43 | +| explained_variance | -1.45 | +| learning_rate | 0.0001 | +| loss | -0.0932 | +| n_updates | 109660 | +| policy_gradient_loss | -0.0665 | +| value_loss | 0.000508 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.27e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 309 | +| iterations | 4915 | +| time_elapsed | 16243 | +| total_timesteps | 5032960 | +| train/ | | +| approx_kl | 1.9495121 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.369 | +| explained_variance | -4.57 | +| learning_rate | 0.0001 | +| loss | -0.0948 | +| n_updates | 109670 | +| policy_gradient_loss | -0.075 | +| value_loss | 0.000381 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.27e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 309 | +| iterations | 4916 | +| time_elapsed | 16247 | +| total_timesteps | 5033984 | +| train/ | | +| approx_kl | 2.2369897 | +| clip_fraction | 0.505 | +| clip_range | 0.2 | +| entropy_loss | -0.439 | +| explained_variance | -1.91 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 109680 | +| policy_gradient_loss | -0.0692 | +| value_loss | 0.00027 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.27e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 309 | +| iterations | 4917 | +| time_elapsed | 16250 | +| total_timesteps | 5035008 | +| train/ | | +| approx_kl | 1.8214904 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.422 | +| explained_variance | -0.947 | +| learning_rate | 0.0001 | +| loss | -0.0493 | +| n_updates | 109690 | +| policy_gradient_loss | -0.0585 | +| value_loss | 0.000272 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.28e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 309 | +| iterations | 4918 | +| time_elapsed | 16254 | +| total_timesteps | 5036032 | +| train/ | | +| approx_kl | 1.9196229 | +| clip_fraction | 0.507 | +| clip_range | 0.2 | +| entropy_loss | -0.408 | +| explained_variance | -2.78 | +| learning_rate | 0.0001 | +| loss | -0.0865 | +| n_updates | 109700 | +| policy_gradient_loss | -0.0746 | +| value_loss | 0.000484 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.28e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 309 | +| iterations | 4919 | +| time_elapsed | 16257 | +| total_timesteps | 5037056 | +| train/ | | +| approx_kl | 2.4043965 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.407 | +| explained_variance | -0.856 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 109710 | +| policy_gradient_loss | -0.0699 | +| value_loss | 0.000542 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.28e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 309 | +| iterations | 4920 | +| time_elapsed | 16261 | +| total_timesteps | 5038080 | +| train/ | | +| approx_kl | 1.7283655 | +| clip_fraction | 0.484 | +| clip_range | 0.2 | +| entropy_loss | -0.407 | +| explained_variance | -1.59 | +| learning_rate | 0.0001 | +| loss | -0.112 | +| n_updates | 109720 | +| policy_gradient_loss | -0.0608 | +| value_loss | 0.000452 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.28e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 309 | +| iterations | 4921 | +| time_elapsed | 16264 | +| total_timesteps | 5039104 | +| train/ | | +| approx_kl | 2.4132853 | +| clip_fraction | 0.492 | +| clip_range | 0.2 | +| entropy_loss | -0.42 | +| explained_variance | -5.31 | +| learning_rate | 0.0001 | +| loss | -0.0753 | +| n_updates | 109730 | +| policy_gradient_loss | -0.0609 | +| value_loss | 0.000384 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.28e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 309 | +| iterations | 4922 | +| time_elapsed | 16268 | +| total_timesteps | 5040128 | +| train/ | | +| approx_kl | 1.8006755 | +| clip_fraction | 0.486 | +| clip_range | 0.2 | +| entropy_loss | -0.411 | +| explained_variance | -0.965 | +| learning_rate | 0.0001 | +| loss | -0.072 | +| n_updates | 109740 | +| policy_gradient_loss | -0.0628 | +| value_loss | 0.00045 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.28e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 309 | +| iterations | 4923 | +| time_elapsed | 16271 | +| total_timesteps | 5041152 | +| train/ | | +| approx_kl | 2.1926792 | +| clip_fraction | 0.553 | +| clip_range | 0.2 | +| entropy_loss | -0.515 | +| explained_variance | -1.38 | +| learning_rate | 0.0001 | +| loss | -0.0914 | +| n_updates | 109750 | +| policy_gradient_loss | -0.0594 | +| value_loss | 0.000378 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.29e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 309 | +| iterations | 4924 | +| time_elapsed | 16274 | +| total_timesteps | 5042176 | +| train/ | | +| approx_kl | 2.0109777 | +| clip_fraction | 0.513 | +| clip_range | 0.2 | +| entropy_loss | -0.442 | +| explained_variance | -1.54 | +| learning_rate | 0.0001 | +| loss | -0.114 | +| n_updates | 109760 | +| policy_gradient_loss | -0.07 | +| value_loss | 0.00026 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.29e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 309 | +| iterations | 4925 | +| time_elapsed | 16277 | +| total_timesteps | 5043200 | +| train/ | | +| approx_kl | 2.7275739 | +| clip_fraction | 0.533 | +| clip_range | 0.2 | +| entropy_loss | -0.444 | +| explained_variance | -0.632 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 109770 | +| policy_gradient_loss | -0.069 | +| value_loss | 0.000547 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.29e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 309 | +| iterations | 4926 | +| time_elapsed | 16280 | +| total_timesteps | 5044224 | +| train/ | | +| approx_kl | 33.95959 | +| clip_fraction | 0.507 | +| clip_range | 0.2 | +| entropy_loss | -0.51 | +| explained_variance | -2.58 | +| learning_rate | 0.0001 | +| loss | -0.0945 | +| n_updates | 109780 | +| policy_gradient_loss | -0.0704 | +| value_loss | 0.000533 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.29e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 309 | +| iterations | 4927 | +| time_elapsed | 16283 | +| total_timesteps | 5045248 | +| train/ | | +| approx_kl | 2.103638 | +| clip_fraction | 0.501 | +| clip_range | 0.2 | +| entropy_loss | -0.437 | +| explained_variance | -2.12 | +| learning_rate | 0.0001 | +| loss | -0.0982 | +| n_updates | 109790 | +| policy_gradient_loss | -0.0717 | +| value_loss | 0.000589 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.29e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 309 | +| iterations | 4928 | +| time_elapsed | 16287 | +| total_timesteps | 5046272 | +| train/ | | +| approx_kl | 2.2744946 | +| clip_fraction | 0.501 | +| clip_range | 0.2 | +| entropy_loss | -0.382 | +| explained_variance | -1.4 | +| learning_rate | 0.0001 | +| loss | -0.0892 | +| n_updates | 109800 | +| policy_gradient_loss | -0.0709 | +| value_loss | 0.000395 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.29e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 309 | +| iterations | 4929 | +| time_elapsed | 16290 | +| total_timesteps | 5047296 | +| train/ | | +| approx_kl | 2.4508834 | +| clip_fraction | 0.497 | +| clip_range | 0.2 | +| entropy_loss | -0.444 | +| explained_variance | -1.09 | +| learning_rate | 0.0001 | +| loss | -0.0862 | +| n_updates | 109810 | +| policy_gradient_loss | -0.0608 | +| value_loss | 0.000332 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.29e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 309 | +| iterations | 4930 | +| time_elapsed | 16293 | +| total_timesteps | 5048320 | +| train/ | | +| approx_kl | 1.6385944 | +| clip_fraction | 0.521 | +| clip_range | 0.2 | +| entropy_loss | -0.484 | +| explained_variance | -0.492 | +| learning_rate | 0.0001 | +| loss | -0.0927 | +| n_updates | 109820 | +| policy_gradient_loss | -0.071 | +| value_loss | 0.000554 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.29e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 309 | +| iterations | 4931 | +| time_elapsed | 16296 | +| total_timesteps | 5049344 | +| train/ | | +| approx_kl | 1.3741052 | +| clip_fraction | 0.494 | +| clip_range | 0.2 | +| entropy_loss | -0.497 | +| explained_variance | -7.21 | +| learning_rate | 0.0001 | +| loss | -0.0887 | +| n_updates | 109830 | +| policy_gradient_loss | -0.0731 | +| value_loss | 0.000339 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.25e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 309 | +| iterations | 4932 | +| time_elapsed | 16299 | +| total_timesteps | 5050368 | +| train/ | | +| approx_kl | 2.3147888 | +| clip_fraction | 0.496 | +| clip_range | 0.2 | +| entropy_loss | -0.409 | +| explained_variance | -1.72 | +| learning_rate | 0.0001 | +| loss | -0.0959 | +| n_updates | 109840 | +| policy_gradient_loss | -0.0632 | +| value_loss | 0.000423 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.24e+03 | +| ep_rew_mean | 0.315 | +| time/ | | +| fps | 309 | +| iterations | 4933 | +| time_elapsed | 16303 | +| total_timesteps | 5051392 | +| train/ | | +| approx_kl | 1.9804343 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.39 | +| explained_variance | -1.92 | +| learning_rate | 0.0001 | +| loss | -0.1 | +| n_updates | 109850 | +| policy_gradient_loss | -0.0683 | +| value_loss | 0.000482 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.24e+03 | +| ep_rew_mean | 0.315 | +| time/ | | +| fps | 309 | +| iterations | 4934 | +| time_elapsed | 16306 | +| total_timesteps | 5052416 | +| train/ | | +| approx_kl | 2.0900679 | +| clip_fraction | 0.516 | +| clip_range | 0.2 | +| entropy_loss | -0.416 | +| explained_variance | -0.578 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 109860 | +| policy_gradient_loss | -0.0623 | +| value_loss | 0.000463 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.24e+03 | +| ep_rew_mean | 0.315 | +| time/ | | +| fps | 309 | +| iterations | 4935 | +| time_elapsed | 16310 | +| total_timesteps | 5053440 | +| train/ | | +| approx_kl | 1.93667 | +| clip_fraction | 0.51 | +| clip_range | 0.2 | +| entropy_loss | -0.43 | +| explained_variance | -1.91 | +| learning_rate | 0.0001 | +| loss | -0.0751 | +| n_updates | 109870 | +| policy_gradient_loss | -0.0703 | +| value_loss | 0.00041 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.24e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 309 | +| iterations | 4936 | +| time_elapsed | 16313 | +| total_timesteps | 5054464 | +| train/ | | +| approx_kl | 1.8682394 | +| clip_fraction | 0.511 | +| clip_range | 0.2 | +| entropy_loss | -0.422 | +| explained_variance | -4.95 | +| learning_rate | 0.0001 | +| loss | -0.0719 | +| n_updates | 109880 | +| policy_gradient_loss | -0.0707 | +| value_loss | 0.000244 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.25e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 309 | +| iterations | 4937 | +| time_elapsed | 16317 | +| total_timesteps | 5055488 | +| train/ | | +| approx_kl | 1.8905599 | +| clip_fraction | 0.473 | +| clip_range | 0.2 | +| entropy_loss | -0.376 | +| explained_variance | -1.11 | +| learning_rate | 0.0001 | +| loss | -0.0773 | +| n_updates | 109890 | +| policy_gradient_loss | -0.0619 | +| value_loss | 0.000309 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.25e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 309 | +| iterations | 4938 | +| time_elapsed | 16320 | +| total_timesteps | 5056512 | +| train/ | | +| approx_kl | 1.7642579 | +| clip_fraction | 0.493 | +| clip_range | 0.2 | +| entropy_loss | -0.373 | +| explained_variance | -2.16 | +| learning_rate | 0.0001 | +| loss | -0.0866 | +| n_updates | 109900 | +| policy_gradient_loss | -0.0722 | +| value_loss | 0.000458 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.25e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 309 | +| iterations | 4939 | +| time_elapsed | 16324 | +| total_timesteps | 5057536 | +| train/ | | +| approx_kl | 1.6249282 | +| clip_fraction | 0.507 | +| clip_range | 0.2 | +| entropy_loss | -0.443 | +| explained_variance | -1.4 | +| learning_rate | 0.0001 | +| loss | -0.0877 | +| n_updates | 109910 | +| policy_gradient_loss | -0.0684 | +| value_loss | 0.000474 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.26e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 309 | +| iterations | 4940 | +| time_elapsed | 16327 | +| total_timesteps | 5058560 | +| train/ | | +| approx_kl | 2.2112403 | +| clip_fraction | 0.517 | +| clip_range | 0.2 | +| entropy_loss | -0.446 | +| explained_variance | -1.31 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 109920 | +| policy_gradient_loss | -0.0735 | +| value_loss | 0.000349 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.25e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 309 | +| iterations | 4941 | +| time_elapsed | 16330 | +| total_timesteps | 5059584 | +| train/ | | +| approx_kl | 6.3946724 | +| clip_fraction | 0.536 | +| clip_range | 0.2 | +| entropy_loss | -0.381 | +| explained_variance | -0.136 | +| learning_rate | 0.0001 | +| loss | -0.0973 | +| n_updates | 109930 | +| policy_gradient_loss | -0.0714 | +| value_loss | 0.000292 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.25e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 309 | +| iterations | 4942 | +| time_elapsed | 16334 | +| total_timesteps | 5060608 | +| train/ | | +| approx_kl | 2.3747396 | +| clip_fraction | 0.508 | +| clip_range | 0.2 | +| entropy_loss | -0.404 | +| explained_variance | -1.43 | +| learning_rate | 0.0001 | +| loss | -0.0955 | +| n_updates | 109940 | +| policy_gradient_loss | -0.0697 | +| value_loss | 0.00054 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.24e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 309 | +| iterations | 4943 | +| time_elapsed | 16337 | +| total_timesteps | 5061632 | +| train/ | | +| approx_kl | 1.6973984 | +| clip_fraction | 0.477 | +| clip_range | 0.2 | +| entropy_loss | -0.439 | +| explained_variance | -1.53 | +| learning_rate | 0.0001 | +| loss | -0.0946 | +| n_updates | 109950 | +| policy_gradient_loss | -0.0642 | +| value_loss | 0.000469 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.24e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 309 | +| iterations | 4944 | +| time_elapsed | 16340 | +| total_timesteps | 5062656 | +| train/ | | +| approx_kl | 1.8235779 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.399 | +| explained_variance | -2.1 | +| learning_rate | 0.0001 | +| loss | -0.114 | +| n_updates | 109960 | +| policy_gradient_loss | -0.0693 | +| value_loss | 0.000432 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.25e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 309 | +| iterations | 4945 | +| time_elapsed | 16343 | +| total_timesteps | 5063680 | +| train/ | | +| approx_kl | 1.8755379 | +| clip_fraction | 0.491 | +| clip_range | 0.2 | +| entropy_loss | -0.387 | +| explained_variance | -2.28 | +| learning_rate | 0.0001 | +| loss | -0.1 | +| n_updates | 109970 | +| policy_gradient_loss | -0.071 | +| value_loss | 0.000599 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.25e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 309 | +| iterations | 4946 | +| time_elapsed | 16346 | +| total_timesteps | 5064704 | +| train/ | | +| approx_kl | 1.6514097 | +| clip_fraction | 0.474 | +| clip_range | 0.2 | +| entropy_loss | -0.418 | +| explained_variance | -1.57 | +| learning_rate | 0.0001 | +| loss | -0.0755 | +| n_updates | 109980 | +| policy_gradient_loss | -0.061 | +| value_loss | 0.000539 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.25e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 309 | +| iterations | 4947 | +| time_elapsed | 16350 | +| total_timesteps | 5065728 | +| train/ | | +| approx_kl | 2.1913936 | +| clip_fraction | 0.539 | +| clip_range | 0.2 | +| entropy_loss | -0.448 | +| explained_variance | -1.74 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 109990 | +| policy_gradient_loss | -0.0723 | +| value_loss | 0.000386 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.26e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 309 | +| iterations | 4948 | +| time_elapsed | 16353 | +| total_timesteps | 5066752 | +| train/ | | +| approx_kl | 2.2450223 | +| clip_fraction | 0.493 | +| clip_range | 0.2 | +| entropy_loss | -0.403 | +| explained_variance | -1.81 | +| learning_rate | 0.0001 | +| loss | -0.0834 | +| n_updates | 110000 | +| policy_gradient_loss | -0.0761 | +| value_loss | 0.000436 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.26e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 309 | +| iterations | 4949 | +| time_elapsed | 16356 | +| total_timesteps | 5067776 | +| train/ | | +| approx_kl | 1.9110547 | +| clip_fraction | 0.467 | +| clip_range | 0.2 | +| entropy_loss | -0.401 | +| explained_variance | -2.4 | +| learning_rate | 0.0001 | +| loss | -0.0911 | +| n_updates | 110010 | +| policy_gradient_loss | -0.0589 | +| value_loss | 0.000241 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.26e+03 | +| ep_rew_mean | 0.306 | +| time/ | | +| fps | 309 | +| iterations | 4950 | +| time_elapsed | 16359 | +| total_timesteps | 5068800 | +| train/ | | +| approx_kl | 2.0047803 | +| clip_fraction | 0.515 | +| clip_range | 0.2 | +| entropy_loss | -0.426 | +| explained_variance | -1.2 | +| learning_rate | 0.0001 | +| loss | -0.099 | +| n_updates | 110020 | +| policy_gradient_loss | -0.0721 | +| value_loss | 0.000363 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.26e+03 | +| ep_rew_mean | 0.306 | +| time/ | | +| fps | 309 | +| iterations | 4951 | +| time_elapsed | 16362 | +| total_timesteps | 5069824 | +| train/ | | +| approx_kl | 1.8266122 | +| clip_fraction | 0.491 | +| clip_range | 0.2 | +| entropy_loss | -0.423 | +| explained_variance | -0.989 | +| learning_rate | 0.0001 | +| loss | -0.0746 | +| n_updates | 110030 | +| policy_gradient_loss | -0.0688 | +| value_loss | 0.000244 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.27e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 309 | +| iterations | 4952 | +| time_elapsed | 16366 | +| total_timesteps | 5070848 | +| train/ | | +| approx_kl | 1.8335271 | +| clip_fraction | 0.479 | +| clip_range | 0.2 | +| entropy_loss | -0.408 | +| explained_variance | -0.53 | +| learning_rate | 0.0001 | +| loss | -0.0838 | +| n_updates | 110040 | +| policy_gradient_loss | -0.061 | +| value_loss | 0.000613 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.27e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 309 | +| iterations | 4953 | +| time_elapsed | 16369 | +| total_timesteps | 5071872 | +| train/ | | +| approx_kl | 2.7813094 | +| clip_fraction | 0.507 | +| clip_range | 0.2 | +| entropy_loss | -0.418 | +| explained_variance | -3.95 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 110050 | +| policy_gradient_loss | -0.0757 | +| value_loss | 0.000304 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.26e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 309 | +| iterations | 4954 | +| time_elapsed | 16373 | +| total_timesteps | 5072896 | +| train/ | | +| approx_kl | 2.0174084 | +| clip_fraction | 0.521 | +| clip_range | 0.2 | +| entropy_loss | -0.461 | +| explained_variance | -0.275 | +| learning_rate | 0.0001 | +| loss | -0.0942 | +| n_updates | 110060 | +| policy_gradient_loss | -0.0632 | +| value_loss | 0.000447 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.26e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 309 | +| iterations | 4955 | +| time_elapsed | 16376 | +| total_timesteps | 5073920 | +| train/ | | +| approx_kl | 1.9504023 | +| clip_fraction | 0.492 | +| clip_range | 0.2 | +| entropy_loss | -0.428 | +| explained_variance | -1.23 | +| learning_rate | 0.0001 | +| loss | -0.0895 | +| n_updates | 110070 | +| policy_gradient_loss | -0.069 | +| value_loss | 0.000675 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.26e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 309 | +| iterations | 4956 | +| time_elapsed | 16379 | +| total_timesteps | 5074944 | +| train/ | | +| approx_kl | 2.1562364 | +| clip_fraction | 0.519 | +| clip_range | 0.2 | +| entropy_loss | -0.435 | +| explained_variance | -1.53 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 110080 | +| policy_gradient_loss | -0.0765 | +| value_loss | 0.000518 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.26e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 309 | +| iterations | 4957 | +| time_elapsed | 16383 | +| total_timesteps | 5075968 | +| train/ | | +| approx_kl | 2.7052827 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.419 | +| explained_variance | -2.36 | +| learning_rate | 0.0001 | +| loss | -0.0343 | +| n_updates | 110090 | +| policy_gradient_loss | -0.064 | +| value_loss | 0.000284 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.26e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 309 | +| iterations | 4958 | +| time_elapsed | 16386 | +| total_timesteps | 5076992 | +| train/ | | +| approx_kl | 2.0929248 | +| clip_fraction | 0.5 | +| clip_range | 0.2 | +| entropy_loss | -0.391 | +| explained_variance | -1.21 | +| learning_rate | 0.0001 | +| loss | -0.0796 | +| n_updates | 110100 | +| policy_gradient_loss | -0.0671 | +| value_loss | 0.000268 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.28e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 309 | +| iterations | 4959 | +| time_elapsed | 16390 | +| total_timesteps | 5078016 | +| train/ | | +| approx_kl | 1.7820529 | +| clip_fraction | 0.49 | +| clip_range | 0.2 | +| entropy_loss | -0.463 | +| explained_variance | -1.51 | +| learning_rate | 0.0001 | +| loss | -0.0984 | +| n_updates | 110110 | +| policy_gradient_loss | -0.061 | +| value_loss | 0.000405 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.28e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 309 | +| iterations | 4960 | +| time_elapsed | 16393 | +| total_timesteps | 5079040 | +| train/ | | +| approx_kl | 1.8838786 | +| clip_fraction | 0.463 | +| clip_range | 0.2 | +| entropy_loss | -0.415 | +| explained_variance | -2.03 | +| learning_rate | 0.0001 | +| loss | -0.108 | +| n_updates | 110120 | +| policy_gradient_loss | -0.0647 | +| value_loss | 0.000314 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.28e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 309 | +| iterations | 4961 | +| time_elapsed | 16396 | +| total_timesteps | 5080064 | +| train/ | | +| approx_kl | 1.8212337 | +| clip_fraction | 0.516 | +| clip_range | 0.2 | +| entropy_loss | -0.478 | +| explained_variance | -1.47 | +| learning_rate | 0.0001 | +| loss | -0.0803 | +| n_updates | 110130 | +| policy_gradient_loss | -0.0685 | +| value_loss | 0.000499 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.3e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 309 | +| iterations | 4962 | +| time_elapsed | 16399 | +| total_timesteps | 5081088 | +| train/ | | +| approx_kl | 2.6530836 | +| clip_fraction | 0.502 | +| clip_range | 0.2 | +| entropy_loss | -0.492 | +| explained_variance | -3.96 | +| learning_rate | 0.0001 | +| loss | -0.0984 | +| n_updates | 110140 | +| policy_gradient_loss | -0.0728 | +| value_loss | 0.000398 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.3e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 309 | +| iterations | 4963 | +| time_elapsed | 16402 | +| total_timesteps | 5082112 | +| train/ | | +| approx_kl | 1.9988871 | +| clip_fraction | 0.5 | +| clip_range | 0.2 | +| entropy_loss | -0.417 | +| explained_variance | -9.84 | +| learning_rate | 0.0001 | +| loss | -0.0882 | +| n_updates | 110150 | +| policy_gradient_loss | -0.0731 | +| value_loss | 0.00035 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.29e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 309 | +| iterations | 4964 | +| time_elapsed | 16405 | +| total_timesteps | 5083136 | +| train/ | | +| approx_kl | 1.9691806 | +| clip_fraction | 0.459 | +| clip_range | 0.2 | +| entropy_loss | -0.346 | +| explained_variance | -0.707 | +| learning_rate | 0.0001 | +| loss | -0.0855 | +| n_updates | 110160 | +| policy_gradient_loss | -0.0651 | +| value_loss | 0.000468 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.29e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 309 | +| iterations | 4965 | +| time_elapsed | 16408 | +| total_timesteps | 5084160 | +| train/ | | +| approx_kl | 1.8428973 | +| clip_fraction | 0.47 | +| clip_range | 0.2 | +| entropy_loss | -0.375 | +| explained_variance | -1.7 | +| learning_rate | 0.0001 | +| loss | -0.056 | +| n_updates | 110170 | +| policy_gradient_loss | -0.0677 | +| value_loss | 0.000295 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.29e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 309 | +| iterations | 4966 | +| time_elapsed | 16412 | +| total_timesteps | 5085184 | +| train/ | | +| approx_kl | 2.142362 | +| clip_fraction | 0.49 | +| clip_range | 0.2 | +| entropy_loss | -0.408 | +| explained_variance | -1.79 | +| learning_rate | 0.0001 | +| loss | -0.0888 | +| n_updates | 110180 | +| policy_gradient_loss | -0.0683 | +| value_loss | 0.0006 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.29e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 309 | +| iterations | 4967 | +| time_elapsed | 16415 | +| total_timesteps | 5086208 | +| train/ | | +| approx_kl | 1.9734467 | +| clip_fraction | 0.526 | +| clip_range | 0.2 | +| entropy_loss | -0.449 | +| explained_variance | -1.73 | +| learning_rate | 0.0001 | +| loss | -0.117 | +| n_updates | 110190 | +| policy_gradient_loss | -0.0774 | +| value_loss | 0.000583 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.28e+03 | +| ep_rew_mean | 0.306 | +| time/ | | +| fps | 309 | +| iterations | 4968 | +| time_elapsed | 16418 | +| total_timesteps | 5087232 | +| train/ | | +| approx_kl | 10.023296 | +| clip_fraction | 0.518 | +| clip_range | 0.2 | +| entropy_loss | -0.436 | +| explained_variance | -2.27 | +| learning_rate | 0.0001 | +| loss | -0.0978 | +| n_updates | 110200 | +| policy_gradient_loss | -0.0735 | +| value_loss | 0.000572 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.28e+03 | +| ep_rew_mean | 0.306 | +| time/ | | +| fps | 309 | +| iterations | 4969 | +| time_elapsed | 16421 | +| total_timesteps | 5088256 | +| train/ | | +| approx_kl | 1.6226209 | +| clip_fraction | 0.455 | +| clip_range | 0.2 | +| entropy_loss | -0.389 | +| explained_variance | -1.49 | +| learning_rate | 0.0001 | +| loss | -0.0963 | +| n_updates | 110210 | +| policy_gradient_loss | -0.0665 | +| value_loss | 0.000406 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.28e+03 | +| ep_rew_mean | 0.306 | +| time/ | | +| fps | 309 | +| iterations | 4970 | +| time_elapsed | 16425 | +| total_timesteps | 5089280 | +| train/ | | +| approx_kl | 1.8939934 | +| clip_fraction | 0.479 | +| clip_range | 0.2 | +| entropy_loss | -0.394 | +| explained_variance | -2.14 | +| learning_rate | 0.0001 | +| loss | -0.0783 | +| n_updates | 110220 | +| policy_gradient_loss | -0.0669 | +| value_loss | 0.000419 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.28e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 309 | +| iterations | 4971 | +| time_elapsed | 16428 | +| total_timesteps | 5090304 | +| train/ | | +| approx_kl | 2.708293 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.403 | +| explained_variance | -2.83 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 110230 | +| policy_gradient_loss | -0.0735 | +| value_loss | 0.000356 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.28e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 309 | +| iterations | 4972 | +| time_elapsed | 16432 | +| total_timesteps | 5091328 | +| train/ | | +| approx_kl | 1.9889193 | +| clip_fraction | 0.485 | +| clip_range | 0.2 | +| entropy_loss | -0.443 | +| explained_variance | -1.13 | +| learning_rate | 0.0001 | +| loss | -0.0622 | +| n_updates | 110240 | +| policy_gradient_loss | -0.0651 | +| value_loss | 0.000329 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.28e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 309 | +| iterations | 4973 | +| time_elapsed | 16435 | +| total_timesteps | 5092352 | +| train/ | | +| approx_kl | 1.5720648 | +| clip_fraction | 0.502 | +| clip_range | 0.2 | +| entropy_loss | -0.474 | +| explained_variance | -1.92 | +| learning_rate | 0.0001 | +| loss | -0.0978 | +| n_updates | 110250 | +| policy_gradient_loss | -0.0735 | +| value_loss | 0.0003 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.28e+03 | +| ep_rew_mean | 0.302 | +| time/ | | +| fps | 309 | +| iterations | 4974 | +| time_elapsed | 16439 | +| total_timesteps | 5093376 | +| train/ | | +| approx_kl | 1.2319785 | +| clip_fraction | 0.513 | +| clip_range | 0.2 | +| entropy_loss | -0.526 | +| explained_variance | -3.29 | +| learning_rate | 0.0001 | +| loss | -0.0825 | +| n_updates | 110260 | +| policy_gradient_loss | -0.0673 | +| value_loss | 0.000119 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.28e+03 | +| ep_rew_mean | 0.302 | +| time/ | | +| fps | 309 | +| iterations | 4975 | +| time_elapsed | 16442 | +| total_timesteps | 5094400 | +| train/ | | +| approx_kl | 1.8162208 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.401 | +| explained_variance | -0.642 | +| learning_rate | 0.0001 | +| loss | -0.0838 | +| n_updates | 110270 | +| policy_gradient_loss | -0.0625 | +| value_loss | 0.000603 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.28e+03 | +| ep_rew_mean | 0.302 | +| time/ | | +| fps | 309 | +| iterations | 4976 | +| time_elapsed | 16446 | +| total_timesteps | 5095424 | +| train/ | | +| approx_kl | 1.833509 | +| clip_fraction | 0.499 | +| clip_range | 0.2 | +| entropy_loss | -0.437 | +| explained_variance | -6.49 | +| learning_rate | 0.0001 | +| loss | -0.0587 | +| n_updates | 110280 | +| policy_gradient_loss | -0.0631 | +| value_loss | 0.000418 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.3e+03 | +| ep_rew_mean | 0.3 | +| time/ | | +| fps | 309 | +| iterations | 4977 | +| time_elapsed | 16449 | +| total_timesteps | 5096448 | +| train/ | | +| approx_kl | 2.221067 | +| clip_fraction | 0.504 | +| clip_range | 0.2 | +| entropy_loss | -0.432 | +| explained_variance | -0.618 | +| learning_rate | 0.0001 | +| loss | -0.106 | +| n_updates | 110290 | +| policy_gradient_loss | -0.0731 | +| value_loss | 0.000474 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.3e+03 | +| ep_rew_mean | 0.3 | +| time/ | | +| fps | 309 | +| iterations | 4978 | +| time_elapsed | 16452 | +| total_timesteps | 5097472 | +| train/ | | +| approx_kl | 1.8071057 | +| clip_fraction | 0.477 | +| clip_range | 0.2 | +| entropy_loss | -0.4 | +| explained_variance | -1.8 | +| learning_rate | 0.0001 | +| loss | -0.109 | +| n_updates | 110300 | +| policy_gradient_loss | -0.0708 | +| value_loss | 0.000501 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.29e+03 | +| ep_rew_mean | 0.298 | +| time/ | | +| fps | 309 | +| iterations | 4979 | +| time_elapsed | 16456 | +| total_timesteps | 5098496 | +| train/ | | +| approx_kl | 1.5575104 | +| clip_fraction | 0.494 | +| clip_range | 0.2 | +| entropy_loss | -0.426 | +| explained_variance | -7.8 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 110310 | +| policy_gradient_loss | -0.0747 | +| value_loss | 0.000256 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.29e+03 | +| ep_rew_mean | 0.298 | +| time/ | | +| fps | 309 | +| iterations | 4980 | +| time_elapsed | 16459 | +| total_timesteps | 5099520 | +| train/ | | +| approx_kl | 1.8609309 | +| clip_fraction | 0.456 | +| clip_range | 0.2 | +| entropy_loss | -0.397 | +| explained_variance | -5.45 | +| learning_rate | 0.0001 | +| loss | -0.0758 | +| n_updates | 110320 | +| policy_gradient_loss | -0.0628 | +| value_loss | 0.000296 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.29e+03 | +| ep_rew_mean | 0.292 | +| time/ | | +| fps | 309 | +| iterations | 4981 | +| time_elapsed | 16462 | +| total_timesteps | 5100544 | +| train/ | | +| approx_kl | 1.5865626 | +| clip_fraction | 0.473 | +| clip_range | 0.2 | +| entropy_loss | -0.424 | +| explained_variance | -4.46 | +| learning_rate | 0.0001 | +| loss | -0.11 | +| n_updates | 110330 | +| policy_gradient_loss | -0.0692 | +| value_loss | 0.00046 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.29e+03 | +| ep_rew_mean | 0.292 | +| time/ | | +| fps | 309 | +| iterations | 4982 | +| time_elapsed | 16465 | +| total_timesteps | 5101568 | +| train/ | | +| approx_kl | 1.75583 | +| clip_fraction | 0.461 | +| clip_range | 0.2 | +| entropy_loss | -0.39 | +| explained_variance | -1.21 | +| learning_rate | 0.0001 | +| loss | -0.0735 | +| n_updates | 110340 | +| policy_gradient_loss | -0.0641 | +| value_loss | 0.000416 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.29e+03 | +| ep_rew_mean | 0.292 | +| time/ | | +| fps | 309 | +| iterations | 4983 | +| time_elapsed | 16468 | +| total_timesteps | 5102592 | +| train/ | | +| approx_kl | 2.0363007 | +| clip_fraction | 0.503 | +| clip_range | 0.2 | +| entropy_loss | -0.384 | +| explained_variance | -2.16 | +| learning_rate | 0.0001 | +| loss | -0.0671 | +| n_updates | 110350 | +| policy_gradient_loss | -0.0754 | +| value_loss | 0.000494 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.3e+03 | +| ep_rew_mean | 0.29 | +| time/ | | +| fps | 309 | +| iterations | 4984 | +| time_elapsed | 16471 | +| total_timesteps | 5103616 | +| train/ | | +| approx_kl | 2.029242 | +| clip_fraction | 0.515 | +| clip_range | 0.2 | +| entropy_loss | -0.462 | +| explained_variance | -3.11 | +| learning_rate | 0.0001 | +| loss | -0.0886 | +| n_updates | 110360 | +| policy_gradient_loss | -0.0707 | +| value_loss | 0.000498 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.3e+03 | +| ep_rew_mean | 0.29 | +| time/ | | +| fps | 309 | +| iterations | 4985 | +| time_elapsed | 16474 | +| total_timesteps | 5104640 | +| train/ | | +| approx_kl | 1.7106605 | +| clip_fraction | 0.507 | +| clip_range | 0.2 | +| entropy_loss | -0.461 | +| explained_variance | -3.76 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 110370 | +| policy_gradient_loss | -0.0693 | +| value_loss | 0.000251 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.3e+03 | +| ep_rew_mean | 0.292 | +| time/ | | +| fps | 309 | +| iterations | 4986 | +| time_elapsed | 16478 | +| total_timesteps | 5105664 | +| train/ | | +| approx_kl | 1.7967186 | +| clip_fraction | 0.539 | +| clip_range | 0.2 | +| entropy_loss | -0.447 | +| explained_variance | -1.81 | +| learning_rate | 0.0001 | +| loss | -0.0833 | +| n_updates | 110380 | +| policy_gradient_loss | -0.0664 | +| value_loss | 0.000549 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.29e+03 | +| ep_rew_mean | 0.293 | +| time/ | | +| fps | 309 | +| iterations | 4987 | +| time_elapsed | 16481 | +| total_timesteps | 5106688 | +| train/ | | +| approx_kl | 1.9358288 | +| clip_fraction | 0.52 | +| clip_range | 0.2 | +| entropy_loss | -0.468 | +| explained_variance | -1.74 | +| learning_rate | 0.0001 | +| loss | -0.0845 | +| n_updates | 110390 | +| policy_gradient_loss | -0.0717 | +| value_loss | 0.00051 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.29e+03 | +| ep_rew_mean | 0.293 | +| time/ | | +| fps | 309 | +| iterations | 4988 | +| time_elapsed | 16485 | +| total_timesteps | 5107712 | +| train/ | | +| approx_kl | 2.127075 | +| clip_fraction | 0.496 | +| clip_range | 0.2 | +| entropy_loss | -0.408 | +| explained_variance | -2.19 | +| learning_rate | 0.0001 | +| loss | -0.0978 | +| n_updates | 110400 | +| policy_gradient_loss | -0.0696 | +| value_loss | 0.000342 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.29e+03 | +| ep_rew_mean | 0.293 | +| time/ | | +| fps | 309 | +| iterations | 4989 | +| time_elapsed | 16488 | +| total_timesteps | 5108736 | +| train/ | | +| approx_kl | 1.9841132 | +| clip_fraction | 0.54 | +| clip_range | 0.2 | +| entropy_loss | -0.47 | +| explained_variance | -1.2 | +| learning_rate | 0.0001 | +| loss | -0.0892 | +| n_updates | 110410 | +| policy_gradient_loss | -0.0727 | +| value_loss | 0.000572 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.28e+03 | +| ep_rew_mean | 0.297 | +| time/ | | +| fps | 309 | +| iterations | 4990 | +| time_elapsed | 16492 | +| total_timesteps | 5109760 | +| train/ | | +| approx_kl | 1.6057202 | +| clip_fraction | 0.504 | +| clip_range | 0.2 | +| entropy_loss | -0.52 | +| explained_variance | -4.63 | +| learning_rate | 0.0001 | +| loss | -0.0938 | +| n_updates | 110420 | +| policy_gradient_loss | -0.0751 | +| value_loss | 0.000245 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.28e+03 | +| ep_rew_mean | 0.297 | +| time/ | | +| fps | 309 | +| iterations | 4991 | +| time_elapsed | 16495 | +| total_timesteps | 5110784 | +| train/ | | +| approx_kl | 2.1355896 | +| clip_fraction | 0.512 | +| clip_range | 0.2 | +| entropy_loss | -0.441 | +| explained_variance | -0.806 | +| learning_rate | 0.0001 | +| loss | -0.0851 | +| n_updates | 110430 | +| policy_gradient_loss | -0.0677 | +| value_loss | 0.000411 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.29e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 309 | +| iterations | 4992 | +| time_elapsed | 16499 | +| total_timesteps | 5111808 | +| train/ | | +| approx_kl | 2.0152874 | +| clip_fraction | 0.533 | +| clip_range | 0.2 | +| entropy_loss | -0.46 | +| explained_variance | -1.45 | +| learning_rate | 0.0001 | +| loss | -0.0992 | +| n_updates | 110440 | +| policy_gradient_loss | -0.0768 | +| value_loss | 0.000324 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.29e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 309 | +| iterations | 4993 | +| time_elapsed | 16502 | +| total_timesteps | 5112832 | +| train/ | | +| approx_kl | 1.6782341 | +| clip_fraction | 0.479 | +| clip_range | 0.2 | +| entropy_loss | -0.436 | +| explained_variance | -0.71 | +| learning_rate | 0.0001 | +| loss | -0.0826 | +| n_updates | 110450 | +| policy_gradient_loss | -0.0653 | +| value_loss | 0.000268 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.3e+03 | +| ep_rew_mean | 0.295 | +| time/ | | +| fps | 309 | +| iterations | 4994 | +| time_elapsed | 16506 | +| total_timesteps | 5113856 | +| train/ | | +| approx_kl | 1.6082404 | +| clip_fraction | 0.5 | +| clip_range | 0.2 | +| entropy_loss | -0.425 | +| explained_variance | -2.13 | +| learning_rate | 0.0001 | +| loss | -0.0944 | +| n_updates | 110460 | +| policy_gradient_loss | -0.0679 | +| value_loss | 0.000417 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.3e+03 | +| ep_rew_mean | 0.295 | +| time/ | | +| fps | 309 | +| iterations | 4995 | +| time_elapsed | 16509 | +| total_timesteps | 5114880 | +| train/ | | +| approx_kl | 2.1630101 | +| clip_fraction | 0.498 | +| clip_range | 0.2 | +| entropy_loss | -0.448 | +| explained_variance | -1.81 | +| learning_rate | 0.0001 | +| loss | -0.0828 | +| n_updates | 110470 | +| policy_gradient_loss | -0.0683 | +| value_loss | 0.000365 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.3e+03 | +| ep_rew_mean | 0.295 | +| time/ | | +| fps | 309 | +| iterations | 4996 | +| time_elapsed | 16512 | +| total_timesteps | 5115904 | +| train/ | | +| approx_kl | 1.5628966 | +| clip_fraction | 0.512 | +| clip_range | 0.2 | +| entropy_loss | -0.53 | +| explained_variance | -0.392 | +| learning_rate | 0.0001 | +| loss | -0.0673 | +| n_updates | 110480 | +| policy_gradient_loss | -0.0657 | +| value_loss | 0.000528 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.3e+03 | +| ep_rew_mean | 0.295 | +| time/ | | +| fps | 309 | +| iterations | 4997 | +| time_elapsed | 16515 | +| total_timesteps | 5116928 | +| train/ | | +| approx_kl | 1.8322191 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.414 | +| explained_variance | -1.85 | +| learning_rate | 0.0001 | +| loss | -0.0946 | +| n_updates | 110490 | +| policy_gradient_loss | -0.0699 | +| value_loss | 0.000533 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.31e+03 | +| ep_rew_mean | 0.291 | +| time/ | | +| fps | 309 | +| iterations | 4998 | +| time_elapsed | 16519 | +| total_timesteps | 5117952 | +| train/ | | +| approx_kl | 1.8757019 | +| clip_fraction | 0.494 | +| clip_range | 0.2 | +| entropy_loss | -0.387 | +| explained_variance | -2.16 | +| learning_rate | 0.0001 | +| loss | -0.1 | +| n_updates | 110500 | +| policy_gradient_loss | -0.0707 | +| value_loss | 0.000492 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.31e+03 | +| ep_rew_mean | 0.291 | +| time/ | | +| fps | 309 | +| iterations | 4999 | +| time_elapsed | 16522 | +| total_timesteps | 5118976 | +| train/ | | +| approx_kl | 1.847437 | +| clip_fraction | 0.534 | +| clip_range | 0.2 | +| entropy_loss | -0.475 | +| explained_variance | -2.04 | +| learning_rate | 0.0001 | +| loss | -0.0844 | +| n_updates | 110510 | +| policy_gradient_loss | -0.0702 | +| value_loss | 0.000312 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.31e+03 | +| ep_rew_mean | 0.291 | +| time/ | | +| fps | 309 | +| iterations | 5000 | +| time_elapsed | 16525 | +| total_timesteps | 5120000 | +| train/ | | +| approx_kl | 1.8912055 | +| clip_fraction | 0.52 | +| clip_range | 0.2 | +| entropy_loss | -0.489 | +| explained_variance | -1.21 | +| learning_rate | 0.0001 | +| loss | -0.0968 | +| n_updates | 110520 | +| policy_gradient_loss | -0.0702 | +| value_loss | 0.000261 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.31e+03 | +| ep_rew_mean | 0.293 | +| time/ | | +| fps | 309 | +| iterations | 5001 | +| time_elapsed | 16528 | +| total_timesteps | 5121024 | +| train/ | | +| approx_kl | 2.2355318 | +| clip_fraction | 0.514 | +| clip_range | 0.2 | +| entropy_loss | -0.477 | +| explained_variance | -5.55 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 110530 | +| policy_gradient_loss | -0.0687 | +| value_loss | 0.000295 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.31e+03 | +| ep_rew_mean | 0.293 | +| time/ | | +| fps | 309 | +| iterations | 5002 | +| time_elapsed | 16531 | +| total_timesteps | 5122048 | +| train/ | | +| approx_kl | 1.4721925 | +| clip_fraction | 0.499 | +| clip_range | 0.2 | +| entropy_loss | -0.436 | +| explained_variance | -2.42 | +| learning_rate | 0.0001 | +| loss | -0.116 | +| n_updates | 110540 | +| policy_gradient_loss | -0.0748 | +| value_loss | 0.000255 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.33e+03 | +| ep_rew_mean | 0.29 | +| time/ | | +| fps | 309 | +| iterations | 5003 | +| time_elapsed | 16534 | +| total_timesteps | 5123072 | +| train/ | | +| approx_kl | 5.120365 | +| clip_fraction | 0.505 | +| clip_range | 0.2 | +| entropy_loss | -0.447 | +| explained_variance | -0.583 | +| learning_rate | 0.0001 | +| loss | -0.082 | +| n_updates | 110550 | +| policy_gradient_loss | -0.0634 | +| value_loss | 0.000619 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.33e+03 | +| ep_rew_mean | 0.29 | +| time/ | | +| fps | 309 | +| iterations | 5004 | +| time_elapsed | 16537 | +| total_timesteps | 5124096 | +| train/ | | +| approx_kl | 1.6604743 | +| clip_fraction | 0.478 | +| clip_range | 0.2 | +| entropy_loss | -0.421 | +| explained_variance | -0.522 | +| learning_rate | 0.0001 | +| loss | -0.1 | +| n_updates | 110560 | +| policy_gradient_loss | -0.068 | +| value_loss | 0.000622 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.33e+03 | +| ep_rew_mean | 0.29 | +| time/ | | +| fps | 309 | +| iterations | 5005 | +| time_elapsed | 16541 | +| total_timesteps | 5125120 | +| train/ | | +| approx_kl | 1.8672051 | +| clip_fraction | 0.485 | +| clip_range | 0.2 | +| entropy_loss | -0.425 | +| explained_variance | -1.1 | +| learning_rate | 0.0001 | +| loss | -0.0757 | +| n_updates | 110570 | +| policy_gradient_loss | -0.0649 | +| value_loss | 0.000456 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.34e+03 | +| ep_rew_mean | 0.289 | +| time/ | | +| fps | 309 | +| iterations | 5006 | +| time_elapsed | 16544 | +| total_timesteps | 5126144 | +| train/ | | +| approx_kl | 5.17336 | +| clip_fraction | 0.506 | +| clip_range | 0.2 | +| entropy_loss | -0.472 | +| explained_variance | -3.25 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 110580 | +| policy_gradient_loss | -0.069 | +| value_loss | 0.000219 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.34e+03 | +| ep_rew_mean | 0.289 | +| time/ | | +| fps | 309 | +| iterations | 5007 | +| time_elapsed | 16548 | +| total_timesteps | 5127168 | +| train/ | | +| approx_kl | 1.4871206 | +| clip_fraction | 0.502 | +| clip_range | 0.2 | +| entropy_loss | -0.45 | +| explained_variance | -0.69 | +| learning_rate | 0.0001 | +| loss | -0.111 | +| n_updates | 110590 | +| policy_gradient_loss | -0.0745 | +| value_loss | 0.000354 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.34e+03 | +| ep_rew_mean | 0.289 | +| time/ | | +| fps | 309 | +| iterations | 5008 | +| time_elapsed | 16551 | +| total_timesteps | 5128192 | +| train/ | | +| approx_kl | 1.6798245 | +| clip_fraction | 0.541 | +| clip_range | 0.2 | +| entropy_loss | -0.51 | +| explained_variance | -1.99 | +| learning_rate | 0.0001 | +| loss | -0.0532 | +| n_updates | 110600 | +| policy_gradient_loss | -0.0706 | +| value_loss | 0.000612 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.35e+03 | +| ep_rew_mean | 0.288 | +| time/ | | +| fps | 309 | +| iterations | 5009 | +| time_elapsed | 16555 | +| total_timesteps | 5129216 | +| train/ | | +| approx_kl | 2.3946366 | +| clip_fraction | 0.518 | +| clip_range | 0.2 | +| entropy_loss | -0.419 | +| explained_variance | -5.61 | +| learning_rate | 0.0001 | +| loss | -0.095 | +| n_updates | 110610 | +| policy_gradient_loss | -0.0802 | +| value_loss | 0.000387 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.35e+03 | +| ep_rew_mean | 0.288 | +| time/ | | +| fps | 309 | +| iterations | 5010 | +| time_elapsed | 16558 | +| total_timesteps | 5130240 | +| train/ | | +| approx_kl | 1.6597297 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.404 | +| explained_variance | -1.19 | +| learning_rate | 0.0001 | +| loss | -0.107 | +| n_updates | 110620 | +| policy_gradient_loss | -0.0682 | +| value_loss | 0.000481 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.35e+03 | +| ep_rew_mean | 0.288 | +| time/ | | +| fps | 309 | +| iterations | 5011 | +| time_elapsed | 16562 | +| total_timesteps | 5131264 | +| train/ | | +| approx_kl | 4.415105 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.414 | +| explained_variance | -1.06 | +| learning_rate | 0.0001 | +| loss | -0.0904 | +| n_updates | 110630 | +| policy_gradient_loss | -0.0693 | +| value_loss | 0.000468 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.36e+03 | +| ep_rew_mean | 0.288 | +| time/ | | +| fps | 309 | +| iterations | 5012 | +| time_elapsed | 16565 | +| total_timesteps | 5132288 | +| train/ | | +| approx_kl | 2.1509542 | +| clip_fraction | 0.502 | +| clip_range | 0.2 | +| entropy_loss | -0.405 | +| explained_variance | -1.78 | +| learning_rate | 0.0001 | +| loss | -0.072 | +| n_updates | 110640 | +| policy_gradient_loss | -0.076 | +| value_loss | 0.000442 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.34e+03 | +| ep_rew_mean | 0.291 | +| time/ | | +| fps | 309 | +| iterations | 5013 | +| time_elapsed | 16569 | +| total_timesteps | 5133312 | +| train/ | | +| approx_kl | 2.3278933 | +| clip_fraction | 0.5 | +| clip_range | 0.2 | +| entropy_loss | -0.441 | +| explained_variance | -2.45 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 110650 | +| policy_gradient_loss | -0.0717 | +| value_loss | 0.000255 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.34e+03 | +| ep_rew_mean | 0.291 | +| time/ | | +| fps | 309 | +| iterations | 5014 | +| time_elapsed | 16572 | +| total_timesteps | 5134336 | +| train/ | | +| approx_kl | 2.0408998 | +| clip_fraction | 0.517 | +| clip_range | 0.2 | +| entropy_loss | -0.426 | +| explained_variance | -0.307 | +| learning_rate | 0.0001 | +| loss | -0.0731 | +| n_updates | 110660 | +| policy_gradient_loss | -0.0643 | +| value_loss | 0.000745 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.34e+03 | +| ep_rew_mean | 0.286 | +| time/ | | +| fps | 309 | +| iterations | 5015 | +| time_elapsed | 16575 | +| total_timesteps | 5135360 | +| train/ | | +| approx_kl | 2.190937 | +| clip_fraction | 0.505 | +| clip_range | 0.2 | +| entropy_loss | -0.437 | +| explained_variance | -4.2 | +| learning_rate | 0.0001 | +| loss | -0.0831 | +| n_updates | 110670 | +| policy_gradient_loss | -0.0753 | +| value_loss | 0.000542 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.32e+03 | +| ep_rew_mean | 0.29 | +| time/ | | +| fps | 309 | +| iterations | 5016 | +| time_elapsed | 16578 | +| total_timesteps | 5136384 | +| train/ | | +| approx_kl | 2.150797 | +| clip_fraction | 0.501 | +| clip_range | 0.2 | +| entropy_loss | -0.438 | +| explained_variance | -1.89 | +| learning_rate | 0.0001 | +| loss | -0.0911 | +| n_updates | 110680 | +| policy_gradient_loss | -0.0732 | +| value_loss | 0.00019 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.32e+03 | +| ep_rew_mean | 0.29 | +| time/ | | +| fps | 309 | +| iterations | 5017 | +| time_elapsed | 16582 | +| total_timesteps | 5137408 | +| train/ | | +| approx_kl | 1.9920099 | +| clip_fraction | 0.522 | +| clip_range | 0.2 | +| entropy_loss | -0.469 | +| explained_variance | -0.458 | +| learning_rate | 0.0001 | +| loss | -0.0778 | +| n_updates | 110690 | +| policy_gradient_loss | -0.0632 | +| value_loss | 0.000892 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.32e+03 | +| ep_rew_mean | 0.29 | +| time/ | | +| fps | 309 | +| iterations | 5018 | +| time_elapsed | 16585 | +| total_timesteps | 5138432 | +| train/ | | +| approx_kl | 2.1376166 | +| clip_fraction | 0.497 | +| clip_range | 0.2 | +| entropy_loss | -0.377 | +| explained_variance | -2.84 | +| learning_rate | 0.0001 | +| loss | -0.0718 | +| n_updates | 110700 | +| policy_gradient_loss | -0.0759 | +| value_loss | 0.000728 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.33e+03 | +| ep_rew_mean | 0.291 | +| time/ | | +| fps | 309 | +| iterations | 5019 | +| time_elapsed | 16588 | +| total_timesteps | 5139456 | +| train/ | | +| approx_kl | 2.0487618 | +| clip_fraction | 0.484 | +| clip_range | 0.2 | +| entropy_loss | -0.444 | +| explained_variance | -9.18 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 110710 | +| policy_gradient_loss | -0.0741 | +| value_loss | 0.000395 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.33e+03 | +| ep_rew_mean | 0.291 | +| time/ | | +| fps | 309 | +| iterations | 5020 | +| time_elapsed | 16591 | +| total_timesteps | 5140480 | +| train/ | | +| approx_kl | 2.078298 | +| clip_fraction | 0.486 | +| clip_range | 0.2 | +| entropy_loss | -0.368 | +| explained_variance | -0.903 | +| learning_rate | 0.0001 | +| loss | -0.084 | +| n_updates | 110720 | +| policy_gradient_loss | -0.0594 | +| value_loss | 0.000481 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.33e+03 | +| ep_rew_mean | 0.291 | +| time/ | | +| fps | 309 | +| iterations | 5021 | +| time_elapsed | 16595 | +| total_timesteps | 5141504 | +| train/ | | +| approx_kl | 2.1180813 | +| clip_fraction | 0.511 | +| clip_range | 0.2 | +| entropy_loss | -0.42 | +| explained_variance | -3.87 | +| learning_rate | 0.0001 | +| loss | -0.0797 | +| n_updates | 110730 | +| policy_gradient_loss | -0.0753 | +| value_loss | 0.000316 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.34e+03 | +| ep_rew_mean | 0.293 | +| time/ | | +| fps | 309 | +| iterations | 5022 | +| time_elapsed | 16598 | +| total_timesteps | 5142528 | +| train/ | | +| approx_kl | 2.043044 | +| clip_fraction | 0.476 | +| clip_range | 0.2 | +| entropy_loss | -0.418 | +| explained_variance | -3.56 | +| learning_rate | 0.0001 | +| loss | -0.0797 | +| n_updates | 110740 | +| policy_gradient_loss | -0.0702 | +| value_loss | 0.000267 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.34e+03 | +| ep_rew_mean | 0.293 | +| time/ | | +| fps | 309 | +| iterations | 5023 | +| time_elapsed | 16601 | +| total_timesteps | 5143552 | +| train/ | | +| approx_kl | 2.2109249 | +| clip_fraction | 0.494 | +| clip_range | 0.2 | +| entropy_loss | -0.422 | +| explained_variance | -0.74 | +| learning_rate | 0.0001 | +| loss | -0.0938 | +| n_updates | 110750 | +| policy_gradient_loss | -0.0653 | +| value_loss | 0.000229 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.34e+03 | +| ep_rew_mean | 0.293 | +| time/ | | +| fps | 309 | +| iterations | 5024 | +| time_elapsed | 16604 | +| total_timesteps | 5144576 | +| train/ | | +| approx_kl | 1.7024366 | +| clip_fraction | 0.482 | +| clip_range | 0.2 | +| entropy_loss | -0.43 | +| explained_variance | -1.22 | +| learning_rate | 0.0001 | +| loss | -0.107 | +| n_updates | 110760 | +| policy_gradient_loss | -0.07 | +| value_loss | 0.000269 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.34e+03 | +| ep_rew_mean | 0.293 | +| time/ | | +| fps | 309 | +| iterations | 5025 | +| time_elapsed | 16608 | +| total_timesteps | 5145600 | +| train/ | | +| approx_kl | 2.8915126 | +| clip_fraction | 0.514 | +| clip_range | 0.2 | +| entropy_loss | -0.398 | +| explained_variance | -1.38 | +| learning_rate | 0.0001 | +| loss | -0.0657 | +| n_updates | 110770 | +| policy_gradient_loss | -0.0648 | +| value_loss | 0.00062 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.34e+03 | +| ep_rew_mean | 0.293 | +| time/ | | +| fps | 309 | +| iterations | 5026 | +| time_elapsed | 16611 | +| total_timesteps | 5146624 | +| train/ | | +| approx_kl | 2.2484748 | +| clip_fraction | 0.451 | +| clip_range | 0.2 | +| entropy_loss | -0.366 | +| explained_variance | -2.24 | +| learning_rate | 0.0001 | +| loss | -0.0951 | +| n_updates | 110780 | +| policy_gradient_loss | -0.0649 | +| value_loss | 0.000401 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.34e+03 | +| ep_rew_mean | 0.293 | +| time/ | | +| fps | 309 | +| iterations | 5027 | +| time_elapsed | 16615 | +| total_timesteps | 5147648 | +| train/ | | +| approx_kl | 2.0053885 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.359 | +| explained_variance | -2.59 | +| learning_rate | 0.0001 | +| loss | -0.0703 | +| n_updates | 110790 | +| policy_gradient_loss | -0.0706 | +| value_loss | 0.000441 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.35e+03 | +| ep_rew_mean | 0.293 | +| time/ | | +| fps | 309 | +| iterations | 5028 | +| time_elapsed | 16618 | +| total_timesteps | 5148672 | +| train/ | | +| approx_kl | 1.540638 | +| clip_fraction | 0.505 | +| clip_range | 0.2 | +| entropy_loss | -0.428 | +| explained_variance | -1.97 | +| learning_rate | 0.0001 | +| loss | -0.106 | +| n_updates | 110800 | +| policy_gradient_loss | -0.0565 | +| value_loss | 0.000574 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.35e+03 | +| ep_rew_mean | 0.293 | +| time/ | | +| fps | 309 | +| iterations | 5029 | +| time_elapsed | 16622 | +| total_timesteps | 5149696 | +| train/ | | +| approx_kl | 2.2759938 | +| clip_fraction | 0.499 | +| clip_range | 0.2 | +| entropy_loss | -0.392 | +| explained_variance | -5.45 | +| learning_rate | 0.0001 | +| loss | -0.098 | +| n_updates | 110810 | +| policy_gradient_loss | -0.0726 | +| value_loss | 0.0002 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.35e+03 | +| ep_rew_mean | 0.293 | +| time/ | | +| fps | 309 | +| iterations | 5030 | +| time_elapsed | 16625 | +| total_timesteps | 5150720 | +| train/ | | +| approx_kl | 1.7307594 | +| clip_fraction | 0.5 | +| clip_range | 0.2 | +| entropy_loss | -0.412 | +| explained_variance | -1.25 | +| learning_rate | 0.0001 | +| loss | -0.0983 | +| n_updates | 110820 | +| policy_gradient_loss | -0.0715 | +| value_loss | 0.00044 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.35e+03 | +| ep_rew_mean | 0.295 | +| time/ | | +| fps | 309 | +| iterations | 5031 | +| time_elapsed | 16628 | +| total_timesteps | 5151744 | +| train/ | | +| approx_kl | 1.6655055 | +| clip_fraction | 0.512 | +| clip_range | 0.2 | +| entropy_loss | -0.428 | +| explained_variance | -3.18 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 110830 | +| policy_gradient_loss | -0.0659 | +| value_loss | 0.000488 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.35e+03 | +| ep_rew_mean | 0.295 | +| time/ | | +| fps | 309 | +| iterations | 5032 | +| time_elapsed | 16632 | +| total_timesteps | 5152768 | +| train/ | | +| approx_kl | 1.7405703 | +| clip_fraction | 0.451 | +| clip_range | 0.2 | +| entropy_loss | -0.378 | +| explained_variance | -5.16 | +| learning_rate | 0.0001 | +| loss | -0.0936 | +| n_updates | 110840 | +| policy_gradient_loss | -0.0665 | +| value_loss | 0.000407 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.35e+03 | +| ep_rew_mean | 0.295 | +| time/ | | +| fps | 309 | +| iterations | 5033 | +| time_elapsed | 16635 | +| total_timesteps | 5153792 | +| train/ | | +| approx_kl | 1.9150529 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.416 | +| explained_variance | -1.34 | +| learning_rate | 0.0001 | +| loss | -0.115 | +| n_updates | 110850 | +| policy_gradient_loss | -0.0738 | +| value_loss | 0.000445 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.37e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 309 | +| iterations | 5034 | +| time_elapsed | 16638 | +| total_timesteps | 5154816 | +| train/ | | +| approx_kl | 2.985312 | +| clip_fraction | 0.51 | +| clip_range | 0.2 | +| entropy_loss | -0.437 | +| explained_variance | -1.65 | +| learning_rate | 0.0001 | +| loss | -0.0914 | +| n_updates | 110860 | +| policy_gradient_loss | -0.0752 | +| value_loss | 0.000407 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.37e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 309 | +| iterations | 5035 | +| time_elapsed | 16641 | +| total_timesteps | 5155840 | +| train/ | | +| approx_kl | 1.7837403 | +| clip_fraction | 0.445 | +| clip_range | 0.2 | +| entropy_loss | -0.367 | +| explained_variance | -5.49 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 110870 | +| policy_gradient_loss | -0.0693 | +| value_loss | 0.000118 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.37e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 309 | +| iterations | 5036 | +| time_elapsed | 16644 | +| total_timesteps | 5156864 | +| train/ | | +| approx_kl | 2.7028077 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.404 | +| explained_variance | -3.2 | +| learning_rate | 0.0001 | +| loss | -0.105 | +| n_updates | 110880 | +| policy_gradient_loss | -0.0744 | +| value_loss | 0.000106 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.38e+03 | +| ep_rew_mean | 0.29 | +| time/ | | +| fps | 309 | +| iterations | 5037 | +| time_elapsed | 16647 | +| total_timesteps | 5157888 | +| train/ | | +| approx_kl | 2.1238492 | +| clip_fraction | 0.514 | +| clip_range | 0.2 | +| entropy_loss | -0.513 | +| explained_variance | -3.83 | +| learning_rate | 0.0001 | +| loss | -0.0981 | +| n_updates | 110890 | +| policy_gradient_loss | -0.0765 | +| value_loss | 7.68e-05 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.38e+03 | +| ep_rew_mean | 0.29 | +| time/ | | +| fps | 309 | +| iterations | 5038 | +| time_elapsed | 16651 | +| total_timesteps | 5158912 | +| train/ | | +| approx_kl | 1.5788031 | +| clip_fraction | 0.424 | +| clip_range | 0.2 | +| entropy_loss | -0.347 | +| explained_variance | -0.264 | +| learning_rate | 0.0001 | +| loss | -0.0726 | +| n_updates | 110900 | +| policy_gradient_loss | -0.0533 | +| value_loss | 0.000403 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.37e+03 | +| ep_rew_mean | 0.287 | +| time/ | | +| fps | 309 | +| iterations | 5039 | +| time_elapsed | 16654 | +| total_timesteps | 5159936 | +| train/ | | +| approx_kl | 3.2467723 | +| clip_fraction | 0.502 | +| clip_range | 0.2 | +| entropy_loss | -0.434 | +| explained_variance | -2.36 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 110910 | +| policy_gradient_loss | -0.073 | +| value_loss | 0.000453 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.37e+03 | +| ep_rew_mean | 0.287 | +| time/ | | +| fps | 309 | +| iterations | 5040 | +| time_elapsed | 16657 | +| total_timesteps | 5160960 | +| train/ | | +| approx_kl | 1.66097 | +| clip_fraction | 0.472 | +| clip_range | 0.2 | +| entropy_loss | -0.378 | +| explained_variance | -1.23 | +| learning_rate | 0.0001 | +| loss | -0.112 | +| n_updates | 110920 | +| policy_gradient_loss | -0.0648 | +| value_loss | 0.000666 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.37e+03 | +| ep_rew_mean | 0.287 | +| time/ | | +| fps | 309 | +| iterations | 5041 | +| time_elapsed | 16660 | +| total_timesteps | 5161984 | +| train/ | | +| approx_kl | 3.1851554 | +| clip_fraction | 0.484 | +| clip_range | 0.2 | +| entropy_loss | -0.362 | +| explained_variance | -2.63 | +| learning_rate | 0.0001 | +| loss | -0.0731 | +| n_updates | 110930 | +| policy_gradient_loss | -0.064 | +| value_loss | 0.000637 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.37e+03 | +| ep_rew_mean | 0.287 | +| time/ | | +| fps | 309 | +| iterations | 5042 | +| time_elapsed | 16664 | +| total_timesteps | 5163008 | +| train/ | | +| approx_kl | 2.5358396 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.4 | +| explained_variance | -1.13 | +| learning_rate | 0.0001 | +| loss | -0.0691 | +| n_updates | 110940 | +| policy_gradient_loss | -0.066 | +| value_loss | 0.000557 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.37e+03 | +| ep_rew_mean | 0.287 | +| time/ | | +| fps | 309 | +| iterations | 5043 | +| time_elapsed | 16667 | +| total_timesteps | 5164032 | +| train/ | | +| approx_kl | 2.3356977 | +| clip_fraction | 0.508 | +| clip_range | 0.2 | +| entropy_loss | -0.437 | +| explained_variance | -6.16 | +| learning_rate | 0.0001 | +| loss | -0.0902 | +| n_updates | 110950 | +| policy_gradient_loss | -0.0724 | +| value_loss | 0.000307 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.38e+03 | +| ep_rew_mean | 0.284 | +| time/ | | +| fps | 309 | +| iterations | 5044 | +| time_elapsed | 16671 | +| total_timesteps | 5165056 | +| train/ | | +| approx_kl | 9.599107 | +| clip_fraction | 0.506 | +| clip_range | 0.2 | +| entropy_loss | -0.431 | +| explained_variance | -1.89 | +| learning_rate | 0.0001 | +| loss | -0.108 | +| n_updates | 110960 | +| policy_gradient_loss | -0.0759 | +| value_loss | 0.000524 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.38e+03 | +| ep_rew_mean | 0.284 | +| time/ | | +| fps | 309 | +| iterations | 5045 | +| time_elapsed | 16674 | +| total_timesteps | 5166080 | +| train/ | | +| approx_kl | 2.1295576 | +| clip_fraction | 0.486 | +| clip_range | 0.2 | +| entropy_loss | -0.394 | +| explained_variance | -10.2 | +| learning_rate | 0.0001 | +| loss | -0.0941 | +| n_updates | 110970 | +| policy_gradient_loss | -0.0711 | +| value_loss | 0.000301 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.38e+03 | +| ep_rew_mean | 0.284 | +| time/ | | +| fps | 309 | +| iterations | 5046 | +| time_elapsed | 16678 | +| total_timesteps | 5167104 | +| train/ | | +| approx_kl | 2.080956 | +| clip_fraction | 0.515 | +| clip_range | 0.2 | +| entropy_loss | -0.418 | +| explained_variance | -0.826 | +| learning_rate | 0.0001 | +| loss | -0.105 | +| n_updates | 110980 | +| policy_gradient_loss | -0.0771 | +| value_loss | 0.000418 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.38e+03 | +| ep_rew_mean | 0.28 | +| time/ | | +| fps | 309 | +| iterations | 5047 | +| time_elapsed | 16681 | +| total_timesteps | 5168128 | +| train/ | | +| approx_kl | 1.8270695 | +| clip_fraction | 0.52 | +| clip_range | 0.2 | +| entropy_loss | -0.484 | +| explained_variance | -5.16 | +| learning_rate | 0.0001 | +| loss | -0.0885 | +| n_updates | 110990 | +| policy_gradient_loss | -0.0746 | +| value_loss | 0.000309 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.38e+03 | +| ep_rew_mean | 0.28 | +| time/ | | +| fps | 309 | +| iterations | 5048 | +| time_elapsed | 16685 | +| total_timesteps | 5169152 | +| train/ | | +| approx_kl | 1.5163207 | +| clip_fraction | 0.478 | +| clip_range | 0.2 | +| entropy_loss | -0.45 | +| explained_variance | -1.83 | +| learning_rate | 0.0001 | +| loss | -0.0899 | +| n_updates | 111000 | +| policy_gradient_loss | -0.0547 | +| value_loss | 0.000128 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.38e+03 | +| ep_rew_mean | 0.28 | +| time/ | | +| fps | 309 | +| iterations | 5049 | +| time_elapsed | 16688 | +| total_timesteps | 5170176 | +| train/ | | +| approx_kl | 2.0121775 | +| clip_fraction | 0.541 | +| clip_range | 0.2 | +| entropy_loss | -0.459 | +| explained_variance | -0.905 | +| learning_rate | 0.0001 | +| loss | -0.0995 | +| n_updates | 111010 | +| policy_gradient_loss | -0.0731 | +| value_loss | 0.000568 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.38e+03 | +| ep_rew_mean | 0.277 | +| time/ | | +| fps | 309 | +| iterations | 5050 | +| time_elapsed | 16691 | +| total_timesteps | 5171200 | +| train/ | | +| approx_kl | 2.0255146 | +| clip_fraction | 0.53 | +| clip_range | 0.2 | +| entropy_loss | -0.43 | +| explained_variance | -2.65 | +| learning_rate | 0.0001 | +| loss | -0.111 | +| n_updates | 111020 | +| policy_gradient_loss | -0.0804 | +| value_loss | 0.000621 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.37e+03 | +| ep_rew_mean | 0.273 | +| time/ | | +| fps | 309 | +| iterations | 5051 | +| time_elapsed | 16695 | +| total_timesteps | 5172224 | +| train/ | | +| approx_kl | 2.128619 | +| clip_fraction | 0.465 | +| clip_range | 0.2 | +| entropy_loss | -0.444 | +| explained_variance | -2.36 | +| learning_rate | 0.0001 | +| loss | -0.0943 | +| n_updates | 111030 | +| policy_gradient_loss | -0.0751 | +| value_loss | 0.000261 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.37e+03 | +| ep_rew_mean | 0.273 | +| time/ | | +| fps | 309 | +| iterations | 5052 | +| time_elapsed | 16698 | +| total_timesteps | 5173248 | +| train/ | | +| approx_kl | 1.6537745 | +| clip_fraction | 0.498 | +| clip_range | 0.2 | +| entropy_loss | -0.484 | +| explained_variance | -1.54 | +| learning_rate | 0.0001 | +| loss | -0.0869 | +| n_updates | 111040 | +| policy_gradient_loss | -0.0639 | +| value_loss | 0.000271 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.37e+03 | +| ep_rew_mean | 0.273 | +| time/ | | +| fps | 309 | +| iterations | 5053 | +| time_elapsed | 16701 | +| total_timesteps | 5174272 | +| train/ | | +| approx_kl | 2.6392462 | +| clip_fraction | 0.527 | +| clip_range | 0.2 | +| entropy_loss | -0.44 | +| explained_variance | -1.16 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 111050 | +| policy_gradient_loss | -0.072 | +| value_loss | 0.000597 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.38e+03 | +| ep_rew_mean | 0.271 | +| time/ | | +| fps | 309 | +| iterations | 5054 | +| time_elapsed | 16704 | +| total_timesteps | 5175296 | +| train/ | | +| approx_kl | 1.6706045 | +| clip_fraction | 0.489 | +| clip_range | 0.2 | +| entropy_loss | -0.486 | +| explained_variance | -1.66 | +| learning_rate | 0.0001 | +| loss | -0.0921 | +| n_updates | 111060 | +| policy_gradient_loss | -0.0717 | +| value_loss | 0.000369 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.38e+03 | +| ep_rew_mean | 0.271 | +| time/ | | +| fps | 309 | +| iterations | 5055 | +| time_elapsed | 16707 | +| total_timesteps | 5176320 | +| train/ | | +| approx_kl | 2.1433535 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.455 | +| explained_variance | -1 | +| learning_rate | 0.0001 | +| loss | -0.0704 | +| n_updates | 111070 | +| policy_gradient_loss | -0.0624 | +| value_loss | 0.000325 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.36e+03 | +| ep_rew_mean | 0.272 | +| time/ | | +| fps | 309 | +| iterations | 5056 | +| time_elapsed | 16711 | +| total_timesteps | 5177344 | +| train/ | | +| approx_kl | 2.0925531 | +| clip_fraction | 0.519 | +| clip_range | 0.2 | +| entropy_loss | -0.471 | +| explained_variance | -0.813 | +| learning_rate | 0.0001 | +| loss | -0.0702 | +| n_updates | 111080 | +| policy_gradient_loss | -0.0666 | +| value_loss | 0.000439 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.34e+03 | +| ep_rew_mean | 0.274 | +| time/ | | +| fps | 309 | +| iterations | 5057 | +| time_elapsed | 16714 | +| total_timesteps | 5178368 | +| train/ | | +| approx_kl | 1.7293315 | +| clip_fraction | 0.47 | +| clip_range | 0.2 | +| entropy_loss | -0.4 | +| explained_variance | -0.706 | +| learning_rate | 0.0001 | +| loss | -0.0843 | +| n_updates | 111090 | +| policy_gradient_loss | -0.0615 | +| value_loss | 0.000634 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.34e+03 | +| ep_rew_mean | 0.274 | +| time/ | | +| fps | 309 | +| iterations | 5058 | +| time_elapsed | 16717 | +| total_timesteps | 5179392 | +| train/ | | +| approx_kl | 1.5735393 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.404 | +| explained_variance | -1.29 | +| learning_rate | 0.0001 | +| loss | -0.0983 | +| n_updates | 111100 | +| policy_gradient_loss | -0.0707 | +| value_loss | 0.000595 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.33e+03 | +| ep_rew_mean | 0.271 | +| time/ | | +| fps | 309 | +| iterations | 5059 | +| time_elapsed | 16720 | +| total_timesteps | 5180416 | +| train/ | | +| approx_kl | 2.0821247 | +| clip_fraction | 0.505 | +| clip_range | 0.2 | +| entropy_loss | -0.42 | +| explained_variance | -2.84 | +| learning_rate | 0.0001 | +| loss | -0.0942 | +| n_updates | 111110 | +| policy_gradient_loss | -0.074 | +| value_loss | 0.000388 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.33e+03 | +| ep_rew_mean | 0.271 | +| time/ | | +| fps | 309 | +| iterations | 5060 | +| time_elapsed | 16724 | +| total_timesteps | 5181440 | +| train/ | | +| approx_kl | 1.5809307 | +| clip_fraction | 0.459 | +| clip_range | 0.2 | +| entropy_loss | -0.399 | +| explained_variance | -2.62 | +| learning_rate | 0.0001 | +| loss | -0.0636 | +| n_updates | 111120 | +| policy_gradient_loss | -0.0676 | +| value_loss | 0.000267 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.33e+03 | +| ep_rew_mean | 0.271 | +| time/ | | +| fps | 309 | +| iterations | 5061 | +| time_elapsed | 16727 | +| total_timesteps | 5182464 | +| train/ | | +| approx_kl | 2.1489363 | +| clip_fraction | 0.537 | +| clip_range | 0.2 | +| entropy_loss | -0.477 | +| explained_variance | -1.1 | +| learning_rate | 0.0001 | +| loss | -0.091 | +| n_updates | 111130 | +| policy_gradient_loss | -0.0813 | +| value_loss | 0.000347 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.35e+03 | +| ep_rew_mean | 0.271 | +| time/ | | +| fps | 309 | +| iterations | 5062 | +| time_elapsed | 16730 | +| total_timesteps | 5183488 | +| train/ | | +| approx_kl | 1.4908476 | +| clip_fraction | 0.527 | +| clip_range | 0.2 | +| entropy_loss | -0.547 | +| explained_variance | -4.42 | +| learning_rate | 0.0001 | +| loss | -0.0972 | +| n_updates | 111140 | +| policy_gradient_loss | -0.072 | +| value_loss | 0.00034 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.35e+03 | +| ep_rew_mean | 0.271 | +| time/ | | +| fps | 309 | +| iterations | 5063 | +| time_elapsed | 16734 | +| total_timesteps | 5184512 | +| train/ | | +| approx_kl | 1.8741844 | +| clip_fraction | 0.476 | +| clip_range | 0.2 | +| entropy_loss | -0.393 | +| explained_variance | -1.4 | +| learning_rate | 0.0001 | +| loss | -0.0859 | +| n_updates | 111150 | +| policy_gradient_loss | -0.0644 | +| value_loss | 0.000308 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.33e+03 | +| ep_rew_mean | 0.269 | +| time/ | | +| fps | 309 | +| iterations | 5064 | +| time_elapsed | 16737 | +| total_timesteps | 5185536 | +| train/ | | +| approx_kl | 1.7982147 | +| clip_fraction | 0.489 | +| clip_range | 0.2 | +| entropy_loss | -0.425 | +| explained_variance | -1.84 | +| learning_rate | 0.0001 | +| loss | -0.0745 | +| n_updates | 111160 | +| policy_gradient_loss | -0.0722 | +| value_loss | 0.000504 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.33e+03 | +| ep_rew_mean | 0.269 | +| time/ | | +| fps | 309 | +| iterations | 5065 | +| time_elapsed | 16741 | +| total_timesteps | 5186560 | +| train/ | | +| approx_kl | 1.6241305 | +| clip_fraction | 0.465 | +| clip_range | 0.2 | +| entropy_loss | -0.397 | +| explained_variance | -1.25 | +| learning_rate | 0.0001 | +| loss | -0.0943 | +| n_updates | 111170 | +| policy_gradient_loss | -0.066 | +| value_loss | 0.000771 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.34e+03 | +| ep_rew_mean | 0.271 | +| time/ | | +| fps | 309 | +| iterations | 5066 | +| time_elapsed | 16744 | +| total_timesteps | 5187584 | +| train/ | | +| approx_kl | 1.9362967 | +| clip_fraction | 0.508 | +| clip_range | 0.2 | +| entropy_loss | -0.447 | +| explained_variance | -1.92 | +| learning_rate | 0.0001 | +| loss | -0.0891 | +| n_updates | 111180 | +| policy_gradient_loss | -0.0684 | +| value_loss | 0.00067 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.34e+03 | +| ep_rew_mean | 0.271 | +| time/ | | +| fps | 309 | +| iterations | 5067 | +| time_elapsed | 16747 | +| total_timesteps | 5188608 | +| train/ | | +| approx_kl | 2.0654798 | +| clip_fraction | 0.484 | +| clip_range | 0.2 | +| entropy_loss | -0.404 | +| explained_variance | -1.79 | +| learning_rate | 0.0001 | +| loss | -0.0705 | +| n_updates | 111190 | +| policy_gradient_loss | -0.0638 | +| value_loss | 0.000372 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.35e+03 | +| ep_rew_mean | 0.267 | +| time/ | | +| fps | 309 | +| iterations | 5068 | +| time_elapsed | 16751 | +| total_timesteps | 5189632 | +| train/ | | +| approx_kl | 2.0299 | +| clip_fraction | 0.505 | +| clip_range | 0.2 | +| entropy_loss | -0.396 | +| explained_variance | -2.95 | +| learning_rate | 0.0001 | +| loss | -0.0637 | +| n_updates | 111200 | +| policy_gradient_loss | -0.0718 | +| value_loss | 0.000556 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.35e+03 | +| ep_rew_mean | 0.267 | +| time/ | | +| fps | 309 | +| iterations | 5069 | +| time_elapsed | 16754 | +| total_timesteps | 5190656 | +| train/ | | +| approx_kl | 1.9036882 | +| clip_fraction | 0.491 | +| clip_range | 0.2 | +| entropy_loss | -0.404 | +| explained_variance | -1.15 | +| learning_rate | 0.0001 | +| loss | -0.0851 | +| n_updates | 111210 | +| policy_gradient_loss | -0.0696 | +| value_loss | 0.000371 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.35e+03 | +| ep_rew_mean | 0.267 | +| time/ | | +| fps | 309 | +| iterations | 5070 | +| time_elapsed | 16757 | +| total_timesteps | 5191680 | +| train/ | | +| approx_kl | 2.1752107 | +| clip_fraction | 0.529 | +| clip_range | 0.2 | +| entropy_loss | -0.447 | +| explained_variance | -1.35 | +| learning_rate | 0.0001 | +| loss | -0.113 | +| n_updates | 111220 | +| policy_gradient_loss | -0.0725 | +| value_loss | 0.000368 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.35e+03 | +| ep_rew_mean | 0.271 | +| time/ | | +| fps | 309 | +| iterations | 5071 | +| time_elapsed | 16760 | +| total_timesteps | 5192704 | +| train/ | | +| approx_kl | 1.5177952 | +| clip_fraction | 0.514 | +| clip_range | 0.2 | +| entropy_loss | -0.542 | +| explained_variance | -5.52 | +| learning_rate | 0.0001 | +| loss | -0.121 | +| n_updates | 111230 | +| policy_gradient_loss | -0.0737 | +| value_loss | 0.000223 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.3e+03 | +| ep_rew_mean | 0.272 | +| time/ | | +| fps | 309 | +| iterations | 5072 | +| time_elapsed | 16763 | +| total_timesteps | 5193728 | +| train/ | | +| approx_kl | 2.5940425 | +| clip_fraction | 0.523 | +| clip_range | 0.2 | +| entropy_loss | -0.442 | +| explained_variance | -0.542 | +| learning_rate | 0.0001 | +| loss | -0.0539 | +| n_updates | 111240 | +| policy_gradient_loss | -0.0645 | +| value_loss | 0.000444 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.3e+03 | +| ep_rew_mean | 0.272 | +| time/ | | +| fps | 309 | +| iterations | 5073 | +| time_elapsed | 16767 | +| total_timesteps | 5194752 | +| train/ | | +| approx_kl | 2.06387 | +| clip_fraction | 0.512 | +| clip_range | 0.2 | +| entropy_loss | -0.446 | +| explained_variance | -1.17 | +| learning_rate | 0.0001 | +| loss | -0.1 | +| n_updates | 111250 | +| policy_gradient_loss | -0.0707 | +| value_loss | 0.000519 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.3e+03 | +| ep_rew_mean | 0.272 | +| time/ | | +| fps | 309 | +| iterations | 5074 | +| time_elapsed | 16770 | +| total_timesteps | 5195776 | +| train/ | | +| approx_kl | 1.9543642 | +| clip_fraction | 0.462 | +| clip_range | 0.2 | +| entropy_loss | -0.409 | +| explained_variance | -1.59 | +| learning_rate | 0.0001 | +| loss | -0.093 | +| n_updates | 111260 | +| policy_gradient_loss | -0.0723 | +| value_loss | 0.000381 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.30e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 309 | +| iterations | 5075 | +| time_elapsed | 16773 | +| total_timesteps | 5196800 | +| train/ | | +| approx_kl | 2.5846617 | +| clip_fraction | 0.537 | +| clip_range | 0.2 | +| entropy_loss | -0.446 | +| explained_variance | -1.02 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 111270 | +| policy_gradient_loss | -0.0765 | +| value_loss | 0.000632 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.30e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 309 | +| iterations | 5076 | +| time_elapsed | 16776 | +| total_timesteps | 5197824 | +| train/ | | +| approx_kl | 1.6909757 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.371 | +| explained_variance | -2.64 | +| learning_rate | 0.0001 | +| loss | -0.083 | +| n_updates | 111280 | +| policy_gradient_loss | -0.0642 | +| value_loss | 0.000501 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.31e+03 | +| ep_rew_mean | 0.271 | +| time/ | | +| fps | 309 | +| iterations | 5077 | +| time_elapsed | 16779 | +| total_timesteps | 5198848 | +| train/ | | +| approx_kl | 1.835151 | +| clip_fraction | 0.525 | +| clip_range | 0.2 | +| entropy_loss | -0.463 | +| explained_variance | -1.34 | +| learning_rate | 0.0001 | +| loss | -0.0807 | +| n_updates | 111290 | +| policy_gradient_loss | -0.0798 | +| value_loss | 0.000533 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.31e+03 | +| ep_rew_mean | 0.271 | +| time/ | | +| fps | 309 | +| iterations | 5078 | +| time_elapsed | 16783 | +| total_timesteps | 5199872 | +| train/ | | +| approx_kl | 2.060837 | +| clip_fraction | 0.47 | +| clip_range | 0.2 | +| entropy_loss | -0.366 | +| explained_variance | -3.56 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 111300 | +| policy_gradient_loss | -0.0708 | +| value_loss | 0.000385 | +-------------------------------------- + +Current state: Champion.Level2.RyuVsKen +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.32e+03 | +| ep_rew_mean | 0.268 | +| time/ | | +| fps | 309 | +| iterations | 5079 | +| time_elapsed | 16786 | +| total_timesteps | 5200896 | +| train/ | | +| approx_kl | 2.2283049 | +| clip_fraction | 0.496 | +| clip_range | 0.2 | +| entropy_loss | -0.45 | +| explained_variance | -0.961 | +| learning_rate | 0.0001 | +| loss | -0.0477 | +| n_updates | 111310 | +| policy_gradient_loss | -0.063 | +| value_loss | 0.000439 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.32e+03 | +| ep_rew_mean | 0.268 | +| time/ | | +| fps | 309 | +| iterations | 5080 | +| time_elapsed | 16790 | +| total_timesteps | 5201920 | +| train/ | | +| approx_kl | 2.0012524 | +| clip_fraction | 0.491 | +| clip_range | 0.2 | +| entropy_loss | -0.488 | +| explained_variance | -3.23 | +| learning_rate | 0.0001 | +| loss | -0.0683 | +| n_updates | 111320 | +| policy_gradient_loss | -0.0705 | +| value_loss | 0.000297 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.32e+03 | +| ep_rew_mean | 0.268 | +| time/ | | +| fps | 309 | +| iterations | 5081 | +| time_elapsed | 16793 | +| total_timesteps | 5202944 | +| train/ | | +| approx_kl | 2.3699007 | +| clip_fraction | 0.478 | +| clip_range | 0.2 | +| entropy_loss | -0.331 | +| explained_variance | -1.85 | +| learning_rate | 0.0001 | +| loss | -0.0679 | +| n_updates | 111330 | +| policy_gradient_loss | -0.0632 | +| value_loss | 0.000423 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.32e+03 | +| ep_rew_mean | 0.268 | +| time/ | | +| fps | 309 | +| iterations | 5082 | +| time_elapsed | 16797 | +| total_timesteps | 5203968 | +| train/ | | +| approx_kl | 2.2096972 | +| clip_fraction | 0.512 | +| clip_range | 0.2 | +| entropy_loss | -0.393 | +| explained_variance | -3.44 | +| learning_rate | 0.0001 | +| loss | -0.0966 | +| n_updates | 111340 | +| policy_gradient_loss | -0.0732 | +| value_loss | 0.000705 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.35e+03 | +| ep_rew_mean | 0.264 | +| time/ | | +| fps | 309 | +| iterations | 5083 | +| time_elapsed | 16800 | +| total_timesteps | 5204992 | +| train/ | | +| approx_kl | 2.2602413 | +| clip_fraction | 0.479 | +| clip_range | 0.2 | +| entropy_loss | -0.418 | +| explained_variance | -2.95 | +| learning_rate | 0.0001 | +| loss | -0.0675 | +| n_updates | 111350 | +| policy_gradient_loss | -0.062 | +| value_loss | 0.000351 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.34e+03 | +| ep_rew_mean | 0.265 | +| time/ | | +| fps | 309 | +| iterations | 5084 | +| time_elapsed | 16804 | +| total_timesteps | 5206016 | +| train/ | | +| approx_kl | 2.7011197 | +| clip_fraction | 0.494 | +| clip_range | 0.2 | +| entropy_loss | -0.353 | +| explained_variance | -1.07 | +| learning_rate | 0.0001 | +| loss | -0.095 | +| n_updates | 111360 | +| policy_gradient_loss | -0.0662 | +| value_loss | 0.000633 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.34e+03 | +| ep_rew_mean | 0.265 | +| time/ | | +| fps | 309 | +| iterations | 5085 | +| time_elapsed | 16807 | +| total_timesteps | 5207040 | +| train/ | | +| approx_kl | 3.3471208 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.378 | +| explained_variance | -1.43 | +| learning_rate | 0.0001 | +| loss | -0.0974 | +| n_updates | 111370 | +| policy_gradient_loss | -0.0635 | +| value_loss | 0.00055 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.33e+03 | +| ep_rew_mean | 0.268 | +| time/ | | +| fps | 309 | +| iterations | 5086 | +| time_elapsed | 16810 | +| total_timesteps | 5208064 | +| train/ | | +| approx_kl | 2.1278768 | +| clip_fraction | 0.494 | +| clip_range | 0.2 | +| entropy_loss | -0.385 | +| explained_variance | -1.09 | +| learning_rate | 0.0001 | +| loss | -0.0964 | +| n_updates | 111380 | +| policy_gradient_loss | -0.0693 | +| value_loss | 0.000463 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.33e+03 | +| ep_rew_mean | 0.269 | +| time/ | | +| fps | 309 | +| iterations | 5087 | +| time_elapsed | 16813 | +| total_timesteps | 5209088 | +| train/ | | +| approx_kl | 7.9548693 | +| clip_fraction | 0.477 | +| clip_range | 0.2 | +| entropy_loss | -0.339 | +| explained_variance | -0.917 | +| learning_rate | 0.0001 | +| loss | -0.114 | +| n_updates | 111390 | +| policy_gradient_loss | -0.0711 | +| value_loss | 0.000778 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.33e+03 | +| ep_rew_mean | 0.269 | +| time/ | | +| fps | 309 | +| iterations | 5088 | +| time_elapsed | 16817 | +| total_timesteps | 5210112 | +| train/ | | +| approx_kl | 2.2892356 | +| clip_fraction | 0.457 | +| clip_range | 0.2 | +| entropy_loss | -0.357 | +| explained_variance | -2.6 | +| learning_rate | 0.0001 | +| loss | -0.0927 | +| n_updates | 111400 | +| policy_gradient_loss | -0.0647 | +| value_loss | 0.000674 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.32e+03 | +| ep_rew_mean | 0.271 | +| time/ | | +| fps | 309 | +| iterations | 5089 | +| time_elapsed | 16820 | +| total_timesteps | 5211136 | +| train/ | | +| approx_kl | 2.9256487 | +| clip_fraction | 0.507 | +| clip_range | 0.2 | +| entropy_loss | -0.395 | +| explained_variance | -2.32 | +| learning_rate | 0.0001 | +| loss | -0.0699 | +| n_updates | 111410 | +| policy_gradient_loss | -0.0689 | +| value_loss | 0.000633 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.31e+03 | +| ep_rew_mean | 0.273 | +| time/ | | +| fps | 309 | +| iterations | 5090 | +| time_elapsed | 16823 | +| total_timesteps | 5212160 | +| train/ | | +| approx_kl | 2.7077255 | +| clip_fraction | 0.477 | +| clip_range | 0.2 | +| entropy_loss | -0.323 | +| explained_variance | -1.44 | +| learning_rate | 0.0001 | +| loss | -0.0939 | +| n_updates | 111420 | +| policy_gradient_loss | -0.0688 | +| value_loss | 0.000815 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.31e+03 | +| ep_rew_mean | 0.273 | +| time/ | | +| fps | 309 | +| iterations | 5091 | +| time_elapsed | 16826 | +| total_timesteps | 5213184 | +| train/ | | +| approx_kl | 2.984747 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.329 | +| explained_variance | -4.35 | +| learning_rate | 0.0001 | +| loss | -0.0816 | +| n_updates | 111430 | +| policy_gradient_loss | -0.0699 | +| value_loss | 0.000631 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.31e+03 | +| ep_rew_mean | 0.277 | +| time/ | | +| fps | 309 | +| iterations | 5092 | +| time_elapsed | 16829 | +| total_timesteps | 5214208 | +| train/ | | +| approx_kl | 2.6836128 | +| clip_fraction | 0.497 | +| clip_range | 0.2 | +| entropy_loss | -0.406 | +| explained_variance | -1.17 | +| learning_rate | 0.0001 | +| loss | -0.0806 | +| n_updates | 111440 | +| policy_gradient_loss | -0.0535 | +| value_loss | 0.000505 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.31e+03 | +| ep_rew_mean | 0.277 | +| time/ | | +| fps | 309 | +| iterations | 5093 | +| time_elapsed | 16833 | +| total_timesteps | 5215232 | +| train/ | | +| approx_kl | 2.480369 | +| clip_fraction | 0.461 | +| clip_range | 0.2 | +| entropy_loss | -0.317 | +| explained_variance | -1.31 | +| learning_rate | 0.0001 | +| loss | -0.06 | +| n_updates | 111450 | +| policy_gradient_loss | -0.0622 | +| value_loss | 0.000519 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.31e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 309 | +| iterations | 5094 | +| time_elapsed | 16836 | +| total_timesteps | 5216256 | +| train/ | | +| approx_kl | 1.9492353 | +| clip_fraction | 0.502 | +| clip_range | 0.2 | +| entropy_loss | -0.413 | +| explained_variance | -6.16 | +| learning_rate | 0.0001 | +| loss | -0.0709 | +| n_updates | 111460 | +| policy_gradient_loss | -0.0709 | +| value_loss | 0.00024 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.29e+03 | +| ep_rew_mean | 0.273 | +| time/ | | +| fps | 309 | +| iterations | 5095 | +| time_elapsed | 16839 | +| total_timesteps | 5217280 | +| train/ | | +| approx_kl | 2.3692179 | +| clip_fraction | 0.452 | +| clip_range | 0.2 | +| entropy_loss | -0.316 | +| explained_variance | -1.99 | +| learning_rate | 0.0001 | +| loss | -0.0671 | +| n_updates | 111470 | +| policy_gradient_loss | -0.061 | +| value_loss | 0.0004 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.29e+03 | +| ep_rew_mean | 0.273 | +| time/ | | +| fps | 309 | +| iterations | 5096 | +| time_elapsed | 16842 | +| total_timesteps | 5218304 | +| train/ | | +| approx_kl | 1.8752191 | +| clip_fraction | 0.467 | +| clip_range | 0.2 | +| entropy_loss | -0.409 | +| explained_variance | -1.38 | +| learning_rate | 0.0001 | +| loss | -0.0918 | +| n_updates | 111480 | +| policy_gradient_loss | -0.0639 | +| value_loss | 0.000333 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.29e+03 | +| ep_rew_mean | 0.273 | +| time/ | | +| fps | 309 | +| iterations | 5097 | +| time_elapsed | 16846 | +| total_timesteps | 5219328 | +| train/ | | +| approx_kl | 2.3408012 | +| clip_fraction | 0.476 | +| clip_range | 0.2 | +| entropy_loss | -0.335 | +| explained_variance | -1.27 | +| learning_rate | 0.0001 | +| loss | -0.0854 | +| n_updates | 111490 | +| policy_gradient_loss | -0.0665 | +| value_loss | 0.000786 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.29e+03 | +| ep_rew_mean | 0.272 | +| time/ | | +| fps | 309 | +| iterations | 5098 | +| time_elapsed | 16849 | +| total_timesteps | 5220352 | +| train/ | | +| approx_kl | 2.4245324 | +| clip_fraction | 0.514 | +| clip_range | 0.2 | +| entropy_loss | -0.346 | +| explained_variance | -4.52 | +| learning_rate | 0.0001 | +| loss | -0.0914 | +| n_updates | 111500 | +| policy_gradient_loss | -0.0663 | +| value_loss | 0.00053 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.3e+03 | +| ep_rew_mean | 0.267 | +| time/ | | +| fps | 309 | +| iterations | 5099 | +| time_elapsed | 16853 | +| total_timesteps | 5221376 | +| train/ | | +| approx_kl | 2.9262705 | +| clip_fraction | 0.461 | +| clip_range | 0.2 | +| entropy_loss | -0.355 | +| explained_variance | -1.17 | +| learning_rate | 0.0001 | +| loss | -0.0685 | +| n_updates | 111510 | +| policy_gradient_loss | -0.0617 | +| value_loss | 0.000517 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.3e+03 | +| ep_rew_mean | 0.267 | +| time/ | | +| fps | 309 | +| iterations | 5100 | +| time_elapsed | 16856 | +| total_timesteps | 5222400 | +| train/ | | +| approx_kl | 2.6077693 | +| clip_fraction | 0.456 | +| clip_range | 0.2 | +| entropy_loss | -0.317 | +| explained_variance | -1.05 | +| learning_rate | 0.0001 | +| loss | -0.0845 | +| n_updates | 111520 | +| policy_gradient_loss | -0.0586 | +| value_loss | 0.000585 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.3e+03 | +| ep_rew_mean | 0.267 | +| time/ | | +| fps | 309 | +| iterations | 5101 | +| time_elapsed | 16860 | +| total_timesteps | 5223424 | +| train/ | | +| approx_kl | 2.3111145 | +| clip_fraction | 0.491 | +| clip_range | 0.2 | +| entropy_loss | -0.346 | +| explained_variance | -3.81 | +| learning_rate | 0.0001 | +| loss | -0.0684 | +| n_updates | 111530 | +| policy_gradient_loss | -0.0726 | +| value_loss | 0.000507 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.31e+03 | +| ep_rew_mean | 0.266 | +| time/ | | +| fps | 309 | +| iterations | 5102 | +| time_elapsed | 16863 | +| total_timesteps | 5224448 | +| train/ | | +| approx_kl | 2.8079252 | +| clip_fraction | 0.522 | +| clip_range | 0.2 | +| entropy_loss | -0.383 | +| explained_variance | -2.8 | +| learning_rate | 0.0001 | +| loss | -0.124 | +| n_updates | 111540 | +| policy_gradient_loss | -0.0812 | +| value_loss | 0.000482 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.3e+03 | +| ep_rew_mean | 0.269 | +| time/ | | +| fps | 309 | +| iterations | 5103 | +| time_elapsed | 16866 | +| total_timesteps | 5225472 | +| train/ | | +| approx_kl | 2.4281483 | +| clip_fraction | 0.463 | +| clip_range | 0.2 | +| entropy_loss | -0.318 | +| explained_variance | -2.4 | +| learning_rate | 0.0001 | +| loss | -0.0859 | +| n_updates | 111550 | +| policy_gradient_loss | -0.0694 | +| value_loss | 0.000689 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.3e+03 | +| ep_rew_mean | 0.269 | +| time/ | | +| fps | 309 | +| iterations | 5104 | +| time_elapsed | 16870 | +| total_timesteps | 5226496 | +| train/ | | +| approx_kl | 2.5699801 | +| clip_fraction | 0.451 | +| clip_range | 0.2 | +| entropy_loss | -0.309 | +| explained_variance | -1.78 | +| learning_rate | 0.0001 | +| loss | -0.109 | +| n_updates | 111560 | +| policy_gradient_loss | -0.0669 | +| value_loss | 0.000401 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.3e+03 | +| ep_rew_mean | 0.269 | +| time/ | | +| fps | 309 | +| iterations | 5105 | +| time_elapsed | 16873 | +| total_timesteps | 5227520 | +| train/ | | +| approx_kl | 2.2235956 | +| clip_fraction | 0.485 | +| clip_range | 0.2 | +| entropy_loss | -0.358 | +| explained_variance | -1.38 | +| learning_rate | 0.0001 | +| loss | -0.0773 | +| n_updates | 111570 | +| policy_gradient_loss | -0.0685 | +| value_loss | 0.000447 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.3e+03 | +| ep_rew_mean | 0.269 | +| time/ | | +| fps | 309 | +| iterations | 5106 | +| time_elapsed | 16876 | +| total_timesteps | 5228544 | +| train/ | | +| approx_kl | 2.0818133 | +| clip_fraction | 0.495 | +| clip_range | 0.2 | +| entropy_loss | -0.447 | +| explained_variance | -1.01 | +| learning_rate | 0.0001 | +| loss | -0.074 | +| n_updates | 111580 | +| policy_gradient_loss | -0.0653 | +| value_loss | 0.000559 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.3e+03 | +| ep_rew_mean | 0.268 | +| time/ | | +| fps | 309 | +| iterations | 5107 | +| time_elapsed | 16879 | +| total_timesteps | 5229568 | +| train/ | | +| approx_kl | 2.0180979 | +| clip_fraction | 0.467 | +| clip_range | 0.2 | +| entropy_loss | -0.357 | +| explained_variance | -0.941 | +| learning_rate | 0.0001 | +| loss | -0.0806 | +| n_updates | 111590 | +| policy_gradient_loss | -0.061 | +| value_loss | 0.000688 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.3e+03 | +| ep_rew_mean | 0.268 | +| time/ | | +| fps | 309 | +| iterations | 5108 | +| time_elapsed | 16882 | +| total_timesteps | 5230592 | +| train/ | | +| approx_kl | 2.312816 | +| clip_fraction | 0.441 | +| clip_range | 0.2 | +| entropy_loss | -0.31 | +| explained_variance | -1.82 | +| learning_rate | 0.0001 | +| loss | -0.083 | +| n_updates | 111600 | +| policy_gradient_loss | -0.0592 | +| value_loss | 0.000469 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.28e+03 | +| ep_rew_mean | 0.268 | +| time/ | | +| fps | 309 | +| iterations | 5109 | +| time_elapsed | 16886 | +| total_timesteps | 5231616 | +| train/ | | +| approx_kl | 2.3961935 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.357 | +| explained_variance | -1.64 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 111610 | +| policy_gradient_loss | -0.0663 | +| value_loss | 0.00057 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.27e+03 | +| ep_rew_mean | 0.269 | +| time/ | | +| fps | 309 | +| iterations | 5110 | +| time_elapsed | 16889 | +| total_timesteps | 5232640 | +| train/ | | +| approx_kl | 2.5777955 | +| clip_fraction | 0.446 | +| clip_range | 0.2 | +| entropy_loss | -0.325 | +| explained_variance | -1.69 | +| learning_rate | 0.0001 | +| loss | -0.0955 | +| n_updates | 111620 | +| policy_gradient_loss | -0.0594 | +| value_loss | 0.00048 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.27e+03 | +| ep_rew_mean | 0.269 | +| time/ | | +| fps | 309 | +| iterations | 5111 | +| time_elapsed | 16892 | +| total_timesteps | 5233664 | +| train/ | | +| approx_kl | 3.0172172 | +| clip_fraction | 0.464 | +| clip_range | 0.2 | +| entropy_loss | -0.351 | +| explained_variance | -0.568 | +| learning_rate | 0.0001 | +| loss | -0.0862 | +| n_updates | 111630 | +| policy_gradient_loss | -0.0681 | +| value_loss | 0.000762 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.27e+03 | +| ep_rew_mean | 0.269 | +| time/ | | +| fps | 309 | +| iterations | 5112 | +| time_elapsed | 16895 | +| total_timesteps | 5234688 | +| train/ | | +| approx_kl | 2.3568 | +| clip_fraction | 0.507 | +| clip_range | 0.2 | +| entropy_loss | -0.376 | +| explained_variance | -4.4 | +| learning_rate | 0.0001 | +| loss | -0.1 | +| n_updates | 111640 | +| policy_gradient_loss | -0.0707 | +| value_loss | 0.000541 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.27e+03 | +| ep_rew_mean | 0.271 | +| time/ | | +| fps | 309 | +| iterations | 5113 | +| time_elapsed | 16898 | +| total_timesteps | 5235712 | +| train/ | | +| approx_kl | 2.7879853 | +| clip_fraction | 0.498 | +| clip_range | 0.2 | +| entropy_loss | -0.389 | +| explained_variance | -7.1 | +| learning_rate | 0.0001 | +| loss | -0.0813 | +| n_updates | 111650 | +| policy_gradient_loss | -0.072 | +| value_loss | 0.000412 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.27e+03 | +| ep_rew_mean | 0.276 | +| time/ | | +| fps | 309 | +| iterations | 5114 | +| time_elapsed | 16902 | +| total_timesteps | 5236736 | +| train/ | | +| approx_kl | 2.547738 | +| clip_fraction | 0.499 | +| clip_range | 0.2 | +| entropy_loss | -0.419 | +| explained_variance | -0.293 | +| learning_rate | 0.0001 | +| loss | -0.0674 | +| n_updates | 111660 | +| policy_gradient_loss | -0.0577 | +| value_loss | 0.000555 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.25e+03 | +| ep_rew_mean | 0.273 | +| time/ | | +| fps | 309 | +| iterations | 5115 | +| time_elapsed | 16906 | +| total_timesteps | 5237760 | +| train/ | | +| approx_kl | 2.3506417 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.318 | +| explained_variance | -1.19 | +| learning_rate | 0.0001 | +| loss | -0.0766 | +| n_updates | 111670 | +| policy_gradient_loss | -0.0661 | +| value_loss | 0.000706 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.25e+03 | +| ep_rew_mean | 0.273 | +| time/ | | +| fps | 309 | +| iterations | 5116 | +| time_elapsed | 16909 | +| total_timesteps | 5238784 | +| train/ | | +| approx_kl | 2.8553228 | +| clip_fraction | 0.47 | +| clip_range | 0.2 | +| entropy_loss | -0.349 | +| explained_variance | -0.835 | +| learning_rate | 0.0001 | +| loss | -0.0854 | +| n_updates | 111680 | +| policy_gradient_loss | -0.0618 | +| value_loss | 0.000749 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.25e+03 | +| ep_rew_mean | 0.272 | +| time/ | | +| fps | 309 | +| iterations | 5117 | +| time_elapsed | 16912 | +| total_timesteps | 5239808 | +| train/ | | +| approx_kl | 2.4269414 | +| clip_fraction | 0.469 | +| clip_range | 0.2 | +| entropy_loss | -0.34 | +| explained_variance | -3.12 | +| learning_rate | 0.0001 | +| loss | -0.094 | +| n_updates | 111690 | +| policy_gradient_loss | -0.0689 | +| value_loss | 0.000376 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.25e+03 | +| ep_rew_mean | 0.272 | +| time/ | | +| fps | 309 | +| iterations | 5118 | +| time_elapsed | 16916 | +| total_timesteps | 5240832 | +| train/ | | +| approx_kl | 2.4031022 | +| clip_fraction | 0.485 | +| clip_range | 0.2 | +| entropy_loss | -0.329 | +| explained_variance | -0.442 | +| learning_rate | 0.0001 | +| loss | -0.0853 | +| n_updates | 111700 | +| policy_gradient_loss | -0.0616 | +| value_loss | 0.000503 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.24e+03 | +| ep_rew_mean | 0.271 | +| time/ | | +| fps | 309 | +| iterations | 5119 | +| time_elapsed | 16920 | +| total_timesteps | 5241856 | +| train/ | | +| approx_kl | 2.215704 | +| clip_fraction | 0.474 | +| clip_range | 0.2 | +| entropy_loss | -0.354 | +| explained_variance | -2.53 | +| learning_rate | 0.0001 | +| loss | -0.0582 | +| n_updates | 111710 | +| policy_gradient_loss | -0.0681 | +| value_loss | 0.000529 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.23e+03 | +| ep_rew_mean | 0.268 | +| time/ | | +| fps | 309 | +| iterations | 5120 | +| time_elapsed | 16923 | +| total_timesteps | 5242880 | +| train/ | | +| approx_kl | 2.382723 | +| clip_fraction | 0.482 | +| clip_range | 0.2 | +| entropy_loss | -0.387 | +| explained_variance | -0.737 | +| learning_rate | 0.0001 | +| loss | -0.076 | +| n_updates | 111720 | +| policy_gradient_loss | -0.0607 | +| value_loss | 0.0004 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.23e+03 | +| ep_rew_mean | 0.268 | +| time/ | | +| fps | 309 | +| iterations | 5121 | +| time_elapsed | 16926 | +| total_timesteps | 5243904 | +| train/ | | +| approx_kl | 2.3802884 | +| clip_fraction | 0.467 | +| clip_range | 0.2 | +| entropy_loss | -0.36 | +| explained_variance | -5.61 | +| learning_rate | 0.0001 | +| loss | -0.0926 | +| n_updates | 111730 | +| policy_gradient_loss | -0.0651 | +| value_loss | 0.000432 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.22e+03 | +| ep_rew_mean | 0.263 | +| time/ | | +| fps | 309 | +| iterations | 5122 | +| time_elapsed | 16930 | +| total_timesteps | 5244928 | +| train/ | | +| approx_kl | 2.2213218 | +| clip_fraction | 0.509 | +| clip_range | 0.2 | +| entropy_loss | -0.397 | +| explained_variance | -1.51 | +| learning_rate | 0.0001 | +| loss | -0.0655 | +| n_updates | 111740 | +| policy_gradient_loss | -0.0652 | +| value_loss | 0.000345 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.21e+03 | +| ep_rew_mean | 0.261 | +| time/ | | +| fps | 309 | +| iterations | 5123 | +| time_elapsed | 16933 | +| total_timesteps | 5245952 | +| train/ | | +| approx_kl | 2.3186717 | +| clip_fraction | 0.492 | +| clip_range | 0.2 | +| entropy_loss | -0.377 | +| explained_variance | -1.25 | +| learning_rate | 0.0001 | +| loss | -0.0786 | +| n_updates | 111750 | +| policy_gradient_loss | -0.0655 | +| value_loss | 0.00045 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.21e+03 | +| ep_rew_mean | 0.261 | +| time/ | | +| fps | 309 | +| iterations | 5124 | +| time_elapsed | 16936 | +| total_timesteps | 5246976 | +| train/ | | +| approx_kl | 2.3716524 | +| clip_fraction | 0.488 | +| clip_range | 0.2 | +| entropy_loss | -0.376 | +| explained_variance | -1.79 | +| learning_rate | 0.0001 | +| loss | -0.097 | +| n_updates | 111760 | +| policy_gradient_loss | -0.0688 | +| value_loss | 0.000533 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.2e+03 | +| ep_rew_mean | 0.258 | +| time/ | | +| fps | 309 | +| iterations | 5125 | +| time_elapsed | 16939 | +| total_timesteps | 5248000 | +| train/ | | +| approx_kl | 2.2221036 | +| clip_fraction | 0.491 | +| clip_range | 0.2 | +| entropy_loss | -0.396 | +| explained_variance | -2.38 | +| learning_rate | 0.0001 | +| loss | -0.0779 | +| n_updates | 111770 | +| policy_gradient_loss | -0.0705 | +| value_loss | 0.000302 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.19e+03 | +| ep_rew_mean | 0.256 | +| time/ | | +| fps | 309 | +| iterations | 5126 | +| time_elapsed | 16943 | +| total_timesteps | 5249024 | +| train/ | | +| approx_kl | 3.9096222 | +| clip_fraction | 0.441 | +| clip_range | 0.2 | +| entropy_loss | -0.298 | +| explained_variance | -1.35 | +| learning_rate | 0.0001 | +| loss | -0.093 | +| n_updates | 111780 | +| policy_gradient_loss | -0.0653 | +| value_loss | 0.000473 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.17e+03 | +| ep_rew_mean | 0.261 | +| time/ | | +| fps | 309 | +| iterations | 5127 | +| time_elapsed | 16946 | +| total_timesteps | 5250048 | +| train/ | | +| approx_kl | 2.1943884 | +| clip_fraction | 0.476 | +| clip_range | 0.2 | +| entropy_loss | -0.372 | +| explained_variance | -0.413 | +| learning_rate | 0.0001 | +| loss | -0.0794 | +| n_updates | 111790 | +| policy_gradient_loss | -0.0606 | +| value_loss | 0.000386 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.17e+03 | +| ep_rew_mean | 0.261 | +| time/ | | +| fps | 309 | +| iterations | 5128 | +| time_elapsed | 16949 | +| total_timesteps | 5251072 | +| train/ | | +| approx_kl | 2.1446576 | +| clip_fraction | 0.488 | +| clip_range | 0.2 | +| entropy_loss | -0.408 | +| explained_variance | -0.0353 | +| learning_rate | 0.0001 | +| loss | -0.0867 | +| n_updates | 111800 | +| policy_gradient_loss | -0.0635 | +| value_loss | 0.000641 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.17e+03 | +| ep_rew_mean | 0.264 | +| time/ | | +| fps | 309 | +| iterations | 5129 | +| time_elapsed | 16952 | +| total_timesteps | 5252096 | +| train/ | | +| approx_kl | 2.29883 | +| clip_fraction | 0.455 | +| clip_range | 0.2 | +| entropy_loss | -0.342 | +| explained_variance | -3.12 | +| learning_rate | 0.0001 | +| loss | -0.0867 | +| n_updates | 111810 | +| policy_gradient_loss | -0.0622 | +| value_loss | 0.000584 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.17e+03 | +| ep_rew_mean | 0.264 | +| time/ | | +| fps | 309 | +| iterations | 5130 | +| time_elapsed | 16955 | +| total_timesteps | 5253120 | +| train/ | | +| approx_kl | 2.3551893 | +| clip_fraction | 0.453 | +| clip_range | 0.2 | +| entropy_loss | -0.329 | +| explained_variance | -2.32 | +| learning_rate | 0.0001 | +| loss | -0.0849 | +| n_updates | 111820 | +| policy_gradient_loss | -0.0565 | +| value_loss | 0.000408 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.16e+03 | +| ep_rew_mean | 0.264 | +| time/ | | +| fps | 309 | +| iterations | 5131 | +| time_elapsed | 16959 | +| total_timesteps | 5254144 | +| train/ | | +| approx_kl | 2.6338065 | +| clip_fraction | 0.434 | +| clip_range | 0.2 | +| entropy_loss | -0.275 | +| explained_variance | -1.91 | +| learning_rate | 0.0001 | +| loss | -0.076 | +| n_updates | 111830 | +| policy_gradient_loss | -0.0613 | +| value_loss | 0.000892 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.16e+03 | +| ep_rew_mean | 0.265 | +| time/ | | +| fps | 309 | +| iterations | 5132 | +| time_elapsed | 16962 | +| total_timesteps | 5255168 | +| train/ | | +| approx_kl | 2.603444 | +| clip_fraction | 0.427 | +| clip_range | 0.2 | +| entropy_loss | -0.293 | +| explained_variance | -1.5 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 111840 | +| policy_gradient_loss | -0.0657 | +| value_loss | 0.000712 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.16e+03 | +| ep_rew_mean | 0.265 | +| time/ | | +| fps | 309 | +| iterations | 5133 | +| time_elapsed | 16966 | +| total_timesteps | 5256192 | +| train/ | | +| approx_kl | 2.337988 | +| clip_fraction | 0.454 | +| clip_range | 0.2 | +| entropy_loss | -0.306 | +| explained_variance | -2.08 | +| learning_rate | 0.0001 | +| loss | -0.108 | +| n_updates | 111850 | +| policy_gradient_loss | -0.0655 | +| value_loss | 0.000687 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.16e+03 | +| ep_rew_mean | 0.265 | +| time/ | | +| fps | 309 | +| iterations | 5134 | +| time_elapsed | 16969 | +| total_timesteps | 5257216 | +| train/ | | +| approx_kl | 2.5929058 | +| clip_fraction | 0.449 | +| clip_range | 0.2 | +| entropy_loss | -0.341 | +| explained_variance | -1.8 | +| learning_rate | 0.0001 | +| loss | -0.0796 | +| n_updates | 111860 | +| policy_gradient_loss | -0.0613 | +| value_loss | 0.000413 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.16e+03 | +| ep_rew_mean | 0.263 | +| time/ | | +| fps | 309 | +| iterations | 5135 | +| time_elapsed | 16972 | +| total_timesteps | 5258240 | +| train/ | | +| approx_kl | 3.8654065 | +| clip_fraction | 0.51 | +| clip_range | 0.2 | +| entropy_loss | -0.429 | +| explained_variance | -2.96 | +| learning_rate | 0.0001 | +| loss | -0.0943 | +| n_updates | 111870 | +| policy_gradient_loss | -0.0677 | +| value_loss | 0.000255 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.16e+03 | +| ep_rew_mean | 0.263 | +| time/ | | +| fps | 309 | +| iterations | 5136 | +| time_elapsed | 16976 | +| total_timesteps | 5259264 | +| train/ | | +| approx_kl | 3.2051063 | +| clip_fraction | 0.441 | +| clip_range | 0.2 | +| entropy_loss | -0.298 | +| explained_variance | -0.733 | +| learning_rate | 0.0001 | +| loss | -0.0806 | +| n_updates | 111880 | +| policy_gradient_loss | -0.0584 | +| value_loss | 0.000526 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.16e+03 | +| ep_rew_mean | 0.264 | +| time/ | | +| fps | 309 | +| iterations | 5137 | +| time_elapsed | 16979 | +| total_timesteps | 5260288 | +| train/ | | +| approx_kl | 1.9884235 | +| clip_fraction | 0.491 | +| clip_range | 0.2 | +| entropy_loss | -0.426 | +| explained_variance | -4.96 | +| learning_rate | 0.0001 | +| loss | -0.0682 | +| n_updates | 111890 | +| policy_gradient_loss | -0.0676 | +| value_loss | 0.000324 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.16e+03 | +| ep_rew_mean | 0.264 | +| time/ | | +| fps | 309 | +| iterations | 5138 | +| time_elapsed | 16983 | +| total_timesteps | 5261312 | +| train/ | | +| approx_kl | 2.2718253 | +| clip_fraction | 0.459 | +| clip_range | 0.2 | +| entropy_loss | -0.315 | +| explained_variance | -1.08 | +| learning_rate | 0.0001 | +| loss | -0.0492 | +| n_updates | 111900 | +| policy_gradient_loss | -0.0558 | +| value_loss | 0.000543 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.16e+03 | +| ep_rew_mean | 0.261 | +| time/ | | +| fps | 309 | +| iterations | 5139 | +| time_elapsed | 16986 | +| total_timesteps | 5262336 | +| train/ | | +| approx_kl | 2.4854696 | +| clip_fraction | 0.502 | +| clip_range | 0.2 | +| entropy_loss | -0.403 | +| explained_variance | -3.29 | +| learning_rate | 0.0001 | +| loss | -0.0802 | +| n_updates | 111910 | +| policy_gradient_loss | -0.0645 | +| value_loss | 0.000401 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.16e+03 | +| ep_rew_mean | 0.261 | +| time/ | | +| fps | 309 | +| iterations | 5140 | +| time_elapsed | 16989 | +| total_timesteps | 5263360 | +| train/ | | +| approx_kl | 2.3087156 | +| clip_fraction | 0.454 | +| clip_range | 0.2 | +| entropy_loss | -0.341 | +| explained_variance | -1.22 | +| learning_rate | 0.0001 | +| loss | -0.052 | +| n_updates | 111920 | +| policy_gradient_loss | -0.0549 | +| value_loss | 0.00053 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.16e+03 | +| ep_rew_mean | 0.257 | +| time/ | | +| fps | 309 | +| iterations | 5141 | +| time_elapsed | 16992 | +| total_timesteps | 5264384 | +| train/ | | +| approx_kl | 2.2438772 | +| clip_fraction | 0.472 | +| clip_range | 0.2 | +| entropy_loss | -0.34 | +| explained_variance | -0.887 | +| learning_rate | 0.0001 | +| loss | -0.0746 | +| n_updates | 111930 | +| policy_gradient_loss | -0.0692 | +| value_loss | 0.000627 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.16e+03 | +| ep_rew_mean | 0.257 | +| time/ | | +| fps | 309 | +| iterations | 5142 | +| time_elapsed | 16996 | +| total_timesteps | 5265408 | +| train/ | | +| approx_kl | 2.3424296 | +| clip_fraction | 0.469 | +| clip_range | 0.2 | +| entropy_loss | -0.347 | +| explained_variance | -0.709 | +| learning_rate | 0.0001 | +| loss | -0.0721 | +| n_updates | 111940 | +| policy_gradient_loss | -0.0562 | +| value_loss | 0.000404 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.16e+03 | +| ep_rew_mean | 0.262 | +| time/ | | +| fps | 309 | +| iterations | 5143 | +| time_elapsed | 16999 | +| total_timesteps | 5266432 | +| train/ | | +| approx_kl | 2.787386 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.341 | +| explained_variance | -0.741 | +| learning_rate | 0.0001 | +| loss | -0.092 | +| n_updates | 111950 | +| policy_gradient_loss | -0.0712 | +| value_loss | 0.000659 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.16e+03 | +| ep_rew_mean | 0.257 | +| time/ | | +| fps | 309 | +| iterations | 5144 | +| time_elapsed | 17002 | +| total_timesteps | 5267456 | +| train/ | | +| approx_kl | 2.1092806 | +| clip_fraction | 0.454 | +| clip_range | 0.2 | +| entropy_loss | -0.338 | +| explained_variance | -0.855 | +| learning_rate | 0.0001 | +| loss | -0.0715 | +| n_updates | 111960 | +| policy_gradient_loss | -0.0644 | +| value_loss | 0.000676 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.16e+03 | +| ep_rew_mean | 0.257 | +| time/ | | +| fps | 309 | +| iterations | 5145 | +| time_elapsed | 17005 | +| total_timesteps | 5268480 | +| train/ | | +| approx_kl | 1.8926713 | +| clip_fraction | 0.476 | +| clip_range | 0.2 | +| entropy_loss | -0.383 | +| explained_variance | -0.303 | +| learning_rate | 0.0001 | +| loss | -0.0404 | +| n_updates | 111970 | +| policy_gradient_loss | -0.0544 | +| value_loss | 0.000532 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.15e+03 | +| ep_rew_mean | 0.258 | +| time/ | | +| fps | 309 | +| iterations | 5146 | +| time_elapsed | 17008 | +| total_timesteps | 5269504 | +| train/ | | +| approx_kl | 2.026143 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.376 | +| explained_variance | -1.8 | +| learning_rate | 0.0001 | +| loss | -0.0659 | +| n_updates | 111980 | +| policy_gradient_loss | -0.0603 | +| value_loss | 0.000447 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.15e+03 | +| ep_rew_mean | 0.258 | +| time/ | | +| fps | 309 | +| iterations | 5147 | +| time_elapsed | 17012 | +| total_timesteps | 5270528 | +| train/ | | +| approx_kl | 4.3095303 | +| clip_fraction | 0.45 | +| clip_range | 0.2 | +| entropy_loss | -0.323 | +| explained_variance | -2.33 | +| learning_rate | 0.0001 | +| loss | -0.0648 | +| n_updates | 111990 | +| policy_gradient_loss | -0.0551 | +| value_loss | 0.000614 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.15e+03 | +| ep_rew_mean | 0.258 | +| time/ | | +| fps | 309 | +| iterations | 5148 | +| time_elapsed | 17015 | +| total_timesteps | 5271552 | +| train/ | | +| approx_kl | 2.3400185 | +| clip_fraction | 0.472 | +| clip_range | 0.2 | +| entropy_loss | -0.38 | +| explained_variance | -5.72 | +| learning_rate | 0.0001 | +| loss | -0.0841 | +| n_updates | 112000 | +| policy_gradient_loss | -0.0667 | +| value_loss | 0.000342 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.16e+03 | +| ep_rew_mean | 0.258 | +| time/ | | +| fps | 309 | +| iterations | 5149 | +| time_elapsed | 17018 | +| total_timesteps | 5272576 | +| train/ | | +| approx_kl | 3.0307536 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.35 | +| explained_variance | -2.07 | +| learning_rate | 0.0001 | +| loss | -0.107 | +| n_updates | 112010 | +| policy_gradient_loss | -0.0701 | +| value_loss | 0.000323 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.16e+03 | +| ep_rew_mean | 0.258 | +| time/ | | +| fps | 309 | +| iterations | 5150 | +| time_elapsed | 17021 | +| total_timesteps | 5273600 | +| train/ | | +| approx_kl | 5.6226425 | +| clip_fraction | 0.429 | +| clip_range | 0.2 | +| entropy_loss | -0.274 | +| explained_variance | -1.5 | +| learning_rate | 0.0001 | +| loss | -0.0712 | +| n_updates | 112020 | +| policy_gradient_loss | -0.0595 | +| value_loss | 0.000535 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.16e+03 | +| ep_rew_mean | 0.258 | +| time/ | | +| fps | 309 | +| iterations | 5151 | +| time_elapsed | 17025 | +| total_timesteps | 5274624 | +| train/ | | +| approx_kl | 2.1831121 | +| clip_fraction | 0.497 | +| clip_range | 0.2 | +| entropy_loss | -0.369 | +| explained_variance | -0.762 | +| learning_rate | 0.0001 | +| loss | -0.0919 | +| n_updates | 112030 | +| policy_gradient_loss | -0.0697 | +| value_loss | 0.000564 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.16e+03 | +| ep_rew_mean | 0.254 | +| time/ | | +| fps | 309 | +| iterations | 5152 | +| time_elapsed | 17029 | +| total_timesteps | 5275648 | +| train/ | | +| approx_kl | 2.541227 | +| clip_fraction | 0.444 | +| clip_range | 0.2 | +| entropy_loss | -0.323 | +| explained_variance | -1.32 | +| learning_rate | 0.0001 | +| loss | -0.0816 | +| n_updates | 112040 | +| policy_gradient_loss | -0.0562 | +| value_loss | 0.000441 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.16e+03 | +| ep_rew_mean | 0.254 | +| time/ | | +| fps | 309 | +| iterations | 5153 | +| time_elapsed | 17032 | +| total_timesteps | 5276672 | +| train/ | | +| approx_kl | 1.9798965 | +| clip_fraction | 0.433 | +| clip_range | 0.2 | +| entropy_loss | -0.29 | +| explained_variance | -0.0381 | +| learning_rate | 0.0001 | +| loss | -0.111 | +| n_updates | 112050 | +| policy_gradient_loss | -0.0662 | +| value_loss | 0.00044 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.16e+03 | +| ep_rew_mean | 0.254 | +| time/ | | +| fps | 309 | +| iterations | 5154 | +| time_elapsed | 17035 | +| total_timesteps | 5277696 | +| train/ | | +| approx_kl | 2.3807096 | +| clip_fraction | 0.455 | +| clip_range | 0.2 | +| entropy_loss | -0.315 | +| explained_variance | -7.72 | +| learning_rate | 0.0001 | +| loss | -0.0953 | +| n_updates | 112060 | +| policy_gradient_loss | -0.0684 | +| value_loss | 0.00052 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.17e+03 | +| ep_rew_mean | 0.255 | +| time/ | | +| fps | 309 | +| iterations | 5155 | +| time_elapsed | 17039 | +| total_timesteps | 5278720 | +| train/ | | +| approx_kl | 2.237936 | +| clip_fraction | 0.482 | +| clip_range | 0.2 | +| entropy_loss | -0.386 | +| explained_variance | -6.16 | +| learning_rate | 0.0001 | +| loss | -0.0628 | +| n_updates | 112070 | +| policy_gradient_loss | -0.067 | +| value_loss | 0.000208 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.16e+03 | +| ep_rew_mean | 0.252 | +| time/ | | +| fps | 309 | +| iterations | 5156 | +| time_elapsed | 17042 | +| total_timesteps | 5279744 | +| train/ | | +| approx_kl | 2.2294326 | +| clip_fraction | 0.45 | +| clip_range | 0.2 | +| entropy_loss | -0.331 | +| explained_variance | -0.525 | +| learning_rate | 0.0001 | +| loss | -0.0815 | +| n_updates | 112080 | +| policy_gradient_loss | -0.0489 | +| value_loss | 0.000381 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.16e+03 | +| ep_rew_mean | 0.252 | +| time/ | | +| fps | 309 | +| iterations | 5157 | +| time_elapsed | 17046 | +| total_timesteps | 5280768 | +| train/ | | +| approx_kl | 2.350862 | +| clip_fraction | 0.454 | +| clip_range | 0.2 | +| entropy_loss | -0.363 | +| explained_variance | 0.317 | +| learning_rate | 0.0001 | +| loss | -0.0615 | +| n_updates | 112090 | +| policy_gradient_loss | -0.0561 | +| value_loss | 0.000377 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.16e+03 | +| ep_rew_mean | 0.252 | +| time/ | | +| fps | 309 | +| iterations | 5158 | +| time_elapsed | 17049 | +| total_timesteps | 5281792 | +| train/ | | +| approx_kl | 2.1002102 | +| clip_fraction | 0.442 | +| clip_range | 0.2 | +| entropy_loss | -0.32 | +| explained_variance | -2.95 | +| learning_rate | 0.0001 | +| loss | -0.071 | +| n_updates | 112100 | +| policy_gradient_loss | -0.0641 | +| value_loss | 0.000499 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.16e+03 | +| ep_rew_mean | 0.253 | +| time/ | | +| fps | 309 | +| iterations | 5159 | +| time_elapsed | 17053 | +| total_timesteps | 5282816 | +| train/ | | +| approx_kl | 1.8336424 | +| clip_fraction | 0.47 | +| clip_range | 0.2 | +| entropy_loss | -0.424 | +| explained_variance | -2.39 | +| learning_rate | 0.0001 | +| loss | -0.0954 | +| n_updates | 112110 | +| policy_gradient_loss | -0.0607 | +| value_loss | 0.000176 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.16e+03 | +| ep_rew_mean | 0.251 | +| time/ | | +| fps | 309 | +| iterations | 5160 | +| time_elapsed | 17056 | +| total_timesteps | 5283840 | +| train/ | | +| approx_kl | 2.5151598 | +| clip_fraction | 0.423 | +| clip_range | 0.2 | +| entropy_loss | -0.266 | +| explained_variance | -0.507 | +| learning_rate | 0.0001 | +| loss | -0.0554 | +| n_updates | 112120 | +| policy_gradient_loss | -0.0544 | +| value_loss | 0.000455 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.16e+03 | +| ep_rew_mean | 0.251 | +| time/ | | +| fps | 309 | +| iterations | 5161 | +| time_elapsed | 17059 | +| total_timesteps | 5284864 | +| train/ | | +| approx_kl | 2.029212 | +| clip_fraction | 0.465 | +| clip_range | 0.2 | +| entropy_loss | -0.359 | +| explained_variance | -0.566 | +| learning_rate | 0.0001 | +| loss | -0.0709 | +| n_updates | 112130 | +| policy_gradient_loss | -0.0596 | +| value_loss | 0.000412 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.14e+03 | +| ep_rew_mean | 0.252 | +| time/ | | +| fps | 309 | +| iterations | 5162 | +| time_elapsed | 17062 | +| total_timesteps | 5285888 | +| train/ | | +| approx_kl | 2.4822602 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.373 | +| explained_variance | -1.23 | +| learning_rate | 0.0001 | +| loss | -0.0683 | +| n_updates | 112140 | +| policy_gradient_loss | -0.0658 | +| value_loss | 0.000383 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.15e+03 | +| ep_rew_mean | 0.254 | +| time/ | | +| fps | 309 | +| iterations | 5163 | +| time_elapsed | 17065 | +| total_timesteps | 5286912 | +| train/ | | +| approx_kl | 2.5999773 | +| clip_fraction | 0.46 | +| clip_range | 0.2 | +| entropy_loss | -0.329 | +| explained_variance | -0.86 | +| learning_rate | 0.0001 | +| loss | -0.0863 | +| n_updates | 112150 | +| policy_gradient_loss | -0.0648 | +| value_loss | 0.000846 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.15e+03 | +| ep_rew_mean | 0.254 | +| time/ | | +| fps | 309 | +| iterations | 5164 | +| time_elapsed | 17068 | +| total_timesteps | 5287936 | +| train/ | | +| approx_kl | 1.9962974 | +| clip_fraction | 0.455 | +| clip_range | 0.2 | +| entropy_loss | -0.326 | +| explained_variance | -1.62 | +| learning_rate | 0.0001 | +| loss | -0.0934 | +| n_updates | 112160 | +| policy_gradient_loss | -0.07 | +| value_loss | 0.000859 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.14e+03 | +| ep_rew_mean | 0.251 | +| time/ | | +| fps | 309 | +| iterations | 5165 | +| time_elapsed | 17072 | +| total_timesteps | 5288960 | +| train/ | | +| approx_kl | 2.448357 | +| clip_fraction | 0.466 | +| clip_range | 0.2 | +| entropy_loss | -0.316 | +| explained_variance | -4.09 | +| learning_rate | 0.0001 | +| loss | -0.0884 | +| n_updates | 112170 | +| policy_gradient_loss | -0.061 | +| value_loss | 0.000596 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.14e+03 | +| ep_rew_mean | 0.251 | +| time/ | | +| fps | 309 | +| iterations | 5166 | +| time_elapsed | 17075 | +| total_timesteps | 5289984 | +| train/ | | +| approx_kl | 2.3709826 | +| clip_fraction | 0.456 | +| clip_range | 0.2 | +| entropy_loss | -0.333 | +| explained_variance | -0.975 | +| learning_rate | 0.0001 | +| loss | -0.0931 | +| n_updates | 112180 | +| policy_gradient_loss | -0.0597 | +| value_loss | 0.000493 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.13e+03 | +| ep_rew_mean | 0.249 | +| time/ | | +| fps | 309 | +| iterations | 5167 | +| time_elapsed | 17078 | +| total_timesteps | 5291008 | +| train/ | | +| approx_kl | 2.1884832 | +| clip_fraction | 0.462 | +| clip_range | 0.2 | +| entropy_loss | -0.322 | +| explained_variance | -5.49 | +| learning_rate | 0.0001 | +| loss | -0.0637 | +| n_updates | 112190 | +| policy_gradient_loss | -0.0682 | +| value_loss | 0.000468 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.11e+03 | +| ep_rew_mean | 0.246 | +| time/ | | +| fps | 309 | +| iterations | 5168 | +| time_elapsed | 17081 | +| total_timesteps | 5292032 | +| train/ | | +| approx_kl | 1.9699345 | +| clip_fraction | 0.452 | +| clip_range | 0.2 | +| entropy_loss | -0.346 | +| explained_variance | -0.985 | +| learning_rate | 0.0001 | +| loss | -0.0887 | +| n_updates | 112200 | +| policy_gradient_loss | -0.053 | +| value_loss | 0.000456 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.11e+03 | +| ep_rew_mean | 0.246 | +| time/ | | +| fps | 309 | +| iterations | 5169 | +| time_elapsed | 17085 | +| total_timesteps | 5293056 | +| train/ | | +| approx_kl | 2.3849776 | +| clip_fraction | 0.424 | +| clip_range | 0.2 | +| entropy_loss | -0.281 | +| explained_variance | -2.58 | +| learning_rate | 0.0001 | +| loss | -0.0921 | +| n_updates | 112210 | +| policy_gradient_loss | -0.0626 | +| value_loss | 0.000588 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.11e+03 | +| ep_rew_mean | 0.246 | +| time/ | | +| fps | 309 | +| iterations | 5170 | +| time_elapsed | 17088 | +| total_timesteps | 5294080 | +| train/ | | +| approx_kl | 2.0749183 | +| clip_fraction | 0.463 | +| clip_range | 0.2 | +| entropy_loss | -0.341 | +| explained_variance | -1.78 | +| learning_rate | 0.0001 | +| loss | -0.0867 | +| n_updates | 112220 | +| policy_gradient_loss | -0.0596 | +| value_loss | 0.000677 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.11e+03 | +| ep_rew_mean | 0.246 | +| time/ | | +| fps | 309 | +| iterations | 5171 | +| time_elapsed | 17091 | +| total_timesteps | 5295104 | +| train/ | | +| approx_kl | 2.1650147 | +| clip_fraction | 0.457 | +| clip_range | 0.2 | +| entropy_loss | -0.352 | +| explained_variance | -5.49 | +| learning_rate | 0.0001 | +| loss | -0.0899 | +| n_updates | 112230 | +| policy_gradient_loss | -0.0647 | +| value_loss | 0.000367 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.11e+03 | +| ep_rew_mean | 0.246 | +| time/ | | +| fps | 309 | +| iterations | 5172 | +| time_elapsed | 17095 | +| total_timesteps | 5296128 | +| train/ | | +| approx_kl | 9.257665 | +| clip_fraction | 0.46 | +| clip_range | 0.2 | +| entropy_loss | -0.367 | +| explained_variance | -1.05 | +| learning_rate | 0.0001 | +| loss | -0.107 | +| n_updates | 112240 | +| policy_gradient_loss | -0.0646 | +| value_loss | 0.000421 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.11e+03 | +| ep_rew_mean | 0.242 | +| time/ | | +| fps | 309 | +| iterations | 5173 | +| time_elapsed | 17098 | +| total_timesteps | 5297152 | +| train/ | | +| approx_kl | 2.3111758 | +| clip_fraction | 0.46 | +| clip_range | 0.2 | +| entropy_loss | -0.32 | +| explained_variance | -2.01 | +| learning_rate | 0.0001 | +| loss | -0.0997 | +| n_updates | 112250 | +| policy_gradient_loss | -0.067 | +| value_loss | 0.000429 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.11e+03 | +| ep_rew_mean | 0.242 | +| time/ | | +| fps | 309 | +| iterations | 5174 | +| time_elapsed | 17101 | +| total_timesteps | 5298176 | +| train/ | | +| approx_kl | 2.8154058 | +| clip_fraction | 0.408 | +| clip_range | 0.2 | +| entropy_loss | -0.299 | +| explained_variance | -2.05 | +| learning_rate | 0.0001 | +| loss | -0.0696 | +| n_updates | 112260 | +| policy_gradient_loss | -0.0524 | +| value_loss | 0.00048 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.09e+03 | +| ep_rew_mean | 0.244 | +| time/ | | +| fps | 309 | +| iterations | 5175 | +| time_elapsed | 17105 | +| total_timesteps | 5299200 | +| train/ | | +| approx_kl | 1.9158528 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.377 | +| explained_variance | -2.3 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 112270 | +| policy_gradient_loss | -0.0676 | +| value_loss | 0.000424 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.09e+03 | +| ep_rew_mean | 0.244 | +| time/ | | +| fps | 309 | +| iterations | 5176 | +| time_elapsed | 17109 | +| total_timesteps | 5300224 | +| train/ | | +| approx_kl | 2.7111506 | +| clip_fraction | 0.443 | +| clip_range | 0.2 | +| entropy_loss | -0.292 | +| explained_variance | -1.03 | +| learning_rate | 0.0001 | +| loss | -0.0945 | +| n_updates | 112280 | +| policy_gradient_loss | -0.0556 | +| value_loss | 0.000647 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.08e+03 | +| ep_rew_mean | 0.246 | +| time/ | | +| fps | 309 | +| iterations | 5177 | +| time_elapsed | 17112 | +| total_timesteps | 5301248 | +| train/ | | +| approx_kl | 2.1148813 | +| clip_fraction | 0.473 | +| clip_range | 0.2 | +| entropy_loss | -0.328 | +| explained_variance | -3.39 | +| learning_rate | 0.0001 | +| loss | -0.08 | +| n_updates | 112290 | +| policy_gradient_loss | -0.0652 | +| value_loss | 0.000563 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.06e+03 | +| ep_rew_mean | 0.249 | +| time/ | | +| fps | 309 | +| iterations | 5178 | +| time_elapsed | 17115 | +| total_timesteps | 5302272 | +| train/ | | +| approx_kl | 2.019112 | +| clip_fraction | 0.462 | +| clip_range | 0.2 | +| entropy_loss | -0.364 | +| explained_variance | -0.442 | +| learning_rate | 0.0001 | +| loss | -0.0636 | +| n_updates | 112300 | +| policy_gradient_loss | -0.0522 | +| value_loss | 0.000405 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.06e+03 | +| ep_rew_mean | 0.249 | +| time/ | | +| fps | 309 | +| iterations | 5179 | +| time_elapsed | 17118 | +| total_timesteps | 5303296 | +| train/ | | +| approx_kl | 2.485468 | +| clip_fraction | 0.466 | +| clip_range | 0.2 | +| entropy_loss | -0.357 | +| explained_variance | -0.186 | +| learning_rate | 0.0001 | +| loss | -0.0822 | +| n_updates | 112310 | +| policy_gradient_loss | -0.0573 | +| value_loss | 0.000655 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.06e+03 | +| ep_rew_mean | 0.25 | +| time/ | | +| fps | 309 | +| iterations | 5180 | +| time_elapsed | 17121 | +| total_timesteps | 5304320 | +| train/ | | +| approx_kl | 3.0124981 | +| clip_fraction | 0.457 | +| clip_range | 0.2 | +| entropy_loss | -0.364 | +| explained_variance | -5.26 | +| learning_rate | 0.0001 | +| loss | -0.106 | +| n_updates | 112320 | +| policy_gradient_loss | -0.0642 | +| value_loss | 0.00045 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.06e+03 | +| ep_rew_mean | 0.25 | +| time/ | | +| fps | 309 | +| iterations | 5181 | +| time_elapsed | 17124 | +| total_timesteps | 5305344 | +| train/ | | +| approx_kl | 2.1773381 | +| clip_fraction | 0.442 | +| clip_range | 0.2 | +| entropy_loss | -0.336 | +| explained_variance | -1.25 | +| learning_rate | 0.0001 | +| loss | -0.0968 | +| n_updates | 112330 | +| policy_gradient_loss | -0.0572 | +| value_loss | 0.000527 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.06e+03 | +| ep_rew_mean | 0.254 | +| time/ | | +| fps | 309 | +| iterations | 5182 | +| time_elapsed | 17128 | +| total_timesteps | 5306368 | +| train/ | | +| approx_kl | 1.9600171 | +| clip_fraction | 0.443 | +| clip_range | 0.2 | +| entropy_loss | -0.344 | +| explained_variance | -5.59 | +| learning_rate | 0.0001 | +| loss | -0.112 | +| n_updates | 112340 | +| policy_gradient_loss | -0.0649 | +| value_loss | 0.00056 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.04e+03 | +| ep_rew_mean | 0.254 | +| time/ | | +| fps | 309 | +| iterations | 5183 | +| time_elapsed | 17131 | +| total_timesteps | 5307392 | +| train/ | | +| approx_kl | 4.388761 | +| clip_fraction | 0.466 | +| clip_range | 0.2 | +| entropy_loss | -0.376 | +| explained_variance | -0.788 | +| learning_rate | 0.0001 | +| loss | 0.00544 | +| n_updates | 112350 | +| policy_gradient_loss | -0.0458 | +| value_loss | 0.000194 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.04e+03 | +| ep_rew_mean | 0.254 | +| time/ | | +| fps | 309 | +| iterations | 5184 | +| time_elapsed | 17134 | +| total_timesteps | 5308416 | +| train/ | | +| approx_kl | 2.2159438 | +| clip_fraction | 0.45 | +| clip_range | 0.2 | +| entropy_loss | -0.351 | +| explained_variance | -1.45 | +| learning_rate | 0.0001 | +| loss | -0.0802 | +| n_updates | 112360 | +| policy_gradient_loss | -0.0547 | +| value_loss | 0.00032 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.04e+03 | +| ep_rew_mean | 0.251 | +| time/ | | +| fps | 309 | +| iterations | 5185 | +| time_elapsed | 17137 | +| total_timesteps | 5309440 | +| train/ | | +| approx_kl | 2.1824129 | +| clip_fraction | 0.494 | +| clip_range | 0.2 | +| entropy_loss | -0.383 | +| explained_variance | -2.05 | +| learning_rate | 0.0001 | +| loss | -0.0654 | +| n_updates | 112370 | +| policy_gradient_loss | -0.0663 | +| value_loss | 0.000683 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.04e+03 | +| ep_rew_mean | 0.251 | +| time/ | | +| fps | 309 | +| iterations | 5186 | +| time_elapsed | 17140 | +| total_timesteps | 5310464 | +| train/ | | +| approx_kl | 2.9061544 | +| clip_fraction | 0.433 | +| clip_range | 0.2 | +| entropy_loss | -0.314 | +| explained_variance | -3.22 | +| learning_rate | 0.0001 | +| loss | -0.0753 | +| n_updates | 112380 | +| policy_gradient_loss | -0.0581 | +| value_loss | 0.000477 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.04e+03 | +| ep_rew_mean | 0.251 | +| time/ | | +| fps | 309 | +| iterations | 5187 | +| time_elapsed | 17144 | +| total_timesteps | 5311488 | +| train/ | | +| approx_kl | 2.4264727 | +| clip_fraction | 0.494 | +| clip_range | 0.2 | +| entropy_loss | -0.384 | +| explained_variance | -1.98 | +| learning_rate | 0.0001 | +| loss | -0.0761 | +| n_updates | 112390 | +| policy_gradient_loss | -0.0592 | +| value_loss | 0.00036 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.04e+03 | +| ep_rew_mean | 0.251 | +| time/ | | +| fps | 309 | +| iterations | 5188 | +| time_elapsed | 17147 | +| total_timesteps | 5312512 | +| train/ | | +| approx_kl | 2.140697 | +| clip_fraction | 0.452 | +| clip_range | 0.2 | +| entropy_loss | -0.325 | +| explained_variance | -0.83 | +| learning_rate | 0.0001 | +| loss | -0.0777 | +| n_updates | 112400 | +| policy_gradient_loss | -0.0565 | +| value_loss | 0.000399 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.04e+03 | +| ep_rew_mean | 0.249 | +| time/ | | +| fps | 309 | +| iterations | 5189 | +| time_elapsed | 17151 | +| total_timesteps | 5313536 | +| train/ | | +| approx_kl | 2.0881586 | +| clip_fraction | 0.457 | +| clip_range | 0.2 | +| entropy_loss | -0.362 | +| explained_variance | -1.51 | +| learning_rate | 0.0001 | +| loss | -0.0675 | +| n_updates | 112410 | +| policy_gradient_loss | -0.0582 | +| value_loss | 0.000448 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.03e+03 | +| ep_rew_mean | 0.247 | +| time/ | | +| fps | 309 | +| iterations | 5190 | +| time_elapsed | 17155 | +| total_timesteps | 5314560 | +| train/ | | +| approx_kl | 2.0839696 | +| clip_fraction | 0.422 | +| clip_range | 0.2 | +| entropy_loss | -0.303 | +| explained_variance | -0.913 | +| learning_rate | 0.0001 | +| loss | -0.0748 | +| n_updates | 112420 | +| policy_gradient_loss | -0.0592 | +| value_loss | 0.000503 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.03e+03 | +| ep_rew_mean | 0.247 | +| time/ | | +| fps | 309 | +| iterations | 5191 | +| time_elapsed | 17158 | +| total_timesteps | 5315584 | +| train/ | | +| approx_kl | 4.3198814 | +| clip_fraction | 0.44 | +| clip_range | 0.2 | +| entropy_loss | -0.331 | +| explained_variance | -0.412 | +| learning_rate | 0.0001 | +| loss | -0.0914 | +| n_updates | 112430 | +| policy_gradient_loss | -0.0626 | +| value_loss | 0.000835 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.02e+03 | +| ep_rew_mean | 0.251 | +| time/ | | +| fps | 309 | +| iterations | 5192 | +| time_elapsed | 17162 | +| total_timesteps | 5316608 | +| train/ | | +| approx_kl | 2.220508 | +| clip_fraction | 0.49 | +| clip_range | 0.2 | +| entropy_loss | -0.391 | +| explained_variance | -1.91 | +| learning_rate | 0.0001 | +| loss | -0.0972 | +| n_updates | 112440 | +| policy_gradient_loss | -0.0663 | +| value_loss | 0.000541 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.02e+03 | +| ep_rew_mean | 0.251 | +| time/ | | +| fps | 309 | +| iterations | 5193 | +| time_elapsed | 17165 | +| total_timesteps | 5317632 | +| train/ | | +| approx_kl | 2.7417488 | +| clip_fraction | 0.43 | +| clip_range | 0.2 | +| entropy_loss | -0.303 | +| explained_variance | -1.47 | +| learning_rate | 0.0001 | +| loss | -0.089 | +| n_updates | 112450 | +| policy_gradient_loss | -0.0634 | +| value_loss | 0.000744 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.04e+03 | +| ep_rew_mean | 0.247 | +| time/ | | +| fps | 309 | +| iterations | 5194 | +| time_elapsed | 17169 | +| total_timesteps | 5318656 | +| train/ | | +| approx_kl | 2.7564025 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.359 | +| explained_variance | -2.4 | +| learning_rate | 0.0001 | +| loss | -0.107 | +| n_updates | 112460 | +| policy_gradient_loss | -0.0699 | +| value_loss | 0.000338 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.02e+03 | +| ep_rew_mean | 0.245 | +| time/ | | +| fps | 309 | +| iterations | 5195 | +| time_elapsed | 17172 | +| total_timesteps | 5319680 | +| train/ | | +| approx_kl | 1.8457943 | +| clip_fraction | 0.467 | +| clip_range | 0.2 | +| entropy_loss | -0.364 | +| explained_variance | -0.517 | +| learning_rate | 0.0001 | +| loss | -0.0574 | +| n_updates | 112470 | +| policy_gradient_loss | -0.052 | +| value_loss | 0.000166 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.02e+03 | +| ep_rew_mean | 0.245 | +| time/ | | +| fps | 309 | +| iterations | 5196 | +| time_elapsed | 17176 | +| total_timesteps | 5320704 | +| train/ | | +| approx_kl | 2.1109004 | +| clip_fraction | 0.455 | +| clip_range | 0.2 | +| entropy_loss | -0.32 | +| explained_variance | -0.0508 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 112480 | +| policy_gradient_loss | -0.0635 | +| value_loss | 0.000403 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.01e+03 | +| ep_rew_mean | 0.244 | +| time/ | | +| fps | 309 | +| iterations | 5197 | +| time_elapsed | 17179 | +| total_timesteps | 5321728 | +| train/ | | +| approx_kl | 2.1304924 | +| clip_fraction | 0.467 | +| clip_range | 0.2 | +| entropy_loss | -0.345 | +| explained_variance | -2.2 | +| learning_rate | 0.0001 | +| loss | -0.064 | +| n_updates | 112490 | +| policy_gradient_loss | -0.0575 | +| value_loss | 0.000477 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.01e+03 | +| ep_rew_mean | 0.244 | +| time/ | | +| fps | 309 | +| iterations | 5198 | +| time_elapsed | 17182 | +| total_timesteps | 5322752 | +| train/ | | +| approx_kl | 2.36138 | +| clip_fraction | 0.454 | +| clip_range | 0.2 | +| entropy_loss | -0.331 | +| explained_variance | -1.01 | +| learning_rate | 0.0001 | +| loss | -0.086 | +| n_updates | 112500 | +| policy_gradient_loss | -0.0591 | +| value_loss | 0.000714 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.01e+03 | +| ep_rew_mean | 0.244 | +| time/ | | +| fps | 309 | +| iterations | 5199 | +| time_elapsed | 17185 | +| total_timesteps | 5323776 | +| train/ | | +| approx_kl | 2.097272 | +| clip_fraction | 0.45 | +| clip_range | 0.2 | +| entropy_loss | -0.36 | +| explained_variance | -1.81 | +| learning_rate | 0.0001 | +| loss | -0.0681 | +| n_updates | 112510 | +| policy_gradient_loss | -0.0619 | +| value_loss | 0.000658 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.01e+03 | +| ep_rew_mean | 0.244 | +| time/ | | +| fps | 309 | +| iterations | 5200 | +| time_elapsed | 17188 | +| total_timesteps | 5324800 | +| train/ | | +| approx_kl | 2.5512767 | +| clip_fraction | 0.476 | +| clip_range | 0.2 | +| entropy_loss | -0.326 | +| explained_variance | -2.33 | +| learning_rate | 0.0001 | +| loss | -0.0977 | +| n_updates | 112520 | +| policy_gradient_loss | -0.0703 | +| value_loss | 0.000446 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.01e+03 | +| ep_rew_mean | 0.244 | +| time/ | | +| fps | 309 | +| iterations | 5201 | +| time_elapsed | 17192 | +| total_timesteps | 5325824 | +| train/ | | +| approx_kl | 1.796402 | +| clip_fraction | 0.431 | +| clip_range | 0.2 | +| entropy_loss | -0.355 | +| explained_variance | -0.929 | +| learning_rate | 0.0001 | +| loss | -0.065 | +| n_updates | 112530 | +| policy_gradient_loss | -0.0529 | +| value_loss | 0.000464 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2e+03 | +| ep_rew_mean | 0.244 | +| time/ | | +| fps | 309 | +| iterations | 5202 | +| time_elapsed | 17195 | +| total_timesteps | 5326848 | +| train/ | | +| approx_kl | 2.4076877 | +| clip_fraction | 0.447 | +| clip_range | 0.2 | +| entropy_loss | -0.299 | +| explained_variance | -2.25 | +| learning_rate | 0.0001 | +| loss | -0.0984 | +| n_updates | 112540 | +| policy_gradient_loss | -0.0622 | +| value_loss | 0.000384 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2e+03 | +| ep_rew_mean | 0.244 | +| time/ | | +| fps | 309 | +| iterations | 5203 | +| time_elapsed | 17198 | +| total_timesteps | 5327872 | +| train/ | | +| approx_kl | 2.153559 | +| clip_fraction | 0.426 | +| clip_range | 0.2 | +| entropy_loss | -0.295 | +| explained_variance | -1.95 | +| learning_rate | 0.0001 | +| loss | -0.0882 | +| n_updates | 112550 | +| policy_gradient_loss | -0.0583 | +| value_loss | 0.000653 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.99e+03 | +| ep_rew_mean | 0.242 | +| time/ | | +| fps | 309 | +| iterations | 5204 | +| time_elapsed | 17202 | +| total_timesteps | 5328896 | +| train/ | | +| approx_kl | 2.5341575 | +| clip_fraction | 0.465 | +| clip_range | 0.2 | +| entropy_loss | -0.304 | +| explained_variance | -1.94 | +| learning_rate | 0.0001 | +| loss | -0.0891 | +| n_updates | 112560 | +| policy_gradient_loss | -0.0679 | +| value_loss | 0.000402 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.99e+03 | +| ep_rew_mean | 0.242 | +| time/ | | +| fps | 309 | +| iterations | 5205 | +| time_elapsed | 17205 | +| total_timesteps | 5329920 | +| train/ | | +| approx_kl | 3.6801143 | +| clip_fraction | 0.401 | +| clip_range | 0.2 | +| entropy_loss | -0.292 | +| explained_variance | -0.947 | +| learning_rate | 0.0001 | +| loss | -0.0592 | +| n_updates | 112570 | +| policy_gradient_loss | -0.0524 | +| value_loss | 0.000575 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.98e+03 | +| ep_rew_mean | 0.243 | +| time/ | | +| fps | 309 | +| iterations | 5206 | +| time_elapsed | 17209 | +| total_timesteps | 5330944 | +| train/ | | +| approx_kl | 1.9196734 | +| clip_fraction | 0.488 | +| clip_range | 0.2 | +| entropy_loss | -0.394 | +| explained_variance | -1.9 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 112580 | +| policy_gradient_loss | -0.0663 | +| value_loss | 0.000623 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.98e+03 | +| ep_rew_mean | 0.243 | +| time/ | | +| fps | 309 | +| iterations | 5207 | +| time_elapsed | 17212 | +| total_timesteps | 5331968 | +| train/ | | +| approx_kl | 2.2497191 | +| clip_fraction | 0.444 | +| clip_range | 0.2 | +| entropy_loss | -0.282 | +| explained_variance | -1.4 | +| learning_rate | 0.0001 | +| loss | -0.0847 | +| n_updates | 112590 | +| policy_gradient_loss | -0.0639 | +| value_loss | 0.000377 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.98e+03 | +| ep_rew_mean | 0.243 | +| time/ | | +| fps | 309 | +| iterations | 5208 | +| time_elapsed | 17215 | +| total_timesteps | 5332992 | +| train/ | | +| approx_kl | 3.7068756 | +| clip_fraction | 0.435 | +| clip_range | 0.2 | +| entropy_loss | -0.319 | +| explained_variance | -5.18 | +| learning_rate | 0.0001 | +| loss | -0.0752 | +| n_updates | 112600 | +| policy_gradient_loss | -0.0624 | +| value_loss | 0.000235 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.01e+03 | +| ep_rew_mean | 0.238 | +| time/ | | +| fps | 309 | +| iterations | 5209 | +| time_elapsed | 17219 | +| total_timesteps | 5334016 | +| train/ | | +| approx_kl | 2.0727322 | +| clip_fraction | 0.455 | +| clip_range | 0.2 | +| entropy_loss | -0.336 | +| explained_variance | -1.51 | +| learning_rate | 0.0001 | +| loss | -0.0817 | +| n_updates | 112610 | +| policy_gradient_loss | -0.0636 | +| value_loss | 0.000372 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.01e+03 | +| ep_rew_mean | 0.238 | +| time/ | | +| fps | 309 | +| iterations | 5210 | +| time_elapsed | 17222 | +| total_timesteps | 5335040 | +| train/ | | +| approx_kl | 41.682453 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.391 | +| explained_variance | -2.49 | +| learning_rate | 0.0001 | +| loss | -0.0825 | +| n_updates | 112620 | +| policy_gradient_loss | -0.0602 | +| value_loss | 0.000498 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2e+03 | +| ep_rew_mean | 0.24 | +| time/ | | +| fps | 309 | +| iterations | 5211 | +| time_elapsed | 17226 | +| total_timesteps | 5336064 | +| train/ | | +| approx_kl | 2.377914 | +| clip_fraction | 0.484 | +| clip_range | 0.2 | +| entropy_loss | -0.32 | +| explained_variance | -3.08 | +| learning_rate | 0.0001 | +| loss | -0.0663 | +| n_updates | 112630 | +| policy_gradient_loss | -0.0711 | +| value_loss | 0.000571 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2e+03 | +| ep_rew_mean | 0.24 | +| time/ | | +| fps | 309 | +| iterations | 5212 | +| time_elapsed | 17229 | +| total_timesteps | 5337088 | +| train/ | | +| approx_kl | 2.33098 | +| clip_fraction | 0.446 | +| clip_range | 0.2 | +| entropy_loss | -0.309 | +| explained_variance | -1.52 | +| learning_rate | 0.0001 | +| loss | -0.0953 | +| n_updates | 112640 | +| policy_gradient_loss | -0.059 | +| value_loss | 0.000406 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2e+03 | +| ep_rew_mean | 0.24 | +| time/ | | +| fps | 309 | +| iterations | 5213 | +| time_elapsed | 17232 | +| total_timesteps | 5338112 | +| train/ | | +| approx_kl | 1.9662623 | +| clip_fraction | 0.467 | +| clip_range | 0.2 | +| entropy_loss | -0.348 | +| explained_variance | -3.71 | +| learning_rate | 0.0001 | +| loss | -0.1 | +| n_updates | 112650 | +| policy_gradient_loss | -0.064 | +| value_loss | 0.000407 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.02e+03 | +| ep_rew_mean | 0.235 | +| time/ | | +| fps | 309 | +| iterations | 5214 | +| time_elapsed | 17236 | +| total_timesteps | 5339136 | +| train/ | | +| approx_kl | 2.0598521 | +| clip_fraction | 0.492 | +| clip_range | 0.2 | +| entropy_loss | -0.402 | +| explained_variance | -1.87 | +| learning_rate | 0.0001 | +| loss | -0.0867 | +| n_updates | 112660 | +| policy_gradient_loss | -0.0611 | +| value_loss | 0.000308 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2e+03 | +| ep_rew_mean | 0.238 | +| time/ | | +| fps | 309 | +| iterations | 5215 | +| time_elapsed | 17239 | +| total_timesteps | 5340160 | +| train/ | | +| approx_kl | 2.478302 | +| clip_fraction | 0.474 | +| clip_range | 0.2 | +| entropy_loss | -0.339 | +| explained_variance | -0.582 | +| learning_rate | 0.0001 | +| loss | -0.0976 | +| n_updates | 112670 | +| policy_gradient_loss | -0.0642 | +| value_loss | 0.000517 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2e+03 | +| ep_rew_mean | 0.238 | +| time/ | | +| fps | 309 | +| iterations | 5216 | +| time_elapsed | 17242 | +| total_timesteps | 5341184 | +| train/ | | +| approx_kl | 2.2755432 | +| clip_fraction | 0.446 | +| clip_range | 0.2 | +| entropy_loss | -0.333 | +| explained_variance | -0.62 | +| learning_rate | 0.0001 | +| loss | -0.0855 | +| n_updates | 112680 | +| policy_gradient_loss | -0.0548 | +| value_loss | 0.000604 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.99e+03 | +| ep_rew_mean | 0.237 | +| time/ | | +| fps | 309 | +| iterations | 5217 | +| time_elapsed | 17245 | +| total_timesteps | 5342208 | +| train/ | | +| approx_kl | 2.0331414 | +| clip_fraction | 0.459 | +| clip_range | 0.2 | +| entropy_loss | -0.333 | +| explained_variance | -2.77 | +| learning_rate | 0.0001 | +| loss | -0.082 | +| n_updates | 112690 | +| policy_gradient_loss | -0.0648 | +| value_loss | 0.000372 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.97e+03 | +| ep_rew_mean | 0.236 | +| time/ | | +| fps | 309 | +| iterations | 5218 | +| time_elapsed | 17248 | +| total_timesteps | 5343232 | +| train/ | | +| approx_kl | 2.712388 | +| clip_fraction | 0.433 | +| clip_range | 0.2 | +| entropy_loss | -0.269 | +| explained_variance | -0.928 | +| learning_rate | 0.0001 | +| loss | -0.0724 | +| n_updates | 112700 | +| policy_gradient_loss | -0.0601 | +| value_loss | 0.00038 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.97e+03 | +| ep_rew_mean | 0.236 | +| time/ | | +| fps | 309 | +| iterations | 5219 | +| time_elapsed | 17251 | +| total_timesteps | 5344256 | +| train/ | | +| approx_kl | 2.1946256 | +| clip_fraction | 0.433 | +| clip_range | 0.2 | +| entropy_loss | -0.29 | +| explained_variance | -0.442 | +| learning_rate | 0.0001 | +| loss | -0.0779 | +| n_updates | 112710 | +| policy_gradient_loss | -0.0626 | +| value_loss | 0.00054 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.96e+03 | +| ep_rew_mean | 0.235 | +| time/ | | +| fps | 309 | +| iterations | 5220 | +| time_elapsed | 17255 | +| total_timesteps | 5345280 | +| train/ | | +| approx_kl | 2.7151413 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.373 | +| explained_variance | -2.74 | +| learning_rate | 0.0001 | +| loss | -0.0083 | +| n_updates | 112720 | +| policy_gradient_loss | -0.0675 | +| value_loss | 0.000413 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.95e+03 | +| ep_rew_mean | 0.236 | +| time/ | | +| fps | 309 | +| iterations | 5221 | +| time_elapsed | 17258 | +| total_timesteps | 5346304 | +| train/ | | +| approx_kl | 2.5292354 | +| clip_fraction | 0.416 | +| clip_range | 0.2 | +| entropy_loss | -0.311 | +| explained_variance | -0.843 | +| learning_rate | 0.0001 | +| loss | -0.0696 | +| n_updates | 112730 | +| policy_gradient_loss | -0.0529 | +| value_loss | 0.000367 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.95e+03 | +| ep_rew_mean | 0.236 | +| time/ | | +| fps | 309 | +| iterations | 5222 | +| time_elapsed | 17261 | +| total_timesteps | 5347328 | +| train/ | | +| approx_kl | 1.8202305 | +| clip_fraction | 0.448 | +| clip_range | 0.2 | +| entropy_loss | -0.353 | +| explained_variance | 0.172 | +| learning_rate | 0.0001 | +| loss | -0.0608 | +| n_updates | 112740 | +| policy_gradient_loss | -0.0588 | +| value_loss | 0.000299 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.93e+03 | +| ep_rew_mean | 0.235 | +| time/ | | +| fps | 309 | +| iterations | 5223 | +| time_elapsed | 17265 | +| total_timesteps | 5348352 | +| train/ | | +| approx_kl | 2.0424762 | +| clip_fraction | 0.451 | +| clip_range | 0.2 | +| entropy_loss | -0.317 | +| explained_variance | -2.23 | +| learning_rate | 0.0001 | +| loss | -0.092 | +| n_updates | 112750 | +| policy_gradient_loss | -0.058 | +| value_loss | 0.000626 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.93e+03 | +| ep_rew_mean | 0.235 | +| time/ | | +| fps | 309 | +| iterations | 5224 | +| time_elapsed | 17268 | +| total_timesteps | 5349376 | +| train/ | | +| approx_kl | 2.4619243 | +| clip_fraction | 0.455 | +| clip_range | 0.2 | +| entropy_loss | -0.358 | +| explained_variance | -1.46 | +| learning_rate | 0.0001 | +| loss | -0.0683 | +| n_updates | 112760 | +| policy_gradient_loss | -0.0581 | +| value_loss | 0.000529 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.93e+03 | +| ep_rew_mean | 0.244 | +| time/ | | +| fps | 309 | +| iterations | 5225 | +| time_elapsed | 17272 | +| total_timesteps | 5350400 | +| train/ | | +| approx_kl | 2.0395398 | +| clip_fraction | 0.47 | +| clip_range | 0.2 | +| entropy_loss | -0.327 | +| explained_variance | -5.49 | +| learning_rate | 0.0001 | +| loss | -0.0877 | +| n_updates | 112770 | +| policy_gradient_loss | -0.0646 | +| value_loss | 0.000587 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.93e+03 | +| ep_rew_mean | 0.244 | +| time/ | | +| fps | 309 | +| iterations | 5226 | +| time_elapsed | 17275 | +| total_timesteps | 5351424 | +| train/ | | +| approx_kl | 2.70697 | +| clip_fraction | 0.474 | +| clip_range | 0.2 | +| entropy_loss | -0.325 | +| explained_variance | -0.792 | +| learning_rate | 0.0001 | +| loss | -0.09 | +| n_updates | 112780 | +| policy_gradient_loss | -0.0667 | +| value_loss | 0.000691 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.92e+03 | +| ep_rew_mean | 0.248 | +| time/ | | +| fps | 309 | +| iterations | 5227 | +| time_elapsed | 17279 | +| total_timesteps | 5352448 | +| train/ | | +| approx_kl | 2.169486 | +| clip_fraction | 0.482 | +| clip_range | 0.2 | +| entropy_loss | -0.36 | +| explained_variance | -2.72 | +| learning_rate | 0.0001 | +| loss | -0.0736 | +| n_updates | 112790 | +| policy_gradient_loss | -0.0649 | +| value_loss | 0.000427 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.92e+03 | +| ep_rew_mean | 0.248 | +| time/ | | +| fps | 309 | +| iterations | 5228 | +| time_elapsed | 17282 | +| total_timesteps | 5353472 | +| train/ | | +| approx_kl | 2.29772 | +| clip_fraction | 0.443 | +| clip_range | 0.2 | +| entropy_loss | -0.298 | +| explained_variance | -0.646 | +| learning_rate | 0.0001 | +| loss | -0.0606 | +| n_updates | 112800 | +| policy_gradient_loss | -0.0571 | +| value_loss | 0.000673 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.92e+03 | +| ep_rew_mean | 0.25 | +| time/ | | +| fps | 309 | +| iterations | 5229 | +| time_elapsed | 17286 | +| total_timesteps | 5354496 | +| train/ | | +| approx_kl | 2.8455281 | +| clip_fraction | 0.47 | +| clip_range | 0.2 | +| entropy_loss | -0.346 | +| explained_variance | -1.6 | +| learning_rate | 0.0001 | +| loss | -0.0775 | +| n_updates | 112810 | +| policy_gradient_loss | -0.067 | +| value_loss | 0.000536 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.92e+03 | +| ep_rew_mean | 0.25 | +| time/ | | +| fps | 309 | +| iterations | 5230 | +| time_elapsed | 17289 | +| total_timesteps | 5355520 | +| train/ | | +| approx_kl | 2.3199506 | +| clip_fraction | 0.453 | +| clip_range | 0.2 | +| entropy_loss | -0.316 | +| explained_variance | -1.45 | +| learning_rate | 0.0001 | +| loss | -0.0893 | +| n_updates | 112820 | +| policy_gradient_loss | -0.058 | +| value_loss | 0.00043 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.92e+03 | +| ep_rew_mean | 0.25 | +| time/ | | +| fps | 309 | +| iterations | 5231 | +| time_elapsed | 17292 | +| total_timesteps | 5356544 | +| train/ | | +| approx_kl | 2.2032793 | +| clip_fraction | 0.473 | +| clip_range | 0.2 | +| entropy_loss | -0.371 | +| explained_variance | -1.58 | +| learning_rate | 0.0001 | +| loss | -0.0797 | +| n_updates | 112830 | +| policy_gradient_loss | -0.0636 | +| value_loss | 0.000321 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.92e+03 | +| ep_rew_mean | 0.25 | +| time/ | | +| fps | 309 | +| iterations | 5232 | +| time_elapsed | 17296 | +| total_timesteps | 5357568 | +| train/ | | +| approx_kl | 2.4875617 | +| clip_fraction | 0.433 | +| clip_range | 0.2 | +| entropy_loss | -0.314 | +| explained_variance | -1.05 | +| learning_rate | 0.0001 | +| loss | -0.0894 | +| n_updates | 112840 | +| policy_gradient_loss | -0.0576 | +| value_loss | 0.000385 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.9e+03 | +| ep_rew_mean | 0.254 | +| time/ | | +| fps | 309 | +| iterations | 5233 | +| time_elapsed | 17299 | +| total_timesteps | 5358592 | +| train/ | | +| approx_kl | 2.1745505 | +| clip_fraction | 0.479 | +| clip_range | 0.2 | +| entropy_loss | -0.35 | +| explained_variance | -2.47 | +| learning_rate | 0.0001 | +| loss | -0.0877 | +| n_updates | 112850 | +| policy_gradient_loss | -0.0559 | +| value_loss | 0.00043 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.9e+03 | +| ep_rew_mean | 0.254 | +| time/ | | +| fps | 309 | +| iterations | 5234 | +| time_elapsed | 17302 | +| total_timesteps | 5359616 | +| train/ | | +| approx_kl | 3.2883272 | +| clip_fraction | 0.429 | +| clip_range | 0.2 | +| entropy_loss | -0.27 | +| explained_variance | -0.821 | +| learning_rate | 0.0001 | +| loss | -0.063 | +| n_updates | 112860 | +| policy_gradient_loss | -0.0564 | +| value_loss | 0.000792 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.9e+03 | +| ep_rew_mean | 0.254 | +| time/ | | +| fps | 309 | +| iterations | 5235 | +| time_elapsed | 17305 | +| total_timesteps | 5360640 | +| train/ | | +| approx_kl | 2.2140949 | +| clip_fraction | 0.458 | +| clip_range | 0.2 | +| entropy_loss | -0.374 | +| explained_variance | -4.66 | +| learning_rate | 0.0001 | +| loss | -0.0798 | +| n_updates | 112870 | +| policy_gradient_loss | -0.0651 | +| value_loss | 0.000401 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.9e+03 | +| ep_rew_mean | 0.254 | +| time/ | | +| fps | 309 | +| iterations | 5236 | +| time_elapsed | 17308 | +| total_timesteps | 5361664 | +| train/ | | +| approx_kl | 2.3226256 | +| clip_fraction | 0.424 | +| clip_range | 0.2 | +| entropy_loss | -0.278 | +| explained_variance | -0.716 | +| learning_rate | 0.0001 | +| loss | -0.0659 | +| n_updates | 112880 | +| policy_gradient_loss | -0.0549 | +| value_loss | 0.000379 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.9e+03 | +| ep_rew_mean | 0.258 | +| time/ | | +| fps | 309 | +| iterations | 5237 | +| time_elapsed | 17312 | +| total_timesteps | 5362688 | +| train/ | | +| approx_kl | 4.0909657 | +| clip_fraction | 0.506 | +| clip_range | 0.2 | +| entropy_loss | -0.39 | +| explained_variance | -1.34 | +| learning_rate | 0.0001 | +| loss | -0.0971 | +| n_updates | 112890 | +| policy_gradient_loss | -0.0771 | +| value_loss | 0.000521 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.89e+03 | +| ep_rew_mean | 0.259 | +| time/ | | +| fps | 309 | +| iterations | 5238 | +| time_elapsed | 17315 | +| total_timesteps | 5363712 | +| train/ | | +| approx_kl | 2.0503726 | +| clip_fraction | 0.449 | +| clip_range | 0.2 | +| entropy_loss | -0.337 | +| explained_variance | -0.894 | +| learning_rate | 0.0001 | +| loss | -0.0784 | +| n_updates | 112900 | +| policy_gradient_loss | -0.0547 | +| value_loss | 0.000523 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.258 | +| time/ | | +| fps | 309 | +| iterations | 5239 | +| time_elapsed | 17318 | +| total_timesteps | 5364736 | +| train/ | | +| approx_kl | 2.6127067 | +| clip_fraction | 0.425 | +| clip_range | 0.2 | +| entropy_loss | -0.368 | +| explained_variance | -0.635 | +| learning_rate | 0.0001 | +| loss | -0.0988 | +| n_updates | 112910 | +| policy_gradient_loss | -0.0648 | +| value_loss | 0.000804 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.258 | +| time/ | | +| fps | 309 | +| iterations | 5240 | +| time_elapsed | 17322 | +| total_timesteps | 5365760 | +| train/ | | +| approx_kl | 1.9549648 | +| clip_fraction | 0.442 | +| clip_range | 0.2 | +| entropy_loss | -0.364 | +| explained_variance | -0.593 | +| learning_rate | 0.0001 | +| loss | -0.0773 | +| n_updates | 112920 | +| policy_gradient_loss | -0.0613 | +| value_loss | 0.000586 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.258 | +| time/ | | +| fps | 309 | +| iterations | 5241 | +| time_elapsed | 17325 | +| total_timesteps | 5366784 | +| train/ | | +| approx_kl | 2.6876755 | +| clip_fraction | 0.453 | +| clip_range | 0.2 | +| entropy_loss | -0.322 | +| explained_variance | -5.69 | +| learning_rate | 0.0001 | +| loss | -0.0861 | +| n_updates | 112930 | +| policy_gradient_loss | -0.0637 | +| value_loss | 0.000408 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.9e+03 | +| ep_rew_mean | 0.254 | +| time/ | | +| fps | 309 | +| iterations | 5242 | +| time_elapsed | 17328 | +| total_timesteps | 5367808 | +| train/ | | +| approx_kl | 2.1173785 | +| clip_fraction | 0.466 | +| clip_range | 0.2 | +| entropy_loss | -0.325 | +| explained_variance | -1.67 | +| learning_rate | 0.0001 | +| loss | -0.11 | +| n_updates | 112940 | +| policy_gradient_loss | -0.0683 | +| value_loss | 0.000453 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.9e+03 | +| ep_rew_mean | 0.254 | +| time/ | | +| fps | 309 | +| iterations | 5243 | +| time_elapsed | 17332 | +| total_timesteps | 5368832 | +| train/ | | +| approx_kl | 5.258253 | +| clip_fraction | 0.448 | +| clip_range | 0.2 | +| entropy_loss | -0.327 | +| explained_variance | -1.56 | +| learning_rate | 0.0001 | +| loss | -0.0799 | +| n_updates | 112950 | +| policy_gradient_loss | -0.0609 | +| value_loss | 0.00042 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.9e+03 | +| ep_rew_mean | 0.259 | +| time/ | | +| fps | 309 | +| iterations | 5244 | +| time_elapsed | 17335 | +| total_timesteps | 5369856 | +| train/ | | +| approx_kl | 2.7847145 | +| clip_fraction | 0.443 | +| clip_range | 0.2 | +| entropy_loss | -0.333 | +| explained_variance | -1.93 | +| learning_rate | 0.0001 | +| loss | -0.0873 | +| n_updates | 112960 | +| policy_gradient_loss | -0.0618 | +| value_loss | 0.000342 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.9e+03 | +| ep_rew_mean | 0.259 | +| time/ | | +| fps | 309 | +| iterations | 5245 | +| time_elapsed | 17339 | +| total_timesteps | 5370880 | +| train/ | | +| approx_kl | 2.1288261 | +| clip_fraction | 0.444 | +| clip_range | 0.2 | +| entropy_loss | -0.332 | +| explained_variance | -0.721 | +| learning_rate | 0.0001 | +| loss | -0.0851 | +| n_updates | 112970 | +| policy_gradient_loss | -0.0606 | +| value_loss | 0.000675 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.257 | +| time/ | | +| fps | 309 | +| iterations | 5246 | +| time_elapsed | 17342 | +| total_timesteps | 5371904 | +| train/ | | +| approx_kl | 2.2209063 | +| clip_fraction | 0.463 | +| clip_range | 0.2 | +| entropy_loss | -0.346 | +| explained_variance | -7.33 | +| learning_rate | 0.0001 | +| loss | -0.096 | +| n_updates | 112980 | +| policy_gradient_loss | -0.0643 | +| value_loss | 0.000378 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.257 | +| time/ | | +| fps | 309 | +| iterations | 5247 | +| time_elapsed | 17345 | +| total_timesteps | 5372928 | +| train/ | | +| approx_kl | 2.5039594 | +| clip_fraction | 0.427 | +| clip_range | 0.2 | +| entropy_loss | -0.303 | +| explained_variance | -0.577 | +| learning_rate | 0.0001 | +| loss | -0.0425 | +| n_updates | 112990 | +| policy_gradient_loss | -0.0516 | +| value_loss | 0.000415 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.261 | +| time/ | | +| fps | 309 | +| iterations | 5248 | +| time_elapsed | 17349 | +| total_timesteps | 5373952 | +| train/ | | +| approx_kl | 2.591491 | +| clip_fraction | 0.445 | +| clip_range | 0.2 | +| entropy_loss | -0.326 | +| explained_variance | -3.92 | +| learning_rate | 0.0001 | +| loss | -0.0989 | +| n_updates | 113000 | +| policy_gradient_loss | -0.0595 | +| value_loss | 0.000366 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.258 | +| time/ | | +| fps | 309 | +| iterations | 5249 | +| time_elapsed | 17352 | +| total_timesteps | 5374976 | +| train/ | | +| approx_kl | 2.3737593 | +| clip_fraction | 0.418 | +| clip_range | 0.2 | +| entropy_loss | -0.297 | +| explained_variance | -0.496 | +| learning_rate | 0.0001 | +| loss | -0.0739 | +| n_updates | 113010 | +| policy_gradient_loss | -0.0556 | +| value_loss | 0.000558 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.258 | +| time/ | | +| fps | 309 | +| iterations | 5250 | +| time_elapsed | 17355 | +| total_timesteps | 5376000 | +| train/ | | +| approx_kl | 2.0643778 | +| clip_fraction | 0.42 | +| clip_range | 0.2 | +| entropy_loss | -0.29 | +| explained_variance | -1.32 | +| learning_rate | 0.0001 | +| loss | -0.0308 | +| n_updates | 113020 | +| policy_gradient_loss | -0.0621 | +| value_loss | 0.000573 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.26 | +| time/ | | +| fps | 309 | +| iterations | 5251 | +| time_elapsed | 17358 | +| total_timesteps | 5377024 | +| train/ | | +| approx_kl | 2.2527614 | +| clip_fraction | 0.492 | +| clip_range | 0.2 | +| entropy_loss | -0.367 | +| explained_variance | -1.87 | +| learning_rate | 0.0001 | +| loss | -0.0916 | +| n_updates | 113030 | +| policy_gradient_loss | -0.0651 | +| value_loss | 0.000548 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.26 | +| time/ | | +| fps | 309 | +| iterations | 5252 | +| time_elapsed | 17361 | +| total_timesteps | 5378048 | +| train/ | | +| approx_kl | 2.310756 | +| clip_fraction | 0.447 | +| clip_range | 0.2 | +| entropy_loss | -0.316 | +| explained_variance | -1.09 | +| learning_rate | 0.0001 | +| loss | -0.0948 | +| n_updates | 113040 | +| policy_gradient_loss | -0.0641 | +| value_loss | 0.000673 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.258 | +| time/ | | +| fps | 309 | +| iterations | 5253 | +| time_elapsed | 17365 | +| total_timesteps | 5379072 | +| train/ | | +| approx_kl | 2.1120527 | +| clip_fraction | 0.49 | +| clip_range | 0.2 | +| entropy_loss | -0.403 | +| explained_variance | -2.43 | +| learning_rate | 0.0001 | +| loss | -0.0653 | +| n_updates | 113050 | +| policy_gradient_loss | -0.067 | +| value_loss | 0.000358 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.258 | +| time/ | | +| fps | 309 | +| iterations | 5254 | +| time_elapsed | 17368 | +| total_timesteps | 5380096 | +| train/ | | +| approx_kl | 2.263893 | +| clip_fraction | 0.468 | +| clip_range | 0.2 | +| entropy_loss | -0.374 | +| explained_variance | -0.525 | +| learning_rate | 0.0001 | +| loss | -0.0894 | +| n_updates | 113060 | +| policy_gradient_loss | -0.0538 | +| value_loss | 0.000434 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.253 | +| time/ | | +| fps | 309 | +| iterations | 5255 | +| time_elapsed | 17371 | +| total_timesteps | 5381120 | +| train/ | | +| approx_kl | 1.8584614 | +| clip_fraction | 0.464 | +| clip_range | 0.2 | +| entropy_loss | -0.375 | +| explained_variance | -11.9 | +| learning_rate | 0.0001 | +| loss | -0.0951 | +| n_updates | 113070 | +| policy_gradient_loss | -0.0645 | +| value_loss | 0.000409 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.253 | +| time/ | | +| fps | 309 | +| iterations | 5256 | +| time_elapsed | 17374 | +| total_timesteps | 5382144 | +| train/ | | +| approx_kl | 1.9355764 | +| clip_fraction | 0.437 | +| clip_range | 0.2 | +| entropy_loss | -0.34 | +| explained_variance | -2.39 | +| learning_rate | 0.0001 | +| loss | -0.0731 | +| n_updates | 113080 | +| policy_gradient_loss | -0.0548 | +| value_loss | 0.000355 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.253 | +| time/ | | +| fps | 309 | +| iterations | 5257 | +| time_elapsed | 17377 | +| total_timesteps | 5383168 | +| train/ | | +| approx_kl | 1.9451507 | +| clip_fraction | 0.498 | +| clip_range | 0.2 | +| entropy_loss | -0.415 | +| explained_variance | -5.59 | +| learning_rate | 0.0001 | +| loss | -0.0972 | +| n_updates | 113090 | +| policy_gradient_loss | -0.077 | +| value_loss | 0.000279 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.249 | +| time/ | | +| fps | 309 | +| iterations | 5258 | +| time_elapsed | 17381 | +| total_timesteps | 5384192 | +| train/ | | +| approx_kl | 1.97508 | +| clip_fraction | 0.499 | +| clip_range | 0.2 | +| entropy_loss | -0.434 | +| explained_variance | -2.03 | +| learning_rate | 0.0001 | +| loss | -0.0801 | +| n_updates | 113100 | +| policy_gradient_loss | -0.0674 | +| value_loss | 0.000288 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.252 | +| time/ | | +| fps | 309 | +| iterations | 5259 | +| time_elapsed | 17384 | +| total_timesteps | 5385216 | +| train/ | | +| approx_kl | 2.954492 | +| clip_fraction | 0.493 | +| clip_range | 0.2 | +| entropy_loss | -0.427 | +| explained_variance | -0.567 | +| learning_rate | 0.0001 | +| loss | -0.08 | +| n_updates | 113110 | +| policy_gradient_loss | -0.0612 | +| value_loss | 0.000467 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.252 | +| time/ | | +| fps | 309 | +| iterations | 5260 | +| time_elapsed | 17388 | +| total_timesteps | 5386240 | +| train/ | | +| approx_kl | 2.5386176 | +| clip_fraction | 0.462 | +| clip_range | 0.2 | +| entropy_loss | -0.374 | +| explained_variance | -0.417 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 113120 | +| policy_gradient_loss | -0.0656 | +| value_loss | 0.000502 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.252 | +| time/ | | +| fps | 309 | +| iterations | 5261 | +| time_elapsed | 17391 | +| total_timesteps | 5387264 | +| train/ | | +| approx_kl | 2.227788 | +| clip_fraction | 0.489 | +| clip_range | 0.2 | +| entropy_loss | -0.326 | +| explained_variance | -6.29 | +| learning_rate | 0.0001 | +| loss | -0.0907 | +| n_updates | 113130 | +| policy_gradient_loss | -0.0719 | +| value_loss | 0.000383 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.251 | +| time/ | | +| fps | 309 | +| iterations | 5262 | +| time_elapsed | 17395 | +| total_timesteps | 5388288 | +| train/ | | +| approx_kl | 2.8704937 | +| clip_fraction | 0.508 | +| clip_range | 0.2 | +| entropy_loss | -0.425 | +| explained_variance | -1.91 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 113140 | +| policy_gradient_loss | -0.0751 | +| value_loss | 0.00025 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.251 | +| time/ | | +| fps | 309 | +| iterations | 5263 | +| time_elapsed | 17398 | +| total_timesteps | 5389312 | +| train/ | | +| approx_kl | 2.085489 | +| clip_fraction | 0.456 | +| clip_range | 0.2 | +| entropy_loss | -0.359 | +| explained_variance | -0.806 | +| learning_rate | 0.0001 | +| loss | -0.0707 | +| n_updates | 113150 | +| policy_gradient_loss | -0.0591 | +| value_loss | 0.000556 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.254 | +| time/ | | +| fps | 309 | +| iterations | 5264 | +| time_elapsed | 17402 | +| total_timesteps | 5390336 | +| train/ | | +| approx_kl | 2.55893 | +| clip_fraction | 0.476 | +| clip_range | 0.2 | +| entropy_loss | -0.363 | +| explained_variance | -1.62 | +| learning_rate | 0.0001 | +| loss | -0.0572 | +| n_updates | 113160 | +| policy_gradient_loss | -0.0663 | +| value_loss | 0.000392 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.249 | +| time/ | | +| fps | 309 | +| iterations | 5265 | +| time_elapsed | 17405 | +| total_timesteps | 5391360 | +| train/ | | +| approx_kl | 2.0128193 | +| clip_fraction | 0.458 | +| clip_range | 0.2 | +| entropy_loss | -0.328 | +| explained_variance | -0.831 | +| learning_rate | 0.0001 | +| loss | -0.0944 | +| n_updates | 113170 | +| policy_gradient_loss | -0.0669 | +| value_loss | 0.000678 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.243 | +| time/ | | +| fps | 309 | +| iterations | 5266 | +| time_elapsed | 17409 | +| total_timesteps | 5392384 | +| train/ | | +| approx_kl | 1.8432198 | +| clip_fraction | 0.461 | +| clip_range | 0.2 | +| entropy_loss | -0.355 | +| explained_variance | -2.58 | +| learning_rate | 0.0001 | +| loss | -0.0642 | +| n_updates | 113180 | +| policy_gradient_loss | -0.0587 | +| value_loss | 0.000695 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.243 | +| time/ | | +| fps | 309 | +| iterations | 5267 | +| time_elapsed | 17412 | +| total_timesteps | 5393408 | +| train/ | | +| approx_kl | 1.6404917 | +| clip_fraction | 0.433 | +| clip_range | 0.2 | +| entropy_loss | -0.346 | +| explained_variance | -2.05 | +| learning_rate | 0.0001 | +| loss | -0.0924 | +| n_updates | 113190 | +| policy_gradient_loss | -0.0643 | +| value_loss | 0.000389 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.239 | +| time/ | | +| fps | 309 | +| iterations | 5268 | +| time_elapsed | 17415 | +| total_timesteps | 5394432 | +| train/ | | +| approx_kl | 2.586604 | +| clip_fraction | 0.52 | +| clip_range | 0.2 | +| entropy_loss | -0.476 | +| explained_variance | -1.38 | +| learning_rate | 0.0001 | +| loss | -0.0731 | +| n_updates | 113200 | +| policy_gradient_loss | -0.0667 | +| value_loss | 0.000433 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.243 | +| time/ | | +| fps | 309 | +| iterations | 5269 | +| time_elapsed | 17418 | +| total_timesteps | 5395456 | +| train/ | | +| approx_kl | 2.0967906 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.351 | +| explained_variance | -0.829 | +| learning_rate | 0.0001 | +| loss | -0.0816 | +| n_updates | 113210 | +| policy_gradient_loss | -0.0666 | +| value_loss | 0.000535 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.243 | +| time/ | | +| fps | 309 | +| iterations | 5270 | +| time_elapsed | 17421 | +| total_timesteps | 5396480 | +| train/ | | +| approx_kl | 4.0805883 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.348 | +| explained_variance | -1.07 | +| learning_rate | 0.0001 | +| loss | -0.106 | +| n_updates | 113220 | +| policy_gradient_loss | -0.0658 | +| value_loss | 0.000581 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.241 | +| time/ | | +| fps | 309 | +| iterations | 5271 | +| time_elapsed | 17424 | +| total_timesteps | 5397504 | +| train/ | | +| approx_kl | 2.2112298 | +| clip_fraction | 0.485 | +| clip_range | 0.2 | +| entropy_loss | -0.359 | +| explained_variance | -2.45 | +| learning_rate | 0.0001 | +| loss | -0.099 | +| n_updates | 113230 | +| policy_gradient_loss | -0.0701 | +| value_loss | 0.000355 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.24 | +| time/ | | +| fps | 309 | +| iterations | 5272 | +| time_elapsed | 17428 | +| total_timesteps | 5398528 | +| train/ | | +| approx_kl | 2.6395793 | +| clip_fraction | 0.455 | +| clip_range | 0.2 | +| entropy_loss | -0.32 | +| explained_variance | -0.595 | +| learning_rate | 0.0001 | +| loss | -0.0626 | +| n_updates | 113240 | +| policy_gradient_loss | -0.0612 | +| value_loss | 0.000425 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.24 | +| time/ | | +| fps | 309 | +| iterations | 5273 | +| time_elapsed | 17431 | +| total_timesteps | 5399552 | +| train/ | | +| approx_kl | 2.2345695 | +| clip_fraction | 0.456 | +| clip_range | 0.2 | +| entropy_loss | -0.351 | +| explained_variance | -1.8 | +| learning_rate | 0.0001 | +| loss | -0.0812 | +| n_updates | 113250 | +| policy_gradient_loss | -0.0633 | +| value_loss | 0.000522 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.24 | +| time/ | | +| fps | 309 | +| iterations | 5274 | +| time_elapsed | 17434 | +| total_timesteps | 5400576 | +| train/ | | +| approx_kl | 2.3630466 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.364 | +| explained_variance | -6.35 | +| learning_rate | 0.0001 | +| loss | -0.0921 | +| n_updates | 113260 | +| policy_gradient_loss | -0.0675 | +| value_loss | 0.000504 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.241 | +| time/ | | +| fps | 309 | +| iterations | 5275 | +| time_elapsed | 17437 | +| total_timesteps | 5401600 | +| train/ | | +| approx_kl | 2.1657603 | +| clip_fraction | 0.484 | +| clip_range | 0.2 | +| entropy_loss | -0.388 | +| explained_variance | -1.67 | +| learning_rate | 0.0001 | +| loss | -0.0372 | +| n_updates | 113270 | +| policy_gradient_loss | -0.0666 | +| value_loss | 0.000339 | +--------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.243 | +| time/ | | +| fps | 309 | +| iterations | 5276 | +| time_elapsed | 17441 | +| total_timesteps | 5402624 | +| train/ | | +| approx_kl | 12.2299185 | +| clip_fraction | 0.467 | +| clip_range | 0.2 | +| entropy_loss | -0.343 | +| explained_variance | -1.36 | +| learning_rate | 0.0001 | +| loss | -0.0958 | +| n_updates | 113280 | +| policy_gradient_loss | -0.0619 | +| value_loss | 0.000492 | +---------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.243 | +| time/ | | +| fps | 309 | +| iterations | 5277 | +| time_elapsed | 17444 | +| total_timesteps | 5403648 | +| train/ | | +| approx_kl | 1.9718785 | +| clip_fraction | 0.469 | +| clip_range | 0.2 | +| entropy_loss | -0.335 | +| explained_variance | -2.06 | +| learning_rate | 0.0001 | +| loss | -0.0928 | +| n_updates | 113290 | +| policy_gradient_loss | -0.0677 | +| value_loss | 0.000341 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.246 | +| time/ | | +| fps | 309 | +| iterations | 5278 | +| time_elapsed | 17447 | +| total_timesteps | 5404672 | +| train/ | | +| approx_kl | 2.3981314 | +| clip_fraction | 0.494 | +| clip_range | 0.2 | +| entropy_loss | -0.371 | +| explained_variance | -0.988 | +| learning_rate | 0.0001 | +| loss | -0.0884 | +| n_updates | 113300 | +| policy_gradient_loss | -0.0638 | +| value_loss | 0.000485 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.246 | +| time/ | | +| fps | 309 | +| iterations | 5279 | +| time_elapsed | 17451 | +| total_timesteps | 5405696 | +| train/ | | +| approx_kl | 2.931886 | +| clip_fraction | 0.463 | +| clip_range | 0.2 | +| entropy_loss | -0.302 | +| explained_variance | -1.38 | +| learning_rate | 0.0001 | +| loss | -0.107 | +| n_updates | 113310 | +| policy_gradient_loss | -0.0683 | +| value_loss | 0.000677 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.244 | +| time/ | | +| fps | 309 | +| iterations | 5280 | +| time_elapsed | 17454 | +| total_timesteps | 5406720 | +| train/ | | +| approx_kl | 1.8164748 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.359 | +| explained_variance | -1.67 | +| learning_rate | 0.0001 | +| loss | -0.0633 | +| n_updates | 113320 | +| policy_gradient_loss | -0.029 | +| value_loss | 0.000388 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.244 | +| time/ | | +| fps | 309 | +| iterations | 5281 | +| time_elapsed | 17457 | +| total_timesteps | 5407744 | +| train/ | | +| approx_kl | 6.484645 | +| clip_fraction | 0.453 | +| clip_range | 0.2 | +| entropy_loss | -0.336 | +| explained_variance | -2.55 | +| learning_rate | 0.0001 | +| loss | -0.0681 | +| n_updates | 113330 | +| policy_gradient_loss | -0.059 | +| value_loss | 0.000376 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.244 | +| time/ | | +| fps | 309 | +| iterations | 5282 | +| time_elapsed | 17461 | +| total_timesteps | 5408768 | +| train/ | | +| approx_kl | 2.3595169 | +| clip_fraction | 0.456 | +| clip_range | 0.2 | +| entropy_loss | -0.339 | +| explained_variance | -2.01 | +| learning_rate | 0.0001 | +| loss | -0.112 | +| n_updates | 113340 | +| policy_gradient_loss | -0.0671 | +| value_loss | 0.000392 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.242 | +| time/ | | +| fps | 309 | +| iterations | 5283 | +| time_elapsed | 17464 | +| total_timesteps | 5409792 | +| train/ | | +| approx_kl | 2.0084848 | +| clip_fraction | 0.465 | +| clip_range | 0.2 | +| entropy_loss | -0.338 | +| explained_variance | -7.78 | +| learning_rate | 0.0001 | +| loss | -0.0864 | +| n_updates | 113350 | +| policy_gradient_loss | -0.0701 | +| value_loss | 0.000307 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.246 | +| time/ | | +| fps | 309 | +| iterations | 5284 | +| time_elapsed | 17467 | +| total_timesteps | 5410816 | +| train/ | | +| approx_kl | 2.1194613 | +| clip_fraction | 0.432 | +| clip_range | 0.2 | +| entropy_loss | -0.294 | +| explained_variance | -0.811 | +| learning_rate | 0.0001 | +| loss | -0.075 | +| n_updates | 113360 | +| policy_gradient_loss | -0.0564 | +| value_loss | 0.000695 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.245 | +| time/ | | +| fps | 309 | +| iterations | 5285 | +| time_elapsed | 17471 | +| total_timesteps | 5411840 | +| train/ | | +| approx_kl | 2.0839374 | +| clip_fraction | 0.44 | +| clip_range | 0.2 | +| entropy_loss | -0.342 | +| explained_variance | -1.31 | +| learning_rate | 0.0001 | +| loss | -0.0738 | +| n_updates | 113370 | +| policy_gradient_loss | -0.0622 | +| value_loss | 0.00109 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.245 | +| time/ | | +| fps | 309 | +| iterations | 5286 | +| time_elapsed | 17474 | +| total_timesteps | 5412864 | +| train/ | | +| approx_kl | 2.1249557 | +| clip_fraction | 0.474 | +| clip_range | 0.2 | +| entropy_loss | -0.347 | +| explained_variance | -1.05 | +| learning_rate | 0.0001 | +| loss | -0.0973 | +| n_updates | 113380 | +| policy_gradient_loss | -0.063 | +| value_loss | 0.000785 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.245 | +| time/ | | +| fps | 309 | +| iterations | 5287 | +| time_elapsed | 17477 | +| total_timesteps | 5413888 | +| train/ | | +| approx_kl | 2.2758408 | +| clip_fraction | 0.428 | +| clip_range | 0.2 | +| entropy_loss | -0.315 | +| explained_variance | -2.46 | +| learning_rate | 0.0001 | +| loss | -0.0542 | +| n_updates | 113390 | +| policy_gradient_loss | -0.0609 | +| value_loss | 0.000855 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.245 | +| time/ | | +| fps | 309 | +| iterations | 5288 | +| time_elapsed | 17480 | +| total_timesteps | 5414912 | +| train/ | | +| approx_kl | 2.4808447 | +| clip_fraction | 0.452 | +| clip_range | 0.2 | +| entropy_loss | -0.311 | +| explained_variance | -0.853 | +| learning_rate | 0.0001 | +| loss | -0.059 | +| n_updates | 113400 | +| policy_gradient_loss | -0.0636 | +| value_loss | 0.00044 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.244 | +| time/ | | +| fps | 309 | +| iterations | 5289 | +| time_elapsed | 17483 | +| total_timesteps | 5415936 | +| train/ | | +| approx_kl | 2.3175921 | +| clip_fraction | 0.495 | +| clip_range | 0.2 | +| entropy_loss | -0.371 | +| explained_variance | -2.12 | +| learning_rate | 0.0001 | +| loss | -0.0257 | +| n_updates | 113410 | +| policy_gradient_loss | -0.0542 | +| value_loss | 0.000379 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.24 | +| time/ | | +| fps | 309 | +| iterations | 5290 | +| time_elapsed | 17486 | +| total_timesteps | 5416960 | +| train/ | | +| approx_kl | 2.6268442 | +| clip_fraction | 0.442 | +| clip_range | 0.2 | +| entropy_loss | -0.313 | +| explained_variance | -1.73 | +| learning_rate | 0.0001 | +| loss | -0.0488 | +| n_updates | 113420 | +| policy_gradient_loss | -0.0562 | +| value_loss | 0.000398 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.24 | +| time/ | | +| fps | 309 | +| iterations | 5291 | +| time_elapsed | 17490 | +| total_timesteps | 5417984 | +| train/ | | +| approx_kl | 2.5175261 | +| clip_fraction | 0.451 | +| clip_range | 0.2 | +| entropy_loss | -0.314 | +| explained_variance | -1.07 | +| learning_rate | 0.0001 | +| loss | -0.0832 | +| n_updates | 113430 | +| policy_gradient_loss | -0.0614 | +| value_loss | 0.000456 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.241 | +| time/ | | +| fps | 309 | +| iterations | 5292 | +| time_elapsed | 17493 | +| total_timesteps | 5419008 | +| train/ | | +| approx_kl | 2.0821176 | +| clip_fraction | 0.488 | +| clip_range | 0.2 | +| entropy_loss | -0.382 | +| explained_variance | -0.947 | +| learning_rate | 0.0001 | +| loss | -0.0724 | +| n_updates | 113440 | +| policy_gradient_loss | -0.063 | +| value_loss | 0.000554 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.236 | +| time/ | | +| fps | 309 | +| iterations | 5293 | +| time_elapsed | 17496 | +| total_timesteps | 5420032 | +| train/ | | +| approx_kl | 2.0364244 | +| clip_fraction | 0.432 | +| clip_range | 0.2 | +| entropy_loss | -0.294 | +| explained_variance | -2.13 | +| learning_rate | 0.0001 | +| loss | -0.0818 | +| n_updates | 113450 | +| policy_gradient_loss | -0.0596 | +| value_loss | 0.000484 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.236 | +| time/ | | +| fps | 309 | +| iterations | 5294 | +| time_elapsed | 17499 | +| total_timesteps | 5421056 | +| train/ | | +| approx_kl | 18.696573 | +| clip_fraction | 0.442 | +| clip_range | 0.2 | +| entropy_loss | -0.281 | +| explained_variance | -4.06 | +| learning_rate | 0.0001 | +| loss | -0.108 | +| n_updates | 113460 | +| policy_gradient_loss | -0.0602 | +| value_loss | 0.000457 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.236 | +| time/ | | +| fps | 309 | +| iterations | 5295 | +| time_elapsed | 17503 | +| total_timesteps | 5422080 | +| train/ | | +| approx_kl | 2.1807284 | +| clip_fraction | 0.437 | +| clip_range | 0.2 | +| entropy_loss | -0.332 | +| explained_variance | -2.8 | +| learning_rate | 0.0001 | +| loss | -0.0563 | +| n_updates | 113470 | +| policy_gradient_loss | -0.063 | +| value_loss | 0.000545 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.238 | +| time/ | | +| fps | 309 | +| iterations | 5296 | +| time_elapsed | 17506 | +| total_timesteps | 5423104 | +| train/ | | +| approx_kl | 2.3691318 | +| clip_fraction | 0.466 | +| clip_range | 0.2 | +| entropy_loss | -0.284 | +| explained_variance | -0.801 | +| learning_rate | 0.0001 | +| loss | -0.0972 | +| n_updates | 113480 | +| policy_gradient_loss | -0.0643 | +| value_loss | 0.000645 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.239 | +| time/ | | +| fps | 309 | +| iterations | 5297 | +| time_elapsed | 17510 | +| total_timesteps | 5424128 | +| train/ | | +| approx_kl | 2.1795068 | +| clip_fraction | 0.466 | +| clip_range | 0.2 | +| entropy_loss | -0.331 | +| explained_variance | -0.475 | +| learning_rate | 0.0001 | +| loss | -0.0629 | +| n_updates | 113490 | +| policy_gradient_loss | -0.0616 | +| value_loss | 0.000733 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.239 | +| time/ | | +| fps | 309 | +| iterations | 5298 | +| time_elapsed | 17513 | +| total_timesteps | 5425152 | +| train/ | | +| approx_kl | 2.3355665 | +| clip_fraction | 0.436 | +| clip_range | 0.2 | +| entropy_loss | -0.294 | +| explained_variance | -1.22 | +| learning_rate | 0.0001 | +| loss | -0.0807 | +| n_updates | 113500 | +| policy_gradient_loss | -0.0342 | +| value_loss | 0.000776 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.242 | +| time/ | | +| fps | 309 | +| iterations | 5299 | +| time_elapsed | 17517 | +| total_timesteps | 5426176 | +| train/ | | +| approx_kl | 2.493371 | +| clip_fraction | 0.478 | +| clip_range | 0.2 | +| entropy_loss | -0.311 | +| explained_variance | -1.93 | +| learning_rate | 0.0001 | +| loss | -0.0635 | +| n_updates | 113510 | +| policy_gradient_loss | -0.0658 | +| value_loss | 0.000742 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.249 | +| time/ | | +| fps | 309 | +| iterations | 5300 | +| time_elapsed | 17520 | +| total_timesteps | 5427200 | +| train/ | | +| approx_kl | 1.8756564 | +| clip_fraction | 0.425 | +| clip_range | 0.2 | +| entropy_loss | -0.301 | +| explained_variance | -2.58 | +| learning_rate | 0.0001 | +| loss | -0.0725 | +| n_updates | 113520 | +| policy_gradient_loss | -0.057 | +| value_loss | 0.000384 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.249 | +| time/ | | +| fps | 309 | +| iterations | 5301 | +| time_elapsed | 17524 | +| total_timesteps | 5428224 | +| train/ | | +| approx_kl | 2.746599 | +| clip_fraction | 0.482 | +| clip_range | 0.2 | +| entropy_loss | -0.352 | +| explained_variance | -0.542 | +| learning_rate | 0.0001 | +| loss | -0.105 | +| n_updates | 113530 | +| policy_gradient_loss | -0.0657 | +| value_loss | 0.000755 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.249 | +| time/ | | +| fps | 309 | +| iterations | 5302 | +| time_elapsed | 17528 | +| total_timesteps | 5429248 | +| train/ | | +| approx_kl | 2.5008526 | +| clip_fraction | 0.491 | +| clip_range | 0.2 | +| entropy_loss | -0.363 | +| explained_variance | -1.39 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 113540 | +| policy_gradient_loss | -0.0633 | +| value_loss | 0.000723 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.249 | +| time/ | | +| fps | 309 | +| iterations | 5303 | +| time_elapsed | 17531 | +| total_timesteps | 5430272 | +| train/ | | +| approx_kl | 2.9456744 | +| clip_fraction | 0.479 | +| clip_range | 0.2 | +| entropy_loss | -0.371 | +| explained_variance | -1.19 | +| learning_rate | 0.0001 | +| loss | -0.0919 | +| n_updates | 113550 | +| policy_gradient_loss | -0.0661 | +| value_loss | 0.00064 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.251 | +| time/ | | +| fps | 309 | +| iterations | 5304 | +| time_elapsed | 17534 | +| total_timesteps | 5431296 | +| train/ | | +| approx_kl | 1.4211986 | +| clip_fraction | 0.496 | +| clip_range | 0.2 | +| entropy_loss | -0.42 | +| explained_variance | -8.4 | +| learning_rate | 0.0001 | +| loss | -0.0972 | +| n_updates | 113560 | +| policy_gradient_loss | -0.074 | +| value_loss | 0.000156 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.252 | +| time/ | | +| fps | 309 | +| iterations | 5305 | +| time_elapsed | 17537 | +| total_timesteps | 5432320 | +| train/ | | +| approx_kl | 1.7339509 | +| clip_fraction | 0.459 | +| clip_range | 0.2 | +| entropy_loss | -0.384 | +| explained_variance | -0.723 | +| learning_rate | 0.0001 | +| loss | -0.0775 | +| n_updates | 113570 | +| policy_gradient_loss | -0.0517 | +| value_loss | 0.000446 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.252 | +| time/ | | +| fps | 309 | +| iterations | 5306 | +| time_elapsed | 17540 | +| total_timesteps | 5433344 | +| train/ | | +| approx_kl | 1.6869048 | +| clip_fraction | 0.489 | +| clip_range | 0.2 | +| entropy_loss | -0.396 | +| explained_variance | -2.01 | +| learning_rate | 0.0001 | +| loss | -0.0929 | +| n_updates | 113580 | +| policy_gradient_loss | -0.0613 | +| value_loss | 0.000459 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.246 | +| time/ | | +| fps | 309 | +| iterations | 5307 | +| time_elapsed | 17543 | +| total_timesteps | 5434368 | +| train/ | | +| approx_kl | 1.8499854 | +| clip_fraction | 0.493 | +| clip_range | 0.2 | +| entropy_loss | -0.444 | +| explained_variance | -5.37 | +| learning_rate | 0.0001 | +| loss | -0.1 | +| n_updates | 113590 | +| policy_gradient_loss | -0.0651 | +| value_loss | 0.000321 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.244 | +| time/ | | +| fps | 309 | +| iterations | 5308 | +| time_elapsed | 17546 | +| total_timesteps | 5435392 | +| train/ | | +| approx_kl | 2.5394287 | +| clip_fraction | 0.464 | +| clip_range | 0.2 | +| entropy_loss | -0.344 | +| explained_variance | -1.22 | +| learning_rate | 0.0001 | +| loss | -0.0826 | +| n_updates | 113600 | +| policy_gradient_loss | -0.0709 | +| value_loss | 0.000607 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.244 | +| time/ | | +| fps | 309 | +| iterations | 5309 | +| time_elapsed | 17550 | +| total_timesteps | 5436416 | +| train/ | | +| approx_kl | 1.9638567 | +| clip_fraction | 0.47 | +| clip_range | 0.2 | +| entropy_loss | -0.389 | +| explained_variance | -2.04 | +| learning_rate | 0.0001 | +| loss | -0.0759 | +| n_updates | 113610 | +| policy_gradient_loss | -0.0603 | +| value_loss | 0.000544 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.244 | +| time/ | | +| fps | 309 | +| iterations | 5310 | +| time_elapsed | 17553 | +| total_timesteps | 5437440 | +| train/ | | +| approx_kl | 2.5661135 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.357 | +| explained_variance | -2.45 | +| learning_rate | 0.0001 | +| loss | -0.0942 | +| n_updates | 113620 | +| policy_gradient_loss | -0.0707 | +| value_loss | 0.000635 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.247 | +| time/ | | +| fps | 309 | +| iterations | 5311 | +| time_elapsed | 17556 | +| total_timesteps | 5438464 | +| train/ | | +| approx_kl | 1.9628406 | +| clip_fraction | 0.455 | +| clip_range | 0.2 | +| entropy_loss | -0.337 | +| explained_variance | -1.32 | +| learning_rate | 0.0001 | +| loss | -0.0881 | +| n_updates | 113630 | +| policy_gradient_loss | -0.0659 | +| value_loss | 0.000672 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.247 | +| time/ | | +| fps | 309 | +| iterations | 5312 | +| time_elapsed | 17559 | +| total_timesteps | 5439488 | +| train/ | | +| approx_kl | 2.3459668 | +| clip_fraction | 0.489 | +| clip_range | 0.2 | +| entropy_loss | -0.351 | +| explained_variance | -1.91 | +| learning_rate | 0.0001 | +| loss | -0.105 | +| n_updates | 113640 | +| policy_gradient_loss | -0.0724 | +| value_loss | 0.000688 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.247 | +| time/ | | +| fps | 309 | +| iterations | 5313 | +| time_elapsed | 17563 | +| total_timesteps | 5440512 | +| train/ | | +| approx_kl | 2.3420205 | +| clip_fraction | 0.499 | +| clip_range | 0.2 | +| entropy_loss | -0.347 | +| explained_variance | -3.92 | +| learning_rate | 0.0001 | +| loss | -0.0717 | +| n_updates | 113650 | +| policy_gradient_loss | -0.0732 | +| value_loss | 0.000562 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.248 | +| time/ | | +| fps | 309 | +| iterations | 5314 | +| time_elapsed | 17566 | +| total_timesteps | 5441536 | +| train/ | | +| approx_kl | 2.8111014 | +| clip_fraction | 0.489 | +| clip_range | 0.2 | +| entropy_loss | -0.34 | +| explained_variance | -2.21 | +| learning_rate | 0.0001 | +| loss | -0.0979 | +| n_updates | 113660 | +| policy_gradient_loss | -0.0732 | +| value_loss | 0.000578 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.82e+03 | +| ep_rew_mean | 0.247 | +| time/ | | +| fps | 309 | +| iterations | 5315 | +| time_elapsed | 17570 | +| total_timesteps | 5442560 | +| train/ | | +| approx_kl | 2.3871403 | +| clip_fraction | 0.447 | +| clip_range | 0.2 | +| entropy_loss | -0.36 | +| explained_variance | -1.36 | +| learning_rate | 0.0001 | +| loss | -0.0739 | +| n_updates | 113670 | +| policy_gradient_loss | -0.0591 | +| value_loss | 0.000534 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.82e+03 | +| ep_rew_mean | 0.247 | +| time/ | | +| fps | 309 | +| iterations | 5316 | +| time_elapsed | 17573 | +| total_timesteps | 5443584 | +| train/ | | +| approx_kl | 2.5519855 | +| clip_fraction | 0.456 | +| clip_range | 0.2 | +| entropy_loss | -0.315 | +| explained_variance | -3.65 | +| learning_rate | 0.0001 | +| loss | -0.0869 | +| n_updates | 113680 | +| policy_gradient_loss | -0.0686 | +| value_loss | 0.000475 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.25 | +| time/ | | +| fps | 309 | +| iterations | 5317 | +| time_elapsed | 17577 | +| total_timesteps | 5444608 | +| train/ | | +| approx_kl | 2.1089122 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.363 | +| explained_variance | -2.01 | +| learning_rate | 0.0001 | +| loss | -0.0373 | +| n_updates | 113690 | +| policy_gradient_loss | -0.0695 | +| value_loss | 0.000272 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.25 | +| time/ | | +| fps | 309 | +| iterations | 5318 | +| time_elapsed | 17580 | +| total_timesteps | 5445632 | +| train/ | | +| approx_kl | 1.8487985 | +| clip_fraction | 0.477 | +| clip_range | 0.2 | +| entropy_loss | -0.364 | +| explained_variance | -1 | +| learning_rate | 0.0001 | +| loss | -0.0702 | +| n_updates | 113700 | +| policy_gradient_loss | -0.0615 | +| value_loss | 0.000413 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.25 | +| time/ | | +| fps | 309 | +| iterations | 5319 | +| time_elapsed | 17583 | +| total_timesteps | 5446656 | +| train/ | | +| approx_kl | 2.4542756 | +| clip_fraction | 0.458 | +| clip_range | 0.2 | +| entropy_loss | -0.336 | +| explained_variance | -1.86 | +| learning_rate | 0.0001 | +| loss | -0.0809 | +| n_updates | 113710 | +| policy_gradient_loss | -0.0551 | +| value_loss | 0.000514 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.252 | +| time/ | | +| fps | 309 | +| iterations | 5320 | +| time_elapsed | 17587 | +| total_timesteps | 5447680 | +| train/ | | +| approx_kl | 2.6382089 | +| clip_fraction | 0.456 | +| clip_range | 0.2 | +| entropy_loss | -0.334 | +| explained_variance | -2.68 | +| learning_rate | 0.0001 | +| loss | -0.109 | +| n_updates | 113720 | +| policy_gradient_loss | -0.0656 | +| value_loss | 0.000492 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.25 | +| time/ | | +| fps | 309 | +| iterations | 5321 | +| time_elapsed | 17590 | +| total_timesteps | 5448704 | +| train/ | | +| approx_kl | 2.314231 | +| clip_fraction | 0.456 | +| clip_range | 0.2 | +| entropy_loss | -0.324 | +| explained_variance | -1.31 | +| learning_rate | 0.0001 | +| loss | -0.084 | +| n_updates | 113730 | +| policy_gradient_loss | -0.0588 | +| value_loss | 0.000513 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.25 | +| time/ | | +| fps | 309 | +| iterations | 5322 | +| time_elapsed | 17593 | +| total_timesteps | 5449728 | +| train/ | | +| approx_kl | 2.302482 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.367 | +| explained_variance | -0.914 | +| learning_rate | 0.0001 | +| loss | -0.0765 | +| n_updates | 113740 | +| policy_gradient_loss | -0.0656 | +| value_loss | 0.000625 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.251 | +| time/ | | +| fps | 309 | +| iterations | 5323 | +| time_elapsed | 17597 | +| total_timesteps | 5450752 | +| train/ | | +| approx_kl | 2.72158 | +| clip_fraction | 0.499 | +| clip_range | 0.2 | +| entropy_loss | -0.371 | +| explained_variance | -1.7 | +| learning_rate | 0.0001 | +| loss | -0.0793 | +| n_updates | 113750 | +| policy_gradient_loss | -0.0753 | +| value_loss | 0.000647 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.251 | +| time/ | | +| fps | 309 | +| iterations | 5324 | +| time_elapsed | 17600 | +| total_timesteps | 5451776 | +| train/ | | +| approx_kl | 2.489846 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.393 | +| explained_variance | -3.19 | +| learning_rate | 0.0001 | +| loss | -0.114 | +| n_updates | 113760 | +| policy_gradient_loss | -0.0665 | +| value_loss | 0.000381 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.251 | +| time/ | | +| fps | 309 | +| iterations | 5325 | +| time_elapsed | 17603 | +| total_timesteps | 5452800 | +| train/ | | +| approx_kl | 4.886771 | +| clip_fraction | 0.472 | +| clip_range | 0.2 | +| entropy_loss | -0.361 | +| explained_variance | -1.95 | +| learning_rate | 0.0001 | +| loss | -0.0532 | +| n_updates | 113770 | +| policy_gradient_loss | -0.0663 | +| value_loss | 0.000351 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.82e+03 | +| ep_rew_mean | 0.251 | +| time/ | | +| fps | 309 | +| iterations | 5326 | +| time_elapsed | 17606 | +| total_timesteps | 5453824 | +| train/ | | +| approx_kl | 2.5511432 | +| clip_fraction | 0.473 | +| clip_range | 0.2 | +| entropy_loss | -0.348 | +| explained_variance | -1.61 | +| learning_rate | 0.0001 | +| loss | -0.106 | +| n_updates | 113780 | +| policy_gradient_loss | -0.0688 | +| value_loss | 0.000495 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.82e+03 | +| ep_rew_mean | 0.251 | +| time/ | | +| fps | 309 | +| iterations | 5327 | +| time_elapsed | 17609 | +| total_timesteps | 5454848 | +| train/ | | +| approx_kl | 2.3539224 | +| clip_fraction | 0.482 | +| clip_range | 0.2 | +| entropy_loss | -0.356 | +| explained_variance | -1.14 | +| learning_rate | 0.0001 | +| loss | -0.0787 | +| n_updates | 113790 | +| policy_gradient_loss | -0.0646 | +| value_loss | 0.000426 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.82e+03 | +| ep_rew_mean | 0.251 | +| time/ | | +| fps | 309 | +| iterations | 5328 | +| time_elapsed | 17612 | +| total_timesteps | 5455872 | +| train/ | | +| approx_kl | 2.3672168 | +| clip_fraction | 0.463 | +| clip_range | 0.2 | +| entropy_loss | -0.323 | +| explained_variance | -1.09 | +| learning_rate | 0.0001 | +| loss | -0.09 | +| n_updates | 113800 | +| policy_gradient_loss | -0.0658 | +| value_loss | 0.000613 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.81e+03 | +| ep_rew_mean | 0.255 | +| time/ | | +| fps | 309 | +| iterations | 5329 | +| time_elapsed | 17615 | +| total_timesteps | 5456896 | +| train/ | | +| approx_kl | 2.0255308 | +| clip_fraction | 0.44 | +| clip_range | 0.2 | +| entropy_loss | -0.36 | +| explained_variance | -0.765 | +| learning_rate | 0.0001 | +| loss | -0.0526 | +| n_updates | 113810 | +| policy_gradient_loss | -0.05 | +| value_loss | 0.000508 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.8e+03 | +| ep_rew_mean | 0.253 | +| time/ | | +| fps | 309 | +| iterations | 5330 | +| time_elapsed | 17619 | +| total_timesteps | 5457920 | +| train/ | | +| approx_kl | 2.4177585 | +| clip_fraction | 0.456 | +| clip_range | 0.2 | +| entropy_loss | -0.346 | +| explained_variance | -0.938 | +| learning_rate | 0.0001 | +| loss | -0.0926 | +| n_updates | 113820 | +| policy_gradient_loss | -0.0674 | +| value_loss | 0.000708 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.8e+03 | +| ep_rew_mean | 0.253 | +| time/ | | +| fps | 309 | +| iterations | 5331 | +| time_elapsed | 17622 | +| total_timesteps | 5458944 | +| train/ | | +| approx_kl | 1.9418938 | +| clip_fraction | 0.422 | +| clip_range | 0.2 | +| entropy_loss | -0.327 | +| explained_variance | -0.774 | +| learning_rate | 0.0001 | +| loss | -0.0828 | +| n_updates | 113830 | +| policy_gradient_loss | -0.056 | +| value_loss | 0.000605 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.8e+03 | +| ep_rew_mean | 0.253 | +| time/ | | +| fps | 309 | +| iterations | 5332 | +| time_elapsed | 17625 | +| total_timesteps | 5459968 | +| train/ | | +| approx_kl | 2.208147 | +| clip_fraction | 0.443 | +| clip_range | 0.2 | +| entropy_loss | -0.307 | +| explained_variance | -2.5 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 113840 | +| policy_gradient_loss | -0.0634 | +| value_loss | 0.000561 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.81e+03 | +| ep_rew_mean | 0.253 | +| time/ | | +| fps | 309 | +| iterations | 5333 | +| time_elapsed | 17629 | +| total_timesteps | 5460992 | +| train/ | | +| approx_kl | 2.200005 | +| clip_fraction | 0.474 | +| clip_range | 0.2 | +| entropy_loss | -0.341 | +| explained_variance | -6.1 | +| learning_rate | 0.0001 | +| loss | -0.0959 | +| n_updates | 113850 | +| policy_gradient_loss | -0.0711 | +| value_loss | 0.000402 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.81e+03 | +| ep_rew_mean | 0.253 | +| time/ | | +| fps | 309 | +| iterations | 5334 | +| time_elapsed | 17632 | +| total_timesteps | 5462016 | +| train/ | | +| approx_kl | 2.4154456 | +| clip_fraction | 0.449 | +| clip_range | 0.2 | +| entropy_loss | -0.302 | +| explained_variance | -0.622 | +| learning_rate | 0.0001 | +| loss | -0.0712 | +| n_updates | 113860 | +| policy_gradient_loss | -0.0543 | +| value_loss | 0.000443 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.81e+03 | +| ep_rew_mean | 0.25 | +| time/ | | +| fps | 309 | +| iterations | 5335 | +| time_elapsed | 17636 | +| total_timesteps | 5463040 | +| train/ | | +| approx_kl | 1.8084643 | +| clip_fraction | 0.506 | +| clip_range | 0.2 | +| entropy_loss | -0.395 | +| explained_variance | -4.45 | +| learning_rate | 0.0001 | +| loss | -0.0984 | +| n_updates | 113870 | +| policy_gradient_loss | -0.0692 | +| value_loss | 0.000421 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.81e+03 | +| ep_rew_mean | 0.25 | +| time/ | | +| fps | 309 | +| iterations | 5336 | +| time_elapsed | 17639 | +| total_timesteps | 5464064 | +| train/ | | +| approx_kl | 2.2753997 | +| clip_fraction | 0.438 | +| clip_range | 0.2 | +| entropy_loss | -0.31 | +| explained_variance | -1.64 | +| learning_rate | 0.0001 | +| loss | -0.083 | +| n_updates | 113880 | +| policy_gradient_loss | -0.0573 | +| value_loss | 0.000755 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.81e+03 | +| ep_rew_mean | 0.25 | +| time/ | | +| fps | 309 | +| iterations | 5337 | +| time_elapsed | 17643 | +| total_timesteps | 5465088 | +| train/ | | +| approx_kl | 1.920196 | +| clip_fraction | 0.469 | +| clip_range | 0.2 | +| entropy_loss | -0.373 | +| explained_variance | -3.44 | +| learning_rate | 0.0001 | +| loss | -0.0978 | +| n_updates | 113890 | +| policy_gradient_loss | -0.0599 | +| value_loss | 0.000249 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.82e+03 | +| ep_rew_mean | 0.253 | +| time/ | | +| fps | 309 | +| iterations | 5338 | +| time_elapsed | 17646 | +| total_timesteps | 5466112 | +| train/ | | +| approx_kl | 1.9724388 | +| clip_fraction | 0.468 | +| clip_range | 0.2 | +| entropy_loss | -0.362 | +| explained_variance | -0.835 | +| learning_rate | 0.0001 | +| loss | -0.0908 | +| n_updates | 113900 | +| policy_gradient_loss | -0.0643 | +| value_loss | 0.00049 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.82e+03 | +| ep_rew_mean | 0.253 | +| time/ | | +| fps | 309 | +| iterations | 5339 | +| time_elapsed | 17650 | +| total_timesteps | 5467136 | +| train/ | | +| approx_kl | 1.9562715 | +| clip_fraction | 0.427 | +| clip_range | 0.2 | +| entropy_loss | -0.315 | +| explained_variance | -1.76 | +| learning_rate | 0.0001 | +| loss | -0.0466 | +| n_updates | 113910 | +| policy_gradient_loss | -0.0575 | +| value_loss | 0.000619 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.25 | +| time/ | | +| fps | 309 | +| iterations | 5340 | +| time_elapsed | 17653 | +| total_timesteps | 5468160 | +| train/ | | +| approx_kl | 1.9436343 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.409 | +| explained_variance | -1.01 | +| learning_rate | 0.0001 | +| loss | -0.0985 | +| n_updates | 113920 | +| policy_gradient_loss | -0.0614 | +| value_loss | 0.000264 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.25 | +| time/ | | +| fps | 309 | +| iterations | 5341 | +| time_elapsed | 17656 | +| total_timesteps | 5469184 | +| train/ | | +| approx_kl | 2.3667026 | +| clip_fraction | 0.456 | +| clip_range | 0.2 | +| entropy_loss | -0.368 | +| explained_variance | -0.837 | +| learning_rate | 0.0001 | +| loss | -0.0623 | +| n_updates | 113930 | +| policy_gradient_loss | -0.0604 | +| value_loss | 0.000682 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.82e+03 | +| ep_rew_mean | 0.25 | +| time/ | | +| fps | 309 | +| iterations | 5342 | +| time_elapsed | 17659 | +| total_timesteps | 5470208 | +| train/ | | +| approx_kl | 2.2856805 | +| clip_fraction | 0.482 | +| clip_range | 0.2 | +| entropy_loss | -0.39 | +| explained_variance | -1.23 | +| learning_rate | 0.0001 | +| loss | -0.0789 | +| n_updates | 113940 | +| policy_gradient_loss | -0.067 | +| value_loss | 0.000648 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.82e+03 | +| ep_rew_mean | 0.25 | +| time/ | | +| fps | 309 | +| iterations | 5343 | +| time_elapsed | 17662 | +| total_timesteps | 5471232 | +| train/ | | +| approx_kl | 2.1864445 | +| clip_fraction | 0.433 | +| clip_range | 0.2 | +| entropy_loss | -0.319 | +| explained_variance | -0.617 | +| learning_rate | 0.0001 | +| loss | -0.0801 | +| n_updates | 113950 | +| policy_gradient_loss | -0.0584 | +| value_loss | 0.000683 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.254 | +| time/ | | +| fps | 309 | +| iterations | 5344 | +| time_elapsed | 17666 | +| total_timesteps | 5472256 | +| train/ | | +| approx_kl | 2.7395234 | +| clip_fraction | 0.454 | +| clip_range | 0.2 | +| entropy_loss | -0.354 | +| explained_variance | -1.48 | +| learning_rate | 0.0001 | +| loss | -0.111 | +| n_updates | 113960 | +| policy_gradient_loss | -0.0649 | +| value_loss | 0.000539 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.254 | +| time/ | | +| fps | 309 | +| iterations | 5345 | +| time_elapsed | 17669 | +| total_timesteps | 5473280 | +| train/ | | +| approx_kl | 2.701889 | +| clip_fraction | 0.462 | +| clip_range | 0.2 | +| entropy_loss | -0.376 | +| explained_variance | -1.59 | +| learning_rate | 0.0001 | +| loss | -0.0719 | +| n_updates | 113970 | +| policy_gradient_loss | -0.0628 | +| value_loss | 0.000484 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.258 | +| time/ | | +| fps | 309 | +| iterations | 5346 | +| time_elapsed | 17672 | +| total_timesteps | 5474304 | +| train/ | | +| approx_kl | 2.1526642 | +| clip_fraction | 0.464 | +| clip_range | 0.2 | +| entropy_loss | -0.317 | +| explained_variance | -2.63 | +| learning_rate | 0.0001 | +| loss | -0.0822 | +| n_updates | 113980 | +| policy_gradient_loss | -0.0691 | +| value_loss | 0.00051 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.258 | +| time/ | | +| fps | 309 | +| iterations | 5347 | +| time_elapsed | 17675 | +| total_timesteps | 5475328 | +| train/ | | +| approx_kl | 3.4947777 | +| clip_fraction | 0.42 | +| clip_range | 0.2 | +| entropy_loss | -0.318 | +| explained_variance | -0.582 | +| learning_rate | 0.0001 | +| loss | -0.0589 | +| n_updates | 113990 | +| policy_gradient_loss | -0.0565 | +| value_loss | 0.000467 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.259 | +| time/ | | +| fps | 309 | +| iterations | 5348 | +| time_elapsed | 17678 | +| total_timesteps | 5476352 | +| train/ | | +| approx_kl | 2.8510497 | +| clip_fraction | 0.459 | +| clip_range | 0.2 | +| entropy_loss | -0.338 | +| explained_variance | -6.64 | +| learning_rate | 0.0001 | +| loss | -0.0917 | +| n_updates | 114000 | +| policy_gradient_loss | -0.0672 | +| value_loss | 0.000411 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.259 | +| time/ | | +| fps | 309 | +| iterations | 5349 | +| time_elapsed | 17682 | +| total_timesteps | 5477376 | +| train/ | | +| approx_kl | 2.244278 | +| clip_fraction | 0.469 | +| clip_range | 0.2 | +| entropy_loss | -0.351 | +| explained_variance | -1.37 | +| learning_rate | 0.0001 | +| loss | -0.0835 | +| n_updates | 114010 | +| policy_gradient_loss | -0.0642 | +| value_loss | 0.000384 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.257 | +| time/ | | +| fps | 309 | +| iterations | 5350 | +| time_elapsed | 17685 | +| total_timesteps | 5478400 | +| train/ | | +| approx_kl | 6.4283504 | +| clip_fraction | 0.466 | +| clip_range | 0.2 | +| entropy_loss | -0.349 | +| explained_variance | -2.47 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 114020 | +| policy_gradient_loss | -0.0648 | +| value_loss | 0.000462 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.257 | +| time/ | | +| fps | 309 | +| iterations | 5351 | +| time_elapsed | 17688 | +| total_timesteps | 5479424 | +| train/ | | +| approx_kl | 2.0326633 | +| clip_fraction | 0.441 | +| clip_range | 0.2 | +| entropy_loss | -0.343 | +| explained_variance | -0.89 | +| learning_rate | 0.0001 | +| loss | -0.05 | +| n_updates | 114030 | +| policy_gradient_loss | -0.0538 | +| value_loss | 0.000333 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.26 | +| time/ | | +| fps | 309 | +| iterations | 5352 | +| time_elapsed | 17692 | +| total_timesteps | 5480448 | +| train/ | | +| approx_kl | 1.76964 | +| clip_fraction | 0.52 | +| clip_range | 0.2 | +| entropy_loss | -0.416 | +| explained_variance | -1.17 | +| learning_rate | 0.0001 | +| loss | -0.0965 | +| n_updates | 114040 | +| policy_gradient_loss | -0.0742 | +| value_loss | 0.000573 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.26 | +| time/ | | +| fps | 309 | +| iterations | 5353 | +| time_elapsed | 17695 | +| total_timesteps | 5481472 | +| train/ | | +| approx_kl | 1.9086199 | +| clip_fraction | 0.434 | +| clip_range | 0.2 | +| entropy_loss | -0.324 | +| explained_variance | -2.07 | +| learning_rate | 0.0001 | +| loss | -0.0848 | +| n_updates | 114050 | +| policy_gradient_loss | -0.0581 | +| value_loss | 0.000531 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.259 | +| time/ | | +| fps | 309 | +| iterations | 5354 | +| time_elapsed | 17698 | +| total_timesteps | 5482496 | +| train/ | | +| approx_kl | 1.9682924 | +| clip_fraction | 0.515 | +| clip_range | 0.2 | +| entropy_loss | -0.437 | +| explained_variance | -1.88 | +| learning_rate | 0.0001 | +| loss | -0.0582 | +| n_updates | 114060 | +| policy_gradient_loss | -0.0614 | +| value_loss | 0.000471 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.259 | +| time/ | | +| fps | 309 | +| iterations | 5355 | +| time_elapsed | 17702 | +| total_timesteps | 5483520 | +| train/ | | +| approx_kl | 2.6335974 | +| clip_fraction | 0.436 | +| clip_range | 0.2 | +| entropy_loss | -0.331 | +| explained_variance | -1.76 | +| learning_rate | 0.0001 | +| loss | -0.088 | +| n_updates | 114070 | +| policy_gradient_loss | -0.0604 | +| value_loss | 0.000579 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.262 | +| time/ | | +| fps | 309 | +| iterations | 5356 | +| time_elapsed | 17705 | +| total_timesteps | 5484544 | +| train/ | | +| approx_kl | 1.788511 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.404 | +| explained_variance | -1.95 | +| learning_rate | 0.0001 | +| loss | -0.0967 | +| n_updates | 114080 | +| policy_gradient_loss | -0.0682 | +| value_loss | 0.000531 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.265 | +| time/ | | +| fps | 309 | +| iterations | 5357 | +| time_elapsed | 17708 | +| total_timesteps | 5485568 | +| train/ | | +| approx_kl | 2.0043957 | +| clip_fraction | 0.439 | +| clip_range | 0.2 | +| entropy_loss | -0.352 | +| explained_variance | -0.841 | +| learning_rate | 0.0001 | +| loss | -0.0681 | +| n_updates | 114090 | +| policy_gradient_loss | -0.0567 | +| value_loss | 0.000367 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.265 | +| time/ | | +| fps | 309 | +| iterations | 5358 | +| time_elapsed | 17712 | +| total_timesteps | 5486592 | +| train/ | | +| approx_kl | 1.9086304 | +| clip_fraction | 0.437 | +| clip_range | 0.2 | +| entropy_loss | -0.365 | +| explained_variance | -0.47 | +| learning_rate | 0.0001 | +| loss | -0.0268 | +| n_updates | 114100 | +| policy_gradient_loss | -0.0538 | +| value_loss | 0.000723 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.265 | +| time/ | | +| fps | 309 | +| iterations | 5359 | +| time_elapsed | 17715 | +| total_timesteps | 5487616 | +| train/ | | +| approx_kl | 2.4089289 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.4 | +| explained_variance | -1.64 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 114110 | +| policy_gradient_loss | -0.0713 | +| value_loss | 0.000444 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.265 | +| time/ | | +| fps | 309 | +| iterations | 5360 | +| time_elapsed | 17718 | +| total_timesteps | 5488640 | +| train/ | | +| approx_kl | 2.248176 | +| clip_fraction | 0.445 | +| clip_range | 0.2 | +| entropy_loss | -0.3 | +| explained_variance | -1.64 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 114120 | +| policy_gradient_loss | -0.0627 | +| value_loss | 0.000582 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.264 | +| time/ | | +| fps | 309 | +| iterations | 5361 | +| time_elapsed | 17721 | +| total_timesteps | 5489664 | +| train/ | | +| approx_kl | 2.3882234 | +| clip_fraction | 0.463 | +| clip_range | 0.2 | +| entropy_loss | -0.358 | +| explained_variance | -8.47 | +| learning_rate | 0.0001 | +| loss | -0.0925 | +| n_updates | 114130 | +| policy_gradient_loss | -0.0727 | +| value_loss | 0.000325 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.265 | +| time/ | | +| fps | 309 | +| iterations | 5362 | +| time_elapsed | 17724 | +| total_timesteps | 5490688 | +| train/ | | +| approx_kl | 2.642857 | +| clip_fraction | 0.44 | +| clip_range | 0.2 | +| entropy_loss | -0.315 | +| explained_variance | -0.339 | +| learning_rate | 0.0001 | +| loss | -0.0636 | +| n_updates | 114140 | +| policy_gradient_loss | -0.0543 | +| value_loss | 0.000599 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.264 | +| time/ | | +| fps | 309 | +| iterations | 5363 | +| time_elapsed | 17727 | +| total_timesteps | 5491712 | +| train/ | | +| approx_kl | 4.8032613 | +| clip_fraction | 0.473 | +| clip_range | 0.2 | +| entropy_loss | -0.355 | +| explained_variance | -1.71 | +| learning_rate | 0.0001 | +| loss | -0.0892 | +| n_updates | 114150 | +| policy_gradient_loss | -0.0732 | +| value_loss | 0.000497 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.264 | +| time/ | | +| fps | 309 | +| iterations | 5364 | +| time_elapsed | 17731 | +| total_timesteps | 5492736 | +| train/ | | +| approx_kl | 2.433992 | +| clip_fraction | 0.439 | +| clip_range | 0.2 | +| entropy_loss | -0.319 | +| explained_variance | -0.125 | +| learning_rate | 0.0001 | +| loss | -0.0851 | +| n_updates | 114160 | +| policy_gradient_loss | -0.0486 | +| value_loss | 0.000509 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.262 | +| time/ | | +| fps | 309 | +| iterations | 5365 | +| time_elapsed | 17734 | +| total_timesteps | 5493760 | +| train/ | | +| approx_kl | 2.178281 | +| clip_fraction | 0.527 | +| clip_range | 0.2 | +| entropy_loss | -0.453 | +| explained_variance | -5.16 | +| learning_rate | 0.0001 | +| loss | -0.0936 | +| n_updates | 114170 | +| policy_gradient_loss | -0.0756 | +| value_loss | 0.00044 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.262 | +| time/ | | +| fps | 309 | +| iterations | 5366 | +| time_elapsed | 17737 | +| total_timesteps | 5494784 | +| train/ | | +| approx_kl | 2.0363731 | +| clip_fraction | 0.449 | +| clip_range | 0.2 | +| entropy_loss | -0.333 | +| explained_variance | -0.814 | +| learning_rate | 0.0001 | +| loss | -0.0721 | +| n_updates | 114180 | +| policy_gradient_loss | -0.0565 | +| value_loss | 0.000456 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.262 | +| time/ | | +| fps | 309 | +| iterations | 5367 | +| time_elapsed | 17740 | +| total_timesteps | 5495808 | +| train/ | | +| approx_kl | 13.128489 | +| clip_fraction | 0.488 | +| clip_range | 0.2 | +| entropy_loss | -0.4 | +| explained_variance | -2.26 | +| learning_rate | 0.0001 | +| loss | -0.0812 | +| n_updates | 114190 | +| policy_gradient_loss | -0.0676 | +| value_loss | 0.000473 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.261 | +| time/ | | +| fps | 309 | +| iterations | 5368 | +| time_elapsed | 17744 | +| total_timesteps | 5496832 | +| train/ | | +| approx_kl | 3.2967882 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.378 | +| explained_variance | -1.34 | +| learning_rate | 0.0001 | +| loss | -0.072 | +| n_updates | 114200 | +| policy_gradient_loss | -0.0637 | +| value_loss | 0.000478 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.261 | +| time/ | | +| fps | 309 | +| iterations | 5369 | +| time_elapsed | 17747 | +| total_timesteps | 5497856 | +| train/ | | +| approx_kl | 2.149747 | +| clip_fraction | 0.51 | +| clip_range | 0.2 | +| entropy_loss | -0.436 | +| explained_variance | -4.35 | +| learning_rate | 0.0001 | +| loss | -0.0973 | +| n_updates | 114210 | +| policy_gradient_loss | -0.0773 | +| value_loss | 0.000241 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.261 | +| time/ | | +| fps | 309 | +| iterations | 5370 | +| time_elapsed | 17751 | +| total_timesteps | 5498880 | +| train/ | | +| approx_kl | 2.04312 | +| clip_fraction | 0.465 | +| clip_range | 0.2 | +| entropy_loss | -0.373 | +| explained_variance | -0.489 | +| learning_rate | 0.0001 | +| loss | -0.0761 | +| n_updates | 114220 | +| policy_gradient_loss | -0.0629 | +| value_loss | 0.000547 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.265 | +| time/ | | +| fps | 309 | +| iterations | 5371 | +| time_elapsed | 17754 | +| total_timesteps | 5499904 | +| train/ | | +| approx_kl | 1.6422133 | +| clip_fraction | 0.519 | +| clip_range | 0.2 | +| entropy_loss | -0.435 | +| explained_variance | -1.41 | +| learning_rate | 0.0001 | +| loss | -0.0956 | +| n_updates | 114230 | +| policy_gradient_loss | -0.0766 | +| value_loss | 0.00035 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.265 | +| time/ | | +| fps | 309 | +| iterations | 5372 | +| time_elapsed | 17758 | +| total_timesteps | 5500928 | +| train/ | | +| approx_kl | 2.157608 | +| clip_fraction | 0.47 | +| clip_range | 0.2 | +| entropy_loss | -0.351 | +| explained_variance | -1.06 | +| learning_rate | 0.0001 | +| loss | -0.108 | +| n_updates | 114240 | +| policy_gradient_loss | -0.0621 | +| value_loss | 0.000473 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.261 | +| time/ | | +| fps | 309 | +| iterations | 5373 | +| time_elapsed | 17761 | +| total_timesteps | 5501952 | +| train/ | | +| approx_kl | 1.875715 | +| clip_fraction | 0.518 | +| clip_range | 0.2 | +| entropy_loss | -0.433 | +| explained_variance | -2.69 | +| learning_rate | 0.0001 | +| loss | -0.076 | +| n_updates | 114250 | +| policy_gradient_loss | -0.0722 | +| value_loss | 0.000482 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.261 | +| time/ | | +| fps | 309 | +| iterations | 5374 | +| time_elapsed | 17765 | +| total_timesteps | 5502976 | +| train/ | | +| approx_kl | 2.1674407 | +| clip_fraction | 0.505 | +| clip_range | 0.2 | +| entropy_loss | -0.427 | +| explained_variance | -1.15 | +| learning_rate | 0.0001 | +| loss | -0.065 | +| n_updates | 114260 | +| policy_gradient_loss | -0.0611 | +| value_loss | 0.000424 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.263 | +| time/ | | +| fps | 309 | +| iterations | 5375 | +| time_elapsed | 17768 | +| total_timesteps | 5504000 | +| train/ | | +| approx_kl | 2.3269486 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.414 | +| explained_variance | -2.91 | +| learning_rate | 0.0001 | +| loss | -0.0997 | +| n_updates | 114270 | +| policy_gradient_loss | -0.0696 | +| value_loss | 0.000306 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.263 | +| time/ | | +| fps | 309 | +| iterations | 5376 | +| time_elapsed | 17771 | +| total_timesteps | 5505024 | +| train/ | | +| approx_kl | 2.5172489 | +| clip_fraction | 0.457 | +| clip_range | 0.2 | +| entropy_loss | -0.37 | +| explained_variance | -0.62 | +| learning_rate | 0.0001 | +| loss | -0.0887 | +| n_updates | 114280 | +| policy_gradient_loss | -0.0632 | +| value_loss | 0.000378 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.266 | +| time/ | | +| fps | 309 | +| iterations | 5377 | +| time_elapsed | 17775 | +| total_timesteps | 5506048 | +| train/ | | +| approx_kl | 2.4735374 | +| clip_fraction | 0.505 | +| clip_range | 0.2 | +| entropy_loss | -0.425 | +| explained_variance | -3.35 | +| learning_rate | 0.0001 | +| loss | -0.0875 | +| n_updates | 114290 | +| policy_gradient_loss | -0.0762 | +| value_loss | 0.000403 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.266 | +| time/ | | +| fps | 309 | +| iterations | 5378 | +| time_elapsed | 17778 | +| total_timesteps | 5507072 | +| train/ | | +| approx_kl | 1.7097856 | +| clip_fraction | 0.459 | +| clip_range | 0.2 | +| entropy_loss | -0.395 | +| explained_variance | -0.585 | +| learning_rate | 0.0001 | +| loss | -0.0756 | +| n_updates | 114300 | +| policy_gradient_loss | -0.0613 | +| value_loss | 0.000405 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.264 | +| time/ | | +| fps | 309 | +| iterations | 5379 | +| time_elapsed | 17781 | +| total_timesteps | 5508096 | +| train/ | | +| approx_kl | 4.7694297 | +| clip_fraction | 0.525 | +| clip_range | 0.2 | +| entropy_loss | -0.44 | +| explained_variance | -2.02 | +| learning_rate | 0.0001 | +| loss | -0.0797 | +| n_updates | 114310 | +| policy_gradient_loss | -0.0709 | +| value_loss | 0.000612 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.267 | +| time/ | | +| fps | 309 | +| iterations | 5380 | +| time_elapsed | 17784 | +| total_timesteps | 5509120 | +| train/ | | +| approx_kl | 2.1488442 | +| clip_fraction | 0.5 | +| clip_range | 0.2 | +| entropy_loss | -0.447 | +| explained_variance | -0.725 | +| learning_rate | 0.0001 | +| loss | -0.0742 | +| n_updates | 114320 | +| policy_gradient_loss | -0.066 | +| value_loss | 0.000589 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.27 | +| time/ | | +| fps | 309 | +| iterations | 5381 | +| time_elapsed | 17787 | +| total_timesteps | 5510144 | +| train/ | | +| approx_kl | 1.4244473 | +| clip_fraction | 0.489 | +| clip_range | 0.2 | +| entropy_loss | -0.472 | +| explained_variance | -0.342 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 114330 | +| policy_gradient_loss | -0.0629 | +| value_loss | 0.000768 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.82e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 309 | +| iterations | 5382 | +| time_elapsed | 17790 | +| total_timesteps | 5511168 | +| train/ | | +| approx_kl | 1.835625 | +| clip_fraction | 0.473 | +| clip_range | 0.2 | +| entropy_loss | -0.402 | +| explained_variance | -0.71 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 114340 | +| policy_gradient_loss | -0.0701 | +| value_loss | 0.000948 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.82e+03 | +| ep_rew_mean | 0.273 | +| time/ | | +| fps | 309 | +| iterations | 5383 | +| time_elapsed | 17794 | +| total_timesteps | 5512192 | +| train/ | | +| approx_kl | 1.7500325 | +| clip_fraction | 0.46 | +| clip_range | 0.2 | +| entropy_loss | -0.368 | +| explained_variance | -0.289 | +| learning_rate | 0.0001 | +| loss | -0.0836 | +| n_updates | 114350 | +| policy_gradient_loss | -0.0675 | +| value_loss | 0.000698 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.82e+03 | +| ep_rew_mean | 0.273 | +| time/ | | +| fps | 309 | +| iterations | 5384 | +| time_elapsed | 17797 | +| total_timesteps | 5513216 | +| train/ | | +| approx_kl | 2.3493512 | +| clip_fraction | 0.485 | +| clip_range | 0.2 | +| entropy_loss | -0.396 | +| explained_variance | -1.3 | +| learning_rate | 0.0001 | +| loss | -0.0993 | +| n_updates | 114360 | +| policy_gradient_loss | -0.0671 | +| value_loss | 0.000497 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.82e+03 | +| ep_rew_mean | 0.273 | +| time/ | | +| fps | 309 | +| iterations | 5385 | +| time_elapsed | 17800 | +| total_timesteps | 5514240 | +| train/ | | +| approx_kl | 2.238016 | +| clip_fraction | 0.508 | +| clip_range | 0.2 | +| entropy_loss | -0.423 | +| explained_variance | -2.1 | +| learning_rate | 0.0001 | +| loss | -0.099 | +| n_updates | 114370 | +| policy_gradient_loss | -0.0762 | +| value_loss | 0.000389 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.81e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 309 | +| iterations | 5386 | +| time_elapsed | 17803 | +| total_timesteps | 5515264 | +| train/ | | +| approx_kl | 1.967443 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.405 | +| explained_variance | -3.05 | +| learning_rate | 0.0001 | +| loss | -0.11 | +| n_updates | 114380 | +| policy_gradient_loss | -0.0749 | +| value_loss | 0.000348 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.81e+03 | +| ep_rew_mean | 0.277 | +| time/ | | +| fps | 309 | +| iterations | 5387 | +| time_elapsed | 17807 | +| total_timesteps | 5516288 | +| train/ | | +| approx_kl | 4.6301737 | +| clip_fraction | 0.465 | +| clip_range | 0.2 | +| entropy_loss | -0.37 | +| explained_variance | -0.611 | +| learning_rate | 0.0001 | +| loss | -0.0725 | +| n_updates | 114390 | +| policy_gradient_loss | -0.063 | +| value_loss | 0.000409 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.81e+03 | +| ep_rew_mean | 0.277 | +| time/ | | +| fps | 309 | +| iterations | 5388 | +| time_elapsed | 17810 | +| total_timesteps | 5517312 | +| train/ | | +| approx_kl | 1.3690604 | +| clip_fraction | 0.458 | +| clip_range | 0.2 | +| entropy_loss | -0.396 | +| explained_variance | -0.143 | +| learning_rate | 0.0001 | +| loss | -0.0766 | +| n_updates | 114400 | +| policy_gradient_loss | -0.0577 | +| value_loss | 0.000288 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.81e+03 | +| ep_rew_mean | 0.277 | +| time/ | | +| fps | 309 | +| iterations | 5389 | +| time_elapsed | 17813 | +| total_timesteps | 5518336 | +| train/ | | +| approx_kl | 2.3601441 | +| clip_fraction | 0.512 | +| clip_range | 0.2 | +| entropy_loss | -0.398 | +| explained_variance | -3.27 | +| learning_rate | 0.0001 | +| loss | -0.112 | +| n_updates | 114410 | +| policy_gradient_loss | -0.0711 | +| value_loss | 0.000508 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.81e+03 | +| ep_rew_mean | 0.277 | +| time/ | | +| fps | 309 | +| iterations | 5390 | +| time_elapsed | 17816 | +| total_timesteps | 5519360 | +| train/ | | +| approx_kl | 2.8113735 | +| clip_fraction | 0.514 | +| clip_range | 0.2 | +| entropy_loss | -0.407 | +| explained_variance | -12.2 | +| learning_rate | 0.0001 | +| loss | -0.106 | +| n_updates | 114420 | +| policy_gradient_loss | -0.0774 | +| value_loss | 0.00036 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.82e+03 | +| ep_rew_mean | 0.278 | +| time/ | | +| fps | 309 | +| iterations | 5391 | +| time_elapsed | 17820 | +| total_timesteps | 5520384 | +| train/ | | +| approx_kl | 1.8483217 | +| clip_fraction | 0.502 | +| clip_range | 0.2 | +| entropy_loss | -0.425 | +| explained_variance | -1.96 | +| learning_rate | 0.0001 | +| loss | -0.0771 | +| n_updates | 114430 | +| policy_gradient_loss | -0.0707 | +| value_loss | 0.000297 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.82e+03 | +| ep_rew_mean | 0.278 | +| time/ | | +| fps | 309 | +| iterations | 5392 | +| time_elapsed | 17823 | +| total_timesteps | 5521408 | +| train/ | | +| approx_kl | 2.305696 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.379 | +| explained_variance | -0.43 | +| learning_rate | 0.0001 | +| loss | -0.0879 | +| n_updates | 114440 | +| policy_gradient_loss | -0.0531 | +| value_loss | 0.000522 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.272 | +| time/ | | +| fps | 309 | +| iterations | 5393 | +| time_elapsed | 17826 | +| total_timesteps | 5522432 | +| train/ | | +| approx_kl | 2.3392944 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.375 | +| explained_variance | -8.74 | +| learning_rate | 0.0001 | +| loss | -0.0909 | +| n_updates | 114450 | +| policy_gradient_loss | -0.068 | +| value_loss | 0.000431 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.272 | +| time/ | | +| fps | 309 | +| iterations | 5394 | +| time_elapsed | 17830 | +| total_timesteps | 5523456 | +| train/ | | +| approx_kl | 2.1226857 | +| clip_fraction | 0.474 | +| clip_range | 0.2 | +| entropy_loss | -0.395 | +| explained_variance | -1.32 | +| learning_rate | 0.0001 | +| loss | -0.0675 | +| n_updates | 114460 | +| policy_gradient_loss | -0.0673 | +| value_loss | 0.000465 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.272 | +| time/ | | +| fps | 309 | +| iterations | 5395 | +| time_elapsed | 17833 | +| total_timesteps | 5524480 | +| train/ | | +| approx_kl | 2.0034394 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.391 | +| explained_variance | -0.502 | +| learning_rate | 0.0001 | +| loss | -0.0594 | +| n_updates | 114470 | +| policy_gradient_loss | -0.0591 | +| value_loss | 0.000507 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.82e+03 | +| ep_rew_mean | 0.278 | +| time/ | | +| fps | 309 | +| iterations | 5396 | +| time_elapsed | 17836 | +| total_timesteps | 5525504 | +| train/ | | +| approx_kl | 1.8097713 | +| clip_fraction | 0.47 | +| clip_range | 0.2 | +| entropy_loss | -0.405 | +| explained_variance | -0.214 | +| learning_rate | 0.0001 | +| loss | -0.0956 | +| n_updates | 114480 | +| policy_gradient_loss | -0.0506 | +| value_loss | 0.00053 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.81e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 309 | +| iterations | 5397 | +| time_elapsed | 17839 | +| total_timesteps | 5526528 | +| train/ | | +| approx_kl | 2.3371055 | +| clip_fraction | 0.464 | +| clip_range | 0.2 | +| entropy_loss | -0.342 | +| explained_variance | -0.604 | +| learning_rate | 0.0001 | +| loss | -0.0788 | +| n_updates | 114490 | +| policy_gradient_loss | -0.0624 | +| value_loss | 0.00112 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.81e+03 | +| ep_rew_mean | 0.285 | +| time/ | | +| fps | 309 | +| iterations | 5398 | +| time_elapsed | 17842 | +| total_timesteps | 5527552 | +| train/ | | +| approx_kl | 2.1165295 | +| clip_fraction | 0.461 | +| clip_range | 0.2 | +| entropy_loss | -0.375 | +| explained_variance | -1.22 | +| learning_rate | 0.0001 | +| loss | -0.0701 | +| n_updates | 114500 | +| policy_gradient_loss | -0.0609 | +| value_loss | 0.0012 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.8e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 309 | +| iterations | 5399 | +| time_elapsed | 17845 | +| total_timesteps | 5528576 | +| train/ | | +| approx_kl | 2.177887 | +| clip_fraction | 0.504 | +| clip_range | 0.2 | +| entropy_loss | -0.4 | +| explained_variance | -1.38 | +| learning_rate | 0.0001 | +| loss | -0.0767 | +| n_updates | 114510 | +| policy_gradient_loss | -0.0691 | +| value_loss | 0.000799 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 309 | +| iterations | 5400 | +| time_elapsed | 17849 | +| total_timesteps | 5529600 | +| train/ | | +| approx_kl | 2.016098 | +| clip_fraction | 0.451 | +| clip_range | 0.2 | +| entropy_loss | -0.32 | +| explained_variance | -1.02 | +| learning_rate | 0.0001 | +| loss | -0.0869 | +| n_updates | 114520 | +| policy_gradient_loss | -0.0682 | +| value_loss | 0.000968 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 309 | +| iterations | 5401 | +| time_elapsed | 17852 | +| total_timesteps | 5530624 | +| train/ | | +| approx_kl | 2.2764854 | +| clip_fraction | 0.484 | +| clip_range | 0.2 | +| entropy_loss | -0.375 | +| explained_variance | -1.18 | +| learning_rate | 0.0001 | +| loss | -0.0808 | +| n_updates | 114530 | +| policy_gradient_loss | -0.0752 | +| value_loss | 0.000573 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.28 | +| time/ | | +| fps | 309 | +| iterations | 5402 | +| time_elapsed | 17855 | +| total_timesteps | 5531648 | +| train/ | | +| approx_kl | 1.9970498 | +| clip_fraction | 0.489 | +| clip_range | 0.2 | +| entropy_loss | -0.409 | +| explained_variance | -1.34 | +| learning_rate | 0.0001 | +| loss | -0.094 | +| n_updates | 114540 | +| policy_gradient_loss | -0.0685 | +| value_loss | 0.000339 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.28 | +| time/ | | +| fps | 309 | +| iterations | 5403 | +| time_elapsed | 17858 | +| total_timesteps | 5532672 | +| train/ | | +| approx_kl | 1.6587502 | +| clip_fraction | 0.434 | +| clip_range | 0.2 | +| entropy_loss | -0.36 | +| explained_variance | -1.15 | +| learning_rate | 0.0001 | +| loss | -0.0569 | +| n_updates | 114550 | +| policy_gradient_loss | -0.0591 | +| value_loss | 0.000295 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.78e+03 | +| ep_rew_mean | 0.286 | +| time/ | | +| fps | 309 | +| iterations | 5404 | +| time_elapsed | 17862 | +| total_timesteps | 5533696 | +| train/ | | +| approx_kl | 24.26656 | +| clip_fraction | 0.516 | +| clip_range | 0.2 | +| entropy_loss | -0.418 | +| explained_variance | -1.08 | +| learning_rate | 0.0001 | +| loss | -0.105 | +| n_updates | 114560 | +| policy_gradient_loss | -0.0726 | +| value_loss | 0.000489 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.28 | +| time/ | | +| fps | 309 | +| iterations | 5405 | +| time_elapsed | 17865 | +| total_timesteps | 5534720 | +| train/ | | +| approx_kl | 2.0872612 | +| clip_fraction | 0.453 | +| clip_range | 0.2 | +| entropy_loss | -0.342 | +| explained_variance | -0.292 | +| learning_rate | 0.0001 | +| loss | -0.0956 | +| n_updates | 114570 | +| policy_gradient_loss | -0.0601 | +| value_loss | 0.000986 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.28 | +| time/ | | +| fps | 309 | +| iterations | 5406 | +| time_elapsed | 17869 | +| total_timesteps | 5535744 | +| train/ | | +| approx_kl | 1.8440005 | +| clip_fraction | 0.474 | +| clip_range | 0.2 | +| entropy_loss | -0.368 | +| explained_variance | -1.03 | +| learning_rate | 0.0001 | +| loss | -0.0709 | +| n_updates | 114580 | +| policy_gradient_loss | -0.0691 | +| value_loss | 0.000789 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.28 | +| time/ | | +| fps | 309 | +| iterations | 5407 | +| time_elapsed | 17872 | +| total_timesteps | 5536768 | +| train/ | | +| approx_kl | 2.4955652 | +| clip_fraction | 0.488 | +| clip_range | 0.2 | +| entropy_loss | -0.384 | +| explained_variance | -1.48 | +| learning_rate | 0.0001 | +| loss | -0.0687 | +| n_updates | 114590 | +| policy_gradient_loss | -0.0669 | +| value_loss | 0.00044 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.28 | +| time/ | | +| fps | 309 | +| iterations | 5408 | +| time_elapsed | 17876 | +| total_timesteps | 5537792 | +| train/ | | +| approx_kl | 2.2945666 | +| clip_fraction | 0.476 | +| clip_range | 0.2 | +| entropy_loss | -0.381 | +| explained_variance | -0.722 | +| learning_rate | 0.0001 | +| loss | -0.0692 | +| n_updates | 114600 | +| policy_gradient_loss | -0.0645 | +| value_loss | 0.000543 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.28 | +| time/ | | +| fps | 309 | +| iterations | 5409 | +| time_elapsed | 17879 | +| total_timesteps | 5538816 | +| train/ | | +| approx_kl | 2.0759332 | +| clip_fraction | 0.468 | +| clip_range | 0.2 | +| entropy_loss | -0.375 | +| explained_variance | -3.65 | +| learning_rate | 0.0001 | +| loss | -0.0867 | +| n_updates | 114610 | +| policy_gradient_loss | -0.062 | +| value_loss | 0.000885 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.277 | +| time/ | | +| fps | 309 | +| iterations | 5410 | +| time_elapsed | 17883 | +| total_timesteps | 5539840 | +| train/ | | +| approx_kl | 2.0465975 | +| clip_fraction | 0.495 | +| clip_range | 0.2 | +| entropy_loss | -0.384 | +| explained_variance | -1.46 | +| learning_rate | 0.0001 | +| loss | -0.0883 | +| n_updates | 114620 | +| policy_gradient_loss | -0.0727 | +| value_loss | 0.000664 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.277 | +| time/ | | +| fps | 309 | +| iterations | 5411 | +| time_elapsed | 17886 | +| total_timesteps | 5540864 | +| train/ | | +| approx_kl | 1.7171457 | +| clip_fraction | 0.485 | +| clip_range | 0.2 | +| entropy_loss | -0.408 | +| explained_variance | -1.37 | +| learning_rate | 0.0001 | +| loss | -0.0898 | +| n_updates | 114630 | +| policy_gradient_loss | -0.0665 | +| value_loss | 0.000593 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.277 | +| time/ | | +| fps | 309 | +| iterations | 5412 | +| time_elapsed | 17890 | +| total_timesteps | 5541888 | +| train/ | | +| approx_kl | 1.8138179 | +| clip_fraction | 0.509 | +| clip_range | 0.2 | +| entropy_loss | -0.462 | +| explained_variance | -4.3 | +| learning_rate | 0.0001 | +| loss | -0.0604 | +| n_updates | 114640 | +| policy_gradient_loss | -0.064 | +| value_loss | 0.000224 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.281 | +| time/ | | +| fps | 309 | +| iterations | 5413 | +| time_elapsed | 17893 | +| total_timesteps | 5542912 | +| train/ | | +| approx_kl | 3.7368531 | +| clip_fraction | 0.512 | +| clip_range | 0.2 | +| entropy_loss | -0.401 | +| explained_variance | -0.528 | +| learning_rate | 0.0001 | +| loss | -0.097 | +| n_updates | 114650 | +| policy_gradient_loss | -0.0671 | +| value_loss | 0.000449 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.281 | +| time/ | | +| fps | 309 | +| iterations | 5414 | +| time_elapsed | 17896 | +| total_timesteps | 5543936 | +| train/ | | +| approx_kl | 2.2203317 | +| clip_fraction | 0.499 | +| clip_range | 0.2 | +| entropy_loss | -0.416 | +| explained_variance | -1.15 | +| learning_rate | 0.0001 | +| loss | -0.0754 | +| n_updates | 114660 | +| policy_gradient_loss | -0.0674 | +| value_loss | 0.000674 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.278 | +| time/ | | +| fps | 309 | +| iterations | 5415 | +| time_elapsed | 17899 | +| total_timesteps | 5544960 | +| train/ | | +| approx_kl | 2.6396422 | +| clip_fraction | 0.464 | +| clip_range | 0.2 | +| entropy_loss | -0.359 | +| explained_variance | -3.74 | +| learning_rate | 0.0001 | +| loss | -0.0957 | +| n_updates | 114670 | +| policy_gradient_loss | -0.0729 | +| value_loss | 0.000554 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.278 | +| time/ | | +| fps | 309 | +| iterations | 5416 | +| time_elapsed | 17903 | +| total_timesteps | 5545984 | +| train/ | | +| approx_kl | 1.9286215 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.396 | +| explained_variance | -1.23 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 114680 | +| policy_gradient_loss | -0.0692 | +| value_loss | 0.000664 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.28 | +| time/ | | +| fps | 309 | +| iterations | 5417 | +| time_elapsed | 17906 | +| total_timesteps | 5547008 | +| train/ | | +| approx_kl | 12.053479 | +| clip_fraction | 0.507 | +| clip_range | 0.2 | +| entropy_loss | -0.402 | +| explained_variance | -4.34 | +| learning_rate | 0.0001 | +| loss | -0.0986 | +| n_updates | 114690 | +| policy_gradient_loss | -0.0758 | +| value_loss | 0.000296 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.28 | +| time/ | | +| fps | 309 | +| iterations | 5418 | +| time_elapsed | 17909 | +| total_timesteps | 5548032 | +| train/ | | +| approx_kl | 1.9925458 | +| clip_fraction | 0.452 | +| clip_range | 0.2 | +| entropy_loss | -0.34 | +| explained_variance | -0.609 | +| learning_rate | 0.0001 | +| loss | -0.0819 | +| n_updates | 114700 | +| policy_gradient_loss | -0.0587 | +| value_loss | 0.000487 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.278 | +| time/ | | +| fps | 309 | +| iterations | 5419 | +| time_elapsed | 17912 | +| total_timesteps | 5549056 | +| train/ | | +| approx_kl | 2.6768212 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.365 | +| explained_variance | -5.02 | +| learning_rate | 0.0001 | +| loss | -0.114 | +| n_updates | 114710 | +| policy_gradient_loss | -0.0735 | +| value_loss | 0.00036 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.278 | +| time/ | | +| fps | 309 | +| iterations | 5420 | +| time_elapsed | 17915 | +| total_timesteps | 5550080 | +| train/ | | +| approx_kl | 1.9482985 | +| clip_fraction | 0.516 | +| clip_range | 0.2 | +| entropy_loss | -0.448 | +| explained_variance | -1.6 | +| learning_rate | 0.0001 | +| loss | -0.0943 | +| n_updates | 114720 | +| policy_gradient_loss | -0.0682 | +| value_loss | 0.000317 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 309 | +| iterations | 5421 | +| time_elapsed | 17918 | +| total_timesteps | 5551104 | +| train/ | | +| approx_kl | 2.1377494 | +| clip_fraction | 0.506 | +| clip_range | 0.2 | +| entropy_loss | -0.435 | +| explained_variance | -0.864 | +| learning_rate | 0.0001 | +| loss | -0.0837 | +| n_updates | 114730 | +| policy_gradient_loss | -0.0672 | +| value_loss | 0.000461 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 309 | +| iterations | 5422 | +| time_elapsed | 17922 | +| total_timesteps | 5552128 | +| train/ | | +| approx_kl | 2.23074 | +| clip_fraction | 0.455 | +| clip_range | 0.2 | +| entropy_loss | -0.382 | +| explained_variance | -1.53 | +| learning_rate | 0.0001 | +| loss | -0.0889 | +| n_updates | 114740 | +| policy_gradient_loss | -0.06 | +| value_loss | 0.000511 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 309 | +| iterations | 5423 | +| time_elapsed | 17925 | +| total_timesteps | 5553152 | +| train/ | | +| approx_kl | 2.6714482 | +| clip_fraction | 0.494 | +| clip_range | 0.2 | +| entropy_loss | -0.425 | +| explained_variance | -0.895 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 114750 | +| policy_gradient_loss | -0.0667 | +| value_loss | 0.000739 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.281 | +| time/ | | +| fps | 309 | +| iterations | 5424 | +| time_elapsed | 17929 | +| total_timesteps | 5554176 | +| train/ | | +| approx_kl | 2.1883073 | +| clip_fraction | 0.469 | +| clip_range | 0.2 | +| entropy_loss | -0.377 | +| explained_variance | -2.3 | +| learning_rate | 0.0001 | +| loss | -0.0918 | +| n_updates | 114760 | +| policy_gradient_loss | -0.0725 | +| value_loss | 0.000612 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.281 | +| time/ | | +| fps | 309 | +| iterations | 5425 | +| time_elapsed | 17932 | +| total_timesteps | 5555200 | +| train/ | | +| approx_kl | 2.144999 | +| clip_fraction | 0.463 | +| clip_range | 0.2 | +| entropy_loss | -0.37 | +| explained_variance | -1 | +| learning_rate | 0.0001 | +| loss | -0.0739 | +| n_updates | 114770 | +| policy_gradient_loss | -0.0655 | +| value_loss | 0.00032 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.281 | +| time/ | | +| fps | 309 | +| iterations | 5426 | +| time_elapsed | 17936 | +| total_timesteps | 5556224 | +| train/ | | +| approx_kl | 2.0650887 | +| clip_fraction | 0.503 | +| clip_range | 0.2 | +| entropy_loss | -0.439 | +| explained_variance | -0.817 | +| learning_rate | 0.0001 | +| loss | -0.0818 | +| n_updates | 114780 | +| policy_gradient_loss | -0.0597 | +| value_loss | 0.000372 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.284 | +| time/ | | +| fps | 309 | +| iterations | 5427 | +| time_elapsed | 17939 | +| total_timesteps | 5557248 | +| train/ | | +| approx_kl | 1.6980852 | +| clip_fraction | 0.513 | +| clip_range | 0.2 | +| entropy_loss | -0.467 | +| explained_variance | -3.32 | +| learning_rate | 0.0001 | +| loss | -0.0986 | +| n_updates | 114790 | +| policy_gradient_loss | -0.0793 | +| value_loss | 0.000436 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.284 | +| time/ | | +| fps | 309 | +| iterations | 5428 | +| time_elapsed | 17943 | +| total_timesteps | 5558272 | +| train/ | | +| approx_kl | 1.8547311 | +| clip_fraction | 0.482 | +| clip_range | 0.2 | +| entropy_loss | -0.434 | +| explained_variance | -1.67 | +| learning_rate | 0.0001 | +| loss | -0.0899 | +| n_updates | 114800 | +| policy_gradient_loss | -0.0702 | +| value_loss | 0.000553 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.284 | +| time/ | | +| fps | 309 | +| iterations | 5429 | +| time_elapsed | 17946 | +| total_timesteps | 5559296 | +| train/ | | +| approx_kl | 1.7013865 | +| clip_fraction | 0.492 | +| clip_range | 0.2 | +| entropy_loss | -0.423 | +| explained_variance | -3.57 | +| learning_rate | 0.0001 | +| loss | -0.0907 | +| n_updates | 114810 | +| policy_gradient_loss | -0.0694 | +| value_loss | 0.000431 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.284 | +| time/ | | +| fps | 309 | +| iterations | 5430 | +| time_elapsed | 17949 | +| total_timesteps | 5560320 | +| train/ | | +| approx_kl | 2.6662498 | +| clip_fraction | 0.504 | +| clip_range | 0.2 | +| entropy_loss | -0.447 | +| explained_variance | -3.26 | +| learning_rate | 0.0001 | +| loss | -0.0787 | +| n_updates | 114820 | +| policy_gradient_loss | -0.0711 | +| value_loss | 0.000303 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 309 | +| iterations | 5431 | +| time_elapsed | 17952 | +| total_timesteps | 5561344 | +| train/ | | +| approx_kl | 1.8907498 | +| clip_fraction | 0.468 | +| clip_range | 0.2 | +| entropy_loss | -0.383 | +| explained_variance | -3.34 | +| learning_rate | 0.0001 | +| loss | -0.0997 | +| n_updates | 114830 | +| policy_gradient_loss | -0.0627 | +| value_loss | 0.000213 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.274 | +| time/ | | +| fps | 309 | +| iterations | 5432 | +| time_elapsed | 17956 | +| total_timesteps | 5562368 | +| train/ | | +| approx_kl | 1.9325999 | +| clip_fraction | 0.489 | +| clip_range | 0.2 | +| entropy_loss | -0.429 | +| explained_variance | -0.911 | +| learning_rate | 0.0001 | +| loss | -0.0895 | +| n_updates | 114840 | +| policy_gradient_loss | -0.0663 | +| value_loss | 0.00051 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.274 | +| time/ | | +| fps | 309 | +| iterations | 5433 | +| time_elapsed | 17959 | +| total_timesteps | 5563392 | +| train/ | | +| approx_kl | 1.9559027 | +| clip_fraction | 0.45 | +| clip_range | 0.2 | +| entropy_loss | -0.386 | +| explained_variance | -1.13 | +| learning_rate | 0.0001 | +| loss | -0.0633 | +| n_updates | 114850 | +| policy_gradient_loss | -0.0617 | +| value_loss | 0.000517 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.273 | +| time/ | | +| fps | 309 | +| iterations | 5434 | +| time_elapsed | 17962 | +| total_timesteps | 5564416 | +| train/ | | +| approx_kl | 2.280017 | +| clip_fraction | 0.511 | +| clip_range | 0.2 | +| entropy_loss | -0.404 | +| explained_variance | -2.1 | +| learning_rate | 0.0001 | +| loss | -0.111 | +| n_updates | 114860 | +| policy_gradient_loss | -0.0743 | +| value_loss | 0.000581 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.273 | +| time/ | | +| fps | 309 | +| iterations | 5435 | +| time_elapsed | 17965 | +| total_timesteps | 5565440 | +| train/ | | +| approx_kl | 1.8104806 | +| clip_fraction | 0.479 | +| clip_range | 0.2 | +| entropy_loss | -0.432 | +| explained_variance | -2.22 | +| learning_rate | 0.0001 | +| loss | -0.0779 | +| n_updates | 114870 | +| policy_gradient_loss | -0.0625 | +| value_loss | 0.000244 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.273 | +| time/ | | +| fps | 309 | +| iterations | 5436 | +| time_elapsed | 17968 | +| total_timesteps | 5566464 | +| train/ | | +| approx_kl | 2.4626112 | +| clip_fraction | 0.525 | +| clip_range | 0.2 | +| entropy_loss | -0.467 | +| explained_variance | -0.757 | +| learning_rate | 0.0001 | +| loss | -0.0647 | +| n_updates | 114880 | +| policy_gradient_loss | -0.0653 | +| value_loss | 0.000496 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.273 | +| time/ | | +| fps | 309 | +| iterations | 5437 | +| time_elapsed | 17971 | +| total_timesteps | 5567488 | +| train/ | | +| approx_kl | 1.8406372 | +| clip_fraction | 0.495 | +| clip_range | 0.2 | +| entropy_loss | -0.458 | +| explained_variance | -6.55 | +| learning_rate | 0.0001 | +| loss | -0.098 | +| n_updates | 114890 | +| policy_gradient_loss | -0.0703 | +| value_loss | 0.000387 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.274 | +| time/ | | +| fps | 309 | +| iterations | 5438 | +| time_elapsed | 17975 | +| total_timesteps | 5568512 | +| train/ | | +| approx_kl | 2.3985193 | +| clip_fraction | 0.492 | +| clip_range | 0.2 | +| entropy_loss | -0.384 | +| explained_variance | -5.94 | +| learning_rate | 0.0001 | +| loss | -0.106 | +| n_updates | 114900 | +| policy_gradient_loss | -0.0737 | +| value_loss | 0.00056 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.273 | +| time/ | | +| fps | 309 | +| iterations | 5439 | +| time_elapsed | 17978 | +| total_timesteps | 5569536 | +| train/ | | +| approx_kl | 1.7720847 | +| clip_fraction | 0.482 | +| clip_range | 0.2 | +| entropy_loss | -0.398 | +| explained_variance | -2.92 | +| learning_rate | 0.0001 | +| loss | -0.0326 | +| n_updates | 114910 | +| policy_gradient_loss | -0.0647 | +| value_loss | 0.000548 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.273 | +| time/ | | +| fps | 309 | +| iterations | 5440 | +| time_elapsed | 17982 | +| total_timesteps | 5570560 | +| train/ | | +| approx_kl | 1.7829425 | +| clip_fraction | 0.502 | +| clip_range | 0.2 | +| entropy_loss | -0.409 | +| explained_variance | -1.31 | +| learning_rate | 0.0001 | +| loss | -0.081 | +| n_updates | 114920 | +| policy_gradient_loss | -0.0663 | +| value_loss | 0.000948 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.273 | +| time/ | | +| fps | 309 | +| iterations | 5441 | +| time_elapsed | 17985 | +| total_timesteps | 5571584 | +| train/ | | +| approx_kl | 4.524419 | +| clip_fraction | 0.495 | +| clip_range | 0.2 | +| entropy_loss | -0.367 | +| explained_variance | -0.744 | +| learning_rate | 0.0001 | +| loss | -0.0843 | +| n_updates | 114930 | +| policy_gradient_loss | -0.0686 | +| value_loss | 0.000807 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.274 | +| time/ | | +| fps | 309 | +| iterations | 5442 | +| time_elapsed | 17989 | +| total_timesteps | 5572608 | +| train/ | | +| approx_kl | 1.7850237 | +| clip_fraction | 0.499 | +| clip_range | 0.2 | +| entropy_loss | -0.473 | +| explained_variance | -1.33 | +| learning_rate | 0.0001 | +| loss | -0.092 | +| n_updates | 114940 | +| policy_gradient_loss | -0.0693 | +| value_loss | 0.000697 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.271 | +| time/ | | +| fps | 309 | +| iterations | 5443 | +| time_elapsed | 17992 | +| total_timesteps | 5573632 | +| train/ | | +| approx_kl | 2.0217137 | +| clip_fraction | 0.492 | +| clip_range | 0.2 | +| entropy_loss | -0.407 | +| explained_variance | -1.17 | +| learning_rate | 0.0001 | +| loss | -0.0872 | +| n_updates | 114950 | +| policy_gradient_loss | -0.0595 | +| value_loss | 0.000537 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.271 | +| time/ | | +| fps | 309 | +| iterations | 5444 | +| time_elapsed | 17996 | +| total_timesteps | 5574656 | +| train/ | | +| approx_kl | 3.047214 | +| clip_fraction | 0.457 | +| clip_range | 0.2 | +| entropy_loss | -0.373 | +| explained_variance | -1.04 | +| learning_rate | 0.0001 | +| loss | -0.0822 | +| n_updates | 114960 | +| policy_gradient_loss | -0.0676 | +| value_loss | 0.000497 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 309 | +| iterations | 5445 | +| time_elapsed | 17999 | +| total_timesteps | 5575680 | +| train/ | | +| approx_kl | 3.9015207 | +| clip_fraction | 0.509 | +| clip_range | 0.2 | +| entropy_loss | -0.425 | +| explained_variance | -2.74 | +| learning_rate | 0.0001 | +| loss | -0.0829 | +| n_updates | 114970 | +| policy_gradient_loss | -0.071 | +| value_loss | 0.000427 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.269 | +| time/ | | +| fps | 309 | +| iterations | 5446 | +| time_elapsed | 18003 | +| total_timesteps | 5576704 | +| train/ | | +| approx_kl | 1.8083929 | +| clip_fraction | 0.455 | +| clip_range | 0.2 | +| entropy_loss | -0.388 | +| explained_variance | -0.84 | +| learning_rate | 0.0001 | +| loss | -0.052 | +| n_updates | 114980 | +| policy_gradient_loss | -0.0602 | +| value_loss | 0.000654 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.274 | +| time/ | | +| fps | 309 | +| iterations | 5447 | +| time_elapsed | 18006 | +| total_timesteps | 5577728 | +| train/ | | +| approx_kl | 2.5436924 | +| clip_fraction | 0.46 | +| clip_range | 0.2 | +| entropy_loss | -0.383 | +| explained_variance | -1.09 | +| learning_rate | 0.0001 | +| loss | -0.0977 | +| n_updates | 114990 | +| policy_gradient_loss | -0.0738 | +| value_loss | 0.000528 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.274 | +| time/ | | +| fps | 309 | +| iterations | 5448 | +| time_elapsed | 18010 | +| total_timesteps | 5578752 | +| train/ | | +| approx_kl | 2.492004 | +| clip_fraction | 0.503 | +| clip_range | 0.2 | +| entropy_loss | -0.463 | +| explained_variance | -0.0898 | +| learning_rate | 0.0001 | +| loss | -0.105 | +| n_updates | 115000 | +| policy_gradient_loss | -0.071 | +| value_loss | 0.000682 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.274 | +| time/ | | +| fps | 309 | +| iterations | 5449 | +| time_elapsed | 18013 | +| total_timesteps | 5579776 | +| train/ | | +| approx_kl | 2.9515665 | +| clip_fraction | 0.486 | +| clip_range | 0.2 | +| entropy_loss | -0.397 | +| explained_variance | -5.79 | +| learning_rate | 0.0001 | +| loss | -0.0895 | +| n_updates | 115010 | +| policy_gradient_loss | -0.0724 | +| value_loss | 0.00045 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.274 | +| time/ | | +| fps | 309 | +| iterations | 5450 | +| time_elapsed | 18016 | +| total_timesteps | 5580800 | +| train/ | | +| approx_kl | 1.7209442 | +| clip_fraction | 0.494 | +| clip_range | 0.2 | +| entropy_loss | -0.477 | +| explained_variance | -1.17 | +| learning_rate | 0.0001 | +| loss | -0.0945 | +| n_updates | 115020 | +| policy_gradient_loss | -0.056 | +| value_loss | 0.000225 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.274 | +| time/ | | +| fps | 309 | +| iterations | 5451 | +| time_elapsed | 18019 | +| total_timesteps | 5581824 | +| train/ | | +| approx_kl | 1.9443756 | +| clip_fraction | 0.491 | +| clip_range | 0.2 | +| entropy_loss | -0.395 | +| explained_variance | -7.79 | +| learning_rate | 0.0001 | +| loss | -0.0883 | +| n_updates | 115030 | +| policy_gradient_loss | -0.0708 | +| value_loss | 0.000389 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.27 | +| time/ | | +| fps | 309 | +| iterations | 5452 | +| time_elapsed | 18022 | +| total_timesteps | 5582848 | +| train/ | | +| approx_kl | 2.3224032 | +| clip_fraction | 0.524 | +| clip_range | 0.2 | +| entropy_loss | -0.47 | +| explained_variance | -3.88 | +| learning_rate | 0.0001 | +| loss | -0.0963 | +| n_updates | 115040 | +| policy_gradient_loss | -0.0748 | +| value_loss | 0.000372 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.27 | +| time/ | | +| fps | 309 | +| iterations | 5453 | +| time_elapsed | 18026 | +| total_timesteps | 5583872 | +| train/ | | +| approx_kl | 3.1761265 | +| clip_fraction | 0.493 | +| clip_range | 0.2 | +| entropy_loss | -0.437 | +| explained_variance | -3.36 | +| learning_rate | 0.0001 | +| loss | -0.0946 | +| n_updates | 115050 | +| policy_gradient_loss | -0.0657 | +| value_loss | 0.000178 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.269 | +| time/ | | +| fps | 309 | +| iterations | 5454 | +| time_elapsed | 18029 | +| total_timesteps | 5584896 | +| train/ | | +| approx_kl | 2.4555902 | +| clip_fraction | 0.533 | +| clip_range | 0.2 | +| entropy_loss | -0.428 | +| explained_variance | -0.998 | +| learning_rate | 0.0001 | +| loss | -0.0466 | +| n_updates | 115060 | +| policy_gradient_loss | -0.0688 | +| value_loss | 0.000294 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.269 | +| time/ | | +| fps | 309 | +| iterations | 5455 | +| time_elapsed | 18032 | +| total_timesteps | 5585920 | +| train/ | | +| approx_kl | 1.7768803 | +| clip_fraction | 0.518 | +| clip_range | 0.2 | +| entropy_loss | -0.496 | +| explained_variance | -1.27 | +| learning_rate | 0.0001 | +| loss | -0.0823 | +| n_updates | 115070 | +| policy_gradient_loss | -0.0694 | +| value_loss | 0.0004 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.268 | +| time/ | | +| fps | 309 | +| iterations | 5456 | +| time_elapsed | 18035 | +| total_timesteps | 5586944 | +| train/ | | +| approx_kl | 2.4578772 | +| clip_fraction | 0.54 | +| clip_range | 0.2 | +| entropy_loss | -0.469 | +| explained_variance | -1.58 | +| learning_rate | 0.0001 | +| loss | -0.0968 | +| n_updates | 115080 | +| policy_gradient_loss | -0.0743 | +| value_loss | 0.000433 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.268 | +| time/ | | +| fps | 309 | +| iterations | 5457 | +| time_elapsed | 18038 | +| total_timesteps | 5587968 | +| train/ | | +| approx_kl | 1.5223498 | +| clip_fraction | 0.493 | +| clip_range | 0.2 | +| entropy_loss | -0.498 | +| explained_variance | -7.73 | +| learning_rate | 0.0001 | +| loss | -0.077 | +| n_updates | 115090 | +| policy_gradient_loss | -0.0677 | +| value_loss | 0.00028 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.266 | +| time/ | | +| fps | 309 | +| iterations | 5458 | +| time_elapsed | 18042 | +| total_timesteps | 5588992 | +| train/ | | +| approx_kl | 2.7824574 | +| clip_fraction | 0.513 | +| clip_range | 0.2 | +| entropy_loss | -0.453 | +| explained_variance | -2.02 | +| learning_rate | 0.0001 | +| loss | -0.082 | +| n_updates | 115100 | +| policy_gradient_loss | -0.068 | +| value_loss | 0.000252 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.266 | +| time/ | | +| fps | 309 | +| iterations | 5459 | +| time_elapsed | 18045 | +| total_timesteps | 5590016 | +| train/ | | +| approx_kl | 1.9660155 | +| clip_fraction | 0.522 | +| clip_range | 0.2 | +| entropy_loss | -0.46 | +| explained_variance | -2.99 | +| learning_rate | 0.0001 | +| loss | -0.107 | +| n_updates | 115110 | +| policy_gradient_loss | -0.082 | +| value_loss | 0.000202 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.264 | +| time/ | | +| fps | 309 | +| iterations | 5460 | +| time_elapsed | 18049 | +| total_timesteps | 5591040 | +| train/ | | +| approx_kl | 1.8252854 | +| clip_fraction | 0.538 | +| clip_range | 0.2 | +| entropy_loss | -0.564 | +| explained_variance | -0.32 | +| learning_rate | 0.0001 | +| loss | -0.066 | +| n_updates | 115120 | +| policy_gradient_loss | -0.0595 | +| value_loss | 0.000279 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.267 | +| time/ | | +| fps | 309 | +| iterations | 5461 | +| time_elapsed | 18052 | +| total_timesteps | 5592064 | +| train/ | | +| approx_kl | 2.0500147 | +| clip_fraction | 0.512 | +| clip_range | 0.2 | +| entropy_loss | -0.436 | +| explained_variance | -1.63 | +| learning_rate | 0.0001 | +| loss | -0.0895 | +| n_updates | 115130 | +| policy_gradient_loss | -0.0741 | +| value_loss | 0.000573 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.267 | +| time/ | | +| fps | 309 | +| iterations | 5462 | +| time_elapsed | 18056 | +| total_timesteps | 5593088 | +| train/ | | +| approx_kl | 1.940854 | +| clip_fraction | 0.485 | +| clip_range | 0.2 | +| entropy_loss | -0.433 | +| explained_variance | -0.963 | +| learning_rate | 0.0001 | +| loss | -0.0697 | +| n_updates | 115140 | +| policy_gradient_loss | -0.0643 | +| value_loss | 0.000674 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.27 | +| time/ | | +| fps | 309 | +| iterations | 5463 | +| time_elapsed | 18059 | +| total_timesteps | 5594112 | +| train/ | | +| approx_kl | 3.417241 | +| clip_fraction | 0.503 | +| clip_range | 0.2 | +| entropy_loss | -0.458 | +| explained_variance | -0.999 | +| learning_rate | 0.0001 | +| loss | -0.078 | +| n_updates | 115150 | +| policy_gradient_loss | -0.068 | +| value_loss | 0.000843 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.27 | +| time/ | | +| fps | 309 | +| iterations | 5464 | +| time_elapsed | 18062 | +| total_timesteps | 5595136 | +| train/ | | +| approx_kl | 3.31879 | +| clip_fraction | 0.479 | +| clip_range | 0.2 | +| entropy_loss | -0.384 | +| explained_variance | -2.48 | +| learning_rate | 0.0001 | +| loss | -0.109 | +| n_updates | 115160 | +| policy_gradient_loss | -0.071 | +| value_loss | 0.000708 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.272 | +| time/ | | +| fps | 309 | +| iterations | 5465 | +| time_elapsed | 18066 | +| total_timesteps | 5596160 | +| train/ | | +| approx_kl | 6.1810193 | +| clip_fraction | 0.494 | +| clip_range | 0.2 | +| entropy_loss | -0.454 | +| explained_variance | -4.43 | +| learning_rate | 0.0001 | +| loss | -0.0963 | +| n_updates | 115170 | +| policy_gradient_loss | -0.0752 | +| value_loss | 0.000542 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.267 | +| time/ | | +| fps | 309 | +| iterations | 5466 | +| time_elapsed | 18069 | +| total_timesteps | 5597184 | +| train/ | | +| approx_kl | 3.4313326 | +| clip_fraction | 0.458 | +| clip_range | 0.2 | +| entropy_loss | -0.331 | +| explained_variance | -1.86 | +| learning_rate | 0.0001 | +| loss | -0.0992 | +| n_updates | 115180 | +| policy_gradient_loss | -0.0676 | +| value_loss | 0.000641 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.267 | +| time/ | | +| fps | 309 | +| iterations | 5467 | +| time_elapsed | 18072 | +| total_timesteps | 5598208 | +| train/ | | +| approx_kl | 2.1171217 | +| clip_fraction | 0.501 | +| clip_range | 0.2 | +| entropy_loss | -0.418 | +| explained_variance | -1.15 | +| learning_rate | 0.0001 | +| loss | -0.107 | +| n_updates | 115190 | +| policy_gradient_loss | -0.0704 | +| value_loss | 0.000874 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.266 | +| time/ | | +| fps | 309 | +| iterations | 5468 | +| time_elapsed | 18076 | +| total_timesteps | 5599232 | +| train/ | | +| approx_kl | 2.2512918 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.41 | +| explained_variance | -4.74 | +| learning_rate | 0.0001 | +| loss | -0.0988 | +| n_updates | 115200 | +| policy_gradient_loss | -0.0765 | +| value_loss | 0.000479 | +--------------------------------------- + +Current state: Champion.Level3.RyuVsChunLi +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.26 | +| time/ | | +| fps | 309 | +| iterations | 5469 | +| time_elapsed | 18079 | +| total_timesteps | 5600256 | +| train/ | | +| approx_kl | 2.3442447 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.378 | +| explained_variance | -0.892 | +| learning_rate | 0.0001 | +| loss | -0.0842 | +| n_updates | 115210 | +| policy_gradient_loss | -0.068 | +| value_loss | 0.000466 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.26 | +| time/ | | +| fps | 309 | +| iterations | 5470 | +| time_elapsed | 18082 | +| total_timesteps | 5601280 | +| train/ | | +| approx_kl | 2.2287383 | +| clip_fraction | 0.513 | +| clip_range | 0.2 | +| entropy_loss | -0.431 | +| explained_variance | -0.799 | +| learning_rate | 0.0001 | +| loss | -0.0795 | +| n_updates | 115220 | +| policy_gradient_loss | -0.0705 | +| value_loss | 0.000656 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.255 | +| time/ | | +| fps | 309 | +| iterations | 5471 | +| time_elapsed | 18085 | +| total_timesteps | 5602304 | +| train/ | | +| approx_kl | 2.5823667 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.407 | +| explained_variance | -3.72 | +| learning_rate | 0.0001 | +| loss | -0.0802 | +| n_updates | 115230 | +| policy_gradient_loss | -0.0695 | +| value_loss | 0.000376 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.26 | +| time/ | | +| fps | 309 | +| iterations | 5472 | +| time_elapsed | 18088 | +| total_timesteps | 5603328 | +| train/ | | +| approx_kl | 3.1376345 | +| clip_fraction | 0.5 | +| clip_range | 0.2 | +| entropy_loss | -0.443 | +| explained_variance | -0.702 | +| learning_rate | 0.0001 | +| loss | -0.109 | +| n_updates | 115240 | +| policy_gradient_loss | -0.0657 | +| value_loss | 0.000556 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.264 | +| time/ | | +| fps | 309 | +| iterations | 5473 | +| time_elapsed | 18092 | +| total_timesteps | 5604352 | +| train/ | | +| approx_kl | 2.9595237 | +| clip_fraction | 0.51 | +| clip_range | 0.2 | +| entropy_loss | -0.392 | +| explained_variance | -0.598 | +| learning_rate | 0.0001 | +| loss | -0.1 | +| n_updates | 115250 | +| policy_gradient_loss | -0.0696 | +| value_loss | 0.00103 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.264 | +| time/ | | +| fps | 309 | +| iterations | 5474 | +| time_elapsed | 18095 | +| total_timesteps | 5605376 | +| train/ | | +| approx_kl | 2.870144 | +| clip_fraction | 0.484 | +| clip_range | 0.2 | +| entropy_loss | -0.346 | +| explained_variance | -1.75 | +| learning_rate | 0.0001 | +| loss | -0.0709 | +| n_updates | 115260 | +| policy_gradient_loss | -0.0696 | +| value_loss | 0.000986 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.267 | +| time/ | | +| fps | 309 | +| iterations | 5475 | +| time_elapsed | 18098 | +| total_timesteps | 5606400 | +| train/ | | +| approx_kl | 2.4204962 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.354 | +| explained_variance | -2.34 | +| learning_rate | 0.0001 | +| loss | -0.0839 | +| n_updates | 115270 | +| policy_gradient_loss | -0.0745 | +| value_loss | 0.000517 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.267 | +| time/ | | +| fps | 309 | +| iterations | 5476 | +| time_elapsed | 18101 | +| total_timesteps | 5607424 | +| train/ | | +| approx_kl | 2.267201 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.333 | +| explained_variance | -1.39 | +| learning_rate | 0.0001 | +| loss | -0.0953 | +| n_updates | 115280 | +| policy_gradient_loss | -0.067 | +| value_loss | 0.000542 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.27 | +| time/ | | +| fps | 309 | +| iterations | 5477 | +| time_elapsed | 18105 | +| total_timesteps | 5608448 | +| train/ | | +| approx_kl | 2.3877573 | +| clip_fraction | 0.477 | +| clip_range | 0.2 | +| entropy_loss | -0.338 | +| explained_variance | -3.29 | +| learning_rate | 0.0001 | +| loss | -0.0891 | +| n_updates | 115290 | +| policy_gradient_loss | -0.0679 | +| value_loss | 0.000448 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.27 | +| time/ | | +| fps | 309 | +| iterations | 5478 | +| time_elapsed | 18108 | +| total_timesteps | 5609472 | +| train/ | | +| approx_kl | 5.0218263 | +| clip_fraction | 0.459 | +| clip_range | 0.2 | +| entropy_loss | -0.301 | +| explained_variance | -1.24 | +| learning_rate | 0.0001 | +| loss | -0.0922 | +| n_updates | 115300 | +| policy_gradient_loss | -0.064 | +| value_loss | 0.000385 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.27 | +| time/ | | +| fps | 309 | +| iterations | 5479 | +| time_elapsed | 18112 | +| total_timesteps | 5610496 | +| train/ | | +| approx_kl | 2.3447797 | +| clip_fraction | 0.491 | +| clip_range | 0.2 | +| entropy_loss | -0.355 | +| explained_variance | -1.07 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 115310 | +| policy_gradient_loss | -0.0696 | +| value_loss | 0.000601 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.272 | +| time/ | | +| fps | 309 | +| iterations | 5480 | +| time_elapsed | 18115 | +| total_timesteps | 5611520 | +| train/ | | +| approx_kl | 2.4873807 | +| clip_fraction | 0.467 | +| clip_range | 0.2 | +| entropy_loss | -0.307 | +| explained_variance | -2.41 | +| learning_rate | 0.0001 | +| loss | -0.107 | +| n_updates | 115320 | +| policy_gradient_loss | -0.0734 | +| value_loss | 0.000732 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 309 | +| iterations | 5481 | +| time_elapsed | 18119 | +| total_timesteps | 5612544 | +| train/ | | +| approx_kl | 2.5349085 | +| clip_fraction | 0.459 | +| clip_range | 0.2 | +| entropy_loss | -0.312 | +| explained_variance | -2.31 | +| learning_rate | 0.0001 | +| loss | -0.0923 | +| n_updates | 115330 | +| policy_gradient_loss | -0.0701 | +| value_loss | 0.000442 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 309 | +| iterations | 5482 | +| time_elapsed | 18122 | +| total_timesteps | 5613568 | +| train/ | | +| approx_kl | 2.8996189 | +| clip_fraction | 0.466 | +| clip_range | 0.2 | +| entropy_loss | -0.311 | +| explained_variance | -2.04 | +| learning_rate | 0.0001 | +| loss | -0.0935 | +| n_updates | 115340 | +| policy_gradient_loss | -0.0712 | +| value_loss | 0.000625 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.273 | +| time/ | | +| fps | 309 | +| iterations | 5483 | +| time_elapsed | 18126 | +| total_timesteps | 5614592 | +| train/ | | +| approx_kl | 3.1930046 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.349 | +| explained_variance | -1.4 | +| learning_rate | 0.0001 | +| loss | -0.065 | +| n_updates | 115350 | +| policy_gradient_loss | -0.0651 | +| value_loss | 0.00081 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.273 | +| time/ | | +| fps | 309 | +| iterations | 5484 | +| time_elapsed | 18129 | +| total_timesteps | 5615616 | +| train/ | | +| approx_kl | 2.6059046 | +| clip_fraction | 0.492 | +| clip_range | 0.2 | +| entropy_loss | -0.362 | +| explained_variance | -1.27 | +| learning_rate | 0.0001 | +| loss | -0.0799 | +| n_updates | 115360 | +| policy_gradient_loss | -0.0725 | +| value_loss | 0.000841 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 309 | +| iterations | 5485 | +| time_elapsed | 18133 | +| total_timesteps | 5616640 | +| train/ | | +| approx_kl | 2.3335304 | +| clip_fraction | 0.497 | +| clip_range | 0.2 | +| entropy_loss | -0.391 | +| explained_variance | -2.36 | +| learning_rate | 0.0001 | +| loss | -0.0882 | +| n_updates | 115370 | +| policy_gradient_loss | -0.0742 | +| value_loss | 0.000595 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 309 | +| iterations | 5486 | +| time_elapsed | 18136 | +| total_timesteps | 5617664 | +| train/ | | +| approx_kl | 2.4541893 | +| clip_fraction | 0.496 | +| clip_range | 0.2 | +| entropy_loss | -0.391 | +| explained_variance | -2.3 | +| learning_rate | 0.0001 | +| loss | -0.0913 | +| n_updates | 115380 | +| policy_gradient_loss | -0.072 | +| value_loss | 0.000694 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 309 | +| iterations | 5487 | +| time_elapsed | 18139 | +| total_timesteps | 5618688 | +| train/ | | +| approx_kl | 2.4630837 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.36 | +| explained_variance | -2.17 | +| learning_rate | 0.0001 | +| loss | -0.0917 | +| n_updates | 115390 | +| policy_gradient_loss | -0.0721 | +| value_loss | 0.000468 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 309 | +| iterations | 5488 | +| time_elapsed | 18142 | +| total_timesteps | 5619712 | +| train/ | | +| approx_kl | 2.7439153 | +| clip_fraction | 0.516 | +| clip_range | 0.2 | +| entropy_loss | -0.428 | +| explained_variance | -0.448 | +| learning_rate | 0.0001 | +| loss | -0.116 | +| n_updates | 115400 | +| policy_gradient_loss | -0.0729 | +| value_loss | 0.000768 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 309 | +| iterations | 5489 | +| time_elapsed | 18145 | +| total_timesteps | 5620736 | +| train/ | | +| approx_kl | 2.1065922 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.323 | +| explained_variance | -1.7 | +| learning_rate | 0.0001 | +| loss | -0.114 | +| n_updates | 115410 | +| policy_gradient_loss | -0.0664 | +| value_loss | 0.000668 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.278 | +| time/ | | +| fps | 309 | +| iterations | 5490 | +| time_elapsed | 18149 | +| total_timesteps | 5621760 | +| train/ | | +| approx_kl | 2.3546927 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.391 | +| explained_variance | -5.64 | +| learning_rate | 0.0001 | +| loss | -0.1 | +| n_updates | 115420 | +| policy_gradient_loss | -0.0665 | +| value_loss | 0.000382 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.28 | +| time/ | | +| fps | 309 | +| iterations | 5491 | +| time_elapsed | 18152 | +| total_timesteps | 5622784 | +| train/ | | +| approx_kl | 2.1790032 | +| clip_fraction | 0.457 | +| clip_range | 0.2 | +| entropy_loss | -0.346 | +| explained_variance | -0.54 | +| learning_rate | 0.0001 | +| loss | -0.057 | +| n_updates | 115430 | +| policy_gradient_loss | -0.0559 | +| value_loss | 0.000526 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.28 | +| time/ | | +| fps | 309 | +| iterations | 5492 | +| time_elapsed | 18155 | +| total_timesteps | 5623808 | +| train/ | | +| approx_kl | 2.5010252 | +| clip_fraction | 0.47 | +| clip_range | 0.2 | +| entropy_loss | -0.344 | +| explained_variance | -1.48 | +| learning_rate | 0.0001 | +| loss | -0.0714 | +| n_updates | 115440 | +| policy_gradient_loss | -0.0712 | +| value_loss | 0.000756 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.28 | +| time/ | | +| fps | 309 | +| iterations | 5493 | +| time_elapsed | 18158 | +| total_timesteps | 5624832 | +| train/ | | +| approx_kl | 2.89035 | +| clip_fraction | 0.491 | +| clip_range | 0.2 | +| entropy_loss | -0.359 | +| explained_variance | -2.63 | +| learning_rate | 0.0001 | +| loss | -0.0555 | +| n_updates | 115450 | +| policy_gradient_loss | -0.0732 | +| value_loss | 0.000671 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 309 | +| iterations | 5494 | +| time_elapsed | 18161 | +| total_timesteps | 5625856 | +| train/ | | +| approx_kl | 2.2642713 | +| clip_fraction | 0.497 | +| clip_range | 0.2 | +| entropy_loss | -0.375 | +| explained_variance | -13.1 | +| learning_rate | 0.0001 | +| loss | -0.11 | +| n_updates | 115460 | +| policy_gradient_loss | -0.0753 | +| value_loss | 0.000425 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 309 | +| iterations | 5495 | +| time_elapsed | 18165 | +| total_timesteps | 5626880 | +| train/ | | +| approx_kl | 2.339829 | +| clip_fraction | 0.474 | +| clip_range | 0.2 | +| entropy_loss | -0.33 | +| explained_variance | -2.18 | +| learning_rate | 0.0001 | +| loss | -0.084 | +| n_updates | 115470 | +| policy_gradient_loss | -0.0685 | +| value_loss | 0.000354 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.28 | +| time/ | | +| fps | 309 | +| iterations | 5496 | +| time_elapsed | 18168 | +| total_timesteps | 5627904 | +| train/ | | +| approx_kl | 2.295 | +| clip_fraction | 0.511 | +| clip_range | 0.2 | +| entropy_loss | -0.397 | +| explained_variance | -0.836 | +| learning_rate | 0.0001 | +| loss | -0.109 | +| n_updates | 115480 | +| policy_gradient_loss | -0.0695 | +| value_loss | 0.000399 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.284 | +| time/ | | +| fps | 309 | +| iterations | 5497 | +| time_elapsed | 18171 | +| total_timesteps | 5628928 | +| train/ | | +| approx_kl | 2.3283806 | +| clip_fraction | 0.476 | +| clip_range | 0.2 | +| entropy_loss | -0.362 | +| explained_variance | -0.924 | +| learning_rate | 0.0001 | +| loss | -0.0824 | +| n_updates | 115490 | +| policy_gradient_loss | -0.064 | +| value_loss | 0.000697 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.284 | +| time/ | | +| fps | 309 | +| iterations | 5498 | +| time_elapsed | 18175 | +| total_timesteps | 5629952 | +| train/ | | +| approx_kl | 2.3151693 | +| clip_fraction | 0.468 | +| clip_range | 0.2 | +| entropy_loss | -0.338 | +| explained_variance | -1.44 | +| learning_rate | 0.0001 | +| loss | -0.0788 | +| n_updates | 115500 | +| policy_gradient_loss | -0.0692 | +| value_loss | 0.000767 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.286 | +| time/ | | +| fps | 309 | +| iterations | 5499 | +| time_elapsed | 18178 | +| total_timesteps | 5630976 | +| train/ | | +| approx_kl | 2.3061843 | +| clip_fraction | 0.514 | +| clip_range | 0.2 | +| entropy_loss | -0.415 | +| explained_variance | -3.1 | +| learning_rate | 0.0001 | +| loss | -0.0884 | +| n_updates | 115510 | +| policy_gradient_loss | -0.0739 | +| value_loss | 0.000736 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.285 | +| time/ | | +| fps | 309 | +| iterations | 5500 | +| time_elapsed | 18181 | +| total_timesteps | 5632000 | +| train/ | | +| approx_kl | 2.3784876 | +| clip_fraction | 0.472 | +| clip_range | 0.2 | +| entropy_loss | -0.324 | +| explained_variance | -1.23 | +| learning_rate | 0.0001 | +| loss | -0.0901 | +| n_updates | 115520 | +| policy_gradient_loss | -0.0648 | +| value_loss | 0.000619 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.285 | +| time/ | | +| fps | 309 | +| iterations | 5501 | +| time_elapsed | 18185 | +| total_timesteps | 5633024 | +| train/ | | +| approx_kl | 2.3693397 | +| clip_fraction | 0.434 | +| clip_range | 0.2 | +| entropy_loss | -0.297 | +| explained_variance | -1.54 | +| learning_rate | 0.0001 | +| loss | -0.072 | +| n_updates | 115530 | +| policy_gradient_loss | -0.0656 | +| value_loss | 0.000542 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.291 | +| time/ | | +| fps | 309 | +| iterations | 5502 | +| time_elapsed | 18188 | +| total_timesteps | 5634048 | +| train/ | | +| approx_kl | 2.1705208 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.355 | +| explained_variance | -1.47 | +| learning_rate | 0.0001 | +| loss | -0.1 | +| n_updates | 115540 | +| policy_gradient_loss | -0.0658 | +| value_loss | 0.000596 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.295 | +| time/ | | +| fps | 309 | +| iterations | 5503 | +| time_elapsed | 18191 | +| total_timesteps | 5635072 | +| train/ | | +| approx_kl | 2.208923 | +| clip_fraction | 0.456 | +| clip_range | 0.2 | +| entropy_loss | -0.348 | +| explained_variance | -0.875 | +| learning_rate | 0.0001 | +| loss | -0.0845 | +| n_updates | 115550 | +| policy_gradient_loss | -0.0655 | +| value_loss | 0.000793 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.294 | +| time/ | | +| fps | 309 | +| iterations | 5504 | +| time_elapsed | 18194 | +| total_timesteps | 5636096 | +| train/ | | +| approx_kl | 2.693868 | +| clip_fraction | 0.465 | +| clip_range | 0.2 | +| entropy_loss | -0.305 | +| explained_variance | -1.47 | +| learning_rate | 0.0001 | +| loss | -0.0889 | +| n_updates | 115560 | +| policy_gradient_loss | -0.0721 | +| value_loss | 0.000742 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.294 | +| time/ | | +| fps | 309 | +| iterations | 5505 | +| time_elapsed | 18197 | +| total_timesteps | 5637120 | +| train/ | | +| approx_kl | 2.2867258 | +| clip_fraction | 0.448 | +| clip_range | 0.2 | +| entropy_loss | -0.313 | +| explained_variance | -1.82 | +| learning_rate | 0.0001 | +| loss | -0.0741 | +| n_updates | 115570 | +| policy_gradient_loss | -0.0697 | +| value_loss | 0.000487 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.293 | +| time/ | | +| fps | 309 | +| iterations | 5506 | +| time_elapsed | 18200 | +| total_timesteps | 5638144 | +| train/ | | +| approx_kl | 3.0087504 | +| clip_fraction | 0.484 | +| clip_range | 0.2 | +| entropy_loss | -0.346 | +| explained_variance | -3.1 | +| learning_rate | 0.0001 | +| loss | -0.0878 | +| n_updates | 115580 | +| policy_gradient_loss | -0.0724 | +| value_loss | 0.000502 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.293 | +| time/ | | +| fps | 309 | +| iterations | 5507 | +| time_elapsed | 18204 | +| total_timesteps | 5639168 | +| train/ | | +| approx_kl | 2.6540654 | +| clip_fraction | 0.449 | +| clip_range | 0.2 | +| entropy_loss | -0.298 | +| explained_variance | -2.1 | +| learning_rate | 0.0001 | +| loss | -0.0929 | +| n_updates | 115590 | +| policy_gradient_loss | -0.0704 | +| value_loss | 0.000511 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.293 | +| time/ | | +| fps | 309 | +| iterations | 5508 | +| time_elapsed | 18207 | +| total_timesteps | 5640192 | +| train/ | | +| approx_kl | 2.2907612 | +| clip_fraction | 0.479 | +| clip_range | 0.2 | +| entropy_loss | -0.341 | +| explained_variance | -1.6 | +| learning_rate | 0.0001 | +| loss | -0.0838 | +| n_updates | 115600 | +| policy_gradient_loss | -0.0651 | +| value_loss | 0.000496 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.288 | +| time/ | | +| fps | 309 | +| iterations | 5509 | +| time_elapsed | 18210 | +| total_timesteps | 5641216 | +| train/ | | +| approx_kl | 2.6185904 | +| clip_fraction | 0.419 | +| clip_range | 0.2 | +| entropy_loss | -0.287 | +| explained_variance | -1.83 | +| learning_rate | 0.0001 | +| loss | -0.0669 | +| n_updates | 115610 | +| policy_gradient_loss | -0.0605 | +| value_loss | 0.000622 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.288 | +| time/ | | +| fps | 309 | +| iterations | 5510 | +| time_elapsed | 18213 | +| total_timesteps | 5642240 | +| train/ | | +| approx_kl | 2.494073 | +| clip_fraction | 0.434 | +| clip_range | 0.2 | +| entropy_loss | -0.296 | +| explained_variance | -1.17 | +| learning_rate | 0.0001 | +| loss | -0.0777 | +| n_updates | 115620 | +| policy_gradient_loss | -0.0656 | +| value_loss | 0.00055 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.288 | +| time/ | | +| fps | 309 | +| iterations | 5511 | +| time_elapsed | 18216 | +| total_timesteps | 5643264 | +| train/ | | +| approx_kl | 4.0691843 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.324 | +| explained_variance | -9.98 | +| learning_rate | 0.0001 | +| loss | -0.0767 | +| n_updates | 115630 | +| policy_gradient_loss | -0.0717 | +| value_loss | 0.00038 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.289 | +| time/ | | +| fps | 309 | +| iterations | 5512 | +| time_elapsed | 18219 | +| total_timesteps | 5644288 | +| train/ | | +| approx_kl | 2.5742612 | +| clip_fraction | 0.484 | +| clip_range | 0.2 | +| entropy_loss | -0.328 | +| explained_variance | -0.962 | +| learning_rate | 0.0001 | +| loss | -0.0917 | +| n_updates | 115640 | +| policy_gradient_loss | -0.0682 | +| value_loss | 0.000614 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.292 | +| time/ | | +| fps | 309 | +| iterations | 5513 | +| time_elapsed | 18223 | +| total_timesteps | 5645312 | +| train/ | | +| approx_kl | 2.3732839 | +| clip_fraction | 0.484 | +| clip_range | 0.2 | +| entropy_loss | -0.371 | +| explained_variance | -1.84 | +| learning_rate | 0.0001 | +| loss | -0.0898 | +| n_updates | 115650 | +| policy_gradient_loss | -0.0704 | +| value_loss | 0.000505 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.294 | +| time/ | | +| fps | 309 | +| iterations | 5514 | +| time_elapsed | 18227 | +| total_timesteps | 5646336 | +| train/ | | +| approx_kl | 2.2347765 | +| clip_fraction | 0.459 | +| clip_range | 0.2 | +| entropy_loss | -0.34 | +| explained_variance | -0.312 | +| learning_rate | 0.0001 | +| loss | -0.0797 | +| n_updates | 115660 | +| policy_gradient_loss | -0.0657 | +| value_loss | 0.000898 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 309 | +| iterations | 5515 | +| time_elapsed | 18230 | +| total_timesteps | 5647360 | +| train/ | | +| approx_kl | 3.2190413 | +| clip_fraction | 0.435 | +| clip_range | 0.2 | +| entropy_loss | -0.302 | +| explained_variance | -2.2 | +| learning_rate | 0.0001 | +| loss | -0.0635 | +| n_updates | 115670 | +| policy_gradient_loss | -0.065 | +| value_loss | 0.000727 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 309 | +| iterations | 5516 | +| time_elapsed | 18234 | +| total_timesteps | 5648384 | +| train/ | | +| approx_kl | 2.8021452 | +| clip_fraction | 0.45 | +| clip_range | 0.2 | +| entropy_loss | -0.298 | +| explained_variance | -0.964 | +| learning_rate | 0.0001 | +| loss | -0.088 | +| n_updates | 115680 | +| policy_gradient_loss | -0.0666 | +| value_loss | 0.000684 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 309 | +| iterations | 5517 | +| time_elapsed | 18237 | +| total_timesteps | 5649408 | +| train/ | | +| approx_kl | 2.445054 | +| clip_fraction | 0.474 | +| clip_range | 0.2 | +| entropy_loss | -0.355 | +| explained_variance | -1.77 | +| learning_rate | 0.0001 | +| loss | -0.0691 | +| n_updates | 115690 | +| policy_gradient_loss | -0.0714 | +| value_loss | 0.000625 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.3 | +| time/ | | +| fps | 309 | +| iterations | 5518 | +| time_elapsed | 18241 | +| total_timesteps | 5650432 | +| train/ | | +| approx_kl | 2.4429936 | +| clip_fraction | 0.479 | +| clip_range | 0.2 | +| entropy_loss | -0.313 | +| explained_variance | -1.11 | +| learning_rate | 0.0001 | +| loss | -0.0574 | +| n_updates | 115700 | +| policy_gradient_loss | -0.0654 | +| value_loss | 0.00084 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.3 | +| time/ | | +| fps | 309 | +| iterations | 5519 | +| time_elapsed | 18244 | +| total_timesteps | 5651456 | +| train/ | | +| approx_kl | 2.2323475 | +| clip_fraction | 0.466 | +| clip_range | 0.2 | +| entropy_loss | -0.353 | +| explained_variance | -1.65 | +| learning_rate | 0.0001 | +| loss | -0.0814 | +| n_updates | 115710 | +| policy_gradient_loss | -0.0635 | +| value_loss | 0.000527 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 309 | +| iterations | 5520 | +| time_elapsed | 18248 | +| total_timesteps | 5652480 | +| train/ | | +| approx_kl | 2.3050566 | +| clip_fraction | 0.482 | +| clip_range | 0.2 | +| entropy_loss | -0.325 | +| explained_variance | -3.07 | +| learning_rate | 0.0001 | +| loss | -0.0941 | +| n_updates | 115720 | +| policy_gradient_loss | -0.0731 | +| value_loss | 0.000366 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 309 | +| iterations | 5521 | +| time_elapsed | 18251 | +| total_timesteps | 5653504 | +| train/ | | +| approx_kl | 2.3371878 | +| clip_fraction | 0.445 | +| clip_range | 0.2 | +| entropy_loss | -0.333 | +| explained_variance | -0.981 | +| learning_rate | 0.0001 | +| loss | -0.0901 | +| n_updates | 115730 | +| policy_gradient_loss | -0.064 | +| value_loss | 0.000269 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.297 | +| time/ | | +| fps | 309 | +| iterations | 5522 | +| time_elapsed | 18254 | +| total_timesteps | 5654528 | +| train/ | | +| approx_kl | 2.3577824 | +| clip_fraction | 0.479 | +| clip_range | 0.2 | +| entropy_loss | -0.349 | +| explained_variance | -0.547 | +| learning_rate | 0.0001 | +| loss | -0.105 | +| n_updates | 115740 | +| policy_gradient_loss | -0.0702 | +| value_loss | 0.000441 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.297 | +| time/ | | +| fps | 309 | +| iterations | 5523 | +| time_elapsed | 18257 | +| total_timesteps | 5655552 | +| train/ | | +| approx_kl | 1.8613176 | +| clip_fraction | 0.479 | +| clip_range | 0.2 | +| entropy_loss | -0.391 | +| explained_variance | -1.64 | +| learning_rate | 0.0001 | +| loss | -0.0923 | +| n_updates | 115750 | +| policy_gradient_loss | -0.0674 | +| value_loss | 0.000358 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 309 | +| iterations | 5524 | +| time_elapsed | 18261 | +| total_timesteps | 5656576 | +| train/ | | +| approx_kl | 2.1029997 | +| clip_fraction | 0.477 | +| clip_range | 0.2 | +| entropy_loss | -0.377 | +| explained_variance | -1.27 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 115760 | +| policy_gradient_loss | -0.0606 | +| value_loss | 0.000457 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 309 | +| iterations | 5525 | +| time_elapsed | 18264 | +| total_timesteps | 5657600 | +| train/ | | +| approx_kl | 1.7438627 | +| clip_fraction | 0.44 | +| clip_range | 0.2 | +| entropy_loss | -0.332 | +| explained_variance | -1.22 | +| learning_rate | 0.0001 | +| loss | -0.0721 | +| n_updates | 115770 | +| policy_gradient_loss | -0.0624 | +| value_loss | 0.000547 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.3 | +| time/ | | +| fps | 309 | +| iterations | 5526 | +| time_elapsed | 18267 | +| total_timesteps | 5658624 | +| train/ | | +| approx_kl | 3.1836252 | +| clip_fraction | 0.499 | +| clip_range | 0.2 | +| entropy_loss | -0.365 | +| explained_variance | -1.69 | +| learning_rate | 0.0001 | +| loss | -0.108 | +| n_updates | 115780 | +| policy_gradient_loss | -0.0747 | +| value_loss | 0.000556 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.3 | +| time/ | | +| fps | 309 | +| iterations | 5527 | +| time_elapsed | 18270 | +| total_timesteps | 5659648 | +| train/ | | +| approx_kl | 2.2005672 | +| clip_fraction | 0.446 | +| clip_range | 0.2 | +| entropy_loss | -0.303 | +| explained_variance | -1.41 | +| learning_rate | 0.0001 | +| loss | -0.0632 | +| n_updates | 115790 | +| policy_gradient_loss | -0.0622 | +| value_loss | 0.000888 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.3 | +| time/ | | +| fps | 309 | +| iterations | 5528 | +| time_elapsed | 18274 | +| total_timesteps | 5660672 | +| train/ | | +| approx_kl | 2.8011913 | +| clip_fraction | 0.465 | +| clip_range | 0.2 | +| entropy_loss | -0.316 | +| explained_variance | -1.47 | +| learning_rate | 0.0001 | +| loss | -0.0886 | +| n_updates | 115800 | +| policy_gradient_loss | -0.0698 | +| value_loss | 0.000752 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.3 | +| time/ | | +| fps | 309 | +| iterations | 5529 | +| time_elapsed | 18277 | +| total_timesteps | 5661696 | +| train/ | | +| approx_kl | 2.2268555 | +| clip_fraction | 0.43 | +| clip_range | 0.2 | +| entropy_loss | -0.284 | +| explained_variance | -2.64 | +| learning_rate | 0.0001 | +| loss | -0.053 | +| n_updates | 115810 | +| policy_gradient_loss | -0.057 | +| value_loss | 0.000638 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 309 | +| iterations | 5530 | +| time_elapsed | 18280 | +| total_timesteps | 5662720 | +| train/ | | +| approx_kl | 3.6068351 | +| clip_fraction | 0.465 | +| clip_range | 0.2 | +| entropy_loss | -0.309 | +| explained_variance | -3.53 | +| learning_rate | 0.0001 | +| loss | -0.1 | +| n_updates | 115820 | +| policy_gradient_loss | -0.0727 | +| value_loss | 0.000553 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 309 | +| iterations | 5531 | +| time_elapsed | 18284 | +| total_timesteps | 5663744 | +| train/ | | +| approx_kl | 3.1375706 | +| clip_fraction | 0.442 | +| clip_range | 0.2 | +| entropy_loss | -0.313 | +| explained_variance | -0.986 | +| learning_rate | 0.0001 | +| loss | -0.0723 | +| n_updates | 115830 | +| policy_gradient_loss | -0.0572 | +| value_loss | 0.000539 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 309 | +| iterations | 5532 | +| time_elapsed | 18287 | +| total_timesteps | 5664768 | +| train/ | | +| approx_kl | 1.9852471 | +| clip_fraction | 0.486 | +| clip_range | 0.2 | +| entropy_loss | -0.363 | +| explained_variance | -5.93 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 115840 | +| policy_gradient_loss | -0.0678 | +| value_loss | 0.000512 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 309 | +| iterations | 5533 | +| time_elapsed | 18290 | +| total_timesteps | 5665792 | +| train/ | | +| approx_kl | 2.10187 | +| clip_fraction | 0.436 | +| clip_range | 0.2 | +| entropy_loss | -0.339 | +| explained_variance | -0.461 | +| learning_rate | 0.0001 | +| loss | -0.085 | +| n_updates | 115850 | +| policy_gradient_loss | -0.056 | +| value_loss | 0.0005 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 309 | +| iterations | 5534 | +| time_elapsed | 18294 | +| total_timesteps | 5666816 | +| train/ | | +| approx_kl | 2.1392934 | +| clip_fraction | 0.411 | +| clip_range | 0.2 | +| entropy_loss | -0.285 | +| explained_variance | -0.157 | +| learning_rate | 0.0001 | +| loss | -0.0819 | +| n_updates | 115860 | +| policy_gradient_loss | -0.0662 | +| value_loss | 0.000855 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 309 | +| iterations | 5535 | +| time_elapsed | 18297 | +| total_timesteps | 5667840 | +| train/ | | +| approx_kl | 2.5574214 | +| clip_fraction | 0.442 | +| clip_range | 0.2 | +| entropy_loss | -0.308 | +| explained_variance | -1.4 | +| learning_rate | 0.0001 | +| loss | -0.0829 | +| n_updates | 115870 | +| policy_gradient_loss | -0.0642 | +| value_loss | 0.00101 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 309 | +| iterations | 5536 | +| time_elapsed | 18301 | +| total_timesteps | 5668864 | +| train/ | | +| approx_kl | 2.6672223 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.369 | +| explained_variance | -1.19 | +| learning_rate | 0.0001 | +| loss | -0.085 | +| n_updates | 115880 | +| policy_gradient_loss | -0.0676 | +| value_loss | 0.000855 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 309 | +| iterations | 5537 | +| time_elapsed | 18304 | +| total_timesteps | 5669888 | +| train/ | | +| approx_kl | 3.417242 | +| clip_fraction | 0.493 | +| clip_range | 0.2 | +| entropy_loss | -0.33 | +| explained_variance | -1.92 | +| learning_rate | 0.0001 | +| loss | -0.0719 | +| n_updates | 115890 | +| policy_gradient_loss | -0.0715 | +| value_loss | 0.000687 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 309 | +| iterations | 5538 | +| time_elapsed | 18308 | +| total_timesteps | 5670912 | +| train/ | | +| approx_kl | 2.5509694 | +| clip_fraction | 0.464 | +| clip_range | 0.2 | +| entropy_loss | -0.311 | +| explained_variance | -1.69 | +| learning_rate | 0.0001 | +| loss | -0.0869 | +| n_updates | 115900 | +| policy_gradient_loss | -0.0629 | +| value_loss | 0.000633 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 309 | +| iterations | 5539 | +| time_elapsed | 18311 | +| total_timesteps | 5671936 | +| train/ | | +| approx_kl | 2.7978363 | +| clip_fraction | 0.473 | +| clip_range | 0.2 | +| entropy_loss | -0.321 | +| explained_variance | -1.61 | +| learning_rate | 0.0001 | +| loss | -0.065 | +| n_updates | 115910 | +| policy_gradient_loss | -0.0641 | +| value_loss | 0.000752 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 309 | +| iterations | 5540 | +| time_elapsed | 18314 | +| total_timesteps | 5672960 | +| train/ | | +| approx_kl | 3.5699856 | +| clip_fraction | 0.434 | +| clip_range | 0.2 | +| entropy_loss | -0.285 | +| explained_variance | -1.26 | +| learning_rate | 0.0001 | +| loss | -0.075 | +| n_updates | 115920 | +| policy_gradient_loss | -0.0657 | +| value_loss | 0.000796 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 309 | +| iterations | 5541 | +| time_elapsed | 18317 | +| total_timesteps | 5673984 | +| train/ | | +| approx_kl | 2.7923121 | +| clip_fraction | 0.451 | +| clip_range | 0.2 | +| entropy_loss | -0.292 | +| explained_variance | -1.05 | +| learning_rate | 0.0001 | +| loss | -0.0873 | +| n_updates | 115930 | +| policy_gradient_loss | -0.0628 | +| value_loss | 0.000782 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 309 | +| iterations | 5542 | +| time_elapsed | 18320 | +| total_timesteps | 5675008 | +| train/ | | +| approx_kl | 2.554483 | +| clip_fraction | 0.479 | +| clip_range | 0.2 | +| entropy_loss | -0.304 | +| explained_variance | -0.899 | +| learning_rate | 0.0001 | +| loss | -0.0916 | +| n_updates | 115940 | +| policy_gradient_loss | -0.0711 | +| value_loss | 0.000778 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 309 | +| iterations | 5543 | +| time_elapsed | 18324 | +| total_timesteps | 5676032 | +| train/ | | +| approx_kl | 2.9133615 | +| clip_fraction | 0.476 | +| clip_range | 0.2 | +| entropy_loss | -0.308 | +| explained_variance | -2.61 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 115950 | +| policy_gradient_loss | -0.0746 | +| value_loss | 0.000767 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 309 | +| iterations | 5544 | +| time_elapsed | 18327 | +| total_timesteps | 5677056 | +| train/ | | +| approx_kl | 3.2713299 | +| clip_fraction | 0.485 | +| clip_range | 0.2 | +| entropy_loss | -0.312 | +| explained_variance | -1.39 | +| learning_rate | 0.0001 | +| loss | -0.109 | +| n_updates | 115960 | +| policy_gradient_loss | -0.0732 | +| value_loss | 0.000667 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 309 | +| iterations | 5545 | +| time_elapsed | 18330 | +| total_timesteps | 5678080 | +| train/ | | +| approx_kl | 4.1517754 | +| clip_fraction | 0.456 | +| clip_range | 0.2 | +| entropy_loss | -0.315 | +| explained_variance | -2.81 | +| learning_rate | 0.0001 | +| loss | -0.0979 | +| n_updates | 115970 | +| policy_gradient_loss | -0.0676 | +| value_loss | 0.000523 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 309 | +| iterations | 5546 | +| time_elapsed | 18333 | +| total_timesteps | 5679104 | +| train/ | | +| approx_kl | 2.9278524 | +| clip_fraction | 0.454 | +| clip_range | 0.2 | +| entropy_loss | -0.325 | +| explained_variance | -1.06 | +| learning_rate | 0.0001 | +| loss | -0.0594 | +| n_updates | 115980 | +| policy_gradient_loss | -0.0676 | +| value_loss | 0.000547 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 309 | +| iterations | 5547 | +| time_elapsed | 18336 | +| total_timesteps | 5680128 | +| train/ | | +| approx_kl | 2.2063398 | +| clip_fraction | 0.451 | +| clip_range | 0.2 | +| entropy_loss | -0.332 | +| explained_variance | -0.941 | +| learning_rate | 0.0001 | +| loss | -0.0982 | +| n_updates | 115990 | +| policy_gradient_loss | -0.0625 | +| value_loss | 0.000707 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 309 | +| iterations | 5548 | +| time_elapsed | 18340 | +| total_timesteps | 5681152 | +| train/ | | +| approx_kl | 6.82934 | +| clip_fraction | 0.476 | +| clip_range | 0.2 | +| entropy_loss | -0.357 | +| explained_variance | -1.23 | +| learning_rate | 0.0001 | +| loss | -0.0965 | +| n_updates | 116000 | +| policy_gradient_loss | -0.0634 | +| value_loss | 0.000548 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 309 | +| iterations | 5549 | +| time_elapsed | 18343 | +| total_timesteps | 5682176 | +| train/ | | +| approx_kl | 2.4889958 | +| clip_fraction | 0.448 | +| clip_range | 0.2 | +| entropy_loss | -0.306 | +| explained_variance | -1.08 | +| learning_rate | 0.0001 | +| loss | -0.0854 | +| n_updates | 116010 | +| policy_gradient_loss | -0.0633 | +| value_loss | 0.000599 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 309 | +| iterations | 5550 | +| time_elapsed | 18347 | +| total_timesteps | 5683200 | +| train/ | | +| approx_kl | 2.716463 | +| clip_fraction | 0.442 | +| clip_range | 0.2 | +| entropy_loss | -0.265 | +| explained_variance | -3.14 | +| learning_rate | 0.0001 | +| loss | -0.0918 | +| n_updates | 116020 | +| policy_gradient_loss | -0.0705 | +| value_loss | 0.000548 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 309 | +| iterations | 5551 | +| time_elapsed | 18350 | +| total_timesteps | 5684224 | +| train/ | | +| approx_kl | 2.8813772 | +| clip_fraction | 0.467 | +| clip_range | 0.2 | +| entropy_loss | -0.311 | +| explained_variance | -0.922 | +| learning_rate | 0.0001 | +| loss | -0.115 | +| n_updates | 116030 | +| policy_gradient_loss | -0.0694 | +| value_loss | 0.000816 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 309 | +| iterations | 5552 | +| time_elapsed | 18354 | +| total_timesteps | 5685248 | +| train/ | | +| approx_kl | 2.8426266 | +| clip_fraction | 0.43 | +| clip_range | 0.2 | +| entropy_loss | -0.293 | +| explained_variance | -1.86 | +| learning_rate | 0.0001 | +| loss | -0.0926 | +| n_updates | 116040 | +| policy_gradient_loss | -0.0673 | +| value_loss | 0.000802 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 309 | +| iterations | 5553 | +| time_elapsed | 18357 | +| total_timesteps | 5686272 | +| train/ | | +| approx_kl | 2.2758188 | +| clip_fraction | 0.447 | +| clip_range | 0.2 | +| entropy_loss | -0.315 | +| explained_variance | -9.56 | +| learning_rate | 0.0001 | +| loss | -0.066 | +| n_updates | 116050 | +| policy_gradient_loss | -0.0707 | +| value_loss | 0.000538 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 309 | +| iterations | 5554 | +| time_elapsed | 18361 | +| total_timesteps | 5687296 | +| train/ | | +| approx_kl | 2.4683826 | +| clip_fraction | 0.449 | +| clip_range | 0.2 | +| entropy_loss | -0.317 | +| explained_variance | -1.13 | +| learning_rate | 0.0001 | +| loss | -0.0943 | +| n_updates | 116060 | +| policy_gradient_loss | -0.0655 | +| value_loss | 0.000578 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.65e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 309 | +| iterations | 5555 | +| time_elapsed | 18364 | +| total_timesteps | 5688320 | +| train/ | | +| approx_kl | 3.5876384 | +| clip_fraction | 0.449 | +| clip_range | 0.2 | +| entropy_loss | -0.291 | +| explained_variance | -2.15 | +| learning_rate | 0.0001 | +| loss | -0.0795 | +| n_updates | 116070 | +| policy_gradient_loss | -0.067 | +| value_loss | 0.0011 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.65e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 309 | +| iterations | 5556 | +| time_elapsed | 18368 | +| total_timesteps | 5689344 | +| train/ | | +| approx_kl | 2.5603023 | +| clip_fraction | 0.43 | +| clip_range | 0.2 | +| entropy_loss | -0.309 | +| explained_variance | -1.58 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 116080 | +| policy_gradient_loss | -0.0617 | +| value_loss | 0.000593 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.65e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 309 | +| iterations | 5557 | +| time_elapsed | 18371 | +| total_timesteps | 5690368 | +| train/ | | +| approx_kl | 6.722391 | +| clip_fraction | 0.455 | +| clip_range | 0.2 | +| entropy_loss | -0.316 | +| explained_variance | -1.95 | +| learning_rate | 0.0001 | +| loss | -0.0773 | +| n_updates | 116090 | +| policy_gradient_loss | -0.0615 | +| value_loss | 0.00053 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 309 | +| iterations | 5558 | +| time_elapsed | 18374 | +| total_timesteps | 5691392 | +| train/ | | +| approx_kl | 2.7645392 | +| clip_fraction | 0.468 | +| clip_range | 0.2 | +| entropy_loss | -0.323 | +| explained_variance | -1.75 | +| learning_rate | 0.0001 | +| loss | -0.0791 | +| n_updates | 116100 | +| policy_gradient_loss | -0.0683 | +| value_loss | 0.000509 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 309 | +| iterations | 5559 | +| time_elapsed | 18377 | +| total_timesteps | 5692416 | +| train/ | | +| approx_kl | 2.3601863 | +| clip_fraction | 0.456 | +| clip_range | 0.2 | +| entropy_loss | -0.346 | +| explained_variance | -0.613 | +| learning_rate | 0.0001 | +| loss | -0.0826 | +| n_updates | 116110 | +| policy_gradient_loss | -0.0567 | +| value_loss | 0.000485 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 309 | +| iterations | 5560 | +| time_elapsed | 18381 | +| total_timesteps | 5693440 | +| train/ | | +| approx_kl | 2.4751844 | +| clip_fraction | 0.477 | +| clip_range | 0.2 | +| entropy_loss | -0.338 | +| explained_variance | -1.91 | +| learning_rate | 0.0001 | +| loss | -0.107 | +| n_updates | 116120 | +| policy_gradient_loss | -0.0657 | +| value_loss | 0.000677 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 309 | +| iterations | 5561 | +| time_elapsed | 18384 | +| total_timesteps | 5694464 | +| train/ | | +| approx_kl | 2.4088922 | +| clip_fraction | 0.468 | +| clip_range | 0.2 | +| entropy_loss | -0.327 | +| explained_variance | -2.31 | +| learning_rate | 0.0001 | +| loss | -0.0523 | +| n_updates | 116130 | +| policy_gradient_loss | -0.061 | +| value_loss | 0.000442 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 309 | +| iterations | 5562 | +| time_elapsed | 18387 | +| total_timesteps | 5695488 | +| train/ | | +| approx_kl | 2.5551543 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.312 | +| explained_variance | -1.67 | +| learning_rate | 0.0001 | +| loss | -0.0995 | +| n_updates | 116140 | +| policy_gradient_loss | -0.07 | +| value_loss | 0.000552 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 309 | +| iterations | 5563 | +| time_elapsed | 18390 | +| total_timesteps | 5696512 | +| train/ | | +| approx_kl | 3.0103393 | +| clip_fraction | 0.45 | +| clip_range | 0.2 | +| entropy_loss | -0.304 | +| explained_variance | -1.38 | +| learning_rate | 0.0001 | +| loss | -0.0856 | +| n_updates | 116150 | +| policy_gradient_loss | -0.0628 | +| value_loss | 0.000663 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 309 | +| iterations | 5564 | +| time_elapsed | 18394 | +| total_timesteps | 5697536 | +| train/ | | +| approx_kl | 3.465364 | +| clip_fraction | 0.469 | +| clip_range | 0.2 | +| entropy_loss | -0.302 | +| explained_variance | -4.98 | +| learning_rate | 0.0001 | +| loss | -0.0852 | +| n_updates | 116160 | +| policy_gradient_loss | -0.0731 | +| value_loss | 0.000543 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 309 | +| iterations | 5565 | +| time_elapsed | 18397 | +| total_timesteps | 5698560 | +| train/ | | +| approx_kl | 6.9422646 | +| clip_fraction | 0.465 | +| clip_range | 0.2 | +| entropy_loss | -0.334 | +| explained_variance | -1.34 | +| learning_rate | 0.0001 | +| loss | -0.0663 | +| n_updates | 116170 | +| policy_gradient_loss | -0.0643 | +| value_loss | 0.000331 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 309 | +| iterations | 5566 | +| time_elapsed | 18400 | +| total_timesteps | 5699584 | +| train/ | | +| approx_kl | 2.800878 | +| clip_fraction | 0.476 | +| clip_range | 0.2 | +| entropy_loss | -0.36 | +| explained_variance | -1.21 | +| learning_rate | 0.0001 | +| loss | -0.0861 | +| n_updates | 116180 | +| policy_gradient_loss | -0.0664 | +| value_loss | 0.000359 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 309 | +| iterations | 5567 | +| time_elapsed | 18404 | +| total_timesteps | 5700608 | +| train/ | | +| approx_kl | 4.331896 | +| clip_fraction | 0.455 | +| clip_range | 0.2 | +| entropy_loss | -0.311 | +| explained_variance | -1.31 | +| learning_rate | 0.0001 | +| loss | -0.0628 | +| n_updates | 116190 | +| policy_gradient_loss | -0.0617 | +| value_loss | 0.000625 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 309 | +| iterations | 5568 | +| time_elapsed | 18407 | +| total_timesteps | 5701632 | +| train/ | | +| approx_kl | 2.1317225 | +| clip_fraction | 0.456 | +| clip_range | 0.2 | +| entropy_loss | -0.331 | +| explained_variance | -0.742 | +| learning_rate | 0.0001 | +| loss | -0.0904 | +| n_updates | 116200 | +| policy_gradient_loss | -0.0644 | +| value_loss | 0.00105 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 309 | +| iterations | 5569 | +| time_elapsed | 18411 | +| total_timesteps | 5702656 | +| train/ | | +| approx_kl | 2.537117 | +| clip_fraction | 0.447 | +| clip_range | 0.2 | +| entropy_loss | -0.338 | +| explained_variance | -1.59 | +| learning_rate | 0.0001 | +| loss | -0.0791 | +| n_updates | 116210 | +| policy_gradient_loss | -0.0672 | +| value_loss | 0.000737 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 309 | +| iterations | 5570 | +| time_elapsed | 18414 | +| total_timesteps | 5703680 | +| train/ | | +| approx_kl | 1.8436546 | +| clip_fraction | 0.491 | +| clip_range | 0.2 | +| entropy_loss | -0.406 | +| explained_variance | -1.66 | +| learning_rate | 0.0001 | +| loss | -0.0957 | +| n_updates | 116220 | +| policy_gradient_loss | -0.0594 | +| value_loss | 0.000416 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 309 | +| iterations | 5571 | +| time_elapsed | 18418 | +| total_timesteps | 5704704 | +| train/ | | +| approx_kl | 2.6494446 | +| clip_fraction | 0.438 | +| clip_range | 0.2 | +| entropy_loss | -0.264 | +| explained_variance | -1.61 | +| learning_rate | 0.0001 | +| loss | -0.0913 | +| n_updates | 116230 | +| policy_gradient_loss | -0.0669 | +| value_loss | 0.000496 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 309 | +| iterations | 5572 | +| time_elapsed | 18421 | +| total_timesteps | 5705728 | +| train/ | | +| approx_kl | 2.6922603 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.323 | +| explained_variance | -1.99 | +| learning_rate | 0.0001 | +| loss | -0.0736 | +| n_updates | 116240 | +| policy_gradient_loss | -0.0691 | +| value_loss | 0.000691 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 309 | +| iterations | 5573 | +| time_elapsed | 18424 | +| total_timesteps | 5706752 | +| train/ | | +| approx_kl | 2.6072588 | +| clip_fraction | 0.462 | +| clip_range | 0.2 | +| entropy_loss | -0.339 | +| explained_variance | -3.08 | +| learning_rate | 0.0001 | +| loss | -0.0858 | +| n_updates | 116250 | +| policy_gradient_loss | -0.0689 | +| value_loss | 0.000357 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 309 | +| iterations | 5574 | +| time_elapsed | 18428 | +| total_timesteps | 5707776 | +| train/ | | +| approx_kl | 2.8804047 | +| clip_fraction | 0.428 | +| clip_range | 0.2 | +| entropy_loss | -0.257 | +| explained_variance | -4.76 | +| learning_rate | 0.0001 | +| loss | -0.075 | +| n_updates | 116260 | +| policy_gradient_loss | -0.0673 | +| value_loss | 0.000492 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 309 | +| iterations | 5575 | +| time_elapsed | 18431 | +| total_timesteps | 5708800 | +| train/ | | +| approx_kl | 2.2643259 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.379 | +| explained_variance | -0.53 | +| learning_rate | 0.0001 | +| loss | -0.0929 | +| n_updates | 116270 | +| policy_gradient_loss | -0.0634 | +| value_loss | 0.000697 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 309 | +| iterations | 5576 | +| time_elapsed | 18434 | +| total_timesteps | 5709824 | +| train/ | | +| approx_kl | 1.9498122 | +| clip_fraction | 0.45 | +| clip_range | 0.2 | +| entropy_loss | -0.336 | +| explained_variance | -2.32 | +| learning_rate | 0.0001 | +| loss | -0.0824 | +| n_updates | 116280 | +| policy_gradient_loss | -0.0643 | +| value_loss | 0.000634 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 309 | +| iterations | 5577 | +| time_elapsed | 18437 | +| total_timesteps | 5710848 | +| train/ | | +| approx_kl | 2.463263 | +| clip_fraction | 0.443 | +| clip_range | 0.2 | +| entropy_loss | -0.302 | +| explained_variance | -0.742 | +| learning_rate | 0.0001 | +| loss | -0.079 | +| n_updates | 116290 | +| policy_gradient_loss | -0.0669 | +| value_loss | 0.000625 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 309 | +| iterations | 5578 | +| time_elapsed | 18440 | +| total_timesteps | 5711872 | +| train/ | | +| approx_kl | 3.4697814 | +| clip_fraction | 0.498 | +| clip_range | 0.2 | +| entropy_loss | -0.329 | +| explained_variance | -0.77 | +| learning_rate | 0.0001 | +| loss | -0.0837 | +| n_updates | 116300 | +| policy_gradient_loss | -0.0696 | +| value_loss | 0.00059 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 309 | +| iterations | 5579 | +| time_elapsed | 18444 | +| total_timesteps | 5712896 | +| train/ | | +| approx_kl | 2.2833693 | +| clip_fraction | 0.474 | +| clip_range | 0.2 | +| entropy_loss | -0.323 | +| explained_variance | -7.11 | +| learning_rate | 0.0001 | +| loss | -0.0891 | +| n_updates | 116310 | +| policy_gradient_loss | -0.0707 | +| value_loss | 0.000791 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 309 | +| iterations | 5580 | +| time_elapsed | 18447 | +| total_timesteps | 5713920 | +| train/ | | +| approx_kl | 2.5421643 | +| clip_fraction | 0.432 | +| clip_range | 0.2 | +| entropy_loss | -0.294 | +| explained_variance | -1.41 | +| learning_rate | 0.0001 | +| loss | -0.0834 | +| n_updates | 116320 | +| policy_gradient_loss | -0.0593 | +| value_loss | 0.000625 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 309 | +| iterations | 5581 | +| time_elapsed | 18450 | +| total_timesteps | 5714944 | +| train/ | | +| approx_kl | 2.1827927 | +| clip_fraction | 0.445 | +| clip_range | 0.2 | +| entropy_loss | -0.288 | +| explained_variance | -2.47 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 116330 | +| policy_gradient_loss | -0.0642 | +| value_loss | 0.000487 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 309 | +| iterations | 5582 | +| time_elapsed | 18453 | +| total_timesteps | 5715968 | +| train/ | | +| approx_kl | 2.13953 | +| clip_fraction | 0.456 | +| clip_range | 0.2 | +| entropy_loss | -0.333 | +| explained_variance | -2.32 | +| learning_rate | 0.0001 | +| loss | -0.0857 | +| n_updates | 116340 | +| policy_gradient_loss | -0.0634 | +| value_loss | 0.000405 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 309 | +| iterations | 5583 | +| time_elapsed | 18457 | +| total_timesteps | 5716992 | +| train/ | | +| approx_kl | 2.5858946 | +| clip_fraction | 0.429 | +| clip_range | 0.2 | +| entropy_loss | -0.292 | +| explained_variance | -1.68 | +| learning_rate | 0.0001 | +| loss | -0.0807 | +| n_updates | 116350 | +| policy_gradient_loss | -0.0597 | +| value_loss | 0.00041 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 309 | +| iterations | 5584 | +| time_elapsed | 18460 | +| total_timesteps | 5718016 | +| train/ | | +| approx_kl | 2.4102068 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.317 | +| explained_variance | -1.87 | +| learning_rate | 0.0001 | +| loss | -0.0881 | +| n_updates | 116360 | +| policy_gradient_loss | -0.0662 | +| value_loss | 0.000635 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 309 | +| iterations | 5585 | +| time_elapsed | 18463 | +| total_timesteps | 5719040 | +| train/ | | +| approx_kl | 2.7304585 | +| clip_fraction | 0.453 | +| clip_range | 0.2 | +| entropy_loss | -0.325 | +| explained_variance | -2.74 | +| learning_rate | 0.0001 | +| loss | -0.0765 | +| n_updates | 116370 | +| policy_gradient_loss | -0.052 | +| value_loss | 0.00046 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 309 | +| iterations | 5586 | +| time_elapsed | 18467 | +| total_timesteps | 5720064 | +| train/ | | +| approx_kl | 2.793511 | +| clip_fraction | 0.474 | +| clip_range | 0.2 | +| entropy_loss | -0.327 | +| explained_variance | -1.7 | +| learning_rate | 0.0001 | +| loss | -0.0461 | +| n_updates | 116380 | +| policy_gradient_loss | -0.0702 | +| value_loss | 0.000469 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 309 | +| iterations | 5587 | +| time_elapsed | 18471 | +| total_timesteps | 5721088 | +| train/ | | +| approx_kl | 3.0663605 | +| clip_fraction | 0.473 | +| clip_range | 0.2 | +| entropy_loss | -0.33 | +| explained_variance | -1.95 | +| learning_rate | 0.0001 | +| loss | -0.0799 | +| n_updates | 116390 | +| policy_gradient_loss | -0.0717 | +| value_loss | 0.000633 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 309 | +| iterations | 5588 | +| time_elapsed | 18474 | +| total_timesteps | 5722112 | +| train/ | | +| approx_kl | 2.4800737 | +| clip_fraction | 0.442 | +| clip_range | 0.2 | +| entropy_loss | -0.298 | +| explained_variance | -1.78 | +| learning_rate | 0.0001 | +| loss | -0.0763 | +| n_updates | 116400 | +| policy_gradient_loss | -0.0635 | +| value_loss | 0.000421 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 309 | +| iterations | 5589 | +| time_elapsed | 18477 | +| total_timesteps | 5723136 | +| train/ | | +| approx_kl | 2.3235385 | +| clip_fraction | 0.439 | +| clip_range | 0.2 | +| entropy_loss | -0.321 | +| explained_variance | -0.991 | +| learning_rate | 0.0001 | +| loss | -0.044 | +| n_updates | 116410 | +| policy_gradient_loss | -0.0616 | +| value_loss | 0.000665 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 309 | +| iterations | 5590 | +| time_elapsed | 18481 | +| total_timesteps | 5724160 | +| train/ | | +| approx_kl | 2.7687678 | +| clip_fraction | 0.455 | +| clip_range | 0.2 | +| entropy_loss | -0.32 | +| explained_variance | -2.58 | +| learning_rate | 0.0001 | +| loss | -0.0973 | +| n_updates | 116420 | +| policy_gradient_loss | -0.0712 | +| value_loss | 0.000783 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 309 | +| iterations | 5591 | +| time_elapsed | 18484 | +| total_timesteps | 5725184 | +| train/ | | +| approx_kl | 3.256968 | +| clip_fraction | 0.444 | +| clip_range | 0.2 | +| entropy_loss | -0.305 | +| explained_variance | -1.46 | +| learning_rate | 0.0001 | +| loss | -0.0894 | +| n_updates | 116430 | +| policy_gradient_loss | -0.0625 | +| value_loss | 0.000648 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 309 | +| iterations | 5592 | +| time_elapsed | 18488 | +| total_timesteps | 5726208 | +| train/ | | +| approx_kl | 2.0079355 | +| clip_fraction | 0.444 | +| clip_range | 0.2 | +| entropy_loss | -0.326 | +| explained_variance | -3.75 | +| learning_rate | 0.0001 | +| loss | -0.0733 | +| n_updates | 116440 | +| policy_gradient_loss | -0.0687 | +| value_loss | 0.000464 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 309 | +| iterations | 5593 | +| time_elapsed | 18491 | +| total_timesteps | 5727232 | +| train/ | | +| approx_kl | 2.5958397 | +| clip_fraction | 0.456 | +| clip_range | 0.2 | +| entropy_loss | -0.322 | +| explained_variance | -1.47 | +| learning_rate | 0.0001 | +| loss | -0.0864 | +| n_updates | 116450 | +| policy_gradient_loss | -0.0643 | +| value_loss | 0.000746 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 309 | +| iterations | 5594 | +| time_elapsed | 18494 | +| total_timesteps | 5728256 | +| train/ | | +| approx_kl | 4.1196957 | +| clip_fraction | 0.449 | +| clip_range | 0.2 | +| entropy_loss | -0.274 | +| explained_variance | -1.75 | +| learning_rate | 0.0001 | +| loss | -0.094 | +| n_updates | 116460 | +| policy_gradient_loss | -0.0689 | +| value_loss | 0.000622 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 309 | +| iterations | 5595 | +| time_elapsed | 18497 | +| total_timesteps | 5729280 | +| train/ | | +| approx_kl | 2.851787 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.327 | +| explained_variance | -4.76 | +| learning_rate | 0.0001 | +| loss | -0.0957 | +| n_updates | 116470 | +| policy_gradient_loss | -0.0699 | +| value_loss | 0.000472 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 309 | +| iterations | 5596 | +| time_elapsed | 18501 | +| total_timesteps | 5730304 | +| train/ | | +| approx_kl | 2.8229802 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.29 | +| explained_variance | -1.93 | +| learning_rate | 0.0001 | +| loss | -0.0899 | +| n_updates | 116480 | +| policy_gradient_loss | -0.0767 | +| value_loss | 0.000531 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 309 | +| iterations | 5597 | +| time_elapsed | 18504 | +| total_timesteps | 5731328 | +| train/ | | +| approx_kl | 3.3175926 | +| clip_fraction | 0.441 | +| clip_range | 0.2 | +| entropy_loss | -0.279 | +| explained_variance | -2.32 | +| learning_rate | 0.0001 | +| loss | -0.0723 | +| n_updates | 116490 | +| policy_gradient_loss | -0.0647 | +| value_loss | 0.000584 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 309 | +| iterations | 5598 | +| time_elapsed | 18507 | +| total_timesteps | 5732352 | +| train/ | | +| approx_kl | 2.8456116 | +| clip_fraction | 0.453 | +| clip_range | 0.2 | +| entropy_loss | -0.29 | +| explained_variance | -0.773 | +| learning_rate | 0.0001 | +| loss | -0.084 | +| n_updates | 116500 | +| policy_gradient_loss | -0.0678 | +| value_loss | 0.000589 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 309 | +| iterations | 5599 | +| time_elapsed | 18510 | +| total_timesteps | 5733376 | +| train/ | | +| approx_kl | 2.3868308 | +| clip_fraction | 0.473 | +| clip_range | 0.2 | +| entropy_loss | -0.333 | +| explained_variance | -4.62 | +| learning_rate | 0.0001 | +| loss | -0.0783 | +| n_updates | 116510 | +| policy_gradient_loss | -0.07 | +| value_loss | 0.000448 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 309 | +| iterations | 5600 | +| time_elapsed | 18514 | +| total_timesteps | 5734400 | +| train/ | | +| approx_kl | 2.9046297 | +| clip_fraction | 0.461 | +| clip_range | 0.2 | +| entropy_loss | -0.289 | +| explained_variance | -2.16 | +| learning_rate | 0.0001 | +| loss | -0.0769 | +| n_updates | 116520 | +| policy_gradient_loss | -0.0635 | +| value_loss | 0.000691 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 309 | +| iterations | 5601 | +| time_elapsed | 18517 | +| total_timesteps | 5735424 | +| train/ | | +| approx_kl | 3.2492092 | +| clip_fraction | 0.463 | +| clip_range | 0.2 | +| entropy_loss | -0.3 | +| explained_variance | -1.18 | +| learning_rate | 0.0001 | +| loss | -0.105 | +| n_updates | 116530 | +| policy_gradient_loss | -0.0644 | +| value_loss | 0.000527 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 309 | +| iterations | 5602 | +| time_elapsed | 18520 | +| total_timesteps | 5736448 | +| train/ | | +| approx_kl | 2.898046 | +| clip_fraction | 0.489 | +| clip_range | 0.2 | +| entropy_loss | -0.35 | +| explained_variance | -2.33 | +| learning_rate | 0.0001 | +| loss | -0.084 | +| n_updates | 116540 | +| policy_gradient_loss | -0.0691 | +| value_loss | 0.000659 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 309 | +| iterations | 5603 | +| time_elapsed | 18524 | +| total_timesteps | 5737472 | +| train/ | | +| approx_kl | 2.5466437 | +| clip_fraction | 0.441 | +| clip_range | 0.2 | +| entropy_loss | -0.294 | +| explained_variance | -3.63 | +| learning_rate | 0.0001 | +| loss | -0.0737 | +| n_updates | 116550 | +| policy_gradient_loss | -0.0673 | +| value_loss | 0.00049 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 309 | +| iterations | 5604 | +| time_elapsed | 18527 | +| total_timesteps | 5738496 | +| train/ | | +| approx_kl | 3.370832 | +| clip_fraction | 0.464 | +| clip_range | 0.2 | +| entropy_loss | -0.303 | +| explained_variance | -2.13 | +| learning_rate | 0.0001 | +| loss | -0.0741 | +| n_updates | 116560 | +| policy_gradient_loss | -0.0696 | +| value_loss | 0.000477 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 309 | +| iterations | 5605 | +| time_elapsed | 18530 | +| total_timesteps | 5739520 | +| train/ | | +| approx_kl | 2.9464016 | +| clip_fraction | 0.458 | +| clip_range | 0.2 | +| entropy_loss | -0.335 | +| explained_variance | -3.63 | +| learning_rate | 0.0001 | +| loss | -0.0837 | +| n_updates | 116570 | +| policy_gradient_loss | -0.0636 | +| value_loss | 0.000424 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 309 | +| iterations | 5606 | +| time_elapsed | 18534 | +| total_timesteps | 5740544 | +| train/ | | +| approx_kl | 2.3323727 | +| clip_fraction | 0.464 | +| clip_range | 0.2 | +| entropy_loss | -0.32 | +| explained_variance | -1.17 | +| learning_rate | 0.0001 | +| loss | -0.0598 | +| n_updates | 116580 | +| policy_gradient_loss | -0.0706 | +| value_loss | 0.000467 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 309 | +| iterations | 5607 | +| time_elapsed | 18537 | +| total_timesteps | 5741568 | +| train/ | | +| approx_kl | 2.285857 | +| clip_fraction | 0.442 | +| clip_range | 0.2 | +| entropy_loss | -0.318 | +| explained_variance | -0.882 | +| learning_rate | 0.0001 | +| loss | -0.0588 | +| n_updates | 116590 | +| policy_gradient_loss | -0.0571 | +| value_loss | 0.000832 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 309 | +| iterations | 5608 | +| time_elapsed | 18541 | +| total_timesteps | 5742592 | +| train/ | | +| approx_kl | 2.4119606 | +| clip_fraction | 0.446 | +| clip_range | 0.2 | +| entropy_loss | -0.319 | +| explained_variance | -1.06 | +| learning_rate | 0.0001 | +| loss | -0.0738 | +| n_updates | 116600 | +| policy_gradient_loss | -0.0659 | +| value_loss | 0.000833 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 309 | +| iterations | 5609 | +| time_elapsed | 18544 | +| total_timesteps | 5743616 | +| train/ | | +| approx_kl | 3.0615916 | +| clip_fraction | 0.432 | +| clip_range | 0.2 | +| entropy_loss | -0.285 | +| explained_variance | -1.93 | +| learning_rate | 0.0001 | +| loss | -0.0451 | +| n_updates | 116610 | +| policy_gradient_loss | -0.0631 | +| value_loss | 0.000616 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 309 | +| iterations | 5610 | +| time_elapsed | 18547 | +| total_timesteps | 5744640 | +| train/ | | +| approx_kl | 5.075721 | +| clip_fraction | 0.476 | +| clip_range | 0.2 | +| entropy_loss | -0.324 | +| explained_variance | -3.64 | +| learning_rate | 0.0001 | +| loss | -0.0748 | +| n_updates | 116620 | +| policy_gradient_loss | -0.0703 | +| value_loss | 0.00041 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 309 | +| iterations | 5611 | +| time_elapsed | 18551 | +| total_timesteps | 5745664 | +| train/ | | +| approx_kl | 2.7903974 | +| clip_fraction | 0.463 | +| clip_range | 0.2 | +| entropy_loss | -0.326 | +| explained_variance | -1.76 | +| learning_rate | 0.0001 | +| loss | -0.0722 | +| n_updates | 116630 | +| policy_gradient_loss | -0.0665 | +| value_loss | 0.000494 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 309 | +| iterations | 5612 | +| time_elapsed | 18554 | +| total_timesteps | 5746688 | +| train/ | | +| approx_kl | 2.5065026 | +| clip_fraction | 0.491 | +| clip_range | 0.2 | +| entropy_loss | -0.349 | +| explained_variance | -0.891 | +| learning_rate | 0.0001 | +| loss | -0.109 | +| n_updates | 116640 | +| policy_gradient_loss | -0.0669 | +| value_loss | 0.000594 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 309 | +| iterations | 5613 | +| time_elapsed | 18557 | +| total_timesteps | 5747712 | +| train/ | | +| approx_kl | 2.166925 | +| clip_fraction | 0.456 | +| clip_range | 0.2 | +| entropy_loss | -0.318 | +| explained_variance | -1.83 | +| learning_rate | 0.0001 | +| loss | -0.0826 | +| n_updates | 116650 | +| policy_gradient_loss | -0.0671 | +| value_loss | 0.000628 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 309 | +| iterations | 5614 | +| time_elapsed | 18560 | +| total_timesteps | 5748736 | +| train/ | | +| approx_kl | 2.5319586 | +| clip_fraction | 0.469 | +| clip_range | 0.2 | +| entropy_loss | -0.327 | +| explained_variance | -7.7 | +| learning_rate | 0.0001 | +| loss | -0.106 | +| n_updates | 116660 | +| policy_gradient_loss | -0.0708 | +| value_loss | 0.000419 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 309 | +| iterations | 5615 | +| time_elapsed | 18563 | +| total_timesteps | 5749760 | +| train/ | | +| approx_kl | 2.4650803 | +| clip_fraction | 0.458 | +| clip_range | 0.2 | +| entropy_loss | -0.294 | +| explained_variance | -1.55 | +| learning_rate | 0.0001 | +| loss | -0.0692 | +| n_updates | 116670 | +| policy_gradient_loss | -0.0668 | +| value_loss | 0.000577 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 309 | +| iterations | 5616 | +| time_elapsed | 18566 | +| total_timesteps | 5750784 | +| train/ | | +| approx_kl | 2.4579854 | +| clip_fraction | 0.464 | +| clip_range | 0.2 | +| entropy_loss | -0.335 | +| explained_variance | -5.79 | +| learning_rate | 0.0001 | +| loss | -0.113 | +| n_updates | 116680 | +| policy_gradient_loss | -0.0723 | +| value_loss | 0.000615 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 309 | +| iterations | 5617 | +| time_elapsed | 18570 | +| total_timesteps | 5751808 | +| train/ | | +| approx_kl | 2.3905902 | +| clip_fraction | 0.466 | +| clip_range | 0.2 | +| entropy_loss | -0.333 | +| explained_variance | -1.08 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 116690 | +| policy_gradient_loss | -0.0674 | +| value_loss | 0.000513 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 309 | +| iterations | 5618 | +| time_elapsed | 18573 | +| total_timesteps | 5752832 | +| train/ | | +| approx_kl | 3.2808743 | +| clip_fraction | 0.465 | +| clip_range | 0.2 | +| entropy_loss | -0.315 | +| explained_variance | -2.32 | +| learning_rate | 0.0001 | +| loss | -0.0951 | +| n_updates | 116700 | +| policy_gradient_loss | -0.0701 | +| value_loss | 0.000688 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 309 | +| iterations | 5619 | +| time_elapsed | 18576 | +| total_timesteps | 5753856 | +| train/ | | +| approx_kl | 2.490829 | +| clip_fraction | 0.467 | +| clip_range | 0.2 | +| entropy_loss | -0.358 | +| explained_variance | -1.43 | +| learning_rate | 0.0001 | +| loss | -0.0779 | +| n_updates | 116710 | +| policy_gradient_loss | -0.0643 | +| value_loss | 0.000489 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 309 | +| iterations | 5620 | +| time_elapsed | 18579 | +| total_timesteps | 5754880 | +| train/ | | +| approx_kl | 2.3539248 | +| clip_fraction | 0.484 | +| clip_range | 0.2 | +| entropy_loss | -0.344 | +| explained_variance | -1.92 | +| learning_rate | 0.0001 | +| loss | -0.0752 | +| n_updates | 116720 | +| policy_gradient_loss | -0.0682 | +| value_loss | 0.000492 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 309 | +| iterations | 5621 | +| time_elapsed | 18583 | +| total_timesteps | 5755904 | +| train/ | | +| approx_kl | 2.6306996 | +| clip_fraction | 0.484 | +| clip_range | 0.2 | +| entropy_loss | -0.347 | +| explained_variance | -1.47 | +| learning_rate | 0.0001 | +| loss | -0.0828 | +| n_updates | 116730 | +| policy_gradient_loss | -0.0634 | +| value_loss | 0.000532 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 309 | +| iterations | 5622 | +| time_elapsed | 18586 | +| total_timesteps | 5756928 | +| train/ | | +| approx_kl | 2.1342964 | +| clip_fraction | 0.504 | +| clip_range | 0.2 | +| entropy_loss | -0.383 | +| explained_variance | -1.86 | +| learning_rate | 0.0001 | +| loss | -0.0849 | +| n_updates | 116740 | +| policy_gradient_loss | -0.0734 | +| value_loss | 0.000674 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 309 | +| iterations | 5623 | +| time_elapsed | 18590 | +| total_timesteps | 5757952 | +| train/ | | +| approx_kl | 2.3697712 | +| clip_fraction | 0.47 | +| clip_range | 0.2 | +| entropy_loss | -0.314 | +| explained_variance | -2.24 | +| learning_rate | 0.0001 | +| loss | -0.0813 | +| n_updates | 116750 | +| policy_gradient_loss | -0.0668 | +| value_loss | 0.000647 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 309 | +| iterations | 5624 | +| time_elapsed | 18593 | +| total_timesteps | 5758976 | +| train/ | | +| approx_kl | 2.4297624 | +| clip_fraction | 0.447 | +| clip_range | 0.2 | +| entropy_loss | -0.312 | +| explained_variance | -0.826 | +| learning_rate | 0.0001 | +| loss | -0.107 | +| n_updates | 116760 | +| policy_gradient_loss | -0.0639 | +| value_loss | 0.0007 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 309 | +| iterations | 5625 | +| time_elapsed | 18597 | +| total_timesteps | 5760000 | +| train/ | | +| approx_kl | 2.3033621 | +| clip_fraction | 0.445 | +| clip_range | 0.2 | +| entropy_loss | -0.307 | +| explained_variance | -0.882 | +| learning_rate | 0.0001 | +| loss | -0.0868 | +| n_updates | 116770 | +| policy_gradient_loss | -0.0678 | +| value_loss | 0.000651 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 309 | +| iterations | 5626 | +| time_elapsed | 18600 | +| total_timesteps | 5761024 | +| train/ | | +| approx_kl | 3.1111336 | +| clip_fraction | 0.482 | +| clip_range | 0.2 | +| entropy_loss | -0.342 | +| explained_variance | -1.54 | +| learning_rate | 0.0001 | +| loss | -0.0871 | +| n_updates | 116780 | +| policy_gradient_loss | -0.0718 | +| value_loss | 0.000686 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 309 | +| iterations | 5627 | +| time_elapsed | 18604 | +| total_timesteps | 5762048 | +| train/ | | +| approx_kl | 2.8690772 | +| clip_fraction | 0.442 | +| clip_range | 0.2 | +| entropy_loss | -0.305 | +| explained_variance | -2.46 | +| learning_rate | 0.0001 | +| loss | -0.0651 | +| n_updates | 116790 | +| policy_gradient_loss | -0.0667 | +| value_loss | 0.000582 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.388 | +| time/ | | +| fps | 309 | +| iterations | 5628 | +| time_elapsed | 18607 | +| total_timesteps | 5763072 | +| train/ | | +| approx_kl | 2.3738317 | +| clip_fraction | 0.444 | +| clip_range | 0.2 | +| entropy_loss | -0.31 | +| explained_variance | -2.11 | +| learning_rate | 0.0001 | +| loss | -0.0617 | +| n_updates | 116800 | +| policy_gradient_loss | -0.0667 | +| value_loss | 0.000483 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.392 | +| time/ | | +| fps | 309 | +| iterations | 5629 | +| time_elapsed | 18611 | +| total_timesteps | 5764096 | +| train/ | | +| approx_kl | 2.7525597 | +| clip_fraction | 0.461 | +| clip_range | 0.2 | +| entropy_loss | -0.306 | +| explained_variance | -1.88 | +| learning_rate | 0.0001 | +| loss | -0.0875 | +| n_updates | 116810 | +| policy_gradient_loss | -0.0661 | +| value_loss | 0.000495 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.392 | +| time/ | | +| fps | 309 | +| iterations | 5630 | +| time_elapsed | 18614 | +| total_timesteps | 5765120 | +| train/ | | +| approx_kl | 2.7063484 | +| clip_fraction | 0.465 | +| clip_range | 0.2 | +| entropy_loss | -0.312 | +| explained_variance | -0.985 | +| learning_rate | 0.0001 | +| loss | -0.0985 | +| n_updates | 116820 | +| policy_gradient_loss | -0.068 | +| value_loss | 0.000819 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.392 | +| time/ | | +| fps | 309 | +| iterations | 5631 | +| time_elapsed | 18617 | +| total_timesteps | 5766144 | +| train/ | | +| approx_kl | 2.6744962 | +| clip_fraction | 0.469 | +| clip_range | 0.2 | +| entropy_loss | -0.348 | +| explained_variance | -1.22 | +| learning_rate | 0.0001 | +| loss | -0.0887 | +| n_updates | 116830 | +| policy_gradient_loss | -0.0687 | +| value_loss | 0.000558 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.392 | +| time/ | | +| fps | 309 | +| iterations | 5632 | +| time_elapsed | 18620 | +| total_timesteps | 5767168 | +| train/ | | +| approx_kl | 2.616075 | +| clip_fraction | 0.447 | +| clip_range | 0.2 | +| entropy_loss | -0.329 | +| explained_variance | -1.38 | +| learning_rate | 0.0001 | +| loss | -0.0949 | +| n_updates | 116840 | +| policy_gradient_loss | -0.0659 | +| value_loss | 0.000635 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.394 | +| time/ | | +| fps | 309 | +| iterations | 5633 | +| time_elapsed | 18623 | +| total_timesteps | 5768192 | +| train/ | | +| approx_kl | 2.3074775 | +| clip_fraction | 0.484 | +| clip_range | 0.2 | +| entropy_loss | -0.348 | +| explained_variance | -1.77 | +| learning_rate | 0.0001 | +| loss | -0.0983 | +| n_updates | 116850 | +| policy_gradient_loss | -0.0689 | +| value_loss | 0.000519 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.397 | +| time/ | | +| fps | 309 | +| iterations | 5634 | +| time_elapsed | 18627 | +| total_timesteps | 5769216 | +| train/ | | +| approx_kl | 2.3910007 | +| clip_fraction | 0.469 | +| clip_range | 0.2 | +| entropy_loss | -0.322 | +| explained_variance | -1.28 | +| learning_rate | 0.0001 | +| loss | -0.0814 | +| n_updates | 116860 | +| policy_gradient_loss | -0.0659 | +| value_loss | 0.00042 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.397 | +| time/ | | +| fps | 309 | +| iterations | 5635 | +| time_elapsed | 18630 | +| total_timesteps | 5770240 | +| train/ | | +| approx_kl | 2.6241255 | +| clip_fraction | 0.451 | +| clip_range | 0.2 | +| entropy_loss | -0.338 | +| explained_variance | -1.3 | +| learning_rate | 0.0001 | +| loss | -0.0774 | +| n_updates | 116870 | +| policy_gradient_loss | -0.0644 | +| value_loss | 0.000506 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.397 | +| time/ | | +| fps | 309 | +| iterations | 5636 | +| time_elapsed | 18633 | +| total_timesteps | 5771264 | +| train/ | | +| approx_kl | 2.708161 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.348 | +| explained_variance | -3.32 | +| learning_rate | 0.0001 | +| loss | -0.0669 | +| n_updates | 116880 | +| policy_gradient_loss | -0.0714 | +| value_loss | 0.000395 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.401 | +| time/ | | +| fps | 309 | +| iterations | 5637 | +| time_elapsed | 18636 | +| total_timesteps | 5772288 | +| train/ | | +| approx_kl | 2.568772 | +| clip_fraction | 0.467 | +| clip_range | 0.2 | +| entropy_loss | -0.328 | +| explained_variance | -0.639 | +| learning_rate | 0.0001 | +| loss | -0.0808 | +| n_updates | 116890 | +| policy_gradient_loss | -0.0638 | +| value_loss | 0.000488 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.405 | +| time/ | | +| fps | 309 | +| iterations | 5638 | +| time_elapsed | 18640 | +| total_timesteps | 5773312 | +| train/ | | +| approx_kl | 2.4946787 | +| clip_fraction | 0.47 | +| clip_range | 0.2 | +| entropy_loss | -0.372 | +| explained_variance | -0.813 | +| learning_rate | 0.0001 | +| loss | -0.0855 | +| n_updates | 116900 | +| policy_gradient_loss | -0.0631 | +| value_loss | 0.000556 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.41 | +| time/ | | +| fps | 309 | +| iterations | 5639 | +| time_elapsed | 18643 | +| total_timesteps | 5774336 | +| train/ | | +| approx_kl | 2.5186887 | +| clip_fraction | 0.484 | +| clip_range | 0.2 | +| entropy_loss | -0.383 | +| explained_variance | -0.559 | +| learning_rate | 0.0001 | +| loss | -0.106 | +| n_updates | 116910 | +| policy_gradient_loss | -0.0602 | +| value_loss | 0.000971 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.41 | +| time/ | | +| fps | 309 | +| iterations | 5640 | +| time_elapsed | 18646 | +| total_timesteps | 5775360 | +| train/ | | +| approx_kl | 2.24162 | +| clip_fraction | 0.49 | +| clip_range | 0.2 | +| entropy_loss | -0.337 | +| explained_variance | -1.77 | +| learning_rate | 0.0001 | +| loss | -0.0836 | +| n_updates | 116920 | +| policy_gradient_loss | -0.0768 | +| value_loss | 0.000778 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.412 | +| time/ | | +| fps | 309 | +| iterations | 5641 | +| time_elapsed | 18650 | +| total_timesteps | 5776384 | +| train/ | | +| approx_kl | 2.877269 | +| clip_fraction | 0.496 | +| clip_range | 0.2 | +| entropy_loss | -0.338 | +| explained_variance | -5.33 | +| learning_rate | 0.0001 | +| loss | -0.115 | +| n_updates | 116930 | +| policy_gradient_loss | -0.0798 | +| value_loss | 0.000467 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.411 | +| time/ | | +| fps | 309 | +| iterations | 5642 | +| time_elapsed | 18653 | +| total_timesteps | 5777408 | +| train/ | | +| approx_kl | 2.3911161 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.347 | +| explained_variance | -0.819 | +| learning_rate | 0.0001 | +| loss | -0.0837 | +| n_updates | 116940 | +| policy_gradient_loss | -0.0711 | +| value_loss | 0.000709 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.411 | +| time/ | | +| fps | 309 | +| iterations | 5643 | +| time_elapsed | 18657 | +| total_timesteps | 5778432 | +| train/ | | +| approx_kl | 2.8917751 | +| clip_fraction | 0.456 | +| clip_range | 0.2 | +| entropy_loss | -0.343 | +| explained_variance | -1.18 | +| learning_rate | 0.0001 | +| loss | -0.0675 | +| n_updates | 116950 | +| policy_gradient_loss | -0.0585 | +| value_loss | 0.000725 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.406 | +| time/ | | +| fps | 309 | +| iterations | 5644 | +| time_elapsed | 18660 | +| total_timesteps | 5779456 | +| train/ | | +| approx_kl | 2.17786 | +| clip_fraction | 0.482 | +| clip_range | 0.2 | +| entropy_loss | -0.34 | +| explained_variance | -2.76 | +| learning_rate | 0.0001 | +| loss | -0.0935 | +| n_updates | 116960 | +| policy_gradient_loss | -0.0698 | +| value_loss | 0.000822 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.406 | +| time/ | | +| fps | 309 | +| iterations | 5645 | +| time_elapsed | 18664 | +| total_timesteps | 5780480 | +| train/ | | +| approx_kl | 2.959289 | +| clip_fraction | 0.46 | +| clip_range | 0.2 | +| entropy_loss | -0.302 | +| explained_variance | -4.8 | +| learning_rate | 0.0001 | +| loss | -0.0532 | +| n_updates | 116970 | +| policy_gradient_loss | -0.0708 | +| value_loss | 0.000467 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.404 | +| time/ | | +| fps | 309 | +| iterations | 5646 | +| time_elapsed | 18667 | +| total_timesteps | 5781504 | +| train/ | | +| approx_kl | 2.472855 | +| clip_fraction | 0.494 | +| clip_range | 0.2 | +| entropy_loss | -0.357 | +| explained_variance | -2.95 | +| learning_rate | 0.0001 | +| loss | -0.0939 | +| n_updates | 116980 | +| policy_gradient_loss | -0.0801 | +| value_loss | 0.000306 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.404 | +| time/ | | +| fps | 309 | +| iterations | 5647 | +| time_elapsed | 18670 | +| total_timesteps | 5782528 | +| train/ | | +| approx_kl | 2.7827573 | +| clip_fraction | 0.474 | +| clip_range | 0.2 | +| entropy_loss | -0.328 | +| explained_variance | -1.19 | +| learning_rate | 0.0001 | +| loss | -0.0739 | +| n_updates | 116990 | +| policy_gradient_loss | -0.0654 | +| value_loss | 0.000542 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.406 | +| time/ | | +| fps | 309 | +| iterations | 5648 | +| time_elapsed | 18674 | +| total_timesteps | 5783552 | +| train/ | | +| approx_kl | 3.9031105 | +| clip_fraction | 0.47 | +| clip_range | 0.2 | +| entropy_loss | -0.343 | +| explained_variance | -1.67 | +| learning_rate | 0.0001 | +| loss | -0.0886 | +| n_updates | 117000 | +| policy_gradient_loss | -0.0677 | +| value_loss | 0.000492 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.406 | +| time/ | | +| fps | 309 | +| iterations | 5649 | +| time_elapsed | 18677 | +| total_timesteps | 5784576 | +| train/ | | +| approx_kl | 2.6769073 | +| clip_fraction | 0.445 | +| clip_range | 0.2 | +| entropy_loss | -0.296 | +| explained_variance | -1.32 | +| learning_rate | 0.0001 | +| loss | -0.0806 | +| n_updates | 117010 | +| policy_gradient_loss | -0.064 | +| value_loss | 0.000429 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.405 | +| time/ | | +| fps | 309 | +| iterations | 5650 | +| time_elapsed | 18680 | +| total_timesteps | 5785600 | +| train/ | | +| approx_kl | 2.5507634 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.347 | +| explained_variance | -3.3 | +| learning_rate | 0.0001 | +| loss | -0.0742 | +| n_updates | 117020 | +| policy_gradient_loss | -0.0673 | +| value_loss | 0.000355 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.403 | +| time/ | | +| fps | 309 | +| iterations | 5651 | +| time_elapsed | 18683 | +| total_timesteps | 5786624 | +| train/ | | +| approx_kl | 2.371079 | +| clip_fraction | 0.45 | +| clip_range | 0.2 | +| entropy_loss | -0.306 | +| explained_variance | -1.62 | +| learning_rate | 0.0001 | +| loss | -0.0659 | +| n_updates | 117030 | +| policy_gradient_loss | -0.0556 | +| value_loss | 0.000552 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.403 | +| time/ | | +| fps | 309 | +| iterations | 5652 | +| time_elapsed | 18686 | +| total_timesteps | 5787648 | +| train/ | | +| approx_kl | 2.498787 | +| clip_fraction | 0.476 | +| clip_range | 0.2 | +| entropy_loss | -0.348 | +| explained_variance | -0.876 | +| learning_rate | 0.0001 | +| loss | -0.0533 | +| n_updates | 117040 | +| policy_gradient_loss | -0.0683 | +| value_loss | 0.000546 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.401 | +| time/ | | +| fps | 309 | +| iterations | 5653 | +| time_elapsed | 18689 | +| total_timesteps | 5788672 | +| train/ | | +| approx_kl | 2.4547899 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.361 | +| explained_variance | -3.72 | +| learning_rate | 0.0001 | +| loss | -0.0931 | +| n_updates | 117050 | +| policy_gradient_loss | -0.0678 | +| value_loss | 0.000537 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.401 | +| time/ | | +| fps | 309 | +| iterations | 5654 | +| time_elapsed | 18692 | +| total_timesteps | 5789696 | +| train/ | | +| approx_kl | 2.6878586 | +| clip_fraction | 0.473 | +| clip_range | 0.2 | +| entropy_loss | -0.354 | +| explained_variance | -1.33 | +| learning_rate | 0.0001 | +| loss | -0.0813 | +| n_updates | 117060 | +| policy_gradient_loss | -0.0673 | +| value_loss | 0.00047 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.402 | +| time/ | | +| fps | 309 | +| iterations | 5655 | +| time_elapsed | 18696 | +| total_timesteps | 5790720 | +| train/ | | +| approx_kl | 2.5383816 | +| clip_fraction | 0.495 | +| clip_range | 0.2 | +| entropy_loss | -0.355 | +| explained_variance | -0.829 | +| learning_rate | 0.0001 | +| loss | -0.0929 | +| n_updates | 117070 | +| policy_gradient_loss | -0.0707 | +| value_loss | 0.000492 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.404 | +| time/ | | +| fps | 309 | +| iterations | 5656 | +| time_elapsed | 18699 | +| total_timesteps | 5791744 | +| train/ | | +| approx_kl | 2.4214334 | +| clip_fraction | 0.458 | +| clip_range | 0.2 | +| entropy_loss | -0.339 | +| explained_variance | -0.808 | +| learning_rate | 0.0001 | +| loss | -0.068 | +| n_updates | 117080 | +| policy_gradient_loss | -0.0643 | +| value_loss | 0.000563 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.404 | +| time/ | | +| fps | 309 | +| iterations | 5657 | +| time_elapsed | 18702 | +| total_timesteps | 5792768 | +| train/ | | +| approx_kl | 2.475626 | +| clip_fraction | 0.488 | +| clip_range | 0.2 | +| entropy_loss | -0.333 | +| explained_variance | -1.04 | +| learning_rate | 0.0001 | +| loss | -0.0975 | +| n_updates | 117090 | +| policy_gradient_loss | -0.0773 | +| value_loss | 0.000558 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.404 | +| time/ | | +| fps | 309 | +| iterations | 5658 | +| time_elapsed | 18706 | +| total_timesteps | 5793792 | +| train/ | | +| approx_kl | 2.3704267 | +| clip_fraction | 0.503 | +| clip_range | 0.2 | +| entropy_loss | -0.369 | +| explained_variance | -2.58 | +| learning_rate | 0.0001 | +| loss | -0.116 | +| n_updates | 117100 | +| policy_gradient_loss | -0.0742 | +| value_loss | 0.000668 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.403 | +| time/ | | +| fps | 309 | +| iterations | 5659 | +| time_elapsed | 18709 | +| total_timesteps | 5794816 | +| train/ | | +| approx_kl | 2.248279 | +| clip_fraction | 0.447 | +| clip_range | 0.2 | +| entropy_loss | -0.308 | +| explained_variance | -1.62 | +| learning_rate | 0.0001 | +| loss | -0.0777 | +| n_updates | 117110 | +| policy_gradient_loss | -0.0657 | +| value_loss | 0.000458 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.403 | +| time/ | | +| fps | 309 | +| iterations | 5660 | +| time_elapsed | 18713 | +| total_timesteps | 5795840 | +| train/ | | +| approx_kl | 2.3896053 | +| clip_fraction | 0.452 | +| clip_range | 0.2 | +| entropy_loss | -0.323 | +| explained_variance | -1.37 | +| learning_rate | 0.0001 | +| loss | -0.114 | +| n_updates | 117120 | +| policy_gradient_loss | -0.0721 | +| value_loss | 0.000495 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.403 | +| time/ | | +| fps | 309 | +| iterations | 5661 | +| time_elapsed | 18716 | +| total_timesteps | 5796864 | +| train/ | | +| approx_kl | 2.0956354 | +| clip_fraction | 0.478 | +| clip_range | 0.2 | +| entropy_loss | -0.352 | +| explained_variance | -3.09 | +| learning_rate | 0.0001 | +| loss | -0.0893 | +| n_updates | 117130 | +| policy_gradient_loss | -0.0683 | +| value_loss | 0.000366 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.401 | +| time/ | | +| fps | 309 | +| iterations | 5662 | +| time_elapsed | 18720 | +| total_timesteps | 5797888 | +| train/ | | +| approx_kl | 2.5639346 | +| clip_fraction | 0.484 | +| clip_range | 0.2 | +| entropy_loss | -0.386 | +| explained_variance | -0.933 | +| learning_rate | 0.0001 | +| loss | -0.0855 | +| n_updates | 117140 | +| policy_gradient_loss | -0.066 | +| value_loss | 0.000391 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.401 | +| time/ | | +| fps | 309 | +| iterations | 5663 | +| time_elapsed | 18723 | +| total_timesteps | 5798912 | +| train/ | | +| approx_kl | 1.865954 | +| clip_fraction | 0.439 | +| clip_range | 0.2 | +| entropy_loss | -0.332 | +| explained_variance | -2.92 | +| learning_rate | 0.0001 | +| loss | -0.108 | +| n_updates | 117150 | +| policy_gradient_loss | -0.0647 | +| value_loss | 0.000441 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.404 | +| time/ | | +| fps | 309 | +| iterations | 5664 | +| time_elapsed | 18727 | +| total_timesteps | 5799936 | +| train/ | | +| approx_kl | 2.7010913 | +| clip_fraction | 0.506 | +| clip_range | 0.2 | +| entropy_loss | -0.367 | +| explained_variance | -2.23 | +| learning_rate | 0.0001 | +| loss | -0.114 | +| n_updates | 117160 | +| policy_gradient_loss | -0.0763 | +| value_loss | 0.000416 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.407 | +| time/ | | +| fps | 309 | +| iterations | 5665 | +| time_elapsed | 18730 | +| total_timesteps | 5800960 | +| train/ | | +| approx_kl | 2.7923687 | +| clip_fraction | 0.486 | +| clip_range | 0.2 | +| entropy_loss | -0.397 | +| explained_variance | -1.78 | +| learning_rate | 0.0001 | +| loss | -0.0995 | +| n_updates | 117170 | +| policy_gradient_loss | -0.066 | +| value_loss | 0.000606 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.407 | +| time/ | | +| fps | 309 | +| iterations | 5666 | +| time_elapsed | 18733 | +| total_timesteps | 5801984 | +| train/ | | +| approx_kl | 2.436875 | +| clip_fraction | 0.489 | +| clip_range | 0.2 | +| entropy_loss | -0.358 | +| explained_variance | -0.543 | +| learning_rate | 0.0001 | +| loss | -0.0822 | +| n_updates | 117180 | +| policy_gradient_loss | -0.0581 | +| value_loss | 0.00081 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.407 | +| time/ | | +| fps | 309 | +| iterations | 5667 | +| time_elapsed | 18737 | +| total_timesteps | 5803008 | +| train/ | | +| approx_kl | 2.3565235 | +| clip_fraction | 0.442 | +| clip_range | 0.2 | +| entropy_loss | -0.323 | +| explained_variance | -3.8 | +| learning_rate | 0.0001 | +| loss | -0.0822 | +| n_updates | 117190 | +| policy_gradient_loss | -0.071 | +| value_loss | 0.000724 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.404 | +| time/ | | +| fps | 309 | +| iterations | 5668 | +| time_elapsed | 18740 | +| total_timesteps | 5804032 | +| train/ | | +| approx_kl | 2.2594354 | +| clip_fraction | 0.493 | +| clip_range | 0.2 | +| entropy_loss | -0.373 | +| explained_variance | -2.08 | +| learning_rate | 0.0001 | +| loss | -0.0968 | +| n_updates | 117200 | +| policy_gradient_loss | -0.0711 | +| value_loss | 0.000349 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.404 | +| time/ | | +| fps | 309 | +| iterations | 5669 | +| time_elapsed | 18743 | +| total_timesteps | 5805056 | +| train/ | | +| approx_kl | 2.5012834 | +| clip_fraction | 0.469 | +| clip_range | 0.2 | +| entropy_loss | -0.377 | +| explained_variance | -4.53 | +| learning_rate | 0.0001 | +| loss | -0.094 | +| n_updates | 117210 | +| policy_gradient_loss | -0.0705 | +| value_loss | 0.000349 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.404 | +| time/ | | +| fps | 309 | +| iterations | 5670 | +| time_elapsed | 18746 | +| total_timesteps | 5806080 | +| train/ | | +| approx_kl | 2.7747064 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.394 | +| explained_variance | -0.303 | +| learning_rate | 0.0001 | +| loss | -0.0979 | +| n_updates | 117220 | +| policy_gradient_loss | -0.0654 | +| value_loss | 0.000415 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.405 | +| time/ | | +| fps | 309 | +| iterations | 5671 | +| time_elapsed | 18750 | +| total_timesteps | 5807104 | +| train/ | | +| approx_kl | 3.4803972 | +| clip_fraction | 0.479 | +| clip_range | 0.2 | +| entropy_loss | -0.349 | +| explained_variance | -1.08 | +| learning_rate | 0.0001 | +| loss | -0.084 | +| n_updates | 117230 | +| policy_gradient_loss | -0.0718 | +| value_loss | 0.000672 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.405 | +| time/ | | +| fps | 309 | +| iterations | 5672 | +| time_elapsed | 18753 | +| total_timesteps | 5808128 | +| train/ | | +| approx_kl | 2.0279388 | +| clip_fraction | 0.444 | +| clip_range | 0.2 | +| entropy_loss | -0.338 | +| explained_variance | -1.35 | +| learning_rate | 0.0001 | +| loss | -0.0848 | +| n_updates | 117240 | +| policy_gradient_loss | -0.0716 | +| value_loss | 0.000596 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.402 | +| time/ | | +| fps | 309 | +| iterations | 5673 | +| time_elapsed | 18756 | +| total_timesteps | 5809152 | +| train/ | | +| approx_kl | 2.5351882 | +| clip_fraction | 0.472 | +| clip_range | 0.2 | +| entropy_loss | -0.356 | +| explained_variance | -1.67 | +| learning_rate | 0.0001 | +| loss | -0.052 | +| n_updates | 117250 | +| policy_gradient_loss | -0.0692 | +| value_loss | 0.000608 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.403 | +| time/ | | +| fps | 309 | +| iterations | 5674 | +| time_elapsed | 18759 | +| total_timesteps | 5810176 | +| train/ | | +| approx_kl | 1.9479189 | +| clip_fraction | 0.428 | +| clip_range | 0.2 | +| entropy_loss | -0.343 | +| explained_variance | -1.03 | +| learning_rate | 0.0001 | +| loss | -0.0775 | +| n_updates | 117260 | +| policy_gradient_loss | -0.0613 | +| value_loss | 0.000467 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.403 | +| time/ | | +| fps | 309 | +| iterations | 5675 | +| time_elapsed | 18763 | +| total_timesteps | 5811200 | +| train/ | | +| approx_kl | 2.423761 | +| clip_fraction | 0.458 | +| clip_range | 0.2 | +| entropy_loss | -0.341 | +| explained_variance | -1.29 | +| learning_rate | 0.0001 | +| loss | -0.1 | +| n_updates | 117270 | +| policy_gradient_loss | -0.0699 | +| value_loss | 0.000552 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.405 | +| time/ | | +| fps | 309 | +| iterations | 5676 | +| time_elapsed | 18766 | +| total_timesteps | 5812224 | +| train/ | | +| approx_kl | 2.9507473 | +| clip_fraction | 0.453 | +| clip_range | 0.2 | +| entropy_loss | -0.311 | +| explained_variance | -1.08 | +| learning_rate | 0.0001 | +| loss | -0.0849 | +| n_updates | 117280 | +| policy_gradient_loss | -0.0658 | +| value_loss | 0.000537 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.407 | +| time/ | | +| fps | 309 | +| iterations | 5677 | +| time_elapsed | 18769 | +| total_timesteps | 5813248 | +| train/ | | +| approx_kl | 2.1158438 | +| clip_fraction | 0.445 | +| clip_range | 0.2 | +| entropy_loss | -0.307 | +| explained_variance | -1.58 | +| learning_rate | 0.0001 | +| loss | -0.091 | +| n_updates | 117290 | +| policy_gradient_loss | -0.0655 | +| value_loss | 0.000525 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.406 | +| time/ | | +| fps | 309 | +| iterations | 5678 | +| time_elapsed | 18773 | +| total_timesteps | 5814272 | +| train/ | | +| approx_kl | 4.7699647 | +| clip_fraction | 0.456 | +| clip_range | 0.2 | +| entropy_loss | -0.323 | +| explained_variance | -1.21 | +| learning_rate | 0.0001 | +| loss | -0.0932 | +| n_updates | 117300 | +| policy_gradient_loss | -0.0647 | +| value_loss | 0.000541 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.406 | +| time/ | | +| fps | 309 | +| iterations | 5679 | +| time_elapsed | 18776 | +| total_timesteps | 5815296 | +| train/ | | +| approx_kl | 2.6482024 | +| clip_fraction | 0.464 | +| clip_range | 0.2 | +| entropy_loss | -0.362 | +| explained_variance | -1.1 | +| learning_rate | 0.0001 | +| loss | -0.0825 | +| n_updates | 117310 | +| policy_gradient_loss | -0.0496 | +| value_loss | 0.000669 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.411 | +| time/ | | +| fps | 309 | +| iterations | 5680 | +| time_elapsed | 18780 | +| total_timesteps | 5816320 | +| train/ | | +| approx_kl | 2.5580637 | +| clip_fraction | 0.497 | +| clip_range | 0.2 | +| entropy_loss | -0.396 | +| explained_variance | -1.2 | +| learning_rate | 0.0001 | +| loss | -0.0904 | +| n_updates | 117320 | +| policy_gradient_loss | -0.0718 | +| value_loss | 0.000625 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.411 | +| time/ | | +| fps | 309 | +| iterations | 5681 | +| time_elapsed | 18783 | +| total_timesteps | 5817344 | +| train/ | | +| approx_kl | 1.8721688 | +| clip_fraction | 0.476 | +| clip_range | 0.2 | +| entropy_loss | -0.369 | +| explained_variance | -1.58 | +| learning_rate | 0.0001 | +| loss | -0.0748 | +| n_updates | 117330 | +| policy_gradient_loss | -0.066 | +| value_loss | 0.000586 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.412 | +| time/ | | +| fps | 309 | +| iterations | 5682 | +| time_elapsed | 18787 | +| total_timesteps | 5818368 | +| train/ | | +| approx_kl | 3.1689355 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.374 | +| explained_variance | -1.56 | +| learning_rate | 0.0001 | +| loss | -0.118 | +| n_updates | 117340 | +| policy_gradient_loss | -0.0688 | +| value_loss | 0.000496 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.412 | +| time/ | | +| fps | 309 | +| iterations | 5683 | +| time_elapsed | 18790 | +| total_timesteps | 5819392 | +| train/ | | +| approx_kl | 2.2369077 | +| clip_fraction | 0.45 | +| clip_range | 0.2 | +| entropy_loss | -0.319 | +| explained_variance | -0.615 | +| learning_rate | 0.0001 | +| loss | -0.107 | +| n_updates | 117350 | +| policy_gradient_loss | -0.0683 | +| value_loss | 0.000512 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.411 | +| time/ | | +| fps | 309 | +| iterations | 5684 | +| time_elapsed | 18793 | +| total_timesteps | 5820416 | +| train/ | | +| approx_kl | 2.4203613 | +| clip_fraction | 0.468 | +| clip_range | 0.2 | +| entropy_loss | -0.349 | +| explained_variance | -2.04 | +| learning_rate | 0.0001 | +| loss | -0.0938 | +| n_updates | 117360 | +| policy_gradient_loss | -0.0708 | +| value_loss | 0.000355 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.412 | +| time/ | | +| fps | 309 | +| iterations | 5685 | +| time_elapsed | 18796 | +| total_timesteps | 5821440 | +| train/ | | +| approx_kl | 2.1182458 | +| clip_fraction | 0.468 | +| clip_range | 0.2 | +| entropy_loss | -0.349 | +| explained_variance | -0.998 | +| learning_rate | 0.0001 | +| loss | -0.0888 | +| n_updates | 117370 | +| policy_gradient_loss | -0.068 | +| value_loss | 0.000593 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.412 | +| time/ | | +| fps | 309 | +| iterations | 5686 | +| time_elapsed | 18800 | +| total_timesteps | 5822464 | +| train/ | | +| approx_kl | 2.1730556 | +| clip_fraction | 0.473 | +| clip_range | 0.2 | +| entropy_loss | -0.361 | +| explained_variance | -0.568 | +| learning_rate | 0.0001 | +| loss | -0.0908 | +| n_updates | 117380 | +| policy_gradient_loss | -0.0645 | +| value_loss | 0.000677 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.412 | +| time/ | | +| fps | 309 | +| iterations | 5687 | +| time_elapsed | 18803 | +| total_timesteps | 5823488 | +| train/ | | +| approx_kl | 3.0649843 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.34 | +| explained_variance | -0.933 | +| learning_rate | 0.0001 | +| loss | -0.0858 | +| n_updates | 117390 | +| policy_gradient_loss | -0.0674 | +| value_loss | 0.000875 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.409 | +| time/ | | +| fps | 309 | +| iterations | 5688 | +| time_elapsed | 18806 | +| total_timesteps | 5824512 | +| train/ | | +| approx_kl | 6.6564617 | +| clip_fraction | 0.489 | +| clip_range | 0.2 | +| entropy_loss | -0.352 | +| explained_variance | -4.6 | +| learning_rate | 0.0001 | +| loss | -0.126 | +| n_updates | 117400 | +| policy_gradient_loss | -0.0787 | +| value_loss | 0.000597 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.413 | +| time/ | | +| fps | 309 | +| iterations | 5689 | +| time_elapsed | 18809 | +| total_timesteps | 5825536 | +| train/ | | +| approx_kl | 2.4808326 | +| clip_fraction | 0.461 | +| clip_range | 0.2 | +| entropy_loss | -0.327 | +| explained_variance | -2.96 | +| learning_rate | 0.0001 | +| loss | -0.107 | +| n_updates | 117410 | +| policy_gradient_loss | -0.0683 | +| value_loss | 0.000473 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.413 | +| time/ | | +| fps | 309 | +| iterations | 5690 | +| time_elapsed | 18812 | +| total_timesteps | 5826560 | +| train/ | | +| approx_kl | 2.5299304 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.361 | +| explained_variance | -0.457 | +| learning_rate | 0.0001 | +| loss | -0.0758 | +| n_updates | 117420 | +| policy_gradient_loss | -0.069 | +| value_loss | 0.000841 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.415 | +| time/ | | +| fps | 309 | +| iterations | 5691 | +| time_elapsed | 18816 | +| total_timesteps | 5827584 | +| train/ | | +| approx_kl | 2.2882233 | +| clip_fraction | 0.49 | +| clip_range | 0.2 | +| entropy_loss | -0.345 | +| explained_variance | -2.99 | +| learning_rate | 0.0001 | +| loss | -0.0766 | +| n_updates | 117430 | +| policy_gradient_loss | -0.0748 | +| value_loss | 0.000577 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.415 | +| time/ | | +| fps | 309 | +| iterations | 5692 | +| time_elapsed | 18819 | +| total_timesteps | 5828608 | +| train/ | | +| approx_kl | 2.3628106 | +| clip_fraction | 0.465 | +| clip_range | 0.2 | +| entropy_loss | -0.366 | +| explained_variance | -2.1 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 117440 | +| policy_gradient_loss | -0.0696 | +| value_loss | 0.000393 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.418 | +| time/ | | +| fps | 309 | +| iterations | 5693 | +| time_elapsed | 18822 | +| total_timesteps | 5829632 | +| train/ | | +| approx_kl | 1.8540603 | +| clip_fraction | 0.488 | +| clip_range | 0.2 | +| entropy_loss | -0.395 | +| explained_variance | -1.35 | +| learning_rate | 0.0001 | +| loss | -0.0842 | +| n_updates | 117450 | +| policy_gradient_loss | -0.0683 | +| value_loss | 0.000478 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.418 | +| time/ | | +| fps | 309 | +| iterations | 5694 | +| time_elapsed | 18826 | +| total_timesteps | 5830656 | +| train/ | | +| approx_kl | 2.5667844 | +| clip_fraction | 0.479 | +| clip_range | 0.2 | +| entropy_loss | -0.36 | +| explained_variance | -1.09 | +| learning_rate | 0.0001 | +| loss | -0.108 | +| n_updates | 117460 | +| policy_gradient_loss | -0.0654 | +| value_loss | 0.000612 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.417 | +| time/ | | +| fps | 309 | +| iterations | 5695 | +| time_elapsed | 18829 | +| total_timesteps | 5831680 | +| train/ | | +| approx_kl | 2.957058 | +| clip_fraction | 0.488 | +| clip_range | 0.2 | +| entropy_loss | -0.355 | +| explained_variance | -2.17 | +| learning_rate | 0.0001 | +| loss | -0.109 | +| n_updates | 117470 | +| policy_gradient_loss | -0.0686 | +| value_loss | 0.000516 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.42 | +| time/ | | +| fps | 309 | +| iterations | 5696 | +| time_elapsed | 18833 | +| total_timesteps | 5832704 | +| train/ | | +| approx_kl | 2.1621838 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.355 | +| explained_variance | -1.18 | +| learning_rate | 0.0001 | +| loss | -0.0832 | +| n_updates | 117480 | +| policy_gradient_loss | -0.066 | +| value_loss | 0.000537 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.42 | +| time/ | | +| fps | 309 | +| iterations | 5697 | +| time_elapsed | 18837 | +| total_timesteps | 5833728 | +| train/ | | +| approx_kl | 2.3760953 | +| clip_fraction | 0.464 | +| clip_range | 0.2 | +| entropy_loss | -0.34 | +| explained_variance | -1.26 | +| learning_rate | 0.0001 | +| loss | -0.0751 | +| n_updates | 117490 | +| policy_gradient_loss | -0.0657 | +| value_loss | 0.000599 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.421 | +| time/ | | +| fps | 309 | +| iterations | 5698 | +| time_elapsed | 18840 | +| total_timesteps | 5834752 | +| train/ | | +| approx_kl | 3.2333586 | +| clip_fraction | 0.52 | +| clip_range | 0.2 | +| entropy_loss | -0.401 | +| explained_variance | -2 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 117500 | +| policy_gradient_loss | -0.0717 | +| value_loss | 0.000623 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.426 | +| time/ | | +| fps | 309 | +| iterations | 5699 | +| time_elapsed | 18843 | +| total_timesteps | 5835776 | +| train/ | | +| approx_kl | 2.294702 | +| clip_fraction | 0.477 | +| clip_range | 0.2 | +| entropy_loss | -0.409 | +| explained_variance | -0.748 | +| learning_rate | 0.0001 | +| loss | -0.0947 | +| n_updates | 117510 | +| policy_gradient_loss | -0.0628 | +| value_loss | 0.000523 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.426 | +| time/ | | +| fps | 309 | +| iterations | 5700 | +| time_elapsed | 18847 | +| total_timesteps | 5836800 | +| train/ | | +| approx_kl | 3.418093 | +| clip_fraction | 0.466 | +| clip_range | 0.2 | +| entropy_loss | -0.358 | +| explained_variance | -0.471 | +| learning_rate | 0.0001 | +| loss | -0.0728 | +| n_updates | 117520 | +| policy_gradient_loss | -0.0674 | +| value_loss | 0.000677 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.43 | +| time/ | | +| fps | 309 | +| iterations | 5701 | +| time_elapsed | 18850 | +| total_timesteps | 5837824 | +| train/ | | +| approx_kl | 3.239695 | +| clip_fraction | 0.502 | +| clip_range | 0.2 | +| entropy_loss | -0.4 | +| explained_variance | -3.35 | +| learning_rate | 0.0001 | +| loss | -0.0985 | +| n_updates | 117530 | +| policy_gradient_loss | -0.0773 | +| value_loss | 0.00044 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.431 | +| time/ | | +| fps | 309 | +| iterations | 5702 | +| time_elapsed | 18854 | +| total_timesteps | 5838848 | +| train/ | | +| approx_kl | 2.2366698 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.378 | +| explained_variance | -0.655 | +| learning_rate | 0.0001 | +| loss | -0.0916 | +| n_updates | 117540 | +| policy_gradient_loss | -0.0682 | +| value_loss | 0.00052 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.426 | +| time/ | | +| fps | 309 | +| iterations | 5703 | +| time_elapsed | 18857 | +| total_timesteps | 5839872 | +| train/ | | +| approx_kl | 1.9520769 | +| clip_fraction | 0.454 | +| clip_range | 0.2 | +| entropy_loss | -0.341 | +| explained_variance | -0.467 | +| learning_rate | 0.0001 | +| loss | -0.109 | +| n_updates | 117550 | +| policy_gradient_loss | -0.068 | +| value_loss | 0.000776 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.426 | +| time/ | | +| fps | 309 | +| iterations | 5704 | +| time_elapsed | 18860 | +| total_timesteps | 5840896 | +| train/ | | +| approx_kl | 2.210639 | +| clip_fraction | 0.473 | +| clip_range | 0.2 | +| entropy_loss | -0.35 | +| explained_variance | -3.86 | +| learning_rate | 0.0001 | +| loss | -0.118 | +| n_updates | 117560 | +| policy_gradient_loss | -0.0744 | +| value_loss | 0.000461 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.426 | +| time/ | | +| fps | 309 | +| iterations | 5705 | +| time_elapsed | 18863 | +| total_timesteps | 5841920 | +| train/ | | +| approx_kl | 2.3021595 | +| clip_fraction | 0.489 | +| clip_range | 0.2 | +| entropy_loss | -0.409 | +| explained_variance | -2.76 | +| learning_rate | 0.0001 | +| loss | -0.077 | +| n_updates | 117570 | +| policy_gradient_loss | -0.0699 | +| value_loss | 0.000433 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.428 | +| time/ | | +| fps | 309 | +| iterations | 5706 | +| time_elapsed | 18866 | +| total_timesteps | 5842944 | +| train/ | | +| approx_kl | 4.7642922 | +| clip_fraction | 0.489 | +| clip_range | 0.2 | +| entropy_loss | -0.372 | +| explained_variance | -0.969 | +| learning_rate | 0.0001 | +| loss | -0.086 | +| n_updates | 117580 | +| policy_gradient_loss | -0.0718 | +| value_loss | 0.000504 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.428 | +| time/ | | +| fps | 309 | +| iterations | 5707 | +| time_elapsed | 18870 | +| total_timesteps | 5843968 | +| train/ | | +| approx_kl | 1.9925969 | +| clip_fraction | 0.427 | +| clip_range | 0.2 | +| entropy_loss | -0.321 | +| explained_variance | -0.253 | +| learning_rate | 0.0001 | +| loss | -0.089 | +| n_updates | 117590 | +| policy_gradient_loss | -0.055 | +| value_loss | 0.000969 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.428 | +| time/ | | +| fps | 309 | +| iterations | 5708 | +| time_elapsed | 18873 | +| total_timesteps | 5844992 | +| train/ | | +| approx_kl | 3.9477549 | +| clip_fraction | 0.485 | +| clip_range | 0.2 | +| entropy_loss | -0.367 | +| explained_variance | -4.26 | +| learning_rate | 0.0001 | +| loss | -0.0972 | +| n_updates | 117600 | +| policy_gradient_loss | -0.0761 | +| value_loss | 0.000561 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.428 | +| time/ | | +| fps | 309 | +| iterations | 5709 | +| time_elapsed | 18876 | +| total_timesteps | 5846016 | +| train/ | | +| approx_kl | 3.584697 | +| clip_fraction | 0.455 | +| clip_range | 0.2 | +| entropy_loss | -0.317 | +| explained_variance | -1.44 | +| learning_rate | 0.0001 | +| loss | -0.0663 | +| n_updates | 117610 | +| policy_gradient_loss | -0.0614 | +| value_loss | 0.000475 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.427 | +| time/ | | +| fps | 309 | +| iterations | 5710 | +| time_elapsed | 18879 | +| total_timesteps | 5847040 | +| train/ | | +| approx_kl | 2.0252912 | +| clip_fraction | 0.488 | +| clip_range | 0.2 | +| entropy_loss | -0.385 | +| explained_variance | -1.1 | +| learning_rate | 0.0001 | +| loss | -0.085 | +| n_updates | 117620 | +| policy_gradient_loss | -0.0696 | +| value_loss | 0.000582 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.424 | +| time/ | | +| fps | 309 | +| iterations | 5711 | +| time_elapsed | 18883 | +| total_timesteps | 5848064 | +| train/ | | +| approx_kl | 2.1024888 | +| clip_fraction | 0.458 | +| clip_range | 0.2 | +| entropy_loss | -0.35 | +| explained_variance | -1.37 | +| learning_rate | 0.0001 | +| loss | -0.0715 | +| n_updates | 117630 | +| policy_gradient_loss | -0.0618 | +| value_loss | 0.000584 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.424 | +| time/ | | +| fps | 309 | +| iterations | 5712 | +| time_elapsed | 18886 | +| total_timesteps | 5849088 | +| train/ | | +| approx_kl | 2.6467156 | +| clip_fraction | 0.444 | +| clip_range | 0.2 | +| entropy_loss | -0.328 | +| explained_variance | -1.31 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 117640 | +| policy_gradient_loss | -0.0685 | +| value_loss | 0.000512 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.424 | +| time/ | | +| fps | 309 | +| iterations | 5713 | +| time_elapsed | 18889 | +| total_timesteps | 5850112 | +| train/ | | +| approx_kl | 2.0957723 | +| clip_fraction | 0.46 | +| clip_range | 0.2 | +| entropy_loss | -0.346 | +| explained_variance | -2.54 | +| learning_rate | 0.0001 | +| loss | -0.116 | +| n_updates | 117650 | +| policy_gradient_loss | -0.0742 | +| value_loss | 0.000536 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.424 | +| time/ | | +| fps | 309 | +| iterations | 5714 | +| time_elapsed | 18893 | +| total_timesteps | 5851136 | +| train/ | | +| approx_kl | 2.3913329 | +| clip_fraction | 0.435 | +| clip_range | 0.2 | +| entropy_loss | -0.31 | +| explained_variance | -1.94 | +| learning_rate | 0.0001 | +| loss | -0.0708 | +| n_updates | 117660 | +| policy_gradient_loss | -0.0655 | +| value_loss | 0.000492 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.424 | +| time/ | | +| fps | 309 | +| iterations | 5715 | +| time_elapsed | 18896 | +| total_timesteps | 5852160 | +| train/ | | +| approx_kl | 2.8963604 | +| clip_fraction | 0.468 | +| clip_range | 0.2 | +| entropy_loss | -0.34 | +| explained_variance | -5.34 | +| learning_rate | 0.0001 | +| loss | -0.0889 | +| n_updates | 117670 | +| policy_gradient_loss | -0.0745 | +| value_loss | 0.000298 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.423 | +| time/ | | +| fps | 309 | +| iterations | 5716 | +| time_elapsed | 18899 | +| total_timesteps | 5853184 | +| train/ | | +| approx_kl | 2.1593356 | +| clip_fraction | 0.497 | +| clip_range | 0.2 | +| entropy_loss | -0.349 | +| explained_variance | -1.16 | +| learning_rate | 0.0001 | +| loss | -0.0902 | +| n_updates | 117680 | +| policy_gradient_loss | -0.0563 | +| value_loss | 0.00027 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.424 | +| time/ | | +| fps | 309 | +| iterations | 5717 | +| time_elapsed | 18902 | +| total_timesteps | 5854208 | +| train/ | | +| approx_kl | 2.478693 | +| clip_fraction | 0.436 | +| clip_range | 0.2 | +| entropy_loss | -0.332 | +| explained_variance | -0.766 | +| learning_rate | 0.0001 | +| loss | -0.072 | +| n_updates | 117690 | +| policy_gradient_loss | -0.0666 | +| value_loss | 0.000524 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.424 | +| time/ | | +| fps | 309 | +| iterations | 5718 | +| time_elapsed | 18906 | +| total_timesteps | 5855232 | +| train/ | | +| approx_kl | 1.8768959 | +| clip_fraction | 0.453 | +| clip_range | 0.2 | +| entropy_loss | -0.367 | +| explained_variance | -0.322 | +| learning_rate | 0.0001 | +| loss | -0.0785 | +| n_updates | 117700 | +| policy_gradient_loss | -0.0622 | +| value_loss | 0.000622 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.424 | +| time/ | | +| fps | 309 | +| iterations | 5719 | +| time_elapsed | 18909 | +| total_timesteps | 5856256 | +| train/ | | +| approx_kl | 2.198295 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.396 | +| explained_variance | -3.06 | +| learning_rate | 0.0001 | +| loss | -0.0929 | +| n_updates | 117710 | +| policy_gradient_loss | -0.0707 | +| value_loss | 0.000415 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.424 | +| time/ | | +| fps | 309 | +| iterations | 5720 | +| time_elapsed | 18913 | +| total_timesteps | 5857280 | +| train/ | | +| approx_kl | 1.90805 | +| clip_fraction | 0.449 | +| clip_range | 0.2 | +| entropy_loss | -0.321 | +| explained_variance | -1.06 | +| learning_rate | 0.0001 | +| loss | -0.0726 | +| n_updates | 117720 | +| policy_gradient_loss | -0.067 | +| value_loss | 0.000464 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.424 | +| time/ | | +| fps | 309 | +| iterations | 5721 | +| time_elapsed | 18916 | +| total_timesteps | 5858304 | +| train/ | | +| approx_kl | 2.124864 | +| clip_fraction | 0.463 | +| clip_range | 0.2 | +| entropy_loss | -0.33 | +| explained_variance | -0.576 | +| learning_rate | 0.0001 | +| loss | -0.0819 | +| n_updates | 117730 | +| policy_gradient_loss | -0.0704 | +| value_loss | 0.000575 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.422 | +| time/ | | +| fps | 309 | +| iterations | 5722 | +| time_elapsed | 18919 | +| total_timesteps | 5859328 | +| train/ | | +| approx_kl | 1.8994079 | +| clip_fraction | 0.467 | +| clip_range | 0.2 | +| entropy_loss | -0.347 | +| explained_variance | -3.45 | +| learning_rate | 0.0001 | +| loss | -0.109 | +| n_updates | 117740 | +| policy_gradient_loss | -0.0689 | +| value_loss | 0.000475 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.422 | +| time/ | | +| fps | 309 | +| iterations | 5723 | +| time_elapsed | 18922 | +| total_timesteps | 5860352 | +| train/ | | +| approx_kl | 2.2276864 | +| clip_fraction | 0.467 | +| clip_range | 0.2 | +| entropy_loss | -0.367 | +| explained_variance | -0.988 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 117750 | +| policy_gradient_loss | -0.0686 | +| value_loss | 0.000512 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.425 | +| time/ | | +| fps | 309 | +| iterations | 5724 | +| time_elapsed | 18925 | +| total_timesteps | 5861376 | +| train/ | | +| approx_kl | 2.6249652 | +| clip_fraction | 0.485 | +| clip_range | 0.2 | +| entropy_loss | -0.362 | +| explained_variance | -2.38 | +| learning_rate | 0.0001 | +| loss | -0.0968 | +| n_updates | 117760 | +| policy_gradient_loss | -0.0768 | +| value_loss | 0.000573 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.425 | +| time/ | | +| fps | 309 | +| iterations | 5725 | +| time_elapsed | 18929 | +| total_timesteps | 5862400 | +| train/ | | +| approx_kl | 2.1338851 | +| clip_fraction | 0.466 | +| clip_range | 0.2 | +| entropy_loss | -0.349 | +| explained_variance | -1.32 | +| learning_rate | 0.0001 | +| loss | -0.0774 | +| n_updates | 117770 | +| policy_gradient_loss | -0.067 | +| value_loss | 0.00053 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.423 | +| time/ | | +| fps | 309 | +| iterations | 5726 | +| time_elapsed | 18932 | +| total_timesteps | 5863424 | +| train/ | | +| approx_kl | 2.0772614 | +| clip_fraction | 0.492 | +| clip_range | 0.2 | +| entropy_loss | -0.402 | +| explained_variance | -2.43 | +| learning_rate | 0.0001 | +| loss | -0.086 | +| n_updates | 117780 | +| policy_gradient_loss | -0.0724 | +| value_loss | 0.000444 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.423 | +| time/ | | +| fps | 309 | +| iterations | 5727 | +| time_elapsed | 18935 | +| total_timesteps | 5864448 | +| train/ | | +| approx_kl | 2.1778793 | +| clip_fraction | 0.466 | +| clip_range | 0.2 | +| entropy_loss | -0.362 | +| explained_variance | -2.21 | +| learning_rate | 0.0001 | +| loss | -0.0799 | +| n_updates | 117790 | +| policy_gradient_loss | -0.0727 | +| value_loss | 0.000305 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.423 | +| time/ | | +| fps | 309 | +| iterations | 5728 | +| time_elapsed | 18938 | +| total_timesteps | 5865472 | +| train/ | | +| approx_kl | 3.9372628 | +| clip_fraction | 0.501 | +| clip_range | 0.2 | +| entropy_loss | -0.416 | +| explained_variance | -1.07 | +| learning_rate | 0.0001 | +| loss | -0.0767 | +| n_updates | 117800 | +| policy_gradient_loss | -0.076 | +| value_loss | 0.0005 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.426 | +| time/ | | +| fps | 309 | +| iterations | 5729 | +| time_elapsed | 18942 | +| total_timesteps | 5866496 | +| train/ | | +| approx_kl | 2.1969712 | +| clip_fraction | 0.493 | +| clip_range | 0.2 | +| entropy_loss | -0.38 | +| explained_variance | -3.76 | +| learning_rate | 0.0001 | +| loss | -0.0526 | +| n_updates | 117810 | +| policy_gradient_loss | -0.0783 | +| value_loss | 0.000425 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.428 | +| time/ | | +| fps | 309 | +| iterations | 5730 | +| time_elapsed | 18945 | +| total_timesteps | 5867520 | +| train/ | | +| approx_kl | 2.3084555 | +| clip_fraction | 0.469 | +| clip_range | 0.2 | +| entropy_loss | -0.332 | +| explained_variance | -1.49 | +| learning_rate | 0.0001 | +| loss | -0.0791 | +| n_updates | 117820 | +| policy_gradient_loss | -0.0706 | +| value_loss | 0.000415 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.428 | +| time/ | | +| fps | 309 | +| iterations | 5731 | +| time_elapsed | 18949 | +| total_timesteps | 5868544 | +| train/ | | +| approx_kl | 2.2166135 | +| clip_fraction | 0.499 | +| clip_range | 0.2 | +| entropy_loss | -0.402 | +| explained_variance | -0.407 | +| learning_rate | 0.0001 | +| loss | -0.096 | +| n_updates | 117830 | +| policy_gradient_loss | -0.0675 | +| value_loss | 0.000592 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.429 | +| time/ | | +| fps | 309 | +| iterations | 5732 | +| time_elapsed | 18953 | +| total_timesteps | 5869568 | +| train/ | | +| approx_kl | 2.4022293 | +| clip_fraction | 0.492 | +| clip_range | 0.2 | +| entropy_loss | -0.367 | +| explained_variance | -2.22 | +| learning_rate | 0.0001 | +| loss | -0.0897 | +| n_updates | 117840 | +| policy_gradient_loss | -0.0732 | +| value_loss | 0.000767 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.431 | +| time/ | | +| fps | 309 | +| iterations | 5733 | +| time_elapsed | 18956 | +| total_timesteps | 5870592 | +| train/ | | +| approx_kl | 2.1113424 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.391 | +| explained_variance | -1.33 | +| learning_rate | 0.0001 | +| loss | -0.0929 | +| n_updates | 117850 | +| policy_gradient_loss | -0.0708 | +| value_loss | 0.00065 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.431 | +| time/ | | +| fps | 309 | +| iterations | 5734 | +| time_elapsed | 18960 | +| total_timesteps | 5871616 | +| train/ | | +| approx_kl | 2.817415 | +| clip_fraction | 0.446 | +| clip_range | 0.2 | +| entropy_loss | -0.315 | +| explained_variance | -1.32 | +| learning_rate | 0.0001 | +| loss | -0.0866 | +| n_updates | 117860 | +| policy_gradient_loss | -0.0712 | +| value_loss | 0.000787 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.434 | +| time/ | | +| fps | 309 | +| iterations | 5735 | +| time_elapsed | 18963 | +| total_timesteps | 5872640 | +| train/ | | +| approx_kl | 2.600545 | +| clip_fraction | 0.474 | +| clip_range | 0.2 | +| entropy_loss | -0.382 | +| explained_variance | -1.79 | +| learning_rate | 0.0001 | +| loss | -0.0877 | +| n_updates | 117870 | +| policy_gradient_loss | -0.0735 | +| value_loss | 0.000514 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.434 | +| time/ | | +| fps | 309 | +| iterations | 5736 | +| time_elapsed | 18967 | +| total_timesteps | 5873664 | +| train/ | | +| approx_kl | 1.7551818 | +| clip_fraction | 0.493 | +| clip_range | 0.2 | +| entropy_loss | -0.402 | +| explained_variance | -1.56 | +| learning_rate | 0.0001 | +| loss | -0.0846 | +| n_updates | 117880 | +| policy_gradient_loss | -0.0678 | +| value_loss | 0.000393 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.435 | +| time/ | | +| fps | 309 | +| iterations | 5737 | +| time_elapsed | 18970 | +| total_timesteps | 5874688 | +| train/ | | +| approx_kl | 2.5407352 | +| clip_fraction | 0.485 | +| clip_range | 0.2 | +| entropy_loss | -0.371 | +| explained_variance | -2.79 | +| learning_rate | 0.0001 | +| loss | -0.0825 | +| n_updates | 117890 | +| policy_gradient_loss | -0.0766 | +| value_loss | 0.00061 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.435 | +| time/ | | +| fps | 309 | +| iterations | 5738 | +| time_elapsed | 18973 | +| total_timesteps | 5875712 | +| train/ | | +| approx_kl | 1.949396 | +| clip_fraction | 0.459 | +| clip_range | 0.2 | +| entropy_loss | -0.376 | +| explained_variance | -1.17 | +| learning_rate | 0.0001 | +| loss | -0.0912 | +| n_updates | 117900 | +| policy_gradient_loss | -0.0641 | +| value_loss | 0.000574 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.435 | +| time/ | | +| fps | 309 | +| iterations | 5739 | +| time_elapsed | 18976 | +| total_timesteps | 5876736 | +| train/ | | +| approx_kl | 2.428718 | +| clip_fraction | 0.502 | +| clip_range | 0.2 | +| entropy_loss | -0.392 | +| explained_variance | -1.62 | +| learning_rate | 0.0001 | +| loss | -0.0647 | +| n_updates | 117910 | +| policy_gradient_loss | -0.0713 | +| value_loss | 0.000485 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.435 | +| time/ | | +| fps | 309 | +| iterations | 5740 | +| time_elapsed | 18980 | +| total_timesteps | 5877760 | +| train/ | | +| approx_kl | 2.192367 | +| clip_fraction | 0.517 | +| clip_range | 0.2 | +| entropy_loss | -0.406 | +| explained_variance | -2.31 | +| learning_rate | 0.0001 | +| loss | -0.096 | +| n_updates | 117920 | +| policy_gradient_loss | -0.0759 | +| value_loss | 0.000503 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.433 | +| time/ | | +| fps | 309 | +| iterations | 5741 | +| time_elapsed | 18983 | +| total_timesteps | 5878784 | +| train/ | | +| approx_kl | 7.2724605 | +| clip_fraction | 0.505 | +| clip_range | 0.2 | +| entropy_loss | -0.43 | +| explained_variance | -1.41 | +| learning_rate | 0.0001 | +| loss | -0.0766 | +| n_updates | 117930 | +| policy_gradient_loss | -0.0738 | +| value_loss | 0.000301 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.437 | +| time/ | | +| fps | 309 | +| iterations | 5742 | +| time_elapsed | 18986 | +| total_timesteps | 5879808 | +| train/ | | +| approx_kl | 2.191461 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.387 | +| explained_variance | -0.768 | +| learning_rate | 0.0001 | +| loss | -0.0808 | +| n_updates | 117940 | +| policy_gradient_loss | -0.0664 | +| value_loss | 0.000338 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.437 | +| time/ | | +| fps | 309 | +| iterations | 5743 | +| time_elapsed | 18989 | +| total_timesteps | 5880832 | +| train/ | | +| approx_kl | 1.8724871 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.398 | +| explained_variance | -0.424 | +| learning_rate | 0.0001 | +| loss | -0.0833 | +| n_updates | 117950 | +| policy_gradient_loss | -0.064 | +| value_loss | 0.000541 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.44 | +| time/ | | +| fps | 309 | +| iterations | 5744 | +| time_elapsed | 18992 | +| total_timesteps | 5881856 | +| train/ | | +| approx_kl | 1.7322066 | +| clip_fraction | 0.493 | +| clip_range | 0.2 | +| entropy_loss | -0.4 | +| explained_variance | -2.13 | +| learning_rate | 0.0001 | +| loss | -0.082 | +| n_updates | 117960 | +| policy_gradient_loss | -0.069 | +| value_loss | 0.000562 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.44 | +| time/ | | +| fps | 309 | +| iterations | 5745 | +| time_elapsed | 18996 | +| total_timesteps | 5882880 | +| train/ | | +| approx_kl | 2.976565 | +| clip_fraction | 0.491 | +| clip_range | 0.2 | +| entropy_loss | -0.399 | +| explained_variance | -0.87 | +| learning_rate | 0.0001 | +| loss | -0.0858 | +| n_updates | 117970 | +| policy_gradient_loss | -0.0713 | +| value_loss | 0.00053 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.44 | +| time/ | | +| fps | 309 | +| iterations | 5746 | +| time_elapsed | 18999 | +| total_timesteps | 5883904 | +| train/ | | +| approx_kl | 2.4301121 | +| clip_fraction | 0.468 | +| clip_range | 0.2 | +| entropy_loss | -0.354 | +| explained_variance | -1.78 | +| learning_rate | 0.0001 | +| loss | -0.0814 | +| n_updates | 117980 | +| policy_gradient_loss | -0.0699 | +| value_loss | 0.000414 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.44 | +| time/ | | +| fps | 309 | +| iterations | 5747 | +| time_elapsed | 19002 | +| total_timesteps | 5884928 | +| train/ | | +| approx_kl | 3.4517992 | +| clip_fraction | 0.49 | +| clip_range | 0.2 | +| entropy_loss | -0.388 | +| explained_variance | -0.456 | +| learning_rate | 0.0001 | +| loss | -0.0609 | +| n_updates | 117990 | +| policy_gradient_loss | -0.061 | +| value_loss | 0.000857 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.44 | +| time/ | | +| fps | 309 | +| iterations | 5748 | +| time_elapsed | 19006 | +| total_timesteps | 5885952 | +| train/ | | +| approx_kl | 2.2053275 | +| clip_fraction | 0.527 | +| clip_range | 0.2 | +| entropy_loss | -0.431 | +| explained_variance | -1.93 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 118000 | +| policy_gradient_loss | -0.0831 | +| value_loss | 0.000732 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.44 | +| time/ | | +| fps | 309 | +| iterations | 5749 | +| time_elapsed | 19009 | +| total_timesteps | 5886976 | +| train/ | | +| approx_kl | 1.6284997 | +| clip_fraction | 0.465 | +| clip_range | 0.2 | +| entropy_loss | -0.396 | +| explained_variance | -1.67 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 118010 | +| policy_gradient_loss | -0.0679 | +| value_loss | 0.000563 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.445 | +| time/ | | +| fps | 309 | +| iterations | 5750 | +| time_elapsed | 19013 | +| total_timesteps | 5888000 | +| train/ | | +| approx_kl | 1.883951 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.399 | +| explained_variance | -1.72 | +| learning_rate | 0.0001 | +| loss | -0.119 | +| n_updates | 118020 | +| policy_gradient_loss | -0.0736 | +| value_loss | 0.000483 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.445 | +| time/ | | +| fps | 309 | +| iterations | 5751 | +| time_elapsed | 19016 | +| total_timesteps | 5889024 | +| train/ | | +| approx_kl | 1.820689 | +| clip_fraction | 0.45 | +| clip_range | 0.2 | +| entropy_loss | -0.343 | +| explained_variance | -1.02 | +| learning_rate | 0.0001 | +| loss | -0.0966 | +| n_updates | 118030 | +| policy_gradient_loss | -0.0631 | +| value_loss | 0.000707 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.448 | +| time/ | | +| fps | 309 | +| iterations | 5752 | +| time_elapsed | 19020 | +| total_timesteps | 5890048 | +| train/ | | +| approx_kl | 2.3146286 | +| clip_fraction | 0.498 | +| clip_range | 0.2 | +| entropy_loss | -0.378 | +| explained_variance | -8.62 | +| learning_rate | 0.0001 | +| loss | -0.0939 | +| n_updates | 118040 | +| policy_gradient_loss | -0.0772 | +| value_loss | 0.000527 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.446 | +| time/ | | +| fps | 309 | +| iterations | 5753 | +| time_elapsed | 19023 | +| total_timesteps | 5891072 | +| train/ | | +| approx_kl | 1.9821341 | +| clip_fraction | 0.488 | +| clip_range | 0.2 | +| entropy_loss | -0.381 | +| explained_variance | -0.47 | +| learning_rate | 0.0001 | +| loss | -0.0751 | +| n_updates | 118050 | +| policy_gradient_loss | -0.0621 | +| value_loss | 0.000458 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.446 | +| time/ | | +| fps | 309 | +| iterations | 5754 | +| time_elapsed | 19027 | +| total_timesteps | 5892096 | +| train/ | | +| approx_kl | 2.4491558 | +| clip_fraction | 0.476 | +| clip_range | 0.2 | +| entropy_loss | -0.378 | +| explained_variance | -1.51 | +| learning_rate | 0.0001 | +| loss | -0.0894 | +| n_updates | 118060 | +| policy_gradient_loss | -0.0714 | +| value_loss | 0.000473 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.445 | +| time/ | | +| fps | 309 | +| iterations | 5755 | +| time_elapsed | 19030 | +| total_timesteps | 5893120 | +| train/ | | +| approx_kl | 2.1240788 | +| clip_fraction | 0.503 | +| clip_range | 0.2 | +| entropy_loss | -0.398 | +| explained_variance | -0.939 | +| learning_rate | 0.0001 | +| loss | -0.0985 | +| n_updates | 118070 | +| policy_gradient_loss | -0.0763 | +| value_loss | 0.000445 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.444 | +| time/ | | +| fps | 309 | +| iterations | 5756 | +| time_elapsed | 19033 | +| total_timesteps | 5894144 | +| train/ | | +| approx_kl | 2.4102943 | +| clip_fraction | 0.489 | +| clip_range | 0.2 | +| entropy_loss | -0.4 | +| explained_variance | -0.819 | +| learning_rate | 0.0001 | +| loss | -0.0892 | +| n_updates | 118080 | +| policy_gradient_loss | -0.0639 | +| value_loss | 0.000536 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.445 | +| time/ | | +| fps | 309 | +| iterations | 5757 | +| time_elapsed | 19036 | +| total_timesteps | 5895168 | +| train/ | | +| approx_kl | 2.3990517 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.42 | +| explained_variance | -1.04 | +| learning_rate | 0.0001 | +| loss | -0.0734 | +| n_updates | 118090 | +| policy_gradient_loss | -0.0714 | +| value_loss | 0.000664 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.446 | +| time/ | | +| fps | 309 | +| iterations | 5758 | +| time_elapsed | 19040 | +| total_timesteps | 5896192 | +| train/ | | +| approx_kl | 2.5079126 | +| clip_fraction | 0.458 | +| clip_range | 0.2 | +| entropy_loss | -0.349 | +| explained_variance | -0.667 | +| learning_rate | 0.0001 | +| loss | -0.0915 | +| n_updates | 118100 | +| policy_gradient_loss | -0.059 | +| value_loss | 0.000895 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.448 | +| time/ | | +| fps | 309 | +| iterations | 5759 | +| time_elapsed | 19043 | +| total_timesteps | 5897216 | +| train/ | | +| approx_kl | 2.36247 | +| clip_fraction | 0.474 | +| clip_range | 0.2 | +| entropy_loss | -0.375 | +| explained_variance | -0.729 | +| learning_rate | 0.0001 | +| loss | -0.0998 | +| n_updates | 118110 | +| policy_gradient_loss | -0.0679 | +| value_loss | 0.000874 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.448 | +| time/ | | +| fps | 309 | +| iterations | 5760 | +| time_elapsed | 19046 | +| total_timesteps | 5898240 | +| train/ | | +| approx_kl | 3.6155748 | +| clip_fraction | 0.472 | +| clip_range | 0.2 | +| entropy_loss | -0.378 | +| explained_variance | -1.86 | +| learning_rate | 0.0001 | +| loss | -0.0678 | +| n_updates | 118120 | +| policy_gradient_loss | -0.0709 | +| value_loss | 0.000568 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.447 | +| time/ | | +| fps | 309 | +| iterations | 5761 | +| time_elapsed | 19049 | +| total_timesteps | 5899264 | +| train/ | | +| approx_kl | 1.9571025 | +| clip_fraction | 0.521 | +| clip_range | 0.2 | +| entropy_loss | -0.461 | +| explained_variance | -1.23 | +| learning_rate | 0.0001 | +| loss | -0.0988 | +| n_updates | 118130 | +| policy_gradient_loss | -0.0743 | +| value_loss | 0.000493 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.447 | +| time/ | | +| fps | 309 | +| iterations | 5762 | +| time_elapsed | 19052 | +| total_timesteps | 5900288 | +| train/ | | +| approx_kl | 2.6296418 | +| clip_fraction | 0.488 | +| clip_range | 0.2 | +| entropy_loss | -0.398 | +| explained_variance | -2.07 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 118140 | +| policy_gradient_loss | -0.0729 | +| value_loss | 0.000381 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.45 | +| time/ | | +| fps | 309 | +| iterations | 5763 | +| time_elapsed | 19056 | +| total_timesteps | 5901312 | +| train/ | | +| approx_kl | 1.9332006 | +| clip_fraction | 0.508 | +| clip_range | 0.2 | +| entropy_loss | -0.408 | +| explained_variance | -1.12 | +| learning_rate | 0.0001 | +| loss | -0.0887 | +| n_updates | 118150 | +| policy_gradient_loss | -0.0744 | +| value_loss | 0.000328 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.451 | +| time/ | | +| fps | 309 | +| iterations | 5764 | +| time_elapsed | 19059 | +| total_timesteps | 5902336 | +| train/ | | +| approx_kl | 2.439794 | +| clip_fraction | 0.495 | +| clip_range | 0.2 | +| entropy_loss | -0.444 | +| explained_variance | -1.11 | +| learning_rate | 0.0001 | +| loss | -0.076 | +| n_updates | 118160 | +| policy_gradient_loss | -0.069 | +| value_loss | 0.000683 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.449 | +| time/ | | +| fps | 309 | +| iterations | 5765 | +| time_elapsed | 19062 | +| total_timesteps | 5903360 | +| train/ | | +| approx_kl | 1.60237 | +| clip_fraction | 0.429 | +| clip_range | 0.2 | +| entropy_loss | -0.392 | +| explained_variance | -0.881 | +| learning_rate | 0.0001 | +| loss | -0.0794 | +| n_updates | 118170 | +| policy_gradient_loss | -0.0607 | +| value_loss | 0.000915 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.449 | +| time/ | | +| fps | 309 | +| iterations | 5766 | +| time_elapsed | 19066 | +| total_timesteps | 5904384 | +| train/ | | +| approx_kl | 1.76879 | +| clip_fraction | 0.454 | +| clip_range | 0.2 | +| entropy_loss | -0.383 | +| explained_variance | -0.811 | +| learning_rate | 0.0001 | +| loss | -0.0921 | +| n_updates | 118180 | +| policy_gradient_loss | -0.0698 | +| value_loss | 0.000549 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.45 | +| time/ | | +| fps | 309 | +| iterations | 5767 | +| time_elapsed | 19069 | +| total_timesteps | 5905408 | +| train/ | | +| approx_kl | 2.098106 | +| clip_fraction | 0.519 | +| clip_range | 0.2 | +| entropy_loss | -0.443 | +| explained_variance | -1.47 | +| learning_rate | 0.0001 | +| loss | -0.106 | +| n_updates | 118190 | +| policy_gradient_loss | -0.0718 | +| value_loss | 0.000436 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.452 | +| time/ | | +| fps | 309 | +| iterations | 5768 | +| time_elapsed | 19073 | +| total_timesteps | 5906432 | +| train/ | | +| approx_kl | 1.8272834 | +| clip_fraction | 0.474 | +| clip_range | 0.2 | +| entropy_loss | -0.394 | +| explained_variance | -0.96 | +| learning_rate | 0.0001 | +| loss | -0.0581 | +| n_updates | 118200 | +| policy_gradient_loss | -0.0632 | +| value_loss | 0.000498 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.452 | +| time/ | | +| fps | 309 | +| iterations | 5769 | +| time_elapsed | 19076 | +| total_timesteps | 5907456 | +| train/ | | +| approx_kl | 2.65515 | +| clip_fraction | 0.489 | +| clip_range | 0.2 | +| entropy_loss | -0.39 | +| explained_variance | -0.786 | +| learning_rate | 0.0001 | +| loss | -0.0841 | +| n_updates | 118210 | +| policy_gradient_loss | -0.0722 | +| value_loss | 0.000409 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.453 | +| time/ | | +| fps | 309 | +| iterations | 5770 | +| time_elapsed | 19080 | +| total_timesteps | 5908480 | +| train/ | | +| approx_kl | 2.1504073 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.401 | +| explained_variance | -2.02 | +| learning_rate | 0.0001 | +| loss | -0.082 | +| n_updates | 118220 | +| policy_gradient_loss | -0.0699 | +| value_loss | 0.000582 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.453 | +| time/ | | +| fps | 309 | +| iterations | 5771 | +| time_elapsed | 19083 | +| total_timesteps | 5909504 | +| train/ | | +| approx_kl | 2.8066142 | +| clip_fraction | 0.493 | +| clip_range | 0.2 | +| entropy_loss | -0.392 | +| explained_variance | -0.402 | +| learning_rate | 0.0001 | +| loss | -0.0789 | +| n_updates | 118230 | +| policy_gradient_loss | -0.0698 | +| value_loss | 0.000974 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.453 | +| time/ | | +| fps | 309 | +| iterations | 5772 | +| time_elapsed | 19087 | +| total_timesteps | 5910528 | +| train/ | | +| approx_kl | 1.855542 | +| clip_fraction | 0.461 | +| clip_range | 0.2 | +| entropy_loss | -0.405 | +| explained_variance | -1.01 | +| learning_rate | 0.0001 | +| loss | -0.0867 | +| n_updates | 118240 | +| policy_gradient_loss | -0.0734 | +| value_loss | 0.000728 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.454 | +| time/ | | +| fps | 309 | +| iterations | 5773 | +| time_elapsed | 19090 | +| total_timesteps | 5911552 | +| train/ | | +| approx_kl | 1.7190758 | +| clip_fraction | 0.489 | +| clip_range | 0.2 | +| entropy_loss | -0.421 | +| explained_variance | -3.26 | +| learning_rate | 0.0001 | +| loss | -0.0984 | +| n_updates | 118250 | +| policy_gradient_loss | -0.0742 | +| value_loss | 0.000455 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.454 | +| time/ | | +| fps | 309 | +| iterations | 5774 | +| time_elapsed | 19093 | +| total_timesteps | 5912576 | +| train/ | | +| approx_kl | 1.9634411 | +| clip_fraction | 0.474 | +| clip_range | 0.2 | +| entropy_loss | -0.346 | +| explained_variance | -0.948 | +| learning_rate | 0.0001 | +| loss | -0.072 | +| n_updates | 118260 | +| policy_gradient_loss | -0.064 | +| value_loss | 0.000547 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.451 | +| time/ | | +| fps | 309 | +| iterations | 5775 | +| time_elapsed | 19096 | +| total_timesteps | 5913600 | +| train/ | | +| approx_kl | 2.4627695 | +| clip_fraction | 0.484 | +| clip_range | 0.2 | +| entropy_loss | -0.403 | +| explained_variance | -7.24 | +| learning_rate | 0.0001 | +| loss | -0.112 | +| n_updates | 118270 | +| policy_gradient_loss | -0.0771 | +| value_loss | 0.000307 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.451 | +| time/ | | +| fps | 309 | +| iterations | 5776 | +| time_elapsed | 19100 | +| total_timesteps | 5914624 | +| train/ | | +| approx_kl | 2.2885597 | +| clip_fraction | 0.476 | +| clip_range | 0.2 | +| entropy_loss | -0.371 | +| explained_variance | -0.813 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 118280 | +| policy_gradient_loss | -0.0641 | +| value_loss | 0.000278 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.45 | +| time/ | | +| fps | 309 | +| iterations | 5777 | +| time_elapsed | 19103 | +| total_timesteps | 5915648 | +| train/ | | +| approx_kl | 2.4118195 | +| clip_fraction | 0.496 | +| clip_range | 0.2 | +| entropy_loss | -0.373 | +| explained_variance | -1.95 | +| learning_rate | 0.0001 | +| loss | -0.0857 | +| n_updates | 118290 | +| policy_gradient_loss | -0.0753 | +| value_loss | 0.000467 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.449 | +| time/ | | +| fps | 309 | +| iterations | 5778 | +| time_elapsed | 19106 | +| total_timesteps | 5916672 | +| train/ | | +| approx_kl | 2.2775784 | +| clip_fraction | 0.468 | +| clip_range | 0.2 | +| entropy_loss | -0.369 | +| explained_variance | -1.41 | +| learning_rate | 0.0001 | +| loss | -0.0939 | +| n_updates | 118300 | +| policy_gradient_loss | -0.0659 | +| value_loss | 0.000387 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.449 | +| time/ | | +| fps | 309 | +| iterations | 5779 | +| time_elapsed | 19109 | +| total_timesteps | 5917696 | +| train/ | | +| approx_kl | 2.0929308 | +| clip_fraction | 0.473 | +| clip_range | 0.2 | +| entropy_loss | -0.378 | +| explained_variance | -0.991 | +| learning_rate | 0.0001 | +| loss | -0.083 | +| n_updates | 118310 | +| policy_gradient_loss | -0.066 | +| value_loss | 0.000626 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.451 | +| time/ | | +| fps | 309 | +| iterations | 5780 | +| time_elapsed | 19112 | +| total_timesteps | 5918720 | +| train/ | | +| approx_kl | 2.4852736 | +| clip_fraction | 0.511 | +| clip_range | 0.2 | +| entropy_loss | -0.394 | +| explained_variance | -2.67 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 118320 | +| policy_gradient_loss | -0.0737 | +| value_loss | 0.000507 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.451 | +| time/ | | +| fps | 309 | +| iterations | 5781 | +| time_elapsed | 19116 | +| total_timesteps | 5919744 | +| train/ | | +| approx_kl | 2.0458524 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.394 | +| explained_variance | -2.78 | +| learning_rate | 0.0001 | +| loss | -0.0936 | +| n_updates | 118330 | +| policy_gradient_loss | -0.0658 | +| value_loss | 0.00029 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.45 | +| time/ | | +| fps | 309 | +| iterations | 5782 | +| time_elapsed | 19119 | +| total_timesteps | 5920768 | +| train/ | | +| approx_kl | 2.1470652 | +| clip_fraction | 0.528 | +| clip_range | 0.2 | +| entropy_loss | -0.453 | +| explained_variance | -0.863 | +| learning_rate | 0.0001 | +| loss | -0.0946 | +| n_updates | 118340 | +| policy_gradient_loss | -0.0747 | +| value_loss | 0.00039 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.45 | +| time/ | | +| fps | 309 | +| iterations | 5783 | +| time_elapsed | 19122 | +| total_timesteps | 5921792 | +| train/ | | +| approx_kl | 1.6728648 | +| clip_fraction | 0.512 | +| clip_range | 0.2 | +| entropy_loss | -0.498 | +| explained_variance | -1.34 | +| learning_rate | 0.0001 | +| loss | -0.089 | +| n_updates | 118350 | +| policy_gradient_loss | -0.0719 | +| value_loss | 0.000294 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.448 | +| time/ | | +| fps | 309 | +| iterations | 5784 | +| time_elapsed | 19126 | +| total_timesteps | 5922816 | +| train/ | | +| approx_kl | 4.1064606 | +| clip_fraction | 0.521 | +| clip_range | 0.2 | +| entropy_loss | -0.387 | +| explained_variance | -1.22 | +| learning_rate | 0.0001 | +| loss | -0.105 | +| n_updates | 118360 | +| policy_gradient_loss | -0.0753 | +| value_loss | 0.000467 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.448 | +| time/ | | +| fps | 309 | +| iterations | 5785 | +| time_elapsed | 19129 | +| total_timesteps | 5923840 | +| train/ | | +| approx_kl | 2.1138785 | +| clip_fraction | 0.508 | +| clip_range | 0.2 | +| entropy_loss | -0.429 | +| explained_variance | -1.81 | +| learning_rate | 0.0001 | +| loss | -0.0917 | +| n_updates | 118370 | +| policy_gradient_loss | -0.0718 | +| value_loss | 0.000471 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.445 | +| time/ | | +| fps | 309 | +| iterations | 5786 | +| time_elapsed | 19133 | +| total_timesteps | 5924864 | +| train/ | | +| approx_kl | 2.5149772 | +| clip_fraction | 0.496 | +| clip_range | 0.2 | +| entropy_loss | -0.372 | +| explained_variance | -2.04 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 118380 | +| policy_gradient_loss | -0.0731 | +| value_loss | 0.000474 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.445 | +| time/ | | +| fps | 309 | +| iterations | 5787 | +| time_elapsed | 19136 | +| total_timesteps | 5925888 | +| train/ | | +| approx_kl | 2.2344618 | +| clip_fraction | 0.507 | +| clip_range | 0.2 | +| entropy_loss | -0.457 | +| explained_variance | -2.15 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 118390 | +| policy_gradient_loss | -0.078 | +| value_loss | 0.000356 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.445 | +| time/ | | +| fps | 309 | +| iterations | 5788 | +| time_elapsed | 19139 | +| total_timesteps | 5926912 | +| train/ | | +| approx_kl | 2.288811 | +| clip_fraction | 0.511 | +| clip_range | 0.2 | +| entropy_loss | -0.471 | +| explained_variance | -1.39 | +| learning_rate | 0.0001 | +| loss | -0.11 | +| n_updates | 118400 | +| policy_gradient_loss | -0.0751 | +| value_loss | 0.00042 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.441 | +| time/ | | +| fps | 309 | +| iterations | 5789 | +| time_elapsed | 19143 | +| total_timesteps | 5927936 | +| train/ | | +| approx_kl | 1.8858402 | +| clip_fraction | 0.479 | +| clip_range | 0.2 | +| entropy_loss | -0.416 | +| explained_variance | -0.756 | +| learning_rate | 0.0001 | +| loss | -0.0711 | +| n_updates | 118410 | +| policy_gradient_loss | -0.0637 | +| value_loss | 0.000711 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.441 | +| time/ | | +| fps | 309 | +| iterations | 5790 | +| time_elapsed | 19146 | +| total_timesteps | 5928960 | +| train/ | | +| approx_kl | 2.0602384 | +| clip_fraction | 0.479 | +| clip_range | 0.2 | +| entropy_loss | -0.426 | +| explained_variance | -2.33 | +| learning_rate | 0.0001 | +| loss | -0.0689 | +| n_updates | 118420 | +| policy_gradient_loss | -0.073 | +| value_loss | 0.000657 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.439 | +| time/ | | +| fps | 309 | +| iterations | 5791 | +| time_elapsed | 19149 | +| total_timesteps | 5929984 | +| train/ | | +| approx_kl | 18.069466 | +| clip_fraction | 0.496 | +| clip_range | 0.2 | +| entropy_loss | -0.412 | +| explained_variance | -1.78 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 118430 | +| policy_gradient_loss | -0.0774 | +| value_loss | 0.000456 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.439 | +| time/ | | +| fps | 309 | +| iterations | 5792 | +| time_elapsed | 19153 | +| total_timesteps | 5931008 | +| train/ | | +| approx_kl | 2.4437246 | +| clip_fraction | 0.496 | +| clip_range | 0.2 | +| entropy_loss | -0.417 | +| explained_variance | -1.46 | +| learning_rate | 0.0001 | +| loss | -0.0842 | +| n_updates | 118440 | +| policy_gradient_loss | -0.0728 | +| value_loss | 0.000518 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.438 | +| time/ | | +| fps | 309 | +| iterations | 5793 | +| time_elapsed | 19156 | +| total_timesteps | 5932032 | +| train/ | | +| approx_kl | 2.1031246 | +| clip_fraction | 0.473 | +| clip_range | 0.2 | +| entropy_loss | -0.409 | +| explained_variance | -3.82 | +| learning_rate | 0.0001 | +| loss | -0.075 | +| n_updates | 118450 | +| policy_gradient_loss | -0.0679 | +| value_loss | 0.000333 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.438 | +| time/ | | +| fps | 309 | +| iterations | 5794 | +| time_elapsed | 19159 | +| total_timesteps | 5933056 | +| train/ | | +| approx_kl | 2.0232167 | +| clip_fraction | 0.476 | +| clip_range | 0.2 | +| entropy_loss | -0.392 | +| explained_variance | -2.21 | +| learning_rate | 0.0001 | +| loss | -0.0967 | +| n_updates | 118460 | +| policy_gradient_loss | -0.0738 | +| value_loss | 0.00036 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.437 | +| time/ | | +| fps | 309 | +| iterations | 5795 | +| time_elapsed | 19162 | +| total_timesteps | 5934080 | +| train/ | | +| approx_kl | 1.617011 | +| clip_fraction | 0.474 | +| clip_range | 0.2 | +| entropy_loss | -0.438 | +| explained_variance | -0.952 | +| learning_rate | 0.0001 | +| loss | -0.0619 | +| n_updates | 118470 | +| policy_gradient_loss | -0.0641 | +| value_loss | 0.000615 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.436 | +| time/ | | +| fps | 309 | +| iterations | 5796 | +| time_elapsed | 19165 | +| total_timesteps | 5935104 | +| train/ | | +| approx_kl | 2.118896 | +| clip_fraction | 0.485 | +| clip_range | 0.2 | +| entropy_loss | -0.411 | +| explained_variance | -1.24 | +| learning_rate | 0.0001 | +| loss | -0.118 | +| n_updates | 118480 | +| policy_gradient_loss | -0.072 | +| value_loss | 0.000574 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.436 | +| time/ | | +| fps | 309 | +| iterations | 5797 | +| time_elapsed | 19169 | +| total_timesteps | 5936128 | +| train/ | | +| approx_kl | 1.547038 | +| clip_fraction | 0.493 | +| clip_range | 0.2 | +| entropy_loss | -0.459 | +| explained_variance | -0.983 | +| learning_rate | 0.0001 | +| loss | -0.0836 | +| n_updates | 118490 | +| policy_gradient_loss | -0.0747 | +| value_loss | 0.000738 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.436 | +| time/ | | +| fps | 309 | +| iterations | 5798 | +| time_elapsed | 19172 | +| total_timesteps | 5937152 | +| train/ | | +| approx_kl | 4.0173674 | +| clip_fraction | 0.52 | +| clip_range | 0.2 | +| entropy_loss | -0.413 | +| explained_variance | -2.2 | +| learning_rate | 0.0001 | +| loss | -0.0997 | +| n_updates | 118500 | +| policy_gradient_loss | -0.0824 | +| value_loss | 0.00075 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.438 | +| time/ | | +| fps | 309 | +| iterations | 5799 | +| time_elapsed | 19175 | +| total_timesteps | 5938176 | +| train/ | | +| approx_kl | 2.0231962 | +| clip_fraction | 0.516 | +| clip_range | 0.2 | +| entropy_loss | -0.443 | +| explained_variance | -0.649 | +| learning_rate | 0.0001 | +| loss | -0.0926 | +| n_updates | 118510 | +| policy_gradient_loss | -0.0676 | +| value_loss | 0.000741 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.438 | +| time/ | | +| fps | 309 | +| iterations | 5800 | +| time_elapsed | 19178 | +| total_timesteps | 5939200 | +| train/ | | +| approx_kl | 1.8859622 | +| clip_fraction | 0.504 | +| clip_range | 0.2 | +| entropy_loss | -0.427 | +| explained_variance | -0.707 | +| learning_rate | 0.0001 | +| loss | -0.0699 | +| n_updates | 118520 | +| policy_gradient_loss | -0.0678 | +| value_loss | 0.000806 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.436 | +| time/ | | +| fps | 309 | +| iterations | 5801 | +| time_elapsed | 19182 | +| total_timesteps | 5940224 | +| train/ | | +| approx_kl | 2.9096642 | +| clip_fraction | 0.517 | +| clip_range | 0.2 | +| entropy_loss | -0.449 | +| explained_variance | -8.23 | +| learning_rate | 0.0001 | +| loss | -0.0962 | +| n_updates | 118530 | +| policy_gradient_loss | -0.0795 | +| value_loss | 0.000295 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.436 | +| time/ | | +| fps | 309 | +| iterations | 5802 | +| time_elapsed | 19186 | +| total_timesteps | 5941248 | +| train/ | | +| approx_kl | 2.51307 | +| clip_fraction | 0.49 | +| clip_range | 0.2 | +| entropy_loss | -0.43 | +| explained_variance | -0.973 | +| learning_rate | 0.0001 | +| loss | -0.0544 | +| n_updates | 118540 | +| policy_gradient_loss | -0.0619 | +| value_loss | 0.000262 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.436 | +| time/ | | +| fps | 309 | +| iterations | 5803 | +| time_elapsed | 19189 | +| total_timesteps | 5942272 | +| train/ | | +| approx_kl | 2.106209 | +| clip_fraction | 0.499 | +| clip_range | 0.2 | +| entropy_loss | -0.392 | +| explained_variance | -0.932 | +| learning_rate | 0.0001 | +| loss | -0.0913 | +| n_updates | 118550 | +| policy_gradient_loss | -0.0695 | +| value_loss | 0.000493 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.436 | +| time/ | | +| fps | 309 | +| iterations | 5804 | +| time_elapsed | 19192 | +| total_timesteps | 5943296 | +| train/ | | +| approx_kl | 1.894207 | +| clip_fraction | 0.505 | +| clip_range | 0.2 | +| entropy_loss | -0.433 | +| explained_variance | -0.752 | +| learning_rate | 0.0001 | +| loss | -0.108 | +| n_updates | 118560 | +| policy_gradient_loss | -0.0571 | +| value_loss | 0.000568 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.439 | +| time/ | | +| fps | 309 | +| iterations | 5805 | +| time_elapsed | 19196 | +| total_timesteps | 5944320 | +| train/ | | +| approx_kl | 2.053307 | +| clip_fraction | 0.504 | +| clip_range | 0.2 | +| entropy_loss | -0.398 | +| explained_variance | -1.43 | +| learning_rate | 0.0001 | +| loss | -0.11 | +| n_updates | 118570 | +| policy_gradient_loss | -0.0735 | +| value_loss | 0.000571 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.44 | +| time/ | | +| fps | 309 | +| iterations | 5806 | +| time_elapsed | 19200 | +| total_timesteps | 5945344 | +| train/ | | +| approx_kl | 1.934766 | +| clip_fraction | 0.495 | +| clip_range | 0.2 | +| entropy_loss | -0.445 | +| explained_variance | -0.641 | +| learning_rate | 0.0001 | +| loss | -0.0895 | +| n_updates | 118580 | +| policy_gradient_loss | -0.0733 | +| value_loss | 0.000948 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | 0.446 | +| time/ | | +| fps | 309 | +| iterations | 5807 | +| time_elapsed | 19203 | +| total_timesteps | 5946368 | +| train/ | | +| approx_kl | 2.065812 | +| clip_fraction | 0.467 | +| clip_range | 0.2 | +| entropy_loss | -0.394 | +| explained_variance | -0.837 | +| learning_rate | 0.0001 | +| loss | -0.088 | +| n_updates | 118590 | +| policy_gradient_loss | -0.0697 | +| value_loss | 0.000954 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | 0.447 | +| time/ | | +| fps | 309 | +| iterations | 5808 | +| time_elapsed | 19207 | +| total_timesteps | 5947392 | +| train/ | | +| approx_kl | 2.1837578 | +| clip_fraction | 0.492 | +| clip_range | 0.2 | +| entropy_loss | -0.381 | +| explained_variance | -0.84 | +| learning_rate | 0.0001 | +| loss | -0.105 | +| n_updates | 118600 | +| policy_gradient_loss | -0.0743 | +| value_loss | 0.00112 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.65e+03 | +| ep_rew_mean | 0.447 | +| time/ | | +| fps | 309 | +| iterations | 5809 | +| time_elapsed | 19210 | +| total_timesteps | 5948416 | +| train/ | | +| approx_kl | 1.7279589 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.425 | +| explained_variance | -2.64 | +| learning_rate | 0.0001 | +| loss | -0.0919 | +| n_updates | 118610 | +| policy_gradient_loss | -0.0752 | +| value_loss | 0.000771 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.65e+03 | +| ep_rew_mean | 0.447 | +| time/ | | +| fps | 309 | +| iterations | 5810 | +| time_elapsed | 19213 | +| total_timesteps | 5949440 | +| train/ | | +| approx_kl | 1.8961608 | +| clip_fraction | 0.47 | +| clip_range | 0.2 | +| entropy_loss | -0.409 | +| explained_variance | -0.665 | +| learning_rate | 0.0001 | +| loss | -0.0883 | +| n_updates | 118620 | +| policy_gradient_loss | -0.0762 | +| value_loss | 0.000572 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.65e+03 | +| ep_rew_mean | 0.447 | +| time/ | | +| fps | 309 | +| iterations | 5811 | +| time_elapsed | 19217 | +| total_timesteps | 5950464 | +| train/ | | +| approx_kl | 2.7982488 | +| clip_fraction | 0.504 | +| clip_range | 0.2 | +| entropy_loss | -0.384 | +| explained_variance | -6.1 | +| learning_rate | 0.0001 | +| loss | -0.12 | +| n_updates | 118630 | +| policy_gradient_loss | -0.0806 | +| value_loss | 0.000601 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | 0.449 | +| time/ | | +| fps | 309 | +| iterations | 5812 | +| time_elapsed | 19220 | +| total_timesteps | 5951488 | +| train/ | | +| approx_kl | 2.3906062 | +| clip_fraction | 0.504 | +| clip_range | 0.2 | +| entropy_loss | -0.366 | +| explained_variance | -2.17 | +| learning_rate | 0.0001 | +| loss | -0.0782 | +| n_updates | 118640 | +| policy_gradient_loss | -0.0797 | +| value_loss | 0.000687 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | 0.449 | +| time/ | | +| fps | 309 | +| iterations | 5813 | +| time_elapsed | 19223 | +| total_timesteps | 5952512 | +| train/ | | +| approx_kl | 3.2650468 | +| clip_fraction | 0.462 | +| clip_range | 0.2 | +| entropy_loss | -0.387 | +| explained_variance | -2.8 | +| learning_rate | 0.0001 | +| loss | -0.0874 | +| n_updates | 118650 | +| policy_gradient_loss | -0.072 | +| value_loss | 0.000409 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.448 | +| time/ | | +| fps | 309 | +| iterations | 5814 | +| time_elapsed | 19226 | +| total_timesteps | 5953536 | +| train/ | | +| approx_kl | 2.2277575 | +| clip_fraction | 0.53 | +| clip_range | 0.2 | +| entropy_loss | -0.443 | +| explained_variance | -1.64 | +| learning_rate | 0.0001 | +| loss | -0.116 | +| n_updates | 118660 | +| policy_gradient_loss | -0.0773 | +| value_loss | 0.000346 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | 0.452 | +| time/ | | +| fps | 309 | +| iterations | 5815 | +| time_elapsed | 19229 | +| total_timesteps | 5954560 | +| train/ | | +| approx_kl | 2.3104107 | +| clip_fraction | 0.431 | +| clip_range | 0.2 | +| entropy_loss | -0.353 | +| explained_variance | -0.857 | +| learning_rate | 0.0001 | +| loss | -0.0949 | +| n_updates | 118670 | +| policy_gradient_loss | -0.0605 | +| value_loss | 0.000444 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | 0.452 | +| time/ | | +| fps | 309 | +| iterations | 5816 | +| time_elapsed | 19232 | +| total_timesteps | 5955584 | +| train/ | | +| approx_kl | 2.27275 | +| clip_fraction | 0.478 | +| clip_range | 0.2 | +| entropy_loss | -0.363 | +| explained_variance | -0.351 | +| learning_rate | 0.0001 | +| loss | -0.0625 | +| n_updates | 118680 | +| policy_gradient_loss | -0.065 | +| value_loss | 0.000874 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | 0.45 | +| time/ | | +| fps | 309 | +| iterations | 5817 | +| time_elapsed | 19236 | +| total_timesteps | 5956608 | +| train/ | | +| approx_kl | 2.0792718 | +| clip_fraction | 0.478 | +| clip_range | 0.2 | +| entropy_loss | -0.38 | +| explained_variance | -1.72 | +| learning_rate | 0.0001 | +| loss | -0.117 | +| n_updates | 118690 | +| policy_gradient_loss | -0.0689 | +| value_loss | 0.000576 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | 0.45 | +| time/ | | +| fps | 309 | +| iterations | 5818 | +| time_elapsed | 19239 | +| total_timesteps | 5957632 | +| train/ | | +| approx_kl | 2.3475547 | +| clip_fraction | 0.472 | +| clip_range | 0.2 | +| entropy_loss | -0.365 | +| explained_variance | -2.04 | +| learning_rate | 0.0001 | +| loss | -0.0725 | +| n_updates | 118700 | +| policy_gradient_loss | -0.0679 | +| value_loss | 0.000482 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.448 | +| time/ | | +| fps | 309 | +| iterations | 5819 | +| time_elapsed | 19242 | +| total_timesteps | 5958656 | +| train/ | | +| approx_kl | 3.454383 | +| clip_fraction | 0.486 | +| clip_range | 0.2 | +| entropy_loss | -0.405 | +| explained_variance | -6.48 | +| learning_rate | 0.0001 | +| loss | -0.0794 | +| n_updates | 118710 | +| policy_gradient_loss | 0.111 | +| value_loss | 0.000429 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.448 | +| time/ | | +| fps | 309 | +| iterations | 5820 | +| time_elapsed | 19246 | +| total_timesteps | 5959680 | +| train/ | | +| approx_kl | 4.2352715 | +| clip_fraction | 0.485 | +| clip_range | 0.2 | +| entropy_loss | -0.397 | +| explained_variance | -0.787 | +| learning_rate | 0.0001 | +| loss | -0.07 | +| n_updates | 118720 | +| policy_gradient_loss | -0.0654 | +| value_loss | 0.000425 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.447 | +| time/ | | +| fps | 309 | +| iterations | 5821 | +| time_elapsed | 19249 | +| total_timesteps | 5960704 | +| train/ | | +| approx_kl | 2.0088964 | +| clip_fraction | 0.507 | +| clip_range | 0.2 | +| entropy_loss | -0.396 | +| explained_variance | -1.27 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 118730 | +| policy_gradient_loss | -0.0713 | +| value_loss | 0.000502 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.448 | +| time/ | | +| fps | 309 | +| iterations | 5822 | +| time_elapsed | 19252 | +| total_timesteps | 5961728 | +| train/ | | +| approx_kl | 1.7978134 | +| clip_fraction | 0.49 | +| clip_range | 0.2 | +| entropy_loss | -0.442 | +| explained_variance | -1.74 | +| learning_rate | 0.0001 | +| loss | -0.0926 | +| n_updates | 118740 | +| policy_gradient_loss | -0.0695 | +| value_loss | 0.000458 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.448 | +| time/ | | +| fps | 309 | +| iterations | 5823 | +| time_elapsed | 19256 | +| total_timesteps | 5962752 | +| train/ | | +| approx_kl | 1.9145554 | +| clip_fraction | 0.467 | +| clip_range | 0.2 | +| entropy_loss | -0.385 | +| explained_variance | -0.851 | +| learning_rate | 0.0001 | +| loss | -0.0875 | +| n_updates | 118750 | +| policy_gradient_loss | -0.0726 | +| value_loss | 0.000492 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.448 | +| time/ | | +| fps | 309 | +| iterations | 5824 | +| time_elapsed | 19259 | +| total_timesteps | 5963776 | +| train/ | | +| approx_kl | 2.323351 | +| clip_fraction | 0.485 | +| clip_range | 0.2 | +| entropy_loss | -0.371 | +| explained_variance | -2.8 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 118760 | +| policy_gradient_loss | -0.0715 | +| value_loss | 0.000579 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.447 | +| time/ | | +| fps | 309 | +| iterations | 5825 | +| time_elapsed | 19262 | +| total_timesteps | 5964800 | +| train/ | | +| approx_kl | 1.9848688 | +| clip_fraction | 0.532 | +| clip_range | 0.2 | +| entropy_loss | -0.443 | +| explained_variance | -1.62 | +| learning_rate | 0.0001 | +| loss | -0.117 | +| n_updates | 118770 | +| policy_gradient_loss | -0.0773 | +| value_loss | 0.000491 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.447 | +| time/ | | +| fps | 309 | +| iterations | 5826 | +| time_elapsed | 19266 | +| total_timesteps | 5965824 | +| train/ | | +| approx_kl | 2.5887384 | +| clip_fraction | 0.459 | +| clip_range | 0.2 | +| entropy_loss | -0.387 | +| explained_variance | -1.8 | +| learning_rate | 0.0001 | +| loss | -0.082 | +| n_updates | 118780 | +| policy_gradient_loss | -0.0648 | +| value_loss | 0.000394 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.449 | +| time/ | | +| fps | 309 | +| iterations | 5827 | +| time_elapsed | 19269 | +| total_timesteps | 5966848 | +| train/ | | +| approx_kl | 2.970907 | +| clip_fraction | 0.499 | +| clip_range | 0.2 | +| entropy_loss | -0.386 | +| explained_variance | -2.04 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 118790 | +| policy_gradient_loss | -0.0783 | +| value_loss | 0.000405 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.442 | +| time/ | | +| fps | 309 | +| iterations | 5828 | +| time_elapsed | 19272 | +| total_timesteps | 5967872 | +| train/ | | +| approx_kl | 2.0081816 | +| clip_fraction | 0.485 | +| clip_range | 0.2 | +| entropy_loss | -0.4 | +| explained_variance | -0.851 | +| learning_rate | 0.0001 | +| loss | -0.106 | +| n_updates | 118800 | +| policy_gradient_loss | -0.0713 | +| value_loss | 0.000512 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.442 | +| time/ | | +| fps | 309 | +| iterations | 5829 | +| time_elapsed | 19276 | +| total_timesteps | 5968896 | +| train/ | | +| approx_kl | 2.0122304 | +| clip_fraction | 0.463 | +| clip_range | 0.2 | +| entropy_loss | -0.374 | +| explained_variance | -1.37 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 118810 | +| policy_gradient_loss | -0.0711 | +| value_loss | 0.000508 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | 0.444 | +| time/ | | +| fps | 309 | +| iterations | 5830 | +| time_elapsed | 19279 | +| total_timesteps | 5969920 | +| train/ | | +| approx_kl | 1.999088 | +| clip_fraction | 0.526 | +| clip_range | 0.2 | +| entropy_loss | -0.436 | +| explained_variance | -1.43 | +| learning_rate | 0.0001 | +| loss | -0.0984 | +| n_updates | 118820 | +| policy_gradient_loss | -0.0769 | +| value_loss | 0.000399 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | 0.444 | +| time/ | | +| fps | 309 | +| iterations | 5831 | +| time_elapsed | 19282 | +| total_timesteps | 5970944 | +| train/ | | +| approx_kl | 1.9380305 | +| clip_fraction | 0.479 | +| clip_range | 0.2 | +| entropy_loss | -0.38 | +| explained_variance | -1.16 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 118830 | +| policy_gradient_loss | -0.0653 | +| value_loss | 0.000394 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | 0.444 | +| time/ | | +| fps | 309 | +| iterations | 5832 | +| time_elapsed | 19285 | +| total_timesteps | 5971968 | +| train/ | | +| approx_kl | 2.1252503 | +| clip_fraction | 0.508 | +| clip_range | 0.2 | +| entropy_loss | -0.442 | +| explained_variance | -0.556 | +| learning_rate | 0.0001 | +| loss | -0.0865 | +| n_updates | 118840 | +| policy_gradient_loss | -0.0776 | +| value_loss | 0.000418 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | 0.444 | +| time/ | | +| fps | 309 | +| iterations | 5833 | +| time_elapsed | 19288 | +| total_timesteps | 5972992 | +| train/ | | +| approx_kl | 2.184229 | +| clip_fraction | 0.495 | +| clip_range | 0.2 | +| entropy_loss | -0.388 | +| explained_variance | -1.29 | +| learning_rate | 0.0001 | +| loss | -0.0773 | +| n_updates | 118850 | +| policy_gradient_loss | -0.0719 | +| value_loss | 0.000455 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | 0.444 | +| time/ | | +| fps | 309 | +| iterations | 5834 | +| time_elapsed | 19292 | +| total_timesteps | 5974016 | +| train/ | | +| approx_kl | 1.9343477 | +| clip_fraction | 0.496 | +| clip_range | 0.2 | +| entropy_loss | -0.39 | +| explained_variance | -1.15 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 118860 | +| policy_gradient_loss | -0.0761 | +| value_loss | 0.000495 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | 0.447 | +| time/ | | +| fps | 309 | +| iterations | 5835 | +| time_elapsed | 19295 | +| total_timesteps | 5975040 | +| train/ | | +| approx_kl | 1.9288415 | +| clip_fraction | 0.503 | +| clip_range | 0.2 | +| entropy_loss | -0.447 | +| explained_variance | -1.51 | +| learning_rate | 0.0001 | +| loss | -0.125 | +| n_updates | 118870 | +| policy_gradient_loss | -0.0743 | +| value_loss | 0.000519 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | 0.447 | +| time/ | | +| fps | 309 | +| iterations | 5836 | +| time_elapsed | 19298 | +| total_timesteps | 5976064 | +| train/ | | +| approx_kl | 2.7739513 | +| clip_fraction | 0.486 | +| clip_range | 0.2 | +| entropy_loss | -0.398 | +| explained_variance | -1.28 | +| learning_rate | 0.0001 | +| loss | -0.0975 | +| n_updates | 118880 | +| policy_gradient_loss | -0.0693 | +| value_loss | 0.000455 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.446 | +| time/ | | +| fps | 309 | +| iterations | 5837 | +| time_elapsed | 19301 | +| total_timesteps | 5977088 | +| train/ | | +| approx_kl | 1.6820381 | +| clip_fraction | 0.493 | +| clip_range | 0.2 | +| entropy_loss | -0.422 | +| explained_variance | -1.66 | +| learning_rate | 0.0001 | +| loss | -0.0945 | +| n_updates | 118890 | +| policy_gradient_loss | -0.0703 | +| value_loss | 0.000414 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.446 | +| time/ | | +| fps | 309 | +| iterations | 5838 | +| time_elapsed | 19305 | +| total_timesteps | 5978112 | +| train/ | | +| approx_kl | 2.1262093 | +| clip_fraction | 0.489 | +| clip_range | 0.2 | +| entropy_loss | -0.375 | +| explained_variance | -0.563 | +| learning_rate | 0.0001 | +| loss | -0.0804 | +| n_updates | 118900 | +| policy_gradient_loss | -0.0626 | +| value_loss | 0.000806 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.447 | +| time/ | | +| fps | 309 | +| iterations | 5839 | +| time_elapsed | 19308 | +| total_timesteps | 5979136 | +| train/ | | +| approx_kl | 1.6557589 | +| clip_fraction | 0.503 | +| clip_range | 0.2 | +| entropy_loss | -0.456 | +| explained_variance | -1.97 | +| learning_rate | 0.0001 | +| loss | -0.111 | +| n_updates | 118910 | +| policy_gradient_loss | -0.0765 | +| value_loss | 0.000478 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.447 | +| time/ | | +| fps | 309 | +| iterations | 5840 | +| time_elapsed | 19312 | +| total_timesteps | 5980160 | +| train/ | | +| approx_kl | 2.7332788 | +| clip_fraction | 0.503 | +| clip_range | 0.2 | +| entropy_loss | -0.43 | +| explained_variance | -2.1 | +| learning_rate | 0.0001 | +| loss | -0.119 | +| n_updates | 118920 | +| policy_gradient_loss | -0.071 | +| value_loss | 0.000608 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.448 | +| time/ | | +| fps | 309 | +| iterations | 5841 | +| time_elapsed | 19316 | +| total_timesteps | 5981184 | +| train/ | | +| approx_kl | 5.4318566 | +| clip_fraction | 0.47 | +| clip_range | 0.2 | +| entropy_loss | -0.371 | +| explained_variance | -2 | +| learning_rate | 0.0001 | +| loss | -0.0917 | +| n_updates | 118930 | +| policy_gradient_loss | -0.0685 | +| value_loss | 0.000583 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.448 | +| time/ | | +| fps | 309 | +| iterations | 5842 | +| time_elapsed | 19319 | +| total_timesteps | 5982208 | +| train/ | | +| approx_kl | 4.359049 | +| clip_fraction | 0.463 | +| clip_range | 0.2 | +| entropy_loss | -0.365 | +| explained_variance | -1.05 | +| learning_rate | 0.0001 | +| loss | -0.0739 | +| n_updates | 118940 | +| policy_gradient_loss | -0.0668 | +| value_loss | 0.000623 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.448 | +| time/ | | +| fps | 309 | +| iterations | 5843 | +| time_elapsed | 19323 | +| total_timesteps | 5983232 | +| train/ | | +| approx_kl | 3.6672976 | +| clip_fraction | 0.49 | +| clip_range | 0.2 | +| entropy_loss | -0.395 | +| explained_variance | -2.97 | +| learning_rate | 0.0001 | +| loss | -0.0814 | +| n_updates | 118950 | +| policy_gradient_loss | -0.0749 | +| value_loss | 0.000591 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.448 | +| time/ | | +| fps | 309 | +| iterations | 5844 | +| time_elapsed | 19327 | +| total_timesteps | 5984256 | +| train/ | | +| approx_kl | 3.7366922 | +| clip_fraction | 0.473 | +| clip_range | 0.2 | +| entropy_loss | -0.361 | +| explained_variance | -1.7 | +| learning_rate | 0.0001 | +| loss | -0.0992 | +| n_updates | 118960 | +| policy_gradient_loss | -0.0657 | +| value_loss | 0.000395 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.448 | +| time/ | | +| fps | 309 | +| iterations | 5845 | +| time_elapsed | 19330 | +| total_timesteps | 5985280 | +| train/ | | +| approx_kl | 2.0597167 | +| clip_fraction | 0.474 | +| clip_range | 0.2 | +| entropy_loss | -0.395 | +| explained_variance | -2.94 | +| learning_rate | 0.0001 | +| loss | -0.0894 | +| n_updates | 118970 | +| policy_gradient_loss | -0.073 | +| value_loss | 0.00047 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.447 | +| time/ | | +| fps | 309 | +| iterations | 5846 | +| time_elapsed | 19333 | +| total_timesteps | 5986304 | +| train/ | | +| approx_kl | 5.1928496 | +| clip_fraction | 0.517 | +| clip_range | 0.2 | +| entropy_loss | -0.43 | +| explained_variance | -1.33 | +| learning_rate | 0.0001 | +| loss | -0.089 | +| n_updates | 118980 | +| policy_gradient_loss | -0.0768 | +| value_loss | 0.000427 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.447 | +| time/ | | +| fps | 309 | +| iterations | 5847 | +| time_elapsed | 19336 | +| total_timesteps | 5987328 | +| train/ | | +| approx_kl | 1.9367028 | +| clip_fraction | 0.463 | +| clip_range | 0.2 | +| entropy_loss | -0.335 | +| explained_variance | -2.32 | +| learning_rate | 0.0001 | +| loss | -0.0819 | +| n_updates | 118990 | +| policy_gradient_loss | -0.0733 | +| value_loss | 0.000599 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.444 | +| time/ | | +| fps | 309 | +| iterations | 5848 | +| time_elapsed | 19340 | +| total_timesteps | 5988352 | +| train/ | | +| approx_kl | 1.804353 | +| clip_fraction | 0.507 | +| clip_range | 0.2 | +| entropy_loss | -0.434 | +| explained_variance | -4.4 | +| learning_rate | 0.0001 | +| loss | -0.0877 | +| n_updates | 119000 | +| policy_gradient_loss | -0.0745 | +| value_loss | 0.000378 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.444 | +| time/ | | +| fps | 309 | +| iterations | 5849 | +| time_elapsed | 19343 | +| total_timesteps | 5989376 | +| train/ | | +| approx_kl | 2.2579894 | +| clip_fraction | 0.508 | +| clip_range | 0.2 | +| entropy_loss | -0.407 | +| explained_variance | -0.78 | +| learning_rate | 0.0001 | +| loss | -0.0689 | +| n_updates | 119010 | +| policy_gradient_loss | -0.0673 | +| value_loss | 0.000374 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.441 | +| time/ | | +| fps | 309 | +| iterations | 5850 | +| time_elapsed | 19346 | +| total_timesteps | 5990400 | +| train/ | | +| approx_kl | 2.3635721 | +| clip_fraction | 0.513 | +| clip_range | 0.2 | +| entropy_loss | -0.424 | +| explained_variance | -4.31 | +| learning_rate | 0.0001 | +| loss | -0.0887 | +| n_updates | 119020 | +| policy_gradient_loss | -0.0754 | +| value_loss | 0.000371 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.441 | +| time/ | | +| fps | 309 | +| iterations | 5851 | +| time_elapsed | 19349 | +| total_timesteps | 5991424 | +| train/ | | +| approx_kl | 1.9060018 | +| clip_fraction | 0.47 | +| clip_range | 0.2 | +| entropy_loss | -0.338 | +| explained_variance | -1.99 | +| learning_rate | 0.0001 | +| loss | -0.0901 | +| n_updates | 119030 | +| policy_gradient_loss | -0.0681 | +| value_loss | 0.000489 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.435 | +| time/ | | +| fps | 309 | +| iterations | 5852 | +| time_elapsed | 19352 | +| total_timesteps | 5992448 | +| train/ | | +| approx_kl | 2.026097 | +| clip_fraction | 0.498 | +| clip_range | 0.2 | +| entropy_loss | -0.42 | +| explained_variance | -2.6 | +| learning_rate | 0.0001 | +| loss | -0.108 | +| n_updates | 119040 | +| policy_gradient_loss | -0.078 | +| value_loss | 0.000455 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.437 | +| time/ | | +| fps | 309 | +| iterations | 5853 | +| time_elapsed | 19356 | +| total_timesteps | 5993472 | +| train/ | | +| approx_kl | 3.0737216 | +| clip_fraction | 0.477 | +| clip_range | 0.2 | +| entropy_loss | -0.377 | +| explained_variance | -0.692 | +| learning_rate | 0.0001 | +| loss | -0.0722 | +| n_updates | 119050 | +| policy_gradient_loss | -0.0641 | +| value_loss | 0.000558 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.437 | +| time/ | | +| fps | 309 | +| iterations | 5854 | +| time_elapsed | 19359 | +| total_timesteps | 5994496 | +| train/ | | +| approx_kl | 1.9802227 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.403 | +| explained_variance | -0.538 | +| learning_rate | 0.0001 | +| loss | -0.0809 | +| n_updates | 119060 | +| policy_gradient_loss | -0.066 | +| value_loss | 0.000699 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.435 | +| time/ | | +| fps | 309 | +| iterations | 5855 | +| time_elapsed | 19362 | +| total_timesteps | 5995520 | +| train/ | | +| approx_kl | 2.1438103 | +| clip_fraction | 0.498 | +| clip_range | 0.2 | +| entropy_loss | -0.398 | +| explained_variance | -4.05 | +| learning_rate | 0.0001 | +| loss | -0.0708 | +| n_updates | 119070 | +| policy_gradient_loss | -0.0781 | +| value_loss | 0.00044 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.436 | +| time/ | | +| fps | 309 | +| iterations | 5856 | +| time_elapsed | 19366 | +| total_timesteps | 5996544 | +| train/ | | +| approx_kl | 1.9064966 | +| clip_fraction | 0.453 | +| clip_range | 0.2 | +| entropy_loss | -0.369 | +| explained_variance | -1.19 | +| learning_rate | 0.0001 | +| loss | -0.0814 | +| n_updates | 119080 | +| policy_gradient_loss | -0.0611 | +| value_loss | 0.000489 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.438 | +| time/ | | +| fps | 309 | +| iterations | 5857 | +| time_elapsed | 19369 | +| total_timesteps | 5997568 | +| train/ | | +| approx_kl | 2.1042488 | +| clip_fraction | 0.474 | +| clip_range | 0.2 | +| entropy_loss | -0.393 | +| explained_variance | -0.598 | +| learning_rate | 0.0001 | +| loss | -0.0937 | +| n_updates | 119090 | +| policy_gradient_loss | -0.0671 | +| value_loss | 0.000659 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.437 | +| time/ | | +| fps | 309 | +| iterations | 5858 | +| time_elapsed | 19373 | +| total_timesteps | 5998592 | +| train/ | | +| approx_kl | 2.1738667 | +| clip_fraction | 0.472 | +| clip_range | 0.2 | +| entropy_loss | -0.383 | +| explained_variance | -0.647 | +| learning_rate | 0.0001 | +| loss | -0.0641 | +| n_updates | 119100 | +| policy_gradient_loss | -0.0679 | +| value_loss | 0.000855 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.437 | +| time/ | | +| fps | 309 | +| iterations | 5859 | +| time_elapsed | 19376 | +| total_timesteps | 5999616 | +| train/ | | +| approx_kl | 3.1567993 | +| clip_fraction | 0.489 | +| clip_range | 0.2 | +| entropy_loss | -0.393 | +| explained_variance | -1.21 | +| learning_rate | 0.0001 | +| loss | -0.0956 | +| n_updates | 119110 | +| policy_gradient_loss | -0.0703 | +| value_loss | 0.000711 | +--------------------------------------- + +Current state: Champion.Level4.RyuVsZangief +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.437 | +| time/ | | +| fps | 309 | +| iterations | 5860 | +| time_elapsed | 19380 | +| total_timesteps | 6000640 | +| train/ | | +| approx_kl | 1.7274485 | +| clip_fraction | 0.516 | +| clip_range | 0.2 | +| entropy_loss | -0.463 | +| explained_variance | -1.61 | +| learning_rate | 0.0001 | +| loss | -0.121 | +| n_updates | 119120 | +| policy_gradient_loss | -0.0746 | +| value_loss | 0.00054 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.437 | +| time/ | | +| fps | 309 | +| iterations | 5861 | +| time_elapsed | 19384 | +| total_timesteps | 6001664 | +| train/ | | +| approx_kl | 1.9772508 | +| clip_fraction | 0.494 | +| clip_range | 0.2 | +| entropy_loss | -0.422 | +| explained_variance | -2.21 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 119130 | +| policy_gradient_loss | -0.0714 | +| value_loss | 0.000413 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.434 | +| time/ | | +| fps | 309 | +| iterations | 5862 | +| time_elapsed | 19387 | +| total_timesteps | 6002688 | +| train/ | | +| approx_kl | 2.5085297 | +| clip_fraction | 0.497 | +| clip_range | 0.2 | +| entropy_loss | -0.382 | +| explained_variance | -1.39 | +| learning_rate | 0.0001 | +| loss | -0.0892 | +| n_updates | 119140 | +| policy_gradient_loss | -0.0742 | +| value_loss | 0.000395 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.433 | +| time/ | | +| fps | 309 | +| iterations | 5863 | +| time_elapsed | 19390 | +| total_timesteps | 6003712 | +| train/ | | +| approx_kl | 1.8661828 | +| clip_fraction | 0.543 | +| clip_range | 0.2 | +| entropy_loss | -0.468 | +| explained_variance | -0.802 | +| learning_rate | 0.0001 | +| loss | -0.093 | +| n_updates | 119150 | +| policy_gradient_loss | -0.0692 | +| value_loss | 0.000334 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.426 | +| time/ | | +| fps | 309 | +| iterations | 5864 | +| time_elapsed | 19393 | +| total_timesteps | 6004736 | +| train/ | | +| approx_kl | 6.0216136 | +| clip_fraction | 0.549 | +| clip_range | 0.2 | +| entropy_loss | -0.528 | +| explained_variance | -0.159 | +| learning_rate | 0.0001 | +| loss | -0.0101 | +| n_updates | 119160 | +| policy_gradient_loss | -0.0571 | +| value_loss | 0.000393 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.426 | +| time/ | | +| fps | 309 | +| iterations | 5865 | +| time_elapsed | 19397 | +| total_timesteps | 6005760 | +| train/ | | +| approx_kl | 1.769665 | +| clip_fraction | 0.508 | +| clip_range | 0.2 | +| entropy_loss | -0.444 | +| explained_variance | -1.53 | +| learning_rate | 0.0001 | +| loss | -0.0959 | +| n_updates | 119170 | +| policy_gradient_loss | -0.0687 | +| value_loss | 0.000307 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.421 | +| time/ | | +| fps | 309 | +| iterations | 5866 | +| time_elapsed | 19400 | +| total_timesteps | 6006784 | +| train/ | | +| approx_kl | 3.78968 | +| clip_fraction | 0.602 | +| clip_range | 0.2 | +| entropy_loss | -0.587 | +| explained_variance | -0.93 | +| learning_rate | 0.0001 | +| loss | -0.074 | +| n_updates | 119180 | +| policy_gradient_loss | -0.0603 | +| value_loss | 0.000252 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.421 | +| time/ | | +| fps | 309 | +| iterations | 5867 | +| time_elapsed | 19403 | +| total_timesteps | 6007808 | +| train/ | | +| approx_kl | 2.009816 | +| clip_fraction | 0.531 | +| clip_range | 0.2 | +| entropy_loss | -0.453 | +| explained_variance | -1.06 | +| learning_rate | 0.0001 | +| loss | -0.0837 | +| n_updates | 119190 | +| policy_gradient_loss | -0.0747 | +| value_loss | 0.000538 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.421 | +| time/ | | +| fps | 309 | +| iterations | 5868 | +| time_elapsed | 19406 | +| total_timesteps | 6008832 | +| train/ | | +| approx_kl | 2.0496697 | +| clip_fraction | 0.539 | +| clip_range | 0.2 | +| entropy_loss | -0.463 | +| explained_variance | -2.75 | +| learning_rate | 0.0001 | +| loss | -0.115 | +| n_updates | 119200 | +| policy_gradient_loss | -0.0735 | +| value_loss | 0.00034 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.421 | +| time/ | | +| fps | 309 | +| iterations | 5869 | +| time_elapsed | 19409 | +| total_timesteps | 6009856 | +| train/ | | +| approx_kl | 2.069745 | +| clip_fraction | 0.53 | +| clip_range | 0.2 | +| entropy_loss | -0.492 | +| explained_variance | -0.53 | +| learning_rate | 0.0001 | +| loss | -0.0311 | +| n_updates | 119210 | +| policy_gradient_loss | -0.0606 | +| value_loss | 0.000262 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.419 | +| time/ | | +| fps | 309 | +| iterations | 5870 | +| time_elapsed | 19413 | +| total_timesteps | 6010880 | +| train/ | | +| approx_kl | 2.1352026 | +| clip_fraction | 0.568 | +| clip_range | 0.2 | +| entropy_loss | -0.55 | +| explained_variance | -2.19 | +| learning_rate | 0.0001 | +| loss | -0.0827 | +| n_updates | 119220 | +| policy_gradient_loss | -0.061 | +| value_loss | 0.000157 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.419 | +| time/ | | +| fps | 309 | +| iterations | 5871 | +| time_elapsed | 19416 | +| total_timesteps | 6011904 | +| train/ | | +| approx_kl | 1.7613249 | +| clip_fraction | 0.554 | +| clip_range | 0.2 | +| entropy_loss | -0.475 | +| explained_variance | -0.313 | +| learning_rate | 0.0001 | +| loss | -0.0547 | +| n_updates | 119230 | +| policy_gradient_loss | -0.0509 | +| value_loss | 0.000166 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.418 | +| time/ | | +| fps | 309 | +| iterations | 5872 | +| time_elapsed | 19419 | +| total_timesteps | 6012928 | +| train/ | | +| approx_kl | 2.8865123 | +| clip_fraction | 0.543 | +| clip_range | 0.2 | +| entropy_loss | -0.566 | +| explained_variance | -2.28 | +| learning_rate | 0.0001 | +| loss | -0.0965 | +| n_updates | 119240 | +| policy_gradient_loss | -0.0722 | +| value_loss | 0.000181 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.409 | +| time/ | | +| fps | 309 | +| iterations | 5873 | +| time_elapsed | 19422 | +| total_timesteps | 6013952 | +| train/ | | +| approx_kl | 1.8822955 | +| clip_fraction | 0.532 | +| clip_range | 0.2 | +| entropy_loss | -0.544 | +| explained_variance | -0.768 | +| learning_rate | 0.0001 | +| loss | -0.0719 | +| n_updates | 119250 | +| policy_gradient_loss | -0.0664 | +| value_loss | 0.000141 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.409 | +| time/ | | +| fps | 309 | +| iterations | 5874 | +| time_elapsed | 19426 | +| total_timesteps | 6014976 | +| train/ | | +| approx_kl | 1.6844559 | +| clip_fraction | 0.56 | +| clip_range | 0.2 | +| entropy_loss | -0.561 | +| explained_variance | -0.49 | +| learning_rate | 0.0001 | +| loss | -0.0957 | +| n_updates | 119260 | +| policy_gradient_loss | -0.0762 | +| value_loss | 0.000518 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.409 | +| time/ | | +| fps | 309 | +| iterations | 5875 | +| time_elapsed | 19429 | +| total_timesteps | 6016000 | +| train/ | | +| approx_kl | 1.6571091 | +| clip_fraction | 0.547 | +| clip_range | 0.2 | +| entropy_loss | -0.502 | +| explained_variance | -3.51 | +| learning_rate | 0.0001 | +| loss | -0.0709 | +| n_updates | 119270 | +| policy_gradient_loss | -0.0752 | +| value_loss | 0.000556 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.407 | +| time/ | | +| fps | 309 | +| iterations | 5876 | +| time_elapsed | 19433 | +| total_timesteps | 6017024 | +| train/ | | +| approx_kl | 1.4274786 | +| clip_fraction | 0.546 | +| clip_range | 0.2 | +| entropy_loss | -0.577 | +| explained_variance | -1.91 | +| learning_rate | 0.0001 | +| loss | -0.0955 | +| n_updates | 119280 | +| policy_gradient_loss | -0.0783 | +| value_loss | 0.000292 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.404 | +| time/ | | +| fps | 309 | +| iterations | 5877 | +| time_elapsed | 19436 | +| total_timesteps | 6018048 | +| train/ | | +| approx_kl | 2.0908875 | +| clip_fraction | 0.534 | +| clip_range | 0.2 | +| entropy_loss | -0.51 | +| explained_variance | -2.47 | +| learning_rate | 0.0001 | +| loss | -0.107 | +| n_updates | 119290 | +| policy_gradient_loss | -0.0766 | +| value_loss | 0.000198 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.398 | +| time/ | | +| fps | 309 | +| iterations | 5878 | +| time_elapsed | 19440 | +| total_timesteps | 6019072 | +| train/ | | +| approx_kl | 1.8149252 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.428 | +| explained_variance | -0.744 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 119300 | +| policy_gradient_loss | -0.0685 | +| value_loss | 0.00023 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.398 | +| time/ | | +| fps | 309 | +| iterations | 5879 | +| time_elapsed | 19443 | +| total_timesteps | 6020096 | +| train/ | | +| approx_kl | 1.593109 | +| clip_fraction | 0.51 | +| clip_range | 0.2 | +| entropy_loss | -0.468 | +| explained_variance | -1.19 | +| learning_rate | 0.0001 | +| loss | -0.0857 | +| n_updates | 119310 | +| policy_gradient_loss | -0.0717 | +| value_loss | 0.000393 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.398 | +| time/ | | +| fps | 309 | +| iterations | 5880 | +| time_elapsed | 19447 | +| total_timesteps | 6021120 | +| train/ | | +| approx_kl | 1.47091 | +| clip_fraction | 0.522 | +| clip_range | 0.2 | +| entropy_loss | -0.499 | +| explained_variance | -3.25 | +| learning_rate | 0.0001 | +| loss | -0.0845 | +| n_updates | 119320 | +| policy_gradient_loss | -0.0781 | +| value_loss | 0.000243 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.399 | +| time/ | | +| fps | 309 | +| iterations | 5881 | +| time_elapsed | 19450 | +| total_timesteps | 6022144 | +| train/ | | +| approx_kl | 1.6781557 | +| clip_fraction | 0.527 | +| clip_range | 0.2 | +| entropy_loss | -0.544 | +| explained_variance | -1.52 | +| learning_rate | 0.0001 | +| loss | -0.0883 | +| n_updates | 119330 | +| policy_gradient_loss | -0.0778 | +| value_loss | 0.000181 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.399 | +| time/ | | +| fps | 309 | +| iterations | 5882 | +| time_elapsed | 19453 | +| total_timesteps | 6023168 | +| train/ | | +| approx_kl | 3.7543793 | +| clip_fraction | 0.537 | +| clip_range | 0.2 | +| entropy_loss | -0.492 | +| explained_variance | -0.603 | +| learning_rate | 0.0001 | +| loss | -0.0732 | +| n_updates | 119340 | +| policy_gradient_loss | -0.0683 | +| value_loss | 0.000318 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.399 | +| time/ | | +| fps | 309 | +| iterations | 5883 | +| time_elapsed | 19457 | +| total_timesteps | 6024192 | +| train/ | | +| approx_kl | 1.6324555 | +| clip_fraction | 0.514 | +| clip_range | 0.2 | +| entropy_loss | -0.511 | +| explained_variance | -1.04 | +| learning_rate | 0.0001 | +| loss | -0.0998 | +| n_updates | 119350 | +| policy_gradient_loss | -0.0573 | +| value_loss | 0.000741 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.398 | +| time/ | | +| fps | 309 | +| iterations | 5884 | +| time_elapsed | 19460 | +| total_timesteps | 6025216 | +| train/ | | +| approx_kl | 1.8226424 | +| clip_fraction | 0.538 | +| clip_range | 0.2 | +| entropy_loss | -0.483 | +| explained_variance | -5.06 | +| learning_rate | 0.0001 | +| loss | -0.117 | +| n_updates | 119360 | +| policy_gradient_loss | -0.0814 | +| value_loss | 0.000647 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.398 | +| time/ | | +| fps | 309 | +| iterations | 5885 | +| time_elapsed | 19463 | +| total_timesteps | 6026240 | +| train/ | | +| approx_kl | 1.4562069 | +| clip_fraction | 0.543 | +| clip_range | 0.2 | +| entropy_loss | -0.595 | +| explained_variance | -2.09 | +| learning_rate | 0.0001 | +| loss | -0.12 | +| n_updates | 119370 | +| policy_gradient_loss | -0.0694 | +| value_loss | 0.000293 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.395 | +| time/ | | +| fps | 309 | +| iterations | 5886 | +| time_elapsed | 19466 | +| total_timesteps | 6027264 | +| train/ | | +| approx_kl | 1.8775954 | +| clip_fraction | 0.535 | +| clip_range | 0.2 | +| entropy_loss | -0.517 | +| explained_variance | -1.35 | +| learning_rate | 0.0001 | +| loss | -0.0936 | +| n_updates | 119380 | +| policy_gradient_loss | -0.0737 | +| value_loss | 0.000748 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.395 | +| time/ | | +| fps | 309 | +| iterations | 5887 | +| time_elapsed | 19469 | +| total_timesteps | 6028288 | +| train/ | | +| approx_kl | 2.1791728 | +| clip_fraction | 0.548 | +| clip_range | 0.2 | +| entropy_loss | -0.57 | +| explained_variance | -0.926 | +| learning_rate | 0.0001 | +| loss | -0.0908 | +| n_updates | 119390 | +| policy_gradient_loss | -0.0682 | +| value_loss | 0.000551 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.396 | +| time/ | | +| fps | 309 | +| iterations | 5888 | +| time_elapsed | 19473 | +| total_timesteps | 6029312 | +| train/ | | +| approx_kl | 1.4250265 | +| clip_fraction | 0.516 | +| clip_range | 0.2 | +| entropy_loss | -0.546 | +| explained_variance | -2.59 | +| learning_rate | 0.0001 | +| loss | -0.0953 | +| n_updates | 119400 | +| policy_gradient_loss | -0.0713 | +| value_loss | 0.000305 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.396 | +| time/ | | +| fps | 309 | +| iterations | 5889 | +| time_elapsed | 19476 | +| total_timesteps | 6030336 | +| train/ | | +| approx_kl | 2.2301388 | +| clip_fraction | 0.529 | +| clip_range | 0.2 | +| entropy_loss | -0.468 | +| explained_variance | -0.932 | +| learning_rate | 0.0001 | +| loss | -0.075 | +| n_updates | 119410 | +| policy_gradient_loss | -0.0754 | +| value_loss | 0.000403 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.394 | +| time/ | | +| fps | 309 | +| iterations | 5890 | +| time_elapsed | 19479 | +| total_timesteps | 6031360 | +| train/ | | +| approx_kl | 1.940573 | +| clip_fraction | 0.55 | +| clip_range | 0.2 | +| entropy_loss | -0.589 | +| explained_variance | -1.27 | +| learning_rate | 0.0001 | +| loss | -0.116 | +| n_updates | 119420 | +| policy_gradient_loss | -0.0719 | +| value_loss | 0.000293 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.394 | +| time/ | | +| fps | 309 | +| iterations | 5891 | +| time_elapsed | 19482 | +| total_timesteps | 6032384 | +| train/ | | +| approx_kl | 1.5532597 | +| clip_fraction | 0.514 | +| clip_range | 0.2 | +| entropy_loss | -0.561 | +| explained_variance | -2.82 | +| learning_rate | 0.0001 | +| loss | -0.0851 | +| n_updates | 119430 | +| policy_gradient_loss | -0.0686 | +| value_loss | 0.000163 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.396 | +| time/ | | +| fps | 309 | +| iterations | 5892 | +| time_elapsed | 19486 | +| total_timesteps | 6033408 | +| train/ | | +| approx_kl | 3.929544 | +| clip_fraction | 0.526 | +| clip_range | 0.2 | +| entropy_loss | -0.499 | +| explained_variance | -0.352 | +| learning_rate | 0.0001 | +| loss | -0.0713 | +| n_updates | 119440 | +| policy_gradient_loss | -0.0715 | +| value_loss | 0.000264 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.395 | +| time/ | | +| fps | 309 | +| iterations | 5893 | +| time_elapsed | 19489 | +| total_timesteps | 6034432 | +| train/ | | +| approx_kl | 2.1076663 | +| clip_fraction | 0.557 | +| clip_range | 0.2 | +| entropy_loss | -0.506 | +| explained_variance | -0.6 | +| learning_rate | 0.0001 | +| loss | -0.0981 | +| n_updates | 119450 | +| policy_gradient_loss | -0.0749 | +| value_loss | 0.000455 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.395 | +| time/ | | +| fps | 309 | +| iterations | 5894 | +| time_elapsed | 19492 | +| total_timesteps | 6035456 | +| train/ | | +| approx_kl | 2.3806148 | +| clip_fraction | 0.488 | +| clip_range | 0.2 | +| entropy_loss | -0.42 | +| explained_variance | -1.11 | +| learning_rate | 0.0001 | +| loss | -0.069 | +| n_updates | 119460 | +| policy_gradient_loss | -0.0663 | +| value_loss | 0.00045 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.391 | +| time/ | | +| fps | 309 | +| iterations | 5895 | +| time_elapsed | 19496 | +| total_timesteps | 6036480 | +| train/ | | +| approx_kl | 3.6238122 | +| clip_fraction | 0.568 | +| clip_range | 0.2 | +| entropy_loss | -0.47 | +| explained_variance | -2.78 | +| learning_rate | 0.0001 | +| loss | -0.085 | +| n_updates | 119470 | +| policy_gradient_loss | -0.0507 | +| value_loss | 0.000232 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.391 | +| time/ | | +| fps | 309 | +| iterations | 5896 | +| time_elapsed | 19499 | +| total_timesteps | 6037504 | +| train/ | | +| approx_kl | 2.1396968 | +| clip_fraction | 0.488 | +| clip_range | 0.2 | +| entropy_loss | -0.434 | +| explained_variance | -0.256 | +| learning_rate | 0.0001 | +| loss | -0.0762 | +| n_updates | 119480 | +| policy_gradient_loss | -0.0625 | +| value_loss | 0.000598 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.391 | +| time/ | | +| fps | 309 | +| iterations | 5897 | +| time_elapsed | 19503 | +| total_timesteps | 6038528 | +| train/ | | +| approx_kl | 1.6666512 | +| clip_fraction | 0.519 | +| clip_range | 0.2 | +| entropy_loss | -0.492 | +| explained_variance | -3.16 | +| learning_rate | 0.0001 | +| loss | -0.0875 | +| n_updates | 119490 | +| policy_gradient_loss | -0.0756 | +| value_loss | 0.000396 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.391 | +| time/ | | +| fps | 309 | +| iterations | 5898 | +| time_elapsed | 19506 | +| total_timesteps | 6039552 | +| train/ | | +| approx_kl | 2.5590687 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.401 | +| explained_variance | -0.933 | +| learning_rate | 0.0001 | +| loss | -0.0841 | +| n_updates | 119500 | +| policy_gradient_loss | -0.0648 | +| value_loss | 0.000631 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.389 | +| time/ | | +| fps | 309 | +| iterations | 5899 | +| time_elapsed | 19509 | +| total_timesteps | 6040576 | +| train/ | | +| approx_kl | 1.5589191 | +| clip_fraction | 0.529 | +| clip_range | 0.2 | +| entropy_loss | -0.49 | +| explained_variance | -1.95 | +| learning_rate | 0.0001 | +| loss | -0.0789 | +| n_updates | 119510 | +| policy_gradient_loss | -0.0726 | +| value_loss | 0.000357 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.389 | +| time/ | | +| fps | 309 | +| iterations | 5900 | +| time_elapsed | 19513 | +| total_timesteps | 6041600 | +| train/ | | +| approx_kl | 1.7312399 | +| clip_fraction | 0.473 | +| clip_range | 0.2 | +| entropy_loss | -0.401 | +| explained_variance | -1.28 | +| learning_rate | 0.0001 | +| loss | -0.00165 | +| n_updates | 119520 | +| policy_gradient_loss | -0.0545 | +| value_loss | 0.000446 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.388 | +| time/ | | +| fps | 309 | +| iterations | 5901 | +| time_elapsed | 19516 | +| total_timesteps | 6042624 | +| train/ | | +| approx_kl | 2.3345137 | +| clip_fraction | 0.543 | +| clip_range | 0.2 | +| entropy_loss | -0.482 | +| explained_variance | -1.26 | +| learning_rate | 0.0001 | +| loss | -0.0964 | +| n_updates | 119530 | +| policy_gradient_loss | -0.0663 | +| value_loss | 0.000543 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 309 | +| iterations | 5902 | +| time_elapsed | 19519 | +| total_timesteps | 6043648 | +| train/ | | +| approx_kl | 1.5700173 | +| clip_fraction | 0.525 | +| clip_range | 0.2 | +| entropy_loss | -0.516 | +| explained_variance | -2.13 | +| learning_rate | 0.0001 | +| loss | -0.0908 | +| n_updates | 119540 | +| policy_gradient_loss | -0.0743 | +| value_loss | 0.000215 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 309 | +| iterations | 5903 | +| time_elapsed | 19522 | +| total_timesteps | 6044672 | +| train/ | | +| approx_kl | 2.2363954 | +| clip_fraction | 0.501 | +| clip_range | 0.2 | +| entropy_loss | -0.394 | +| explained_variance | -0.882 | +| learning_rate | 0.0001 | +| loss | -0.0815 | +| n_updates | 119550 | +| policy_gradient_loss | -0.0684 | +| value_loss | 0.000415 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 309 | +| iterations | 5904 | +| time_elapsed | 19525 | +| total_timesteps | 6045696 | +| train/ | | +| approx_kl | 4.236677 | +| clip_fraction | 0.539 | +| clip_range | 0.2 | +| entropy_loss | -0.474 | +| explained_variance | -2.62 | +| learning_rate | 0.0001 | +| loss | -0.0717 | +| n_updates | 119560 | +| policy_gradient_loss | -0.0719 | +| value_loss | 0.000363 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 309 | +| iterations | 5905 | +| time_elapsed | 19529 | +| total_timesteps | 6046720 | +| train/ | | +| approx_kl | 1.6963315 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.405 | +| explained_variance | -1.85 | +| learning_rate | 0.0001 | +| loss | -0.0842 | +| n_updates | 119570 | +| policy_gradient_loss | -0.0674 | +| value_loss | 0.000488 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 309 | +| iterations | 5906 | +| time_elapsed | 19532 | +| total_timesteps | 6047744 | +| train/ | | +| approx_kl | 1.7822187 | +| clip_fraction | 0.529 | +| clip_range | 0.2 | +| entropy_loss | -0.503 | +| explained_variance | -1.1 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 119580 | +| policy_gradient_loss | -0.0771 | +| value_loss | 0.00044 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 309 | +| iterations | 5907 | +| time_elapsed | 19535 | +| total_timesteps | 6048768 | +| train/ | | +| approx_kl | 1.9006097 | +| clip_fraction | 0.515 | +| clip_range | 0.2 | +| entropy_loss | -0.46 | +| explained_variance | -0.885 | +| learning_rate | 0.0001 | +| loss | -0.0918 | +| n_updates | 119590 | +| policy_gradient_loss | -0.0708 | +| value_loss | 0.000427 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 309 | +| iterations | 5908 | +| time_elapsed | 19538 | +| total_timesteps | 6049792 | +| train/ | | +| approx_kl | 1.9959553 | +| clip_fraction | 0.531 | +| clip_range | 0.2 | +| entropy_loss | -0.508 | +| explained_variance | -3.11 | +| learning_rate | 0.0001 | +| loss | -0.0967 | +| n_updates | 119600 | +| policy_gradient_loss | -0.0706 | +| value_loss | 0.000418 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 309 | +| iterations | 5909 | +| time_elapsed | 19542 | +| total_timesteps | 6050816 | +| train/ | | +| approx_kl | 1.7537835 | +| clip_fraction | 0.492 | +| clip_range | 0.2 | +| entropy_loss | -0.424 | +| explained_variance | -2.17 | +| learning_rate | 0.0001 | +| loss | -0.0922 | +| n_updates | 119610 | +| policy_gradient_loss | -0.073 | +| value_loss | 0.000361 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 309 | +| iterations | 5910 | +| time_elapsed | 19545 | +| total_timesteps | 6051840 | +| train/ | | +| approx_kl | 1.5420494 | +| clip_fraction | 0.498 | +| clip_range | 0.2 | +| entropy_loss | -0.497 | +| explained_variance | -2.27 | +| learning_rate | 0.0001 | +| loss | -0.123 | +| n_updates | 119620 | +| policy_gradient_loss | -0.0652 | +| value_loss | 0.000303 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 309 | +| iterations | 5911 | +| time_elapsed | 19549 | +| total_timesteps | 6052864 | +| train/ | | +| approx_kl | 2.533547 | +| clip_fraction | 0.505 | +| clip_range | 0.2 | +| entropy_loss | -0.423 | +| explained_variance | -3.2 | +| learning_rate | 0.0001 | +| loss | -0.0791 | +| n_updates | 119630 | +| policy_gradient_loss | -0.0672 | +| value_loss | 0.000376 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 309 | +| iterations | 5912 | +| time_elapsed | 19552 | +| total_timesteps | 6053888 | +| train/ | | +| approx_kl | 2.228038 | +| clip_fraction | 0.532 | +| clip_range | 0.2 | +| entropy_loss | -0.487 | +| explained_variance | -1.65 | +| learning_rate | 0.0001 | +| loss | -0.0792 | +| n_updates | 119640 | +| policy_gradient_loss | -0.0742 | +| value_loss | 0.000349 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 309 | +| iterations | 5913 | +| time_elapsed | 19556 | +| total_timesteps | 6054912 | +| train/ | | +| approx_kl | 1.7169449 | +| clip_fraction | 0.528 | +| clip_range | 0.2 | +| entropy_loss | -0.496 | +| explained_variance | -5.73 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 119650 | +| policy_gradient_loss | -0.0858 | +| value_loss | 0.000171 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 309 | +| iterations | 5914 | +| time_elapsed | 19559 | +| total_timesteps | 6055936 | +| train/ | | +| approx_kl | 1.6355847 | +| clip_fraction | 0.496 | +| clip_range | 0.2 | +| entropy_loss | -0.442 | +| explained_variance | -1.04 | +| learning_rate | 0.0001 | +| loss | -0.0736 | +| n_updates | 119660 | +| policy_gradient_loss | -0.0539 | +| value_loss | 0.000117 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 309 | +| iterations | 5915 | +| time_elapsed | 19562 | +| total_timesteps | 6056960 | +| train/ | | +| approx_kl | 1.8391058 | +| clip_fraction | 0.493 | +| clip_range | 0.2 | +| entropy_loss | -0.417 | +| explained_variance | -0.571 | +| learning_rate | 0.0001 | +| loss | -0.051 | +| n_updates | 119670 | +| policy_gradient_loss | -0.0609 | +| value_loss | 0.000294 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 309 | +| iterations | 5916 | +| time_elapsed | 19566 | +| total_timesteps | 6057984 | +| train/ | | +| approx_kl | 3.005125 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.384 | +| explained_variance | -0.706 | +| learning_rate | 0.0001 | +| loss | -0.0561 | +| n_updates | 119680 | +| policy_gradient_loss | -0.0589 | +| value_loss | 0.000423 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 309 | +| iterations | 5917 | +| time_elapsed | 19569 | +| total_timesteps | 6059008 | +| train/ | | +| approx_kl | 1.9559793 | +| clip_fraction | 0.469 | +| clip_range | 0.2 | +| entropy_loss | -0.424 | +| explained_variance | -0.351 | +| learning_rate | 0.0001 | +| loss | -0.083 | +| n_updates | 119690 | +| policy_gradient_loss | -0.0607 | +| value_loss | 0.00052 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 309 | +| iterations | 5918 | +| time_elapsed | 19573 | +| total_timesteps | 6060032 | +| train/ | | +| approx_kl | 1.780035 | +| clip_fraction | 0.518 | +| clip_range | 0.2 | +| entropy_loss | -0.483 | +| explained_variance | -0.394 | +| learning_rate | 0.0001 | +| loss | -0.0959 | +| n_updates | 119700 | +| policy_gradient_loss | -0.0703 | +| value_loss | 0.000687 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 309 | +| iterations | 5919 | +| time_elapsed | 19576 | +| total_timesteps | 6061056 | +| train/ | | +| approx_kl | 2.2671795 | +| clip_fraction | 0.504 | +| clip_range | 0.2 | +| entropy_loss | -0.401 | +| explained_variance | -2.13 | +| learning_rate | 0.0001 | +| loss | -0.0935 | +| n_updates | 119710 | +| policy_gradient_loss | -0.0734 | +| value_loss | 0.000714 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 309 | +| iterations | 5920 | +| time_elapsed | 19579 | +| total_timesteps | 6062080 | +| train/ | | +| approx_kl | 1.8496633 | +| clip_fraction | 0.512 | +| clip_range | 0.2 | +| entropy_loss | -0.415 | +| explained_variance | -2.64 | +| learning_rate | 0.0001 | +| loss | -0.1 | +| n_updates | 119720 | +| policy_gradient_loss | -0.0699 | +| value_loss | 0.000546 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 309 | +| iterations | 5921 | +| time_elapsed | 19582 | +| total_timesteps | 6063104 | +| train/ | | +| approx_kl | 2.2541888 | +| clip_fraction | 0.493 | +| clip_range | 0.2 | +| entropy_loss | -0.354 | +| explained_variance | -1.55 | +| learning_rate | 0.0001 | +| loss | -0.0892 | +| n_updates | 119730 | +| policy_gradient_loss | -0.0462 | +| value_loss | 0.000275 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 309 | +| iterations | 5922 | +| time_elapsed | 19585 | +| total_timesteps | 6064128 | +| train/ | | +| approx_kl | 2.9791417 | +| clip_fraction | 0.517 | +| clip_range | 0.2 | +| entropy_loss | -0.439 | +| explained_variance | -1.76 | +| learning_rate | 0.0001 | +| loss | -0.0851 | +| n_updates | 119740 | +| policy_gradient_loss | -0.0724 | +| value_loss | 0.000352 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 309 | +| iterations | 5923 | +| time_elapsed | 19589 | +| total_timesteps | 6065152 | +| train/ | | +| approx_kl | 1.6931808 | +| clip_fraction | 0.496 | +| clip_range | 0.2 | +| entropy_loss | -0.449 | +| explained_variance | -1.26 | +| learning_rate | 0.0001 | +| loss | -0.106 | +| n_updates | 119750 | +| policy_gradient_loss | -0.0723 | +| value_loss | 0.000237 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 309 | +| iterations | 5924 | +| time_elapsed | 19592 | +| total_timesteps | 6066176 | +| train/ | | +| approx_kl | 1.6613269 | +| clip_fraction | 0.533 | +| clip_range | 0.2 | +| entropy_loss | -0.501 | +| explained_variance | -3.79 | +| learning_rate | 0.0001 | +| loss | -0.0869 | +| n_updates | 119760 | +| policy_gradient_loss | -0.0717 | +| value_loss | 0.000101 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 309 | +| iterations | 5925 | +| time_elapsed | 19595 | +| total_timesteps | 6067200 | +| train/ | | +| approx_kl | 2.0333123 | +| clip_fraction | 0.499 | +| clip_range | 0.2 | +| entropy_loss | -0.446 | +| explained_variance | -0.772 | +| learning_rate | 0.0001 | +| loss | -0.0817 | +| n_updates | 119770 | +| policy_gradient_loss | -0.0484 | +| value_loss | 0.000172 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 309 | +| iterations | 5926 | +| time_elapsed | 19598 | +| total_timesteps | 6068224 | +| train/ | | +| approx_kl | 1.5923604 | +| clip_fraction | 0.504 | +| clip_range | 0.2 | +| entropy_loss | -0.454 | +| explained_variance | -0.841 | +| learning_rate | 0.0001 | +| loss | -0.111 | +| n_updates | 119780 | +| policy_gradient_loss | -0.0728 | +| value_loss | 0.00041 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 309 | +| iterations | 5927 | +| time_elapsed | 19602 | +| total_timesteps | 6069248 | +| train/ | | +| approx_kl | 1.9869576 | +| clip_fraction | 0.511 | +| clip_range | 0.2 | +| entropy_loss | -0.448 | +| explained_variance | -1.79 | +| learning_rate | 0.0001 | +| loss | -0.112 | +| n_updates | 119790 | +| policy_gradient_loss | -0.0766 | +| value_loss | 0.000491 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 309 | +| iterations | 5928 | +| time_elapsed | 19605 | +| total_timesteps | 6070272 | +| train/ | | +| approx_kl | 5.3653345 | +| clip_fraction | 0.568 | +| clip_range | 0.2 | +| entropy_loss | -0.463 | +| explained_variance | -2.24 | +| learning_rate | 0.0001 | +| loss | -0.0905 | +| n_updates | 119800 | +| policy_gradient_loss | -0.0707 | +| value_loss | 0.000758 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 309 | +| iterations | 5929 | +| time_elapsed | 19608 | +| total_timesteps | 6071296 | +| train/ | | +| approx_kl | 1.6915032 | +| clip_fraction | 0.491 | +| clip_range | 0.2 | +| entropy_loss | -0.44 | +| explained_variance | -3.61 | +| learning_rate | 0.0001 | +| loss | -0.106 | +| n_updates | 119810 | +| policy_gradient_loss | -0.0752 | +| value_loss | 0.000544 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 309 | +| iterations | 5930 | +| time_elapsed | 19612 | +| total_timesteps | 6072320 | +| train/ | | +| approx_kl | 2.299995 | +| clip_fraction | 0.489 | +| clip_range | 0.2 | +| entropy_loss | -0.361 | +| explained_variance | -1.33 | +| learning_rate | 0.0001 | +| loss | -0.0784 | +| n_updates | 119820 | +| policy_gradient_loss | -0.065 | +| value_loss | 0.000677 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 309 | +| iterations | 5931 | +| time_elapsed | 19615 | +| total_timesteps | 6073344 | +| train/ | | +| approx_kl | 2.0212762 | +| clip_fraction | 0.504 | +| clip_range | 0.2 | +| entropy_loss | -0.425 | +| explained_variance | -2.25 | +| learning_rate | 0.0001 | +| loss | -0.0751 | +| n_updates | 119830 | +| policy_gradient_loss | -0.0771 | +| value_loss | 0.000571 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 309 | +| iterations | 5932 | +| time_elapsed | 19618 | +| total_timesteps | 6074368 | +| train/ | | +| approx_kl | 3.436376 | +| clip_fraction | 0.497 | +| clip_range | 0.2 | +| entropy_loss | -0.432 | +| explained_variance | -2.63 | +| learning_rate | 0.0001 | +| loss | -0.0835 | +| n_updates | 119840 | +| policy_gradient_loss | -0.0716 | +| value_loss | 0.000315 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 309 | +| iterations | 5933 | +| time_elapsed | 19622 | +| total_timesteps | 6075392 | +| train/ | | +| approx_kl | 1.9533517 | +| clip_fraction | 0.513 | +| clip_range | 0.2 | +| entropy_loss | -0.428 | +| explained_variance | -1.6 | +| learning_rate | 0.0001 | +| loss | -0.0941 | +| n_updates | 119850 | +| policy_gradient_loss | -0.0679 | +| value_loss | 0.000185 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 309 | +| iterations | 5934 | +| time_elapsed | 19625 | +| total_timesteps | 6076416 | +| train/ | | +| approx_kl | 1.8388984 | +| clip_fraction | 0.513 | +| clip_range | 0.2 | +| entropy_loss | -0.508 | +| explained_variance | -0.653 | +| learning_rate | 0.0001 | +| loss | -0.098 | +| n_updates | 119860 | +| policy_gradient_loss | -0.0667 | +| value_loss | 0.000462 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 309 | +| iterations | 5935 | +| time_elapsed | 19628 | +| total_timesteps | 6077440 | +| train/ | | +| approx_kl | 1.9332038 | +| clip_fraction | 0.515 | +| clip_range | 0.2 | +| entropy_loss | -0.52 | +| explained_variance | -1.35 | +| learning_rate | 0.0001 | +| loss | -0.0974 | +| n_updates | 119870 | +| policy_gradient_loss | -0.0615 | +| value_loss | 0.00025 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 309 | +| iterations | 5936 | +| time_elapsed | 19632 | +| total_timesteps | 6078464 | +| train/ | | +| approx_kl | 3.7339873 | +| clip_fraction | 0.507 | +| clip_range | 0.2 | +| entropy_loss | -0.442 | +| explained_variance | -0.704 | +| learning_rate | 0.0001 | +| loss | -0.0934 | +| n_updates | 119880 | +| policy_gradient_loss | -0.0627 | +| value_loss | 0.000343 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 309 | +| iterations | 5937 | +| time_elapsed | 19635 | +| total_timesteps | 6079488 | +| train/ | | +| approx_kl | 2.1011424 | +| clip_fraction | 0.526 | +| clip_range | 0.2 | +| entropy_loss | -0.448 | +| explained_variance | -1.07 | +| learning_rate | 0.0001 | +| loss | -0.0922 | +| n_updates | 119890 | +| policy_gradient_loss | -0.0719 | +| value_loss | 0.000507 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 309 | +| iterations | 5938 | +| time_elapsed | 19638 | +| total_timesteps | 6080512 | +| train/ | | +| approx_kl | 3.0731034 | +| clip_fraction | 0.515 | +| clip_range | 0.2 | +| entropy_loss | -0.4 | +| explained_variance | -3.29 | +| learning_rate | 0.0001 | +| loss | -0.0911 | +| n_updates | 119900 | +| policy_gradient_loss | -0.0783 | +| value_loss | 0.000349 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 309 | +| iterations | 5939 | +| time_elapsed | 19641 | +| total_timesteps | 6081536 | +| train/ | | +| approx_kl | 2.1492825 | +| clip_fraction | 0.504 | +| clip_range | 0.2 | +| entropy_loss | -0.427 | +| explained_variance | -0.946 | +| learning_rate | 0.0001 | +| loss | -0.108 | +| n_updates | 119910 | +| policy_gradient_loss | -0.0716 | +| value_loss | 0.00057 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 309 | +| iterations | 5940 | +| time_elapsed | 19644 | +| total_timesteps | 6082560 | +| train/ | | +| approx_kl | 2.1896086 | +| clip_fraction | 0.491 | +| clip_range | 0.2 | +| entropy_loss | -0.398 | +| explained_variance | -1.18 | +| learning_rate | 0.0001 | +| loss | -0.0888 | +| n_updates | 119920 | +| policy_gradient_loss | -0.0687 | +| value_loss | 0.000532 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 309 | +| iterations | 5941 | +| time_elapsed | 19648 | +| total_timesteps | 6083584 | +| train/ | | +| approx_kl | 1.9340311 | +| clip_fraction | 0.509 | +| clip_range | 0.2 | +| entropy_loss | -0.467 | +| explained_variance | -2.12 | +| learning_rate | 0.0001 | +| loss | -0.0764 | +| n_updates | 119930 | +| policy_gradient_loss | -0.0796 | +| value_loss | 0.000343 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 309 | +| iterations | 5942 | +| time_elapsed | 19651 | +| total_timesteps | 6084608 | +| train/ | | +| approx_kl | 1.9111382 | +| clip_fraction | 0.497 | +| clip_range | 0.2 | +| entropy_loss | -0.43 | +| explained_variance | -2.26 | +| learning_rate | 0.0001 | +| loss | -0.107 | +| n_updates | 119940 | +| policy_gradient_loss | -0.0697 | +| value_loss | 0.000194 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 309 | +| iterations | 5943 | +| time_elapsed | 19654 | +| total_timesteps | 6085632 | +| train/ | | +| approx_kl | 1.5448955 | +| clip_fraction | 0.51 | +| clip_range | 0.2 | +| entropy_loss | -0.505 | +| explained_variance | -0.687 | +| learning_rate | 0.0001 | +| loss | -0.0903 | +| n_updates | 119950 | +| policy_gradient_loss | -0.0708 | +| value_loss | 0.000277 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.78e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 309 | +| iterations | 5944 | +| time_elapsed | 19657 | +| total_timesteps | 6086656 | +| train/ | | +| approx_kl | 1.8628784 | +| clip_fraction | 0.468 | +| clip_range | 0.2 | +| entropy_loss | -0.413 | +| explained_variance | -1.21 | +| learning_rate | 0.0001 | +| loss | 0.0955 | +| n_updates | 119960 | +| policy_gradient_loss | -0.0618 | +| value_loss | 0.000325 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.78e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 309 | +| iterations | 5945 | +| time_elapsed | 19660 | +| total_timesteps | 6087680 | +| train/ | | +| approx_kl | 1.4129984 | +| clip_fraction | 0.451 | +| clip_range | 0.2 | +| entropy_loss | -0.435 | +| explained_variance | -1.23 | +| learning_rate | 0.0001 | +| loss | -0.107 | +| n_updates | 119970 | +| policy_gradient_loss | -0.0649 | +| value_loss | 0.000141 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 309 | +| iterations | 5946 | +| time_elapsed | 19664 | +| total_timesteps | 6088704 | +| train/ | | +| approx_kl | 1.3750201 | +| clip_fraction | 0.503 | +| clip_range | 0.2 | +| entropy_loss | -0.485 | +| explained_variance | -0.286 | +| learning_rate | 0.0001 | +| loss | -0.0692 | +| n_updates | 119980 | +| policy_gradient_loss | -0.0621 | +| value_loss | 0.000217 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 309 | +| iterations | 5947 | +| time_elapsed | 19667 | +| total_timesteps | 6089728 | +| train/ | | +| approx_kl | 1.293606 | +| clip_fraction | 0.463 | +| clip_range | 0.2 | +| entropy_loss | -0.428 | +| explained_variance | -1.04 | +| learning_rate | 0.0001 | +| loss | -0.108 | +| n_updates | 119990 | +| policy_gradient_loss | -0.0686 | +| value_loss | 0.000244 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 309 | +| iterations | 5948 | +| time_elapsed | 19671 | +| total_timesteps | 6090752 | +| train/ | | +| approx_kl | 2.4446933 | +| clip_fraction | 0.499 | +| clip_range | 0.2 | +| entropy_loss | -0.421 | +| explained_variance | -1.36 | +| learning_rate | 0.0001 | +| loss | -0.107 | +| n_updates | 120000 | +| policy_gradient_loss | -0.0581 | +| value_loss | 0.000675 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 309 | +| iterations | 5949 | +| time_elapsed | 19674 | +| total_timesteps | 6091776 | +| train/ | | +| approx_kl | 3.129038 | +| clip_fraction | 0.466 | +| clip_range | 0.2 | +| entropy_loss | -0.338 | +| explained_variance | -2.48 | +| learning_rate | 0.0001 | +| loss | -0.0942 | +| n_updates | 120010 | +| policy_gradient_loss | -0.0562 | +| value_loss | 0.000597 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 309 | +| iterations | 5950 | +| time_elapsed | 19678 | +| total_timesteps | 6092800 | +| train/ | | +| approx_kl | 2.488235 | +| clip_fraction | 0.51 | +| clip_range | 0.2 | +| entropy_loss | -0.416 | +| explained_variance | -2.29 | +| learning_rate | 0.0001 | +| loss | -0.063 | +| n_updates | 120020 | +| policy_gradient_loss | -0.0694 | +| value_loss | 0.000864 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 309 | +| iterations | 5951 | +| time_elapsed | 19681 | +| total_timesteps | 6093824 | +| train/ | | +| approx_kl | 2.3265657 | +| clip_fraction | 0.485 | +| clip_range | 0.2 | +| entropy_loss | -0.34 | +| explained_variance | -3.38 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 120030 | +| policy_gradient_loss | -0.0705 | +| value_loss | 0.00075 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 309 | +| iterations | 5952 | +| time_elapsed | 19684 | +| total_timesteps | 6094848 | +| train/ | | +| approx_kl | 2.0425181 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.394 | +| explained_variance | -0.867 | +| learning_rate | 0.0001 | +| loss | -0.0994 | +| n_updates | 120040 | +| policy_gradient_loss | -0.0646 | +| value_loss | 0.000413 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 309 | +| iterations | 5953 | +| time_elapsed | 19688 | +| total_timesteps | 6095872 | +| train/ | | +| approx_kl | 2.1169748 | +| clip_fraction | 0.535 | +| clip_range | 0.2 | +| entropy_loss | -0.468 | +| explained_variance | -0.768 | +| learning_rate | 0.0001 | +| loss | -0.0906 | +| n_updates | 120050 | +| policy_gradient_loss | -0.0729 | +| value_loss | 0.000507 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 309 | +| iterations | 5954 | +| time_elapsed | 19691 | +| total_timesteps | 6096896 | +| train/ | | +| approx_kl | 2.147675 | +| clip_fraction | 0.484 | +| clip_range | 0.2 | +| entropy_loss | -0.415 | +| explained_variance | -4.48 | +| learning_rate | 0.0001 | +| loss | -0.0493 | +| n_updates | 120060 | +| policy_gradient_loss | -0.0577 | +| value_loss | 0.000263 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 309 | +| iterations | 5955 | +| time_elapsed | 19694 | +| total_timesteps | 6097920 | +| train/ | | +| approx_kl | 2.556428 | +| clip_fraction | 0.476 | +| clip_range | 0.2 | +| entropy_loss | -0.415 | +| explained_variance | -1.15 | +| learning_rate | 0.0001 | +| loss | -0.0623 | +| n_updates | 120070 | +| policy_gradient_loss | -0.0651 | +| value_loss | 0.000271 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 309 | +| iterations | 5956 | +| time_elapsed | 19697 | +| total_timesteps | 6098944 | +| train/ | | +| approx_kl | 1.916249 | +| clip_fraction | 0.456 | +| clip_range | 0.2 | +| entropy_loss | -0.408 | +| explained_variance | -2.61 | +| learning_rate | 0.0001 | +| loss | -0.1 | +| n_updates | 120080 | +| policy_gradient_loss | -0.066 | +| value_loss | 0.000267 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 309 | +| iterations | 5957 | +| time_elapsed | 19701 | +| total_timesteps | 6099968 | +| train/ | | +| approx_kl | 1.969389 | +| clip_fraction | 0.514 | +| clip_range | 0.2 | +| entropy_loss | -0.438 | +| explained_variance | -0.887 | +| learning_rate | 0.0001 | +| loss | -0.0866 | +| n_updates | 120090 | +| policy_gradient_loss | -0.0709 | +| value_loss | 0.000419 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 309 | +| iterations | 5958 | +| time_elapsed | 19704 | +| total_timesteps | 6100992 | +| train/ | | +| approx_kl | 1.9397464 | +| clip_fraction | 0.492 | +| clip_range | 0.2 | +| entropy_loss | -0.408 | +| explained_variance | -2.31 | +| learning_rate | 0.0001 | +| loss | -0.0979 | +| n_updates | 120100 | +| policy_gradient_loss | -0.0642 | +| value_loss | 0.000329 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 309 | +| iterations | 5959 | +| time_elapsed | 19707 | +| total_timesteps | 6102016 | +| train/ | | +| approx_kl | 1.4429011 | +| clip_fraction | 0.484 | +| clip_range | 0.2 | +| entropy_loss | -0.445 | +| explained_variance | -1.42 | +| learning_rate | 0.0001 | +| loss | -0.1 | +| n_updates | 120110 | +| policy_gradient_loss | -0.0619 | +| value_loss | 0.000174 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 309 | +| iterations | 5960 | +| time_elapsed | 19710 | +| total_timesteps | 6103040 | +| train/ | | +| approx_kl | 1.5894961 | +| clip_fraction | 0.51 | +| clip_range | 0.2 | +| entropy_loss | -0.468 | +| explained_variance | -0.733 | +| learning_rate | 0.0001 | +| loss | -0.113 | +| n_updates | 120120 | +| policy_gradient_loss | -0.0685 | +| value_loss | 0.000211 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.304 | +| time/ | | +| fps | 309 | +| iterations | 5961 | +| time_elapsed | 19714 | +| total_timesteps | 6104064 | +| train/ | | +| approx_kl | 1.5261108 | +| clip_fraction | 0.528 | +| clip_range | 0.2 | +| entropy_loss | -0.514 | +| explained_variance | -1.05 | +| learning_rate | 0.0001 | +| loss | -0.0907 | +| n_updates | 120130 | +| policy_gradient_loss | -0.0728 | +| value_loss | 0.000529 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.304 | +| time/ | | +| fps | 309 | +| iterations | 5962 | +| time_elapsed | 19717 | +| total_timesteps | 6105088 | +| train/ | | +| approx_kl | 1.533978 | +| clip_fraction | 0.503 | +| clip_range | 0.2 | +| entropy_loss | -0.488 | +| explained_variance | -2.08 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 120140 | +| policy_gradient_loss | -0.0705 | +| value_loss | 0.000311 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 309 | +| iterations | 5963 | +| time_elapsed | 19720 | +| total_timesteps | 6106112 | +| train/ | | +| approx_kl | 1.5660566 | +| clip_fraction | 0.515 | +| clip_range | 0.2 | +| entropy_loss | -0.466 | +| explained_variance | -1.16 | +| learning_rate | 0.0001 | +| loss | -0.0866 | +| n_updates | 120150 | +| policy_gradient_loss | -0.0711 | +| value_loss | 0.000168 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.295 | +| time/ | | +| fps | 309 | +| iterations | 5964 | +| time_elapsed | 19724 | +| total_timesteps | 6107136 | +| train/ | | +| approx_kl | 2.3905158 | +| clip_fraction | 0.493 | +| clip_range | 0.2 | +| entropy_loss | -0.401 | +| explained_variance | -1.34 | +| learning_rate | 0.0001 | +| loss | -0.11 | +| n_updates | 120160 | +| policy_gradient_loss | -0.0691 | +| value_loss | 0.000395 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.29 | +| time/ | | +| fps | 309 | +| iterations | 5965 | +| time_elapsed | 19727 | +| total_timesteps | 6108160 | +| train/ | | +| approx_kl | 1.7528536 | +| clip_fraction | 0.463 | +| clip_range | 0.2 | +| entropy_loss | -0.43 | +| explained_variance | -0.723 | +| learning_rate | 0.0001 | +| loss | -0.0897 | +| n_updates | 120170 | +| policy_gradient_loss | -0.062 | +| value_loss | 0.00033 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.29 | +| time/ | | +| fps | 309 | +| iterations | 5966 | +| time_elapsed | 19731 | +| total_timesteps | 6109184 | +| train/ | | +| approx_kl | 1.6615328 | +| clip_fraction | 0.484 | +| clip_range | 0.2 | +| entropy_loss | -0.459 | +| explained_variance | -1.05 | +| learning_rate | 0.0001 | +| loss | -0.0978 | +| n_updates | 120180 | +| policy_gradient_loss | -0.0694 | +| value_loss | 0.000371 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.29 | +| time/ | | +| fps | 309 | +| iterations | 5967 | +| time_elapsed | 19734 | +| total_timesteps | 6110208 | +| train/ | | +| approx_kl | 2.594968 | +| clip_fraction | 0.529 | +| clip_range | 0.2 | +| entropy_loss | -0.405 | +| explained_variance | -0.954 | +| learning_rate | 0.0001 | +| loss | -0.0864 | +| n_updates | 120190 | +| policy_gradient_loss | -0.0793 | +| value_loss | 0.000906 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.287 | +| time/ | | +| fps | 309 | +| iterations | 5968 | +| time_elapsed | 19738 | +| total_timesteps | 6111232 | +| train/ | | +| approx_kl | 2.5151913 | +| clip_fraction | 0.505 | +| clip_range | 0.2 | +| entropy_loss | -0.383 | +| explained_variance | -4.86 | +| learning_rate | 0.0001 | +| loss | -0.0809 | +| n_updates | 120200 | +| policy_gradient_loss | -0.0766 | +| value_loss | 0.00067 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.287 | +| time/ | | +| fps | 309 | +| iterations | 5969 | +| time_elapsed | 19741 | +| total_timesteps | 6112256 | +| train/ | | +| approx_kl | 2.4873424 | +| clip_fraction | 0.5 | +| clip_range | 0.2 | +| entropy_loss | -0.378 | +| explained_variance | -3.64 | +| learning_rate | 0.0001 | +| loss | -0.0942 | +| n_updates | 120210 | +| policy_gradient_loss | -0.0475 | +| value_loss | 0.00069 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.288 | +| time/ | | +| fps | 309 | +| iterations | 5970 | +| time_elapsed | 19744 | +| total_timesteps | 6113280 | +| train/ | | +| approx_kl | 1.8691505 | +| clip_fraction | 0.522 | +| clip_range | 0.2 | +| entropy_loss | -0.446 | +| explained_variance | -1.46 | +| learning_rate | 0.0001 | +| loss | -0.0913 | +| n_updates | 120220 | +| policy_gradient_loss | -0.0636 | +| value_loss | 0.0005 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.288 | +| time/ | | +| fps | 309 | +| iterations | 5971 | +| time_elapsed | 19748 | +| total_timesteps | 6114304 | +| train/ | | +| approx_kl | 1.4325598 | +| clip_fraction | 0.484 | +| clip_range | 0.2 | +| entropy_loss | -0.411 | +| explained_variance | -0.616 | +| learning_rate | 0.0001 | +| loss | -0.0928 | +| n_updates | 120230 | +| policy_gradient_loss | -0.0614 | +| value_loss | 0.000481 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.281 | +| time/ | | +| fps | 309 | +| iterations | 5972 | +| time_elapsed | 19751 | +| total_timesteps | 6115328 | +| train/ | | +| approx_kl | 2.3656547 | +| clip_fraction | 0.507 | +| clip_range | 0.2 | +| entropy_loss | -0.475 | +| explained_variance | -2.59 | +| learning_rate | 0.0001 | +| loss | -0.0671 | +| n_updates | 120240 | +| policy_gradient_loss | -0.0668 | +| value_loss | 0.000202 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.281 | +| time/ | | +| fps | 309 | +| iterations | 5973 | +| time_elapsed | 19754 | +| total_timesteps | 6116352 | +| train/ | | +| approx_kl | 1.4832814 | +| clip_fraction | 0.461 | +| clip_range | 0.2 | +| entropy_loss | -0.414 | +| explained_variance | -1.33 | +| learning_rate | 0.0001 | +| loss | -0.109 | +| n_updates | 120250 | +| policy_gradient_loss | -0.0666 | +| value_loss | 0.000154 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 309 | +| iterations | 5974 | +| time_elapsed | 19757 | +| total_timesteps | 6117376 | +| train/ | | +| approx_kl | 1.8688782 | +| clip_fraction | 0.522 | +| clip_range | 0.2 | +| entropy_loss | -0.455 | +| explained_variance | -0.483 | +| learning_rate | 0.0001 | +| loss | -0.107 | +| n_updates | 120260 | +| policy_gradient_loss | -0.0741 | +| value_loss | 0.000453 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 309 | +| iterations | 5975 | +| time_elapsed | 19761 | +| total_timesteps | 6118400 | +| train/ | | +| approx_kl | 1.7768686 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.414 | +| explained_variance | -2.91 | +| learning_rate | 0.0001 | +| loss | -0.0683 | +| n_updates | 120270 | +| policy_gradient_loss | -0.0657 | +| value_loss | 0.000462 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.276 | +| time/ | | +| fps | 309 | +| iterations | 5976 | +| time_elapsed | 19764 | +| total_timesteps | 6119424 | +| train/ | | +| approx_kl | 3.1726797 | +| clip_fraction | 0.486 | +| clip_range | 0.2 | +| entropy_loss | -0.414 | +| explained_variance | -0.773 | +| learning_rate | 0.0001 | +| loss | -0.105 | +| n_updates | 120280 | +| policy_gradient_loss | -0.0579 | +| value_loss | 0.000571 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.27 | +| time/ | | +| fps | 309 | +| iterations | 5977 | +| time_elapsed | 19767 | +| total_timesteps | 6120448 | +| train/ | | +| approx_kl | 1.7481742 | +| clip_fraction | 0.491 | +| clip_range | 0.2 | +| entropy_loss | -0.453 | +| explained_variance | -1.09 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 120290 | +| policy_gradient_loss | -0.0613 | +| value_loss | 0.000314 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.27 | +| time/ | | +| fps | 309 | +| iterations | 5978 | +| time_elapsed | 19770 | +| total_timesteps | 6121472 | +| train/ | | +| approx_kl | 1.473599 | +| clip_fraction | 0.45 | +| clip_range | 0.2 | +| entropy_loss | -0.401 | +| explained_variance | -0.754 | +| learning_rate | 0.0001 | +| loss | -0.0793 | +| n_updates | 120300 | +| policy_gradient_loss | -0.0621 | +| value_loss | 0.000404 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.265 | +| time/ | | +| fps | 309 | +| iterations | 5979 | +| time_elapsed | 19773 | +| total_timesteps | 6122496 | +| train/ | | +| approx_kl | 1.4919951 | +| clip_fraction | 0.488 | +| clip_range | 0.2 | +| entropy_loss | -0.42 | +| explained_variance | -1.2 | +| learning_rate | 0.0001 | +| loss | -0.0991 | +| n_updates | 120310 | +| policy_gradient_loss | -0.0728 | +| value_loss | 0.000356 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.269 | +| time/ | | +| fps | 309 | +| iterations | 5980 | +| time_elapsed | 19776 | +| total_timesteps | 6123520 | +| train/ | | +| approx_kl | 2.4266512 | +| clip_fraction | 0.495 | +| clip_range | 0.2 | +| entropy_loss | -0.367 | +| explained_variance | -2.34 | +| learning_rate | 0.0001 | +| loss | -0.0682 | +| n_updates | 120320 | +| policy_gradient_loss | -0.0585 | +| value_loss | 0.000426 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.269 | +| time/ | | +| fps | 309 | +| iterations | 5981 | +| time_elapsed | 19780 | +| total_timesteps | 6124544 | +| train/ | | +| approx_kl | 2.1643739 | +| clip_fraction | 0.494 | +| clip_range | 0.2 | +| entropy_loss | -0.354 | +| explained_variance | -0.483 | +| learning_rate | 0.0001 | +| loss | -0.0837 | +| n_updates | 120330 | +| policy_gradient_loss | -0.0672 | +| value_loss | 0.00104 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.269 | +| time/ | | +| fps | 309 | +| iterations | 5982 | +| time_elapsed | 19783 | +| total_timesteps | 6125568 | +| train/ | | +| approx_kl | 2.8401508 | +| clip_fraction | 0.468 | +| clip_range | 0.2 | +| entropy_loss | -0.421 | +| explained_variance | -3.39 | +| learning_rate | 0.0001 | +| loss | -0.0551 | +| n_updates | 120340 | +| policy_gradient_loss | -0.0636 | +| value_loss | 0.000461 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.266 | +| time/ | | +| fps | 309 | +| iterations | 5983 | +| time_elapsed | 19786 | +| total_timesteps | 6126592 | +| train/ | | +| approx_kl | 1.7304368 | +| clip_fraction | 0.494 | +| clip_range | 0.2 | +| entropy_loss | -0.41 | +| explained_variance | -0.478 | +| learning_rate | 0.0001 | +| loss | -0.0837 | +| n_updates | 120350 | +| policy_gradient_loss | -0.0639 | +| value_loss | 0.000348 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.266 | +| time/ | | +| fps | 309 | +| iterations | 5984 | +| time_elapsed | 19790 | +| total_timesteps | 6127616 | +| train/ | | +| approx_kl | 1.5435958 | +| clip_fraction | 0.469 | +| clip_range | 0.2 | +| entropy_loss | -0.388 | +| explained_variance | -3.74 | +| learning_rate | 0.0001 | +| loss | -0.0914 | +| n_updates | 120360 | +| policy_gradient_loss | -0.061 | +| value_loss | 0.000221 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.266 | +| time/ | | +| fps | 309 | +| iterations | 5985 | +| time_elapsed | 19793 | +| total_timesteps | 6128640 | +| train/ | | +| approx_kl | 1.8290961 | +| clip_fraction | 0.501 | +| clip_range | 0.2 | +| entropy_loss | -0.402 | +| explained_variance | -0.641 | +| learning_rate | 0.0001 | +| loss | -0.0859 | +| n_updates | 120370 | +| policy_gradient_loss | -0.0715 | +| value_loss | 0.000437 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.268 | +| time/ | | +| fps | 309 | +| iterations | 5986 | +| time_elapsed | 19797 | +| total_timesteps | 6129664 | +| train/ | | +| approx_kl | 2.5063214 | +| clip_fraction | 0.496 | +| clip_range | 0.2 | +| entropy_loss | -0.4 | +| explained_variance | -0.835 | +| learning_rate | 0.0001 | +| loss | -0.0977 | +| n_updates | 120380 | +| policy_gradient_loss | -0.0659 | +| value_loss | 0.000477 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.268 | +| time/ | | +| fps | 309 | +| iterations | 5987 | +| time_elapsed | 19801 | +| total_timesteps | 6130688 | +| train/ | | +| approx_kl | 2.536311 | +| clip_fraction | 0.453 | +| clip_range | 0.2 | +| entropy_loss | -0.298 | +| explained_variance | -1.44 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 120390 | +| policy_gradient_loss | -0.0587 | +| value_loss | 0.000786 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.267 | +| time/ | | +| fps | 309 | +| iterations | 5988 | +| time_elapsed | 19804 | +| total_timesteps | 6131712 | +| train/ | | +| approx_kl | 2.4866564 | +| clip_fraction | 0.466 | +| clip_range | 0.2 | +| entropy_loss | -0.364 | +| explained_variance | -1.65 | +| learning_rate | 0.0001 | +| loss | -0.0679 | +| n_updates | 120400 | +| policy_gradient_loss | -0.067 | +| value_loss | 0.000528 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.267 | +| time/ | | +| fps | 309 | +| iterations | 5989 | +| time_elapsed | 19808 | +| total_timesteps | 6132736 | +| train/ | | +| approx_kl | 2.673194 | +| clip_fraction | 0.455 | +| clip_range | 0.2 | +| entropy_loss | -0.322 | +| explained_variance | -1.26 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 120410 | +| policy_gradient_loss | -0.0664 | +| value_loss | 0.000554 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.269 | +| time/ | | +| fps | 309 | +| iterations | 5990 | +| time_elapsed | 19811 | +| total_timesteps | 6133760 | +| train/ | | +| approx_kl | 2.943795 | +| clip_fraction | 0.52 | +| clip_range | 0.2 | +| entropy_loss | -0.408 | +| explained_variance | -0.956 | +| learning_rate | 0.0001 | +| loss | -0.113 | +| n_updates | 120420 | +| policy_gradient_loss | -0.0754 | +| value_loss | 0.000472 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.269 | +| time/ | | +| fps | 309 | +| iterations | 5991 | +| time_elapsed | 19814 | +| total_timesteps | 6134784 | +| train/ | | +| approx_kl | 2.3829646 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.353 | +| explained_variance | -1.54 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 120430 | +| policy_gradient_loss | -0.0687 | +| value_loss | 0.000614 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.271 | +| time/ | | +| fps | 309 | +| iterations | 5992 | +| time_elapsed | 19817 | +| total_timesteps | 6135808 | +| train/ | | +| approx_kl | 1.8906785 | +| clip_fraction | 0.47 | +| clip_range | 0.2 | +| entropy_loss | -0.4 | +| explained_variance | -4.53 | +| learning_rate | 0.0001 | +| loss | -0.0833 | +| n_updates | 120440 | +| policy_gradient_loss | -0.0712 | +| value_loss | 0.000336 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.267 | +| time/ | | +| fps | 309 | +| iterations | 5993 | +| time_elapsed | 19820 | +| total_timesteps | 6136832 | +| train/ | | +| approx_kl | 1.8239741 | +| clip_fraction | 0.478 | +| clip_range | 0.2 | +| entropy_loss | -0.386 | +| explained_variance | -6.28 | +| learning_rate | 0.0001 | +| loss | -0.0982 | +| n_updates | 120450 | +| policy_gradient_loss | -0.0718 | +| value_loss | 0.000234 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.267 | +| time/ | | +| fps | 309 | +| iterations | 5994 | +| time_elapsed | 19824 | +| total_timesteps | 6137856 | +| train/ | | +| approx_kl | 1.6307192 | +| clip_fraction | 0.456 | +| clip_range | 0.2 | +| entropy_loss | -0.368 | +| explained_variance | -0.459 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 120460 | +| policy_gradient_loss | -0.0623 | +| value_loss | 0.000315 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.267 | +| time/ | | +| fps | 309 | +| iterations | 5995 | +| time_elapsed | 19827 | +| total_timesteps | 6138880 | +| train/ | | +| approx_kl | 2.242922 | +| clip_fraction | 0.514 | +| clip_range | 0.2 | +| entropy_loss | -0.371 | +| explained_variance | -1.19 | +| learning_rate | 0.0001 | +| loss | -0.0935 | +| n_updates | 120470 | +| policy_gradient_loss | -0.062 | +| value_loss | 0.000336 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.78e+03 | +| ep_rew_mean | 0.269 | +| time/ | | +| fps | 309 | +| iterations | 5996 | +| time_elapsed | 19830 | +| total_timesteps | 6139904 | +| train/ | | +| approx_kl | 2.5712938 | +| clip_fraction | 0.49 | +| clip_range | 0.2 | +| entropy_loss | -0.345 | +| explained_variance | -3.84 | +| learning_rate | 0.0001 | +| loss | -0.0955 | +| n_updates | 120480 | +| policy_gradient_loss | -0.0688 | +| value_loss | 0.00049 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.78e+03 | +| ep_rew_mean | 0.269 | +| time/ | | +| fps | 309 | +| iterations | 5997 | +| time_elapsed | 19833 | +| total_timesteps | 6140928 | +| train/ | | +| approx_kl | 1.7043058 | +| clip_fraction | 0.466 | +| clip_range | 0.2 | +| entropy_loss | -0.396 | +| explained_variance | -1.59 | +| learning_rate | 0.0001 | +| loss | 0.0275 | +| n_updates | 120490 | +| policy_gradient_loss | -0.0512 | +| value_loss | 0.000466 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.269 | +| time/ | | +| fps | 309 | +| iterations | 5998 | +| time_elapsed | 19837 | +| total_timesteps | 6141952 | +| train/ | | +| approx_kl | 2.0460963 | +| clip_fraction | 0.496 | +| clip_range | 0.2 | +| entropy_loss | -0.41 | +| explained_variance | -1.68 | +| learning_rate | 0.0001 | +| loss | -0.0899 | +| n_updates | 120500 | +| policy_gradient_loss | -0.0698 | +| value_loss | 0.000382 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.268 | +| time/ | | +| fps | 309 | +| iterations | 5999 | +| time_elapsed | 19840 | +| total_timesteps | 6142976 | +| train/ | | +| approx_kl | 2.2447114 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.388 | +| explained_variance | -1.93 | +| learning_rate | 0.0001 | +| loss | -0.0857 | +| n_updates | 120510 | +| policy_gradient_loss | -0.0661 | +| value_loss | 0.000365 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.276 | +| time/ | | +| fps | 309 | +| iterations | 6000 | +| time_elapsed | 19843 | +| total_timesteps | 6144000 | +| train/ | | +| approx_kl | 12.240467 | +| clip_fraction | 0.493 | +| clip_range | 0.2 | +| entropy_loss | -0.406 | +| explained_variance | -0.833 | +| learning_rate | 0.0001 | +| loss | -0.0656 | +| n_updates | 120520 | +| policy_gradient_loss | -0.0585 | +| value_loss | 0.0006 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.271 | +| time/ | | +| fps | 309 | +| iterations | 6001 | +| time_elapsed | 19847 | +| total_timesteps | 6145024 | +| train/ | | +| approx_kl | 2.5624113 | +| clip_fraction | 0.517 | +| clip_range | 0.2 | +| entropy_loss | -0.361 | +| explained_variance | -1.05 | +| learning_rate | 0.0001 | +| loss | -0.0818 | +| n_updates | 120530 | +| policy_gradient_loss | -0.0701 | +| value_loss | 0.00087 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.271 | +| time/ | | +| fps | 309 | +| iterations | 6002 | +| time_elapsed | 19850 | +| total_timesteps | 6146048 | +| train/ | | +| approx_kl | 2.2066503 | +| clip_fraction | 0.465 | +| clip_range | 0.2 | +| entropy_loss | -0.332 | +| explained_variance | -4.78 | +| learning_rate | 0.0001 | +| loss | -0.0971 | +| n_updates | 120540 | +| policy_gradient_loss | -0.0655 | +| value_loss | 0.000622 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.269 | +| time/ | | +| fps | 309 | +| iterations | 6003 | +| time_elapsed | 19854 | +| total_timesteps | 6147072 | +| train/ | | +| approx_kl | 2.221176 | +| clip_fraction | 0.458 | +| clip_range | 0.2 | +| entropy_loss | -0.335 | +| explained_variance | -2.03 | +| learning_rate | 0.0001 | +| loss | -0.0539 | +| n_updates | 120550 | +| policy_gradient_loss | -0.0567 | +| value_loss | 0.000368 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.269 | +| time/ | | +| fps | 309 | +| iterations | 6004 | +| time_elapsed | 19857 | +| total_timesteps | 6148096 | +| train/ | | +| approx_kl | 2.1942353 | +| clip_fraction | 0.494 | +| clip_range | 0.2 | +| entropy_loss | -0.384 | +| explained_variance | -2.36 | +| learning_rate | 0.0001 | +| loss | -0.0708 | +| n_updates | 120560 | +| policy_gradient_loss | -0.0607 | +| value_loss | 0.000243 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.267 | +| time/ | | +| fps | 309 | +| iterations | 6005 | +| time_elapsed | 19861 | +| total_timesteps | 6149120 | +| train/ | | +| approx_kl | 3.820328 | +| clip_fraction | 0.505 | +| clip_range | 0.2 | +| entropy_loss | -0.437 | +| explained_variance | -0.552 | +| learning_rate | 0.0001 | +| loss | -0.0835 | +| n_updates | 120570 | +| policy_gradient_loss | -0.0653 | +| value_loss | 0.000271 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.267 | +| time/ | | +| fps | 309 | +| iterations | 6006 | +| time_elapsed | 19864 | +| total_timesteps | 6150144 | +| train/ | | +| approx_kl | 1.4277655 | +| clip_fraction | 0.449 | +| clip_range | 0.2 | +| entropy_loss | -0.404 | +| explained_variance | -1.34 | +| learning_rate | 0.0001 | +| loss | -0.0631 | +| n_updates | 120580 | +| policy_gradient_loss | -0.0586 | +| value_loss | 0.000198 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.26 | +| time/ | | +| fps | 309 | +| iterations | 6007 | +| time_elapsed | 19867 | +| total_timesteps | 6151168 | +| train/ | | +| approx_kl | 2.0596359 | +| clip_fraction | 0.515 | +| clip_range | 0.2 | +| entropy_loss | -0.477 | +| explained_variance | -2.52 | +| learning_rate | 0.0001 | +| loss | -0.086 | +| n_updates | 120590 | +| policy_gradient_loss | -0.0707 | +| value_loss | 0.000164 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.258 | +| time/ | | +| fps | 309 | +| iterations | 6008 | +| time_elapsed | 19871 | +| total_timesteps | 6152192 | +| train/ | | +| approx_kl | 2.1869369 | +| clip_fraction | 0.472 | +| clip_range | 0.2 | +| entropy_loss | -0.371 | +| explained_variance | -0.278 | +| learning_rate | 0.0001 | +| loss | -0.0742 | +| n_updates | 120600 | +| policy_gradient_loss | -0.0657 | +| value_loss | 0.000517 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.258 | +| time/ | | +| fps | 309 | +| iterations | 6009 | +| time_elapsed | 19874 | +| total_timesteps | 6153216 | +| train/ | | +| approx_kl | 1.9962696 | +| clip_fraction | 0.489 | +| clip_range | 0.2 | +| entropy_loss | -0.398 | +| explained_variance | -2.26 | +| learning_rate | 0.0001 | +| loss | -0.0826 | +| n_updates | 120610 | +| policy_gradient_loss | -0.063 | +| value_loss | 0.000617 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.257 | +| time/ | | +| fps | 309 | +| iterations | 6010 | +| time_elapsed | 19877 | +| total_timesteps | 6154240 | +| train/ | | +| approx_kl | 2.6968265 | +| clip_fraction | 0.477 | +| clip_range | 0.2 | +| entropy_loss | -0.373 | +| explained_variance | -3.36 | +| learning_rate | 0.0001 | +| loss | -0.0565 | +| n_updates | 120620 | +| policy_gradient_loss | -0.0626 | +| value_loss | 0.000559 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.257 | +| time/ | | +| fps | 309 | +| iterations | 6011 | +| time_elapsed | 19880 | +| total_timesteps | 6155264 | +| train/ | | +| approx_kl | 2.3005934 | +| clip_fraction | 0.466 | +| clip_range | 0.2 | +| entropy_loss | -0.361 | +| explained_variance | -1.28 | +| learning_rate | 0.0001 | +| loss | -0.0714 | +| n_updates | 120630 | +| policy_gradient_loss | -0.0579 | +| value_loss | 0.000371 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.256 | +| time/ | | +| fps | 309 | +| iterations | 6012 | +| time_elapsed | 19883 | +| total_timesteps | 6156288 | +| train/ | | +| approx_kl | 2.55862 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.323 | +| explained_variance | -3.18 | +| learning_rate | 0.0001 | +| loss | -0.0847 | +| n_updates | 120640 | +| policy_gradient_loss | -0.0737 | +| value_loss | 0.000489 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.258 | +| time/ | | +| fps | 309 | +| iterations | 6013 | +| time_elapsed | 19887 | +| total_timesteps | 6157312 | +| train/ | | +| approx_kl | 2.5053368 | +| clip_fraction | 0.448 | +| clip_range | 0.2 | +| entropy_loss | -0.361 | +| explained_variance | -0.444 | +| learning_rate | 0.0001 | +| loss | -0.0605 | +| n_updates | 120650 | +| policy_gradient_loss | -0.0535 | +| value_loss | 0.000563 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.258 | +| time/ | | +| fps | 309 | +| iterations | 6014 | +| time_elapsed | 19890 | +| total_timesteps | 6158336 | +| train/ | | +| approx_kl | 2.681075 | +| clip_fraction | 0.502 | +| clip_range | 0.2 | +| entropy_loss | -0.357 | +| explained_variance | -1.97 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 120660 | +| policy_gradient_loss | -0.065 | +| value_loss | 0.000636 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.26 | +| time/ | | +| fps | 309 | +| iterations | 6015 | +| time_elapsed | 19893 | +| total_timesteps | 6159360 | +| train/ | | +| approx_kl | 1.9629672 | +| clip_fraction | 0.485 | +| clip_range | 0.2 | +| entropy_loss | -0.394 | +| explained_variance | -1.43 | +| learning_rate | 0.0001 | +| loss | -0.117 | +| n_updates | 120670 | +| policy_gradient_loss | -0.0703 | +| value_loss | 0.000487 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.259 | +| time/ | | +| fps | 309 | +| iterations | 6016 | +| time_elapsed | 19896 | +| total_timesteps | 6160384 | +| train/ | | +| approx_kl | 2.7683923 | +| clip_fraction | 0.489 | +| clip_range | 0.2 | +| entropy_loss | -0.396 | +| explained_variance | -1.01 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 120680 | +| policy_gradient_loss | -0.066 | +| value_loss | 0.000735 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.259 | +| time/ | | +| fps | 309 | +| iterations | 6017 | +| time_elapsed | 19899 | +| total_timesteps | 6161408 | +| train/ | | +| approx_kl | 1.6200953 | +| clip_fraction | 0.467 | +| clip_range | 0.2 | +| entropy_loss | -0.38 | +| explained_variance | -1.6 | +| learning_rate | 0.0001 | +| loss | -0.0945 | +| n_updates | 120690 | +| policy_gradient_loss | -0.0655 | +| value_loss | 0.000476 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.26 | +| time/ | | +| fps | 309 | +| iterations | 6018 | +| time_elapsed | 19903 | +| total_timesteps | 6162432 | +| train/ | | +| approx_kl | 3.0708518 | +| clip_fraction | 0.491 | +| clip_range | 0.2 | +| entropy_loss | -0.362 | +| explained_variance | -1.3 | +| learning_rate | 0.0001 | +| loss | -0.0819 | +| n_updates | 120700 | +| policy_gradient_loss | -0.0718 | +| value_loss | 0.00064 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.26 | +| time/ | | +| fps | 309 | +| iterations | 6019 | +| time_elapsed | 19907 | +| total_timesteps | 6163456 | +| train/ | | +| approx_kl | 1.8437966 | +| clip_fraction | 0.468 | +| clip_range | 0.2 | +| entropy_loss | -0.411 | +| explained_variance | -0.936 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 120710 | +| policy_gradient_loss | -0.0627 | +| value_loss | 0.000389 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.262 | +| time/ | | +| fps | 309 | +| iterations | 6020 | +| time_elapsed | 19910 | +| total_timesteps | 6164480 | +| train/ | | +| approx_kl | 3.3959904 | +| clip_fraction | 0.519 | +| clip_range | 0.2 | +| entropy_loss | -0.403 | +| explained_variance | -2.58 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 120720 | +| policy_gradient_loss | -0.0668 | +| value_loss | 0.000477 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.255 | +| time/ | | +| fps | 309 | +| iterations | 6021 | +| time_elapsed | 19913 | +| total_timesteps | 6165504 | +| train/ | | +| approx_kl | 1.9659595 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.405 | +| explained_variance | -1.72 | +| learning_rate | 0.0001 | +| loss | -0.0953 | +| n_updates | 120730 | +| policy_gradient_loss | -0.0656 | +| value_loss | 0.000399 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.255 | +| time/ | | +| fps | 309 | +| iterations | 6022 | +| time_elapsed | 19917 | +| total_timesteps | 6166528 | +| train/ | | +| approx_kl | 2.3066916 | +| clip_fraction | 0.5 | +| clip_range | 0.2 | +| entropy_loss | -0.425 | +| explained_variance | -0.993 | +| learning_rate | 0.0001 | +| loss | -0.0727 | +| n_updates | 120740 | +| policy_gradient_loss | -0.0649 | +| value_loss | 0.000406 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.258 | +| time/ | | +| fps | 309 | +| iterations | 6023 | +| time_elapsed | 19920 | +| total_timesteps | 6167552 | +| train/ | | +| approx_kl | 1.9689674 | +| clip_fraction | 0.47 | +| clip_range | 0.2 | +| entropy_loss | -0.39 | +| explained_variance | -2.19 | +| learning_rate | 0.0001 | +| loss | -0.0609 | +| n_updates | 120750 | +| policy_gradient_loss | -0.0629 | +| value_loss | 0.000382 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.258 | +| time/ | | +| fps | 309 | +| iterations | 6024 | +| time_elapsed | 19924 | +| total_timesteps | 6168576 | +| train/ | | +| approx_kl | 4.0324316 | +| clip_fraction | 0.517 | +| clip_range | 0.2 | +| entropy_loss | -0.423 | +| explained_variance | -2.35 | +| learning_rate | 0.0001 | +| loss | -0.0794 | +| n_updates | 120760 | +| policy_gradient_loss | -0.0706 | +| value_loss | 0.000393 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.254 | +| time/ | | +| fps | 309 | +| iterations | 6025 | +| time_elapsed | 19928 | +| total_timesteps | 6169600 | +| train/ | | +| approx_kl | 2.5154948 | +| clip_fraction | 0.506 | +| clip_range | 0.2 | +| entropy_loss | -0.375 | +| explained_variance | -0.856 | +| learning_rate | 0.0001 | +| loss | -0.0655 | +| n_updates | 120770 | +| policy_gradient_loss | -0.0683 | +| value_loss | 0.000561 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.253 | +| time/ | | +| fps | 309 | +| iterations | 6026 | +| time_elapsed | 19931 | +| total_timesteps | 6170624 | +| train/ | | +| approx_kl | 1.9100615 | +| clip_fraction | 0.513 | +| clip_range | 0.2 | +| entropy_loss | -0.449 | +| explained_variance | -1.43 | +| learning_rate | 0.0001 | +| loss | -0.0933 | +| n_updates | 120780 | +| policy_gradient_loss | -0.0717 | +| value_loss | 0.000609 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.254 | +| time/ | | +| fps | 309 | +| iterations | 6027 | +| time_elapsed | 19934 | +| total_timesteps | 6171648 | +| train/ | | +| approx_kl | 2.271183 | +| clip_fraction | 0.513 | +| clip_range | 0.2 | +| entropy_loss | -0.414 | +| explained_variance | -0.827 | +| learning_rate | 0.0001 | +| loss | -0.109 | +| n_updates | 120790 | +| policy_gradient_loss | -0.071 | +| value_loss | 0.000783 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.254 | +| time/ | | +| fps | 309 | +| iterations | 6028 | +| time_elapsed | 19937 | +| total_timesteps | 6172672 | +| train/ | | +| approx_kl | 1.3985085 | +| clip_fraction | 0.497 | +| clip_range | 0.2 | +| entropy_loss | -0.434 | +| explained_variance | -0.989 | +| learning_rate | 0.0001 | +| loss | -0.095 | +| n_updates | 120800 | +| policy_gradient_loss | -0.0716 | +| value_loss | 0.000671 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.252 | +| time/ | | +| fps | 309 | +| iterations | 6029 | +| time_elapsed | 19940 | +| total_timesteps | 6173696 | +| train/ | | +| approx_kl | 2.2895489 | +| clip_fraction | 0.536 | +| clip_range | 0.2 | +| entropy_loss | -0.455 | +| explained_variance | -1.97 | +| learning_rate | 0.0001 | +| loss | -0.114 | +| n_updates | 120810 | +| policy_gradient_loss | -0.0732 | +| value_loss | 0.000477 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.254 | +| time/ | | +| fps | 309 | +| iterations | 6030 | +| time_elapsed | 19944 | +| total_timesteps | 6174720 | +| train/ | | +| approx_kl | 1.8670404 | +| clip_fraction | 0.491 | +| clip_range | 0.2 | +| entropy_loss | -0.388 | +| explained_variance | -0.742 | +| learning_rate | 0.0001 | +| loss | -0.0983 | +| n_updates | 120820 | +| policy_gradient_loss | -0.0616 | +| value_loss | 0.000668 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.254 | +| time/ | | +| fps | 309 | +| iterations | 6031 | +| time_elapsed | 19947 | +| total_timesteps | 6175744 | +| train/ | | +| approx_kl | 1.8803582 | +| clip_fraction | 0.5 | +| clip_range | 0.2 | +| entropy_loss | -0.401 | +| explained_variance | -0.914 | +| learning_rate | 0.0001 | +| loss | -0.08 | +| n_updates | 120830 | +| policy_gradient_loss | -0.0665 | +| value_loss | 0.000543 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.255 | +| time/ | | +| fps | 309 | +| iterations | 6032 | +| time_elapsed | 19950 | +| total_timesteps | 6176768 | +| train/ | | +| approx_kl | 2.411876 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.37 | +| explained_variance | -2.56 | +| learning_rate | 0.0001 | +| loss | -0.0927 | +| n_updates | 120840 | +| policy_gradient_loss | -0.0675 | +| value_loss | 0.000334 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.255 | +| time/ | | +| fps | 309 | +| iterations | 6033 | +| time_elapsed | 19953 | +| total_timesteps | 6177792 | +| train/ | | +| approx_kl | 1.8602171 | +| clip_fraction | 0.472 | +| clip_range | 0.2 | +| entropy_loss | -0.372 | +| explained_variance | -1.67 | +| learning_rate | 0.0001 | +| loss | -0.0904 | +| n_updates | 120850 | +| policy_gradient_loss | -0.0711 | +| value_loss | 0.000253 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.257 | +| time/ | | +| fps | 309 | +| iterations | 6034 | +| time_elapsed | 19956 | +| total_timesteps | 6178816 | +| train/ | | +| approx_kl | 2.1935916 | +| clip_fraction | 0.491 | +| clip_range | 0.2 | +| entropy_loss | -0.411 | +| explained_variance | -0.425 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 120860 | +| policy_gradient_loss | -0.0563 | +| value_loss | 0.000271 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.262 | +| time/ | | +| fps | 309 | +| iterations | 6035 | +| time_elapsed | 19960 | +| total_timesteps | 6179840 | +| train/ | | +| approx_kl | 2.1971745 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.367 | +| explained_variance | -1.2 | +| learning_rate | 0.0001 | +| loss | -0.095 | +| n_updates | 120870 | +| policy_gradient_loss | -0.0705 | +| value_loss | 0.000592 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.254 | +| time/ | | +| fps | 309 | +| iterations | 6036 | +| time_elapsed | 19963 | +| total_timesteps | 6180864 | +| train/ | | +| approx_kl | 2.038107 | +| clip_fraction | 0.536 | +| clip_range | 0.2 | +| entropy_loss | -0.417 | +| explained_variance | -1.86 | +| learning_rate | 0.0001 | +| loss | -0.0774 | +| n_updates | 120880 | +| policy_gradient_loss | -0.0667 | +| value_loss | 0.000741 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.258 | +| time/ | | +| fps | 309 | +| iterations | 6037 | +| time_elapsed | 19966 | +| total_timesteps | 6181888 | +| train/ | | +| approx_kl | 1.7111574 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.44 | +| explained_variance | -1.73 | +| learning_rate | 0.0001 | +| loss | -0.0784 | +| n_updates | 120890 | +| policy_gradient_loss | -0.0698 | +| value_loss | 0.000243 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.258 | +| time/ | | +| fps | 309 | +| iterations | 6038 | +| time_elapsed | 19969 | +| total_timesteps | 6182912 | +| train/ | | +| approx_kl | 2.6400132 | +| clip_fraction | 0.541 | +| clip_range | 0.2 | +| entropy_loss | -0.466 | +| explained_variance | -0.276 | +| learning_rate | 0.0001 | +| loss | -0.107 | +| n_updates | 120900 | +| policy_gradient_loss | -0.0708 | +| value_loss | 0.000527 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.261 | +| time/ | | +| fps | 309 | +| iterations | 6039 | +| time_elapsed | 19973 | +| total_timesteps | 6183936 | +| train/ | | +| approx_kl | 2.0983834 | +| clip_fraction | 0.455 | +| clip_range | 0.2 | +| entropy_loss | -0.385 | +| explained_variance | -2.22 | +| learning_rate | 0.0001 | +| loss | -0.0927 | +| n_updates | 120910 | +| policy_gradient_loss | -0.0694 | +| value_loss | 0.000368 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.261 | +| time/ | | +| fps | 309 | +| iterations | 6040 | +| time_elapsed | 19976 | +| total_timesteps | 6184960 | +| train/ | | +| approx_kl | 2.3231924 | +| clip_fraction | 0.515 | +| clip_range | 0.2 | +| entropy_loss | -0.408 | +| explained_variance | -0.963 | +| learning_rate | 0.0001 | +| loss | -0.084 | +| n_updates | 120920 | +| policy_gradient_loss | -0.0685 | +| value_loss | 0.000727 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.267 | +| time/ | | +| fps | 309 | +| iterations | 6041 | +| time_elapsed | 19980 | +| total_timesteps | 6185984 | +| train/ | | +| approx_kl | 2.9842818 | +| clip_fraction | 0.5 | +| clip_range | 0.2 | +| entropy_loss | -0.374 | +| explained_variance | -2.78 | +| learning_rate | 0.0001 | +| loss | -0.0778 | +| n_updates | 120930 | +| policy_gradient_loss | -0.0648 | +| value_loss | 0.000695 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.264 | +| time/ | | +| fps | 309 | +| iterations | 6042 | +| time_elapsed | 19983 | +| total_timesteps | 6187008 | +| train/ | | +| approx_kl | 2.4617872 | +| clip_fraction | 0.47 | +| clip_range | 0.2 | +| entropy_loss | -0.304 | +| explained_variance | -2.94 | +| learning_rate | 0.0001 | +| loss | -0.109 | +| n_updates | 120940 | +| policy_gradient_loss | -0.0723 | +| value_loss | 0.000533 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.264 | +| time/ | | +| fps | 309 | +| iterations | 6043 | +| time_elapsed | 19986 | +| total_timesteps | 6188032 | +| train/ | | +| approx_kl | 24.31085 | +| clip_fraction | 0.521 | +| clip_range | 0.2 | +| entropy_loss | -0.42 | +| explained_variance | -0.284 | +| learning_rate | 0.0001 | +| loss | -0.0599 | +| n_updates | 120950 | +| policy_gradient_loss | -0.0586 | +| value_loss | 0.000357 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.265 | +| time/ | | +| fps | 309 | +| iterations | 6044 | +| time_elapsed | 19990 | +| total_timesteps | 6189056 | +| train/ | | +| approx_kl | 2.6482825 | +| clip_fraction | 0.472 | +| clip_range | 0.2 | +| entropy_loss | -0.341 | +| explained_variance | -1.78 | +| learning_rate | 0.0001 | +| loss | -0.0811 | +| n_updates | 120960 | +| policy_gradient_loss | -0.0683 | +| value_loss | 0.00068 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.268 | +| time/ | | +| fps | 309 | +| iterations | 6045 | +| time_elapsed | 19993 | +| total_timesteps | 6190080 | +| train/ | | +| approx_kl | 1.6807785 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.393 | +| explained_variance | -1.4 | +| learning_rate | 0.0001 | +| loss | -0.0716 | +| n_updates | 120970 | +| policy_gradient_loss | -0.0699 | +| value_loss | 0.000494 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.268 | +| time/ | | +| fps | 309 | +| iterations | 6046 | +| time_elapsed | 19996 | +| total_timesteps | 6191104 | +| train/ | | +| approx_kl | 1.4122943 | +| clip_fraction | 0.503 | +| clip_range | 0.2 | +| entropy_loss | -0.471 | +| explained_variance | -0.835 | +| learning_rate | 0.0001 | +| loss | -0.0783 | +| n_updates | 120980 | +| policy_gradient_loss | -0.0492 | +| value_loss | 0.000352 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.274 | +| time/ | | +| fps | 309 | +| iterations | 6047 | +| time_elapsed | 19999 | +| total_timesteps | 6192128 | +| train/ | | +| approx_kl | 2.4385147 | +| clip_fraction | 0.521 | +| clip_range | 0.2 | +| entropy_loss | -0.404 | +| explained_variance | -1.46 | +| learning_rate | 0.0001 | +| loss | -0.0836 | +| n_updates | 120990 | +| policy_gradient_loss | -0.0775 | +| value_loss | 0.000414 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.278 | +| time/ | | +| fps | 309 | +| iterations | 6048 | +| time_elapsed | 20003 | +| total_timesteps | 6193152 | +| train/ | | +| approx_kl | 2.407913 | +| clip_fraction | 0.522 | +| clip_range | 0.2 | +| entropy_loss | -0.39 | +| explained_variance | -1.11 | +| learning_rate | 0.0001 | +| loss | -0.0449 | +| n_updates | 121000 | +| policy_gradient_loss | -0.0653 | +| value_loss | 0.000377 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 309 | +| iterations | 6049 | +| time_elapsed | 20006 | +| total_timesteps | 6194176 | +| train/ | | +| approx_kl | 2.0747743 | +| clip_fraction | 0.502 | +| clip_range | 0.2 | +| entropy_loss | -0.37 | +| explained_variance | -0.8 | +| learning_rate | 0.0001 | +| loss | -0.0937 | +| n_updates | 121010 | +| policy_gradient_loss | -0.0685 | +| value_loss | 0.000779 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 309 | +| iterations | 6050 | +| time_elapsed | 20009 | +| total_timesteps | 6195200 | +| train/ | | +| approx_kl | 1.8447406 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.373 | +| explained_variance | -2.13 | +| learning_rate | 0.0001 | +| loss | -0.076 | +| n_updates | 121020 | +| policy_gradient_loss | -0.0677 | +| value_loss | 0.000641 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.274 | +| time/ | | +| fps | 309 | +| iterations | 6051 | +| time_elapsed | 20012 | +| total_timesteps | 6196224 | +| train/ | | +| approx_kl | 3.1913788 | +| clip_fraction | 0.506 | +| clip_range | 0.2 | +| entropy_loss | -0.376 | +| explained_variance | -2.78 | +| learning_rate | 0.0001 | +| loss | -0.04 | +| n_updates | 121030 | +| policy_gradient_loss | -0.0592 | +| value_loss | 0.000617 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.274 | +| time/ | | +| fps | 309 | +| iterations | 6052 | +| time_elapsed | 20015 | +| total_timesteps | 6197248 | +| train/ | | +| approx_kl | 3.2757485 | +| clip_fraction | 0.491 | +| clip_range | 0.2 | +| entropy_loss | -0.349 | +| explained_variance | -1.43 | +| learning_rate | 0.0001 | +| loss | -0.0884 | +| n_updates | 121040 | +| policy_gradient_loss | -0.0734 | +| value_loss | 0.000586 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.273 | +| time/ | | +| fps | 309 | +| iterations | 6053 | +| time_elapsed | 20018 | +| total_timesteps | 6198272 | +| train/ | | +| approx_kl | 2.4878805 | +| clip_fraction | 0.497 | +| clip_range | 0.2 | +| entropy_loss | -0.38 | +| explained_variance | -1.93 | +| learning_rate | 0.0001 | +| loss | -0.0672 | +| n_updates | 121050 | +| policy_gradient_loss | -0.0676 | +| value_loss | 0.000463 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.27 | +| time/ | | +| fps | 309 | +| iterations | 6054 | +| time_elapsed | 20022 | +| total_timesteps | 6199296 | +| train/ | | +| approx_kl | 3.893956 | +| clip_fraction | 0.485 | +| clip_range | 0.2 | +| entropy_loss | -0.378 | +| explained_variance | -1.14 | +| learning_rate | 0.0001 | +| loss | -0.109 | +| n_updates | 121060 | +| policy_gradient_loss | -0.0718 | +| value_loss | 0.000568 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.27 | +| time/ | | +| fps | 309 | +| iterations | 6055 | +| time_elapsed | 20025 | +| total_timesteps | 6200320 | +| train/ | | +| approx_kl | 2.2047195 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.353 | +| explained_variance | -2 | +| learning_rate | 0.0001 | +| loss | -0.123 | +| n_updates | 121070 | +| policy_gradient_loss | -0.0685 | +| value_loss | 0.000473 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.271 | +| time/ | | +| fps | 309 | +| iterations | 6056 | +| time_elapsed | 20029 | +| total_timesteps | 6201344 | +| train/ | | +| approx_kl | 2.478395 | +| clip_fraction | 0.479 | +| clip_range | 0.2 | +| entropy_loss | -0.325 | +| explained_variance | -0.958 | +| learning_rate | 0.0001 | +| loss | -0.0785 | +| n_updates | 121080 | +| policy_gradient_loss | -0.0644 | +| value_loss | 0.000505 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.271 | +| time/ | | +| fps | 309 | +| iterations | 6057 | +| time_elapsed | 20032 | +| total_timesteps | 6202368 | +| train/ | | +| approx_kl | 2.3450465 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.347 | +| explained_variance | -1.67 | +| learning_rate | 0.0001 | +| loss | -0.0872 | +| n_updates | 121090 | +| policy_gradient_loss | -0.0592 | +| value_loss | 0.000447 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.267 | +| time/ | | +| fps | 309 | +| iterations | 6058 | +| time_elapsed | 20036 | +| total_timesteps | 6203392 | +| train/ | | +| approx_kl | 2.119679 | +| clip_fraction | 0.47 | +| clip_range | 0.2 | +| entropy_loss | -0.334 | +| explained_variance | -2.06 | +| learning_rate | 0.0001 | +| loss | -0.112 | +| n_updates | 121100 | +| policy_gradient_loss | -0.0682 | +| value_loss | 0.000379 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.267 | +| time/ | | +| fps | 309 | +| iterations | 6059 | +| time_elapsed | 20039 | +| total_timesteps | 6204416 | +| train/ | | +| approx_kl | 2.458403 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.334 | +| explained_variance | -1.59 | +| learning_rate | 0.0001 | +| loss | -0.0727 | +| n_updates | 121110 | +| policy_gradient_loss | -0.0671 | +| value_loss | 0.0005 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.268 | +| time/ | | +| fps | 309 | +| iterations | 6060 | +| time_elapsed | 20042 | +| total_timesteps | 6205440 | +| train/ | | +| approx_kl | 2.6270094 | +| clip_fraction | 0.499 | +| clip_range | 0.2 | +| entropy_loss | -0.376 | +| explained_variance | -1.51 | +| learning_rate | 0.0001 | +| loss | -0.0557 | +| n_updates | 121120 | +| policy_gradient_loss | -0.0498 | +| value_loss | 0.000421 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.267 | +| time/ | | +| fps | 309 | +| iterations | 6061 | +| time_elapsed | 20046 | +| total_timesteps | 6206464 | +| train/ | | +| approx_kl | 2.4465945 | +| clip_fraction | 0.45 | +| clip_range | 0.2 | +| entropy_loss | -0.34 | +| explained_variance | -3.74 | +| learning_rate | 0.0001 | +| loss | -0.0945 | +| n_updates | 121130 | +| policy_gradient_loss | -0.0654 | +| value_loss | 0.000281 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.267 | +| time/ | | +| fps | 309 | +| iterations | 6062 | +| time_elapsed | 20049 | +| total_timesteps | 6207488 | +| train/ | | +| approx_kl | 1.7827452 | +| clip_fraction | 0.467 | +| clip_range | 0.2 | +| entropy_loss | -0.376 | +| explained_variance | -0.618 | +| learning_rate | 0.0001 | +| loss | -0.0386 | +| n_updates | 121140 | +| policy_gradient_loss | -0.0523 | +| value_loss | 0.000399 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.265 | +| time/ | | +| fps | 309 | +| iterations | 6063 | +| time_elapsed | 20052 | +| total_timesteps | 6208512 | +| train/ | | +| approx_kl | 2.3343883 | +| clip_fraction | 0.534 | +| clip_range | 0.2 | +| entropy_loss | -0.453 | +| explained_variance | -1.65 | +| learning_rate | 0.0001 | +| loss | -0.107 | +| n_updates | 121150 | +| policy_gradient_loss | -0.0731 | +| value_loss | 0.000573 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.266 | +| time/ | | +| fps | 309 | +| iterations | 6064 | +| time_elapsed | 20055 | +| total_timesteps | 6209536 | +| train/ | | +| approx_kl | 1.7096688 | +| clip_fraction | 0.491 | +| clip_range | 0.2 | +| entropy_loss | -0.403 | +| explained_variance | -1.9 | +| learning_rate | 0.0001 | +| loss | -0.0971 | +| n_updates | 121160 | +| policy_gradient_loss | -0.0602 | +| value_loss | 0.00056 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.264 | +| time/ | | +| fps | 309 | +| iterations | 6065 | +| time_elapsed | 20059 | +| total_timesteps | 6210560 | +| train/ | | +| approx_kl | 2.1365943 | +| clip_fraction | 0.472 | +| clip_range | 0.2 | +| entropy_loss | -0.336 | +| explained_variance | -1.3 | +| learning_rate | 0.0001 | +| loss | -0.087 | +| n_updates | 121170 | +| policy_gradient_loss | -0.0549 | +| value_loss | 0.000973 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.264 | +| time/ | | +| fps | 309 | +| iterations | 6066 | +| time_elapsed | 20062 | +| total_timesteps | 6211584 | +| train/ | | +| approx_kl | 2.3101125 | +| clip_fraction | 0.491 | +| clip_range | 0.2 | +| entropy_loss | -0.381 | +| explained_variance | -1.25 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 121180 | +| policy_gradient_loss | -0.0692 | +| value_loss | 0.000546 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.265 | +| time/ | | +| fps | 309 | +| iterations | 6067 | +| time_elapsed | 20065 | +| total_timesteps | 6212608 | +| train/ | | +| approx_kl | 2.4359117 | +| clip_fraction | 0.453 | +| clip_range | 0.2 | +| entropy_loss | -0.385 | +| explained_variance | -1.57 | +| learning_rate | 0.0001 | +| loss | -0.0524 | +| n_updates | 121190 | +| policy_gradient_loss | -0.053 | +| value_loss | 0.000286 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.262 | +| time/ | | +| fps | 309 | +| iterations | 6068 | +| time_elapsed | 20068 | +| total_timesteps | 6213632 | +| train/ | | +| approx_kl | 2.087852 | +| clip_fraction | 0.477 | +| clip_range | 0.2 | +| entropy_loss | -0.365 | +| explained_variance | -1.08 | +| learning_rate | 0.0001 | +| loss | -0.0804 | +| n_updates | 121200 | +| policy_gradient_loss | -0.0621 | +| value_loss | 0.000761 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.262 | +| time/ | | +| fps | 309 | +| iterations | 6069 | +| time_elapsed | 20071 | +| total_timesteps | 6214656 | +| train/ | | +| approx_kl | 2.7216947 | +| clip_fraction | 0.499 | +| clip_range | 0.2 | +| entropy_loss | -0.402 | +| explained_variance | -2.22 | +| learning_rate | 0.0001 | +| loss | -0.0828 | +| n_updates | 121210 | +| policy_gradient_loss | -0.0673 | +| value_loss | 0.000592 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.26 | +| time/ | | +| fps | 309 | +| iterations | 6070 | +| time_elapsed | 20075 | +| total_timesteps | 6215680 | +| train/ | | +| approx_kl | 2.5292292 | +| clip_fraction | 0.484 | +| clip_range | 0.2 | +| entropy_loss | -0.38 | +| explained_variance | -1.21 | +| learning_rate | 0.0001 | +| loss | -0.0778 | +| n_updates | 121220 | +| policy_gradient_loss | -0.0639 | +| value_loss | 0.000356 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.26 | +| time/ | | +| fps | 309 | +| iterations | 6071 | +| time_elapsed | 20078 | +| total_timesteps | 6216704 | +| train/ | | +| approx_kl | 2.5820882 | +| clip_fraction | 0.491 | +| clip_range | 0.2 | +| entropy_loss | -0.393 | +| explained_variance | -2.62 | +| learning_rate | 0.0001 | +| loss | -0.0936 | +| n_updates | 121230 | +| policy_gradient_loss | -0.0591 | +| value_loss | 0.000206 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.262 | +| time/ | | +| fps | 309 | +| iterations | 6072 | +| time_elapsed | 20082 | +| total_timesteps | 6217728 | +| train/ | | +| approx_kl | 2.1027768 | +| clip_fraction | 0.522 | +| clip_range | 0.2 | +| entropy_loss | -0.425 | +| explained_variance | -0.394 | +| learning_rate | 0.0001 | +| loss | -0.0902 | +| n_updates | 121240 | +| policy_gradient_loss | -0.0584 | +| value_loss | 0.000389 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.262 | +| time/ | | +| fps | 309 | +| iterations | 6073 | +| time_elapsed | 20085 | +| total_timesteps | 6218752 | +| train/ | | +| approx_kl | 1.7830333 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.381 | +| explained_variance | -1.83 | +| learning_rate | 0.0001 | +| loss | -0.0854 | +| n_updates | 121250 | +| policy_gradient_loss | -0.0621 | +| value_loss | 0.000399 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.264 | +| time/ | | +| fps | 309 | +| iterations | 6074 | +| time_elapsed | 20088 | +| total_timesteps | 6219776 | +| train/ | | +| approx_kl | 2.4939857 | +| clip_fraction | 0.522 | +| clip_range | 0.2 | +| entropy_loss | -0.408 | +| explained_variance | -2.05 | +| learning_rate | 0.0001 | +| loss | -0.0722 | +| n_updates | 121260 | +| policy_gradient_loss | -0.054 | +| value_loss | 0.000278 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | 0.265 | +| time/ | | +| fps | 309 | +| iterations | 6075 | +| time_elapsed | 20092 | +| total_timesteps | 6220800 | +| train/ | | +| approx_kl | 2.0711403 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.369 | +| explained_variance | -0.529 | +| learning_rate | 0.0001 | +| loss | -0.0659 | +| n_updates | 121270 | +| policy_gradient_loss | -0.0604 | +| value_loss | 0.000542 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | 0.262 | +| time/ | | +| fps | 309 | +| iterations | 6076 | +| time_elapsed | 20095 | +| total_timesteps | 6221824 | +| train/ | | +| approx_kl | 2.435039 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.343 | +| explained_variance | -7.42 | +| learning_rate | 0.0001 | +| loss | -0.114 | +| n_updates | 121280 | +| policy_gradient_loss | -0.0704 | +| value_loss | 0.00037 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | 0.262 | +| time/ | | +| fps | 309 | +| iterations | 6077 | +| time_elapsed | 20099 | +| total_timesteps | 6222848 | +| train/ | | +| approx_kl | 2.4520893 | +| clip_fraction | 0.488 | +| clip_range | 0.2 | +| entropy_loss | -0.386 | +| explained_variance | -0.741 | +| learning_rate | 0.0001 | +| loss | -0.079 | +| n_updates | 121290 | +| policy_gradient_loss | -0.0627 | +| value_loss | 0.00029 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | 0.266 | +| time/ | | +| fps | 309 | +| iterations | 6078 | +| time_elapsed | 20102 | +| total_timesteps | 6223872 | +| train/ | | +| approx_kl | 2.3987377 | +| clip_fraction | 0.485 | +| clip_range | 0.2 | +| entropy_loss | -0.369 | +| explained_variance | -2.42 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 121300 | +| policy_gradient_loss | -0.0681 | +| value_loss | 0.000548 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | 0.259 | +| time/ | | +| fps | 309 | +| iterations | 6079 | +| time_elapsed | 20106 | +| total_timesteps | 6224896 | +| train/ | | +| approx_kl | 2.6437845 | +| clip_fraction | 0.499 | +| clip_range | 0.2 | +| entropy_loss | -0.41 | +| explained_variance | -1.56 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 121310 | +| policy_gradient_loss | -0.0584 | +| value_loss | 0.000428 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.65e+03 | +| ep_rew_mean | 0.257 | +| time/ | | +| fps | 309 | +| iterations | 6080 | +| time_elapsed | 20109 | +| total_timesteps | 6225920 | +| train/ | | +| approx_kl | 2.1415951 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.364 | +| explained_variance | -2.14 | +| learning_rate | 0.0001 | +| loss | -0.0855 | +| n_updates | 121320 | +| policy_gradient_loss | -0.07 | +| value_loss | 0.000386 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.65e+03 | +| ep_rew_mean | 0.257 | +| time/ | | +| fps | 309 | +| iterations | 6081 | +| time_elapsed | 20112 | +| total_timesteps | 6226944 | +| train/ | | +| approx_kl | 2.5622475 | +| clip_fraction | 0.448 | +| clip_range | 0.2 | +| entropy_loss | -0.347 | +| explained_variance | -1.31 | +| learning_rate | 0.0001 | +| loss | -0.0661 | +| n_updates | 121330 | +| policy_gradient_loss | -0.053 | +| value_loss | 0.000761 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.64e+03 | +| ep_rew_mean | 0.25 | +| time/ | | +| fps | 309 | +| iterations | 6082 | +| time_elapsed | 20115 | +| total_timesteps | 6227968 | +| train/ | | +| approx_kl | 1.7271005 | +| clip_fraction | 0.474 | +| clip_range | 0.2 | +| entropy_loss | -0.417 | +| explained_variance | -0.609 | +| learning_rate | 0.0001 | +| loss | -0.0223 | +| n_updates | 121340 | +| policy_gradient_loss | -0.0626 | +| value_loss | 0.000502 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.63e+03 | +| ep_rew_mean | 0.25 | +| time/ | | +| fps | 309 | +| iterations | 6083 | +| time_elapsed | 20118 | +| total_timesteps | 6228992 | +| train/ | | +| approx_kl | 1.9896866 | +| clip_fraction | 0.473 | +| clip_range | 0.2 | +| entropy_loss | -0.364 | +| explained_variance | -0.425 | +| learning_rate | 0.0001 | +| loss | -0.0838 | +| n_updates | 121350 | +| policy_gradient_loss | -0.0656 | +| value_loss | 0.000362 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.63e+03 | +| ep_rew_mean | 0.25 | +| time/ | | +| fps | 309 | +| iterations | 6084 | +| time_elapsed | 20122 | +| total_timesteps | 6230016 | +| train/ | | +| approx_kl | 1.9817083 | +| clip_fraction | 0.469 | +| clip_range | 0.2 | +| entropy_loss | -0.37 | +| explained_variance | -1.64 | +| learning_rate | 0.0001 | +| loss | -0.109 | +| n_updates | 121360 | +| policy_gradient_loss | -0.0659 | +| value_loss | 0.000444 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.63e+03 | +| ep_rew_mean | 0.248 | +| time/ | | +| fps | 309 | +| iterations | 6085 | +| time_elapsed | 20125 | +| total_timesteps | 6231040 | +| train/ | | +| approx_kl | 2.0779467 | +| clip_fraction | 0.526 | +| clip_range | 0.2 | +| entropy_loss | -0.445 | +| explained_variance | -0.525 | +| learning_rate | 0.0001 | +| loss | -0.0716 | +| n_updates | 121370 | +| policy_gradient_loss | -0.0658 | +| value_loss | 0.000583 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.63e+03 | +| ep_rew_mean | 0.248 | +| time/ | | +| fps | 309 | +| iterations | 6086 | +| time_elapsed | 20128 | +| total_timesteps | 6232064 | +| train/ | | +| approx_kl | 2.413186 | +| clip_fraction | 0.484 | +| clip_range | 0.2 | +| entropy_loss | -0.414 | +| explained_variance | -1.64 | +| learning_rate | 0.0001 | +| loss | -0.0811 | +| n_updates | 121380 | +| policy_gradient_loss | -0.0586 | +| value_loss | 0.00034 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.63e+03 | +| ep_rew_mean | 0.248 | +| time/ | | +| fps | 309 | +| iterations | 6087 | +| time_elapsed | 20131 | +| total_timesteps | 6233088 | +| train/ | | +| approx_kl | 2.325907 | +| clip_fraction | 0.511 | +| clip_range | 0.2 | +| entropy_loss | -0.416 | +| explained_variance | -2.52 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 121390 | +| policy_gradient_loss | -0.0671 | +| value_loss | 0.000405 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.64e+03 | +| ep_rew_mean | 0.247 | +| time/ | | +| fps | 309 | +| iterations | 6088 | +| time_elapsed | 20134 | +| total_timesteps | 6234112 | +| train/ | | +| approx_kl | 5.551179 | +| clip_fraction | 0.502 | +| clip_range | 0.2 | +| entropy_loss | -0.415 | +| explained_variance | -2.63 | +| learning_rate | 0.0001 | +| loss | -0.0698 | +| n_updates | 121400 | +| policy_gradient_loss | -0.0685 | +| value_loss | 0.000292 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.63e+03 | +| ep_rew_mean | 0.248 | +| time/ | | +| fps | 309 | +| iterations | 6089 | +| time_elapsed | 20137 | +| total_timesteps | 6235136 | +| train/ | | +| approx_kl | 2.064493 | +| clip_fraction | 0.491 | +| clip_range | 0.2 | +| entropy_loss | -0.397 | +| explained_variance | -1.06 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 121410 | +| policy_gradient_loss | -0.0682 | +| value_loss | 0.00047 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.63e+03 | +| ep_rew_mean | 0.248 | +| time/ | | +| fps | 309 | +| iterations | 6090 | +| time_elapsed | 20141 | +| total_timesteps | 6236160 | +| train/ | | +| approx_kl | 1.8887166 | +| clip_fraction | 0.495 | +| clip_range | 0.2 | +| entropy_loss | -0.391 | +| explained_variance | -0.984 | +| learning_rate | 0.0001 | +| loss | -0.0687 | +| n_updates | 121420 | +| policy_gradient_loss | -0.0701 | +| value_loss | 0.000738 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.63e+03 | +| ep_rew_mean | 0.251 | +| time/ | | +| fps | 309 | +| iterations | 6091 | +| time_elapsed | 20144 | +| total_timesteps | 6237184 | +| train/ | | +| approx_kl | 2.246199 | +| clip_fraction | 0.466 | +| clip_range | 0.2 | +| entropy_loss | -0.366 | +| explained_variance | -2.14 | +| learning_rate | 0.0001 | +| loss | -0.0437 | +| n_updates | 121430 | +| policy_gradient_loss | -0.0665 | +| value_loss | 0.00063 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.63e+03 | +| ep_rew_mean | 0.251 | +| time/ | | +| fps | 309 | +| iterations | 6092 | +| time_elapsed | 20148 | +| total_timesteps | 6238208 | +| train/ | | +| approx_kl | 2.0254161 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.335 | +| explained_variance | -2.88 | +| learning_rate | 0.0001 | +| loss | -0.0853 | +| n_updates | 121440 | +| policy_gradient_loss | -0.0668 | +| value_loss | 0.000475 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.64e+03 | +| ep_rew_mean | 0.254 | +| time/ | | +| fps | 309 | +| iterations | 6093 | +| time_elapsed | 20151 | +| total_timesteps | 6239232 | +| train/ | | +| approx_kl | 1.6648211 | +| clip_fraction | 0.508 | +| clip_range | 0.2 | +| entropy_loss | -0.424 | +| explained_variance | -1.8 | +| learning_rate | 0.0001 | +| loss | -0.0874 | +| n_updates | 121450 | +| policy_gradient_loss | -0.069 | +| value_loss | 0.000479 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.64e+03 | +| ep_rew_mean | 0.254 | +| time/ | | +| fps | 309 | +| iterations | 6094 | +| time_elapsed | 20155 | +| total_timesteps | 6240256 | +| train/ | | +| approx_kl | 3.923059 | +| clip_fraction | 0.462 | +| clip_range | 0.2 | +| entropy_loss | -0.327 | +| explained_variance | -2.36 | +| learning_rate | 0.0001 | +| loss | -0.0974 | +| n_updates | 121460 | +| policy_gradient_loss | -0.0709 | +| value_loss | 0.000466 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.64e+03 | +| ep_rew_mean | 0.256 | +| time/ | | +| fps | 309 | +| iterations | 6095 | +| time_elapsed | 20158 | +| total_timesteps | 6241280 | +| train/ | | +| approx_kl | 2.8859315 | +| clip_fraction | 0.452 | +| clip_range | 0.2 | +| entropy_loss | -0.346 | +| explained_variance | -1.61 | +| learning_rate | 0.0001 | +| loss | -0.0484 | +| n_updates | 121470 | +| policy_gradient_loss | -0.0588 | +| value_loss | 0.000696 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.64e+03 | +| ep_rew_mean | 0.256 | +| time/ | | +| fps | 309 | +| iterations | 6096 | +| time_elapsed | 20162 | +| total_timesteps | 6242304 | +| train/ | | +| approx_kl | 1.677999 | +| clip_fraction | 0.431 | +| clip_range | 0.2 | +| entropy_loss | -0.348 | +| explained_variance | -5.45 | +| learning_rate | 0.0001 | +| loss | -0.0705 | +| n_updates | 121480 | +| policy_gradient_loss | -0.0644 | +| value_loss | 0.000436 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.64e+03 | +| ep_rew_mean | 0.256 | +| time/ | | +| fps | 309 | +| iterations | 6097 | +| time_elapsed | 20165 | +| total_timesteps | 6243328 | +| train/ | | +| approx_kl | 1.8032522 | +| clip_fraction | 0.501 | +| clip_range | 0.2 | +| entropy_loss | -0.415 | +| explained_variance | -0.982 | +| learning_rate | 0.0001 | +| loss | -0.106 | +| n_updates | 121490 | +| policy_gradient_loss | -0.0638 | +| value_loss | 0.000384 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.63e+03 | +| ep_rew_mean | 0.253 | +| time/ | | +| fps | 309 | +| iterations | 6098 | +| time_elapsed | 20169 | +| total_timesteps | 6244352 | +| train/ | | +| approx_kl | 2.1969695 | +| clip_fraction | 0.454 | +| clip_range | 0.2 | +| entropy_loss | -0.358 | +| explained_variance | -1.39 | +| learning_rate | 0.0001 | +| loss | -0.0943 | +| n_updates | 121500 | +| policy_gradient_loss | -0.0599 | +| value_loss | 0.000445 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.63e+03 | +| ep_rew_mean | 0.253 | +| time/ | | +| fps | 309 | +| iterations | 6099 | +| time_elapsed | 20172 | +| total_timesteps | 6245376 | +| train/ | | +| approx_kl | 1.7732806 | +| clip_fraction | 0.459 | +| clip_range | 0.2 | +| entropy_loss | -0.359 | +| explained_variance | -3.32 | +| learning_rate | 0.0001 | +| loss | -0.0782 | +| n_updates | 121510 | +| policy_gradient_loss | -0.0693 | +| value_loss | 0.000395 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.63e+03 | +| ep_rew_mean | 0.251 | +| time/ | | +| fps | 309 | +| iterations | 6100 | +| time_elapsed | 20175 | +| total_timesteps | 6246400 | +| train/ | | +| approx_kl | 1.762895 | +| clip_fraction | 0.479 | +| clip_range | 0.2 | +| entropy_loss | -0.431 | +| explained_variance | -1.18 | +| learning_rate | 0.0001 | +| loss | -0.0922 | +| n_updates | 121520 | +| policy_gradient_loss | -0.0653 | +| value_loss | 0.000268 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.63e+03 | +| ep_rew_mean | 0.251 | +| time/ | | +| fps | 309 | +| iterations | 6101 | +| time_elapsed | 20179 | +| total_timesteps | 6247424 | +| train/ | | +| approx_kl | 2.3120782 | +| clip_fraction | 0.507 | +| clip_range | 0.2 | +| entropy_loss | -0.401 | +| explained_variance | -0.545 | +| learning_rate | 0.0001 | +| loss | -0.0961 | +| n_updates | 121530 | +| policy_gradient_loss | -0.0696 | +| value_loss | 0.000358 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.62e+03 | +| ep_rew_mean | 0.25 | +| time/ | | +| fps | 309 | +| iterations | 6102 | +| time_elapsed | 20182 | +| total_timesteps | 6248448 | +| train/ | | +| approx_kl | 1.4562621 | +| clip_fraction | 0.492 | +| clip_range | 0.2 | +| entropy_loss | -0.429 | +| explained_variance | -1.32 | +| learning_rate | 0.0001 | +| loss | -0.0823 | +| n_updates | 121540 | +| policy_gradient_loss | -0.0624 | +| value_loss | 0.000412 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.63e+03 | +| ep_rew_mean | 0.254 | +| time/ | | +| fps | 309 | +| iterations | 6103 | +| time_elapsed | 20185 | +| total_timesteps | 6249472 | +| train/ | | +| approx_kl | 1.5908097 | +| clip_fraction | 0.501 | +| clip_range | 0.2 | +| entropy_loss | -0.487 | +| explained_variance | -0.712 | +| learning_rate | 0.0001 | +| loss | -0.0759 | +| n_updates | 121550 | +| policy_gradient_loss | -0.0633 | +| value_loss | 0.000498 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.63e+03 | +| ep_rew_mean | 0.261 | +| time/ | | +| fps | 309 | +| iterations | 6104 | +| time_elapsed | 20188 | +| total_timesteps | 6250496 | +| train/ | | +| approx_kl | 2.0718513 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.375 | +| explained_variance | -2.03 | +| learning_rate | 0.0001 | +| loss | -0.0294 | +| n_updates | 121560 | +| policy_gradient_loss | -0.0633 | +| value_loss | 0.000449 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.63e+03 | +| ep_rew_mean | 0.261 | +| time/ | | +| fps | 309 | +| iterations | 6105 | +| time_elapsed | 20192 | +| total_timesteps | 6251520 | +| train/ | | +| approx_kl | 2.8960748 | +| clip_fraction | 0.49 | +| clip_range | 0.2 | +| entropy_loss | -0.365 | +| explained_variance | -0.742 | +| learning_rate | 0.0001 | +| loss | -0.0669 | +| n_updates | 121570 | +| policy_gradient_loss | -0.0693 | +| value_loss | 0.00065 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.63e+03 | +| ep_rew_mean | 0.265 | +| time/ | | +| fps | 309 | +| iterations | 6106 | +| time_elapsed | 20195 | +| total_timesteps | 6252544 | +| train/ | | +| approx_kl | 3.048643 | +| clip_fraction | 0.512 | +| clip_range | 0.2 | +| entropy_loss | -0.403 | +| explained_variance | -3.41 | +| learning_rate | 0.0001 | +| loss | -0.0877 | +| n_updates | 121580 | +| policy_gradient_loss | -0.0581 | +| value_loss | 0.000528 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.63e+03 | +| ep_rew_mean | 0.265 | +| time/ | | +| fps | 309 | +| iterations | 6107 | +| time_elapsed | 20198 | +| total_timesteps | 6253568 | +| train/ | | +| approx_kl | 2.1522954 | +| clip_fraction | 0.495 | +| clip_range | 0.2 | +| entropy_loss | -0.384 | +| explained_variance | -2.08 | +| learning_rate | 0.0001 | +| loss | -0.0911 | +| n_updates | 121590 | +| policy_gradient_loss | -0.0672 | +| value_loss | 0.000444 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.63e+03 | +| ep_rew_mean | 0.268 | +| time/ | | +| fps | 309 | +| iterations | 6108 | +| time_elapsed | 20202 | +| total_timesteps | 6254592 | +| train/ | | +| approx_kl | 1.7040195 | +| clip_fraction | 0.476 | +| clip_range | 0.2 | +| entropy_loss | -0.395 | +| explained_variance | -2.81 | +| learning_rate | 0.0001 | +| loss | -0.0943 | +| n_updates | 121600 | +| policy_gradient_loss | -0.0576 | +| value_loss | 0.000829 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.63e+03 | +| ep_rew_mean | 0.273 | +| time/ | | +| fps | 309 | +| iterations | 6109 | +| time_elapsed | 20205 | +| total_timesteps | 6255616 | +| train/ | | +| approx_kl | 2.7689695 | +| clip_fraction | 0.527 | +| clip_range | 0.2 | +| entropy_loss | -0.436 | +| explained_variance | -1.12 | +| learning_rate | 0.0001 | +| loss | -0.0994 | +| n_updates | 121610 | +| policy_gradient_loss | -0.077 | +| value_loss | 0.000402 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.63e+03 | +| ep_rew_mean | 0.274 | +| time/ | | +| fps | 309 | +| iterations | 6110 | +| time_elapsed | 20208 | +| total_timesteps | 6256640 | +| train/ | | +| approx_kl | 2.450235 | +| clip_fraction | 0.498 | +| clip_range | 0.2 | +| entropy_loss | -0.377 | +| explained_variance | -1.21 | +| learning_rate | 0.0001 | +| loss | -0.111 | +| n_updates | 121620 | +| policy_gradient_loss | -0.0575 | +| value_loss | 0.000412 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.63e+03 | +| ep_rew_mean | 0.274 | +| time/ | | +| fps | 309 | +| iterations | 6111 | +| time_elapsed | 20212 | +| total_timesteps | 6257664 | +| train/ | | +| approx_kl | 2.0052125 | +| clip_fraction | 0.49 | +| clip_range | 0.2 | +| entropy_loss | -0.398 | +| explained_variance | -1.21 | +| learning_rate | 0.0001 | +| loss | -0.0635 | +| n_updates | 121630 | +| policy_gradient_loss | -0.0696 | +| value_loss | 0.000789 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.63e+03 | +| ep_rew_mean | 0.274 | +| time/ | | +| fps | 309 | +| iterations | 6112 | +| time_elapsed | 20215 | +| total_timesteps | 6258688 | +| train/ | | +| approx_kl | 1.7901212 | +| clip_fraction | 0.469 | +| clip_range | 0.2 | +| entropy_loss | -0.428 | +| explained_variance | -1.59 | +| learning_rate | 0.0001 | +| loss | -0.0801 | +| n_updates | 121640 | +| policy_gradient_loss | -0.0614 | +| value_loss | 0.000435 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.64e+03 | +| ep_rew_mean | 0.272 | +| time/ | | +| fps | 309 | +| iterations | 6113 | +| time_elapsed | 20219 | +| total_timesteps | 6259712 | +| train/ | | +| approx_kl | 2.6842585 | +| clip_fraction | 0.494 | +| clip_range | 0.2 | +| entropy_loss | -0.376 | +| explained_variance | -1.75 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 121650 | +| policy_gradient_loss | -0.0698 | +| value_loss | 0.000313 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.64e+03 | +| ep_rew_mean | 0.272 | +| time/ | | +| fps | 309 | +| iterations | 6114 | +| time_elapsed | 20222 | +| total_timesteps | 6260736 | +| train/ | | +| approx_kl | 3.4591742 | +| clip_fraction | 0.505 | +| clip_range | 0.2 | +| entropy_loss | -0.394 | +| explained_variance | -0.662 | +| learning_rate | 0.0001 | +| loss | -0.0843 | +| n_updates | 121660 | +| policy_gradient_loss | -0.0646 | +| value_loss | 0.000412 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.64e+03 | +| ep_rew_mean | 0.273 | +| time/ | | +| fps | 309 | +| iterations | 6115 | +| time_elapsed | 20225 | +| total_timesteps | 6261760 | +| train/ | | +| approx_kl | 2.5424953 | +| clip_fraction | 0.506 | +| clip_range | 0.2 | +| entropy_loss | -0.367 | +| explained_variance | -1.21 | +| learning_rate | 0.0001 | +| loss | -0.0982 | +| n_updates | 121670 | +| policy_gradient_loss | -0.0645 | +| value_loss | 0.000496 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.64e+03 | +| ep_rew_mean | 0.273 | +| time/ | | +| fps | 309 | +| iterations | 6116 | +| time_elapsed | 20229 | +| total_timesteps | 6262784 | +| train/ | | +| approx_kl | 2.4604034 | +| clip_fraction | 0.522 | +| clip_range | 0.2 | +| entropy_loss | -0.368 | +| explained_variance | -2.13 | +| learning_rate | 0.0001 | +| loss | -0.0881 | +| n_updates | 121680 | +| policy_gradient_loss | -0.0644 | +| value_loss | 0.000276 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.64e+03 | +| ep_rew_mean | 0.273 | +| time/ | | +| fps | 309 | +| iterations | 6117 | +| time_elapsed | 20232 | +| total_timesteps | 6263808 | +| train/ | | +| approx_kl | 2.2914624 | +| clip_fraction | 0.497 | +| clip_range | 0.2 | +| entropy_loss | -0.411 | +| explained_variance | -0.887 | +| learning_rate | 0.0001 | +| loss | -0.0868 | +| n_updates | 121690 | +| policy_gradient_loss | -0.0629 | +| value_loss | 0.000453 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.64e+03 | +| ep_rew_mean | 0.274 | +| time/ | | +| fps | 309 | +| iterations | 6118 | +| time_elapsed | 20235 | +| total_timesteps | 6264832 | +| train/ | | +| approx_kl | 2.7611601 | +| clip_fraction | 0.505 | +| clip_range | 0.2 | +| entropy_loss | -0.353 | +| explained_variance | -2.79 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 121700 | +| policy_gradient_loss | -0.0704 | +| value_loss | 0.000468 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.64e+03 | +| ep_rew_mean | 0.281 | +| time/ | | +| fps | 309 | +| iterations | 6119 | +| time_elapsed | 20238 | +| total_timesteps | 6265856 | +| train/ | | +| approx_kl | 1.9125822 | +| clip_fraction | 0.509 | +| clip_range | 0.2 | +| entropy_loss | -0.414 | +| explained_variance | -1.55 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 121710 | +| policy_gradient_loss | -0.0617 | +| value_loss | 0.000458 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.64e+03 | +| ep_rew_mean | 0.281 | +| time/ | | +| fps | 309 | +| iterations | 6120 | +| time_elapsed | 20241 | +| total_timesteps | 6266880 | +| train/ | | +| approx_kl | 2.320045 | +| clip_fraction | 0.524 | +| clip_range | 0.2 | +| entropy_loss | -0.423 | +| explained_variance | -0.393 | +| learning_rate | 0.0001 | +| loss | -0.072 | +| n_updates | 121720 | +| policy_gradient_loss | -0.0563 | +| value_loss | 0.000768 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.64e+03 | +| ep_rew_mean | 0.281 | +| time/ | | +| fps | 309 | +| iterations | 6121 | +| time_elapsed | 20245 | +| total_timesteps | 6267904 | +| train/ | | +| approx_kl | 2.1872106 | +| clip_fraction | 0.511 | +| clip_range | 0.2 | +| entropy_loss | -0.408 | +| explained_variance | -2.92 | +| learning_rate | 0.0001 | +| loss | -0.0537 | +| n_updates | 121730 | +| policy_gradient_loss | -0.0664 | +| value_loss | 0.000612 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.64e+03 | +| ep_rew_mean | 0.281 | +| time/ | | +| fps | 309 | +| iterations | 6122 | +| time_elapsed | 20248 | +| total_timesteps | 6268928 | +| train/ | | +| approx_kl | 1.9949194 | +| clip_fraction | 0.506 | +| clip_range | 0.2 | +| entropy_loss | -0.381 | +| explained_variance | -3.24 | +| learning_rate | 0.0001 | +| loss | -0.0943 | +| n_updates | 121740 | +| policy_gradient_loss | -0.0695 | +| value_loss | 0.000513 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.64e+03 | +| ep_rew_mean | 0.283 | +| time/ | | +| fps | 309 | +| iterations | 6123 | +| time_elapsed | 20251 | +| total_timesteps | 6269952 | +| train/ | | +| approx_kl | 1.8815284 | +| clip_fraction | 0.492 | +| clip_range | 0.2 | +| entropy_loss | -0.409 | +| explained_variance | -1.38 | +| learning_rate | 0.0001 | +| loss | -0.0937 | +| n_updates | 121750 | +| policy_gradient_loss | -0.0244 | +| value_loss | 0.000464 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.64e+03 | +| ep_rew_mean | 0.283 | +| time/ | | +| fps | 309 | +| iterations | 6124 | +| time_elapsed | 20254 | +| total_timesteps | 6270976 | +| train/ | | +| approx_kl | 1.3870819 | +| clip_fraction | 0.457 | +| clip_range | 0.2 | +| entropy_loss | -0.41 | +| explained_variance | -1.8 | +| learning_rate | 0.0001 | +| loss | -0.0757 | +| n_updates | 121760 | +| policy_gradient_loss | -0.0544 | +| value_loss | 0.000277 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.65e+03 | +| ep_rew_mean | 0.286 | +| time/ | | +| fps | 309 | +| iterations | 6125 | +| time_elapsed | 20257 | +| total_timesteps | 6272000 | +| train/ | | +| approx_kl | 2.440189 | +| clip_fraction | 0.472 | +| clip_range | 0.2 | +| entropy_loss | -0.337 | +| explained_variance | -0.94 | +| learning_rate | 0.0001 | +| loss | -0.0946 | +| n_updates | 121770 | +| policy_gradient_loss | -0.0637 | +| value_loss | 0.000474 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.65e+03 | +| ep_rew_mean | 0.286 | +| time/ | | +| fps | 309 | +| iterations | 6126 | +| time_elapsed | 20260 | +| total_timesteps | 6273024 | +| train/ | | +| approx_kl | 3.7107816 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.378 | +| explained_variance | -1.51 | +| learning_rate | 0.0001 | +| loss | -0.105 | +| n_updates | 121780 | +| policy_gradient_loss | -0.0688 | +| value_loss | 0.000441 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | 0.289 | +| time/ | | +| fps | 309 | +| iterations | 6127 | +| time_elapsed | 20264 | +| total_timesteps | 6274048 | +| train/ | | +| approx_kl | 2.4451919 | +| clip_fraction | 0.505 | +| clip_range | 0.2 | +| entropy_loss | -0.378 | +| explained_variance | -1.39 | +| learning_rate | 0.0001 | +| loss | -0.117 | +| n_updates | 121790 | +| policy_gradient_loss | -0.0726 | +| value_loss | 0.000332 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | 0.289 | +| time/ | | +| fps | 309 | +| iterations | 6128 | +| time_elapsed | 20268 | +| total_timesteps | 6275072 | +| train/ | | +| approx_kl | 4.352229 | +| clip_fraction | 0.5 | +| clip_range | 0.2 | +| entropy_loss | -0.385 | +| explained_variance | -3.99 | +| learning_rate | 0.0001 | +| loss | -0.113 | +| n_updates | 121800 | +| policy_gradient_loss | -0.0725 | +| value_loss | 0.000481 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.65e+03 | +| ep_rew_mean | 0.287 | +| time/ | | +| fps | 309 | +| iterations | 6129 | +| time_elapsed | 20271 | +| total_timesteps | 6276096 | +| train/ | | +| approx_kl | 1.8602768 | +| clip_fraction | 0.511 | +| clip_range | 0.2 | +| entropy_loss | -0.441 | +| explained_variance | -1.34 | +| learning_rate | 0.0001 | +| loss | -0.0755 | +| n_updates | 121810 | +| policy_gradient_loss | -0.0653 | +| value_loss | 0.000384 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.63e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 309 | +| iterations | 6130 | +| time_elapsed | 20274 | +| total_timesteps | 6277120 | +| train/ | | +| approx_kl | 2.5325513 | +| clip_fraction | 0.453 | +| clip_range | 0.2 | +| entropy_loss | -0.334 | +| explained_variance | -2.26 | +| learning_rate | 0.0001 | +| loss | -0.0684 | +| n_updates | 121820 | +| policy_gradient_loss | -0.0556 | +| value_loss | 0.000561 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.63e+03 | +| ep_rew_mean | 0.286 | +| time/ | | +| fps | 309 | +| iterations | 6131 | +| time_elapsed | 20278 | +| total_timesteps | 6278144 | +| train/ | | +| approx_kl | 2.5927734 | +| clip_fraction | 0.445 | +| clip_range | 0.2 | +| entropy_loss | -0.311 | +| explained_variance | -0.973 | +| learning_rate | 0.0001 | +| loss | -0.0852 | +| n_updates | 121830 | +| policy_gradient_loss | -0.0617 | +| value_loss | 0.000463 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.63e+03 | +| ep_rew_mean | 0.286 | +| time/ | | +| fps | 309 | +| iterations | 6132 | +| time_elapsed | 20281 | +| total_timesteps | 6279168 | +| train/ | | +| approx_kl | 1.7891581 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.418 | +| explained_variance | -0.717 | +| learning_rate | 0.0001 | +| loss | -0.0903 | +| n_updates | 121840 | +| policy_gradient_loss | -0.0626 | +| value_loss | 0.00042 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.62e+03 | +| ep_rew_mean | 0.286 | +| time/ | | +| fps | 309 | +| iterations | 6133 | +| time_elapsed | 20285 | +| total_timesteps | 6280192 | +| train/ | | +| approx_kl | 3.1081219 | +| clip_fraction | 0.496 | +| clip_range | 0.2 | +| entropy_loss | -0.376 | +| explained_variance | -1.53 | +| learning_rate | 0.0001 | +| loss | -0.0868 | +| n_updates | 121850 | +| policy_gradient_loss | -0.0677 | +| value_loss | 0.000334 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.62e+03 | +| ep_rew_mean | 0.288 | +| time/ | | +| fps | 309 | +| iterations | 6134 | +| time_elapsed | 20288 | +| total_timesteps | 6281216 | +| train/ | | +| approx_kl | 4.6474957 | +| clip_fraction | 0.49 | +| clip_range | 0.2 | +| entropy_loss | -0.34 | +| explained_variance | -0.884 | +| learning_rate | 0.0001 | +| loss | -0.0756 | +| n_updates | 121860 | +| policy_gradient_loss | -0.064 | +| value_loss | 0.000763 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.62e+03 | +| ep_rew_mean | 0.288 | +| time/ | | +| fps | 309 | +| iterations | 6135 | +| time_elapsed | 20291 | +| total_timesteps | 6282240 | +| train/ | | +| approx_kl | 2.4687593 | +| clip_fraction | 0.477 | +| clip_range | 0.2 | +| entropy_loss | -0.351 | +| explained_variance | -1.03 | +| learning_rate | 0.0001 | +| loss | -0.117 | +| n_updates | 121870 | +| policy_gradient_loss | -0.067 | +| value_loss | 0.000441 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.62e+03 | +| ep_rew_mean | 0.29 | +| time/ | | +| fps | 309 | +| iterations | 6136 | +| time_elapsed | 20295 | +| total_timesteps | 6283264 | +| train/ | | +| approx_kl | 2.298621 | +| clip_fraction | 0.479 | +| clip_range | 0.2 | +| entropy_loss | -0.382 | +| explained_variance | -1.75 | +| learning_rate | 0.0001 | +| loss | -0.0896 | +| n_updates | 121880 | +| policy_gradient_loss | -0.0733 | +| value_loss | 0.000393 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.62e+03 | +| ep_rew_mean | 0.291 | +| time/ | | +| fps | 309 | +| iterations | 6137 | +| time_elapsed | 20298 | +| total_timesteps | 6284288 | +| train/ | | +| approx_kl | 3.7204583 | +| clip_fraction | 0.468 | +| clip_range | 0.2 | +| entropy_loss | -0.357 | +| explained_variance | -0.876 | +| learning_rate | 0.0001 | +| loss | -0.0836 | +| n_updates | 121890 | +| policy_gradient_loss | -0.066 | +| value_loss | 0.000468 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.62e+03 | +| ep_rew_mean | 0.291 | +| time/ | | +| fps | 309 | +| iterations | 6138 | +| time_elapsed | 20301 | +| total_timesteps | 6285312 | +| train/ | | +| approx_kl | 2.263535 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.375 | +| explained_variance | -0.495 | +| learning_rate | 0.0001 | +| loss | -0.0864 | +| n_updates | 121900 | +| policy_gradient_loss | -0.0647 | +| value_loss | 0.000517 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | 0.294 | +| time/ | | +| fps | 309 | +| iterations | 6139 | +| time_elapsed | 20304 | +| total_timesteps | 6286336 | +| train/ | | +| approx_kl | 2.3924952 | +| clip_fraction | 0.465 | +| clip_range | 0.2 | +| entropy_loss | -0.348 | +| explained_variance | -0.617 | +| learning_rate | 0.0001 | +| loss | -0.0868 | +| n_updates | 121910 | +| policy_gradient_loss | -0.0602 | +| value_loss | 0.000602 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | 0.294 | +| time/ | | +| fps | 309 | +| iterations | 6140 | +| time_elapsed | 20307 | +| total_timesteps | 6287360 | +| train/ | | +| approx_kl | 4.0796347 | +| clip_fraction | 0.519 | +| clip_range | 0.2 | +| entropy_loss | -0.301 | +| explained_variance | -1.01 | +| learning_rate | 0.0001 | +| loss | -0.0918 | +| n_updates | 121920 | +| policy_gradient_loss | -0.0694 | +| value_loss | 0.000948 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | 0.29 | +| time/ | | +| fps | 309 | +| iterations | 6141 | +| time_elapsed | 20310 | +| total_timesteps | 6288384 | +| train/ | | +| approx_kl | 15.649936 | +| clip_fraction | 0.504 | +| clip_range | 0.2 | +| entropy_loss | -0.462 | +| explained_variance | -5.69 | +| learning_rate | 0.0001 | +| loss | -0.0885 | +| n_updates | 121930 | +| policy_gradient_loss | -0.0597 | +| value_loss | 0.000304 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | 0.29 | +| time/ | | +| fps | 309 | +| iterations | 6142 | +| time_elapsed | 20314 | +| total_timesteps | 6289408 | +| train/ | | +| approx_kl | 1.9352653 | +| clip_fraction | 0.495 | +| clip_range | 0.2 | +| entropy_loss | -0.411 | +| explained_variance | -1.05 | +| learning_rate | 0.0001 | +| loss | -0.0839 | +| n_updates | 121940 | +| policy_gradient_loss | -0.0689 | +| value_loss | 0.000304 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | 0.29 | +| time/ | | +| fps | 309 | +| iterations | 6143 | +| time_elapsed | 20317 | +| total_timesteps | 6290432 | +| train/ | | +| approx_kl | 2.3174071 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.334 | +| explained_variance | -1.57 | +| learning_rate | 0.0001 | +| loss | -0.0703 | +| n_updates | 121950 | +| policy_gradient_loss | -0.0715 | +| value_loss | 0.000519 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | 0.287 | +| time/ | | +| fps | 309 | +| iterations | 6144 | +| time_elapsed | 20320 | +| total_timesteps | 6291456 | +| train/ | | +| approx_kl | 2.5777388 | +| clip_fraction | 0.503 | +| clip_range | 0.2 | +| entropy_loss | -0.383 | +| explained_variance | -1.13 | +| learning_rate | 0.0001 | +| loss | -0.0898 | +| n_updates | 121960 | +| policy_gradient_loss | -0.067 | +| value_loss | 0.000474 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | 0.287 | +| time/ | | +| fps | 309 | +| iterations | 6145 | +| time_elapsed | 20324 | +| total_timesteps | 6292480 | +| train/ | | +| approx_kl | 2.3229957 | +| clip_fraction | 0.477 | +| clip_range | 0.2 | +| entropy_loss | -0.401 | +| explained_variance | -0.805 | +| learning_rate | 0.0001 | +| loss | -0.108 | +| n_updates | 121970 | +| policy_gradient_loss | -0.0734 | +| value_loss | 0.000445 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | 0.285 | +| time/ | | +| fps | 309 | +| iterations | 6146 | +| time_elapsed | 20327 | +| total_timesteps | 6293504 | +| train/ | | +| approx_kl | 2.9523158 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.42 | +| explained_variance | -0.604 | +| learning_rate | 0.0001 | +| loss | -0.0985 | +| n_updates | 121980 | +| policy_gradient_loss | -0.0655 | +| value_loss | 0.000698 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | 0.285 | +| time/ | | +| fps | 309 | +| iterations | 6147 | +| time_elapsed | 20331 | +| total_timesteps | 6294528 | +| train/ | | +| approx_kl | 5.014487 | +| clip_fraction | 0.569 | +| clip_range | 0.2 | +| entropy_loss | -0.345 | +| explained_variance | -0.829 | +| learning_rate | 0.0001 | +| loss | -0.0738 | +| n_updates | 121990 | +| policy_gradient_loss | -0.0615 | +| value_loss | 0.000442 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | 0.283 | +| time/ | | +| fps | 309 | +| iterations | 6148 | +| time_elapsed | 20334 | +| total_timesteps | 6295552 | +| train/ | | +| approx_kl | 2.2095647 | +| clip_fraction | 0.49 | +| clip_range | 0.2 | +| entropy_loss | -0.392 | +| explained_variance | -3.52 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 122000 | +| policy_gradient_loss | -0.0718 | +| value_loss | 0.000623 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | 0.289 | +| time/ | | +| fps | 309 | +| iterations | 6149 | +| time_elapsed | 20337 | +| total_timesteps | 6296576 | +| train/ | | +| approx_kl | 2.5202036 | +| clip_fraction | 0.506 | +| clip_range | 0.2 | +| entropy_loss | -0.351 | +| explained_variance | -0.295 | +| learning_rate | 0.0001 | +| loss | -0.0816 | +| n_updates | 122010 | +| policy_gradient_loss | -0.0676 | +| value_loss | 0.000618 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.58e+03 | +| ep_rew_mean | 0.284 | +| time/ | | +| fps | 309 | +| iterations | 6150 | +| time_elapsed | 20341 | +| total_timesteps | 6297600 | +| train/ | | +| approx_kl | 2.0062392 | +| clip_fraction | 0.508 | +| clip_range | 0.2 | +| entropy_loss | -0.423 | +| explained_variance | -1.13 | +| learning_rate | 0.0001 | +| loss | -0.0688 | +| n_updates | 122020 | +| policy_gradient_loss | -0.0513 | +| value_loss | 0.000589 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.57e+03 | +| ep_rew_mean | 0.287 | +| time/ | | +| fps | 309 | +| iterations | 6151 | +| time_elapsed | 20344 | +| total_timesteps | 6298624 | +| train/ | | +| approx_kl | 2.2103548 | +| clip_fraction | 0.474 | +| clip_range | 0.2 | +| entropy_loss | -0.383 | +| explained_variance | -1.01 | +| learning_rate | 0.0001 | +| loss | -0.0911 | +| n_updates | 122030 | +| policy_gradient_loss | -0.0712 | +| value_loss | 0.00058 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.57e+03 | +| ep_rew_mean | 0.287 | +| time/ | | +| fps | 309 | +| iterations | 6152 | +| time_elapsed | 20347 | +| total_timesteps | 6299648 | +| train/ | | +| approx_kl | 2.1385384 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.394 | +| explained_variance | -1.65 | +| learning_rate | 0.0001 | +| loss | -0.0649 | +| n_updates | 122040 | +| policy_gradient_loss | -0.0668 | +| value_loss | 0.000584 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.58e+03 | +| ep_rew_mean | 0.288 | +| time/ | | +| fps | 309 | +| iterations | 6153 | +| time_elapsed | 20350 | +| total_timesteps | 6300672 | +| train/ | | +| approx_kl | 1.8851049 | +| clip_fraction | 0.529 | +| clip_range | 0.2 | +| entropy_loss | -0.406 | +| explained_variance | -1.65 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 122050 | +| policy_gradient_loss | -0.0756 | +| value_loss | 0.000371 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.58e+03 | +| ep_rew_mean | 0.288 | +| time/ | | +| fps | 309 | +| iterations | 6154 | +| time_elapsed | 20353 | +| total_timesteps | 6301696 | +| train/ | | +| approx_kl | 1.9908124 | +| clip_fraction | 0.485 | +| clip_range | 0.2 | +| entropy_loss | -0.419 | +| explained_variance | -2.39 | +| learning_rate | 0.0001 | +| loss | -0.0735 | +| n_updates | 122060 | +| policy_gradient_loss | -0.0669 | +| value_loss | 0.000237 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.58e+03 | +| ep_rew_mean | 0.288 | +| time/ | | +| fps | 309 | +| iterations | 6155 | +| time_elapsed | 20357 | +| total_timesteps | 6302720 | +| train/ | | +| approx_kl | 2.1217747 | +| clip_fraction | 0.497 | +| clip_range | 0.2 | +| entropy_loss | -0.427 | +| explained_variance | -1.08 | +| learning_rate | 0.0001 | +| loss | -0.0842 | +| n_updates | 122070 | +| policy_gradient_loss | -0.0647 | +| value_loss | 0.00056 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | 0.284 | +| time/ | | +| fps | 309 | +| iterations | 6156 | +| time_elapsed | 20360 | +| total_timesteps | 6303744 | +| train/ | | +| approx_kl | 1.8501308 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.432 | +| explained_variance | -4.06 | +| learning_rate | 0.0001 | +| loss | -0.105 | +| n_updates | 122080 | +| policy_gradient_loss | -0.0719 | +| value_loss | 0.000433 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | 0.283 | +| time/ | | +| fps | 309 | +| iterations | 6157 | +| time_elapsed | 20363 | +| total_timesteps | 6304768 | +| train/ | | +| approx_kl | 1.8817399 | +| clip_fraction | 0.476 | +| clip_range | 0.2 | +| entropy_loss | -0.407 | +| explained_variance | -1.06 | +| learning_rate | 0.0001 | +| loss | -0.0535 | +| n_updates | 122090 | +| policy_gradient_loss | -0.0594 | +| value_loss | 0.000405 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | 0.281 | +| time/ | | +| fps | 309 | +| iterations | 6158 | +| time_elapsed | 20366 | +| total_timesteps | 6305792 | +| train/ | | +| approx_kl | 1.9515549 | +| clip_fraction | 0.493 | +| clip_range | 0.2 | +| entropy_loss | -0.38 | +| explained_variance | -0.967 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 122100 | +| policy_gradient_loss | -0.0677 | +| value_loss | 0.00043 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | 0.281 | +| time/ | | +| fps | 309 | +| iterations | 6159 | +| time_elapsed | 20369 | +| total_timesteps | 6306816 | +| train/ | | +| approx_kl | 2.450985 | +| clip_fraction | 0.482 | +| clip_range | 0.2 | +| entropy_loss | -0.368 | +| explained_variance | -2.12 | +| learning_rate | 0.0001 | +| loss | -0.056 | +| n_updates | 122110 | +| policy_gradient_loss | -0.0653 | +| value_loss | 0.000598 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | 0.284 | +| time/ | | +| fps | 309 | +| iterations | 6160 | +| time_elapsed | 20372 | +| total_timesteps | 6307840 | +| train/ | | +| approx_kl | 1.8258749 | +| clip_fraction | 0.509 | +| clip_range | 0.2 | +| entropy_loss | -0.448 | +| explained_variance | -1.23 | +| learning_rate | 0.0001 | +| loss | -0.0897 | +| n_updates | 122120 | +| policy_gradient_loss | -0.069 | +| value_loss | 0.000459 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | 0.284 | +| time/ | | +| fps | 309 | +| iterations | 6161 | +| time_elapsed | 20376 | +| total_timesteps | 6308864 | +| train/ | | +| approx_kl | 1.7673752 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.436 | +| explained_variance | -1.36 | +| learning_rate | 0.0001 | +| loss | -0.0939 | +| n_updates | 122130 | +| policy_gradient_loss | -0.059 | +| value_loss | 0.000311 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | 0.289 | +| time/ | | +| fps | 309 | +| iterations | 6162 | +| time_elapsed | 20379 | +| total_timesteps | 6309888 | +| train/ | | +| approx_kl | 1.9005191 | +| clip_fraction | 0.477 | +| clip_range | 0.2 | +| entropy_loss | -0.362 | +| explained_variance | -0.824 | +| learning_rate | 0.0001 | +| loss | -0.0921 | +| n_updates | 122140 | +| policy_gradient_loss | -0.0678 | +| value_loss | 0.000695 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | 0.289 | +| time/ | | +| fps | 309 | +| iterations | 6163 | +| time_elapsed | 20382 | +| total_timesteps | 6310912 | +| train/ | | +| approx_kl | 1.8729744 | +| clip_fraction | 0.459 | +| clip_range | 0.2 | +| entropy_loss | -0.357 | +| explained_variance | -3.17 | +| learning_rate | 0.0001 | +| loss | -0.0831 | +| n_updates | 122150 | +| policy_gradient_loss | -0.0568 | +| value_loss | 0.000433 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | 0.289 | +| time/ | | +| fps | 309 | +| iterations | 6164 | +| time_elapsed | 20385 | +| total_timesteps | 6311936 | +| train/ | | +| approx_kl | 3.5156841 | +| clip_fraction | 0.57 | +| clip_range | 0.2 | +| entropy_loss | -0.504 | +| explained_variance | -1.27 | +| learning_rate | 0.0001 | +| loss | -0.0756 | +| n_updates | 122160 | +| policy_gradient_loss | -0.0569 | +| value_loss | 0.000201 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | 0.288 | +| time/ | | +| fps | 309 | +| iterations | 6165 | +| time_elapsed | 20389 | +| total_timesteps | 6312960 | +| train/ | | +| approx_kl | 1.9421604 | +| clip_fraction | 0.485 | +| clip_range | 0.2 | +| entropy_loss | -0.406 | +| explained_variance | -0.809 | +| learning_rate | 0.0001 | +| loss | -0.0717 | +| n_updates | 122170 | +| policy_gradient_loss | -0.0612 | +| value_loss | 0.000395 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.58e+03 | +| ep_rew_mean | 0.283 | +| time/ | | +| fps | 309 | +| iterations | 6166 | +| time_elapsed | 20392 | +| total_timesteps | 6313984 | +| train/ | | +| approx_kl | 2.4261603 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.386 | +| explained_variance | -0.61 | +| learning_rate | 0.0001 | +| loss | -0.0989 | +| n_updates | 122180 | +| policy_gradient_loss | -0.0664 | +| value_loss | 0.000381 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.58e+03 | +| ep_rew_mean | 0.283 | +| time/ | | +| fps | 309 | +| iterations | 6167 | +| time_elapsed | 20396 | +| total_timesteps | 6315008 | +| train/ | | +| approx_kl | 1.6318197 | +| clip_fraction | 0.469 | +| clip_range | 0.2 | +| entropy_loss | -0.379 | +| explained_variance | -1.02 | +| learning_rate | 0.0001 | +| loss | -0.0977 | +| n_updates | 122190 | +| policy_gradient_loss | -0.0731 | +| value_loss | 0.000297 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.58e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 309 | +| iterations | 6168 | +| time_elapsed | 20399 | +| total_timesteps | 6316032 | +| train/ | | +| approx_kl | 2.2494044 | +| clip_fraction | 0.512 | +| clip_range | 0.2 | +| entropy_loss | -0.438 | +| explained_variance | -1.01 | +| learning_rate | 0.0001 | +| loss | -0.0687 | +| n_updates | 122200 | +| policy_gradient_loss | -0.0729 | +| value_loss | 0.000488 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.58e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 309 | +| iterations | 6169 | +| time_elapsed | 20403 | +| total_timesteps | 6317056 | +| train/ | | +| approx_kl | 2.5971208 | +| clip_fraction | 0.436 | +| clip_range | 0.2 | +| entropy_loss | -0.332 | +| explained_variance | -1.93 | +| learning_rate | 0.0001 | +| loss | -0.069 | +| n_updates | 122210 | +| policy_gradient_loss | -0.0586 | +| value_loss | 0.000418 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.58e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 309 | +| iterations | 6170 | +| time_elapsed | 20406 | +| total_timesteps | 6318080 | +| train/ | | +| approx_kl | 1.8619876 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.385 | +| explained_variance | -0.53 | +| learning_rate | 0.0001 | +| loss | -0.0946 | +| n_updates | 122220 | +| policy_gradient_loss | -0.0615 | +| value_loss | 0.00045 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.58e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 309 | +| iterations | 6171 | +| time_elapsed | 20410 | +| total_timesteps | 6319104 | +| train/ | | +| approx_kl | 2.3407564 | +| clip_fraction | 0.469 | +| clip_range | 0.2 | +| entropy_loss | -0.327 | +| explained_variance | -2.29 | +| learning_rate | 0.0001 | +| loss | -0.0832 | +| n_updates | 122230 | +| policy_gradient_loss | -0.0595 | +| value_loss | 0.000435 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 309 | +| iterations | 6172 | +| time_elapsed | 20413 | +| total_timesteps | 6320128 | +| train/ | | +| approx_kl | 1.8913198 | +| clip_fraction | 0.504 | +| clip_range | 0.2 | +| entropy_loss | -0.445 | +| explained_variance | -5.01 | +| learning_rate | 0.0001 | +| loss | -0.0804 | +| n_updates | 122240 | +| policy_gradient_loss | -0.068 | +| value_loss | 0.000351 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 309 | +| iterations | 6173 | +| time_elapsed | 20416 | +| total_timesteps | 6321152 | +| train/ | | +| approx_kl | 2.2055116 | +| clip_fraction | 0.482 | +| clip_range | 0.2 | +| entropy_loss | -0.396 | +| explained_variance | -0.707 | +| learning_rate | 0.0001 | +| loss | -0.0946 | +| n_updates | 122250 | +| policy_gradient_loss | -0.0613 | +| value_loss | 0.000466 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | 0.277 | +| time/ | | +| fps | 309 | +| iterations | 6174 | +| time_elapsed | 20419 | +| total_timesteps | 6322176 | +| train/ | | +| approx_kl | 2.0721397 | +| clip_fraction | 0.477 | +| clip_range | 0.2 | +| entropy_loss | -0.396 | +| explained_variance | -0.831 | +| learning_rate | 0.0001 | +| loss | -0.0889 | +| n_updates | 122260 | +| policy_gradient_loss | -0.0605 | +| value_loss | 0.000554 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | 0.277 | +| time/ | | +| fps | 309 | +| iterations | 6175 | +| time_elapsed | 20422 | +| total_timesteps | 6323200 | +| train/ | | +| approx_kl | 2.2358654 | +| clip_fraction | 0.549 | +| clip_range | 0.2 | +| entropy_loss | -0.482 | +| explained_variance | -0.875 | +| learning_rate | 0.0001 | +| loss | -0.112 | +| n_updates | 122270 | +| policy_gradient_loss | -0.0718 | +| value_loss | 0.000458 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | 0.28 | +| time/ | | +| fps | 309 | +| iterations | 6176 | +| time_elapsed | 20426 | +| total_timesteps | 6324224 | +| train/ | | +| approx_kl | 2.1998968 | +| clip_fraction | 0.49 | +| clip_range | 0.2 | +| entropy_loss | -0.428 | +| explained_variance | -1.28 | +| learning_rate | 0.0001 | +| loss | -0.0673 | +| n_updates | 122280 | +| policy_gradient_loss | -0.0646 | +| value_loss | 0.000454 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | 0.28 | +| time/ | | +| fps | 309 | +| iterations | 6177 | +| time_elapsed | 20429 | +| total_timesteps | 6325248 | +| train/ | | +| approx_kl | 1.688043 | +| clip_fraction | 0.497 | +| clip_range | 0.2 | +| entropy_loss | -0.418 | +| explained_variance | -0.595 | +| learning_rate | 0.0001 | +| loss | -0.0807 | +| n_updates | 122290 | +| policy_gradient_loss | -0.0615 | +| value_loss | 0.000276 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.61e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 309 | +| iterations | 6178 | +| time_elapsed | 20432 | +| total_timesteps | 6326272 | +| train/ | | +| approx_kl | 1.9955266 | +| clip_fraction | 0.523 | +| clip_range | 0.2 | +| entropy_loss | -0.452 | +| explained_variance | -1.66 | +| learning_rate | 0.0001 | +| loss | -0.0776 | +| n_updates | 122300 | +| policy_gradient_loss | -0.0678 | +| value_loss | 0.000283 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.61e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 309 | +| iterations | 6179 | +| time_elapsed | 20435 | +| total_timesteps | 6327296 | +| train/ | | +| approx_kl | 1.9445794 | +| clip_fraction | 0.488 | +| clip_range | 0.2 | +| entropy_loss | -0.407 | +| explained_variance | -0.868 | +| learning_rate | 0.0001 | +| loss | -0.0821 | +| n_updates | 122310 | +| policy_gradient_loss | -0.0634 | +| value_loss | 0.000465 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.61e+03 | +| ep_rew_mean | 0.281 | +| time/ | | +| fps | 309 | +| iterations | 6180 | +| time_elapsed | 20438 | +| total_timesteps | 6328320 | +| train/ | | +| approx_kl | 2.8067703 | +| clip_fraction | 0.486 | +| clip_range | 0.2 | +| entropy_loss | -0.46 | +| explained_variance | -3.34 | +| learning_rate | 0.0001 | +| loss | -0.077 | +| n_updates | 122320 | +| policy_gradient_loss | -0.0661 | +| value_loss | 0.000604 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.61e+03 | +| ep_rew_mean | 0.281 | +| time/ | | +| fps | 309 | +| iterations | 6181 | +| time_elapsed | 20442 | +| total_timesteps | 6329344 | +| train/ | | +| approx_kl | 2.9256277 | +| clip_fraction | 0.488 | +| clip_range | 0.2 | +| entropy_loss | -0.393 | +| explained_variance | -1.68 | +| learning_rate | 0.0001 | +| loss | -0.0839 | +| n_updates | 122330 | +| policy_gradient_loss | -0.0678 | +| value_loss | 0.000468 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.61e+03 | +| ep_rew_mean | 0.285 | +| time/ | | +| fps | 309 | +| iterations | 6182 | +| time_elapsed | 20446 | +| total_timesteps | 6330368 | +| train/ | | +| approx_kl | 3.1531942 | +| clip_fraction | 0.512 | +| clip_range | 0.2 | +| entropy_loss | -0.397 | +| explained_variance | -0.392 | +| learning_rate | 0.0001 | +| loss | -0.0905 | +| n_updates | 122340 | +| policy_gradient_loss | -0.0721 | +| value_loss | 0.000419 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.61e+03 | +| ep_rew_mean | 0.285 | +| time/ | | +| fps | 309 | +| iterations | 6183 | +| time_elapsed | 20449 | +| total_timesteps | 6331392 | +| train/ | | +| approx_kl | 2.1209676 | +| clip_fraction | 0.495 | +| clip_range | 0.2 | +| entropy_loss | -0.39 | +| explained_variance | -0.824 | +| learning_rate | 0.0001 | +| loss | -0.0944 | +| n_updates | 122350 | +| policy_gradient_loss | -0.0692 | +| value_loss | 0.000489 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.62e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 309 | +| iterations | 6184 | +| time_elapsed | 20453 | +| total_timesteps | 6332416 | +| train/ | | +| approx_kl | 1.9049325 | +| clip_fraction | 0.495 | +| clip_range | 0.2 | +| entropy_loss | -0.435 | +| explained_variance | -1.72 | +| learning_rate | 0.0001 | +| loss | -0.0708 | +| n_updates | 122360 | +| policy_gradient_loss | -0.0638 | +| value_loss | 0.00034 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.62e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 309 | +| iterations | 6185 | +| time_elapsed | 20456 | +| total_timesteps | 6333440 | +| train/ | | +| approx_kl | 1.7440577 | +| clip_fraction | 0.461 | +| clip_range | 0.2 | +| entropy_loss | -0.401 | +| explained_variance | -1.06 | +| learning_rate | 0.0001 | +| loss | -0.0896 | +| n_updates | 122370 | +| policy_gradient_loss | -0.0628 | +| value_loss | 0.000426 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.62e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 309 | +| iterations | 6186 | +| time_elapsed | 20460 | +| total_timesteps | 6334464 | +| train/ | | +| approx_kl | 2.6476316 | +| clip_fraction | 0.521 | +| clip_range | 0.2 | +| entropy_loss | -0.437 | +| explained_variance | -1.33 | +| learning_rate | 0.0001 | +| loss | -0.0852 | +| n_updates | 122380 | +| policy_gradient_loss | -0.0536 | +| value_loss | 0.000488 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.62e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 309 | +| iterations | 6187 | +| time_elapsed | 20463 | +| total_timesteps | 6335488 | +| train/ | | +| approx_kl | 1.536952 | +| clip_fraction | 0.47 | +| clip_range | 0.2 | +| entropy_loss | -0.391 | +| explained_variance | -1.61 | +| learning_rate | 0.0001 | +| loss | -0.0893 | +| n_updates | 122390 | +| policy_gradient_loss | -0.057 | +| value_loss | 0.000543 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.63e+03 | +| ep_rew_mean | 0.28 | +| time/ | | +| fps | 309 | +| iterations | 6188 | +| time_elapsed | 20467 | +| total_timesteps | 6336512 | +| train/ | | +| approx_kl | 2.223442 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.401 | +| explained_variance | -1.25 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 122400 | +| policy_gradient_loss | -0.0694 | +| value_loss | 0.000433 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.63e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 309 | +| iterations | 6189 | +| time_elapsed | 20470 | +| total_timesteps | 6337536 | +| train/ | | +| approx_kl | 2.3870578 | +| clip_fraction | 0.496 | +| clip_range | 0.2 | +| entropy_loss | -0.373 | +| explained_variance | -2.47 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 122410 | +| policy_gradient_loss | -0.07 | +| value_loss | 0.000432 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.62e+03 | +| ep_rew_mean | 0.268 | +| time/ | | +| fps | 309 | +| iterations | 6190 | +| time_elapsed | 20473 | +| total_timesteps | 6338560 | +| train/ | | +| approx_kl | 1.81403 | +| clip_fraction | 0.469 | +| clip_range | 0.2 | +| entropy_loss | -0.409 | +| explained_variance | -1.74 | +| learning_rate | 0.0001 | +| loss | -0.0694 | +| n_updates | 122420 | +| policy_gradient_loss | -0.0662 | +| value_loss | 0.000406 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.62e+03 | +| ep_rew_mean | 0.268 | +| time/ | | +| fps | 309 | +| iterations | 6191 | +| time_elapsed | 20477 | +| total_timesteps | 6339584 | +| train/ | | +| approx_kl | 1.7539995 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.413 | +| explained_variance | -1.33 | +| learning_rate | 0.0001 | +| loss | -0.082 | +| n_updates | 122430 | +| policy_gradient_loss | -0.0625 | +| value_loss | 0.000274 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.62e+03 | +| ep_rew_mean | 0.27 | +| time/ | | +| fps | 309 | +| iterations | 6192 | +| time_elapsed | 20480 | +| total_timesteps | 6340608 | +| train/ | | +| approx_kl | 1.8001771 | +| clip_fraction | 0.498 | +| clip_range | 0.2 | +| entropy_loss | -0.41 | +| explained_variance | -0.567 | +| learning_rate | 0.0001 | +| loss | -0.0733 | +| n_updates | 122440 | +| policy_gradient_loss | -0.0566 | +| value_loss | 0.000502 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.62e+03 | +| ep_rew_mean | 0.27 | +| time/ | | +| fps | 309 | +| iterations | 6193 | +| time_elapsed | 20483 | +| total_timesteps | 6341632 | +| train/ | | +| approx_kl | 2.3239205 | +| clip_fraction | 0.476 | +| clip_range | 0.2 | +| entropy_loss | -0.359 | +| explained_variance | -1.54 | +| learning_rate | 0.0001 | +| loss | -0.0553 | +| n_updates | 122450 | +| policy_gradient_loss | -0.0622 | +| value_loss | 0.000822 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.62e+03 | +| ep_rew_mean | 0.27 | +| time/ | | +| fps | 309 | +| iterations | 6194 | +| time_elapsed | 20486 | +| total_timesteps | 6342656 | +| train/ | | +| approx_kl | 4.4341383 | +| clip_fraction | 0.49 | +| clip_range | 0.2 | +| entropy_loss | -0.415 | +| explained_variance | -0.156 | +| learning_rate | 0.0001 | +| loss | -0.0739 | +| n_updates | 122460 | +| policy_gradient_loss | -0.0691 | +| value_loss | 0.000859 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.62e+03 | +| ep_rew_mean | 0.277 | +| time/ | | +| fps | 309 | +| iterations | 6195 | +| time_elapsed | 20489 | +| total_timesteps | 6343680 | +| train/ | | +| approx_kl | 2.2418857 | +| clip_fraction | 0.498 | +| clip_range | 0.2 | +| entropy_loss | -0.431 | +| explained_variance | -1.48 | +| learning_rate | 0.0001 | +| loss | -0.0982 | +| n_updates | 122470 | +| policy_gradient_loss | -0.0674 | +| value_loss | 0.000611 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.62e+03 | +| ep_rew_mean | 0.277 | +| time/ | | +| fps | 309 | +| iterations | 6196 | +| time_elapsed | 20492 | +| total_timesteps | 6344704 | +| train/ | | +| approx_kl | 2.4450765 | +| clip_fraction | 0.497 | +| clip_range | 0.2 | +| entropy_loss | -0.368 | +| explained_variance | -1.55 | +| learning_rate | 0.0001 | +| loss | -0.0899 | +| n_updates | 122480 | +| policy_gradient_loss | -0.0687 | +| value_loss | 0.000859 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.63e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 309 | +| iterations | 6197 | +| time_elapsed | 20496 | +| total_timesteps | 6345728 | +| train/ | | +| approx_kl | 3.8975005 | +| clip_fraction | 0.509 | +| clip_range | 0.2 | +| entropy_loss | -0.397 | +| explained_variance | -2.55 | +| learning_rate | 0.0001 | +| loss | -0.124 | +| n_updates | 122490 | +| policy_gradient_loss | -0.0718 | +| value_loss | 0.000469 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.63e+03 | +| ep_rew_mean | 0.273 | +| time/ | | +| fps | 309 | +| iterations | 6198 | +| time_elapsed | 20499 | +| total_timesteps | 6346752 | +| train/ | | +| approx_kl | 3.1172824 | +| clip_fraction | 0.54 | +| clip_range | 0.2 | +| entropy_loss | -0.426 | +| explained_variance | -0.77 | +| learning_rate | 0.0001 | +| loss | -0.0822 | +| n_updates | 122500 | +| policy_gradient_loss | -0.0604 | +| value_loss | 0.000612 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.62e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 309 | +| iterations | 6199 | +| time_elapsed | 20502 | +| total_timesteps | 6347776 | +| train/ | | +| approx_kl | 4.0656767 | +| clip_fraction | 0.509 | +| clip_range | 0.2 | +| entropy_loss | -0.433 | +| explained_variance | -1.21 | +| learning_rate | 0.0001 | +| loss | -0.0972 | +| n_updates | 122510 | +| policy_gradient_loss | -0.0664 | +| value_loss | 0.000444 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.62e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 309 | +| iterations | 6200 | +| time_elapsed | 20506 | +| total_timesteps | 6348800 | +| train/ | | +| approx_kl | 1.8870819 | +| clip_fraction | 0.494 | +| clip_range | 0.2 | +| entropy_loss | -0.399 | +| explained_variance | -0.373 | +| learning_rate | 0.0001 | +| loss | -0.0852 | +| n_updates | 122520 | +| policy_gradient_loss | -0.0681 | +| value_loss | 0.000752 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.62e+03 | +| ep_rew_mean | 0.276 | +| time/ | | +| fps | 309 | +| iterations | 6201 | +| time_elapsed | 20509 | +| total_timesteps | 6349824 | +| train/ | | +| approx_kl | 1.7389169 | +| clip_fraction | 0.492 | +| clip_range | 0.2 | +| entropy_loss | -0.48 | +| explained_variance | -4.99 | +| learning_rate | 0.0001 | +| loss | -0.0911 | +| n_updates | 122530 | +| policy_gradient_loss | -0.0649 | +| value_loss | 0.000298 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.62e+03 | +| ep_rew_mean | 0.278 | +| time/ | | +| fps | 309 | +| iterations | 6202 | +| time_elapsed | 20513 | +| total_timesteps | 6350848 | +| train/ | | +| approx_kl | 2.8429198 | +| clip_fraction | 0.472 | +| clip_range | 0.2 | +| entropy_loss | -0.394 | +| explained_variance | -0.418 | +| learning_rate | 0.0001 | +| loss | -0.0673 | +| n_updates | 122540 | +| policy_gradient_loss | -0.0625 | +| value_loss | 0.000476 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.62e+03 | +| ep_rew_mean | 0.278 | +| time/ | | +| fps | 309 | +| iterations | 6203 | +| time_elapsed | 20517 | +| total_timesteps | 6351872 | +| train/ | | +| approx_kl | 1.8656725 | +| clip_fraction | 0.494 | +| clip_range | 0.2 | +| entropy_loss | -0.437 | +| explained_variance | -1.25 | +| learning_rate | 0.0001 | +| loss | -0.108 | +| n_updates | 122550 | +| policy_gradient_loss | -0.0664 | +| value_loss | 0.000429 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.62e+03 | +| ep_rew_mean | 0.28 | +| time/ | | +| fps | 309 | +| iterations | 6204 | +| time_elapsed | 20520 | +| total_timesteps | 6352896 | +| train/ | | +| approx_kl | 2.109179 | +| clip_fraction | 0.506 | +| clip_range | 0.2 | +| entropy_loss | -0.398 | +| explained_variance | -0.428 | +| learning_rate | 0.0001 | +| loss | -0.0734 | +| n_updates | 122560 | +| policy_gradient_loss | -0.0646 | +| value_loss | 0.000551 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.62e+03 | +| ep_rew_mean | 0.28 | +| time/ | | +| fps | 309 | +| iterations | 6205 | +| time_elapsed | 20523 | +| total_timesteps | 6353920 | +| train/ | | +| approx_kl | 2.1552467 | +| clip_fraction | 0.473 | +| clip_range | 0.2 | +| entropy_loss | -0.381 | +| explained_variance | -1.15 | +| learning_rate | 0.0001 | +| loss | -0.0802 | +| n_updates | 122570 | +| policy_gradient_loss | -0.0577 | +| value_loss | 0.000709 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.62e+03 | +| ep_rew_mean | 0.277 | +| time/ | | +| fps | 309 | +| iterations | 6206 | +| time_elapsed | 20527 | +| total_timesteps | 6354944 | +| train/ | | +| approx_kl | 1.7164325 | +| clip_fraction | 0.502 | +| clip_range | 0.2 | +| entropy_loss | -0.45 | +| explained_variance | -3.01 | +| learning_rate | 0.0001 | +| loss | -0.0891 | +| n_updates | 122580 | +| policy_gradient_loss | -0.0722 | +| value_loss | 0.000374 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.63e+03 | +| ep_rew_mean | 0.274 | +| time/ | | +| fps | 309 | +| iterations | 6207 | +| time_elapsed | 20530 | +| total_timesteps | 6355968 | +| train/ | | +| approx_kl | 2.4842582 | +| clip_fraction | 0.493 | +| clip_range | 0.2 | +| entropy_loss | -0.436 | +| explained_variance | -0.503 | +| learning_rate | 0.0001 | +| loss | -0.085 | +| n_updates | 122590 | +| policy_gradient_loss | -0.0639 | +| value_loss | 0.000411 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.63e+03 | +| ep_rew_mean | 0.274 | +| time/ | | +| fps | 309 | +| iterations | 6208 | +| time_elapsed | 20533 | +| total_timesteps | 6356992 | +| train/ | | +| approx_kl | 1.9392158 | +| clip_fraction | 0.485 | +| clip_range | 0.2 | +| entropy_loss | -0.39 | +| explained_variance | -0.355 | +| learning_rate | 0.0001 | +| loss | -0.0764 | +| n_updates | 122600 | +| policy_gradient_loss | -0.0762 | +| value_loss | 0.000786 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.64e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 309 | +| iterations | 6209 | +| time_elapsed | 20537 | +| total_timesteps | 6358016 | +| train/ | | +| approx_kl | 2.031617 | +| clip_fraction | 0.527 | +| clip_range | 0.2 | +| entropy_loss | -0.449 | +| explained_variance | -2.62 | +| learning_rate | 0.0001 | +| loss | -0.131 | +| n_updates | 122610 | +| policy_gradient_loss | -0.0727 | +| value_loss | 0.000587 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.64e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 309 | +| iterations | 6210 | +| time_elapsed | 20540 | +| total_timesteps | 6359040 | +| train/ | | +| approx_kl | 1.7921014 | +| clip_fraction | 0.486 | +| clip_range | 0.2 | +| entropy_loss | -0.423 | +| explained_variance | -0.263 | +| learning_rate | 0.0001 | +| loss | -0.0641 | +| n_updates | 122620 | +| policy_gradient_loss | -0.0591 | +| value_loss | 0.000407 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.64e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 309 | +| iterations | 6211 | +| time_elapsed | 20543 | +| total_timesteps | 6360064 | +| train/ | | +| approx_kl | 2.3451915 | +| clip_fraction | 0.508 | +| clip_range | 0.2 | +| entropy_loss | -0.417 | +| explained_variance | -0.808 | +| learning_rate | 0.0001 | +| loss | -0.085 | +| n_updates | 122630 | +| policy_gradient_loss | -0.0768 | +| value_loss | 0.000434 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.64e+03 | +| ep_rew_mean | 0.276 | +| time/ | | +| fps | 309 | +| iterations | 6212 | +| time_elapsed | 20547 | +| total_timesteps | 6361088 | +| train/ | | +| approx_kl | 2.6152382 | +| clip_fraction | 0.517 | +| clip_range | 0.2 | +| entropy_loss | -0.454 | +| explained_variance | -1.47 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 122640 | +| policy_gradient_loss | -0.0636 | +| value_loss | 0.000253 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.64e+03 | +| ep_rew_mean | 0.276 | +| time/ | | +| fps | 309 | +| iterations | 6213 | +| time_elapsed | 20550 | +| total_timesteps | 6362112 | +| train/ | | +| approx_kl | 2.2664237 | +| clip_fraction | 0.474 | +| clip_range | 0.2 | +| entropy_loss | -0.45 | +| explained_variance | -1.05 | +| learning_rate | 0.0001 | +| loss | -0.0583 | +| n_updates | 122650 | +| policy_gradient_loss | -0.0583 | +| value_loss | 0.000307 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.64e+03 | +| ep_rew_mean | 0.276 | +| time/ | | +| fps | 309 | +| iterations | 6214 | +| time_elapsed | 20553 | +| total_timesteps | 6363136 | +| train/ | | +| approx_kl | 1.7213577 | +| clip_fraction | 0.478 | +| clip_range | 0.2 | +| entropy_loss | -0.413 | +| explained_variance | 0.167 | +| learning_rate | 0.0001 | +| loss | -0.0431 | +| n_updates | 122660 | +| policy_gradient_loss | -0.0659 | +| value_loss | 0.000392 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.65e+03 | +| ep_rew_mean | 0.278 | +| time/ | | +| fps | 309 | +| iterations | 6215 | +| time_elapsed | 20556 | +| total_timesteps | 6364160 | +| train/ | | +| approx_kl | 1.273433 | +| clip_fraction | 0.492 | +| clip_range | 0.2 | +| entropy_loss | -0.501 | +| explained_variance | -1.45 | +| learning_rate | 0.0001 | +| loss | -0.0929 | +| n_updates | 122670 | +| policy_gradient_loss | -0.0673 | +| value_loss | 0.000311 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.65e+03 | +| ep_rew_mean | 0.278 | +| time/ | | +| fps | 309 | +| iterations | 6216 | +| time_elapsed | 20559 | +| total_timesteps | 6365184 | +| train/ | | +| approx_kl | 1.7353392 | +| clip_fraction | 0.478 | +| clip_range | 0.2 | +| entropy_loss | -0.424 | +| explained_variance | -0.0744 | +| learning_rate | 0.0001 | +| loss | -0.106 | +| n_updates | 122680 | +| policy_gradient_loss | -0.0648 | +| value_loss | 0.000315 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.65e+03 | +| ep_rew_mean | 0.277 | +| time/ | | +| fps | 309 | +| iterations | 6217 | +| time_elapsed | 20563 | +| total_timesteps | 6366208 | +| train/ | | +| approx_kl | 1.9182842 | +| clip_fraction | 0.495 | +| clip_range | 0.2 | +| entropy_loss | -0.474 | +| explained_variance | -0.995 | +| learning_rate | 0.0001 | +| loss | -0.076 | +| n_updates | 122690 | +| policy_gradient_loss | -0.0709 | +| value_loss | 0.000603 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.65e+03 | +| ep_rew_mean | 0.277 | +| time/ | | +| fps | 309 | +| iterations | 6218 | +| time_elapsed | 20566 | +| total_timesteps | 6367232 | +| train/ | | +| approx_kl | 2.1595547 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.398 | +| explained_variance | -0.705 | +| learning_rate | 0.0001 | +| loss | -0.0704 | +| n_updates | 122700 | +| policy_gradient_loss | -0.00371 | +| value_loss | 0.000964 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.65e+03 | +| ep_rew_mean | 0.277 | +| time/ | | +| fps | 309 | +| iterations | 6219 | +| time_elapsed | 20570 | +| total_timesteps | 6368256 | +| train/ | | +| approx_kl | 2.3624625 | +| clip_fraction | 0.513 | +| clip_range | 0.2 | +| entropy_loss | -0.422 | +| explained_variance | -6.32 | +| learning_rate | 0.0001 | +| loss | -0.0915 | +| n_updates | 122710 | +| policy_gradient_loss | -0.075 | +| value_loss | 0.000371 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | 0.278 | +| time/ | | +| fps | 309 | +| iterations | 6220 | +| time_elapsed | 20573 | +| total_timesteps | 6369280 | +| train/ | | +| approx_kl | 2.4322865 | +| clip_fraction | 0.513 | +| clip_range | 0.2 | +| entropy_loss | -0.458 | +| explained_variance | -1.98 | +| learning_rate | 0.0001 | +| loss | -0.119 | +| n_updates | 122720 | +| policy_gradient_loss | -0.0763 | +| value_loss | 0.000259 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.65e+03 | +| ep_rew_mean | 0.278 | +| time/ | | +| fps | 309 | +| iterations | 6221 | +| time_elapsed | 20577 | +| total_timesteps | 6370304 | +| train/ | | +| approx_kl | 3.488473 | +| clip_fraction | 0.507 | +| clip_range | 0.2 | +| entropy_loss | -0.44 | +| explained_variance | -0.699 | +| learning_rate | 0.0001 | +| loss | -0.0844 | +| n_updates | 122730 | +| policy_gradient_loss | -0.0638 | +| value_loss | 0.000302 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.65e+03 | +| ep_rew_mean | 0.278 | +| time/ | | +| fps | 309 | +| iterations | 6222 | +| time_elapsed | 20580 | +| total_timesteps | 6371328 | +| train/ | | +| approx_kl | 1.8313046 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.383 | +| explained_variance | -0.517 | +| learning_rate | 0.0001 | +| loss | -0.0883 | +| n_updates | 122740 | +| policy_gradient_loss | -0.0655 | +| value_loss | 0.000421 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.65e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 309 | +| iterations | 6223 | +| time_elapsed | 20583 | +| total_timesteps | 6372352 | +| train/ | | +| approx_kl | 2.4311447 | +| clip_fraction | 0.515 | +| clip_range | 0.2 | +| entropy_loss | -0.413 | +| explained_variance | -3.22 | +| learning_rate | 0.0001 | +| loss | -0.0791 | +| n_updates | 122750 | +| policy_gradient_loss | -0.0715 | +| value_loss | 0.000513 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.65e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 309 | +| iterations | 6224 | +| time_elapsed | 20587 | +| total_timesteps | 6373376 | +| train/ | | +| approx_kl | 2.0011518 | +| clip_fraction | 0.478 | +| clip_range | 0.2 | +| entropy_loss | -0.42 | +| explained_variance | -1.39 | +| learning_rate | 0.0001 | +| loss | -0.0617 | +| n_updates | 122760 | +| policy_gradient_loss | -0.0576 | +| value_loss | 0.000349 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | 0.28 | +| time/ | | +| fps | 309 | +| iterations | 6225 | +| time_elapsed | 20590 | +| total_timesteps | 6374400 | +| train/ | | +| approx_kl | 2.3179836 | +| clip_fraction | 0.495 | +| clip_range | 0.2 | +| entropy_loss | -0.369 | +| explained_variance | -2.24 | +| learning_rate | 0.0001 | +| loss | -0.116 | +| n_updates | 122770 | +| policy_gradient_loss | -0.0704 | +| value_loss | 0.000524 | +--------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | 0.274 | +| time/ | | +| fps | 309 | +| iterations | 6226 | +| time_elapsed | 20593 | +| total_timesteps | 6375424 | +| train/ | | +| approx_kl | 11.7452755 | +| clip_fraction | 0.473 | +| clip_range | 0.2 | +| entropy_loss | -0.374 | +| explained_variance | -1.05 | +| learning_rate | 0.0001 | +| loss | -0.0548 | +| n_updates | 122780 | +| policy_gradient_loss | -0.0581 | +| value_loss | 0.000396 | +---------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | 0.274 | +| time/ | | +| fps | 309 | +| iterations | 6227 | +| time_elapsed | 20597 | +| total_timesteps | 6376448 | +| train/ | | +| approx_kl | 1.6732165 | +| clip_fraction | 0.456 | +| clip_range | 0.2 | +| entropy_loss | -0.393 | +| explained_variance | -0.502 | +| learning_rate | 0.0001 | +| loss | -0.0913 | +| n_updates | 122790 | +| policy_gradient_loss | -0.0532 | +| value_loss | 0.000518 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.277 | +| time/ | | +| fps | 309 | +| iterations | 6228 | +| time_elapsed | 20600 | +| total_timesteps | 6377472 | +| train/ | | +| approx_kl | 2.3804955 | +| clip_fraction | 0.497 | +| clip_range | 0.2 | +| entropy_loss | -0.398 | +| explained_variance | -3.71 | +| learning_rate | 0.0001 | +| loss | -0.0628 | +| n_updates | 122800 | +| policy_gradient_loss | -0.0745 | +| value_loss | 0.000519 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.277 | +| time/ | | +| fps | 309 | +| iterations | 6229 | +| time_elapsed | 20603 | +| total_timesteps | 6378496 | +| train/ | | +| approx_kl | 2.3702695 | +| clip_fraction | 0.42 | +| clip_range | 0.2 | +| entropy_loss | -0.333 | +| explained_variance | -1.11 | +| learning_rate | 0.0001 | +| loss | -0.0641 | +| n_updates | 122810 | +| policy_gradient_loss | -0.0577 | +| value_loss | 0.000257 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.277 | +| time/ | | +| fps | 309 | +| iterations | 6230 | +| time_elapsed | 20606 | +| total_timesteps | 6379520 | +| train/ | | +| approx_kl | 1.9793012 | +| clip_fraction | 0.501 | +| clip_range | 0.2 | +| entropy_loss | -0.376 | +| explained_variance | -1.59 | +| learning_rate | 0.0001 | +| loss | -0.0901 | +| n_updates | 122820 | +| policy_gradient_loss | -0.071 | +| value_loss | 0.000236 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 309 | +| iterations | 6231 | +| time_elapsed | 20609 | +| total_timesteps | 6380544 | +| train/ | | +| approx_kl | 1.5754442 | +| clip_fraction | 0.496 | +| clip_range | 0.2 | +| entropy_loss | -0.443 | +| explained_variance | -4.21 | +| learning_rate | 0.0001 | +| loss | -0.077 | +| n_updates | 122830 | +| policy_gradient_loss | -0.0688 | +| value_loss | 0.00015 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 309 | +| iterations | 6232 | +| time_elapsed | 20612 | +| total_timesteps | 6381568 | +| train/ | | +| approx_kl | 1.9377599 | +| clip_fraction | 0.459 | +| clip_range | 0.2 | +| entropy_loss | -0.362 | +| explained_variance | -0.272 | +| learning_rate | 0.0001 | +| loss | -0.087 | +| n_updates | 122840 | +| policy_gradient_loss | -0.0584 | +| value_loss | 0.000327 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.281 | +| time/ | | +| fps | 309 | +| iterations | 6233 | +| time_elapsed | 20616 | +| total_timesteps | 6382592 | +| train/ | | +| approx_kl | 1.704912 | +| clip_fraction | 0.485 | +| clip_range | 0.2 | +| entropy_loss | -0.417 | +| explained_variance | -1.18 | +| learning_rate | 0.0001 | +| loss | -0.108 | +| n_updates | 122850 | +| policy_gradient_loss | -0.0627 | +| value_loss | 0.000601 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.281 | +| time/ | | +| fps | 309 | +| iterations | 6234 | +| time_elapsed | 20619 | +| total_timesteps | 6383616 | +| train/ | | +| approx_kl | 1.5171568 | +| clip_fraction | 0.47 | +| clip_range | 0.2 | +| entropy_loss | -0.444 | +| explained_variance | -0.881 | +| learning_rate | 0.0001 | +| loss | -0.0844 | +| n_updates | 122860 | +| policy_gradient_loss | -0.0654 | +| value_loss | 0.000434 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.283 | +| time/ | | +| fps | 309 | +| iterations | 6235 | +| time_elapsed | 20622 | +| total_timesteps | 6384640 | +| train/ | | +| approx_kl | 2.5014648 | +| clip_fraction | 0.524 | +| clip_range | 0.2 | +| entropy_loss | -0.469 | +| explained_variance | -0.791 | +| learning_rate | 0.0001 | +| loss | -0.0839 | +| n_updates | 122870 | +| policy_gradient_loss | -0.0744 | +| value_loss | 0.000451 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 309 | +| iterations | 6236 | +| time_elapsed | 20626 | +| total_timesteps | 6385664 | +| train/ | | +| approx_kl | 2.166706 | +| clip_fraction | 0.45 | +| clip_range | 0.2 | +| entropy_loss | -0.347 | +| explained_variance | -0.939 | +| learning_rate | 0.0001 | +| loss | -0.0897 | +| n_updates | 122880 | +| policy_gradient_loss | -0.0613 | +| value_loss | 0.000719 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 309 | +| iterations | 6237 | +| time_elapsed | 20629 | +| total_timesteps | 6386688 | +| train/ | | +| approx_kl | 1.5770475 | +| clip_fraction | 0.465 | +| clip_range | 0.2 | +| entropy_loss | -0.406 | +| explained_variance | -0.54 | +| learning_rate | 0.0001 | +| loss | -0.0864 | +| n_updates | 122890 | +| policy_gradient_loss | -0.0685 | +| value_loss | 0.000532 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 309 | +| iterations | 6238 | +| time_elapsed | 20633 | +| total_timesteps | 6387712 | +| train/ | | +| approx_kl | 2.098786 | +| clip_fraction | 0.451 | +| clip_range | 0.2 | +| entropy_loss | -0.371 | +| explained_variance | 0.121 | +| learning_rate | 0.0001 | +| loss | -0.0867 | +| n_updates | 122900 | +| policy_gradient_loss | -0.0687 | +| value_loss | 0.000318 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.283 | +| time/ | | +| fps | 309 | +| iterations | 6239 | +| time_elapsed | 20636 | +| total_timesteps | 6388736 | +| train/ | | +| approx_kl | 2.445228 | +| clip_fraction | 0.582 | +| clip_range | 0.2 | +| entropy_loss | -0.535 | +| explained_variance | -1.21 | +| learning_rate | 0.0001 | +| loss | -0.0939 | +| n_updates | 122910 | +| policy_gradient_loss | -0.0818 | +| value_loss | 0.000529 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.283 | +| time/ | | +| fps | 309 | +| iterations | 6240 | +| time_elapsed | 20640 | +| total_timesteps | 6389760 | +| train/ | | +| approx_kl | 1.4376547 | +| clip_fraction | 0.437 | +| clip_range | 0.2 | +| entropy_loss | -0.395 | +| explained_variance | -2.13 | +| learning_rate | 0.0001 | +| loss | -0.0571 | +| n_updates | 122920 | +| policy_gradient_loss | -0.0561 | +| value_loss | 0.000292 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.286 | +| time/ | | +| fps | 309 | +| iterations | 6241 | +| time_elapsed | 20643 | +| total_timesteps | 6390784 | +| train/ | | +| approx_kl | 2.1658514 | +| clip_fraction | 0.539 | +| clip_range | 0.2 | +| entropy_loss | -0.487 | +| explained_variance | -1.05 | +| learning_rate | 0.0001 | +| loss | -0.0528 | +| n_updates | 122930 | +| policy_gradient_loss | -0.0658 | +| value_loss | 0.000431 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.286 | +| time/ | | +| fps | 309 | +| iterations | 6242 | +| time_elapsed | 20647 | +| total_timesteps | 6391808 | +| train/ | | +| approx_kl | 1.9853241 | +| clip_fraction | 0.473 | +| clip_range | 0.2 | +| entropy_loss | -0.406 | +| explained_variance | -1.48 | +| learning_rate | 0.0001 | +| loss | -0.1 | +| n_updates | 122940 | +| policy_gradient_loss | -0.0706 | +| value_loss | 0.000501 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.287 | +| time/ | | +| fps | 309 | +| iterations | 6243 | +| time_elapsed | 20650 | +| total_timesteps | 6392832 | +| train/ | | +| approx_kl | 1.840003 | +| clip_fraction | 0.469 | +| clip_range | 0.2 | +| entropy_loss | -0.425 | +| explained_variance | -1.59 | +| learning_rate | 0.0001 | +| loss | -0.115 | +| n_updates | 122950 | +| policy_gradient_loss | -0.0732 | +| value_loss | 0.000545 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.293 | +| time/ | | +| fps | 309 | +| iterations | 6244 | +| time_elapsed | 20653 | +| total_timesteps | 6393856 | +| train/ | | +| approx_kl | 2.9251537 | +| clip_fraction | 0.449 | +| clip_range | 0.2 | +| entropy_loss | -0.359 | +| explained_variance | -1.66 | +| learning_rate | 0.0001 | +| loss | -0.0961 | +| n_updates | 122960 | +| policy_gradient_loss | -0.0528 | +| value_loss | 0.00122 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.293 | +| time/ | | +| fps | 309 | +| iterations | 6245 | +| time_elapsed | 20657 | +| total_timesteps | 6394880 | +| train/ | | +| approx_kl | 2.2639954 | +| clip_fraction | 0.47 | +| clip_range | 0.2 | +| entropy_loss | -0.399 | +| explained_variance | -0.455 | +| learning_rate | 0.0001 | +| loss | -0.0855 | +| n_updates | 122970 | +| policy_gradient_loss | -0.0642 | +| value_loss | 0.000606 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.295 | +| time/ | | +| fps | 309 | +| iterations | 6246 | +| time_elapsed | 20660 | +| total_timesteps | 6395904 | +| train/ | | +| approx_kl | 1.9489235 | +| clip_fraction | 0.512 | +| clip_range | 0.2 | +| entropy_loss | -0.404 | +| explained_variance | -4.97 | +| learning_rate | 0.0001 | +| loss | -0.0916 | +| n_updates | 122980 | +| policy_gradient_loss | -0.0688 | +| value_loss | 0.000376 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.295 | +| time/ | | +| fps | 309 | +| iterations | 6247 | +| time_elapsed | 20663 | +| total_timesteps | 6396928 | +| train/ | | +| approx_kl | 1.8663485 | +| clip_fraction | 0.46 | +| clip_range | 0.2 | +| entropy_loss | -0.399 | +| explained_variance | -0.813 | +| learning_rate | 0.0001 | +| loss | -0.0733 | +| n_updates | 122990 | +| policy_gradient_loss | -0.0566 | +| value_loss | 0.000291 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 309 | +| iterations | 6248 | +| time_elapsed | 20666 | +| total_timesteps | 6397952 | +| train/ | | +| approx_kl | 2.117072 | +| clip_fraction | 0.53 | +| clip_range | 0.2 | +| entropy_loss | -0.467 | +| explained_variance | -0.552 | +| learning_rate | 0.0001 | +| loss | -0.0983 | +| n_updates | 123000 | +| policy_gradient_loss | -0.0707 | +| value_loss | 0.000432 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 309 | +| iterations | 6249 | +| time_elapsed | 20669 | +| total_timesteps | 6398976 | +| train/ | | +| approx_kl | 1.8998137 | +| clip_fraction | 0.436 | +| clip_range | 0.2 | +| entropy_loss | -0.381 | +| explained_variance | -1.05 | +| learning_rate | 0.0001 | +| loss | -0.0686 | +| n_updates | 123010 | +| policy_gradient_loss | -0.0627 | +| value_loss | 0.000729 | +--------------------------------------- + +Current state: Champion.Level5.RyuVsDhalsim +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.302 | +| time/ | | +| fps | 309 | +| iterations | 6250 | +| time_elapsed | 20673 | +| total_timesteps | 6400000 | +| train/ | | +| approx_kl | 1.9202728 | +| clip_fraction | 0.521 | +| clip_range | 0.2 | +| entropy_loss | -0.459 | +| explained_variance | -1.3 | +| learning_rate | 0.0001 | +| loss | -0.107 | +| n_updates | 123020 | +| policy_gradient_loss | -0.082 | +| value_loss | 0.000666 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.302 | +| time/ | | +| fps | 309 | +| iterations | 6251 | +| time_elapsed | 20676 | +| total_timesteps | 6401024 | +| train/ | | +| approx_kl | 1.6889162 | +| clip_fraction | 0.443 | +| clip_range | 0.2 | +| entropy_loss | -0.426 | +| explained_variance | -0.389 | +| learning_rate | 0.0001 | +| loss | -0.0776 | +| n_updates | 123030 | +| policy_gradient_loss | -0.0514 | +| value_loss | 0.00028 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.302 | +| time/ | | +| fps | 309 | +| iterations | 6252 | +| time_elapsed | 20679 | +| total_timesteps | 6402048 | +| train/ | | +| approx_kl | 1.7402395 | +| clip_fraction | 0.516 | +| clip_range | 0.2 | +| entropy_loss | -0.487 | +| explained_variance | -0.863 | +| learning_rate | 0.0001 | +| loss | -0.0885 | +| n_updates | 123040 | +| policy_gradient_loss | -0.0737 | +| value_loss | 0.000308 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.302 | +| time/ | | +| fps | 309 | +| iterations | 6253 | +| time_elapsed | 20682 | +| total_timesteps | 6403072 | +| train/ | | +| approx_kl | 3.0747232 | +| clip_fraction | 0.508 | +| clip_range | 0.2 | +| entropy_loss | -0.347 | +| explained_variance | -0.686 | +| learning_rate | 0.0001 | +| loss | -0.0743 | +| n_updates | 123050 | +| policy_gradient_loss | -0.0626 | +| value_loss | 0.000279 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.302 | +| time/ | | +| fps | 309 | +| iterations | 6254 | +| time_elapsed | 20686 | +| total_timesteps | 6404096 | +| train/ | | +| approx_kl | 3.7931867 | +| clip_fraction | 0.509 | +| clip_range | 0.2 | +| entropy_loss | -0.331 | +| explained_variance | -1.54 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 123060 | +| policy_gradient_loss | -0.0604 | +| value_loss | 0.000432 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 309 | +| iterations | 6255 | +| time_elapsed | 20689 | +| total_timesteps | 6405120 | +| train/ | | +| approx_kl | 2.662798 | +| clip_fraction | 0.486 | +| clip_range | 0.2 | +| entropy_loss | -0.332 | +| explained_variance | -1.82 | +| learning_rate | 0.0001 | +| loss | -0.0794 | +| n_updates | 123070 | +| policy_gradient_loss | -0.0441 | +| value_loss | 0.000395 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 309 | +| iterations | 6256 | +| time_elapsed | 20692 | +| total_timesteps | 6406144 | +| train/ | | +| approx_kl | 2.574901 | +| clip_fraction | 0.476 | +| clip_range | 0.2 | +| entropy_loss | -0.318 | +| explained_variance | -1.87 | +| learning_rate | 0.0001 | +| loss | -0.0804 | +| n_updates | 123080 | +| policy_gradient_loss | -0.0588 | +| value_loss | 0.000318 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 309 | +| iterations | 6257 | +| time_elapsed | 20696 | +| total_timesteps | 6407168 | +| train/ | | +| approx_kl | 2.1080413 | +| clip_fraction | 0.476 | +| clip_range | 0.2 | +| entropy_loss | -0.353 | +| explained_variance | -1.29 | +| learning_rate | 0.0001 | +| loss | -0.0852 | +| n_updates | 123090 | +| policy_gradient_loss | -0.0587 | +| value_loss | 0.000216 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.298 | +| time/ | | +| fps | 309 | +| iterations | 6258 | +| time_elapsed | 20699 | +| total_timesteps | 6408192 | +| train/ | | +| approx_kl | 2.3494115 | +| clip_fraction | 0.476 | +| clip_range | 0.2 | +| entropy_loss | -0.331 | +| explained_variance | -1.47 | +| learning_rate | 0.0001 | +| loss | -0.0961 | +| n_updates | 123100 | +| policy_gradient_loss | -0.0608 | +| value_loss | 0.000311 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.298 | +| time/ | | +| fps | 309 | +| iterations | 6259 | +| time_elapsed | 20702 | +| total_timesteps | 6409216 | +| train/ | | +| approx_kl | 2.3896828 | +| clip_fraction | 0.495 | +| clip_range | 0.2 | +| entropy_loss | -0.41 | +| explained_variance | -0.0674 | +| learning_rate | 0.0001 | +| loss | -0.111 | +| n_updates | 123110 | +| policy_gradient_loss | -0.048 | +| value_loss | 0.000367 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.295 | +| time/ | | +| fps | 309 | +| iterations | 6260 | +| time_elapsed | 20706 | +| total_timesteps | 6410240 | +| train/ | | +| approx_kl | 2.2589655 | +| clip_fraction | 0.482 | +| clip_range | 0.2 | +| entropy_loss | -0.405 | +| explained_variance | 0.0407 | +| learning_rate | 0.0001 | +| loss | -0.0719 | +| n_updates | 123120 | +| policy_gradient_loss | -0.0533 | +| value_loss | 0.000597 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.295 | +| time/ | | +| fps | 309 | +| iterations | 6261 | +| time_elapsed | 20709 | +| total_timesteps | 6411264 | +| train/ | | +| approx_kl | 2.6006644 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.355 | +| explained_variance | 0.0725 | +| learning_rate | 0.0001 | +| loss | -0.087 | +| n_updates | 123130 | +| policy_gradient_loss | 0.0414 | +| value_loss | 0.000416 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 309 | +| iterations | 6262 | +| time_elapsed | 20712 | +| total_timesteps | 6412288 | +| train/ | | +| approx_kl | 2.200079 | +| clip_fraction | 0.452 | +| clip_range | 0.2 | +| entropy_loss | -0.315 | +| explained_variance | -1.37 | +| learning_rate | 0.0001 | +| loss | -0.0856 | +| n_updates | 123140 | +| policy_gradient_loss | -0.0605 | +| value_loss | 0.000469 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 309 | +| iterations | 6263 | +| time_elapsed | 20715 | +| total_timesteps | 6413312 | +| train/ | | +| approx_kl | 1.9309182 | +| clip_fraction | 0.466 | +| clip_range | 0.2 | +| entropy_loss | -0.354 | +| explained_variance | -0.349 | +| learning_rate | 0.0001 | +| loss | -0.0467 | +| n_updates | 123150 | +| policy_gradient_loss | -0.0568 | +| value_loss | 0.000533 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 309 | +| iterations | 6264 | +| time_elapsed | 20719 | +| total_timesteps | 6414336 | +| train/ | | +| approx_kl | 1.8221729 | +| clip_fraction | 0.485 | +| clip_range | 0.2 | +| entropy_loss | -0.411 | +| explained_variance | -3.18 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 123160 | +| policy_gradient_loss | -0.0682 | +| value_loss | 0.000278 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 309 | +| iterations | 6265 | +| time_elapsed | 20722 | +| total_timesteps | 6415360 | +| train/ | | +| approx_kl | 3.5060167 | +| clip_fraction | 0.53 | +| clip_range | 0.2 | +| entropy_loss | -0.329 | +| explained_variance | -0.51 | +| learning_rate | 0.0001 | +| loss | -0.0859 | +| n_updates | 123170 | +| policy_gradient_loss | -0.0503 | +| value_loss | 0.000545 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 309 | +| iterations | 6266 | +| time_elapsed | 20725 | +| total_timesteps | 6416384 | +| train/ | | +| approx_kl | 6.502912 | +| clip_fraction | 0.484 | +| clip_range | 0.2 | +| entropy_loss | -0.292 | +| explained_variance | -2.95 | +| learning_rate | 0.0001 | +| loss | -0.0886 | +| n_updates | 123180 | +| policy_gradient_loss | -0.0661 | +| value_loss | 0.000634 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 309 | +| iterations | 6267 | +| time_elapsed | 20728 | +| total_timesteps | 6417408 | +| train/ | | +| approx_kl | 2.8466864 | +| clip_fraction | 0.491 | +| clip_range | 0.2 | +| entropy_loss | -0.327 | +| explained_variance | -1.22 | +| learning_rate | 0.0001 | +| loss | -0.0714 | +| n_updates | 123190 | +| policy_gradient_loss | -0.0535 | +| value_loss | 0.000432 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 309 | +| iterations | 6268 | +| time_elapsed | 20731 | +| total_timesteps | 6418432 | +| train/ | | +| approx_kl | 2.3399456 | +| clip_fraction | 0.446 | +| clip_range | 0.2 | +| entropy_loss | -0.296 | +| explained_variance | -0.00887 | +| learning_rate | 0.0001 | +| loss | -0.0752 | +| n_updates | 123200 | +| policy_gradient_loss | -0.0515 | +| value_loss | 0.000331 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 309 | +| iterations | 6269 | +| time_elapsed | 20734 | +| total_timesteps | 6419456 | +| train/ | | +| approx_kl | 2.1449378 | +| clip_fraction | 0.467 | +| clip_range | 0.2 | +| entropy_loss | -0.344 | +| explained_variance | -2.35 | +| learning_rate | 0.0001 | +| loss | -0.0798 | +| n_updates | 123210 | +| policy_gradient_loss | -0.0579 | +| value_loss | 0.000505 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 309 | +| iterations | 6270 | +| time_elapsed | 20738 | +| total_timesteps | 6420480 | +| train/ | | +| approx_kl | 2.4851592 | +| clip_fraction | 0.432 | +| clip_range | 0.2 | +| entropy_loss | -0.285 | +| explained_variance | -0.596 | +| learning_rate | 0.0001 | +| loss | -0.0872 | +| n_updates | 123220 | +| policy_gradient_loss | -0.0526 | +| value_loss | 0.000457 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 309 | +| iterations | 6271 | +| time_elapsed | 20741 | +| total_timesteps | 6421504 | +| train/ | | +| approx_kl | 2.9899437 | +| clip_fraction | 0.516 | +| clip_range | 0.2 | +| entropy_loss | -0.349 | +| explained_variance | -3.75 | +| learning_rate | 0.0001 | +| loss | -0.111 | +| n_updates | 123230 | +| policy_gradient_loss | -0.0663 | +| value_loss | 0.000408 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 309 | +| iterations | 6272 | +| time_elapsed | 20744 | +| total_timesteps | 6422528 | +| train/ | | +| approx_kl | 1.9869597 | +| clip_fraction | 0.476 | +| clip_range | 0.2 | +| entropy_loss | -0.355 | +| explained_variance | -0.519 | +| learning_rate | 0.0001 | +| loss | -0.0959 | +| n_updates | 123240 | +| policy_gradient_loss | -0.052 | +| value_loss | 0.000381 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 309 | +| iterations | 6273 | +| time_elapsed | 20748 | +| total_timesteps | 6423552 | +| train/ | | +| approx_kl | 2.5951767 | +| clip_fraction | 0.4 | +| clip_range | 0.2 | +| entropy_loss | -0.237 | +| explained_variance | -0.726 | +| learning_rate | 0.0001 | +| loss | -0.0721 | +| n_updates | 123250 | +| policy_gradient_loss | -0.0517 | +| value_loss | 0.000397 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 309 | +| iterations | 6274 | +| time_elapsed | 20751 | +| total_timesteps | 6424576 | +| train/ | | +| approx_kl | 1.6202531 | +| clip_fraction | 0.472 | +| clip_range | 0.2 | +| entropy_loss | -0.37 | +| explained_variance | -1.78 | +| learning_rate | 0.0001 | +| loss | -0.0846 | +| n_updates | 123260 | +| policy_gradient_loss | -0.0569 | +| value_loss | 0.000227 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 309 | +| iterations | 6275 | +| time_elapsed | 20755 | +| total_timesteps | 6425600 | +| train/ | | +| approx_kl | 2.0435562 | +| clip_fraction | 0.429 | +| clip_range | 0.2 | +| entropy_loss | -0.316 | +| explained_variance | 0.154 | +| learning_rate | 0.0001 | +| loss | -0.0746 | +| n_updates | 123270 | +| policy_gradient_loss | -0.0444 | +| value_loss | 0.000205 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 309 | +| iterations | 6276 | +| time_elapsed | 20758 | +| total_timesteps | 6426624 | +| train/ | | +| approx_kl | 2.0666022 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.379 | +| explained_variance | -0.897 | +| learning_rate | 0.0001 | +| loss | -0.0486 | +| n_updates | 123280 | +| policy_gradient_loss | -0.0521 | +| value_loss | 0.000342 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 309 | +| iterations | 6277 | +| time_elapsed | 20762 | +| total_timesteps | 6427648 | +| train/ | | +| approx_kl | 2.3092968 | +| clip_fraction | 0.401 | +| clip_range | 0.2 | +| entropy_loss | -0.249 | +| explained_variance | -1.08 | +| learning_rate | 0.0001 | +| loss | -0.0739 | +| n_updates | 123290 | +| policy_gradient_loss | -0.0587 | +| value_loss | 0.000406 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 309 | +| iterations | 6278 | +| time_elapsed | 20765 | +| total_timesteps | 6428672 | +| train/ | | +| approx_kl | 1.6591785 | +| clip_fraction | 0.477 | +| clip_range | 0.2 | +| entropy_loss | -0.358 | +| explained_variance | -0.496 | +| learning_rate | 0.0001 | +| loss | -0.0884 | +| n_updates | 123300 | +| policy_gradient_loss | -0.0554 | +| value_loss | 0.000293 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 309 | +| iterations | 6279 | +| time_elapsed | 20769 | +| total_timesteps | 6429696 | +| train/ | | +| approx_kl | 4.315248 | +| clip_fraction | 0.45 | +| clip_range | 0.2 | +| entropy_loss | -0.31 | +| explained_variance | -0.299 | +| learning_rate | 0.0001 | +| loss | -0.0771 | +| n_updates | 123310 | +| policy_gradient_loss | -0.0567 | +| value_loss | 0.000376 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 309 | +| iterations | 6280 | +| time_elapsed | 20772 | +| total_timesteps | 6430720 | +| train/ | | +| approx_kl | 2.8019063 | +| clip_fraction | 0.503 | +| clip_range | 0.2 | +| entropy_loss | -0.349 | +| explained_variance | -0.207 | +| learning_rate | 0.0001 | +| loss | -0.0954 | +| n_updates | 123320 | +| policy_gradient_loss | -0.0649 | +| value_loss | 0.000493 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.302 | +| time/ | | +| fps | 309 | +| iterations | 6281 | +| time_elapsed | 20775 | +| total_timesteps | 6431744 | +| train/ | | +| approx_kl | 2.2562318 | +| clip_fraction | 0.506 | +| clip_range | 0.2 | +| entropy_loss | -0.328 | +| explained_variance | -1.28 | +| learning_rate | 0.0001 | +| loss | -0.0879 | +| n_updates | 123330 | +| policy_gradient_loss | -0.0609 | +| value_loss | 0.00026 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.302 | +| time/ | | +| fps | 309 | +| iterations | 6282 | +| time_elapsed | 20778 | +| total_timesteps | 6432768 | +| train/ | | +| approx_kl | 3.4629402 | +| clip_fraction | 0.468 | +| clip_range | 0.2 | +| entropy_loss | -0.292 | +| explained_variance | -0.454 | +| learning_rate | 0.0001 | +| loss | -0.0893 | +| n_updates | 123340 | +| policy_gradient_loss | -0.0625 | +| value_loss | 0.000481 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.302 | +| time/ | | +| fps | 309 | +| iterations | 6283 | +| time_elapsed | 20781 | +| total_timesteps | 6433792 | +| train/ | | +| approx_kl | 3.0717719 | +| clip_fraction | 0.502 | +| clip_range | 0.2 | +| entropy_loss | -0.325 | +| explained_variance | -1.34 | +| learning_rate | 0.0001 | +| loss | 0.322 | +| n_updates | 123350 | +| policy_gradient_loss | -0.0608 | +| value_loss | 0.000346 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.78e+03 | +| ep_rew_mean | 0.304 | +| time/ | | +| fps | 309 | +| iterations | 6284 | +| time_elapsed | 20785 | +| total_timesteps | 6434816 | +| train/ | | +| approx_kl | 2.3620057 | +| clip_fraction | 0.502 | +| clip_range | 0.2 | +| entropy_loss | -0.411 | +| explained_variance | -1.1 | +| learning_rate | 0.0001 | +| loss | -0.0884 | +| n_updates | 123360 | +| policy_gradient_loss | -0.0567 | +| value_loss | 0.000351 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.78e+03 | +| ep_rew_mean | 0.304 | +| time/ | | +| fps | 309 | +| iterations | 6285 | +| time_elapsed | 20788 | +| total_timesteps | 6435840 | +| train/ | | +| approx_kl | 2.2152238 | +| clip_fraction | 0.429 | +| clip_range | 0.2 | +| entropy_loss | -0.294 | +| explained_variance | -1.81 | +| learning_rate | 0.0001 | +| loss | -0.0532 | +| n_updates | 123370 | +| policy_gradient_loss | -0.0518 | +| value_loss | 0.000627 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.78e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 309 | +| iterations | 6286 | +| time_elapsed | 20791 | +| total_timesteps | 6436864 | +| train/ | | +| approx_kl | 2.5502195 | +| clip_fraction | 0.428 | +| clip_range | 0.2 | +| entropy_loss | -0.25 | +| explained_variance | -1.98 | +| learning_rate | 0.0001 | +| loss | -0.0847 | +| n_updates | 123380 | +| policy_gradient_loss | -0.0641 | +| value_loss | 0.000612 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.78e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 309 | +| iterations | 6287 | +| time_elapsed | 20794 | +| total_timesteps | 6437888 | +| train/ | | +| approx_kl | 2.0599995 | +| clip_fraction | 0.468 | +| clip_range | 0.2 | +| entropy_loss | -0.32 | +| explained_variance | -1.19 | +| learning_rate | 0.0001 | +| loss | -0.1 | +| n_updates | 123390 | +| policy_gradient_loss | -0.0736 | +| value_loss | 0.00036 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.78e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 309 | +| iterations | 6288 | +| time_elapsed | 20797 | +| total_timesteps | 6438912 | +| train/ | | +| approx_kl | 3.030086 | +| clip_fraction | 0.461 | +| clip_range | 0.2 | +| entropy_loss | -0.314 | +| explained_variance | -0.707 | +| learning_rate | 0.0001 | +| loss | -0.0772 | +| n_updates | 123400 | +| policy_gradient_loss | -0.0529 | +| value_loss | 0.000294 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.8e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 309 | +| iterations | 6289 | +| time_elapsed | 20801 | +| total_timesteps | 6439936 | +| train/ | | +| approx_kl | 2.4783688 | +| clip_fraction | 0.453 | +| clip_range | 0.2 | +| entropy_loss | -0.308 | +| explained_variance | -1.41 | +| learning_rate | 0.0001 | +| loss | -0.0963 | +| n_updates | 123410 | +| policy_gradient_loss | -0.0467 | +| value_loss | 0.00047 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.8e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 309 | +| iterations | 6290 | +| time_elapsed | 20805 | +| total_timesteps | 6440960 | +| train/ | | +| approx_kl | 2.7057054 | +| clip_fraction | 0.495 | +| clip_range | 0.2 | +| entropy_loss | -0.349 | +| explained_variance | -3.77 | +| learning_rate | 0.0001 | +| loss | -0.0697 | +| n_updates | 123420 | +| policy_gradient_loss | -0.0667 | +| value_loss | 0.000651 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.8e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 309 | +| iterations | 6291 | +| time_elapsed | 20808 | +| total_timesteps | 6441984 | +| train/ | | +| approx_kl | 2.107719 | +| clip_fraction | 0.493 | +| clip_range | 0.2 | +| entropy_loss | -0.383 | +| explained_variance | -0.815 | +| learning_rate | 0.0001 | +| loss | -0.0749 | +| n_updates | 123430 | +| policy_gradient_loss | -0.0657 | +| value_loss | 0.000537 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.82e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 309 | +| iterations | 6292 | +| time_elapsed | 20812 | +| total_timesteps | 6443008 | +| train/ | | +| approx_kl | 4.2204223 | +| clip_fraction | 0.504 | +| clip_range | 0.2 | +| entropy_loss | -0.381 | +| explained_variance | -4.04 | +| learning_rate | 0.0001 | +| loss | -0.0942 | +| n_updates | 123440 | +| policy_gradient_loss | -0.0672 | +| value_loss | 0.000405 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.82e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 309 | +| iterations | 6293 | +| time_elapsed | 20815 | +| total_timesteps | 6444032 | +| train/ | | +| approx_kl | 5.355358 | +| clip_fraction | 0.51 | +| clip_range | 0.2 | +| entropy_loss | -0.389 | +| explained_variance | -2.63 | +| learning_rate | 0.0001 | +| loss | -0.0951 | +| n_updates | 123450 | +| policy_gradient_loss | -0.07 | +| value_loss | 0.000149 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.82e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 309 | +| iterations | 6294 | +| time_elapsed | 20819 | +| total_timesteps | 6445056 | +| train/ | | +| approx_kl | 2.4515123 | +| clip_fraction | 0.455 | +| clip_range | 0.2 | +| entropy_loss | -0.296 | +| explained_variance | -0.461 | +| learning_rate | 0.0001 | +| loss | -0.0697 | +| n_updates | 123460 | +| policy_gradient_loss | -0.0573 | +| value_loss | 0.000316 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.82e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 309 | +| iterations | 6295 | +| time_elapsed | 20822 | +| total_timesteps | 6446080 | +| train/ | | +| approx_kl | 2.7341645 | +| clip_fraction | 0.543 | +| clip_range | 0.2 | +| entropy_loss | -0.429 | +| explained_variance | -2.9 | +| learning_rate | 0.0001 | +| loss | -0.0818 | +| n_updates | 123470 | +| policy_gradient_loss | -0.0663 | +| value_loss | 0.000151 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.82e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 309 | +| iterations | 6296 | +| time_elapsed | 20826 | +| total_timesteps | 6447104 | +| train/ | | +| approx_kl | 2.221395 | +| clip_fraction | 0.466 | +| clip_range | 0.2 | +| entropy_loss | -0.33 | +| explained_variance | -0.883 | +| learning_rate | 0.0001 | +| loss | -0.0801 | +| n_updates | 123480 | +| policy_gradient_loss | -0.0531 | +| value_loss | 0.000302 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 309 | +| iterations | 6297 | +| time_elapsed | 20829 | +| total_timesteps | 6448128 | +| train/ | | +| approx_kl | 1.9976159 | +| clip_fraction | 0.472 | +| clip_range | 0.2 | +| entropy_loss | -0.358 | +| explained_variance | -1.06 | +| learning_rate | 0.0001 | +| loss | -0.0825 | +| n_updates | 123490 | +| policy_gradient_loss | -0.0585 | +| value_loss | 0.000515 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 309 | +| iterations | 6298 | +| time_elapsed | 20833 | +| total_timesteps | 6449152 | +| train/ | | +| approx_kl | 1.976033 | +| clip_fraction | 0.508 | +| clip_range | 0.2 | +| entropy_loss | -0.403 | +| explained_variance | -1.1 | +| learning_rate | 0.0001 | +| loss | -0.0473 | +| n_updates | 123500 | +| policy_gradient_loss | -0.0554 | +| value_loss | 0.000406 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 309 | +| iterations | 6299 | +| time_elapsed | 20836 | +| total_timesteps | 6450176 | +| train/ | | +| approx_kl | 2.2858233 | +| clip_fraction | 0.449 | +| clip_range | 0.2 | +| entropy_loss | -0.287 | +| explained_variance | -7.4 | +| learning_rate | 0.0001 | +| loss | -0.0632 | +| n_updates | 123510 | +| policy_gradient_loss | -0.0579 | +| value_loss | 0.00039 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 309 | +| iterations | 6300 | +| time_elapsed | 20839 | +| total_timesteps | 6451200 | +| train/ | | +| approx_kl | 4.213367 | +| clip_fraction | 0.512 | +| clip_range | 0.2 | +| entropy_loss | -0.351 | +| explained_variance | -0.486 | +| learning_rate | 0.0001 | +| loss | -0.0683 | +| n_updates | 123520 | +| policy_gradient_loss | -0.0606 | +| value_loss | 0.000301 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 309 | +| iterations | 6301 | +| time_elapsed | 20842 | +| total_timesteps | 6452224 | +| train/ | | +| approx_kl | 2.1757345 | +| clip_fraction | 0.467 | +| clip_range | 0.2 | +| entropy_loss | -0.329 | +| explained_variance | -3.73 | +| learning_rate | 0.0001 | +| loss | -0.0796 | +| n_updates | 123530 | +| policy_gradient_loss | -0.0599 | +| value_loss | 0.000864 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 309 | +| iterations | 6302 | +| time_elapsed | 20845 | +| total_timesteps | 6453248 | +| train/ | | +| approx_kl | 2.6517782 | +| clip_fraction | 0.445 | +| clip_range | 0.2 | +| entropy_loss | -0.278 | +| explained_variance | -1.03 | +| learning_rate | 0.0001 | +| loss | -0.0681 | +| n_updates | 123540 | +| policy_gradient_loss | -0.0638 | +| value_loss | 0.000523 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 309 | +| iterations | 6303 | +| time_elapsed | 20848 | +| total_timesteps | 6454272 | +| train/ | | +| approx_kl | 9.240702 | +| clip_fraction | 0.497 | +| clip_range | 0.2 | +| entropy_loss | -0.388 | +| explained_variance | -4.62 | +| learning_rate | 0.0001 | +| loss | -0.094 | +| n_updates | 123550 | +| policy_gradient_loss | -0.0605 | +| value_loss | 0.000284 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 309 | +| iterations | 6304 | +| time_elapsed | 20851 | +| total_timesteps | 6455296 | +| train/ | | +| approx_kl | 2.5987628 | +| clip_fraction | 0.474 | +| clip_range | 0.2 | +| entropy_loss | -0.322 | +| explained_variance | -1.36 | +| learning_rate | 0.0001 | +| loss | -0.0856 | +| n_updates | 123560 | +| policy_gradient_loss | -0.061 | +| value_loss | 0.000304 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.306 | +| time/ | | +| fps | 309 | +| iterations | 6305 | +| time_elapsed | 20854 | +| total_timesteps | 6456320 | +| train/ | | +| approx_kl | 2.9132948 | +| clip_fraction | 0.464 | +| clip_range | 0.2 | +| entropy_loss | -0.322 | +| explained_variance | -3.14 | +| learning_rate | 0.0001 | +| loss | -0.0945 | +| n_updates | 123570 | +| policy_gradient_loss | -0.0591 | +| value_loss | 0.000286 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.306 | +| time/ | | +| fps | 309 | +| iterations | 6306 | +| time_elapsed | 20858 | +| total_timesteps | 6457344 | +| train/ | | +| approx_kl | 2.027109 | +| clip_fraction | 0.47 | +| clip_range | 0.2 | +| entropy_loss | -0.343 | +| explained_variance | -0.719 | +| learning_rate | 0.0001 | +| loss | -0.0734 | +| n_updates | 123580 | +| policy_gradient_loss | -0.0498 | +| value_loss | 0.00042 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.306 | +| time/ | | +| fps | 309 | +| iterations | 6307 | +| time_elapsed | 20861 | +| total_timesteps | 6458368 | +| train/ | | +| approx_kl | 2.5913272 | +| clip_fraction | 0.515 | +| clip_range | 0.2 | +| entropy_loss | -0.345 | +| explained_variance | -2.8 | +| learning_rate | 0.0001 | +| loss | -0.0979 | +| n_updates | 123590 | +| policy_gradient_loss | -0.0618 | +| value_loss | 0.000521 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 309 | +| iterations | 6308 | +| time_elapsed | 20865 | +| total_timesteps | 6459392 | +| train/ | | +| approx_kl | 2.5340817 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.365 | +| explained_variance | -1.56 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 123600 | +| policy_gradient_loss | -0.068 | +| value_loss | 0.00061 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 309 | +| iterations | 6309 | +| time_elapsed | 20868 | +| total_timesteps | 6460416 | +| train/ | | +| approx_kl | 2.063923 | +| clip_fraction | 0.467 | +| clip_range | 0.2 | +| entropy_loss | -0.321 | +| explained_variance | -4.74 | +| learning_rate | 0.0001 | +| loss | -0.099 | +| n_updates | 123610 | +| policy_gradient_loss | -0.0606 | +| value_loss | 0.000331 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 309 | +| iterations | 6310 | +| time_elapsed | 20872 | +| total_timesteps | 6461440 | +| train/ | | +| approx_kl | 2.3519492 | +| clip_fraction | 0.495 | +| clip_range | 0.2 | +| entropy_loss | -0.356 | +| explained_variance | -0.892 | +| learning_rate | 0.0001 | +| loss | -0.0964 | +| n_updates | 123620 | +| policy_gradient_loss | -0.059 | +| value_loss | 0.000203 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 309 | +| iterations | 6311 | +| time_elapsed | 20875 | +| total_timesteps | 6462464 | +| train/ | | +| approx_kl | 1.5913539 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.417 | +| explained_variance | -0.965 | +| learning_rate | 0.0001 | +| loss | -0.0724 | +| n_updates | 123630 | +| policy_gradient_loss | -0.0556 | +| value_loss | 0.000179 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 309 | +| iterations | 6312 | +| time_elapsed | 20879 | +| total_timesteps | 6463488 | +| train/ | | +| approx_kl | 3.491413 | +| clip_fraction | 0.523 | +| clip_range | 0.2 | +| entropy_loss | -0.423 | +| explained_variance | -0.156 | +| learning_rate | 0.0001 | +| loss | -0.0641 | +| n_updates | 123640 | +| policy_gradient_loss | -0.0582 | +| value_loss | 0.000317 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 309 | +| iterations | 6313 | +| time_elapsed | 20882 | +| total_timesteps | 6464512 | +| train/ | | +| approx_kl | 1.7743878 | +| clip_fraction | 0.506 | +| clip_range | 0.2 | +| entropy_loss | -0.453 | +| explained_variance | -2.06 | +| learning_rate | 0.0001 | +| loss | -0.0737 | +| n_updates | 123650 | +| policy_gradient_loss | -0.068 | +| value_loss | 0.000404 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 309 | +| iterations | 6314 | +| time_elapsed | 20885 | +| total_timesteps | 6465536 | +| train/ | | +| approx_kl | 2.891079 | +| clip_fraction | 0.506 | +| clip_range | 0.2 | +| entropy_loss | -0.336 | +| explained_variance | -0.433 | +| learning_rate | 0.0001 | +| loss | -0.0932 | +| n_updates | 123660 | +| policy_gradient_loss | -0.0642 | +| value_loss | 0.000465 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 309 | +| iterations | 6315 | +| time_elapsed | 20889 | +| total_timesteps | 6466560 | +| train/ | | +| approx_kl | 3.3023138 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.328 | +| explained_variance | -2.88 | +| learning_rate | 0.0001 | +| loss | -0.0856 | +| n_updates | 123670 | +| policy_gradient_loss | -0.0505 | +| value_loss | 0.000897 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.89e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 309 | +| iterations | 6316 | +| time_elapsed | 20892 | +| total_timesteps | 6467584 | +| train/ | | +| approx_kl | 3.5779498 | +| clip_fraction | 0.47 | +| clip_range | 0.2 | +| entropy_loss | -0.312 | +| explained_variance | -5.5 | +| learning_rate | 0.0001 | +| loss | -0.105 | +| n_updates | 123680 | +| policy_gradient_loss | -0.0634 | +| value_loss | 0.00051 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.89e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 309 | +| iterations | 6317 | +| time_elapsed | 20895 | +| total_timesteps | 6468608 | +| train/ | | +| approx_kl | 2.6458042 | +| clip_fraction | 0.491 | +| clip_range | 0.2 | +| entropy_loss | -0.329 | +| explained_variance | -0.73 | +| learning_rate | 0.0001 | +| loss | -0.0846 | +| n_updates | 123690 | +| policy_gradient_loss | -0.0585 | +| value_loss | 0.000516 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.89e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 309 | +| iterations | 6318 | +| time_elapsed | 20898 | +| total_timesteps | 6469632 | +| train/ | | +| approx_kl | 2.4171615 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.35 | +| explained_variance | -0.511 | +| learning_rate | 0.0001 | +| loss | -0.0874 | +| n_updates | 123700 | +| policy_gradient_loss | -0.0599 | +| value_loss | 0.000854 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.89e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 309 | +| iterations | 6319 | +| time_elapsed | 20902 | +| total_timesteps | 6470656 | +| train/ | | +| approx_kl | 2.8255832 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.325 | +| explained_variance | -0.393 | +| learning_rate | 0.0001 | +| loss | -0.0803 | +| n_updates | 123710 | +| policy_gradient_loss | -0.0637 | +| value_loss | 0.000617 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.9e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 309 | +| iterations | 6320 | +| time_elapsed | 20905 | +| total_timesteps | 6471680 | +| train/ | | +| approx_kl | 1.7409272 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.432 | +| explained_variance | -2.26 | +| learning_rate | 0.0001 | +| loss | -0.0961 | +| n_updates | 123720 | +| policy_gradient_loss | -0.0652 | +| value_loss | 0.00024 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.9e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 309 | +| iterations | 6321 | +| time_elapsed | 20908 | +| total_timesteps | 6472704 | +| train/ | | +| approx_kl | 2.4591935 | +| clip_fraction | 0.494 | +| clip_range | 0.2 | +| entropy_loss | -0.358 | +| explained_variance | -0.0846 | +| learning_rate | 0.0001 | +| loss | -0.0938 | +| n_updates | 123730 | +| policy_gradient_loss | -0.0567 | +| value_loss | 0.00037 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.9e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 309 | +| iterations | 6322 | +| time_elapsed | 20911 | +| total_timesteps | 6473728 | +| train/ | | +| approx_kl | 2.6844072 | +| clip_fraction | 0.461 | +| clip_range | 0.2 | +| entropy_loss | -0.289 | +| explained_variance | -3.07 | +| learning_rate | 0.0001 | +| loss | -0.083 | +| n_updates | 123740 | +| policy_gradient_loss | -0.057 | +| value_loss | 0.000315 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.91e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 309 | +| iterations | 6323 | +| time_elapsed | 20914 | +| total_timesteps | 6474752 | +| train/ | | +| approx_kl | 2.3907342 | +| clip_fraction | 0.478 | +| clip_range | 0.2 | +| entropy_loss | -0.324 | +| explained_variance | -0.868 | +| learning_rate | 0.0001 | +| loss | -0.0879 | +| n_updates | 123750 | +| policy_gradient_loss | -0.0688 | +| value_loss | 0.000417 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.91e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 309 | +| iterations | 6324 | +| time_elapsed | 20918 | +| total_timesteps | 6475776 | +| train/ | | +| approx_kl | 2.6632195 | +| clip_fraction | 0.497 | +| clip_range | 0.2 | +| entropy_loss | -0.321 | +| explained_variance | -0.904 | +| learning_rate | 0.0001 | +| loss | -0.0668 | +| n_updates | 123760 | +| policy_gradient_loss | -0.0664 | +| value_loss | 0.000462 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.91e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 309 | +| iterations | 6325 | +| time_elapsed | 20921 | +| total_timesteps | 6476800 | +| train/ | | +| approx_kl | 2.673868 | +| clip_fraction | 0.472 | +| clip_range | 0.2 | +| entropy_loss | -0.314 | +| explained_variance | -4.13 | +| learning_rate | 0.0001 | +| loss | -0.0787 | +| n_updates | 123770 | +| policy_gradient_loss | -0.0603 | +| value_loss | 0.000406 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.93e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 309 | +| iterations | 6326 | +| time_elapsed | 20924 | +| total_timesteps | 6477824 | +| train/ | | +| approx_kl | 2.1238215 | +| clip_fraction | 0.459 | +| clip_range | 0.2 | +| entropy_loss | -0.303 | +| explained_variance | -3.72 | +| learning_rate | 0.0001 | +| loss | -0.0464 | +| n_updates | 123780 | +| policy_gradient_loss | -0.0549 | +| value_loss | 0.00036 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.93e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 309 | +| iterations | 6327 | +| time_elapsed | 20928 | +| total_timesteps | 6478848 | +| train/ | | +| approx_kl | 2.6366403 | +| clip_fraction | 0.484 | +| clip_range | 0.2 | +| entropy_loss | -0.347 | +| explained_variance | -0.614 | +| learning_rate | 0.0001 | +| loss | -0.0892 | +| n_updates | 123790 | +| policy_gradient_loss | -0.0586 | +| value_loss | 0.000514 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.94e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 309 | +| iterations | 6328 | +| time_elapsed | 20931 | +| total_timesteps | 6479872 | +| train/ | | +| approx_kl | 1.3196716 | +| clip_fraction | 0.501 | +| clip_range | 0.2 | +| entropy_loss | -0.474 | +| explained_variance | -1.74 | +| learning_rate | 0.0001 | +| loss | -0.0792 | +| n_updates | 123800 | +| policy_gradient_loss | -0.0597 | +| value_loss | 0.000227 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.94e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 309 | +| iterations | 6329 | +| time_elapsed | 20934 | +| total_timesteps | 6480896 | +| train/ | | +| approx_kl | 1.9731377 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.349 | +| explained_variance | -0.7 | +| learning_rate | 0.0001 | +| loss | -0.0772 | +| n_updates | 123810 | +| policy_gradient_loss | -0.0629 | +| value_loss | 0.000415 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.95e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 309 | +| iterations | 6330 | +| time_elapsed | 20938 | +| total_timesteps | 6481920 | +| train/ | | +| approx_kl | 2.1974556 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.335 | +| explained_variance | -2.11 | +| learning_rate | 0.0001 | +| loss | -0.0708 | +| n_updates | 123820 | +| policy_gradient_loss | -0.0612 | +| value_loss | 0.000265 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.95e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 309 | +| iterations | 6331 | +| time_elapsed | 20941 | +| total_timesteps | 6482944 | +| train/ | | +| approx_kl | 2.5485864 | +| clip_fraction | 0.489 | +| clip_range | 0.2 | +| entropy_loss | -0.357 | +| explained_variance | -0.93 | +| learning_rate | 0.0001 | +| loss | -0.0742 | +| n_updates | 123830 | +| policy_gradient_loss | -0.0551 | +| value_loss | 0.000153 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.95e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 309 | +| iterations | 6332 | +| time_elapsed | 20944 | +| total_timesteps | 6483968 | +| train/ | | +| approx_kl | 2.2502398 | +| clip_fraction | 0.474 | +| clip_range | 0.2 | +| entropy_loss | -0.349 | +| explained_variance | -2.28 | +| learning_rate | 0.0001 | +| loss | -0.107 | +| n_updates | 123840 | +| policy_gradient_loss | -0.0685 | +| value_loss | 0.000179 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.95e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 309 | +| iterations | 6333 | +| time_elapsed | 20948 | +| total_timesteps | 6484992 | +| train/ | | +| approx_kl | 2.698468 | +| clip_fraction | 0.523 | +| clip_range | 0.2 | +| entropy_loss | -0.387 | +| explained_variance | -0.786 | +| learning_rate | 0.0001 | +| loss | -0.0957 | +| n_updates | 123850 | +| policy_gradient_loss | -0.0733 | +| value_loss | 0.000444 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.95e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 309 | +| iterations | 6334 | +| time_elapsed | 20951 | +| total_timesteps | 6486016 | +| train/ | | +| approx_kl | 1.8717469 | +| clip_fraction | 0.456 | +| clip_range | 0.2 | +| entropy_loss | -0.349 | +| explained_variance | -3.5 | +| learning_rate | 0.0001 | +| loss | -0.1 | +| n_updates | 123860 | +| policy_gradient_loss | -0.0646 | +| value_loss | 0.000447 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.95e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 309 | +| iterations | 6335 | +| time_elapsed | 20954 | +| total_timesteps | 6487040 | +| train/ | | +| approx_kl | 2.2201133 | +| clip_fraction | 0.577 | +| clip_range | 0.2 | +| entropy_loss | -0.55 | +| explained_variance | -1.53 | +| learning_rate | 0.0001 | +| loss | -0.0855 | +| n_updates | 123870 | +| policy_gradient_loss | -0.0473 | +| value_loss | 0.000169 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.95e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 309 | +| iterations | 6336 | +| time_elapsed | 20957 | +| total_timesteps | 6488064 | +| train/ | | +| approx_kl | 3.4143457 | +| clip_fraction | 0.421 | +| clip_range | 0.2 | +| entropy_loss | -0.489 | +| explained_variance | -0.246 | +| learning_rate | 0.0001 | +| loss | -0.0767 | +| n_updates | 123880 | +| policy_gradient_loss | -0.0454 | +| value_loss | 0.00114 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.95e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 309 | +| iterations | 6337 | +| time_elapsed | 20960 | +| total_timesteps | 6489088 | +| train/ | | +| approx_kl | 2.0794291 | +| clip_fraction | 0.476 | +| clip_range | 0.2 | +| entropy_loss | -0.327 | +| explained_variance | -6.01 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 123890 | +| policy_gradient_loss | -0.0709 | +| value_loss | 0.000573 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.01e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 309 | +| iterations | 6338 | +| time_elapsed | 20964 | +| total_timesteps | 6490112 | +| train/ | | +| approx_kl | 2.0824332 | +| clip_fraction | 0.506 | +| clip_range | 0.2 | +| entropy_loss | -0.385 | +| explained_variance | -3.19 | +| learning_rate | 0.0001 | +| loss | -0.112 | +| n_updates | 123900 | +| policy_gradient_loss | -0.0695 | +| value_loss | 0.000359 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.01e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 309 | +| iterations | 6339 | +| time_elapsed | 20967 | +| total_timesteps | 6491136 | +| train/ | | +| approx_kl | 2.8677092 | +| clip_fraction | 0.513 | +| clip_range | 0.2 | +| entropy_loss | -0.394 | +| explained_variance | -3.13 | +| learning_rate | 0.0001 | +| loss | -0.0681 | +| n_updates | 123910 | +| policy_gradient_loss | -0.0657 | +| value_loss | 0.000194 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.01e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 309 | +| iterations | 6340 | +| time_elapsed | 20970 | +| total_timesteps | 6492160 | +| train/ | | +| approx_kl | 3.4865005 | +| clip_fraction | 0.448 | +| clip_range | 0.2 | +| entropy_loss | -0.34 | +| explained_variance | -0.425 | +| learning_rate | 0.0001 | +| loss | 0.00943 | +| n_updates | 123920 | +| policy_gradient_loss | -0.0417 | +| value_loss | 0.000736 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.02e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 309 | +| iterations | 6341 | +| time_elapsed | 20973 | +| total_timesteps | 6493184 | +| train/ | | +| approx_kl | 2.0451694 | +| clip_fraction | 0.458 | +| clip_range | 0.2 | +| entropy_loss | -0.369 | +| explained_variance | -3.61 | +| learning_rate | 0.0001 | +| loss | -0.0935 | +| n_updates | 123930 | +| policy_gradient_loss | -0.0612 | +| value_loss | 0.000494 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.02e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 309 | +| iterations | 6342 | +| time_elapsed | 20976 | +| total_timesteps | 6494208 | +| train/ | | +| approx_kl | 2.7653408 | +| clip_fraction | 0.473 | +| clip_range | 0.2 | +| entropy_loss | -0.342 | +| explained_variance | -0.963 | +| learning_rate | 0.0001 | +| loss | -0.0678 | +| n_updates | 123940 | +| policy_gradient_loss | -0.0602 | +| value_loss | 0.00064 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.02e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 309 | +| iterations | 6343 | +| time_elapsed | 20980 | +| total_timesteps | 6495232 | +| train/ | | +| approx_kl | 2.3452883 | +| clip_fraction | 0.484 | +| clip_range | 0.2 | +| entropy_loss | -0.402 | +| explained_variance | -0.737 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 123950 | +| policy_gradient_loss | -0.0672 | +| value_loss | 0.000419 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.02e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 309 | +| iterations | 6344 | +| time_elapsed | 20983 | +| total_timesteps | 6496256 | +| train/ | | +| approx_kl | 2.5945878 | +| clip_fraction | 0.457 | +| clip_range | 0.2 | +| entropy_loss | -0.295 | +| explained_variance | -0.358 | +| learning_rate | 0.0001 | +| loss | -0.0579 | +| n_updates | 123960 | +| policy_gradient_loss | -0.0497 | +| value_loss | 0.000264 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.02e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 309 | +| iterations | 6345 | +| time_elapsed | 20987 | +| total_timesteps | 6497280 | +| train/ | | +| approx_kl | 2.4620929 | +| clip_fraction | 0.493 | +| clip_range | 0.2 | +| entropy_loss | -0.343 | +| explained_variance | -1.93 | +| learning_rate | 0.0001 | +| loss | -0.095 | +| n_updates | 123970 | +| policy_gradient_loss | -0.0648 | +| value_loss | 0.000428 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.03e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 309 | +| iterations | 6346 | +| time_elapsed | 20990 | +| total_timesteps | 6498304 | +| train/ | | +| approx_kl | 2.1535492 | +| clip_fraction | 0.447 | +| clip_range | 0.2 | +| entropy_loss | -0.307 | +| explained_variance | -4.33 | +| learning_rate | 0.0001 | +| loss | -0.11 | +| n_updates | 123980 | +| policy_gradient_loss | -0.0686 | +| value_loss | 0.00038 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.03e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 309 | +| iterations | 6347 | +| time_elapsed | 20994 | +| total_timesteps | 6499328 | +| train/ | | +| approx_kl | 2.1851878 | +| clip_fraction | 0.507 | +| clip_range | 0.2 | +| entropy_loss | -0.396 | +| explained_variance | -0.33 | +| learning_rate | 0.0001 | +| loss | -0.0785 | +| n_updates | 123990 | +| policy_gradient_loss | -0.0436 | +| value_loss | 0.000623 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.04e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 309 | +| iterations | 6348 | +| time_elapsed | 20997 | +| total_timesteps | 6500352 | +| train/ | | +| approx_kl | 1.8162568 | +| clip_fraction | 0.476 | +| clip_range | 0.2 | +| entropy_loss | -0.38 | +| explained_variance | -1.06 | +| learning_rate | 0.0001 | +| loss | -0.098 | +| n_updates | 124000 | +| policy_gradient_loss | -0.0644 | +| value_loss | 0.000446 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.04e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 309 | +| iterations | 6349 | +| time_elapsed | 21000 | +| total_timesteps | 6501376 | +| train/ | | +| approx_kl | 2.1838722 | +| clip_fraction | 0.479 | +| clip_range | 0.2 | +| entropy_loss | -0.34 | +| explained_variance | -0.59 | +| learning_rate | 0.0001 | +| loss | -0.0497 | +| n_updates | 124010 | +| policy_gradient_loss | -0.0563 | +| value_loss | 0.000365 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.05e+03 | +| ep_rew_mean | 0.304 | +| time/ | | +| fps | 309 | +| iterations | 6350 | +| time_elapsed | 21004 | +| total_timesteps | 6502400 | +| train/ | | +| approx_kl | 2.2173376 | +| clip_fraction | 0.473 | +| clip_range | 0.2 | +| entropy_loss | -0.343 | +| explained_variance | -1.16 | +| learning_rate | 0.0001 | +| loss | -0.0917 | +| n_updates | 124020 | +| policy_gradient_loss | -0.0618 | +| value_loss | 0.000264 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.05e+03 | +| ep_rew_mean | 0.304 | +| time/ | | +| fps | 309 | +| iterations | 6351 | +| time_elapsed | 21007 | +| total_timesteps | 6503424 | +| train/ | | +| approx_kl | 2.0335982 | +| clip_fraction | 0.432 | +| clip_range | 0.2 | +| entropy_loss | -0.294 | +| explained_variance | -0.0394 | +| learning_rate | 0.0001 | +| loss | -0.0819 | +| n_updates | 124030 | +| policy_gradient_loss | -0.0564 | +| value_loss | 0.00038 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.06e+03 | +| ep_rew_mean | 0.302 | +| time/ | | +| fps | 309 | +| iterations | 6352 | +| time_elapsed | 21010 | +| total_timesteps | 6504448 | +| train/ | | +| approx_kl | 2.7317562 | +| clip_fraction | 0.516 | +| clip_range | 0.2 | +| entropy_loss | -0.375 | +| explained_variance | -1.61 | +| learning_rate | 0.0001 | +| loss | -0.0941 | +| n_updates | 124040 | +| policy_gradient_loss | -0.0666 | +| value_loss | 0.000399 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.06e+03 | +| ep_rew_mean | 0.302 | +| time/ | | +| fps | 309 | +| iterations | 6353 | +| time_elapsed | 21014 | +| total_timesteps | 6505472 | +| train/ | | +| approx_kl | 2.8363316 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.335 | +| explained_variance | -1.94 | +| learning_rate | 0.0001 | +| loss | -0.113 | +| n_updates | 124050 | +| policy_gradient_loss | -0.0644 | +| value_loss | 0.000413 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.06e+03 | +| ep_rew_mean | 0.302 | +| time/ | | +| fps | 309 | +| iterations | 6354 | +| time_elapsed | 21017 | +| total_timesteps | 6506496 | +| train/ | | +| approx_kl | 1.964294 | +| clip_fraction | 0.472 | +| clip_range | 0.2 | +| entropy_loss | -0.333 | +| explained_variance | -0.503 | +| learning_rate | 0.0001 | +| loss | -0.0893 | +| n_updates | 124060 | +| policy_gradient_loss | -0.059 | +| value_loss | 0.00044 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.07e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 309 | +| iterations | 6355 | +| time_elapsed | 21020 | +| total_timesteps | 6507520 | +| train/ | | +| approx_kl | 2.055683 | +| clip_fraction | 0.503 | +| clip_range | 0.2 | +| entropy_loss | -0.377 | +| explained_variance | -1.32 | +| learning_rate | 0.0001 | +| loss | -0.064 | +| n_updates | 124070 | +| policy_gradient_loss | -0.059 | +| value_loss | 0.000378 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.07e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 309 | +| iterations | 6356 | +| time_elapsed | 21023 | +| total_timesteps | 6508544 | +| train/ | | +| approx_kl | 2.0630348 | +| clip_fraction | 0.512 | +| clip_range | 0.2 | +| entropy_loss | -0.43 | +| explained_variance | -1.76 | +| learning_rate | 0.0001 | +| loss | -0.0942 | +| n_updates | 124080 | +| policy_gradient_loss | -0.0697 | +| value_loss | 0.000231 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.06e+03 | +| ep_rew_mean | 0.302 | +| time/ | | +| fps | 309 | +| iterations | 6357 | +| time_elapsed | 21026 | +| total_timesteps | 6509568 | +| train/ | | +| approx_kl | 2.418021 | +| clip_fraction | 0.538 | +| clip_range | 0.2 | +| entropy_loss | -0.427 | +| explained_variance | -0.406 | +| learning_rate | 0.0001 | +| loss | -0.093 | +| n_updates | 124090 | +| policy_gradient_loss | -0.0573 | +| value_loss | 0.000493 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.06e+03 | +| ep_rew_mean | 0.302 | +| time/ | | +| fps | 309 | +| iterations | 6358 | +| time_elapsed | 21030 | +| total_timesteps | 6510592 | +| train/ | | +| approx_kl | 2.4266694 | +| clip_fraction | 0.488 | +| clip_range | 0.2 | +| entropy_loss | -0.378 | +| explained_variance | -0.776 | +| learning_rate | 0.0001 | +| loss | -0.0872 | +| n_updates | 124100 | +| policy_gradient_loss | -0.0599 | +| value_loss | 0.000396 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.07e+03 | +| ep_rew_mean | 0.304 | +| time/ | | +| fps | 309 | +| iterations | 6359 | +| time_elapsed | 21033 | +| total_timesteps | 6511616 | +| train/ | | +| approx_kl | 1.6367874 | +| clip_fraction | 0.509 | +| clip_range | 0.2 | +| entropy_loss | -0.441 | +| explained_variance | -1.34 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 124110 | +| policy_gradient_loss | -0.0727 | +| value_loss | 0.000315 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.07e+03 | +| ep_rew_mean | 0.304 | +| time/ | | +| fps | 309 | +| iterations | 6360 | +| time_elapsed | 21036 | +| total_timesteps | 6512640 | +| train/ | | +| approx_kl | 3.4567928 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.32 | +| explained_variance | -1.31 | +| learning_rate | 0.0001 | +| loss | -0.0601 | +| n_updates | 124120 | +| policy_gradient_loss | -0.0465 | +| value_loss | 0.000475 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.07e+03 | +| ep_rew_mean | 0.304 | +| time/ | | +| fps | 309 | +| iterations | 6361 | +| time_elapsed | 21039 | +| total_timesteps | 6513664 | +| train/ | | +| approx_kl | 2.2897687 | +| clip_fraction | 0.499 | +| clip_range | 0.2 | +| entropy_loss | -0.432 | +| explained_variance | -2.27 | +| learning_rate | 0.0001 | +| loss | -0.0859 | +| n_updates | 124130 | +| policy_gradient_loss | -0.0666 | +| value_loss | 0.000321 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.07e+03 | +| ep_rew_mean | 0.304 | +| time/ | | +| fps | 309 | +| iterations | 6362 | +| time_elapsed | 21042 | +| total_timesteps | 6514688 | +| train/ | | +| approx_kl | 1.9417709 | +| clip_fraction | 0.458 | +| clip_range | 0.2 | +| entropy_loss | -0.324 | +| explained_variance | -0.594 | +| learning_rate | 0.0001 | +| loss | -0.0878 | +| n_updates | 124140 | +| policy_gradient_loss | -0.0529 | +| value_loss | 0.000406 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.08e+03 | +| ep_rew_mean | 0.302 | +| time/ | | +| fps | 309 | +| iterations | 6363 | +| time_elapsed | 21046 | +| total_timesteps | 6515712 | +| train/ | | +| approx_kl | 2.47335 | +| clip_fraction | 0.482 | +| clip_range | 0.2 | +| entropy_loss | -0.294 | +| explained_variance | -2.56 | +| learning_rate | 0.0001 | +| loss | -0.099 | +| n_updates | 124150 | +| policy_gradient_loss | -0.0679 | +| value_loss | 0.000564 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.08e+03 | +| ep_rew_mean | 0.302 | +| time/ | | +| fps | 309 | +| iterations | 6364 | +| time_elapsed | 21049 | +| total_timesteps | 6516736 | +| train/ | | +| approx_kl | 2.5711231 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.36 | +| explained_variance | -0.185 | +| learning_rate | 0.0001 | +| loss | -0.0895 | +| n_updates | 124160 | +| policy_gradient_loss | -0.0588 | +| value_loss | 0.000546 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.08e+03 | +| ep_rew_mean | 0.302 | +| time/ | | +| fps | 309 | +| iterations | 6365 | +| time_elapsed | 21052 | +| total_timesteps | 6517760 | +| train/ | | +| approx_kl | 2.6427584 | +| clip_fraction | 0.454 | +| clip_range | 0.2 | +| entropy_loss | -0.276 | +| explained_variance | -3.91 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 124170 | +| policy_gradient_loss | -0.0647 | +| value_loss | 0.000374 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.08e+03 | +| ep_rew_mean | 0.302 | +| time/ | | +| fps | 309 | +| iterations | 6366 | +| time_elapsed | 21056 | +| total_timesteps | 6518784 | +| train/ | | +| approx_kl | 2.156467 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.362 | +| explained_variance | -0.615 | +| learning_rate | 0.0001 | +| loss | -0.0783 | +| n_updates | 124180 | +| policy_gradient_loss | -0.0591 | +| value_loss | 0.000382 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.09e+03 | +| ep_rew_mean | 0.302 | +| time/ | | +| fps | 309 | +| iterations | 6367 | +| time_elapsed | 21059 | +| total_timesteps | 6519808 | +| train/ | | +| approx_kl | 2.6827016 | +| clip_fraction | 0.5 | +| clip_range | 0.2 | +| entropy_loss | -0.344 | +| explained_variance | -2.24 | +| learning_rate | 0.0001 | +| loss | -0.0749 | +| n_updates | 124190 | +| policy_gradient_loss | -0.0679 | +| value_loss | 0.000544 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.09e+03 | +| ep_rew_mean | 0.302 | +| time/ | | +| fps | 309 | +| iterations | 6368 | +| time_elapsed | 21062 | +| total_timesteps | 6520832 | +| train/ | | +| approx_kl | 2.6940842 | +| clip_fraction | 0.438 | +| clip_range | 0.2 | +| entropy_loss | -0.32 | +| explained_variance | -0.731 | +| learning_rate | 0.0001 | +| loss | -0.0866 | +| n_updates | 124200 | +| policy_gradient_loss | -0.0506 | +| value_loss | 0.00031 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.09e+03 | +| ep_rew_mean | 0.302 | +| time/ | | +| fps | 309 | +| iterations | 6369 | +| time_elapsed | 21066 | +| total_timesteps | 6521856 | +| train/ | | +| approx_kl | 2.6223645 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.335 | +| explained_variance | -3.76 | +| learning_rate | 0.0001 | +| loss | -0.0851 | +| n_updates | 124210 | +| policy_gradient_loss | -0.0645 | +| value_loss | 0.000185 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.11e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 309 | +| iterations | 6370 | +| time_elapsed | 21069 | +| total_timesteps | 6522880 | +| train/ | | +| approx_kl | 1.6536144 | +| clip_fraction | 0.455 | +| clip_range | 0.2 | +| entropy_loss | -0.355 | +| explained_variance | -0.573 | +| learning_rate | 0.0001 | +| loss | -0.0896 | +| n_updates | 124220 | +| policy_gradient_loss | -0.0653 | +| value_loss | 0.000254 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.11e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 309 | +| iterations | 6371 | +| time_elapsed | 21072 | +| total_timesteps | 6523904 | +| train/ | | +| approx_kl | 2.2653434 | +| clip_fraction | 0.452 | +| clip_range | 0.2 | +| entropy_loss | -0.294 | +| explained_variance | -0.75 | +| learning_rate | 0.0001 | +| loss | -0.0703 | +| n_updates | 124230 | +| policy_gradient_loss | -0.0524 | +| value_loss | 0.000447 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.12e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 309 | +| iterations | 6372 | +| time_elapsed | 21075 | +| total_timesteps | 6524928 | +| train/ | | +| approx_kl | 2.3059173 | +| clip_fraction | 0.486 | +| clip_range | 0.2 | +| entropy_loss | -0.343 | +| explained_variance | -4.13 | +| learning_rate | 0.0001 | +| loss | -0.0896 | +| n_updates | 124240 | +| policy_gradient_loss | -0.0688 | +| value_loss | 0.00024 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.12e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 309 | +| iterations | 6373 | +| time_elapsed | 21079 | +| total_timesteps | 6525952 | +| train/ | | +| approx_kl | 2.4856873 | +| clip_fraction | 0.473 | +| clip_range | 0.2 | +| entropy_loss | -0.335 | +| explained_variance | 0.00416 | +| learning_rate | 0.0001 | +| loss | -0.0808 | +| n_updates | 124250 | +| policy_gradient_loss | -0.057 | +| value_loss | 0.000364 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.12e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 309 | +| iterations | 6374 | +| time_elapsed | 21082 | +| total_timesteps | 6526976 | +| train/ | | +| approx_kl | 2.3219151 | +| clip_fraction | 0.502 | +| clip_range | 0.2 | +| entropy_loss | -0.42 | +| explained_variance | -3.28 | +| learning_rate | 0.0001 | +| loss | -0.0909 | +| n_updates | 124260 | +| policy_gradient_loss | -0.0689 | +| value_loss | 0.000341 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.14e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 309 | +| iterations | 6375 | +| time_elapsed | 21085 | +| total_timesteps | 6528000 | +| train/ | | +| approx_kl | 1.9832263 | +| clip_fraction | 0.507 | +| clip_range | 0.2 | +| entropy_loss | -0.397 | +| explained_variance | -0.847 | +| learning_rate | 0.0001 | +| loss | -0.107 | +| n_updates | 124270 | +| policy_gradient_loss | -0.0655 | +| value_loss | 0.000225 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.14e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 309 | +| iterations | 6376 | +| time_elapsed | 21088 | +| total_timesteps | 6529024 | +| train/ | | +| approx_kl | 1.572507 | +| clip_fraction | 0.486 | +| clip_range | 0.2 | +| entropy_loss | -0.454 | +| explained_variance | 0.237 | +| learning_rate | 0.0001 | +| loss | -0.0448 | +| n_updates | 124280 | +| policy_gradient_loss | -0.0428 | +| value_loss | 0.000263 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.14e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 309 | +| iterations | 6377 | +| time_elapsed | 21091 | +| total_timesteps | 6530048 | +| train/ | | +| approx_kl | 4.7859535 | +| clip_fraction | 0.55 | +| clip_range | 0.2 | +| entropy_loss | -0.437 | +| explained_variance | -8.74 | +| learning_rate | 0.0001 | +| loss | -0.11 | +| n_updates | 124290 | +| policy_gradient_loss | -0.0691 | +| value_loss | 0.000255 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.15e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 309 | +| iterations | 6378 | +| time_elapsed | 21094 | +| total_timesteps | 6531072 | +| train/ | | +| approx_kl | 2.2694187 | +| clip_fraction | 0.493 | +| clip_range | 0.2 | +| entropy_loss | -0.347 | +| explained_variance | -1.98 | +| learning_rate | 0.0001 | +| loss | -0.0792 | +| n_updates | 124300 | +| policy_gradient_loss | -0.0604 | +| value_loss | 0.000395 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.15e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 309 | +| iterations | 6379 | +| time_elapsed | 21097 | +| total_timesteps | 6532096 | +| train/ | | +| approx_kl | 2.6320162 | +| clip_fraction | 0.525 | +| clip_range | 0.2 | +| entropy_loss | -0.44 | +| explained_variance | -0.803 | +| learning_rate | 0.0001 | +| loss | -0.0585 | +| n_updates | 124310 | +| policy_gradient_loss | -0.0412 | +| value_loss | 0.000251 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.16e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 309 | +| iterations | 6380 | +| time_elapsed | 21101 | +| total_timesteps | 6533120 | +| train/ | | +| approx_kl | 2.409525 | +| clip_fraction | 0.485 | +| clip_range | 0.2 | +| entropy_loss | -0.388 | +| explained_variance | -0.91 | +| learning_rate | 0.0001 | +| loss | -0.0792 | +| n_updates | 124320 | +| policy_gradient_loss | -0.0701 | +| value_loss | 0.000425 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.16e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 309 | +| iterations | 6381 | +| time_elapsed | 21104 | +| total_timesteps | 6534144 | +| train/ | | +| approx_kl | 3.5283065 | +| clip_fraction | 0.464 | +| clip_range | 0.2 | +| entropy_loss | -0.38 | +| explained_variance | -0.832 | +| learning_rate | 0.0001 | +| loss | -0.0202 | +| n_updates | 124330 | +| policy_gradient_loss | -0.055 | +| value_loss | 0.000557 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.15e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 309 | +| iterations | 6382 | +| time_elapsed | 21108 | +| total_timesteps | 6535168 | +| train/ | | +| approx_kl | 2.3422022 | +| clip_fraction | 0.486 | +| clip_range | 0.2 | +| entropy_loss | -0.335 | +| explained_variance | -0.812 | +| learning_rate | 0.0001 | +| loss | -0.0912 | +| n_updates | 124340 | +| policy_gradient_loss | -0.0663 | +| value_loss | 0.000833 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.15e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 309 | +| iterations | 6383 | +| time_elapsed | 21111 | +| total_timesteps | 6536192 | +| train/ | | +| approx_kl | 2.463556 | +| clip_fraction | 0.459 | +| clip_range | 0.2 | +| entropy_loss | -0.303 | +| explained_variance | -2.06 | +| learning_rate | 0.0001 | +| loss | -0.0878 | +| n_updates | 124350 | +| policy_gradient_loss | -0.0553 | +| value_loss | 0.000399 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.15e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 309 | +| iterations | 6384 | +| time_elapsed | 21115 | +| total_timesteps | 6537216 | +| train/ | | +| approx_kl | 2.1126108 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.385 | +| explained_variance | -2.47 | +| learning_rate | 0.0001 | +| loss | -0.0987 | +| n_updates | 124360 | +| policy_gradient_loss | -0.0614 | +| value_loss | 0.000256 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.15e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 309 | +| iterations | 6385 | +| time_elapsed | 21118 | +| total_timesteps | 6538240 | +| train/ | | +| approx_kl | 2.5400095 | +| clip_fraction | 0.428 | +| clip_range | 0.2 | +| entropy_loss | -0.289 | +| explained_variance | -2.88 | +| learning_rate | 0.0001 | +| loss | -0.081 | +| n_updates | 124370 | +| policy_gradient_loss | -0.0534 | +| value_loss | 0.000271 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.15e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 309 | +| iterations | 6386 | +| time_elapsed | 21121 | +| total_timesteps | 6539264 | +| train/ | | +| approx_kl | 2.1525304 | +| clip_fraction | 0.477 | +| clip_range | 0.2 | +| entropy_loss | -0.356 | +| explained_variance | -3.89 | +| learning_rate | 0.0001 | +| loss | -0.107 | +| n_updates | 124380 | +| policy_gradient_loss | -0.0717 | +| value_loss | 0.000212 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.15e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 309 | +| iterations | 6387 | +| time_elapsed | 21125 | +| total_timesteps | 6540288 | +| train/ | | +| approx_kl | 0.9642144 | +| clip_fraction | 0.398 | +| clip_range | 0.2 | +| entropy_loss | -0.499 | +| explained_variance | 0.274 | +| learning_rate | 0.0001 | +| loss | -0.0251 | +| n_updates | 124390 | +| policy_gradient_loss | -0.0245 | +| value_loss | 0.000567 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.19e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 309 | +| iterations | 6388 | +| time_elapsed | 21128 | +| total_timesteps | 6541312 | +| train/ | | +| approx_kl | 2.6965237 | +| clip_fraction | 0.51 | +| clip_range | 0.2 | +| entropy_loss | -0.373 | +| explained_variance | -2.32 | +| learning_rate | 0.0001 | +| loss | -0.0881 | +| n_updates | 124400 | +| policy_gradient_loss | -0.065 | +| value_loss | 0.000414 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.18e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 309 | +| iterations | 6389 | +| time_elapsed | 21132 | +| total_timesteps | 6542336 | +| train/ | | +| approx_kl | 2.7788978 | +| clip_fraction | 0.441 | +| clip_range | 0.2 | +| entropy_loss | -0.316 | +| explained_variance | -0.849 | +| learning_rate | 0.0001 | +| loss | -0.0849 | +| n_updates | 124410 | +| policy_gradient_loss | -0.0598 | +| value_loss | 0.000721 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.18e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 309 | +| iterations | 6390 | +| time_elapsed | 21135 | +| total_timesteps | 6543360 | +| train/ | | +| approx_kl | 1.9459081 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.389 | +| explained_variance | 0.196 | +| learning_rate | 0.0001 | +| loss | -0.0602 | +| n_updates | 124420 | +| policy_gradient_loss | -0.0654 | +| value_loss | 0.00064 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.18e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 309 | +| iterations | 6391 | +| time_elapsed | 21138 | +| total_timesteps | 6544384 | +| train/ | | +| approx_kl | 3.0763721 | +| clip_fraction | 0.456 | +| clip_range | 0.2 | +| entropy_loss | -0.302 | +| explained_variance | -7.72 | +| learning_rate | 0.0001 | +| loss | -0.0991 | +| n_updates | 124430 | +| policy_gradient_loss | -0.0627 | +| value_loss | 0.000568 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.19e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 309 | +| iterations | 6392 | +| time_elapsed | 21141 | +| total_timesteps | 6545408 | +| train/ | | +| approx_kl | 2.8381581 | +| clip_fraction | 0.477 | +| clip_range | 0.2 | +| entropy_loss | -0.349 | +| explained_variance | -1.26 | +| learning_rate | 0.0001 | +| loss | -0.083 | +| n_updates | 124440 | +| policy_gradient_loss | -0.0658 | +| value_loss | 0.000446 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.19e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 309 | +| iterations | 6393 | +| time_elapsed | 21145 | +| total_timesteps | 6546432 | +| train/ | | +| approx_kl | 1.6347735 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.397 | +| explained_variance | -1.86 | +| learning_rate | 0.0001 | +| loss | -0.067 | +| n_updates | 124450 | +| policy_gradient_loss | -0.0558 | +| value_loss | 0.000393 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.19e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 309 | +| iterations | 6394 | +| time_elapsed | 21148 | +| total_timesteps | 6547456 | +| train/ | | +| approx_kl | 3.062183 | +| clip_fraction | 0.511 | +| clip_range | 0.2 | +| entropy_loss | -0.423 | +| explained_variance | -1.87 | +| learning_rate | 0.0001 | +| loss | -0.0853 | +| n_updates | 124460 | +| policy_gradient_loss | -0.067 | +| value_loss | 0.000446 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.19e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 309 | +| iterations | 6395 | +| time_elapsed | 21151 | +| total_timesteps | 6548480 | +| train/ | | +| approx_kl | 4.6038456 | +| clip_fraction | 0.479 | +| clip_range | 0.2 | +| entropy_loss | -0.363 | +| explained_variance | 0.103 | +| learning_rate | 0.0001 | +| loss | -0.059 | +| n_updates | 124470 | +| policy_gradient_loss | -0.0518 | +| value_loss | 0.000306 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.19e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 309 | +| iterations | 6396 | +| time_elapsed | 21155 | +| total_timesteps | 6549504 | +| train/ | | +| approx_kl | 2.6367345 | +| clip_fraction | 0.485 | +| clip_range | 0.2 | +| entropy_loss | -0.347 | +| explained_variance | -2.95 | +| learning_rate | 0.0001 | +| loss | -0.0964 | +| n_updates | 124480 | +| policy_gradient_loss | -0.0547 | +| value_loss | 0.000226 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.19e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 309 | +| iterations | 6397 | +| time_elapsed | 21158 | +| total_timesteps | 6550528 | +| train/ | | +| approx_kl | 2.3892403 | +| clip_fraction | 0.45 | +| clip_range | 0.2 | +| entropy_loss | -0.316 | +| explained_variance | -0.124 | +| learning_rate | 0.0001 | +| loss | -0.0667 | +| n_updates | 124490 | +| policy_gradient_loss | -0.0574 | +| value_loss | 0.000673 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.19e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 309 | +| iterations | 6398 | +| time_elapsed | 21161 | +| total_timesteps | 6551552 | +| train/ | | +| approx_kl | 2.408648 | +| clip_fraction | 0.502 | +| clip_range | 0.2 | +| entropy_loss | -0.373 | +| explained_variance | -3.51 | +| learning_rate | 0.0001 | +| loss | -0.095 | +| n_updates | 124500 | +| policy_gradient_loss | -0.0644 | +| value_loss | 0.000431 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.19e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 309 | +| iterations | 6399 | +| time_elapsed | 21165 | +| total_timesteps | 6552576 | +| train/ | | +| approx_kl | 2.2377524 | +| clip_fraction | 0.44 | +| clip_range | 0.2 | +| entropy_loss | -0.335 | +| explained_variance | -0.216 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 124510 | +| policy_gradient_loss | -0.059 | +| value_loss | 0.000374 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.19e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 309 | +| iterations | 6400 | +| time_elapsed | 21169 | +| total_timesteps | 6553600 | +| train/ | | +| approx_kl | 2.0595064 | +| clip_fraction | 0.459 | +| clip_range | 0.2 | +| entropy_loss | -0.317 | +| explained_variance | -2.23 | +| learning_rate | 0.0001 | +| loss | -0.0762 | +| n_updates | 124520 | +| policy_gradient_loss | -0.0565 | +| value_loss | 0.000403 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.19e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 309 | +| iterations | 6401 | +| time_elapsed | 21172 | +| total_timesteps | 6554624 | +| train/ | | +| approx_kl | 2.5211883 | +| clip_fraction | 0.507 | +| clip_range | 0.2 | +| entropy_loss | -0.369 | +| explained_variance | -1.46 | +| learning_rate | 0.0001 | +| loss | -0.117 | +| n_updates | 124530 | +| policy_gradient_loss | -0.0807 | +| value_loss | 0.000289 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.21e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 309 | +| iterations | 6402 | +| time_elapsed | 21176 | +| total_timesteps | 6555648 | +| train/ | | +| approx_kl | 2.4594212 | +| clip_fraction | 0.498 | +| clip_range | 0.2 | +| entropy_loss | -0.342 | +| explained_variance | -1.3 | +| learning_rate | 0.0001 | +| loss | -0.0921 | +| n_updates | 124540 | +| policy_gradient_loss | -0.0654 | +| value_loss | 0.000302 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.21e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 309 | +| iterations | 6403 | +| time_elapsed | 21179 | +| total_timesteps | 6556672 | +| train/ | | +| approx_kl | 2.425932 | +| clip_fraction | 0.452 | +| clip_range | 0.2 | +| entropy_loss | -0.347 | +| explained_variance | -0.35 | +| learning_rate | 0.0001 | +| loss | -0.0794 | +| n_updates | 124550 | +| policy_gradient_loss | -0.0516 | +| value_loss | 0.000364 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.21e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 309 | +| iterations | 6404 | +| time_elapsed | 21183 | +| total_timesteps | 6557696 | +| train/ | | +| approx_kl | 1.5308483 | +| clip_fraction | 0.494 | +| clip_range | 0.2 | +| entropy_loss | -0.45 | +| explained_variance | -3.3 | +| learning_rate | 0.0001 | +| loss | -0.083 | +| n_updates | 124560 | +| policy_gradient_loss | -0.0648 | +| value_loss | 0.000276 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.21e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 309 | +| iterations | 6405 | +| time_elapsed | 21186 | +| total_timesteps | 6558720 | +| train/ | | +| approx_kl | 2.6967933 | +| clip_fraction | 0.477 | +| clip_range | 0.2 | +| entropy_loss | -0.325 | +| explained_variance | -0.606 | +| learning_rate | 0.0001 | +| loss | -0.0496 | +| n_updates | 124570 | +| policy_gradient_loss | -0.0571 | +| value_loss | 0.000569 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.21e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 309 | +| iterations | 6406 | +| time_elapsed | 21190 | +| total_timesteps | 6559744 | +| train/ | | +| approx_kl | 2.3220544 | +| clip_fraction | 0.504 | +| clip_range | 0.2 | +| entropy_loss | -0.365 | +| explained_variance | -2.8 | +| learning_rate | 0.0001 | +| loss | -0.111 | +| n_updates | 124580 | +| policy_gradient_loss | -0.0761 | +| value_loss | 0.000597 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.23e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 309 | +| iterations | 6407 | +| time_elapsed | 21193 | +| total_timesteps | 6560768 | +| train/ | | +| approx_kl | 4.928755 | +| clip_fraction | 0.491 | +| clip_range | 0.2 | +| entropy_loss | -0.407 | +| explained_variance | -1.98 | +| learning_rate | 0.0001 | +| loss | -0.0628 | +| n_updates | 124590 | +| policy_gradient_loss | -0.0619 | +| value_loss | 0.000246 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.23e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 309 | +| iterations | 6408 | +| time_elapsed | 21196 | +| total_timesteps | 6561792 | +| train/ | | +| approx_kl | 2.1432896 | +| clip_fraction | 0.499 | +| clip_range | 0.2 | +| entropy_loss | -0.362 | +| explained_variance | -3.83 | +| learning_rate | 0.0001 | +| loss | -0.0846 | +| n_updates | 124600 | +| policy_gradient_loss | -0.0685 | +| value_loss | 0.000305 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.24e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 309 | +| iterations | 6409 | +| time_elapsed | 21199 | +| total_timesteps | 6562816 | +| train/ | | +| approx_kl | 2.432222 | +| clip_fraction | 0.499 | +| clip_range | 0.2 | +| entropy_loss | -0.352 | +| explained_variance | -2.16 | +| learning_rate | 0.0001 | +| loss | -0.111 | +| n_updates | 124610 | +| policy_gradient_loss | -0.0709 | +| value_loss | 0.000335 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.24e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 309 | +| iterations | 6410 | +| time_elapsed | 21202 | +| total_timesteps | 6563840 | +| train/ | | +| approx_kl | 3.0836349 | +| clip_fraction | 0.505 | +| clip_range | 0.2 | +| entropy_loss | -0.366 | +| explained_variance | -2.75 | +| learning_rate | 0.0001 | +| loss | -0.0908 | +| n_updates | 124620 | +| policy_gradient_loss | -0.0676 | +| value_loss | 0.000406 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.24e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 309 | +| iterations | 6411 | +| time_elapsed | 21205 | +| total_timesteps | 6564864 | +| train/ | | +| approx_kl | 2.1505003 | +| clip_fraction | 0.477 | +| clip_range | 0.2 | +| entropy_loss | -0.347 | +| explained_variance | -3.11 | +| learning_rate | 0.0001 | +| loss | -0.0806 | +| n_updates | 124630 | +| policy_gradient_loss | -0.0654 | +| value_loss | 0.000583 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.24e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 309 | +| iterations | 6412 | +| time_elapsed | 21209 | +| total_timesteps | 6565888 | +| train/ | | +| approx_kl | 2.0766318 | +| clip_fraction | 0.476 | +| clip_range | 0.2 | +| entropy_loss | -0.414 | +| explained_variance | -1.65 | +| learning_rate | 0.0001 | +| loss | -0.0673 | +| n_updates | 124640 | +| policy_gradient_loss | -0.0603 | +| value_loss | 0.000411 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.24e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 309 | +| iterations | 6413 | +| time_elapsed | 21212 | +| total_timesteps | 6566912 | +| train/ | | +| approx_kl | 4.088675 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.361 | +| explained_variance | 0.0324 | +| learning_rate | 0.0001 | +| loss | -0.0593 | +| n_updates | 124650 | +| policy_gradient_loss | -0.0527 | +| value_loss | 0.00049 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.25e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 309 | +| iterations | 6414 | +| time_elapsed | 21215 | +| total_timesteps | 6567936 | +| train/ | | +| approx_kl | 2.090317 | +| clip_fraction | 0.503 | +| clip_range | 0.2 | +| entropy_loss | -0.392 | +| explained_variance | -1.23 | +| learning_rate | 0.0001 | +| loss | -0.0957 | +| n_updates | 124660 | +| policy_gradient_loss | -0.0698 | +| value_loss | 0.000478 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.25e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 309 | +| iterations | 6415 | +| time_elapsed | 21218 | +| total_timesteps | 6568960 | +| train/ | | +| approx_kl | 5.242017 | +| clip_fraction | 0.514 | +| clip_range | 0.2 | +| entropy_loss | -0.388 | +| explained_variance | -0.759 | +| learning_rate | 0.0001 | +| loss | -0.0968 | +| n_updates | 124670 | +| policy_gradient_loss | -0.0615 | +| value_loss | 0.000358 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.24e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 309 | +| iterations | 6416 | +| time_elapsed | 21222 | +| total_timesteps | 6569984 | +| train/ | | +| approx_kl | 2.6858819 | +| clip_fraction | 0.519 | +| clip_range | 0.2 | +| entropy_loss | -0.424 | +| explained_variance | -2.46 | +| learning_rate | 0.0001 | +| loss | -0.0922 | +| n_updates | 124680 | +| policy_gradient_loss | -0.0686 | +| value_loss | 0.000526 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.24e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 309 | +| iterations | 6417 | +| time_elapsed | 21225 | +| total_timesteps | 6571008 | +| train/ | | +| approx_kl | 1.9297528 | +| clip_fraction | 0.469 | +| clip_range | 0.2 | +| entropy_loss | -0.342 | +| explained_variance | -0.718 | +| learning_rate | 0.0001 | +| loss | -0.0809 | +| n_updates | 124690 | +| policy_gradient_loss | -0.0518 | +| value_loss | 0.000432 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.25e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 309 | +| iterations | 6418 | +| time_elapsed | 21228 | +| total_timesteps | 6572032 | +| train/ | | +| approx_kl | 2.987129 | +| clip_fraction | 0.504 | +| clip_range | 0.2 | +| entropy_loss | -0.371 | +| explained_variance | -2.46 | +| learning_rate | 0.0001 | +| loss | -0.0638 | +| n_updates | 124700 | +| policy_gradient_loss | -0.0647 | +| value_loss | 0.000372 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.25e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 309 | +| iterations | 6419 | +| time_elapsed | 21232 | +| total_timesteps | 6573056 | +| train/ | | +| approx_kl | 2.9758358 | +| clip_fraction | 0.504 | +| clip_range | 0.2 | +| entropy_loss | -0.388 | +| explained_variance | -0.549 | +| learning_rate | 0.0001 | +| loss | -0.0592 | +| n_updates | 124710 | +| policy_gradient_loss | -0.0546 | +| value_loss | 0.000226 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.26e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 309 | +| iterations | 6420 | +| time_elapsed | 21235 | +| total_timesteps | 6574080 | +| train/ | | +| approx_kl | 2.692411 | +| clip_fraction | 0.479 | +| clip_range | 0.2 | +| entropy_loss | -0.384 | +| explained_variance | -1.69 | +| learning_rate | 0.0001 | +| loss | -0.0981 | +| n_updates | 124720 | +| policy_gradient_loss | -0.0602 | +| value_loss | 0.00043 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.26e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 309 | +| iterations | 6421 | +| time_elapsed | 21239 | +| total_timesteps | 6575104 | +| train/ | | +| approx_kl | 2.0867438 | +| clip_fraction | 0.478 | +| clip_range | 0.2 | +| entropy_loss | -0.358 | +| explained_variance | -1.28 | +| learning_rate | 0.0001 | +| loss | -0.0501 | +| n_updates | 124730 | +| policy_gradient_loss | -0.0559 | +| value_loss | 0.000632 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.26e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 309 | +| iterations | 6422 | +| time_elapsed | 21242 | +| total_timesteps | 6576128 | +| train/ | | +| approx_kl | 2.0810697 | +| clip_fraction | 0.454 | +| clip_range | 0.2 | +| entropy_loss | -0.303 | +| explained_variance | -1.72 | +| learning_rate | 0.0001 | +| loss | -0.0848 | +| n_updates | 124740 | +| policy_gradient_loss | -0.0684 | +| value_loss | 0.000773 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.27e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 309 | +| iterations | 6423 | +| time_elapsed | 21246 | +| total_timesteps | 6577152 | +| train/ | | +| approx_kl | 4.3132033 | +| clip_fraction | 0.511 | +| clip_range | 0.2 | +| entropy_loss | -0.472 | +| explained_variance | -1.47 | +| learning_rate | 0.0001 | +| loss | -0.0937 | +| n_updates | 124750 | +| policy_gradient_loss | -0.0696 | +| value_loss | 0.000218 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.27e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 309 | +| iterations | 6424 | +| time_elapsed | 21249 | +| total_timesteps | 6578176 | +| train/ | | +| approx_kl | 2.3506417 | +| clip_fraction | 0.44 | +| clip_range | 0.2 | +| entropy_loss | -0.272 | +| explained_variance | -0.595 | +| learning_rate | 0.0001 | +| loss | -0.0455 | +| n_updates | 124760 | +| policy_gradient_loss | -0.0461 | +| value_loss | 0.000277 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.27e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 309 | +| iterations | 6425 | +| time_elapsed | 21252 | +| total_timesteps | 6579200 | +| train/ | | +| approx_kl | 1.9855044 | +| clip_fraction | 0.501 | +| clip_range | 0.2 | +| entropy_loss | -0.369 | +| explained_variance | -0.554 | +| learning_rate | 0.0001 | +| loss | -0.0445 | +| n_updates | 124770 | +| policy_gradient_loss | -0.0601 | +| value_loss | 0.000763 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.27e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 309 | +| iterations | 6426 | +| time_elapsed | 21255 | +| total_timesteps | 6580224 | +| train/ | | +| approx_kl | 2.6938415 | +| clip_fraction | 0.53 | +| clip_range | 0.2 | +| entropy_loss | -0.402 | +| explained_variance | -0.724 | +| learning_rate | 0.0001 | +| loss | -0.0926 | +| n_updates | 124780 | +| policy_gradient_loss | -0.0606 | +| value_loss | 0.000511 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.29e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 309 | +| iterations | 6427 | +| time_elapsed | 21259 | +| total_timesteps | 6581248 | +| train/ | | +| approx_kl | 2.6188393 | +| clip_fraction | 0.5 | +| clip_range | 0.2 | +| entropy_loss | -0.38 | +| explained_variance | -4.61 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 124790 | +| policy_gradient_loss | -0.0685 | +| value_loss | 0.000301 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.28e+03 | +| ep_rew_mean | 0.304 | +| time/ | | +| fps | 309 | +| iterations | 6428 | +| time_elapsed | 21262 | +| total_timesteps | 6582272 | +| train/ | | +| approx_kl | 2.1245341 | +| clip_fraction | 0.486 | +| clip_range | 0.2 | +| entropy_loss | -0.38 | +| explained_variance | -3.22 | +| learning_rate | 0.0001 | +| loss | -0.0956 | +| n_updates | 124800 | +| policy_gradient_loss | -0.0751 | +| value_loss | 0.000263 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.28e+03 | +| ep_rew_mean | 0.304 | +| time/ | | +| fps | 309 | +| iterations | 6429 | +| time_elapsed | 21265 | +| total_timesteps | 6583296 | +| train/ | | +| approx_kl | 3.0673974 | +| clip_fraction | 0.469 | +| clip_range | 0.2 | +| entropy_loss | -0.294 | +| explained_variance | -0.699 | +| learning_rate | 0.0001 | +| loss | -0.0664 | +| n_updates | 124810 | +| policy_gradient_loss | -0.0448 | +| value_loss | 0.000587 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.28e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 309 | +| iterations | 6430 | +| time_elapsed | 21268 | +| total_timesteps | 6584320 | +| train/ | | +| approx_kl | 2.5008516 | +| clip_fraction | 0.508 | +| clip_range | 0.2 | +| entropy_loss | -0.408 | +| explained_variance | -0.686 | +| learning_rate | 0.0001 | +| loss | -0.0704 | +| n_updates | 124820 | +| policy_gradient_loss | -0.0629 | +| value_loss | 0.000315 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.28e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 309 | +| iterations | 6431 | +| time_elapsed | 21271 | +| total_timesteps | 6585344 | +| train/ | | +| approx_kl | 1.9277222 | +| clip_fraction | 0.486 | +| clip_range | 0.2 | +| entropy_loss | -0.43 | +| explained_variance | -0.0431 | +| learning_rate | 0.0001 | +| loss | -0.0775 | +| n_updates | 124830 | +| policy_gradient_loss | -0.0604 | +| value_loss | 0.000308 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.28e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 309 | +| iterations | 6432 | +| time_elapsed | 21275 | +| total_timesteps | 6586368 | +| train/ | | +| approx_kl | 2.2150295 | +| clip_fraction | 0.482 | +| clip_range | 0.2 | +| entropy_loss | -0.318 | +| explained_variance | -6.17 | +| learning_rate | 0.0001 | +| loss | -0.0976 | +| n_updates | 124840 | +| policy_gradient_loss | -0.0633 | +| value_loss | 0.000471 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.29e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 309 | +| iterations | 6433 | +| time_elapsed | 21278 | +| total_timesteps | 6587392 | +| train/ | | +| approx_kl | 1.6932347 | +| clip_fraction | 0.489 | +| clip_range | 0.2 | +| entropy_loss | -0.435 | +| explained_variance | -4.44 | +| learning_rate | 0.0001 | +| loss | -0.116 | +| n_updates | 124850 | +| policy_gradient_loss | -0.0709 | +| value_loss | 0.000375 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.29e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 309 | +| iterations | 6434 | +| time_elapsed | 21281 | +| total_timesteps | 6588416 | +| train/ | | +| approx_kl | 1.8795452 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.418 | +| explained_variance | -0.101 | +| learning_rate | 0.0001 | +| loss | -0.0755 | +| n_updates | 124860 | +| policy_gradient_loss | -0.0484 | +| value_loss | 0.000239 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.29e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 309 | +| iterations | 6435 | +| time_elapsed | 21285 | +| total_timesteps | 6589440 | +| train/ | | +| approx_kl | 1.7710412 | +| clip_fraction | 0.512 | +| clip_range | 0.2 | +| entropy_loss | -0.513 | +| explained_variance | -0.82 | +| learning_rate | 0.0001 | +| loss | -0.117 | +| n_updates | 124870 | +| policy_gradient_loss | -0.0628 | +| value_loss | 0.000323 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.29e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 309 | +| iterations | 6436 | +| time_elapsed | 21288 | +| total_timesteps | 6590464 | +| train/ | | +| approx_kl | 2.6014233 | +| clip_fraction | 0.484 | +| clip_range | 0.2 | +| entropy_loss | -0.337 | +| explained_variance | -1.83 | +| learning_rate | 0.0001 | +| loss | -0.0736 | +| n_updates | 124880 | +| policy_gradient_loss | -0.0669 | +| value_loss | 0.000383 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.29e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 309 | +| iterations | 6437 | +| time_elapsed | 21292 | +| total_timesteps | 6591488 | +| train/ | | +| approx_kl | 2.8112602 | +| clip_fraction | 0.455 | +| clip_range | 0.2 | +| entropy_loss | -0.286 | +| explained_variance | -0.625 | +| learning_rate | 0.0001 | +| loss | -0.0769 | +| n_updates | 124890 | +| policy_gradient_loss | -0.0543 | +| value_loss | 0.000664 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.3e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 309 | +| iterations | 6438 | +| time_elapsed | 21295 | +| total_timesteps | 6592512 | +| train/ | | +| approx_kl | 3.0682142 | +| clip_fraction | 0.517 | +| clip_range | 0.2 | +| entropy_loss | -0.39 | +| explained_variance | -1.76 | +| learning_rate | 0.0001 | +| loss | -0.113 | +| n_updates | 124900 | +| policy_gradient_loss | -0.0734 | +| value_loss | 0.00049 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.29e+03 | +| ep_rew_mean | 0.304 | +| time/ | | +| fps | 309 | +| iterations | 6439 | +| time_elapsed | 21298 | +| total_timesteps | 6593536 | +| train/ | | +| approx_kl | 2.096885 | +| clip_fraction | 0.465 | +| clip_range | 0.2 | +| entropy_loss | -0.355 | +| explained_variance | -0.8 | +| learning_rate | 0.0001 | +| loss | -0.044 | +| n_updates | 124910 | +| policy_gradient_loss | -0.0511 | +| value_loss | 0.000499 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.29e+03 | +| ep_rew_mean | 0.304 | +| time/ | | +| fps | 309 | +| iterations | 6440 | +| time_elapsed | 21302 | +| total_timesteps | 6594560 | +| train/ | | +| approx_kl | 2.496375 | +| clip_fraction | 0.45 | +| clip_range | 0.2 | +| entropy_loss | -0.395 | +| explained_variance | 0.122 | +| learning_rate | 0.0001 | +| loss | -0.0814 | +| n_updates | 124920 | +| policy_gradient_loss | -0.0605 | +| value_loss | 0.000668 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.29e+03 | +| ep_rew_mean | 0.304 | +| time/ | | +| fps | 309 | +| iterations | 6441 | +| time_elapsed | 21305 | +| total_timesteps | 6595584 | +| train/ | | +| approx_kl | 2.2594337 | +| clip_fraction | 0.494 | +| clip_range | 0.2 | +| entropy_loss | -0.398 | +| explained_variance | -4.68 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 124930 | +| policy_gradient_loss | -0.0674 | +| value_loss | 0.000344 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.29e+03 | +| ep_rew_mean | 0.304 | +| time/ | | +| fps | 309 | +| iterations | 6442 | +| time_elapsed | 21309 | +| total_timesteps | 6596608 | +| train/ | | +| approx_kl | 1.9561373 | +| clip_fraction | 0.525 | +| clip_range | 0.2 | +| entropy_loss | -0.47 | +| explained_variance | -0.953 | +| learning_rate | 0.0001 | +| loss | -0.0873 | +| n_updates | 124940 | +| policy_gradient_loss | -0.0687 | +| value_loss | 0.000402 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.31e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 309 | +| iterations | 6443 | +| time_elapsed | 21312 | +| total_timesteps | 6597632 | +| train/ | | +| approx_kl | 2.2582011 | +| clip_fraction | 0.5 | +| clip_range | 0.2 | +| entropy_loss | -0.369 | +| explained_variance | -1.57 | +| learning_rate | 0.0001 | +| loss | -0.112 | +| n_updates | 124950 | +| policy_gradient_loss | -0.0626 | +| value_loss | 0.000257 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.31e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 309 | +| iterations | 6444 | +| time_elapsed | 21315 | +| total_timesteps | 6598656 | +| train/ | | +| approx_kl | 2.7190738 | +| clip_fraction | 0.457 | +| clip_range | 0.2 | +| entropy_loss | -0.29 | +| explained_variance | -0.401 | +| learning_rate | 0.0001 | +| loss | -0.0766 | +| n_updates | 124960 | +| policy_gradient_loss | -0.0487 | +| value_loss | 0.000513 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.31e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 309 | +| iterations | 6445 | +| time_elapsed | 21318 | +| total_timesteps | 6599680 | +| train/ | | +| approx_kl | 2.4932358 | +| clip_fraction | 0.467 | +| clip_range | 0.2 | +| entropy_loss | -0.325 | +| explained_variance | -1.26 | +| learning_rate | 0.0001 | +| loss | -0.0932 | +| n_updates | 124970 | +| policy_gradient_loss | -0.0614 | +| value_loss | 0.000604 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.31e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 309 | +| iterations | 6446 | +| time_elapsed | 21321 | +| total_timesteps | 6600704 | +| train/ | | +| approx_kl | 21.63205 | +| clip_fraction | 0.45 | +| clip_range | 0.2 | +| entropy_loss | -0.342 | +| explained_variance | -0.465 | +| learning_rate | 0.0001 | +| loss | -0.0602 | +| n_updates | 124980 | +| policy_gradient_loss | -0.0598 | +| value_loss | 0.000419 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.31e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 309 | +| iterations | 6447 | +| time_elapsed | 21325 | +| total_timesteps | 6601728 | +| train/ | | +| approx_kl | 2.737448 | +| clip_fraction | 0.516 | +| clip_range | 0.2 | +| entropy_loss | -0.377 | +| explained_variance | -9.48 | +| learning_rate | 0.0001 | +| loss | -0.0969 | +| n_updates | 124990 | +| policy_gradient_loss | -0.0742 | +| value_loss | 0.000178 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.32e+03 | +| ep_rew_mean | 0.304 | +| time/ | | +| fps | 309 | +| iterations | 6448 | +| time_elapsed | 21328 | +| total_timesteps | 6602752 | +| train/ | | +| approx_kl | 2.412807 | +| clip_fraction | 0.507 | +| clip_range | 0.2 | +| entropy_loss | -0.35 | +| explained_variance | -1.19 | +| learning_rate | 0.0001 | +| loss | -0.111 | +| n_updates | 125000 | +| policy_gradient_loss | -0.0619 | +| value_loss | 0.000419 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.32e+03 | +| ep_rew_mean | 0.304 | +| time/ | | +| fps | 309 | +| iterations | 6449 | +| time_elapsed | 21331 | +| total_timesteps | 6603776 | +| train/ | | +| approx_kl | 2.496244 | +| clip_fraction | 0.502 | +| clip_range | 0.2 | +| entropy_loss | -0.366 | +| explained_variance | -0.94 | +| learning_rate | 0.0001 | +| loss | -0.0831 | +| n_updates | 125010 | +| policy_gradient_loss | -0.0606 | +| value_loss | 0.000425 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.32e+03 | +| ep_rew_mean | 0.304 | +| time/ | | +| fps | 309 | +| iterations | 6450 | +| time_elapsed | 21334 | +| total_timesteps | 6604800 | +| train/ | | +| approx_kl | 2.4957588 | +| clip_fraction | 0.519 | +| clip_range | 0.2 | +| entropy_loss | -0.368 | +| explained_variance | -3.57 | +| learning_rate | 0.0001 | +| loss | -0.0714 | +| n_updates | 125020 | +| policy_gradient_loss | -0.056 | +| value_loss | 0.000284 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.33e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 309 | +| iterations | 6451 | +| time_elapsed | 21337 | +| total_timesteps | 6605824 | +| train/ | | +| approx_kl | 3.5933056 | +| clip_fraction | 0.47 | +| clip_range | 0.2 | +| entropy_loss | -0.315 | +| explained_variance | -1.94 | +| learning_rate | 0.0001 | +| loss | -0.0893 | +| n_updates | 125030 | +| policy_gradient_loss | -0.068 | +| value_loss | 0.000444 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.33e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 309 | +| iterations | 6452 | +| time_elapsed | 21341 | +| total_timesteps | 6606848 | +| train/ | | +| approx_kl | 2.5812068 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.373 | +| explained_variance | -1.33 | +| learning_rate | 0.0001 | +| loss | -0.0711 | +| n_updates | 125040 | +| policy_gradient_loss | -0.0593 | +| value_loss | 0.00032 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.33e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 309 | +| iterations | 6453 | +| time_elapsed | 21344 | +| total_timesteps | 6607872 | +| train/ | | +| approx_kl | 2.348369 | +| clip_fraction | 0.514 | +| clip_range | 0.2 | +| entropy_loss | -0.429 | +| explained_variance | -0.873 | +| learning_rate | 0.0001 | +| loss | -0.0813 | +| n_updates | 125050 | +| policy_gradient_loss | -0.0625 | +| value_loss | 0.00057 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.34e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 309 | +| iterations | 6454 | +| time_elapsed | 21348 | +| total_timesteps | 6608896 | +| train/ | | +| approx_kl | 2.801443 | +| clip_fraction | 0.461 | +| clip_range | 0.2 | +| entropy_loss | -0.306 | +| explained_variance | -0.944 | +| learning_rate | 0.0001 | +| loss | -0.075 | +| n_updates | 125060 | +| policy_gradient_loss | -0.0565 | +| value_loss | 0.000544 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.34e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 309 | +| iterations | 6455 | +| time_elapsed | 21351 | +| total_timesteps | 6609920 | +| train/ | | +| approx_kl | 2.0816693 | +| clip_fraction | 0.443 | +| clip_range | 0.2 | +| entropy_loss | -0.315 | +| explained_variance | -0.199 | +| learning_rate | 0.0001 | +| loss | -0.0705 | +| n_updates | 125070 | +| policy_gradient_loss | -0.0546 | +| value_loss | 0.000337 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.33e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 309 | +| iterations | 6456 | +| time_elapsed | 21354 | +| total_timesteps | 6610944 | +| train/ | | +| approx_kl | 2.1270552 | +| clip_fraction | 0.467 | +| clip_range | 0.2 | +| entropy_loss | -0.352 | +| explained_variance | -2.29 | +| learning_rate | 0.0001 | +| loss | -0.0813 | +| n_updates | 125080 | +| policy_gradient_loss | -0.0676 | +| value_loss | 0.00037 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.33e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 309 | +| iterations | 6457 | +| time_elapsed | 21358 | +| total_timesteps | 6611968 | +| train/ | | +| approx_kl | 2.5217361 | +| clip_fraction | 0.442 | +| clip_range | 0.2 | +| entropy_loss | -0.325 | +| explained_variance | -0.183 | +| learning_rate | 0.0001 | +| loss | -0.0604 | +| n_updates | 125090 | +| policy_gradient_loss | -0.0534 | +| value_loss | 0.000344 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.32e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 309 | +| iterations | 6458 | +| time_elapsed | 21361 | +| total_timesteps | 6612992 | +| train/ | | +| approx_kl | 1.9610496 | +| clip_fraction | 0.473 | +| clip_range | 0.2 | +| entropy_loss | -0.368 | +| explained_variance | -1.34 | +| learning_rate | 0.0001 | +| loss | -0.0771 | +| n_updates | 125100 | +| policy_gradient_loss | -0.0613 | +| value_loss | 0.000602 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.32e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 309 | +| iterations | 6459 | +| time_elapsed | 21365 | +| total_timesteps | 6614016 | +| train/ | | +| approx_kl | 2.219026 | +| clip_fraction | 0.494 | +| clip_range | 0.2 | +| entropy_loss | -0.422 | +| explained_variance | -0.322 | +| learning_rate | 0.0001 | +| loss | -0.0488 | +| n_updates | 125110 | +| policy_gradient_loss | -0.0633 | +| value_loss | 0.000505 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.33e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 309 | +| iterations | 6460 | +| time_elapsed | 21368 | +| total_timesteps | 6615040 | +| train/ | | +| approx_kl | 8.180244 | +| clip_fraction | 0.515 | +| clip_range | 0.2 | +| entropy_loss | -0.475 | +| explained_variance | -2.33 | +| learning_rate | 0.0001 | +| loss | -0.107 | +| n_updates | 125120 | +| policy_gradient_loss | -0.0746 | +| value_loss | 0.000206 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.33e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 309 | +| iterations | 6461 | +| time_elapsed | 21371 | +| total_timesteps | 6616064 | +| train/ | | +| approx_kl | 2.150663 | +| clip_fraction | 0.465 | +| clip_range | 0.2 | +| entropy_loss | -0.318 | +| explained_variance | -0.118 | +| learning_rate | 0.0001 | +| loss | -0.0899 | +| n_updates | 125130 | +| policy_gradient_loss | -0.0639 | +| value_loss | 0.000556 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.33e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 309 | +| iterations | 6462 | +| time_elapsed | 21375 | +| total_timesteps | 6617088 | +| train/ | | +| approx_kl | 2.2706892 | +| clip_fraction | 0.496 | +| clip_range | 0.2 | +| entropy_loss | -0.396 | +| explained_variance | -2.56 | +| learning_rate | 0.0001 | +| loss | -0.0565 | +| n_updates | 125140 | +| policy_gradient_loss | -0.0669 | +| value_loss | 0.000838 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.33e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 309 | +| iterations | 6463 | +| time_elapsed | 21378 | +| total_timesteps | 6618112 | +| train/ | | +| approx_kl | 1.9444323 | +| clip_fraction | 0.456 | +| clip_range | 0.2 | +| entropy_loss | -0.386 | +| explained_variance | -0.471 | +| learning_rate | 0.0001 | +| loss | -0.0533 | +| n_updates | 125150 | +| policy_gradient_loss | -0.0592 | +| value_loss | 0.00041 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.34e+03 | +| ep_rew_mean | 0.302 | +| time/ | | +| fps | 309 | +| iterations | 6464 | +| time_elapsed | 21381 | +| total_timesteps | 6619136 | +| train/ | | +| approx_kl | 2.0960245 | +| clip_fraction | 0.489 | +| clip_range | 0.2 | +| entropy_loss | -0.359 | +| explained_variance | -1.21 | +| learning_rate | 0.0001 | +| loss | -0.111 | +| n_updates | 125160 | +| policy_gradient_loss | -0.0575 | +| value_loss | 0.000374 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.34e+03 | +| ep_rew_mean | 0.302 | +| time/ | | +| fps | 309 | +| iterations | 6465 | +| time_elapsed | 21384 | +| total_timesteps | 6620160 | +| train/ | | +| approx_kl | 3.4438756 | +| clip_fraction | 0.453 | +| clip_range | 0.2 | +| entropy_loss | -0.318 | +| explained_variance | -0.431 | +| learning_rate | 0.0001 | +| loss | -0.0993 | +| n_updates | 125170 | +| policy_gradient_loss | -0.0587 | +| value_loss | 0.000351 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.34e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 309 | +| iterations | 6466 | +| time_elapsed | 21387 | +| total_timesteps | 6621184 | +| train/ | | +| approx_kl | 3.0811155 | +| clip_fraction | 0.497 | +| clip_range | 0.2 | +| entropy_loss | -0.38 | +| explained_variance | -3.36 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 125180 | +| policy_gradient_loss | -0.0637 | +| value_loss | 0.000267 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.34e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 309 | +| iterations | 6467 | +| time_elapsed | 21390 | +| total_timesteps | 6622208 | +| train/ | | +| approx_kl | 2.2948766 | +| clip_fraction | 0.477 | +| clip_range | 0.2 | +| entropy_loss | -0.31 | +| explained_variance | -0.207 | +| learning_rate | 0.0001 | +| loss | -0.0787 | +| n_updates | 125190 | +| policy_gradient_loss | -0.0545 | +| value_loss | 0.000585 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.34e+03 | +| ep_rew_mean | 0.3 | +| time/ | | +| fps | 309 | +| iterations | 6468 | +| time_elapsed | 21394 | +| total_timesteps | 6623232 | +| train/ | | +| approx_kl | 3.6714785 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.45 | +| explained_variance | -3.23 | +| learning_rate | 0.0001 | +| loss | -0.0918 | +| n_updates | 125200 | +| policy_gradient_loss | -0.0644 | +| value_loss | 0.000505 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.34e+03 | +| ep_rew_mean | 0.3 | +| time/ | | +| fps | 309 | +| iterations | 6469 | +| time_elapsed | 21397 | +| total_timesteps | 6624256 | +| train/ | | +| approx_kl | 4.5176864 | +| clip_fraction | 0.469 | +| clip_range | 0.2 | +| entropy_loss | -0.346 | +| explained_variance | -0.137 | +| learning_rate | 0.0001 | +| loss | -0.0774 | +| n_updates | 125210 | +| policy_gradient_loss | -0.0546 | +| value_loss | 0.000545 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.34e+03 | +| ep_rew_mean | 0.3 | +| time/ | | +| fps | 309 | +| iterations | 6470 | +| time_elapsed | 21400 | +| total_timesteps | 6625280 | +| train/ | | +| approx_kl | 2.215909 | +| clip_fraction | 0.478 | +| clip_range | 0.2 | +| entropy_loss | -0.336 | +| explained_variance | -2.19 | +| learning_rate | 0.0001 | +| loss | -0.0924 | +| n_updates | 125220 | +| policy_gradient_loss | -0.0711 | +| value_loss | 0.000437 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.35e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 309 | +| iterations | 6471 | +| time_elapsed | 21403 | +| total_timesteps | 6626304 | +| train/ | | +| approx_kl | 2.0763385 | +| clip_fraction | 0.505 | +| clip_range | 0.2 | +| entropy_loss | -0.382 | +| explained_variance | -0.783 | +| learning_rate | 0.0001 | +| loss | -0.0657 | +| n_updates | 125230 | +| policy_gradient_loss | -0.0602 | +| value_loss | 0.000387 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.35e+03 | +| ep_rew_mean | 0.295 | +| time/ | | +| fps | 309 | +| iterations | 6472 | +| time_elapsed | 21407 | +| total_timesteps | 6627328 | +| train/ | | +| approx_kl | 2.2913096 | +| clip_fraction | 0.497 | +| clip_range | 0.2 | +| entropy_loss | -0.438 | +| explained_variance | -0.627 | +| learning_rate | 0.0001 | +| loss | -0.0751 | +| n_updates | 125240 | +| policy_gradient_loss | -0.0575 | +| value_loss | 0.000428 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.35e+03 | +| ep_rew_mean | 0.295 | +| time/ | | +| fps | 309 | +| iterations | 6473 | +| time_elapsed | 21410 | +| total_timesteps | 6628352 | +| train/ | | +| approx_kl | 2.1243513 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.351 | +| explained_variance | 0.00357 | +| learning_rate | 0.0001 | +| loss | -0.126 | +| n_updates | 125250 | +| policy_gradient_loss | -0.0648 | +| value_loss | 0.000296 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.35e+03 | +| ep_rew_mean | 0.295 | +| time/ | | +| fps | 309 | +| iterations | 6474 | +| time_elapsed | 21414 | +| total_timesteps | 6629376 | +| train/ | | +| approx_kl | 1.9676735 | +| clip_fraction | 0.5 | +| clip_range | 0.2 | +| entropy_loss | -0.365 | +| explained_variance | -5.18 | +| learning_rate | 0.0001 | +| loss | -0.0998 | +| n_updates | 125260 | +| policy_gradient_loss | -0.0626 | +| value_loss | 0.000269 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.35e+03 | +| ep_rew_mean | 0.295 | +| time/ | | +| fps | 309 | +| iterations | 6475 | +| time_elapsed | 21417 | +| total_timesteps | 6630400 | +| train/ | | +| approx_kl | 2.5811653 | +| clip_fraction | 0.517 | +| clip_range | 0.2 | +| entropy_loss | -0.368 | +| explained_variance | -5.21 | +| learning_rate | 0.0001 | +| loss | -0.0815 | +| n_updates | 125270 | +| policy_gradient_loss | -0.0645 | +| value_loss | 0.000628 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.38e+03 | +| ep_rew_mean | 0.292 | +| time/ | | +| fps | 309 | +| iterations | 6476 | +| time_elapsed | 21420 | +| total_timesteps | 6631424 | +| train/ | | +| approx_kl | 2.1406064 | +| clip_fraction | 0.491 | +| clip_range | 0.2 | +| entropy_loss | -0.368 | +| explained_variance | -0.647 | +| learning_rate | 0.0001 | +| loss | -0.0635 | +| n_updates | 125280 | +| policy_gradient_loss | -0.0631 | +| value_loss | 0.000413 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.38e+03 | +| ep_rew_mean | 0.292 | +| time/ | | +| fps | 309 | +| iterations | 6477 | +| time_elapsed | 21424 | +| total_timesteps | 6632448 | +| train/ | | +| approx_kl | 2.0144215 | +| clip_fraction | 0.443 | +| clip_range | 0.2 | +| entropy_loss | -0.299 | +| explained_variance | -0.57 | +| learning_rate | 0.0001 | +| loss | -0.0739 | +| n_updates | 125290 | +| policy_gradient_loss | -0.0535 | +| value_loss | 0.00068 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.37e+03 | +| ep_rew_mean | 0.294 | +| time/ | | +| fps | 309 | +| iterations | 6478 | +| time_elapsed | 21427 | +| total_timesteps | 6633472 | +| train/ | | +| approx_kl | 2.1577349 | +| clip_fraction | 0.514 | +| clip_range | 0.2 | +| entropy_loss | -0.378 | +| explained_variance | -2.19 | +| learning_rate | 0.0001 | +| loss | -0.0737 | +| n_updates | 125300 | +| policy_gradient_loss | -0.0676 | +| value_loss | 0.000738 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.37e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 309 | +| iterations | 6479 | +| time_elapsed | 21430 | +| total_timesteps | 6634496 | +| train/ | | +| approx_kl | 2.4412544 | +| clip_fraction | 0.466 | +| clip_range | 0.2 | +| entropy_loss | -0.331 | +| explained_variance | -1.12 | +| learning_rate | 0.0001 | +| loss | -0.0768 | +| n_updates | 125310 | +| policy_gradient_loss | -0.0625 | +| value_loss | 0.000605 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.37e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 309 | +| iterations | 6480 | +| time_elapsed | 21433 | +| total_timesteps | 6635520 | +| train/ | | +| approx_kl | 1.7711247 | +| clip_fraction | 0.502 | +| clip_range | 0.2 | +| entropy_loss | -0.431 | +| explained_variance | -0.281 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 125320 | +| policy_gradient_loss | -0.0696 | +| value_loss | 0.000535 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.36e+03 | +| ep_rew_mean | 0.297 | +| time/ | | +| fps | 309 | +| iterations | 6481 | +| time_elapsed | 21437 | +| total_timesteps | 6636544 | +| train/ | | +| approx_kl | 2.215229 | +| clip_fraction | 0.469 | +| clip_range | 0.2 | +| entropy_loss | -0.359 | +| explained_variance | -2.33 | +| learning_rate | 0.0001 | +| loss | -0.0882 | +| n_updates | 125330 | +| policy_gradient_loss | -0.0611 | +| value_loss | 0.000337 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.36e+03 | +| ep_rew_mean | 0.297 | +| time/ | | +| fps | 309 | +| iterations | 6482 | +| time_elapsed | 21440 | +| total_timesteps | 6637568 | +| train/ | | +| approx_kl | 4.1318436 | +| clip_fraction | 0.509 | +| clip_range | 0.2 | +| entropy_loss | -0.384 | +| explained_variance | -0.337 | +| learning_rate | 0.0001 | +| loss | -0.0811 | +| n_updates | 125340 | +| policy_gradient_loss | -0.0621 | +| value_loss | 0.000648 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.37e+03 | +| ep_rew_mean | 0.295 | +| time/ | | +| fps | 309 | +| iterations | 6483 | +| time_elapsed | 21443 | +| total_timesteps | 6638592 | +| train/ | | +| approx_kl | 3.984858 | +| clip_fraction | 0.489 | +| clip_range | 0.2 | +| entropy_loss | -0.396 | +| explained_variance | -6.93 | +| learning_rate | 0.0001 | +| loss | -0.0813 | +| n_updates | 125350 | +| policy_gradient_loss | -0.069 | +| value_loss | 0.000527 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.35e+03 | +| ep_rew_mean | 0.297 | +| time/ | | +| fps | 309 | +| iterations | 6484 | +| time_elapsed | 21446 | +| total_timesteps | 6639616 | +| train/ | | +| approx_kl | 1.9131242 | +| clip_fraction | 0.498 | +| clip_range | 0.2 | +| entropy_loss | -0.413 | +| explained_variance | -0.157 | +| learning_rate | 0.0001 | +| loss | -0.0755 | +| n_updates | 125360 | +| policy_gradient_loss | -0.0573 | +| value_loss | 0.000479 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.35e+03 | +| ep_rew_mean | 0.297 | +| time/ | | +| fps | 309 | +| iterations | 6485 | +| time_elapsed | 21449 | +| total_timesteps | 6640640 | +| train/ | | +| approx_kl | 2.2766957 | +| clip_fraction | 0.488 | +| clip_range | 0.2 | +| entropy_loss | -0.396 | +| explained_variance | -0.204 | +| learning_rate | 0.0001 | +| loss | -0.0833 | +| n_updates | 125370 | +| policy_gradient_loss | -0.0629 | +| value_loss | 0.00066 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.34e+03 | +| ep_rew_mean | 0.295 | +| time/ | | +| fps | 309 | +| iterations | 6486 | +| time_elapsed | 21452 | +| total_timesteps | 6641664 | +| train/ | | +| approx_kl | 2.3876388 | +| clip_fraction | 0.438 | +| clip_range | 0.2 | +| entropy_loss | -0.333 | +| explained_variance | -3.7 | +| learning_rate | 0.0001 | +| loss | -0.0697 | +| n_updates | 125380 | +| policy_gradient_loss | -0.059 | +| value_loss | 0.000474 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.34e+03 | +| ep_rew_mean | 0.295 | +| time/ | | +| fps | 309 | +| iterations | 6487 | +| time_elapsed | 21455 | +| total_timesteps | 6642688 | +| train/ | | +| approx_kl | 2.2705064 | +| clip_fraction | 0.486 | +| clip_range | 0.2 | +| entropy_loss | -0.397 | +| explained_variance | -0.189 | +| learning_rate | 0.0001 | +| loss | -0.0594 | +| n_updates | 125390 | +| policy_gradient_loss | -0.0552 | +| value_loss | 0.000277 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.35e+03 | +| ep_rew_mean | 0.289 | +| time/ | | +| fps | 309 | +| iterations | 6488 | +| time_elapsed | 21459 | +| total_timesteps | 6643712 | +| train/ | | +| approx_kl | 2.5739791 | +| clip_fraction | 0.457 | +| clip_range | 0.2 | +| entropy_loss | -0.316 | +| explained_variance | -3.44 | +| learning_rate | 0.0001 | +| loss | -0.0974 | +| n_updates | 125400 | +| policy_gradient_loss | -0.0653 | +| value_loss | 0.000361 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.34e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 309 | +| iterations | 6489 | +| time_elapsed | 21462 | +| total_timesteps | 6644736 | +| train/ | | +| approx_kl | 3.019288 | +| clip_fraction | 0.444 | +| clip_range | 0.2 | +| entropy_loss | -0.335 | +| explained_variance | -0.494 | +| learning_rate | 0.0001 | +| loss | -0.0518 | +| n_updates | 125410 | +| policy_gradient_loss | -0.0464 | +| value_loss | 0.000378 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.34e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 309 | +| iterations | 6490 | +| time_elapsed | 21466 | +| total_timesteps | 6645760 | +| train/ | | +| approx_kl | 1.9828347 | +| clip_fraction | 0.417 | +| clip_range | 0.2 | +| entropy_loss | -0.298 | +| explained_variance | -0.191 | +| learning_rate | 0.0001 | +| loss | -0.0661 | +| n_updates | 125420 | +| policy_gradient_loss | -0.0566 | +| value_loss | 0.00113 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.34e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 309 | +| iterations | 6491 | +| time_elapsed | 21469 | +| total_timesteps | 6646784 | +| train/ | | +| approx_kl | 4.4097433 | +| clip_fraction | 0.505 | +| clip_range | 0.2 | +| entropy_loss | -0.348 | +| explained_variance | -4.97 | +| learning_rate | 0.0001 | +| loss | -0.0803 | +| n_updates | 125430 | +| policy_gradient_loss | -0.071 | +| value_loss | 0.000777 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.36e+03 | +| ep_rew_mean | 0.292 | +| time/ | | +| fps | 309 | +| iterations | 6492 | +| time_elapsed | 21472 | +| total_timesteps | 6647808 | +| train/ | | +| approx_kl | 2.3493352 | +| clip_fraction | 0.486 | +| clip_range | 0.2 | +| entropy_loss | -0.392 | +| explained_variance | -2.64 | +| learning_rate | 0.0001 | +| loss | -0.108 | +| n_updates | 125440 | +| policy_gradient_loss | -0.0682 | +| value_loss | 0.000611 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.36e+03 | +| ep_rew_mean | 0.292 | +| time/ | | +| fps | 309 | +| iterations | 6493 | +| time_elapsed | 21476 | +| total_timesteps | 6648832 | +| train/ | | +| approx_kl | 2.860903 | +| clip_fraction | 0.451 | +| clip_range | 0.2 | +| entropy_loss | -0.312 | +| explained_variance | -1.29 | +| learning_rate | 0.0001 | +| loss | -0.0604 | +| n_updates | 125450 | +| policy_gradient_loss | -0.0567 | +| value_loss | 0.000447 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.36e+03 | +| ep_rew_mean | 0.288 | +| time/ | | +| fps | 309 | +| iterations | 6494 | +| time_elapsed | 21479 | +| total_timesteps | 6649856 | +| train/ | | +| approx_kl | 2.758038 | +| clip_fraction | 0.492 | +| clip_range | 0.2 | +| entropy_loss | -0.348 | +| explained_variance | -5.68 | +| learning_rate | 0.0001 | +| loss | -0.105 | +| n_updates | 125460 | +| policy_gradient_loss | -0.0656 | +| value_loss | 0.000309 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.36e+03 | +| ep_rew_mean | 0.288 | +| time/ | | +| fps | 309 | +| iterations | 6495 | +| time_elapsed | 21483 | +| total_timesteps | 6650880 | +| train/ | | +| approx_kl | 2.0461864 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.384 | +| explained_variance | -0.458 | +| learning_rate | 0.0001 | +| loss | -0.0708 | +| n_updates | 125470 | +| policy_gradient_loss | -0.053 | +| value_loss | 0.000218 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.36e+03 | +| ep_rew_mean | 0.291 | +| time/ | | +| fps | 309 | +| iterations | 6496 | +| time_elapsed | 21486 | +| total_timesteps | 6651904 | +| train/ | | +| approx_kl | 3.9249206 | +| clip_fraction | 0.515 | +| clip_range | 0.2 | +| entropy_loss | -0.382 | +| explained_variance | -0.487 | +| learning_rate | 0.0001 | +| loss | -0.0839 | +| n_updates | 125480 | +| policy_gradient_loss | -0.0517 | +| value_loss | 0.000325 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.36e+03 | +| ep_rew_mean | 0.291 | +| time/ | | +| fps | 309 | +| iterations | 6497 | +| time_elapsed | 21490 | +| total_timesteps | 6652928 | +| train/ | | +| approx_kl | 2.049823 | +| clip_fraction | 0.47 | +| clip_range | 0.2 | +| entropy_loss | -0.368 | +| explained_variance | -0.449 | +| learning_rate | 0.0001 | +| loss | -0.0962 | +| n_updates | 125490 | +| policy_gradient_loss | -0.0581 | +| value_loss | 0.000544 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.37e+03 | +| ep_rew_mean | 0.295 | +| time/ | | +| fps | 309 | +| iterations | 6498 | +| time_elapsed | 21493 | +| total_timesteps | 6653952 | +| train/ | | +| approx_kl | 3.8946397 | +| clip_fraction | 0.476 | +| clip_range | 0.2 | +| entropy_loss | -0.388 | +| explained_variance | -1.38 | +| learning_rate | 0.0001 | +| loss | -0.113 | +| n_updates | 125500 | +| policy_gradient_loss | -0.0639 | +| value_loss | 0.000706 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.37e+03 | +| ep_rew_mean | 0.295 | +| time/ | | +| fps | 309 | +| iterations | 6499 | +| time_elapsed | 21496 | +| total_timesteps | 6654976 | +| train/ | | +| approx_kl | 2.0929286 | +| clip_fraction | 0.473 | +| clip_range | 0.2 | +| entropy_loss | -0.338 | +| explained_variance | -0.39 | +| learning_rate | 0.0001 | +| loss | -0.0834 | +| n_updates | 125510 | +| policy_gradient_loss | -0.0673 | +| value_loss | 0.00053 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.37e+03 | +| ep_rew_mean | 0.292 | +| time/ | | +| fps | 309 | +| iterations | 6500 | +| time_elapsed | 21499 | +| total_timesteps | 6656000 | +| train/ | | +| approx_kl | 1.961626 | +| clip_fraction | 0.495 | +| clip_range | 0.2 | +| entropy_loss | -0.388 | +| explained_variance | -1.52 | +| learning_rate | 0.0001 | +| loss | -0.0773 | +| n_updates | 125520 | +| policy_gradient_loss | -0.0593 | +| value_loss | 0.000596 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.37e+03 | +| ep_rew_mean | 0.292 | +| time/ | | +| fps | 309 | +| iterations | 6501 | +| time_elapsed | 21502 | +| total_timesteps | 6657024 | +| train/ | | +| approx_kl | 5.2409735 | +| clip_fraction | 0.46 | +| clip_range | 0.2 | +| entropy_loss | -0.341 | +| explained_variance | -1.1 | +| learning_rate | 0.0001 | +| loss | -0.0803 | +| n_updates | 125530 | +| policy_gradient_loss | -0.0594 | +| value_loss | 0.000507 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.36e+03 | +| ep_rew_mean | 0.291 | +| time/ | | +| fps | 309 | +| iterations | 6502 | +| time_elapsed | 21506 | +| total_timesteps | 6658048 | +| train/ | | +| approx_kl | 2.480719 | +| clip_fraction | 0.5 | +| clip_range | 0.2 | +| entropy_loss | -0.389 | +| explained_variance | -4.17 | +| learning_rate | 0.0001 | +| loss | -0.12 | +| n_updates | 125540 | +| policy_gradient_loss | -0.0706 | +| value_loss | 0.000384 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.36e+03 | +| ep_rew_mean | 0.291 | +| time/ | | +| fps | 309 | +| iterations | 6503 | +| time_elapsed | 21509 | +| total_timesteps | 6659072 | +| train/ | | +| approx_kl | 2.1327877 | +| clip_fraction | 0.529 | +| clip_range | 0.2 | +| entropy_loss | -0.48 | +| explained_variance | -0.455 | +| learning_rate | 0.0001 | +| loss | -0.0803 | +| n_updates | 125550 | +| policy_gradient_loss | -0.0603 | +| value_loss | 0.000609 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.36e+03 | +| ep_rew_mean | 0.291 | +| time/ | | +| fps | 309 | +| iterations | 6504 | +| time_elapsed | 21512 | +| total_timesteps | 6660096 | +| train/ | | +| approx_kl | 2.4957585 | +| clip_fraction | 0.486 | +| clip_range | 0.2 | +| entropy_loss | -0.351 | +| explained_variance | -2.79 | +| learning_rate | 0.0001 | +| loss | -0.0828 | +| n_updates | 125560 | +| policy_gradient_loss | -0.0643 | +| value_loss | 0.000477 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.37e+03 | +| ep_rew_mean | 0.292 | +| time/ | | +| fps | 309 | +| iterations | 6505 | +| time_elapsed | 21515 | +| total_timesteps | 6661120 | +| train/ | | +| approx_kl | 2.4916954 | +| clip_fraction | 0.488 | +| clip_range | 0.2 | +| entropy_loss | -0.348 | +| explained_variance | -2.91 | +| learning_rate | 0.0001 | +| loss | -0.0973 | +| n_updates | 125570 | +| policy_gradient_loss | -0.0631 | +| value_loss | 0.000343 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.37e+03 | +| ep_rew_mean | 0.292 | +| time/ | | +| fps | 309 | +| iterations | 6506 | +| time_elapsed | 21518 | +| total_timesteps | 6662144 | +| train/ | | +| approx_kl | 1.9557737 | +| clip_fraction | 0.494 | +| clip_range | 0.2 | +| entropy_loss | -0.414 | +| explained_variance | -0.845 | +| learning_rate | 0.0001 | +| loss | -0.0645 | +| n_updates | 125580 | +| policy_gradient_loss | -0.0524 | +| value_loss | 0.000475 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.37e+03 | +| ep_rew_mean | 0.29 | +| time/ | | +| fps | 309 | +| iterations | 6507 | +| time_elapsed | 21522 | +| total_timesteps | 6663168 | +| train/ | | +| approx_kl | 2.7682261 | +| clip_fraction | 0.495 | +| clip_range | 0.2 | +| entropy_loss | -0.411 | +| explained_variance | -6.7 | +| learning_rate | 0.0001 | +| loss | -0.114 | +| n_updates | 125590 | +| policy_gradient_loss | -0.0719 | +| value_loss | 0.000508 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.37e+03 | +| ep_rew_mean | 0.29 | +| time/ | | +| fps | 309 | +| iterations | 6508 | +| time_elapsed | 21525 | +| total_timesteps | 6664192 | +| train/ | | +| approx_kl | 3.0091128 | +| clip_fraction | 0.5 | +| clip_range | 0.2 | +| entropy_loss | -0.38 | +| explained_variance | -1.14 | +| learning_rate | 0.0001 | +| loss | -0.0529 | +| n_updates | 125600 | +| policy_gradient_loss | -0.0549 | +| value_loss | 0.000348 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.37e+03 | +| ep_rew_mean | 0.29 | +| time/ | | +| fps | 309 | +| iterations | 6509 | +| time_elapsed | 21529 | +| total_timesteps | 6665216 | +| train/ | | +| approx_kl | 3.9995458 | +| clip_fraction | 0.514 | +| clip_range | 0.2 | +| entropy_loss | -0.365 | +| explained_variance | -4.74 | +| learning_rate | 0.0001 | +| loss | -0.0695 | +| n_updates | 125610 | +| policy_gradient_loss | -0.0628 | +| value_loss | 0.000375 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.38e+03 | +| ep_rew_mean | 0.291 | +| time/ | | +| fps | 309 | +| iterations | 6510 | +| time_elapsed | 21533 | +| total_timesteps | 6666240 | +| train/ | | +| approx_kl | 2.6813245 | +| clip_fraction | 0.493 | +| clip_range | 0.2 | +| entropy_loss | -0.352 | +| explained_variance | -8.8 | +| learning_rate | 0.0001 | +| loss | -0.0987 | +| n_updates | 125620 | +| policy_gradient_loss | -0.0597 | +| value_loss | 0.000362 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.38e+03 | +| ep_rew_mean | 0.291 | +| time/ | | +| fps | 309 | +| iterations | 6511 | +| time_elapsed | 21536 | +| total_timesteps | 6667264 | +| train/ | | +| approx_kl | 2.2174077 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.35 | +| explained_variance | -0.171 | +| learning_rate | 0.0001 | +| loss | -0.0702 | +| n_updates | 125630 | +| policy_gradient_loss | -0.0604 | +| value_loss | 0.000629 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.38e+03 | +| ep_rew_mean | 0.291 | +| time/ | | +| fps | 309 | +| iterations | 6512 | +| time_elapsed | 21540 | +| total_timesteps | 6668288 | +| train/ | | +| approx_kl | 2.429805 | +| clip_fraction | 0.504 | +| clip_range | 0.2 | +| entropy_loss | -0.418 | +| explained_variance | -3.52 | +| learning_rate | 0.0001 | +| loss | -0.0967 | +| n_updates | 125640 | +| policy_gradient_loss | -0.0598 | +| value_loss | 0.000895 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.39e+03 | +| ep_rew_mean | 0.294 | +| time/ | | +| fps | 309 | +| iterations | 6513 | +| time_elapsed | 21543 | +| total_timesteps | 6669312 | +| train/ | | +| approx_kl | 2.156342 | +| clip_fraction | 0.542 | +| clip_range | 0.2 | +| entropy_loss | -0.473 | +| explained_variance | -2 | +| learning_rate | 0.0001 | +| loss | -0.111 | +| n_updates | 125650 | +| policy_gradient_loss | -0.0704 | +| value_loss | 0.000387 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.39e+03 | +| ep_rew_mean | 0.294 | +| time/ | | +| fps | 309 | +| iterations | 6514 | +| time_elapsed | 21547 | +| total_timesteps | 6670336 | +| train/ | | +| approx_kl | 2.101967 | +| clip_fraction | 0.515 | +| clip_range | 0.2 | +| entropy_loss | -0.414 | +| explained_variance | -0.692 | +| learning_rate | 0.0001 | +| loss | -0.0924 | +| n_updates | 125660 | +| policy_gradient_loss | -0.0613 | +| value_loss | 0.000378 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.39e+03 | +| ep_rew_mean | 0.295 | +| time/ | | +| fps | 309 | +| iterations | 6515 | +| time_elapsed | 21550 | +| total_timesteps | 6671360 | +| train/ | | +| approx_kl | 4.2275085 | +| clip_fraction | 0.504 | +| clip_range | 0.2 | +| entropy_loss | -0.415 | +| explained_variance | -1.04 | +| learning_rate | 0.0001 | +| loss | -0.0941 | +| n_updates | 125670 | +| policy_gradient_loss | -0.0646 | +| value_loss | 0.000477 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.39e+03 | +| ep_rew_mean | 0.295 | +| time/ | | +| fps | 309 | +| iterations | 6516 | +| time_elapsed | 21553 | +| total_timesteps | 6672384 | +| train/ | | +| approx_kl | 2.8274002 | +| clip_fraction | 0.486 | +| clip_range | 0.2 | +| entropy_loss | -0.364 | +| explained_variance | -1.3 | +| learning_rate | 0.0001 | +| loss | -0.0321 | +| n_updates | 125680 | +| policy_gradient_loss | -0.0393 | +| value_loss | 0.00043 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.39e+03 | +| ep_rew_mean | 0.289 | +| time/ | | +| fps | 309 | +| iterations | 6517 | +| time_elapsed | 21556 | +| total_timesteps | 6673408 | +| train/ | | +| approx_kl | 2.3150997 | +| clip_fraction | 0.484 | +| clip_range | 0.2 | +| entropy_loss | -0.423 | +| explained_variance | -4.69 | +| learning_rate | 0.0001 | +| loss | -0.0962 | +| n_updates | 125690 | +| policy_gradient_loss | -0.0634 | +| value_loss | 0.000153 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.39e+03 | +| ep_rew_mean | 0.289 | +| time/ | | +| fps | 309 | +| iterations | 6518 | +| time_elapsed | 21559 | +| total_timesteps | 6674432 | +| train/ | | +| approx_kl | 2.9601903 | +| clip_fraction | 0.492 | +| clip_range | 0.2 | +| entropy_loss | -0.371 | +| explained_variance | -0.308 | +| learning_rate | 0.0001 | +| loss | -0.0574 | +| n_updates | 125700 | +| policy_gradient_loss | -0.0425 | +| value_loss | 0.000254 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.39e+03 | +| ep_rew_mean | 0.289 | +| time/ | | +| fps | 309 | +| iterations | 6519 | +| time_elapsed | 21563 | +| total_timesteps | 6675456 | +| train/ | | +| approx_kl | 1.8597981 | +| clip_fraction | 0.507 | +| clip_range | 0.2 | +| entropy_loss | -0.472 | +| explained_variance | -5.02 | +| learning_rate | 0.0001 | +| loss | -0.0651 | +| n_updates | 125710 | +| policy_gradient_loss | -0.0712 | +| value_loss | 0.000114 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.39e+03 | +| ep_rew_mean | 0.289 | +| time/ | | +| fps | 309 | +| iterations | 6520 | +| time_elapsed | 21566 | +| total_timesteps | 6676480 | +| train/ | | +| approx_kl | 4.090171 | +| clip_fraction | 0.508 | +| clip_range | 0.2 | +| entropy_loss | -0.498 | +| explained_variance | -0.618 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 125720 | +| policy_gradient_loss | -0.075 | +| value_loss | 0.000253 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.39e+03 | +| ep_rew_mean | 0.289 | +| time/ | | +| fps | 309 | +| iterations | 6521 | +| time_elapsed | 21569 | +| total_timesteps | 6677504 | +| train/ | | +| approx_kl | 2.458288 | +| clip_fraction | 0.45 | +| clip_range | 0.2 | +| entropy_loss | -0.308 | +| explained_variance | -1.25 | +| learning_rate | 0.0001 | +| loss | -0.0787 | +| n_updates | 125730 | +| policy_gradient_loss | -0.0571 | +| value_loss | 0.000557 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.38e+03 | +| ep_rew_mean | 0.29 | +| time/ | | +| fps | 309 | +| iterations | 6522 | +| time_elapsed | 21572 | +| total_timesteps | 6678528 | +| train/ | | +| approx_kl | 1.9563398 | +| clip_fraction | 0.514 | +| clip_range | 0.2 | +| entropy_loss | -0.451 | +| explained_variance | -1.03 | +| learning_rate | 0.0001 | +| loss | -0.0696 | +| n_updates | 125740 | +| policy_gradient_loss | -0.0653 | +| value_loss | 0.000289 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.38e+03 | +| ep_rew_mean | 0.29 | +| time/ | | +| fps | 309 | +| iterations | 6523 | +| time_elapsed | 21575 | +| total_timesteps | 6679552 | +| train/ | | +| approx_kl | 1.6297725 | +| clip_fraction | 0.497 | +| clip_range | 0.2 | +| entropy_loss | -0.476 | +| explained_variance | -0.178 | +| learning_rate | 0.0001 | +| loss | -0.0436 | +| n_updates | 125750 | +| policy_gradient_loss | -0.055 | +| value_loss | 0.000288 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.37e+03 | +| ep_rew_mean | 0.287 | +| time/ | | +| fps | 309 | +| iterations | 6524 | +| time_elapsed | 21578 | +| total_timesteps | 6680576 | +| train/ | | +| approx_kl | 2.200289 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.38 | +| explained_variance | -2.64 | +| learning_rate | 0.0001 | +| loss | -0.0912 | +| n_updates | 125760 | +| policy_gradient_loss | -0.0707 | +| value_loss | 0.000681 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.37e+03 | +| ep_rew_mean | 0.287 | +| time/ | | +| fps | 309 | +| iterations | 6525 | +| time_elapsed | 21582 | +| total_timesteps | 6681600 | +| train/ | | +| approx_kl | 2.389875 | +| clip_fraction | 0.482 | +| clip_range | 0.2 | +| entropy_loss | -0.353 | +| explained_variance | -0.428 | +| learning_rate | 0.0001 | +| loss | -0.0599 | +| n_updates | 125770 | +| policy_gradient_loss | -0.0646 | +| value_loss | 0.000708 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.37e+03 | +| ep_rew_mean | 0.285 | +| time/ | | +| fps | 309 | +| iterations | 6526 | +| time_elapsed | 21585 | +| total_timesteps | 6682624 | +| train/ | | +| approx_kl | 2.3445702 | +| clip_fraction | 0.477 | +| clip_range | 0.2 | +| entropy_loss | -0.324 | +| explained_variance | -5.47 | +| learning_rate | 0.0001 | +| loss | -0.0744 | +| n_updates | 125780 | +| policy_gradient_loss | -0.0549 | +| value_loss | 0.000501 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.35e+03 | +| ep_rew_mean | 0.288 | +| time/ | | +| fps | 309 | +| iterations | 6527 | +| time_elapsed | 21589 | +| total_timesteps | 6683648 | +| train/ | | +| approx_kl | 2.2865157 | +| clip_fraction | 0.476 | +| clip_range | 0.2 | +| entropy_loss | -0.34 | +| explained_variance | -0.349 | +| learning_rate | 0.0001 | +| loss | -0.0515 | +| n_updates | 125790 | +| policy_gradient_loss | -0.0622 | +| value_loss | 0.000568 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.35e+03 | +| ep_rew_mean | 0.288 | +| time/ | | +| fps | 309 | +| iterations | 6528 | +| time_elapsed | 21592 | +| total_timesteps | 6684672 | +| train/ | | +| approx_kl | 2.3909078 | +| clip_fraction | 0.467 | +| clip_range | 0.2 | +| entropy_loss | -0.381 | +| explained_variance | -0.0273 | +| learning_rate | 0.0001 | +| loss | -0.0885 | +| n_updates | 125800 | +| policy_gradient_loss | -0.0606 | +| value_loss | 0.000834 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.35e+03 | +| ep_rew_mean | 0.288 | +| time/ | | +| fps | 309 | +| iterations | 6529 | +| time_elapsed | 21596 | +| total_timesteps | 6685696 | +| train/ | | +| approx_kl | 1.7424018 | +| clip_fraction | 0.502 | +| clip_range | 0.2 | +| entropy_loss | -0.421 | +| explained_variance | -1.39 | +| learning_rate | 0.0001 | +| loss | -0.119 | +| n_updates | 125810 | +| policy_gradient_loss | -0.0685 | +| value_loss | 0.000657 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.36e+03 | +| ep_rew_mean | 0.287 | +| time/ | | +| fps | 309 | +| iterations | 6530 | +| time_elapsed | 21599 | +| total_timesteps | 6686720 | +| train/ | | +| approx_kl | 2.5016174 | +| clip_fraction | 0.518 | +| clip_range | 0.2 | +| entropy_loss | -0.472 | +| explained_variance | -1.03 | +| learning_rate | 0.0001 | +| loss | -0.0833 | +| n_updates | 125820 | +| policy_gradient_loss | -0.0746 | +| value_loss | 0.000369 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.36e+03 | +| ep_rew_mean | 0.287 | +| time/ | | +| fps | 309 | +| iterations | 6531 | +| time_elapsed | 21603 | +| total_timesteps | 6687744 | +| train/ | | +| approx_kl | 1.6620605 | +| clip_fraction | 0.534 | +| clip_range | 0.2 | +| entropy_loss | -0.519 | +| explained_variance | -0.377 | +| learning_rate | 0.0001 | +| loss | -0.0826 | +| n_updates | 125830 | +| policy_gradient_loss | -0.0531 | +| value_loss | 0.000225 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.35e+03 | +| ep_rew_mean | 0.288 | +| time/ | | +| fps | 309 | +| iterations | 6532 | +| time_elapsed | 21606 | +| total_timesteps | 6688768 | +| train/ | | +| approx_kl | 2.7733214 | +| clip_fraction | 0.496 | +| clip_range | 0.2 | +| entropy_loss | -0.396 | +| explained_variance | -1 | +| learning_rate | 0.0001 | +| loss | -0.0855 | +| n_updates | 125840 | +| policy_gradient_loss | -0.0566 | +| value_loss | 0.00031 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.35e+03 | +| ep_rew_mean | 0.288 | +| time/ | | +| fps | 309 | +| iterations | 6533 | +| time_elapsed | 21609 | +| total_timesteps | 6689792 | +| train/ | | +| approx_kl | 2.5477757 | +| clip_fraction | 0.493 | +| clip_range | 0.2 | +| entropy_loss | -0.367 | +| explained_variance | -1.43 | +| learning_rate | 0.0001 | +| loss | -0.0709 | +| n_updates | 125850 | +| policy_gradient_loss | -0.0618 | +| value_loss | 0.000721 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.34e+03 | +| ep_rew_mean | 0.29 | +| time/ | | +| fps | 309 | +| iterations | 6534 | +| time_elapsed | 21613 | +| total_timesteps | 6690816 | +| train/ | | +| approx_kl | 2.6596437 | +| clip_fraction | 0.497 | +| clip_range | 0.2 | +| entropy_loss | -0.347 | +| explained_variance | -2.84 | +| learning_rate | 0.0001 | +| loss | -0.0945 | +| n_updates | 125860 | +| policy_gradient_loss | -0.0652 | +| value_loss | 0.000835 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.34e+03 | +| ep_rew_mean | 0.29 | +| time/ | | +| fps | 309 | +| iterations | 6535 | +| time_elapsed | 21616 | +| total_timesteps | 6691840 | +| train/ | | +| approx_kl | 1.9163872 | +| clip_fraction | 0.511 | +| clip_range | 0.2 | +| entropy_loss | -0.493 | +| explained_variance | -1 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 125870 | +| policy_gradient_loss | -0.065 | +| value_loss | 0.000601 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.34e+03 | +| ep_rew_mean | 0.29 | +| time/ | | +| fps | 309 | +| iterations | 6536 | +| time_elapsed | 21619 | +| total_timesteps | 6692864 | +| train/ | | +| approx_kl | 1.9784886 | +| clip_fraction | 0.529 | +| clip_range | 0.2 | +| entropy_loss | -0.468 | +| explained_variance | -4.46 | +| learning_rate | 0.0001 | +| loss | -0.12 | +| n_updates | 125880 | +| policy_gradient_loss | -0.0777 | +| value_loss | 0.000203 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.34e+03 | +| ep_rew_mean | 0.29 | +| time/ | | +| fps | 309 | +| iterations | 6537 | +| time_elapsed | 21622 | +| total_timesteps | 6693888 | +| train/ | | +| approx_kl | 2.0085092 | +| clip_fraction | 0.493 | +| clip_range | 0.2 | +| entropy_loss | -0.401 | +| explained_variance | -4.99 | +| learning_rate | 0.0001 | +| loss | -0.106 | +| n_updates | 125890 | +| policy_gradient_loss | -0.0717 | +| value_loss | 0.000187 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.34e+03 | +| ep_rew_mean | 0.29 | +| time/ | | +| fps | 309 | +| iterations | 6538 | +| time_elapsed | 21625 | +| total_timesteps | 6694912 | +| train/ | | +| approx_kl | 2.1936991 | +| clip_fraction | 0.518 | +| clip_range | 0.2 | +| entropy_loss | -0.394 | +| explained_variance | -1.99 | +| learning_rate | 0.0001 | +| loss | -0.0959 | +| n_updates | 125900 | +| policy_gradient_loss | -0.0645 | +| value_loss | 0.000511 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.34e+03 | +| ep_rew_mean | 0.29 | +| time/ | | +| fps | 309 | +| iterations | 6539 | +| time_elapsed | 21629 | +| total_timesteps | 6695936 | +| train/ | | +| approx_kl | 1.187234 | +| clip_fraction | 0.426 | +| clip_range | 0.2 | +| entropy_loss | -0.571 | +| explained_variance | -0.0966 | +| learning_rate | 0.0001 | +| loss | -0.0566 | +| n_updates | 125910 | +| policy_gradient_loss | -0.0346 | +| value_loss | 0.000918 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.34e+03 | +| ep_rew_mean | 0.29 | +| time/ | | +| fps | 309 | +| iterations | 6540 | +| time_elapsed | 21632 | +| total_timesteps | 6696960 | +| train/ | | +| approx_kl | 1.7959306 | +| clip_fraction | 0.519 | +| clip_range | 0.2 | +| entropy_loss | -0.534 | +| explained_variance | -5.09 | +| learning_rate | 0.0001 | +| loss | -0.1 | +| n_updates | 125920 | +| policy_gradient_loss | -0.0731 | +| value_loss | 0.00083 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.39e+03 | +| ep_rew_mean | 0.292 | +| time/ | | +| fps | 309 | +| iterations | 6541 | +| time_elapsed | 21635 | +| total_timesteps | 6697984 | +| train/ | | +| approx_kl | 2.5488663 | +| clip_fraction | 0.538 | +| clip_range | 0.2 | +| entropy_loss | -0.403 | +| explained_variance | -3.48 | +| learning_rate | 0.0001 | +| loss | -0.0928 | +| n_updates | 125930 | +| policy_gradient_loss | -0.0783 | +| value_loss | 0.000391 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.39e+03 | +| ep_rew_mean | 0.292 | +| time/ | | +| fps | 309 | +| iterations | 6542 | +| time_elapsed | 21638 | +| total_timesteps | 6699008 | +| train/ | | +| approx_kl | 2.5263531 | +| clip_fraction | 0.525 | +| clip_range | 0.2 | +| entropy_loss | -0.403 | +| explained_variance | -0.785 | +| learning_rate | 0.0001 | +| loss | -0.0416 | +| n_updates | 125940 | +| policy_gradient_loss | -0.0572 | +| value_loss | 0.000301 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.39e+03 | +| ep_rew_mean | 0.292 | +| time/ | | +| fps | 309 | +| iterations | 6543 | +| time_elapsed | 21642 | +| total_timesteps | 6700032 | +| train/ | | +| approx_kl | 1.8780346 | +| clip_fraction | 0.544 | +| clip_range | 0.2 | +| entropy_loss | -0.549 | +| explained_variance | -1.87 | +| learning_rate | 0.0001 | +| loss | -0.067 | +| n_updates | 125950 | +| policy_gradient_loss | -0.068 | +| value_loss | 0.000556 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.39e+03 | +| ep_rew_mean | 0.294 | +| time/ | | +| fps | 309 | +| iterations | 6544 | +| time_elapsed | 21645 | +| total_timesteps | 6701056 | +| train/ | | +| approx_kl | 2.0264378 | +| clip_fraction | 0.543 | +| clip_range | 0.2 | +| entropy_loss | -0.573 | +| explained_variance | -1.5 | +| learning_rate | 0.0001 | +| loss | -0.0865 | +| n_updates | 125960 | +| policy_gradient_loss | -0.0711 | +| value_loss | 0.000373 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.39e+03 | +| ep_rew_mean | 0.294 | +| time/ | | +| fps | 309 | +| iterations | 6545 | +| time_elapsed | 21648 | +| total_timesteps | 6702080 | +| train/ | | +| approx_kl | 1.9612889 | +| clip_fraction | 0.488 | +| clip_range | 0.2 | +| entropy_loss | -0.436 | +| explained_variance | -0.74 | +| learning_rate | 0.0001 | +| loss | -0.0398 | +| n_updates | 125970 | +| policy_gradient_loss | -0.0533 | +| value_loss | 0.000326 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.39e+03 | +| ep_rew_mean | 0.292 | +| time/ | | +| fps | 309 | +| iterations | 6546 | +| time_elapsed | 21652 | +| total_timesteps | 6703104 | +| train/ | | +| approx_kl | 2.1030724 | +| clip_fraction | 0.517 | +| clip_range | 0.2 | +| entropy_loss | -0.396 | +| explained_variance | -0.906 | +| learning_rate | 0.0001 | +| loss | -0.0783 | +| n_updates | 125980 | +| policy_gradient_loss | -0.0692 | +| value_loss | 0.000322 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.39e+03 | +| ep_rew_mean | 0.292 | +| time/ | | +| fps | 309 | +| iterations | 6547 | +| time_elapsed | 21655 | +| total_timesteps | 6704128 | +| train/ | | +| approx_kl | 2.6213996 | +| clip_fraction | 0.455 | +| clip_range | 0.2 | +| entropy_loss | -0.391 | +| explained_variance | -0.618 | +| learning_rate | 0.0001 | +| loss | -0.0584 | +| n_updates | 125990 | +| policy_gradient_loss | -0.0571 | +| value_loss | 0.000476 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.39e+03 | +| ep_rew_mean | 0.292 | +| time/ | | +| fps | 309 | +| iterations | 6548 | +| time_elapsed | 21658 | +| total_timesteps | 6705152 | +| train/ | | +| approx_kl | 2.3612912 | +| clip_fraction | 0.507 | +| clip_range | 0.2 | +| entropy_loss | -0.41 | +| explained_variance | -1.49 | +| learning_rate | 0.0001 | +| loss | -0.0794 | +| n_updates | 126000 | +| policy_gradient_loss | -0.0658 | +| value_loss | 0.000368 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.41e+03 | +| ep_rew_mean | 0.291 | +| time/ | | +| fps | 309 | +| iterations | 6549 | +| time_elapsed | 21662 | +| total_timesteps | 6706176 | +| train/ | | +| approx_kl | 2.5213933 | +| clip_fraction | 0.52 | +| clip_range | 0.2 | +| entropy_loss | -0.448 | +| explained_variance | -1.81 | +| learning_rate | 0.0001 | +| loss | -0.0649 | +| n_updates | 126010 | +| policy_gradient_loss | -0.0729 | +| value_loss | 0.000347 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.41e+03 | +| ep_rew_mean | 0.291 | +| time/ | | +| fps | 309 | +| iterations | 6550 | +| time_elapsed | 21665 | +| total_timesteps | 6707200 | +| train/ | | +| approx_kl | 2.7501454 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.377 | +| explained_variance | -0.764 | +| learning_rate | 0.0001 | +| loss | -0.0694 | +| n_updates | 126020 | +| policy_gradient_loss | -0.0487 | +| value_loss | 0.000216 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.41e+03 | +| ep_rew_mean | 0.295 | +| time/ | | +| fps | 309 | +| iterations | 6551 | +| time_elapsed | 21668 | +| total_timesteps | 6708224 | +| train/ | | +| approx_kl | 2.0024128 | +| clip_fraction | 0.491 | +| clip_range | 0.2 | +| entropy_loss | -0.406 | +| explained_variance | -1.8 | +| learning_rate | 0.0001 | +| loss | -0.0872 | +| n_updates | 126030 | +| policy_gradient_loss | -0.0671 | +| value_loss | 0.000447 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.41e+03 | +| ep_rew_mean | 0.295 | +| time/ | | +| fps | 309 | +| iterations | 6552 | +| time_elapsed | 21671 | +| total_timesteps | 6709248 | +| train/ | | +| approx_kl | 2.6695156 | +| clip_fraction | 0.522 | +| clip_range | 0.2 | +| entropy_loss | -0.444 | +| explained_variance | -0.651 | +| learning_rate | 0.0001 | +| loss | -0.0931 | +| n_updates | 126040 | +| policy_gradient_loss | -0.0655 | +| value_loss | 0.000733 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.41e+03 | +| ep_rew_mean | 0.295 | +| time/ | | +| fps | 309 | +| iterations | 6553 | +| time_elapsed | 21675 | +| total_timesteps | 6710272 | +| train/ | | +| approx_kl | 1.8534943 | +| clip_fraction | 0.513 | +| clip_range | 0.2 | +| entropy_loss | -0.419 | +| explained_variance | -1.88 | +| learning_rate | 0.0001 | +| loss | -0.105 | +| n_updates | 126050 | +| policy_gradient_loss | -0.0663 | +| value_loss | 0.00039 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.41e+03 | +| ep_rew_mean | 0.295 | +| time/ | | +| fps | 309 | +| iterations | 6554 | +| time_elapsed | 21678 | +| total_timesteps | 6711296 | +| train/ | | +| approx_kl | 2.587906 | +| clip_fraction | 0.515 | +| clip_range | 0.2 | +| entropy_loss | -0.381 | +| explained_variance | -1.72 | +| learning_rate | 0.0001 | +| loss | -0.0927 | +| n_updates | 126060 | +| policy_gradient_loss | -0.0745 | +| value_loss | 0.000288 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.43e+03 | +| ep_rew_mean | 0.293 | +| time/ | | +| fps | 309 | +| iterations | 6555 | +| time_elapsed | 21681 | +| total_timesteps | 6712320 | +| train/ | | +| approx_kl | 2.0399027 | +| clip_fraction | 0.506 | +| clip_range | 0.2 | +| entropy_loss | -0.363 | +| explained_variance | -1.11 | +| learning_rate | 0.0001 | +| loss | -0.0563 | +| n_updates | 126070 | +| policy_gradient_loss | -0.0712 | +| value_loss | 0.000532 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.43e+03 | +| ep_rew_mean | 0.293 | +| time/ | | +| fps | 309 | +| iterations | 6556 | +| time_elapsed | 21684 | +| total_timesteps | 6713344 | +| train/ | | +| approx_kl | 1.9662771 | +| clip_fraction | 0.508 | +| clip_range | 0.2 | +| entropy_loss | -0.393 | +| explained_variance | -2.21 | +| learning_rate | 0.0001 | +| loss | -0.0641 | +| n_updates | 126080 | +| policy_gradient_loss | -0.0576 | +| value_loss | 0.000479 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.43e+03 | +| ep_rew_mean | 0.293 | +| time/ | | +| fps | 309 | +| iterations | 6557 | +| time_elapsed | 21687 | +| total_timesteps | 6714368 | +| train/ | | +| approx_kl | 2.9315438 | +| clip_fraction | 0.516 | +| clip_range | 0.2 | +| entropy_loss | -0.421 | +| explained_variance | -1.03 | +| learning_rate | 0.0001 | +| loss | -0.0874 | +| n_updates | 126090 | +| policy_gradient_loss | -0.0692 | +| value_loss | 0.000312 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.44e+03 | +| ep_rew_mean | 0.293 | +| time/ | | +| fps | 309 | +| iterations | 6558 | +| time_elapsed | 21690 | +| total_timesteps | 6715392 | +| train/ | | +| approx_kl | 2.4074883 | +| clip_fraction | 0.519 | +| clip_range | 0.2 | +| entropy_loss | -0.426 | +| explained_variance | -2.01 | +| learning_rate | 0.0001 | +| loss | -0.0667 | +| n_updates | 126100 | +| policy_gradient_loss | -0.0678 | +| value_loss | 0.000255 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.44e+03 | +| ep_rew_mean | 0.293 | +| time/ | | +| fps | 309 | +| iterations | 6559 | +| time_elapsed | 21693 | +| total_timesteps | 6716416 | +| train/ | | +| approx_kl | 3.072892 | +| clip_fraction | 0.476 | +| clip_range | 0.2 | +| entropy_loss | -0.41 | +| explained_variance | -0.291 | +| learning_rate | 0.0001 | +| loss | -0.0812 | +| n_updates | 126110 | +| policy_gradient_loss | -0.0516 | +| value_loss | 0.000356 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.43e+03 | +| ep_rew_mean | 0.294 | +| time/ | | +| fps | 309 | +| iterations | 6560 | +| time_elapsed | 21697 | +| total_timesteps | 6717440 | +| train/ | | +| approx_kl | 2.6151285 | +| clip_fraction | 0.523 | +| clip_range | 0.2 | +| entropy_loss | -0.432 | +| explained_variance | -2.04 | +| learning_rate | 0.0001 | +| loss | -0.0828 | +| n_updates | 126120 | +| policy_gradient_loss | -0.0653 | +| value_loss | 0.000499 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.43e+03 | +| ep_rew_mean | 0.294 | +| time/ | | +| fps | 309 | +| iterations | 6561 | +| time_elapsed | 21700 | +| total_timesteps | 6718464 | +| train/ | | +| approx_kl | 2.0716774 | +| clip_fraction | 0.489 | +| clip_range | 0.2 | +| entropy_loss | -0.415 | +| explained_variance | -0.416 | +| learning_rate | 0.0001 | +| loss | -0.0716 | +| n_updates | 126130 | +| policy_gradient_loss | -0.0562 | +| value_loss | 0.000621 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.42e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 309 | +| iterations | 6562 | +| time_elapsed | 21703 | +| total_timesteps | 6719488 | +| train/ | | +| approx_kl | 2.9172196 | +| clip_fraction | 0.5 | +| clip_range | 0.2 | +| entropy_loss | -0.374 | +| explained_variance | -3.15 | +| learning_rate | 0.0001 | +| loss | -0.105 | +| n_updates | 126140 | +| policy_gradient_loss | -0.0724 | +| value_loss | 0.000311 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.42e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 309 | +| iterations | 6563 | +| time_elapsed | 21707 | +| total_timesteps | 6720512 | +| train/ | | +| approx_kl | 2.0878196 | +| clip_fraction | 0.558 | +| clip_range | 0.2 | +| entropy_loss | -0.544 | +| explained_variance | -0.393 | +| learning_rate | 0.0001 | +| loss | -0.108 | +| n_updates | 126150 | +| policy_gradient_loss | -0.0724 | +| value_loss | 0.000245 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.42e+03 | +| ep_rew_mean | 0.297 | +| time/ | | +| fps | 309 | +| iterations | 6564 | +| time_elapsed | 21710 | +| total_timesteps | 6721536 | +| train/ | | +| approx_kl | 2.5309014 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.373 | +| explained_variance | -1.78 | +| learning_rate | 0.0001 | +| loss | -0.0811 | +| n_updates | 126160 | +| policy_gradient_loss | -0.0515 | +| value_loss | 0.000637 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.4e+03 | +| ep_rew_mean | 0.302 | +| time/ | | +| fps | 309 | +| iterations | 6565 | +| time_elapsed | 21714 | +| total_timesteps | 6722560 | +| train/ | | +| approx_kl | 1.9322584 | +| clip_fraction | 0.507 | +| clip_range | 0.2 | +| entropy_loss | -0.435 | +| explained_variance | -0.16 | +| learning_rate | 0.0001 | +| loss | -0.0562 | +| n_updates | 126170 | +| policy_gradient_loss | -0.0689 | +| value_loss | 0.001 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.4e+03 | +| ep_rew_mean | 0.302 | +| time/ | | +| fps | 309 | +| iterations | 6566 | +| time_elapsed | 21717 | +| total_timesteps | 6723584 | +| train/ | | +| approx_kl | 3.032989 | +| clip_fraction | 0.477 | +| clip_range | 0.2 | +| entropy_loss | -0.406 | +| explained_variance | -0.412 | +| learning_rate | 0.0001 | +| loss | -0.0716 | +| n_updates | 126180 | +| policy_gradient_loss | -0.065 | +| value_loss | 0.000827 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.34e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 309 | +| iterations | 6567 | +| time_elapsed | 21721 | +| total_timesteps | 6724608 | +| train/ | | +| approx_kl | 2.4451766 | +| clip_fraction | 0.531 | +| clip_range | 0.2 | +| entropy_loss | -0.515 | +| explained_variance | -4.18 | +| learning_rate | 0.0001 | +| loss | -0.093 | +| n_updates | 126190 | +| policy_gradient_loss | -0.0743 | +| value_loss | 0.000415 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.34e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 309 | +| iterations | 6568 | +| time_elapsed | 21724 | +| total_timesteps | 6725632 | +| train/ | | +| approx_kl | 2.3420167 | +| clip_fraction | 0.509 | +| clip_range | 0.2 | +| entropy_loss | -0.406 | +| explained_variance | -0.223 | +| learning_rate | 0.0001 | +| loss | -0.0906 | +| n_updates | 126200 | +| policy_gradient_loss | -0.0596 | +| value_loss | 0.00045 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.36e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 309 | +| iterations | 6569 | +| time_elapsed | 21728 | +| total_timesteps | 6726656 | +| train/ | | +| approx_kl | 2.1183403 | +| clip_fraction | 0.493 | +| clip_range | 0.2 | +| entropy_loss | -0.48 | +| explained_variance | -2.41 | +| learning_rate | 0.0001 | +| loss | -0.0367 | +| n_updates | 126210 | +| policy_gradient_loss | -0.0685 | +| value_loss | 0.000604 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.36e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 309 | +| iterations | 6570 | +| time_elapsed | 21731 | +| total_timesteps | 6727680 | +| train/ | | +| approx_kl | 2.523994 | +| clip_fraction | 0.454 | +| clip_range | 0.2 | +| entropy_loss | -0.324 | +| explained_variance | -1.27 | +| learning_rate | 0.0001 | +| loss | -0.0439 | +| n_updates | 126220 | +| policy_gradient_loss | -0.0542 | +| value_loss | 0.000588 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.36e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 309 | +| iterations | 6571 | +| time_elapsed | 21734 | +| total_timesteps | 6728704 | +| train/ | | +| approx_kl | 3.1690948 | +| clip_fraction | 0.531 | +| clip_range | 0.2 | +| entropy_loss | -0.402 | +| explained_variance | -1.6 | +| learning_rate | 0.0001 | +| loss | -0.0527 | +| n_updates | 126230 | +| policy_gradient_loss | -0.0548 | +| value_loss | 0.000593 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.36e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 309 | +| iterations | 6572 | +| time_elapsed | 21737 | +| total_timesteps | 6729728 | +| train/ | | +| approx_kl | 2.304255 | +| clip_fraction | 0.473 | +| clip_range | 0.2 | +| entropy_loss | -0.384 | +| explained_variance | -0.889 | +| learning_rate | 0.0001 | +| loss | -0.107 | +| n_updates | 126240 | +| policy_gradient_loss | -0.0637 | +| value_loss | 0.000532 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.35e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 309 | +| iterations | 6573 | +| time_elapsed | 21740 | +| total_timesteps | 6730752 | +| train/ | | +| approx_kl | 2.2673488 | +| clip_fraction | 0.509 | +| clip_range | 0.2 | +| entropy_loss | -0.407 | +| explained_variance | -5.06 | +| learning_rate | 0.0001 | +| loss | -0.0953 | +| n_updates | 126250 | +| policy_gradient_loss | -0.0617 | +| value_loss | 0.000341 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.35e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 309 | +| iterations | 6574 | +| time_elapsed | 21744 | +| total_timesteps | 6731776 | +| train/ | | +| approx_kl | 2.5485444 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.356 | +| explained_variance | -0.568 | +| learning_rate | 0.0001 | +| loss | -0.0577 | +| n_updates | 126260 | +| policy_gradient_loss | -0.0532 | +| value_loss | 0.000454 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.35e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 309 | +| iterations | 6575 | +| time_elapsed | 21747 | +| total_timesteps | 6732800 | +| train/ | | +| approx_kl | 2.0609798 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.355 | +| explained_variance | -4.1 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 126270 | +| policy_gradient_loss | -0.0714 | +| value_loss | 0.000218 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.35e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 309 | +| iterations | 6576 | +| time_elapsed | 21750 | +| total_timesteps | 6733824 | +| train/ | | +| approx_kl | 2.775735 | +| clip_fraction | 0.52 | +| clip_range | 0.2 | +| entropy_loss | -0.456 | +| explained_variance | -0.438 | +| learning_rate | 0.0001 | +| loss | -0.0897 | +| n_updates | 126280 | +| policy_gradient_loss | -0.0572 | +| value_loss | 0.000312 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.35e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 309 | +| iterations | 6577 | +| time_elapsed | 21753 | +| total_timesteps | 6734848 | +| train/ | | +| approx_kl | 1.7029401 | +| clip_fraction | 0.452 | +| clip_range | 0.2 | +| entropy_loss | -0.351 | +| explained_variance | -3.14 | +| learning_rate | 0.0001 | +| loss | -0.0843 | +| n_updates | 126290 | +| policy_gradient_loss | -0.0628 | +| value_loss | 0.000176 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.35e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 309 | +| iterations | 6578 | +| time_elapsed | 21756 | +| total_timesteps | 6735872 | +| train/ | | +| approx_kl | 2.3647041 | +| clip_fraction | 0.464 | +| clip_range | 0.2 | +| entropy_loss | -0.354 | +| explained_variance | -0.545 | +| learning_rate | 0.0001 | +| loss | -0.0835 | +| n_updates | 126300 | +| policy_gradient_loss | -0.0489 | +| value_loss | 0.000813 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.34e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 309 | +| iterations | 6579 | +| time_elapsed | 21760 | +| total_timesteps | 6736896 | +| train/ | | +| approx_kl | 1.7766378 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.378 | +| explained_variance | -4.88 | +| learning_rate | 0.0001 | +| loss | -0.0522 | +| n_updates | 126310 | +| policy_gradient_loss | -0.061 | +| value_loss | 0.000633 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.34e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 309 | +| iterations | 6580 | +| time_elapsed | 21763 | +| total_timesteps | 6737920 | +| train/ | | +| approx_kl | 2.1425629 | +| clip_fraction | 0.449 | +| clip_range | 0.2 | +| entropy_loss | -0.343 | +| explained_variance | -1.47 | +| learning_rate | 0.0001 | +| loss | -0.0662 | +| n_updates | 126320 | +| policy_gradient_loss | -0.0577 | +| value_loss | 0.000544 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.34e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 309 | +| iterations | 6581 | +| time_elapsed | 21766 | +| total_timesteps | 6738944 | +| train/ | | +| approx_kl | 10.729731 | +| clip_fraction | 0.486 | +| clip_range | 0.2 | +| entropy_loss | -0.334 | +| explained_variance | -5.21 | +| learning_rate | 0.0001 | +| loss | -0.0925 | +| n_updates | 126330 | +| policy_gradient_loss | -0.0696 | +| value_loss | 0.000365 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.34e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 309 | +| iterations | 6582 | +| time_elapsed | 21769 | +| total_timesteps | 6739968 | +| train/ | | +| approx_kl | 2.310203 | +| clip_fraction | 0.476 | +| clip_range | 0.2 | +| entropy_loss | -0.39 | +| explained_variance | -0.579 | +| learning_rate | 0.0001 | +| loss | -0.0678 | +| n_updates | 126340 | +| policy_gradient_loss | -0.0543 | +| value_loss | 0.000394 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.34e+03 | +| ep_rew_mean | 0.297 | +| time/ | | +| fps | 309 | +| iterations | 6583 | +| time_elapsed | 21773 | +| total_timesteps | 6740992 | +| train/ | | +| approx_kl | 3.6962368 | +| clip_fraction | 0.522 | +| clip_range | 0.2 | +| entropy_loss | -0.497 | +| explained_variance | -1.12 | +| learning_rate | 0.0001 | +| loss | -0.0875 | +| n_updates | 126350 | +| policy_gradient_loss | -0.0629 | +| value_loss | 0.000323 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.34e+03 | +| ep_rew_mean | 0.297 | +| time/ | | +| fps | 309 | +| iterations | 6584 | +| time_elapsed | 21776 | +| total_timesteps | 6742016 | +| train/ | | +| approx_kl | 2.6540914 | +| clip_fraction | 0.474 | +| clip_range | 0.2 | +| entropy_loss | -0.401 | +| explained_variance | -0.611 | +| learning_rate | 0.0001 | +| loss | -0.0641 | +| n_updates | 126360 | +| policy_gradient_loss | -0.0573 | +| value_loss | 0.00056 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.34e+03 | +| ep_rew_mean | 0.297 | +| time/ | | +| fps | 309 | +| iterations | 6585 | +| time_elapsed | 21779 | +| total_timesteps | 6743040 | +| train/ | | +| approx_kl | 2.37147 | +| clip_fraction | 0.508 | +| clip_range | 0.2 | +| entropy_loss | -0.431 | +| explained_variance | -5.07 | +| learning_rate | 0.0001 | +| loss | -0.0888 | +| n_updates | 126370 | +| policy_gradient_loss | -0.065 | +| value_loss | 0.00029 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.35e+03 | +| ep_rew_mean | 0.294 | +| time/ | | +| fps | 309 | +| iterations | 6586 | +| time_elapsed | 21783 | +| total_timesteps | 6744064 | +| train/ | | +| approx_kl | 3.0773106 | +| clip_fraction | 0.5 | +| clip_range | 0.2 | +| entropy_loss | -0.312 | +| explained_variance | -1.07 | +| learning_rate | 0.0001 | +| loss | -0.0763 | +| n_updates | 126380 | +| policy_gradient_loss | -0.0607 | +| value_loss | 0.000338 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.34e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 309 | +| iterations | 6587 | +| time_elapsed | 21786 | +| total_timesteps | 6745088 | +| train/ | | +| approx_kl | 2.7542741 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.376 | +| explained_variance | -0.738 | +| learning_rate | 0.0001 | +| loss | -0.0799 | +| n_updates | 126390 | +| policy_gradient_loss | -0.0567 | +| value_loss | 0.000375 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.33e+03 | +| ep_rew_mean | 0.304 | +| time/ | | +| fps | 309 | +| iterations | 6588 | +| time_elapsed | 21789 | +| total_timesteps | 6746112 | +| train/ | | +| approx_kl | 2.2702422 | +| clip_fraction | 0.482 | +| clip_range | 0.2 | +| entropy_loss | -0.344 | +| explained_variance | -0.108 | +| learning_rate | 0.0001 | +| loss | -0.0685 | +| n_updates | 126400 | +| policy_gradient_loss | -0.0681 | +| value_loss | 0.00079 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.33e+03 | +| ep_rew_mean | 0.304 | +| time/ | | +| fps | 309 | +| iterations | 6589 | +| time_elapsed | 21792 | +| total_timesteps | 6747136 | +| train/ | | +| approx_kl | 2.0505018 | +| clip_fraction | 0.495 | +| clip_range | 0.2 | +| entropy_loss | -0.417 | +| explained_variance | 0.0624 | +| learning_rate | 0.0001 | +| loss | -0.0842 | +| n_updates | 126410 | +| policy_gradient_loss | -0.0548 | +| value_loss | 0.000723 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.33e+03 | +| ep_rew_mean | 0.304 | +| time/ | | +| fps | 309 | +| iterations | 6590 | +| time_elapsed | 21795 | +| total_timesteps | 6748160 | +| train/ | | +| approx_kl | 2.4597173 | +| clip_fraction | 0.489 | +| clip_range | 0.2 | +| entropy_loss | -0.368 | +| explained_variance | -3.83 | +| learning_rate | 0.0001 | +| loss | -0.109 | +| n_updates | 126420 | +| policy_gradient_loss | -0.0648 | +| value_loss | 0.000367 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.33e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 309 | +| iterations | 6591 | +| time_elapsed | 21799 | +| total_timesteps | 6749184 | +| train/ | | +| approx_kl | 2.134556 | +| clip_fraction | 0.479 | +| clip_range | 0.2 | +| entropy_loss | -0.412 | +| explained_variance | -5.68 | +| learning_rate | 0.0001 | +| loss | -0.0824 | +| n_updates | 126430 | +| policy_gradient_loss | -0.0693 | +| value_loss | 0.000251 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.33e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 309 | +| iterations | 6592 | +| time_elapsed | 21802 | +| total_timesteps | 6750208 | +| train/ | | +| approx_kl | 2.3774915 | +| clip_fraction | 0.519 | +| clip_range | 0.2 | +| entropy_loss | -0.429 | +| explained_variance | -0.456 | +| learning_rate | 0.0001 | +| loss | -0.0767 | +| n_updates | 126440 | +| policy_gradient_loss | -0.0508 | +| value_loss | 0.000244 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.32e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 309 | +| iterations | 6593 | +| time_elapsed | 21805 | +| total_timesteps | 6751232 | +| train/ | | +| approx_kl | 4.046343 | +| clip_fraction | 0.522 | +| clip_range | 0.2 | +| entropy_loss | -0.416 | +| explained_variance | -3.53 | +| learning_rate | 0.0001 | +| loss | -0.0954 | +| n_updates | 126450 | +| policy_gradient_loss | -0.0713 | +| value_loss | 0.000267 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.32e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 309 | +| iterations | 6594 | +| time_elapsed | 21808 | +| total_timesteps | 6752256 | +| train/ | | +| approx_kl | 2.634769 | +| clip_fraction | 0.509 | +| clip_range | 0.2 | +| entropy_loss | -0.363 | +| explained_variance | -0.844 | +| learning_rate | 0.0001 | +| loss | -0.0351 | +| n_updates | 126460 | +| policy_gradient_loss | -0.0613 | +| value_loss | 0.00075 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.32e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 309 | +| iterations | 6595 | +| time_elapsed | 21811 | +| total_timesteps | 6753280 | +| train/ | | +| approx_kl | 2.8057678 | +| clip_fraction | 0.486 | +| clip_range | 0.2 | +| entropy_loss | -0.366 | +| explained_variance | -1.41 | +| learning_rate | 0.0001 | +| loss | -0.08 | +| n_updates | 126470 | +| policy_gradient_loss | -0.0694 | +| value_loss | 0.000423 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.31e+03 | +| ep_rew_mean | 0.3 | +| time/ | | +| fps | 309 | +| iterations | 6596 | +| time_elapsed | 21815 | +| total_timesteps | 6754304 | +| train/ | | +| approx_kl | 2.0598037 | +| clip_fraction | 0.51 | +| clip_range | 0.2 | +| entropy_loss | -0.431 | +| explained_variance | -2.22 | +| learning_rate | 0.0001 | +| loss | -0.0923 | +| n_updates | 126480 | +| policy_gradient_loss | -0.0633 | +| value_loss | 0.000387 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.31e+03 | +| ep_rew_mean | 0.3 | +| time/ | | +| fps | 309 | +| iterations | 6597 | +| time_elapsed | 21818 | +| total_timesteps | 6755328 | +| train/ | | +| approx_kl | 9.811149 | +| clip_fraction | 0.478 | +| clip_range | 0.2 | +| entropy_loss | -0.401 | +| explained_variance | -0.549 | +| learning_rate | 0.0001 | +| loss | -0.0851 | +| n_updates | 126490 | +| policy_gradient_loss | -0.0594 | +| value_loss | 0.000302 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.31e+03 | +| ep_rew_mean | 0.3 | +| time/ | | +| fps | 309 | +| iterations | 6598 | +| time_elapsed | 21821 | +| total_timesteps | 6756352 | +| train/ | | +| approx_kl | 2.5290954 | +| clip_fraction | 0.527 | +| clip_range | 0.2 | +| entropy_loss | -0.421 | +| explained_variance | -1.38 | +| learning_rate | 0.0001 | +| loss | -0.107 | +| n_updates | 126500 | +| policy_gradient_loss | -0.07 | +| value_loss | 0.000449 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.32e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 309 | +| iterations | 6599 | +| time_elapsed | 21825 | +| total_timesteps | 6757376 | +| train/ | | +| approx_kl | 2.0496373 | +| clip_fraction | 0.503 | +| clip_range | 0.2 | +| entropy_loss | -0.425 | +| explained_variance | -2.16 | +| learning_rate | 0.0001 | +| loss | -0.122 | +| n_updates | 126510 | +| policy_gradient_loss | -0.0688 | +| value_loss | 0.000407 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.32e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 309 | +| iterations | 6600 | +| time_elapsed | 21828 | +| total_timesteps | 6758400 | +| train/ | | +| approx_kl | 2.2647443 | +| clip_fraction | 0.53 | +| clip_range | 0.2 | +| entropy_loss | -0.443 | +| explained_variance | -0.0796 | +| learning_rate | 0.0001 | +| loss | -0.0885 | +| n_updates | 126520 | +| policy_gradient_loss | -0.06 | +| value_loss | 0.00058 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.31e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 309 | +| iterations | 6601 | +| time_elapsed | 21832 | +| total_timesteps | 6759424 | +| train/ | | +| approx_kl | 2.052895 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.4 | +| explained_variance | -3.64 | +| learning_rate | 0.0001 | +| loss | -0.0819 | +| n_updates | 126530 | +| policy_gradient_loss | -0.0684 | +| value_loss | 0.000318 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.31e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 309 | +| iterations | 6602 | +| time_elapsed | 21835 | +| total_timesteps | 6760448 | +| train/ | | +| approx_kl | 2.29255 | +| clip_fraction | 0.465 | +| clip_range | 0.2 | +| entropy_loss | -0.351 | +| explained_variance | -0.414 | +| learning_rate | 0.0001 | +| loss | -0.0783 | +| n_updates | 126540 | +| policy_gradient_loss | -0.0548 | +| value_loss | 0.000336 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.31e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 309 | +| iterations | 6603 | +| time_elapsed | 21838 | +| total_timesteps | 6761472 | +| train/ | | +| approx_kl | 2.3372774 | +| clip_fraction | 0.567 | +| clip_range | 0.2 | +| entropy_loss | -0.581 | +| explained_variance | -1.14 | +| learning_rate | 0.0001 | +| loss | -0.0864 | +| n_updates | 126550 | +| policy_gradient_loss | -0.0731 | +| value_loss | 0.000286 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.31e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 309 | +| iterations | 6604 | +| time_elapsed | 21842 | +| total_timesteps | 6762496 | +| train/ | | +| approx_kl | 1.8325465 | +| clip_fraction | 0.492 | +| clip_range | 0.2 | +| entropy_loss | -0.458 | +| explained_variance | -0.275 | +| learning_rate | 0.0001 | +| loss | -0.0911 | +| n_updates | 126560 | +| policy_gradient_loss | -0.0484 | +| value_loss | 0.000273 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.31e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 309 | +| iterations | 6605 | +| time_elapsed | 21845 | +| total_timesteps | 6763520 | +| train/ | | +| approx_kl | 4.0199943 | +| clip_fraction | 0.493 | +| clip_range | 0.2 | +| entropy_loss | -0.347 | +| explained_variance | -2.91 | +| learning_rate | 0.0001 | +| loss | -0.0852 | +| n_updates | 126570 | +| policy_gradient_loss | -0.0685 | +| value_loss | 0.000348 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.32e+03 | +| ep_rew_mean | 0.3 | +| time/ | | +| fps | 309 | +| iterations | 6606 | +| time_elapsed | 21849 | +| total_timesteps | 6764544 | +| train/ | | +| approx_kl | 1.5181314 | +| clip_fraction | 0.484 | +| clip_range | 0.2 | +| entropy_loss | -0.423 | +| explained_variance | -6.18 | +| learning_rate | 0.0001 | +| loss | -0.0988 | +| n_updates | 126580 | +| policy_gradient_loss | -0.0714 | +| value_loss | 0.000238 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.32e+03 | +| ep_rew_mean | 0.3 | +| time/ | | +| fps | 309 | +| iterations | 6607 | +| time_elapsed | 21852 | +| total_timesteps | 6765568 | +| train/ | | +| approx_kl | 2.0067549 | +| clip_fraction | 0.504 | +| clip_range | 0.2 | +| entropy_loss | -0.415 | +| explained_variance | -0.527 | +| learning_rate | 0.0001 | +| loss | -0.0596 | +| n_updates | 126590 | +| policy_gradient_loss | -0.0505 | +| value_loss | 0.000373 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.31e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 309 | +| iterations | 6608 | +| time_elapsed | 21855 | +| total_timesteps | 6766592 | +| train/ | | +| approx_kl | 2.1590886 | +| clip_fraction | 0.498 | +| clip_range | 0.2 | +| entropy_loss | -0.443 | +| explained_variance | -1.14 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 126600 | +| policy_gradient_loss | -0.0695 | +| value_loss | 0.00044 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.31e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 309 | +| iterations | 6609 | +| time_elapsed | 21858 | +| total_timesteps | 6767616 | +| train/ | | +| approx_kl | 2.5147202 | +| clip_fraction | 0.484 | +| clip_range | 0.2 | +| entropy_loss | -0.347 | +| explained_variance | -1.67 | +| learning_rate | 0.0001 | +| loss | -0.0641 | +| n_updates | 126610 | +| policy_gradient_loss | -0.0529 | +| value_loss | 0.000509 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.31e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 309 | +| iterations | 6610 | +| time_elapsed | 21861 | +| total_timesteps | 6768640 | +| train/ | | +| approx_kl | 2.0406432 | +| clip_fraction | 0.55 | +| clip_range | 0.2 | +| entropy_loss | -0.487 | +| explained_variance | -3.91 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 126620 | +| policy_gradient_loss | -0.0793 | +| value_loss | 0.000415 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.28e+03 | +| ep_rew_mean | 0.302 | +| time/ | | +| fps | 309 | +| iterations | 6611 | +| time_elapsed | 21865 | +| total_timesteps | 6769664 | +| train/ | | +| approx_kl | 2.2938213 | +| clip_fraction | 0.542 | +| clip_range | 0.2 | +| entropy_loss | -0.431 | +| explained_variance | -1.11 | +| learning_rate | 0.0001 | +| loss | -0.125 | +| n_updates | 126630 | +| policy_gradient_loss | -0.0671 | +| value_loss | 0.000286 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.28e+03 | +| ep_rew_mean | 0.302 | +| time/ | | +| fps | 309 | +| iterations | 6612 | +| time_elapsed | 21868 | +| total_timesteps | 6770688 | +| train/ | | +| approx_kl | 2.0558436 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.384 | +| explained_variance | -1.38 | +| learning_rate | 0.0001 | +| loss | -0.0881 | +| n_updates | 126640 | +| policy_gradient_loss | -0.0561 | +| value_loss | 0.000221 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.29e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 309 | +| iterations | 6613 | +| time_elapsed | 21871 | +| total_timesteps | 6771712 | +| train/ | | +| approx_kl | 1.9655021 | +| clip_fraction | 0.535 | +| clip_range | 0.2 | +| entropy_loss | -0.506 | +| explained_variance | -1.04 | +| learning_rate | 0.0001 | +| loss | -0.0657 | +| n_updates | 126650 | +| policy_gradient_loss | -0.0699 | +| value_loss | 0.000517 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.28e+03 | +| ep_rew_mean | 0.297 | +| time/ | | +| fps | 309 | +| iterations | 6614 | +| time_elapsed | 21874 | +| total_timesteps | 6772736 | +| train/ | | +| approx_kl | 1.8281969 | +| clip_fraction | 0.506 | +| clip_range | 0.2 | +| entropy_loss | -0.451 | +| explained_variance | -1.01 | +| learning_rate | 0.0001 | +| loss | -0.0972 | +| n_updates | 126660 | +| policy_gradient_loss | -0.0652 | +| value_loss | 0.000673 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.28e+03 | +| ep_rew_mean | 0.297 | +| time/ | | +| fps | 309 | +| iterations | 6615 | +| time_elapsed | 21877 | +| total_timesteps | 6773760 | +| train/ | | +| approx_kl | 2.2665184 | +| clip_fraction | 0.503 | +| clip_range | 0.2 | +| entropy_loss | -0.425 | +| explained_variance | 0.0201 | +| learning_rate | 0.0001 | +| loss | -0.0894 | +| n_updates | 126670 | +| policy_gradient_loss | -0.0697 | +| value_loss | 0.000594 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.28e+03 | +| ep_rew_mean | 0.297 | +| time/ | | +| fps | 309 | +| iterations | 6616 | +| time_elapsed | 21881 | +| total_timesteps | 6774784 | +| train/ | | +| approx_kl | 1.674077 | +| clip_fraction | 0.502 | +| clip_range | 0.2 | +| entropy_loss | -0.566 | +| explained_variance | -1.29 | +| learning_rate | 0.0001 | +| loss | -0.0975 | +| n_updates | 126680 | +| policy_gradient_loss | -0.0664 | +| value_loss | 0.000632 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.28e+03 | +| ep_rew_mean | 0.298 | +| time/ | | +| fps | 309 | +| iterations | 6617 | +| time_elapsed | 21884 | +| total_timesteps | 6775808 | +| train/ | | +| approx_kl | 2.2872767 | +| clip_fraction | 0.533 | +| clip_range | 0.2 | +| entropy_loss | -0.425 | +| explained_variance | -3.72 | +| learning_rate | 0.0001 | +| loss | -0.0981 | +| n_updates | 126690 | +| policy_gradient_loss | -0.0754 | +| value_loss | 0.00037 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.27e+03 | +| ep_rew_mean | 0.298 | +| time/ | | +| fps | 309 | +| iterations | 6618 | +| time_elapsed | 21888 | +| total_timesteps | 6776832 | +| train/ | | +| approx_kl | 1.9850923 | +| clip_fraction | 0.468 | +| clip_range | 0.2 | +| entropy_loss | -0.385 | +| explained_variance | -0.117 | +| learning_rate | 0.0001 | +| loss | -0.0669 | +| n_updates | 126700 | +| policy_gradient_loss | -0.064 | +| value_loss | 0.000367 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.27e+03 | +| ep_rew_mean | 0.298 | +| time/ | | +| fps | 309 | +| iterations | 6619 | +| time_elapsed | 21892 | +| total_timesteps | 6777856 | +| train/ | | +| approx_kl | 1.7841868 | +| clip_fraction | 0.455 | +| clip_range | 0.2 | +| entropy_loss | -0.402 | +| explained_variance | 0.0117 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 126710 | +| policy_gradient_loss | -0.0708 | +| value_loss | 0.000632 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.27e+03 | +| ep_rew_mean | 0.298 | +| time/ | | +| fps | 309 | +| iterations | 6620 | +| time_elapsed | 21895 | +| total_timesteps | 6778880 | +| train/ | | +| approx_kl | 4.216793 | +| clip_fraction | 0.519 | +| clip_range | 0.2 | +| entropy_loss | -0.478 | +| explained_variance | -4.73 | +| learning_rate | 0.0001 | +| loss | -0.059 | +| n_updates | 126720 | +| policy_gradient_loss | -0.0656 | +| value_loss | 0.000638 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.28e+03 | +| ep_rew_mean | 0.3 | +| time/ | | +| fps | 309 | +| iterations | 6621 | +| time_elapsed | 21899 | +| total_timesteps | 6779904 | +| train/ | | +| approx_kl | 3.1335797 | +| clip_fraction | 0.493 | +| clip_range | 0.2 | +| entropy_loss | -0.355 | +| explained_variance | -3.79 | +| learning_rate | 0.0001 | +| loss | -0.0994 | +| n_updates | 126730 | +| policy_gradient_loss | -0.0692 | +| value_loss | 0.000424 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.28e+03 | +| ep_rew_mean | 0.3 | +| time/ | | +| fps | 309 | +| iterations | 6622 | +| time_elapsed | 21902 | +| total_timesteps | 6780928 | +| train/ | | +| approx_kl | 1.6979842 | +| clip_fraction | 0.486 | +| clip_range | 0.2 | +| entropy_loss | -0.449 | +| explained_variance | -0.468 | +| learning_rate | 0.0001 | +| loss | -0.0652 | +| n_updates | 126740 | +| policy_gradient_loss | -0.0548 | +| value_loss | 0.00045 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.28e+03 | +| ep_rew_mean | 0.3 | +| time/ | | +| fps | 309 | +| iterations | 6623 | +| time_elapsed | 21906 | +| total_timesteps | 6781952 | +| train/ | | +| approx_kl | 2.8480232 | +| clip_fraction | 0.513 | +| clip_range | 0.2 | +| entropy_loss | -0.378 | +| explained_variance | -6.88 | +| learning_rate | 0.0001 | +| loss | -0.0994 | +| n_updates | 126750 | +| policy_gradient_loss | -0.0741 | +| value_loss | 0.000386 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.27e+03 | +| ep_rew_mean | 0.298 | +| time/ | | +| fps | 309 | +| iterations | 6624 | +| time_elapsed | 21909 | +| total_timesteps | 6782976 | +| train/ | | +| approx_kl | 2.7378953 | +| clip_fraction | 0.495 | +| clip_range | 0.2 | +| entropy_loss | -0.38 | +| explained_variance | -2.01 | +| learning_rate | 0.0001 | +| loss | -0.0998 | +| n_updates | 126760 | +| policy_gradient_loss | -0.0604 | +| value_loss | 0.000393 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.27e+03 | +| ep_rew_mean | 0.297 | +| time/ | | +| fps | 309 | +| iterations | 6625 | +| time_elapsed | 21912 | +| total_timesteps | 6784000 | +| train/ | | +| approx_kl | 2.5420418 | +| clip_fraction | 0.504 | +| clip_range | 0.2 | +| entropy_loss | -0.384 | +| explained_variance | -1.31 | +| learning_rate | 0.0001 | +| loss | -0.0838 | +| n_updates | 126770 | +| policy_gradient_loss | -0.0641 | +| value_loss | 0.000751 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.27e+03 | +| ep_rew_mean | 0.297 | +| time/ | | +| fps | 309 | +| iterations | 6626 | +| time_elapsed | 21916 | +| total_timesteps | 6785024 | +| train/ | | +| approx_kl | 2.155657 | +| clip_fraction | 0.517 | +| clip_range | 0.2 | +| entropy_loss | -0.413 | +| explained_variance | -2.64 | +| learning_rate | 0.0001 | +| loss | -0.0832 | +| n_updates | 126780 | +| policy_gradient_loss | -0.0735 | +| value_loss | 0.00043 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.27e+03 | +| ep_rew_mean | 0.297 | +| time/ | | +| fps | 309 | +| iterations | 6627 | +| time_elapsed | 21919 | +| total_timesteps | 6786048 | +| train/ | | +| approx_kl | 2.424952 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.374 | +| explained_variance | -0.818 | +| learning_rate | 0.0001 | +| loss | -0.0944 | +| n_updates | 126790 | +| policy_gradient_loss | -0.0591 | +| value_loss | 0.000519 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.26e+03 | +| ep_rew_mean | 0.294 | +| time/ | | +| fps | 309 | +| iterations | 6628 | +| time_elapsed | 21922 | +| total_timesteps | 6787072 | +| train/ | | +| approx_kl | 2.4274158 | +| clip_fraction | 0.511 | +| clip_range | 0.2 | +| entropy_loss | -0.412 | +| explained_variance | -2.35 | +| learning_rate | 0.0001 | +| loss | -0.0873 | +| n_updates | 126800 | +| policy_gradient_loss | -0.0691 | +| value_loss | 0.000341 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.26e+03 | +| ep_rew_mean | 0.298 | +| time/ | | +| fps | 309 | +| iterations | 6629 | +| time_elapsed | 21925 | +| total_timesteps | 6788096 | +| train/ | | +| approx_kl | 2.5863132 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.354 | +| explained_variance | -0.506 | +| learning_rate | 0.0001 | +| loss | -0.0798 | +| n_updates | 126810 | +| policy_gradient_loss | -0.0623 | +| value_loss | 0.000433 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.26e+03 | +| ep_rew_mean | 0.298 | +| time/ | | +| fps | 309 | +| iterations | 6630 | +| time_elapsed | 21928 | +| total_timesteps | 6789120 | +| train/ | | +| approx_kl | 1.3432794 | +| clip_fraction | 0.52 | +| clip_range | 0.2 | +| entropy_loss | -0.567 | +| explained_variance | -0.0238 | +| learning_rate | 0.0001 | +| loss | -0.0093 | +| n_updates | 126820 | +| policy_gradient_loss | -0.0436 | +| value_loss | 0.000753 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.26e+03 | +| ep_rew_mean | 0.298 | +| time/ | | +| fps | 309 | +| iterations | 6631 | +| time_elapsed | 21931 | +| total_timesteps | 6790144 | +| train/ | | +| approx_kl | 2.1671114 | +| clip_fraction | 0.535 | +| clip_range | 0.2 | +| entropy_loss | -0.438 | +| explained_variance | -1.95 | +| learning_rate | 0.0001 | +| loss | -0.0943 | +| n_updates | 126830 | +| policy_gradient_loss | -0.0758 | +| value_loss | 0.000432 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.26e+03 | +| ep_rew_mean | 0.302 | +| time/ | | +| fps | 309 | +| iterations | 6632 | +| time_elapsed | 21934 | +| total_timesteps | 6791168 | +| train/ | | +| approx_kl | 2.2487705 | +| clip_fraction | 0.532 | +| clip_range | 0.2 | +| entropy_loss | -0.48 | +| explained_variance | -1.01 | +| learning_rate | 0.0001 | +| loss | -0.092 | +| n_updates | 126840 | +| policy_gradient_loss | -0.0728 | +| value_loss | 0.000233 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.26e+03 | +| ep_rew_mean | 0.302 | +| time/ | | +| fps | 309 | +| iterations | 6633 | +| time_elapsed | 21938 | +| total_timesteps | 6792192 | +| train/ | | +| approx_kl | 1.9431087 | +| clip_fraction | 0.52 | +| clip_range | 0.2 | +| entropy_loss | -0.465 | +| explained_variance | -0.219 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 126850 | +| policy_gradient_loss | -0.0555 | +| value_loss | 0.000287 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.27e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 309 | +| iterations | 6634 | +| time_elapsed | 21941 | +| total_timesteps | 6793216 | +| train/ | | +| approx_kl | 1.379904 | +| clip_fraction | 0.501 | +| clip_range | 0.2 | +| entropy_loss | -0.52 | +| explained_variance | -2.09 | +| learning_rate | 0.0001 | +| loss | -0.105 | +| n_updates | 126860 | +| policy_gradient_loss | -0.0684 | +| value_loss | 0.000346 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.27e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 309 | +| iterations | 6635 | +| time_elapsed | 21944 | +| total_timesteps | 6794240 | +| train/ | | +| approx_kl | 2.0888681 | +| clip_fraction | 0.506 | +| clip_range | 0.2 | +| entropy_loss | -0.538 | +| explained_variance | -0.575 | +| learning_rate | 0.0001 | +| loss | -0.0698 | +| n_updates | 126870 | +| policy_gradient_loss | -0.0614 | +| value_loss | 0.000458 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.27e+03 | +| ep_rew_mean | 0.298 | +| time/ | | +| fps | 309 | +| iterations | 6636 | +| time_elapsed | 21948 | +| total_timesteps | 6795264 | +| train/ | | +| approx_kl | 2.9629848 | +| clip_fraction | 0.521 | +| clip_range | 0.2 | +| entropy_loss | -0.423 | +| explained_variance | -2.77 | +| learning_rate | 0.0001 | +| loss | -0.0969 | +| n_updates | 126880 | +| policy_gradient_loss | -0.0707 | +| value_loss | 0.000338 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.27e+03 | +| ep_rew_mean | 0.298 | +| time/ | | +| fps | 309 | +| iterations | 6637 | +| time_elapsed | 21951 | +| total_timesteps | 6796288 | +| train/ | | +| approx_kl | 2.1045694 | +| clip_fraction | 0.42 | +| clip_range | 0.2 | +| entropy_loss | -0.324 | +| explained_variance | -0.609 | +| learning_rate | 0.0001 | +| loss | -0.0609 | +| n_updates | 126890 | +| policy_gradient_loss | -0.0509 | +| value_loss | 0.000604 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.28e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 309 | +| iterations | 6638 | +| time_elapsed | 21955 | +| total_timesteps | 6797312 | +| train/ | | +| approx_kl | 1.70913 | +| clip_fraction | 0.531 | +| clip_range | 0.2 | +| entropy_loss | -0.544 | +| explained_variance | -1.35 | +| learning_rate | 0.0001 | +| loss | -0.108 | +| n_updates | 126900 | +| policy_gradient_loss | -0.0756 | +| value_loss | 0.000306 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.28e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 309 | +| iterations | 6639 | +| time_elapsed | 21958 | +| total_timesteps | 6798336 | +| train/ | | +| approx_kl | 2.0784683 | +| clip_fraction | 0.493 | +| clip_range | 0.2 | +| entropy_loss | -0.554 | +| explained_variance | 0.0371 | +| learning_rate | 0.0001 | +| loss | -0.123 | +| n_updates | 126910 | +| policy_gradient_loss | -0.0615 | +| value_loss | 0.000262 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.28e+03 | +| ep_rew_mean | 0.3 | +| time/ | | +| fps | 309 | +| iterations | 6640 | +| time_elapsed | 21962 | +| total_timesteps | 6799360 | +| train/ | | +| approx_kl | 2.498851 | +| clip_fraction | 0.545 | +| clip_range | 0.2 | +| entropy_loss | -0.55 | +| explained_variance | -0.765 | +| learning_rate | 0.0001 | +| loss | -0.067 | +| n_updates | 126920 | +| policy_gradient_loss | -0.0676 | +| value_loss | 0.000506 | +-------------------------------------- + +Current state: Champion.Level6.RyuVsRyu +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.28e+03 | +| ep_rew_mean | 0.3 | +| time/ | | +| fps | 309 | +| iterations | 6641 | +| time_elapsed | 21965 | +| total_timesteps | 6800384 | +| train/ | | +| approx_kl | 1.3793563 | +| clip_fraction | 0.504 | +| clip_range | 0.2 | +| entropy_loss | -0.565 | +| explained_variance | -0.297 | +| learning_rate | 0.0001 | +| loss | -0.0786 | +| n_updates | 126930 | +| policy_gradient_loss | -0.0609 | +| value_loss | 0.000299 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.28e+03 | +| ep_rew_mean | 0.3 | +| time/ | | +| fps | 309 | +| iterations | 6642 | +| time_elapsed | 21969 | +| total_timesteps | 6801408 | +| train/ | | +| approx_kl | 2.089913 | +| clip_fraction | 0.494 | +| clip_range | 0.2 | +| entropy_loss | -0.425 | +| explained_variance | -1.35 | +| learning_rate | 0.0001 | +| loss | -0.107 | +| n_updates | 126940 | +| policy_gradient_loss | -0.066 | +| value_loss | 0.000368 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.28e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 309 | +| iterations | 6643 | +| time_elapsed | 21972 | +| total_timesteps | 6802432 | +| train/ | | +| approx_kl | 2.0686398 | +| clip_fraction | 0.552 | +| clip_range | 0.2 | +| entropy_loss | -0.576 | +| explained_variance | -0.627 | +| learning_rate | 0.0001 | +| loss | -0.0955 | +| n_updates | 126950 | +| policy_gradient_loss | -0.0746 | +| value_loss | 0.000287 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.27e+03 | +| ep_rew_mean | 0.294 | +| time/ | | +| fps | 309 | +| iterations | 6644 | +| time_elapsed | 21975 | +| total_timesteps | 6803456 | +| train/ | | +| approx_kl | 1.5279851 | +| clip_fraction | 0.547 | +| clip_range | 0.2 | +| entropy_loss | -0.661 | +| explained_variance | -3.02 | +| learning_rate | 0.0001 | +| loss | -0.0802 | +| n_updates | 126960 | +| policy_gradient_loss | -0.0732 | +| value_loss | 0.000528 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.27e+03 | +| ep_rew_mean | 0.294 | +| time/ | | +| fps | 309 | +| iterations | 6645 | +| time_elapsed | 21978 | +| total_timesteps | 6804480 | +| train/ | | +| approx_kl | 1.4063972 | +| clip_fraction | 0.517 | +| clip_range | 0.2 | +| entropy_loss | -0.558 | +| explained_variance | -2.07 | +| learning_rate | 0.0001 | +| loss | -0.0996 | +| n_updates | 126970 | +| policy_gradient_loss | -0.0664 | +| value_loss | 0.000804 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.26e+03 | +| ep_rew_mean | 0.291 | +| time/ | | +| fps | 309 | +| iterations | 6646 | +| time_elapsed | 21981 | +| total_timesteps | 6805504 | +| train/ | | +| approx_kl | 3.4883256 | +| clip_fraction | 0.585 | +| clip_range | 0.2 | +| entropy_loss | -0.963 | +| explained_variance | -3.53 | +| learning_rate | 0.0001 | +| loss | -0.0944 | +| n_updates | 126980 | +| policy_gradient_loss | -0.0755 | +| value_loss | 0.000531 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.25e+03 | +| ep_rew_mean | 0.285 | +| time/ | | +| fps | 309 | +| iterations | 6647 | +| time_elapsed | 21985 | +| total_timesteps | 6806528 | +| train/ | | +| approx_kl | 1.5599284 | +| clip_fraction | 0.545 | +| clip_range | 0.2 | +| entropy_loss | -0.56 | +| explained_variance | -10.6 | +| learning_rate | 0.0001 | +| loss | -0.093 | +| n_updates | 126990 | +| policy_gradient_loss | -0.0738 | +| value_loss | 0.000773 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.25e+03 | +| ep_rew_mean | 0.284 | +| time/ | | +| fps | 309 | +| iterations | 6648 | +| time_elapsed | 21988 | +| total_timesteps | 6807552 | +| train/ | | +| approx_kl | 1.4526708 | +| clip_fraction | 0.517 | +| clip_range | 0.2 | +| entropy_loss | -0.662 | +| explained_variance | -2.28 | +| learning_rate | 0.0001 | +| loss | -0.0957 | +| n_updates | 127000 | +| policy_gradient_loss | -0.0676 | +| value_loss | 0.000564 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.25e+03 | +| ep_rew_mean | 0.284 | +| time/ | | +| fps | 309 | +| iterations | 6649 | +| time_elapsed | 21991 | +| total_timesteps | 6808576 | +| train/ | | +| approx_kl | 1.8998221 | +| clip_fraction | 0.548 | +| clip_range | 0.2 | +| entropy_loss | -0.651 | +| explained_variance | -1.38 | +| learning_rate | 0.0001 | +| loss | -0.122 | +| n_updates | 127010 | +| policy_gradient_loss | -0.0745 | +| value_loss | 0.000524 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.25e+03 | +| ep_rew_mean | 0.284 | +| time/ | | +| fps | 309 | +| iterations | 6650 | +| time_elapsed | 21994 | +| total_timesteps | 6809600 | +| train/ | | +| approx_kl | 1.4918547 | +| clip_fraction | 0.606 | +| clip_range | 0.2 | +| entropy_loss | -0.947 | +| explained_variance | -1.35 | +| learning_rate | 0.0001 | +| loss | -0.0583 | +| n_updates | 127020 | +| policy_gradient_loss | -0.0769 | +| value_loss | 0.000629 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.26e+03 | +| ep_rew_mean | 0.285 | +| time/ | | +| fps | 309 | +| iterations | 6651 | +| time_elapsed | 21997 | +| total_timesteps | 6810624 | +| train/ | | +| approx_kl | 1.600785 | +| clip_fraction | 0.519 | +| clip_range | 0.2 | +| entropy_loss | -0.538 | +| explained_variance | -13.6 | +| learning_rate | 0.0001 | +| loss | -0.0697 | +| n_updates | 127030 | +| policy_gradient_loss | -0.0689 | +| value_loss | 0.000712 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.25e+03 | +| ep_rew_mean | 0.29 | +| time/ | | +| fps | 309 | +| iterations | 6652 | +| time_elapsed | 22001 | +| total_timesteps | 6811648 | +| train/ | | +| approx_kl | 1.5500332 | +| clip_fraction | 0.536 | +| clip_range | 0.2 | +| entropy_loss | -0.741 | +| explained_variance | -2.64 | +| learning_rate | 0.0001 | +| loss | -0.0919 | +| n_updates | 127040 | +| policy_gradient_loss | -0.0735 | +| value_loss | 0.00041 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.25e+03 | +| ep_rew_mean | 0.29 | +| time/ | | +| fps | 309 | +| iterations | 6653 | +| time_elapsed | 22004 | +| total_timesteps | 6812672 | +| train/ | | +| approx_kl | 1.6174917 | +| clip_fraction | 0.517 | +| clip_range | 0.2 | +| entropy_loss | -0.63 | +| explained_variance | -0.327 | +| learning_rate | 0.0001 | +| loss | -0.0899 | +| n_updates | 127050 | +| policy_gradient_loss | -0.0733 | +| value_loss | 0.000383 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.24e+03 | +| ep_rew_mean | 0.286 | +| time/ | | +| fps | 309 | +| iterations | 6654 | +| time_elapsed | 22007 | +| total_timesteps | 6813696 | +| train/ | | +| approx_kl | 1.8246034 | +| clip_fraction | 0.532 | +| clip_range | 0.2 | +| entropy_loss | -0.602 | +| explained_variance | -8.59 | +| learning_rate | 0.0001 | +| loss | -0.0945 | +| n_updates | 127060 | +| policy_gradient_loss | -0.0811 | +| value_loss | 0.000386 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.24e+03 | +| ep_rew_mean | 0.286 | +| time/ | | +| fps | 309 | +| iterations | 6655 | +| time_elapsed | 22011 | +| total_timesteps | 6814720 | +| train/ | | +| approx_kl | 1.2653959 | +| clip_fraction | 0.524 | +| clip_range | 0.2 | +| entropy_loss | -0.559 | +| explained_variance | -1.05 | +| learning_rate | 0.0001 | +| loss | -0.0922 | +| n_updates | 127070 | +| policy_gradient_loss | -0.0749 | +| value_loss | 0.000636 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.23e+03 | +| ep_rew_mean | 0.283 | +| time/ | | +| fps | 309 | +| iterations | 6656 | +| time_elapsed | 22014 | +| total_timesteps | 6815744 | +| train/ | | +| approx_kl | 1.7387371 | +| clip_fraction | 0.545 | +| clip_range | 0.2 | +| entropy_loss | -0.629 | +| explained_variance | -4.21 | +| learning_rate | 0.0001 | +| loss | -0.0671 | +| n_updates | 127080 | +| policy_gradient_loss | -0.0736 | +| value_loss | 0.000522 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.23e+03 | +| ep_rew_mean | 0.283 | +| time/ | | +| fps | 309 | +| iterations | 6657 | +| time_elapsed | 22018 | +| total_timesteps | 6816768 | +| train/ | | +| approx_kl | 1.4617915 | +| clip_fraction | 0.513 | +| clip_range | 0.2 | +| entropy_loss | -0.548 | +| explained_variance | -1.13 | +| learning_rate | 0.0001 | +| loss | -0.0638 | +| n_updates | 127090 | +| policy_gradient_loss | -0.0679 | +| value_loss | 0.000909 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.24e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 309 | +| iterations | 6658 | +| time_elapsed | 22021 | +| total_timesteps | 6817792 | +| train/ | | +| approx_kl | 1.9658134 | +| clip_fraction | 0.529 | +| clip_range | 0.2 | +| entropy_loss | -0.661 | +| explained_variance | -2.24 | +| learning_rate | 0.0001 | +| loss | -0.0886 | +| n_updates | 127100 | +| policy_gradient_loss | -0.074 | +| value_loss | 0.000811 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.22e+03 | +| ep_rew_mean | 0.274 | +| time/ | | +| fps | 309 | +| iterations | 6659 | +| time_elapsed | 22025 | +| total_timesteps | 6818816 | +| train/ | | +| approx_kl | 1.6766858 | +| clip_fraction | 0.538 | +| clip_range | 0.2 | +| entropy_loss | -0.68 | +| explained_variance | -4.34 | +| learning_rate | 0.0001 | +| loss | -0.109 | +| n_updates | 127110 | +| policy_gradient_loss | -0.0764 | +| value_loss | 0.000497 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.22e+03 | +| ep_rew_mean | 0.274 | +| time/ | | +| fps | 309 | +| iterations | 6660 | +| time_elapsed | 22028 | +| total_timesteps | 6819840 | +| train/ | | +| approx_kl | 1.3115633 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.556 | +| explained_variance | -1.99 | +| learning_rate | 0.0001 | +| loss | -0.0848 | +| n_updates | 127120 | +| policy_gradient_loss | -0.0629 | +| value_loss | 0.000795 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.21e+03 | +| ep_rew_mean | 0.265 | +| time/ | | +| fps | 309 | +| iterations | 6661 | +| time_elapsed | 22031 | +| total_timesteps | 6820864 | +| train/ | | +| approx_kl | 1.6461178 | +| clip_fraction | 0.506 | +| clip_range | 0.2 | +| entropy_loss | -0.507 | +| explained_variance | -7 | +| learning_rate | 0.0001 | +| loss | -0.0951 | +| n_updates | 127130 | +| policy_gradient_loss | -0.0776 | +| value_loss | 0.00046 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.19e+03 | +| ep_rew_mean | 0.262 | +| time/ | | +| fps | 309 | +| iterations | 6662 | +| time_elapsed | 22034 | +| total_timesteps | 6821888 | +| train/ | | +| approx_kl | 1.7974527 | +| clip_fraction | 0.505 | +| clip_range | 0.2 | +| entropy_loss | -0.577 | +| explained_variance | -1 | +| learning_rate | 0.0001 | +| loss | -0.0882 | +| n_updates | 127140 | +| policy_gradient_loss | -0.0644 | +| value_loss | 0.00046 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.19e+03 | +| ep_rew_mean | 0.262 | +| time/ | | +| fps | 309 | +| iterations | 6663 | +| time_elapsed | 22038 | +| total_timesteps | 6822912 | +| train/ | | +| approx_kl | 1.4649597 | +| clip_fraction | 0.492 | +| clip_range | 0.2 | +| entropy_loss | -0.566 | +| explained_variance | -1.08 | +| learning_rate | 0.0001 | +| loss | -0.0819 | +| n_updates | 127150 | +| policy_gradient_loss | -0.076 | +| value_loss | 0.000362 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.18e+03 | +| ep_rew_mean | 0.262 | +| time/ | | +| fps | 309 | +| iterations | 6664 | +| time_elapsed | 22041 | +| total_timesteps | 6823936 | +| train/ | | +| approx_kl | 1.4242524 | +| clip_fraction | 0.533 | +| clip_range | 0.2 | +| entropy_loss | -0.643 | +| explained_variance | -0.859 | +| learning_rate | 0.0001 | +| loss | -0.0599 | +| n_updates | 127160 | +| policy_gradient_loss | -0.0665 | +| value_loss | 0.000282 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.18e+03 | +| ep_rew_mean | 0.255 | +| time/ | | +| fps | 309 | +| iterations | 6665 | +| time_elapsed | 22044 | +| total_timesteps | 6824960 | +| train/ | | +| approx_kl | 1.4364873 | +| clip_fraction | 0.511 | +| clip_range | 0.2 | +| entropy_loss | -0.589 | +| explained_variance | -1.22 | +| learning_rate | 0.0001 | +| loss | -0.0923 | +| n_updates | 127170 | +| policy_gradient_loss | -0.068 | +| value_loss | 0.000471 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.18e+03 | +| ep_rew_mean | 0.255 | +| time/ | | +| fps | 309 | +| iterations | 6666 | +| time_elapsed | 22047 | +| total_timesteps | 6825984 | +| train/ | | +| approx_kl | 1.874748 | +| clip_fraction | 0.509 | +| clip_range | 0.2 | +| entropy_loss | -0.535 | +| explained_variance | -2.37 | +| learning_rate | 0.0001 | +| loss | -0.0723 | +| n_updates | 127180 | +| policy_gradient_loss | -0.069 | +| value_loss | 0.000575 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.17e+03 | +| ep_rew_mean | 0.254 | +| time/ | | +| fps | 309 | +| iterations | 6667 | +| time_elapsed | 22050 | +| total_timesteps | 6827008 | +| train/ | | +| approx_kl | 1.4150307 | +| clip_fraction | 0.533 | +| clip_range | 0.2 | +| entropy_loss | -0.605 | +| explained_variance | -3.84 | +| learning_rate | 0.0001 | +| loss | -0.117 | +| n_updates | 127190 | +| policy_gradient_loss | -0.0777 | +| value_loss | 0.000557 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.17e+03 | +| ep_rew_mean | 0.252 | +| time/ | | +| fps | 309 | +| iterations | 6668 | +| time_elapsed | 22054 | +| total_timesteps | 6828032 | +| train/ | | +| approx_kl | 1.1257458 | +| clip_fraction | 0.522 | +| clip_range | 0.2 | +| entropy_loss | -0.598 | +| explained_variance | -5.58 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 127200 | +| policy_gradient_loss | -0.0755 | +| value_loss | 0.000642 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.17e+03 | +| ep_rew_mean | 0.252 | +| time/ | | +| fps | 309 | +| iterations | 6669 | +| time_elapsed | 22057 | +| total_timesteps | 6829056 | +| train/ | | +| approx_kl | 1.8136754 | +| clip_fraction | 0.515 | +| clip_range | 0.2 | +| entropy_loss | -0.618 | +| explained_variance | -2.86 | +| learning_rate | 0.0001 | +| loss | -0.0739 | +| n_updates | 127210 | +| policy_gradient_loss | -0.0605 | +| value_loss | 0.000506 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.17e+03 | +| ep_rew_mean | 0.244 | +| time/ | | +| fps | 309 | +| iterations | 6670 | +| time_elapsed | 22060 | +| total_timesteps | 6830080 | +| train/ | | +| approx_kl | 1.2954459 | +| clip_fraction | 0.524 | +| clip_range | 0.2 | +| entropy_loss | -0.631 | +| explained_variance | -6.31 | +| learning_rate | 0.0001 | +| loss | -0.114 | +| n_updates | 127220 | +| policy_gradient_loss | -0.0708 | +| value_loss | 0.000244 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.17e+03 | +| ep_rew_mean | 0.244 | +| time/ | | +| fps | 309 | +| iterations | 6671 | +| time_elapsed | 22063 | +| total_timesteps | 6831104 | +| train/ | | +| approx_kl | 1.4888177 | +| clip_fraction | 0.51 | +| clip_range | 0.2 | +| entropy_loss | -0.573 | +| explained_variance | -0.806 | +| learning_rate | 0.0001 | +| loss | -0.0958 | +| n_updates | 127230 | +| policy_gradient_loss | -0.0626 | +| value_loss | 0.000448 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.17e+03 | +| ep_rew_mean | 0.237 | +| time/ | | +| fps | 309 | +| iterations | 6672 | +| time_elapsed | 22067 | +| total_timesteps | 6832128 | +| train/ | | +| approx_kl | 1.2172415 | +| clip_fraction | 0.543 | +| clip_range | 0.2 | +| entropy_loss | -0.728 | +| explained_variance | -6.74 | +| learning_rate | 0.0001 | +| loss | -0.0906 | +| n_updates | 127240 | +| policy_gradient_loss | -0.064 | +| value_loss | 0.000659 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.16e+03 | +| ep_rew_mean | 0.232 | +| time/ | | +| fps | 309 | +| iterations | 6673 | +| time_elapsed | 22070 | +| total_timesteps | 6833152 | +| train/ | | +| approx_kl | 2.088946 | +| clip_fraction | 0.497 | +| clip_range | 0.2 | +| entropy_loss | -0.563 | +| explained_variance | -3.01 | +| learning_rate | 0.0001 | +| loss | -0.0871 | +| n_updates | 127250 | +| policy_gradient_loss | -0.0694 | +| value_loss | 0.000447 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.16e+03 | +| ep_rew_mean | 0.232 | +| time/ | | +| fps | 309 | +| iterations | 6674 | +| time_elapsed | 22074 | +| total_timesteps | 6834176 | +| train/ | | +| approx_kl | 1.3285675 | +| clip_fraction | 0.5 | +| clip_range | 0.2 | +| entropy_loss | -0.591 | +| explained_variance | -1.34 | +| learning_rate | 0.0001 | +| loss | -0.0838 | +| n_updates | 127260 | +| policy_gradient_loss | -0.063 | +| value_loss | 0.000745 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.16e+03 | +| ep_rew_mean | 0.228 | +| time/ | | +| fps | 309 | +| iterations | 6675 | +| time_elapsed | 22078 | +| total_timesteps | 6835200 | +| train/ | | +| approx_kl | 1.5971758 | +| clip_fraction | 0.548 | +| clip_range | 0.2 | +| entropy_loss | -0.679 | +| explained_variance | -6.01 | +| learning_rate | 0.0001 | +| loss | -0.0797 | +| n_updates | 127270 | +| policy_gradient_loss | -0.0704 | +| value_loss | 0.000625 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.15e+03 | +| ep_rew_mean | 0.227 | +| time/ | | +| fps | 309 | +| iterations | 6676 | +| time_elapsed | 22081 | +| total_timesteps | 6836224 | +| train/ | | +| approx_kl | 1.3733048 | +| clip_fraction | 0.54 | +| clip_range | 0.2 | +| entropy_loss | -0.567 | +| explained_variance | -3.5 | +| learning_rate | 0.0001 | +| loss | -0.0792 | +| n_updates | 127280 | +| policy_gradient_loss | -0.0751 | +| value_loss | 0.000888 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.15e+03 | +| ep_rew_mean | 0.227 | +| time/ | | +| fps | 309 | +| iterations | 6677 | +| time_elapsed | 22085 | +| total_timesteps | 6837248 | +| train/ | | +| approx_kl | 2.8668084 | +| clip_fraction | 0.488 | +| clip_range | 0.2 | +| entropy_loss | -0.525 | +| explained_variance | -4.26 | +| learning_rate | 0.0001 | +| loss | -0.0804 | +| n_updates | 127290 | +| policy_gradient_loss | -0.0698 | +| value_loss | 0.000632 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.15e+03 | +| ep_rew_mean | 0.227 | +| time/ | | +| fps | 309 | +| iterations | 6678 | +| time_elapsed | 22088 | +| total_timesteps | 6838272 | +| train/ | | +| approx_kl | 1.2615021 | +| clip_fraction | 0.543 | +| clip_range | 0.2 | +| entropy_loss | -0.76 | +| explained_variance | -1.22 | +| learning_rate | 0.0001 | +| loss | -0.0973 | +| n_updates | 127300 | +| policy_gradient_loss | -0.0739 | +| value_loss | 0.000747 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.15e+03 | +| ep_rew_mean | 0.227 | +| time/ | | +| fps | 309 | +| iterations | 6679 | +| time_elapsed | 22091 | +| total_timesteps | 6839296 | +| train/ | | +| approx_kl | 1.709512 | +| clip_fraction | 0.546 | +| clip_range | 0.2 | +| entropy_loss | -0.662 | +| explained_variance | -3.38 | +| learning_rate | 0.0001 | +| loss | -0.0676 | +| n_updates | 127310 | +| policy_gradient_loss | -0.074 | +| value_loss | 0.000469 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.14e+03 | +| ep_rew_mean | 0.224 | +| time/ | | +| fps | 309 | +| iterations | 6680 | +| time_elapsed | 22094 | +| total_timesteps | 6840320 | +| train/ | | +| approx_kl | 3.262104 | +| clip_fraction | 0.524 | +| clip_range | 0.2 | +| entropy_loss | -0.705 | +| explained_variance | -4.07 | +| learning_rate | 0.0001 | +| loss | -0.0841 | +| n_updates | 127320 | +| policy_gradient_loss | -0.0708 | +| value_loss | 0.000515 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.14e+03 | +| ep_rew_mean | 0.224 | +| time/ | | +| fps | 309 | +| iterations | 6681 | +| time_elapsed | 22097 | +| total_timesteps | 6841344 | +| train/ | | +| approx_kl | 2.7744308 | +| clip_fraction | 0.49 | +| clip_range | 0.2 | +| entropy_loss | -0.533 | +| explained_variance | -3.36 | +| learning_rate | 0.0001 | +| loss | -0.0838 | +| n_updates | 127330 | +| policy_gradient_loss | -0.0741 | +| value_loss | 0.00034 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.15e+03 | +| ep_rew_mean | 0.223 | +| time/ | | +| fps | 309 | +| iterations | 6682 | +| time_elapsed | 22101 | +| total_timesteps | 6842368 | +| train/ | | +| approx_kl | 1.6258274 | +| clip_fraction | 0.53 | +| clip_range | 0.2 | +| entropy_loss | -0.58 | +| explained_variance | -2.91 | +| learning_rate | 0.0001 | +| loss | -0.0576 | +| n_updates | 127340 | +| policy_gradient_loss | -0.0709 | +| value_loss | 0.000452 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.15e+03 | +| ep_rew_mean | 0.223 | +| time/ | | +| fps | 309 | +| iterations | 6683 | +| time_elapsed | 22104 | +| total_timesteps | 6843392 | +| train/ | | +| approx_kl | 1.5921253 | +| clip_fraction | 0.502 | +| clip_range | 0.2 | +| entropy_loss | -0.587 | +| explained_variance | -1.04 | +| learning_rate | 0.0001 | +| loss | -0.0682 | +| n_updates | 127350 | +| policy_gradient_loss | -0.0686 | +| value_loss | 0.000559 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.12e+03 | +| ep_rew_mean | 0.223 | +| time/ | | +| fps | 309 | +| iterations | 6684 | +| time_elapsed | 22107 | +| total_timesteps | 6844416 | +| train/ | | +| approx_kl | 1.5605264 | +| clip_fraction | 0.521 | +| clip_range | 0.2 | +| entropy_loss | -0.659 | +| explained_variance | -2.76 | +| learning_rate | 0.0001 | +| loss | -0.095 | +| n_updates | 127360 | +| policy_gradient_loss | -0.0767 | +| value_loss | 0.000583 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.12e+03 | +| ep_rew_mean | 0.214 | +| time/ | | +| fps | 309 | +| iterations | 6685 | +| time_elapsed | 22110 | +| total_timesteps | 6845440 | +| train/ | | +| approx_kl | 1.7969282 | +| clip_fraction | 0.493 | +| clip_range | 0.2 | +| entropy_loss | -0.554 | +| explained_variance | -3.78 | +| learning_rate | 0.0001 | +| loss | -0.0937 | +| n_updates | 127370 | +| policy_gradient_loss | -0.072 | +| value_loss | 0.000444 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.11e+03 | +| ep_rew_mean | 0.211 | +| time/ | | +| fps | 309 | +| iterations | 6686 | +| time_elapsed | 22113 | +| total_timesteps | 6846464 | +| train/ | | +| approx_kl | 1.3391769 | +| clip_fraction | 0.476 | +| clip_range | 0.2 | +| entropy_loss | -0.651 | +| explained_variance | -0.284 | +| learning_rate | 0.0001 | +| loss | -0.0796 | +| n_updates | 127380 | +| policy_gradient_loss | -0.062 | +| value_loss | 0.000866 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.11e+03 | +| ep_rew_mean | 0.205 | +| time/ | | +| fps | 309 | +| iterations | 6687 | +| time_elapsed | 22117 | +| total_timesteps | 6847488 | +| train/ | | +| approx_kl | 1.598105 | +| clip_fraction | 0.439 | +| clip_range | 0.2 | +| entropy_loss | -0.473 | +| explained_variance | -3.65 | +| learning_rate | 0.0001 | +| loss | -0.0847 | +| n_updates | 127390 | +| policy_gradient_loss | -0.0556 | +| value_loss | 0.000647 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.11e+03 | +| ep_rew_mean | 0.205 | +| time/ | | +| fps | 309 | +| iterations | 6688 | +| time_elapsed | 22120 | +| total_timesteps | 6848512 | +| train/ | | +| approx_kl | 1.2845793 | +| clip_fraction | 0.502 | +| clip_range | 0.2 | +| entropy_loss | -0.541 | +| explained_variance | -3.4 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 127400 | +| policy_gradient_loss | -0.0726 | +| value_loss | 0.000628 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.11e+03 | +| ep_rew_mean | 0.201 | +| time/ | | +| fps | 309 | +| iterations | 6689 | +| time_elapsed | 22123 | +| total_timesteps | 6849536 | +| train/ | | +| approx_kl | 1.4429426 | +| clip_fraction | 0.516 | +| clip_range | 0.2 | +| entropy_loss | -0.662 | +| explained_variance | -4.14 | +| learning_rate | 0.0001 | +| loss | -0.0681 | +| n_updates | 127410 | +| policy_gradient_loss | -0.0647 | +| value_loss | 0.000252 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.11e+03 | +| ep_rew_mean | 0.194 | +| time/ | | +| fps | 309 | +| iterations | 6690 | +| time_elapsed | 22126 | +| total_timesteps | 6850560 | +| train/ | | +| approx_kl | 1.2194388 | +| clip_fraction | 0.482 | +| clip_range | 0.2 | +| entropy_loss | -0.602 | +| explained_variance | -0.837 | +| learning_rate | 0.0001 | +| loss | -0.0857 | +| n_updates | 127420 | +| policy_gradient_loss | -0.0628 | +| value_loss | 0.000799 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.11e+03 | +| ep_rew_mean | 0.194 | +| time/ | | +| fps | 309 | +| iterations | 6691 | +| time_elapsed | 22130 | +| total_timesteps | 6851584 | +| train/ | | +| approx_kl | 2.226151 | +| clip_fraction | 0.491 | +| clip_range | 0.2 | +| entropy_loss | -0.546 | +| explained_variance | -4.17 | +| learning_rate | 0.0001 | +| loss | -0.0551 | +| n_updates | 127430 | +| policy_gradient_loss | -0.0616 | +| value_loss | 0.000425 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.1e+03 | +| ep_rew_mean | 0.194 | +| time/ | | +| fps | 309 | +| iterations | 6692 | +| time_elapsed | 22133 | +| total_timesteps | 6852608 | +| train/ | | +| approx_kl | 1.5282719 | +| clip_fraction | 0.516 | +| clip_range | 0.2 | +| entropy_loss | -0.53 | +| explained_variance | -1.16 | +| learning_rate | 0.0001 | +| loss | -0.0982 | +| n_updates | 127440 | +| policy_gradient_loss | -0.0751 | +| value_loss | 0.000544 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.1e+03 | +| ep_rew_mean | 0.195 | +| time/ | | +| fps | 309 | +| iterations | 6693 | +| time_elapsed | 22136 | +| total_timesteps | 6853632 | +| train/ | | +| approx_kl | 1.7760401 | +| clip_fraction | 0.512 | +| clip_range | 0.2 | +| entropy_loss | -0.559 | +| explained_variance | -1.65 | +| learning_rate | 0.0001 | +| loss | -0.0684 | +| n_updates | 127450 | +| policy_gradient_loss | -0.076 | +| value_loss | 0.000449 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.1e+03 | +| ep_rew_mean | 0.195 | +| time/ | | +| fps | 309 | +| iterations | 6694 | +| time_elapsed | 22140 | +| total_timesteps | 6854656 | +| train/ | | +| approx_kl | 1.4131439 | +| clip_fraction | 0.495 | +| clip_range | 0.2 | +| entropy_loss | -0.619 | +| explained_variance | -5.73 | +| learning_rate | 0.0001 | +| loss | -0.0922 | +| n_updates | 127460 | +| policy_gradient_loss | -0.0721 | +| value_loss | 0.000528 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.11e+03 | +| ep_rew_mean | 0.187 | +| time/ | | +| fps | 309 | +| iterations | 6695 | +| time_elapsed | 22143 | +| total_timesteps | 6855680 | +| train/ | | +| approx_kl | 1.7582624 | +| clip_fraction | 0.502 | +| clip_range | 0.2 | +| entropy_loss | -0.551 | +| explained_variance | -1.34 | +| learning_rate | 0.0001 | +| loss | -0.0962 | +| n_updates | 127470 | +| policy_gradient_loss | -0.0667 | +| value_loss | 0.000391 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.11e+03 | +| ep_rew_mean | 0.187 | +| time/ | | +| fps | 309 | +| iterations | 6696 | +| time_elapsed | 22146 | +| total_timesteps | 6856704 | +| train/ | | +| approx_kl | 1.7850535 | +| clip_fraction | 0.499 | +| clip_range | 0.2 | +| entropy_loss | -0.472 | +| explained_variance | -1.88 | +| learning_rate | 0.0001 | +| loss | -0.0881 | +| n_updates | 127480 | +| policy_gradient_loss | -0.067 | +| value_loss | 0.000448 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.1e+03 | +| ep_rew_mean | 0.187 | +| time/ | | +| fps | 309 | +| iterations | 6697 | +| time_elapsed | 22149 | +| total_timesteps | 6857728 | +| train/ | | +| approx_kl | 1.5658712 | +| clip_fraction | 0.525 | +| clip_range | 0.2 | +| entropy_loss | -0.605 | +| explained_variance | -1.47 | +| learning_rate | 0.0001 | +| loss | -0.0853 | +| n_updates | 127490 | +| policy_gradient_loss | -0.0735 | +| value_loss | 0.000569 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.1e+03 | +| ep_rew_mean | 0.187 | +| time/ | | +| fps | 309 | +| iterations | 6698 | +| time_elapsed | 22153 | +| total_timesteps | 6858752 | +| train/ | | +| approx_kl | 1.6225744 | +| clip_fraction | 0.492 | +| clip_range | 0.2 | +| entropy_loss | -0.609 | +| explained_variance | -3.39 | +| learning_rate | 0.0001 | +| loss | -0.0936 | +| n_updates | 127500 | +| policy_gradient_loss | -0.062 | +| value_loss | 0.000533 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.09e+03 | +| ep_rew_mean | 0.19 | +| time/ | | +| fps | 309 | +| iterations | 6699 | +| time_elapsed | 22156 | +| total_timesteps | 6859776 | +| train/ | | +| approx_kl | 1.5338719 | +| clip_fraction | 0.511 | +| clip_range | 0.2 | +| entropy_loss | -0.554 | +| explained_variance | -1.92 | +| learning_rate | 0.0001 | +| loss | -0.0706 | +| n_updates | 127510 | +| policy_gradient_loss | -0.0664 | +| value_loss | 0.000762 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.09e+03 | +| ep_rew_mean | 0.185 | +| time/ | | +| fps | 309 | +| iterations | 6700 | +| time_elapsed | 22159 | +| total_timesteps | 6860800 | +| train/ | | +| approx_kl | 1.5382513 | +| clip_fraction | 0.485 | +| clip_range | 0.2 | +| entropy_loss | -0.497 | +| explained_variance | -2.68 | +| learning_rate | 0.0001 | +| loss | -0.0526 | +| n_updates | 127520 | +| policy_gradient_loss | -0.0662 | +| value_loss | 0.000538 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.09e+03 | +| ep_rew_mean | 0.185 | +| time/ | | +| fps | 309 | +| iterations | 6701 | +| time_elapsed | 22162 | +| total_timesteps | 6861824 | +| train/ | | +| approx_kl | 1.7758012 | +| clip_fraction | 0.466 | +| clip_range | 0.2 | +| entropy_loss | -0.454 | +| explained_variance | -2.59 | +| learning_rate | 0.0001 | +| loss | -0.0858 | +| n_updates | 127530 | +| policy_gradient_loss | -0.0628 | +| value_loss | 0.000687 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.09e+03 | +| ep_rew_mean | 0.18 | +| time/ | | +| fps | 309 | +| iterations | 6702 | +| time_elapsed | 22165 | +| total_timesteps | 6862848 | +| train/ | | +| approx_kl | 1.3288264 | +| clip_fraction | 0.52 | +| clip_range | 0.2 | +| entropy_loss | -0.699 | +| explained_variance | -3.59 | +| learning_rate | 0.0001 | +| loss | -0.0884 | +| n_updates | 127540 | +| policy_gradient_loss | -0.0644 | +| value_loss | 0.000446 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.09e+03 | +| ep_rew_mean | 0.18 | +| time/ | | +| fps | 309 | +| iterations | 6703 | +| time_elapsed | 22168 | +| total_timesteps | 6863872 | +| train/ | | +| approx_kl | 1.5636635 | +| clip_fraction | 0.451 | +| clip_range | 0.2 | +| entropy_loss | -0.46 | +| explained_variance | -2.25 | +| learning_rate | 0.0001 | +| loss | -0.0754 | +| n_updates | 127550 | +| policy_gradient_loss | -0.0614 | +| value_loss | 0.000909 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.08e+03 | +| ep_rew_mean | 0.178 | +| time/ | | +| fps | 309 | +| iterations | 6704 | +| time_elapsed | 22172 | +| total_timesteps | 6864896 | +| train/ | | +| approx_kl | 1.9836235 | +| clip_fraction | 0.531 | +| clip_range | 0.2 | +| entropy_loss | -0.638 | +| explained_variance | -3.45 | +| learning_rate | 0.0001 | +| loss | -0.0815 | +| n_updates | 127560 | +| policy_gradient_loss | -0.0694 | +| value_loss | 0.000581 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.08e+03 | +| ep_rew_mean | 0.178 | +| time/ | | +| fps | 309 | +| iterations | 6705 | +| time_elapsed | 22175 | +| total_timesteps | 6865920 | +| train/ | | +| approx_kl | 1.3391323 | +| clip_fraction | 0.534 | +| clip_range | 0.2 | +| entropy_loss | -0.692 | +| explained_variance | -1.59 | +| learning_rate | 0.0001 | +| loss | -0.082 | +| n_updates | 127570 | +| policy_gradient_loss | -0.0666 | +| value_loss | 0.000599 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.08e+03 | +| ep_rew_mean | 0.18 | +| time/ | | +| fps | 309 | +| iterations | 6706 | +| time_elapsed | 22178 | +| total_timesteps | 6866944 | +| train/ | | +| approx_kl | 1.5359179 | +| clip_fraction | 0.538 | +| clip_range | 0.2 | +| entropy_loss | -0.572 | +| explained_variance | -3.12 | +| learning_rate | 0.0001 | +| loss | -0.0889 | +| n_updates | 127580 | +| policy_gradient_loss | -0.0691 | +| value_loss | 0.000474 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.08e+03 | +| ep_rew_mean | 0.18 | +| time/ | | +| fps | 309 | +| iterations | 6707 | +| time_elapsed | 22181 | +| total_timesteps | 6867968 | +| train/ | | +| approx_kl | 1.716372 | +| clip_fraction | 0.537 | +| clip_range | 0.2 | +| entropy_loss | -0.545 | +| explained_variance | -1.06 | +| learning_rate | 0.0001 | +| loss | -0.0894 | +| n_updates | 127590 | +| policy_gradient_loss | -0.0704 | +| value_loss | 0.000624 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.09e+03 | +| ep_rew_mean | 0.184 | +| time/ | | +| fps | 309 | +| iterations | 6708 | +| time_elapsed | 22185 | +| total_timesteps | 6868992 | +| train/ | | +| approx_kl | 1.659661 | +| clip_fraction | 0.507 | +| clip_range | 0.2 | +| entropy_loss | -0.542 | +| explained_variance | -2.41 | +| learning_rate | 0.0001 | +| loss | -0.0723 | +| n_updates | 127600 | +| policy_gradient_loss | -0.0595 | +| value_loss | 0.000854 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.09e+03 | +| ep_rew_mean | 0.184 | +| time/ | | +| fps | 309 | +| iterations | 6709 | +| time_elapsed | 22188 | +| total_timesteps | 6870016 | +| train/ | | +| approx_kl | 2.8614173 | +| clip_fraction | 0.507 | +| clip_range | 0.2 | +| entropy_loss | -0.506 | +| explained_variance | -3.24 | +| learning_rate | 0.0001 | +| loss | -0.0864 | +| n_updates | 127610 | +| policy_gradient_loss | -0.0688 | +| value_loss | 0.000551 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.08e+03 | +| ep_rew_mean | 0.181 | +| time/ | | +| fps | 309 | +| iterations | 6710 | +| time_elapsed | 22192 | +| total_timesteps | 6871040 | +| train/ | | +| approx_kl | 2.2552986 | +| clip_fraction | 0.529 | +| clip_range | 0.2 | +| entropy_loss | -0.611 | +| explained_variance | -2.3 | +| learning_rate | 0.0001 | +| loss | -0.087 | +| n_updates | 127620 | +| policy_gradient_loss | -0.0766 | +| value_loss | 0.000501 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.08e+03 | +| ep_rew_mean | 0.181 | +| time/ | | +| fps | 309 | +| iterations | 6711 | +| time_elapsed | 22195 | +| total_timesteps | 6872064 | +| train/ | | +| approx_kl | 1.3204403 | +| clip_fraction | 0.513 | +| clip_range | 0.2 | +| entropy_loss | -0.709 | +| explained_variance | -6.2 | +| learning_rate | 0.0001 | +| loss | -0.106 | +| n_updates | 127630 | +| policy_gradient_loss | -0.0668 | +| value_loss | 0.000153 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.07e+03 | +| ep_rew_mean | 0.18 | +| time/ | | +| fps | 309 | +| iterations | 6712 | +| time_elapsed | 22199 | +| total_timesteps | 6873088 | +| train/ | | +| approx_kl | 1.5044907 | +| clip_fraction | 0.548 | +| clip_range | 0.2 | +| entropy_loss | -0.667 | +| explained_variance | -0.813 | +| learning_rate | 0.0001 | +| loss | -0.0992 | +| n_updates | 127640 | +| policy_gradient_loss | -0.0736 | +| value_loss | 0.000427 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.05e+03 | +| ep_rew_mean | 0.175 | +| time/ | | +| fps | 309 | +| iterations | 6713 | +| time_elapsed | 22202 | +| total_timesteps | 6874112 | +| train/ | | +| approx_kl | 1.3128846 | +| clip_fraction | 0.54 | +| clip_range | 0.2 | +| entropy_loss | -0.724 | +| explained_variance | -3.53 | +| learning_rate | 0.0001 | +| loss | -0.0581 | +| n_updates | 127650 | +| policy_gradient_loss | -0.0702 | +| value_loss | 0.000324 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.05e+03 | +| ep_rew_mean | 0.175 | +| time/ | | +| fps | 309 | +| iterations | 6714 | +| time_elapsed | 22206 | +| total_timesteps | 6875136 | +| train/ | | +| approx_kl | 1.3155483 | +| clip_fraction | 0.504 | +| clip_range | 0.2 | +| entropy_loss | -0.615 | +| explained_variance | -6.11 | +| learning_rate | 0.0001 | +| loss | -0.0432 | +| n_updates | 127660 | +| policy_gradient_loss | -0.0645 | +| value_loss | 0.000644 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.05e+03 | +| ep_rew_mean | 0.168 | +| time/ | | +| fps | 309 | +| iterations | 6715 | +| time_elapsed | 22209 | +| total_timesteps | 6876160 | +| train/ | | +| approx_kl | 1.5878445 | +| clip_fraction | 0.525 | +| clip_range | 0.2 | +| entropy_loss | -0.573 | +| explained_variance | -3.19 | +| learning_rate | 0.0001 | +| loss | -0.0784 | +| n_updates | 127670 | +| policy_gradient_loss | -0.0693 | +| value_loss | 0.000463 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.05e+03 | +| ep_rew_mean | 0.168 | +| time/ | | +| fps | 309 | +| iterations | 6716 | +| time_elapsed | 22212 | +| total_timesteps | 6877184 | +| train/ | | +| approx_kl | 5.299161 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.485 | +| explained_variance | -2.6 | +| learning_rate | 0.0001 | +| loss | -0.0939 | +| n_updates | 127680 | +| policy_gradient_loss | -0.0682 | +| value_loss | 0.000427 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.04e+03 | +| ep_rew_mean | 0.169 | +| time/ | | +| fps | 309 | +| iterations | 6717 | +| time_elapsed | 22215 | +| total_timesteps | 6878208 | +| train/ | | +| approx_kl | 1.6511871 | +| clip_fraction | 0.522 | +| clip_range | 0.2 | +| entropy_loss | -0.601 | +| explained_variance | -2.61 | +| learning_rate | 0.0001 | +| loss | -0.106 | +| n_updates | 127690 | +| policy_gradient_loss | -0.0672 | +| value_loss | 0.00037 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.03e+03 | +| ep_rew_mean | 0.173 | +| time/ | | +| fps | 309 | +| iterations | 6718 | +| time_elapsed | 22219 | +| total_timesteps | 6879232 | +| train/ | | +| approx_kl | 1.777293 | +| clip_fraction | 0.515 | +| clip_range | 0.2 | +| entropy_loss | -0.545 | +| explained_variance | -0.695 | +| learning_rate | 0.0001 | +| loss | -0.0923 | +| n_updates | 127700 | +| policy_gradient_loss | -0.0681 | +| value_loss | 0.000588 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.03e+03 | +| ep_rew_mean | 0.173 | +| time/ | | +| fps | 309 | +| iterations | 6719 | +| time_elapsed | 22222 | +| total_timesteps | 6880256 | +| train/ | | +| approx_kl | 1.6250036 | +| clip_fraction | 0.516 | +| clip_range | 0.2 | +| entropy_loss | -0.604 | +| explained_variance | -1.81 | +| learning_rate | 0.0001 | +| loss | -0.0553 | +| n_updates | 127710 | +| policy_gradient_loss | -0.0709 | +| value_loss | 0.000509 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.03e+03 | +| ep_rew_mean | 0.173 | +| time/ | | +| fps | 309 | +| iterations | 6720 | +| time_elapsed | 22225 | +| total_timesteps | 6881280 | +| train/ | | +| approx_kl | 1.471776 | +| clip_fraction | 0.511 | +| clip_range | 0.2 | +| entropy_loss | -0.603 | +| explained_variance | -1.19 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 127720 | +| policy_gradient_loss | -0.0707 | +| value_loss | 0.000612 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.03e+03 | +| ep_rew_mean | 0.173 | +| time/ | | +| fps | 309 | +| iterations | 6721 | +| time_elapsed | 22228 | +| total_timesteps | 6882304 | +| train/ | | +| approx_kl | 1.9819245 | +| clip_fraction | 0.493 | +| clip_range | 0.2 | +| entropy_loss | -0.564 | +| explained_variance | -3.05 | +| learning_rate | 0.0001 | +| loss | -0.109 | +| n_updates | 127730 | +| policy_gradient_loss | -0.0727 | +| value_loss | 0.000463 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.03e+03 | +| ep_rew_mean | 0.175 | +| time/ | | +| fps | 309 | +| iterations | 6722 | +| time_elapsed | 22231 | +| total_timesteps | 6883328 | +| train/ | | +| approx_kl | 1.6661866 | +| clip_fraction | 0.533 | +| clip_range | 0.2 | +| entropy_loss | -0.669 | +| explained_variance | -1.53 | +| learning_rate | 0.0001 | +| loss | -0.0899 | +| n_updates | 127740 | +| policy_gradient_loss | -0.0743 | +| value_loss | 0.000802 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.03e+03 | +| ep_rew_mean | 0.175 | +| time/ | | +| fps | 309 | +| iterations | 6723 | +| time_elapsed | 22235 | +| total_timesteps | 6884352 | +| train/ | | +| approx_kl | 1.8113596 | +| clip_fraction | 0.494 | +| clip_range | 0.2 | +| entropy_loss | -0.523 | +| explained_variance | -4.85 | +| learning_rate | 0.0001 | +| loss | -0.075 | +| n_updates | 127750 | +| policy_gradient_loss | -0.0716 | +| value_loss | 0.000704 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.03e+03 | +| ep_rew_mean | 0.175 | +| time/ | | +| fps | 309 | +| iterations | 6724 | +| time_elapsed | 22238 | +| total_timesteps | 6885376 | +| train/ | | +| approx_kl | 2.3618546 | +| clip_fraction | 0.516 | +| clip_range | 0.2 | +| entropy_loss | -0.578 | +| explained_variance | -5.34 | +| learning_rate | 0.0001 | +| loss | -0.0925 | +| n_updates | 127760 | +| policy_gradient_loss | -0.0685 | +| value_loss | 0.000598 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.03e+03 | +| ep_rew_mean | 0.176 | +| time/ | | +| fps | 309 | +| iterations | 6725 | +| time_elapsed | 22241 | +| total_timesteps | 6886400 | +| train/ | | +| approx_kl | 1.5195799 | +| clip_fraction | 0.524 | +| clip_range | 0.2 | +| entropy_loss | -0.597 | +| explained_variance | -3.07 | +| learning_rate | 0.0001 | +| loss | -0.0901 | +| n_updates | 127770 | +| policy_gradient_loss | -0.0581 | +| value_loss | 0.00103 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.03e+03 | +| ep_rew_mean | 0.176 | +| time/ | | +| fps | 309 | +| iterations | 6726 | +| time_elapsed | 22245 | +| total_timesteps | 6887424 | +| train/ | | +| approx_kl | 1.6236444 | +| clip_fraction | 0.497 | +| clip_range | 0.2 | +| entropy_loss | -0.558 | +| explained_variance | -3.85 | +| learning_rate | 0.0001 | +| loss | -0.0818 | +| n_updates | 127780 | +| policy_gradient_loss | -0.067 | +| value_loss | 0.000651 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.03e+03 | +| ep_rew_mean | 0.176 | +| time/ | | +| fps | 309 | +| iterations | 6727 | +| time_elapsed | 22249 | +| total_timesteps | 6888448 | +| train/ | | +| approx_kl | 1.9699821 | +| clip_fraction | 0.533 | +| clip_range | 0.2 | +| entropy_loss | -0.655 | +| explained_variance | -3.04 | +| learning_rate | 0.0001 | +| loss | -0.113 | +| n_updates | 127790 | +| policy_gradient_loss | -0.077 | +| value_loss | 0.000263 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.05e+03 | +| ep_rew_mean | 0.172 | +| time/ | | +| fps | 309 | +| iterations | 6728 | +| time_elapsed | 22252 | +| total_timesteps | 6889472 | +| train/ | | +| approx_kl | 1.3352003 | +| clip_fraction | 0.54 | +| clip_range | 0.2 | +| entropy_loss | -0.603 | +| explained_variance | -5.19 | +| learning_rate | 0.0001 | +| loss | -0.106 | +| n_updates | 127800 | +| policy_gradient_loss | -0.068 | +| value_loss | 0.00024 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.05e+03 | +| ep_rew_mean | 0.172 | +| time/ | | +| fps | 309 | +| iterations | 6729 | +| time_elapsed | 22256 | +| total_timesteps | 6890496 | +| train/ | | +| approx_kl | 1.82288 | +| clip_fraction | 0.498 | +| clip_range | 0.2 | +| entropy_loss | -0.509 | +| explained_variance | -1.77 | +| learning_rate | 0.0001 | +| loss | -0.0986 | +| n_updates | 127810 | +| policy_gradient_loss | -0.0742 | +| value_loss | 0.000602 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.05e+03 | +| ep_rew_mean | 0.169 | +| time/ | | +| fps | 309 | +| iterations | 6730 | +| time_elapsed | 22260 | +| total_timesteps | 6891520 | +| train/ | | +| approx_kl | 1.705991 | +| clip_fraction | 0.531 | +| clip_range | 0.2 | +| entropy_loss | -0.578 | +| explained_variance | -5.67 | +| learning_rate | 0.0001 | +| loss | -0.0927 | +| n_updates | 127820 | +| policy_gradient_loss | -0.0738 | +| value_loss | 0.000521 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.04e+03 | +| ep_rew_mean | 0.173 | +| time/ | | +| fps | 309 | +| iterations | 6731 | +| time_elapsed | 22263 | +| total_timesteps | 6892544 | +| train/ | | +| approx_kl | 1.6389365 | +| clip_fraction | 0.537 | +| clip_range | 0.2 | +| entropy_loss | -0.602 | +| explained_variance | -1.08 | +| learning_rate | 0.0001 | +| loss | -0.0581 | +| n_updates | 127830 | +| policy_gradient_loss | -0.0714 | +| value_loss | 0.000542 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.03e+03 | +| ep_rew_mean | 0.167 | +| time/ | | +| fps | 309 | +| iterations | 6732 | +| time_elapsed | 22267 | +| total_timesteps | 6893568 | +| train/ | | +| approx_kl | 1.4821984 | +| clip_fraction | 0.485 | +| clip_range | 0.2 | +| entropy_loss | -0.544 | +| explained_variance | -0.759 | +| learning_rate | 0.0001 | +| loss | -0.0705 | +| n_updates | 127840 | +| policy_gradient_loss | -0.0651 | +| value_loss | 0.000574 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.03e+03 | +| ep_rew_mean | 0.167 | +| time/ | | +| fps | 309 | +| iterations | 6733 | +| time_elapsed | 22270 | +| total_timesteps | 6894592 | +| train/ | | +| approx_kl | 2.6015165 | +| clip_fraction | 0.486 | +| clip_range | 0.2 | +| entropy_loss | -0.499 | +| explained_variance | -3.86 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 127850 | +| policy_gradient_loss | -0.0737 | +| value_loss | 0.000602 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.03e+03 | +| ep_rew_mean | 0.167 | +| time/ | | +| fps | 309 | +| iterations | 6734 | +| time_elapsed | 22273 | +| total_timesteps | 6895616 | +| train/ | | +| approx_kl | 1.9794873 | +| clip_fraction | 0.509 | +| clip_range | 0.2 | +| entropy_loss | -0.476 | +| explained_variance | -2.15 | +| learning_rate | 0.0001 | +| loss | -0.115 | +| n_updates | 127860 | +| policy_gradient_loss | -0.0752 | +| value_loss | 0.000592 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.98e+03 | +| ep_rew_mean | 0.166 | +| time/ | | +| fps | 309 | +| iterations | 6735 | +| time_elapsed | 22276 | +| total_timesteps | 6896640 | +| train/ | | +| approx_kl | 2.257072 | +| clip_fraction | 0.525 | +| clip_range | 0.2 | +| entropy_loss | -0.574 | +| explained_variance | -8.38 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 127870 | +| policy_gradient_loss | -0.0757 | +| value_loss | 0.000432 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.97e+03 | +| ep_rew_mean | 0.159 | +| time/ | | +| fps | 309 | +| iterations | 6736 | +| time_elapsed | 22279 | +| total_timesteps | 6897664 | +| train/ | | +| approx_kl | 1.6438428 | +| clip_fraction | 0.486 | +| clip_range | 0.2 | +| entropy_loss | -0.441 | +| explained_variance | -6.55 | +| learning_rate | 0.0001 | +| loss | -0.119 | +| n_updates | 127880 | +| policy_gradient_loss | -0.0736 | +| value_loss | 0.00058 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.97e+03 | +| ep_rew_mean | 0.159 | +| time/ | | +| fps | 309 | +| iterations | 6737 | +| time_elapsed | 22282 | +| total_timesteps | 6898688 | +| train/ | | +| approx_kl | 1.3912101 | +| clip_fraction | 0.449 | +| clip_range | 0.2 | +| entropy_loss | -0.424 | +| explained_variance | -0.823 | +| learning_rate | 0.0001 | +| loss | -0.0838 | +| n_updates | 127890 | +| policy_gradient_loss | -0.0631 | +| value_loss | 0.000784 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.96e+03 | +| ep_rew_mean | 0.16 | +| time/ | | +| fps | 309 | +| iterations | 6738 | +| time_elapsed | 22286 | +| total_timesteps | 6899712 | +| train/ | | +| approx_kl | 4.0219913 | +| clip_fraction | 0.52 | +| clip_range | 0.2 | +| entropy_loss | -0.539 | +| explained_variance | -3.16 | +| learning_rate | 0.0001 | +| loss | -0.0896 | +| n_updates | 127900 | +| policy_gradient_loss | -0.0684 | +| value_loss | 0.000804 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.96e+03 | +| ep_rew_mean | 0.16 | +| time/ | | +| fps | 309 | +| iterations | 6739 | +| time_elapsed | 22289 | +| total_timesteps | 6900736 | +| train/ | | +| approx_kl | 3.759005 | +| clip_fraction | 0.478 | +| clip_range | 0.2 | +| entropy_loss | -0.462 | +| explained_variance | -2.48 | +| learning_rate | 0.0001 | +| loss | -0.0374 | +| n_updates | 127910 | +| policy_gradient_loss | -0.0612 | +| value_loss | 0.00112 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.95e+03 | +| ep_rew_mean | 0.153 | +| time/ | | +| fps | 309 | +| iterations | 6740 | +| time_elapsed | 22292 | +| total_timesteps | 6901760 | +| train/ | | +| approx_kl | 2.206716 | +| clip_fraction | 0.476 | +| clip_range | 0.2 | +| entropy_loss | -0.448 | +| explained_variance | -8.29 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 127920 | +| policy_gradient_loss | -0.0703 | +| value_loss | 0.000564 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.95e+03 | +| ep_rew_mean | 0.153 | +| time/ | | +| fps | 309 | +| iterations | 6741 | +| time_elapsed | 22295 | +| total_timesteps | 6902784 | +| train/ | | +| approx_kl | 2.3201604 | +| clip_fraction | 0.473 | +| clip_range | 0.2 | +| entropy_loss | -0.46 | +| explained_variance | -5.81 | +| learning_rate | 0.0001 | +| loss | -0.0869 | +| n_updates | 127930 | +| policy_gradient_loss | -0.0611 | +| value_loss | 0.000315 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.95e+03 | +| ep_rew_mean | 0.149 | +| time/ | | +| fps | 309 | +| iterations | 6742 | +| time_elapsed | 22298 | +| total_timesteps | 6903808 | +| train/ | | +| approx_kl | 1.9569967 | +| clip_fraction | 0.543 | +| clip_range | 0.2 | +| entropy_loss | -0.496 | +| explained_variance | -0.797 | +| learning_rate | 0.0001 | +| loss | -0.0897 | +| n_updates | 127940 | +| policy_gradient_loss | -0.072 | +| value_loss | 0.000413 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.93e+03 | +| ep_rew_mean | 0.146 | +| time/ | | +| fps | 309 | +| iterations | 6743 | +| time_elapsed | 22302 | +| total_timesteps | 6904832 | +| train/ | | +| approx_kl | 1.9542868 | +| clip_fraction | 0.491 | +| clip_range | 0.2 | +| entropy_loss | -0.474 | +| explained_variance | -3.07 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 127950 | +| policy_gradient_loss | -0.0667 | +| value_loss | 0.000398 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.91e+03 | +| ep_rew_mean | 0.142 | +| time/ | | +| fps | 309 | +| iterations | 6744 | +| time_elapsed | 22305 | +| total_timesteps | 6905856 | +| train/ | | +| approx_kl | 1.994997 | +| clip_fraction | 0.509 | +| clip_range | 0.2 | +| entropy_loss | -0.486 | +| explained_variance | -3.56 | +| learning_rate | 0.0001 | +| loss | -0.0863 | +| n_updates | 127960 | +| policy_gradient_loss | -0.0753 | +| value_loss | 0.000415 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.91e+03 | +| ep_rew_mean | 0.142 | +| time/ | | +| fps | 309 | +| iterations | 6745 | +| time_elapsed | 22309 | +| total_timesteps | 6906880 | +| train/ | | +| approx_kl | 2.0388162 | +| clip_fraction | 0.477 | +| clip_range | 0.2 | +| entropy_loss | -0.407 | +| explained_variance | -1.92 | +| learning_rate | 0.0001 | +| loss | -0.0808 | +| n_updates | 127970 | +| policy_gradient_loss | -0.0649 | +| value_loss | 0.000656 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.9e+03 | +| ep_rew_mean | 0.137 | +| time/ | | +| fps | 309 | +| iterations | 6746 | +| time_elapsed | 22312 | +| total_timesteps | 6907904 | +| train/ | | +| approx_kl | 1.6950934 | +| clip_fraction | 0.496 | +| clip_range | 0.2 | +| entropy_loss | -0.541 | +| explained_variance | -5.7 | +| learning_rate | 0.0001 | +| loss | -0.0974 | +| n_updates | 127980 | +| policy_gradient_loss | -0.0636 | +| value_loss | 0.000559 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.9e+03 | +| ep_rew_mean | 0.137 | +| time/ | | +| fps | 309 | +| iterations | 6747 | +| time_elapsed | 22316 | +| total_timesteps | 6908928 | +| train/ | | +| approx_kl | 1.7751379 | +| clip_fraction | 0.449 | +| clip_range | 0.2 | +| entropy_loss | -0.408 | +| explained_variance | -2.97 | +| learning_rate | 0.0001 | +| loss | -0.0886 | +| n_updates | 127990 | +| policy_gradient_loss | -0.0652 | +| value_loss | 0.000404 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.9e+03 | +| ep_rew_mean | 0.134 | +| time/ | | +| fps | 309 | +| iterations | 6748 | +| time_elapsed | 22319 | +| total_timesteps | 6909952 | +| train/ | | +| approx_kl | 1.5745718 | +| clip_fraction | 0.535 | +| clip_range | 0.2 | +| entropy_loss | -0.582 | +| explained_variance | -3.91 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 128000 | +| policy_gradient_loss | -0.0783 | +| value_loss | 0.000584 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.9e+03 | +| ep_rew_mean | 0.134 | +| time/ | | +| fps | 309 | +| iterations | 6749 | +| time_elapsed | 22323 | +| total_timesteps | 6910976 | +| train/ | | +| approx_kl | 1.7199163 | +| clip_fraction | 0.479 | +| clip_range | 0.2 | +| entropy_loss | -0.465 | +| explained_variance | -3.11 | +| learning_rate | 0.0001 | +| loss | -0.0742 | +| n_updates | 128010 | +| policy_gradient_loss | -0.0677 | +| value_loss | 0.000497 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.91e+03 | +| ep_rew_mean | 0.128 | +| time/ | | +| fps | 309 | +| iterations | 6750 | +| time_elapsed | 22326 | +| total_timesteps | 6912000 | +| train/ | | +| approx_kl | 1.5530081 | +| clip_fraction | 0.505 | +| clip_range | 0.2 | +| entropy_loss | -0.499 | +| explained_variance | -3.63 | +| learning_rate | 0.0001 | +| loss | -0.106 | +| n_updates | 128020 | +| policy_gradient_loss | -0.0755 | +| value_loss | 0.000433 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.91e+03 | +| ep_rew_mean | 0.128 | +| time/ | | +| fps | 309 | +| iterations | 6751 | +| time_elapsed | 22329 | +| total_timesteps | 6913024 | +| train/ | | +| approx_kl | 1.4661107 | +| clip_fraction | 0.49 | +| clip_range | 0.2 | +| entropy_loss | -0.47 | +| explained_variance | -0.846 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 128030 | +| policy_gradient_loss | -0.0686 | +| value_loss | 0.000406 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.91e+03 | +| ep_rew_mean | 0.128 | +| time/ | | +| fps | 309 | +| iterations | 6752 | +| time_elapsed | 22333 | +| total_timesteps | 6914048 | +| train/ | | +| approx_kl | 2.1489556 | +| clip_fraction | 0.526 | +| clip_range | 0.2 | +| entropy_loss | -0.613 | +| explained_variance | -6.68 | +| learning_rate | 0.0001 | +| loss | -0.0933 | +| n_updates | 128040 | +| policy_gradient_loss | -0.0765 | +| value_loss | 0.000443 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.92e+03 | +| ep_rew_mean | 0.123 | +| time/ | | +| fps | 309 | +| iterations | 6753 | +| time_elapsed | 22336 | +| total_timesteps | 6915072 | +| train/ | | +| approx_kl | 2.4947603 | +| clip_fraction | 0.469 | +| clip_range | 0.2 | +| entropy_loss | -0.45 | +| explained_variance | -4.08 | +| learning_rate | 0.0001 | +| loss | -0.0979 | +| n_updates | 128050 | +| policy_gradient_loss | -0.0718 | +| value_loss | 0.000611 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.92e+03 | +| ep_rew_mean | 0.116 | +| time/ | | +| fps | 309 | +| iterations | 6754 | +| time_elapsed | 22339 | +| total_timesteps | 6916096 | +| train/ | | +| approx_kl | 2.8298125 | +| clip_fraction | 0.479 | +| clip_range | 0.2 | +| entropy_loss | -0.399 | +| explained_variance | -5.36 | +| learning_rate | 0.0001 | +| loss | -0.0728 | +| n_updates | 128060 | +| policy_gradient_loss | -0.0667 | +| value_loss | 0.00045 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.92e+03 | +| ep_rew_mean | 0.116 | +| time/ | | +| fps | 309 | +| iterations | 6755 | +| time_elapsed | 22342 | +| total_timesteps | 6917120 | +| train/ | | +| approx_kl | 2.8239212 | +| clip_fraction | 0.456 | +| clip_range | 0.2 | +| entropy_loss | -0.433 | +| explained_variance | -2.42 | +| learning_rate | 0.0001 | +| loss | -0.068 | +| n_updates | 128070 | +| policy_gradient_loss | -0.0633 | +| value_loss | 0.00067 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.9e+03 | +| ep_rew_mean | 0.102 | +| time/ | | +| fps | 309 | +| iterations | 6756 | +| time_elapsed | 22346 | +| total_timesteps | 6918144 | +| train/ | | +| approx_kl | 1.8149607 | +| clip_fraction | 0.44 | +| clip_range | 0.2 | +| entropy_loss | -0.433 | +| explained_variance | -9.1 | +| learning_rate | 0.0001 | +| loss | -0.0894 | +| n_updates | 128080 | +| policy_gradient_loss | -0.0579 | +| value_loss | 0.000625 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.9e+03 | +| ep_rew_mean | 0.102 | +| time/ | | +| fps | 309 | +| iterations | 6757 | +| time_elapsed | 22349 | +| total_timesteps | 6919168 | +| train/ | | +| approx_kl | 1.6614015 | +| clip_fraction | 0.394 | +| clip_range | 0.2 | +| entropy_loss | -0.367 | +| explained_variance | -0.533 | +| learning_rate | 0.0001 | +| loss | -0.0735 | +| n_updates | 128090 | +| policy_gradient_loss | -0.0511 | +| value_loss | 0.000731 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.9e+03 | +| ep_rew_mean | 0.105 | +| time/ | | +| fps | 309 | +| iterations | 6758 | +| time_elapsed | 22352 | +| total_timesteps | 6920192 | +| train/ | | +| approx_kl | 2.925498 | +| clip_fraction | 0.459 | +| clip_range | 0.2 | +| entropy_loss | -0.451 | +| explained_variance | -3.93 | +| learning_rate | 0.0001 | +| loss | -0.0456 | +| n_updates | 128100 | +| policy_gradient_loss | -0.0656 | +| value_loss | 0.000625 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.9e+03 | +| ep_rew_mean | 0.105 | +| time/ | | +| fps | 309 | +| iterations | 6759 | +| time_elapsed | 22355 | +| total_timesteps | 6921216 | +| train/ | | +| approx_kl | 1.7386715 | +| clip_fraction | 0.493 | +| clip_range | 0.2 | +| entropy_loss | -0.442 | +| explained_variance | -1.86 | +| learning_rate | 0.0001 | +| loss | -0.0635 | +| n_updates | 128110 | +| policy_gradient_loss | -0.0519 | +| value_loss | 0.000886 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.9e+03 | +| ep_rew_mean | 0.105 | +| time/ | | +| fps | 309 | +| iterations | 6760 | +| time_elapsed | 22358 | +| total_timesteps | 6922240 | +| train/ | | +| approx_kl | 1.7974617 | +| clip_fraction | 0.516 | +| clip_range | 0.2 | +| entropy_loss | -0.497 | +| explained_variance | -2.94 | +| learning_rate | 0.0001 | +| loss | -0.0657 | +| n_updates | 128120 | +| policy_gradient_loss | -0.072 | +| value_loss | 0.00069 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.9e+03 | +| ep_rew_mean | 0.105 | +| time/ | | +| fps | 309 | +| iterations | 6761 | +| time_elapsed | 22362 | +| total_timesteps | 6923264 | +| train/ | | +| approx_kl | 2.0951753 | +| clip_fraction | 0.524 | +| clip_range | 0.2 | +| entropy_loss | -0.473 | +| explained_variance | -2.16 | +| learning_rate | 0.0001 | +| loss | -0.0808 | +| n_updates | 128130 | +| policy_gradient_loss | -0.0666 | +| value_loss | 0.000618 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.9e+03 | +| ep_rew_mean | 0.105 | +| time/ | | +| fps | 309 | +| iterations | 6762 | +| time_elapsed | 22365 | +| total_timesteps | 6924288 | +| train/ | | +| approx_kl | 2.2295606 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.413 | +| explained_variance | -1.15 | +| learning_rate | 0.0001 | +| loss | -0.0597 | +| n_updates | 128140 | +| policy_gradient_loss | -0.0608 | +| value_loss | 0.000572 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.9e+03 | +| ep_rew_mean | 0.102 | +| time/ | | +| fps | 309 | +| iterations | 6763 | +| time_elapsed | 22369 | +| total_timesteps | 6925312 | +| train/ | | +| approx_kl | 2.0665224 | +| clip_fraction | 0.517 | +| clip_range | 0.2 | +| entropy_loss | -0.493 | +| explained_variance | -3.67 | +| learning_rate | 0.0001 | +| loss | -0.0794 | +| n_updates | 128150 | +| policy_gradient_loss | -0.0669 | +| value_loss | 0.000355 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.9e+03 | +| ep_rew_mean | 0.102 | +| time/ | | +| fps | 309 | +| iterations | 6764 | +| time_elapsed | 22372 | +| total_timesteps | 6926336 | +| train/ | | +| approx_kl | 1.9939196 | +| clip_fraction | 0.477 | +| clip_range | 0.2 | +| entropy_loss | -0.423 | +| explained_variance | -1.64 | +| learning_rate | 0.0001 | +| loss | -0.109 | +| n_updates | 128160 | +| policy_gradient_loss | -0.0614 | +| value_loss | 0.000607 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.9e+03 | +| ep_rew_mean | 0.103 | +| time/ | | +| fps | 309 | +| iterations | 6765 | +| time_elapsed | 22375 | +| total_timesteps | 6927360 | +| train/ | | +| approx_kl | 2.0717907 | +| clip_fraction | 0.486 | +| clip_range | 0.2 | +| entropy_loss | -0.448 | +| explained_variance | -2.88 | +| learning_rate | 0.0001 | +| loss | -0.0831 | +| n_updates | 128170 | +| policy_gradient_loss | -0.0665 | +| value_loss | 0.000751 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.89e+03 | +| ep_rew_mean | 0.1 | +| time/ | | +| fps | 309 | +| iterations | 6766 | +| time_elapsed | 22379 | +| total_timesteps | 6928384 | +| train/ | | +| approx_kl | 1.8517909 | +| clip_fraction | 0.433 | +| clip_range | 0.2 | +| entropy_loss | -0.362 | +| explained_variance | -10.6 | +| learning_rate | 0.0001 | +| loss | -0.0812 | +| n_updates | 128180 | +| policy_gradient_loss | -0.0549 | +| value_loss | 0.000533 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.89e+03 | +| ep_rew_mean | 0.0957 | +| time/ | | +| fps | 309 | +| iterations | 6767 | +| time_elapsed | 22382 | +| total_timesteps | 6929408 | +| train/ | | +| approx_kl | 2.2718003 | +| clip_fraction | 0.434 | +| clip_range | 0.2 | +| entropy_loss | -0.394 | +| explained_variance | -1.07 | +| learning_rate | 0.0001 | +| loss | -0.0582 | +| n_updates | 128190 | +| policy_gradient_loss | -0.0519 | +| value_loss | 0.00102 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.0907 | +| time/ | | +| fps | 309 | +| iterations | 6768 | +| time_elapsed | 22386 | +| total_timesteps | 6930432 | +| train/ | | +| approx_kl | 1.486198 | +| clip_fraction | 0.463 | +| clip_range | 0.2 | +| entropy_loss | -0.412 | +| explained_variance | -2.07 | +| learning_rate | 0.0001 | +| loss | -0.0751 | +| n_updates | 128200 | +| policy_gradient_loss | -0.0628 | +| value_loss | 0.000542 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.0907 | +| time/ | | +| fps | 309 | +| iterations | 6769 | +| time_elapsed | 22389 | +| total_timesteps | 6931456 | +| train/ | | +| approx_kl | 3.0476778 | +| clip_fraction | 0.439 | +| clip_range | 0.2 | +| entropy_loss | -0.367 | +| explained_variance | -1.32 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 128210 | +| policy_gradient_loss | -0.0601 | +| value_loss | 0.000798 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.0834 | +| time/ | | +| fps | 309 | +| iterations | 6770 | +| time_elapsed | 22392 | +| total_timesteps | 6932480 | +| train/ | | +| approx_kl | 2.555692 | +| clip_fraction | 0.522 | +| clip_range | 0.2 | +| entropy_loss | -0.52 | +| explained_variance | -3.57 | +| learning_rate | 0.0001 | +| loss | -0.0848 | +| n_updates | 128220 | +| policy_gradient_loss | -0.0666 | +| value_loss | 0.000863 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.0834 | +| time/ | | +| fps | 309 | +| iterations | 6771 | +| time_elapsed | 22395 | +| total_timesteps | 6933504 | +| train/ | | +| approx_kl | 1.5045902 | +| clip_fraction | 0.476 | +| clip_range | 0.2 | +| entropy_loss | -0.44 | +| explained_variance | -6.9 | +| learning_rate | 0.0001 | +| loss | -0.0722 | +| n_updates | 128230 | +| policy_gradient_loss | -0.0615 | +| value_loss | 0.00073 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.077 | +| time/ | | +| fps | 309 | +| iterations | 6772 | +| time_elapsed | 22398 | +| total_timesteps | 6934528 | +| train/ | | +| approx_kl | 1.7947742 | +| clip_fraction | 0.485 | +| clip_range | 0.2 | +| entropy_loss | -0.499 | +| explained_variance | -6.69 | +| learning_rate | 0.0001 | +| loss | -0.105 | +| n_updates | 128240 | +| policy_gradient_loss | -0.0583 | +| value_loss | 0.000701 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.077 | +| time/ | | +| fps | 309 | +| iterations | 6773 | +| time_elapsed | 22402 | +| total_timesteps | 6935552 | +| train/ | | +| approx_kl | 2.425878 | +| clip_fraction | 0.464 | +| clip_range | 0.2 | +| entropy_loss | -0.43 | +| explained_variance | -1.65 | +| learning_rate | 0.0001 | +| loss | -0.076 | +| n_updates | 128250 | +| policy_gradient_loss | -0.0603 | +| value_loss | 0.000813 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.0792 | +| time/ | | +| fps | 309 | +| iterations | 6774 | +| time_elapsed | 22405 | +| total_timesteps | 6936576 | +| train/ | | +| approx_kl | 1.4598017 | +| clip_fraction | 0.491 | +| clip_range | 0.2 | +| entropy_loss | -0.492 | +| explained_variance | -3.14 | +| learning_rate | 0.0001 | +| loss | -0.0953 | +| n_updates | 128260 | +| policy_gradient_loss | -0.0665 | +| value_loss | 0.000512 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.0792 | +| time/ | | +| fps | 309 | +| iterations | 6775 | +| time_elapsed | 22408 | +| total_timesteps | 6937600 | +| train/ | | +| approx_kl | 2.103344 | +| clip_fraction | 0.446 | +| clip_range | 0.2 | +| entropy_loss | -0.397 | +| explained_variance | -4.8 | +| learning_rate | 0.0001 | +| loss | -0.0869 | +| n_updates | 128270 | +| policy_gradient_loss | -0.0641 | +| value_loss | 0.0005 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.0751 | +| time/ | | +| fps | 309 | +| iterations | 6776 | +| time_elapsed | 22411 | +| total_timesteps | 6938624 | +| train/ | | +| approx_kl | 1.826477 | +| clip_fraction | 0.532 | +| clip_range | 0.2 | +| entropy_loss | -0.507 | +| explained_variance | -0.935 | +| learning_rate | 0.0001 | +| loss | -0.0701 | +| n_updates | 128280 | +| policy_gradient_loss | -0.0646 | +| value_loss | 0.000678 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.0751 | +| time/ | | +| fps | 309 | +| iterations | 6777 | +| time_elapsed | 22414 | +| total_timesteps | 6939648 | +| train/ | | +| approx_kl | 7.521614 | +| clip_fraction | 0.417 | +| clip_range | 0.2 | +| entropy_loss | -0.338 | +| explained_variance | -4.02 | +| learning_rate | 0.0001 | +| loss | -0.0914 | +| n_updates | 128290 | +| policy_gradient_loss | -0.0539 | +| value_loss | 0.000533 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.0712 | +| time/ | | +| fps | 309 | +| iterations | 6778 | +| time_elapsed | 22417 | +| total_timesteps | 6940672 | +| train/ | | +| approx_kl | 1.9069148 | +| clip_fraction | 0.482 | +| clip_range | 0.2 | +| entropy_loss | -0.486 | +| explained_variance | -10.3 | +| learning_rate | 0.0001 | +| loss | -0.0885 | +| n_updates | 128300 | +| policy_gradient_loss | -0.065 | +| value_loss | 0.000684 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.0686 | +| time/ | | +| fps | 309 | +| iterations | 6779 | +| time_elapsed | 22421 | +| total_timesteps | 6941696 | +| train/ | | +| approx_kl | 4.1911287 | +| clip_fraction | 0.47 | +| clip_range | 0.2 | +| entropy_loss | -0.393 | +| explained_variance | -1.55 | +| learning_rate | 0.0001 | +| loss | -0.0922 | +| n_updates | 128310 | +| policy_gradient_loss | -0.0643 | +| value_loss | 0.00063 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.0686 | +| time/ | | +| fps | 309 | +| iterations | 6780 | +| time_elapsed | 22424 | +| total_timesteps | 6942720 | +| train/ | | +| approx_kl | 1.7315971 | +| clip_fraction | 0.464 | +| clip_range | 0.2 | +| entropy_loss | -0.41 | +| explained_variance | -2.36 | +| learning_rate | 0.0001 | +| loss | -0.0918 | +| n_updates | 128320 | +| policy_gradient_loss | -0.0616 | +| value_loss | 0.000588 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.0695 | +| time/ | | +| fps | 309 | +| iterations | 6781 | +| time_elapsed | 22428 | +| total_timesteps | 6943744 | +| train/ | | +| approx_kl | 1.9944016 | +| clip_fraction | 0.508 | +| clip_range | 0.2 | +| entropy_loss | -0.473 | +| explained_variance | -1.39 | +| learning_rate | 0.0001 | +| loss | -0.061 | +| n_updates | 128330 | +| policy_gradient_loss | -0.071 | +| value_loss | 0.000404 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.0695 | +| time/ | | +| fps | 309 | +| iterations | 6782 | +| time_elapsed | 22431 | +| total_timesteps | 6944768 | +| train/ | | +| approx_kl | 2.0963805 | +| clip_fraction | 0.473 | +| clip_range | 0.2 | +| entropy_loss | -0.43 | +| explained_variance | -1.02 | +| learning_rate | 0.0001 | +| loss | -0.116 | +| n_updates | 128340 | +| policy_gradient_loss | -0.0647 | +| value_loss | 0.000651 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.0655 | +| time/ | | +| fps | 309 | +| iterations | 6783 | +| time_elapsed | 22435 | +| total_timesteps | 6945792 | +| train/ | | +| approx_kl | 1.7719398 | +| clip_fraction | 0.501 | +| clip_range | 0.2 | +| entropy_loss | -0.543 | +| explained_variance | -3.39 | +| learning_rate | 0.0001 | +| loss | -0.0952 | +| n_updates | 128350 | +| policy_gradient_loss | -0.0683 | +| value_loss | 0.000565 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.0611 | +| time/ | | +| fps | 309 | +| iterations | 6784 | +| time_elapsed | 22438 | +| total_timesteps | 6946816 | +| train/ | | +| approx_kl | 1.859273 | +| clip_fraction | 0.441 | +| clip_range | 0.2 | +| entropy_loss | -0.473 | +| explained_variance | -4.92 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 128360 | +| policy_gradient_loss | -0.0622 | +| value_loss | 0.000188 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.0611 | +| time/ | | +| fps | 309 | +| iterations | 6785 | +| time_elapsed | 22442 | +| total_timesteps | 6947840 | +| train/ | | +| approx_kl | 2.3397431 | +| clip_fraction | 0.444 | +| clip_range | 0.2 | +| entropy_loss | -0.394 | +| explained_variance | -0.769 | +| learning_rate | 0.0001 | +| loss | -0.0712 | +| n_updates | 128370 | +| policy_gradient_loss | -0.0548 | +| value_loss | 0.000422 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.0547 | +| time/ | | +| fps | 309 | +| iterations | 6786 | +| time_elapsed | 22445 | +| total_timesteps | 6948864 | +| train/ | | +| approx_kl | 2.0918083 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.399 | +| explained_variance | -3.31 | +| learning_rate | 0.0001 | +| loss | -0.0952 | +| n_updates | 128380 | +| policy_gradient_loss | -0.0726 | +| value_loss | 0.000683 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.0547 | +| time/ | | +| fps | 309 | +| iterations | 6787 | +| time_elapsed | 22449 | +| total_timesteps | 6949888 | +| train/ | | +| approx_kl | 1.7939075 | +| clip_fraction | 0.469 | +| clip_range | 0.2 | +| entropy_loss | -0.386 | +| explained_variance | -1.79 | +| learning_rate | 0.0001 | +| loss | -0.0853 | +| n_updates | 128390 | +| policy_gradient_loss | -0.0622 | +| value_loss | 0.000899 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.81e+03 | +| ep_rew_mean | 0.0554 | +| time/ | | +| fps | 309 | +| iterations | 6788 | +| time_elapsed | 22452 | +| total_timesteps | 6950912 | +| train/ | | +| approx_kl | 4.529676 | +| clip_fraction | 0.531 | +| clip_range | 0.2 | +| entropy_loss | -0.556 | +| explained_variance | -3.01 | +| learning_rate | 0.0001 | +| loss | -0.0964 | +| n_updates | 128400 | +| policy_gradient_loss | -0.0731 | +| value_loss | 0.000495 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.81e+03 | +| ep_rew_mean | 0.0554 | +| time/ | | +| fps | 309 | +| iterations | 6789 | +| time_elapsed | 22455 | +| total_timesteps | 6951936 | +| train/ | | +| approx_kl | 2.2901459 | +| clip_fraction | 0.493 | +| clip_range | 0.2 | +| entropy_loss | -0.45 | +| explained_variance | -3.82 | +| learning_rate | 0.0001 | +| loss | -0.0725 | +| n_updates | 128410 | +| policy_gradient_loss | -0.0678 | +| value_loss | 0.000536 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.81e+03 | +| ep_rew_mean | 0.0554 | +| time/ | | +| fps | 309 | +| iterations | 6790 | +| time_elapsed | 22458 | +| total_timesteps | 6952960 | +| train/ | | +| approx_kl | 1.9034857 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.445 | +| explained_variance | -1.48 | +| learning_rate | 0.0001 | +| loss | -0.0813 | +| n_updates | 128420 | +| policy_gradient_loss | -0.0647 | +| value_loss | 0.000709 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.82e+03 | +| ep_rew_mean | 0.0566 | +| time/ | | +| fps | 309 | +| iterations | 6791 | +| time_elapsed | 22462 | +| total_timesteps | 6953984 | +| train/ | | +| approx_kl | 1.8493016 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.397 | +| explained_variance | -3.61 | +| learning_rate | 0.0001 | +| loss | -0.0785 | +| n_updates | 128430 | +| policy_gradient_loss | -0.0671 | +| value_loss | 0.00043 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.82e+03 | +| ep_rew_mean | 0.0477 | +| time/ | | +| fps | 309 | +| iterations | 6792 | +| time_elapsed | 22465 | +| total_timesteps | 6955008 | +| train/ | | +| approx_kl | 2.0877345 | +| clip_fraction | 0.493 | +| clip_range | 0.2 | +| entropy_loss | -0.419 | +| explained_variance | -6.42 | +| learning_rate | 0.0001 | +| loss | -0.0879 | +| n_updates | 128440 | +| policy_gradient_loss | -0.0568 | +| value_loss | 0.000584 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.82e+03 | +| ep_rew_mean | 0.0477 | +| time/ | | +| fps | 309 | +| iterations | 6793 | +| time_elapsed | 22468 | +| total_timesteps | 6956032 | +| train/ | | +| approx_kl | 2.42942 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.498 | +| explained_variance | -1.09 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 128450 | +| policy_gradient_loss | -0.0593 | +| value_loss | 0.000548 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.81e+03 | +| ep_rew_mean | 0.0406 | +| time/ | | +| fps | 309 | +| iterations | 6794 | +| time_elapsed | 22471 | +| total_timesteps | 6957056 | +| train/ | | +| approx_kl | 1.6306381 | +| clip_fraction | 0.497 | +| clip_range | 0.2 | +| entropy_loss | -0.497 | +| explained_variance | -4.92 | +| learning_rate | 0.0001 | +| loss | -0.0986 | +| n_updates | 128460 | +| policy_gradient_loss | -0.0687 | +| value_loss | 0.000562 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.8e+03 | +| ep_rew_mean | 0.0347 | +| time/ | | +| fps | 309 | +| iterations | 6795 | +| time_elapsed | 22474 | +| total_timesteps | 6958080 | +| train/ | | +| approx_kl | 1.8089529 | +| clip_fraction | 0.458 | +| clip_range | 0.2 | +| entropy_loss | -0.422 | +| explained_variance | -1.27 | +| learning_rate | 0.0001 | +| loss | -0.0691 | +| n_updates | 128470 | +| policy_gradient_loss | -0.0612 | +| value_loss | 0.000732 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.0317 | +| time/ | | +| fps | 309 | +| iterations | 6796 | +| time_elapsed | 22478 | +| total_timesteps | 6959104 | +| train/ | | +| approx_kl | 1.8026797 | +| clip_fraction | 0.51 | +| clip_range | 0.2 | +| entropy_loss | -0.477 | +| explained_variance | -0.929 | +| learning_rate | 0.0001 | +| loss | -0.0517 | +| n_updates | 128480 | +| policy_gradient_loss | -0.0669 | +| value_loss | 0.000809 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.0317 | +| time/ | | +| fps | 309 | +| iterations | 6797 | +| time_elapsed | 22481 | +| total_timesteps | 6960128 | +| train/ | | +| approx_kl | 1.6826743 | +| clip_fraction | 0.505 | +| clip_range | 0.2 | +| entropy_loss | -0.483 | +| explained_variance | -4.71 | +| learning_rate | 0.0001 | +| loss | -0.0694 | +| n_updates | 128490 | +| policy_gradient_loss | -0.0691 | +| value_loss | 0.000575 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.0294 | +| time/ | | +| fps | 309 | +| iterations | 6798 | +| time_elapsed | 22484 | +| total_timesteps | 6961152 | +| train/ | | +| approx_kl | 1.905268 | +| clip_fraction | 0.486 | +| clip_range | 0.2 | +| entropy_loss | -0.505 | +| explained_variance | -8.94 | +| learning_rate | 0.0001 | +| loss | -0.0875 | +| n_updates | 128500 | +| policy_gradient_loss | -0.0632 | +| value_loss | 0.000564 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.0294 | +| time/ | | +| fps | 309 | +| iterations | 6799 | +| time_elapsed | 22488 | +| total_timesteps | 6962176 | +| train/ | | +| approx_kl | 4.1587896 | +| clip_fraction | 0.505 | +| clip_range | 0.2 | +| entropy_loss | -0.473 | +| explained_variance | -5.9 | +| learning_rate | 0.0001 | +| loss | -0.0725 | +| n_updates | 128510 | +| policy_gradient_loss | -0.0679 | +| value_loss | 0.000464 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.78e+03 | +| ep_rew_mean | 0.023 | +| time/ | | +| fps | 309 | +| iterations | 6800 | +| time_elapsed | 22491 | +| total_timesteps | 6963200 | +| train/ | | +| approx_kl | 1.6559503 | +| clip_fraction | 0.489 | +| clip_range | 0.2 | +| entropy_loss | -0.549 | +| explained_variance | -4.75 | +| learning_rate | 0.0001 | +| loss | -0.0921 | +| n_updates | 128520 | +| policy_gradient_loss | -0.0617 | +| value_loss | 0.000324 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.0206 | +| time/ | | +| fps | 309 | +| iterations | 6801 | +| time_elapsed | 22495 | +| total_timesteps | 6964224 | +| train/ | | +| approx_kl | 1.53105 | +| clip_fraction | 0.494 | +| clip_range | 0.2 | +| entropy_loss | -0.508 | +| explained_variance | -0.686 | +| learning_rate | 0.0001 | +| loss | -0.0742 | +| n_updates | 128530 | +| policy_gradient_loss | -0.0626 | +| value_loss | 0.000382 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.0206 | +| time/ | | +| fps | 309 | +| iterations | 6802 | +| time_elapsed | 22498 | +| total_timesteps | 6965248 | +| train/ | | +| approx_kl | 2.0502498 | +| clip_fraction | 0.447 | +| clip_range | 0.2 | +| entropy_loss | -0.396 | +| explained_variance | -3.67 | +| learning_rate | 0.0001 | +| loss | -0.0981 | +| n_updates | 128540 | +| policy_gradient_loss | -0.0641 | +| value_loss | 0.000455 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.78e+03 | +| ep_rew_mean | 0.0114 | +| time/ | | +| fps | 309 | +| iterations | 6803 | +| time_elapsed | 22501 | +| total_timesteps | 6966272 | +| train/ | | +| approx_kl | 1.4982641 | +| clip_fraction | 0.537 | +| clip_range | 0.2 | +| entropy_loss | -0.635 | +| explained_variance | -4.79 | +| learning_rate | 0.0001 | +| loss | -0.0781 | +| n_updates | 128550 | +| policy_gradient_loss | -0.0648 | +| value_loss | 0.000407 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.78e+03 | +| ep_rew_mean | 0.0114 | +| time/ | | +| fps | 309 | +| iterations | 6804 | +| time_elapsed | 22505 | +| total_timesteps | 6967296 | +| train/ | | +| approx_kl | 1.464375 | +| clip_fraction | 0.47 | +| clip_range | 0.2 | +| entropy_loss | -0.448 | +| explained_variance | -4.33 | +| learning_rate | 0.0001 | +| loss | -0.0674 | +| n_updates | 128560 | +| policy_gradient_loss | -0.0634 | +| value_loss | 0.00052 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.78e+03 | +| ep_rew_mean | 0.00998 | +| time/ | | +| fps | 309 | +| iterations | 6805 | +| time_elapsed | 22508 | +| total_timesteps | 6968320 | +| train/ | | +| approx_kl | 2.304625 | +| clip_fraction | 0.476 | +| clip_range | 0.2 | +| entropy_loss | -0.393 | +| explained_variance | -3.59 | +| learning_rate | 0.0001 | +| loss | -0.0433 | +| n_updates | 128570 | +| policy_gradient_loss | -0.0599 | +| value_loss | 0.000572 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.78e+03 | +| ep_rew_mean | 0.00998 | +| time/ | | +| fps | 309 | +| iterations | 6806 | +| time_elapsed | 22511 | +| total_timesteps | 6969344 | +| train/ | | +| approx_kl | 1.7518284 | +| clip_fraction | 0.492 | +| clip_range | 0.2 | +| entropy_loss | -0.511 | +| explained_variance | -2.05 | +| learning_rate | 0.0001 | +| loss | -0.0788 | +| n_updates | 128580 | +| policy_gradient_loss | -0.0636 | +| value_loss | 0.000348 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.78e+03 | +| ep_rew_mean | 0.00489 | +| time/ | | +| fps | 309 | +| iterations | 6807 | +| time_elapsed | 22514 | +| total_timesteps | 6970368 | +| train/ | | +| approx_kl | 2.097629 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.393 | +| explained_variance | -4.68 | +| learning_rate | 0.0001 | +| loss | -0.0844 | +| n_updates | 128590 | +| policy_gradient_loss | -0.0683 | +| value_loss | 0.00053 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.00415 | +| time/ | | +| fps | 309 | +| iterations | 6808 | +| time_elapsed | 22518 | +| total_timesteps | 6971392 | +| train/ | | +| approx_kl | 1.524108 | +| clip_fraction | 0.445 | +| clip_range | 0.2 | +| entropy_loss | -0.43 | +| explained_variance | -4.22 | +| learning_rate | 0.0001 | +| loss | -0.0325 | +| n_updates | 128600 | +| policy_gradient_loss | -0.0592 | +| value_loss | 0.000549 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.00415 | +| time/ | | +| fps | 309 | +| iterations | 6809 | +| time_elapsed | 22521 | +| total_timesteps | 6972416 | +| train/ | | +| approx_kl | 2.2430274 | +| clip_fraction | 0.447 | +| clip_range | 0.2 | +| entropy_loss | -0.403 | +| explained_variance | -2.33 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 128610 | +| policy_gradient_loss | -0.0528 | +| value_loss | 0.000512 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | -0.00349 | +| time/ | | +| fps | 309 | +| iterations | 6810 | +| time_elapsed | 22524 | +| total_timesteps | 6973440 | +| train/ | | +| approx_kl | 1.486931 | +| clip_fraction | 0.466 | +| clip_range | 0.2 | +| entropy_loss | -0.37 | +| explained_variance | -6.54 | +| learning_rate | 0.0001 | +| loss | -0.0895 | +| n_updates | 128620 | +| policy_gradient_loss | -0.0732 | +| value_loss | 0.000476 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | -0.00349 | +| time/ | | +| fps | 309 | +| iterations | 6811 | +| time_elapsed | 22527 | +| total_timesteps | 6974464 | +| train/ | | +| approx_kl | 2.012968 | +| clip_fraction | 0.434 | +| clip_range | 0.2 | +| entropy_loss | -0.402 | +| explained_variance | -0.916 | +| learning_rate | 0.0001 | +| loss | -0.0697 | +| n_updates | 128630 | +| policy_gradient_loss | -0.0561 | +| value_loss | 0.000554 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | -0.00673 | +| time/ | | +| fps | 309 | +| iterations | 6812 | +| time_elapsed | 22530 | +| total_timesteps | 6975488 | +| train/ | | +| approx_kl | 1.8717375 | +| clip_fraction | 0.472 | +| clip_range | 0.2 | +| entropy_loss | -0.379 | +| explained_variance | -2.55 | +| learning_rate | 0.0001 | +| loss | -0.0893 | +| n_updates | 128640 | +| policy_gradient_loss | -0.0674 | +| value_loss | 0.000848 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | -0.0132 | +| time/ | | +| fps | 309 | +| iterations | 6813 | +| time_elapsed | 22533 | +| total_timesteps | 6976512 | +| train/ | | +| approx_kl | 1.933368 | +| clip_fraction | 0.455 | +| clip_range | 0.2 | +| entropy_loss | -0.399 | +| explained_variance | -8.26 | +| learning_rate | 0.0001 | +| loss | -0.0767 | +| n_updates | 128650 | +| policy_gradient_loss | -0.0627 | +| value_loss | 0.000396 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | -0.0132 | +| time/ | | +| fps | 309 | +| iterations | 6814 | +| time_elapsed | 22537 | +| total_timesteps | 6977536 | +| train/ | | +| approx_kl | 1.7295895 | +| clip_fraction | 0.439 | +| clip_range | 0.2 | +| entropy_loss | -0.362 | +| explained_variance | -0.999 | +| learning_rate | 0.0001 | +| loss | -0.0537 | +| n_updates | 128660 | +| policy_gradient_loss | -0.0593 | +| value_loss | 0.0006 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | -0.00953 | +| time/ | | +| fps | 309 | +| iterations | 6815 | +| time_elapsed | 22540 | +| total_timesteps | 6978560 | +| train/ | | +| approx_kl | 2.5634127 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.365 | +| explained_variance | -2.14 | +| learning_rate | 0.0001 | +| loss | -0.0802 | +| n_updates | 128670 | +| policy_gradient_loss | -0.0652 | +| value_loss | 0.000764 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | -0.0122 | +| time/ | | +| fps | 309 | +| iterations | 6816 | +| time_elapsed | 22543 | +| total_timesteps | 6979584 | +| train/ | | +| approx_kl | 1.7663333 | +| clip_fraction | 0.452 | +| clip_range | 0.2 | +| entropy_loss | -0.403 | +| explained_variance | -6.14 | +| learning_rate | 0.0001 | +| loss | -0.0769 | +| n_updates | 128680 | +| policy_gradient_loss | -0.0633 | +| value_loss | 0.000441 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | -0.0122 | +| time/ | | +| fps | 309 | +| iterations | 6817 | +| time_elapsed | 22547 | +| total_timesteps | 6980608 | +| train/ | | +| approx_kl | 2.5127513 | +| clip_fraction | 0.442 | +| clip_range | 0.2 | +| entropy_loss | -0.337 | +| explained_variance | -3.75 | +| learning_rate | 0.0001 | +| loss | -0.115 | +| n_updates | 128690 | +| policy_gradient_loss | -0.06 | +| value_loss | 0.000586 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | -0.01 | +| time/ | | +| fps | 309 | +| iterations | 6818 | +| time_elapsed | 22550 | +| total_timesteps | 6981632 | +| train/ | | +| approx_kl | 2.6254916 | +| clip_fraction | 0.524 | +| clip_range | 0.2 | +| entropy_loss | -0.457 | +| explained_variance | -3.13 | +| learning_rate | 0.0001 | +| loss | -0.0868 | +| n_updates | 128700 | +| policy_gradient_loss | -0.0647 | +| value_loss | 0.000615 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | -0.01 | +| time/ | | +| fps | 309 | +| iterations | 6819 | +| time_elapsed | 22554 | +| total_timesteps | 6982656 | +| train/ | | +| approx_kl | 1.672255 | +| clip_fraction | 0.486 | +| clip_range | 0.2 | +| entropy_loss | -0.49 | +| explained_variance | -5.87 | +| learning_rate | 0.0001 | +| loss | -0.091 | +| n_updates | 128710 | +| policy_gradient_loss | -0.0643 | +| value_loss | 0.000525 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | -0.00976 | +| time/ | | +| fps | 309 | +| iterations | 6820 | +| time_elapsed | 22557 | +| total_timesteps | 6983680 | +| train/ | | +| approx_kl | 3.0697277 | +| clip_fraction | 0.46 | +| clip_range | 0.2 | +| entropy_loss | -0.372 | +| explained_variance | -6.16 | +| learning_rate | 0.0001 | +| loss | -0.0796 | +| n_updates | 128720 | +| policy_gradient_loss | -0.0644 | +| value_loss | 0.000847 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | -0.0136 | +| time/ | | +| fps | 309 | +| iterations | 6821 | +| time_elapsed | 22561 | +| total_timesteps | 6984704 | +| train/ | | +| approx_kl | 2.4914517 | +| clip_fraction | 0.441 | +| clip_range | 0.2 | +| entropy_loss | -0.398 | +| explained_variance | -1.7 | +| learning_rate | 0.0001 | +| loss | -0.0816 | +| n_updates | 128730 | +| policy_gradient_loss | -0.0616 | +| value_loss | 0.000564 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | -0.0136 | +| time/ | | +| fps | 309 | +| iterations | 6822 | +| time_elapsed | 22564 | +| total_timesteps | 6985728 | +| train/ | | +| approx_kl | 2.0034642 | +| clip_fraction | 0.474 | +| clip_range | 0.2 | +| entropy_loss | -0.402 | +| explained_variance | -2.53 | +| learning_rate | 0.0001 | +| loss | -0.0536 | +| n_updates | 128740 | +| policy_gradient_loss | -0.0581 | +| value_loss | 0.000568 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | -0.0209 | +| time/ | | +| fps | 309 | +| iterations | 6823 | +| time_elapsed | 22567 | +| total_timesteps | 6986752 | +| train/ | | +| approx_kl | 1.6514784 | +| clip_fraction | 0.455 | +| clip_range | 0.2 | +| entropy_loss | -0.379 | +| explained_variance | -3.62 | +| learning_rate | 0.0001 | +| loss | -0.0803 | +| n_updates | 128750 | +| policy_gradient_loss | -0.0588 | +| value_loss | 0.000562 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | -0.0216 | +| time/ | | +| fps | 309 | +| iterations | 6824 | +| time_elapsed | 22571 | +| total_timesteps | 6987776 | +| train/ | | +| approx_kl | 2.6764088 | +| clip_fraction | 0.436 | +| clip_range | 0.2 | +| entropy_loss | -0.34 | +| explained_variance | -2.19 | +| learning_rate | 0.0001 | +| loss | -0.083 | +| n_updates | 128760 | +| policy_gradient_loss | -0.0656 | +| value_loss | 0.000756 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | -0.0233 | +| time/ | | +| fps | 309 | +| iterations | 6825 | +| time_elapsed | 22574 | +| total_timesteps | 6988800 | +| train/ | | +| approx_kl | 1.9911331 | +| clip_fraction | 0.438 | +| clip_range | 0.2 | +| entropy_loss | -0.321 | +| explained_variance | -5.49 | +| learning_rate | 0.0001 | +| loss | -0.0917 | +| n_updates | 128770 | +| policy_gradient_loss | -0.068 | +| value_loss | 0.000513 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | -0.0233 | +| time/ | | +| fps | 309 | +| iterations | 6826 | +| time_elapsed | 22577 | +| total_timesteps | 6989824 | +| train/ | | +| approx_kl | 3.9077327 | +| clip_fraction | 0.455 | +| clip_range | 0.2 | +| entropy_loss | -0.362 | +| explained_variance | -2.47 | +| learning_rate | 0.0001 | +| loss | -0.0862 | +| n_updates | 128780 | +| policy_gradient_loss | -0.0656 | +| value_loss | 0.000515 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | -0.0233 | +| time/ | | +| fps | 309 | +| iterations | 6827 | +| time_elapsed | 22580 | +| total_timesteps | 6990848 | +| train/ | | +| approx_kl | 1.3945918 | +| clip_fraction | 0.501 | +| clip_range | 0.2 | +| entropy_loss | -0.476 | +| explained_variance | -1.24 | +| learning_rate | 0.0001 | +| loss | -0.0861 | +| n_updates | 128790 | +| policy_gradient_loss | -0.0621 | +| value_loss | 0.000698 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | -0.0252 | +| time/ | | +| fps | 309 | +| iterations | 6828 | +| time_elapsed | 22584 | +| total_timesteps | 6991872 | +| train/ | | +| approx_kl | 2.2482057 | +| clip_fraction | 0.494 | +| clip_range | 0.2 | +| entropy_loss | -0.388 | +| explained_variance | -3.44 | +| learning_rate | 0.0001 | +| loss | -0.068 | +| n_updates | 128800 | +| policy_gradient_loss | -0.0568 | +| value_loss | 0.000588 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | -0.0256 | +| time/ | | +| fps | 309 | +| iterations | 6829 | +| time_elapsed | 22587 | +| total_timesteps | 6992896 | +| train/ | | +| approx_kl | 2.1662009 | +| clip_fraction | 0.477 | +| clip_range | 0.2 | +| entropy_loss | -0.385 | +| explained_variance | -3.16 | +| learning_rate | 0.0001 | +| loss | -0.116 | +| n_updates | 128810 | +| policy_gradient_loss | -0.0674 | +| value_loss | 0.0004 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | -0.0233 | +| time/ | | +| fps | 309 | +| iterations | 6830 | +| time_elapsed | 22590 | +| total_timesteps | 6993920 | +| train/ | | +| approx_kl | 2.0167537 | +| clip_fraction | 0.441 | +| clip_range | 0.2 | +| entropy_loss | -0.357 | +| explained_variance | -1.91 | +| learning_rate | 0.0001 | +| loss | -0.0779 | +| n_updates | 128820 | +| policy_gradient_loss | -0.0592 | +| value_loss | 0.000797 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | -0.0233 | +| time/ | | +| fps | 309 | +| iterations | 6831 | +| time_elapsed | 22593 | +| total_timesteps | 6994944 | +| train/ | | +| approx_kl | 1.9905317 | +| clip_fraction | 0.46 | +| clip_range | 0.2 | +| entropy_loss | -0.343 | +| explained_variance | -2.79 | +| learning_rate | 0.0001 | +| loss | -0.0769 | +| n_updates | 128830 | +| policy_gradient_loss | -0.0603 | +| value_loss | 0.000689 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | -0.0221 | +| time/ | | +| fps | 309 | +| iterations | 6832 | +| time_elapsed | 22596 | +| total_timesteps | 6995968 | +| train/ | | +| approx_kl | 1.821327 | +| clip_fraction | 0.503 | +| clip_range | 0.2 | +| entropy_loss | -0.485 | +| explained_variance | -2.22 | +| learning_rate | 0.0001 | +| loss | -0.1 | +| n_updates | 128840 | +| policy_gradient_loss | -0.0579 | +| value_loss | 0.000509 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | -0.0242 | +| time/ | | +| fps | 309 | +| iterations | 6833 | +| time_elapsed | 22599 | +| total_timesteps | 6996992 | +| train/ | | +| approx_kl | 1.8684576 | +| clip_fraction | 0.455 | +| clip_range | 0.2 | +| entropy_loss | -0.372 | +| explained_variance | -3.96 | +| learning_rate | 0.0001 | +| loss | -0.0586 | +| n_updates | 128850 | +| policy_gradient_loss | -0.0627 | +| value_loss | 0.000581 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | -0.0242 | +| time/ | | +| fps | 309 | +| iterations | 6834 | +| time_elapsed | 22603 | +| total_timesteps | 6998016 | +| train/ | | +| approx_kl | 1.7744224 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.409 | +| explained_variance | -3.91 | +| learning_rate | 0.0001 | +| loss | -0.0884 | +| n_updates | 128860 | +| policy_gradient_loss | -0.0655 | +| value_loss | 0.000746 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | -0.021 | +| time/ | | +| fps | 309 | +| iterations | 6835 | +| time_elapsed | 22607 | +| total_timesteps | 6999040 | +| train/ | | +| approx_kl | 1.8014545 | +| clip_fraction | 0.451 | +| clip_range | 0.2 | +| entropy_loss | -0.336 | +| explained_variance | -3.61 | +| learning_rate | 0.0001 | +| loss | -0.0777 | +| n_updates | 128870 | +| policy_gradient_loss | -0.0636 | +| value_loss | 0.000777 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | -0.021 | +| time/ | | +| fps | 309 | +| iterations | 6836 | +| time_elapsed | 22610 | +| total_timesteps | 7000064 | +| train/ | | +| approx_kl | 1.9073762 | +| clip_fraction | 0.451 | +| clip_range | 0.2 | +| entropy_loss | -0.393 | +| explained_variance | -3.56 | +| learning_rate | 0.0001 | +| loss | -0.0925 | +| n_updates | 128880 | +| policy_gradient_loss | -0.061 | +| value_loss | 0.000823 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | -0.0215 | +| time/ | | +| fps | 309 | +| iterations | 6837 | +| time_elapsed | 22614 | +| total_timesteps | 7001088 | +| train/ | | +| approx_kl | 1.7039859 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.408 | +| explained_variance | -3.57 | +| learning_rate | 0.0001 | +| loss | -0.0894 | +| n_updates | 128890 | +| policy_gradient_loss | -0.0645 | +| value_loss | 0.00053 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | -0.022 | +| time/ | | +| fps | 309 | +| iterations | 6838 | +| time_elapsed | 22617 | +| total_timesteps | 7002112 | +| train/ | | +| approx_kl | 2.4179044 | +| clip_fraction | 0.494 | +| clip_range | 0.2 | +| entropy_loss | -0.564 | +| explained_variance | -3.66 | +| learning_rate | 0.0001 | +| loss | -0.0544 | +| n_updates | 128900 | +| policy_gradient_loss | -0.0683 | +| value_loss | 0.000326 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | -0.022 | +| time/ | | +| fps | 309 | +| iterations | 6839 | +| time_elapsed | 22621 | +| total_timesteps | 7003136 | +| train/ | | +| approx_kl | 2.0337067 | +| clip_fraction | 0.498 | +| clip_range | 0.2 | +| entropy_loss | -0.406 | +| explained_variance | -1.35 | +| learning_rate | 0.0001 | +| loss | -0.0943 | +| n_updates | 128910 | +| policy_gradient_loss | -0.065 | +| value_loss | 0.000423 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | -0.0163 | +| time/ | | +| fps | 309 | +| iterations | 6840 | +| time_elapsed | 22624 | +| total_timesteps | 7004160 | +| train/ | | +| approx_kl | 5.3955817 | +| clip_fraction | 0.515 | +| clip_range | 0.2 | +| entropy_loss | -0.448 | +| explained_variance | -1.4 | +| learning_rate | 0.0001 | +| loss | -0.0975 | +| n_updates | 128920 | +| policy_gradient_loss | -0.0689 | +| value_loss | 0.000585 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | -0.0163 | +| time/ | | +| fps | 309 | +| iterations | 6841 | +| time_elapsed | 22628 | +| total_timesteps | 7005184 | +| train/ | | +| approx_kl | 1.7812865 | +| clip_fraction | 0.482 | +| clip_range | 0.2 | +| entropy_loss | -0.422 | +| explained_variance | -1.41 | +| learning_rate | 0.0001 | +| loss | -0.0806 | +| n_updates | 128930 | +| policy_gradient_loss | -0.0694 | +| value_loss | 0.000431 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | -0.0126 | +| time/ | | +| fps | 309 | +| iterations | 6842 | +| time_elapsed | 22631 | +| total_timesteps | 7006208 | +| train/ | | +| approx_kl | 2.1150658 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.448 | +| explained_variance | -1.93 | +| learning_rate | 0.0001 | +| loss | -0.0818 | +| n_updates | 128940 | +| policy_gradient_loss | -0.068 | +| value_loss | 0.000528 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | -0.0127 | +| time/ | | +| fps | 309 | +| iterations | 6843 | +| time_elapsed | 22634 | +| total_timesteps | 7007232 | +| train/ | | +| approx_kl | 2.1090136 | +| clip_fraction | 0.418 | +| clip_range | 0.2 | +| entropy_loss | -0.366 | +| explained_variance | -10.3 | +| learning_rate | 0.0001 | +| loss | -0.08 | +| n_updates | 128950 | +| policy_gradient_loss | -0.0541 | +| value_loss | 0.00055 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | -0.00812 | +| time/ | | +| fps | 309 | +| iterations | 6844 | +| time_elapsed | 22637 | +| total_timesteps | 7008256 | +| train/ | | +| approx_kl | 1.5548737 | +| clip_fraction | 0.457 | +| clip_range | 0.2 | +| entropy_loss | -0.381 | +| explained_variance | -1.35 | +| learning_rate | 0.0001 | +| loss | -0.0684 | +| n_updates | 128960 | +| policy_gradient_loss | -0.0607 | +| value_loss | 0.000716 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | -0.00812 | +| time/ | | +| fps | 309 | +| iterations | 6845 | +| time_elapsed | 22640 | +| total_timesteps | 7009280 | +| train/ | | +| approx_kl | 2.0612268 | +| clip_fraction | 0.441 | +| clip_range | 0.2 | +| entropy_loss | -0.347 | +| explained_variance | -3.74 | +| learning_rate | 0.0001 | +| loss | -0.063 | +| n_updates | 128970 | +| policy_gradient_loss | -0.0538 | +| value_loss | 0.000863 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | -0.00991 | +| time/ | | +| fps | 309 | +| iterations | 6846 | +| time_elapsed | 22644 | +| total_timesteps | 7010304 | +| train/ | | +| approx_kl | 2.4195654 | +| clip_fraction | 0.482 | +| clip_range | 0.2 | +| entropy_loss | -0.5 | +| explained_variance | -5.06 | +| learning_rate | 0.0001 | +| loss | -0.0747 | +| n_updates | 128980 | +| policy_gradient_loss | -0.0618 | +| value_loss | 0.000721 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | -0.015 | +| time/ | | +| fps | 309 | +| iterations | 6847 | +| time_elapsed | 22647 | +| total_timesteps | 7011328 | +| train/ | | +| approx_kl | 1.738466 | +| clip_fraction | 0.463 | +| clip_range | 0.2 | +| entropy_loss | -0.441 | +| explained_variance | -1.87 | +| learning_rate | 0.0001 | +| loss | -0.0854 | +| n_updates | 128990 | +| policy_gradient_loss | -0.0652 | +| value_loss | 0.00046 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | -0.015 | +| time/ | | +| fps | 309 | +| iterations | 6848 | +| time_elapsed | 22650 | +| total_timesteps | 7012352 | +| train/ | | +| approx_kl | 2.1990135 | +| clip_fraction | 0.465 | +| clip_range | 0.2 | +| entropy_loss | -0.387 | +| explained_variance | -4.42 | +| learning_rate | 0.0001 | +| loss | -0.0703 | +| n_updates | 129000 | +| policy_gradient_loss | -0.0656 | +| value_loss | 0.000575 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | -0.015 | +| time/ | | +| fps | 309 | +| iterations | 6849 | +| time_elapsed | 22653 | +| total_timesteps | 7013376 | +| train/ | | +| approx_kl | 2.6448598 | +| clip_fraction | 0.496 | +| clip_range | 0.2 | +| entropy_loss | -0.42 | +| explained_variance | -2.53 | +| learning_rate | 0.0001 | +| loss | -0.0681 | +| n_updates | 129010 | +| policy_gradient_loss | -0.0688 | +| value_loss | 0.00035 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | -0.015 | +| time/ | | +| fps | 309 | +| iterations | 6850 | +| time_elapsed | 22656 | +| total_timesteps | 7014400 | +| train/ | | +| approx_kl | 3.0553532 | +| clip_fraction | 0.479 | +| clip_range | 0.2 | +| entropy_loss | -0.405 | +| explained_variance | -0.661 | +| learning_rate | 0.0001 | +| loss | -0.0875 | +| n_updates | 129020 | +| policy_gradient_loss | -0.0617 | +| value_loss | 0.000701 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | -0.0128 | +| time/ | | +| fps | 309 | +| iterations | 6851 | +| time_elapsed | 22659 | +| total_timesteps | 7015424 | +| train/ | | +| approx_kl | 2.216086 | +| clip_fraction | 0.463 | +| clip_range | 0.2 | +| entropy_loss | -0.369 | +| explained_variance | -8.79 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 129030 | +| policy_gradient_loss | -0.0676 | +| value_loss | 0.000842 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | -0.0164 | +| time/ | | +| fps | 309 | +| iterations | 6852 | +| time_elapsed | 22663 | +| total_timesteps | 7016448 | +| train/ | | +| approx_kl | 2.1495202 | +| clip_fraction | 0.438 | +| clip_range | 0.2 | +| entropy_loss | -0.387 | +| explained_variance | -5.74 | +| learning_rate | 0.0001 | +| loss | -0.0958 | +| n_updates | 129040 | +| policy_gradient_loss | -0.0543 | +| value_loss | 0.000591 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | -0.0137 | +| time/ | | +| fps | 309 | +| iterations | 6853 | +| time_elapsed | 22666 | +| total_timesteps | 7017472 | +| train/ | | +| approx_kl | 2.4252954 | +| clip_fraction | 0.418 | +| clip_range | 0.2 | +| entropy_loss | -0.326 | +| explained_variance | -3.55 | +| learning_rate | 0.0001 | +| loss | -0.0682 | +| n_updates | 129050 | +| policy_gradient_loss | -0.0561 | +| value_loss | 0.000605 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | -0.0137 | +| time/ | | +| fps | 309 | +| iterations | 6854 | +| time_elapsed | 22670 | +| total_timesteps | 7018496 | +| train/ | | +| approx_kl | 3.3560119 | +| clip_fraction | 0.434 | +| clip_range | 0.2 | +| entropy_loss | -0.353 | +| explained_variance | -4.27 | +| learning_rate | 0.0001 | +| loss | -0.0899 | +| n_updates | 129060 | +| policy_gradient_loss | -0.0612 | +| value_loss | 0.00044 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | -0.0178 | +| time/ | | +| fps | 309 | +| iterations | 6855 | +| time_elapsed | 22673 | +| total_timesteps | 7019520 | +| train/ | | +| approx_kl | 2.0937762 | +| clip_fraction | 0.464 | +| clip_range | 0.2 | +| entropy_loss | -0.365 | +| explained_variance | -2.64 | +| learning_rate | 0.0001 | +| loss | -0.0928 | +| n_updates | 129070 | +| policy_gradient_loss | -0.0672 | +| value_loss | 0.000677 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | -0.0178 | +| time/ | | +| fps | 309 | +| iterations | 6856 | +| time_elapsed | 22677 | +| total_timesteps | 7020544 | +| train/ | | +| approx_kl | 2.6331353 | +| clip_fraction | 0.433 | +| clip_range | 0.2 | +| entropy_loss | -0.326 | +| explained_variance | -2.89 | +| learning_rate | 0.0001 | +| loss | -0.0838 | +| n_updates | 129080 | +| policy_gradient_loss | -0.0621 | +| value_loss | 0.000569 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | -0.0185 | +| time/ | | +| fps | 309 | +| iterations | 6857 | +| time_elapsed | 22680 | +| total_timesteps | 7021568 | +| train/ | | +| approx_kl | 3.724016 | +| clip_fraction | 0.446 | +| clip_range | 0.2 | +| entropy_loss | -0.34 | +| explained_variance | -2.39 | +| learning_rate | 0.0001 | +| loss | -0.0704 | +| n_updates | 129090 | +| policy_gradient_loss | -0.0635 | +| value_loss | 0.000546 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | -0.0185 | +| time/ | | +| fps | 309 | +| iterations | 6858 | +| time_elapsed | 22684 | +| total_timesteps | 7022592 | +| train/ | | +| approx_kl | 2.2680478 | +| clip_fraction | 0.426 | +| clip_range | 0.2 | +| entropy_loss | -0.362 | +| explained_variance | -3.46 | +| learning_rate | 0.0001 | +| loss | -0.0729 | +| n_updates | 129100 | +| policy_gradient_loss | -0.0622 | +| value_loss | 0.000553 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | -0.0124 | +| time/ | | +| fps | 309 | +| iterations | 6859 | +| time_elapsed | 22687 | +| total_timesteps | 7023616 | +| train/ | | +| approx_kl | 3.0192027 | +| clip_fraction | 0.458 | +| clip_range | 0.2 | +| entropy_loss | -0.358 | +| explained_variance | -1.76 | +| learning_rate | 0.0001 | +| loss | -0.0947 | +| n_updates | 129110 | +| policy_gradient_loss | -0.0701 | +| value_loss | 0.000753 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | -0.0111 | +| time/ | | +| fps | 309 | +| iterations | 6860 | +| time_elapsed | 22690 | +| total_timesteps | 7024640 | +| train/ | | +| approx_kl | 2.17625 | +| clip_fraction | 0.46 | +| clip_range | 0.2 | +| entropy_loss | -0.384 | +| explained_variance | -5.96 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 129120 | +| policy_gradient_loss | -0.0568 | +| value_loss | 0.000359 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | -0.0111 | +| time/ | | +| fps | 309 | +| iterations | 6861 | +| time_elapsed | 22694 | +| total_timesteps | 7025664 | +| train/ | | +| approx_kl | 2.6340642 | +| clip_fraction | 0.444 | +| clip_range | 0.2 | +| entropy_loss | -0.49 | +| explained_variance | -1.7 | +| learning_rate | 0.0001 | +| loss | -0.0629 | +| n_updates | 129130 | +| policy_gradient_loss | -0.0561 | +| value_loss | 0.000512 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | -0.0137 | +| time/ | | +| fps | 309 | +| iterations | 6862 | +| time_elapsed | 22697 | +| total_timesteps | 7026688 | +| train/ | | +| approx_kl | 1.6299114 | +| clip_fraction | 0.508 | +| clip_range | 0.2 | +| entropy_loss | -0.506 | +| explained_variance | -8.76 | +| learning_rate | 0.0001 | +| loss | -0.0815 | +| n_updates | 129140 | +| policy_gradient_loss | -0.0478 | +| value_loss | 0.000639 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | -0.0177 | +| time/ | | +| fps | 309 | +| iterations | 6863 | +| time_elapsed | 22700 | +| total_timesteps | 7027712 | +| train/ | | +| approx_kl | 2.2976565 | +| clip_fraction | 0.432 | +| clip_range | 0.2 | +| entropy_loss | -0.355 | +| explained_variance | -1.34 | +| learning_rate | 0.0001 | +| loss | -0.0437 | +| n_updates | 129150 | +| policy_gradient_loss | -0.0621 | +| value_loss | 0.000483 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | -0.0177 | +| time/ | | +| fps | 309 | +| iterations | 6864 | +| time_elapsed | 22703 | +| total_timesteps | 7028736 | +| train/ | | +| approx_kl | 1.715337 | +| clip_fraction | 0.438 | +| clip_range | 0.2 | +| entropy_loss | -0.375 | +| explained_variance | -1.35 | +| learning_rate | 0.0001 | +| loss | -0.0711 | +| n_updates | 129160 | +| policy_gradient_loss | -0.0626 | +| value_loss | 0.000793 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | -0.0178 | +| time/ | | +| fps | 309 | +| iterations | 6865 | +| time_elapsed | 22706 | +| total_timesteps | 7029760 | +| train/ | | +| approx_kl | 1.7473104 | +| clip_fraction | 0.501 | +| clip_range | 0.2 | +| entropy_loss | -0.455 | +| explained_variance | -8.07 | +| learning_rate | 0.0001 | +| loss | -0.0837 | +| n_updates | 129170 | +| policy_gradient_loss | -0.0512 | +| value_loss | 0.000477 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | -0.0235 | +| time/ | | +| fps | 309 | +| iterations | 6866 | +| time_elapsed | 22710 | +| total_timesteps | 7030784 | +| train/ | | +| approx_kl | 1.9688501 | +| clip_fraction | 0.457 | +| clip_range | 0.2 | +| entropy_loss | -0.392 | +| explained_variance | -4.63 | +| learning_rate | 0.0001 | +| loss | -0.0771 | +| n_updates | 129180 | +| policy_gradient_loss | -0.0373 | +| value_loss | 0.00053 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | -0.0235 | +| time/ | | +| fps | 309 | +| iterations | 6867 | +| time_elapsed | 22713 | +| total_timesteps | 7031808 | +| train/ | | +| approx_kl | 1.8546388 | +| clip_fraction | 0.445 | +| clip_range | 0.2 | +| entropy_loss | -0.336 | +| explained_variance | -1.72 | +| learning_rate | 0.0001 | +| loss | -0.0447 | +| n_updates | 129190 | +| policy_gradient_loss | -0.0578 | +| value_loss | 0.000981 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | -0.0238 | +| time/ | | +| fps | 309 | +| iterations | 6868 | +| time_elapsed | 22716 | +| total_timesteps | 7032832 | +| train/ | | +| approx_kl | 2.1348195 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.375 | +| explained_variance | -1.47 | +| learning_rate | 0.0001 | +| loss | -0.0705 | +| n_updates | 129200 | +| policy_gradient_loss | -0.061 | +| value_loss | 0.000671 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | -0.0238 | +| time/ | | +| fps | 309 | +| iterations | 6869 | +| time_elapsed | 22719 | +| total_timesteps | 7033856 | +| train/ | | +| approx_kl | 1.9155746 | +| clip_fraction | 0.456 | +| clip_range | 0.2 | +| entropy_loss | -0.359 | +| explained_variance | -6.67 | +| learning_rate | 0.0001 | +| loss | -0.0806 | +| n_updates | 129210 | +| policy_gradient_loss | -0.0652 | +| value_loss | 0.000426 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | -0.0229 | +| time/ | | +| fps | 309 | +| iterations | 6870 | +| time_elapsed | 22723 | +| total_timesteps | 7034880 | +| train/ | | +| approx_kl | 1.8795481 | +| clip_fraction | 0.457 | +| clip_range | 0.2 | +| entropy_loss | -0.347 | +| explained_variance | -5.79 | +| learning_rate | 0.0001 | +| loss | -0.0877 | +| n_updates | 129220 | +| policy_gradient_loss | -0.0584 | +| value_loss | 0.000552 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | -0.0229 | +| time/ | | +| fps | 309 | +| iterations | 6871 | +| time_elapsed | 22726 | +| total_timesteps | 7035904 | +| train/ | | +| approx_kl | 2.0445814 | +| clip_fraction | 0.466 | +| clip_range | 0.2 | +| entropy_loss | -0.389 | +| explained_variance | -2.52 | +| learning_rate | 0.0001 | +| loss | -0.0752 | +| n_updates | 129230 | +| policy_gradient_loss | -0.0643 | +| value_loss | 0.000662 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | -0.0236 | +| time/ | | +| fps | 309 | +| iterations | 6872 | +| time_elapsed | 22729 | +| total_timesteps | 7036928 | +| train/ | | +| approx_kl | 1.7530456 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.475 | +| explained_variance | -6.83 | +| learning_rate | 0.0001 | +| loss | -0.0983 | +| n_updates | 129240 | +| policy_gradient_loss | -0.0585 | +| value_loss | 0.000282 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | -0.0258 | +| time/ | | +| fps | 309 | +| iterations | 6873 | +| time_elapsed | 22733 | +| total_timesteps | 7037952 | +| train/ | | +| approx_kl | 3.3305829 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.464 | +| explained_variance | -3.17 | +| learning_rate | 0.0001 | +| loss | -0.0639 | +| n_updates | 129250 | +| policy_gradient_loss | -0.0635 | +| value_loss | 0.00044 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | -0.0258 | +| time/ | | +| fps | 309 | +| iterations | 6874 | +| time_elapsed | 22736 | +| total_timesteps | 7038976 | +| train/ | | +| approx_kl | 1.894932 | +| clip_fraction | 0.442 | +| clip_range | 0.2 | +| entropy_loss | -0.336 | +| explained_variance | -1.68 | +| learning_rate | 0.0001 | +| loss | -0.0578 | +| n_updates | 129260 | +| policy_gradient_loss | -0.0616 | +| value_loss | 0.000499 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | -0.0258 | +| time/ | | +| fps | 309 | +| iterations | 6875 | +| time_elapsed | 22739 | +| total_timesteps | 7040000 | +| train/ | | +| approx_kl | 2.8713865 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.396 | +| explained_variance | -2.87 | +| learning_rate | 0.0001 | +| loss | -0.0871 | +| n_updates | 129270 | +| policy_gradient_loss | -0.0606 | +| value_loss | 0.000558 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | -0.0269 | +| time/ | | +| fps | 309 | +| iterations | 6876 | +| time_elapsed | 22743 | +| total_timesteps | 7041024 | +| train/ | | +| approx_kl | 1.8773408 | +| clip_fraction | 0.431 | +| clip_range | 0.2 | +| entropy_loss | -0.331 | +| explained_variance | -2.24 | +| learning_rate | 0.0001 | +| loss | -0.086 | +| n_updates | 129280 | +| policy_gradient_loss | -0.063 | +| value_loss | 0.000772 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | -0.0325 | +| time/ | | +| fps | 309 | +| iterations | 6877 | +| time_elapsed | 22746 | +| total_timesteps | 7042048 | +| train/ | | +| approx_kl | 2.544929 | +| clip_fraction | 0.442 | +| clip_range | 0.2 | +| entropy_loss | -0.349 | +| explained_variance | -4.97 | +| learning_rate | 0.0001 | +| loss | -0.0669 | +| n_updates | 129290 | +| policy_gradient_loss | -0.0672 | +| value_loss | 0.000464 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | -0.0336 | +| time/ | | +| fps | 309 | +| iterations | 6878 | +| time_elapsed | 22749 | +| total_timesteps | 7043072 | +| train/ | | +| approx_kl | 2.0180075 | +| clip_fraction | 0.436 | +| clip_range | 0.2 | +| entropy_loss | -0.386 | +| explained_variance | -2.8 | +| learning_rate | 0.0001 | +| loss | -0.066 | +| n_updates | 129300 | +| policy_gradient_loss | -0.0601 | +| value_loss | 0.000441 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | -0.0336 | +| time/ | | +| fps | 309 | +| iterations | 6879 | +| time_elapsed | 22752 | +| total_timesteps | 7044096 | +| train/ | | +| approx_kl | 2.0596771 | +| clip_fraction | 0.46 | +| clip_range | 0.2 | +| entropy_loss | -0.35 | +| explained_variance | -3.25 | +| learning_rate | 0.0001 | +| loss | -0.0917 | +| n_updates | 129310 | +| policy_gradient_loss | -0.0577 | +| value_loss | 0.000839 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | -0.0338 | +| time/ | | +| fps | 309 | +| iterations | 6880 | +| time_elapsed | 22756 | +| total_timesteps | 7045120 | +| train/ | | +| approx_kl | 1.7723335 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.392 | +| explained_variance | -2.57 | +| learning_rate | 0.0001 | +| loss | -0.0961 | +| n_updates | 129320 | +| policy_gradient_loss | -0.0684 | +| value_loss | 0.000633 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | -0.0338 | +| time/ | | +| fps | 309 | +| iterations | 6881 | +| time_elapsed | 22759 | +| total_timesteps | 7046144 | +| train/ | | +| approx_kl | 1.9813573 | +| clip_fraction | 0.458 | +| clip_range | 0.2 | +| entropy_loss | -0.43 | +| explained_variance | -3.26 | +| learning_rate | 0.0001 | +| loss | -0.0723 | +| n_updates | 129330 | +| policy_gradient_loss | -0.0562 | +| value_loss | 0.00036 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | -0.0338 | +| time/ | | +| fps | 309 | +| iterations | 6882 | +| time_elapsed | 22762 | +| total_timesteps | 7047168 | +| train/ | | +| approx_kl | 1.7172759 | +| clip_fraction | 0.473 | +| clip_range | 0.2 | +| entropy_loss | -0.428 | +| explained_variance | -8.1 | +| learning_rate | 0.0001 | +| loss | -0.0695 | +| n_updates | 129340 | +| policy_gradient_loss | -0.067 | +| value_loss | 0.000531 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | -0.0309 | +| time/ | | +| fps | 309 | +| iterations | 6883 | +| time_elapsed | 22765 | +| total_timesteps | 7048192 | +| train/ | | +| approx_kl | 2.0818424 | +| clip_fraction | 0.473 | +| clip_range | 0.2 | +| entropy_loss | -0.365 | +| explained_variance | -1.54 | +| learning_rate | 0.0001 | +| loss | -0.0826 | +| n_updates | 129350 | +| policy_gradient_loss | -0.0652 | +| value_loss | 0.000644 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | -0.0309 | +| time/ | | +| fps | 309 | +| iterations | 6884 | +| time_elapsed | 22768 | +| total_timesteps | 7049216 | +| train/ | | +| approx_kl | 1.6737664 | +| clip_fraction | 0.438 | +| clip_range | 0.2 | +| entropy_loss | -0.358 | +| explained_variance | -7.73 | +| learning_rate | 0.0001 | +| loss | -0.0735 | +| n_updates | 129360 | +| policy_gradient_loss | -0.054 | +| value_loss | 0.000652 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | -0.0296 | +| time/ | | +| fps | 309 | +| iterations | 6885 | +| time_elapsed | 22772 | +| total_timesteps | 7050240 | +| train/ | | +| approx_kl | 3.4179971 | +| clip_fraction | 0.51 | +| clip_range | 0.2 | +| entropy_loss | -0.471 | +| explained_variance | -1.78 | +| learning_rate | 0.0001 | +| loss | -0.0822 | +| n_updates | 129370 | +| policy_gradient_loss | -0.0662 | +| value_loss | 0.000579 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | -0.0287 | +| time/ | | +| fps | 309 | +| iterations | 6886 | +| time_elapsed | 22775 | +| total_timesteps | 7051264 | +| train/ | | +| approx_kl | 2.2619758 | +| clip_fraction | 0.438 | +| clip_range | 0.2 | +| entropy_loss | -0.373 | +| explained_variance | -2.09 | +| learning_rate | 0.0001 | +| loss | -0.0141 | +| n_updates | 129380 | +| policy_gradient_loss | -0.055 | +| value_loss | 0.000752 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | -0.0287 | +| time/ | | +| fps | 309 | +| iterations | 6887 | +| time_elapsed | 22778 | +| total_timesteps | 7052288 | +| train/ | | +| approx_kl | 1.9278338 | +| clip_fraction | 0.433 | +| clip_range | 0.2 | +| entropy_loss | -0.327 | +| explained_variance | -3.1 | +| learning_rate | 0.0001 | +| loss | -0.0915 | +| n_updates | 129390 | +| policy_gradient_loss | -0.0571 | +| value_loss | 0.000466 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | -0.0363 | +| time/ | | +| fps | 309 | +| iterations | 6888 | +| time_elapsed | 22782 | +| total_timesteps | 7053312 | +| train/ | | +| approx_kl | 1.7838353 | +| clip_fraction | 0.463 | +| clip_range | 0.2 | +| entropy_loss | -0.357 | +| explained_variance | -4.9 | +| learning_rate | 0.0001 | +| loss | -0.0711 | +| n_updates | 129400 | +| policy_gradient_loss | -0.0669 | +| value_loss | 0.000503 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | -0.0363 | +| time/ | | +| fps | 309 | +| iterations | 6889 | +| time_elapsed | 22785 | +| total_timesteps | 7054336 | +| train/ | | +| approx_kl | 2.358677 | +| clip_fraction | 0.428 | +| clip_range | 0.2 | +| entropy_loss | -0.339 | +| explained_variance | -6 | +| learning_rate | 0.0001 | +| loss | -0.1 | +| n_updates | 129410 | +| policy_gradient_loss | -0.0615 | +| value_loss | 0.000661 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | -0.0363 | +| time/ | | +| fps | 309 | +| iterations | 6890 | +| time_elapsed | 22788 | +| total_timesteps | 7055360 | +| train/ | | +| approx_kl | 2.031901 | +| clip_fraction | 0.474 | +| clip_range | 0.2 | +| entropy_loss | -0.405 | +| explained_variance | -4.06 | +| learning_rate | 0.0001 | +| loss | -0.0812 | +| n_updates | 129420 | +| policy_gradient_loss | -0.0599 | +| value_loss | 0.000621 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | -0.0396 | +| time/ | | +| fps | 309 | +| iterations | 6891 | +| time_elapsed | 22792 | +| total_timesteps | 7056384 | +| train/ | | +| approx_kl | 2.1281276 | +| clip_fraction | 0.46 | +| clip_range | 0.2 | +| entropy_loss | -0.379 | +| explained_variance | -1.66 | +| learning_rate | 0.0001 | +| loss | -0.105 | +| n_updates | 129430 | +| policy_gradient_loss | -0.0647 | +| value_loss | 0.00057 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | -0.0442 | +| time/ | | +| fps | 309 | +| iterations | 6892 | +| time_elapsed | 22795 | +| total_timesteps | 7057408 | +| train/ | | +| approx_kl | 1.8358274 | +| clip_fraction | 0.486 | +| clip_range | 0.2 | +| entropy_loss | -0.411 | +| explained_variance | -2.16 | +| learning_rate | 0.0001 | +| loss | -0.0766 | +| n_updates | 129440 | +| policy_gradient_loss | -0.0683 | +| value_loss | 0.000513 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | -0.0442 | +| time/ | | +| fps | 309 | +| iterations | 6893 | +| time_elapsed | 22799 | +| total_timesteps | 7058432 | +| train/ | | +| approx_kl | 1.9979903 | +| clip_fraction | 0.499 | +| clip_range | 0.2 | +| entropy_loss | -0.473 | +| explained_variance | -0.833 | +| learning_rate | 0.0001 | +| loss | -0.0526 | +| n_updates | 129450 | +| policy_gradient_loss | -0.0564 | +| value_loss | 0.000547 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | -0.0423 | +| time/ | | +| fps | 309 | +| iterations | 6894 | +| time_elapsed | 22802 | +| total_timesteps | 7059456 | +| train/ | | +| approx_kl | 2.1479144 | +| clip_fraction | 0.499 | +| clip_range | 0.2 | +| entropy_loss | -0.41 | +| explained_variance | -2.99 | +| learning_rate | 0.0001 | +| loss | -0.09 | +| n_updates | 129460 | +| policy_gradient_loss | -0.0637 | +| value_loss | 0.000503 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | -0.0423 | +| time/ | | +| fps | 309 | +| iterations | 6895 | +| time_elapsed | 22806 | +| total_timesteps | 7060480 | +| train/ | | +| approx_kl | 2.1413746 | +| clip_fraction | 0.505 | +| clip_range | 0.2 | +| entropy_loss | -0.427 | +| explained_variance | -1.75 | +| learning_rate | 0.0001 | +| loss | -0.0761 | +| n_updates | 129470 | +| policy_gradient_loss | -0.0666 | +| value_loss | 0.000618 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | -0.0423 | +| time/ | | +| fps | 309 | +| iterations | 6896 | +| time_elapsed | 22809 | +| total_timesteps | 7061504 | +| train/ | | +| approx_kl | 1.8507525 | +| clip_fraction | 0.49 | +| clip_range | 0.2 | +| entropy_loss | -0.413 | +| explained_variance | -5.11 | +| learning_rate | 0.0001 | +| loss | -0.082 | +| n_updates | 129480 | +| policy_gradient_loss | -0.0643 | +| value_loss | 0.000693 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | -0.0475 | +| time/ | | +| fps | 309 | +| iterations | 6897 | +| time_elapsed | 22813 | +| total_timesteps | 7062528 | +| train/ | | +| approx_kl | 1.7639859 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.447 | +| explained_variance | -9.21 | +| learning_rate | 0.0001 | +| loss | -0.0931 | +| n_updates | 129490 | +| policy_gradient_loss | -0.0613 | +| value_loss | 0.00021 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | -0.0498 | +| time/ | | +| fps | 309 | +| iterations | 6898 | +| time_elapsed | 22816 | +| total_timesteps | 7063552 | +| train/ | | +| approx_kl | 1.7720544 | +| clip_fraction | 0.5 | +| clip_range | 0.2 | +| entropy_loss | -0.541 | +| explained_variance | -0.879 | +| learning_rate | 0.0001 | +| loss | -0.0833 | +| n_updates | 129500 | +| policy_gradient_loss | -0.061 | +| value_loss | 0.000247 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | -0.0594 | +| time/ | | +| fps | 309 | +| iterations | 6899 | +| time_elapsed | 22819 | +| total_timesteps | 7064576 | +| train/ | | +| approx_kl | 1.7564042 | +| clip_fraction | 0.458 | +| clip_range | 0.2 | +| entropy_loss | -0.369 | +| explained_variance | -1.63 | +| learning_rate | 0.0001 | +| loss | -0.0809 | +| n_updates | 129510 | +| policy_gradient_loss | -0.0642 | +| value_loss | 0.000533 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | -0.0594 | +| time/ | | +| fps | 309 | +| iterations | 6900 | +| time_elapsed | 22822 | +| total_timesteps | 7065600 | +| train/ | | +| approx_kl | 3.3607974 | +| clip_fraction | 0.436 | +| clip_range | 0.2 | +| entropy_loss | -0.36 | +| explained_variance | -0.652 | +| learning_rate | 0.0001 | +| loss | -0.0976 | +| n_updates | 129520 | +| policy_gradient_loss | -0.0629 | +| value_loss | 0.000659 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | -0.0661 | +| time/ | | +| fps | 309 | +| iterations | 6901 | +| time_elapsed | 22825 | +| total_timesteps | 7066624 | +| train/ | | +| approx_kl | 1.64733 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.463 | +| explained_variance | -8.83 | +| learning_rate | 0.0001 | +| loss | -0.0874 | +| n_updates | 129530 | +| policy_gradient_loss | -0.0706 | +| value_loss | 0.000476 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | -0.0661 | +| time/ | | +| fps | 309 | +| iterations | 6902 | +| time_elapsed | 22829 | +| total_timesteps | 7067648 | +| train/ | | +| approx_kl | 2.6139927 | +| clip_fraction | 0.442 | +| clip_range | 0.2 | +| entropy_loss | -0.345 | +| explained_variance | -1.56 | +| learning_rate | 0.0001 | +| loss | -0.0831 | +| n_updates | 129540 | +| policy_gradient_loss | -0.0652 | +| value_loss | 0.000741 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | -0.0616 | +| time/ | | +| fps | 309 | +| iterations | 6903 | +| time_elapsed | 22832 | +| total_timesteps | 7068672 | +| train/ | | +| approx_kl | 1.9003829 | +| clip_fraction | 0.474 | +| clip_range | 0.2 | +| entropy_loss | -0.419 | +| explained_variance | -3.68 | +| learning_rate | 0.0001 | +| loss | -0.113 | +| n_updates | 129550 | +| policy_gradient_loss | -0.064 | +| value_loss | 0.000685 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | -0.0616 | +| time/ | | +| fps | 309 | +| iterations | 6904 | +| time_elapsed | 22835 | +| total_timesteps | 7069696 | +| train/ | | +| approx_kl | 2.9053936 | +| clip_fraction | 0.464 | +| clip_range | 0.2 | +| entropy_loss | -0.386 | +| explained_variance | -3.77 | +| learning_rate | 0.0001 | +| loss | -0.0887 | +| n_updates | 129560 | +| policy_gradient_loss | -0.0663 | +| value_loss | 0.000698 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | -0.0677 | +| time/ | | +| fps | 309 | +| iterations | 6905 | +| time_elapsed | 22838 | +| total_timesteps | 7070720 | +| train/ | | +| approx_kl | 2.568027 | +| clip_fraction | 0.465 | +| clip_range | 0.2 | +| entropy_loss | -0.399 | +| explained_variance | -7.51 | +| learning_rate | 0.0001 | +| loss | -0.0833 | +| n_updates | 129570 | +| policy_gradient_loss | -0.0597 | +| value_loss | 0.000448 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | -0.0698 | +| time/ | | +| fps | 309 | +| iterations | 6906 | +| time_elapsed | 22842 | +| total_timesteps | 7071744 | +| train/ | | +| approx_kl | 1.782222 | +| clip_fraction | 0.452 | +| clip_range | 0.2 | +| entropy_loss | -0.368 | +| explained_variance | -1.53 | +| learning_rate | 0.0001 | +| loss | -0.0942 | +| n_updates | 129580 | +| policy_gradient_loss | -0.0637 | +| value_loss | 0.000724 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | -0.0698 | +| time/ | | +| fps | 309 | +| iterations | 6907 | +| time_elapsed | 22845 | +| total_timesteps | 7072768 | +| train/ | | +| approx_kl | 7.6008167 | +| clip_fraction | 0.465 | +| clip_range | 0.2 | +| entropy_loss | -0.412 | +| explained_variance | -1.08 | +| learning_rate | 0.0001 | +| loss | 0.0675 | +| n_updates | 129590 | +| policy_gradient_loss | -0.052 | +| value_loss | 0.000707 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | -0.0659 | +| time/ | | +| fps | 309 | +| iterations | 6908 | +| time_elapsed | 22848 | +| total_timesteps | 7073792 | +| train/ | | +| approx_kl | 2.5087242 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.342 | +| explained_variance | -1.6 | +| learning_rate | 0.0001 | +| loss | -0.0907 | +| n_updates | 129600 | +| policy_gradient_loss | -0.0654 | +| value_loss | 0.000695 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | -0.0659 | +| time/ | | +| fps | 309 | +| iterations | 6909 | +| time_elapsed | 22851 | +| total_timesteps | 7074816 | +| train/ | | +| approx_kl | 1.7318873 | +| clip_fraction | 0.505 | +| clip_range | 0.2 | +| entropy_loss | -0.439 | +| explained_variance | -1.54 | +| learning_rate | 0.0001 | +| loss | -0.0891 | +| n_updates | 129610 | +| policy_gradient_loss | -0.0716 | +| value_loss | 0.00044 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | -0.0658 | +| time/ | | +| fps | 309 | +| iterations | 6910 | +| time_elapsed | 22855 | +| total_timesteps | 7075840 | +| train/ | | +| approx_kl | 1.9710159 | +| clip_fraction | 0.508 | +| clip_range | 0.2 | +| entropy_loss | -0.437 | +| explained_variance | -1.83 | +| learning_rate | 0.0001 | +| loss | -0.0819 | +| n_updates | 129620 | +| policy_gradient_loss | -0.0713 | +| value_loss | 0.000381 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | -0.0643 | +| time/ | | +| fps | 309 | +| iterations | 6911 | +| time_elapsed | 22858 | +| total_timesteps | 7076864 | +| train/ | | +| approx_kl | 2.1439695 | +| clip_fraction | 0.457 | +| clip_range | 0.2 | +| entropy_loss | -0.404 | +| explained_variance | -1.12 | +| learning_rate | 0.0001 | +| loss | -0.0867 | +| n_updates | 129630 | +| policy_gradient_loss | -0.059 | +| value_loss | 0.000397 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | -0.0643 | +| time/ | | +| fps | 309 | +| iterations | 6912 | +| time_elapsed | 22861 | +| total_timesteps | 7077888 | +| train/ | | +| approx_kl | 1.7443423 | +| clip_fraction | 0.441 | +| clip_range | 0.2 | +| entropy_loss | -0.381 | +| explained_variance | -6.77 | +| learning_rate | 0.0001 | +| loss | -0.0779 | +| n_updates | 129640 | +| policy_gradient_loss | -0.0628 | +| value_loss | 0.000627 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | -0.0646 | +| time/ | | +| fps | 309 | +| iterations | 6913 | +| time_elapsed | 22865 | +| total_timesteps | 7078912 | +| train/ | | +| approx_kl | 2.1215732 | +| clip_fraction | 0.502 | +| clip_range | 0.2 | +| entropy_loss | -0.466 | +| explained_variance | -2.83 | +| learning_rate | 0.0001 | +| loss | -0.0668 | +| n_updates | 129650 | +| policy_gradient_loss | -0.062 | +| value_loss | 0.000576 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | -0.0646 | +| time/ | | +| fps | 309 | +| iterations | 6914 | +| time_elapsed | 22868 | +| total_timesteps | 7079936 | +| train/ | | +| approx_kl | 1.5155066 | +| clip_fraction | 0.466 | +| clip_range | 0.2 | +| entropy_loss | -0.428 | +| explained_variance | -3.89 | +| learning_rate | 0.0001 | +| loss | -0.108 | +| n_updates | 129660 | +| policy_gradient_loss | -0.0703 | +| value_loss | 0.000343 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | -0.0659 | +| time/ | | +| fps | 309 | +| iterations | 6915 | +| time_elapsed | 22871 | +| total_timesteps | 7080960 | +| train/ | | +| approx_kl | 2.0369463 | +| clip_fraction | 0.5 | +| clip_range | 0.2 | +| entropy_loss | -0.425 | +| explained_variance | -3.03 | +| learning_rate | 0.0001 | +| loss | -0.0812 | +| n_updates | 129670 | +| policy_gradient_loss | -0.0727 | +| value_loss | 0.000506 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | -0.0662 | +| time/ | | +| fps | 309 | +| iterations | 6916 | +| time_elapsed | 22874 | +| total_timesteps | 7081984 | +| train/ | | +| approx_kl | 1.7194841 | +| clip_fraction | 0.461 | +| clip_range | 0.2 | +| entropy_loss | -0.419 | +| explained_variance | -3.73 | +| learning_rate | 0.0001 | +| loss | -0.088 | +| n_updates | 129680 | +| policy_gradient_loss | -0.0576 | +| value_loss | 0.000408 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | -0.0662 | +| time/ | | +| fps | 309 | +| iterations | 6917 | +| time_elapsed | 22877 | +| total_timesteps | 7083008 | +| train/ | | +| approx_kl | 2.2786534 | +| clip_fraction | 0.477 | +| clip_range | 0.2 | +| entropy_loss | -0.414 | +| explained_variance | -2.37 | +| learning_rate | 0.0001 | +| loss | -0.0808 | +| n_updates | 129690 | +| policy_gradient_loss | -0.0704 | +| value_loss | 0.000363 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | -0.0691 | +| time/ | | +| fps | 309 | +| iterations | 6918 | +| time_elapsed | 22880 | +| total_timesteps | 7084032 | +| train/ | | +| approx_kl | 1.855357 | +| clip_fraction | 0.461 | +| clip_range | 0.2 | +| entropy_loss | -0.327 | +| explained_variance | -3.95 | +| learning_rate | 0.0001 | +| loss | -0.0754 | +| n_updates | 129700 | +| policy_gradient_loss | -0.0672 | +| value_loss | 0.000324 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | -0.0691 | +| time/ | | +| fps | 309 | +| iterations | 6919 | +| time_elapsed | 22884 | +| total_timesteps | 7085056 | +| train/ | | +| approx_kl | 2.0853236 | +| clip_fraction | 0.421 | +| clip_range | 0.2 | +| entropy_loss | -0.298 | +| explained_variance | -0.984 | +| learning_rate | 0.0001 | +| loss | -0.077 | +| n_updates | 129710 | +| policy_gradient_loss | -0.0656 | +| value_loss | 0.000761 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | -0.0653 | +| time/ | | +| fps | 309 | +| iterations | 6920 | +| time_elapsed | 22887 | +| total_timesteps | 7086080 | +| train/ | | +| approx_kl | 1.9663501 | +| clip_fraction | 0.442 | +| clip_range | 0.2 | +| entropy_loss | -0.307 | +| explained_variance | -2.64 | +| learning_rate | 0.0001 | +| loss | -0.0557 | +| n_updates | 129720 | +| policy_gradient_loss | -0.0589 | +| value_loss | 0.000813 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | -0.0653 | +| time/ | | +| fps | 309 | +| iterations | 6921 | +| time_elapsed | 22890 | +| total_timesteps | 7087104 | +| train/ | | +| approx_kl | 2.1902971 | +| clip_fraction | 0.467 | +| clip_range | 0.2 | +| entropy_loss | -0.379 | +| explained_variance | -6.14 | +| learning_rate | 0.0001 | +| loss | -0.0897 | +| n_updates | 129730 | +| policy_gradient_loss | -0.0709 | +| value_loss | 0.000508 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | -0.0627 | +| time/ | | +| fps | 309 | +| iterations | 6922 | +| time_elapsed | 22893 | +| total_timesteps | 7088128 | +| train/ | | +| approx_kl | 2.138829 | +| clip_fraction | 0.466 | +| clip_range | 0.2 | +| entropy_loss | -0.453 | +| explained_variance | -3.07 | +| learning_rate | 0.0001 | +| loss | -0.0331 | +| n_updates | 129740 | +| policy_gradient_loss | -0.0629 | +| value_loss | 0.000447 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | -0.0625 | +| time/ | | +| fps | 309 | +| iterations | 6923 | +| time_elapsed | 22896 | +| total_timesteps | 7089152 | +| train/ | | +| approx_kl | 1.7191755 | +| clip_fraction | 0.488 | +| clip_range | 0.2 | +| entropy_loss | -0.431 | +| explained_variance | -5.88 | +| learning_rate | 0.0001 | +| loss | -0.0781 | +| n_updates | 129750 | +| policy_gradient_loss | -0.0645 | +| value_loss | 0.000351 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | -0.0625 | +| time/ | | +| fps | 309 | +| iterations | 6924 | +| time_elapsed | 22899 | +| total_timesteps | 7090176 | +| train/ | | +| approx_kl | 1.6377099 | +| clip_fraction | 0.436 | +| clip_range | 0.2 | +| entropy_loss | -0.381 | +| explained_variance | -2.41 | +| learning_rate | 0.0001 | +| loss | -0.0711 | +| n_updates | 129760 | +| policy_gradient_loss | -0.0584 | +| value_loss | 0.00077 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | -0.0686 | +| time/ | | +| fps | 309 | +| iterations | 6925 | +| time_elapsed | 22903 | +| total_timesteps | 7091200 | +| train/ | | +| approx_kl | 1.5986913 | +| clip_fraction | 0.497 | +| clip_range | 0.2 | +| entropy_loss | -0.514 | +| explained_variance | -4.06 | +| learning_rate | 0.0001 | +| loss | -0.0655 | +| n_updates | 129770 | +| policy_gradient_loss | -0.0619 | +| value_loss | 0.000452 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | -0.0686 | +| time/ | | +| fps | 309 | +| iterations | 6926 | +| time_elapsed | 22906 | +| total_timesteps | 7092224 | +| train/ | | +| approx_kl | 1.8661004 | +| clip_fraction | 0.432 | +| clip_range | 0.2 | +| entropy_loss | -0.319 | +| explained_variance | -2.31 | +| learning_rate | 0.0001 | +| loss | -0.0819 | +| n_updates | 129780 | +| policy_gradient_loss | -0.0599 | +| value_loss | 0.000596 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | -0.0745 | +| time/ | | +| fps | 309 | +| iterations | 6927 | +| time_elapsed | 22910 | +| total_timesteps | 7093248 | +| train/ | | +| approx_kl | 1.7053589 | +| clip_fraction | 0.486 | +| clip_range | 0.2 | +| entropy_loss | -0.455 | +| explained_variance | -7 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 129790 | +| policy_gradient_loss | -0.0614 | +| value_loss | 0.000562 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | -0.0745 | +| time/ | | +| fps | 309 | +| iterations | 6928 | +| time_elapsed | 22913 | +| total_timesteps | 7094272 | +| train/ | | +| approx_kl | 1.8913388 | +| clip_fraction | 0.457 | +| clip_range | 0.2 | +| entropy_loss | -0.357 | +| explained_variance | -5.73 | +| learning_rate | 0.0001 | +| loss | -0.0973 | +| n_updates | 129800 | +| policy_gradient_loss | -0.0556 | +| value_loss | 0.0007 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | -0.0729 | +| time/ | | +| fps | 309 | +| iterations | 6929 | +| time_elapsed | 22917 | +| total_timesteps | 7095296 | +| train/ | | +| approx_kl | 1.8936455 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.408 | +| explained_variance | -1.97 | +| learning_rate | 0.0001 | +| loss | -0.0749 | +| n_updates | 129810 | +| policy_gradient_loss | -0.0648 | +| value_loss | 0.000714 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | -0.0785 | +| time/ | | +| fps | 309 | +| iterations | 6930 | +| time_elapsed | 22920 | +| total_timesteps | 7096320 | +| train/ | | +| approx_kl | 1.8758588 | +| clip_fraction | 0.485 | +| clip_range | 0.2 | +| entropy_loss | -0.436 | +| explained_variance | -7.65 | +| learning_rate | 0.0001 | +| loss | -0.115 | +| n_updates | 129820 | +| policy_gradient_loss | -0.0682 | +| value_loss | 0.000359 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | -0.0787 | +| time/ | | +| fps | 309 | +| iterations | 6931 | +| time_elapsed | 22924 | +| total_timesteps | 7097344 | +| train/ | | +| approx_kl | 1.8878738 | +| clip_fraction | 0.46 | +| clip_range | 0.2 | +| entropy_loss | -0.397 | +| explained_variance | -1.21 | +| learning_rate | 0.0001 | +| loss | -0.0807 | +| n_updates | 129830 | +| policy_gradient_loss | -0.059 | +| value_loss | 0.000481 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | -0.0787 | +| time/ | | +| fps | 309 | +| iterations | 6932 | +| time_elapsed | 22927 | +| total_timesteps | 7098368 | +| train/ | | +| approx_kl | 1.7366686 | +| clip_fraction | 0.469 | +| clip_range | 0.2 | +| entropy_loss | -0.4 | +| explained_variance | -1.11 | +| learning_rate | 0.0001 | +| loss | -0.0776 | +| n_updates | 129840 | +| policy_gradient_loss | -0.064 | +| value_loss | 0.000703 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | -0.0746 | +| time/ | | +| fps | 309 | +| iterations | 6933 | +| time_elapsed | 22930 | +| total_timesteps | 7099392 | +| train/ | | +| approx_kl | 1.6182513 | +| clip_fraction | 0.479 | +| clip_range | 0.2 | +| entropy_loss | -0.401 | +| explained_variance | -2.38 | +| learning_rate | 0.0001 | +| loss | -0.0804 | +| n_updates | 129850 | +| policy_gradient_loss | -0.0567 | +| value_loss | 0.000657 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | -0.0746 | +| time/ | | +| fps | 309 | +| iterations | 6934 | +| time_elapsed | 22934 | +| total_timesteps | 7100416 | +| train/ | | +| approx_kl | 1.4831337 | +| clip_fraction | 0.465 | +| clip_range | 0.2 | +| entropy_loss | -0.446 | +| explained_variance | -8.34 | +| learning_rate | 0.0001 | +| loss | -0.0558 | +| n_updates | 129860 | +| policy_gradient_loss | -0.0643 | +| value_loss | 0.000286 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | -0.0727 | +| time/ | | +| fps | 309 | +| iterations | 6935 | +| time_elapsed | 22937 | +| total_timesteps | 7101440 | +| train/ | | +| approx_kl | 1.558134 | +| clip_fraction | 0.506 | +| clip_range | 0.2 | +| entropy_loss | -0.491 | +| explained_variance | -1.76 | +| learning_rate | 0.0001 | +| loss | -0.0899 | +| n_updates | 129870 | +| policy_gradient_loss | -0.0708 | +| value_loss | 0.000465 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | -0.0728 | +| time/ | | +| fps | 309 | +| iterations | 6936 | +| time_elapsed | 22940 | +| total_timesteps | 7102464 | +| train/ | | +| approx_kl | 1.452988 | +| clip_fraction | 0.468 | +| clip_range | 0.2 | +| entropy_loss | -0.473 | +| explained_variance | -5.8 | +| learning_rate | 0.0001 | +| loss | -0.0896 | +| n_updates | 129880 | +| policy_gradient_loss | -0.064 | +| value_loss | 0.000252 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | -0.0728 | +| time/ | | +| fps | 309 | +| iterations | 6937 | +| time_elapsed | 22943 | +| total_timesteps | 7103488 | +| train/ | | +| approx_kl | 2.1091645 | +| clip_fraction | 0.462 | +| clip_range | 0.2 | +| entropy_loss | -0.439 | +| explained_variance | -1.26 | +| learning_rate | 0.0001 | +| loss | -0.0977 | +| n_updates | 129890 | +| policy_gradient_loss | -0.0598 | +| value_loss | 0.000392 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | -0.0766 | +| time/ | | +| fps | 309 | +| iterations | 6938 | +| time_elapsed | 22946 | +| total_timesteps | 7104512 | +| train/ | | +| approx_kl | 1.7489238 | +| clip_fraction | 0.488 | +| clip_range | 0.2 | +| entropy_loss | -0.487 | +| explained_variance | -6.98 | +| learning_rate | 0.0001 | +| loss | -0.0786 | +| n_updates | 129900 | +| policy_gradient_loss | -0.0667 | +| value_loss | 0.00033 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | -0.0766 | +| time/ | | +| fps | 309 | +| iterations | 6939 | +| time_elapsed | 22949 | +| total_timesteps | 7105536 | +| train/ | | +| approx_kl | 1.431663 | +| clip_fraction | 0.443 | +| clip_range | 0.2 | +| entropy_loss | -0.449 | +| explained_variance | -1.49 | +| learning_rate | 0.0001 | +| loss | -0.0427 | +| n_updates | 129910 | +| policy_gradient_loss | -0.0529 | +| value_loss | 0.000485 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | -0.0799 | +| time/ | | +| fps | 309 | +| iterations | 6940 | +| time_elapsed | 22953 | +| total_timesteps | 7106560 | +| train/ | | +| approx_kl | 1.7743356 | +| clip_fraction | 0.527 | +| clip_range | 0.2 | +| entropy_loss | -0.478 | +| explained_variance | -3.23 | +| learning_rate | 0.0001 | +| loss | -0.0917 | +| n_updates | 129920 | +| policy_gradient_loss | -0.0671 | +| value_loss | 0.000527 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | -0.0821 | +| time/ | | +| fps | 309 | +| iterations | 6941 | +| time_elapsed | 22956 | +| total_timesteps | 7107584 | +| train/ | | +| approx_kl | 1.8998426 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.471 | +| explained_variance | -11.8 | +| learning_rate | 0.0001 | +| loss | -0.0999 | +| n_updates | 129930 | +| policy_gradient_loss | -0.062 | +| value_loss | 0.000761 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | -0.0821 | +| time/ | | +| fps | 309 | +| iterations | 6942 | +| time_elapsed | 22959 | +| total_timesteps | 7108608 | +| train/ | | +| approx_kl | 1.7760316 | +| clip_fraction | 0.438 | +| clip_range | 0.2 | +| entropy_loss | -0.367 | +| explained_variance | -4.19 | +| learning_rate | 0.0001 | +| loss | -0.0678 | +| n_updates | 129940 | +| policy_gradient_loss | -0.059 | +| value_loss | 0.000765 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | -0.0822 | +| time/ | | +| fps | 309 | +| iterations | 6943 | +| time_elapsed | 22963 | +| total_timesteps | 7109632 | +| train/ | | +| approx_kl | 1.3487244 | +| clip_fraction | 0.515 | +| clip_range | 0.2 | +| entropy_loss | -0.64 | +| explained_variance | -8.82 | +| learning_rate | 0.0001 | +| loss | -0.0999 | +| n_updates | 129950 | +| policy_gradient_loss | -0.0733 | +| value_loss | 0.000231 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | -0.0822 | +| time/ | | +| fps | 309 | +| iterations | 6944 | +| time_elapsed | 22966 | +| total_timesteps | 7110656 | +| train/ | | +| approx_kl | 2.0163364 | +| clip_fraction | 0.469 | +| clip_range | 0.2 | +| entropy_loss | -0.403 | +| explained_variance | -2.34 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 129960 | +| policy_gradient_loss | -0.0664 | +| value_loss | 0.000378 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | -0.0812 | +| time/ | | +| fps | 309 | +| iterations | 6945 | +| time_elapsed | 22970 | +| total_timesteps | 7111680 | +| train/ | | +| approx_kl | 2.3570533 | +| clip_fraction | 0.478 | +| clip_range | 0.2 | +| entropy_loss | -0.447 | +| explained_variance | -2.97 | +| learning_rate | 0.0001 | +| loss | -0.0673 | +| n_updates | 129970 | +| policy_gradient_loss | -0.0676 | +| value_loss | 0.000431 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | -0.0835 | +| time/ | | +| fps | 309 | +| iterations | 6946 | +| time_elapsed | 22973 | +| total_timesteps | 7112704 | +| train/ | | +| approx_kl | 1.7128707 | +| clip_fraction | 0.484 | +| clip_range | 0.2 | +| entropy_loss | -0.443 | +| explained_variance | -1.48 | +| learning_rate | 0.0001 | +| loss | -0.0953 | +| n_updates | 129980 | +| policy_gradient_loss | -0.0657 | +| value_loss | 0.000573 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | -0.0835 | +| time/ | | +| fps | 309 | +| iterations | 6947 | +| time_elapsed | 22977 | +| total_timesteps | 7113728 | +| train/ | | +| approx_kl | 2.1115093 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.534 | +| explained_variance | -1.46 | +| learning_rate | 0.0001 | +| loss | -0.0899 | +| n_updates | 129990 | +| policy_gradient_loss | -0.0634 | +| value_loss | 0.000345 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | -0.0832 | +| time/ | | +| fps | 309 | +| iterations | 6948 | +| time_elapsed | 22980 | +| total_timesteps | 7114752 | +| train/ | | +| approx_kl | 2.0832534 | +| clip_fraction | 0.446 | +| clip_range | 0.2 | +| entropy_loss | -0.361 | +| explained_variance | -6.34 | +| learning_rate | 0.0001 | +| loss | -0.0527 | +| n_updates | 130000 | +| policy_gradient_loss | -0.064 | +| value_loss | 0.00052 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | -0.0806 | +| time/ | | +| fps | 309 | +| iterations | 6949 | +| time_elapsed | 22984 | +| total_timesteps | 7115776 | +| train/ | | +| approx_kl | 2.1428454 | +| clip_fraction | 0.463 | +| clip_range | 0.2 | +| entropy_loss | -0.437 | +| explained_variance | -1.76 | +| learning_rate | 0.0001 | +| loss | -0.0911 | +| n_updates | 130010 | +| policy_gradient_loss | -0.0645 | +| value_loss | 0.000398 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | -0.0806 | +| time/ | | +| fps | 309 | +| iterations | 6950 | +| time_elapsed | 22987 | +| total_timesteps | 7116800 | +| train/ | | +| approx_kl | 1.9346206 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.375 | +| explained_variance | -3.25 | +| learning_rate | 0.0001 | +| loss | -0.0825 | +| n_updates | 130020 | +| policy_gradient_loss | -0.0641 | +| value_loss | 0.000751 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | -0.0802 | +| time/ | | +| fps | 309 | +| iterations | 6951 | +| time_elapsed | 22990 | +| total_timesteps | 7117824 | +| train/ | | +| approx_kl | 1.818422 | +| clip_fraction | 0.517 | +| clip_range | 0.2 | +| entropy_loss | -0.475 | +| explained_variance | -3.72 | +| learning_rate | 0.0001 | +| loss | -0.0787 | +| n_updates | 130030 | +| policy_gradient_loss | -0.0635 | +| value_loss | 0.000633 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | -0.0871 | +| time/ | | +| fps | 309 | +| iterations | 6952 | +| time_elapsed | 22994 | +| total_timesteps | 7118848 | +| train/ | | +| approx_kl | 2.7781813 | +| clip_fraction | 0.488 | +| clip_range | 0.2 | +| entropy_loss | -0.485 | +| explained_variance | -5.51 | +| learning_rate | 0.0001 | +| loss | -0.0584 | +| n_updates | 130040 | +| policy_gradient_loss | -0.0614 | +| value_loss | 0.000669 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | -0.0871 | +| time/ | | +| fps | 309 | +| iterations | 6953 | +| time_elapsed | 22997 | +| total_timesteps | 7119872 | +| train/ | | +| approx_kl | 1.5898907 | +| clip_fraction | 0.47 | +| clip_range | 0.2 | +| entropy_loss | -0.463 | +| explained_variance | -1.87 | +| learning_rate | 0.0001 | +| loss | -0.082 | +| n_updates | 130050 | +| policy_gradient_loss | -0.0565 | +| value_loss | 0.000693 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | -0.0919 | +| time/ | | +| fps | 309 | +| iterations | 6954 | +| time_elapsed | 23000 | +| total_timesteps | 7120896 | +| train/ | | +| approx_kl | 1.9314713 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.456 | +| explained_variance | -10.8 | +| learning_rate | 0.0001 | +| loss | -0.0894 | +| n_updates | 130060 | +| policy_gradient_loss | -0.0597 | +| value_loss | 0.000526 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | -0.0882 | +| time/ | | +| fps | 309 | +| iterations | 6955 | +| time_elapsed | 23003 | +| total_timesteps | 7121920 | +| train/ | | +| approx_kl | 2.063212 | +| clip_fraction | 0.498 | +| clip_range | 0.2 | +| entropy_loss | -0.454 | +| explained_variance | -1.43 | +| learning_rate | 0.0001 | +| loss | -0.115 | +| n_updates | 130070 | +| policy_gradient_loss | -0.0609 | +| value_loss | 0.000344 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | -0.0882 | +| time/ | | +| fps | 309 | +| iterations | 6956 | +| time_elapsed | 23006 | +| total_timesteps | 7122944 | +| train/ | | +| approx_kl | 1.5271236 | +| clip_fraction | 0.468 | +| clip_range | 0.2 | +| entropy_loss | -0.43 | +| explained_variance | -2.97 | +| learning_rate | 0.0001 | +| loss | -0.0918 | +| n_updates | 130080 | +| policy_gradient_loss | -0.0622 | +| value_loss | 0.000596 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | -0.0854 | +| time/ | | +| fps | 309 | +| iterations | 6957 | +| time_elapsed | 23010 | +| total_timesteps | 7123968 | +| train/ | | +| approx_kl | 1.6047246 | +| clip_fraction | 0.506 | +| clip_range | 0.2 | +| entropy_loss | -0.505 | +| explained_variance | -2.72 | +| learning_rate | 0.0001 | +| loss | -0.0661 | +| n_updates | 130090 | +| policy_gradient_loss | -0.0643 | +| value_loss | 0.000459 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | -0.0854 | +| time/ | | +| fps | 309 | +| iterations | 6958 | +| time_elapsed | 23013 | +| total_timesteps | 7124992 | +| train/ | | +| approx_kl | 1.9471595 | +| clip_fraction | 0.489 | +| clip_range | 0.2 | +| entropy_loss | -0.426 | +| explained_variance | -4.4 | +| learning_rate | 0.0001 | +| loss | -0.0723 | +| n_updates | 130100 | +| policy_gradient_loss | -0.0653 | +| value_loss | 0.000317 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | -0.0818 | +| time/ | | +| fps | 309 | +| iterations | 6959 | +| time_elapsed | 23016 | +| total_timesteps | 7126016 | +| train/ | | +| approx_kl | 1.7106603 | +| clip_fraction | 0.546 | +| clip_range | 0.2 | +| entropy_loss | -0.602 | +| explained_variance | -2.52 | +| learning_rate | 0.0001 | +| loss | -0.0928 | +| n_updates | 130110 | +| policy_gradient_loss | -0.0685 | +| value_loss | 0.000247 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | -0.0857 | +| time/ | | +| fps | 309 | +| iterations | 6960 | +| time_elapsed | 23019 | +| total_timesteps | 7127040 | +| train/ | | +| approx_kl | 1.8548367 | +| clip_fraction | 0.504 | +| clip_range | 0.2 | +| entropy_loss | -0.551 | +| explained_variance | -1.16 | +| learning_rate | 0.0001 | +| loss | -0.0845 | +| n_updates | 130120 | +| policy_gradient_loss | -0.0693 | +| value_loss | 0.000444 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | -0.0857 | +| time/ | | +| fps | 309 | +| iterations | 6961 | +| time_elapsed | 23023 | +| total_timesteps | 7128064 | +| train/ | | +| approx_kl | 1.4871347 | +| clip_fraction | 0.486 | +| clip_range | 0.2 | +| entropy_loss | -0.604 | +| explained_variance | -1.62 | +| learning_rate | 0.0001 | +| loss | -0.0567 | +| n_updates | 130130 | +| policy_gradient_loss | -0.0529 | +| value_loss | 0.000478 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | -0.0864 | +| time/ | | +| fps | 309 | +| iterations | 6962 | +| time_elapsed | 23026 | +| total_timesteps | 7129088 | +| train/ | | +| approx_kl | 1.7445651 | +| clip_fraction | 0.498 | +| clip_range | 0.2 | +| entropy_loss | -0.472 | +| explained_variance | -2.16 | +| learning_rate | 0.0001 | +| loss | -0.0866 | +| n_updates | 130140 | +| policy_gradient_loss | -0.0644 | +| value_loss | 0.000529 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | -0.0864 | +| time/ | | +| fps | 309 | +| iterations | 6963 | +| time_elapsed | 23030 | +| total_timesteps | 7130112 | +| train/ | | +| approx_kl | 2.5448837 | +| clip_fraction | 0.469 | +| clip_range | 0.2 | +| entropy_loss | -0.424 | +| explained_variance | -5.97 | +| learning_rate | 0.0001 | +| loss | -0.0848 | +| n_updates | 130150 | +| policy_gradient_loss | -0.045 | +| value_loss | 0.000572 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | -0.0864 | +| time/ | | +| fps | 309 | +| iterations | 6964 | +| time_elapsed | 23033 | +| total_timesteps | 7131136 | +| train/ | | +| approx_kl | 1.8093363 | +| clip_fraction | 0.461 | +| clip_range | 0.2 | +| entropy_loss | -0.468 | +| explained_variance | -2.26 | +| learning_rate | 0.0001 | +| loss | -0.087 | +| n_updates | 130160 | +| policy_gradient_loss | -0.063 | +| value_loss | 0.000498 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | -0.0871 | +| time/ | | +| fps | 309 | +| iterations | 6965 | +| time_elapsed | 23037 | +| total_timesteps | 7132160 | +| train/ | | +| approx_kl | 1.5932808 | +| clip_fraction | 0.529 | +| clip_range | 0.2 | +| entropy_loss | -0.545 | +| explained_variance | -4.13 | +| learning_rate | 0.0001 | +| loss | -0.105 | +| n_updates | 130170 | +| policy_gradient_loss | -0.0773 | +| value_loss | 0.000287 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | -0.0881 | +| time/ | | +| fps | 309 | +| iterations | 6966 | +| time_elapsed | 23040 | +| total_timesteps | 7133184 | +| train/ | | +| approx_kl | 1.7917516 | +| clip_fraction | 0.503 | +| clip_range | 0.2 | +| entropy_loss | -0.488 | +| explained_variance | -3.17 | +| learning_rate | 0.0001 | +| loss | -0.095 | +| n_updates | 130180 | +| policy_gradient_loss | -0.0649 | +| value_loss | 0.000468 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | -0.0881 | +| time/ | | +| fps | 309 | +| iterations | 6967 | +| time_elapsed | 23044 | +| total_timesteps | 7134208 | +| train/ | | +| approx_kl | 4.04243 | +| clip_fraction | 0.501 | +| clip_range | 0.2 | +| entropy_loss | -0.51 | +| explained_variance | -0.768 | +| learning_rate | 0.0001 | +| loss | -0.0507 | +| n_updates | 130190 | +| policy_gradient_loss | -0.0589 | +| value_loss | 0.00055 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | -0.0926 | +| time/ | | +| fps | 309 | +| iterations | 6968 | +| time_elapsed | 23047 | +| total_timesteps | 7135232 | +| train/ | | +| approx_kl | 1.7083837 | +| clip_fraction | 0.504 | +| clip_range | 0.2 | +| entropy_loss | -0.494 | +| explained_variance | -4.7 | +| learning_rate | 0.0001 | +| loss | -0.11 | +| n_updates | 130200 | +| policy_gradient_loss | -0.0717 | +| value_loss | 0.000619 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | -0.0926 | +| time/ | | +| fps | 309 | +| iterations | 6969 | +| time_elapsed | 23050 | +| total_timesteps | 7136256 | +| train/ | | +| approx_kl | 1.7969601 | +| clip_fraction | 0.505 | +| clip_range | 0.2 | +| entropy_loss | -0.491 | +| explained_variance | -4.06 | +| learning_rate | 0.0001 | +| loss | -0.089 | +| n_updates | 130210 | +| policy_gradient_loss | -0.0648 | +| value_loss | 0.00103 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | -0.0912 | +| time/ | | +| fps | 309 | +| iterations | 6970 | +| time_elapsed | 23054 | +| total_timesteps | 7137280 | +| train/ | | +| approx_kl | 1.5423429 | +| clip_fraction | 0.504 | +| clip_range | 0.2 | +| entropy_loss | -0.454 | +| explained_variance | -5.65 | +| learning_rate | 0.0001 | +| loss | -0.0876 | +| n_updates | 130220 | +| policy_gradient_loss | -0.0705 | +| value_loss | 0.00071 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | -0.0909 | +| time/ | | +| fps | 309 | +| iterations | 6971 | +| time_elapsed | 23057 | +| total_timesteps | 7138304 | +| train/ | | +| approx_kl | 1.6844137 | +| clip_fraction | 0.507 | +| clip_range | 0.2 | +| entropy_loss | -0.434 | +| explained_variance | -2.68 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 130230 | +| policy_gradient_loss | -0.0756 | +| value_loss | 0.000507 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | -0.0903 | +| time/ | | +| fps | 309 | +| iterations | 6972 | +| time_elapsed | 23060 | +| total_timesteps | 7139328 | +| train/ | | +| approx_kl | 2.6211724 | +| clip_fraction | 0.503 | +| clip_range | 0.2 | +| entropy_loss | -0.47 | +| explained_variance | -1.82 | +| learning_rate | 0.0001 | +| loss | -0.0837 | +| n_updates | 130240 | +| policy_gradient_loss | -0.0659 | +| value_loss | 0.00055 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | -0.0903 | +| time/ | | +| fps | 309 | +| iterations | 6973 | +| time_elapsed | 23063 | +| total_timesteps | 7140352 | +| train/ | | +| approx_kl | 1.7066078 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.433 | +| explained_variance | -2.88 | +| learning_rate | 0.0001 | +| loss | -0.0795 | +| n_updates | 130250 | +| policy_gradient_loss | -0.0678 | +| value_loss | 0.000491 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | -0.0952 | +| time/ | | +| fps | 309 | +| iterations | 6974 | +| time_elapsed | 23066 | +| total_timesteps | 7141376 | +| train/ | | +| approx_kl | 2.7938118 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.466 | +| explained_variance | -5.04 | +| learning_rate | 0.0001 | +| loss | -0.0804 | +| n_updates | 130260 | +| policy_gradient_loss | -0.0625 | +| value_loss | 0.000287 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | -0.0952 | +| time/ | | +| fps | 309 | +| iterations | 6975 | +| time_elapsed | 23070 | +| total_timesteps | 7142400 | +| train/ | | +| approx_kl | 1.6300958 | +| clip_fraction | 0.469 | +| clip_range | 0.2 | +| entropy_loss | -0.445 | +| explained_variance | -0.676 | +| learning_rate | 0.0001 | +| loss | -0.0629 | +| n_updates | 130270 | +| policy_gradient_loss | -0.0582 | +| value_loss | 0.000515 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | -0.0911 | +| time/ | | +| fps | 309 | +| iterations | 6976 | +| time_elapsed | 23073 | +| total_timesteps | 7143424 | +| train/ | | +| approx_kl | 1.851013 | +| clip_fraction | 0.508 | +| clip_range | 0.2 | +| entropy_loss | -0.462 | +| explained_variance | -3.78 | +| learning_rate | 0.0001 | +| loss | -0.0524 | +| n_updates | 130280 | +| policy_gradient_loss | -0.0692 | +| value_loss | 0.000291 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | -0.0927 | +| time/ | | +| fps | 309 | +| iterations | 6977 | +| time_elapsed | 23076 | +| total_timesteps | 7144448 | +| train/ | | +| approx_kl | 1.921495 | +| clip_fraction | 0.517 | +| clip_range | 0.2 | +| entropy_loss | -0.53 | +| explained_variance | -2.89 | +| learning_rate | 0.0001 | +| loss | -0.0939 | +| n_updates | 130290 | +| policy_gradient_loss | -0.0666 | +| value_loss | 0.000302 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | -0.0891 | +| time/ | | +| fps | 309 | +| iterations | 6978 | +| time_elapsed | 23079 | +| total_timesteps | 7145472 | +| train/ | | +| approx_kl | 3.3970673 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.418 | +| explained_variance | -1.03 | +| learning_rate | 0.0001 | +| loss | -0.0897 | +| n_updates | 130300 | +| policy_gradient_loss | -0.0621 | +| value_loss | 0.000585 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.65e+03 | +| ep_rew_mean | -0.0892 | +| time/ | | +| fps | 309 | +| iterations | 6979 | +| time_elapsed | 23083 | +| total_timesteps | 7146496 | +| train/ | | +| approx_kl | 1.9603223 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.404 | +| explained_variance | -3.03 | +| learning_rate | 0.0001 | +| loss | -0.122 | +| n_updates | 130310 | +| policy_gradient_loss | -0.0741 | +| value_loss | 0.000616 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.65e+03 | +| ep_rew_mean | -0.088 | +| time/ | | +| fps | 309 | +| iterations | 6980 | +| time_elapsed | 23086 | +| total_timesteps | 7147520 | +| train/ | | +| approx_kl | 2.1392207 | +| clip_fraction | 0.466 | +| clip_range | 0.2 | +| entropy_loss | -0.386 | +| explained_variance | -3.35 | +| learning_rate | 0.0001 | +| loss | -0.089 | +| n_updates | 130320 | +| policy_gradient_loss | -0.0653 | +| value_loss | 0.000532 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.65e+03 | +| ep_rew_mean | -0.088 | +| time/ | | +| fps | 309 | +| iterations | 6981 | +| time_elapsed | 23090 | +| total_timesteps | 7148544 | +| train/ | | +| approx_kl | 1.6041377 | +| clip_fraction | 0.498 | +| clip_range | 0.2 | +| entropy_loss | -0.489 | +| explained_variance | -2.3 | +| learning_rate | 0.0001 | +| loss | -0.0966 | +| n_updates | 130330 | +| policy_gradient_loss | -0.0691 | +| value_loss | 0.000455 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.65e+03 | +| ep_rew_mean | -0.0885 | +| time/ | | +| fps | 309 | +| iterations | 6982 | +| time_elapsed | 23093 | +| total_timesteps | 7149568 | +| train/ | | +| approx_kl | 1.7810127 | +| clip_fraction | 0.451 | +| clip_range | 0.2 | +| entropy_loss | -0.469 | +| explained_variance | -2.64 | +| learning_rate | 0.0001 | +| loss | -0.0799 | +| n_updates | 130340 | +| policy_gradient_loss | -0.0529 | +| value_loss | 0.000575 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.65e+03 | +| ep_rew_mean | -0.0908 | +| time/ | | +| fps | 309 | +| iterations | 6983 | +| time_elapsed | 23096 | +| total_timesteps | 7150592 | +| train/ | | +| approx_kl | 1.8088044 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.468 | +| explained_variance | -1.92 | +| learning_rate | 0.0001 | +| loss | -0.083 | +| n_updates | 130350 | +| policy_gradient_loss | -0.0681 | +| value_loss | 0.000501 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.65e+03 | +| ep_rew_mean | -0.0908 | +| time/ | | +| fps | 309 | +| iterations | 6984 | +| time_elapsed | 23100 | +| total_timesteps | 7151616 | +| train/ | | +| approx_kl | 1.8158091 | +| clip_fraction | 0.488 | +| clip_range | 0.2 | +| entropy_loss | -0.514 | +| explained_variance | -1.41 | +| learning_rate | 0.0001 | +| loss | -0.0565 | +| n_updates | 130360 | +| policy_gradient_loss | -0.0647 | +| value_loss | 0.00075 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.65e+03 | +| ep_rew_mean | -0.0913 | +| time/ | | +| fps | 309 | +| iterations | 6985 | +| time_elapsed | 23103 | +| total_timesteps | 7152640 | +| train/ | | +| approx_kl | 2.1553192 | +| clip_fraction | 0.502 | +| clip_range | 0.2 | +| entropy_loss | -0.458 | +| explained_variance | -4.86 | +| learning_rate | 0.0001 | +| loss | -0.0906 | +| n_updates | 130370 | +| policy_gradient_loss | -0.0707 | +| value_loss | 0.000481 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.65e+03 | +| ep_rew_mean | -0.0913 | +| time/ | | +| fps | 309 | +| iterations | 6986 | +| time_elapsed | 23107 | +| total_timesteps | 7153664 | +| train/ | | +| approx_kl | 3.0101366 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.441 | +| explained_variance | -3.15 | +| learning_rate | 0.0001 | +| loss | -0.112 | +| n_updates | 130380 | +| policy_gradient_loss | -0.0704 | +| value_loss | 0.000338 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | -0.0927 | +| time/ | | +| fps | 309 | +| iterations | 6987 | +| time_elapsed | 23110 | +| total_timesteps | 7154688 | +| train/ | | +| approx_kl | 1.7146413 | +| clip_fraction | 0.524 | +| clip_range | 0.2 | +| entropy_loss | -0.563 | +| explained_variance | -3.7 | +| learning_rate | 0.0001 | +| loss | -0.1 | +| n_updates | 130390 | +| policy_gradient_loss | -0.0697 | +| value_loss | 0.000394 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | -0.0927 | +| time/ | | +| fps | 309 | +| iterations | 6988 | +| time_elapsed | 23113 | +| total_timesteps | 7155712 | +| train/ | | +| approx_kl | 6.8323975 | +| clip_fraction | 0.465 | +| clip_range | 0.2 | +| entropy_loss | -0.398 | +| explained_variance | -1.14 | +| learning_rate | 0.0001 | +| loss | -0.0697 | +| n_updates | 130400 | +| policy_gradient_loss | -0.059 | +| value_loss | 0.000578 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.65e+03 | +| ep_rew_mean | -0.0955 | +| time/ | | +| fps | 309 | +| iterations | 6989 | +| time_elapsed | 23116 | +| total_timesteps | 7156736 | +| train/ | | +| approx_kl | 1.4231677 | +| clip_fraction | 0.476 | +| clip_range | 0.2 | +| entropy_loss | -0.431 | +| explained_variance | -2.75 | +| learning_rate | 0.0001 | +| loss | -0.109 | +| n_updates | 130410 | +| policy_gradient_loss | -0.062 | +| value_loss | 0.000743 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.65e+03 | +| ep_rew_mean | -0.0955 | +| time/ | | +| fps | 309 | +| iterations | 6990 | +| time_elapsed | 23120 | +| total_timesteps | 7157760 | +| train/ | | +| approx_kl | 2.0435538 | +| clip_fraction | 0.464 | +| clip_range | 0.2 | +| entropy_loss | -0.443 | +| explained_variance | -3.89 | +| learning_rate | 0.0001 | +| loss | -0.0795 | +| n_updates | 130420 | +| policy_gradient_loss | -0.07 | +| value_loss | 0.00035 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.65e+03 | +| ep_rew_mean | -0.0954 | +| time/ | | +| fps | 309 | +| iterations | 6991 | +| time_elapsed | 23123 | +| total_timesteps | 7158784 | +| train/ | | +| approx_kl | 1.7359991 | +| clip_fraction | 0.491 | +| clip_range | 0.2 | +| entropy_loss | -0.501 | +| explained_variance | -5.84 | +| learning_rate | 0.0001 | +| loss | -0.0898 | +| n_updates | 130430 | +| policy_gradient_loss | -0.0684 | +| value_loss | 0.00026 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.65e+03 | +| ep_rew_mean | -0.0954 | +| time/ | | +| fps | 309 | +| iterations | 6992 | +| time_elapsed | 23126 | +| total_timesteps | 7159808 | +| train/ | | +| approx_kl | 1.6044037 | +| clip_fraction | 0.45 | +| clip_range | 0.2 | +| entropy_loss | -0.4 | +| explained_variance | -0.419 | +| learning_rate | 0.0001 | +| loss | -0.0736 | +| n_updates | 130440 | +| policy_gradient_loss | -0.0545 | +| value_loss | 0.00084 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | -0.0913 | +| time/ | | +| fps | 309 | +| iterations | 6993 | +| time_elapsed | 23129 | +| total_timesteps | 7160832 | +| train/ | | +| approx_kl | 1.8396156 | +| clip_fraction | 0.52 | +| clip_range | 0.2 | +| entropy_loss | -0.447 | +| explained_variance | -6.28 | +| learning_rate | 0.0001 | +| loss | -0.000454 | +| n_updates | 130450 | +| policy_gradient_loss | -0.0758 | +| value_loss | 0.000463 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | -0.0938 | +| time/ | | +| fps | 309 | +| iterations | 6994 | +| time_elapsed | 23132 | +| total_timesteps | 7161856 | +| train/ | | +| approx_kl | 1.66176 | +| clip_fraction | 0.502 | +| clip_range | 0.2 | +| entropy_loss | -0.472 | +| explained_variance | -1.62 | +| learning_rate | 0.0001 | +| loss | -0.0858 | +| n_updates | 130460 | +| policy_gradient_loss | -0.0649 | +| value_loss | 0.000385 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | -0.0938 | +| time/ | | +| fps | 309 | +| iterations | 6995 | +| time_elapsed | 23135 | +| total_timesteps | 7162880 | +| train/ | | +| approx_kl | 1.4378386 | +| clip_fraction | 0.444 | +| clip_range | 0.2 | +| entropy_loss | -0.415 | +| explained_variance | -2.37 | +| learning_rate | 0.0001 | +| loss | -0.107 | +| n_updates | 130470 | +| policy_gradient_loss | -0.0629 | +| value_loss | 0.000913 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | -0.0951 | +| time/ | | +| fps | 309 | +| iterations | 6996 | +| time_elapsed | 23139 | +| total_timesteps | 7163904 | +| train/ | | +| approx_kl | 1.571462 | +| clip_fraction | 0.502 | +| clip_range | 0.2 | +| entropy_loss | -0.488 | +| explained_variance | -2.98 | +| learning_rate | 0.0001 | +| loss | -0.08 | +| n_updates | 130480 | +| policy_gradient_loss | -0.0666 | +| value_loss | 0.000557 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | -0.0941 | +| time/ | | +| fps | 309 | +| iterations | 6997 | +| time_elapsed | 23142 | +| total_timesteps | 7164928 | +| train/ | | +| approx_kl | 2.4816093 | +| clip_fraction | 0.519 | +| clip_range | 0.2 | +| entropy_loss | -0.486 | +| explained_variance | -2.84 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 130490 | +| policy_gradient_loss | -0.0775 | +| value_loss | 0.000556 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | -0.0941 | +| time/ | | +| fps | 309 | +| iterations | 6998 | +| time_elapsed | 23145 | +| total_timesteps | 7165952 | +| train/ | | +| approx_kl | 4.454376 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.449 | +| explained_variance | -3.22 | +| learning_rate | 0.0001 | +| loss | 0.113 | +| n_updates | 130500 | +| policy_gradient_loss | -0.0638 | +| value_loss | 0.000363 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | -0.0947 | +| time/ | | +| fps | 309 | +| iterations | 6999 | +| time_elapsed | 23149 | +| total_timesteps | 7166976 | +| train/ | | +| approx_kl | 3.162402 | +| clip_fraction | 0.476 | +| clip_range | 0.2 | +| entropy_loss | -0.412 | +| explained_variance | -4.59 | +| learning_rate | 0.0001 | +| loss | -0.0844 | +| n_updates | 130510 | +| policy_gradient_loss | -0.0637 | +| value_loss | 0.000865 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | -0.0944 | +| time/ | | +| fps | 309 | +| iterations | 7000 | +| time_elapsed | 23152 | +| total_timesteps | 7168000 | +| train/ | | +| approx_kl | 2.0937443 | +| clip_fraction | 0.448 | +| clip_range | 0.2 | +| entropy_loss | -0.376 | +| explained_variance | -2.02 | +| learning_rate | 0.0001 | +| loss | -0.0967 | +| n_updates | 130520 | +| policy_gradient_loss | -0.0665 | +| value_loss | 0.000459 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | -0.0944 | +| time/ | | +| fps | 309 | +| iterations | 7001 | +| time_elapsed | 23156 | +| total_timesteps | 7169024 | +| train/ | | +| approx_kl | 1.6634462 | +| clip_fraction | 0.479 | +| clip_range | 0.2 | +| entropy_loss | -0.424 | +| explained_variance | -4.7 | +| learning_rate | 0.0001 | +| loss | -0.0755 | +| n_updates | 130530 | +| policy_gradient_loss | -0.0675 | +| value_loss | 0.000344 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | -0.0941 | +| time/ | | +| fps | 309 | +| iterations | 7002 | +| time_elapsed | 23159 | +| total_timesteps | 7170048 | +| train/ | | +| approx_kl | 2.0058384 | +| clip_fraction | 0.486 | +| clip_range | 0.2 | +| entropy_loss | -0.477 | +| explained_variance | -1.82 | +| learning_rate | 0.0001 | +| loss | -0.0948 | +| n_updates | 130540 | +| policy_gradient_loss | -0.0703 | +| value_loss | 0.000526 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | -0.0941 | +| time/ | | +| fps | 309 | +| iterations | 7003 | +| time_elapsed | 23163 | +| total_timesteps | 7171072 | +| train/ | | +| approx_kl | 2.2437158 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.368 | +| explained_variance | -1.26 | +| learning_rate | 0.0001 | +| loss | -0.0736 | +| n_updates | 130550 | +| policy_gradient_loss | -0.0724 | +| value_loss | 0.00057 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | -0.0942 | +| time/ | | +| fps | 309 | +| iterations | 7004 | +| time_elapsed | 23166 | +| total_timesteps | 7172096 | +| train/ | | +| approx_kl | 1.7675011 | +| clip_fraction | 0.479 | +| clip_range | 0.2 | +| entropy_loss | -0.531 | +| explained_variance | -2.92 | +| learning_rate | 0.0001 | +| loss | -0.0997 | +| n_updates | 130560 | +| policy_gradient_loss | -0.0662 | +| value_loss | 0.00034 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | -0.0942 | +| time/ | | +| fps | 309 | +| iterations | 7005 | +| time_elapsed | 23170 | +| total_timesteps | 7173120 | +| train/ | | +| approx_kl | 21.018692 | +| clip_fraction | 0.485 | +| clip_range | 0.2 | +| entropy_loss | -0.435 | +| explained_variance | -1.68 | +| learning_rate | 0.0001 | +| loss | -0.0809 | +| n_updates | 130570 | +| policy_gradient_loss | -0.0646 | +| value_loss | 0.000407 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | -0.088 | +| time/ | | +| fps | 309 | +| iterations | 7006 | +| time_elapsed | 23173 | +| total_timesteps | 7174144 | +| train/ | | +| approx_kl | 2.417293 | +| clip_fraction | 0.47 | +| clip_range | 0.2 | +| entropy_loss | -0.375 | +| explained_variance | -1.79 | +| learning_rate | 0.0001 | +| loss | -0.116 | +| n_updates | 130580 | +| policy_gradient_loss | -0.0647 | +| value_loss | 0.000862 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | -0.0887 | +| time/ | | +| fps | 309 | +| iterations | 7007 | +| time_elapsed | 23176 | +| total_timesteps | 7175168 | +| train/ | | +| approx_kl | 1.8951347 | +| clip_fraction | 0.476 | +| clip_range | 0.2 | +| entropy_loss | -0.404 | +| explained_variance | -1.45 | +| learning_rate | 0.0001 | +| loss | -0.0848 | +| n_updates | 130590 | +| policy_gradient_loss | -0.0624 | +| value_loss | 0.000581 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | -0.0887 | +| time/ | | +| fps | 309 | +| iterations | 7008 | +| time_elapsed | 23179 | +| total_timesteps | 7176192 | +| train/ | | +| approx_kl | 1.7854755 | +| clip_fraction | 0.479 | +| clip_range | 0.2 | +| entropy_loss | -0.534 | +| explained_variance | -5.75 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 130600 | +| policy_gradient_loss | -0.0621 | +| value_loss | 0.000222 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | -0.0847 | +| time/ | | +| fps | 309 | +| iterations | 7009 | +| time_elapsed | 23183 | +| total_timesteps | 7177216 | +| train/ | | +| approx_kl | 1.7573643 | +| clip_fraction | 0.53 | +| clip_range | 0.2 | +| entropy_loss | -0.576 | +| explained_variance | -0.532 | +| learning_rate | 0.0001 | +| loss | -0.0775 | +| n_updates | 130610 | +| policy_gradient_loss | -0.0653 | +| value_loss | 0.000504 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | -0.0844 | +| time/ | | +| fps | 309 | +| iterations | 7010 | +| time_elapsed | 23186 | +| total_timesteps | 7178240 | +| train/ | | +| approx_kl | 1.8302966 | +| clip_fraction | 0.442 | +| clip_range | 0.2 | +| entropy_loss | -0.368 | +| explained_variance | -3.11 | +| learning_rate | 0.0001 | +| loss | -0.0898 | +| n_updates | 130620 | +| policy_gradient_loss | -0.0694 | +| value_loss | 0.000787 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | -0.0844 | +| time/ | | +| fps | 309 | +| iterations | 7011 | +| time_elapsed | 23189 | +| total_timesteps | 7179264 | +| train/ | | +| approx_kl | 2.1072383 | +| clip_fraction | 0.485 | +| clip_range | 0.2 | +| entropy_loss | -0.362 | +| explained_variance | -1.24 | +| learning_rate | 0.0001 | +| loss | -0.0555 | +| n_updates | 130630 | +| policy_gradient_loss | -0.0645 | +| value_loss | 0.00075 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | -0.0844 | +| time/ | | +| fps | 309 | +| iterations | 7012 | +| time_elapsed | 23192 | +| total_timesteps | 7180288 | +| train/ | | +| approx_kl | 2.0035577 | +| clip_fraction | 0.484 | +| clip_range | 0.2 | +| entropy_loss | -0.463 | +| explained_variance | -2.92 | +| learning_rate | 0.0001 | +| loss | -0.0341 | +| n_updates | 130640 | +| policy_gradient_loss | -0.0649 | +| value_loss | 0.000604 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | -0.0844 | +| time/ | | +| fps | 309 | +| iterations | 7013 | +| time_elapsed | 23195 | +| total_timesteps | 7181312 | +| train/ | | +| approx_kl | 2.1081045 | +| clip_fraction | 0.453 | +| clip_range | 0.2 | +| entropy_loss | -0.356 | +| explained_variance | -2.29 | +| learning_rate | 0.0001 | +| loss | -0.113 | +| n_updates | 130650 | +| policy_gradient_loss | -0.0681 | +| value_loss | 0.000583 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | -0.0883 | +| time/ | | +| fps | 309 | +| iterations | 7014 | +| time_elapsed | 23198 | +| total_timesteps | 7182336 | +| train/ | | +| approx_kl | 1.8877338 | +| clip_fraction | 0.486 | +| clip_range | 0.2 | +| entropy_loss | -0.418 | +| explained_variance | -5.22 | +| learning_rate | 0.0001 | +| loss | -0.0787 | +| n_updates | 130660 | +| policy_gradient_loss | -0.0674 | +| value_loss | 0.000625 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | -0.0899 | +| time/ | | +| fps | 309 | +| iterations | 7015 | +| time_elapsed | 23202 | +| total_timesteps | 7183360 | +| train/ | | +| approx_kl | 1.7419305 | +| clip_fraction | 0.498 | +| clip_range | 0.2 | +| entropy_loss | -0.438 | +| explained_variance | -1.9 | +| learning_rate | 0.0001 | +| loss | -0.0727 | +| n_updates | 130670 | +| policy_gradient_loss | -0.0645 | +| value_loss | 0.000444 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | -0.0928 | +| time/ | | +| fps | 309 | +| iterations | 7016 | +| time_elapsed | 23205 | +| total_timesteps | 7184384 | +| train/ | | +| approx_kl | 1.7329376 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.445 | +| explained_variance | -0.985 | +| learning_rate | 0.0001 | +| loss | -0.0999 | +| n_updates | 130680 | +| policy_gradient_loss | -0.0662 | +| value_loss | 0.000354 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | -0.0928 | +| time/ | | +| fps | 309 | +| iterations | 7017 | +| time_elapsed | 23208 | +| total_timesteps | 7185408 | +| train/ | | +| approx_kl | 1.8950348 | +| clip_fraction | 0.45 | +| clip_range | 0.2 | +| entropy_loss | -0.361 | +| explained_variance | -1.05 | +| learning_rate | 0.0001 | +| loss | -0.076 | +| n_updates | 130690 | +| policy_gradient_loss | -0.0602 | +| value_loss | 0.000668 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | -0.0941 | +| time/ | | +| fps | 309 | +| iterations | 7018 | +| time_elapsed | 23212 | +| total_timesteps | 7186432 | +| train/ | | +| approx_kl | 1.6819575 | +| clip_fraction | 0.518 | +| clip_range | 0.2 | +| entropy_loss | -0.561 | +| explained_variance | -4.44 | +| learning_rate | 0.0001 | +| loss | -0.106 | +| n_updates | 130700 | +| policy_gradient_loss | -0.0733 | +| value_loss | 0.000638 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | -0.0959 | +| time/ | | +| fps | 309 | +| iterations | 7019 | +| time_elapsed | 23215 | +| total_timesteps | 7187456 | +| train/ | | +| approx_kl | 1.4823205 | +| clip_fraction | 0.497 | +| clip_range | 0.2 | +| entropy_loss | -0.479 | +| explained_variance | -1.79 | +| learning_rate | 0.0001 | +| loss | -0.0723 | +| n_updates | 130710 | +| policy_gradient_loss | -0.0668 | +| value_loss | 0.000514 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | -0.0959 | +| time/ | | +| fps | 309 | +| iterations | 7020 | +| time_elapsed | 23219 | +| total_timesteps | 7188480 | +| train/ | | +| approx_kl | 1.4869983 | +| clip_fraction | 0.449 | +| clip_range | 0.2 | +| entropy_loss | -0.393 | +| explained_variance | -1.8 | +| learning_rate | 0.0001 | +| loss | -0.0846 | +| n_updates | 130720 | +| policy_gradient_loss | -0.0578 | +| value_loss | 0.000767 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | -0.0982 | +| time/ | | +| fps | 309 | +| iterations | 7021 | +| time_elapsed | 23222 | +| total_timesteps | 7189504 | +| train/ | | +| approx_kl | 1.7509251 | +| clip_fraction | 0.49 | +| clip_range | 0.2 | +| entropy_loss | -0.402 | +| explained_variance | -3.21 | +| learning_rate | 0.0001 | +| loss | -0.0962 | +| n_updates | 130730 | +| policy_gradient_loss | -0.0576 | +| value_loss | 0.000573 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | -0.0982 | +| time/ | | +| fps | 309 | +| iterations | 7022 | +| time_elapsed | 23225 | +| total_timesteps | 7190528 | +| train/ | | +| approx_kl | 1.6958714 | +| clip_fraction | 0.444 | +| clip_range | 0.2 | +| entropy_loss | -0.385 | +| explained_variance | -3.66 | +| learning_rate | 0.0001 | +| loss | -0.0893 | +| n_updates | 130740 | +| policy_gradient_loss | -0.0658 | +| value_loss | 0.000559 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | -0.0951 | +| time/ | | +| fps | 309 | +| iterations | 7023 | +| time_elapsed | 23229 | +| total_timesteps | 7191552 | +| train/ | | +| approx_kl | 1.6393085 | +| clip_fraction | 0.496 | +| clip_range | 0.2 | +| entropy_loss | -0.459 | +| explained_variance | -1.5 | +| learning_rate | 0.0001 | +| loss | -0.0687 | +| n_updates | 130750 | +| policy_gradient_loss | -0.0625 | +| value_loss | 0.00055 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | -0.0951 | +| time/ | | +| fps | 309 | +| iterations | 7024 | +| time_elapsed | 23232 | +| total_timesteps | 7192576 | +| train/ | | +| approx_kl | 2.0845351 | +| clip_fraction | 0.472 | +| clip_range | 0.2 | +| entropy_loss | -0.408 | +| explained_variance | -1.26 | +| learning_rate | 0.0001 | +| loss | -0.0887 | +| n_updates | 130760 | +| policy_gradient_loss | -0.0611 | +| value_loss | 0.000452 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | -0.0927 | +| time/ | | +| fps | 309 | +| iterations | 7025 | +| time_elapsed | 23235 | +| total_timesteps | 7193600 | +| train/ | | +| approx_kl | 1.9165858 | +| clip_fraction | 0.499 | +| clip_range | 0.2 | +| entropy_loss | -0.453 | +| explained_variance | -3.65 | +| learning_rate | 0.0001 | +| loss | -0.0949 | +| n_updates | 130770 | +| policy_gradient_loss | -0.066 | +| value_loss | 0.000566 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | -0.0927 | +| time/ | | +| fps | 309 | +| iterations | 7026 | +| time_elapsed | 23238 | +| total_timesteps | 7194624 | +| train/ | | +| approx_kl | 1.5103977 | +| clip_fraction | 0.465 | +| clip_range | 0.2 | +| entropy_loss | -0.452 | +| explained_variance | -8.4 | +| learning_rate | 0.0001 | +| loss | -0.095 | +| n_updates | 130780 | +| policy_gradient_loss | -0.0619 | +| value_loss | 0.000597 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | -0.0928 | +| time/ | | +| fps | 309 | +| iterations | 7027 | +| time_elapsed | 23241 | +| total_timesteps | 7195648 | +| train/ | | +| approx_kl | 1.626015 | +| clip_fraction | 0.501 | +| clip_range | 0.2 | +| entropy_loss | -0.471 | +| explained_variance | -6.22 | +| learning_rate | 0.0001 | +| loss | -0.0763 | +| n_updates | 130790 | +| policy_gradient_loss | -0.0633 | +| value_loss | 0.000389 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | -0.0936 | +| time/ | | +| fps | 309 | +| iterations | 7028 | +| time_elapsed | 23245 | +| total_timesteps | 7196672 | +| train/ | | +| approx_kl | 2.111778 | +| clip_fraction | 0.451 | +| clip_range | 0.2 | +| entropy_loss | -0.391 | +| explained_variance | -0.667 | +| learning_rate | 0.0001 | +| loss | -0.0122 | +| n_updates | 130800 | +| policy_gradient_loss | -0.0618 | +| value_loss | 0.000876 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | -0.093 | +| time/ | | +| fps | 309 | +| iterations | 7029 | +| time_elapsed | 23248 | +| total_timesteps | 7197696 | +| train/ | | +| approx_kl | 1.9769961 | +| clip_fraction | 0.476 | +| clip_range | 0.2 | +| entropy_loss | -0.367 | +| explained_variance | -3.57 | +| learning_rate | 0.0001 | +| loss | -0.0641 | +| n_updates | 130810 | +| policy_gradient_loss | -0.0598 | +| value_loss | 0.000548 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | -0.093 | +| time/ | | +| fps | 309 | +| iterations | 7030 | +| time_elapsed | 23251 | +| total_timesteps | 7198720 | +| train/ | | +| approx_kl | 1.5793216 | +| clip_fraction | 0.456 | +| clip_range | 0.2 | +| entropy_loss | -0.39 | +| explained_variance | -2.54 | +| learning_rate | 0.0001 | +| loss | -0.0681 | +| n_updates | 130820 | +| policy_gradient_loss | -0.062 | +| value_loss | 0.000846 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | -0.099 | +| time/ | | +| fps | 309 | +| iterations | 7031 | +| time_elapsed | 23254 | +| total_timesteps | 7199744 | +| train/ | | +| approx_kl | 2.126295 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.443 | +| explained_variance | -11.5 | +| learning_rate | 0.0001 | +| loss | -0.0881 | +| n_updates | 130830 | +| policy_gradient_loss | -0.0657 | +| value_loss | 0.000679 | +-------------------------------------- + +Current state: Champion.Level7.RyuVsEHonda +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | -0.099 | +| time/ | | +| fps | 309 | +| iterations | 7032 | +| time_elapsed | 23257 | +| total_timesteps | 7200768 | +| train/ | | +| approx_kl | 2.0571208 | +| clip_fraction | 0.442 | +| clip_range | 0.2 | +| entropy_loss | -0.407 | +| explained_variance | -1.52 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 130840 | +| policy_gradient_loss | -0.0563 | +| value_loss | 0.000657 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | -0.1 | +| time/ | | +| fps | 309 | +| iterations | 7033 | +| time_elapsed | 23261 | +| total_timesteps | 7201792 | +| train/ | | +| approx_kl | 1.9664347 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.413 | +| explained_variance | -5.76 | +| learning_rate | 0.0001 | +| loss | -0.0729 | +| n_updates | 130850 | +| policy_gradient_loss | -0.063 | +| value_loss | 0.000601 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | -0.0976 | +| time/ | | +| fps | 309 | +| iterations | 7034 | +| time_elapsed | 23264 | +| total_timesteps | 7202816 | +| train/ | | +| approx_kl | 2.155445 | +| clip_fraction | 0.519 | +| clip_range | 0.2 | +| entropy_loss | -0.436 | +| explained_variance | -1.19 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 130860 | +| policy_gradient_loss | -0.0695 | +| value_loss | 0.0004 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | -0.0957 | +| time/ | | +| fps | 309 | +| iterations | 7035 | +| time_elapsed | 23267 | +| total_timesteps | 7203840 | +| train/ | | +| approx_kl | 2.0769203 | +| clip_fraction | 0.526 | +| clip_range | 0.2 | +| entropy_loss | -0.457 | +| explained_variance | -1.93 | +| learning_rate | 0.0001 | +| loss | -0.11 | +| n_updates | 130870 | +| policy_gradient_loss | -0.0646 | +| value_loss | 0.000429 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | -0.0957 | +| time/ | | +| fps | 309 | +| iterations | 7036 | +| time_elapsed | 23271 | +| total_timesteps | 7204864 | +| train/ | | +| approx_kl | 1.7894236 | +| clip_fraction | 0.495 | +| clip_range | 0.2 | +| entropy_loss | -0.413 | +| explained_variance | -1.47 | +| learning_rate | 0.0001 | +| loss | -0.0846 | +| n_updates | 130880 | +| policy_gradient_loss | -0.0697 | +| value_loss | 0.000511 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.65e+03 | +| ep_rew_mean | -0.098 | +| time/ | | +| fps | 309 | +| iterations | 7037 | +| time_elapsed | 23274 | +| total_timesteps | 7205888 | +| train/ | | +| approx_kl | 12.062022 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.436 | +| explained_variance | -4.23 | +| learning_rate | 0.0001 | +| loss | -0.0848 | +| n_updates | 130890 | +| policy_gradient_loss | -0.069 | +| value_loss | 0.000286 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.65e+03 | +| ep_rew_mean | -0.098 | +| time/ | | +| fps | 309 | +| iterations | 7038 | +| time_elapsed | 23278 | +| total_timesteps | 7206912 | +| train/ | | +| approx_kl | 1.8474249 | +| clip_fraction | 0.507 | +| clip_range | 0.2 | +| entropy_loss | -0.463 | +| explained_variance | -4.65 | +| learning_rate | 0.0001 | +| loss | -0.105 | +| n_updates | 130900 | +| policy_gradient_loss | -0.079 | +| value_loss | 0.000329 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | -0.0947 | +| time/ | | +| fps | 309 | +| iterations | 7039 | +| time_elapsed | 23281 | +| total_timesteps | 7207936 | +| train/ | | +| approx_kl | 1.8056175 | +| clip_fraction | 0.494 | +| clip_range | 0.2 | +| entropy_loss | -0.428 | +| explained_variance | -1.4 | +| learning_rate | 0.0001 | +| loss | -0.0778 | +| n_updates | 130910 | +| policy_gradient_loss | -0.0678 | +| value_loss | 0.000651 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | -0.0947 | +| time/ | | +| fps | 309 | +| iterations | 7040 | +| time_elapsed | 23285 | +| total_timesteps | 7208960 | +| train/ | | +| approx_kl | 2.0887184 | +| clip_fraction | 0.479 | +| clip_range | 0.2 | +| entropy_loss | -0.4 | +| explained_variance | -2.42 | +| learning_rate | 0.0001 | +| loss | -0.0663 | +| n_updates | 130920 | +| policy_gradient_loss | -0.0647 | +| value_loss | 0.000551 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.65e+03 | +| ep_rew_mean | -0.0988 | +| time/ | | +| fps | 309 | +| iterations | 7041 | +| time_elapsed | 23288 | +| total_timesteps | 7209984 | +| train/ | | +| approx_kl | 1.6763841 | +| clip_fraction | 0.501 | +| clip_range | 0.2 | +| entropy_loss | -0.481 | +| explained_variance | -5.81 | +| learning_rate | 0.0001 | +| loss | -0.0795 | +| n_updates | 130930 | +| policy_gradient_loss | -0.0613 | +| value_loss | 0.000355 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.65e+03 | +| ep_rew_mean | -0.0988 | +| time/ | | +| fps | 309 | +| iterations | 7042 | +| time_elapsed | 23292 | +| total_timesteps | 7211008 | +| train/ | | +| approx_kl | 4.8435807 | +| clip_fraction | 0.438 | +| clip_range | 0.2 | +| entropy_loss | -0.394 | +| explained_variance | -0.339 | +| learning_rate | 0.0001 | +| loss | -0.0809 | +| n_updates | 130940 | +| policy_gradient_loss | -0.0523 | +| value_loss | 0.000473 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.64e+03 | +| ep_rew_mean | -0.102 | +| time/ | | +| fps | 309 | +| iterations | 7043 | +| time_elapsed | 23295 | +| total_timesteps | 7212032 | +| train/ | | +| approx_kl | 1.6458323 | +| clip_fraction | 0.469 | +| clip_range | 0.2 | +| entropy_loss | -0.423 | +| explained_variance | -3.11 | +| learning_rate | 0.0001 | +| loss | -0.0806 | +| n_updates | 130950 | +| policy_gradient_loss | -0.0595 | +| value_loss | 0.000354 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.64e+03 | +| ep_rew_mean | -0.102 | +| time/ | | +| fps | 309 | +| iterations | 7044 | +| time_elapsed | 23298 | +| total_timesteps | 7213056 | +| train/ | | +| approx_kl | 1.7787932 | +| clip_fraction | 0.488 | +| clip_range | 0.2 | +| entropy_loss | -0.4 | +| explained_variance | -1.14 | +| learning_rate | 0.0001 | +| loss | -0.0508 | +| n_updates | 130960 | +| policy_gradient_loss | -0.0534 | +| value_loss | 0.000291 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.64e+03 | +| ep_rew_mean | -0.0986 | +| time/ | | +| fps | 309 | +| iterations | 7045 | +| time_elapsed | 23301 | +| total_timesteps | 7214080 | +| train/ | | +| approx_kl | 3.5381913 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.377 | +| explained_variance | -1.41 | +| learning_rate | 0.0001 | +| loss | -0.074 | +| n_updates | 130970 | +| policy_gradient_loss | -0.0625 | +| value_loss | 0.000492 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.64e+03 | +| ep_rew_mean | -0.0986 | +| time/ | | +| fps | 309 | +| iterations | 7046 | +| time_elapsed | 23304 | +| total_timesteps | 7215104 | +| train/ | | +| approx_kl | 1.6854497 | +| clip_fraction | 0.457 | +| clip_range | 0.2 | +| entropy_loss | -0.407 | +| explained_variance | -3.23 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 130980 | +| policy_gradient_loss | -0.0641 | +| value_loss | 0.000444 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.65e+03 | +| ep_rew_mean | -0.101 | +| time/ | | +| fps | 309 | +| iterations | 7047 | +| time_elapsed | 23308 | +| total_timesteps | 7216128 | +| train/ | | +| approx_kl | 1.6092408 | +| clip_fraction | 0.474 | +| clip_range | 0.2 | +| entropy_loss | -0.423 | +| explained_variance | -4.91 | +| learning_rate | 0.0001 | +| loss | -0.0859 | +| n_updates | 130990 | +| policy_gradient_loss | -0.0671 | +| value_loss | 0.000294 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.64e+03 | +| ep_rew_mean | -0.102 | +| time/ | | +| fps | 309 | +| iterations | 7048 | +| time_elapsed | 23311 | +| total_timesteps | 7217152 | +| train/ | | +| approx_kl | 3.8754847 | +| clip_fraction | 0.449 | +| clip_range | 0.2 | +| entropy_loss | -0.428 | +| explained_variance | -0.727 | +| learning_rate | 0.0001 | +| loss | 0.128 | +| n_updates | 131000 | +| policy_gradient_loss | -0.0557 | +| value_loss | 0.000154 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.63e+03 | +| ep_rew_mean | -0.105 | +| time/ | | +| fps | 309 | +| iterations | 7049 | +| time_elapsed | 23314 | +| total_timesteps | 7218176 | +| train/ | | +| approx_kl | 1.5657659 | +| clip_fraction | 0.453 | +| clip_range | 0.2 | +| entropy_loss | -0.401 | +| explained_variance | -1.48 | +| learning_rate | 0.0001 | +| loss | -0.1 | +| n_updates | 131010 | +| policy_gradient_loss | -0.0637 | +| value_loss | 0.000425 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.63e+03 | +| ep_rew_mean | -0.104 | +| time/ | | +| fps | 309 | +| iterations | 7050 | +| time_elapsed | 23317 | +| total_timesteps | 7219200 | +| train/ | | +| approx_kl | 2.2688866 | +| clip_fraction | 0.442 | +| clip_range | 0.2 | +| entropy_loss | -0.411 | +| explained_variance | -2.17 | +| learning_rate | 0.0001 | +| loss | -0.0736 | +| n_updates | 131020 | +| policy_gradient_loss | -0.0564 | +| value_loss | 0.000419 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.63e+03 | +| ep_rew_mean | -0.104 | +| time/ | | +| fps | 309 | +| iterations | 7051 | +| time_elapsed | 23321 | +| total_timesteps | 7220224 | +| train/ | | +| approx_kl | 1.9765054 | +| clip_fraction | 0.461 | +| clip_range | 0.2 | +| entropy_loss | -0.366 | +| explained_variance | -1.59 | +| learning_rate | 0.0001 | +| loss | -0.0834 | +| n_updates | 131030 | +| policy_gradient_loss | -0.0637 | +| value_loss | 0.00054 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.63e+03 | +| ep_rew_mean | -0.104 | +| time/ | | +| fps | 309 | +| iterations | 7052 | +| time_elapsed | 23325 | +| total_timesteps | 7221248 | +| train/ | | +| approx_kl | 1.8505127 | +| clip_fraction | 0.452 | +| clip_range | 0.2 | +| entropy_loss | -0.416 | +| explained_variance | -5.32 | +| learning_rate | 0.0001 | +| loss | -0.099 | +| n_updates | 131040 | +| policy_gradient_loss | -0.0552 | +| value_loss | 0.000302 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.62e+03 | +| ep_rew_mean | -0.107 | +| time/ | | +| fps | 309 | +| iterations | 7053 | +| time_elapsed | 23328 | +| total_timesteps | 7222272 | +| train/ | | +| approx_kl | 1.4705641 | +| clip_fraction | 0.445 | +| clip_range | 0.2 | +| entropy_loss | -0.382 | +| explained_variance | -4.22 | +| learning_rate | 0.0001 | +| loss | -0.0979 | +| n_updates | 131050 | +| policy_gradient_loss | -0.0697 | +| value_loss | 0.000538 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.61e+03 | +| ep_rew_mean | -0.106 | +| time/ | | +| fps | 309 | +| iterations | 7054 | +| time_elapsed | 23332 | +| total_timesteps | 7223296 | +| train/ | | +| approx_kl | 1.8946673 | +| clip_fraction | 0.454 | +| clip_range | 0.2 | +| entropy_loss | -0.395 | +| explained_variance | -2.3 | +| learning_rate | 0.0001 | +| loss | -0.0997 | +| n_updates | 131060 | +| policy_gradient_loss | -0.0599 | +| value_loss | 0.00104 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.61e+03 | +| ep_rew_mean | -0.105 | +| time/ | | +| fps | 309 | +| iterations | 7055 | +| time_elapsed | 23335 | +| total_timesteps | 7224320 | +| train/ | | +| approx_kl | 3.8385942 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.386 | +| explained_variance | -3.09 | +| learning_rate | 0.0001 | +| loss | -0.0912 | +| n_updates | 131070 | +| policy_gradient_loss | -0.0715 | +| value_loss | 0.000543 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.61e+03 | +| ep_rew_mean | -0.105 | +| time/ | | +| fps | 309 | +| iterations | 7056 | +| time_elapsed | 23339 | +| total_timesteps | 7225344 | +| train/ | | +| approx_kl | 1.8850529 | +| clip_fraction | 0.51 | +| clip_range | 0.2 | +| entropy_loss | -0.445 | +| explained_variance | -2.53 | +| learning_rate | 0.0001 | +| loss | -0.0791 | +| n_updates | 131080 | +| policy_gradient_loss | -0.073 | +| value_loss | 0.000433 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.61e+03 | +| ep_rew_mean | -0.0987 | +| time/ | | +| fps | 309 | +| iterations | 7057 | +| time_elapsed | 23342 | +| total_timesteps | 7226368 | +| train/ | | +| approx_kl | 2.4748893 | +| clip_fraction | 0.516 | +| clip_range | 0.2 | +| entropy_loss | -0.429 | +| explained_variance | -1.28 | +| learning_rate | 0.0001 | +| loss | -0.0739 | +| n_updates | 131090 | +| policy_gradient_loss | -0.0744 | +| value_loss | 0.000834 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.62e+03 | +| ep_rew_mean | -0.0932 | +| time/ | | +| fps | 309 | +| iterations | 7058 | +| time_elapsed | 23346 | +| total_timesteps | 7227392 | +| train/ | | +| approx_kl | 1.9807312 | +| clip_fraction | 0.515 | +| clip_range | 0.2 | +| entropy_loss | -0.482 | +| explained_variance | -2.28 | +| learning_rate | 0.0001 | +| loss | -0.115 | +| n_updates | 131100 | +| policy_gradient_loss | -0.0725 | +| value_loss | 0.000483 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.62e+03 | +| ep_rew_mean | -0.0932 | +| time/ | | +| fps | 309 | +| iterations | 7059 | +| time_elapsed | 23350 | +| total_timesteps | 7228416 | +| train/ | | +| approx_kl | 1.8028643 | +| clip_fraction | 0.484 | +| clip_range | 0.2 | +| entropy_loss | -0.413 | +| explained_variance | -2 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 131110 | +| policy_gradient_loss | -0.0711 | +| value_loss | 0.000389 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.62e+03 | +| ep_rew_mean | -0.0919 | +| time/ | | +| fps | 309 | +| iterations | 7060 | +| time_elapsed | 23353 | +| total_timesteps | 7229440 | +| train/ | | +| approx_kl | 1.9708751 | +| clip_fraction | 0.478 | +| clip_range | 0.2 | +| entropy_loss | -0.42 | +| explained_variance | -2.64 | +| learning_rate | 0.0001 | +| loss | -0.089 | +| n_updates | 131120 | +| policy_gradient_loss | -0.0692 | +| value_loss | 0.000305 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.62e+03 | +| ep_rew_mean | -0.0908 | +| time/ | | +| fps | 309 | +| iterations | 7061 | +| time_elapsed | 23356 | +| total_timesteps | 7230464 | +| train/ | | +| approx_kl | 1.8989096 | +| clip_fraction | 0.491 | +| clip_range | 0.2 | +| entropy_loss | -0.443 | +| explained_variance | -1.52 | +| learning_rate | 0.0001 | +| loss | -0.0566 | +| n_updates | 131130 | +| policy_gradient_loss | -0.0679 | +| value_loss | 0.000569 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.61e+03 | +| ep_rew_mean | -0.0908 | +| time/ | | +| fps | 309 | +| iterations | 7062 | +| time_elapsed | 23359 | +| total_timesteps | 7231488 | +| train/ | | +| approx_kl | 1.986382 | +| clip_fraction | 0.501 | +| clip_range | 0.2 | +| entropy_loss | -0.421 | +| explained_variance | -3.21 | +| learning_rate | 0.0001 | +| loss | -0.12 | +| n_updates | 131140 | +| policy_gradient_loss | -0.0722 | +| value_loss | 0.000398 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.61e+03 | +| ep_rew_mean | -0.0908 | +| time/ | | +| fps | 309 | +| iterations | 7063 | +| time_elapsed | 23362 | +| total_timesteps | 7232512 | +| train/ | | +| approx_kl | 2.6211472 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.364 | +| explained_variance | -1.05 | +| learning_rate | 0.0001 | +| loss | -0.065 | +| n_updates | 131150 | +| policy_gradient_loss | -0.0684 | +| value_loss | 0.000627 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.62e+03 | +| ep_rew_mean | -0.0862 | +| time/ | | +| fps | 309 | +| iterations | 7064 | +| time_elapsed | 23366 | +| total_timesteps | 7233536 | +| train/ | | +| approx_kl | 2.0171072 | +| clip_fraction | 0.476 | +| clip_range | 0.2 | +| entropy_loss | -0.393 | +| explained_variance | -1.12 | +| learning_rate | 0.0001 | +| loss | -0.0772 | +| n_updates | 131160 | +| policy_gradient_loss | -0.0691 | +| value_loss | 0.00058 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | -0.0912 | +| time/ | | +| fps | 309 | +| iterations | 7065 | +| time_elapsed | 23369 | +| total_timesteps | 7234560 | +| train/ | | +| approx_kl | 1.7736071 | +| clip_fraction | 0.442 | +| clip_range | 0.2 | +| entropy_loss | -0.411 | +| explained_variance | -3.02 | +| learning_rate | 0.0001 | +| loss | -0.0999 | +| n_updates | 131170 | +| policy_gradient_loss | -0.0614 | +| value_loss | 0.000611 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | -0.0912 | +| time/ | | +| fps | 309 | +| iterations | 7066 | +| time_elapsed | 23372 | +| total_timesteps | 7235584 | +| train/ | | +| approx_kl | 1.6064748 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.428 | +| explained_variance | -1.27 | +| learning_rate | 0.0001 | +| loss | -0.0866 | +| n_updates | 131180 | +| policy_gradient_loss | -0.0632 | +| value_loss | 0.000557 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.61e+03 | +| ep_rew_mean | -0.089 | +| time/ | | +| fps | 309 | +| iterations | 7067 | +| time_elapsed | 23375 | +| total_timesteps | 7236608 | +| train/ | | +| approx_kl | 1.8177948 | +| clip_fraction | 0.458 | +| clip_range | 0.2 | +| entropy_loss | -0.411 | +| explained_variance | -2.78 | +| learning_rate | 0.0001 | +| loss | -0.0987 | +| n_updates | 131190 | +| policy_gradient_loss | -0.0679 | +| value_loss | 0.000798 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.61e+03 | +| ep_rew_mean | -0.0884 | +| time/ | | +| fps | 309 | +| iterations | 7068 | +| time_elapsed | 23378 | +| total_timesteps | 7237632 | +| train/ | | +| approx_kl | 3.1445673 | +| clip_fraction | 0.49 | +| clip_range | 0.2 | +| entropy_loss | -0.508 | +| explained_variance | -3.82 | +| learning_rate | 0.0001 | +| loss | -0.0855 | +| n_updates | 131200 | +| policy_gradient_loss | -0.0694 | +| value_loss | 0.000457 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.61e+03 | +| ep_rew_mean | -0.0884 | +| time/ | | +| fps | 309 | +| iterations | 7069 | +| time_elapsed | 23382 | +| total_timesteps | 7238656 | +| train/ | | +| approx_kl | 2.3996115 | +| clip_fraction | 0.482 | +| clip_range | 0.2 | +| entropy_loss | -0.463 | +| explained_variance | -0.937 | +| learning_rate | 0.0001 | +| loss | -0.113 | +| n_updates | 131210 | +| policy_gradient_loss | -0.0643 | +| value_loss | 0.00055 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.61e+03 | +| ep_rew_mean | -0.0856 | +| time/ | | +| fps | 309 | +| iterations | 7070 | +| time_elapsed | 23385 | +| total_timesteps | 7239680 | +| train/ | | +| approx_kl | 1.9512112 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.403 | +| explained_variance | -4.52 | +| learning_rate | 0.0001 | +| loss | -0.0847 | +| n_updates | 131220 | +| policy_gradient_loss | -0.0723 | +| value_loss | 0.000764 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | -0.0857 | +| time/ | | +| fps | 309 | +| iterations | 7071 | +| time_elapsed | 23389 | +| total_timesteps | 7240704 | +| train/ | | +| approx_kl | 1.4441609 | +| clip_fraction | 0.464 | +| clip_range | 0.2 | +| entropy_loss | -0.368 | +| explained_variance | -3.05 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 131230 | +| policy_gradient_loss | -0.072 | +| value_loss | 0.000585 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | -0.0857 | +| time/ | | +| fps | 309 | +| iterations | 7072 | +| time_elapsed | 23392 | +| total_timesteps | 7241728 | +| train/ | | +| approx_kl | 1.3332797 | +| clip_fraction | 0.438 | +| clip_range | 0.2 | +| entropy_loss | -0.424 | +| explained_variance | -1.88 | +| learning_rate | 0.0001 | +| loss | -0.0821 | +| n_updates | 131240 | +| policy_gradient_loss | -0.0675 | +| value_loss | 0.000442 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.61e+03 | +| ep_rew_mean | -0.0841 | +| time/ | | +| fps | 309 | +| iterations | 7073 | +| time_elapsed | 23396 | +| total_timesteps | 7242752 | +| train/ | | +| approx_kl | 1.378493 | +| clip_fraction | 0.466 | +| clip_range | 0.2 | +| entropy_loss | -0.431 | +| explained_variance | -2.97 | +| learning_rate | 0.0001 | +| loss | -0.109 | +| n_updates | 131250 | +| policy_gradient_loss | -0.0681 | +| value_loss | 0.000259 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | -0.0808 | +| time/ | | +| fps | 309 | +| iterations | 7074 | +| time_elapsed | 23399 | +| total_timesteps | 7243776 | +| train/ | | +| approx_kl | 1.6628475 | +| clip_fraction | 0.437 | +| clip_range | 0.2 | +| entropy_loss | -0.351 | +| explained_variance | -2.79 | +| learning_rate | 0.0001 | +| loss | -0.0985 | +| n_updates | 131260 | +| policy_gradient_loss | -0.0667 | +| value_loss | 0.00047 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | -0.0808 | +| time/ | | +| fps | 309 | +| iterations | 7075 | +| time_elapsed | 23403 | +| total_timesteps | 7244800 | +| train/ | | +| approx_kl | 2.420157 | +| clip_fraction | 0.456 | +| clip_range | 0.2 | +| entropy_loss | -0.332 | +| explained_variance | -1.56 | +| learning_rate | 0.0001 | +| loss | -0.0784 | +| n_updates | 131270 | +| policy_gradient_loss | -0.0591 | +| value_loss | 0.00105 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | -0.0811 | +| time/ | | +| fps | 309 | +| iterations | 7076 | +| time_elapsed | 23406 | +| total_timesteps | 7245824 | +| train/ | | +| approx_kl | 1.6690121 | +| clip_fraction | 0.439 | +| clip_range | 0.2 | +| entropy_loss | -0.371 | +| explained_variance | -3.51 | +| learning_rate | 0.0001 | +| loss | -0.0822 | +| n_updates | 131280 | +| policy_gradient_loss | -0.0666 | +| value_loss | 0.000564 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | -0.0798 | +| time/ | | +| fps | 309 | +| iterations | 7077 | +| time_elapsed | 23410 | +| total_timesteps | 7246848 | +| train/ | | +| approx_kl | 2.0267906 | +| clip_fraction | 0.452 | +| clip_range | 0.2 | +| entropy_loss | -0.357 | +| explained_variance | -1.89 | +| learning_rate | 0.0001 | +| loss | -0.0831 | +| n_updates | 131290 | +| policy_gradient_loss | -0.0584 | +| value_loss | 0.00106 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | -0.0798 | +| time/ | | +| fps | 309 | +| iterations | 7078 | +| time_elapsed | 23413 | +| total_timesteps | 7247872 | +| train/ | | +| approx_kl | 1.9758232 | +| clip_fraction | 0.43 | +| clip_range | 0.2 | +| entropy_loss | -0.354 | +| explained_variance | -3.45 | +| learning_rate | 0.0001 | +| loss | -0.0889 | +| n_updates | 131300 | +| policy_gradient_loss | -0.0598 | +| value_loss | 0.000622 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | -0.0762 | +| time/ | | +| fps | 309 | +| iterations | 7079 | +| time_elapsed | 23416 | +| total_timesteps | 7248896 | +| train/ | | +| approx_kl | 1.4085226 | +| clip_fraction | 0.466 | +| clip_range | 0.2 | +| entropy_loss | -0.432 | +| explained_variance | -2.18 | +| learning_rate | 0.0001 | +| loss | -0.114 | +| n_updates | 131310 | +| policy_gradient_loss | -0.0614 | +| value_loss | 0.000376 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | -0.0725 | +| time/ | | +| fps | 309 | +| iterations | 7080 | +| time_elapsed | 23419 | +| total_timesteps | 7249920 | +| train/ | | +| approx_kl | 1.5903506 | +| clip_fraction | 0.393 | +| clip_range | 0.2 | +| entropy_loss | -0.323 | +| explained_variance | -2.05 | +| learning_rate | 0.0001 | +| loss | -0.0844 | +| n_updates | 131320 | +| policy_gradient_loss | -0.056 | +| value_loss | 0.000647 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | -0.0725 | +| time/ | | +| fps | 309 | +| iterations | 7081 | +| time_elapsed | 23423 | +| total_timesteps | 7250944 | +| train/ | | +| approx_kl | 1.9887741 | +| clip_fraction | 0.466 | +| clip_range | 0.2 | +| entropy_loss | -0.366 | +| explained_variance | -2.57 | +| learning_rate | 0.0001 | +| loss | -0.0767 | +| n_updates | 131330 | +| policy_gradient_loss | -0.067 | +| value_loss | 0.000568 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | -0.0668 | +| time/ | | +| fps | 309 | +| iterations | 7082 | +| time_elapsed | 23426 | +| total_timesteps | 7251968 | +| train/ | | +| approx_kl | 2.3143373 | +| clip_fraction | 0.488 | +| clip_range | 0.2 | +| entropy_loss | -0.411 | +| explained_variance | -1.48 | +| learning_rate | 0.0001 | +| loss | -0.0862 | +| n_updates | 131340 | +| policy_gradient_loss | -0.0643 | +| value_loss | 0.000654 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | -0.0668 | +| time/ | | +| fps | 309 | +| iterations | 7083 | +| time_elapsed | 23429 | +| total_timesteps | 7252992 | +| train/ | | +| approx_kl | 1.982547 | +| clip_fraction | 0.459 | +| clip_range | 0.2 | +| entropy_loss | -0.392 | +| explained_variance | -1.35 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 131350 | +| policy_gradient_loss | -0.066 | +| value_loss | 0.000734 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.58e+03 | +| ep_rew_mean | -0.0627 | +| time/ | | +| fps | 309 | +| iterations | 7084 | +| time_elapsed | 23432 | +| total_timesteps | 7254016 | +| train/ | | +| approx_kl | 2.2153778 | +| clip_fraction | 0.479 | +| clip_range | 0.2 | +| entropy_loss | -0.393 | +| explained_variance | -1.53 | +| learning_rate | 0.0001 | +| loss | -0.0748 | +| n_updates | 131360 | +| policy_gradient_loss | -0.0674 | +| value_loss | 0.000625 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.58e+03 | +| ep_rew_mean | -0.0627 | +| time/ | | +| fps | 309 | +| iterations | 7085 | +| time_elapsed | 23435 | +| total_timesteps | 7255040 | +| train/ | | +| approx_kl | 2.9075453 | +| clip_fraction | 0.416 | +| clip_range | 0.2 | +| entropy_loss | -0.349 | +| explained_variance | -2.39 | +| learning_rate | 0.0001 | +| loss | -0.0553 | +| n_updates | 131370 | +| policy_gradient_loss | -0.0574 | +| value_loss | 0.000932 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | -0.0599 | +| time/ | | +| fps | 309 | +| iterations | 7086 | +| time_elapsed | 23439 | +| total_timesteps | 7256064 | +| train/ | | +| approx_kl | 1.9549177 | +| clip_fraction | 0.462 | +| clip_range | 0.2 | +| entropy_loss | -0.432 | +| explained_variance | -4.77 | +| learning_rate | 0.0001 | +| loss | -0.0964 | +| n_updates | 131380 | +| policy_gradient_loss | -0.0649 | +| value_loss | 0.000303 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | -0.0599 | +| time/ | | +| fps | 309 | +| iterations | 7087 | +| time_elapsed | 23442 | +| total_timesteps | 7257088 | +| train/ | | +| approx_kl | 1.5900751 | +| clip_fraction | 0.431 | +| clip_range | 0.2 | +| entropy_loss | -0.375 | +| explained_variance | -3.35 | +| learning_rate | 0.0001 | +| loss | -0.0453 | +| n_updates | 131390 | +| policy_gradient_loss | -0.0552 | +| value_loss | 0.000379 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | -0.0599 | +| time/ | | +| fps | 309 | +| iterations | 7088 | +| time_elapsed | 23445 | +| total_timesteps | 7258112 | +| train/ | | +| approx_kl | 1.3508055 | +| clip_fraction | 0.482 | +| clip_range | 0.2 | +| entropy_loss | -0.527 | +| explained_variance | -4.94 | +| learning_rate | 0.0001 | +| loss | -0.0927 | +| n_updates | 131400 | +| policy_gradient_loss | -0.068 | +| value_loss | 0.000125 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | -0.0601 | +| time/ | | +| fps | 309 | +| iterations | 7089 | +| time_elapsed | 23449 | +| total_timesteps | 7259136 | +| train/ | | +| approx_kl | 1.8861479 | +| clip_fraction | 0.477 | +| clip_range | 0.2 | +| entropy_loss | -0.425 | +| explained_variance | -0.778 | +| learning_rate | 0.0001 | +| loss | -0.0896 | +| n_updates | 131410 | +| policy_gradient_loss | -0.0588 | +| value_loss | 0.000315 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | -0.0567 | +| time/ | | +| fps | 309 | +| iterations | 7090 | +| time_elapsed | 23452 | +| total_timesteps | 7260160 | +| train/ | | +| approx_kl | 2.3381302 | +| clip_fraction | 0.5 | +| clip_range | 0.2 | +| entropy_loss | -0.413 | +| explained_variance | -1.3 | +| learning_rate | 0.0001 | +| loss | -0.0926 | +| n_updates | 131420 | +| policy_gradient_loss | -0.0699 | +| value_loss | 0.000411 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | -0.0567 | +| time/ | | +| fps | 309 | +| iterations | 7091 | +| time_elapsed | 23456 | +| total_timesteps | 7261184 | +| train/ | | +| approx_kl | 1.5459696 | +| clip_fraction | 0.468 | +| clip_range | 0.2 | +| entropy_loss | -0.395 | +| explained_variance | -1.64 | +| learning_rate | 0.0001 | +| loss | -0.078 | +| n_updates | 131430 | +| policy_gradient_loss | -0.0669 | +| value_loss | 0.000806 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.58e+03 | +| ep_rew_mean | -0.0519 | +| time/ | | +| fps | 309 | +| iterations | 7092 | +| time_elapsed | 23459 | +| total_timesteps | 7262208 | +| train/ | | +| approx_kl | 2.096796 | +| clip_fraction | 0.438 | +| clip_range | 0.2 | +| entropy_loss | -0.317 | +| explained_variance | -2.99 | +| learning_rate | 0.0001 | +| loss | -0.0784 | +| n_updates | 131440 | +| policy_gradient_loss | -0.0677 | +| value_loss | 0.000778 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.58e+03 | +| ep_rew_mean | -0.0519 | +| time/ | | +| fps | 309 | +| iterations | 7093 | +| time_elapsed | 23462 | +| total_timesteps | 7263232 | +| train/ | | +| approx_kl | 2.172164 | +| clip_fraction | 0.496 | +| clip_range | 0.2 | +| entropy_loss | -0.449 | +| explained_variance | -5.6 | +| learning_rate | 0.0001 | +| loss | -0.0838 | +| n_updates | 131450 | +| policy_gradient_loss | -0.0671 | +| value_loss | 0.000772 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.58e+03 | +| ep_rew_mean | -0.0524 | +| time/ | | +| fps | 309 | +| iterations | 7094 | +| time_elapsed | 23466 | +| total_timesteps | 7264256 | +| train/ | | +| approx_kl | 2.3881655 | +| clip_fraction | 0.498 | +| clip_range | 0.2 | +| entropy_loss | -0.427 | +| explained_variance | -2.49 | +| learning_rate | 0.0001 | +| loss | -0.0894 | +| n_updates | 131460 | +| policy_gradient_loss | -0.0632 | +| value_loss | 0.000529 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.58e+03 | +| ep_rew_mean | -0.0524 | +| time/ | | +| fps | 309 | +| iterations | 7095 | +| time_elapsed | 23469 | +| total_timesteps | 7265280 | +| train/ | | +| approx_kl | 25.323904 | +| clip_fraction | 0.455 | +| clip_range | 0.2 | +| entropy_loss | -0.382 | +| explained_variance | -2.22 | +| learning_rate | 0.0001 | +| loss | -0.0837 | +| n_updates | 131470 | +| policy_gradient_loss | -0.07 | +| value_loss | 0.000459 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.58e+03 | +| ep_rew_mean | -0.0465 | +| time/ | | +| fps | 309 | +| iterations | 7096 | +| time_elapsed | 23472 | +| total_timesteps | 7266304 | +| train/ | | +| approx_kl | 2.0520616 | +| clip_fraction | 0.47 | +| clip_range | 0.2 | +| entropy_loss | -0.376 | +| explained_variance | -0.916 | +| learning_rate | 0.0001 | +| loss | -0.0713 | +| n_updates | 131480 | +| policy_gradient_loss | -0.0673 | +| value_loss | 0.000775 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.58e+03 | +| ep_rew_mean | -0.0464 | +| time/ | | +| fps | 309 | +| iterations | 7097 | +| time_elapsed | 23476 | +| total_timesteps | 7267328 | +| train/ | | +| approx_kl | 1.9337842 | +| clip_fraction | 0.474 | +| clip_range | 0.2 | +| entropy_loss | -0.397 | +| explained_variance | -2.93 | +| learning_rate | 0.0001 | +| loss | -0.078 | +| n_updates | 131490 | +| policy_gradient_loss | -0.0675 | +| value_loss | 0.000744 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.57e+03 | +| ep_rew_mean | -0.0484 | +| time/ | | +| fps | 309 | +| iterations | 7098 | +| time_elapsed | 23479 | +| total_timesteps | 7268352 | +| train/ | | +| approx_kl | 2.7602253 | +| clip_fraction | 0.459 | +| clip_range | 0.2 | +| entropy_loss | -0.359 | +| explained_variance | -3 | +| learning_rate | 0.0001 | +| loss | -0.083 | +| n_updates | 131500 | +| policy_gradient_loss | -0.0734 | +| value_loss | 0.000445 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.57e+03 | +| ep_rew_mean | -0.0483 | +| time/ | | +| fps | 309 | +| iterations | 7099 | +| time_elapsed | 23482 | +| total_timesteps | 7269376 | +| train/ | | +| approx_kl | 1.7232597 | +| clip_fraction | 0.416 | +| clip_range | 0.2 | +| entropy_loss | -0.337 | +| explained_variance | -0.988 | +| learning_rate | 0.0001 | +| loss | -0.068 | +| n_updates | 131510 | +| policy_gradient_loss | -0.0607 | +| value_loss | 0.000569 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.57e+03 | +| ep_rew_mean | -0.0483 | +| time/ | | +| fps | 309 | +| iterations | 7100 | +| time_elapsed | 23485 | +| total_timesteps | 7270400 | +| train/ | | +| approx_kl | 6.9689255 | +| clip_fraction | 0.421 | +| clip_range | 0.2 | +| entropy_loss | -0.359 | +| explained_variance | -1.35 | +| learning_rate | 0.0001 | +| loss | -0.0614 | +| n_updates | 131520 | +| policy_gradient_loss | -0.062 | +| value_loss | 0.000496 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.57e+03 | +| ep_rew_mean | -0.0489 | +| time/ | | +| fps | 309 | +| iterations | 7101 | +| time_elapsed | 23488 | +| total_timesteps | 7271424 | +| train/ | | +| approx_kl | 1.763264 | +| clip_fraction | 0.484 | +| clip_range | 0.2 | +| entropy_loss | -0.417 | +| explained_variance | -0.983 | +| learning_rate | 0.0001 | +| loss | -0.0909 | +| n_updates | 131530 | +| policy_gradient_loss | -0.0702 | +| value_loss | 0.000525 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.57e+03 | +| ep_rew_mean | -0.0494 | +| time/ | | +| fps | 309 | +| iterations | 7102 | +| time_elapsed | 23492 | +| total_timesteps | 7272448 | +| train/ | | +| approx_kl | 1.9376104 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.391 | +| explained_variance | -3.78 | +| learning_rate | 0.0001 | +| loss | -0.0993 | +| n_updates | 131540 | +| policy_gradient_loss | -0.0629 | +| value_loss | 0.000449 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.56e+03 | +| ep_rew_mean | -0.0485 | +| time/ | | +| fps | 309 | +| iterations | 7103 | +| time_elapsed | 23495 | +| total_timesteps | 7273472 | +| train/ | | +| approx_kl | 1.6780571 | +| clip_fraction | 0.417 | +| clip_range | 0.2 | +| entropy_loss | -0.334 | +| explained_variance | -1.19 | +| learning_rate | 0.0001 | +| loss | -0.0728 | +| n_updates | 131550 | +| policy_gradient_loss | -0.0615 | +| value_loss | 0.000736 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.55e+03 | +| ep_rew_mean | -0.0442 | +| time/ | | +| fps | 309 | +| iterations | 7104 | +| time_elapsed | 23498 | +| total_timesteps | 7274496 | +| train/ | | +| approx_kl | 1.5808536 | +| clip_fraction | 0.455 | +| clip_range | 0.2 | +| entropy_loss | -0.389 | +| explained_variance | -2.42 | +| learning_rate | 0.0001 | +| loss | -0.0852 | +| n_updates | 131560 | +| policy_gradient_loss | -0.0579 | +| value_loss | 0.000427 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.55e+03 | +| ep_rew_mean | -0.0389 | +| time/ | | +| fps | 309 | +| iterations | 7105 | +| time_elapsed | 23502 | +| total_timesteps | 7275520 | +| train/ | | +| approx_kl | 2.223404 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.412 | +| explained_variance | -0.913 | +| learning_rate | 0.0001 | +| loss | -0.0792 | +| n_updates | 131570 | +| policy_gradient_loss | -0.0592 | +| value_loss | 0.000738 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.55e+03 | +| ep_rew_mean | -0.0389 | +| time/ | | +| fps | 309 | +| iterations | 7106 | +| time_elapsed | 23505 | +| total_timesteps | 7276544 | +| train/ | | +| approx_kl | 2.5630095 | +| clip_fraction | 0.501 | +| clip_range | 0.2 | +| entropy_loss | -0.419 | +| explained_variance | -1.25 | +| learning_rate | 0.0001 | +| loss | -0.0798 | +| n_updates | 131580 | +| policy_gradient_loss | -0.0685 | +| value_loss | 0.00139 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.55e+03 | +| ep_rew_mean | -0.0356 | +| time/ | | +| fps | 309 | +| iterations | 7107 | +| time_elapsed | 23509 | +| total_timesteps | 7277568 | +| train/ | | +| approx_kl | 2.485401 | +| clip_fraction | 0.495 | +| clip_range | 0.2 | +| entropy_loss | -0.387 | +| explained_variance | -1.42 | +| learning_rate | 0.0001 | +| loss | -0.0882 | +| n_updates | 131590 | +| policy_gradient_loss | -0.068 | +| value_loss | 0.000729 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.54e+03 | +| ep_rew_mean | -0.0357 | +| time/ | | +| fps | 309 | +| iterations | 7108 | +| time_elapsed | 23512 | +| total_timesteps | 7278592 | +| train/ | | +| approx_kl | 2.1386962 | +| clip_fraction | 0.476 | +| clip_range | 0.2 | +| entropy_loss | -0.345 | +| explained_variance | -1.44 | +| learning_rate | 0.0001 | +| loss | -0.0775 | +| n_updates | 131600 | +| policy_gradient_loss | -0.0677 | +| value_loss | 0.00055 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.54e+03 | +| ep_rew_mean | -0.0355 | +| time/ | | +| fps | 309 | +| iterations | 7109 | +| time_elapsed | 23516 | +| total_timesteps | 7279616 | +| train/ | | +| approx_kl | 1.4941882 | +| clip_fraction | 0.443 | +| clip_range | 0.2 | +| entropy_loss | -0.395 | +| explained_variance | -1.57 | +| learning_rate | 0.0001 | +| loss | -0.0808 | +| n_updates | 131610 | +| policy_gradient_loss | -0.0595 | +| value_loss | 0.000446 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.54e+03 | +| ep_rew_mean | -0.0355 | +| time/ | | +| fps | 309 | +| iterations | 7110 | +| time_elapsed | 23519 | +| total_timesteps | 7280640 | +| train/ | | +| approx_kl | 2.4328933 | +| clip_fraction | 0.469 | +| clip_range | 0.2 | +| entropy_loss | -0.356 | +| explained_variance | -1.9 | +| learning_rate | 0.0001 | +| loss | -0.0828 | +| n_updates | 131620 | +| policy_gradient_loss | -0.0673 | +| value_loss | 0.000519 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.54e+03 | +| ep_rew_mean | -0.027 | +| time/ | | +| fps | 309 | +| iterations | 7111 | +| time_elapsed | 23523 | +| total_timesteps | 7281664 | +| train/ | | +| approx_kl | 2.211454 | +| clip_fraction | 0.491 | +| clip_range | 0.2 | +| entropy_loss | -0.4 | +| explained_variance | -0.923 | +| learning_rate | 0.0001 | +| loss | -0.0818 | +| n_updates | 131630 | +| policy_gradient_loss | -0.0666 | +| value_loss | 0.000603 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.54e+03 | +| ep_rew_mean | -0.026 | +| time/ | | +| fps | 309 | +| iterations | 7112 | +| time_elapsed | 23526 | +| total_timesteps | 7282688 | +| train/ | | +| approx_kl | 5.6160727 | +| clip_fraction | 0.47 | +| clip_range | 0.2 | +| entropy_loss | -0.362 | +| explained_variance | -1.42 | +| learning_rate | 0.0001 | +| loss | -0.0913 | +| n_updates | 131640 | +| policy_gradient_loss | -0.0624 | +| value_loss | 0.000596 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.54e+03 | +| ep_rew_mean | -0.0167 | +| time/ | | +| fps | 309 | +| iterations | 7113 | +| time_elapsed | 23530 | +| total_timesteps | 7283712 | +| train/ | | +| approx_kl | 1.8085436 | +| clip_fraction | 0.459 | +| clip_range | 0.2 | +| entropy_loss | -0.356 | +| explained_variance | -2.16 | +| learning_rate | 0.0001 | +| loss | -0.0789 | +| n_updates | 131650 | +| policy_gradient_loss | -0.0676 | +| value_loss | 0.000318 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.54e+03 | +| ep_rew_mean | -0.0167 | +| time/ | | +| fps | 309 | +| iterations | 7114 | +| time_elapsed | 23533 | +| total_timesteps | 7284736 | +| train/ | | +| approx_kl | 2.20698 | +| clip_fraction | 0.491 | +| clip_range | 0.2 | +| entropy_loss | -0.368 | +| explained_variance | -0.284 | +| learning_rate | 0.0001 | +| loss | -0.0663 | +| n_updates | 131660 | +| policy_gradient_loss | -0.0665 | +| value_loss | 0.000705 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.54e+03 | +| ep_rew_mean | -0.0142 | +| time/ | | +| fps | 309 | +| iterations | 7115 | +| time_elapsed | 23536 | +| total_timesteps | 7285760 | +| train/ | | +| approx_kl | 1.8962857 | +| clip_fraction | 0.474 | +| clip_range | 0.2 | +| entropy_loss | -0.405 | +| explained_variance | -2.35 | +| learning_rate | 0.0001 | +| loss | -0.111 | +| n_updates | 131670 | +| policy_gradient_loss | -0.0674 | +| value_loss | 0.000629 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.54e+03 | +| ep_rew_mean | -0.013 | +| time/ | | +| fps | 309 | +| iterations | 7116 | +| time_elapsed | 23539 | +| total_timesteps | 7286784 | +| train/ | | +| approx_kl | 2.0710692 | +| clip_fraction | 0.426 | +| clip_range | 0.2 | +| entropy_loss | -0.306 | +| explained_variance | -7.41 | +| learning_rate | 0.0001 | +| loss | -0.071 | +| n_updates | 131680 | +| policy_gradient_loss | -0.059 | +| value_loss | 0.000955 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.53e+03 | +| ep_rew_mean | -0.0101 | +| time/ | | +| fps | 309 | +| iterations | 7117 | +| time_elapsed | 23542 | +| total_timesteps | 7287808 | +| train/ | | +| approx_kl | 1.858856 | +| clip_fraction | 0.445 | +| clip_range | 0.2 | +| entropy_loss | -0.379 | +| explained_variance | -2.55 | +| learning_rate | 0.0001 | +| loss | -0.0608 | +| n_updates | 131690 | +| policy_gradient_loss | -0.0606 | +| value_loss | 0.000536 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.52e+03 | +| ep_rew_mean | -0.0102 | +| time/ | | +| fps | 309 | +| iterations | 7118 | +| time_elapsed | 23546 | +| total_timesteps | 7288832 | +| train/ | | +| approx_kl | 1.5687418 | +| clip_fraction | 0.449 | +| clip_range | 0.2 | +| entropy_loss | -0.382 | +| explained_variance | -2.04 | +| learning_rate | 0.0001 | +| loss | -0.0907 | +| n_updates | 131700 | +| policy_gradient_loss | -0.0673 | +| value_loss | 0.000441 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.51e+03 | +| ep_rew_mean | -0.0116 | +| time/ | | +| fps | 309 | +| iterations | 7119 | +| time_elapsed | 23549 | +| total_timesteps | 7289856 | +| train/ | | +| approx_kl | 2.1382222 | +| clip_fraction | 0.463 | +| clip_range | 0.2 | +| entropy_loss | -0.379 | +| explained_variance | -5.12 | +| learning_rate | 0.0001 | +| loss | -0.0669 | +| n_updates | 131710 | +| policy_gradient_loss | -0.0623 | +| value_loss | 0.000503 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.51e+03 | +| ep_rew_mean | -0.0108 | +| time/ | | +| fps | 309 | +| iterations | 7120 | +| time_elapsed | 23552 | +| total_timesteps | 7290880 | +| train/ | | +| approx_kl | 1.9595014 | +| clip_fraction | 0.43 | +| clip_range | 0.2 | +| entropy_loss | -0.345 | +| explained_variance | -1.8 | +| learning_rate | 0.0001 | +| loss | -0.066 | +| n_updates | 131720 | +| policy_gradient_loss | -0.0581 | +| value_loss | 0.000469 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.51e+03 | +| ep_rew_mean | -0.0108 | +| time/ | | +| fps | 309 | +| iterations | 7121 | +| time_elapsed | 23555 | +| total_timesteps | 7291904 | +| train/ | | +| approx_kl | 2.7728019 | +| clip_fraction | 0.437 | +| clip_range | 0.2 | +| entropy_loss | -0.357 | +| explained_variance | -2.45 | +| learning_rate | 0.0001 | +| loss | -0.0875 | +| n_updates | 131730 | +| policy_gradient_loss | -0.0553 | +| value_loss | 0.000561 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.52e+03 | +| ep_rew_mean | -0.00585 | +| time/ | | +| fps | 309 | +| iterations | 7122 | +| time_elapsed | 23558 | +| total_timesteps | 7292928 | +| train/ | | +| approx_kl | 1.5021856 | +| clip_fraction | 0.447 | +| clip_range | 0.2 | +| entropy_loss | -0.389 | +| explained_variance | -1.95 | +| learning_rate | 0.0001 | +| loss | -0.1 | +| n_updates | 131740 | +| policy_gradient_loss | -0.0646 | +| value_loss | 0.000397 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.51e+03 | +| ep_rew_mean | -0.00535 | +| time/ | | +| fps | 309 | +| iterations | 7123 | +| time_elapsed | 23562 | +| total_timesteps | 7293952 | +| train/ | | +| approx_kl | 2.9797165 | +| clip_fraction | 0.427 | +| clip_range | 0.2 | +| entropy_loss | -0.331 | +| explained_variance | -1.73 | +| learning_rate | 0.0001 | +| loss | -0.0752 | +| n_updates | 131750 | +| policy_gradient_loss | -0.0651 | +| value_loss | 0.000548 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.51e+03 | +| ep_rew_mean | -0.00782 | +| time/ | | +| fps | 309 | +| iterations | 7124 | +| time_elapsed | 23565 | +| total_timesteps | 7294976 | +| train/ | | +| approx_kl | 1.8114744 | +| clip_fraction | 0.459 | +| clip_range | 0.2 | +| entropy_loss | -0.368 | +| explained_variance | -5.14 | +| learning_rate | 0.0001 | +| loss | -0.0904 | +| n_updates | 131760 | +| policy_gradient_loss | -0.0611 | +| value_loss | 0.000585 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.5e+03 | +| ep_rew_mean | -0.0115 | +| time/ | | +| fps | 309 | +| iterations | 7125 | +| time_elapsed | 23569 | +| total_timesteps | 7296000 | +| train/ | | +| approx_kl | 2.0985036 | +| clip_fraction | 0.452 | +| clip_range | 0.2 | +| entropy_loss | -0.385 | +| explained_variance | -1.55 | +| learning_rate | 0.0001 | +| loss | -0.086 | +| n_updates | 131770 | +| policy_gradient_loss | -0.0632 | +| value_loss | 0.00053 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.5e+03 | +| ep_rew_mean | -0.00962 | +| time/ | | +| fps | 309 | +| iterations | 7126 | +| time_elapsed | 23572 | +| total_timesteps | 7297024 | +| train/ | | +| approx_kl | 2.0716596 | +| clip_fraction | 0.448 | +| clip_range | 0.2 | +| entropy_loss | -0.333 | +| explained_variance | -1.62 | +| learning_rate | 0.0001 | +| loss | -0.0817 | +| n_updates | 131780 | +| policy_gradient_loss | -0.0605 | +| value_loss | 0.000672 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.5e+03 | +| ep_rew_mean | -0.0101 | +| time/ | | +| fps | 309 | +| iterations | 7127 | +| time_elapsed | 23575 | +| total_timesteps | 7298048 | +| train/ | | +| approx_kl | 1.7783101 | +| clip_fraction | 0.431 | +| clip_range | 0.2 | +| entropy_loss | -0.363 | +| explained_variance | -3.83 | +| learning_rate | 0.0001 | +| loss | -0.091 | +| n_updates | 131790 | +| policy_gradient_loss | -0.0623 | +| value_loss | 0.000403 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.5e+03 | +| ep_rew_mean | -0.0101 | +| time/ | | +| fps | 309 | +| iterations | 7128 | +| time_elapsed | 23578 | +| total_timesteps | 7299072 | +| train/ | | +| approx_kl | 2.0063157 | +| clip_fraction | 0.42 | +| clip_range | 0.2 | +| entropy_loss | -0.305 | +| explained_variance | -0.896 | +| learning_rate | 0.0001 | +| loss | -0.0858 | +| n_updates | 131800 | +| policy_gradient_loss | -0.0628 | +| value_loss | 0.000766 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.5e+03 | +| ep_rew_mean | -0.00625 | +| time/ | | +| fps | 309 | +| iterations | 7129 | +| time_elapsed | 23581 | +| total_timesteps | 7300096 | +| train/ | | +| approx_kl | 3.0009327 | +| clip_fraction | 0.476 | +| clip_range | 0.2 | +| entropy_loss | -0.335 | +| explained_variance | -1.76 | +| learning_rate | 0.0001 | +| loss | -0.0817 | +| n_updates | 131810 | +| policy_gradient_loss | -0.0722 | +| value_loss | 0.000632 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.5e+03 | +| ep_rew_mean | -0.00624 | +| time/ | | +| fps | 309 | +| iterations | 7130 | +| time_elapsed | 23585 | +| total_timesteps | 7301120 | +| train/ | | +| approx_kl | 5.0419626 | +| clip_fraction | 0.49 | +| clip_range | 0.2 | +| entropy_loss | -0.449 | +| explained_variance | -7.09 | +| learning_rate | 0.0001 | +| loss | -0.0748 | +| n_updates | 131820 | +| policy_gradient_loss | -0.06 | +| value_loss | 0.000383 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.5e+03 | +| ep_rew_mean | -0.00624 | +| time/ | | +| fps | 309 | +| iterations | 7131 | +| time_elapsed | 23588 | +| total_timesteps | 7302144 | +| train/ | | +| approx_kl | 1.6850128 | +| clip_fraction | 0.432 | +| clip_range | 0.2 | +| entropy_loss | -0.33 | +| explained_variance | -1.03 | +| learning_rate | 0.0001 | +| loss | -0.1 | +| n_updates | 131830 | +| policy_gradient_loss | -0.0639 | +| value_loss | 0.000567 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.5e+03 | +| ep_rew_mean | -0.00541 | +| time/ | | +| fps | 309 | +| iterations | 7132 | +| time_elapsed | 23591 | +| total_timesteps | 7303168 | +| train/ | | +| approx_kl | 1.7608086 | +| clip_fraction | 0.44 | +| clip_range | 0.2 | +| entropy_loss | -0.38 | +| explained_variance | -3.06 | +| learning_rate | 0.0001 | +| loss | -0.0885 | +| n_updates | 131840 | +| policy_gradient_loss | -0.0519 | +| value_loss | 0.000484 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.5e+03 | +| ep_rew_mean | 0.00137 | +| time/ | | +| fps | 309 | +| iterations | 7133 | +| time_elapsed | 23594 | +| total_timesteps | 7304192 | +| train/ | | +| approx_kl | 2.1642013 | +| clip_fraction | 0.415 | +| clip_range | 0.2 | +| entropy_loss | -0.343 | +| explained_variance | -1.38 | +| learning_rate | 0.0001 | +| loss | -0.0668 | +| n_updates | 131850 | +| policy_gradient_loss | -0.0389 | +| value_loss | 0.000627 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.49e+03 | +| ep_rew_mean | -0.00106 | +| time/ | | +| fps | 309 | +| iterations | 7134 | +| time_elapsed | 23597 | +| total_timesteps | 7305216 | +| train/ | | +| approx_kl | 1.7201011 | +| clip_fraction | 0.458 | +| clip_range | 0.2 | +| entropy_loss | -0.383 | +| explained_variance | -1.41 | +| learning_rate | 0.0001 | +| loss | -0.0985 | +| n_updates | 131860 | +| policy_gradient_loss | -0.0699 | +| value_loss | 0.000737 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.47e+03 | +| ep_rew_mean | -0.00118 | +| time/ | | +| fps | 309 | +| iterations | 7135 | +| time_elapsed | 23601 | +| total_timesteps | 7306240 | +| train/ | | +| approx_kl | 1.8296182 | +| clip_fraction | 0.455 | +| clip_range | 0.2 | +| entropy_loss | -0.359 | +| explained_variance | -2.68 | +| learning_rate | 0.0001 | +| loss | -0.0638 | +| n_updates | 131870 | +| policy_gradient_loss | -0.0636 | +| value_loss | 0.0008 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.46e+03 | +| ep_rew_mean | -0.00546 | +| time/ | | +| fps | 309 | +| iterations | 7136 | +| time_elapsed | 23604 | +| total_timesteps | 7307264 | +| train/ | | +| approx_kl | 2.0914752 | +| clip_fraction | 0.458 | +| clip_range | 0.2 | +| entropy_loss | -0.377 | +| explained_variance | -0.935 | +| learning_rate | 0.0001 | +| loss | -0.0986 | +| n_updates | 131880 | +| policy_gradient_loss | -0.0607 | +| value_loss | 0.000612 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.46e+03 | +| ep_rew_mean | -0.00184 | +| time/ | | +| fps | 309 | +| iterations | 7137 | +| time_elapsed | 23607 | +| total_timesteps | 7308288 | +| train/ | | +| approx_kl | 1.8759248 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.377 | +| explained_variance | -1.41 | +| learning_rate | 0.0001 | +| loss | -0.078 | +| n_updates | 131890 | +| policy_gradient_loss | -0.0631 | +| value_loss | 0.000563 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.46e+03 | +| ep_rew_mean | -0.00184 | +| time/ | | +| fps | 309 | +| iterations | 7138 | +| time_elapsed | 23610 | +| total_timesteps | 7309312 | +| train/ | | +| approx_kl | 2.327263 | +| clip_fraction | 0.458 | +| clip_range | 0.2 | +| entropy_loss | -0.382 | +| explained_variance | -4.9 | +| learning_rate | 0.0001 | +| loss | -0.0888 | +| n_updates | 131900 | +| policy_gradient_loss | -0.0676 | +| value_loss | 0.000813 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.47e+03 | +| ep_rew_mean | -0.00302 | +| time/ | | +| fps | 309 | +| iterations | 7139 | +| time_elapsed | 23613 | +| total_timesteps | 7310336 | +| train/ | | +| approx_kl | 2.4410353 | +| clip_fraction | 0.429 | +| clip_range | 0.2 | +| entropy_loss | -0.348 | +| explained_variance | -9.43 | +| learning_rate | 0.0001 | +| loss | -0.0574 | +| n_updates | 131910 | +| policy_gradient_loss | -0.0603 | +| value_loss | 0.000168 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.47e+03 | +| ep_rew_mean | -0.00302 | +| time/ | | +| fps | 309 | +| iterations | 7140 | +| time_elapsed | 23616 | +| total_timesteps | 7311360 | +| train/ | | +| approx_kl | 1.6087759 | +| clip_fraction | 0.433 | +| clip_range | 0.2 | +| entropy_loss | -0.362 | +| explained_variance | -0.468 | +| learning_rate | 0.0001 | +| loss | -0.0592 | +| n_updates | 131920 | +| policy_gradient_loss | -0.0549 | +| value_loss | 0.000326 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.47e+03 | +| ep_rew_mean | -0.00555 | +| time/ | | +| fps | 309 | +| iterations | 7141 | +| time_elapsed | 23620 | +| total_timesteps | 7312384 | +| train/ | | +| approx_kl | 5.22833 | +| clip_fraction | 0.448 | +| clip_range | 0.2 | +| entropy_loss | -0.377 | +| explained_variance | -6.17 | +| learning_rate | 0.0001 | +| loss | -0.0841 | +| n_updates | 131930 | +| policy_gradient_loss | -0.0606 | +| value_loss | 0.000248 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.46e+03 | +| ep_rew_mean | -0.00778 | +| time/ | | +| fps | 309 | +| iterations | 7142 | +| time_elapsed | 23623 | +| total_timesteps | 7313408 | +| train/ | | +| approx_kl | 1.7928073 | +| clip_fraction | 0.434 | +| clip_range | 0.2 | +| entropy_loss | -0.346 | +| explained_variance | -1.95 | +| learning_rate | 0.0001 | +| loss | -0.0867 | +| n_updates | 131940 | +| policy_gradient_loss | -0.0604 | +| value_loss | 0.000433 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.46e+03 | +| ep_rew_mean | -0.00778 | +| time/ | | +| fps | 309 | +| iterations | 7143 | +| time_elapsed | 23626 | +| total_timesteps | 7314432 | +| train/ | | +| approx_kl | 1.7719647 | +| clip_fraction | 0.415 | +| clip_range | 0.2 | +| entropy_loss | -0.338 | +| explained_variance | -0.961 | +| learning_rate | 0.0001 | +| loss | -0.0774 | +| n_updates | 131950 | +| policy_gradient_loss | -0.063 | +| value_loss | 0.000802 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.45e+03 | +| ep_rew_mean | -0.00989 | +| time/ | | +| fps | 309 | +| iterations | 7144 | +| time_elapsed | 23630 | +| total_timesteps | 7315456 | +| train/ | | +| approx_kl | 2.2549925 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.37 | +| explained_variance | -2.53 | +| learning_rate | 0.0001 | +| loss | -0.0728 | +| n_updates | 131960 | +| policy_gradient_loss | -0.0709 | +| value_loss | 0.00056 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.45e+03 | +| ep_rew_mean | -0.0139 | +| time/ | | +| fps | 309 | +| iterations | 7145 | +| time_elapsed | 23633 | +| total_timesteps | 7316480 | +| train/ | | +| approx_kl | 3.8490322 | +| clip_fraction | 0.502 | +| clip_range | 0.2 | +| entropy_loss | -0.365 | +| explained_variance | -3.47 | +| learning_rate | 0.0001 | +| loss | -0.0851 | +| n_updates | 131970 | +| policy_gradient_loss | -0.0727 | +| value_loss | 0.000406 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.44e+03 | +| ep_rew_mean | -0.0175 | +| time/ | | +| fps | 309 | +| iterations | 7146 | +| time_elapsed | 23636 | +| total_timesteps | 7317504 | +| train/ | | +| approx_kl | 2.1954362 | +| clip_fraction | 0.412 | +| clip_range | 0.2 | +| entropy_loss | -0.327 | +| explained_variance | -1.28 | +| learning_rate | 0.0001 | +| loss | -0.0703 | +| n_updates | 131980 | +| policy_gradient_loss | -0.0548 | +| value_loss | 0.000745 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.44e+03 | +| ep_rew_mean | -0.0175 | +| time/ | | +| fps | 309 | +| iterations | 7147 | +| time_elapsed | 23640 | +| total_timesteps | 7318528 | +| train/ | | +| approx_kl | 1.354665 | +| clip_fraction | 0.423 | +| clip_range | 0.2 | +| entropy_loss | -0.359 | +| explained_variance | -3.04 | +| learning_rate | 0.0001 | +| loss | -0.0845 | +| n_updates | 131990 | +| policy_gradient_loss | -0.0634 | +| value_loss | 0.000639 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.44e+03 | +| ep_rew_mean | -0.0175 | +| time/ | | +| fps | 309 | +| iterations | 7148 | +| time_elapsed | 23643 | +| total_timesteps | 7319552 | +| train/ | | +| approx_kl | 2.8031363 | +| clip_fraction | 0.514 | +| clip_range | 0.2 | +| entropy_loss | -0.38 | +| explained_variance | -1.38 | +| learning_rate | 0.0001 | +| loss | -0.0883 | +| n_updates | 132000 | +| policy_gradient_loss | -0.0597 | +| value_loss | 0.000966 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.45e+03 | +| ep_rew_mean | -0.0141 | +| time/ | | +| fps | 309 | +| iterations | 7149 | +| time_elapsed | 23647 | +| total_timesteps | 7320576 | +| train/ | | +| approx_kl | 2.1895323 | +| clip_fraction | 0.496 | +| clip_range | 0.2 | +| entropy_loss | -0.41 | +| explained_variance | -1.23 | +| learning_rate | 0.0001 | +| loss | -0.0747 | +| n_updates | 132010 | +| policy_gradient_loss | -0.0664 | +| value_loss | 0.00111 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.45e+03 | +| ep_rew_mean | -0.0141 | +| time/ | | +| fps | 309 | +| iterations | 7150 | +| time_elapsed | 23650 | +| total_timesteps | 7321600 | +| train/ | | +| approx_kl | 1.980565 | +| clip_fraction | 0.497 | +| clip_range | 0.2 | +| entropy_loss | -0.449 | +| explained_variance | -1.84 | +| learning_rate | 0.0001 | +| loss | -0.0876 | +| n_updates | 132020 | +| policy_gradient_loss | -0.0606 | +| value_loss | 0.000501 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.45e+03 | +| ep_rew_mean | -0.0148 | +| time/ | | +| fps | 309 | +| iterations | 7151 | +| time_elapsed | 23653 | +| total_timesteps | 7322624 | +| train/ | | +| approx_kl | 2.146297 | +| clip_fraction | 0.489 | +| clip_range | 0.2 | +| entropy_loss | -0.379 | +| explained_variance | -2.15 | +| learning_rate | 0.0001 | +| loss | -0.0798 | +| n_updates | 132030 | +| policy_gradient_loss | -0.0713 | +| value_loss | 0.000432 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.45e+03 | +| ep_rew_mean | -0.0177 | +| time/ | | +| fps | 309 | +| iterations | 7152 | +| time_elapsed | 23656 | +| total_timesteps | 7323648 | +| train/ | | +| approx_kl | 2.1451552 | +| clip_fraction | 0.45 | +| clip_range | 0.2 | +| entropy_loss | -0.367 | +| explained_variance | -4.38 | +| learning_rate | 0.0001 | +| loss | -0.0867 | +| n_updates | 132040 | +| policy_gradient_loss | -0.0653 | +| value_loss | 0.000465 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.45e+03 | +| ep_rew_mean | -0.0177 | +| time/ | | +| fps | 309 | +| iterations | 7153 | +| time_elapsed | 23659 | +| total_timesteps | 7324672 | +| train/ | | +| approx_kl | 1.7237463 | +| clip_fraction | 0.42 | +| clip_range | 0.2 | +| entropy_loss | -0.327 | +| explained_variance | -1.2 | +| learning_rate | 0.0001 | +| loss | -0.0869 | +| n_updates | 132050 | +| policy_gradient_loss | -0.0581 | +| value_loss | 0.000593 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.45e+03 | +| ep_rew_mean | -0.0178 | +| time/ | | +| fps | 309 | +| iterations | 7154 | +| time_elapsed | 23663 | +| total_timesteps | 7325696 | +| train/ | | +| approx_kl | 1.7984519 | +| clip_fraction | 0.446 | +| clip_range | 0.2 | +| entropy_loss | -0.353 | +| explained_variance | -3.01 | +| learning_rate | 0.0001 | +| loss | -0.084 | +| n_updates | 132060 | +| policy_gradient_loss | -0.0615 | +| value_loss | 0.000478 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.45e+03 | +| ep_rew_mean | -0.0177 | +| time/ | | +| fps | 309 | +| iterations | 7155 | +| time_elapsed | 23666 | +| total_timesteps | 7326720 | +| train/ | | +| approx_kl | 1.7698468 | +| clip_fraction | 0.484 | +| clip_range | 0.2 | +| entropy_loss | -0.406 | +| explained_variance | -2.16 | +| learning_rate | 0.0001 | +| loss | -0.0811 | +| n_updates | 132070 | +| policy_gradient_loss | -0.0671 | +| value_loss | 0.000499 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.45e+03 | +| ep_rew_mean | -0.0169 | +| time/ | | +| fps | 309 | +| iterations | 7156 | +| time_elapsed | 23669 | +| total_timesteps | 7327744 | +| train/ | | +| approx_kl | 1.8832 | +| clip_fraction | 0.494 | +| clip_range | 0.2 | +| entropy_loss | -0.436 | +| explained_variance | -1.67 | +| learning_rate | 0.0001 | +| loss | -0.083 | +| n_updates | 132080 | +| policy_gradient_loss | -0.0619 | +| value_loss | 0.000481 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.45e+03 | +| ep_rew_mean | -0.00823 | +| time/ | | +| fps | 309 | +| iterations | 7157 | +| time_elapsed | 23672 | +| total_timesteps | 7328768 | +| train/ | | +| approx_kl | 2.208106 | +| clip_fraction | 0.469 | +| clip_range | 0.2 | +| entropy_loss | -0.403 | +| explained_variance | -1.4 | +| learning_rate | 0.0001 | +| loss | -0.0691 | +| n_updates | 132090 | +| policy_gradient_loss | -0.0613 | +| value_loss | 0.000433 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.44e+03 | +| ep_rew_mean | -0.00552 | +| time/ | | +| fps | 309 | +| iterations | 7158 | +| time_elapsed | 23675 | +| total_timesteps | 7329792 | +| train/ | | +| approx_kl | 2.2512717 | +| clip_fraction | 0.468 | +| clip_range | 0.2 | +| entropy_loss | -0.373 | +| explained_variance | -0.807 | +| learning_rate | 0.0001 | +| loss | -0.0985 | +| n_updates | 132100 | +| policy_gradient_loss | -0.0548 | +| value_loss | 0.000852 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.44e+03 | +| ep_rew_mean | -0.00552 | +| time/ | | +| fps | 309 | +| iterations | 7159 | +| time_elapsed | 23679 | +| total_timesteps | 7330816 | +| train/ | | +| approx_kl | 1.6437476 | +| clip_fraction | 0.442 | +| clip_range | 0.2 | +| entropy_loss | -0.412 | +| explained_variance | -2.3 | +| learning_rate | 0.0001 | +| loss | -0.0473 | +| n_updates | 132110 | +| policy_gradient_loss | -0.0536 | +| value_loss | 0.000799 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.44e+03 | +| ep_rew_mean | -0.00328 | +| time/ | | +| fps | 309 | +| iterations | 7160 | +| time_elapsed | 23682 | +| total_timesteps | 7331840 | +| train/ | | +| approx_kl | 1.8143765 | +| clip_fraction | 0.44 | +| clip_range | 0.2 | +| entropy_loss | -0.343 | +| explained_variance | -4.54 | +| learning_rate | 0.0001 | +| loss | -0.087 | +| n_updates | 132120 | +| policy_gradient_loss | -0.061 | +| value_loss | 0.00039 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.43e+03 | +| ep_rew_mean | -0.00411 | +| time/ | | +| fps | 309 | +| iterations | 7161 | +| time_elapsed | 23686 | +| total_timesteps | 7332864 | +| train/ | | +| approx_kl | 1.4591259 | +| clip_fraction | 0.472 | +| clip_range | 0.2 | +| entropy_loss | -0.405 | +| explained_variance | -2.46 | +| learning_rate | 0.0001 | +| loss | -0.0652 | +| n_updates | 132130 | +| policy_gradient_loss | -0.0684 | +| value_loss | 0.000464 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | -0.00805 | +| time/ | | +| fps | 309 | +| iterations | 7162 | +| time_elapsed | 23689 | +| total_timesteps | 7333888 | +| train/ | | +| approx_kl | 1.905852 | +| clip_fraction | 0.442 | +| clip_range | 0.2 | +| entropy_loss | -0.351 | +| explained_variance | -0.751 | +| learning_rate | 0.0001 | +| loss | -0.07 | +| n_updates | 132140 | +| policy_gradient_loss | -0.0626 | +| value_loss | 0.000477 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | -0.00805 | +| time/ | | +| fps | 309 | +| iterations | 7163 | +| time_elapsed | 23692 | +| total_timesteps | 7334912 | +| train/ | | +| approx_kl | 1.7221124 | +| clip_fraction | 0.435 | +| clip_range | 0.2 | +| entropy_loss | -0.315 | +| explained_variance | -1.93 | +| learning_rate | 0.0001 | +| loss | -0.0786 | +| n_updates | 132150 | +| policy_gradient_loss | -0.0619 | +| value_loss | 0.000628 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.43e+03 | +| ep_rew_mean | -0.00388 | +| time/ | | +| fps | 309 | +| iterations | 7164 | +| time_elapsed | 23696 | +| total_timesteps | 7335936 | +| train/ | | +| approx_kl | 2.4962363 | +| clip_fraction | 0.473 | +| clip_range | 0.2 | +| entropy_loss | -0.359 | +| explained_variance | -2.88 | +| learning_rate | 0.0001 | +| loss | -0.0945 | +| n_updates | 132160 | +| policy_gradient_loss | -0.0646 | +| value_loss | 0.000562 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.43e+03 | +| ep_rew_mean | -0.00388 | +| time/ | | +| fps | 309 | +| iterations | 7165 | +| time_elapsed | 23699 | +| total_timesteps | 7336960 | +| train/ | | +| approx_kl | 2.499438 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.393 | +| explained_variance | -2.54 | +| learning_rate | 0.0001 | +| loss | -0.0794 | +| n_updates | 132170 | +| policy_gradient_loss | -0.0647 | +| value_loss | 0.000525 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.43e+03 | +| ep_rew_mean | -0.00388 | +| time/ | | +| fps | 309 | +| iterations | 7166 | +| time_elapsed | 23703 | +| total_timesteps | 7337984 | +| train/ | | +| approx_kl | 1.9315755 | +| clip_fraction | 0.495 | +| clip_range | 0.2 | +| entropy_loss | -0.413 | +| explained_variance | -2.51 | +| learning_rate | 0.0001 | +| loss | -0.0792 | +| n_updates | 132180 | +| policy_gradient_loss | -0.0619 | +| value_loss | 0.000381 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.44e+03 | +| ep_rew_mean | 0.00185 | +| time/ | | +| fps | 309 | +| iterations | 7167 | +| time_elapsed | 23706 | +| total_timesteps | 7339008 | +| train/ | | +| approx_kl | 1.8656569 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.413 | +| explained_variance | -1.79 | +| learning_rate | 0.0001 | +| loss | -0.079 | +| n_updates | 132190 | +| policy_gradient_loss | -0.0709 | +| value_loss | 0.00064 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.44e+03 | +| ep_rew_mean | 0.00185 | +| time/ | | +| fps | 309 | +| iterations | 7168 | +| time_elapsed | 23710 | +| total_timesteps | 7340032 | +| train/ | | +| approx_kl | 8.351928 | +| clip_fraction | 0.461 | +| clip_range | 0.2 | +| entropy_loss | -0.378 | +| explained_variance | -3.53 | +| learning_rate | 0.0001 | +| loss | -0.0841 | +| n_updates | 132200 | +| policy_gradient_loss | -0.0624 | +| value_loss | 0.000306 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.45e+03 | +| ep_rew_mean | 0.00136 | +| time/ | | +| fps | 309 | +| iterations | 7169 | +| time_elapsed | 23713 | +| total_timesteps | 7341056 | +| train/ | | +| approx_kl | 1.7835643 | +| clip_fraction | 0.479 | +| clip_range | 0.2 | +| entropy_loss | -0.402 | +| explained_variance | -0.973 | +| learning_rate | 0.0001 | +| loss | -0.0609 | +| n_updates | 132210 | +| policy_gradient_loss | -0.0609 | +| value_loss | 0.000289 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.45e+03 | +| ep_rew_mean | 0.00136 | +| time/ | | +| fps | 309 | +| iterations | 7170 | +| time_elapsed | 23716 | +| total_timesteps | 7342080 | +| train/ | | +| approx_kl | 1.5664734 | +| clip_fraction | 0.407 | +| clip_range | 0.2 | +| entropy_loss | -0.347 | +| explained_variance | -2.81 | +| learning_rate | 0.0001 | +| loss | -0.0788 | +| n_updates | 132220 | +| policy_gradient_loss | -0.0535 | +| value_loss | 0.000316 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.45e+03 | +| ep_rew_mean | 0.00745 | +| time/ | | +| fps | 309 | +| iterations | 7171 | +| time_elapsed | 23719 | +| total_timesteps | 7343104 | +| train/ | | +| approx_kl | 2.0107176 | +| clip_fraction | 0.485 | +| clip_range | 0.2 | +| entropy_loss | -0.385 | +| explained_variance | -1.05 | +| learning_rate | 0.0001 | +| loss | -0.0787 | +| n_updates | 132230 | +| policy_gradient_loss | -0.0635 | +| value_loss | 0.000731 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.45e+03 | +| ep_rew_mean | 0.00745 | +| time/ | | +| fps | 309 | +| iterations | 7172 | +| time_elapsed | 23722 | +| total_timesteps | 7344128 | +| train/ | | +| approx_kl | 1.6954924 | +| clip_fraction | 0.45 | +| clip_range | 0.2 | +| entropy_loss | -0.391 | +| explained_variance | -1.94 | +| learning_rate | 0.0001 | +| loss | -0.0714 | +| n_updates | 132240 | +| policy_gradient_loss | -0.061 | +| value_loss | 0.000656 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.45e+03 | +| ep_rew_mean | 0.00704 | +| time/ | | +| fps | 309 | +| iterations | 7173 | +| time_elapsed | 23725 | +| total_timesteps | 7345152 | +| train/ | | +| approx_kl | 1.6214173 | +| clip_fraction | 0.452 | +| clip_range | 0.2 | +| entropy_loss | -0.36 | +| explained_variance | -8.79 | +| learning_rate | 0.0001 | +| loss | -0.0887 | +| n_updates | 132250 | +| policy_gradient_loss | -0.0644 | +| value_loss | 0.000455 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.44e+03 | +| ep_rew_mean | 0.00343 | +| time/ | | +| fps | 309 | +| iterations | 7174 | +| time_elapsed | 23729 | +| total_timesteps | 7346176 | +| train/ | | +| approx_kl | 2.021675 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.381 | +| explained_variance | -0.915 | +| learning_rate | 0.0001 | +| loss | -0.0761 | +| n_updates | 132260 | +| policy_gradient_loss | -0.0628 | +| value_loss | 0.000738 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.44e+03 | +| ep_rew_mean | 0.00343 | +| time/ | | +| fps | 309 | +| iterations | 7175 | +| time_elapsed | 23732 | +| total_timesteps | 7347200 | +| train/ | | +| approx_kl | 20.102777 | +| clip_fraction | 0.441 | +| clip_range | 0.2 | +| entropy_loss | -0.361 | +| explained_variance | -1.13 | +| learning_rate | 0.0001 | +| loss | -0.0755 | +| n_updates | 132270 | +| policy_gradient_loss | -0.0549 | +| value_loss | 0.000537 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.45e+03 | +| ep_rew_mean | 0.00615 | +| time/ | | +| fps | 309 | +| iterations | 7176 | +| time_elapsed | 23735 | +| total_timesteps | 7348224 | +| train/ | | +| approx_kl | 2.3683558 | +| clip_fraction | 0.493 | +| clip_range | 0.2 | +| entropy_loss | -0.383 | +| explained_variance | -1.89 | +| learning_rate | 0.0001 | +| loss | -0.0966 | +| n_updates | 132280 | +| policy_gradient_loss | -0.0699 | +| value_loss | 0.000627 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.45e+03 | +| ep_rew_mean | 0.00615 | +| time/ | | +| fps | 309 | +| iterations | 7177 | +| time_elapsed | 23738 | +| total_timesteps | 7349248 | +| train/ | | +| approx_kl | 2.0763183 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.379 | +| explained_variance | -2.46 | +| learning_rate | 0.0001 | +| loss | -0.0909 | +| n_updates | 132290 | +| policy_gradient_loss | -0.0651 | +| value_loss | 0.000624 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.44e+03 | +| ep_rew_mean | 0.00299 | +| time/ | | +| fps | 309 | +| iterations | 7178 | +| time_elapsed | 23742 | +| total_timesteps | 7350272 | +| train/ | | +| approx_kl | 1.9911035 | +| clip_fraction | 0.461 | +| clip_range | 0.2 | +| entropy_loss | -0.348 | +| explained_variance | -3.36 | +| learning_rate | 0.0001 | +| loss | -0.0919 | +| n_updates | 132300 | +| policy_gradient_loss | -0.0708 | +| value_loss | 0.000438 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.43e+03 | +| ep_rew_mean | -0.00215 | +| time/ | | +| fps | 309 | +| iterations | 7179 | +| time_elapsed | 23745 | +| total_timesteps | 7351296 | +| train/ | | +| approx_kl | 1.9062867 | +| clip_fraction | 0.465 | +| clip_range | 0.2 | +| entropy_loss | -0.37 | +| explained_variance | -2.19 | +| learning_rate | 0.0001 | +| loss | -0.0957 | +| n_updates | 132310 | +| policy_gradient_loss | -0.0659 | +| value_loss | 0.000505 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | -0.000259 | +| time/ | | +| fps | 309 | +| iterations | 7180 | +| time_elapsed | 23749 | +| total_timesteps | 7352320 | +| train/ | | +| approx_kl | 1.8006098 | +| clip_fraction | 0.417 | +| clip_range | 0.2 | +| entropy_loss | -0.324 | +| explained_variance | -1.43 | +| learning_rate | 0.0001 | +| loss | -0.0894 | +| n_updates | 132320 | +| policy_gradient_loss | -0.0562 | +| value_loss | 0.000683 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.43e+03 | +| ep_rew_mean | 0.000959 | +| time/ | | +| fps | 309 | +| iterations | 7181 | +| time_elapsed | 23752 | +| total_timesteps | 7353344 | +| train/ | | +| approx_kl | 1.753846 | +| clip_fraction | 0.455 | +| clip_range | 0.2 | +| entropy_loss | -0.361 | +| explained_variance | -2.31 | +| learning_rate | 0.0001 | +| loss | -0.0639 | +| n_updates | 132330 | +| policy_gradient_loss | -0.0657 | +| value_loss | 0.000391 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.43e+03 | +| ep_rew_mean | 0.000959 | +| time/ | | +| fps | 309 | +| iterations | 7182 | +| time_elapsed | 23756 | +| total_timesteps | 7354368 | +| train/ | | +| approx_kl | 2.5219402 | +| clip_fraction | 0.507 | +| clip_range | 0.2 | +| entropy_loss | -0.437 | +| explained_variance | -0.93 | +| learning_rate | 0.0001 | +| loss | -0.0815 | +| n_updates | 132340 | +| policy_gradient_loss | -0.0643 | +| value_loss | 0.000583 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.43e+03 | +| ep_rew_mean | 0.00432 | +| time/ | | +| fps | 309 | +| iterations | 7183 | +| time_elapsed | 23759 | +| total_timesteps | 7355392 | +| train/ | | +| approx_kl | 3.4102893 | +| clip_fraction | 0.542 | +| clip_range | 0.2 | +| entropy_loss | -0.505 | +| explained_variance | -2.58 | +| learning_rate | 0.0001 | +| loss | -0.112 | +| n_updates | 132350 | +| policy_gradient_loss | -0.0626 | +| value_loss | 0.000421 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.00311 | +| time/ | | +| fps | 309 | +| iterations | 7184 | +| time_elapsed | 23762 | +| total_timesteps | 7356416 | +| train/ | | +| approx_kl | 2.0063052 | +| clip_fraction | 0.47 | +| clip_range | 0.2 | +| entropy_loss | -0.394 | +| explained_variance | -1.02 | +| learning_rate | 0.0001 | +| loss | -0.108 | +| n_updates | 132360 | +| policy_gradient_loss | -0.0579 | +| value_loss | 0.000488 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.00435 | +| time/ | | +| fps | 309 | +| iterations | 7185 | +| time_elapsed | 23766 | +| total_timesteps | 7357440 | +| train/ | | +| approx_kl | 2.604639 | +| clip_fraction | 0.453 | +| clip_range | 0.2 | +| entropy_loss | -0.327 | +| explained_variance | -1.97 | +| learning_rate | 0.0001 | +| loss | -0.0848 | +| n_updates | 132370 | +| policy_gradient_loss | -0.0645 | +| value_loss | 0.00075 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.00306 | +| time/ | | +| fps | 309 | +| iterations | 7186 | +| time_elapsed | 23769 | +| total_timesteps | 7358464 | +| train/ | | +| approx_kl | 7.0068007 | +| clip_fraction | 0.464 | +| clip_range | 0.2 | +| entropy_loss | -0.334 | +| explained_variance | -4.02 | +| learning_rate | 0.0001 | +| loss | -0.0716 | +| n_updates | 132380 | +| policy_gradient_loss | -0.0591 | +| value_loss | 0.000538 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.00279 | +| time/ | | +| fps | 309 | +| iterations | 7187 | +| time_elapsed | 23773 | +| total_timesteps | 7359488 | +| train/ | | +| approx_kl | 2.061525 | +| clip_fraction | 0.392 | +| clip_range | 0.2 | +| entropy_loss | -0.327 | +| explained_variance | -1.5 | +| learning_rate | 0.0001 | +| loss | -0.0799 | +| n_updates | 132390 | +| policy_gradient_loss | -0.0544 | +| value_loss | 0.000683 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.00312 | +| time/ | | +| fps | 309 | +| iterations | 7188 | +| time_elapsed | 23776 | +| total_timesteps | 7360512 | +| train/ | | +| approx_kl | 1.9236934 | +| clip_fraction | 0.396 | +| clip_range | 0.2 | +| entropy_loss | -0.309 | +| explained_variance | -0.73 | +| learning_rate | 0.0001 | +| loss | -0.0811 | +| n_updates | 132400 | +| policy_gradient_loss | -0.0485 | +| value_loss | 0.000563 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.00312 | +| time/ | | +| fps | 309 | +| iterations | 7189 | +| time_elapsed | 23779 | +| total_timesteps | 7361536 | +| train/ | | +| approx_kl | 2.1007032 | +| clip_fraction | 0.44 | +| clip_range | 0.2 | +| entropy_loss | -0.327 | +| explained_variance | -1.56 | +| learning_rate | 0.0001 | +| loss | -0.0506 | +| n_updates | 132410 | +| policy_gradient_loss | -0.0532 | +| value_loss | 0.000617 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.00583 | +| time/ | | +| fps | 309 | +| iterations | 7190 | +| time_elapsed | 23782 | +| total_timesteps | 7362560 | +| train/ | | +| approx_kl | 1.4870377 | +| clip_fraction | 0.417 | +| clip_range | 0.2 | +| entropy_loss | -0.309 | +| explained_variance | -4.72 | +| learning_rate | 0.0001 | +| loss | -0.063 | +| n_updates | 132420 | +| policy_gradient_loss | -0.0615 | +| value_loss | 0.000473 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.00583 | +| time/ | | +| fps | 309 | +| iterations | 7191 | +| time_elapsed | 23785 | +| total_timesteps | 7363584 | +| train/ | | +| approx_kl | 2.6931226 | +| clip_fraction | 0.442 | +| clip_range | 0.2 | +| entropy_loss | -0.34 | +| explained_variance | -0.508 | +| learning_rate | 0.0001 | +| loss | -0.0864 | +| n_updates | 132430 | +| policy_gradient_loss | -0.0565 | +| value_loss | 0.000791 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.0108 | +| time/ | | +| fps | 309 | +| iterations | 7192 | +| time_elapsed | 23789 | +| total_timesteps | 7364608 | +| train/ | | +| approx_kl | 2.0508876 | +| clip_fraction | 0.502 | +| clip_range | 0.2 | +| entropy_loss | -0.426 | +| explained_variance | -1.39 | +| learning_rate | 0.0001 | +| loss | -0.0879 | +| n_updates | 132440 | +| policy_gradient_loss | -0.0735 | +| value_loss | 0.000741 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.0108 | +| time/ | | +| fps | 309 | +| iterations | 7193 | +| time_elapsed | 23792 | +| total_timesteps | 7365632 | +| train/ | | +| approx_kl | 11.441455 | +| clip_fraction | 0.462 | +| clip_range | 0.2 | +| entropy_loss | -0.399 | +| explained_variance | -7.58 | +| learning_rate | 0.0001 | +| loss | -0.0854 | +| n_updates | 132450 | +| policy_gradient_loss | -0.0623 | +| value_loss | 0.000504 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.0116 | +| time/ | | +| fps | 309 | +| iterations | 7194 | +| time_elapsed | 23795 | +| total_timesteps | 7366656 | +| train/ | | +| approx_kl | 15.869501 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.399 | +| explained_variance | -3.35 | +| learning_rate | 0.0001 | +| loss | -0.0822 | +| n_updates | 132460 | +| policy_gradient_loss | -0.068 | +| value_loss | 0.000471 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.00628 | +| time/ | | +| fps | 309 | +| iterations | 7195 | +| time_elapsed | 23798 | +| total_timesteps | 7367680 | +| train/ | | +| approx_kl | 1.6504058 | +| clip_fraction | 0.416 | +| clip_range | 0.2 | +| entropy_loss | -0.314 | +| explained_variance | -3 | +| learning_rate | 0.0001 | +| loss | -0.0696 | +| n_updates | 132470 | +| policy_gradient_loss | -0.059 | +| value_loss | 0.000701 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.00628 | +| time/ | | +| fps | 309 | +| iterations | 7196 | +| time_elapsed | 23802 | +| total_timesteps | 7368704 | +| train/ | | +| approx_kl | 1.912433 | +| clip_fraction | 0.448 | +| clip_range | 0.2 | +| entropy_loss | -0.337 | +| explained_variance | -4.04 | +| learning_rate | 0.0001 | +| loss | -0.082 | +| n_updates | 132480 | +| policy_gradient_loss | -0.0651 | +| value_loss | 0.00035 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.000668 | +| time/ | | +| fps | 309 | +| iterations | 7197 | +| time_elapsed | 23805 | +| total_timesteps | 7369728 | +| train/ | | +| approx_kl | 1.3652701 | +| clip_fraction | 0.434 | +| clip_range | 0.2 | +| entropy_loss | -0.333 | +| explained_variance | -4.98 | +| learning_rate | 0.0001 | +| loss | -0.0704 | +| n_updates | 132490 | +| policy_gradient_loss | -0.0636 | +| value_loss | 0.000321 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.000668 | +| time/ | | +| fps | 309 | +| iterations | 7198 | +| time_elapsed | 23808 | +| total_timesteps | 7370752 | +| train/ | | +| approx_kl | 1.7380581 | +| clip_fraction | 0.421 | +| clip_range | 0.2 | +| entropy_loss | -0.371 | +| explained_variance | -0.554 | +| learning_rate | 0.0001 | +| loss | -0.049 | +| n_updates | 132500 | +| policy_gradient_loss | -0.0541 | +| value_loss | 0.000545 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.43e+03 | +| ep_rew_mean | 0.00698 | +| time/ | | +| fps | 309 | +| iterations | 7199 | +| time_elapsed | 23812 | +| total_timesteps | 7371776 | +| train/ | | +| approx_kl | 1.7939255 | +| clip_fraction | 0.458 | +| clip_range | 0.2 | +| entropy_loss | -0.364 | +| explained_variance | -0.811 | +| learning_rate | 0.0001 | +| loss | -0.0771 | +| n_updates | 132510 | +| policy_gradient_loss | -0.0638 | +| value_loss | 0.000682 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.00457 | +| time/ | | +| fps | 309 | +| iterations | 7200 | +| time_elapsed | 23815 | +| total_timesteps | 7372800 | +| train/ | | +| approx_kl | 1.9792166 | +| clip_fraction | 0.461 | +| clip_range | 0.2 | +| entropy_loss | -0.372 | +| explained_variance | -1.64 | +| learning_rate | 0.0001 | +| loss | -0.0937 | +| n_updates | 132520 | +| policy_gradient_loss | -0.0663 | +| value_loss | 0.000476 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.00457 | +| time/ | | +| fps | 309 | +| iterations | 7201 | +| time_elapsed | 23819 | +| total_timesteps | 7373824 | +| train/ | | +| approx_kl | 2.061579 | +| clip_fraction | 0.387 | +| clip_range | 0.2 | +| entropy_loss | -0.309 | +| explained_variance | -3.52 | +| learning_rate | 0.0001 | +| loss | -0.0708 | +| n_updates | 132530 | +| policy_gradient_loss | -0.0588 | +| value_loss | 0.000271 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.43e+03 | +| ep_rew_mean | 0.00998 | +| time/ | | +| fps | 309 | +| iterations | 7202 | +| time_elapsed | 23822 | +| total_timesteps | 7374848 | +| train/ | | +| approx_kl | 2.4608998 | +| clip_fraction | 0.461 | +| clip_range | 0.2 | +| entropy_loss | -0.388 | +| explained_variance | -1.14 | +| learning_rate | 0.0001 | +| loss | -0.0687 | +| n_updates | 132540 | +| policy_gradient_loss | -0.0616 | +| value_loss | 0.000596 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.43e+03 | +| ep_rew_mean | 0.00998 | +| time/ | | +| fps | 309 | +| iterations | 7203 | +| time_elapsed | 23825 | +| total_timesteps | 7375872 | +| train/ | | +| approx_kl | 1.6174748 | +| clip_fraction | 0.452 | +| clip_range | 0.2 | +| entropy_loss | -0.391 | +| explained_variance | -4.76 | +| learning_rate | 0.0001 | +| loss | -0.0841 | +| n_updates | 132550 | +| policy_gradient_loss | -0.062 | +| value_loss | 0.000286 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.43e+03 | +| ep_rew_mean | 0.00998 | +| time/ | | +| fps | 309 | +| iterations | 7204 | +| time_elapsed | 23829 | +| total_timesteps | 7376896 | +| train/ | | +| approx_kl | 2.0687985 | +| clip_fraction | 0.543 | +| clip_range | 0.2 | +| entropy_loss | -0.466 | +| explained_variance | -2.15 | +| learning_rate | 0.0001 | +| loss | -0.0792 | +| n_updates | 132560 | +| policy_gradient_loss | -0.0705 | +| value_loss | 0.000485 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.44e+03 | +| ep_rew_mean | 0.011 | +| time/ | | +| fps | 309 | +| iterations | 7205 | +| time_elapsed | 23832 | +| total_timesteps | 7377920 | +| train/ | | +| approx_kl | 2.4216838 | +| clip_fraction | 0.49 | +| clip_range | 0.2 | +| entropy_loss | -0.374 | +| explained_variance | -2.15 | +| learning_rate | 0.0001 | +| loss | -0.0869 | +| n_updates | 132570 | +| policy_gradient_loss | -0.0712 | +| value_loss | 0.000589 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.45e+03 | +| ep_rew_mean | 0.0146 | +| time/ | | +| fps | 309 | +| iterations | 7206 | +| time_elapsed | 23835 | +| total_timesteps | 7378944 | +| train/ | | +| approx_kl | 1.8163188 | +| clip_fraction | 0.49 | +| clip_range | 0.2 | +| entropy_loss | -0.421 | +| explained_variance | -3.3 | +| learning_rate | 0.0001 | +| loss | -0.0849 | +| n_updates | 132580 | +| policy_gradient_loss | -0.0655 | +| value_loss | 0.000497 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.45e+03 | +| ep_rew_mean | 0.0146 | +| time/ | | +| fps | 309 | +| iterations | 7207 | +| time_elapsed | 23838 | +| total_timesteps | 7379968 | +| train/ | | +| approx_kl | 6.118294 | +| clip_fraction | 0.504 | +| clip_range | 0.2 | +| entropy_loss | -0.377 | +| explained_variance | -1.32 | +| learning_rate | 0.0001 | +| loss | -0.0898 | +| n_updates | 132590 | +| policy_gradient_loss | -0.0621 | +| value_loss | 0.000588 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.44e+03 | +| ep_rew_mean | 0.0137 | +| time/ | | +| fps | 309 | +| iterations | 7208 | +| time_elapsed | 23841 | +| total_timesteps | 7380992 | +| train/ | | +| approx_kl | 2.2562585 | +| clip_fraction | 0.515 | +| clip_range | 0.2 | +| entropy_loss | -0.411 | +| explained_variance | -1.45 | +| learning_rate | 0.0001 | +| loss | -0.106 | +| n_updates | 132600 | +| policy_gradient_loss | -0.0719 | +| value_loss | 0.000541 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.45e+03 | +| ep_rew_mean | 0.0146 | +| time/ | | +| fps | 309 | +| iterations | 7209 | +| time_elapsed | 23845 | +| total_timesteps | 7382016 | +| train/ | | +| approx_kl | 2.5436463 | +| clip_fraction | 0.479 | +| clip_range | 0.2 | +| entropy_loss | -0.401 | +| explained_variance | -4.12 | +| learning_rate | 0.0001 | +| loss | -0.0814 | +| n_updates | 132610 | +| policy_gradient_loss | -0.0651 | +| value_loss | 0.000664 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.45e+03 | +| ep_rew_mean | 0.0146 | +| time/ | | +| fps | 309 | +| iterations | 7210 | +| time_elapsed | 23848 | +| total_timesteps | 7383040 | +| train/ | | +| approx_kl | 1.8098851 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.376 | +| explained_variance | -2.24 | +| learning_rate | 0.0001 | +| loss | -0.0826 | +| n_updates | 132620 | +| policy_gradient_loss | -0.0635 | +| value_loss | 0.000577 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.44e+03 | +| ep_rew_mean | 0.00999 | +| time/ | | +| fps | 309 | +| iterations | 7211 | +| time_elapsed | 23851 | +| total_timesteps | 7384064 | +| train/ | | +| approx_kl | 1.5746967 | +| clip_fraction | 0.435 | +| clip_range | 0.2 | +| entropy_loss | -0.379 | +| explained_variance | -4.5 | +| learning_rate | 0.0001 | +| loss | -0.0431 | +| n_updates | 132630 | +| policy_gradient_loss | -0.0506 | +| value_loss | 0.000256 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.45e+03 | +| ep_rew_mean | 0.0107 | +| time/ | | +| fps | 309 | +| iterations | 7212 | +| time_elapsed | 23854 | +| total_timesteps | 7385088 | +| train/ | | +| approx_kl | 2.2748628 | +| clip_fraction | 0.458 | +| clip_range | 0.2 | +| entropy_loss | -0.403 | +| explained_variance | -0.171 | +| learning_rate | 0.0001 | +| loss | -0.0934 | +| n_updates | 132640 | +| policy_gradient_loss | -0.0575 | +| value_loss | 0.000418 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.45e+03 | +| ep_rew_mean | 0.0107 | +| time/ | | +| fps | 309 | +| iterations | 7213 | +| time_elapsed | 23857 | +| total_timesteps | 7386112 | +| train/ | | +| approx_kl | 2.0586076 | +| clip_fraction | 0.428 | +| clip_range | 0.2 | +| entropy_loss | -0.325 | +| explained_variance | -1.97 | +| learning_rate | 0.0001 | +| loss | -0.0842 | +| n_updates | 132650 | +| policy_gradient_loss | -0.0583 | +| value_loss | 0.000771 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.44e+03 | +| ep_rew_mean | 0.011 | +| time/ | | +| fps | 309 | +| iterations | 7214 | +| time_elapsed | 23861 | +| total_timesteps | 7387136 | +| train/ | | +| approx_kl | 2.0125475 | +| clip_fraction | 0.436 | +| clip_range | 0.2 | +| entropy_loss | -0.32 | +| explained_variance | -12 | +| learning_rate | 0.0001 | +| loss | -0.0856 | +| n_updates | 132660 | +| policy_gradient_loss | -0.0691 | +| value_loss | 0.000469 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.44e+03 | +| ep_rew_mean | 0.0118 | +| time/ | | +| fps | 309 | +| iterations | 7215 | +| time_elapsed | 23864 | +| total_timesteps | 7388160 | +| train/ | | +| approx_kl | 2.1365829 | +| clip_fraction | 0.431 | +| clip_range | 0.2 | +| entropy_loss | -0.353 | +| explained_variance | -1.31 | +| learning_rate | 0.0001 | +| loss | -0.107 | +| n_updates | 132670 | +| policy_gradient_loss | -0.0606 | +| value_loss | 0.00051 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.44e+03 | +| ep_rew_mean | 0.00932 | +| time/ | | +| fps | 309 | +| iterations | 7216 | +| time_elapsed | 23868 | +| total_timesteps | 7389184 | +| train/ | | +| approx_kl | 1.9849086 | +| clip_fraction | 0.431 | +| clip_range | 0.2 | +| entropy_loss | -0.323 | +| explained_variance | -2.01 | +| learning_rate | 0.0001 | +| loss | -0.0908 | +| n_updates | 132680 | +| policy_gradient_loss | -0.0607 | +| value_loss | 0.000518 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.44e+03 | +| ep_rew_mean | 0.00932 | +| time/ | | +| fps | 309 | +| iterations | 7217 | +| time_elapsed | 23871 | +| total_timesteps | 7390208 | +| train/ | | +| approx_kl | 2.5807276 | +| clip_fraction | 0.476 | +| clip_range | 0.2 | +| entropy_loss | -0.375 | +| explained_variance | -5.01 | +| learning_rate | 0.0001 | +| loss | -0.0654 | +| n_updates | 132690 | +| policy_gradient_loss | -0.0671 | +| value_loss | 0.00055 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.44e+03 | +| ep_rew_mean | 0.00804 | +| time/ | | +| fps | 309 | +| iterations | 7218 | +| time_elapsed | 23875 | +| total_timesteps | 7391232 | +| train/ | | +| approx_kl | 2.3607922 | +| clip_fraction | 0.456 | +| clip_range | 0.2 | +| entropy_loss | -0.356 | +| explained_variance | -4.47 | +| learning_rate | 0.0001 | +| loss | -0.082 | +| n_updates | 132700 | +| policy_gradient_loss | -0.0587 | +| value_loss | 0.000372 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.43e+03 | +| ep_rew_mean | 0.0133 | +| time/ | | +| fps | 309 | +| iterations | 7219 | +| time_elapsed | 23878 | +| total_timesteps | 7392256 | +| train/ | | +| approx_kl | 2.2635837 | +| clip_fraction | 0.458 | +| clip_range | 0.2 | +| entropy_loss | -0.383 | +| explained_variance | -0.958 | +| learning_rate | 0.0001 | +| loss | -0.0921 | +| n_updates | 132710 | +| policy_gradient_loss | -0.0563 | +| value_loss | 0.000483 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.43e+03 | +| ep_rew_mean | 0.0133 | +| time/ | | +| fps | 309 | +| iterations | 7220 | +| time_elapsed | 23882 | +| total_timesteps | 7393280 | +| train/ | | +| approx_kl | 2.08741 | +| clip_fraction | 0.466 | +| clip_range | 0.2 | +| entropy_loss | -0.36 | +| explained_variance | -0.695 | +| learning_rate | 0.0001 | +| loss | -0.0883 | +| n_updates | 132720 | +| policy_gradient_loss | -0.0633 | +| value_loss | 0.000826 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.44e+03 | +| ep_rew_mean | 0.0178 | +| time/ | | +| fps | 309 | +| iterations | 7221 | +| time_elapsed | 23885 | +| total_timesteps | 7394304 | +| train/ | | +| approx_kl | 2.3384476 | +| clip_fraction | 0.473 | +| clip_range | 0.2 | +| entropy_loss | -0.387 | +| explained_variance | -0.945 | +| learning_rate | 0.0001 | +| loss | -0.0945 | +| n_updates | 132730 | +| policy_gradient_loss | -0.0722 | +| value_loss | 0.000714 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.44e+03 | +| ep_rew_mean | 0.0178 | +| time/ | | +| fps | 309 | +| iterations | 7222 | +| time_elapsed | 23889 | +| total_timesteps | 7395328 | +| train/ | | +| approx_kl | 1.9530666 | +| clip_fraction | 0.44 | +| clip_range | 0.2 | +| entropy_loss | -0.376 | +| explained_variance | -3.94 | +| learning_rate | 0.0001 | +| loss | -0.0784 | +| n_updates | 132740 | +| policy_gradient_loss | -0.0594 | +| value_loss | 0.000558 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.45e+03 | +| ep_rew_mean | 0.0176 | +| time/ | | +| fps | 309 | +| iterations | 7223 | +| time_elapsed | 23892 | +| total_timesteps | 7396352 | +| train/ | | +| approx_kl | 1.8479544 | +| clip_fraction | 0.429 | +| clip_range | 0.2 | +| entropy_loss | -0.314 | +| explained_variance | -2.18 | +| learning_rate | 0.0001 | +| loss | -0.0882 | +| n_updates | 132750 | +| policy_gradient_loss | -0.0618 | +| value_loss | 0.000674 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.45e+03 | +| ep_rew_mean | 0.0176 | +| time/ | | +| fps | 309 | +| iterations | 7224 | +| time_elapsed | 23895 | +| total_timesteps | 7397376 | +| train/ | | +| approx_kl | 10.401965 | +| clip_fraction | 0.407 | +| clip_range | 0.2 | +| entropy_loss | -0.325 | +| explained_variance | -3.11 | +| learning_rate | 0.0001 | +| loss | -0.0733 | +| n_updates | 132760 | +| policy_gradient_loss | -0.0507 | +| value_loss | 0.000254 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.45e+03 | +| ep_rew_mean | 0.018 | +| time/ | | +| fps | 309 | +| iterations | 7225 | +| time_elapsed | 23898 | +| total_timesteps | 7398400 | +| train/ | | +| approx_kl | 4.2041855 | +| clip_fraction | 0.428 | +| clip_range | 0.2 | +| entropy_loss | -0.328 | +| explained_variance | -1.58 | +| learning_rate | 0.0001 | +| loss | -0.0677 | +| n_updates | 132770 | +| policy_gradient_loss | -0.0631 | +| value_loss | 0.000558 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.46e+03 | +| ep_rew_mean | 0.0186 | +| time/ | | +| fps | 309 | +| iterations | 7226 | +| time_elapsed | 23902 | +| total_timesteps | 7399424 | +| train/ | | +| approx_kl | 1.9414078 | +| clip_fraction | 0.465 | +| clip_range | 0.2 | +| entropy_loss | -0.403 | +| explained_variance | -1.3 | +| learning_rate | 0.0001 | +| loss | -0.0684 | +| n_updates | 132780 | +| policy_gradient_loss | -0.0629 | +| value_loss | 0.000564 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.46e+03 | +| ep_rew_mean | 0.0186 | +| time/ | | +| fps | 309 | +| iterations | 7227 | +| time_elapsed | 23905 | +| total_timesteps | 7400448 | +| train/ | | +| approx_kl | 1.4792769 | +| clip_fraction | 0.453 | +| clip_range | 0.2 | +| entropy_loss | -0.376 | +| explained_variance | -7.22 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 132790 | +| policy_gradient_loss | -0.0617 | +| value_loss | 0.00037 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.45e+03 | +| ep_rew_mean | 0.0158 | +| time/ | | +| fps | 309 | +| iterations | 7228 | +| time_elapsed | 23908 | +| total_timesteps | 7401472 | +| train/ | | +| approx_kl | 1.7139168 | +| clip_fraction | 0.458 | +| clip_range | 0.2 | +| entropy_loss | -0.376 | +| explained_variance | -5.16 | +| learning_rate | 0.0001 | +| loss | -0.0922 | +| n_updates | 132800 | +| policy_gradient_loss | -0.0642 | +| value_loss | 0.000202 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.44e+03 | +| ep_rew_mean | 0.0177 | +| time/ | | +| fps | 309 | +| iterations | 7229 | +| time_elapsed | 23911 | +| total_timesteps | 7402496 | +| train/ | | +| approx_kl | 1.7572656 | +| clip_fraction | 0.427 | +| clip_range | 0.2 | +| entropy_loss | -0.359 | +| explained_variance | -0.175 | +| learning_rate | 0.0001 | +| loss | -0.085 | +| n_updates | 132810 | +| policy_gradient_loss | -0.0549 | +| value_loss | 0.000728 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.44e+03 | +| ep_rew_mean | 0.0177 | +| time/ | | +| fps | 309 | +| iterations | 7230 | +| time_elapsed | 23915 | +| total_timesteps | 7403520 | +| train/ | | +| approx_kl | 2.7351198 | +| clip_fraction | 0.467 | +| clip_range | 0.2 | +| entropy_loss | -0.326 | +| explained_variance | -4.43 | +| learning_rate | 0.0001 | +| loss | -0.0973 | +| n_updates | 132820 | +| policy_gradient_loss | -0.0711 | +| value_loss | 0.000712 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.43e+03 | +| ep_rew_mean | 0.014 | +| time/ | | +| fps | 309 | +| iterations | 7231 | +| time_elapsed | 23918 | +| total_timesteps | 7404544 | +| train/ | | +| approx_kl | 1.763983 | +| clip_fraction | 0.47 | +| clip_range | 0.2 | +| entropy_loss | -0.408 | +| explained_variance | -4.98 | +| learning_rate | 0.0001 | +| loss | -0.112 | +| n_updates | 132830 | +| policy_gradient_loss | -0.058 | +| value_loss | 0.000687 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.43e+03 | +| ep_rew_mean | 0.014 | +| time/ | | +| fps | 309 | +| iterations | 7232 | +| time_elapsed | 23921 | +| total_timesteps | 7405568 | +| train/ | | +| approx_kl | 1.705162 | +| clip_fraction | 0.419 | +| clip_range | 0.2 | +| entropy_loss | -0.317 | +| explained_variance | -0.674 | +| learning_rate | 0.0001 | +| loss | -0.0778 | +| n_updates | 132840 | +| policy_gradient_loss | -0.0525 | +| value_loss | 0.000738 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.44e+03 | +| ep_rew_mean | 0.0156 | +| time/ | | +| fps | 309 | +| iterations | 7233 | +| time_elapsed | 23925 | +| total_timesteps | 7406592 | +| train/ | | +| approx_kl | 1.7533666 | +| clip_fraction | 0.492 | +| clip_range | 0.2 | +| entropy_loss | -0.43 | +| explained_variance | -3.9 | +| learning_rate | 0.0001 | +| loss | -0.0968 | +| n_updates | 132850 | +| policy_gradient_loss | -0.0677 | +| value_loss | 0.000457 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.45e+03 | +| ep_rew_mean | 0.0182 | +| time/ | | +| fps | 309 | +| iterations | 7234 | +| time_elapsed | 23928 | +| total_timesteps | 7407616 | +| train/ | | +| approx_kl | 2.2312937 | +| clip_fraction | 0.46 | +| clip_range | 0.2 | +| entropy_loss | -0.366 | +| explained_variance | -2.2 | +| learning_rate | 0.0001 | +| loss | -0.0811 | +| n_updates | 132860 | +| policy_gradient_loss | -0.0621 | +| value_loss | 0.000482 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.45e+03 | +| ep_rew_mean | 0.0182 | +| time/ | | +| fps | 309 | +| iterations | 7235 | +| time_elapsed | 23931 | +| total_timesteps | 7408640 | +| train/ | | +| approx_kl | 2.2577095 | +| clip_fraction | 0.446 | +| clip_range | 0.2 | +| entropy_loss | -0.387 | +| explained_variance | -1.5 | +| learning_rate | 0.0001 | +| loss | -0.0765 | +| n_updates | 132870 | +| policy_gradient_loss | -0.0607 | +| value_loss | 0.000549 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.45e+03 | +| ep_rew_mean | 0.0182 | +| time/ | | +| fps | 309 | +| iterations | 7236 | +| time_elapsed | 23934 | +| total_timesteps | 7409664 | +| train/ | | +| approx_kl | 2.2558022 | +| clip_fraction | 0.511 | +| clip_range | 0.2 | +| entropy_loss | -0.401 | +| explained_variance | -0.997 | +| learning_rate | 0.0001 | +| loss | -0.0789 | +| n_updates | 132880 | +| policy_gradient_loss | -0.0684 | +| value_loss | 0.000582 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.46e+03 | +| ep_rew_mean | 0.0235 | +| time/ | | +| fps | 309 | +| iterations | 7237 | +| time_elapsed | 23938 | +| total_timesteps | 7410688 | +| train/ | | +| approx_kl | 1.8214417 | +| clip_fraction | 0.465 | +| clip_range | 0.2 | +| entropy_loss | -0.402 | +| explained_variance | -5.66 | +| learning_rate | 0.0001 | +| loss | -0.105 | +| n_updates | 132890 | +| policy_gradient_loss | -0.0653 | +| value_loss | 0.000363 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.46e+03 | +| ep_rew_mean | 0.0249 | +| time/ | | +| fps | 309 | +| iterations | 7238 | +| time_elapsed | 23941 | +| total_timesteps | 7411712 | +| train/ | | +| approx_kl | 2.1381598 | +| clip_fraction | 0.477 | +| clip_range | 0.2 | +| entropy_loss | -0.395 | +| explained_variance | -0.835 | +| learning_rate | 0.0001 | +| loss | -0.081 | +| n_updates | 132900 | +| policy_gradient_loss | -0.0646 | +| value_loss | 0.000772 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.46e+03 | +| ep_rew_mean | 0.0271 | +| time/ | | +| fps | 309 | +| iterations | 7239 | +| time_elapsed | 23944 | +| total_timesteps | 7412736 | +| train/ | | +| approx_kl | 1.9966102 | +| clip_fraction | 0.476 | +| clip_range | 0.2 | +| entropy_loss | -0.388 | +| explained_variance | -3.44 | +| learning_rate | 0.0001 | +| loss | -0.0856 | +| n_updates | 132910 | +| policy_gradient_loss | -0.0667 | +| value_loss | 0.000769 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.46e+03 | +| ep_rew_mean | 0.0271 | +| time/ | | +| fps | 309 | +| iterations | 7240 | +| time_elapsed | 23948 | +| total_timesteps | 7413760 | +| train/ | | +| approx_kl | 2.6184907 | +| clip_fraction | 0.47 | +| clip_range | 0.2 | +| entropy_loss | -0.375 | +| explained_variance | -2.34 | +| learning_rate | 0.0001 | +| loss | -0.105 | +| n_updates | 132920 | +| policy_gradient_loss | -0.0727 | +| value_loss | 0.000491 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.47e+03 | +| ep_rew_mean | 0.0283 | +| time/ | | +| fps | 309 | +| iterations | 7241 | +| time_elapsed | 23951 | +| total_timesteps | 7414784 | +| train/ | | +| approx_kl | 1.6818743 | +| clip_fraction | 0.429 | +| clip_range | 0.2 | +| entropy_loss | -0.343 | +| explained_variance | -3.85 | +| learning_rate | 0.0001 | +| loss | -0.0717 | +| n_updates | 132930 | +| policy_gradient_loss | -0.0621 | +| value_loss | 0.000364 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.47e+03 | +| ep_rew_mean | 0.0283 | +| time/ | | +| fps | 309 | +| iterations | 7242 | +| time_elapsed | 23954 | +| total_timesteps | 7415808 | +| train/ | | +| approx_kl | 1.7243721 | +| clip_fraction | 0.454 | +| clip_range | 0.2 | +| entropy_loss | -0.341 | +| explained_variance | -1.19 | +| learning_rate | 0.0001 | +| loss | -0.0979 | +| n_updates | 132940 | +| policy_gradient_loss | -0.0699 | +| value_loss | 0.000378 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.47e+03 | +| ep_rew_mean | 0.0339 | +| time/ | | +| fps | 309 | +| iterations | 7243 | +| time_elapsed | 23957 | +| total_timesteps | 7416832 | +| train/ | | +| approx_kl | 2.1702664 | +| clip_fraction | 0.431 | +| clip_range | 0.2 | +| entropy_loss | -0.324 | +| explained_variance | -0.736 | +| learning_rate | 0.0001 | +| loss | -0.0867 | +| n_updates | 132950 | +| policy_gradient_loss | -0.0604 | +| value_loss | 0.000758 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.47e+03 | +| ep_rew_mean | 0.0358 | +| time/ | | +| fps | 309 | +| iterations | 7244 | +| time_elapsed | 23960 | +| total_timesteps | 7417856 | +| train/ | | +| approx_kl | 2.3199954 | +| clip_fraction | 0.456 | +| clip_range | 0.2 | +| entropy_loss | -0.344 | +| explained_variance | -2.84 | +| learning_rate | 0.0001 | +| loss | -0.0865 | +| n_updates | 132960 | +| policy_gradient_loss | -0.0653 | +| value_loss | 0.000951 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.47e+03 | +| ep_rew_mean | 0.0378 | +| time/ | | +| fps | 309 | +| iterations | 7245 | +| time_elapsed | 23964 | +| total_timesteps | 7418880 | +| train/ | | +| approx_kl | 2.1327543 | +| clip_fraction | 0.461 | +| clip_range | 0.2 | +| entropy_loss | -0.388 | +| explained_variance | -3.53 | +| learning_rate | 0.0001 | +| loss | -0.0985 | +| n_updates | 132970 | +| policy_gradient_loss | -0.0666 | +| value_loss | 0.000435 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.47e+03 | +| ep_rew_mean | 0.0391 | +| time/ | | +| fps | 309 | +| iterations | 7246 | +| time_elapsed | 23967 | +| total_timesteps | 7419904 | +| train/ | | +| approx_kl | 1.9249992 | +| clip_fraction | 0.448 | +| clip_range | 0.2 | +| entropy_loss | -0.366 | +| explained_variance | -1.56 | +| learning_rate | 0.0001 | +| loss | -0.0858 | +| n_updates | 132980 | +| policy_gradient_loss | -0.0493 | +| value_loss | 0.00049 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.46e+03 | +| ep_rew_mean | 0.036 | +| time/ | | +| fps | 309 | +| iterations | 7247 | +| time_elapsed | 23970 | +| total_timesteps | 7420928 | +| train/ | | +| approx_kl | 1.7996745 | +| clip_fraction | 0.445 | +| clip_range | 0.2 | +| entropy_loss | -0.343 | +| explained_variance | -1.3 | +| learning_rate | 0.0001 | +| loss | -0.0686 | +| n_updates | 132990 | +| policy_gradient_loss | -0.0556 | +| value_loss | 0.000591 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.46e+03 | +| ep_rew_mean | 0.036 | +| time/ | | +| fps | 309 | +| iterations | 7248 | +| time_elapsed | 23973 | +| total_timesteps | 7421952 | +| train/ | | +| approx_kl | 1.5522704 | +| clip_fraction | 0.413 | +| clip_range | 0.2 | +| entropy_loss | -0.314 | +| explained_variance | -1.33 | +| learning_rate | 0.0001 | +| loss | -0.0778 | +| n_updates | 133000 | +| policy_gradient_loss | -0.0579 | +| value_loss | 0.000857 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.48e+03 | +| ep_rew_mean | 0.0369 | +| time/ | | +| fps | 309 | +| iterations | 7249 | +| time_elapsed | 23976 | +| total_timesteps | 7422976 | +| train/ | | +| approx_kl | 1.8155258 | +| clip_fraction | 0.496 | +| clip_range | 0.2 | +| entropy_loss | -0.43 | +| explained_variance | -2.81 | +| learning_rate | 0.0001 | +| loss | -0.113 | +| n_updates | 133010 | +| policy_gradient_loss | -0.0608 | +| value_loss | 0.000595 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.48e+03 | +| ep_rew_mean | 0.0369 | +| time/ | | +| fps | 309 | +| iterations | 7250 | +| time_elapsed | 23979 | +| total_timesteps | 7424000 | +| train/ | | +| approx_kl | 1.7901955 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.402 | +| explained_variance | -4.77 | +| learning_rate | 0.0001 | +| loss | -0.0945 | +| n_updates | 133020 | +| policy_gradient_loss | -0.0669 | +| value_loss | 0.000464 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.47e+03 | +| ep_rew_mean | 0.0327 | +| time/ | | +| fps | 309 | +| iterations | 7251 | +| time_elapsed | 23983 | +| total_timesteps | 7425024 | +| train/ | | +| approx_kl | 1.7353292 | +| clip_fraction | 0.444 | +| clip_range | 0.2 | +| entropy_loss | -0.348 | +| explained_variance | -2.42 | +| learning_rate | 0.0001 | +| loss | -0.095 | +| n_updates | 133030 | +| policy_gradient_loss | -0.065 | +| value_loss | 0.000479 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.48e+03 | +| ep_rew_mean | 0.0333 | +| time/ | | +| fps | 309 | +| iterations | 7252 | +| time_elapsed | 23986 | +| total_timesteps | 7426048 | +| train/ | | +| approx_kl | 2.0487602 | +| clip_fraction | 0.468 | +| clip_range | 0.2 | +| entropy_loss | -0.396 | +| explained_variance | -1.78 | +| learning_rate | 0.0001 | +| loss | -0.1 | +| n_updates | 133040 | +| policy_gradient_loss | -0.0593 | +| value_loss | 0.00068 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.48e+03 | +| ep_rew_mean | 0.0333 | +| time/ | | +| fps | 309 | +| iterations | 7253 | +| time_elapsed | 23989 | +| total_timesteps | 7427072 | +| train/ | | +| approx_kl | 2.4013057 | +| clip_fraction | 0.477 | +| clip_range | 0.2 | +| entropy_loss | -0.367 | +| explained_variance | -3.02 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 133050 | +| policy_gradient_loss | -0.0673 | +| value_loss | 0.000511 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.48e+03 | +| ep_rew_mean | 0.0362 | +| time/ | | +| fps | 309 | +| iterations | 7254 | +| time_elapsed | 23993 | +| total_timesteps | 7428096 | +| train/ | | +| approx_kl | 2.0696938 | +| clip_fraction | 0.482 | +| clip_range | 0.2 | +| entropy_loss | -0.369 | +| explained_variance | -1.94 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 133060 | +| policy_gradient_loss | -0.0719 | +| value_loss | 0.000744 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.48e+03 | +| ep_rew_mean | 0.0276 | +| time/ | | +| fps | 309 | +| iterations | 7255 | +| time_elapsed | 23996 | +| total_timesteps | 7429120 | +| train/ | | +| approx_kl | 2.9993296 | +| clip_fraction | 0.462 | +| clip_range | 0.2 | +| entropy_loss | -0.375 | +| explained_variance | -5.87 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 133070 | +| policy_gradient_loss | -0.0612 | +| value_loss | 0.000412 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.46e+03 | +| ep_rew_mean | 0.0195 | +| time/ | | +| fps | 309 | +| iterations | 7256 | +| time_elapsed | 24000 | +| total_timesteps | 7430144 | +| train/ | | +| approx_kl | 5.7403045 | +| clip_fraction | 0.425 | +| clip_range | 0.2 | +| entropy_loss | -0.357 | +| explained_variance | -0.503 | +| learning_rate | 0.0001 | +| loss | -0.0649 | +| n_updates | 133080 | +| policy_gradient_loss | -0.0572 | +| value_loss | 0.000446 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.46e+03 | +| ep_rew_mean | 0.0195 | +| time/ | | +| fps | 309 | +| iterations | 7257 | +| time_elapsed | 24003 | +| total_timesteps | 7431168 | +| train/ | | +| approx_kl | 1.840759 | +| clip_fraction | 0.432 | +| clip_range | 0.2 | +| entropy_loss | -0.327 | +| explained_variance | -1.8 | +| learning_rate | 0.0001 | +| loss | -0.053 | +| n_updates | 133090 | +| policy_gradient_loss | -0.0561 | +| value_loss | 0.000745 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.46e+03 | +| ep_rew_mean | 0.0195 | +| time/ | | +| fps | 309 | +| iterations | 7258 | +| time_elapsed | 24007 | +| total_timesteps | 7432192 | +| train/ | | +| approx_kl | 2.693088 | +| clip_fraction | 0.509 | +| clip_range | 0.2 | +| entropy_loss | -0.447 | +| explained_variance | -2.26 | +| learning_rate | 0.0001 | +| loss | -0.0851 | +| n_updates | 133100 | +| policy_gradient_loss | -0.071 | +| value_loss | 0.000706 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.47e+03 | +| ep_rew_mean | 0.023 | +| time/ | | +| fps | 309 | +| iterations | 7259 | +| time_elapsed | 24010 | +| total_timesteps | 7433216 | +| train/ | | +| approx_kl | 1.9944835 | +| clip_fraction | 0.452 | +| clip_range | 0.2 | +| entropy_loss | -0.367 | +| explained_variance | -3.72 | +| learning_rate | 0.0001 | +| loss | -0.122 | +| n_updates | 133110 | +| policy_gradient_loss | -0.0649 | +| value_loss | 0.000439 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.48e+03 | +| ep_rew_mean | 0.024 | +| time/ | | +| fps | 309 | +| iterations | 7260 | +| time_elapsed | 24013 | +| total_timesteps | 7434240 | +| train/ | | +| approx_kl | 1.9015248 | +| clip_fraction | 0.458 | +| clip_range | 0.2 | +| entropy_loss | -0.356 | +| explained_variance | -5.24 | +| learning_rate | 0.0001 | +| loss | -0.0982 | +| n_updates | 133120 | +| policy_gradient_loss | -0.0636 | +| value_loss | 0.000425 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.48e+03 | +| ep_rew_mean | 0.0211 | +| time/ | | +| fps | 309 | +| iterations | 7261 | +| time_elapsed | 24016 | +| total_timesteps | 7435264 | +| train/ | | +| approx_kl | 2.115096 | +| clip_fraction | 0.422 | +| clip_range | 0.2 | +| entropy_loss | -0.359 | +| explained_variance | -2.5 | +| learning_rate | 0.0001 | +| loss | -0.0654 | +| n_updates | 133130 | +| policy_gradient_loss | -0.0566 | +| value_loss | 0.000403 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.48e+03 | +| ep_rew_mean | 0.0209 | +| time/ | | +| fps | 309 | +| iterations | 7262 | +| time_elapsed | 24020 | +| total_timesteps | 7436288 | +| train/ | | +| approx_kl | 2.0315366 | +| clip_fraction | 0.474 | +| clip_range | 0.2 | +| entropy_loss | -0.396 | +| explained_variance | -0.879 | +| learning_rate | 0.0001 | +| loss | -0.0876 | +| n_updates | 133140 | +| policy_gradient_loss | -0.0691 | +| value_loss | 0.000444 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.48e+03 | +| ep_rew_mean | 0.0205 | +| time/ | | +| fps | 309 | +| iterations | 7263 | +| time_elapsed | 24023 | +| total_timesteps | 7437312 | +| train/ | | +| approx_kl | 6.3448515 | +| clip_fraction | 0.5 | +| clip_range | 0.2 | +| entropy_loss | -0.423 | +| explained_variance | -4.29 | +| learning_rate | 0.0001 | +| loss | -0.093 | +| n_updates | 133150 | +| policy_gradient_loss | -0.0641 | +| value_loss | 0.000429 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.48e+03 | +| ep_rew_mean | 0.0205 | +| time/ | | +| fps | 309 | +| iterations | 7264 | +| time_elapsed | 24026 | +| total_timesteps | 7438336 | +| train/ | | +| approx_kl | 3.0186806 | +| clip_fraction | 0.435 | +| clip_range | 0.2 | +| entropy_loss | -0.368 | +| explained_variance | -1.52 | +| learning_rate | 0.0001 | +| loss | -0.083 | +| n_updates | 133160 | +| policy_gradient_loss | -0.0634 | +| value_loss | 0.000367 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.48e+03 | +| ep_rew_mean | 0.0246 | +| time/ | | +| fps | 309 | +| iterations | 7265 | +| time_elapsed | 24029 | +| total_timesteps | 7439360 | +| train/ | | +| approx_kl | 2.2533574 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.376 | +| explained_variance | -1.81 | +| learning_rate | 0.0001 | +| loss | -0.0877 | +| n_updates | 133170 | +| policy_gradient_loss | -0.0682 | +| value_loss | 0.000502 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.48e+03 | +| ep_rew_mean | 0.0246 | +| time/ | | +| fps | 309 | +| iterations | 7266 | +| time_elapsed | 24032 | +| total_timesteps | 7440384 | +| train/ | | +| approx_kl | 2.2465425 | +| clip_fraction | 0.478 | +| clip_range | 0.2 | +| entropy_loss | -0.368 | +| explained_variance | -3.31 | +| learning_rate | 0.0001 | +| loss | -0.0588 | +| n_updates | 133180 | +| policy_gradient_loss | -0.0718 | +| value_loss | 0.000407 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.48e+03 | +| ep_rew_mean | 0.0246 | +| time/ | | +| fps | 309 | +| iterations | 7267 | +| time_elapsed | 24036 | +| total_timesteps | 7441408 | +| train/ | | +| approx_kl | 2.0229442 | +| clip_fraction | 0.484 | +| clip_range | 0.2 | +| entropy_loss | -0.406 | +| explained_variance | -1.02 | +| learning_rate | 0.0001 | +| loss | -0.0794 | +| n_updates | 133190 | +| policy_gradient_loss | -0.0684 | +| value_loss | 0.000572 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.5e+03 | +| ep_rew_mean | 0.0267 | +| time/ | | +| fps | 309 | +| iterations | 7268 | +| time_elapsed | 24039 | +| total_timesteps | 7442432 | +| train/ | | +| approx_kl | 1.8620354 | +| clip_fraction | 0.497 | +| clip_range | 0.2 | +| entropy_loss | -0.46 | +| explained_variance | -11.7 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 133200 | +| policy_gradient_loss | -0.0625 | +| value_loss | 0.000269 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.5e+03 | +| ep_rew_mean | 0.0267 | +| time/ | | +| fps | 309 | +| iterations | 7269 | +| time_elapsed | 24042 | +| total_timesteps | 7443456 | +| train/ | | +| approx_kl | 1.8510652 | +| clip_fraction | 0.517 | +| clip_range | 0.2 | +| entropy_loss | -0.489 | +| explained_variance | -2.02 | +| learning_rate | 0.0001 | +| loss | -0.0839 | +| n_updates | 133210 | +| policy_gradient_loss | -0.0631 | +| value_loss | 0.000272 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.5e+03 | +| ep_rew_mean | 0.0267 | +| time/ | | +| fps | 309 | +| iterations | 7270 | +| time_elapsed | 24046 | +| total_timesteps | 7444480 | +| train/ | | +| approx_kl | 2.547858 | +| clip_fraction | 0.532 | +| clip_range | 0.2 | +| entropy_loss | -0.473 | +| explained_variance | -3.06 | +| learning_rate | 0.0001 | +| loss | -0.0847 | +| n_updates | 133220 | +| policy_gradient_loss | -0.0638 | +| value_loss | 0.000274 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.5e+03 | +| ep_rew_mean | 0.0267 | +| time/ | | +| fps | 309 | +| iterations | 7271 | +| time_elapsed | 24049 | +| total_timesteps | 7445504 | +| train/ | | +| approx_kl | 1.7931004 | +| clip_fraction | 0.448 | +| clip_range | 0.2 | +| entropy_loss | -0.387 | +| explained_variance | -2.34 | +| learning_rate | 0.0001 | +| loss | -0.0865 | +| n_updates | 133230 | +| policy_gradient_loss | -0.0536 | +| value_loss | 0.000298 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.5e+03 | +| ep_rew_mean | 0.0267 | +| time/ | | +| fps | 309 | +| iterations | 7272 | +| time_elapsed | 24053 | +| total_timesteps | 7446528 | +| train/ | | +| approx_kl | 1.9201769 | +| clip_fraction | 0.52 | +| clip_range | 0.2 | +| entropy_loss | -0.492 | +| explained_variance | -1.1 | +| learning_rate | 0.0001 | +| loss | -0.0877 | +| n_updates | 133240 | +| policy_gradient_loss | -0.0689 | +| value_loss | 0.00036 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.53e+03 | +| ep_rew_mean | 0.0339 | +| time/ | | +| fps | 309 | +| iterations | 7273 | +| time_elapsed | 24056 | +| total_timesteps | 7447552 | +| train/ | | +| approx_kl | 2.1513777 | +| clip_fraction | 0.496 | +| clip_range | 0.2 | +| entropy_loss | -0.432 | +| explained_variance | -2.29 | +| learning_rate | 0.0001 | +| loss | -0.11 | +| n_updates | 133250 | +| policy_gradient_loss | -0.0707 | +| value_loss | 0.000648 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.53e+03 | +| ep_rew_mean | 0.0353 | +| time/ | | +| fps | 309 | +| iterations | 7274 | +| time_elapsed | 24060 | +| total_timesteps | 7448576 | +| train/ | | +| approx_kl | 1.816794 | +| clip_fraction | 0.484 | +| clip_range | 0.2 | +| entropy_loss | -0.45 | +| explained_variance | -8.41 | +| learning_rate | 0.0001 | +| loss | -0.0932 | +| n_updates | 133260 | +| policy_gradient_loss | -0.0652 | +| value_loss | 0.000705 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.53e+03 | +| ep_rew_mean | 0.036 | +| time/ | | +| fps | 309 | +| iterations | 7275 | +| time_elapsed | 24063 | +| total_timesteps | 7449600 | +| train/ | | +| approx_kl | 4.922769 | +| clip_fraction | 0.459 | +| clip_range | 0.2 | +| entropy_loss | -0.364 | +| explained_variance | -1.23 | +| learning_rate | 0.0001 | +| loss | -0.0929 | +| n_updates | 133270 | +| policy_gradient_loss | -0.065 | +| value_loss | 0.000631 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.53e+03 | +| ep_rew_mean | 0.036 | +| time/ | | +| fps | 309 | +| iterations | 7276 | +| time_elapsed | 24067 | +| total_timesteps | 7450624 | +| train/ | | +| approx_kl | 1.784687 | +| clip_fraction | 0.451 | +| clip_range | 0.2 | +| entropy_loss | -0.357 | +| explained_variance | -5.48 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 133280 | +| policy_gradient_loss | -0.0684 | +| value_loss | 0.000505 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.53e+03 | +| ep_rew_mean | 0.036 | +| time/ | | +| fps | 309 | +| iterations | 7277 | +| time_elapsed | 24070 | +| total_timesteps | 7451648 | +| train/ | | +| approx_kl | 2.2060277 | +| clip_fraction | 0.45 | +| clip_range | 0.2 | +| entropy_loss | -0.382 | +| explained_variance | -1.59 | +| learning_rate | 0.0001 | +| loss | -0.0697 | +| n_updates | 133290 | +| policy_gradient_loss | -0.062 | +| value_loss | 0.000403 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.54e+03 | +| ep_rew_mean | 0.0417 | +| time/ | | +| fps | 309 | +| iterations | 7278 | +| time_elapsed | 24073 | +| total_timesteps | 7452672 | +| train/ | | +| approx_kl | 1.9785564 | +| clip_fraction | 0.461 | +| clip_range | 0.2 | +| entropy_loss | -0.403 | +| explained_variance | -1.56 | +| learning_rate | 0.0001 | +| loss | -0.04 | +| n_updates | 133300 | +| policy_gradient_loss | -0.0496 | +| value_loss | 0.000623 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.54e+03 | +| ep_rew_mean | 0.0392 | +| time/ | | +| fps | 309 | +| iterations | 7279 | +| time_elapsed | 24076 | +| total_timesteps | 7453696 | +| train/ | | +| approx_kl | 2.0009995 | +| clip_fraction | 0.463 | +| clip_range | 0.2 | +| entropy_loss | -0.412 | +| explained_variance | -2.29 | +| learning_rate | 0.0001 | +| loss | -0.105 | +| n_updates | 133310 | +| policy_gradient_loss | -0.0626 | +| value_loss | 0.000381 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.54e+03 | +| ep_rew_mean | 0.0413 | +| time/ | | +| fps | 309 | +| iterations | 7280 | +| time_elapsed | 24079 | +| total_timesteps | 7454720 | +| train/ | | +| approx_kl | 5.9866896 | +| clip_fraction | 0.435 | +| clip_range | 0.2 | +| entropy_loss | -0.339 | +| explained_variance | -2.72 | +| learning_rate | 0.0001 | +| loss | -0.0729 | +| n_updates | 133320 | +| policy_gradient_loss | -0.0675 | +| value_loss | 0.000739 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.54e+03 | +| ep_rew_mean | 0.0413 | +| time/ | | +| fps | 309 | +| iterations | 7281 | +| time_elapsed | 24083 | +| total_timesteps | 7455744 | +| train/ | | +| approx_kl | 1.6383034 | +| clip_fraction | 0.432 | +| clip_range | 0.2 | +| entropy_loss | -0.341 | +| explained_variance | -2.56 | +| learning_rate | 0.0001 | +| loss | -0.0752 | +| n_updates | 133330 | +| policy_gradient_loss | -0.0615 | +| value_loss | 0.00028 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.54e+03 | +| ep_rew_mean | 0.0413 | +| time/ | | +| fps | 309 | +| iterations | 7282 | +| time_elapsed | 24086 | +| total_timesteps | 7456768 | +| train/ | | +| approx_kl | 2.0501742 | +| clip_fraction | 0.44 | +| clip_range | 0.2 | +| entropy_loss | -0.327 | +| explained_variance | -2.82 | +| learning_rate | 0.0001 | +| loss | -0.0874 | +| n_updates | 133340 | +| policy_gradient_loss | -0.0629 | +| value_loss | 0.000433 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.53e+03 | +| ep_rew_mean | 0.0349 | +| time/ | | +| fps | 309 | +| iterations | 7283 | +| time_elapsed | 24089 | +| total_timesteps | 7457792 | +| train/ | | +| approx_kl | 1.8483781 | +| clip_fraction | 0.407 | +| clip_range | 0.2 | +| entropy_loss | -0.343 | +| explained_variance | -1.65 | +| learning_rate | 0.0001 | +| loss | -0.0722 | +| n_updates | 133350 | +| policy_gradient_loss | -0.0532 | +| value_loss | 0.000608 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.54e+03 | +| ep_rew_mean | 0.0361 | +| time/ | | +| fps | 309 | +| iterations | 7284 | +| time_elapsed | 24092 | +| total_timesteps | 7458816 | +| train/ | | +| approx_kl | 1.9035649 | +| clip_fraction | 0.465 | +| clip_range | 0.2 | +| entropy_loss | -0.365 | +| explained_variance | -1.96 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 133360 | +| policy_gradient_loss | -0.0675 | +| value_loss | 0.000589 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.54e+03 | +| ep_rew_mean | 0.0361 | +| time/ | | +| fps | 309 | +| iterations | 7285 | +| time_elapsed | 24095 | +| total_timesteps | 7459840 | +| train/ | | +| approx_kl | 2.0839858 | +| clip_fraction | 0.428 | +| clip_range | 0.2 | +| entropy_loss | -0.358 | +| explained_variance | -2.41 | +| learning_rate | 0.0001 | +| loss | -0.0859 | +| n_updates | 133370 | +| policy_gradient_loss | -0.0623 | +| value_loss | 0.000447 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.55e+03 | +| ep_rew_mean | 0.0366 | +| time/ | | +| fps | 309 | +| iterations | 7286 | +| time_elapsed | 24099 | +| total_timesteps | 7460864 | +| train/ | | +| approx_kl | 1.9042362 | +| clip_fraction | 0.474 | +| clip_range | 0.2 | +| entropy_loss | -0.408 | +| explained_variance | -3.21 | +| learning_rate | 0.0001 | +| loss | -0.0805 | +| n_updates | 133380 | +| policy_gradient_loss | -0.0664 | +| value_loss | 0.000461 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.55e+03 | +| ep_rew_mean | 0.0407 | +| time/ | | +| fps | 309 | +| iterations | 7287 | +| time_elapsed | 24102 | +| total_timesteps | 7461888 | +| train/ | | +| approx_kl | 1.5397563 | +| clip_fraction | 0.489 | +| clip_range | 0.2 | +| entropy_loss | -0.44 | +| explained_variance | -0.954 | +| learning_rate | 0.0001 | +| loss | -0.0745 | +| n_updates | 133390 | +| policy_gradient_loss | -0.0624 | +| value_loss | 0.000763 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.55e+03 | +| ep_rew_mean | 0.0407 | +| time/ | | +| fps | 309 | +| iterations | 7288 | +| time_elapsed | 24105 | +| total_timesteps | 7462912 | +| train/ | | +| approx_kl | 2.039197 | +| clip_fraction | 0.532 | +| clip_range | 0.2 | +| entropy_loss | -0.434 | +| explained_variance | -3.33 | +| learning_rate | 0.0001 | +| loss | -0.0951 | +| n_updates | 133400 | +| policy_gradient_loss | -0.0762 | +| value_loss | 0.000584 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.55e+03 | +| ep_rew_mean | 0.0427 | +| time/ | | +| fps | 309 | +| iterations | 7289 | +| time_elapsed | 24109 | +| total_timesteps | 7463936 | +| train/ | | +| approx_kl | 1.7221342 | +| clip_fraction | 0.457 | +| clip_range | 0.2 | +| entropy_loss | -0.361 | +| explained_variance | -2.65 | +| learning_rate | 0.0001 | +| loss | -0.0774 | +| n_updates | 133410 | +| policy_gradient_loss | -0.0698 | +| value_loss | 0.000674 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.55e+03 | +| ep_rew_mean | 0.0427 | +| time/ | | +| fps | 309 | +| iterations | 7290 | +| time_elapsed | 24113 | +| total_timesteps | 7464960 | +| train/ | | +| approx_kl | 3.8184667 | +| clip_fraction | 0.453 | +| clip_range | 0.2 | +| entropy_loss | -0.4 | +| explained_variance | -3.56 | +| learning_rate | 0.0001 | +| loss | -0.0633 | +| n_updates | 133420 | +| policy_gradient_loss | -0.0536 | +| value_loss | 0.000355 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.56e+03 | +| ep_rew_mean | 0.0453 | +| time/ | | +| fps | 309 | +| iterations | 7291 | +| time_elapsed | 24116 | +| total_timesteps | 7465984 | +| train/ | | +| approx_kl | 1.925082 | +| clip_fraction | 0.412 | +| clip_range | 0.2 | +| entropy_loss | -0.332 | +| explained_variance | -2.89 | +| learning_rate | 0.0001 | +| loss | -0.0969 | +| n_updates | 133430 | +| policy_gradient_loss | -0.0576 | +| value_loss | 0.000557 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.55e+03 | +| ep_rew_mean | 0.0466 | +| time/ | | +| fps | 309 | +| iterations | 7292 | +| time_elapsed | 24120 | +| total_timesteps | 7467008 | +| train/ | | +| approx_kl | 1.9336114 | +| clip_fraction | 0.46 | +| clip_range | 0.2 | +| entropy_loss | -0.379 | +| explained_variance | -1.04 | +| learning_rate | 0.0001 | +| loss | -0.0662 | +| n_updates | 133440 | +| policy_gradient_loss | -0.063 | +| value_loss | 0.000504 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.55e+03 | +| ep_rew_mean | 0.0466 | +| time/ | | +| fps | 309 | +| iterations | 7293 | +| time_elapsed | 24123 | +| total_timesteps | 7468032 | +| train/ | | +| approx_kl | 1.9738512 | +| clip_fraction | 0.416 | +| clip_range | 0.2 | +| entropy_loss | -0.326 | +| explained_variance | -2.74 | +| learning_rate | 0.0001 | +| loss | -0.0982 | +| n_updates | 133450 | +| policy_gradient_loss | -0.069 | +| value_loss | 0.000373 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.56e+03 | +| ep_rew_mean | 0.0481 | +| time/ | | +| fps | 309 | +| iterations | 7294 | +| time_elapsed | 24126 | +| total_timesteps | 7469056 | +| train/ | | +| approx_kl | 1.9585434 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.426 | +| explained_variance | -2.89 | +| learning_rate | 0.0001 | +| loss | -0.099 | +| n_updates | 133460 | +| policy_gradient_loss | -0.0636 | +| value_loss | 0.000414 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.56e+03 | +| ep_rew_mean | 0.0481 | +| time/ | | +| fps | 309 | +| iterations | 7295 | +| time_elapsed | 24130 | +| total_timesteps | 7470080 | +| train/ | | +| approx_kl | 2.1017146 | +| clip_fraction | 0.468 | +| clip_range | 0.2 | +| entropy_loss | -0.363 | +| explained_variance | -1.37 | +| learning_rate | 0.0001 | +| loss | -0.0752 | +| n_updates | 133470 | +| policy_gradient_loss | -0.0678 | +| value_loss | 0.000382 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.57e+03 | +| ep_rew_mean | 0.0507 | +| time/ | | +| fps | 309 | +| iterations | 7296 | +| time_elapsed | 24133 | +| total_timesteps | 7471104 | +| train/ | | +| approx_kl | 3.1730745 | +| clip_fraction | 0.422 | +| clip_range | 0.2 | +| entropy_loss | -0.342 | +| explained_variance | -8.68 | +| learning_rate | 0.0001 | +| loss | -0.0967 | +| n_updates | 133480 | +| policy_gradient_loss | -0.0592 | +| value_loss | 0.000256 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.57e+03 | +| ep_rew_mean | 0.0507 | +| time/ | | +| fps | 309 | +| iterations | 7297 | +| time_elapsed | 24136 | +| total_timesteps | 7472128 | +| train/ | | +| approx_kl | 1.6801555 | +| clip_fraction | 0.42 | +| clip_range | 0.2 | +| entropy_loss | -0.348 | +| explained_variance | -2.23 | +| learning_rate | 0.0001 | +| loss | -0.106 | +| n_updates | 133490 | +| policy_gradient_loss | -0.0617 | +| value_loss | 0.000407 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.57e+03 | +| ep_rew_mean | 0.0507 | +| time/ | | +| fps | 309 | +| iterations | 7298 | +| time_elapsed | 24139 | +| total_timesteps | 7473152 | +| train/ | | +| approx_kl | 4.1818023 | +| clip_fraction | 0.449 | +| clip_range | 0.2 | +| entropy_loss | -0.349 | +| explained_variance | -0.662 | +| learning_rate | 0.0001 | +| loss | -0.0621 | +| n_updates | 133500 | +| policy_gradient_loss | -0.0595 | +| value_loss | 0.00103 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.58e+03 | +| ep_rew_mean | 0.0547 | +| time/ | | +| fps | 309 | +| iterations | 7299 | +| time_elapsed | 24143 | +| total_timesteps | 7474176 | +| train/ | | +| approx_kl | 2.1744027 | +| clip_fraction | 0.492 | +| clip_range | 0.2 | +| entropy_loss | -0.39 | +| explained_variance | -5.22 | +| learning_rate | 0.0001 | +| loss | -0.0719 | +| n_updates | 133510 | +| policy_gradient_loss | -0.0617 | +| value_loss | 0.000459 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | 0.0627 | +| time/ | | +| fps | 309 | +| iterations | 7300 | +| time_elapsed | 24146 | +| total_timesteps | 7475200 | +| train/ | | +| approx_kl | 2.2793865 | +| clip_fraction | 0.49 | +| clip_range | 0.2 | +| entropy_loss | -0.378 | +| explained_variance | -1.09 | +| learning_rate | 0.0001 | +| loss | -0.1 | +| n_updates | 133520 | +| policy_gradient_loss | -0.0676 | +| value_loss | 0.000549 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.58e+03 | +| ep_rew_mean | 0.0635 | +| time/ | | +| fps | 309 | +| iterations | 7301 | +| time_elapsed | 24149 | +| total_timesteps | 7476224 | +| train/ | | +| approx_kl | 1.9185168 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.406 | +| explained_variance | -1.11 | +| learning_rate | 0.0001 | +| loss | -0.054 | +| n_updates | 133530 | +| policy_gradient_loss | -0.066 | +| value_loss | 0.000633 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.57e+03 | +| ep_rew_mean | 0.0597 | +| time/ | | +| fps | 309 | +| iterations | 7302 | +| time_elapsed | 24153 | +| total_timesteps | 7477248 | +| train/ | | +| approx_kl | 2.0409222 | +| clip_fraction | 0.462 | +| clip_range | 0.2 | +| entropy_loss | -0.357 | +| explained_variance | -2.63 | +| learning_rate | 0.0001 | +| loss | -0.0876 | +| n_updates | 133540 | +| policy_gradient_loss | -0.0648 | +| value_loss | 0.000577 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.56e+03 | +| ep_rew_mean | 0.0603 | +| time/ | | +| fps | 309 | +| iterations | 7303 | +| time_elapsed | 24156 | +| total_timesteps | 7478272 | +| train/ | | +| approx_kl | 1.4527994 | +| clip_fraction | 0.458 | +| clip_range | 0.2 | +| entropy_loss | -0.365 | +| explained_variance | -2.57 | +| learning_rate | 0.0001 | +| loss | -0.0573 | +| n_updates | 133550 | +| policy_gradient_loss | -0.0636 | +| value_loss | 0.000384 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.56e+03 | +| ep_rew_mean | 0.0603 | +| time/ | | +| fps | 309 | +| iterations | 7304 | +| time_elapsed | 24159 | +| total_timesteps | 7479296 | +| train/ | | +| approx_kl | 1.9917622 | +| clip_fraction | 0.505 | +| clip_range | 0.2 | +| entropy_loss | -0.448 | +| explained_variance | -1.68 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 133560 | +| policy_gradient_loss | -0.0712 | +| value_loss | 0.000422 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.57e+03 | +| ep_rew_mean | 0.0648 | +| time/ | | +| fps | 309 | +| iterations | 7305 | +| time_elapsed | 24162 | +| total_timesteps | 7480320 | +| train/ | | +| approx_kl | 1.9175608 | +| clip_fraction | 0.453 | +| clip_range | 0.2 | +| entropy_loss | -0.346 | +| explained_variance | -3.78 | +| learning_rate | 0.0001 | +| loss | -0.0844 | +| n_updates | 133570 | +| policy_gradient_loss | -0.0652 | +| value_loss | 0.000482 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.57e+03 | +| ep_rew_mean | 0.0648 | +| time/ | | +| fps | 309 | +| iterations | 7306 | +| time_elapsed | 24166 | +| total_timesteps | 7481344 | +| train/ | | +| approx_kl | 2.208766 | +| clip_fraction | 0.478 | +| clip_range | 0.2 | +| entropy_loss | -0.4 | +| explained_variance | -0.88 | +| learning_rate | 0.0001 | +| loss | -0.0665 | +| n_updates | 133580 | +| policy_gradient_loss | -0.0557 | +| value_loss | 0.00043 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.57e+03 | +| ep_rew_mean | 0.0648 | +| time/ | | +| fps | 309 | +| iterations | 7307 | +| time_elapsed | 24169 | +| total_timesteps | 7482368 | +| train/ | | +| approx_kl | 1.7725842 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.38 | +| explained_variance | -1.87 | +| learning_rate | 0.0001 | +| loss | -0.0931 | +| n_updates | 133590 | +| policy_gradient_loss | -0.0661 | +| value_loss | 0.00042 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.58e+03 | +| ep_rew_mean | 0.0691 | +| time/ | | +| fps | 309 | +| iterations | 7308 | +| time_elapsed | 24173 | +| total_timesteps | 7483392 | +| train/ | | +| approx_kl | 1.7644881 | +| clip_fraction | 0.456 | +| clip_range | 0.2 | +| entropy_loss | -0.381 | +| explained_variance | -2.35 | +| learning_rate | 0.0001 | +| loss | -0.0633 | +| n_updates | 133600 | +| policy_gradient_loss | -0.0625 | +| value_loss | 0.000372 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.57e+03 | +| ep_rew_mean | 0.0721 | +| time/ | | +| fps | 309 | +| iterations | 7309 | +| time_elapsed | 24176 | +| total_timesteps | 7484416 | +| train/ | | +| approx_kl | 2.193049 | +| clip_fraction | 0.477 | +| clip_range | 0.2 | +| entropy_loss | -0.374 | +| explained_variance | -1.11 | +| learning_rate | 0.0001 | +| loss | -0.0658 | +| n_updates | 133610 | +| policy_gradient_loss | -0.0708 | +| value_loss | 0.000485 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.57e+03 | +| ep_rew_mean | 0.0722 | +| time/ | | +| fps | 309 | +| iterations | 7310 | +| time_elapsed | 24180 | +| total_timesteps | 7485440 | +| train/ | | +| approx_kl | 1.6482395 | +| clip_fraction | 0.437 | +| clip_range | 0.2 | +| entropy_loss | -0.359 | +| explained_variance | -3.26 | +| learning_rate | 0.0001 | +| loss | -0.106 | +| n_updates | 133620 | +| policy_gradient_loss | -0.0657 | +| value_loss | 0.000413 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.57e+03 | +| ep_rew_mean | 0.0678 | +| time/ | | +| fps | 309 | +| iterations | 7311 | +| time_elapsed | 24183 | +| total_timesteps | 7486464 | +| train/ | | +| approx_kl | 1.5263386 | +| clip_fraction | 0.433 | +| clip_range | 0.2 | +| entropy_loss | -0.34 | +| explained_variance | -0.722 | +| learning_rate | 0.0001 | +| loss | -0.0917 | +| n_updates | 133630 | +| policy_gradient_loss | -0.0623 | +| value_loss | 0.000446 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.57e+03 | +| ep_rew_mean | 0.0678 | +| time/ | | +| fps | 309 | +| iterations | 7312 | +| time_elapsed | 24186 | +| total_timesteps | 7487488 | +| train/ | | +| approx_kl | 2.1753938 | +| clip_fraction | 0.472 | +| clip_range | 0.2 | +| entropy_loss | -0.404 | +| explained_variance | -1.08 | +| learning_rate | 0.0001 | +| loss | -0.0897 | +| n_updates | 133640 | +| policy_gradient_loss | -0.0641 | +| value_loss | 0.000518 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.57e+03 | +| ep_rew_mean | 0.0678 | +| time/ | | +| fps | 309 | +| iterations | 7313 | +| time_elapsed | 24190 | +| total_timesteps | 7488512 | +| train/ | | +| approx_kl | 2.0991237 | +| clip_fraction | 0.521 | +| clip_range | 0.2 | +| entropy_loss | -0.46 | +| explained_variance | -1.4 | +| learning_rate | 0.0001 | +| loss | -0.117 | +| n_updates | 133650 | +| policy_gradient_loss | -0.0734 | +| value_loss | 0.000511 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | 0.0719 | +| time/ | | +| fps | 309 | +| iterations | 7314 | +| time_elapsed | 24193 | +| total_timesteps | 7489536 | +| train/ | | +| approx_kl | 2.0183735 | +| clip_fraction | 0.488 | +| clip_range | 0.2 | +| entropy_loss | -0.448 | +| explained_variance | -10 | +| learning_rate | 0.0001 | +| loss | -0.106 | +| n_updates | 133660 | +| policy_gradient_loss | -0.0733 | +| value_loss | 0.000343 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | 0.0758 | +| time/ | | +| fps | 309 | +| iterations | 7315 | +| time_elapsed | 24196 | +| total_timesteps | 7490560 | +| train/ | | +| approx_kl | 1.8679547 | +| clip_fraction | 0.488 | +| clip_range | 0.2 | +| entropy_loss | -0.395 | +| explained_variance | -0.515 | +| learning_rate | 0.0001 | +| loss | -0.0691 | +| n_updates | 133670 | +| policy_gradient_loss | -0.0631 | +| value_loss | 0.000711 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | 0.0758 | +| time/ | | +| fps | 309 | +| iterations | 7316 | +| time_elapsed | 24199 | +| total_timesteps | 7491584 | +| train/ | | +| approx_kl | 1.6626266 | +| clip_fraction | 0.454 | +| clip_range | 0.2 | +| entropy_loss | -0.457 | +| explained_variance | -1.64 | +| learning_rate | 0.0001 | +| loss | -0.0725 | +| n_updates | 133680 | +| policy_gradient_loss | -0.0565 | +| value_loss | 0.000403 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | 0.0769 | +| time/ | | +| fps | 309 | +| iterations | 7317 | +| time_elapsed | 24202 | +| total_timesteps | 7492608 | +| train/ | | +| approx_kl | 2.3305845 | +| clip_fraction | 0.477 | +| clip_range | 0.2 | +| entropy_loss | -0.364 | +| explained_variance | -4 | +| learning_rate | 0.0001 | +| loss | -0.0766 | +| n_updates | 133690 | +| policy_gradient_loss | -0.0689 | +| value_loss | 0.000345 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | 0.0795 | +| time/ | | +| fps | 309 | +| iterations | 7318 | +| time_elapsed | 24205 | +| total_timesteps | 7493632 | +| train/ | | +| approx_kl | 1.8786061 | +| clip_fraction | 0.477 | +| clip_range | 0.2 | +| entropy_loss | -0.419 | +| explained_variance | -1 | +| learning_rate | 0.0001 | +| loss | -0.079 | +| n_updates | 133700 | +| policy_gradient_loss | -0.0608 | +| value_loss | 0.000458 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | 0.078 | +| time/ | | +| fps | 309 | +| iterations | 7319 | +| time_elapsed | 24209 | +| total_timesteps | 7494656 | +| train/ | | +| approx_kl | 3.133871 | +| clip_fraction | 0.437 | +| clip_range | 0.2 | +| entropy_loss | -0.351 | +| explained_variance | -2.79 | +| learning_rate | 0.0001 | +| loss | -0.0654 | +| n_updates | 133710 | +| policy_gradient_loss | -0.0564 | +| value_loss | 0.000612 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | 0.078 | +| time/ | | +| fps | 309 | +| iterations | 7320 | +| time_elapsed | 24212 | +| total_timesteps | 7495680 | +| train/ | | +| approx_kl | 2.1186185 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.388 | +| explained_variance | -2.01 | +| learning_rate | 0.0001 | +| loss | -0.0835 | +| n_updates | 133720 | +| policy_gradient_loss | -0.0623 | +| value_loss | 0.000529 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.57e+03 | +| ep_rew_mean | 0.0788 | +| time/ | | +| fps | 309 | +| iterations | 7321 | +| time_elapsed | 24215 | +| total_timesteps | 7496704 | +| train/ | | +| approx_kl | 1.902044 | +| clip_fraction | 0.465 | +| clip_range | 0.2 | +| entropy_loss | -0.348 | +| explained_variance | -1.11 | +| learning_rate | 0.0001 | +| loss | -0.0621 | +| n_updates | 133730 | +| policy_gradient_loss | -0.066 | +| value_loss | 0.000791 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.57e+03 | +| ep_rew_mean | 0.0788 | +| time/ | | +| fps | 309 | +| iterations | 7322 | +| time_elapsed | 24218 | +| total_timesteps | 7497728 | +| train/ | | +| approx_kl | 1.9366748 | +| clip_fraction | 0.426 | +| clip_range | 0.2 | +| entropy_loss | -0.341 | +| explained_variance | -3.03 | +| learning_rate | 0.0001 | +| loss | -0.0956 | +| n_updates | 133740 | +| policy_gradient_loss | -0.0607 | +| value_loss | 0.00045 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.58e+03 | +| ep_rew_mean | 0.0838 | +| time/ | | +| fps | 309 | +| iterations | 7323 | +| time_elapsed | 24222 | +| total_timesteps | 7498752 | +| train/ | | +| approx_kl | 1.5786275 | +| clip_fraction | 0.478 | +| clip_range | 0.2 | +| entropy_loss | -0.404 | +| explained_variance | -2.71 | +| learning_rate | 0.0001 | +| loss | -0.0883 | +| n_updates | 133750 | +| policy_gradient_loss | -0.0667 | +| value_loss | 0.000351 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.56e+03 | +| ep_rew_mean | 0.0876 | +| time/ | | +| fps | 309 | +| iterations | 7324 | +| time_elapsed | 24226 | +| total_timesteps | 7499776 | +| train/ | | +| approx_kl | 2.062067 | +| clip_fraction | 0.455 | +| clip_range | 0.2 | +| entropy_loss | -0.389 | +| explained_variance | -1.39 | +| learning_rate | 0.0001 | +| loss | -0.0645 | +| n_updates | 133760 | +| policy_gradient_loss | -0.0612 | +| value_loss | 0.000538 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.56e+03 | +| ep_rew_mean | 0.0927 | +| time/ | | +| fps | 309 | +| iterations | 7325 | +| time_elapsed | 24229 | +| total_timesteps | 7500800 | +| train/ | | +| approx_kl | 2.0287294 | +| clip_fraction | 0.47 | +| clip_range | 0.2 | +| entropy_loss | -0.407 | +| explained_variance | -0.568 | +| learning_rate | 0.0001 | +| loss | -0.0971 | +| n_updates | 133770 | +| policy_gradient_loss | -0.0678 | +| value_loss | 0.000761 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.56e+03 | +| ep_rew_mean | 0.0927 | +| time/ | | +| fps | 309 | +| iterations | 7326 | +| time_elapsed | 24232 | +| total_timesteps | 7501824 | +| train/ | | +| approx_kl | 2.3169413 | +| clip_fraction | 0.464 | +| clip_range | 0.2 | +| entropy_loss | -0.371 | +| explained_variance | -2.67 | +| learning_rate | 0.0001 | +| loss | -0.0834 | +| n_updates | 133780 | +| policy_gradient_loss | -0.0725 | +| value_loss | 0.000806 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.57e+03 | +| ep_rew_mean | 0.097 | +| time/ | | +| fps | 309 | +| iterations | 7327 | +| time_elapsed | 24236 | +| total_timesteps | 7502848 | +| train/ | | +| approx_kl | 2.230469 | +| clip_fraction | 0.479 | +| clip_range | 0.2 | +| entropy_loss | -0.407 | +| explained_variance | -2.01 | +| learning_rate | 0.0001 | +| loss | -0.0353 | +| n_updates | 133790 | +| policy_gradient_loss | -0.0581 | +| value_loss | 0.000532 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.58e+03 | +| ep_rew_mean | 0.104 | +| time/ | | +| fps | 309 | +| iterations | 7328 | +| time_elapsed | 24240 | +| total_timesteps | 7503872 | +| train/ | | +| approx_kl | 1.9601942 | +| clip_fraction | 0.441 | +| clip_range | 0.2 | +| entropy_loss | -0.344 | +| explained_variance | -1.31 | +| learning_rate | 0.0001 | +| loss | -0.0946 | +| n_updates | 133800 | +| policy_gradient_loss | -0.0599 | +| value_loss | 0.000568 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.58e+03 | +| ep_rew_mean | 0.104 | +| time/ | | +| fps | 309 | +| iterations | 7329 | +| time_elapsed | 24243 | +| total_timesteps | 7504896 | +| train/ | | +| approx_kl | 1.6528401 | +| clip_fraction | 0.442 | +| clip_range | 0.2 | +| entropy_loss | -0.402 | +| explained_variance | -4.71 | +| learning_rate | 0.0001 | +| loss | -0.0854 | +| n_updates | 133810 | +| policy_gradient_loss | -0.0633 | +| value_loss | 0.000412 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.57e+03 | +| ep_rew_mean | 0.106 | +| time/ | | +| fps | 309 | +| iterations | 7330 | +| time_elapsed | 24246 | +| total_timesteps | 7505920 | +| train/ | | +| approx_kl | 2.1740334 | +| clip_fraction | 0.489 | +| clip_range | 0.2 | +| entropy_loss | -0.405 | +| explained_variance | -1.21 | +| learning_rate | 0.0001 | +| loss | -0.0714 | +| n_updates | 133820 | +| policy_gradient_loss | -0.0601 | +| value_loss | 0.00056 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.57e+03 | +| ep_rew_mean | 0.106 | +| time/ | | +| fps | 309 | +| iterations | 7331 | +| time_elapsed | 24250 | +| total_timesteps | 7506944 | +| train/ | | +| approx_kl | 1.8187598 | +| clip_fraction | 0.464 | +| clip_range | 0.2 | +| entropy_loss | -0.402 | +| explained_variance | -2.64 | +| learning_rate | 0.0001 | +| loss | -0.0824 | +| n_updates | 133830 | +| policy_gradient_loss | -0.0614 | +| value_loss | 0.000624 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.57e+03 | +| ep_rew_mean | 0.111 | +| time/ | | +| fps | 309 | +| iterations | 7332 | +| time_elapsed | 24253 | +| total_timesteps | 7507968 | +| train/ | | +| approx_kl | 1.9127214 | +| clip_fraction | 0.455 | +| clip_range | 0.2 | +| entropy_loss | -0.355 | +| explained_variance | -7.41 | +| learning_rate | 0.0001 | +| loss | -0.119 | +| n_updates | 133840 | +| policy_gradient_loss | -0.0679 | +| value_loss | 0.000185 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.57e+03 | +| ep_rew_mean | 0.113 | +| time/ | | +| fps | 309 | +| iterations | 7333 | +| time_elapsed | 24256 | +| total_timesteps | 7508992 | +| train/ | | +| approx_kl | 2.6944945 | +| clip_fraction | 0.412 | +| clip_range | 0.2 | +| entropy_loss | -0.314 | +| explained_variance | -0.651 | +| learning_rate | 0.0001 | +| loss | -0.0795 | +| n_updates | 133850 | +| policy_gradient_loss | -0.0512 | +| value_loss | 0.000476 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.57e+03 | +| ep_rew_mean | 0.113 | +| time/ | | +| fps | 309 | +| iterations | 7334 | +| time_elapsed | 24259 | +| total_timesteps | 7510016 | +| train/ | | +| approx_kl | 2.1457422 | +| clip_fraction | 0.465 | +| clip_range | 0.2 | +| entropy_loss | -0.351 | +| explained_variance | -2.34 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 133860 | +| policy_gradient_loss | -0.069 | +| value_loss | 0.000951 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.58e+03 | +| ep_rew_mean | 0.116 | +| time/ | | +| fps | 309 | +| iterations | 7335 | +| time_elapsed | 24263 | +| total_timesteps | 7511040 | +| train/ | | +| approx_kl | 2.006408 | +| clip_fraction | 0.486 | +| clip_range | 0.2 | +| entropy_loss | -0.385 | +| explained_variance | -1.74 | +| learning_rate | 0.0001 | +| loss | -0.0867 | +| n_updates | 133870 | +| policy_gradient_loss | -0.0679 | +| value_loss | 0.000573 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.57e+03 | +| ep_rew_mean | 0.116 | +| time/ | | +| fps | 309 | +| iterations | 7336 | +| time_elapsed | 24266 | +| total_timesteps | 7512064 | +| train/ | | +| approx_kl | 1.8729773 | +| clip_fraction | 0.474 | +| clip_range | 0.2 | +| entropy_loss | -0.387 | +| explained_variance | -2.26 | +| learning_rate | 0.0001 | +| loss | -0.099 | +| n_updates | 133880 | +| policy_gradient_loss | -0.0684 | +| value_loss | 0.000287 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.57e+03 | +| ep_rew_mean | 0.111 | +| time/ | | +| fps | 309 | +| iterations | 7337 | +| time_elapsed | 24269 | +| total_timesteps | 7513088 | +| train/ | | +| approx_kl | 1.9056573 | +| clip_fraction | 0.507 | +| clip_range | 0.2 | +| entropy_loss | -0.464 | +| explained_variance | -0.386 | +| learning_rate | 0.0001 | +| loss | -0.0973 | +| n_updates | 133890 | +| policy_gradient_loss | -0.0726 | +| value_loss | 0.000658 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.57e+03 | +| ep_rew_mean | 0.111 | +| time/ | | +| fps | 309 | +| iterations | 7338 | +| time_elapsed | 24272 | +| total_timesteps | 7514112 | +| train/ | | +| approx_kl | 1.5541854 | +| clip_fraction | 0.451 | +| clip_range | 0.2 | +| entropy_loss | -0.364 | +| explained_variance | -1.79 | +| learning_rate | 0.0001 | +| loss | -0.0739 | +| n_updates | 133900 | +| policy_gradient_loss | -0.0627 | +| value_loss | 0.000608 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.57e+03 | +| ep_rew_mean | 0.11 | +| time/ | | +| fps | 309 | +| iterations | 7339 | +| time_elapsed | 24275 | +| total_timesteps | 7515136 | +| train/ | | +| approx_kl | 2.0310392 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.418 | +| explained_variance | -3.09 | +| learning_rate | 0.0001 | +| loss | -0.0611 | +| n_updates | 133910 | +| policy_gradient_loss | -0.0662 | +| value_loss | 0.000312 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.58e+03 | +| ep_rew_mean | 0.113 | +| time/ | | +| fps | 309 | +| iterations | 7340 | +| time_elapsed | 24279 | +| total_timesteps | 7516160 | +| train/ | | +| approx_kl | 1.9426906 | +| clip_fraction | 0.453 | +| clip_range | 0.2 | +| entropy_loss | -0.377 | +| explained_variance | -3.88 | +| learning_rate | 0.0001 | +| loss | -0.0848 | +| n_updates | 133920 | +| policy_gradient_loss | -0.0653 | +| value_loss | 0.000419 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.58e+03 | +| ep_rew_mean | 0.113 | +| time/ | | +| fps | 309 | +| iterations | 7341 | +| time_elapsed | 24282 | +| total_timesteps | 7517184 | +| train/ | | +| approx_kl | 1.5190926 | +| clip_fraction | 0.436 | +| clip_range | 0.2 | +| entropy_loss | -0.34 | +| explained_variance | -3.43 | +| learning_rate | 0.0001 | +| loss | -0.0771 | +| n_updates | 133930 | +| policy_gradient_loss | -0.061 | +| value_loss | 0.000587 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.58e+03 | +| ep_rew_mean | 0.114 | +| time/ | | +| fps | 309 | +| iterations | 7342 | +| time_elapsed | 24286 | +| total_timesteps | 7518208 | +| train/ | | +| approx_kl | 1.5882404 | +| clip_fraction | 0.447 | +| clip_range | 0.2 | +| entropy_loss | -0.359 | +| explained_variance | -3 | +| learning_rate | 0.0001 | +| loss | -0.0899 | +| n_updates | 133940 | +| policy_gradient_loss | -0.064 | +| value_loss | 0.000462 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.58e+03 | +| ep_rew_mean | 0.113 | +| time/ | | +| fps | 309 | +| iterations | 7343 | +| time_elapsed | 24289 | +| total_timesteps | 7519232 | +| train/ | | +| approx_kl | 2.9432874 | +| clip_fraction | 0.404 | +| clip_range | 0.2 | +| entropy_loss | -0.324 | +| explained_variance | -2.22 | +| learning_rate | 0.0001 | +| loss | -0.079 | +| n_updates | 133950 | +| policy_gradient_loss | -0.0643 | +| value_loss | 0.000498 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.58e+03 | +| ep_rew_mean | 0.108 | +| time/ | | +| fps | 309 | +| iterations | 7344 | +| time_elapsed | 24292 | +| total_timesteps | 7520256 | +| train/ | | +| approx_kl | 4.637066 | +| clip_fraction | 0.431 | +| clip_range | 0.2 | +| entropy_loss | -0.357 | +| explained_variance | -3.21 | +| learning_rate | 0.0001 | +| loss | -0.117 | +| n_updates | 133960 | +| policy_gradient_loss | -0.0606 | +| value_loss | 0.000438 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.58e+03 | +| ep_rew_mean | 0.108 | +| time/ | | +| fps | 309 | +| iterations | 7345 | +| time_elapsed | 24296 | +| total_timesteps | 7521280 | +| train/ | | +| approx_kl | 1.1913174 | +| clip_fraction | 0.394 | +| clip_range | 0.2 | +| entropy_loss | -0.336 | +| explained_variance | -1.94 | +| learning_rate | 0.0001 | +| loss | -0.0937 | +| n_updates | 133970 | +| policy_gradient_loss | -0.0566 | +| value_loss | 0.000503 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.58e+03 | +| ep_rew_mean | 0.108 | +| time/ | | +| fps | 309 | +| iterations | 7346 | +| time_elapsed | 24299 | +| total_timesteps | 7522304 | +| train/ | | +| approx_kl | 2.4677896 | +| clip_fraction | 0.505 | +| clip_range | 0.2 | +| entropy_loss | -0.382 | +| explained_variance | -2.26 | +| learning_rate | 0.0001 | +| loss | -0.114 | +| n_updates | 133980 | +| policy_gradient_loss | -0.0721 | +| value_loss | 0.00082 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.57e+03 | +| ep_rew_mean | 0.107 | +| time/ | | +| fps | 309 | +| iterations | 7347 | +| time_elapsed | 24302 | +| total_timesteps | 7523328 | +| train/ | | +| approx_kl | 2.6544518 | +| clip_fraction | 0.533 | +| clip_range | 0.2 | +| entropy_loss | -0.545 | +| explained_variance | -7.93 | +| learning_rate | 0.0001 | +| loss | -0.0687 | +| n_updates | 133990 | +| policy_gradient_loss | -0.0522 | +| value_loss | 0.000279 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.57e+03 | +| ep_rew_mean | 0.107 | +| time/ | | +| fps | 309 | +| iterations | 7348 | +| time_elapsed | 24306 | +| total_timesteps | 7524352 | +| train/ | | +| approx_kl | 2.1759715 | +| clip_fraction | 0.424 | +| clip_range | 0.2 | +| entropy_loss | -0.337 | +| explained_variance | -1.48 | +| learning_rate | 0.0001 | +| loss | -0.0715 | +| n_updates | 134000 | +| policy_gradient_loss | -0.0584 | +| value_loss | 0.000564 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.58e+03 | +| ep_rew_mean | 0.112 | +| time/ | | +| fps | 309 | +| iterations | 7349 | +| time_elapsed | 24309 | +| total_timesteps | 7525376 | +| train/ | | +| approx_kl | 2.3475535 | +| clip_fraction | 0.503 | +| clip_range | 0.2 | +| entropy_loss | -0.374 | +| explained_variance | -2.49 | +| learning_rate | 0.0001 | +| loss | -0.0709 | +| n_updates | 134010 | +| policy_gradient_loss | -0.0717 | +| value_loss | 0.000758 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.58e+03 | +| ep_rew_mean | 0.112 | +| time/ | | +| fps | 309 | +| iterations | 7350 | +| time_elapsed | 24312 | +| total_timesteps | 7526400 | +| train/ | | +| approx_kl | 1.6669772 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.465 | +| explained_variance | -2.51 | +| learning_rate | 0.0001 | +| loss | -0.0864 | +| n_updates | 134020 | +| policy_gradient_loss | -0.0629 | +| value_loss | 0.000766 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.58e+03 | +| ep_rew_mean | 0.112 | +| time/ | | +| fps | 309 | +| iterations | 7351 | +| time_elapsed | 24315 | +| total_timesteps | 7527424 | +| train/ | | +| approx_kl | 3.6706958 | +| clip_fraction | 0.498 | +| clip_range | 0.2 | +| entropy_loss | -0.443 | +| explained_variance | -1.48 | +| learning_rate | 0.0001 | +| loss | -0.0914 | +| n_updates | 134030 | +| policy_gradient_loss | -0.061 | +| value_loss | 0.000539 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | 0.119 | +| time/ | | +| fps | 309 | +| iterations | 7352 | +| time_elapsed | 24319 | +| total_timesteps | 7528448 | +| train/ | | +| approx_kl | 2.7625856 | +| clip_fraction | 0.544 | +| clip_range | 0.2 | +| entropy_loss | -0.535 | +| explained_variance | -1.74 | +| learning_rate | 0.0001 | +| loss | -0.112 | +| n_updates | 134040 | +| policy_gradient_loss | -0.0627 | +| value_loss | 0.000357 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.58e+03 | +| ep_rew_mean | 0.113 | +| time/ | | +| fps | 309 | +| iterations | 7353 | +| time_elapsed | 24322 | +| total_timesteps | 7529472 | +| train/ | | +| approx_kl | 2.9406219 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.412 | +| explained_variance | -2.88 | +| learning_rate | 0.0001 | +| loss | -0.0923 | +| n_updates | 134050 | +| policy_gradient_loss | -0.0628 | +| value_loss | 0.000254 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.58e+03 | +| ep_rew_mean | 0.113 | +| time/ | | +| fps | 309 | +| iterations | 7354 | +| time_elapsed | 24325 | +| total_timesteps | 7530496 | +| train/ | | +| approx_kl | 1.9362376 | +| clip_fraction | 0.434 | +| clip_range | 0.2 | +| entropy_loss | -0.327 | +| explained_variance | -1.05 | +| learning_rate | 0.0001 | +| loss | -0.0775 | +| n_updates | 134060 | +| policy_gradient_loss | -0.0651 | +| value_loss | 0.000637 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.58e+03 | +| ep_rew_mean | 0.115 | +| time/ | | +| fps | 309 | +| iterations | 7355 | +| time_elapsed | 24328 | +| total_timesteps | 7531520 | +| train/ | | +| approx_kl | 2.4056783 | +| clip_fraction | 0.473 | +| clip_range | 0.2 | +| entropy_loss | -0.356 | +| explained_variance | -3.29 | +| learning_rate | 0.0001 | +| loss | -0.0641 | +| n_updates | 134070 | +| policy_gradient_loss | -0.0634 | +| value_loss | 0.000607 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.57e+03 | +| ep_rew_mean | 0.11 | +| time/ | | +| fps | 309 | +| iterations | 7356 | +| time_elapsed | 24331 | +| total_timesteps | 7532544 | +| train/ | | +| approx_kl | 2.3484693 | +| clip_fraction | 0.431 | +| clip_range | 0.2 | +| entropy_loss | -0.309 | +| explained_variance | -4.12 | +| learning_rate | 0.0001 | +| loss | -0.076 | +| n_updates | 134080 | +| policy_gradient_loss | -0.0599 | +| value_loss | 0.00054 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.56e+03 | +| ep_rew_mean | 0.112 | +| time/ | | +| fps | 309 | +| iterations | 7357 | +| time_elapsed | 24334 | +| total_timesteps | 7533568 | +| train/ | | +| approx_kl | 1.9967042 | +| clip_fraction | 0.432 | +| clip_range | 0.2 | +| entropy_loss | -0.328 | +| explained_variance | -0.104 | +| learning_rate | 0.0001 | +| loss | -0.091 | +| n_updates | 134090 | +| policy_gradient_loss | -0.0546 | +| value_loss | 0.00072 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.55e+03 | +| ep_rew_mean | 0.117 | +| time/ | | +| fps | 309 | +| iterations | 7358 | +| time_elapsed | 24337 | +| total_timesteps | 7534592 | +| train/ | | +| approx_kl | 2.0133524 | +| clip_fraction | 0.452 | +| clip_range | 0.2 | +| entropy_loss | -0.37 | +| explained_variance | -1.97 | +| learning_rate | 0.0001 | +| loss | -0.0696 | +| n_updates | 134100 | +| policy_gradient_loss | -0.06 | +| value_loss | 0.000842 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.55e+03 | +| ep_rew_mean | 0.117 | +| time/ | | +| fps | 309 | +| iterations | 7359 | +| time_elapsed | 24341 | +| total_timesteps | 7535616 | +| train/ | | +| approx_kl | 1.9748619 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.39 | +| explained_variance | -1.17 | +| learning_rate | 0.0001 | +| loss | -0.0672 | +| n_updates | 134110 | +| policy_gradient_loss | -0.0564 | +| value_loss | 0.000971 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.56e+03 | +| ep_rew_mean | 0.119 | +| time/ | | +| fps | 309 | +| iterations | 7360 | +| time_elapsed | 24344 | +| total_timesteps | 7536640 | +| train/ | | +| approx_kl | 2.8126397 | +| clip_fraction | 0.485 | +| clip_range | 0.2 | +| entropy_loss | -0.352 | +| explained_variance | -2.61 | +| learning_rate | 0.0001 | +| loss | -0.0954 | +| n_updates | 134120 | +| policy_gradient_loss | -0.0607 | +| value_loss | 0.000721 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.56e+03 | +| ep_rew_mean | 0.119 | +| time/ | | +| fps | 309 | +| iterations | 7361 | +| time_elapsed | 24348 | +| total_timesteps | 7537664 | +| train/ | | +| approx_kl | 2.3259761 | +| clip_fraction | 0.489 | +| clip_range | 0.2 | +| entropy_loss | -0.4 | +| explained_variance | -2.39 | +| learning_rate | 0.0001 | +| loss | -0.0971 | +| n_updates | 134130 | +| policy_gradient_loss | -0.0692 | +| value_loss | 0.000404 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.56e+03 | +| ep_rew_mean | 0.119 | +| time/ | | +| fps | 309 | +| iterations | 7362 | +| time_elapsed | 24351 | +| total_timesteps | 7538688 | +| train/ | | +| approx_kl | 1.9747236 | +| clip_fraction | 0.505 | +| clip_range | 0.2 | +| entropy_loss | -0.512 | +| explained_variance | -1.01 | +| learning_rate | 0.0001 | +| loss | -0.0877 | +| n_updates | 134140 | +| policy_gradient_loss | -0.0605 | +| value_loss | 0.000333 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.56e+03 | +| ep_rew_mean | 0.119 | +| time/ | | +| fps | 309 | +| iterations | 7363 | +| time_elapsed | 24355 | +| total_timesteps | 7539712 | +| train/ | | +| approx_kl | 1.9933419 | +| clip_fraction | 0.448 | +| clip_range | 0.2 | +| entropy_loss | -0.337 | +| explained_variance | -6 | +| learning_rate | 0.0001 | +| loss | -0.0784 | +| n_updates | 134150 | +| policy_gradient_loss | -0.063 | +| value_loss | 0.000859 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.57e+03 | +| ep_rew_mean | 0.125 | +| time/ | | +| fps | 309 | +| iterations | 7364 | +| time_elapsed | 24358 | +| total_timesteps | 7540736 | +| train/ | | +| approx_kl | 2.1703763 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.343 | +| explained_variance | -2.39 | +| learning_rate | 0.0001 | +| loss | -0.087 | +| n_updates | 134160 | +| policy_gradient_loss | -0.0675 | +| value_loss | 0.000587 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.57e+03 | +| ep_rew_mean | 0.121 | +| time/ | | +| fps | 309 | +| iterations | 7365 | +| time_elapsed | 24362 | +| total_timesteps | 7541760 | +| train/ | | +| approx_kl | 2.0609906 | +| clip_fraction | 0.476 | +| clip_range | 0.2 | +| entropy_loss | -0.374 | +| explained_variance | -1.52 | +| learning_rate | 0.0001 | +| loss | -0.0829 | +| n_updates | 134170 | +| policy_gradient_loss | -0.0645 | +| value_loss | 0.000625 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.56e+03 | +| ep_rew_mean | 0.119 | +| time/ | | +| fps | 309 | +| iterations | 7366 | +| time_elapsed | 24365 | +| total_timesteps | 7542784 | +| train/ | | +| approx_kl | 1.3212225 | +| clip_fraction | 0.394 | +| clip_range | 0.2 | +| entropy_loss | -0.346 | +| explained_variance | -2.23 | +| learning_rate | 0.0001 | +| loss | -0.0789 | +| n_updates | 134180 | +| policy_gradient_loss | -0.0547 | +| value_loss | 0.000927 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.56e+03 | +| ep_rew_mean | 0.118 | +| time/ | | +| fps | 309 | +| iterations | 7367 | +| time_elapsed | 24369 | +| total_timesteps | 7543808 | +| train/ | | +| approx_kl | 1.9977329 | +| clip_fraction | 0.458 | +| clip_range | 0.2 | +| entropy_loss | -0.368 | +| explained_variance | -1.55 | +| learning_rate | 0.0001 | +| loss | -0.0792 | +| n_updates | 134190 | +| policy_gradient_loss | -0.0661 | +| value_loss | 0.000518 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.56e+03 | +| ep_rew_mean | 0.118 | +| time/ | | +| fps | 309 | +| iterations | 7368 | +| time_elapsed | 24372 | +| total_timesteps | 7544832 | +| train/ | | +| approx_kl | 2.2249174 | +| clip_fraction | 0.464 | +| clip_range | 0.2 | +| entropy_loss | -0.349 | +| explained_variance | -1.61 | +| learning_rate | 0.0001 | +| loss | -0.0522 | +| n_updates | 134200 | +| policy_gradient_loss | -0.064 | +| value_loss | 0.000451 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.56e+03 | +| ep_rew_mean | 0.123 | +| time/ | | +| fps | 309 | +| iterations | 7369 | +| time_elapsed | 24375 | +| total_timesteps | 7545856 | +| train/ | | +| approx_kl | 2.7136354 | +| clip_fraction | 0.496 | +| clip_range | 0.2 | +| entropy_loss | -0.422 | +| explained_variance | -1.91 | +| learning_rate | 0.0001 | +| loss | -0.0814 | +| n_updates | 134210 | +| policy_gradient_loss | -0.0682 | +| value_loss | 0.00073 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.56e+03 | +| ep_rew_mean | 0.127 | +| time/ | | +| fps | 309 | +| iterations | 7370 | +| time_elapsed | 24378 | +| total_timesteps | 7546880 | +| train/ | | +| approx_kl | 2.0991006 | +| clip_fraction | 0.498 | +| clip_range | 0.2 | +| entropy_loss | -0.39 | +| explained_variance | -1.43 | +| learning_rate | 0.0001 | +| loss | -0.098 | +| n_updates | 134220 | +| policy_gradient_loss | -0.0674 | +| value_loss | 0.000625 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.56e+03 | +| ep_rew_mean | 0.127 | +| time/ | | +| fps | 309 | +| iterations | 7371 | +| time_elapsed | 24381 | +| total_timesteps | 7547904 | +| train/ | | +| approx_kl | 1.6960257 | +| clip_fraction | 0.477 | +| clip_range | 0.2 | +| entropy_loss | -0.441 | +| explained_variance | -0.976 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 134230 | +| policy_gradient_loss | -0.0687 | +| value_loss | 0.000715 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.57e+03 | +| ep_rew_mean | 0.124 | +| time/ | | +| fps | 309 | +| iterations | 7372 | +| time_elapsed | 24385 | +| total_timesteps | 7548928 | +| train/ | | +| approx_kl | 1.6659682 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.443 | +| explained_variance | -1.8 | +| learning_rate | 0.0001 | +| loss | -0.0811 | +| n_updates | 134240 | +| policy_gradient_loss | -0.0688 | +| value_loss | 0.000737 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.56e+03 | +| ep_rew_mean | 0.126 | +| time/ | | +| fps | 309 | +| iterations | 7373 | +| time_elapsed | 24388 | +| total_timesteps | 7549952 | +| train/ | | +| approx_kl | 1.4643207 | +| clip_fraction | 0.446 | +| clip_range | 0.2 | +| entropy_loss | -0.388 | +| explained_variance | -0.617 | +| learning_rate | 0.0001 | +| loss | -0.0825 | +| n_updates | 134250 | +| policy_gradient_loss | -0.0619 | +| value_loss | 0.000598 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.56e+03 | +| ep_rew_mean | 0.126 | +| time/ | | +| fps | 309 | +| iterations | 7374 | +| time_elapsed | 24391 | +| total_timesteps | 7550976 | +| train/ | | +| approx_kl | 1.8465245 | +| clip_fraction | 0.454 | +| clip_range | 0.2 | +| entropy_loss | -0.379 | +| explained_variance | -0.209 | +| learning_rate | 0.0001 | +| loss | -0.0803 | +| n_updates | 134260 | +| policy_gradient_loss | -0.0622 | +| value_loss | 0.000761 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.55e+03 | +| ep_rew_mean | 0.129 | +| time/ | | +| fps | 309 | +| iterations | 7375 | +| time_elapsed | 24394 | +| total_timesteps | 7552000 | +| train/ | | +| approx_kl | 1.7038165 | +| clip_fraction | 0.461 | +| clip_range | 0.2 | +| entropy_loss | -0.413 | +| explained_variance | -2.55 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 134270 | +| policy_gradient_loss | -0.0652 | +| value_loss | 0.000471 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.55e+03 | +| ep_rew_mean | 0.132 | +| time/ | | +| fps | 309 | +| iterations | 7376 | +| time_elapsed | 24397 | +| total_timesteps | 7553024 | +| train/ | | +| approx_kl | 2.2472715 | +| clip_fraction | 0.458 | +| clip_range | 0.2 | +| entropy_loss | -0.331 | +| explained_variance | -0.793 | +| learning_rate | 0.0001 | +| loss | -0.0793 | +| n_updates | 134280 | +| policy_gradient_loss | -0.063 | +| value_loss | 0.000722 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.55e+03 | +| ep_rew_mean | 0.132 | +| time/ | | +| fps | 309 | +| iterations | 7377 | +| time_elapsed | 24401 | +| total_timesteps | 7554048 | +| train/ | | +| approx_kl | 2.027193 | +| clip_fraction | 0.465 | +| clip_range | 0.2 | +| entropy_loss | -0.37 | +| explained_variance | -0.944 | +| learning_rate | 0.0001 | +| loss | -0.0745 | +| n_updates | 134290 | +| policy_gradient_loss | -0.0657 | +| value_loss | 0.000802 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.55e+03 | +| ep_rew_mean | 0.138 | +| time/ | | +| fps | 309 | +| iterations | 7378 | +| time_elapsed | 24404 | +| total_timesteps | 7555072 | +| train/ | | +| approx_kl | 2.3946366 | +| clip_fraction | 0.53 | +| clip_range | 0.2 | +| entropy_loss | -0.461 | +| explained_variance | -1.94 | +| learning_rate | 0.0001 | +| loss | -0.0979 | +| n_updates | 134300 | +| policy_gradient_loss | -0.073 | +| value_loss | 0.00043 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.55e+03 | +| ep_rew_mean | 0.138 | +| time/ | | +| fps | 309 | +| iterations | 7379 | +| time_elapsed | 24408 | +| total_timesteps | 7556096 | +| train/ | | +| approx_kl | 2.2836685 | +| clip_fraction | 0.494 | +| clip_range | 0.2 | +| entropy_loss | -0.387 | +| explained_variance | -1.03 | +| learning_rate | 0.0001 | +| loss | -0.0844 | +| n_updates | 134310 | +| policy_gradient_loss | -0.0641 | +| value_loss | 0.000734 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.56e+03 | +| ep_rew_mean | 0.146 | +| time/ | | +| fps | 309 | +| iterations | 7380 | +| time_elapsed | 24411 | +| total_timesteps | 7557120 | +| train/ | | +| approx_kl | 2.185578 | +| clip_fraction | 0.484 | +| clip_range | 0.2 | +| entropy_loss | -0.426 | +| explained_variance | -1.32 | +| learning_rate | 0.0001 | +| loss | -0.0993 | +| n_updates | 134320 | +| policy_gradient_loss | -0.0663 | +| value_loss | 0.000524 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.56e+03 | +| ep_rew_mean | 0.145 | +| time/ | | +| fps | 309 | +| iterations | 7381 | +| time_elapsed | 24414 | +| total_timesteps | 7558144 | +| train/ | | +| approx_kl | 1.92907 | +| clip_fraction | 0.474 | +| clip_range | 0.2 | +| entropy_loss | -0.423 | +| explained_variance | -2.3 | +| learning_rate | 0.0001 | +| loss | -0.0999 | +| n_updates | 134330 | +| policy_gradient_loss | -0.0616 | +| value_loss | 0.000443 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.56e+03 | +| ep_rew_mean | 0.145 | +| time/ | | +| fps | 309 | +| iterations | 7382 | +| time_elapsed | 24418 | +| total_timesteps | 7559168 | +| train/ | | +| approx_kl | 1.9752539 | +| clip_fraction | 0.466 | +| clip_range | 0.2 | +| entropy_loss | -0.368 | +| explained_variance | -1.37 | +| learning_rate | 0.0001 | +| loss | -0.0787 | +| n_updates | 134340 | +| policy_gradient_loss | -0.0645 | +| value_loss | 0.000532 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.56e+03 | +| ep_rew_mean | 0.149 | +| time/ | | +| fps | 309 | +| iterations | 7383 | +| time_elapsed | 24421 | +| total_timesteps | 7560192 | +| train/ | | +| approx_kl | 1.8463134 | +| clip_fraction | 0.472 | +| clip_range | 0.2 | +| entropy_loss | -0.393 | +| explained_variance | -1.56 | +| learning_rate | 0.0001 | +| loss | -0.0675 | +| n_updates | 134350 | +| policy_gradient_loss | -0.0678 | +| value_loss | 0.000536 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.56e+03 | +| ep_rew_mean | 0.149 | +| time/ | | +| fps | 309 | +| iterations | 7384 | +| time_elapsed | 24425 | +| total_timesteps | 7561216 | +| train/ | | +| approx_kl | 1.7274064 | +| clip_fraction | 0.411 | +| clip_range | 0.2 | +| entropy_loss | -0.327 | +| explained_variance | -1.78 | +| learning_rate | 0.0001 | +| loss | -0.0782 | +| n_updates | 134360 | +| policy_gradient_loss | -0.0642 | +| value_loss | 0.000478 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.55e+03 | +| ep_rew_mean | 0.144 | +| time/ | | +| fps | 309 | +| iterations | 7385 | +| time_elapsed | 24428 | +| total_timesteps | 7562240 | +| train/ | | +| approx_kl | 1.5893526 | +| clip_fraction | 0.455 | +| clip_range | 0.2 | +| entropy_loss | -0.362 | +| explained_variance | -8.04 | +| learning_rate | 0.0001 | +| loss | -0.0896 | +| n_updates | 134370 | +| policy_gradient_loss | -0.07 | +| value_loss | 0.000366 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.55e+03 | +| ep_rew_mean | 0.144 | +| time/ | | +| fps | 309 | +| iterations | 7386 | +| time_elapsed | 24432 | +| total_timesteps | 7563264 | +| train/ | | +| approx_kl | 1.8768173 | +| clip_fraction | 0.435 | +| clip_range | 0.2 | +| entropy_loss | -0.378 | +| explained_variance | -1.31 | +| learning_rate | 0.0001 | +| loss | -0.079 | +| n_updates | 134380 | +| policy_gradient_loss | -0.0566 | +| value_loss | 0.000398 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.55e+03 | +| ep_rew_mean | 0.144 | +| time/ | | +| fps | 309 | +| iterations | 7387 | +| time_elapsed | 24435 | +| total_timesteps | 7564288 | +| train/ | | +| approx_kl | 1.7656027 | +| clip_fraction | 0.439 | +| clip_range | 0.2 | +| entropy_loss | -0.334 | +| explained_variance | -0.713 | +| learning_rate | 0.0001 | +| loss | -0.082 | +| n_updates | 134390 | +| policy_gradient_loss | -0.0576 | +| value_loss | 0.000575 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.55e+03 | +| ep_rew_mean | 0.142 | +| time/ | | +| fps | 309 | +| iterations | 7388 | +| time_elapsed | 24438 | +| total_timesteps | 7565312 | +| train/ | | +| approx_kl | 1.96619 | +| clip_fraction | 0.458 | +| clip_range | 0.2 | +| entropy_loss | -0.38 | +| explained_variance | -2.29 | +| learning_rate | 0.0001 | +| loss | -0.0749 | +| n_updates | 134400 | +| policy_gradient_loss | -0.0644 | +| value_loss | 0.000444 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.55e+03 | +| ep_rew_mean | 0.142 | +| time/ | | +| fps | 309 | +| iterations | 7389 | +| time_elapsed | 24441 | +| total_timesteps | 7566336 | +| train/ | | +| approx_kl | 1.802737 | +| clip_fraction | 0.466 | +| clip_range | 0.2 | +| entropy_loss | -0.415 | +| explained_variance | -2.95 | +| learning_rate | 0.0001 | +| loss | -0.0649 | +| n_updates | 134410 | +| policy_gradient_loss | -0.0629 | +| value_loss | 0.000362 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.55e+03 | +| ep_rew_mean | 0.138 | +| time/ | | +| fps | 309 | +| iterations | 7390 | +| time_elapsed | 24444 | +| total_timesteps | 7567360 | +| train/ | | +| approx_kl | 2.1941392 | +| clip_fraction | 0.507 | +| clip_range | 0.2 | +| entropy_loss | -0.422 | +| explained_variance | -1.88 | +| learning_rate | 0.0001 | +| loss | -0.0844 | +| n_updates | 134420 | +| policy_gradient_loss | -0.0679 | +| value_loss | 0.000542 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.55e+03 | +| ep_rew_mean | 0.136 | +| time/ | | +| fps | 309 | +| iterations | 7391 | +| time_elapsed | 24447 | +| total_timesteps | 7568384 | +| train/ | | +| approx_kl | 2.1090777 | +| clip_fraction | 0.444 | +| clip_range | 0.2 | +| entropy_loss | -0.322 | +| explained_variance | -1.69 | +| learning_rate | 0.0001 | +| loss | -0.0848 | +| n_updates | 134430 | +| policy_gradient_loss | -0.0648 | +| value_loss | 0.000734 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.55e+03 | +| ep_rew_mean | 0.134 | +| time/ | | +| fps | 309 | +| iterations | 7392 | +| time_elapsed | 24451 | +| total_timesteps | 7569408 | +| train/ | | +| approx_kl | 1.8818469 | +| clip_fraction | 0.451 | +| clip_range | 0.2 | +| entropy_loss | -0.326 | +| explained_variance | -5.24 | +| learning_rate | 0.0001 | +| loss | -0.0992 | +| n_updates | 134440 | +| policy_gradient_loss | -0.0659 | +| value_loss | 0.000446 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.55e+03 | +| ep_rew_mean | 0.134 | +| time/ | | +| fps | 309 | +| iterations | 7393 | +| time_elapsed | 24454 | +| total_timesteps | 7570432 | +| train/ | | +| approx_kl | 1.8659219 | +| clip_fraction | 0.473 | +| clip_range | 0.2 | +| entropy_loss | -0.422 | +| explained_variance | -1.39 | +| learning_rate | 0.0001 | +| loss | -0.0743 | +| n_updates | 134450 | +| policy_gradient_loss | -0.0634 | +| value_loss | 0.000262 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.55e+03 | +| ep_rew_mean | 0.131 | +| time/ | | +| fps | 309 | +| iterations | 7394 | +| time_elapsed | 24457 | +| total_timesteps | 7571456 | +| train/ | | +| approx_kl | 1.7841073 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.44 | +| explained_variance | -0.738 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 134460 | +| policy_gradient_loss | -0.0669 | +| value_loss | 0.000404 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.55e+03 | +| ep_rew_mean | 0.131 | +| time/ | | +| fps | 309 | +| iterations | 7395 | +| time_elapsed | 24460 | +| total_timesteps | 7572480 | +| train/ | | +| approx_kl | 1.9584492 | +| clip_fraction | 0.501 | +| clip_range | 0.2 | +| entropy_loss | -0.389 | +| explained_variance | -2.74 | +| learning_rate | 0.0001 | +| loss | -0.0941 | +| n_updates | 134470 | +| policy_gradient_loss | -0.0718 | +| value_loss | 0.000526 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.55e+03 | +| ep_rew_mean | 0.133 | +| time/ | | +| fps | 309 | +| iterations | 7396 | +| time_elapsed | 24464 | +| total_timesteps | 7573504 | +| train/ | | +| approx_kl | 2.1177127 | +| clip_fraction | 0.474 | +| clip_range | 0.2 | +| entropy_loss | -0.349 | +| explained_variance | -1.1 | +| learning_rate | 0.0001 | +| loss | -0.0501 | +| n_updates | 134480 | +| policy_gradient_loss | -0.0569 | +| value_loss | 0.000803 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.56e+03 | +| ep_rew_mean | 0.134 | +| time/ | | +| fps | 309 | +| iterations | 7397 | +| time_elapsed | 24467 | +| total_timesteps | 7574528 | +| train/ | | +| approx_kl | 1.8896413 | +| clip_fraction | 0.47 | +| clip_range | 0.2 | +| entropy_loss | -0.422 | +| explained_variance | -10.8 | +| learning_rate | 0.0001 | +| loss | -0.11 | +| n_updates | 134490 | +| policy_gradient_loss | -0.067 | +| value_loss | 0.000429 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.56e+03 | +| ep_rew_mean | 0.134 | +| time/ | | +| fps | 309 | +| iterations | 7398 | +| time_elapsed | 24471 | +| total_timesteps | 7575552 | +| train/ | | +| approx_kl | 1.8903455 | +| clip_fraction | 0.476 | +| clip_range | 0.2 | +| entropy_loss | -0.392 | +| explained_variance | -1.55 | +| learning_rate | 0.0001 | +| loss | -0.0764 | +| n_updates | 134500 | +| policy_gradient_loss | -0.0611 | +| value_loss | 0.000724 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.56e+03 | +| ep_rew_mean | 0.132 | +| time/ | | +| fps | 309 | +| iterations | 7399 | +| time_elapsed | 24474 | +| total_timesteps | 7576576 | +| train/ | | +| approx_kl | 2.098657 | +| clip_fraction | 0.47 | +| clip_range | 0.2 | +| entropy_loss | -0.388 | +| explained_variance | -5.14 | +| learning_rate | 0.0001 | +| loss | -0.0712 | +| n_updates | 134510 | +| policy_gradient_loss | -0.0643 | +| value_loss | 0.000571 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.56e+03 | +| ep_rew_mean | 0.132 | +| time/ | | +| fps | 309 | +| iterations | 7400 | +| time_elapsed | 24478 | +| total_timesteps | 7577600 | +| train/ | | +| approx_kl | 2.1765938 | +| clip_fraction | 0.453 | +| clip_range | 0.2 | +| entropy_loss | -0.389 | +| explained_variance | -1.49 | +| learning_rate | 0.0001 | +| loss | -0.097 | +| n_updates | 134520 | +| policy_gradient_loss | -0.0582 | +| value_loss | 0.000526 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.58e+03 | +| ep_rew_mean | 0.138 | +| time/ | | +| fps | 309 | +| iterations | 7401 | +| time_elapsed | 24481 | +| total_timesteps | 7578624 | +| train/ | | +| approx_kl | 2.2632346 | +| clip_fraction | 0.522 | +| clip_range | 0.2 | +| entropy_loss | -0.485 | +| explained_variance | -0.879 | +| learning_rate | 0.0001 | +| loss | -0.0814 | +| n_updates | 134530 | +| policy_gradient_loss | -0.0659 | +| value_loss | 0.00051 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.58e+03 | +| ep_rew_mean | 0.138 | +| time/ | | +| fps | 309 | +| iterations | 7402 | +| time_elapsed | 24485 | +| total_timesteps | 7579648 | +| train/ | | +| approx_kl | 2.0366685 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.405 | +| explained_variance | -12.7 | +| learning_rate | 0.0001 | +| loss | -0.0899 | +| n_updates | 134540 | +| policy_gradient_loss | -0.0691 | +| value_loss | 0.000293 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.58e+03 | +| ep_rew_mean | 0.138 | +| time/ | | +| fps | 309 | +| iterations | 7403 | +| time_elapsed | 24488 | +| total_timesteps | 7580672 | +| train/ | | +| approx_kl | 2.0454245 | +| clip_fraction | 0.456 | +| clip_range | 0.2 | +| entropy_loss | -0.389 | +| explained_variance | -0.683 | +| learning_rate | 0.0001 | +| loss | -0.0666 | +| n_updates | 134550 | +| policy_gradient_loss | -0.0609 | +| value_loss | 0.00042 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.58e+03 | +| ep_rew_mean | 0.138 | +| time/ | | +| fps | 309 | +| iterations | 7404 | +| time_elapsed | 24492 | +| total_timesteps | 7581696 | +| train/ | | +| approx_kl | 1.9279456 | +| clip_fraction | 0.468 | +| clip_range | 0.2 | +| entropy_loss | -0.382 | +| explained_variance | -2.86 | +| learning_rate | 0.0001 | +| loss | -0.105 | +| n_updates | 134560 | +| policy_gradient_loss | -0.0632 | +| value_loss | 0.000465 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.58e+03 | +| ep_rew_mean | 0.141 | +| time/ | | +| fps | 309 | +| iterations | 7405 | +| time_elapsed | 24495 | +| total_timesteps | 7582720 | +| train/ | | +| approx_kl | 1.847574 | +| clip_fraction | 0.484 | +| clip_range | 0.2 | +| entropy_loss | -0.415 | +| explained_variance | -3.57 | +| learning_rate | 0.0001 | +| loss | -0.0822 | +| n_updates | 134570 | +| policy_gradient_loss | -0.0641 | +| value_loss | 0.000354 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.58e+03 | +| ep_rew_mean | 0.141 | +| time/ | | +| fps | 309 | +| iterations | 7406 | +| time_elapsed | 24498 | +| total_timesteps | 7583744 | +| train/ | | +| approx_kl | 2.099742 | +| clip_fraction | 0.464 | +| clip_range | 0.2 | +| entropy_loss | -0.37 | +| explained_variance | -1.1 | +| learning_rate | 0.0001 | +| loss | -0.0993 | +| n_updates | 134580 | +| policy_gradient_loss | -0.0678 | +| value_loss | 0.000572 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | 0.144 | +| time/ | | +| fps | 309 | +| iterations | 7407 | +| time_elapsed | 24501 | +| total_timesteps | 7584768 | +| train/ | | +| approx_kl | 2.0971425 | +| clip_fraction | 0.515 | +| clip_range | 0.2 | +| entropy_loss | -0.441 | +| explained_variance | -1.82 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 134590 | +| policy_gradient_loss | -0.0733 | +| value_loss | 0.000511 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.58e+03 | +| ep_rew_mean | 0.137 | +| time/ | | +| fps | 309 | +| iterations | 7408 | +| time_elapsed | 24504 | +| total_timesteps | 7585792 | +| train/ | | +| approx_kl | 2.1817145 | +| clip_fraction | 0.482 | +| clip_range | 0.2 | +| entropy_loss | -0.395 | +| explained_variance | -2.37 | +| learning_rate | 0.0001 | +| loss | 0.11 | +| n_updates | 134600 | +| policy_gradient_loss | -0.0658 | +| value_loss | 0.000434 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.58e+03 | +| ep_rew_mean | 0.137 | +| time/ | | +| fps | 309 | +| iterations | 7409 | +| time_elapsed | 24508 | +| total_timesteps | 7586816 | +| train/ | | +| approx_kl | 8.516734 | +| clip_fraction | 0.449 | +| clip_range | 0.2 | +| entropy_loss | -0.365 | +| explained_variance | -1.93 | +| learning_rate | 0.0001 | +| loss | -0.0621 | +| n_updates | 134610 | +| policy_gradient_loss | -0.0507 | +| value_loss | 0.000515 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.58e+03 | +| ep_rew_mean | 0.144 | +| time/ | | +| fps | 309 | +| iterations | 7410 | +| time_elapsed | 24511 | +| total_timesteps | 7587840 | +| train/ | | +| approx_kl | 2.1185527 | +| clip_fraction | 0.469 | +| clip_range | 0.2 | +| entropy_loss | -0.351 | +| explained_variance | -1.52 | +| learning_rate | 0.0001 | +| loss | -0.0896 | +| n_updates | 134620 | +| policy_gradient_loss | -0.0599 | +| value_loss | 0.000506 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | 0.145 | +| time/ | | +| fps | 309 | +| iterations | 7411 | +| time_elapsed | 24514 | +| total_timesteps | 7588864 | +| train/ | | +| approx_kl | 1.9057577 | +| clip_fraction | 0.434 | +| clip_range | 0.2 | +| entropy_loss | -0.325 | +| explained_variance | -4.63 | +| learning_rate | 0.0001 | +| loss | -0.0615 | +| n_updates | 134630 | +| policy_gradient_loss | -0.0563 | +| value_loss | 0.000488 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | 0.144 | +| time/ | | +| fps | 309 | +| iterations | 7412 | +| time_elapsed | 24517 | +| total_timesteps | 7589888 | +| train/ | | +| approx_kl | 1.9215672 | +| clip_fraction | 0.454 | +| clip_range | 0.2 | +| entropy_loss | -0.339 | +| explained_variance | -3.08 | +| learning_rate | 0.0001 | +| loss | -0.0783 | +| n_updates | 134640 | +| policy_gradient_loss | -0.0646 | +| value_loss | 0.000472 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | 0.144 | +| time/ | | +| fps | 309 | +| iterations | 7413 | +| time_elapsed | 24521 | +| total_timesteps | 7590912 | +| train/ | | +| approx_kl | 1.6244545 | +| clip_fraction | 0.451 | +| clip_range | 0.2 | +| entropy_loss | -0.406 | +| explained_variance | -1.55 | +| learning_rate | 0.0001 | +| loss | -0.0517 | +| n_updates | 134650 | +| policy_gradient_loss | -0.0627 | +| value_loss | 0.000206 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | 0.145 | +| time/ | | +| fps | 309 | +| iterations | 7414 | +| time_elapsed | 24524 | +| total_timesteps | 7591936 | +| train/ | | +| approx_kl | 2.0837636 | +| clip_fraction | 0.506 | +| clip_range | 0.2 | +| entropy_loss | -0.423 | +| explained_variance | -0.67 | +| learning_rate | 0.0001 | +| loss | -0.0934 | +| n_updates | 134660 | +| policy_gradient_loss | -0.0705 | +| value_loss | 0.000415 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | 0.145 | +| time/ | | +| fps | 309 | +| iterations | 7415 | +| time_elapsed | 24528 | +| total_timesteps | 7592960 | +| train/ | | +| approx_kl | 2.0441012 | +| clip_fraction | 0.495 | +| clip_range | 0.2 | +| entropy_loss | -0.385 | +| explained_variance | -1.04 | +| learning_rate | 0.0001 | +| loss | -0.0882 | +| n_updates | 134670 | +| policy_gradient_loss | -0.0667 | +| value_loss | 0.00114 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | 0.152 | +| time/ | | +| fps | 309 | +| iterations | 7416 | +| time_elapsed | 24531 | +| total_timesteps | 7593984 | +| train/ | | +| approx_kl | 2.1136432 | +| clip_fraction | 0.526 | +| clip_range | 0.2 | +| entropy_loss | -0.491 | +| explained_variance | -2.91 | +| learning_rate | 0.0001 | +| loss | -0.111 | +| n_updates | 134680 | +| policy_gradient_loss | -0.0715 | +| value_loss | 0.00072 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | 0.152 | +| time/ | | +| fps | 309 | +| iterations | 7417 | +| time_elapsed | 24535 | +| total_timesteps | 7595008 | +| train/ | | +| approx_kl | 4.430468 | +| clip_fraction | 0.529 | +| clip_range | 0.2 | +| entropy_loss | -0.412 | +| explained_variance | -2.91 | +| learning_rate | 0.0001 | +| loss | -0.0869 | +| n_updates | 134690 | +| policy_gradient_loss | -0.0723 | +| value_loss | 0.000659 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | 0.158 | +| time/ | | +| fps | 309 | +| iterations | 7418 | +| time_elapsed | 24538 | +| total_timesteps | 7596032 | +| train/ | | +| approx_kl | 2.1209464 | +| clip_fraction | 0.513 | +| clip_range | 0.2 | +| entropy_loss | -0.417 | +| explained_variance | -2.89 | +| learning_rate | 0.0001 | +| loss | -0.109 | +| n_updates | 134700 | +| policy_gradient_loss | -0.0701 | +| value_loss | 0.00052 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | 0.158 | +| time/ | | +| fps | 309 | +| iterations | 7419 | +| time_elapsed | 24541 | +| total_timesteps | 7597056 | +| train/ | | +| approx_kl | 2.4557955 | +| clip_fraction | 0.53 | +| clip_range | 0.2 | +| entropy_loss | -0.427 | +| explained_variance | -0.884 | +| learning_rate | 0.0001 | +| loss | -0.0946 | +| n_updates | 134710 | +| policy_gradient_loss | -0.0706 | +| value_loss | 0.000602 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.61e+03 | +| ep_rew_mean | 0.163 | +| time/ | | +| fps | 309 | +| iterations | 7420 | +| time_elapsed | 24545 | +| total_timesteps | 7598080 | +| train/ | | +| approx_kl | 2.3514488 | +| clip_fraction | 0.504 | +| clip_range | 0.2 | +| entropy_loss | -0.436 | +| explained_variance | -3.02 | +| learning_rate | 0.0001 | +| loss | -0.0737 | +| n_updates | 134720 | +| policy_gradient_loss | -0.0701 | +| value_loss | 0.000544 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.61e+03 | +| ep_rew_mean | 0.166 | +| time/ | | +| fps | 309 | +| iterations | 7421 | +| time_elapsed | 24548 | +| total_timesteps | 7599104 | +| train/ | | +| approx_kl | 1.8614486 | +| clip_fraction | 0.445 | +| clip_range | 0.2 | +| entropy_loss | -0.337 | +| explained_variance | -1.11 | +| learning_rate | 0.0001 | +| loss | -0.0612 | +| n_updates | 134730 | +| policy_gradient_loss | -0.0667 | +| value_loss | 0.000898 | +--------------------------------------- + +Current state: Champion.Level8.RyuVsBlanka +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.61e+03 | +| ep_rew_mean | 0.164 | +| time/ | | +| fps | 309 | +| iterations | 7422 | +| time_elapsed | 24552 | +| total_timesteps | 7600128 | +| train/ | | +| approx_kl | 1.7897938 | +| clip_fraction | 0.489 | +| clip_range | 0.2 | +| entropy_loss | -0.418 | +| explained_variance | -4.98 | +| learning_rate | 0.0001 | +| loss | -0.108 | +| n_updates | 134740 | +| policy_gradient_loss | -0.0668 | +| value_loss | 0.000384 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.61e+03 | +| ep_rew_mean | 0.164 | +| time/ | | +| fps | 309 | +| iterations | 7423 | +| time_elapsed | 24555 | +| total_timesteps | 7601152 | +| train/ | | +| approx_kl | 3.7035403 | +| clip_fraction | 0.49 | +| clip_range | 0.2 | +| entropy_loss | -0.381 | +| explained_variance | -1.11 | +| learning_rate | 0.0001 | +| loss | -0.106 | +| n_updates | 134750 | +| policy_gradient_loss | -0.0704 | +| value_loss | 0.000508 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | 0.165 | +| time/ | | +| fps | 309 | +| iterations | 7424 | +| time_elapsed | 24558 | +| total_timesteps | 7602176 | +| train/ | | +| approx_kl | 2.1661792 | +| clip_fraction | 0.478 | +| clip_range | 0.2 | +| entropy_loss | -0.348 | +| explained_variance | -3.61 | +| learning_rate | 0.0001 | +| loss | -0.0864 | +| n_updates | 134760 | +| policy_gradient_loss | -0.0705 | +| value_loss | 0.000474 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | 0.163 | +| time/ | | +| fps | 309 | +| iterations | 7425 | +| time_elapsed | 24561 | +| total_timesteps | 7603200 | +| train/ | | +| approx_kl | 2.4331732 | +| clip_fraction | 0.469 | +| clip_range | 0.2 | +| entropy_loss | -0.344 | +| explained_variance | -0.916 | +| learning_rate | 0.0001 | +| loss | -0.0902 | +| n_updates | 134770 | +| policy_gradient_loss | -0.0708 | +| value_loss | 0.000501 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | 0.163 | +| time/ | | +| fps | 309 | +| iterations | 7426 | +| time_elapsed | 24564 | +| total_timesteps | 7604224 | +| train/ | | +| approx_kl | 2.4345703 | +| clip_fraction | 0.488 | +| clip_range | 0.2 | +| entropy_loss | -0.393 | +| explained_variance | -0.884 | +| learning_rate | 0.0001 | +| loss | -0.0836 | +| n_updates | 134780 | +| policy_gradient_loss | -0.0661 | +| value_loss | 0.000477 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.57e+03 | +| ep_rew_mean | 0.164 | +| time/ | | +| fps | 309 | +| iterations | 7427 | +| time_elapsed | 24568 | +| total_timesteps | 7605248 | +| train/ | | +| approx_kl | 2.3545215 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.37 | +| explained_variance | -1.54 | +| learning_rate | 0.0001 | +| loss | -0.0933 | +| n_updates | 134790 | +| policy_gradient_loss | -0.0693 | +| value_loss | 0.000663 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.58e+03 | +| ep_rew_mean | 0.169 | +| time/ | | +| fps | 309 | +| iterations | 7428 | +| time_elapsed | 24571 | +| total_timesteps | 7606272 | +| train/ | | +| approx_kl | 7.0427713 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.324 | +| explained_variance | -2.93 | +| learning_rate | 0.0001 | +| loss | -0.096 | +| n_updates | 134800 | +| policy_gradient_loss | -0.0724 | +| value_loss | 0.000574 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.58e+03 | +| ep_rew_mean | 0.169 | +| time/ | | +| fps | 309 | +| iterations | 7429 | +| time_elapsed | 24574 | +| total_timesteps | 7607296 | +| train/ | | +| approx_kl | 3.3263505 | +| clip_fraction | 0.509 | +| clip_range | 0.2 | +| entropy_loss | -0.407 | +| explained_variance | -0.868 | +| learning_rate | 0.0001 | +| loss | -0.069 | +| n_updates | 134810 | +| policy_gradient_loss | -0.0669 | +| value_loss | 0.00101 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.58e+03 | +| ep_rew_mean | 0.169 | +| time/ | | +| fps | 309 | +| iterations | 7430 | +| time_elapsed | 24577 | +| total_timesteps | 7608320 | +| train/ | | +| approx_kl | 2.5663762 | +| clip_fraction | 0.494 | +| clip_range | 0.2 | +| entropy_loss | -0.332 | +| explained_variance | -4.46 | +| learning_rate | 0.0001 | +| loss | -0.0871 | +| n_updates | 134820 | +| policy_gradient_loss | -0.0692 | +| value_loss | 0.000588 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | 0.171 | +| time/ | | +| fps | 309 | +| iterations | 7431 | +| time_elapsed | 24580 | +| total_timesteps | 7609344 | +| train/ | | +| approx_kl | 2.5767689 | +| clip_fraction | 0.49 | +| clip_range | 0.2 | +| entropy_loss | -0.388 | +| explained_variance | -5.21 | +| learning_rate | 0.0001 | +| loss | -0.0952 | +| n_updates | 134830 | +| policy_gradient_loss | -0.0729 | +| value_loss | 0.000358 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.58e+03 | +| ep_rew_mean | 0.163 | +| time/ | | +| fps | 309 | +| iterations | 7432 | +| time_elapsed | 24584 | +| total_timesteps | 7610368 | +| train/ | | +| approx_kl | 2.647725 | +| clip_fraction | 0.47 | +| clip_range | 0.2 | +| entropy_loss | -0.321 | +| explained_variance | -1.71 | +| learning_rate | 0.0001 | +| loss | -0.0774 | +| n_updates | 134840 | +| policy_gradient_loss | -0.0714 | +| value_loss | 0.000674 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.58e+03 | +| ep_rew_mean | 0.163 | +| time/ | | +| fps | 309 | +| iterations | 7433 | +| time_elapsed | 24587 | +| total_timesteps | 7611392 | +| train/ | | +| approx_kl | 1.7362711 | +| clip_fraction | 0.445 | +| clip_range | 0.2 | +| entropy_loss | -0.366 | +| explained_variance | -1.11 | +| learning_rate | 0.0001 | +| loss | -0.0642 | +| n_updates | 134850 | +| policy_gradient_loss | -0.0428 | +| value_loss | 0.000483 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.58e+03 | +| ep_rew_mean | 0.163 | +| time/ | | +| fps | 309 | +| iterations | 7434 | +| time_elapsed | 24591 | +| total_timesteps | 7612416 | +| train/ | | +| approx_kl | 6.0905676 | +| clip_fraction | 0.478 | +| clip_range | 0.2 | +| entropy_loss | -0.323 | +| explained_variance | -10.2 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 134860 | +| policy_gradient_loss | -0.0759 | +| value_loss | 0.000527 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | 0.166 | +| time/ | | +| fps | 309 | +| iterations | 7435 | +| time_elapsed | 24595 | +| total_timesteps | 7613440 | +| train/ | | +| approx_kl | 6.26148 | +| clip_fraction | 0.482 | +| clip_range | 0.2 | +| entropy_loss | -0.352 | +| explained_variance | -1.02 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 134870 | +| policy_gradient_loss | -0.0668 | +| value_loss | 0.000659 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | 0.166 | +| time/ | | +| fps | 309 | +| iterations | 7436 | +| time_elapsed | 24598 | +| total_timesteps | 7614464 | +| train/ | | +| approx_kl | 1.9384651 | +| clip_fraction | 0.425 | +| clip_range | 0.2 | +| entropy_loss | -0.31 | +| explained_variance | -1.97 | +| learning_rate | 0.0001 | +| loss | -0.0899 | +| n_updates | 134880 | +| policy_gradient_loss | -0.0642 | +| value_loss | 0.000707 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | 0.165 | +| time/ | | +| fps | 309 | +| iterations | 7437 | +| time_elapsed | 24602 | +| total_timesteps | 7615488 | +| train/ | | +| approx_kl | 2.5482974 | +| clip_fraction | 0.474 | +| clip_range | 0.2 | +| entropy_loss | -0.318 | +| explained_variance | -2.22 | +| learning_rate | 0.0001 | +| loss | -0.0919 | +| n_updates | 134890 | +| policy_gradient_loss | -0.0651 | +| value_loss | 0.000732 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | 0.165 | +| time/ | | +| fps | 309 | +| iterations | 7438 | +| time_elapsed | 24605 | +| total_timesteps | 7616512 | +| train/ | | +| approx_kl | 2.7492754 | +| clip_fraction | 0.476 | +| clip_range | 0.2 | +| entropy_loss | -0.374 | +| explained_variance | -2.47 | +| learning_rate | 0.0001 | +| loss | -0.082 | +| n_updates | 134900 | +| policy_gradient_loss | -0.0606 | +| value_loss | 0.000559 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | 0.17 | +| time/ | | +| fps | 309 | +| iterations | 7439 | +| time_elapsed | 24608 | +| total_timesteps | 7617536 | +| train/ | | +| approx_kl | 2.4391994 | +| clip_fraction | 0.479 | +| clip_range | 0.2 | +| entropy_loss | -0.347 | +| explained_variance | -1.65 | +| learning_rate | 0.0001 | +| loss | -0.0993 | +| n_updates | 134910 | +| policy_gradient_loss | -0.0681 | +| value_loss | 0.000564 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | 0.174 | +| time/ | | +| fps | 309 | +| iterations | 7440 | +| time_elapsed | 24612 | +| total_timesteps | 7618560 | +| train/ | | +| approx_kl | 2.70942 | +| clip_fraction | 0.47 | +| clip_range | 0.2 | +| entropy_loss | -0.34 | +| explained_variance | -12.4 | +| learning_rate | 0.0001 | +| loss | -0.0929 | +| n_updates | 134920 | +| policy_gradient_loss | -0.0704 | +| value_loss | 0.000475 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | 0.174 | +| time/ | | +| fps | 309 | +| iterations | 7441 | +| time_elapsed | 24615 | +| total_timesteps | 7619584 | +| train/ | | +| approx_kl | 2.5370123 | +| clip_fraction | 0.5 | +| clip_range | 0.2 | +| entropy_loss | -0.359 | +| explained_variance | -1.07 | +| learning_rate | 0.0001 | +| loss | -0.0945 | +| n_updates | 134930 | +| policy_gradient_loss | -0.069 | +| value_loss | 0.000512 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | 0.177 | +| time/ | | +| fps | 309 | +| iterations | 7442 | +| time_elapsed | 24618 | +| total_timesteps | 7620608 | +| train/ | | +| approx_kl | 2.1677117 | +| clip_fraction | 0.464 | +| clip_range | 0.2 | +| entropy_loss | -0.347 | +| explained_variance | -2 | +| learning_rate | 0.0001 | +| loss | -0.0725 | +| n_updates | 134940 | +| policy_gradient_loss | -0.0642 | +| value_loss | 0.000588 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | 0.177 | +| time/ | | +| fps | 309 | +| iterations | 7443 | +| time_elapsed | 24621 | +| total_timesteps | 7621632 | +| train/ | | +| approx_kl | 2.2698362 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.356 | +| explained_variance | -7.29 | +| learning_rate | 0.0001 | +| loss | -0.0898 | +| n_updates | 134950 | +| policy_gradient_loss | -0.0669 | +| value_loss | 0.000409 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | 0.177 | +| time/ | | +| fps | 309 | +| iterations | 7444 | +| time_elapsed | 24624 | +| total_timesteps | 7622656 | +| train/ | | +| approx_kl | 1.8340877 | +| clip_fraction | 0.491 | +| clip_range | 0.2 | +| entropy_loss | -0.391 | +| explained_variance | -6.12 | +| learning_rate | 0.0001 | +| loss | -0.11 | +| n_updates | 134960 | +| policy_gradient_loss | -0.0664 | +| value_loss | 0.00032 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.62e+03 | +| ep_rew_mean | 0.176 | +| time/ | | +| fps | 309 | +| iterations | 7445 | +| time_elapsed | 24628 | +| total_timesteps | 7623680 | +| train/ | | +| approx_kl | 4.3920617 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.344 | +| explained_variance | -1.03 | +| learning_rate | 0.0001 | +| loss | -0.0893 | +| n_updates | 134970 | +| policy_gradient_loss | -0.0715 | +| value_loss | 0.000387 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.62e+03 | +| ep_rew_mean | 0.176 | +| time/ | | +| fps | 309 | +| iterations | 7446 | +| time_elapsed | 24631 | +| total_timesteps | 7624704 | +| train/ | | +| approx_kl | 2.1389642 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.351 | +| explained_variance | -3.89 | +| learning_rate | 0.0001 | +| loss | -0.0921 | +| n_updates | 134980 | +| policy_gradient_loss | -0.0706 | +| value_loss | 0.000479 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.62e+03 | +| ep_rew_mean | 0.173 | +| time/ | | +| fps | 309 | +| iterations | 7447 | +| time_elapsed | 24634 | +| total_timesteps | 7625728 | +| train/ | | +| approx_kl | 3.6153412 | +| clip_fraction | 0.465 | +| clip_range | 0.2 | +| entropy_loss | -0.334 | +| explained_variance | -2.02 | +| learning_rate | 0.0001 | +| loss | -0.0958 | +| n_updates | 134990 | +| policy_gradient_loss | -0.0639 | +| value_loss | 0.000653 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.61e+03 | +| ep_rew_mean | 0.178 | +| time/ | | +| fps | 309 | +| iterations | 7448 | +| time_elapsed | 24637 | +| total_timesteps | 7626752 | +| train/ | | +| approx_kl | 2.835744 | +| clip_fraction | 0.468 | +| clip_range | 0.2 | +| entropy_loss | -0.347 | +| explained_variance | -1.38 | +| learning_rate | 0.0001 | +| loss | -0.0763 | +| n_updates | 135000 | +| policy_gradient_loss | -0.0693 | +| value_loss | 0.000548 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.61e+03 | +| ep_rew_mean | 0.178 | +| time/ | | +| fps | 309 | +| iterations | 7449 | +| time_elapsed | 24640 | +| total_timesteps | 7627776 | +| train/ | | +| approx_kl | 2.487907 | +| clip_fraction | 0.488 | +| clip_range | 0.2 | +| entropy_loss | -0.367 | +| explained_variance | -1.32 | +| learning_rate | 0.0001 | +| loss | -0.089 | +| n_updates | 135010 | +| policy_gradient_loss | -0.0668 | +| value_loss | 0.000618 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.61e+03 | +| ep_rew_mean | 0.178 | +| time/ | | +| fps | 309 | +| iterations | 7450 | +| time_elapsed | 24644 | +| total_timesteps | 7628800 | +| train/ | | +| approx_kl | 2.421029 | +| clip_fraction | 0.463 | +| clip_range | 0.2 | +| entropy_loss | -0.369 | +| explained_variance | -1.34 | +| learning_rate | 0.0001 | +| loss | -0.115 | +| n_updates | 135020 | +| policy_gradient_loss | -0.066 | +| value_loss | 0.0005 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.61e+03 | +| ep_rew_mean | 0.182 | +| time/ | | +| fps | 309 | +| iterations | 7451 | +| time_elapsed | 24647 | +| total_timesteps | 7629824 | +| train/ | | +| approx_kl | 2.8388395 | +| clip_fraction | 0.478 | +| clip_range | 0.2 | +| entropy_loss | -0.353 | +| explained_variance | -3.45 | +| learning_rate | 0.0001 | +| loss | -0.112 | +| n_updates | 135030 | +| policy_gradient_loss | -0.0687 | +| value_loss | 0.000539 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.61e+03 | +| ep_rew_mean | 0.182 | +| time/ | | +| fps | 309 | +| iterations | 7452 | +| time_elapsed | 24650 | +| total_timesteps | 7630848 | +| train/ | | +| approx_kl | 2.2348258 | +| clip_fraction | 0.454 | +| clip_range | 0.2 | +| entropy_loss | -0.351 | +| explained_variance | -2.06 | +| learning_rate | 0.0001 | +| loss | -0.0813 | +| n_updates | 135040 | +| policy_gradient_loss | -0.0616 | +| value_loss | 0.000457 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.61e+03 | +| ep_rew_mean | 0.182 | +| time/ | | +| fps | 309 | +| iterations | 7453 | +| time_elapsed | 24654 | +| total_timesteps | 7631872 | +| train/ | | +| approx_kl | 3.1183343 | +| clip_fraction | 0.486 | +| clip_range | 0.2 | +| entropy_loss | -0.391 | +| explained_variance | -5 | +| learning_rate | 0.0001 | +| loss | -0.094 | +| n_updates | 135050 | +| policy_gradient_loss | -0.0693 | +| value_loss | 0.000388 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.61e+03 | +| ep_rew_mean | 0.184 | +| time/ | | +| fps | 309 | +| iterations | 7454 | +| time_elapsed | 24657 | +| total_timesteps | 7632896 | +| train/ | | +| approx_kl | 1.8852364 | +| clip_fraction | 0.488 | +| clip_range | 0.2 | +| entropy_loss | -0.411 | +| explained_variance | -1.13 | +| learning_rate | 0.0001 | +| loss | -0.09 | +| n_updates | 135060 | +| policy_gradient_loss | -0.069 | +| value_loss | 0.000779 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.61e+03 | +| ep_rew_mean | 0.184 | +| time/ | | +| fps | 309 | +| iterations | 7455 | +| time_elapsed | 24660 | +| total_timesteps | 7633920 | +| train/ | | +| approx_kl | 2.3356466 | +| clip_fraction | 0.482 | +| clip_range | 0.2 | +| entropy_loss | -0.396 | +| explained_variance | -3.16 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 135070 | +| policy_gradient_loss | -0.0699 | +| value_loss | 0.00045 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.61e+03 | +| ep_rew_mean | 0.183 | +| time/ | | +| fps | 309 | +| iterations | 7456 | +| time_elapsed | 24664 | +| total_timesteps | 7634944 | +| train/ | | +| approx_kl | 2.7158062 | +| clip_fraction | 0.499 | +| clip_range | 0.2 | +| entropy_loss | -0.364 | +| explained_variance | -2.39 | +| learning_rate | 0.0001 | +| loss | -0.0771 | +| n_updates | 135080 | +| policy_gradient_loss | -0.0755 | +| value_loss | 0.0005 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.61e+03 | +| ep_rew_mean | 0.183 | +| time/ | | +| fps | 309 | +| iterations | 7457 | +| time_elapsed | 24667 | +| total_timesteps | 7635968 | +| train/ | | +| approx_kl | 3.2772121 | +| clip_fraction | 0.477 | +| clip_range | 0.2 | +| entropy_loss | -0.337 | +| explained_variance | -2.8 | +| learning_rate | 0.0001 | +| loss | -0.0948 | +| n_updates | 135090 | +| policy_gradient_loss | -0.0718 | +| value_loss | 0.000528 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.62e+03 | +| ep_rew_mean | 0.178 | +| time/ | | +| fps | 309 | +| iterations | 7458 | +| time_elapsed | 24670 | +| total_timesteps | 7636992 | +| train/ | | +| approx_kl | 1.9216735 | +| clip_fraction | 0.511 | +| clip_range | 0.2 | +| entropy_loss | -0.42 | +| explained_variance | -3.75 | +| learning_rate | 0.0001 | +| loss | -0.0915 | +| n_updates | 135100 | +| policy_gradient_loss | -0.0688 | +| value_loss | 0.000453 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.62e+03 | +| ep_rew_mean | 0.178 | +| time/ | | +| fps | 309 | +| iterations | 7459 | +| time_elapsed | 24673 | +| total_timesteps | 7638016 | +| train/ | | +| approx_kl | 2.0834322 | +| clip_fraction | 0.482 | +| clip_range | 0.2 | +| entropy_loss | -0.354 | +| explained_variance | -3.95 | +| learning_rate | 0.0001 | +| loss | -0.0977 | +| n_updates | 135110 | +| policy_gradient_loss | -0.0762 | +| value_loss | 0.000598 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.63e+03 | +| ep_rew_mean | 0.177 | +| time/ | | +| fps | 309 | +| iterations | 7460 | +| time_elapsed | 24677 | +| total_timesteps | 7639040 | +| train/ | | +| approx_kl | 2.24397 | +| clip_fraction | 0.489 | +| clip_range | 0.2 | +| entropy_loss | -0.401 | +| explained_variance | -2.08 | +| learning_rate | 0.0001 | +| loss | -0.0857 | +| n_updates | 135120 | +| policy_gradient_loss | -0.0661 | +| value_loss | 0.000552 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.63e+03 | +| ep_rew_mean | 0.183 | +| time/ | | +| fps | 309 | +| iterations | 7461 | +| time_elapsed | 24680 | +| total_timesteps | 7640064 | +| train/ | | +| approx_kl | 2.4968963 | +| clip_fraction | 0.503 | +| clip_range | 0.2 | +| entropy_loss | -0.373 | +| explained_variance | -1.33 | +| learning_rate | 0.0001 | +| loss | -0.0961 | +| n_updates | 135130 | +| policy_gradient_loss | -0.074 | +| value_loss | 0.000746 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.63e+03 | +| ep_rew_mean | 0.183 | +| time/ | | +| fps | 309 | +| iterations | 7462 | +| time_elapsed | 24683 | +| total_timesteps | 7641088 | +| train/ | | +| approx_kl | 2.2188554 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.352 | +| explained_variance | -1.26 | +| learning_rate | 0.0001 | +| loss | -0.0696 | +| n_updates | 135140 | +| policy_gradient_loss | -0.0623 | +| value_loss | 0.000786 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.63e+03 | +| ep_rew_mean | 0.178 | +| time/ | | +| fps | 309 | +| iterations | 7463 | +| time_elapsed | 24686 | +| total_timesteps | 7642112 | +| train/ | | +| approx_kl | 2.1050673 | +| clip_fraction | 0.448 | +| clip_range | 0.2 | +| entropy_loss | -0.364 | +| explained_variance | -6.71 | +| learning_rate | 0.0001 | +| loss | -0.067 | +| n_updates | 135150 | +| policy_gradient_loss | -0.0648 | +| value_loss | 0.000382 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.63e+03 | +| ep_rew_mean | 0.177 | +| time/ | | +| fps | 309 | +| iterations | 7464 | +| time_elapsed | 24689 | +| total_timesteps | 7643136 | +| train/ | | +| approx_kl | 1.9453437 | +| clip_fraction | 0.467 | +| clip_range | 0.2 | +| entropy_loss | -0.38 | +| explained_variance | -1.03 | +| learning_rate | 0.0001 | +| loss | -0.0975 | +| n_updates | 135160 | +| policy_gradient_loss | -0.0634 | +| value_loss | 0.000693 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.63e+03 | +| ep_rew_mean | 0.177 | +| time/ | | +| fps | 309 | +| iterations | 7465 | +| time_elapsed | 24692 | +| total_timesteps | 7644160 | +| train/ | | +| approx_kl | 2.575479 | +| clip_fraction | 0.497 | +| clip_range | 0.2 | +| entropy_loss | -0.397 | +| explained_variance | -0.952 | +| learning_rate | 0.0001 | +| loss | -0.0831 | +| n_updates | 135170 | +| policy_gradient_loss | -0.0697 | +| value_loss | 0.000504 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.62e+03 | +| ep_rew_mean | 0.175 | +| time/ | | +| fps | 309 | +| iterations | 7466 | +| time_elapsed | 24696 | +| total_timesteps | 7645184 | +| train/ | | +| approx_kl | 1.7494165 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.404 | +| explained_variance | -2.49 | +| learning_rate | 0.0001 | +| loss | -0.0881 | +| n_updates | 135180 | +| policy_gradient_loss | -0.0665 | +| value_loss | 0.000557 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.62e+03 | +| ep_rew_mean | 0.175 | +| time/ | | +| fps | 309 | +| iterations | 7467 | +| time_elapsed | 24699 | +| total_timesteps | 7646208 | +| train/ | | +| approx_kl | 3.7697973 | +| clip_fraction | 0.49 | +| clip_range | 0.2 | +| entropy_loss | -0.359 | +| explained_variance | -4.37 | +| learning_rate | 0.0001 | +| loss | -0.113 | +| n_updates | 135190 | +| policy_gradient_loss | -0.0651 | +| value_loss | 0.00035 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.63e+03 | +| ep_rew_mean | 0.177 | +| time/ | | +| fps | 309 | +| iterations | 7468 | +| time_elapsed | 24702 | +| total_timesteps | 7647232 | +| train/ | | +| approx_kl | 2.3799577 | +| clip_fraction | 0.498 | +| clip_range | 0.2 | +| entropy_loss | -0.382 | +| explained_variance | -0.92 | +| learning_rate | 0.0001 | +| loss | -0.0913 | +| n_updates | 135200 | +| policy_gradient_loss | -0.0645 | +| value_loss | 0.00032 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.63e+03 | +| ep_rew_mean | 0.177 | +| time/ | | +| fps | 309 | +| iterations | 7469 | +| time_elapsed | 24706 | +| total_timesteps | 7648256 | +| train/ | | +| approx_kl | 2.62356 | +| clip_fraction | 0.469 | +| clip_range | 0.2 | +| entropy_loss | -0.379 | +| explained_variance | -1.77 | +| learning_rate | 0.0001 | +| loss | -0.0606 | +| n_updates | 135210 | +| policy_gradient_loss | -0.0608 | +| value_loss | 0.000481 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.63e+03 | +| ep_rew_mean | 0.177 | +| time/ | | +| fps | 309 | +| iterations | 7470 | +| time_elapsed | 24709 | +| total_timesteps | 7649280 | +| train/ | | +| approx_kl | 2.5132344 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.335 | +| explained_variance | -1.97 | +| learning_rate | 0.0001 | +| loss | -0.0826 | +| n_updates | 135220 | +| policy_gradient_loss | -0.0705 | +| value_loss | 0.000549 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.64e+03 | +| ep_rew_mean | 0.182 | +| time/ | | +| fps | 309 | +| iterations | 7471 | +| time_elapsed | 24713 | +| total_timesteps | 7650304 | +| train/ | | +| approx_kl | 4.0091567 | +| clip_fraction | 0.473 | +| clip_range | 0.2 | +| entropy_loss | -0.345 | +| explained_variance | -2.62 | +| learning_rate | 0.0001 | +| loss | -0.0757 | +| n_updates | 135230 | +| policy_gradient_loss | -0.0694 | +| value_loss | 0.000775 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.64e+03 | +| ep_rew_mean | 0.182 | +| time/ | | +| fps | 309 | +| iterations | 7472 | +| time_elapsed | 24716 | +| total_timesteps | 7651328 | +| train/ | | +| approx_kl | 2.352508 | +| clip_fraction | 0.479 | +| clip_range | 0.2 | +| entropy_loss | -0.346 | +| explained_variance | -1.65 | +| learning_rate | 0.0001 | +| loss | -0.091 | +| n_updates | 135240 | +| policy_gradient_loss | -0.0652 | +| value_loss | 0.000568 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | 0.184 | +| time/ | | +| fps | 309 | +| iterations | 7473 | +| time_elapsed | 24720 | +| total_timesteps | 7652352 | +| train/ | | +| approx_kl | 2.7401378 | +| clip_fraction | 0.5 | +| clip_range | 0.2 | +| entropy_loss | -0.408 | +| explained_variance | -2.91 | +| learning_rate | 0.0001 | +| loss | -0.0848 | +| n_updates | 135250 | +| policy_gradient_loss | -0.0755 | +| value_loss | 0.0005 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.64e+03 | +| ep_rew_mean | 0.177 | +| time/ | | +| fps | 309 | +| iterations | 7474 | +| time_elapsed | 24723 | +| total_timesteps | 7653376 | +| train/ | | +| approx_kl | 2.409266 | +| clip_fraction | 0.482 | +| clip_range | 0.2 | +| entropy_loss | -0.35 | +| explained_variance | -1.85 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 135260 | +| policy_gradient_loss | -0.0687 | +| value_loss | 0.000493 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.64e+03 | +| ep_rew_mean | 0.177 | +| time/ | | +| fps | 309 | +| iterations | 7475 | +| time_elapsed | 24727 | +| total_timesteps | 7654400 | +| train/ | | +| approx_kl | 1.7539675 | +| clip_fraction | 0.458 | +| clip_range | 0.2 | +| entropy_loss | -0.359 | +| explained_variance | -1.06 | +| learning_rate | 0.0001 | +| loss | -0.0987 | +| n_updates | 135270 | +| policy_gradient_loss | -0.0654 | +| value_loss | 0.00048 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.64e+03 | +| ep_rew_mean | 0.177 | +| time/ | | +| fps | 309 | +| iterations | 7476 | +| time_elapsed | 24730 | +| total_timesteps | 7655424 | +| train/ | | +| approx_kl | 2.211668 | +| clip_fraction | 0.5 | +| clip_range | 0.2 | +| entropy_loss | -0.381 | +| explained_variance | -1.53 | +| learning_rate | 0.0001 | +| loss | -0.099 | +| n_updates | 135280 | +| policy_gradient_loss | -0.0704 | +| value_loss | 0.000663 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.65e+03 | +| ep_rew_mean | 0.178 | +| time/ | | +| fps | 309 | +| iterations | 7477 | +| time_elapsed | 24733 | +| total_timesteps | 7656448 | +| train/ | | +| approx_kl | 2.2531095 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.354 | +| explained_variance | -3.17 | +| learning_rate | 0.0001 | +| loss | -0.0454 | +| n_updates | 135290 | +| policy_gradient_loss | -0.0667 | +| value_loss | 0.00069 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.65e+03 | +| ep_rew_mean | 0.178 | +| time/ | | +| fps | 309 | +| iterations | 7478 | +| time_elapsed | 24736 | +| total_timesteps | 7657472 | +| train/ | | +| approx_kl | 2.5256665 | +| clip_fraction | 0.491 | +| clip_range | 0.2 | +| entropy_loss | -0.393 | +| explained_variance | -1.48 | +| learning_rate | 0.0001 | +| loss | -0.0766 | +| n_updates | 135300 | +| policy_gradient_loss | -0.0677 | +| value_loss | 0.000618 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | 0.181 | +| time/ | | +| fps | 309 | +| iterations | 7479 | +| time_elapsed | 24739 | +| total_timesteps | 7658496 | +| train/ | | +| approx_kl | 2.148193 | +| clip_fraction | 0.515 | +| clip_range | 0.2 | +| entropy_loss | -0.459 | +| explained_variance | -1.59 | +| learning_rate | 0.0001 | +| loss | -0.0799 | +| n_updates | 135310 | +| policy_gradient_loss | -0.0757 | +| value_loss | 0.00072 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | 0.181 | +| time/ | | +| fps | 309 | +| iterations | 7480 | +| time_elapsed | 24743 | +| total_timesteps | 7659520 | +| train/ | | +| approx_kl | 2.2242713 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.346 | +| explained_variance | -2.01 | +| learning_rate | 0.0001 | +| loss | -0.0768 | +| n_updates | 135320 | +| policy_gradient_loss | -0.0649 | +| value_loss | 0.000763 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.182 | +| time/ | | +| fps | 309 | +| iterations | 7481 | +| time_elapsed | 24746 | +| total_timesteps | 7660544 | +| train/ | | +| approx_kl | 2.0639582 | +| clip_fraction | 0.51 | +| clip_range | 0.2 | +| entropy_loss | -0.426 | +| explained_variance | -3.59 | +| learning_rate | 0.0001 | +| loss | -0.0845 | +| n_updates | 135330 | +| policy_gradient_loss | -0.0713 | +| value_loss | 0.000455 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.181 | +| time/ | | +| fps | 309 | +| iterations | 7482 | +| time_elapsed | 24749 | +| total_timesteps | 7661568 | +| train/ | | +| approx_kl | 2.0203834 | +| clip_fraction | 0.496 | +| clip_range | 0.2 | +| entropy_loss | -0.405 | +| explained_variance | -2.36 | +| learning_rate | 0.0001 | +| loss | -0.0762 | +| n_updates | 135340 | +| policy_gradient_loss | -0.0653 | +| value_loss | 0.000301 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.181 | +| time/ | | +| fps | 309 | +| iterations | 7483 | +| time_elapsed | 24752 | +| total_timesteps | 7662592 | +| train/ | | +| approx_kl | 2.1952028 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.377 | +| explained_variance | -1.08 | +| learning_rate | 0.0001 | +| loss | -0.0957 | +| n_updates | 135350 | +| policy_gradient_loss | -0.0644 | +| value_loss | 0.000658 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.182 | +| time/ | | +| fps | 309 | +| iterations | 7484 | +| time_elapsed | 24755 | +| total_timesteps | 7663616 | +| train/ | | +| approx_kl | 2.2839856 | +| clip_fraction | 0.496 | +| clip_range | 0.2 | +| entropy_loss | -0.365 | +| explained_variance | -4.11 | +| learning_rate | 0.0001 | +| loss | -0.0606 | +| n_updates | 135360 | +| policy_gradient_loss | -0.0706 | +| value_loss | 0.000473 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.182 | +| time/ | | +| fps | 309 | +| iterations | 7485 | +| time_elapsed | 24759 | +| total_timesteps | 7664640 | +| train/ | | +| approx_kl | 2.7380714 | +| clip_fraction | 0.513 | +| clip_range | 0.2 | +| entropy_loss | -0.422 | +| explained_variance | -0.724 | +| learning_rate | 0.0001 | +| loss | -0.0805 | +| n_updates | 135370 | +| policy_gradient_loss | -0.0673 | +| value_loss | 0.000653 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | 0.183 | +| time/ | | +| fps | 309 | +| iterations | 7486 | +| time_elapsed | 24762 | +| total_timesteps | 7665664 | +| train/ | | +| approx_kl | 1.939796 | +| clip_fraction | 0.496 | +| clip_range | 0.2 | +| entropy_loss | -0.401 | +| explained_variance | -2.74 | +| learning_rate | 0.0001 | +| loss | -0.0521 | +| n_updates | 135380 | +| policy_gradient_loss | -0.0649 | +| value_loss | 0.000702 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.173 | +| time/ | | +| fps | 309 | +| iterations | 7487 | +| time_elapsed | 24766 | +| total_timesteps | 7666688 | +| train/ | | +| approx_kl | 2.5017862 | +| clip_fraction | 0.499 | +| clip_range | 0.2 | +| entropy_loss | -0.376 | +| explained_variance | -1.42 | +| learning_rate | 0.0001 | +| loss | -0.1 | +| n_updates | 135390 | +| policy_gradient_loss | -0.0633 | +| value_loss | 0.000678 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.173 | +| time/ | | +| fps | 309 | +| iterations | 7488 | +| time_elapsed | 24769 | +| total_timesteps | 7667712 | +| train/ | | +| approx_kl | 2.43777 | +| clip_fraction | 0.462 | +| clip_range | 0.2 | +| entropy_loss | -0.35 | +| explained_variance | -0.831 | +| learning_rate | 0.0001 | +| loss | -0.0497 | +| n_updates | 135400 | +| policy_gradient_loss | -0.0615 | +| value_loss | 0.000797 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.173 | +| time/ | | +| fps | 309 | +| iterations | 7489 | +| time_elapsed | 24773 | +| total_timesteps | 7668736 | +| train/ | | +| approx_kl | 2.8364964 | +| clip_fraction | 0.51 | +| clip_range | 0.2 | +| entropy_loss | -0.416 | +| explained_variance | -2.75 | +| learning_rate | 0.0001 | +| loss | -0.113 | +| n_updates | 135410 | +| policy_gradient_loss | -0.0603 | +| value_loss | 0.00055 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.173 | +| time/ | | +| fps | 309 | +| iterations | 7490 | +| time_elapsed | 24776 | +| total_timesteps | 7669760 | +| train/ | | +| approx_kl | 2.7966633 | +| clip_fraction | 0.506 | +| clip_range | 0.2 | +| entropy_loss | -0.414 | +| explained_variance | -3.91 | +| learning_rate | 0.0001 | +| loss | -0.0915 | +| n_updates | 135420 | +| policy_gradient_loss | -0.0756 | +| value_loss | 0.000299 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.167 | +| time/ | | +| fps | 309 | +| iterations | 7491 | +| time_elapsed | 24780 | +| total_timesteps | 7670784 | +| train/ | | +| approx_kl | 2.2628982 | +| clip_fraction | 0.457 | +| clip_range | 0.2 | +| entropy_loss | -0.353 | +| explained_variance | -2.21 | +| learning_rate | 0.0001 | +| loss | -0.088 | +| n_updates | 135430 | +| policy_gradient_loss | -0.0638 | +| value_loss | 0.000479 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.167 | +| time/ | | +| fps | 309 | +| iterations | 7492 | +| time_elapsed | 24783 | +| total_timesteps | 7671808 | +| train/ | | +| approx_kl | 2.4535656 | +| clip_fraction | 0.455 | +| clip_range | 0.2 | +| entropy_loss | -0.376 | +| explained_variance | -1.32 | +| learning_rate | 0.0001 | +| loss | -0.0747 | +| n_updates | 135440 | +| policy_gradient_loss | -0.0679 | +| value_loss | 0.000448 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.167 | +| time/ | | +| fps | 309 | +| iterations | 7493 | +| time_elapsed | 24787 | +| total_timesteps | 7672832 | +| train/ | | +| approx_kl | 2.2399688 | +| clip_fraction | 0.492 | +| clip_range | 0.2 | +| entropy_loss | -0.384 | +| explained_variance | -0.446 | +| learning_rate | 0.0001 | +| loss | -0.0968 | +| n_updates | 135450 | +| policy_gradient_loss | -0.0632 | +| value_loss | 0.000519 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.167 | +| time/ | | +| fps | 309 | +| iterations | 7494 | +| time_elapsed | 24790 | +| total_timesteps | 7673856 | +| train/ | | +| approx_kl | 11.757904 | +| clip_fraction | 0.443 | +| clip_range | 0.2 | +| entropy_loss | -0.342 | +| explained_variance | -3.25 | +| learning_rate | 0.0001 | +| loss | -0.0639 | +| n_updates | 135460 | +| policy_gradient_loss | -0.0622 | +| value_loss | 0.000542 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.166 | +| time/ | | +| fps | 309 | +| iterations | 7495 | +| time_elapsed | 24793 | +| total_timesteps | 7674880 | +| train/ | | +| approx_kl | 2.5590189 | +| clip_fraction | 0.504 | +| clip_range | 0.2 | +| entropy_loss | -0.382 | +| explained_variance | -2.81 | +| learning_rate | 0.0001 | +| loss | -0.0903 | +| n_updates | 135470 | +| policy_gradient_loss | -0.073 | +| value_loss | 0.000532 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.166 | +| time/ | | +| fps | 309 | +| iterations | 7496 | +| time_elapsed | 24796 | +| total_timesteps | 7675904 | +| train/ | | +| approx_kl | 2.8227031 | +| clip_fraction | 0.474 | +| clip_range | 0.2 | +| entropy_loss | -0.308 | +| explained_variance | -4.03 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 135480 | +| policy_gradient_loss | -0.0716 | +| value_loss | 0.000677 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.168 | +| time/ | | +| fps | 309 | +| iterations | 7497 | +| time_elapsed | 24799 | +| total_timesteps | 7676928 | +| train/ | | +| approx_kl | 2.1664286 | +| clip_fraction | 0.47 | +| clip_range | 0.2 | +| entropy_loss | -0.351 | +| explained_variance | -0.765 | +| learning_rate | 0.0001 | +| loss | -0.0841 | +| n_updates | 135490 | +| policy_gradient_loss | -0.0601 | +| value_loss | 0.000708 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.168 | +| time/ | | +| fps | 309 | +| iterations | 7498 | +| time_elapsed | 24803 | +| total_timesteps | 7677952 | +| train/ | | +| approx_kl | 1.9196371 | +| clip_fraction | 0.434 | +| clip_range | 0.2 | +| entropy_loss | -0.317 | +| explained_variance | -3.16 | +| learning_rate | 0.0001 | +| loss | -0.115 | +| n_updates | 135500 | +| policy_gradient_loss | -0.0633 | +| value_loss | 0.000506 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.168 | +| time/ | | +| fps | 309 | +| iterations | 7499 | +| time_elapsed | 24806 | +| total_timesteps | 7678976 | +| train/ | | +| approx_kl | 2.2782505 | +| clip_fraction | 0.458 | +| clip_range | 0.2 | +| entropy_loss | -0.35 | +| explained_variance | -4.42 | +| learning_rate | 0.0001 | +| loss | -0.0807 | +| n_updates | 135510 | +| policy_gradient_loss | -0.0635 | +| value_loss | 0.000269 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.168 | +| time/ | | +| fps | 309 | +| iterations | 7500 | +| time_elapsed | 24809 | +| total_timesteps | 7680000 | +| train/ | | +| approx_kl | 2.1676922 | +| clip_fraction | 0.444 | +| clip_range | 0.2 | +| entropy_loss | -0.32 | +| explained_variance | -0.36 | +| learning_rate | 0.0001 | +| loss | -0.0802 | +| n_updates | 135520 | +| policy_gradient_loss | -0.0618 | +| value_loss | 0.000586 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.169 | +| time/ | | +| fps | 309 | +| iterations | 7501 | +| time_elapsed | 24812 | +| total_timesteps | 7681024 | +| train/ | | +| approx_kl | 2.3322377 | +| clip_fraction | 0.519 | +| clip_range | 0.2 | +| entropy_loss | -0.445 | +| explained_variance | -5.27 | +| learning_rate | 0.0001 | +| loss | -0.0803 | +| n_updates | 135530 | +| policy_gradient_loss | -0.0726 | +| value_loss | 0.000679 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.167 | +| time/ | | +| fps | 309 | +| iterations | 7502 | +| time_elapsed | 24815 | +| total_timesteps | 7682048 | +| train/ | | +| approx_kl | 1.8357785 | +| clip_fraction | 0.492 | +| clip_range | 0.2 | +| entropy_loss | -0.413 | +| explained_variance | -1.81 | +| learning_rate | 0.0001 | +| loss | -0.0722 | +| n_updates | 135540 | +| policy_gradient_loss | -0.068 | +| value_loss | 0.000612 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.167 | +| time/ | | +| fps | 309 | +| iterations | 7503 | +| time_elapsed | 24818 | +| total_timesteps | 7683072 | +| train/ | | +| approx_kl | 2.1228616 | +| clip_fraction | 0.466 | +| clip_range | 0.2 | +| entropy_loss | -0.364 | +| explained_variance | -3.28 | +| learning_rate | 0.0001 | +| loss | -0.0773 | +| n_updates | 135550 | +| policy_gradient_loss | -0.0645 | +| value_loss | 0.000602 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.167 | +| time/ | | +| fps | 309 | +| iterations | 7504 | +| time_elapsed | 24822 | +| total_timesteps | 7684096 | +| train/ | | +| approx_kl | 2.4539733 | +| clip_fraction | 0.463 | +| clip_range | 0.2 | +| entropy_loss | -0.326 | +| explained_variance | -3.25 | +| learning_rate | 0.0001 | +| loss | -0.0968 | +| n_updates | 135560 | +| policy_gradient_loss | -0.0693 | +| value_loss | 0.000666 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.169 | +| time/ | | +| fps | 309 | +| iterations | 7505 | +| time_elapsed | 24825 | +| total_timesteps | 7685120 | +| train/ | | +| approx_kl | 2.2657502 | +| clip_fraction | 0.5 | +| clip_range | 0.2 | +| entropy_loss | -0.458 | +| explained_variance | -2.15 | +| learning_rate | 0.0001 | +| loss | -0.0859 | +| n_updates | 135570 | +| policy_gradient_loss | -0.069 | +| value_loss | 0.000493 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.173 | +| time/ | | +| fps | 309 | +| iterations | 7506 | +| time_elapsed | 24829 | +| total_timesteps | 7686144 | +| train/ | | +| approx_kl | 2.5039763 | +| clip_fraction | 0.47 | +| clip_range | 0.2 | +| entropy_loss | -0.348 | +| explained_variance | -1.79 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 135580 | +| policy_gradient_loss | -0.0663 | +| value_loss | 0.000535 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.18 | +| time/ | | +| fps | 309 | +| iterations | 7507 | +| time_elapsed | 24832 | +| total_timesteps | 7687168 | +| train/ | | +| approx_kl | 2.7708154 | +| clip_fraction | 0.434 | +| clip_range | 0.2 | +| entropy_loss | -0.319 | +| explained_variance | -1.13 | +| learning_rate | 0.0001 | +| loss | -0.0955 | +| n_updates | 135590 | +| policy_gradient_loss | -0.0644 | +| value_loss | 0.000655 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.18 | +| time/ | | +| fps | 309 | +| iterations | 7508 | +| time_elapsed | 24836 | +| total_timesteps | 7688192 | +| train/ | | +| approx_kl | 3.770266 | +| clip_fraction | 0.467 | +| clip_range | 0.2 | +| entropy_loss | -0.327 | +| explained_variance | -1.1 | +| learning_rate | 0.0001 | +| loss | -0.0795 | +| n_updates | 135600 | +| policy_gradient_loss | -0.07 | +| value_loss | 0.000961 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.186 | +| time/ | | +| fps | 309 | +| iterations | 7509 | +| time_elapsed | 24839 | +| total_timesteps | 7689216 | +| train/ | | +| approx_kl | 2.2391405 | +| clip_fraction | 0.482 | +| clip_range | 0.2 | +| entropy_loss | -0.374 | +| explained_variance | -2.99 | +| learning_rate | 0.0001 | +| loss | -0.085 | +| n_updates | 135610 | +| policy_gradient_loss | -0.0694 | +| value_loss | 0.000579 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.186 | +| time/ | | +| fps | 309 | +| iterations | 7510 | +| time_elapsed | 24843 | +| total_timesteps | 7690240 | +| train/ | | +| approx_kl | 2.2852101 | +| clip_fraction | 0.463 | +| clip_range | 0.2 | +| entropy_loss | -0.336 | +| explained_variance | -1.2 | +| learning_rate | 0.0001 | +| loss | -0.09 | +| n_updates | 135620 | +| policy_gradient_loss | -0.0736 | +| value_loss | 0.000625 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.188 | +| time/ | | +| fps | 309 | +| iterations | 7511 | +| time_elapsed | 24846 | +| total_timesteps | 7691264 | +| train/ | | +| approx_kl | 1.9444597 | +| clip_fraction | 0.462 | +| clip_range | 0.2 | +| entropy_loss | -0.353 | +| explained_variance | -1.5 | +| learning_rate | 0.0001 | +| loss | -0.043 | +| n_updates | 135630 | +| policy_gradient_loss | -0.064 | +| value_loss | 0.000489 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.188 | +| time/ | | +| fps | 309 | +| iterations | 7512 | +| time_elapsed | 24850 | +| total_timesteps | 7692288 | +| train/ | | +| approx_kl | 3.4190528 | +| clip_fraction | 0.469 | +| clip_range | 0.2 | +| entropy_loss | -0.355 | +| explained_variance | -14.2 | +| learning_rate | 0.0001 | +| loss | -0.0814 | +| n_updates | 135640 | +| policy_gradient_loss | -0.0672 | +| value_loss | 0.000875 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.187 | +| time/ | | +| fps | 309 | +| iterations | 7513 | +| time_elapsed | 24853 | +| total_timesteps | 7693312 | +| train/ | | +| approx_kl | 2.3321347 | +| clip_fraction | 0.467 | +| clip_range | 0.2 | +| entropy_loss | -0.341 | +| explained_variance | -7.32 | +| learning_rate | 0.0001 | +| loss | -0.112 | +| n_updates | 135650 | +| policy_gradient_loss | -0.0687 | +| value_loss | 0.000525 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.187 | +| time/ | | +| fps | 309 | +| iterations | 7514 | +| time_elapsed | 24856 | +| total_timesteps | 7694336 | +| train/ | | +| approx_kl | 2.3482234 | +| clip_fraction | 0.461 | +| clip_range | 0.2 | +| entropy_loss | -0.347 | +| explained_variance | -0.532 | +| learning_rate | 0.0001 | +| loss | -0.0825 | +| n_updates | 135660 | +| policy_gradient_loss | -0.0652 | +| value_loss | 0.000525 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.187 | +| time/ | | +| fps | 309 | +| iterations | 7515 | +| time_elapsed | 24859 | +| total_timesteps | 7695360 | +| train/ | | +| approx_kl | 2.6404 | +| clip_fraction | 0.506 | +| clip_range | 0.2 | +| entropy_loss | -0.368 | +| explained_variance | -3.87 | +| learning_rate | 0.0001 | +| loss | -0.0953 | +| n_updates | 135670 | +| policy_gradient_loss | -0.073 | +| value_loss | 0.000635 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.186 | +| time/ | | +| fps | 309 | +| iterations | 7516 | +| time_elapsed | 24863 | +| total_timesteps | 7696384 | +| train/ | | +| approx_kl | 2.5641794 | +| clip_fraction | 0.492 | +| clip_range | 0.2 | +| entropy_loss | -0.329 | +| explained_variance | -2.07 | +| learning_rate | 0.0001 | +| loss | -0.094 | +| n_updates | 135680 | +| policy_gradient_loss | -0.069 | +| value_loss | 0.000708 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.186 | +| time/ | | +| fps | 309 | +| iterations | 7517 | +| time_elapsed | 24866 | +| total_timesteps | 7697408 | +| train/ | | +| approx_kl | 2.2494538 | +| clip_fraction | 0.418 | +| clip_range | 0.2 | +| entropy_loss | -0.301 | +| explained_variance | -1.44 | +| learning_rate | 0.0001 | +| loss | -0.0608 | +| n_updates | 135690 | +| policy_gradient_loss | -0.0552 | +| value_loss | 0.000855 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.186 | +| time/ | | +| fps | 309 | +| iterations | 7518 | +| time_elapsed | 24869 | +| total_timesteps | 7698432 | +| train/ | | +| approx_kl | 2.5132663 | +| clip_fraction | 0.489 | +| clip_range | 0.2 | +| entropy_loss | -0.347 | +| explained_variance | -3.51 | +| learning_rate | 0.0001 | +| loss | -0.079 | +| n_updates | 135700 | +| policy_gradient_loss | -0.0709 | +| value_loss | 0.000688 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.182 | +| time/ | | +| fps | 309 | +| iterations | 7519 | +| time_elapsed | 24872 | +| total_timesteps | 7699456 | +| train/ | | +| approx_kl | 3.3831563 | +| clip_fraction | 0.494 | +| clip_range | 0.2 | +| entropy_loss | -0.401 | +| explained_variance | -3.06 | +| learning_rate | 0.0001 | +| loss | -0.0961 | +| n_updates | 135710 | +| policy_gradient_loss | -0.0685 | +| value_loss | 0.000523 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.182 | +| time/ | | +| fps | 309 | +| iterations | 7520 | +| time_elapsed | 24875 | +| total_timesteps | 7700480 | +| train/ | | +| approx_kl | 2.410224 | +| clip_fraction | 0.465 | +| clip_range | 0.2 | +| entropy_loss | -0.362 | +| explained_variance | -3.55 | +| learning_rate | 0.0001 | +| loss | -0.0676 | +| n_updates | 135720 | +| policy_gradient_loss | -0.0662 | +| value_loss | 0.000288 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.183 | +| time/ | | +| fps | 309 | +| iterations | 7521 | +| time_elapsed | 24879 | +| total_timesteps | 7701504 | +| train/ | | +| approx_kl | 2.3642998 | +| clip_fraction | 0.509 | +| clip_range | 0.2 | +| entropy_loss | -0.421 | +| explained_variance | -0.548 | +| learning_rate | 0.0001 | +| loss | -0.0928 | +| n_updates | 135730 | +| policy_gradient_loss | -0.0644 | +| value_loss | 0.000505 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.183 | +| time/ | | +| fps | 309 | +| iterations | 7522 | +| time_elapsed | 24882 | +| total_timesteps | 7702528 | +| train/ | | +| approx_kl | 1.7795444 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.404 | +| explained_variance | -1.54 | +| learning_rate | 0.0001 | +| loss | -0.0593 | +| n_updates | 135740 | +| policy_gradient_loss | -0.0584 | +| value_loss | 0.000576 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.187 | +| time/ | | +| fps | 309 | +| iterations | 7523 | +| time_elapsed | 24886 | +| total_timesteps | 7703552 | +| train/ | | +| approx_kl | 2.525755 | +| clip_fraction | 0.497 | +| clip_range | 0.2 | +| entropy_loss | -0.347 | +| explained_variance | -2.8 | +| learning_rate | 0.0001 | +| loss | -0.0704 | +| n_updates | 135750 | +| policy_gradient_loss | -0.0685 | +| value_loss | 0.000593 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.187 | +| time/ | | +| fps | 309 | +| iterations | 7524 | +| time_elapsed | 24889 | +| total_timesteps | 7704576 | +| train/ | | +| approx_kl | 2.1272826 | +| clip_fraction | 0.469 | +| clip_range | 0.2 | +| entropy_loss | -0.343 | +| explained_variance | -2.82 | +| learning_rate | 0.0001 | +| loss | -0.0885 | +| n_updates | 135760 | +| policy_gradient_loss | -0.0609 | +| value_loss | 0.000802 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.187 | +| time/ | | +| fps | 309 | +| iterations | 7525 | +| time_elapsed | 24892 | +| total_timesteps | 7705600 | +| train/ | | +| approx_kl | 2.4125984 | +| clip_fraction | 0.493 | +| clip_range | 0.2 | +| entropy_loss | -0.331 | +| explained_variance | -2.12 | +| learning_rate | 0.0001 | +| loss | -0.0925 | +| n_updates | 135770 | +| policy_gradient_loss | -0.0665 | +| value_loss | 0.000503 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.188 | +| time/ | | +| fps | 309 | +| iterations | 7526 | +| time_elapsed | 24896 | +| total_timesteps | 7706624 | +| train/ | | +| approx_kl | 2.3561335 | +| clip_fraction | 0.49 | +| clip_range | 0.2 | +| entropy_loss | -0.332 | +| explained_variance | -1.83 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 135780 | +| policy_gradient_loss | -0.0687 | +| value_loss | 0.000561 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.188 | +| time/ | | +| fps | 309 | +| iterations | 7527 | +| time_elapsed | 24899 | +| total_timesteps | 7707648 | +| train/ | | +| approx_kl | 2.3657198 | +| clip_fraction | 0.464 | +| clip_range | 0.2 | +| entropy_loss | -0.323 | +| explained_variance | -2.81 | +| learning_rate | 0.0001 | +| loss | -0.0726 | +| n_updates | 135790 | +| policy_gradient_loss | -0.0585 | +| value_loss | 0.000595 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.195 | +| time/ | | +| fps | 309 | +| iterations | 7528 | +| time_elapsed | 24903 | +| total_timesteps | 7708672 | +| train/ | | +| approx_kl | 2.393135 | +| clip_fraction | 0.461 | +| clip_range | 0.2 | +| entropy_loss | -0.321 | +| explained_variance | -6.59 | +| learning_rate | 0.0001 | +| loss | -0.053 | +| n_updates | 135800 | +| policy_gradient_loss | -0.0678 | +| value_loss | 0.000465 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.195 | +| time/ | | +| fps | 309 | +| iterations | 7529 | +| time_elapsed | 24906 | +| total_timesteps | 7709696 | +| train/ | | +| approx_kl | 2.1479068 | +| clip_fraction | 0.469 | +| clip_range | 0.2 | +| entropy_loss | -0.378 | +| explained_variance | -3.02 | +| learning_rate | 0.0001 | +| loss | -0.0901 | +| n_updates | 135810 | +| policy_gradient_loss | -0.0656 | +| value_loss | 0.000611 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.192 | +| time/ | | +| fps | 309 | +| iterations | 7530 | +| time_elapsed | 24909 | +| total_timesteps | 7710720 | +| train/ | | +| approx_kl | 2.8393068 | +| clip_fraction | 0.484 | +| clip_range | 0.2 | +| entropy_loss | -0.334 | +| explained_variance | -7.46 | +| learning_rate | 0.0001 | +| loss | -0.0747 | +| n_updates | 135820 | +| policy_gradient_loss | -0.065 | +| value_loss | 0.000569 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.192 | +| time/ | | +| fps | 309 | +| iterations | 7531 | +| time_elapsed | 24913 | +| total_timesteps | 7711744 | +| train/ | | +| approx_kl | 2.2932022 | +| clip_fraction | 0.468 | +| clip_range | 0.2 | +| entropy_loss | -0.329 | +| explained_variance | -1.05 | +| learning_rate | 0.0001 | +| loss | -0.0764 | +| n_updates | 135830 | +| policy_gradient_loss | -0.0635 | +| value_loss | 0.000604 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.192 | +| time/ | | +| fps | 309 | +| iterations | 7532 | +| time_elapsed | 24916 | +| total_timesteps | 7712768 | +| train/ | | +| approx_kl | 3.3124914 | +| clip_fraction | 0.461 | +| clip_range | 0.2 | +| entropy_loss | -0.316 | +| explained_variance | -3.68 | +| learning_rate | 0.0001 | +| loss | -0.0798 | +| n_updates | 135840 | +| policy_gradient_loss | -0.0646 | +| value_loss | 0.000572 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.192 | +| time/ | | +| fps | 309 | +| iterations | 7533 | +| time_elapsed | 24919 | +| total_timesteps | 7713792 | +| train/ | | +| approx_kl | 2.6043158 | +| clip_fraction | 0.466 | +| clip_range | 0.2 | +| entropy_loss | -0.324 | +| explained_variance | -22.7 | +| learning_rate | 0.0001 | +| loss | -0.082 | +| n_updates | 135850 | +| policy_gradient_loss | -0.0692 | +| value_loss | 0.000366 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.78e+03 | +| ep_rew_mean | 0.192 | +| time/ | | +| fps | 309 | +| iterations | 7534 | +| time_elapsed | 24922 | +| total_timesteps | 7714816 | +| train/ | | +| approx_kl | 2.7086494 | +| clip_fraction | 0.473 | +| clip_range | 0.2 | +| entropy_loss | -0.332 | +| explained_variance | -1.09 | +| learning_rate | 0.0001 | +| loss | -0.0953 | +| n_updates | 135860 | +| policy_gradient_loss | -0.0618 | +| value_loss | 0.000761 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.188 | +| time/ | | +| fps | 309 | +| iterations | 7535 | +| time_elapsed | 24925 | +| total_timesteps | 7715840 | +| train/ | | +| approx_kl | 6.2474356 | +| clip_fraction | 0.485 | +| clip_range | 0.2 | +| entropy_loss | -0.348 | +| explained_variance | -0.38 | +| learning_rate | 0.0001 | +| loss | -0.0405 | +| n_updates | 135870 | +| policy_gradient_loss | -0.059 | +| value_loss | 0.00124 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.188 | +| time/ | | +| fps | 309 | +| iterations | 7536 | +| time_elapsed | 24928 | +| total_timesteps | 7716864 | +| train/ | | +| approx_kl | 2.6108296 | +| clip_fraction | 0.44 | +| clip_range | 0.2 | +| entropy_loss | -0.276 | +| explained_variance | -8.42 | +| learning_rate | 0.0001 | +| loss | -0.08 | +| n_updates | 135880 | +| policy_gradient_loss | -0.0647 | +| value_loss | 0.00101 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.189 | +| time/ | | +| fps | 309 | +| iterations | 7537 | +| time_elapsed | 24932 | +| total_timesteps | 7717888 | +| train/ | | +| approx_kl | 2.602294 | +| clip_fraction | 0.466 | +| clip_range | 0.2 | +| entropy_loss | -0.315 | +| explained_variance | -1.02 | +| learning_rate | 0.0001 | +| loss | -0.0829 | +| n_updates | 135890 | +| policy_gradient_loss | -0.0642 | +| value_loss | 0.00063 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.78e+03 | +| ep_rew_mean | 0.193 | +| time/ | | +| fps | 309 | +| iterations | 7538 | +| time_elapsed | 24935 | +| total_timesteps | 7718912 | +| train/ | | +| approx_kl | 5.0758214 | +| clip_fraction | 0.44 | +| clip_range | 0.2 | +| entropy_loss | -0.306 | +| explained_variance | -2.69 | +| learning_rate | 0.0001 | +| loss | -0.075 | +| n_updates | 135900 | +| policy_gradient_loss | -0.0642 | +| value_loss | 0.000492 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.78e+03 | +| ep_rew_mean | 0.193 | +| time/ | | +| fps | 309 | +| iterations | 7539 | +| time_elapsed | 24938 | +| total_timesteps | 7719936 | +| train/ | | +| approx_kl | 2.879457 | +| clip_fraction | 0.484 | +| clip_range | 0.2 | +| entropy_loss | -0.336 | +| explained_variance | -1.85 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 135910 | +| policy_gradient_loss | -0.0627 | +| value_loss | 0.000686 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.78e+03 | +| ep_rew_mean | 0.193 | +| time/ | | +| fps | 309 | +| iterations | 7540 | +| time_elapsed | 24941 | +| total_timesteps | 7720960 | +| train/ | | +| approx_kl | 3.4041653 | +| clip_fraction | 0.473 | +| clip_range | 0.2 | +| entropy_loss | -0.331 | +| explained_variance | -1.54 | +| learning_rate | 0.0001 | +| loss | -0.0838 | +| n_updates | 135920 | +| policy_gradient_loss | -0.0675 | +| value_loss | 0.000833 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.196 | +| time/ | | +| fps | 309 | +| iterations | 7541 | +| time_elapsed | 24945 | +| total_timesteps | 7721984 | +| train/ | | +| approx_kl | 2.4044757 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.334 | +| explained_variance | -1.1 | +| learning_rate | 0.0001 | +| loss | -0.0647 | +| n_updates | 135930 | +| policy_gradient_loss | -0.0663 | +| value_loss | 0.000742 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.2 | +| time/ | | +| fps | 309 | +| iterations | 7542 | +| time_elapsed | 24948 | +| total_timesteps | 7723008 | +| train/ | | +| approx_kl | 2.5056775 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.33 | +| explained_variance | -1.66 | +| learning_rate | 0.0001 | +| loss | -0.0777 | +| n_updates | 135940 | +| policy_gradient_loss | -0.0652 | +| value_loss | 0.000494 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.2 | +| time/ | | +| fps | 309 | +| iterations | 7543 | +| time_elapsed | 24952 | +| total_timesteps | 7724032 | +| train/ | | +| approx_kl | 2.1414337 | +| clip_fraction | 0.466 | +| clip_range | 0.2 | +| entropy_loss | -0.361 | +| explained_variance | -1.1 | +| learning_rate | 0.0001 | +| loss | -0.0704 | +| n_updates | 135950 | +| policy_gradient_loss | -0.0614 | +| value_loss | 0.000423 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.2 | +| time/ | | +| fps | 309 | +| iterations | 7544 | +| time_elapsed | 24955 | +| total_timesteps | 7725056 | +| train/ | | +| approx_kl | 2.6552658 | +| clip_fraction | 0.492 | +| clip_range | 0.2 | +| entropy_loss | -0.349 | +| explained_variance | -1.65 | +| learning_rate | 0.0001 | +| loss | -0.107 | +| n_updates | 135960 | +| policy_gradient_loss | -0.0657 | +| value_loss | 0.000555 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.2 | +| time/ | | +| fps | 309 | +| iterations | 7545 | +| time_elapsed | 24959 | +| total_timesteps | 7726080 | +| train/ | | +| approx_kl | 2.6689825 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.392 | +| explained_variance | -4.52 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 135970 | +| policy_gradient_loss | -0.0728 | +| value_loss | 0.000389 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.81e+03 | +| ep_rew_mean | 0.199 | +| time/ | | +| fps | 309 | +| iterations | 7546 | +| time_elapsed | 24962 | +| total_timesteps | 7727104 | +| train/ | | +| approx_kl | 2.4803624 | +| clip_fraction | 0.5 | +| clip_range | 0.2 | +| entropy_loss | -0.376 | +| explained_variance | -1.31 | +| learning_rate | 0.0001 | +| loss | -0.0557 | +| n_updates | 135980 | +| policy_gradient_loss | -0.0683 | +| value_loss | 0.000402 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.81e+03 | +| ep_rew_mean | 0.199 | +| time/ | | +| fps | 309 | +| iterations | 7547 | +| time_elapsed | 24966 | +| total_timesteps | 7728128 | +| train/ | | +| approx_kl | 3.1089902 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.324 | +| explained_variance | -1.22 | +| learning_rate | 0.0001 | +| loss | -0.0963 | +| n_updates | 135990 | +| policy_gradient_loss | -0.0721 | +| value_loss | 0.000682 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.82e+03 | +| ep_rew_mean | 0.196 | +| time/ | | +| fps | 309 | +| iterations | 7548 | +| time_elapsed | 24969 | +| total_timesteps | 7729152 | +| train/ | | +| approx_kl | 2.4602828 | +| clip_fraction | 0.467 | +| clip_range | 0.2 | +| entropy_loss | -0.307 | +| explained_variance | -7.91 | +| learning_rate | 0.0001 | +| loss | -0.126 | +| n_updates | 136000 | +| policy_gradient_loss | -0.0711 | +| value_loss | 0.000543 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.82e+03 | +| ep_rew_mean | 0.2 | +| time/ | | +| fps | 309 | +| iterations | 7549 | +| time_elapsed | 24972 | +| total_timesteps | 7730176 | +| train/ | | +| approx_kl | 2.21004 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.367 | +| explained_variance | -3.17 | +| learning_rate | 0.0001 | +| loss | -0.0731 | +| n_updates | 136010 | +| policy_gradient_loss | -0.0652 | +| value_loss | 0.000503 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.82e+03 | +| ep_rew_mean | 0.2 | +| time/ | | +| fps | 309 | +| iterations | 7550 | +| time_elapsed | 24976 | +| total_timesteps | 7731200 | +| train/ | | +| approx_kl | 3.2730722 | +| clip_fraction | 0.498 | +| clip_range | 0.2 | +| entropy_loss | -0.365 | +| explained_variance | -0.312 | +| learning_rate | 0.0001 | +| loss | -0.0687 | +| n_updates | 136020 | +| policy_gradient_loss | -0.0642 | +| value_loss | 0.000749 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.82e+03 | +| ep_rew_mean | 0.2 | +| time/ | | +| fps | 309 | +| iterations | 7551 | +| time_elapsed | 24979 | +| total_timesteps | 7732224 | +| train/ | | +| approx_kl | 4.892237 | +| clip_fraction | 0.533 | +| clip_range | 0.2 | +| entropy_loss | -0.388 | +| explained_variance | -1.71 | +| learning_rate | 0.0001 | +| loss | -0.081 | +| n_updates | 136030 | +| policy_gradient_loss | -0.0588 | +| value_loss | 0.000671 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.194 | +| time/ | | +| fps | 309 | +| iterations | 7552 | +| time_elapsed | 24982 | +| total_timesteps | 7733248 | +| train/ | | +| approx_kl | 2.5128186 | +| clip_fraction | 0.478 | +| clip_range | 0.2 | +| entropy_loss | -0.313 | +| explained_variance | -11.3 | +| learning_rate | 0.0001 | +| loss | -0.11 | +| n_updates | 136040 | +| policy_gradient_loss | -0.0727 | +| value_loss | 0.000537 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.194 | +| time/ | | +| fps | 309 | +| iterations | 7553 | +| time_elapsed | 24985 | +| total_timesteps | 7734272 | +| train/ | | +| approx_kl | 2.7853007 | +| clip_fraction | 0.467 | +| clip_range | 0.2 | +| entropy_loss | -0.333 | +| explained_variance | -2.73 | +| learning_rate | 0.0001 | +| loss | -0.109 | +| n_updates | 136050 | +| policy_gradient_loss | -0.0703 | +| value_loss | 0.000574 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.194 | +| time/ | | +| fps | 309 | +| iterations | 7554 | +| time_elapsed | 24988 | +| total_timesteps | 7735296 | +| train/ | | +| approx_kl | 2.3396325 | +| clip_fraction | 0.459 | +| clip_range | 0.2 | +| entropy_loss | -0.32 | +| explained_variance | -2.34 | +| learning_rate | 0.0001 | +| loss | -0.0923 | +| n_updates | 136060 | +| policy_gradient_loss | -0.0685 | +| value_loss | 0.000823 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.194 | +| time/ | | +| fps | 309 | +| iterations | 7555 | +| time_elapsed | 24992 | +| total_timesteps | 7736320 | +| train/ | | +| approx_kl | 2.2989845 | +| clip_fraction | 0.435 | +| clip_range | 0.2 | +| entropy_loss | -0.301 | +| explained_variance | -1.53 | +| learning_rate | 0.0001 | +| loss | -0.0763 | +| n_updates | 136070 | +| policy_gradient_loss | -0.0589 | +| value_loss | 0.000603 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.189 | +| time/ | | +| fps | 309 | +| iterations | 7556 | +| time_elapsed | 24995 | +| total_timesteps | 7737344 | +| train/ | | +| approx_kl | 3.131552 | +| clip_fraction | 0.492 | +| clip_range | 0.2 | +| entropy_loss | -0.374 | +| explained_variance | -5.61 | +| learning_rate | 0.0001 | +| loss | -0.0927 | +| n_updates | 136080 | +| policy_gradient_loss | -0.0716 | +| value_loss | 0.000362 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.189 | +| time/ | | +| fps | 309 | +| iterations | 7557 | +| time_elapsed | 24998 | +| total_timesteps | 7738368 | +| train/ | | +| approx_kl | 3.7737443 | +| clip_fraction | 0.499 | +| clip_range | 0.2 | +| entropy_loss | -0.429 | +| explained_variance | -5.31 | +| learning_rate | 0.0001 | +| loss | -0.0816 | +| n_updates | 136090 | +| policy_gradient_loss | -0.0624 | +| value_loss | 0.00018 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.182 | +| time/ | | +| fps | 309 | +| iterations | 7558 | +| time_elapsed | 25001 | +| total_timesteps | 7739392 | +| train/ | | +| approx_kl | 2.1584468 | +| clip_fraction | 0.478 | +| clip_range | 0.2 | +| entropy_loss | -0.365 | +| explained_variance | -1.32 | +| learning_rate | 0.0001 | +| loss | -0.0703 | +| n_updates | 136100 | +| policy_gradient_loss | -0.066 | +| value_loss | 0.000585 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.182 | +| time/ | | +| fps | 309 | +| iterations | 7559 | +| time_elapsed | 25005 | +| total_timesteps | 7740416 | +| train/ | | +| approx_kl | 2.083949 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.345 | +| explained_variance | -4.08 | +| learning_rate | 0.0001 | +| loss | -0.0731 | +| n_updates | 136110 | +| policy_gradient_loss | -0.0666 | +| value_loss | 0.00047 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.178 | +| time/ | | +| fps | 309 | +| iterations | 7560 | +| time_elapsed | 25008 | +| total_timesteps | 7741440 | +| train/ | | +| approx_kl | 2.537006 | +| clip_fraction | 0.45 | +| clip_range | 0.2 | +| entropy_loss | -0.307 | +| explained_variance | -1.29 | +| learning_rate | 0.0001 | +| loss | -0.0873 | +| n_updates | 136120 | +| policy_gradient_loss | -0.0646 | +| value_loss | 0.000579 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.178 | +| time/ | | +| fps | 309 | +| iterations | 7561 | +| time_elapsed | 25012 | +| total_timesteps | 7742464 | +| train/ | | +| approx_kl | 3.1467805 | +| clip_fraction | 0.434 | +| clip_range | 0.2 | +| entropy_loss | -0.294 | +| explained_variance | -6.56 | +| learning_rate | 0.0001 | +| loss | -0.0906 | +| n_updates | 136130 | +| policy_gradient_loss | -0.0593 | +| value_loss | 0.000568 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.179 | +| time/ | | +| fps | 309 | +| iterations | 7562 | +| time_elapsed | 25015 | +| total_timesteps | 7743488 | +| train/ | | +| approx_kl | 2.4663649 | +| clip_fraction | 0.505 | +| clip_range | 0.2 | +| entropy_loss | -0.365 | +| explained_variance | -1.37 | +| learning_rate | 0.0001 | +| loss | -0.109 | +| n_updates | 136140 | +| policy_gradient_loss | -0.074 | +| value_loss | 0.00047 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.179 | +| time/ | | +| fps | 309 | +| iterations | 7563 | +| time_elapsed | 25018 | +| total_timesteps | 7744512 | +| train/ | | +| approx_kl | 2.082463 | +| clip_fraction | 0.465 | +| clip_range | 0.2 | +| entropy_loss | -0.332 | +| explained_variance | -1.28 | +| learning_rate | 0.0001 | +| loss | -0.106 | +| n_updates | 136150 | +| policy_gradient_loss | -0.0685 | +| value_loss | 0.000613 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.179 | +| time/ | | +| fps | 309 | +| iterations | 7564 | +| time_elapsed | 25022 | +| total_timesteps | 7745536 | +| train/ | | +| approx_kl | 2.4669573 | +| clip_fraction | 0.438 | +| clip_range | 0.2 | +| entropy_loss | -0.31 | +| explained_variance | -3.3 | +| learning_rate | 0.0001 | +| loss | -0.099 | +| n_updates | 136160 | +| policy_gradient_loss | -0.062 | +| value_loss | 0.000508 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.181 | +| time/ | | +| fps | 309 | +| iterations | 7565 | +| time_elapsed | 25025 | +| total_timesteps | 7746560 | +| train/ | | +| approx_kl | 2.6795735 | +| clip_fraction | 0.474 | +| clip_range | 0.2 | +| entropy_loss | -0.384 | +| explained_variance | -3.33 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 136170 | +| policy_gradient_loss | -0.0657 | +| value_loss | 0.000404 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.181 | +| time/ | | +| fps | 309 | +| iterations | 7566 | +| time_elapsed | 25028 | +| total_timesteps | 7747584 | +| train/ | | +| approx_kl | 2.4063125 | +| clip_fraction | 0.464 | +| clip_range | 0.2 | +| entropy_loss | -0.342 | +| explained_variance | -1.35 | +| learning_rate | 0.0001 | +| loss | -0.0663 | +| n_updates | 136180 | +| policy_gradient_loss | -0.068 | +| value_loss | 0.000695 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.179 | +| time/ | | +| fps | 309 | +| iterations | 7567 | +| time_elapsed | 25032 | +| total_timesteps | 7748608 | +| train/ | | +| approx_kl | 2.2318106 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.34 | +| explained_variance | -2.26 | +| learning_rate | 0.0001 | +| loss | -0.078 | +| n_updates | 136190 | +| policy_gradient_loss | -0.0683 | +| value_loss | 0.000893 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.174 | +| time/ | | +| fps | 309 | +| iterations | 7568 | +| time_elapsed | 25035 | +| total_timesteps | 7749632 | +| train/ | | +| approx_kl | 2.0966434 | +| clip_fraction | 0.473 | +| clip_range | 0.2 | +| entropy_loss | -0.34 | +| explained_variance | -6.28 | +| learning_rate | 0.0001 | +| loss | -0.11 | +| n_updates | 136200 | +| policy_gradient_loss | -0.064 | +| value_loss | 0.000551 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.174 | +| time/ | | +| fps | 309 | +| iterations | 7569 | +| time_elapsed | 25038 | +| total_timesteps | 7750656 | +| train/ | | +| approx_kl | 2.70583 | +| clip_fraction | 0.452 | +| clip_range | 0.2 | +| entropy_loss | -0.338 | +| explained_variance | -1.44 | +| learning_rate | 0.0001 | +| loss | -0.109 | +| n_updates | 136210 | +| policy_gradient_loss | -0.0654 | +| value_loss | 0.000704 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.178 | +| time/ | | +| fps | 309 | +| iterations | 7570 | +| time_elapsed | 25041 | +| total_timesteps | 7751680 | +| train/ | | +| approx_kl | 2.3277984 | +| clip_fraction | 0.476 | +| clip_range | 0.2 | +| entropy_loss | -0.341 | +| explained_variance | -1.99 | +| learning_rate | 0.0001 | +| loss | -0.0659 | +| n_updates | 136220 | +| policy_gradient_loss | -0.066 | +| value_loss | 0.000828 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.178 | +| time/ | | +| fps | 309 | +| iterations | 7571 | +| time_elapsed | 25044 | +| total_timesteps | 7752704 | +| train/ | | +| approx_kl | 2.112039 | +| clip_fraction | 0.496 | +| clip_range | 0.2 | +| entropy_loss | -0.398 | +| explained_variance | -2.11 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 136230 | +| policy_gradient_loss | -0.0614 | +| value_loss | 0.000736 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.184 | +| time/ | | +| fps | 309 | +| iterations | 7572 | +| time_elapsed | 25047 | +| total_timesteps | 7753728 | +| train/ | | +| approx_kl | 2.3137884 | +| clip_fraction | 0.497 | +| clip_range | 0.2 | +| entropy_loss | -0.379 | +| explained_variance | -2.98 | +| learning_rate | 0.0001 | +| loss | -0.0949 | +| n_updates | 136240 | +| policy_gradient_loss | -0.071 | +| value_loss | 0.000743 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.189 | +| time/ | | +| fps | 309 | +| iterations | 7573 | +| time_elapsed | 25051 | +| total_timesteps | 7754752 | +| train/ | | +| approx_kl | 2.659348 | +| clip_fraction | 0.477 | +| clip_range | 0.2 | +| entropy_loss | -0.316 | +| explained_variance | -3.55 | +| learning_rate | 0.0001 | +| loss | -0.0684 | +| n_updates | 136250 | +| policy_gradient_loss | -0.0692 | +| value_loss | 0.000944 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.189 | +| time/ | | +| fps | 309 | +| iterations | 7574 | +| time_elapsed | 25054 | +| total_timesteps | 7755776 | +| train/ | | +| approx_kl | 2.8225942 | +| clip_fraction | 0.485 | +| clip_range | 0.2 | +| entropy_loss | -0.373 | +| explained_variance | -1.96 | +| learning_rate | 0.0001 | +| loss | -0.0864 | +| n_updates | 136260 | +| policy_gradient_loss | -0.07 | +| value_loss | 0.000791 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.188 | +| time/ | | +| fps | 309 | +| iterations | 7575 | +| time_elapsed | 25057 | +| total_timesteps | 7756800 | +| train/ | | +| approx_kl | 3.9108624 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.357 | +| explained_variance | -4.82 | +| learning_rate | 0.0001 | +| loss | -0.0982 | +| n_updates | 136270 | +| policy_gradient_loss | -0.0705 | +| value_loss | 0.000513 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.188 | +| time/ | | +| fps | 309 | +| iterations | 7576 | +| time_elapsed | 25060 | +| total_timesteps | 7757824 | +| train/ | | +| approx_kl | 2.3723683 | +| clip_fraction | 0.488 | +| clip_range | 0.2 | +| entropy_loss | -0.367 | +| explained_variance | -4.37 | +| learning_rate | 0.0001 | +| loss | -0.0645 | +| n_updates | 136280 | +| policy_gradient_loss | -0.0694 | +| value_loss | 0.00073 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.19 | +| time/ | | +| fps | 309 | +| iterations | 7577 | +| time_elapsed | 25064 | +| total_timesteps | 7758848 | +| train/ | | +| approx_kl | 2.6882644 | +| clip_fraction | 0.509 | +| clip_range | 0.2 | +| entropy_loss | -0.426 | +| explained_variance | -1.27 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 136290 | +| policy_gradient_loss | -0.0703 | +| value_loss | 0.000527 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.188 | +| time/ | | +| fps | 309 | +| iterations | 7578 | +| time_elapsed | 25067 | +| total_timesteps | 7759872 | +| train/ | | +| approx_kl | 2.3330564 | +| clip_fraction | 0.5 | +| clip_range | 0.2 | +| entropy_loss | -0.383 | +| explained_variance | -1.56 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 136300 | +| policy_gradient_loss | -0.0758 | +| value_loss | 0.000506 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.188 | +| time/ | | +| fps | 309 | +| iterations | 7579 | +| time_elapsed | 25071 | +| total_timesteps | 7760896 | +| train/ | | +| approx_kl | 2.0846848 | +| clip_fraction | 0.465 | +| clip_range | 0.2 | +| entropy_loss | -0.388 | +| explained_variance | -1.35 | +| learning_rate | 0.0001 | +| loss | -0.0778 | +| n_updates | 136310 | +| policy_gradient_loss | -0.064 | +| value_loss | 0.000498 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.191 | +| time/ | | +| fps | 309 | +| iterations | 7580 | +| time_elapsed | 25074 | +| total_timesteps | 7761920 | +| train/ | | +| approx_kl | 2.1882002 | +| clip_fraction | 0.458 | +| clip_range | 0.2 | +| entropy_loss | -0.311 | +| explained_variance | -1.92 | +| learning_rate | 0.0001 | +| loss | -0.1 | +| n_updates | 136320 | +| policy_gradient_loss | -0.0642 | +| value_loss | 0.000771 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.195 | +| time/ | | +| fps | 309 | +| iterations | 7581 | +| time_elapsed | 25078 | +| total_timesteps | 7762944 | +| train/ | | +| approx_kl | 2.321566 | +| clip_fraction | 0.491 | +| clip_range | 0.2 | +| entropy_loss | -0.366 | +| explained_variance | -1.51 | +| learning_rate | 0.0001 | +| loss | -0.0826 | +| n_updates | 136330 | +| policy_gradient_loss | -0.0711 | +| value_loss | 0.000709 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.189 | +| time/ | | +| fps | 309 | +| iterations | 7582 | +| time_elapsed | 25082 | +| total_timesteps | 7763968 | +| train/ | | +| approx_kl | 2.8879275 | +| clip_fraction | 0.474 | +| clip_range | 0.2 | +| entropy_loss | -0.342 | +| explained_variance | -1.16 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 136340 | +| policy_gradient_loss | -0.0618 | +| value_loss | 0.000734 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.189 | +| time/ | | +| fps | 309 | +| iterations | 7583 | +| time_elapsed | 25085 | +| total_timesteps | 7764992 | +| train/ | | +| approx_kl | 2.3479548 | +| clip_fraction | 0.421 | +| clip_range | 0.2 | +| entropy_loss | -0.293 | +| explained_variance | -4.15 | +| learning_rate | 0.0001 | +| loss | -0.0863 | +| n_updates | 136350 | +| policy_gradient_loss | -0.0623 | +| value_loss | 0.000838 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.191 | +| time/ | | +| fps | 309 | +| iterations | 7584 | +| time_elapsed | 25088 | +| total_timesteps | 7766016 | +| train/ | | +| approx_kl | 2.2501967 | +| clip_fraction | 0.508 | +| clip_range | 0.2 | +| entropy_loss | -0.406 | +| explained_variance | -1.64 | +| learning_rate | 0.0001 | +| loss | -0.0553 | +| n_updates | 136360 | +| policy_gradient_loss | -0.068 | +| value_loss | 0.000906 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.191 | +| time/ | | +| fps | 309 | +| iterations | 7585 | +| time_elapsed | 25092 | +| total_timesteps | 7767040 | +| train/ | | +| approx_kl | 2.138294 | +| clip_fraction | 0.488 | +| clip_range | 0.2 | +| entropy_loss | -0.378 | +| explained_variance | -2.65 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 136370 | +| policy_gradient_loss | -0.0646 | +| value_loss | 0.000546 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.189 | +| time/ | | +| fps | 309 | +| iterations | 7586 | +| time_elapsed | 25095 | +| total_timesteps | 7768064 | +| train/ | | +| approx_kl | 2.4365067 | +| clip_fraction | 0.49 | +| clip_range | 0.2 | +| entropy_loss | -0.399 | +| explained_variance | -4.74 | +| learning_rate | 0.0001 | +| loss | -0.0924 | +| n_updates | 136380 | +| policy_gradient_loss | -0.0723 | +| value_loss | 0.0005 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.189 | +| time/ | | +| fps | 309 | +| iterations | 7587 | +| time_elapsed | 25098 | +| total_timesteps | 7769088 | +| train/ | | +| approx_kl | 2.0767252 | +| clip_fraction | 0.514 | +| clip_range | 0.2 | +| entropy_loss | -0.418 | +| explained_variance | -3.06 | +| learning_rate | 0.0001 | +| loss | -0.0951 | +| n_updates | 136390 | +| policy_gradient_loss | -0.0702 | +| value_loss | 0.000585 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.193 | +| time/ | | +| fps | 309 | +| iterations | 7588 | +| time_elapsed | 25101 | +| total_timesteps | 7770112 | +| train/ | | +| approx_kl | 2.0324624 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.368 | +| explained_variance | -2.89 | +| learning_rate | 0.0001 | +| loss | -0.0699 | +| n_updates | 136400 | +| policy_gradient_loss | -0.0649 | +| value_loss | 0.000426 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.191 | +| time/ | | +| fps | 309 | +| iterations | 7589 | +| time_elapsed | 25104 | +| total_timesteps | 7771136 | +| train/ | | +| approx_kl | 2.6178427 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.354 | +| explained_variance | -18.9 | +| learning_rate | 0.0001 | +| loss | -0.118 | +| n_updates | 136410 | +| policy_gradient_loss | -0.0671 | +| value_loss | 0.000306 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.191 | +| time/ | | +| fps | 309 | +| iterations | 7590 | +| time_elapsed | 25107 | +| total_timesteps | 7772160 | +| train/ | | +| approx_kl | 2.1388774 | +| clip_fraction | 0.466 | +| clip_range | 0.2 | +| entropy_loss | -0.357 | +| explained_variance | -0.676 | +| learning_rate | 0.0001 | +| loss | -0.0626 | +| n_updates | 136420 | +| policy_gradient_loss | -0.0559 | +| value_loss | 0.000498 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.192 | +| time/ | | +| fps | 309 | +| iterations | 7591 | +| time_elapsed | 25111 | +| total_timesteps | 7773184 | +| train/ | | +| approx_kl | 2.1878767 | +| clip_fraction | 0.498 | +| clip_range | 0.2 | +| entropy_loss | -0.377 | +| explained_variance | -4.46 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 136430 | +| policy_gradient_loss | -0.0686 | +| value_loss | 0.000478 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.192 | +| time/ | | +| fps | 309 | +| iterations | 7592 | +| time_elapsed | 25114 | +| total_timesteps | 7774208 | +| train/ | | +| approx_kl | 2.1336067 | +| clip_fraction | 0.535 | +| clip_range | 0.2 | +| entropy_loss | -0.439 | +| explained_variance | -4.83 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 136440 | +| policy_gradient_loss | -0.0726 | +| value_loss | 0.00033 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.195 | +| time/ | | +| fps | 309 | +| iterations | 7593 | +| time_elapsed | 25117 | +| total_timesteps | 7775232 | +| train/ | | +| approx_kl | 2.1039777 | +| clip_fraction | 0.489 | +| clip_range | 0.2 | +| entropy_loss | -0.4 | +| explained_variance | -0.676 | +| learning_rate | 0.0001 | +| loss | -0.0773 | +| n_updates | 136450 | +| policy_gradient_loss | -0.0612 | +| value_loss | 0.000676 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.195 | +| time/ | | +| fps | 309 | +| iterations | 7594 | +| time_elapsed | 25120 | +| total_timesteps | 7776256 | +| train/ | | +| approx_kl | 2.1656933 | +| clip_fraction | 0.514 | +| clip_range | 0.2 | +| entropy_loss | -0.403 | +| explained_variance | -2.25 | +| learning_rate | 0.0001 | +| loss | -0.0811 | +| n_updates | 136460 | +| policy_gradient_loss | -0.0728 | +| value_loss | 0.000682 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.192 | +| time/ | | +| fps | 309 | +| iterations | 7595 | +| time_elapsed | 25124 | +| total_timesteps | 7777280 | +| train/ | | +| approx_kl | 2.0074105 | +| clip_fraction | 0.496 | +| clip_range | 0.2 | +| entropy_loss | -0.444 | +| explained_variance | -1.24 | +| learning_rate | 0.0001 | +| loss | -0.0863 | +| n_updates | 136470 | +| policy_gradient_loss | -0.067 | +| value_loss | 0.000373 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.192 | +| time/ | | +| fps | 309 | +| iterations | 7596 | +| time_elapsed | 25127 | +| total_timesteps | 7778304 | +| train/ | | +| approx_kl | 2.5200498 | +| clip_fraction | 0.502 | +| clip_range | 0.2 | +| entropy_loss | -0.411 | +| explained_variance | -0.738 | +| learning_rate | 0.0001 | +| loss | -0.0793 | +| n_updates | 136480 | +| policy_gradient_loss | -0.0657 | +| value_loss | 0.000509 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.19 | +| time/ | | +| fps | 309 | +| iterations | 7597 | +| time_elapsed | 25131 | +| total_timesteps | 7779328 | +| train/ | | +| approx_kl | 1.6846008 | +| clip_fraction | 0.46 | +| clip_range | 0.2 | +| entropy_loss | -0.398 | +| explained_variance | -1.14 | +| learning_rate | 0.0001 | +| loss | -0.0714 | +| n_updates | 136490 | +| policy_gradient_loss | -0.0552 | +| value_loss | 0.000463 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.19 | +| time/ | | +| fps | 309 | +| iterations | 7598 | +| time_elapsed | 25134 | +| total_timesteps | 7780352 | +| train/ | | +| approx_kl | 4.697893 | +| clip_fraction | 0.545 | +| clip_range | 0.2 | +| entropy_loss | -0.453 | +| explained_variance | -2.46 | +| learning_rate | 0.0001 | +| loss | -0.0552 | +| n_updates | 136500 | +| policy_gradient_loss | -0.0645 | +| value_loss | 0.000376 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.19 | +| time/ | | +| fps | 309 | +| iterations | 7599 | +| time_elapsed | 25138 | +| total_timesteps | 7781376 | +| train/ | | +| approx_kl | 2.0066063 | +| clip_fraction | 0.529 | +| clip_range | 0.2 | +| entropy_loss | -0.445 | +| explained_variance | -4.44 | +| learning_rate | 0.0001 | +| loss | -0.105 | +| n_updates | 136510 | +| policy_gradient_loss | -0.0704 | +| value_loss | 0.000343 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.191 | +| time/ | | +| fps | 309 | +| iterations | 7600 | +| time_elapsed | 25141 | +| total_timesteps | 7782400 | +| train/ | | +| approx_kl | 2.0634294 | +| clip_fraction | 0.46 | +| clip_range | 0.2 | +| entropy_loss | -0.35 | +| explained_variance | -4.53 | +| learning_rate | 0.0001 | +| loss | -0.071 | +| n_updates | 136520 | +| policy_gradient_loss | -0.0641 | +| value_loss | 0.000781 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.19 | +| time/ | | +| fps | 309 | +| iterations | 7601 | +| time_elapsed | 25145 | +| total_timesteps | 7783424 | +| train/ | | +| approx_kl | 1.9361769 | +| clip_fraction | 0.49 | +| clip_range | 0.2 | +| entropy_loss | -0.376 | +| explained_variance | -1.14 | +| learning_rate | 0.0001 | +| loss | -0.0749 | +| n_updates | 136530 | +| policy_gradient_loss | -0.0688 | +| value_loss | 0.00109 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.19 | +| time/ | | +| fps | 309 | +| iterations | 7602 | +| time_elapsed | 25148 | +| total_timesteps | 7784448 | +| train/ | | +| approx_kl | 2.4302483 | +| clip_fraction | 0.497 | +| clip_range | 0.2 | +| entropy_loss | -0.393 | +| explained_variance | -4.16 | +| learning_rate | 0.0001 | +| loss | -0.06 | +| n_updates | 136540 | +| policy_gradient_loss | -0.0703 | +| value_loss | 0.000847 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.188 | +| time/ | | +| fps | 309 | +| iterations | 7603 | +| time_elapsed | 25152 | +| total_timesteps | 7785472 | +| train/ | | +| approx_kl | 2.2824128 | +| clip_fraction | 0.511 | +| clip_range | 0.2 | +| entropy_loss | -0.403 | +| explained_variance | -2.35 | +| learning_rate | 0.0001 | +| loss | -0.115 | +| n_updates | 136550 | +| policy_gradient_loss | -0.0754 | +| value_loss | 0.000668 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.188 | +| time/ | | +| fps | 309 | +| iterations | 7604 | +| time_elapsed | 25155 | +| total_timesteps | 7786496 | +| train/ | | +| approx_kl | 2.0764074 | +| clip_fraction | 0.5 | +| clip_range | 0.2 | +| entropy_loss | -0.366 | +| explained_variance | -1.84 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 136560 | +| policy_gradient_loss | -0.0711 | +| value_loss | 0.000449 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.193 | +| time/ | | +| fps | 309 | +| iterations | 7605 | +| time_elapsed | 25158 | +| total_timesteps | 7787520 | +| train/ | | +| approx_kl | 2.0675058 | +| clip_fraction | 0.506 | +| clip_range | 0.2 | +| entropy_loss | -0.384 | +| explained_variance | -1.55 | +| learning_rate | 0.0001 | +| loss | -0.0359 | +| n_updates | 136570 | +| policy_gradient_loss | -0.0698 | +| value_loss | 0.000757 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.188 | +| time/ | | +| fps | 309 | +| iterations | 7606 | +| time_elapsed | 25161 | +| total_timesteps | 7788544 | +| train/ | | +| approx_kl | 3.2368743 | +| clip_fraction | 0.524 | +| clip_range | 0.2 | +| entropy_loss | -0.424 | +| explained_variance | -2.57 | +| learning_rate | 0.0001 | +| loss | -0.0778 | +| n_updates | 136580 | +| policy_gradient_loss | -0.0661 | +| value_loss | 0.000502 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.187 | +| time/ | | +| fps | 309 | +| iterations | 7607 | +| time_elapsed | 25164 | +| total_timesteps | 7789568 | +| train/ | | +| approx_kl | 2.522174 | +| clip_fraction | 0.5 | +| clip_range | 0.2 | +| entropy_loss | -0.352 | +| explained_variance | -6.95 | +| learning_rate | 0.0001 | +| loss | -0.0878 | +| n_updates | 136590 | +| policy_gradient_loss | -0.0684 | +| value_loss | 0.000285 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.187 | +| time/ | | +| fps | 309 | +| iterations | 7608 | +| time_elapsed | 25167 | +| total_timesteps | 7790592 | +| train/ | | +| approx_kl | 1.8751704 | +| clip_fraction | 0.454 | +| clip_range | 0.2 | +| entropy_loss | -0.343 | +| explained_variance | -1.53 | +| learning_rate | 0.0001 | +| loss | -0.0924 | +| n_updates | 136600 | +| policy_gradient_loss | -0.0619 | +| value_loss | 0.000529 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.187 | +| time/ | | +| fps | 309 | +| iterations | 7609 | +| time_elapsed | 25170 | +| total_timesteps | 7791616 | +| train/ | | +| approx_kl | 2.259232 | +| clip_fraction | 0.49 | +| clip_range | 0.2 | +| entropy_loss | -0.386 | +| explained_variance | -0.776 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 136610 | +| policy_gradient_loss | -0.0653 | +| value_loss | 0.000845 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.181 | +| time/ | | +| fps | 309 | +| iterations | 7610 | +| time_elapsed | 25174 | +| total_timesteps | 7792640 | +| train/ | | +| approx_kl | 4.3189564 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.374 | +| explained_variance | -3.98 | +| learning_rate | 0.0001 | +| loss | -0.0646 | +| n_updates | 136620 | +| policy_gradient_loss | -0.0644 | +| value_loss | 0.000334 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.183 | +| time/ | | +| fps | 309 | +| iterations | 7611 | +| time_elapsed | 25177 | +| total_timesteps | 7793664 | +| train/ | | +| approx_kl | 3.172206 | +| clip_fraction | 0.477 | +| clip_range | 0.2 | +| entropy_loss | -0.363 | +| explained_variance | -0.927 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 136630 | +| policy_gradient_loss | -0.0658 | +| value_loss | 0.000886 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.183 | +| time/ | | +| fps | 309 | +| iterations | 7612 | +| time_elapsed | 25180 | +| total_timesteps | 7794688 | +| train/ | | +| approx_kl | 2.018296 | +| clip_fraction | 0.474 | +| clip_range | 0.2 | +| entropy_loss | -0.389 | +| explained_variance | -1.23 | +| learning_rate | 0.0001 | +| loss | -0.0655 | +| n_updates | 136640 | +| policy_gradient_loss | -0.0683 | +| value_loss | 0.000468 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.186 | +| time/ | | +| fps | 309 | +| iterations | 7613 | +| time_elapsed | 25184 | +| total_timesteps | 7795712 | +| train/ | | +| approx_kl | 1.8354784 | +| clip_fraction | 0.478 | +| clip_range | 0.2 | +| entropy_loss | -0.381 | +| explained_variance | -5.79 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 136650 | +| policy_gradient_loss | -0.0682 | +| value_loss | 0.000359 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.186 | +| time/ | | +| fps | 309 | +| iterations | 7614 | +| time_elapsed | 25187 | +| total_timesteps | 7796736 | +| train/ | | +| approx_kl | 2.4467897 | +| clip_fraction | 0.454 | +| clip_range | 0.2 | +| entropy_loss | -0.362 | +| explained_variance | -0.809 | +| learning_rate | 0.0001 | +| loss | -0.0864 | +| n_updates | 136660 | +| policy_gradient_loss | -0.0653 | +| value_loss | 0.000475 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.187 | +| time/ | | +| fps | 309 | +| iterations | 7615 | +| time_elapsed | 25190 | +| total_timesteps | 7797760 | +| train/ | | +| approx_kl | 2.0421119 | +| clip_fraction | 0.496 | +| clip_range | 0.2 | +| entropy_loss | -0.396 | +| explained_variance | -5.21 | +| learning_rate | 0.0001 | +| loss | -0.0984 | +| n_updates | 136670 | +| policy_gradient_loss | -0.0723 | +| value_loss | 0.000623 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.191 | +| time/ | | +| fps | 309 | +| iterations | 7616 | +| time_elapsed | 25194 | +| total_timesteps | 7798784 | +| train/ | | +| approx_kl | 4.382224 | +| clip_fraction | 0.49 | +| clip_range | 0.2 | +| entropy_loss | -0.381 | +| explained_variance | -1.08 | +| learning_rate | 0.0001 | +| loss | -0.0837 | +| n_updates | 136680 | +| policy_gradient_loss | -0.0673 | +| value_loss | 0.000561 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.191 | +| time/ | | +| fps | 309 | +| iterations | 7617 | +| time_elapsed | 25197 | +| total_timesteps | 7799808 | +| train/ | | +| approx_kl | 2.1762676 | +| clip_fraction | 0.467 | +| clip_range | 0.2 | +| entropy_loss | -0.356 | +| explained_variance | -1.84 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 136690 | +| policy_gradient_loss | -0.0675 | +| value_loss | 0.000733 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.196 | +| time/ | | +| fps | 309 | +| iterations | 7618 | +| time_elapsed | 25201 | +| total_timesteps | 7800832 | +| train/ | | +| approx_kl | 2.5097713 | +| clip_fraction | 0.523 | +| clip_range | 0.2 | +| entropy_loss | -0.429 | +| explained_variance | -1.44 | +| learning_rate | 0.0001 | +| loss | -0.077 | +| n_updates | 136700 | +| policy_gradient_loss | -0.07 | +| value_loss | 0.000868 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.196 | +| time/ | | +| fps | 309 | +| iterations | 7619 | +| time_elapsed | 25204 | +| total_timesteps | 7801856 | +| train/ | | +| approx_kl | 2.3121645 | +| clip_fraction | 0.482 | +| clip_range | 0.2 | +| entropy_loss | -0.354 | +| explained_variance | -2.33 | +| learning_rate | 0.0001 | +| loss | -0.0825 | +| n_updates | 136710 | +| policy_gradient_loss | -0.069 | +| value_loss | 0.000586 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.196 | +| time/ | | +| fps | 309 | +| iterations | 7620 | +| time_elapsed | 25208 | +| total_timesteps | 7802880 | +| train/ | | +| approx_kl | 2.7471843 | +| clip_fraction | 0.507 | +| clip_range | 0.2 | +| entropy_loss | -0.35 | +| explained_variance | -2.28 | +| learning_rate | 0.0001 | +| loss | -0.096 | +| n_updates | 136720 | +| policy_gradient_loss | -0.0678 | +| value_loss | 0.000595 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.196 | +| time/ | | +| fps | 309 | +| iterations | 7621 | +| time_elapsed | 25211 | +| total_timesteps | 7803904 | +| train/ | | +| approx_kl | 2.4537873 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.349 | +| explained_variance | -7.92 | +| learning_rate | 0.0001 | +| loss | -0.0917 | +| n_updates | 136730 | +| policy_gradient_loss | -0.0693 | +| value_loss | 0.000458 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.196 | +| time/ | | +| fps | 309 | +| iterations | 7622 | +| time_elapsed | 25214 | +| total_timesteps | 7804928 | +| train/ | | +| approx_kl | 2.573964 | +| clip_fraction | 0.462 | +| clip_range | 0.2 | +| entropy_loss | -0.352 | +| explained_variance | -2.03 | +| learning_rate | 0.0001 | +| loss | -0.0908 | +| n_updates | 136740 | +| policy_gradient_loss | -0.0616 | +| value_loss | 0.000599 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.198 | +| time/ | | +| fps | 309 | +| iterations | 7623 | +| time_elapsed | 25218 | +| total_timesteps | 7805952 | +| train/ | | +| approx_kl | 2.261687 | +| clip_fraction | 0.482 | +| clip_range | 0.2 | +| entropy_loss | -0.388 | +| explained_variance | -1.95 | +| learning_rate | 0.0001 | +| loss | -0.0842 | +| n_updates | 136750 | +| policy_gradient_loss | -0.0639 | +| value_loss | 0.000512 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.198 | +| time/ | | +| fps | 309 | +| iterations | 7624 | +| time_elapsed | 25221 | +| total_timesteps | 7806976 | +| train/ | | +| approx_kl | 2.6115801 | +| clip_fraction | 0.47 | +| clip_range | 0.2 | +| entropy_loss | -0.361 | +| explained_variance | -1.29 | +| learning_rate | 0.0001 | +| loss | -0.0965 | +| n_updates | 136760 | +| policy_gradient_loss | -0.0679 | +| value_loss | 0.000876 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.201 | +| time/ | | +| fps | 309 | +| iterations | 7625 | +| time_elapsed | 25224 | +| total_timesteps | 7808000 | +| train/ | | +| approx_kl | 2.3303633 | +| clip_fraction | 0.51 | +| clip_range | 0.2 | +| entropy_loss | -0.411 | +| explained_variance | -1.85 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 136770 | +| policy_gradient_loss | -0.0746 | +| value_loss | 0.000499 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.201 | +| time/ | | +| fps | 309 | +| iterations | 7626 | +| time_elapsed | 25227 | +| total_timesteps | 7809024 | +| train/ | | +| approx_kl | 2.187404 | +| clip_fraction | 0.478 | +| clip_range | 0.2 | +| entropy_loss | -0.414 | +| explained_variance | -4.08 | +| learning_rate | 0.0001 | +| loss | -0.0935 | +| n_updates | 136780 | +| policy_gradient_loss | -0.0673 | +| value_loss | 0.000295 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.2 | +| time/ | | +| fps | 309 | +| iterations | 7627 | +| time_elapsed | 25231 | +| total_timesteps | 7810048 | +| train/ | | +| approx_kl | 2.4256575 | +| clip_fraction | 0.493 | +| clip_range | 0.2 | +| entropy_loss | -0.382 | +| explained_variance | -0.881 | +| learning_rate | 0.0001 | +| loss | -0.0816 | +| n_updates | 136790 | +| policy_gradient_loss | -0.0716 | +| value_loss | 0.000425 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.201 | +| time/ | | +| fps | 309 | +| iterations | 7628 | +| time_elapsed | 25234 | +| total_timesteps | 7811072 | +| train/ | | +| approx_kl | 2.2326684 | +| clip_fraction | 0.454 | +| clip_range | 0.2 | +| entropy_loss | -0.337 | +| explained_variance | -1.75 | +| learning_rate | 0.0001 | +| loss | -0.0749 | +| n_updates | 136800 | +| policy_gradient_loss | -0.0638 | +| value_loss | 0.000545 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.202 | +| time/ | | +| fps | 309 | +| iterations | 7629 | +| time_elapsed | 25237 | +| total_timesteps | 7812096 | +| train/ | | +| approx_kl | 2.370751 | +| clip_fraction | 0.461 | +| clip_range | 0.2 | +| entropy_loss | -0.365 | +| explained_variance | -2.19 | +| learning_rate | 0.0001 | +| loss | -0.0764 | +| n_updates | 136810 | +| policy_gradient_loss | -0.0704 | +| value_loss | 0.000486 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.205 | +| time/ | | +| fps | 309 | +| iterations | 7630 | +| time_elapsed | 25240 | +| total_timesteps | 7813120 | +| train/ | | +| approx_kl | 2.6473503 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.35 | +| explained_variance | -0.468 | +| learning_rate | 0.0001 | +| loss | -0.0766 | +| n_updates | 136820 | +| policy_gradient_loss | -0.0579 | +| value_loss | 0.000889 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.205 | +| time/ | | +| fps | 309 | +| iterations | 7631 | +| time_elapsed | 25244 | +| total_timesteps | 7814144 | +| train/ | | +| approx_kl | 2.3997433 | +| clip_fraction | 0.476 | +| clip_range | 0.2 | +| entropy_loss | -0.372 | +| explained_variance | -1.86 | +| learning_rate | 0.0001 | +| loss | -0.0925 | +| n_updates | 136830 | +| policy_gradient_loss | -0.0664 | +| value_loss | 0.000749 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.208 | +| time/ | | +| fps | 309 | +| iterations | 7632 | +| time_elapsed | 25247 | +| total_timesteps | 7815168 | +| train/ | | +| approx_kl | 4.5551314 | +| clip_fraction | 0.484 | +| clip_range | 0.2 | +| entropy_loss | -0.368 | +| explained_variance | -1.22 | +| learning_rate | 0.0001 | +| loss | -0.0753 | +| n_updates | 136840 | +| policy_gradient_loss | -0.0688 | +| value_loss | 0.000739 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.208 | +| time/ | | +| fps | 309 | +| iterations | 7633 | +| time_elapsed | 25250 | +| total_timesteps | 7816192 | +| train/ | | +| approx_kl | 2.4992082 | +| clip_fraction | 0.46 | +| clip_range | 0.2 | +| entropy_loss | -0.299 | +| explained_variance | -5.62 | +| learning_rate | 0.0001 | +| loss | -0.112 | +| n_updates | 136850 | +| policy_gradient_loss | -0.0631 | +| value_loss | 0.00054 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.208 | +| time/ | | +| fps | 309 | +| iterations | 7634 | +| time_elapsed | 25254 | +| total_timesteps | 7817216 | +| train/ | | +| approx_kl | 2.6569993 | +| clip_fraction | 0.477 | +| clip_range | 0.2 | +| entropy_loss | -0.349 | +| explained_variance | -1.97 | +| learning_rate | 0.0001 | +| loss | -0.0905 | +| n_updates | 136860 | +| policy_gradient_loss | -0.0679 | +| value_loss | 0.000386 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.208 | +| time/ | | +| fps | 309 | +| iterations | 7635 | +| time_elapsed | 25257 | +| total_timesteps | 7818240 | +| train/ | | +| approx_kl | 4.9833155 | +| clip_fraction | 0.51 | +| clip_range | 0.2 | +| entropy_loss | -0.398 | +| explained_variance | -1.17 | +| learning_rate | 0.0001 | +| loss | -0.0797 | +| n_updates | 136870 | +| policy_gradient_loss | -0.071 | +| value_loss | 0.00054 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.208 | +| time/ | | +| fps | 309 | +| iterations | 7636 | +| time_elapsed | 25261 | +| total_timesteps | 7819264 | +| train/ | | +| approx_kl | 2.2910643 | +| clip_fraction | 0.492 | +| clip_range | 0.2 | +| entropy_loss | -0.393 | +| explained_variance | -1.63 | +| learning_rate | 0.0001 | +| loss | -0.0562 | +| n_updates | 136880 | +| policy_gradient_loss | -0.0685 | +| value_loss | 0.000668 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.207 | +| time/ | | +| fps | 309 | +| iterations | 7637 | +| time_elapsed | 25264 | +| total_timesteps | 7820288 | +| train/ | | +| approx_kl | 2.114472 | +| clip_fraction | 0.472 | +| clip_range | 0.2 | +| entropy_loss | -0.364 | +| explained_variance | -3.26 | +| learning_rate | 0.0001 | +| loss | -0.0976 | +| n_updates | 136890 | +| policy_gradient_loss | -0.0675 | +| value_loss | 0.000629 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.207 | +| time/ | | +| fps | 309 | +| iterations | 7638 | +| time_elapsed | 25268 | +| total_timesteps | 7821312 | +| train/ | | +| approx_kl | 2.343249 | +| clip_fraction | 0.467 | +| clip_range | 0.2 | +| entropy_loss | -0.368 | +| explained_variance | -2.88 | +| learning_rate | 0.0001 | +| loss | -0.105 | +| n_updates | 136900 | +| policy_gradient_loss | -0.0687 | +| value_loss | 0.000494 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.205 | +| time/ | | +| fps | 309 | +| iterations | 7639 | +| time_elapsed | 25271 | +| total_timesteps | 7822336 | +| train/ | | +| approx_kl | 2.7239304 | +| clip_fraction | 0.499 | +| clip_range | 0.2 | +| entropy_loss | -0.371 | +| explained_variance | -9.3 | +| learning_rate | 0.0001 | +| loss | -0.0972 | +| n_updates | 136910 | +| policy_gradient_loss | -0.071 | +| value_loss | 0.000498 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.196 | +| time/ | | +| fps | 309 | +| iterations | 7640 | +| time_elapsed | 25274 | +| total_timesteps | 7823360 | +| train/ | | +| approx_kl | 2.065864 | +| clip_fraction | 0.474 | +| clip_range | 0.2 | +| entropy_loss | -0.4 | +| explained_variance | -0.961 | +| learning_rate | 0.0001 | +| loss | -0.0898 | +| n_updates | 136920 | +| policy_gradient_loss | -0.0695 | +| value_loss | 0.00056 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.196 | +| time/ | | +| fps | 309 | +| iterations | 7641 | +| time_elapsed | 25277 | +| total_timesteps | 7824384 | +| train/ | | +| approx_kl | 1.8364968 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.381 | +| explained_variance | -2.67 | +| learning_rate | 0.0001 | +| loss | -0.0758 | +| n_updates | 136930 | +| policy_gradient_loss | -0.0683 | +| value_loss | 0.000517 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.196 | +| time/ | | +| fps | 309 | +| iterations | 7642 | +| time_elapsed | 25280 | +| total_timesteps | 7825408 | +| train/ | | +| approx_kl | 1.7256942 | +| clip_fraction | 0.513 | +| clip_range | 0.2 | +| entropy_loss | -0.433 | +| explained_variance | -6.81 | +| learning_rate | 0.0001 | +| loss | -0.098 | +| n_updates | 136940 | +| policy_gradient_loss | -0.0694 | +| value_loss | 0.000571 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.198 | +| time/ | | +| fps | 309 | +| iterations | 7643 | +| time_elapsed | 25283 | +| total_timesteps | 7826432 | +| train/ | | +| approx_kl | 2.4709826 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.356 | +| explained_variance | -3.55 | +| learning_rate | 0.0001 | +| loss | -0.097 | +| n_updates | 136950 | +| policy_gradient_loss | -0.0737 | +| value_loss | 0.000932 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.198 | +| time/ | | +| fps | 309 | +| iterations | 7644 | +| time_elapsed | 25287 | +| total_timesteps | 7827456 | +| train/ | | +| approx_kl | 2.2321844 | +| clip_fraction | 0.462 | +| clip_range | 0.2 | +| entropy_loss | -0.331 | +| explained_variance | -2.62 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 136960 | +| policy_gradient_loss | -0.0674 | +| value_loss | 0.000839 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.199 | +| time/ | | +| fps | 309 | +| iterations | 7645 | +| time_elapsed | 25290 | +| total_timesteps | 7828480 | +| train/ | | +| approx_kl | 2.2777257 | +| clip_fraction | 0.514 | +| clip_range | 0.2 | +| entropy_loss | -0.406 | +| explained_variance | -7.97 | +| learning_rate | 0.0001 | +| loss | -0.105 | +| n_updates | 136970 | +| policy_gradient_loss | -0.0656 | +| value_loss | 0.000403 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.199 | +| time/ | | +| fps | 309 | +| iterations | 7646 | +| time_elapsed | 25293 | +| total_timesteps | 7829504 | +| train/ | | +| approx_kl | 2.4447937 | +| clip_fraction | 0.526 | +| clip_range | 0.2 | +| entropy_loss | -0.461 | +| explained_variance | -1.78 | +| learning_rate | 0.0001 | +| loss | -0.0819 | +| n_updates | 136980 | +| policy_gradient_loss | -0.074 | +| value_loss | 0.000402 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.197 | +| time/ | | +| fps | 309 | +| iterations | 7647 | +| time_elapsed | 25296 | +| total_timesteps | 7830528 | +| train/ | | +| approx_kl | 2.492476 | +| clip_fraction | 0.514 | +| clip_range | 0.2 | +| entropy_loss | -0.396 | +| explained_variance | -0.777 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 136990 | +| policy_gradient_loss | -0.0682 | +| value_loss | 0.000882 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.197 | +| time/ | | +| fps | 309 | +| iterations | 7648 | +| time_elapsed | 25299 | +| total_timesteps | 7831552 | +| train/ | | +| approx_kl | 1.9397448 | +| clip_fraction | 0.448 | +| clip_range | 0.2 | +| entropy_loss | -0.311 | +| explained_variance | -2 | +| learning_rate | 0.0001 | +| loss | -0.084 | +| n_updates | 137000 | +| policy_gradient_loss | -0.0601 | +| value_loss | 0.000872 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.82e+03 | +| ep_rew_mean | 0.194 | +| time/ | | +| fps | 309 | +| iterations | 7649 | +| time_elapsed | 25303 | +| total_timesteps | 7832576 | +| train/ | | +| approx_kl | 2.1735961 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.387 | +| explained_variance | -1.88 | +| learning_rate | 0.0001 | +| loss | -0.113 | +| n_updates | 137010 | +| policy_gradient_loss | -0.0681 | +| value_loss | 0.000617 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.82e+03 | +| ep_rew_mean | 0.195 | +| time/ | | +| fps | 309 | +| iterations | 7650 | +| time_elapsed | 25306 | +| total_timesteps | 7833600 | +| train/ | | +| approx_kl | 2.3450344 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.365 | +| explained_variance | -2.27 | +| learning_rate | 0.0001 | +| loss | -0.0831 | +| n_updates | 137020 | +| policy_gradient_loss | -0.0648 | +| value_loss | 0.00041 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.82e+03 | +| ep_rew_mean | 0.195 | +| time/ | | +| fps | 309 | +| iterations | 7651 | +| time_elapsed | 25310 | +| total_timesteps | 7834624 | +| train/ | | +| approx_kl | 2.3119462 | +| clip_fraction | 0.486 | +| clip_range | 0.2 | +| entropy_loss | -0.376 | +| explained_variance | -1.11 | +| learning_rate | 0.0001 | +| loss | -0.0967 | +| n_updates | 137030 | +| policy_gradient_loss | -0.0696 | +| value_loss | 0.000705 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.203 | +| time/ | | +| fps | 309 | +| iterations | 7652 | +| time_elapsed | 25313 | +| total_timesteps | 7835648 | +| train/ | | +| approx_kl | 1.9575367 | +| clip_fraction | 0.474 | +| clip_range | 0.2 | +| entropy_loss | -0.421 | +| explained_variance | -4.03 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 137040 | +| policy_gradient_loss | -0.07 | +| value_loss | 0.000584 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.203 | +| time/ | | +| fps | 309 | +| iterations | 7653 | +| time_elapsed | 25317 | +| total_timesteps | 7836672 | +| train/ | | +| approx_kl | 2.5484962 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.368 | +| explained_variance | -1.91 | +| learning_rate | 0.0001 | +| loss | -0.0549 | +| n_updates | 137050 | +| policy_gradient_loss | -0.0676 | +| value_loss | 0.000592 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.81e+03 | +| ep_rew_mean | 0.205 | +| time/ | | +| fps | 309 | +| iterations | 7654 | +| time_elapsed | 25320 | +| total_timesteps | 7837696 | +| train/ | | +| approx_kl | 2.22892 | +| clip_fraction | 0.459 | +| clip_range | 0.2 | +| entropy_loss | -0.341 | +| explained_variance | -1.57 | +| learning_rate | 0.0001 | +| loss | -0.0982 | +| n_updates | 137060 | +| policy_gradient_loss | -0.0636 | +| value_loss | 0.00104 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.81e+03 | +| ep_rew_mean | 0.205 | +| time/ | | +| fps | 309 | +| iterations | 7655 | +| time_elapsed | 25324 | +| total_timesteps | 7838720 | +| train/ | | +| approx_kl | 16.559338 | +| clip_fraction | 0.495 | +| clip_range | 0.2 | +| entropy_loss | -0.373 | +| explained_variance | -2.51 | +| learning_rate | 0.0001 | +| loss | -0.0876 | +| n_updates | 137070 | +| policy_gradient_loss | -0.0655 | +| value_loss | 0.00107 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.81e+03 | +| ep_rew_mean | 0.205 | +| time/ | | +| fps | 309 | +| iterations | 7656 | +| time_elapsed | 25327 | +| total_timesteps | 7839744 | +| train/ | | +| approx_kl | 2.7369363 | +| clip_fraction | 0.502 | +| clip_range | 0.2 | +| entropy_loss | -0.342 | +| explained_variance | -4.32 | +| learning_rate | 0.0001 | +| loss | -0.0975 | +| n_updates | 137080 | +| policy_gradient_loss | -0.0728 | +| value_loss | 0.000674 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.81e+03 | +| ep_rew_mean | 0.203 | +| time/ | | +| fps | 309 | +| iterations | 7657 | +| time_elapsed | 25330 | +| total_timesteps | 7840768 | +| train/ | | +| approx_kl | 2.3452954 | +| clip_fraction | 0.457 | +| clip_range | 0.2 | +| entropy_loss | -0.308 | +| explained_variance | -1.95 | +| learning_rate | 0.0001 | +| loss | -0.0906 | +| n_updates | 137090 | +| policy_gradient_loss | -0.0683 | +| value_loss | 0.000461 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.81e+03 | +| ep_rew_mean | 0.203 | +| time/ | | +| fps | 309 | +| iterations | 7658 | +| time_elapsed | 25334 | +| total_timesteps | 7841792 | +| train/ | | +| approx_kl | 3.3630254 | +| clip_fraction | 0.478 | +| clip_range | 0.2 | +| entropy_loss | -0.313 | +| explained_variance | -3.77 | +| learning_rate | 0.0001 | +| loss | -0.0951 | +| n_updates | 137100 | +| policy_gradient_loss | -0.0674 | +| value_loss | 0.000802 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.81e+03 | +| ep_rew_mean | 0.206 | +| time/ | | +| fps | 309 | +| iterations | 7659 | +| time_elapsed | 25337 | +| total_timesteps | 7842816 | +| train/ | | +| approx_kl | 2.8584998 | +| clip_fraction | 0.499 | +| clip_range | 0.2 | +| entropy_loss | -0.349 | +| explained_variance | -1.14 | +| learning_rate | 0.0001 | +| loss | -0.0924 | +| n_updates | 137110 | +| policy_gradient_loss | -0.0664 | +| value_loss | 0.000633 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.81e+03 | +| ep_rew_mean | 0.206 | +| time/ | | +| fps | 309 | +| iterations | 7660 | +| time_elapsed | 25340 | +| total_timesteps | 7843840 | +| train/ | | +| approx_kl | 2.2033486 | +| clip_fraction | 0.46 | +| clip_range | 0.2 | +| entropy_loss | -0.334 | +| explained_variance | -1.22 | +| learning_rate | 0.0001 | +| loss | -0.0586 | +| n_updates | 137120 | +| policy_gradient_loss | -0.0658 | +| value_loss | 0.0007 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.81e+03 | +| ep_rew_mean | 0.206 | +| time/ | | +| fps | 309 | +| iterations | 7661 | +| time_elapsed | 25343 | +| total_timesteps | 7844864 | +| train/ | | +| approx_kl | 1.8868698 | +| clip_fraction | 0.502 | +| clip_range | 0.2 | +| entropy_loss | -0.425 | +| explained_variance | -2.05 | +| learning_rate | 0.0001 | +| loss | -0.0953 | +| n_updates | 137130 | +| policy_gradient_loss | -0.072 | +| value_loss | 0.000411 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.81e+03 | +| ep_rew_mean | 0.206 | +| time/ | | +| fps | 309 | +| iterations | 7662 | +| time_elapsed | 25346 | +| total_timesteps | 7845888 | +| train/ | | +| approx_kl | 2.4286804 | +| clip_fraction | 0.491 | +| clip_range | 0.2 | +| entropy_loss | -0.371 | +| explained_variance | -0.818 | +| learning_rate | 0.0001 | +| loss | -0.084 | +| n_updates | 137140 | +| policy_gradient_loss | -0.0629 | +| value_loss | 0.0005 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.81e+03 | +| ep_rew_mean | 0.206 | +| time/ | | +| fps | 309 | +| iterations | 7663 | +| time_elapsed | 25350 | +| total_timesteps | 7846912 | +| train/ | | +| approx_kl | 2.494667 | +| clip_fraction | 0.473 | +| clip_range | 0.2 | +| entropy_loss | -0.352 | +| explained_variance | -2.13 | +| learning_rate | 0.0001 | +| loss | -0.106 | +| n_updates | 137150 | +| policy_gradient_loss | -0.0734 | +| value_loss | 0.000819 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.82e+03 | +| ep_rew_mean | 0.21 | +| time/ | | +| fps | 309 | +| iterations | 7664 | +| time_elapsed | 25353 | +| total_timesteps | 7847936 | +| train/ | | +| approx_kl | 2.5961814 | +| clip_fraction | 0.463 | +| clip_range | 0.2 | +| entropy_loss | -0.354 | +| explained_variance | -2.07 | +| learning_rate | 0.0001 | +| loss | -0.0602 | +| n_updates | 137160 | +| policy_gradient_loss | -0.0614 | +| value_loss | 0.000517 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.82e+03 | +| ep_rew_mean | 0.21 | +| time/ | | +| fps | 309 | +| iterations | 7665 | +| time_elapsed | 25356 | +| total_timesteps | 7848960 | +| train/ | | +| approx_kl | 4.0296597 | +| clip_fraction | 0.463 | +| clip_range | 0.2 | +| entropy_loss | -0.33 | +| explained_variance | -4.79 | +| learning_rate | 0.0001 | +| loss | -0.1 | +| n_updates | 137170 | +| policy_gradient_loss | -0.0712 | +| value_loss | 0.000617 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.8e+03 | +| ep_rew_mean | 0.21 | +| time/ | | +| fps | 309 | +| iterations | 7666 | +| time_elapsed | 25359 | +| total_timesteps | 7849984 | +| train/ | | +| approx_kl | 2.406115 | +| clip_fraction | 0.513 | +| clip_range | 0.2 | +| entropy_loss | -0.389 | +| explained_variance | -1.04 | +| learning_rate | 0.0001 | +| loss | -0.0764 | +| n_updates | 137180 | +| policy_gradient_loss | -0.0616 | +| value_loss | 0.000473 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.81e+03 | +| ep_rew_mean | 0.216 | +| time/ | | +| fps | 309 | +| iterations | 7667 | +| time_elapsed | 25362 | +| total_timesteps | 7851008 | +| train/ | | +| approx_kl | 2.337697 | +| clip_fraction | 0.477 | +| clip_range | 0.2 | +| entropy_loss | -0.359 | +| explained_variance | -1.55 | +| learning_rate | 0.0001 | +| loss | -0.0795 | +| n_updates | 137190 | +| policy_gradient_loss | -0.0562 | +| value_loss | 0.000815 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.8e+03 | +| ep_rew_mean | 0.212 | +| time/ | | +| fps | 309 | +| iterations | 7668 | +| time_elapsed | 25366 | +| total_timesteps | 7852032 | +| train/ | | +| approx_kl | 3.0952046 | +| clip_fraction | 0.482 | +| clip_range | 0.2 | +| entropy_loss | -0.322 | +| explained_variance | -1.75 | +| learning_rate | 0.0001 | +| loss | -0.0947 | +| n_updates | 137200 | +| policy_gradient_loss | -0.0638 | +| value_loss | 0.000922 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.8e+03 | +| ep_rew_mean | 0.212 | +| time/ | | +| fps | 309 | +| iterations | 7669 | +| time_elapsed | 25369 | +| total_timesteps | 7853056 | +| train/ | | +| approx_kl | 3.2075207 | +| clip_fraction | 0.461 | +| clip_range | 0.2 | +| entropy_loss | -0.383 | +| explained_variance | -2.21 | +| learning_rate | 0.0001 | +| loss | -0.0826 | +| n_updates | 137210 | +| policy_gradient_loss | -0.0629 | +| value_loss | 0.000656 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.211 | +| time/ | | +| fps | 309 | +| iterations | 7670 | +| time_elapsed | 25372 | +| total_timesteps | 7854080 | +| train/ | | +| approx_kl | 2.3443193 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.321 | +| explained_variance | -1.51 | +| learning_rate | 0.0001 | +| loss | -0.0633 | +| n_updates | 137220 | +| policy_gradient_loss | -0.064 | +| value_loss | 0.000809 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.211 | +| time/ | | +| fps | 309 | +| iterations | 7671 | +| time_elapsed | 25376 | +| total_timesteps | 7855104 | +| train/ | | +| approx_kl | 2.8017912 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.322 | +| explained_variance | -3.3 | +| learning_rate | 0.0001 | +| loss | -0.0765 | +| n_updates | 137230 | +| policy_gradient_loss | -0.0719 | +| value_loss | 0.000636 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.206 | +| time/ | | +| fps | 309 | +| iterations | 7672 | +| time_elapsed | 25379 | +| total_timesteps | 7856128 | +| train/ | | +| approx_kl | 2.4712658 | +| clip_fraction | 0.476 | +| clip_range | 0.2 | +| entropy_loss | -0.33 | +| explained_variance | -5.08 | +| learning_rate | 0.0001 | +| loss | -0.12 | +| n_updates | 137240 | +| policy_gradient_loss | -0.0712 | +| value_loss | 0.000486 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.206 | +| time/ | | +| fps | 309 | +| iterations | 7673 | +| time_elapsed | 25382 | +| total_timesteps | 7857152 | +| train/ | | +| approx_kl | 2.13739 | +| clip_fraction | 0.444 | +| clip_range | 0.2 | +| entropy_loss | -0.313 | +| explained_variance | -1.32 | +| learning_rate | 0.0001 | +| loss | -0.111 | +| n_updates | 137250 | +| policy_gradient_loss | -0.0638 | +| value_loss | 0.000323 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.8e+03 | +| ep_rew_mean | 0.21 | +| time/ | | +| fps | 309 | +| iterations | 7674 | +| time_elapsed | 25386 | +| total_timesteps | 7858176 | +| train/ | | +| approx_kl | 2.3373098 | +| clip_fraction | 0.465 | +| clip_range | 0.2 | +| entropy_loss | -0.33 | +| explained_variance | -2.11 | +| learning_rate | 0.0001 | +| loss | -0.072 | +| n_updates | 137260 | +| policy_gradient_loss | -0.0632 | +| value_loss | 0.00059 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.211 | +| time/ | | +| fps | 309 | +| iterations | 7675 | +| time_elapsed | 25389 | +| total_timesteps | 7859200 | +| train/ | | +| approx_kl | 2.6576538 | +| clip_fraction | 0.478 | +| clip_range | 0.2 | +| entropy_loss | -0.34 | +| explained_variance | -1.9 | +| learning_rate | 0.0001 | +| loss | -0.0811 | +| n_updates | 137270 | +| policy_gradient_loss | -0.0627 | +| value_loss | 0.000721 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.211 | +| time/ | | +| fps | 309 | +| iterations | 7676 | +| time_elapsed | 25392 | +| total_timesteps | 7860224 | +| train/ | | +| approx_kl | 1.9756479 | +| clip_fraction | 0.472 | +| clip_range | 0.2 | +| entropy_loss | -0.361 | +| explained_variance | -1.97 | +| learning_rate | 0.0001 | +| loss | -0.0818 | +| n_updates | 137280 | +| policy_gradient_loss | -0.07 | +| value_loss | 0.000887 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.209 | +| time/ | | +| fps | 309 | +| iterations | 7677 | +| time_elapsed | 25395 | +| total_timesteps | 7861248 | +| train/ | | +| approx_kl | 1.9960358 | +| clip_fraction | 0.474 | +| clip_range | 0.2 | +| entropy_loss | -0.378 | +| explained_variance | -2.62 | +| learning_rate | 0.0001 | +| loss | -0.0932 | +| n_updates | 137290 | +| policy_gradient_loss | -0.0659 | +| value_loss | 0.000511 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.209 | +| time/ | | +| fps | 309 | +| iterations | 7678 | +| time_elapsed | 25398 | +| total_timesteps | 7862272 | +| train/ | | +| approx_kl | 2.8314302 | +| clip_fraction | 0.456 | +| clip_range | 0.2 | +| entropy_loss | -0.305 | +| explained_variance | -1.75 | +| learning_rate | 0.0001 | +| loss | -0.0948 | +| n_updates | 137300 | +| policy_gradient_loss | -0.069 | +| value_loss | 0.000466 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.78e+03 | +| ep_rew_mean | 0.207 | +| time/ | | +| fps | 309 | +| iterations | 7679 | +| time_elapsed | 25401 | +| total_timesteps | 7863296 | +| train/ | | +| approx_kl | 2.154211 | +| clip_fraction | 0.5 | +| clip_range | 0.2 | +| entropy_loss | -0.384 | +| explained_variance | -1.1 | +| learning_rate | 0.0001 | +| loss | -0.0603 | +| n_updates | 137310 | +| policy_gradient_loss | -0.066 | +| value_loss | 0.000672 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.78e+03 | +| ep_rew_mean | 0.207 | +| time/ | | +| fps | 309 | +| iterations | 7680 | +| time_elapsed | 25405 | +| total_timesteps | 7864320 | +| train/ | | +| approx_kl | 2.2345874 | +| clip_fraction | 0.452 | +| clip_range | 0.2 | +| entropy_loss | -0.33 | +| explained_variance | -2.76 | +| learning_rate | 0.0001 | +| loss | -0.0607 | +| n_updates | 137320 | +| policy_gradient_loss | -0.0629 | +| value_loss | 0.000615 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.209 | +| time/ | | +| fps | 309 | +| iterations | 7681 | +| time_elapsed | 25408 | +| total_timesteps | 7865344 | +| train/ | | +| approx_kl | 2.781557 | +| clip_fraction | 0.497 | +| clip_range | 0.2 | +| entropy_loss | -0.37 | +| explained_variance | -1.56 | +| learning_rate | 0.0001 | +| loss | -0.0662 | +| n_updates | 137330 | +| policy_gradient_loss | -0.062 | +| value_loss | 0.00052 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.209 | +| time/ | | +| fps | 309 | +| iterations | 7682 | +| time_elapsed | 25411 | +| total_timesteps | 7866368 | +| train/ | | +| approx_kl | 2.1193676 | +| clip_fraction | 0.466 | +| clip_range | 0.2 | +| entropy_loss | -0.358 | +| explained_variance | -1.01 | +| learning_rate | 0.0001 | +| loss | -0.0636 | +| n_updates | 137340 | +| policy_gradient_loss | -0.0673 | +| value_loss | 0.000385 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.207 | +| time/ | | +| fps | 309 | +| iterations | 7683 | +| time_elapsed | 25414 | +| total_timesteps | 7867392 | +| train/ | | +| approx_kl | 2.4098983 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.317 | +| explained_variance | -2.62 | +| learning_rate | 0.0001 | +| loss | -0.0835 | +| n_updates | 137350 | +| policy_gradient_loss | -0.07 | +| value_loss | 0.000735 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.203 | +| time/ | | +| fps | 309 | +| iterations | 7684 | +| time_elapsed | 25417 | +| total_timesteps | 7868416 | +| train/ | | +| approx_kl | 3.3582141 | +| clip_fraction | 0.506 | +| clip_range | 0.2 | +| entropy_loss | -0.376 | +| explained_variance | -1.66 | +| learning_rate | 0.0001 | +| loss | -0.0866 | +| n_updates | 137360 | +| policy_gradient_loss | -0.0641 | +| value_loss | 0.000768 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.203 | +| time/ | | +| fps | 309 | +| iterations | 7685 | +| time_elapsed | 25420 | +| total_timesteps | 7869440 | +| train/ | | +| approx_kl | 2.445344 | +| clip_fraction | 0.461 | +| clip_range | 0.2 | +| entropy_loss | -0.323 | +| explained_variance | -4.47 | +| learning_rate | 0.0001 | +| loss | -0.0851 | +| n_updates | 137370 | +| policy_gradient_loss | -0.067 | +| value_loss | 0.000574 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.78e+03 | +| ep_rew_mean | 0.208 | +| time/ | | +| fps | 309 | +| iterations | 7686 | +| time_elapsed | 25424 | +| total_timesteps | 7870464 | +| train/ | | +| approx_kl | 2.1172276 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.376 | +| explained_variance | -0.63 | +| learning_rate | 0.0001 | +| loss | -0.082 | +| n_updates | 137380 | +| policy_gradient_loss | -0.0637 | +| value_loss | 0.000864 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.78e+03 | +| ep_rew_mean | 0.216 | +| time/ | | +| fps | 309 | +| iterations | 7687 | +| time_elapsed | 25427 | +| total_timesteps | 7871488 | +| train/ | | +| approx_kl | 2.0879068 | +| clip_fraction | 0.462 | +| clip_range | 0.2 | +| entropy_loss | -0.357 | +| explained_variance | -1.78 | +| learning_rate | 0.0001 | +| loss | -0.0899 | +| n_updates | 137390 | +| policy_gradient_loss | -0.067 | +| value_loss | 0.000901 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.78e+03 | +| ep_rew_mean | 0.216 | +| time/ | | +| fps | 309 | +| iterations | 7688 | +| time_elapsed | 25431 | +| total_timesteps | 7872512 | +| train/ | | +| approx_kl | 1.9272425 | +| clip_fraction | 0.477 | +| clip_range | 0.2 | +| entropy_loss | -0.393 | +| explained_variance | -0.981 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 137400 | +| policy_gradient_loss | -0.0626 | +| value_loss | 0.000739 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.78e+03 | +| ep_rew_mean | 0.216 | +| time/ | | +| fps | 309 | +| iterations | 7689 | +| time_elapsed | 25434 | +| total_timesteps | 7873536 | +| train/ | | +| approx_kl | 2.5357666 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.364 | +| explained_variance | -5.93 | +| learning_rate | 0.0001 | +| loss | -0.0845 | +| n_updates | 137410 | +| policy_gradient_loss | -0.0601 | +| value_loss | 0.000496 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.216 | +| time/ | | +| fps | 309 | +| iterations | 7690 | +| time_elapsed | 25438 | +| total_timesteps | 7874560 | +| train/ | | +| approx_kl | 2.150646 | +| clip_fraction | 0.498 | +| clip_range | 0.2 | +| entropy_loss | -0.381 | +| explained_variance | -3.61 | +| learning_rate | 0.0001 | +| loss | -0.0838 | +| n_updates | 137420 | +| policy_gradient_loss | -0.0643 | +| value_loss | 0.000293 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.216 | +| time/ | | +| fps | 309 | +| iterations | 7691 | +| time_elapsed | 25441 | +| total_timesteps | 7875584 | +| train/ | | +| approx_kl | 3.0319033 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.318 | +| explained_variance | -2.14 | +| learning_rate | 0.0001 | +| loss | -0.088 | +| n_updates | 137430 | +| policy_gradient_loss | -0.0649 | +| value_loss | 0.000565 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.216 | +| time/ | | +| fps | 309 | +| iterations | 7692 | +| time_elapsed | 25445 | +| total_timesteps | 7876608 | +| train/ | | +| approx_kl | 2.6326404 | +| clip_fraction | 0.493 | +| clip_range | 0.2 | +| entropy_loss | -0.375 | +| explained_variance | -3.17 | +| learning_rate | 0.0001 | +| loss | -0.106 | +| n_updates | 137440 | +| policy_gradient_loss | -0.0679 | +| value_loss | 0.000389 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.81e+03 | +| ep_rew_mean | 0.221 | +| time/ | | +| fps | 309 | +| iterations | 7693 | +| time_elapsed | 25448 | +| total_timesteps | 7877632 | +| train/ | | +| approx_kl | 2.2857225 | +| clip_fraction | 0.462 | +| clip_range | 0.2 | +| entropy_loss | -0.338 | +| explained_variance | -6.25 | +| learning_rate | 0.0001 | +| loss | -0.0871 | +| n_updates | 137450 | +| policy_gradient_loss | -0.0647 | +| value_loss | 0.00054 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.81e+03 | +| ep_rew_mean | 0.221 | +| time/ | | +| fps | 309 | +| iterations | 7694 | +| time_elapsed | 25451 | +| total_timesteps | 7878656 | +| train/ | | +| approx_kl | 3.277163 | +| clip_fraction | 0.468 | +| clip_range | 0.2 | +| entropy_loss | -0.335 | +| explained_variance | -1.16 | +| learning_rate | 0.0001 | +| loss | -0.0973 | +| n_updates | 137460 | +| policy_gradient_loss | -0.0606 | +| value_loss | 0.000556 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.81e+03 | +| ep_rew_mean | 0.22 | +| time/ | | +| fps | 309 | +| iterations | 7695 | +| time_elapsed | 25454 | +| total_timesteps | 7879680 | +| train/ | | +| approx_kl | 2.2349892 | +| clip_fraction | 0.494 | +| clip_range | 0.2 | +| entropy_loss | -0.371 | +| explained_variance | -6.64 | +| learning_rate | 0.0001 | +| loss | -0.0668 | +| n_updates | 137470 | +| policy_gradient_loss | -0.0654 | +| value_loss | 0.000243 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.81e+03 | +| ep_rew_mean | 0.221 | +| time/ | | +| fps | 309 | +| iterations | 7696 | +| time_elapsed | 25458 | +| total_timesteps | 7880704 | +| train/ | | +| approx_kl | 2.4988737 | +| clip_fraction | 0.47 | +| clip_range | 0.2 | +| entropy_loss | -0.324 | +| explained_variance | -0.606 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 137480 | +| policy_gradient_loss | -0.0589 | +| value_loss | 0.000452 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.8e+03 | +| ep_rew_mean | 0.215 | +| time/ | | +| fps | 309 | +| iterations | 7697 | +| time_elapsed | 25461 | +| total_timesteps | 7881728 | +| train/ | | +| approx_kl | 1.9853697 | +| clip_fraction | 0.472 | +| clip_range | 0.2 | +| entropy_loss | -0.363 | +| explained_variance | -0.742 | +| learning_rate | 0.0001 | +| loss | -0.0883 | +| n_updates | 137490 | +| policy_gradient_loss | -0.0627 | +| value_loss | 0.000485 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.8e+03 | +| ep_rew_mean | 0.215 | +| time/ | | +| fps | 309 | +| iterations | 7698 | +| time_elapsed | 25464 | +| total_timesteps | 7882752 | +| train/ | | +| approx_kl | 2.3441246 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.371 | +| explained_variance | -1.66 | +| learning_rate | 0.0001 | +| loss | -0.0869 | +| n_updates | 137500 | +| policy_gradient_loss | -0.0693 | +| value_loss | 0.000495 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.8e+03 | +| ep_rew_mean | 0.215 | +| time/ | | +| fps | 309 | +| iterations | 7699 | +| time_elapsed | 25467 | +| total_timesteps | 7883776 | +| train/ | | +| approx_kl | 2.2128487 | +| clip_fraction | 0.482 | +| clip_range | 0.2 | +| entropy_loss | -0.372 | +| explained_variance | -1.39 | +| learning_rate | 0.0001 | +| loss | -0.0972 | +| n_updates | 137510 | +| policy_gradient_loss | -0.0654 | +| value_loss | 0.000563 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.81e+03 | +| ep_rew_mean | 0.217 | +| time/ | | +| fps | 309 | +| iterations | 7700 | +| time_elapsed | 25471 | +| total_timesteps | 7884800 | +| train/ | | +| approx_kl | 2.1032968 | +| clip_fraction | 0.478 | +| clip_range | 0.2 | +| entropy_loss | -0.399 | +| explained_variance | -3.36 | +| learning_rate | 0.0001 | +| loss | -0.0975 | +| n_updates | 137520 | +| policy_gradient_loss | -0.0703 | +| value_loss | 0.000465 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.81e+03 | +| ep_rew_mean | 0.217 | +| time/ | | +| fps | 309 | +| iterations | 7701 | +| time_elapsed | 25474 | +| total_timesteps | 7885824 | +| train/ | | +| approx_kl | 2.5274649 | +| clip_fraction | 0.469 | +| clip_range | 0.2 | +| entropy_loss | -0.326 | +| explained_variance | -1.39 | +| learning_rate | 0.0001 | +| loss | -0.0961 | +| n_updates | 137530 | +| policy_gradient_loss | -0.065 | +| value_loss | 0.000417 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.8e+03 | +| ep_rew_mean | 0.218 | +| time/ | | +| fps | 309 | +| iterations | 7702 | +| time_elapsed | 25477 | +| total_timesteps | 7886848 | +| train/ | | +| approx_kl | 2.5808125 | +| clip_fraction | 0.484 | +| clip_range | 0.2 | +| entropy_loss | -0.373 | +| explained_variance | -1.22 | +| learning_rate | 0.0001 | +| loss | -0.0862 | +| n_updates | 137540 | +| policy_gradient_loss | -0.0682 | +| value_loss | 0.000576 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.8e+03 | +| ep_rew_mean | 0.218 | +| time/ | | +| fps | 309 | +| iterations | 7703 | +| time_elapsed | 25480 | +| total_timesteps | 7887872 | +| train/ | | +| approx_kl | 2.1056914 | +| clip_fraction | 0.436 | +| clip_range | 0.2 | +| entropy_loss | -0.324 | +| explained_variance | -2.37 | +| learning_rate | 0.0001 | +| loss | -0.068 | +| n_updates | 137550 | +| policy_gradient_loss | -0.0633 | +| value_loss | 0.000615 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.8e+03 | +| ep_rew_mean | 0.22 | +| time/ | | +| fps | 309 | +| iterations | 7704 | +| time_elapsed | 25484 | +| total_timesteps | 7888896 | +| train/ | | +| approx_kl | 2.3232822 | +| clip_fraction | 0.492 | +| clip_range | 0.2 | +| entropy_loss | -0.36 | +| explained_variance | -1.98 | +| learning_rate | 0.0001 | +| loss | -0.0783 | +| n_updates | 137560 | +| policy_gradient_loss | -0.0638 | +| value_loss | 0.000698 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.215 | +| time/ | | +| fps | 309 | +| iterations | 7705 | +| time_elapsed | 25487 | +| total_timesteps | 7889920 | +| train/ | | +| approx_kl | 3.5352747 | +| clip_fraction | 0.448 | +| clip_range | 0.2 | +| entropy_loss | -0.307 | +| explained_variance | -4.03 | +| learning_rate | 0.0001 | +| loss | -0.0859 | +| n_updates | 137570 | +| policy_gradient_loss | -0.0615 | +| value_loss | 0.000517 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.217 | +| time/ | | +| fps | 309 | +| iterations | 7706 | +| time_elapsed | 25491 | +| total_timesteps | 7890944 | +| train/ | | +| approx_kl | 2.3627508 | +| clip_fraction | 0.448 | +| clip_range | 0.2 | +| entropy_loss | -0.321 | +| explained_variance | -0.494 | +| learning_rate | 0.0001 | +| loss | -0.0783 | +| n_updates | 137580 | +| policy_gradient_loss | -0.0583 | +| value_loss | 0.000967 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.209 | +| time/ | | +| fps | 309 | +| iterations | 7707 | +| time_elapsed | 25494 | +| total_timesteps | 7891968 | +| train/ | | +| approx_kl | 2.4012666 | +| clip_fraction | 0.488 | +| clip_range | 0.2 | +| entropy_loss | -0.389 | +| explained_variance | -1.1 | +| learning_rate | 0.0001 | +| loss | -0.0704 | +| n_updates | 137590 | +| policy_gradient_loss | -0.0658 | +| value_loss | 0.000784 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.209 | +| time/ | | +| fps | 309 | +| iterations | 7708 | +| time_elapsed | 25498 | +| total_timesteps | 7892992 | +| train/ | | +| approx_kl | 2.5651975 | +| clip_fraction | 0.485 | +| clip_range | 0.2 | +| entropy_loss | -0.4 | +| explained_variance | -3.41 | +| learning_rate | 0.0001 | +| loss | -0.0849 | +| n_updates | 137600 | +| policy_gradient_loss | -0.0709 | +| value_loss | 0.000446 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.78e+03 | +| ep_rew_mean | 0.213 | +| time/ | | +| fps | 309 | +| iterations | 7709 | +| time_elapsed | 25501 | +| total_timesteps | 7894016 | +| train/ | | +| approx_kl | 2.0966084 | +| clip_fraction | 0.476 | +| clip_range | 0.2 | +| entropy_loss | -0.392 | +| explained_variance | -0.542 | +| learning_rate | 0.0001 | +| loss | -0.115 | +| n_updates | 137610 | +| policy_gradient_loss | -0.0621 | +| value_loss | 0.000347 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.78e+03 | +| ep_rew_mean | 0.211 | +| time/ | | +| fps | 309 | +| iterations | 7710 | +| time_elapsed | 25505 | +| total_timesteps | 7895040 | +| train/ | | +| approx_kl | 2.4202194 | +| clip_fraction | 0.467 | +| clip_range | 0.2 | +| entropy_loss | -0.357 | +| explained_variance | -0.702 | +| learning_rate | 0.0001 | +| loss | -0.0964 | +| n_updates | 137620 | +| policy_gradient_loss | -0.0645 | +| value_loss | 0.000555 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.78e+03 | +| ep_rew_mean | 0.211 | +| time/ | | +| fps | 309 | +| iterations | 7711 | +| time_elapsed | 25508 | +| total_timesteps | 7896064 | +| train/ | | +| approx_kl | 2.4650853 | +| clip_fraction | 0.465 | +| clip_range | 0.2 | +| entropy_loss | -0.341 | +| explained_variance | -2.12 | +| learning_rate | 0.0001 | +| loss | -0.0977 | +| n_updates | 137630 | +| policy_gradient_loss | -0.0706 | +| value_loss | 0.000942 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.78e+03 | +| ep_rew_mean | 0.214 | +| time/ | | +| fps | 309 | +| iterations | 7712 | +| time_elapsed | 25511 | +| total_timesteps | 7897088 | +| train/ | | +| approx_kl | 2.4701724 | +| clip_fraction | 0.496 | +| clip_range | 0.2 | +| entropy_loss | -0.384 | +| explained_variance | -2.56 | +| learning_rate | 0.0001 | +| loss | -0.106 | +| n_updates | 137640 | +| policy_gradient_loss | -0.0704 | +| value_loss | 0.000731 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.214 | +| time/ | | +| fps | 309 | +| iterations | 7713 | +| time_elapsed | 25514 | +| total_timesteps | 7898112 | +| train/ | | +| approx_kl | 11.439872 | +| clip_fraction | 0.454 | +| clip_range | 0.2 | +| entropy_loss | -0.336 | +| explained_variance | -1.84 | +| learning_rate | 0.0001 | +| loss | -0.0772 | +| n_updates | 137650 | +| policy_gradient_loss | -0.0637 | +| value_loss | 0.000718 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.214 | +| time/ | | +| fps | 309 | +| iterations | 7714 | +| time_elapsed | 25518 | +| total_timesteps | 7899136 | +| train/ | | +| approx_kl | 2.4319074 | +| clip_fraction | 0.445 | +| clip_range | 0.2 | +| entropy_loss | -0.353 | +| explained_variance | -0.493 | +| learning_rate | 0.0001 | +| loss | -0.0693 | +| n_updates | 137660 | +| policy_gradient_loss | -0.0613 | +| value_loss | 0.000743 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.212 | +| time/ | | +| fps | 309 | +| iterations | 7715 | +| time_elapsed | 25521 | +| total_timesteps | 7900160 | +| train/ | | +| approx_kl | 2.5948896 | +| clip_fraction | 0.506 | +| clip_range | 0.2 | +| entropy_loss | -0.376 | +| explained_variance | -2.6 | +| learning_rate | 0.0001 | +| loss | -0.0786 | +| n_updates | 137670 | +| policy_gradient_loss | -0.0707 | +| value_loss | 0.000695 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.212 | +| time/ | | +| fps | 309 | +| iterations | 7716 | +| time_elapsed | 25524 | +| total_timesteps | 7901184 | +| train/ | | +| approx_kl | 2.0151322 | +| clip_fraction | 0.462 | +| clip_range | 0.2 | +| entropy_loss | -0.354 | +| explained_variance | -1.39 | +| learning_rate | 0.0001 | +| loss | -0.0705 | +| n_updates | 137680 | +| policy_gradient_loss | -0.0613 | +| value_loss | 0.000582 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.212 | +| time/ | | +| fps | 309 | +| iterations | 7717 | +| time_elapsed | 25527 | +| total_timesteps | 7902208 | +| train/ | | +| approx_kl | 2.4050784 | +| clip_fraction | 0.497 | +| clip_range | 0.2 | +| entropy_loss | -0.34 | +| explained_variance | -1.31 | +| learning_rate | 0.0001 | +| loss | -0.0787 | +| n_updates | 137690 | +| policy_gradient_loss | -0.0729 | +| value_loss | 0.000634 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.212 | +| time/ | | +| fps | 309 | +| iterations | 7718 | +| time_elapsed | 25530 | +| total_timesteps | 7903232 | +| train/ | | +| approx_kl | 3.84436 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.335 | +| explained_variance | -2.06 | +| learning_rate | 0.0001 | +| loss | -0.0877 | +| n_updates | 137700 | +| policy_gradient_loss | -0.0688 | +| value_loss | 0.000574 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.213 | +| time/ | | +| fps | 309 | +| iterations | 7719 | +| time_elapsed | 25534 | +| total_timesteps | 7904256 | +| train/ | | +| approx_kl | 1.8198618 | +| clip_fraction | 0.491 | +| clip_range | 0.2 | +| entropy_loss | -0.428 | +| explained_variance | -6.32 | +| learning_rate | 0.0001 | +| loss | -0.0878 | +| n_updates | 137710 | +| policy_gradient_loss | -0.0701 | +| value_loss | 0.000307 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.213 | +| time/ | | +| fps | 309 | +| iterations | 7720 | +| time_elapsed | 25537 | +| total_timesteps | 7905280 | +| train/ | | +| approx_kl | 35.850163 | +| clip_fraction | 0.491 | +| clip_range | 0.2 | +| entropy_loss | -0.37 | +| explained_variance | -5.48 | +| learning_rate | 0.0001 | +| loss | -0.0616 | +| n_updates | 137720 | +| policy_gradient_loss | -0.0696 | +| value_loss | 0.000387 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.21 | +| time/ | | +| fps | 309 | +| iterations | 7721 | +| time_elapsed | 25540 | +| total_timesteps | 7906304 | +| train/ | | +| approx_kl | 2.1485777 | +| clip_fraction | 0.5 | +| clip_range | 0.2 | +| entropy_loss | -0.445 | +| explained_variance | -1.06 | +| learning_rate | 0.0001 | +| loss | -0.114 | +| n_updates | 137730 | +| policy_gradient_loss | -0.0701 | +| value_loss | 0.000374 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.215 | +| time/ | | +| fps | 309 | +| iterations | 7722 | +| time_elapsed | 25543 | +| total_timesteps | 7907328 | +| train/ | | +| approx_kl | 2.621752 | +| clip_fraction | 0.454 | +| clip_range | 0.2 | +| entropy_loss | -0.335 | +| explained_variance | -1.26 | +| learning_rate | 0.0001 | +| loss | -0.0714 | +| n_updates | 137740 | +| policy_gradient_loss | -0.058 | +| value_loss | 0.000636 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.215 | +| time/ | | +| fps | 309 | +| iterations | 7723 | +| time_elapsed | 25547 | +| total_timesteps | 7908352 | +| train/ | | +| approx_kl | 2.4227748 | +| clip_fraction | 0.485 | +| clip_range | 0.2 | +| entropy_loss | -0.354 | +| explained_variance | -0.616 | +| learning_rate | 0.0001 | +| loss | -0.0675 | +| n_updates | 137750 | +| policy_gradient_loss | -0.065 | +| value_loss | 0.00125 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.215 | +| time/ | | +| fps | 309 | +| iterations | 7724 | +| time_elapsed | 25550 | +| total_timesteps | 7909376 | +| train/ | | +| approx_kl | 2.635284 | +| clip_fraction | 0.473 | +| clip_range | 0.2 | +| entropy_loss | -0.318 | +| explained_variance | -3.14 | +| learning_rate | 0.0001 | +| loss | -0.0716 | +| n_updates | 137760 | +| policy_gradient_loss | -0.0684 | +| value_loss | 0.000994 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.221 | +| time/ | | +| fps | 309 | +| iterations | 7725 | +| time_elapsed | 25554 | +| total_timesteps | 7910400 | +| train/ | | +| approx_kl | 2.832303 | +| clip_fraction | 0.482 | +| clip_range | 0.2 | +| entropy_loss | -0.336 | +| explained_variance | -1.38 | +| learning_rate | 0.0001 | +| loss | -0.0596 | +| n_updates | 137770 | +| policy_gradient_loss | -0.0653 | +| value_loss | 0.000812 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.226 | +| time/ | | +| fps | 309 | +| iterations | 7726 | +| time_elapsed | 25557 | +| total_timesteps | 7911424 | +| train/ | | +| approx_kl | 2.2475784 | +| clip_fraction | 0.493 | +| clip_range | 0.2 | +| entropy_loss | -0.388 | +| explained_variance | -1.56 | +| learning_rate | 0.0001 | +| loss | -0.0771 | +| n_updates | 137780 | +| policy_gradient_loss | -0.0637 | +| value_loss | 0.000586 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.226 | +| time/ | | +| fps | 309 | +| iterations | 7727 | +| time_elapsed | 25561 | +| total_timesteps | 7912448 | +| train/ | | +| approx_kl | 2.6937227 | +| clip_fraction | 0.472 | +| clip_range | 0.2 | +| entropy_loss | -0.358 | +| explained_variance | -1.95 | +| learning_rate | 0.0001 | +| loss | -0.0878 | +| n_updates | 137790 | +| policy_gradient_loss | -0.0657 | +| value_loss | 0.000555 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.226 | +| time/ | | +| fps | 309 | +| iterations | 7728 | +| time_elapsed | 25564 | +| total_timesteps | 7913472 | +| train/ | | +| approx_kl | 3.1257763 | +| clip_fraction | 0.528 | +| clip_range | 0.2 | +| entropy_loss | -0.387 | +| explained_variance | -3.67 | +| learning_rate | 0.0001 | +| loss | -0.0943 | +| n_updates | 137800 | +| policy_gradient_loss | -0.0777 | +| value_loss | 0.000492 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.23 | +| time/ | | +| fps | 309 | +| iterations | 7729 | +| time_elapsed | 25568 | +| total_timesteps | 7914496 | +| train/ | | +| approx_kl | 3.2549934 | +| clip_fraction | 0.493 | +| clip_range | 0.2 | +| entropy_loss | -0.355 | +| explained_variance | -1.12 | +| learning_rate | 0.0001 | +| loss | -0.0918 | +| n_updates | 137810 | +| policy_gradient_loss | -0.0695 | +| value_loss | 0.000593 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.221 | +| time/ | | +| fps | 309 | +| iterations | 7730 | +| time_elapsed | 25571 | +| total_timesteps | 7915520 | +| train/ | | +| approx_kl | 2.199666 | +| clip_fraction | 0.451 | +| clip_range | 0.2 | +| entropy_loss | -0.328 | +| explained_variance | -1.19 | +| learning_rate | 0.0001 | +| loss | -0.107 | +| n_updates | 137820 | +| policy_gradient_loss | -0.0644 | +| value_loss | 0.000626 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.221 | +| time/ | | +| fps | 309 | +| iterations | 7731 | +| time_elapsed | 25574 | +| total_timesteps | 7916544 | +| train/ | | +| approx_kl | 1.7119502 | +| clip_fraction | 0.464 | +| clip_range | 0.2 | +| entropy_loss | -0.373 | +| explained_variance | -1.26 | +| learning_rate | 0.0001 | +| loss | -0.0976 | +| n_updates | 137830 | +| policy_gradient_loss | -0.0647 | +| value_loss | 0.000438 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.22 | +| time/ | | +| fps | 309 | +| iterations | 7732 | +| time_elapsed | 25577 | +| total_timesteps | 7917568 | +| train/ | | +| approx_kl | 2.813067 | +| clip_fraction | 0.479 | +| clip_range | 0.2 | +| entropy_loss | -0.423 | +| explained_variance | -2.76 | +| learning_rate | 0.0001 | +| loss | -0.0716 | +| n_updates | 137840 | +| policy_gradient_loss | -0.0623 | +| value_loss | 0.000379 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.221 | +| time/ | | +| fps | 309 | +| iterations | 7733 | +| time_elapsed | 25581 | +| total_timesteps | 7918592 | +| train/ | | +| approx_kl | 1.7687881 | +| clip_fraction | 0.444 | +| clip_range | 0.2 | +| entropy_loss | -0.38 | +| explained_variance | -1.2 | +| learning_rate | 0.0001 | +| loss | -0.0737 | +| n_updates | 137850 | +| policy_gradient_loss | -0.0662 | +| value_loss | 0.000292 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.221 | +| time/ | | +| fps | 309 | +| iterations | 7734 | +| time_elapsed | 25584 | +| total_timesteps | 7919616 | +| train/ | | +| approx_kl | 2.1889508 | +| clip_fraction | 0.477 | +| clip_range | 0.2 | +| entropy_loss | -0.386 | +| explained_variance | -1.04 | +| learning_rate | 0.0001 | +| loss | -0.0609 | +| n_updates | 137860 | +| policy_gradient_loss | -0.064 | +| value_loss | 0.000441 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.227 | +| time/ | | +| fps | 309 | +| iterations | 7735 | +| time_elapsed | 25587 | +| total_timesteps | 7920640 | +| train/ | | +| approx_kl | 2.7126474 | +| clip_fraction | 0.477 | +| clip_range | 0.2 | +| entropy_loss | -0.459 | +| explained_variance | -8.33 | +| learning_rate | 0.0001 | +| loss | -0.0556 | +| n_updates | 137870 | +| policy_gradient_loss | -0.0626 | +| value_loss | 0.00025 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.221 | +| time/ | | +| fps | 309 | +| iterations | 7736 | +| time_elapsed | 25590 | +| total_timesteps | 7921664 | +| train/ | | +| approx_kl | 2.4152293 | +| clip_fraction | 0.463 | +| clip_range | 0.2 | +| entropy_loss | -0.335 | +| explained_variance | -0.456 | +| learning_rate | 0.0001 | +| loss | -0.0834 | +| n_updates | 137880 | +| policy_gradient_loss | -0.0506 | +| value_loss | 0.000568 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.221 | +| time/ | | +| fps | 309 | +| iterations | 7737 | +| time_elapsed | 25594 | +| total_timesteps | 7922688 | +| train/ | | +| approx_kl | 2.206314 | +| clip_fraction | 0.498 | +| clip_range | 0.2 | +| entropy_loss | -0.387 | +| explained_variance | -4.46 | +| learning_rate | 0.0001 | +| loss | -0.0858 | +| n_updates | 137890 | +| policy_gradient_loss | -0.0679 | +| value_loss | 0.000502 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.219 | +| time/ | | +| fps | 309 | +| iterations | 7738 | +| time_elapsed | 25597 | +| total_timesteps | 7923712 | +| train/ | | +| approx_kl | 2.1725917 | +| clip_fraction | 0.524 | +| clip_range | 0.2 | +| entropy_loss | -0.402 | +| explained_variance | -0.856 | +| learning_rate | 0.0001 | +| loss | -0.0786 | +| n_updates | 137900 | +| policy_gradient_loss | -0.0715 | +| value_loss | 0.00083 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.222 | +| time/ | | +| fps | 309 | +| iterations | 7739 | +| time_elapsed | 25600 | +| total_timesteps | 7924736 | +| train/ | | +| approx_kl | 2.6246264 | +| clip_fraction | 0.497 | +| clip_range | 0.2 | +| entropy_loss | -0.354 | +| explained_variance | -11.7 | +| learning_rate | 0.0001 | +| loss | -0.0752 | +| n_updates | 137910 | +| policy_gradient_loss | -0.0705 | +| value_loss | 0.000825 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.222 | +| time/ | | +| fps | 309 | +| iterations | 7740 | +| time_elapsed | 25604 | +| total_timesteps | 7925760 | +| train/ | | +| approx_kl | 2.468502 | +| clip_fraction | 0.492 | +| clip_range | 0.2 | +| entropy_loss | -0.349 | +| explained_variance | -0.824 | +| learning_rate | 0.0001 | +| loss | -0.114 | +| n_updates | 137920 | +| policy_gradient_loss | -0.0694 | +| value_loss | 0.000876 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.225 | +| time/ | | +| fps | 309 | +| iterations | 7741 | +| time_elapsed | 25607 | +| total_timesteps | 7926784 | +| train/ | | +| approx_kl | 2.792055 | +| clip_fraction | 0.485 | +| clip_range | 0.2 | +| entropy_loss | -0.36 | +| explained_variance | -2.31 | +| learning_rate | 0.0001 | +| loss | -0.105 | +| n_updates | 137930 | +| policy_gradient_loss | -0.0748 | +| value_loss | 0.000619 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.225 | +| time/ | | +| fps | 309 | +| iterations | 7742 | +| time_elapsed | 25610 | +| total_timesteps | 7927808 | +| train/ | | +| approx_kl | 2.17527 | +| clip_fraction | 0.515 | +| clip_range | 0.2 | +| entropy_loss | -0.414 | +| explained_variance | -1.24 | +| learning_rate | 0.0001 | +| loss | -0.0978 | +| n_updates | 137940 | +| policy_gradient_loss | -0.0685 | +| value_loss | 0.000625 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.225 | +| time/ | | +| fps | 309 | +| iterations | 7743 | +| time_elapsed | 25614 | +| total_timesteps | 7928832 | +| train/ | | +| approx_kl | 2.5778313 | +| clip_fraction | 0.495 | +| clip_range | 0.2 | +| entropy_loss | -0.361 | +| explained_variance | -5.45 | +| learning_rate | 0.0001 | +| loss | -0.0799 | +| n_updates | 137950 | +| policy_gradient_loss | -0.0714 | +| value_loss | 0.000593 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.221 | +| time/ | | +| fps | 309 | +| iterations | 7744 | +| time_elapsed | 25617 | +| total_timesteps | 7929856 | +| train/ | | +| approx_kl | 2.338298 | +| clip_fraction | 0.466 | +| clip_range | 0.2 | +| entropy_loss | -0.342 | +| explained_variance | -2.67 | +| learning_rate | 0.0001 | +| loss | -0.0827 | +| n_updates | 137960 | +| policy_gradient_loss | -0.0691 | +| value_loss | 0.000625 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.227 | +| time/ | | +| fps | 309 | +| iterations | 7745 | +| time_elapsed | 25621 | +| total_timesteps | 7930880 | +| train/ | | +| approx_kl | 1.9006951 | +| clip_fraction | 0.493 | +| clip_range | 0.2 | +| entropy_loss | -0.369 | +| explained_variance | -1.65 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 137970 | +| policy_gradient_loss | -0.0666 | +| value_loss | 0.000592 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.227 | +| time/ | | +| fps | 309 | +| iterations | 7746 | +| time_elapsed | 25624 | +| total_timesteps | 7931904 | +| train/ | | +| approx_kl | 2.2880683 | +| clip_fraction | 0.467 | +| clip_range | 0.2 | +| entropy_loss | -0.336 | +| explained_variance | -0.388 | +| learning_rate | 0.0001 | +| loss | -0.0827 | +| n_updates | 137980 | +| policy_gradient_loss | -0.0672 | +| value_loss | 0.000805 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.225 | +| time/ | | +| fps | 309 | +| iterations | 7747 | +| time_elapsed | 25627 | +| total_timesteps | 7932928 | +| train/ | | +| approx_kl | 1.8561553 | +| clip_fraction | 0.474 | +| clip_range | 0.2 | +| entropy_loss | -0.39 | +| explained_variance | -12.5 | +| learning_rate | 0.0001 | +| loss | -0.106 | +| n_updates | 137990 | +| policy_gradient_loss | -0.075 | +| value_loss | 0.00042 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.225 | +| time/ | | +| fps | 309 | +| iterations | 7748 | +| time_elapsed | 25630 | +| total_timesteps | 7933952 | +| train/ | | +| approx_kl | 2.3970475 | +| clip_fraction | 0.496 | +| clip_range | 0.2 | +| entropy_loss | -0.369 | +| explained_variance | -2.6 | +| learning_rate | 0.0001 | +| loss | -0.0967 | +| n_updates | 138000 | +| policy_gradient_loss | -0.073 | +| value_loss | 0.000225 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.222 | +| time/ | | +| fps | 309 | +| iterations | 7749 | +| time_elapsed | 25634 | +| total_timesteps | 7934976 | +| train/ | | +| approx_kl | 3.0781255 | +| clip_fraction | 0.509 | +| clip_range | 0.2 | +| entropy_loss | -0.401 | +| explained_variance | -0.614 | +| learning_rate | 0.0001 | +| loss | -0.0744 | +| n_updates | 138010 | +| policy_gradient_loss | -0.0601 | +| value_loss | 0.000649 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.222 | +| time/ | | +| fps | 309 | +| iterations | 7750 | +| time_elapsed | 25637 | +| total_timesteps | 7936000 | +| train/ | | +| approx_kl | 2.1767092 | +| clip_fraction | 0.489 | +| clip_range | 0.2 | +| entropy_loss | -0.392 | +| explained_variance | -2.47 | +| learning_rate | 0.0001 | +| loss | -0.0966 | +| n_updates | 138020 | +| policy_gradient_loss | -0.0739 | +| value_loss | 0.000596 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.225 | +| time/ | | +| fps | 309 | +| iterations | 7751 | +| time_elapsed | 25640 | +| total_timesteps | 7937024 | +| train/ | | +| approx_kl | 2.2163916 | +| clip_fraction | 0.484 | +| clip_range | 0.2 | +| entropy_loss | -0.434 | +| explained_variance | -0.352 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 138030 | +| policy_gradient_loss | -0.0669 | +| value_loss | 0.000544 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.225 | +| time/ | | +| fps | 309 | +| iterations | 7752 | +| time_elapsed | 25643 | +| total_timesteps | 7938048 | +| train/ | | +| approx_kl | 2.2534595 | +| clip_fraction | 0.465 | +| clip_range | 0.2 | +| entropy_loss | -0.323 | +| explained_variance | -2.98 | +| learning_rate | 0.0001 | +| loss | -0.114 | +| n_updates | 138040 | +| policy_gradient_loss | -0.0718 | +| value_loss | 0.000614 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.225 | +| time/ | | +| fps | 309 | +| iterations | 7753 | +| time_elapsed | 25646 | +| total_timesteps | 7939072 | +| train/ | | +| approx_kl | 1.9624379 | +| clip_fraction | 0.486 | +| clip_range | 0.2 | +| entropy_loss | -0.4 | +| explained_variance | -1.67 | +| learning_rate | 0.0001 | +| loss | -0.0739 | +| n_updates | 138050 | +| policy_gradient_loss | -0.0641 | +| value_loss | 0.000475 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.222 | +| time/ | | +| fps | 309 | +| iterations | 7754 | +| time_elapsed | 25650 | +| total_timesteps | 7940096 | +| train/ | | +| approx_kl | 2.6739025 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.361 | +| explained_variance | -2.34 | +| learning_rate | 0.0001 | +| loss | -0.0527 | +| n_updates | 138060 | +| policy_gradient_loss | -0.0624 | +| value_loss | 0.00086 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.222 | +| time/ | | +| fps | 309 | +| iterations | 7755 | +| time_elapsed | 25653 | +| total_timesteps | 7941120 | +| train/ | | +| approx_kl | 2.7039866 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.382 | +| explained_variance | -10.2 | +| learning_rate | 0.0001 | +| loss | -0.114 | +| n_updates | 138070 | +| policy_gradient_loss | -0.068 | +| value_loss | 0.000805 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.223 | +| time/ | | +| fps | 309 | +| iterations | 7756 | +| time_elapsed | 25656 | +| total_timesteps | 7942144 | +| train/ | | +| approx_kl | 1.6311154 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.399 | +| explained_variance | -0.787 | +| learning_rate | 0.0001 | +| loss | -0.124 | +| n_updates | 138080 | +| policy_gradient_loss | -0.0656 | +| value_loss | 0.00051 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.223 | +| time/ | | +| fps | 309 | +| iterations | 7757 | +| time_elapsed | 25659 | +| total_timesteps | 7943168 | +| train/ | | +| approx_kl | 1.8948631 | +| clip_fraction | 0.474 | +| clip_range | 0.2 | +| entropy_loss | -0.372 | +| explained_variance | -0.961 | +| learning_rate | 0.0001 | +| loss | -0.0661 | +| n_updates | 138090 | +| policy_gradient_loss | -0.0678 | +| value_loss | 0.00083 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.227 | +| time/ | | +| fps | 309 | +| iterations | 7758 | +| time_elapsed | 25663 | +| total_timesteps | 7944192 | +| train/ | | +| approx_kl | 2.1663241 | +| clip_fraction | 0.507 | +| clip_range | 0.2 | +| entropy_loss | -0.4 | +| explained_variance | -5.68 | +| learning_rate | 0.0001 | +| loss | -0.0892 | +| n_updates | 138100 | +| policy_gradient_loss | -0.0699 | +| value_loss | 0.00064 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.231 | +| time/ | | +| fps | 309 | +| iterations | 7759 | +| time_elapsed | 25666 | +| total_timesteps | 7945216 | +| train/ | | +| approx_kl | 4.114977 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.367 | +| explained_variance | -2.17 | +| learning_rate | 0.0001 | +| loss | -0.0839 | +| n_updates | 138110 | +| policy_gradient_loss | -0.0688 | +| value_loss | 0.000553 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.231 | +| time/ | | +| fps | 309 | +| iterations | 7760 | +| time_elapsed | 25670 | +| total_timesteps | 7946240 | +| train/ | | +| approx_kl | 2.1235523 | +| clip_fraction | 0.509 | +| clip_range | 0.2 | +| entropy_loss | -0.396 | +| explained_variance | -1.69 | +| learning_rate | 0.0001 | +| loss | -0.1 | +| n_updates | 138120 | +| policy_gradient_loss | -0.0638 | +| value_loss | 0.000687 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.225 | +| time/ | | +| fps | 309 | +| iterations | 7761 | +| time_elapsed | 25673 | +| total_timesteps | 7947264 | +| train/ | | +| approx_kl | 1.5110584 | +| clip_fraction | 0.463 | +| clip_range | 0.2 | +| entropy_loss | -0.427 | +| explained_variance | -8.51 | +| learning_rate | 0.0001 | +| loss | -0.0693 | +| n_updates | 138130 | +| policy_gradient_loss | -0.0682 | +| value_loss | 0.000394 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.228 | +| time/ | | +| fps | 309 | +| iterations | 7762 | +| time_elapsed | 25677 | +| total_timesteps | 7948288 | +| train/ | | +| approx_kl | 1.3336418 | +| clip_fraction | 0.45 | +| clip_range | 0.2 | +| entropy_loss | -0.417 | +| explained_variance | -0.31 | +| learning_rate | 0.0001 | +| loss | -0.0853 | +| n_updates | 138140 | +| policy_gradient_loss | -0.0565 | +| value_loss | 0.000662 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.228 | +| time/ | | +| fps | 309 | +| iterations | 7763 | +| time_elapsed | 25680 | +| total_timesteps | 7949312 | +| train/ | | +| approx_kl | 2.2827525 | +| clip_fraction | 0.449 | +| clip_range | 0.2 | +| entropy_loss | -0.323 | +| explained_variance | -3.99 | +| learning_rate | 0.0001 | +| loss | -0.0732 | +| n_updates | 138150 | +| policy_gradient_loss | -0.0685 | +| value_loss | 0.00096 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.222 | +| time/ | | +| fps | 309 | +| iterations | 7764 | +| time_elapsed | 25684 | +| total_timesteps | 7950336 | +| train/ | | +| approx_kl | 1.9437206 | +| clip_fraction | 0.501 | +| clip_range | 0.2 | +| entropy_loss | -0.437 | +| explained_variance | -2.25 | +| learning_rate | 0.0001 | +| loss | -0.0627 | +| n_updates | 138160 | +| policy_gradient_loss | -0.0683 | +| value_loss | 0.000647 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.22 | +| time/ | | +| fps | 309 | +| iterations | 7765 | +| time_elapsed | 25687 | +| total_timesteps | 7951360 | +| train/ | | +| approx_kl | 2.1814733 | +| clip_fraction | 0.457 | +| clip_range | 0.2 | +| entropy_loss | -0.381 | +| explained_variance | -1.45 | +| learning_rate | 0.0001 | +| loss | -0.109 | +| n_updates | 138170 | +| policy_gradient_loss | -0.063 | +| value_loss | 0.000618 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.22 | +| time/ | | +| fps | 309 | +| iterations | 7766 | +| time_elapsed | 25690 | +| total_timesteps | 7952384 | +| train/ | | +| approx_kl | 2.2539775 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.384 | +| explained_variance | -2.05 | +| learning_rate | 0.0001 | +| loss | -0.0884 | +| n_updates | 138180 | +| policy_gradient_loss | -0.0704 | +| value_loss | 0.00059 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.22 | +| time/ | | +| fps | 309 | +| iterations | 7767 | +| time_elapsed | 25694 | +| total_timesteps | 7953408 | +| train/ | | +| approx_kl | 2.1442733 | +| clip_fraction | 0.502 | +| clip_range | 0.2 | +| entropy_loss | -0.443 | +| explained_variance | -1.02 | +| learning_rate | 0.0001 | +| loss | -0.0596 | +| n_updates | 138190 | +| policy_gradient_loss | -0.0656 | +| value_loss | 0.00066 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.22 | +| time/ | | +| fps | 309 | +| iterations | 7768 | +| time_elapsed | 25697 | +| total_timesteps | 7954432 | +| train/ | | +| approx_kl | 1.8717098 | +| clip_fraction | 0.509 | +| clip_range | 0.2 | +| entropy_loss | -0.474 | +| explained_variance | -3.25 | +| learning_rate | 0.0001 | +| loss | -0.092 | +| n_updates | 138200 | +| policy_gradient_loss | -0.0669 | +| value_loss | 0.00038 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.225 | +| time/ | | +| fps | 309 | +| iterations | 7769 | +| time_elapsed | 25700 | +| total_timesteps | 7955456 | +| train/ | | +| approx_kl | 3.3485203 | +| clip_fraction | 0.497 | +| clip_range | 0.2 | +| entropy_loss | -0.405 | +| explained_variance | -0.932 | +| learning_rate | 0.0001 | +| loss | -0.0812 | +| n_updates | 138210 | +| policy_gradient_loss | -0.0635 | +| value_loss | 0.000383 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.217 | +| time/ | | +| fps | 309 | +| iterations | 7770 | +| time_elapsed | 25703 | +| total_timesteps | 7956480 | +| train/ | | +| approx_kl | 1.8653526 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.415 | +| explained_variance | -2.34 | +| learning_rate | 0.0001 | +| loss | -0.0653 | +| n_updates | 138220 | +| policy_gradient_loss | -0.0622 | +| value_loss | 0.000644 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.22 | +| time/ | | +| fps | 309 | +| iterations | 7771 | +| time_elapsed | 25706 | +| total_timesteps | 7957504 | +| train/ | | +| approx_kl | 1.6257613 | +| clip_fraction | 0.453 | +| clip_range | 0.2 | +| entropy_loss | -0.4 | +| explained_variance | -2.33 | +| learning_rate | 0.0001 | +| loss | -0.0893 | +| n_updates | 138230 | +| policy_gradient_loss | -0.0621 | +| value_loss | 0.000553 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.219 | +| time/ | | +| fps | 309 | +| iterations | 7772 | +| time_elapsed | 25710 | +| total_timesteps | 7958528 | +| train/ | | +| approx_kl | 1.5645157 | +| clip_fraction | 0.473 | +| clip_range | 0.2 | +| entropy_loss | -0.388 | +| explained_variance | -1.64 | +| learning_rate | 0.0001 | +| loss | -0.0982 | +| n_updates | 138240 | +| policy_gradient_loss | -0.0678 | +| value_loss | 0.000878 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.219 | +| time/ | | +| fps | 309 | +| iterations | 7773 | +| time_elapsed | 25713 | +| total_timesteps | 7959552 | +| train/ | | +| approx_kl | 2.5115292 | +| clip_fraction | 0.463 | +| clip_range | 0.2 | +| entropy_loss | -0.367 | +| explained_variance | -1.82 | +| learning_rate | 0.0001 | +| loss | -0.0762 | +| n_updates | 138250 | +| policy_gradient_loss | -0.0681 | +| value_loss | 0.000791 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.218 | +| time/ | | +| fps | 309 | +| iterations | 7774 | +| time_elapsed | 25716 | +| total_timesteps | 7960576 | +| train/ | | +| approx_kl | 2.0606663 | +| clip_fraction | 0.489 | +| clip_range | 0.2 | +| entropy_loss | -0.403 | +| explained_variance | -2.4 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 138260 | +| policy_gradient_loss | -0.0713 | +| value_loss | 0.000654 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.218 | +| time/ | | +| fps | 309 | +| iterations | 7775 | +| time_elapsed | 25719 | +| total_timesteps | 7961600 | +| train/ | | +| approx_kl | 1.9501464 | +| clip_fraction | 0.462 | +| clip_range | 0.2 | +| entropy_loss | -0.344 | +| explained_variance | -3.94 | +| learning_rate | 0.0001 | +| loss | -0.0626 | +| n_updates | 138270 | +| policy_gradient_loss | -0.0659 | +| value_loss | 0.000638 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.22 | +| time/ | | +| fps | 309 | +| iterations | 7776 | +| time_elapsed | 25722 | +| total_timesteps | 7962624 | +| train/ | | +| approx_kl | 1.6932104 | +| clip_fraction | 0.508 | +| clip_range | 0.2 | +| entropy_loss | -0.472 | +| explained_variance | -1.73 | +| learning_rate | 0.0001 | +| loss | -0.0727 | +| n_updates | 138280 | +| policy_gradient_loss | -0.0724 | +| value_loss | 0.000504 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.22 | +| time/ | | +| fps | 309 | +| iterations | 7777 | +| time_elapsed | 25726 | +| total_timesteps | 7963648 | +| train/ | | +| approx_kl | 1.8757255 | +| clip_fraction | 0.484 | +| clip_range | 0.2 | +| entropy_loss | -0.416 | +| explained_variance | -2.85 | +| learning_rate | 0.0001 | +| loss | -0.0783 | +| n_updates | 138290 | +| policy_gradient_loss | -0.0614 | +| value_loss | 0.000222 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.214 | +| time/ | | +| fps | 309 | +| iterations | 7778 | +| time_elapsed | 25729 | +| total_timesteps | 7964672 | +| train/ | | +| approx_kl | 1.8492821 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.438 | +| explained_variance | -0.767 | +| learning_rate | 0.0001 | +| loss | -0.078 | +| n_updates | 138300 | +| policy_gradient_loss | -0.0561 | +| value_loss | 0.000245 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.214 | +| time/ | | +| fps | 309 | +| iterations | 7779 | +| time_elapsed | 25732 | +| total_timesteps | 7965696 | +| train/ | | +| approx_kl | 1.9385091 | +| clip_fraction | 0.509 | +| clip_range | 0.2 | +| entropy_loss | -0.427 | +| explained_variance | -2.25 | +| learning_rate | 0.0001 | +| loss | -0.0769 | +| n_updates | 138310 | +| policy_gradient_loss | -0.073 | +| value_loss | 0.000498 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.218 | +| time/ | | +| fps | 309 | +| iterations | 7780 | +| time_elapsed | 25736 | +| total_timesteps | 7966720 | +| train/ | | +| approx_kl | 2.3776634 | +| clip_fraction | 0.508 | +| clip_range | 0.2 | +| entropy_loss | -0.39 | +| explained_variance | -1.41 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 138320 | +| policy_gradient_loss | -0.0779 | +| value_loss | 0.000657 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.218 | +| time/ | | +| fps | 309 | +| iterations | 7781 | +| time_elapsed | 25739 | +| total_timesteps | 7967744 | +| train/ | | +| approx_kl | 1.4470224 | +| clip_fraction | 0.492 | +| clip_range | 0.2 | +| entropy_loss | -0.478 | +| explained_variance | -5.38 | +| learning_rate | 0.0001 | +| loss | -0.0452 | +| n_updates | 138330 | +| policy_gradient_loss | -0.0751 | +| value_loss | 0.000257 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.217 | +| time/ | | +| fps | 309 | +| iterations | 7782 | +| time_elapsed | 25742 | +| total_timesteps | 7968768 | +| train/ | | +| approx_kl | 1.6091521 | +| clip_fraction | 0.477 | +| clip_range | 0.2 | +| entropy_loss | -0.459 | +| explained_variance | -1.98 | +| learning_rate | 0.0001 | +| loss | -0.0849 | +| n_updates | 138340 | +| policy_gradient_loss | -0.0665 | +| value_loss | 0.000374 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.212 | +| time/ | | +| fps | 309 | +| iterations | 7783 | +| time_elapsed | 25746 | +| total_timesteps | 7969792 | +| train/ | | +| approx_kl | 1.6483172 | +| clip_fraction | 0.482 | +| clip_range | 0.2 | +| entropy_loss | -0.419 | +| explained_variance | -0.921 | +| learning_rate | 0.0001 | +| loss | -0.0985 | +| n_updates | 138350 | +| policy_gradient_loss | -0.0622 | +| value_loss | 0.000578 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.212 | +| time/ | | +| fps | 309 | +| iterations | 7784 | +| time_elapsed | 25749 | +| total_timesteps | 7970816 | +| train/ | | +| approx_kl | 2.2544055 | +| clip_fraction | 0.466 | +| clip_range | 0.2 | +| entropy_loss | -0.423 | +| explained_variance | -1.5 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 138360 | +| policy_gradient_loss | -0.0714 | +| value_loss | 0.00054 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.21 | +| time/ | | +| fps | 309 | +| iterations | 7785 | +| time_elapsed | 25752 | +| total_timesteps | 7971840 | +| train/ | | +| approx_kl | 2.1220741 | +| clip_fraction | 0.507 | +| clip_range | 0.2 | +| entropy_loss | -0.428 | +| explained_variance | -5.67 | +| learning_rate | 0.0001 | +| loss | -0.116 | +| n_updates | 138370 | +| policy_gradient_loss | -0.0792 | +| value_loss | 0.000429 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.207 | +| time/ | | +| fps | 309 | +| iterations | 7786 | +| time_elapsed | 25755 | +| total_timesteps | 7972864 | +| train/ | | +| approx_kl | 2.6243572 | +| clip_fraction | 0.49 | +| clip_range | 0.2 | +| entropy_loss | -0.386 | +| explained_variance | -2.45 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 138380 | +| policy_gradient_loss | -0.078 | +| value_loss | 0.000576 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.207 | +| time/ | | +| fps | 309 | +| iterations | 7787 | +| time_elapsed | 25758 | +| total_timesteps | 7973888 | +| train/ | | +| approx_kl | 2.4490075 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.386 | +| explained_variance | -3.04 | +| learning_rate | 0.0001 | +| loss | -0.0891 | +| n_updates | 138390 | +| policy_gradient_loss | -0.0658 | +| value_loss | 0.000657 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.201 | +| time/ | | +| fps | 309 | +| iterations | 7788 | +| time_elapsed | 25762 | +| total_timesteps | 7974912 | +| train/ | | +| approx_kl | 2.0650306 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.421 | +| explained_variance | -4.03 | +| learning_rate | 0.0001 | +| loss | -0.107 | +| n_updates | 138400 | +| policy_gradient_loss | -0.0747 | +| value_loss | 0.00033 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.201 | +| time/ | | +| fps | 309 | +| iterations | 7789 | +| time_elapsed | 25765 | +| total_timesteps | 7975936 | +| train/ | | +| approx_kl | 3.0594282 | +| clip_fraction | 0.494 | +| clip_range | 0.2 | +| entropy_loss | -0.462 | +| explained_variance | -1.95 | +| learning_rate | 0.0001 | +| loss | -0.0983 | +| n_updates | 138410 | +| policy_gradient_loss | -0.067 | +| value_loss | 0.000596 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.201 | +| time/ | | +| fps | 309 | +| iterations | 7790 | +| time_elapsed | 25768 | +| total_timesteps | 7976960 | +| train/ | | +| approx_kl | 2.3700433 | +| clip_fraction | 0.491 | +| clip_range | 0.2 | +| entropy_loss | -0.421 | +| explained_variance | -1.18 | +| learning_rate | 0.0001 | +| loss | -0.09 | +| n_updates | 138420 | +| policy_gradient_loss | -0.0675 | +| value_loss | 0.00103 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.2 | +| time/ | | +| fps | 309 | +| iterations | 7791 | +| time_elapsed | 25771 | +| total_timesteps | 7977984 | +| train/ | | +| approx_kl | 1.755697 | +| clip_fraction | 0.427 | +| clip_range | 0.2 | +| entropy_loss | -0.362 | +| explained_variance | -3.4 | +| learning_rate | 0.0001 | +| loss | -0.0925 | +| n_updates | 138430 | +| policy_gradient_loss | -0.0705 | +| value_loss | 0.000439 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.2 | +| time/ | | +| fps | 309 | +| iterations | 7792 | +| time_elapsed | 25774 | +| total_timesteps | 7979008 | +| train/ | | +| approx_kl | 1.6031203 | +| clip_fraction | 0.444 | +| clip_range | 0.2 | +| entropy_loss | -0.393 | +| explained_variance | -2.26 | +| learning_rate | 0.0001 | +| loss | -0.0947 | +| n_updates | 138440 | +| policy_gradient_loss | -0.0667 | +| value_loss | 0.000285 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.202 | +| time/ | | +| fps | 309 | +| iterations | 7793 | +| time_elapsed | 25777 | +| total_timesteps | 7980032 | +| train/ | | +| approx_kl | 1.9054155 | +| clip_fraction | 0.502 | +| clip_range | 0.2 | +| entropy_loss | -0.461 | +| explained_variance | -1.3 | +| learning_rate | 0.0001 | +| loss | -0.053 | +| n_updates | 138450 | +| policy_gradient_loss | -0.0694 | +| value_loss | 0.000446 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.197 | +| time/ | | +| fps | 309 | +| iterations | 7794 | +| time_elapsed | 25781 | +| total_timesteps | 7981056 | +| train/ | | +| approx_kl | 2.2011132 | +| clip_fraction | 0.452 | +| clip_range | 0.2 | +| entropy_loss | -0.351 | +| explained_variance | -1.64 | +| learning_rate | 0.0001 | +| loss | -0.0844 | +| n_updates | 138460 | +| policy_gradient_loss | -0.068 | +| value_loss | 0.000647 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.197 | +| time/ | | +| fps | 309 | +| iterations | 7795 | +| time_elapsed | 25784 | +| total_timesteps | 7982080 | +| train/ | | +| approx_kl | 2.2175846 | +| clip_fraction | 0.472 | +| clip_range | 0.2 | +| entropy_loss | -0.423 | +| explained_variance | -1.66 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 138470 | +| policy_gradient_loss | -0.074 | +| value_loss | 0.00058 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.192 | +| time/ | | +| fps | 309 | +| iterations | 7796 | +| time_elapsed | 25788 | +| total_timesteps | 7983104 | +| train/ | | +| approx_kl | 2.3702507 | +| clip_fraction | 0.479 | +| clip_range | 0.2 | +| entropy_loss | -0.387 | +| explained_variance | -1.59 | +| learning_rate | 0.0001 | +| loss | -0.0974 | +| n_updates | 138480 | +| policy_gradient_loss | -0.0735 | +| value_loss | 0.000531 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.187 | +| time/ | | +| fps | 309 | +| iterations | 7797 | +| time_elapsed | 25791 | +| total_timesteps | 7984128 | +| train/ | | +| approx_kl | 2.0441916 | +| clip_fraction | 0.452 | +| clip_range | 0.2 | +| entropy_loss | -0.36 | +| explained_variance | -1.75 | +| learning_rate | 0.0001 | +| loss | -0.105 | +| n_updates | 138490 | +| policy_gradient_loss | -0.0707 | +| value_loss | 0.000653 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.187 | +| time/ | | +| fps | 309 | +| iterations | 7798 | +| time_elapsed | 25794 | +| total_timesteps | 7985152 | +| train/ | | +| approx_kl | 2.4689386 | +| clip_fraction | 0.457 | +| clip_range | 0.2 | +| entropy_loss | -0.333 | +| explained_variance | -3.69 | +| learning_rate | 0.0001 | +| loss | -0.0943 | +| n_updates | 138500 | +| policy_gradient_loss | -0.0715 | +| value_loss | 0.000541 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.187 | +| time/ | | +| fps | 309 | +| iterations | 7799 | +| time_elapsed | 25798 | +| total_timesteps | 7986176 | +| train/ | | +| approx_kl | 2.8066444 | +| clip_fraction | 0.496 | +| clip_range | 0.2 | +| entropy_loss | -0.42 | +| explained_variance | -1.61 | +| learning_rate | 0.0001 | +| loss | -0.115 | +| n_updates | 138510 | +| policy_gradient_loss | -0.0707 | +| value_loss | 0.000723 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.187 | +| time/ | | +| fps | 309 | +| iterations | 7800 | +| time_elapsed | 25801 | +| total_timesteps | 7987200 | +| train/ | | +| approx_kl | 2.1018825 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.404 | +| explained_variance | -2.37 | +| learning_rate | 0.0001 | +| loss | -0.0951 | +| n_updates | 138520 | +| policy_gradient_loss | -0.0689 | +| value_loss | 0.000429 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.187 | +| time/ | | +| fps | 309 | +| iterations | 7801 | +| time_elapsed | 25805 | +| total_timesteps | 7988224 | +| train/ | | +| approx_kl | 2.596427 | +| clip_fraction | 0.503 | +| clip_range | 0.2 | +| entropy_loss | -0.414 | +| explained_variance | -1.19 | +| learning_rate | 0.0001 | +| loss | -0.082 | +| n_updates | 138530 | +| policy_gradient_loss | -0.0705 | +| value_loss | 0.000556 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.187 | +| time/ | | +| fps | 309 | +| iterations | 7802 | +| time_elapsed | 25808 | +| total_timesteps | 7989248 | +| train/ | | +| approx_kl | 2.4460654 | +| clip_fraction | 0.429 | +| clip_range | 0.2 | +| entropy_loss | -0.362 | +| explained_variance | -1.37 | +| learning_rate | 0.0001 | +| loss | -0.085 | +| n_updates | 138540 | +| policy_gradient_loss | -0.0653 | +| value_loss | 0.00065 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.191 | +| time/ | | +| fps | 309 | +| iterations | 7803 | +| time_elapsed | 25811 | +| total_timesteps | 7990272 | +| train/ | | +| approx_kl | 1.8200557 | +| clip_fraction | 0.502 | +| clip_range | 0.2 | +| entropy_loss | -0.413 | +| explained_variance | -1.73 | +| learning_rate | 0.0001 | +| loss | -0.075 | +| n_updates | 138550 | +| policy_gradient_loss | -0.0725 | +| value_loss | 0.000556 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.191 | +| time/ | | +| fps | 309 | +| iterations | 7804 | +| time_elapsed | 25815 | +| total_timesteps | 7991296 | +| train/ | | +| approx_kl | 2.6336327 | +| clip_fraction | 0.479 | +| clip_range | 0.2 | +| entropy_loss | -0.362 | +| explained_variance | -2.67 | +| learning_rate | 0.0001 | +| loss | -0.0857 | +| n_updates | 138560 | +| policy_gradient_loss | -0.0696 | +| value_loss | 0.00051 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.196 | +| time/ | | +| fps | 309 | +| iterations | 7805 | +| time_elapsed | 25818 | +| total_timesteps | 7992320 | +| train/ | | +| approx_kl | 2.061451 | +| clip_fraction | 0.488 | +| clip_range | 0.2 | +| entropy_loss | -0.368 | +| explained_variance | -2.65 | +| learning_rate | 0.0001 | +| loss | -0.109 | +| n_updates | 138570 | +| policy_gradient_loss | -0.0661 | +| value_loss | 0.000725 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.196 | +| time/ | | +| fps | 309 | +| iterations | 7806 | +| time_elapsed | 25821 | +| total_timesteps | 7993344 | +| train/ | | +| approx_kl | 2.3113217 | +| clip_fraction | 0.495 | +| clip_range | 0.2 | +| entropy_loss | -0.392 | +| explained_variance | -1.56 | +| learning_rate | 0.0001 | +| loss | -0.0633 | +| n_updates | 138580 | +| policy_gradient_loss | -0.071 | +| value_loss | 0.000535 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.2 | +| time/ | | +| fps | 309 | +| iterations | 7807 | +| time_elapsed | 25824 | +| total_timesteps | 7994368 | +| train/ | | +| approx_kl | 2.4573967 | +| clip_fraction | 0.536 | +| clip_range | 0.2 | +| entropy_loss | -0.426 | +| explained_variance | -7.85 | +| learning_rate | 0.0001 | +| loss | -0.117 | +| n_updates | 138590 | +| policy_gradient_loss | -0.0751 | +| value_loss | 0.000492 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.203 | +| time/ | | +| fps | 309 | +| iterations | 7808 | +| time_elapsed | 25827 | +| total_timesteps | 7995392 | +| train/ | | +| approx_kl | 3.409102 | +| clip_fraction | 0.468 | +| clip_range | 0.2 | +| entropy_loss | -0.363 | +| explained_variance | -2.14 | +| learning_rate | 0.0001 | +| loss | -0.0602 | +| n_updates | 138600 | +| policy_gradient_loss | -0.0682 | +| value_loss | 0.000565 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.203 | +| time/ | | +| fps | 309 | +| iterations | 7809 | +| time_elapsed | 25831 | +| total_timesteps | 7996416 | +| train/ | | +| approx_kl | 2.0454152 | +| clip_fraction | 0.514 | +| clip_range | 0.2 | +| entropy_loss | -0.414 | +| explained_variance | -2.22 | +| learning_rate | 0.0001 | +| loss | -0.0876 | +| n_updates | 138610 | +| policy_gradient_loss | -0.0713 | +| value_loss | 0.00053 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.205 | +| time/ | | +| fps | 309 | +| iterations | 7810 | +| time_elapsed | 25834 | +| total_timesteps | 7997440 | +| train/ | | +| approx_kl | 2.6026235 | +| clip_fraction | 0.521 | +| clip_range | 0.2 | +| entropy_loss | -0.455 | +| explained_variance | -0.883 | +| learning_rate | 0.0001 | +| loss | -0.0958 | +| n_updates | 138620 | +| policy_gradient_loss | -0.0672 | +| value_loss | 0.000797 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.205 | +| time/ | | +| fps | 309 | +| iterations | 7811 | +| time_elapsed | 25837 | +| total_timesteps | 7998464 | +| train/ | | +| approx_kl | 4.322837 | +| clip_fraction | 0.484 | +| clip_range | 0.2 | +| entropy_loss | -0.365 | +| explained_variance | -2.43 | +| learning_rate | 0.0001 | +| loss | -0.0949 | +| n_updates | 138630 | +| policy_gradient_loss | -0.0713 | +| value_loss | 0.000624 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.202 | +| time/ | | +| fps | 309 | +| iterations | 7812 | +| time_elapsed | 25840 | +| total_timesteps | 7999488 | +| train/ | | +| approx_kl | 1.6846848 | +| clip_fraction | 0.477 | +| clip_range | 0.2 | +| entropy_loss | -0.394 | +| explained_variance | -3.69 | +| learning_rate | 0.0001 | +| loss | -0.089 | +| n_updates | 138640 | +| policy_gradient_loss | -0.0665 | +| value_loss | 0.000727 | +--------------------------------------- + +Current state: Champion.Level9.RyuVsBalrog +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.211 | +| time/ | | +| fps | 309 | +| iterations | 7813 | +| time_elapsed | 25844 | +| total_timesteps | 8000512 | +| train/ | | +| approx_kl | 2.3200195 | +| clip_fraction | 0.49 | +| clip_range | 0.2 | +| entropy_loss | -0.381 | +| explained_variance | -0.81 | +| learning_rate | 0.0001 | +| loss | -0.084 | +| n_updates | 138650 | +| policy_gradient_loss | -0.0652 | +| value_loss | 0.000784 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.211 | +| time/ | | +| fps | 309 | +| iterations | 7814 | +| time_elapsed | 25847 | +| total_timesteps | 8001536 | +| train/ | | +| approx_kl | 2.5707216 | +| clip_fraction | 0.51 | +| clip_range | 0.2 | +| entropy_loss | -0.362 | +| explained_variance | -1.54 | +| learning_rate | 0.0001 | +| loss | -0.0833 | +| n_updates | 138660 | +| policy_gradient_loss | -0.0717 | +| value_loss | 0.000608 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.7e+03 | +| ep_rew_mean | 0.216 | +| time/ | | +| fps | 309 | +| iterations | 7815 | +| time_elapsed | 25851 | +| total_timesteps | 8002560 | +| train/ | | +| approx_kl | 3.6355324 | +| clip_fraction | 0.466 | +| clip_range | 0.2 | +| entropy_loss | -0.306 | +| explained_variance | -3.1 | +| learning_rate | 0.0001 | +| loss | -0.0877 | +| n_updates | 138670 | +| policy_gradient_loss | -0.0506 | +| value_loss | 0.00053 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.212 | +| time/ | | +| fps | 309 | +| iterations | 7816 | +| time_elapsed | 25854 | +| total_timesteps | 8003584 | +| train/ | | +| approx_kl | 2.870841 | +| clip_fraction | 0.508 | +| clip_range | 0.2 | +| entropy_loss | -0.325 | +| explained_variance | -0.772 | +| learning_rate | 0.0001 | +| loss | -0.0858 | +| n_updates | 138680 | +| policy_gradient_loss | -0.0573 | +| value_loss | 0.000823 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.212 | +| time/ | | +| fps | 309 | +| iterations | 7817 | +| time_elapsed | 25858 | +| total_timesteps | 8004608 | +| train/ | | +| approx_kl | 3.375627 | +| clip_fraction | 0.454 | +| clip_range | 0.2 | +| entropy_loss | -0.278 | +| explained_variance | -0.434 | +| learning_rate | 0.0001 | +| loss | -0.0631 | +| n_updates | 138690 | +| policy_gradient_loss | -0.0636 | +| value_loss | 0.00108 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.21 | +| time/ | | +| fps | 309 | +| iterations | 7818 | +| time_elapsed | 25861 | +| total_timesteps | 8005632 | +| train/ | | +| approx_kl | 3.8336134 | +| clip_fraction | 0.451 | +| clip_range | 0.2 | +| entropy_loss | -0.255 | +| explained_variance | -0.928 | +| learning_rate | 0.0001 | +| loss | -0.108 | +| n_updates | 138700 | +| policy_gradient_loss | -0.0674 | +| value_loss | 0.000876 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.213 | +| time/ | | +| fps | 309 | +| iterations | 7819 | +| time_elapsed | 25865 | +| total_timesteps | 8006656 | +| train/ | | +| approx_kl | 2.887936 | +| clip_fraction | 0.492 | +| clip_range | 0.2 | +| entropy_loss | -0.297 | +| explained_variance | -1.73 | +| learning_rate | 0.0001 | +| loss | -0.1 | +| n_updates | 138710 | +| policy_gradient_loss | -0.0697 | +| value_loss | 0.00105 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | 0.215 | +| time/ | | +| fps | 309 | +| iterations | 7820 | +| time_elapsed | 25868 | +| total_timesteps | 8007680 | +| train/ | | +| approx_kl | 2.5520792 | +| clip_fraction | 0.453 | +| clip_range | 0.2 | +| entropy_loss | -0.289 | +| explained_variance | -0.545 | +| learning_rate | 0.0001 | +| loss | -0.0564 | +| n_updates | 138720 | +| policy_gradient_loss | -0.0614 | +| value_loss | 0.000866 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | 0.213 | +| time/ | | +| fps | 309 | +| iterations | 7821 | +| time_elapsed | 25871 | +| total_timesteps | 8008704 | +| train/ | | +| approx_kl | 2.363491 | +| clip_fraction | 0.425 | +| clip_range | 0.2 | +| entropy_loss | -0.268 | +| explained_variance | -2.69 | +| learning_rate | 0.0001 | +| loss | -0.0728 | +| n_updates | 138730 | +| policy_gradient_loss | -0.0568 | +| value_loss | 0.000727 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.65e+03 | +| ep_rew_mean | 0.212 | +| time/ | | +| fps | 309 | +| iterations | 7822 | +| time_elapsed | 25874 | +| total_timesteps | 8009728 | +| train/ | | +| approx_kl | 2.5606337 | +| clip_fraction | 0.425 | +| clip_range | 0.2 | +| entropy_loss | -0.257 | +| explained_variance | -1.72 | +| learning_rate | 0.0001 | +| loss | -0.0664 | +| n_updates | 138740 | +| policy_gradient_loss | -0.0569 | +| value_loss | 0.000806 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.64e+03 | +| ep_rew_mean | 0.208 | +| time/ | | +| fps | 309 | +| iterations | 7823 | +| time_elapsed | 25878 | +| total_timesteps | 8010752 | +| train/ | | +| approx_kl | 3.21778 | +| clip_fraction | 0.437 | +| clip_range | 0.2 | +| entropy_loss | -0.271 | +| explained_variance | -0.701 | +| learning_rate | 0.0001 | +| loss | -0.0728 | +| n_updates | 138750 | +| policy_gradient_loss | -0.059 | +| value_loss | 0.000648 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.64e+03 | +| ep_rew_mean | 0.208 | +| time/ | | +| fps | 309 | +| iterations | 7824 | +| time_elapsed | 25881 | +| total_timesteps | 8011776 | +| train/ | | +| approx_kl | 2.485496 | +| clip_fraction | 0.486 | +| clip_range | 0.2 | +| entropy_loss | -0.309 | +| explained_variance | -1.74 | +| learning_rate | 0.0001 | +| loss | -0.0913 | +| n_updates | 138760 | +| policy_gradient_loss | -0.0641 | +| value_loss | 0.000691 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.65e+03 | +| ep_rew_mean | 0.212 | +| time/ | | +| fps | 309 | +| iterations | 7825 | +| time_elapsed | 25884 | +| total_timesteps | 8012800 | +| train/ | | +| approx_kl | 2.5616531 | +| clip_fraction | 0.432 | +| clip_range | 0.2 | +| entropy_loss | -0.283 | +| explained_variance | -1.32 | +| learning_rate | 0.0001 | +| loss | -0.0855 | +| n_updates | 138770 | +| policy_gradient_loss | -0.0559 | +| value_loss | 0.000462 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.65e+03 | +| ep_rew_mean | 0.212 | +| time/ | | +| fps | 309 | +| iterations | 7826 | +| time_elapsed | 25887 | +| total_timesteps | 8013824 | +| train/ | | +| approx_kl | 3.6605587 | +| clip_fraction | 0.469 | +| clip_range | 0.2 | +| entropy_loss | -0.294 | +| explained_variance | -1.75 | +| learning_rate | 0.0001 | +| loss | -0.0896 | +| n_updates | 138780 | +| policy_gradient_loss | -0.0593 | +| value_loss | 0.00041 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.65e+03 | +| ep_rew_mean | 0.212 | +| time/ | | +| fps | 309 | +| iterations | 7827 | +| time_elapsed | 25890 | +| total_timesteps | 8014848 | +| train/ | | +| approx_kl | 2.603846 | +| clip_fraction | 0.454 | +| clip_range | 0.2 | +| entropy_loss | -0.271 | +| explained_variance | -1.76 | +| learning_rate | 0.0001 | +| loss | -0.0775 | +| n_updates | 138790 | +| policy_gradient_loss | -0.0603 | +| value_loss | 0.000567 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.65e+03 | +| ep_rew_mean | 0.212 | +| time/ | | +| fps | 309 | +| iterations | 7828 | +| time_elapsed | 25893 | +| total_timesteps | 8015872 | +| train/ | | +| approx_kl | 2.5478818 | +| clip_fraction | 0.438 | +| clip_range | 0.2 | +| entropy_loss | -0.279 | +| explained_variance | -1.14 | +| learning_rate | 0.0001 | +| loss | -0.0865 | +| n_updates | 138800 | +| policy_gradient_loss | -0.0616 | +| value_loss | 0.000662 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.63e+03 | +| ep_rew_mean | 0.211 | +| time/ | | +| fps | 309 | +| iterations | 7829 | +| time_elapsed | 25897 | +| total_timesteps | 8016896 | +| train/ | | +| approx_kl | 2.8064327 | +| clip_fraction | 0.447 | +| clip_range | 0.2 | +| entropy_loss | -0.265 | +| explained_variance | -0.988 | +| learning_rate | 0.0001 | +| loss | -0.0793 | +| n_updates | 138810 | +| policy_gradient_loss | -0.0609 | +| value_loss | 0.000848 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.63e+03 | +| ep_rew_mean | 0.211 | +| time/ | | +| fps | 309 | +| iterations | 7830 | +| time_elapsed | 25900 | +| total_timesteps | 8017920 | +| train/ | | +| approx_kl | 2.9317029 | +| clip_fraction | 0.446 | +| clip_range | 0.2 | +| entropy_loss | -0.267 | +| explained_variance | -1.01 | +| learning_rate | 0.0001 | +| loss | -0.0859 | +| n_updates | 138820 | +| policy_gradient_loss | -0.061 | +| value_loss | 0.00071 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.61e+03 | +| ep_rew_mean | 0.21 | +| time/ | | +| fps | 309 | +| iterations | 7831 | +| time_elapsed | 25903 | +| total_timesteps | 8018944 | +| train/ | | +| approx_kl | 2.5976691 | +| clip_fraction | 0.43 | +| clip_range | 0.2 | +| entropy_loss | -0.263 | +| explained_variance | -2.13 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 138830 | +| policy_gradient_loss | -0.0636 | +| value_loss | 0.000583 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.61e+03 | +| ep_rew_mean | 0.208 | +| time/ | | +| fps | 309 | +| iterations | 7832 | +| time_elapsed | 25907 | +| total_timesteps | 8019968 | +| train/ | | +| approx_kl | 2.556322 | +| clip_fraction | 0.427 | +| clip_range | 0.2 | +| entropy_loss | -0.272 | +| explained_variance | -1.76 | +| learning_rate | 0.0001 | +| loss | -0.086 | +| n_updates | 138840 | +| policy_gradient_loss | -0.0557 | +| value_loss | 0.000646 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | 0.208 | +| time/ | | +| fps | 309 | +| iterations | 7833 | +| time_elapsed | 25910 | +| total_timesteps | 8020992 | +| train/ | | +| approx_kl | 2.5482092 | +| clip_fraction | 0.444 | +| clip_range | 0.2 | +| entropy_loss | -0.29 | +| explained_variance | -1.6 | +| learning_rate | 0.0001 | +| loss | -0.0504 | +| n_updates | 138850 | +| policy_gradient_loss | -0.0604 | +| value_loss | 0.000607 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | 0.205 | +| time/ | | +| fps | 309 | +| iterations | 7834 | +| time_elapsed | 25914 | +| total_timesteps | 8022016 | +| train/ | | +| approx_kl | 2.330305 | +| clip_fraction | 0.415 | +| clip_range | 0.2 | +| entropy_loss | -0.252 | +| explained_variance | -1.27 | +| learning_rate | 0.0001 | +| loss | -0.0921 | +| n_updates | 138860 | +| policy_gradient_loss | -0.0545 | +| value_loss | 0.000807 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.58e+03 | +| ep_rew_mean | 0.206 | +| time/ | | +| fps | 309 | +| iterations | 7835 | +| time_elapsed | 25917 | +| total_timesteps | 8023040 | +| train/ | | +| approx_kl | 2.6719103 | +| clip_fraction | 0.479 | +| clip_range | 0.2 | +| entropy_loss | -0.294 | +| explained_variance | -3.55 | +| learning_rate | 0.0001 | +| loss | -0.0739 | +| n_updates | 138870 | +| policy_gradient_loss | -0.0637 | +| value_loss | 0.000715 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.57e+03 | +| ep_rew_mean | 0.202 | +| time/ | | +| fps | 309 | +| iterations | 7836 | +| time_elapsed | 25921 | +| total_timesteps | 8024064 | +| train/ | | +| approx_kl | 4.506192 | +| clip_fraction | 0.447 | +| clip_range | 0.2 | +| entropy_loss | -0.264 | +| explained_variance | -0.937 | +| learning_rate | 0.0001 | +| loss | -0.0997 | +| n_updates | 138880 | +| policy_gradient_loss | -0.0643 | +| value_loss | 0.000674 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.57e+03 | +| ep_rew_mean | 0.205 | +| time/ | | +| fps | 309 | +| iterations | 7837 | +| time_elapsed | 25924 | +| total_timesteps | 8025088 | +| train/ | | +| approx_kl | 2.4341066 | +| clip_fraction | 0.446 | +| clip_range | 0.2 | +| entropy_loss | -0.29 | +| explained_variance | -1.35 | +| learning_rate | 0.0001 | +| loss | -0.0787 | +| n_updates | 138890 | +| policy_gradient_loss | -0.0651 | +| value_loss | 0.000932 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.56e+03 | +| ep_rew_mean | 0.206 | +| time/ | | +| fps | 309 | +| iterations | 7838 | +| time_elapsed | 25928 | +| total_timesteps | 8026112 | +| train/ | | +| approx_kl | 2.6673548 | +| clip_fraction | 0.454 | +| clip_range | 0.2 | +| entropy_loss | -0.283 | +| explained_variance | -0.773 | +| learning_rate | 0.0001 | +| loss | -0.0945 | +| n_updates | 138900 | +| policy_gradient_loss | -0.0582 | +| value_loss | 0.000804 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.56e+03 | +| ep_rew_mean | 0.202 | +| time/ | | +| fps | 309 | +| iterations | 7839 | +| time_elapsed | 25931 | +| total_timesteps | 8027136 | +| train/ | | +| approx_kl | 2.3794155 | +| clip_fraction | 0.412 | +| clip_range | 0.2 | +| entropy_loss | -0.261 | +| explained_variance | -1.54 | +| learning_rate | 0.0001 | +| loss | -0.0697 | +| n_updates | 138910 | +| policy_gradient_loss | -0.0548 | +| value_loss | 0.000851 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.56e+03 | +| ep_rew_mean | 0.202 | +| time/ | | +| fps | 309 | +| iterations | 7840 | +| time_elapsed | 25934 | +| total_timesteps | 8028160 | +| train/ | | +| approx_kl | 2.7735615 | +| clip_fraction | 0.428 | +| clip_range | 0.2 | +| entropy_loss | -0.223 | +| explained_variance | -2.25 | +| learning_rate | 0.0001 | +| loss | -0.0762 | +| n_updates | 138920 | +| policy_gradient_loss | -0.0582 | +| value_loss | 0.000818 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.54e+03 | +| ep_rew_mean | 0.203 | +| time/ | | +| fps | 309 | +| iterations | 7841 | +| time_elapsed | 25937 | +| total_timesteps | 8029184 | +| train/ | | +| approx_kl | 2.896651 | +| clip_fraction | 0.371 | +| clip_range | 0.2 | +| entropy_loss | -0.211 | +| explained_variance | -0.625 | +| learning_rate | 0.0001 | +| loss | -0.0567 | +| n_updates | 138930 | +| policy_gradient_loss | -0.0487 | +| value_loss | 0.000869 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.53e+03 | +| ep_rew_mean | 0.201 | +| time/ | | +| fps | 309 | +| iterations | 7842 | +| time_elapsed | 25941 | +| total_timesteps | 8030208 | +| train/ | | +| approx_kl | 2.4579158 | +| clip_fraction | 0.438 | +| clip_range | 0.2 | +| entropy_loss | -0.271 | +| explained_variance | -6.1 | +| learning_rate | 0.0001 | +| loss | -0.0929 | +| n_updates | 138940 | +| policy_gradient_loss | -0.0667 | +| value_loss | 0.000615 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.52e+03 | +| ep_rew_mean | 0.205 | +| time/ | | +| fps | 309 | +| iterations | 7843 | +| time_elapsed | 25944 | +| total_timesteps | 8031232 | +| train/ | | +| approx_kl | 4.17336 | +| clip_fraction | 0.419 | +| clip_range | 0.2 | +| entropy_loss | -0.257 | +| explained_variance | -0.968 | +| learning_rate | 0.0001 | +| loss | -0.0821 | +| n_updates | 138950 | +| policy_gradient_loss | -0.0582 | +| value_loss | 0.000683 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.52e+03 | +| ep_rew_mean | 0.205 | +| time/ | | +| fps | 309 | +| iterations | 7844 | +| time_elapsed | 25947 | +| total_timesteps | 8032256 | +| train/ | | +| approx_kl | 2.5874507 | +| clip_fraction | 0.45 | +| clip_range | 0.2 | +| entropy_loss | -0.272 | +| explained_variance | -2.96 | +| learning_rate | 0.0001 | +| loss | -0.078 | +| n_updates | 138960 | +| policy_gradient_loss | -0.065 | +| value_loss | 0.000682 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.52e+03 | +| ep_rew_mean | 0.207 | +| time/ | | +| fps | 309 | +| iterations | 7845 | +| time_elapsed | 25950 | +| total_timesteps | 8033280 | +| train/ | | +| approx_kl | 3.2032118 | +| clip_fraction | 0.447 | +| clip_range | 0.2 | +| entropy_loss | -0.3 | +| explained_variance | -1.29 | +| learning_rate | 0.0001 | +| loss | -0.0852 | +| n_updates | 138970 | +| policy_gradient_loss | -0.0583 | +| value_loss | 0.00076 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.52e+03 | +| ep_rew_mean | 0.21 | +| time/ | | +| fps | 309 | +| iterations | 7846 | +| time_elapsed | 25953 | +| total_timesteps | 8034304 | +| train/ | | +| approx_kl | 3.1886883 | +| clip_fraction | 0.443 | +| clip_range | 0.2 | +| entropy_loss | -0.275 | +| explained_variance | -1.29 | +| learning_rate | 0.0001 | +| loss | -0.0913 | +| n_updates | 138980 | +| policy_gradient_loss | -0.062 | +| value_loss | 0.000799 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.51e+03 | +| ep_rew_mean | 0.206 | +| time/ | | +| fps | 309 | +| iterations | 7847 | +| time_elapsed | 25957 | +| total_timesteps | 8035328 | +| train/ | | +| approx_kl | 2.8440177 | +| clip_fraction | 0.419 | +| clip_range | 0.2 | +| entropy_loss | -0.227 | +| explained_variance | -3.05 | +| learning_rate | 0.0001 | +| loss | -0.096 | +| n_updates | 138990 | +| policy_gradient_loss | -0.0598 | +| value_loss | 0.000969 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.49e+03 | +| ep_rew_mean | 0.205 | +| time/ | | +| fps | 309 | +| iterations | 7848 | +| time_elapsed | 25960 | +| total_timesteps | 8036352 | +| train/ | | +| approx_kl | 2.7434618 | +| clip_fraction | 0.392 | +| clip_range | 0.2 | +| entropy_loss | -0.236 | +| explained_variance | -2.44 | +| learning_rate | 0.0001 | +| loss | -0.0576 | +| n_updates | 139000 | +| policy_gradient_loss | -0.0588 | +| value_loss | 0.00076 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.48e+03 | +| ep_rew_mean | 0.205 | +| time/ | | +| fps | 309 | +| iterations | 7849 | +| time_elapsed | 25963 | +| total_timesteps | 8037376 | +| train/ | | +| approx_kl | 5.1218843 | +| clip_fraction | 0.407 | +| clip_range | 0.2 | +| entropy_loss | -0.238 | +| explained_variance | -1.03 | +| learning_rate | 0.0001 | +| loss | -0.0609 | +| n_updates | 139010 | +| policy_gradient_loss | -0.0547 | +| value_loss | 0.000686 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.49e+03 | +| ep_rew_mean | 0.213 | +| time/ | | +| fps | 309 | +| iterations | 7850 | +| time_elapsed | 25967 | +| total_timesteps | 8038400 | +| train/ | | +| approx_kl | 2.3588166 | +| clip_fraction | 0.383 | +| clip_range | 0.2 | +| entropy_loss | -0.2 | +| explained_variance | -0.657 | +| learning_rate | 0.0001 | +| loss | -0.0933 | +| n_updates | 139020 | +| policy_gradient_loss | -0.0528 | +| value_loss | 0.00104 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.49e+03 | +| ep_rew_mean | 0.213 | +| time/ | | +| fps | 309 | +| iterations | 7851 | +| time_elapsed | 25970 | +| total_timesteps | 8039424 | +| train/ | | +| approx_kl | 2.5294433 | +| clip_fraction | 0.392 | +| clip_range | 0.2 | +| entropy_loss | -0.225 | +| explained_variance | -1.13 | +| learning_rate | 0.0001 | +| loss | -0.0773 | +| n_updates | 139030 | +| policy_gradient_loss | -0.0597 | +| value_loss | 0.000736 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.49e+03 | +| ep_rew_mean | 0.212 | +| time/ | | +| fps | 309 | +| iterations | 7852 | +| time_elapsed | 25974 | +| total_timesteps | 8040448 | +| train/ | | +| approx_kl | 3.466424 | +| clip_fraction | 0.43 | +| clip_range | 0.2 | +| entropy_loss | -0.245 | +| explained_variance | -1.78 | +| learning_rate | 0.0001 | +| loss | -0.0828 | +| n_updates | 139040 | +| policy_gradient_loss | -0.0561 | +| value_loss | 0.000684 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.48e+03 | +| ep_rew_mean | 0.212 | +| time/ | | +| fps | 309 | +| iterations | 7853 | +| time_elapsed | 25977 | +| total_timesteps | 8041472 | +| train/ | | +| approx_kl | 2.8213685 | +| clip_fraction | 0.399 | +| clip_range | 0.2 | +| entropy_loss | -0.196 | +| explained_variance | -1.59 | +| learning_rate | 0.0001 | +| loss | -0.0898 | +| n_updates | 139050 | +| policy_gradient_loss | -0.0555 | +| value_loss | 0.000707 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.47e+03 | +| ep_rew_mean | 0.208 | +| time/ | | +| fps | 309 | +| iterations | 7854 | +| time_elapsed | 25981 | +| total_timesteps | 8042496 | +| train/ | | +| approx_kl | 2.7750921 | +| clip_fraction | 0.391 | +| clip_range | 0.2 | +| entropy_loss | -0.233 | +| explained_variance | -0.371 | +| learning_rate | 0.0001 | +| loss | -0.0506 | +| n_updates | 139060 | +| policy_gradient_loss | -0.056 | +| value_loss | 0.000964 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.47e+03 | +| ep_rew_mean | 0.208 | +| time/ | | +| fps | 309 | +| iterations | 7855 | +| time_elapsed | 25984 | +| total_timesteps | 8043520 | +| train/ | | +| approx_kl | 2.8751035 | +| clip_fraction | 0.392 | +| clip_range | 0.2 | +| entropy_loss | -0.215 | +| explained_variance | -0.719 | +| learning_rate | 0.0001 | +| loss | -0.0884 | +| n_updates | 139070 | +| policy_gradient_loss | -0.0531 | +| value_loss | 0.000785 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.47e+03 | +| ep_rew_mean | 0.209 | +| time/ | | +| fps | 309 | +| iterations | 7856 | +| time_elapsed | 25987 | +| total_timesteps | 8044544 | +| train/ | | +| approx_kl | 3.1470757 | +| clip_fraction | 0.446 | +| clip_range | 0.2 | +| entropy_loss | -0.253 | +| explained_variance | -1.19 | +| learning_rate | 0.0001 | +| loss | -0.0871 | +| n_updates | 139080 | +| policy_gradient_loss | -0.0649 | +| value_loss | 0.00101 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.47e+03 | +| ep_rew_mean | 0.211 | +| time/ | | +| fps | 309 | +| iterations | 7857 | +| time_elapsed | 25991 | +| total_timesteps | 8045568 | +| train/ | | +| approx_kl | 2.3062615 | +| clip_fraction | 0.373 | +| clip_range | 0.2 | +| entropy_loss | -0.235 | +| explained_variance | -0.853 | +| learning_rate | 0.0001 | +| loss | -0.0562 | +| n_updates | 139090 | +| policy_gradient_loss | -0.0522 | +| value_loss | 0.000773 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.47e+03 | +| ep_rew_mean | 0.211 | +| time/ | | +| fps | 309 | +| iterations | 7858 | +| time_elapsed | 25994 | +| total_timesteps | 8046592 | +| train/ | | +| approx_kl | 2.5128653 | +| clip_fraction | 0.389 | +| clip_range | 0.2 | +| entropy_loss | -0.212 | +| explained_variance | -0.756 | +| learning_rate | 0.0001 | +| loss | -0.0734 | +| n_updates | 139100 | +| policy_gradient_loss | -0.0558 | +| value_loss | 0.000824 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.47e+03 | +| ep_rew_mean | 0.211 | +| time/ | | +| fps | 309 | +| iterations | 7859 | +| time_elapsed | 25997 | +| total_timesteps | 8047616 | +| train/ | | +| approx_kl | 2.6915145 | +| clip_fraction | 0.382 | +| clip_range | 0.2 | +| entropy_loss | -0.225 | +| explained_variance | -1.53 | +| learning_rate | 0.0001 | +| loss | -0.0779 | +| n_updates | 139110 | +| policy_gradient_loss | -0.0545 | +| value_loss | 0.000596 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.46e+03 | +| ep_rew_mean | 0.21 | +| time/ | | +| fps | 309 | +| iterations | 7860 | +| time_elapsed | 26000 | +| total_timesteps | 8048640 | +| train/ | | +| approx_kl | 3.398466 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.273 | +| explained_variance | -1.75 | +| learning_rate | 0.0001 | +| loss | -0.0684 | +| n_updates | 139120 | +| policy_gradient_loss | -0.0601 | +| value_loss | 0.000723 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.46e+03 | +| ep_rew_mean | 0.215 | +| time/ | | +| fps | 309 | +| iterations | 7861 | +| time_elapsed | 26003 | +| total_timesteps | 8049664 | +| train/ | | +| approx_kl | 2.8585672 | +| clip_fraction | 0.393 | +| clip_range | 0.2 | +| entropy_loss | -0.228 | +| explained_variance | -1.91 | +| learning_rate | 0.0001 | +| loss | -0.0686 | +| n_updates | 139130 | +| policy_gradient_loss | -0.0559 | +| value_loss | 0.000706 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.46e+03 | +| ep_rew_mean | 0.215 | +| time/ | | +| fps | 309 | +| iterations | 7862 | +| time_elapsed | 26007 | +| total_timesteps | 8050688 | +| train/ | | +| approx_kl | 2.7461965 | +| clip_fraction | 0.415 | +| clip_range | 0.2 | +| entropy_loss | -0.236 | +| explained_variance | -0.832 | +| learning_rate | 0.0001 | +| loss | -0.0826 | +| n_updates | 139140 | +| policy_gradient_loss | -0.0577 | +| value_loss | 0.000804 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.45e+03 | +| ep_rew_mean | 0.214 | +| time/ | | +| fps | 309 | +| iterations | 7863 | +| time_elapsed | 26010 | +| total_timesteps | 8051712 | +| train/ | | +| approx_kl | 3.2092125 | +| clip_fraction | 0.463 | +| clip_range | 0.2 | +| entropy_loss | -0.274 | +| explained_variance | -2.14 | +| learning_rate | 0.0001 | +| loss | -0.09 | +| n_updates | 139150 | +| policy_gradient_loss | -0.066 | +| value_loss | 0.000725 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.45e+03 | +| ep_rew_mean | 0.209 | +| time/ | | +| fps | 309 | +| iterations | 7864 | +| time_elapsed | 26013 | +| total_timesteps | 8052736 | +| train/ | | +| approx_kl | 3.0062284 | +| clip_fraction | 0.391 | +| clip_range | 0.2 | +| entropy_loss | -0.195 | +| explained_variance | -1.6 | +| learning_rate | 0.0001 | +| loss | -0.0695 | +| n_updates | 139160 | +| policy_gradient_loss | -0.0539 | +| value_loss | 0.000485 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.46e+03 | +| ep_rew_mean | 0.207 | +| time/ | | +| fps | 309 | +| iterations | 7865 | +| time_elapsed | 26016 | +| total_timesteps | 8053760 | +| train/ | | +| approx_kl | 3.0146298 | +| clip_fraction | 0.39 | +| clip_range | 0.2 | +| entropy_loss | -0.213 | +| explained_variance | -0.515 | +| learning_rate | 0.0001 | +| loss | -0.0624 | +| n_updates | 139170 | +| policy_gradient_loss | -0.0604 | +| value_loss | 0.000619 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.46e+03 | +| ep_rew_mean | 0.207 | +| time/ | | +| fps | 309 | +| iterations | 7866 | +| time_elapsed | 26020 | +| total_timesteps | 8054784 | +| train/ | | +| approx_kl | 2.8896317 | +| clip_fraction | 0.447 | +| clip_range | 0.2 | +| entropy_loss | -0.277 | +| explained_variance | -1.44 | +| learning_rate | 0.0001 | +| loss | -0.078 | +| n_updates | 139180 | +| policy_gradient_loss | -0.0648 | +| value_loss | 0.000863 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.45e+03 | +| ep_rew_mean | 0.207 | +| time/ | | +| fps | 309 | +| iterations | 7867 | +| time_elapsed | 26023 | +| total_timesteps | 8055808 | +| train/ | | +| approx_kl | 2.6543498 | +| clip_fraction | 0.418 | +| clip_range | 0.2 | +| entropy_loss | -0.217 | +| explained_variance | -0.996 | +| learning_rate | 0.0001 | +| loss | -0.0755 | +| n_updates | 139190 | +| policy_gradient_loss | -0.0607 | +| value_loss | 0.000735 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.45e+03 | +| ep_rew_mean | 0.206 | +| time/ | | +| fps | 309 | +| iterations | 7868 | +| time_elapsed | 26026 | +| total_timesteps | 8056832 | +| train/ | | +| approx_kl | 2.7786672 | +| clip_fraction | 0.407 | +| clip_range | 0.2 | +| entropy_loss | -0.221 | +| explained_variance | -1.02 | +| learning_rate | 0.0001 | +| loss | -0.078 | +| n_updates | 139200 | +| policy_gradient_loss | -0.055 | +| value_loss | 0.000932 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.43e+03 | +| ep_rew_mean | 0.21 | +| time/ | | +| fps | 309 | +| iterations | 7869 | +| time_elapsed | 26030 | +| total_timesteps | 8057856 | +| train/ | | +| approx_kl | 3.552857 | +| clip_fraction | 0.401 | +| clip_range | 0.2 | +| entropy_loss | -0.234 | +| explained_variance | -0.906 | +| learning_rate | 0.0001 | +| loss | -0.0828 | +| n_updates | 139210 | +| policy_gradient_loss | -0.0591 | +| value_loss | 0.000716 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.44e+03 | +| ep_rew_mean | 0.211 | +| time/ | | +| fps | 309 | +| iterations | 7870 | +| time_elapsed | 26033 | +| total_timesteps | 8058880 | +| train/ | | +| approx_kl | 2.507485 | +| clip_fraction | 0.402 | +| clip_range | 0.2 | +| entropy_loss | -0.233 | +| explained_variance | -0.617 | +| learning_rate | 0.0001 | +| loss | -0.0868 | +| n_updates | 139220 | +| policy_gradient_loss | -0.0526 | +| value_loss | 0.00083 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.44e+03 | +| ep_rew_mean | 0.218 | +| time/ | | +| fps | 309 | +| iterations | 7871 | +| time_elapsed | 26037 | +| total_timesteps | 8059904 | +| train/ | | +| approx_kl | 2.9248755 | +| clip_fraction | 0.376 | +| clip_range | 0.2 | +| entropy_loss | -0.196 | +| explained_variance | -1.53 | +| learning_rate | 0.0001 | +| loss | -0.0877 | +| n_updates | 139230 | +| policy_gradient_loss | -0.0535 | +| value_loss | 0.000711 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.44e+03 | +| ep_rew_mean | 0.223 | +| time/ | | +| fps | 309 | +| iterations | 7872 | +| time_elapsed | 26040 | +| total_timesteps | 8060928 | +| train/ | | +| approx_kl | 2.428819 | +| clip_fraction | 0.372 | +| clip_range | 0.2 | +| entropy_loss | -0.23 | +| explained_variance | -0.715 | +| learning_rate | 0.0001 | +| loss | -0.0523 | +| n_updates | 139240 | +| policy_gradient_loss | -0.0512 | +| value_loss | 0.000774 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.44e+03 | +| ep_rew_mean | 0.223 | +| time/ | | +| fps | 309 | +| iterations | 7873 | +| time_elapsed | 26044 | +| total_timesteps | 8061952 | +| train/ | | +| approx_kl | 2.2238204 | +| clip_fraction | 0.416 | +| clip_range | 0.2 | +| entropy_loss | -0.259 | +| explained_variance | -1.77 | +| learning_rate | 0.0001 | +| loss | -0.0512 | +| n_updates | 139250 | +| policy_gradient_loss | -0.0537 | +| value_loss | 0.000627 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.44e+03 | +| ep_rew_mean | 0.223 | +| time/ | | +| fps | 309 | +| iterations | 7874 | +| time_elapsed | 26047 | +| total_timesteps | 8062976 | +| train/ | | +| approx_kl | 2.7856064 | +| clip_fraction | 0.419 | +| clip_range | 0.2 | +| entropy_loss | -0.239 | +| explained_variance | -3.19 | +| learning_rate | 0.0001 | +| loss | -0.0878 | +| n_updates | 139260 | +| policy_gradient_loss | -0.0563 | +| value_loss | 0.000611 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.43e+03 | +| ep_rew_mean | 0.224 | +| time/ | | +| fps | 309 | +| iterations | 7875 | +| time_elapsed | 26050 | +| total_timesteps | 8064000 | +| train/ | | +| approx_kl | 2.9925995 | +| clip_fraction | 0.396 | +| clip_range | 0.2 | +| entropy_loss | -0.23 | +| explained_variance | -0.933 | +| learning_rate | 0.0001 | +| loss | -0.0748 | +| n_updates | 139270 | +| policy_gradient_loss | -0.059 | +| value_loss | 0.000559 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.43e+03 | +| ep_rew_mean | 0.224 | +| time/ | | +| fps | 309 | +| iterations | 7876 | +| time_elapsed | 26054 | +| total_timesteps | 8065024 | +| train/ | | +| approx_kl | 2.2587426 | +| clip_fraction | 0.357 | +| clip_range | 0.2 | +| entropy_loss | -0.204 | +| explained_variance | -0.544 | +| learning_rate | 0.0001 | +| loss | -0.062 | +| n_updates | 139280 | +| policy_gradient_loss | -0.0522 | +| value_loss | 0.000542 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.44e+03 | +| ep_rew_mean | 0.225 | +| time/ | | +| fps | 309 | +| iterations | 7877 | +| time_elapsed | 26057 | +| total_timesteps | 8066048 | +| train/ | | +| approx_kl | 2.6564963 | +| clip_fraction | 0.407 | +| clip_range | 0.2 | +| entropy_loss | -0.227 | +| explained_variance | -1.97 | +| learning_rate | 0.0001 | +| loss | -0.0953 | +| n_updates | 139290 | +| policy_gradient_loss | -0.0654 | +| value_loss | 0.000464 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.43e+03 | +| ep_rew_mean | 0.224 | +| time/ | | +| fps | 309 | +| iterations | 7878 | +| time_elapsed | 26060 | +| total_timesteps | 8067072 | +| train/ | | +| approx_kl | 2.854669 | +| clip_fraction | 0.377 | +| clip_range | 0.2 | +| entropy_loss | -0.213 | +| explained_variance | -0.357 | +| learning_rate | 0.0001 | +| loss | -0.0863 | +| n_updates | 139300 | +| policy_gradient_loss | -0.0453 | +| value_loss | 0.000637 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.43e+03 | +| ep_rew_mean | 0.219 | +| time/ | | +| fps | 309 | +| iterations | 7879 | +| time_elapsed | 26063 | +| total_timesteps | 8068096 | +| train/ | | +| approx_kl | 2.445753 | +| clip_fraction | 0.351 | +| clip_range | 0.2 | +| entropy_loss | -0.212 | +| explained_variance | -0.319 | +| learning_rate | 0.0001 | +| loss | -0.0818 | +| n_updates | 139310 | +| policy_gradient_loss | -0.0499 | +| value_loss | 0.000743 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.217 | +| time/ | | +| fps | 309 | +| iterations | 7880 | +| time_elapsed | 26066 | +| total_timesteps | 8069120 | +| train/ | | +| approx_kl | 2.179277 | +| clip_fraction | 0.343 | +| clip_range | 0.2 | +| entropy_loss | -0.206 | +| explained_variance | -0.44 | +| learning_rate | 0.0001 | +| loss | -0.0478 | +| n_updates | 139320 | +| policy_gradient_loss | -0.0509 | +| value_loss | 0.000757 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.217 | +| time/ | | +| fps | 309 | +| iterations | 7881 | +| time_elapsed | 26070 | +| total_timesteps | 8070144 | +| train/ | | +| approx_kl | 2.6584454 | +| clip_fraction | 0.433 | +| clip_range | 0.2 | +| entropy_loss | -0.263 | +| explained_variance | -1.53 | +| learning_rate | 0.0001 | +| loss | -0.097 | +| n_updates | 139330 | +| policy_gradient_loss | -0.0611 | +| value_loss | 0.000722 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.219 | +| time/ | | +| fps | 309 | +| iterations | 7882 | +| time_elapsed | 26073 | +| total_timesteps | 8071168 | +| train/ | | +| approx_kl | 2.1150799 | +| clip_fraction | 0.423 | +| clip_range | 0.2 | +| entropy_loss | -0.274 | +| explained_variance | -4.45 | +| learning_rate | 0.0001 | +| loss | -0.0795 | +| n_updates | 139340 | +| policy_gradient_loss | -0.0599 | +| value_loss | 0.000345 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.217 | +| time/ | | +| fps | 309 | +| iterations | 7883 | +| time_elapsed | 26076 | +| total_timesteps | 8072192 | +| train/ | | +| approx_kl | 2.5936985 | +| clip_fraction | 0.427 | +| clip_range | 0.2 | +| entropy_loss | -0.282 | +| explained_variance | -0.602 | +| learning_rate | 0.0001 | +| loss | -0.0805 | +| n_updates | 139350 | +| policy_gradient_loss | -0.0473 | +| value_loss | 0.000492 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.217 | +| time/ | | +| fps | 309 | +| iterations | 7884 | +| time_elapsed | 26079 | +| total_timesteps | 8073216 | +| train/ | | +| approx_kl | 2.6786883 | +| clip_fraction | 0.434 | +| clip_range | 0.2 | +| entropy_loss | -0.264 | +| explained_variance | -0.772 | +| learning_rate | 0.0001 | +| loss | -0.0672 | +| n_updates | 139360 | +| policy_gradient_loss | -0.0613 | +| value_loss | 0.000673 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.22 | +| time/ | | +| fps | 309 | +| iterations | 7885 | +| time_elapsed | 26083 | +| total_timesteps | 8074240 | +| train/ | | +| approx_kl | 2.9388936 | +| clip_fraction | 0.482 | +| clip_range | 0.2 | +| entropy_loss | -0.264 | +| explained_variance | -3.59 | +| learning_rate | 0.0001 | +| loss | -0.0922 | +| n_updates | 139370 | +| policy_gradient_loss | -0.0677 | +| value_loss | 0.000839 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.218 | +| time/ | | +| fps | 309 | +| iterations | 7886 | +| time_elapsed | 26086 | +| total_timesteps | 8075264 | +| train/ | | +| approx_kl | 2.7906966 | +| clip_fraction | 0.464 | +| clip_range | 0.2 | +| entropy_loss | -0.284 | +| explained_variance | -2.38 | +| learning_rate | 0.0001 | +| loss | -0.0981 | +| n_updates | 139380 | +| policy_gradient_loss | -0.0696 | +| value_loss | 0.000623 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.22 | +| time/ | | +| fps | 309 | +| iterations | 7887 | +| time_elapsed | 26090 | +| total_timesteps | 8076288 | +| train/ | | +| approx_kl | 2.8249178 | +| clip_fraction | 0.418 | +| clip_range | 0.2 | +| entropy_loss | -0.263 | +| explained_variance | -0.652 | +| learning_rate | 0.0001 | +| loss | -0.0657 | +| n_updates | 139390 | +| policy_gradient_loss | -0.0552 | +| value_loss | 0.000814 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.219 | +| time/ | | +| fps | 309 | +| iterations | 7888 | +| time_elapsed | 26093 | +| total_timesteps | 8077312 | +| train/ | | +| approx_kl | 2.333699 | +| clip_fraction | 0.435 | +| clip_range | 0.2 | +| entropy_loss | -0.276 | +| explained_variance | -2.78 | +| learning_rate | 0.0001 | +| loss | -0.0643 | +| n_updates | 139400 | +| policy_gradient_loss | -0.0607 | +| value_loss | 0.000614 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.219 | +| time/ | | +| fps | 309 | +| iterations | 7889 | +| time_elapsed | 26096 | +| total_timesteps | 8078336 | +| train/ | | +| approx_kl | 2.8370762 | +| clip_fraction | 0.462 | +| clip_range | 0.2 | +| entropy_loss | -0.277 | +| explained_variance | -1.26 | +| learning_rate | 0.0001 | +| loss | -0.0853 | +| n_updates | 139410 | +| policy_gradient_loss | -0.0616 | +| value_loss | 0.000647 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.221 | +| time/ | | +| fps | 309 | +| iterations | 7890 | +| time_elapsed | 26100 | +| total_timesteps | 8079360 | +| train/ | | +| approx_kl | 2.9531097 | +| clip_fraction | 0.438 | +| clip_range | 0.2 | +| entropy_loss | -0.241 | +| explained_variance | -1.43 | +| learning_rate | 0.0001 | +| loss | -0.0823 | +| n_updates | 139420 | +| policy_gradient_loss | -0.0607 | +| value_loss | 0.000855 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.223 | +| time/ | | +| fps | 309 | +| iterations | 7891 | +| time_elapsed | 26103 | +| total_timesteps | 8080384 | +| train/ | | +| approx_kl | 2.6368153 | +| clip_fraction | 0.406 | +| clip_range | 0.2 | +| entropy_loss | -0.275 | +| explained_variance | -2.08 | +| learning_rate | 0.0001 | +| loss | -0.0907 | +| n_updates | 139430 | +| policy_gradient_loss | -0.0559 | +| value_loss | 0.000791 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.22 | +| time/ | | +| fps | 309 | +| iterations | 7892 | +| time_elapsed | 26106 | +| total_timesteps | 8081408 | +| train/ | | +| approx_kl | 2.6466746 | +| clip_fraction | 0.441 | +| clip_range | 0.2 | +| entropy_loss | -0.301 | +| explained_variance | -1.53 | +| learning_rate | 0.0001 | +| loss | -0.0833 | +| n_updates | 139440 | +| policy_gradient_loss | -0.0598 | +| value_loss | 0.000673 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.22 | +| time/ | | +| fps | 309 | +| iterations | 7893 | +| time_elapsed | 26110 | +| total_timesteps | 8082432 | +| train/ | | +| approx_kl | 2.976518 | +| clip_fraction | 0.41 | +| clip_range | 0.2 | +| entropy_loss | -0.258 | +| explained_variance | -1.44 | +| learning_rate | 0.0001 | +| loss | -0.0541 | +| n_updates | 139450 | +| policy_gradient_loss | -0.06 | +| value_loss | 0.00115 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.22 | +| time/ | | +| fps | 309 | +| iterations | 7894 | +| time_elapsed | 26113 | +| total_timesteps | 8083456 | +| train/ | | +| approx_kl | 2.7251801 | +| clip_fraction | 0.412 | +| clip_range | 0.2 | +| entropy_loss | -0.285 | +| explained_variance | -1.44 | +| learning_rate | 0.0001 | +| loss | -0.0764 | +| n_updates | 139460 | +| policy_gradient_loss | -0.0541 | +| value_loss | 0.000702 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.226 | +| time/ | | +| fps | 309 | +| iterations | 7895 | +| time_elapsed | 26116 | +| total_timesteps | 8084480 | +| train/ | | +| approx_kl | 2.738686 | +| clip_fraction | 0.461 | +| clip_range | 0.2 | +| entropy_loss | -0.282 | +| explained_variance | -1.2 | +| learning_rate | 0.0001 | +| loss | -0.0605 | +| n_updates | 139470 | +| policy_gradient_loss | -0.0607 | +| value_loss | 0.000604 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.223 | +| time/ | | +| fps | 309 | +| iterations | 7896 | +| time_elapsed | 26119 | +| total_timesteps | 8085504 | +| train/ | | +| approx_kl | 3.1829448 | +| clip_fraction | 0.426 | +| clip_range | 0.2 | +| entropy_loss | -0.26 | +| explained_variance | -0.723 | +| learning_rate | 0.0001 | +| loss | -0.0692 | +| n_updates | 139480 | +| policy_gradient_loss | -0.0601 | +| value_loss | 0.000764 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.226 | +| time/ | | +| fps | 309 | +| iterations | 7897 | +| time_elapsed | 26122 | +| total_timesteps | 8086528 | +| train/ | | +| approx_kl | 2.2809052 | +| clip_fraction | 0.425 | +| clip_range | 0.2 | +| entropy_loss | -0.243 | +| explained_variance | -3.2 | +| learning_rate | 0.0001 | +| loss | -0.0861 | +| n_updates | 139490 | +| policy_gradient_loss | -0.0554 | +| value_loss | 0.000676 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.226 | +| time/ | | +| fps | 309 | +| iterations | 7898 | +| time_elapsed | 26126 | +| total_timesteps | 8087552 | +| train/ | | +| approx_kl | 1.9775891 | +| clip_fraction | 0.399 | +| clip_range | 0.2 | +| entropy_loss | -0.256 | +| explained_variance | -0.648 | +| learning_rate | 0.0001 | +| loss | -0.0487 | +| n_updates | 139500 | +| policy_gradient_loss | -0.0504 | +| value_loss | 0.000608 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.226 | +| time/ | | +| fps | 309 | +| iterations | 7899 | +| time_elapsed | 26129 | +| total_timesteps | 8088576 | +| train/ | | +| approx_kl | 2.637897 | +| clip_fraction | 0.465 | +| clip_range | 0.2 | +| entropy_loss | -0.289 | +| explained_variance | -2.28 | +| learning_rate | 0.0001 | +| loss | -0.0634 | +| n_updates | 139510 | +| policy_gradient_loss | -0.0623 | +| value_loss | 0.000848 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.229 | +| time/ | | +| fps | 309 | +| iterations | 7900 | +| time_elapsed | 26132 | +| total_timesteps | 8089600 | +| train/ | | +| approx_kl | 3.0000288 | +| clip_fraction | 0.414 | +| clip_range | 0.2 | +| entropy_loss | -0.245 | +| explained_variance | -1.2 | +| learning_rate | 0.0001 | +| loss | -0.0718 | +| n_updates | 139520 | +| policy_gradient_loss | -0.0625 | +| value_loss | 0.000679 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.229 | +| time/ | | +| fps | 309 | +| iterations | 7901 | +| time_elapsed | 26135 | +| total_timesteps | 8090624 | +| train/ | | +| approx_kl | 3.07401 | +| clip_fraction | 0.446 | +| clip_range | 0.2 | +| entropy_loss | -0.257 | +| explained_variance | -1.46 | +| learning_rate | 0.0001 | +| loss | -0.1 | +| n_updates | 139530 | +| policy_gradient_loss | -0.065 | +| value_loss | 0.000755 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.237 | +| time/ | | +| fps | 309 | +| iterations | 7902 | +| time_elapsed | 26138 | +| total_timesteps | 8091648 | +| train/ | | +| approx_kl | 2.2929094 | +| clip_fraction | 0.415 | +| clip_range | 0.2 | +| entropy_loss | -0.254 | +| explained_variance | -1.31 | +| learning_rate | 0.0001 | +| loss | -0.0665 | +| n_updates | 139540 | +| policy_gradient_loss | -0.051 | +| value_loss | 0.00103 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.237 | +| time/ | | +| fps | 309 | +| iterations | 7903 | +| time_elapsed | 26142 | +| total_timesteps | 8092672 | +| train/ | | +| approx_kl | 2.5980678 | +| clip_fraction | 0.428 | +| clip_range | 0.2 | +| entropy_loss | -0.281 | +| explained_variance | -1.05 | +| learning_rate | 0.0001 | +| loss | -0.0723 | +| n_updates | 139550 | +| policy_gradient_loss | -0.0572 | +| value_loss | 0.000945 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.237 | +| time/ | | +| fps | 309 | +| iterations | 7904 | +| time_elapsed | 26145 | +| total_timesteps | 8093696 | +| train/ | | +| approx_kl | 2.8115497 | +| clip_fraction | 0.467 | +| clip_range | 0.2 | +| entropy_loss | -0.282 | +| explained_variance | -4.31 | +| learning_rate | 0.0001 | +| loss | -0.0881 | +| n_updates | 139560 | +| policy_gradient_loss | -0.0659 | +| value_loss | 0.00063 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.242 | +| time/ | | +| fps | 309 | +| iterations | 7905 | +| time_elapsed | 26149 | +| total_timesteps | 8094720 | +| train/ | | +| approx_kl | 2.177699 | +| clip_fraction | 0.409 | +| clip_range | 0.2 | +| entropy_loss | -0.272 | +| explained_variance | -2.04 | +| learning_rate | 0.0001 | +| loss | -0.0887 | +| n_updates | 139570 | +| policy_gradient_loss | -0.0565 | +| value_loss | 0.000738 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.245 | +| time/ | | +| fps | 309 | +| iterations | 7906 | +| time_elapsed | 26152 | +| total_timesteps | 8095744 | +| train/ | | +| approx_kl | 2.6373038 | +| clip_fraction | 0.437 | +| clip_range | 0.2 | +| entropy_loss | -0.274 | +| explained_variance | -3.65 | +| learning_rate | 0.0001 | +| loss | -0.0822 | +| n_updates | 139580 | +| policy_gradient_loss | -0.0583 | +| value_loss | 0.000491 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.245 | +| time/ | | +| fps | 309 | +| iterations | 7907 | +| time_elapsed | 26155 | +| total_timesteps | 8096768 | +| train/ | | +| approx_kl | 3.1620767 | +| clip_fraction | 0.455 | +| clip_range | 0.2 | +| entropy_loss | -0.263 | +| explained_variance | -1.03 | +| learning_rate | 0.0001 | +| loss | -0.0809 | +| n_updates | 139590 | +| policy_gradient_loss | -0.0657 | +| value_loss | 0.000573 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.251 | +| time/ | | +| fps | 309 | +| iterations | 7908 | +| time_elapsed | 26159 | +| total_timesteps | 8097792 | +| train/ | | +| approx_kl | 3.1043391 | +| clip_fraction | 0.425 | +| clip_range | 0.2 | +| entropy_loss | -0.241 | +| explained_variance | -2.26 | +| learning_rate | 0.0001 | +| loss | -0.0794 | +| n_updates | 139600 | +| policy_gradient_loss | -0.0639 | +| value_loss | 0.000861 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.251 | +| time/ | | +| fps | 309 | +| iterations | 7909 | +| time_elapsed | 26162 | +| total_timesteps | 8098816 | +| train/ | | +| approx_kl | 2.8772845 | +| clip_fraction | 0.42 | +| clip_range | 0.2 | +| entropy_loss | -0.226 | +| explained_variance | -1.22 | +| learning_rate | 0.0001 | +| loss | -0.0794 | +| n_updates | 139610 | +| policy_gradient_loss | -0.0599 | +| value_loss | 0.00124 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.25 | +| time/ | | +| fps | 309 | +| iterations | 7910 | +| time_elapsed | 26166 | +| total_timesteps | 8099840 | +| train/ | | +| approx_kl | 2.411415 | +| clip_fraction | 0.416 | +| clip_range | 0.2 | +| entropy_loss | -0.265 | +| explained_variance | -3.46 | +| learning_rate | 0.0001 | +| loss | -0.0759 | +| n_updates | 139620 | +| policy_gradient_loss | -0.0555 | +| value_loss | 0.000805 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.252 | +| time/ | | +| fps | 309 | +| iterations | 7911 | +| time_elapsed | 26169 | +| total_timesteps | 8100864 | +| train/ | | +| approx_kl | 3.650043 | +| clip_fraction | 0.415 | +| clip_range | 0.2 | +| entropy_loss | -0.265 | +| explained_variance | -0.906 | +| learning_rate | 0.0001 | +| loss | -0.0775 | +| n_updates | 139630 | +| policy_gradient_loss | -0.0575 | +| value_loss | 0.00071 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.259 | +| time/ | | +| fps | 309 | +| iterations | 7912 | +| time_elapsed | 26172 | +| total_timesteps | 8101888 | +| train/ | | +| approx_kl | 2.3724537 | +| clip_fraction | 0.386 | +| clip_range | 0.2 | +| entropy_loss | -0.246 | +| explained_variance | -0.608 | +| learning_rate | 0.0001 | +| loss | -0.0677 | +| n_updates | 139640 | +| policy_gradient_loss | -0.057 | +| value_loss | 0.000755 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.259 | +| time/ | | +| fps | 309 | +| iterations | 7913 | +| time_elapsed | 26175 | +| total_timesteps | 8102912 | +| train/ | | +| approx_kl | 2.4442794 | +| clip_fraction | 0.379 | +| clip_range | 0.2 | +| entropy_loss | -0.222 | +| explained_variance | -0.596 | +| learning_rate | 0.0001 | +| loss | -0.0974 | +| n_updates | 139650 | +| policy_gradient_loss | -0.0558 | +| value_loss | 0.00106 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.266 | +| time/ | | +| fps | 309 | +| iterations | 7914 | +| time_elapsed | 26179 | +| total_timesteps | 8103936 | +| train/ | | +| approx_kl | 2.5594897 | +| clip_fraction | 0.399 | +| clip_range | 0.2 | +| entropy_loss | -0.241 | +| explained_variance | -0.649 | +| learning_rate | 0.0001 | +| loss | -0.0724 | +| n_updates | 139660 | +| policy_gradient_loss | -0.0558 | +| value_loss | 0.000753 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.273 | +| time/ | | +| fps | 309 | +| iterations | 7915 | +| time_elapsed | 26182 | +| total_timesteps | 8104960 | +| train/ | | +| approx_kl | 2.9255545 | +| clip_fraction | 0.409 | +| clip_range | 0.2 | +| entropy_loss | -0.231 | +| explained_variance | -0.782 | +| learning_rate | 0.0001 | +| loss | -0.0619 | +| n_updates | 139670 | +| policy_gradient_loss | -0.063 | +| value_loss | 0.000679 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 309 | +| iterations | 7916 | +| time_elapsed | 26185 | +| total_timesteps | 8105984 | +| train/ | | +| approx_kl | 2.8195677 | +| clip_fraction | 0.432 | +| clip_range | 0.2 | +| entropy_loss | -0.242 | +| explained_variance | -0.865 | +| learning_rate | 0.0001 | +| loss | -0.0699 | +| n_updates | 139680 | +| policy_gradient_loss | -0.063 | +| value_loss | 0.000831 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 309 | +| iterations | 7917 | +| time_elapsed | 26188 | +| total_timesteps | 8107008 | +| train/ | | +| approx_kl | 2.4452438 | +| clip_fraction | 0.45 | +| clip_range | 0.2 | +| entropy_loss | -0.301 | +| explained_variance | -1.22 | +| learning_rate | 0.0001 | +| loss | -0.0909 | +| n_updates | 139690 | +| policy_gradient_loss | -0.0638 | +| value_loss | 0.000833 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 309 | +| iterations | 7918 | +| time_elapsed | 26191 | +| total_timesteps | 8108032 | +| train/ | | +| approx_kl | 2.7533293 | +| clip_fraction | 0.439 | +| clip_range | 0.2 | +| entropy_loss | -0.275 | +| explained_variance | -1.33 | +| learning_rate | 0.0001 | +| loss | -0.0785 | +| n_updates | 139700 | +| policy_gradient_loss | -0.0636 | +| value_loss | 0.000734 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.276 | +| time/ | | +| fps | 309 | +| iterations | 7919 | +| time_elapsed | 26194 | +| total_timesteps | 8109056 | +| train/ | | +| approx_kl | 2.3033648 | +| clip_fraction | 0.433 | +| clip_range | 0.2 | +| entropy_loss | -0.25 | +| explained_variance | -1.78 | +| learning_rate | 0.0001 | +| loss | -0.0695 | +| n_updates | 139710 | +| policy_gradient_loss | -0.0697 | +| value_loss | 0.000669 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.278 | +| time/ | | +| fps | 309 | +| iterations | 7920 | +| time_elapsed | 26198 | +| total_timesteps | 8110080 | +| train/ | | +| approx_kl | 2.1537213 | +| clip_fraction | 0.427 | +| clip_range | 0.2 | +| entropy_loss | -0.26 | +| explained_variance | -1.56 | +| learning_rate | 0.0001 | +| loss | -0.071 | +| n_updates | 139720 | +| policy_gradient_loss | -0.0558 | +| value_loss | 0.000655 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.278 | +| time/ | | +| fps | 309 | +| iterations | 7921 | +| time_elapsed | 26201 | +| total_timesteps | 8111104 | +| train/ | | +| approx_kl | 2.6409707 | +| clip_fraction | 0.415 | +| clip_range | 0.2 | +| entropy_loss | -0.254 | +| explained_variance | -2.28 | +| learning_rate | 0.0001 | +| loss | -0.0843 | +| n_updates | 139730 | +| policy_gradient_loss | -0.0562 | +| value_loss | 0.000424 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.28 | +| time/ | | +| fps | 309 | +| iterations | 7922 | +| time_elapsed | 26205 | +| total_timesteps | 8112128 | +| train/ | | +| approx_kl | 2.6091359 | +| clip_fraction | 0.454 | +| clip_range | 0.2 | +| entropy_loss | -0.268 | +| explained_variance | -0.895 | +| learning_rate | 0.0001 | +| loss | -0.0811 | +| n_updates | 139740 | +| policy_gradient_loss | -0.0587 | +| value_loss | 0.000719 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.278 | +| time/ | | +| fps | 309 | +| iterations | 7923 | +| time_elapsed | 26208 | +| total_timesteps | 8113152 | +| train/ | | +| approx_kl | 3.4928648 | +| clip_fraction | 0.434 | +| clip_range | 0.2 | +| entropy_loss | -0.25 | +| explained_variance | -1.97 | +| learning_rate | 0.0001 | +| loss | -0.0671 | +| n_updates | 139750 | +| policy_gradient_loss | -0.0602 | +| value_loss | 0.000953 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.276 | +| time/ | | +| fps | 309 | +| iterations | 7924 | +| time_elapsed | 26212 | +| total_timesteps | 8114176 | +| train/ | | +| approx_kl | 2.5038157 | +| clip_fraction | 0.436 | +| clip_range | 0.2 | +| entropy_loss | -0.265 | +| explained_variance | -2.43 | +| learning_rate | 0.0001 | +| loss | -0.0932 | +| n_updates | 139760 | +| policy_gradient_loss | -0.0574 | +| value_loss | 0.000598 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.276 | +| time/ | | +| fps | 309 | +| iterations | 7925 | +| time_elapsed | 26215 | +| total_timesteps | 8115200 | +| train/ | | +| approx_kl | 2.369839 | +| clip_fraction | 0.421 | +| clip_range | 0.2 | +| entropy_loss | -0.26 | +| explained_variance | -1.5 | +| learning_rate | 0.0001 | +| loss | -0.0713 | +| n_updates | 139770 | +| policy_gradient_loss | -0.0577 | +| value_loss | 0.000668 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.278 | +| time/ | | +| fps | 309 | +| iterations | 7926 | +| time_elapsed | 26218 | +| total_timesteps | 8116224 | +| train/ | | +| approx_kl | 3.4045947 | +| clip_fraction | 0.426 | +| clip_range | 0.2 | +| entropy_loss | -0.272 | +| explained_variance | -1.66 | +| learning_rate | 0.0001 | +| loss | -0.0865 | +| n_updates | 139780 | +| policy_gradient_loss | -0.0595 | +| value_loss | 0.000664 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 309 | +| iterations | 7927 | +| time_elapsed | 26222 | +| total_timesteps | 8117248 | +| train/ | | +| approx_kl | 2.630507 | +| clip_fraction | 0.404 | +| clip_range | 0.2 | +| entropy_loss | -0.251 | +| explained_variance | -1.44 | +| learning_rate | 0.0001 | +| loss | -0.0682 | +| n_updates | 139790 | +| policy_gradient_loss | -0.0562 | +| value_loss | 0.000879 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 309 | +| iterations | 7928 | +| time_elapsed | 26225 | +| total_timesteps | 8118272 | +| train/ | | +| approx_kl | 3.0456827 | +| clip_fraction | 0.45 | +| clip_range | 0.2 | +| entropy_loss | -0.243 | +| explained_variance | -3.53 | +| learning_rate | 0.0001 | +| loss | -0.106 | +| n_updates | 139800 | +| policy_gradient_loss | -0.062 | +| value_loss | 0.000686 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.273 | +| time/ | | +| fps | 309 | +| iterations | 7929 | +| time_elapsed | 26229 | +| total_timesteps | 8119296 | +| train/ | | +| approx_kl | 4.1695204 | +| clip_fraction | 0.427 | +| clip_range | 0.2 | +| entropy_loss | -0.252 | +| explained_variance | -1.68 | +| learning_rate | 0.0001 | +| loss | -0.0826 | +| n_updates | 139810 | +| policy_gradient_loss | -0.0613 | +| value_loss | 0.000645 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.266 | +| time/ | | +| fps | 309 | +| iterations | 7930 | +| time_elapsed | 26232 | +| total_timesteps | 8120320 | +| train/ | | +| approx_kl | 2.4044352 | +| clip_fraction | 0.413 | +| clip_range | 0.2 | +| entropy_loss | -0.249 | +| explained_variance | -1.02 | +| learning_rate | 0.0001 | +| loss | -0.0792 | +| n_updates | 139820 | +| policy_gradient_loss | -0.0453 | +| value_loss | 0.000822 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.266 | +| time/ | | +| fps | 309 | +| iterations | 7931 | +| time_elapsed | 26235 | +| total_timesteps | 8121344 | +| train/ | | +| approx_kl | 2.3532004 | +| clip_fraction | 0.437 | +| clip_range | 0.2 | +| entropy_loss | -0.283 | +| explained_variance | -0.333 | +| learning_rate | 0.0001 | +| loss | -0.0902 | +| n_updates | 139830 | +| policy_gradient_loss | -0.0556 | +| value_loss | 0.000692 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.26 | +| time/ | | +| fps | 309 | +| iterations | 7932 | +| time_elapsed | 26238 | +| total_timesteps | 8122368 | +| train/ | | +| approx_kl | 2.7345953 | +| clip_fraction | 0.431 | +| clip_range | 0.2 | +| entropy_loss | -0.273 | +| explained_variance | -1.65 | +| learning_rate | 0.0001 | +| loss | -0.0713 | +| n_updates | 139840 | +| policy_gradient_loss | -0.059 | +| value_loss | 0.00102 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.259 | +| time/ | | +| fps | 309 | +| iterations | 7933 | +| time_elapsed | 26242 | +| total_timesteps | 8123392 | +| train/ | | +| approx_kl | 2.8262959 | +| clip_fraction | 0.447 | +| clip_range | 0.2 | +| entropy_loss | -0.278 | +| explained_variance | -1.59 | +| learning_rate | 0.0001 | +| loss | -0.0847 | +| n_updates | 139850 | +| policy_gradient_loss | -0.0629 | +| value_loss | 0.000771 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.26 | +| time/ | | +| fps | 309 | +| iterations | 7934 | +| time_elapsed | 26245 | +| total_timesteps | 8124416 | +| train/ | | +| approx_kl | 2.2620573 | +| clip_fraction | 0.428 | +| clip_range | 0.2 | +| entropy_loss | -0.253 | +| explained_variance | -0.553 | +| learning_rate | 0.0001 | +| loss | -0.0662 | +| n_updates | 139860 | +| policy_gradient_loss | -0.058 | +| value_loss | 0.00086 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.252 | +| time/ | | +| fps | 309 | +| iterations | 7935 | +| time_elapsed | 26248 | +| total_timesteps | 8125440 | +| train/ | | +| approx_kl | 2.368661 | +| clip_fraction | 0.444 | +| clip_range | 0.2 | +| entropy_loss | -0.289 | +| explained_variance | -2.22 | +| learning_rate | 0.0001 | +| loss | -0.0595 | +| n_updates | 139870 | +| policy_gradient_loss | -0.0581 | +| value_loss | 0.000551 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.246 | +| time/ | | +| fps | 309 | +| iterations | 7936 | +| time_elapsed | 26251 | +| total_timesteps | 8126464 | +| train/ | | +| approx_kl | 2.4932516 | +| clip_fraction | 0.45 | +| clip_range | 0.2 | +| entropy_loss | -0.303 | +| explained_variance | -0.765 | +| learning_rate | 0.0001 | +| loss | -0.0886 | +| n_updates | 139880 | +| policy_gradient_loss | -0.0588 | +| value_loss | 0.000324 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.246 | +| time/ | | +| fps | 309 | +| iterations | 7937 | +| time_elapsed | 26254 | +| total_timesteps | 8127488 | +| train/ | | +| approx_kl | 2.6529474 | +| clip_fraction | 0.448 | +| clip_range | 0.2 | +| entropy_loss | -0.269 | +| explained_variance | -1.14 | +| learning_rate | 0.0001 | +| loss | -0.0925 | +| n_updates | 139890 | +| policy_gradient_loss | -0.0584 | +| value_loss | 0.000624 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.243 | +| time/ | | +| fps | 309 | +| iterations | 7938 | +| time_elapsed | 26257 | +| total_timesteps | 8128512 | +| train/ | | +| approx_kl | 2.6455991 | +| clip_fraction | 0.441 | +| clip_range | 0.2 | +| entropy_loss | -0.291 | +| explained_variance | -2.35 | +| learning_rate | 0.0001 | +| loss | -0.076 | +| n_updates | 139900 | +| policy_gradient_loss | -0.0607 | +| value_loss | 0.000903 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.244 | +| time/ | | +| fps | 309 | +| iterations | 7939 | +| time_elapsed | 26261 | +| total_timesteps | 8129536 | +| train/ | | +| approx_kl | 2.5141096 | +| clip_fraction | 0.446 | +| clip_range | 0.2 | +| entropy_loss | -0.303 | +| explained_variance | -1.34 | +| learning_rate | 0.0001 | +| loss | -0.0761 | +| n_updates | 139910 | +| policy_gradient_loss | -0.051 | +| value_loss | 0.00083 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.243 | +| time/ | | +| fps | 309 | +| iterations | 7940 | +| time_elapsed | 26264 | +| total_timesteps | 8130560 | +| train/ | | +| approx_kl | 3.7246852 | +| clip_fraction | 0.421 | +| clip_range | 0.2 | +| entropy_loss | -0.212 | +| explained_variance | -2.02 | +| learning_rate | 0.0001 | +| loss | -0.0734 | +| n_updates | 139920 | +| policy_gradient_loss | -0.0566 | +| value_loss | 0.000749 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.243 | +| time/ | | +| fps | 309 | +| iterations | 7941 | +| time_elapsed | 26268 | +| total_timesteps | 8131584 | +| train/ | | +| approx_kl | 2.7512097 | +| clip_fraction | 0.45 | +| clip_range | 0.2 | +| entropy_loss | -0.289 | +| explained_variance | -1.47 | +| learning_rate | 0.0001 | +| loss | -0.0402 | +| n_updates | 139930 | +| policy_gradient_loss | -0.0652 | +| value_loss | 0.000691 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.244 | +| time/ | | +| fps | 309 | +| iterations | 7942 | +| time_elapsed | 26271 | +| total_timesteps | 8132608 | +| train/ | | +| approx_kl | 3.1854627 | +| clip_fraction | 0.446 | +| clip_range | 0.2 | +| entropy_loss | -0.274 | +| explained_variance | -2.82 | +| learning_rate | 0.0001 | +| loss | -0.075 | +| n_updates | 139940 | +| policy_gradient_loss | -0.0648 | +| value_loss | 0.000627 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.236 | +| time/ | | +| fps | 309 | +| iterations | 7943 | +| time_elapsed | 26275 | +| total_timesteps | 8133632 | +| train/ | | +| approx_kl | 3.28076 | +| clip_fraction | 0.447 | +| clip_range | 0.2 | +| entropy_loss | -0.241 | +| explained_variance | -1.06 | +| learning_rate | 0.0001 | +| loss | -0.0915 | +| n_updates | 139950 | +| policy_gradient_loss | -0.0603 | +| value_loss | 0.000755 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.235 | +| time/ | | +| fps | 309 | +| iterations | 7944 | +| time_elapsed | 26278 | +| total_timesteps | 8134656 | +| train/ | | +| approx_kl | 3.4298728 | +| clip_fraction | 0.392 | +| clip_range | 0.2 | +| entropy_loss | -0.235 | +| explained_variance | -1.05 | +| learning_rate | 0.0001 | +| loss | -0.0583 | +| n_updates | 139960 | +| policy_gradient_loss | -0.0467 | +| value_loss | 0.000994 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.23 | +| time/ | | +| fps | 309 | +| iterations | 7945 | +| time_elapsed | 26282 | +| total_timesteps | 8135680 | +| train/ | | +| approx_kl | 3.0169616 | +| clip_fraction | 0.429 | +| clip_range | 0.2 | +| entropy_loss | -0.23 | +| explained_variance | -3.58 | +| learning_rate | 0.0001 | +| loss | -0.0754 | +| n_updates | 139970 | +| policy_gradient_loss | -0.0548 | +| value_loss | 0.000798 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.229 | +| time/ | | +| fps | 309 | +| iterations | 7946 | +| time_elapsed | 26285 | +| total_timesteps | 8136704 | +| train/ | | +| approx_kl | 2.402276 | +| clip_fraction | 0.423 | +| clip_range | 0.2 | +| entropy_loss | -0.254 | +| explained_variance | -1.92 | +| learning_rate | 0.0001 | +| loss | -0.0924 | +| n_updates | 139980 | +| policy_gradient_loss | -0.0619 | +| value_loss | 0.000648 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.225 | +| time/ | | +| fps | 309 | +| iterations | 7947 | +| time_elapsed | 26288 | +| total_timesteps | 8137728 | +| train/ | | +| approx_kl | 2.391192 | +| clip_fraction | 0.376 | +| clip_range | 0.2 | +| entropy_loss | -0.221 | +| explained_variance | -5.43 | +| learning_rate | 0.0001 | +| loss | -0.071 | +| n_updates | 139990 | +| policy_gradient_loss | -0.0573 | +| value_loss | 0.000436 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.225 | +| time/ | | +| fps | 309 | +| iterations | 7948 | +| time_elapsed | 26292 | +| total_timesteps | 8138752 | +| train/ | | +| approx_kl | 2.1626115 | +| clip_fraction | 0.38 | +| clip_range | 0.2 | +| entropy_loss | -0.228 | +| explained_variance | -0.325 | +| learning_rate | 0.0001 | +| loss | -0.0504 | +| n_updates | 140000 | +| policy_gradient_loss | -0.0542 | +| value_loss | 0.000875 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.226 | +| time/ | | +| fps | 309 | +| iterations | 7949 | +| time_elapsed | 26295 | +| total_timesteps | 8139776 | +| train/ | | +| approx_kl | 2.3848667 | +| clip_fraction | 0.406 | +| clip_range | 0.2 | +| entropy_loss | -0.243 | +| explained_variance | -4.1 | +| learning_rate | 0.0001 | +| loss | -0.0864 | +| n_updates | 140010 | +| policy_gradient_loss | -0.0606 | +| value_loss | 0.000788 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.225 | +| time/ | | +| fps | 309 | +| iterations | 7950 | +| time_elapsed | 26298 | +| total_timesteps | 8140800 | +| train/ | | +| approx_kl | 2.096108 | +| clip_fraction | 0.401 | +| clip_range | 0.2 | +| entropy_loss | -0.255 | +| explained_variance | -1.36 | +| learning_rate | 0.0001 | +| loss | -0.0662 | +| n_updates | 140020 | +| policy_gradient_loss | -0.0521 | +| value_loss | 0.000689 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.232 | +| time/ | | +| fps | 309 | +| iterations | 7951 | +| time_elapsed | 26302 | +| total_timesteps | 8141824 | +| train/ | | +| approx_kl | 2.6412427 | +| clip_fraction | 0.411 | +| clip_range | 0.2 | +| entropy_loss | -0.248 | +| explained_variance | -0.963 | +| learning_rate | 0.0001 | +| loss | -0.0694 | +| n_updates | 140030 | +| policy_gradient_loss | -0.0553 | +| value_loss | 0.000892 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.232 | +| time/ | | +| fps | 309 | +| iterations | 7952 | +| time_elapsed | 26305 | +| total_timesteps | 8142848 | +| train/ | | +| approx_kl | 3.0602403 | +| clip_fraction | 0.424 | +| clip_range | 0.2 | +| entropy_loss | -0.249 | +| explained_variance | -0.647 | +| learning_rate | 0.0001 | +| loss | -0.0799 | +| n_updates | 140040 | +| policy_gradient_loss | -0.052 | +| value_loss | 0.000818 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.229 | +| time/ | | +| fps | 309 | +| iterations | 7953 | +| time_elapsed | 26308 | +| total_timesteps | 8143872 | +| train/ | | +| approx_kl | 3.589113 | +| clip_fraction | 0.469 | +| clip_range | 0.2 | +| entropy_loss | -0.266 | +| explained_variance | -2.93 | +| learning_rate | 0.0001 | +| loss | -0.0753 | +| n_updates | 140050 | +| policy_gradient_loss | -0.0626 | +| value_loss | 0.000829 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.235 | +| time/ | | +| fps | 309 | +| iterations | 7954 | +| time_elapsed | 26311 | +| total_timesteps | 8144896 | +| train/ | | +| approx_kl | 3.4057255 | +| clip_fraction | 0.45 | +| clip_range | 0.2 | +| entropy_loss | -0.26 | +| explained_variance | -1.48 | +| learning_rate | 0.0001 | +| loss | -0.0914 | +| n_updates | 140060 | +| policy_gradient_loss | -0.0586 | +| value_loss | 0.000863 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.235 | +| time/ | | +| fps | 309 | +| iterations | 7955 | +| time_elapsed | 26314 | +| total_timesteps | 8145920 | +| train/ | | +| approx_kl | 3.096944 | +| clip_fraction | 0.436 | +| clip_range | 0.2 | +| entropy_loss | -0.252 | +| explained_variance | -1.29 | +| learning_rate | 0.0001 | +| loss | -0.0616 | +| n_updates | 140070 | +| policy_gradient_loss | -0.0567 | +| value_loss | 0.0008 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.235 | +| time/ | | +| fps | 309 | +| iterations | 7956 | +| time_elapsed | 26318 | +| total_timesteps | 8146944 | +| train/ | | +| approx_kl | 2.366918 | +| clip_fraction | 0.409 | +| clip_range | 0.2 | +| entropy_loss | -0.248 | +| explained_variance | -1.5 | +| learning_rate | 0.0001 | +| loss | -0.0501 | +| n_updates | 140080 | +| policy_gradient_loss | -0.0567 | +| value_loss | 0.000864 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.232 | +| time/ | | +| fps | 309 | +| iterations | 7957 | +| time_elapsed | 26321 | +| total_timesteps | 8147968 | +| train/ | | +| approx_kl | 2.622225 | +| clip_fraction | 0.438 | +| clip_range | 0.2 | +| entropy_loss | -0.262 | +| explained_variance | -1.81 | +| learning_rate | 0.0001 | +| loss | -0.0904 | +| n_updates | 140090 | +| policy_gradient_loss | -0.0655 | +| value_loss | 0.000788 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.23 | +| time/ | | +| fps | 309 | +| iterations | 7958 | +| time_elapsed | 26325 | +| total_timesteps | 8148992 | +| train/ | | +| approx_kl | 2.0484438 | +| clip_fraction | 0.367 | +| clip_range | 0.2 | +| entropy_loss | -0.236 | +| explained_variance | -3.9 | +| learning_rate | 0.0001 | +| loss | -0.0619 | +| n_updates | 140100 | +| policy_gradient_loss | -0.0477 | +| value_loss | 0.000603 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.226 | +| time/ | | +| fps | 309 | +| iterations | 7959 | +| time_elapsed | 26328 | +| total_timesteps | 8150016 | +| train/ | | +| approx_kl | 3.1907954 | +| clip_fraction | 0.405 | +| clip_range | 0.2 | +| entropy_loss | -0.229 | +| explained_variance | -2.73 | +| learning_rate | 0.0001 | +| loss | -0.0797 | +| n_updates | 140110 | +| policy_gradient_loss | -0.0568 | +| value_loss | 0.000754 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.227 | +| time/ | | +| fps | 309 | +| iterations | 7960 | +| time_elapsed | 26331 | +| total_timesteps | 8151040 | +| train/ | | +| approx_kl | 2.1366634 | +| clip_fraction | 0.385 | +| clip_range | 0.2 | +| entropy_loss | -0.25 | +| explained_variance | -0.811 | +| learning_rate | 0.0001 | +| loss | -0.0843 | +| n_updates | 140120 | +| policy_gradient_loss | -0.0562 | +| value_loss | 0.000585 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.222 | +| time/ | | +| fps | 309 | +| iterations | 7961 | +| time_elapsed | 26334 | +| total_timesteps | 8152064 | +| train/ | | +| approx_kl | 2.1210704 | +| clip_fraction | 0.397 | +| clip_range | 0.2 | +| entropy_loss | -0.242 | +| explained_variance | -1.68 | +| learning_rate | 0.0001 | +| loss | -0.048 | +| n_updates | 140130 | +| policy_gradient_loss | -0.0546 | +| value_loss | 0.000604 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.222 | +| time/ | | +| fps | 309 | +| iterations | 7962 | +| time_elapsed | 26338 | +| total_timesteps | 8153088 | +| train/ | | +| approx_kl | 2.9887438 | +| clip_fraction | 0.383 | +| clip_range | 0.2 | +| entropy_loss | -0.237 | +| explained_variance | -0.968 | +| learning_rate | 0.0001 | +| loss | -0.0512 | +| n_updates | 140140 | +| policy_gradient_loss | -0.0528 | +| value_loss | 0.000879 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.222 | +| time/ | | +| fps | 309 | +| iterations | 7963 | +| time_elapsed | 26341 | +| total_timesteps | 8154112 | +| train/ | | +| approx_kl | 2.75768 | +| clip_fraction | 0.422 | +| clip_range | 0.2 | +| entropy_loss | -0.248 | +| explained_variance | -2.52 | +| learning_rate | 0.0001 | +| loss | -0.0518 | +| n_updates | 140150 | +| policy_gradient_loss | -0.0516 | +| value_loss | 0.000551 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.223 | +| time/ | | +| fps | 309 | +| iterations | 7964 | +| time_elapsed | 26344 | +| total_timesteps | 8155136 | +| train/ | | +| approx_kl | 2.3276525 | +| clip_fraction | 0.418 | +| clip_range | 0.2 | +| entropy_loss | -0.274 | +| explained_variance | -1.92 | +| learning_rate | 0.0001 | +| loss | -0.0728 | +| n_updates | 140160 | +| policy_gradient_loss | -0.0568 | +| value_loss | 0.000676 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.229 | +| time/ | | +| fps | 309 | +| iterations | 7965 | +| time_elapsed | 26348 | +| total_timesteps | 8156160 | +| train/ | | +| approx_kl | 2.7659698 | +| clip_fraction | 0.443 | +| clip_range | 0.2 | +| entropy_loss | -0.275 | +| explained_variance | -2.25 | +| learning_rate | 0.0001 | +| loss | -0.0763 | +| n_updates | 140170 | +| policy_gradient_loss | -0.0564 | +| value_loss | 0.000625 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.229 | +| time/ | | +| fps | 309 | +| iterations | 7966 | +| time_elapsed | 26351 | +| total_timesteps | 8157184 | +| train/ | | +| approx_kl | 2.9476337 | +| clip_fraction | 0.447 | +| clip_range | 0.2 | +| entropy_loss | -0.274 | +| explained_variance | -0.546 | +| learning_rate | 0.0001 | +| loss | -0.0537 | +| n_updates | 140180 | +| policy_gradient_loss | -0.0581 | +| value_loss | 0.00109 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.222 | +| time/ | | +| fps | 309 | +| iterations | 7967 | +| time_elapsed | 26354 | +| total_timesteps | 8158208 | +| train/ | | +| approx_kl | 2.5509863 | +| clip_fraction | 0.399 | +| clip_range | 0.2 | +| entropy_loss | -0.242 | +| explained_variance | -4.3 | +| learning_rate | 0.0001 | +| loss | -0.0844 | +| n_updates | 140190 | +| policy_gradient_loss | -0.05 | +| value_loss | 0.000992 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.22 | +| time/ | | +| fps | 309 | +| iterations | 7968 | +| time_elapsed | 26357 | +| total_timesteps | 8159232 | +| train/ | | +| approx_kl | 2.5097523 | +| clip_fraction | 0.396 | +| clip_range | 0.2 | +| entropy_loss | -0.24 | +| explained_variance | -2.31 | +| learning_rate | 0.0001 | +| loss | -0.0818 | +| n_updates | 140200 | +| policy_gradient_loss | -0.0537 | +| value_loss | 0.000953 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.214 | +| time/ | | +| fps | 309 | +| iterations | 7969 | +| time_elapsed | 26361 | +| total_timesteps | 8160256 | +| train/ | | +| approx_kl | 2.272654 | +| clip_fraction | 0.451 | +| clip_range | 0.2 | +| entropy_loss | -0.285 | +| explained_variance | -2.48 | +| learning_rate | 0.0001 | +| loss | -0.0845 | +| n_updates | 140210 | +| policy_gradient_loss | -0.0628 | +| value_loss | 0.000536 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.217 | +| time/ | | +| fps | 309 | +| iterations | 7970 | +| time_elapsed | 26364 | +| total_timesteps | 8161280 | +| train/ | | +| approx_kl | 2.8023577 | +| clip_fraction | 0.467 | +| clip_range | 0.2 | +| entropy_loss | -0.282 | +| explained_variance | -1.67 | +| learning_rate | 0.0001 | +| loss | -0.0732 | +| n_updates | 140220 | +| policy_gradient_loss | -0.0608 | +| value_loss | 0.000546 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.218 | +| time/ | | +| fps | 309 | +| iterations | 7971 | +| time_elapsed | 26367 | +| total_timesteps | 8162304 | +| train/ | | +| approx_kl | 4.4438252 | +| clip_fraction | 0.436 | +| clip_range | 0.2 | +| entropy_loss | -0.291 | +| explained_variance | -1.54 | +| learning_rate | 0.0001 | +| loss | -0.0829 | +| n_updates | 140230 | +| policy_gradient_loss | -0.0589 | +| value_loss | 0.000632 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.218 | +| time/ | | +| fps | 309 | +| iterations | 7972 | +| time_elapsed | 26370 | +| total_timesteps | 8163328 | +| train/ | | +| approx_kl | 2.3995628 | +| clip_fraction | 0.427 | +| clip_range | 0.2 | +| entropy_loss | -0.25 | +| explained_variance | -1.05 | +| learning_rate | 0.0001 | +| loss | -0.051 | +| n_updates | 140240 | +| policy_gradient_loss | -0.0615 | +| value_loss | 0.000748 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.221 | +| time/ | | +| fps | 309 | +| iterations | 7973 | +| time_elapsed | 26373 | +| total_timesteps | 8164352 | +| train/ | | +| approx_kl | 2.2920043 | +| clip_fraction | 0.434 | +| clip_range | 0.2 | +| entropy_loss | -0.277 | +| explained_variance | -1.16 | +| learning_rate | 0.0001 | +| loss | -0.062 | +| n_updates | 140250 | +| policy_gradient_loss | -0.0556 | +| value_loss | 0.000818 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.223 | +| time/ | | +| fps | 309 | +| iterations | 7974 | +| time_elapsed | 26376 | +| total_timesteps | 8165376 | +| train/ | | +| approx_kl | 2.3940027 | +| clip_fraction | 0.426 | +| clip_range | 0.2 | +| entropy_loss | -0.267 | +| explained_variance | -0.613 | +| learning_rate | 0.0001 | +| loss | -0.0627 | +| n_updates | 140260 | +| policy_gradient_loss | -0.0557 | +| value_loss | 0.000666 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.218 | +| time/ | | +| fps | 309 | +| iterations | 7975 | +| time_elapsed | 26379 | +| total_timesteps | 8166400 | +| train/ | | +| approx_kl | 2.3063972 | +| clip_fraction | 0.462 | +| clip_range | 0.2 | +| entropy_loss | -0.325 | +| explained_variance | -0.855 | +| learning_rate | 0.0001 | +| loss | -0.112 | +| n_updates | 140270 | +| policy_gradient_loss | -0.062 | +| value_loss | 0.000677 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.218 | +| time/ | | +| fps | 309 | +| iterations | 7976 | +| time_elapsed | 26383 | +| total_timesteps | 8167424 | +| train/ | | +| approx_kl | 2.2679381 | +| clip_fraction | 0.414 | +| clip_range | 0.2 | +| entropy_loss | -0.262 | +| explained_variance | -1.05 | +| learning_rate | 0.0001 | +| loss | -0.063 | +| n_updates | 140280 | +| policy_gradient_loss | -0.059 | +| value_loss | 0.000718 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.208 | +| time/ | | +| fps | 309 | +| iterations | 7977 | +| time_elapsed | 26386 | +| total_timesteps | 8168448 | +| train/ | | +| approx_kl | 2.3313198 | +| clip_fraction | 0.421 | +| clip_range | 0.2 | +| entropy_loss | -0.244 | +| explained_variance | -1.27 | +| learning_rate | 0.0001 | +| loss | -0.0664 | +| n_updates | 140290 | +| policy_gradient_loss | -0.0634 | +| value_loss | 0.000771 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.208 | +| time/ | | +| fps | 309 | +| iterations | 7978 | +| time_elapsed | 26390 | +| total_timesteps | 8169472 | +| train/ | | +| approx_kl | 3.0613055 | +| clip_fraction | 0.424 | +| clip_range | 0.2 | +| entropy_loss | -0.246 | +| explained_variance | -1.88 | +| learning_rate | 0.0001 | +| loss | -0.0439 | +| n_updates | 140300 | +| policy_gradient_loss | -0.0424 | +| value_loss | 0.00107 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.206 | +| time/ | | +| fps | 309 | +| iterations | 7979 | +| time_elapsed | 26393 | +| total_timesteps | 8170496 | +| train/ | | +| approx_kl | 2.268444 | +| clip_fraction | 0.417 | +| clip_range | 0.2 | +| entropy_loss | -0.277 | +| explained_variance | -1.27 | +| learning_rate | 0.0001 | +| loss | -0.0683 | +| n_updates | 140310 | +| policy_gradient_loss | -0.0559 | +| value_loss | 0.000718 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.206 | +| time/ | | +| fps | 309 | +| iterations | 7980 | +| time_elapsed | 26397 | +| total_timesteps | 8171520 | +| train/ | | +| approx_kl | 2.812561 | +| clip_fraction | 0.427 | +| clip_range | 0.2 | +| entropy_loss | -0.241 | +| explained_variance | -1.98 | +| learning_rate | 0.0001 | +| loss | -0.0814 | +| n_updates | 140320 | +| policy_gradient_loss | -0.0628 | +| value_loss | 0.001 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.209 | +| time/ | | +| fps | 309 | +| iterations | 7981 | +| time_elapsed | 26400 | +| total_timesteps | 8172544 | +| train/ | | +| approx_kl | 2.6024494 | +| clip_fraction | 0.425 | +| clip_range | 0.2 | +| entropy_loss | -0.244 | +| explained_variance | -2.67 | +| learning_rate | 0.0001 | +| loss | -0.108 | +| n_updates | 140330 | +| policy_gradient_loss | -0.0619 | +| value_loss | 0.00062 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.21 | +| time/ | | +| fps | 309 | +| iterations | 7982 | +| time_elapsed | 26404 | +| total_timesteps | 8173568 | +| train/ | | +| approx_kl | 3.2357688 | +| clip_fraction | 0.44 | +| clip_range | 0.2 | +| entropy_loss | -0.251 | +| explained_variance | -1.42 | +| learning_rate | 0.0001 | +| loss | -0.0602 | +| n_updates | 140340 | +| policy_gradient_loss | -0.059 | +| value_loss | 0.000667 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.203 | +| time/ | | +| fps | 309 | +| iterations | 7983 | +| time_elapsed | 26407 | +| total_timesteps | 8174592 | +| train/ | | +| approx_kl | 3.585301 | +| clip_fraction | 0.426 | +| clip_range | 0.2 | +| entropy_loss | -0.236 | +| explained_variance | -0.953 | +| learning_rate | 0.0001 | +| loss | -0.0629 | +| n_updates | 140350 | +| policy_gradient_loss | -0.0603 | +| value_loss | 0.000841 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.203 | +| time/ | | +| fps | 309 | +| iterations | 7984 | +| time_elapsed | 26410 | +| total_timesteps | 8175616 | +| train/ | | +| approx_kl | 2.4170315 | +| clip_fraction | 0.399 | +| clip_range | 0.2 | +| entropy_loss | -0.225 | +| explained_variance | -2.14 | +| learning_rate | 0.0001 | +| loss | -0.0882 | +| n_updates | 140360 | +| policy_gradient_loss | -0.0594 | +| value_loss | 0.000653 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.196 | +| time/ | | +| fps | 309 | +| iterations | 7985 | +| time_elapsed | 26414 | +| total_timesteps | 8176640 | +| train/ | | +| approx_kl | 2.5135531 | +| clip_fraction | 0.434 | +| clip_range | 0.2 | +| entropy_loss | -0.272 | +| explained_variance | -0.75 | +| learning_rate | 0.0001 | +| loss | -0.0709 | +| n_updates | 140370 | +| policy_gradient_loss | -0.0616 | +| value_loss | 0.000618 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.196 | +| time/ | | +| fps | 309 | +| iterations | 7986 | +| time_elapsed | 26417 | +| total_timesteps | 8177664 | +| train/ | | +| approx_kl | 2.4571953 | +| clip_fraction | 0.414 | +| clip_range | 0.2 | +| entropy_loss | -0.245 | +| explained_variance | -2.66 | +| learning_rate | 0.0001 | +| loss | -0.0905 | +| n_updates | 140380 | +| policy_gradient_loss | -0.0583 | +| value_loss | 0.000688 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.192 | +| time/ | | +| fps | 309 | +| iterations | 7987 | +| time_elapsed | 26420 | +| total_timesteps | 8178688 | +| train/ | | +| approx_kl | 3.31391 | +| clip_fraction | 0.448 | +| clip_range | 0.2 | +| entropy_loss | -0.25 | +| explained_variance | -1.63 | +| learning_rate | 0.0001 | +| loss | -0.0974 | +| n_updates | 140390 | +| policy_gradient_loss | -0.0581 | +| value_loss | 0.00092 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.192 | +| time/ | | +| fps | 309 | +| iterations | 7988 | +| time_elapsed | 26423 | +| total_timesteps | 8179712 | +| train/ | | +| approx_kl | 2.4915798 | +| clip_fraction | 0.45 | +| clip_range | 0.2 | +| entropy_loss | -0.257 | +| explained_variance | -2.21 | +| learning_rate | 0.0001 | +| loss | -0.0531 | +| n_updates | 140400 | +| policy_gradient_loss | -0.0467 | +| value_loss | 0.000781 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.192 | +| time/ | | +| fps | 309 | +| iterations | 7989 | +| time_elapsed | 26426 | +| total_timesteps | 8180736 | +| train/ | | +| approx_kl | 3.3090453 | +| clip_fraction | 0.43 | +| clip_range | 0.2 | +| entropy_loss | -0.257 | +| explained_variance | -0.948 | +| learning_rate | 0.0001 | +| loss | -0.0761 | +| n_updates | 140410 | +| policy_gradient_loss | -0.059 | +| value_loss | 0.00091 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.192 | +| time/ | | +| fps | 309 | +| iterations | 7990 | +| time_elapsed | 26430 | +| total_timesteps | 8181760 | +| train/ | | +| approx_kl | 2.7964077 | +| clip_fraction | 0.426 | +| clip_range | 0.2 | +| entropy_loss | -0.285 | +| explained_variance | -1.95 | +| learning_rate | 0.0001 | +| loss | -0.0728 | +| n_updates | 140420 | +| policy_gradient_loss | -0.051 | +| value_loss | 0.000656 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.194 | +| time/ | | +| fps | 309 | +| iterations | 7991 | +| time_elapsed | 26433 | +| total_timesteps | 8182784 | +| train/ | | +| approx_kl | 2.505117 | +| clip_fraction | 0.435 | +| clip_range | 0.2 | +| entropy_loss | -0.26 | +| explained_variance | -1.61 | +| learning_rate | 0.0001 | +| loss | -0.00952 | +| n_updates | 140430 | +| policy_gradient_loss | -0.0588 | +| value_loss | 0.000848 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.194 | +| time/ | | +| fps | 309 | +| iterations | 7992 | +| time_elapsed | 26436 | +| total_timesteps | 8183808 | +| train/ | | +| approx_kl | 2.2459705 | +| clip_fraction | 0.44 | +| clip_range | 0.2 | +| entropy_loss | -0.282 | +| explained_variance | -1.46 | +| learning_rate | 0.0001 | +| loss | -0.0937 | +| n_updates | 140440 | +| policy_gradient_loss | -0.0622 | +| value_loss | 0.00078 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.191 | +| time/ | | +| fps | 309 | +| iterations | 7993 | +| time_elapsed | 26439 | +| total_timesteps | 8184832 | +| train/ | | +| approx_kl | 3.1951487 | +| clip_fraction | 0.457 | +| clip_range | 0.2 | +| entropy_loss | -0.262 | +| explained_variance | -2.15 | +| learning_rate | 0.0001 | +| loss | -0.0851 | +| n_updates | 140450 | +| policy_gradient_loss | -0.0593 | +| value_loss | 0.00058 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.19 | +| time/ | | +| fps | 309 | +| iterations | 7994 | +| time_elapsed | 26443 | +| total_timesteps | 8185856 | +| train/ | | +| approx_kl | 2.3833985 | +| clip_fraction | 0.441 | +| clip_range | 0.2 | +| entropy_loss | -0.269 | +| explained_variance | -3.1 | +| learning_rate | 0.0001 | +| loss | -0.0852 | +| n_updates | 140460 | +| policy_gradient_loss | -0.062 | +| value_loss | 0.00062 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.188 | +| time/ | | +| fps | 309 | +| iterations | 7995 | +| time_elapsed | 26446 | +| total_timesteps | 8186880 | +| train/ | | +| approx_kl | 2.549879 | +| clip_fraction | 0.434 | +| clip_range | 0.2 | +| entropy_loss | -0.275 | +| explained_variance | -1.09 | +| learning_rate | 0.0001 | +| loss | -0.096 | +| n_updates | 140470 | +| policy_gradient_loss | -0.0526 | +| value_loss | 0.000555 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.185 | +| time/ | | +| fps | 309 | +| iterations | 7996 | +| time_elapsed | 26450 | +| total_timesteps | 8187904 | +| train/ | | +| approx_kl | 3.4404814 | +| clip_fraction | 0.432 | +| clip_range | 0.2 | +| entropy_loss | -0.284 | +| explained_variance | -1.07 | +| learning_rate | 0.0001 | +| loss | -0.0646 | +| n_updates | 140480 | +| policy_gradient_loss | -0.0541 | +| value_loss | 0.000852 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.187 | +| time/ | | +| fps | 309 | +| iterations | 7997 | +| time_elapsed | 26453 | +| total_timesteps | 8188928 | +| train/ | | +| approx_kl | 2.7462974 | +| clip_fraction | 0.42 | +| clip_range | 0.2 | +| entropy_loss | -0.26 | +| explained_variance | -2.74 | +| learning_rate | 0.0001 | +| loss | -0.0796 | +| n_updates | 140490 | +| policy_gradient_loss | -0.0572 | +| value_loss | 0.000751 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.184 | +| time/ | | +| fps | 309 | +| iterations | 7998 | +| time_elapsed | 26456 | +| total_timesteps | 8189952 | +| train/ | | +| approx_kl | 3.1484804 | +| clip_fraction | 0.465 | +| clip_range | 0.2 | +| entropy_loss | -0.302 | +| explained_variance | -0.728 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 140500 | +| policy_gradient_loss | -0.0624 | +| value_loss | 0.00107 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.184 | +| time/ | | +| fps | 309 | +| iterations | 7999 | +| time_elapsed | 26460 | +| total_timesteps | 8190976 | +| train/ | | +| approx_kl | 4.312768 | +| clip_fraction | 0.432 | +| clip_range | 0.2 | +| entropy_loss | -0.225 | +| explained_variance | -3.12 | +| learning_rate | 0.0001 | +| loss | -0.0801 | +| n_updates | 140510 | +| policy_gradient_loss | -0.0612 | +| value_loss | 0.000877 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.187 | +| time/ | | +| fps | 309 | +| iterations | 8000 | +| time_elapsed | 26463 | +| total_timesteps | 8192000 | +| train/ | | +| approx_kl | 2.4383154 | +| clip_fraction | 0.425 | +| clip_range | 0.2 | +| entropy_loss | -0.277 | +| explained_variance | -2.19 | +| learning_rate | 0.0001 | +| loss | -0.0801 | +| n_updates | 140520 | +| policy_gradient_loss | -0.0616 | +| value_loss | 0.000518 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.185 | +| time/ | | +| fps | 309 | +| iterations | 8001 | +| time_elapsed | 26466 | +| total_timesteps | 8193024 | +| train/ | | +| approx_kl | 2.5754547 | +| clip_fraction | 0.417 | +| clip_range | 0.2 | +| entropy_loss | -0.251 | +| explained_variance | -0.671 | +| learning_rate | 0.0001 | +| loss | -0.0772 | +| n_updates | 140530 | +| policy_gradient_loss | -0.0578 | +| value_loss | 0.000734 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.189 | +| time/ | | +| fps | 309 | +| iterations | 8002 | +| time_elapsed | 26469 | +| total_timesteps | 8194048 | +| train/ | | +| approx_kl | 1.8788741 | +| clip_fraction | 0.402 | +| clip_range | 0.2 | +| entropy_loss | -0.281 | +| explained_variance | -1.17 | +| learning_rate | 0.0001 | +| loss | -0.0715 | +| n_updates | 140540 | +| policy_gradient_loss | -0.0572 | +| value_loss | 0.000689 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.19 | +| time/ | | +| fps | 309 | +| iterations | 8003 | +| time_elapsed | 26473 | +| total_timesteps | 8195072 | +| train/ | | +| approx_kl | 2.225435 | +| clip_fraction | 0.46 | +| clip_range | 0.2 | +| entropy_loss | -0.294 | +| explained_variance | -0.345 | +| learning_rate | 0.0001 | +| loss | -0.0758 | +| n_updates | 140550 | +| policy_gradient_loss | -0.0508 | +| value_loss | 0.00102 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.19 | +| time/ | | +| fps | 309 | +| iterations | 8004 | +| time_elapsed | 26476 | +| total_timesteps | 8196096 | +| train/ | | +| approx_kl | 3.013564 | +| clip_fraction | 0.443 | +| clip_range | 0.2 | +| entropy_loss | -0.253 | +| explained_variance | -1.22 | +| learning_rate | 0.0001 | +| loss | -0.0708 | +| n_updates | 140560 | +| policy_gradient_loss | -0.0679 | +| value_loss | 0.00105 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.189 | +| time/ | | +| fps | 309 | +| iterations | 8005 | +| time_elapsed | 26479 | +| total_timesteps | 8197120 | +| train/ | | +| approx_kl | 2.8656015 | +| clip_fraction | 0.454 | +| clip_range | 0.2 | +| entropy_loss | -0.296 | +| explained_variance | -3.87 | +| learning_rate | 0.0001 | +| loss | -0.09 | +| n_updates | 140570 | +| policy_gradient_loss | -0.0641 | +| value_loss | 0.00094 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.187 | +| time/ | | +| fps | 309 | +| iterations | 8006 | +| time_elapsed | 26482 | +| total_timesteps | 8198144 | +| train/ | | +| approx_kl | 1.958932 | +| clip_fraction | 0.411 | +| clip_range | 0.2 | +| entropy_loss | -0.259 | +| explained_variance | -2.92 | +| learning_rate | 0.0001 | +| loss | -0.0628 | +| n_updates | 140580 | +| policy_gradient_loss | -0.0506 | +| value_loss | 0.000636 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.187 | +| time/ | | +| fps | 309 | +| iterations | 8007 | +| time_elapsed | 26485 | +| total_timesteps | 8199168 | +| train/ | | +| approx_kl | 2.2691622 | +| clip_fraction | 0.452 | +| clip_range | 0.2 | +| entropy_loss | -0.286 | +| explained_variance | -2.34 | +| learning_rate | 0.0001 | +| loss | -0.0614 | +| n_updates | 140590 | +| policy_gradient_loss | -0.0647 | +| value_loss | 0.000701 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.188 | +| time/ | | +| fps | 309 | +| iterations | 8008 | +| time_elapsed | 26489 | +| total_timesteps | 8200192 | +| train/ | | +| approx_kl | 3.137022 | +| clip_fraction | 0.458 | +| clip_range | 0.2 | +| entropy_loss | -0.257 | +| explained_variance | -1.19 | +| learning_rate | 0.0001 | +| loss | -0.0918 | +| n_updates | 140600 | +| policy_gradient_loss | -0.0678 | +| value_loss | 0.000859 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.186 | +| time/ | | +| fps | 309 | +| iterations | 8009 | +| time_elapsed | 26492 | +| total_timesteps | 8201216 | +| train/ | | +| approx_kl | 2.2266216 | +| clip_fraction | 0.408 | +| clip_range | 0.2 | +| entropy_loss | -0.242 | +| explained_variance | -3.58 | +| learning_rate | 0.0001 | +| loss | -0.0974 | +| n_updates | 140610 | +| policy_gradient_loss | -0.0577 | +| value_loss | 0.000695 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.184 | +| time/ | | +| fps | 309 | +| iterations | 8010 | +| time_elapsed | 26495 | +| total_timesteps | 8202240 | +| train/ | | +| approx_kl | 2.6539636 | +| clip_fraction | 0.405 | +| clip_range | 0.2 | +| entropy_loss | -0.25 | +| explained_variance | -3.14 | +| learning_rate | 0.0001 | +| loss | -0.0744 | +| n_updates | 140620 | +| policy_gradient_loss | -0.0506 | +| value_loss | 0.00065 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.186 | +| time/ | | +| fps | 309 | +| iterations | 8011 | +| time_elapsed | 26498 | +| total_timesteps | 8203264 | +| train/ | | +| approx_kl | 2.5452855 | +| clip_fraction | 0.41 | +| clip_range | 0.2 | +| entropy_loss | -0.248 | +| explained_variance | -1.54 | +| learning_rate | 0.0001 | +| loss | -0.081 | +| n_updates | 140630 | +| policy_gradient_loss | -0.0591 | +| value_loss | 0.000606 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.186 | +| time/ | | +| fps | 309 | +| iterations | 8012 | +| time_elapsed | 26502 | +| total_timesteps | 8204288 | +| train/ | | +| approx_kl | 2.5943701 | +| clip_fraction | 0.459 | +| clip_range | 0.2 | +| entropy_loss | -0.295 | +| explained_variance | -1.85 | +| learning_rate | 0.0001 | +| loss | -0.07 | +| n_updates | 140640 | +| policy_gradient_loss | -0.0651 | +| value_loss | 0.000756 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.181 | +| time/ | | +| fps | 309 | +| iterations | 8013 | +| time_elapsed | 26505 | +| total_timesteps | 8205312 | +| train/ | | +| approx_kl | 2.7390862 | +| clip_fraction | 0.442 | +| clip_range | 0.2 | +| entropy_loss | -0.253 | +| explained_variance | -2.17 | +| learning_rate | 0.0001 | +| loss | -0.0893 | +| n_updates | 140650 | +| policy_gradient_loss | -0.0625 | +| value_loss | 0.000424 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.177 | +| time/ | | +| fps | 309 | +| iterations | 8014 | +| time_elapsed | 26509 | +| total_timesteps | 8206336 | +| train/ | | +| approx_kl | 2.9406872 | +| clip_fraction | 0.473 | +| clip_range | 0.2 | +| entropy_loss | -0.326 | +| explained_variance | -1.3 | +| learning_rate | 0.0001 | +| loss | -0.0759 | +| n_updates | 140660 | +| policy_gradient_loss | -0.0606 | +| value_loss | 0.00079 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.173 | +| time/ | | +| fps | 309 | +| iterations | 8015 | +| time_elapsed | 26512 | +| total_timesteps | 8207360 | +| train/ | | +| approx_kl | 2.5785797 | +| clip_fraction | 0.476 | +| clip_range | 0.2 | +| entropy_loss | -0.308 | +| explained_variance | -3.53 | +| learning_rate | 0.0001 | +| loss | -0.0877 | +| n_updates | 140670 | +| policy_gradient_loss | -0.0691 | +| value_loss | 0.000829 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.177 | +| time/ | | +| fps | 309 | +| iterations | 8016 | +| time_elapsed | 26516 | +| total_timesteps | 8208384 | +| train/ | | +| approx_kl | 3.4105806 | +| clip_fraction | 0.435 | +| clip_range | 0.2 | +| entropy_loss | -0.254 | +| explained_variance | -1.45 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 140680 | +| policy_gradient_loss | -0.0665 | +| value_loss | 0.000773 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.177 | +| time/ | | +| fps | 309 | +| iterations | 8017 | +| time_elapsed | 26519 | +| total_timesteps | 8209408 | +| train/ | | +| approx_kl | 2.525143 | +| clip_fraction | 0.442 | +| clip_range | 0.2 | +| entropy_loss | -0.27 | +| explained_variance | -0.798 | +| learning_rate | 0.0001 | +| loss | -0.0674 | +| n_updates | 140690 | +| policy_gradient_loss | -0.0611 | +| value_loss | 0.001 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.14e+03 | +| ep_rew_mean | 0.17 | +| time/ | | +| fps | 309 | +| iterations | 8018 | +| time_elapsed | 26523 | +| total_timesteps | 8210432 | +| train/ | | +| approx_kl | 2.2279336 | +| clip_fraction | 0.423 | +| clip_range | 0.2 | +| entropy_loss | -0.26 | +| explained_variance | -3.66 | +| learning_rate | 0.0001 | +| loss | -0.0611 | +| n_updates | 140700 | +| policy_gradient_loss | -0.0569 | +| value_loss | 0.000572 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.14e+03 | +| ep_rew_mean | 0.169 | +| time/ | | +| fps | 309 | +| iterations | 8019 | +| time_elapsed | 26526 | +| total_timesteps | 8211456 | +| train/ | | +| approx_kl | 2.229261 | +| clip_fraction | 0.418 | +| clip_range | 0.2 | +| entropy_loss | -0.282 | +| explained_variance | -2.35 | +| learning_rate | 0.0001 | +| loss | -0.0783 | +| n_updates | 140710 | +| policy_gradient_loss | -0.0532 | +| value_loss | 0.000439 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.164 | +| time/ | | +| fps | 309 | +| iterations | 8020 | +| time_elapsed | 26530 | +| total_timesteps | 8212480 | +| train/ | | +| approx_kl | 5.3242936 | +| clip_fraction | 0.452 | +| clip_range | 0.2 | +| entropy_loss | -0.287 | +| explained_variance | -1.08 | +| learning_rate | 0.0001 | +| loss | -0.0785 | +| n_updates | 140720 | +| policy_gradient_loss | -0.0634 | +| value_loss | 0.000685 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.13e+03 | +| ep_rew_mean | 0.152 | +| time/ | | +| fps | 309 | +| iterations | 8021 | +| time_elapsed | 26533 | +| total_timesteps | 8213504 | +| train/ | | +| approx_kl | 2.7607849 | +| clip_fraction | 0.436 | +| clip_range | 0.2 | +| entropy_loss | -0.255 | +| explained_variance | -3.94 | +| learning_rate | 0.0001 | +| loss | -0.111 | +| n_updates | 140730 | +| policy_gradient_loss | -0.0593 | +| value_loss | 0.000618 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.13e+03 | +| ep_rew_mean | 0.152 | +| time/ | | +| fps | 309 | +| iterations | 8022 | +| time_elapsed | 26536 | +| total_timesteps | 8214528 | +| train/ | | +| approx_kl | 2.8199215 | +| clip_fraction | 0.395 | +| clip_range | 0.2 | +| entropy_loss | -0.259 | +| explained_variance | -0.548 | +| learning_rate | 0.0001 | +| loss | -0.0853 | +| n_updates | 140740 | +| policy_gradient_loss | -0.0638 | +| value_loss | 0.000717 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.14e+03 | +| ep_rew_mean | 0.149 | +| time/ | | +| fps | 309 | +| iterations | 8023 | +| time_elapsed | 26539 | +| total_timesteps | 8215552 | +| train/ | | +| approx_kl | 2.8482294 | +| clip_fraction | 0.459 | +| clip_range | 0.2 | +| entropy_loss | -0.283 | +| explained_variance | -2.54 | +| learning_rate | 0.0001 | +| loss | -0.109 | +| n_updates | 140750 | +| policy_gradient_loss | -0.0595 | +| value_loss | 0.000657 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.14e+03 | +| ep_rew_mean | 0.149 | +| time/ | | +| fps | 309 | +| iterations | 8024 | +| time_elapsed | 26543 | +| total_timesteps | 8216576 | +| train/ | | +| approx_kl | 2.243452 | +| clip_fraction | 0.443 | +| clip_range | 0.2 | +| entropy_loss | -0.294 | +| explained_variance | -1.75 | +| learning_rate | 0.0001 | +| loss | -0.0807 | +| n_updates | 140760 | +| policy_gradient_loss | -0.0644 | +| value_loss | 0.000498 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.14e+03 | +| ep_rew_mean | 0.153 | +| time/ | | +| fps | 309 | +| iterations | 8025 | +| time_elapsed | 26546 | +| total_timesteps | 8217600 | +| train/ | | +| approx_kl | 2.4919376 | +| clip_fraction | 0.459 | +| clip_range | 0.2 | +| entropy_loss | -0.302 | +| explained_variance | -1.3 | +| learning_rate | 0.0001 | +| loss | -0.0874 | +| n_updates | 140770 | +| policy_gradient_loss | -0.0635 | +| value_loss | 0.000683 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.14e+03 | +| ep_rew_mean | 0.147 | +| time/ | | +| fps | 309 | +| iterations | 8026 | +| time_elapsed | 26549 | +| total_timesteps | 8218624 | +| train/ | | +| approx_kl | 2.432771 | +| clip_fraction | 0.451 | +| clip_range | 0.2 | +| entropy_loss | -0.278 | +| explained_variance | -2.29 | +| learning_rate | 0.0001 | +| loss | -0.0588 | +| n_updates | 140780 | +| policy_gradient_loss | -0.0668 | +| value_loss | 0.000965 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.14e+03 | +| ep_rew_mean | 0.142 | +| time/ | | +| fps | 309 | +| iterations | 8027 | +| time_elapsed | 26552 | +| total_timesteps | 8219648 | +| train/ | | +| approx_kl | 2.7176833 | +| clip_fraction | 0.453 | +| clip_range | 0.2 | +| entropy_loss | -0.259 | +| explained_variance | -2.44 | +| learning_rate | 0.0001 | +| loss | -0.0713 | +| n_updates | 140790 | +| policy_gradient_loss | -0.0593 | +| value_loss | 0.000766 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.14e+03 | +| ep_rew_mean | 0.139 | +| time/ | | +| fps | 309 | +| iterations | 8028 | +| time_elapsed | 26556 | +| total_timesteps | 8220672 | +| train/ | | +| approx_kl | 4.2768683 | +| clip_fraction | 0.428 | +| clip_range | 0.2 | +| entropy_loss | -0.271 | +| explained_variance | -1.32 | +| learning_rate | 0.0001 | +| loss | -0.0795 | +| n_updates | 140800 | +| policy_gradient_loss | -0.0578 | +| value_loss | 0.000712 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.14e+03 | +| ep_rew_mean | 0.137 | +| time/ | | +| fps | 309 | +| iterations | 8029 | +| time_elapsed | 26559 | +| total_timesteps | 8221696 | +| train/ | | +| approx_kl | 2.0886211 | +| clip_fraction | 0.428 | +| clip_range | 0.2 | +| entropy_loss | -0.283 | +| explained_variance | -1.47 | +| learning_rate | 0.0001 | +| loss | -0.0845 | +| n_updates | 140810 | +| policy_gradient_loss | -0.0596 | +| value_loss | 0.000736 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.14e+03 | +| ep_rew_mean | 0.135 | +| time/ | | +| fps | 309 | +| iterations | 8030 | +| time_elapsed | 26562 | +| total_timesteps | 8222720 | +| train/ | | +| approx_kl | 2.500008 | +| clip_fraction | 0.445 | +| clip_range | 0.2 | +| entropy_loss | -0.291 | +| explained_variance | -1.91 | +| learning_rate | 0.0001 | +| loss | -0.0719 | +| n_updates | 140820 | +| policy_gradient_loss | -0.0645 | +| value_loss | 0.000518 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.13e+03 | +| ep_rew_mean | 0.13 | +| time/ | | +| fps | 309 | +| iterations | 8031 | +| time_elapsed | 26566 | +| total_timesteps | 8223744 | +| train/ | | +| approx_kl | 2.2443275 | +| clip_fraction | 0.402 | +| clip_range | 0.2 | +| entropy_loss | -0.259 | +| explained_variance | -2.35 | +| learning_rate | 0.0001 | +| loss | -0.06 | +| n_updates | 140830 | +| policy_gradient_loss | -0.06 | +| value_loss | 0.000488 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.12e+03 | +| ep_rew_mean | 0.128 | +| time/ | | +| fps | 309 | +| iterations | 8032 | +| time_elapsed | 26569 | +| total_timesteps | 8224768 | +| train/ | | +| approx_kl | 2.5328321 | +| clip_fraction | 0.41 | +| clip_range | 0.2 | +| entropy_loss | -0.269 | +| explained_variance | -0.762 | +| learning_rate | 0.0001 | +| loss | -0.0606 | +| n_updates | 140840 | +| policy_gradient_loss | -0.0577 | +| value_loss | 0.000492 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.12e+03 | +| ep_rew_mean | 0.127 | +| time/ | | +| fps | 309 | +| iterations | 8033 | +| time_elapsed | 26573 | +| total_timesteps | 8225792 | +| train/ | | +| approx_kl | 2.357443 | +| clip_fraction | 0.404 | +| clip_range | 0.2 | +| entropy_loss | -0.255 | +| explained_variance | -0.114 | +| learning_rate | 0.0001 | +| loss | -0.0801 | +| n_updates | 140850 | +| policy_gradient_loss | -0.0564 | +| value_loss | 0.000752 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.12e+03 | +| ep_rew_mean | 0.127 | +| time/ | | +| fps | 309 | +| iterations | 8034 | +| time_elapsed | 26576 | +| total_timesteps | 8226816 | +| train/ | | +| approx_kl | 1.8946342 | +| clip_fraction | 0.438 | +| clip_range | 0.2 | +| entropy_loss | -0.297 | +| explained_variance | -1.54 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 140860 | +| policy_gradient_loss | -0.0563 | +| value_loss | 0.00062 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.13e+03 | +| ep_rew_mean | 0.128 | +| time/ | | +| fps | 309 | +| iterations | 8035 | +| time_elapsed | 26580 | +| total_timesteps | 8227840 | +| train/ | | +| approx_kl | 2.1243062 | +| clip_fraction | 0.456 | +| clip_range | 0.2 | +| entropy_loss | -0.32 | +| explained_variance | -1.07 | +| learning_rate | 0.0001 | +| loss | -0.0576 | +| n_updates | 140870 | +| policy_gradient_loss | -0.065 | +| value_loss | 0.000538 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.12e+03 | +| ep_rew_mean | 0.124 | +| time/ | | +| fps | 309 | +| iterations | 8036 | +| time_elapsed | 26583 | +| total_timesteps | 8228864 | +| train/ | | +| approx_kl | 2.5871677 | +| clip_fraction | 0.408 | +| clip_range | 0.2 | +| entropy_loss | -0.26 | +| explained_variance | -1.39 | +| learning_rate | 0.0001 | +| loss | -0.0799 | +| n_updates | 140880 | +| policy_gradient_loss | -0.0574 | +| value_loss | 0.000635 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.12e+03 | +| ep_rew_mean | 0.121 | +| time/ | | +| fps | 309 | +| iterations | 8037 | +| time_elapsed | 26587 | +| total_timesteps | 8229888 | +| train/ | | +| approx_kl | 2.2643433 | +| clip_fraction | 0.422 | +| clip_range | 0.2 | +| entropy_loss | -0.271 | +| explained_variance | -2.3 | +| learning_rate | 0.0001 | +| loss | -0.0915 | +| n_updates | 140890 | +| policy_gradient_loss | -0.0558 | +| value_loss | 0.000596 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.12e+03 | +| ep_rew_mean | 0.123 | +| time/ | | +| fps | 309 | +| iterations | 8038 | +| time_elapsed | 26590 | +| total_timesteps | 8230912 | +| train/ | | +| approx_kl | 2.8205378 | +| clip_fraction | 0.429 | +| clip_range | 0.2 | +| entropy_loss | -0.27 | +| explained_variance | -0.923 | +| learning_rate | 0.0001 | +| loss | -0.0736 | +| n_updates | 140900 | +| policy_gradient_loss | -0.0587 | +| value_loss | 0.000838 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.12e+03 | +| ep_rew_mean | 0.125 | +| time/ | | +| fps | 309 | +| iterations | 8039 | +| time_elapsed | 26593 | +| total_timesteps | 8231936 | +| train/ | | +| approx_kl | 2.938826 | +| clip_fraction | 0.414 | +| clip_range | 0.2 | +| entropy_loss | -0.236 | +| explained_variance | -1.2 | +| learning_rate | 0.0001 | +| loss | -0.0861 | +| n_updates | 140910 | +| policy_gradient_loss | -0.0538 | +| value_loss | 0.00079 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.12e+03 | +| ep_rew_mean | 0.129 | +| time/ | | +| fps | 309 | +| iterations | 8040 | +| time_elapsed | 26596 | +| total_timesteps | 8232960 | +| train/ | | +| approx_kl | 3.2042718 | +| clip_fraction | 0.416 | +| clip_range | 0.2 | +| entropy_loss | -0.245 | +| explained_variance | -0.936 | +| learning_rate | 0.0001 | +| loss | -0.0856 | +| n_updates | 140920 | +| policy_gradient_loss | -0.0581 | +| value_loss | 0.000854 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.12e+03 | +| ep_rew_mean | 0.129 | +| time/ | | +| fps | 309 | +| iterations | 8041 | +| time_elapsed | 26600 | +| total_timesteps | 8233984 | +| train/ | | +| approx_kl | 3.0777278 | +| clip_fraction | 0.453 | +| clip_range | 0.2 | +| entropy_loss | -0.262 | +| explained_variance | -2 | +| learning_rate | 0.0001 | +| loss | -0.0993 | +| n_updates | 140930 | +| policy_gradient_loss | -0.0666 | +| value_loss | 0.0011 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.12e+03 | +| ep_rew_mean | 0.135 | +| time/ | | +| fps | 309 | +| iterations | 8042 | +| time_elapsed | 26603 | +| total_timesteps | 8235008 | +| train/ | | +| approx_kl | 2.787033 | +| clip_fraction | 0.428 | +| clip_range | 0.2 | +| entropy_loss | -0.256 | +| explained_variance | -1.3 | +| learning_rate | 0.0001 | +| loss | -0.0681 | +| n_updates | 140940 | +| policy_gradient_loss | -0.0617 | +| value_loss | 0.000915 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.13e+03 | +| ep_rew_mean | 0.136 | +| time/ | | +| fps | 309 | +| iterations | 8043 | +| time_elapsed | 26606 | +| total_timesteps | 8236032 | +| train/ | | +| approx_kl | 2.5890164 | +| clip_fraction | 0.41 | +| clip_range | 0.2 | +| entropy_loss | -0.244 | +| explained_variance | -2.5 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 140950 | +| policy_gradient_loss | -0.0546 | +| value_loss | 0.0012 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.13e+03 | +| ep_rew_mean | 0.139 | +| time/ | | +| fps | 309 | +| iterations | 8044 | +| time_elapsed | 26609 | +| total_timesteps | 8237056 | +| train/ | | +| approx_kl | 3.8040519 | +| clip_fraction | 0.432 | +| clip_range | 0.2 | +| entropy_loss | -0.269 | +| explained_variance | -1.98 | +| learning_rate | 0.0001 | +| loss | -0.0692 | +| n_updates | 140960 | +| policy_gradient_loss | -0.0604 | +| value_loss | 0.00113 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.13e+03 | +| ep_rew_mean | 0.139 | +| time/ | | +| fps | 309 | +| iterations | 8045 | +| time_elapsed | 26612 | +| total_timesteps | 8238080 | +| train/ | | +| approx_kl | 2.6036115 | +| clip_fraction | 0.424 | +| clip_range | 0.2 | +| entropy_loss | -0.25 | +| explained_variance | -1.85 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 140970 | +| policy_gradient_loss | -0.0573 | +| value_loss | 0.000829 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.13e+03 | +| ep_rew_mean | 0.147 | +| time/ | | +| fps | 309 | +| iterations | 8046 | +| time_elapsed | 26615 | +| total_timesteps | 8239104 | +| train/ | | +| approx_kl | 2.6708107 | +| clip_fraction | 0.426 | +| clip_range | 0.2 | +| entropy_loss | -0.236 | +| explained_variance | -1.51 | +| learning_rate | 0.0001 | +| loss | -0.069 | +| n_updates | 140980 | +| policy_gradient_loss | -0.0631 | +| value_loss | 0.000868 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.13e+03 | +| ep_rew_mean | 0.152 | +| time/ | | +| fps | 309 | +| iterations | 8047 | +| time_elapsed | 26619 | +| total_timesteps | 8240128 | +| train/ | | +| approx_kl | 2.720475 | +| clip_fraction | 0.428 | +| clip_range | 0.2 | +| entropy_loss | -0.255 | +| explained_variance | -2.05 | +| learning_rate | 0.0001 | +| loss | -0.0878 | +| n_updates | 140990 | +| policy_gradient_loss | -0.0561 | +| value_loss | 0.000705 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.13e+03 | +| ep_rew_mean | 0.151 | +| time/ | | +| fps | 309 | +| iterations | 8048 | +| time_elapsed | 26622 | +| total_timesteps | 8241152 | +| train/ | | +| approx_kl | 2.7929926 | +| clip_fraction | 0.432 | +| clip_range | 0.2 | +| entropy_loss | -0.252 | +| explained_variance | -0.724 | +| learning_rate | 0.0001 | +| loss | -0.0828 | +| n_updates | 141000 | +| policy_gradient_loss | -0.0623 | +| value_loss | 0.00105 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.13e+03 | +| ep_rew_mean | 0.153 | +| time/ | | +| fps | 309 | +| iterations | 8049 | +| time_elapsed | 26626 | +| total_timesteps | 8242176 | +| train/ | | +| approx_kl | 2.7615466 | +| clip_fraction | 0.444 | +| clip_range | 0.2 | +| entropy_loss | -0.26 | +| explained_variance | -1.63 | +| learning_rate | 0.0001 | +| loss | -0.0726 | +| n_updates | 141010 | +| policy_gradient_loss | -0.0581 | +| value_loss | 0.000829 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.13e+03 | +| ep_rew_mean | 0.151 | +| time/ | | +| fps | 309 | +| iterations | 8050 | +| time_elapsed | 26629 | +| total_timesteps | 8243200 | +| train/ | | +| approx_kl | 2.6883502 | +| clip_fraction | 0.461 | +| clip_range | 0.2 | +| entropy_loss | -0.311 | +| explained_variance | -0.791 | +| learning_rate | 0.0001 | +| loss | -0.067 | +| n_updates | 141020 | +| policy_gradient_loss | -0.0538 | +| value_loss | 0.000662 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.13e+03 | +| ep_rew_mean | 0.151 | +| time/ | | +| fps | 309 | +| iterations | 8051 | +| time_elapsed | 26633 | +| total_timesteps | 8244224 | +| train/ | | +| approx_kl | 2.4556396 | +| clip_fraction | 0.438 | +| clip_range | 0.2 | +| entropy_loss | -0.277 | +| explained_variance | -1.67 | +| learning_rate | 0.0001 | +| loss | -0.079 | +| n_updates | 141030 | +| policy_gradient_loss | -0.0585 | +| value_loss | 0.000881 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.13e+03 | +| ep_rew_mean | 0.152 | +| time/ | | +| fps | 309 | +| iterations | 8052 | +| time_elapsed | 26636 | +| total_timesteps | 8245248 | +| train/ | | +| approx_kl | 2.7867832 | +| clip_fraction | 0.446 | +| clip_range | 0.2 | +| entropy_loss | -0.284 | +| explained_variance | -3.54 | +| learning_rate | 0.0001 | +| loss | -0.0898 | +| n_updates | 141040 | +| policy_gradient_loss | -0.0594 | +| value_loss | 0.000775 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.13e+03 | +| ep_rew_mean | 0.154 | +| time/ | | +| fps | 309 | +| iterations | 8053 | +| time_elapsed | 26640 | +| total_timesteps | 8246272 | +| train/ | | +| approx_kl | 2.8904276 | +| clip_fraction | 0.442 | +| clip_range | 0.2 | +| entropy_loss | -0.27 | +| explained_variance | -1.07 | +| learning_rate | 0.0001 | +| loss | -0.0925 | +| n_updates | 141050 | +| policy_gradient_loss | -0.0633 | +| value_loss | 0.000806 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.13e+03 | +| ep_rew_mean | 0.157 | +| time/ | | +| fps | 309 | +| iterations | 8054 | +| time_elapsed | 26643 | +| total_timesteps | 8247296 | +| train/ | | +| approx_kl | 3.0335984 | +| clip_fraction | 0.402 | +| clip_range | 0.2 | +| entropy_loss | -0.252 | +| explained_variance | -3.38 | +| learning_rate | 0.0001 | +| loss | -0.0763 | +| n_updates | 141060 | +| policy_gradient_loss | -0.0567 | +| value_loss | 0.000751 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.14e+03 | +| ep_rew_mean | 0.161 | +| time/ | | +| fps | 309 | +| iterations | 8055 | +| time_elapsed | 26647 | +| total_timesteps | 8248320 | +| train/ | | +| approx_kl | 2.9951987 | +| clip_fraction | 0.435 | +| clip_range | 0.2 | +| entropy_loss | -0.261 | +| explained_variance | -1.17 | +| learning_rate | 0.0001 | +| loss | -0.0651 | +| n_updates | 141070 | +| policy_gradient_loss | -0.0611 | +| value_loss | 0.000862 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.14e+03 | +| ep_rew_mean | 0.161 | +| time/ | | +| fps | 309 | +| iterations | 8056 | +| time_elapsed | 26650 | +| total_timesteps | 8249344 | +| train/ | | +| approx_kl | 2.7750974 | +| clip_fraction | 0.386 | +| clip_range | 0.2 | +| entropy_loss | -0.229 | +| explained_variance | -3.25 | +| learning_rate | 0.0001 | +| loss | -0.0738 | +| n_updates | 141080 | +| policy_gradient_loss | -0.0594 | +| value_loss | 0.000525 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.14e+03 | +| ep_rew_mean | 0.164 | +| time/ | | +| fps | 309 | +| iterations | 8057 | +| time_elapsed | 26653 | +| total_timesteps | 8250368 | +| train/ | | +| approx_kl | 2.236155 | +| clip_fraction | 0.425 | +| clip_range | 0.2 | +| entropy_loss | -0.275 | +| explained_variance | -0.866 | +| learning_rate | 0.0001 | +| loss | -0.0684 | +| n_updates | 141090 | +| policy_gradient_loss | -0.057 | +| value_loss | 0.000599 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.14e+03 | +| ep_rew_mean | 0.164 | +| time/ | | +| fps | 309 | +| iterations | 8058 | +| time_elapsed | 26657 | +| total_timesteps | 8251392 | +| train/ | | +| approx_kl | 3.4225993 | +| clip_fraction | 0.405 | +| clip_range | 0.2 | +| entropy_loss | -0.233 | +| explained_variance | -1.37 | +| learning_rate | 0.0001 | +| loss | -0.092 | +| n_updates | 141100 | +| policy_gradient_loss | -0.0587 | +| value_loss | 0.000628 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.14e+03 | +| ep_rew_mean | 0.17 | +| time/ | | +| fps | 309 | +| iterations | 8059 | +| time_elapsed | 26660 | +| total_timesteps | 8252416 | +| train/ | | +| approx_kl | 2.2402568 | +| clip_fraction | 0.428 | +| clip_range | 0.2 | +| entropy_loss | -0.279 | +| explained_variance | -2 | +| learning_rate | 0.0001 | +| loss | -0.0841 | +| n_updates | 141110 | +| policy_gradient_loss | -0.0615 | +| value_loss | 0.00062 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.14e+03 | +| ep_rew_mean | 0.169 | +| time/ | | +| fps | 309 | +| iterations | 8060 | +| time_elapsed | 26663 | +| total_timesteps | 8253440 | +| train/ | | +| approx_kl | 3.7112684 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.303 | +| explained_variance | -1.53 | +| learning_rate | 0.0001 | +| loss | -0.0879 | +| n_updates | 141120 | +| policy_gradient_loss | -0.0639 | +| value_loss | 0.000635 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.14e+03 | +| ep_rew_mean | 0.17 | +| time/ | | +| fps | 309 | +| iterations | 8061 | +| time_elapsed | 26666 | +| total_timesteps | 8254464 | +| train/ | | +| approx_kl | 2.5266242 | +| clip_fraction | 0.432 | +| clip_range | 0.2 | +| entropy_loss | -0.256 | +| explained_variance | -1.82 | +| learning_rate | 0.0001 | +| loss | -0.0775 | +| n_updates | 141130 | +| policy_gradient_loss | -0.0613 | +| value_loss | 0.000693 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.14e+03 | +| ep_rew_mean | 0.17 | +| time/ | | +| fps | 309 | +| iterations | 8062 | +| time_elapsed | 26670 | +| total_timesteps | 8255488 | +| train/ | | +| approx_kl | 2.6324646 | +| clip_fraction | 0.479 | +| clip_range | 0.2 | +| entropy_loss | -0.291 | +| explained_variance | -2.37 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 141140 | +| policy_gradient_loss | -0.0531 | +| value_loss | 0.000877 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.169 | +| time/ | | +| fps | 309 | +| iterations | 8063 | +| time_elapsed | 26673 | +| total_timesteps | 8256512 | +| train/ | | +| approx_kl | 2.7145376 | +| clip_fraction | 0.466 | +| clip_range | 0.2 | +| entropy_loss | -0.311 | +| explained_variance | -1.67 | +| learning_rate | 0.0001 | +| loss | -0.071 | +| n_updates | 141150 | +| policy_gradient_loss | -0.0684 | +| value_loss | 0.000699 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.175 | +| time/ | | +| fps | 309 | +| iterations | 8064 | +| time_elapsed | 26676 | +| total_timesteps | 8257536 | +| train/ | | +| approx_kl | 2.5005953 | +| clip_fraction | 0.445 | +| clip_range | 0.2 | +| entropy_loss | -0.272 | +| explained_variance | -1.76 | +| learning_rate | 0.0001 | +| loss | -0.0712 | +| n_updates | 141160 | +| policy_gradient_loss | -0.0574 | +| value_loss | 0.000751 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.18 | +| time/ | | +| fps | 309 | +| iterations | 8065 | +| time_elapsed | 26679 | +| total_timesteps | 8258560 | +| train/ | | +| approx_kl | 3.4704359 | +| clip_fraction | 0.469 | +| clip_range | 0.2 | +| entropy_loss | -0.309 | +| explained_variance | -0.945 | +| learning_rate | 0.0001 | +| loss | -0.0674 | +| n_updates | 141170 | +| policy_gradient_loss | -0.0682 | +| value_loss | 0.000901 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.18 | +| time/ | | +| fps | 309 | +| iterations | 8066 | +| time_elapsed | 26683 | +| total_timesteps | 8259584 | +| train/ | | +| approx_kl | 3.158732 | +| clip_fraction | 0.464 | +| clip_range | 0.2 | +| entropy_loss | -0.298 | +| explained_variance | -1.26 | +| learning_rate | 0.0001 | +| loss | -0.0677 | +| n_updates | 141180 | +| policy_gradient_loss | -0.0629 | +| value_loss | 0.000963 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.18 | +| time/ | | +| fps | 309 | +| iterations | 8067 | +| time_elapsed | 26686 | +| total_timesteps | 8260608 | +| train/ | | +| approx_kl | 2.8669891 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.318 | +| explained_variance | -2.47 | +| learning_rate | 0.0001 | +| loss | -0.0834 | +| n_updates | 141190 | +| policy_gradient_loss | -0.0688 | +| value_loss | 0.000537 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.18 | +| time/ | | +| fps | 309 | +| iterations | 8068 | +| time_elapsed | 26689 | +| total_timesteps | 8261632 | +| train/ | | +| approx_kl | 2.9944718 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.291 | +| explained_variance | -1.1 | +| learning_rate | 0.0001 | +| loss | -0.0863 | +| n_updates | 141200 | +| policy_gradient_loss | -0.0656 | +| value_loss | 0.00065 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.179 | +| time/ | | +| fps | 309 | +| iterations | 8069 | +| time_elapsed | 26693 | +| total_timesteps | 8262656 | +| train/ | | +| approx_kl | 2.2049468 | +| clip_fraction | 0.435 | +| clip_range | 0.2 | +| entropy_loss | -0.314 | +| explained_variance | -1.14 | +| learning_rate | 0.0001 | +| loss | -0.0858 | +| n_updates | 141210 | +| policy_gradient_loss | -0.0653 | +| value_loss | 0.000706 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.187 | +| time/ | | +| fps | 309 | +| iterations | 8070 | +| time_elapsed | 26696 | +| total_timesteps | 8263680 | +| train/ | | +| approx_kl | 2.6600914 | +| clip_fraction | 0.401 | +| clip_range | 0.2 | +| entropy_loss | -0.264 | +| explained_variance | -0.695 | +| learning_rate | 0.0001 | +| loss | -0.0581 | +| n_updates | 141220 | +| policy_gradient_loss | -0.059 | +| value_loss | 0.000699 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.189 | +| time/ | | +| fps | 309 | +| iterations | 8071 | +| time_elapsed | 26699 | +| total_timesteps | 8264704 | +| train/ | | +| approx_kl | 5.2487 | +| clip_fraction | 0.494 | +| clip_range | 0.2 | +| entropy_loss | -0.292 | +| explained_variance | -0.754 | +| learning_rate | 0.0001 | +| loss | -0.0728 | +| n_updates | 141230 | +| policy_gradient_loss | -0.0715 | +| value_loss | 0.000827 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.192 | +| time/ | | +| fps | 309 | +| iterations | 8072 | +| time_elapsed | 26703 | +| total_timesteps | 8265728 | +| train/ | | +| approx_kl | 2.9296472 | +| clip_fraction | 0.466 | +| clip_range | 0.2 | +| entropy_loss | -0.279 | +| explained_variance | -1.94 | +| learning_rate | 0.0001 | +| loss | -0.0762 | +| n_updates | 141240 | +| policy_gradient_loss | -0.0663 | +| value_loss | 0.000742 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.14e+03 | +| ep_rew_mean | 0.19 | +| time/ | | +| fps | 309 | +| iterations | 8073 | +| time_elapsed | 26706 | +| total_timesteps | 8266752 | +| train/ | | +| approx_kl | 2.4363868 | +| clip_fraction | 0.442 | +| clip_range | 0.2 | +| entropy_loss | -0.272 | +| explained_variance | -2.17 | +| learning_rate | 0.0001 | +| loss | -0.0548 | +| n_updates | 141250 | +| policy_gradient_loss | -0.0653 | +| value_loss | 0.000677 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.14e+03 | +| ep_rew_mean | 0.194 | +| time/ | | +| fps | 309 | +| iterations | 8074 | +| time_elapsed | 26710 | +| total_timesteps | 8267776 | +| train/ | | +| approx_kl | 2.1455555 | +| clip_fraction | 0.425 | +| clip_range | 0.2 | +| entropy_loss | -0.266 | +| explained_variance | -1.27 | +| learning_rate | 0.0001 | +| loss | -0.0856 | +| n_updates | 141260 | +| policy_gradient_loss | -0.0613 | +| value_loss | 0.000694 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.14e+03 | +| ep_rew_mean | 0.193 | +| time/ | | +| fps | 309 | +| iterations | 8075 | +| time_elapsed | 26713 | +| total_timesteps | 8268800 | +| train/ | | +| approx_kl | 3.9315875 | +| clip_fraction | 0.458 | +| clip_range | 0.2 | +| entropy_loss | -0.31 | +| explained_variance | -0.709 | +| learning_rate | 0.0001 | +| loss | -0.0758 | +| n_updates | 141270 | +| policy_gradient_loss | -0.054 | +| value_loss | 0.000888 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.14e+03 | +| ep_rew_mean | 0.193 | +| time/ | | +| fps | 309 | +| iterations | 8076 | +| time_elapsed | 26716 | +| total_timesteps | 8269824 | +| train/ | | +| approx_kl | 2.1423013 | +| clip_fraction | 0.43 | +| clip_range | 0.2 | +| entropy_loss | -0.284 | +| explained_variance | -1.09 | +| learning_rate | 0.0001 | +| loss | -0.0937 | +| n_updates | 141280 | +| policy_gradient_loss | -0.0585 | +| value_loss | 0.0005 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.14e+03 | +| ep_rew_mean | 0.193 | +| time/ | | +| fps | 309 | +| iterations | 8077 | +| time_elapsed | 26719 | +| total_timesteps | 8270848 | +| train/ | | +| approx_kl | 2.9138932 | +| clip_fraction | 0.456 | +| clip_range | 0.2 | +| entropy_loss | -0.276 | +| explained_variance | -1.27 | +| learning_rate | 0.0001 | +| loss | -0.0902 | +| n_updates | 141290 | +| policy_gradient_loss | -0.0666 | +| value_loss | 0.000604 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.192 | +| time/ | | +| fps | 309 | +| iterations | 8078 | +| time_elapsed | 26722 | +| total_timesteps | 8271872 | +| train/ | | +| approx_kl | 3.9393468 | +| clip_fraction | 0.444 | +| clip_range | 0.2 | +| entropy_loss | -0.285 | +| explained_variance | -0.982 | +| learning_rate | 0.0001 | +| loss | -0.0924 | +| n_updates | 141300 | +| policy_gradient_loss | -0.0646 | +| value_loss | 0.000783 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.199 | +| time/ | | +| fps | 309 | +| iterations | 8079 | +| time_elapsed | 26725 | +| total_timesteps | 8272896 | +| train/ | | +| approx_kl | 2.6447592 | +| clip_fraction | 0.442 | +| clip_range | 0.2 | +| entropy_loss | -0.309 | +| explained_variance | -2.77 | +| learning_rate | 0.0001 | +| loss | -0.0878 | +| n_updates | 141310 | +| policy_gradient_loss | -0.0633 | +| value_loss | 0.000913 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.14e+03 | +| ep_rew_mean | 0.202 | +| time/ | | +| fps | 309 | +| iterations | 8080 | +| time_elapsed | 26729 | +| total_timesteps | 8273920 | +| train/ | | +| approx_kl | 4.059358 | +| clip_fraction | 0.506 | +| clip_range | 0.2 | +| entropy_loss | -0.316 | +| explained_variance | -0.488 | +| learning_rate | 0.0001 | +| loss | -0.0952 | +| n_updates | 141320 | +| policy_gradient_loss | -0.0656 | +| value_loss | 0.000753 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.207 | +| time/ | | +| fps | 309 | +| iterations | 8081 | +| time_elapsed | 26732 | +| total_timesteps | 8274944 | +| train/ | | +| approx_kl | 3.1348596 | +| clip_fraction | 0.435 | +| clip_range | 0.2 | +| entropy_loss | -0.293 | +| explained_variance | -1.42 | +| learning_rate | 0.0001 | +| loss | -0.0665 | +| n_updates | 141330 | +| policy_gradient_loss | -0.0608 | +| value_loss | 0.000972 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.207 | +| time/ | | +| fps | 309 | +| iterations | 8082 | +| time_elapsed | 26735 | +| total_timesteps | 8275968 | +| train/ | | +| approx_kl | 2.9349165 | +| clip_fraction | 0.444 | +| clip_range | 0.2 | +| entropy_loss | -0.303 | +| explained_variance | -1.66 | +| learning_rate | 0.0001 | +| loss | -0.0965 | +| n_updates | 141340 | +| policy_gradient_loss | -0.0544 | +| value_loss | 0.000809 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.205 | +| time/ | | +| fps | 309 | +| iterations | 8083 | +| time_elapsed | 26738 | +| total_timesteps | 8276992 | +| train/ | | +| approx_kl | 3.532226 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.306 | +| explained_variance | -4.36 | +| learning_rate | 0.0001 | +| loss | -0.0762 | +| n_updates | 141350 | +| policy_gradient_loss | -0.0674 | +| value_loss | 0.000503 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.209 | +| time/ | | +| fps | 309 | +| iterations | 8084 | +| time_elapsed | 26742 | +| total_timesteps | 8278016 | +| train/ | | +| approx_kl | 2.9254494 | +| clip_fraction | 0.466 | +| clip_range | 0.2 | +| entropy_loss | -0.33 | +| explained_variance | -0.875 | +| learning_rate | 0.0001 | +| loss | -0.0781 | +| n_updates | 141360 | +| policy_gradient_loss | -0.065 | +| value_loss | 0.000676 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.213 | +| time/ | | +| fps | 309 | +| iterations | 8085 | +| time_elapsed | 26745 | +| total_timesteps | 8279040 | +| train/ | | +| approx_kl | 2.212773 | +| clip_fraction | 0.426 | +| clip_range | 0.2 | +| entropy_loss | -0.273 | +| explained_variance | -0.872 | +| learning_rate | 0.0001 | +| loss | -0.0708 | +| n_updates | 141370 | +| policy_gradient_loss | -0.0532 | +| value_loss | 0.000841 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.14e+03 | +| ep_rew_mean | 0.214 | +| time/ | | +| fps | 309 | +| iterations | 8086 | +| time_elapsed | 26749 | +| total_timesteps | 8280064 | +| train/ | | +| approx_kl | 2.6017535 | +| clip_fraction | 0.445 | +| clip_range | 0.2 | +| entropy_loss | -0.318 | +| explained_variance | -0.786 | +| learning_rate | 0.0001 | +| loss | -0.0877 | +| n_updates | 141380 | +| policy_gradient_loss | -0.0622 | +| value_loss | 0.000965 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.22 | +| time/ | | +| fps | 309 | +| iterations | 8087 | +| time_elapsed | 26752 | +| total_timesteps | 8281088 | +| train/ | | +| approx_kl | 3.3448648 | +| clip_fraction | 0.459 | +| clip_range | 0.2 | +| entropy_loss | -0.293 | +| explained_variance | -1.12 | +| learning_rate | 0.0001 | +| loss | -0.0947 | +| n_updates | 141390 | +| policy_gradient_loss | -0.0691 | +| value_loss | 0.000969 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.22 | +| time/ | | +| fps | 309 | +| iterations | 8088 | +| time_elapsed | 26756 | +| total_timesteps | 8282112 | +| train/ | | +| approx_kl | 2.4999528 | +| clip_fraction | 0.437 | +| clip_range | 0.2 | +| entropy_loss | -0.287 | +| explained_variance | -1.14 | +| learning_rate | 0.0001 | +| loss | -0.0763 | +| n_updates | 141400 | +| policy_gradient_loss | -0.0653 | +| value_loss | 0.000844 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.226 | +| time/ | | +| fps | 309 | +| iterations | 8089 | +| time_elapsed | 26759 | +| total_timesteps | 8283136 | +| train/ | | +| approx_kl | 2.7247198 | +| clip_fraction | 0.482 | +| clip_range | 0.2 | +| entropy_loss | -0.292 | +| explained_variance | -1.73 | +| learning_rate | 0.0001 | +| loss | -0.0757 | +| n_updates | 141410 | +| policy_gradient_loss | -0.0689 | +| value_loss | 0.00079 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.229 | +| time/ | | +| fps | 309 | +| iterations | 8090 | +| time_elapsed | 26763 | +| total_timesteps | 8284160 | +| train/ | | +| approx_kl | 2.0783458 | +| clip_fraction | 0.461 | +| clip_range | 0.2 | +| entropy_loss | -0.327 | +| explained_variance | -2.13 | +| learning_rate | 0.0001 | +| loss | -0.0829 | +| n_updates | 141420 | +| policy_gradient_loss | -0.0656 | +| value_loss | 0.000437 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.228 | +| time/ | | +| fps | 309 | +| iterations | 8091 | +| time_elapsed | 26766 | +| total_timesteps | 8285184 | +| train/ | | +| approx_kl | 2.8294125 | +| clip_fraction | 0.444 | +| clip_range | 0.2 | +| entropy_loss | -0.298 | +| explained_variance | -1.43 | +| learning_rate | 0.0001 | +| loss | -0.0747 | +| n_updates | 141430 | +| policy_gradient_loss | -0.0629 | +| value_loss | 0.000585 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.227 | +| time/ | | +| fps | 309 | +| iterations | 8092 | +| time_elapsed | 26770 | +| total_timesteps | 8286208 | +| train/ | | +| approx_kl | 2.4386683 | +| clip_fraction | 0.457 | +| clip_range | 0.2 | +| entropy_loss | -0.311 | +| explained_variance | -0.917 | +| learning_rate | 0.0001 | +| loss | -0.0873 | +| n_updates | 141440 | +| policy_gradient_loss | -0.0621 | +| value_loss | 0.000723 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.227 | +| time/ | | +| fps | 309 | +| iterations | 8093 | +| time_elapsed | 26773 | +| total_timesteps | 8287232 | +| train/ | | +| approx_kl | 3.2108874 | +| clip_fraction | 0.418 | +| clip_range | 0.2 | +| entropy_loss | -0.294 | +| explained_variance | -1.33 | +| learning_rate | 0.0001 | +| loss | -0.0863 | +| n_updates | 141450 | +| policy_gradient_loss | -0.0598 | +| value_loss | 0.000817 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.227 | +| time/ | | +| fps | 309 | +| iterations | 8094 | +| time_elapsed | 26776 | +| total_timesteps | 8288256 | +| train/ | | +| approx_kl | 3.058449 | +| clip_fraction | 0.411 | +| clip_range | 0.2 | +| entropy_loss | -0.262 | +| explained_variance | -1.55 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 141460 | +| policy_gradient_loss | -0.0616 | +| value_loss | 0.000436 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.222 | +| time/ | | +| fps | 309 | +| iterations | 8095 | +| time_elapsed | 26779 | +| total_timesteps | 8289280 | +| train/ | | +| approx_kl | 2.5622363 | +| clip_fraction | 0.468 | +| clip_range | 0.2 | +| entropy_loss | -0.307 | +| explained_variance | -2.36 | +| learning_rate | 0.0001 | +| loss | -0.0823 | +| n_updates | 141470 | +| policy_gradient_loss | -0.0611 | +| value_loss | 0.000453 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.229 | +| time/ | | +| fps | 309 | +| iterations | 8096 | +| time_elapsed | 26782 | +| total_timesteps | 8290304 | +| train/ | | +| approx_kl | 2.6471438 | +| clip_fraction | 0.441 | +| clip_range | 0.2 | +| entropy_loss | -0.288 | +| explained_variance | -1.53 | +| learning_rate | 0.0001 | +| loss | -0.0648 | +| n_updates | 141480 | +| policy_gradient_loss | -0.0641 | +| value_loss | 0.000577 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.23 | +| time/ | | +| fps | 309 | +| iterations | 8097 | +| time_elapsed | 26786 | +| total_timesteps | 8291328 | +| train/ | | +| approx_kl | 3.0375013 | +| clip_fraction | 0.461 | +| clip_range | 0.2 | +| entropy_loss | -0.304 | +| explained_variance | -0.518 | +| learning_rate | 0.0001 | +| loss | -0.0874 | +| n_updates | 141490 | +| policy_gradient_loss | -0.0644 | +| value_loss | 0.000907 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.23 | +| time/ | | +| fps | 309 | +| iterations | 8098 | +| time_elapsed | 26789 | +| total_timesteps | 8292352 | +| train/ | | +| approx_kl | 2.1711178 | +| clip_fraction | 0.466 | +| clip_range | 0.2 | +| entropy_loss | -0.317 | +| explained_variance | -1.6 | +| learning_rate | 0.0001 | +| loss | -0.0949 | +| n_updates | 141500 | +| policy_gradient_loss | -0.0668 | +| value_loss | 0.000613 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.226 | +| time/ | | +| fps | 309 | +| iterations | 8099 | +| time_elapsed | 26792 | +| total_timesteps | 8293376 | +| train/ | | +| approx_kl | 5.87939 | +| clip_fraction | 0.455 | +| clip_range | 0.2 | +| entropy_loss | -0.293 | +| explained_variance | -2.71 | +| learning_rate | 0.0001 | +| loss | -0.0957 | +| n_updates | 141510 | +| policy_gradient_loss | -0.0577 | +| value_loss | 0.000686 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.231 | +| time/ | | +| fps | 309 | +| iterations | 8100 | +| time_elapsed | 26795 | +| total_timesteps | 8294400 | +| train/ | | +| approx_kl | 2.4550362 | +| clip_fraction | 0.448 | +| clip_range | 0.2 | +| entropy_loss | -0.322 | +| explained_variance | -1.19 | +| learning_rate | 0.0001 | +| loss | -0.0714 | +| n_updates | 141520 | +| policy_gradient_loss | -0.0667 | +| value_loss | 0.000749 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.231 | +| time/ | | +| fps | 309 | +| iterations | 8101 | +| time_elapsed | 26798 | +| total_timesteps | 8295424 | +| train/ | | +| approx_kl | 2.0979104 | +| clip_fraction | 0.43 | +| clip_range | 0.2 | +| entropy_loss | -0.287 | +| explained_variance | -1.77 | +| learning_rate | 0.0001 | +| loss | -0.0728 | +| n_updates | 141530 | +| policy_gradient_loss | -0.0583 | +| value_loss | 0.000581 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.227 | +| time/ | | +| fps | 309 | +| iterations | 8102 | +| time_elapsed | 26802 | +| total_timesteps | 8296448 | +| train/ | | +| approx_kl | 1.7913266 | +| clip_fraction | 0.446 | +| clip_range | 0.2 | +| entropy_loss | -0.33 | +| explained_variance | -1.22 | +| learning_rate | 0.0001 | +| loss | -0.0825 | +| n_updates | 141540 | +| policy_gradient_loss | -0.0621 | +| value_loss | 0.000483 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.234 | +| time/ | | +| fps | 309 | +| iterations | 8103 | +| time_elapsed | 26805 | +| total_timesteps | 8297472 | +| train/ | | +| approx_kl | 1.9413228 | +| clip_fraction | 0.43 | +| clip_range | 0.2 | +| entropy_loss | -0.317 | +| explained_variance | -1.28 | +| learning_rate | 0.0001 | +| loss | -0.0668 | +| n_updates | 141550 | +| policy_gradient_loss | -0.0604 | +| value_loss | 0.000807 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.232 | +| time/ | | +| fps | 309 | +| iterations | 8104 | +| time_elapsed | 26808 | +| total_timesteps | 8298496 | +| train/ | | +| approx_kl | 2.2519782 | +| clip_fraction | 0.428 | +| clip_range | 0.2 | +| entropy_loss | -0.301 | +| explained_variance | -1.21 | +| learning_rate | 0.0001 | +| loss | -0.0967 | +| n_updates | 141560 | +| policy_gradient_loss | -0.0539 | +| value_loss | 0.000785 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.234 | +| time/ | | +| fps | 309 | +| iterations | 8105 | +| time_elapsed | 26812 | +| total_timesteps | 8299520 | +| train/ | | +| approx_kl | 2.642745 | +| clip_fraction | 0.428 | +| clip_range | 0.2 | +| entropy_loss | -0.305 | +| explained_variance | -0.961 | +| learning_rate | 0.0001 | +| loss | -0.0741 | +| n_updates | 141570 | +| policy_gradient_loss | -0.0602 | +| value_loss | 0.000725 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.234 | +| time/ | | +| fps | 309 | +| iterations | 8106 | +| time_elapsed | 26815 | +| total_timesteps | 8300544 | +| train/ | | +| approx_kl | 1.8679243 | +| clip_fraction | 0.421 | +| clip_range | 0.2 | +| entropy_loss | -0.294 | +| explained_variance | -1.55 | +| learning_rate | 0.0001 | +| loss | -0.0878 | +| n_updates | 141580 | +| policy_gradient_loss | -0.0616 | +| value_loss | 0.000522 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.241 | +| time/ | | +| fps | 309 | +| iterations | 8107 | +| time_elapsed | 26819 | +| total_timesteps | 8301568 | +| train/ | | +| approx_kl | 2.0297484 | +| clip_fraction | 0.451 | +| clip_range | 0.2 | +| entropy_loss | -0.313 | +| explained_variance | -0.642 | +| learning_rate | 0.0001 | +| loss | -0.0577 | +| n_updates | 141590 | +| policy_gradient_loss | -0.0588 | +| value_loss | 0.000708 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.241 | +| time/ | | +| fps | 309 | +| iterations | 8108 | +| time_elapsed | 26822 | +| total_timesteps | 8302592 | +| train/ | | +| approx_kl | 2.7949028 | +| clip_fraction | 0.419 | +| clip_range | 0.2 | +| entropy_loss | -0.278 | +| explained_variance | -0.773 | +| learning_rate | 0.0001 | +| loss | -0.0921 | +| n_updates | 141600 | +| policy_gradient_loss | -0.0627 | +| value_loss | 0.000789 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.242 | +| time/ | | +| fps | 309 | +| iterations | 8109 | +| time_elapsed | 26825 | +| total_timesteps | 8303616 | +| train/ | | +| approx_kl | 1.9815481 | +| clip_fraction | 0.399 | +| clip_range | 0.2 | +| entropy_loss | -0.272 | +| explained_variance | -1.64 | +| learning_rate | 0.0001 | +| loss | -0.0379 | +| n_updates | 141610 | +| policy_gradient_loss | -0.0383 | +| value_loss | 0.000697 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.242 | +| time/ | | +| fps | 309 | +| iterations | 8110 | +| time_elapsed | 26829 | +| total_timesteps | 8304640 | +| train/ | | +| approx_kl | 2.683751 | +| clip_fraction | 0.437 | +| clip_range | 0.2 | +| entropy_loss | -0.279 | +| explained_variance | -1.78 | +| learning_rate | 0.0001 | +| loss | -0.0876 | +| n_updates | 141620 | +| policy_gradient_loss | -0.0656 | +| value_loss | 0.000636 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.242 | +| time/ | | +| fps | 309 | +| iterations | 8111 | +| time_elapsed | 26832 | +| total_timesteps | 8305664 | +| train/ | | +| approx_kl | 1.9133302 | +| clip_fraction | 0.446 | +| clip_range | 0.2 | +| entropy_loss | -0.33 | +| explained_variance | -0.905 | +| learning_rate | 0.0001 | +| loss | -0.0784 | +| n_updates | 141630 | +| policy_gradient_loss | -0.0559 | +| value_loss | 0.000637 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.244 | +| time/ | | +| fps | 309 | +| iterations | 8112 | +| time_elapsed | 26835 | +| total_timesteps | 8306688 | +| train/ | | +| approx_kl | 2.6477704 | +| clip_fraction | 0.462 | +| clip_range | 0.2 | +| entropy_loss | -0.31 | +| explained_variance | -2.66 | +| learning_rate | 0.0001 | +| loss | -0.0483 | +| n_updates | 141640 | +| policy_gradient_loss | -0.0589 | +| value_loss | 0.000712 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.246 | +| time/ | | +| fps | 309 | +| iterations | 8113 | +| time_elapsed | 26838 | +| total_timesteps | 8307712 | +| train/ | | +| approx_kl | 3.1132894 | +| clip_fraction | 0.424 | +| clip_range | 0.2 | +| entropy_loss | -0.289 | +| explained_variance | -0.386 | +| learning_rate | 0.0001 | +| loss | -0.0823 | +| n_updates | 141650 | +| policy_gradient_loss | -0.0575 | +| value_loss | 0.000753 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.246 | +| time/ | | +| fps | 309 | +| iterations | 8114 | +| time_elapsed | 26841 | +| total_timesteps | 8308736 | +| train/ | | +| approx_kl | 2.5652442 | +| clip_fraction | 0.449 | +| clip_range | 0.2 | +| entropy_loss | -0.295 | +| explained_variance | -0.596 | +| learning_rate | 0.0001 | +| loss | 0.00107 | +| n_updates | 141660 | +| policy_gradient_loss | -0.0601 | +| value_loss | 0.00082 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.246 | +| time/ | | +| fps | 309 | +| iterations | 8115 | +| time_elapsed | 26845 | +| total_timesteps | 8309760 | +| train/ | | +| approx_kl | 1.714529 | +| clip_fraction | 0.404 | +| clip_range | 0.2 | +| entropy_loss | -0.287 | +| explained_variance | -1.78 | +| learning_rate | 0.0001 | +| loss | -0.087 | +| n_updates | 141670 | +| policy_gradient_loss | -0.0582 | +| value_loss | 0.000565 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.14e+03 | +| ep_rew_mean | 0.246 | +| time/ | | +| fps | 309 | +| iterations | 8116 | +| time_elapsed | 26848 | +| total_timesteps | 8310784 | +| train/ | | +| approx_kl | 3.1677043 | +| clip_fraction | 0.508 | +| clip_range | 0.2 | +| entropy_loss | -0.307 | +| explained_variance | -0.762 | +| learning_rate | 0.0001 | +| loss | -0.0742 | +| n_updates | 141680 | +| policy_gradient_loss | -0.065 | +| value_loss | 0.00104 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.14e+03 | +| ep_rew_mean | 0.246 | +| time/ | | +| fps | 309 | +| iterations | 8117 | +| time_elapsed | 26851 | +| total_timesteps | 8311808 | +| train/ | | +| approx_kl | 2.6212666 | +| clip_fraction | 0.46 | +| clip_range | 0.2 | +| entropy_loss | -0.293 | +| explained_variance | -4.41 | +| learning_rate | 0.0001 | +| loss | -0.0912 | +| n_updates | 141690 | +| policy_gradient_loss | -0.076 | +| value_loss | 0.000796 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.247 | +| time/ | | +| fps | 309 | +| iterations | 8118 | +| time_elapsed | 26854 | +| total_timesteps | 8312832 | +| train/ | | +| approx_kl | 1.973043 | +| clip_fraction | 0.477 | +| clip_range | 0.2 | +| entropy_loss | -0.326 | +| explained_variance | -1.98 | +| learning_rate | 0.0001 | +| loss | -0.0873 | +| n_updates | 141700 | +| policy_gradient_loss | -0.0686 | +| value_loss | 0.000516 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.14e+03 | +| ep_rew_mean | 0.245 | +| time/ | | +| fps | 309 | +| iterations | 8119 | +| time_elapsed | 26857 | +| total_timesteps | 8313856 | +| train/ | | +| approx_kl | 2.5247314 | +| clip_fraction | 0.453 | +| clip_range | 0.2 | +| entropy_loss | -0.292 | +| explained_variance | -1.83 | +| learning_rate | 0.0001 | +| loss | -0.11 | +| n_updates | 141710 | +| policy_gradient_loss | -0.0668 | +| value_loss | 0.000567 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.14e+03 | +| ep_rew_mean | 0.246 | +| time/ | | +| fps | 309 | +| iterations | 8120 | +| time_elapsed | 26860 | +| total_timesteps | 8314880 | +| train/ | | +| approx_kl | 2.907683 | +| clip_fraction | 0.459 | +| clip_range | 0.2 | +| entropy_loss | -0.272 | +| explained_variance | -1.31 | +| learning_rate | 0.0001 | +| loss | -0.0907 | +| n_updates | 141720 | +| policy_gradient_loss | -0.0645 | +| value_loss | 0.000839 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.251 | +| time/ | | +| fps | 309 | +| iterations | 8121 | +| time_elapsed | 26864 | +| total_timesteps | 8315904 | +| train/ | | +| approx_kl | 3.038364 | +| clip_fraction | 0.472 | +| clip_range | 0.2 | +| entropy_loss | -0.287 | +| explained_variance | -4.54 | +| learning_rate | 0.0001 | +| loss | -0.0712 | +| n_updates | 141730 | +| policy_gradient_loss | -0.0703 | +| value_loss | 0.00082 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.252 | +| time/ | | +| fps | 309 | +| iterations | 8122 | +| time_elapsed | 26867 | +| total_timesteps | 8316928 | +| train/ | | +| approx_kl | 2.0030222 | +| clip_fraction | 0.46 | +| clip_range | 0.2 | +| entropy_loss | -0.326 | +| explained_variance | -0.755 | +| learning_rate | 0.0001 | +| loss | -0.0795 | +| n_updates | 141740 | +| policy_gradient_loss | -0.0536 | +| value_loss | 0.000737 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.252 | +| time/ | | +| fps | 309 | +| iterations | 8123 | +| time_elapsed | 26871 | +| total_timesteps | 8317952 | +| train/ | | +| approx_kl | 4.761693 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.31 | +| explained_variance | -3.01 | +| learning_rate | 0.0001 | +| loss | -0.0928 | +| n_updates | 141750 | +| policy_gradient_loss | -0.0632 | +| value_loss | 0.000578 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.252 | +| time/ | | +| fps | 309 | +| iterations | 8124 | +| time_elapsed | 26874 | +| total_timesteps | 8318976 | +| train/ | | +| approx_kl | 2.5320873 | +| clip_fraction | 0.465 | +| clip_range | 0.2 | +| entropy_loss | -0.333 | +| explained_variance | -0.911 | +| learning_rate | 0.0001 | +| loss | -0.0855 | +| n_updates | 141760 | +| policy_gradient_loss | -0.068 | +| value_loss | 0.000683 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.249 | +| time/ | | +| fps | 309 | +| iterations | 8125 | +| time_elapsed | 26878 | +| total_timesteps | 8320000 | +| train/ | | +| approx_kl | 2.0564222 | +| clip_fraction | 0.454 | +| clip_range | 0.2 | +| entropy_loss | -0.304 | +| explained_variance | -1.89 | +| learning_rate | 0.0001 | +| loss | -0.0999 | +| n_updates | 141770 | +| policy_gradient_loss | -0.0666 | +| value_loss | 0.000473 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.249 | +| time/ | | +| fps | 309 | +| iterations | 8126 | +| time_elapsed | 26881 | +| total_timesteps | 8321024 | +| train/ | | +| approx_kl | 10.403627 | +| clip_fraction | 0.435 | +| clip_range | 0.2 | +| entropy_loss | -0.271 | +| explained_variance | -1.62 | +| learning_rate | 0.0001 | +| loss | -0.0838 | +| n_updates | 141780 | +| policy_gradient_loss | -0.0619 | +| value_loss | 0.000532 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.249 | +| time/ | | +| fps | 309 | +| iterations | 8127 | +| time_elapsed | 26885 | +| total_timesteps | 8322048 | +| train/ | | +| approx_kl | 3.6962152 | +| clip_fraction | 0.43 | +| clip_range | 0.2 | +| entropy_loss | -0.274 | +| explained_variance | -1.15 | +| learning_rate | 0.0001 | +| loss | -0.0683 | +| n_updates | 141790 | +| policy_gradient_loss | -0.0606 | +| value_loss | 0.000572 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.244 | +| time/ | | +| fps | 309 | +| iterations | 8128 | +| time_elapsed | 26888 | +| total_timesteps | 8323072 | +| train/ | | +| approx_kl | 2.746008 | +| clip_fraction | 0.484 | +| clip_range | 0.2 | +| entropy_loss | -0.293 | +| explained_variance | -2.5 | +| learning_rate | 0.0001 | +| loss | -0.0839 | +| n_updates | 141800 | +| policy_gradient_loss | -0.0724 | +| value_loss | 0.00093 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.244 | +| time/ | | +| fps | 309 | +| iterations | 8129 | +| time_elapsed | 26891 | +| total_timesteps | 8324096 | +| train/ | | +| approx_kl | 2.962259 | +| clip_fraction | 0.442 | +| clip_range | 0.2 | +| entropy_loss | -0.29 | +| explained_variance | -3.19 | +| learning_rate | 0.0001 | +| loss | -0.0879 | +| n_updates | 141810 | +| policy_gradient_loss | -0.0611 | +| value_loss | 0.000692 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.245 | +| time/ | | +| fps | 309 | +| iterations | 8130 | +| time_elapsed | 26895 | +| total_timesteps | 8325120 | +| train/ | | +| approx_kl | 2.6095872 | +| clip_fraction | 0.491 | +| clip_range | 0.2 | +| entropy_loss | -0.313 | +| explained_variance | -5.64 | +| learning_rate | 0.0001 | +| loss | -0.0599 | +| n_updates | 141820 | +| policy_gradient_loss | -0.0666 | +| value_loss | 0.000755 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.246 | +| time/ | | +| fps | 309 | +| iterations | 8131 | +| time_elapsed | 26898 | +| total_timesteps | 8326144 | +| train/ | | +| approx_kl | 2.7506087 | +| clip_fraction | 0.496 | +| clip_range | 0.2 | +| entropy_loss | -0.345 | +| explained_variance | -1.36 | +| learning_rate | 0.0001 | +| loss | -0.0899 | +| n_updates | 141830 | +| policy_gradient_loss | -0.0714 | +| value_loss | 0.000444 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.245 | +| time/ | | +| fps | 309 | +| iterations | 8132 | +| time_elapsed | 26901 | +| total_timesteps | 8327168 | +| train/ | | +| approx_kl | 2.5761452 | +| clip_fraction | 0.451 | +| clip_range | 0.2 | +| entropy_loss | -0.313 | +| explained_variance | -1.66 | +| learning_rate | 0.0001 | +| loss | -0.0983 | +| n_updates | 141840 | +| policy_gradient_loss | -0.0685 | +| value_loss | 0.000521 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.246 | +| time/ | | +| fps | 309 | +| iterations | 8133 | +| time_elapsed | 26904 | +| total_timesteps | 8328192 | +| train/ | | +| approx_kl | 2.2958658 | +| clip_fraction | 0.423 | +| clip_range | 0.2 | +| entropy_loss | -0.297 | +| explained_variance | -1.88 | +| learning_rate | 0.0001 | +| loss | -0.093 | +| n_updates | 141850 | +| policy_gradient_loss | -0.0624 | +| value_loss | 0.000613 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.25 | +| time/ | | +| fps | 309 | +| iterations | 8134 | +| time_elapsed | 26907 | +| total_timesteps | 8329216 | +| train/ | | +| approx_kl | 1.908879 | +| clip_fraction | 0.412 | +| clip_range | 0.2 | +| entropy_loss | -0.294 | +| explained_variance | -2.54 | +| learning_rate | 0.0001 | +| loss | -0.088 | +| n_updates | 141860 | +| policy_gradient_loss | -0.0643 | +| value_loss | 0.000478 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.256 | +| time/ | | +| fps | 309 | +| iterations | 8135 | +| time_elapsed | 26911 | +| total_timesteps | 8330240 | +| train/ | | +| approx_kl | 2.335823 | +| clip_fraction | 0.416 | +| clip_range | 0.2 | +| entropy_loss | -0.298 | +| explained_variance | -1 | +| learning_rate | 0.0001 | +| loss | -0.0634 | +| n_updates | 141870 | +| policy_gradient_loss | -0.0557 | +| value_loss | 0.000659 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.253 | +| time/ | | +| fps | 309 | +| iterations | 8136 | +| time_elapsed | 26914 | +| total_timesteps | 8331264 | +| train/ | | +| approx_kl | 3.163931 | +| clip_fraction | 0.457 | +| clip_range | 0.2 | +| entropy_loss | -0.305 | +| explained_variance | -1.46 | +| learning_rate | 0.0001 | +| loss | -0.0866 | +| n_updates | 141880 | +| policy_gradient_loss | -0.0645 | +| value_loss | 0.000526 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.253 | +| time/ | | +| fps | 309 | +| iterations | 8137 | +| time_elapsed | 26917 | +| total_timesteps | 8332288 | +| train/ | | +| approx_kl | 1.6639494 | +| clip_fraction | 0.423 | +| clip_range | 0.2 | +| entropy_loss | -0.309 | +| explained_variance | -2.51 | +| learning_rate | 0.0001 | +| loss | -0.0727 | +| n_updates | 141890 | +| policy_gradient_loss | -0.058 | +| value_loss | 0.00069 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.252 | +| time/ | | +| fps | 309 | +| iterations | 8138 | +| time_elapsed | 26920 | +| total_timesteps | 8333312 | +| train/ | | +| approx_kl | 2.3492508 | +| clip_fraction | 0.441 | +| clip_range | 0.2 | +| entropy_loss | -0.298 | +| explained_variance | -1.92 | +| learning_rate | 0.0001 | +| loss | -0.09 | +| n_updates | 141900 | +| policy_gradient_loss | -0.0444 | +| value_loss | 0.000908 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.251 | +| time/ | | +| fps | 309 | +| iterations | 8139 | +| time_elapsed | 26924 | +| total_timesteps | 8334336 | +| train/ | | +| approx_kl | 2.8454952 | +| clip_fraction | 0.437 | +| clip_range | 0.2 | +| entropy_loss | -0.313 | +| explained_variance | -2.18 | +| learning_rate | 0.0001 | +| loss | -0.0669 | +| n_updates | 141910 | +| policy_gradient_loss | -0.0651 | +| value_loss | 0.000815 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.254 | +| time/ | | +| fps | 309 | +| iterations | 8140 | +| time_elapsed | 26927 | +| total_timesteps | 8335360 | +| train/ | | +| approx_kl | 1.9465506 | +| clip_fraction | 0.449 | +| clip_range | 0.2 | +| entropy_loss | -0.338 | +| explained_variance | -3.12 | +| learning_rate | 0.0001 | +| loss | -0.0671 | +| n_updates | 141920 | +| policy_gradient_loss | -0.0539 | +| value_loss | 0.000502 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.251 | +| time/ | | +| fps | 309 | +| iterations | 8141 | +| time_elapsed | 26931 | +| total_timesteps | 8336384 | +| train/ | | +| approx_kl | 2.2028832 | +| clip_fraction | 0.466 | +| clip_range | 0.2 | +| entropy_loss | -0.325 | +| explained_variance | -1.34 | +| learning_rate | 0.0001 | +| loss | -0.0796 | +| n_updates | 141930 | +| policy_gradient_loss | -0.064 | +| value_loss | 0.000708 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.251 | +| time/ | | +| fps | 309 | +| iterations | 8142 | +| time_elapsed | 26934 | +| total_timesteps | 8337408 | +| train/ | | +| approx_kl | 2.3553858 | +| clip_fraction | 0.429 | +| clip_range | 0.2 | +| entropy_loss | -0.302 | +| explained_variance | -3.06 | +| learning_rate | 0.0001 | +| loss | -0.0843 | +| n_updates | 141940 | +| policy_gradient_loss | -0.0606 | +| value_loss | 0.000563 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.253 | +| time/ | | +| fps | 309 | +| iterations | 8143 | +| time_elapsed | 26938 | +| total_timesteps | 8338432 | +| train/ | | +| approx_kl | 2.7662392 | +| clip_fraction | 0.49 | +| clip_range | 0.2 | +| entropy_loss | -0.324 | +| explained_variance | -1.59 | +| learning_rate | 0.0001 | +| loss | -0.0915 | +| n_updates | 141950 | +| policy_gradient_loss | -0.0651 | +| value_loss | 0.000867 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.256 | +| time/ | | +| fps | 309 | +| iterations | 8144 | +| time_elapsed | 26941 | +| total_timesteps | 8339456 | +| train/ | | +| approx_kl | 2.967009 | +| clip_fraction | 0.432 | +| clip_range | 0.2 | +| entropy_loss | -0.305 | +| explained_variance | -1.6 | +| learning_rate | 0.0001 | +| loss | -0.0596 | +| n_updates | 141960 | +| policy_gradient_loss | -0.0604 | +| value_loss | 0.000773 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.256 | +| time/ | | +| fps | 309 | +| iterations | 8145 | +| time_elapsed | 26945 | +| total_timesteps | 8340480 | +| train/ | | +| approx_kl | 2.0763297 | +| clip_fraction | 0.441 | +| clip_range | 0.2 | +| entropy_loss | -0.306 | +| explained_variance | -4.53 | +| learning_rate | 0.0001 | +| loss | -0.0712 | +| n_updates | 141970 | +| policy_gradient_loss | -0.0593 | +| value_loss | 0.000605 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.259 | +| time/ | | +| fps | 309 | +| iterations | 8146 | +| time_elapsed | 26948 | +| total_timesteps | 8341504 | +| train/ | | +| approx_kl | 2.7149286 | +| clip_fraction | 0.469 | +| clip_range | 0.2 | +| entropy_loss | -0.305 | +| explained_variance | -0.605 | +| learning_rate | 0.0001 | +| loss | -0.0976 | +| n_updates | 141980 | +| policy_gradient_loss | -0.0671 | +| value_loss | 0.000516 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.261 | +| time/ | | +| fps | 309 | +| iterations | 8147 | +| time_elapsed | 26951 | +| total_timesteps | 8342528 | +| train/ | | +| approx_kl | 2.5750182 | +| clip_fraction | 0.428 | +| clip_range | 0.2 | +| entropy_loss | -0.244 | +| explained_variance | -1.67 | +| learning_rate | 0.0001 | +| loss | -0.0863 | +| n_updates | 141990 | +| policy_gradient_loss | -0.0632 | +| value_loss | 0.000865 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.261 | +| time/ | | +| fps | 309 | +| iterations | 8148 | +| time_elapsed | 26954 | +| total_timesteps | 8343552 | +| train/ | | +| approx_kl | 1.8672938 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.331 | +| explained_variance | -1.28 | +| learning_rate | 0.0001 | +| loss | -0.0944 | +| n_updates | 142000 | +| policy_gradient_loss | -0.0677 | +| value_loss | 0.000484 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.264 | +| time/ | | +| fps | 309 | +| iterations | 8149 | +| time_elapsed | 26958 | +| total_timesteps | 8344576 | +| train/ | | +| approx_kl | 2.8655853 | +| clip_fraction | 0.465 | +| clip_range | 0.2 | +| entropy_loss | -0.313 | +| explained_variance | -1.41 | +| learning_rate | 0.0001 | +| loss | -0.0864 | +| n_updates | 142010 | +| policy_gradient_loss | -0.0641 | +| value_loss | 0.000659 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.261 | +| time/ | | +| fps | 309 | +| iterations | 8150 | +| time_elapsed | 26961 | +| total_timesteps | 8345600 | +| train/ | | +| approx_kl | 2.744304 | +| clip_fraction | 0.433 | +| clip_range | 0.2 | +| entropy_loss | -0.271 | +| explained_variance | -2.94 | +| learning_rate | 0.0001 | +| loss | -0.0949 | +| n_updates | 142020 | +| policy_gradient_loss | -0.0652 | +| value_loss | 0.000653 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.26 | +| time/ | | +| fps | 309 | +| iterations | 8151 | +| time_elapsed | 26964 | +| total_timesteps | 8346624 | +| train/ | | +| approx_kl | 3.7135754 | +| clip_fraction | 0.456 | +| clip_range | 0.2 | +| entropy_loss | -0.286 | +| explained_variance | -2.12 | +| learning_rate | 0.0001 | +| loss | -0.0687 | +| n_updates | 142030 | +| policy_gradient_loss | -0.0595 | +| value_loss | 0.00058 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.26 | +| time/ | | +| fps | 309 | +| iterations | 8152 | +| time_elapsed | 26967 | +| total_timesteps | 8347648 | +| train/ | | +| approx_kl | 2.7017808 | +| clip_fraction | 0.431 | +| clip_range | 0.2 | +| entropy_loss | -0.283 | +| explained_variance | -2.58 | +| learning_rate | 0.0001 | +| loss | -0.0876 | +| n_updates | 142040 | +| policy_gradient_loss | -0.065 | +| value_loss | 0.000553 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.263 | +| time/ | | +| fps | 309 | +| iterations | 8153 | +| time_elapsed | 26971 | +| total_timesteps | 8348672 | +| train/ | | +| approx_kl | 3.3865283 | +| clip_fraction | 0.498 | +| clip_range | 0.2 | +| entropy_loss | -0.346 | +| explained_variance | -1.58 | +| learning_rate | 0.0001 | +| loss | -0.0983 | +| n_updates | 142050 | +| policy_gradient_loss | -0.0729 | +| value_loss | 0.000777 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.263 | +| time/ | | +| fps | 309 | +| iterations | 8154 | +| time_elapsed | 26974 | +| total_timesteps | 8349696 | +| train/ | | +| approx_kl | 2.12408 | +| clip_fraction | 0.441 | +| clip_range | 0.2 | +| entropy_loss | -0.314 | +| explained_variance | -1.38 | +| learning_rate | 0.0001 | +| loss | -0.0824 | +| n_updates | 142060 | +| policy_gradient_loss | -0.0651 | +| value_loss | 0.00083 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.26 | +| time/ | | +| fps | 309 | +| iterations | 8155 | +| time_elapsed | 26977 | +| total_timesteps | 8350720 | +| train/ | | +| approx_kl | 2.8043647 | +| clip_fraction | 0.462 | +| clip_range | 0.2 | +| entropy_loss | -0.261 | +| explained_variance | -5.77 | +| learning_rate | 0.0001 | +| loss | -0.0954 | +| n_updates | 142070 | +| policy_gradient_loss | -0.0671 | +| value_loss | 0.000642 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.26 | +| time/ | | +| fps | 309 | +| iterations | 8156 | +| time_elapsed | 26980 | +| total_timesteps | 8351744 | +| train/ | | +| approx_kl | 2.244595 | +| clip_fraction | 0.421 | +| clip_range | 0.2 | +| entropy_loss | -0.284 | +| explained_variance | -1.24 | +| learning_rate | 0.0001 | +| loss | -0.095 | +| n_updates | 142080 | +| policy_gradient_loss | -0.0624 | +| value_loss | 0.000716 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.26 | +| time/ | | +| fps | 309 | +| iterations | 8157 | +| time_elapsed | 26984 | +| total_timesteps | 8352768 | +| train/ | | +| approx_kl | 2.856957 | +| clip_fraction | 0.461 | +| clip_range | 0.2 | +| entropy_loss | -0.296 | +| explained_variance | -1.31 | +| learning_rate | 0.0001 | +| loss | -0.0714 | +| n_updates | 142090 | +| policy_gradient_loss | -0.0692 | +| value_loss | 0.000679 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.257 | +| time/ | | +| fps | 309 | +| iterations | 8158 | +| time_elapsed | 26987 | +| total_timesteps | 8353792 | +| train/ | | +| approx_kl | 2.9554696 | +| clip_fraction | 0.432 | +| clip_range | 0.2 | +| entropy_loss | -0.267 | +| explained_variance | -2.11 | +| learning_rate | 0.0001 | +| loss | -0.0925 | +| n_updates | 142100 | +| policy_gradient_loss | -0.0638 | +| value_loss | 0.000758 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.249 | +| time/ | | +| fps | 309 | +| iterations | 8159 | +| time_elapsed | 26991 | +| total_timesteps | 8354816 | +| train/ | | +| approx_kl | 2.0578156 | +| clip_fraction | 0.431 | +| clip_range | 0.2 | +| entropy_loss | -0.306 | +| explained_variance | -1.38 | +| learning_rate | 0.0001 | +| loss | -0.07 | +| n_updates | 142110 | +| policy_gradient_loss | -0.0571 | +| value_loss | 0.000671 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.25 | +| time/ | | +| fps | 309 | +| iterations | 8160 | +| time_elapsed | 26994 | +| total_timesteps | 8355840 | +| train/ | | +| approx_kl | 2.0400124 | +| clip_fraction | 0.423 | +| clip_range | 0.2 | +| entropy_loss | -0.274 | +| explained_variance | -0.521 | +| learning_rate | 0.0001 | +| loss | -0.0757 | +| n_updates | 142120 | +| policy_gradient_loss | -0.0589 | +| value_loss | 0.0011 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.25 | +| time/ | | +| fps | 309 | +| iterations | 8161 | +| time_elapsed | 26998 | +| total_timesteps | 8356864 | +| train/ | | +| approx_kl | 2.7351928 | +| clip_fraction | 0.42 | +| clip_range | 0.2 | +| entropy_loss | -0.242 | +| explained_variance | -2.76 | +| learning_rate | 0.0001 | +| loss | -0.0817 | +| n_updates | 142130 | +| policy_gradient_loss | -0.0663 | +| value_loss | 0.000721 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.245 | +| time/ | | +| fps | 309 | +| iterations | 8162 | +| time_elapsed | 27002 | +| total_timesteps | 8357888 | +| train/ | | +| approx_kl | 2.1435905 | +| clip_fraction | 0.456 | +| clip_range | 0.2 | +| entropy_loss | -0.336 | +| explained_variance | -1.04 | +| learning_rate | 0.0001 | +| loss | -0.0617 | +| n_updates | 142140 | +| policy_gradient_loss | -0.062 | +| value_loss | 0.000485 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.239 | +| time/ | | +| fps | 309 | +| iterations | 8163 | +| time_elapsed | 27005 | +| total_timesteps | 8358912 | +| train/ | | +| approx_kl | 2.463767 | +| clip_fraction | 0.432 | +| clip_range | 0.2 | +| entropy_loss | -0.279 | +| explained_variance | -3.94 | +| learning_rate | 0.0001 | +| loss | -0.0923 | +| n_updates | 142150 | +| policy_gradient_loss | -0.0551 | +| value_loss | 0.000473 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.234 | +| time/ | | +| fps | 309 | +| iterations | 8164 | +| time_elapsed | 27009 | +| total_timesteps | 8359936 | +| train/ | | +| approx_kl | 2.3617458 | +| clip_fraction | 0.432 | +| clip_range | 0.2 | +| entropy_loss | -0.304 | +| explained_variance | -1.52 | +| learning_rate | 0.0001 | +| loss | -0.0814 | +| n_updates | 142160 | +| policy_gradient_loss | -0.0608 | +| value_loss | 0.000481 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.231 | +| time/ | | +| fps | 309 | +| iterations | 8165 | +| time_elapsed | 27012 | +| total_timesteps | 8360960 | +| train/ | | +| approx_kl | 2.5455608 | +| clip_fraction | 0.426 | +| clip_range | 0.2 | +| entropy_loss | -0.276 | +| explained_variance | -0.736 | +| learning_rate | 0.0001 | +| loss | -0.085 | +| n_updates | 142170 | +| policy_gradient_loss | -0.0615 | +| value_loss | 0.000967 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.234 | +| time/ | | +| fps | 309 | +| iterations | 8166 | +| time_elapsed | 27015 | +| total_timesteps | 8361984 | +| train/ | | +| approx_kl | 3.0101244 | +| clip_fraction | 0.454 | +| clip_range | 0.2 | +| entropy_loss | -0.286 | +| explained_variance | -4.17 | +| learning_rate | 0.0001 | +| loss | -0.0819 | +| n_updates | 142180 | +| policy_gradient_loss | -0.0628 | +| value_loss | 0.00101 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.225 | +| time/ | | +| fps | 309 | +| iterations | 8167 | +| time_elapsed | 27019 | +| total_timesteps | 8363008 | +| train/ | | +| approx_kl | 2.2962046 | +| clip_fraction | 0.421 | +| clip_range | 0.2 | +| entropy_loss | -0.262 | +| explained_variance | -2.76 | +| learning_rate | 0.0001 | +| loss | -0.0944 | +| n_updates | 142190 | +| policy_gradient_loss | -0.0624 | +| value_loss | 0.000411 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.223 | +| time/ | | +| fps | 309 | +| iterations | 8168 | +| time_elapsed | 27022 | +| total_timesteps | 8364032 | +| train/ | | +| approx_kl | 2.2991376 | +| clip_fraction | 0.412 | +| clip_range | 0.2 | +| entropy_loss | -0.26 | +| explained_variance | -0.745 | +| learning_rate | 0.0001 | +| loss | -0.0824 | +| n_updates | 142200 | +| policy_gradient_loss | -0.0544 | +| value_loss | 0.000606 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.223 | +| time/ | | +| fps | 309 | +| iterations | 8169 | +| time_elapsed | 27025 | +| total_timesteps | 8365056 | +| train/ | | +| approx_kl | 2.444016 | +| clip_fraction | 0.434 | +| clip_range | 0.2 | +| entropy_loss | -0.281 | +| explained_variance | -2.81 | +| learning_rate | 0.0001 | +| loss | -0.0834 | +| n_updates | 142210 | +| policy_gradient_loss | -0.0612 | +| value_loss | 0.000605 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.219 | +| time/ | | +| fps | 309 | +| iterations | 8170 | +| time_elapsed | 27028 | +| total_timesteps | 8366080 | +| train/ | | +| approx_kl | 1.8910526 | +| clip_fraction | 0.434 | +| clip_range | 0.2 | +| entropy_loss | -0.311 | +| explained_variance | -1.73 | +| learning_rate | 0.0001 | +| loss | -0.0868 | +| n_updates | 142220 | +| policy_gradient_loss | -0.0609 | +| value_loss | 0.000593 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.216 | +| time/ | | +| fps | 309 | +| iterations | 8171 | +| time_elapsed | 27031 | +| total_timesteps | 8367104 | +| train/ | | +| approx_kl | 2.0703425 | +| clip_fraction | 0.396 | +| clip_range | 0.2 | +| entropy_loss | -0.252 | +| explained_variance | -2.27 | +| learning_rate | 0.0001 | +| loss | -0.0854 | +| n_updates | 142230 | +| policy_gradient_loss | -0.0616 | +| value_loss | 0.000496 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.217 | +| time/ | | +| fps | 309 | +| iterations | 8172 | +| time_elapsed | 27035 | +| total_timesteps | 8368128 | +| train/ | | +| approx_kl | 2.5141575 | +| clip_fraction | 0.402 | +| clip_range | 0.2 | +| entropy_loss | -0.246 | +| explained_variance | -1.3 | +| learning_rate | 0.0001 | +| loss | -0.0911 | +| n_updates | 142240 | +| policy_gradient_loss | -0.0584 | +| value_loss | 0.000765 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.217 | +| time/ | | +| fps | 309 | +| iterations | 8173 | +| time_elapsed | 27038 | +| total_timesteps | 8369152 | +| train/ | | +| approx_kl | 3.3084023 | +| clip_fraction | 0.45 | +| clip_range | 0.2 | +| entropy_loss | -0.34 | +| explained_variance | -0.958 | +| learning_rate | 0.0001 | +| loss | -0.0745 | +| n_updates | 142250 | +| policy_gradient_loss | -0.0563 | +| value_loss | 0.000811 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.218 | +| time/ | | +| fps | 309 | +| iterations | 8174 | +| time_elapsed | 27041 | +| total_timesteps | 8370176 | +| train/ | | +| approx_kl | 2.3488967 | +| clip_fraction | 0.45 | +| clip_range | 0.2 | +| entropy_loss | -0.301 | +| explained_variance | -1.94 | +| learning_rate | 0.0001 | +| loss | -0.0863 | +| n_updates | 142260 | +| policy_gradient_loss | -0.0639 | +| value_loss | 0.000616 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.219 | +| time/ | | +| fps | 309 | +| iterations | 8175 | +| time_elapsed | 27045 | +| total_timesteps | 8371200 | +| train/ | | +| approx_kl | 2.117638 | +| clip_fraction | 0.449 | +| clip_range | 0.2 | +| entropy_loss | -0.313 | +| explained_variance | -1.67 | +| learning_rate | 0.0001 | +| loss | -0.0623 | +| n_updates | 142270 | +| policy_gradient_loss | -0.0619 | +| value_loss | 0.000503 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.221 | +| time/ | | +| fps | 309 | +| iterations | 8176 | +| time_elapsed | 27048 | +| total_timesteps | 8372224 | +| train/ | | +| approx_kl | 2.324545 | +| clip_fraction | 0.453 | +| clip_range | 0.2 | +| entropy_loss | -0.315 | +| explained_variance | -0.943 | +| learning_rate | 0.0001 | +| loss | -0.048 | +| n_updates | 142280 | +| policy_gradient_loss | -0.0581 | +| value_loss | 0.000665 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.221 | +| time/ | | +| fps | 309 | +| iterations | 8177 | +| time_elapsed | 27052 | +| total_timesteps | 8373248 | +| train/ | | +| approx_kl | 2.1216626 | +| clip_fraction | 0.424 | +| clip_range | 0.2 | +| entropy_loss | -0.282 | +| explained_variance | -3.89 | +| learning_rate | 0.0001 | +| loss | -0.0745 | +| n_updates | 142290 | +| policy_gradient_loss | -0.0586 | +| value_loss | 0.00046 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.219 | +| time/ | | +| fps | 309 | +| iterations | 8178 | +| time_elapsed | 27055 | +| total_timesteps | 8374272 | +| train/ | | +| approx_kl | 1.9647557 | +| clip_fraction | 0.472 | +| clip_range | 0.2 | +| entropy_loss | -0.313 | +| explained_variance | -1.55 | +| learning_rate | 0.0001 | +| loss | -0.0589 | +| n_updates | 142300 | +| policy_gradient_loss | -0.058 | +| value_loss | 0.000516 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.219 | +| time/ | | +| fps | 309 | +| iterations | 8179 | +| time_elapsed | 27058 | +| total_timesteps | 8375296 | +| train/ | | +| approx_kl | 1.9115212 | +| clip_fraction | 0.424 | +| clip_range | 0.2 | +| entropy_loss | -0.31 | +| explained_variance | -0.951 | +| learning_rate | 0.0001 | +| loss | -0.0893 | +| n_updates | 142310 | +| policy_gradient_loss | -0.0636 | +| value_loss | 0.000893 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.215 | +| time/ | | +| fps | 309 | +| iterations | 8180 | +| time_elapsed | 27062 | +| total_timesteps | 8376320 | +| train/ | | +| approx_kl | 1.6546587 | +| clip_fraction | 0.418 | +| clip_range | 0.2 | +| entropy_loss | -0.315 | +| explained_variance | -1.81 | +| learning_rate | 0.0001 | +| loss | -0.0622 | +| n_updates | 142320 | +| policy_gradient_loss | -0.0574 | +| value_loss | 0.000796 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.212 | +| time/ | | +| fps | 309 | +| iterations | 8181 | +| time_elapsed | 27065 | +| total_timesteps | 8377344 | +| train/ | | +| approx_kl | 3.3991964 | +| clip_fraction | 0.482 | +| clip_range | 0.2 | +| entropy_loss | -0.306 | +| explained_variance | -2.84 | +| learning_rate | 0.0001 | +| loss | -0.108 | +| n_updates | 142330 | +| policy_gradient_loss | -0.0707 | +| value_loss | 0.000781 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.216 | +| time/ | | +| fps | 309 | +| iterations | 8182 | +| time_elapsed | 27069 | +| total_timesteps | 8378368 | +| train/ | | +| approx_kl | 3.5711718 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.309 | +| explained_variance | -1.77 | +| learning_rate | 0.0001 | +| loss | -0.0931 | +| n_updates | 142340 | +| policy_gradient_loss | -0.0637 | +| value_loss | 0.000587 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.211 | +| time/ | | +| fps | 309 | +| iterations | 8183 | +| time_elapsed | 27072 | +| total_timesteps | 8379392 | +| train/ | | +| approx_kl | 2.6367006 | +| clip_fraction | 0.44 | +| clip_range | 0.2 | +| entropy_loss | -0.272 | +| explained_variance | -0.41 | +| learning_rate | 0.0001 | +| loss | -0.0692 | +| n_updates | 142350 | +| policy_gradient_loss | -0.0493 | +| value_loss | 0.000906 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.211 | +| time/ | | +| fps | 309 | +| iterations | 8184 | +| time_elapsed | 27075 | +| total_timesteps | 8380416 | +| train/ | | +| approx_kl | 2.5227976 | +| clip_fraction | 0.468 | +| clip_range | 0.2 | +| entropy_loss | -0.302 | +| explained_variance | -7.48 | +| learning_rate | 0.0001 | +| loss | -0.124 | +| n_updates | 142360 | +| policy_gradient_loss | -0.0687 | +| value_loss | 0.000726 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.214 | +| time/ | | +| fps | 309 | +| iterations | 8185 | +| time_elapsed | 27078 | +| total_timesteps | 8381440 | +| train/ | | +| approx_kl | 2.7213635 | +| clip_fraction | 0.459 | +| clip_range | 0.2 | +| entropy_loss | -0.328 | +| explained_variance | -1.3 | +| learning_rate | 0.0001 | +| loss | -0.0874 | +| n_updates | 142370 | +| policy_gradient_loss | -0.0623 | +| value_loss | 0.000504 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.213 | +| time/ | | +| fps | 309 | +| iterations | 8186 | +| time_elapsed | 27081 | +| total_timesteps | 8382464 | +| train/ | | +| approx_kl | 2.0126338 | +| clip_fraction | 0.433 | +| clip_range | 0.2 | +| entropy_loss | -0.295 | +| explained_variance | -0.777 | +| learning_rate | 0.0001 | +| loss | -0.077 | +| n_updates | 142380 | +| policy_gradient_loss | -0.0692 | +| value_loss | 0.000588 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.213 | +| time/ | | +| fps | 309 | +| iterations | 8187 | +| time_elapsed | 27085 | +| total_timesteps | 8383488 | +| train/ | | +| approx_kl | 2.2089548 | +| clip_fraction | 0.462 | +| clip_range | 0.2 | +| entropy_loss | -0.318 | +| explained_variance | -0.783 | +| learning_rate | 0.0001 | +| loss | -0.0907 | +| n_updates | 142390 | +| policy_gradient_loss | -0.0589 | +| value_loss | 0.00107 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.209 | +| time/ | | +| fps | 309 | +| iterations | 8188 | +| time_elapsed | 27088 | +| total_timesteps | 8384512 | +| train/ | | +| approx_kl | 2.2936964 | +| clip_fraction | 0.437 | +| clip_range | 0.2 | +| entropy_loss | -0.291 | +| explained_variance | -2.52 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 142400 | +| policy_gradient_loss | -0.0652 | +| value_loss | 0.000765 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.212 | +| time/ | | +| fps | 309 | +| iterations | 8189 | +| time_elapsed | 27091 | +| total_timesteps | 8385536 | +| train/ | | +| approx_kl | 3.0668209 | +| clip_fraction | 0.438 | +| clip_range | 0.2 | +| entropy_loss | -0.273 | +| explained_variance | -3.04 | +| learning_rate | 0.0001 | +| loss | -0.105 | +| n_updates | 142410 | +| policy_gradient_loss | -0.0706 | +| value_loss | 0.00069 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.203 | +| time/ | | +| fps | 309 | +| iterations | 8190 | +| time_elapsed | 27094 | +| total_timesteps | 8386560 | +| train/ | | +| approx_kl | 2.0145822 | +| clip_fraction | 0.441 | +| clip_range | 0.2 | +| entropy_loss | -0.294 | +| explained_variance | -0.704 | +| learning_rate | 0.0001 | +| loss | -0.0757 | +| n_updates | 142420 | +| policy_gradient_loss | -0.0644 | +| value_loss | 0.000678 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.197 | +| time/ | | +| fps | 309 | +| iterations | 8191 | +| time_elapsed | 27097 | +| total_timesteps | 8387584 | +| train/ | | +| approx_kl | 2.355566 | +| clip_fraction | 0.414 | +| clip_range | 0.2 | +| entropy_loss | -0.273 | +| explained_variance | -3.51 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 142430 | +| policy_gradient_loss | -0.0563 | +| value_loss | 0.000636 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.197 | +| time/ | | +| fps | 309 | +| iterations | 8192 | +| time_elapsed | 27101 | +| total_timesteps | 8388608 | +| train/ | | +| approx_kl | 2.099153 | +| clip_fraction | 0.434 | +| clip_range | 0.2 | +| entropy_loss | -0.295 | +| explained_variance | -2.28 | +| learning_rate | 0.0001 | +| loss | -0.0959 | +| n_updates | 142440 | +| policy_gradient_loss | -0.0637 | +| value_loss | 0.000655 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.189 | +| time/ | | +| fps | 309 | +| iterations | 8193 | +| time_elapsed | 27104 | +| total_timesteps | 8389632 | +| train/ | | +| approx_kl | 3.0067327 | +| clip_fraction | 0.476 | +| clip_range | 0.2 | +| entropy_loss | -0.305 | +| explained_variance | -0.873 | +| learning_rate | 0.0001 | +| loss | -0.0981 | +| n_updates | 142450 | +| policy_gradient_loss | -0.0625 | +| value_loss | 0.000775 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.189 | +| time/ | | +| fps | 309 | +| iterations | 8194 | +| time_elapsed | 27108 | +| total_timesteps | 8390656 | +| train/ | | +| approx_kl | 1.9377213 | +| clip_fraction | 0.41 | +| clip_range | 0.2 | +| entropy_loss | -0.272 | +| explained_variance | -1.67 | +| learning_rate | 0.0001 | +| loss | -0.0793 | +| n_updates | 142460 | +| policy_gradient_loss | -0.0615 | +| value_loss | 0.000793 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.185 | +| time/ | | +| fps | 309 | +| iterations | 8195 | +| time_elapsed | 27111 | +| total_timesteps | 8391680 | +| train/ | | +| approx_kl | 3.3847327 | +| clip_fraction | 0.419 | +| clip_range | 0.2 | +| entropy_loss | -0.247 | +| explained_variance | -2.26 | +| learning_rate | 0.0001 | +| loss | -0.0893 | +| n_updates | 142470 | +| policy_gradient_loss | -0.0597 | +| value_loss | 0.000738 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.178 | +| time/ | | +| fps | 309 | +| iterations | 8196 | +| time_elapsed | 27115 | +| total_timesteps | 8392704 | +| train/ | | +| approx_kl | 2.994275 | +| clip_fraction | 0.453 | +| clip_range | 0.2 | +| entropy_loss | -0.303 | +| explained_variance | -2.98 | +| learning_rate | 0.0001 | +| loss | -0.0645 | +| n_updates | 142480 | +| policy_gradient_loss | -0.0647 | +| value_loss | 0.000511 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.178 | +| time/ | | +| fps | 309 | +| iterations | 8197 | +| time_elapsed | 27118 | +| total_timesteps | 8393728 | +| train/ | | +| approx_kl | 2.4728098 | +| clip_fraction | 0.454 | +| clip_range | 0.2 | +| entropy_loss | -0.298 | +| explained_variance | -0.454 | +| learning_rate | 0.0001 | +| loss | -0.0558 | +| n_updates | 142490 | +| policy_gradient_loss | -0.0619 | +| value_loss | 0.000754 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.174 | +| time/ | | +| fps | 309 | +| iterations | 8198 | +| time_elapsed | 27122 | +| total_timesteps | 8394752 | +| train/ | | +| approx_kl | 2.3112743 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.31 | +| explained_variance | -2.35 | +| learning_rate | 0.0001 | +| loss | -0.0737 | +| n_updates | 142500 | +| policy_gradient_loss | -0.0694 | +| value_loss | 0.000895 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.164 | +| time/ | | +| fps | 309 | +| iterations | 8199 | +| time_elapsed | 27125 | +| total_timesteps | 8395776 | +| train/ | | +| approx_kl | 2.6976857 | +| clip_fraction | 0.449 | +| clip_range | 0.2 | +| entropy_loss | -0.275 | +| explained_variance | -1.66 | +| learning_rate | 0.0001 | +| loss | -0.107 | +| n_updates | 142510 | +| policy_gradient_loss | -0.0701 | +| value_loss | 0.000614 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.16 | +| time/ | | +| fps | 309 | +| iterations | 8200 | +| time_elapsed | 27129 | +| total_timesteps | 8396800 | +| train/ | | +| approx_kl | 1.9300848 | +| clip_fraction | 0.437 | +| clip_range | 0.2 | +| entropy_loss | -0.278 | +| explained_variance | -0.696 | +| learning_rate | 0.0001 | +| loss | -0.0649 | +| n_updates | 142520 | +| policy_gradient_loss | -0.0581 | +| value_loss | 0.000794 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.156 | +| time/ | | +| fps | 309 | +| iterations | 8201 | +| time_elapsed | 27132 | +| total_timesteps | 8397824 | +| train/ | | +| approx_kl | 2.4271984 | +| clip_fraction | 0.446 | +| clip_range | 0.2 | +| entropy_loss | -0.289 | +| explained_variance | -3.27 | +| learning_rate | 0.0001 | +| loss | -0.0966 | +| n_updates | 142530 | +| policy_gradient_loss | -0.041 | +| value_loss | 0.000797 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.152 | +| time/ | | +| fps | 309 | +| iterations | 8202 | +| time_elapsed | 27135 | +| total_timesteps | 8398848 | +| train/ | | +| approx_kl | 1.9348288 | +| clip_fraction | 0.432 | +| clip_range | 0.2 | +| entropy_loss | -0.328 | +| explained_variance | -2.13 | +| learning_rate | 0.0001 | +| loss | -0.047 | +| n_updates | 142540 | +| policy_gradient_loss | -0.0597 | +| value_loss | 0.000691 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.148 | +| time/ | | +| fps | 309 | +| iterations | 8203 | +| time_elapsed | 27139 | +| total_timesteps | 8399872 | +| train/ | | +| approx_kl | 2.4460902 | +| clip_fraction | 0.478 | +| clip_range | 0.2 | +| entropy_loss | -0.314 | +| explained_variance | -1.87 | +| learning_rate | 0.0001 | +| loss | -0.0878 | +| n_updates | 142550 | +| policy_gradient_loss | -0.0692 | +| value_loss | 0.000447 | +--------------------------------------- + +Current state: Champion.Level10.RyuVsVega +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.145 | +| time/ | | +| fps | 309 | +| iterations | 8204 | +| time_elapsed | 27142 | +| total_timesteps | 8400896 | +| train/ | | +| approx_kl | 2.6365132 | +| clip_fraction | 0.449 | +| clip_range | 0.2 | +| entropy_loss | -0.307 | +| explained_variance | -0.602 | +| learning_rate | 0.0001 | +| loss | -0.0671 | +| n_updates | 142560 | +| policy_gradient_loss | -0.0622 | +| value_loss | 0.000646 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.145 | +| time/ | | +| fps | 309 | +| iterations | 8205 | +| time_elapsed | 27145 | +| total_timesteps | 8401920 | +| train/ | | +| approx_kl | 2.3274875 | +| clip_fraction | 0.461 | +| clip_range | 0.2 | +| entropy_loss | -0.331 | +| explained_variance | -2.87 | +| learning_rate | 0.0001 | +| loss | -0.1 | +| n_updates | 142570 | +| policy_gradient_loss | -0.0663 | +| value_loss | 0.000747 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.143 | +| time/ | | +| fps | 309 | +| iterations | 8206 | +| time_elapsed | 27148 | +| total_timesteps | 8402944 | +| train/ | | +| approx_kl | 3.111861 | +| clip_fraction | 0.509 | +| clip_range | 0.2 | +| entropy_loss | -0.362 | +| explained_variance | -4.7 | +| learning_rate | 0.0001 | +| loss | -0.0869 | +| n_updates | 142580 | +| policy_gradient_loss | -0.0673 | +| value_loss | 0.000673 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.143 | +| time/ | | +| fps | 309 | +| iterations | 8207 | +| time_elapsed | 27152 | +| total_timesteps | 8403968 | +| train/ | | +| approx_kl | 2.8769138 | +| clip_fraction | 0.523 | +| clip_range | 0.2 | +| entropy_loss | -0.401 | +| explained_variance | -1.72 | +| learning_rate | 0.0001 | +| loss | -0.0863 | +| n_updates | 142590 | +| policy_gradient_loss | -0.0736 | +| value_loss | 0.000519 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.143 | +| time/ | | +| fps | 309 | +| iterations | 8208 | +| time_elapsed | 27155 | +| total_timesteps | 8404992 | +| train/ | | +| approx_kl | 2.739561 | +| clip_fraction | 0.534 | +| clip_range | 0.2 | +| entropy_loss | -0.391 | +| explained_variance | -3.32 | +| learning_rate | 0.0001 | +| loss | -0.0966 | +| n_updates | 142600 | +| policy_gradient_loss | -0.0722 | +| value_loss | 0.000461 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.144 | +| time/ | | +| fps | 309 | +| iterations | 8209 | +| time_elapsed | 27158 | +| total_timesteps | 8406016 | +| train/ | | +| approx_kl | 2.2925158 | +| clip_fraction | 0.527 | +| clip_range | 0.2 | +| entropy_loss | -0.384 | +| explained_variance | -1.5 | +| learning_rate | 0.0001 | +| loss | -0.0796 | +| n_updates | 142610 | +| policy_gradient_loss | -0.0665 | +| value_loss | 0.000361 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.145 | +| time/ | | +| fps | 309 | +| iterations | 8210 | +| time_elapsed | 27162 | +| total_timesteps | 8407040 | +| train/ | | +| approx_kl | 3.3652632 | +| clip_fraction | 0.506 | +| clip_range | 0.2 | +| entropy_loss | -0.416 | +| explained_variance | -1.26 | +| learning_rate | 0.0001 | +| loss | -0.0991 | +| n_updates | 142620 | +| policy_gradient_loss | -0.0664 | +| value_loss | 0.000743 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.145 | +| time/ | | +| fps | 309 | +| iterations | 8211 | +| time_elapsed | 27165 | +| total_timesteps | 8408064 | +| train/ | | +| approx_kl | 2.52541 | +| clip_fraction | 0.52 | +| clip_range | 0.2 | +| entropy_loss | -0.402 | +| explained_variance | -3.32 | +| learning_rate | 0.0001 | +| loss | -0.0887 | +| n_updates | 142630 | +| policy_gradient_loss | -0.0673 | +| value_loss | 0.000272 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.145 | +| time/ | | +| fps | 309 | +| iterations | 8212 | +| time_elapsed | 27168 | +| total_timesteps | 8409088 | +| train/ | | +| approx_kl | 2.452409 | +| clip_fraction | 0.531 | +| clip_range | 0.2 | +| entropy_loss | -0.384 | +| explained_variance | -0.377 | +| learning_rate | 0.0001 | +| loss | -0.0832 | +| n_updates | 142640 | +| policy_gradient_loss | -0.0724 | +| value_loss | 0.000753 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.144 | +| time/ | | +| fps | 309 | +| iterations | 8213 | +| time_elapsed | 27172 | +| total_timesteps | 8410112 | +| train/ | | +| approx_kl | 2.0967352 | +| clip_fraction | 0.504 | +| clip_range | 0.2 | +| entropy_loss | -0.401 | +| explained_variance | -1.92 | +| learning_rate | 0.0001 | +| loss | -0.0722 | +| n_updates | 142650 | +| policy_gradient_loss | -0.0735 | +| value_loss | 0.000345 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.144 | +| time/ | | +| fps | 309 | +| iterations | 8214 | +| time_elapsed | 27175 | +| total_timesteps | 8411136 | +| train/ | | +| approx_kl | 2.392456 | +| clip_fraction | 0.472 | +| clip_range | 0.2 | +| entropy_loss | -0.338 | +| explained_variance | -3.65 | +| learning_rate | 0.0001 | +| loss | -0.0733 | +| n_updates | 142660 | +| policy_gradient_loss | -0.0669 | +| value_loss | 0.000818 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.144 | +| time/ | | +| fps | 309 | +| iterations | 8215 | +| time_elapsed | 27178 | +| total_timesteps | 8412160 | +| train/ | | +| approx_kl | 3.3760738 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.375 | +| explained_variance | -8.4 | +| learning_rate | 0.0001 | +| loss | -0.0797 | +| n_updates | 142670 | +| policy_gradient_loss | -0.0599 | +| value_loss | 0.000658 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.143 | +| time/ | | +| fps | 309 | +| iterations | 8216 | +| time_elapsed | 27182 | +| total_timesteps | 8413184 | +| train/ | | +| approx_kl | 2.0848918 | +| clip_fraction | 0.501 | +| clip_range | 0.2 | +| entropy_loss | -0.426 | +| explained_variance | -3.13 | +| learning_rate | 0.0001 | +| loss | -0.0844 | +| n_updates | 142680 | +| policy_gradient_loss | -0.0611 | +| value_loss | 0.000342 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.143 | +| time/ | | +| fps | 309 | +| iterations | 8217 | +| time_elapsed | 27185 | +| total_timesteps | 8414208 | +| train/ | | +| approx_kl | 2.7400746 | +| clip_fraction | 0.493 | +| clip_range | 0.2 | +| entropy_loss | -0.41 | +| explained_variance | -2.46 | +| learning_rate | 0.0001 | +| loss | -0.0791 | +| n_updates | 142690 | +| policy_gradient_loss | -0.0698 | +| value_loss | 0.000329 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.143 | +| time/ | | +| fps | 309 | +| iterations | 8218 | +| time_elapsed | 27188 | +| total_timesteps | 8415232 | +| train/ | | +| approx_kl | 2.56644 | +| clip_fraction | 0.503 | +| clip_range | 0.2 | +| entropy_loss | -0.334 | +| explained_variance | -2.29 | +| learning_rate | 0.0001 | +| loss | -0.0888 | +| n_updates | 142700 | +| policy_gradient_loss | -0.0762 | +| value_loss | 0.000558 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.144 | +| time/ | | +| fps | 309 | +| iterations | 8219 | +| time_elapsed | 27191 | +| total_timesteps | 8416256 | +| train/ | | +| approx_kl | 2.6650229 | +| clip_fraction | 0.491 | +| clip_range | 0.2 | +| entropy_loss | -0.344 | +| explained_variance | -5.27 | +| learning_rate | 0.0001 | +| loss | -0.0751 | +| n_updates | 142710 | +| policy_gradient_loss | -0.0766 | +| value_loss | 0.000598 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.144 | +| time/ | | +| fps | 309 | +| iterations | 8220 | +| time_elapsed | 27195 | +| total_timesteps | 8417280 | +| train/ | | +| approx_kl | 2.9384704 | +| clip_fraction | 0.499 | +| clip_range | 0.2 | +| entropy_loss | -0.405 | +| explained_variance | -8.01 | +| learning_rate | 0.0001 | +| loss | -0.111 | +| n_updates | 142720 | +| policy_gradient_loss | -0.0733 | +| value_loss | 0.000468 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.144 | +| time/ | | +| fps | 309 | +| iterations | 8221 | +| time_elapsed | 27198 | +| total_timesteps | 8418304 | +| train/ | | +| approx_kl | 3.5007427 | +| clip_fraction | 0.504 | +| clip_range | 0.2 | +| entropy_loss | -0.382 | +| explained_variance | -1.09 | +| learning_rate | 0.0001 | +| loss | -0.0782 | +| n_updates | 142730 | +| policy_gradient_loss | -0.0701 | +| value_loss | 0.000497 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.144 | +| time/ | | +| fps | 309 | +| iterations | 8222 | +| time_elapsed | 27201 | +| total_timesteps | 8419328 | +| train/ | | +| approx_kl | 2.0307603 | +| clip_fraction | 0.513 | +| clip_range | 0.2 | +| entropy_loss | -0.436 | +| explained_variance | -2.99 | +| learning_rate | 0.0001 | +| loss | -0.0852 | +| n_updates | 142740 | +| policy_gradient_loss | -0.068 | +| value_loss | 0.000394 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.144 | +| time/ | | +| fps | 309 | +| iterations | 8223 | +| time_elapsed | 27204 | +| total_timesteps | 8420352 | +| train/ | | +| approx_kl | 3.0773392 | +| clip_fraction | 0.5 | +| clip_range | 0.2 | +| entropy_loss | -0.349 | +| explained_variance | -3.31 | +| learning_rate | 0.0001 | +| loss | -0.0957 | +| n_updates | 142750 | +| policy_gradient_loss | -0.0723 | +| value_loss | 0.000874 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.144 | +| time/ | | +| fps | 309 | +| iterations | 8224 | +| time_elapsed | 27207 | +| total_timesteps | 8421376 | +| train/ | | +| approx_kl | 2.392457 | +| clip_fraction | 0.489 | +| clip_range | 0.2 | +| entropy_loss | -0.351 | +| explained_variance | -3.13 | +| learning_rate | 0.0001 | +| loss | -0.0878 | +| n_updates | 142760 | +| policy_gradient_loss | -0.0567 | +| value_loss | 0.000576 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.144 | +| time/ | | +| fps | 309 | +| iterations | 8225 | +| time_elapsed | 27210 | +| total_timesteps | 8422400 | +| train/ | | +| approx_kl | 1.8876263 | +| clip_fraction | 0.514 | +| clip_range | 0.2 | +| entropy_loss | -0.428 | +| explained_variance | -4.18 | +| learning_rate | 0.0001 | +| loss | -0.1 | +| n_updates | 142770 | +| policy_gradient_loss | -0.0692 | +| value_loss | 0.000425 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.144 | +| time/ | | +| fps | 309 | +| iterations | 8226 | +| time_elapsed | 27214 | +| total_timesteps | 8423424 | +| train/ | | +| approx_kl | 2.5520034 | +| clip_fraction | 0.508 | +| clip_range | 0.2 | +| entropy_loss | -0.398 | +| explained_variance | -5.59 | +| learning_rate | 0.0001 | +| loss | -0.085 | +| n_updates | 142780 | +| policy_gradient_loss | -0.0745 | +| value_loss | 0.000283 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.144 | +| time/ | | +| fps | 309 | +| iterations | 8227 | +| time_elapsed | 27217 | +| total_timesteps | 8424448 | +| train/ | | +| approx_kl | 3.3848004 | +| clip_fraction | 0.508 | +| clip_range | 0.2 | +| entropy_loss | -0.537 | +| explained_variance | -0.149 | +| learning_rate | 0.0001 | +| loss | -0.0448 | +| n_updates | 142790 | +| policy_gradient_loss | -0.0372 | +| value_loss | 0.000771 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.143 | +| time/ | | +| fps | 309 | +| iterations | 8228 | +| time_elapsed | 27220 | +| total_timesteps | 8425472 | +| train/ | | +| approx_kl | 2.4772134 | +| clip_fraction | 0.504 | +| clip_range | 0.2 | +| entropy_loss | -0.386 | +| explained_variance | -5 | +| learning_rate | 0.0001 | +| loss | -0.0771 | +| n_updates | 142800 | +| policy_gradient_loss | -0.0702 | +| value_loss | 0.000578 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.143 | +| time/ | | +| fps | 309 | +| iterations | 8229 | +| time_elapsed | 27223 | +| total_timesteps | 8426496 | +| train/ | | +| approx_kl | 2.6856246 | +| clip_fraction | 0.496 | +| clip_range | 0.2 | +| entropy_loss | -0.335 | +| explained_variance | -3.12 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 142810 | +| policy_gradient_loss | -0.075 | +| value_loss | 0.000643 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.143 | +| time/ | | +| fps | 309 | +| iterations | 8230 | +| time_elapsed | 27227 | +| total_timesteps | 8427520 | +| train/ | | +| approx_kl | 2.1734428 | +| clip_fraction | 0.49 | +| clip_range | 0.2 | +| entropy_loss | -0.37 | +| explained_variance | -3.02 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 142820 | +| policy_gradient_loss | -0.072 | +| value_loss | 0.000467 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.145 | +| time/ | | +| fps | 309 | +| iterations | 8231 | +| time_elapsed | 27230 | +| total_timesteps | 8428544 | +| train/ | | +| approx_kl | 2.8539157 | +| clip_fraction | 0.53 | +| clip_range | 0.2 | +| entropy_loss | -0.408 | +| explained_variance | -1.4 | +| learning_rate | 0.0001 | +| loss | -0.0959 | +| n_updates | 142830 | +| policy_gradient_loss | -0.0706 | +| value_loss | 0.000504 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.145 | +| time/ | | +| fps | 309 | +| iterations | 8232 | +| time_elapsed | 27234 | +| total_timesteps | 8429568 | +| train/ | | +| approx_kl | 2.164149 | +| clip_fraction | 0.496 | +| clip_range | 0.2 | +| entropy_loss | -0.408 | +| explained_variance | -12 | +| learning_rate | 0.0001 | +| loss | -0.106 | +| n_updates | 142840 | +| policy_gradient_loss | -0.0777 | +| value_loss | 0.000279 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.145 | +| time/ | | +| fps | 309 | +| iterations | 8233 | +| time_elapsed | 27237 | +| total_timesteps | 8430592 | +| train/ | | +| approx_kl | 2.7630637 | +| clip_fraction | 0.502 | +| clip_range | 0.2 | +| entropy_loss | -0.364 | +| explained_variance | -0.617 | +| learning_rate | 0.0001 | +| loss | -0.107 | +| n_updates | 142850 | +| policy_gradient_loss | -0.0708 | +| value_loss | 0.00056 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.143 | +| time/ | | +| fps | 309 | +| iterations | 8234 | +| time_elapsed | 27241 | +| total_timesteps | 8431616 | +| train/ | | +| approx_kl | 2.5245495 | +| clip_fraction | 0.476 | +| clip_range | 0.2 | +| entropy_loss | -0.348 | +| explained_variance | -2.14 | +| learning_rate | 0.0001 | +| loss | -0.0775 | +| n_updates | 142860 | +| policy_gradient_loss | -0.0689 | +| value_loss | 0.000992 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.143 | +| time/ | | +| fps | 309 | +| iterations | 8235 | +| time_elapsed | 27244 | +| total_timesteps | 8432640 | +| train/ | | +| approx_kl | 2.1378384 | +| clip_fraction | 0.497 | +| clip_range | 0.2 | +| entropy_loss | -0.348 | +| explained_variance | -5.29 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 142870 | +| policy_gradient_loss | -0.077 | +| value_loss | 0.000519 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.142 | +| time/ | | +| fps | 309 | +| iterations | 8236 | +| time_elapsed | 27248 | +| total_timesteps | 8433664 | +| train/ | | +| approx_kl | 2.2068832 | +| clip_fraction | 0.503 | +| clip_range | 0.2 | +| entropy_loss | -0.394 | +| explained_variance | -1.04 | +| learning_rate | 0.0001 | +| loss | -0.0941 | +| n_updates | 142880 | +| policy_gradient_loss | -0.0719 | +| value_loss | 0.000352 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.142 | +| time/ | | +| fps | 309 | +| iterations | 8237 | +| time_elapsed | 27251 | +| total_timesteps | 8434688 | +| train/ | | +| approx_kl | 2.1400332 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.418 | +| explained_variance | -1.92 | +| learning_rate | 0.0001 | +| loss | -0.0828 | +| n_updates | 142890 | +| policy_gradient_loss | -0.0611 | +| value_loss | 0.000247 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.142 | +| time/ | | +| fps | 309 | +| iterations | 8238 | +| time_elapsed | 27254 | +| total_timesteps | 8435712 | +| train/ | | +| approx_kl | 2.546493 | +| clip_fraction | 0.465 | +| clip_range | 0.2 | +| entropy_loss | -0.323 | +| explained_variance | -5.38 | +| learning_rate | 0.0001 | +| loss | -0.0868 | +| n_updates | 142900 | +| policy_gradient_loss | -0.0687 | +| value_loss | 0.00034 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.142 | +| time/ | | +| fps | 309 | +| iterations | 8239 | +| time_elapsed | 27257 | +| total_timesteps | 8436736 | +| train/ | | +| approx_kl | 2.179451 | +| clip_fraction | 0.486 | +| clip_range | 0.2 | +| entropy_loss | -0.372 | +| explained_variance | -1.1 | +| learning_rate | 0.0001 | +| loss | -0.0587 | +| n_updates | 142910 | +| policy_gradient_loss | -0.0559 | +| value_loss | 0.000816 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.142 | +| time/ | | +| fps | 309 | +| iterations | 8240 | +| time_elapsed | 27261 | +| total_timesteps | 8437760 | +| train/ | | +| approx_kl | 2.3124847 | +| clip_fraction | 0.479 | +| clip_range | 0.2 | +| entropy_loss | -0.346 | +| explained_variance | -3.11 | +| learning_rate | 0.0001 | +| loss | -0.0703 | +| n_updates | 142920 | +| policy_gradient_loss | -0.0711 | +| value_loss | 0.000856 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.14 | +| time/ | | +| fps | 309 | +| iterations | 8241 | +| time_elapsed | 27264 | +| total_timesteps | 8438784 | +| train/ | | +| approx_kl | 9.449405 | +| clip_fraction | 0.523 | +| clip_range | 0.2 | +| entropy_loss | -0.382 | +| explained_variance | -1.86 | +| learning_rate | 0.0001 | +| loss | -0.109 | +| n_updates | 142930 | +| policy_gradient_loss | -0.072 | +| value_loss | 0.000431 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.14 | +| time/ | | +| fps | 309 | +| iterations | 8242 | +| time_elapsed | 27267 | +| total_timesteps | 8439808 | +| train/ | | +| approx_kl | 2.6107278 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.352 | +| explained_variance | -1.82 | +| learning_rate | 0.0001 | +| loss | -0.0922 | +| n_updates | 142940 | +| policy_gradient_loss | -0.0663 | +| value_loss | 0.000469 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.139 | +| time/ | | +| fps | 309 | +| iterations | 8243 | +| time_elapsed | 27270 | +| total_timesteps | 8440832 | +| train/ | | +| approx_kl | 2.7265255 | +| clip_fraction | 0.535 | +| clip_range | 0.2 | +| entropy_loss | -0.438 | +| explained_variance | -2.66 | +| learning_rate | 0.0001 | +| loss | -0.0859 | +| n_updates | 142950 | +| policy_gradient_loss | -0.066 | +| value_loss | 0.000435 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.139 | +| time/ | | +| fps | 309 | +| iterations | 8244 | +| time_elapsed | 27273 | +| total_timesteps | 8441856 | +| train/ | | +| approx_kl | 2.467891 | +| clip_fraction | 0.478 | +| clip_range | 0.2 | +| entropy_loss | -0.342 | +| explained_variance | -1.24 | +| learning_rate | 0.0001 | +| loss | -0.0936 | +| n_updates | 142960 | +| policy_gradient_loss | -0.0727 | +| value_loss | 0.000667 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.142 | +| time/ | | +| fps | 309 | +| iterations | 8245 | +| time_elapsed | 27277 | +| total_timesteps | 8442880 | +| train/ | | +| approx_kl | 2.008549 | +| clip_fraction | 0.473 | +| clip_range | 0.2 | +| entropy_loss | -0.351 | +| explained_variance | -1.95 | +| learning_rate | 0.0001 | +| loss | -0.111 | +| n_updates | 142970 | +| policy_gradient_loss | -0.0629 | +| value_loss | 0.000775 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.142 | +| time/ | | +| fps | 309 | +| iterations | 8246 | +| time_elapsed | 27280 | +| total_timesteps | 8443904 | +| train/ | | +| approx_kl | 4.846716 | +| clip_fraction | 0.495 | +| clip_range | 0.2 | +| entropy_loss | -0.376 | +| explained_variance | -3.47 | +| learning_rate | 0.0001 | +| loss | -0.0937 | +| n_updates | 142980 | +| policy_gradient_loss | -0.0708 | +| value_loss | 0.000855 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.147 | +| time/ | | +| fps | 309 | +| iterations | 8247 | +| time_elapsed | 27283 | +| total_timesteps | 8444928 | +| train/ | | +| approx_kl | 2.580662 | +| clip_fraction | 0.529 | +| clip_range | 0.2 | +| entropy_loss | -0.398 | +| explained_variance | -1.7 | +| learning_rate | 0.0001 | +| loss | -0.0841 | +| n_updates | 142990 | +| policy_gradient_loss | -0.0742 | +| value_loss | 0.0004 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.147 | +| time/ | | +| fps | 309 | +| iterations | 8248 | +| time_elapsed | 27287 | +| total_timesteps | 8445952 | +| train/ | | +| approx_kl | 2.3090475 | +| clip_fraction | 0.511 | +| clip_range | 0.2 | +| entropy_loss | -0.381 | +| explained_variance | -1.46 | +| learning_rate | 0.0001 | +| loss | -0.0734 | +| n_updates | 143000 | +| policy_gradient_loss | -0.0632 | +| value_loss | 0.000722 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.142 | +| time/ | | +| fps | 309 | +| iterations | 8249 | +| time_elapsed | 27290 | +| total_timesteps | 8446976 | +| train/ | | +| approx_kl | 2.3396592 | +| clip_fraction | 0.516 | +| clip_range | 0.2 | +| entropy_loss | -0.396 | +| explained_variance | -4.69 | +| learning_rate | 0.0001 | +| loss | -0.0939 | +| n_updates | 143010 | +| policy_gradient_loss | -0.0734 | +| value_loss | 0.000368 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.142 | +| time/ | | +| fps | 309 | +| iterations | 8250 | +| time_elapsed | 27294 | +| total_timesteps | 8448000 | +| train/ | | +| approx_kl | 2.7463784 | +| clip_fraction | 0.501 | +| clip_range | 0.2 | +| entropy_loss | -0.364 | +| explained_variance | -3.74 | +| learning_rate | 0.0001 | +| loss | -0.0809 | +| n_updates | 143020 | +| policy_gradient_loss | -0.072 | +| value_loss | 0.000339 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.142 | +| time/ | | +| fps | 309 | +| iterations | 8251 | +| time_elapsed | 27297 | +| total_timesteps | 8449024 | +| train/ | | +| approx_kl | 2.4459827 | +| clip_fraction | 0.519 | +| clip_range | 0.2 | +| entropy_loss | -0.358 | +| explained_variance | -1.91 | +| learning_rate | 0.0001 | +| loss | -0.0683 | +| n_updates | 143030 | +| policy_gradient_loss | -0.0729 | +| value_loss | 0.000329 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.43e+03 | +| ep_rew_mean | 0.14 | +| time/ | | +| fps | 309 | +| iterations | 8252 | +| time_elapsed | 27301 | +| total_timesteps | 8450048 | +| train/ | | +| approx_kl | 2.9833837 | +| clip_fraction | 0.49 | +| clip_range | 0.2 | +| entropy_loss | -0.386 | +| explained_variance | -3.31 | +| learning_rate | 0.0001 | +| loss | -0.0666 | +| n_updates | 143040 | +| policy_gradient_loss | -0.0632 | +| value_loss | 0.000267 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.43e+03 | +| ep_rew_mean | 0.14 | +| time/ | | +| fps | 309 | +| iterations | 8253 | +| time_elapsed | 27304 | +| total_timesteps | 8451072 | +| train/ | | +| approx_kl | 2.0725214 | +| clip_fraction | 0.492 | +| clip_range | 0.2 | +| entropy_loss | -0.375 | +| explained_variance | -1.15 | +| learning_rate | 0.0001 | +| loss | -0.0744 | +| n_updates | 143050 | +| policy_gradient_loss | -0.0663 | +| value_loss | 0.000412 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.44e+03 | +| ep_rew_mean | 0.135 | +| time/ | | +| fps | 309 | +| iterations | 8254 | +| time_elapsed | 27308 | +| total_timesteps | 8452096 | +| train/ | | +| approx_kl | 2.1042883 | +| clip_fraction | 0.497 | +| clip_range | 0.2 | +| entropy_loss | -0.401 | +| explained_variance | -2.24 | +| learning_rate | 0.0001 | +| loss | -0.0847 | +| n_updates | 143060 | +| policy_gradient_loss | -0.0729 | +| value_loss | 0.000391 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.44e+03 | +| ep_rew_mean | 0.135 | +| time/ | | +| fps | 309 | +| iterations | 8255 | +| time_elapsed | 27311 | +| total_timesteps | 8453120 | +| train/ | | +| approx_kl | 2.6037662 | +| clip_fraction | 0.494 | +| clip_range | 0.2 | +| entropy_loss | -0.365 | +| explained_variance | -5.51 | +| learning_rate | 0.0001 | +| loss | -0.116 | +| n_updates | 143070 | +| policy_gradient_loss | -0.067 | +| value_loss | 0.000403 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.46e+03 | +| ep_rew_mean | 0.133 | +| time/ | | +| fps | 309 | +| iterations | 8256 | +| time_elapsed | 27314 | +| total_timesteps | 8454144 | +| train/ | | +| approx_kl | 2.22823 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.366 | +| explained_variance | -1.24 | +| learning_rate | 0.0001 | +| loss | -0.09 | +| n_updates | 143080 | +| policy_gradient_loss | -0.0683 | +| value_loss | 0.000535 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.46e+03 | +| ep_rew_mean | 0.133 | +| time/ | | +| fps | 309 | +| iterations | 8257 | +| time_elapsed | 27317 | +| total_timesteps | 8455168 | +| train/ | | +| approx_kl | 2.569211 | +| clip_fraction | 0.459 | +| clip_range | 0.2 | +| entropy_loss | -0.355 | +| explained_variance | -1.6 | +| learning_rate | 0.0001 | +| loss | -0.0983 | +| n_updates | 143090 | +| policy_gradient_loss | -0.0579 | +| value_loss | 0.00113 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.46e+03 | +| ep_rew_mean | 0.133 | +| time/ | | +| fps | 309 | +| iterations | 8258 | +| time_elapsed | 27320 | +| total_timesteps | 8456192 | +| train/ | | +| approx_kl | 3.434846 | +| clip_fraction | 0.505 | +| clip_range | 0.2 | +| entropy_loss | -0.351 | +| explained_variance | -4.65 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 143100 | +| policy_gradient_loss | -0.0732 | +| value_loss | 0.00058 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.48e+03 | +| ep_rew_mean | 0.137 | +| time/ | | +| fps | 309 | +| iterations | 8259 | +| time_elapsed | 27324 | +| total_timesteps | 8457216 | +| train/ | | +| approx_kl | 1.7186701 | +| clip_fraction | 0.515 | +| clip_range | 0.2 | +| entropy_loss | -0.386 | +| explained_variance | -2.86 | +| learning_rate | 0.0001 | +| loss | -0.0674 | +| n_updates | 143110 | +| policy_gradient_loss | -0.0768 | +| value_loss | 0.000924 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.48e+03 | +| ep_rew_mean | 0.137 | +| time/ | | +| fps | 309 | +| iterations | 8260 | +| time_elapsed | 27327 | +| total_timesteps | 8458240 | +| train/ | | +| approx_kl | 3.1667833 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.332 | +| explained_variance | -3.16 | +| learning_rate | 0.0001 | +| loss | -0.0912 | +| n_updates | 143120 | +| policy_gradient_loss | -0.0722 | +| value_loss | 0.000294 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.48e+03 | +| ep_rew_mean | 0.137 | +| time/ | | +| fps | 309 | +| iterations | 8261 | +| time_elapsed | 27330 | +| total_timesteps | 8459264 | +| train/ | | +| approx_kl | 2.5075614 | +| clip_fraction | 0.489 | +| clip_range | 0.2 | +| entropy_loss | -0.377 | +| explained_variance | -2.9 | +| learning_rate | 0.0001 | +| loss | -0.0927 | +| n_updates | 143130 | +| policy_gradient_loss | -0.0684 | +| value_loss | 0.00036 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.5e+03 | +| ep_rew_mean | 0.129 | +| time/ | | +| fps | 309 | +| iterations | 8262 | +| time_elapsed | 27333 | +| total_timesteps | 8460288 | +| train/ | | +| approx_kl | 3.1644945 | +| clip_fraction | 0.498 | +| clip_range | 0.2 | +| entropy_loss | -0.392 | +| explained_variance | -6.66 | +| learning_rate | 0.0001 | +| loss | -0.112 | +| n_updates | 143140 | +| policy_gradient_loss | -0.0782 | +| value_loss | 0.000226 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.51e+03 | +| ep_rew_mean | 0.133 | +| time/ | | +| fps | 309 | +| iterations | 8263 | +| time_elapsed | 27336 | +| total_timesteps | 8461312 | +| train/ | | +| approx_kl | 2.5113919 | +| clip_fraction | 0.498 | +| clip_range | 0.2 | +| entropy_loss | -0.357 | +| explained_variance | -1.11 | +| learning_rate | 0.0001 | +| loss | -0.0952 | +| n_updates | 143150 | +| policy_gradient_loss | -0.0717 | +| value_loss | 0.000557 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.51e+03 | +| ep_rew_mean | 0.133 | +| time/ | | +| fps | 309 | +| iterations | 8264 | +| time_elapsed | 27339 | +| total_timesteps | 8462336 | +| train/ | | +| approx_kl | 3.0128026 | +| clip_fraction | 0.508 | +| clip_range | 0.2 | +| entropy_loss | -0.363 | +| explained_variance | -2.35 | +| learning_rate | 0.0001 | +| loss | -0.116 | +| n_updates | 143160 | +| policy_gradient_loss | -0.0717 | +| value_loss | 0.000612 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.51e+03 | +| ep_rew_mean | 0.133 | +| time/ | | +| fps | 309 | +| iterations | 8265 | +| time_elapsed | 27343 | +| total_timesteps | 8463360 | +| train/ | | +| approx_kl | 12.051306 | +| clip_fraction | 0.457 | +| clip_range | 0.2 | +| entropy_loss | -0.33 | +| explained_variance | -5.15 | +| learning_rate | 0.0001 | +| loss | -0.0968 | +| n_updates | 143170 | +| policy_gradient_loss | -0.0708 | +| value_loss | 0.000438 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.52e+03 | +| ep_rew_mean | 0.133 | +| time/ | | +| fps | 309 | +| iterations | 8266 | +| time_elapsed | 27346 | +| total_timesteps | 8464384 | +| train/ | | +| approx_kl | 2.8035955 | +| clip_fraction | 0.495 | +| clip_range | 0.2 | +| entropy_loss | -0.354 | +| explained_variance | -1.23 | +| learning_rate | 0.0001 | +| loss | -0.0646 | +| n_updates | 143180 | +| policy_gradient_loss | -0.0701 | +| value_loss | 0.000621 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.52e+03 | +| ep_rew_mean | 0.133 | +| time/ | | +| fps | 309 | +| iterations | 8267 | +| time_elapsed | 27350 | +| total_timesteps | 8465408 | +| train/ | | +| approx_kl | 2.7095666 | +| clip_fraction | 0.456 | +| clip_range | 0.2 | +| entropy_loss | -0.307 | +| explained_variance | -7.72 | +| learning_rate | 0.0001 | +| loss | -0.108 | +| n_updates | 143190 | +| policy_gradient_loss | -0.0666 | +| value_loss | 0.000622 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.53e+03 | +| ep_rew_mean | 0.132 | +| time/ | | +| fps | 309 | +| iterations | 8268 | +| time_elapsed | 27353 | +| total_timesteps | 8466432 | +| train/ | | +| approx_kl | 2.8364959 | +| clip_fraction | 0.47 | +| clip_range | 0.2 | +| entropy_loss | -0.343 | +| explained_variance | -4.1 | +| learning_rate | 0.0001 | +| loss | -0.0978 | +| n_updates | 143200 | +| policy_gradient_loss | -0.0707 | +| value_loss | 0.000441 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.53e+03 | +| ep_rew_mean | 0.132 | +| time/ | | +| fps | 309 | +| iterations | 8269 | +| time_elapsed | 27357 | +| total_timesteps | 8467456 | +| train/ | | +| approx_kl | 2.275307 | +| clip_fraction | 0.464 | +| clip_range | 0.2 | +| entropy_loss | -0.344 | +| explained_variance | -1.22 | +| learning_rate | 0.0001 | +| loss | -0.0784 | +| n_updates | 143210 | +| policy_gradient_loss | -0.0653 | +| value_loss | 0.000529 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.53e+03 | +| ep_rew_mean | 0.132 | +| time/ | | +| fps | 309 | +| iterations | 8270 | +| time_elapsed | 27360 | +| total_timesteps | 8468480 | +| train/ | | +| approx_kl | 3.4632826 | +| clip_fraction | 0.511 | +| clip_range | 0.2 | +| entropy_loss | -0.355 | +| explained_variance | -3.19 | +| learning_rate | 0.0001 | +| loss | -0.0815 | +| n_updates | 143220 | +| policy_gradient_loss | -0.0744 | +| value_loss | 0.000347 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.55e+03 | +| ep_rew_mean | 0.13 | +| time/ | | +| fps | 309 | +| iterations | 8271 | +| time_elapsed | 27364 | +| total_timesteps | 8469504 | +| train/ | | +| approx_kl | 2.4500027 | +| clip_fraction | 0.488 | +| clip_range | 0.2 | +| entropy_loss | -0.375 | +| explained_variance | -1.83 | +| learning_rate | 0.0001 | +| loss | -0.0989 | +| n_updates | 143230 | +| policy_gradient_loss | -0.066 | +| value_loss | 0.000227 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.55e+03 | +| ep_rew_mean | 0.131 | +| time/ | | +| fps | 309 | +| iterations | 8272 | +| time_elapsed | 27367 | +| total_timesteps | 8470528 | +| train/ | | +| approx_kl | 2.332686 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.367 | +| explained_variance | -3.79 | +| learning_rate | 0.0001 | +| loss | -0.0809 | +| n_updates | 143240 | +| policy_gradient_loss | -0.0699 | +| value_loss | 0.000173 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.54e+03 | +| ep_rew_mean | 0.138 | +| time/ | | +| fps | 309 | +| iterations | 8273 | +| time_elapsed | 27371 | +| total_timesteps | 8471552 | +| train/ | | +| approx_kl | 2.9160056 | +| clip_fraction | 0.514 | +| clip_range | 0.2 | +| entropy_loss | -0.395 | +| explained_variance | -0.359 | +| learning_rate | 0.0001 | +| loss | -0.0731 | +| n_updates | 143250 | +| policy_gradient_loss | -0.0654 | +| value_loss | 0.000578 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.54e+03 | +| ep_rew_mean | 0.138 | +| time/ | | +| fps | 309 | +| iterations | 8274 | +| time_elapsed | 27374 | +| total_timesteps | 8472576 | +| train/ | | +| approx_kl | 2.6803164 | +| clip_fraction | 0.511 | +| clip_range | 0.2 | +| entropy_loss | -0.384 | +| explained_variance | -0.809 | +| learning_rate | 0.0001 | +| loss | -0.1 | +| n_updates | 143260 | +| policy_gradient_loss | -0.073 | +| value_loss | 0.00107 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.54e+03 | +| ep_rew_mean | 0.138 | +| time/ | | +| fps | 309 | +| iterations | 8275 | +| time_elapsed | 27377 | +| total_timesteps | 8473600 | +| train/ | | +| approx_kl | 1.839923 | +| clip_fraction | 0.482 | +| clip_range | 0.2 | +| entropy_loss | -0.389 | +| explained_variance | -22.2 | +| learning_rate | 0.0001 | +| loss | -0.0987 | +| n_updates | 143270 | +| policy_gradient_loss | -0.0733 | +| value_loss | 0.000569 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.55e+03 | +| ep_rew_mean | 0.136 | +| time/ | | +| fps | 309 | +| iterations | 8276 | +| time_elapsed | 27380 | +| total_timesteps | 8474624 | +| train/ | | +| approx_kl | 3.855327 | +| clip_fraction | 0.486 | +| clip_range | 0.2 | +| entropy_loss | -0.356 | +| explained_variance | -2.76 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 143280 | +| policy_gradient_loss | -0.0704 | +| value_loss | 0.000448 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.56e+03 | +| ep_rew_mean | 0.14 | +| time/ | | +| fps | 309 | +| iterations | 8277 | +| time_elapsed | 27384 | +| total_timesteps | 8475648 | +| train/ | | +| approx_kl | 2.2934127 | +| clip_fraction | 0.468 | +| clip_range | 0.2 | +| entropy_loss | -0.298 | +| explained_variance | -1.64 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 143290 | +| policy_gradient_loss | -0.0613 | +| value_loss | 0.000811 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.56e+03 | +| ep_rew_mean | 0.14 | +| time/ | | +| fps | 309 | +| iterations | 8278 | +| time_elapsed | 27387 | +| total_timesteps | 8476672 | +| train/ | | +| approx_kl | 2.8481312 | +| clip_fraction | 0.459 | +| clip_range | 0.2 | +| entropy_loss | -0.292 | +| explained_variance | -2.07 | +| learning_rate | 0.0001 | +| loss | -0.0835 | +| n_updates | 143300 | +| policy_gradient_loss | -0.0666 | +| value_loss | 0.000966 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.56e+03 | +| ep_rew_mean | 0.14 | +| time/ | | +| fps | 309 | +| iterations | 8279 | +| time_elapsed | 27390 | +| total_timesteps | 8477696 | +| train/ | | +| approx_kl | 3.1185536 | +| clip_fraction | 0.489 | +| clip_range | 0.2 | +| entropy_loss | -0.33 | +| explained_variance | -5.81 | +| learning_rate | 0.0001 | +| loss | -0.0815 | +| n_updates | 143310 | +| policy_gradient_loss | -0.0645 | +| value_loss | 0.00034 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.58e+03 | +| ep_rew_mean | 0.141 | +| time/ | | +| fps | 309 | +| iterations | 8280 | +| time_elapsed | 27393 | +| total_timesteps | 8478720 | +| train/ | | +| approx_kl | 2.3783565 | +| clip_fraction | 0.52 | +| clip_range | 0.2 | +| entropy_loss | -0.368 | +| explained_variance | -0.828 | +| learning_rate | 0.0001 | +| loss | -0.0988 | +| n_updates | 143320 | +| policy_gradient_loss | -0.0701 | +| value_loss | 0.000374 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.58e+03 | +| ep_rew_mean | 0.141 | +| time/ | | +| fps | 309 | +| iterations | 8281 | +| time_elapsed | 27397 | +| total_timesteps | 8479744 | +| train/ | | +| approx_kl | 2.7422562 | +| clip_fraction | 0.447 | +| clip_range | 0.2 | +| entropy_loss | -0.312 | +| explained_variance | -2.26 | +| learning_rate | 0.0001 | +| loss | -0.0855 | +| n_updates | 143330 | +| policy_gradient_loss | -0.0494 | +| value_loss | 0.000665 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | 0.14 | +| time/ | | +| fps | 309 | +| iterations | 8282 | +| time_elapsed | 27400 | +| total_timesteps | 8480768 | +| train/ | | +| approx_kl | 3.1162665 | +| clip_fraction | 0.484 | +| clip_range | 0.2 | +| entropy_loss | -0.335 | +| explained_variance | -3.63 | +| learning_rate | 0.0001 | +| loss | -0.0844 | +| n_updates | 143340 | +| policy_gradient_loss | -0.0726 | +| value_loss | 0.000488 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | 0.14 | +| time/ | | +| fps | 309 | +| iterations | 8283 | +| time_elapsed | 27403 | +| total_timesteps | 8481792 | +| train/ | | +| approx_kl | 2.5610492 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.374 | +| explained_variance | -1.62 | +| learning_rate | 0.0001 | +| loss | -0.094 | +| n_updates | 143350 | +| policy_gradient_loss | -0.0657 | +| value_loss | 0.000392 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | 0.14 | +| time/ | | +| fps | 309 | +| iterations | 8284 | +| time_elapsed | 27407 | +| total_timesteps | 8482816 | +| train/ | | +| approx_kl | 2.4085631 | +| clip_fraction | 0.504 | +| clip_range | 0.2 | +| entropy_loss | -0.375 | +| explained_variance | -2.24 | +| learning_rate | 0.0001 | +| loss | -0.0976 | +| n_updates | 143360 | +| policy_gradient_loss | -0.0725 | +| value_loss | 0.000514 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | 0.142 | +| time/ | | +| fps | 309 | +| iterations | 8285 | +| time_elapsed | 27410 | +| total_timesteps | 8483840 | +| train/ | | +| approx_kl | 2.682615 | +| clip_fraction | 0.52 | +| clip_range | 0.2 | +| entropy_loss | -0.392 | +| explained_variance | -2.59 | +| learning_rate | 0.0001 | +| loss | -0.0931 | +| n_updates | 143370 | +| policy_gradient_loss | -0.0545 | +| value_loss | 0.000576 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | 0.142 | +| time/ | | +| fps | 309 | +| iterations | 8286 | +| time_elapsed | 27413 | +| total_timesteps | 8484864 | +| train/ | | +| approx_kl | 5.104332 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.375 | +| explained_variance | -1.56 | +| learning_rate | 0.0001 | +| loss | -0.0791 | +| n_updates | 143380 | +| policy_gradient_loss | -0.065 | +| value_loss | 0.00062 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | 0.141 | +| time/ | | +| fps | 309 | +| iterations | 8287 | +| time_elapsed | 27417 | +| total_timesteps | 8485888 | +| train/ | | +| approx_kl | 2.3629959 | +| clip_fraction | 0.484 | +| clip_range | 0.2 | +| entropy_loss | -0.342 | +| explained_variance | -5.37 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 143390 | +| policy_gradient_loss | -0.0744 | +| value_loss | 0.000629 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | 0.141 | +| time/ | | +| fps | 309 | +| iterations | 8288 | +| time_elapsed | 27420 | +| total_timesteps | 8486912 | +| train/ | | +| approx_kl | 2.5237668 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.325 | +| explained_variance | -3.21 | +| learning_rate | 0.0001 | +| loss | -0.0831 | +| n_updates | 143400 | +| policy_gradient_loss | -0.0682 | +| value_loss | 0.000651 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.62e+03 | +| ep_rew_mean | 0.144 | +| time/ | | +| fps | 309 | +| iterations | 8289 | +| time_elapsed | 27423 | +| total_timesteps | 8487936 | +| train/ | | +| approx_kl | 3.176853 | +| clip_fraction | 0.52 | +| clip_range | 0.2 | +| entropy_loss | -0.398 | +| explained_variance | -1.93 | +| learning_rate | 0.0001 | +| loss | -0.0481 | +| n_updates | 143410 | +| policy_gradient_loss | -0.065 | +| value_loss | 0.000652 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.62e+03 | +| ep_rew_mean | 0.144 | +| time/ | | +| fps | 309 | +| iterations | 8290 | +| time_elapsed | 27427 | +| total_timesteps | 8488960 | +| train/ | | +| approx_kl | 3.6032648 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.368 | +| explained_variance | -1.56 | +| learning_rate | 0.0001 | +| loss | -0.0714 | +| n_updates | 143420 | +| policy_gradient_loss | -0.0694 | +| value_loss | 0.000704 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.63e+03 | +| ep_rew_mean | 0.147 | +| time/ | | +| fps | 309 | +| iterations | 8291 | +| time_elapsed | 27430 | +| total_timesteps | 8489984 | +| train/ | | +| approx_kl | 3.0365849 | +| clip_fraction | 0.488 | +| clip_range | 0.2 | +| entropy_loss | -0.357 | +| explained_variance | -4 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 143430 | +| policy_gradient_loss | -0.0751 | +| value_loss | 0.00049 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.63e+03 | +| ep_rew_mean | 0.147 | +| time/ | | +| fps | 309 | +| iterations | 8292 | +| time_elapsed | 27433 | +| total_timesteps | 8491008 | +| train/ | | +| approx_kl | 10.695516 | +| clip_fraction | 0.464 | +| clip_range | 0.2 | +| entropy_loss | -0.347 | +| explained_variance | -3.02 | +| learning_rate | 0.0001 | +| loss | -0.0634 | +| n_updates | 143440 | +| policy_gradient_loss | -0.0563 | +| value_loss | 0.000386 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.63e+03 | +| ep_rew_mean | 0.147 | +| time/ | | +| fps | 309 | +| iterations | 8293 | +| time_elapsed | 27437 | +| total_timesteps | 8492032 | +| train/ | | +| approx_kl | 3.150383 | +| clip_fraction | 0.504 | +| clip_range | 0.2 | +| entropy_loss | -0.349 | +| explained_variance | -2.56 | +| learning_rate | 0.0001 | +| loss | -0.106 | +| n_updates | 143450 | +| policy_gradient_loss | -0.0734 | +| value_loss | 0.000392 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.63e+03 | +| ep_rew_mean | 0.147 | +| time/ | | +| fps | 309 | +| iterations | 8294 | +| time_elapsed | 27440 | +| total_timesteps | 8493056 | +| train/ | | +| approx_kl | 3.952383 | +| clip_fraction | 0.506 | +| clip_range | 0.2 | +| entropy_loss | -0.398 | +| explained_variance | -1.15 | +| learning_rate | 0.0001 | +| loss | -0.0931 | +| n_updates | 143460 | +| policy_gradient_loss | -0.0719 | +| value_loss | 0.000503 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.65e+03 | +| ep_rew_mean | 0.149 | +| time/ | | +| fps | 309 | +| iterations | 8295 | +| time_elapsed | 27443 | +| total_timesteps | 8494080 | +| train/ | | +| approx_kl | 2.177067 | +| clip_fraction | 0.482 | +| clip_range | 0.2 | +| entropy_loss | -0.364 | +| explained_variance | -6.74 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 143470 | +| policy_gradient_loss | -0.0683 | +| value_loss | 0.000378 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.65e+03 | +| ep_rew_mean | 0.149 | +| time/ | | +| fps | 309 | +| iterations | 8296 | +| time_elapsed | 27446 | +| total_timesteps | 8495104 | +| train/ | | +| approx_kl | 2.5260057 | +| clip_fraction | 0.527 | +| clip_range | 0.2 | +| entropy_loss | -0.393 | +| explained_variance | -0.577 | +| learning_rate | 0.0001 | +| loss | -0.0882 | +| n_updates | 143480 | +| policy_gradient_loss | -0.0686 | +| value_loss | 0.000682 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.65e+03 | +| ep_rew_mean | 0.149 | +| time/ | | +| fps | 309 | +| iterations | 8297 | +| time_elapsed | 27449 | +| total_timesteps | 8496128 | +| train/ | | +| approx_kl | 2.1631546 | +| clip_fraction | 0.503 | +| clip_range | 0.2 | +| entropy_loss | -0.356 | +| explained_variance | -4.83 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 143490 | +| policy_gradient_loss | -0.0711 | +| value_loss | 0.000426 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.151 | +| time/ | | +| fps | 309 | +| iterations | 8298 | +| time_elapsed | 27452 | +| total_timesteps | 8497152 | +| train/ | | +| approx_kl | 2.2158902 | +| clip_fraction | 0.507 | +| clip_range | 0.2 | +| entropy_loss | -0.397 | +| explained_variance | -2.32 | +| learning_rate | 0.0001 | +| loss | -0.112 | +| n_updates | 143500 | +| policy_gradient_loss | -0.0668 | +| value_loss | 0.000508 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.155 | +| time/ | | +| fps | 309 | +| iterations | 8299 | +| time_elapsed | 27456 | +| total_timesteps | 8498176 | +| train/ | | +| approx_kl | 2.9492106 | +| clip_fraction | 0.468 | +| clip_range | 0.2 | +| entropy_loss | -0.329 | +| explained_variance | -1.97 | +| learning_rate | 0.0001 | +| loss | -0.0875 | +| n_updates | 143510 | +| policy_gradient_loss | -0.0664 | +| value_loss | 0.00059 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.155 | +| time/ | | +| fps | 309 | +| iterations | 8300 | +| time_elapsed | 27459 | +| total_timesteps | 8499200 | +| train/ | | +| approx_kl | 3.1399689 | +| clip_fraction | 0.519 | +| clip_range | 0.2 | +| entropy_loss | -0.394 | +| explained_variance | -1.06 | +| learning_rate | 0.0001 | +| loss | -0.0922 | +| n_updates | 143520 | +| policy_gradient_loss | -0.0713 | +| value_loss | 0.00057 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.155 | +| time/ | | +| fps | 309 | +| iterations | 8301 | +| time_elapsed | 27462 | +| total_timesteps | 8500224 | +| train/ | | +| approx_kl | 2.3948445 | +| clip_fraction | 0.465 | +| clip_range | 0.2 | +| entropy_loss | -0.333 | +| explained_variance | -14.4 | +| learning_rate | 0.0001 | +| loss | -0.0439 | +| n_updates | 143530 | +| policy_gradient_loss | -0.0668 | +| value_loss | 0.000326 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.158 | +| time/ | | +| fps | 309 | +| iterations | 8302 | +| time_elapsed | 27466 | +| total_timesteps | 8501248 | +| train/ | | +| approx_kl | 2.5799565 | +| clip_fraction | 0.557 | +| clip_range | 0.2 | +| entropy_loss | -0.469 | +| explained_variance | -0.43 | +| learning_rate | 0.0001 | +| loss | -0.0945 | +| n_updates | 143540 | +| policy_gradient_loss | -0.0654 | +| value_loss | 0.000458 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.158 | +| time/ | | +| fps | 309 | +| iterations | 8303 | +| time_elapsed | 27469 | +| total_timesteps | 8502272 | +| train/ | | +| approx_kl | 4.370715 | +| clip_fraction | 0.511 | +| clip_range | 0.2 | +| entropy_loss | -0.39 | +| explained_variance | -1.97 | +| learning_rate | 0.0001 | +| loss | -0.109 | +| n_updates | 143550 | +| policy_gradient_loss | -0.0723 | +| value_loss | 0.000646 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.158 | +| time/ | | +| fps | 309 | +| iterations | 8304 | +| time_elapsed | 27473 | +| total_timesteps | 8503296 | +| train/ | | +| approx_kl | 1.964196 | +| clip_fraction | 0.485 | +| clip_range | 0.2 | +| entropy_loss | -0.369 | +| explained_variance | -2.98 | +| learning_rate | 0.0001 | +| loss | -0.1 | +| n_updates | 143560 | +| policy_gradient_loss | -0.0672 | +| value_loss | 0.000402 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.159 | +| time/ | | +| fps | 309 | +| iterations | 8305 | +| time_elapsed | 27476 | +| total_timesteps | 8504320 | +| train/ | | +| approx_kl | 1.8542266 | +| clip_fraction | 0.496 | +| clip_range | 0.2 | +| entropy_loss | -0.403 | +| explained_variance | -1.5 | +| learning_rate | 0.0001 | +| loss | -0.0785 | +| n_updates | 143570 | +| policy_gradient_loss | -0.0676 | +| value_loss | 0.000357 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.159 | +| time/ | | +| fps | 309 | +| iterations | 8306 | +| time_elapsed | 27480 | +| total_timesteps | 8505344 | +| train/ | | +| approx_kl | 2.3859162 | +| clip_fraction | 0.488 | +| clip_range | 0.2 | +| entropy_loss | -0.369 | +| explained_variance | -1.19 | +| learning_rate | 0.0001 | +| loss | -0.0659 | +| n_updates | 143580 | +| policy_gradient_loss | -0.0656 | +| value_loss | 0.000825 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.162 | +| time/ | | +| fps | 309 | +| iterations | 8307 | +| time_elapsed | 27483 | +| total_timesteps | 8506368 | +| train/ | | +| approx_kl | 2.2261052 | +| clip_fraction | 0.503 | +| clip_range | 0.2 | +| entropy_loss | -0.356 | +| explained_variance | -4.28 | +| learning_rate | 0.0001 | +| loss | -0.0627 | +| n_updates | 143590 | +| policy_gradient_loss | -0.0691 | +| value_loss | 0.000776 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.162 | +| time/ | | +| fps | 309 | +| iterations | 8308 | +| time_elapsed | 27487 | +| total_timesteps | 8507392 | +| train/ | | +| approx_kl | 2.9844534 | +| clip_fraction | 0.514 | +| clip_range | 0.2 | +| entropy_loss | -0.388 | +| explained_variance | -2.63 | +| learning_rate | 0.0001 | +| loss | -0.0778 | +| n_updates | 143600 | +| policy_gradient_loss | -0.0664 | +| value_loss | 0.000379 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.16 | +| time/ | | +| fps | 309 | +| iterations | 8309 | +| time_elapsed | 27490 | +| total_timesteps | 8508416 | +| train/ | | +| approx_kl | 2.2889667 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.352 | +| explained_variance | -1.22 | +| learning_rate | 0.0001 | +| loss | -0.04 | +| n_updates | 143610 | +| policy_gradient_loss | -0.0708 | +| value_loss | 0.000843 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.16 | +| time/ | | +| fps | 309 | +| iterations | 8310 | +| time_elapsed | 27493 | +| total_timesteps | 8509440 | +| train/ | | +| approx_kl | 1.8815252 | +| clip_fraction | 0.445 | +| clip_range | 0.2 | +| entropy_loss | -0.362 | +| explained_variance | -4.14 | +| learning_rate | 0.0001 | +| loss | -0.0669 | +| n_updates | 143620 | +| policy_gradient_loss | -0.0636 | +| value_loss | 0.00033 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.16 | +| time/ | | +| fps | 309 | +| iterations | 8311 | +| time_elapsed | 27496 | +| total_timesteps | 8510464 | +| train/ | | +| approx_kl | 3.455595 | +| clip_fraction | 0.492 | +| clip_range | 0.2 | +| entropy_loss | -0.368 | +| explained_variance | -1.76 | +| learning_rate | 0.0001 | +| loss | -0.0482 | +| n_updates | 143630 | +| policy_gradient_loss | -0.0636 | +| value_loss | 0.000354 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.162 | +| time/ | | +| fps | 309 | +| iterations | 8312 | +| time_elapsed | 27500 | +| total_timesteps | 8511488 | +| train/ | | +| approx_kl | 2.189474 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.347 | +| explained_variance | -6 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 143640 | +| policy_gradient_loss | -0.0803 | +| value_loss | 0.000433 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.162 | +| time/ | | +| fps | 309 | +| iterations | 8313 | +| time_elapsed | 27503 | +| total_timesteps | 8512512 | +| train/ | | +| approx_kl | 17.691006 | +| clip_fraction | 0.488 | +| clip_range | 0.2 | +| entropy_loss | -0.356 | +| explained_variance | -5.79 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 143650 | +| policy_gradient_loss | -0.0749 | +| value_loss | 0.000308 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.162 | +| time/ | | +| fps | 309 | +| iterations | 8314 | +| time_elapsed | 27506 | +| total_timesteps | 8513536 | +| train/ | | +| approx_kl | 1.8725703 | +| clip_fraction | 0.448 | +| clip_range | 0.2 | +| entropy_loss | -0.361 | +| explained_variance | -2.04 | +| learning_rate | 0.0001 | +| loss | -0.0902 | +| n_updates | 143660 | +| policy_gradient_loss | -0.0629 | +| value_loss | 0.000719 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.161 | +| time/ | | +| fps | 309 | +| iterations | 8315 | +| time_elapsed | 27510 | +| total_timesteps | 8514560 | +| train/ | | +| approx_kl | 3.2811646 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.354 | +| explained_variance | -3.94 | +| learning_rate | 0.0001 | +| loss | -0.088 | +| n_updates | 143670 | +| policy_gradient_loss | -0.0751 | +| value_loss | 0.000395 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.161 | +| time/ | | +| fps | 309 | +| iterations | 8316 | +| time_elapsed | 27513 | +| total_timesteps | 8515584 | +| train/ | | +| approx_kl | 2.5915775 | +| clip_fraction | 0.458 | +| clip_range | 0.2 | +| entropy_loss | -0.361 | +| explained_variance | -0.875 | +| learning_rate | 0.0001 | +| loss | -0.0903 | +| n_updates | 143680 | +| policy_gradient_loss | -0.064 | +| value_loss | 0.00041 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.166 | +| time/ | | +| fps | 309 | +| iterations | 8317 | +| time_elapsed | 27516 | +| total_timesteps | 8516608 | +| train/ | | +| approx_kl | 2.4332197 | +| clip_fraction | 0.498 | +| clip_range | 0.2 | +| entropy_loss | -0.378 | +| explained_variance | -2.04 | +| learning_rate | 0.0001 | +| loss | -0.0603 | +| n_updates | 143690 | +| policy_gradient_loss | -0.0629 | +| value_loss | 0.000767 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.166 | +| time/ | | +| fps | 309 | +| iterations | 8318 | +| time_elapsed | 27519 | +| total_timesteps | 8517632 | +| train/ | | +| approx_kl | 2.5837257 | +| clip_fraction | 0.463 | +| clip_range | 0.2 | +| entropy_loss | -0.31 | +| explained_variance | -1.31 | +| learning_rate | 0.0001 | +| loss | -0.109 | +| n_updates | 143700 | +| policy_gradient_loss | -0.0678 | +| value_loss | 0.00104 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.166 | +| time/ | | +| fps | 309 | +| iterations | 8319 | +| time_elapsed | 27523 | +| total_timesteps | 8518656 | +| train/ | | +| approx_kl | 2.8067513 | +| clip_fraction | 0.493 | +| clip_range | 0.2 | +| entropy_loss | -0.358 | +| explained_variance | -10.7 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 143710 | +| policy_gradient_loss | -0.076 | +| value_loss | 0.00043 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.8e+03 | +| ep_rew_mean | 0.17 | +| time/ | | +| fps | 309 | +| iterations | 8320 | +| time_elapsed | 27526 | +| total_timesteps | 8519680 | +| train/ | | +| approx_kl | 2.4125886 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.333 | +| explained_variance | -2.71 | +| learning_rate | 0.0001 | +| loss | -0.0746 | +| n_updates | 143720 | +| policy_gradient_loss | -0.0694 | +| value_loss | 0.000403 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.8e+03 | +| ep_rew_mean | 0.17 | +| time/ | | +| fps | 309 | +| iterations | 8321 | +| time_elapsed | 27529 | +| total_timesteps | 8520704 | +| train/ | | +| approx_kl | 3.5398762 | +| clip_fraction | 0.472 | +| clip_range | 0.2 | +| entropy_loss | -0.357 | +| explained_variance | -1.6 | +| learning_rate | 0.0001 | +| loss | -0.0681 | +| n_updates | 143730 | +| policy_gradient_loss | -0.0654 | +| value_loss | 0.000644 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.8e+03 | +| ep_rew_mean | 0.168 | +| time/ | | +| fps | 309 | +| iterations | 8322 | +| time_elapsed | 27533 | +| total_timesteps | 8521728 | +| train/ | | +| approx_kl | 2.29726 | +| clip_fraction | 0.507 | +| clip_range | 0.2 | +| entropy_loss | -0.378 | +| explained_variance | -2.79 | +| learning_rate | 0.0001 | +| loss | -0.0632 | +| n_updates | 143740 | +| policy_gradient_loss | -0.0774 | +| value_loss | 0.000439 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.8e+03 | +| ep_rew_mean | 0.168 | +| time/ | | +| fps | 309 | +| iterations | 8323 | +| time_elapsed | 27536 | +| total_timesteps | 8522752 | +| train/ | | +| approx_kl | 2.3830223 | +| clip_fraction | 0.482 | +| clip_range | 0.2 | +| entropy_loss | -0.341 | +| explained_variance | -3.34 | +| learning_rate | 0.0001 | +| loss | -0.0937 | +| n_updates | 143750 | +| policy_gradient_loss | -0.0658 | +| value_loss | 0.000337 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.81e+03 | +| ep_rew_mean | 0.165 | +| time/ | | +| fps | 309 | +| iterations | 8324 | +| time_elapsed | 27539 | +| total_timesteps | 8523776 | +| train/ | | +| approx_kl | 1.9197477 | +| clip_fraction | 0.47 | +| clip_range | 0.2 | +| entropy_loss | -0.386 | +| explained_variance | -1.97 | +| learning_rate | 0.0001 | +| loss | -0.0913 | +| n_updates | 143760 | +| policy_gradient_loss | -0.062 | +| value_loss | 0.000194 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.81e+03 | +| ep_rew_mean | 0.165 | +| time/ | | +| fps | 309 | +| iterations | 8325 | +| time_elapsed | 27543 | +| total_timesteps | 8524800 | +| train/ | | +| approx_kl | 2.5254664 | +| clip_fraction | 0.415 | +| clip_range | 0.2 | +| entropy_loss | -0.275 | +| explained_variance | -2.71 | +| learning_rate | 0.0001 | +| loss | -0.0879 | +| n_updates | 143770 | +| policy_gradient_loss | -0.0627 | +| value_loss | 0.000523 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.81e+03 | +| ep_rew_mean | 0.165 | +| time/ | | +| fps | 309 | +| iterations | 8326 | +| time_elapsed | 27546 | +| total_timesteps | 8525824 | +| train/ | | +| approx_kl | 2.488721 | +| clip_fraction | 0.496 | +| clip_range | 0.2 | +| entropy_loss | -0.35 | +| explained_variance | -4.35 | +| learning_rate | 0.0001 | +| loss | -0.0731 | +| n_updates | 143780 | +| policy_gradient_loss | -0.0715 | +| value_loss | 0.000655 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.164 | +| time/ | | +| fps | 309 | +| iterations | 8327 | +| time_elapsed | 27550 | +| total_timesteps | 8526848 | +| train/ | | +| approx_kl | 1.8607616 | +| clip_fraction | 0.467 | +| clip_range | 0.2 | +| entropy_loss | -0.318 | +| explained_variance | -5.24 | +| learning_rate | 0.0001 | +| loss | -0.11 | +| n_updates | 143790 | +| policy_gradient_loss | -0.0731 | +| value_loss | 0.00051 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.164 | +| time/ | | +| fps | 309 | +| iterations | 8328 | +| time_elapsed | 27553 | +| total_timesteps | 8527872 | +| train/ | | +| approx_kl | 3.1353645 | +| clip_fraction | 0.444 | +| clip_range | 0.2 | +| entropy_loss | -0.292 | +| explained_variance | -1.84 | +| learning_rate | 0.0001 | +| loss | -0.0939 | +| n_updates | 143800 | +| policy_gradient_loss | -0.0645 | +| value_loss | 0.00054 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.164 | +| time/ | | +| fps | 309 | +| iterations | 8329 | +| time_elapsed | 27556 | +| total_timesteps | 8528896 | +| train/ | | +| approx_kl | 2.5814233 | +| clip_fraction | 0.477 | +| clip_range | 0.2 | +| entropy_loss | -0.333 | +| explained_variance | -1.97 | +| learning_rate | 0.0001 | +| loss | -0.0772 | +| n_updates | 143810 | +| policy_gradient_loss | -0.0708 | +| value_loss | 0.000527 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.165 | +| time/ | | +| fps | 309 | +| iterations | 8330 | +| time_elapsed | 27559 | +| total_timesteps | 8529920 | +| train/ | | +| approx_kl | 2.3599753 | +| clip_fraction | 0.523 | +| clip_range | 0.2 | +| entropy_loss | -0.418 | +| explained_variance | -4.16 | +| learning_rate | 0.0001 | +| loss | -0.107 | +| n_updates | 143820 | +| policy_gradient_loss | -0.0737 | +| value_loss | 0.000487 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.165 | +| time/ | | +| fps | 309 | +| iterations | 8331 | +| time_elapsed | 27562 | +| total_timesteps | 8530944 | +| train/ | | +| approx_kl | 3.147459 | +| clip_fraction | 0.491 | +| clip_range | 0.2 | +| entropy_loss | -0.335 | +| explained_variance | -1.94 | +| learning_rate | 0.0001 | +| loss | -0.0968 | +| n_updates | 143830 | +| policy_gradient_loss | -0.0719 | +| value_loss | 0.000701 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.165 | +| time/ | | +| fps | 309 | +| iterations | 8332 | +| time_elapsed | 27565 | +| total_timesteps | 8531968 | +| train/ | | +| approx_kl | 4.117743 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.38 | +| explained_variance | -1.95 | +| learning_rate | 0.0001 | +| loss | -0.0965 | +| n_updates | 143840 | +| policy_gradient_loss | -0.06 | +| value_loss | 0.000678 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.169 | +| time/ | | +| fps | 309 | +| iterations | 8333 | +| time_elapsed | 27569 | +| total_timesteps | 8532992 | +| train/ | | +| approx_kl | 2.258387 | +| clip_fraction | 0.518 | +| clip_range | 0.2 | +| entropy_loss | -0.417 | +| explained_variance | -3.12 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 143850 | +| policy_gradient_loss | -0.0702 | +| value_loss | 0.000276 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.169 | +| time/ | | +| fps | 309 | +| iterations | 8334 | +| time_elapsed | 27572 | +| total_timesteps | 8534016 | +| train/ | | +| approx_kl | 2.0578866 | +| clip_fraction | 0.477 | +| clip_range | 0.2 | +| entropy_loss | -0.356 | +| explained_variance | -3.08 | +| learning_rate | 0.0001 | +| loss | -0.1 | +| n_updates | 143860 | +| policy_gradient_loss | -0.0733 | +| value_loss | 0.000295 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.167 | +| time/ | | +| fps | 309 | +| iterations | 8335 | +| time_elapsed | 27575 | +| total_timesteps | 8535040 | +| train/ | | +| approx_kl | 2.416157 | +| clip_fraction | 0.508 | +| clip_range | 0.2 | +| entropy_loss | -0.395 | +| explained_variance | -0.829 | +| learning_rate | 0.0001 | +| loss | -0.107 | +| n_updates | 143870 | +| policy_gradient_loss | -0.068 | +| value_loss | 0.000396 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.17 | +| time/ | | +| fps | 309 | +| iterations | 8336 | +| time_elapsed | 27579 | +| total_timesteps | 8536064 | +| train/ | | +| approx_kl | 2.0533183 | +| clip_fraction | 0.512 | +| clip_range | 0.2 | +| entropy_loss | -0.391 | +| explained_variance | -2.49 | +| learning_rate | 0.0001 | +| loss | -0.0861 | +| n_updates | 143880 | +| policy_gradient_loss | -0.0763 | +| value_loss | 0.000542 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.17 | +| time/ | | +| fps | 309 | +| iterations | 8337 | +| time_elapsed | 27582 | +| total_timesteps | 8537088 | +| train/ | | +| approx_kl | 2.453086 | +| clip_fraction | 0.51 | +| clip_range | 0.2 | +| entropy_loss | -0.409 | +| explained_variance | -1.04 | +| learning_rate | 0.0001 | +| loss | -0.0853 | +| n_updates | 143890 | +| policy_gradient_loss | -0.0655 | +| value_loss | 0.000758 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.17 | +| time/ | | +| fps | 309 | +| iterations | 8338 | +| time_elapsed | 27586 | +| total_timesteps | 8538112 | +| train/ | | +| approx_kl | 2.5565462 | +| clip_fraction | 0.448 | +| clip_range | 0.2 | +| entropy_loss | -0.32 | +| explained_variance | -22.2 | +| learning_rate | 0.0001 | +| loss | -0.077 | +| n_updates | 143900 | +| policy_gradient_loss | -0.0668 | +| value_loss | 0.000719 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.89e+03 | +| ep_rew_mean | 0.173 | +| time/ | | +| fps | 309 | +| iterations | 8339 | +| time_elapsed | 27590 | +| total_timesteps | 8539136 | +| train/ | | +| approx_kl | 2.1874928 | +| clip_fraction | 0.512 | +| clip_range | 0.2 | +| entropy_loss | -0.406 | +| explained_variance | -2.24 | +| learning_rate | 0.0001 | +| loss | -0.0648 | +| n_updates | 143910 | +| policy_gradient_loss | -0.0721 | +| value_loss | 0.000665 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.89e+03 | +| ep_rew_mean | 0.173 | +| time/ | | +| fps | 309 | +| iterations | 8340 | +| time_elapsed | 27593 | +| total_timesteps | 8540160 | +| train/ | | +| approx_kl | 2.3323019 | +| clip_fraction | 0.488 | +| clip_range | 0.2 | +| entropy_loss | -0.395 | +| explained_variance | -1.94 | +| learning_rate | 0.0001 | +| loss | -0.105 | +| n_updates | 143920 | +| policy_gradient_loss | -0.0675 | +| value_loss | 0.000507 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.89e+03 | +| ep_rew_mean | 0.173 | +| time/ | | +| fps | 309 | +| iterations | 8341 | +| time_elapsed | 27596 | +| total_timesteps | 8541184 | +| train/ | | +| approx_kl | 2.3114164 | +| clip_fraction | 0.486 | +| clip_range | 0.2 | +| entropy_loss | -0.355 | +| explained_variance | -5.33 | +| learning_rate | 0.0001 | +| loss | -0.0579 | +| n_updates | 143930 | +| policy_gradient_loss | -0.0659 | +| value_loss | 0.000631 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.91e+03 | +| ep_rew_mean | 0.175 | +| time/ | | +| fps | 309 | +| iterations | 8342 | +| time_elapsed | 27600 | +| total_timesteps | 8542208 | +| train/ | | +| approx_kl | 2.3969412 | +| clip_fraction | 0.49 | +| clip_range | 0.2 | +| entropy_loss | -0.365 | +| explained_variance | -6.97 | +| learning_rate | 0.0001 | +| loss | -0.11 | +| n_updates | 143940 | +| policy_gradient_loss | -0.0725 | +| value_loss | 0.000398 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.91e+03 | +| ep_rew_mean | 0.175 | +| time/ | | +| fps | 309 | +| iterations | 8343 | +| time_elapsed | 27603 | +| total_timesteps | 8543232 | +| train/ | | +| approx_kl | 15.736112 | +| clip_fraction | 0.477 | +| clip_range | 0.2 | +| entropy_loss | -0.339 | +| explained_variance | -1.58 | +| learning_rate | 0.0001 | +| loss | -0.0839 | +| n_updates | 143950 | +| policy_gradient_loss | -0.0621 | +| value_loss | 0.000567 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.92e+03 | +| ep_rew_mean | 0.175 | +| time/ | | +| fps | 309 | +| iterations | 8344 | +| time_elapsed | 27607 | +| total_timesteps | 8544256 | +| train/ | | +| approx_kl | 2.6599321 | +| clip_fraction | 0.524 | +| clip_range | 0.2 | +| entropy_loss | -0.444 | +| explained_variance | -2 | +| learning_rate | 0.0001 | +| loss | -0.0893 | +| n_updates | 143960 | +| policy_gradient_loss | -0.0707 | +| value_loss | 0.000532 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.92e+03 | +| ep_rew_mean | 0.175 | +| time/ | | +| fps | 309 | +| iterations | 8345 | +| time_elapsed | 27610 | +| total_timesteps | 8545280 | +| train/ | | +| approx_kl | 2.1365833 | +| clip_fraction | 0.486 | +| clip_range | 0.2 | +| entropy_loss | -0.353 | +| explained_variance | -4.18 | +| learning_rate | 0.0001 | +| loss | -0.0732 | +| n_updates | 143970 | +| policy_gradient_loss | -0.0669 | +| value_loss | 0.000372 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.93e+03 | +| ep_rew_mean | 0.177 | +| time/ | | +| fps | 309 | +| iterations | 8346 | +| time_elapsed | 27614 | +| total_timesteps | 8546304 | +| train/ | | +| approx_kl | 2.283183 | +| clip_fraction | 0.478 | +| clip_range | 0.2 | +| entropy_loss | -0.357 | +| explained_variance | -1.58 | +| learning_rate | 0.0001 | +| loss | -0.0816 | +| n_updates | 143980 | +| policy_gradient_loss | -0.0646 | +| value_loss | 0.000462 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.93e+03 | +| ep_rew_mean | 0.177 | +| time/ | | +| fps | 309 | +| iterations | 8347 | +| time_elapsed | 27617 | +| total_timesteps | 8547328 | +| train/ | | +| approx_kl | 6.2336884 | +| clip_fraction | 0.519 | +| clip_range | 0.2 | +| entropy_loss | -0.388 | +| explained_variance | -1.71 | +| learning_rate | 0.0001 | +| loss | -0.11 | +| n_updates | 143990 | +| policy_gradient_loss | -0.0707 | +| value_loss | 0.000879 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.93e+03 | +| ep_rew_mean | 0.177 | +| time/ | | +| fps | 309 | +| iterations | 8348 | +| time_elapsed | 27621 | +| total_timesteps | 8548352 | +| train/ | | +| approx_kl | 2.6837564 | +| clip_fraction | 0.493 | +| clip_range | 0.2 | +| entropy_loss | -0.348 | +| explained_variance | -3.01 | +| learning_rate | 0.0001 | +| loss | -0.0982 | +| n_updates | 144000 | +| policy_gradient_loss | -0.0762 | +| value_loss | 0.000415 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.93e+03 | +| ep_rew_mean | 0.177 | +| time/ | | +| fps | 309 | +| iterations | 8349 | +| time_elapsed | 27624 | +| total_timesteps | 8549376 | +| train/ | | +| approx_kl | 2.6201725 | +| clip_fraction | 0.485 | +| clip_range | 0.2 | +| entropy_loss | -0.353 | +| explained_variance | -6.07 | +| learning_rate | 0.0001 | +| loss | -0.106 | +| n_updates | 144010 | +| policy_gradient_loss | -0.072 | +| value_loss | 0.00023 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.96e+03 | +| ep_rew_mean | 0.183 | +| time/ | | +| fps | 309 | +| iterations | 8350 | +| time_elapsed | 27628 | +| total_timesteps | 8550400 | +| train/ | | +| approx_kl | 2.2075753 | +| clip_fraction | 0.521 | +| clip_range | 0.2 | +| entropy_loss | -0.402 | +| explained_variance | -0.659 | +| learning_rate | 0.0001 | +| loss | -0.0782 | +| n_updates | 144020 | +| policy_gradient_loss | -0.0577 | +| value_loss | 0.000338 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.96e+03 | +| ep_rew_mean | 0.183 | +| time/ | | +| fps | 309 | +| iterations | 8351 | +| time_elapsed | 27631 | +| total_timesteps | 8551424 | +| train/ | | +| approx_kl | 3.8068757 | +| clip_fraction | 0.517 | +| clip_range | 0.2 | +| entropy_loss | -0.379 | +| explained_variance | -2.21 | +| learning_rate | 0.0001 | +| loss | -0.0908 | +| n_updates | 144030 | +| policy_gradient_loss | -0.0696 | +| value_loss | 0.00066 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.96e+03 | +| ep_rew_mean | 0.183 | +| time/ | | +| fps | 309 | +| iterations | 8352 | +| time_elapsed | 27634 | +| total_timesteps | 8552448 | +| train/ | | +| approx_kl | 1.9497159 | +| clip_fraction | 0.492 | +| clip_range | 0.2 | +| entropy_loss | -0.349 | +| explained_variance | -1.63 | +| learning_rate | 0.0001 | +| loss | -0.0941 | +| n_updates | 144040 | +| policy_gradient_loss | -0.0683 | +| value_loss | 0.000502 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.97e+03 | +| ep_rew_mean | 0.182 | +| time/ | | +| fps | 309 | +| iterations | 8353 | +| time_elapsed | 27638 | +| total_timesteps | 8553472 | +| train/ | | +| approx_kl | 2.548312 | +| clip_fraction | 0.506 | +| clip_range | 0.2 | +| entropy_loss | -0.409 | +| explained_variance | -3.36 | +| learning_rate | 0.0001 | +| loss | -0.0881 | +| n_updates | 144050 | +| policy_gradient_loss | -0.074 | +| value_loss | 0.000401 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.97e+03 | +| ep_rew_mean | 0.182 | +| time/ | | +| fps | 309 | +| iterations | 8354 | +| time_elapsed | 27641 | +| total_timesteps | 8554496 | +| train/ | | +| approx_kl | 2.1899796 | +| clip_fraction | 0.511 | +| clip_range | 0.2 | +| entropy_loss | -0.404 | +| explained_variance | -1.38 | +| learning_rate | 0.0001 | +| loss | -0.0935 | +| n_updates | 144060 | +| policy_gradient_loss | -0.073 | +| value_loss | 0.000542 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.97e+03 | +| ep_rew_mean | 0.182 | +| time/ | | +| fps | 309 | +| iterations | 8355 | +| time_elapsed | 27645 | +| total_timesteps | 8555520 | +| train/ | | +| approx_kl | 2.3677874 | +| clip_fraction | 0.496 | +| clip_range | 0.2 | +| entropy_loss | -0.388 | +| explained_variance | -2.33 | +| learning_rate | 0.0001 | +| loss | -0.0657 | +| n_updates | 144070 | +| policy_gradient_loss | -0.071 | +| value_loss | 0.0004 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.99e+03 | +| ep_rew_mean | 0.184 | +| time/ | | +| fps | 309 | +| iterations | 8356 | +| time_elapsed | 27648 | +| total_timesteps | 8556544 | +| train/ | | +| approx_kl | 2.7029517 | +| clip_fraction | 0.493 | +| clip_range | 0.2 | +| entropy_loss | -0.362 | +| explained_variance | -1.37 | +| learning_rate | 0.0001 | +| loss | -0.0266 | +| n_updates | 144080 | +| policy_gradient_loss | -0.0626 | +| value_loss | 0.000523 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.99e+03 | +| ep_rew_mean | 0.184 | +| time/ | | +| fps | 309 | +| iterations | 8357 | +| time_elapsed | 27652 | +| total_timesteps | 8557568 | +| train/ | | +| approx_kl | 2.246408 | +| clip_fraction | 0.531 | +| clip_range | 0.2 | +| entropy_loss | -0.467 | +| explained_variance | -0.889 | +| learning_rate | 0.0001 | +| loss | -0.0955 | +| n_updates | 144090 | +| policy_gradient_loss | -0.0707 | +| value_loss | 0.000486 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2e+03 | +| ep_rew_mean | 0.187 | +| time/ | | +| fps | 309 | +| iterations | 8358 | +| time_elapsed | 27655 | +| total_timesteps | 8558592 | +| train/ | | +| approx_kl | 2.464601 | +| clip_fraction | 0.512 | +| clip_range | 0.2 | +| entropy_loss | -0.391 | +| explained_variance | -8.18 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 144100 | +| policy_gradient_loss | -0.0697 | +| value_loss | 0.000221 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2e+03 | +| ep_rew_mean | 0.187 | +| time/ | | +| fps | 309 | +| iterations | 8359 | +| time_elapsed | 27659 | +| total_timesteps | 8559616 | +| train/ | | +| approx_kl | 2.8539157 | +| clip_fraction | 0.511 | +| clip_range | 0.2 | +| entropy_loss | -0.393 | +| explained_variance | -0.8 | +| learning_rate | 0.0001 | +| loss | -0.0883 | +| n_updates | 144110 | +| policy_gradient_loss | -0.0657 | +| value_loss | 0.000654 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2e+03 | +| ep_rew_mean | 0.187 | +| time/ | | +| fps | 309 | +| iterations | 8360 | +| time_elapsed | 27662 | +| total_timesteps | 8560640 | +| train/ | | +| approx_kl | 1.8554331 | +| clip_fraction | 0.524 | +| clip_range | 0.2 | +| entropy_loss | -0.389 | +| explained_variance | -1.39 | +| learning_rate | 0.0001 | +| loss | -0.097 | +| n_updates | 144120 | +| policy_gradient_loss | -0.0721 | +| value_loss | 0.000622 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.01e+03 | +| ep_rew_mean | 0.193 | +| time/ | | +| fps | 309 | +| iterations | 8361 | +| time_elapsed | 27666 | +| total_timesteps | 8561664 | +| train/ | | +| approx_kl | 2.0960104 | +| clip_fraction | 0.512 | +| clip_range | 0.2 | +| entropy_loss | -0.409 | +| explained_variance | -3.47 | +| learning_rate | 0.0001 | +| loss | -0.071 | +| n_updates | 144130 | +| policy_gradient_loss | -0.0719 | +| value_loss | 0.000568 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.01e+03 | +| ep_rew_mean | 0.193 | +| time/ | | +| fps | 309 | +| iterations | 8362 | +| time_elapsed | 27669 | +| total_timesteps | 8562688 | +| train/ | | +| approx_kl | 2.4800358 | +| clip_fraction | 0.523 | +| clip_range | 0.2 | +| entropy_loss | -0.399 | +| explained_variance | -8.47 | +| learning_rate | 0.0001 | +| loss | -0.0997 | +| n_updates | 144140 | +| policy_gradient_loss | -0.0766 | +| value_loss | 0.000405 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.03e+03 | +| ep_rew_mean | 0.195 | +| time/ | | +| fps | 309 | +| iterations | 8363 | +| time_elapsed | 27672 | +| total_timesteps | 8563712 | +| train/ | | +| approx_kl | 2.173231 | +| clip_fraction | 0.51 | +| clip_range | 0.2 | +| entropy_loss | -0.424 | +| explained_variance | -1.39 | +| learning_rate | 0.0001 | +| loss | -0.0796 | +| n_updates | 144150 | +| policy_gradient_loss | -0.068 | +| value_loss | 0.000773 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.03e+03 | +| ep_rew_mean | 0.195 | +| time/ | | +| fps | 309 | +| iterations | 8364 | +| time_elapsed | 27675 | +| total_timesteps | 8564736 | +| train/ | | +| approx_kl | 2.462956 | +| clip_fraction | 0.488 | +| clip_range | 0.2 | +| entropy_loss | -0.359 | +| explained_variance | -6.31 | +| learning_rate | 0.0001 | +| loss | -0.0936 | +| n_updates | 144160 | +| policy_gradient_loss | -0.0726 | +| value_loss | 0.000456 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.03e+03 | +| ep_rew_mean | 0.192 | +| time/ | | +| fps | 309 | +| iterations | 8365 | +| time_elapsed | 27679 | +| total_timesteps | 8565760 | +| train/ | | +| approx_kl | 1.8627533 | +| clip_fraction | 0.493 | +| clip_range | 0.2 | +| entropy_loss | -0.422 | +| explained_variance | -1.72 | +| learning_rate | 0.0001 | +| loss | -0.0853 | +| n_updates | 144170 | +| policy_gradient_loss | -0.0648 | +| value_loss | 0.000523 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.03e+03 | +| ep_rew_mean | 0.192 | +| time/ | | +| fps | 309 | +| iterations | 8366 | +| time_elapsed | 27682 | +| total_timesteps | 8566784 | +| train/ | | +| approx_kl | 2.0600595 | +| clip_fraction | 0.526 | +| clip_range | 0.2 | +| entropy_loss | -0.434 | +| explained_variance | -1.54 | +| learning_rate | 0.0001 | +| loss | -0.0808 | +| n_updates | 144180 | +| policy_gradient_loss | -0.0725 | +| value_loss | 0.000339 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.05e+03 | +| ep_rew_mean | 0.198 | +| time/ | | +| fps | 309 | +| iterations | 8367 | +| time_elapsed | 27685 | +| total_timesteps | 8567808 | +| train/ | | +| approx_kl | 2.1479278 | +| clip_fraction | 0.52 | +| clip_range | 0.2 | +| entropy_loss | -0.411 | +| explained_variance | -1.08 | +| learning_rate | 0.0001 | +| loss | -0.115 | +| n_updates | 144190 | +| policy_gradient_loss | -0.0658 | +| value_loss | 0.000507 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.05e+03 | +| ep_rew_mean | 0.198 | +| time/ | | +| fps | 309 | +| iterations | 8368 | +| time_elapsed | 27688 | +| total_timesteps | 8568832 | +| train/ | | +| approx_kl | 2.2771552 | +| clip_fraction | 0.508 | +| clip_range | 0.2 | +| entropy_loss | -0.417 | +| explained_variance | -2.4 | +| learning_rate | 0.0001 | +| loss | -0.0949 | +| n_updates | 144200 | +| policy_gradient_loss | -0.0705 | +| value_loss | 0.000304 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.05e+03 | +| ep_rew_mean | 0.198 | +| time/ | | +| fps | 309 | +| iterations | 8369 | +| time_elapsed | 27691 | +| total_timesteps | 8569856 | +| train/ | | +| approx_kl | 2.5779803 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.309 | +| explained_variance | -3.76 | +| learning_rate | 0.0001 | +| loss | -0.0874 | +| n_updates | 144210 | +| policy_gradient_loss | -0.0652 | +| value_loss | 0.000456 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.07e+03 | +| ep_rew_mean | 0.2 | +| time/ | | +| fps | 309 | +| iterations | 8370 | +| time_elapsed | 27695 | +| total_timesteps | 8570880 | +| train/ | | +| approx_kl | 2.0731122 | +| clip_fraction | 0.535 | +| clip_range | 0.2 | +| entropy_loss | -0.443 | +| explained_variance | -2.57 | +| learning_rate | 0.0001 | +| loss | -0.109 | +| n_updates | 144220 | +| policy_gradient_loss | -0.077 | +| value_loss | 0.000469 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.07e+03 | +| ep_rew_mean | 0.2 | +| time/ | | +| fps | 309 | +| iterations | 8371 | +| time_elapsed | 27698 | +| total_timesteps | 8571904 | +| train/ | | +| approx_kl | 2.352274 | +| clip_fraction | 0.533 | +| clip_range | 0.2 | +| entropy_loss | -0.47 | +| explained_variance | -2.24 | +| learning_rate | 0.0001 | +| loss | -0.0725 | +| n_updates | 144230 | +| policy_gradient_loss | -0.0677 | +| value_loss | 0.000792 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.07e+03 | +| ep_rew_mean | 0.2 | +| time/ | | +| fps | 309 | +| iterations | 8372 | +| time_elapsed | 27701 | +| total_timesteps | 8572928 | +| train/ | | +| approx_kl | 2.2342281 | +| clip_fraction | 0.53 | +| clip_range | 0.2 | +| entropy_loss | -0.444 | +| explained_variance | -2.95 | +| learning_rate | 0.0001 | +| loss | -0.116 | +| n_updates | 144240 | +| policy_gradient_loss | -0.0725 | +| value_loss | 0.000588 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.08e+03 | +| ep_rew_mean | 0.201 | +| time/ | | +| fps | 309 | +| iterations | 8373 | +| time_elapsed | 27705 | +| total_timesteps | 8573952 | +| train/ | | +| approx_kl | 2.4591045 | +| clip_fraction | 0.491 | +| clip_range | 0.2 | +| entropy_loss | -0.39 | +| explained_variance | -3.47 | +| learning_rate | 0.0001 | +| loss | -0.0826 | +| n_updates | 144250 | +| policy_gradient_loss | -0.0562 | +| value_loss | 0.000584 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.08e+03 | +| ep_rew_mean | 0.201 | +| time/ | | +| fps | 309 | +| iterations | 8374 | +| time_elapsed | 27708 | +| total_timesteps | 8574976 | +| train/ | | +| approx_kl | 2.2331085 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.378 | +| explained_variance | -2.65 | +| learning_rate | 0.0001 | +| loss | -0.0814 | +| n_updates | 144260 | +| policy_gradient_loss | -0.0631 | +| value_loss | 0.000465 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.09e+03 | +| ep_rew_mean | 0.203 | +| time/ | | +| fps | 309 | +| iterations | 8375 | +| time_elapsed | 27712 | +| total_timesteps | 8576000 | +| train/ | | +| approx_kl | 2.7157578 | +| clip_fraction | 0.521 | +| clip_range | 0.2 | +| entropy_loss | -0.36 | +| explained_variance | -3.98 | +| learning_rate | 0.0001 | +| loss | -0.0807 | +| n_updates | 144270 | +| policy_gradient_loss | -0.079 | +| value_loss | 0.000648 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.09e+03 | +| ep_rew_mean | 0.203 | +| time/ | | +| fps | 309 | +| iterations | 8376 | +| time_elapsed | 27715 | +| total_timesteps | 8577024 | +| train/ | | +| approx_kl | 2.6071525 | +| clip_fraction | 0.517 | +| clip_range | 0.2 | +| entropy_loss | -0.41 | +| explained_variance | -3.7 | +| learning_rate | 0.0001 | +| loss | -0.091 | +| n_updates | 144280 | +| policy_gradient_loss | -0.0746 | +| value_loss | 0.000674 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.11e+03 | +| ep_rew_mean | 0.208 | +| time/ | | +| fps | 309 | +| iterations | 8377 | +| time_elapsed | 27719 | +| total_timesteps | 8578048 | +| train/ | | +| approx_kl | 2.6167336 | +| clip_fraction | 0.488 | +| clip_range | 0.2 | +| entropy_loss | -0.369 | +| explained_variance | -2.07 | +| learning_rate | 0.0001 | +| loss | -0.0813 | +| n_updates | 144290 | +| policy_gradient_loss | -0.073 | +| value_loss | 0.000334 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.11e+03 | +| ep_rew_mean | 0.208 | +| time/ | | +| fps | 309 | +| iterations | 8378 | +| time_elapsed | 27722 | +| total_timesteps | 8579072 | +| train/ | | +| approx_kl | 2.8443344 | +| clip_fraction | 0.55 | +| clip_range | 0.2 | +| entropy_loss | -0.408 | +| explained_variance | -0.713 | +| learning_rate | 0.0001 | +| loss | -0.0681 | +| n_updates | 144300 | +| policy_gradient_loss | -0.0708 | +| value_loss | 0.000464 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.12e+03 | +| ep_rew_mean | 0.206 | +| time/ | | +| fps | 309 | +| iterations | 8379 | +| time_elapsed | 27726 | +| total_timesteps | 8580096 | +| train/ | | +| approx_kl | 1.7064624 | +| clip_fraction | 0.465 | +| clip_range | 0.2 | +| entropy_loss | -0.389 | +| explained_variance | -3.18 | +| learning_rate | 0.0001 | +| loss | -0.0318 | +| n_updates | 144310 | +| policy_gradient_loss | -0.0671 | +| value_loss | 0.000322 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.12e+03 | +| ep_rew_mean | 0.206 | +| time/ | | +| fps | 309 | +| iterations | 8380 | +| time_elapsed | 27729 | +| total_timesteps | 8581120 | +| train/ | | +| approx_kl | 1.7719997 | +| clip_fraction | 0.458 | +| clip_range | 0.2 | +| entropy_loss | -0.366 | +| explained_variance | -2.87 | +| learning_rate | 0.0001 | +| loss | -0.0957 | +| n_updates | 144320 | +| policy_gradient_loss | -0.0659 | +| value_loss | 0.000208 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.12e+03 | +| ep_rew_mean | 0.204 | +| time/ | | +| fps | 309 | +| iterations | 8381 | +| time_elapsed | 27732 | +| total_timesteps | 8582144 | +| train/ | | +| approx_kl | 2.1081526 | +| clip_fraction | 0.479 | +| clip_range | 0.2 | +| entropy_loss | -0.392 | +| explained_variance | -0.446 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 144330 | +| policy_gradient_loss | -0.0637 | +| value_loss | 0.000537 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.12e+03 | +| ep_rew_mean | 0.204 | +| time/ | | +| fps | 309 | +| iterations | 8382 | +| time_elapsed | 27736 | +| total_timesteps | 8583168 | +| train/ | | +| approx_kl | 2.510908 | +| clip_fraction | 0.502 | +| clip_range | 0.2 | +| entropy_loss | -0.366 | +| explained_variance | -2.2 | +| learning_rate | 0.0001 | +| loss | -0.0865 | +| n_updates | 144340 | +| policy_gradient_loss | -0.0708 | +| value_loss | 0.000607 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.12e+03 | +| ep_rew_mean | 0.202 | +| time/ | | +| fps | 309 | +| iterations | 8383 | +| time_elapsed | 27739 | +| total_timesteps | 8584192 | +| train/ | | +| approx_kl | 1.8462808 | +| clip_fraction | 0.517 | +| clip_range | 0.2 | +| entropy_loss | -0.436 | +| explained_variance | -2.86 | +| learning_rate | 0.0001 | +| loss | -0.099 | +| n_updates | 144350 | +| policy_gradient_loss | -0.0717 | +| value_loss | 0.000652 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.12e+03 | +| ep_rew_mean | 0.202 | +| time/ | | +| fps | 309 | +| iterations | 8384 | +| time_elapsed | 27742 | +| total_timesteps | 8585216 | +| train/ | | +| approx_kl | 1.9705237 | +| clip_fraction | 0.508 | +| clip_range | 0.2 | +| entropy_loss | -0.388 | +| explained_variance | -6.43 | +| learning_rate | 0.0001 | +| loss | -0.11 | +| n_updates | 144360 | +| policy_gradient_loss | -0.0715 | +| value_loss | 0.000778 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.14e+03 | +| ep_rew_mean | 0.203 | +| time/ | | +| fps | 309 | +| iterations | 8385 | +| time_elapsed | 27745 | +| total_timesteps | 8586240 | +| train/ | | +| approx_kl | 1.9916965 | +| clip_fraction | 0.494 | +| clip_range | 0.2 | +| entropy_loss | -0.36 | +| explained_variance | -3.04 | +| learning_rate | 0.0001 | +| loss | -0.0783 | +| n_updates | 144370 | +| policy_gradient_loss | -0.0732 | +| value_loss | 0.000546 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.14e+03 | +| ep_rew_mean | 0.203 | +| time/ | | +| fps | 309 | +| iterations | 8386 | +| time_elapsed | 27748 | +| total_timesteps | 8587264 | +| train/ | | +| approx_kl | 2.3822331 | +| clip_fraction | 0.51 | +| clip_range | 0.2 | +| entropy_loss | -0.413 | +| explained_variance | -5.37 | +| learning_rate | 0.0001 | +| loss | -0.0852 | +| n_updates | 144380 | +| policy_gradient_loss | -0.0711 | +| value_loss | 0.000475 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.14e+03 | +| ep_rew_mean | 0.201 | +| time/ | | +| fps | 309 | +| iterations | 8387 | +| time_elapsed | 27752 | +| total_timesteps | 8588288 | +| train/ | | +| approx_kl | 2.011774 | +| clip_fraction | 0.512 | +| clip_range | 0.2 | +| entropy_loss | -0.414 | +| explained_variance | -9.72 | +| learning_rate | 0.0001 | +| loss | -0.0938 | +| n_updates | 144390 | +| policy_gradient_loss | -0.0719 | +| value_loss | 0.000571 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.14e+03 | +| ep_rew_mean | 0.201 | +| time/ | | +| fps | 309 | +| iterations | 8388 | +| time_elapsed | 27755 | +| total_timesteps | 8589312 | +| train/ | | +| approx_kl | 3.5813022 | +| clip_fraction | 0.495 | +| clip_range | 0.2 | +| entropy_loss | -0.401 | +| explained_variance | -4.08 | +| learning_rate | 0.0001 | +| loss | -0.0929 | +| n_updates | 144400 | +| policy_gradient_loss | -0.0664 | +| value_loss | 0.000825 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.14e+03 | +| ep_rew_mean | 0.201 | +| time/ | | +| fps | 309 | +| iterations | 8389 | +| time_elapsed | 27758 | +| total_timesteps | 8590336 | +| train/ | | +| approx_kl | 2.174573 | +| clip_fraction | 0.518 | +| clip_range | 0.2 | +| entropy_loss | -0.392 | +| explained_variance | -2.19 | +| learning_rate | 0.0001 | +| loss | -0.1 | +| n_updates | 144410 | +| policy_gradient_loss | -0.0785 | +| value_loss | 0.000461 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.17e+03 | +| ep_rew_mean | 0.203 | +| time/ | | +| fps | 309 | +| iterations | 8390 | +| time_elapsed | 27762 | +| total_timesteps | 8591360 | +| train/ | | +| approx_kl | 4.16313 | +| clip_fraction | 0.54 | +| clip_range | 0.2 | +| entropy_loss | -0.434 | +| explained_variance | -1.97 | +| learning_rate | 0.0001 | +| loss | -0.0947 | +| n_updates | 144420 | +| policy_gradient_loss | -0.0731 | +| value_loss | 0.000433 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.17e+03 | +| ep_rew_mean | 0.203 | +| time/ | | +| fps | 309 | +| iterations | 8391 | +| time_elapsed | 27765 | +| total_timesteps | 8592384 | +| train/ | | +| approx_kl | 2.1051512 | +| clip_fraction | 0.519 | +| clip_range | 0.2 | +| entropy_loss | -0.392 | +| explained_variance | -5.86 | +| learning_rate | 0.0001 | +| loss | -0.0905 | +| n_updates | 144430 | +| policy_gradient_loss | -0.0783 | +| value_loss | 0.00022 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.17e+03 | +| ep_rew_mean | 0.203 | +| time/ | | +| fps | 309 | +| iterations | 8392 | +| time_elapsed | 27768 | +| total_timesteps | 8593408 | +| train/ | | +| approx_kl | 2.9045258 | +| clip_fraction | 0.513 | +| clip_range | 0.2 | +| entropy_loss | -0.348 | +| explained_variance | -13.4 | +| learning_rate | 0.0001 | +| loss | -0.105 | +| n_updates | 144440 | +| policy_gradient_loss | -0.0774 | +| value_loss | 0.000159 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.19e+03 | +| ep_rew_mean | 0.2 | +| time/ | | +| fps | 309 | +| iterations | 8393 | +| time_elapsed | 27772 | +| total_timesteps | 8594432 | +| train/ | | +| approx_kl | 2.1369514 | +| clip_fraction | 0.526 | +| clip_range | 0.2 | +| entropy_loss | -0.392 | +| explained_variance | -1.63 | +| learning_rate | 0.0001 | +| loss | -0.0992 | +| n_updates | 144450 | +| policy_gradient_loss | -0.0752 | +| value_loss | 0.000486 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.19e+03 | +| ep_rew_mean | 0.2 | +| time/ | | +| fps | 309 | +| iterations | 8394 | +| time_elapsed | 27775 | +| total_timesteps | 8595456 | +| train/ | | +| approx_kl | 2.0042582 | +| clip_fraction | 0.477 | +| clip_range | 0.2 | +| entropy_loss | -0.349 | +| explained_variance | -1.52 | +| learning_rate | 0.0001 | +| loss | -0.0631 | +| n_updates | 144460 | +| policy_gradient_loss | -0.0678 | +| value_loss | 0.000416 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.19e+03 | +| ep_rew_mean | 0.2 | +| time/ | | +| fps | 309 | +| iterations | 8395 | +| time_elapsed | 27779 | +| total_timesteps | 8596480 | +| train/ | | +| approx_kl | 2.758041 | +| clip_fraction | 0.484 | +| clip_range | 0.2 | +| entropy_loss | -0.325 | +| explained_variance | -4.32 | +| learning_rate | 0.0001 | +| loss | -0.0801 | +| n_updates | 144470 | +| policy_gradient_loss | -0.0636 | +| value_loss | 0.000355 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.2e+03 | +| ep_rew_mean | 0.199 | +| time/ | | +| fps | 309 | +| iterations | 8396 | +| time_elapsed | 27782 | +| total_timesteps | 8597504 | +| train/ | | +| approx_kl | 2.8425956 | +| clip_fraction | 0.522 | +| clip_range | 0.2 | +| entropy_loss | -0.396 | +| explained_variance | -2.03 | +| learning_rate | 0.0001 | +| loss | -0.113 | +| n_updates | 144480 | +| policy_gradient_loss | -0.0776 | +| value_loss | 0.000473 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.2e+03 | +| ep_rew_mean | 0.199 | +| time/ | | +| fps | 309 | +| iterations | 8397 | +| time_elapsed | 27785 | +| total_timesteps | 8598528 | +| train/ | | +| approx_kl | 2.8857763 | +| clip_fraction | 0.506 | +| clip_range | 0.2 | +| entropy_loss | -0.375 | +| explained_variance | -4.14 | +| learning_rate | 0.0001 | +| loss | -0.0925 | +| n_updates | 144490 | +| policy_gradient_loss | -0.0729 | +| value_loss | 0.000438 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.22e+03 | +| ep_rew_mean | 0.19 | +| time/ | | +| fps | 309 | +| iterations | 8398 | +| time_elapsed | 27789 | +| total_timesteps | 8599552 | +| train/ | | +| approx_kl | 2.668254 | +| clip_fraction | 0.519 | +| clip_range | 0.2 | +| entropy_loss | -0.378 | +| explained_variance | -16.2 | +| learning_rate | 0.0001 | +| loss | -0.0932 | +| n_updates | 144500 | +| policy_gradient_loss | -0.072 | +| value_loss | 0.000572 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.22e+03 | +| ep_rew_mean | 0.19 | +| time/ | | +| fps | 309 | +| iterations | 8399 | +| time_elapsed | 27792 | +| total_timesteps | 8600576 | +| train/ | | +| approx_kl | 3.6672728 | +| clip_fraction | 0.506 | +| clip_range | 0.2 | +| entropy_loss | -0.371 | +| explained_variance | -1.48 | +| learning_rate | 0.0001 | +| loss | -0.0838 | +| n_updates | 144510 | +| policy_gradient_loss | -0.0644 | +| value_loss | 0.000449 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.22e+03 | +| ep_rew_mean | 0.19 | +| time/ | | +| fps | 309 | +| iterations | 8400 | +| time_elapsed | 27795 | +| total_timesteps | 8601600 | +| train/ | | +| approx_kl | 2.6587365 | +| clip_fraction | 0.465 | +| clip_range | 0.2 | +| entropy_loss | -0.305 | +| explained_variance | -3.08 | +| learning_rate | 0.0001 | +| loss | -0.0779 | +| n_updates | 144520 | +| policy_gradient_loss | -0.0722 | +| value_loss | 0.000617 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.24e+03 | +| ep_rew_mean | 0.192 | +| time/ | | +| fps | 309 | +| iterations | 8401 | +| time_elapsed | 27798 | +| total_timesteps | 8602624 | +| train/ | | +| approx_kl | 2.3828893 | +| clip_fraction | 0.519 | +| clip_range | 0.2 | +| entropy_loss | -0.406 | +| explained_variance | -4.13 | +| learning_rate | 0.0001 | +| loss | -0.0821 | +| n_updates | 144530 | +| policy_gradient_loss | -0.0729 | +| value_loss | 0.000389 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.24e+03 | +| ep_rew_mean | 0.192 | +| time/ | | +| fps | 309 | +| iterations | 8402 | +| time_elapsed | 27802 | +| total_timesteps | 8603648 | +| train/ | | +| approx_kl | 2.687891 | +| clip_fraction | 0.51 | +| clip_range | 0.2 | +| entropy_loss | -0.39 | +| explained_variance | -2.28 | +| learning_rate | 0.0001 | +| loss | -0.0876 | +| n_updates | 144540 | +| policy_gradient_loss | -0.0664 | +| value_loss | 0.000265 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.24e+03 | +| ep_rew_mean | 0.192 | +| time/ | | +| fps | 309 | +| iterations | 8403 | +| time_elapsed | 27805 | +| total_timesteps | 8604672 | +| train/ | | +| approx_kl | 2.600437 | +| clip_fraction | 0.498 | +| clip_range | 0.2 | +| entropy_loss | -0.378 | +| explained_variance | -8.89 | +| learning_rate | 0.0001 | +| loss | -0.106 | +| n_updates | 144550 | +| policy_gradient_loss | -0.0747 | +| value_loss | 0.000357 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.24e+03 | +| ep_rew_mean | 0.187 | +| time/ | | +| fps | 309 | +| iterations | 8404 | +| time_elapsed | 27808 | +| total_timesteps | 8605696 | +| train/ | | +| approx_kl | 2.2107537 | +| clip_fraction | 0.474 | +| clip_range | 0.2 | +| entropy_loss | -0.342 | +| explained_variance | -0.974 | +| learning_rate | 0.0001 | +| loss | -0.0633 | +| n_updates | 144560 | +| policy_gradient_loss | -0.0607 | +| value_loss | 0.000593 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.24e+03 | +| ep_rew_mean | 0.181 | +| time/ | | +| fps | 309 | +| iterations | 8405 | +| time_elapsed | 27811 | +| total_timesteps | 8606720 | +| train/ | | +| approx_kl | 4.885947 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.378 | +| explained_variance | -3.88 | +| learning_rate | 0.0001 | +| loss | -0.0667 | +| n_updates | 144570 | +| policy_gradient_loss | -0.0711 | +| value_loss | 0.000585 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.24e+03 | +| ep_rew_mean | 0.181 | +| time/ | | +| fps | 309 | +| iterations | 8406 | +| time_elapsed | 27814 | +| total_timesteps | 8607744 | +| train/ | | +| approx_kl | 2.0746188 | +| clip_fraction | 0.448 | +| clip_range | 0.2 | +| entropy_loss | -0.312 | +| explained_variance | -1.65 | +| learning_rate | 0.0001 | +| loss | -0.0814 | +| n_updates | 144580 | +| policy_gradient_loss | -0.0671 | +| value_loss | 0.000797 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.25e+03 | +| ep_rew_mean | 0.176 | +| time/ | | +| fps | 309 | +| iterations | 8407 | +| time_elapsed | 27818 | +| total_timesteps | 8608768 | +| train/ | | +| approx_kl | 2.1595836 | +| clip_fraction | 0.45 | +| clip_range | 0.2 | +| entropy_loss | -0.312 | +| explained_variance | -6.12 | +| learning_rate | 0.0001 | +| loss | -0.0834 | +| n_updates | 144590 | +| policy_gradient_loss | -0.0659 | +| value_loss | 0.000825 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.25e+03 | +| ep_rew_mean | 0.176 | +| time/ | | +| fps | 309 | +| iterations | 8408 | +| time_elapsed | 27821 | +| total_timesteps | 8609792 | +| train/ | | +| approx_kl | 2.250494 | +| clip_fraction | 0.452 | +| clip_range | 0.2 | +| entropy_loss | -0.35 | +| explained_variance | -1.83 | +| learning_rate | 0.0001 | +| loss | -0.0721 | +| n_updates | 144600 | +| policy_gradient_loss | -0.0683 | +| value_loss | 0.000421 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.25e+03 | +| ep_rew_mean | 0.176 | +| time/ | | +| fps | 309 | +| iterations | 8409 | +| time_elapsed | 27825 | +| total_timesteps | 8610816 | +| train/ | | +| approx_kl | 2.6238604 | +| clip_fraction | 0.529 | +| clip_range | 0.2 | +| entropy_loss | -0.372 | +| explained_variance | -2.01 | +| learning_rate | 0.0001 | +| loss | -0.0785 | +| n_updates | 144610 | +| policy_gradient_loss | -0.0699 | +| value_loss | 0.000496 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.27e+03 | +| ep_rew_mean | 0.18 | +| time/ | | +| fps | 309 | +| iterations | 8410 | +| time_elapsed | 27828 | +| total_timesteps | 8611840 | +| train/ | | +| approx_kl | 2.7023427 | +| clip_fraction | 0.491 | +| clip_range | 0.2 | +| entropy_loss | -0.406 | +| explained_variance | -3.11 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 144620 | +| policy_gradient_loss | -0.0663 | +| value_loss | 0.000273 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.27e+03 | +| ep_rew_mean | 0.187 | +| time/ | | +| fps | 309 | +| iterations | 8411 | +| time_elapsed | 27832 | +| total_timesteps | 8612864 | +| train/ | | +| approx_kl | 2.9974592 | +| clip_fraction | 0.492 | +| clip_range | 0.2 | +| entropy_loss | -0.369 | +| explained_variance | -0.986 | +| learning_rate | 0.0001 | +| loss | -0.064 | +| n_updates | 144630 | +| policy_gradient_loss | -0.0678 | +| value_loss | 0.000507 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.27e+03 | +| ep_rew_mean | 0.187 | +| time/ | | +| fps | 309 | +| iterations | 8412 | +| time_elapsed | 27835 | +| total_timesteps | 8613888 | +| train/ | | +| approx_kl | 2.4176188 | +| clip_fraction | 0.485 | +| clip_range | 0.2 | +| entropy_loss | -0.368 | +| explained_variance | -1.69 | +| learning_rate | 0.0001 | +| loss | -0.0787 | +| n_updates | 144640 | +| policy_gradient_loss | -0.069 | +| value_loss | 0.000709 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.27e+03 | +| ep_rew_mean | 0.187 | +| time/ | | +| fps | 309 | +| iterations | 8413 | +| time_elapsed | 27839 | +| total_timesteps | 8614912 | +| train/ | | +| approx_kl | 2.1189842 | +| clip_fraction | 0.486 | +| clip_range | 0.2 | +| entropy_loss | -0.36 | +| explained_variance | -2.01 | +| learning_rate | 0.0001 | +| loss | -0.0719 | +| n_updates | 144650 | +| policy_gradient_loss | -0.0709 | +| value_loss | 0.00079 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.3e+03 | +| ep_rew_mean | 0.189 | +| time/ | | +| fps | 309 | +| iterations | 8414 | +| time_elapsed | 27842 | +| total_timesteps | 8615936 | +| train/ | | +| approx_kl | 5.164825 | +| clip_fraction | 0.498 | +| clip_range | 0.2 | +| entropy_loss | -0.421 | +| explained_variance | -3.71 | +| learning_rate | 0.0001 | +| loss | -0.0716 | +| n_updates | 144660 | +| policy_gradient_loss | -0.063 | +| value_loss | 0.00035 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.3e+03 | +| ep_rew_mean | 0.189 | +| time/ | | +| fps | 309 | +| iterations | 8415 | +| time_elapsed | 27846 | +| total_timesteps | 8616960 | +| train/ | | +| approx_kl | 3.0380082 | +| clip_fraction | 0.492 | +| clip_range | 0.2 | +| entropy_loss | -0.358 | +| explained_variance | -6.75 | +| learning_rate | 0.0001 | +| loss | -0.0778 | +| n_updates | 144670 | +| policy_gradient_loss | -0.0672 | +| value_loss | 0.00054 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.3e+03 | +| ep_rew_mean | 0.189 | +| time/ | | +| fps | 309 | +| iterations | 8416 | +| time_elapsed | 27849 | +| total_timesteps | 8617984 | +| train/ | | +| approx_kl | 2.2114768 | +| clip_fraction | 0.507 | +| clip_range | 0.2 | +| entropy_loss | -0.404 | +| explained_variance | -3.52 | +| learning_rate | 0.0001 | +| loss | -0.0651 | +| n_updates | 144680 | +| policy_gradient_loss | -0.0697 | +| value_loss | 0.000496 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.32e+03 | +| ep_rew_mean | 0.189 | +| time/ | | +| fps | 309 | +| iterations | 8417 | +| time_elapsed | 27852 | +| total_timesteps | 8619008 | +| train/ | | +| approx_kl | 2.4830008 | +| clip_fraction | 0.5 | +| clip_range | 0.2 | +| entropy_loss | -0.389 | +| explained_variance | -2.95 | +| learning_rate | 0.0001 | +| loss | -0.0712 | +| n_updates | 144690 | +| policy_gradient_loss | -0.0712 | +| value_loss | 0.00031 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.32e+03 | +| ep_rew_mean | 0.189 | +| time/ | | +| fps | 309 | +| iterations | 8418 | +| time_elapsed | 27856 | +| total_timesteps | 8620032 | +| train/ | | +| approx_kl | 2.7091978 | +| clip_fraction | 0.479 | +| clip_range | 0.2 | +| entropy_loss | -0.354 | +| explained_variance | -2.09 | +| learning_rate | 0.0001 | +| loss | -0.088 | +| n_updates | 144700 | +| policy_gradient_loss | -0.0705 | +| value_loss | 0.000537 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.32e+03 | +| ep_rew_mean | 0.189 | +| time/ | | +| fps | 309 | +| iterations | 8419 | +| time_elapsed | 27859 | +| total_timesteps | 8621056 | +| train/ | | +| approx_kl | 2.6954362 | +| clip_fraction | 0.482 | +| clip_range | 0.2 | +| entropy_loss | -0.381 | +| explained_variance | -4.13 | +| learning_rate | 0.0001 | +| loss | -0.0803 | +| n_updates | 144710 | +| policy_gradient_loss | -0.0669 | +| value_loss | 0.000766 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.34e+03 | +| ep_rew_mean | 0.19 | +| time/ | | +| fps | 309 | +| iterations | 8420 | +| time_elapsed | 27862 | +| total_timesteps | 8622080 | +| train/ | | +| approx_kl | 2.3557847 | +| clip_fraction | 0.491 | +| clip_range | 0.2 | +| entropy_loss | -0.372 | +| explained_variance | -6.42 | +| learning_rate | 0.0001 | +| loss | -0.0906 | +| n_updates | 144720 | +| policy_gradient_loss | -0.0543 | +| value_loss | 0.000474 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.34e+03 | +| ep_rew_mean | 0.19 | +| time/ | | +| fps | 309 | +| iterations | 8421 | +| time_elapsed | 27865 | +| total_timesteps | 8623104 | +| train/ | | +| approx_kl | 1.874531 | +| clip_fraction | 0.443 | +| clip_range | 0.2 | +| entropy_loss | -0.365 | +| explained_variance | -0.751 | +| learning_rate | 0.0001 | +| loss | -0.0487 | +| n_updates | 144730 | +| policy_gradient_loss | -0.0543 | +| value_loss | 0.00067 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.34e+03 | +| ep_rew_mean | 0.193 | +| time/ | | +| fps | 309 | +| iterations | 8422 | +| time_elapsed | 27868 | +| total_timesteps | 8624128 | +| train/ | | +| approx_kl | 1.9853809 | +| clip_fraction | 0.476 | +| clip_range | 0.2 | +| entropy_loss | -0.357 | +| explained_variance | -1.31 | +| learning_rate | 0.0001 | +| loss | -0.0707 | +| n_updates | 144740 | +| policy_gradient_loss | -0.0673 | +| value_loss | 0.000585 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.34e+03 | +| ep_rew_mean | 0.193 | +| time/ | | +| fps | 309 | +| iterations | 8423 | +| time_elapsed | 27872 | +| total_timesteps | 8625152 | +| train/ | | +| approx_kl | 2.4674058 | +| clip_fraction | 0.466 | +| clip_range | 0.2 | +| entropy_loss | -0.352 | +| explained_variance | -2.19 | +| learning_rate | 0.0001 | +| loss | -0.0965 | +| n_updates | 144750 | +| policy_gradient_loss | -0.0658 | +| value_loss | 0.000897 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.36e+03 | +| ep_rew_mean | 0.2 | +| time/ | | +| fps | 309 | +| iterations | 8424 | +| time_elapsed | 27875 | +| total_timesteps | 8626176 | +| train/ | | +| approx_kl | 3.6778836 | +| clip_fraction | 0.486 | +| clip_range | 0.2 | +| entropy_loss | -0.352 | +| explained_variance | -2.24 | +| learning_rate | 0.0001 | +| loss | -0.116 | +| n_updates | 144760 | +| policy_gradient_loss | -0.0759 | +| value_loss | 0.000559 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.36e+03 | +| ep_rew_mean | 0.2 | +| time/ | | +| fps | 309 | +| iterations | 8425 | +| time_elapsed | 27878 | +| total_timesteps | 8627200 | +| train/ | | +| approx_kl | 2.6033344 | +| clip_fraction | 0.456 | +| clip_range | 0.2 | +| entropy_loss | -0.349 | +| explained_variance | -2.97 | +| learning_rate | 0.0001 | +| loss | -0.0878 | +| n_updates | 144770 | +| policy_gradient_loss | -0.0607 | +| value_loss | 0.0004 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.37e+03 | +| ep_rew_mean | 0.2 | +| time/ | | +| fps | 309 | +| iterations | 8426 | +| time_elapsed | 27881 | +| total_timesteps | 8628224 | +| train/ | | +| approx_kl | 2.963159 | +| clip_fraction | 0.507 | +| clip_range | 0.2 | +| entropy_loss | -0.361 | +| explained_variance | -1.94 | +| learning_rate | 0.0001 | +| loss | -0.0973 | +| n_updates | 144780 | +| policy_gradient_loss | -0.0681 | +| value_loss | 0.000692 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.37e+03 | +| ep_rew_mean | 0.2 | +| time/ | | +| fps | 309 | +| iterations | 8427 | +| time_elapsed | 27885 | +| total_timesteps | 8629248 | +| train/ | | +| approx_kl | 2.5589929 | +| clip_fraction | 0.468 | +| clip_range | 0.2 | +| entropy_loss | -0.33 | +| explained_variance | -10.7 | +| learning_rate | 0.0001 | +| loss | -0.0846 | +| n_updates | 144790 | +| policy_gradient_loss | -0.0648 | +| value_loss | 0.000397 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.38e+03 | +| ep_rew_mean | 0.202 | +| time/ | | +| fps | 309 | +| iterations | 8428 | +| time_elapsed | 27888 | +| total_timesteps | 8630272 | +| train/ | | +| approx_kl | 1.9532547 | +| clip_fraction | 0.472 | +| clip_range | 0.2 | +| entropy_loss | -0.373 | +| explained_variance | -2.58 | +| learning_rate | 0.0001 | +| loss | -0.0905 | +| n_updates | 144800 | +| policy_gradient_loss | 0.117 | +| value_loss | 0.000397 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.38e+03 | +| ep_rew_mean | 0.202 | +| time/ | | +| fps | 309 | +| iterations | 8429 | +| time_elapsed | 27891 | +| total_timesteps | 8631296 | +| train/ | | +| approx_kl | 2.5513225 | +| clip_fraction | 0.504 | +| clip_range | 0.2 | +| entropy_loss | -0.38 | +| explained_variance | -1.48 | +| learning_rate | 0.0001 | +| loss | -0.0872 | +| n_updates | 144810 | +| policy_gradient_loss | -0.0665 | +| value_loss | 0.00054 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.38e+03 | +| ep_rew_mean | 0.202 | +| time/ | | +| fps | 309 | +| iterations | 8430 | +| time_elapsed | 27895 | +| total_timesteps | 8632320 | +| train/ | | +| approx_kl | 2.8413887 | +| clip_fraction | 0.489 | +| clip_range | 0.2 | +| entropy_loss | -0.33 | +| explained_variance | -4.76 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 144820 | +| policy_gradient_loss | -0.0694 | +| value_loss | 0.00075 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.39e+03 | +| ep_rew_mean | 0.203 | +| time/ | | +| fps | 309 | +| iterations | 8431 | +| time_elapsed | 27898 | +| total_timesteps | 8633344 | +| train/ | | +| approx_kl | 2.1020267 | +| clip_fraction | 0.506 | +| clip_range | 0.2 | +| entropy_loss | -0.392 | +| explained_variance | -1.34 | +| learning_rate | 0.0001 | +| loss | -0.0744 | +| n_updates | 144830 | +| policy_gradient_loss | -0.0649 | +| value_loss | 0.000409 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.4e+03 | +| ep_rew_mean | 0.206 | +| time/ | | +| fps | 309 | +| iterations | 8432 | +| time_elapsed | 27901 | +| total_timesteps | 8634368 | +| train/ | | +| approx_kl | 1.968551 | +| clip_fraction | 0.49 | +| clip_range | 0.2 | +| entropy_loss | -0.373 | +| explained_variance | -1 | +| learning_rate | 0.0001 | +| loss | -0.0931 | +| n_updates | 144840 | +| policy_gradient_loss | -0.068 | +| value_loss | 0.000559 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.4e+03 | +| ep_rew_mean | 0.206 | +| time/ | | +| fps | 309 | +| iterations | 8433 | +| time_elapsed | 27905 | +| total_timesteps | 8635392 | +| train/ | | +| approx_kl | 2.2199302 | +| clip_fraction | 0.47 | +| clip_range | 0.2 | +| entropy_loss | -0.374 | +| explained_variance | -0.863 | +| learning_rate | 0.0001 | +| loss | -0.0505 | +| n_updates | 144850 | +| policy_gradient_loss | -0.0632 | +| value_loss | 0.000658 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.4e+03 | +| ep_rew_mean | 0.206 | +| time/ | | +| fps | 309 | +| iterations | 8434 | +| time_elapsed | 27908 | +| total_timesteps | 8636416 | +| train/ | | +| approx_kl | 2.1942463 | +| clip_fraction | 0.477 | +| clip_range | 0.2 | +| entropy_loss | -0.35 | +| explained_variance | -7.68 | +| learning_rate | 0.0001 | +| loss | -0.0835 | +| n_updates | 144860 | +| policy_gradient_loss | -0.0687 | +| value_loss | 0.000444 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.41e+03 | +| ep_rew_mean | 0.21 | +| time/ | | +| fps | 309 | +| iterations | 8435 | +| time_elapsed | 27911 | +| total_timesteps | 8637440 | +| train/ | | +| approx_kl | 3.1644115 | +| clip_fraction | 0.529 | +| clip_range | 0.2 | +| entropy_loss | -0.345 | +| explained_variance | -10.2 | +| learning_rate | 0.0001 | +| loss | -0.0851 | +| n_updates | 144870 | +| policy_gradient_loss | -0.075 | +| value_loss | 0.000491 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.41e+03 | +| ep_rew_mean | 0.21 | +| time/ | | +| fps | 309 | +| iterations | 8436 | +| time_elapsed | 27914 | +| total_timesteps | 8638464 | +| train/ | | +| approx_kl | 2.3725574 | +| clip_fraction | 0.479 | +| clip_range | 0.2 | +| entropy_loss | -0.33 | +| explained_variance | -1.71 | +| learning_rate | 0.0001 | +| loss | -0.0765 | +| n_updates | 144880 | +| policy_gradient_loss | -0.0668 | +| value_loss | 0.000815 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.42e+03 | +| ep_rew_mean | 0.213 | +| time/ | | +| fps | 309 | +| iterations | 8437 | +| time_elapsed | 27917 | +| total_timesteps | 8639488 | +| train/ | | +| approx_kl | 2.026147 | +| clip_fraction | 0.472 | +| clip_range | 0.2 | +| entropy_loss | -0.374 | +| explained_variance | -0.702 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 144890 | +| policy_gradient_loss | -0.0668 | +| value_loss | 0.000994 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.42e+03 | +| ep_rew_mean | 0.213 | +| time/ | | +| fps | 309 | +| iterations | 8438 | +| time_elapsed | 27921 | +| total_timesteps | 8640512 | +| train/ | | +| approx_kl | 4.5529118 | +| clip_fraction | 0.431 | +| clip_range | 0.2 | +| entropy_loss | -0.302 | +| explained_variance | -11.6 | +| learning_rate | 0.0001 | +| loss | -0.0878 | +| n_updates | 144900 | +| policy_gradient_loss | -0.0643 | +| value_loss | 0.000565 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.44e+03 | +| ep_rew_mean | 0.211 | +| time/ | | +| fps | 309 | +| iterations | 8439 | +| time_elapsed | 27924 | +| total_timesteps | 8641536 | +| train/ | | +| approx_kl | 3.6927454 | +| clip_fraction | 0.472 | +| clip_range | 0.2 | +| entropy_loss | -0.328 | +| explained_variance | -1.6 | +| learning_rate | 0.0001 | +| loss | -0.0617 | +| n_updates | 144910 | +| policy_gradient_loss | -0.0679 | +| value_loss | 0.000672 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.44e+03 | +| ep_rew_mean | 0.211 | +| time/ | | +| fps | 309 | +| iterations | 8440 | +| time_elapsed | 27927 | +| total_timesteps | 8642560 | +| train/ | | +| approx_kl | 2.4599898 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.356 | +| explained_variance | -4.2 | +| learning_rate | 0.0001 | +| loss | -0.0755 | +| n_updates | 144920 | +| policy_gradient_loss | -0.0669 | +| value_loss | 0.000389 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.45e+03 | +| ep_rew_mean | 0.212 | +| time/ | | +| fps | 309 | +| iterations | 8441 | +| time_elapsed | 27930 | +| total_timesteps | 8643584 | +| train/ | | +| approx_kl | 2.5222154 | +| clip_fraction | 0.516 | +| clip_range | 0.2 | +| entropy_loss | -0.352 | +| explained_variance | -2.09 | +| learning_rate | 0.0001 | +| loss | -0.0765 | +| n_updates | 144930 | +| policy_gradient_loss | -0.0712 | +| value_loss | 0.000651 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.45e+03 | +| ep_rew_mean | 0.212 | +| time/ | | +| fps | 309 | +| iterations | 8442 | +| time_elapsed | 27933 | +| total_timesteps | 8644608 | +| train/ | | +| approx_kl | 2.3557158 | +| clip_fraction | 0.5 | +| clip_range | 0.2 | +| entropy_loss | -0.355 | +| explained_variance | -6.11 | +| learning_rate | 0.0001 | +| loss | -0.0705 | +| n_updates | 144940 | +| policy_gradient_loss | -0.069 | +| value_loss | 0.000568 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.45e+03 | +| ep_rew_mean | 0.212 | +| time/ | | +| fps | 309 | +| iterations | 8443 | +| time_elapsed | 27937 | +| total_timesteps | 8645632 | +| train/ | | +| approx_kl | 2.8591757 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.318 | +| explained_variance | -2.45 | +| learning_rate | 0.0001 | +| loss | -0.0764 | +| n_updates | 144950 | +| policy_gradient_loss | -0.0685 | +| value_loss | 0.000672 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.47e+03 | +| ep_rew_mean | 0.217 | +| time/ | | +| fps | 309 | +| iterations | 8444 | +| time_elapsed | 27940 | +| total_timesteps | 8646656 | +| train/ | | +| approx_kl | 3.6145568 | +| clip_fraction | 0.486 | +| clip_range | 0.2 | +| entropy_loss | -0.338 | +| explained_variance | -4.04 | +| learning_rate | 0.0001 | +| loss | 0.00605 | +| n_updates | 144960 | +| policy_gradient_loss | -0.0746 | +| value_loss | 0.000537 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.47e+03 | +| ep_rew_mean | 0.217 | +| time/ | | +| fps | 309 | +| iterations | 8445 | +| time_elapsed | 27943 | +| total_timesteps | 8647680 | +| train/ | | +| approx_kl | 2.3424647 | +| clip_fraction | 0.467 | +| clip_range | 0.2 | +| entropy_loss | -0.322 | +| explained_variance | -2.56 | +| learning_rate | 0.0001 | +| loss | -0.0689 | +| n_updates | 144970 | +| policy_gradient_loss | -0.0668 | +| value_loss | 0.00047 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.47e+03 | +| ep_rew_mean | 0.22 | +| time/ | | +| fps | 309 | +| iterations | 8446 | +| time_elapsed | 27947 | +| total_timesteps | 8648704 | +| train/ | | +| approx_kl | 2.7298832 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.358 | +| explained_variance | -1.62 | +| learning_rate | 0.0001 | +| loss | -0.0944 | +| n_updates | 144980 | +| policy_gradient_loss | -0.0663 | +| value_loss | 0.000711 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.47e+03 | +| ep_rew_mean | 0.22 | +| time/ | | +| fps | 309 | +| iterations | 8447 | +| time_elapsed | 27950 | +| total_timesteps | 8649728 | +| train/ | | +| approx_kl | 3.300796 | +| clip_fraction | 0.439 | +| clip_range | 0.2 | +| entropy_loss | -0.288 | +| explained_variance | -2.9 | +| learning_rate | 0.0001 | +| loss | -0.0992 | +| n_updates | 144990 | +| policy_gradient_loss | -0.0641 | +| value_loss | 0.000888 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.48e+03 | +| ep_rew_mean | 0.22 | +| time/ | | +| fps | 309 | +| iterations | 8448 | +| time_elapsed | 27954 | +| total_timesteps | 8650752 | +| train/ | | +| approx_kl | 3.4881556 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.31 | +| explained_variance | -6.31 | +| learning_rate | 0.0001 | +| loss | -0.0755 | +| n_updates | 145000 | +| policy_gradient_loss | -0.0702 | +| value_loss | 0.000688 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.48e+03 | +| ep_rew_mean | 0.22 | +| time/ | | +| fps | 309 | +| iterations | 8449 | +| time_elapsed | 27957 | +| total_timesteps | 8651776 | +| train/ | | +| approx_kl | 2.3860676 | +| clip_fraction | 0.432 | +| clip_range | 0.2 | +| entropy_loss | -0.37 | +| explained_variance | -2.97 | +| learning_rate | 0.0001 | +| loss | -0.0935 | +| n_updates | 145010 | +| policy_gradient_loss | -0.0594 | +| value_loss | 0.000418 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.48e+03 | +| ep_rew_mean | 0.22 | +| time/ | | +| fps | 309 | +| iterations | 8450 | +| time_elapsed | 27961 | +| total_timesteps | 8652800 | +| train/ | | +| approx_kl | 3.0395727 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.362 | +| explained_variance | -2.03 | +| learning_rate | 0.0001 | +| loss | -0.0817 | +| n_updates | 145020 | +| policy_gradient_loss | -0.0679 | +| value_loss | 0.000448 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.48e+03 | +| ep_rew_mean | 0.218 | +| time/ | | +| fps | 309 | +| iterations | 8451 | +| time_elapsed | 27964 | +| total_timesteps | 8653824 | +| train/ | | +| approx_kl | 2.4814873 | +| clip_fraction | 0.474 | +| clip_range | 0.2 | +| entropy_loss | -0.34 | +| explained_variance | -2.81 | +| learning_rate | 0.0001 | +| loss | -0.0633 | +| n_updates | 145030 | +| policy_gradient_loss | -0.0658 | +| value_loss | 0.00071 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.48e+03 | +| ep_rew_mean | 0.218 | +| time/ | | +| fps | 309 | +| iterations | 8452 | +| time_elapsed | 27968 | +| total_timesteps | 8654848 | +| train/ | | +| approx_kl | 3.1488214 | +| clip_fraction | 0.462 | +| clip_range | 0.2 | +| entropy_loss | -0.315 | +| explained_variance | -1.81 | +| learning_rate | 0.0001 | +| loss | -0.0608 | +| n_updates | 145040 | +| policy_gradient_loss | -0.0606 | +| value_loss | 0.000361 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.48e+03 | +| ep_rew_mean | 0.218 | +| time/ | | +| fps | 309 | +| iterations | 8453 | +| time_elapsed | 27971 | +| total_timesteps | 8655872 | +| train/ | | +| approx_kl | 1.9295624 | +| clip_fraction | 0.458 | +| clip_range | 0.2 | +| entropy_loss | -0.317 | +| explained_variance | -2.93 | +| learning_rate | 0.0001 | +| loss | -0.083 | +| n_updates | 145050 | +| policy_gradient_loss | -0.0667 | +| value_loss | 0.000333 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.5e+03 | +| ep_rew_mean | 0.217 | +| time/ | | +| fps | 309 | +| iterations | 8454 | +| time_elapsed | 27974 | +| total_timesteps | 8656896 | +| train/ | | +| approx_kl | 2.5110285 | +| clip_fraction | 0.449 | +| clip_range | 0.2 | +| entropy_loss | -0.348 | +| explained_variance | -2.39 | +| learning_rate | 0.0001 | +| loss | -0.0594 | +| n_updates | 145060 | +| policy_gradient_loss | -0.0543 | +| value_loss | 0.000301 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.5e+03 | +| ep_rew_mean | 0.217 | +| time/ | | +| fps | 309 | +| iterations | 8455 | +| time_elapsed | 27977 | +| total_timesteps | 8657920 | +| train/ | | +| approx_kl | 2.9820995 | +| clip_fraction | 0.451 | +| clip_range | 0.2 | +| entropy_loss | -0.313 | +| explained_variance | -5.69 | +| learning_rate | 0.0001 | +| loss | -0.0579 | +| n_updates | 145070 | +| policy_gradient_loss | -0.0663 | +| value_loss | 0.00021 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.5e+03 | +| ep_rew_mean | 0.217 | +| time/ | | +| fps | 309 | +| iterations | 8456 | +| time_elapsed | 27981 | +| total_timesteps | 8658944 | +| train/ | | +| approx_kl | 2.4047184 | +| clip_fraction | 0.499 | +| clip_range | 0.2 | +| entropy_loss | -0.348 | +| explained_variance | -0.972 | +| learning_rate | 0.0001 | +| loss | -0.0856 | +| n_updates | 145080 | +| policy_gradient_loss | -0.0663 | +| value_loss | 0.000791 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.5e+03 | +| ep_rew_mean | 0.216 | +| time/ | | +| fps | 309 | +| iterations | 8457 | +| time_elapsed | 27984 | +| total_timesteps | 8659968 | +| train/ | | +| approx_kl | 1.6917479 | +| clip_fraction | 0.489 | +| clip_range | 0.2 | +| entropy_loss | -0.414 | +| explained_variance | -5.09 | +| learning_rate | 0.0001 | +| loss | -0.0893 | +| n_updates | 145090 | +| policy_gradient_loss | -0.0588 | +| value_loss | 0.000387 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.5e+03 | +| ep_rew_mean | 0.216 | +| time/ | | +| fps | 309 | +| iterations | 8458 | +| time_elapsed | 27987 | +| total_timesteps | 8660992 | +| train/ | | +| approx_kl | 2.9586341 | +| clip_fraction | 0.441 | +| clip_range | 0.2 | +| entropy_loss | -0.288 | +| explained_variance | -2.1 | +| learning_rate | 0.0001 | +| loss | -0.0868 | +| n_updates | 145100 | +| policy_gradient_loss | -0.0595 | +| value_loss | 0.000527 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.49e+03 | +| ep_rew_mean | 0.215 | +| time/ | | +| fps | 309 | +| iterations | 8459 | +| time_elapsed | 27990 | +| total_timesteps | 8662016 | +| train/ | | +| approx_kl | 2.6644113 | +| clip_fraction | 0.463 | +| clip_range | 0.2 | +| entropy_loss | -0.362 | +| explained_variance | -3.26 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 145110 | +| policy_gradient_loss | -0.0657 | +| value_loss | 0.000421 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.47e+03 | +| ep_rew_mean | 0.218 | +| time/ | | +| fps | 309 | +| iterations | 8460 | +| time_elapsed | 27994 | +| total_timesteps | 8663040 | +| train/ | | +| approx_kl | 2.1357386 | +| clip_fraction | 0.444 | +| clip_range | 0.2 | +| entropy_loss | -0.323 | +| explained_variance | -2.59 | +| learning_rate | 0.0001 | +| loss | -0.0945 | +| n_updates | 145120 | +| policy_gradient_loss | -0.0687 | +| value_loss | 0.000618 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.47e+03 | +| ep_rew_mean | 0.218 | +| time/ | | +| fps | 309 | +| iterations | 8461 | +| time_elapsed | 27997 | +| total_timesteps | 8664064 | +| train/ | | +| approx_kl | 2.6015277 | +| clip_fraction | 0.47 | +| clip_range | 0.2 | +| entropy_loss | -0.313 | +| explained_variance | -0.725 | +| learning_rate | 0.0001 | +| loss | -0.0489 | +| n_updates | 145130 | +| policy_gradient_loss | -0.0624 | +| value_loss | 0.000996 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.46e+03 | +| ep_rew_mean | 0.218 | +| time/ | | +| fps | 309 | +| iterations | 8462 | +| time_elapsed | 28000 | +| total_timesteps | 8665088 | +| train/ | | +| approx_kl | 2.5638604 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.352 | +| explained_variance | -4.4 | +| learning_rate | 0.0001 | +| loss | -0.073 | +| n_updates | 145140 | +| policy_gradient_loss | -0.0687 | +| value_loss | 0.000556 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.46e+03 | +| ep_rew_mean | 0.218 | +| time/ | | +| fps | 309 | +| iterations | 8463 | +| time_elapsed | 28003 | +| total_timesteps | 8666112 | +| train/ | | +| approx_kl | 2.5554004 | +| clip_fraction | 0.467 | +| clip_range | 0.2 | +| entropy_loss | -0.349 | +| explained_variance | -7.03 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 145150 | +| policy_gradient_loss | -0.0635 | +| value_loss | 0.000961 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.46e+03 | +| ep_rew_mean | 0.218 | +| time/ | | +| fps | 309 | +| iterations | 8464 | +| time_elapsed | 28007 | +| total_timesteps | 8667136 | +| train/ | | +| approx_kl | 2.0482874 | +| clip_fraction | 0.463 | +| clip_range | 0.2 | +| entropy_loss | -0.345 | +| explained_variance | -3.32 | +| learning_rate | 0.0001 | +| loss | -0.0754 | +| n_updates | 145160 | +| policy_gradient_loss | -0.063 | +| value_loss | 0.000639 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.43e+03 | +| ep_rew_mean | 0.219 | +| time/ | | +| fps | 309 | +| iterations | 8465 | +| time_elapsed | 28010 | +| total_timesteps | 8668160 | +| train/ | | +| approx_kl | 2.104444 | +| clip_fraction | 0.497 | +| clip_range | 0.2 | +| entropy_loss | -0.378 | +| explained_variance | -5.48 | +| learning_rate | 0.0001 | +| loss | -0.092 | +| n_updates | 145170 | +| policy_gradient_loss | -0.0728 | +| value_loss | 0.000284 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.43e+03 | +| ep_rew_mean | 0.219 | +| time/ | | +| fps | 309 | +| iterations | 8466 | +| time_elapsed | 28013 | +| total_timesteps | 8669184 | +| train/ | | +| approx_kl | 3.158608 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.351 | +| explained_variance | -1.56 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 145180 | +| policy_gradient_loss | -0.0639 | +| value_loss | 0.000617 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.41e+03 | +| ep_rew_mean | 0.219 | +| time/ | | +| fps | 309 | +| iterations | 8467 | +| time_elapsed | 28017 | +| total_timesteps | 8670208 | +| train/ | | +| approx_kl | 2.3914719 | +| clip_fraction | 0.458 | +| clip_range | 0.2 | +| entropy_loss | -0.316 | +| explained_variance | -2.74 | +| learning_rate | 0.0001 | +| loss | -0.0801 | +| n_updates | 145190 | +| policy_gradient_loss | -0.0647 | +| value_loss | 0.000807 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.41e+03 | +| ep_rew_mean | 0.219 | +| time/ | | +| fps | 309 | +| iterations | 8468 | +| time_elapsed | 28020 | +| total_timesteps | 8671232 | +| train/ | | +| approx_kl | 2.4328094 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.337 | +| explained_variance | -3.56 | +| learning_rate | 0.0001 | +| loss | -0.108 | +| n_updates | 145200 | +| policy_gradient_loss | -0.0684 | +| value_loss | 0.000753 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.41e+03 | +| ep_rew_mean | 0.218 | +| time/ | | +| fps | 309 | +| iterations | 8469 | +| time_elapsed | 28024 | +| total_timesteps | 8672256 | +| train/ | | +| approx_kl | 2.429128 | +| clip_fraction | 0.499 | +| clip_range | 0.2 | +| entropy_loss | -0.341 | +| explained_variance | -1.14 | +| learning_rate | 0.0001 | +| loss | -0.099 | +| n_updates | 145210 | +| policy_gradient_loss | -0.0712 | +| value_loss | 0.000624 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.41e+03 | +| ep_rew_mean | 0.218 | +| time/ | | +| fps | 309 | +| iterations | 8470 | +| time_elapsed | 28027 | +| total_timesteps | 8673280 | +| train/ | | +| approx_kl | 1.8040607 | +| clip_fraction | 0.425 | +| clip_range | 0.2 | +| entropy_loss | -0.295 | +| explained_variance | -3.37 | +| learning_rate | 0.0001 | +| loss | -0.0884 | +| n_updates | 145220 | +| policy_gradient_loss | -0.0666 | +| value_loss | 0.000451 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.41e+03 | +| ep_rew_mean | 0.22 | +| time/ | | +| fps | 309 | +| iterations | 8471 | +| time_elapsed | 28030 | +| total_timesteps | 8674304 | +| train/ | | +| approx_kl | 3.3164327 | +| clip_fraction | 0.512 | +| clip_range | 0.2 | +| entropy_loss | -0.337 | +| explained_variance | -1.16 | +| learning_rate | 0.0001 | +| loss | -0.0943 | +| n_updates | 145230 | +| policy_gradient_loss | -0.0714 | +| value_loss | 0.000667 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.41e+03 | +| ep_rew_mean | 0.22 | +| time/ | | +| fps | 309 | +| iterations | 8472 | +| time_elapsed | 28034 | +| total_timesteps | 8675328 | +| train/ | | +| approx_kl | 4.01982 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.361 | +| explained_variance | -1.81 | +| learning_rate | 0.0001 | +| loss | -0.0659 | +| n_updates | 145240 | +| policy_gradient_loss | -0.071 | +| value_loss | 0.00042 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.4e+03 | +| ep_rew_mean | 0.224 | +| time/ | | +| fps | 309 | +| iterations | 8473 | +| time_elapsed | 28037 | +| total_timesteps | 8676352 | +| train/ | | +| approx_kl | 3.0386362 | +| clip_fraction | 0.492 | +| clip_range | 0.2 | +| entropy_loss | -0.351 | +| explained_variance | -1.15 | +| learning_rate | 0.0001 | +| loss | -0.0761 | +| n_updates | 145250 | +| policy_gradient_loss | -0.061 | +| value_loss | 0.000814 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.4e+03 | +| ep_rew_mean | 0.224 | +| time/ | | +| fps | 309 | +| iterations | 8474 | +| time_elapsed | 28040 | +| total_timesteps | 8677376 | +| train/ | | +| approx_kl | 2.4547338 | +| clip_fraction | 0.521 | +| clip_range | 0.2 | +| entropy_loss | -0.371 | +| explained_variance | -1.53 | +| learning_rate | 0.0001 | +| loss | -0.0725 | +| n_updates | 145260 | +| policy_gradient_loss | -0.0771 | +| value_loss | 0.000931 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.4e+03 | +| ep_rew_mean | 0.224 | +| time/ | | +| fps | 309 | +| iterations | 8475 | +| time_elapsed | 28043 | +| total_timesteps | 8678400 | +| train/ | | +| approx_kl | 2.3346148 | +| clip_fraction | 0.504 | +| clip_range | 0.2 | +| entropy_loss | -0.381 | +| explained_variance | -1.57 | +| learning_rate | 0.0001 | +| loss | -0.0761 | +| n_updates | 145270 | +| policy_gradient_loss | -0.0733 | +| value_loss | 0.000813 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.4e+03 | +| ep_rew_mean | 0.224 | +| time/ | | +| fps | 309 | +| iterations | 8476 | +| time_elapsed | 28046 | +| total_timesteps | 8679424 | +| train/ | | +| approx_kl | 2.6416254 | +| clip_fraction | 0.454 | +| clip_range | 0.2 | +| entropy_loss | -0.361 | +| explained_variance | -1.77 | +| learning_rate | 0.0001 | +| loss | -0.0572 | +| n_updates | 145280 | +| policy_gradient_loss | -0.0589 | +| value_loss | 0.000921 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.4e+03 | +| ep_rew_mean | 0.226 | +| time/ | | +| fps | 309 | +| iterations | 8477 | +| time_elapsed | 28049 | +| total_timesteps | 8680448 | +| train/ | | +| approx_kl | 3.032978 | +| clip_fraction | 0.506 | +| clip_range | 0.2 | +| entropy_loss | -0.353 | +| explained_variance | -6.73 | +| learning_rate | 0.0001 | +| loss | -0.0827 | +| n_updates | 145290 | +| policy_gradient_loss | -0.075 | +| value_loss | 0.000534 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.4e+03 | +| ep_rew_mean | 0.226 | +| time/ | | +| fps | 309 | +| iterations | 8478 | +| time_elapsed | 28053 | +| total_timesteps | 8681472 | +| train/ | | +| approx_kl | 2.3238964 | +| clip_fraction | 0.444 | +| clip_range | 0.2 | +| entropy_loss | -0.322 | +| explained_variance | -1.44 | +| learning_rate | 0.0001 | +| loss | -0.0711 | +| n_updates | 145300 | +| policy_gradient_loss | -0.0683 | +| value_loss | 0.000691 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.4e+03 | +| ep_rew_mean | 0.224 | +| time/ | | +| fps | 309 | +| iterations | 8479 | +| time_elapsed | 28056 | +| total_timesteps | 8682496 | +| train/ | | +| approx_kl | 2.88668 | +| clip_fraction | 0.519 | +| clip_range | 0.2 | +| entropy_loss | -0.343 | +| explained_variance | -1.71 | +| learning_rate | 0.0001 | +| loss | -0.105 | +| n_updates | 145310 | +| policy_gradient_loss | -0.0756 | +| value_loss | 0.000512 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.4e+03 | +| ep_rew_mean | 0.224 | +| time/ | | +| fps | 309 | +| iterations | 8480 | +| time_elapsed | 28059 | +| total_timesteps | 8683520 | +| train/ | | +| approx_kl | 2.284843 | +| clip_fraction | 0.46 | +| clip_range | 0.2 | +| entropy_loss | -0.324 | +| explained_variance | -1.31 | +| learning_rate | 0.0001 | +| loss | -0.0817 | +| n_updates | 145320 | +| policy_gradient_loss | -0.0608 | +| value_loss | 0.000567 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.4e+03 | +| ep_rew_mean | 0.224 | +| time/ | | +| fps | 309 | +| iterations | 8481 | +| time_elapsed | 28062 | +| total_timesteps | 8684544 | +| train/ | | +| approx_kl | 2.1195579 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.365 | +| explained_variance | -1.13 | +| learning_rate | 0.0001 | +| loss | -0.0771 | +| n_updates | 145330 | +| policy_gradient_loss | -0.0652 | +| value_loss | 0.000777 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.4e+03 | +| ep_rew_mean | 0.224 | +| time/ | | +| fps | 309 | +| iterations | 8482 | +| time_elapsed | 28066 | +| total_timesteps | 8685568 | +| train/ | | +| approx_kl | 2.3696504 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.364 | +| explained_variance | -1.23 | +| learning_rate | 0.0001 | +| loss | -0.0599 | +| n_updates | 145340 | +| policy_gradient_loss | -0.0626 | +| value_loss | 0.000534 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.4e+03 | +| ep_rew_mean | 0.224 | +| time/ | | +| fps | 309 | +| iterations | 8483 | +| time_elapsed | 28069 | +| total_timesteps | 8686592 | +| train/ | | +| approx_kl | 2.747328 | +| clip_fraction | 0.453 | +| clip_range | 0.2 | +| entropy_loss | -0.323 | +| explained_variance | -3.18 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 145350 | +| policy_gradient_loss | -0.0653 | +| value_loss | 0.000609 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.4e+03 | +| ep_rew_mean | 0.225 | +| time/ | | +| fps | 309 | +| iterations | 8484 | +| time_elapsed | 28073 | +| total_timesteps | 8687616 | +| train/ | | +| approx_kl | 2.5012407 | +| clip_fraction | 0.507 | +| clip_range | 0.2 | +| entropy_loss | -0.366 | +| explained_variance | -2.37 | +| learning_rate | 0.0001 | +| loss | -0.0834 | +| n_updates | 145360 | +| policy_gradient_loss | -0.0722 | +| value_loss | 0.000463 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.39e+03 | +| ep_rew_mean | 0.228 | +| time/ | | +| fps | 309 | +| iterations | 8485 | +| time_elapsed | 28076 | +| total_timesteps | 8688640 | +| train/ | | +| approx_kl | 2.9288843 | +| clip_fraction | 0.476 | +| clip_range | 0.2 | +| entropy_loss | -0.337 | +| explained_variance | -1.21 | +| learning_rate | 0.0001 | +| loss | -0.092 | +| n_updates | 145370 | +| policy_gradient_loss | -0.0653 | +| value_loss | 0.000648 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.39e+03 | +| ep_rew_mean | 0.228 | +| time/ | | +| fps | 309 | +| iterations | 8486 | +| time_elapsed | 28080 | +| total_timesteps | 8689664 | +| train/ | | +| approx_kl | 2.127803 | +| clip_fraction | 0.499 | +| clip_range | 0.2 | +| entropy_loss | -0.4 | +| explained_variance | -1.53 | +| learning_rate | 0.0001 | +| loss | -0.0616 | +| n_updates | 145380 | +| policy_gradient_loss | -0.0669 | +| value_loss | 0.000527 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.39e+03 | +| ep_rew_mean | 0.228 | +| time/ | | +| fps | 309 | +| iterations | 8487 | +| time_elapsed | 28083 | +| total_timesteps | 8690688 | +| train/ | | +| approx_kl | 2.3223977 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.33 | +| explained_variance | -4.95 | +| learning_rate | 0.0001 | +| loss | -0.0976 | +| n_updates | 145390 | +| policy_gradient_loss | -0.0666 | +| value_loss | 0.000576 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.39e+03 | +| ep_rew_mean | 0.232 | +| time/ | | +| fps | 309 | +| iterations | 8488 | +| time_elapsed | 28087 | +| total_timesteps | 8691712 | +| train/ | | +| approx_kl | 2.2349539 | +| clip_fraction | 0.516 | +| clip_range | 0.2 | +| entropy_loss | -0.399 | +| explained_variance | -1.18 | +| learning_rate | 0.0001 | +| loss | -0.0821 | +| n_updates | 145400 | +| policy_gradient_loss | -0.0685 | +| value_loss | 0.000504 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.39e+03 | +| ep_rew_mean | 0.232 | +| time/ | | +| fps | 309 | +| iterations | 8489 | +| time_elapsed | 28090 | +| total_timesteps | 8692736 | +| train/ | | +| approx_kl | 2.1591508 | +| clip_fraction | 0.445 | +| clip_range | 0.2 | +| entropy_loss | -0.328 | +| explained_variance | -1.87 | +| learning_rate | 0.0001 | +| loss | -0.0921 | +| n_updates | 145410 | +| policy_gradient_loss | -0.0703 | +| value_loss | 0.000807 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.4e+03 | +| ep_rew_mean | 0.232 | +| time/ | | +| fps | 309 | +| iterations | 8490 | +| time_elapsed | 28093 | +| total_timesteps | 8693760 | +| train/ | | +| approx_kl | 2.2738068 | +| clip_fraction | 0.492 | +| clip_range | 0.2 | +| entropy_loss | -0.364 | +| explained_variance | -2.61 | +| learning_rate | 0.0001 | +| loss | -0.0915 | +| n_updates | 145420 | +| policy_gradient_loss | -0.0745 | +| value_loss | 0.00037 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.4e+03 | +| ep_rew_mean | 0.232 | +| time/ | | +| fps | 309 | +| iterations | 8491 | +| time_elapsed | 28096 | +| total_timesteps | 8694784 | +| train/ | | +| approx_kl | 7.900146 | +| clip_fraction | 0.464 | +| clip_range | 0.2 | +| entropy_loss | -0.325 | +| explained_variance | -2.69 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 145430 | +| policy_gradient_loss | -0.0658 | +| value_loss | 0.000475 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.4e+03 | +| ep_rew_mean | 0.232 | +| time/ | | +| fps | 309 | +| iterations | 8492 | +| time_elapsed | 28099 | +| total_timesteps | 8695808 | +| train/ | | +| approx_kl | 2.77225 | +| clip_fraction | 0.515 | +| clip_range | 0.2 | +| entropy_loss | -0.381 | +| explained_variance | -0.834 | +| learning_rate | 0.0001 | +| loss | -0.0881 | +| n_updates | 145440 | +| policy_gradient_loss | -0.0691 | +| value_loss | 0.00075 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.39e+03 | +| ep_rew_mean | 0.233 | +| time/ | | +| fps | 309 | +| iterations | 8493 | +| time_elapsed | 28102 | +| total_timesteps | 8696832 | +| train/ | | +| approx_kl | 2.677402 | +| clip_fraction | 0.512 | +| clip_range | 0.2 | +| entropy_loss | -0.35 | +| explained_variance | -9.2 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 145450 | +| policy_gradient_loss | -0.0725 | +| value_loss | 0.000347 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.39e+03 | +| ep_rew_mean | 0.233 | +| time/ | | +| fps | 309 | +| iterations | 8494 | +| time_elapsed | 28106 | +| total_timesteps | 8697856 | +| train/ | | +| approx_kl | 3.2649715 | +| clip_fraction | 0.442 | +| clip_range | 0.2 | +| entropy_loss | -0.327 | +| explained_variance | -1.25 | +| learning_rate | 0.0001 | +| loss | -0.0825 | +| n_updates | 145460 | +| policy_gradient_loss | -0.0677 | +| value_loss | 0.0009 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.39e+03 | +| ep_rew_mean | 0.236 | +| time/ | | +| fps | 309 | +| iterations | 8495 | +| time_elapsed | 28109 | +| total_timesteps | 8698880 | +| train/ | | +| approx_kl | 2.1948075 | +| clip_fraction | 0.461 | +| clip_range | 0.2 | +| entropy_loss | -0.372 | +| explained_variance | -3.85 | +| learning_rate | 0.0001 | +| loss | -0.0963 | +| n_updates | 145470 | +| policy_gradient_loss | -0.0592 | +| value_loss | 0.00045 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.39e+03 | +| ep_rew_mean | 0.236 | +| time/ | | +| fps | 309 | +| iterations | 8496 | +| time_elapsed | 28112 | +| total_timesteps | 8699904 | +| train/ | | +| approx_kl | 2.9492903 | +| clip_fraction | 0.492 | +| clip_range | 0.2 | +| entropy_loss | -0.326 | +| explained_variance | -1.68 | +| learning_rate | 0.0001 | +| loss | -0.078 | +| n_updates | 145480 | +| policy_gradient_loss | -0.0711 | +| value_loss | 0.000549 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.39e+03 | +| ep_rew_mean | 0.234 | +| time/ | | +| fps | 309 | +| iterations | 8497 | +| time_elapsed | 28115 | +| total_timesteps | 8700928 | +| train/ | | +| approx_kl | 2.846617 | +| clip_fraction | 0.469 | +| clip_range | 0.2 | +| entropy_loss | -0.336 | +| explained_variance | -3.68 | +| learning_rate | 0.0001 | +| loss | -0.113 | +| n_updates | 145490 | +| policy_gradient_loss | -0.0681 | +| value_loss | 0.000376 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.39e+03 | +| ep_rew_mean | 0.234 | +| time/ | | +| fps | 309 | +| iterations | 8498 | +| time_elapsed | 28118 | +| total_timesteps | 8701952 | +| train/ | | +| approx_kl | 2.5547388 | +| clip_fraction | 0.473 | +| clip_range | 0.2 | +| entropy_loss | -0.327 | +| explained_variance | -1.46 | +| learning_rate | 0.0001 | +| loss | -0.0884 | +| n_updates | 145500 | +| policy_gradient_loss | -0.0687 | +| value_loss | 0.000743 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.39e+03 | +| ep_rew_mean | 0.234 | +| time/ | | +| fps | 309 | +| iterations | 8499 | +| time_elapsed | 28122 | +| total_timesteps | 8702976 | +| train/ | | +| approx_kl | 3.2241757 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.347 | +| explained_variance | -1.48 | +| learning_rate | 0.0001 | +| loss | -0.0791 | +| n_updates | 145510 | +| policy_gradient_loss | -0.0688 | +| value_loss | 0.000726 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.4e+03 | +| ep_rew_mean | 0.234 | +| time/ | | +| fps | 309 | +| iterations | 8500 | +| time_elapsed | 28125 | +| total_timesteps | 8704000 | +| train/ | | +| approx_kl | 2.63471 | +| clip_fraction | 0.5 | +| clip_range | 0.2 | +| entropy_loss | -0.352 | +| explained_variance | -3.7 | +| learning_rate | 0.0001 | +| loss | -0.0853 | +| n_updates | 145520 | +| policy_gradient_loss | -0.071 | +| value_loss | 0.000351 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.4e+03 | +| ep_rew_mean | 0.234 | +| time/ | | +| fps | 309 | +| iterations | 8501 | +| time_elapsed | 28129 | +| total_timesteps | 8705024 | +| train/ | | +| approx_kl | 3.7711616 | +| clip_fraction | 0.472 | +| clip_range | 0.2 | +| entropy_loss | -0.309 | +| explained_variance | -1.5 | +| learning_rate | 0.0001 | +| loss | -0.0909 | +| n_updates | 145530 | +| policy_gradient_loss | -0.0714 | +| value_loss | 0.000777 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.4e+03 | +| ep_rew_mean | 0.234 | +| time/ | | +| fps | 309 | +| iterations | 8502 | +| time_elapsed | 28132 | +| total_timesteps | 8706048 | +| train/ | | +| approx_kl | 3.1413734 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.327 | +| explained_variance | -2.08 | +| learning_rate | 0.0001 | +| loss | -0.0796 | +| n_updates | 145540 | +| policy_gradient_loss | -0.0652 | +| value_loss | 0.00106 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.4e+03 | +| ep_rew_mean | 0.237 | +| time/ | | +| fps | 309 | +| iterations | 8503 | +| time_elapsed | 28136 | +| total_timesteps | 8707072 | +| train/ | | +| approx_kl | 2.109035 | +| clip_fraction | 0.494 | +| clip_range | 0.2 | +| entropy_loss | -0.323 | +| explained_variance | -3.73 | +| learning_rate | 0.0001 | +| loss | -0.0756 | +| n_updates | 145550 | +| policy_gradient_loss | -0.0729 | +| value_loss | 0.000806 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.39e+03 | +| ep_rew_mean | 0.234 | +| time/ | | +| fps | 309 | +| iterations | 8504 | +| time_elapsed | 28139 | +| total_timesteps | 8708096 | +| train/ | | +| approx_kl | 2.884307 | +| clip_fraction | 0.464 | +| clip_range | 0.2 | +| entropy_loss | -0.323 | +| explained_variance | -5.08 | +| learning_rate | 0.0001 | +| loss | -0.0914 | +| n_updates | 145560 | +| policy_gradient_loss | -0.07 | +| value_loss | 0.000765 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.39e+03 | +| ep_rew_mean | 0.234 | +| time/ | | +| fps | 309 | +| iterations | 8505 | +| time_elapsed | 28142 | +| total_timesteps | 8709120 | +| train/ | | +| approx_kl | 2.498598 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.328 | +| explained_variance | -3.77 | +| learning_rate | 0.0001 | +| loss | -0.0973 | +| n_updates | 145570 | +| policy_gradient_loss | -0.0634 | +| value_loss | 0.000536 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.39e+03 | +| ep_rew_mean | 0.234 | +| time/ | | +| fps | 309 | +| iterations | 8506 | +| time_elapsed | 28146 | +| total_timesteps | 8710144 | +| train/ | | +| approx_kl | 11.694918 | +| clip_fraction | 0.52 | +| clip_range | 0.2 | +| entropy_loss | -0.365 | +| explained_variance | -0.934 | +| learning_rate | 0.0001 | +| loss | -0.0794 | +| n_updates | 145580 | +| policy_gradient_loss | -0.0705 | +| value_loss | 0.000439 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.4e+03 | +| ep_rew_mean | 0.23 | +| time/ | | +| fps | 309 | +| iterations | 8507 | +| time_elapsed | 28149 | +| total_timesteps | 8711168 | +| train/ | | +| approx_kl | 2.3215837 | +| clip_fraction | 0.491 | +| clip_range | 0.2 | +| entropy_loss | -0.357 | +| explained_variance | -2.01 | +| learning_rate | 0.0001 | +| loss | -0.0607 | +| n_updates | 145590 | +| policy_gradient_loss | -0.0616 | +| value_loss | 0.000429 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.4e+03 | +| ep_rew_mean | 0.23 | +| time/ | | +| fps | 309 | +| iterations | 8508 | +| time_elapsed | 28152 | +| total_timesteps | 8712192 | +| train/ | | +| approx_kl | 2.4018629 | +| clip_fraction | 0.492 | +| clip_range | 0.2 | +| entropy_loss | -0.341 | +| explained_variance | -4.36 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 145600 | +| policy_gradient_loss | -0.0704 | +| value_loss | 0.000413 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.41e+03 | +| ep_rew_mean | 0.227 | +| time/ | | +| fps | 309 | +| iterations | 8509 | +| time_elapsed | 28155 | +| total_timesteps | 8713216 | +| train/ | | +| approx_kl | 1.7225928 | +| clip_fraction | 0.456 | +| clip_range | 0.2 | +| entropy_loss | -0.366 | +| explained_variance | -0.368 | +| learning_rate | 0.0001 | +| loss | -0.0636 | +| n_updates | 145610 | +| policy_gradient_loss | -0.0569 | +| value_loss | 0.000562 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.41e+03 | +| ep_rew_mean | 0.227 | +| time/ | | +| fps | 309 | +| iterations | 8510 | +| time_elapsed | 28159 | +| total_timesteps | 8714240 | +| train/ | | +| approx_kl | 3.589385 | +| clip_fraction | 0.479 | +| clip_range | 0.2 | +| entropy_loss | -0.337 | +| explained_variance | -7.03 | +| learning_rate | 0.0001 | +| loss | -0.0949 | +| n_updates | 145620 | +| policy_gradient_loss | -0.073 | +| value_loss | 0.00035 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.41e+03 | +| ep_rew_mean | 0.231 | +| time/ | | +| fps | 309 | +| iterations | 8511 | +| time_elapsed | 28162 | +| total_timesteps | 8715264 | +| train/ | | +| approx_kl | 2.0751846 | +| clip_fraction | 0.504 | +| clip_range | 0.2 | +| entropy_loss | -0.347 | +| explained_variance | -0.775 | +| learning_rate | 0.0001 | +| loss | -0.0775 | +| n_updates | 145630 | +| policy_gradient_loss | -0.0665 | +| value_loss | 0.000717 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.41e+03 | +| ep_rew_mean | 0.231 | +| time/ | | +| fps | 309 | +| iterations | 8512 | +| time_elapsed | 28165 | +| total_timesteps | 8716288 | +| train/ | | +| approx_kl | 2.2844753 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.323 | +| explained_variance | -3.6 | +| learning_rate | 0.0001 | +| loss | -0.0433 | +| n_updates | 145640 | +| policy_gradient_loss | -0.0648 | +| value_loss | 0.000585 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.41e+03 | +| ep_rew_mean | 0.231 | +| time/ | | +| fps | 309 | +| iterations | 8513 | +| time_elapsed | 28168 | +| total_timesteps | 8717312 | +| train/ | | +| approx_kl | 2.6938004 | +| clip_fraction | 0.504 | +| clip_range | 0.2 | +| entropy_loss | -0.386 | +| explained_variance | -1.18 | +| learning_rate | 0.0001 | +| loss | -0.0723 | +| n_updates | 145650 | +| policy_gradient_loss | -0.0626 | +| value_loss | 0.000489 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.42e+03 | +| ep_rew_mean | 0.229 | +| time/ | | +| fps | 309 | +| iterations | 8514 | +| time_elapsed | 28171 | +| total_timesteps | 8718336 | +| train/ | | +| approx_kl | 2.5512018 | +| clip_fraction | 0.506 | +| clip_range | 0.2 | +| entropy_loss | -0.381 | +| explained_variance | -5.23 | +| learning_rate | 0.0001 | +| loss | -0.11 | +| n_updates | 145660 | +| policy_gradient_loss | -0.0724 | +| value_loss | 0.00031 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.42e+03 | +| ep_rew_mean | 0.229 | +| time/ | | +| fps | 309 | +| iterations | 8515 | +| time_elapsed | 28174 | +| total_timesteps | 8719360 | +| train/ | | +| approx_kl | 2.6472785 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.384 | +| explained_variance | -1.06 | +| learning_rate | 0.0001 | +| loss | -0.0639 | +| n_updates | 145670 | +| policy_gradient_loss | -0.0592 | +| value_loss | 0.000524 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.41e+03 | +| ep_rew_mean | 0.233 | +| time/ | | +| fps | 309 | +| iterations | 8516 | +| time_elapsed | 28178 | +| total_timesteps | 8720384 | +| train/ | | +| approx_kl | 2.3488898 | +| clip_fraction | 0.503 | +| clip_range | 0.2 | +| entropy_loss | -0.392 | +| explained_variance | -1.02 | +| learning_rate | 0.0001 | +| loss | -0.0934 | +| n_updates | 145680 | +| policy_gradient_loss | -0.0664 | +| value_loss | 0.000681 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.41e+03 | +| ep_rew_mean | 0.233 | +| time/ | | +| fps | 309 | +| iterations | 8517 | +| time_elapsed | 28181 | +| total_timesteps | 8721408 | +| train/ | | +| approx_kl | 2.4377236 | +| clip_fraction | 0.499 | +| clip_range | 0.2 | +| entropy_loss | -0.346 | +| explained_variance | -1.98 | +| learning_rate | 0.0001 | +| loss | -0.0981 | +| n_updates | 145690 | +| policy_gradient_loss | -0.0735 | +| value_loss | 0.000663 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.41e+03 | +| ep_rew_mean | 0.233 | +| time/ | | +| fps | 309 | +| iterations | 8518 | +| time_elapsed | 28185 | +| total_timesteps | 8722432 | +| train/ | | +| approx_kl | 2.688953 | +| clip_fraction | 0.51 | +| clip_range | 0.2 | +| entropy_loss | -0.38 | +| explained_variance | -2.41 | +| learning_rate | 0.0001 | +| loss | -0.0804 | +| n_updates | 145700 | +| policy_gradient_loss | -0.0651 | +| value_loss | 0.000451 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.42e+03 | +| ep_rew_mean | 0.234 | +| time/ | | +| fps | 309 | +| iterations | 8519 | +| time_elapsed | 28188 | +| total_timesteps | 8723456 | +| train/ | | +| approx_kl | 3.2345142 | +| clip_fraction | 0.515 | +| clip_range | 0.2 | +| entropy_loss | -0.396 | +| explained_variance | -2.16 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 145710 | +| policy_gradient_loss | -0.0749 | +| value_loss | 0.000442 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.42e+03 | +| ep_rew_mean | 0.234 | +| time/ | | +| fps | 309 | +| iterations | 8520 | +| time_elapsed | 28192 | +| total_timesteps | 8724480 | +| train/ | | +| approx_kl | 2.7254653 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.356 | +| explained_variance | -5.64 | +| learning_rate | 0.0001 | +| loss | -0.0838 | +| n_updates | 145720 | +| policy_gradient_loss | -0.0714 | +| value_loss | 0.000548 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.42e+03 | +| ep_rew_mean | 0.233 | +| time/ | | +| fps | 309 | +| iterations | 8521 | +| time_elapsed | 28195 | +| total_timesteps | 8725504 | +| train/ | | +| approx_kl | 2.5005662 | +| clip_fraction | 0.491 | +| clip_range | 0.2 | +| entropy_loss | -0.359 | +| explained_variance | -2.98 | +| learning_rate | 0.0001 | +| loss | -0.0806 | +| n_updates | 145730 | +| policy_gradient_loss | -0.0701 | +| value_loss | 0.000755 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.42e+03 | +| ep_rew_mean | 0.233 | +| time/ | | +| fps | 309 | +| iterations | 8522 | +| time_elapsed | 28199 | +| total_timesteps | 8726528 | +| train/ | | +| approx_kl | 2.189185 | +| clip_fraction | 0.506 | +| clip_range | 0.2 | +| entropy_loss | -0.379 | +| explained_variance | -2.76 | +| learning_rate | 0.0001 | +| loss | -0.0727 | +| n_updates | 145740 | +| policy_gradient_loss | -0.0709 | +| value_loss | 0.000689 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.42e+03 | +| ep_rew_mean | 0.233 | +| time/ | | +| fps | 309 | +| iterations | 8523 | +| time_elapsed | 28202 | +| total_timesteps | 8727552 | +| train/ | | +| approx_kl | 2.2727132 | +| clip_fraction | 0.479 | +| clip_range | 0.2 | +| entropy_loss | -0.371 | +| explained_variance | -5.38 | +| learning_rate | 0.0001 | +| loss | -0.094 | +| n_updates | 145750 | +| policy_gradient_loss | -0.0652 | +| value_loss | 0.000778 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.42e+03 | +| ep_rew_mean | 0.233 | +| time/ | | +| fps | 309 | +| iterations | 8524 | +| time_elapsed | 28206 | +| total_timesteps | 8728576 | +| train/ | | +| approx_kl | 2.3177328 | +| clip_fraction | 0.474 | +| clip_range | 0.2 | +| entropy_loss | -0.379 | +| explained_variance | -1.81 | +| learning_rate | 0.0001 | +| loss | -0.0448 | +| n_updates | 145760 | +| policy_gradient_loss | -0.0632 | +| value_loss | 0.000631 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.44e+03 | +| ep_rew_mean | 0.234 | +| time/ | | +| fps | 309 | +| iterations | 8525 | +| time_elapsed | 28209 | +| total_timesteps | 8729600 | +| train/ | | +| approx_kl | 2.1055794 | +| clip_fraction | 0.51 | +| clip_range | 0.2 | +| entropy_loss | -0.384 | +| explained_variance | -1.9 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 145770 | +| policy_gradient_loss | -0.0721 | +| value_loss | 0.000501 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.43e+03 | +| ep_rew_mean | 0.23 | +| time/ | | +| fps | 309 | +| iterations | 8526 | +| time_elapsed | 28212 | +| total_timesteps | 8730624 | +| train/ | | +| approx_kl | 2.8184597 | +| clip_fraction | 0.478 | +| clip_range | 0.2 | +| entropy_loss | -0.36 | +| explained_variance | -10.1 | +| learning_rate | 0.0001 | +| loss | -0.0676 | +| n_updates | 145780 | +| policy_gradient_loss | -0.0693 | +| value_loss | 0.000351 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.41e+03 | +| ep_rew_mean | 0.233 | +| time/ | | +| fps | 309 | +| iterations | 8527 | +| time_elapsed | 28216 | +| total_timesteps | 8731648 | +| train/ | | +| approx_kl | 2.9273686 | +| clip_fraction | 0.466 | +| clip_range | 0.2 | +| entropy_loss | -0.342 | +| explained_variance | -0.521 | +| learning_rate | 0.0001 | +| loss | -0.0882 | +| n_updates | 145790 | +| policy_gradient_loss | -0.0621 | +| value_loss | 0.000574 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.41e+03 | +| ep_rew_mean | 0.233 | +| time/ | | +| fps | 309 | +| iterations | 8528 | +| time_elapsed | 28219 | +| total_timesteps | 8732672 | +| train/ | | +| approx_kl | 2.5619338 | +| clip_fraction | 0.512 | +| clip_range | 0.2 | +| entropy_loss | -0.408 | +| explained_variance | -1.14 | +| learning_rate | 0.0001 | +| loss | -0.09 | +| n_updates | 145800 | +| policy_gradient_loss | -0.0682 | +| value_loss | 0.00102 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.39e+03 | +| ep_rew_mean | 0.235 | +| time/ | | +| fps | 309 | +| iterations | 8529 | +| time_elapsed | 28222 | +| total_timesteps | 8733696 | +| train/ | | +| approx_kl | 2.3015952 | +| clip_fraction | 0.512 | +| clip_range | 0.2 | +| entropy_loss | -0.405 | +| explained_variance | -1.08 | +| learning_rate | 0.0001 | +| loss | -0.0782 | +| n_updates | 145810 | +| policy_gradient_loss | -0.07 | +| value_loss | 0.000752 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.39e+03 | +| ep_rew_mean | 0.235 | +| time/ | | +| fps | 309 | +| iterations | 8530 | +| time_elapsed | 28225 | +| total_timesteps | 8734720 | +| train/ | | +| approx_kl | 2.534237 | +| clip_fraction | 0.503 | +| clip_range | 0.2 | +| entropy_loss | -0.355 | +| explained_variance | -1.37 | +| learning_rate | 0.0001 | +| loss | -0.077 | +| n_updates | 145820 | +| policy_gradient_loss | -0.0628 | +| value_loss | 0.000595 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.39e+03 | +| ep_rew_mean | 0.238 | +| time/ | | +| fps | 309 | +| iterations | 8531 | +| time_elapsed | 28228 | +| total_timesteps | 8735744 | +| train/ | | +| approx_kl | 2.3952017 | +| clip_fraction | 0.514 | +| clip_range | 0.2 | +| entropy_loss | -0.397 | +| explained_variance | -1.3 | +| learning_rate | 0.0001 | +| loss | -0.114 | +| n_updates | 145830 | +| policy_gradient_loss | -0.0771 | +| value_loss | 0.000619 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.39e+03 | +| ep_rew_mean | 0.238 | +| time/ | | +| fps | 309 | +| iterations | 8532 | +| time_elapsed | 28232 | +| total_timesteps | 8736768 | +| train/ | | +| approx_kl | 2.93091 | +| clip_fraction | 0.477 | +| clip_range | 0.2 | +| entropy_loss | -0.346 | +| explained_variance | -4.71 | +| learning_rate | 0.0001 | +| loss | -0.0957 | +| n_updates | 145840 | +| policy_gradient_loss | -0.0737 | +| value_loss | 0.000788 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.4e+03 | +| ep_rew_mean | 0.233 | +| time/ | | +| fps | 309 | +| iterations | 8533 | +| time_elapsed | 28235 | +| total_timesteps | 8737792 | +| train/ | | +| approx_kl | 4.1136885 | +| clip_fraction | 0.468 | +| clip_range | 0.2 | +| entropy_loss | -0.357 | +| explained_variance | -2.6 | +| learning_rate | 0.0001 | +| loss | -0.0797 | +| n_updates | 145850 | +| policy_gradient_loss | -0.0626 | +| value_loss | 0.000393 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.4e+03 | +| ep_rew_mean | 0.233 | +| time/ | | +| fps | 309 | +| iterations | 8534 | +| time_elapsed | 28238 | +| total_timesteps | 8738816 | +| train/ | | +| approx_kl | 2.029109 | +| clip_fraction | 0.461 | +| clip_range | 0.2 | +| entropy_loss | -0.348 | +| explained_variance | -4.28 | +| learning_rate | 0.0001 | +| loss | -0.0901 | +| n_updates | 145860 | +| policy_gradient_loss | -0.0673 | +| value_loss | 0.000395 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.39e+03 | +| ep_rew_mean | 0.233 | +| time/ | | +| fps | 309 | +| iterations | 8535 | +| time_elapsed | 28241 | +| total_timesteps | 8739840 | +| train/ | | +| approx_kl | 2.470674 | +| clip_fraction | 0.506 | +| clip_range | 0.2 | +| entropy_loss | -0.387 | +| explained_variance | -1 | +| learning_rate | 0.0001 | +| loss | -0.0753 | +| n_updates | 145870 | +| policy_gradient_loss | -0.0662 | +| value_loss | 0.000759 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.39e+03 | +| ep_rew_mean | 0.233 | +| time/ | | +| fps | 309 | +| iterations | 8536 | +| time_elapsed | 28245 | +| total_timesteps | 8740864 | +| train/ | | +| approx_kl | 2.129831 | +| clip_fraction | 0.473 | +| clip_range | 0.2 | +| entropy_loss | -0.34 | +| explained_variance | -3.47 | +| learning_rate | 0.0001 | +| loss | -0.0761 | +| n_updates | 145880 | +| policy_gradient_loss | -0.0739 | +| value_loss | 0.000702 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.39e+03 | +| ep_rew_mean | 0.233 | +| time/ | | +| fps | 309 | +| iterations | 8537 | +| time_elapsed | 28248 | +| total_timesteps | 8741888 | +| train/ | | +| approx_kl | 2.5739768 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.342 | +| explained_variance | -1.89 | +| learning_rate | 0.0001 | +| loss | -0.0924 | +| n_updates | 145890 | +| policy_gradient_loss | -0.0694 | +| value_loss | 0.000708 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.39e+03 | +| ep_rew_mean | 0.232 | +| time/ | | +| fps | 309 | +| iterations | 8538 | +| time_elapsed | 28251 | +| total_timesteps | 8742912 | +| train/ | | +| approx_kl | 2.617952 | +| clip_fraction | 0.497 | +| clip_range | 0.2 | +| entropy_loss | -0.392 | +| explained_variance | -1.71 | +| learning_rate | 0.0001 | +| loss | -0.0802 | +| n_updates | 145900 | +| policy_gradient_loss | -0.066 | +| value_loss | 0.000417 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.39e+03 | +| ep_rew_mean | 0.232 | +| time/ | | +| fps | 309 | +| iterations | 8539 | +| time_elapsed | 28254 | +| total_timesteps | 8743936 | +| train/ | | +| approx_kl | 2.823381 | +| clip_fraction | 0.497 | +| clip_range | 0.2 | +| entropy_loss | -0.359 | +| explained_variance | -2.32 | +| learning_rate | 0.0001 | +| loss | -0.0772 | +| n_updates | 145910 | +| policy_gradient_loss | -0.0738 | +| value_loss | 0.000475 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.38e+03 | +| ep_rew_mean | 0.23 | +| time/ | | +| fps | 309 | +| iterations | 8540 | +| time_elapsed | 28258 | +| total_timesteps | 8744960 | +| train/ | | +| approx_kl | 26.024569 | +| clip_fraction | 0.453 | +| clip_range | 0.2 | +| entropy_loss | -0.346 | +| explained_variance | -1.6 | +| learning_rate | 0.0001 | +| loss | -0.106 | +| n_updates | 145920 | +| policy_gradient_loss | -0.0643 | +| value_loss | 0.000597 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.38e+03 | +| ep_rew_mean | 0.23 | +| time/ | | +| fps | 309 | +| iterations | 8541 | +| time_elapsed | 28261 | +| total_timesteps | 8745984 | +| train/ | | +| approx_kl | 2.791518 | +| clip_fraction | 0.479 | +| clip_range | 0.2 | +| entropy_loss | -0.352 | +| explained_variance | -9.64 | +| learning_rate | 0.0001 | +| loss | -0.0834 | +| n_updates | 145930 | +| policy_gradient_loss | -0.066 | +| value_loss | 0.000418 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.38e+03 | +| ep_rew_mean | 0.225 | +| time/ | | +| fps | 309 | +| iterations | 8542 | +| time_elapsed | 28265 | +| total_timesteps | 8747008 | +| train/ | | +| approx_kl | 2.7400756 | +| clip_fraction | 0.504 | +| clip_range | 0.2 | +| entropy_loss | -0.339 | +| explained_variance | -6.01 | +| learning_rate | 0.0001 | +| loss | -0.0998 | +| n_updates | 145940 | +| policy_gradient_loss | -0.0763 | +| value_loss | 0.00047 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.38e+03 | +| ep_rew_mean | 0.225 | +| time/ | | +| fps | 309 | +| iterations | 8543 | +| time_elapsed | 28268 | +| total_timesteps | 8748032 | +| train/ | | +| approx_kl | 2.698453 | +| clip_fraction | 0.467 | +| clip_range | 0.2 | +| entropy_loss | -0.331 | +| explained_variance | -1.88 | +| learning_rate | 0.0001 | +| loss | -0.0764 | +| n_updates | 145950 | +| policy_gradient_loss | -0.0613 | +| value_loss | 0.000399 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.38e+03 | +| ep_rew_mean | 0.225 | +| time/ | | +| fps | 309 | +| iterations | 8544 | +| time_elapsed | 28271 | +| total_timesteps | 8749056 | +| train/ | | +| approx_kl | 3.101325 | +| clip_fraction | 0.461 | +| clip_range | 0.2 | +| entropy_loss | -0.301 | +| explained_variance | -3.71 | +| learning_rate | 0.0001 | +| loss | -0.0906 | +| n_updates | 145960 | +| policy_gradient_loss | -0.0681 | +| value_loss | 0.000798 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.39e+03 | +| ep_rew_mean | 0.228 | +| time/ | | +| fps | 309 | +| iterations | 8545 | +| time_elapsed | 28274 | +| total_timesteps | 8750080 | +| train/ | | +| approx_kl | 2.4817111 | +| clip_fraction | 0.498 | +| clip_range | 0.2 | +| entropy_loss | -0.366 | +| explained_variance | -1.56 | +| learning_rate | 0.0001 | +| loss | -0.0757 | +| n_updates | 145970 | +| policy_gradient_loss | -0.0659 | +| value_loss | 0.00103 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.39e+03 | +| ep_rew_mean | 0.228 | +| time/ | | +| fps | 309 | +| iterations | 8546 | +| time_elapsed | 28278 | +| total_timesteps | 8751104 | +| train/ | | +| approx_kl | 2.0436397 | +| clip_fraction | 0.46 | +| clip_range | 0.2 | +| entropy_loss | -0.355 | +| explained_variance | -10.1 | +| learning_rate | 0.0001 | +| loss | -0.0983 | +| n_updates | 145980 | +| policy_gradient_loss | -0.0644 | +| value_loss | 0.000407 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.39e+03 | +| ep_rew_mean | 0.228 | +| time/ | | +| fps | 309 | +| iterations | 8547 | +| time_elapsed | 28281 | +| total_timesteps | 8752128 | +| train/ | | +| approx_kl | 2.0597148 | +| clip_fraction | 0.478 | +| clip_range | 0.2 | +| entropy_loss | -0.348 | +| explained_variance | -3.42 | +| learning_rate | 0.0001 | +| loss | -0.0563 | +| n_updates | 145990 | +| policy_gradient_loss | -0.0666 | +| value_loss | 0.000664 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.39e+03 | +| ep_rew_mean | 0.228 | +| time/ | | +| fps | 309 | +| iterations | 8548 | +| time_elapsed | 28284 | +| total_timesteps | 8753152 | +| train/ | | +| approx_kl | 2.737943 | +| clip_fraction | 0.472 | +| clip_range | 0.2 | +| entropy_loss | -0.318 | +| explained_variance | -10.2 | +| learning_rate | 0.0001 | +| loss | -0.111 | +| n_updates | 146000 | +| policy_gradient_loss | -0.072 | +| value_loss | 0.000468 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.4e+03 | +| ep_rew_mean | 0.228 | +| time/ | | +| fps | 309 | +| iterations | 8549 | +| time_elapsed | 28287 | +| total_timesteps | 8754176 | +| train/ | | +| approx_kl | 2.5392308 | +| clip_fraction | 0.513 | +| clip_range | 0.2 | +| entropy_loss | -0.356 | +| explained_variance | -0.654 | +| learning_rate | 0.0001 | +| loss | -0.0826 | +| n_updates | 146010 | +| policy_gradient_loss | -0.0714 | +| value_loss | 0.000373 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.39e+03 | +| ep_rew_mean | 0.229 | +| time/ | | +| fps | 309 | +| iterations | 8550 | +| time_elapsed | 28290 | +| total_timesteps | 8755200 | +| train/ | | +| approx_kl | 2.2835958 | +| clip_fraction | 0.452 | +| clip_range | 0.2 | +| entropy_loss | -0.293 | +| explained_variance | -1.31 | +| learning_rate | 0.0001 | +| loss | -0.0761 | +| n_updates | 146020 | +| policy_gradient_loss | -0.0627 | +| value_loss | 0.000685 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.39e+03 | +| ep_rew_mean | 0.229 | +| time/ | | +| fps | 309 | +| iterations | 8551 | +| time_elapsed | 28293 | +| total_timesteps | 8756224 | +| train/ | | +| approx_kl | 3.3285599 | +| clip_fraction | 0.484 | +| clip_range | 0.2 | +| entropy_loss | -0.328 | +| explained_variance | -1.18 | +| learning_rate | 0.0001 | +| loss | -0.0919 | +| n_updates | 146030 | +| policy_gradient_loss | -0.0735 | +| value_loss | 0.000763 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.39e+03 | +| ep_rew_mean | 0.229 | +| time/ | | +| fps | 309 | +| iterations | 8552 | +| time_elapsed | 28296 | +| total_timesteps | 8757248 | +| train/ | | +| approx_kl | 2.5335608 | +| clip_fraction | 0.448 | +| clip_range | 0.2 | +| entropy_loss | -0.299 | +| explained_variance | -10.6 | +| learning_rate | 0.0001 | +| loss | -0.098 | +| n_updates | 146040 | +| policy_gradient_loss | -0.0718 | +| value_loss | 0.000851 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.39e+03 | +| ep_rew_mean | 0.229 | +| time/ | | +| fps | 309 | +| iterations | 8553 | +| time_elapsed | 28300 | +| total_timesteps | 8758272 | +| train/ | | +| approx_kl | 2.2854571 | +| clip_fraction | 0.523 | +| clip_range | 0.2 | +| entropy_loss | -0.383 | +| explained_variance | -4.53 | +| learning_rate | 0.0001 | +| loss | -0.0927 | +| n_updates | 146050 | +| policy_gradient_loss | -0.0686 | +| value_loss | 0.000378 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.4e+03 | +| ep_rew_mean | 0.227 | +| time/ | | +| fps | 309 | +| iterations | 8554 | +| time_elapsed | 28303 | +| total_timesteps | 8759296 | +| train/ | | +| approx_kl | 2.5285096 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.384 | +| explained_variance | -1.01 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 146060 | +| policy_gradient_loss | -0.0678 | +| value_loss | 0.00056 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.4e+03 | +| ep_rew_mean | 0.227 | +| time/ | | +| fps | 309 | +| iterations | 8555 | +| time_elapsed | 28307 | +| total_timesteps | 8760320 | +| train/ | | +| approx_kl | 18.606707 | +| clip_fraction | 0.479 | +| clip_range | 0.2 | +| entropy_loss | -0.338 | +| explained_variance | -4.12 | +| learning_rate | 0.0001 | +| loss | -0.0813 | +| n_updates | 146070 | +| policy_gradient_loss | -0.0694 | +| value_loss | 0.000349 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.4e+03 | +| ep_rew_mean | 0.226 | +| time/ | | +| fps | 309 | +| iterations | 8556 | +| time_elapsed | 28310 | +| total_timesteps | 8761344 | +| train/ | | +| approx_kl | 2.8721025 | +| clip_fraction | 0.486 | +| clip_range | 0.2 | +| entropy_loss | -0.316 | +| explained_variance | -1.19 | +| learning_rate | 0.0001 | +| loss | -0.0503 | +| n_updates | 146080 | +| policy_gradient_loss | -0.0568 | +| value_loss | 0.000324 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.4e+03 | +| ep_rew_mean | 0.226 | +| time/ | | +| fps | 309 | +| iterations | 8557 | +| time_elapsed | 28314 | +| total_timesteps | 8762368 | +| train/ | | +| approx_kl | 3.27026 | +| clip_fraction | 0.485 | +| clip_range | 0.2 | +| entropy_loss | -0.381 | +| explained_variance | -5.81 | +| learning_rate | 0.0001 | +| loss | -0.0541 | +| n_updates | 146090 | +| policy_gradient_loss | -0.0691 | +| value_loss | 0.000382 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.4e+03 | +| ep_rew_mean | 0.225 | +| time/ | | +| fps | 309 | +| iterations | 8558 | +| time_elapsed | 28317 | +| total_timesteps | 8763392 | +| train/ | | +| approx_kl | 2.9815662 | +| clip_fraction | 0.485 | +| clip_range | 0.2 | +| entropy_loss | -0.338 | +| explained_variance | -1.76 | +| learning_rate | 0.0001 | +| loss | -0.0846 | +| n_updates | 146100 | +| policy_gradient_loss | -0.0686 | +| value_loss | 0.000758 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.4e+03 | +| ep_rew_mean | 0.225 | +| time/ | | +| fps | 309 | +| iterations | 8559 | +| time_elapsed | 28321 | +| total_timesteps | 8764416 | +| train/ | | +| approx_kl | 3.2132487 | +| clip_fraction | 0.453 | +| clip_range | 0.2 | +| entropy_loss | -0.289 | +| explained_variance | -4.38 | +| learning_rate | 0.0001 | +| loss | -0.106 | +| n_updates | 146110 | +| policy_gradient_loss | -0.0702 | +| value_loss | 0.000442 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.4e+03 | +| ep_rew_mean | 0.225 | +| time/ | | +| fps | 309 | +| iterations | 8560 | +| time_elapsed | 28324 | +| total_timesteps | 8765440 | +| train/ | | +| approx_kl | 3.2726092 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.347 | +| explained_variance | -2.09 | +| learning_rate | 0.0001 | +| loss | -0.0787 | +| n_updates | 146120 | +| policy_gradient_loss | -0.0695 | +| value_loss | 0.000495 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.4e+03 | +| ep_rew_mean | 0.227 | +| time/ | | +| fps | 309 | +| iterations | 8561 | +| time_elapsed | 28328 | +| total_timesteps | 8766464 | +| train/ | | +| approx_kl | 2.4468093 | +| clip_fraction | 0.506 | +| clip_range | 0.2 | +| entropy_loss | -0.387 | +| explained_variance | -3.21 | +| learning_rate | 0.0001 | +| loss | -0.0793 | +| n_updates | 146130 | +| policy_gradient_loss | -0.0669 | +| value_loss | 0.000433 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.4e+03 | +| ep_rew_mean | 0.227 | +| time/ | | +| fps | 309 | +| iterations | 8562 | +| time_elapsed | 28331 | +| total_timesteps | 8767488 | +| train/ | | +| approx_kl | 2.3881826 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.348 | +| explained_variance | -8.76 | +| learning_rate | 0.0001 | +| loss | -0.109 | +| n_updates | 146140 | +| policy_gradient_loss | -0.0637 | +| value_loss | 0.000492 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.4e+03 | +| ep_rew_mean | 0.227 | +| time/ | | +| fps | 309 | +| iterations | 8563 | +| time_elapsed | 28334 | +| total_timesteps | 8768512 | +| train/ | | +| approx_kl | 2.764485 | +| clip_fraction | 0.511 | +| clip_range | 0.2 | +| entropy_loss | -0.341 | +| explained_variance | -2.04 | +| learning_rate | 0.0001 | +| loss | -0.0629 | +| n_updates | 146150 | +| policy_gradient_loss | -0.0653 | +| value_loss | 0.000613 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.39e+03 | +| ep_rew_mean | 0.23 | +| time/ | | +| fps | 309 | +| iterations | 8564 | +| time_elapsed | 28337 | +| total_timesteps | 8769536 | +| train/ | | +| approx_kl | 2.5592997 | +| clip_fraction | 0.521 | +| clip_range | 0.2 | +| entropy_loss | -0.384 | +| explained_variance | -1.81 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 146160 | +| policy_gradient_loss | -0.0725 | +| value_loss | 0.000371 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.39e+03 | +| ep_rew_mean | 0.23 | +| time/ | | +| fps | 309 | +| iterations | 8565 | +| time_elapsed | 28340 | +| total_timesteps | 8770560 | +| train/ | | +| approx_kl | 7.56737 | +| clip_fraction | 0.473 | +| clip_range | 0.2 | +| entropy_loss | -0.33 | +| explained_variance | -2.97 | +| learning_rate | 0.0001 | +| loss | -0.0994 | +| n_updates | 146170 | +| policy_gradient_loss | -0.068 | +| value_loss | 0.000546 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.39e+03 | +| ep_rew_mean | 0.23 | +| time/ | | +| fps | 309 | +| iterations | 8566 | +| time_elapsed | 28343 | +| total_timesteps | 8771584 | +| train/ | | +| approx_kl | 2.1799345 | +| clip_fraction | 0.482 | +| clip_range | 0.2 | +| entropy_loss | -0.334 | +| explained_variance | -1.03 | +| learning_rate | 0.0001 | +| loss | -0.0845 | +| n_updates | 146180 | +| policy_gradient_loss | -0.0719 | +| value_loss | 0.000573 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.39e+03 | +| ep_rew_mean | 0.229 | +| time/ | | +| fps | 309 | +| iterations | 8567 | +| time_elapsed | 28347 | +| total_timesteps | 8772608 | +| train/ | | +| approx_kl | 2.6038427 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.32 | +| explained_variance | -10.9 | +| learning_rate | 0.0001 | +| loss | -0.0718 | +| n_updates | 146190 | +| policy_gradient_loss | -0.069 | +| value_loss | 0.000451 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.39e+03 | +| ep_rew_mean | 0.229 | +| time/ | | +| fps | 309 | +| iterations | 8568 | +| time_elapsed | 28350 | +| total_timesteps | 8773632 | +| train/ | | +| approx_kl | 2.4250097 | +| clip_fraction | 0.463 | +| clip_range | 0.2 | +| entropy_loss | -0.317 | +| explained_variance | -1.11 | +| learning_rate | 0.0001 | +| loss | -0.0879 | +| n_updates | 146200 | +| policy_gradient_loss | -0.063 | +| value_loss | 0.000489 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.4e+03 | +| ep_rew_mean | 0.228 | +| time/ | | +| fps | 309 | +| iterations | 8569 | +| time_elapsed | 28353 | +| total_timesteps | 8774656 | +| train/ | | +| approx_kl | 2.2908425 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.355 | +| explained_variance | -2.81 | +| learning_rate | 0.0001 | +| loss | -0.0925 | +| n_updates | 146210 | +| policy_gradient_loss | -0.0627 | +| value_loss | 0.000636 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.4e+03 | +| ep_rew_mean | 0.228 | +| time/ | | +| fps | 309 | +| iterations | 8570 | +| time_elapsed | 28356 | +| total_timesteps | 8775680 | +| train/ | | +| approx_kl | 2.1601505 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.353 | +| explained_variance | -8.03 | +| learning_rate | 0.0001 | +| loss | -0.0936 | +| n_updates | 146220 | +| policy_gradient_loss | -0.0712 | +| value_loss | 0.000392 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.4e+03 | +| ep_rew_mean | 0.228 | +| time/ | | +| fps | 309 | +| iterations | 8571 | +| time_elapsed | 28359 | +| total_timesteps | 8776704 | +| train/ | | +| approx_kl | 2.9907 | +| clip_fraction | 0.462 | +| clip_range | 0.2 | +| entropy_loss | -0.304 | +| explained_variance | -7.34 | +| learning_rate | 0.0001 | +| loss | -0.0758 | +| n_updates | 146230 | +| policy_gradient_loss | -0.0665 | +| value_loss | 0.000334 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.41e+03 | +| ep_rew_mean | 0.225 | +| time/ | | +| fps | 309 | +| iterations | 8572 | +| time_elapsed | 28363 | +| total_timesteps | 8777728 | +| train/ | | +| approx_kl | 2.5286028 | +| clip_fraction | 0.504 | +| clip_range | 0.2 | +| entropy_loss | -0.354 | +| explained_variance | -0.819 | +| learning_rate | 0.0001 | +| loss | -0.107 | +| n_updates | 146240 | +| policy_gradient_loss | -0.0719 | +| value_loss | 0.000798 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.41e+03 | +| ep_rew_mean | 0.225 | +| time/ | | +| fps | 309 | +| iterations | 8573 | +| time_elapsed | 28366 | +| total_timesteps | 8778752 | +| train/ | | +| approx_kl | 2.4702942 | +| clip_fraction | 0.494 | +| clip_range | 0.2 | +| entropy_loss | -0.343 | +| explained_variance | -8.47 | +| learning_rate | 0.0001 | +| loss | -0.0701 | +| n_updates | 146250 | +| policy_gradient_loss | -0.0736 | +| value_loss | 0.000486 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.41e+03 | +| ep_rew_mean | 0.227 | +| time/ | | +| fps | 309 | +| iterations | 8574 | +| time_elapsed | 28370 | +| total_timesteps | 8779776 | +| train/ | | +| approx_kl | 2.5227094 | +| clip_fraction | 0.498 | +| clip_range | 0.2 | +| entropy_loss | -0.355 | +| explained_variance | -1.26 | +| learning_rate | 0.0001 | +| loss | -0.0832 | +| n_updates | 146260 | +| policy_gradient_loss | -0.0652 | +| value_loss | 0.000659 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.41e+03 | +| ep_rew_mean | 0.227 | +| time/ | | +| fps | 309 | +| iterations | 8575 | +| time_elapsed | 28373 | +| total_timesteps | 8780800 | +| train/ | | +| approx_kl | 1.9844587 | +| clip_fraction | 0.505 | +| clip_range | 0.2 | +| entropy_loss | -0.399 | +| explained_variance | -2.27 | +| learning_rate | 0.0001 | +| loss | -0.0927 | +| n_updates | 146270 | +| policy_gradient_loss | -0.064 | +| value_loss | 0.000449 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.41e+03 | +| ep_rew_mean | 0.227 | +| time/ | | +| fps | 309 | +| iterations | 8576 | +| time_elapsed | 28376 | +| total_timesteps | 8781824 | +| train/ | | +| approx_kl | 2.5035207 | +| clip_fraction | 0.45 | +| clip_range | 0.2 | +| entropy_loss | -0.309 | +| explained_variance | -1.17 | +| learning_rate | 0.0001 | +| loss | -0.0895 | +| n_updates | 146280 | +| policy_gradient_loss | -0.062 | +| value_loss | 0.000607 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.4e+03 | +| ep_rew_mean | 0.228 | +| time/ | | +| fps | 309 | +| iterations | 8577 | +| time_elapsed | 28380 | +| total_timesteps | 8782848 | +| train/ | | +| approx_kl | 2.2583895 | +| clip_fraction | 0.469 | +| clip_range | 0.2 | +| entropy_loss | -0.338 | +| explained_variance | -9.64 | +| learning_rate | 0.0001 | +| loss | -0.0879 | +| n_updates | 146290 | +| policy_gradient_loss | -0.0698 | +| value_loss | 0.000534 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.4e+03 | +| ep_rew_mean | 0.228 | +| time/ | | +| fps | 309 | +| iterations | 8578 | +| time_elapsed | 28383 | +| total_timesteps | 8783872 | +| train/ | | +| approx_kl | 4.1950965 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.336 | +| explained_variance | -5.07 | +| learning_rate | 0.0001 | +| loss | -0.11 | +| n_updates | 146300 | +| policy_gradient_loss | -0.0722 | +| value_loss | 0.000629 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.41e+03 | +| ep_rew_mean | 0.224 | +| time/ | | +| fps | 309 | +| iterations | 8579 | +| time_elapsed | 28386 | +| total_timesteps | 8784896 | +| train/ | | +| approx_kl | 2.552622 | +| clip_fraction | 0.453 | +| clip_range | 0.2 | +| entropy_loss | -0.349 | +| explained_variance | -8.7 | +| learning_rate | 0.0001 | +| loss | -0.0897 | +| n_updates | 146310 | +| policy_gradient_loss | -0.0605 | +| value_loss | 0.000436 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.41e+03 | +| ep_rew_mean | 0.224 | +| time/ | | +| fps | 309 | +| iterations | 8580 | +| time_elapsed | 28390 | +| total_timesteps | 8785920 | +| train/ | | +| approx_kl | 1.9544492 | +| clip_fraction | 0.444 | +| clip_range | 0.2 | +| entropy_loss | -0.318 | +| explained_variance | -1.99 | +| learning_rate | 0.0001 | +| loss | -0.106 | +| n_updates | 146320 | +| policy_gradient_loss | -0.0682 | +| value_loss | 0.000448 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.41e+03 | +| ep_rew_mean | 0.224 | +| time/ | | +| fps | 309 | +| iterations | 8581 | +| time_elapsed | 28393 | +| total_timesteps | 8786944 | +| train/ | | +| approx_kl | 2.4735732 | +| clip_fraction | 0.501 | +| clip_range | 0.2 | +| entropy_loss | -0.345 | +| explained_variance | -2.08 | +| learning_rate | 0.0001 | +| loss | -0.0822 | +| n_updates | 146330 | +| policy_gradient_loss | -0.066 | +| value_loss | 0.000545 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.41e+03 | +| ep_rew_mean | 0.224 | +| time/ | | +| fps | 309 | +| iterations | 8582 | +| time_elapsed | 28396 | +| total_timesteps | 8787968 | +| train/ | | +| approx_kl | 2.3919764 | +| clip_fraction | 0.508 | +| clip_range | 0.2 | +| entropy_loss | -0.379 | +| explained_variance | -1.34 | +| learning_rate | 0.0001 | +| loss | -0.0873 | +| n_updates | 146340 | +| policy_gradient_loss | -0.0727 | +| value_loss | 0.000435 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.41e+03 | +| ep_rew_mean | 0.224 | +| time/ | | +| fps | 309 | +| iterations | 8583 | +| time_elapsed | 28399 | +| total_timesteps | 8788992 | +| train/ | | +| approx_kl | 2.9272327 | +| clip_fraction | 0.474 | +| clip_range | 0.2 | +| entropy_loss | -0.33 | +| explained_variance | -3.08 | +| learning_rate | 0.0001 | +| loss | -0.0961 | +| n_updates | 146350 | +| policy_gradient_loss | -0.0718 | +| value_loss | 0.000387 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.41e+03 | +| ep_rew_mean | 0.224 | +| time/ | | +| fps | 309 | +| iterations | 8584 | +| time_elapsed | 28402 | +| total_timesteps | 8790016 | +| train/ | | +| approx_kl | 2.214628 | +| clip_fraction | 0.506 | +| clip_range | 0.2 | +| entropy_loss | -0.414 | +| explained_variance | -0.353 | +| learning_rate | 0.0001 | +| loss | -0.0853 | +| n_updates | 146360 | +| policy_gradient_loss | -0.0484 | +| value_loss | 0.000155 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.45e+03 | +| ep_rew_mean | 0.218 | +| time/ | | +| fps | 309 | +| iterations | 8585 | +| time_elapsed | 28405 | +| total_timesteps | 8791040 | +| train/ | | +| approx_kl | 2.5010605 | +| clip_fraction | 0.424 | +| clip_range | 0.2 | +| entropy_loss | -0.495 | +| explained_variance | -0.138 | +| learning_rate | 0.0001 | +| loss | -0.0745 | +| n_updates | 146370 | +| policy_gradient_loss | -0.0488 | +| value_loss | 0.00109 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.45e+03 | +| ep_rew_mean | 0.218 | +| time/ | | +| fps | 309 | +| iterations | 8586 | +| time_elapsed | 28409 | +| total_timesteps | 8792064 | +| train/ | | +| approx_kl | 3.3825881 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.329 | +| explained_variance | -7.35 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 146380 | +| policy_gradient_loss | -0.0719 | +| value_loss | 0.000809 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.45e+03 | +| ep_rew_mean | 0.218 | +| time/ | | +| fps | 309 | +| iterations | 8587 | +| time_elapsed | 28412 | +| total_timesteps | 8793088 | +| train/ | | +| approx_kl | 2.512144 | +| clip_fraction | 0.464 | +| clip_range | 0.2 | +| entropy_loss | -0.333 | +| explained_variance | -5.41 | +| learning_rate | 0.0001 | +| loss | -0.0931 | +| n_updates | 146390 | +| policy_gradient_loss | -0.0695 | +| value_loss | 0.000779 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.44e+03 | +| ep_rew_mean | 0.217 | +| time/ | | +| fps | 309 | +| iterations | 8588 | +| time_elapsed | 28415 | +| total_timesteps | 8794112 | +| train/ | | +| approx_kl | 2.7440588 | +| clip_fraction | 0.493 | +| clip_range | 0.2 | +| entropy_loss | -0.358 | +| explained_variance | -5.26 | +| learning_rate | 0.0001 | +| loss | -0.0608 | +| n_updates | 146400 | +| policy_gradient_loss | -0.0683 | +| value_loss | 0.000485 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.44e+03 | +| ep_rew_mean | 0.217 | +| time/ | | +| fps | 309 | +| iterations | 8589 | +| time_elapsed | 28418 | +| total_timesteps | 8795136 | +| train/ | | +| approx_kl | 2.6091158 | +| clip_fraction | 0.494 | +| clip_range | 0.2 | +| entropy_loss | -0.363 | +| explained_variance | -0.831 | +| learning_rate | 0.0001 | +| loss | -0.109 | +| n_updates | 146410 | +| policy_gradient_loss | -0.0693 | +| value_loss | 0.000843 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.42e+03 | +| ep_rew_mean | 0.22 | +| time/ | | +| fps | 309 | +| iterations | 8590 | +| time_elapsed | 28422 | +| total_timesteps | 8796160 | +| train/ | | +| approx_kl | 2.204612 | +| clip_fraction | 0.497 | +| clip_range | 0.2 | +| entropy_loss | -0.387 | +| explained_variance | -8.26 | +| learning_rate | 0.0001 | +| loss | -0.0628 | +| n_updates | 146420 | +| policy_gradient_loss | -0.0721 | +| value_loss | 0.000443 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.42e+03 | +| ep_rew_mean | 0.22 | +| time/ | | +| fps | 309 | +| iterations | 8591 | +| time_elapsed | 28425 | +| total_timesteps | 8797184 | +| train/ | | +| approx_kl | 4.2546964 | +| clip_fraction | 0.484 | +| clip_range | 0.2 | +| entropy_loss | -0.328 | +| explained_variance | -2.29 | +| learning_rate | 0.0001 | +| loss | -0.0883 | +| n_updates | 146430 | +| policy_gradient_loss | -0.0721 | +| value_loss | 0.000602 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.42e+03 | +| ep_rew_mean | 0.22 | +| time/ | | +| fps | 309 | +| iterations | 8592 | +| time_elapsed | 28429 | +| total_timesteps | 8798208 | +| train/ | | +| approx_kl | 2.2601242 | +| clip_fraction | 0.502 | +| clip_range | 0.2 | +| entropy_loss | -0.373 | +| explained_variance | -1.13 | +| learning_rate | 0.0001 | +| loss | -0.0967 | +| n_updates | 146440 | +| policy_gradient_loss | -0.0718 | +| value_loss | 0.000565 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.43e+03 | +| ep_rew_mean | 0.22 | +| time/ | | +| fps | 309 | +| iterations | 8593 | +| time_elapsed | 28432 | +| total_timesteps | 8799232 | +| train/ | | +| approx_kl | 2.3488946 | +| clip_fraction | 0.52 | +| clip_range | 0.2 | +| entropy_loss | -0.391 | +| explained_variance | -11.6 | +| learning_rate | 0.0001 | +| loss | -0.0779 | +| n_updates | 146450 | +| policy_gradient_loss | -0.0763 | +| value_loss | 0.000143 | +--------------------------------------- + +Current state: Champion.Level11.RyuVsSagat +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.43e+03 | +| ep_rew_mean | 0.22 | +| time/ | | +| fps | 309 | +| iterations | 8594 | +| time_elapsed | 28436 | +| total_timesteps | 8800256 | +| train/ | | +| approx_kl | 1.8247313 | +| clip_fraction | 0.454 | +| clip_range | 0.2 | +| entropy_loss | -0.345 | +| explained_variance | -2.92 | +| learning_rate | 0.0001 | +| loss | -0.0835 | +| n_updates | 146460 | +| policy_gradient_loss | -0.0652 | +| value_loss | 8.05e-05 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.43e+03 | +| ep_rew_mean | 0.22 | +| time/ | | +| fps | 309 | +| iterations | 8595 | +| time_elapsed | 28439 | +| total_timesteps | 8801280 | +| train/ | | +| approx_kl | 1.9166026 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.354 | +| explained_variance | -0.0802 | +| learning_rate | 0.0001 | +| loss | -0.0771 | +| n_updates | 146470 | +| policy_gradient_loss | -0.0633 | +| value_loss | 0.000452 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.44e+03 | +| ep_rew_mean | 0.221 | +| time/ | | +| fps | 309 | +| iterations | 8596 | +| time_elapsed | 28442 | +| total_timesteps | 8802304 | +| train/ | | +| approx_kl | 2.1259408 | +| clip_fraction | 0.496 | +| clip_range | 0.2 | +| entropy_loss | -0.372 | +| explained_variance | -2.24 | +| learning_rate | 0.0001 | +| loss | -0.0779 | +| n_updates | 146480 | +| policy_gradient_loss | -0.069 | +| value_loss | 0.000661 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.42e+03 | +| ep_rew_mean | 0.225 | +| time/ | | +| fps | 309 | +| iterations | 8597 | +| time_elapsed | 28446 | +| total_timesteps | 8803328 | +| train/ | | +| approx_kl | 3.282259 | +| clip_fraction | 0.515 | +| clip_range | 0.2 | +| entropy_loss | -0.484 | +| explained_variance | -1.54 | +| learning_rate | 0.0001 | +| loss | -0.0837 | +| n_updates | 146490 | +| policy_gradient_loss | -0.0637 | +| value_loss | 0.000794 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.4e+03 | +| ep_rew_mean | 0.221 | +| time/ | | +| fps | 309 | +| iterations | 8598 | +| time_elapsed | 28449 | +| total_timesteps | 8804352 | +| train/ | | +| approx_kl | 2.2243493 | +| clip_fraction | 0.56 | +| clip_range | 0.2 | +| entropy_loss | -0.563 | +| explained_variance | -0.359 | +| learning_rate | 0.0001 | +| loss | -0.0964 | +| n_updates | 146500 | +| policy_gradient_loss | -0.067 | +| value_loss | 0.000727 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.4e+03 | +| ep_rew_mean | 0.227 | +| time/ | | +| fps | 309 | +| iterations | 8599 | +| time_elapsed | 28453 | +| total_timesteps | 8805376 | +| train/ | | +| approx_kl | 1.631436 | +| clip_fraction | 0.53 | +| clip_range | 0.2 | +| entropy_loss | -0.586 | +| explained_variance | -1.15 | +| learning_rate | 0.0001 | +| loss | -0.113 | +| n_updates | 146510 | +| policy_gradient_loss | -0.0701 | +| value_loss | 0.000563 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.38e+03 | +| ep_rew_mean | 0.223 | +| time/ | | +| fps | 309 | +| iterations | 8600 | +| time_elapsed | 28456 | +| total_timesteps | 8806400 | +| train/ | | +| approx_kl | 1.3696269 | +| clip_fraction | 0.541 | +| clip_range | 0.2 | +| entropy_loss | -0.573 | +| explained_variance | -0.661 | +| learning_rate | 0.0001 | +| loss | -0.0922 | +| n_updates | 146520 | +| policy_gradient_loss | -0.0696 | +| value_loss | 0.000584 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.38e+03 | +| ep_rew_mean | 0.223 | +| time/ | | +| fps | 309 | +| iterations | 8601 | +| time_elapsed | 28459 | +| total_timesteps | 8807424 | +| train/ | | +| approx_kl | 1.3279898 | +| clip_fraction | 0.53 | +| clip_range | 0.2 | +| entropy_loss | -0.671 | +| explained_variance | -0.939 | +| learning_rate | 0.0001 | +| loss | -0.105 | +| n_updates | 146530 | +| policy_gradient_loss | -0.0681 | +| value_loss | 0.000313 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.37e+03 | +| ep_rew_mean | 0.221 | +| time/ | | +| fps | 309 | +| iterations | 8602 | +| time_elapsed | 28462 | +| total_timesteps | 8808448 | +| train/ | | +| approx_kl | 1.9858181 | +| clip_fraction | 0.526 | +| clip_range | 0.2 | +| entropy_loss | -0.558 | +| explained_variance | -2.54 | +| learning_rate | 0.0001 | +| loss | -0.0833 | +| n_updates | 146540 | +| policy_gradient_loss | -0.0802 | +| value_loss | 0.000298 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.36e+03 | +| ep_rew_mean | 0.219 | +| time/ | | +| fps | 309 | +| iterations | 8603 | +| time_elapsed | 28465 | +| total_timesteps | 8809472 | +| train/ | | +| approx_kl | 1.540144 | +| clip_fraction | 0.518 | +| clip_range | 0.2 | +| entropy_loss | -0.526 | +| explained_variance | -1.4 | +| learning_rate | 0.0001 | +| loss | -0.0724 | +| n_updates | 146550 | +| policy_gradient_loss | -0.0729 | +| value_loss | 0.000299 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.35e+03 | +| ep_rew_mean | 0.219 | +| time/ | | +| fps | 309 | +| iterations | 8604 | +| time_elapsed | 28469 | +| total_timesteps | 8810496 | +| train/ | | +| approx_kl | 1.5376127 | +| clip_fraction | 0.545 | +| clip_range | 0.2 | +| entropy_loss | -0.606 | +| explained_variance | -1.08 | +| learning_rate | 0.0001 | +| loss | -0.116 | +| n_updates | 146560 | +| policy_gradient_loss | -0.0781 | +| value_loss | 0.0005 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.34e+03 | +| ep_rew_mean | 0.22 | +| time/ | | +| fps | 309 | +| iterations | 8605 | +| time_elapsed | 28472 | +| total_timesteps | 8811520 | +| train/ | | +| approx_kl | 1.2271578 | +| clip_fraction | 0.479 | +| clip_range | 0.2 | +| entropy_loss | -0.467 | +| explained_variance | -0.604 | +| learning_rate | 0.0001 | +| loss | -0.0908 | +| n_updates | 146570 | +| policy_gradient_loss | -0.073 | +| value_loss | 0.00058 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.34e+03 | +| ep_rew_mean | 0.22 | +| time/ | | +| fps | 309 | +| iterations | 8606 | +| time_elapsed | 28475 | +| total_timesteps | 8812544 | +| train/ | | +| approx_kl | 1.4405661 | +| clip_fraction | 0.542 | +| clip_range | 0.2 | +| entropy_loss | -0.63 | +| explained_variance | -1.14 | +| learning_rate | 0.0001 | +| loss | -0.0604 | +| n_updates | 146580 | +| policy_gradient_loss | -0.0746 | +| value_loss | 0.000541 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.33e+03 | +| ep_rew_mean | 0.218 | +| time/ | | +| fps | 309 | +| iterations | 8607 | +| time_elapsed | 28478 | +| total_timesteps | 8813568 | +| train/ | | +| approx_kl | 1.7148539 | +| clip_fraction | 0.497 | +| clip_range | 0.2 | +| entropy_loss | -0.503 | +| explained_variance | -2.73 | +| learning_rate | 0.0001 | +| loss | -0.0919 | +| n_updates | 146590 | +| policy_gradient_loss | -0.0692 | +| value_loss | 0.000359 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.33e+03 | +| ep_rew_mean | 0.216 | +| time/ | | +| fps | 309 | +| iterations | 8608 | +| time_elapsed | 28482 | +| total_timesteps | 8814592 | +| train/ | | +| approx_kl | 1.4109695 | +| clip_fraction | 0.477 | +| clip_range | 0.2 | +| entropy_loss | -0.565 | +| explained_variance | -0.87 | +| learning_rate | 0.0001 | +| loss | -0.0808 | +| n_updates | 146600 | +| policy_gradient_loss | -0.0591 | +| value_loss | 0.000226 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.32e+03 | +| ep_rew_mean | 0.214 | +| time/ | | +| fps | 309 | +| iterations | 8609 | +| time_elapsed | 28485 | +| total_timesteps | 8815616 | +| train/ | | +| approx_kl | 1.8762627 | +| clip_fraction | 0.517 | +| clip_range | 0.2 | +| entropy_loss | -0.489 | +| explained_variance | -3.85 | +| learning_rate | 0.0001 | +| loss | -0.11 | +| n_updates | 146610 | +| policy_gradient_loss | -0.0773 | +| value_loss | 0.000406 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.32e+03 | +| ep_rew_mean | 0.214 | +| time/ | | +| fps | 309 | +| iterations | 8610 | +| time_elapsed | 28488 | +| total_timesteps | 8816640 | +| train/ | | +| approx_kl | 1.8541677 | +| clip_fraction | 0.506 | +| clip_range | 0.2 | +| entropy_loss | -0.498 | +| explained_variance | -1.71 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 146620 | +| policy_gradient_loss | -0.0711 | +| value_loss | 0.000692 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.31e+03 | +| ep_rew_mean | 0.216 | +| time/ | | +| fps | 309 | +| iterations | 8611 | +| time_elapsed | 28492 | +| total_timesteps | 8817664 | +| train/ | | +| approx_kl | 1.8242323 | +| clip_fraction | 0.562 | +| clip_range | 0.2 | +| entropy_loss | -0.597 | +| explained_variance | -2.69 | +| learning_rate | 0.0001 | +| loss | -0.111 | +| n_updates | 146630 | +| policy_gradient_loss | -0.0749 | +| value_loss | 0.000242 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.31e+03 | +| ep_rew_mean | 0.218 | +| time/ | | +| fps | 309 | +| iterations | 8612 | +| time_elapsed | 28495 | +| total_timesteps | 8818688 | +| train/ | | +| approx_kl | 1.3331455 | +| clip_fraction | 0.476 | +| clip_range | 0.2 | +| entropy_loss | -0.469 | +| explained_variance | -1.9 | +| learning_rate | 0.0001 | +| loss | -0.0509 | +| n_updates | 146640 | +| policy_gradient_loss | -0.0641 | +| value_loss | 0.000203 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.31e+03 | +| ep_rew_mean | 0.218 | +| time/ | | +| fps | 309 | +| iterations | 8613 | +| time_elapsed | 28498 | +| total_timesteps | 8819712 | +| train/ | | +| approx_kl | 1.8998301 | +| clip_fraction | 0.525 | +| clip_range | 0.2 | +| entropy_loss | -0.455 | +| explained_variance | -0.656 | +| learning_rate | 0.0001 | +| loss | -0.117 | +| n_updates | 146650 | +| policy_gradient_loss | -0.0728 | +| value_loss | 0.000283 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.28e+03 | +| ep_rew_mean | 0.214 | +| time/ | | +| fps | 309 | +| iterations | 8614 | +| time_elapsed | 28502 | +| total_timesteps | 8820736 | +| train/ | | +| approx_kl | 2.7716227 | +| clip_fraction | 0.55 | +| clip_range | 0.2 | +| entropy_loss | -0.614 | +| explained_variance | -1.24 | +| learning_rate | 0.0001 | +| loss | -0.0922 | +| n_updates | 146660 | +| policy_gradient_loss | -0.0702 | +| value_loss | 0.00043 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.27e+03 | +| ep_rew_mean | 0.213 | +| time/ | | +| fps | 309 | +| iterations | 8615 | +| time_elapsed | 28505 | +| total_timesteps | 8821760 | +| train/ | | +| approx_kl | 2.2125177 | +| clip_fraction | 0.505 | +| clip_range | 0.2 | +| entropy_loss | -0.461 | +| explained_variance | -5.27 | +| learning_rate | 0.0001 | +| loss | -0.0958 | +| n_updates | 146670 | +| policy_gradient_loss | -0.0706 | +| value_loss | 0.000449 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.26e+03 | +| ep_rew_mean | 0.213 | +| time/ | | +| fps | 309 | +| iterations | 8616 | +| time_elapsed | 28508 | +| total_timesteps | 8822784 | +| train/ | | +| approx_kl | 2.0568793 | +| clip_fraction | 0.507 | +| clip_range | 0.2 | +| entropy_loss | -0.503 | +| explained_variance | -2.98 | +| learning_rate | 0.0001 | +| loss | -0.091 | +| n_updates | 146680 | +| policy_gradient_loss | -0.0708 | +| value_loss | 0.00038 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.26e+03 | +| ep_rew_mean | 0.213 | +| time/ | | +| fps | 309 | +| iterations | 8617 | +| time_elapsed | 28512 | +| total_timesteps | 8823808 | +| train/ | | +| approx_kl | 2.255194 | +| clip_fraction | 0.527 | +| clip_range | 0.2 | +| entropy_loss | -0.509 | +| explained_variance | -5.37 | +| learning_rate | 0.0001 | +| loss | -0.0912 | +| n_updates | 146690 | +| policy_gradient_loss | -0.0702 | +| value_loss | 0.00064 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.26e+03 | +| ep_rew_mean | 0.213 | +| time/ | | +| fps | 309 | +| iterations | 8618 | +| time_elapsed | 28515 | +| total_timesteps | 8824832 | +| train/ | | +| approx_kl | 2.2037683 | +| clip_fraction | 0.512 | +| clip_range | 0.2 | +| entropy_loss | -0.466 | +| explained_variance | -2.66 | +| learning_rate | 0.0001 | +| loss | -0.112 | +| n_updates | 146700 | +| policy_gradient_loss | -0.0763 | +| value_loss | 0.000714 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.26e+03 | +| ep_rew_mean | 0.214 | +| time/ | | +| fps | 309 | +| iterations | 8619 | +| time_elapsed | 28518 | +| total_timesteps | 8825856 | +| train/ | | +| approx_kl | 1.7283943 | +| clip_fraction | 0.519 | +| clip_range | 0.2 | +| entropy_loss | -0.533 | +| explained_variance | -5.79 | +| learning_rate | 0.0001 | +| loss | -0.0962 | +| n_updates | 146710 | +| policy_gradient_loss | -0.0722 | +| value_loss | 0.000212 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.24e+03 | +| ep_rew_mean | 0.21 | +| time/ | | +| fps | 309 | +| iterations | 8620 | +| time_elapsed | 28521 | +| total_timesteps | 8826880 | +| train/ | | +| approx_kl | 2.0524158 | +| clip_fraction | 0.508 | +| clip_range | 0.2 | +| entropy_loss | -0.468 | +| explained_variance | -0.793 | +| learning_rate | 0.0001 | +| loss | -0.0859 | +| n_updates | 146720 | +| policy_gradient_loss | -0.069 | +| value_loss | 0.000287 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.22e+03 | +| ep_rew_mean | 0.212 | +| time/ | | +| fps | 309 | +| iterations | 8621 | +| time_elapsed | 28524 | +| total_timesteps | 8827904 | +| train/ | | +| approx_kl | 1.9649594 | +| clip_fraction | 0.484 | +| clip_range | 0.2 | +| entropy_loss | -0.468 | +| explained_variance | -0.829 | +| learning_rate | 0.0001 | +| loss | -0.0476 | +| n_updates | 146730 | +| policy_gradient_loss | -0.0708 | +| value_loss | 0.000481 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.22e+03 | +| ep_rew_mean | 0.209 | +| time/ | | +| fps | 309 | +| iterations | 8622 | +| time_elapsed | 28527 | +| total_timesteps | 8828928 | +| train/ | | +| approx_kl | 1.376237 | +| clip_fraction | 0.511 | +| clip_range | 0.2 | +| entropy_loss | -0.522 | +| explained_variance | -3.61 | +| learning_rate | 0.0001 | +| loss | -0.0831 | +| n_updates | 146740 | +| policy_gradient_loss | -0.063 | +| value_loss | 0.00031 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.21e+03 | +| ep_rew_mean | 0.208 | +| time/ | | +| fps | 309 | +| iterations | 8623 | +| time_elapsed | 28531 | +| total_timesteps | 8829952 | +| train/ | | +| approx_kl | 1.2057438 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.579 | +| explained_variance | -0.909 | +| learning_rate | 0.0001 | +| loss | -0.0854 | +| n_updates | 146750 | +| policy_gradient_loss | -0.0664 | +| value_loss | 0.000337 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.21e+03 | +| ep_rew_mean | 0.208 | +| time/ | | +| fps | 309 | +| iterations | 8624 | +| time_elapsed | 28534 | +| total_timesteps | 8830976 | +| train/ | | +| approx_kl | 1.8339282 | +| clip_fraction | 0.477 | +| clip_range | 0.2 | +| entropy_loss | -0.454 | +| explained_variance | -1.31 | +| learning_rate | 0.0001 | +| loss | -0.0827 | +| n_updates | 146760 | +| policy_gradient_loss | -0.065 | +| value_loss | 0.00042 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.2e+03 | +| ep_rew_mean | 0.206 | +| time/ | | +| fps | 309 | +| iterations | 8625 | +| time_elapsed | 28537 | +| total_timesteps | 8832000 | +| train/ | | +| approx_kl | 1.4786165 | +| clip_fraction | 0.498 | +| clip_range | 0.2 | +| entropy_loss | -0.489 | +| explained_variance | -0.355 | +| learning_rate | 0.0001 | +| loss | -0.0581 | +| n_updates | 146770 | +| policy_gradient_loss | -0.0693 | +| value_loss | 0.000669 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.19e+03 | +| ep_rew_mean | 0.2 | +| time/ | | +| fps | 309 | +| iterations | 8626 | +| time_elapsed | 28540 | +| total_timesteps | 8833024 | +| train/ | | +| approx_kl | 1.5334834 | +| clip_fraction | 0.524 | +| clip_range | 0.2 | +| entropy_loss | -0.572 | +| explained_variance | -2.29 | +| learning_rate | 0.0001 | +| loss | -0.0639 | +| n_updates | 146780 | +| policy_gradient_loss | -0.0627 | +| value_loss | 0.000395 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.18e+03 | +| ep_rew_mean | 0.199 | +| time/ | | +| fps | 309 | +| iterations | 8627 | +| time_elapsed | 28544 | +| total_timesteps | 8834048 | +| train/ | | +| approx_kl | 1.5867102 | +| clip_fraction | 0.518 | +| clip_range | 0.2 | +| entropy_loss | -0.514 | +| explained_variance | -3.27 | +| learning_rate | 0.0001 | +| loss | -0.0971 | +| n_updates | 146790 | +| policy_gradient_loss | -0.0766 | +| value_loss | 0.000349 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.16e+03 | +| ep_rew_mean | 0.198 | +| time/ | | +| fps | 309 | +| iterations | 8628 | +| time_elapsed | 28547 | +| total_timesteps | 8835072 | +| train/ | | +| approx_kl | 2.025356 | +| clip_fraction | 0.522 | +| clip_range | 0.2 | +| entropy_loss | -0.478 | +| explained_variance | -1.34 | +| learning_rate | 0.0001 | +| loss | -0.114 | +| n_updates | 146800 | +| policy_gradient_loss | -0.0758 | +| value_loss | 0.000471 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.16e+03 | +| ep_rew_mean | 0.198 | +| time/ | | +| fps | 309 | +| iterations | 8629 | +| time_elapsed | 28551 | +| total_timesteps | 8836096 | +| train/ | | +| approx_kl | 2.2410789 | +| clip_fraction | 0.547 | +| clip_range | 0.2 | +| entropy_loss | -0.52 | +| explained_variance | -2.42 | +| learning_rate | 0.0001 | +| loss | -0.0903 | +| n_updates | 146810 | +| policy_gradient_loss | -0.078 | +| value_loss | 0.000394 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.15e+03 | +| ep_rew_mean | 0.197 | +| time/ | | +| fps | 309 | +| iterations | 8630 | +| time_elapsed | 28554 | +| total_timesteps | 8837120 | +| train/ | | +| approx_kl | 3.8588176 | +| clip_fraction | 0.518 | +| clip_range | 0.2 | +| entropy_loss | -0.461 | +| explained_variance | -0.857 | +| learning_rate | 0.0001 | +| loss | -0.0797 | +| n_updates | 146820 | +| policy_gradient_loss | -0.0719 | +| value_loss | 0.000557 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.14e+03 | +| ep_rew_mean | 0.192 | +| time/ | | +| fps | 309 | +| iterations | 8631 | +| time_elapsed | 28557 | +| total_timesteps | 8838144 | +| train/ | | +| approx_kl | 1.8020585 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.424 | +| explained_variance | -1.55 | +| learning_rate | 0.0001 | +| loss | -0.0492 | +| n_updates | 146830 | +| policy_gradient_loss | -0.0692 | +| value_loss | 0.000509 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.13e+03 | +| ep_rew_mean | 0.187 | +| time/ | | +| fps | 309 | +| iterations | 8632 | +| time_elapsed | 28561 | +| total_timesteps | 8839168 | +| train/ | | +| approx_kl | 2.1174312 | +| clip_fraction | 0.465 | +| clip_range | 0.2 | +| entropy_loss | -0.387 | +| explained_variance | -1.47 | +| learning_rate | 0.0001 | +| loss | -0.0791 | +| n_updates | 146840 | +| policy_gradient_loss | -0.0672 | +| value_loss | 0.000591 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.13e+03 | +| ep_rew_mean | 0.187 | +| time/ | | +| fps | 309 | +| iterations | 8633 | +| time_elapsed | 28564 | +| total_timesteps | 8840192 | +| train/ | | +| approx_kl | 2.0741992 | +| clip_fraction | 0.492 | +| clip_range | 0.2 | +| entropy_loss | -0.462 | +| explained_variance | -1.9 | +| learning_rate | 0.0001 | +| loss | -0.0902 | +| n_updates | 146850 | +| policy_gradient_loss | -0.0702 | +| value_loss | 0.000389 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.13e+03 | +| ep_rew_mean | 0.187 | +| time/ | | +| fps | 309 | +| iterations | 8634 | +| time_elapsed | 28568 | +| total_timesteps | 8841216 | +| train/ | | +| approx_kl | 2.0029128 | +| clip_fraction | 0.543 | +| clip_range | 0.2 | +| entropy_loss | -0.509 | +| explained_variance | -1.61 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 146860 | +| policy_gradient_loss | -0.0789 | +| value_loss | 0.000314 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.12e+03 | +| ep_rew_mean | 0.188 | +| time/ | | +| fps | 309 | +| iterations | 8635 | +| time_elapsed | 28571 | +| total_timesteps | 8842240 | +| train/ | | +| approx_kl | 1.6205008 | +| clip_fraction | 0.503 | +| clip_range | 0.2 | +| entropy_loss | -0.513 | +| explained_variance | -1.06 | +| learning_rate | 0.0001 | +| loss | -0.0694 | +| n_updates | 146870 | +| policy_gradient_loss | -0.0681 | +| value_loss | 0.000218 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.11e+03 | +| ep_rew_mean | 0.188 | +| time/ | | +| fps | 309 | +| iterations | 8636 | +| time_elapsed | 28574 | +| total_timesteps | 8843264 | +| train/ | | +| approx_kl | 2.569581 | +| clip_fraction | 0.482 | +| clip_range | 0.2 | +| entropy_loss | -0.449 | +| explained_variance | -1.62 | +| learning_rate | 0.0001 | +| loss | -0.0687 | +| n_updates | 146880 | +| policy_gradient_loss | -0.0699 | +| value_loss | 0.000483 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.11e+03 | +| ep_rew_mean | 0.188 | +| time/ | | +| fps | 309 | +| iterations | 8637 | +| time_elapsed | 28577 | +| total_timesteps | 8844288 | +| train/ | | +| approx_kl | 1.9325798 | +| clip_fraction | 0.515 | +| clip_range | 0.2 | +| entropy_loss | -0.467 | +| explained_variance | -2.98 | +| learning_rate | 0.0001 | +| loss | -0.0955 | +| n_updates | 146890 | +| policy_gradient_loss | -0.0751 | +| value_loss | 0.000479 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.11e+03 | +| ep_rew_mean | 0.181 | +| time/ | | +| fps | 309 | +| iterations | 8638 | +| time_elapsed | 28580 | +| total_timesteps | 8845312 | +| train/ | | +| approx_kl | 1.6454444 | +| clip_fraction | 0.504 | +| clip_range | 0.2 | +| entropy_loss | -0.464 | +| explained_variance | -1.94 | +| learning_rate | 0.0001 | +| loss | -0.0809 | +| n_updates | 146900 | +| policy_gradient_loss | -0.067 | +| value_loss | 0.000342 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.09e+03 | +| ep_rew_mean | 0.179 | +| time/ | | +| fps | 309 | +| iterations | 8639 | +| time_elapsed | 28584 | +| total_timesteps | 8846336 | +| train/ | | +| approx_kl | 2.0371418 | +| clip_fraction | 0.493 | +| clip_range | 0.2 | +| entropy_loss | -0.44 | +| explained_variance | -3.29 | +| learning_rate | 0.0001 | +| loss | -0.0852 | +| n_updates | 146910 | +| policy_gradient_loss | -0.0661 | +| value_loss | 0.000555 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.08e+03 | +| ep_rew_mean | 0.176 | +| time/ | | +| fps | 309 | +| iterations | 8640 | +| time_elapsed | 28587 | +| total_timesteps | 8847360 | +| train/ | | +| approx_kl | 1.8105214 | +| clip_fraction | 0.515 | +| clip_range | 0.2 | +| entropy_loss | -0.495 | +| explained_variance | -1.3 | +| learning_rate | 0.0001 | +| loss | -0.0891 | +| n_updates | 146920 | +| policy_gradient_loss | -0.0397 | +| value_loss | 0.000559 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.07e+03 | +| ep_rew_mean | 0.177 | +| time/ | | +| fps | 309 | +| iterations | 8641 | +| time_elapsed | 28590 | +| total_timesteps | 8848384 | +| train/ | | +| approx_kl | 1.8047655 | +| clip_fraction | 0.503 | +| clip_range | 0.2 | +| entropy_loss | -0.445 | +| explained_variance | -2.83 | +| learning_rate | 0.0001 | +| loss | -0.0831 | +| n_updates | 146930 | +| policy_gradient_loss | -0.0707 | +| value_loss | 0.000562 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.06e+03 | +| ep_rew_mean | 0.173 | +| time/ | | +| fps | 309 | +| iterations | 8642 | +| time_elapsed | 28593 | +| total_timesteps | 8849408 | +| train/ | | +| approx_kl | 1.911708 | +| clip_fraction | 0.515 | +| clip_range | 0.2 | +| entropy_loss | -0.486 | +| explained_variance | -2.79 | +| learning_rate | 0.0001 | +| loss | -0.0813 | +| n_updates | 146940 | +| policy_gradient_loss | -0.0733 | +| value_loss | 0.000357 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.06e+03 | +| ep_rew_mean | 0.173 | +| time/ | | +| fps | 309 | +| iterations | 8643 | +| time_elapsed | 28596 | +| total_timesteps | 8850432 | +| train/ | | +| approx_kl | 1.8340995 | +| clip_fraction | 0.482 | +| clip_range | 0.2 | +| entropy_loss | -0.437 | +| explained_variance | -1.59 | +| learning_rate | 0.0001 | +| loss | -0.0875 | +| n_updates | 146950 | +| policy_gradient_loss | -0.0686 | +| value_loss | 0.000319 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.05e+03 | +| ep_rew_mean | 0.171 | +| time/ | | +| fps | 309 | +| iterations | 8644 | +| time_elapsed | 28599 | +| total_timesteps | 8851456 | +| train/ | | +| approx_kl | 2.4096916 | +| clip_fraction | 0.508 | +| clip_range | 0.2 | +| entropy_loss | -0.489 | +| explained_variance | -1.59 | +| learning_rate | 0.0001 | +| loss | -0.107 | +| n_updates | 146960 | +| policy_gradient_loss | -0.0681 | +| value_loss | 0.00038 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.05e+03 | +| ep_rew_mean | 0.171 | +| time/ | | +| fps | 309 | +| iterations | 8645 | +| time_elapsed | 28603 | +| total_timesteps | 8852480 | +| train/ | | +| approx_kl | 1.2930889 | +| clip_fraction | 0.484 | +| clip_range | 0.2 | +| entropy_loss | -0.458 | +| explained_variance | -1.49 | +| learning_rate | 0.0001 | +| loss | -0.0915 | +| n_updates | 146970 | +| policy_gradient_loss | -0.0654 | +| value_loss | 0.000363 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.05e+03 | +| ep_rew_mean | 0.172 | +| time/ | | +| fps | 309 | +| iterations | 8646 | +| time_elapsed | 28606 | +| total_timesteps | 8853504 | +| train/ | | +| approx_kl | 1.5914174 | +| clip_fraction | 0.502 | +| clip_range | 0.2 | +| entropy_loss | -0.488 | +| explained_variance | -0.948 | +| learning_rate | 0.0001 | +| loss | -0.0777 | +| n_updates | 146980 | +| policy_gradient_loss | -0.0713 | +| value_loss | 0.000375 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.04e+03 | +| ep_rew_mean | 0.171 | +| time/ | | +| fps | 309 | +| iterations | 8647 | +| time_elapsed | 28610 | +| total_timesteps | 8854528 | +| train/ | | +| approx_kl | 1.5843129 | +| clip_fraction | 0.498 | +| clip_range | 0.2 | +| entropy_loss | -0.486 | +| explained_variance | -1.17 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 146990 | +| policy_gradient_loss | -0.0665 | +| value_loss | 0.000303 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.02e+03 | +| ep_rew_mean | 0.168 | +| time/ | | +| fps | 309 | +| iterations | 8648 | +| time_elapsed | 28613 | +| total_timesteps | 8855552 | +| train/ | | +| approx_kl | 2.1348667 | +| clip_fraction | 0.488 | +| clip_range | 0.2 | +| entropy_loss | -0.444 | +| explained_variance | -2.91 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 147000 | +| policy_gradient_loss | -0.0776 | +| value_loss | 0.000342 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.99e+03 | +| ep_rew_mean | 0.165 | +| time/ | | +| fps | 309 | +| iterations | 8649 | +| time_elapsed | 28616 | +| total_timesteps | 8856576 | +| train/ | | +| approx_kl | 2.459238 | +| clip_fraction | 0.497 | +| clip_range | 0.2 | +| entropy_loss | -0.44 | +| explained_variance | -0.879 | +| learning_rate | 0.0001 | +| loss | -0.0935 | +| n_updates | 147010 | +| policy_gradient_loss | -0.0735 | +| value_loss | 0.000516 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.99e+03 | +| ep_rew_mean | 0.165 | +| time/ | | +| fps | 309 | +| iterations | 8650 | +| time_elapsed | 28620 | +| total_timesteps | 8857600 | +| train/ | | +| approx_kl | 3.0610075 | +| clip_fraction | 0.488 | +| clip_range | 0.2 | +| entropy_loss | -0.483 | +| explained_variance | -0.882 | +| learning_rate | 0.0001 | +| loss | -0.0891 | +| n_updates | 147020 | +| policy_gradient_loss | -0.0661 | +| value_loss | 0.000527 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.99e+03 | +| ep_rew_mean | 0.164 | +| time/ | | +| fps | 309 | +| iterations | 8651 | +| time_elapsed | 28623 | +| total_timesteps | 8858624 | +| train/ | | +| approx_kl | 1.7495091 | +| clip_fraction | 0.531 | +| clip_range | 0.2 | +| entropy_loss | -0.496 | +| explained_variance | -1.59 | +| learning_rate | 0.0001 | +| loss | -0.0876 | +| n_updates | 147030 | +| policy_gradient_loss | -0.0706 | +| value_loss | 0.000261 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.98e+03 | +| ep_rew_mean | 0.163 | +| time/ | | +| fps | 309 | +| iterations | 8652 | +| time_elapsed | 28626 | +| total_timesteps | 8859648 | +| train/ | | +| approx_kl | 1.6818185 | +| clip_fraction | 0.446 | +| clip_range | 0.2 | +| entropy_loss | -0.383 | +| explained_variance | -2.16 | +| learning_rate | 0.0001 | +| loss | -0.0605 | +| n_updates | 147040 | +| policy_gradient_loss | -0.0664 | +| value_loss | 0.000469 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.97e+03 | +| ep_rew_mean | 0.156 | +| time/ | | +| fps | 309 | +| iterations | 8653 | +| time_elapsed | 28630 | +| total_timesteps | 8860672 | +| train/ | | +| approx_kl | 1.743011 | +| clip_fraction | 0.517 | +| clip_range | 0.2 | +| entropy_loss | -0.512 | +| explained_variance | -3.03 | +| learning_rate | 0.0001 | +| loss | -0.0973 | +| n_updates | 147050 | +| policy_gradient_loss | -0.0645 | +| value_loss | 0.00045 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.97e+03 | +| ep_rew_mean | 0.156 | +| time/ | | +| fps | 309 | +| iterations | 8654 | +| time_elapsed | 28633 | +| total_timesteps | 8861696 | +| train/ | | +| approx_kl | 1.5965974 | +| clip_fraction | 0.498 | +| clip_range | 0.2 | +| entropy_loss | -0.488 | +| explained_variance | -2.07 | +| learning_rate | 0.0001 | +| loss | -0.0944 | +| n_updates | 147060 | +| policy_gradient_loss | -0.07 | +| value_loss | 0.000278 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.97e+03 | +| ep_rew_mean | 0.153 | +| time/ | | +| fps | 309 | +| iterations | 8655 | +| time_elapsed | 28636 | +| total_timesteps | 8862720 | +| train/ | | +| approx_kl | 2.1105294 | +| clip_fraction | 0.543 | +| clip_range | 0.2 | +| entropy_loss | -0.522 | +| explained_variance | -2.26 | +| learning_rate | 0.0001 | +| loss | -0.0771 | +| n_updates | 147070 | +| policy_gradient_loss | -0.0683 | +| value_loss | 0.000236 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.96e+03 | +| ep_rew_mean | 0.154 | +| time/ | | +| fps | 309 | +| iterations | 8656 | +| time_elapsed | 28639 | +| total_timesteps | 8863744 | +| train/ | | +| approx_kl | 1.7641683 | +| clip_fraction | 0.488 | +| clip_range | 0.2 | +| entropy_loss | -0.454 | +| explained_variance | -1.79 | +| learning_rate | 0.0001 | +| loss | -0.0726 | +| n_updates | 147080 | +| policy_gradient_loss | -0.0681 | +| value_loss | 0.000597 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.95e+03 | +| ep_rew_mean | 0.15 | +| time/ | | +| fps | 309 | +| iterations | 8657 | +| time_elapsed | 28642 | +| total_timesteps | 8864768 | +| train/ | | +| approx_kl | 1.90294 | +| clip_fraction | 0.498 | +| clip_range | 0.2 | +| entropy_loss | -0.427 | +| explained_variance | -6.1 | +| learning_rate | 0.0001 | +| loss | -0.0699 | +| n_updates | 147090 | +| policy_gradient_loss | -0.0664 | +| value_loss | 0.000422 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.94e+03 | +| ep_rew_mean | 0.148 | +| time/ | | +| fps | 309 | +| iterations | 8658 | +| time_elapsed | 28645 | +| total_timesteps | 8865792 | +| train/ | | +| approx_kl | 2.8797107 | +| clip_fraction | 0.495 | +| clip_range | 0.2 | +| entropy_loss | -0.412 | +| explained_variance | -1.48 | +| learning_rate | 0.0001 | +| loss | -0.0933 | +| n_updates | 147100 | +| policy_gradient_loss | -0.073 | +| value_loss | 0.00088 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.93e+03 | +| ep_rew_mean | 0.143 | +| time/ | | +| fps | 309 | +| iterations | 8659 | +| time_elapsed | 28649 | +| total_timesteps | 8866816 | +| train/ | | +| approx_kl | 1.9575286 | +| clip_fraction | 0.476 | +| clip_range | 0.2 | +| entropy_loss | -0.369 | +| explained_variance | -3.73 | +| learning_rate | 0.0001 | +| loss | -0.0881 | +| n_updates | 147110 | +| policy_gradient_loss | -0.07 | +| value_loss | 0.000597 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.93e+03 | +| ep_rew_mean | 0.143 | +| time/ | | +| fps | 309 | +| iterations | 8660 | +| time_elapsed | 28652 | +| total_timesteps | 8867840 | +| train/ | | +| approx_kl | 1.9106121 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.414 | +| explained_variance | -1.56 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 147120 | +| policy_gradient_loss | -0.0708 | +| value_loss | 0.000426 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.93e+03 | +| ep_rew_mean | 0.139 | +| time/ | | +| fps | 309 | +| iterations | 8661 | +| time_elapsed | 28655 | +| total_timesteps | 8868864 | +| train/ | | +| approx_kl | 3.848212 | +| clip_fraction | 0.514 | +| clip_range | 0.2 | +| entropy_loss | -0.457 | +| explained_variance | -1.1 | +| learning_rate | 0.0001 | +| loss | -0.0702 | +| n_updates | 147130 | +| policy_gradient_loss | -0.0721 | +| value_loss | 0.00052 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.93e+03 | +| ep_rew_mean | 0.139 | +| time/ | | +| fps | 309 | +| iterations | 8662 | +| time_elapsed | 28658 | +| total_timesteps | 8869888 | +| train/ | | +| approx_kl | 1.9800684 | +| clip_fraction | 0.505 | +| clip_range | 0.2 | +| entropy_loss | -0.43 | +| explained_variance | -2.59 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 147140 | +| policy_gradient_loss | -0.0705 | +| value_loss | 0.000444 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.92e+03 | +| ep_rew_mean | 0.135 | +| time/ | | +| fps | 309 | +| iterations | 8663 | +| time_elapsed | 28661 | +| total_timesteps | 8870912 | +| train/ | | +| approx_kl | 1.9667222 | +| clip_fraction | 0.543 | +| clip_range | 0.2 | +| entropy_loss | -0.428 | +| explained_variance | -0.904 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 147150 | +| policy_gradient_loss | -0.0764 | +| value_loss | 0.000589 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.92e+03 | +| ep_rew_mean | 0.135 | +| time/ | | +| fps | 309 | +| iterations | 8664 | +| time_elapsed | 28665 | +| total_timesteps | 8871936 | +| train/ | | +| approx_kl | 2.475335 | +| clip_fraction | 0.512 | +| clip_range | 0.2 | +| entropy_loss | -0.441 | +| explained_variance | -2.62 | +| learning_rate | 0.0001 | +| loss | -0.091 | +| n_updates | 147160 | +| policy_gradient_loss | -0.0719 | +| value_loss | 0.000339 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.91e+03 | +| ep_rew_mean | 0.134 | +| time/ | | +| fps | 309 | +| iterations | 8665 | +| time_elapsed | 28668 | +| total_timesteps | 8872960 | +| train/ | | +| approx_kl | 1.9450455 | +| clip_fraction | 0.502 | +| clip_range | 0.2 | +| entropy_loss | -0.464 | +| explained_variance | -0.687 | +| learning_rate | 0.0001 | +| loss | -0.0879 | +| n_updates | 147170 | +| policy_gradient_loss | -0.0665 | +| value_loss | 0.000333 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.91e+03 | +| ep_rew_mean | 0.134 | +| time/ | | +| fps | 309 | +| iterations | 8666 | +| time_elapsed | 28672 | +| total_timesteps | 8873984 | +| train/ | | +| approx_kl | 2.1009355 | +| clip_fraction | 0.493 | +| clip_range | 0.2 | +| entropy_loss | -0.458 | +| explained_variance | -0.729 | +| learning_rate | 0.0001 | +| loss | -0.0785 | +| n_updates | 147180 | +| policy_gradient_loss | -0.0641 | +| value_loss | 0.000474 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.9e+03 | +| ep_rew_mean | 0.13 | +| time/ | | +| fps | 309 | +| iterations | 8667 | +| time_elapsed | 28675 | +| total_timesteps | 8875008 | +| train/ | | +| approx_kl | 2.560502 | +| clip_fraction | 0.514 | +| clip_range | 0.2 | +| entropy_loss | -0.504 | +| explained_variance | -2.29 | +| learning_rate | 0.0001 | +| loss | -0.0943 | +| n_updates | 147190 | +| policy_gradient_loss | -0.0728 | +| value_loss | 0.000369 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.89e+03 | +| ep_rew_mean | 0.128 | +| time/ | | +| fps | 309 | +| iterations | 8668 | +| time_elapsed | 28678 | +| total_timesteps | 8876032 | +| train/ | | +| approx_kl | 1.5891032 | +| clip_fraction | 0.502 | +| clip_range | 0.2 | +| entropy_loss | -0.5 | +| explained_variance | -1.78 | +| learning_rate | 0.0001 | +| loss | -0.0918 | +| n_updates | 147200 | +| policy_gradient_loss | -0.0692 | +| value_loss | 0.000376 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.89e+03 | +| ep_rew_mean | 0.128 | +| time/ | | +| fps | 309 | +| iterations | 8669 | +| time_elapsed | 28682 | +| total_timesteps | 8877056 | +| train/ | | +| approx_kl | 1.4972217 | +| clip_fraction | 0.468 | +| clip_range | 0.2 | +| entropy_loss | -0.424 | +| explained_variance | -5.23 | +| learning_rate | 0.0001 | +| loss | -0.0827 | +| n_updates | 147210 | +| policy_gradient_loss | -0.0634 | +| value_loss | 0.000288 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.89e+03 | +| ep_rew_mean | 0.123 | +| time/ | | +| fps | 309 | +| iterations | 8670 | +| time_elapsed | 28685 | +| total_timesteps | 8878080 | +| train/ | | +| approx_kl | 4.317985 | +| clip_fraction | 0.537 | +| clip_range | 0.2 | +| entropy_loss | -0.489 | +| explained_variance | -1.14 | +| learning_rate | 0.0001 | +| loss | -0.0696 | +| n_updates | 147220 | +| policy_gradient_loss | -0.0751 | +| value_loss | 0.00038 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.118 | +| time/ | | +| fps | 309 | +| iterations | 8671 | +| time_elapsed | 28688 | +| total_timesteps | 8879104 | +| train/ | | +| approx_kl | 2.7436476 | +| clip_fraction | 0.501 | +| clip_range | 0.2 | +| entropy_loss | -0.502 | +| explained_variance | -1.34 | +| learning_rate | 0.0001 | +| loss | -0.0722 | +| n_updates | 147230 | +| policy_gradient_loss | -0.0655 | +| value_loss | 0.00105 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.116 | +| time/ | | +| fps | 309 | +| iterations | 8672 | +| time_elapsed | 28692 | +| total_timesteps | 8880128 | +| train/ | | +| approx_kl | 2.660162 | +| clip_fraction | 0.526 | +| clip_range | 0.2 | +| entropy_loss | -0.498 | +| explained_variance | -4.48 | +| learning_rate | 0.0001 | +| loss | -0.11 | +| n_updates | 147240 | +| policy_gradient_loss | -0.081 | +| value_loss | 0.000507 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.114 | +| time/ | | +| fps | 309 | +| iterations | 8673 | +| time_elapsed | 28695 | +| total_timesteps | 8881152 | +| train/ | | +| approx_kl | 2.00931 | +| clip_fraction | 0.492 | +| clip_range | 0.2 | +| entropy_loss | -0.402 | +| explained_variance | -0.978 | +| learning_rate | 0.0001 | +| loss | -0.0947 | +| n_updates | 147250 | +| policy_gradient_loss | -0.0648 | +| value_loss | 0.0004 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.114 | +| time/ | | +| fps | 309 | +| iterations | 8674 | +| time_elapsed | 28698 | +| total_timesteps | 8882176 | +| train/ | | +| approx_kl | 2.1650481 | +| clip_fraction | 0.46 | +| clip_range | 0.2 | +| entropy_loss | -0.411 | +| explained_variance | -1.22 | +| learning_rate | 0.0001 | +| loss | -0.0853 | +| n_updates | 147260 | +| policy_gradient_loss | -0.0657 | +| value_loss | 0.000552 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.85e+03 | +| ep_rew_mean | 0.112 | +| time/ | | +| fps | 309 | +| iterations | 8675 | +| time_elapsed | 28701 | +| total_timesteps | 8883200 | +| train/ | | +| approx_kl | 2.5637217 | +| clip_fraction | 0.507 | +| clip_range | 0.2 | +| entropy_loss | -0.46 | +| explained_variance | -2.27 | +| learning_rate | 0.0001 | +| loss | -0.0544 | +| n_updates | 147270 | +| policy_gradient_loss | -0.0708 | +| value_loss | 0.000405 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.106 | +| time/ | | +| fps | 309 | +| iterations | 8676 | +| time_elapsed | 28704 | +| total_timesteps | 8884224 | +| train/ | | +| approx_kl | 1.8379291 | +| clip_fraction | 0.463 | +| clip_range | 0.2 | +| entropy_loss | -0.402 | +| explained_variance | -4.6 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 147280 | +| policy_gradient_loss | -0.0699 | +| value_loss | 0.000576 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.81e+03 | +| ep_rew_mean | 0.104 | +| time/ | | +| fps | 309 | +| iterations | 8677 | +| time_elapsed | 28708 | +| total_timesteps | 8885248 | +| train/ | | +| approx_kl | 1.6596569 | +| clip_fraction | 0.482 | +| clip_range | 0.2 | +| entropy_loss | -0.453 | +| explained_variance | -1.19 | +| learning_rate | 0.0001 | +| loss | -0.0876 | +| n_updates | 147290 | +| policy_gradient_loss | -0.0655 | +| value_loss | 0.000615 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.101 | +| time/ | | +| fps | 309 | +| iterations | 8678 | +| time_elapsed | 28711 | +| total_timesteps | 8886272 | +| train/ | | +| approx_kl | 2.4000304 | +| clip_fraction | 0.491 | +| clip_range | 0.2 | +| entropy_loss | -0.413 | +| explained_variance | -1.15 | +| learning_rate | 0.0001 | +| loss | -0.107 | +| n_updates | 147300 | +| policy_gradient_loss | -0.0686 | +| value_loss | 0.000599 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.101 | +| time/ | | +| fps | 309 | +| iterations | 8679 | +| time_elapsed | 28714 | +| total_timesteps | 8887296 | +| train/ | | +| approx_kl | 2.074659 | +| clip_fraction | 0.49 | +| clip_range | 0.2 | +| entropy_loss | -0.431 | +| explained_variance | -2.97 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 147310 | +| policy_gradient_loss | -0.079 | +| value_loss | 0.000422 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.8e+03 | +| ep_rew_mean | 0.107 | +| time/ | | +| fps | 309 | +| iterations | 8680 | +| time_elapsed | 28717 | +| total_timesteps | 8888320 | +| train/ | | +| approx_kl | 2.0329332 | +| clip_fraction | 0.563 | +| clip_range | 0.2 | +| entropy_loss | -0.552 | +| explained_variance | -0.974 | +| learning_rate | 0.0001 | +| loss | -0.0837 | +| n_updates | 147320 | +| policy_gradient_loss | -0.0745 | +| value_loss | 0.000481 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.104 | +| time/ | | +| fps | 309 | +| iterations | 8681 | +| time_elapsed | 28720 | +| total_timesteps | 8889344 | +| train/ | | +| approx_kl | 1.8023043 | +| clip_fraction | 0.495 | +| clip_range | 0.2 | +| entropy_loss | -0.454 | +| explained_variance | -2.83 | +| learning_rate | 0.0001 | +| loss | -0.114 | +| n_updates | 147330 | +| policy_gradient_loss | -0.0704 | +| value_loss | 0.00064 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.0993 | +| time/ | | +| fps | 309 | +| iterations | 8682 | +| time_elapsed | 28724 | +| total_timesteps | 8890368 | +| train/ | | +| approx_kl | 1.7601466 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.503 | +| explained_variance | -0.343 | +| learning_rate | 0.0001 | +| loss | -0.0604 | +| n_updates | 147340 | +| policy_gradient_loss | -0.0643 | +| value_loss | 0.000654 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.0968 | +| time/ | | +| fps | 309 | +| iterations | 8683 | +| time_elapsed | 28727 | +| total_timesteps | 8891392 | +| train/ | | +| approx_kl | 2.0556188 | +| clip_fraction | 0.47 | +| clip_range | 0.2 | +| entropy_loss | -0.4 | +| explained_variance | -0.63 | +| learning_rate | 0.0001 | +| loss | -0.0781 | +| n_updates | 147350 | +| policy_gradient_loss | -0.0656 | +| value_loss | 0.000535 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.0968 | +| time/ | | +| fps | 309 | +| iterations | 8684 | +| time_elapsed | 28731 | +| total_timesteps | 8892416 | +| train/ | | +| approx_kl | 1.8152688 | +| clip_fraction | 0.49 | +| clip_range | 0.2 | +| entropy_loss | -0.466 | +| explained_variance | -0.821 | +| learning_rate | 0.0001 | +| loss | -0.0649 | +| n_updates | 147360 | +| policy_gradient_loss | -0.0671 | +| value_loss | 0.000338 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.0956 | +| time/ | | +| fps | 309 | +| iterations | 8685 | +| time_elapsed | 28734 | +| total_timesteps | 8893440 | +| train/ | | +| approx_kl | 2.3187027 | +| clip_fraction | 0.511 | +| clip_range | 0.2 | +| entropy_loss | -0.44 | +| explained_variance | -2.49 | +| learning_rate | 0.0001 | +| loss | -0.087 | +| n_updates | 147370 | +| policy_gradient_loss | -0.0705 | +| value_loss | 0.00036 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.0902 | +| time/ | | +| fps | 309 | +| iterations | 8686 | +| time_elapsed | 28737 | +| total_timesteps | 8894464 | +| train/ | | +| approx_kl | 1.5601532 | +| clip_fraction | 0.44 | +| clip_range | 0.2 | +| entropy_loss | -0.39 | +| explained_variance | -0.219 | +| learning_rate | 0.0001 | +| loss | -0.0766 | +| n_updates | 147380 | +| policy_gradient_loss | -0.0552 | +| value_loss | 0.000474 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.0892 | +| time/ | | +| fps | 309 | +| iterations | 8687 | +| time_elapsed | 28741 | +| total_timesteps | 8895488 | +| train/ | | +| approx_kl | 2.1653233 | +| clip_fraction | 0.467 | +| clip_range | 0.2 | +| entropy_loss | -0.41 | +| explained_variance | -0.864 | +| learning_rate | 0.0001 | +| loss | -0.074 | +| n_updates | 147390 | +| policy_gradient_loss | -0.0667 | +| value_loss | 0.00056 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.73e+03 | +| ep_rew_mean | 0.0892 | +| time/ | | +| fps | 309 | +| iterations | 8688 | +| time_elapsed | 28744 | +| total_timesteps | 8896512 | +| train/ | | +| approx_kl | 1.5877721 | +| clip_fraction | 0.469 | +| clip_range | 0.2 | +| entropy_loss | -0.448 | +| explained_variance | -0.426 | +| learning_rate | 0.0001 | +| loss | -0.0908 | +| n_updates | 147400 | +| policy_gradient_loss | -0.065 | +| value_loss | 0.000537 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.0889 | +| time/ | | +| fps | 309 | +| iterations | 8689 | +| time_elapsed | 28748 | +| total_timesteps | 8897536 | +| train/ | | +| approx_kl | 2.043312 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.414 | +| explained_variance | -2.53 | +| learning_rate | 0.0001 | +| loss | -0.073 | +| n_updates | 147410 | +| policy_gradient_loss | -0.0708 | +| value_loss | 0.000399 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.0925 | +| time/ | | +| fps | 309 | +| iterations | 8690 | +| time_elapsed | 28751 | +| total_timesteps | 8898560 | +| train/ | | +| approx_kl | 1.7590806 | +| clip_fraction | 0.478 | +| clip_range | 0.2 | +| entropy_loss | -0.461 | +| explained_variance | -0.775 | +| learning_rate | 0.0001 | +| loss | -0.071 | +| n_updates | 147420 | +| policy_gradient_loss | -0.0671 | +| value_loss | 0.000645 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.0944 | +| time/ | | +| fps | 309 | +| iterations | 8691 | +| time_elapsed | 28754 | +| total_timesteps | 8899584 | +| train/ | | +| approx_kl | 1.8169875 | +| clip_fraction | 0.516 | +| clip_range | 0.2 | +| entropy_loss | -0.492 | +| explained_variance | -0.322 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 147430 | +| policy_gradient_loss | -0.0774 | +| value_loss | 0.000737 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.0895 | +| time/ | | +| fps | 309 | +| iterations | 8692 | +| time_elapsed | 28757 | +| total_timesteps | 8900608 | +| train/ | | +| approx_kl | 1.9639361 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.387 | +| explained_variance | -1.12 | +| learning_rate | 0.0001 | +| loss | -0.0814 | +| n_updates | 147440 | +| policy_gradient_loss | -0.0694 | +| value_loss | 0.000681 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.0855 | +| time/ | | +| fps | 309 | +| iterations | 8693 | +| time_elapsed | 28760 | +| total_timesteps | 8901632 | +| train/ | | +| approx_kl | 1.6903591 | +| clip_fraction | 0.461 | +| clip_range | 0.2 | +| entropy_loss | -0.387 | +| explained_variance | -1.26 | +| learning_rate | 0.0001 | +| loss | -0.088 | +| n_updates | 147450 | +| policy_gradient_loss | -0.0688 | +| value_loss | 0.000579 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.0796 | +| time/ | | +| fps | 309 | +| iterations | 8694 | +| time_elapsed | 28763 | +| total_timesteps | 8902656 | +| train/ | | +| approx_kl | 1.5504844 | +| clip_fraction | 0.465 | +| clip_range | 0.2 | +| entropy_loss | -0.456 | +| explained_variance | -0.209 | +| learning_rate | 0.0001 | +| loss | -0.0703 | +| n_updates | 147460 | +| policy_gradient_loss | -0.0626 | +| value_loss | 0.000527 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | 0.0787 | +| time/ | | +| fps | 309 | +| iterations | 8695 | +| time_elapsed | 28766 | +| total_timesteps | 8903680 | +| train/ | | +| approx_kl | 1.8980477 | +| clip_fraction | 0.467 | +| clip_range | 0.2 | +| entropy_loss | -0.43 | +| explained_variance | -0.693 | +| learning_rate | 0.0001 | +| loss | -0.0739 | +| n_updates | 147470 | +| policy_gradient_loss | -0.0622 | +| value_loss | 0.000554 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.66e+03 | +| ep_rew_mean | 0.0787 | +| time/ | | +| fps | 309 | +| iterations | 8696 | +| time_elapsed | 28770 | +| total_timesteps | 8904704 | +| train/ | | +| approx_kl | 1.8364257 | +| clip_fraction | 0.463 | +| clip_range | 0.2 | +| entropy_loss | -0.444 | +| explained_variance | -0.195 | +| learning_rate | 0.0001 | +| loss | -0.0865 | +| n_updates | 147480 | +| policy_gradient_loss | -0.0666 | +| value_loss | 0.000428 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.65e+03 | +| ep_rew_mean | 0.0749 | +| time/ | | +| fps | 309 | +| iterations | 8697 | +| time_elapsed | 28773 | +| total_timesteps | 8905728 | +| train/ | | +| approx_kl | 1.6800431 | +| clip_fraction | 0.488 | +| clip_range | 0.2 | +| entropy_loss | -0.449 | +| explained_variance | -1.81 | +| learning_rate | 0.0001 | +| loss | -0.0782 | +| n_updates | 147490 | +| policy_gradient_loss | -0.0661 | +| value_loss | 0.000371 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.64e+03 | +| ep_rew_mean | 0.0729 | +| time/ | | +| fps | 309 | +| iterations | 8698 | +| time_elapsed | 28776 | +| total_timesteps | 8906752 | +| train/ | | +| approx_kl | 1.342145 | +| clip_fraction | 0.422 | +| clip_range | 0.2 | +| entropy_loss | -0.395 | +| explained_variance | -0.425 | +| learning_rate | 0.0001 | +| loss | -0.0382 | +| n_updates | 147500 | +| policy_gradient_loss | -0.0521 | +| value_loss | 0.000382 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.63e+03 | +| ep_rew_mean | 0.0737 | +| time/ | | +| fps | 309 | +| iterations | 8699 | +| time_elapsed | 28779 | +| total_timesteps | 8907776 | +| train/ | | +| approx_kl | 9.17563 | +| clip_fraction | 0.431 | +| clip_range | 0.2 | +| entropy_loss | -0.324 | +| explained_variance | -0.0643 | +| learning_rate | 0.0001 | +| loss | -0.0876 | +| n_updates | 147510 | +| policy_gradient_loss | -0.0603 | +| value_loss | 0.000597 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.63e+03 | +| ep_rew_mean | 0.0737 | +| time/ | | +| fps | 309 | +| iterations | 8700 | +| time_elapsed | 28783 | +| total_timesteps | 8908800 | +| train/ | | +| approx_kl | 3.627882 | +| clip_fraction | 0.47 | +| clip_range | 0.2 | +| entropy_loss | -0.398 | +| explained_variance | -0.722 | +| learning_rate | 0.0001 | +| loss | -0.0727 | +| n_updates | 147520 | +| policy_gradient_loss | -0.0596 | +| value_loss | 0.000599 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | 0.0761 | +| time/ | | +| fps | 309 | +| iterations | 8701 | +| time_elapsed | 28786 | +| total_timesteps | 8909824 | +| train/ | | +| approx_kl | 1.5931726 | +| clip_fraction | 0.469 | +| clip_range | 0.2 | +| entropy_loss | -0.385 | +| explained_variance | -0.681 | +| learning_rate | 0.0001 | +| loss | -0.108 | +| n_updates | 147530 | +| policy_gradient_loss | -0.0755 | +| value_loss | 0.000508 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | 0.0761 | +| time/ | | +| fps | 309 | +| iterations | 8702 | +| time_elapsed | 28790 | +| total_timesteps | 8910848 | +| train/ | | +| approx_kl | 2.0363364 | +| clip_fraction | 0.457 | +| clip_range | 0.2 | +| entropy_loss | -0.397 | +| explained_variance | -0.888 | +| learning_rate | 0.0001 | +| loss | -0.0812 | +| n_updates | 147540 | +| policy_gradient_loss | -0.0554 | +| value_loss | 0.000776 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.57e+03 | +| ep_rew_mean | 0.0671 | +| time/ | | +| fps | 309 | +| iterations | 8703 | +| time_elapsed | 28793 | +| total_timesteps | 8911872 | +| train/ | | +| approx_kl | 1.5343857 | +| clip_fraction | 0.519 | +| clip_range | 0.2 | +| entropy_loss | -0.463 | +| explained_variance | -3.61 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 147550 | +| policy_gradient_loss | -0.0758 | +| value_loss | 0.000285 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.57e+03 | +| ep_rew_mean | 0.0671 | +| time/ | | +| fps | 309 | +| iterations | 8704 | +| time_elapsed | 28797 | +| total_timesteps | 8912896 | +| train/ | | +| approx_kl | 1.8276657 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.436 | +| explained_variance | -0.563 | +| learning_rate | 0.0001 | +| loss | -0.0702 | +| n_updates | 147560 | +| policy_gradient_loss | -0.0676 | +| value_loss | 0.000577 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.55e+03 | +| ep_rew_mean | 0.0661 | +| time/ | | +| fps | 309 | +| iterations | 8705 | +| time_elapsed | 28800 | +| total_timesteps | 8913920 | +| train/ | | +| approx_kl | 1.7675962 | +| clip_fraction | 0.49 | +| clip_range | 0.2 | +| entropy_loss | -0.444 | +| explained_variance | -1.52 | +| learning_rate | 0.0001 | +| loss | -0.0952 | +| n_updates | 147570 | +| policy_gradient_loss | -0.0631 | +| value_loss | 0.000552 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.54e+03 | +| ep_rew_mean | 0.0688 | +| time/ | | +| fps | 309 | +| iterations | 8706 | +| time_elapsed | 28804 | +| total_timesteps | 8914944 | +| train/ | | +| approx_kl | 1.5557067 | +| clip_fraction | 0.458 | +| clip_range | 0.2 | +| entropy_loss | -0.376 | +| explained_variance | -0.753 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 147580 | +| policy_gradient_loss | -0.065 | +| value_loss | 0.000568 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.54e+03 | +| ep_rew_mean | 0.0688 | +| time/ | | +| fps | 309 | +| iterations | 8707 | +| time_elapsed | 28807 | +| total_timesteps | 8915968 | +| train/ | | +| approx_kl | 2.5559926 | +| clip_fraction | 0.496 | +| clip_range | 0.2 | +| entropy_loss | -0.436 | +| explained_variance | -2.24 | +| learning_rate | 0.0001 | +| loss | -0.0959 | +| n_updates | 147590 | +| policy_gradient_loss | -0.0692 | +| value_loss | 0.000366 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.53e+03 | +| ep_rew_mean | 0.0702 | +| time/ | | +| fps | 309 | +| iterations | 8708 | +| time_elapsed | 28810 | +| total_timesteps | 8916992 | +| train/ | | +| approx_kl | 3.4579897 | +| clip_fraction | 0.503 | +| clip_range | 0.2 | +| entropy_loss | -0.439 | +| explained_variance | -1.26 | +| learning_rate | 0.0001 | +| loss | -0.0792 | +| n_updates | 147600 | +| policy_gradient_loss | -0.0622 | +| value_loss | 0.000238 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.53e+03 | +| ep_rew_mean | 0.0702 | +| time/ | | +| fps | 309 | +| iterations | 8709 | +| time_elapsed | 28814 | +| total_timesteps | 8918016 | +| train/ | | +| approx_kl | 1.8572598 | +| clip_fraction | 0.476 | +| clip_range | 0.2 | +| entropy_loss | -0.423 | +| explained_variance | -0.0938 | +| learning_rate | 0.0001 | +| loss | -0.0728 | +| n_updates | 147610 | +| policy_gradient_loss | -0.0592 | +| value_loss | 0.000239 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.52e+03 | +| ep_rew_mean | 0.0694 | +| time/ | | +| fps | 309 | +| iterations | 8710 | +| time_elapsed | 28817 | +| total_timesteps | 8919040 | +| train/ | | +| approx_kl | 1.2566829 | +| clip_fraction | 0.505 | +| clip_range | 0.2 | +| entropy_loss | -0.536 | +| explained_variance | -5.82 | +| learning_rate | 0.0001 | +| loss | -0.0906 | +| n_updates | 147620 | +| policy_gradient_loss | -0.0651 | +| value_loss | 0.000452 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.51e+03 | +| ep_rew_mean | 0.0669 | +| time/ | | +| fps | 309 | +| iterations | 8711 | +| time_elapsed | 28820 | +| total_timesteps | 8920064 | +| train/ | | +| approx_kl | 1.5799098 | +| clip_fraction | 0.473 | +| clip_range | 0.2 | +| entropy_loss | -0.439 | +| explained_variance | -0.578 | +| learning_rate | 0.0001 | +| loss | -0.0664 | +| n_updates | 147630 | +| policy_gradient_loss | -0.0614 | +| value_loss | 0.000417 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.49e+03 | +| ep_rew_mean | 0.0675 | +| time/ | | +| fps | 309 | +| iterations | 8712 | +| time_elapsed | 28823 | +| total_timesteps | 8921088 | +| train/ | | +| approx_kl | 1.7118123 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.401 | +| explained_variance | -0.593 | +| learning_rate | 0.0001 | +| loss | -0.0659 | +| n_updates | 147640 | +| policy_gradient_loss | -0.0612 | +| value_loss | 0.000294 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.49e+03 | +| ep_rew_mean | 0.0675 | +| time/ | | +| fps | 309 | +| iterations | 8713 | +| time_elapsed | 28826 | +| total_timesteps | 8922112 | +| train/ | | +| approx_kl | 1.7921495 | +| clip_fraction | 0.462 | +| clip_range | 0.2 | +| entropy_loss | -0.478 | +| explained_variance | -0.894 | +| learning_rate | 0.0001 | +| loss | -0.0826 | +| n_updates | 147650 | +| policy_gradient_loss | -0.0636 | +| value_loss | 0.000492 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.48e+03 | +| ep_rew_mean | 0.0685 | +| time/ | | +| fps | 309 | +| iterations | 8714 | +| time_elapsed | 28829 | +| total_timesteps | 8923136 | +| train/ | | +| approx_kl | 1.9184613 | +| clip_fraction | 0.473 | +| clip_range | 0.2 | +| entropy_loss | -0.446 | +| explained_variance | -1.09 | +| learning_rate | 0.0001 | +| loss | -0.057 | +| n_updates | 147660 | +| policy_gradient_loss | -0.0614 | +| value_loss | 0.000316 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.47e+03 | +| ep_rew_mean | 0.0667 | +| time/ | | +| fps | 309 | +| iterations | 8715 | +| time_elapsed | 28833 | +| total_timesteps | 8924160 | +| train/ | | +| approx_kl | 1.5096787 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.458 | +| explained_variance | -0.28 | +| learning_rate | 0.0001 | +| loss | -0.0427 | +| n_updates | 147670 | +| policy_gradient_loss | -0.0643 | +| value_loss | 0.000545 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.47e+03 | +| ep_rew_mean | 0.0667 | +| time/ | | +| fps | 309 | +| iterations | 8716 | +| time_elapsed | 28836 | +| total_timesteps | 8925184 | +| train/ | | +| approx_kl | 2.2619576 | +| clip_fraction | 0.455 | +| clip_range | 0.2 | +| entropy_loss | -0.404 | +| explained_variance | -0.446 | +| learning_rate | 0.0001 | +| loss | -0.0851 | +| n_updates | 147680 | +| policy_gradient_loss | -0.0638 | +| value_loss | 0.000589 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.46e+03 | +| ep_rew_mean | 0.0659 | +| time/ | | +| fps | 309 | +| iterations | 8717 | +| time_elapsed | 28839 | +| total_timesteps | 8926208 | +| train/ | | +| approx_kl | 2.4373264 | +| clip_fraction | 0.542 | +| clip_range | 0.2 | +| entropy_loss | -0.476 | +| explained_variance | -2.13 | +| learning_rate | 0.0001 | +| loss | -0.1 | +| n_updates | 147690 | +| policy_gradient_loss | -0.0767 | +| value_loss | 0.000522 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.45e+03 | +| ep_rew_mean | 0.0673 | +| time/ | | +| fps | 309 | +| iterations | 8718 | +| time_elapsed | 28842 | +| total_timesteps | 8927232 | +| train/ | | +| approx_kl | 2.0637875 | +| clip_fraction | 0.493 | +| clip_range | 0.2 | +| entropy_loss | -0.417 | +| explained_variance | -1.11 | +| learning_rate | 0.0001 | +| loss | -0.0478 | +| n_updates | 147700 | +| policy_gradient_loss | -0.0617 | +| value_loss | 0.000527 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.45e+03 | +| ep_rew_mean | 0.0673 | +| time/ | | +| fps | 309 | +| iterations | 8719 | +| time_elapsed | 28846 | +| total_timesteps | 8928256 | +| train/ | | +| approx_kl | 3.8825457 | +| clip_fraction | 0.489 | +| clip_range | 0.2 | +| entropy_loss | -0.406 | +| explained_variance | -2.28 | +| learning_rate | 0.0001 | +| loss | -0.0811 | +| n_updates | 147710 | +| policy_gradient_loss | -0.0706 | +| value_loss | 0.000693 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.44e+03 | +| ep_rew_mean | 0.0729 | +| time/ | | +| fps | 309 | +| iterations | 8720 | +| time_elapsed | 28849 | +| total_timesteps | 8929280 | +| train/ | | +| approx_kl | 2.5265834 | +| clip_fraction | 0.499 | +| clip_range | 0.2 | +| entropy_loss | -0.421 | +| explained_variance | -0.874 | +| learning_rate | 0.0001 | +| loss | -0.0862 | +| n_updates | 147720 | +| policy_gradient_loss | -0.0742 | +| value_loss | 0.000445 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.0738 | +| time/ | | +| fps | 309 | +| iterations | 8721 | +| time_elapsed | 28852 | +| total_timesteps | 8930304 | +| train/ | | +| approx_kl | 4.0931463 | +| clip_fraction | 0.505 | +| clip_range | 0.2 | +| entropy_loss | -0.404 | +| explained_variance | -1.13 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 147730 | +| policy_gradient_loss | -0.08 | +| value_loss | 0.000492 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.0738 | +| time/ | | +| fps | 309 | +| iterations | 8722 | +| time_elapsed | 28856 | +| total_timesteps | 8931328 | +| train/ | | +| approx_kl | 2.278549 | +| clip_fraction | 0.491 | +| clip_range | 0.2 | +| entropy_loss | -0.367 | +| explained_variance | -2.29 | +| learning_rate | 0.0001 | +| loss | -0.112 | +| n_updates | 147740 | +| policy_gradient_loss | -0.0758 | +| value_loss | 0.000578 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.0719 | +| time/ | | +| fps | 309 | +| iterations | 8723 | +| time_elapsed | 28859 | +| total_timesteps | 8932352 | +| train/ | | +| approx_kl | 2.0607843 | +| clip_fraction | 0.511 | +| clip_range | 0.2 | +| entropy_loss | -0.462 | +| explained_variance | -3.25 | +| learning_rate | 0.0001 | +| loss | -0.0937 | +| n_updates | 147750 | +| policy_gradient_loss | -0.0723 | +| value_loss | 0.000485 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.065 | +| time/ | | +| fps | 309 | +| iterations | 8724 | +| time_elapsed | 28863 | +| total_timesteps | 8933376 | +| train/ | | +| approx_kl | 1.4965599 | +| clip_fraction | 0.495 | +| clip_range | 0.2 | +| entropy_loss | -0.44 | +| explained_variance | -3.18 | +| learning_rate | 0.0001 | +| loss | -0.0622 | +| n_updates | 147760 | +| policy_gradient_loss | -0.0651 | +| value_loss | 0.000383 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.065 | +| time/ | | +| fps | 309 | +| iterations | 8725 | +| time_elapsed | 28866 | +| total_timesteps | 8934400 | +| train/ | | +| approx_kl | 2.169742 | +| clip_fraction | 0.53 | +| clip_range | 0.2 | +| entropy_loss | -0.431 | +| explained_variance | -1.52 | +| learning_rate | 0.0001 | +| loss | -0.0751 | +| n_updates | 147770 | +| policy_gradient_loss | -0.0712 | +| value_loss | 0.00042 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0634 | +| time/ | | +| fps | 309 | +| iterations | 8726 | +| time_elapsed | 28870 | +| total_timesteps | 8935424 | +| train/ | | +| approx_kl | 1.658115 | +| clip_fraction | 0.478 | +| clip_range | 0.2 | +| entropy_loss | -0.407 | +| explained_variance | -3.16 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 147780 | +| policy_gradient_loss | -0.0666 | +| value_loss | 0.00036 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0634 | +| time/ | | +| fps | 309 | +| iterations | 8727 | +| time_elapsed | 28873 | +| total_timesteps | 8936448 | +| train/ | | +| approx_kl | 2.5112908 | +| clip_fraction | 0.492 | +| clip_range | 0.2 | +| entropy_loss | -0.444 | +| explained_variance | -1.76 | +| learning_rate | 0.0001 | +| loss | -0.0967 | +| n_updates | 147790 | +| policy_gradient_loss | -0.0733 | +| value_loss | 0.000351 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0535 | +| time/ | | +| fps | 309 | +| iterations | 8728 | +| time_elapsed | 28876 | +| total_timesteps | 8937472 | +| train/ | | +| approx_kl | 1.6659344 | +| clip_fraction | 0.521 | +| clip_range | 0.2 | +| entropy_loss | -0.487 | +| explained_variance | -0.653 | +| learning_rate | 0.0001 | +| loss | -0.0844 | +| n_updates | 147800 | +| policy_gradient_loss | -0.0716 | +| value_loss | 0.000378 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0535 | +| time/ | | +| fps | 309 | +| iterations | 8729 | +| time_elapsed | 28879 | +| total_timesteps | 8938496 | +| train/ | | +| approx_kl | 1.7651379 | +| clip_fraction | 0.529 | +| clip_range | 0.2 | +| entropy_loss | -0.479 | +| explained_variance | -1.85 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 147810 | +| policy_gradient_loss | -0.0653 | +| value_loss | 0.000489 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.05 | +| time/ | | +| fps | 309 | +| iterations | 8730 | +| time_elapsed | 28882 | +| total_timesteps | 8939520 | +| train/ | | +| approx_kl | 1.5301068 | +| clip_fraction | 0.523 | +| clip_range | 0.2 | +| entropy_loss | -0.529 | +| explained_variance | -4.05 | +| learning_rate | 0.0001 | +| loss | -0.1 | +| n_updates | 147820 | +| policy_gradient_loss | -0.0734 | +| value_loss | 0.000622 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0462 | +| time/ | | +| fps | 309 | +| iterations | 8731 | +| time_elapsed | 28886 | +| total_timesteps | 8940544 | +| train/ | | +| approx_kl | 2.0530434 | +| clip_fraction | 0.524 | +| clip_range | 0.2 | +| entropy_loss | -0.453 | +| explained_variance | -3.05 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 147830 | +| policy_gradient_loss | -0.0785 | +| value_loss | 0.000691 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0437 | +| time/ | | +| fps | 309 | +| iterations | 8732 | +| time_elapsed | 28889 | +| total_timesteps | 8941568 | +| train/ | | +| approx_kl | 2.0382538 | +| clip_fraction | 0.507 | +| clip_range | 0.2 | +| entropy_loss | -0.429 | +| explained_variance | -2.14 | +| learning_rate | 0.0001 | +| loss | -0.0783 | +| n_updates | 147840 | +| policy_gradient_loss | -0.075 | +| value_loss | 0.000704 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0423 | +| time/ | | +| fps | 309 | +| iterations | 8733 | +| time_elapsed | 28892 | +| total_timesteps | 8942592 | +| train/ | | +| approx_kl | 1.5968578 | +| clip_fraction | 0.509 | +| clip_range | 0.2 | +| entropy_loss | -0.505 | +| explained_variance | -1.08 | +| learning_rate | 0.0001 | +| loss | -0.0999 | +| n_updates | 147850 | +| policy_gradient_loss | -0.0652 | +| value_loss | 0.00052 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0427 | +| time/ | | +| fps | 309 | +| iterations | 8734 | +| time_elapsed | 28895 | +| total_timesteps | 8943616 | +| train/ | | +| approx_kl | 1.838351 | +| clip_fraction | 0.5 | +| clip_range | 0.2 | +| entropy_loss | -0.459 | +| explained_variance | -6.42 | +| learning_rate | 0.0001 | +| loss | -0.092 | +| n_updates | 147860 | +| policy_gradient_loss | -0.0738 | +| value_loss | 0.000307 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0427 | +| time/ | | +| fps | 309 | +| iterations | 8735 | +| time_elapsed | 28898 | +| total_timesteps | 8944640 | +| train/ | | +| approx_kl | 3.4093459 | +| clip_fraction | 0.501 | +| clip_range | 0.2 | +| entropy_loss | -0.453 | +| explained_variance | -2.54 | +| learning_rate | 0.0001 | +| loss | -0.115 | +| n_updates | 147870 | +| policy_gradient_loss | -0.073 | +| value_loss | 0.000379 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0407 | +| time/ | | +| fps | 309 | +| iterations | 8736 | +| time_elapsed | 28902 | +| total_timesteps | 8945664 | +| train/ | | +| approx_kl | 1.7966952 | +| clip_fraction | 0.548 | +| clip_range | 0.2 | +| entropy_loss | -0.546 | +| explained_variance | -2.37 | +| learning_rate | 0.0001 | +| loss | -0.0766 | +| n_updates | 147880 | +| policy_gradient_loss | -0.079 | +| value_loss | 0.000294 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0372 | +| time/ | | +| fps | 309 | +| iterations | 8737 | +| time_elapsed | 28905 | +| total_timesteps | 8946688 | +| train/ | | +| approx_kl | 1.8224087 | +| clip_fraction | 0.496 | +| clip_range | 0.2 | +| entropy_loss | -0.438 | +| explained_variance | -3.75 | +| learning_rate | 0.0001 | +| loss | -0.112 | +| n_updates | 147890 | +| policy_gradient_loss | -0.0719 | +| value_loss | 0.000579 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0367 | +| time/ | | +| fps | 309 | +| iterations | 8738 | +| time_elapsed | 28909 | +| total_timesteps | 8947712 | +| train/ | | +| approx_kl | 1.8050768 | +| clip_fraction | 0.482 | +| clip_range | 0.2 | +| entropy_loss | -0.445 | +| explained_variance | -1.47 | +| learning_rate | 0.0001 | +| loss | -0.113 | +| n_updates | 147900 | +| policy_gradient_loss | -0.0656 | +| value_loss | 0.000493 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0366 | +| time/ | | +| fps | 309 | +| iterations | 8739 | +| time_elapsed | 28912 | +| total_timesteps | 8948736 | +| train/ | | +| approx_kl | 2.0543218 | +| clip_fraction | 0.477 | +| clip_range | 0.2 | +| entropy_loss | -0.382 | +| explained_variance | -2.01 | +| learning_rate | 0.0001 | +| loss | -0.0429 | +| n_updates | 147910 | +| policy_gradient_loss | -0.0662 | +| value_loss | 0.000358 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.034 | +| time/ | | +| fps | 309 | +| iterations | 8740 | +| time_elapsed | 28916 | +| total_timesteps | 8949760 | +| train/ | | +| approx_kl | 2.1202204 | +| clip_fraction | 0.5 | +| clip_range | 0.2 | +| entropy_loss | -0.388 | +| explained_variance | -3.24 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 147920 | +| policy_gradient_loss | -0.0746 | +| value_loss | 0.000442 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0332 | +| time/ | | +| fps | 309 | +| iterations | 8741 | +| time_elapsed | 28919 | +| total_timesteps | 8950784 | +| train/ | | +| approx_kl | 1.4463699 | +| clip_fraction | 0.479 | +| clip_range | 0.2 | +| entropy_loss | -0.405 | +| explained_variance | -2.2 | +| learning_rate | 0.0001 | +| loss | -0.0931 | +| n_updates | 147930 | +| policy_gradient_loss | -0.0708 | +| value_loss | 0.000545 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0332 | +| time/ | | +| fps | 309 | +| iterations | 8742 | +| time_elapsed | 28923 | +| total_timesteps | 8951808 | +| train/ | | +| approx_kl | 1.9571757 | +| clip_fraction | 0.515 | +| clip_range | 0.2 | +| entropy_loss | -0.445 | +| explained_variance | -2.01 | +| learning_rate | 0.0001 | +| loss | -0.0982 | +| n_updates | 147940 | +| policy_gradient_loss | -0.0776 | +| value_loss | 0.000255 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0318 | +| time/ | | +| fps | 309 | +| iterations | 8743 | +| time_elapsed | 28926 | +| total_timesteps | 8952832 | +| train/ | | +| approx_kl | 2.730358 | +| clip_fraction | 0.479 | +| clip_range | 0.2 | +| entropy_loss | -0.375 | +| explained_variance | -1.54 | +| learning_rate | 0.0001 | +| loss | -0.0447 | +| n_updates | 147950 | +| policy_gradient_loss | -0.0621 | +| value_loss | 0.000217 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0318 | +| time/ | | +| fps | 309 | +| iterations | 8744 | +| time_elapsed | 28930 | +| total_timesteps | 8953856 | +| train/ | | +| approx_kl | 1.971764 | +| clip_fraction | 0.46 | +| clip_range | 0.2 | +| entropy_loss | -0.367 | +| explained_variance | -1.63 | +| learning_rate | 0.0001 | +| loss | -0.0953 | +| n_updates | 147960 | +| policy_gradient_loss | -0.0699 | +| value_loss | 0.000437 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0302 | +| time/ | | +| fps | 309 | +| iterations | 8745 | +| time_elapsed | 28933 | +| total_timesteps | 8954880 | +| train/ | | +| approx_kl | 1.6622136 | +| clip_fraction | 0.5 | +| clip_range | 0.2 | +| entropy_loss | -0.446 | +| explained_variance | -1.63 | +| learning_rate | 0.0001 | +| loss | -0.0894 | +| n_updates | 147970 | +| policy_gradient_loss | -0.072 | +| value_loss | 0.000477 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0302 | +| time/ | | +| fps | 309 | +| iterations | 8746 | +| time_elapsed | 28936 | +| total_timesteps | 8955904 | +| train/ | | +| approx_kl | 4.395133 | +| clip_fraction | 0.445 | +| clip_range | 0.2 | +| entropy_loss | -0.37 | +| explained_variance | -1.41 | +| learning_rate | 0.0001 | +| loss | -0.0941 | +| n_updates | 147980 | +| policy_gradient_loss | -0.0586 | +| value_loss | 0.000503 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0309 | +| time/ | | +| fps | 309 | +| iterations | 8747 | +| time_elapsed | 28939 | +| total_timesteps | 8956928 | +| train/ | | +| approx_kl | 2.0026913 | +| clip_fraction | 0.517 | +| clip_range | 0.2 | +| entropy_loss | -0.446 | +| explained_variance | -1.05 | +| learning_rate | 0.0001 | +| loss | -0.0852 | +| n_updates | 147990 | +| policy_gradient_loss | -0.0679 | +| value_loss | 0.000422 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0294 | +| time/ | | +| fps | 309 | +| iterations | 8748 | +| time_elapsed | 28943 | +| total_timesteps | 8957952 | +| train/ | | +| approx_kl | 1.5950122 | +| clip_fraction | 0.474 | +| clip_range | 0.2 | +| entropy_loss | -0.425 | +| explained_variance | -0.607 | +| learning_rate | 0.0001 | +| loss | -0.0964 | +| n_updates | 148000 | +| policy_gradient_loss | -0.0658 | +| value_loss | 0.000486 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0294 | +| time/ | | +| fps | 309 | +| iterations | 8749 | +| time_elapsed | 28946 | +| total_timesteps | 8958976 | +| train/ | | +| approx_kl | 5.1771803 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.401 | +| explained_variance | -3.66 | +| learning_rate | 0.0001 | +| loss | -0.0497 | +| n_updates | 148010 | +| policy_gradient_loss | -0.0687 | +| value_loss | 0.000661 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0293 | +| time/ | | +| fps | 309 | +| iterations | 8750 | +| time_elapsed | 28949 | +| total_timesteps | 8960000 | +| train/ | | +| approx_kl | 1.9730833 | +| clip_fraction | 0.519 | +| clip_range | 0.2 | +| entropy_loss | -0.476 | +| explained_variance | -1.07 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 148020 | +| policy_gradient_loss | -0.0705 | +| value_loss | 0.000513 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0293 | +| time/ | | +| fps | 309 | +| iterations | 8751 | +| time_elapsed | 28952 | +| total_timesteps | 8961024 | +| train/ | | +| approx_kl | 1.7982855 | +| clip_fraction | 0.484 | +| clip_range | 0.2 | +| entropy_loss | -0.401 | +| explained_variance | -2.07 | +| learning_rate | 0.0001 | +| loss | -0.111 | +| n_updates | 148030 | +| policy_gradient_loss | -0.0635 | +| value_loss | 0.000498 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0302 | +| time/ | | +| fps | 309 | +| iterations | 8752 | +| time_elapsed | 28955 | +| total_timesteps | 8962048 | +| train/ | | +| approx_kl | 2.4263225 | +| clip_fraction | 0.461 | +| clip_range | 0.2 | +| entropy_loss | -0.331 | +| explained_variance | -5.03 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 148040 | +| policy_gradient_loss | -0.0679 | +| value_loss | 0.000712 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0302 | +| time/ | | +| fps | 309 | +| iterations | 8753 | +| time_elapsed | 28958 | +| total_timesteps | 8963072 | +| train/ | | +| approx_kl | 2.2400641 | +| clip_fraction | 0.458 | +| clip_range | 0.2 | +| entropy_loss | -0.346 | +| explained_variance | -1.91 | +| learning_rate | 0.0001 | +| loss | -0.093 | +| n_updates | 148050 | +| policy_gradient_loss | -0.0679 | +| value_loss | 0.000557 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.033 | +| time/ | | +| fps | 309 | +| iterations | 8754 | +| time_elapsed | 28962 | +| total_timesteps | 8964096 | +| train/ | | +| approx_kl | 1.5680664 | +| clip_fraction | 0.484 | +| clip_range | 0.2 | +| entropy_loss | -0.451 | +| explained_variance | -2.26 | +| learning_rate | 0.0001 | +| loss | -0.0987 | +| n_updates | 148060 | +| policy_gradient_loss | -0.0641 | +| value_loss | 0.000391 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0346 | +| time/ | | +| fps | 309 | +| iterations | 8755 | +| time_elapsed | 28965 | +| total_timesteps | 8965120 | +| train/ | | +| approx_kl | 1.9401335 | +| clip_fraction | 0.479 | +| clip_range | 0.2 | +| entropy_loss | -0.37 | +| explained_variance | -1.02 | +| learning_rate | 0.0001 | +| loss | -0.0545 | +| n_updates | 148070 | +| policy_gradient_loss | -0.0654 | +| value_loss | 0.00048 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.036 | +| time/ | | +| fps | 309 | +| iterations | 8756 | +| time_elapsed | 28969 | +| total_timesteps | 8966144 | +| train/ | | +| approx_kl | 2.6268814 | +| clip_fraction | 0.482 | +| clip_range | 0.2 | +| entropy_loss | -0.383 | +| explained_variance | -1.53 | +| learning_rate | 0.0001 | +| loss | -0.0953 | +| n_updates | 148080 | +| policy_gradient_loss | -0.0655 | +| value_loss | 0.000416 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0356 | +| time/ | | +| fps | 309 | +| iterations | 8757 | +| time_elapsed | 28972 | +| total_timesteps | 8967168 | +| train/ | | +| approx_kl | 1.9314499 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.379 | +| explained_variance | -3.32 | +| learning_rate | 0.0001 | +| loss | -0.0595 | +| n_updates | 148090 | +| policy_gradient_loss | -0.0657 | +| value_loss | 0.000228 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0338 | +| time/ | | +| fps | 309 | +| iterations | 8758 | +| time_elapsed | 28975 | +| total_timesteps | 8968192 | +| train/ | | +| approx_kl | 2.129533 | +| clip_fraction | 0.46 | +| clip_range | 0.2 | +| entropy_loss | -0.367 | +| explained_variance | -0.982 | +| learning_rate | 0.0001 | +| loss | -0.0675 | +| n_updates | 148100 | +| policy_gradient_loss | -0.0707 | +| value_loss | 0.000447 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0338 | +| time/ | | +| fps | 309 | +| iterations | 8759 | +| time_elapsed | 28979 | +| total_timesteps | 8969216 | +| train/ | | +| approx_kl | 1.9230323 | +| clip_fraction | 0.456 | +| clip_range | 0.2 | +| entropy_loss | -0.405 | +| explained_variance | -1.49 | +| learning_rate | 0.0001 | +| loss | -0.0915 | +| n_updates | 148110 | +| policy_gradient_loss | -0.0636 | +| value_loss | 0.000457 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0331 | +| time/ | | +| fps | 309 | +| iterations | 8760 | +| time_elapsed | 28982 | +| total_timesteps | 8970240 | +| train/ | | +| approx_kl | 2.0395646 | +| clip_fraction | 0.503 | +| clip_range | 0.2 | +| entropy_loss | -0.399 | +| explained_variance | -6.38 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 148120 | +| policy_gradient_loss | -0.0705 | +| value_loss | 0.000471 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0331 | +| time/ | | +| fps | 309 | +| iterations | 8761 | +| time_elapsed | 28985 | +| total_timesteps | 8971264 | +| train/ | | +| approx_kl | 1.8054826 | +| clip_fraction | 0.45 | +| clip_range | 0.2 | +| entropy_loss | -0.383 | +| explained_variance | -1.12 | +| learning_rate | 0.0001 | +| loss | -0.0967 | +| n_updates | 148130 | +| policy_gradient_loss | -0.0618 | +| value_loss | 0.000492 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0351 | +| time/ | | +| fps | 309 | +| iterations | 8762 | +| time_elapsed | 28989 | +| total_timesteps | 8972288 | +| train/ | | +| approx_kl | 1.9726269 | +| clip_fraction | 0.495 | +| clip_range | 0.2 | +| entropy_loss | -0.411 | +| explained_variance | -1.49 | +| learning_rate | 0.0001 | +| loss | -0.093 | +| n_updates | 148140 | +| policy_gradient_loss | -0.0677 | +| value_loss | 0.000581 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0352 | +| time/ | | +| fps | 309 | +| iterations | 8763 | +| time_elapsed | 28992 | +| total_timesteps | 8973312 | +| train/ | | +| approx_kl | 2.3631938 | +| clip_fraction | 0.477 | +| clip_range | 0.2 | +| entropy_loss | -0.349 | +| explained_variance | -2.72 | +| learning_rate | 0.0001 | +| loss | -0.113 | +| n_updates | 148150 | +| policy_gradient_loss | -0.0716 | +| value_loss | 0.00065 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0307 | +| time/ | | +| fps | 309 | +| iterations | 8764 | +| time_elapsed | 28995 | +| total_timesteps | 8974336 | +| train/ | | +| approx_kl | 1.9725175 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.422 | +| explained_variance | -6.07 | +| learning_rate | 0.0001 | +| loss | -0.0867 | +| n_updates | 148160 | +| policy_gradient_loss | -0.0706 | +| value_loss | 0.000411 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0307 | +| time/ | | +| fps | 309 | +| iterations | 8765 | +| time_elapsed | 28998 | +| total_timesteps | 8975360 | +| train/ | | +| approx_kl | 1.9131407 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.439 | +| explained_variance | -1.21 | +| learning_rate | 0.0001 | +| loss | -0.0896 | +| n_updates | 148170 | +| policy_gradient_loss | -0.0644 | +| value_loss | 0.000395 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0331 | +| time/ | | +| fps | 309 | +| iterations | 8766 | +| time_elapsed | 29002 | +| total_timesteps | 8976384 | +| train/ | | +| approx_kl | 2.1725736 | +| clip_fraction | 0.522 | +| clip_range | 0.2 | +| entropy_loss | -0.442 | +| explained_variance | -0.622 | +| learning_rate | 0.0001 | +| loss | -0.0893 | +| n_updates | 148180 | +| policy_gradient_loss | -0.0664 | +| value_loss | 0.000555 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0283 | +| time/ | | +| fps | 309 | +| iterations | 8767 | +| time_elapsed | 29005 | +| total_timesteps | 8977408 | +| train/ | | +| approx_kl | 2.0864005 | +| clip_fraction | 0.473 | +| clip_range | 0.2 | +| entropy_loss | -0.387 | +| explained_variance | -3.54 | +| learning_rate | 0.0001 | +| loss | -0.0929 | +| n_updates | 148190 | +| policy_gradient_loss | -0.0664 | +| value_loss | 0.000368 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0303 | +| time/ | | +| fps | 309 | +| iterations | 8768 | +| time_elapsed | 29008 | +| total_timesteps | 8978432 | +| train/ | | +| approx_kl | 2.1410894 | +| clip_fraction | 0.445 | +| clip_range | 0.2 | +| entropy_loss | -0.378 | +| explained_variance | -0.764 | +| learning_rate | 0.0001 | +| loss | -0.0675 | +| n_updates | 148200 | +| policy_gradient_loss | -0.0546 | +| value_loss | 0.000675 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0303 | +| time/ | | +| fps | 309 | +| iterations | 8769 | +| time_elapsed | 29011 | +| total_timesteps | 8979456 | +| train/ | | +| approx_kl | 1.6593692 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.398 | +| explained_variance | -4.6 | +| learning_rate | 0.0001 | +| loss | -0.0932 | +| n_updates | 148210 | +| policy_gradient_loss | -0.0613 | +| value_loss | 0.00025 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0308 | +| time/ | | +| fps | 309 | +| iterations | 8770 | +| time_elapsed | 29014 | +| total_timesteps | 8980480 | +| train/ | | +| approx_kl | 1.9993566 | +| clip_fraction | 0.504 | +| clip_range | 0.2 | +| entropy_loss | -0.368 | +| explained_variance | -1.14 | +| learning_rate | 0.0001 | +| loss | -0.0738 | +| n_updates | 148220 | +| policy_gradient_loss | -0.066 | +| value_loss | 0.000545 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0306 | +| time/ | | +| fps | 309 | +| iterations | 8771 | +| time_elapsed | 29017 | +| total_timesteps | 8981504 | +| train/ | | +| approx_kl | 2.3016636 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.37 | +| explained_variance | -2.32 | +| learning_rate | 0.0001 | +| loss | -0.0952 | +| n_updates | 148230 | +| policy_gradient_loss | -0.0658 | +| value_loss | 0.000702 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0286 | +| time/ | | +| fps | 309 | +| iterations | 8772 | +| time_elapsed | 29021 | +| total_timesteps | 8982528 | +| train/ | | +| approx_kl | 2.235314 | +| clip_fraction | 0.465 | +| clip_range | 0.2 | +| entropy_loss | -0.38 | +| explained_variance | -2.24 | +| learning_rate | 0.0001 | +| loss | -0.0823 | +| n_updates | 148240 | +| policy_gradient_loss | -0.0684 | +| value_loss | 0.000338 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.028 | +| time/ | | +| fps | 309 | +| iterations | 8773 | +| time_elapsed | 29024 | +| total_timesteps | 8983552 | +| train/ | | +| approx_kl | 2.484965 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.39 | +| explained_variance | -1 | +| learning_rate | 0.0001 | +| loss | -0.0724 | +| n_updates | 148250 | +| policy_gradient_loss | -0.061 | +| value_loss | 0.000285 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0272 | +| time/ | | +| fps | 309 | +| iterations | 8774 | +| time_elapsed | 29028 | +| total_timesteps | 8984576 | +| train/ | | +| approx_kl | 2.0102649 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.413 | +| explained_variance | -0.863 | +| learning_rate | 0.0001 | +| loss | -0.0726 | +| n_updates | 148260 | +| policy_gradient_loss | -0.0596 | +| value_loss | 0.000254 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0229 | +| time/ | | +| fps | 309 | +| iterations | 8775 | +| time_elapsed | 29031 | +| total_timesteps | 8985600 | +| train/ | | +| approx_kl | 1.5411838 | +| clip_fraction | 0.432 | +| clip_range | 0.2 | +| entropy_loss | -0.36 | +| explained_variance | -0.786 | +| learning_rate | 0.0001 | +| loss | -0.0865 | +| n_updates | 148270 | +| policy_gradient_loss | -0.059 | +| value_loss | 0.000125 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0234 | +| time/ | | +| fps | 309 | +| iterations | 8776 | +| time_elapsed | 29034 | +| total_timesteps | 8986624 | +| train/ | | +| approx_kl | 1.8955784 | +| clip_fraction | 0.442 | +| clip_range | 0.2 | +| entropy_loss | -0.381 | +| explained_variance | -0.505 | +| learning_rate | 0.0001 | +| loss | -0.0483 | +| n_updates | 148280 | +| policy_gradient_loss | -0.0624 | +| value_loss | 0.000425 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0234 | +| time/ | | +| fps | 309 | +| iterations | 8777 | +| time_elapsed | 29038 | +| total_timesteps | 8987648 | +| train/ | | +| approx_kl | 1.6444559 | +| clip_fraction | 0.507 | +| clip_range | 0.2 | +| entropy_loss | -0.482 | +| explained_variance | -2.97 | +| learning_rate | 0.0001 | +| loss | -0.053 | +| n_updates | 148290 | +| policy_gradient_loss | -0.0624 | +| value_loss | 0.000428 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0253 | +| time/ | | +| fps | 309 | +| iterations | 8778 | +| time_elapsed | 29041 | +| total_timesteps | 8988672 | +| train/ | | +| approx_kl | 1.8192878 | +| clip_fraction | 0.509 | +| clip_range | 0.2 | +| entropy_loss | -0.453 | +| explained_variance | -1.82 | +| learning_rate | 0.0001 | +| loss | -0.116 | +| n_updates | 148300 | +| policy_gradient_loss | -0.0705 | +| value_loss | 0.000528 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0276 | +| time/ | | +| fps | 309 | +| iterations | 8779 | +| time_elapsed | 29045 | +| total_timesteps | 8989696 | +| train/ | | +| approx_kl | 1.6219059 | +| clip_fraction | 0.51 | +| clip_range | 0.2 | +| entropy_loss | -0.488 | +| explained_variance | -0.542 | +| learning_rate | 0.0001 | +| loss | -0.0912 | +| n_updates | 148310 | +| policy_gradient_loss | -0.0661 | +| value_loss | 0.000532 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0249 | +| time/ | | +| fps | 309 | +| iterations | 8780 | +| time_elapsed | 29048 | +| total_timesteps | 8990720 | +| train/ | | +| approx_kl | 1.5170757 | +| clip_fraction | 0.467 | +| clip_range | 0.2 | +| entropy_loss | -0.398 | +| explained_variance | -2.77 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 148320 | +| policy_gradient_loss | -0.0679 | +| value_loss | 0.000576 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0249 | +| time/ | | +| fps | 309 | +| iterations | 8781 | +| time_elapsed | 29051 | +| total_timesteps | 8991744 | +| train/ | | +| approx_kl | 2.2672775 | +| clip_fraction | 0.515 | +| clip_range | 0.2 | +| entropy_loss | -0.476 | +| explained_variance | -0.981 | +| learning_rate | 0.0001 | +| loss | -0.105 | +| n_updates | 148330 | +| policy_gradient_loss | -0.0743 | +| value_loss | 0.000343 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0263 | +| time/ | | +| fps | 309 | +| iterations | 8782 | +| time_elapsed | 29054 | +| total_timesteps | 8992768 | +| train/ | | +| approx_kl | 1.7781911 | +| clip_fraction | 0.498 | +| clip_range | 0.2 | +| entropy_loss | -0.415 | +| explained_variance | -1.2 | +| learning_rate | 0.0001 | +| loss | -0.098 | +| n_updates | 148340 | +| policy_gradient_loss | -0.0633 | +| value_loss | 0.000395 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0267 | +| time/ | | +| fps | 309 | +| iterations | 8783 | +| time_elapsed | 29057 | +| total_timesteps | 8993792 | +| train/ | | +| approx_kl | 1.5308179 | +| clip_fraction | 0.494 | +| clip_range | 0.2 | +| entropy_loss | -0.448 | +| explained_variance | -3.15 | +| learning_rate | 0.0001 | +| loss | -0.0893 | +| n_updates | 148350 | +| policy_gradient_loss | -0.0685 | +| value_loss | 0.000403 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0284 | +| time/ | | +| fps | 309 | +| iterations | 8784 | +| time_elapsed | 29061 | +| total_timesteps | 8994816 | +| train/ | | +| approx_kl | 1.7081006 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.388 | +| explained_variance | -1.69 | +| learning_rate | 0.0001 | +| loss | -0.0917 | +| n_updates | 148360 | +| policy_gradient_loss | -0.0751 | +| value_loss | 0.000688 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0261 | +| time/ | | +| fps | 309 | +| iterations | 8785 | +| time_elapsed | 29064 | +| total_timesteps | 8995840 | +| train/ | | +| approx_kl | 1.8282706 | +| clip_fraction | 0.468 | +| clip_range | 0.2 | +| entropy_loss | -0.362 | +| explained_variance | -5.01 | +| learning_rate | 0.0001 | +| loss | -0.0998 | +| n_updates | 148370 | +| policy_gradient_loss | -0.0693 | +| value_loss | 0.000577 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0261 | +| time/ | | +| fps | 309 | +| iterations | 8786 | +| time_elapsed | 29067 | +| total_timesteps | 8996864 | +| train/ | | +| approx_kl | 2.293792 | +| clip_fraction | 0.512 | +| clip_range | 0.2 | +| entropy_loss | -0.403 | +| explained_variance | -1.71 | +| learning_rate | 0.0001 | +| loss | -0.0977 | +| n_updates | 148380 | +| policy_gradient_loss | -0.0736 | +| value_loss | 0.000522 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0286 | +| time/ | | +| fps | 309 | +| iterations | 8787 | +| time_elapsed | 29070 | +| total_timesteps | 8997888 | +| train/ | | +| approx_kl | 2.1063519 | +| clip_fraction | 0.494 | +| clip_range | 0.2 | +| entropy_loss | -0.403 | +| explained_variance | -4.78 | +| learning_rate | 0.0001 | +| loss | -0.0863 | +| n_updates | 148390 | +| policy_gradient_loss | -0.0689 | +| value_loss | 0.000542 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0269 | +| time/ | | +| fps | 309 | +| iterations | 8788 | +| time_elapsed | 29073 | +| total_timesteps | 8998912 | +| train/ | | +| approx_kl | 2.5533223 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.397 | +| explained_variance | -2.98 | +| learning_rate | 0.0001 | +| loss | -0.0818 | +| n_updates | 148400 | +| policy_gradient_loss | -0.0677 | +| value_loss | 0.000442 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0277 | +| time/ | | +| fps | 309 | +| iterations | 8789 | +| time_elapsed | 29076 | +| total_timesteps | 8999936 | +| train/ | | +| approx_kl | 1.8320029 | +| clip_fraction | 0.472 | +| clip_range | 0.2 | +| entropy_loss | -0.418 | +| explained_variance | -0.687 | +| learning_rate | 0.0001 | +| loss | -0.0812 | +| n_updates | 148410 | +| policy_gradient_loss | -0.0599 | +| value_loss | 0.000449 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0257 | +| time/ | | +| fps | 309 | +| iterations | 8790 | +| time_elapsed | 29080 | +| total_timesteps | 9000960 | +| train/ | | +| approx_kl | 2.048541 | +| clip_fraction | 0.461 | +| clip_range | 0.2 | +| entropy_loss | -0.325 | +| explained_variance | -4.6 | +| learning_rate | 0.0001 | +| loss | -0.0849 | +| n_updates | 148420 | +| policy_gradient_loss | -0.0674 | +| value_loss | 0.000352 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0228 | +| time/ | | +| fps | 309 | +| iterations | 8791 | +| time_elapsed | 29083 | +| total_timesteps | 9001984 | +| train/ | | +| approx_kl | 2.1647375 | +| clip_fraction | 0.493 | +| clip_range | 0.2 | +| entropy_loss | -0.404 | +| explained_variance | -1.2 | +| learning_rate | 0.0001 | +| loss | -0.0987 | +| n_updates | 148430 | +| policy_gradient_loss | -0.0684 | +| value_loss | 0.00047 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.0219 | +| time/ | | +| fps | 309 | +| iterations | 8792 | +| time_elapsed | 29087 | +| total_timesteps | 9003008 | +| train/ | | +| approx_kl | 1.8747267 | +| clip_fraction | 0.452 | +| clip_range | 0.2 | +| entropy_loss | -0.347 | +| explained_variance | -2.94 | +| learning_rate | 0.0001 | +| loss | -0.0826 | +| n_updates | 148440 | +| policy_gradient_loss | -0.0711 | +| value_loss | 0.000692 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.0219 | +| time/ | | +| fps | 309 | +| iterations | 8793 | +| time_elapsed | 29090 | +| total_timesteps | 9004032 | +| train/ | | +| approx_kl | 1.6517463 | +| clip_fraction | 0.457 | +| clip_range | 0.2 | +| entropy_loss | -0.4 | +| explained_variance | -2.5 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 148450 | +| policy_gradient_loss | -0.0633 | +| value_loss | 0.000517 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0183 | +| time/ | | +| fps | 309 | +| iterations | 8794 | +| time_elapsed | 29093 | +| total_timesteps | 9005056 | +| train/ | | +| approx_kl | 2.0692723 | +| clip_fraction | 0.472 | +| clip_range | 0.2 | +| entropy_loss | -0.356 | +| explained_variance | -2.34 | +| learning_rate | 0.0001 | +| loss | -0.0797 | +| n_updates | 148460 | +| policy_gradient_loss | -0.0712 | +| value_loss | 0.00035 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.0178 | +| time/ | | +| fps | 309 | +| iterations | 8795 | +| time_elapsed | 29097 | +| total_timesteps | 9006080 | +| train/ | | +| approx_kl | 2.4918602 | +| clip_fraction | 0.509 | +| clip_range | 0.2 | +| entropy_loss | -0.419 | +| explained_variance | -1.78 | +| learning_rate | 0.0001 | +| loss | -0.0944 | +| n_updates | 148470 | +| policy_gradient_loss | -0.0717 | +| value_loss | 0.00036 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.0195 | +| time/ | | +| fps | 309 | +| iterations | 8796 | +| time_elapsed | 29100 | +| total_timesteps | 9007104 | +| train/ | | +| approx_kl | 2.1594837 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.383 | +| explained_variance | -1.21 | +| learning_rate | 0.0001 | +| loss | -0.0957 | +| n_updates | 148480 | +| policy_gradient_loss | -0.0621 | +| value_loss | 0.000755 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.0195 | +| time/ | | +| fps | 309 | +| iterations | 8797 | +| time_elapsed | 29104 | +| total_timesteps | 9008128 | +| train/ | | +| approx_kl | 2.5058618 | +| clip_fraction | 0.474 | +| clip_range | 0.2 | +| entropy_loss | -0.347 | +| explained_variance | -6.29 | +| learning_rate | 0.0001 | +| loss | -0.0717 | +| n_updates | 148490 | +| policy_gradient_loss | -0.0697 | +| value_loss | 0.000644 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.0214 | +| time/ | | +| fps | 309 | +| iterations | 8798 | +| time_elapsed | 29107 | +| total_timesteps | 9009152 | +| train/ | | +| approx_kl | 1.9775659 | +| clip_fraction | 0.469 | +| clip_range | 0.2 | +| entropy_loss | -0.428 | +| explained_variance | -1.9 | +| learning_rate | 0.0001 | +| loss | -0.0862 | +| n_updates | 148500 | +| policy_gradient_loss | -0.061 | +| value_loss | 0.000523 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.0214 | +| time/ | | +| fps | 309 | +| iterations | 8799 | +| time_elapsed | 29110 | +| total_timesteps | 9010176 | +| train/ | | +| approx_kl | 4.997961 | +| clip_fraction | 0.491 | +| clip_range | 0.2 | +| entropy_loss | -0.351 | +| explained_variance | -1.29 | +| learning_rate | 0.0001 | +| loss | -0.0962 | +| n_updates | 148510 | +| policy_gradient_loss | -0.0756 | +| value_loss | 0.000559 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0265 | +| time/ | | +| fps | 309 | +| iterations | 8800 | +| time_elapsed | 29113 | +| total_timesteps | 9011200 | +| train/ | | +| approx_kl | 1.7916753 | +| clip_fraction | 0.462 | +| clip_range | 0.2 | +| entropy_loss | -0.382 | +| explained_variance | -1.62 | +| learning_rate | 0.0001 | +| loss | -0.0865 | +| n_updates | 148520 | +| policy_gradient_loss | -0.07 | +| value_loss | 0.000543 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0241 | +| time/ | | +| fps | 309 | +| iterations | 8801 | +| time_elapsed | 29117 | +| total_timesteps | 9012224 | +| train/ | | +| approx_kl | 1.9133973 | +| clip_fraction | 0.489 | +| clip_range | 0.2 | +| entropy_loss | -0.394 | +| explained_variance | -2.4 | +| learning_rate | 0.0001 | +| loss | -0.0923 | +| n_updates | 148530 | +| policy_gradient_loss | -0.0628 | +| value_loss | 0.000317 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0241 | +| time/ | | +| fps | 309 | +| iterations | 8802 | +| time_elapsed | 29120 | +| total_timesteps | 9013248 | +| train/ | | +| approx_kl | 1.9659972 | +| clip_fraction | 0.446 | +| clip_range | 0.2 | +| entropy_loss | -0.361 | +| explained_variance | -0.747 | +| learning_rate | 0.0001 | +| loss | -0.0824 | +| n_updates | 148540 | +| policy_gradient_loss | -0.0581 | +| value_loss | 0.000438 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0226 | +| time/ | | +| fps | 309 | +| iterations | 8803 | +| time_elapsed | 29123 | +| total_timesteps | 9014272 | +| train/ | | +| approx_kl | 2.3079944 | +| clip_fraction | 0.496 | +| clip_range | 0.2 | +| entropy_loss | -0.395 | +| explained_variance | -1.73 | +| learning_rate | 0.0001 | +| loss | -0.0713 | +| n_updates | 148550 | +| policy_gradient_loss | -0.0693 | +| value_loss | 0.000505 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0217 | +| time/ | | +| fps | 309 | +| iterations | 8804 | +| time_elapsed | 29126 | +| total_timesteps | 9015296 | +| train/ | | +| approx_kl | 2.4127278 | +| clip_fraction | 0.423 | +| clip_range | 0.2 | +| entropy_loss | -0.298 | +| explained_variance | -0.813 | +| learning_rate | 0.0001 | +| loss | -0.0734 | +| n_updates | 148560 | +| policy_gradient_loss | -0.0586 | +| value_loss | 0.000619 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0244 | +| time/ | | +| fps | 309 | +| iterations | 8805 | +| time_elapsed | 29129 | +| total_timesteps | 9016320 | +| train/ | | +| approx_kl | 2.658578 | +| clip_fraction | 0.467 | +| clip_range | 0.2 | +| entropy_loss | -0.34 | +| explained_variance | -2.34 | +| learning_rate | 0.0001 | +| loss | -0.0833 | +| n_updates | 148570 | +| policy_gradient_loss | -0.063 | +| value_loss | 0.00037 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0244 | +| time/ | | +| fps | 309 | +| iterations | 8806 | +| time_elapsed | 29132 | +| total_timesteps | 9017344 | +| train/ | | +| approx_kl | 2.159036 | +| clip_fraction | 0.468 | +| clip_range | 0.2 | +| entropy_loss | -0.369 | +| explained_variance | -1.88 | +| learning_rate | 0.0001 | +| loss | -0.0913 | +| n_updates | 148580 | +| policy_gradient_loss | -0.069 | +| value_loss | 0.000525 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0259 | +| time/ | | +| fps | 309 | +| iterations | 8807 | +| time_elapsed | 29136 | +| total_timesteps | 9018368 | +| train/ | | +| approx_kl | 2.192046 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.334 | +| explained_variance | -2.07 | +| learning_rate | 0.0001 | +| loss | -0.0804 | +| n_updates | 148590 | +| policy_gradient_loss | -0.0633 | +| value_loss | 0.000361 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0259 | +| time/ | | +| fps | 309 | +| iterations | 8808 | +| time_elapsed | 29139 | +| total_timesteps | 9019392 | +| train/ | | +| approx_kl | 2.2326071 | +| clip_fraction | 0.494 | +| clip_range | 0.2 | +| entropy_loss | -0.395 | +| explained_variance | -1.54 | +| learning_rate | 0.0001 | +| loss | -0.0851 | +| n_updates | 148600 | +| policy_gradient_loss | -0.0639 | +| value_loss | 0.000454 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0269 | +| time/ | | +| fps | 309 | +| iterations | 8809 | +| time_elapsed | 29142 | +| total_timesteps | 9020416 | +| train/ | | +| approx_kl | 1.7924421 | +| clip_fraction | 0.431 | +| clip_range | 0.2 | +| entropy_loss | -0.337 | +| explained_variance | -1.87 | +| learning_rate | 0.0001 | +| loss | -0.0826 | +| n_updates | 148610 | +| policy_gradient_loss | -0.0565 | +| value_loss | 0.000432 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0224 | +| time/ | | +| fps | 309 | +| iterations | 8810 | +| time_elapsed | 29146 | +| total_timesteps | 9021440 | +| train/ | | +| approx_kl | 2.0279326 | +| clip_fraction | 0.426 | +| clip_range | 0.2 | +| entropy_loss | -0.291 | +| explained_variance | -1.77 | +| learning_rate | 0.0001 | +| loss | -0.0899 | +| n_updates | 148620 | +| policy_gradient_loss | -0.0616 | +| value_loss | 0.000496 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0224 | +| time/ | | +| fps | 309 | +| iterations | 8811 | +| time_elapsed | 29149 | +| total_timesteps | 9022464 | +| train/ | | +| approx_kl | 3.0501218 | +| clip_fraction | 0.451 | +| clip_range | 0.2 | +| entropy_loss | -0.327 | +| explained_variance | -1.76 | +| learning_rate | 0.0001 | +| loss | -0.0755 | +| n_updates | 148630 | +| policy_gradient_loss | -0.0714 | +| value_loss | 0.000646 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0233 | +| time/ | | +| fps | 309 | +| iterations | 8812 | +| time_elapsed | 29153 | +| total_timesteps | 9023488 | +| train/ | | +| approx_kl | 1.9605114 | +| clip_fraction | 0.492 | +| clip_range | 0.2 | +| entropy_loss | -0.405 | +| explained_variance | -0.831 | +| learning_rate | 0.0001 | +| loss | -0.0835 | +| n_updates | 148640 | +| policy_gradient_loss | -0.0709 | +| value_loss | 0.000694 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0251 | +| time/ | | +| fps | 309 | +| iterations | 8813 | +| time_elapsed | 29156 | +| total_timesteps | 9024512 | +| train/ | | +| approx_kl | 2.5101802 | +| clip_fraction | 0.458 | +| clip_range | 0.2 | +| entropy_loss | -0.344 | +| explained_variance | -2.67 | +| learning_rate | 0.0001 | +| loss | -0.0541 | +| n_updates | 148650 | +| policy_gradient_loss | -0.0698 | +| value_loss | 0.000571 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0225 | +| time/ | | +| fps | 309 | +| iterations | 8814 | +| time_elapsed | 29160 | +| total_timesteps | 9025536 | +| train/ | | +| approx_kl | 2.217414 | +| clip_fraction | 0.42 | +| clip_range | 0.2 | +| entropy_loss | -0.318 | +| explained_variance | -2.11 | +| learning_rate | 0.0001 | +| loss | -0.0841 | +| n_updates | 148660 | +| policy_gradient_loss | -0.0591 | +| value_loss | 0.000419 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0222 | +| time/ | | +| fps | 309 | +| iterations | 8815 | +| time_elapsed | 29163 | +| total_timesteps | 9026560 | +| train/ | | +| approx_kl | 1.9633448 | +| clip_fraction | 0.463 | +| clip_range | 0.2 | +| entropy_loss | -0.335 | +| explained_variance | -1.54 | +| learning_rate | 0.0001 | +| loss | -0.0808 | +| n_updates | 148670 | +| policy_gradient_loss | -0.0605 | +| value_loss | 0.000423 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0219 | +| time/ | | +| fps | 309 | +| iterations | 8816 | +| time_elapsed | 29167 | +| total_timesteps | 9027584 | +| train/ | | +| approx_kl | 1.8808198 | +| clip_fraction | 0.437 | +| clip_range | 0.2 | +| entropy_loss | -0.349 | +| explained_variance | -1.28 | +| learning_rate | 0.0001 | +| loss | -0.0727 | +| n_updates | 148680 | +| policy_gradient_loss | -0.0631 | +| value_loss | 0.000386 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.02 | +| time/ | | +| fps | 309 | +| iterations | 8817 | +| time_elapsed | 29170 | +| total_timesteps | 9028608 | +| train/ | | +| approx_kl | 1.9441248 | +| clip_fraction | 0.478 | +| clip_range | 0.2 | +| entropy_loss | -0.381 | +| explained_variance | -1.19 | +| learning_rate | 0.0001 | +| loss | -0.0813 | +| n_updates | 148690 | +| policy_gradient_loss | -0.0668 | +| value_loss | 0.000456 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0194 | +| time/ | | +| fps | 309 | +| iterations | 8818 | +| time_elapsed | 29173 | +| total_timesteps | 9029632 | +| train/ | | +| approx_kl | 2.0450358 | +| clip_fraction | 0.482 | +| clip_range | 0.2 | +| entropy_loss | -0.417 | +| explained_variance | -1.37 | +| learning_rate | 0.0001 | +| loss | -0.0647 | +| n_updates | 148700 | +| policy_gradient_loss | -0.0611 | +| value_loss | 0.000503 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0113 | +| time/ | | +| fps | 309 | +| iterations | 8819 | +| time_elapsed | 29176 | +| total_timesteps | 9030656 | +| train/ | | +| approx_kl | 1.7415986 | +| clip_fraction | 0.439 | +| clip_range | 0.2 | +| entropy_loss | -0.309 | +| explained_variance | -3.92 | +| learning_rate | 0.0001 | +| loss | -0.115 | +| n_updates | 148710 | +| policy_gradient_loss | -0.0632 | +| value_loss | 0.000529 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0113 | +| time/ | | +| fps | 309 | +| iterations | 8820 | +| time_elapsed | 29180 | +| total_timesteps | 9031680 | +| train/ | | +| approx_kl | 31.703768 | +| clip_fraction | 0.47 | +| clip_range | 0.2 | +| entropy_loss | -0.323 | +| explained_variance | -1.27 | +| learning_rate | 0.0001 | +| loss | -0.0982 | +| n_updates | 148720 | +| policy_gradient_loss | -0.0653 | +| value_loss | 0.000431 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0118 | +| time/ | | +| fps | 309 | +| iterations | 8821 | +| time_elapsed | 29183 | +| total_timesteps | 9032704 | +| train/ | | +| approx_kl | 2.7087548 | +| clip_fraction | 0.519 | +| clip_range | 0.2 | +| entropy_loss | -0.39 | +| explained_variance | -2.87 | +| learning_rate | 0.0001 | +| loss | -0.0832 | +| n_updates | 148730 | +| policy_gradient_loss | -0.0657 | +| value_loss | 0.000484 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0159 | +| time/ | | +| fps | 309 | +| iterations | 8822 | +| time_elapsed | 29186 | +| total_timesteps | 9033728 | +| train/ | | +| approx_kl | 2.1973891 | +| clip_fraction | 0.461 | +| clip_range | 0.2 | +| entropy_loss | -0.34 | +| explained_variance | -0.773 | +| learning_rate | 0.0001 | +| loss | -0.0915 | +| n_updates | 148740 | +| policy_gradient_loss | -0.0635 | +| value_loss | 0.000382 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0159 | +| time/ | | +| fps | 309 | +| iterations | 8823 | +| time_elapsed | 29189 | +| total_timesteps | 9034752 | +| train/ | | +| approx_kl | 1.7500331 | +| clip_fraction | 0.452 | +| clip_range | 0.2 | +| entropy_loss | -0.367 | +| explained_variance | -0.0184 | +| learning_rate | 0.0001 | +| loss | -0.0599 | +| n_updates | 148750 | +| policy_gradient_loss | -0.0574 | +| value_loss | 0.000603 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0139 | +| time/ | | +| fps | 309 | +| iterations | 8824 | +| time_elapsed | 29192 | +| total_timesteps | 9035776 | +| train/ | | +| approx_kl | 2.4719796 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.352 | +| explained_variance | -4.3 | +| learning_rate | 0.0001 | +| loss | -0.116 | +| n_updates | 148760 | +| policy_gradient_loss | -0.0675 | +| value_loss | 0.000615 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0139 | +| time/ | | +| fps | 309 | +| iterations | 8825 | +| time_elapsed | 29196 | +| total_timesteps | 9036800 | +| train/ | | +| approx_kl | 1.8733087 | +| clip_fraction | 0.409 | +| clip_range | 0.2 | +| entropy_loss | -0.304 | +| explained_variance | -0.421 | +| learning_rate | 0.0001 | +| loss | -0.0765 | +| n_updates | 148770 | +| policy_gradient_loss | -0.0477 | +| value_loss | 0.000638 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0139 | +| time/ | | +| fps | 309 | +| iterations | 8826 | +| time_elapsed | 29199 | +| total_timesteps | 9037824 | +| train/ | | +| approx_kl | 2.1538613 | +| clip_fraction | 0.445 | +| clip_range | 0.2 | +| entropy_loss | -0.324 | +| explained_variance | -0.713 | +| learning_rate | 0.0001 | +| loss | -0.0782 | +| n_updates | 148780 | +| policy_gradient_loss | -0.0643 | +| value_loss | 0.00053 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0157 | +| time/ | | +| fps | 309 | +| iterations | 8827 | +| time_elapsed | 29202 | +| total_timesteps | 9038848 | +| train/ | | +| approx_kl | 2.0399559 | +| clip_fraction | 0.513 | +| clip_range | 0.2 | +| entropy_loss | -0.421 | +| explained_variance | -1.97 | +| learning_rate | 0.0001 | +| loss | -0.105 | +| n_updates | 148790 | +| policy_gradient_loss | -0.0696 | +| value_loss | 0.000512 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0151 | +| time/ | | +| fps | 309 | +| iterations | 8828 | +| time_elapsed | 29206 | +| total_timesteps | 9039872 | +| train/ | | +| approx_kl | 1.8495119 | +| clip_fraction | 0.426 | +| clip_range | 0.2 | +| entropy_loss | -0.328 | +| explained_variance | -0.912 | +| learning_rate | 0.0001 | +| loss | -0.0849 | +| n_updates | 148800 | +| policy_gradient_loss | -0.0494 | +| value_loss | 0.000357 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0148 | +| time/ | | +| fps | 309 | +| iterations | 8829 | +| time_elapsed | 29209 | +| total_timesteps | 9040896 | +| train/ | | +| approx_kl | 1.8890127 | +| clip_fraction | 0.452 | +| clip_range | 0.2 | +| entropy_loss | -0.345 | +| explained_variance | 0.0256 | +| learning_rate | 0.0001 | +| loss | -0.0917 | +| n_updates | 148810 | +| policy_gradient_loss | -0.0658 | +| value_loss | 0.000329 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0148 | +| time/ | | +| fps | 309 | +| iterations | 8830 | +| time_elapsed | 29212 | +| total_timesteps | 9041920 | +| train/ | | +| approx_kl | 2.0176125 | +| clip_fraction | 0.434 | +| clip_range | 0.2 | +| entropy_loss | -0.304 | +| explained_variance | -0.331 | +| learning_rate | 0.0001 | +| loss | -0.0757 | +| n_updates | 148820 | +| policy_gradient_loss | -0.0657 | +| value_loss | 0.000414 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0149 | +| time/ | | +| fps | 309 | +| iterations | 8831 | +| time_elapsed | 29215 | +| total_timesteps | 9042944 | +| train/ | | +| approx_kl | 1.9583069 | +| clip_fraction | 0.478 | +| clip_range | 0.2 | +| entropy_loss | -0.374 | +| explained_variance | -1.07 | +| learning_rate | 0.0001 | +| loss | -0.107 | +| n_updates | 148830 | +| policy_gradient_loss | -0.0675 | +| value_loss | 0.000471 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0122 | +| time/ | | +| fps | 309 | +| iterations | 8832 | +| time_elapsed | 29219 | +| total_timesteps | 9043968 | +| train/ | | +| approx_kl | 2.3133144 | +| clip_fraction | 0.421 | +| clip_range | 0.2 | +| entropy_loss | -0.255 | +| explained_variance | -2.12 | +| learning_rate | 0.0001 | +| loss | -0.0921 | +| n_updates | 148840 | +| policy_gradient_loss | -0.0602 | +| value_loss | 0.000548 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0122 | +| time/ | | +| fps | 309 | +| iterations | 8833 | +| time_elapsed | 29222 | +| total_timesteps | 9044992 | +| train/ | | +| approx_kl | 2.6595592 | +| clip_fraction | 0.502 | +| clip_range | 0.2 | +| entropy_loss | -0.37 | +| explained_variance | -0.971 | +| learning_rate | 0.0001 | +| loss | -0.0919 | +| n_updates | 148850 | +| policy_gradient_loss | -0.0695 | +| value_loss | 0.000529 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0138 | +| time/ | | +| fps | 309 | +| iterations | 8834 | +| time_elapsed | 29226 | +| total_timesteps | 9046016 | +| train/ | | +| approx_kl | 1.8163823 | +| clip_fraction | 0.456 | +| clip_range | 0.2 | +| entropy_loss | -0.344 | +| explained_variance | -0.665 | +| learning_rate | 0.0001 | +| loss | -0.0765 | +| n_updates | 148860 | +| policy_gradient_loss | -0.0734 | +| value_loss | 0.000348 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0171 | +| time/ | | +| fps | 309 | +| iterations | 8835 | +| time_elapsed | 29229 | +| total_timesteps | 9047040 | +| train/ | | +| approx_kl | 1.9810005 | +| clip_fraction | 0.448 | +| clip_range | 0.2 | +| entropy_loss | -0.358 | +| explained_variance | -2.23 | +| learning_rate | 0.0001 | +| loss | -0.0846 | +| n_updates | 148870 | +| policy_gradient_loss | -0.0533 | +| value_loss | 0.00058 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0181 | +| time/ | | +| fps | 309 | +| iterations | 8836 | +| time_elapsed | 29232 | +| total_timesteps | 9048064 | +| train/ | | +| approx_kl | 1.9743446 | +| clip_fraction | 0.435 | +| clip_range | 0.2 | +| entropy_loss | -0.352 | +| explained_variance | -0.981 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 148880 | +| policy_gradient_loss | -0.0619 | +| value_loss | 0.00058 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0181 | +| time/ | | +| fps | 309 | +| iterations | 8837 | +| time_elapsed | 29235 | +| total_timesteps | 9049088 | +| train/ | | +| approx_kl | 1.6834764 | +| clip_fraction | 0.424 | +| clip_range | 0.2 | +| entropy_loss | -0.294 | +| explained_variance | -1.11 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 148890 | +| policy_gradient_loss | -0.046 | +| value_loss | 0.00043 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0226 | +| time/ | | +| fps | 309 | +| iterations | 8838 | +| time_elapsed | 29238 | +| total_timesteps | 9050112 | +| train/ | | +| approx_kl | 11.662822 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.328 | +| explained_variance | -2.66 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 148900 | +| policy_gradient_loss | -0.069 | +| value_loss | 0.000552 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0205 | +| time/ | | +| fps | 309 | +| iterations | 8839 | +| time_elapsed | 29242 | +| total_timesteps | 9051136 | +| train/ | | +| approx_kl | 2.2402854 | +| clip_fraction | 0.452 | +| clip_range | 0.2 | +| entropy_loss | -0.325 | +| explained_variance | -1.11 | +| learning_rate | 0.0001 | +| loss | -0.0952 | +| n_updates | 148910 | +| policy_gradient_loss | -0.0706 | +| value_loss | 0.000698 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0216 | +| time/ | | +| fps | 309 | +| iterations | 8840 | +| time_elapsed | 29245 | +| total_timesteps | 9052160 | +| train/ | | +| approx_kl | 2.2006674 | +| clip_fraction | 0.406 | +| clip_range | 0.2 | +| entropy_loss | -0.304 | +| explained_variance | -0.841 | +| learning_rate | 0.0001 | +| loss | -0.068 | +| n_updates | 148920 | +| policy_gradient_loss | -0.0606 | +| value_loss | 0.000543 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0193 | +| time/ | | +| fps | 309 | +| iterations | 8841 | +| time_elapsed | 29248 | +| total_timesteps | 9053184 | +| train/ | | +| approx_kl | 1.9356862 | +| clip_fraction | 0.401 | +| clip_range | 0.2 | +| entropy_loss | -0.296 | +| explained_variance | -0.31 | +| learning_rate | 0.0001 | +| loss | -0.0809 | +| n_updates | 148930 | +| policy_gradient_loss | -0.0653 | +| value_loss | 0.000481 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0202 | +| time/ | | +| fps | 309 | +| iterations | 8842 | +| time_elapsed | 29251 | +| total_timesteps | 9054208 | +| train/ | | +| approx_kl | 3.077672 | +| clip_fraction | 0.404 | +| clip_range | 0.2 | +| entropy_loss | -0.253 | +| explained_variance | -0.332 | +| learning_rate | 0.0001 | +| loss | -0.0755 | +| n_updates | 148940 | +| policy_gradient_loss | -0.0622 | +| value_loss | 0.000562 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0219 | +| time/ | | +| fps | 309 | +| iterations | 8843 | +| time_elapsed | 29254 | +| total_timesteps | 9055232 | +| train/ | | +| approx_kl | 1.6829549 | +| clip_fraction | 0.421 | +| clip_range | 0.2 | +| entropy_loss | -0.339 | +| explained_variance | 0.0782 | +| learning_rate | 0.0001 | +| loss | -0.0978 | +| n_updates | 148950 | +| policy_gradient_loss | -0.0635 | +| value_loss | 0.000379 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.021 | +| time/ | | +| fps | 309 | +| iterations | 8844 | +| time_elapsed | 29257 | +| total_timesteps | 9056256 | +| train/ | | +| approx_kl | 2.3922145 | +| clip_fraction | 0.422 | +| clip_range | 0.2 | +| entropy_loss | -0.308 | +| explained_variance | -0.0924 | +| learning_rate | 0.0001 | +| loss | -0.047 | +| n_updates | 148960 | +| policy_gradient_loss | -0.0608 | +| value_loss | 0.00078 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.021 | +| time/ | | +| fps | 309 | +| iterations | 8845 | +| time_elapsed | 29261 | +| total_timesteps | 9057280 | +| train/ | | +| approx_kl | 1.9398816 | +| clip_fraction | 0.381 | +| clip_range | 0.2 | +| entropy_loss | -0.266 | +| explained_variance | -0.657 | +| learning_rate | 0.0001 | +| loss | -0.0674 | +| n_updates | 148970 | +| policy_gradient_loss | -0.0502 | +| value_loss | 0.000811 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0201 | +| time/ | | +| fps | 309 | +| iterations | 8846 | +| time_elapsed | 29264 | +| total_timesteps | 9058304 | +| train/ | | +| approx_kl | 1.9931008 | +| clip_fraction | 0.478 | +| clip_range | 0.2 | +| entropy_loss | -0.357 | +| explained_variance | -2.43 | +| learning_rate | 0.0001 | +| loss | -0.0833 | +| n_updates | 148980 | +| policy_gradient_loss | -0.0653 | +| value_loss | 0.000588 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0187 | +| time/ | | +| fps | 309 | +| iterations | 8847 | +| time_elapsed | 29268 | +| total_timesteps | 9059328 | +| train/ | | +| approx_kl | 1.9177437 | +| clip_fraction | 0.427 | +| clip_range | 0.2 | +| entropy_loss | -0.359 | +| explained_variance | -0.482 | +| learning_rate | 0.0001 | +| loss | -0.0939 | +| n_updates | 148990 | +| policy_gradient_loss | -0.0648 | +| value_loss | 0.000537 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0187 | +| time/ | | +| fps | 309 | +| iterations | 8848 | +| time_elapsed | 29271 | +| total_timesteps | 9060352 | +| train/ | | +| approx_kl | 1.6505461 | +| clip_fraction | 0.435 | +| clip_range | 0.2 | +| entropy_loss | -0.323 | +| explained_variance | -0.998 | +| learning_rate | 0.0001 | +| loss | -0.0642 | +| n_updates | 149000 | +| policy_gradient_loss | -0.0547 | +| value_loss | 0.000411 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0166 | +| time/ | | +| fps | 309 | +| iterations | 8849 | +| time_elapsed | 29275 | +| total_timesteps | 9061376 | +| train/ | | +| approx_kl | 1.9970994 | +| clip_fraction | 0.449 | +| clip_range | 0.2 | +| entropy_loss | -0.368 | +| explained_variance | -2.91 | +| learning_rate | 0.0001 | +| loss | -0.0897 | +| n_updates | 149010 | +| policy_gradient_loss | -0.0753 | +| value_loss | 0.000269 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0148 | +| time/ | | +| fps | 309 | +| iterations | 8850 | +| time_elapsed | 29278 | +| total_timesteps | 9062400 | +| train/ | | +| approx_kl | 1.8372784 | +| clip_fraction | 0.425 | +| clip_range | 0.2 | +| entropy_loss | -0.334 | +| explained_variance | 0.0689 | +| learning_rate | 0.0001 | +| loss | -0.0903 | +| n_updates | 149020 | +| policy_gradient_loss | -0.0538 | +| value_loss | 0.000407 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0173 | +| time/ | | +| fps | 309 | +| iterations | 8851 | +| time_elapsed | 29282 | +| total_timesteps | 9063424 | +| train/ | | +| approx_kl | 1.6048424 | +| clip_fraction | 0.385 | +| clip_range | 0.2 | +| entropy_loss | -0.277 | +| explained_variance | 0.186 | +| learning_rate | 0.0001 | +| loss | -0.0503 | +| n_updates | 149030 | +| policy_gradient_loss | -0.0582 | +| value_loss | 0.000526 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0173 | +| time/ | | +| fps | 309 | +| iterations | 8852 | +| time_elapsed | 29285 | +| total_timesteps | 9064448 | +| train/ | | +| approx_kl | 2.0027294 | +| clip_fraction | 0.463 | +| clip_range | 0.2 | +| entropy_loss | -0.35 | +| explained_variance | -0.228 | +| learning_rate | 0.0001 | +| loss | -0.0756 | +| n_updates | 149040 | +| policy_gradient_loss | -0.0655 | +| value_loss | 0.00049 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0176 | +| time/ | | +| fps | 309 | +| iterations | 8853 | +| time_elapsed | 29289 | +| total_timesteps | 9065472 | +| train/ | | +| approx_kl | 2.6125638 | +| clip_fraction | 0.482 | +| clip_range | 0.2 | +| entropy_loss | -0.349 | +| explained_variance | -2.55 | +| learning_rate | 0.0001 | +| loss | -0.0891 | +| n_updates | 149050 | +| policy_gradient_loss | -0.0641 | +| value_loss | 0.000602 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0194 | +| time/ | | +| fps | 309 | +| iterations | 8854 | +| time_elapsed | 29292 | +| total_timesteps | 9066496 | +| train/ | | +| approx_kl | 2.228633 | +| clip_fraction | 0.437 | +| clip_range | 0.2 | +| entropy_loss | -0.298 | +| explained_variance | -0.753 | +| learning_rate | 0.0001 | +| loss | -0.0832 | +| n_updates | 149060 | +| policy_gradient_loss | -0.0568 | +| value_loss | 0.00054 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.018 | +| time/ | | +| fps | 309 | +| iterations | 8855 | +| time_elapsed | 29295 | +| total_timesteps | 9067520 | +| train/ | | +| approx_kl | 3.4373803 | +| clip_fraction | 0.415 | +| clip_range | 0.2 | +| entropy_loss | -0.29 | +| explained_variance | -1.21 | +| learning_rate | 0.0001 | +| loss | -0.0744 | +| n_updates | 149070 | +| policy_gradient_loss | -0.0579 | +| value_loss | 0.000539 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.0181 | +| time/ | | +| fps | 309 | +| iterations | 8856 | +| time_elapsed | 29298 | +| total_timesteps | 9068544 | +| train/ | | +| approx_kl | 2.1352818 | +| clip_fraction | 0.453 | +| clip_range | 0.2 | +| entropy_loss | -0.339 | +| explained_variance | -0.669 | +| learning_rate | 0.0001 | +| loss | -0.0716 | +| n_updates | 149080 | +| policy_gradient_loss | -0.0645 | +| value_loss | 0.000516 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0198 | +| time/ | | +| fps | 309 | +| iterations | 8857 | +| time_elapsed | 29301 | +| total_timesteps | 9069568 | +| train/ | | +| approx_kl | 1.686872 | +| clip_fraction | 0.417 | +| clip_range | 0.2 | +| entropy_loss | -0.315 | +| explained_variance | -0.749 | +| learning_rate | 0.0001 | +| loss | -0.0877 | +| n_updates | 149090 | +| policy_gradient_loss | -0.0543 | +| value_loss | 0.000327 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0238 | +| time/ | | +| fps | 309 | +| iterations | 8858 | +| time_elapsed | 29304 | +| total_timesteps | 9070592 | +| train/ | | +| approx_kl | 1.6666121 | +| clip_fraction | 0.435 | +| clip_range | 0.2 | +| entropy_loss | -0.327 | +| explained_variance | -0.313 | +| learning_rate | 0.0001 | +| loss | -0.0804 | +| n_updates | 149100 | +| policy_gradient_loss | -0.0636 | +| value_loss | 0.000266 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0238 | +| time/ | | +| fps | 309 | +| iterations | 8859 | +| time_elapsed | 29307 | +| total_timesteps | 9071616 | +| train/ | | +| approx_kl | 2.1807594 | +| clip_fraction | 0.441 | +| clip_range | 0.2 | +| entropy_loss | -0.311 | +| explained_variance | -0.925 | +| learning_rate | 0.0001 | +| loss | -0.0774 | +| n_updates | 149110 | +| policy_gradient_loss | -0.0587 | +| value_loss | 0.00038 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0224 | +| time/ | | +| fps | 309 | +| iterations | 8860 | +| time_elapsed | 29311 | +| total_timesteps | 9072640 | +| train/ | | +| approx_kl | 3.0840292 | +| clip_fraction | 0.434 | +| clip_range | 0.2 | +| entropy_loss | -0.328 | +| explained_variance | -0.36 | +| learning_rate | 0.0001 | +| loss | -0.0838 | +| n_updates | 149120 | +| policy_gradient_loss | -0.0627 | +| value_loss | 0.000588 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0224 | +| time/ | | +| fps | 309 | +| iterations | 8861 | +| time_elapsed | 29314 | +| total_timesteps | 9073664 | +| train/ | | +| approx_kl | 1.2491893 | +| clip_fraction | 0.386 | +| clip_range | 0.2 | +| entropy_loss | -0.333 | +| explained_variance | 0.266 | +| learning_rate | 0.0001 | +| loss | -0.0233 | +| n_updates | 149130 | +| policy_gradient_loss | -0.0448 | +| value_loss | 0.000282 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0224 | +| time/ | | +| fps | 309 | +| iterations | 8862 | +| time_elapsed | 29317 | +| total_timesteps | 9074688 | +| train/ | | +| approx_kl | 1.7449988 | +| clip_fraction | 0.436 | +| clip_range | 0.2 | +| entropy_loss | -0.362 | +| explained_variance | -1.48 | +| learning_rate | 0.0001 | +| loss | -0.0826 | +| n_updates | 149140 | +| policy_gradient_loss | -0.0556 | +| value_loss | 0.000398 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0259 | +| time/ | | +| fps | 309 | +| iterations | 8863 | +| time_elapsed | 29320 | +| total_timesteps | 9075712 | +| train/ | | +| approx_kl | 1.4848721 | +| clip_fraction | 0.448 | +| clip_range | 0.2 | +| entropy_loss | -0.381 | +| explained_variance | -0.689 | +| learning_rate | 0.0001 | +| loss | -0.0799 | +| n_updates | 149150 | +| policy_gradient_loss | -0.0659 | +| value_loss | 0.00017 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0275 | +| time/ | | +| fps | 309 | +| iterations | 8864 | +| time_elapsed | 29324 | +| total_timesteps | 9076736 | +| train/ | | +| approx_kl | 2.0080707 | +| clip_fraction | 0.466 | +| clip_range | 0.2 | +| entropy_loss | -0.378 | +| explained_variance | -0.537 | +| learning_rate | 0.0001 | +| loss | -0.0756 | +| n_updates | 149160 | +| policy_gradient_loss | -0.0603 | +| value_loss | 0.000372 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0276 | +| time/ | | +| fps | 309 | +| iterations | 8865 | +| time_elapsed | 29327 | +| total_timesteps | 9077760 | +| train/ | | +| approx_kl | 2.1116252 | +| clip_fraction | 0.448 | +| clip_range | 0.2 | +| entropy_loss | -0.338 | +| explained_variance | -0.622 | +| learning_rate | 0.0001 | +| loss | -0.0859 | +| n_updates | 149170 | +| policy_gradient_loss | -0.0654 | +| value_loss | 0.000436 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0313 | +| time/ | | +| fps | 309 | +| iterations | 8866 | +| time_elapsed | 29330 | +| total_timesteps | 9078784 | +| train/ | | +| approx_kl | 1.5865662 | +| clip_fraction | 0.451 | +| clip_range | 0.2 | +| entropy_loss | -0.395 | +| explained_variance | 0.247 | +| learning_rate | 0.0001 | +| loss | -0.0764 | +| n_updates | 149180 | +| policy_gradient_loss | -0.0692 | +| value_loss | 0.000251 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0313 | +| time/ | | +| fps | 309 | +| iterations | 8867 | +| time_elapsed | 29334 | +| total_timesteps | 9079808 | +| train/ | | +| approx_kl | 1.826728 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.379 | +| explained_variance | -0.347 | +| learning_rate | 0.0001 | +| loss | -0.0798 | +| n_updates | 149190 | +| policy_gradient_loss | -0.062 | +| value_loss | 0.000314 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0327 | +| time/ | | +| fps | 309 | +| iterations | 8868 | +| time_elapsed | 29337 | +| total_timesteps | 9080832 | +| train/ | | +| approx_kl | 2.0046508 | +| clip_fraction | 0.449 | +| clip_range | 0.2 | +| entropy_loss | -0.356 | +| explained_variance | -1.91 | +| learning_rate | 0.0001 | +| loss | -0.0501 | +| n_updates | 149200 | +| policy_gradient_loss | -0.0615 | +| value_loss | 0.000511 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0327 | +| time/ | | +| fps | 309 | +| iterations | 8869 | +| time_elapsed | 29340 | +| total_timesteps | 9081856 | +| train/ | | +| approx_kl | 2.3271523 | +| clip_fraction | 0.413 | +| clip_range | 0.2 | +| entropy_loss | -0.279 | +| explained_variance | 0.166 | +| learning_rate | 0.0001 | +| loss | -0.0587 | +| n_updates | 149210 | +| policy_gradient_loss | -0.0558 | +| value_loss | 0.000578 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0346 | +| time/ | | +| fps | 309 | +| iterations | 8870 | +| time_elapsed | 29343 | +| total_timesteps | 9082880 | +| train/ | | +| approx_kl | 2.0367298 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.376 | +| explained_variance | -2.63 | +| learning_rate | 0.0001 | +| loss | -0.0944 | +| n_updates | 149220 | +| policy_gradient_loss | -0.0701 | +| value_loss | 0.000405 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0346 | +| time/ | | +| fps | 309 | +| iterations | 8871 | +| time_elapsed | 29347 | +| total_timesteps | 9083904 | +| train/ | | +| approx_kl | 1.7919235 | +| clip_fraction | 0.417 | +| clip_range | 0.2 | +| entropy_loss | -0.303 | +| explained_variance | -0.47 | +| learning_rate | 0.0001 | +| loss | -0.0881 | +| n_updates | 149230 | +| policy_gradient_loss | -0.0538 | +| value_loss | 0.000503 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0392 | +| time/ | | +| fps | 309 | +| iterations | 8872 | +| time_elapsed | 29350 | +| total_timesteps | 9084928 | +| train/ | | +| approx_kl | 1.6886946 | +| clip_fraction | 0.453 | +| clip_range | 0.2 | +| entropy_loss | -0.397 | +| explained_variance | -2.75 | +| learning_rate | 0.0001 | +| loss | -0.112 | +| n_updates | 149240 | +| policy_gradient_loss | -0.066 | +| value_loss | 0.000342 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0403 | +| time/ | | +| fps | 309 | +| iterations | 8873 | +| time_elapsed | 29353 | +| total_timesteps | 9085952 | +| train/ | | +| approx_kl | 1.9357452 | +| clip_fraction | 0.435 | +| clip_range | 0.2 | +| entropy_loss | -0.32 | +| explained_variance | -0.137 | +| learning_rate | 0.0001 | +| loss | -0.0513 | +| n_updates | 149250 | +| policy_gradient_loss | -0.0565 | +| value_loss | 0.000314 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0403 | +| time/ | | +| fps | 309 | +| iterations | 8874 | +| time_elapsed | 29356 | +| total_timesteps | 9086976 | +| train/ | | +| approx_kl | 1.530446 | +| clip_fraction | 0.386 | +| clip_range | 0.2 | +| entropy_loss | -0.318 | +| explained_variance | -0.409 | +| learning_rate | 0.0001 | +| loss | -0.0613 | +| n_updates | 149260 | +| policy_gradient_loss | -0.058 | +| value_loss | 0.000438 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0408 | +| time/ | | +| fps | 309 | +| iterations | 8875 | +| time_elapsed | 29359 | +| total_timesteps | 9088000 | +| train/ | | +| approx_kl | 1.8646094 | +| clip_fraction | 0.41 | +| clip_range | 0.2 | +| entropy_loss | -0.343 | +| explained_variance | -1.99 | +| learning_rate | 0.0001 | +| loss | -0.0785 | +| n_updates | 149270 | +| policy_gradient_loss | -0.0583 | +| value_loss | 0.000375 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0459 | +| time/ | | +| fps | 309 | +| iterations | 8876 | +| time_elapsed | 29362 | +| total_timesteps | 9089024 | +| train/ | | +| approx_kl | 2.0204418 | +| clip_fraction | 0.461 | +| clip_range | 0.2 | +| entropy_loss | -0.387 | +| explained_variance | -0.311 | +| learning_rate | 0.0001 | +| loss | -0.0902 | +| n_updates | 149280 | +| policy_gradient_loss | -0.0612 | +| value_loss | 0.000464 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0459 | +| time/ | | +| fps | 309 | +| iterations | 8877 | +| time_elapsed | 29366 | +| total_timesteps | 9090048 | +| train/ | | +| approx_kl | 1.3527098 | +| clip_fraction | 0.361 | +| clip_range | 0.2 | +| entropy_loss | -0.292 | +| explained_variance | 0.183 | +| learning_rate | 0.0001 | +| loss | -0.0595 | +| n_updates | 149290 | +| policy_gradient_loss | -0.0501 | +| value_loss | 0.000382 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.045 | +| time/ | | +| fps | 309 | +| iterations | 8878 | +| time_elapsed | 29369 | +| total_timesteps | 9091072 | +| train/ | | +| approx_kl | 2.390707 | +| clip_fraction | 0.453 | +| clip_range | 0.2 | +| entropy_loss | -0.361 | +| explained_variance | -0.918 | +| learning_rate | 0.0001 | +| loss | -0.0951 | +| n_updates | 149300 | +| policy_gradient_loss | -0.064 | +| value_loss | 0.000486 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0463 | +| time/ | | +| fps | 309 | +| iterations | 8879 | +| time_elapsed | 29372 | +| total_timesteps | 9092096 | +| train/ | | +| approx_kl | 1.4364114 | +| clip_fraction | 0.367 | +| clip_range | 0.2 | +| entropy_loss | -0.312 | +| explained_variance | 0.0717 | +| learning_rate | 0.0001 | +| loss | -0.0759 | +| n_updates | 149310 | +| policy_gradient_loss | -0.0475 | +| value_loss | 0.000515 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0512 | +| time/ | | +| fps | 309 | +| iterations | 8880 | +| time_elapsed | 29375 | +| total_timesteps | 9093120 | +| train/ | | +| approx_kl | 1.8945785 | +| clip_fraction | 0.434 | +| clip_range | 0.2 | +| entropy_loss | -0.357 | +| explained_variance | -1.08 | +| learning_rate | 0.0001 | +| loss | -0.0539 | +| n_updates | 149320 | +| policy_gradient_loss | -0.0602 | +| value_loss | 0.000501 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0512 | +| time/ | | +| fps | 309 | +| iterations | 8881 | +| time_elapsed | 29378 | +| total_timesteps | 9094144 | +| train/ | | +| approx_kl | 2.2544389 | +| clip_fraction | 0.452 | +| clip_range | 0.2 | +| entropy_loss | -0.342 | +| explained_variance | -1.07 | +| learning_rate | 0.0001 | +| loss | -0.0788 | +| n_updates | 149330 | +| policy_gradient_loss | -0.055 | +| value_loss | 0.000566 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0528 | +| time/ | | +| fps | 309 | +| iterations | 8882 | +| time_elapsed | 29382 | +| total_timesteps | 9095168 | +| train/ | | +| approx_kl | 2.1083164 | +| clip_fraction | 0.499 | +| clip_range | 0.2 | +| entropy_loss | -0.371 | +| explained_variance | -1.34 | +| learning_rate | 0.0001 | +| loss | -0.0752 | +| n_updates | 149340 | +| policy_gradient_loss | -0.0723 | +| value_loss | 0.000452 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0601 | +| time/ | | +| fps | 309 | +| iterations | 8883 | +| time_elapsed | 29385 | +| total_timesteps | 9096192 | +| train/ | | +| approx_kl | 2.6789894 | +| clip_fraction | 0.477 | +| clip_range | 0.2 | +| entropy_loss | -0.399 | +| explained_variance | -1.36 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 149350 | +| policy_gradient_loss | -0.0647 | +| value_loss | 0.00061 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0601 | +| time/ | | +| fps | 309 | +| iterations | 8884 | +| time_elapsed | 29389 | +| total_timesteps | 9097216 | +| train/ | | +| approx_kl | 1.8710093 | +| clip_fraction | 0.445 | +| clip_range | 0.2 | +| entropy_loss | -0.352 | +| explained_variance | -0.46 | +| learning_rate | 0.0001 | +| loss | -0.0803 | +| n_updates | 149360 | +| policy_gradient_loss | -0.0585 | +| value_loss | 0.00063 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0622 | +| time/ | | +| fps | 309 | +| iterations | 8885 | +| time_elapsed | 29392 | +| total_timesteps | 9098240 | +| train/ | | +| approx_kl | 2.3322067 | +| clip_fraction | 0.479 | +| clip_range | 0.2 | +| entropy_loss | -0.331 | +| explained_variance | -1.57 | +| learning_rate | 0.0001 | +| loss | -0.0917 | +| n_updates | 149370 | +| policy_gradient_loss | -0.0706 | +| value_loss | 0.000528 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0611 | +| time/ | | +| fps | 309 | +| iterations | 8886 | +| time_elapsed | 29395 | +| total_timesteps | 9099264 | +| train/ | | +| approx_kl | 1.522547 | +| clip_fraction | 0.419 | +| clip_range | 0.2 | +| entropy_loss | -0.332 | +| explained_variance | -2.34 | +| learning_rate | 0.0001 | +| loss | -0.0575 | +| n_updates | 149380 | +| policy_gradient_loss | -0.0486 | +| value_loss | 0.000395 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0609 | +| time/ | | +| fps | 309 | +| iterations | 8887 | +| time_elapsed | 29399 | +| total_timesteps | 9100288 | +| train/ | | +| approx_kl | 6.548788 | +| clip_fraction | 0.381 | +| clip_range | 0.2 | +| entropy_loss | -0.278 | +| explained_variance | -1.15 | +| learning_rate | 0.0001 | +| loss | -0.0606 | +| n_updates | 149390 | +| policy_gradient_loss | -0.0541 | +| value_loss | 0.000472 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0619 | +| time/ | | +| fps | 309 | +| iterations | 8888 | +| time_elapsed | 29402 | +| total_timesteps | 9101312 | +| train/ | | +| approx_kl | 1.5890146 | +| clip_fraction | 0.405 | +| clip_range | 0.2 | +| entropy_loss | -0.323 | +| explained_variance | 0.0508 | +| learning_rate | 0.0001 | +| loss | -0.0666 | +| n_updates | 149400 | +| policy_gradient_loss | -0.0538 | +| value_loss | 0.000626 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0619 | +| time/ | | +| fps | 309 | +| iterations | 8889 | +| time_elapsed | 29406 | +| total_timesteps | 9102336 | +| train/ | | +| approx_kl | 2.503018 | +| clip_fraction | 0.42 | +| clip_range | 0.2 | +| entropy_loss | -0.293 | +| explained_variance | -0.289 | +| learning_rate | 0.0001 | +| loss | -0.0974 | +| n_updates | 149410 | +| policy_gradient_loss | -0.0639 | +| value_loss | 0.000366 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0656 | +| time/ | | +| fps | 309 | +| iterations | 8890 | +| time_elapsed | 29409 | +| total_timesteps | 9103360 | +| train/ | | +| approx_kl | 3.5006466 | +| clip_fraction | 0.484 | +| clip_range | 0.2 | +| entropy_loss | -0.372 | +| explained_variance | -1.19 | +| learning_rate | 0.0001 | +| loss | -0.0779 | +| n_updates | 149420 | +| policy_gradient_loss | -0.0614 | +| value_loss | 0.000658 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.067 | +| time/ | | +| fps | 309 | +| iterations | 8891 | +| time_elapsed | 29412 | +| total_timesteps | 9104384 | +| train/ | | +| approx_kl | 2.2416406 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.388 | +| explained_variance | -3.35 | +| learning_rate | 0.0001 | +| loss | -0.0999 | +| n_updates | 149430 | +| policy_gradient_loss | -0.0648 | +| value_loss | 0.000273 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.067 | +| time/ | | +| fps | 309 | +| iterations | 8892 | +| time_elapsed | 29416 | +| total_timesteps | 9105408 | +| train/ | | +| approx_kl | 2.0348406 | +| clip_fraction | 0.491 | +| clip_range | 0.2 | +| entropy_loss | -0.385 | +| explained_variance | -1.76 | +| learning_rate | 0.0001 | +| loss | -0.109 | +| n_updates | 149440 | +| policy_gradient_loss | -0.0688 | +| value_loss | 0.000256 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0617 | +| time/ | | +| fps | 309 | +| iterations | 8893 | +| time_elapsed | 29419 | +| total_timesteps | 9106432 | +| train/ | | +| approx_kl | 2.1786866 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.367 | +| explained_variance | -3.57 | +| learning_rate | 0.0001 | +| loss | -0.0737 | +| n_updates | 149450 | +| policy_gradient_loss | -0.0673 | +| value_loss | 0.000601 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0617 | +| time/ | | +| fps | 309 | +| iterations | 8894 | +| time_elapsed | 29422 | +| total_timesteps | 9107456 | +| train/ | | +| approx_kl | 6.766693 | +| clip_fraction | 0.453 | +| clip_range | 0.2 | +| entropy_loss | -0.379 | +| explained_variance | -0.811 | +| learning_rate | 0.0001 | +| loss | -0.0616 | +| n_updates | 149460 | +| policy_gradient_loss | -0.0602 | +| value_loss | 0.000691 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0675 | +| time/ | | +| fps | 309 | +| iterations | 8895 | +| time_elapsed | 29425 | +| total_timesteps | 9108480 | +| train/ | | +| approx_kl | 2.011229 | +| clip_fraction | 0.461 | +| clip_range | 0.2 | +| entropy_loss | -0.372 | +| explained_variance | -1.5 | +| learning_rate | 0.0001 | +| loss | -0.0828 | +| n_updates | 149470 | +| policy_gradient_loss | -0.0537 | +| value_loss | 0.000489 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0652 | +| time/ | | +| fps | 309 | +| iterations | 8896 | +| time_elapsed | 29428 | +| total_timesteps | 9109504 | +| train/ | | +| approx_kl | 2.916348 | +| clip_fraction | 0.465 | +| clip_range | 0.2 | +| entropy_loss | -0.339 | +| explained_variance | -2.2 | +| learning_rate | 0.0001 | +| loss | -0.0797 | +| n_updates | 149480 | +| policy_gradient_loss | -0.068 | +| value_loss | 0.000454 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0652 | +| time/ | | +| fps | 309 | +| iterations | 8897 | +| time_elapsed | 29432 | +| total_timesteps | 9110528 | +| train/ | | +| approx_kl | 1.6814592 | +| clip_fraction | 0.473 | +| clip_range | 0.2 | +| entropy_loss | -0.417 | +| explained_variance | -3.11 | +| learning_rate | 0.0001 | +| loss | -0.0925 | +| n_updates | 149490 | +| policy_gradient_loss | -0.0627 | +| value_loss | 0.000296 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0698 | +| time/ | | +| fps | 309 | +| iterations | 8898 | +| time_elapsed | 29435 | +| total_timesteps | 9111552 | +| train/ | | +| approx_kl | 2.2298105 | +| clip_fraction | 0.485 | +| clip_range | 0.2 | +| entropy_loss | -0.357 | +| explained_variance | -1.17 | +| learning_rate | 0.0001 | +| loss | -0.0743 | +| n_updates | 149500 | +| policy_gradient_loss | -0.0652 | +| value_loss | 0.000402 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0701 | +| time/ | | +| fps | 309 | +| iterations | 8899 | +| time_elapsed | 29438 | +| total_timesteps | 9112576 | +| train/ | | +| approx_kl | 1.6726396 | +| clip_fraction | 0.461 | +| clip_range | 0.2 | +| entropy_loss | -0.39 | +| explained_variance | -1.77 | +| learning_rate | 0.0001 | +| loss | -0.0654 | +| n_updates | 149510 | +| policy_gradient_loss | -0.0659 | +| value_loss | 0.000541 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0701 | +| time/ | | +| fps | 309 | +| iterations | 8900 | +| time_elapsed | 29441 | +| total_timesteps | 9113600 | +| train/ | | +| approx_kl | 1.6472889 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.406 | +| explained_variance | -3.51 | +| learning_rate | 0.0001 | +| loss | -0.0851 | +| n_updates | 149520 | +| policy_gradient_loss | -0.0658 | +| value_loss | 0.000544 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0724 | +| time/ | | +| fps | 309 | +| iterations | 8901 | +| time_elapsed | 29445 | +| total_timesteps | 9114624 | +| train/ | | +| approx_kl | 3.9596665 | +| clip_fraction | 0.435 | +| clip_range | 0.2 | +| entropy_loss | -0.326 | +| explained_variance | -2.18 | +| learning_rate | 0.0001 | +| loss | -0.0641 | +| n_updates | 149530 | +| policy_gradient_loss | -0.0562 | +| value_loss | 0.000508 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0702 | +| time/ | | +| fps | 309 | +| iterations | 8902 | +| time_elapsed | 29448 | +| total_timesteps | 9115648 | +| train/ | | +| approx_kl | 2.3284965 | +| clip_fraction | 0.452 | +| clip_range | 0.2 | +| entropy_loss | -0.327 | +| explained_variance | -0.93 | +| learning_rate | 0.0001 | +| loss | -0.0905 | +| n_updates | 149540 | +| policy_gradient_loss | -0.0608 | +| value_loss | 0.000652 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0702 | +| time/ | | +| fps | 309 | +| iterations | 8903 | +| time_elapsed | 29452 | +| total_timesteps | 9116672 | +| train/ | | +| approx_kl | 1.7448535 | +| clip_fraction | 0.415 | +| clip_range | 0.2 | +| entropy_loss | -0.342 | +| explained_variance | -2.67 | +| learning_rate | 0.0001 | +| loss | -0.0946 | +| n_updates | 149550 | +| policy_gradient_loss | -0.0584 | +| value_loss | 0.000352 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0721 | +| time/ | | +| fps | 309 | +| iterations | 8904 | +| time_elapsed | 29455 | +| total_timesteps | 9117696 | +| train/ | | +| approx_kl | 2.2681794 | +| clip_fraction | 0.518 | +| clip_range | 0.2 | +| entropy_loss | -0.381 | +| explained_variance | -1.57 | +| learning_rate | 0.0001 | +| loss | -0.0724 | +| n_updates | 149560 | +| policy_gradient_loss | -0.0718 | +| value_loss | 0.000598 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0721 | +| time/ | | +| fps | 309 | +| iterations | 8905 | +| time_elapsed | 29459 | +| total_timesteps | 9118720 | +| train/ | | +| approx_kl | 1.7014391 | +| clip_fraction | 0.429 | +| clip_range | 0.2 | +| entropy_loss | -0.32 | +| explained_variance | -3 | +| learning_rate | 0.0001 | +| loss | -0.0773 | +| n_updates | 149570 | +| policy_gradient_loss | -0.0589 | +| value_loss | 0.00056 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0742 | +| time/ | | +| fps | 309 | +| iterations | 8906 | +| time_elapsed | 29462 | +| total_timesteps | 9119744 | +| train/ | | +| approx_kl | 2.7884288 | +| clip_fraction | 0.462 | +| clip_range | 0.2 | +| entropy_loss | -0.349 | +| explained_variance | -1.26 | +| learning_rate | 0.0001 | +| loss | -0.0519 | +| n_updates | 149580 | +| policy_gradient_loss | -0.0545 | +| value_loss | 0.000536 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0721 | +| time/ | | +| fps | 309 | +| iterations | 8907 | +| time_elapsed | 29466 | +| total_timesteps | 9120768 | +| train/ | | +| approx_kl | 2.9479828 | +| clip_fraction | 0.499 | +| clip_range | 0.2 | +| entropy_loss | -0.412 | +| explained_variance | -1.93 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 149590 | +| policy_gradient_loss | -0.0665 | +| value_loss | 0.000405 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0721 | +| time/ | | +| fps | 309 | +| iterations | 8908 | +| time_elapsed | 29469 | +| total_timesteps | 9121792 | +| train/ | | +| approx_kl | 2.196478 | +| clip_fraction | 0.498 | +| clip_range | 0.2 | +| entropy_loss | -0.381 | +| explained_variance | -1.75 | +| learning_rate | 0.0001 | +| loss | -0.0799 | +| n_updates | 149600 | +| policy_gradient_loss | -0.0652 | +| value_loss | 0.000302 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0704 | +| time/ | | +| fps | 309 | +| iterations | 8909 | +| time_elapsed | 29472 | +| total_timesteps | 9122816 | +| train/ | | +| approx_kl | 2.4147544 | +| clip_fraction | 0.492 | +| clip_range | 0.2 | +| entropy_loss | -0.391 | +| explained_variance | -2.02 | +| learning_rate | 0.0001 | +| loss | -0.0639 | +| n_updates | 149610 | +| policy_gradient_loss | -0.0634 | +| value_loss | 0.000355 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0704 | +| time/ | | +| fps | 309 | +| iterations | 8910 | +| time_elapsed | 29475 | +| total_timesteps | 9123840 | +| train/ | | +| approx_kl | 1.3475918 | +| clip_fraction | 0.4 | +| clip_range | 0.2 | +| entropy_loss | -0.341 | +| explained_variance | -2.12 | +| learning_rate | 0.0001 | +| loss | -0.0821 | +| n_updates | 149620 | +| policy_gradient_loss | -0.0621 | +| value_loss | 0.000342 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0693 | +| time/ | | +| fps | 309 | +| iterations | 8911 | +| time_elapsed | 29479 | +| total_timesteps | 9124864 | +| train/ | | +| approx_kl | 1.8044562 | +| clip_fraction | 0.52 | +| clip_range | 0.2 | +| entropy_loss | -0.483 | +| explained_variance | -0.959 | +| learning_rate | 0.0001 | +| loss | -0.0798 | +| n_updates | 149630 | +| policy_gradient_loss | -0.0635 | +| value_loss | 0.000223 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0693 | +| time/ | | +| fps | 309 | +| iterations | 8912 | +| time_elapsed | 29482 | +| total_timesteps | 9125888 | +| train/ | | +| approx_kl | 2.5610578 | +| clip_fraction | 0.467 | +| clip_range | 0.2 | +| entropy_loss | -0.339 | +| explained_variance | -1.93 | +| learning_rate | 0.0001 | +| loss | -0.0903 | +| n_updates | 149640 | +| policy_gradient_loss | -0.067 | +| value_loss | 0.000341 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0708 | +| time/ | | +| fps | 309 | +| iterations | 8913 | +| time_elapsed | 29485 | +| total_timesteps | 9126912 | +| train/ | | +| approx_kl | 1.7836697 | +| clip_fraction | 0.482 | +| clip_range | 0.2 | +| entropy_loss | -0.422 | +| explained_variance | -2.13 | +| learning_rate | 0.0001 | +| loss | -0.106 | +| n_updates | 149650 | +| policy_gradient_loss | -0.0656 | +| value_loss | 0.000465 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0706 | +| time/ | | +| fps | 309 | +| iterations | 8914 | +| time_elapsed | 29488 | +| total_timesteps | 9127936 | +| train/ | | +| approx_kl | 2.1912055 | +| clip_fraction | 0.528 | +| clip_range | 0.2 | +| entropy_loss | -0.422 | +| explained_variance | -0.932 | +| learning_rate | 0.0001 | +| loss | -0.0713 | +| n_updates | 149660 | +| policy_gradient_loss | -0.0744 | +| value_loss | 0.000382 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0701 | +| time/ | | +| fps | 309 | +| iterations | 8915 | +| time_elapsed | 29491 | +| total_timesteps | 9128960 | +| train/ | | +| approx_kl | 2.0197089 | +| clip_fraction | 0.478 | +| clip_range | 0.2 | +| entropy_loss | -0.38 | +| explained_variance | -3.56 | +| learning_rate | 0.0001 | +| loss | -0.0633 | +| n_updates | 149670 | +| policy_gradient_loss | -0.0597 | +| value_loss | 0.000662 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0712 | +| time/ | | +| fps | 309 | +| iterations | 8916 | +| time_elapsed | 29495 | +| total_timesteps | 9129984 | +| train/ | | +| approx_kl | 3.092647 | +| clip_fraction | 0.485 | +| clip_range | 0.2 | +| entropy_loss | -0.373 | +| explained_variance | -1.23 | +| learning_rate | 0.0001 | +| loss | -0.078 | +| n_updates | 149680 | +| policy_gradient_loss | -0.0584 | +| value_loss | 0.000545 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0712 | +| time/ | | +| fps | 309 | +| iterations | 8917 | +| time_elapsed | 29498 | +| total_timesteps | 9131008 | +| train/ | | +| approx_kl | 2.8226056 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.403 | +| explained_variance | -2.1 | +| learning_rate | 0.0001 | +| loss | -0.112 | +| n_updates | 149690 | +| policy_gradient_loss | -0.0664 | +| value_loss | 0.000478 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.071 | +| time/ | | +| fps | 309 | +| iterations | 8918 | +| time_elapsed | 29501 | +| total_timesteps | 9132032 | +| train/ | | +| approx_kl | 1.720377 | +| clip_fraction | 0.473 | +| clip_range | 0.2 | +| entropy_loss | -0.425 | +| explained_variance | -1.68 | +| learning_rate | 0.0001 | +| loss | -0.0721 | +| n_updates | 149700 | +| policy_gradient_loss | -0.0656 | +| value_loss | 0.000485 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0699 | +| time/ | | +| fps | 309 | +| iterations | 8919 | +| time_elapsed | 29505 | +| total_timesteps | 9133056 | +| train/ | | +| approx_kl | 2.3752394 | +| clip_fraction | 0.466 | +| clip_range | 0.2 | +| entropy_loss | -0.319 | +| explained_variance | -1.43 | +| learning_rate | 0.0001 | +| loss | -0.0953 | +| n_updates | 149710 | +| policy_gradient_loss | -0.0681 | +| value_loss | 0.000682 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0707 | +| time/ | | +| fps | 309 | +| iterations | 8920 | +| time_elapsed | 29508 | +| total_timesteps | 9134080 | +| train/ | | +| approx_kl | 2.6885996 | +| clip_fraction | 0.462 | +| clip_range | 0.2 | +| entropy_loss | -0.339 | +| explained_variance | -2.84 | +| learning_rate | 0.0001 | +| loss | -0.08 | +| n_updates | 149720 | +| policy_gradient_loss | -0.0667 | +| value_loss | 0.000732 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0682 | +| time/ | | +| fps | 309 | +| iterations | 8921 | +| time_elapsed | 29512 | +| total_timesteps | 9135104 | +| train/ | | +| approx_kl | 2.0856082 | +| clip_fraction | 0.482 | +| clip_range | 0.2 | +| entropy_loss | -0.414 | +| explained_variance | -3.58 | +| learning_rate | 0.0001 | +| loss | -0.0941 | +| n_updates | 149730 | +| policy_gradient_loss | -0.07 | +| value_loss | 0.000497 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0682 | +| time/ | | +| fps | 309 | +| iterations | 8922 | +| time_elapsed | 29515 | +| total_timesteps | 9136128 | +| train/ | | +| approx_kl | 2.1365948 | +| clip_fraction | 0.469 | +| clip_range | 0.2 | +| entropy_loss | -0.353 | +| explained_variance | -1.65 | +| learning_rate | 0.0001 | +| loss | -0.109 | +| n_updates | 149740 | +| policy_gradient_loss | -0.0654 | +| value_loss | 0.000553 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0712 | +| time/ | | +| fps | 309 | +| iterations | 8923 | +| time_elapsed | 29519 | +| total_timesteps | 9137152 | +| train/ | | +| approx_kl | 2.244639 | +| clip_fraction | 0.531 | +| clip_range | 0.2 | +| entropy_loss | -0.436 | +| explained_variance | -0.382 | +| learning_rate | 0.0001 | +| loss | -0.0974 | +| n_updates | 149750 | +| policy_gradient_loss | -0.0731 | +| value_loss | 0.000581 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0728 | +| time/ | | +| fps | 309 | +| iterations | 8924 | +| time_elapsed | 29522 | +| total_timesteps | 9138176 | +| train/ | | +| approx_kl | 3.2393847 | +| clip_fraction | 0.459 | +| clip_range | 0.2 | +| entropy_loss | -0.37 | +| explained_variance | -3.08 | +| learning_rate | 0.0001 | +| loss | -0.0862 | +| n_updates | 149760 | +| policy_gradient_loss | -0.0629 | +| value_loss | 0.000506 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0728 | +| time/ | | +| fps | 309 | +| iterations | 8925 | +| time_elapsed | 29526 | +| total_timesteps | 9139200 | +| train/ | | +| approx_kl | 2.1441903 | +| clip_fraction | 0.469 | +| clip_range | 0.2 | +| entropy_loss | -0.339 | +| explained_variance | -4.26 | +| learning_rate | 0.0001 | +| loss | -0.0744 | +| n_updates | 149770 | +| policy_gradient_loss | -0.065 | +| value_loss | 0.000417 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.0731 | +| time/ | | +| fps | 309 | +| iterations | 8926 | +| time_elapsed | 29529 | +| total_timesteps | 9140224 | +| train/ | | +| approx_kl | 2.6463943 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.313 | +| explained_variance | -2.42 | +| learning_rate | 0.0001 | +| loss | -0.0619 | +| n_updates | 149780 | +| policy_gradient_loss | -0.0591 | +| value_loss | 0.000273 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.0753 | +| time/ | | +| fps | 309 | +| iterations | 8927 | +| time_elapsed | 29532 | +| total_timesteps | 9141248 | +| train/ | | +| approx_kl | 2.5077462 | +| clip_fraction | 0.472 | +| clip_range | 0.2 | +| entropy_loss | -0.335 | +| explained_variance | -1.24 | +| learning_rate | 0.0001 | +| loss | -0.083 | +| n_updates | 149790 | +| policy_gradient_loss | -0.0608 | +| value_loss | 0.000656 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.0753 | +| time/ | | +| fps | 309 | +| iterations | 8928 | +| time_elapsed | 29536 | +| total_timesteps | 9142272 | +| train/ | | +| approx_kl | 2.0503488 | +| clip_fraction | 0.461 | +| clip_range | 0.2 | +| entropy_loss | -0.328 | +| explained_variance | -0.998 | +| learning_rate | 0.0001 | +| loss | -0.0289 | +| n_updates | 149800 | +| policy_gradient_loss | -0.0648 | +| value_loss | 0.00059 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.0757 | +| time/ | | +| fps | 309 | +| iterations | 8929 | +| time_elapsed | 29539 | +| total_timesteps | 9143296 | +| train/ | | +| approx_kl | 2.1175103 | +| clip_fraction | 0.438 | +| clip_range | 0.2 | +| entropy_loss | -0.313 | +| explained_variance | -2.67 | +| learning_rate | 0.0001 | +| loss | -0.082 | +| n_updates | 149810 | +| policy_gradient_loss | -0.0626 | +| value_loss | 0.000468 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.0738 | +| time/ | | +| fps | 309 | +| iterations | 8930 | +| time_elapsed | 29542 | +| total_timesteps | 9144320 | +| train/ | | +| approx_kl | 2.3716414 | +| clip_fraction | 0.473 | +| clip_range | 0.2 | +| entropy_loss | -0.354 | +| explained_variance | -1.26 | +| learning_rate | 0.0001 | +| loss | -0.0836 | +| n_updates | 149820 | +| policy_gradient_loss | -0.0648 | +| value_loss | 0.00038 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.0697 | +| time/ | | +| fps | 309 | +| iterations | 8931 | +| time_elapsed | 29545 | +| total_timesteps | 9145344 | +| train/ | | +| approx_kl | 2.233492 | +| clip_fraction | 0.495 | +| clip_range | 0.2 | +| entropy_loss | -0.402 | +| explained_variance | -1.76 | +| learning_rate | 0.0001 | +| loss | -0.0605 | +| n_updates | 149830 | +| policy_gradient_loss | -0.0681 | +| value_loss | 0.000357 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.0697 | +| time/ | | +| fps | 309 | +| iterations | 8932 | +| time_elapsed | 29549 | +| total_timesteps | 9146368 | +| train/ | | +| approx_kl | 1.977802 | +| clip_fraction | 0.453 | +| clip_range | 0.2 | +| entropy_loss | -0.346 | +| explained_variance | -1.07 | +| learning_rate | 0.0001 | +| loss | -0.0861 | +| n_updates | 149840 | +| policy_gradient_loss | -0.0599 | +| value_loss | 0.000438 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0656 | +| time/ | | +| fps | 309 | +| iterations | 8933 | +| time_elapsed | 29552 | +| total_timesteps | 9147392 | +| train/ | | +| approx_kl | 2.4478612 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.393 | +| explained_variance | -0.861 | +| learning_rate | 0.0001 | +| loss | -0.0914 | +| n_updates | 149850 | +| policy_gradient_loss | -0.0653 | +| value_loss | 0.000327 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0698 | +| time/ | | +| fps | 309 | +| iterations | 8934 | +| time_elapsed | 29555 | +| total_timesteps | 9148416 | +| train/ | | +| approx_kl | 2.250133 | +| clip_fraction | 0.463 | +| clip_range | 0.2 | +| entropy_loss | -0.392 | +| explained_variance | -0.676 | +| learning_rate | 0.0001 | +| loss | -0.0808 | +| n_updates | 149860 | +| policy_gradient_loss | -0.0594 | +| value_loss | 0.000423 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0705 | +| time/ | | +| fps | 309 | +| iterations | 8935 | +| time_elapsed | 29558 | +| total_timesteps | 9149440 | +| train/ | | +| approx_kl | 1.9380612 | +| clip_fraction | 0.463 | +| clip_range | 0.2 | +| entropy_loss | -0.372 | +| explained_variance | -0.831 | +| learning_rate | 0.0001 | +| loss | -0.0949 | +| n_updates | 149870 | +| policy_gradient_loss | -0.0656 | +| value_loss | 0.000388 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0705 | +| time/ | | +| fps | 309 | +| iterations | 8936 | +| time_elapsed | 29562 | +| total_timesteps | 9150464 | +| train/ | | +| approx_kl | 3.371932 | +| clip_fraction | 0.474 | +| clip_range | 0.2 | +| entropy_loss | -0.395 | +| explained_variance | -0.843 | +| learning_rate | 0.0001 | +| loss | -0.0806 | +| n_updates | 149880 | +| policy_gradient_loss | -0.0686 | +| value_loss | 0.000416 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.0731 | +| time/ | | +| fps | 309 | +| iterations | 8937 | +| time_elapsed | 29565 | +| total_timesteps | 9151488 | +| train/ | | +| approx_kl | 2.219046 | +| clip_fraction | 0.49 | +| clip_range | 0.2 | +| entropy_loss | -0.383 | +| explained_variance | -1.65 | +| learning_rate | 0.0001 | +| loss | -0.0826 | +| n_updates | 149890 | +| policy_gradient_loss | -0.0721 | +| value_loss | 0.00046 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.0731 | +| time/ | | +| fps | 309 | +| iterations | 8938 | +| time_elapsed | 29568 | +| total_timesteps | 9152512 | +| train/ | | +| approx_kl | 1.9477191 | +| clip_fraction | 0.452 | +| clip_range | 0.2 | +| entropy_loss | -0.352 | +| explained_variance | -2.71 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 149900 | +| policy_gradient_loss | -0.068 | +| value_loss | 0.000639 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0733 | +| time/ | | +| fps | 309 | +| iterations | 8939 | +| time_elapsed | 29572 | +| total_timesteps | 9153536 | +| train/ | | +| approx_kl | 2.876821 | +| clip_fraction | 0.502 | +| clip_range | 0.2 | +| entropy_loss | -0.433 | +| explained_variance | -3.84 | +| learning_rate | 0.0001 | +| loss | -0.0864 | +| n_updates | 149910 | +| policy_gradient_loss | -0.0715 | +| value_loss | 0.000622 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0738 | +| time/ | | +| fps | 309 | +| iterations | 8940 | +| time_elapsed | 29575 | +| total_timesteps | 9154560 | +| train/ | | +| approx_kl | 2.3171139 | +| clip_fraction | 0.479 | +| clip_range | 0.2 | +| entropy_loss | -0.345 | +| explained_variance | -5.12 | +| learning_rate | 0.0001 | +| loss | -0.0853 | +| n_updates | 149920 | +| policy_gradient_loss | -0.0705 | +| value_loss | 0.000338 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0738 | +| time/ | | +| fps | 309 | +| iterations | 8941 | +| time_elapsed | 29578 | +| total_timesteps | 9155584 | +| train/ | | +| approx_kl | 2.2470417 | +| clip_fraction | 0.498 | +| clip_range | 0.2 | +| entropy_loss | -0.415 | +| explained_variance | -2.12 | +| learning_rate | 0.0001 | +| loss | -0.109 | +| n_updates | 149930 | +| policy_gradient_loss | -0.0698 | +| value_loss | 0.000555 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.0742 | +| time/ | | +| fps | 309 | +| iterations | 8942 | +| time_elapsed | 29582 | +| total_timesteps | 9156608 | +| train/ | | +| approx_kl | 2.8955884 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.36 | +| explained_variance | -1.34 | +| learning_rate | 0.0001 | +| loss | -0.107 | +| n_updates | 149940 | +| policy_gradient_loss | -0.0684 | +| value_loss | 0.000616 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.0742 | +| time/ | | +| fps | 309 | +| iterations | 8943 | +| time_elapsed | 29585 | +| total_timesteps | 9157632 | +| train/ | | +| approx_kl | 2.2829 | +| clip_fraction | 0.494 | +| clip_range | 0.2 | +| entropy_loss | -0.378 | +| explained_variance | -1.71 | +| learning_rate | 0.0001 | +| loss | -0.097 | +| n_updates | 149950 | +| policy_gradient_loss | -0.073 | +| value_loss | 0.000718 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0732 | +| time/ | | +| fps | 309 | +| iterations | 8944 | +| time_elapsed | 29588 | +| total_timesteps | 9158656 | +| train/ | | +| approx_kl | 2.2650962 | +| clip_fraction | 0.467 | +| clip_range | 0.2 | +| entropy_loss | -0.29 | +| explained_variance | -3.66 | +| learning_rate | 0.0001 | +| loss | -0.0746 | +| n_updates | 149960 | +| policy_gradient_loss | -0.0667 | +| value_loss | 0.000559 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.071 | +| time/ | | +| fps | 309 | +| iterations | 8945 | +| time_elapsed | 29592 | +| total_timesteps | 9159680 | +| train/ | | +| approx_kl | 3.1898496 | +| clip_fraction | 0.428 | +| clip_range | 0.2 | +| entropy_loss | -0.306 | +| explained_variance | -1.38 | +| learning_rate | 0.0001 | +| loss | -0.0842 | +| n_updates | 149970 | +| policy_gradient_loss | -0.061 | +| value_loss | 0.00038 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.071 | +| time/ | | +| fps | 309 | +| iterations | 8946 | +| time_elapsed | 29595 | +| total_timesteps | 9160704 | +| train/ | | +| approx_kl | 1.9037614 | +| clip_fraction | 0.439 | +| clip_range | 0.2 | +| entropy_loss | -0.332 | +| explained_variance | -0.83 | +| learning_rate | 0.0001 | +| loss | -0.0811 | +| n_updates | 149980 | +| policy_gradient_loss | -0.0629 | +| value_loss | 0.000382 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0731 | +| time/ | | +| fps | 309 | +| iterations | 8947 | +| time_elapsed | 29598 | +| total_timesteps | 9161728 | +| train/ | | +| approx_kl | 2.321079 | +| clip_fraction | 0.489 | +| clip_range | 0.2 | +| entropy_loss | -0.342 | +| explained_variance | -1.02 | +| learning_rate | 0.0001 | +| loss | -0.0831 | +| n_updates | 149990 | +| policy_gradient_loss | -0.064 | +| value_loss | 0.000441 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0731 | +| time/ | | +| fps | 309 | +| iterations | 8948 | +| time_elapsed | 29601 | +| total_timesteps | 9162752 | +| train/ | | +| approx_kl | 2.2164297 | +| clip_fraction | 0.491 | +| clip_range | 0.2 | +| entropy_loss | -0.441 | +| explained_variance | -2.25 | +| learning_rate | 0.0001 | +| loss | -0.0873 | +| n_updates | 150000 | +| policy_gradient_loss | -0.0624 | +| value_loss | 0.000224 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.0751 | +| time/ | | +| fps | 309 | +| iterations | 8949 | +| time_elapsed | 29604 | +| total_timesteps | 9163776 | +| train/ | | +| approx_kl | 2.4028687 | +| clip_fraction | 0.482 | +| clip_range | 0.2 | +| entropy_loss | -0.343 | +| explained_variance | -2.68 | +| learning_rate | 0.0001 | +| loss | -0.0772 | +| n_updates | 150010 | +| policy_gradient_loss | -0.0627 | +| value_loss | 0.000299 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.0743 | +| time/ | | +| fps | 309 | +| iterations | 8950 | +| time_elapsed | 29608 | +| total_timesteps | 9164800 | +| train/ | | +| approx_kl | 2.3751886 | +| clip_fraction | 0.452 | +| clip_range | 0.2 | +| entropy_loss | -0.341 | +| explained_variance | -1.74 | +| learning_rate | 0.0001 | +| loss | -0.083 | +| n_updates | 150020 | +| policy_gradient_loss | -0.0592 | +| value_loss | 0.000351 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.0758 | +| time/ | | +| fps | 309 | +| iterations | 8951 | +| time_elapsed | 29611 | +| total_timesteps | 9165824 | +| train/ | | +| approx_kl | 3.2251801 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.387 | +| explained_variance | -0.822 | +| learning_rate | 0.0001 | +| loss | -0.0907 | +| n_updates | 150030 | +| policy_gradient_loss | -0.0746 | +| value_loss | 0.00048 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.0758 | +| time/ | | +| fps | 309 | +| iterations | 8952 | +| time_elapsed | 29614 | +| total_timesteps | 9166848 | +| train/ | | +| approx_kl | 2.1184707 | +| clip_fraction | 0.444 | +| clip_range | 0.2 | +| entropy_loss | -0.338 | +| explained_variance | -1.22 | +| learning_rate | 0.0001 | +| loss | -0.0783 | +| n_updates | 150040 | +| policy_gradient_loss | -0.0622 | +| value_loss | 0.000427 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.0772 | +| time/ | | +| fps | 309 | +| iterations | 8953 | +| time_elapsed | 29617 | +| total_timesteps | 9167872 | +| train/ | | +| approx_kl | 1.7412211 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.423 | +| explained_variance | -0.991 | +| learning_rate | 0.0001 | +| loss | -0.0935 | +| n_updates | 150050 | +| policy_gradient_loss | -0.0709 | +| value_loss | 0.000369 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.0844 | +| time/ | | +| fps | 309 | +| iterations | 8954 | +| time_elapsed | 29621 | +| total_timesteps | 9168896 | +| train/ | | +| approx_kl | 2.1583288 | +| clip_fraction | 0.472 | +| clip_range | 0.2 | +| entropy_loss | -0.355 | +| explained_variance | -1.28 | +| learning_rate | 0.0001 | +| loss | -0.091 | +| n_updates | 150060 | +| policy_gradient_loss | -0.0674 | +| value_loss | 0.000489 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.0887 | +| time/ | | +| fps | 309 | +| iterations | 8955 | +| time_elapsed | 29624 | +| total_timesteps | 9169920 | +| train/ | | +| approx_kl | 2.352373 | +| clip_fraction | 0.499 | +| clip_range | 0.2 | +| entropy_loss | -0.417 | +| explained_variance | -0.269 | +| learning_rate | 0.0001 | +| loss | -0.0772 | +| n_updates | 150070 | +| policy_gradient_loss | -0.0652 | +| value_loss | 0.000691 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.0887 | +| time/ | | +| fps | 309 | +| iterations | 8956 | +| time_elapsed | 29628 | +| total_timesteps | 9170944 | +| train/ | | +| approx_kl | 2.1665673 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.387 | +| explained_variance | -1.16 | +| learning_rate | 0.0001 | +| loss | -0.0993 | +| n_updates | 150080 | +| policy_gradient_loss | -0.0703 | +| value_loss | 0.000838 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.0835 | +| time/ | | +| fps | 309 | +| iterations | 8957 | +| time_elapsed | 29631 | +| total_timesteps | 9171968 | +| train/ | | +| approx_kl | 3.7972202 | +| clip_fraction | 0.477 | +| clip_range | 0.2 | +| entropy_loss | -0.393 | +| explained_variance | -8.78 | +| learning_rate | 0.0001 | +| loss | -0.0852 | +| n_updates | 150090 | +| policy_gradient_loss | -0.0746 | +| value_loss | 0.000512 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.0848 | +| time/ | | +| fps | 309 | +| iterations | 8958 | +| time_elapsed | 29635 | +| total_timesteps | 9172992 | +| train/ | | +| approx_kl | 2.2856774 | +| clip_fraction | 0.466 | +| clip_range | 0.2 | +| entropy_loss | -0.367 | +| explained_variance | -0.651 | +| learning_rate | 0.0001 | +| loss | -0.0875 | +| n_updates | 150100 | +| policy_gradient_loss | -0.0525 | +| value_loss | 0.000476 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.0908 | +| time/ | | +| fps | 309 | +| iterations | 8959 | +| time_elapsed | 29638 | +| total_timesteps | 9174016 | +| train/ | | +| approx_kl | 1.6454165 | +| clip_fraction | 0.447 | +| clip_range | 0.2 | +| entropy_loss | -0.366 | +| explained_variance | -0.343 | +| learning_rate | 0.0001 | +| loss | -0.0875 | +| n_updates | 150110 | +| policy_gradient_loss | -0.0634 | +| value_loss | 0.000402 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.0913 | +| time/ | | +| fps | 309 | +| iterations | 8960 | +| time_elapsed | 29642 | +| total_timesteps | 9175040 | +| train/ | | +| approx_kl | 1.7559878 | +| clip_fraction | 0.459 | +| clip_range | 0.2 | +| entropy_loss | -0.365 | +| explained_variance | -0.503 | +| learning_rate | 0.0001 | +| loss | -0.0759 | +| n_updates | 150120 | +| policy_gradient_loss | -0.0612 | +| value_loss | 0.000631 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.0913 | +| time/ | | +| fps | 309 | +| iterations | 8961 | +| time_elapsed | 29645 | +| total_timesteps | 9176064 | +| train/ | | +| approx_kl | 2.605602 | +| clip_fraction | 0.459 | +| clip_range | 0.2 | +| entropy_loss | -0.369 | +| explained_variance | -4 | +| learning_rate | 0.0001 | +| loss | -0.0873 | +| n_updates | 150130 | +| policy_gradient_loss | -0.0703 | +| value_loss | 0.000639 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.0912 | +| time/ | | +| fps | 309 | +| iterations | 8962 | +| time_elapsed | 29649 | +| total_timesteps | 9177088 | +| train/ | | +| approx_kl | 2.3766384 | +| clip_fraction | 0.465 | +| clip_range | 0.2 | +| entropy_loss | -0.342 | +| explained_variance | -2.07 | +| learning_rate | 0.0001 | +| loss | -0.0749 | +| n_updates | 150140 | +| policy_gradient_loss | -0.0588 | +| value_loss | 0.000464 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.0941 | +| time/ | | +| fps | 309 | +| iterations | 8963 | +| time_elapsed | 29652 | +| total_timesteps | 9178112 | +| train/ | | +| approx_kl | 1.6683152 | +| clip_fraction | 0.451 | +| clip_range | 0.2 | +| entropy_loss | -0.35 | +| explained_variance | -0.287 | +| learning_rate | 0.0001 | +| loss | -0.0838 | +| n_updates | 150150 | +| policy_gradient_loss | -0.0641 | +| value_loss | 0.000741 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0909 | +| time/ | | +| fps | 309 | +| iterations | 8964 | +| time_elapsed | 29655 | +| total_timesteps | 9179136 | +| train/ | | +| approx_kl | 2.1527839 | +| clip_fraction | 0.45 | +| clip_range | 0.2 | +| entropy_loss | -0.334 | +| explained_variance | -4.25 | +| learning_rate | 0.0001 | +| loss | -0.0854 | +| n_updates | 150160 | +| policy_gradient_loss | -0.068 | +| value_loss | 0.000496 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0881 | +| time/ | | +| fps | 309 | +| iterations | 8965 | +| time_elapsed | 29658 | +| total_timesteps | 9180160 | +| train/ | | +| approx_kl | 2.0728455 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.355 | +| explained_variance | -1.08 | +| learning_rate | 0.0001 | +| loss | -0.0816 | +| n_updates | 150170 | +| policy_gradient_loss | -0.0633 | +| value_loss | 0.000481 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0857 | +| time/ | | +| fps | 309 | +| iterations | 8966 | +| time_elapsed | 29661 | +| total_timesteps | 9181184 | +| train/ | | +| approx_kl | 2.1170883 | +| clip_fraction | 0.45 | +| clip_range | 0.2 | +| entropy_loss | -0.342 | +| explained_variance | -0.677 | +| learning_rate | 0.0001 | +| loss | -0.0768 | +| n_updates | 150180 | +| policy_gradient_loss | -0.0645 | +| value_loss | 0.000514 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0833 | +| time/ | | +| fps | 309 | +| iterations | 8967 | +| time_elapsed | 29664 | +| total_timesteps | 9182208 | +| train/ | | +| approx_kl | 1.6212612 | +| clip_fraction | 0.448 | +| clip_range | 0.2 | +| entropy_loss | -0.346 | +| explained_variance | -1.75 | +| learning_rate | 0.0001 | +| loss | -0.0892 | +| n_updates | 150190 | +| policy_gradient_loss | -0.0631 | +| value_loss | 0.000534 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0862 | +| time/ | | +| fps | 309 | +| iterations | 8968 | +| time_elapsed | 29668 | +| total_timesteps | 9183232 | +| train/ | | +| approx_kl | 1.8553262 | +| clip_fraction | 0.421 | +| clip_range | 0.2 | +| entropy_loss | -0.287 | +| explained_variance | -0.425 | +| learning_rate | 0.0001 | +| loss | -0.0573 | +| n_updates | 150200 | +| policy_gradient_loss | -0.062 | +| value_loss | 0.000579 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0819 | +| time/ | | +| fps | 309 | +| iterations | 8969 | +| time_elapsed | 29671 | +| total_timesteps | 9184256 | +| train/ | | +| approx_kl | 4.3096232 | +| clip_fraction | 0.432 | +| clip_range | 0.2 | +| entropy_loss | -0.321 | +| explained_variance | -0.0179 | +| learning_rate | 0.0001 | +| loss | -0.0707 | +| n_updates | 150210 | +| policy_gradient_loss | -0.0578 | +| value_loss | 0.000794 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0803 | +| time/ | | +| fps | 309 | +| iterations | 8970 | +| time_elapsed | 29674 | +| total_timesteps | 9185280 | +| train/ | | +| approx_kl | 2.012438 | +| clip_fraction | 0.421 | +| clip_range | 0.2 | +| entropy_loss | -0.307 | +| explained_variance | -0.309 | +| learning_rate | 0.0001 | +| loss | -0.0649 | +| n_updates | 150220 | +| policy_gradient_loss | -0.0652 | +| value_loss | 0.000685 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0826 | +| time/ | | +| fps | 309 | +| iterations | 8971 | +| time_elapsed | 29677 | +| total_timesteps | 9186304 | +| train/ | | +| approx_kl | 2.5012407 | +| clip_fraction | 0.44 | +| clip_range | 0.2 | +| entropy_loss | -0.32 | +| explained_variance | -0.251 | +| learning_rate | 0.0001 | +| loss | -0.0616 | +| n_updates | 150230 | +| policy_gradient_loss | -0.0586 | +| value_loss | 0.00086 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.082 | +| time/ | | +| fps | 309 | +| iterations | 8972 | +| time_elapsed | 29680 | +| total_timesteps | 9187328 | +| train/ | | +| approx_kl | 2.012982 | +| clip_fraction | 0.447 | +| clip_range | 0.2 | +| entropy_loss | -0.346 | +| explained_variance | -1.87 | +| learning_rate | 0.0001 | +| loss | -0.107 | +| n_updates | 150240 | +| policy_gradient_loss | -0.0624 | +| value_loss | 0.000661 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.082 | +| time/ | | +| fps | 309 | +| iterations | 8973 | +| time_elapsed | 29684 | +| total_timesteps | 9188352 | +| train/ | | +| approx_kl | 2.0539694 | +| clip_fraction | 0.453 | +| clip_range | 0.2 | +| entropy_loss | -0.326 | +| explained_variance | -2 | +| learning_rate | 0.0001 | +| loss | -0.0848 | +| n_updates | 150250 | +| policy_gradient_loss | -0.0671 | +| value_loss | 0.000294 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.078 | +| time/ | | +| fps | 309 | +| iterations | 8974 | +| time_elapsed | 29687 | +| total_timesteps | 9189376 | +| train/ | | +| approx_kl | 3.2380805 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.347 | +| explained_variance | -2.52 | +| learning_rate | 0.0001 | +| loss | -0.0783 | +| n_updates | 150260 | +| policy_gradient_loss | -0.0678 | +| value_loss | 0.000483 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0729 | +| time/ | | +| fps | 309 | +| iterations | 8975 | +| time_elapsed | 29691 | +| total_timesteps | 9190400 | +| train/ | | +| approx_kl | 2.2826452 | +| clip_fraction | 0.45 | +| clip_range | 0.2 | +| entropy_loss | -0.319 | +| explained_variance | -1.38 | +| learning_rate | 0.0001 | +| loss | -0.0558 | +| n_updates | 150270 | +| policy_gradient_loss | -0.0642 | +| value_loss | 0.000508 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0729 | +| time/ | | +| fps | 309 | +| iterations | 8976 | +| time_elapsed | 29694 | +| total_timesteps | 9191424 | +| train/ | | +| approx_kl | 1.9111035 | +| clip_fraction | 0.43 | +| clip_range | 0.2 | +| entropy_loss | -0.333 | +| explained_variance | -2.66 | +| learning_rate | 0.0001 | +| loss | -0.0672 | +| n_updates | 150280 | +| policy_gradient_loss | -0.0603 | +| value_loss | 0.000342 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0744 | +| time/ | | +| fps | 309 | +| iterations | 8977 | +| time_elapsed | 29697 | +| total_timesteps | 9192448 | +| train/ | | +| approx_kl | 1.9984062 | +| clip_fraction | 0.47 | +| clip_range | 0.2 | +| entropy_loss | -0.336 | +| explained_variance | -1.6 | +| learning_rate | 0.0001 | +| loss | -0.0977 | +| n_updates | 150290 | +| policy_gradient_loss | -0.0686 | +| value_loss | 0.000343 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0768 | +| time/ | | +| fps | 309 | +| iterations | 8978 | +| time_elapsed | 29701 | +| total_timesteps | 9193472 | +| train/ | | +| approx_kl | 2.2264075 | +| clip_fraction | 0.449 | +| clip_range | 0.2 | +| entropy_loss | -0.342 | +| explained_variance | -1.36 | +| learning_rate | 0.0001 | +| loss | -0.0705 | +| n_updates | 150300 | +| policy_gradient_loss | -0.0664 | +| value_loss | 0.000569 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.077 | +| time/ | | +| fps | 309 | +| iterations | 8979 | +| time_elapsed | 29704 | +| total_timesteps | 9194496 | +| train/ | | +| approx_kl | 2.0526183 | +| clip_fraction | 0.424 | +| clip_range | 0.2 | +| entropy_loss | -0.307 | +| explained_variance | -1.71 | +| learning_rate | 0.0001 | +| loss | -0.0733 | +| n_updates | 150310 | +| policy_gradient_loss | -0.0557 | +| value_loss | 0.000765 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.077 | +| time/ | | +| fps | 309 | +| iterations | 8980 | +| time_elapsed | 29707 | +| total_timesteps | 9195520 | +| train/ | | +| approx_kl | 1.810038 | +| clip_fraction | 0.467 | +| clip_range | 0.2 | +| entropy_loss | -0.363 | +| explained_variance | -2.39 | +| learning_rate | 0.0001 | +| loss | -0.0944 | +| n_updates | 150320 | +| policy_gradient_loss | -0.0693 | +| value_loss | 0.000538 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0784 | +| time/ | | +| fps | 309 | +| iterations | 8981 | +| time_elapsed | 29710 | +| total_timesteps | 9196544 | +| train/ | | +| approx_kl | 2.1534414 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.383 | +| explained_variance | -1.02 | +| learning_rate | 0.0001 | +| loss | -0.0707 | +| n_updates | 150330 | +| policy_gradient_loss | -0.0627 | +| value_loss | 0.000574 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0762 | +| time/ | | +| fps | 309 | +| iterations | 8982 | +| time_elapsed | 29713 | +| total_timesteps | 9197568 | +| train/ | | +| approx_kl | 2.144628 | +| clip_fraction | 0.426 | +| clip_range | 0.2 | +| entropy_loss | -0.334 | +| explained_variance | -0.933 | +| learning_rate | 0.0001 | +| loss | -0.0877 | +| n_updates | 150340 | +| policy_gradient_loss | -0.063 | +| value_loss | 0.000383 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0737 | +| time/ | | +| fps | 309 | +| iterations | 8983 | +| time_elapsed | 29717 | +| total_timesteps | 9198592 | +| train/ | | +| approx_kl | 1.8480202 | +| clip_fraction | 0.416 | +| clip_range | 0.2 | +| entropy_loss | -0.319 | +| explained_variance | -0.123 | +| learning_rate | 0.0001 | +| loss | -0.0799 | +| n_updates | 150350 | +| policy_gradient_loss | -0.0579 | +| value_loss | 0.000436 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0737 | +| time/ | | +| fps | 309 | +| iterations | 8984 | +| time_elapsed | 29720 | +| total_timesteps | 9199616 | +| train/ | | +| approx_kl | 2.0762148 | +| clip_fraction | 0.426 | +| clip_range | 0.2 | +| entropy_loss | -0.286 | +| explained_variance | -0.00016 | +| learning_rate | 0.0001 | +| loss | -0.0904 | +| n_updates | 150360 | +| policy_gradient_loss | -0.064 | +| value_loss | 0.000625 | +--------------------------------------- + +Current state: Champion.Level12.RyuVsBison +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0758 | +| time/ | | +| fps | 309 | +| iterations | 8985 | +| time_elapsed | 29723 | +| total_timesteps | 9200640 | +| train/ | | +| approx_kl | 4.24239 | +| clip_fraction | 0.486 | +| clip_range | 0.2 | +| entropy_loss | -0.373 | +| explained_variance | -5.62 | +| learning_rate | 0.0001 | +| loss | -0.0911 | +| n_updates | 150370 | +| policy_gradient_loss | -0.0671 | +| value_loss | 0.00047 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0758 | +| time/ | | +| fps | 309 | +| iterations | 8986 | +| time_elapsed | 29726 | +| total_timesteps | 9201664 | +| train/ | | +| approx_kl | 2.5149252 | +| clip_fraction | 0.455 | +| clip_range | 0.2 | +| entropy_loss | -0.321 | +| explained_variance | -0.858 | +| learning_rate | 0.0001 | +| loss | -0.0479 | +| n_updates | 150380 | +| policy_gradient_loss | -0.0604 | +| value_loss | 0.000501 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0781 | +| time/ | | +| fps | 309 | +| iterations | 8987 | +| time_elapsed | 29729 | +| total_timesteps | 9202688 | +| train/ | | +| approx_kl | 3.1605113 | +| clip_fraction | 0.495 | +| clip_range | 0.2 | +| entropy_loss | -0.287 | +| explained_variance | -2.88 | +| learning_rate | 0.0001 | +| loss | -0.082 | +| n_updates | 150390 | +| policy_gradient_loss | -0.0688 | +| value_loss | 0.00069 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0747 | +| time/ | | +| fps | 309 | +| iterations | 8988 | +| time_elapsed | 29732 | +| total_timesteps | 9203712 | +| train/ | | +| approx_kl | 4.044694 | +| clip_fraction | 0.44 | +| clip_range | 0.2 | +| entropy_loss | -0.247 | +| explained_variance | -5.39 | +| learning_rate | 0.0001 | +| loss | -0.0893 | +| n_updates | 150400 | +| policy_gradient_loss | -0.0562 | +| value_loss | 0.000491 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0759 | +| time/ | | +| fps | 309 | +| iterations | 8989 | +| time_elapsed | 29736 | +| total_timesteps | 9204736 | +| train/ | | +| approx_kl | 2.947947 | +| clip_fraction | 0.457 | +| clip_range | 0.2 | +| entropy_loss | -0.277 | +| explained_variance | -0.432 | +| learning_rate | 0.0001 | +| loss | -0.0821 | +| n_updates | 150410 | +| policy_gradient_loss | -0.0581 | +| value_loss | 0.000751 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0759 | +| time/ | | +| fps | 309 | +| iterations | 8990 | +| time_elapsed | 29739 | +| total_timesteps | 9205760 | +| train/ | | +| approx_kl | 3.110269 | +| clip_fraction | 0.449 | +| clip_range | 0.2 | +| entropy_loss | -0.272 | +| explained_variance | -2.13 | +| learning_rate | 0.0001 | +| loss | -0.0801 | +| n_updates | 150420 | +| policy_gradient_loss | -0.0644 | +| value_loss | 0.000662 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.0807 | +| time/ | | +| fps | 309 | +| iterations | 8991 | +| time_elapsed | 29742 | +| total_timesteps | 9206784 | +| train/ | | +| approx_kl | 2.9948244 | +| clip_fraction | 0.466 | +| clip_range | 0.2 | +| entropy_loss | -0.312 | +| explained_variance | -0.887 | +| learning_rate | 0.0001 | +| loss | -0.0511 | +| n_updates | 150430 | +| policy_gradient_loss | -0.0657 | +| value_loss | 0.000702 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.082 | +| time/ | | +| fps | 309 | +| iterations | 8992 | +| time_elapsed | 29746 | +| total_timesteps | 9207808 | +| train/ | | +| approx_kl | 3.8649156 | +| clip_fraction | 0.468 | +| clip_range | 0.2 | +| entropy_loss | -0.286 | +| explained_variance | -1.68 | +| learning_rate | 0.0001 | +| loss | -0.0814 | +| n_updates | 150440 | +| policy_gradient_loss | -0.0693 | +| value_loss | 0.000779 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.082 | +| time/ | | +| fps | 309 | +| iterations | 8993 | +| time_elapsed | 29749 | +| total_timesteps | 9208832 | +| train/ | | +| approx_kl | 3.6578634 | +| clip_fraction | 0.461 | +| clip_range | 0.2 | +| entropy_loss | -0.279 | +| explained_variance | -3.21 | +| learning_rate | 0.0001 | +| loss | -0.0557 | +| n_updates | 150450 | +| policy_gradient_loss | -0.0636 | +| value_loss | 0.000786 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.0842 | +| time/ | | +| fps | 309 | +| iterations | 8994 | +| time_elapsed | 29753 | +| total_timesteps | 9209856 | +| train/ | | +| approx_kl | 2.6190019 | +| clip_fraction | 0.463 | +| clip_range | 0.2 | +| entropy_loss | -0.308 | +| explained_variance | -4.04 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 150460 | +| policy_gradient_loss | -0.0654 | +| value_loss | 0.000703 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0896 | +| time/ | | +| fps | 309 | +| iterations | 8995 | +| time_elapsed | 29756 | +| total_timesteps | 9210880 | +| train/ | | +| approx_kl | 3.4283056 | +| clip_fraction | 0.498 | +| clip_range | 0.2 | +| entropy_loss | -0.309 | +| explained_variance | -0.75 | +| learning_rate | 0.0001 | +| loss | -0.0954 | +| n_updates | 150470 | +| policy_gradient_loss | -0.0665 | +| value_loss | 0.000604 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0868 | +| time/ | | +| fps | 309 | +| iterations | 8996 | +| time_elapsed | 29760 | +| total_timesteps | 9211904 | +| train/ | | +| approx_kl | 8.221508 | +| clip_fraction | 0.466 | +| clip_range | 0.2 | +| entropy_loss | -0.309 | +| explained_variance | -1.58 | +| learning_rate | 0.0001 | +| loss | -0.0852 | +| n_updates | 150480 | +| policy_gradient_loss | -0.0629 | +| value_loss | 0.000719 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0881 | +| time/ | | +| fps | 309 | +| iterations | 8997 | +| time_elapsed | 29763 | +| total_timesteps | 9212928 | +| train/ | | +| approx_kl | 3.3161945 | +| clip_fraction | 0.419 | +| clip_range | 0.2 | +| entropy_loss | -0.237 | +| explained_variance | -1.36 | +| learning_rate | 0.0001 | +| loss | -0.0742 | +| n_updates | 150490 | +| policy_gradient_loss | -0.0633 | +| value_loss | 0.00058 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0881 | +| time/ | | +| fps | 309 | +| iterations | 8998 | +| time_elapsed | 29766 | +| total_timesteps | 9213952 | +| train/ | | +| approx_kl | 2.4616084 | +| clip_fraction | 0.433 | +| clip_range | 0.2 | +| entropy_loss | -0.272 | +| explained_variance | -0.317 | +| learning_rate | 0.0001 | +| loss | -0.091 | +| n_updates | 150500 | +| policy_gradient_loss | -0.0586 | +| value_loss | 0.000634 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0878 | +| time/ | | +| fps | 309 | +| iterations | 8999 | +| time_elapsed | 29770 | +| total_timesteps | 9214976 | +| train/ | | +| approx_kl | 2.3385682 | +| clip_fraction | 0.442 | +| clip_range | 0.2 | +| entropy_loss | -0.267 | +| explained_variance | -1.9 | +| learning_rate | 0.0001 | +| loss | -0.0815 | +| n_updates | 150510 | +| policy_gradient_loss | -0.0621 | +| value_loss | 0.000554 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0916 | +| time/ | | +| fps | 309 | +| iterations | 9000 | +| time_elapsed | 29773 | +| total_timesteps | 9216000 | +| train/ | | +| approx_kl | 2.9204397 | +| clip_fraction | 0.461 | +| clip_range | 0.2 | +| entropy_loss | -0.306 | +| explained_variance | -1.14 | +| learning_rate | 0.0001 | +| loss | -0.0982 | +| n_updates | 150520 | +| policy_gradient_loss | -0.0633 | +| value_loss | 0.000494 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0916 | +| time/ | | +| fps | 309 | +| iterations | 9001 | +| time_elapsed | 29776 | +| total_timesteps | 9217024 | +| train/ | | +| approx_kl | 2.3578076 | +| clip_fraction | 0.442 | +| clip_range | 0.2 | +| entropy_loss | -0.294 | +| explained_variance | -1.9 | +| learning_rate | 0.0001 | +| loss | -0.0791 | +| n_updates | 150530 | +| policy_gradient_loss | -0.0653 | +| value_loss | 0.000641 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0947 | +| time/ | | +| fps | 309 | +| iterations | 9002 | +| time_elapsed | 29780 | +| total_timesteps | 9218048 | +| train/ | | +| approx_kl | 2.5988507 | +| clip_fraction | 0.462 | +| clip_range | 0.2 | +| entropy_loss | -0.318 | +| explained_variance | -1.15 | +| learning_rate | 0.0001 | +| loss | -0.065 | +| n_updates | 150540 | +| policy_gradient_loss | -0.0566 | +| value_loss | 0.000621 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0958 | +| time/ | | +| fps | 309 | +| iterations | 9003 | +| time_elapsed | 29783 | +| total_timesteps | 9219072 | +| train/ | | +| approx_kl | 2.1518366 | +| clip_fraction | 0.452 | +| clip_range | 0.2 | +| entropy_loss | -0.278 | +| explained_variance | -1.63 | +| learning_rate | 0.0001 | +| loss | -0.0713 | +| n_updates | 150550 | +| policy_gradient_loss | -0.0663 | +| value_loss | 0.000636 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0993 | +| time/ | | +| fps | 309 | +| iterations | 9004 | +| time_elapsed | 29786 | +| total_timesteps | 9220096 | +| train/ | | +| approx_kl | 2.454998 | +| clip_fraction | 0.442 | +| clip_range | 0.2 | +| entropy_loss | -0.284 | +| explained_variance | -2.64 | +| learning_rate | 0.0001 | +| loss | -0.0827 | +| n_updates | 150560 | +| policy_gradient_loss | -0.0624 | +| value_loss | 0.000585 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.101 | +| time/ | | +| fps | 309 | +| iterations | 9005 | +| time_elapsed | 29789 | +| total_timesteps | 9221120 | +| train/ | | +| approx_kl | 7.0532045 | +| clip_fraction | 0.452 | +| clip_range | 0.2 | +| entropy_loss | -0.306 | +| explained_variance | -0.528 | +| learning_rate | 0.0001 | +| loss | -0.0909 | +| n_updates | 150570 | +| policy_gradient_loss | -0.054 | +| value_loss | 0.000878 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.101 | +| time/ | | +| fps | 309 | +| iterations | 9006 | +| time_elapsed | 29792 | +| total_timesteps | 9222144 | +| train/ | | +| approx_kl | 2.3885703 | +| clip_fraction | 0.412 | +| clip_range | 0.2 | +| entropy_loss | -0.266 | +| explained_variance | -2.07 | +| learning_rate | 0.0001 | +| loss | -0.0412 | +| n_updates | 150580 | +| policy_gradient_loss | -0.0523 | +| value_loss | 0.000574 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.104 | +| time/ | | +| fps | 309 | +| iterations | 9007 | +| time_elapsed | 29796 | +| total_timesteps | 9223168 | +| train/ | | +| approx_kl | 4.0012465 | +| clip_fraction | 0.466 | +| clip_range | 0.2 | +| entropy_loss | -0.291 | +| explained_variance | -0.982 | +| learning_rate | 0.0001 | +| loss | -0.0755 | +| n_updates | 150590 | +| policy_gradient_loss | -0.0632 | +| value_loss | 0.000705 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.108 | +| time/ | | +| fps | 309 | +| iterations | 9008 | +| time_elapsed | 29799 | +| total_timesteps | 9224192 | +| train/ | | +| approx_kl | 3.0806658 | +| clip_fraction | 0.461 | +| clip_range | 0.2 | +| entropy_loss | -0.281 | +| explained_variance | -1.63 | +| learning_rate | 0.0001 | +| loss | -0.075 | +| n_updates | 150600 | +| policy_gradient_loss | -0.0643 | +| value_loss | 0.000668 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.108 | +| time/ | | +| fps | 309 | +| iterations | 9009 | +| time_elapsed | 29802 | +| total_timesteps | 9225216 | +| train/ | | +| approx_kl | 3.4615335 | +| clip_fraction | 0.445 | +| clip_range | 0.2 | +| entropy_loss | -0.27 | +| explained_variance | -0.971 | +| learning_rate | 0.0001 | +| loss | -0.099 | +| n_updates | 150610 | +| policy_gradient_loss | -0.0635 | +| value_loss | 0.000861 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.111 | +| time/ | | +| fps | 309 | +| iterations | 9010 | +| time_elapsed | 29806 | +| total_timesteps | 9226240 | +| train/ | | +| approx_kl | 3.6939664 | +| clip_fraction | 0.432 | +| clip_range | 0.2 | +| entropy_loss | -0.27 | +| explained_variance | -2.45 | +| learning_rate | 0.0001 | +| loss | -0.0809 | +| n_updates | 150620 | +| policy_gradient_loss | -0.0622 | +| value_loss | 0.000505 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.111 | +| time/ | | +| fps | 309 | +| iterations | 9011 | +| time_elapsed | 29809 | +| total_timesteps | 9227264 | +| train/ | | +| approx_kl | 2.0617723 | +| clip_fraction | 0.425 | +| clip_range | 0.2 | +| entropy_loss | -0.308 | +| explained_variance | -0.35 | +| learning_rate | 0.0001 | +| loss | -0.088 | +| n_updates | 150630 | +| policy_gradient_loss | -0.0543 | +| value_loss | 0.000542 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.113 | +| time/ | | +| fps | 309 | +| iterations | 9012 | +| time_elapsed | 29813 | +| total_timesteps | 9228288 | +| train/ | | +| approx_kl | 6.2407503 | +| clip_fraction | 0.464 | +| clip_range | 0.2 | +| entropy_loss | -0.305 | +| explained_variance | -0.652 | +| learning_rate | 0.0001 | +| loss | -0.0687 | +| n_updates | 150640 | +| policy_gradient_loss | -0.0542 | +| value_loss | 0.000692 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.112 | +| time/ | | +| fps | 309 | +| iterations | 9013 | +| time_elapsed | 29816 | +| total_timesteps | 9229312 | +| train/ | | +| approx_kl | 2.3559198 | +| clip_fraction | 0.482 | +| clip_range | 0.2 | +| entropy_loss | -0.335 | +| explained_variance | -1.37 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 150650 | +| policy_gradient_loss | -0.0674 | +| value_loss | 0.000496 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.112 | +| time/ | | +| fps | 309 | +| iterations | 9014 | +| time_elapsed | 29820 | +| total_timesteps | 9230336 | +| train/ | | +| approx_kl | 3.1411548 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.305 | +| explained_variance | -0.563 | +| learning_rate | 0.0001 | +| loss | -0.087 | +| n_updates | 150660 | +| policy_gradient_loss | -0.0694 | +| value_loss | 0.000836 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.112 | +| time/ | | +| fps | 309 | +| iterations | 9015 | +| time_elapsed | 29823 | +| total_timesteps | 9231360 | +| train/ | | +| approx_kl | 2.2946634 | +| clip_fraction | 0.473 | +| clip_range | 0.2 | +| entropy_loss | -0.312 | +| explained_variance | -1.31 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 150670 | +| policy_gradient_loss | -0.0709 | +| value_loss | 0.000687 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.106 | +| time/ | | +| fps | 309 | +| iterations | 9016 | +| time_elapsed | 29827 | +| total_timesteps | 9232384 | +| train/ | | +| approx_kl | 2.6380386 | +| clip_fraction | 0.466 | +| clip_range | 0.2 | +| entropy_loss | -0.29 | +| explained_variance | -2.44 | +| learning_rate | 0.0001 | +| loss | -0.0971 | +| n_updates | 150680 | +| policy_gradient_loss | -0.0687 | +| value_loss | 0.000663 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.106 | +| time/ | | +| fps | 309 | +| iterations | 9017 | +| time_elapsed | 29830 | +| total_timesteps | 9233408 | +| train/ | | +| approx_kl | 3.1335542 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.296 | +| explained_variance | -0.908 | +| learning_rate | 0.0001 | +| loss | -0.0865 | +| n_updates | 150690 | +| policy_gradient_loss | -0.0652 | +| value_loss | 0.000695 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.111 | +| time/ | | +| fps | 309 | +| iterations | 9018 | +| time_elapsed | 29833 | +| total_timesteps | 9234432 | +| train/ | | +| approx_kl | 3.7147062 | +| clip_fraction | 0.461 | +| clip_range | 0.2 | +| entropy_loss | -0.286 | +| explained_variance | -1.17 | +| learning_rate | 0.0001 | +| loss | -0.0952 | +| n_updates | 150700 | +| policy_gradient_loss | -0.0665 | +| value_loss | 0.000469 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.111 | +| time/ | | +| fps | 309 | +| iterations | 9019 | +| time_elapsed | 29836 | +| total_timesteps | 9235456 | +| train/ | | +| approx_kl | 4.1514764 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.327 | +| explained_variance | -0.643 | +| learning_rate | 0.0001 | +| loss | -0.0797 | +| n_updates | 150710 | +| policy_gradient_loss | -0.0685 | +| value_loss | 0.000611 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.111 | +| time/ | | +| fps | 309 | +| iterations | 9020 | +| time_elapsed | 29839 | +| total_timesteps | 9236480 | +| train/ | | +| approx_kl | 3.916314 | +| clip_fraction | 0.459 | +| clip_range | 0.2 | +| entropy_loss | -0.286 | +| explained_variance | -1.38 | +| learning_rate | 0.0001 | +| loss | -0.0827 | +| n_updates | 150720 | +| policy_gradient_loss | -0.0652 | +| value_loss | 0.000627 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.115 | +| time/ | | +| fps | 309 | +| iterations | 9021 | +| time_elapsed | 29843 | +| total_timesteps | 9237504 | +| train/ | | +| approx_kl | 2.6323266 | +| clip_fraction | 0.447 | +| clip_range | 0.2 | +| entropy_loss | -0.283 | +| explained_variance | 0.0846 | +| learning_rate | 0.0001 | +| loss | -0.0794 | +| n_updates | 150730 | +| policy_gradient_loss | -0.0599 | +| value_loss | 0.000778 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.115 | +| time/ | | +| fps | 309 | +| iterations | 9022 | +| time_elapsed | 29846 | +| total_timesteps | 9238528 | +| train/ | | +| approx_kl | 2.8239222 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.311 | +| explained_variance | -2.55 | +| learning_rate | 0.0001 | +| loss | -0.0862 | +| n_updates | 150740 | +| policy_gradient_loss | -0.0668 | +| value_loss | 0.000537 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.119 | +| time/ | | +| fps | 309 | +| iterations | 9023 | +| time_elapsed | 29849 | +| total_timesteps | 9239552 | +| train/ | | +| approx_kl | 3.6478221 | +| clip_fraction | 0.459 | +| clip_range | 0.2 | +| entropy_loss | -0.305 | +| explained_variance | -0.659 | +| learning_rate | 0.0001 | +| loss | -0.0696 | +| n_updates | 150750 | +| policy_gradient_loss | -0.0565 | +| value_loss | 0.000533 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.122 | +| time/ | | +| fps | 309 | +| iterations | 9024 | +| time_elapsed | 29852 | +| total_timesteps | 9240576 | +| train/ | | +| approx_kl | 2.2830472 | +| clip_fraction | 0.407 | +| clip_range | 0.2 | +| entropy_loss | -0.259 | +| explained_variance | -0.663 | +| learning_rate | 0.0001 | +| loss | -0.0788 | +| n_updates | 150760 | +| policy_gradient_loss | -0.0594 | +| value_loss | 0.000784 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.122 | +| time/ | | +| fps | 309 | +| iterations | 9025 | +| time_elapsed | 29855 | +| total_timesteps | 9241600 | +| train/ | | +| approx_kl | 4.630015 | +| clip_fraction | 0.424 | +| clip_range | 0.2 | +| entropy_loss | -0.283 | +| explained_variance | -0.505 | +| learning_rate | 0.0001 | +| loss | -0.0841 | +| n_updates | 150770 | +| policy_gradient_loss | -0.0613 | +| value_loss | 0.000985 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.135 | +| time/ | | +| fps | 309 | +| iterations | 9026 | +| time_elapsed | 29858 | +| total_timesteps | 9242624 | +| train/ | | +| approx_kl | 2.6495113 | +| clip_fraction | 0.452 | +| clip_range | 0.2 | +| entropy_loss | -0.287 | +| explained_variance | -4.42 | +| learning_rate | 0.0001 | +| loss | -0.082 | +| n_updates | 150780 | +| policy_gradient_loss | -0.064 | +| value_loss | 0.00064 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.135 | +| time/ | | +| fps | 309 | +| iterations | 9027 | +| time_elapsed | 29862 | +| total_timesteps | 9243648 | +| train/ | | +| approx_kl | 3.9365559 | +| clip_fraction | 0.455 | +| clip_range | 0.2 | +| entropy_loss | -0.286 | +| explained_variance | -0.402 | +| learning_rate | 0.0001 | +| loss | -0.076 | +| n_updates | 150790 | +| policy_gradient_loss | -0.0628 | +| value_loss | 0.000748 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.136 | +| time/ | | +| fps | 309 | +| iterations | 9028 | +| time_elapsed | 29866 | +| total_timesteps | 9244672 | +| train/ | | +| approx_kl | 2.5563169 | +| clip_fraction | 0.448 | +| clip_range | 0.2 | +| entropy_loss | -0.287 | +| explained_variance | -0.709 | +| learning_rate | 0.0001 | +| loss | -0.0673 | +| n_updates | 150800 | +| policy_gradient_loss | -0.0624 | +| value_loss | 0.000727 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.136 | +| time/ | | +| fps | 309 | +| iterations | 9029 | +| time_elapsed | 29869 | +| total_timesteps | 9245696 | +| train/ | | +| approx_kl | 2.4373388 | +| clip_fraction | 0.451 | +| clip_range | 0.2 | +| entropy_loss | -0.302 | +| explained_variance | -2.19 | +| learning_rate | 0.0001 | +| loss | -0.113 | +| n_updates | 150810 | +| policy_gradient_loss | -0.0598 | +| value_loss | 0.000413 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.136 | +| time/ | | +| fps | 309 | +| iterations | 9030 | +| time_elapsed | 29873 | +| total_timesteps | 9246720 | +| train/ | | +| approx_kl | 2.183745 | +| clip_fraction | 0.443 | +| clip_range | 0.2 | +| entropy_loss | -0.306 | +| explained_variance | -1.34 | +| learning_rate | 0.0001 | +| loss | -0.088 | +| n_updates | 150820 | +| policy_gradient_loss | -0.0664 | +| value_loss | 0.000458 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.14 | +| time/ | | +| fps | 309 | +| iterations | 9031 | +| time_elapsed | 29876 | +| total_timesteps | 9247744 | +| train/ | | +| approx_kl | 2.9261565 | +| clip_fraction | 0.461 | +| clip_range | 0.2 | +| entropy_loss | -0.284 | +| explained_variance | -1.83 | +| learning_rate | 0.0001 | +| loss | -0.111 | +| n_updates | 150830 | +| policy_gradient_loss | -0.0685 | +| value_loss | 0.00052 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.14 | +| time/ | | +| fps | 309 | +| iterations | 9032 | +| time_elapsed | 29880 | +| total_timesteps | 9248768 | +| train/ | | +| approx_kl | 2.8227997 | +| clip_fraction | 0.459 | +| clip_range | 0.2 | +| entropy_loss | -0.286 | +| explained_variance | -1.31 | +| learning_rate | 0.0001 | +| loss | -0.0875 | +| n_updates | 150840 | +| policy_gradient_loss | -0.0655 | +| value_loss | 0.000833 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.143 | +| time/ | | +| fps | 309 | +| iterations | 9033 | +| time_elapsed | 29883 | +| total_timesteps | 9249792 | +| train/ | | +| approx_kl | 2.516098 | +| clip_fraction | 0.476 | +| clip_range | 0.2 | +| entropy_loss | -0.322 | +| explained_variance | -1.83 | +| learning_rate | 0.0001 | +| loss | -0.0999 | +| n_updates | 150850 | +| policy_gradient_loss | -0.0676 | +| value_loss | 0.000468 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.147 | +| time/ | | +| fps | 309 | +| iterations | 9034 | +| time_elapsed | 29886 | +| total_timesteps | 9250816 | +| train/ | | +| approx_kl | 2.4861562 | +| clip_fraction | 0.46 | +| clip_range | 0.2 | +| entropy_loss | -0.309 | +| explained_variance | -1.56 | +| learning_rate | 0.0001 | +| loss | -0.0672 | +| n_updates | 150860 | +| policy_gradient_loss | -0.0605 | +| value_loss | 0.000454 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.154 | +| time/ | | +| fps | 309 | +| iterations | 9035 | +| time_elapsed | 29890 | +| total_timesteps | 9251840 | +| train/ | | +| approx_kl | 2.3877482 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.345 | +| explained_variance | -0.571 | +| learning_rate | 0.0001 | +| loss | -0.0633 | +| n_updates | 150870 | +| policy_gradient_loss | -0.0665 | +| value_loss | 0.000804 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.154 | +| time/ | | +| fps | 309 | +| iterations | 9036 | +| time_elapsed | 29893 | +| total_timesteps | 9252864 | +| train/ | | +| approx_kl | 3.0106435 | +| clip_fraction | 0.496 | +| clip_range | 0.2 | +| entropy_loss | -0.327 | +| explained_variance | -1.53 | +| learning_rate | 0.0001 | +| loss | -0.0803 | +| n_updates | 150880 | +| policy_gradient_loss | -0.0724 | +| value_loss | 0.00083 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.156 | +| time/ | | +| fps | 309 | +| iterations | 9037 | +| time_elapsed | 29896 | +| total_timesteps | 9253888 | +| train/ | | +| approx_kl | 2.820788 | +| clip_fraction | 0.476 | +| clip_range | 0.2 | +| entropy_loss | -0.306 | +| explained_variance | -1.64 | +| learning_rate | 0.0001 | +| loss | -0.0977 | +| n_updates | 150890 | +| policy_gradient_loss | -0.0709 | +| value_loss | 0.000605 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.156 | +| time/ | | +| fps | 309 | +| iterations | 9038 | +| time_elapsed | 29900 | +| total_timesteps | 9254912 | +| train/ | | +| approx_kl | 2.8538008 | +| clip_fraction | 0.468 | +| clip_range | 0.2 | +| entropy_loss | -0.317 | +| explained_variance | -1.44 | +| learning_rate | 0.0001 | +| loss | -0.0749 | +| n_updates | 150900 | +| policy_gradient_loss | -0.0649 | +| value_loss | 0.00052 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.161 | +| time/ | | +| fps | 309 | +| iterations | 9039 | +| time_elapsed | 29903 | +| total_timesteps | 9255936 | +| train/ | | +| approx_kl | 3.6546621 | +| clip_fraction | 0.463 | +| clip_range | 0.2 | +| entropy_loss | -0.304 | +| explained_variance | -1.17 | +| learning_rate | 0.0001 | +| loss | -0.0806 | +| n_updates | 150910 | +| policy_gradient_loss | -0.0679 | +| value_loss | 0.000435 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.164 | +| time/ | | +| fps | 309 | +| iterations | 9040 | +| time_elapsed | 29906 | +| total_timesteps | 9256960 | +| train/ | | +| approx_kl | 2.644262 | +| clip_fraction | 0.458 | +| clip_range | 0.2 | +| entropy_loss | -0.305 | +| explained_variance | -1.89 | +| learning_rate | 0.0001 | +| loss | -0.0897 | +| n_updates | 150920 | +| policy_gradient_loss | -0.071 | +| value_loss | 0.000616 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.163 | +| time/ | | +| fps | 309 | +| iterations | 9041 | +| time_elapsed | 29909 | +| total_timesteps | 9257984 | +| train/ | | +| approx_kl | 2.630587 | +| clip_fraction | 0.474 | +| clip_range | 0.2 | +| entropy_loss | -0.312 | +| explained_variance | -1.42 | +| learning_rate | 0.0001 | +| loss | -0.0889 | +| n_updates | 150930 | +| policy_gradient_loss | -0.0656 | +| value_loss | 0.000562 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.163 | +| time/ | | +| fps | 309 | +| iterations | 9042 | +| time_elapsed | 29913 | +| total_timesteps | 9259008 | +| train/ | | +| approx_kl | 1.9956616 | +| clip_fraction | 0.442 | +| clip_range | 0.2 | +| entropy_loss | -0.306 | +| explained_variance | -1.17 | +| learning_rate | 0.0001 | +| loss | -0.0942 | +| n_updates | 150940 | +| policy_gradient_loss | -0.0674 | +| value_loss | 0.000531 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.163 | +| time/ | | +| fps | 309 | +| iterations | 9043 | +| time_elapsed | 29916 | +| total_timesteps | 9260032 | +| train/ | | +| approx_kl | 2.435584 | +| clip_fraction | 0.4 | +| clip_range | 0.2 | +| entropy_loss | -0.253 | +| explained_variance | -0.435 | +| learning_rate | 0.0001 | +| loss | -0.0615 | +| n_updates | 150950 | +| policy_gradient_loss | -0.0481 | +| value_loss | 0.000397 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.167 | +| time/ | | +| fps | 309 | +| iterations | 9044 | +| time_elapsed | 29919 | +| total_timesteps | 9261056 | +| train/ | | +| approx_kl | 3.3230138 | +| clip_fraction | 0.473 | +| clip_range | 0.2 | +| entropy_loss | -0.293 | +| explained_variance | -3.57 | +| learning_rate | 0.0001 | +| loss | -0.0455 | +| n_updates | 150960 | +| policy_gradient_loss | -0.0608 | +| value_loss | 0.000602 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.167 | +| time/ | | +| fps | 309 | +| iterations | 9045 | +| time_elapsed | 29923 | +| total_timesteps | 9262080 | +| train/ | | +| approx_kl | 2.4362335 | +| clip_fraction | 0.489 | +| clip_range | 0.2 | +| entropy_loss | -0.326 | +| explained_variance | -1.85 | +| learning_rate | 0.0001 | +| loss | -0.0779 | +| n_updates | 150970 | +| policy_gradient_loss | -0.0668 | +| value_loss | 0.00049 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.168 | +| time/ | | +| fps | 309 | +| iterations | 9046 | +| time_elapsed | 29926 | +| total_timesteps | 9263104 | +| train/ | | +| approx_kl | 2.8366487 | +| clip_fraction | 0.491 | +| clip_range | 0.2 | +| entropy_loss | -0.366 | +| explained_variance | -1.67 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 150980 | +| policy_gradient_loss | -0.0641 | +| value_loss | 0.000591 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.168 | +| time/ | | +| fps | 309 | +| iterations | 9047 | +| time_elapsed | 29929 | +| total_timesteps | 9264128 | +| train/ | | +| approx_kl | 2.4526308 | +| clip_fraction | 0.43 | +| clip_range | 0.2 | +| entropy_loss | -0.272 | +| explained_variance | -1.95 | +| learning_rate | 0.0001 | +| loss | -0.0835 | +| n_updates | 150990 | +| policy_gradient_loss | -0.063 | +| value_loss | 0.000513 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.17 | +| time/ | | +| fps | 309 | +| iterations | 9048 | +| time_elapsed | 29933 | +| total_timesteps | 9265152 | +| train/ | | +| approx_kl | 4.6398487 | +| clip_fraction | 0.464 | +| clip_range | 0.2 | +| entropy_loss | -0.302 | +| explained_variance | -3.45 | +| learning_rate | 0.0001 | +| loss | -0.0993 | +| n_updates | 151000 | +| policy_gradient_loss | -0.0662 | +| value_loss | 0.000526 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.17 | +| time/ | | +| fps | 309 | +| iterations | 9049 | +| time_elapsed | 29936 | +| total_timesteps | 9266176 | +| train/ | | +| approx_kl | 6.7132087 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.312 | +| explained_variance | -1.63 | +| learning_rate | 0.0001 | +| loss | -0.094 | +| n_updates | 151010 | +| policy_gradient_loss | -0.0706 | +| value_loss | 0.000669 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.169 | +| time/ | | +| fps | 309 | +| iterations | 9050 | +| time_elapsed | 29939 | +| total_timesteps | 9267200 | +| train/ | | +| approx_kl | 2.4949307 | +| clip_fraction | 0.464 | +| clip_range | 0.2 | +| entropy_loss | -0.313 | +| explained_variance | -1.37 | +| learning_rate | 0.0001 | +| loss | -0.0673 | +| n_updates | 151020 | +| policy_gradient_loss | -0.0643 | +| value_loss | 0.000586 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.172 | +| time/ | | +| fps | 309 | +| iterations | 9051 | +| time_elapsed | 29943 | +| total_timesteps | 9268224 | +| train/ | | +| approx_kl | 3.277096 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.316 | +| explained_variance | -1.07 | +| learning_rate | 0.0001 | +| loss | -0.0943 | +| n_updates | 151030 | +| policy_gradient_loss | -0.0684 | +| value_loss | 0.000545 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.173 | +| time/ | | +| fps | 309 | +| iterations | 9052 | +| time_elapsed | 29946 | +| total_timesteps | 9269248 | +| train/ | | +| approx_kl | 2.3900247 | +| clip_fraction | 0.444 | +| clip_range | 0.2 | +| entropy_loss | -0.309 | +| explained_variance | -2.47 | +| learning_rate | 0.0001 | +| loss | -0.0726 | +| n_updates | 151040 | +| policy_gradient_loss | -0.0666 | +| value_loss | 0.000511 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.175 | +| time/ | | +| fps | 309 | +| iterations | 9053 | +| time_elapsed | 29949 | +| total_timesteps | 9270272 | +| train/ | | +| approx_kl | 2.5156775 | +| clip_fraction | 0.466 | +| clip_range | 0.2 | +| entropy_loss | -0.335 | +| explained_variance | -2.39 | +| learning_rate | 0.0001 | +| loss | -0.0871 | +| n_updates | 151050 | +| policy_gradient_loss | -0.069 | +| value_loss | 0.000613 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.175 | +| time/ | | +| fps | 309 | +| iterations | 9054 | +| time_elapsed | 29952 | +| total_timesteps | 9271296 | +| train/ | | +| approx_kl | 2.9955015 | +| clip_fraction | 0.49 | +| clip_range | 0.2 | +| entropy_loss | -0.317 | +| explained_variance | -1.15 | +| learning_rate | 0.0001 | +| loss | -0.074 | +| n_updates | 151060 | +| policy_gradient_loss | -0.0664 | +| value_loss | 0.00059 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.184 | +| time/ | | +| fps | 309 | +| iterations | 9055 | +| time_elapsed | 29955 | +| total_timesteps | 9272320 | +| train/ | | +| approx_kl | 2.2620854 | +| clip_fraction | 0.467 | +| clip_range | 0.2 | +| entropy_loss | -0.321 | +| explained_variance | -1.86 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 151070 | +| policy_gradient_loss | -0.0649 | +| value_loss | 0.000536 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.187 | +| time/ | | +| fps | 309 | +| iterations | 9056 | +| time_elapsed | 29959 | +| total_timesteps | 9273344 | +| train/ | | +| approx_kl | 1.9881096 | +| clip_fraction | 0.486 | +| clip_range | 0.2 | +| entropy_loss | -0.363 | +| explained_variance | -0.811 | +| learning_rate | 0.0001 | +| loss | -0.0588 | +| n_updates | 151080 | +| policy_gradient_loss | -0.0613 | +| value_loss | 0.00068 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.191 | +| time/ | | +| fps | 309 | +| iterations | 9057 | +| time_elapsed | 29962 | +| total_timesteps | 9274368 | +| train/ | | +| approx_kl | 2.7662187 | +| clip_fraction | 0.452 | +| clip_range | 0.2 | +| entropy_loss | -0.286 | +| explained_variance | -1.25 | +| learning_rate | 0.0001 | +| loss | -0.105 | +| n_updates | 151090 | +| policy_gradient_loss | -0.0647 | +| value_loss | 0.000941 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.191 | +| time/ | | +| fps | 309 | +| iterations | 9058 | +| time_elapsed | 29965 | +| total_timesteps | 9275392 | +| train/ | | +| approx_kl | 2.278102 | +| clip_fraction | 0.442 | +| clip_range | 0.2 | +| entropy_loss | -0.298 | +| explained_variance | -2.08 | +| learning_rate | 0.0001 | +| loss | -0.0912 | +| n_updates | 151100 | +| policy_gradient_loss | -0.0632 | +| value_loss | 0.000648 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.19 | +| time/ | | +| fps | 309 | +| iterations | 9059 | +| time_elapsed | 29968 | +| total_timesteps | 9276416 | +| train/ | | +| approx_kl | 3.082264 | +| clip_fraction | 0.46 | +| clip_range | 0.2 | +| entropy_loss | -0.327 | +| explained_variance | -1.23 | +| learning_rate | 0.0001 | +| loss | -0.092 | +| n_updates | 151110 | +| policy_gradient_loss | -0.0633 | +| value_loss | 0.000722 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.191 | +| time/ | | +| fps | 309 | +| iterations | 9060 | +| time_elapsed | 29971 | +| total_timesteps | 9277440 | +| train/ | | +| approx_kl | 43.19232 | +| clip_fraction | 0.429 | +| clip_range | 0.2 | +| entropy_loss | -0.283 | +| explained_variance | -2.03 | +| learning_rate | 0.0001 | +| loss | -0.0585 | +| n_updates | 151120 | +| policy_gradient_loss | -0.0549 | +| value_loss | 0.0006 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.191 | +| time/ | | +| fps | 309 | +| iterations | 9061 | +| time_elapsed | 29975 | +| total_timesteps | 9278464 | +| train/ | | +| approx_kl | 2.5107284 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.331 | +| explained_variance | -1.38 | +| learning_rate | 0.0001 | +| loss | -0.0769 | +| n_updates | 151130 | +| policy_gradient_loss | -0.064 | +| value_loss | 0.00051 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.193 | +| time/ | | +| fps | 309 | +| iterations | 9062 | +| time_elapsed | 29978 | +| total_timesteps | 9279488 | +| train/ | | +| approx_kl | 3.1028047 | +| clip_fraction | 0.478 | +| clip_range | 0.2 | +| entropy_loss | -0.329 | +| explained_variance | -1.73 | +| learning_rate | 0.0001 | +| loss | -0.0788 | +| n_updates | 151140 | +| policy_gradient_loss | -0.0698 | +| value_loss | 0.00053 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.197 | +| time/ | | +| fps | 309 | +| iterations | 9063 | +| time_elapsed | 29981 | +| total_timesteps | 9280512 | +| train/ | | +| approx_kl | 2.3055615 | +| clip_fraction | 0.44 | +| clip_range | 0.2 | +| entropy_loss | -0.332 | +| explained_variance | -1 | +| learning_rate | 0.0001 | +| loss | -0.0871 | +| n_updates | 151150 | +| policy_gradient_loss | -0.0646 | +| value_loss | 0.000457 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.197 | +| time/ | | +| fps | 309 | +| iterations | 9064 | +| time_elapsed | 29985 | +| total_timesteps | 9281536 | +| train/ | | +| approx_kl | 2.5911725 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.322 | +| explained_variance | -0.724 | +| learning_rate | 0.0001 | +| loss | -0.0756 | +| n_updates | 151160 | +| policy_gradient_loss | -0.0657 | +| value_loss | 0.000709 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.199 | +| time/ | | +| fps | 309 | +| iterations | 9065 | +| time_elapsed | 29988 | +| total_timesteps | 9282560 | +| train/ | | +| approx_kl | 2.4523764 | +| clip_fraction | 0.464 | +| clip_range | 0.2 | +| entropy_loss | -0.321 | +| explained_variance | -2.6 | +| learning_rate | 0.0001 | +| loss | -0.0911 | +| n_updates | 151170 | +| policy_gradient_loss | -0.0696 | +| value_loss | 0.000734 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.199 | +| time/ | | +| fps | 309 | +| iterations | 9066 | +| time_elapsed | 29992 | +| total_timesteps | 9283584 | +| train/ | | +| approx_kl | 3.2878423 | +| clip_fraction | 0.443 | +| clip_range | 0.2 | +| entropy_loss | -0.287 | +| explained_variance | -1.89 | +| learning_rate | 0.0001 | +| loss | -0.0723 | +| n_updates | 151180 | +| policy_gradient_loss | -0.0676 | +| value_loss | 0.000598 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.201 | +| time/ | | +| fps | 309 | +| iterations | 9067 | +| time_elapsed | 29995 | +| total_timesteps | 9284608 | +| train/ | | +| approx_kl | 2.4494605 | +| clip_fraction | 0.493 | +| clip_range | 0.2 | +| entropy_loss | -0.304 | +| explained_variance | -3.85 | +| learning_rate | 0.0001 | +| loss | -0.0766 | +| n_updates | 151190 | +| policy_gradient_loss | -0.0736 | +| value_loss | 0.000369 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.201 | +| time/ | | +| fps | 309 | +| iterations | 9068 | +| time_elapsed | 29998 | +| total_timesteps | 9285632 | +| train/ | | +| approx_kl | 2.6924286 | +| clip_fraction | 0.493 | +| clip_range | 0.2 | +| entropy_loss | -0.327 | +| explained_variance | -0.738 | +| learning_rate | 0.0001 | +| loss | -0.107 | +| n_updates | 151200 | +| policy_gradient_loss | -0.0741 | +| value_loss | 0.000486 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.204 | +| time/ | | +| fps | 309 | +| iterations | 9069 | +| time_elapsed | 30002 | +| total_timesteps | 9286656 | +| train/ | | +| approx_kl | 2.2793703 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.322 | +| explained_variance | -1.99 | +| learning_rate | 0.0001 | +| loss | -0.0939 | +| n_updates | 151210 | +| policy_gradient_loss | -0.0659 | +| value_loss | 0.000664 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.203 | +| time/ | | +| fps | 309 | +| iterations | 9070 | +| time_elapsed | 30005 | +| total_timesteps | 9287680 | +| train/ | | +| approx_kl | 2.8359623 | +| clip_fraction | 0.484 | +| clip_range | 0.2 | +| entropy_loss | -0.322 | +| explained_variance | -1.01 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 151220 | +| policy_gradient_loss | -0.0725 | +| value_loss | 0.000436 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.203 | +| time/ | | +| fps | 309 | +| iterations | 9071 | +| time_elapsed | 30009 | +| total_timesteps | 9288704 | +| train/ | | +| approx_kl | 2.302596 | +| clip_fraction | 0.459 | +| clip_range | 0.2 | +| entropy_loss | -0.298 | +| explained_variance | -2.21 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 151230 | +| policy_gradient_loss | -0.0627 | +| value_loss | 0.000424 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.209 | +| time/ | | +| fps | 309 | +| iterations | 9072 | +| time_elapsed | 30012 | +| total_timesteps | 9289728 | +| train/ | | +| approx_kl | 2.4105687 | +| clip_fraction | 0.465 | +| clip_range | 0.2 | +| entropy_loss | -0.318 | +| explained_variance | -1.26 | +| learning_rate | 0.0001 | +| loss | -0.089 | +| n_updates | 151240 | +| policy_gradient_loss | -0.0598 | +| value_loss | 0.00062 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.21 | +| time/ | | +| fps | 309 | +| iterations | 9073 | +| time_elapsed | 30015 | +| total_timesteps | 9290752 | +| train/ | | +| approx_kl | 2.3280802 | +| clip_fraction | 0.496 | +| clip_range | 0.2 | +| entropy_loss | -0.345 | +| explained_variance | -0.705 | +| learning_rate | 0.0001 | +| loss | -0.0433 | +| n_updates | 151250 | +| policy_gradient_loss | -0.0592 | +| value_loss | 0.000776 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.209 | +| time/ | | +| fps | 309 | +| iterations | 9074 | +| time_elapsed | 30019 | +| total_timesteps | 9291776 | +| train/ | | +| approx_kl | 2.9489346 | +| clip_fraction | 0.445 | +| clip_range | 0.2 | +| entropy_loss | -0.317 | +| explained_variance | -2.19 | +| learning_rate | 0.0001 | +| loss | -0.0731 | +| n_updates | 151260 | +| policy_gradient_loss | -0.0646 | +| value_loss | 0.000649 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.209 | +| time/ | | +| fps | 309 | +| iterations | 9075 | +| time_elapsed | 30022 | +| total_timesteps | 9292800 | +| train/ | | +| approx_kl | 2.5254936 | +| clip_fraction | 0.45 | +| clip_range | 0.2 | +| entropy_loss | -0.294 | +| explained_variance | -1.76 | +| learning_rate | 0.0001 | +| loss | -0.113 | +| n_updates | 151270 | +| policy_gradient_loss | -0.059 | +| value_loss | 0.000745 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.213 | +| time/ | | +| fps | 309 | +| iterations | 9076 | +| time_elapsed | 30025 | +| total_timesteps | 9293824 | +| train/ | | +| approx_kl | 2.6198506 | +| clip_fraction | 0.467 | +| clip_range | 0.2 | +| entropy_loss | -0.285 | +| explained_variance | -2.28 | +| learning_rate | 0.0001 | +| loss | -0.0899 | +| n_updates | 151280 | +| policy_gradient_loss | -0.0685 | +| value_loss | 0.000683 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.214 | +| time/ | | +| fps | 309 | +| iterations | 9077 | +| time_elapsed | 30028 | +| total_timesteps | 9294848 | +| train/ | | +| approx_kl | 2.518121 | +| clip_fraction | 0.47 | +| clip_range | 0.2 | +| entropy_loss | -0.348 | +| explained_variance | -0.997 | +| learning_rate | 0.0001 | +| loss | -0.0498 | +| n_updates | 151290 | +| policy_gradient_loss | -0.06 | +| value_loss | 0.000555 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.214 | +| time/ | | +| fps | 309 | +| iterations | 9078 | +| time_elapsed | 30031 | +| total_timesteps | 9295872 | +| train/ | | +| approx_kl | 2.127856 | +| clip_fraction | 0.472 | +| clip_range | 0.2 | +| entropy_loss | -0.314 | +| explained_variance | -2.89 | +| learning_rate | 0.0001 | +| loss | -0.0774 | +| n_updates | 151300 | +| policy_gradient_loss | -0.0671 | +| value_loss | 0.00052 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.214 | +| time/ | | +| fps | 309 | +| iterations | 9079 | +| time_elapsed | 30035 | +| total_timesteps | 9296896 | +| train/ | | +| approx_kl | 2.8267663 | +| clip_fraction | 0.489 | +| clip_range | 0.2 | +| entropy_loss | -0.333 | +| explained_variance | -1.05 | +| learning_rate | 0.0001 | +| loss | -0.0862 | +| n_updates | 151310 | +| policy_gradient_loss | -0.0651 | +| value_loss | 0.000658 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.214 | +| time/ | | +| fps | 309 | +| iterations | 9080 | +| time_elapsed | 30038 | +| total_timesteps | 9297920 | +| train/ | | +| approx_kl | 2.6960716 | +| clip_fraction | 0.463 | +| clip_range | 0.2 | +| entropy_loss | -0.321 | +| explained_variance | -2.69 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 151320 | +| policy_gradient_loss | -0.0645 | +| value_loss | 0.000648 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.218 | +| time/ | | +| fps | 309 | +| iterations | 9081 | +| time_elapsed | 30041 | +| total_timesteps | 9298944 | +| train/ | | +| approx_kl | 2.3360882 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.33 | +| explained_variance | -1.34 | +| learning_rate | 0.0001 | +| loss | -0.0825 | +| n_updates | 151330 | +| policy_gradient_loss | -0.0639 | +| value_loss | 0.000422 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.218 | +| time/ | | +| fps | 309 | +| iterations | 9082 | +| time_elapsed | 30044 | +| total_timesteps | 9299968 | +| train/ | | +| approx_kl | 7.477767 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.325 | +| explained_variance | -2.1 | +| learning_rate | 0.0001 | +| loss | -0.077 | +| n_updates | 151340 | +| policy_gradient_loss | -0.0747 | +| value_loss | 0.000349 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.224 | +| time/ | | +| fps | 309 | +| iterations | 9083 | +| time_elapsed | 30048 | +| total_timesteps | 9300992 | +| train/ | | +| approx_kl | 2.474102 | +| clip_fraction | 0.479 | +| clip_range | 0.2 | +| entropy_loss | -0.343 | +| explained_variance | -0.669 | +| learning_rate | 0.0001 | +| loss | -0.0942 | +| n_updates | 151350 | +| policy_gradient_loss | -0.0692 | +| value_loss | 0.00053 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.228 | +| time/ | | +| fps | 309 | +| iterations | 9084 | +| time_elapsed | 30051 | +| total_timesteps | 9302016 | +| train/ | | +| approx_kl | 3.5185952 | +| clip_fraction | 0.46 | +| clip_range | 0.2 | +| entropy_loss | -0.304 | +| explained_variance | -1.34 | +| learning_rate | 0.0001 | +| loss | -0.092 | +| n_updates | 151360 | +| policy_gradient_loss | -0.0698 | +| value_loss | 0.00103 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.228 | +| time/ | | +| fps | 309 | +| iterations | 9085 | +| time_elapsed | 30054 | +| total_timesteps | 9303040 | +| train/ | | +| approx_kl | 2.5187492 | +| clip_fraction | 0.464 | +| clip_range | 0.2 | +| entropy_loss | -0.309 | +| explained_variance | -1.22 | +| learning_rate | 0.0001 | +| loss | -0.0987 | +| n_updates | 151370 | +| policy_gradient_loss | -0.0731 | +| value_loss | 0.000766 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.232 | +| time/ | | +| fps | 309 | +| iterations | 9086 | +| time_elapsed | 30058 | +| total_timesteps | 9304064 | +| train/ | | +| approx_kl | 1.9248354 | +| clip_fraction | 0.464 | +| clip_range | 0.2 | +| entropy_loss | -0.341 | +| explained_variance | -1.15 | +| learning_rate | 0.0001 | +| loss | -0.11 | +| n_updates | 151380 | +| policy_gradient_loss | -0.0587 | +| value_loss | 0.000737 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.225 | +| time/ | | +| fps | 309 | +| iterations | 9087 | +| time_elapsed | 30061 | +| total_timesteps | 9305088 | +| train/ | | +| approx_kl | 2.228323 | +| clip_fraction | 0.446 | +| clip_range | 0.2 | +| entropy_loss | -0.319 | +| explained_variance | -1.66 | +| learning_rate | 0.0001 | +| loss | -0.0763 | +| n_updates | 151390 | +| policy_gradient_loss | -0.0564 | +| value_loss | 0.000451 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.225 | +| time/ | | +| fps | 309 | +| iterations | 9088 | +| time_elapsed | 30064 | +| total_timesteps | 9306112 | +| train/ | | +| approx_kl | 2.0924058 | +| clip_fraction | 0.473 | +| clip_range | 0.2 | +| entropy_loss | -0.322 | +| explained_variance | -0.78 | +| learning_rate | 0.0001 | +| loss | -0.074 | +| n_updates | 151400 | +| policy_gradient_loss | -0.0625 | +| value_loss | 0.000532 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.224 | +| time/ | | +| fps | 309 | +| iterations | 9089 | +| time_elapsed | 30068 | +| total_timesteps | 9307136 | +| train/ | | +| approx_kl | 2.0858743 | +| clip_fraction | 0.477 | +| clip_range | 0.2 | +| entropy_loss | -0.358 | +| explained_variance | -1.55 | +| learning_rate | 0.0001 | +| loss | -0.0976 | +| n_updates | 151410 | +| policy_gradient_loss | -0.0711 | +| value_loss | 0.000475 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.223 | +| time/ | | +| fps | 309 | +| iterations | 9090 | +| time_elapsed | 30071 | +| total_timesteps | 9308160 | +| train/ | | +| approx_kl | 3.2197852 | +| clip_fraction | 0.449 | +| clip_range | 0.2 | +| entropy_loss | -0.293 | +| explained_variance | -2.4 | +| learning_rate | 0.0001 | +| loss | -0.0762 | +| n_updates | 151420 | +| policy_gradient_loss | -0.0705 | +| value_loss | 0.000469 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.223 | +| time/ | | +| fps | 309 | +| iterations | 9091 | +| time_elapsed | 30074 | +| total_timesteps | 9309184 | +| train/ | | +| approx_kl | 2.47087 | +| clip_fraction | 0.473 | +| clip_range | 0.2 | +| entropy_loss | -0.332 | +| explained_variance | -1.44 | +| learning_rate | 0.0001 | +| loss | -0.0893 | +| n_updates | 151430 | +| policy_gradient_loss | -0.066 | +| value_loss | 0.000462 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.223 | +| time/ | | +| fps | 309 | +| iterations | 9092 | +| time_elapsed | 30077 | +| total_timesteps | 9310208 | +| train/ | | +| approx_kl | 12.499495 | +| clip_fraction | 0.515 | +| clip_range | 0.2 | +| entropy_loss | -0.372 | +| explained_variance | -0.827 | +| learning_rate | 0.0001 | +| loss | -0.107 | +| n_updates | 151440 | +| policy_gradient_loss | -0.0666 | +| value_loss | 0.000581 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.22 | +| time/ | | +| fps | 309 | +| iterations | 9093 | +| time_elapsed | 30081 | +| total_timesteps | 9311232 | +| train/ | | +| approx_kl | 2.2870176 | +| clip_fraction | 0.476 | +| clip_range | 0.2 | +| entropy_loss | -0.346 | +| explained_variance | -1.12 | +| learning_rate | 0.0001 | +| loss | -0.0867 | +| n_updates | 151450 | +| policy_gradient_loss | -0.0668 | +| value_loss | 0.000671 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.223 | +| time/ | | +| fps | 309 | +| iterations | 9094 | +| time_elapsed | 30084 | +| total_timesteps | 9312256 | +| train/ | | +| approx_kl | 2.7312465 | +| clip_fraction | 0.476 | +| clip_range | 0.2 | +| entropy_loss | -0.324 | +| explained_variance | -2.17 | +| learning_rate | 0.0001 | +| loss | -0.0841 | +| n_updates | 151460 | +| policy_gradient_loss | -0.0659 | +| value_loss | 0.000665 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.223 | +| time/ | | +| fps | 309 | +| iterations | 9095 | +| time_elapsed | 30087 | +| total_timesteps | 9313280 | +| train/ | | +| approx_kl | 1.8465811 | +| clip_fraction | 0.453 | +| clip_range | 0.2 | +| entropy_loss | -0.34 | +| explained_variance | -1.76 | +| learning_rate | 0.0001 | +| loss | -0.097 | +| n_updates | 151470 | +| policy_gradient_loss | -0.0659 | +| value_loss | 0.000557 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.224 | +| time/ | | +| fps | 309 | +| iterations | 9096 | +| time_elapsed | 30090 | +| total_timesteps | 9314304 | +| train/ | | +| approx_kl | 7.801225 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.334 | +| explained_variance | -2.02 | +| learning_rate | 0.0001 | +| loss | -0.0977 | +| n_updates | 151480 | +| policy_gradient_loss | -0.0689 | +| value_loss | 0.00061 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.223 | +| time/ | | +| fps | 309 | +| iterations | 9097 | +| time_elapsed | 30093 | +| total_timesteps | 9315328 | +| train/ | | +| approx_kl | 2.4317636 | +| clip_fraction | 0.466 | +| clip_range | 0.2 | +| entropy_loss | -0.312 | +| explained_variance | -1.12 | +| learning_rate | 0.0001 | +| loss | -0.084 | +| n_updates | 151490 | +| policy_gradient_loss | -0.0651 | +| value_loss | 0.000701 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.225 | +| time/ | | +| fps | 309 | +| iterations | 9098 | +| time_elapsed | 30096 | +| total_timesteps | 9316352 | +| train/ | | +| approx_kl | 3.9961104 | +| clip_fraction | 0.465 | +| clip_range | 0.2 | +| entropy_loss | -0.317 | +| explained_variance | -4.39 | +| learning_rate | 0.0001 | +| loss | -0.0941 | +| n_updates | 151500 | +| policy_gradient_loss | -0.0578 | +| value_loss | 0.000491 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.233 | +| time/ | | +| fps | 309 | +| iterations | 9099 | +| time_elapsed | 30100 | +| total_timesteps | 9317376 | +| train/ | | +| approx_kl | 2.5490575 | +| clip_fraction | 0.453 | +| clip_range | 0.2 | +| entropy_loss | -0.296 | +| explained_variance | -1.01 | +| learning_rate | 0.0001 | +| loss | -0.0574 | +| n_updates | 151510 | +| policy_gradient_loss | -0.0561 | +| value_loss | 0.000409 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.233 | +| time/ | | +| fps | 309 | +| iterations | 9100 | +| time_elapsed | 30103 | +| total_timesteps | 9318400 | +| train/ | | +| approx_kl | 2.4326458 | +| clip_fraction | 0.435 | +| clip_range | 0.2 | +| entropy_loss | -0.292 | +| explained_variance | -0.534 | +| learning_rate | 0.0001 | +| loss | -0.0594 | +| n_updates | 151520 | +| policy_gradient_loss | -0.0613 | +| value_loss | 0.000561 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.234 | +| time/ | | +| fps | 309 | +| iterations | 9101 | +| time_elapsed | 30107 | +| total_timesteps | 9319424 | +| train/ | | +| approx_kl | 2.1473012 | +| clip_fraction | 0.501 | +| clip_range | 0.2 | +| entropy_loss | -0.361 | +| explained_variance | -3.17 | +| learning_rate | 0.0001 | +| loss | -0.0476 | +| n_updates | 151530 | +| policy_gradient_loss | -0.0623 | +| value_loss | 0.000533 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.234 | +| time/ | | +| fps | 309 | +| iterations | 9102 | +| time_elapsed | 30110 | +| total_timesteps | 9320448 | +| train/ | | +| approx_kl | 2.2795153 | +| clip_fraction | 0.436 | +| clip_range | 0.2 | +| entropy_loss | -0.309 | +| explained_variance | -0.709 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 151540 | +| policy_gradient_loss | -0.056 | +| value_loss | 0.000599 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.237 | +| time/ | | +| fps | 309 | +| iterations | 9103 | +| time_elapsed | 30114 | +| total_timesteps | 9321472 | +| train/ | | +| approx_kl | 2.3967218 | +| clip_fraction | 0.484 | +| clip_range | 0.2 | +| entropy_loss | -0.347 | +| explained_variance | -3.88 | +| learning_rate | 0.0001 | +| loss | -0.0812 | +| n_updates | 151550 | +| policy_gradient_loss | -0.0693 | +| value_loss | 0.000425 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.237 | +| time/ | | +| fps | 309 | +| iterations | 9104 | +| time_elapsed | 30117 | +| total_timesteps | 9322496 | +| train/ | | +| approx_kl | 3.207151 | +| clip_fraction | 0.45 | +| clip_range | 0.2 | +| entropy_loss | -0.269 | +| explained_variance | -5.71 | +| learning_rate | 0.0001 | +| loss | -0.0962 | +| n_updates | 151560 | +| policy_gradient_loss | -0.0594 | +| value_loss | 0.000338 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.237 | +| time/ | | +| fps | 309 | +| iterations | 9105 | +| time_elapsed | 30120 | +| total_timesteps | 9323520 | +| train/ | | +| approx_kl | 1.9797612 | +| clip_fraction | 0.482 | +| clip_range | 0.2 | +| entropy_loss | -0.342 | +| explained_variance | -0.824 | +| learning_rate | 0.0001 | +| loss | -0.0799 | +| n_updates | 151570 | +| policy_gradient_loss | -0.0683 | +| value_loss | 0.000415 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.239 | +| time/ | | +| fps | 309 | +| iterations | 9106 | +| time_elapsed | 30124 | +| total_timesteps | 9324544 | +| train/ | | +| approx_kl | 3.2356324 | +| clip_fraction | 0.463 | +| clip_range | 0.2 | +| entropy_loss | -0.308 | +| explained_variance | -2.49 | +| learning_rate | 0.0001 | +| loss | -0.0891 | +| n_updates | 151580 | +| policy_gradient_loss | -0.068 | +| value_loss | 0.00053 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.239 | +| time/ | | +| fps | 309 | +| iterations | 9107 | +| time_elapsed | 30127 | +| total_timesteps | 9325568 | +| train/ | | +| approx_kl | 3.0656934 | +| clip_fraction | 0.443 | +| clip_range | 0.2 | +| entropy_loss | -0.285 | +| explained_variance | -0.968 | +| learning_rate | 0.0001 | +| loss | -0.0869 | +| n_updates | 151590 | +| policy_gradient_loss | -0.0659 | +| value_loss | 0.000647 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.245 | +| time/ | | +| fps | 309 | +| iterations | 9108 | +| time_elapsed | 30130 | +| total_timesteps | 9326592 | +| train/ | | +| approx_kl | 2.3704019 | +| clip_fraction | 0.491 | +| clip_range | 0.2 | +| entropy_loss | -0.348 | +| explained_variance | -1.42 | +| learning_rate | 0.0001 | +| loss | -0.0982 | +| n_updates | 151600 | +| policy_gradient_loss | -0.0689 | +| value_loss | 0.000565 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.245 | +| time/ | | +| fps | 309 | +| iterations | 9109 | +| time_elapsed | 30134 | +| total_timesteps | 9327616 | +| train/ | | +| approx_kl | 13.984058 | +| clip_fraction | 0.445 | +| clip_range | 0.2 | +| entropy_loss | -0.296 | +| explained_variance | -2.17 | +| learning_rate | 0.0001 | +| loss | -0.0816 | +| n_updates | 151610 | +| policy_gradient_loss | -0.0647 | +| value_loss | 0.000491 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.245 | +| time/ | | +| fps | 309 | +| iterations | 9110 | +| time_elapsed | 30137 | +| total_timesteps | 9328640 | +| train/ | | +| approx_kl | 2.7378058 | +| clip_fraction | 0.465 | +| clip_range | 0.2 | +| entropy_loss | -0.317 | +| explained_variance | -0.916 | +| learning_rate | 0.0001 | +| loss | -0.0906 | +| n_updates | 151620 | +| policy_gradient_loss | -0.0647 | +| value_loss | 0.00051 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.251 | +| time/ | | +| fps | 309 | +| iterations | 9111 | +| time_elapsed | 30140 | +| total_timesteps | 9329664 | +| train/ | | +| approx_kl | 1.7967451 | +| clip_fraction | 0.47 | +| clip_range | 0.2 | +| entropy_loss | -0.376 | +| explained_variance | -0.285 | +| learning_rate | 0.0001 | +| loss | -0.0718 | +| n_updates | 151630 | +| policy_gradient_loss | -0.056 | +| value_loss | 0.00051 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.255 | +| time/ | | +| fps | 309 | +| iterations | 9112 | +| time_elapsed | 30143 | +| total_timesteps | 9330688 | +| train/ | | +| approx_kl | 2.5336661 | +| clip_fraction | 0.408 | +| clip_range | 0.2 | +| entropy_loss | -0.248 | +| explained_variance | -0.501 | +| learning_rate | 0.0001 | +| loss | -0.0859 | +| n_updates | 151640 | +| policy_gradient_loss | -0.0565 | +| value_loss | 0.000651 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.253 | +| time/ | | +| fps | 309 | +| iterations | 9113 | +| time_elapsed | 30147 | +| total_timesteps | 9331712 | +| train/ | | +| approx_kl | 2.370351 | +| clip_fraction | 0.45 | +| clip_range | 0.2 | +| entropy_loss | -0.353 | +| explained_variance | -2.34 | +| learning_rate | 0.0001 | +| loss | -0.0904 | +| n_updates | 151650 | +| policy_gradient_loss | -0.067 | +| value_loss | 0.000468 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.253 | +| time/ | | +| fps | 309 | +| iterations | 9114 | +| time_elapsed | 30150 | +| total_timesteps | 9332736 | +| train/ | | +| approx_kl | 3.1950517 | +| clip_fraction | 0.438 | +| clip_range | 0.2 | +| entropy_loss | -0.319 | +| explained_variance | -1.24 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 151660 | +| policy_gradient_loss | -0.064 | +| value_loss | 0.000331 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.254 | +| time/ | | +| fps | 309 | +| iterations | 9115 | +| time_elapsed | 30153 | +| total_timesteps | 9333760 | +| train/ | | +| approx_kl | 2.8824124 | +| clip_fraction | 0.529 | +| clip_range | 0.2 | +| entropy_loss | -0.387 | +| explained_variance | -1.69 | +| learning_rate | 0.0001 | +| loss | -0.0625 | +| n_updates | 151670 | +| policy_gradient_loss | -0.0693 | +| value_loss | 0.000579 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.254 | +| time/ | | +| fps | 309 | +| iterations | 9116 | +| time_elapsed | 30156 | +| total_timesteps | 9334784 | +| train/ | | +| approx_kl | 4.217674 | +| clip_fraction | 0.474 | +| clip_range | 0.2 | +| entropy_loss | -0.337 | +| explained_variance | -2.64 | +| learning_rate | 0.0001 | +| loss | -0.0883 | +| n_updates | 151680 | +| policy_gradient_loss | -0.0677 | +| value_loss | 0.000426 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.254 | +| time/ | | +| fps | 309 | +| iterations | 9117 | +| time_elapsed | 30160 | +| total_timesteps | 9335808 | +| train/ | | +| approx_kl | 13.87412 | +| clip_fraction | 0.467 | +| clip_range | 0.2 | +| entropy_loss | -0.348 | +| explained_variance | -1.22 | +| learning_rate | 0.0001 | +| loss | -0.071 | +| n_updates | 151690 | +| policy_gradient_loss | -0.0589 | +| value_loss | 0.000486 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.254 | +| time/ | | +| fps | 309 | +| iterations | 9118 | +| time_elapsed | 30163 | +| total_timesteps | 9336832 | +| train/ | | +| approx_kl | 2.034015 | +| clip_fraction | 0.41 | +| clip_range | 0.2 | +| entropy_loss | -0.315 | +| explained_variance | -1.85 | +| learning_rate | 0.0001 | +| loss | -0.0599 | +| n_updates | 151700 | +| policy_gradient_loss | -0.0529 | +| value_loss | 0.000435 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.255 | +| time/ | | +| fps | 309 | +| iterations | 9119 | +| time_elapsed | 30166 | +| total_timesteps | 9337856 | +| train/ | | +| approx_kl | 2.0771387 | +| clip_fraction | 0.405 | +| clip_range | 0.2 | +| entropy_loss | -0.276 | +| explained_variance | -0.357 | +| learning_rate | 0.0001 | +| loss | -0.0639 | +| n_updates | 151710 | +| policy_gradient_loss | -0.0565 | +| value_loss | 0.000566 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.255 | +| time/ | | +| fps | 309 | +| iterations | 9120 | +| time_elapsed | 30170 | +| total_timesteps | 9338880 | +| train/ | | +| approx_kl | 2.0764675 | +| clip_fraction | 0.442 | +| clip_range | 0.2 | +| entropy_loss | -0.318 | +| explained_variance | -1.27 | +| learning_rate | 0.0001 | +| loss | -0.0905 | +| n_updates | 151720 | +| policy_gradient_loss | -0.0622 | +| value_loss | 0.000563 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.261 | +| time/ | | +| fps | 309 | +| iterations | 9121 | +| time_elapsed | 30173 | +| total_timesteps | 9339904 | +| train/ | | +| approx_kl | 2.341807 | +| clip_fraction | 0.425 | +| clip_range | 0.2 | +| entropy_loss | -0.333 | +| explained_variance | -1.15 | +| learning_rate | 0.0001 | +| loss | -0.0591 | +| n_updates | 151730 | +| policy_gradient_loss | -0.0613 | +| value_loss | 0.000432 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.261 | +| time/ | | +| fps | 309 | +| iterations | 9122 | +| time_elapsed | 30177 | +| total_timesteps | 9340928 | +| train/ | | +| approx_kl | 2.0120764 | +| clip_fraction | 0.459 | +| clip_range | 0.2 | +| entropy_loss | -0.331 | +| explained_variance | -0.753 | +| learning_rate | 0.0001 | +| loss | -0.091 | +| n_updates | 151740 | +| policy_gradient_loss | -0.065 | +| value_loss | 0.000687 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.261 | +| time/ | | +| fps | 309 | +| iterations | 9123 | +| time_elapsed | 30180 | +| total_timesteps | 9341952 | +| train/ | | +| approx_kl | 2.4284782 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.297 | +| explained_variance | -2 | +| learning_rate | 0.0001 | +| loss | -0.0719 | +| n_updates | 151750 | +| policy_gradient_loss | -0.0684 | +| value_loss | 0.000616 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.258 | +| time/ | | +| fps | 309 | +| iterations | 9124 | +| time_elapsed | 30184 | +| total_timesteps | 9342976 | +| train/ | | +| approx_kl | 1.948473 | +| clip_fraction | 0.457 | +| clip_range | 0.2 | +| entropy_loss | -0.321 | +| explained_variance | -1.24 | +| learning_rate | 0.0001 | +| loss | -0.0979 | +| n_updates | 151760 | +| policy_gradient_loss | -0.0683 | +| value_loss | 0.000549 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.26 | +| time/ | | +| fps | 309 | +| iterations | 9125 | +| time_elapsed | 30187 | +| total_timesteps | 9344000 | +| train/ | | +| approx_kl | 1.8943418 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.378 | +| explained_variance | -1.83 | +| learning_rate | 0.0001 | +| loss | -0.0787 | +| n_updates | 151770 | +| policy_gradient_loss | -0.0656 | +| value_loss | 0.000392 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.26 | +| time/ | | +| fps | 309 | +| iterations | 9126 | +| time_elapsed | 30190 | +| total_timesteps | 9345024 | +| train/ | | +| approx_kl | 8.57214 | +| clip_fraction | 0.457 | +| clip_range | 0.2 | +| entropy_loss | -0.37 | +| explained_variance | -0.527 | +| learning_rate | 0.0001 | +| loss | -0.109 | +| n_updates | 151780 | +| policy_gradient_loss | -0.0605 | +| value_loss | 0.000591 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.26 | +| time/ | | +| fps | 309 | +| iterations | 9127 | +| time_elapsed | 30194 | +| total_timesteps | 9346048 | +| train/ | | +| approx_kl | 2.4140973 | +| clip_fraction | 0.47 | +| clip_range | 0.2 | +| entropy_loss | -0.316 | +| explained_variance | -3.01 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 151790 | +| policy_gradient_loss | -0.064 | +| value_loss | 0.000555 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.259 | +| time/ | | +| fps | 309 | +| iterations | 9128 | +| time_elapsed | 30197 | +| total_timesteps | 9347072 | +| train/ | | +| approx_kl | 2.587325 | +| clip_fraction | 0.479 | +| clip_range | 0.2 | +| entropy_loss | -0.319 | +| explained_variance | -2.09 | +| learning_rate | 0.0001 | +| loss | -0.0896 | +| n_updates | 151800 | +| policy_gradient_loss | -0.0704 | +| value_loss | 0.000432 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.258 | +| time/ | | +| fps | 309 | +| iterations | 9129 | +| time_elapsed | 30200 | +| total_timesteps | 9348096 | +| train/ | | +| approx_kl | 2.625958 | +| clip_fraction | 0.45 | +| clip_range | 0.2 | +| entropy_loss | -0.351 | +| explained_variance | -0.693 | +| learning_rate | 0.0001 | +| loss | -0.0542 | +| n_updates | 151810 | +| policy_gradient_loss | -0.0606 | +| value_loss | 0.000765 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.258 | +| time/ | | +| fps | 309 | +| iterations | 9130 | +| time_elapsed | 30203 | +| total_timesteps | 9349120 | +| train/ | | +| approx_kl | 1.941014 | +| clip_fraction | 0.461 | +| clip_range | 0.2 | +| entropy_loss | -0.323 | +| explained_variance | -1.54 | +| learning_rate | 0.0001 | +| loss | -0.089 | +| n_updates | 151820 | +| policy_gradient_loss | -0.0684 | +| value_loss | 0.000576 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.258 | +| time/ | | +| fps | 309 | +| iterations | 9131 | +| time_elapsed | 30206 | +| total_timesteps | 9350144 | +| train/ | | +| approx_kl | 2.6192112 | +| clip_fraction | 0.489 | +| clip_range | 0.2 | +| entropy_loss | -0.337 | +| explained_variance | -1 | +| learning_rate | 0.0001 | +| loss | -0.0751 | +| n_updates | 151830 | +| policy_gradient_loss | -0.0597 | +| value_loss | 0.000506 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.253 | +| time/ | | +| fps | 309 | +| iterations | 9132 | +| time_elapsed | 30210 | +| total_timesteps | 9351168 | +| train/ | | +| approx_kl | 2.3083475 | +| clip_fraction | 0.44 | +| clip_range | 0.2 | +| entropy_loss | -0.326 | +| explained_variance | -2.52 | +| learning_rate | 0.0001 | +| loss | -0.0829 | +| n_updates | 151840 | +| policy_gradient_loss | -0.0672 | +| value_loss | 0.000635 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.256 | +| time/ | | +| fps | 309 | +| iterations | 9133 | +| time_elapsed | 30213 | +| total_timesteps | 9352192 | +| train/ | | +| approx_kl | 2.7542734 | +| clip_fraction | 0.467 | +| clip_range | 0.2 | +| entropy_loss | -0.313 | +| explained_variance | -1.95 | +| learning_rate | 0.0001 | +| loss | -0.0975 | +| n_updates | 151850 | +| policy_gradient_loss | -0.063 | +| value_loss | 0.000489 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.258 | +| time/ | | +| fps | 309 | +| iterations | 9134 | +| time_elapsed | 30216 | +| total_timesteps | 9353216 | +| train/ | | +| approx_kl | 3.7300346 | +| clip_fraction | 0.428 | +| clip_range | 0.2 | +| entropy_loss | -0.282 | +| explained_variance | -1.25 | +| learning_rate | 0.0001 | +| loss | -0.0887 | +| n_updates | 151860 | +| policy_gradient_loss | -0.066 | +| value_loss | 0.000499 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.258 | +| time/ | | +| fps | 309 | +| iterations | 9135 | +| time_elapsed | 30219 | +| total_timesteps | 9354240 | +| train/ | | +| approx_kl | 2.2612967 | +| clip_fraction | 0.428 | +| clip_range | 0.2 | +| entropy_loss | -0.278 | +| explained_variance | -1.18 | +| learning_rate | 0.0001 | +| loss | -0.0767 | +| n_updates | 151870 | +| policy_gradient_loss | -0.0677 | +| value_loss | 0.000641 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.259 | +| time/ | | +| fps | 309 | +| iterations | 9136 | +| time_elapsed | 30223 | +| total_timesteps | 9355264 | +| train/ | | +| approx_kl | 2.9394426 | +| clip_fraction | 0.493 | +| clip_range | 0.2 | +| entropy_loss | -0.377 | +| explained_variance | -2.15 | +| learning_rate | 0.0001 | +| loss | -0.109 | +| n_updates | 151880 | +| policy_gradient_loss | -0.0607 | +| value_loss | 0.000395 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.255 | +| time/ | | +| fps | 309 | +| iterations | 9137 | +| time_elapsed | 30226 | +| total_timesteps | 9356288 | +| train/ | | +| approx_kl | 1.7044066 | +| clip_fraction | 0.409 | +| clip_range | 0.2 | +| entropy_loss | -0.304 | +| explained_variance | -1.2 | +| learning_rate | 0.0001 | +| loss | -0.0559 | +| n_updates | 151890 | +| policy_gradient_loss | -0.0571 | +| value_loss | 0.000445 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.255 | +| time/ | | +| fps | 309 | +| iterations | 9138 | +| time_elapsed | 30230 | +| total_timesteps | 9357312 | +| train/ | | +| approx_kl | 2.2128396 | +| clip_fraction | 0.419 | +| clip_range | 0.2 | +| entropy_loss | -0.293 | +| explained_variance | -1.08 | +| learning_rate | 0.0001 | +| loss | -0.077 | +| n_updates | 151900 | +| policy_gradient_loss | -0.0589 | +| value_loss | 0.000678 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.256 | +| time/ | | +| fps | 309 | +| iterations | 9139 | +| time_elapsed | 30233 | +| total_timesteps | 9358336 | +| train/ | | +| approx_kl | 2.7547686 | +| clip_fraction | 0.512 | +| clip_range | 0.2 | +| entropy_loss | -0.341 | +| explained_variance | -4.07 | +| learning_rate | 0.0001 | +| loss | -0.0502 | +| n_updates | 151910 | +| policy_gradient_loss | -0.0757 | +| value_loss | 0.000466 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.255 | +| time/ | | +| fps | 309 | +| iterations | 9140 | +| time_elapsed | 30237 | +| total_timesteps | 9359360 | +| train/ | | +| approx_kl | 2.4650347 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.317 | +| explained_variance | -1.06 | +| learning_rate | 0.0001 | +| loss | -0.0874 | +| n_updates | 151920 | +| policy_gradient_loss | -0.0655 | +| value_loss | 0.000458 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.255 | +| time/ | | +| fps | 309 | +| iterations | 9141 | +| time_elapsed | 30240 | +| total_timesteps | 9360384 | +| train/ | | +| approx_kl | 3.0936193 | +| clip_fraction | 0.484 | +| clip_range | 0.2 | +| entropy_loss | -0.314 | +| explained_variance | -1.41 | +| learning_rate | 0.0001 | +| loss | -0.0927 | +| n_updates | 151930 | +| policy_gradient_loss | -0.0747 | +| value_loss | 0.00046 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.254 | +| time/ | | +| fps | 309 | +| iterations | 9142 | +| time_elapsed | 30244 | +| total_timesteps | 9361408 | +| train/ | | +| approx_kl | 4.3534956 | +| clip_fraction | 0.504 | +| clip_range | 0.2 | +| entropy_loss | -0.33 | +| explained_variance | -1.48 | +| learning_rate | 0.0001 | +| loss | -0.106 | +| n_updates | 151940 | +| policy_gradient_loss | -0.067 | +| value_loss | 0.000481 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.256 | +| time/ | | +| fps | 309 | +| iterations | 9143 | +| time_elapsed | 30248 | +| total_timesteps | 9362432 | +| train/ | | +| approx_kl | 2.2366297 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.344 | +| explained_variance | -1.13 | +| learning_rate | 0.0001 | +| loss | -0.0932 | +| n_updates | 151950 | +| policy_gradient_loss | -0.069 | +| value_loss | 0.000583 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.254 | +| time/ | | +| fps | 309 | +| iterations | 9144 | +| time_elapsed | 30251 | +| total_timesteps | 9363456 | +| train/ | | +| approx_kl | 2.2210033 | +| clip_fraction | 0.453 | +| clip_range | 0.2 | +| entropy_loss | -0.35 | +| explained_variance | -1.1 | +| learning_rate | 0.0001 | +| loss | -0.0778 | +| n_updates | 151960 | +| policy_gradient_loss | -0.0654 | +| value_loss | 0.000635 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.254 | +| time/ | | +| fps | 309 | +| iterations | 9145 | +| time_elapsed | 30254 | +| total_timesteps | 9364480 | +| train/ | | +| approx_kl | 2.720316 | +| clip_fraction | 0.462 | +| clip_range | 0.2 | +| entropy_loss | -0.311 | +| explained_variance | -4.41 | +| learning_rate | 0.0001 | +| loss | -0.0972 | +| n_updates | 151970 | +| policy_gradient_loss | -0.0707 | +| value_loss | 0.000426 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.249 | +| time/ | | +| fps | 309 | +| iterations | 9146 | +| time_elapsed | 30257 | +| total_timesteps | 9365504 | +| train/ | | +| approx_kl | 2.4250727 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.347 | +| explained_variance | -1.13 | +| learning_rate | 0.0001 | +| loss | -0.0967 | +| n_updates | 151980 | +| policy_gradient_loss | -0.0649 | +| value_loss | 0.000555 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.245 | +| time/ | | +| fps | 309 | +| iterations | 9147 | +| time_elapsed | 30261 | +| total_timesteps | 9366528 | +| train/ | | +| approx_kl | 2.483285 | +| clip_fraction | 0.45 | +| clip_range | 0.2 | +| entropy_loss | -0.317 | +| explained_variance | -6.17 | +| learning_rate | 0.0001 | +| loss | -0.0863 | +| n_updates | 151990 | +| policy_gradient_loss | -0.0677 | +| value_loss | 0.000436 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.249 | +| time/ | | +| fps | 309 | +| iterations | 9148 | +| time_elapsed | 30264 | +| total_timesteps | 9367552 | +| train/ | | +| approx_kl | 2.8990273 | +| clip_fraction | 0.453 | +| clip_range | 0.2 | +| entropy_loss | -0.303 | +| explained_variance | -0.461 | +| learning_rate | 0.0001 | +| loss | -0.0765 | +| n_updates | 152000 | +| policy_gradient_loss | -0.062 | +| value_loss | 0.000642 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.252 | +| time/ | | +| fps | 309 | +| iterations | 9149 | +| time_elapsed | 30267 | +| total_timesteps | 9368576 | +| train/ | | +| approx_kl | 2.052971 | +| clip_fraction | 0.429 | +| clip_range | 0.2 | +| entropy_loss | -0.278 | +| explained_variance | -1.11 | +| learning_rate | 0.0001 | +| loss | -0.062 | +| n_updates | 152010 | +| policy_gradient_loss | -0.0594 | +| value_loss | 0.00104 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.251 | +| time/ | | +| fps | 309 | +| iterations | 9150 | +| time_elapsed | 30270 | +| total_timesteps | 9369600 | +| train/ | | +| approx_kl | 2.3583322 | +| clip_fraction | 0.413 | +| clip_range | 0.2 | +| entropy_loss | -0.278 | +| explained_variance | -2.04 | +| learning_rate | 0.0001 | +| loss | -0.0618 | +| n_updates | 152020 | +| policy_gradient_loss | -0.0638 | +| value_loss | 0.000732 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.248 | +| time/ | | +| fps | 309 | +| iterations | 9151 | +| time_elapsed | 30274 | +| total_timesteps | 9370624 | +| train/ | | +| approx_kl | 2.4097018 | +| clip_fraction | 0.433 | +| clip_range | 0.2 | +| entropy_loss | -0.276 | +| explained_variance | -1.23 | +| learning_rate | 0.0001 | +| loss | -0.0919 | +| n_updates | 152030 | +| policy_gradient_loss | -0.0625 | +| value_loss | 0.000601 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.248 | +| time/ | | +| fps | 309 | +| iterations | 9152 | +| time_elapsed | 30277 | +| total_timesteps | 9371648 | +| train/ | | +| approx_kl | 2.1574795 | +| clip_fraction | 0.464 | +| clip_range | 0.2 | +| entropy_loss | -0.348 | +| explained_variance | -1.92 | +| learning_rate | 0.0001 | +| loss | -0.111 | +| n_updates | 152040 | +| policy_gradient_loss | -0.0676 | +| value_loss | 0.000449 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.254 | +| time/ | | +| fps | 309 | +| iterations | 9153 | +| time_elapsed | 30280 | +| total_timesteps | 9372672 | +| train/ | | +| approx_kl | 2.0974038 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.332 | +| explained_variance | -0.635 | +| learning_rate | 0.0001 | +| loss | -0.0884 | +| n_updates | 152050 | +| policy_gradient_loss | -0.067 | +| value_loss | 0.000544 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.253 | +| time/ | | +| fps | 309 | +| iterations | 9154 | +| time_elapsed | 30284 | +| total_timesteps | 9373696 | +| train/ | | +| approx_kl | 2.5266643 | +| clip_fraction | 0.413 | +| clip_range | 0.2 | +| entropy_loss | -0.266 | +| explained_variance | -1.04 | +| learning_rate | 0.0001 | +| loss | -0.0994 | +| n_updates | 152060 | +| policy_gradient_loss | -0.0632 | +| value_loss | 0.000505 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.253 | +| time/ | | +| fps | 309 | +| iterations | 9155 | +| time_elapsed | 30287 | +| total_timesteps | 9374720 | +| train/ | | +| approx_kl | 11.07839 | +| clip_fraction | 0.434 | +| clip_range | 0.2 | +| entropy_loss | -0.289 | +| explained_variance | -2.2 | +| learning_rate | 0.0001 | +| loss | -0.0772 | +| n_updates | 152070 | +| policy_gradient_loss | -0.0657 | +| value_loss | 0.000583 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.253 | +| time/ | | +| fps | 309 | +| iterations | 9156 | +| time_elapsed | 30290 | +| total_timesteps | 9375744 | +| train/ | | +| approx_kl | 2.1521292 | +| clip_fraction | 0.466 | +| clip_range | 0.2 | +| entropy_loss | -0.365 | +| explained_variance | -1.61 | +| learning_rate | 0.0001 | +| loss | -0.068 | +| n_updates | 152080 | +| policy_gradient_loss | -0.0613 | +| value_loss | 0.000493 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.252 | +| time/ | | +| fps | 309 | +| iterations | 9157 | +| time_elapsed | 30294 | +| total_timesteps | 9376768 | +| train/ | | +| approx_kl | 2.2860527 | +| clip_fraction | 0.421 | +| clip_range | 0.2 | +| entropy_loss | -0.287 | +| explained_variance | -2.11 | +| learning_rate | 0.0001 | +| loss | -0.0849 | +| n_updates | 152090 | +| policy_gradient_loss | -0.0627 | +| value_loss | 0.000507 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.248 | +| time/ | | +| fps | 309 | +| iterations | 9158 | +| time_elapsed | 30297 | +| total_timesteps | 9377792 | +| train/ | | +| approx_kl | 2.217056 | +| clip_fraction | 0.454 | +| clip_range | 0.2 | +| entropy_loss | -0.29 | +| explained_variance | -2.39 | +| learning_rate | 0.0001 | +| loss | -0.0861 | +| n_updates | 152100 | +| policy_gradient_loss | -0.0707 | +| value_loss | 0.000362 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.239 | +| time/ | | +| fps | 309 | +| iterations | 9159 | +| time_elapsed | 30301 | +| total_timesteps | 9378816 | +| train/ | | +| approx_kl | 2.2165384 | +| clip_fraction | 0.433 | +| clip_range | 0.2 | +| entropy_loss | -0.345 | +| explained_variance | -2.1 | +| learning_rate | 0.0001 | +| loss | -0.086 | +| n_updates | 152110 | +| policy_gradient_loss | -0.0623 | +| value_loss | 0.000567 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.238 | +| time/ | | +| fps | 309 | +| iterations | 9160 | +| time_elapsed | 30304 | +| total_timesteps | 9379840 | +| train/ | | +| approx_kl | 1.9875064 | +| clip_fraction | 0.432 | +| clip_range | 0.2 | +| entropy_loss | -0.28 | +| explained_variance | -1.3 | +| learning_rate | 0.0001 | +| loss | -0.0775 | +| n_updates | 152120 | +| policy_gradient_loss | -0.061 | +| value_loss | 0.000641 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.234 | +| time/ | | +| fps | 309 | +| iterations | 9161 | +| time_elapsed | 30308 | +| total_timesteps | 9380864 | +| train/ | | +| approx_kl | 2.1623597 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.342 | +| explained_variance | -1.53 | +| learning_rate | 0.0001 | +| loss | -0.078 | +| n_updates | 152130 | +| policy_gradient_loss | -0.0687 | +| value_loss | 0.000457 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.234 | +| time/ | | +| fps | 309 | +| iterations | 9162 | +| time_elapsed | 30311 | +| total_timesteps | 9381888 | +| train/ | | +| approx_kl | 8.827924 | +| clip_fraction | 0.436 | +| clip_range | 0.2 | +| entropy_loss | -0.297 | +| explained_variance | -2.21 | +| learning_rate | 0.0001 | +| loss | -0.0845 | +| n_updates | 152140 | +| policy_gradient_loss | -0.0571 | +| value_loss | 0.000632 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.233 | +| time/ | | +| fps | 309 | +| iterations | 9163 | +| time_elapsed | 30314 | +| total_timesteps | 9382912 | +| train/ | | +| approx_kl | 2.5295212 | +| clip_fraction | 0.476 | +| clip_range | 0.2 | +| entropy_loss | -0.298 | +| explained_variance | -0.874 | +| learning_rate | 0.0001 | +| loss | -0.0926 | +| n_updates | 152150 | +| policy_gradient_loss | -0.0711 | +| value_loss | 0.000713 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.23 | +| time/ | | +| fps | 309 | +| iterations | 9164 | +| time_elapsed | 30317 | +| total_timesteps | 9383936 | +| train/ | | +| approx_kl | 2.2374423 | +| clip_fraction | 0.417 | +| clip_range | 0.2 | +| entropy_loss | -0.265 | +| explained_variance | -0.831 | +| learning_rate | 0.0001 | +| loss | -0.0647 | +| n_updates | 152160 | +| policy_gradient_loss | -0.0578 | +| value_loss | 0.000606 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.23 | +| time/ | | +| fps | 309 | +| iterations | 9165 | +| time_elapsed | 30321 | +| total_timesteps | 9384960 | +| train/ | | +| approx_kl | 2.3286412 | +| clip_fraction | 0.423 | +| clip_range | 0.2 | +| entropy_loss | -0.278 | +| explained_variance | -3.16 | +| learning_rate | 0.0001 | +| loss | -0.0749 | +| n_updates | 152170 | +| policy_gradient_loss | -0.0578 | +| value_loss | 0.000552 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.233 | +| time/ | | +| fps | 309 | +| iterations | 9166 | +| time_elapsed | 30324 | +| total_timesteps | 9385984 | +| train/ | | +| approx_kl | 2.5533462 | +| clip_fraction | 0.482 | +| clip_range | 0.2 | +| entropy_loss | -0.367 | +| explained_variance | -1.35 | +| learning_rate | 0.0001 | +| loss | -0.1 | +| n_updates | 152180 | +| policy_gradient_loss | -0.0644 | +| value_loss | 0.000744 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.232 | +| time/ | | +| fps | 309 | +| iterations | 9167 | +| time_elapsed | 30327 | +| total_timesteps | 9387008 | +| train/ | | +| approx_kl | 4.878961 | +| clip_fraction | 0.402 | +| clip_range | 0.2 | +| entropy_loss | -0.249 | +| explained_variance | -1.58 | +| learning_rate | 0.0001 | +| loss | -0.0641 | +| n_updates | 152190 | +| policy_gradient_loss | -0.0603 | +| value_loss | 0.000483 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.232 | +| time/ | | +| fps | 309 | +| iterations | 9168 | +| time_elapsed | 30330 | +| total_timesteps | 9388032 | +| train/ | | +| approx_kl | 2.7708893 | +| clip_fraction | 0.447 | +| clip_range | 0.2 | +| entropy_loss | -0.328 | +| explained_variance | -0.732 | +| learning_rate | 0.0001 | +| loss | -0.0866 | +| n_updates | 152200 | +| policy_gradient_loss | -0.06 | +| value_loss | 0.00061 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.233 | +| time/ | | +| fps | 309 | +| iterations | 9169 | +| time_elapsed | 30334 | +| total_timesteps | 9389056 | +| train/ | | +| approx_kl | 3.6619387 | +| clip_fraction | 0.484 | +| clip_range | 0.2 | +| entropy_loss | -0.315 | +| explained_variance | -1.87 | +| learning_rate | 0.0001 | +| loss | -0.0936 | +| n_updates | 152210 | +| policy_gradient_loss | -0.0773 | +| value_loss | 0.00058 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.228 | +| time/ | | +| fps | 309 | +| iterations | 9170 | +| time_elapsed | 30337 | +| total_timesteps | 9390080 | +| train/ | | +| approx_kl | 1.9662699 | +| clip_fraction | 0.492 | +| clip_range | 0.2 | +| entropy_loss | -0.359 | +| explained_variance | -1.88 | +| learning_rate | 0.0001 | +| loss | -0.0878 | +| n_updates | 152220 | +| policy_gradient_loss | -0.0741 | +| value_loss | 0.00027 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.228 | +| time/ | | +| fps | 309 | +| iterations | 9171 | +| time_elapsed | 30340 | +| total_timesteps | 9391104 | +| train/ | | +| approx_kl | 2.4702563 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.356 | +| explained_variance | -0.612 | +| learning_rate | 0.0001 | +| loss | -0.0731 | +| n_updates | 152230 | +| policy_gradient_loss | -0.0689 | +| value_loss | 0.000375 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.227 | +| time/ | | +| fps | 309 | +| iterations | 9172 | +| time_elapsed | 30344 | +| total_timesteps | 9392128 | +| train/ | | +| approx_kl | 3.1811404 | +| clip_fraction | 0.498 | +| clip_range | 0.2 | +| entropy_loss | -0.355 | +| explained_variance | -1.49 | +| learning_rate | 0.0001 | +| loss | -0.0903 | +| n_updates | 152240 | +| policy_gradient_loss | -0.0688 | +| value_loss | 0.000536 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.227 | +| time/ | | +| fps | 309 | +| iterations | 9173 | +| time_elapsed | 30347 | +| total_timesteps | 9393152 | +| train/ | | +| approx_kl | 4.1862154 | +| clip_fraction | 0.449 | +| clip_range | 0.2 | +| entropy_loss | -0.31 | +| explained_variance | -2.44 | +| learning_rate | 0.0001 | +| loss | -0.111 | +| n_updates | 152250 | +| policy_gradient_loss | -0.0668 | +| value_loss | 0.000642 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.224 | +| time/ | | +| fps | 309 | +| iterations | 9174 | +| time_elapsed | 30351 | +| total_timesteps | 9394176 | +| train/ | | +| approx_kl | 4.516604 | +| clip_fraction | 0.482 | +| clip_range | 0.2 | +| entropy_loss | -0.358 | +| explained_variance | -4.36 | +| learning_rate | 0.0001 | +| loss | -0.0702 | +| n_updates | 152260 | +| policy_gradient_loss | -0.0671 | +| value_loss | 0.000475 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.224 | +| time/ | | +| fps | 309 | +| iterations | 9175 | +| time_elapsed | 30354 | +| total_timesteps | 9395200 | +| train/ | | +| approx_kl | 2.2994037 | +| clip_fraction | 0.506 | +| clip_range | 0.2 | +| entropy_loss | -0.37 | +| explained_variance | -1.3 | +| learning_rate | 0.0001 | +| loss | -0.107 | +| n_updates | 152270 | +| policy_gradient_loss | -0.0694 | +| value_loss | 0.00061 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.226 | +| time/ | | +| fps | 309 | +| iterations | 9176 | +| time_elapsed | 30358 | +| total_timesteps | 9396224 | +| train/ | | +| approx_kl | 2.7427669 | +| clip_fraction | 0.495 | +| clip_range | 0.2 | +| entropy_loss | -0.388 | +| explained_variance | -1.14 | +| learning_rate | 0.0001 | +| loss | -0.0829 | +| n_updates | 152280 | +| policy_gradient_loss | -0.0642 | +| value_loss | 0.000533 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.224 | +| time/ | | +| fps | 309 | +| iterations | 9177 | +| time_elapsed | 30361 | +| total_timesteps | 9397248 | +| train/ | | +| approx_kl | 2.145007 | +| clip_fraction | 0.459 | +| clip_range | 0.2 | +| entropy_loss | -0.317 | +| explained_variance | -2.27 | +| learning_rate | 0.0001 | +| loss | -0.0849 | +| n_updates | 152290 | +| policy_gradient_loss | -0.0649 | +| value_loss | 0.000606 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.226 | +| time/ | | +| fps | 309 | +| iterations | 9178 | +| time_elapsed | 30365 | +| total_timesteps | 9398272 | +| train/ | | +| approx_kl | 2.240131 | +| clip_fraction | 0.451 | +| clip_range | 0.2 | +| entropy_loss | -0.319 | +| explained_variance | -6.87 | +| learning_rate | 0.0001 | +| loss | -0.0866 | +| n_updates | 152300 | +| policy_gradient_loss | -0.0621 | +| value_loss | 0.00055 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.225 | +| time/ | | +| fps | 309 | +| iterations | 9179 | +| time_elapsed | 30368 | +| total_timesteps | 9399296 | +| train/ | | +| approx_kl | 2.7398367 | +| clip_fraction | 0.479 | +| clip_range | 0.2 | +| entropy_loss | -0.317 | +| explained_variance | -1.39 | +| learning_rate | 0.0001 | +| loss | -0.116 | +| n_updates | 152310 | +| policy_gradient_loss | -0.0728 | +| value_loss | 0.000494 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.227 | +| time/ | | +| fps | 309 | +| iterations | 9180 | +| time_elapsed | 30372 | +| total_timesteps | 9400320 | +| train/ | | +| approx_kl | 2.6757514 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.329 | +| explained_variance | -1.68 | +| learning_rate | 0.0001 | +| loss | -0.0535 | +| n_updates | 152320 | +| policy_gradient_loss | -0.069 | +| value_loss | 0.000692 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.227 | +| time/ | | +| fps | 309 | +| iterations | 9181 | +| time_elapsed | 30375 | +| total_timesteps | 9401344 | +| train/ | | +| approx_kl | 2.2625213 | +| clip_fraction | 0.461 | +| clip_range | 0.2 | +| entropy_loss | -0.333 | +| explained_variance | -1.47 | +| learning_rate | 0.0001 | +| loss | -0.0791 | +| n_updates | 152330 | +| policy_gradient_loss | -0.0635 | +| value_loss | 0.000518 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.229 | +| time/ | | +| fps | 309 | +| iterations | 9182 | +| time_elapsed | 30378 | +| total_timesteps | 9402368 | +| train/ | | +| approx_kl | 2.138527 | +| clip_fraction | 0.469 | +| clip_range | 0.2 | +| entropy_loss | -0.352 | +| explained_variance | -0.604 | +| learning_rate | 0.0001 | +| loss | -0.0943 | +| n_updates | 152340 | +| policy_gradient_loss | -0.0599 | +| value_loss | 0.000705 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.229 | +| time/ | | +| fps | 309 | +| iterations | 9183 | +| time_elapsed | 30381 | +| total_timesteps | 9403392 | +| train/ | | +| approx_kl | 3.6585221 | +| clip_fraction | 0.447 | +| clip_range | 0.2 | +| entropy_loss | -0.302 | +| explained_variance | -2.62 | +| learning_rate | 0.0001 | +| loss | -0.0716 | +| n_updates | 152350 | +| policy_gradient_loss | -0.0592 | +| value_loss | 0.000626 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.233 | +| time/ | | +| fps | 309 | +| iterations | 9184 | +| time_elapsed | 30385 | +| total_timesteps | 9404416 | +| train/ | | +| approx_kl | 2.2618914 | +| clip_fraction | 0.472 | +| clip_range | 0.2 | +| entropy_loss | -0.34 | +| explained_variance | -2.76 | +| learning_rate | 0.0001 | +| loss | -0.087 | +| n_updates | 152360 | +| policy_gradient_loss | -0.0674 | +| value_loss | 0.000449 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.233 | +| time/ | | +| fps | 309 | +| iterations | 9185 | +| time_elapsed | 30388 | +| total_timesteps | 9405440 | +| train/ | | +| approx_kl | 2.926749 | +| clip_fraction | 0.476 | +| clip_range | 0.2 | +| entropy_loss | -0.288 | +| explained_variance | -0.873 | +| learning_rate | 0.0001 | +| loss | -0.083 | +| n_updates | 152370 | +| policy_gradient_loss | -0.066 | +| value_loss | 0.000694 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.231 | +| time/ | | +| fps | 309 | +| iterations | 9186 | +| time_elapsed | 30391 | +| total_timesteps | 9406464 | +| train/ | | +| approx_kl | 2.6723294 | +| clip_fraction | 0.462 | +| clip_range | 0.2 | +| entropy_loss | -0.311 | +| explained_variance | -2.57 | +| learning_rate | 0.0001 | +| loss | -0.0942 | +| n_updates | 152380 | +| policy_gradient_loss | -0.0704 | +| value_loss | 0.000495 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.229 | +| time/ | | +| fps | 309 | +| iterations | 9187 | +| time_elapsed | 30394 | +| total_timesteps | 9407488 | +| train/ | | +| approx_kl | 1.9307117 | +| clip_fraction | 0.424 | +| clip_range | 0.2 | +| entropy_loss | -0.291 | +| explained_variance | -1.45 | +| learning_rate | 0.0001 | +| loss | -0.0802 | +| n_updates | 152390 | +| policy_gradient_loss | -0.0555 | +| value_loss | 0.000552 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.229 | +| time/ | | +| fps | 309 | +| iterations | 9188 | +| time_elapsed | 30398 | +| total_timesteps | 9408512 | +| train/ | | +| approx_kl | 6.246387 | +| clip_fraction | 0.43 | +| clip_range | 0.2 | +| entropy_loss | -0.285 | +| explained_variance | -1.48 | +| learning_rate | 0.0001 | +| loss | -0.0628 | +| n_updates | 152400 | +| policy_gradient_loss | -0.0594 | +| value_loss | 0.000655 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.23 | +| time/ | | +| fps | 309 | +| iterations | 9189 | +| time_elapsed | 30401 | +| total_timesteps | 9409536 | +| train/ | | +| approx_kl | 2.656414 | +| clip_fraction | 0.509 | +| clip_range | 0.2 | +| entropy_loss | -0.357 | +| explained_variance | -1.47 | +| learning_rate | 0.0001 | +| loss | -0.0696 | +| n_updates | 152410 | +| policy_gradient_loss | -0.0757 | +| value_loss | 0.000669 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.226 | +| time/ | | +| fps | 309 | +| iterations | 9190 | +| time_elapsed | 30404 | +| total_timesteps | 9410560 | +| train/ | | +| approx_kl | 2.7659242 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.312 | +| explained_variance | -1.96 | +| learning_rate | 0.0001 | +| loss | -0.1 | +| n_updates | 152420 | +| policy_gradient_loss | -0.0667 | +| value_loss | 0.000381 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.226 | +| time/ | | +| fps | 309 | +| iterations | 9191 | +| time_elapsed | 30408 | +| total_timesteps | 9411584 | +| train/ | | +| approx_kl | 2.1528041 | +| clip_fraction | 0.436 | +| clip_range | 0.2 | +| entropy_loss | -0.327 | +| explained_variance | -0.571 | +| learning_rate | 0.0001 | +| loss | -0.0768 | +| n_updates | 152430 | +| policy_gradient_loss | -0.0643 | +| value_loss | 0.000491 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.222 | +| time/ | | +| fps | 309 | +| iterations | 9192 | +| time_elapsed | 30411 | +| total_timesteps | 9412608 | +| train/ | | +| approx_kl | 2.416698 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.33 | +| explained_variance | -2.62 | +| learning_rate | 0.0001 | +| loss | -0.108 | +| n_updates | 152440 | +| policy_gradient_loss | -0.0727 | +| value_loss | 0.000627 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.222 | +| time/ | | +| fps | 309 | +| iterations | 9193 | +| time_elapsed | 30415 | +| total_timesteps | 9413632 | +| train/ | | +| approx_kl | 2.5545785 | +| clip_fraction | 0.425 | +| clip_range | 0.2 | +| entropy_loss | -0.306 | +| explained_variance | -0.738 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 152450 | +| policy_gradient_loss | -0.0633 | +| value_loss | 0.000564 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.22 | +| time/ | | +| fps | 309 | +| iterations | 9194 | +| time_elapsed | 30418 | +| total_timesteps | 9414656 | +| train/ | | +| approx_kl | 2.431268 | +| clip_fraction | 0.457 | +| clip_range | 0.2 | +| entropy_loss | -0.318 | +| explained_variance | -7.47 | +| learning_rate | 0.0001 | +| loss | -0.0967 | +| n_updates | 152460 | +| policy_gradient_loss | -0.0707 | +| value_loss | 0.000548 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.22 | +| time/ | | +| fps | 309 | +| iterations | 9195 | +| time_elapsed | 30421 | +| total_timesteps | 9415680 | +| train/ | | +| approx_kl | 2.0671005 | +| clip_fraction | 0.449 | +| clip_range | 0.2 | +| entropy_loss | -0.315 | +| explained_variance | -1.02 | +| learning_rate | 0.0001 | +| loss | -0.0573 | +| n_updates | 152470 | +| policy_gradient_loss | -0.0604 | +| value_loss | 0.000631 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.218 | +| time/ | | +| fps | 309 | +| iterations | 9196 | +| time_elapsed | 30425 | +| total_timesteps | 9416704 | +| train/ | | +| approx_kl | 3.795938 | +| clip_fraction | 0.455 | +| clip_range | 0.2 | +| entropy_loss | -0.358 | +| explained_variance | -0.856 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 152480 | +| policy_gradient_loss | -0.0641 | +| value_loss | 0.000515 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.221 | +| time/ | | +| fps | 309 | +| iterations | 9197 | +| time_elapsed | 30428 | +| total_timesteps | 9417728 | +| train/ | | +| approx_kl | 1.7851397 | +| clip_fraction | 0.448 | +| clip_range | 0.2 | +| entropy_loss | -0.346 | +| explained_variance | -1.13 | +| learning_rate | 0.0001 | +| loss | -0.0828 | +| n_updates | 152490 | +| policy_gradient_loss | -0.0538 | +| value_loss | 0.000485 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.221 | +| time/ | | +| fps | 309 | +| iterations | 9198 | +| time_elapsed | 30431 | +| total_timesteps | 9418752 | +| train/ | | +| approx_kl | 2.4539998 | +| clip_fraction | 0.419 | +| clip_range | 0.2 | +| entropy_loss | -0.254 | +| explained_variance | -0.627 | +| learning_rate | 0.0001 | +| loss | -0.0442 | +| n_updates | 152500 | +| policy_gradient_loss | -0.0439 | +| value_loss | 0.00057 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.222 | +| time/ | | +| fps | 309 | +| iterations | 9199 | +| time_elapsed | 30434 | +| total_timesteps | 9419776 | +| train/ | | +| approx_kl | 2.7200234 | +| clip_fraction | 0.486 | +| clip_range | 0.2 | +| entropy_loss | -0.33 | +| explained_variance | -4.05 | +| learning_rate | 0.0001 | +| loss | -0.0925 | +| n_updates | 152510 | +| policy_gradient_loss | -0.0681 | +| value_loss | 0.00044 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.222 | +| time/ | | +| fps | 309 | +| iterations | 9200 | +| time_elapsed | 30438 | +| total_timesteps | 9420800 | +| train/ | | +| approx_kl | 2.4340556 | +| clip_fraction | 0.482 | +| clip_range | 0.2 | +| entropy_loss | -0.328 | +| explained_variance | -2.83 | +| learning_rate | 0.0001 | +| loss | -0.0955 | +| n_updates | 152520 | +| policy_gradient_loss | -0.073 | +| value_loss | 0.000347 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.221 | +| time/ | | +| fps | 309 | +| iterations | 9201 | +| time_elapsed | 30441 | +| total_timesteps | 9421824 | +| train/ | | +| approx_kl | 2.1765664 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.344 | +| explained_variance | -1.05 | +| learning_rate | 0.0001 | +| loss | -0.0928 | +| n_updates | 152530 | +| policy_gradient_loss | -0.0624 | +| value_loss | 0.000595 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.225 | +| time/ | | +| fps | 309 | +| iterations | 9202 | +| time_elapsed | 30444 | +| total_timesteps | 9422848 | +| train/ | | +| approx_kl | 2.7145863 | +| clip_fraction | 0.463 | +| clip_range | 0.2 | +| entropy_loss | -0.322 | +| explained_variance | -0.659 | +| learning_rate | 0.0001 | +| loss | -0.0842 | +| n_updates | 152540 | +| policy_gradient_loss | -0.0689 | +| value_loss | 0.00067 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.224 | +| time/ | | +| fps | 309 | +| iterations | 9203 | +| time_elapsed | 30447 | +| total_timesteps | 9423872 | +| train/ | | +| approx_kl | 2.1909547 | +| clip_fraction | 0.445 | +| clip_range | 0.2 | +| entropy_loss | -0.318 | +| explained_variance | -0.867 | +| learning_rate | 0.0001 | +| loss | -0.074 | +| n_updates | 152550 | +| policy_gradient_loss | -0.0575 | +| value_loss | 0.00093 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.224 | +| time/ | | +| fps | 309 | +| iterations | 9204 | +| time_elapsed | 30451 | +| total_timesteps | 9424896 | +| train/ | | +| approx_kl | 2.337102 | +| clip_fraction | 0.469 | +| clip_range | 0.2 | +| entropy_loss | -0.316 | +| explained_variance | -2.41 | +| learning_rate | 0.0001 | +| loss | -0.0634 | +| n_updates | 152560 | +| policy_gradient_loss | -0.0617 | +| value_loss | 0.000692 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.218 | +| time/ | | +| fps | 309 | +| iterations | 9205 | +| time_elapsed | 30454 | +| total_timesteps | 9425920 | +| train/ | | +| approx_kl | 2.7427287 | +| clip_fraction | 0.463 | +| clip_range | 0.2 | +| entropy_loss | -0.311 | +| explained_variance | -2.45 | +| learning_rate | 0.0001 | +| loss | -0.0916 | +| n_updates | 152570 | +| policy_gradient_loss | -0.0673 | +| value_loss | 0.00063 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.217 | +| time/ | | +| fps | 309 | +| iterations | 9206 | +| time_elapsed | 30457 | +| total_timesteps | 9426944 | +| train/ | | +| approx_kl | 2.6526103 | +| clip_fraction | 0.423 | +| clip_range | 0.2 | +| entropy_loss | -0.275 | +| explained_variance | -1.58 | +| learning_rate | 0.0001 | +| loss | -0.0747 | +| n_updates | 152580 | +| policy_gradient_loss | -0.0602 | +| value_loss | 0.000623 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.211 | +| time/ | | +| fps | 309 | +| iterations | 9207 | +| time_elapsed | 30460 | +| total_timesteps | 9427968 | +| train/ | | +| approx_kl | 3.9698281 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.339 | +| explained_variance | -1.99 | +| learning_rate | 0.0001 | +| loss | -0.0918 | +| n_updates | 152590 | +| policy_gradient_loss | -0.0709 | +| value_loss | 0.000537 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.216 | +| time/ | | +| fps | 309 | +| iterations | 9208 | +| time_elapsed | 30464 | +| total_timesteps | 9428992 | +| train/ | | +| approx_kl | 2.2215705 | +| clip_fraction | 0.365 | +| clip_range | 0.2 | +| entropy_loss | -0.248 | +| explained_variance | -0.372 | +| learning_rate | 0.0001 | +| loss | -0.0609 | +| n_updates | 152600 | +| policy_gradient_loss | -0.0423 | +| value_loss | 0.000446 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.222 | +| time/ | | +| fps | 309 | +| iterations | 9209 | +| time_elapsed | 30467 | +| total_timesteps | 9430016 | +| train/ | | +| approx_kl | 2.2773705 | +| clip_fraction | 0.431 | +| clip_range | 0.2 | +| entropy_loss | -0.316 | +| explained_variance | -0.343 | +| learning_rate | 0.0001 | +| loss | -0.0703 | +| n_updates | 152610 | +| policy_gradient_loss | -0.0636 | +| value_loss | 0.000744 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.221 | +| time/ | | +| fps | 309 | +| iterations | 9210 | +| time_elapsed | 30471 | +| total_timesteps | 9431040 | +| train/ | | +| approx_kl | 1.9352925 | +| clip_fraction | 0.435 | +| clip_range | 0.2 | +| entropy_loss | -0.329 | +| explained_variance | -1.21 | +| learning_rate | 0.0001 | +| loss | -0.0933 | +| n_updates | 152620 | +| policy_gradient_loss | -0.0612 | +| value_loss | 0.000987 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.221 | +| time/ | | +| fps | 309 | +| iterations | 9211 | +| time_elapsed | 30474 | +| total_timesteps | 9432064 | +| train/ | | +| approx_kl | 2.3355732 | +| clip_fraction | 0.441 | +| clip_range | 0.2 | +| entropy_loss | -0.3 | +| explained_variance | -1.72 | +| learning_rate | 0.0001 | +| loss | -0.107 | +| n_updates | 152630 | +| policy_gradient_loss | -0.0653 | +| value_loss | 0.000651 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.222 | +| time/ | | +| fps | 309 | +| iterations | 9212 | +| time_elapsed | 30478 | +| total_timesteps | 9433088 | +| train/ | | +| approx_kl | 1.9797993 | +| clip_fraction | 0.452 | +| clip_range | 0.2 | +| entropy_loss | -0.345 | +| explained_variance | -2.77 | +| learning_rate | 0.0001 | +| loss | -0.109 | +| n_updates | 152640 | +| policy_gradient_loss | -0.0662 | +| value_loss | 0.000533 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.225 | +| time/ | | +| fps | 309 | +| iterations | 9213 | +| time_elapsed | 30481 | +| total_timesteps | 9434112 | +| train/ | | +| approx_kl | 2.1920037 | +| clip_fraction | 0.47 | +| clip_range | 0.2 | +| entropy_loss | -0.33 | +| explained_variance | -1.38 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 152650 | +| policy_gradient_loss | -0.0742 | +| value_loss | 0.000389 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.228 | +| time/ | | +| fps | 309 | +| iterations | 9214 | +| time_elapsed | 30485 | +| total_timesteps | 9435136 | +| train/ | | +| approx_kl | 2.8063626 | +| clip_fraction | 0.465 | +| clip_range | 0.2 | +| entropy_loss | -0.304 | +| explained_variance | -1.21 | +| learning_rate | 0.0001 | +| loss | -0.0825 | +| n_updates | 152660 | +| policy_gradient_loss | -0.0634 | +| value_loss | 0.000683 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.228 | +| time/ | | +| fps | 309 | +| iterations | 9215 | +| time_elapsed | 30488 | +| total_timesteps | 9436160 | +| train/ | | +| approx_kl | 2.2829223 | +| clip_fraction | 0.453 | +| clip_range | 0.2 | +| entropy_loss | -0.3 | +| explained_variance | -1.64 | +| learning_rate | 0.0001 | +| loss | -0.11 | +| n_updates | 152670 | +| policy_gradient_loss | -0.0684 | +| value_loss | 0.000584 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.226 | +| time/ | | +| fps | 309 | +| iterations | 9216 | +| time_elapsed | 30492 | +| total_timesteps | 9437184 | +| train/ | | +| approx_kl | 1.9719675 | +| clip_fraction | 0.505 | +| clip_range | 0.2 | +| entropy_loss | -0.407 | +| explained_variance | -1 | +| learning_rate | 0.0001 | +| loss | -0.107 | +| n_updates | 152680 | +| policy_gradient_loss | -0.0758 | +| value_loss | 0.0006 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.221 | +| time/ | | +| fps | 309 | +| iterations | 9217 | +| time_elapsed | 30495 | +| total_timesteps | 9438208 | +| train/ | | +| approx_kl | 3.0166173 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.3 | +| explained_variance | -1.51 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 152690 | +| policy_gradient_loss | -0.0665 | +| value_loss | 0.000529 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.217 | +| time/ | | +| fps | 309 | +| iterations | 9218 | +| time_elapsed | 30498 | +| total_timesteps | 9439232 | +| train/ | | +| approx_kl | 2.752492 | +| clip_fraction | 0.467 | +| clip_range | 0.2 | +| entropy_loss | -0.28 | +| explained_variance | -3.39 | +| learning_rate | 0.0001 | +| loss | -0.0931 | +| n_updates | 152700 | +| policy_gradient_loss | -0.0693 | +| value_loss | 0.000588 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.217 | +| time/ | | +| fps | 309 | +| iterations | 9219 | +| time_elapsed | 30502 | +| total_timesteps | 9440256 | +| train/ | | +| approx_kl | 2.251155 | +| clip_fraction | 0.458 | +| clip_range | 0.2 | +| entropy_loss | -0.313 | +| explained_variance | -1.93 | +| learning_rate | 0.0001 | +| loss | -0.0711 | +| n_updates | 152710 | +| policy_gradient_loss | -0.066 | +| value_loss | 0.000408 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.213 | +| time/ | | +| fps | 309 | +| iterations | 9220 | +| time_elapsed | 30505 | +| total_timesteps | 9441280 | +| train/ | | +| approx_kl | 2.4886174 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.339 | +| explained_variance | -1.13 | +| learning_rate | 0.0001 | +| loss | -0.0823 | +| n_updates | 152720 | +| policy_gradient_loss | -0.0678 | +| value_loss | 0.000507 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.217 | +| time/ | | +| fps | 309 | +| iterations | 9221 | +| time_elapsed | 30508 | +| total_timesteps | 9442304 | +| train/ | | +| approx_kl | 2.1901507 | +| clip_fraction | 0.476 | +| clip_range | 0.2 | +| entropy_loss | -0.336 | +| explained_variance | -0.956 | +| learning_rate | 0.0001 | +| loss | -0.0816 | +| n_updates | 152730 | +| policy_gradient_loss | -0.071 | +| value_loss | 0.000495 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.217 | +| time/ | | +| fps | 309 | +| iterations | 9222 | +| time_elapsed | 30511 | +| total_timesteps | 9443328 | +| train/ | | +| approx_kl | 1.7833896 | +| clip_fraction | 0.456 | +| clip_range | 0.2 | +| entropy_loss | -0.354 | +| explained_variance | -1.28 | +| learning_rate | 0.0001 | +| loss | -0.0676 | +| n_updates | 152740 | +| policy_gradient_loss | -0.0617 | +| value_loss | 0.000408 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.216 | +| time/ | | +| fps | 309 | +| iterations | 9223 | +| time_elapsed | 30515 | +| total_timesteps | 9444352 | +| train/ | | +| approx_kl | 2.4831343 | +| clip_fraction | 0.503 | +| clip_range | 0.2 | +| entropy_loss | -0.362 | +| explained_variance | -1.62 | +| learning_rate | 0.0001 | +| loss | -0.0899 | +| n_updates | 152750 | +| policy_gradient_loss | -0.0653 | +| value_loss | 0.000499 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.216 | +| time/ | | +| fps | 309 | +| iterations | 9224 | +| time_elapsed | 30518 | +| total_timesteps | 9445376 | +| train/ | | +| approx_kl | 2.640056 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.367 | +| explained_variance | -1.87 | +| learning_rate | 0.0001 | +| loss | -0.0778 | +| n_updates | 152760 | +| policy_gradient_loss | -0.0663 | +| value_loss | 0.000469 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.219 | +| time/ | | +| fps | 309 | +| iterations | 9225 | +| time_elapsed | 30521 | +| total_timesteps | 9446400 | +| train/ | | +| approx_kl | 2.1025307 | +| clip_fraction | 0.449 | +| clip_range | 0.2 | +| entropy_loss | -0.315 | +| explained_variance | -4.34 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 152770 | +| policy_gradient_loss | -0.0624 | +| value_loss | 0.000431 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.217 | +| time/ | | +| fps | 309 | +| iterations | 9226 | +| time_elapsed | 30525 | +| total_timesteps | 9447424 | +| train/ | | +| approx_kl | 2.2137108 | +| clip_fraction | 0.467 | +| clip_range | 0.2 | +| entropy_loss | -0.328 | +| explained_variance | -1.51 | +| learning_rate | 0.0001 | +| loss | -0.0844 | +| n_updates | 152780 | +| policy_gradient_loss | -0.0709 | +| value_loss | 0.000506 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.217 | +| time/ | | +| fps | 309 | +| iterations | 9227 | +| time_elapsed | 30528 | +| total_timesteps | 9448448 | +| train/ | | +| approx_kl | 2.231516 | +| clip_fraction | 0.463 | +| clip_range | 0.2 | +| entropy_loss | -0.355 | +| explained_variance | -1.87 | +| learning_rate | 0.0001 | +| loss | -0.0903 | +| n_updates | 152790 | +| policy_gradient_loss | -0.0666 | +| value_loss | 0.000559 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.22 | +| time/ | | +| fps | 309 | +| iterations | 9228 | +| time_elapsed | 30531 | +| total_timesteps | 9449472 | +| train/ | | +| approx_kl | 3.3217537 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.346 | +| explained_variance | -1.12 | +| learning_rate | 0.0001 | +| loss | -0.0893 | +| n_updates | 152800 | +| policy_gradient_loss | -0.0719 | +| value_loss | 0.00057 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.215 | +| time/ | | +| fps | 309 | +| iterations | 9229 | +| time_elapsed | 30535 | +| total_timesteps | 9450496 | +| train/ | | +| approx_kl | 2.325035 | +| clip_fraction | 0.423 | +| clip_range | 0.2 | +| entropy_loss | -0.262 | +| explained_variance | -1.09 | +| learning_rate | 0.0001 | +| loss | -0.0747 | +| n_updates | 152810 | +| policy_gradient_loss | -0.0646 | +| value_loss | 0.000616 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.219 | +| time/ | | +| fps | 309 | +| iterations | 9230 | +| time_elapsed | 30538 | +| total_timesteps | 9451520 | +| train/ | | +| approx_kl | 1.857948 | +| clip_fraction | 0.435 | +| clip_range | 0.2 | +| entropy_loss | -0.32 | +| explained_variance | -0.649 | +| learning_rate | 0.0001 | +| loss | -0.0916 | +| n_updates | 152820 | +| policy_gradient_loss | -0.0585 | +| value_loss | 0.00052 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.219 | +| time/ | | +| fps | 309 | +| iterations | 9231 | +| time_elapsed | 30542 | +| total_timesteps | 9452544 | +| train/ | | +| approx_kl | 1.8215175 | +| clip_fraction | 0.414 | +| clip_range | 0.2 | +| entropy_loss | -0.36 | +| explained_variance | -0.309 | +| learning_rate | 0.0001 | +| loss | -0.0927 | +| n_updates | 152830 | +| policy_gradient_loss | -0.0575 | +| value_loss | 0.000564 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.222 | +| time/ | | +| fps | 309 | +| iterations | 9232 | +| time_elapsed | 30545 | +| total_timesteps | 9453568 | +| train/ | | +| approx_kl | 2.404564 | +| clip_fraction | 0.454 | +| clip_range | 0.2 | +| entropy_loss | -0.338 | +| explained_variance | -1.3 | +| learning_rate | 0.0001 | +| loss | -0.0851 | +| n_updates | 152840 | +| policy_gradient_loss | -0.058 | +| value_loss | 0.000599 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.223 | +| time/ | | +| fps | 309 | +| iterations | 9233 | +| time_elapsed | 30549 | +| total_timesteps | 9454592 | +| train/ | | +| approx_kl | 2.3671267 | +| clip_fraction | 0.458 | +| clip_range | 0.2 | +| entropy_loss | -0.327 | +| explained_variance | -2.2 | +| learning_rate | 0.0001 | +| loss | -0.0866 | +| n_updates | 152850 | +| policy_gradient_loss | -0.0566 | +| value_loss | 0.000539 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.217 | +| time/ | | +| fps | 309 | +| iterations | 9234 | +| time_elapsed | 30552 | +| total_timesteps | 9455616 | +| train/ | | +| approx_kl | 2.4898882 | +| clip_fraction | 0.435 | +| clip_range | 0.2 | +| entropy_loss | -0.289 | +| explained_variance | -2.74 | +| learning_rate | 0.0001 | +| loss | -0.0885 | +| n_updates | 152860 | +| policy_gradient_loss | -0.0623 | +| value_loss | 0.000493 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.213 | +| time/ | | +| fps | 309 | +| iterations | 9235 | +| time_elapsed | 30555 | +| total_timesteps | 9456640 | +| train/ | | +| approx_kl | 1.945588 | +| clip_fraction | 0.454 | +| clip_range | 0.2 | +| entropy_loss | -0.332 | +| explained_variance | -1.66 | +| learning_rate | 0.0001 | +| loss | -0.093 | +| n_updates | 152870 | +| policy_gradient_loss | -0.0662 | +| value_loss | 0.000412 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.213 | +| time/ | | +| fps | 309 | +| iterations | 9236 | +| time_elapsed | 30558 | +| total_timesteps | 9457664 | +| train/ | | +| approx_kl | 1.9899918 | +| clip_fraction | 0.426 | +| clip_range | 0.2 | +| entropy_loss | -0.315 | +| explained_variance | -1.61 | +| learning_rate | 0.0001 | +| loss | -0.0862 | +| n_updates | 152880 | +| policy_gradient_loss | -0.0596 | +| value_loss | 0.000542 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.213 | +| time/ | | +| fps | 309 | +| iterations | 9237 | +| time_elapsed | 30562 | +| total_timesteps | 9458688 | +| train/ | | +| approx_kl | 1.8997587 | +| clip_fraction | 0.474 | +| clip_range | 0.2 | +| entropy_loss | -0.396 | +| explained_variance | -1.27 | +| learning_rate | 0.0001 | +| loss | -0.105 | +| n_updates | 152890 | +| policy_gradient_loss | -0.0604 | +| value_loss | 0.000451 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.213 | +| time/ | | +| fps | 309 | +| iterations | 9238 | +| time_elapsed | 30565 | +| total_timesteps | 9459712 | +| train/ | | +| approx_kl | 2.1015077 | +| clip_fraction | 0.459 | +| clip_range | 0.2 | +| entropy_loss | -0.364 | +| explained_variance | -0.739 | +| learning_rate | 0.0001 | +| loss | -0.113 | +| n_updates | 152900 | +| policy_gradient_loss | -0.0642 | +| value_loss | 0.000367 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.213 | +| time/ | | +| fps | 309 | +| iterations | 9239 | +| time_elapsed | 30568 | +| total_timesteps | 9460736 | +| train/ | | +| approx_kl | 1.776201 | +| clip_fraction | 0.431 | +| clip_range | 0.2 | +| entropy_loss | -0.343 | +| explained_variance | -1.57 | +| learning_rate | 0.0001 | +| loss | -0.0814 | +| n_updates | 152910 | +| policy_gradient_loss | -0.062 | +| value_loss | 0.000407 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.213 | +| time/ | | +| fps | 309 | +| iterations | 9240 | +| time_elapsed | 30571 | +| total_timesteps | 9461760 | +| train/ | | +| approx_kl | 3.0170135 | +| clip_fraction | 0.47 | +| clip_range | 0.2 | +| entropy_loss | -0.389 | +| explained_variance | -1.49 | +| learning_rate | 0.0001 | +| loss | -0.119 | +| n_updates | 152920 | +| policy_gradient_loss | -0.0698 | +| value_loss | 0.000355 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.212 | +| time/ | | +| fps | 309 | +| iterations | 9241 | +| time_elapsed | 30574 | +| total_timesteps | 9462784 | +| train/ | | +| approx_kl | 1.9792516 | +| clip_fraction | 0.439 | +| clip_range | 0.2 | +| entropy_loss | -0.334 | +| explained_variance | -0.745 | +| learning_rate | 0.0001 | +| loss | -0.0611 | +| n_updates | 152930 | +| policy_gradient_loss | -0.0602 | +| value_loss | 0.000675 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.212 | +| time/ | | +| fps | 309 | +| iterations | 9242 | +| time_elapsed | 30578 | +| total_timesteps | 9463808 | +| train/ | | +| approx_kl | 2.5000083 | +| clip_fraction | 0.462 | +| clip_range | 0.2 | +| entropy_loss | -0.338 | +| explained_variance | -0.831 | +| learning_rate | 0.0001 | +| loss | -0.0924 | +| n_updates | 152940 | +| policy_gradient_loss | -0.0674 | +| value_loss | 0.000694 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.2 | +| time/ | | +| fps | 309 | +| iterations | 9243 | +| time_elapsed | 30581 | +| total_timesteps | 9464832 | +| train/ | | +| approx_kl | 3.4353473 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.338 | +| explained_variance | -5.46 | +| learning_rate | 0.0001 | +| loss | -0.0975 | +| n_updates | 152950 | +| policy_gradient_loss | -0.0755 | +| value_loss | 0.000625 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.2 | +| time/ | | +| fps | 309 | +| iterations | 9244 | +| time_elapsed | 30585 | +| total_timesteps | 9465856 | +| train/ | | +| approx_kl | 2.8158686 | +| clip_fraction | 0.449 | +| clip_range | 0.2 | +| entropy_loss | -0.32 | +| explained_variance | -2.15 | +| learning_rate | 0.0001 | +| loss | -0.0661 | +| n_updates | 152960 | +| policy_gradient_loss | -0.0515 | +| value_loss | 0.000554 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.199 | +| time/ | | +| fps | 309 | +| iterations | 9245 | +| time_elapsed | 30589 | +| total_timesteps | 9466880 | +| train/ | | +| approx_kl | 2.5706744 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.387 | +| explained_variance | -4.24 | +| learning_rate | 0.0001 | +| loss | -0.0987 | +| n_updates | 152970 | +| policy_gradient_loss | -0.07 | +| value_loss | 0.000327 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.202 | +| time/ | | +| fps | 309 | +| iterations | 9246 | +| time_elapsed | 30592 | +| total_timesteps | 9467904 | +| train/ | | +| approx_kl | 2.418575 | +| clip_fraction | 0.518 | +| clip_range | 0.2 | +| entropy_loss | -0.381 | +| explained_variance | -1.49 | +| learning_rate | 0.0001 | +| loss | -0.083 | +| n_updates | 152980 | +| policy_gradient_loss | -0.0735 | +| value_loss | 0.000404 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.202 | +| time/ | | +| fps | 309 | +| iterations | 9247 | +| time_elapsed | 30596 | +| total_timesteps | 9468928 | +| train/ | | +| approx_kl | 5.2678556 | +| clip_fraction | 0.461 | +| clip_range | 0.2 | +| entropy_loss | -0.372 | +| explained_variance | -3.27 | +| learning_rate | 0.0001 | +| loss | -0.112 | +| n_updates | 152990 | +| policy_gradient_loss | -0.0648 | +| value_loss | 0.00039 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.202 | +| time/ | | +| fps | 309 | +| iterations | 9248 | +| time_elapsed | 30599 | +| total_timesteps | 9469952 | +| train/ | | +| approx_kl | 2.474426 | +| clip_fraction | 0.488 | +| clip_range | 0.2 | +| entropy_loss | -0.376 | +| explained_variance | -0.795 | +| learning_rate | 0.0001 | +| loss | -0.075 | +| n_updates | 153000 | +| policy_gradient_loss | -0.0631 | +| value_loss | 0.000603 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.2 | +| time/ | | +| fps | 309 | +| iterations | 9249 | +| time_elapsed | 30603 | +| total_timesteps | 9470976 | +| train/ | | +| approx_kl | 1.9020469 | +| clip_fraction | 0.448 | +| clip_range | 0.2 | +| entropy_loss | -0.357 | +| explained_variance | -1.82 | +| learning_rate | 0.0001 | +| loss | -0.0904 | +| n_updates | 153010 | +| policy_gradient_loss | -0.0629 | +| value_loss | 0.000583 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.199 | +| time/ | | +| fps | 309 | +| iterations | 9250 | +| time_elapsed | 30606 | +| total_timesteps | 9472000 | +| train/ | | +| approx_kl | 4.3048353 | +| clip_fraction | 0.449 | +| clip_range | 0.2 | +| entropy_loss | -0.321 | +| explained_variance | -2.49 | +| learning_rate | 0.0001 | +| loss | -0.0604 | +| n_updates | 153020 | +| policy_gradient_loss | -0.0629 | +| value_loss | 0.000487 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.196 | +| time/ | | +| fps | 309 | +| iterations | 9251 | +| time_elapsed | 30610 | +| total_timesteps | 9473024 | +| train/ | | +| approx_kl | 1.9342093 | +| clip_fraction | 0.489 | +| clip_range | 0.2 | +| entropy_loss | -0.355 | +| explained_variance | -1.45 | +| learning_rate | 0.0001 | +| loss | -0.0696 | +| n_updates | 153030 | +| policy_gradient_loss | -0.0642 | +| value_loss | 0.000279 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.196 | +| time/ | | +| fps | 309 | +| iterations | 9252 | +| time_elapsed | 30613 | +| total_timesteps | 9474048 | +| train/ | | +| approx_kl | 1.911982 | +| clip_fraction | 0.454 | +| clip_range | 0.2 | +| entropy_loss | -0.361 | +| explained_variance | -0.819 | +| learning_rate | 0.0001 | +| loss | -0.0936 | +| n_updates | 153040 | +| policy_gradient_loss | -0.0596 | +| value_loss | 0.000508 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.199 | +| time/ | | +| fps | 309 | +| iterations | 9253 | +| time_elapsed | 30616 | +| total_timesteps | 9475072 | +| train/ | | +| approx_kl | 1.5693053 | +| clip_fraction | 0.47 | +| clip_range | 0.2 | +| entropy_loss | -0.4 | +| explained_variance | -1.46 | +| learning_rate | 0.0001 | +| loss | -0.0799 | +| n_updates | 153050 | +| policy_gradient_loss | -0.0656 | +| value_loss | 0.000458 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.195 | +| time/ | | +| fps | 309 | +| iterations | 9254 | +| time_elapsed | 30619 | +| total_timesteps | 9476096 | +| train/ | | +| approx_kl | 3.0584698 | +| clip_fraction | 0.47 | +| clip_range | 0.2 | +| entropy_loss | -0.344 | +| explained_variance | -2.35 | +| learning_rate | 0.0001 | +| loss | -0.0983 | +| n_updates | 153060 | +| policy_gradient_loss | -0.0744 | +| value_loss | 0.000491 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.195 | +| time/ | | +| fps | 309 | +| iterations | 9255 | +| time_elapsed | 30623 | +| total_timesteps | 9477120 | +| train/ | | +| approx_kl | 1.3405625 | +| clip_fraction | 0.457 | +| clip_range | 0.2 | +| entropy_loss | -0.433 | +| explained_variance | -0.895 | +| learning_rate | 0.0001 | +| loss | -0.0819 | +| n_updates | 153070 | +| policy_gradient_loss | -0.0665 | +| value_loss | 0.000343 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.195 | +| time/ | | +| fps | 309 | +| iterations | 9256 | +| time_elapsed | 30626 | +| total_timesteps | 9478144 | +| train/ | | +| approx_kl | 2.1060348 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.342 | +| explained_variance | -2.16 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 153080 | +| policy_gradient_loss | -0.0736 | +| value_loss | 0.000342 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.195 | +| time/ | | +| fps | 309 | +| iterations | 9257 | +| time_elapsed | 30629 | +| total_timesteps | 9479168 | +| train/ | | +| approx_kl | 2.3814833 | +| clip_fraction | 0.466 | +| clip_range | 0.2 | +| entropy_loss | -0.339 | +| explained_variance | -1.19 | +| learning_rate | 0.0001 | +| loss | -0.0998 | +| n_updates | 153090 | +| policy_gradient_loss | -0.0689 | +| value_loss | 0.000454 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.2 | +| time/ | | +| fps | 309 | +| iterations | 9258 | +| time_elapsed | 30632 | +| total_timesteps | 9480192 | +| train/ | | +| approx_kl | 2.5022655 | +| clip_fraction | 0.513 | +| clip_range | 0.2 | +| entropy_loss | -0.388 | +| explained_variance | -0.961 | +| learning_rate | 0.0001 | +| loss | -0.0981 | +| n_updates | 153100 | +| policy_gradient_loss | -0.0723 | +| value_loss | 0.000567 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.204 | +| time/ | | +| fps | 309 | +| iterations | 9259 | +| time_elapsed | 30636 | +| total_timesteps | 9481216 | +| train/ | | +| approx_kl | 2.5572639 | +| clip_fraction | 0.51 | +| clip_range | 0.2 | +| entropy_loss | -0.394 | +| explained_variance | -0.783 | +| learning_rate | 0.0001 | +| loss | -0.124 | +| n_updates | 153110 | +| policy_gradient_loss | -0.0697 | +| value_loss | 0.00043 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.2 | +| time/ | | +| fps | 309 | +| iterations | 9260 | +| time_elapsed | 30639 | +| total_timesteps | 9482240 | +| train/ | | +| approx_kl | 1.787292 | +| clip_fraction | 0.467 | +| clip_range | 0.2 | +| entropy_loss | -0.377 | +| explained_variance | -2.23 | +| learning_rate | 0.0001 | +| loss | -0.0981 | +| n_updates | 153120 | +| policy_gradient_loss | -0.0718 | +| value_loss | 0.000427 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.2 | +| time/ | | +| fps | 309 | +| iterations | 9261 | +| time_elapsed | 30642 | +| total_timesteps | 9483264 | +| train/ | | +| approx_kl | 2.1032 | +| clip_fraction | 0.445 | +| clip_range | 0.2 | +| entropy_loss | -0.324 | +| explained_variance | -0.771 | +| learning_rate | 0.0001 | +| loss | -0.0977 | +| n_updates | 153130 | +| policy_gradient_loss | -0.0571 | +| value_loss | 0.000513 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.2 | +| time/ | | +| fps | 309 | +| iterations | 9262 | +| time_elapsed | 30646 | +| total_timesteps | 9484288 | +| train/ | | +| approx_kl | 2.1194146 | +| clip_fraction | 0.444 | +| clip_range | 0.2 | +| entropy_loss | -0.336 | +| explained_variance | -1.4 | +| learning_rate | 0.0001 | +| loss | -0.068 | +| n_updates | 153140 | +| policy_gradient_loss | -0.0631 | +| value_loss | 0.000689 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.201 | +| time/ | | +| fps | 309 | +| iterations | 9263 | +| time_elapsed | 30649 | +| total_timesteps | 9485312 | +| train/ | | +| approx_kl | 2.2203827 | +| clip_fraction | 0.478 | +| clip_range | 0.2 | +| entropy_loss | -0.352 | +| explained_variance | -1.32 | +| learning_rate | 0.0001 | +| loss | -0.0934 | +| n_updates | 153150 | +| policy_gradient_loss | -0.0695 | +| value_loss | 0.000894 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.204 | +| time/ | | +| fps | 309 | +| iterations | 9264 | +| time_elapsed | 30653 | +| total_timesteps | 9486336 | +| train/ | | +| approx_kl | 2.7369366 | +| clip_fraction | 0.491 | +| clip_range | 0.2 | +| entropy_loss | -0.328 | +| explained_variance | -1.93 | +| learning_rate | 0.0001 | +| loss | -0.0991 | +| n_updates | 153160 | +| policy_gradient_loss | -0.0772 | +| value_loss | 0.000556 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.204 | +| time/ | | +| fps | 309 | +| iterations | 9265 | +| time_elapsed | 30656 | +| total_timesteps | 9487360 | +| train/ | | +| approx_kl | 3.5895052 | +| clip_fraction | 0.489 | +| clip_range | 0.2 | +| entropy_loss | -0.356 | +| explained_variance | -1.47 | +| learning_rate | 0.0001 | +| loss | -0.0819 | +| n_updates | 153170 | +| policy_gradient_loss | -0.0694 | +| value_loss | 0.000503 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.205 | +| time/ | | +| fps | 309 | +| iterations | 9266 | +| time_elapsed | 30660 | +| total_timesteps | 9488384 | +| train/ | | +| approx_kl | 1.8704975 | +| clip_fraction | 0.469 | +| clip_range | 0.2 | +| entropy_loss | -0.368 | +| explained_variance | -1.75 | +| learning_rate | 0.0001 | +| loss | -0.0807 | +| n_updates | 153180 | +| policy_gradient_loss | -0.0609 | +| value_loss | 0.000639 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.203 | +| time/ | | +| fps | 309 | +| iterations | 9267 | +| time_elapsed | 30663 | +| total_timesteps | 9489408 | +| train/ | | +| approx_kl | 2.0960896 | +| clip_fraction | 0.474 | +| clip_range | 0.2 | +| entropy_loss | -0.331 | +| explained_variance | -3.84 | +| learning_rate | 0.0001 | +| loss | -0.0757 | +| n_updates | 153190 | +| policy_gradient_loss | -0.0595 | +| value_loss | 0.000522 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.199 | +| time/ | | +| fps | 309 | +| iterations | 9268 | +| time_elapsed | 30667 | +| total_timesteps | 9490432 | +| train/ | | +| approx_kl | 2.1144466 | +| clip_fraction | 0.458 | +| clip_range | 0.2 | +| entropy_loss | -0.323 | +| explained_variance | -3.54 | +| learning_rate | 0.0001 | +| loss | -0.0781 | +| n_updates | 153200 | +| policy_gradient_loss | -0.0649 | +| value_loss | 0.000342 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.195 | +| time/ | | +| fps | 309 | +| iterations | 9269 | +| time_elapsed | 30670 | +| total_timesteps | 9491456 | +| train/ | | +| approx_kl | 3.6945105 | +| clip_fraction | 0.478 | +| clip_range | 0.2 | +| entropy_loss | -0.347 | +| explained_variance | -2.37 | +| learning_rate | 0.0001 | +| loss | -0.0958 | +| n_updates | 153210 | +| policy_gradient_loss | -0.0734 | +| value_loss | 0.000524 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.195 | +| time/ | | +| fps | 309 | +| iterations | 9270 | +| time_elapsed | 30673 | +| total_timesteps | 9492480 | +| train/ | | +| approx_kl | 2.532605 | +| clip_fraction | 0.448 | +| clip_range | 0.2 | +| entropy_loss | -0.341 | +| explained_variance | -1.42 | +| learning_rate | 0.0001 | +| loss | -0.0953 | +| n_updates | 153220 | +| policy_gradient_loss | -0.0644 | +| value_loss | 0.000452 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.198 | +| time/ | | +| fps | 309 | +| iterations | 9271 | +| time_elapsed | 30676 | +| total_timesteps | 9493504 | +| train/ | | +| approx_kl | 2.932332 | +| clip_fraction | 0.478 | +| clip_range | 0.2 | +| entropy_loss | -0.295 | +| explained_variance | -1.62 | +| learning_rate | 0.0001 | +| loss | -0.0999 | +| n_updates | 153230 | +| policy_gradient_loss | -0.0628 | +| value_loss | 0.000548 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.198 | +| time/ | | +| fps | 309 | +| iterations | 9272 | +| time_elapsed | 30680 | +| total_timesteps | 9494528 | +| train/ | | +| approx_kl | 2.1882215 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.379 | +| explained_variance | -0.605 | +| learning_rate | 0.0001 | +| loss | -0.0982 | +| n_updates | 153240 | +| policy_gradient_loss | -0.0663 | +| value_loss | 0.000798 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.198 | +| time/ | | +| fps | 309 | +| iterations | 9273 | +| time_elapsed | 30683 | +| total_timesteps | 9495552 | +| train/ | | +| approx_kl | 2.542715 | +| clip_fraction | 0.465 | +| clip_range | 0.2 | +| entropy_loss | -0.352 | +| explained_variance | -1.54 | +| learning_rate | 0.0001 | +| loss | -0.0944 | +| n_updates | 153250 | +| policy_gradient_loss | -0.0724 | +| value_loss | 0.000653 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.202 | +| time/ | | +| fps | 309 | +| iterations | 9274 | +| time_elapsed | 30686 | +| total_timesteps | 9496576 | +| train/ | | +| approx_kl | 2.3600054 | +| clip_fraction | 0.445 | +| clip_range | 0.2 | +| entropy_loss | -0.317 | +| explained_variance | -2.97 | +| learning_rate | 0.0001 | +| loss | -0.0603 | +| n_updates | 153260 | +| policy_gradient_loss | -0.0672 | +| value_loss | 0.000564 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.196 | +| time/ | | +| fps | 309 | +| iterations | 9275 | +| time_elapsed | 30690 | +| total_timesteps | 9497600 | +| train/ | | +| approx_kl | 4.2207274 | +| clip_fraction | 0.49 | +| clip_range | 0.2 | +| entropy_loss | -0.394 | +| explained_variance | -1.03 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 153270 | +| policy_gradient_loss | -0.0644 | +| value_loss | 0.000459 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.191 | +| time/ | | +| fps | 309 | +| iterations | 9276 | +| time_elapsed | 30693 | +| total_timesteps | 9498624 | +| train/ | | +| approx_kl | 1.9390084 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.381 | +| explained_variance | -1.76 | +| learning_rate | 0.0001 | +| loss | -0.077 | +| n_updates | 153280 | +| policy_gradient_loss | -0.064 | +| value_loss | 0.000396 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.191 | +| time/ | | +| fps | 309 | +| iterations | 9277 | +| time_elapsed | 30696 | +| total_timesteps | 9499648 | +| train/ | | +| approx_kl | 2.4045577 | +| clip_fraction | 0.482 | +| clip_range | 0.2 | +| entropy_loss | -0.377 | +| explained_variance | -1.52 | +| learning_rate | 0.0001 | +| loss | -0.0704 | +| n_updates | 153290 | +| policy_gradient_loss | -0.0709 | +| value_loss | 0.000431 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.191 | +| time/ | | +| fps | 309 | +| iterations | 9278 | +| time_elapsed | 30699 | +| total_timesteps | 9500672 | +| train/ | | +| approx_kl | 2.1480403 | +| clip_fraction | 0.504 | +| clip_range | 0.2 | +| entropy_loss | -0.416 | +| explained_variance | -1.4 | +| learning_rate | 0.0001 | +| loss | -0.114 | +| n_updates | 153300 | +| policy_gradient_loss | -0.0709 | +| value_loss | 0.000442 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.191 | +| time/ | | +| fps | 309 | +| iterations | 9279 | +| time_elapsed | 30703 | +| total_timesteps | 9501696 | +| train/ | | +| approx_kl | 2.5615344 | +| clip_fraction | 0.449 | +| clip_range | 0.2 | +| entropy_loss | -0.3 | +| explained_variance | -1.82 | +| learning_rate | 0.0001 | +| loss | -0.0964 | +| n_updates | 153310 | +| policy_gradient_loss | -0.0694 | +| value_loss | 0.000585 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.197 | +| time/ | | +| fps | 309 | +| iterations | 9280 | +| time_elapsed | 30706 | +| total_timesteps | 9502720 | +| train/ | | +| approx_kl | 2.1161327 | +| clip_fraction | 0.437 | +| clip_range | 0.2 | +| entropy_loss | -0.318 | +| explained_variance | -0.821 | +| learning_rate | 0.0001 | +| loss | -0.0837 | +| n_updates | 153320 | +| policy_gradient_loss | -0.0621 | +| value_loss | 0.000582 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.194 | +| time/ | | +| fps | 309 | +| iterations | 9281 | +| time_elapsed | 30710 | +| total_timesteps | 9503744 | +| train/ | | +| approx_kl | 2.435606 | +| clip_fraction | 0.482 | +| clip_range | 0.2 | +| entropy_loss | -0.33 | +| explained_variance | -0.931 | +| learning_rate | 0.0001 | +| loss | -0.0735 | +| n_updates | 153330 | +| policy_gradient_loss | -0.0691 | +| value_loss | 0.000661 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.194 | +| time/ | | +| fps | 309 | +| iterations | 9282 | +| time_elapsed | 30713 | +| total_timesteps | 9504768 | +| train/ | | +| approx_kl | 2.630879 | +| clip_fraction | 0.442 | +| clip_range | 0.2 | +| entropy_loss | -0.3 | +| explained_variance | -2.98 | +| learning_rate | 0.0001 | +| loss | -0.0743 | +| n_updates | 153340 | +| policy_gradient_loss | -0.0647 | +| value_loss | 0.00044 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.191 | +| time/ | | +| fps | 309 | +| iterations | 9283 | +| time_elapsed | 30717 | +| total_timesteps | 9505792 | +| train/ | | +| approx_kl | 2.1915092 | +| clip_fraction | 0.52 | +| clip_range | 0.2 | +| entropy_loss | -0.442 | +| explained_variance | -1.1 | +| learning_rate | 0.0001 | +| loss | -0.0998 | +| n_updates | 153350 | +| policy_gradient_loss | -0.0701 | +| value_loss | 0.000398 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.187 | +| time/ | | +| fps | 309 | +| iterations | 9284 | +| time_elapsed | 30720 | +| total_timesteps | 9506816 | +| train/ | | +| approx_kl | 2.2964482 | +| clip_fraction | 0.466 | +| clip_range | 0.2 | +| entropy_loss | -0.32 | +| explained_variance | -1.37 | +| learning_rate | 0.0001 | +| loss | -0.0802 | +| n_updates | 153360 | +| policy_gradient_loss | -0.0639 | +| value_loss | 0.000573 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.187 | +| time/ | | +| fps | 309 | +| iterations | 9285 | +| time_elapsed | 30724 | +| total_timesteps | 9507840 | +| train/ | | +| approx_kl | 2.273985 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.374 | +| explained_variance | -2.19 | +| learning_rate | 0.0001 | +| loss | -0.107 | +| n_updates | 153370 | +| policy_gradient_loss | -0.0755 | +| value_loss | 0.000442 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.188 | +| time/ | | +| fps | 309 | +| iterations | 9286 | +| time_elapsed | 30727 | +| total_timesteps | 9508864 | +| train/ | | +| approx_kl | 2.4799554 | +| clip_fraction | 0.479 | +| clip_range | 0.2 | +| entropy_loss | -0.373 | +| explained_variance | -1.58 | +| learning_rate | 0.0001 | +| loss | -0.117 | +| n_updates | 153380 | +| policy_gradient_loss | -0.0717 | +| value_loss | 0.000308 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.182 | +| time/ | | +| fps | 309 | +| iterations | 9287 | +| time_elapsed | 30731 | +| total_timesteps | 9509888 | +| train/ | | +| approx_kl | 2.3151834 | +| clip_fraction | 0.47 | +| clip_range | 0.2 | +| entropy_loss | -0.35 | +| explained_variance | -0.884 | +| learning_rate | 0.0001 | +| loss | -0.0741 | +| n_updates | 153390 | +| policy_gradient_loss | -0.0672 | +| value_loss | 0.000485 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.178 | +| time/ | | +| fps | 309 | +| iterations | 9288 | +| time_elapsed | 30734 | +| total_timesteps | 9510912 | +| train/ | | +| approx_kl | 2.214047 | +| clip_fraction | 0.401 | +| clip_range | 0.2 | +| entropy_loss | -0.253 | +| explained_variance | -1.64 | +| learning_rate | 0.0001 | +| loss | -0.0818 | +| n_updates | 153400 | +| policy_gradient_loss | -0.0614 | +| value_loss | 0.000528 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.178 | +| time/ | | +| fps | 309 | +| iterations | 9289 | +| time_elapsed | 30737 | +| total_timesteps | 9511936 | +| train/ | | +| approx_kl | 2.128436 | +| clip_fraction | 0.51 | +| clip_range | 0.2 | +| entropy_loss | -0.392 | +| explained_variance | -1.14 | +| learning_rate | 0.0001 | +| loss | -0.073 | +| n_updates | 153410 | +| policy_gradient_loss | -0.0696 | +| value_loss | 0.00059 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.183 | +| time/ | | +| fps | 309 | +| iterations | 9290 | +| time_elapsed | 30740 | +| total_timesteps | 9512960 | +| train/ | | +| approx_kl | 3.256668 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.335 | +| explained_variance | -2.68 | +| learning_rate | 0.0001 | +| loss | -0.0952 | +| n_updates | 153420 | +| policy_gradient_loss | -0.0697 | +| value_loss | 0.000629 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.183 | +| time/ | | +| fps | 309 | +| iterations | 9291 | +| time_elapsed | 30744 | +| total_timesteps | 9513984 | +| train/ | | +| approx_kl | 3.0498376 | +| clip_fraction | 0.467 | +| clip_range | 0.2 | +| entropy_loss | -0.313 | +| explained_variance | -2.51 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 153430 | +| policy_gradient_loss | -0.0673 | +| value_loss | 0.000419 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.184 | +| time/ | | +| fps | 309 | +| iterations | 9292 | +| time_elapsed | 30747 | +| total_timesteps | 9515008 | +| train/ | | +| approx_kl | 2.1885033 | +| clip_fraction | 0.497 | +| clip_range | 0.2 | +| entropy_loss | -0.396 | +| explained_variance | -1.11 | +| learning_rate | 0.0001 | +| loss | -0.0837 | +| n_updates | 153440 | +| policy_gradient_loss | -0.0689 | +| value_loss | 0.000484 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.19 | +| time/ | | +| fps | 309 | +| iterations | 9293 | +| time_elapsed | 30750 | +| total_timesteps | 9516032 | +| train/ | | +| approx_kl | 2.3326797 | +| clip_fraction | 0.511 | +| clip_range | 0.2 | +| entropy_loss | -0.385 | +| explained_variance | -1.24 | +| learning_rate | 0.0001 | +| loss | -0.0842 | +| n_updates | 153450 | +| policy_gradient_loss | -0.0772 | +| value_loss | 0.000537 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.19 | +| time/ | | +| fps | 309 | +| iterations | 9294 | +| time_elapsed | 30753 | +| total_timesteps | 9517056 | +| train/ | | +| approx_kl | 2.0019982 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.348 | +| explained_variance | -1.89 | +| learning_rate | 0.0001 | +| loss | -0.0235 | +| n_updates | 153460 | +| policy_gradient_loss | -0.0662 | +| value_loss | 0.000659 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.192 | +| time/ | | +| fps | 309 | +| iterations | 9295 | +| time_elapsed | 30756 | +| total_timesteps | 9518080 | +| train/ | | +| approx_kl | 2.099722 | +| clip_fraction | 0.492 | +| clip_range | 0.2 | +| entropy_loss | -0.369 | +| explained_variance | -1.91 | +| learning_rate | 0.0001 | +| loss | -0.0882 | +| n_updates | 153470 | +| policy_gradient_loss | -0.0677 | +| value_loss | 0.000523 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.192 | +| time/ | | +| fps | 309 | +| iterations | 9296 | +| time_elapsed | 30759 | +| total_timesteps | 9519104 | +| train/ | | +| approx_kl | 1.8930895 | +| clip_fraction | 0.493 | +| clip_range | 0.2 | +| entropy_loss | -0.406 | +| explained_variance | -2.3 | +| learning_rate | 0.0001 | +| loss | -0.0813 | +| n_updates | 153480 | +| policy_gradient_loss | -0.0711 | +| value_loss | 0.000416 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.197 | +| time/ | | +| fps | 309 | +| iterations | 9297 | +| time_elapsed | 30763 | +| total_timesteps | 9520128 | +| train/ | | +| approx_kl | 1.8821132 | +| clip_fraction | 0.465 | +| clip_range | 0.2 | +| entropy_loss | -0.313 | +| explained_variance | -0.925 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 153490 | +| policy_gradient_loss | -0.0679 | +| value_loss | 0.000592 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.189 | +| time/ | | +| fps | 309 | +| iterations | 9298 | +| time_elapsed | 30766 | +| total_timesteps | 9521152 | +| train/ | | +| approx_kl | 2.7435775 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.338 | +| explained_variance | -3.47 | +| learning_rate | 0.0001 | +| loss | -0.107 | +| n_updates | 153500 | +| policy_gradient_loss | -0.0801 | +| value_loss | 0.000345 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.19 | +| time/ | | +| fps | 309 | +| iterations | 9299 | +| time_elapsed | 30769 | +| total_timesteps | 9522176 | +| train/ | | +| approx_kl | 1.9438303 | +| clip_fraction | 0.467 | +| clip_range | 0.2 | +| entropy_loss | -0.346 | +| explained_variance | -0.799 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 153510 | +| policy_gradient_loss | -0.0604 | +| value_loss | 0.00052 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.19 | +| time/ | | +| fps | 309 | +| iterations | 9300 | +| time_elapsed | 30773 | +| total_timesteps | 9523200 | +| train/ | | +| approx_kl | 2.649548 | +| clip_fraction | 0.454 | +| clip_range | 0.2 | +| entropy_loss | -0.349 | +| explained_variance | -1.47 | +| learning_rate | 0.0001 | +| loss | -0.0893 | +| n_updates | 153520 | +| policy_gradient_loss | -0.0568 | +| value_loss | 0.00041 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.186 | +| time/ | | +| fps | 309 | +| iterations | 9301 | +| time_elapsed | 30776 | +| total_timesteps | 9524224 | +| train/ | | +| approx_kl | 1.9613413 | +| clip_fraction | 0.495 | +| clip_range | 0.2 | +| entropy_loss | -0.43 | +| explained_variance | -1.81 | +| learning_rate | 0.0001 | +| loss | -0.0933 | +| n_updates | 153530 | +| policy_gradient_loss | -0.0671 | +| value_loss | 0.000291 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.182 | +| time/ | | +| fps | 309 | +| iterations | 9302 | +| time_elapsed | 30779 | +| total_timesteps | 9525248 | +| train/ | | +| approx_kl | 2.1085577 | +| clip_fraction | 0.438 | +| clip_range | 0.2 | +| entropy_loss | -0.344 | +| explained_variance | -0.979 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 153540 | +| policy_gradient_loss | -0.0623 | +| value_loss | 0.000439 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.182 | +| time/ | | +| fps | 309 | +| iterations | 9303 | +| time_elapsed | 30783 | +| total_timesteps | 9526272 | +| train/ | | +| approx_kl | 2.6427622 | +| clip_fraction | 0.449 | +| clip_range | 0.2 | +| entropy_loss | -0.313 | +| explained_variance | -1.09 | +| learning_rate | 0.0001 | +| loss | -0.0902 | +| n_updates | 153550 | +| policy_gradient_loss | -0.0549 | +| value_loss | 0.00033 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.182 | +| time/ | | +| fps | 309 | +| iterations | 9304 | +| time_elapsed | 30786 | +| total_timesteps | 9527296 | +| train/ | | +| approx_kl | 2.3364682 | +| clip_fraction | 0.509 | +| clip_range | 0.2 | +| entropy_loss | -0.375 | +| explained_variance | -1.92 | +| learning_rate | 0.0001 | +| loss | -0.0703 | +| n_updates | 153560 | +| policy_gradient_loss | -0.00559 | +| value_loss | 0.000427 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.179 | +| time/ | | +| fps | 309 | +| iterations | 9305 | +| time_elapsed | 30789 | +| total_timesteps | 9528320 | +| train/ | | +| approx_kl | 2.5737183 | +| clip_fraction | 0.492 | +| clip_range | 0.2 | +| entropy_loss | -0.364 | +| explained_variance | -1.94 | +| learning_rate | 0.0001 | +| loss | -0.0782 | +| n_updates | 153570 | +| policy_gradient_loss | -0.0705 | +| value_loss | 0.000626 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.186 | +| time/ | | +| fps | 309 | +| iterations | 9306 | +| time_elapsed | 30793 | +| total_timesteps | 9529344 | +| train/ | | +| approx_kl | 2.2818537 | +| clip_fraction | 0.491 | +| clip_range | 0.2 | +| entropy_loss | -0.352 | +| explained_variance | -1.56 | +| learning_rate | 0.0001 | +| loss | -0.0909 | +| n_updates | 153580 | +| policy_gradient_loss | -0.0768 | +| value_loss | 0.000596 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.186 | +| time/ | | +| fps | 309 | +| iterations | 9307 | +| time_elapsed | 30796 | +| total_timesteps | 9530368 | +| train/ | | +| approx_kl | 2.1608593 | +| clip_fraction | 0.452 | +| clip_range | 0.2 | +| entropy_loss | -0.342 | +| explained_variance | -0.455 | +| learning_rate | 0.0001 | +| loss | -0.0657 | +| n_updates | 153590 | +| policy_gradient_loss | -0.0609 | +| value_loss | 0.000947 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.184 | +| time/ | | +| fps | 309 | +| iterations | 9308 | +| time_elapsed | 30799 | +| total_timesteps | 9531392 | +| train/ | | +| approx_kl | 2.2797318 | +| clip_fraction | 0.52 | +| clip_range | 0.2 | +| entropy_loss | -0.35 | +| explained_variance | -3.53 | +| learning_rate | 0.0001 | +| loss | -0.0855 | +| n_updates | 153600 | +| policy_gradient_loss | -0.0754 | +| value_loss | 0.000501 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.187 | +| time/ | | +| fps | 309 | +| iterations | 9309 | +| time_elapsed | 30802 | +| total_timesteps | 9532416 | +| train/ | | +| approx_kl | 1.9734116 | +| clip_fraction | 0.469 | +| clip_range | 0.2 | +| entropy_loss | -0.354 | +| explained_variance | -1.07 | +| learning_rate | 0.0001 | +| loss | -0.108 | +| n_updates | 153610 | +| policy_gradient_loss | -0.0635 | +| value_loss | 0.000406 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.19 | +| time/ | | +| fps | 309 | +| iterations | 9310 | +| time_elapsed | 30805 | +| total_timesteps | 9533440 | +| train/ | | +| approx_kl | 3.0575194 | +| clip_fraction | 0.455 | +| clip_range | 0.2 | +| entropy_loss | -0.347 | +| explained_variance | -0.93 | +| learning_rate | 0.0001 | +| loss | -0.0935 | +| n_updates | 153620 | +| policy_gradient_loss | -0.0687 | +| value_loss | 0.000562 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.191 | +| time/ | | +| fps | 309 | +| iterations | 9311 | +| time_elapsed | 30808 | +| total_timesteps | 9534464 | +| train/ | | +| approx_kl | 3.330861 | +| clip_fraction | 0.485 | +| clip_range | 0.2 | +| entropy_loss | -0.342 | +| explained_variance | -1.14 | +| learning_rate | 0.0001 | +| loss | -0.0897 | +| n_updates | 153630 | +| policy_gradient_loss | -0.0731 | +| value_loss | 0.000736 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.191 | +| time/ | | +| fps | 309 | +| iterations | 9312 | +| time_elapsed | 30812 | +| total_timesteps | 9535488 | +| train/ | | +| approx_kl | 2.7428122 | +| clip_fraction | 0.472 | +| clip_range | 0.2 | +| entropy_loss | -0.321 | +| explained_variance | -3.27 | +| learning_rate | 0.0001 | +| loss | -0.0722 | +| n_updates | 153640 | +| policy_gradient_loss | -0.0711 | +| value_loss | 0.000533 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.193 | +| time/ | | +| fps | 309 | +| iterations | 9313 | +| time_elapsed | 30815 | +| total_timesteps | 9536512 | +| train/ | | +| approx_kl | 3.6996856 | +| clip_fraction | 0.5 | +| clip_range | 0.2 | +| entropy_loss | -0.388 | +| explained_variance | -1.94 | +| learning_rate | 0.0001 | +| loss | -0.0709 | +| n_updates | 153650 | +| policy_gradient_loss | -0.0686 | +| value_loss | 0.00041 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.188 | +| time/ | | +| fps | 309 | +| iterations | 9314 | +| time_elapsed | 30818 | +| total_timesteps | 9537536 | +| train/ | | +| approx_kl | 2.09929 | +| clip_fraction | 0.464 | +| clip_range | 0.2 | +| entropy_loss | -0.334 | +| explained_variance | -1.53 | +| learning_rate | 0.0001 | +| loss | -0.098 | +| n_updates | 153660 | +| policy_gradient_loss | -0.0702 | +| value_loss | 0.000357 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.186 | +| time/ | | +| fps | 309 | +| iterations | 9315 | +| time_elapsed | 30822 | +| total_timesteps | 9538560 | +| train/ | | +| approx_kl | 1.7808383 | +| clip_fraction | 0.448 | +| clip_range | 0.2 | +| entropy_loss | -0.347 | +| explained_variance | -1.11 | +| learning_rate | 0.0001 | +| loss | -0.0681 | +| n_updates | 153670 | +| policy_gradient_loss | -0.0679 | +| value_loss | 0.000311 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.18 | +| time/ | | +| fps | 309 | +| iterations | 9316 | +| time_elapsed | 30825 | +| total_timesteps | 9539584 | +| train/ | | +| approx_kl | 1.8294904 | +| clip_fraction | 0.469 | +| clip_range | 0.2 | +| entropy_loss | -0.368 | +| explained_variance | -0.866 | +| learning_rate | 0.0001 | +| loss | -0.0813 | +| n_updates | 153680 | +| policy_gradient_loss | -0.067 | +| value_loss | 0.000444 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.18 | +| time/ | | +| fps | 309 | +| iterations | 9317 | +| time_elapsed | 30828 | +| total_timesteps | 9540608 | +| train/ | | +| approx_kl | 2.964693 | +| clip_fraction | 0.485 | +| clip_range | 0.2 | +| entropy_loss | -0.345 | +| explained_variance | -1.15 | +| learning_rate | 0.0001 | +| loss | -0.0845 | +| n_updates | 153690 | +| policy_gradient_loss | -0.0683 | +| value_loss | 0.000415 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.18 | +| time/ | | +| fps | 309 | +| iterations | 9318 | +| time_elapsed | 30832 | +| total_timesteps | 9541632 | +| train/ | | +| approx_kl | 2.375694 | +| clip_fraction | 0.489 | +| clip_range | 0.2 | +| entropy_loss | -0.343 | +| explained_variance | -3.45 | +| learning_rate | 0.0001 | +| loss | -0.0925 | +| n_updates | 153700 | +| policy_gradient_loss | -0.0658 | +| value_loss | 0.000394 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.188 | +| time/ | | +| fps | 309 | +| iterations | 9319 | +| time_elapsed | 30835 | +| total_timesteps | 9542656 | +| train/ | | +| approx_kl | 2.2006862 | +| clip_fraction | 0.493 | +| clip_range | 0.2 | +| entropy_loss | -0.399 | +| explained_variance | -0.695 | +| learning_rate | 0.0001 | +| loss | -0.0651 | +| n_updates | 153710 | +| policy_gradient_loss | -0.0639 | +| value_loss | 0.000668 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.186 | +| time/ | | +| fps | 309 | +| iterations | 9320 | +| time_elapsed | 30839 | +| total_timesteps | 9543680 | +| train/ | | +| approx_kl | 2.2669482 | +| clip_fraction | 0.484 | +| clip_range | 0.2 | +| entropy_loss | -0.345 | +| explained_variance | -1.12 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 153720 | +| policy_gradient_loss | -0.0665 | +| value_loss | 0.000652 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.186 | +| time/ | | +| fps | 309 | +| iterations | 9321 | +| time_elapsed | 30842 | +| total_timesteps | 9544704 | +| train/ | | +| approx_kl | 2.2225442 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.359 | +| explained_variance | -1.3 | +| learning_rate | 0.0001 | +| loss | -0.0796 | +| n_updates | 153730 | +| policy_gradient_loss | -0.0724 | +| value_loss | 0.000646 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.19 | +| time/ | | +| fps | 309 | +| iterations | 9322 | +| time_elapsed | 30846 | +| total_timesteps | 9545728 | +| train/ | | +| approx_kl | 2.9023476 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.355 | +| explained_variance | -2.6 | +| learning_rate | 0.0001 | +| loss | -0.111 | +| n_updates | 153740 | +| policy_gradient_loss | -0.0663 | +| value_loss | 0.000352 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.185 | +| time/ | | +| fps | 309 | +| iterations | 9323 | +| time_elapsed | 30849 | +| total_timesteps | 9546752 | +| train/ | | +| approx_kl | 2.0580387 | +| clip_fraction | 0.469 | +| clip_range | 0.2 | +| entropy_loss | -0.324 | +| explained_variance | -0.611 | +| learning_rate | 0.0001 | +| loss | -0.0776 | +| n_updates | 153750 | +| policy_gradient_loss | -0.0717 | +| value_loss | 0.000219 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.183 | +| time/ | | +| fps | 309 | +| iterations | 9324 | +| time_elapsed | 30852 | +| total_timesteps | 9547776 | +| train/ | | +| approx_kl | 1.9803387 | +| clip_fraction | 0.44 | +| clip_range | 0.2 | +| entropy_loss | -0.316 | +| explained_variance | -0.546 | +| learning_rate | 0.0001 | +| loss | -0.0685 | +| n_updates | 153760 | +| policy_gradient_loss | -0.0588 | +| value_loss | 0.000407 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.186 | +| time/ | | +| fps | 309 | +| iterations | 9325 | +| time_elapsed | 30856 | +| total_timesteps | 9548800 | +| train/ | | +| approx_kl | 1.9126173 | +| clip_fraction | 0.461 | +| clip_range | 0.2 | +| entropy_loss | -0.35 | +| explained_variance | -1.37 | +| learning_rate | 0.0001 | +| loss | -0.0399 | +| n_updates | 153770 | +| policy_gradient_loss | -0.067 | +| value_loss | 0.000562 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.186 | +| time/ | | +| fps | 309 | +| iterations | 9326 | +| time_elapsed | 30859 | +| total_timesteps | 9549824 | +| train/ | | +| approx_kl | 1.5958731 | +| clip_fraction | 0.498 | +| clip_range | 0.2 | +| entropy_loss | -0.474 | +| explained_variance | 0.11 | +| learning_rate | 0.0001 | +| loss | -0.0954 | +| n_updates | 153780 | +| policy_gradient_loss | -0.0694 | +| value_loss | 0.000774 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.186 | +| time/ | | +| fps | 309 | +| iterations | 9327 | +| time_elapsed | 30862 | +| total_timesteps | 9550848 | +| train/ | | +| approx_kl | 2.1713636 | +| clip_fraction | 0.468 | +| clip_range | 0.2 | +| entropy_loss | -0.382 | +| explained_variance | -2.12 | +| learning_rate | 0.0001 | +| loss | -0.0977 | +| n_updates | 153790 | +| policy_gradient_loss | -0.0674 | +| value_loss | 0.000634 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.187 | +| time/ | | +| fps | 309 | +| iterations | 9328 | +| time_elapsed | 30865 | +| total_timesteps | 9551872 | +| train/ | | +| approx_kl | 2.3339543 | +| clip_fraction | 0.518 | +| clip_range | 0.2 | +| entropy_loss | -0.391 | +| explained_variance | -1.41 | +| learning_rate | 0.0001 | +| loss | -0.117 | +| n_updates | 153800 | +| policy_gradient_loss | -0.0734 | +| value_loss | 0.000467 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.185 | +| time/ | | +| fps | 309 | +| iterations | 9329 | +| time_elapsed | 30868 | +| total_timesteps | 9552896 | +| train/ | | +| approx_kl | 2.233529 | +| clip_fraction | 0.473 | +| clip_range | 0.2 | +| entropy_loss | -0.366 | +| explained_variance | -2.99 | +| learning_rate | 0.0001 | +| loss | -0.0555 | +| n_updates | 153810 | +| policy_gradient_loss | -0.0574 | +| value_loss | 0.000497 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.189 | +| time/ | | +| fps | 309 | +| iterations | 9330 | +| time_elapsed | 30872 | +| total_timesteps | 9553920 | +| train/ | | +| approx_kl | 2.2440195 | +| clip_fraction | 0.467 | +| clip_range | 0.2 | +| entropy_loss | -0.34 | +| explained_variance | -1.01 | +| learning_rate | 0.0001 | +| loss | -0.0942 | +| n_updates | 153820 | +| policy_gradient_loss | -0.0692 | +| value_loss | 0.000561 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.189 | +| time/ | | +| fps | 309 | +| iterations | 9331 | +| time_elapsed | 30875 | +| total_timesteps | 9554944 | +| train/ | | +| approx_kl | 2.3723392 | +| clip_fraction | 0.488 | +| clip_range | 0.2 | +| entropy_loss | -0.357 | +| explained_variance | -0.571 | +| learning_rate | 0.0001 | +| loss | -0.105 | +| n_updates | 153830 | +| policy_gradient_loss | -0.0719 | +| value_loss | 0.000609 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.193 | +| time/ | | +| fps | 309 | +| iterations | 9332 | +| time_elapsed | 30878 | +| total_timesteps | 9555968 | +| train/ | | +| approx_kl | 2.2442172 | +| clip_fraction | 0.526 | +| clip_range | 0.2 | +| entropy_loss | -0.409 | +| explained_variance | -2.29 | +| learning_rate | 0.0001 | +| loss | -0.121 | +| n_updates | 153840 | +| policy_gradient_loss | -0.0712 | +| value_loss | 0.000685 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.187 | +| time/ | | +| fps | 309 | +| iterations | 9333 | +| time_elapsed | 30882 | +| total_timesteps | 9556992 | +| train/ | | +| approx_kl | 1.8629603 | +| clip_fraction | 0.431 | +| clip_range | 0.2 | +| entropy_loss | -0.321 | +| explained_variance | -0.834 | +| learning_rate | 0.0001 | +| loss | -0.0754 | +| n_updates | 153850 | +| policy_gradient_loss | -0.0602 | +| value_loss | 0.00046 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.184 | +| time/ | | +| fps | 309 | +| iterations | 9334 | +| time_elapsed | 30885 | +| total_timesteps | 9558016 | +| train/ | | +| approx_kl | 1.8888166 | +| clip_fraction | 0.456 | +| clip_range | 0.2 | +| entropy_loss | -0.386 | +| explained_variance | -1.14 | +| learning_rate | 0.0001 | +| loss | -0.0917 | +| n_updates | 153860 | +| policy_gradient_loss | -0.0641 | +| value_loss | 0.000427 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.184 | +| time/ | | +| fps | 309 | +| iterations | 9335 | +| time_elapsed | 30889 | +| total_timesteps | 9559040 | +| train/ | | +| approx_kl | 28.4801 | +| clip_fraction | 0.405 | +| clip_range | 0.2 | +| entropy_loss | -0.287 | +| explained_variance | -1.55 | +| learning_rate | 0.0001 | +| loss | -0.094 | +| n_updates | 153870 | +| policy_gradient_loss | -0.0612 | +| value_loss | 0.000382 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.187 | +| time/ | | +| fps | 309 | +| iterations | 9336 | +| time_elapsed | 30892 | +| total_timesteps | 9560064 | +| train/ | | +| approx_kl | 2.150421 | +| clip_fraction | 0.486 | +| clip_range | 0.2 | +| entropy_loss | -0.381 | +| explained_variance | -3.57 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 153880 | +| policy_gradient_loss | -0.0731 | +| value_loss | 0.000342 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.187 | +| time/ | | +| fps | 309 | +| iterations | 9337 | +| time_elapsed | 30896 | +| total_timesteps | 9561088 | +| train/ | | +| approx_kl | 1.9483951 | +| clip_fraction | 0.417 | +| clip_range | 0.2 | +| entropy_loss | -0.314 | +| explained_variance | -0.544 | +| learning_rate | 0.0001 | +| loss | -0.0348 | +| n_updates | 153890 | +| policy_gradient_loss | -0.0559 | +| value_loss | 0.000574 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.188 | +| time/ | | +| fps | 309 | +| iterations | 9338 | +| time_elapsed | 30899 | +| total_timesteps | 9562112 | +| train/ | | +| approx_kl | 2.5492504 | +| clip_fraction | 0.502 | +| clip_range | 0.2 | +| entropy_loss | -0.354 | +| explained_variance | -1.63 | +| learning_rate | 0.0001 | +| loss | -0.0701 | +| n_updates | 153900 | +| policy_gradient_loss | -0.0724 | +| value_loss | 0.000595 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.192 | +| time/ | | +| fps | 309 | +| iterations | 9339 | +| time_elapsed | 30903 | +| total_timesteps | 9563136 | +| train/ | | +| approx_kl | 2.829914 | +| clip_fraction | 0.485 | +| clip_range | 0.2 | +| entropy_loss | -0.341 | +| explained_variance | -0.837 | +| learning_rate | 0.0001 | +| loss | -0.105 | +| n_updates | 153910 | +| policy_gradient_loss | -0.0718 | +| value_loss | 0.00071 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.192 | +| time/ | | +| fps | 309 | +| iterations | 9340 | +| time_elapsed | 30906 | +| total_timesteps | 9564160 | +| train/ | | +| approx_kl | 2.215889 | +| clip_fraction | 0.486 | +| clip_range | 0.2 | +| entropy_loss | -0.36 | +| explained_variance | -2.7 | +| learning_rate | 0.0001 | +| loss | -0.114 | +| n_updates | 153920 | +| policy_gradient_loss | -0.0756 | +| value_loss | 0.000471 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.186 | +| time/ | | +| fps | 309 | +| iterations | 9341 | +| time_elapsed | 30910 | +| total_timesteps | 9565184 | +| train/ | | +| approx_kl | 2.7526522 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.383 | +| explained_variance | -1.27 | +| learning_rate | 0.0001 | +| loss | -0.0934 | +| n_updates | 153930 | +| policy_gradient_loss | -0.0656 | +| value_loss | 0.000509 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.179 | +| time/ | | +| fps | 309 | +| iterations | 9342 | +| time_elapsed | 30913 | +| total_timesteps | 9566208 | +| train/ | | +| approx_kl | 2.047751 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.353 | +| explained_variance | -3.07 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 153940 | +| policy_gradient_loss | -0.0729 | +| value_loss | 0.000339 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.179 | +| time/ | | +| fps | 309 | +| iterations | 9343 | +| time_elapsed | 30916 | +| total_timesteps | 9567232 | +| train/ | | +| approx_kl | 3.771766 | +| clip_fraction | 0.474 | +| clip_range | 0.2 | +| entropy_loss | -0.34 | +| explained_variance | -0.774 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 153950 | +| policy_gradient_loss | -0.0744 | +| value_loss | 0.000542 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.179 | +| time/ | | +| fps | 309 | +| iterations | 9344 | +| time_elapsed | 30919 | +| total_timesteps | 9568256 | +| train/ | | +| approx_kl | 2.5700603 | +| clip_fraction | 0.469 | +| clip_range | 0.2 | +| entropy_loss | -0.334 | +| explained_variance | -1.65 | +| learning_rate | 0.0001 | +| loss | -0.0762 | +| n_updates | 153960 | +| policy_gradient_loss | -0.064 | +| value_loss | 0.000462 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.179 | +| time/ | | +| fps | 309 | +| iterations | 9345 | +| time_elapsed | 30923 | +| total_timesteps | 9569280 | +| train/ | | +| approx_kl | 2.3852887 | +| clip_fraction | 0.513 | +| clip_range | 0.2 | +| entropy_loss | -0.372 | +| explained_variance | -1.16 | +| learning_rate | 0.0001 | +| loss | -0.109 | +| n_updates | 153970 | +| policy_gradient_loss | -0.0767 | +| value_loss | 0.000415 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.179 | +| time/ | | +| fps | 309 | +| iterations | 9346 | +| time_elapsed | 30926 | +| total_timesteps | 9570304 | +| train/ | | +| approx_kl | 2.053953 | +| clip_fraction | 0.46 | +| clip_range | 0.2 | +| entropy_loss | -0.337 | +| explained_variance | -1.73 | +| learning_rate | 0.0001 | +| loss | -0.0793 | +| n_updates | 153980 | +| policy_gradient_loss | -0.0674 | +| value_loss | 0.00038 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.181 | +| time/ | | +| fps | 309 | +| iterations | 9347 | +| time_elapsed | 30929 | +| total_timesteps | 9571328 | +| train/ | | +| approx_kl | 1.995257 | +| clip_fraction | 0.488 | +| clip_range | 0.2 | +| entropy_loss | -0.361 | +| explained_variance | -1.63 | +| learning_rate | 0.0001 | +| loss | -0.0802 | +| n_updates | 153990 | +| policy_gradient_loss | -0.0713 | +| value_loss | 0.000541 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.181 | +| time/ | | +| fps | 309 | +| iterations | 9348 | +| time_elapsed | 30932 | +| total_timesteps | 9572352 | +| train/ | | +| approx_kl | 2.1571684 | +| clip_fraction | 0.459 | +| clip_range | 0.2 | +| entropy_loss | -0.34 | +| explained_variance | -4.28 | +| learning_rate | 0.0001 | +| loss | -0.0672 | +| n_updates | 154000 | +| policy_gradient_loss | -0.0676 | +| value_loss | 0.000557 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.177 | +| time/ | | +| fps | 309 | +| iterations | 9349 | +| time_elapsed | 30935 | +| total_timesteps | 9573376 | +| train/ | | +| approx_kl | 1.4839232 | +| clip_fraction | 0.466 | +| clip_range | 0.2 | +| entropy_loss | -0.355 | +| explained_variance | -0.999 | +| learning_rate | 0.0001 | +| loss | -0.108 | +| n_updates | 154010 | +| policy_gradient_loss | -0.0621 | +| value_loss | 0.000655 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.177 | +| time/ | | +| fps | 309 | +| iterations | 9350 | +| time_elapsed | 30938 | +| total_timesteps | 9574400 | +| train/ | | +| approx_kl | 1.7791185 | +| clip_fraction | 0.451 | +| clip_range | 0.2 | +| entropy_loss | -0.362 | +| explained_variance | -1.99 | +| learning_rate | 0.0001 | +| loss | -0.1 | +| n_updates | 154020 | +| policy_gradient_loss | -0.0648 | +| value_loss | 0.000553 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.176 | +| time/ | | +| fps | 309 | +| iterations | 9351 | +| time_elapsed | 30942 | +| total_timesteps | 9575424 | +| train/ | | +| approx_kl | 2.8214755 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.325 | +| explained_variance | -1.65 | +| learning_rate | 0.0001 | +| loss | -0.0992 | +| n_updates | 154030 | +| policy_gradient_loss | -0.0674 | +| value_loss | 0.000354 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.176 | +| time/ | | +| fps | 309 | +| iterations | 9352 | +| time_elapsed | 30946 | +| total_timesteps | 9576448 | +| train/ | | +| approx_kl | 1.9861684 | +| clip_fraction | 0.499 | +| clip_range | 0.2 | +| entropy_loss | -0.375 | +| explained_variance | -1.68 | +| learning_rate | 0.0001 | +| loss | -0.0828 | +| n_updates | 154040 | +| policy_gradient_loss | -0.07 | +| value_loss | 0.000582 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.18 | +| time/ | | +| fps | 309 | +| iterations | 9353 | +| time_elapsed | 30949 | +| total_timesteps | 9577472 | +| train/ | | +| approx_kl | 2.2328053 | +| clip_fraction | 0.507 | +| clip_range | 0.2 | +| entropy_loss | -0.366 | +| explained_variance | -1.54 | +| learning_rate | 0.0001 | +| loss | -0.0547 | +| n_updates | 154050 | +| policy_gradient_loss | -0.0705 | +| value_loss | 0.000584 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.186 | +| time/ | | +| fps | 309 | +| iterations | 9354 | +| time_elapsed | 30952 | +| total_timesteps | 9578496 | +| train/ | | +| approx_kl | 2.3344364 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.361 | +| explained_variance | -0.519 | +| learning_rate | 0.0001 | +| loss | -0.0798 | +| n_updates | 154060 | +| policy_gradient_loss | -0.0665 | +| value_loss | 0.000677 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.185 | +| time/ | | +| fps | 309 | +| iterations | 9355 | +| time_elapsed | 30956 | +| total_timesteps | 9579520 | +| train/ | | +| approx_kl | 2.1636662 | +| clip_fraction | 0.468 | +| clip_range | 0.2 | +| entropy_loss | -0.341 | +| explained_variance | -0.361 | +| learning_rate | 0.0001 | +| loss | -0.109 | +| n_updates | 154070 | +| policy_gradient_loss | -0.0636 | +| value_loss | 0.000885 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.185 | +| time/ | | +| fps | 309 | +| iterations | 9356 | +| time_elapsed | 30959 | +| total_timesteps | 9580544 | +| train/ | | +| approx_kl | 2.12886 | +| clip_fraction | 0.473 | +| clip_range | 0.2 | +| entropy_loss | -0.332 | +| explained_variance | -1.83 | +| learning_rate | 0.0001 | +| loss | -0.119 | +| n_updates | 154080 | +| policy_gradient_loss | -0.0688 | +| value_loss | 0.000776 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.186 | +| time/ | | +| fps | 309 | +| iterations | 9357 | +| time_elapsed | 30963 | +| total_timesteps | 9581568 | +| train/ | | +| approx_kl | 2.3543677 | +| clip_fraction | 0.47 | +| clip_range | 0.2 | +| entropy_loss | -0.319 | +| explained_variance | -1.69 | +| learning_rate | 0.0001 | +| loss | -0.0966 | +| n_updates | 154090 | +| policy_gradient_loss | -0.0675 | +| value_loss | 0.000654 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.191 | +| time/ | | +| fps | 309 | +| iterations | 9358 | +| time_elapsed | 30967 | +| total_timesteps | 9582592 | +| train/ | | +| approx_kl | 2.9048634 | +| clip_fraction | 0.433 | +| clip_range | 0.2 | +| entropy_loss | -0.369 | +| explained_variance | -1.71 | +| learning_rate | 0.0001 | +| loss | -0.0607 | +| n_updates | 154100 | +| policy_gradient_loss | -0.0616 | +| value_loss | 0.000622 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.191 | +| time/ | | +| fps | 309 | +| iterations | 9359 | +| time_elapsed | 30970 | +| total_timesteps | 9583616 | +| train/ | | +| approx_kl | 3.1416843 | +| clip_fraction | 0.514 | +| clip_range | 0.2 | +| entropy_loss | -0.4 | +| explained_variance | -0.846 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 154110 | +| policy_gradient_loss | -0.0737 | +| value_loss | 0.000557 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.196 | +| time/ | | +| fps | 309 | +| iterations | 9360 | +| time_elapsed | 30973 | +| total_timesteps | 9584640 | +| train/ | | +| approx_kl | 2.5190768 | +| clip_fraction | 0.491 | +| clip_range | 0.2 | +| entropy_loss | -0.389 | +| explained_variance | -1.33 | +| learning_rate | 0.0001 | +| loss | -0.0983 | +| n_updates | 154120 | +| policy_gradient_loss | -0.0738 | +| value_loss | 0.000439 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.192 | +| time/ | | +| fps | 309 | +| iterations | 9361 | +| time_elapsed | 30977 | +| total_timesteps | 9585664 | +| train/ | | +| approx_kl | 3.3900025 | +| clip_fraction | 0.439 | +| clip_range | 0.2 | +| entropy_loss | -0.324 | +| explained_variance | -1.19 | +| learning_rate | 0.0001 | +| loss | -0.0729 | +| n_updates | 154130 | +| policy_gradient_loss | -0.0648 | +| value_loss | 0.000485 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.192 | +| time/ | | +| fps | 309 | +| iterations | 9362 | +| time_elapsed | 30980 | +| total_timesteps | 9586688 | +| train/ | | +| approx_kl | 2.2183166 | +| clip_fraction | 0.463 | +| clip_range | 0.2 | +| entropy_loss | -0.31 | +| explained_variance | -1.46 | +| learning_rate | 0.0001 | +| loss | -0.0854 | +| n_updates | 154140 | +| policy_gradient_loss | -0.0671 | +| value_loss | 0.000539 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.188 | +| time/ | | +| fps | 309 | +| iterations | 9363 | +| time_elapsed | 30983 | +| total_timesteps | 9587712 | +| train/ | | +| approx_kl | 3.9238048 | +| clip_fraction | 0.478 | +| clip_range | 0.2 | +| entropy_loss | -0.328 | +| explained_variance | -1.62 | +| learning_rate | 0.0001 | +| loss | -0.0708 | +| n_updates | 154150 | +| policy_gradient_loss | -0.0681 | +| value_loss | 0.000521 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.188 | +| time/ | | +| fps | 309 | +| iterations | 9364 | +| time_elapsed | 30986 | +| total_timesteps | 9588736 | +| train/ | | +| approx_kl | 2.2293444 | +| clip_fraction | 0.434 | +| clip_range | 0.2 | +| entropy_loss | -0.34 | +| explained_variance | -1.23 | +| learning_rate | 0.0001 | +| loss | -0.0931 | +| n_updates | 154160 | +| policy_gradient_loss | -0.0581 | +| value_loss | 0.000333 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.185 | +| time/ | | +| fps | 309 | +| iterations | 9365 | +| time_elapsed | 30989 | +| total_timesteps | 9589760 | +| train/ | | +| approx_kl | 2.2792814 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.344 | +| explained_variance | -1.02 | +| learning_rate | 0.0001 | +| loss | -0.0898 | +| n_updates | 154170 | +| policy_gradient_loss | -0.0701 | +| value_loss | 0.000459 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.185 | +| time/ | | +| fps | 309 | +| iterations | 9366 | +| time_elapsed | 30993 | +| total_timesteps | 9590784 | +| train/ | | +| approx_kl | 2.26964 | +| clip_fraction | 0.45 | +| clip_range | 0.2 | +| entropy_loss | -0.321 | +| explained_variance | -1.26 | +| learning_rate | 0.0001 | +| loss | -0.0636 | +| n_updates | 154180 | +| policy_gradient_loss | -0.0586 | +| value_loss | 0.000584 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.185 | +| time/ | | +| fps | 309 | +| iterations | 9367 | +| time_elapsed | 30996 | +| total_timesteps | 9591808 | +| train/ | | +| approx_kl | 2.663126 | +| clip_fraction | 0.463 | +| clip_range | 0.2 | +| entropy_loss | -0.308 | +| explained_variance | -1.78 | +| learning_rate | 0.0001 | +| loss | -0.0999 | +| n_updates | 154190 | +| policy_gradient_loss | -0.0728 | +| value_loss | 0.000506 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.19 | +| time/ | | +| fps | 309 | +| iterations | 9368 | +| time_elapsed | 30999 | +| total_timesteps | 9592832 | +| train/ | | +| approx_kl | 3.098304 | +| clip_fraction | 0.489 | +| clip_range | 0.2 | +| entropy_loss | -0.351 | +| explained_variance | -1.58 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 154200 | +| policy_gradient_loss | -0.0671 | +| value_loss | 0.000588 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.195 | +| time/ | | +| fps | 309 | +| iterations | 9369 | +| time_elapsed | 31003 | +| total_timesteps | 9593856 | +| train/ | | +| approx_kl | 2.328383 | +| clip_fraction | 0.426 | +| clip_range | 0.2 | +| entropy_loss | -0.27 | +| explained_variance | -1.97 | +| learning_rate | 0.0001 | +| loss | -0.0658 | +| n_updates | 154210 | +| policy_gradient_loss | -0.062 | +| value_loss | 0.000479 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.195 | +| time/ | | +| fps | 309 | +| iterations | 9370 | +| time_elapsed | 31006 | +| total_timesteps | 9594880 | +| train/ | | +| approx_kl | 3.0814247 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.334 | +| explained_variance | -1.15 | +| learning_rate | 0.0001 | +| loss | -0.0766 | +| n_updates | 154220 | +| policy_gradient_loss | -0.0723 | +| value_loss | 0.000552 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.191 | +| time/ | | +| fps | 309 | +| iterations | 9371 | +| time_elapsed | 31009 | +| total_timesteps | 9595904 | +| train/ | | +| approx_kl | 2.0058703 | +| clip_fraction | 0.434 | +| clip_range | 0.2 | +| entropy_loss | -0.291 | +| explained_variance | -2.96 | +| learning_rate | 0.0001 | +| loss | -0.0957 | +| n_updates | 154230 | +| policy_gradient_loss | -0.0625 | +| value_loss | 0.000306 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.189 | +| time/ | | +| fps | 309 | +| iterations | 9372 | +| time_elapsed | 31013 | +| total_timesteps | 9596928 | +| train/ | | +| approx_kl | 3.1438956 | +| clip_fraction | 0.504 | +| clip_range | 0.2 | +| entropy_loss | -0.396 | +| explained_variance | -1.98 | +| learning_rate | 0.0001 | +| loss | -0.0956 | +| n_updates | 154240 | +| policy_gradient_loss | -0.0678 | +| value_loss | 0.000303 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.19 | +| time/ | | +| fps | 309 | +| iterations | 9373 | +| time_elapsed | 31016 | +| total_timesteps | 9597952 | +| train/ | | +| approx_kl | 2.0982194 | +| clip_fraction | 0.491 | +| clip_range | 0.2 | +| entropy_loss | -0.379 | +| explained_variance | -0.92 | +| learning_rate | 0.0001 | +| loss | -0.097 | +| n_updates | 154250 | +| policy_gradient_loss | -0.0689 | +| value_loss | 0.000539 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.19 | +| time/ | | +| fps | 309 | +| iterations | 9374 | +| time_elapsed | 31020 | +| total_timesteps | 9598976 | +| train/ | | +| approx_kl | 2.486475 | +| clip_fraction | 0.503 | +| clip_range | 0.2 | +| entropy_loss | -0.391 | +| explained_variance | -2.4 | +| learning_rate | 0.0001 | +| loss | -0.108 | +| n_updates | 154260 | +| policy_gradient_loss | -0.0783 | +| value_loss | 0.000418 | +-------------------------------------- + +Current state: Champion.Level1.RyuVsGuile +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.189 | +| time/ | | +| fps | 309 | +| iterations | 9375 | +| time_elapsed | 31023 | +| total_timesteps | 9600000 | +| train/ | | +| approx_kl | 2.2149553 | +| clip_fraction | 0.494 | +| clip_range | 0.2 | +| entropy_loss | -0.365 | +| explained_variance | -1.1 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 154270 | +| policy_gradient_loss | -0.0682 | +| value_loss | 0.000515 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.187 | +| time/ | | +| fps | 309 | +| iterations | 9376 | +| time_elapsed | 31026 | +| total_timesteps | 9601024 | +| train/ | | +| approx_kl | 2.0402179 | +| clip_fraction | 0.453 | +| clip_range | 0.2 | +| entropy_loss | -0.348 | +| explained_variance | -2.51 | +| learning_rate | 0.0001 | +| loss | -0.0971 | +| n_updates | 154280 | +| policy_gradient_loss | -0.0688 | +| value_loss | 0.00058 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.187 | +| time/ | | +| fps | 309 | +| iterations | 9377 | +| time_elapsed | 31030 | +| total_timesteps | 9602048 | +| train/ | | +| approx_kl | 1.5421753 | +| clip_fraction | 0.436 | +| clip_range | 0.2 | +| entropy_loss | -0.38 | +| explained_variance | -3.54 | +| learning_rate | 0.0001 | +| loss | -0.0522 | +| n_updates | 154290 | +| policy_gradient_loss | -0.0536 | +| value_loss | 0.000222 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.187 | +| time/ | | +| fps | 309 | +| iterations | 9378 | +| time_elapsed | 31033 | +| total_timesteps | 9603072 | +| train/ | | +| approx_kl | 2.1118057 | +| clip_fraction | 0.53 | +| clip_range | 0.2 | +| entropy_loss | -0.443 | +| explained_variance | -3.29 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 154300 | +| policy_gradient_loss | -0.071 | +| value_loss | 0.000269 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.189 | +| time/ | | +| fps | 309 | +| iterations | 9379 | +| time_elapsed | 31036 | +| total_timesteps | 9604096 | +| train/ | | +| approx_kl | 1.4019897 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.481 | +| explained_variance | -2.39 | +| learning_rate | 0.0001 | +| loss | -0.0763 | +| n_updates | 154310 | +| policy_gradient_loss | -0.0694 | +| value_loss | 7.42e-05 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.193 | +| time/ | | +| fps | 309 | +| iterations | 9380 | +| time_elapsed | 31039 | +| total_timesteps | 9605120 | +| train/ | | +| approx_kl | 4.4183455 | +| clip_fraction | 0.454 | +| clip_range | 0.2 | +| entropy_loss | -0.37 | +| explained_variance | -0.122 | +| learning_rate | 0.0001 | +| loss | -0.0933 | +| n_updates | 154320 | +| policy_gradient_loss | -0.0606 | +| value_loss | 0.000139 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.193 | +| time/ | | +| fps | 309 | +| iterations | 9381 | +| time_elapsed | 31042 | +| total_timesteps | 9606144 | +| train/ | | +| approx_kl | 1.6616261 | +| clip_fraction | 0.54 | +| clip_range | 0.2 | +| entropy_loss | -0.497 | +| explained_variance | -0.202 | +| learning_rate | 0.0001 | +| loss | -0.0777 | +| n_updates | 154330 | +| policy_gradient_loss | -0.0719 | +| value_loss | 0.000587 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.193 | +| time/ | | +| fps | 309 | +| iterations | 9382 | +| time_elapsed | 31046 | +| total_timesteps | 9607168 | +| train/ | | +| approx_kl | 3.3312454 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.381 | +| explained_variance | -2.02 | +| learning_rate | 0.0001 | +| loss | -0.11 | +| n_updates | 154340 | +| policy_gradient_loss | -0.0676 | +| value_loss | 0.000348 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.192 | +| time/ | | +| fps | 309 | +| iterations | 9383 | +| time_elapsed | 31049 | +| total_timesteps | 9608192 | +| train/ | | +| approx_kl | 2.3104146 | +| clip_fraction | 0.494 | +| clip_range | 0.2 | +| entropy_loss | -0.417 | +| explained_variance | -2.72 | +| learning_rate | 0.0001 | +| loss | -0.0913 | +| n_updates | 154350 | +| policy_gradient_loss | -0.0763 | +| value_loss | 0.000442 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.192 | +| time/ | | +| fps | 309 | +| iterations | 9384 | +| time_elapsed | 31052 | +| total_timesteps | 9609216 | +| train/ | | +| approx_kl | 2.1804006 | +| clip_fraction | 0.469 | +| clip_range | 0.2 | +| entropy_loss | -0.379 | +| explained_variance | -4 | +| learning_rate | 0.0001 | +| loss | -0.0844 | +| n_updates | 154360 | +| policy_gradient_loss | -0.074 | +| value_loss | 0.000618 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.192 | +| time/ | | +| fps | 309 | +| iterations | 9385 | +| time_elapsed | 31055 | +| total_timesteps | 9610240 | +| train/ | | +| approx_kl | 2.1534467 | +| clip_fraction | 0.493 | +| clip_range | 0.2 | +| entropy_loss | -0.391 | +| explained_variance | -1.97 | +| learning_rate | 0.0001 | +| loss | -0.084 | +| n_updates | 154370 | +| policy_gradient_loss | -0.0685 | +| value_loss | 0.000664 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.192 | +| time/ | | +| fps | 309 | +| iterations | 9386 | +| time_elapsed | 31058 | +| total_timesteps | 9611264 | +| train/ | | +| approx_kl | 2.0256886 | +| clip_fraction | 0.477 | +| clip_range | 0.2 | +| entropy_loss | -0.367 | +| explained_variance | -10.7 | +| learning_rate | 0.0001 | +| loss | -0.0992 | +| n_updates | 154380 | +| policy_gradient_loss | -0.0768 | +| value_loss | 0.000258 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.192 | +| time/ | | +| fps | 309 | +| iterations | 9387 | +| time_elapsed | 31062 | +| total_timesteps | 9612288 | +| train/ | | +| approx_kl | 1.5157566 | +| clip_fraction | 0.46 | +| clip_range | 0.2 | +| entropy_loss | -0.381 | +| explained_variance | -3.61 | +| learning_rate | 0.0001 | +| loss | -0.0881 | +| n_updates | 154390 | +| policy_gradient_loss | -0.0752 | +| value_loss | 0.000143 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.43e+03 | +| ep_rew_mean | 0.197 | +| time/ | | +| fps | 309 | +| iterations | 9388 | +| time_elapsed | 31065 | +| total_timesteps | 9613312 | +| train/ | | +| approx_kl | 1.8917142 | +| clip_fraction | 0.512 | +| clip_range | 0.2 | +| entropy_loss | -0.427 | +| explained_variance | -0.244 | +| learning_rate | 0.0001 | +| loss | -0.0948 | +| n_updates | 154400 | +| policy_gradient_loss | -0.0665 | +| value_loss | 0.000454 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.43e+03 | +| ep_rew_mean | 0.197 | +| time/ | | +| fps | 309 | +| iterations | 9389 | +| time_elapsed | 31069 | +| total_timesteps | 9614336 | +| train/ | | +| approx_kl | 2.5912766 | +| clip_fraction | 0.473 | +| clip_range | 0.2 | +| entropy_loss | -0.391 | +| explained_variance | -3.17 | +| learning_rate | 0.0001 | +| loss | -0.091 | +| n_updates | 154410 | +| policy_gradient_loss | -0.0714 | +| value_loss | 0.000252 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.44e+03 | +| ep_rew_mean | 0.202 | +| time/ | | +| fps | 309 | +| iterations | 9390 | +| time_elapsed | 31072 | +| total_timesteps | 9615360 | +| train/ | | +| approx_kl | 1.8550038 | +| clip_fraction | 0.523 | +| clip_range | 0.2 | +| entropy_loss | -0.469 | +| explained_variance | -0.992 | +| learning_rate | 0.0001 | +| loss | -0.0876 | +| n_updates | 154420 | +| policy_gradient_loss | -0.0755 | +| value_loss | 0.000304 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.44e+03 | +| ep_rew_mean | 0.202 | +| time/ | | +| fps | 309 | +| iterations | 9391 | +| time_elapsed | 31076 | +| total_timesteps | 9616384 | +| train/ | | +| approx_kl | 1.711945 | +| clip_fraction | 0.499 | +| clip_range | 0.2 | +| entropy_loss | -0.435 | +| explained_variance | -0.907 | +| learning_rate | 0.0001 | +| loss | -0.0975 | +| n_updates | 154430 | +| policy_gradient_loss | -0.0788 | +| value_loss | 0.000249 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.45e+03 | +| ep_rew_mean | 0.204 | +| time/ | | +| fps | 309 | +| iterations | 9392 | +| time_elapsed | 31079 | +| total_timesteps | 9617408 | +| train/ | | +| approx_kl | 2.0927286 | +| clip_fraction | 0.503 | +| clip_range | 0.2 | +| entropy_loss | -0.421 | +| explained_variance | -1 | +| learning_rate | 0.0001 | +| loss | -0.0914 | +| n_updates | 154440 | +| policy_gradient_loss | -0.0707 | +| value_loss | 0.000656 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.45e+03 | +| ep_rew_mean | 0.204 | +| time/ | | +| fps | 309 | +| iterations | 9393 | +| time_elapsed | 31082 | +| total_timesteps | 9618432 | +| train/ | | +| approx_kl | 2.2342541 | +| clip_fraction | 0.472 | +| clip_range | 0.2 | +| entropy_loss | -0.376 | +| explained_variance | -6.03 | +| learning_rate | 0.0001 | +| loss | -0.095 | +| n_updates | 154450 | +| policy_gradient_loss | -0.07 | +| value_loss | 0.000277 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.45e+03 | +| ep_rew_mean | 0.204 | +| time/ | | +| fps | 309 | +| iterations | 9394 | +| time_elapsed | 31086 | +| total_timesteps | 9619456 | +| train/ | | +| approx_kl | 2.0573692 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.373 | +| explained_variance | -1.21 | +| learning_rate | 0.0001 | +| loss | -0.0912 | +| n_updates | 154460 | +| policy_gradient_loss | -0.0681 | +| value_loss | 0.000225 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.46e+03 | +| ep_rew_mean | 0.205 | +| time/ | | +| fps | 309 | +| iterations | 9395 | +| time_elapsed | 31089 | +| total_timesteps | 9620480 | +| train/ | | +| approx_kl | 2.5408802 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.378 | +| explained_variance | -1.92 | +| learning_rate | 0.0001 | +| loss | -0.11 | +| n_updates | 154470 | +| policy_gradient_loss | -0.0677 | +| value_loss | 0.000404 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.46e+03 | +| ep_rew_mean | 0.205 | +| time/ | | +| fps | 309 | +| iterations | 9396 | +| time_elapsed | 31093 | +| total_timesteps | 9621504 | +| train/ | | +| approx_kl | 1.808768 | +| clip_fraction | 0.537 | +| clip_range | 0.2 | +| entropy_loss | -0.455 | +| explained_variance | -2 | +| learning_rate | 0.0001 | +| loss | -0.0216 | +| n_updates | 154480 | +| policy_gradient_loss | -0.0811 | +| value_loss | 0.00073 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.46e+03 | +| ep_rew_mean | 0.205 | +| time/ | | +| fps | 309 | +| iterations | 9397 | +| time_elapsed | 31096 | +| total_timesteps | 9622528 | +| train/ | | +| approx_kl | 1.7887646 | +| clip_fraction | 0.515 | +| clip_range | 0.2 | +| entropy_loss | -0.447 | +| explained_variance | -2.16 | +| learning_rate | 0.0001 | +| loss | -0.0825 | +| n_updates | 154490 | +| policy_gradient_loss | -0.0692 | +| value_loss | 0.00026 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.46e+03 | +| ep_rew_mean | 0.205 | +| time/ | | +| fps | 309 | +| iterations | 9398 | +| time_elapsed | 31099 | +| total_timesteps | 9623552 | +| train/ | | +| approx_kl | 1.7683854 | +| clip_fraction | 0.533 | +| clip_range | 0.2 | +| entropy_loss | -0.481 | +| explained_variance | -1.36 | +| learning_rate | 0.0001 | +| loss | -0.0746 | +| n_updates | 154500 | +| policy_gradient_loss | -0.0685 | +| value_loss | 0.00017 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.48e+03 | +| ep_rew_mean | 0.207 | +| time/ | | +| fps | 309 | +| iterations | 9399 | +| time_elapsed | 31102 | +| total_timesteps | 9624576 | +| train/ | | +| approx_kl | 1.8755634 | +| clip_fraction | 0.477 | +| clip_range | 0.2 | +| entropy_loss | -0.435 | +| explained_variance | -2.44 | +| learning_rate | 0.0001 | +| loss | -0.0854 | +| n_updates | 154510 | +| policy_gradient_loss | -0.066 | +| value_loss | 0.000251 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.48e+03 | +| ep_rew_mean | 0.207 | +| time/ | | +| fps | 309 | +| iterations | 9400 | +| time_elapsed | 31105 | +| total_timesteps | 9625600 | +| train/ | | +| approx_kl | 1.2765589 | +| clip_fraction | 0.47 | +| clip_range | 0.2 | +| entropy_loss | -0.418 | +| explained_variance | -0.834 | +| learning_rate | 0.0001 | +| loss | -0.0826 | +| n_updates | 154520 | +| policy_gradient_loss | -0.0657 | +| value_loss | 0.000118 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.49e+03 | +| ep_rew_mean | 0.207 | +| time/ | | +| fps | 309 | +| iterations | 9401 | +| time_elapsed | 31109 | +| total_timesteps | 9626624 | +| train/ | | +| approx_kl | 2.9446292 | +| clip_fraction | 0.529 | +| clip_range | 0.2 | +| entropy_loss | -0.437 | +| explained_variance | -0.756 | +| learning_rate | 0.0001 | +| loss | -0.0909 | +| n_updates | 154530 | +| policy_gradient_loss | -0.0707 | +| value_loss | 0.000384 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.49e+03 | +| ep_rew_mean | 0.207 | +| time/ | | +| fps | 309 | +| iterations | 9402 | +| time_elapsed | 31112 | +| total_timesteps | 9627648 | +| train/ | | +| approx_kl | 1.7347728 | +| clip_fraction | 0.466 | +| clip_range | 0.2 | +| entropy_loss | -0.393 | +| explained_variance | -1.1 | +| learning_rate | 0.0001 | +| loss | -0.0927 | +| n_updates | 154540 | +| policy_gradient_loss | -0.0651 | +| value_loss | 0.000668 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.49e+03 | +| ep_rew_mean | 0.209 | +| time/ | | +| fps | 309 | +| iterations | 9403 | +| time_elapsed | 31115 | +| total_timesteps | 9628672 | +| train/ | | +| approx_kl | 2.0897288 | +| clip_fraction | 0.496 | +| clip_range | 0.2 | +| entropy_loss | -0.388 | +| explained_variance | -3.32 | +| learning_rate | 0.0001 | +| loss | -0.0813 | +| n_updates | 154550 | +| policy_gradient_loss | -0.0731 | +| value_loss | 0.000752 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.49e+03 | +| ep_rew_mean | 0.209 | +| time/ | | +| fps | 309 | +| iterations | 9404 | +| time_elapsed | 31118 | +| total_timesteps | 9629696 | +| train/ | | +| approx_kl | 2.0415368 | +| clip_fraction | 0.484 | +| clip_range | 0.2 | +| entropy_loss | -0.419 | +| explained_variance | -1.33 | +| learning_rate | 0.0001 | +| loss | -0.0808 | +| n_updates | 154560 | +| policy_gradient_loss | -0.0675 | +| value_loss | 0.000542 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.49e+03 | +| ep_rew_mean | 0.206 | +| time/ | | +| fps | 309 | +| iterations | 9405 | +| time_elapsed | 31122 | +| total_timesteps | 9630720 | +| train/ | | +| approx_kl | 1.8688178 | +| clip_fraction | 0.513 | +| clip_range | 0.2 | +| entropy_loss | -0.441 | +| explained_variance | -4.22 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 154570 | +| policy_gradient_loss | -0.0785 | +| value_loss | 0.000283 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.49e+03 | +| ep_rew_mean | 0.206 | +| time/ | | +| fps | 309 | +| iterations | 9406 | +| time_elapsed | 31125 | +| total_timesteps | 9631744 | +| train/ | | +| approx_kl | 1.6978722 | +| clip_fraction | 0.468 | +| clip_range | 0.2 | +| entropy_loss | -0.389 | +| explained_variance | -1.39 | +| learning_rate | 0.0001 | +| loss | -0.0763 | +| n_updates | 154580 | +| policy_gradient_loss | -0.0648 | +| value_loss | 0.000245 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.49e+03 | +| ep_rew_mean | 0.206 | +| time/ | | +| fps | 309 | +| iterations | 9407 | +| time_elapsed | 31128 | +| total_timesteps | 9632768 | +| train/ | | +| approx_kl | 1.827385 | +| clip_fraction | 0.503 | +| clip_range | 0.2 | +| entropy_loss | -0.422 | +| explained_variance | -0.712 | +| learning_rate | 0.0001 | +| loss | -0.0677 | +| n_updates | 154590 | +| policy_gradient_loss | -0.0708 | +| value_loss | 0.000559 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.52e+03 | +| ep_rew_mean | 0.211 | +| time/ | | +| fps | 309 | +| iterations | 9408 | +| time_elapsed | 31132 | +| total_timesteps | 9633792 | +| train/ | | +| approx_kl | 1.904836 | +| clip_fraction | 0.478 | +| clip_range | 0.2 | +| entropy_loss | -0.416 | +| explained_variance | -2.82 | +| learning_rate | 0.0001 | +| loss | -0.0886 | +| n_updates | 154600 | +| policy_gradient_loss | -0.0721 | +| value_loss | 0.000239 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.52e+03 | +| ep_rew_mean | 0.211 | +| time/ | | +| fps | 309 | +| iterations | 9409 | +| time_elapsed | 31135 | +| total_timesteps | 9634816 | +| train/ | | +| approx_kl | 1.7184327 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.398 | +| explained_variance | -1.11 | +| learning_rate | 0.0001 | +| loss | -0.0764 | +| n_updates | 154610 | +| policy_gradient_loss | -0.0665 | +| value_loss | 0.000168 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.52e+03 | +| ep_rew_mean | 0.213 | +| time/ | | +| fps | 309 | +| iterations | 9410 | +| time_elapsed | 31138 | +| total_timesteps | 9635840 | +| train/ | | +| approx_kl | 2.5210576 | +| clip_fraction | 0.528 | +| clip_range | 0.2 | +| entropy_loss | -0.45 | +| explained_variance | -0.558 | +| learning_rate | 0.0001 | +| loss | -0.0637 | +| n_updates | 154620 | +| policy_gradient_loss | -0.0715 | +| value_loss | 0.00047 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.52e+03 | +| ep_rew_mean | 0.213 | +| time/ | | +| fps | 309 | +| iterations | 9411 | +| time_elapsed | 31141 | +| total_timesteps | 9636864 | +| train/ | | +| approx_kl | 15.763993 | +| clip_fraction | 0.458 | +| clip_range | 0.2 | +| entropy_loss | -0.375 | +| explained_variance | -1.27 | +| learning_rate | 0.0001 | +| loss | -0.0821 | +| n_updates | 154630 | +| policy_gradient_loss | -0.0642 | +| value_loss | 0.000462 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.53e+03 | +| ep_rew_mean | 0.214 | +| time/ | | +| fps | 309 | +| iterations | 9412 | +| time_elapsed | 31145 | +| total_timesteps | 9637888 | +| train/ | | +| approx_kl | 1.9888034 | +| clip_fraction | 0.499 | +| clip_range | 0.2 | +| entropy_loss | -0.432 | +| explained_variance | -2.35 | +| learning_rate | 0.0001 | +| loss | -0.0797 | +| n_updates | 154640 | +| policy_gradient_loss | -0.0777 | +| value_loss | 0.00034 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.53e+03 | +| ep_rew_mean | 0.214 | +| time/ | | +| fps | 309 | +| iterations | 9413 | +| time_elapsed | 31148 | +| total_timesteps | 9638912 | +| train/ | | +| approx_kl | 1.5545176 | +| clip_fraction | 0.493 | +| clip_range | 0.2 | +| entropy_loss | -0.472 | +| explained_variance | -1.23 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 154650 | +| policy_gradient_loss | -0.0684 | +| value_loss | 0.000672 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.53e+03 | +| ep_rew_mean | 0.214 | +| time/ | | +| fps | 309 | +| iterations | 9414 | +| time_elapsed | 31151 | +| total_timesteps | 9639936 | +| train/ | | +| approx_kl | 2.0902896 | +| clip_fraction | 0.51 | +| clip_range | 0.2 | +| entropy_loss | -0.412 | +| explained_variance | -2.02 | +| learning_rate | 0.0001 | +| loss | -0.0669 | +| n_updates | 154660 | +| policy_gradient_loss | -0.0782 | +| value_loss | 0.000341 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.54e+03 | +| ep_rew_mean | 0.21 | +| time/ | | +| fps | 309 | +| iterations | 9415 | +| time_elapsed | 31154 | +| total_timesteps | 9640960 | +| train/ | | +| approx_kl | 1.9126718 | +| clip_fraction | 0.51 | +| clip_range | 0.2 | +| entropy_loss | -0.423 | +| explained_variance | -1.36 | +| learning_rate | 0.0001 | +| loss | -0.0984 | +| n_updates | 154670 | +| policy_gradient_loss | -0.074 | +| value_loss | 0.000305 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.54e+03 | +| ep_rew_mean | 0.21 | +| time/ | | +| fps | 309 | +| iterations | 9416 | +| time_elapsed | 31157 | +| total_timesteps | 9641984 | +| train/ | | +| approx_kl | 1.9070175 | +| clip_fraction | 0.5 | +| clip_range | 0.2 | +| entropy_loss | -0.435 | +| explained_variance | -0.69 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 154680 | +| policy_gradient_loss | -0.0693 | +| value_loss | 0.000559 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.55e+03 | +| ep_rew_mean | 0.213 | +| time/ | | +| fps | 309 | +| iterations | 9417 | +| time_elapsed | 31161 | +| total_timesteps | 9643008 | +| train/ | | +| approx_kl | 2.1859255 | +| clip_fraction | 0.474 | +| clip_range | 0.2 | +| entropy_loss | -0.34 | +| explained_variance | -2.31 | +| learning_rate | 0.0001 | +| loss | -0.0672 | +| n_updates | 154690 | +| policy_gradient_loss | -0.0683 | +| value_loss | 0.000393 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.55e+03 | +| ep_rew_mean | 0.213 | +| time/ | | +| fps | 309 | +| iterations | 9418 | +| time_elapsed | 31164 | +| total_timesteps | 9644032 | +| train/ | | +| approx_kl | 2.113618 | +| clip_fraction | 0.479 | +| clip_range | 0.2 | +| entropy_loss | -0.413 | +| explained_variance | -0.401 | +| learning_rate | 0.0001 | +| loss | -0.0915 | +| n_updates | 154700 | +| policy_gradient_loss | -0.0674 | +| value_loss | 0.000487 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.56e+03 | +| ep_rew_mean | 0.217 | +| time/ | | +| fps | 309 | +| iterations | 9419 | +| time_elapsed | 31167 | +| total_timesteps | 9645056 | +| train/ | | +| approx_kl | 1.6187716 | +| clip_fraction | 0.515 | +| clip_range | 0.2 | +| entropy_loss | -0.484 | +| explained_variance | -1.07 | +| learning_rate | 0.0001 | +| loss | -0.0879 | +| n_updates | 154710 | +| policy_gradient_loss | -0.073 | +| value_loss | 0.000534 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.56e+03 | +| ep_rew_mean | 0.217 | +| time/ | | +| fps | 309 | +| iterations | 9420 | +| time_elapsed | 31170 | +| total_timesteps | 9646080 | +| train/ | | +| approx_kl | 1.715449 | +| clip_fraction | 0.463 | +| clip_range | 0.2 | +| entropy_loss | -0.421 | +| explained_variance | -0.679 | +| learning_rate | 0.0001 | +| loss | -0.0909 | +| n_updates | 154720 | +| policy_gradient_loss | -0.0694 | +| value_loss | 0.00023 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.56e+03 | +| ep_rew_mean | 0.217 | +| time/ | | +| fps | 309 | +| iterations | 9421 | +| time_elapsed | 31173 | +| total_timesteps | 9647104 | +| train/ | | +| approx_kl | 3.154661 | +| clip_fraction | 0.508 | +| clip_range | 0.2 | +| entropy_loss | -0.468 | +| explained_variance | -0.316 | +| learning_rate | 0.0001 | +| loss | -0.0755 | +| n_updates | 154730 | +| policy_gradient_loss | -0.0575 | +| value_loss | 0.0005 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.57e+03 | +| ep_rew_mean | 0.222 | +| time/ | | +| fps | 309 | +| iterations | 9422 | +| time_elapsed | 31177 | +| total_timesteps | 9648128 | +| train/ | | +| approx_kl | 1.5343912 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.44 | +| explained_variance | -3.18 | +| learning_rate | 0.0001 | +| loss | -0.0753 | +| n_updates | 154740 | +| policy_gradient_loss | -0.0706 | +| value_loss | 0.00058 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.57e+03 | +| ep_rew_mean | 0.222 | +| time/ | | +| fps | 309 | +| iterations | 9423 | +| time_elapsed | 31180 | +| total_timesteps | 9649152 | +| train/ | | +| approx_kl | 1.7128537 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.47 | +| explained_variance | -0.332 | +| learning_rate | 0.0001 | +| loss | -0.0657 | +| n_updates | 154750 | +| policy_gradient_loss | -0.063 | +| value_loss | 0.000273 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.57e+03 | +| ep_rew_mean | 0.222 | +| time/ | | +| fps | 309 | +| iterations | 9424 | +| time_elapsed | 31183 | +| total_timesteps | 9650176 | +| train/ | | +| approx_kl | 1.6751604 | +| clip_fraction | 0.51 | +| clip_range | 0.2 | +| entropy_loss | -0.522 | +| explained_variance | -3.47 | +| learning_rate | 0.0001 | +| loss | -0.106 | +| n_updates | 154760 | +| policy_gradient_loss | -0.0781 | +| value_loss | 0.00017 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | 0.225 | +| time/ | | +| fps | 309 | +| iterations | 9425 | +| time_elapsed | 31187 | +| total_timesteps | 9651200 | +| train/ | | +| approx_kl | 2.0364218 | +| clip_fraction | 0.515 | +| clip_range | 0.2 | +| entropy_loss | -0.438 | +| explained_variance | -1.34 | +| learning_rate | 0.0001 | +| loss | -0.072 | +| n_updates | 154770 | +| policy_gradient_loss | -0.0719 | +| value_loss | 0.00032 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | 0.227 | +| time/ | | +| fps | 309 | +| iterations | 9426 | +| time_elapsed | 31190 | +| total_timesteps | 9652224 | +| train/ | | +| approx_kl | 1.7518883 | +| clip_fraction | 0.459 | +| clip_range | 0.2 | +| entropy_loss | -0.389 | +| explained_variance | -1.85 | +| learning_rate | 0.0001 | +| loss | -0.0488 | +| n_updates | 154780 | +| policy_gradient_loss | -0.0606 | +| value_loss | 0.000492 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | 0.227 | +| time/ | | +| fps | 309 | +| iterations | 9427 | +| time_elapsed | 31194 | +| total_timesteps | 9653248 | +| train/ | | +| approx_kl | 2.0371575 | +| clip_fraction | 0.509 | +| clip_range | 0.2 | +| entropy_loss | -0.448 | +| explained_variance | -0.517 | +| learning_rate | 0.0001 | +| loss | -0.0766 | +| n_updates | 154790 | +| policy_gradient_loss | -0.0654 | +| value_loss | 0.000828 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.59e+03 | +| ep_rew_mean | 0.227 | +| time/ | | +| fps | 309 | +| iterations | 9428 | +| time_elapsed | 31197 | +| total_timesteps | 9654272 | +| train/ | | +| approx_kl | 2.9899035 | +| clip_fraction | 0.514 | +| clip_range | 0.2 | +| entropy_loss | -0.488 | +| explained_variance | -3.1 | +| learning_rate | 0.0001 | +| loss | -0.109 | +| n_updates | 154800 | +| policy_gradient_loss | -0.078 | +| value_loss | 0.000511 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.61e+03 | +| ep_rew_mean | 0.229 | +| time/ | | +| fps | 309 | +| iterations | 9429 | +| time_elapsed | 31200 | +| total_timesteps | 9655296 | +| train/ | | +| approx_kl | 1.3662992 | +| clip_fraction | 0.506 | +| clip_range | 0.2 | +| entropy_loss | -0.488 | +| explained_variance | -1.67 | +| learning_rate | 0.0001 | +| loss | -0.0947 | +| n_updates | 154810 | +| policy_gradient_loss | -0.0712 | +| value_loss | 0.000557 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.61e+03 | +| ep_rew_mean | 0.229 | +| time/ | | +| fps | 309 | +| iterations | 9430 | +| time_elapsed | 31204 | +| total_timesteps | 9656320 | +| train/ | | +| approx_kl | 1.7403654 | +| clip_fraction | 0.504 | +| clip_range | 0.2 | +| entropy_loss | -0.466 | +| explained_variance | -0.65 | +| learning_rate | 0.0001 | +| loss | -0.0899 | +| n_updates | 154820 | +| policy_gradient_loss | -0.0653 | +| value_loss | 0.000376 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | 0.23 | +| time/ | | +| fps | 309 | +| iterations | 9431 | +| time_elapsed | 31207 | +| total_timesteps | 9657344 | +| train/ | | +| approx_kl | 2.2627945 | +| clip_fraction | 0.497 | +| clip_range | 0.2 | +| entropy_loss | -0.444 | +| explained_variance | -2.05 | +| learning_rate | 0.0001 | +| loss | -0.0869 | +| n_updates | 154830 | +| policy_gradient_loss | -0.0742 | +| value_loss | 0.000518 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | 0.23 | +| time/ | | +| fps | 309 | +| iterations | 9432 | +| time_elapsed | 31210 | +| total_timesteps | 9658368 | +| train/ | | +| approx_kl | 2.1057448 | +| clip_fraction | 0.486 | +| clip_range | 0.2 | +| entropy_loss | -0.407 | +| explained_variance | -1.38 | +| learning_rate | 0.0001 | +| loss | -0.0854 | +| n_updates | 154840 | +| policy_gradient_loss | -0.0728 | +| value_loss | 0.000529 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | 0.23 | +| time/ | | +| fps | 309 | +| iterations | 9433 | +| time_elapsed | 31214 | +| total_timesteps | 9659392 | +| train/ | | +| approx_kl | 3.189999 | +| clip_fraction | 0.515 | +| clip_range | 0.2 | +| entropy_loss | -0.533 | +| explained_variance | -0.979 | +| learning_rate | 0.0001 | +| loss | -0.105 | +| n_updates | 154850 | +| policy_gradient_loss | -0.0747 | +| value_loss | 0.000407 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | 0.23 | +| time/ | | +| fps | 309 | +| iterations | 9434 | +| time_elapsed | 31217 | +| total_timesteps | 9660416 | +| train/ | | +| approx_kl | 2.264792 | +| clip_fraction | 0.505 | +| clip_range | 0.2 | +| entropy_loss | -0.418 | +| explained_variance | -4.1 | +| learning_rate | 0.0001 | +| loss | -0.0948 | +| n_updates | 154860 | +| policy_gradient_loss | -0.0751 | +| value_loss | 0.000268 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | 0.23 | +| time/ | | +| fps | 309 | +| iterations | 9435 | +| time_elapsed | 31220 | +| total_timesteps | 9661440 | +| train/ | | +| approx_kl | 2.2867217 | +| clip_fraction | 0.495 | +| clip_range | 0.2 | +| entropy_loss | -0.37 | +| explained_variance | -6.03 | +| learning_rate | 0.0001 | +| loss | -0.0996 | +| n_updates | 154870 | +| policy_gradient_loss | -0.0796 | +| value_loss | 0.000244 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | 0.23 | +| time/ | | +| fps | 309 | +| iterations | 9436 | +| time_elapsed | 31223 | +| total_timesteps | 9662464 | +| train/ | | +| approx_kl | 1.0268612 | +| clip_fraction | 0.404 | +| clip_range | 0.2 | +| entropy_loss | -0.51 | +| explained_variance | -0.0182 | +| learning_rate | 0.0001 | +| loss | -0.0458 | +| n_updates | 154880 | +| policy_gradient_loss | -0.0273 | +| value_loss | 0.000848 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.6e+03 | +| ep_rew_mean | 0.23 | +| time/ | | +| fps | 309 | +| iterations | 9437 | +| time_elapsed | 31227 | +| total_timesteps | 9663488 | +| train/ | | +| approx_kl | 1.8425854 | +| clip_fraction | 0.502 | +| clip_range | 0.2 | +| entropy_loss | -0.4 | +| explained_variance | -2.41 | +| learning_rate | 0.0001 | +| loss | -0.0805 | +| n_updates | 154890 | +| policy_gradient_loss | -0.0711 | +| value_loss | 0.000781 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.235 | +| time/ | | +| fps | 309 | +| iterations | 9438 | +| time_elapsed | 31230 | +| total_timesteps | 9664512 | +| train/ | | +| approx_kl | 2.364952 | +| clip_fraction | 0.53 | +| clip_range | 0.2 | +| entropy_loss | -0.423 | +| explained_variance | -4.9 | +| learning_rate | 0.0001 | +| loss | -0.0889 | +| n_updates | 154900 | +| policy_gradient_loss | -0.0796 | +| value_loss | 0.000409 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.67e+03 | +| ep_rew_mean | 0.235 | +| time/ | | +| fps | 309 | +| iterations | 9439 | +| time_elapsed | 31233 | +| total_timesteps | 9665536 | +| train/ | | +| approx_kl | 2.2644157 | +| clip_fraction | 0.511 | +| clip_range | 0.2 | +| entropy_loss | -0.378 | +| explained_variance | -1.33 | +| learning_rate | 0.0001 | +| loss | -0.108 | +| n_updates | 154910 | +| policy_gradient_loss | -0.0589 | +| value_loss | 0.000409 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.24 | +| time/ | | +| fps | 309 | +| iterations | 9440 | +| time_elapsed | 31236 | +| total_timesteps | 9666560 | +| train/ | | +| approx_kl | 1.8365214 | +| clip_fraction | 0.514 | +| clip_range | 0.2 | +| entropy_loss | -0.468 | +| explained_variance | -1.71 | +| learning_rate | 0.0001 | +| loss | -0.0916 | +| n_updates | 154920 | +| policy_gradient_loss | -0.0767 | +| value_loss | 0.000667 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.245 | +| time/ | | +| fps | 309 | +| iterations | 9441 | +| time_elapsed | 31239 | +| total_timesteps | 9667584 | +| train/ | | +| approx_kl | 1.3791779 | +| clip_fraction | 0.489 | +| clip_range | 0.2 | +| entropy_loss | -0.457 | +| explained_variance | -1.94 | +| learning_rate | 0.0001 | +| loss | -0.0919 | +| n_updates | 154930 | +| policy_gradient_loss | -0.069 | +| value_loss | 0.000358 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.245 | +| time/ | | +| fps | 309 | +| iterations | 9442 | +| time_elapsed | 31243 | +| total_timesteps | 9668608 | +| train/ | | +| approx_kl | 1.9842207 | +| clip_fraction | 0.529 | +| clip_range | 0.2 | +| entropy_loss | -0.464 | +| explained_variance | -0.513 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 154940 | +| policy_gradient_loss | -0.0761 | +| value_loss | 0.000515 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.243 | +| time/ | | +| fps | 309 | +| iterations | 9443 | +| time_elapsed | 31246 | +| total_timesteps | 9669632 | +| train/ | | +| approx_kl | 2.1716242 | +| clip_fraction | 0.542 | +| clip_range | 0.2 | +| entropy_loss | -0.457 | +| explained_variance | -5.55 | +| learning_rate | 0.0001 | +| loss | -0.0701 | +| n_updates | 154950 | +| policy_gradient_loss | -0.0697 | +| value_loss | 0.000283 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.243 | +| time/ | | +| fps | 309 | +| iterations | 9444 | +| time_elapsed | 31250 | +| total_timesteps | 9670656 | +| train/ | | +| approx_kl | 1.4037199 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.461 | +| explained_variance | -3.05 | +| learning_rate | 0.0001 | +| loss | -0.0955 | +| n_updates | 154960 | +| policy_gradient_loss | -0.0718 | +| value_loss | 0.000114 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.68e+03 | +| ep_rew_mean | 0.243 | +| time/ | | +| fps | 309 | +| iterations | 9445 | +| time_elapsed | 31253 | +| total_timesteps | 9671680 | +| train/ | | +| approx_kl | 2.1977167 | +| clip_fraction | 0.565 | +| clip_range | 0.2 | +| entropy_loss | -0.544 | +| explained_variance | -0.231 | +| learning_rate | 0.0001 | +| loss | -0.118 | +| n_updates | 154970 | +| policy_gradient_loss | -0.0768 | +| value_loss | 0.000419 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.244 | +| time/ | | +| fps | 309 | +| iterations | 9446 | +| time_elapsed | 31257 | +| total_timesteps | 9672704 | +| train/ | | +| approx_kl | 5.1959825 | +| clip_fraction | 0.519 | +| clip_range | 0.2 | +| entropy_loss | -0.469 | +| explained_variance | -1.85 | +| learning_rate | 0.0001 | +| loss | -0.0912 | +| n_updates | 154980 | +| policy_gradient_loss | -0.0737 | +| value_loss | 0.000769 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.244 | +| time/ | | +| fps | 309 | +| iterations | 9447 | +| time_elapsed | 31261 | +| total_timesteps | 9673728 | +| train/ | | +| approx_kl | 1.9832405 | +| clip_fraction | 0.506 | +| clip_range | 0.2 | +| entropy_loss | -0.437 | +| explained_variance | -1.55 | +| learning_rate | 0.0001 | +| loss | -0.094 | +| n_updates | 154990 | +| policy_gradient_loss | -0.0738 | +| value_loss | 0.00039 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.243 | +| time/ | | +| fps | 309 | +| iterations | 9448 | +| time_elapsed | 31264 | +| total_timesteps | 9674752 | +| train/ | | +| approx_kl | 3.0385911 | +| clip_fraction | 0.537 | +| clip_range | 0.2 | +| entropy_loss | -0.452 | +| explained_variance | -1.53 | +| learning_rate | 0.0001 | +| loss | -0.105 | +| n_updates | 155000 | +| policy_gradient_loss | -0.077 | +| value_loss | 0.000448 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.243 | +| time/ | | +| fps | 309 | +| iterations | 9449 | +| time_elapsed | 31268 | +| total_timesteps | 9675776 | +| train/ | | +| approx_kl | 1.6667469 | +| clip_fraction | 0.493 | +| clip_range | 0.2 | +| entropy_loss | -0.484 | +| explained_variance | -0.929 | +| learning_rate | 0.0001 | +| loss | -0.0933 | +| n_updates | 155010 | +| policy_gradient_loss | -0.0682 | +| value_loss | 0.000262 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.69e+03 | +| ep_rew_mean | 0.243 | +| time/ | | +| fps | 309 | +| iterations | 9450 | +| time_elapsed | 31271 | +| total_timesteps | 9676800 | +| train/ | | +| approx_kl | 1.8289845 | +| clip_fraction | 0.533 | +| clip_range | 0.2 | +| entropy_loss | -0.542 | +| explained_variance | -0.245 | +| learning_rate | 0.0001 | +| loss | -0.0951 | +| n_updates | 155020 | +| policy_gradient_loss | -0.0736 | +| value_loss | 0.000202 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.248 | +| time/ | | +| fps | 309 | +| iterations | 9451 | +| time_elapsed | 31274 | +| total_timesteps | 9677824 | +| train/ | | +| approx_kl | 1.651404 | +| clip_fraction | 0.536 | +| clip_range | 0.2 | +| entropy_loss | -0.507 | +| explained_variance | -0.968 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 155030 | +| policy_gradient_loss | -0.0716 | +| value_loss | 0.000203 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.249 | +| time/ | | +| fps | 309 | +| iterations | 9452 | +| time_elapsed | 31277 | +| total_timesteps | 9678848 | +| train/ | | +| approx_kl | 1.6189461 | +| clip_fraction | 0.509 | +| clip_range | 0.2 | +| entropy_loss | -0.534 | +| explained_variance | -0.689 | +| learning_rate | 0.0001 | +| loss | -0.0672 | +| n_updates | 155040 | +| policy_gradient_loss | -0.0689 | +| value_loss | 0.000225 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.249 | +| time/ | | +| fps | 309 | +| iterations | 9453 | +| time_elapsed | 31281 | +| total_timesteps | 9679872 | +| train/ | | +| approx_kl | 2.1115923 | +| clip_fraction | 0.51 | +| clip_range | 0.2 | +| entropy_loss | -0.433 | +| explained_variance | -0.529 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 155050 | +| policy_gradient_loss | -0.0735 | +| value_loss | 0.000356 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.71e+03 | +| ep_rew_mean | 0.249 | +| time/ | | +| fps | 309 | +| iterations | 9454 | +| time_elapsed | 31284 | +| total_timesteps | 9680896 | +| train/ | | +| approx_kl | 2.1209943 | +| clip_fraction | 0.51 | +| clip_range | 0.2 | +| entropy_loss | -0.449 | +| explained_variance | -2.86 | +| learning_rate | 0.0001 | +| loss | -0.0903 | +| n_updates | 155060 | +| policy_gradient_loss | -0.0775 | +| value_loss | 0.000441 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.252 | +| time/ | | +| fps | 309 | +| iterations | 9455 | +| time_elapsed | 31287 | +| total_timesteps | 9681920 | +| train/ | | +| approx_kl | 1.8783466 | +| clip_fraction | 0.515 | +| clip_range | 0.2 | +| entropy_loss | -0.485 | +| explained_variance | -1.56 | +| learning_rate | 0.0001 | +| loss | -0.0791 | +| n_updates | 155070 | +| policy_gradient_loss | -0.0704 | +| value_loss | 0.000641 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.72e+03 | +| ep_rew_mean | 0.252 | +| time/ | | +| fps | 309 | +| iterations | 9456 | +| time_elapsed | 31290 | +| total_timesteps | 9682944 | +| train/ | | +| approx_kl | 1.6705877 | +| clip_fraction | 0.473 | +| clip_range | 0.2 | +| entropy_loss | -0.446 | +| explained_variance | -0.806 | +| learning_rate | 0.0001 | +| loss | -0.0858 | +| n_updates | 155080 | +| policy_gradient_loss | -0.07 | +| value_loss | 0.000563 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.257 | +| time/ | | +| fps | 309 | +| iterations | 9457 | +| time_elapsed | 31293 | +| total_timesteps | 9683968 | +| train/ | | +| approx_kl | 1.2509639 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.494 | +| explained_variance | -1.98 | +| learning_rate | 0.0001 | +| loss | -0.0912 | +| n_updates | 155090 | +| policy_gradient_loss | -0.0711 | +| value_loss | 0.000378 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.74e+03 | +| ep_rew_mean | 0.257 | +| time/ | | +| fps | 309 | +| iterations | 9458 | +| time_elapsed | 31296 | +| total_timesteps | 9684992 | +| train/ | | +| approx_kl | 1.6756401 | +| clip_fraction | 0.458 | +| clip_range | 0.2 | +| entropy_loss | -0.397 | +| explained_variance | -2.78 | +| learning_rate | 0.0001 | +| loss | -0.0818 | +| n_updates | 155100 | +| policy_gradient_loss | -0.0623 | +| value_loss | 0.00052 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.254 | +| time/ | | +| fps | 309 | +| iterations | 9459 | +| time_elapsed | 31300 | +| total_timesteps | 9686016 | +| train/ | | +| approx_kl | 3.3684392 | +| clip_fraction | 0.506 | +| clip_range | 0.2 | +| entropy_loss | -0.481 | +| explained_variance | -5.34 | +| learning_rate | 0.0001 | +| loss | -0.107 | +| n_updates | 155110 | +| policy_gradient_loss | -0.0725 | +| value_loss | 0.000245 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.254 | +| time/ | | +| fps | 309 | +| iterations | 9460 | +| time_elapsed | 31303 | +| total_timesteps | 9687040 | +| train/ | | +| approx_kl | 1.6990292 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.414 | +| explained_variance | -1.02 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 155120 | +| policy_gradient_loss | -0.0693 | +| value_loss | 0.000333 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.253 | +| time/ | | +| fps | 309 | +| iterations | 9461 | +| time_elapsed | 31306 | +| total_timesteps | 9688064 | +| train/ | | +| approx_kl | 2.4917746 | +| clip_fraction | 0.525 | +| clip_range | 0.2 | +| entropy_loss | -0.464 | +| explained_variance | -0.596 | +| learning_rate | 0.0001 | +| loss | -0.0852 | +| n_updates | 155130 | +| policy_gradient_loss | -0.0743 | +| value_loss | 0.000511 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.257 | +| time/ | | +| fps | 309 | +| iterations | 9462 | +| time_elapsed | 31310 | +| total_timesteps | 9689088 | +| train/ | | +| approx_kl | 1.6087358 | +| clip_fraction | 0.516 | +| clip_range | 0.2 | +| entropy_loss | -0.482 | +| explained_variance | -1.14 | +| learning_rate | 0.0001 | +| loss | -0.0887 | +| n_updates | 155140 | +| policy_gradient_loss | -0.0713 | +| value_loss | 0.000366 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.257 | +| time/ | | +| fps | 309 | +| iterations | 9463 | +| time_elapsed | 31313 | +| total_timesteps | 9690112 | +| train/ | | +| approx_kl | 1.9299039 | +| clip_fraction | 0.501 | +| clip_range | 0.2 | +| entropy_loss | -0.423 | +| explained_variance | -0.211 | +| learning_rate | 0.0001 | +| loss | -0.0883 | +| n_updates | 155150 | +| policy_gradient_loss | -0.0691 | +| value_loss | 0.000607 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.261 | +| time/ | | +| fps | 309 | +| iterations | 9464 | +| time_elapsed | 31317 | +| total_timesteps | 9691136 | +| train/ | | +| approx_kl | 1.743767 | +| clip_fraction | 0.538 | +| clip_range | 0.2 | +| entropy_loss | -0.512 | +| explained_variance | -1.42 | +| learning_rate | 0.0001 | +| loss | -0.092 | +| n_updates | 155160 | +| policy_gradient_loss | -0.0738 | +| value_loss | 0.00069 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.261 | +| time/ | | +| fps | 309 | +| iterations | 9465 | +| time_elapsed | 31320 | +| total_timesteps | 9692160 | +| train/ | | +| approx_kl | 1.8504708 | +| clip_fraction | 0.506 | +| clip_range | 0.2 | +| entropy_loss | -0.472 | +| explained_variance | -0.803 | +| learning_rate | 0.0001 | +| loss | -0.0919 | +| n_updates | 155170 | +| policy_gradient_loss | -0.0766 | +| value_loss | 0.000582 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.75e+03 | +| ep_rew_mean | 0.261 | +| time/ | | +| fps | 309 | +| iterations | 9466 | +| time_elapsed | 31324 | +| total_timesteps | 9693184 | +| train/ | | +| approx_kl | 3.3481007 | +| clip_fraction | 0.504 | +| clip_range | 0.2 | +| entropy_loss | -0.47 | +| explained_variance | -2.58 | +| learning_rate | 0.0001 | +| loss | -0.0779 | +| n_updates | 155180 | +| policy_gradient_loss | -0.0658 | +| value_loss | 0.00045 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.262 | +| time/ | | +| fps | 309 | +| iterations | 9467 | +| time_elapsed | 31327 | +| total_timesteps | 9694208 | +| train/ | | +| approx_kl | 2.6793027 | +| clip_fraction | 0.528 | +| clip_range | 0.2 | +| entropy_loss | -0.488 | +| explained_variance | -0.711 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 155190 | +| policy_gradient_loss | -0.0678 | +| value_loss | 0.0003 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.262 | +| time/ | | +| fps | 309 | +| iterations | 9468 | +| time_elapsed | 31331 | +| total_timesteps | 9695232 | +| train/ | | +| approx_kl | 2.2955456 | +| clip_fraction | 0.494 | +| clip_range | 0.2 | +| entropy_loss | -0.443 | +| explained_variance | -6.51 | +| learning_rate | 0.0001 | +| loss | -0.0988 | +| n_updates | 155200 | +| policy_gradient_loss | -0.076 | +| value_loss | 0.000399 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.76e+03 | +| ep_rew_mean | 0.262 | +| time/ | | +| fps | 309 | +| iterations | 9469 | +| time_elapsed | 31334 | +| total_timesteps | 9696256 | +| train/ | | +| approx_kl | 2.4449615 | +| clip_fraction | 0.526 | +| clip_range | 0.2 | +| entropy_loss | -0.487 | +| explained_variance | -3.52 | +| learning_rate | 0.0001 | +| loss | -0.0669 | +| n_updates | 155210 | +| policy_gradient_loss | -0.0767 | +| value_loss | 0.000467 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.26 | +| time/ | | +| fps | 309 | +| iterations | 9470 | +| time_elapsed | 31337 | +| total_timesteps | 9697280 | +| train/ | | +| approx_kl | 2.1969726 | +| clip_fraction | 0.544 | +| clip_range | 0.2 | +| entropy_loss | -0.471 | +| explained_variance | -1.1 | +| learning_rate | 0.0001 | +| loss | -0.1 | +| n_updates | 155220 | +| policy_gradient_loss | -0.0789 | +| value_loss | 0.000438 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.26 | +| time/ | | +| fps | 309 | +| iterations | 9471 | +| time_elapsed | 31340 | +| total_timesteps | 9698304 | +| train/ | | +| approx_kl | 2.1716702 | +| clip_fraction | 0.511 | +| clip_range | 0.2 | +| entropy_loss | -0.434 | +| explained_variance | -0.507 | +| learning_rate | 0.0001 | +| loss | -0.0883 | +| n_updates | 155230 | +| policy_gradient_loss | -0.0698 | +| value_loss | 0.000389 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.77e+03 | +| ep_rew_mean | 0.26 | +| time/ | | +| fps | 309 | +| iterations | 9472 | +| time_elapsed | 31343 | +| total_timesteps | 9699328 | +| train/ | | +| approx_kl | 1.8572718 | +| clip_fraction | 0.525 | +| clip_range | 0.2 | +| entropy_loss | -0.506 | +| explained_variance | -2.24 | +| learning_rate | 0.0001 | +| loss | -0.121 | +| n_updates | 155240 | +| policy_gradient_loss | -0.0803 | +| value_loss | 0.000268 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.265 | +| time/ | | +| fps | 309 | +| iterations | 9473 | +| time_elapsed | 31347 | +| total_timesteps | 9700352 | +| train/ | | +| approx_kl | 1.6713471 | +| clip_fraction | 0.528 | +| clip_range | 0.2 | +| entropy_loss | -0.496 | +| explained_variance | -1.97 | +| learning_rate | 0.0001 | +| loss | -0.0977 | +| n_updates | 155250 | +| policy_gradient_loss | -0.0788 | +| value_loss | 0.000255 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.265 | +| time/ | | +| fps | 309 | +| iterations | 9474 | +| time_elapsed | 31350 | +| total_timesteps | 9701376 | +| train/ | | +| approx_kl | 1.7653917 | +| clip_fraction | 0.492 | +| clip_range | 0.2 | +| entropy_loss | -0.454 | +| explained_variance | -0.439 | +| learning_rate | 0.0001 | +| loss | -0.0998 | +| n_updates | 155260 | +| policy_gradient_loss | -0.067 | +| value_loss | 0.000337 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.79e+03 | +| ep_rew_mean | 0.265 | +| time/ | | +| fps | 309 | +| iterations | 9475 | +| time_elapsed | 31353 | +| total_timesteps | 9702400 | +| train/ | | +| approx_kl | 3.4194767 | +| clip_fraction | 0.51 | +| clip_range | 0.2 | +| entropy_loss | -0.441 | +| explained_variance | -8.85 | +| learning_rate | 0.0001 | +| loss | -0.0967 | +| n_updates | 155270 | +| policy_gradient_loss | -0.066 | +| value_loss | 0.000312 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.81e+03 | +| ep_rew_mean | 0.267 | +| time/ | | +| fps | 309 | +| iterations | 9476 | +| time_elapsed | 31356 | +| total_timesteps | 9703424 | +| train/ | | +| approx_kl | 2.9658651 | +| clip_fraction | 0.534 | +| clip_range | 0.2 | +| entropy_loss | -0.444 | +| explained_variance | -1.4 | +| learning_rate | 0.0001 | +| loss | -0.0943 | +| n_updates | 155280 | +| policy_gradient_loss | -0.0748 | +| value_loss | 0.000485 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.81e+03 | +| ep_rew_mean | 0.268 | +| time/ | | +| fps | 309 | +| iterations | 9477 | +| time_elapsed | 31359 | +| total_timesteps | 9704448 | +| train/ | | +| approx_kl | 1.6981745 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.406 | +| explained_variance | -1.28 | +| learning_rate | 0.0001 | +| loss | -0.0775 | +| n_updates | 155290 | +| policy_gradient_loss | -0.0694 | +| value_loss | 0.000473 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.81e+03 | +| ep_rew_mean | 0.268 | +| time/ | | +| fps | 309 | +| iterations | 9478 | +| time_elapsed | 31363 | +| total_timesteps | 9705472 | +| train/ | | +| approx_kl | 1.3453627 | +| clip_fraction | 0.472 | +| clip_range | 0.2 | +| entropy_loss | -0.4 | +| explained_variance | -0.176 | +| learning_rate | 0.0001 | +| loss | -0.0814 | +| n_updates | 155300 | +| policy_gradient_loss | -0.0722 | +| value_loss | 0.00065 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.81e+03 | +| ep_rew_mean | 0.268 | +| time/ | | +| fps | 309 | +| iterations | 9479 | +| time_elapsed | 31366 | +| total_timesteps | 9706496 | +| train/ | | +| approx_kl | 2.1147795 | +| clip_fraction | 0.535 | +| clip_range | 0.2 | +| entropy_loss | -0.448 | +| explained_variance | -2 | +| learning_rate | 0.0001 | +| loss | -0.122 | +| n_updates | 155310 | +| policy_gradient_loss | -0.0796 | +| value_loss | 0.000753 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.272 | +| time/ | | +| fps | 309 | +| iterations | 9480 | +| time_elapsed | 31370 | +| total_timesteps | 9707520 | +| train/ | | +| approx_kl | 1.9316725 | +| clip_fraction | 0.53 | +| clip_range | 0.2 | +| entropy_loss | -0.481 | +| explained_variance | -2.58 | +| learning_rate | 0.0001 | +| loss | -0.114 | +| n_updates | 155320 | +| policy_gradient_loss | -0.081 | +| value_loss | 0.000309 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.83e+03 | +| ep_rew_mean | 0.272 | +| time/ | | +| fps | 309 | +| iterations | 9481 | +| time_elapsed | 31373 | +| total_timesteps | 9708544 | +| train/ | | +| approx_kl | 1.8092079 | +| clip_fraction | 0.503 | +| clip_range | 0.2 | +| entropy_loss | -0.477 | +| explained_variance | -0.51 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 155330 | +| policy_gradient_loss | -0.0701 | +| value_loss | 0.000167 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.276 | +| time/ | | +| fps | 309 | +| iterations | 9482 | +| time_elapsed | 31377 | +| total_timesteps | 9709568 | +| train/ | | +| approx_kl | 2.183426 | +| clip_fraction | 0.544 | +| clip_range | 0.2 | +| entropy_loss | -0.474 | +| explained_variance | -0.272 | +| learning_rate | 0.0001 | +| loss | -0.0747 | +| n_updates | 155340 | +| policy_gradient_loss | -0.0658 | +| value_loss | 0.000634 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.276 | +| time/ | | +| fps | 309 | +| iterations | 9483 | +| time_elapsed | 31380 | +| total_timesteps | 9710592 | +| train/ | | +| approx_kl | 2.3766675 | +| clip_fraction | 0.458 | +| clip_range | 0.2 | +| entropy_loss | -0.413 | +| explained_variance | -3.17 | +| learning_rate | 0.0001 | +| loss | -0.0683 | +| n_updates | 155350 | +| policy_gradient_loss | -0.0655 | +| value_loss | 0.000548 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.84e+03 | +| ep_rew_mean | 0.276 | +| time/ | | +| fps | 309 | +| iterations | 9484 | +| time_elapsed | 31384 | +| total_timesteps | 9711616 | +| train/ | | +| approx_kl | 2.1572065 | +| clip_fraction | 0.524 | +| clip_range | 0.2 | +| entropy_loss | -0.476 | +| explained_variance | -1.68 | +| learning_rate | 0.0001 | +| loss | -0.0996 | +| n_updates | 155360 | +| policy_gradient_loss | -0.0795 | +| value_loss | 0.000307 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 309 | +| iterations | 9485 | +| time_elapsed | 31387 | +| total_timesteps | 9712640 | +| train/ | | +| approx_kl | 1.8699179 | +| clip_fraction | 0.498 | +| clip_range | 0.2 | +| entropy_loss | -0.49 | +| explained_variance | -3.93 | +| learning_rate | 0.0001 | +| loss | -0.114 | +| n_updates | 155370 | +| policy_gradient_loss | -0.0735 | +| value_loss | 0.000182 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.86e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 309 | +| iterations | 9486 | +| time_elapsed | 31390 | +| total_timesteps | 9713664 | +| train/ | | +| approx_kl | 1.5701948 | +| clip_fraction | 0.45 | +| clip_range | 0.2 | +| entropy_loss | -0.387 | +| explained_variance | -0.565 | +| learning_rate | 0.0001 | +| loss | -0.0975 | +| n_updates | 155380 | +| policy_gradient_loss | -0.064 | +| value_loss | 0.000361 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.28 | +| time/ | | +| fps | 309 | +| iterations | 9487 | +| time_elapsed | 31394 | +| total_timesteps | 9714688 | +| train/ | | +| approx_kl | 2.008439 | +| clip_fraction | 0.501 | +| clip_range | 0.2 | +| entropy_loss | -0.468 | +| explained_variance | -1.43 | +| learning_rate | 0.0001 | +| loss | -0.114 | +| n_updates | 155390 | +| policy_gradient_loss | -0.0725 | +| value_loss | 0.000359 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.87e+03 | +| ep_rew_mean | 0.28 | +| time/ | | +| fps | 309 | +| iterations | 9488 | +| time_elapsed | 31397 | +| total_timesteps | 9715712 | +| train/ | | +| approx_kl | 1.4610472 | +| clip_fraction | 0.551 | +| clip_range | 0.2 | +| entropy_loss | -0.556 | +| explained_variance | -2.25 | +| learning_rate | 0.0001 | +| loss | -0.0998 | +| n_updates | 155400 | +| policy_gradient_loss | -0.0816 | +| value_loss | 0.000282 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 309 | +| iterations | 9489 | +| time_elapsed | 31400 | +| total_timesteps | 9716736 | +| train/ | | +| approx_kl | 1.9514862 | +| clip_fraction | 0.514 | +| clip_range | 0.2 | +| entropy_loss | -0.424 | +| explained_variance | -0.874 | +| learning_rate | 0.0001 | +| loss | -0.0893 | +| n_updates | 155410 | +| policy_gradient_loss | -0.0722 | +| value_loss | 0.00062 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 309 | +| iterations | 9490 | +| time_elapsed | 31403 | +| total_timesteps | 9717760 | +| train/ | | +| approx_kl | 2.5595653 | +| clip_fraction | 0.529 | +| clip_range | 0.2 | +| entropy_loss | -0.452 | +| explained_variance | -1.29 | +| learning_rate | 0.0001 | +| loss | -0.108 | +| n_updates | 155420 | +| policy_gradient_loss | -0.082 | +| value_loss | 0.000677 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 309 | +| iterations | 9491 | +| time_elapsed | 31406 | +| total_timesteps | 9718784 | +| train/ | | +| approx_kl | 2.409225 | +| clip_fraction | 0.507 | +| clip_range | 0.2 | +| entropy_loss | -0.483 | +| explained_variance | -3.51 | +| learning_rate | 0.0001 | +| loss | -0.111 | +| n_updates | 155430 | +| policy_gradient_loss | -0.0687 | +| value_loss | 0.000236 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 309 | +| iterations | 9492 | +| time_elapsed | 31410 | +| total_timesteps | 9719808 | +| train/ | | +| approx_kl | 1.6206973 | +| clip_fraction | 0.479 | +| clip_range | 0.2 | +| entropy_loss | -0.406 | +| explained_variance | -0.761 | +| learning_rate | 0.0001 | +| loss | -0.0758 | +| n_updates | 155440 | +| policy_gradient_loss | -0.067 | +| value_loss | 0.000102 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 309 | +| iterations | 9493 | +| time_elapsed | 31413 | +| total_timesteps | 9720832 | +| train/ | | +| approx_kl | 1.6435955 | +| clip_fraction | 0.5 | +| clip_range | 0.2 | +| entropy_loss | -0.423 | +| explained_variance | -1.04 | +| learning_rate | 0.0001 | +| loss | -0.0874 | +| n_updates | 155450 | +| policy_gradient_loss | -0.0696 | +| value_loss | 0.000135 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.89e+03 | +| ep_rew_mean | 0.276 | +| time/ | | +| fps | 309 | +| iterations | 9494 | +| time_elapsed | 31416 | +| total_timesteps | 9721856 | +| train/ | | +| approx_kl | 1.4632425 | +| clip_fraction | 0.533 | +| clip_range | 0.2 | +| entropy_loss | -0.547 | +| explained_variance | -0.374 | +| learning_rate | 0.0001 | +| loss | -0.108 | +| n_updates | 155460 | +| policy_gradient_loss | -0.069 | +| value_loss | 0.000729 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.89e+03 | +| ep_rew_mean | 0.276 | +| time/ | | +| fps | 309 | +| iterations | 9495 | +| time_elapsed | 31419 | +| total_timesteps | 9722880 | +| train/ | | +| approx_kl | 1.6750746 | +| clip_fraction | 0.526 | +| clip_range | 0.2 | +| entropy_loss | -0.504 | +| explained_variance | -1.72 | +| learning_rate | 0.0001 | +| loss | -0.0853 | +| n_updates | 155470 | +| policy_gradient_loss | -0.0744 | +| value_loss | 0.000407 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.91e+03 | +| ep_rew_mean | 0.277 | +| time/ | | +| fps | 309 | +| iterations | 9496 | +| time_elapsed | 31423 | +| total_timesteps | 9723904 | +| train/ | | +| approx_kl | 1.6920958 | +| clip_fraction | 0.543 | +| clip_range | 0.2 | +| entropy_loss | -0.489 | +| explained_variance | -8.8 | +| learning_rate | 0.0001 | +| loss | -0.106 | +| n_updates | 155480 | +| policy_gradient_loss | -0.0807 | +| value_loss | 0.000398 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.91e+03 | +| ep_rew_mean | 0.277 | +| time/ | | +| fps | 309 | +| iterations | 9497 | +| time_elapsed | 31427 | +| total_timesteps | 9724928 | +| train/ | | +| approx_kl | 1.9641968 | +| clip_fraction | 0.494 | +| clip_range | 0.2 | +| entropy_loss | -0.406 | +| explained_variance | -1.28 | +| learning_rate | 0.0001 | +| loss | -0.108 | +| n_updates | 155490 | +| policy_gradient_loss | -0.0678 | +| value_loss | 0.00056 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.91e+03 | +| ep_rew_mean | 0.277 | +| time/ | | +| fps | 309 | +| iterations | 9498 | +| time_elapsed | 31430 | +| total_timesteps | 9725952 | +| train/ | | +| approx_kl | 1.5506176 | +| clip_fraction | 0.534 | +| clip_range | 0.2 | +| entropy_loss | -0.51 | +| explained_variance | -0.895 | +| learning_rate | 0.0001 | +| loss | -0.0967 | +| n_updates | 155500 | +| policy_gradient_loss | -0.0726 | +| value_loss | 0.000377 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.92e+03 | +| ep_rew_mean | 0.28 | +| time/ | | +| fps | 309 | +| iterations | 9499 | +| time_elapsed | 31434 | +| total_timesteps | 9726976 | +| train/ | | +| approx_kl | 1.7974011 | +| clip_fraction | 0.549 | +| clip_range | 0.2 | +| entropy_loss | -0.568 | +| explained_variance | -10.6 | +| learning_rate | 0.0001 | +| loss | -0.0837 | +| n_updates | 155510 | +| policy_gradient_loss | -0.0824 | +| value_loss | 0.000322 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.92e+03 | +| ep_rew_mean | 0.28 | +| time/ | | +| fps | 309 | +| iterations | 9500 | +| time_elapsed | 31437 | +| total_timesteps | 9728000 | +| train/ | | +| approx_kl | 1.4383643 | +| clip_fraction | 0.506 | +| clip_range | 0.2 | +| entropy_loss | -0.541 | +| explained_variance | -1.47 | +| learning_rate | 0.0001 | +| loss | -0.0852 | +| n_updates | 155520 | +| policy_gradient_loss | -0.0632 | +| value_loss | 0.000189 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.92e+03 | +| ep_rew_mean | 0.28 | +| time/ | | +| fps | 309 | +| iterations | 9501 | +| time_elapsed | 31441 | +| total_timesteps | 9729024 | +| train/ | | +| approx_kl | 1.7692448 | +| clip_fraction | 0.531 | +| clip_range | 0.2 | +| entropy_loss | -0.43 | +| explained_variance | -6.3 | +| learning_rate | 0.0001 | +| loss | -0.128 | +| n_updates | 155530 | +| policy_gradient_loss | -0.0808 | +| value_loss | 0.000512 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.93e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 309 | +| iterations | 9502 | +| time_elapsed | 31444 | +| total_timesteps | 9730048 | +| train/ | | +| approx_kl | 1.7420197 | +| clip_fraction | 0.524 | +| clip_range | 0.2 | +| entropy_loss | -0.483 | +| explained_variance | -2.72 | +| learning_rate | 0.0001 | +| loss | -0.0935 | +| n_updates | 155540 | +| policy_gradient_loss | -0.0765 | +| value_loss | 0.000317 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.94e+03 | +| ep_rew_mean | 0.28 | +| time/ | | +| fps | 309 | +| iterations | 9503 | +| time_elapsed | 31447 | +| total_timesteps | 9731072 | +| train/ | | +| approx_kl | 1.9240794 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.399 | +| explained_variance | -0.824 | +| learning_rate | 0.0001 | +| loss | -0.0621 | +| n_updates | 155550 | +| policy_gradient_loss | -0.0587 | +| value_loss | 0.000432 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.94e+03 | +| ep_rew_mean | 0.28 | +| time/ | | +| fps | 309 | +| iterations | 9504 | +| time_elapsed | 31451 | +| total_timesteps | 9732096 | +| train/ | | +| approx_kl | 1.3867655 | +| clip_fraction | 0.51 | +| clip_range | 0.2 | +| entropy_loss | -0.532 | +| explained_variance | -0.387 | +| learning_rate | 0.0001 | +| loss | -0.09 | +| n_updates | 155560 | +| policy_gradient_loss | -0.06 | +| value_loss | 0.00052 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.95e+03 | +| ep_rew_mean | 0.28 | +| time/ | | +| fps | 309 | +| iterations | 9505 | +| time_elapsed | 31454 | +| total_timesteps | 9733120 | +| train/ | | +| approx_kl | 55.53546 | +| clip_fraction | 0.518 | +| clip_range | 0.2 | +| entropy_loss | -0.464 | +| explained_variance | -3.45 | +| learning_rate | 0.0001 | +| loss | -0.0861 | +| n_updates | 155570 | +| policy_gradient_loss | -0.0656 | +| value_loss | 0.000315 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.95e+03 | +| ep_rew_mean | 0.28 | +| time/ | | +| fps | 309 | +| iterations | 9506 | +| time_elapsed | 31458 | +| total_timesteps | 9734144 | +| train/ | | +| approx_kl | 1.8739464 | +| clip_fraction | 0.462 | +| clip_range | 0.2 | +| entropy_loss | -0.389 | +| explained_variance | -0.868 | +| learning_rate | 0.0001 | +| loss | -0.087 | +| n_updates | 155580 | +| policy_gradient_loss | -0.0665 | +| value_loss | 0.000452 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.96e+03 | +| ep_rew_mean | 0.287 | +| time/ | | +| fps | 309 | +| iterations | 9507 | +| time_elapsed | 31461 | +| total_timesteps | 9735168 | +| train/ | | +| approx_kl | 2.3859808 | +| clip_fraction | 0.565 | +| clip_range | 0.2 | +| entropy_loss | -0.528 | +| explained_variance | -0.586 | +| learning_rate | 0.0001 | +| loss | -0.0814 | +| n_updates | 155590 | +| policy_gradient_loss | -0.0755 | +| value_loss | 0.000636 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.96e+03 | +| ep_rew_mean | 0.287 | +| time/ | | +| fps | 309 | +| iterations | 9508 | +| time_elapsed | 31464 | +| total_timesteps | 9736192 | +| train/ | | +| approx_kl | 2.060248 | +| clip_fraction | 0.514 | +| clip_range | 0.2 | +| entropy_loss | -0.498 | +| explained_variance | -0.92 | +| learning_rate | 0.0001 | +| loss | -0.0944 | +| n_updates | 155600 | +| policy_gradient_loss | -0.0717 | +| value_loss | 0.000636 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.96e+03 | +| ep_rew_mean | 0.289 | +| time/ | | +| fps | 309 | +| iterations | 9509 | +| time_elapsed | 31468 | +| total_timesteps | 9737216 | +| train/ | | +| approx_kl | 3.6960435 | +| clip_fraction | 0.546 | +| clip_range | 0.2 | +| entropy_loss | -0.497 | +| explained_variance | -1.74 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 155610 | +| policy_gradient_loss | -0.0846 | +| value_loss | 0.000635 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.96e+03 | +| ep_rew_mean | 0.289 | +| time/ | | +| fps | 309 | +| iterations | 9510 | +| time_elapsed | 31471 | +| total_timesteps | 9738240 | +| train/ | | +| approx_kl | 1.7320027 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.377 | +| explained_variance | -2.01 | +| learning_rate | 0.0001 | +| loss | -0.111 | +| n_updates | 155620 | +| policy_gradient_loss | -0.0643 | +| value_loss | 0.000547 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.96e+03 | +| ep_rew_mean | 0.289 | +| time/ | | +| fps | 309 | +| iterations | 9511 | +| time_elapsed | 31474 | +| total_timesteps | 9739264 | +| train/ | | +| approx_kl | 2.1608958 | +| clip_fraction | 0.518 | +| clip_range | 0.2 | +| entropy_loss | -0.457 | +| explained_variance | -0.95 | +| learning_rate | 0.0001 | +| loss | -0.0941 | +| n_updates | 155630 | +| policy_gradient_loss | -0.0784 | +| value_loss | 0.000553 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.98e+03 | +| ep_rew_mean | 0.288 | +| time/ | | +| fps | 309 | +| iterations | 9512 | +| time_elapsed | 31478 | +| total_timesteps | 9740288 | +| train/ | | +| approx_kl | 1.5642841 | +| clip_fraction | 0.5 | +| clip_range | 0.2 | +| entropy_loss | -0.478 | +| explained_variance | -5.58 | +| learning_rate | 0.0001 | +| loss | -0.112 | +| n_updates | 155640 | +| policy_gradient_loss | -0.078 | +| value_loss | 0.000477 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.98e+03 | +| ep_rew_mean | 0.288 | +| time/ | | +| fps | 309 | +| iterations | 9513 | +| time_elapsed | 31481 | +| total_timesteps | 9741312 | +| train/ | | +| approx_kl | 2.3850017 | +| clip_fraction | 0.49 | +| clip_range | 0.2 | +| entropy_loss | -0.416 | +| explained_variance | -0.647 | +| learning_rate | 0.0001 | +| loss | -0.0672 | +| n_updates | 155650 | +| policy_gradient_loss | -0.0621 | +| value_loss | 0.000566 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.99e+03 | +| ep_rew_mean | 0.292 | +| time/ | | +| fps | 309 | +| iterations | 9514 | +| time_elapsed | 31485 | +| total_timesteps | 9742336 | +| train/ | | +| approx_kl | 1.4132674 | +| clip_fraction | 0.519 | +| clip_range | 0.2 | +| entropy_loss | -0.572 | +| explained_variance | -1.75 | +| learning_rate | 0.0001 | +| loss | -0.0727 | +| n_updates | 155660 | +| policy_gradient_loss | -0.0654 | +| value_loss | 0.000257 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.99e+03 | +| ep_rew_mean | 0.292 | +| time/ | | +| fps | 309 | +| iterations | 9515 | +| time_elapsed | 31488 | +| total_timesteps | 9743360 | +| train/ | | +| approx_kl | 1.741156 | +| clip_fraction | 0.491 | +| clip_range | 0.2 | +| entropy_loss | -0.413 | +| explained_variance | -4.07 | +| learning_rate | 0.0001 | +| loss | -0.0873 | +| n_updates | 155670 | +| policy_gradient_loss | -0.0775 | +| value_loss | 0.000174 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.99e+03 | +| ep_rew_mean | 0.292 | +| time/ | | +| fps | 309 | +| iterations | 9516 | +| time_elapsed | 31491 | +| total_timesteps | 9744384 | +| train/ | | +| approx_kl | 2.340958 | +| clip_fraction | 0.55 | +| clip_range | 0.2 | +| entropy_loss | -0.487 | +| explained_variance | -0.52 | +| learning_rate | 0.0001 | +| loss | -0.0989 | +| n_updates | 155680 | +| policy_gradient_loss | -0.0702 | +| value_loss | 0.000353 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.01e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 309 | +| iterations | 9517 | +| time_elapsed | 31494 | +| total_timesteps | 9745408 | +| train/ | | +| approx_kl | 2.0536695 | +| clip_fraction | 0.523 | +| clip_range | 0.2 | +| entropy_loss | -0.437 | +| explained_variance | -1.31 | +| learning_rate | 0.0001 | +| loss | -0.076 | +| n_updates | 155690 | +| policy_gradient_loss | -0.0691 | +| value_loss | 0.000392 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.01e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 309 | +| iterations | 9518 | +| time_elapsed | 31498 | +| total_timesteps | 9746432 | +| train/ | | +| approx_kl | 2.1178036 | +| clip_fraction | 0.491 | +| clip_range | 0.2 | +| entropy_loss | -0.426 | +| explained_variance | -0.97 | +| learning_rate | 0.0001 | +| loss | -0.0854 | +| n_updates | 155700 | +| policy_gradient_loss | -0.0744 | +| value_loss | 0.000243 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.02e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 309 | +| iterations | 9519 | +| time_elapsed | 31501 | +| total_timesteps | 9747456 | +| train/ | | +| approx_kl | 1.4297332 | +| clip_fraction | 0.55 | +| clip_range | 0.2 | +| entropy_loss | -0.636 | +| explained_variance | -0.848 | +| learning_rate | 0.0001 | +| loss | -0.0935 | +| n_updates | 155710 | +| policy_gradient_loss | -0.0718 | +| value_loss | 0.000159 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.02e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 309 | +| iterations | 9520 | +| time_elapsed | 31504 | +| total_timesteps | 9748480 | +| train/ | | +| approx_kl | 1.6569743 | +| clip_fraction | 0.534 | +| clip_range | 0.2 | +| entropy_loss | -0.514 | +| explained_variance | -0.826 | +| learning_rate | 0.0001 | +| loss | -0.094 | +| n_updates | 155720 | +| policy_gradient_loss | -0.077 | +| value_loss | 0.000241 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.02e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 309 | +| iterations | 9521 | +| time_elapsed | 31508 | +| total_timesteps | 9749504 | +| train/ | | +| approx_kl | 1.549005 | +| clip_fraction | 0.516 | +| clip_range | 0.2 | +| entropy_loss | -0.453 | +| explained_variance | -0.557 | +| learning_rate | 0.0001 | +| loss | -0.0896 | +| n_updates | 155730 | +| policy_gradient_loss | -0.0677 | +| value_loss | 0.000525 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.04e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 309 | +| iterations | 9522 | +| time_elapsed | 31511 | +| total_timesteps | 9750528 | +| train/ | | +| approx_kl | 1.839785 | +| clip_fraction | 0.52 | +| clip_range | 0.2 | +| entropy_loss | -0.488 | +| explained_variance | -5.93 | +| learning_rate | 0.0001 | +| loss | -0.109 | +| n_updates | 155740 | +| policy_gradient_loss | -0.0818 | +| value_loss | 0.000323 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.04e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 309 | +| iterations | 9523 | +| time_elapsed | 31515 | +| total_timesteps | 9751552 | +| train/ | | +| approx_kl | 1.8991365 | +| clip_fraction | 0.526 | +| clip_range | 0.2 | +| entropy_loss | -0.491 | +| explained_variance | -1.26 | +| learning_rate | 0.0001 | +| loss | -0.0794 | +| n_updates | 155750 | +| policy_gradient_loss | -0.073 | +| value_loss | 0.000334 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.04e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 309 | +| iterations | 9524 | +| time_elapsed | 31518 | +| total_timesteps | 9752576 | +| train/ | | +| approx_kl | 2.066458 | +| clip_fraction | 0.524 | +| clip_range | 0.2 | +| entropy_loss | -0.467 | +| explained_variance | -0.378 | +| learning_rate | 0.0001 | +| loss | -0.0946 | +| n_updates | 155760 | +| policy_gradient_loss | -0.0717 | +| value_loss | 0.000805 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.04e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 309 | +| iterations | 9525 | +| time_elapsed | 31521 | +| total_timesteps | 9753600 | +| train/ | | +| approx_kl | 1.8682239 | +| clip_fraction | 0.524 | +| clip_range | 0.2 | +| entropy_loss | -0.421 | +| explained_variance | -2.5 | +| learning_rate | 0.0001 | +| loss | -0.0888 | +| n_updates | 155770 | +| policy_gradient_loss | -0.0734 | +| value_loss | 0.000882 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.04e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 309 | +| iterations | 9526 | +| time_elapsed | 31524 | +| total_timesteps | 9754624 | +| train/ | | +| approx_kl | 1.3896817 | +| clip_fraction | 0.5 | +| clip_range | 0.2 | +| entropy_loss | -0.516 | +| explained_variance | -1.84 | +| learning_rate | 0.0001 | +| loss | -0.0792 | +| n_updates | 155780 | +| policy_gradient_loss | -0.0687 | +| value_loss | 0.000469 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.04e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 309 | +| iterations | 9527 | +| time_elapsed | 31527 | +| total_timesteps | 9755648 | +| train/ | | +| approx_kl | 2.372754 | +| clip_fraction | 0.524 | +| clip_range | 0.2 | +| entropy_loss | -0.489 | +| explained_variance | -1.19 | +| learning_rate | 0.0001 | +| loss | -0.0377 | +| n_updates | 155790 | +| policy_gradient_loss | -0.073 | +| value_loss | 0.000271 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.06e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 309 | +| iterations | 9528 | +| time_elapsed | 31531 | +| total_timesteps | 9756672 | +| train/ | | +| approx_kl | 1.4566456 | +| clip_fraction | 0.544 | +| clip_range | 0.2 | +| entropy_loss | -0.567 | +| explained_variance | -1.92 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 155800 | +| policy_gradient_loss | -0.0699 | +| value_loss | 0.000196 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.06e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 309 | +| iterations | 9529 | +| time_elapsed | 31534 | +| total_timesteps | 9757696 | +| train/ | | +| approx_kl | 1.6603904 | +| clip_fraction | 0.495 | +| clip_range | 0.2 | +| entropy_loss | -0.511 | +| explained_variance | -2.24 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 155810 | +| policy_gradient_loss | -0.0717 | +| value_loss | 0.000256 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.07e+03 | +| ep_rew_mean | 0.304 | +| time/ | | +| fps | 309 | +| iterations | 9530 | +| time_elapsed | 31537 | +| total_timesteps | 9758720 | +| train/ | | +| approx_kl | 1.081901 | +| clip_fraction | 0.534 | +| clip_range | 0.2 | +| entropy_loss | -0.61 | +| explained_variance | -1.1 | +| learning_rate | 0.0001 | +| loss | -0.116 | +| n_updates | 155820 | +| policy_gradient_loss | -0.0813 | +| value_loss | 0.000158 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.07e+03 | +| ep_rew_mean | 0.304 | +| time/ | | +| fps | 309 | +| iterations | 9531 | +| time_elapsed | 31540 | +| total_timesteps | 9759744 | +| train/ | | +| approx_kl | 5.2496514 | +| clip_fraction | 0.492 | +| clip_range | 0.2 | +| entropy_loss | -0.453 | +| explained_variance | -1.24 | +| learning_rate | 0.0001 | +| loss | -0.0832 | +| n_updates | 155830 | +| policy_gradient_loss | -0.0657 | +| value_loss | 0.000267 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.07e+03 | +| ep_rew_mean | 0.304 | +| time/ | | +| fps | 309 | +| iterations | 9532 | +| time_elapsed | 31544 | +| total_timesteps | 9760768 | +| train/ | | +| approx_kl | 1.8601253 | +| clip_fraction | 0.532 | +| clip_range | 0.2 | +| entropy_loss | -0.476 | +| explained_variance | -2.44 | +| learning_rate | 0.0001 | +| loss | -0.0962 | +| n_updates | 155840 | +| policy_gradient_loss | -0.0748 | +| value_loss | 0.000357 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.09e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 309 | +| iterations | 9533 | +| time_elapsed | 31547 | +| total_timesteps | 9761792 | +| train/ | | +| approx_kl | 1.6350229 | +| clip_fraction | 0.505 | +| clip_range | 0.2 | +| entropy_loss | -0.439 | +| explained_variance | -1.24 | +| learning_rate | 0.0001 | +| loss | -0.0889 | +| n_updates | 155850 | +| policy_gradient_loss | -0.0706 | +| value_loss | 0.000522 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.09e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 309 | +| iterations | 9534 | +| time_elapsed | 31551 | +| total_timesteps | 9762816 | +| train/ | | +| approx_kl | 1.4049377 | +| clip_fraction | 0.528 | +| clip_range | 0.2 | +| entropy_loss | -0.613 | +| explained_variance | -2.12 | +| learning_rate | 0.0001 | +| loss | -0.0796 | +| n_updates | 155860 | +| policy_gradient_loss | -0.0739 | +| value_loss | 0.000229 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.1e+03 | +| ep_rew_mean | 0.304 | +| time/ | | +| fps | 309 | +| iterations | 9535 | +| time_elapsed | 31554 | +| total_timesteps | 9763840 | +| train/ | | +| approx_kl | 1.5957063 | +| clip_fraction | 0.548 | +| clip_range | 0.2 | +| entropy_loss | -0.527 | +| explained_variance | -2.33 | +| learning_rate | 0.0001 | +| loss | -0.107 | +| n_updates | 155870 | +| policy_gradient_loss | -0.0822 | +| value_loss | 0.000134 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.1e+03 | +| ep_rew_mean | 0.304 | +| time/ | | +| fps | 309 | +| iterations | 9536 | +| time_elapsed | 31558 | +| total_timesteps | 9764864 | +| train/ | | +| approx_kl | 1.7254425 | +| clip_fraction | 0.537 | +| clip_range | 0.2 | +| entropy_loss | -0.529 | +| explained_variance | -0.328 | +| learning_rate | 0.0001 | +| loss | -0.0938 | +| n_updates | 155880 | +| policy_gradient_loss | -0.0738 | +| value_loss | 0.000305 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.1e+03 | +| ep_rew_mean | 0.302 | +| time/ | | +| fps | 309 | +| iterations | 9537 | +| time_elapsed | 31561 | +| total_timesteps | 9765888 | +| train/ | | +| approx_kl | 2.4171536 | +| clip_fraction | 0.535 | +| clip_range | 0.2 | +| entropy_loss | -0.499 | +| explained_variance | -4.36 | +| learning_rate | 0.0001 | +| loss | -0.112 | +| n_updates | 155890 | +| policy_gradient_loss | -0.0781 | +| value_loss | 0.000552 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.1e+03 | +| ep_rew_mean | 0.302 | +| time/ | | +| fps | 309 | +| iterations | 9538 | +| time_elapsed | 31565 | +| total_timesteps | 9766912 | +| train/ | | +| approx_kl | 2.9011753 | +| clip_fraction | 0.503 | +| clip_range | 0.2 | +| entropy_loss | -0.442 | +| explained_variance | -2.04 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 155900 | +| policy_gradient_loss | -0.0701 | +| value_loss | 0.000446 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.11e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 309 | +| iterations | 9539 | +| time_elapsed | 31568 | +| total_timesteps | 9767936 | +| train/ | | +| approx_kl | 1.417275 | +| clip_fraction | 0.539 | +| clip_range | 0.2 | +| entropy_loss | -0.605 | +| explained_variance | -0.594 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 155910 | +| policy_gradient_loss | -0.075 | +| value_loss | 0.000486 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.11e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 309 | +| iterations | 9540 | +| time_elapsed | 31572 | +| total_timesteps | 9768960 | +| train/ | | +| approx_kl | 1.793093 | +| clip_fraction | 0.53 | +| clip_range | 0.2 | +| entropy_loss | -0.485 | +| explained_variance | -0.832 | +| learning_rate | 0.0001 | +| loss | -0.0742 | +| n_updates | 155920 | +| policy_gradient_loss | -0.0769 | +| value_loss | 0.00043 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.11e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 309 | +| iterations | 9541 | +| time_elapsed | 31575 | +| total_timesteps | 9769984 | +| train/ | | +| approx_kl | 1.965029 | +| clip_fraction | 0.5 | +| clip_range | 0.2 | +| entropy_loss | -0.448 | +| explained_variance | -2.66 | +| learning_rate | 0.0001 | +| loss | -0.111 | +| n_updates | 155930 | +| policy_gradient_loss | -0.0693 | +| value_loss | 0.000314 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.13e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 309 | +| iterations | 9542 | +| time_elapsed | 31578 | +| total_timesteps | 9771008 | +| train/ | | +| approx_kl | 2.0016477 | +| clip_fraction | 0.502 | +| clip_range | 0.2 | +| entropy_loss | -0.421 | +| explained_variance | -3.9 | +| learning_rate | 0.0001 | +| loss | -0.0986 | +| n_updates | 155940 | +| policy_gradient_loss | -0.0733 | +| value_loss | 0.000167 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.13e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 309 | +| iterations | 9543 | +| time_elapsed | 31582 | +| total_timesteps | 9772032 | +| train/ | | +| approx_kl | 1.713454 | +| clip_fraction | 0.505 | +| clip_range | 0.2 | +| entropy_loss | -0.473 | +| explained_variance | -0.759 | +| learning_rate | 0.0001 | +| loss | -0.0997 | +| n_updates | 155950 | +| policy_gradient_loss | -0.0624 | +| value_loss | 0.000229 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.13e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 309 | +| iterations | 9544 | +| time_elapsed | 31585 | +| total_timesteps | 9773056 | +| train/ | | +| approx_kl | 1.8798542 | +| clip_fraction | 0.496 | +| clip_range | 0.2 | +| entropy_loss | -0.416 | +| explained_variance | -0.755 | +| learning_rate | 0.0001 | +| loss | -0.0826 | +| n_updates | 155960 | +| policy_gradient_loss | -0.0684 | +| value_loss | 0.000556 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.12e+03 | +| ep_rew_mean | 0.315 | +| time/ | | +| fps | 309 | +| iterations | 9545 | +| time_elapsed | 31588 | +| total_timesteps | 9774080 | +| train/ | | +| approx_kl | 1.6057134 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.417 | +| explained_variance | -1.64 | +| learning_rate | 0.0001 | +| loss | -0.027 | +| n_updates | 155970 | +| policy_gradient_loss | -0.0711 | +| value_loss | 0.000419 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.12e+03 | +| ep_rew_mean | 0.315 | +| time/ | | +| fps | 309 | +| iterations | 9546 | +| time_elapsed | 31591 | +| total_timesteps | 9775104 | +| train/ | | +| approx_kl | 3.269879 | +| clip_fraction | 0.529 | +| clip_range | 0.2 | +| entropy_loss | -0.46 | +| explained_variance | -0.239 | +| learning_rate | 0.0001 | +| loss | -0.114 | +| n_updates | 155980 | +| policy_gradient_loss | -0.0698 | +| value_loss | 0.000721 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.13e+03 | +| ep_rew_mean | 0.315 | +| time/ | | +| fps | 309 | +| iterations | 9547 | +| time_elapsed | 31594 | +| total_timesteps | 9776128 | +| train/ | | +| approx_kl | 2.3688521 | +| clip_fraction | 0.515 | +| clip_range | 0.2 | +| entropy_loss | -0.432 | +| explained_variance | -2.9 | +| learning_rate | 0.0001 | +| loss | -0.1 | +| n_updates | 155990 | +| policy_gradient_loss | -0.0741 | +| value_loss | 0.000663 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.13e+03 | +| ep_rew_mean | 0.315 | +| time/ | | +| fps | 309 | +| iterations | 9548 | +| time_elapsed | 31598 | +| total_timesteps | 9777152 | +| train/ | | +| approx_kl | 1.6615155 | +| clip_fraction | 0.509 | +| clip_range | 0.2 | +| entropy_loss | -0.478 | +| explained_variance | -2.02 | +| learning_rate | 0.0001 | +| loss | -0.0881 | +| n_updates | 156000 | +| policy_gradient_loss | -0.0741 | +| value_loss | 0.000289 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.13e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 309 | +| iterations | 9549 | +| time_elapsed | 31601 | +| total_timesteps | 9778176 | +| train/ | | +| approx_kl | 2.3637815 | +| clip_fraction | 0.514 | +| clip_range | 0.2 | +| entropy_loss | -0.426 | +| explained_variance | -0.923 | +| learning_rate | 0.0001 | +| loss | -0.0913 | +| n_updates | 156010 | +| policy_gradient_loss | -0.0653 | +| value_loss | 0.00026 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.13e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 309 | +| iterations | 9550 | +| time_elapsed | 31605 | +| total_timesteps | 9779200 | +| train/ | | +| approx_kl | 1.565016 | +| clip_fraction | 0.497 | +| clip_range | 0.2 | +| entropy_loss | -0.471 | +| explained_variance | -1.24 | +| learning_rate | 0.0001 | +| loss | -0.0812 | +| n_updates | 156020 | +| policy_gradient_loss | -0.0686 | +| value_loss | 0.000257 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.13e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 309 | +| iterations | 9551 | +| time_elapsed | 31608 | +| total_timesteps | 9780224 | +| train/ | | +| approx_kl | 11.107352 | +| clip_fraction | 0.539 | +| clip_range | 0.2 | +| entropy_loss | -0.552 | +| explained_variance | -0.704 | +| learning_rate | 0.0001 | +| loss | -0.0935 | +| n_updates | 156030 | +| policy_gradient_loss | -0.0776 | +| value_loss | 0.000365 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.15e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 309 | +| iterations | 9552 | +| time_elapsed | 31612 | +| total_timesteps | 9781248 | +| train/ | | +| approx_kl | 1.8621376 | +| clip_fraction | 0.544 | +| clip_range | 0.2 | +| entropy_loss | -0.549 | +| explained_variance | -4.12 | +| learning_rate | 0.0001 | +| loss | -0.0853 | +| n_updates | 156040 | +| policy_gradient_loss | -0.0791 | +| value_loss | 0.0003 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.15e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 309 | +| iterations | 9553 | +| time_elapsed | 31615 | +| total_timesteps | 9782272 | +| train/ | | +| approx_kl | 1.6922382 | +| clip_fraction | 0.5 | +| clip_range | 0.2 | +| entropy_loss | -0.446 | +| explained_variance | -0.337 | +| learning_rate | 0.0001 | +| loss | -0.0956 | +| n_updates | 156050 | +| policy_gradient_loss | -0.0579 | +| value_loss | 0.000325 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.15e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 309 | +| iterations | 9554 | +| time_elapsed | 31619 | +| total_timesteps | 9783296 | +| train/ | | +| approx_kl | 2.2476938 | +| clip_fraction | 0.488 | +| clip_range | 0.2 | +| entropy_loss | -0.439 | +| explained_variance | -1.05 | +| learning_rate | 0.0001 | +| loss | -0.113 | +| n_updates | 156060 | +| policy_gradient_loss | -0.0758 | +| value_loss | 0.000606 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.15e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 309 | +| iterations | 9555 | +| time_elapsed | 31623 | +| total_timesteps | 9784320 | +| train/ | | +| approx_kl | 1.7644106 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.419 | +| explained_variance | -1.96 | +| learning_rate | 0.0001 | +| loss | -0.0913 | +| n_updates | 156070 | +| policy_gradient_loss | -0.0638 | +| value_loss | 0.000634 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.15e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 309 | +| iterations | 9556 | +| time_elapsed | 31626 | +| total_timesteps | 9785344 | +| train/ | | +| approx_kl | 8.241612 | +| clip_fraction | 0.552 | +| clip_range | 0.2 | +| entropy_loss | -0.56 | +| explained_variance | -0.746 | +| learning_rate | 0.0001 | +| loss | -0.127 | +| n_updates | 156080 | +| policy_gradient_loss | -0.0827 | +| value_loss | 0.00032 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.17e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 309 | +| iterations | 9557 | +| time_elapsed | 31630 | +| total_timesteps | 9786368 | +| train/ | | +| approx_kl | 1.917017 | +| clip_fraction | 0.523 | +| clip_range | 0.2 | +| entropy_loss | -0.489 | +| explained_variance | -6.71 | +| learning_rate | 0.0001 | +| loss | -0.0903 | +| n_updates | 156090 | +| policy_gradient_loss | -0.0783 | +| value_loss | 0.000361 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.17e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 309 | +| iterations | 9558 | +| time_elapsed | 31633 | +| total_timesteps | 9787392 | +| train/ | | +| approx_kl | 2.5855231 | +| clip_fraction | 0.488 | +| clip_range | 0.2 | +| entropy_loss | -0.427 | +| explained_variance | -9.66 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 156100 | +| policy_gradient_loss | -0.0746 | +| value_loss | 9.88e-05 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.17e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 309 | +| iterations | 9559 | +| time_elapsed | 31636 | +| total_timesteps | 9788416 | +| train/ | | +| approx_kl | 1.8512983 | +| clip_fraction | 0.521 | +| clip_range | 0.2 | +| entropy_loss | -0.448 | +| explained_variance | -0.419 | +| learning_rate | 0.0001 | +| loss | -0.0905 | +| n_updates | 156110 | +| policy_gradient_loss | -0.0662 | +| value_loss | 0.000512 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.19e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 309 | +| iterations | 9560 | +| time_elapsed | 31639 | +| total_timesteps | 9789440 | +| train/ | | +| approx_kl | 1.9373556 | +| clip_fraction | 0.51 | +| clip_range | 0.2 | +| entropy_loss | -0.432 | +| explained_variance | -1.85 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 156120 | +| policy_gradient_loss | -0.073 | +| value_loss | 0.000691 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.19e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 309 | +| iterations | 9561 | +| time_elapsed | 31642 | +| total_timesteps | 9790464 | +| train/ | | +| approx_kl | 2.0614593 | +| clip_fraction | 0.511 | +| clip_range | 0.2 | +| entropy_loss | -0.434 | +| explained_variance | -3.93 | +| learning_rate | 0.0001 | +| loss | -0.108 | +| n_updates | 156130 | +| policy_gradient_loss | -0.0816 | +| value_loss | 0.000332 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.19e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 309 | +| iterations | 9562 | +| time_elapsed | 31646 | +| total_timesteps | 9791488 | +| train/ | | +| approx_kl | 1.9299383 | +| clip_fraction | 0.554 | +| clip_range | 0.2 | +| entropy_loss | -0.534 | +| explained_variance | -1.28 | +| learning_rate | 0.0001 | +| loss | -0.0859 | +| n_updates | 156140 | +| policy_gradient_loss | -0.0779 | +| value_loss | 0.000277 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.2e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 309 | +| iterations | 9563 | +| time_elapsed | 31649 | +| total_timesteps | 9792512 | +| train/ | | +| approx_kl | 1.4669144 | +| clip_fraction | 0.512 | +| clip_range | 0.2 | +| entropy_loss | -0.469 | +| explained_variance | -6.38 | +| learning_rate | 0.0001 | +| loss | -0.0996 | +| n_updates | 156150 | +| policy_gradient_loss | -0.075 | +| value_loss | 0.000233 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.2e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 309 | +| iterations | 9564 | +| time_elapsed | 31653 | +| total_timesteps | 9793536 | +| train/ | | +| approx_kl | 1.2445185 | +| clip_fraction | 0.521 | +| clip_range | 0.2 | +| entropy_loss | -0.51 | +| explained_variance | -0.502 | +| learning_rate | 0.0001 | +| loss | -0.0949 | +| n_updates | 156160 | +| policy_gradient_loss | -0.0668 | +| value_loss | 0.00027 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.2e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 309 | +| iterations | 9565 | +| time_elapsed | 31656 | +| total_timesteps | 9794560 | +| train/ | | +| approx_kl | 2.416181 | +| clip_fraction | 0.521 | +| clip_range | 0.2 | +| entropy_loss | -0.462 | +| explained_variance | -2.71 | +| learning_rate | 0.0001 | +| loss | -0.0848 | +| n_updates | 156170 | +| policy_gradient_loss | -0.0712 | +| value_loss | 0.000267 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.21e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 309 | +| iterations | 9566 | +| time_elapsed | 31659 | +| total_timesteps | 9795584 | +| train/ | | +| approx_kl | 2.0615845 | +| clip_fraction | 0.523 | +| clip_range | 0.2 | +| entropy_loss | -0.483 | +| explained_variance | -2.51 | +| learning_rate | 0.0001 | +| loss | -0.0699 | +| n_updates | 156180 | +| policy_gradient_loss | -0.0766 | +| value_loss | 0.000359 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.21e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 309 | +| iterations | 9567 | +| time_elapsed | 31663 | +| total_timesteps | 9796608 | +| train/ | | +| approx_kl | 1.5830529 | +| clip_fraction | 0.471 | +| clip_range | 0.2 | +| entropy_loss | -0.442 | +| explained_variance | -3.71 | +| learning_rate | 0.0001 | +| loss | -0.0772 | +| n_updates | 156190 | +| policy_gradient_loss | -0.0703 | +| value_loss | 0.000204 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.21e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 309 | +| iterations | 9568 | +| time_elapsed | 31666 | +| total_timesteps | 9797632 | +| train/ | | +| approx_kl | 2.0292988 | +| clip_fraction | 0.555 | +| clip_range | 0.2 | +| entropy_loss | -0.495 | +| explained_variance | -0.301 | +| learning_rate | 0.0001 | +| loss | -0.0849 | +| n_updates | 156200 | +| policy_gradient_loss | -0.0691 | +| value_loss | 0.000346 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.22e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 309 | +| iterations | 9569 | +| time_elapsed | 31670 | +| total_timesteps | 9798656 | +| train/ | | +| approx_kl | 2.7017803 | +| clip_fraction | 0.525 | +| clip_range | 0.2 | +| entropy_loss | -0.445 | +| explained_variance | -2.12 | +| learning_rate | 0.0001 | +| loss | -0.111 | +| n_updates | 156210 | +| policy_gradient_loss | -0.0729 | +| value_loss | 0.000497 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.22e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 309 | +| iterations | 9570 | +| time_elapsed | 31673 | +| total_timesteps | 9799680 | +| train/ | | +| approx_kl | 1.3393316 | +| clip_fraction | 0.478 | +| clip_range | 0.2 | +| entropy_loss | -0.471 | +| explained_variance | -5.55 | +| learning_rate | 0.0001 | +| loss | -0.105 | +| n_updates | 156220 | +| policy_gradient_loss | -0.069 | +| value_loss | 0.000421 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.23e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 309 | +| iterations | 9571 | +| time_elapsed | 31677 | +| total_timesteps | 9800704 | +| train/ | | +| approx_kl | 2.3879242 | +| clip_fraction | 0.567 | +| clip_range | 0.2 | +| entropy_loss | -0.58 | +| explained_variance | -1.31 | +| learning_rate | 0.0001 | +| loss | -0.108 | +| n_updates | 156230 | +| policy_gradient_loss | -0.0779 | +| value_loss | 0.000231 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.23e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 309 | +| iterations | 9572 | +| time_elapsed | 31680 | +| total_timesteps | 9801728 | +| train/ | | +| approx_kl | 1.4506533 | +| clip_fraction | 0.515 | +| clip_range | 0.2 | +| entropy_loss | -0.509 | +| explained_variance | -2.4 | +| learning_rate | 0.0001 | +| loss | -0.0952 | +| n_updates | 156240 | +| policy_gradient_loss | -0.0693 | +| value_loss | 0.000195 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.24e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 309 | +| iterations | 9573 | +| time_elapsed | 31684 | +| total_timesteps | 9802752 | +| train/ | | +| approx_kl | 1.691728 | +| clip_fraction | 0.527 | +| clip_range | 0.2 | +| entropy_loss | -0.489 | +| explained_variance | -0.742 | +| learning_rate | 0.0001 | +| loss | -0.0235 | +| n_updates | 156250 | +| policy_gradient_loss | -0.0637 | +| value_loss | 0.000615 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.24e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 309 | +| iterations | 9574 | +| time_elapsed | 31687 | +| total_timesteps | 9803776 | +| train/ | | +| approx_kl | 1.9351985 | +| clip_fraction | 0.496 | +| clip_range | 0.2 | +| entropy_loss | -0.486 | +| explained_variance | -2.33 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 156260 | +| policy_gradient_loss | -0.0769 | +| value_loss | 0.000543 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.26e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 309 | +| iterations | 9575 | +| time_elapsed | 31691 | +| total_timesteps | 9804800 | +| train/ | | +| approx_kl | 2.077188 | +| clip_fraction | 0.513 | +| clip_range | 0.2 | +| entropy_loss | -0.469 | +| explained_variance | -2.88 | +| learning_rate | 0.0001 | +| loss | -0.122 | +| n_updates | 156270 | +| policy_gradient_loss | -0.0838 | +| value_loss | 0.000417 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.26e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 309 | +| iterations | 9576 | +| time_elapsed | 31694 | +| total_timesteps | 9805824 | +| train/ | | +| approx_kl | 2.3695183 | +| clip_fraction | 0.522 | +| clip_range | 0.2 | +| entropy_loss | -0.543 | +| explained_variance | -3.98 | +| learning_rate | 0.0001 | +| loss | -0.0889 | +| n_updates | 156280 | +| policy_gradient_loss | -0.0734 | +| value_loss | 0.000335 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.26e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 309 | +| iterations | 9577 | +| time_elapsed | 31697 | +| total_timesteps | 9806848 | +| train/ | | +| approx_kl | 1.9455011 | +| clip_fraction | 0.533 | +| clip_range | 0.2 | +| entropy_loss | -0.476 | +| explained_variance | -3.03 | +| learning_rate | 0.0001 | +| loss | -0.0844 | +| n_updates | 156290 | +| policy_gradient_loss | -0.0758 | +| value_loss | 0.000513 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.26e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 309 | +| iterations | 9578 | +| time_elapsed | 31701 | +| total_timesteps | 9807872 | +| train/ | | +| approx_kl | 1.6338608 | +| clip_fraction | 0.534 | +| clip_range | 0.2 | +| entropy_loss | -0.455 | +| explained_variance | -1.26 | +| learning_rate | 0.0001 | +| loss | -0.108 | +| n_updates | 156300 | +| policy_gradient_loss | -0.0787 | +| value_loss | 0.000538 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.26e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 309 | +| iterations | 9579 | +| time_elapsed | 31704 | +| total_timesteps | 9808896 | +| train/ | | +| approx_kl | 1.5133343 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.428 | +| explained_variance | -3.49 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 156310 | +| policy_gradient_loss | -0.0639 | +| value_loss | 0.000323 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.28e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 309 | +| iterations | 9580 | +| time_elapsed | 31707 | +| total_timesteps | 9809920 | +| train/ | | +| approx_kl | 1.6880801 | +| clip_fraction | 0.526 | +| clip_range | 0.2 | +| entropy_loss | -0.479 | +| explained_variance | -3.57 | +| learning_rate | 0.0001 | +| loss | -0.082 | +| n_updates | 156320 | +| policy_gradient_loss | -0.0806 | +| value_loss | 0.000223 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.28e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 309 | +| iterations | 9581 | +| time_elapsed | 31710 | +| total_timesteps | 9810944 | +| train/ | | +| approx_kl | 1.4640553 | +| clip_fraction | 0.492 | +| clip_range | 0.2 | +| entropy_loss | -0.534 | +| explained_variance | -1.71 | +| learning_rate | 0.0001 | +| loss | -0.0916 | +| n_updates | 156330 | +| policy_gradient_loss | -0.0732 | +| value_loss | 0.00015 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.28e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 309 | +| iterations | 9582 | +| time_elapsed | 31714 | +| total_timesteps | 9811968 | +| train/ | | +| approx_kl | 1.9404501 | +| clip_fraction | 0.563 | +| clip_range | 0.2 | +| entropy_loss | -0.581 | +| explained_variance | -0.589 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 156340 | +| policy_gradient_loss | -0.0744 | +| value_loss | 0.00034 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.28e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 309 | +| iterations | 9583 | +| time_elapsed | 31717 | +| total_timesteps | 9812992 | +| train/ | | +| approx_kl | 2.6950436 | +| clip_fraction | 0.482 | +| clip_range | 0.2 | +| entropy_loss | -0.418 | +| explained_variance | -1.16 | +| learning_rate | 0.0001 | +| loss | -0.0883 | +| n_updates | 156350 | +| policy_gradient_loss | -0.0732 | +| value_loss | 0.000853 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.28e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 309 | +| iterations | 9584 | +| time_elapsed | 31720 | +| total_timesteps | 9814016 | +| train/ | | +| approx_kl | 2.0000136 | +| clip_fraction | 0.558 | +| clip_range | 0.2 | +| entropy_loss | -0.518 | +| explained_variance | -1.17 | +| learning_rate | 0.0001 | +| loss | -0.0868 | +| n_updates | 156360 | +| policy_gradient_loss | -0.0786 | +| value_loss | 0.000517 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.28e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 309 | +| iterations | 9585 | +| time_elapsed | 31723 | +| total_timesteps | 9815040 | +| train/ | | +| approx_kl | 2.5447614 | +| clip_fraction | 0.502 | +| clip_range | 0.2 | +| entropy_loss | -0.42 | +| explained_variance | -1.22 | +| learning_rate | 0.0001 | +| loss | -0.0721 | +| n_updates | 156370 | +| policy_gradient_loss | -0.075 | +| value_loss | 0.000648 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.28e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 309 | +| iterations | 9586 | +| time_elapsed | 31727 | +| total_timesteps | 9816064 | +| train/ | | +| approx_kl | 2.0995584 | +| clip_fraction | 0.525 | +| clip_range | 0.2 | +| entropy_loss | -0.434 | +| explained_variance | -2.5 | +| learning_rate | 0.0001 | +| loss | -0.0567 | +| n_updates | 156380 | +| policy_gradient_loss | -0.0727 | +| value_loss | 0.00054 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.28e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 309 | +| iterations | 9587 | +| time_elapsed | 31730 | +| total_timesteps | 9817088 | +| train/ | | +| approx_kl | 1.8275607 | +| clip_fraction | 0.519 | +| clip_range | 0.2 | +| entropy_loss | -0.449 | +| explained_variance | -2.36 | +| learning_rate | 0.0001 | +| loss | -0.088 | +| n_updates | 156390 | +| policy_gradient_loss | -0.071 | +| value_loss | 0.000229 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.31e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 309 | +| iterations | 9588 | +| time_elapsed | 31734 | +| total_timesteps | 9818112 | +| train/ | | +| approx_kl | 17.051086 | +| clip_fraction | 0.542 | +| clip_range | 0.2 | +| entropy_loss | -0.51 | +| explained_variance | -1.07 | +| learning_rate | 0.0001 | +| loss | -0.0825 | +| n_updates | 156400 | +| policy_gradient_loss | -0.0736 | +| value_loss | 0.000347 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.31e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 309 | +| iterations | 9589 | +| time_elapsed | 31737 | +| total_timesteps | 9819136 | +| train/ | | +| approx_kl | 1.921772 | +| clip_fraction | 0.542 | +| clip_range | 0.2 | +| entropy_loss | -0.555 | +| explained_variance | -1.44 | +| learning_rate | 0.0001 | +| loss | -0.0881 | +| n_updates | 156410 | +| policy_gradient_loss | -0.0738 | +| value_loss | 0.000149 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.31e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 309 | +| iterations | 9590 | +| time_elapsed | 31740 | +| total_timesteps | 9820160 | +| train/ | | +| approx_kl | 1.870736 | +| clip_fraction | 0.523 | +| clip_range | 0.2 | +| entropy_loss | -0.48 | +| explained_variance | -0.517 | +| learning_rate | 0.0001 | +| loss | -0.0751 | +| n_updates | 156420 | +| policy_gradient_loss | -0.0643 | +| value_loss | 0.000251 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.31e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 309 | +| iterations | 9591 | +| time_elapsed | 31744 | +| total_timesteps | 9821184 | +| train/ | | +| approx_kl | 1.9275675 | +| clip_fraction | 0.513 | +| clip_range | 0.2 | +| entropy_loss | -0.426 | +| explained_variance | -1.37 | +| learning_rate | 0.0001 | +| loss | -0.107 | +| n_updates | 156430 | +| policy_gradient_loss | -0.0663 | +| value_loss | 0.000498 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.32e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 309 | +| iterations | 9592 | +| time_elapsed | 31747 | +| total_timesteps | 9822208 | +| train/ | | +| approx_kl | 2.1969008 | +| clip_fraction | 0.515 | +| clip_range | 0.2 | +| entropy_loss | -0.424 | +| explained_variance | -3.18 | +| learning_rate | 0.0001 | +| loss | -0.125 | +| n_updates | 156440 | +| policy_gradient_loss | -0.0827 | +| value_loss | 0.000301 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.32e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 309 | +| iterations | 9593 | +| time_elapsed | 31750 | +| total_timesteps | 9823232 | +| train/ | | +| approx_kl | 1.5077379 | +| clip_fraction | 0.486 | +| clip_range | 0.2 | +| entropy_loss | -0.43 | +| explained_variance | -0.902 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 156450 | +| policy_gradient_loss | -0.0735 | +| value_loss | 0.000397 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.34e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 309 | +| iterations | 9594 | +| time_elapsed | 31754 | +| total_timesteps | 9824256 | +| train/ | | +| approx_kl | 1.4710014 | +| clip_fraction | 0.535 | +| clip_range | 0.2 | +| entropy_loss | -0.637 | +| explained_variance | -5.14 | +| learning_rate | 0.0001 | +| loss | -0.122 | +| n_updates | 156460 | +| policy_gradient_loss | -0.0749 | +| value_loss | 0.00019 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.34e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 309 | +| iterations | 9595 | +| time_elapsed | 31757 | +| total_timesteps | 9825280 | +| train/ | | +| approx_kl | 1.3946944 | +| clip_fraction | 0.482 | +| clip_range | 0.2 | +| entropy_loss | -0.428 | +| explained_variance | -1.57 | +| learning_rate | 0.0001 | +| loss | -0.113 | +| n_updates | 156470 | +| policy_gradient_loss | -0.0677 | +| value_loss | 0.000238 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.34e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 309 | +| iterations | 9596 | +| time_elapsed | 31760 | +| total_timesteps | 9826304 | +| train/ | | +| approx_kl | 1.7568256 | +| clip_fraction | 0.497 | +| clip_range | 0.2 | +| entropy_loss | -0.479 | +| explained_variance | -4.72 | +| learning_rate | 0.0001 | +| loss | -0.107 | +| n_updates | 156480 | +| policy_gradient_loss | -0.0746 | +| value_loss | 0.000172 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.34e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 309 | +| iterations | 9597 | +| time_elapsed | 31763 | +| total_timesteps | 9827328 | +| train/ | | +| approx_kl | 2.3509252 | +| clip_fraction | 0.521 | +| clip_range | 0.2 | +| entropy_loss | -0.463 | +| explained_variance | -0.419 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 156490 | +| policy_gradient_loss | -0.0645 | +| value_loss | 0.000312 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.34e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 309 | +| iterations | 9598 | +| time_elapsed | 31766 | +| total_timesteps | 9828352 | +| train/ | | +| approx_kl | 2.0363903 | +| clip_fraction | 0.526 | +| clip_range | 0.2 | +| entropy_loss | -0.464 | +| explained_variance | -2.48 | +| learning_rate | 0.0001 | +| loss | -0.0984 | +| n_updates | 156500 | +| policy_gradient_loss | -0.079 | +| value_loss | 0.000532 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.35e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 309 | +| iterations | 9599 | +| time_elapsed | 31770 | +| total_timesteps | 9829376 | +| train/ | | +| approx_kl | 1.8511971 | +| clip_fraction | 0.514 | +| clip_range | 0.2 | +| entropy_loss | -0.449 | +| explained_variance | -2.78 | +| learning_rate | 0.0001 | +| loss | -0.0727 | +| n_updates | 156510 | +| policy_gradient_loss | -0.0747 | +| value_loss | 0.000558 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.35e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 309 | +| iterations | 9600 | +| time_elapsed | 31773 | +| total_timesteps | 9830400 | +| train/ | | +| approx_kl | 1.8088175 | +| clip_fraction | 0.509 | +| clip_range | 0.2 | +| entropy_loss | -0.449 | +| explained_variance | -1.66 | +| learning_rate | 0.0001 | +| loss | -0.0781 | +| n_updates | 156520 | +| policy_gradient_loss | -0.0721 | +| value_loss | 0.000495 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.35e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 309 | +| iterations | 9601 | +| time_elapsed | 31776 | +| total_timesteps | 9831424 | +| train/ | | +| approx_kl | 2.0726185 | +| clip_fraction | 0.527 | +| clip_range | 0.2 | +| entropy_loss | -0.44 | +| explained_variance | -0.981 | +| learning_rate | 0.0001 | +| loss | -0.11 | +| n_updates | 156530 | +| policy_gradient_loss | -0.0795 | +| value_loss | 0.000665 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.35e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 309 | +| iterations | 9602 | +| time_elapsed | 31780 | +| total_timesteps | 9832448 | +| train/ | | +| approx_kl | 1.4167922 | +| clip_fraction | 0.502 | +| clip_range | 0.2 | +| entropy_loss | -0.473 | +| explained_variance | -3.54 | +| learning_rate | 0.0001 | +| loss | -0.0949 | +| n_updates | 156540 | +| policy_gradient_loss | -0.0765 | +| value_loss | 0.000408 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.35e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 309 | +| iterations | 9603 | +| time_elapsed | 31783 | +| total_timesteps | 9833472 | +| train/ | | +| approx_kl | 1.6862828 | +| clip_fraction | 0.516 | +| clip_range | 0.2 | +| entropy_loss | -0.434 | +| explained_variance | -2.58 | +| learning_rate | 0.0001 | +| loss | -0.0719 | +| n_updates | 156550 | +| policy_gradient_loss | -0.071 | +| value_loss | 0.000192 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.36e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 309 | +| iterations | 9604 | +| time_elapsed | 31786 | +| total_timesteps | 9834496 | +| train/ | | +| approx_kl | 8.433395 | +| clip_fraction | 0.557 | +| clip_range | 0.2 | +| entropy_loss | -0.525 | +| explained_variance | -0.912 | +| learning_rate | 0.0001 | +| loss | -0.07 | +| n_updates | 156560 | +| policy_gradient_loss | -0.0601 | +| value_loss | 0.000281 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.36e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 309 | +| iterations | 9605 | +| time_elapsed | 31790 | +| total_timesteps | 9835520 | +| train/ | | +| approx_kl | 1.8392189 | +| clip_fraction | 0.49 | +| clip_range | 0.2 | +| entropy_loss | -0.409 | +| explained_variance | -1.93 | +| learning_rate | 0.0001 | +| loss | -0.111 | +| n_updates | 156570 | +| policy_gradient_loss | -0.0742 | +| value_loss | 0.000251 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.36e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 309 | +| iterations | 9606 | +| time_elapsed | 31793 | +| total_timesteps | 9836544 | +| train/ | | +| approx_kl | 2.3732328 | +| clip_fraction | 0.549 | +| clip_range | 0.2 | +| entropy_loss | -0.479 | +| explained_variance | -0.838 | +| learning_rate | 0.0001 | +| loss | -0.0672 | +| n_updates | 156580 | +| policy_gradient_loss | -0.0728 | +| value_loss | 0.000507 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.36e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 309 | +| iterations | 9607 | +| time_elapsed | 31796 | +| total_timesteps | 9837568 | +| train/ | | +| approx_kl | 2.1295042 | +| clip_fraction | 0.492 | +| clip_range | 0.2 | +| entropy_loss | -0.402 | +| explained_variance | -2.41 | +| learning_rate | 0.0001 | +| loss | -0.0545 | +| n_updates | 156590 | +| policy_gradient_loss | -0.0713 | +| value_loss | 0.000337 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.38e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 309 | +| iterations | 9608 | +| time_elapsed | 31800 | +| total_timesteps | 9838592 | +| train/ | | +| approx_kl | 2.196708 | +| clip_fraction | 0.531 | +| clip_range | 0.2 | +| entropy_loss | -0.466 | +| explained_variance | -0.92 | +| learning_rate | 0.0001 | +| loss | -0.0929 | +| n_updates | 156600 | +| policy_gradient_loss | -0.0781 | +| value_loss | 0.000455 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.38e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 309 | +| iterations | 9609 | +| time_elapsed | 31803 | +| total_timesteps | 9839616 | +| train/ | | +| approx_kl | 2.0682397 | +| clip_fraction | 0.518 | +| clip_range | 0.2 | +| entropy_loss | -0.443 | +| explained_variance | -5.96 | +| learning_rate | 0.0001 | +| loss | -0.0909 | +| n_updates | 156610 | +| policy_gradient_loss | -0.0789 | +| value_loss | 0.000274 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.37e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 309 | +| iterations | 9610 | +| time_elapsed | 31807 | +| total_timesteps | 9840640 | +| train/ | | +| approx_kl | 1.9538871 | +| clip_fraction | 0.497 | +| clip_range | 0.2 | +| entropy_loss | -0.401 | +| explained_variance | -0.818 | +| learning_rate | 0.0001 | +| loss | -0.0837 | +| n_updates | 156620 | +| policy_gradient_loss | -0.0665 | +| value_loss | 0.000513 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.37e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 309 | +| iterations | 9611 | +| time_elapsed | 31810 | +| total_timesteps | 9841664 | +| train/ | | +| approx_kl | 1.6910038 | +| clip_fraction | 0.526 | +| clip_range | 0.2 | +| entropy_loss | -0.534 | +| explained_variance | -1.21 | +| learning_rate | 0.0001 | +| loss | -0.106 | +| n_updates | 156630 | +| policy_gradient_loss | -0.0646 | +| value_loss | 0.000498 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.37e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 309 | +| iterations | 9612 | +| time_elapsed | 31813 | +| total_timesteps | 9842688 | +| train/ | | +| approx_kl | 1.8812149 | +| clip_fraction | 0.491 | +| clip_range | 0.2 | +| entropy_loss | -0.386 | +| explained_variance | -1.6 | +| learning_rate | 0.0001 | +| loss | -0.0789 | +| n_updates | 156640 | +| policy_gradient_loss | -0.0741 | +| value_loss | 0.000604 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.37e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 309 | +| iterations | 9613 | +| time_elapsed | 31816 | +| total_timesteps | 9843712 | +| train/ | | +| approx_kl | 1.8755739 | +| clip_fraction | 0.491 | +| clip_range | 0.2 | +| entropy_loss | -0.407 | +| explained_variance | -1.13 | +| learning_rate | 0.0001 | +| loss | -0.0891 | +| n_updates | 156650 | +| policy_gradient_loss | -0.0701 | +| value_loss | 0.000549 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.37e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 309 | +| iterations | 9614 | +| time_elapsed | 31820 | +| total_timesteps | 9844736 | +| train/ | | +| approx_kl | 2.4244947 | +| clip_fraction | 0.485 | +| clip_range | 0.2 | +| entropy_loss | -0.419 | +| explained_variance | -4.99 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 156660 | +| policy_gradient_loss | -0.0781 | +| value_loss | 0.00035 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.37e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 309 | +| iterations | 9615 | +| time_elapsed | 31823 | +| total_timesteps | 9845760 | +| train/ | | +| approx_kl | 2.0784235 | +| clip_fraction | 0.512 | +| clip_range | 0.2 | +| entropy_loss | -0.43 | +| explained_variance | -0.57 | +| learning_rate | 0.0001 | +| loss | -0.0898 | +| n_updates | 156670 | +| policy_gradient_loss | -0.0705 | +| value_loss | 0.00024 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.37e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 309 | +| iterations | 9616 | +| time_elapsed | 31826 | +| total_timesteps | 9846784 | +| train/ | | +| approx_kl | 1.8489919 | +| clip_fraction | 0.504 | +| clip_range | 0.2 | +| entropy_loss | -0.475 | +| explained_variance | -1.62 | +| learning_rate | 0.0001 | +| loss | -0.0992 | +| n_updates | 156680 | +| policy_gradient_loss | -0.065 | +| value_loss | 0.000688 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.36e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 309 | +| iterations | 9617 | +| time_elapsed | 31829 | +| total_timesteps | 9847808 | +| train/ | | +| approx_kl | 1.9663852 | +| clip_fraction | 0.542 | +| clip_range | 0.2 | +| entropy_loss | -0.559 | +| explained_variance | -5.34 | +| learning_rate | 0.0001 | +| loss | -0.114 | +| n_updates | 156690 | +| policy_gradient_loss | -0.0812 | +| value_loss | 0.000381 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.36e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 309 | +| iterations | 9618 | +| time_elapsed | 31832 | +| total_timesteps | 9848832 | +| train/ | | +| approx_kl | 1.6913157 | +| clip_fraction | 0.499 | +| clip_range | 0.2 | +| entropy_loss | -0.434 | +| explained_variance | -1.02 | +| learning_rate | 0.0001 | +| loss | -0.094 | +| n_updates | 156700 | +| policy_gradient_loss | -0.0683 | +| value_loss | 0.000288 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.36e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 309 | +| iterations | 9619 | +| time_elapsed | 31836 | +| total_timesteps | 9849856 | +| train/ | | +| approx_kl | 1.5879383 | +| clip_fraction | 0.508 | +| clip_range | 0.2 | +| entropy_loss | -0.453 | +| explained_variance | -1.37 | +| learning_rate | 0.0001 | +| loss | -0.0846 | +| n_updates | 156710 | +| policy_gradient_loss | -0.0792 | +| value_loss | 0.000428 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.37e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 309 | +| iterations | 9620 | +| time_elapsed | 31839 | +| total_timesteps | 9850880 | +| train/ | | +| approx_kl | 1.6408865 | +| clip_fraction | 0.513 | +| clip_range | 0.2 | +| entropy_loss | -0.454 | +| explained_variance | -8.78 | +| learning_rate | 0.0001 | +| loss | -0.107 | +| n_updates | 156720 | +| policy_gradient_loss | -0.0709 | +| value_loss | 0.00049 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.37e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 309 | +| iterations | 9621 | +| time_elapsed | 31842 | +| total_timesteps | 9851904 | +| train/ | | +| approx_kl | 1.7514416 | +| clip_fraction | 0.509 | +| clip_range | 0.2 | +| entropy_loss | -0.478 | +| explained_variance | -1.05 | +| learning_rate | 0.0001 | +| loss | -0.0851 | +| n_updates | 156730 | +| policy_gradient_loss | -0.0652 | +| value_loss | 0.000348 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.37e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 309 | +| iterations | 9622 | +| time_elapsed | 31846 | +| total_timesteps | 9852928 | +| train/ | | +| approx_kl | 2.3517284 | +| clip_fraction | 0.565 | +| clip_range | 0.2 | +| entropy_loss | -0.562 | +| explained_variance | -1.31 | +| learning_rate | 0.0001 | +| loss | -0.093 | +| n_updates | 156740 | +| policy_gradient_loss | -0.0797 | +| value_loss | 0.000516 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.37e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 309 | +| iterations | 9623 | +| time_elapsed | 31849 | +| total_timesteps | 9853952 | +| train/ | | +| approx_kl | 12.276117 | +| clip_fraction | 0.486 | +| clip_range | 0.2 | +| entropy_loss | -0.486 | +| explained_variance | -2.01 | +| learning_rate | 0.0001 | +| loss | -0.0826 | +| n_updates | 156750 | +| policy_gradient_loss | -0.0707 | +| value_loss | 0.000266 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.37e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 309 | +| iterations | 9624 | +| time_elapsed | 31853 | +| total_timesteps | 9854976 | +| train/ | | +| approx_kl | 3.3395953 | +| clip_fraction | 0.504 | +| clip_range | 0.2 | +| entropy_loss | -0.489 | +| explained_variance | -0.766 | +| learning_rate | 0.0001 | +| loss | -0.0938 | +| n_updates | 156760 | +| policy_gradient_loss | -0.0692 | +| value_loss | 0.00028 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.37e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 309 | +| iterations | 9625 | +| time_elapsed | 31856 | +| total_timesteps | 9856000 | +| train/ | | +| approx_kl | 3.4749923 | +| clip_fraction | 0.499 | +| clip_range | 0.2 | +| entropy_loss | -0.449 | +| explained_variance | -2.18 | +| learning_rate | 0.0001 | +| loss | -0.0848 | +| n_updates | 156770 | +| policy_gradient_loss | -0.0722 | +| value_loss | 0.000552 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.37e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 309 | +| iterations | 9626 | +| time_elapsed | 31859 | +| total_timesteps | 9857024 | +| train/ | | +| approx_kl | 1.8447901 | +| clip_fraction | 0.518 | +| clip_range | 0.2 | +| entropy_loss | -0.448 | +| explained_variance | -3 | +| learning_rate | 0.0001 | +| loss | -0.0802 | +| n_updates | 156780 | +| policy_gradient_loss | -0.0711 | +| value_loss | 0.00049 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.37e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 309 | +| iterations | 9627 | +| time_elapsed | 31863 | +| total_timesteps | 9858048 | +| train/ | | +| approx_kl | 1.8259656 | +| clip_fraction | 0.556 | +| clip_range | 0.2 | +| entropy_loss | -0.529 | +| explained_variance | -0.946 | +| learning_rate | 0.0001 | +| loss | -0.106 | +| n_updates | 156790 | +| policy_gradient_loss | -0.0879 | +| value_loss | 0.000391 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.37e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 309 | +| iterations | 9628 | +| time_elapsed | 31866 | +| total_timesteps | 9859072 | +| train/ | | +| approx_kl | 1.6301514 | +| clip_fraction | 0.512 | +| clip_range | 0.2 | +| entropy_loss | -0.456 | +| explained_variance | -1.81 | +| learning_rate | 0.0001 | +| loss | -0.119 | +| n_updates | 156800 | +| policy_gradient_loss | -0.0662 | +| value_loss | 0.000471 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.36e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 309 | +| iterations | 9629 | +| time_elapsed | 31869 | +| total_timesteps | 9860096 | +| train/ | | +| approx_kl | 2.1698365 | +| clip_fraction | 0.535 | +| clip_range | 0.2 | +| entropy_loss | -0.443 | +| explained_variance | -2.28 | +| learning_rate | 0.0001 | +| loss | -0.0986 | +| n_updates | 156810 | +| policy_gradient_loss | -0.0778 | +| value_loss | 0.000641 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.36e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 309 | +| iterations | 9630 | +| time_elapsed | 31873 | +| total_timesteps | 9861120 | +| train/ | | +| approx_kl | 1.5769877 | +| clip_fraction | 0.514 | +| clip_range | 0.2 | +| entropy_loss | -0.466 | +| explained_variance | -5.52 | +| learning_rate | 0.0001 | +| loss | -0.0834 | +| n_updates | 156820 | +| policy_gradient_loss | -0.071 | +| value_loss | 0.000406 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.36e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 309 | +| iterations | 9631 | +| time_elapsed | 31876 | +| total_timesteps | 9862144 | +| train/ | | +| approx_kl | 2.5873032 | +| clip_fraction | 0.531 | +| clip_range | 0.2 | +| entropy_loss | -0.46 | +| explained_variance | -2.66 | +| learning_rate | 0.0001 | +| loss | -0.0944 | +| n_updates | 156830 | +| policy_gradient_loss | -0.0768 | +| value_loss | 0.000357 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.37e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 309 | +| iterations | 9632 | +| time_elapsed | 31879 | +| total_timesteps | 9863168 | +| train/ | | +| approx_kl | 1.7871082 | +| clip_fraction | 0.526 | +| clip_range | 0.2 | +| entropy_loss | -0.553 | +| explained_variance | -1.2 | +| learning_rate | 0.0001 | +| loss | -0.0941 | +| n_updates | 156840 | +| policy_gradient_loss | -0.0744 | +| value_loss | 0.000303 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.37e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 309 | +| iterations | 9633 | +| time_elapsed | 31883 | +| total_timesteps | 9864192 | +| train/ | | +| approx_kl | 2.2530565 | +| clip_fraction | 0.504 | +| clip_range | 0.2 | +| entropy_loss | -0.471 | +| explained_variance | -2.08 | +| learning_rate | 0.0001 | +| loss | -0.096 | +| n_updates | 156850 | +| policy_gradient_loss | -0.0729 | +| value_loss | 0.000346 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.37e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 309 | +| iterations | 9634 | +| time_elapsed | 31886 | +| total_timesteps | 9865216 | +| train/ | | +| approx_kl | 2.1426647 | +| clip_fraction | 0.501 | +| clip_range | 0.2 | +| entropy_loss | -0.394 | +| explained_variance | -0.941 | +| learning_rate | 0.0001 | +| loss | -0.0939 | +| n_updates | 156860 | +| policy_gradient_loss | -0.0754 | +| value_loss | 0.00052 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.38e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 309 | +| iterations | 9635 | +| time_elapsed | 31889 | +| total_timesteps | 9866240 | +| train/ | | +| approx_kl | 2.1064582 | +| clip_fraction | 0.503 | +| clip_range | 0.2 | +| entropy_loss | -0.373 | +| explained_variance | -2.26 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 156870 | +| policy_gradient_loss | -0.0739 | +| value_loss | 0.000668 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.38e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 309 | +| iterations | 9636 | +| time_elapsed | 31893 | +| total_timesteps | 9867264 | +| train/ | | +| approx_kl | 1.9290035 | +| clip_fraction | 0.515 | +| clip_range | 0.2 | +| entropy_loss | -0.46 | +| explained_variance | -5.93 | +| learning_rate | 0.0001 | +| loss | -0.0971 | +| n_updates | 156880 | +| policy_gradient_loss | -0.0714 | +| value_loss | 0.000369 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.38e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 309 | +| iterations | 9637 | +| time_elapsed | 31896 | +| total_timesteps | 9868288 | +| train/ | | +| approx_kl | 2.8426418 | +| clip_fraction | 0.492 | +| clip_range | 0.2 | +| entropy_loss | -0.415 | +| explained_variance | -2.54 | +| learning_rate | 0.0001 | +| loss | -0.097 | +| n_updates | 156890 | +| policy_gradient_loss | -0.0744 | +| value_loss | 0.000314 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.39e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 309 | +| iterations | 9638 | +| time_elapsed | 31900 | +| total_timesteps | 9869312 | +| train/ | | +| approx_kl | 2.850544 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.388 | +| explained_variance | -7.95 | +| learning_rate | 0.0001 | +| loss | -0.0857 | +| n_updates | 156900 | +| policy_gradient_loss | -0.0783 | +| value_loss | 0.00011 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.39e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 309 | +| iterations | 9639 | +| time_elapsed | 31903 | +| total_timesteps | 9870336 | +| train/ | | +| approx_kl | 1.6620816 | +| clip_fraction | 0.465 | +| clip_range | 0.2 | +| entropy_loss | -0.411 | +| explained_variance | -0.195 | +| learning_rate | 0.0001 | +| loss | -0.0844 | +| n_updates | 156910 | +| policy_gradient_loss | -0.0636 | +| value_loss | 0.000312 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.37e+03 | +| ep_rew_mean | 0.315 | +| time/ | | +| fps | 309 | +| iterations | 9640 | +| time_elapsed | 31907 | +| total_timesteps | 9871360 | +| train/ | | +| approx_kl | 2.880608 | +| clip_fraction | 0.516 | +| clip_range | 0.2 | +| entropy_loss | -0.442 | +| explained_variance | -2.43 | +| learning_rate | 0.0001 | +| loss | -0.0845 | +| n_updates | 156920 | +| policy_gradient_loss | -0.071 | +| value_loss | 0.000361 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.37e+03 | +| ep_rew_mean | 0.315 | +| time/ | | +| fps | 309 | +| iterations | 9641 | +| time_elapsed | 31910 | +| total_timesteps | 9872384 | +| train/ | | +| approx_kl | 1.9951844 | +| clip_fraction | 0.506 | +| clip_range | 0.2 | +| entropy_loss | -0.45 | +| explained_variance | -1.78 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 156930 | +| policy_gradient_loss | -0.0765 | +| value_loss | 0.000352 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.38e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 309 | +| iterations | 9642 | +| time_elapsed | 31914 | +| total_timesteps | 9873408 | +| train/ | | +| approx_kl | 1.8107399 | +| clip_fraction | 0.52 | +| clip_range | 0.2 | +| entropy_loss | -0.466 | +| explained_variance | -3.01 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 156940 | +| policy_gradient_loss | -0.0786 | +| value_loss | 0.000334 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.38e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 309 | +| iterations | 9643 | +| time_elapsed | 31917 | +| total_timesteps | 9874432 | +| train/ | | +| approx_kl | 1.8293893 | +| clip_fraction | 0.488 | +| clip_range | 0.2 | +| entropy_loss | -0.42 | +| explained_variance | -0.894 | +| learning_rate | 0.0001 | +| loss | -0.089 | +| n_updates | 156950 | +| policy_gradient_loss | -0.0706 | +| value_loss | 0.000563 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.37e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 309 | +| iterations | 9644 | +| time_elapsed | 31920 | +| total_timesteps | 9875456 | +| train/ | | +| approx_kl | 1.67294 | +| clip_fraction | 0.502 | +| clip_range | 0.2 | +| entropy_loss | -0.5 | +| explained_variance | -2.31 | +| learning_rate | 0.0001 | +| loss | -0.1 | +| n_updates | 156960 | +| policy_gradient_loss | -0.0754 | +| value_loss | 0.000343 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.37e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 309 | +| iterations | 9645 | +| time_elapsed | 31924 | +| total_timesteps | 9876480 | +| train/ | | +| approx_kl | 1.8103617 | +| clip_fraction | 0.482 | +| clip_range | 0.2 | +| entropy_loss | -0.426 | +| explained_variance | -5.11 | +| learning_rate | 0.0001 | +| loss | -0.0971 | +| n_updates | 156970 | +| policy_gradient_loss | -0.0705 | +| value_loss | 0.000139 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.37e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 309 | +| iterations | 9646 | +| time_elapsed | 31927 | +| total_timesteps | 9877504 | +| train/ | | +| approx_kl | 1.9659467 | +| clip_fraction | 0.503 | +| clip_range | 0.2 | +| entropy_loss | -0.416 | +| explained_variance | -1.23 | +| learning_rate | 0.0001 | +| loss | -0.113 | +| n_updates | 156980 | +| policy_gradient_loss | -0.0692 | +| value_loss | 0.000196 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.38e+03 | +| ep_rew_mean | 0.306 | +| time/ | | +| fps | 309 | +| iterations | 9647 | +| time_elapsed | 31931 | +| total_timesteps | 9878528 | +| train/ | | +| approx_kl | 1.8786633 | +| clip_fraction | 0.524 | +| clip_range | 0.2 | +| entropy_loss | -0.425 | +| explained_variance | -10.2 | +| learning_rate | 0.0001 | +| loss | -0.0958 | +| n_updates | 156990 | +| policy_gradient_loss | -0.0717 | +| value_loss | 0.000252 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.38e+03 | +| ep_rew_mean | 0.306 | +| time/ | | +| fps | 309 | +| iterations | 9648 | +| time_elapsed | 31934 | +| total_timesteps | 9879552 | +| train/ | | +| approx_kl | 2.6601174 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.376 | +| explained_variance | -2.58 | +| learning_rate | 0.0001 | +| loss | -0.111 | +| n_updates | 157000 | +| policy_gradient_loss | -0.071 | +| value_loss | 0.000225 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.38e+03 | +| ep_rew_mean | 0.306 | +| time/ | | +| fps | 309 | +| iterations | 9649 | +| time_elapsed | 31937 | +| total_timesteps | 9880576 | +| train/ | | +| approx_kl | 2.8239303 | +| clip_fraction | 0.517 | +| clip_range | 0.2 | +| entropy_loss | -0.413 | +| explained_variance | -8.99 | +| learning_rate | 0.0001 | +| loss | -0.106 | +| n_updates | 157010 | +| policy_gradient_loss | -0.0702 | +| value_loss | 0.000584 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.39e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 309 | +| iterations | 9650 | +| time_elapsed | 31941 | +| total_timesteps | 9881600 | +| train/ | | +| approx_kl | 1.6584797 | +| clip_fraction | 0.516 | +| clip_range | 0.2 | +| entropy_loss | -0.486 | +| explained_variance | -4.64 | +| learning_rate | 0.0001 | +| loss | -0.0882 | +| n_updates | 157020 | +| policy_gradient_loss | -0.0669 | +| value_loss | 0.000513 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.39e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 309 | +| iterations | 9651 | +| time_elapsed | 31944 | +| total_timesteps | 9882624 | +| train/ | | +| approx_kl | 1.9779919 | +| clip_fraction | 0.504 | +| clip_range | 0.2 | +| entropy_loss | -0.396 | +| explained_variance | -1.27 | +| learning_rate | 0.0001 | +| loss | -0.0766 | +| n_updates | 157030 | +| policy_gradient_loss | -0.0745 | +| value_loss | 0.00049 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.39e+03 | +| ep_rew_mean | 0.304 | +| time/ | | +| fps | 309 | +| iterations | 9652 | +| time_elapsed | 31947 | +| total_timesteps | 9883648 | +| train/ | | +| approx_kl | 4.5043736 | +| clip_fraction | 0.54 | +| clip_range | 0.2 | +| entropy_loss | -0.464 | +| explained_variance | -0.951 | +| learning_rate | 0.0001 | +| loss | -0.12 | +| n_updates | 157040 | +| policy_gradient_loss | -0.0827 | +| value_loss | 0.00071 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.39e+03 | +| ep_rew_mean | 0.304 | +| time/ | | +| fps | 309 | +| iterations | 9653 | +| time_elapsed | 31951 | +| total_timesteps | 9884672 | +| train/ | | +| approx_kl | 1.6404114 | +| clip_fraction | 0.491 | +| clip_range | 0.2 | +| entropy_loss | -0.45 | +| explained_variance | -2.2 | +| learning_rate | 0.0001 | +| loss | -0.0808 | +| n_updates | 157050 | +| policy_gradient_loss | -0.0679 | +| value_loss | 0.000281 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.39e+03 | +| ep_rew_mean | 0.304 | +| time/ | | +| fps | 309 | +| iterations | 9654 | +| time_elapsed | 31954 | +| total_timesteps | 9885696 | +| train/ | | +| approx_kl | 1.6298444 | +| clip_fraction | 0.527 | +| clip_range | 0.2 | +| entropy_loss | -0.464 | +| explained_variance | -2.38 | +| learning_rate | 0.0001 | +| loss | -0.115 | +| n_updates | 157060 | +| policy_gradient_loss | -0.0788 | +| value_loss | 0.000232 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.38e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 309 | +| iterations | 9655 | +| time_elapsed | 31957 | +| total_timesteps | 9886720 | +| train/ | | +| approx_kl | 2.1090362 | +| clip_fraction | 0.538 | +| clip_range | 0.2 | +| entropy_loss | -0.435 | +| explained_variance | -5.56 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 157070 | +| policy_gradient_loss | -0.0824 | +| value_loss | 0.000292 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.38e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 309 | +| iterations | 9656 | +| time_elapsed | 31961 | +| total_timesteps | 9887744 | +| train/ | | +| approx_kl | 1.925769 | +| clip_fraction | 0.511 | +| clip_range | 0.2 | +| entropy_loss | -0.41 | +| explained_variance | -0.664 | +| learning_rate | 0.0001 | +| loss | -0.0954 | +| n_updates | 157080 | +| policy_gradient_loss | -0.0677 | +| value_loss | 0.000572 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.38e+03 | +| ep_rew_mean | 0.297 | +| time/ | | +| fps | 309 | +| iterations | 9657 | +| time_elapsed | 31964 | +| total_timesteps | 9888768 | +| train/ | | +| approx_kl | 2.3088562 | +| clip_fraction | 0.522 | +| clip_range | 0.2 | +| entropy_loss | -0.494 | +| explained_variance | -6.43 | +| learning_rate | 0.0001 | +| loss | -0.11 | +| n_updates | 157090 | +| policy_gradient_loss | -0.0694 | +| value_loss | 0.000497 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.38e+03 | +| ep_rew_mean | 0.297 | +| time/ | | +| fps | 309 | +| iterations | 9658 | +| time_elapsed | 31968 | +| total_timesteps | 9889792 | +| train/ | | +| approx_kl | 1.4986691 | +| clip_fraction | 0.453 | +| clip_range | 0.2 | +| entropy_loss | -0.373 | +| explained_variance | -0.662 | +| learning_rate | 0.0001 | +| loss | -0.0694 | +| n_updates | 157100 | +| policy_gradient_loss | -0.06 | +| value_loss | 0.000283 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.38e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 309 | +| iterations | 9659 | +| time_elapsed | 31971 | +| total_timesteps | 9890816 | +| train/ | | +| approx_kl | 1.8495452 | +| clip_fraction | 0.531 | +| clip_range | 0.2 | +| entropy_loss | -0.445 | +| explained_variance | -0.799 | +| learning_rate | 0.0001 | +| loss | -0.0871 | +| n_updates | 157110 | +| policy_gradient_loss | -0.0741 | +| value_loss | 0.00029 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.38e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 309 | +| iterations | 9660 | +| time_elapsed | 31974 | +| total_timesteps | 9891840 | +| train/ | | +| approx_kl | 2.1826472 | +| clip_fraction | 0.489 | +| clip_range | 0.2 | +| entropy_loss | -0.381 | +| explained_variance | -2.15 | +| learning_rate | 0.0001 | +| loss | -0.0872 | +| n_updates | 157120 | +| policy_gradient_loss | -0.075 | +| value_loss | 0.000574 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.38e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 309 | +| iterations | 9661 | +| time_elapsed | 31978 | +| total_timesteps | 9892864 | +| train/ | | +| approx_kl | 2.6844685 | +| clip_fraction | 0.516 | +| clip_range | 0.2 | +| entropy_loss | -0.398 | +| explained_variance | -3.15 | +| learning_rate | 0.0001 | +| loss | -0.1 | +| n_updates | 157130 | +| policy_gradient_loss | -0.0787 | +| value_loss | 0.000458 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.39e+03 | +| ep_rew_mean | 0.295 | +| time/ | | +| fps | 309 | +| iterations | 9662 | +| time_elapsed | 31981 | +| total_timesteps | 9893888 | +| train/ | | +| approx_kl | 2.9337296 | +| clip_fraction | 0.526 | +| clip_range | 0.2 | +| entropy_loss | -0.358 | +| explained_variance | -1.28 | +| learning_rate | 0.0001 | +| loss | -0.113 | +| n_updates | 157140 | +| policy_gradient_loss | -0.0655 | +| value_loss | 0.000312 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.39e+03 | +| ep_rew_mean | 0.295 | +| time/ | | +| fps | 309 | +| iterations | 9663 | +| time_elapsed | 31985 | +| total_timesteps | 9894912 | +| train/ | | +| approx_kl | 2.0704474 | +| clip_fraction | 0.484 | +| clip_range | 0.2 | +| entropy_loss | -0.369 | +| explained_variance | -1.51 | +| learning_rate | 0.0001 | +| loss | -0.091 | +| n_updates | 157150 | +| policy_gradient_loss | -0.0712 | +| value_loss | 0.000412 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.39e+03 | +| ep_rew_mean | 0.294 | +| time/ | | +| fps | 309 | +| iterations | 9664 | +| time_elapsed | 31988 | +| total_timesteps | 9895936 | +| train/ | | +| approx_kl | 2.1862588 | +| clip_fraction | 0.527 | +| clip_range | 0.2 | +| entropy_loss | -0.448 | +| explained_variance | -0.466 | +| learning_rate | 0.0001 | +| loss | -0.107 | +| n_updates | 157160 | +| policy_gradient_loss | -0.0791 | +| value_loss | 0.000498 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.39e+03 | +| ep_rew_mean | 0.294 | +| time/ | | +| fps | 309 | +| iterations | 9665 | +| time_elapsed | 31992 | +| total_timesteps | 9896960 | +| train/ | | +| approx_kl | 2.0364296 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.412 | +| explained_variance | -0.753 | +| learning_rate | 0.0001 | +| loss | -0.107 | +| n_updates | 157170 | +| policy_gradient_loss | -0.067 | +| value_loss | 0.000575 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.34e+03 | +| ep_rew_mean | 0.289 | +| time/ | | +| fps | 309 | +| iterations | 9666 | +| time_elapsed | 31995 | +| total_timesteps | 9897984 | +| train/ | | +| approx_kl | 2.2729025 | +| clip_fraction | 0.523 | +| clip_range | 0.2 | +| entropy_loss | -0.443 | +| explained_variance | -11.8 | +| learning_rate | 0.0001 | +| loss | -0.108 | +| n_updates | 157180 | +| policy_gradient_loss | -0.0763 | +| value_loss | 0.000375 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.34e+03 | +| ep_rew_mean | 0.289 | +| time/ | | +| fps | 309 | +| iterations | 9667 | +| time_elapsed | 31998 | +| total_timesteps | 9899008 | +| train/ | | +| approx_kl | 1.4351208 | +| clip_fraction | 0.485 | +| clip_range | 0.2 | +| entropy_loss | -0.471 | +| explained_variance | -3.28 | +| learning_rate | 0.0001 | +| loss | -0.115 | +| n_updates | 157190 | +| policy_gradient_loss | -0.068 | +| value_loss | 0.000261 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.34e+03 | +| ep_rew_mean | 0.289 | +| time/ | | +| fps | 309 | +| iterations | 9668 | +| time_elapsed | 32001 | +| total_timesteps | 9900032 | +| train/ | | +| approx_kl | 2.0468478 | +| clip_fraction | 0.54 | +| clip_range | 0.2 | +| entropy_loss | -0.425 | +| explained_variance | -1.15 | +| learning_rate | 0.0001 | +| loss | -0.0871 | +| n_updates | 157200 | +| policy_gradient_loss | -0.0716 | +| value_loss | 0.000646 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.34e+03 | +| ep_rew_mean | 0.289 | +| time/ | | +| fps | 309 | +| iterations | 9669 | +| time_elapsed | 32005 | +| total_timesteps | 9901056 | +| train/ | | +| approx_kl | 1.8685983 | +| clip_fraction | 0.499 | +| clip_range | 0.2 | +| entropy_loss | -0.41 | +| explained_variance | -1.3 | +| learning_rate | 0.0001 | +| loss | -0.108 | +| n_updates | 157210 | +| policy_gradient_loss | -0.0715 | +| value_loss | 0.000543 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.34e+03 | +| ep_rew_mean | 0.289 | +| time/ | | +| fps | 309 | +| iterations | 9670 | +| time_elapsed | 32008 | +| total_timesteps | 9902080 | +| train/ | | +| approx_kl | 1.9480946 | +| clip_fraction | 0.546 | +| clip_range | 0.2 | +| entropy_loss | -0.464 | +| explained_variance | -2.99 | +| learning_rate | 0.0001 | +| loss | -0.0987 | +| n_updates | 157220 | +| policy_gradient_loss | -0.0729 | +| value_loss | 0.000386 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.35e+03 | +| ep_rew_mean | 0.283 | +| time/ | | +| fps | 309 | +| iterations | 9671 | +| time_elapsed | 32012 | +| total_timesteps | 9903104 | +| train/ | | +| approx_kl | 2.2269406 | +| clip_fraction | 0.515 | +| clip_range | 0.2 | +| entropy_loss | -0.44 | +| explained_variance | -9.54 | +| learning_rate | 0.0001 | +| loss | -0.0884 | +| n_updates | 157230 | +| policy_gradient_loss | -0.0797 | +| value_loss | 0.000207 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.35e+03 | +| ep_rew_mean | 0.283 | +| time/ | | +| fps | 309 | +| iterations | 9672 | +| time_elapsed | 32015 | +| total_timesteps | 9904128 | +| train/ | | +| approx_kl | 1.8547846 | +| clip_fraction | 0.519 | +| clip_range | 0.2 | +| entropy_loss | -0.46 | +| explained_variance | -0.161 | +| learning_rate | 0.0001 | +| loss | -0.113 | +| n_updates | 157240 | +| policy_gradient_loss | -0.0745 | +| value_loss | 0.000388 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.35e+03 | +| ep_rew_mean | 0.286 | +| time/ | | +| fps | 309 | +| iterations | 9673 | +| time_elapsed | 32018 | +| total_timesteps | 9905152 | +| train/ | | +| approx_kl | 2.0492556 | +| clip_fraction | 0.568 | +| clip_range | 0.2 | +| entropy_loss | -0.539 | +| explained_variance | -3.71 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 157250 | +| policy_gradient_loss | -0.0861 | +| value_loss | 0.00025 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.35e+03 | +| ep_rew_mean | 0.286 | +| time/ | | +| fps | 309 | +| iterations | 9674 | +| time_elapsed | 32021 | +| total_timesteps | 9906176 | +| train/ | | +| approx_kl | 1.3724895 | +| clip_fraction | 0.479 | +| clip_range | 0.2 | +| entropy_loss | -0.495 | +| explained_variance | -2.93 | +| learning_rate | 0.0001 | +| loss | -0.0902 | +| n_updates | 157260 | +| policy_gradient_loss | -0.0699 | +| value_loss | 7.26e-05 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.35e+03 | +| ep_rew_mean | 0.286 | +| time/ | | +| fps | 309 | +| iterations | 9675 | +| time_elapsed | 32025 | +| total_timesteps | 9907200 | +| train/ | | +| approx_kl | 1.9359233 | +| clip_fraction | 0.527 | +| clip_range | 0.2 | +| entropy_loss | -0.446 | +| explained_variance | -0.296 | +| learning_rate | 0.0001 | +| loss | -0.0519 | +| n_updates | 157270 | +| policy_gradient_loss | -0.0602 | +| value_loss | 0.000594 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.37e+03 | +| ep_rew_mean | 0.283 | +| time/ | | +| fps | 309 | +| iterations | 9676 | +| time_elapsed | 32028 | +| total_timesteps | 9908224 | +| train/ | | +| approx_kl | 2.0067155 | +| clip_fraction | 0.501 | +| clip_range | 0.2 | +| entropy_loss | -0.425 | +| explained_variance | -3 | +| learning_rate | 0.0001 | +| loss | -0.115 | +| n_updates | 157280 | +| policy_gradient_loss | -0.0753 | +| value_loss | 0.000575 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.37e+03 | +| ep_rew_mean | 0.283 | +| time/ | | +| fps | 309 | +| iterations | 9677 | +| time_elapsed | 32032 | +| total_timesteps | 9909248 | +| train/ | | +| approx_kl | 1.5525999 | +| clip_fraction | 0.473 | +| clip_range | 0.2 | +| entropy_loss | -0.428 | +| explained_variance | -0.994 | +| learning_rate | 0.0001 | +| loss | -0.0809 | +| n_updates | 157290 | +| policy_gradient_loss | -0.0634 | +| value_loss | 0.000287 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.37e+03 | +| ep_rew_mean | 0.283 | +| time/ | | +| fps | 309 | +| iterations | 9678 | +| time_elapsed | 32035 | +| total_timesteps | 9910272 | +| train/ | | +| approx_kl | 1.7669244 | +| clip_fraction | 0.526 | +| clip_range | 0.2 | +| entropy_loss | -0.454 | +| explained_variance | -1.35 | +| learning_rate | 0.0001 | +| loss | -0.0747 | +| n_updates | 157300 | +| policy_gradient_loss | -0.0791 | +| value_loss | 0.000198 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.37e+03 | +| ep_rew_mean | 0.283 | +| time/ | | +| fps | 309 | +| iterations | 9679 | +| time_elapsed | 32039 | +| total_timesteps | 9911296 | +| train/ | | +| approx_kl | 2.129371 | +| clip_fraction | 0.533 | +| clip_range | 0.2 | +| entropy_loss | -0.479 | +| explained_variance | -0.495 | +| learning_rate | 0.0001 | +| loss | -0.0643 | +| n_updates | 157310 | +| policy_gradient_loss | -0.0571 | +| value_loss | 0.000562 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.37e+03 | +| ep_rew_mean | 0.286 | +| time/ | | +| fps | 309 | +| iterations | 9680 | +| time_elapsed | 32042 | +| total_timesteps | 9912320 | +| train/ | | +| approx_kl | 1.3977168 | +| clip_fraction | 0.51 | +| clip_range | 0.2 | +| entropy_loss | -0.441 | +| explained_variance | -4.32 | +| learning_rate | 0.0001 | +| loss | -0.086 | +| n_updates | 157320 | +| policy_gradient_loss | -0.0772 | +| value_loss | 0.000429 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.37e+03 | +| ep_rew_mean | 0.286 | +| time/ | | +| fps | 309 | +| iterations | 9681 | +| time_elapsed | 32046 | +| total_timesteps | 9913344 | +| train/ | | +| approx_kl | 1.7015721 | +| clip_fraction | 0.477 | +| clip_range | 0.2 | +| entropy_loss | -0.392 | +| explained_variance | -1.7 | +| learning_rate | 0.0001 | +| loss | -0.0694 | +| n_updates | 157330 | +| policy_gradient_loss | -0.0679 | +| value_loss | 0.00032 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.37e+03 | +| ep_rew_mean | 0.286 | +| time/ | | +| fps | 309 | +| iterations | 9682 | +| time_elapsed | 32050 | +| total_timesteps | 9914368 | +| train/ | | +| approx_kl | 2.043334 | +| clip_fraction | 0.518 | +| clip_range | 0.2 | +| entropy_loss | -0.463 | +| explained_variance | -1.05 | +| learning_rate | 0.0001 | +| loss | -0.0864 | +| n_updates | 157340 | +| policy_gradient_loss | -0.073 | +| value_loss | 0.000588 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.38e+03 | +| ep_rew_mean | 0.287 | +| time/ | | +| fps | 309 | +| iterations | 9683 | +| time_elapsed | 32053 | +| total_timesteps | 9915392 | +| train/ | | +| approx_kl | 2.1141927 | +| clip_fraction | 0.52 | +| clip_range | 0.2 | +| entropy_loss | -0.515 | +| explained_variance | -3.4 | +| learning_rate | 0.0001 | +| loss | -0.0799 | +| n_updates | 157350 | +| policy_gradient_loss | -0.0779 | +| value_loss | 0.000272 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.38e+03 | +| ep_rew_mean | 0.287 | +| time/ | | +| fps | 309 | +| iterations | 9684 | +| time_elapsed | 32056 | +| total_timesteps | 9916416 | +| train/ | | +| approx_kl | 1.434667 | +| clip_fraction | 0.478 | +| clip_range | 0.2 | +| entropy_loss | -0.48 | +| explained_variance | -1.29 | +| learning_rate | 0.0001 | +| loss | -0.087 | +| n_updates | 157360 | +| policy_gradient_loss | -0.0664 | +| value_loss | 0.000258 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.38e+03 | +| ep_rew_mean | 0.29 | +| time/ | | +| fps | 309 | +| iterations | 9685 | +| time_elapsed | 32060 | +| total_timesteps | 9917440 | +| train/ | | +| approx_kl | 1.844622 | +| clip_fraction | 0.525 | +| clip_range | 0.2 | +| entropy_loss | -0.491 | +| explained_variance | -0.783 | +| learning_rate | 0.0001 | +| loss | -0.0944 | +| n_updates | 157370 | +| policy_gradient_loss | -0.0712 | +| value_loss | 0.000451 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.37e+03 | +| ep_rew_mean | 0.291 | +| time/ | | +| fps | 309 | +| iterations | 9686 | +| time_elapsed | 32063 | +| total_timesteps | 9918464 | +| train/ | | +| approx_kl | 3.1023922 | +| clip_fraction | 0.511 | +| clip_range | 0.2 | +| entropy_loss | -0.484 | +| explained_variance | -1.32 | +| learning_rate | 0.0001 | +| loss | -0.105 | +| n_updates | 157380 | +| policy_gradient_loss | -0.0775 | +| value_loss | 0.000407 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.37e+03 | +| ep_rew_mean | 0.291 | +| time/ | | +| fps | 309 | +| iterations | 9687 | +| time_elapsed | 32066 | +| total_timesteps | 9919488 | +| train/ | | +| approx_kl | 1.7300562 | +| clip_fraction | 0.505 | +| clip_range | 0.2 | +| entropy_loss | -0.472 | +| explained_variance | -0.828 | +| learning_rate | 0.0001 | +| loss | -0.0831 | +| n_updates | 157390 | +| policy_gradient_loss | -0.0722 | +| value_loss | 0.00046 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.37e+03 | +| ep_rew_mean | 0.291 | +| time/ | | +| fps | 309 | +| iterations | 9688 | +| time_elapsed | 32070 | +| total_timesteps | 9920512 | +| train/ | | +| approx_kl | 2.3007658 | +| clip_fraction | 0.527 | +| clip_range | 0.2 | +| entropy_loss | -0.414 | +| explained_variance | -6.22 | +| learning_rate | 0.0001 | +| loss | -0.0725 | +| n_updates | 157400 | +| policy_gradient_loss | -0.0802 | +| value_loss | 0.000366 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.38e+03 | +| ep_rew_mean | 0.289 | +| time/ | | +| fps | 309 | +| iterations | 9689 | +| time_elapsed | 32073 | +| total_timesteps | 9921536 | +| train/ | | +| approx_kl | 2.267139 | +| clip_fraction | 0.507 | +| clip_range | 0.2 | +| entropy_loss | -0.415 | +| explained_variance | -11.1 | +| learning_rate | 0.0001 | +| loss | -0.108 | +| n_updates | 157410 | +| policy_gradient_loss | -0.0786 | +| value_loss | 0.000193 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.38e+03 | +| ep_rew_mean | 0.289 | +| time/ | | +| fps | 309 | +| iterations | 9690 | +| time_elapsed | 32076 | +| total_timesteps | 9922560 | +| train/ | | +| approx_kl | 2.1773138 | +| clip_fraction | 0.512 | +| clip_range | 0.2 | +| entropy_loss | -0.456 | +| explained_variance | -0.62 | +| learning_rate | 0.0001 | +| loss | -0.0931 | +| n_updates | 157420 | +| policy_gradient_loss | -0.0685 | +| value_loss | 0.000428 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.37e+03 | +| ep_rew_mean | 0.291 | +| time/ | | +| fps | 309 | +| iterations | 9691 | +| time_elapsed | 32079 | +| total_timesteps | 9923584 | +| train/ | | +| approx_kl | 1.9072218 | +| clip_fraction | 0.52 | +| clip_range | 0.2 | +| entropy_loss | -0.424 | +| explained_variance | -2.67 | +| learning_rate | 0.0001 | +| loss | -0.0859 | +| n_updates | 157430 | +| policy_gradient_loss | -0.0791 | +| value_loss | 0.000464 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.37e+03 | +| ep_rew_mean | 0.293 | +| time/ | | +| fps | 309 | +| iterations | 9692 | +| time_elapsed | 32083 | +| total_timesteps | 9924608 | +| train/ | | +| approx_kl | 1.8479241 | +| clip_fraction | 0.489 | +| clip_range | 0.2 | +| entropy_loss | -0.425 | +| explained_variance | -0.42 | +| learning_rate | 0.0001 | +| loss | -0.0797 | +| n_updates | 157440 | +| policy_gradient_loss | -0.0608 | +| value_loss | 0.000312 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.37e+03 | +| ep_rew_mean | 0.293 | +| time/ | | +| fps | 309 | +| iterations | 9693 | +| time_elapsed | 32086 | +| total_timesteps | 9925632 | +| train/ | | +| approx_kl | 1.8674533 | +| clip_fraction | 0.51 | +| clip_range | 0.2 | +| entropy_loss | -0.437 | +| explained_variance | -0.811 | +| learning_rate | 0.0001 | +| loss | -0.0719 | +| n_updates | 157450 | +| policy_gradient_loss | -0.0719 | +| value_loss | 0.000552 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.37e+03 | +| ep_rew_mean | 0.291 | +| time/ | | +| fps | 309 | +| iterations | 9694 | +| time_elapsed | 32089 | +| total_timesteps | 9926656 | +| train/ | | +| approx_kl | 1.8954802 | +| clip_fraction | 0.506 | +| clip_range | 0.2 | +| entropy_loss | -0.437 | +| explained_variance | -0.993 | +| learning_rate | 0.0001 | +| loss | -0.114 | +| n_updates | 157460 | +| policy_gradient_loss | -0.0696 | +| value_loss | 0.000736 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.37e+03 | +| ep_rew_mean | 0.291 | +| time/ | | +| fps | 309 | +| iterations | 9695 | +| time_elapsed | 32093 | +| total_timesteps | 9927680 | +| train/ | | +| approx_kl | 1.6239812 | +| clip_fraction | 0.509 | +| clip_range | 0.2 | +| entropy_loss | -0.501 | +| explained_variance | -4.98 | +| learning_rate | 0.0001 | +| loss | -0.11 | +| n_updates | 157470 | +| policy_gradient_loss | -0.0732 | +| value_loss | 0.000325 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.37e+03 | +| ep_rew_mean | 0.291 | +| time/ | | +| fps | 309 | +| iterations | 9696 | +| time_elapsed | 32096 | +| total_timesteps | 9928704 | +| train/ | | +| approx_kl | 2.5044188 | +| clip_fraction | 0.538 | +| clip_range | 0.2 | +| entropy_loss | -0.48 | +| explained_variance | -0.335 | +| learning_rate | 0.0001 | +| loss | -0.0505 | +| n_updates | 157480 | +| policy_gradient_loss | -0.071 | +| value_loss | 0.000569 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.37e+03 | +| ep_rew_mean | 0.291 | +| time/ | | +| fps | 309 | +| iterations | 9697 | +| time_elapsed | 32100 | +| total_timesteps | 9929728 | +| train/ | | +| approx_kl | 1.6991562 | +| clip_fraction | 0.534 | +| clip_range | 0.2 | +| entropy_loss | -0.525 | +| explained_variance | -4.73 | +| learning_rate | 0.0001 | +| loss | -0.128 | +| n_updates | 157490 | +| policy_gradient_loss | -0.079 | +| value_loss | 0.000257 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.36e+03 | +| ep_rew_mean | 0.288 | +| time/ | | +| fps | 309 | +| iterations | 9698 | +| time_elapsed | 32103 | +| total_timesteps | 9930752 | +| train/ | | +| approx_kl | 1.7499661 | +| clip_fraction | 0.505 | +| clip_range | 0.2 | +| entropy_loss | -0.461 | +| explained_variance | -2.72 | +| learning_rate | 0.0001 | +| loss | -0.0959 | +| n_updates | 157500 | +| policy_gradient_loss | -0.0729 | +| value_loss | 0.000355 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.36e+03 | +| ep_rew_mean | 0.288 | +| time/ | | +| fps | 309 | +| iterations | 9699 | +| time_elapsed | 32107 | +| total_timesteps | 9931776 | +| train/ | | +| approx_kl | 2.154225 | +| clip_fraction | 0.53 | +| clip_range | 0.2 | +| entropy_loss | -0.481 | +| explained_variance | -1.69 | +| learning_rate | 0.0001 | +| loss | -0.107 | +| n_updates | 157510 | +| policy_gradient_loss | -0.075 | +| value_loss | 0.000471 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.36e+03 | +| ep_rew_mean | 0.291 | +| time/ | | +| fps | 309 | +| iterations | 9700 | +| time_elapsed | 32110 | +| total_timesteps | 9932800 | +| train/ | | +| approx_kl | 1.9138963 | +| clip_fraction | 0.559 | +| clip_range | 0.2 | +| entropy_loss | -0.55 | +| explained_variance | -1.47 | +| learning_rate | 0.0001 | +| loss | -0.0922 | +| n_updates | 157520 | +| policy_gradient_loss | -0.0769 | +| value_loss | 0.000378 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.36e+03 | +| ep_rew_mean | 0.291 | +| time/ | | +| fps | 309 | +| iterations | 9701 | +| time_elapsed | 32113 | +| total_timesteps | 9933824 | +| train/ | | +| approx_kl | 2.4789639 | +| clip_fraction | 0.535 | +| clip_range | 0.2 | +| entropy_loss | -0.45 | +| explained_variance | -2.42 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 157530 | +| policy_gradient_loss | -0.0748 | +| value_loss | 0.000431 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.35e+03 | +| ep_rew_mean | 0.288 | +| time/ | | +| fps | 309 | +| iterations | 9702 | +| time_elapsed | 32116 | +| total_timesteps | 9934848 | +| train/ | | +| approx_kl | 2.1693044 | +| clip_fraction | 0.528 | +| clip_range | 0.2 | +| entropy_loss | -0.43 | +| explained_variance | -1.03 | +| learning_rate | 0.0001 | +| loss | -0.109 | +| n_updates | 157540 | +| policy_gradient_loss | -0.0767 | +| value_loss | 0.000408 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.35e+03 | +| ep_rew_mean | 0.288 | +| time/ | | +| fps | 309 | +| iterations | 9703 | +| time_elapsed | 32120 | +| total_timesteps | 9935872 | +| train/ | | +| approx_kl | 1.5450684 | +| clip_fraction | 0.496 | +| clip_range | 0.2 | +| entropy_loss | -0.442 | +| explained_variance | -3.22 | +| learning_rate | 0.0001 | +| loss | -0.0902 | +| n_updates | 157550 | +| policy_gradient_loss | -0.0699 | +| value_loss | 0.000328 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.34e+03 | +| ep_rew_mean | 0.283 | +| time/ | | +| fps | 309 | +| iterations | 9704 | +| time_elapsed | 32123 | +| total_timesteps | 9936896 | +| train/ | | +| approx_kl | 1.6555245 | +| clip_fraction | 0.528 | +| clip_range | 0.2 | +| entropy_loss | -0.48 | +| explained_variance | -3.12 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 157560 | +| policy_gradient_loss | -0.0837 | +| value_loss | 0.000213 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.34e+03 | +| ep_rew_mean | 0.283 | +| time/ | | +| fps | 309 | +| iterations | 9705 | +| time_elapsed | 32127 | +| total_timesteps | 9937920 | +| train/ | | +| approx_kl | 1.5750415 | +| clip_fraction | 0.511 | +| clip_range | 0.2 | +| entropy_loss | -0.439 | +| explained_variance | -0.788 | +| learning_rate | 0.0001 | +| loss | -0.0751 | +| n_updates | 157570 | +| policy_gradient_loss | -0.0633 | +| value_loss | 0.000536 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.34e+03 | +| ep_rew_mean | 0.283 | +| time/ | | +| fps | 309 | +| iterations | 9706 | +| time_elapsed | 32130 | +| total_timesteps | 9938944 | +| train/ | | +| approx_kl | 2.3235915 | +| clip_fraction | 0.519 | +| clip_range | 0.2 | +| entropy_loss | -0.421 | +| explained_variance | -4.17 | +| learning_rate | 0.0001 | +| loss | -0.0712 | +| n_updates | 157580 | +| policy_gradient_loss | -0.0728 | +| value_loss | 0.000487 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.36e+03 | +| ep_rew_mean | 0.281 | +| time/ | | +| fps | 309 | +| iterations | 9707 | +| time_elapsed | 32133 | +| total_timesteps | 9939968 | +| train/ | | +| approx_kl | 1.9208186 | +| clip_fraction | 0.541 | +| clip_range | 0.2 | +| entropy_loss | -0.473 | +| explained_variance | -1.16 | +| learning_rate | 0.0001 | +| loss | -0.109 | +| n_updates | 157590 | +| policy_gradient_loss | -0.0786 | +| value_loss | 0.00043 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.36e+03 | +| ep_rew_mean | 0.281 | +| time/ | | +| fps | 309 | +| iterations | 9708 | +| time_elapsed | 32137 | +| total_timesteps | 9940992 | +| train/ | | +| approx_kl | 2.2093518 | +| clip_fraction | 0.547 | +| clip_range | 0.2 | +| entropy_loss | -0.52 | +| explained_variance | -6.9 | +| learning_rate | 0.0001 | +| loss | -0.0991 | +| n_updates | 157600 | +| policy_gradient_loss | -0.0761 | +| value_loss | 0.000211 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.36e+03 | +| ep_rew_mean | 0.281 | +| time/ | | +| fps | 309 | +| iterations | 9709 | +| time_elapsed | 32140 | +| total_timesteps | 9942016 | +| train/ | | +| approx_kl | 1.9818103 | +| clip_fraction | 0.521 | +| clip_range | 0.2 | +| entropy_loss | -0.495 | +| explained_variance | -3.35 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 157610 | +| policy_gradient_loss | -0.0752 | +| value_loss | 9.27e-05 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.36e+03 | +| ep_rew_mean | 0.281 | +| time/ | | +| fps | 309 | +| iterations | 9710 | +| time_elapsed | 32143 | +| total_timesteps | 9943040 | +| train/ | | +| approx_kl | 1.9033991 | +| clip_fraction | 0.53 | +| clip_range | 0.2 | +| entropy_loss | -0.442 | +| explained_variance | -0.422 | +| learning_rate | 0.0001 | +| loss | -0.051 | +| n_updates | 157620 | +| policy_gradient_loss | -0.0692 | +| value_loss | 0.000402 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.36e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 309 | +| iterations | 9711 | +| time_elapsed | 32147 | +| total_timesteps | 9944064 | +| train/ | | +| approx_kl | 1.8995285 | +| clip_fraction | 0.496 | +| clip_range | 0.2 | +| entropy_loss | -0.457 | +| explained_variance | -4.14 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 157630 | +| policy_gradient_loss | -0.0721 | +| value_loss | 0.000268 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.36e+03 | +| ep_rew_mean | 0.281 | +| time/ | | +| fps | 309 | +| iterations | 9712 | +| time_elapsed | 32150 | +| total_timesteps | 9945088 | +| train/ | | +| approx_kl | 1.812924 | +| clip_fraction | 0.513 | +| clip_range | 0.2 | +| entropy_loss | -0.499 | +| explained_variance | -0.614 | +| learning_rate | 0.0001 | +| loss | -0.0866 | +| n_updates | 157640 | +| policy_gradient_loss | -0.0691 | +| value_loss | 0.000191 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.36e+03 | +| ep_rew_mean | 0.281 | +| time/ | | +| fps | 309 | +| iterations | 9713 | +| time_elapsed | 32154 | +| total_timesteps | 9946112 | +| train/ | | +| approx_kl | 1.9536961 | +| clip_fraction | 0.511 | +| clip_range | 0.2 | +| entropy_loss | -0.469 | +| explained_variance | -0.688 | +| learning_rate | 0.0001 | +| loss | -0.106 | +| n_updates | 157650 | +| policy_gradient_loss | -0.0719 | +| value_loss | 0.000409 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.34e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 309 | +| iterations | 9714 | +| time_elapsed | 32157 | +| total_timesteps | 9947136 | +| train/ | | +| approx_kl | 17.22402 | +| clip_fraction | 0.514 | +| clip_range | 0.2 | +| entropy_loss | -0.415 | +| explained_variance | -1.23 | +| learning_rate | 0.0001 | +| loss | -0.095 | +| n_updates | 157660 | +| policy_gradient_loss | -0.0702 | +| value_loss | 0.000614 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.34e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 309 | +| iterations | 9715 | +| time_elapsed | 32161 | +| total_timesteps | 9948160 | +| train/ | | +| approx_kl | 1.5154529 | +| clip_fraction | 0.514 | +| clip_range | 0.2 | +| entropy_loss | -0.512 | +| explained_variance | -1.64 | +| learning_rate | 0.0001 | +| loss | -0.111 | +| n_updates | 157670 | +| policy_gradient_loss | -0.0754 | +| value_loss | 0.00029 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.34e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 309 | +| iterations | 9716 | +| time_elapsed | 32164 | +| total_timesteps | 9949184 | +| train/ | | +| approx_kl | 3.2387946 | +| clip_fraction | 0.499 | +| clip_range | 0.2 | +| entropy_loss | -0.416 | +| explained_variance | -8.22 | +| learning_rate | 0.0001 | +| loss | -0.0892 | +| n_updates | 157680 | +| policy_gradient_loss | -0.0752 | +| value_loss | 0.00026 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.35e+03 | +| ep_rew_mean | 0.278 | +| time/ | | +| fps | 309 | +| iterations | 9717 | +| time_elapsed | 32167 | +| total_timesteps | 9950208 | +| train/ | | +| approx_kl | 1.698518 | +| clip_fraction | 0.503 | +| clip_range | 0.2 | +| entropy_loss | -0.444 | +| explained_variance | -0.962 | +| learning_rate | 0.0001 | +| loss | -0.09 | +| n_updates | 157690 | +| policy_gradient_loss | -0.0723 | +| value_loss | 0.000308 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.35e+03 | +| ep_rew_mean | 0.278 | +| time/ | | +| fps | 309 | +| iterations | 9718 | +| time_elapsed | 32171 | +| total_timesteps | 9951232 | +| train/ | | +| approx_kl | 2.0229824 | +| clip_fraction | 0.532 | +| clip_range | 0.2 | +| entropy_loss | -0.535 | +| explained_variance | -1.21 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 157700 | +| policy_gradient_loss | -0.0701 | +| value_loss | 0.000436 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.36e+03 | +| ep_rew_mean | 0.277 | +| time/ | | +| fps | 309 | +| iterations | 9719 | +| time_elapsed | 32174 | +| total_timesteps | 9952256 | +| train/ | | +| approx_kl | 2.043139 | +| clip_fraction | 0.572 | +| clip_range | 0.2 | +| entropy_loss | -0.546 | +| explained_variance | -1.35 | +| learning_rate | 0.0001 | +| loss | -0.0819 | +| n_updates | 157710 | +| policy_gradient_loss | -0.076 | +| value_loss | 0.000335 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.36e+03 | +| ep_rew_mean | 0.277 | +| time/ | | +| fps | 309 | +| iterations | 9720 | +| time_elapsed | 32177 | +| total_timesteps | 9953280 | +| train/ | | +| approx_kl | 1.7407014 | +| clip_fraction | 0.513 | +| clip_range | 0.2 | +| entropy_loss | -0.474 | +| explained_variance | -3.62 | +| learning_rate | 0.0001 | +| loss | -0.118 | +| n_updates | 157720 | +| policy_gradient_loss | -0.0814 | +| value_loss | 0.000226 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.36e+03 | +| ep_rew_mean | 0.277 | +| time/ | | +| fps | 309 | +| iterations | 9721 | +| time_elapsed | 32180 | +| total_timesteps | 9954304 | +| train/ | | +| approx_kl | 2.053904 | +| clip_fraction | 0.503 | +| clip_range | 0.2 | +| entropy_loss | -0.469 | +| explained_variance | -3.08 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 157730 | +| policy_gradient_loss | -0.0727 | +| value_loss | 0.000207 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.36e+03 | +| ep_rew_mean | 0.277 | +| time/ | | +| fps | 309 | +| iterations | 9722 | +| time_elapsed | 32184 | +| total_timesteps | 9955328 | +| train/ | | +| approx_kl | 2.011887 | +| clip_fraction | 0.512 | +| clip_range | 0.2 | +| entropy_loss | -0.434 | +| explained_variance | -1.88 | +| learning_rate | 0.0001 | +| loss | -0.0978 | +| n_updates | 157740 | +| policy_gradient_loss | -0.0745 | +| value_loss | 0.000272 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.36e+03 | +| ep_rew_mean | 0.277 | +| time/ | | +| fps | 309 | +| iterations | 9723 | +| time_elapsed | 32187 | +| total_timesteps | 9956352 | +| train/ | | +| approx_kl | 1.4969144 | +| clip_fraction | 0.482 | +| clip_range | 0.2 | +| entropy_loss | -0.42 | +| explained_variance | -2.22 | +| learning_rate | 0.0001 | +| loss | -0.073 | +| n_updates | 157750 | +| policy_gradient_loss | -0.0732 | +| value_loss | 0.000379 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.36e+03 | +| ep_rew_mean | 0.276 | +| time/ | | +| fps | 309 | +| iterations | 9724 | +| time_elapsed | 32190 | +| total_timesteps | 9957376 | +| train/ | | +| approx_kl | 2.0822678 | +| clip_fraction | 0.508 | +| clip_range | 0.2 | +| entropy_loss | -0.424 | +| explained_variance | -1.48 | +| learning_rate | 0.0001 | +| loss | -0.123 | +| n_updates | 157760 | +| policy_gradient_loss | -0.0769 | +| value_loss | 0.000835 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.36e+03 | +| ep_rew_mean | 0.276 | +| time/ | | +| fps | 309 | +| iterations | 9725 | +| time_elapsed | 32194 | +| total_timesteps | 9958400 | +| train/ | | +| approx_kl | 1.9788744 | +| clip_fraction | 0.533 | +| clip_range | 0.2 | +| entropy_loss | -0.448 | +| explained_variance | -2.28 | +| learning_rate | 0.0001 | +| loss | -0.106 | +| n_updates | 157770 | +| policy_gradient_loss | -0.0736 | +| value_loss | 0.00037 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.36e+03 | +| ep_rew_mean | 0.276 | +| time/ | | +| fps | 309 | +| iterations | 9726 | +| time_elapsed | 32197 | +| total_timesteps | 9959424 | +| train/ | | +| approx_kl | 1.8235593 | +| clip_fraction | 0.543 | +| clip_range | 0.2 | +| entropy_loss | -0.498 | +| explained_variance | -2.9 | +| learning_rate | 0.0001 | +| loss | -0.0578 | +| n_updates | 157780 | +| policy_gradient_loss | -0.0777 | +| value_loss | 0.000286 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.37e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 309 | +| iterations | 9727 | +| time_elapsed | 32200 | +| total_timesteps | 9960448 | +| train/ | | +| approx_kl | 1.9535232 | +| clip_fraction | 0.511 | +| clip_range | 0.2 | +| entropy_loss | -0.437 | +| explained_variance | -0.745 | +| learning_rate | 0.0001 | +| loss | -0.0843 | +| n_updates | 157790 | +| policy_gradient_loss | -0.0712 | +| value_loss | 0.000547 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.37e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 309 | +| iterations | 9728 | +| time_elapsed | 32203 | +| total_timesteps | 9961472 | +| train/ | | +| approx_kl | 2.7539098 | +| clip_fraction | 0.526 | +| clip_range | 0.2 | +| entropy_loss | -0.488 | +| explained_variance | -4.21 | +| learning_rate | 0.0001 | +| loss | -0.116 | +| n_updates | 157800 | +| policy_gradient_loss | -0.078 | +| value_loss | 0.000504 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.37e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 309 | +| iterations | 9729 | +| time_elapsed | 32207 | +| total_timesteps | 9962496 | +| train/ | | +| approx_kl | 1.7567644 | +| clip_fraction | 0.529 | +| clip_range | 0.2 | +| entropy_loss | -0.496 | +| explained_variance | -2.31 | +| learning_rate | 0.0001 | +| loss | -0.0891 | +| n_updates | 157810 | +| policy_gradient_loss | -0.0737 | +| value_loss | 0.000322 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.36e+03 | +| ep_rew_mean | 0.271 | +| time/ | | +| fps | 309 | +| iterations | 9730 | +| time_elapsed | 32210 | +| total_timesteps | 9963520 | +| train/ | | +| approx_kl | 2.093123 | +| clip_fraction | 0.515 | +| clip_range | 0.2 | +| entropy_loss | -0.405 | +| explained_variance | -2.62 | +| learning_rate | 0.0001 | +| loss | -0.092 | +| n_updates | 157820 | +| policy_gradient_loss | -0.0774 | +| value_loss | 0.000323 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.36e+03 | +| ep_rew_mean | 0.271 | +| time/ | | +| fps | 309 | +| iterations | 9731 | +| time_elapsed | 32213 | +| total_timesteps | 9964544 | +| train/ | | +| approx_kl | 2.5207293 | +| clip_fraction | 0.505 | +| clip_range | 0.2 | +| entropy_loss | -0.418 | +| explained_variance | -0.945 | +| learning_rate | 0.0001 | +| loss | -0.114 | +| n_updates | 157830 | +| policy_gradient_loss | -0.0691 | +| value_loss | 0.000585 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.36e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 309 | +| iterations | 9732 | +| time_elapsed | 32217 | +| total_timesteps | 9965568 | +| train/ | | +| approx_kl | 1.7555903 | +| clip_fraction | 0.514 | +| clip_range | 0.2 | +| entropy_loss | -0.495 | +| explained_variance | -1.3 | +| learning_rate | 0.0001 | +| loss | -0.0905 | +| n_updates | 157840 | +| policy_gradient_loss | -0.0703 | +| value_loss | 0.000461 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.36e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 309 | +| iterations | 9733 | +| time_elapsed | 32220 | +| total_timesteps | 9966592 | +| train/ | | +| approx_kl | 2.1221871 | +| clip_fraction | 0.505 | +| clip_range | 0.2 | +| entropy_loss | -0.468 | +| explained_variance | -3.05 | +| learning_rate | 0.0001 | +| loss | -0.0923 | +| n_updates | 157850 | +| policy_gradient_loss | -0.072 | +| value_loss | 0.000267 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.37e+03 | +| ep_rew_mean | 0.277 | +| time/ | | +| fps | 309 | +| iterations | 9734 | +| time_elapsed | 32223 | +| total_timesteps | 9967616 | +| train/ | | +| approx_kl | 2.0033731 | +| clip_fraction | 0.508 | +| clip_range | 0.2 | +| entropy_loss | -0.439 | +| explained_variance | -1.34 | +| learning_rate | 0.0001 | +| loss | -0.0644 | +| n_updates | 157860 | +| policy_gradient_loss | -0.0693 | +| value_loss | 0.000433 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.37e+03 | +| ep_rew_mean | 0.277 | +| time/ | | +| fps | 309 | +| iterations | 9735 | +| time_elapsed | 32227 | +| total_timesteps | 9968640 | +| train/ | | +| approx_kl | 1.9032757 | +| clip_fraction | 0.513 | +| clip_range | 0.2 | +| entropy_loss | -0.463 | +| explained_variance | -1.56 | +| learning_rate | 0.0001 | +| loss | -0.0991 | +| n_updates | 157870 | +| policy_gradient_loss | -0.0709 | +| value_loss | 0.000925 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.37e+03 | +| ep_rew_mean | 0.277 | +| time/ | | +| fps | 309 | +| iterations | 9736 | +| time_elapsed | 32230 | +| total_timesteps | 9969664 | +| train/ | | +| approx_kl | 2.3280523 | +| clip_fraction | 0.505 | +| clip_range | 0.2 | +| entropy_loss | -0.422 | +| explained_variance | -2.98 | +| learning_rate | 0.0001 | +| loss | -0.0767 | +| n_updates | 157880 | +| policy_gradient_loss | -0.0713 | +| value_loss | 0.00044 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.38e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 309 | +| iterations | 9737 | +| time_elapsed | 32234 | +| total_timesteps | 9970688 | +| train/ | | +| approx_kl | 4.3560333 | +| clip_fraction | 0.515 | +| clip_range | 0.2 | +| entropy_loss | -0.434 | +| explained_variance | -0.981 | +| learning_rate | 0.0001 | +| loss | -0.0964 | +| n_updates | 157890 | +| policy_gradient_loss | -0.0676 | +| value_loss | 0.00045 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.38e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 309 | +| iterations | 9738 | +| time_elapsed | 32237 | +| total_timesteps | 9971712 | +| train/ | | +| approx_kl | 3.1391685 | +| clip_fraction | 0.521 | +| clip_range | 0.2 | +| entropy_loss | -0.43 | +| explained_variance | -3.68 | +| learning_rate | 0.0001 | +| loss | -0.0905 | +| n_updates | 157900 | +| policy_gradient_loss | -0.0738 | +| value_loss | 0.000209 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.38e+03 | +| ep_rew_mean | 0.278 | +| time/ | | +| fps | 309 | +| iterations | 9739 | +| time_elapsed | 32240 | +| total_timesteps | 9972736 | +| train/ | | +| approx_kl | 1.9451959 | +| clip_fraction | 0.537 | +| clip_range | 0.2 | +| entropy_loss | -0.449 | +| explained_variance | -0.804 | +| learning_rate | 0.0001 | +| loss | -0.0879 | +| n_updates | 157910 | +| policy_gradient_loss | -0.0805 | +| value_loss | 0.000223 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.38e+03 | +| ep_rew_mean | 0.278 | +| time/ | | +| fps | 309 | +| iterations | 9740 | +| time_elapsed | 32244 | +| total_timesteps | 9973760 | +| train/ | | +| approx_kl | 2.0141668 | +| clip_fraction | 0.524 | +| clip_range | 0.2 | +| entropy_loss | -0.463 | +| explained_variance | -0.734 | +| learning_rate | 0.0001 | +| loss | -0.1 | +| n_updates | 157920 | +| policy_gradient_loss | -0.067 | +| value_loss | 0.000342 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.38e+03 | +| ep_rew_mean | 0.278 | +| time/ | | +| fps | 309 | +| iterations | 9741 | +| time_elapsed | 32247 | +| total_timesteps | 9974784 | +| train/ | | +| approx_kl | 1.7190349 | +| clip_fraction | 0.527 | +| clip_range | 0.2 | +| entropy_loss | -0.497 | +| explained_variance | -2.21 | +| learning_rate | 0.0001 | +| loss | -0.1 | +| n_updates | 157930 | +| policy_gradient_loss | -0.0753 | +| value_loss | 0.000334 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.39e+03 | +| ep_rew_mean | 0.276 | +| time/ | | +| fps | 309 | +| iterations | 9742 | +| time_elapsed | 32251 | +| total_timesteps | 9975808 | +| train/ | | +| approx_kl | 2.0713947 | +| clip_fraction | 0.514 | +| clip_range | 0.2 | +| entropy_loss | -0.449 | +| explained_variance | -2.2 | +| learning_rate | 0.0001 | +| loss | -0.0831 | +| n_updates | 157940 | +| policy_gradient_loss | -0.0708 | +| value_loss | 0.000513 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.39e+03 | +| ep_rew_mean | 0.276 | +| time/ | | +| fps | 309 | +| iterations | 9743 | +| time_elapsed | 32254 | +| total_timesteps | 9976832 | +| train/ | | +| approx_kl | 1.6792467 | +| clip_fraction | 0.488 | +| clip_range | 0.2 | +| entropy_loss | -0.445 | +| explained_variance | -1.15 | +| learning_rate | 0.0001 | +| loss | -0.0876 | +| n_updates | 157950 | +| policy_gradient_loss | -0.0648 | +| value_loss | 0.000434 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.38e+03 | +| ep_rew_mean | 0.277 | +| time/ | | +| fps | 309 | +| iterations | 9744 | +| time_elapsed | 32257 | +| total_timesteps | 9977856 | +| train/ | | +| approx_kl | 1.8991386 | +| clip_fraction | 0.541 | +| clip_range | 0.2 | +| entropy_loss | -0.571 | +| explained_variance | -1.32 | +| learning_rate | 0.0001 | +| loss | -0.0808 | +| n_updates | 157960 | +| policy_gradient_loss | -0.0712 | +| value_loss | 0.000619 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.38e+03 | +| ep_rew_mean | 0.277 | +| time/ | | +| fps | 309 | +| iterations | 9745 | +| time_elapsed | 32261 | +| total_timesteps | 9978880 | +| train/ | | +| approx_kl | 2.1290588 | +| clip_fraction | 0.514 | +| clip_range | 0.2 | +| entropy_loss | -0.438 | +| explained_variance | -0.972 | +| learning_rate | 0.0001 | +| loss | -0.113 | +| n_updates | 157970 | +| policy_gradient_loss | -0.0782 | +| value_loss | 0.000515 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.38e+03 | +| ep_rew_mean | 0.277 | +| time/ | | +| fps | 309 | +| iterations | 9746 | +| time_elapsed | 32264 | +| total_timesteps | 9979904 | +| train/ | | +| approx_kl | 3.2814846 | +| clip_fraction | 0.52 | +| clip_range | 0.2 | +| entropy_loss | -0.408 | +| explained_variance | -2.47 | +| learning_rate | 0.0001 | +| loss | -0.107 | +| n_updates | 157980 | +| policy_gradient_loss | -0.0784 | +| value_loss | 0.000423 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.38e+03 | +| ep_rew_mean | 0.277 | +| time/ | | +| fps | 309 | +| iterations | 9747 | +| time_elapsed | 32268 | +| total_timesteps | 9980928 | +| train/ | | +| approx_kl | 2.280479 | +| clip_fraction | 0.514 | +| clip_range | 0.2 | +| entropy_loss | -0.463 | +| explained_variance | -10 | +| learning_rate | 0.0001 | +| loss | -0.0972 | +| n_updates | 157990 | +| policy_gradient_loss | -0.0773 | +| value_loss | 0.000197 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.38e+03 | +| ep_rew_mean | 0.277 | +| time/ | | +| fps | 309 | +| iterations | 9748 | +| time_elapsed | 32271 | +| total_timesteps | 9981952 | +| train/ | | +| approx_kl | 2.2932537 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.416 | +| explained_variance | -4.78 | +| learning_rate | 0.0001 | +| loss | -0.0863 | +| n_updates | 158000 | +| policy_gradient_loss | -0.0727 | +| value_loss | 3.98e-05 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.38e+03 | +| ep_rew_mean | 0.277 | +| time/ | | +| fps | 309 | +| iterations | 9749 | +| time_elapsed | 32275 | +| total_timesteps | 9982976 | +| train/ | | +| approx_kl | 1.9574353 | +| clip_fraction | 0.486 | +| clip_range | 0.2 | +| entropy_loss | -0.388 | +| explained_variance | -0.325 | +| learning_rate | 0.0001 | +| loss | -0.0802 | +| n_updates | 158010 | +| policy_gradient_loss | -0.0562 | +| value_loss | 0.000275 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.39e+03 | +| ep_rew_mean | 0.276 | +| time/ | | +| fps | 309 | +| iterations | 9750 | +| time_elapsed | 32278 | +| total_timesteps | 9984000 | +| train/ | | +| approx_kl | 7.9551883 | +| clip_fraction | 0.535 | +| clip_range | 0.2 | +| entropy_loss | -0.422 | +| explained_variance | -1.76 | +| learning_rate | 0.0001 | +| loss | -0.0799 | +| n_updates | 158020 | +| policy_gradient_loss | -0.0791 | +| value_loss | 0.000578 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.39e+03 | +| ep_rew_mean | 0.276 | +| time/ | | +| fps | 309 | +| iterations | 9751 | +| time_elapsed | 32282 | +| total_timesteps | 9985024 | +| train/ | | +| approx_kl | 1.9658992 | +| clip_fraction | 0.496 | +| clip_range | 0.2 | +| entropy_loss | -0.464 | +| explained_variance | -2.5 | +| learning_rate | 0.0001 | +| loss | -0.0932 | +| n_updates | 158030 | +| policy_gradient_loss | -0.0733 | +| value_loss | 0.000332 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.39e+03 | +| ep_rew_mean | 0.276 | +| time/ | | +| fps | 309 | +| iterations | 9752 | +| time_elapsed | 32285 | +| total_timesteps | 9986048 | +| train/ | | +| approx_kl | 1.9886228 | +| clip_fraction | 0.511 | +| clip_range | 0.2 | +| entropy_loss | -0.419 | +| explained_variance | -1.35 | +| learning_rate | 0.0001 | +| loss | -0.0965 | +| n_updates | 158040 | +| policy_gradient_loss | -0.0716 | +| value_loss | 0.000408 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.39e+03 | +| ep_rew_mean | 0.274 | +| time/ | | +| fps | 309 | +| iterations | 9753 | +| time_elapsed | 32289 | +| total_timesteps | 9987072 | +| train/ | | +| approx_kl | 1.9249879 | +| clip_fraction | 0.538 | +| clip_range | 0.2 | +| entropy_loss | -0.477 | +| explained_variance | -4.82 | +| learning_rate | 0.0001 | +| loss | -0.0947 | +| n_updates | 158050 | +| policy_gradient_loss | -0.0752 | +| value_loss | 0.000274 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.39e+03 | +| ep_rew_mean | 0.274 | +| time/ | | +| fps | 309 | +| iterations | 9754 | +| time_elapsed | 32292 | +| total_timesteps | 9988096 | +| train/ | | +| approx_kl | 2.3304036 | +| clip_fraction | 0.493 | +| clip_range | 0.2 | +| entropy_loss | -0.395 | +| explained_variance | -1.18 | +| learning_rate | 0.0001 | +| loss | -0.0815 | +| n_updates | 158060 | +| policy_gradient_loss | -0.0631 | +| value_loss | 0.000386 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.38e+03 | +| ep_rew_mean | 0.272 | +| time/ | | +| fps | 309 | +| iterations | 9755 | +| time_elapsed | 32295 | +| total_timesteps | 9989120 | +| train/ | | +| approx_kl | 1.7039711 | +| clip_fraction | 0.528 | +| clip_range | 0.2 | +| entropy_loss | -0.501 | +| explained_variance | -2.68 | +| learning_rate | 0.0001 | +| loss | -0.0903 | +| n_updates | 158070 | +| policy_gradient_loss | -0.0756 | +| value_loss | 0.000435 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.38e+03 | +| ep_rew_mean | 0.272 | +| time/ | | +| fps | 309 | +| iterations | 9756 | +| time_elapsed | 32299 | +| total_timesteps | 9990144 | +| train/ | | +| approx_kl | 1.6093377 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.443 | +| explained_variance | -0.687 | +| learning_rate | 0.0001 | +| loss | -0.0761 | +| n_updates | 158080 | +| policy_gradient_loss | -0.071 | +| value_loss | 0.000585 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.39e+03 | +| ep_rew_mean | 0.27 | +| time/ | | +| fps | 309 | +| iterations | 9757 | +| time_elapsed | 32302 | +| total_timesteps | 9991168 | +| train/ | | +| approx_kl | 1.4421185 | +| clip_fraction | 0.498 | +| clip_range | 0.2 | +| entropy_loss | -0.483 | +| explained_variance | -0.957 | +| learning_rate | 0.0001 | +| loss | -0.109 | +| n_updates | 158090 | +| policy_gradient_loss | -0.0682 | +| value_loss | 0.000433 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.39e+03 | +| ep_rew_mean | 0.27 | +| time/ | | +| fps | 309 | +| iterations | 9758 | +| time_elapsed | 32306 | +| total_timesteps | 9992192 | +| train/ | | +| approx_kl | 1.4800669 | +| clip_fraction | 0.457 | +| clip_range | 0.2 | +| entropy_loss | -0.443 | +| explained_variance | -2.65 | +| learning_rate | 0.0001 | +| loss | -0.0954 | +| n_updates | 158100 | +| policy_gradient_loss | -0.0592 | +| value_loss | 0.00017 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.39e+03 | +| ep_rew_mean | 0.27 | +| time/ | | +| fps | 309 | +| iterations | 9759 | +| time_elapsed | 32309 | +| total_timesteps | 9993216 | +| train/ | | +| approx_kl | 2.5148468 | +| clip_fraction | 0.569 | +| clip_range | 0.2 | +| entropy_loss | -0.546 | +| explained_variance | -3.05 | +| learning_rate | 0.0001 | +| loss | -0.0929 | +| n_updates | 158110 | +| policy_gradient_loss | -0.0787 | +| value_loss | 0.0002 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.39e+03 | +| ep_rew_mean | 0.27 | +| time/ | | +| fps | 309 | +| iterations | 9760 | +| time_elapsed | 32312 | +| total_timesteps | 9994240 | +| train/ | | +| approx_kl | 2.4634304 | +| clip_fraction | 0.514 | +| clip_range | 0.2 | +| entropy_loss | -0.403 | +| explained_variance | -7.33 | +| learning_rate | 0.0001 | +| loss | -0.0729 | +| n_updates | 158120 | +| policy_gradient_loss | -0.078 | +| value_loss | 0.000399 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.42e+03 | +| ep_rew_mean | 0.268 | +| time/ | | +| fps | 309 | +| iterations | 9761 | +| time_elapsed | 32315 | +| total_timesteps | 9995264 | +| train/ | | +| approx_kl | 2.0819225 | +| clip_fraction | 0.509 | +| clip_range | 0.2 | +| entropy_loss | -0.425 | +| explained_variance | -1.83 | +| learning_rate | 0.0001 | +| loss | -0.097 | +| n_updates | 158130 | +| policy_gradient_loss | -0.0739 | +| value_loss | 0.000304 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.42e+03 | +| ep_rew_mean | 0.268 | +| time/ | | +| fps | 309 | +| iterations | 9762 | +| time_elapsed | 32318 | +| total_timesteps | 9996288 | +| train/ | | +| approx_kl | 1.9275212 | +| clip_fraction | 0.494 | +| clip_range | 0.2 | +| entropy_loss | -0.425 | +| explained_variance | -1.58 | +| learning_rate | 0.0001 | +| loss | -0.082 | +| n_updates | 158140 | +| policy_gradient_loss | -0.0699 | +| value_loss | 0.000474 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.41e+03 | +| ep_rew_mean | 0.266 | +| time/ | | +| fps | 309 | +| iterations | 9763 | +| time_elapsed | 32322 | +| total_timesteps | 9997312 | +| train/ | | +| approx_kl | 2.705143 | +| clip_fraction | 0.5 | +| clip_range | 0.2 | +| entropy_loss | -0.399 | +| explained_variance | -4.07 | +| learning_rate | 0.0001 | +| loss | -0.0977 | +| n_updates | 158150 | +| policy_gradient_loss | -0.0806 | +| value_loss | 0.000452 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.41e+03 | +| ep_rew_mean | 0.266 | +| time/ | | +| fps | 309 | +| iterations | 9764 | +| time_elapsed | 32325 | +| total_timesteps | 9998336 | +| train/ | | +| approx_kl | 1.6900434 | +| clip_fraction | 0.506 | +| clip_range | 0.2 | +| entropy_loss | -0.486 | +| explained_variance | -1.14 | +| learning_rate | 0.0001 | +| loss | -0.0911 | +| n_updates | 158160 | +| policy_gradient_loss | -0.0782 | +| value_loss | 0.000379 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.41e+03 | +| ep_rew_mean | 0.272 | +| time/ | | +| fps | 309 | +| iterations | 9765 | +| time_elapsed | 32329 | +| total_timesteps | 9999360 | +| train/ | | +| approx_kl | 1.9196101 | +| clip_fraction | 0.525 | +| clip_range | 0.2 | +| entropy_loss | -0.444 | +| explained_variance | -0.84 | +| learning_rate | 0.0001 | +| loss | -0.0966 | +| n_updates | 158170 | +| policy_gradient_loss | -0.0759 | +| value_loss | 0.000715 | +--------------------------------------- + +Current state: Champion.Level2.RyuVsKen +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.41e+03 | +| ep_rew_mean | 0.272 | +| time/ | | +| fps | 309 | +| iterations | 9766 | +| time_elapsed | 32332 | +| total_timesteps | 10000384 | +| train/ | | +| approx_kl | 2.0557296 | +| clip_fraction | 0.507 | +| clip_range | 0.2 | +| entropy_loss | -0.438 | +| explained_variance | -4.58 | +| learning_rate | 0.0001 | +| loss | -0.111 | +| n_updates | 158180 | +| policy_gradient_loss | -0.076 | +| value_loss | 0.00026 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.41e+03 | +| ep_rew_mean | 0.272 | +| time/ | | +| fps | 309 | +| iterations | 9767 | +| time_elapsed | 32336 | +| total_timesteps | 10001408 | +| train/ | | +| approx_kl | 1.7463712 | +| clip_fraction | 0.512 | +| clip_range | 0.2 | +| entropy_loss | -0.473 | +| explained_variance | -3.04 | +| learning_rate | 0.0001 | +| loss | -0.0878 | +| n_updates | 158190 | +| policy_gradient_loss | -0.0738 | +| value_loss | 0.000134 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.41e+03 | +| ep_rew_mean | 0.266 | +| time/ | | +| fps | 309 | +| iterations | 9768 | +| time_elapsed | 32339 | +| total_timesteps | 10002432 | +| train/ | | +| approx_kl | 2.6748226 | +| clip_fraction | 0.517 | +| clip_range | 0.2 | +| entropy_loss | -0.437 | +| explained_variance | -4.7 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 158200 | +| policy_gradient_loss | -0.0811 | +| value_loss | 0.000133 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.41e+03 | +| ep_rew_mean | 0.266 | +| time/ | | +| fps | 309 | +| iterations | 9769 | +| time_elapsed | 32343 | +| total_timesteps | 10003456 | +| train/ | | +| approx_kl | 3.5878286 | +| clip_fraction | 0.501 | +| clip_range | 0.2 | +| entropy_loss | -0.462 | +| explained_variance | -0.244 | +| learning_rate | 0.0001 | +| loss | -0.0509 | +| n_updates | 158210 | +| policy_gradient_loss | -0.0504 | +| value_loss | 0.000526 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.41e+03 | +| ep_rew_mean | 0.266 | +| time/ | | +| fps | 309 | +| iterations | 9770 | +| time_elapsed | 32346 | +| total_timesteps | 10004480 | +| train/ | | +| approx_kl | 2.0173368 | +| clip_fraction | 0.54 | +| clip_range | 0.2 | +| entropy_loss | -0.494 | +| explained_variance | -4.39 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 158220 | +| policy_gradient_loss | -0.0785 | +| value_loss | 0.00047 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.41e+03 | +| ep_rew_mean | 0.266 | +| time/ | | +| fps | 309 | +| iterations | 9771 | +| time_elapsed | 32349 | +| total_timesteps | 10005504 | +| train/ | | +| approx_kl | 1.7782347 | +| clip_fraction | 0.489 | +| clip_range | 0.2 | +| entropy_loss | -0.422 | +| explained_variance | -6.5 | +| learning_rate | 0.0001 | +| loss | -0.0935 | +| n_updates | 158230 | +| policy_gradient_loss | -0.0755 | +| value_loss | 0.000413 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.4e+03 | +| ep_rew_mean | 0.265 | +| time/ | | +| fps | 309 | +| iterations | 9772 | +| time_elapsed | 32353 | +| total_timesteps | 10006528 | +| train/ | | +| approx_kl | 3.0147276 | +| clip_fraction | 0.532 | +| clip_range | 0.2 | +| entropy_loss | -0.495 | +| explained_variance | -0.397 | +| learning_rate | 0.0001 | +| loss | -0.094 | +| n_updates | 158240 | +| policy_gradient_loss | -0.0738 | +| value_loss | 0.000543 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.4e+03 | +| ep_rew_mean | 0.26 | +| time/ | | +| fps | 309 | +| iterations | 9773 | +| time_elapsed | 32356 | +| total_timesteps | 10007552 | +| train/ | | +| approx_kl | 3.6705906 | +| clip_fraction | 0.523 | +| clip_range | 0.2 | +| entropy_loss | -0.48 | +| explained_variance | -2.07 | +| learning_rate | 0.0001 | +| loss | -0.0842 | +| n_updates | 158250 | +| policy_gradient_loss | -0.0764 | +| value_loss | 0.000454 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.38e+03 | +| ep_rew_mean | 0.255 | +| time/ | | +| fps | 309 | +| iterations | 9774 | +| time_elapsed | 32359 | +| total_timesteps | 10008576 | +| train/ | | +| approx_kl | 2.2995067 | +| clip_fraction | 0.52 | +| clip_range | 0.2 | +| entropy_loss | -0.451 | +| explained_variance | -2.37 | +| learning_rate | 0.0001 | +| loss | -0.111 | +| n_updates | 158260 | +| policy_gradient_loss | -0.0815 | +| value_loss | 0.000315 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.38e+03 | +| ep_rew_mean | 0.255 | +| time/ | | +| fps | 309 | +| iterations | 9775 | +| time_elapsed | 32362 | +| total_timesteps | 10009600 | +| train/ | | +| approx_kl | 1.9090962 | +| clip_fraction | 0.496 | +| clip_range | 0.2 | +| entropy_loss | -0.484 | +| explained_variance | -0.663 | +| learning_rate | 0.0001 | +| loss | -0.0908 | +| n_updates | 158270 | +| policy_gradient_loss | -0.0749 | +| value_loss | 0.000429 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.38e+03 | +| ep_rew_mean | 0.253 | +| time/ | | +| fps | 309 | +| iterations | 9776 | +| time_elapsed | 32366 | +| total_timesteps | 10010624 | +| train/ | | +| approx_kl | 5.471398 | +| clip_fraction | 0.526 | +| clip_range | 0.2 | +| entropy_loss | -0.452 | +| explained_variance | -1.61 | +| learning_rate | 0.0001 | +| loss | -0.0822 | +| n_updates | 158280 | +| policy_gradient_loss | -0.0796 | +| value_loss | 0.000263 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.38e+03 | +| ep_rew_mean | 0.253 | +| time/ | | +| fps | 309 | +| iterations | 9777 | +| time_elapsed | 32369 | +| total_timesteps | 10011648 | +| train/ | | +| approx_kl | 2.075863 | +| clip_fraction | 0.509 | +| clip_range | 0.2 | +| entropy_loss | -0.432 | +| explained_variance | -1.41 | +| learning_rate | 0.0001 | +| loss | -0.0929 | +| n_updates | 158290 | +| policy_gradient_loss | -0.072 | +| value_loss | 0.000444 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.38e+03 | +| ep_rew_mean | 0.253 | +| time/ | | +| fps | 309 | +| iterations | 9778 | +| time_elapsed | 32372 | +| total_timesteps | 10012672 | +| train/ | | +| approx_kl | 1.9588394 | +| clip_fraction | 0.527 | +| clip_range | 0.2 | +| entropy_loss | -0.479 | +| explained_variance | -2.51 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 158300 | +| policy_gradient_loss | -0.0802 | +| value_loss | 0.000558 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.39e+03 | +| ep_rew_mean | 0.249 | +| time/ | | +| fps | 309 | +| iterations | 9779 | +| time_elapsed | 32376 | +| total_timesteps | 10013696 | +| train/ | | +| approx_kl | 1.99673 | +| clip_fraction | 0.54 | +| clip_range | 0.2 | +| entropy_loss | -0.571 | +| explained_variance | -1.74 | +| learning_rate | 0.0001 | +| loss | -0.0913 | +| n_updates | 158310 | +| policy_gradient_loss | -0.0743 | +| value_loss | 0.000426 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.38e+03 | +| ep_rew_mean | 0.246 | +| time/ | | +| fps | 309 | +| iterations | 9780 | +| time_elapsed | 32379 | +| total_timesteps | 10014720 | +| train/ | | +| approx_kl | 2.3202271 | +| clip_fraction | 0.515 | +| clip_range | 0.2 | +| entropy_loss | -0.46 | +| explained_variance | -1.85 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 158320 | +| policy_gradient_loss | -0.0749 | +| value_loss | 0.000298 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.37e+03 | +| ep_rew_mean | 0.239 | +| time/ | | +| fps | 309 | +| iterations | 9781 | +| time_elapsed | 32383 | +| total_timesteps | 10015744 | +| train/ | | +| approx_kl | 1.949141 | +| clip_fraction | 0.492 | +| clip_range | 0.2 | +| entropy_loss | -0.416 | +| explained_variance | -3.42 | +| learning_rate | 0.0001 | +| loss | -0.108 | +| n_updates | 158330 | +| policy_gradient_loss | -0.0747 | +| value_loss | 0.000303 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.37e+03 | +| ep_rew_mean | 0.239 | +| time/ | | +| fps | 309 | +| iterations | 9782 | +| time_elapsed | 32386 | +| total_timesteps | 10016768 | +| train/ | | +| approx_kl | 1.9105053 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.442 | +| explained_variance | -0.791 | +| learning_rate | 0.0001 | +| loss | -0.0858 | +| n_updates | 158340 | +| policy_gradient_loss | -0.0722 | +| value_loss | 0.000386 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.37e+03 | +| ep_rew_mean | 0.239 | +| time/ | | +| fps | 309 | +| iterations | 9783 | +| time_elapsed | 32390 | +| total_timesteps | 10017792 | +| train/ | | +| approx_kl | 1.6197586 | +| clip_fraction | 0.526 | +| clip_range | 0.2 | +| entropy_loss | -0.472 | +| explained_variance | -5.57 | +| learning_rate | 0.0001 | +| loss | -0.116 | +| n_updates | 158350 | +| policy_gradient_loss | -0.0828 | +| value_loss | 0.000203 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.38e+03 | +| ep_rew_mean | 0.236 | +| time/ | | +| fps | 309 | +| iterations | 9784 | +| time_elapsed | 32393 | +| total_timesteps | 10018816 | +| train/ | | +| approx_kl | 2.0878148 | +| clip_fraction | 0.519 | +| clip_range | 0.2 | +| entropy_loss | -0.457 | +| explained_variance | -2.73 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 158360 | +| policy_gradient_loss | -0.0741 | +| value_loss | 0.000293 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.37e+03 | +| ep_rew_mean | 0.234 | +| time/ | | +| fps | 309 | +| iterations | 9785 | +| time_elapsed | 32397 | +| total_timesteps | 10019840 | +| train/ | | +| approx_kl | 2.1757193 | +| clip_fraction | 0.542 | +| clip_range | 0.2 | +| entropy_loss | -0.454 | +| explained_variance | -1.61 | +| learning_rate | 0.0001 | +| loss | -0.121 | +| n_updates | 158370 | +| policy_gradient_loss | -0.0799 | +| value_loss | 0.000593 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.37e+03 | +| ep_rew_mean | 0.234 | +| time/ | | +| fps | 309 | +| iterations | 9786 | +| time_elapsed | 32400 | +| total_timesteps | 10020864 | +| train/ | | +| approx_kl | 1.8649002 | +| clip_fraction | 0.474 | +| clip_range | 0.2 | +| entropy_loss | -0.387 | +| explained_variance | -5.82 | +| learning_rate | 0.0001 | +| loss | -0.088 | +| n_updates | 158380 | +| policy_gradient_loss | -0.0689 | +| value_loss | 0.000349 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.35e+03 | +| ep_rew_mean | 0.233 | +| time/ | | +| fps | 309 | +| iterations | 9787 | +| time_elapsed | 32404 | +| total_timesteps | 10021888 | +| train/ | | +| approx_kl | 1.6662772 | +| clip_fraction | 0.505 | +| clip_range | 0.2 | +| entropy_loss | -0.462 | +| explained_variance | -0.624 | +| learning_rate | 0.0001 | +| loss | -0.11 | +| n_updates | 158390 | +| policy_gradient_loss | -0.0722 | +| value_loss | 0.000466 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.35e+03 | +| ep_rew_mean | 0.233 | +| time/ | | +| fps | 309 | +| iterations | 9788 | +| time_elapsed | 32407 | +| total_timesteps | 10022912 | +| train/ | | +| approx_kl | 2.143805 | +| clip_fraction | 0.507 | +| clip_range | 0.2 | +| entropy_loss | -0.439 | +| explained_variance | -1.74 | +| learning_rate | 0.0001 | +| loss | -0.105 | +| n_updates | 158400 | +| policy_gradient_loss | -0.0753 | +| value_loss | 0.000366 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.34e+03 | +| ep_rew_mean | 0.231 | +| time/ | | +| fps | 309 | +| iterations | 9789 | +| time_elapsed | 32410 | +| total_timesteps | 10023936 | +| train/ | | +| approx_kl | 2.2635098 | +| clip_fraction | 0.527 | +| clip_range | 0.2 | +| entropy_loss | -0.44 | +| explained_variance | -2.86 | +| learning_rate | 0.0001 | +| loss | -0.0974 | +| n_updates | 158410 | +| policy_gradient_loss | -0.0821 | +| value_loss | 0.000221 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.32e+03 | +| ep_rew_mean | 0.227 | +| time/ | | +| fps | 309 | +| iterations | 9790 | +| time_elapsed | 32414 | +| total_timesteps | 10024960 | +| train/ | | +| approx_kl | 2.589107 | +| clip_fraction | 0.491 | +| clip_range | 0.2 | +| entropy_loss | -0.389 | +| explained_variance | -1.37 | +| learning_rate | 0.0001 | +| loss | -0.0988 | +| n_updates | 158420 | +| policy_gradient_loss | -0.0773 | +| value_loss | 0.000693 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.32e+03 | +| ep_rew_mean | 0.227 | +| time/ | | +| fps | 309 | +| iterations | 9791 | +| time_elapsed | 32417 | +| total_timesteps | 10025984 | +| train/ | | +| approx_kl | 1.7266593 | +| clip_fraction | 0.501 | +| clip_range | 0.2 | +| entropy_loss | -0.479 | +| explained_variance | -1.7 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 158430 | +| policy_gradient_loss | -0.0786 | +| value_loss | 0.000329 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.32e+03 | +| ep_rew_mean | 0.227 | +| time/ | | +| fps | 309 | +| iterations | 9792 | +| time_elapsed | 32420 | +| total_timesteps | 10027008 | +| train/ | | +| approx_kl | 2.9931054 | +| clip_fraction | 0.539 | +| clip_range | 0.2 | +| entropy_loss | -0.466 | +| explained_variance | -0.858 | +| learning_rate | 0.0001 | +| loss | -0.0859 | +| n_updates | 158440 | +| policy_gradient_loss | -0.0724 | +| value_loss | 0.000399 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.33e+03 | +| ep_rew_mean | 0.226 | +| time/ | | +| fps | 309 | +| iterations | 9793 | +| time_elapsed | 32423 | +| total_timesteps | 10028032 | +| train/ | | +| approx_kl | 2.4863183 | +| clip_fraction | 0.496 | +| clip_range | 0.2 | +| entropy_loss | -0.387 | +| explained_variance | -13.4 | +| learning_rate | 0.0001 | +| loss | -0.108 | +| n_updates | 158450 | +| policy_gradient_loss | -0.0805 | +| value_loss | 0.000438 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.31e+03 | +| ep_rew_mean | 0.222 | +| time/ | | +| fps | 309 | +| iterations | 9794 | +| time_elapsed | 32427 | +| total_timesteps | 10029056 | +| train/ | | +| approx_kl | 1.757378 | +| clip_fraction | 0.518 | +| clip_range | 0.2 | +| entropy_loss | -0.417 | +| explained_variance | -4.01 | +| learning_rate | 0.0001 | +| loss | -0.0979 | +| n_updates | 158460 | +| policy_gradient_loss | -0.0799 | +| value_loss | 0.000583 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.31e+03 | +| ep_rew_mean | 0.222 | +| time/ | | +| fps | 309 | +| iterations | 9795 | +| time_elapsed | 32430 | +| total_timesteps | 10030080 | +| train/ | | +| approx_kl | 1.7049812 | +| clip_fraction | 0.508 | +| clip_range | 0.2 | +| entropy_loss | -0.483 | +| explained_variance | -2.25 | +| learning_rate | 0.0001 | +| loss | -0.0711 | +| n_updates | 158470 | +| policy_gradient_loss | -0.074 | +| value_loss | 0.000673 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.31e+03 | +| ep_rew_mean | 0.222 | +| time/ | | +| fps | 309 | +| iterations | 9796 | +| time_elapsed | 32433 | +| total_timesteps | 10031104 | +| train/ | | +| approx_kl | 2.067742 | +| clip_fraction | 0.58 | +| clip_range | 0.2 | +| entropy_loss | -0.582 | +| explained_variance | -1.18 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 158480 | +| policy_gradient_loss | -0.0758 | +| value_loss | 0.00034 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.31e+03 | +| ep_rew_mean | 0.224 | +| time/ | | +| fps | 309 | +| iterations | 9797 | +| time_elapsed | 32436 | +| total_timesteps | 10032128 | +| train/ | | +| approx_kl | 1.8490119 | +| clip_fraction | 0.534 | +| clip_range | 0.2 | +| entropy_loss | -0.501 | +| explained_variance | -8.02 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 158490 | +| policy_gradient_loss | -0.0823 | +| value_loss | 0.0002 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.31e+03 | +| ep_rew_mean | 0.216 | +| time/ | | +| fps | 309 | +| iterations | 9798 | +| time_elapsed | 32440 | +| total_timesteps | 10033152 | +| train/ | | +| approx_kl | 12.12476 | +| clip_fraction | 0.496 | +| clip_range | 0.2 | +| entropy_loss | -0.437 | +| explained_variance | -1.45 | +| learning_rate | 0.0001 | +| loss | -0.0694 | +| n_updates | 158500 | +| policy_gradient_loss | -0.0678 | +| value_loss | 0.000666 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.31e+03 | +| ep_rew_mean | 0.216 | +| time/ | | +| fps | 309 | +| iterations | 9799 | +| time_elapsed | 32443 | +| total_timesteps | 10034176 | +| train/ | | +| approx_kl | 1.9256285 | +| clip_fraction | 0.469 | +| clip_range | 0.2 | +| entropy_loss | -0.379 | +| explained_variance | -1.21 | +| learning_rate | 0.0001 | +| loss | -0.0922 | +| n_updates | 158510 | +| policy_gradient_loss | -0.0719 | +| value_loss | 0.00085 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.29e+03 | +| ep_rew_mean | 0.219 | +| time/ | | +| fps | 309 | +| iterations | 9800 | +| time_elapsed | 32446 | +| total_timesteps | 10035200 | +| train/ | | +| approx_kl | 1.981765 | +| clip_fraction | 0.532 | +| clip_range | 0.2 | +| entropy_loss | -0.434 | +| explained_variance | -2.74 | +| learning_rate | 0.0001 | +| loss | -0.109 | +| n_updates | 158520 | +| policy_gradient_loss | -0.0785 | +| value_loss | 0.000583 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.29e+03 | +| ep_rew_mean | 0.219 | +| time/ | | +| fps | 309 | +| iterations | 9801 | +| time_elapsed | 32450 | +| total_timesteps | 10036224 | +| train/ | | +| approx_kl | 2.5664744 | +| clip_fraction | 0.543 | +| clip_range | 0.2 | +| entropy_loss | -0.546 | +| explained_variance | -2.82 | +| learning_rate | 0.0001 | +| loss | -0.0965 | +| n_updates | 158530 | +| policy_gradient_loss | -0.0805 | +| value_loss | 0.000283 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.3e+03 | +| ep_rew_mean | 0.222 | +| time/ | | +| fps | 309 | +| iterations | 9802 | +| time_elapsed | 32453 | +| total_timesteps | 10037248 | +| train/ | | +| approx_kl | 4.011426 | +| clip_fraction | 0.532 | +| clip_range | 0.2 | +| entropy_loss | -0.534 | +| explained_variance | -1.38 | +| learning_rate | 0.0001 | +| loss | -0.106 | +| n_updates | 158540 | +| policy_gradient_loss | -0.0776 | +| value_loss | 0.000287 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.3e+03 | +| ep_rew_mean | 0.222 | +| time/ | | +| fps | 309 | +| iterations | 9803 | +| time_elapsed | 32457 | +| total_timesteps | 10038272 | +| train/ | | +| approx_kl | 1.9631289 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.435 | +| explained_variance | -1.62 | +| learning_rate | 0.0001 | +| loss | -0.0909 | +| n_updates | 158550 | +| policy_gradient_loss | -0.0676 | +| value_loss | 0.000335 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.29e+03 | +| ep_rew_mean | 0.228 | +| time/ | | +| fps | 309 | +| iterations | 9804 | +| time_elapsed | 32460 | +| total_timesteps | 10039296 | +| train/ | | +| approx_kl | 2.2725677 | +| clip_fraction | 0.487 | +| clip_range | 0.2 | +| entropy_loss | -0.398 | +| explained_variance | -1.07 | +| learning_rate | 0.0001 | +| loss | -0.0696 | +| n_updates | 158560 | +| policy_gradient_loss | -0.0701 | +| value_loss | 0.000559 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.28e+03 | +| ep_rew_mean | 0.229 | +| time/ | | +| fps | 309 | +| iterations | 9805 | +| time_elapsed | 32463 | +| total_timesteps | 10040320 | +| train/ | | +| approx_kl | 1.9264221 | +| clip_fraction | 0.474 | +| clip_range | 0.2 | +| entropy_loss | -0.415 | +| explained_variance | -1.16 | +| learning_rate | 0.0001 | +| loss | -0.0774 | +| n_updates | 158570 | +| policy_gradient_loss | -0.0693 | +| value_loss | 0.000695 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.28e+03 | +| ep_rew_mean | 0.229 | +| time/ | | +| fps | 309 | +| iterations | 9806 | +| time_elapsed | 32467 | +| total_timesteps | 10041344 | +| train/ | | +| approx_kl | 2.0983398 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.346 | +| explained_variance | -1.52 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 158580 | +| policy_gradient_loss | -0.0708 | +| value_loss | 0.000736 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.29e+03 | +| ep_rew_mean | 0.226 | +| time/ | | +| fps | 309 | +| iterations | 9807 | +| time_elapsed | 32470 | +| total_timesteps | 10042368 | +| train/ | | +| approx_kl | 2.6002188 | +| clip_fraction | 0.543 | +| clip_range | 0.2 | +| entropy_loss | -0.464 | +| explained_variance | -20.7 | +| learning_rate | 0.0001 | +| loss | -0.115 | +| n_updates | 158590 | +| policy_gradient_loss | -0.0866 | +| value_loss | 0.000292 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.29e+03 | +| ep_rew_mean | 0.226 | +| time/ | | +| fps | 309 | +| iterations | 9808 | +| time_elapsed | 32474 | +| total_timesteps | 10043392 | +| train/ | | +| approx_kl | 1.8297763 | +| clip_fraction | 0.519 | +| clip_range | 0.2 | +| entropy_loss | -0.52 | +| explained_variance | -1.5 | +| learning_rate | 0.0001 | +| loss | -0.118 | +| n_updates | 158600 | +| policy_gradient_loss | -0.0686 | +| value_loss | 0.000211 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.29e+03 | +| ep_rew_mean | 0.224 | +| time/ | | +| fps | 309 | +| iterations | 9809 | +| time_elapsed | 32477 | +| total_timesteps | 10044416 | +| train/ | | +| approx_kl | 2.0572915 | +| clip_fraction | 0.505 | +| clip_range | 0.2 | +| entropy_loss | -0.396 | +| explained_variance | -1.42 | +| learning_rate | 0.0001 | +| loss | -0.0862 | +| n_updates | 158610 | +| policy_gradient_loss | -0.0687 | +| value_loss | 0.000312 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.27e+03 | +| ep_rew_mean | 0.219 | +| time/ | | +| fps | 309 | +| iterations | 9810 | +| time_elapsed | 32480 | +| total_timesteps | 10045440 | +| train/ | | +| approx_kl | 3.1104689 | +| clip_fraction | 0.499 | +| clip_range | 0.2 | +| entropy_loss | -0.407 | +| explained_variance | -1.7 | +| learning_rate | 0.0001 | +| loss | -0.115 | +| n_updates | 158620 | +| policy_gradient_loss | -0.0759 | +| value_loss | 0.000376 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.27e+03 | +| ep_rew_mean | 0.219 | +| time/ | | +| fps | 309 | +| iterations | 9811 | +| time_elapsed | 32484 | +| total_timesteps | 10046464 | +| train/ | | +| approx_kl | 2.1244693 | +| clip_fraction | 0.499 | +| clip_range | 0.2 | +| entropy_loss | -0.431 | +| explained_variance | -0.895 | +| learning_rate | 0.0001 | +| loss | -0.0602 | +| n_updates | 158630 | +| policy_gradient_loss | -0.0698 | +| value_loss | 0.000491 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.26e+03 | +| ep_rew_mean | 0.218 | +| time/ | | +| fps | 309 | +| iterations | 9812 | +| time_elapsed | 32487 | +| total_timesteps | 10047488 | +| train/ | | +| approx_kl | 2.0034494 | +| clip_fraction | 0.518 | +| clip_range | 0.2 | +| entropy_loss | -0.433 | +| explained_variance | -1.93 | +| learning_rate | 0.0001 | +| loss | -0.112 | +| n_updates | 158640 | +| policy_gradient_loss | -0.0774 | +| value_loss | 0.000447 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.26e+03 | +| ep_rew_mean | 0.218 | +| time/ | | +| fps | 309 | +| iterations | 9813 | +| time_elapsed | 32490 | +| total_timesteps | 10048512 | +| train/ | | +| approx_kl | 2.265259 | +| clip_fraction | 0.516 | +| clip_range | 0.2 | +| entropy_loss | -0.43 | +| explained_variance | -1.04 | +| learning_rate | 0.0001 | +| loss | -0.106 | +| n_updates | 158650 | +| policy_gradient_loss | -0.0551 | +| value_loss | 0.000537 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.26e+03 | +| ep_rew_mean | 0.221 | +| time/ | | +| fps | 309 | +| iterations | 9814 | +| time_elapsed | 32494 | +| total_timesteps | 10049536 | +| train/ | | +| approx_kl | 2.3146887 | +| clip_fraction | 0.518 | +| clip_range | 0.2 | +| entropy_loss | -0.435 | +| explained_variance | -2.28 | +| learning_rate | 0.0001 | +| loss | -0.114 | +| n_updates | 158660 | +| policy_gradient_loss | -0.0772 | +| value_loss | 0.000567 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.26e+03 | +| ep_rew_mean | 0.221 | +| time/ | | +| fps | 309 | +| iterations | 9815 | +| time_elapsed | 32497 | +| total_timesteps | 10050560 | +| train/ | | +| approx_kl | 3.2316592 | +| clip_fraction | 0.537 | +| clip_range | 0.2 | +| entropy_loss | -0.471 | +| explained_variance | -1.11 | +| learning_rate | 0.0001 | +| loss | -0.112 | +| n_updates | 158670 | +| policy_gradient_loss | -0.08 | +| value_loss | 0.000508 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.25e+03 | +| ep_rew_mean | 0.223 | +| time/ | | +| fps | 309 | +| iterations | 9816 | +| time_elapsed | 32500 | +| total_timesteps | 10051584 | +| train/ | | +| approx_kl | 2.1905665 | +| clip_fraction | 0.559 | +| clip_range | 0.2 | +| entropy_loss | -0.501 | +| explained_variance | -1.54 | +| learning_rate | 0.0001 | +| loss | -0.108 | +| n_updates | 158680 | +| policy_gradient_loss | -0.0793 | +| value_loss | 0.000392 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.24e+03 | +| ep_rew_mean | 0.222 | +| time/ | | +| fps | 309 | +| iterations | 9817 | +| time_elapsed | 32504 | +| total_timesteps | 10052608 | +| train/ | | +| approx_kl | 2.5058703 | +| clip_fraction | 0.533 | +| clip_range | 0.2 | +| entropy_loss | -0.44 | +| explained_variance | -1.53 | +| learning_rate | 0.0001 | +| loss | -0.0935 | +| n_updates | 158690 | +| policy_gradient_loss | -0.0772 | +| value_loss | 0.000419 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.24e+03 | +| ep_rew_mean | 0.222 | +| time/ | | +| fps | 309 | +| iterations | 9818 | +| time_elapsed | 32507 | +| total_timesteps | 10053632 | +| train/ | | +| approx_kl | 2.7221467 | +| clip_fraction | 0.529 | +| clip_range | 0.2 | +| entropy_loss | -0.43 | +| explained_variance | -1.33 | +| learning_rate | 0.0001 | +| loss | -0.0903 | +| n_updates | 158700 | +| policy_gradient_loss | -0.0766 | +| value_loss | 0.000563 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.24e+03 | +| ep_rew_mean | 0.217 | +| time/ | | +| fps | 309 | +| iterations | 9819 | +| time_elapsed | 32511 | +| total_timesteps | 10054656 | +| train/ | | +| approx_kl | 1.8727245 | +| clip_fraction | 0.519 | +| clip_range | 0.2 | +| entropy_loss | -0.409 | +| explained_variance | -4.4 | +| learning_rate | 0.0001 | +| loss | -0.097 | +| n_updates | 158710 | +| policy_gradient_loss | -0.0762 | +| value_loss | 0.000473 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.24e+03 | +| ep_rew_mean | 0.217 | +| time/ | | +| fps | 309 | +| iterations | 9820 | +| time_elapsed | 32514 | +| total_timesteps | 10055680 | +| train/ | | +| approx_kl | 2.3210225 | +| clip_fraction | 0.489 | +| clip_range | 0.2 | +| entropy_loss | -0.392 | +| explained_variance | -0.848 | +| learning_rate | 0.0001 | +| loss | -0.0822 | +| n_updates | 158720 | +| policy_gradient_loss | -0.0743 | +| value_loss | 0.000519 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.25e+03 | +| ep_rew_mean | 0.217 | +| time/ | | +| fps | 309 | +| iterations | 9821 | +| time_elapsed | 32518 | +| total_timesteps | 10056704 | +| train/ | | +| approx_kl | 2.6098192 | +| clip_fraction | 0.526 | +| clip_range | 0.2 | +| entropy_loss | -0.461 | +| explained_variance | -2.95 | +| learning_rate | 0.0001 | +| loss | -0.126 | +| n_updates | 158730 | +| policy_gradient_loss | -0.0792 | +| value_loss | 0.000235 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.25e+03 | +| ep_rew_mean | 0.217 | +| time/ | | +| fps | 309 | +| iterations | 9822 | +| time_elapsed | 32521 | +| total_timesteps | 10057728 | +| train/ | | +| approx_kl | 2.0206666 | +| clip_fraction | 0.516 | +| clip_range | 0.2 | +| entropy_loss | -0.43 | +| explained_variance | -1.63 | +| learning_rate | 0.0001 | +| loss | -0.0888 | +| n_updates | 158740 | +| policy_gradient_loss | -0.0747 | +| value_loss | 0.000311 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.24e+03 | +| ep_rew_mean | 0.218 | +| time/ | | +| fps | 309 | +| iterations | 9823 | +| time_elapsed | 32525 | +| total_timesteps | 10058752 | +| train/ | | +| approx_kl | 1.9090073 | +| clip_fraction | 0.497 | +| clip_range | 0.2 | +| entropy_loss | -0.432 | +| explained_variance | -0.78 | +| learning_rate | 0.0001 | +| loss | -0.117 | +| n_updates | 158750 | +| policy_gradient_loss | -0.0727 | +| value_loss | 0.000279 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.24e+03 | +| ep_rew_mean | 0.218 | +| time/ | | +| fps | 309 | +| iterations | 9824 | +| time_elapsed | 32528 | +| total_timesteps | 10059776 | +| train/ | | +| approx_kl | 2.072137 | +| clip_fraction | 0.505 | +| clip_range | 0.2 | +| entropy_loss | -0.469 | +| explained_variance | -2.44 | +| learning_rate | 0.0001 | +| loss | -0.0688 | +| n_updates | 158760 | +| policy_gradient_loss | -0.0722 | +| value_loss | 0.000238 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.24e+03 | +| ep_rew_mean | 0.217 | +| time/ | | +| fps | 309 | +| iterations | 9825 | +| time_elapsed | 32531 | +| total_timesteps | 10060800 | +| train/ | | +| approx_kl | 2.0251088 | +| clip_fraction | 0.559 | +| clip_range | 0.2 | +| entropy_loss | -0.596 | +| explained_variance | -1.2 | +| learning_rate | 0.0001 | +| loss | -0.0882 | +| n_updates | 158770 | +| policy_gradient_loss | -0.0731 | +| value_loss | 0.000219 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.23e+03 | +| ep_rew_mean | 0.215 | +| time/ | | +| fps | 309 | +| iterations | 9826 | +| time_elapsed | 32535 | +| total_timesteps | 10061824 | +| train/ | | +| approx_kl | 1.8640643 | +| clip_fraction | 0.494 | +| clip_range | 0.2 | +| entropy_loss | -0.42 | +| explained_variance | -2.55 | +| learning_rate | 0.0001 | +| loss | -0.0772 | +| n_updates | 158780 | +| policy_gradient_loss | -0.0695 | +| value_loss | 0.000208 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.22e+03 | +| ep_rew_mean | 0.207 | +| time/ | | +| fps | 309 | +| iterations | 9827 | +| time_elapsed | 32538 | +| total_timesteps | 10062848 | +| train/ | | +| approx_kl | 2.4427726 | +| clip_fraction | 0.5 | +| clip_range | 0.2 | +| entropy_loss | -0.408 | +| explained_variance | -0.327 | +| learning_rate | 0.0001 | +| loss | -0.076 | +| n_updates | 158790 | +| policy_gradient_loss | -0.0637 | +| value_loss | 0.000635 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.22e+03 | +| ep_rew_mean | 0.207 | +| time/ | | +| fps | 309 | +| iterations | 9828 | +| time_elapsed | 32541 | +| total_timesteps | 10063872 | +| train/ | | +| approx_kl | 1.774662 | +| clip_fraction | 0.488 | +| clip_range | 0.2 | +| entropy_loss | -0.444 | +| explained_variance | -2.36 | +| learning_rate | 0.0001 | +| loss | -0.0771 | +| n_updates | 158800 | +| policy_gradient_loss | -0.074 | +| value_loss | 0.00044 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.22e+03 | +| ep_rew_mean | 0.203 | +| time/ | | +| fps | 309 | +| iterations | 9829 | +| time_elapsed | 32544 | +| total_timesteps | 10064896 | +| train/ | | +| approx_kl | 2.0801668 | +| clip_fraction | 0.524 | +| clip_range | 0.2 | +| entropy_loss | -0.425 | +| explained_variance | -1.12 | +| learning_rate | 0.0001 | +| loss | -0.0941 | +| n_updates | 158810 | +| policy_gradient_loss | -0.0739 | +| value_loss | 0.0008 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.22e+03 | +| ep_rew_mean | 0.203 | +| time/ | | +| fps | 309 | +| iterations | 9830 | +| time_elapsed | 32548 | +| total_timesteps | 10065920 | +| train/ | | +| approx_kl | 2.587892 | +| clip_fraction | 0.503 | +| clip_range | 0.2 | +| entropy_loss | -0.434 | +| explained_variance | -5.69 | +| learning_rate | 0.0001 | +| loss | -0.108 | +| n_updates | 158820 | +| policy_gradient_loss | -0.0749 | +| value_loss | 0.000281 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.22e+03 | +| ep_rew_mean | 0.207 | +| time/ | | +| fps | 309 | +| iterations | 9831 | +| time_elapsed | 32551 | +| total_timesteps | 10066944 | +| train/ | | +| approx_kl | 2.213804 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.389 | +| explained_variance | -0.891 | +| learning_rate | 0.0001 | +| loss | -0.0786 | +| n_updates | 158830 | +| policy_gradient_loss | -0.0727 | +| value_loss | 0.000417 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.22e+03 | +| ep_rew_mean | 0.207 | +| time/ | | +| fps | 309 | +| iterations | 9832 | +| time_elapsed | 32554 | +| total_timesteps | 10067968 | +| train/ | | +| approx_kl | 2.065158 | +| clip_fraction | 0.533 | +| clip_range | 0.2 | +| entropy_loss | -0.529 | +| explained_variance | -0.579 | +| learning_rate | 0.0001 | +| loss | -0.0768 | +| n_updates | 158840 | +| policy_gradient_loss | -0.0711 | +| value_loss | 0.000619 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.22e+03 | +| ep_rew_mean | 0.207 | +| time/ | | +| fps | 309 | +| iterations | 9833 | +| time_elapsed | 32557 | +| total_timesteps | 10068992 | +| train/ | | +| approx_kl | 3.38313 | +| clip_fraction | 0.531 | +| clip_range | 0.2 | +| entropy_loss | -0.421 | +| explained_variance | -7.46 | +| learning_rate | 0.0001 | +| loss | -0.0984 | +| n_updates | 158850 | +| policy_gradient_loss | -0.0823 | +| value_loss | 0.000562 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.22e+03 | +| ep_rew_mean | 0.206 | +| time/ | | +| fps | 309 | +| iterations | 9834 | +| time_elapsed | 32560 | +| total_timesteps | 10070016 | +| train/ | | +| approx_kl | 2.4295082 | +| clip_fraction | 0.523 | +| clip_range | 0.2 | +| entropy_loss | -0.43 | +| explained_variance | -3.2 | +| learning_rate | 0.0001 | +| loss | -0.0944 | +| n_updates | 158860 | +| policy_gradient_loss | -0.0778 | +| value_loss | 0.000358 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.21e+03 | +| ep_rew_mean | 0.209 | +| time/ | | +| fps | 309 | +| iterations | 9835 | +| time_elapsed | 32564 | +| total_timesteps | 10071040 | +| train/ | | +| approx_kl | 2.3181422 | +| clip_fraction | 0.519 | +| clip_range | 0.2 | +| entropy_loss | -0.429 | +| explained_variance | -0.977 | +| learning_rate | 0.0001 | +| loss | -0.089 | +| n_updates | 158870 | +| policy_gradient_loss | -0.0687 | +| value_loss | 0.000279 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.21e+03 | +| ep_rew_mean | 0.209 | +| time/ | | +| fps | 309 | +| iterations | 9836 | +| time_elapsed | 32567 | +| total_timesteps | 10072064 | +| train/ | | +| approx_kl | 2.3520942 | +| clip_fraction | 0.525 | +| clip_range | 0.2 | +| entropy_loss | -0.443 | +| explained_variance | -0.557 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 158880 | +| policy_gradient_loss | -0.0704 | +| value_loss | 0.000424 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.2e+03 | +| ep_rew_mean | 0.204 | +| time/ | | +| fps | 309 | +| iterations | 9837 | +| time_elapsed | 32570 | +| total_timesteps | 10073088 | +| train/ | | +| approx_kl | 11.766523 | +| clip_fraction | 0.52 | +| clip_range | 0.2 | +| entropy_loss | -0.443 | +| explained_variance | -3.52 | +| learning_rate | 0.0001 | +| loss | -0.0914 | +| n_updates | 158890 | +| policy_gradient_loss | -0.078 | +| value_loss | 0.000405 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.2e+03 | +| ep_rew_mean | 0.204 | +| time/ | | +| fps | 309 | +| iterations | 9838 | +| time_elapsed | 32574 | +| total_timesteps | 10074112 | +| train/ | | +| approx_kl | 2.012324 | +| clip_fraction | 0.52 | +| clip_range | 0.2 | +| entropy_loss | -0.472 | +| explained_variance | -0.992 | +| learning_rate | 0.0001 | +| loss | -0.0922 | +| n_updates | 158900 | +| policy_gradient_loss | -0.0738 | +| value_loss | 0.000488 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.2e+03 | +| ep_rew_mean | 0.204 | +| time/ | | +| fps | 309 | +| iterations | 9839 | +| time_elapsed | 32577 | +| total_timesteps | 10075136 | +| train/ | | +| approx_kl | 1.7646945 | +| clip_fraction | 0.514 | +| clip_range | 0.2 | +| entropy_loss | -0.469 | +| explained_variance | -3.27 | +| learning_rate | 0.0001 | +| loss | -0.091 | +| n_updates | 158910 | +| policy_gradient_loss | -0.0752 | +| value_loss | 0.000279 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.18e+03 | +| ep_rew_mean | 0.202 | +| time/ | | +| fps | 309 | +| iterations | 9840 | +| time_elapsed | 32581 | +| total_timesteps | 10076160 | +| train/ | | +| approx_kl | 2.116401 | +| clip_fraction | 0.499 | +| clip_range | 0.2 | +| entropy_loss | -0.424 | +| explained_variance | -1.21 | +| learning_rate | 0.0001 | +| loss | -0.0845 | +| n_updates | 158920 | +| policy_gradient_loss | -0.0718 | +| value_loss | 0.000306 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.17e+03 | +| ep_rew_mean | 0.199 | +| time/ | | +| fps | 309 | +| iterations | 9841 | +| time_elapsed | 32584 | +| total_timesteps | 10077184 | +| train/ | | +| approx_kl | 1.5995264 | +| clip_fraction | 0.475 | +| clip_range | 0.2 | +| entropy_loss | -0.443 | +| explained_variance | -2.89 | +| learning_rate | 0.0001 | +| loss | -0.115 | +| n_updates | 158930 | +| policy_gradient_loss | -0.0662 | +| value_loss | 0.000379 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.17e+03 | +| ep_rew_mean | 0.199 | +| time/ | | +| fps | 309 | +| iterations | 9842 | +| time_elapsed | 32587 | +| total_timesteps | 10078208 | +| train/ | | +| approx_kl | 3.2975628 | +| clip_fraction | 0.506 | +| clip_range | 0.2 | +| entropy_loss | -0.382 | +| explained_variance | -0.946 | +| learning_rate | 0.0001 | +| loss | -0.054 | +| n_updates | 158940 | +| policy_gradient_loss | -0.0674 | +| value_loss | 0.000554 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.15e+03 | +| ep_rew_mean | 0.198 | +| time/ | | +| fps | 309 | +| iterations | 9843 | +| time_elapsed | 32590 | +| total_timesteps | 10079232 | +| train/ | | +| approx_kl | 2.3116922 | +| clip_fraction | 0.521 | +| clip_range | 0.2 | +| entropy_loss | -0.432 | +| explained_variance | -2.16 | +| learning_rate | 0.0001 | +| loss | -0.121 | +| n_updates | 158950 | +| policy_gradient_loss | -0.0792 | +| value_loss | 0.000577 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.15e+03 | +| ep_rew_mean | 0.198 | +| time/ | | +| fps | 309 | +| iterations | 9844 | +| time_elapsed | 32594 | +| total_timesteps | 10080256 | +| train/ | | +| approx_kl | 3.5859888 | +| clip_fraction | 0.478 | +| clip_range | 0.2 | +| entropy_loss | -0.374 | +| explained_variance | -2.06 | +| learning_rate | 0.0001 | +| loss | -0.098 | +| n_updates | 158960 | +| policy_gradient_loss | -0.0736 | +| value_loss | 0.000535 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.14e+03 | +| ep_rew_mean | 0.196 | +| time/ | | +| fps | 309 | +| iterations | 9845 | +| time_elapsed | 32597 | +| total_timesteps | 10081280 | +| train/ | | +| approx_kl | 2.1589656 | +| clip_fraction | 0.545 | +| clip_range | 0.2 | +| entropy_loss | -0.438 | +| explained_variance | -2 | +| learning_rate | 0.0001 | +| loss | -0.0924 | +| n_updates | 158970 | +| policy_gradient_loss | -0.0745 | +| value_loss | 0.000421 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.14e+03 | +| ep_rew_mean | 0.196 | +| time/ | | +| fps | 309 | +| iterations | 9846 | +| time_elapsed | 32600 | +| total_timesteps | 10082304 | +| train/ | | +| approx_kl | 2.1910594 | +| clip_fraction | 0.505 | +| clip_range | 0.2 | +| entropy_loss | -0.396 | +| explained_variance | -1.87 | +| learning_rate | 0.0001 | +| loss | -0.0978 | +| n_updates | 158980 | +| policy_gradient_loss | -0.0746 | +| value_loss | 0.000379 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.14e+03 | +| ep_rew_mean | 0.196 | +| time/ | | +| fps | 309 | +| iterations | 9847 | +| time_elapsed | 32604 | +| total_timesteps | 10083328 | +| train/ | | +| approx_kl | 2.6288462 | +| clip_fraction | 0.513 | +| clip_range | 0.2 | +| entropy_loss | -0.434 | +| explained_variance | -2.44 | +| learning_rate | 0.0001 | +| loss | -0.0928 | +| n_updates | 158990 | +| policy_gradient_loss | -0.0727 | +| value_loss | 0.000406 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.15e+03 | +| ep_rew_mean | 0.199 | +| time/ | | +| fps | 309 | +| iterations | 9848 | +| time_elapsed | 32607 | +| total_timesteps | 10084352 | +| train/ | | +| approx_kl | 1.6332126 | +| clip_fraction | 0.542 | +| clip_range | 0.2 | +| entropy_loss | -0.562 | +| explained_variance | -4.36 | +| learning_rate | 0.0001 | +| loss | -0.11 | +| n_updates | 159000 | +| policy_gradient_loss | -0.0781 | +| value_loss | 0.000347 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.15e+03 | +| ep_rew_mean | 0.199 | +| time/ | | +| fps | 309 | +| iterations | 9849 | +| time_elapsed | 32610 | +| total_timesteps | 10085376 | +| train/ | | +| approx_kl | 2.2800367 | +| clip_fraction | 0.532 | +| clip_range | 0.2 | +| entropy_loss | -0.464 | +| explained_variance | -0.735 | +| learning_rate | 0.0001 | +| loss | -0.0952 | +| n_updates | 159010 | +| policy_gradient_loss | -0.0644 | +| value_loss | 0.000425 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.16e+03 | +| ep_rew_mean | 0.201 | +| time/ | | +| fps | 309 | +| iterations | 9850 | +| time_elapsed | 32613 | +| total_timesteps | 10086400 | +| train/ | | +| approx_kl | 4.3431168 | +| clip_fraction | 0.535 | +| clip_range | 0.2 | +| entropy_loss | -0.498 | +| explained_variance | -4.02 | +| learning_rate | 0.0001 | +| loss | -0.114 | +| n_updates | 159020 | +| policy_gradient_loss | -0.0771 | +| value_loss | 0.000315 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.16e+03 | +| ep_rew_mean | 0.201 | +| time/ | | +| fps | 309 | +| iterations | 9851 | +| time_elapsed | 32617 | +| total_timesteps | 10087424 | +| train/ | | +| approx_kl | 1.8966843 | +| clip_fraction | 0.499 | +| clip_range | 0.2 | +| entropy_loss | -0.406 | +| explained_variance | -1.44 | +| learning_rate | 0.0001 | +| loss | -0.0925 | +| n_updates | 159030 | +| policy_gradient_loss | -0.072 | +| value_loss | 0.000309 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.16e+03 | +| ep_rew_mean | 0.202 | +| time/ | | +| fps | 309 | +| iterations | 9852 | +| time_elapsed | 32620 | +| total_timesteps | 10088448 | +| train/ | | +| approx_kl | 2.1548147 | +| clip_fraction | 0.5 | +| clip_range | 0.2 | +| entropy_loss | -0.42 | +| explained_variance | -3.39 | +| learning_rate | 0.0001 | +| loss | -0.0827 | +| n_updates | 159040 | +| policy_gradient_loss | -0.0701 | +| value_loss | 0.000427 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.16e+03 | +| ep_rew_mean | 0.202 | +| time/ | | +| fps | 309 | +| iterations | 9853 | +| time_elapsed | 32624 | +| total_timesteps | 10089472 | +| train/ | | +| approx_kl | 2.03147 | +| clip_fraction | 0.526 | +| clip_range | 0.2 | +| entropy_loss | -0.454 | +| explained_variance | -2.24 | +| learning_rate | 0.0001 | +| loss | -0.0871 | +| n_updates | 159050 | +| policy_gradient_loss | -0.0777 | +| value_loss | 0.000409 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.15e+03 | +| ep_rew_mean | 0.203 | +| time/ | | +| fps | 309 | +| iterations | 9854 | +| time_elapsed | 32627 | +| total_timesteps | 10090496 | +| train/ | | +| approx_kl | 2.2226067 | +| clip_fraction | 0.514 | +| clip_range | 0.2 | +| entropy_loss | -0.436 | +| explained_variance | -2.03 | +| learning_rate | 0.0001 | +| loss | -0.085 | +| n_updates | 159060 | +| policy_gradient_loss | -0.0694 | +| value_loss | 0.000513 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.15e+03 | +| ep_rew_mean | 0.203 | +| time/ | | +| fps | 309 | +| iterations | 9855 | +| time_elapsed | 32631 | +| total_timesteps | 10091520 | +| train/ | | +| approx_kl | 2.2823713 | +| clip_fraction | 0.491 | +| clip_range | 0.2 | +| entropy_loss | -0.423 | +| explained_variance | -1.13 | +| learning_rate | 0.0001 | +| loss | -0.112 | +| n_updates | 159070 | +| policy_gradient_loss | -0.075 | +| value_loss | 0.000925 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.14e+03 | +| ep_rew_mean | 0.205 | +| time/ | | +| fps | 309 | +| iterations | 9856 | +| time_elapsed | 32634 | +| total_timesteps | 10092544 | +| train/ | | +| approx_kl | 2.6982179 | +| clip_fraction | 0.517 | +| clip_range | 0.2 | +| entropy_loss | -0.489 | +| explained_variance | -3.59 | +| learning_rate | 0.0001 | +| loss | -0.113 | +| n_updates | 159080 | +| policy_gradient_loss | -0.0788 | +| value_loss | 0.000717 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.14e+03 | +| ep_rew_mean | 0.205 | +| time/ | | +| fps | 309 | +| iterations | 9857 | +| time_elapsed | 32637 | +| total_timesteps | 10093568 | +| train/ | | +| approx_kl | 2.2026184 | +| clip_fraction | 0.498 | +| clip_range | 0.2 | +| entropy_loss | -0.391 | +| explained_variance | -0.911 | +| learning_rate | 0.0001 | +| loss | -0.0942 | +| n_updates | 159090 | +| policy_gradient_loss | -0.0678 | +| value_loss | 0.000529 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.13e+03 | +| ep_rew_mean | 0.207 | +| time/ | | +| fps | 309 | +| iterations | 9858 | +| time_elapsed | 32641 | +| total_timesteps | 10094592 | +| train/ | | +| approx_kl | 2.2825284 | +| clip_fraction | 0.528 | +| clip_range | 0.2 | +| entropy_loss | -0.415 | +| explained_variance | -3.64 | +| learning_rate | 0.0001 | +| loss | -0.111 | +| n_updates | 159100 | +| policy_gradient_loss | -0.0791 | +| value_loss | 0.000361 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.13e+03 | +| ep_rew_mean | 0.207 | +| time/ | | +| fps | 309 | +| iterations | 9859 | +| time_elapsed | 32644 | +| total_timesteps | 10095616 | +| train/ | | +| approx_kl | 2.0087564 | +| clip_fraction | 0.498 | +| clip_range | 0.2 | +| entropy_loss | -0.376 | +| explained_variance | -1.5 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 159110 | +| policy_gradient_loss | -0.0713 | +| value_loss | 0.000479 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.13e+03 | +| ep_rew_mean | 0.205 | +| time/ | | +| fps | 309 | +| iterations | 9860 | +| time_elapsed | 32648 | +| total_timesteps | 10096640 | +| train/ | | +| approx_kl | 2.4584258 | +| clip_fraction | 0.536 | +| clip_range | 0.2 | +| entropy_loss | -0.405 | +| explained_variance | -1.34 | +| learning_rate | 0.0001 | +| loss | -0.0952 | +| n_updates | 159120 | +| policy_gradient_loss | -0.0772 | +| value_loss | 0.000545 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.13e+03 | +| ep_rew_mean | 0.205 | +| time/ | | +| fps | 309 | +| iterations | 9861 | +| time_elapsed | 32651 | +| total_timesteps | 10097664 | +| train/ | | +| approx_kl | 3.174616 | +| clip_fraction | 0.509 | +| clip_range | 0.2 | +| entropy_loss | -0.4 | +| explained_variance | -1.69 | +| learning_rate | 0.0001 | +| loss | -0.106 | +| n_updates | 159130 | +| policy_gradient_loss | -0.0765 | +| value_loss | 0.000336 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.12e+03 | +| ep_rew_mean | 0.208 | +| time/ | | +| fps | 309 | +| iterations | 9862 | +| time_elapsed | 32655 | +| total_timesteps | 10098688 | +| train/ | | +| approx_kl | 2.087049 | +| clip_fraction | 0.509 | +| clip_range | 0.2 | +| entropy_loss | -0.422 | +| explained_variance | -3.53 | +| learning_rate | 0.0001 | +| loss | -0.0875 | +| n_updates | 159140 | +| policy_gradient_loss | -0.0734 | +| value_loss | 0.000306 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.12e+03 | +| ep_rew_mean | 0.208 | +| time/ | | +| fps | 309 | +| iterations | 9863 | +| time_elapsed | 32658 | +| total_timesteps | 10099712 | +| train/ | | +| approx_kl | 2.2153563 | +| clip_fraction | 0.468 | +| clip_range | 0.2 | +| entropy_loss | -0.382 | +| explained_variance | -1.3 | +| learning_rate | 0.0001 | +| loss | -0.0714 | +| n_updates | 159150 | +| policy_gradient_loss | -0.0615 | +| value_loss | 0.000389 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.12e+03 | +| ep_rew_mean | 0.209 | +| time/ | | +| fps | 309 | +| iterations | 9864 | +| time_elapsed | 32661 | +| total_timesteps | 10100736 | +| train/ | | +| approx_kl | 2.135915 | +| clip_fraction | 0.503 | +| clip_range | 0.2 | +| entropy_loss | -0.413 | +| explained_variance | -1.32 | +| learning_rate | 0.0001 | +| loss | -0.0829 | +| n_updates | 159160 | +| policy_gradient_loss | -0.0696 | +| value_loss | 0.000533 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.11e+03 | +| ep_rew_mean | 0.203 | +| time/ | | +| fps | 309 | +| iterations | 9865 | +| time_elapsed | 32665 | +| total_timesteps | 10101760 | +| train/ | | +| approx_kl | 2.106559 | +| clip_fraction | 0.496 | +| clip_range | 0.2 | +| entropy_loss | -0.388 | +| explained_variance | -2.9 | +| learning_rate | 0.0001 | +| loss | -0.0993 | +| n_updates | 159170 | +| policy_gradient_loss | -0.0732 | +| value_loss | 0.000361 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.11e+03 | +| ep_rew_mean | 0.203 | +| time/ | | +| fps | 309 | +| iterations | 9866 | +| time_elapsed | 32668 | +| total_timesteps | 10102784 | +| train/ | | +| approx_kl | 1.72569 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.424 | +| explained_variance | -1.09 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 159180 | +| policy_gradient_loss | -0.0757 | +| value_loss | 0.000252 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.1e+03 | +| ep_rew_mean | 0.201 | +| time/ | | +| fps | 309 | +| iterations | 9867 | +| time_elapsed | 32671 | +| total_timesteps | 10103808 | +| train/ | | +| approx_kl | 2.2533238 | +| clip_fraction | 0.497 | +| clip_range | 0.2 | +| entropy_loss | -0.415 | +| explained_variance | -1.71 | +| learning_rate | 0.0001 | +| loss | -0.0663 | +| n_updates | 159190 | +| policy_gradient_loss | -0.0719 | +| value_loss | 0.000293 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.09e+03 | +| ep_rew_mean | 0.195 | +| time/ | | +| fps | 309 | +| iterations | 9868 | +| time_elapsed | 32675 | +| total_timesteps | 10104832 | +| train/ | | +| approx_kl | 2.4302115 | +| clip_fraction | 0.519 | +| clip_range | 0.2 | +| entropy_loss | -0.437 | +| explained_variance | -0.451 | +| learning_rate | 0.0001 | +| loss | -0.0799 | +| n_updates | 159200 | +| policy_gradient_loss | -0.0724 | +| value_loss | 0.000494 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.09e+03 | +| ep_rew_mean | 0.195 | +| time/ | | +| fps | 309 | +| iterations | 9869 | +| time_elapsed | 32678 | +| total_timesteps | 10105856 | +| train/ | | +| approx_kl | 2.5480049 | +| clip_fraction | 0.506 | +| clip_range | 0.2 | +| entropy_loss | -0.398 | +| explained_variance | -1.66 | +| learning_rate | 0.0001 | +| loss | -0.116 | +| n_updates | 159210 | +| policy_gradient_loss | -0.0779 | +| value_loss | 0.000447 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.09e+03 | +| ep_rew_mean | 0.197 | +| time/ | | +| fps | 309 | +| iterations | 9870 | +| time_elapsed | 32681 | +| total_timesteps | 10106880 | +| train/ | | +| approx_kl | 2.2634606 | +| clip_fraction | 0.538 | +| clip_range | 0.2 | +| entropy_loss | -0.541 | +| explained_variance | -1.17 | +| learning_rate | 0.0001 | +| loss | -0.0915 | +| n_updates | 159220 | +| policy_gradient_loss | -0.0749 | +| value_loss | 0.00044 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.09e+03 | +| ep_rew_mean | 0.197 | +| time/ | | +| fps | 309 | +| iterations | 9871 | +| time_elapsed | 32685 | +| total_timesteps | 10107904 | +| train/ | | +| approx_kl | 1.8651531 | +| clip_fraction | 0.511 | +| clip_range | 0.2 | +| entropy_loss | -0.463 | +| explained_variance | -5.32 | +| learning_rate | 0.0001 | +| loss | -0.102 | +| n_updates | 159230 | +| policy_gradient_loss | -0.0723 | +| value_loss | 0.000972 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.08e+03 | +| ep_rew_mean | 0.194 | +| time/ | | +| fps | 309 | +| iterations | 9872 | +| time_elapsed | 32688 | +| total_timesteps | 10108928 | +| train/ | | +| approx_kl | 2.1499033 | +| clip_fraction | 0.511 | +| clip_range | 0.2 | +| entropy_loss | -0.448 | +| explained_variance | -1.14 | +| learning_rate | 0.0001 | +| loss | -0.108 | +| n_updates | 159240 | +| policy_gradient_loss | -0.0724 | +| value_loss | 0.000469 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.08e+03 | +| ep_rew_mean | 0.194 | +| time/ | | +| fps | 309 | +| iterations | 9873 | +| time_elapsed | 32692 | +| total_timesteps | 10109952 | +| train/ | | +| approx_kl | 2.293803 | +| clip_fraction | 0.509 | +| clip_range | 0.2 | +| entropy_loss | -0.378 | +| explained_variance | -6.14 | +| learning_rate | 0.0001 | +| loss | -0.118 | +| n_updates | 159250 | +| policy_gradient_loss | -0.0745 | +| value_loss | 0.000443 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.08e+03 | +| ep_rew_mean | 0.194 | +| time/ | | +| fps | 309 | +| iterations | 9874 | +| time_elapsed | 32695 | +| total_timesteps | 10110976 | +| train/ | | +| approx_kl | 2.214844 | +| clip_fraction | 0.541 | +| clip_range | 0.2 | +| entropy_loss | -0.44 | +| explained_variance | -0.985 | +| learning_rate | 0.0001 | +| loss | -0.0716 | +| n_updates | 159260 | +| policy_gradient_loss | -0.0807 | +| value_loss | 0.000313 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.07e+03 | +| ep_rew_mean | 0.2 | +| time/ | | +| fps | 309 | +| iterations | 9875 | +| time_elapsed | 32699 | +| total_timesteps | 10112000 | +| train/ | | +| approx_kl | 2.2056162 | +| clip_fraction | 0.521 | +| clip_range | 0.2 | +| entropy_loss | -0.489 | +| explained_variance | -1.08 | +| learning_rate | 0.0001 | +| loss | -0.112 | +| n_updates | 159270 | +| policy_gradient_loss | -0.071 | +| value_loss | 0.000331 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.07e+03 | +| ep_rew_mean | 0.2 | +| time/ | | +| fps | 309 | +| iterations | 9876 | +| time_elapsed | 32702 | +| total_timesteps | 10113024 | +| train/ | | +| approx_kl | 2.290906 | +| clip_fraction | 0.506 | +| clip_range | 0.2 | +| entropy_loss | -0.441 | +| explained_variance | -0.357 | +| learning_rate | 0.0001 | +| loss | -0.109 | +| n_updates | 159280 | +| policy_gradient_loss | -0.061 | +| value_loss | 0.000993 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.07e+03 | +| ep_rew_mean | 0.2 | +| time/ | | +| fps | 309 | +| iterations | 9877 | +| time_elapsed | 32706 | +| total_timesteps | 10114048 | +| train/ | | +| approx_kl | 2.0894809 | +| clip_fraction | 0.528 | +| clip_range | 0.2 | +| entropy_loss | -0.464 | +| explained_variance | -9.32 | +| learning_rate | 0.0001 | +| loss | -0.0913 | +| n_updates | 159290 | +| policy_gradient_loss | -0.0825 | +| value_loss | 0.000428 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.07e+03 | +| ep_rew_mean | 0.198 | +| time/ | | +| fps | 309 | +| iterations | 9878 | +| time_elapsed | 32709 | +| total_timesteps | 10115072 | +| train/ | | +| approx_kl | 5.169214 | +| clip_fraction | 0.526 | +| clip_range | 0.2 | +| entropy_loss | -0.449 | +| explained_variance | -4.37 | +| learning_rate | 0.0001 | +| loss | -0.128 | +| n_updates | 159300 | +| policy_gradient_loss | -0.0799 | +| value_loss | 0.000181 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.07e+03 | +| ep_rew_mean | 0.198 | +| time/ | | +| fps | 309 | +| iterations | 9879 | +| time_elapsed | 32713 | +| total_timesteps | 10116096 | +| train/ | | +| approx_kl | 2.579628 | +| clip_fraction | 0.512 | +| clip_range | 0.2 | +| entropy_loss | -0.389 | +| explained_variance | -0.978 | +| learning_rate | 0.0001 | +| loss | -0.101 | +| n_updates | 159310 | +| policy_gradient_loss | -0.0785 | +| value_loss | 0.000262 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.07e+03 | +| ep_rew_mean | 0.197 | +| time/ | | +| fps | 309 | +| iterations | 9880 | +| time_elapsed | 32716 | +| total_timesteps | 10117120 | +| train/ | | +| approx_kl | 2.4851751 | +| clip_fraction | 0.508 | +| clip_range | 0.2 | +| entropy_loss | -0.401 | +| explained_variance | -1.26 | +| learning_rate | 0.0001 | +| loss | -0.112 | +| n_updates | 159320 | +| policy_gradient_loss | -0.0762 | +| value_loss | 0.000378 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.06e+03 | +| ep_rew_mean | 0.192 | +| time/ | | +| fps | 309 | +| iterations | 9881 | +| time_elapsed | 32719 | +| total_timesteps | 10118144 | +| train/ | | +| approx_kl | 10.708248 | +| clip_fraction | 0.489 | +| clip_range | 0.2 | +| entropy_loss | -0.378 | +| explained_variance | -2.13 | +| learning_rate | 0.0001 | +| loss | -0.0937 | +| n_updates | 159330 | +| policy_gradient_loss | -0.0761 | +| value_loss | 0.000486 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.06e+03 | +| ep_rew_mean | 0.192 | +| time/ | | +| fps | 309 | +| iterations | 9882 | +| time_elapsed | 32722 | +| total_timesteps | 10119168 | +| train/ | | +| approx_kl | 2.0539792 | +| clip_fraction | 0.443 | +| clip_range | 0.2 | +| entropy_loss | -0.316 | +| explained_variance | -1.56 | +| learning_rate | 0.0001 | +| loss | -0.0846 | +| n_updates | 159340 | +| policy_gradient_loss | -0.0717 | +| value_loss | 0.00052 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.05e+03 | +| ep_rew_mean | 0.19 | +| time/ | | +| fps | 309 | +| iterations | 9883 | +| time_elapsed | 32726 | +| total_timesteps | 10120192 | +| train/ | | +| approx_kl | 2.0617716 | +| clip_fraction | 0.511 | +| clip_range | 0.2 | +| entropy_loss | -0.421 | +| explained_variance | -3.27 | +| learning_rate | 0.0001 | +| loss | -0.107 | +| n_updates | 159350 | +| policy_gradient_loss | -0.0798 | +| value_loss | 0.000285 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.05e+03 | +| ep_rew_mean | 0.184 | +| time/ | | +| fps | 309 | +| iterations | 9884 | +| time_elapsed | 32729 | +| total_timesteps | 10121216 | +| train/ | | +| approx_kl | 1.8934453 | +| clip_fraction | 0.492 | +| clip_range | 0.2 | +| entropy_loss | -0.411 | +| explained_variance | -0.842 | +| learning_rate | 0.0001 | +| loss | -0.0517 | +| n_updates | 159360 | +| policy_gradient_loss | -0.0619 | +| value_loss | 0.00017 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.05e+03 | +| ep_rew_mean | 0.184 | +| time/ | | +| fps | 309 | +| iterations | 9885 | +| time_elapsed | 32732 | +| total_timesteps | 10122240 | +| train/ | | +| approx_kl | 1.9417113 | +| clip_fraction | 0.491 | +| clip_range | 0.2 | +| entropy_loss | -0.431 | +| explained_variance | -1.3 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 159370 | +| policy_gradient_loss | -0.0762 | +| value_loss | 0.000217 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 2.05e+03 | +| ep_rew_mean | 0.179 | +| time/ | | +| fps | 309 | +| iterations | 9886 | +| time_elapsed | 32736 | +| total_timesteps | 10123264 | +| train/ | | +| approx_kl | 4.206357 | +| clip_fraction | 0.495 | +| clip_range | 0.2 | +| entropy_loss | -0.383 | +| explained_variance | -2.34 | +| learning_rate | 0.0001 | +| loss | -0.0952 | +| n_updates | 159380 | +| policy_gradient_loss | -0.0744 | +| value_loss | 0.000387 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.05e+03 | +| ep_rew_mean | 0.179 | +| time/ | | +| fps | 309 | +| iterations | 9887 | +| time_elapsed | 32739 | +| total_timesteps | 10124288 | +| train/ | | +| approx_kl | 2.1370268 | +| clip_fraction | 0.484 | +| clip_range | 0.2 | +| entropy_loss | -0.374 | +| explained_variance | -4.32 | +| learning_rate | 0.0001 | +| loss | -0.0907 | +| n_updates | 159390 | +| policy_gradient_loss | -0.072 | +| value_loss | 0.000602 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.05e+03 | +| ep_rew_mean | 0.179 | +| time/ | | +| fps | 309 | +| iterations | 9888 | +| time_elapsed | 32743 | +| total_timesteps | 10125312 | +| train/ | | +| approx_kl | 1.9726167 | +| clip_fraction | 0.521 | +| clip_range | 0.2 | +| entropy_loss | -0.402 | +| explained_variance | -1.29 | +| learning_rate | 0.0001 | +| loss | -0.09 | +| n_updates | 159400 | +| policy_gradient_loss | -0.0706 | +| value_loss | 0.000494 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.05e+03 | +| ep_rew_mean | 0.179 | +| time/ | | +| fps | 309 | +| iterations | 9889 | +| time_elapsed | 32746 | +| total_timesteps | 10126336 | +| train/ | | +| approx_kl | 2.0562844 | +| clip_fraction | 0.486 | +| clip_range | 0.2 | +| entropy_loss | -0.403 | +| explained_variance | -9.13 | +| learning_rate | 0.0001 | +| loss | -0.0941 | +| n_updates | 159410 | +| policy_gradient_loss | -0.071 | +| value_loss | 0.000338 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.04e+03 | +| ep_rew_mean | 0.181 | +| time/ | | +| fps | 309 | +| iterations | 9890 | +| time_elapsed | 32749 | +| total_timesteps | 10127360 | +| train/ | | +| approx_kl | 14.889776 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.384 | +| explained_variance | -1.4 | +| learning_rate | 0.0001 | +| loss | -0.0971 | +| n_updates | 159420 | +| policy_gradient_loss | -0.0663 | +| value_loss | 0.000356 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.04e+03 | +| ep_rew_mean | 0.181 | +| time/ | | +| fps | 309 | +| iterations | 9891 | +| time_elapsed | 32753 | +| total_timesteps | 10128384 | +| train/ | | +| approx_kl | 2.0020373 | +| clip_fraction | 0.493 | +| clip_range | 0.2 | +| entropy_loss | -0.381 | +| explained_variance | -1.02 | +| learning_rate | 0.0001 | +| loss | -0.0784 | +| n_updates | 159430 | +| policy_gradient_loss | -0.072 | +| value_loss | 0.00074 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.04e+03 | +| ep_rew_mean | 0.176 | +| time/ | | +| fps | 309 | +| iterations | 9892 | +| time_elapsed | 32756 | +| total_timesteps | 10129408 | +| train/ | | +| approx_kl | 2.3576698 | +| clip_fraction | 0.489 | +| clip_range | 0.2 | +| entropy_loss | -0.383 | +| explained_variance | -2.41 | +| learning_rate | 0.0001 | +| loss | -0.122 | +| n_updates | 159440 | +| policy_gradient_loss | -0.0747 | +| value_loss | 0.000422 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.04e+03 | +| ep_rew_mean | 0.174 | +| time/ | | +| fps | 309 | +| iterations | 9893 | +| time_elapsed | 32759 | +| total_timesteps | 10130432 | +| train/ | | +| approx_kl | 2.2683012 | +| clip_fraction | 0.476 | +| clip_range | 0.2 | +| entropy_loss | -0.356 | +| explained_variance | -0.762 | +| learning_rate | 0.0001 | +| loss | -0.0778 | +| n_updates | 159450 | +| policy_gradient_loss | -0.0684 | +| value_loss | 0.000547 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.04e+03 | +| ep_rew_mean | 0.174 | +| time/ | | +| fps | 309 | +| iterations | 9894 | +| time_elapsed | 32763 | +| total_timesteps | 10131456 | +| train/ | | +| approx_kl | 3.3230698 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.357 | +| explained_variance | -3.97 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 159460 | +| policy_gradient_loss | -0.0721 | +| value_loss | 0.00033 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.04e+03 | +| ep_rew_mean | 0.166 | +| time/ | | +| fps | 309 | +| iterations | 9895 | +| time_elapsed | 32766 | +| total_timesteps | 10132480 | +| train/ | | +| approx_kl | 2.6248531 | +| clip_fraction | 0.511 | +| clip_range | 0.2 | +| entropy_loss | -0.409 | +| explained_variance | -2.47 | +| learning_rate | 0.0001 | +| loss | -0.0903 | +| n_updates | 159470 | +| policy_gradient_loss | -0.0743 | +| value_loss | 0.000289 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.03e+03 | +| ep_rew_mean | 0.163 | +| time/ | | +| fps | 309 | +| iterations | 9896 | +| time_elapsed | 32770 | +| total_timesteps | 10133504 | +| train/ | | +| approx_kl | 2.2778707 | +| clip_fraction | 0.484 | +| clip_range | 0.2 | +| entropy_loss | -0.41 | +| explained_variance | -0.675 | +| learning_rate | 0.0001 | +| loss | -0.0815 | +| n_updates | 159480 | +| policy_gradient_loss | -0.0631 | +| value_loss | 0.000276 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.03e+03 | +| ep_rew_mean | 0.163 | +| time/ | | +| fps | 309 | +| iterations | 9897 | +| time_elapsed | 32773 | +| total_timesteps | 10134528 | +| train/ | | +| approx_kl | 1.9276857 | +| clip_fraction | 0.488 | +| clip_range | 0.2 | +| entropy_loss | -0.38 | +| explained_variance | -4.65 | +| learning_rate | 0.0001 | +| loss | -0.1 | +| n_updates | 159490 | +| policy_gradient_loss | -0.0727 | +| value_loss | 0.000297 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.03e+03 | +| ep_rew_mean | 0.158 | +| time/ | | +| fps | 309 | +| iterations | 9898 | +| time_elapsed | 32776 | +| total_timesteps | 10135552 | +| train/ | | +| approx_kl | 3.0550091 | +| clip_fraction | 0.543 | +| clip_range | 0.2 | +| entropy_loss | -0.516 | +| explained_variance | -0.768 | +| learning_rate | 0.0001 | +| loss | -0.0946 | +| n_updates | 159500 | +| policy_gradient_loss | -0.0714 | +| value_loss | 0.000262 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.03e+03 | +| ep_rew_mean | 0.158 | +| time/ | | +| fps | 309 | +| iterations | 9899 | +| time_elapsed | 32780 | +| total_timesteps | 10136576 | +| train/ | | +| approx_kl | 1.6669933 | +| clip_fraction | 0.524 | +| clip_range | 0.2 | +| entropy_loss | -0.483 | +| explained_variance | -2.23 | +| learning_rate | 0.0001 | +| loss | -0.0765 | +| n_updates | 159510 | +| policy_gradient_loss | -0.0673 | +| value_loss | 0.00026 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.02e+03 | +| ep_rew_mean | 0.16 | +| time/ | | +| fps | 309 | +| iterations | 9900 | +| time_elapsed | 32783 | +| total_timesteps | 10137600 | +| train/ | | +| approx_kl | 2.4339352 | +| clip_fraction | 0.511 | +| clip_range | 0.2 | +| entropy_loss | -0.416 | +| explained_variance | -0.789 | +| learning_rate | 0.0001 | +| loss | -0.113 | +| n_updates | 159520 | +| policy_gradient_loss | -0.0757 | +| value_loss | 0.000563 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.02e+03 | +| ep_rew_mean | 0.16 | +| time/ | | +| fps | 309 | +| iterations | 9901 | +| time_elapsed | 32786 | +| total_timesteps | 10138624 | +| train/ | | +| approx_kl | 2.2371044 | +| clip_fraction | 0.517 | +| clip_range | 0.2 | +| entropy_loss | -0.416 | +| explained_variance | -2.17 | +| learning_rate | 0.0001 | +| loss | -0.0944 | +| n_updates | 159530 | +| policy_gradient_loss | -0.0718 | +| value_loss | 0.00104 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.03e+03 | +| ep_rew_mean | 0.164 | +| time/ | | +| fps | 309 | +| iterations | 9902 | +| time_elapsed | 32790 | +| total_timesteps | 10139648 | +| train/ | | +| approx_kl | 1.8682215 | +| clip_fraction | 0.506 | +| clip_range | 0.2 | +| entropy_loss | -0.397 | +| explained_variance | -5.9 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 159540 | +| policy_gradient_loss | -0.0768 | +| value_loss | 0.000309 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.03e+03 | +| ep_rew_mean | 0.164 | +| time/ | | +| fps | 309 | +| iterations | 9903 | +| time_elapsed | 32793 | +| total_timesteps | 10140672 | +| train/ | | +| approx_kl | 2.2369702 | +| clip_fraction | 0.497 | +| clip_range | 0.2 | +| entropy_loss | -0.397 | +| explained_variance | -0.964 | +| learning_rate | 0.0001 | +| loss | -0.0926 | +| n_updates | 159550 | +| policy_gradient_loss | -0.0647 | +| value_loss | 0.000419 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 2.01e+03 | +| ep_rew_mean | 0.162 | +| time/ | | +| fps | 309 | +| iterations | 9904 | +| time_elapsed | 32796 | +| total_timesteps | 10141696 | +| train/ | | +| approx_kl | 2.0507026 | +| clip_fraction | 0.508 | +| clip_range | 0.2 | +| entropy_loss | -0.402 | +| explained_variance | -1.69 | +| learning_rate | 0.0001 | +| loss | -0.095 | +| n_updates | 159560 | +| policy_gradient_loss | -0.0754 | +| value_loss | 0.000481 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.99e+03 | +| ep_rew_mean | 0.163 | +| time/ | | +| fps | 309 | +| iterations | 9905 | +| time_elapsed | 32800 | +| total_timesteps | 10142720 | +| train/ | | +| approx_kl | 2.1165388 | +| clip_fraction | 0.484 | +| clip_range | 0.2 | +| entropy_loss | -0.394 | +| explained_variance | -1.22 | +| learning_rate | 0.0001 | +| loss | -0.0862 | +| n_updates | 159570 | +| policy_gradient_loss | -0.0692 | +| value_loss | 0.000619 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.99e+03 | +| ep_rew_mean | 0.163 | +| time/ | | +| fps | 309 | +| iterations | 9906 | +| time_elapsed | 32803 | +| total_timesteps | 10143744 | +| train/ | | +| approx_kl | 2.1105638 | +| clip_fraction | 0.499 | +| clip_range | 0.2 | +| entropy_loss | -0.402 | +| explained_variance | -2.78 | +| learning_rate | 0.0001 | +| loss | -0.0895 | +| n_updates | 159580 | +| policy_gradient_loss | -0.0755 | +| value_loss | 0.00036 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.99e+03 | +| ep_rew_mean | 0.159 | +| time/ | | +| fps | 309 | +| iterations | 9907 | +| time_elapsed | 32807 | +| total_timesteps | 10144768 | +| train/ | | +| approx_kl | 2.5180995 | +| clip_fraction | 0.49 | +| clip_range | 0.2 | +| entropy_loss | -0.384 | +| explained_variance | -1.93 | +| learning_rate | 0.0001 | +| loss | -0.0934 | +| n_updates | 159590 | +| policy_gradient_loss | -0.0682 | +| value_loss | 0.000454 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.99e+03 | +| ep_rew_mean | 0.159 | +| time/ | | +| fps | 309 | +| iterations | 9908 | +| time_elapsed | 32812 | +| total_timesteps | 10145792 | +| train/ | | +| approx_kl | 2.173164 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.371 | +| explained_variance | -1.88 | +| learning_rate | 0.0001 | +| loss | -0.1 | +| n_updates | 159600 | +| policy_gradient_loss | -0.0751 | +| value_loss | 0.000583 | +-------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.99e+03 | +| ep_rew_mean | 0.157 | +| time/ | | +| fps | 309 | +| iterations | 9909 | +| time_elapsed | 32816 | +| total_timesteps | 10146816 | +| train/ | | +| approx_kl | 4.98734 | +| clip_fraction | 0.499 | +| clip_range | 0.2 | +| entropy_loss | -0.361 | +| explained_variance | -7.41 | +| learning_rate | 0.0001 | +| loss | -0.0929 | +| n_updates | 159610 | +| policy_gradient_loss | -0.0785 | +| value_loss | 0.000458 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.98e+03 | +| ep_rew_mean | 0.157 | +| time/ | | +| fps | 309 | +| iterations | 9910 | +| time_elapsed | 32820 | +| total_timesteps | 10147840 | +| train/ | | +| approx_kl | 2.7513475 | +| clip_fraction | 0.507 | +| clip_range | 0.2 | +| entropy_loss | -0.394 | +| explained_variance | -1.4 | +| learning_rate | 0.0001 | +| loss | -0.0686 | +| n_updates | 159620 | +| policy_gradient_loss | -0.0698 | +| value_loss | 0.000429 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.98e+03 | +| ep_rew_mean | 0.157 | +| time/ | | +| fps | 309 | +| iterations | 9911 | +| time_elapsed | 32825 | +| total_timesteps | 10148864 | +| train/ | | +| approx_kl | 2.0548189 | +| clip_fraction | 0.5 | +| clip_range | 0.2 | +| entropy_loss | -0.38 | +| explained_variance | -1.37 | +| learning_rate | 0.0001 | +| loss | -0.077 | +| n_updates | 159630 | +| policy_gradient_loss | -0.0747 | +| value_loss | 0.000555 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.97e+03 | +| ep_rew_mean | 0.156 | +| time/ | | +| fps | 309 | +| iterations | 9912 | +| time_elapsed | 32829 | +| total_timesteps | 10149888 | +| train/ | | +| approx_kl | 1.7853096 | +| clip_fraction | 0.527 | +| clip_range | 0.2 | +| entropy_loss | -0.452 | +| explained_variance | -0.686 | +| learning_rate | 0.0001 | +| loss | -0.0904 | +| n_updates | 159640 | +| policy_gradient_loss | -0.0709 | +| value_loss | 0.000503 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.97e+03 | +| ep_rew_mean | 0.156 | +| time/ | | +| fps | 309 | +| iterations | 9913 | +| time_elapsed | 32833 | +| total_timesteps | 10150912 | +| train/ | | +| approx_kl | 2.1560545 | +| clip_fraction | 0.508 | +| clip_range | 0.2 | +| entropy_loss | -0.413 | +| explained_variance | -1.7 | +| learning_rate | 0.0001 | +| loss | -0.12 | +| n_updates | 159650 | +| policy_gradient_loss | -0.0733 | +| value_loss | 0.000583 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.96e+03 | +| ep_rew_mean | 0.161 | +| time/ | | +| fps | 309 | +| iterations | 9914 | +| time_elapsed | 32837 | +| total_timesteps | 10151936 | +| train/ | | +| approx_kl | 2.4942446 | +| clip_fraction | 0.529 | +| clip_range | 0.2 | +| entropy_loss | -0.48 | +| explained_variance | -3.22 | +| learning_rate | 0.0001 | +| loss | -0.114 | +| n_updates | 159660 | +| policy_gradient_loss | -0.0815 | +| value_loss | 0.000417 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.96e+03 | +| ep_rew_mean | 0.161 | +| time/ | | +| fps | 309 | +| iterations | 9915 | +| time_elapsed | 32841 | +| total_timesteps | 10152960 | +| train/ | | +| approx_kl | 2.5271223 | +| clip_fraction | 0.516 | +| clip_range | 0.2 | +| entropy_loss | -0.389 | +| explained_variance | -1.65 | +| learning_rate | 0.0001 | +| loss | -0.0909 | +| n_updates | 159670 | +| policy_gradient_loss | -0.0728 | +| value_loss | 0.000512 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.97e+03 | +| ep_rew_mean | 0.158 | +| time/ | | +| fps | 309 | +| iterations | 9916 | +| time_elapsed | 32845 | +| total_timesteps | 10153984 | +| train/ | | +| approx_kl | 2.4357653 | +| clip_fraction | 0.501 | +| clip_range | 0.2 | +| entropy_loss | -0.433 | +| explained_variance | -1.79 | +| learning_rate | 0.0001 | +| loss | -0.0994 | +| n_updates | 159680 | +| policy_gradient_loss | -0.0735 | +| value_loss | 0.000394 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.97e+03 | +| ep_rew_mean | 0.158 | +| time/ | | +| fps | 309 | +| iterations | 9917 | +| time_elapsed | 32850 | +| total_timesteps | 10155008 | +| train/ | | +| approx_kl | 2.42383 | +| clip_fraction | 0.486 | +| clip_range | 0.2 | +| entropy_loss | -0.396 | +| explained_variance | -2.85 | +| learning_rate | 0.0001 | +| loss | -0.0957 | +| n_updates | 159690 | +| policy_gradient_loss | -0.0746 | +| value_loss | 0.000228 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.95e+03 | +| ep_rew_mean | 0.155 | +| time/ | | +| fps | 309 | +| iterations | 9918 | +| time_elapsed | 32854 | +| total_timesteps | 10156032 | +| train/ | | +| approx_kl | 1.8666329 | +| clip_fraction | 0.486 | +| clip_range | 0.2 | +| entropy_loss | -0.399 | +| explained_variance | -5.79 | +| learning_rate | 0.0001 | +| loss | -0.0676 | +| n_updates | 159700 | +| policy_gradient_loss | -0.0717 | +| value_loss | 0.000193 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.95e+03 | +| ep_rew_mean | 0.155 | +| time/ | | +| fps | 309 | +| iterations | 9919 | +| time_elapsed | 32858 | +| total_timesteps | 10157056 | +| train/ | | +| approx_kl | 3.21368 | +| clip_fraction | 0.509 | +| clip_range | 0.2 | +| entropy_loss | -0.35 | +| explained_variance | -5.52 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 159710 | +| policy_gradient_loss | -0.0826 | +| value_loss | 0.00027 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.94e+03 | +| ep_rew_mean | 0.154 | +| time/ | | +| fps | 309 | +| iterations | 9920 | +| time_elapsed | 32862 | +| total_timesteps | 10158080 | +| train/ | | +| approx_kl | 1.8795459 | +| clip_fraction | 0.517 | +| clip_range | 0.2 | +| entropy_loss | -0.418 | +| explained_variance | -1.44 | +| learning_rate | 0.0001 | +| loss | -0.0918 | +| n_updates | 159720 | +| policy_gradient_loss | -0.0789 | +| value_loss | 0.000383 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.94e+03 | +| ep_rew_mean | 0.154 | +| time/ | | +| fps | 309 | +| iterations | 9921 | +| time_elapsed | 32866 | +| total_timesteps | 10159104 | +| train/ | | +| approx_kl | 2.2486835 | +| clip_fraction | 0.481 | +| clip_range | 0.2 | +| entropy_loss | -0.379 | +| explained_variance | -1.49 | +| learning_rate | 0.0001 | +| loss | -0.0879 | +| n_updates | 159730 | +| policy_gradient_loss | -0.0703 | +| value_loss | 0.000408 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.94e+03 | +| ep_rew_mean | 0.154 | +| time/ | | +| fps | 309 | +| iterations | 9922 | +| time_elapsed | 32870 | +| total_timesteps | 10160128 | +| train/ | | +| approx_kl | 4.524974 | +| clip_fraction | 0.508 | +| clip_range | 0.2 | +| entropy_loss | -0.401 | +| explained_variance | -3.41 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 159740 | +| policy_gradient_loss | -0.0747 | +| value_loss | 0.000399 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.96e+03 | +| ep_rew_mean | 0.152 | +| time/ | | +| fps | 309 | +| iterations | 9923 | +| time_elapsed | 32875 | +| total_timesteps | 10161152 | +| train/ | | +| approx_kl | 2.4171813 | +| clip_fraction | 0.488 | +| clip_range | 0.2 | +| entropy_loss | -0.364 | +| explained_variance | -9.76 | +| learning_rate | 0.0001 | +| loss | -0.0687 | +| n_updates | 159750 | +| policy_gradient_loss | -0.0729 | +| value_loss | 0.000437 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.96e+03 | +| ep_rew_mean | 0.152 | +| time/ | | +| fps | 309 | +| iterations | 9924 | +| time_elapsed | 32879 | +| total_timesteps | 10162176 | +| train/ | | +| approx_kl | 2.136922 | +| clip_fraction | 0.48 | +| clip_range | 0.2 | +| entropy_loss | -0.356 | +| explained_variance | -1.66 | +| learning_rate | 0.0001 | +| loss | -0.0753 | +| n_updates | 159760 | +| policy_gradient_loss | -0.0634 | +| value_loss | 0.000373 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.96e+03 | +| ep_rew_mean | 0.152 | +| time/ | | +| fps | 309 | +| iterations | 9925 | +| time_elapsed | 32883 | +| total_timesteps | 10163200 | +| train/ | | +| approx_kl | 2.1929975 | +| clip_fraction | 0.535 | +| clip_range | 0.2 | +| entropy_loss | -0.419 | +| explained_variance | -1.28 | +| learning_rate | 0.0001 | +| loss | -0.128 | +| n_updates | 159770 | +| policy_gradient_loss | -0.0757 | +| value_loss | 0.000602 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.96e+03 | +| ep_rew_mean | 0.151 | +| time/ | | +| fps | 309 | +| iterations | 9926 | +| time_elapsed | 32887 | +| total_timesteps | 10164224 | +| train/ | | +| approx_kl | 2.6682105 | +| clip_fraction | 0.507 | +| clip_range | 0.2 | +| entropy_loss | -0.388 | +| explained_variance | -1.92 | +| learning_rate | 0.0001 | +| loss | -0.104 | +| n_updates | 159780 | +| policy_gradient_loss | -0.0783 | +| value_loss | 0.000291 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.95e+03 | +| ep_rew_mean | 0.147 | +| time/ | | +| fps | 309 | +| iterations | 9927 | +| time_elapsed | 32891 | +| total_timesteps | 10165248 | +| train/ | | +| approx_kl | 2.2416348 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.363 | +| explained_variance | -1.17 | +| learning_rate | 0.0001 | +| loss | -0.0995 | +| n_updates | 159790 | +| policy_gradient_loss | -0.071 | +| value_loss | 0.000479 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.95e+03 | +| ep_rew_mean | 0.147 | +| time/ | | +| fps | 309 | +| iterations | 9928 | +| time_elapsed | 32895 | +| total_timesteps | 10166272 | +| train/ | | +| approx_kl | 2.0834694 | +| clip_fraction | 0.492 | +| clip_range | 0.2 | +| entropy_loss | -0.406 | +| explained_variance | -1.7 | +| learning_rate | 0.0001 | +| loss | -0.0753 | +| n_updates | 159800 | +| policy_gradient_loss | -0.0742 | +| value_loss | 0.000541 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.94e+03 | +| ep_rew_mean | 0.144 | +| time/ | | +| fps | 309 | +| iterations | 9929 | +| time_elapsed | 32900 | +| total_timesteps | 10167296 | +| train/ | | +| approx_kl | 2.444008 | +| clip_fraction | 0.483 | +| clip_range | 0.2 | +| entropy_loss | -0.358 | +| explained_variance | -2.55 | +| learning_rate | 0.0001 | +| loss | -0.105 | +| n_updates | 159810 | +| policy_gradient_loss | -0.0726 | +| value_loss | 0.000596 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.94e+03 | +| ep_rew_mean | 0.144 | +| time/ | | +| fps | 309 | +| iterations | 9930 | +| time_elapsed | 32904 | +| total_timesteps | 10168320 | +| train/ | | +| approx_kl | 2.3719208 | +| clip_fraction | 0.468 | +| clip_range | 0.2 | +| entropy_loss | -0.351 | +| explained_variance | -1.66 | +| learning_rate | 0.0001 | +| loss | -0.0871 | +| n_updates | 159820 | +| policy_gradient_loss | -0.0723 | +| value_loss | 0.000505 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.94e+03 | +| ep_rew_mean | 0.144 | +| time/ | | +| fps | 309 | +| iterations | 9931 | +| time_elapsed | 32908 | +| total_timesteps | 10169344 | +| train/ | | +| approx_kl | 1.9863634 | +| clip_fraction | 0.509 | +| clip_range | 0.2 | +| entropy_loss | -0.437 | +| explained_variance | -3.41 | +| learning_rate | 0.0001 | +| loss | -0.1 | +| n_updates | 159830 | +| policy_gradient_loss | -0.0726 | +| value_loss | 0.000373 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.94e+03 | +| ep_rew_mean | 0.144 | +| time/ | | +| fps | 309 | +| iterations | 9932 | +| time_elapsed | 32912 | +| total_timesteps | 10170368 | +| train/ | | +| approx_kl | 2.4474263 | +| clip_fraction | 0.515 | +| clip_range | 0.2 | +| entropy_loss | -0.425 | +| explained_variance | -0.41 | +| learning_rate | 0.0001 | +| loss | -0.12 | +| n_updates | 159840 | +| policy_gradient_loss | -0.0679 | +| value_loss | 0.000376 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.93e+03 | +| ep_rew_mean | 0.137 | +| time/ | | +| fps | 309 | +| iterations | 9933 | +| time_elapsed | 32916 | +| total_timesteps | 10171392 | +| train/ | | +| approx_kl | 2.3095171 | +| clip_fraction | 0.477 | +| clip_range | 0.2 | +| entropy_loss | -0.35 | +| explained_variance | -5.88 | +| learning_rate | 0.0001 | +| loss | -0.0848 | +| n_updates | 159850 | +| policy_gradient_loss | -0.0711 | +| value_loss | 0.000425 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.93e+03 | +| ep_rew_mean | 0.137 | +| time/ | | +| fps | 308 | +| iterations | 9934 | +| time_elapsed | 32921 | +| total_timesteps | 10172416 | +| train/ | | +| approx_kl | 2.8967733 | +| clip_fraction | 0.501 | +| clip_range | 0.2 | +| entropy_loss | -0.403 | +| explained_variance | -0.788 | +| learning_rate | 0.0001 | +| loss | -0.0986 | +| n_updates | 159860 | +| policy_gradient_loss | -0.0713 | +| value_loss | 0.000706 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.92e+03 | +| ep_rew_mean | 0.136 | +| time/ | | +| fps | 308 | +| iterations | 9935 | +| time_elapsed | 32925 | +| total_timesteps | 10173440 | +| train/ | | +| approx_kl | 2.0020838 | +| clip_fraction | 0.501 | +| clip_range | 0.2 | +| entropy_loss | -0.379 | +| explained_variance | -4.45 | +| learning_rate | 0.0001 | +| loss | -0.121 | +| n_updates | 159870 | +| policy_gradient_loss | -0.0771 | +| value_loss | 0.000434 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.9e+03 | +| ep_rew_mean | 0.128 | +| time/ | | +| fps | 308 | +| iterations | 9936 | +| time_elapsed | 32929 | +| total_timesteps | 10174464 | +| train/ | | +| approx_kl | 1.8324046 | +| clip_fraction | 0.514 | +| clip_range | 0.2 | +| entropy_loss | -0.422 | +| explained_variance | -1.15 | +| learning_rate | 0.0001 | +| loss | -0.11 | +| n_updates | 159880 | +| policy_gradient_loss | -0.0759 | +| value_loss | 0.000252 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.9e+03 | +| ep_rew_mean | 0.128 | +| time/ | | +| fps | 308 | +| iterations | 9937 | +| time_elapsed | 32933 | +| total_timesteps | 10175488 | +| train/ | | +| approx_kl | 2.0264463 | +| clip_fraction | 0.468 | +| clip_range | 0.2 | +| entropy_loss | -0.329 | +| explained_variance | -0.508 | +| learning_rate | 0.0001 | +| loss | -0.0911 | +| n_updates | 159890 | +| policy_gradient_loss | -0.0477 | +| value_loss | 0.000718 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.89e+03 | +| ep_rew_mean | 0.129 | +| time/ | | +| fps | 308 | +| iterations | 9938 | +| time_elapsed | 32937 | +| total_timesteps | 10176512 | +| train/ | | +| approx_kl | 2.3098197 | +| clip_fraction | 0.465 | +| clip_range | 0.2 | +| entropy_loss | -0.327 | +| explained_variance | -2.63 | +| learning_rate | 0.0001 | +| loss | -0.103 | +| n_updates | 159900 | +| policy_gradient_loss | -0.0719 | +| value_loss | 0.000526 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.127 | +| time/ | | +| fps | 308 | +| iterations | 9939 | +| time_elapsed | 32941 | +| total_timesteps | 10177536 | +| train/ | | +| approx_kl | 3.0026236 | +| clip_fraction | 0.494 | +| clip_range | 0.2 | +| entropy_loss | -0.424 | +| explained_variance | -1.91 | +| learning_rate | 0.0001 | +| loss | -0.076 | +| n_updates | 159910 | +| policy_gradient_loss | -0.07 | +| value_loss | 0.000356 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.127 | +| time/ | | +| fps | 308 | +| iterations | 9940 | +| time_elapsed | 32944 | +| total_timesteps | 10178560 | +| train/ | | +| approx_kl | 2.8083224 | +| clip_fraction | 0.479 | +| clip_range | 0.2 | +| entropy_loss | -0.354 | +| explained_variance | -1.75 | +| learning_rate | 0.0001 | +| loss | -0.0836 | +| n_updates | 159920 | +| policy_gradient_loss | -0.0629 | +| value_loss | 0.000608 | +--------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.88e+03 | +| ep_rew_mean | 0.127 | +| time/ | | +| fps | 308 | +| iterations | 9941 | +| time_elapsed | 32947 | +| total_timesteps | 10179584 | +| train/ | | +| approx_kl | 2.153439 | +| clip_fraction | 0.486 | +| clip_range | 0.2 | +| entropy_loss | -0.365 | +| explained_variance | -9.65 | +| learning_rate | 0.0001 | +| loss | -0.0811 | +| n_updates | 159930 | +| policy_gradient_loss | -0.0724 | +| value_loss | 0.00033 | +-------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.89e+03 | +| ep_rew_mean | 0.122 | +| time/ | | +| fps | 308 | +| iterations | 9942 | +| time_elapsed | 32951 | +| total_timesteps | 10180608 | +| train/ | | +| approx_kl | 2.8069293 | +| clip_fraction | 0.479 | +| clip_range | 0.2 | +| entropy_loss | -0.338 | +| explained_variance | -1.36 | +| learning_rate | 0.0001 | +| loss | -0.0862 | +| n_updates | 159940 | +| policy_gradient_loss | -0.0723 | +| value_loss | 0.000305 | +--------------------------------------- diff --git a/004_image_stack_ram_based_reward_custom/tune_ppo.py b/004_rgb_stack_ram_based_reward_custom/tune_ppo.py similarity index 100% rename from 004_image_stack_ram_based_reward_custom/tune_ppo.py rename to 004_rgb_stack_ram_based_reward_custom/tune_ppo.py diff --git a/006_rgb_stack_ram_based_reward_time_reward_final_round/__pycache__/street_fighter_custom_wrapper.cpython-38.pyc b/006_rgb_stack_ram_based_reward_time_reward_final_round/__pycache__/street_fighter_custom_wrapper.cpython-38.pyc new file mode 100644 index 0000000..b2c9a45 Binary files /dev/null and b/006_rgb_stack_ram_based_reward_time_reward_final_round/__pycache__/street_fighter_custom_wrapper.cpython-38.pyc differ diff --git a/006_rgb_stack_ram_based_reward_time_reward_final_round/check_reward.py b/006_rgb_stack_ram_based_reward_time_reward_final_round/check_reward.py new file mode 100644 index 0000000..b3b7256 --- /dev/null +++ b/006_rgb_stack_ram_based_reward_time_reward_final_round/check_reward.py @@ -0,0 +1,51 @@ +import os +import time + +import retro +from stable_baselines3.common.monitor import Monitor + +from street_fighter_custom_wrapper import StreetFighterCustomWrapper + +LOG_DIR = 'logs/' +os.makedirs(LOG_DIR, exist_ok=True) + +def make_env(game, state): + def _init(): + env = retro.make( + game=game, + state=state, + use_restricted_actions=retro.Actions.FILTERED, + obs_type=retro.Observations.IMAGE + ) + env = StreetFighterCustomWrapper(env) + return env + return _init + +game = "StreetFighterIISpecialChampionEdition-Genesis" +state = "Champion.Level1.RyuVsGuile" + +env = make_env(game, state)() +env = Monitor(env, 'logs/') + +num_episodes = 30 +episode_reward_sum = 0 +for _ in range(num_episodes): + done = False + obs = env.reset() + total_reward = 0 + while not done: + timestamp = time.time() + obs, reward, done, info = env.step(env.action_space.sample()) + + # Note that if player wins but only has 0 HP left, the winning reward is still 0, so it won't be printed. + if reward != 0: + total_reward += reward + print("Reward: {}, playerHP: {}, enemyHP:{}".format(reward, info['health'], info['enemy_health'])) + env.render() + # time.sleep(0.005) + + print("Total reward: {}".format(total_reward)) + episode_reward_sum += total_reward + +env.close() +print("Average reward for random strategy: {}".format(episode_reward_sum/num_episodes)) diff --git a/006_rgb_stack_ram_based_reward_time_reward_final_round/custom_cnn.py b/006_rgb_stack_ram_based_reward_time_reward_final_round/custom_cnn.py new file mode 100644 index 0000000..25c50ea --- /dev/null +++ b/006_rgb_stack_ram_based_reward_time_reward_final_round/custom_cnn.py @@ -0,0 +1,24 @@ +import gym +import torch +import torch.nn as nn +from stable_baselines3.common.torch_layers import BaseFeaturesExtractor + +# Custom feature extractor (CNN) +class CustomCNN(BaseFeaturesExtractor): + def __init__(self, observation_space: gym.Space): + super(CustomCNN, self).__init__(observation_space, features_dim=512) + self.cnn = nn.Sequential( + nn.Conv2d(4, 32, kernel_size=5, stride=2, padding=0), + nn.ReLU(), + nn.Conv2d(32, 64, kernel_size=5, stride=2, padding=0), + nn.ReLU(), + nn.Conv2d(64, 64, kernel_size=3, stride=1, padding=0), + nn.ReLU(), + nn.Flatten(), + nn.Linear(16384, self.features_dim), + nn.ReLU() + ) + + def forward(self, observations: torch.Tensor) -> torch.Tensor: + return self.cnn(observations) + \ No newline at end of file diff --git a/006_rgb_stack_ram_based_reward_time_reward_final_round/evaluate.py b/006_rgb_stack_ram_based_reward_time_reward_final_round/evaluate.py new file mode 100644 index 0000000..c435f08 --- /dev/null +++ b/006_rgb_stack_ram_based_reward_time_reward_final_round/evaluate.py @@ -0,0 +1,52 @@ +import retro + +from stable_baselines3 import PPO +from stable_baselines3.common.vec_env import DummyVecEnv +from stable_baselines3.common.monitor import Monitor +from stable_baselines3.common.evaluation import evaluate_policy + +from custom_cnn import CustomCNN +from street_fighter_custom_wrapper import StreetFighterCustomWrapper + +def make_env(game, state): + def _init(): + env = retro.make( + game=game, + state=state, + use_restricted_actions=retro.Actions.FILTERED, + obs_type=retro.Observations.IMAGE + ) + env = StreetFighterCustomWrapper(env) + return env + return _init + +game = "StreetFighterIISpecialChampionEdition-Genesis" +state_stages = [ + "Champion.Level1.ChunLiVsGuile", + "Champion.Level2.ChunLiVsKen", + "Champion.Level3.ChunLiVsChunLi", + "Champion.Level4.ChunLiVsZangief", + "Champion.Level5.ChunLiVsDhalsim", + "Champion.Level6.ChunLiVsRyu", + "Champion.Level7.ChunLiVsEHonda", + "Champion.Level8.ChunLiVsBlanka", + "Champion.Level9.ChunLiVsBalrog", + "Champion.Level10.ChunLiVsVega", + "Champion.Level11.ChunLiVsSagat", + "Champion.Level12.ChunLiVsBison" + # Add other stages as necessary +] + +env = make_env(game, state_stages[0])() + +# Wrap the environment +# env = Monitor(env, 'logs/') + +policy_kwargs = {'features_extractor_class': CustomCNN} +model = PPO("CnnPolicy", env, policy_kwargs=policy_kwargs) + +model = PPO.load(r"dummy_model_ppo_chunli") +# model.load(r"trained_models/ppo_chunli_864000_steps") + +mean_reward, std_reward = evaluate_policy(model, env, render=True, n_eval_episodes=10, deterministic=False, return_episode_rewards=True) +print(f"Mean reward: {mean_reward:.2f} +/- {std_reward:.2f}") diff --git a/006_rgb_stack_ram_based_reward_time_reward_final_round/logs/0/monitor.csv b/006_rgb_stack_ram_based_reward_time_reward_final_round/logs/0/monitor.csv new file mode 100644 index 0000000..a1b646d --- /dev/null +++ b/006_rgb_stack_ram_based_reward_time_reward_final_round/logs/0/monitor.csv @@ -0,0 +1,464 @@ +#{"t_start": 1680618620.5349822, "env_id": null} +r,l,t +0.175557,1694,26.36644 +0.297453,1369,42.001171 +0.316258,1349,58.591356 +-0.170979,551,64.691608 +0.285042,2022,89.397835 +0.260378,1503,107.777022 +0.327621,2248,134.342297 +0.049971,1636,154.193691 +-0.338,722,163.37777 +0.32358,1678,183.294785 +0.469401,1670,203.313653 +0.048136,864,214.0148 +0.447798,1455,230.978593 +0.244277,1188,244.869213 +-0.234288,740,254.000359 +0.296153,1443,271.444621 +0.121057,1170,286.05505 +-0.009942,1274,300.347498 +0.2613,1472,318.778883 +0.317495,1748,340.185676 +0.326699,1736,360.501755 +0.608096,1223,375.595313 +0.023881,1224,389.735857 +0.302357,1134,403.209213 +-0.013502,859,413.638698 +-0.003771,709,421.642036 +0.214053,1559,440.962049 +0.239167,1053,453.375899 +0.222053,1276,468.919704 +0.491652,992,480.978358 +0.649052,920,492.035498 +-0.021502,1106,504.816763 +0.200453,950,516.712689 +0.463972,1674,536.901105 +-0.044298,1047,549.271691 +-0.035422,818,558.745198 +0.300258,1840,581.078904 +0.319538,1544,599.347467 +0.522776,1395,616.199559 +0.491601,1755,637.816793 +0.16923,1275,652.479726 +-0.339,657,661.302035 +0.57078,1290,677.027712 +0.109344,974,688.32304 +0.257589,1771,710.142448 +0.298258,1557,728.640277 +0.461099,1445,746.890524 +0.180714,1616,765.837248 +0.11065,921,776.889595 +0.228488,1574,796.39212 +0.293206,2062,821.380586 +0.046971,1389,838.711424 +0.053519,1254,853.282397 +0.225866,1361,870.16437 +0.475065,1791,891.784577 +0.496056,1186,905.485129 +0.518465,1347,922.047951 +0.039437,1258,936.985906 +0.432745,1695,957.366476 +0.335699,1596,975.894452 +0.032887,1525,994.848077 +0.53634,953,1007.43495 +-0.133312,802,1017.196602 +-0.034337,1330,1033.05701 +0.183921,1446,1051.375265 +0.028737,1181,1065.463056 +0.040887,1575,1084.176345 +0.479735,1724,1105.099921 +0.172059,1033,1117.39676 +0.124314,1440,1134.371906 +0.100714,1218,1149.526981 +0.234277,1711,1170.180137 +-0.036295,1138,1184.258761 +0.03155,1438,1201.610575 +0.164701,1590,1220.618049 +0.432393,1555,1240.277837 +0.536552,1404,1257.231191 +0.483204,1414,1274.08168 +0.57104,990,1285.386045 +0.326661,1785,1307.336887 +0.06549,1007,1319.882915 +0.343843,1468,1337.97112 +0.248053,1252,1352.204933 +0.087668,1002,1364.593586 +0.219816,1289,1380.274341 +0.242589,1259,1396.035966 +0.482868,1713,1418.177613 +0.337621,2126,1443.281836 +0.268667,1316,1458.889297 +0.433817,2276,1486.579544 +0.332098,1543,1505.131691 +0.274734,1167,1518.92915 +0.125053,1339,1535.974616 +0.101368,1144,1550.556735 +0.061437,1608,1570.741634 +0.118238,1089,1585.305697 +0.360843,1716,1605.706502 +0.337699,1928,1627.63124 +0.128277,1154,1640.786158 +0.194157,1866,1662.864744 +0.300308,1997,1685.972941 +0.326098,1862,1707.278988 +0.636146,1103,1720.53155 +-0.347,595,1726.632068 +0.181714,1429,1743.764102 +0.444632,2344,1770.811991 +0.300258,1141,1784.098058 +0.178714,1327,1799.044747 +0.003368,928,1809.444721 +0.517836,1486,1826.960614 +0.455779,1225,1841.166777 +-0.332,769,1849.872639 +0.512481,1292,1864.532353 +0.540794,1128,1876.500257 +0.258488,1012,1888.252762 +0.303598,1672,1907.596181 +0.223053,1287,1922.413469 +0.670465,918,1933.83377 +0.072959,1235,1947.624959 +0.187014,1118,1960.727214 +0.085926,1021,1972.587279 +0.150057,1146,1986.131281 +0.009728,875,1996.565743 +0.302527,1030,2010.020566 +0.213053,1128,2024.718174 +0.312924,1682,2045.451381 +0.193014,947,2055.757803 +0.575344,963,2067.128321 +0.555002,1525,2084.293831 +0.324621,1579,2101.63007 +0.128519,921,2111.887091 +0.274453,1156,2124.838457 +0.36994,1843,2146.109775 +0.344808,1617,2163.565612 +0.341843,1458,2180.11848 +-0.074307,1340,2194.751863 +0.514612,1472,2211.486664 +-0.034422,1117,2223.175213 +0.228589,1235,2237.243429 +0.381803,1704,2256.084846 +0.517507,1571,2274.374554 +0.348699,1693,2293.017474 +0.296153,2052,2316.02149 +-0.044531,828,2324.76264 +0.69311,863,2334.65857 +0.078437,773,2343.129894 +-0.038674,894,2353.176141 +0.217053,1508,2370.197885 +0.215053,1453,2386.21162 +0.075421,1371,2401.645391 +0.207432,1015,2412.943262 +0.580551,1305,2427.207219 +0.067711,1452,2443.335835 +0.35297,1989,2466.184271 +0.335495,1148,2479.008814 +0.344808,1421,2494.967132 +0.309357,1703,2513.563421 +0.624178,1342,2529.162301 +0.227384,1379,2544.510073 +0.358876,1594,2561.802312 +0.382843,2032,2584.296656 +0.343661,1269,2598.55894 +0.121057,1305,2612.879102 +0.189396,1586,2630.230506 +0.099302,988,2641.533065 +0.35394,1896,2662.955544 +0.542399,1068,2674.425554 +0.519446,1642,2692.759789 +0.594168,1210,2705.809661 +0.36494,1616,2723.962691 +-0.152979,820,2733.775229 +0.276863,1660,2751.342108 +-0.123312,774,2760.769773 +0.203564,1249,2774.112725 +0.236783,1364,2789.566412 +0.264488,1202,2802.716457 +0.293153,2071,2826.603885 +0.46435,2436,2853.80781 +0.204692,1544,2871.240605 +0.355737,2243,2895.827897 +0.264098,1355,2911.224123 +0.35797,1253,2925.375071 +-0.168979,1207,2938.171709 +0.522026,1162,2951.124314 +0.07349,1238,2965.168098 +0.293924,1508,2981.098013 +0.171322,1121,2994.042814 +0.608848,1212,3007.983826 +0.308404,1887,3028.726074 +0.026737,1167,3042.548907 +0.575871,1387,3057.178848 +0.504268,1599,3075.434563 +0.34894,1555,3092.733527 +0.06387,1289,3107.038562 +-0.051531,1043,3118.402655 +0.266598,1608,3136.720351 +0.211053,1188,3149.853019 +0.323308,1113,3162.57177 +0.332098,1860,3183.106149 +0.213297,1416,3199.626201 +0.088302,1242,3214.171248 +0.648562,972,3225.875777 +-0.229288,760,3234.679651 +0.582557,1252,3248.116014 +0.367908,1294,3263.714815 +0.308357,1516,3280.409474 +0.17223,1359,3296.520706 +0.244488,1459,3313.307134 +-0.346,790,3323.84806 +0.357843,2008,3347.341581 +0.499568,1650,3367.446578 +0.194883,1398,3384.355377 +0.17823,1349,3401.118892 +0.608593,1078,3413.490413 +0.186515,1291,3429.041662 +0.06387,1234,3444.374147 +0.493711,1251,3459.628421 +0.294206,1564,3478.220637 +0.163883,1142,3491.996987 +0.666636,898,3502.836125 +0.684686,730,3510.901565 +0.095023,860,3521.750679 +0.1743,1264,3537.059595 +0.245816,1282,3551.651176 +0.266378,1290,3566.179015 +0.089926,988,3577.700983 +0.098368,1345,3592.450832 +0.239876,2164,3616.827502 +0.05332,953,3627.962656 +0.226488,1201,3641.088664 +0.127564,1434,3656.926814 +0.472911,1803,3677.026037 +0.119028,1322,3692.391764 +0.516877,1409,3708.148608 +0.194322,905,3718.415336 +-0.166979,937,3728.645482 +0.18523,1452,3744.869764 +0.437404,1306,3760.482677 +-0.079263,1195,3773.632644 +-0.042345,871,3783.554236 +0.484613,1520,3800.948073 +0.330737,1505,3817.120873 +0.355808,1550,3834.397148 +0.027518,750,3842.836147 +-0.151677,1119,3855.572821 +0.08087,1158,3868.711388 +-0.114489,594,3875.689814 +0.335808,1933,3897.234256 +0.027948,870,3907.236917 +0.438204,2030,3929.982847 +0.129564,1668,3948.548026 +0.018402,1072,3960.193839 +0.185866,1797,3980.055534 +0.573204,1235,3993.963613 +0.328538,1493,4010.071692 +0.066305,1113,4022.629319 +0.181322,1249,4036.651772 +0.351661,1221,4049.893539 +0.477994,1584,4068.102012 +0.081302,1281,4082.581761 +0.308667,1383,4097.385808 +0.523528,1214,4112.098281 +0.345538,1454,4128.3088 +0.523595,1480,4145.45736 +-0.015623,1387,4161.665227 +0.19123,1233,4175.034482 +-0.039345,1000,4186.564679 +0.586696,1083,4199.508359 +0.280734,1669,4218.347484 +0.098538,804,4227.332446 +0.474698,1604,4245.184968 +0.499757,1331,4261.029082 +0.636879,916,4271.360873 +-0.339,664,4278.64682 +0.150921,1103,4291.413805 +0.344843,1487,4307.738596 +0.700451,880,4317.696767 +0.002058,1050,4330.114878 +0.238984,1764,4349.224837 +0.572113,1378,4364.903683 +0.217277,1647,4383.289084 +0.351876,1563,4400.559933 +0.232783,1775,4420.61872 +0.2663,1328,4435.42546 +0.251153,1779,4455.635929 +0.336737,1650,4474.271004 +0.330661,1852,4495.420458 +0.014225,992,4505.971641 +-0.044345,901,4516.000974 +0.167883,1368,4531.585924 +0.335773,1563,4548.844691 +0.466269,1920,4570.345135 +0.008855,1086,4583.138252 +0.51341,1767,4603.449596 +0.134043,1691,4622.456842 +0.458607,1346,4637.203973 +0.728215,900,4647.647573 +0.021881,1221,4661.729426 +0.646557,1252,4675.96687 +0.532706,1495,4691.924966 +0.217277,1241,4706.247124 +0.508811,1206,4719.482471 +0.270598,1409,4735.074966 +0.439135,1981,4757.485094 +0.576995,1302,4771.897727 +0.502181,1335,4787.464476 +0.176059,1162,4800.515446 +0.153124,1519,4817.95117 +0.332621,2309,4843.701416 +0.324661,1545,4860.983007 +0.032737,1402,4876.839892 +0.472529,1807,4897.035953 +0.505624,1570,4914.387007 +0.326661,1808,4934.827081 +0.57339,1376,4950.579439 +0.524841,1594,4968.299503 +0.483006,1741,4988.21197 +-0.121489,916,4998.519326 +0.18023,1581,5016.166409 +0.211297,1119,5029.045728 +0.134807,1190,5042.244612 +0.251138,1121,5055.102743 +0.337773,1725,5075.130495 +0.76264,647,5082.386138 +0.478803,1704,5101.194198 +0.161792,1080,5112.910315 +0.735003,762,5121.424225 +0.522147,1407,5137.301287 +0.587642,1245,5151.690204 +0.60636,1443,5167.605267 +0.06287,1154,5180.6469 +0.098926,1261,5195.044199 +0.351326,1728,5215.255989 +0.569762,1066,5227.075678 +0.520698,1381,5242.859142 +0.606955,1006,5254.483362 +0.461047,1855,5274.79125 +0.460597,1389,5290.798057 +0.39797,1782,5310.985806 +0.189866,1336,5325.973648 +-0.007623,1008,5337.363266 +0.340206,1660,5356.572809 +0.48075,1345,5372.469926 +0.266138,1365,5387.254716 +0.466624,1806,5408.679072 +-0.043345,731,5416.204696 +0.477815,1310,5431.968788 +0.694265,844,5440.870117 +0.331538,2129,5465.153203 +0.613811,1206,5478.325413 +0.423455,1717,5498.278373 +-0.245923,1193,5511.695644 +0.074484,1316,5526.462827 +0.614219,1114,5539.513687 +0.136043,1298,5554.171403 +0.229167,1246,5568.650827 +0.187557,1795,5589.095341 +0.599668,1374,5604.684873 +0.492923,1576,5622.234624 +0.596422,1136,5635.306347 +0.071421,1124,5648.295425 +0.000402,901,5658.593491 +0.758645,811,5667.525487 +0.252488,1111,5680.703352 +0.544255,1222,5694.107345 +0.11565,978,5705.746945 +0.431188,1898,5727.809695 +0.635139,954,5738.481991 +0.508543,1434,5754.592428 +0.045971,1076,5767.457963 +0.35894,1817,5788.039174 +0.516551,1632,5806.85286 +0.623126,1064,5818.56877 +0.305984,1271,5833.28462 +-0.150268,721,5840.905219 +0.47923,1853,5862.669937 +0.119936,1275,5877.552455 +0.425672,1999,5900.94608 +0.5119,1752,5920.666188 +0.36794,1415,5937.2164 +0.822401,614,5944.546984 +0.512924,1924,5966.507948 +-0.043298,1268,5981.052058 +0.214167,1737,6001.260277 +0.475352,1718,6021.28685 +0.265453,1817,6042.673456 +0.35197,1579,6062.035438 +0.295924,2182,6088.071027 +0.703221,1058,6100.298678 +0.224384,1889,6122.557107 +0.559914,1001,6133.57758 +0.643215,900,6144.276534 +0.259384,1142,6157.747023 +0.173396,1391,6174.053352 +0.496446,1642,6193.3997 +0.137792,1478,6211.115602 +0.079538,1000,6222.277927 +0.24722,1359,6239.064489 +0.155314,1101,6252.877259 +0.220277,1691,6273.626719 +-0.057623,1174,6288.141941 +0.183322,1202,6302.138001 +0.477904,1762,6323.976152 +0.339843,1684,6344.669239 +0.452762,1586,6364.194056 +0.692593,1078,6376.667487 +0.723344,948,6388.713135 +0.280984,1786,6409.199019 +0.215714,1298,6426.196382 +0.131057,1165,6440.076642 +0.564551,1305,6456.376497 +0.659598,982,6468.684055 +0.620668,1374,6484.172106 +0.67507,854,6494.765885 +-0.346,677,6502.479073 +0.700528,577,6509.757691 +0.238053,1302,6525.169837 +0.089023,1563,6543.374559 +-0.149111,1110,6556.931417 +0.185322,1700,6577.216203 +-0.135121,962,6589.221593 +-0.339,770,6598.652669 +0.248495,1765,6618.751398 +0.452182,1921,6642.034839 +0.336538,2305,6669.776224 +0.230688,1678,6691.416605 +0.59298,1282,6706.72366 +0.146921,1287,6722.147993 +0.479047,1946,6745.467303 +0.313357,1696,6766.038196 +0.581554,807,6775.622432 +0.318924,1567,6795.989762 +0.670478,894,6807.084485 +0.32158,1460,6824.755363 +0.153322,1156,6838.955743 +0.334621,1672,6859.535887 +0.343773,1596,6879.214252 +0.602528,1159,6893.1659 +0.112703,922,6904.186761 +0.057484,1119,6917.707233 +0.239876,1489,6935.015982 +0.190866,1396,6952.128572 +0.338621,1951,6975.63249 +0.589668,1456,6994.47972 +-0.053674,1073,7007.079554 +0.5772,1155,7021.077112 +0.14065,1285,7036.832731 +0.679005,901,7047.709272 +0.189515,1374,7064.904315 +0.2533,1728,7085.216779 +0.263138,1279,7100.762434 +0.531219,1626,7121.197615 +0.417875,1913,7145.021642 +0.165792,1282,7160.562574 +0.787483,588,7168.28985 +-0.161979,901,7179.210262 +0.53139,1572,7198.08008 +0.697722,1002,7210.548492 +0.537207,1499,7228.86597 +0.095668,1048,7241.318922 +0.084302,1211,7255.369863 +0.097023,1270,7270.621816 diff --git a/006_rgb_stack_ram_based_reward_time_reward_final_round/logs/1/monitor.csv b/006_rgb_stack_ram_based_reward_time_reward_final_round/logs/1/monitor.csv new file mode 100644 index 0000000..084af60 --- /dev/null +++ b/006_rgb_stack_ram_based_reward_time_reward_final_round/logs/1/monitor.csv @@ -0,0 +1,477 @@ +#{"t_start": 1680618620.5359814, "env_id": null} +r,l,t +-0.041282,1650,25.179703 +0.477116,1645,44.972401 +0.02455,1267,60.09565 +0.600054,1081,73.384743 +0.32645,1752,94.228608 +0.37397,1958,118.447109 +0.121816,1191,132.545189 +0.31858,1259,147.887785 +-0.168677,777,157.080308 +0.282924,1951,180.311305 +0.541891,1620,200.114001 +-0.172791,767,209.476433 +-0.18035,901,220.107748 +-0.347,747,229.060402 +0.054971,1170,243.033744 +0.234384,1578,261.868997 +-0.024345,1049,274.393688 +-0.128489,1222,289.262488 +-0.35,910,300.028502 +-0.020298,931,311.163597 +0.045971,1681,331.250468 +0.285984,1662,351.267477 +-0.018623,1284,366.643852 +0.492012,1408,383.680312 +0.432956,1593,402.962212 +-0.071913,851,412.376018 +0.255167,1314,428.765921 +-0.125489,681,436.580059 +0.07823,1233,451.651291 +0.259378,1376,467.621689 +0.257453,1643,487.636364 +0.267598,1553,506.293225 +0.343876,1786,527.837933 +-0.161979,828,538.353995 +0.550543,1434,555.362123 +0.07187,1193,569.165365 +0.178396,1162,582.855779 +0.267667,1856,605.399148 +0.385963,1485,622.87458 +0.328699,1459,641.251167 +0.076959,1605,660.165778 +0.35365,2063,685.348186 +-0.134121,889,696.237098 +-0.011623,1130,710.212449 +0.5069,1752,731.535379 +0.490815,1310,747.220525 +0.131564,1227,762.474298 +0.277527,1592,781.313341 +0.094668,1429,798.386295 +0.277378,1528,816.947526 +0.235783,1968,841.848094 +0.202297,1308,857.599852 +0.054994,1167,871.668802 +0.51804,1601,891.490577 +0.32158,1573,909.899316 +0.086926,1182,923.587173 +0.439794,1949,946.366853 +0.282598,2094,972.412912 +0.054437,872,982.135221 +0.071139,971,994.706775 +0.368661,1219,1010.535471 +-0.323,497,1015.841691 +0.048971,1249,1031.390479 +0.332661,2146,1057.665394 +0.341661,1689,1078.025789 +0.18523,1213,1093.076896 +0.126057,1242,1106.973181 +0.185258,1703,1127.989442 +0.418655,2327,1155.895261 +0.353908,1454,1173.56826 +0.35497,1739,1195.252969 +-0.022623,1052,1207.815617 +-0.040298,1050,1220.476818 +0.138043,1193,1235.611367 +0.020225,1020,1247.050922 +0.238488,1743,1268.266366 +0.019518,1118,1282.02533 +0.241965,2063,1307.154889 +0.195876,1446,1324.552756 +0.324,1258,1339.712272 +0.484661,1715,1359.950237 +-0.24835,437,1365.947384 +0.079538,1682,1386.428053 +0.468732,1826,1409.189488 +0.017855,971,1421.504305 +0.463043,1721,1441.873211 +-0.030282,1077,1455.419904 +0.328908,1946,1478.624956 +0.202396,1283,1494.149474 +0.600033,1032,1506.498879 +0.434386,1708,1526.847021 +-0.046674,931,1539.162309 +-0.013623,1017,1552.064923 +0.102866,1038,1565.349419 +0.479773,1858,1588.82365 +0.647148,787,1598.408194 +0.434046,1866,1620.119695 +0.287042,1516,1637.634017 +0.076728,967,1648.236692 +0.291598,1377,1664.335497 +0.156515,1515,1681.824734 +0.470739,2075,1705.848419 +0.199432,1501,1723.428679 +-0.085357,1132,1736.618508 +0.510612,1472,1753.021368 +0.357843,1245,1767.880664 +0.308153,1412,1784.22406 +0.432438,1679,1803.397932 +0.011058,803,1812.378924 +0.204258,1433,1829.654957 +0.337661,1539,1847.015913 +0.516779,1225,1860.375845 +0.332773,1488,1877.630482 +0.244138,1606,1895.656998 +0.615875,1082,1908.818524 +0.503529,1807,1929.548541 +0.623739,1140,1943.016832 +0.157322,1885,1964.873559 +-0.031345,875,1974.249643 +0.095368,1223,1989.071544 +0.319538,1163,2003.308738 +0.522229,1287,2019.996664 +0.720872,810,2029.998028 +0.013139,1020,2042.919974 +0.675238,1015,2054.290576 +0.489071,1592,2072.818539 +-0.019502,1048,2084.45117 +0.679737,874,2094.260188 +-0.162979,861,2103.29844 +0.331621,1481,2120.401725 +0.071139,1213,2134.640445 +-0.113489,1102,2146.385777 +0.25422,1554,2163.589632 +0.180714,1200,2177.301262 +-0.35,589,2183.334232 +0.545124,1524,2200.418355 +0.265667,1594,2218.669544 +-0.033282,852,2227.45265 +0.26022,1653,2245.998016 +0.123792,1640,2264.586469 +-0.145268,1161,2277.499456 +-0.071913,883,2287.456232 +0.221816,1810,2307.510643 +0.282876,1365,2323.13476 +-0.338,597,2329.089879 +0.611748,946,2340.270594 +0.469368,1154,2353.079141 +0.518337,1506,2370.078889 +-0.083274,916,2380.337291 +0.348908,2269,2404.719039 +0.050484,959,2415.912711 +0.513545,1678,2434.367003 +0.240488,1227,2448.756545 +0.099028,1105,2460.577778 +0.187059,1305,2475.049229 +0.336737,1766,2495.153133 +0.099028,1465,2511.853848 +0.196014,1497,2528.09907 +-0.288452,604,2534.983848 +0.336773,1694,2553.509826 +0.480668,1456,2570.150786 +0.223488,1419,2585.759849 +0.35594,1539,2602.862566 +-0.093598,800,2611.571071 +0.190714,1334,2626.982116 +0.271734,2326,2652.784012 +0.484811,1206,2665.953443 +0.462053,1812,2685.822472 +0.196059,1149,2698.597231 +0.184866,1022,2709.876891 +0.497229,1444,2726.524678 +-0.120312,1060,2738.230793 +0.271799,1943,2759.598367 +0.17623,1544,2776.785417 +0.425038,1350,2792.187411 +0.791714,734,2799.775677 +0.05332,906,2810.078031 +0.307734,1357,2825.477617 +0.044971,1091,2838.062276 +0.441812,1603,2855.530995 +0.330699,1558,2872.971552 +0.203816,1799,2893.013849 +0.438956,2059,2915.891831 +0.194701,1102,2928.423086 +0.106139,1420,2944.0418 +0.185014,1265,2958.227577 +0.306308,1558,2975.21943 +-0.334,792,2983.939814 +0.210014,1215,2998.063529 +0.551815,1310,3012.495224 +0.302153,1674,3031.513418 +-0.17135,938,3041.594515 +0.62194,1199,3055.469154 +0.2613,1448,3071.281371 +0.503706,1495,3088.343107 +0.191014,1102,3100.093676 +0.318538,1227,3114.024554 +-0.036282,1175,3126.867581 +0.17823,1485,3143.909972 +0.224277,1302,3158.350388 +0.313206,1793,3178.522325 +-0.038282,1016,3190.249428 +-0.103489,680,3198.131331 +0.138564,1602,3216.922885 +0.343843,1332,3232.023546 +0.36497,1632,3250.844542 +0.011225,1016,3262.434549 +0.479525,1776,3283.007194 +0.264598,1369,3298.22981 +0.532233,1080,3311.527011 +0.174621,1286,3327.133468 +0.629644,1271,3342.496607 +-0.096771,1396,3359.54005 +0.572487,1246,3373.714899 +0.624773,1077,3387.316348 +0.360808,1455,3404.501177 +0.026139,821,3414.829833 +0.162701,987,3426.051981 +0.440224,1729,3447.556683 +-0.11133,1261,3462.894055 +0.240688,1157,3476.74106 +0.329538,1288,3492.096988 +0.491602,1426,3509.147616 +0.625254,1267,3524.71119 +-0.141121,1001,3536.904597 +0.211936,1237,3550.411983 +0.254138,1383,3566.223016 +0.560282,1280,3580.861377 +-0.078591,789,3589.601909 +0.251053,1715,3609.465057 +0.04649,1035,3620.892251 +-0.220029,839,3629.762424 +-0.347,775,3638.350036 +0.639268,1091,3651.126335 +-0.026337,1013,3662.581686 +0.000643,1073,3674.141022 +0.187714,1419,3689.892271 +0.166701,1176,3703.756302 +0.341843,1942,3725.625615 +0.051994,1144,3738.691587 +0.344876,1695,3757.685364 +-0.124312,864,3767.701318 +0.531034,1295,3782.096885 +0.536958,1501,3798.44066 +0.255378,1357,3814.133177 +0.77988,771,3822.644981 +-0.052422,939,3832.970188 +0.005643,1064,3845.373218 +0.623617,1201,3858.618289 +-0.16906,1127,3871.491773 +0.211816,1222,3884.596366 +0.202564,1035,3897.056262 +0.327699,1587,3914.436171 +0.517762,1586,3931.823106 +0.067728,1163,3944.689109 +-0.094118,780,3954.235307 +-0.162677,817,3962.98274 +0.270688,1045,3974.447237 +-0.099603,1391,3989.961539 +0.303667,1524,4006.835846 +0.278527,1481,4022.847908 +0.302098,2182,4047.197115 +0.507711,1251,4061.199708 +0.03732,941,4072.348645 +0.50034,1616,4090.048233 +0.544518,1233,4104.669749 +0.587381,1096,4116.668284 +0.416801,1560,4135.111554 +0.162314,909,4145.358358 +0.221277,1216,4159.036087 +0.381876,1377,4174.851023 +0.813797,635,4182.065594 +0.276863,1888,4203.958518 +0.341808,2119,4227.469902 +-0.235288,763,4236.262852 +0.40298,1282,4250.943388 +0.706595,690,4259.358941 +0.46592,1824,4279.976725 +-0.009623,805,4288.653227 +0.539131,1281,4303.299704 +0.690737,874,4313.19968 +0.137703,1063,4324.792691 +0.528248,1254,4339.031111 +0.178714,1225,4353.18136 +0.301308,1650,4371.647652 +0.148495,1427,4387.406858 +-0.039282,1122,4399.290053 +0.511048,1357,4415.031892 +0.222488,1842,4435.447468 +0.497998,930,4446.704185 +0.086926,1165,4459.670791 +0.076728,1230,4472.901116 +0.153322,972,4484.196718 +0.458662,1631,4502.661168 +0.193453,1122,4514.572329 +0.484919,1559,4532.847166 +0.500939,1431,4548.608694 +0.668024,882,4558.658953 +0.347876,1391,4574.31461 +0.300667,999,4584.837418 +0.247138,1477,4602.190318 +-0.097674,864,4612.117309 +0.349959,1813,4632.551789 +0.217053,1267,4647.356575 +0.344908,1536,4664.606158 +0.522616,1668,4683.141483 +-0.06206,1121,4695.903475 +0.152564,1265,4709.321517 +0.494459,1489,4726.405362 +-0.351,976,4737.556562 +0.096926,1021,4748.896534 +0.598399,1068,4760.443395 +-0.050263,884,4770.325862 +0.714311,585,4776.450638 +0.091994,1305,4791.949922 +-0.042298,764,4800.522442 +0.319495,1479,4816.861089 +-0.046345,1012,4828.228336 +-0.120312,807,4837.070343 +0.569735,1277,4851.320153 +0.329495,1289,4865.848243 +0.329737,1643,4884.389238 +0.515381,1096,4897.136956 +0.108028,1144,4910.044282 +0.309153,1137,4923.015024 +0.328206,1106,4934.941314 +0.648262,740,4943.478564 +-0.127268,653,4950.787583 +0.606294,1203,4965.012823 +-0.164979,777,4973.845608 +0.360876,1580,4991.099653 +0.241936,1084,5003.083744 +0.170059,1254,5017.509923 +0.06049,1362,5033.288361 +0.493459,1390,5049.125674 +0.640773,1077,5060.824379 +0.474601,1755,5081.063961 +0.470907,1703,5099.829197 +0.202692,1212,5113.999015 +0.01255,1209,5127.053973 +0.039437,1103,5139.862991 +0.59337,1178,5153.05679 +0.36297,1458,5168.963468 +0.063959,1159,5182.045964 +0.290598,1475,5199.147475 +0.253138,1047,5211.063522 +0.027643,910,5221.29264 +0.604049,1217,5235.531852 +0.208816,1265,5250.038618 +0.265378,1468,5266.187881 +0.504735,1094,5278.755157 +-0.074913,958,5289.349256 +-0.339,537,5295.182504 +0.095302,1246,5309.50557 +0.45263,1291,5324.324619 +0.453003,1619,5343.042045 +0.280863,1598,5360.924152 +-0.352,737,5369.531033 +-0.010138,1374,5385.379901 +-0.212121,377,5389.678125 +0.183322,1237,5403.30112 +0.198564,1489,5420.34576 +0.454213,1769,5440.692161 +0.292773,1467,5456.720282 +0.269667,1631,5475.402048 +0.538361,1234,5489.713038 +0.514189,1356,5504.569935 +-0.031282,1579,5523.185163 +0.320984,1560,5540.931877 +0.339808,2022,5564.228002 +0.243589,1591,5581.93515 +0.467668,1418,5597.852278 +-0.06006,1248,5612.062626 +0.346908,1335,5626.866021 +0.584494,1073,5639.553015 +0.35694,1669,5658.66949 +0.101703,1136,5671.682127 +0.339843,1513,5688.448664 +0.337495,1539,5706.140301 +0.339876,1701,5726.466233 +0.32258,1564,5744.230237 +0.468586,1545,5761.830224 +0.483497,1597,5779.607389 +0.346876,1816,5801.193311 +0.448483,1688,5820.034971 +0.117368,1400,5836.21472 +0.122792,1358,5851.26188 +0.01065,837,5861.169245 +0.463871,1387,5877.473456 +0.367908,2231,5902.862411 +0.05432,976,5914.541129 +0.117792,1296,5929.640148 +0.600428,1014,5941.516991 +0.009058,1244,5956.11761 +0.600382,799,5964.935676 +0.210297,1086,5976.883512 +0.346621,1183,5990.954215 +-0.291704,1355,6006.073925 +0.481017,1610,6025.727232 +0.06287,1098,6037.964622 +0.099703,1496,6056.338862 +0.129057,1354,6072.723303 +0.168043,1433,6089.662483 +0.17023,1675,6109.215059 +-0.083675,1104,6121.485902 +-0.089138,1080,6134.870818 +0.08087,1402,6151.482525 +0.232783,1757,6172.217339 +0.004139,775,6181.258817 +0.520265,1241,6195.058164 +0.435865,1175,6208.617135 +0.006139,1009,6220.713161 +0.245488,1239,6236.024914 +0.335737,1284,6251.476427 +-0.065591,1034,6264.147904 +0.192297,1436,6281.899275 +0.226589,1647,6302.059002 +0.581406,1266,6317.687304 +0.588588,1298,6333.511002 +0.744941,960,6345.895518 +0.446421,1240,6360.034364 +0.333621,1475,6378.162559 +0.70266,517,6384.336938 +0.256453,1405,6401.093258 +0.597284,1384,6418.47401 +0.482468,1481,6435.590601 +0.145495,1478,6454.832299 +-0.000138,1050,6467.357221 +0.249488,1326,6483.712855 +-0.02385,1207,6497.737642 +0.267042,1879,6520.39744 +0.341808,1949,6543.209559 +-0.015298,1149,6556.906418 +0.467946,1372,6573.766623 +0.001136,1485,6590.978997 +0.093926,1439,6608.138718 +0.491282,1280,6623.394316 +0.189157,1509,6641.86684 +-0.014623,1291,6657.213011 +0.279924,1274,6672.70099 +0.212297,1096,6686.826469 +0.354908,1570,6705.408511 +0.589894,864,6715.962878 +0.32358,2204,6742.290024 +0.13523,959,6753.61221 +0.53722,1185,6769.020388 +0.126344,1240,6783.595837 +0.301098,1732,6805.609483 +0.163921,1459,6823.348138 +0.159043,1484,6841.983439 +-0.120298,776,6851.651133 +0.019881,1010,6864.082328 +0.328661,1910,6887.154526 +0.599204,1363,6902.958347 +0.329737,1724,6924.06895 +0.172921,1379,6940.936145 +0.286984,1705,6961.385517 +0.517014,1823,6983.429223 +0.366908,2350,7013.079989 +0.235589,1689,7033.491761 +0.36997,1678,7053.885855 +0.000402,1374,7070.959652 +0.648138,1053,7083.408571 +0.593668,1418,7100.511434 +0.015225,1234,7116.117562 +0.650811,1206,7130.69609 +0.579026,1162,7145.02464 +0.256167,1345,7161.902751 +0.25222,1854,7184.082782 +0.089302,1241,7199.525251 +0.485471,1606,7218.483402 +0.164701,1054,7231.936863 +-0.17635,929,7242.930369 +0.472103,1516,7261.122343 +-0.035345,994,7272.340141 diff --git a/006_rgb_stack_ram_based_reward_time_reward_final_round/logs/10/monitor.csv b/006_rgb_stack_ram_based_reward_time_reward_final_round/logs/10/monitor.csv new file mode 100644 index 0000000..991e77d --- /dev/null +++ b/006_rgb_stack_ram_based_reward_time_reward_final_round/logs/10/monitor.csv @@ -0,0 +1,472 @@ +#{"t_start": 1680618620.72098, "env_id": null} +r,l,t +0.438368,1215,20.276661 +-0.047345,839,30.590898 +0.485764,1714,50.768246 +0.598535,1177,64.435611 +0.35694,1493,82.752773 +0.299984,1016,95.295859 +0.35494,1909,118.307114 +0.347908,1512,135.718237 +0.36094,1339,152.358803 +0.098023,1474,169.627162 +0.088728,931,181.484545 +0.340808,1602,200.2182 +0.054994,1253,215.522329 +0.028737,1163,229.180121 +0.573577,1449,246.242511 +0.310667,1791,268.232236 +0.061959,1197,282.928179 +0.105538,1202,296.867978 +0.144314,1142,310.946599 +0.268876,1817,332.572729 +0.367699,1845,355.461869 +0.522774,1630,374.174127 +0.099668,1404,391.065657 +-0.212126,777,400.081338 +0.35797,1776,421.40304 +0.137792,1213,436.310558 +0.309206,1609,454.992077 +0.484711,1251,470.433748 +0.317404,1109,484.055371 +0.027737,1030,496.563744 +0.551152,1460,513.693546 +-0.123719,902,524.595618 +0.046994,776,533.899175 +0.170883,1490,552.135818 +0.305153,1232,567.172964 +-0.150268,744,575.124197 +0.261527,1758,596.245811 +0.047994,986,608.435282 +-0.037298,875,619.122978 +-0.030422,1042,631.733318 +0.200701,1771,653.468694 +0.166921,1561,672.297303 +0.305667,1337,688.166045 +0.132314,908,699.2002 +0.333661,1243,714.588161 +0.25522,1719,735.731523 +0.241488,1261,750.286129 +0.225277,2147,776.596599 +0.345661,1185,790.323135 +-0.087274,905,802.458335 +0.283863,2155,827.733394 +0.531085,1371,844.971792 +0.504597,1389,862.066504 +-0.16344,894,872.974279 +-0.227113,795,882.340795 +0.498758,1676,902.171432 +0.338538,1102,915.770547 +0.154124,1243,930.63288 +0.147921,1444,947.535463 +0.28394,1490,965.082624 +0.033136,954,976.996367 +0.495666,1622,997.502555 +0.507056,2211,1024.571488 +0.490453,1615,1043.830751 +0.195515,1323,1060.404964 +0.268876,1259,1076.053826 +0.158322,1586,1094.646172 +0.442924,1924,1117.357149 +0.495124,1468,1135.430118 +-0.335,562,1141.926031 +0.184883,1127,1155.65726 +-0.062674,1118,1168.7374 +0.116519,1340,1185.70629 +0.158124,1218,1200.087407 +0.182701,1202,1215.604593 +0.535034,1295,1231.012619 +0.007229,1175,1245.110722 +-0.346,534,1251.329462 +0.31745,1914,1274.226408 +0.092368,1376,1291.383666 +-0.16235,692,1299.454491 +-0.099133,847,1310.102959 +0.087926,1011,1322.62034 +0.602094,1255,1337.843123 +0.120792,1543,1356.28091 +0.583587,1056,1369.040789 +0.052136,1041,1381.590549 +0.107668,1269,1397.557037 +0.320748,1903,1421.360307 +0.583789,1535,1439.898825 +0.11365,1592,1458.679303 +-0.333,461,1464.69434 +-0.227288,540,1470.985627 +0.462017,1610,1490.800342 +0.291138,1534,1509.242406 +0.213564,1374,1526.188025 +0.490855,1060,1539.072311 +0.192866,1602,1558.940402 +0.51036,1443,1578.377879 +-0.091603,693,1586.849732 +0.009402,1315,1602.497469 +0.140043,1108,1615.508242 +0.302206,2093,1639.128268 +0.257,1462,1656.806925 +0.331661,1362,1671.630405 +0.550892,1344,1687.334651 +-0.017295,1044,1699.179375 +-0.216029,718,1708.365569 +-0.334,1017,1720.26455 +0.192157,1128,1732.317176 +0.439394,1530,1749.890667 +0.131807,1623,1769.165975 +0.773369,839,1779.402427 +0.228589,1756,1798.942749 +0.543622,1129,1812.060925 +0.179272,943,1822.581332 +0.080139,1337,1838.365869 +0.520178,1342,1853.009564 +0.232688,1288,1867.714679 +0.2903,1761,1887.996766 +0.75135,769,1896.87449 +-0.347,499,1902.850085 +-0.032422,881,1913.125128 +0.530624,1806,1933.904775 +0.014023,853,1944.241601 +0.332661,1688,1963.430479 +0.409527,2204,1989.011301 +0.590692,1164,2003.268742 +0.10765,1090,2018.033081 +0.401661,1904,2042.346704 +0.00155,831,2051.060227 +0.280984,1439,2067.269324 +0.037518,796,2076.950866 +0.284378,1549,2094.057189 +0.109028,1245,2107.57226 +0.301598,1095,2120.193726 +0.457911,1803,2140.568018 +0.303258,1702,2159.231945 +0.344876,1697,2178.580277 +0.474428,1727,2197.468288 +0.343,1708,2216.002644 +-0.343,546,2222.696215 +0.509204,1429,2238.466139 +0.385876,1238,2252.644814 +0.364699,1655,2271.268737 +0.051971,1180,2284.318014 +0.159701,1308,2298.632479 +0.340495,1820,2318.902822 +0.154711,1147,2331.636009 +0.172272,1266,2345.865039 +0.685404,1057,2357.341025 +0.281984,1457,2374.409061 +0.223924,1328,2388.747811 +0.295153,1753,2408.485049 +0.199297,1493,2424.424473 +0.338661,1285,2438.853667 +0.304258,1355,2454.582353 +0.600924,1365,2470.169868 +-0.053913,609,2476.209422 +-0.002598,1703,2496.094342 +0.519472,1354,2510.557767 +0.467741,1569,2528.885298 +0.297863,1547,2545.849851 +0.557368,1522,2562.838156 +0.011058,805,2571.432462 +0.580789,1535,2588.354419 +-0.17535,936,2598.587068 +0.202432,1494,2615.538138 +-0.107708,827,2624.28983 +0.176124,1189,2638.157079 +0.265876,1292,2652.558014 +0.331122,1957,2674.110381 +0.331661,2272,2699.526706 +-0.163677,745,2707.879656 +0.347876,1696,2726.480906 +0.165564,1066,2738.182795 +0.350843,1909,2759.421369 +0.137519,1208,2772.512541 +0.021402,740,2780.957161 +-0.000406,1027,2792.345414 +0.675783,1028,2803.977892 +0.343773,1629,2822.405226 +0.232297,1298,2836.725453 +-0.35,669,2844.074411 +0.265598,1597,2862.532549 +0.517572,1220,2875.721097 +0.71353,1003,2887.071178 +0.234783,1185,2900.102517 +-0.16235,859,2909.896945 +-0.036298,861,2919.743251 +0.292042,1758,2939.329334 +0.502422,1136,2952.016745 +0.475033,2058,2974.775433 +0.36397,1608,2992.320186 +0.456301,1748,3012.202981 +0.074538,1487,3028.536072 +0.532919,1559,3046.632667 +0.590164,939,3056.791563 +0.232138,1327,3071.183373 +0.123792,1472,3088.164114 +0.018881,1076,3099.799676 +0.467625,1360,3115.172757 +0.246138,1297,3129.488099 +0.062887,905,3139.519639 +0.522413,1079,3151.238605 +0.374843,1682,3171.013745 +0.346661,1129,3182.977153 +0.351699,1294,3199.000906 +0.608865,1263,3212.656294 +-0.034422,901,3223.149244 +0.141272,1536,3240.644574 +0.275863,1610,3259.51603 +0.160515,1560,3277.169625 +0.466061,1692,3296.588584 +0.122057,1232,3311.461035 +0.35194,1689,3331.776319 +0.454349,1514,3350.209249 +0.564355,1041,3362.671492 +0.321538,2055,3387.359349 +-0.116312,906,3398.311018 +0.523413,1221,3413.249414 +0.104714,1096,3425.923985 +0.227488,1544,3445.633458 +-0.007502,794,3455.01071 +0.218432,1172,3468.937257 +0.510023,1655,3488.841172 +0.260453,1257,3504.145869 +0.556706,1544,3522.897432 +0.200692,1266,3538.173021 +0.455802,1417,3554.214714 +0.499501,1756,3573.47334 +-0.285322,741,3582.107774 +0.595748,946,3593.304813 +0.346737,2427,3620.540011 +0.412869,1551,3637.785064 +0.636847,1303,3652.29489 +0.173711,1049,3663.893744 +0.143495,1156,3676.718042 +0.220167,1348,3692.170765 +0.327661,1987,3714.005399 +0.646758,941,3724.421617 +0.493038,1558,3742.808177 +0.161701,1315,3757.52628 +0.120519,1217,3770.867698 +0.357737,1817,3792.006066 +0.128792,1159,3805.120968 +0.230384,1755,3824.059319 +0.659517,1084,3836.743377 +0.342808,1882,3858.043507 +0.588379,1286,3872.575149 +0.04532,706,3879.913451 +-0.014771,1198,3892.967732 +0.699859,750,3901.644709 +0.05449,1441,3918.304858 +0.494586,1545,3935.50652 +0.264488,1186,3948.574029 +0.008862,765,3957.184949 +0.282984,1637,3975.472943 +0.346808,1881,3995.599637 +-0.305704,585,4002.390872 +0.291098,1172,4015.500226 +-0.323,593,4022.331319 +0.496401,1420,4037.969574 +0.155711,1686,4056.64725 +0.31758,1484,4073.627889 +0.622248,1254,4087.153477 +0.44533,1355,4103.145411 +0.422152,2018,4126.414501 +0.066305,1127,4139.266704 +0.467833,1502,4155.971108 +-0.167677,830,4165.862994 +0.490589,1659,4184.684233 +-0.014406,832,4193.828047 +0.170589,1172,4207.0079 +0.314495,1434,4224.095072 +0.347808,1357,4238.960591 +0.698813,837,4248.984934 +0.237965,1166,4262.227571 +0.272876,1375,4278.131423 +0.017139,1413,4294.089099 +0.132807,1357,4308.883924 +0.237876,1086,4321.470191 +0.301308,1751,4340.43566 +0.504381,1009,4351.864889 +0.329699,1833,4372.967637 +0.245053,1364,4387.502862 +0.152124,1378,4403.224391 +0.260527,1408,4419.054482 +0.485584,1278,4433.601255 +0.271138,882,4443.7256 +0.35658,1290,4458.119895 +0.480719,1511,4475.322904 +0.553357,1474,4491.24739 +0.45638,1466,4508.21729 +-0.170979,651,4515.507976 +0.336808,1662,4534.159106 +0.230488,1126,4546.846473 +0.338258,1153,4559.812454 +0.021518,1017,4571.213356 +0.339308,1919,4593.05988 +0.31345,1201,4606.287962 +0.285924,1443,4622.446844 +0.177322,1479,4639.757312 +0.321843,2193,4664.484159 +0.275378,1519,4681.443689 +0.254378,1590,4698.92355 +0.613618,1106,4711.717599 +0.496461,1505,4728.818712 +0.491336,1428,4744.49063 +0.089139,823,4753.1621 +0.512066,1541,4770.269513 +0.068057,1438,4786.33448 +-0.218034,665,4794.586008 +0.472842,1510,4810.943159 +0.110023,1252,4825.204951 +0.60618,1349,4840.832817 +0.143711,1664,4859.431377 +-0.231113,1176,4872.456592 +0.226167,1744,4892.480951 +0.309,1694,4911.224027 +0.239053,944,4921.672947 +0.287737,1284,4936.079718 +0.117792,1217,4950.324438 +0.323538,1516,4967.738504 +-0.10633,562,4973.786605 +0.261527,1872,4995.142853 +0.345843,1615,5012.927752 +0.334404,1323,5028.513247 +0.190557,1210,5041.834614 +0.612729,1188,5054.949746 +0.275667,1415,5070.977744 +0.579284,1384,5086.741742 +0.026737,1204,5100.732198 +0.108948,1545,5118.005459 +0.645285,1036,5129.437844 +-0.141121,894,5139.635998 +0.280799,1803,5159.928066 +0.700057,766,5168.472109 +0.216936,1406,5184.451507 +0.723605,686,5191.894493 +0.004855,1280,5206.341065 +0.706798,1044,5218.223797 +0.763657,674,5226.556163 +0.510905,1742,5245.708246 +0.125314,1421,5261.737666 +0.330699,1289,5276.10279 +0.457393,1555,5293.628951 +-0.009138,1069,5306.342307 +0.215816,1193,5319.674334 +0.646038,1059,5331.525176 +0.703339,958,5342.906045 +0.60898,1517,5360.448152 +0.610399,1068,5372.410142 +0.345843,1051,5384.074445 +0.710556,942,5395.380213 +0.339808,1375,5410.300748 +0.554536,1153,5423.308679 +0.710399,1068,5436.210798 +0.176396,997,5447.535115 +0.727859,1017,5458.042445 +-0.068591,654,5466.28741 +0.234783,1668,5485.204688 +0.229488,1794,5505.595555 +0.661008,1211,5518.904334 +0.630074,653,5526.26883 +0.350908,1934,5548.259028 +0.524743,1111,5561.224242 +0.636095,1400,5577.372226 +0.138807,1336,5592.059631 +0.495211,1565,5610.276464 +0.078926,1364,5625.161508 +0.35094,1744,5645.407924 +0.214692,1529,5662.928793 +0.238783,1508,5680.531355 +0.333737,1794,5701.110355 +0.316495,1605,5719.228808 +0.648652,992,5730.812575 +0.649382,871,5740.983668 +0.459442,1918,5762.896558 +0.217167,1456,5779.228391 +0.116368,916,5789.517645 +0.224816,1835,5810.932675 +0.10665,1483,5827.290935 +0.523801,1685,5846.542442 +0.197701,1698,5866.736525 +0.341843,1994,5889.344254 +-0.049531,1164,5902.705413 +0.181043,1008,5914.503131 +0.072728,1073,5926.726429 +0.199396,1334,5942.837764 +0.315308,1812,5963.469961 +0.499361,1234,5977.796097 +0.220167,1560,5995.417805 +-0.042298,865,6005.651303 +0.562146,1385,6021.349336 +0.411042,2071,6046.860092 +0.482422,1383,6062.311504 +-0.149159,665,6071.12075 +0.192297,1354,6086.681167 +0.31545,1321,6102.924686 +0.191396,1612,6121.137904 +0.462047,1236,6136.181577 +0.298153,1188,6149.90375 +0.54239,1376,6166.276056 +0.238783,1363,6181.505914 +0.641866,1250,6196.312358 +0.49922,1185,6210.877605 +0.547812,1603,6229.726599 +0.675554,807,6239.033972 +0.173921,1299,6254.728941 +0.183059,1352,6271.971792 +-0.046298,1189,6286.461039 +-0.046422,1148,6300.345589 +0.324621,1633,6320.57874 +0.064305,1161,6334.803717 +-0.046298,1265,6350.367739 +0.304984,1155,6364.184059 +0.552836,1486,6382.402914 +0.34358,1649,6402.175427 +0.031518,1426,6419.761273 +0.527707,1448,6436.792685 +0.522325,1260,6452.930313 +0.160792,1057,6465.704679 +0.18423,1321,6480.950158 +0.517156,1557,6500.372833 +-0.033295,1023,6512.400909 +0.148921,1371,6528.182647 +0.208816,1223,6543.01656 +0.219661,1583,6561.588888 +0.03032,905,6572.344295 +0.609694,1170,6586.347723 +0.175322,1469,6604.659519 +0.216277,1609,6623.245321 +0.237816,1146,6637.04598 +0.277799,1361,6653.780116 +0.543566,1614,6673.794941 +0.243053,1499,6691.653608 +0.213167,1357,6708.243165 +0.326042,1295,6723.611863 +0.151711,1317,6739.118014 +0.516108,1549,6758.120038 +0.379201,1749,6780.056337 +0.022402,992,6792.795049 +0.648528,1214,6807.28849 +0.211936,1619,6827.694409 +0.137807,1243,6843.261644 +0.505683,1561,6862.33754 +0.266384,1782,6883.896337 +0.563972,1205,6897.962988 +0.247688,1167,6911.682166 +-0.126406,1230,6926.942385 +0.073139,1229,6942.216841 +0.462078,1833,6964.294891 +0.072305,968,6975.485491 +-0.303704,1037,6989.284021 +0.189866,1471,7006.845556 +0.560254,1267,7022.318356 +0.256378,1528,7041.094508 +0.477552,1404,7058.318071 +0.318495,1434,7075.671412 +0.528897,1351,7092.347734 +-0.055531,1215,7106.720792 +0.211432,1247,7122.442802 +0.322206,2065,7147.862244 +0.651042,1150,7161.896031 +0.397997,1637,7182.175039 +0.452,2197,7208.789288 +0.304924,1508,7227.168281 +-0.022298,1393,7244.104225 +0.54089,1237,7258.113696 diff --git a/006_rgb_stack_ram_based_reward_time_reward_final_round/logs/100/monitor.csv b/006_rgb_stack_ram_based_reward_time_reward_final_round/logs/100/monitor.csv new file mode 100644 index 0000000..c5d3779 --- /dev/null +++ b/006_rgb_stack_ram_based_reward_time_reward_final_round/logs/100/monitor.csv @@ -0,0 +1,6 @@ +#{"t_start": 1680662852.9334967, "env_id": null} +r,l,t +-1.005,841,14.128964 +-0.227183,1382,31.444051 +-0.043787,1626,52.073473 +0.038725,1672,72.33961 diff --git a/006_rgb_stack_ram_based_reward_time_reward_final_round/logs/101/monitor.csv b/006_rgb_stack_ram_based_reward_time_reward_final_round/logs/101/monitor.csv new file mode 100644 index 0000000..21b46be --- /dev/null +++ b/006_rgb_stack_ram_based_reward_time_reward_final_round/logs/101/monitor.csv @@ -0,0 +1,5 @@ +#{"t_start": 1680662852.8304982, "env_id": null} +r,l,t +-0.028137,1480,22.021395 +-0.022018,1528,41.114172 +-0.087373,1226,57.143639 diff --git a/006_rgb_stack_ram_based_reward_time_reward_final_round/logs/102/monitor.csv b/006_rgb_stack_ram_based_reward_time_reward_final_round/logs/102/monitor.csv new file mode 100644 index 0000000..e57cb1e --- /dev/null +++ b/006_rgb_stack_ram_based_reward_time_reward_final_round/logs/102/monitor.csv @@ -0,0 +1,7 @@ +#{"t_start": 1680662852.7464976, "env_id": null} +r,l,t +-0.353827,968,15.882917 +0.245057,1084,29.733406 +0.184328,1484,47.724474 +-0.687377,493,54.150028 +0.044874,1560,72.811608 diff --git a/006_rgb_stack_ram_based_reward_time_reward_final_round/logs/103/monitor.csv b/006_rgb_stack_ram_based_reward_time_reward_final_round/logs/103/monitor.csv new file mode 100644 index 0000000..488a360 --- /dev/null +++ b/006_rgb_stack_ram_based_reward_time_reward_final_round/logs/103/monitor.csv @@ -0,0 +1,6 @@ +#{"t_start": 1680662852.8734999, "env_id": null} +r,l,t +-1.035,641,12.319541 +0.050398,1707,33.201489 +-0.072227,1548,52.354353 +-0.113528,1374,69.416364 diff --git a/006_rgb_stack_ram_based_reward_time_reward_final_round/logs/104/monitor.csv b/006_rgb_stack_ram_based_reward_time_reward_final_round/logs/104/monitor.csv new file mode 100644 index 0000000..a6509de --- /dev/null +++ b/006_rgb_stack_ram_based_reward_time_reward_final_round/logs/104/monitor.csv @@ -0,0 +1,5 @@ +#{"t_start": 1680662852.739499, "env_id": null} +r,l,t +0.015925,1780,25.46844 +-0.123925,1587,45.973249 +-0.186104,1316,62.104875 diff --git a/006_rgb_stack_ram_based_reward_time_reward_final_round/logs/105/monitor.csv b/006_rgb_stack_ram_based_reward_time_reward_final_round/logs/105/monitor.csv new file mode 100644 index 0000000..a68aab1 --- /dev/null +++ b/006_rgb_stack_ram_based_reward_time_reward_final_round/logs/105/monitor.csv @@ -0,0 +1,6 @@ +#{"t_start": 1680662852.750498, "env_id": null} +r,l,t +-0.257084,1356,20.533222 +-0.621363,1089,34.657994 +0.036373,1572,54.098028 +0.035425,1568,72.791608 diff --git a/006_rgb_stack_ram_based_reward_time_reward_final_round/logs/106/monitor.csv b/006_rgb_stack_ram_based_reward_time_reward_final_round/logs/106/monitor.csv new file mode 100644 index 0000000..41723fc --- /dev/null +++ b/006_rgb_stack_ram_based_reward_time_reward_final_round/logs/106/monitor.csv @@ -0,0 +1,7 @@ +#{"t_start": 1680662852.9255009, "env_id": null} +r,l,t +-0.177858,1114,17.348807 +-0.49899,826,28.048742 +0.123352,1573,47.443473 +-0.150925,916,58.852932 +-0.304548,1295,74.224591 diff --git a/006_rgb_stack_ram_based_reward_time_reward_final_round/logs/107/monitor.csv b/006_rgb_stack_ram_based_reward_time_reward_final_round/logs/107/monitor.csv new file mode 100644 index 0000000..4afebb1 --- /dev/null +++ b/006_rgb_stack_ram_based_reward_time_reward_final_round/logs/107/monitor.csv @@ -0,0 +1,5 @@ +#{"t_start": 1680662852.9997003, "env_id": null} +r,l,t +-0.048227,1080,17.138605 +0.015472,2184,44.218814 +-0.233829,1358,61.578909 diff --git a/006_rgb_stack_ram_based_reward_time_reward_final_round/logs/108/monitor.csv b/006_rgb_stack_ram_based_reward_time_reward_final_round/logs/108/monitor.csv new file mode 100644 index 0000000..d8713bd --- /dev/null +++ b/006_rgb_stack_ram_based_reward_time_reward_final_round/logs/108/monitor.csv @@ -0,0 +1,6 @@ +#{"t_start": 1680662853.0537002, "env_id": null} +r,l,t +-0.549181,898,15.264543 +-1.047,446,20.178923 +0.00282,2009,45.587042 +-0.009372,2231,72.483404 diff --git a/006_rgb_stack_ram_based_reward_time_reward_final_round/logs/109/monitor.csv b/006_rgb_stack_ram_based_reward_time_reward_final_round/logs/109/monitor.csv new file mode 100644 index 0000000..bda1d1f --- /dev/null +++ b/006_rgb_stack_ram_based_reward_time_reward_final_round/logs/109/monitor.csv @@ -0,0 +1,5 @@ +#{"t_start": 1680662852.9424999, "env_id": null} +r,l,t +-0.253049,1646,23.653224 +-0.030412,1462,42.445939 +0.003275,1981,66.611012 diff --git a/006_rgb_stack_ram_based_reward_time_reward_final_round/logs/11/monitor.csv b/006_rgb_stack_ram_based_reward_time_reward_final_round/logs/11/monitor.csv new file mode 100644 index 0000000..a83814d --- /dev/null +++ b/006_rgb_stack_ram_based_reward_time_reward_final_round/logs/11/monitor.csv @@ -0,0 +1,468 @@ +#{"t_start": 1680618620.9859805, "env_id": null} +r,l,t +0.334661,1737,26.102417 +0.307357,1361,42.706581 +0.588673,1061,55.191012 +0.182701,1932,77.824859 +-0.210034,997,90.428038 +0.194157,1667,110.441958 +0.753839,705,118.435232 +-0.020345,1196,133.570909 +0.068484,1069,146.06254 +-0.15844,742,155.115239 +0.457333,1490,173.384399 +-0.041345,1014,184.696044 +-0.346,851,195.215206 +0.345876,1550,213.830291 +0.312357,1851,236.535189 +0.247138,1346,252.053269 +0.39255,1786,273.91169 +0.451357,1607,293.315518 +0.679291,1020,305.701823 +0.194157,1598,324.601108 +0.452352,1718,345.870156 +0.072139,1289,361.273944 +-0.014623,956,372.277471 +0.261527,1227,387.45187 +0.345737,1630,405.983433 +-0.169677,975,417.964829 +0.534632,1258,433.041203 +0.03232,662,440.741073 +0.492958,1501,459.097734 +0.649209,1216,473.272543 +0.284598,1371,490.205327 +0.36497,2013,514.66875 +0.566846,897,525.57289 +0.066421,1504,542.893856 +0.307042,1686,563.828514 +0.229432,1950,586.728153 +0.304357,1531,604.949149 +0.189157,1265,620.416648 +0.218277,1188,634.560938 +0.258378,1955,658.098675 +0.35097,2519,689.265277 +0.10765,1146,703.273265 +0.327495,1273,718.756101 +0.576846,1033,731.069382 +0.326699,1890,754.274703 +-0.126489,1410,771.403234 +0.144384,1210,785.398421 +0.224167,1287,800.990136 +0.209692,1367,817.823886 +-0.044674,969,829.171188 +0.06187,1185,844.508789 +0.201692,1285,860.144939 +0.186014,1474,877.453823 +0.688383,592,885.103231 +0.254378,1503,903.126617 +0.203816,1915,925.902415 +0.131792,1197,939.703949 +0.055971,1328,955.561954 +0.24922,2520,986.329093 +0.015855,1022,999.066106 +0.443838,1447,1016.884605 +0.206692,1620,1037.05475 +0.183866,1439,1054.272974 +0.210936,1552,1073.081071 +-0.221029,1402,1089.846232 +0.575465,918,1100.471466 +0.359,1886,1123.130198 +-0.058462,1023,1135.583347 +-0.173312,966,1147.656135 +0.304734,1535,1166.440491 +0.067421,1293,1182.196976 +0.73107,854,1191.989945 +0.442823,1402,1209.242561 +-0.017282,1119,1223.08111 +0.144711,1021,1235.502366 +0.531586,1545,1254.078344 +0.616451,880,1264.68509 +0.175883,1216,1279.892297 +0.603228,1314,1295.701062 +0.113238,1418,1312.937943 +0.34258,1622,1332.919513 +-0.06006,1045,1345.229395 +0.443563,1988,1368.920788 +0.658535,1024,1381.395548 +0.770478,894,1392.572741 +0.278598,1397,1410.316487 +0.099703,1093,1424.127204 +0.51355,1147,1437.963706 +0.592625,1360,1453.745403 +0.109948,1396,1470.741015 +0.309357,1833,1493.473477 +0.540434,1808,1514.895121 +0.268378,1461,1532.559361 +0.110668,1195,1547.179632 +-0.062138,821,1558.42889 +0.06387,1262,1574.914303 +0.181866,1686,1596.312468 +0.324098,1808,1616.773617 +0.329404,1337,1631.615403 +0.123792,1068,1644.530071 +0.511695,1686,1663.825691 +0.703955,1006,1675.411404 +-0.231288,507,1681.301735 +0.034136,1333,1696.099462 +-0.171979,883,1706.849992 +0.156124,1241,1721.583525 +0.2503,1333,1736.417507 +0.632458,993,1748.013879 +0.354908,1528,1765.872038 +0.115948,1218,1779.582423 +0.690536,889,1790.067767 +-0.091675,784,1799.741224 +0.340773,1672,1818.894393 +0.574674,1100,1830.880083 +0.31345,1641,1849.665641 +0.565159,1026,1861.366381 +0.76348,610,1868.555676 +0.310153,1296,1883.149517 +0.075538,1681,1902.537084 +0.327,1864,1924.513077 +0.166272,1491,1941.232373 +0.158921,936,1952.531569 +0.552572,1220,1966.223078 +0.57875,1552,1984.330969 +0.233688,1970,2009.419565 +0.340737,1256,2024.669176 +0.37397,1809,2047.666029 +0.084139,1205,2060.978318 +0.065959,861,2070.915956 +0.257876,1257,2084.293254 +0.306308,1298,2099.512651 +0.070959,1342,2114.247368 +0.075421,1124,2127.22783 +0.097703,1707,2145.98778 +0.514099,1445,2162.777614 +0.263699,1326,2176.981266 +0.281667,1411,2192.830459 +0.345843,1965,2214.251878 +0.34294,1961,2236.584162 +0.687611,820,2245.461018 +0.24822,1690,2264.257469 +0.332153,1435,2280.083975 +0.113023,989,2291.359929 +0.175059,1403,2307.056644 +0.070728,1182,2320.055788 +0.108948,1307,2335.41211 +0.118238,1104,2347.038453 +0.234876,1280,2361.315325 +0.27445,1365,2377.020681 +0.305404,1758,2396.797512 +0.249384,1400,2411.466612 +0.353908,1399,2426.964221 +0.231488,1476,2444.176679 +0.293598,1382,2459.857781 +0.512368,1522,2476.981618 +0.358808,1583,2494.551134 +-0.060118,1082,2506.107989 +0.156792,1002,2517.473455 +0.446875,1913,2538.785218 +0.032887,1794,2558.729449 +0.290863,1470,2575.346577 +0.48394,1665,2593.885161 +0.361,1707,2612.489102 +0.096302,888,2622.445365 +0.37994,1550,2639.655865 +0.196059,1319,2654.127732 +0.675568,1112,2666.924699 +-0.030406,732,2675.273798 +0.171883,1563,2692.313794 +0.281863,1758,2712.007546 +0.593196,1173,2724.866867 +0.510447,1450,2740.911479 +0.483464,1340,2756.112116 +0.706998,930,2766.184166 +0.074538,1210,2779.435811 +0.064421,1434,2796.02406 +0.201297,1882,2816.678083 +0.324538,1328,2831.956266 +0.218816,1086,2843.737411 +0.151711,1042,2855.252505 +0.426,1751,2875.303097 +0.075139,1174,2888.29799 +-0.14135,924,2898.370341 +-0.049422,1106,2910.941203 +0.271667,1640,2929.35223 +0.463265,1831,2949.325315 +0.163515,937,2960.414124 +0.196866,1878,2980.499016 +-0.160979,969,2991.853982 +0.208816,1137,3004.638401 +0.275734,1700,3023.592448 +0.489715,1734,3042.563248 +-0.023041,966,3053.692975 +-0.05985,1043,3065.247172 +0.452422,1383,3080.85291 +0.251783,1326,3095.254214 +0.788759,587,3102.224553 +0.300153,1329,3116.601215 +0.439962,1912,3137.90327 +0.465804,1743,3157.846389 +0.335699,1434,3173.905541 +0.281924,1761,3194.513732 +0.197297,1242,3209.145557 +0.524755,1352,3224.093567 +0.039136,963,3235.600452 +0.132792,1724,3254.842832 +0.467111,2138,3279.630478 +0.296799,1678,3298.97705 +0.626513,816,3308.203902 +0.140936,776,3317.561921 +0.06849,1442,3335.755067 +0.151495,1431,3352.894873 +0.481166,1691,3373.021898 +0.361,1253,3388.442799 +-0.305704,1196,3402.478626 +0.499108,1636,3422.18284 +0.17723,1402,3439.222935 +-0.218591,672,3447.217682 +0.183557,1061,3459.662744 +0.552504,1368,3476.443063 +0.295924,1262,3491.701989 +-0.166979,702,3499.672485 +-0.009138,1377,3516.522165 +0.306357,1755,3538.067027 +0.227816,1015,3549.710984 +0.343737,1548,3567.089223 +0.432457,1580,3584.827883 +0.494586,1545,3602.068952 +0.573757,1331,3617.528902 +-0.173979,796,3626.284485 +0.171322,1290,3640.63867 +0.60911,863,3650.592337 +-0.118489,1072,3662.290825 +-0.226113,885,3672.142954 +0.306357,1926,3693.663709 +0.241053,1452,3709.526848 +0.233277,1662,3728.399105 +0.216277,1225,3742.734427 +0.032737,1075,3754.618427 +0.641207,984,3766.058215 +0.25222,1610,3784.499963 +0.414925,2169,3809.145583 +0.074538,1290,3823.443114 +0.075538,1152,3836.397376 +0.532974,1379,3850.991847 +0.093959,985,3862.544352 +0.311924,1358,3878.091341 +0.315495,1367,3892.694732 +0.485815,1310,3908.213099 +0.106023,1194,3921.158636 +-0.108,805,3929.950405 +0.317258,1441,3946.728595 +0.734959,906,3956.78695 +0.559784,1366,3971.283738 +0.638936,1416,3986.922472 +0.48274,1471,4003.568127 +0.119344,1384,4019.25826 +-0.064307,767,4027.709418 +0.25522,1541,4044.804292 +-0.326,424,4049.325546 +0.648255,1222,4063.319678 +0.105926,1295,4077.712816 +0.633407,928,4088.090472 +0.323404,1899,4110.069494 +0.115948,862,4119.324662 +0.474759,1527,4136.505159 +0.273667,1592,4155.48559 +0.389781,1847,4175.96487 +0.188014,989,4187.602129 +0.243816,1247,4202.104736 +-0.337,535,4207.98474 +0.287098,1462,4224.218068 +-0.106133,765,4232.984983 +0.293098,1639,4251.920814 +0.243277,1269,4266.641701 +0.309153,1416,4282.525674 +-0.038422,682,4289.858781 +0.33658,1706,4309.846445 +0.451465,2092,4332.797949 +0.18023,1010,4344.302271 +-0.041531,1238,4358.47522 +0.337308,1162,4371.359694 +0.619832,1231,4384.525367 +0.527204,1414,4400.251473 +0.35394,1813,4421.438914 +-0.345,444,4426.125419 +0.729873,681,4433.591779 +0.723894,864,4443.591598 +0.548341,1581,4461.044292 +0.552751,1194,4475.083905 +0.279799,1692,4493.716176 +-0.342,530,4499.585668 +0.315404,1347,4515.172568 +0.651939,955,4525.495158 +0.62994,1256,4539.61752 +0.473509,1766,4559.64146 +-0.000771,1011,4571.013362 +0.423743,1111,4582.933487 +0.218053,1154,4596.191166 +0.125238,1128,4609.053587 +0.469047,1855,4630.589572 +0.547323,1348,4645.633086 +-0.17635,897,4655.771472 +0.091421,947,4666.972805 +0.351908,1917,4688.284292 +0.332773,1721,4707.246695 +0.179322,1302,4721.755678 +-0.036345,632,4728.83035 +0.054881,935,4738.902105 +0.450554,1623,4757.103286 +0.516439,1299,4771.515731 +0.31045,1551,4788.927194 +0.282,1143,4801.874136 +0.511037,1336,4817.638172 +0.291098,1067,4829.153629 +0.130238,1255,4843.441425 +-0.129422,840,4852.259389 +0.201297,1310,4867.812062 +0.183866,1621,4885.404429 +0.068305,1309,4900.827471 +0.153124,1561,4918.242851 +0.53607,1415,4934.240084 +0.336,1635,4952.935525 +-0.292704,714,4960.521928 +0.002229,1051,4972.294347 +0.528209,1216,4986.287386 +0.146711,1099,4998.283835 +0.621455,1202,5012.515339 +0.278863,1649,5031.219442 +0.084302,921,5041.553613 +0.202866,1362,5057.218748 +-0.059029,1067,5069.040455 +0.340808,1698,5087.912931 +0.614666,1622,5106.434333 +0.31145,1693,5125.093736 +0.25422,1276,5139.564992 +0.452108,1627,5158.169408 +0.341699,2072,5181.38297 +0.122948,1216,5194.674202 +0.308357,1257,5209.11972 +0.280984,1444,5226.317159 +0.219167,1292,5240.874894 +0.238488,1628,5258.671273 +0.168322,1458,5275.571787 +0.637189,1356,5290.461221 +0.122519,1463,5307.492958 +0.313258,1383,5323.587862 +0.520751,1194,5336.710701 +0.35797,1877,5358.626508 +0.510849,1478,5375.042626 +0.258378,1580,5392.658263 +0.368699,1883,5414.193287 +0.529107,1740,5434.540558 +-0.223113,993,5445.87773 +0.354876,1369,5460.56295 +-0.133111,946,5471.879735 +0.223714,1564,5489.372247 +0.167883,857,5499.273804 +0.257378,1861,5520.054992 +0.251053,1569,5537.849488 +0.461831,1494,5555.137341 +0.292734,1172,5568.394897 +0.432072,2019,5591.591631 +0.198564,1254,5605.758363 +0.341661,1631,5623.526856 +0.480519,2026,5646.8501 +0.341843,1609,5665.644041 +0.152495,1207,5679.124976 +0.352843,1271,5693.717349 +0.353843,1521,5711.595893 +0.411003,1619,5730.479571 +0.524152,1933,5752.513113 +0.592528,1214,5765.938687 +0.525335,1327,5781.638173 +0.34358,1553,5799.447959 +-0.35,561,5805.299976 +0.236688,1554,5822.835716 +0.363428,1840,5844.571093 +0.383189,2005,5866.923752 +0.569279,1436,5884.363823 +0.563551,1632,5902.51541 +-0.006357,1271,5917.29341 +0.141495,1406,5933.844587 +0.205564,1377,5949.960223 +0.151711,1266,5964.543678 +0.747401,614,5971.673461 +0.34158,1441,5987.785171 +0.358737,1776,6008.359622 +0.157322,1385,6025.268233 +0.651211,1149,6038.720021 +0.30894,1793,6060.149425 +0.35097,1513,6077.426339 +0.355699,1686,6098.217061 +0.728413,1079,6110.302429 +-0.291452,891,6120.819903 +0.101344,1658,6140.705336 +0.233488,1492,6158.429848 +-0.127312,720,6166.257253 +0.240488,1381,6182.505949 +0.268598,2178,6207.971137 +0.720259,919,6218.647412 +0.234688,1124,6232.60733 +0.472372,1661,6252.654449 +0.238965,1414,6270.079107 +0.507103,1476,6289.035688 +0.481071,1592,6307.814622 +-0.08713,868,6318.663745 +0.667115,770,6328.112879 +0.535962,1309,6344.08624 +0.30945,1728,6365.19325 +0.349876,1175,6379.140407 +0.169124,1522,6397.457281 +0.434,1751,6418.27396 +0.369876,1147,6432.089352 +0.207557,1369,6449.502847 +0.287984,2007,6474.31187 +0.287527,1399,6490.962324 +0.734106,1000,6502.077076 +0.047437,1246,6517.135322 +0.190014,1449,6534.062604 +0.336661,1373,6550.519028 +0.199701,1372,6567.246014 +-0.169791,681,6575.24683 +0.48225,1886,6598.363002 +0.513625,1360,6614.715274 +-0.149979,733,6622.905318 +0.560171,1261,6638.212426 +0.468357,2107,6664.116561 +-0.125111,762,6673.483943 +0.504897,1351,6689.725638 +-0.171979,789,6699.002311 +0.261527,1261,6714.162558 +0.092139,1317,6729.586485 +0.157921,1558,6749.53685 +0.513377,1689,6770.102238 +0.301042,1339,6786.304035 +0.623817,986,6798.873616 +0.311098,1058,6811.689035 +0.380843,1464,6830.360331 +0.186924,2072,6855.79975 +0.513904,1611,6874.588863 +0.405523,2567,6905.468969 +0.110368,1358,6922.185797 +-0.292704,949,6934.159276 +0.6107,1176,6948.205958 +-0.158677,841,6957.98212 +0.152124,1276,6973.549842 +0.194157,1452,6992.230088 +-0.046298,1080,7005.055441 +0.019881,1315,7020.685114 +0.634688,1213,7036.151734 +0.356876,1614,7055.241091 +-0.013942,1041,7068.851371 +0.102297,1624,7087.751817 +0.568109,1583,7107.73485 +-0.047422,733,7116.019565 +0.072728,1138,7130.313089 +0.163883,1722,7152.132237 +0.150043,996,7163.508792 +0.357699,1526,7182.224039 +0.382876,1542,7200.847432 +0.732327,808,7211.568865 +-0.335,732,7219.583929 +0.36194,1633,7239.55068 +0.570465,1347,7256.126328 +0.063994,1050,7268.478737 diff --git a/006_rgb_stack_ram_based_reward_time_reward_final_round/logs/110/monitor.csv b/006_rgb_stack_ram_based_reward_time_reward_final_round/logs/110/monitor.csv new file mode 100644 index 0000000..ef40cd5 --- /dev/null +++ b/006_rgb_stack_ram_based_reward_time_reward_final_round/logs/110/monitor.csv @@ -0,0 +1,6 @@ +#{"t_start": 1680662853.1196983, "env_id": null} +r,l,t +-0.54999,989,15.597717 +-0.585332,1261,31.373851 +0.056911,1481,50.296234 +0.101098,1629,69.52541 diff --git a/006_rgb_stack_ram_based_reward_time_reward_final_round/logs/111/monitor.csv b/006_rgb_stack_ram_based_reward_time_reward_final_round/logs/111/monitor.csv new file mode 100644 index 0000000..d4e05af --- /dev/null +++ b/006_rgb_stack_ram_based_reward_time_reward_final_round/logs/111/monitor.csv @@ -0,0 +1,7 @@ +#{"t_start": 1680662853.1576984, "env_id": null} +r,l,t +-0.51999,774,13.61839 +-0.133847,1304,29.445205 +0.279086,1162,43.968311 +0.371325,1348,60.249705 +-0.479021,1037,72.542407 diff --git a/006_rgb_stack_ram_based_reward_time_reward_final_round/logs/112/monitor.csv b/006_rgb_stack_ram_based_reward_time_reward_final_round/logs/112/monitor.csv new file mode 100644 index 0000000..9b27358 --- /dev/null +++ b/006_rgb_stack_ram_based_reward_time_reward_final_round/logs/112/monitor.csv @@ -0,0 +1,5 @@ +#{"t_start": 1680662852.9714959, "env_id": null} +r,l,t +0.08835,2020,28.360771 +-0.349736,1175,42.83251 +-0.174352,1214,58.724937 diff --git a/006_rgb_stack_ram_based_reward_time_reward_final_round/logs/113/monitor.csv b/006_rgb_stack_ram_based_reward_time_reward_final_round/logs/113/monitor.csv new file mode 100644 index 0000000..cf4c1ec --- /dev/null +++ b/006_rgb_stack_ram_based_reward_time_reward_final_round/logs/113/monitor.csv @@ -0,0 +1,5 @@ +#{"t_start": 1680662852.8454967, "env_id": null} +r,l,t +-0.286736,1433,21.799815 +-0.069048,1852,44.456018 +-0.020874,1648,65.05857 diff --git a/006_rgb_stack_ram_based_reward_time_reward_final_round/logs/114/monitor.csv b/006_rgb_stack_ram_based_reward_time_reward_final_round/logs/114/monitor.csv new file mode 100644 index 0000000..552af47 --- /dev/null +++ b/006_rgb_stack_ram_based_reward_time_reward_final_round/logs/114/monitor.csv @@ -0,0 +1,6 @@ +#{"t_start": 1680662852.9245012, "env_id": null} +r,l,t +-1.05,847,14.161959 +-0.072048,1720,36.092166 +0.008098,1319,52.259354 +-0.364897,979,64.68901 diff --git a/006_rgb_stack_ram_based_reward_time_reward_final_round/logs/115/monitor.csv b/006_rgb_stack_ram_based_reward_time_reward_final_round/logs/115/monitor.csv new file mode 100644 index 0000000..4ea051d --- /dev/null +++ b/006_rgb_stack_ram_based_reward_time_reward_final_round/logs/115/monitor.csv @@ -0,0 +1,6 @@ +#{"t_start": 1680662852.8464973, "env_id": null} +r,l,t +-0.515025,911,15.534917 +-0.262049,963,26.831795 +-0.223548,1363,44.267508 +-0.076847,1643,64.836572 diff --git a/006_rgb_stack_ram_based_reward_time_reward_final_round/logs/12/monitor.csv b/006_rgb_stack_ram_based_reward_time_reward_final_round/logs/12/monitor.csv new file mode 100644 index 0000000..122b655 --- /dev/null +++ b/006_rgb_stack_ram_based_reward_time_reward_final_round/logs/12/monitor.csv @@ -0,0 +1,475 @@ +#{"t_start": 1680618620.7379794, "env_id": null} +r,l,t +0.481325,1334,21.711144 +0.050437,1223,35.630146 +0.253053,1156,50.490248 +0.221936,1299,65.667209 +0.343876,1781,87.36652 +0.598205,1179,101.393135 +-0.173979,726,109.474281 +0.242589,1503,127.845206 +0.2603,1564,146.478542 +-0.133189,967,158.505563 +0.364621,1248,173.758401 +0.315863,1410,190.60395 +0.03632,876,201.397053 +0.497023,1655,221.341551 +0.226277,1442,238.374816 +0.493079,1673,258.390096 +0.335737,1364,274.342167 +0.654251,1377,290.817571 +-0.167677,1052,303.273921 +0.119948,1812,326.147284 +0.162883,1663,346.145161 +0.286453,1266,361.445944 +-0.113719,881,371.180978 +0.296098,1871,393.921488 +0.037887,1040,406.085433 +0.210053,979,418.081074 +0.100023,1193,431.871973 +0.333538,1568,450.299101 +0.230688,1632,470.393508 +0.239783,1616,490.310326 +0.170701,1901,513.317546 +0.2583,2151,538.480998 +0.312495,1952,562.542551 +0.377109,1583,580.959906 +0.532529,1375,597.542007 +0.315258,1486,614.777946 +-0.344,1068,628.568152 +0.266965,1734,649.065772 +-0.092603,674,657.92463 +0.094926,957,669.243386 +0.168883,1613,689.306278 +0.252688,1545,708.145714 +0.443589,1195,722.192161 +0.520082,1315,737.689214 +0.220384,1863,760.772095 +0.05032,1085,773.510016 +0.35497,1459,791.481138 +0.073959,897,802.541336 +0.110322,816,812.060636 +0.237167,1329,827.764396 +-0.341,678,836.958384 +-0.076591,765,846.382959 +0.179059,1629,865.510433 +0.425397,2134,891.60958 +0.137272,2077,916.020547 +0.335737,1897,938.55773 +0.36694,1502,957.150481 +0.373808,1726,977.228368 +0.127564,2037,1002.745547 +0.137043,1526,1021.642201 +0.140384,1671,1042.209283 +0.277734,1713,1063.476667 +0.050971,1771,1085.107349 +0.172453,1367,1100.589469 +-0.083913,1036,1112.858318 +0.149272,1764,1134.181911 +0.043302,1359,1150.918224 +-0.34,563,1157.379524 +-0.012942,1360,1174.702187 +0.062484,918,1185.65629 +0.507956,2059,1210.849104 +-0.168979,1080,1223.454439 +0.277924,2179,1249.892459 +0.186714,1330,1266.381292 +0.203816,1570,1285.036909 +0.223432,1244,1300.672723 +0.321495,1092,1313.38204 +0.437924,1924,1336.611846 +-0.084274,1005,1348.836058 +0.031518,1241,1364.202341 +0.277598,1752,1385.967057 +-0.154677,750,1394.437344 +0.147711,1302,1411.767127 +0.275527,1851,1433.761521 +0.227384,1576,1452.469646 +0.204042,1266,1467.927111 +-0.150979,985,1479.957602 +0.275138,1522,1498.58382 +0.470038,1350,1513.935774 +0.17523,1401,1531.384114 +0.577115,1618,1552.095931 +0.568305,1228,1568.417053 +-0.17935,992,1580.438984 +-0.06606,589,1588.485476 +0.255378,1556,1606.948642 +0.542317,1451,1623.15351 +0.193866,1190,1637.400019 +-0.073307,1107,1649.644672 +0.581,1011,1661.386557 +0.246965,1169,1674.537291 +0.300308,1392,1690.499785 +0.275404,1212,1705.456419 +0.55275,1338,1720.614323 +-0.061591,964,1732.000175 +0.348,1243,1745.593307 +0.155495,975,1757.236258 +0.259453,1610,1776.49847 +0.605173,886,1786.892148 +0.215866,881,1796.032603 +-0.079913,1032,1808.810514 +0.242488,1251,1822.489335 +0.502912,1394,1838.49768 +0.271876,1527,1855.777876 +0.535042,1150,1868.962285 +0.588031,1174,1882.128485 +0.20723,1258,1896.797491 +0.231816,1211,1911.455953 +0.327699,1747,1930.972197 +-0.06585,1112,1944.292605 +0.264598,1675,1963.429481 +0.211053,1673,1982.976874 +0.098023,1108,1996.319746 +0.574428,1046,2009.846567 +0.105344,1366,2027.683855 +0.584176,1248,2042.689975 +0.176515,1414,2058.442605 +0.089807,1473,2075.651078 +0.617613,1353,2090.245296 +0.094703,1856,2111.580626 +0.300206,1336,2126.247634 +0.303527,987,2137.675713 +0.10565,1222,2151.711991 +0.513679,1284,2165.919737 +0.371908,2005,2187.529947 +0.116519,1355,2203.006715 +0.538398,1142,2215.688893 +0.17523,1875,2235.817537 +0.303357,1609,2254.339634 +0.501897,1647,2272.919372 +0.146495,1265,2287.179236 +0.356843,1654,2305.73809 +0.554885,1296,2320.084123 +0.224488,1219,2333.137641 +0.457146,1720,2352.866148 +0.51035,1652,2371.437462 +0.35297,1324,2385.962623 +0.594587,1056,2397.459979 +0.541688,1403,2412.955607 +0.327661,1351,2428.377801 +0.068484,1198,2441.650151 +0.227936,1241,2455.904581 +0.439508,1465,2471.874313 +0.175396,1339,2487.377935 +0.245589,1440,2503.278128 +0.292042,1279,2517.580181 +0.740879,878,2527.624072 +0.495678,1649,2545.899853 +0.603384,1184,2558.86445 +0.232488,1617,2576.961086 +0.506331,1247,2590.139107 +0.253053,1072,2602.614568 +0.468577,1449,2618.505672 +0.250965,1650,2637.00487 +0.058484,994,2648.298688 +0.487227,1548,2665.615447 +0.517735,2036,2688.165703 +0.154564,1065,2699.700219 +-0.346,794,2708.239657 +0.288,1635,2726.600907 +0.286863,1659,2745.261176 +0.551644,1367,2760.665776 +0.31958,1471,2776.637422 +-0.091603,1102,2789.281417 +0.643597,870,2799.097643 +0.1763,1524,2815.588259 +0.425331,1498,2832.421267 +0.619607,1339,2847.927626 +0.359538,1380,2862.783175 +-0.07433,677,2871.09761 +-0.14835,871,2881.022458 +-0.133189,958,2891.201415 +0.579204,1414,2906.905183 +-0.003598,1180,2919.908253 +0.123057,1127,2932.446826 +-0.12144,611,2939.409341 +0.349808,1491,2956.329743 +0.326699,1329,2970.688188 +0.337773,1890,2992.040983 +0.21123,1115,3003.818411 +0.244138,1502,3020.98418 +0.045971,980,3032.586807 +0.205564,974,3042.759247 +0.604338,1004,3054.032974 +0.276876,1120,3066.773363 +0.657726,1039,3078.252404 +0.149921,1464,3095.031213 +0.452427,1538,3112.150374 +0.472758,1676,3130.690291 +0.096703,1089,3142.389156 +0.173396,1242,3156.62891 +-0.348,686,3164.032417 +0.263527,1852,3185.341541 +0.347808,1514,3202.515204 +0.191557,1290,3218.103757 +0.176396,1164,3231.579544 +0.502699,1304,3246.218696 +-0.125489,890,3256.399969 +0.37894,1810,3277.012355 +0.655871,1116,3290.1165 +0.523847,1303,3304.981074 +0.221432,1197,3319.328391 +0.130807,1664,3339.370866 +0.52222,1185,3353.522085 +0.330737,1318,3370.10545 +0.209692,1426,3387.123352 +0.553459,1390,3404.044164 +-0.174979,895,3414.675832 +0.837972,579,3421.073664 +0.247138,1426,3438.195739 +0.163495,1109,3452.102714 +0.553133,1204,3466.146866 +0.314538,1361,3482.835323 +0.558481,1292,3498.288798 +0.466278,1131,3512.048892 +0.172396,1996,3536.671596 +-0.139189,1094,3548.724002 +0.068484,1008,3560.163451 +0.012862,904,3570.347636 +0.233564,1263,3584.946886 +0.440049,1393,3600.629439 +0.329661,2394,3627.72066 +-0.165979,785,3636.400702 +0.130564,1388,3652.125891 +0.288984,1713,3670.950768 +-0.170979,805,3679.641692 +0.192059,1472,3696.614816 +0.654929,1289,3710.936024 +0.257453,1568,3728.442485 +0.518048,1016,3740.108378 +0.05532,1135,3753.113377 +0.238688,1541,3770.609699 +0.002058,955,3780.791689 +0.330737,1803,3801.152077 +0.193157,1499,3818.213044 +0.241053,1711,3837.93168 +0.065737,1275,3851.244852 +0.206357,1543,3869.644537 +0.469926,1602,3887.032258 +0.206014,1263,3901.381484 +0.195432,1672,3919.951653 +0.657633,856,3929.867851 +0.677539,957,3940.051443 +0.279924,1685,3958.724767 +0.2533,1501,3975.645943 +0.084139,919,3985.681527 +0.619422,1136,3998.212519 +0.132948,1143,4011.164879 +0.714207,984,4022.294323 +0.187866,1285,4036.454774 +0.580156,1557,4053.78946 +0.57663,1291,4068.076017 +-0.344,924,4078.232818 +0.506859,1568,4095.743625 +0.546735,1425,4113.110638 +0.330538,1395,4128.194795 +0.157322,1878,4149.903009 +0.266667,1457,4167.160206 +0.577955,1006,4177.723867 +0.633541,781,4186.568684 +0.099023,1171,4200.809561 +0.312495,1532,4218.131488 +-0.001598,987,4228.893775 +0.147043,843,4238.814592 +0.645324,890,4249.044937 +0.607036,1070,4261.001087 +0.146921,1363,4276.825813 +0.199157,1587,4294.41832 +0.2733,1149,4307.440699 +0.25122,1193,4321.378189 +0.557712,1182,4334.30314 +0.615864,1157,4347.307492 +0.625257,1307,4361.726604 +0.481509,1766,4381.670619 +0.280667,2113,4404.796597 +0.182701,1307,4420.197723 +0.011402,900,4430.454099 +0.210432,1041,4442.15351 +0.365505,1850,4462.58822 +0.523623,987,4473.935789 +0.702059,1048,4485.39442 +0.265589,1399,4501.208782 +0.652347,1025,4512.759778 +0.43739,1572,4530.097777 +0.328661,1511,4547.098472 +0.002862,1351,4562.668928 +0.295206,1484,4578.822881 +0.136519,1000,4590.493554 +0.185866,1245,4604.759486 +0.650625,1360,4619.660255 +0.313495,1967,4642.738281 +0.329661,1419,4658.744777 +0.091302,1374,4674.258501 +-0.060674,1009,4684.747336 +-0.017113,1327,4700.164912 +-0.019623,1229,4713.487639 +0.338308,1190,4727.473452 +0.716891,677,4734.666641 +0.066737,939,4744.83863 +0.540317,1451,4761.457337 +0.293924,1061,4773.063227 +0.264598,1195,4786.274481 +0.476434,1808,4806.567435 +0.554333,909,4817.781173 +0.329538,1160,4830.6608 +0.154519,1203,4843.756424 +0.63155,967,4855.001756 +0.280378,1599,4872.507592 +0.196714,1180,4885.62343 +0.363456,1497,4902.774272 +0.666522,875,4912.715342 +0.52792,1824,4933.201784 +-0.349,1095,4945.908463 +0.60477,1324,4960.674929 +0.281527,1422,4976.681549 +0.451329,1778,4996.846713 +0.333495,1395,5012.767338 +0.261453,1728,5031.819445 +0.378876,1327,5047.456207 +0.230908,1315,5061.924583 +0.493976,1567,5079.539266 +0.444302,1758,5099.486383 +0.277453,1681,5118.270464 +0.1213,1362,5133.751803 +0.162711,1531,5151.279915 +0.355876,2087,5174.416631 +0.353808,1904,5196.104409 +0.597381,1009,5207.641267 +0.336737,1647,5226.63116 +0.182396,1094,5238.459942 +-0.036422,964,5249.90662 +0.012377,1107,5261.795659 +0.600032,1156,5274.663252 +0.285984,1598,5293.328122 +0.259378,1527,5310.682811 +0.427685,2130,5334.413499 +0.245589,1629,5353.419287 +0.304357,1845,5375.024402 +0.263965,1112,5386.957717 +0.32958,1327,5402.766127 +0.025518,1040,5414.242921 +0.314206,1464,5430.632373 +0.150043,1617,5449.152055 +0.587546,947,5459.374647 +-0.147159,736,5467.976724 +0.254699,1364,5483.810898 +0.35594,2181,5508.426215 +0.613071,1430,5524.637542 +0.746594,617,5531.840106 +0.537849,1478,5548.215028 +0.230167,1328,5564.052004 +0.239965,1242,5577.589215 +0.290042,1722,5597.485769 +0.535228,1617,5615.081618 +0.228488,1484,5632.312654 +0.571204,1097,5645.225924 +0.203692,1456,5661.460487 +0.060994,1014,5673.063394 +-0.166979,732,5681.974411 +0.601886,1276,5696.584595 +0.638719,1146,5710.008366 +0.810869,717,5717.682629 +-0.173979,905,5727.908422 +0.603945,850,5738.177996 +0.646428,988,5749.706495 +0.356699,1153,5762.806559 +0.264876,1465,5779.179418 +0.749541,781,5787.960176 +0.228589,1213,5802.353126 +0.481357,1474,5818.455773 +0.592488,825,5828.450188 +0.118792,1476,5844.979469 +0.000643,1356,5860.831246 +0.652211,1149,5874.248426 +0.226384,2040,5897.820345 +0.2713,1192,5911.432737 +0.511352,1320,5926.54543 +0.554836,1380,5942.850763 +0.079959,1082,5954.892402 +0.32158,1630,5973.60215 +-0.056307,848,5983.566898 +0.554026,1162,5996.885072 +0.542595,1480,6013.258729 +0.242053,1529,6031.920054 +0.54933,1355,6048.548228 +0.026519,1011,6060.502431 +0.586228,1314,6075.899647 +0.522428,1046,6088.254547 +0.663059,1048,6100.439883 +0.078926,1351,6116.564892 +-0.128312,1097,6129.982816 +0.614434,923,6140.787901 +0.093368,1306,6155.829161 +-0.162677,838,6166.102054 +-0.013771,814,6175.138451 +0.500547,1537,6193.130701 +-0.038298,964,6203.921608 +-0.332,593,6211.17062 +0.054484,1565,6229.876599 +0.050495,898,6240.521473 +0.162883,1032,6253.100453 +0.591623,987,6265.534578 +0.166701,1304,6281.65328 +0.039971,1340,6298.502664 +0.336661,1253,6314.061122 +0.046994,1298,6329.904117 +0.642536,1153,6344.145453 +0.016139,1166,6358.0303 +0.344876,1709,6378.055566 +0.27222,1329,6394.590099 +0.330737,1767,6415.361811 +0.496668,1418,6432.411352 +0.435288,2081,6459.245439 +0.435176,1248,6473.420567 +0.290042,1481,6491.449704 +0.256965,1319,6506.842366 +0.444869,1551,6525.196846 +0.558904,1762,6546.232519 +0.461453,1787,6567.637751 +0.490226,1515,6586.124724 +0.07487,1484,6604.477737 +-0.170979,1053,6616.683745 +0.220667,1355,6632.488224 +0.54069,1578,6652.128247 +0.486966,1127,6665.804996 +0.418483,1688,6686.598471 +0.62677,1055,6699.078312 +0.526539,1457,6716.027162 +-0.155677,799,6726.364292 +0.008862,1029,6738.710495 +0.528707,1448,6756.256815 +0.524639,1396,6773.49044 +-0.011406,1340,6789.796413 +0.323661,1758,6811.846028 +0.372773,1424,6829.331651 +-0.010345,782,6838.858748 +0.573085,1371,6856.128756 +0.341876,1408,6873.08763 +0.35858,1493,6891.414638 +0.148921,883,6902.260354 +0.174495,901,6912.784636 +-0.091312,628,6920.473823 +0.499742,1410,6937.534743 +0.446505,1850,6959.636853 +0.297153,1929,6983.097224 +0.654251,1137,6997.512223 +0.501557,1252,7012.917995 +0.325,1301,7028.562754 +0.301258,1456,7045.965038 +-0.042282,1146,7060.046389 +0.239277,1353,7077.023611 +-0.17935,801,7086.341578 +0.567802,1088,7100.044439 +0.07287,1104,7113.024878 +-0.070591,751,7122.511802 +0.355495,888,7133.662225 +0.098728,1363,7150.821078 +0.501017,1610,7169.846622 +0.704918,1110,7183.747788 +0.4108,1753,7205.358906 +0.452428,1727,7225.739067 +0.082883,1084,7239.435687 +0.655291,1020,7250.759753 +0.224816,1470,7268.758737 diff --git a/006_rgb_stack_ram_based_reward_time_reward_final_round/logs/13/monitor.csv b/006_rgb_stack_ram_based_reward_time_reward_final_round/logs/13/monitor.csv new file mode 100644 index 0000000..ceb1145 --- /dev/null +++ b/006_rgb_stack_ram_based_reward_time_reward_final_round/logs/13/monitor.csv @@ -0,0 +1,466 @@ +#{"t_start": 1680618620.7559795, "env_id": null} +r,l,t +0.101344,1336,21.701143 +0.288098,1670,41.560176 +0.582347,1025,53.887788 +0.199322,1204,67.573297 +0.231053,1288,83.050873 +-0.022623,1143,97.105707 +0.116519,1211,112.189789 +-0.292704,597,119.713484 +0.202564,1483,137.043998 +0.241965,1494,155.274239 +0.594748,966,166.484429 +0.500182,2137,192.253952 +0.021402,1015,204.696767 +0.004643,1122,218.383931 +-0.078913,863,227.820405 +-0.171979,708,236.938189 +0.505637,1528,255.248851 +-0.008942,1066,268.116239 +0.170883,1684,287.840542 +0.494226,1515,306.336075 +0.244876,1452,324.535916 +0.338808,2417,352.715197 +0.04849,1578,372.349474 +0.303258,1916,395.259233 +0.414051,2337,422.707302 +0.199564,1572,441.099055 +0.217053,1997,465.652141 +0.726542,962,476.622555 +0.328699,1853,499.611778 +-0.036298,1014,511.91037 +0.25522,1713,532.268687 +0.027737,841,542.771777 +0.539234,1875,564.46573 +0.326699,1264,579.571259 +-0.209113,738,588.552907 +0.302206,1579,607.135081 +0.222053,1882,630.27001 +0.135043,1284,645.851338 +0.509457,1580,664.71539 +0.275,1123,678.741903 +0.197564,1359,695.718101 +0.026737,1311,711.445623 +0.070305,1661,731.385382 +-0.057674,947,742.456552 +0.32458,1775,764.102811 +0.067421,1483,782.487555 +0.488119,1682,802.71387 +0.50692,1824,824.506702 +-0.078591,886,835.643421 +0.295206,1835,858.735941 +0.617766,1359,874.602314 +0.152124,1621,894.466439 +0.274378,1535,912.754265 +0.215167,1260,927.690207 +0.197322,1312,942.890217 +0.218816,1468,960.523606 +0.466566,1614,980.106732 +-0.002357,1514,999.218784 +0.495612,1472,1017.139607 +0.223692,1297,1032.869015 +0.369843,1557,1052.670232 +0.006229,807,1062.053402 +0.194396,975,1074.465379 +0.082302,1179,1088.297122 +0.514471,1606,1106.745165 +0.344843,1539,1125.019202 +0.252138,1036,1137.530376 +0.31545,1991,1162.074383 +0.102023,1035,1174.907189 +0.475404,1306,1190.551273 +0.068305,1182,1205.782408 +0.670598,982,1217.219015 +0.522936,1316,1232.836013 +0.35,1845,1255.676492 +-0.224288,755,1264.754092 +0.281799,1739,1285.170049 +0.414885,1439,1303.659776 +-0.031282,993,1314.962579 +-0.149111,1200,1330.095295 +0.337699,1226,1344.195955 +-0.298452,859,1354.832094 +0.518726,1595,1374.92053 +-0.15944,773,1384.33866 +0.470204,1097,1397.530542 +0.112028,1402,1415.074754 +0.102023,1216,1430.431904 +0.331661,1820,1452.137653 +0.429219,1626,1471.085014 +0.359908,1581,1490.788342 +0.099703,1239,1506.00088 +0.20823,1036,1518.28888 +0.32858,1667,1538.928311 +0.268053,946,1550.466736 +0.302357,1781,1573.613685 +-0.004138,775,1583.516972 +0.523939,1782,1605.276134 +0.174059,1480,1621.685058 +0.435401,1990,1644.877066 +0.155238,1063,1657.093928 +-0.076913,1112,1669.968638 +0.136314,1340,1684.830727 +0.666268,1091,1697.72033 +-0.210034,732,1706.882995 +-0.048422,1377,1722.121522 +0.390011,1702,1742.241631 +-0.101603,1482,1758.912215 +0.17223,1122,1772.242175 +-0.16735,1286,1787.19215 +0.17523,1129,1800.244227 +0.397201,1749,1820.690172 +0.052994,1020,1832.340652 +-0.348,989,1842.852174 +0.143711,1509,1860.147847 +0.446257,2208,1885.100432 +0.278527,1563,1903.992293 +0.583447,1450,1920.454043 +0.480661,1715,1939.977752 +0.018855,916,1950.320514 +0.571291,1300,1966.202107 +0.121792,1227,1980.102934 +0.658352,968,1991.721072 +0.121792,1361,2008.474682 +0.235876,1842,2032.848212 +0.345773,1505,2050.73991 +0.463878,1585,2068.423831 +0.324661,1862,2089.753708 +0.56686,1169,2102.613985 +0.584887,1638,2120.360726 +-0.044029,732,2128.950811 +0.384876,1445,2144.943497 +0.084305,1450,2161.731131 +0.429231,1779,2181.341581 +-0.077675,991,2191.92349 +0.481224,1729,2211.472919 +0.33358,1786,2231.255699 +0.585478,1259,2245.552022 +0.162883,1319,2260.06153 +0.152921,1616,2278.550414 +0.131564,1148,2291.286148 +-0.010337,726,2298.769477 +0.200014,1348,2314.339321 +0.323404,1409,2330.011831 +0.200866,1351,2344.571839 +-0.037295,846,2354.386574 +0.033887,958,2364.580277 +0.203816,1747,2384.601385 +0.439554,1623,2402.791712 +0.505536,1153,2415.609717 +0.639946,965,2425.808977 +0.263378,1611,2444.386671 +0.35697,2110,2467.597784 +0.593924,1365,2483.211725 +0.294153,1578,2500.66514 +0.129589,1265,2514.792779 +0.342808,1371,2530.450405 +0.459706,1495,2547.243704 +0.165883,1549,2564.340706 +0.748146,1005,2575.517581 +0.272598,1897,2595.86347 +0.61304,990,2607.1025 +0.701299,999,2618.419673 +-0.168979,708,2626.749118 +0.547525,1776,2645.750216 +0.127238,1138,2658.552658 +0.01455,1097,2671.216142 +0.394398,1907,2692.375481 +0.55779,1317,2706.771853 +0.244688,1479,2723.476498 +0.184714,1573,2740.959482 +-0.132121,734,2749.267291 +0.538103,1516,2765.265745 +0.591688,1403,2781.013391 +0.470698,1604,2799.269643 +0.619625,1360,2815.114552 +0.254357,1175,2827.960162 +0.181866,1394,2843.667412 +0.148711,1542,2860.991462 +0.279598,1853,2881.339459 +0.709453,790,2889.997918 +0.327538,1286,2904.264915 +0.213866,1148,2917.045278 +0.610535,1177,2930.745738 +0.583523,1118,2942.460586 +-0.030406,1056,2954.928973 +0.012855,1012,2965.297302 +0.521215,1483,2982.111494 +0.568735,1277,2996.481133 +0.275799,1557,3013.821219 +0.735161,822,3023.64445 +0.056959,1312,3038.188463 +0.621268,1108,3050.812332 +0.031643,914,3060.844405 +0.711775,658,3068.10182 +0.354908,1712,3086.895479 +-0.055674,691,3095.040213 +0.155783,1740,3113.868566 +0.380808,1701,3132.514032 +0.122057,1691,3152.177094 +0.329621,1756,3171.370746 +-0.039345,1536,3188.743802 +0.349908,1537,3206.863789 +0.171701,1385,3222.977244 +-0.255979,550,3229.01437 +0.25222,1235,3243.342491 +0.431394,1113,3256.400972 +-0.055674,1168,3269.631295 +0.209734,995,3281.366872 +0.592974,1379,3297.545812 +0.493336,1643,3316.21533 +0.350908,2332,3345.240472 +0.567621,1226,3359.541054 +-0.10333,793,3368.860226 +0.504336,1428,3385.87696 +0.372503,1397,3402.857622 +-0.080274,863,3413.338414 +-0.344,634,3420.976663 +0.245936,1910,3444.304152 +-0.222029,851,3454.941708 +0.276799,1524,3473.314224 +0.508367,1398,3490.180472 +0.702913,1038,3502.584128 +0.115344,886,3513.329985 +-0.016623,866,3523.175437 +0.519186,1392,3539.87995 +0.559644,1367,3555.724008 +0.327357,1695,3574.775268 +0.284924,1459,3590.943354 +0.164883,1343,3606.472889 +0.169124,1271,3620.732256 +0.547736,1297,3635.102288 +0.059959,1036,3646.758652 +0.539712,1182,3659.690002 +0.242053,1589,3677.940206 +0.293,1045,3689.477275 +0.303206,1952,3711.130021 +0.542305,1228,3725.480621 +0.082816,1350,3740.266379 +0.525706,1764,3760.557764 +-0.339,812,3769.417004 +0.160863,1336,3784.862963 +0.214816,1404,3800.87008 +0.484089,1508,3817.952863 +0.212816,1036,3829.51083 +0.492907,1684,3848.097835 +0.04232,757,3856.736087 +0.468873,1846,3877.175189 +0.463661,1904,3898.582095 +0.153495,991,3909.935878 +0.351908,1409,3925.677292 +0.504639,1396,3941.387966 +-0.174979,1216,3954.432307 +0.206936,2156,3978.541353 +-0.129489,967,3989.617544 +0.306357,1365,4004.039127 +0.286843,1085,4016.77083 +0.339808,1560,4033.779168 +0.532215,1483,4050.75332 +0.205157,1057,4062.256232 +0.348876,2064,4085.411986 +0.518597,1389,4101.571816 +0.308404,1471,4117.926887 +0.304598,1534,4135.251557 +0.36294,1991,4158.657088 +0.513228,1617,4176.285868 +0.275799,1476,4193.686048 +0.613735,1425,4209.753175 +-0.318,488,4215.387849 +0.284042,1774,4235.880855 +0.31745,1780,4256.223096 +0.536035,1343,4271.246876 +-0.014502,1124,4284.156912 +0.007855,1232,4298.442945 +0.015402,1205,4311.644536 +0.338808,1610,4329.965881 +0.331,1364,4344.65927 +-0.226288,540,4350.540172 +0.682937,823,4360.260408 +0.351495,1449,4376.167305 +0.075538,1225,4390.15775 +-0.012623,894,4400.186935 +-0.128312,678,4407.536257 +0.229688,1786,4427.843964 +0.565498,1319,4442.448023 +0.299924,1555,4460.767282 +0.353,1778,4479.886486 +0.572246,1523,4496.984212 +0.256053,1333,4512.589777 +0.519826,1543,4529.82511 +0.525038,1558,4546.995473 +-0.131677,597,4553.945785 +0.213053,1837,4574.338006 +0.342737,1377,4590.281551 +0.224014,1015,4601.802322 +0.218053,1401,4617.741273 +0.642726,1039,4629.35757 +0.326699,1785,4649.969762 +0.346876,1681,4668.759501 +0.236876,1543,4685.835168 +0.559411,1435,4701.71729 +-0.038295,1157,4714.733729 +0.282667,1504,4731.762348 +0.100238,1240,4745.774797 +0.058959,968,4755.965584 +0.594048,1016,4767.325559 +0.021881,1297,4781.761109 +-0.228288,1025,4793.331769 +-0.088708,940,4804.576564 +0.130057,1455,4820.751041 +0.48704,1575,4838.143841 +0.456971,1983,4860.792013 +0.10865,1609,4878.309065 +0.54534,1616,4896.912959 +0.159515,1182,4909.959286 +-0.143979,892,4920.126445 +0.542023,1461,4936.181 +0.133807,996,4947.600741 +0.35697,2458,4975.431337 +0.345171,1832,4996.736528 +0.158711,1136,5009.727741 +0.020518,1108,5021.687951 +0.039887,912,5031.833446 +0.174515,833,5041.783614 +0.265527,1359,5057.435749 +0.284667,1244,5070.926743 +0.294908,1524,5088.142932 +0.330699,2310,5114.055023 +-0.106719,904,5124.059486 +0.217866,1281,5138.435498 +0.201564,1475,5155.647048 +-0.076913,960,5165.915907 +0.342737,1559,5184.279507 +0.186557,1305,5198.804096 +0.196396,1001,5210.485525 +0.002402,869,5219.627495 +0.617464,1340,5235.344855 +0.548457,1580,5252.998708 +0.225277,1117,5265.86364 +0.075139,940,5276.015789 +0.24722,1232,5290.42326 +0.330495,1608,5307.998961 +0.070971,807,5317.924624 +0.001538,1488,5334.317499 +0.146432,1142,5347.37343 +0.151564,1361,5363.310552 +0.112948,904,5373.805174 +0.38994,1564,5391.179842 +0.060959,1380,5407.218138 +0.739151,944,5417.352648 +-0.044674,698,5425.854716 +0.513624,1570,5443.462951 +0.591394,1113,5456.235886 +0.348908,1997,5478.166418 +0.276734,1689,5498.008374 +0.114238,1600,5515.875891 +0.050994,946,5526.341105 +0.224167,1521,5543.925457 +0.007855,1339,5559.717654 +0.72155,967,5570.088306 +0.318495,1693,5590.152556 +0.577974,1379,5604.839877 +0.630047,1236,5619.145925 +0.531996,1469,5635.419594 +0.14923,1361,5651.407179 +-0.163979,664,5658.75169 +0.10865,936,5670.03071 +0.127564,1274,5684.842259 +0.534849,1478,5701.320359 +0.455318,1863,5723.252352 +0.117028,1056,5735.210043 +0.38197,1626,5754.010552 +0.219714,1269,5767.665929 +0.655889,1145,5780.803939 +0.625551,1305,5796.64609 +0.494668,1536,5813.893469 +0.339773,1801,5834.462299 +0.157921,1094,5846.485441 +-0.108,648,5853.817877 +0.321538,2205,5880.155851 +0.18123,1195,5893.565651 +0.312984,1430,5910.001549 +0.552189,1274,5924.918439 +0.504273,1573,5942.978764 +0.513394,1530,5960.642339 +0.151711,1690,5979.621541 +0.053737,1301,5995.220558 +0.311308,1408,6011.404044 +0.658859,1017,6023.911777 +0.598341,1273,6037.852624 +0.623147,1229,6053.17798 +0.54374,1471,6071.05075 +0.550784,1366,6086.662166 +0.625923,1576,6105.838936 +0.489721,1774,6125.765044 +0.243167,1372,6142.469951 +-0.047345,1203,6157.091837 +0.157124,1357,6172.326341 +0.335773,1401,6188.710562 +-0.046345,880,6199.241096 +0.386843,1191,6212.734009 +-0.149979,789,6222.073931 +0.533633,1725,6243.351528 +0.33045,1348,6259.25249 +0.156515,1036,6273.220727 +0.490485,1473,6291.079361 +0.138043,1894,6314.21196 +0.224488,1309,6330.077116 +0.498047,1236,6345.642523 +0.199432,1182,6359.568032 +0.517394,1530,6377.902562 +0.245965,1472,6395.022805 +0.055959,1194,6410.174639 +0.167059,1391,6427.446969 +0.089023,1753,6448.307793 +0.193014,1522,6467.163244 +-0.10233,1037,6479.363653 +-0.007771,1101,6492.93044 +0.316495,2071,6517.341322 +0.11065,1157,6531.181228 +0.141272,1269,6546.131521 +0.220863,981,6558.179942 +0.17523,1758,6578.709491 +0.116692,1384,6595.657822 +0.538275,1556,6613.890005 +0.218714,1406,6630.900028 +0.051484,1039,6644.361705 +0.605711,1251,6658.517557 +0.35597,2063,6683.748919 +0.326699,1464,6702.070714 +0.232589,1389,6718.842746 +-0.102675,1077,6731.168333 +0.2563,1244,6746.737095 +0.211564,1208,6761.188973 +0.064484,1556,6780.164337 +0.266621,1545,6799.371942 +0.565492,998,6811.949025 +0.139043,1039,6824.717365 +-0.168979,762,6834.103423 +0.020518,883,6845.137253 +0.102344,1504,6863.901331 +0.567957,1493,6882.153715 +0.63883,1122,6894.813267 +0.362224,1909,6917.901238 +0.689024,882,6928.590664 +0.242053,1573,6948.32996 +0.497589,1659,6967.623891 +0.234876,1826,6990.968825 +-0.138189,1393,7008.152118 +0.142272,1390,7024.218842 +0.143495,1419,7042.405694 +-0.115295,864,7052.304229 +0.504529,1375,7069.399621 +0.558812,1603,7089.222453 +0.145053,1254,7103.628037 +0.201692,1203,7119.142464 +0.298258,1920,7143.018729 +0.082728,883,7153.933899 +-0.088675,1173,7168.126853 +0.234053,1523,7186.759635 +0.048887,1040,7199.33025 +0.476213,1769,7220.954556 +-0.042298,1436,7238.122848 +-0.134121,799,7247.520976 +0.197564,1245,7262.585545 +0.18023,1116,7276.29621 diff --git a/006_rgb_stack_ram_based_reward_time_reward_final_round/logs/14/monitor.csv b/006_rgb_stack_ram_based_reward_time_reward_final_round/logs/14/monitor.csv new file mode 100644 index 0000000..212c98a --- /dev/null +++ b/006_rgb_stack_ram_based_reward_time_reward_final_round/logs/14/monitor.csv @@ -0,0 +1,466 @@ +#{"t_start": 1680618620.7879794, "env_id": null} +r,l,t +0.60918,1349,21.720144 +0.292924,1293,36.996639 +0.336808,1483,55.238012 +0.257453,2233,81.290633 +0.352773,1395,98.463044 +0.267138,1892,121.406368 +-0.091282,973,132.577192 +0.058994,1244,147.875785 +0.262378,1315,163.489306 +-0.026502,1056,176.886717 +0.485855,2170,202.886657 +0.35394,1838,224.619752 +-0.006771,1164,238.487876 +0.071139,1003,250.598066 +0.121344,1176,264.972714 +0.159701,1318,280.115302 +0.599612,927,291.967794 +0.359808,1709,312.380745 +0.054437,958,323.467916 +-0.24635,549,330.758472 +0.132564,885,341.50853 +-0.027282,996,352.691219 +0.187866,1473,370.92333 +0.621238,804,380.323103 +0.289799,892,390.924657 +0.164515,1251,405.973433 +0.113238,1338,421.40204 +0.214014,1348,437.863598 +0.227488,1223,452.950901 +0.323621,1722,473.335546 +0.560874,1151,487.28882 +0.244965,1354,504.117828 +0.081302,1050,516.440694 +-0.096118,1180,530.514914 +0.115238,1230,545.727369 +0.086057,1056,558.160515 +0.279799,1643,577.712334 +0.191866,1030,589.858609 +-0.022623,1510,608.157282 +0.529894,1462,625.536099 +-0.34,782,634.790941 +0.201692,1352,651.785729 +0.018518,1100,664.547392 +0.101926,1113,678.527904 +0.365808,1319,694.300588 +0.334699,1653,714.513161 +0.223277,1503,732.771561 +-0.046298,1402,749.909132 +0.071139,1619,768.909048 +0.565632,1258,784.139984 +-0.038531,1358,801.036131 +-0.057674,936,812.088636 +0.344876,1644,832.316344 +0.142272,995,844.770795 +0.020402,1290,860.427938 +0.496826,1543,879.077022 +-0.137121,966,891.23358 +0.47885,1694,911.137577 +0.214936,1688,930.79288 +-0.028298,894,941.361227 +0.382347,1547,960.279605 +0.051994,1031,972.395917 +0.192157,1592,992.562902 +-0.239923,856,1002.636549 +-0.063623,1091,1016.783605 +0.210816,1115,1029.655745 +0.351538,2072,1055.7052 +0.25022,1334,1071.578397 +0.252138,1442,1088.527209 +0.238564,1397,1105.107979 +0.107344,995,1117.247148 +0.162701,2045,1141.880139 +0.31758,1433,1158.938996 +0.231488,1052,1171.794308 +0.309357,1682,1193.239553 +0.352808,1853,1215.61359 +0.599101,1021,1227.853033 +0.204564,1515,1246.443926 +0.276598,1559,1264.82409 +0.083926,1474,1283.128211 +0.518644,1271,1297.807575 +0.654783,1028,1310.255142 +0.135238,1402,1327.33662 +-0.044406,987,1339.488276 +0.431625,1360,1356.191909 +0.149564,1261,1371.838314 +0.1803,1390,1388.019087 +0.112668,1152,1402.598521 +0.191866,1396,1419.944619 +0.08665,1804,1441.691215 +0.172396,1653,1461.715436 +-0.207029,860,1472.376281 +0.318308,1395,1489.269042 +0.137043,1330,1504.936694 +0.251589,1617,1524.795101 +0.707413,1079,1537.602479 +0.670453,625,1545.694158 +0.565192,1167,1560.636329 +0.315357,1859,1585.117702 +0.260843,1549,1603.835774 +0.216277,1563,1621.557056 +-0.001138,1328,1637.298021 +0.284799,1072,1649.405384 +0.036887,1327,1664.2265 +0.352876,1723,1684.497165 +-0.208301,843,1693.453009 +-0.104312,617,1700.713852 +0.057887,1034,1713.269874 +0.33445,1412,1729.352033 +0.20123,1509,1746.860908 +0.337661,1621,1766.029039 +0.036737,943,1776.713851 +0.545107,1132,1790.084538 +0.134314,1204,1803.343399 +0.206692,1465,1820.787173 +0.137272,1447,1837.003401 +0.333773,2095,1861.324383 +0.322538,1324,1875.97992 +0.208564,1543,1893.697502 +0.416896,1936,1916.076693 +0.388742,1410,1932.313521 +0.009058,762,1941.339759 +0.366876,1767,1961.856467 +0.569572,1220,1975.58348 +0.30845,1564,1994.683191 +0.342808,1492,2013.2879 +0.173883,1064,2027.653854 +0.649268,1108,2041.133963 +0.014225,744,2049.582705 +0.338843,2231,2074.464272 +0.071139,1282,2089.721709 +0.460637,1464,2105.791523 +-0.130189,847,2115.634856 +0.370815,1310,2130.229537 +0.613798,1244,2144.451103 +0.162057,976,2154.855289 +0.364219,1635,2172.974951 +0.343,1376,2188.591237 +-0.17235,1074,2200.120181 +0.35045,1878,2221.217261 +0.35497,1642,2239.619186 +-0.351,555,2245.61202 +-0.173979,706,2253.017323 +0.130807,1428,2269.861394 +0.195866,1404,2285.518025 +0.77907,854,2294.35117 +0.245053,1939,2316.042493 +0.151519,1028,2327.435426 +0.446966,1509,2344.432824 +0.405931,2339,2370.271909 +0.581871,1387,2386.012623 +0.218936,1513,2402.899785 +0.485878,1585,2420.170991 +0.116344,1083,2432.632069 +0.537189,1274,2447.149766 +0.329258,1860,2467.572783 +0.063421,1064,2480.058042 +0.337737,2025,2502.987711 +0.328538,1900,2523.532491 +0.33358,1728,2543.046697 +0.684874,1049,2554.603809 +0.301153,1137,2567.214678 +0.251384,1247,2581.166799 +0.593796,1270,2595.454355 +-0.223029,1278,2609.654846 +0.166059,1317,2624.040829 +0.213167,1221,2637.17087 +0.055881,1481,2654.128733 +0.479976,1477,2671.023144 +-0.120312,793,2679.680524 +0.051484,1148,2692.328483 +0.680154,969,2702.631724 +0.114948,1168,2715.33839 +0.265488,1613,2733.790234 +0.479541,1894,2754.985479 +-0.142111,700,2762.25842 +-0.122489,941,2773.52651 +0.489815,1804,2793.473111 +-0.030422,897,2803.639895 +0.154322,1421,2819.546852 +0.223277,1288,2833.715292 +0.311495,1580,2850.973192 +0.604439,1299,2865.597697 +0.641466,803,2875.297095 +0.509735,1425,2891.05813 +0.17523,1104,2902.794339 +0.292098,1742,2922.536658 +0.192714,1329,2936.718546 +-0.351,1017,2948.137724 +0.510823,1402,2963.8111 +0.011058,883,2973.650248 +0.299042,1326,2989.053032 +0.471243,1810,3009.254145 +0.343843,1937,3031.128053 +0.115023,1193,3044.057451 +0.424787,1648,3062.438121 +0.134043,1207,3075.467058 +0.290863,1276,3089.785546 +0.36897,1451,3106.634569 +0.569832,1231,3119.597814 +0.272699,1206,3133.660542 +0.507774,1630,3152.088828 +0.39566,2232,3176.84086 +0.013402,829,3185.703401 +0.409545,1828,3207.997349 +0.202432,1370,3223.077244 +0.04449,1131,3236.151453 +0.166701,1645,3255.07423 +0.18423,1331,3270.745683 +0.229688,1558,3288.716289 +0.570335,1327,3303.65145 +0.17523,921,3314.584637 +0.25222,1712,3335.992068 +0.47241,1737,3356.461054 +0.346,1464,3374.633143 +0.056737,1093,3387.245355 +0.071484,1278,3402.711625 +0.192157,1075,3416.06303 +-0.016771,760,3425.325764 +0.44947,2014,3449.069476 +0.126948,1116,3462.778057 +0.652918,1110,3476.413063 +0.401637,1464,3493.52979 +0.592497,1597,3513.313215 +-0.166979,874,3523.188432 +0.102703,1307,3539.545946 +0.435107,1740,3558.786594 +0.287527,1550,3576.289798 +0.557071,1430,3592.288815 +0.145057,1418,3609.116058 +0.26722,1186,3622.135053 +0.136519,1566,3639.314675 +0.118519,948,3649.71013 +-0.004138,992,3661.077194 +0.450721,2216,3686.411819 +0.38497,1402,3701.158361 +0.412923,1576,3719.652578 +0.151921,1294,3734.217308 +0.05432,1491,3751.412854 +0.046887,1413,3767.434322 +0.637783,1028,3778.927573 +0.365808,1237,3792.29829 +0.373006,1741,3812.364957 +0.181799,1263,3826.551014 +0.145711,1076,3838.218731 +0.168057,910,3848.228988 +0.010862,974,3859.78963 +-0.085274,696,3867.11078 +-0.088118,855,3877.017188 +0.168059,1392,3892.627733 +0.026518,1203,3905.830735 +0.667112,891,3915.802368 +0.144807,1352,3931.296405 +0.225816,1376,3946.916596 +0.097668,1177,3959.839843 +0.682875,1082,3971.41248 +0.330699,1728,3990.967718 +0.037518,1109,4002.540813 +0.521696,1083,4015.290227 +0.701395,723,4022.62191 +0.128238,1325,4037.894569 +0.253965,1443,4053.83146 +0.521254,1267,4068.026017 +0.354737,1479,4085.148987 +0.310153,1321,4100.015927 +0.213936,1171,4113.28766 +-0.079913,967,4124.813579 +0.302357,1527,4141.138383 +0.345773,1705,4161.490236 +0.558463,1227,4174.816484 +0.03532,1251,4189.297156 +0.594189,1274,4203.949519 +0.213692,1702,4222.979431 +0.308404,1691,4242.981111 +0.328661,1954,4265.240294 +0.206816,1604,4282.863674 +0.527607,1346,4298.591939 +0.167701,1289,4312.978684 +0.119519,1402,4328.676042 +0.186396,1648,4347.257492 +0.060959,922,4357.381076 +0.120238,1355,4372.927638 +0.231783,1671,4391.439956 +0.584946,1372,4406.151057 +0.416553,2507,4434.988467 +0.458779,1225,4449.254522 +0.02755,1140,4461.234284 +0.307206,1989,4483.953726 +0.339843,1680,4502.628476 +0.377036,1781,4522.803198 +0.7737,541,4528.607367 +0.317495,1687,4547.220473 +0.555054,1081,4559.90846 +0.348908,1426,4575.852412 +0.243053,1536,4593.246881 +0.104926,1307,4607.879401 +0.35594,1498,4625.134707 +0.310258,950,4635.452195 +0.323661,1510,4653.07078 +0.31545,1383,4668.817903 +0.00755,1177,4681.596848 +0.342773,1433,4697.424759 +0.231688,1414,4713.414641 +0.2513,1870,4734.604649 +0.435551,1632,4752.906099 +0.267488,1301,4767.25056 +-0.16244,871,4777.258164 +0.274863,1692,4796.091667 +0.298773,1444,4812.264949 +0.49775,1552,4829.489635 +0.043437,1217,4843.63142 +0.115139,979,4854.915756 +0.2623,1540,4872.18259 +0.484916,1323,4886.853578 +0.704288,853,4896.701957 +0.302357,1765,4915.692607 +0.285042,1362,4931.65403 +0.597398,1142,4944.591759 +0.577003,1619,4963.317716 +0.327206,1383,4978.172239 +-0.007357,1008,4989.527383 +0.712956,733,4998.22333 +0.491094,1566,5015.813414 +0.073959,1221,5029.99795 +-0.043298,990,5040.51923 +0.519018,1262,5054.916749 +0.029136,1350,5070.699744 +0.354908,1503,5087.819931 +0.110014,1450,5103.83616 +0.663513,816,5112.586316 +0.421498,2065,5135.486111 +0.129921,1255,5150.049665 +0.591061,1322,5165.4879 +0.54739,1376,5180.347906 +0.359876,1547,5197.733383 +0.668562,972,5209.183719 +0.026139,1188,5222.587141 +0.464579,2038,5245.691247 +0.499618,1106,5258.615978 +0.35294,1794,5278.642157 +0.47744,1633,5297.458794 +0.33245,1287,5311.97026 +0.304206,1927,5334.011131 +0.160515,1199,5347.278428 +0.531698,1381,5363.29355 +0.383843,1259,5377.972137 +0.54988,1526,5395.32322 +0.543759,1527,5412.657652 +0.464272,1690,5431.867793 +0.326206,1259,5446.128734 +0.230688,1576,5463.489529 +0.305924,1147,5476.549252 +0.489705,1152,5489.600249 +0.260527,1848,5510.161999 +0.492282,1280,5524.81054 +0.275598,1341,5540.701882 +-0.218029,736,5549.218143 +-0.038422,1033,5560.978242 +0.181714,1971,5583.155735 +0.308258,1649,5601.791377 +0.491459,1390,5617.546404 +0.274598,1428,5633.683088 +0.222488,1195,5647.031106 +0.69464,722,5655.627324 +0.267138,1563,5673.128394 +0.366843,1580,5691.15205 +0.332773,1717,5711.675894 +0.207866,1124,5724.747663 +0.313206,1613,5742.691233 +0.615963,1485,5760.054595 +0.322621,1184,5773.259474 +0.17323,1337,5789.099409 +0.632859,750,5797.017091 +0.146711,2069,5821.102338 +0.107948,1283,5835.851723 +0.362908,1926,5857.865725 +0.545325,1334,5872.9744 +0.268378,1218,5887.50783 +0.332737,1564,5905.42521 +0.137807,1690,5924.890439 +0.512472,1354,5941.115992 +0.598398,1142,5954.338174 +0.257378,1227,5967.700222 +0.312495,1548,5985.189434 +0.342,1542,6002.885984 +0.540639,1396,6019.247468 +0.073305,1307,6034.819223 +-0.110312,952,6046.869089 +-0.138159,585,6053.264979 +0.663033,1032,6065.247508 +0.143711,1290,6080.726256 +0.625234,989,6092.619577 +0.315495,1841,6114.746153 +0.016139,814,6124.013357 +0.198688,1055,6136.324579 +0.515556,1641,6155.78416 +0.556406,1266,6170.653786 +0.206936,1664,6190.068152 +0.254053,1798,6211.057608 +0.054518,1444,6228.173722 +0.2503,1423,6245.112403 +0.335661,1393,6262.310744 +0.232384,1396,6279.929045 +-0.344,799,6289.653043 +0.208936,1165,6303.430675 +0.235167,1719,6325.181443 +0.151564,1340,6341.221251 +0.320308,1564,6360.812594 +0.059519,721,6368.935634 +0.35197,2010,6393.172035 +0.134564,1187,6407.234667 +0.314495,1550,6426.293956 +0.419905,2155,6453.038778 +0.477265,1241,6468.588798 +0.185322,1344,6483.933109 +0.665446,1090,6497.459645 +-0.077913,1345,6512.762429 +0.306153,1798,6534.252605 +0.110344,960,6546.04652 +0.540577,1239,6561.212889 +0.135057,1055,6573.7034 +0.123519,1208,6587.790422 +0.018518,1228,6603.119998 +0.543089,1508,6621.216071 +0.569762,860,6630.868028 +0.015855,1205,6645.96267 +0.676381,978,6657.057016 +0.626548,1183,6672.171992 +-0.025138,811,6681.959136 +0.353908,1718,6702.365711 +0.581679,1284,6717.620556 +0.615589,1195,6732.487979 +0.190014,1462,6750.07885 +0.316258,1507,6768.896655 +0.11365,1165,6783.167841 +-0.096312,1159,6797.608157 +0.255589,1534,6816.560681 +0.035518,1315,6832.539666 +0.482585,1605,6852.949658 +0.712748,946,6864.04333 +0.2543,1546,6882.56054 +0.530204,1429,6900.705792 +-0.017771,1238,6914.640441 +0.231688,1837,6937.55459 +0.127564,1022,6949.95962 +0.296924,1581,6968.855687 +0.31758,1351,6985.930681 +0.023518,992,6997.634221 +0.637712,1264,7013.099992 +0.078959,1043,7025.613319 +0.291042,1654,7045.891037 +0.245783,1311,7061.730133 +0.315098,1323,7078.501569 +0.164883,1273,7093.849227 +0.501007,1802,7115.965568 +0.555924,1365,7132.298456 +0.638953,1076,7146.176795 +0.597446,1090,7158.923405 +0.470589,1687,7180.43847 +0.277924,1115,7193.22033 +0.336737,1894,7216.540977 +0.339808,1781,7238.131847 +0.272667,1276,7253.478762 +0.117344,1207,7267.333389 diff --git a/006_rgb_stack_ram_based_reward_time_reward_final_round/logs/15/monitor.csv b/006_rgb_stack_ram_based_reward_time_reward_final_round/logs/15/monitor.csv new file mode 100644 index 0000000..1019ea9 --- /dev/null +++ b/006_rgb_stack_ram_based_reward_time_reward_final_round/logs/15/monitor.csv @@ -0,0 +1,480 @@ +#{"t_start": 1680618620.6389818, "env_id": null} +r,l,t +0.195432,1337,21.822141 +0.194557,1416,38.615349 +0.34858,1431,55.635145 +0.292598,1213,70.234045 +0.090272,1188,84.462968 +0.438706,1544,103.131364 +-0.345,463,109.14206 +0.590183,1294,124.597372 +0.007862,1252,139.904093 +-0.151677,802,149.350352 +0.02932,1163,163.315307 +0.131807,1325,178.807105 +0.063971,1231,193.808281 +0.31858,1960,217.192252 +0.300308,1567,235.728514 +0.511589,1687,256.764589 +0.00755,1243,271.279621 +0.510694,1170,284.876271 +0.654485,843,295.340607 +0.261527,1056,308.039696 +0.252053,1623,327.942912 +0.042887,1506,346.292157 +0.407855,2214,372.56547 +-0.124489,638,380.310868 +0.176495,1179,394.111484 +0.35197,1650,413.631097 +-0.119719,762,422.832312 +0.257453,2181,448.682318 +-0.138268,639,456.530237 +0.679726,1039,468.998705 +0.557446,1090,482.536097 +0.154057,1199,496.745739 +0.260783,1145,510.577966 +0.05865,1339,526.310536 +0.198396,929,538.245995 +0.455311,1768,559.630135 +0.316206,1501,576.641821 +0.028139,1267,591.744363 +0.34994,2407,620.895647 +0.33758,1398,637.951797 +0.083807,1454,655.368968 +0.280598,1778,677.178714 +0.491589,1659,697.538268 +0.602577,1239,712.911505 +0.37394,1405,729.793715 +0.318042,1604,748.691148 +0.287863,1572,768.581627 +0.190396,1968,791.713138 +0.422632,2311,819.806078 +0.297153,1669,840.395598 +0.122028,1523,859.05117 +0.090344,1008,871.462801 +-0.154677,820,880.914259 +0.173883,1658,900.715163 +-0.020502,1055,913.152268 +0.037136,816,923.355729 +0.197564,1314,938.594727 +0.426758,1676,958.949214 +0.018518,1143,972.548913 +0.442311,1908,996.178843 +0.309863,1289,1012.311131 +0.037437,1299,1028.014618 +0.234688,1608,1048.185863 +0.543168,974,1059.258489 +0.581697,1117,1073.312068 +0.24922,1448,1090.261616 +0.024881,1141,1103.812689 +0.281924,1688,1124.677969 +0.539804,1743,1145.171866 +0.507679,1284,1160.643185 +-0.339,891,1171.805309 +0.349808,1470,1190.296888 +0.590974,1379,1206.384404 +0.149711,1486,1224.918405 +0.666654,628,1232.668011 +-0.16735,722,1241.668998 +0.150124,2085,1266.48829 +0.246053,1437,1283.582271 +0.495368,1154,1297.766367 +0.32294,1368,1314.733577 +0.156515,1100,1327.448619 +0.17423,1124,1341.158784 +0.064994,1077,1354.680093 +0.064926,1185,1368.99779 +0.155124,1228,1383.332283 +0.217277,1491,1402.528744 +0.135043,1526,1421.446304 +0.084926,1438,1438.571096 +0.127057,1530,1457.10311 +0.490257,1307,1472.652276 +0.127314,896,1483.434713 +0.290042,1643,1503.428974 +0.366737,1491,1521.724303 +0.504402,1190,1536.034615 +0.535907,1358,1553.695184 +-0.101406,886,1565.231418 +0.272783,1555,1585.184696 +0.06087,1351,1601.113718 +0.281734,1677,1620.280024 +0.021881,1073,1633.116528 +-0.143677,768,1641.877379 +0.068421,718,1649.793668 +0.073238,1595,1668.551117 +0.35,1537,1686.088944 +0.033136,1080,1698.021322 +-0.168791,1271,1713.397873 +0.829591,632,1720.72832 +0.194396,1267,1735.220188 +0.146807,1327,1751.016563 +0.683779,742,1759.005211 +0.018862,809,1769.057972 +0.156711,1325,1784.12606 +-0.337,908,1794.532757 +0.60356,1382,1810.588138 +0.289042,1656,1829.688146 +0.328661,1582,1847.218913 +-0.056531,1077,1859.958846 +-0.17735,964,1870.442014 +0.345538,1238,1884.935205 +0.53075,1338,1899.993541 +0.586508,1465,1917.548639 +0.455764,1714,1936.995341 +0.522679,1284,1951.765287 +0.224277,1186,1965.217707 +0.596953,1243,1980.14893 +0.38894,2097,2005.207499 +0.277598,1356,2023.187581 +0.218053,1576,2042.825973 +0.218557,1262,2057.084301 +0.128057,800,2066.003567 +0.28622,1354,2081.6218 +0.316404,1682,2100.157644 +0.269598,1704,2120.013724 +0.504759,1527,2136.450257 +0.35597,1705,2156.206059 +-0.037298,865,2165.937735 +0.422781,1847,2185.918657 +-0.013942,991,2197.311281 +0.263598,1743,2216.011131 +0.498401,1670,2234.480028 +0.35297,2167,2258.891273 +0.218277,1633,2277.392456 +0.284453,1256,2291.573694 +0.549877,1409,2307.303646 +0.311495,1851,2327.562424 +0.342737,1719,2347.197448 +0.224014,1105,2358.94604 +0.260783,981,2370.218886 +0.35694,1576,2387.612365 +0.456179,2495,2415.757714 +0.180272,721,2423.11466 +0.003862,1021,2434.465003 +0.208692,1186,2448.696083 +0.63401,805,2457.443821 +0.344737,1601,2475.833424 +0.516275,1556,2493.207377 +0.093668,1375,2507.849886 +-0.035422,859,2517.742336 +0.083926,1004,2529.185305 +0.153322,1205,2542.057483 +0.337808,2021,2564.668873 +-0.017623,1141,2577.293084 +0.124238,1490,2594.23216 +0.34794,1742,2612.962101 +-0.111406,595,2619.97054 +-0.129489,1136,2632.775574 +0.545077,1192,2645.768211 +0.342876,2063,2668.74448 +0.151921,1403,2684.316406 +0.494321,1341,2699.639706 +-0.230489,444,2704.105895 +0.2513,1589,2722.229369 +0.738418,812,2731.001302 +0.357876,1769,2750.904826 +0.2753,1308,2765.177742 +0.155314,1159,2778.150263 +0.303734,1550,2795.187546 +0.653398,1142,2808.3372 +0.583455,1202,2821.352307 +0.052994,1111,2833.988288 +-0.17035,947,2845.139641 +0.258688,1078,2856.811013 +-0.16344,803,2865.682695 +0.274799,2081,2889.700687 +0.070557,1646,2907.150178 +-0.003623,1244,2921.3265 +0.140272,1293,2935.380054 +0.631954,1054,2946.86949 +0.125519,1079,2959.523846 +0.471465,1347,2973.875245 +-0.128121,852,2983.694372 +0.047994,1231,2997.874532 +-0.225288,889,3007.817826 +0.35294,1511,3024.201446 +0.311495,1681,3043.878248 +0.035225,917,3053.880973 +-0.048422,1127,3066.64536 +0.567492,1272,3080.041719 +-0.136979,734,3088.410109 +0.141238,1699,3107.091561 +0.30797,1378,3122.577623 +0.152519,1177,3135.491353 +0.316,1664,3154.174365 +0.152272,1250,3168.430245 +0.207564,1187,3181.572514 +0.100297,994,3193.530821 +0.004855,793,3202.571204 +0.442913,1038,3215.20068 +0.484595,1512,3232.014544 +0.472227,1548,3249.494347 +0.345908,1702,3269.634296 +0.575957,1493,3286.269001 +0.509765,1463,3303.680444 +0.535329,1634,3323.76806 +0.085302,1091,3336.381063 +0.289098,1200,3350.514249 +0.367843,1734,3371.898689 +0.589678,1613,3391.878087 +0.538228,1617,3410.489055 +0.545168,1210,3425.59476 +0.191396,1229,3439.816239 +0.01355,1062,3453.511395 +-0.149979,742,3461.579421 +0.325621,1527,3479.983171 +-0.062913,533,3487.231443 +0.167495,1289,3502.684125 +-0.327,670,3510.522567 +-0.341,837,3520.189183 +0.203564,1572,3539.722949 +0.283667,1435,3555.837006 +0.716782,806,3564.733099 +0.661125,910,3574.968265 +0.141272,1224,3589.181298 +0.466601,1755,3609.252055 +0.197297,1425,3625.049272 +0.339404,1009,3636.414695 +-0.067591,1117,3648.325862 +0.155272,1248,3662.560683 +-0.153677,507,3668.228614 +-0.226113,607,3675.175174 +0.232688,1518,3692.257763 +0.35515,1843,3712.581201 +0.598294,914,3722.868209 +0.274863,1323,3737.524347 +0.551204,1097,3750.391167 +0.507973,2126,3774.805516 +0.120792,1142,3787.651264 +0.213167,1483,3804.018743 +0.354876,1548,3821.212765 +0.523401,1420,3837.059373 +-0.066591,645,3844.188012 +0.418786,1880,3865.796867 +0.347876,1769,3885.605954 +-0.04606,723,3893.971918 +0.356737,1551,3911.363573 +0.10465,1367,3926.001288 +0.132314,1056,3938.460882 +-0.167677,592,3944.488108 +0.127519,1349,3959.995842 +0.431357,2107,3982.940794 +0.286042,1162,3995.622278 +0.270598,1542,4012.878462 +0.466099,1445,4029.466835 +0.346773,1698,4048.202954 +0.343,2123,4071.254381 +-0.343,439,4076.705297 +0.108668,1071,4088.590818 +0.461094,1566,4106.388899 +0.681322,1102,4119.438437 +-0.034282,1202,4132.588238 +0.35594,1643,4151.549188 +0.175124,938,4162.98397 +0.246692,1219,4176.258866 +0.543402,1190,4189.612166 +0.247138,1282,4204.282859 +-0.139121,1033,4216.797878 +0.038518,1116,4228.972771 +0.546995,1302,4243.563109 +0.263783,1390,4259.670892 +0.637552,1404,4275.704351 +0.572465,1347,4291.310808 +0.225589,1513,4308.66892 +0.324495,1342,4323.147152 +0.610368,1215,4337.180798 +-0.092118,559,4343.205551 +0.128688,1467,4359.19922 +0.05449,1230,4373.300634 +-0.004516,1037,4384.758364 +0.236936,1126,4397.457258 +0.604489,1208,4410.741489 +0.14065,1336,4426.354185 +-0.136121,842,4435.333461 +0.612984,1043,4447.986076 +0.680955,1006,4458.416232 +0.274863,1654,4477.084414 +0.671112,891,4487.069435 +0.012862,759,4495.62146 +0.345843,1928,4517.257489 +0.131807,1400,4533.026362 +0.112948,1296,4547.31347 +0.711426,1196,4561.383233 +-0.348,869,4570.318137 +0.501522,875,4580.391436 +0.194432,1418,4596.554164 +-0.036282,844,4606.396959 +0.179714,1579,4624.00462 +-0.100603,1423,4640.210311 +0.019518,1140,4653.302787 +0.046887,888,4663.318934 +0.146807,885,4673.230495 +0.377737,1786,4693.201257 +-0.16135,922,4703.47707 +0.030225,1280,4717.930962 +0.334495,1496,4734.761637 +0.163701,1380,4750.29161 +0.511305,1228,4763.368889 +0.473726,1986,4786.180237 +0.470036,1781,4806.338432 +0.156495,1216,4819.669463 +0.714775,658,4826.903049 +0.340699,2051,4850.776149 +-0.06185,641,4857.976576 +0.054959,1562,4875.35744 +-0.068531,880,4885.32243 +0.163515,1402,4901.155471 +0.347,1816,4921.516394 +0.766087,696,4929.025754 +0.099538,1052,4940.604407 +0.565535,1177,4954.776659 +0.233816,1007,4965.314398 +-0.35,834,4975.300873 +0.264598,1128,4988.054973 +0.040971,1351,5002.889743 +0.264598,1797,5023.263241 +0.057344,1388,5039.081424 +0.448684,1870,5060.513828 +0.687347,1025,5072.23102 +0.345773,1751,5092.191869 +0.439565,1562,5109.621207 +0.615301,795,5118.26846 +0.316924,1539,5135.391086 +0.077305,883,5145.647581 +0.263138,1691,5164.393617 +0.150921,1547,5181.820986 +0.559465,1347,5197.498732 +-0.155677,523,5203.285161 +0.698322,1102,5215.42025 +0.164883,1456,5232.576207 +0.664774,976,5242.970335 +0.040971,897,5253.237708 +-0.037282,1292,5267.752908 +0.082538,1394,5283.524248 +0.085139,1211,5297.733793 +0.56977,1324,5312.359258 +0.307042,1315,5327.254244 +0.201432,1689,5347.173526 +0.53469,1578,5365.003968 +0.206936,1046,5376.872992 +0.083926,1343,5392.521749 +0.067305,1558,5410.109726 +0.67854,952,5420.36443 +0.019518,987,5432.093788 +0.066737,1062,5443.705028 +0.62604,990,5455.07462 +0.020139,1038,5466.655407 +0.639255,1222,5480.916161 +0.2743,1725,5499.967801 +0.640735,1094,5512.943767 +0.347908,1794,5533.375095 +0.588056,1186,5546.762664 +0.173883,983,5558.294451 +0.306404,1667,5577.308551 +0.508971,1712,5596.256037 +0.262527,1700,5615.126615 +0.246053,1526,5632.523654 +0.613588,1298,5647.228099 +0.566706,1495,5664.597564 +-0.170979,853,5674.578761 +0.607413,1079,5686.795997 +-0.041632,833,5696.742593 +0.419266,2238,5722.146915 +0.538851,1099,5735.242042 +0.343843,1444,5751.493543 +-0.344,595,5758.558369 +0.525113,1378,5773.547469 +0.532301,1590,5792.400625 +0.762131,720,5800.076957 +-0.35,851,5809.9193 +0.32045,1858,5831.531713 +0.235277,1381,5846.682838 +0.199297,1146,5859.808033 +0.38397,1978,5883.375645 +-0.17635,922,5893.760156 +-0.080675,971,5905.455199 +0.324042,1568,5923.437296 +0.167701,1328,5938.606197 +0.195157,1393,5954.828173 +0.561639,1396,5970.749178 +0.531352,1320,5985.405432 +0.625598,884,5995.666801 +0.167057,812,6005.680308 +0.263783,1339,6021.21036 +0.224384,1186,6034.94522 +0.471894,1462,6053.113978 +0.700951,873,6063.39565 +0.245138,1682,6083.436945 +0.455826,1825,6104.690366 +0.232167,1057,6116.758158 +0.521985,1834,6139.219182 +0.2633,1478,6155.957159 +0.588739,1140,6169.356385 +-0.348,583,6176.554461 +0.342843,1900,6198.040333 +0.52453,1003,6209.845417 +0.066959,1439,6226.858862 +0.47694,1722,6248.150423 +-0.08545,817,6257.792214 +0.004139,1221,6273.518724 +0.35997,2114,6298.90801 +0.649185,979,6311.324883 +0.254384,1256,6326.896738 +-0.129312,668,6334.836713 +0.185714,1701,6355.271837 +0.605685,997,6367.4717 +0.270527,1610,6387.113415 +0.631221,1058,6399.481639 +0.354908,1571,6418.573007 +0.299453,1035,6430.953164 +5.8e-05,959,6443.336869 +0.53509,1092,6456.484205 +0.361661,1822,6479.103412 +0.203432,1448,6496.10647 +0.32445,2002,6520.240442 +0.38394,1579,6538.632864 +0.431166,1691,6558.509164 +-0.120298,993,6570.627675 +0.587847,1303,6586.228723 +0.165936,1162,6600.303686 +0.243783,1727,6621.301063 +0.232783,1432,6638.351263 +0.369876,1719,6658.589556 +-0.216034,817,6669.197223 +0.429066,2597,6700.662503 +0.127238,1671,6720.682979 +0.561186,1392,6737.33754 +0.258378,1239,6751.924918 +-0.045298,1132,6766.035219 +0.604831,1494,6784.887597 +0.53944,1633,6805.387481 +0.195297,958,6816.753678 +0.086302,1208,6832.275656 +0.335495,1840,6854.707803 +0.192014,1205,6868.837626 +0.618846,921,6880.701533 +-0.09533,1373,6896.543252 +-0.150979,1045,6909.801697 +0.70655,967,6920.903818 +0.31845,1750,6942.40984 +0.177557,1212,6956.77937 +0.658779,1225,6972.036425 +0.030737,877,6982.98369 +0.335808,1885,7005.579374 +0.331737,1723,7027.066599 +0.389513,2346,7055.479089 +0.144711,1147,7069.552618 +0.64888,771,7078.852565 +0.484753,1440,7095.962231 +0.630357,1474,7114.587081 +0.296799,979,7127.189766 +0.208936,1353,7143.316725 +0.272378,1426,7160.533569 +0.355773,1631,7180.854469 +0.287042,994,7193.121676 +0.086538,868,7203.913593 +-0.078591,699,7212.087861 +0.114238,1175,7225.926065 +0.346737,2246,7253.52576 +0.084668,1247,7268.588738 diff --git a/006_rgb_stack_ram_based_reward_time_reward_final_round/logs/2/monitor.csv b/006_rgb_stack_ram_based_reward_time_reward_final_round/logs/2/monitor.csv new file mode 100644 index 0000000..f535221 --- /dev/null +++ b/006_rgb_stack_ram_based_reward_time_reward_final_round/logs/2/monitor.csv @@ -0,0 +1,459 @@ +#{"t_start": 1680618620.6389818, "env_id": null} +r,l,t +0.483231,1779,26.616413 +-0.352,863,37.145637 +0.283984,1446,54.251784 +0.06387,1088,67.476416 +0.442745,1695,87.802513 +0.548995,1302,103.30443 +0.31958,1506,121.683367 +0.091023,1585,140.422091 +0.502515,1529,158.872559 +0.195157,1525,177.379935 +0.088302,1036,189.542314 +0.440094,2097,215.513017 +0.216396,1426,232.348036 +0.105668,1348,248.908447 +0.024518,986,260.253842 +0.347538,1380,277.162457 +0.407114,1770,298.356868 +0.065124,1340,314.176596 +0.198432,1338,330.876468 +0.326538,2444,360.205755 +0.183714,1098,372.770521 +0.552352,968,384.921225 +0.614145,964,396.697431 +0.223297,1365,412.152018 +0.539329,1564,430.562729 +0.345908,1728,451.720291 +0.219277,1738,472.182941 +0.542225,1582,491.971498 +-0.052531,926,502.995867 +0.445569,1141,516.68469 +0.171059,1280,532.268682 +0.013225,958,543.232854 +-0.352,578,550.651236 +-0.347,649,558.405199 +0.137792,851,568.771359 +0.204816,2228,594.779283 +-0.089708,1171,608.687278 +0.457508,1465,627.081726 +-0.222029,606,633.613755 +0.267453,1867,656.778402 +0.398751,2186,683.464423 +0.003538,998,695.847098 +0.209692,1182,710.033447 +0.35294,1553,728.516254 +-0.16635,603,736.03452 +0.594668,1311,751.804066 +0.447124,1969,776.323594 +0.04849,1224,790.244131 +0.38097,2211,816.89815 +0.075538,1104,830.897033 +-0.050345,919,842.025094 +-0.343,601,849.735727 +-0.075274,1500,868.302166 +0.615637,1528,886.825751 +0.24922,1478,903.723616 +0.121519,1308,919.222058 +0.345908,1629,938.602727 +0.057484,1021,950.923841 +0.246053,1640,970.914768 +0.345621,1690,991.41205 +0.003139,1345,1008.81681 +0.251053,1662,1029.281272 +0.020518,1159,1043.475752 +0.272667,1536,1061.978224 +0.546796,1270,1077.586787 +0.123792,1355,1093.230896 +0.109948,1282,1108.319621 +0.105028,1190,1122.001725 +0.268667,1882,1145.171866 +0.159921,1951,1168.768396 +0.646501,913,1180.830746 +0.170692,1602,1199.954406 +0.34994,2034,1224.878404 +-0.075861,1552,1243.536804 +0.063421,1594,1262.121866 +0.077807,1327,1278.76532 +-0.041531,1051,1291.492567 +0.227488,1281,1307.113888 +0.073994,1129,1321.122097 +0.547892,1344,1336.729844 +0.351908,1346,1353.370824 +0.595193,1161,1367.482863 +0.28722,1082,1380.224339 +0.18123,1297,1397.291941 +0.498946,1372,1413.77015 +0.641458,993,1426.159294 +-0.011138,1067,1438.665096 +-0.091118,973,1450.815346 +0.616494,1073,1463.405841 +-0.009138,1551,1481.89978 +0.418413,2162,1508.086151 +0.498291,1300,1524.656718 +-0.132312,1184,1539.14931 +0.157519,867,1550.305733 +-0.045422,1286,1566.826562 +0.591026,1168,1581.846705 +0.440786,2171,1608.258949 +0.520472,1513,1625.669055 +-0.172979,709,1633.205948 +0.247138,1856,1655.306344 +0.085302,1275,1669.806375 +0.505275,1556,1687.321647 +-0.049422,1251,1700.936847 +0.241277,1687,1721.825319 +-0.080775,1009,1733.425359 +0.339773,2130,1757.368254 +0.353,1676,1776.878854 +-0.027406,1134,1790.26054 +0.566757,1331,1805.013565 +0.344908,1494,1822.522331 +0.306308,1230,1836.941397 +0.288984,1596,1854.46076 +0.257138,1538,1871.972515 +0.33945,1451,1889.25317 +0.437615,1916,1911.55495 +0.565625,1360,1926.597812 +0.150043,1098,1939.801508 +0.564624,1089,1951.840286 +0.497669,1018,1963.649482 +0.282598,1678,1983.220871 +0.504886,1276,1998.411935 +0.180272,1422,2016.822866 +0.600838,1447,2036.182843 +0.004498,1052,2048.219025 +0.359808,1428,2064.323708 +-0.32,375,2068.575828 +0.439322,1852,2088.972373 +0.271799,1331,2104.409944 +0.810087,696,2111.869091 +0.420892,1835,2133.21384 +0.192876,1311,2147.671219 +0.499712,1182,2160.581619 +0.432751,2186,2184.641468 +-0.112719,1059,2196.261734 +0.463806,1657,2214.680877 +0.079139,970,2225.825225 +0.395322,1391,2241.363533 +0.479294,1203,2254.57263 +0.602611,785,2263.270389 +0.333737,1712,2283.018854 +-0.022623,904,2292.962477 +0.030737,1366,2308.552206 +0.35497,1320,2323.071759 +0.531207,1499,2340.015595 +0.332357,1169,2352.89474 +0.359908,1680,2371.595456 +0.104344,1066,2383.284884 +0.10465,1639,2401.584393 +0.082484,1340,2416.021712 +0.36797,1754,2435.73924 +-0.005138,1246,2450.168274 +0.07087,1155,2463.198428 +0.303206,1754,2483.065725 +0.350843,1984,2504.867535 +0.427718,1892,2526.203884 +0.510801,1560,2543.25869 +0.138043,1291,2557.573552 +0.461096,1922,2578.746422 +0.517776,1395,2594.379618 +0.349843,1375,2609.894842 +0.295153,1552,2627.091301 +0.026136,1246,2641.209064 +0.322621,1939,2662.811544 +0.394317,1451,2678.515333 +0.492698,1604,2696.70879 +0.278924,1657,2715.078841 +0.318538,1690,2733.832232 +0.223277,1682,2752.350108 +0.282378,1214,2765.367742 +0.139807,1575,2783.717285 +0.307258,1302,2797.980287 +0.486207,1499,2815.256545 +0.35597,1793,2835.134498 +0.551242,1842,2855.401994 +0.238688,1561,2872.857553 +0.345843,1393,2888.577987 +0.181396,1827,2908.621745 +0.607487,1246,2922.715648 +0.319538,2221,2946.88049 +-0.006357,859,2956.781573 +0.251138,1305,2971.003185 +0.481107,1740,2990.839801 +-0.123312,992,3002.128759 +0.508156,1663,3020.880898 +0.314538,1756,3040.043102 +0.058959,1068,3052.440571 +0.150711,1324,3066.940361 +0.159711,1803,3087.028478 +0.585876,1181,3099.986678 +0.377808,1241,3113.967553 +0.540566,1189,3126.86158 +0.069728,1219,3140.925849 +0.600509,1669,3159.724677 +-0.037295,1060,3171.423743 +0.618339,958,3182.710151 +0.622764,1134,3196.194293 +0.305042,1624,3214.154248 +0.260527,1728,3234.664652 +0.481874,1049,3246.37969 +0.65758,1067,3258.278278 +-0.016113,904,3268.486764 +-0.058674,1099,3281.62087 +0.491447,1450,3298.06781 +0.428058,1844,3320.717588 +0.698148,787,3330.092698 +0.31858,1562,3348.716605 +0.078926,1059,3361.238763 +0.359843,1560,3380.874 +0.502781,1847,3402.734621 +0.691855,713,3411.611251 +0.118238,1222,3425.777759 +0.188014,997,3438.01853 +0.090538,945,3449.202473 +0.246384,1390,3466.052861 +0.077139,1086,3479.573169 +0.335699,1862,3501.394958 +0.464939,1782,3523.15543 +0.62269,1050,3535.631713 +0.021518,946,3547.095709 +0.215936,1267,3561.396742 +0.513465,1347,3576.319794 +0.35297,1811,3596.617183 +0.519031,1533,3613.87238 +0.174883,1242,3627.988656 +0.25622,1188,3641.065667 +0.172059,906,3651.169336 +-0.34,721,3659.463184 +0.747003,762,3668.154613 +0.154495,1216,3681.229372 +0.128948,1260,3695.422174 +0.099668,777,3704.031497 +-0.142121,1023,3715.677605 +0.146921,961,3726.991831 +0.57594,1199,3740.269376 +0.188396,1301,3754.897425 +-0.03006,567,3761.893308 +0.692102,712,3769.424999 +0.455781,1847,3790.664772 +0.300258,1809,3811.040801 +0.341843,1899,3832.481233 +0.341843,1632,3849.928638 +0.322495,1664,3868.770719 +0.320621,2093,3892.725729 +-0.17135,761,3901.376631 +-0.017623,1199,3914.393168 +0.114028,1488,3931.396403 +0.519613,1520,3948.46403 +0.219816,1189,3961.493431 +0.250053,1671,3979.933534 +0.435485,1473,3995.708635 +0.176059,1280,4010.047694 +0.292153,1430,4026.601229 +0.271799,1391,4041.185238 +0.54049,1062,4053.820458 +0.613783,1028,4065.184355 +0.665866,1250,4079.416031 +0.342843,1613,4097.138807 +0.337773,1665,4116.448284 +0.444995,1302,4131.073246 +0.044437,819,4140.923382 +0.128314,1639,4160.011948 +0.628031,1174,4173.147782 +0.565522,1312,4187.922125 +0.270378,1639,4206.804687 +0.245384,1713,4225.907821 +0.374428,1840,4247.541151 +0.637439,1299,4262.225565 +0.052484,766,4271.075873 +0.174396,1107,4282.958671 +0.277138,1603,4301.55994 +0.20223,934,4311.802535 +0.486556,1641,4330.256876 +0.552124,1524,4347.41449 +0.059484,1112,4360.174406 +0.222936,1475,4376.1843 +0.633735,1094,4388.746342 +0.058421,1266,4403.029185 +0.210053,1406,4417.986281 +0.185965,1231,4432.277259 +0.062807,1419,4448.324383 +0.508452,1829,4468.539616 +-0.022502,1029,4480.926671 +-0.160677,820,4489.686517 +0.190714,1311,4504.280422 +0.35158,1545,4521.643393 +0.487483,1688,4540.181256 +0.593282,1280,4554.500089 +0.051994,1332,4569.999135 +0.345876,1373,4585.792443 +0.602755,1352,4600.728849 +0.300667,1548,4618.193272 +-0.090118,1392,4634.015784 +0.427311,1768,4654.539 +0.553726,1595,4671.940376 +0.149272,1376,4687.430506 +0.35294,1954,4709.189516 +0.514337,1506,4726.336379 +0.540996,1469,4743.094921 +0.594071,1430,4758.815562 +0.676048,1016,4770.119859 +0.257621,1528,4787.419477 +0.438341,1581,4804.969558 +0.56008,1138,4818.07017 +0.619518,1233,4832.153005 +0.170124,1088,4843.862431 +0.553539,1457,4859.859547 +0.47302,1731,4879.737089 +0.172059,1257,4894.131492 +0.123519,972,4904.430294 +-0.005942,938,4915.504269 +0.008377,999,4926.302793 +0.04732,884,4936.261975 +0.241053,1620,4955.020339 +0.524547,1537,4972.490345 +0.238277,1370,4988.048973 +0.180396,1216,5001.33732 +0.342773,1633,5020.199581 +-0.024295,1204,5033.43136 +0.342737,1720,5053.358343 +0.139272,1244,5067.700262 +0.615308,1063,5079.457165 +0.026402,1072,5091.188671 +0.348737,1902,5112.628191 +-0.038422,573,5119.527797 +0.066994,1238,5132.644832 +0.415688,1403,5148.768578 +0.589617,1201,5162.822095 +0.386879,2463,5190.398996 +0.470907,1703,5209.411716 +0.485447,1450,5225.659635 +0.573464,1340,5241.383891 +0.350876,1958,5263.332421 +0.223488,1612,5281.828029 +0.222053,1593,5299.466769 +-0.172979,1537,5316.860918 +0.245138,1608,5335.651158 +0.171495,1059,5347.447425 +0.513668,1536,5365.097366 +0.32258,1579,5382.829882 +0.234589,1648,5401.77091 +0.173883,1313,5417.137416 +-0.082274,891,5427.304768 +-0.174979,928,5437.791759 +0.292734,1348,5452.317284 +0.582465,1347,5468.009721 +0.734636,898,5478.088413 +0.659324,890,5488.283042 +0.472914,1193,5501.471302 +0.38097,1279,5516.063874 +0.085668,1120,5529.08496 +0.330737,1454,5545.42124 +0.412189,2224,5571.325786 +0.654755,1352,5586.199504 +0.144272,1382,5601.986375 +0.229688,1529,5619.258923 +0.346908,1668,5638.254016 +0.502279,1436,5654.425675 +-0.167677,726,5663.044789 +0.641984,1043,5674.76176 +0.17123,1229,5689.38934 +0.268734,1517,5706.072299 +0.037437,1057,5719.08229 +0.35597,1936,5741.154665 +0.210936,1466,5757.410136 +0.419046,2153,5782.19117 +0.343876,1381,5798.365305 +0.627,1011,5809.7913 +0.023881,1231,5823.217641 +0.688042,1150,5836.440228 +0.323042,1528,5853.955873 +0.249965,1525,5871.718887 +0.354773,1293,5886.547232 +0.551633,1725,5907.029814 +0.321404,1382,5923.323296 +-0.037282,813,5932.576401 +-0.17335,763,5941.464988 +0.342699,1315,5956.341608 +0.308404,1885,5978.007095 +0.586254,1267,5992.486754 +0.731673,1061,6004.448484 +0.250589,1280,6019.400978 +0.265667,1332,6036.009222 +0.337773,1984,6059.219807 +0.334661,1553,6077.600819 +0.341773,1841,6100.04868 +0.240488,1307,6114.99615 +0.492229,1287,6130.221814 +0.594463,1227,6144.164535 +0.030136,1168,6158.707849 +0.131807,1053,6170.729786 +0.119028,630,6178.179433 +-0.128489,776,6187.112056 +0.35494,2215,6212.746005 +0.159495,1012,6225.050049 +0.038136,916,6235.951915 +0.536907,1358,6252.837261 +0.623673,1061,6265.579573 +0.450859,1568,6284.908381 +0.295808,1100,6298.648661 +0.175557,1052,6311.369881 +0.200432,1493,6330.031112 +0.518529,1375,6346.126515 +0.342773,1762,6367.548955 +0.499082,1315,6383.958593 +0.39094,1457,6400.943259 +0.052484,1130,6415.133628 +0.522204,1429,6432.258351 +0.267378,1077,6445.258145 +0.467265,1831,6468.595058 +0.03632,759,6477.577673 +0.415039,1958,6500.61683 +0.163701,1216,6514.456945 +0.226157,929,6526.406682 +0.079959,827,6535.777077 +0.31645,1615,6555.140184 +0.54814,959,6566.178476 +0.313357,1780,6587.833418 +0.225564,1254,6603.264995 +0.350843,1381,6619.803588 +0.477812,1603,6638.579424 +0.092368,1430,6655.57731 +-0.168677,791,6665.908994 +0.528735,1724,6686.847468 +0.498842,1510,6705.189514 +0.179557,1149,6719.016743 +0.178557,983,6729.952482 +-0.142121,1093,6743.869265 +0.289098,1745,6765.673197 +0.243876,1213,6780.129334 +0.271799,1386,6797.633291 +0.566939,955,6808.98189 +0.154043,1318,6826.036094 +-0.086,607,6832.699662 +0.563811,1206,6848.263444 +0.609688,1213,6862.639539 +0.288042,1609,6882.410715 +0.31958,1708,6902.741347 +0.345908,1937,6925.711095 +0.038737,989,6937.971588 +0.514439,1299,6953.6582 +0.04532,832,6964.301888 +0.346876,1792,6986.230678 +0.369737,1432,7003.889944 +0.488047,1664,7024.034842 +0.631268,1108,7037.939428 +0.180495,878,7047.721819 +0.188921,1141,7061.846129 +0.298984,1454,7080.159431 +-0.129489,1037,7092.556727 +0.32051,2001,7116.460563 +0.50853,1726,7138.550243 +0.476568,1650,7158.80537 +0.347,2164,7185.313065 +0.237816,2001,7209.119283 +0.34794,1571,7228.798976 +-0.083675,839,7238.399153 +0.303357,1787,7259.701137 diff --git a/006_rgb_stack_ram_based_reward_time_reward_final_round/logs/3/monitor.csv b/006_rgb_stack_ram_based_reward_time_reward_final_round/logs/3/monitor.csv new file mode 100644 index 0000000..a24083b --- /dev/null +++ b/006_rgb_stack_ram_based_reward_time_reward_final_round/logs/3/monitor.csv @@ -0,0 +1,477 @@ +#{"t_start": 1680618620.706982, "env_id": null} +r,l,t +0.020225,1048,18.60177 +0.256378,1292,33.828418 +0.266667,1253,49.032585 +0.556507,1571,67.356746 +0.234277,1794,89.107836 +0.336661,1498,107.46302 +0.022229,657,115.236996 +0.452637,1528,133.775906 +0.034136,1026,146.094538 +0.459568,1112,158.742558 +0.228053,1335,175.401557 +0.34545,1831,197.021293 +0.226564,1151,211.032816 +0.298799,1511,229.076119 +0.240688,1603,247.731721 +0.459139,1854,271.013621 +0.343876,1593,289.383326 +-0.086274,1141,303.170916 +0.005862,1056,315.739164 +0.46181,1937,339.991676 +-0.020462,891,350.726246 +-0.140111,808,360.164755 +0.336737,1397,377.029025 +0.312495,1557,395.418231 +0.348808,1226,410.264647 +-0.042298,855,419.862421 +0.234876,2078,444.245875 +0.158272,1394,461.258552 +0.122057,1839,484.012371 +0.519594,1706,504.466821 +-0.129489,870,515.015749 +0.559916,1323,530.686913 +0.558936,1416,547.639508 +0.106557,2040,571.957679 +0.35094,1788,593.207905 +0.666506,1051,605.574612 +0.061421,1103,619.266978 +0.184714,1074,631.994488 +0.260378,1384,649.059769 +0.490774,1630,669.231384 +0.191157,1319,685.034185 +0.57033,1355,701.948756 +0.103028,1481,719.298496 +0.575529,1285,734.667268 +-0.336,431,740.592701 +0.199297,1455,757.918737 +0.197157,1257,773.348664 +0.198515,1481,791.415136 +0.079926,1638,810.607296 +0.619026,1168,824.619698 +0.174807,1510,843.499351 +0.220277,1489,862.054503 +-0.080133,924,873.081279 +0.143432,1255,888.500402 +0.154807,1555,906.696726 +-0.162979,611,914.278345 +-0.016771,860,924.654313 +0.593498,1319,939.929945 +0.088302,1387,957.04229 +0.169701,1254,971.156768 +0.319495,1779,993.114898 +0.348908,1513,1012.318129 +0.173396,1757,1034.239696 +0.447551,1305,1049.855903 +0.267598,1543,1068.611217 +0.219384,1693,1088.659206 +0.583306,1539,1106.846162 +0.101139,919,1118.618335 +0.197432,1428,1135.578114 +0.000139,902,1146.472102 +-0.055674,1250,1161.874382 +0.291843,1861,1184.249756 +0.270598,1274,1199.910404 +-0.041531,1170,1214.225274 +0.056484,1560,1232.847011 +0.335808,1492,1251.214462 +0.182714,1752,1272.45713 +0.094139,1221,1286.753208 +-0.137189,838,1297.575366 +-0.139121,781,1306.970932 +0.052437,1069,1319.764915 +0.2503,1635,1339.530272 +0.321538,1446,1356.57819 +0.194297,1385,1373.799668 +-0.142159,744,1383.056284 +0.418892,1835,1405.820973 +0.344843,1812,1427.90556 +0.212053,1321,1444.424067 +0.259589,1376,1461.310219 +0.216053,1179,1475.328078 +0.092515,1155,1489.241038 +0.609953,1243,1503.513998 +0.135807,1335,1520.124887 +0.330699,1617,1540.548675 +0.181557,1137,1553.992193 +0.757197,858,1565.417422 +0.217816,1199,1581.639707 +0.342876,1613,1600.911718 +-0.144979,677,1608.569944 +0.089305,1074,1621.375412 +0.503896,1936,1643.35017 +-0.022623,826,1652.698866 +0.140272,1170,1666.730002 +0.119344,1206,1680.140366 +0.143711,1233,1694.576754 +0.560807,1432,1711.52499 +0.212816,1793,1732.035172 +0.085302,1271,1746.698907 +0.254053,1310,1761.803927 +0.624323,1348,1776.913847 +0.527509,1669,1796.077598 +0.101668,1028,1808.841512 +0.306598,1186,1822.251171 +0.467501,1756,1842.488958 +0.321,1162,1855.525873 +0.662023,925,1865.915879 +0.270598,1416,1881.900329 +-0.167979,744,1890.68278 +0.331308,1768,1911.447952 +0.190714,1326,1926.350809 +0.273799,1372,1942.708831 +0.407166,1691,1961.899463 +0.223936,1325,1977.072675 +0.297153,2157,2003.127739 +-0.159677,807,2013.383898 +0.285042,1291,2029.823029 +0.453895,1890,2052.50287 +0.540393,1555,2070.087311 +0.374808,1338,2085.612369 +0.575625,1360,2100.174642 +0.076728,854,2110.237453 +0.47248,1660,2128.928809 +0.099028,1604,2147.388218 +0.263965,1462,2163.280611 +0.70854,1040,2174.574142 +-0.351,719,2182.89623 +0.32158,1214,2196.051496 +0.188883,1110,2208.745308 +0.473006,1646,2227.009648 +0.726645,811,2235.659312 +0.005643,698,2244.07201 +0.345808,1861,2264.46147 +0.047737,1106,2277.141456 +-0.011771,937,2287.316231 +0.185014,1026,2298.690474 +0.284042,1594,2316.192745 +0.34994,1475,2332.983639 +0.122344,787,2341.665267 +-0.35,627,2348.655172 +0.642708,776,2357.285023 +0.42848,1326,2371.886458 +-0.021345,983,2383.227884 +0.152711,1165,2395.991268 +0.06749,1007,2407.310231 +0.091139,1131,2419.993504 +-0.071274,1030,2431.277618 +0.314404,1828,2451.777198 +0.484225,1582,2470.170651 +0.241053,1230,2483.351722 +0.36797,1436,2499.297812 +-0.337,585,2506.19799 +0.312495,1544,2523.451499 +-0.222288,1081,2535.934352 +0.761858,685,2543.13069 +0.336308,1630,2561.457017 +0.620798,1244,2574.557401 +0.231157,1239,2588.492305 +0.063238,1507,2605.600728 +-0.003138,922,2615.645136 +0.36097,1283,2629.923506 +0.138272,1651,2648.429688 +0.087302,1839,2668.67648 +0.010643,1088,2681.179077 +0.040737,1188,2693.995152 +0.09087,1097,2706.63285 +0.199297,1114,2718.253203 +0.597492,998,2729.570032 +0.442872,1960,2751.159108 +-0.352,1013,2762.383416 +0.175396,1188,2776.403532 +0.120948,887,2786.344491 +0.284734,2182,2810.880272 +0.298799,1258,2824.115423 +-0.049345,1179,2837.974272 +0.225692,1354,2852.526584 +0.221167,1079,2865.31323 +0.333773,1397,2881.094453 +0.236876,1780,2901.024697 +0.093668,1373,2915.646829 +0.564446,1090,2928.133854 +0.628607,1346,2942.485597 +0.570572,1008,2953.840782 +0.632056,1186,2966.702758 +0.277667,1434,2983.390372 +-0.290704,917,2993.647815 +0.668062,818,3002.281761 +0.280843,1494,3019.409417 +0.298984,1512,3036.773124 +-0.169979,599,3042.775243 +0.300098,1230,3056.798562 +0.323538,1440,3072.629483 +0.329495,1421,3088.392108 +0.092305,1076,3100.974165 +0.173883,1010,3112.216372 +0.164495,1095,3123.91478 +0.35297,2014,3146.574481 +0.055959,1166,3159.668678 +-0.162979,581,3166.626812 +0.059959,1199,3179.781515 +0.336808,2491,3208.383344 +0.142043,1598,3227.256768 +-0.024345,1138,3240.302853 +0.361,1640,3259.250785 +0.199984,1606,3277.11635 +0.452372,1661,3296.396707 +0.172059,1606,3315.853821 +0.048994,1680,3336.126063 +0.553779,1225,3350.342247 +0.17423,1316,3366.924041 +-0.322,377,3371.566689 +0.522492,1272,3385.913957 +0.331357,1119,3399.787042 +0.242053,1590,3419.242265 +-0.054591,963,3430.469065 +0.66294,1256,3445.893453 +0.248876,1162,3459.759739 +0.235688,1623,3479.616171 +0.372876,1528,3498.038796 +0.201564,1400,3514.942502 +0.311357,1359,3530.912704 +-0.333,664,3538.613464 +0.161322,1103,3551.501174 +0.159515,1754,3571.713377 +0.545492,998,3583.276338 +0.096926,1284,3597.61671 +0.011058,1036,3609.256053 +0.247053,1952,3630.773105 +0.472515,1529,3648.049855 +0.079538,1437,3663.937742 +-0.034422,933,3674.033031 +0.255378,2129,3698.146792 +0.294153,1826,3718.527338 +0.490401,1420,3734.514303 +0.325538,1171,3748.568419 +0.199014,1561,3766.148211 +-0.139189,857,3775.105511 +0.63489,1218,3789.267813 +0.298863,1466,3805.484964 +0.476607,1339,3820.954509 +0.266527,1526,3838.100676 +0.113948,1014,3849.449982 +0.570559,1265,3863.988739 +0.361636,2606,3892.729729 +0.483338,1085,3904.563888 +0.200297,1456,3921.323638 +0.187322,1565,3938.633878 +0.310153,1387,3954.250306 +0.335153,1268,3968.399149 +0.491234,1875,3988.591361 +0.464887,1638,4006.839846 +0.536696,1158,4019.837258 +0.749102,712,4028.062416 +-0.044113,686,4035.243363 +0.282527,1368,4050.937313 +0.303258,1200,4063.92464 +0.243053,1167,4076.861297 +0.347876,1578,4095.377112 +0.114948,984,4106.243385 +-0.352,729,4114.886095 +0.189866,1024,4126.5955 +0.551644,1318,4141.14438 +0.18523,1348,4157.216306 +0.169059,1335,4171.929751 +0.108668,1034,4183.550714 +-0.026502,907,4193.96905 +0.570229,1287,4209.454647 +0.471612,1472,4225.77182 +0.667492,1272,4240.327023 +0.093368,1132,4253.45139 +0.2763,1291,4268.288842 +0.308667,1350,4282.943671 +0.498848,1212,4297.199458 +0.462684,1870,4318.497252 +0.796708,776,4327.067646 +0.335737,1898,4347.63049 +0.231688,1494,4364.738682 +0.484996,1628,4383.057091 +0.300308,2052,4405.949776 +0.59404,1601,4423.571894 +0.011402,964,4435.007461 +0.005855,933,4445.294235 +0.094538,1312,4459.823326 +0.092368,1514,4476.969416 +0.491229,1444,4493.716174 +-0.138189,1078,4505.554642 +-0.167979,734,4513.99291 +0.238488,1221,4527.169672 +0.231589,1421,4542.974391 +0.174396,1152,4555.904329 +0.394372,1661,4574.550002 +0.147495,1362,4590.45055 +0.110921,838,4599.407365 +0.086668,1141,4612.28331 +0.322495,1283,4626.893366 +0.360808,1308,4642.668278 +0.14665,1372,4657.511975 +0.462996,1628,4675.979872 +0.631762,1066,4687.489505 +0.477966,1509,4704.753798 +-0.165677,902,4714.849724 +0.284924,1467,4731.728342 +0.215692,1470,4747.559347 +0.604974,1379,4763.066886 +0.312495,1954,4784.79532 +0.539508,1465,4801.834133 +0.48533,1355,4816.702089 +0.325621,1776,4836.750344 +0.7881,688,4843.99942 +0.537588,1298,4859.380374 +-0.027406,1276,4873.763125 +0.427168,2096,4897.015954 +0.638102,1198,4910.116283 +-0.346,569,4917.009467 +0.566914,1193,4930.291442 +0.524101,1268,4944.723758 +-0.163677,708,4953.174521 +-0.052422,1259,4966.704883 +0.107948,943,4977.965733 +-0.064118,1036,4989.424384 +0.318357,1383,5005.275507 +0.445777,1639,5023.227238 +0.259453,1372,5038.987425 +0.429872,1793,5059.186636 +0.316,1965,5082.095138 +0.226014,1318,5096.550705 +0.287098,1626,5115.135564 +0.275734,1503,5131.18824 +0.193557,1514,5148.632578 +0.187921,1121,5161.423704 +0.522329,1778,5181.537403 +0.525731,1219,5194.860199 +0.432206,1321,5210.579528 +-0.125111,643,5217.923795 +-0.161677,748,5225.559126 +0.202564,1238,5239.958626 +0.542446,1090,5252.796362 +0.257277,1142,5265.753634 +0.023139,1254,5279.024209 +-0.003357,779,5287.909243 +0.32245,1237,5302.149348 +0.202432,1544,5319.715334 +0.274734,1634,5338.488308 +0.168883,1267,5353.275285 +0.49345,1130,5366.24682 +-0.039531,777,5375.130621 +0.199059,1005,5386.619715 +0.134043,1488,5403.062119 +-0.031298,1213,5417.107415 +0.635413,1221,5430.662368 +-0.048274,659,5437.978132 +0.266488,1068,5450.536219 +0.009855,1039,5462.055421 +0.165883,1357,5476.87825 +0.182883,1136,5489.867243 +0.568204,1429,5506.04287 +0.303357,1560,5524.542344 +0.148711,1387,5539.668746 +0.547735,1094,5552.529718 +0.547133,1204,5565.900548 +0.350843,1687,5585.847369 +0.219384,1252,5599.244967 +0.478229,1287,5613.662111 +0.643569,1141,5626.757025 +0.438748,1903,5648.525152 +0.288042,1537,5666.112037 +0.55055,1147,5679.364974 +0.540887,1638,5698.337148 +-0.008942,1089,5711.552686 +0.501607,1346,5726.472234 +0.060421,1080,5738.525993 +-0.012942,1188,5752.743114 +0.458108,1822,5773.284035 +0.223564,1169,5786.467795 +0.496801,1685,5805.621978 +0.544038,1558,5823.16164 +0.551719,1511,5840.637708 +-0.236121,869,5850.936882 +0.174495,1031,5862.582939 +0.489895,1890,5884.77982 +-0.054531,1497,5902.332631 +0.476225,1370,5917.55641 +0.518089,1484,5935.32581 +0.697913,1038,5947.297655 +0.126314,790,5956.232607 +0.274138,1110,5969.087 +0.088484,1326,5983.804893 +0.06587,1110,5996.908069 +0.470917,1772,6017.570665 +0.467357,1607,6036.289413 +0.142057,954,6048.439018 +0.26822,1300,6063.497838 +0.265378,1312,6079.084197 +0.537331,1498,6097.092046 +0.308924,1405,6113.449901 +0.109344,1261,6128.459917 +0.669762,860,6138.055008 +0.152711,1242,6152.879194 +0.063421,778,6161.991296 +0.35197,1972,6185.461678 +0.148948,1205,6199.281093 +0.538404,1306,6214.279584 +0.36597,1486,6232.746969 +0.333737,2107,6257.690215 +0.012402,1063,6271.692791 +0.364,1484,6289.58904 +0.622855,1060,6301.971003 +0.162883,1357,6319.036739 +0.246965,1650,6339.435691 +0.291734,1039,6351.891389 +0.192297,1578,6370.576223 +0.275699,1859,6393.211031 +0.554031,1533,6411.894744 +0.77624,761,6421.38866 +0.297258,1330,6436.910682 +0.243936,1476,6456.092498 +0.287863,1059,6468.730793 +0.617868,1470,6485.671503 +-0.117502,620,6493.193437 +0.523279,1436,6510.953708 +0.232783,1281,6526.300683 +0.126057,975,6537.273669 +0.101272,979,6549.056252 +0.419805,1763,6570.412484 +0.291799,1811,6592.143195 +0.217167,1187,6606.281862 +0.447968,1446,6623.184317 +0.134564,863,6633.910758 +0.126948,1179,6647.806896 +0.392301,1748,6669.317222 +0.690824,846,6680.193 +0.214692,1726,6700.671504 +0.498734,1388,6717.363555 +0.221157,1243,6732.418976 +0.566529,1285,6748.233417 +0.600228,924,6759.402407 +0.091564,1052,6772.035427 +0.480459,1489,6791.080731 +0.089302,1211,6805.517682 +-0.124719,1039,6818.269203 +0.490603,1745,6840.216898 +0.090302,1132,6854.461658 +0.265453,1377,6870.286272 +0.266667,1857,6893.170039 +0.33245,1952,6916.297037 +-0.304704,764,6925.548095 +-0.162979,1039,6938.010589 +0.290153,1531,6956.734369 +0.191157,1677,6977.03902 +0.27422,1267,6992.918086 +-0.346,587,7000.632542 +0.182883,898,7011.477269 +0.172396,1444,7028.761753 +0.190014,1847,7051.965228 +-0.044345,1524,7070.669652 +0.277965,1385,7086.521573 +0.682262,740,7095.729229 +0.315258,1963,7119.546574 +0.420007,2273,7147.984242 +0.62755,967,7160.184568 +-0.273288,654,7168.183851 +0.058421,1960,7191.698081 +0.523352,1718,7213.321492 +0.152921,1338,7228.931495 +0.270527,1052,7241.422172 +0.166701,1561,7259.785138 diff --git a/006_rgb_stack_ram_based_reward_time_reward_final_round/logs/4/monitor.csv b/006_rgb_stack_ram_based_reward_time_reward_final_round/logs/4/monitor.csv new file mode 100644 index 0000000..69e7ed9 --- /dev/null +++ b/006_rgb_stack_ram_based_reward_time_reward_final_round/logs/4/monitor.csv @@ -0,0 +1,460 @@ +#{"t_start": 1680618620.5619814, "env_id": null} +r,l,t +-0.209126,798,15.495865 +0.296258,1666,35.448927 +-0.000771,956,46.476265 +0.36494,2022,70.496044 +0.042971,1102,84.352511 +0.191059,1245,98.82504 +-0.004623,1253,114.090027 +0.35258,1804,135.765235 +0.582757,1331,152.34095 +0.177701,1233,166.650425 +0.200357,1232,181.737547 +0.209014,1252,196.943296 +0.272734,1596,215.743326 +0.36097,1759,237.080189 +0.11165,940,247.794722 +0.585196,1173,262.052264 +0.487152,1460,280.040301 +0.217277,1670,299.9905 +0.10865,1444,317.233394 +0.221277,1237,332.484731 +0.013862,898,343.348797 +0.244384,1438,360.384756 +0.297378,1247,375.573317 +0.143564,1009,387.852867 +0.34994,1453,404.698465 +0.550607,1339,420.131447 +0.321258,1831,442.56352 +-0.150159,1207,456.676237 +0.274783,839,467.300693 +-0.174979,617,474.854721 +0.59314,959,485.928885 +-0.071913,1124,499.785774 +0.068959,1117,513.492543 +0.35197,1571,532.285683 +0.230688,1348,547.85951 +0.35197,1198,562.778036 +-0.089118,857,572.234677 +0.057971,952,584.103354 +0.197297,1077,596.463809 +0.514368,1154,610.310973 +0.31045,1826,633.237673 +0.598026,1162,647.373414 +0.042437,1175,661.404036 +0.295799,1625,681.604767 +-0.147111,1191,695.896099 +0.259527,2018,720.595149 +0.230936,1713,740.85102 +0.118519,1326,756.577826 +0.087668,1179,771.727233 +0.552639,1396,787.459887 +0.535719,1511,806.074966 +0.242783,1778,827.778393 +0.135272,1234,843.409334 +0.371908,1887,866.731896 +0.279863,1749,887.229335 +-0.000775,1112,900.645164 +0.010855,1205,914.664349 +0.636234,989,926.559214 +0.267378,1718,946.421853 +0.18223,1565,966.352822 +0.19023,1413,983.279476 +-0.084274,1003,995.996242 +0.346308,1482,1013.979606 +0.254384,1395,1031.272479 +0.117519,1416,1048.426856 +-0.089118,1309,1064.00166 +-0.011138,758,1073.456068 +0.062948,1559,1091.892384 +0.086302,1431,1109.664215 +0.212692,1206,1123.458683 +0.37997,1895,1146.621102 +0.25422,1602,1165.611773 +0.359808,1926,1189.187743 +-0.083913,971,1201.542576 +0.234589,1519,1220.269446 +0.005402,1372,1237.111561 +0.185059,1246,1251.476462 +0.37197,1674,1271.396582 +-0.11233,615,1279.010865 +0.35197,2616,1311.609653 +0.028518,1160,1325.718545 +0.467726,1595,1344.280744 +0.115028,1225,1359.524373 +0.32845,1435,1376.930275 +0.191297,1264,1392.747741 +0.260378,1404,1410.502486 +0.167272,1080,1423.217164 +0.369843,1477,1441.541211 +0.319206,1658,1461.553221 +0.074728,1208,1475.665178 +0.548189,1356,1492.455154 +0.298924,1191,1506.467877 +0.082302,1172,1520.403888 +-0.088675,1364,1537.501266 +0.441694,2158,1565.318418 +-0.16144,966,1577.268431 +0.121432,1275,1593.708437 +-0.032113,1394,1609.985203 +0.519243,1047,1621.775052 +0.425078,1833,1643.30417 +0.122792,1632,1661.59155 +0.001028,1020,1673.228978 +0.259378,1687,1692.216984 +0.165921,1153,1706.94399 +-0.011295,878,1716.499381 +0.563248,1254,1730.965372 +0.542607,1346,1746.834907 +0.020518,1302,1761.908933 +0.518552,1404,1778.221351 +0.348908,1921,1800.356223 +0.339843,1550,1818.066865 +-0.062674,1205,1831.394082 +0.351621,1998,1854.393761 +0.391613,1838,1874.967459 +0.438529,1285,1889.749467 +0.532383,1598,1908.819521 +0.358737,1457,1925.260255 +0.335661,1503,1943.070518 +0.507877,1409,1959.162694 +0.050994,979,1970.842567 +0.323404,1286,1985.961279 +-0.075274,619,1993.231571 +0.216277,1563,2013.2039 +-0.002771,983,2025.088174 +0.588066,1541,2044.314266 +0.36894,1621,2062.910535 +0.702403,983,2074.292737 +0.782471,735,2082.77484 +0.346843,1743,2101.698065 +0.290098,1390,2117.559944 +0.286453,1344,2132.296377 +0.182866,1070,2144.866098 +0.122023,1410,2160.51511 +0.52769,1050,2171.871964 +-0.243389,915,2181.830578 +0.129564,1189,2195.841496 +0.237564,1362,2210.372499 +0.536995,1302,2224.631061 +0.657484,1124,2237.301429 +0.249965,1405,2253.078815 +0.291153,1466,2270.074392 +0.720333,909,2280.138974 +0.226589,1409,2295.766322 +0.57597,1104,2307.565963 +0.505225,1582,2325.847925 +0.331661,1372,2340.503596 +0.227053,1646,2358.932651 +0.51178,1290,2373.406551 +0.538954,1054,2385.85862 +0.178557,1132,2397.662976 +0.609417,727,2405.964509 +0.317495,1605,2424.169536 +0.286,1337,2438.796666 +0.134043,1197,2451.963198 +0.31245,1359,2467.572583 +0.35594,1227,2481.691506 +0.452734,1388,2496.57534 +0.555897,1351,2511.94185 +0.475724,1667,2530.649403 +0.557393,1555,2547.684705 +-0.056531,1435,2563.411155 +0.492331,1625,2581.560798 +0.468531,1588,2598.901066 +0.308206,1718,2618.556669 +0.180557,1224,2631.701961 +0.601254,1267,2645.920212 +-0.295704,757,2654.467729 +0.032881,935,2665.636445 +0.145238,1315,2679.944522 +0.130807,1368,2695.231075 +0.260453,1606,2712.569545 +0.571335,1327,2726.958905 +0.478706,1544,2745.167173 +0.509625,1360,2759.654516 +0.255167,1051,2771.190321 +0.572426,1196,2785.116878 +0.521885,1439,2800.940102 +-0.34,653,2808.374857 +0.611094,1255,2822.481225 +0.100302,1300,2836.806452 +0.17223,1886,2858.250896 +0.236384,1589,2875.766093 +0.094023,1116,2888.518988 +0.102495,1594,2905.83457 +0.147495,1281,2920.104252 +0.35494,1688,2939.330334 +0.588038,1059,2950.97753 +0.160515,1063,2962.44082 +0.558924,1365,2977.871629 +0.140948,1017,2989.339029 +0.340843,1715,3008.149826 +0.228816,1290,3022.662215 +-0.091675,1273,3037.144441 +0.609757,1331,3052.369377 +0.50974,1471,3068.399817 +0.177396,1455,3084.273316 +0.142807,1273,3098.497115 +0.276863,2045,3121.247102 +0.607755,1352,3136.707352 +0.055314,1412,3152.490093 +0.307357,1607,3170.166893 +0.156921,1760,3190.373449 +-0.012502,838,3200.779052 +0.015225,1338,3215.632683 +0.302527,1478,3233.203139 +0.708112,891,3243.307488 +0.040887,773,3252.18839 +0.672288,853,3261.235342 +0.04949,862,3271.278678 +0.212053,1665,3290.533495 +0.526613,1045,3302.509899 +0.70249,1062,3315.993821 +0.272799,1420,3333.145315 +0.058959,1128,3346.924581 +0.555484,1124,3359.807204 +0.579642,1245,3375.051143 +0.475042,2071,3399.924043 +0.301308,1554,3418.216075 +-0.095118,958,3430.446065 +0.299206,1591,3449.295474 +0.266053,1337,3465.932858 +0.004643,1111,3478.520002 +0.412416,1589,3498.258796 +0.182557,1396,3515.1425 +-0.34,811,3524.771183 +0.030136,1163,3538.598022 +0.435408,1930,3560.408447 +0.193014,1388,3576.392796 +-0.091675,1026,3587.990402 +0.238564,1066,3599.642537 +0.496281,1459,3616.588251 +0.449841,1594,3633.914497 +0.312206,1508,3651.141335 +0.325621,1970,3672.752952 +0.235876,1799,3692.801764 +0.71707,854,3702.636904 +0.187866,1719,3722.649194 +0.214297,1159,3735.792566 +0.036225,1133,3747.717238 +0.331621,1613,3766.477213 +0.680876,1181,3779.510572 +0.257453,1213,3793.733659 +0.574885,1439,3809.794586 +0.183557,1456,3825.707838 +0.517484,1124,3838.455727 +0.07187,1257,3852.595418 +0.061484,1179,3865.942179 +0.544891,1620,3884.293366 +-0.132121,851,3894.039914 +0.649809,1012,3904.730886 +0.598178,1342,3920.095649 +0.120344,1065,3931.747108 +0.546059,1048,3943.294376 +0.210053,1411,3958.964763 +0.312495,1906,3980.196535 +0.114023,1363,3995.542024 +0.555109,1583,4012.962463 +0.467352,1320,4028.128417 +-0.341,538,4033.905165 +0.677846,897,4043.91508 +0.507186,1591,4061.20671 +0.611885,1296,4075.562071 +-0.088675,1292,4091.117446 +0.521401,1747,4110.681627 +0.337621,1568,4128.336792 +0.576343,691,4136.602443 +0.063421,912,4147.038756 +0.277527,1200,4160.470852 +0.37097,1384,4176.305866 +0.178495,1539,4193.946043 +0.102926,1095,4206.839688 +0.483171,1832,4227.351449 +0.141057,1459,4243.616108 +0.129519,1225,4258.021635 +0.150124,1519,4275.529996 +0.01655,901,4285.705831 +0.165057,1154,4298.797936 +0.148564,913,4308.959923 +0.614729,1188,4321.946188 +0.353737,1448,4338.77211 +0.093023,1224,4351.9899 +0.153043,1355,4367.54233 +0.481144,1876,4387.774116 +0.08587,1049,4400.290937 +0.489678,1649,4418.963476 +0.175701,1403,4434.059775 +0.433136,1910,4455.668929 +0.126519,1503,4472.749919 +0.465974,1379,4488.340888 +0.503976,1567,4505.832642 +0.715425,899,4515.852976 +0.015881,927,4526.043385 +0.507187,1452,4542.85811 +-0.035295,1094,4554.51809 +0.606096,1223,4568.615863 +0.496335,1841,4589.277127 +0.324621,1975,4612.071309 +0.468574,1579,4629.735074 +0.538347,1547,4647.491574 +0.596794,1105,4660.252706 +0.123792,1461,4676.163871 +0.382301,1748,4696.017477 +-0.134121,1095,4707.858303 +0.219432,1265,4722.202675 +0.743381,752,4730.608249 +0.462,1751,4750.356609 +-0.018502,1114,4762.026683 +0.343699,1987,4784.767811 +-0.344,612,4791.98292 +0.335773,1337,4806.616432 +-0.029422,714,4815.152374 +0.065305,996,4826.505159 +0.302357,1798,4846.671583 +0.310042,2118,4869.966268 +0.34994,1728,4889.800222 +0.201432,1432,4905.635499 +0.366773,1361,4921.468394 +-0.048422,927,4931.768029 +-0.021295,1040,4943.342564 +0.046136,967,4953.852458 +0.143807,1400,4969.809473 +0.530849,1478,4986.739385 +0.287863,1269,5001.219321 +0.202692,1484,5017.552063 +0.313308,1611,5036.215589 +-0.041298,777,5044.867123 +0.292153,1463,5061.849582 +0.472614,2188,5086.60974 +0.680636,898,5096.589704 +0.053887,1208,5109.897209 +0.698211,1149,5122.671472 +-0.196557,913,5132.672828 +-0.079591,1256,5147.265236 +0.183714,1410,5163.090096 +0.327699,2020,5186.078418 +0.623432,1279,5200.474032 +0.300308,2038,5223.944845 +0.292527,1409,5239.894394 +0.38694,1516,5257.172964 +0.35297,1608,5274.682654 +0.548124,1468,5291.893407 +-0.170791,1194,5305.147111 +0.182866,1509,5322.540303 +-0.157677,979,5333.12213 +0.159515,1387,5349.073024 +0.033518,952,5360.54815 +0.230488,1890,5381.360235 +0.153921,1650,5400.32511 +0.35794,1967,5423.108675 +0.514966,2072,5446.468728 +0.11865,917,5456.567883 +0.50733,1355,5472.286735 +0.396119,1682,5491.123705 +0.240816,1019,5502.731107 +-0.013942,966,5513.315768 +0.225384,1319,5528.965958 +0.35797,1776,5548.47414 +0.37794,2104,5573.073294 +0.275598,1356,5587.908343 +0.48877,1055,5600.408177 +-0.136111,972,5610.834406 +0.176396,1320,5626.470021 +0.490096,1922,5648.327425 +0.599889,1145,5661.415296 +0.072421,1101,5673.373691 +0.105028,1559,5691.317049 +0.148272,786,5700.236743 +0.231384,2085,5725.04166 +0.566826,1543,5742.682064 +0.370302,1758,5762.986556 +0.463674,1816,5783.550745 +0.06749,750,5792.352622 +0.257378,1326,5807.03337 +0.030518,1055,5818.68777 +0.323661,1476,5836.16872 +0.227488,1206,5849.594887 +0.341876,1343,5865.471511 +-0.089041,1286,5880.442847 +0.503213,1507,5896.988096 +0.201564,1257,5911.826651 +0.230621,1371,5928.144929 +0.146807,1256,5942.948762 +0.461301,1943,5964.992688 +0.342808,1847,5985.52543 +0.33558,1504,6003.079978 +0.449841,1594,6022.645684 +0.450833,1502,6039.541019 +0.434386,1942,6063.463652 +0.476603,1745,6083.753951 +0.188014,1653,6103.363189 +0.347843,1517,6121.177904 +0.492894,1337,6136.634088 +-0.069913,743,6145.617011 +0.095139,1012,6157.571836 +0.444225,1681,6177.023634 +0.316258,1466,6194.668253 +0.446583,1796,6215.743192 +-0.11533,816,6225.18205 +0.441875,1913,6248.28342 +0.559368,1215,6263.723622 +0.565958,1501,6281.795277 +-0.329,816,6292.53823 +0.493115,1618,6311.535882 +0.475036,1070,6325.230255 +0.206692,1476,6342.946611 +0.330699,1642,6362.778564 +0.650181,934,6373.650766 +0.544109,1242,6388.931136 +0.176059,1246,6404.061615 +0.248167,1038,6416.890991 +0.666477,760,6426.235595 +0.460771,2115,6451.708419 +0.350773,2013,6476.435416 +0.24922,977,6488.407927 +0.298153,1452,6505.260869 +0.654523,1118,6518.919887 +0.446694,2158,6544.562004 +0.250965,1655,6564.423909 +0.086926,1382,6580.37198 +-0.020623,946,6592.264196 +-0.082337,1332,6607.982719 +0.433118,2070,6632.595228 +0.134043,1214,6647.688895 +0.309734,1609,6666.427161 +0.270734,1670,6687.105469 +0.544574,1579,6706.768667 +0.016302,1251,6721.056486 +0.368876,1771,6742.433026 +0.497383,1598,6762.73797 +0.271598,1302,6778.552567 +0.545657,1123,6792.887048 +0.328404,1146,6807.090486 +0.468644,1318,6823.127139 +0.313308,1548,6842.021439 +0.531878,1585,6861.236839 +0.278667,1153,6875.035861 +0.410905,1742,6896.386442 +0.341808,1435,6913.322745 +0.538186,1540,6931.917734 +0.50607,1415,6948.994963 +0.533101,1021,6961.516516 +0.544248,1254,6977.065021 +0.455186,2056,7002.526242 +0.308042,1341,7019.245758 +0.195866,1651,7039.582637 +0.542085,1371,7055.62609 +-0.043345,1084,7069.443371 +0.105703,1144,7083.273569 +0.032881,890,7094.044217 +0.489317,1451,7111.544741 +0.146807,1404,7129.038409 +0.346908,2024,7154.187896 +0.470507,1571,7173.097499 +0.473595,1480,7191.536077 +0.454365,973,7202.826272 +0.51198,1517,7221.347555 +0.38794,1409,7238.406844 +0.37694,1731,7259.465137 diff --git a/006_rgb_stack_ram_based_reward_time_reward_final_round/logs/5/monitor.csv b/006_rgb_stack_ram_based_reward_time_reward_final_round/logs/5/monitor.csv new file mode 100644 index 0000000..69d4b74 --- /dev/null +++ b/006_rgb_stack_ram_based_reward_time_reward_final_round/logs/5/monitor.csv @@ -0,0 +1,478 @@ +#{"t_start": 1680618620.5359814, "env_id": null} +r,l,t +0.138807,1422,23.224307 +-0.313,758,32.338928 +0.276843,1201,46.345266 +0.220053,1144,59.958649 +0.19023,1297,75.166647 +0.5842,1155,89.361837 +0.270734,1415,106.353744 +0.080484,986,118.566231 +0.299308,2114,143.457037 +-0.015771,1209,158.574562 +0.345876,1532,177.137711 +0.462202,1821,198.6698 +0.680955,1006,211.063816 +0.234783,1252,226.096113 +0.38994,1767,246.398508 +0.16923,1341,263.42783 +0.355876,1614,281.92955 +0.534006,1646,301.811632 +0.572018,1262,317.286394 +0.179714,1391,334.16512 +0.659673,1061,346.721392 +0.080926,1012,358.978505 +0.330699,1906,382.081633 +0.18023,1257,397.043733 +0.014402,1038,409.194811 +0.228157,1209,423.162299 +0.114519,1689,444.027879 +0.151272,1290,459.542734 +-0.168979,749,468.808704 +0.137272,1126,481.431869 +0.170495,1230,496.828739 +0.320495,1769,518.225907 +0.096495,1144,532.275686 +0.138272,1250,547.44302 +0.2683,1675,567.352961 +0.742294,914,578.013326 +0.104028,1710,597.944783 +0.157515,1519,616.300561 +0.215167,1499,634.858937 +0.078926,1171,649.074575 +-0.141121,766,658.328671 +0.721102,712,666.515627 +0.501865,1263,682.109279 +0.294098,2464,712.862504 +0.144043,1704,733.003559 +0.35394,1463,750.388128 +0.561523,1118,764.146571 +0.332773,1788,785.756419 +0.324538,1644,805.870749 +0.152711,1327,821.576584 +-0.004357,879,832.556342 +0.515046,1329,848.527761 +-0.084138,806,859.045937 +0.05932,1056,871.645802 +0.462864,1814,893.306036 +0.052437,940,904.008617 +0.444446,1642,923.708173 +0.205014,1270,938.790728 +0.021518,1052,951.237841 +0.339258,1714,972.529913 +-0.030295,1020,985.01216 +-0.13744,627,992.940899 +0.037518,1021,1005.766875 +0.582402,1253,1020.432917 +0.35194,1511,1039.242459 +-0.022406,1025,1051.67488 +-0.35,744,1060.810016 +0.333773,1490,1079.32295 +-0.099489,744,1088.383114 +0.535734,1388,1103.95569 +0.168883,1470,1121.840723 +0.188157,1608,1140.848499 +0.258378,1890,1164.013869 +-0.058531,1448,1182.475661 +-0.137189,1082,1195.368964 +0.138272,1441,1212.813464 +0.01355,753,1221.947333 +-0.007502,1098,1235.719368 +-0.015074,826,1245.303717 +0.325661,2451,1274.430778 +-0.348,635,1282.266331 +0.306258,1022,1294.763351 +0.017881,1026,1307.312889 +0.208098,1094,1321.182919 +0.246053,1534,1339.573951 +-0.045422,813,1349.003054 +0.199701,1320,1364.697588 +-0.030298,1068,1378.450882 +0.207692,1285,1394.333645 +0.368699,1653,1415.140474 +0.642365,973,1426.431293 +0.262453,1630,1446.282755 +-0.17235,628,1454.022406 +0.515333,1490,1472.380011 +0.108028,1005,1483.612094 +0.284042,1707,1504.903693 +0.197432,1227,1518.941149 +0.355699,1396,1536.233615 +0.640802,1088,1550.581736 +-0.092603,847,1560.879324 +0.052484,1029,1574.114197 +0.311404,1189,1590.23325 +0.486652,1677,1609.906203 +0.563455,1202,1623.260621 +0.280863,1916,1645.208063 +0.519804,1743,1665.696667 +-0.291452,639,1673.016888 +0.310153,1832,1693.538331 +0.448039,1958,1716.573025 +0.647535,1024,1728.151665 +0.553879,878,1738.334259 +-0.206126,1011,1750.017663 +0.597047,1236,1764.816576 +0.143495,1210,1778.499352 +0.490868,1470,1795.928092 +0.238876,1663,1814.995018 +0.186883,1460,1831.349082 +0.02255,887,1841.490778 +0.275863,1508,1858.780499 +0.331,1577,1876.392253 +0.546325,1260,1891.046075 +0.484894,1337,1907.080943 +0.096368,924,1917.677638 +0.569077,1192,1931.089197 +-0.019295,1050,1943.239464 +0.489734,1388,1959.250692 +0.181396,1206,1973.810444 +0.476637,1464,1990.560492 +0.112368,784,2000.036848 +0.475394,1113,2014.934103 +-0.17235,835,2025.065173 +0.080305,1182,2041.00696 +0.507124,1524,2057.279302 +0.568798,1044,2069.893999 +0.507698,1381,2084.693258 +0.295799,1673,2103.290439 +0.163711,986,2114.716364 +0.298843,2511,2143.391788 +0.653251,1137,2156.250059 +0.532209,1216,2169.111147 +0.123519,1197,2182.951234 +0.189557,1086,2194.713861 +0.622038,1350,2210.100123 +-0.014942,1124,2221.780261 +0.428993,2020,2244.534011 +0.630134,1422,2260.383584 +0.087297,1134,2273.197369 +0.486706,1544,2290.340854 +0.068484,968,2301.660161 +0.435712,1264,2315.890495 +-0.163979,701,2323.2723 +0.504206,1956,2344.770879 +-0.047345,868,2354.687563 +0.252876,1141,2367.481938 +0.138876,1173,2380.560558 +-0.020282,853,2390.265046 +0.465735,1724,2408.987415 +0.026737,1179,2422.751661 +0.35094,1506,2438.973665 +0.47649,1707,2458.818019 +0.610855,1060,2470.478866 +0.71862,751,2478.973812 +-0.032295,997,2490.375743 +0.005229,566,2496.40134 +0.272799,1476,2513.158028 +0.442213,1507,2529.437463 +0.280799,1488,2546.179851 +0.097302,922,2556.266311 +0.219384,1300,2570.39229 +0.074139,1350,2585.751849 +0.099368,1006,2597.080492 +-0.042422,1140,2609.886842 +0.048437,801,2618.565668 +-0.04051,882,2628.556955 +-0.055118,849,2637.386868 +0.200564,1424,2654.100401 +0.292153,1563,2671.358139 +0.448401,1757,2690.122593 +0.357,2176,2714.21876 +0.198297,1413,2729.899118 +0.150124,1296,2745.253173 +0.373773,1831,2765.232746 +0.039518,936,2775.456354 +0.462213,1507,2792.400413 +0.550017,1610,2811.011273 +0.328699,2489,2838.317271 +0.739327,808,2847.029501 +0.082302,1185,2861.149456 +0.084305,1047,2872.755558 +0.243876,1604,2890.194683 +0.131807,1384,2905.772572 +0.673953,1243,2919.883252 +0.374908,1272,2933.899886 +0.155564,1606,2951.251289 +0.349,1933,2972.571433 +0.247688,1349,2988.027501 +0.181883,1221,3001.26357 +0.439401,1747,3021.205177 +0.324984,1723,3041.17308 +0.223277,1192,3054.087973 +0.463505,1850,3074.306573 +0.180921,1144,3087.183477 +-0.003138,949,3098.224687 +0.190799,1023,3109.690752 +0.599719,1146,3122.373541 +0.26222,1724,3141.120851 +0.198883,1186,3154.265364 +-0.288704,593,3161.293564 +0.493103,1516,3178.470325 +-0.099489,636,3185.644535 +-0.114,1093,3198.206844 +0.154322,1031,3210.088557 +0.580228,924,3221.410223 +0.476226,1515,3238.019096 +0.277924,1228,3252.389701 +0.463838,1723,3272.475891 +0.134792,1041,3284.476217 +-0.008138,1079,3296.586705 +0.206816,1444,3313.311138 +-0.156674,837,3324.057063 +0.148272,1744,3345.452471 +0.06349,926,3356.492112 +0.692369,839,3365.971308 +0.589206,1321,3382.594228 +0.597541,908,3393.58596 +0.229589,1807,3414.94583 +0.280924,1433,3432.107409 +0.241384,1454,3449.405472 +0.40788,2275,3476.955061 +-0.040041,773,3486.219748 +-0.033307,774,3495.484195 +0.354843,1968,3519.916952 +0.664536,889,3530.766478 +0.362773,1923,3552.905202 +0.117519,1651,3571.768207 +0.588368,1215,3585.167884 +0.071728,753,3593.673338 +0.39194,1527,3610.964561 +0.254688,1306,3625.33827 +0.156711,1097,3637.95006 +0.099538,1016,3649.491131 +0.104703,1133,3661.426191 +0.33,1581,3679.577765 +-0.109312,719,3687.096105 +0.046994,1039,3698.548074 +0.076994,999,3709.902849 +0.33545,1366,3725.798618 +-0.162979,774,3734.520305 +-0.161979,721,3743.002174 +0.38747,1941,3764.983494 +0.560739,1140,3777.792395 +0.079421,1186,3790.917767 +-0.160677,647,3798.244659 +0.351699,1174,3811.32342 +0.505966,1127,3824.057316 +0.320206,1467,3840.074166 +0.087302,1164,3853.820105 +0.573492,998,3864.584116 +0.632942,950,3875.701815 +0.170701,1831,3895.844597 +0.300308,1536,3913.140787 +0.300984,1564,3930.404404 +0.121057,1265,3944.583108 +0.148495,1190,3957.646485 +-0.347,832,3967.27599 +0.601841,1594,3984.517316 +0.043136,904,3994.393916 +0.6027,1176,4008.22407 +0.186557,1755,4027.105627 +0.311495,1951,4049.571546 +0.248138,1568,4066.791749 +0.692999,661,4074.044888 +0.087668,858,4084.116702 +0.166921,1159,4097.07081 +0.110948,1389,4113.359636 +0.611916,1323,4128.166792 +0.337808,1684,4147.170753 +0.226432,1461,4164.466783 +0.746885,721,4172.054754 +0.346808,1421,4188.191127 +0.102344,1146,4201.310559 +0.241692,1299,4215.841038 +0.112302,1206,4230.346637 +0.56294,1199,4243.532108 +0.145948,1010,4255.179572 +0.462078,1833,4275.867585 +0.233688,1661,4294.677318 +0.545008,1211,4308.894923 +0.346908,1560,4326.108296 +0.118792,1324,4340.616657 +0.280799,1183,4354.571451 +0.594625,1325,4369.104594 +0.737541,781,4377.706674 +0.089023,836,4387.369865 +0.268453,1485,4403.50539 +0.620428,1014,4415.074893 +-0.025502,1120,4427.970958 +0.069305,1383,4443.798594 +-0.154979,1057,4455.472928 +0.469244,1608,4472.950116 +0.159272,1130,4485.709877 +0.460272,1690,4505.503643 +0.129564,1070,4517.154489 +-0.329,688,4524.598015 +0.537972,1674,4543.164392 +0.453802,1417,4559.018203 +0.371699,1879,4580.383436 +0.345843,1655,4599.367776 +0.347876,1416,4615.231843 +0.36797,1245,4629.63857 +0.274863,1573,4647.517574 +-0.114719,901,4657.588975 +0.2683,1039,4669.200903 +0.194432,1204,4683.060899 +0.125703,1225,4696.238477 +0.349621,1699,4716.111465 +0.32145,1523,4732.258342 +0.613041,1180,4746.048792 +-0.082913,1280,4760.246172 +0.359876,1783,4780.238814 +0.502152,1532,4797.476446 +0.32645,1688,4816.57993 +-0.011771,1083,4828.250335 +0.135238,1354,4843.823416 +0.283984,1379,4859.488377 +0.408907,1684,4878.258063 +0.077484,1063,4889.968424 +0.099028,1365,4905.537493 +-0.055913,863,4914.583271 +0.490697,1658,4933.532782 +0.571897,1351,4949.135445 +0.439033,2058,4972.550346 +-0.137189,1063,4984.151366 +0.342876,1739,5004.197264 +0.050887,865,5014.274953 +0.368108,1627,5032.001444 +0.4381,1899,5053.611562 +-0.076913,875,5063.502293 +0.308357,1310,5078.251864 +0.449282,1709,5097.985686 +0.131314,1070,5109.863211 +0.086139,1302,5124.198483 +0.161667,1738,5144.190762 +0.099703,1397,5160.028065 +0.260965,1523,5177.30632 +-0.044531,873,5186.356901 +0.352699,1347,5201.98023 +0.312308,1294,5216.866516 +0.076305,1056,5228.534352 +0.71237,830,5238.406938 +0.399626,1951,5260.346721 +0.248783,1484,5277.303561 +0.553085,1371,5292.251651 +0.112948,1553,5309.673569 +0.480666,1622,5328.570979 +0.326357,1620,5347.324527 +0.33358,1644,5366.353816 +0.06149,878,5375.630621 +0.248053,1749,5395.831092 +0.344357,1723,5415.79843 +0.150043,1211,5429.179421 +0.343843,1876,5450.674222 +0.563402,1190,5463.754787 +0.554588,1298,5478.281416 +0.60497,1104,5491.142705 +0.222488,1437,5507.35287 +0.540239,1191,5520.585312 +0.423335,1841,5542.35187 +0.004862,1024,5553.956404 +-0.287452,696,5561.454239 +0.46241,1767,5581.87615 +0.35097,2103,5605.058874 +-0.066563,1040,5616.692059 +0.531275,1556,5635.226351 +0.528294,1203,5648.555151 +0.147043,1331,5663.39879 +0.097368,1039,5675.094759 +0.502492,1272,5689.908337 +0.395695,1686,5710.268363 +-0.249304,622,5716.561306 +0.294098,1478,5734.087307 +0.629645,772,5742.83906 +0.494595,1480,5760.170593 +0.331737,1773,5779.611389 +0.180396,1435,5796.88909 +0.209396,1310,5811.310674 +0.051994,1207,5824.744041 +0.572699,1304,5840.401128 +0.253773,1705,5859.653034 +0.095668,1217,5873.364398 +0.48548,1326,5889.314252 +0.669613,1353,5904.444622 +0.312357,1725,5925.011432 +0.002862,1040,5937.013401 +0.566401,1420,5953.363943 +-0.068274,850,5963.420959 +0.672714,759,5972.01746 +0.155314,1029,5983.646897 +0.161701,1488,6000.130953 +0.031225,1339,6016.122821 +0.225014,1559,6034.839023 +0.112023,1196,6048.88268 +0.18822,1327,6065.047503 +0.218157,1378,6080.894253 +0.268667,1780,6102.016077 +0.216816,1565,6119.997996 +0.146711,1286,6136.187202 +0.206936,1257,6150.20875 +-0.17835,1298,6165.279835 +-0.033531,884,6175.551636 +-0.277452,844,6185.878542 +0.293206,1641,6205.228605 +-0.097118,1246,6220.249409 +0.002139,929,6231.310787 +0.323661,1214,6245.312399 +0.686062,818,6255.996121 +0.132564,1628,6275.496944 +0.329661,1545,6294.460893 +0.070421,1317,6311.286881 +0.265667,1691,6331.740227 +0.341876,1852,6353.861008 +0.322621,1862,6376.572551 +0.306206,1742,6397.861279 +0.337737,1929,6421.463782 +0.645384,1184,6435.330602 +0.189014,1636,6456.232499 +0.318495,1337,6471.92039 +0.451237,1932,6494.873887 +0.339843,1609,6514.271947 +0.585535,1177,6528.218644 +0.357876,1638,6547.729216 +0.716126,1064,6560.196843 +0.570361,1160,6574.101398 +0.183059,1164,6588.014418 +0.2853,1583,6607.758074 +0.224488,1470,6624.847458 +-0.016623,933,6635.727566 +0.356773,1448,6653.777599 +0.255965,1208,6668.032563 +0.165272,1725,6689.888126 +-0.163979,796,6699.204311 +0.558099,1445,6716.120149 +0.485924,1924,6739.191012 +0.478211,1565,6758.257037 +0.421679,1795,6780.375335 +0.159322,1337,6797.68129 +0.145057,1262,6813.414412 +0.577736,1297,6829.353648 +0.035225,748,6838.738698 +0.340357,1458,6856.368746 +0.124314,1297,6871.871648 +0.303357,1570,6890.507452 +0.064421,1108,6904.305763 +-0.15744,1110,6917.819236 +0.013139,1077,6930.33535 +0.722007,779,6939.683836 +0.598305,1228,6955.139404 +-0.352,568,6961.522518 +0.430225,1582,6981.547068 +0.358699,1495,6999.491172 +0.091538,1163,7013.52807 +0.349876,1918,7036.940974 +0.151495,941,7049.018231 +0.533662,1631,7069.31037 +0.121792,1182,7083.327569 +0.235589,1480,7100.677435 +0.308308,1407,7118.030991 +0.347,1716,7140.095402 +0.128792,1373,7156.10409 +0.498858,1518,7174.772199 +-0.142979,1025,7187.271074 +0.477219,1114,7201.118431 +0.174396,1754,7222.718013 +0.108668,836,7232.277865 +0.308042,1760,7253.75476 +0.571337,1506,7271.992543 diff --git a/006_rgb_stack_ram_based_reward_time_reward_final_round/logs/6/monitor.csv b/006_rgb_stack_ram_based_reward_time_reward_final_round/logs/6/monitor.csv new file mode 100644 index 0000000..62c8bb0 --- /dev/null +++ b/006_rgb_stack_ram_based_reward_time_reward_final_round/logs/6/monitor.csv @@ -0,0 +1,475 @@ +#{"t_start": 1680618620.5979824, "env_id": null} +r,l,t +0.298258,1798,27.716616 +0.682344,963,38.687349 +0.339843,1474,56.841347 +0.081701,992,67.701295 +0.011402,983,79.718077 +-0.165677,694,87.987511 +0.669809,1012,100.301895 +0.37097,1860,123.154617 +0.180714,1654,143.147541 +0.027136,1056,155.574236 +0.011959,834,166.237176 +0.466326,1728,186.415308 +0.021518,759,195.5372 +0.348908,1277,211.094816 +0.025518,1440,227.864401 +0.298098,1364,244.576717 +0.073728,826,254.03436 +0.345737,2075,279.8553 +0.630451,880,289.539325 +0.298153,1250,304.810189 +0.045437,974,317.020392 +0.496161,1887,340.051676 +0.11365,1418,357.059107 +0.253053,1015,369.333243 +0.053994,1008,380.589351 +0.237432,1457,398.364772 +0.172059,1860,420.023445 +-0.127489,819,430.260439 +0.313495,2482,459.662959 +0.468273,1573,478.269941 +0.154314,1498,496.80674 +0.684956,733,505.980038 +-0.107,1033,518.190905 +-0.019345,1148,532.258684 +-0.041282,963,543.242853 +0.438927,1454,561.211913 +0.268734,1691,581.079903 +0.481459,1651,600.760435 +0.359808,1968,624.289984 +0.018518,1088,637.908796 +0.37097,1624,657.025401 +0.479115,1618,677.174713 +-0.047345,932,688.288039 +-0.134189,710,697.461266 +0.143043,964,708.686765 +0.727686,730,717.743878 +0.431133,1075,731.23431 +0.194432,1292,746.850524 +0.173396,1391,762.769526 +0.220053,1312,779.518211 +-0.025337,883,790.018872 +0.279799,1292,805.761747 +0.07087,1227,820.005078 +0.179495,1579,840.228688 +-0.022502,816,849.834729 +0.48025,1886,873.018277 +-0.044674,1067,885.599535 +0.096692,1575,903.900617 +0.105344,1162,917.754556 +-0.237288,1128,931.153876 +0.2703,1913,954.286529 +0.484393,1555,972.737911 +0.310404,1728,994.566772 +0.35497,2042,1020.04674 +0.109028,1103,1033.011012 +0.094023,1008,1045.41319 +0.153314,1155,1059.287496 +0.05049,986,1071.776392 +0.166059,1899,1094.69517 +0.327699,1899,1117.295761 +0.36894,1530,1135.634113 +-0.017502,1203,1149.745984 +0.319308,1473,1168.375681 +0.350908,1764,1189.142742 +0.229384,930,1201.311573 +-0.009771,1107,1214.370252 +0.119023,1350,1231.067615 +0.016643,876,1241.788 +0.061959,1773,1263.192183 +0.004855,1255,1277.516297 +0.237688,2055,1302.694722 +0.085538,1031,1315.155576 +0.559034,1295,1331.722915 +0.37294,1968,1354.93509 +-0.160979,961,1366.162654 +-0.11533,1407,1383.389282 +0.716501,913,1395.653841 +0.248053,1342,1412.136258 +0.181714,1411,1429.31213 +0.354843,2201,1455.640906 +-0.122719,996,1467.942108 +0.160515,1462,1485.118804 +0.113948,1394,1502.035221 +0.55508,1138,1515.651144 +-0.118489,988,1528.123317 +0.257053,2029,1553.771189 +0.53575,1338,1570.635635 +0.093668,893,1582.17171 +0.021703,709,1591.825716 +0.128057,1101,1604.193856 +0.24822,1772,1624.690584 +0.479726,1595,1643.335168 +0.492342,1482,1660.058912 +0.724507,852,1670.084374 +-0.195034,835,1679.101265 +-0.225288,1047,1691.753781 +0.145519,935,1702.544095 +-0.017771,1417,1719.168867 +0.206667,1488,1736.493504 +0.266667,1133,1748.654876 +0.343,1794,1770.572988 +0.649159,1086,1782.673775 +0.000862,1006,1794.44594 +0.481789,1535,1812.066926 +0.643875,1082,1824.059609 +0.350808,1472,1841.25978 +0.303357,2066,1864.636353 +0.472469,1333,1879.301341 +0.354,1837,1901.259758 +0.557699,1304,1916.16169 +0.38597,1392,1932.316372 +0.601211,1565,1950.235515 +0.115948,1309,1965.175707 +0.114344,1101,1978.570072 +0.271453,1392,1994.911186 +0.200153,1236,2010.237567 +0.522998,930,2022.980386 +0.200924,1750,2044.198266 +0.466858,1518,2061.464315 +0.227488,1583,2079.900959 +0.246936,1086,2091.609511 +0.258453,1334,2106.23287 +0.502229,1444,2123.142263 +-0.174979,808,2132.017271 +0.694254,622,2139.163469 +0.269667,1441,2155.041286 +0.171043,979,2166.125733 +0.46534,1616,2183.350232 +0.180515,1312,2198.75149 +0.233783,1434,2214.439362 +0.321357,1527,2231.373693 +0.683251,1137,2244.262009 +0.63158,1067,2255.901846 +-0.346,836,2265.704462 +0.154124,1506,2281.850452 +0.581731,1219,2295.836541 +0.291098,1601,2313.288182 +0.102368,1319,2328.633878 +0.258053,1024,2340.107593 +0.560778,1200,2353.10514 +0.307598,1255,2367.317937 +0.270688,1459,2383.361882 +0.536358,1830,2404.131006 +0.295153,1628,2421.63375 +0.280527,1298,2435.916241 +0.185488,1398,2451.886198 +0.327621,1767,2471.910309 +-0.145677,928,2482.052507 +0.296843,1614,2500.601138 +-0.146159,942,2510.679763 +0.51534,1616,2529.203295 +0.212053,1243,2543.105689 +0.61737,830,2551.896993 +0.314538,1181,2564.788873 +0.189866,1272,2578.85842 +0.024881,1153,2591.748188 +0.264488,1221,2605.724725 +0.664257,835,2614.448596 +0.424585,1504,2631.487961 +0.033643,876,2641.424066 +0.647086,915,2651.452669 +0.439625,1325,2666.040442 +0.440401,1420,2682.555133 +0.37094,1473,2698.432232 +0.07387,1561,2715.449841 +0.669865,1175,2728.300036 +0.509108,1627,2746.914703 +-0.339,854,2756.541115 +0.242876,1297,2770.963319 +-0.016422,853,2780.773812 +0.321621,1110,2792.487411 +0.563099,1445,2809.572821 +0.340737,1625,2826.931886 +-0.062307,814,2836.588452 +0.173396,1622,2854.165807 +0.323661,1752,2874.23977 +0.190157,1647,2892.733604 +0.178714,2202,2917.060273 +-0.133189,834,2926.730408 +0.202714,1381,2941.193061 +-0.174979,852,2951.061314 +0.65558,1067,2962.531817 +0.294206,1647,2980.907014 +0.544264,1197,2995.051252 +0.10465,1394,3009.847222 +0.063959,1177,3023.84145 +0.100028,1401,3039.676879 +0.334621,1583,3056.92556 +0.341,1542,3074.090573 +0.504469,1427,3089.848543 +0.084139,972,3101.122159 +0.225384,1147,3113.825554 +0.360908,1628,3131.229287 +0.581196,1173,3145.141298 +0.027881,1056,3156.782905 +0.709851,855,3166.74481 +0.028855,1051,3178.349322 +0.540625,1325,3193.513562 +0.256453,1597,3212.344999 +0.42234,1616,3230.506413 +-0.083675,809,3240.294852 +0.687327,862,3249.453347 +0.035887,1093,3262.357553 +0.283924,1771,3282.90519 +0.313863,1237,3296.63458 +0.38894,1586,3316.01282 +0.249965,1517,3334.618844 +0.125519,1382,3350.468246 +0.490551,1305,3366.997041 +-0.317,524,3373.216893 +0.132792,1237,3387.487349 +0.656106,1000,3399.843042 +0.592559,1265,3414.940829 +0.473698,1705,3435.235045 +0.41147,1941,3458.51676 +0.016402,1158,3473.43222 +0.190984,1362,3489.132172 +0.089023,1163,3503.062124 +0.500358,1830,3526.000498 +0.341538,1575,3544.307274 +0.276667,1207,3557.545525 +0.366843,1684,3576.542795 +0.153322,978,3587.961401 +0.189396,1622,3606.509885 +-0.205034,646,3613.731376 +0.257378,1130,3626.48348 +0.449907,1684,3645.251209 +0.649878,996,3656.494813 +0.59802,741,3664.173741 +0.469442,1918,3685.581949 +0.377,1516,3702.618902 +0.537639,1396,3718.542341 +0.110344,1148,3731.592927 +0.133807,1801,3751.93439 +0.354,1345,3767.657318 +0.194014,1128,3779.543571 +-0.005138,1378,3795.420282 +0.534006,1646,3814.079175 +0.224167,1289,3828.42161 +0.198701,1554,3845.581723 +0.364773,1479,3862.785347 +0.059959,1097,3874.469676 +0.075421,1175,3888.315777 +0.250699,1413,3904.285693 +-0.114502,737,3911.799571 +0.341843,2007,3934.449293 +0.635874,1049,3946.05741 +0.282453,1441,3962.706338 +0.093421,1271,3975.988941 +0.703927,841,3985.721523 +0.351495,1190,3998.457709 +0.331098,1417,4014.301898 +0.238783,1300,4029.459837 +-0.223113,839,4038.211571 +0.372773,1388,4053.948457 +0.513107,1132,4066.652756 +0.297984,2611,4095.758622 +-0.352,586,4103.162904 +0.058421,1197,4116.455283 +0.379773,1176,4129.680209 +0.526267,1421,4145.681646 +0.34058,1651,4164.787457 +0.749148,840,4174.749027 +0.149272,1143,4187.879125 +-0.029295,1077,4199.787361 +0.720093,1109,4212.591236 +0.479905,1742,4232.042753 +0.327621,1466,4249.215096 +0.24722,1907,4271.210872 +0.191059,1424,4287.067845 +0.243783,1086,4299.014511 +0.238783,1417,4315.829577 +0.326699,1594,4333.11095 +0.414613,1353,4348.758838 +0.420926,1602,4366.194094 +0.333,1571,4383.410085 +0.046437,1192,4397.327253 +0.187866,988,4407.833321 +0.222866,998,4419.244478 +-0.187304,1141,4432.29526 +0.224432,1286,4446.885262 +0.088668,1092,4459.521788 +0.027737,1283,4473.946783 +0.039668,837,4482.80633 +0.490715,1734,4502.608164 +-0.118603,878,4512.669774 +0.217816,1508,4528.854364 +0.260138,1500,4545.800291 +0.256453,1490,4562.857925 +-0.031029,1074,4574.587003 +0.154124,1438,4590.808269 +0.207692,1407,4606.624958 +0.407798,2101,4631.039571 +0.435152,1532,4648.787788 +0.300042,1265,4662.990934 +-0.096118,985,4673.333495 +0.185921,1292,4687.612505 +0.547766,1359,4703.363067 +-0.135189,1009,4714.810449 +0.108703,1217,4727.96971 +0.605621,1226,4741.885323 +0.115703,1198,4754.848861 +-0.133189,939,4765.88638 +0.443053,1982,4787.746774 +-0.15535,532,4793.571764 +0.219432,1426,4809.581749 +0.331,1796,4830.730262 +0.694796,902,4840.834816 +0.577877,1409,4856.621232 +0.666293,765,4865.281994 +0.178688,1761,4884.322234 +0.34258,1608,4902.853269 +0.515757,1331,4917.379091 +0.141948,959,4928.856676 +0.224866,1420,4944.754756 +0.115948,1258,4959.200819 +-0.035298,1083,4971.122972 +0.252783,1255,4985.322579 +-0.046298,775,4994.100638 +-0.115719,808,5002.917742 +0.04132,803,5012.754339 +0.055484,1170,5025.87182 +0.224936,1234,5039.191426 +0.349908,1934,5060.891378 +0.352495,1471,5078.057863 +0.090668,1118,5090.93567 +0.094023,1277,5105.30718 +0.391908,1834,5125.444731 +-0.090719,773,5134.0228 +0.527116,1645,5152.9654 +-0.172979,921,5163.094096 +0.403468,1481,5180.21769 +0.06949,992,5190.717014 +-0.343,696,5199.04948 +0.273734,1786,5219.528543 +0.481456,1497,5235.858103 +0.011058,785,5245.554102 +0.326661,1717,5264.732526 +0.118792,1114,5277.357558 +0.189701,1465,5293.611117 +0.224277,1310,5308.177957 +0.138883,1117,5321.265038 +0.328,1799,5341.661896 +0.368908,1256,5356.375808 +0.506257,1307,5371.116925 +-0.007357,1125,5384.080443 +0.257453,1659,5403.06512 +0.548251,1377,5418.674519 +0.534855,1060,5430.643368 +0.589268,1108,5443.436946 +0.240488,1353,5458.062444 +0.578038,1350,5473.786426 +0.643228,1143,5486.82358 +0.545017,1610,5504.540937 +0.234876,1636,5523.391162 +0.043737,949,5533.83175 +0.539342,1482,5551.188206 +-0.10733,629,5558.538449 +0.081421,966,5569.866735 +-0.017332,1016,5580.666753 +0.091668,971,5592.042629 +0.617868,1470,5608.911271 +0.761301,795,5617.7254 +0.237936,1414,5633.816085 +0.637159,1026,5645.510921 +0.482094,1255,5659.977897 +0.255378,1658,5679.134658 +0.117344,1023,5690.891046 +-0.094118,968,5701.508351 +0.742262,740,5710.375365 +0.261876,1142,5723.531345 +0.460163,2180,5748.5195 +0.149564,1128,5761.602221 +0.421485,1361,5776.464231 +0.514535,1697,5796.768085 +0.239965,1622,5814.363431 +0.223277,1446,5831.525713 +0.316495,1980,5853.833596 +0.685099,809,5862.820048 +0.406958,1971,5886.265018 +0.560637,1464,5902.792409 +0.205816,1532,5920.569188 +-0.352,768,5929.680148 +0.691764,1134,5942.997758 +0.343699,1835,5963.711959 +0.526071,995,5975.23434 +0.358699,1554,5992.791503 +0.152866,1535,6010.432978 +0.260527,1421,6027.4577 +0.155272,892,6037.914621 +0.274667,1687,6058.017179 +0.085959,1628,6077.649817 +0.355,1455,6095.497191 +0.557876,1181,6109.136051 +0.611032,1156,6122.63911 +0.627731,1219,6136.585084 +0.144314,1185,6151.290521 +0.000402,902,6161.859296 +0.582705,1152,6175.136451 +0.434207,1499,6191.973464 +0.17623,813,6202.195663 +0.359808,1142,6215.670187 +0.461895,1890,6237.63976 +0.150711,1187,6252.841259 +0.51269,1578,6272.073786 +0.161515,1011,6284.758302 +0.573204,1414,6301.839002 +0.143272,1721,6322.450826 +0.045887,962,6334.819711 +0.435009,1386,6351.860385 +0.338843,1541,6370.392224 +0.536953,1243,6384.504936 +0.563836,1380,6401.151257 +0.185014,1546,6420.236432 +0.332699,2021,6445.202812 +0.449773,1858,6468.654057 +0.62978,1290,6483.792851 +0.126703,1662,6503.611038 +0.104344,1384,6520.285444 +0.458778,1621,6538.843986 +0.16622,1030,6550.941029 +-0.10368,1020,6563.273019 +0.34997,1388,6580.206978 +0.155157,1409,6597.235048 +0.343404,1377,6613.772698 +-0.346,985,6626.007693 +0.481607,1346,6641.730843 +0.364737,2104,6666.467161 +0.178714,1612,6686.912474 +-0.006272,1024,6699.270308 +0.474594,1871,6722.093991 +0.486796,1270,6737.257535 +0.261378,1136,6750.389845 +-0.122489,910,6762.566968 +0.390612,1596,6781.755507 +-0.011029,1047,6794.65059 +0.284042,2157,6821.551014 +0.121057,1490,6840.242897 +0.348737,1500,6858.070393 +0.241277,994,6870.258234 +-0.014942,1222,6885.545792 +0.35694,1685,6905.583968 +0.56308,1138,6919.292414 +0.57689,1218,6933.409275 +0.356908,1803,6955.374401 +0.304598,1657,6975.548489 +0.256378,1409,6993.075087 +0.071994,1045,7006.68333 +0.337737,1513,7024.299839 +0.338808,1793,7046.162035 +0.567359,1166,7060.337385 +0.072866,971,7072.619162 +0.184714,1204,7086.699573 +0.331699,1726,7108.34585 +0.579239,1191,7122.775986 +0.179059,1539,7141.865017 +0.197053,1341,7158.792367 +0.042437,1162,7172.938499 +0.273453,1609,7191.920076 +0.363773,2186,7218.472399 +0.045887,1269,7233.824295 +0.218692,1627,7253.746759 +0.098959,1138,7267.321335 diff --git a/006_rgb_stack_ram_based_reward_time_reward_final_round/logs/7/monitor.csv b/006_rgb_stack_ram_based_reward_time_reward_final_round/logs/7/monitor.csv new file mode 100644 index 0000000..0970781 --- /dev/null +++ b/006_rgb_stack_ram_based_reward_time_reward_final_round/logs/7/monitor.csv @@ -0,0 +1,466 @@ +#{"t_start": 1680618620.619981, "env_id": null} +r,l,t +-0.003138,913,17.011386 +0.648126,1064,29.396698 +0.416699,1304,44.833403 +0.482453,1787,66.036718 +0.326357,1992,90.674037 +-0.343,593,97.190704 +0.243053,1662,117.164116 +0.259453,1401,134.178301 +0.119519,1162,148.107784 +0.502122,1730,169.418167 +0.307404,1855,191.003949 +0.53041,1458,209.410433 +0.198866,1375,224.99976 +0.045437,1224,240.126973 +0.086302,1177,253.947363 +0.107926,1248,269.635406 +0.513329,1634,289.146483 +0.288098,1662,309.313333 +0.500231,1779,330.805471 +0.229384,1125,343.607801 +0.347908,2143,369.634246 +0.344908,1598,389.272933 +0.472633,1725,409.130322 +0.221936,1492,427.259561 +0.614719,1146,440.92105 +0.264053,1371,456.71724 +0.568735,1425,474.769718 +0.048518,1338,490.571326 +0.47202,1731,511.869364 +0.058959,999,523.15196 +0.465485,1361,539.910224 +0.315495,1823,561.421916 +0.516789,1535,579.653148 +0.24658,1419,596.392812 +0.230053,1793,617.925869 +0.578644,1271,633.526758 +0.352908,1620,653.654695 +0.249053,1443,670.978104 +0.536637,1464,689.412276 +-0.083675,1273,705.024469 +0.17623,1317,720.665153 +0.571336,1428,737.643009 +0.166124,1542,756.345813 +0.206816,1561,775.13029 +0.331699,1559,793.554417 +0.536679,1284,809.2164 +0.297153,1709,830.770033 +-0.10233,1070,843.525336 +0.084668,1322,859.325171 +0.052437,1423,877.450824 +0.269527,1624,896.295343 +0.157515,1361,912.910262 +0.249053,1509,930.818879 +0.166277,1038,942.946214 +0.103921,1766,964.720623 +-0.003771,809,974.0159 +0.2803,1627,994.39034 +0.544268,1108,1007.623528 +0.050994,1438,1026.007038 +0.319773,2056,1051.198081 +-0.224029,888,1061.937224 +-0.126312,955,1073.266069 +0.301908,1332,1088.730206 +0.032136,864,1099.18925 +0.467103,1760,1120.30682 +0.546675,1232,1135.507115 +0.568963,1485,1152.835846 +-0.086274,988,1165.281517 +0.527565,1562,1184.286759 +0.729845,991,1196.745569 +0.459241,1653,1217.088015 +0.529103,1516,1235.532365 +0.114519,1178,1249.652671 +-0.346,757,1258.695639 +0.177322,1070,1271.154581 +0.218936,1369,1288.140747 +0.314404,1923,1311.619899 +-0.046298,956,1322.848341 +0.085314,1042,1335.186141 +0.477402,1190,1350.183369 +0.161701,2230,1376.945275 +0.137314,1728,1399.094372 +0.574147,1229,1413.718154 +0.49023,1475,1432.15213 +0.109028,1407,1449.092113 +0.049994,1337,1464.854292 +-0.006623,871,1475.50368 +0.161322,1277,1490.952338 +0.132807,1255,1506.241877 +0.26222,1561,1524.889096 +-0.11233,771,1534.367698 +0.328699,1815,1557.259264 +0.142043,1352,1575.241306 +0.260527,1369,1592.101718 +0.330699,2036,1615.786397 +-0.100345,851,1625.914059 +0.289984,1624,1644.774063 +0.167921,1125,1657.256926 +0.08187,1524,1674.594288 +0.169711,1068,1687.322648 +0.052484,1247,1700.92785 +0.013862,1390,1717.801319 +-0.216034,727,1726.317602 +0.315404,1765,1746.794905 +0.59562,751,1755.599296 +0.085668,1253,1769.452978 +0.05649,770,1778.447351 +0.268734,1233,1793.077449 +0.196157,1878,1814.846016 +-0.172979,1054,1826.853369 +-0.309,639,1834.087948 +0.039881,1036,1845.661749 +0.167863,1087,1857.574813 +0.250138,2005,1880.696752 +0.03932,799,1889.71448 +0.228589,1592,1908.761521 +0.105368,1555,1926.516813 +0.555472,1354,1942.786833 +0.345737,1605,1960.686196 +0.785401,675,1968.207456 +-0.181892,683,1976.934675 +0.164701,1375,1992.175069 +0.326699,1305,2009.828563 +0.510204,1414,2027.894854 +0.558637,1528,2046.736211 +0.211816,1314,2061.321317 +0.176711,1088,2073.08454 +0.258378,1503,2090.220293 +0.351843,2129,2114.417683 +-0.139268,574,2120.417725 +0.205297,1445,2137.492543 +0.527154,1600,2154.977287 +0.252783,1241,2168.831939 +0.581038,1350,2183.274232 +-0.029406,1092,2195.9605 +0.201297,1858,2216.041642 +0.178883,1526,2233.049304 +0.613595,1029,2244.559019 +0.044737,1118,2257.264391 +-0.091118,705,2265.690464 +0.505337,1506,2281.832453 +0.571569,1141,2294.542168 +0.505282,1280,2308.91821 +0.492875,1972,2331.467008 +-0.108,1043,2342.923895 +0.232167,1248,2357.069834 +0.088926,981,2367.47994 +0.386869,1551,2384.826384 +0.337773,1692,2404.118008 +0.2673,2140,2427.246221 +-0.040531,859,2437.190084 +0.331737,1851,2457.661882 +0.540762,1586,2476.014422 +0.504815,1804,2496.274344 +0.625189,757,2504.762538 +0.507512,1554,2522.007929 +0.198564,1091,2533.668365 +0.141564,1789,2553.461828 +0.444332,1293,2568.586301 +0.491972,1205,2581.460799 +0.66555,1147,2594.34562 +0.544368,1522,2611.351077 +0.551709,1503,2628.374781 +0.67796,887,2637.356867 +0.535995,1302,2652.664012 +0.099028,1384,2667.465698 +0.41688,1526,2684.401407 +0.157515,1147,2697.111793 +0.295042,1600,2715.237844 +0.487719,1511,2732.30477 +0.06249,1063,2743.937929 +0.499956,970,2755.004472 +0.189157,1177,2767.891569 +0.222816,870,2777.892261 +0.502995,1302,2792.166411 +0.710478,894,2802.263457 +0.181863,1037,2813.963376 +0.265598,1392,2829.484369 +-0.018771,1288,2843.854412 +-0.06185,1028,2855.293996 +0.223258,1612,2872.945554 +0.218432,1921,2894.436141 +0.667428,1046,2906.760833 +0.044971,1058,2918.287471 +0.2683,1492,2934.135887 +0.116519,1271,2948.317723 +0.693774,936,2959.458843 +0.548742,1410,2974.940431 +0.700088,704,2982.340492 +0.368737,1905,3003.811409 +0.423997,1637,3022.44822 +0.337773,1403,3038.328462 +0.316538,2205,3062.625121 +0.087668,827,3072.350482 +0.10465,1234,3085.587041 +0.030225,873,3095.426213 +0.298734,1575,3112.686375 +0.691879,916,3122.71462 +0.239876,1282,3136.939532 +0.003643,1346,3152.489096 +0.182396,1579,3170.048896 +0.356876,1467,3187.015773 +0.635688,1403,3203.7974 +0.238783,1636,3222.764239 +0.444339,1885,3243.54049 +0.059484,857,3253.728659 +0.271734,1253,3268.196766 +0.143272,1023,3279.972475 +0.02355,1517,3297.724813 +0.35094,1947,3320.804591 +0.217936,1198,3334.915847 +0.442147,1407,3351.947086 +0.434518,1883,3374.916142 +0.235876,1628,3394.919178 +0.466787,1648,3413.632701 +0.522531,1588,3433.435621 +0.342876,2019,3458.06393 +0.529023,1461,3475.244587 +0.256453,1666,3495.291964 +-0.067274,818,3504.670756 +0.281984,1305,3521.423678 +0.527311,1125,3534.261922 +0.482229,1287,3548.992001 +0.278863,1844,3570.360635 +0.114948,1102,3583.354341 +0.292153,1783,3602.49295 +0.440637,1528,3619.673842 +0.221866,1052,3632.112554 +0.399897,1647,3649.882127 +0.35897,1562,3668.091906 +0.364843,1456,3683.999087 +0.440318,1863,3705.172496 +0.072887,985,3715.730609 +0.325661,1799,3736.097757 +-0.080913,1118,3748.983667 +-0.142121,952,3760.358678 +-0.344,810,3769.231796 +0.591329,1209,3782.294888 +0.129057,1187,3796.496624 +0.091302,1335,3811.140804 +0.247688,1272,3825.383822 +0.234816,1159,3838.310678 +0.340773,1685,3857.040086 +0.055136,1089,3869.842533 +0.178396,1129,3881.684038 +0.58038,1466,3898.603474 +0.436725,1938,3920.12465 +0.504806,1577,3937.476025 +0.145711,1425,3954.161308 +0.530071,1430,3969.850402 +0.053971,802,3978.58635 +0.511156,1574,3995.62598 +0.448207,1491,4012.700203 +0.378843,1434,4028.310417 +0.517865,1868,4049.528543 +0.210936,1613,4066.916794 +-0.035295,973,4078.202819 +0.306984,1764,4098.363976 +0.36594,1812,4119.314441 +0.163515,1436,4135.275556 +0.055484,1051,4147.150754 +-0.050345,1083,4160.139952 +0.365,1586,4177.718358 +-0.019295,1029,4189.465154 +0.153948,1260,4204.064518 +0.525871,1116,4216.92088 +0.249965,1717,4236.166852 +0.203564,1796,4256.579097 +0.353621,1470,4273.922145 +0.082926,1076,4285.752848 +0.187714,1567,4303.318704 +0.055959,1343,4318.769488 +0.275863,1701,4337.450799 +0.274843,1382,4353.242364 +0.269876,1283,4367.551332 +0.299308,1821,4387.55686 +0.651793,931,4397.710257 +0.323538,1266,4412.136186 +0.468473,1412,4428.118958 +0.368013,1683,4447.065249 +0.437362,1172,4460.980281 +0.06849,975,4471.365567 +0.2823,1452,4488.12189 +-0.32,656,4495.388462 +0.578321,1341,4510.05491 +0.245589,1503,4527.138385 +0.037737,928,4537.281479 +0.017225,1302,4551.656803 +0.191866,1202,4565.703463 +0.078926,1286,4580.159435 +0.142314,1219,4593.545879 +-0.151268,823,4603.446597 +0.501868,1470,4619.685608 +0.544189,1356,4635.356193 +0.298527,1172,4648.88279 +0.529644,1318,4663.341934 +-0.120623,612,4670.390572 +0.282598,1762,4690.213776 +0.741933,590,4696.251478 +0.101728,1261,4710.529812 +0.01955,1075,4723.318745 +0.333357,1686,4741.799326 +0.007402,937,4751.914416 +0.478988,1550,4769.039683 +0.245138,1321,4784.476811 +0.31958,1573,4802.051136 +0.480169,1042,4813.793997 +0.050994,1131,4826.602163 +0.558368,1215,4839.773037 +0.06887,1030,4851.244153 +0.49022,1031,4862.811507 +0.327661,1848,4884.098237 +0.573874,1049,4895.676389 +0.24822,1882,4917.113791 +0.602191,1328,4931.921028 +0.592875,1082,4944.596759 +0.340843,1568,4962.246087 +0.113703,1408,4978.125731 +0.363908,1998,5000.108081 +0.373908,1629,5018.821387 +0.542894,1337,5034.508061 +-0.17435,669,5041.895613 +0.461213,2082,5065.039278 +0.53156,1382,5080.99996 +0.51835,1652,5099.531381 +-0.118719,859,5109.554208 +0.083302,1117,5121.283228 +0.256378,1447,5138.209496 +0.43744,2027,5160.361477 +0.290153,1405,5176.256321 +0.259527,2481,5204.852788 +-0.004771,821,5213.982476 +0.103344,1438,5229.991593 +0.093023,1373,5245.837246 +0.077926,1347,5261.545786 +0.55133,1355,5276.198786 +0.430685,2130,5300.772758 +0.356737,1377,5316.539918 +0.107344,903,5326.949245 +0.695344,948,5337.187701 +0.305404,2345,5363.741716 +0.543926,1602,5382.585435 +0.282667,1601,5400.369112 +0.108139,1398,5416.174699 +0.340773,1671,5435.2298 +0.335773,1363,5450.838222 +0.243053,1354,5466.45341 +0.441937,1224,5479.775322 +0.314737,1633,5498.401374 +0.216167,1026,5510.181998 +0.611874,1151,5523.338164 +0.443907,1684,5542.553869 +-0.05806,645,5549.735928 +0.633146,1005,5561.370239 +0.305863,1760,5581.76715 +0.553094,1566,5599.168684 +0.511469,1333,5613.749112 +0.612099,809,5623.554852 +0.345908,1412,5639.569018 +0.088728,1027,5651.427177 +0.533512,1554,5668.944499 +0.486131,1609,5687.957154 +0.535924,1365,5703.03827 +0.575624,1089,5716.103305 +0.565109,1308,5730.945572 +0.29522,1275,5745.554399 +0.116302,936,5755.986764 +0.138792,877,5766.168686 +0.303042,1316,5780.898937 +0.216396,1202,5795.312059 +0.312495,1520,5812.527732 +-0.144675,918,5822.919549 +0.724748,966,5833.452745 +0.35994,1574,5852.221326 +0.18223,1142,5865.363511 +0.600838,1447,5882.003186 +0.707872,810,5890.955435 +0.05749,954,5902.461629 +0.128792,1104,5914.680128 +0.275863,1190,5929.348155 +0.192124,821,5938.487195 +0.279598,1472,5955.034399 +0.655913,1022,5966.609461 +0.395574,1579,5985.171432 +-0.146979,736,5993.851869 +0.06787,1026,6005.687302 +0.583243,1047,6017.687053 +0.196297,1811,6039.218021 +0.079926,1012,6051.645775 +0.452802,2048,6075.849628 +0.67949,1062,6088.272232 +0.769845,709,6097.080048 +0.28722,1559,6115.034152 +0.182124,1043,6127.191451 +-0.013623,1256,6142.416656 +-0.05506,928,6152.946195 +0.227167,1344,6169.128387 +0.091994,1023,6181.111818 +-0.348,620,6187.427215 +0.031136,872,6197.949337 +0.468789,1535,6215.941192 +0.123238,1301,6231.537787 +0.36697,1883,6254.586939 +0.287098,2003,6279.84804 +0.333773,1509,6297.424596 +0.31958,1366,6314.500671 +0.019855,1289,6330.282115 +0.318808,1706,6351.718386 +0.018139,1002,6362.937565 +0.243965,1242,6378.123561 +0.286378,1259,6393.319031 +0.293924,1864,6415.541811 +-0.020406,895,6426.525953 +0.10765,1153,6440.377152 +0.495666,1640,6461.296754 +0.35297,1930,6484.101107 +0.431933,2198,6511.040709 +0.356699,1016,6522.26502 +0.504215,1483,6540.31685 +0.586712,1182,6553.973114 +0.377,1270,6569.293019 +0.308,1424,6586.415721 +0.292924,1486,6604.793517 +0.485011,1702,6624.84246 +-0.348,858,6635.431566 +0.172124,1093,6648.010899 +0.538152,1460,6666.13916 +0.592672,917,6677.36776 +-0.049531,1000,6689.960126 +0.211816,1439,6706.920662 +0.461807,1373,6723.593275 +0.150495,1180,6737.497953 +0.485589,1687,6758.106039 +0.133314,1065,6771.852427 +0.363843,2014,6796.250783 +0.530502,1746,6818.192205 +0.167883,1356,6835.387843 +-0.065133,703,6843.539642 +0.316538,1769,6865.45853 +0.131028,1495,6883.804332 +0.094023,914,6894.557262 +-0.152268,921,6905.531969 +0.17223,1332,6921.01201 +0.277863,2699,6953.731201 +0.347876,1749,6975.349043 +0.020855,890,6986.361195 +0.484047,1664,7006.899554 +0.425553,2160,7033.402759 +0.589544,861,7044.111364 +0.043971,785,7053.658856 +-0.025298,691,7061.70513 +0.173515,982,7074.023267 +0.092368,1252,7089.33445 +0.600341,1273,7103.820503 +0.186714,1068,7117.702993 +0.620054,1081,7130.737944 +0.326404,1651,7151.248561 +-0.039282,1314,7167.009431 +0.312404,1477,7185.461264 +0.282984,1954,7209.069284 +0.314098,1339,7225.683064 +0.252876,1381,7242.631175 +-0.130111,823,7252.140748 +0.151692,1420,7268.908735 diff --git a/006_rgb_stack_ram_based_reward_time_reward_final_round/logs/8/monitor.csv b/006_rgb_stack_ram_based_reward_time_reward_final_round/logs/8/monitor.csv new file mode 100644 index 0000000..0e1210d --- /dev/null +++ b/006_rgb_stack_ram_based_reward_time_reward_final_round/logs/8/monitor.csv @@ -0,0 +1,473 @@ +#{"t_start": 1680618620.87198, "env_id": null} +r,l,t +0.172396,1522,23.302892 +0.215157,1729,44.463405 +-0.106133,990,56.595346 +0.239589,1384,71.922024 +0.616802,1088,85.841853 +0.182124,1639,105.860745 +0.372773,1614,124.700379 +0.337773,1712,145.979539 +0.289667,999,158.125559 +0.581522,1312,173.666402 +0.11065,1244,188.797785 +-0.037345,1259,203.183863 +0.168322,1110,216.892252 +0.384908,1783,238.326878 +0.192157,1236,253.379182 +0.254378,1524,272.167841 +0.217157,1155,285.709054 +0.544613,1045,298.049871 +0.014855,1169,312.199704 +0.56377,1324,327.830121 +0.130807,1493,346.136159 +0.235737,1651,366.020851 +0.427182,2137,390.934657 +0.294098,1499,408.908319 +0.079538,1198,422.826653 +-0.011138,919,434.575887 +-0.144121,1374,450.201101 +0.223564,1619,470.236507 +-0.098603,1669,490.373327 +0.230688,2060,515.027316 +0.263965,1088,528.738161 +0.166059,1184,542.741777 +0.348808,1691,562.676038 +-0.349,729,571.627681 +0.49309,1092,584.046355 +0.251965,1876,606.83708 +0.140314,1328,622.51882 +0.039518,954,634.602939 +0.126314,1304,650.385392 +0.145272,1452,667.750824 +0.281984,1593,687.760044 +0.511759,971,699.040199 +0.330661,1511,717.519882 +0.05849,1006,729.725713 +0.634962,1309,745.387799 +0.154322,1818,768.315628 +0.299667,1435,785.29742 +-0.15044,830,794.797752 +0.124057,1247,810.255299 +0.107322,1720,830.838397 +0.574468,1481,849.523733 +0.245488,1574,868.39626 +0.310153,1389,885.334536 +0.760836,701,894.186208 +-0.089675,1029,906.30513 +0.30845,1819,927.653507 +-0.167677,1081,939.982949 +0.238692,1239,955.472685 +0.713327,862,966.057822 +0.060994,1537,984.60916 +0.312495,1738,1005.742515 +0.760115,716,1015.196693 +0.144314,1168,1029.330748 +0.340773,1699,1049.766897 +0.26222,1769,1071.522395 +0.043881,1011,1083.705347 +0.541584,1278,1098.862244 +0.38774,1471,1115.877432 +0.491715,1734,1137.184377 +0.091139,1600,1156.932526 +0.055959,1180,1171.357308 +0.630146,1103,1184.208759 +0.438972,1674,1204.57023 +0.02655,837,1215.514591 +0.219714,1109,1229.151381 +-0.051422,742,1237.264685 +0.063959,1000,1249.668673 +0.35297,2024,1273.968409 +0.084728,977,1286.28121 +0.255589,1400,1303.548777 +0.657817,986,1314.819578 +0.281667,1370,1331.712425 +0.245453,1652,1351.627611 +0.127564,977,1363.878344 +0.263384,1398,1380.020343 +0.166883,1219,1395.622968 +0.238384,1869,1419.457619 +0.125948,1181,1433.50751 +0.2563,1558,1452.138649 +0.476226,1515,1470.652444 +0.242384,2038,1495.294835 +0.271667,1244,1509.449495 +0.292799,1577,1529.380485 +0.501936,1416,1546.992353 +0.259378,1518,1566.679564 +0.109344,1667,1588.251473 +0.078322,1706,1608.251947 +0.266527,1806,1628.681549 +0.221277,1442,1645.000496 +-0.015295,751,1653.993105 +0.622971,1027,1665.608756 +0.258876,1468,1682.891933 +0.639176,1120,1695.869464 +0.149807,1139,1708.70208 +0.343773,1532,1726.34507 +0.195157,892,1736.62307 +0.650528,1214,1750.993565 +0.582229,1287,1766.004038 +0.72207,854,1776.338469 +0.207297,1469,1792.865451 +0.524836,1380,1808.872514 +0.493108,1549,1826.636618 +0.03332,1159,1839.650954 +0.567466,1546,1857.125813 +0.269598,1191,1870.360229 +-0.109489,919,1881.584329 +0.31245,1534,1899.376541 +0.646916,788,1908.454519 +0.17023,1518,1926.040578 +0.245783,1559,1944.095603 +0.208432,1475,1960.532196 +0.26522,1494,1978.375075 +0.017959,1657,1997.969935 +0.282863,1500,2017.792085 +0.248936,1191,2032.799211 +0.304308,1927,2055.315802 +-0.001942,864,2065.40557 +0.44053,1726,2084.261339 +-0.129111,1131,2096.989154 +0.739513,816,2105.970871 +-0.152159,766,2114.511367 +0.248688,1657,2133.335035 +0.460648,2050,2156.257061 +0.277799,1955,2178.442279 +0.132314,1328,2193.003462 +0.288098,1920,2214.246363 +0.055971,1431,2229.962351 +0.670597,870,2239.777361 +0.262453,1343,2255.350852 +0.804379,648,2262.564211 +0.461589,1687,2281.30919 +0.327495,1463,2297.182932 +0.292667,1099,2309.875528 +0.311206,1387,2325.519925 +0.334538,1604,2342.831898 +0.318538,1359,2358.399584 +0.335737,1291,2372.851552 +0.532607,1411,2388.517809 +0.655902,1330,2402.883784 +0.262598,1433,2418.620306 +0.338843,1447,2435.313242 +0.332258,1327,2450.054275 +0.484071,1592,2468.519781 +0.535557,1252,2481.770509 +-0.138121,768,2490.466205 +0.541461,1505,2507.456888 +0.39797,1616,2525.896877 +0.082484,1362,2540.424793 +0.678308,1063,2552.782558 +0.232589,1223,2565.818486 +-0.169677,969,2576.902083 +0.56335,1119,2589.521776 +-0.011623,1063,2601.099671 +0.212014,1247,2615.228793 +-0.040422,860,2624.14683 +0.263,1348,2639.624866 +0.234538,1431,2655.459325 +0.374808,1559,2672.709154 +-0.10633,682,2680.844079 +0.433188,1898,2701.157493 +0.10465,1408,2716.678404 +0.12265,1126,2729.312251 +0.12965,1119,2742.199118 +0.244783,1310,2756.417752 +0.17123,1161,2769.372818 +0.174272,958,2780.526159 +0.628399,1068,2792.072413 +0.343843,1865,2813.579373 +0.030136,1129,2825.334621 +0.205157,1157,2838.189454 +0.354908,1775,2858.254894 +0.682151,944,2869.456588 +0.211816,1192,2882.556012 +0.625168,974,2893.787935 +0.01655,1160,2906.58118 +0.586178,1342,2921.119503 +0.06687,1179,2933.837887 +0.216297,1398,2949.481315 +0.774109,593,2956.434278 +0.01455,1142,2969.130482 +0.336538,1708,2987.821508 +0.239876,1133,3000.721571 +-0.042113,850,3010.60342 +0.459438,1679,3029.533696 +-0.042422,1305,3043.882251 +0.228688,1604,3062.049128 +0.285661,1407,3077.811204 +0.467702,1915,3098.272116 +0.626783,1028,3110.575127 +0.622268,1108,3122.296755 +0.210621,1919,3143.747969 +0.664333,909,3153.860364 +0.685422,1136,3166.762989 +0.32345,1970,3189.676392 +0.437836,1902,3211.102751 +0.523406,1266,3225.849785 +0.31545,1435,3241.97972 +0.173396,1373,3257.990284 +0.330621,1712,3278.097098 +0.199157,1761,3297.861813 +-0.041345,1102,3311.248034 +-0.331,630,3319.015374 +0.488108,1627,3338.910869 +0.315258,1543,3357.60727 +0.444152,2018,3381.116031 +-0.04785,1288,3396.67229 +0.216167,1442,3414.537832 +0.545206,1321,3430.249066 +0.227488,1374,3447.174684 +0.354661,1501,3465.509533 +0.195396,1302,3480.951741 +0.307308,1438,3498.014801 +0.576108,1549,3516.560165 +0.562929,1289,3532.221939 +0.235688,1755,3552.667207 +0.492166,1691,3571.69738 +0.550794,981,3583.19834 +0.153272,1391,3598.906538 +-0.172979,753,3606.595888 +0.640735,1094,3619.204839 +0.352,1252,3633.348503 +0.531878,1585,3650.888337 +-0.20233,1045,3662.484822 +0.347808,1687,3681.082377 +0.222384,1161,3694.875173 +-0.352,626,3701.059359 +0.075421,1139,3713.983417 +0.624623,987,3725.506836 +0.227488,1327,3740.183377 +0.55222,1185,3754.328977 +0.732741,961,3764.829 +0.31958,1767,3784.785966 +0.4028,1753,3804.989965 +-0.121502,1048,3816.556657 +0.427428,1727,3835.453206 +0.34894,1777,3855.332822 +0.541181,1335,3871.034775 +0.54822,1185,3884.01737 +0.294206,1110,3896.75926 +0.189714,1817,3916.919111 +0.550972,1205,3930.024407 +0.01555,1088,3942.664376 +-0.352,480,3947.289597 +0.356843,1091,3959.892842 +0.151124,1131,3972.595017 +0.058421,1079,3984.092317 +0.60689,1218,3997.934518 +-0.039298,659,4005.130514 +-0.009942,982,4016.521376 +0.130238,1429,4032.130841 +0.200564,1392,4047.83495 +-0.027422,646,4054.936151 +0.168701,1395,4070.558639 +0.37797,1440,4086.72369 +-0.050422,1067,4098.333745 +0.31245,1790,4119.228441 +0.280924,1526,4136.436162 +0.086302,1156,4149.740853 +0.168701,932,4160.196851 +0.283984,1611,4178.791054 +-0.040298,968,4190.368719 +0.248053,1541,4207.897536 +0.146711,1042,4219.563843 +-0.157677,875,4229.838642 +0.490745,1695,4248.868936 +0.342621,1419,4265.144296 +0.273453,1643,4283.885913 +0.127057,1409,4299.783131 +0.611146,1103,4311.664804 +0.211692,1382,4327.18371 +0.475016,1438,4343.163805 +0.569522,1312,4358.549224 +0.144564,1086,4370.164369 +0.062421,910,4380.274095 +0.334699,1442,4396.093095 +0.290984,1894,4417.643284 +0.213053,1462,4434.754462 +0.563082,1492,4451.063373 +0.771115,770,4459.642329 +-0.144979,691,4467.95562 +0.366843,1677,4486.62888 +0.346843,1472,4502.659477 +0.177701,1084,4515.364976 +0.065994,954,4525.671387 +0.590724,1023,4537.07248 +0.163515,1268,4551.3118 +0.576766,1359,4566.84164 +0.50209,1092,4578.724882 +0.660879,878,4588.93313 +0.42241,1458,4605.954749 +0.347773,1476,4622.255845 +0.617169,1042,4633.861786 +0.648821,767,4642.830312 +0.164883,1698,4662.645934 +0.610492,998,4673.051497 +0.563364,1369,4688.638286 +0.623979,859,4698.520303 +0.468338,1413,4714.445454 +0.470061,1692,4733.106452 +0.62677,1324,4747.483349 +0.534079,1288,4761.663649 +0.513885,1296,4777.03916 +0.323042,1364,4791.838922 +0.281598,1294,4806.318435 +0.296667,883,4816.502091 +0.606338,1085,4829.040573 +0.477196,1173,4842.124003 +0.311808,1373,4857.756582 +0.297924,1551,4875.086441 +0.847268,546,4880.892138 +0.54241,1458,4897.025957 +-0.35,573,4903.928208 +0.116519,1295,4918.445863 +0.114344,1382,4934.286082 +0.494432,1279,4948.687444 +0.660228,1143,4961.84862 +0.610726,1039,4973.540606 +0.215053,1575,4990.772657 +0.077538,1311,5005.465507 +0.433718,1892,5027.13357 +0.335808,1631,5045.876309 +0.454595,1512,5062.956296 +0.425896,1936,5084.912547 +0.350699,1291,5099.263382 +0.356843,1467,5115.354568 +0.49375,1345,5130.799968 +0.651026,1168,5143.969769 +0.468331,1247,5158.223407 +0.321621,1974,5180.152905 +-0.342,673,5187.397099 +0.596621,1226,5201.680234 +0.197936,1591,5219.533495 +0.338773,1836,5241.019891 +0.272799,1723,5260.111723 +0.065971,731,5268.670165 +0.205557,996,5279.99167 +0.129564,1372,5294.881505 +0.132688,1406,5310.810259 +0.435927,1454,5328.07398 +0.475891,1620,5345.851937 +0.33097,1550,5363.497715 +0.178714,1645,5382.524885 +0.074728,1064,5395.234213 +0.35097,1883,5415.894696 +0.52148,1326,5431.742793 +0.130807,1822,5451.898288 +0.484849,1478,5468.096723 +0.310863,1776,5488.305042 +0.238965,1250,5502.666583 +-0.036295,1034,5514.390511 +0.36794,1595,5533.146094 +0.524597,1389,5549.112147 +0.323206,1452,5565.466294 +0.48138,1466,5581.754152 +0.454806,1577,5600.076176 +0.517071,1430,5616.078887 +0.187714,1284,5630.658033 +0.004139,1027,5642.31416 +0.606265,1241,5656.814892 +0.529465,1347,5671.624127 +0.303357,1455,5688.154113 +0.225589,1565,5706.948527 +0.2543,1563,5724.798665 +-0.237288,741,5733.572307 +0.176557,1176,5746.787208 +0.487355,1041,5758.54437 +0.224866,936,5768.904255 +0.330737,1837,5790.603365 +0.563131,1281,5805.137164 +0.18223,1097,5816.998405 +0.463326,1728,5837.308693 +0.217621,1462,5853.635874 +0.307308,1525,5871.375543 +0.10965,1353,5887.466829 +-0.05906,814,5896.438466 +0.163515,1239,5911.195736 +0.369737,1041,5923.192297 +0.419946,1372,5939.525607 +0.657101,1021,5951.273435 +0.834697,548,5957.28634 +0.054484,1006,5968.836002 +0.288984,1984,5990.954224 +0.174396,1425,6007.25518 +0.606033,1032,6019.278509 +0.308357,1572,6038.81702 +0.544616,1668,6058.787808 +0.498778,1621,6077.455869 +0.339773,2076,6102.773686 +0.595971,975,6113.479903 +0.497927,1454,6131.352545 +0.333773,1945,6154.020424 +0.078139,1046,6166.158253 +-0.121312,993,6177.923434 +0.366,1722,6197.665338 +0.087668,1125,6210.940607 +0.189014,1412,6227.910722 +-0.096603,1566,6246.441458 +0.697971,975,6258.813319 +0.670763,1007,6271.591788 +0.739384,848,6281.502282 +0.488221,1700,6302.822367 +0.185866,1046,6315.593111 +0.583338,1004,6328.060878 +0.094703,1424,6345.504517 +0.135043,1003,6357.724298 +0.545504,1368,6373.312768 +0.152495,1187,6387.30042 +-0.352,740,6396.364987 +0.205432,1340,6413.274777 +0.530031,1533,6431.92835 +0.241783,1606,6451.39042 +0.323042,1499,6470.038024 +-0.053913,733,6478.950414 +-0.129312,858,6488.498443 +0.337808,1622,6508.074202 +0.321621,1549,6526.490683 +0.074139,1295,6541.651359 +0.002402,798,6551.810611 +0.299,1120,6564.543882 +0.350773,1610,6584.358228 +0.308042,1186,6598.562002 +0.340843,1859,6621.116065 +0.358876,1876,6643.179869 +-0.126121,841,6653.545789 +0.249699,891,6664.354559 +0.114519,1230,6678.931521 +0.485688,1403,6696.059886 +0.263598,1763,6717.372557 +0.04349,864,6727.899092 +0.38297,1564,6746.778096 +0.354773,1757,6768.745655 +0.197564,1399,6786.177035 +0.121519,1061,6799.05794 +0.412553,2118,6825.764096 +0.368,2032,6851.011962 +0.13165,1074,6863.738331 +0.306308,1522,6882.116717 +0.126396,1705,6902.433349 +0.186984,964,6914.217441 +0.669845,991,6925.479099 +0.627428,1046,6938.941769 +0.456939,1782,6959.757853 +0.496791,1612,6979.866807 +0.057421,985,6992.470091 +0.153272,1276,7008.109123 +0.123792,1295,7023.752844 +0.191714,1555,7042.530563 +0.199714,1036,7055.201091 +0.109703,1126,7069.193374 +0.659428,988,7081.36042 +0.324661,1342,7097.133245 +-0.198557,686,7105.140692 +0.35094,1381,7122.501989 +-0.118,1568,7141.70102 +0.099023,1066,7155.442092 +0.36597,1885,7178.738757 +0.225816,1565,7197.597085 +0.31045,1788,7219.352615 +0.335737,1389,7236.251952 +0.184866,1369,7252.066943 +0.201701,1177,7265.740589 diff --git a/006_rgb_stack_ram_based_reward_time_reward_final_round/logs/9/monitor.csv b/006_rgb_stack_ram_based_reward_time_reward_final_round/logs/9/monitor.csv new file mode 100644 index 0000000..d5e3a01 --- /dev/null +++ b/006_rgb_stack_ram_based_reward_time_reward_final_round/logs/9/monitor.csv @@ -0,0 +1,480 @@ +#{"t_start": 1680618620.820981, "env_id": null} +r,l,t +-0.125489,747,13.91124 +0.173396,1854,36.791129 +0.151124,1144,50.564244 +0.573957,1493,67.520298 +0.315924,1407,84.524265 +0.351808,1714,105.942747 +-0.030345,857,115.52935 +0.051518,847,126.164596 +0.53223,1475,144.396034 +0.018862,1067,156.894502 +0.103703,1057,169.428163 +0.321621,1607,189.022787 +0.38697,1374,206.005282 +0.288098,1948,228.894122 +-0.030295,990,240.164219 +-0.263034,763,249.220959 +0.587885,1296,266.170997 +-0.337,634,273.73716 +0.011058,1241,287.678539 +0.206432,1560,306.355074 +-0.000357,1080,319.986094 +-0.005138,994,332.118727 +0.348876,1628,351.014479 +0.045737,1311,367.569078 +0.231688,1248,381.891633 +0.270453,1273,396.913733 +0.119948,1428,413.634281 +0.37794,1285,428.885922 +0.111948,1364,445.472295 +0.607783,1028,457.909497 +0.240488,1399,474.859372 +0.166564,915,485.747886 +0.532481,1292,501.36066 +0.167124,1281,516.669691 +0.33845,1355,533.565176 +0.024225,999,545.755367 +0.108948,1222,559.820645 +0.202297,1375,576.326822 +0.495737,874,586.865153 +0.261527,1589,605.400612 +-0.163345,873,616.043563 +0.273598,1082,629.879644 +0.661267,895,640.759166 +0.264453,1852,662.817923 +0.213557,1630,683.076424 +0.554219,1635,702.172059 +0.290667,1521,720.738449 +-0.086274,770,729.921713 +0.581143,949,742.040037 +-0.24335,618,749.754932 +0.062421,1325,765.433249 +0.258053,1200,779.595724 +0.45469,1578,799.281793 +0.189396,1479,816.620529 +0.262527,1571,836.714774 +0.338661,1568,855.738474 +0.285042,1795,877.370825 +0.051437,751,886.681751 +0.066421,1086,899.017877 +0.463103,1516,917.243087 +0.171921,1192,930.925878 +-0.06106,1218,945.842604 +0.129057,1329,961.827129 +0.10465,1619,981.53522 +0.321538,1639,1002.292962 +0.116519,1371,1018.572527 +0.19923,1288,1034.370698 +0.475359,1166,1049.416624 +0.027136,969,1060.438959 +0.153322,1288,1076.219826 +-0.149268,711,1085.144532 +0.478122,1730,1105.074977 +0.265688,1249,1120.154818 +0.350699,1063,1132.700224 +0.311495,2293,1160.477183 +0.699311,585,1168.263886 +0.033136,923,1179.362045 +0.17323,1379,1196.535569 +0.037887,1164,1210.700102 +0.553679,1284,1226.197681 +0.164701,920,1237.126562 +0.153124,1146,1251.080462 +0.341357,1433,1268.03836 +0.44723,1853,1291.102665 +0.527503,1397,1308.195106 +0.638783,1028,1320.796916 +0.198396,1905,1343.669562 +0.492775,1869,1365.780385 +0.261378,1136,1379.821342 +0.270667,1491,1398.952434 +0.31545,1177,1413.360153 +0.697322,1052,1425.982295 +0.299734,1128,1439.752825 +0.35694,1624,1459.652967 +0.445864,1814,1481.346781 +-0.026282,1266,1496.778249 +0.546008,1211,1510.802186 +0.17223,1108,1524.601715 +0.290667,1401,1542.080183 +0.641428,1046,1555.255842 +0.114519,1352,1572.151813 +0.10665,1553,1593.077907 +0.289527,2191,1618.224486 +-0.326,1010,1629.817775 +0.486297,1820,1650.7745 +0.254378,1595,1668.504117 +0.656164,939,1679.831369 +0.021139,1168,1693.01815 +0.150948,1301,1708.419076 +0.253167,1823,1729.17018 +0.025737,1519,1746.728908 +0.469459,1651,1766.013038 +0.234688,1646,1785.40363 +0.526557,1252,1799.911223 +-0.344,478,1804.705565 +0.435904,1762,1825.194301 +0.551595,1480,1842.413961 +0.103023,1179,1855.52687 +-0.048345,1203,1868.915286 +-0.09033,645,1876.103257 +0.683961,940,1887.553612 +0.32445,1350,1902.750084 +0.204816,1664,1921.951267 +-0.169677,656,1929.452143 +0.140272,1184,1943.070465 +0.567562,972,1954.550684 +0.595159,1086,1967.578336 +0.58048,1326,1982.824871 +0.545032,1156,1996.372744 +0.450234,1875,2021.08885 +0.270667,1694,2042.362975 +0.051484,1237,2056.538302 +0.06487,1088,2068.38283 +0.04532,1014,2079.91196 +0.72975,907,2089.954293 +-0.057771,923,2099.983645 +0.020881,825,2109.923454 +0.487801,1560,2127.366833 +0.246688,1116,2140.180788 +0.36097,1606,2157.646799 +0.460887,1638,2175.736696 +0.485625,1360,2191.402722 +0.521766,1359,2205.839351 +0.610946,1372,2221.262258 +0.277783,1856,2241.51682 +0.343876,1599,2259.922529 +0.312258,1363,2275.47795 +0.521543,1434,2291.292148 +0.079538,1007,2302.690022 +-0.160677,772,2311.233703 +0.270965,1191,2324.300037 +0.68037,830,2333.07464 +0.317495,1003,2344.441823 +0.317495,1258,2358.609584 +0.516326,1728,2378.490508 +-0.089708,906,2388.461811 +-0.039345,983,2398.75979 +0.102302,1075,2411.258313 +0.350808,1571,2428.389812 +0.442866,1250,2442.763626 +-0.042345,866,2452.735356 +0.688879,916,2462.920429 +0.382908,1398,2478.592496 +0.037136,903,2488.67055 +0.610572,1008,2500.139138 +0.184866,1031,2511.487851 +0.196322,1061,2523.221279 +0.436801,1685,2541.712619 +0.010402,715,2549.940353 +0.116519,1529,2566.969679 +-0.046422,1120,2578.650423 +0.123057,1210,2592.658698 +-0.346,580,2598.571068 +0.490359,1166,2611.445593 +0.713115,716,2619.796542 +0.136043,1302,2634.10141 +0.588036,1070,2646.690632 +0.12165,1303,2661.098179 +0.532383,1598,2678.394336 +-0.025502,1415,2693.965152 +0.318357,1772,2713.782761 +0.38197,1176,2726.635904 +0.601079,1288,2741.118478 +0.276734,1653,2759.473517 +-0.117489,1191,2773.458508 +0.322621,1913,2794.687546 +0.160322,1585,2812.362984 +0.472023,1655,2830.796757 +0.50423,1475,2846.760504 +0.35894,2113,2871.090607 +0.479301,1590,2888.496988 +-0.037295,1205,2902.418127 +0.278799,1408,2918.025517 +0.318538,2133,2940.970063 +0.454911,1803,2961.033345 +-0.344,443,2966.342762 +0.644086,915,2976.327619 +0.302258,1600,2994.819258 +0.60871,1487,3010.901422 +0.217053,1343,3026.583015 +0.129519,1158,3039.519881 +0.711238,881,3049.413339 +0.783899,506,3055.031155 +-0.115,888,3064.141344 +0.367661,2000,3086.811478 +0.32158,1655,3105.312031 +-0.333,654,3112.413375 +0.367698,1705,3131.02129 +0.684611,798,3140.639639 +0.467613,1735,3159.693681 +0.697181,934,3170.879744 +0.472257,1307,3185.329535 +-0.024422,953,3196.344841 +-0.042345,1439,3212.574292 +0.364699,1532,3230.414393 +0.267589,1153,3243.45133 +0.163314,1015,3255.150229 +0.589407,1030,3266.860985 +-0.344,442,3272.401404 +0.397497,1597,3290.376812 +-0.35,513,3296.440583 +0.118792,1600,3315.88333 +-0.048422,782,3325.352278 +0.270667,1486,3343.623116 +0.127138,1669,3363.766709 +0.621984,1043,3376.213537 +0.425698,1705,3396.537285 +0.464776,1794,3417.837076 +0.462276,1897,3441.003642 +0.133792,1277,3456.508923 +0.343876,1863,3478.296001 +0.307308,1492,3496.60833 +0.10965,1305,3512.099887 +0.328495,1370,3529.098896 +-0.347,698,3537.033598 +0.141495,1530,3554.49722 +0.501758,941,3565.751015 +0.277863,1595,3583.560858 +0.289667,1204,3597.545707 +0.357661,1519,3613.842596 +-0.002623,843,3623.686219 +0.227936,1233,3637.732063 +0.353876,1647,3656.284813 +0.208692,1371,3671.042005 +0.081971,694,3679.276765 +0.281734,1732,3698.150811 +0.262453,1942,3719.934461 +0.038518,810,3729.737544 +0.218866,1281,3744.243645 +0.263138,1385,3760.19068 +0.255965,1086,3771.99095 +0.745661,726,3780.402683 +0.209816,1782,3800.697074 +0.361876,1877,3821.068769 +0.325621,2013,3843.853014 +0.489632,1258,3858.197549 +0.04232,1091,3870.058897 +0.207297,1402,3885.668057 +-0.157268,1111,3898.4651 +0.54519,1010,3909.896876 +0.201157,1450,3925.783291 +0.655189,1274,3940.000441 +-0.067119,746,3948.535028 +0.212053,1379,3964.069202 +-0.141111,839,3972.915021 +0.171921,1157,3985.699526 +0.361843,1471,4002.265873 +0.179059,1387,4018.022734 +0.348538,1568,4035.048367 +0.608046,1329,4049.654143 +0.537031,1174,4063.463549 +0.581855,1060,4075.01607 +0.050484,1236,4088.516821 +0.59957,937,4099.94293 +0.161322,881,4110.182983 +0.199432,1429,4126.363498 +0.267667,1343,4141.027384 +0.66264,722,4149.727853 +0.278667,1642,4168.671201 +0.277924,1593,4186.333681 +0.091538,1156,4199.598362 +0.66564,922,4209.838173 +0.465492,998,4221.343596 +0.440892,1835,4242.934113 +-0.049345,1016,4254.610572 +0.441037,1275,4269.359841 +0.312357,1561,4286.718846 +0.661386,821,4295.74408 +0.117519,1254,4310.076445 +0.279453,1549,4327.179709 +0.635981,1087,4339.870413 +0.344908,1724,4358.792221 +0.562624,1089,4370.394655 +0.330621,1326,4385.839679 +-0.223113,823,4394.668636 +0.533252,1467,4411.632183 +0.346621,2038,4434.784466 +0.289098,1490,4451.087369 +-0.273029,713,4459.42479 +0.050437,1150,4472.340919 +0.748418,812,4481.103673 +0.239965,1890,4502.515168 +0.319661,1695,4521.433394 +0.657794,981,4532.669168 +-0.067307,1104,4544.34706 +0.552698,1381,4560.055457 +0.369843,1486,4577.179613 +0.353808,1046,4588.908127 +0.329098,1405,4604.786748 +0.427528,1159,4617.949273 +0.279924,2175,4642.79628 +0.238432,1589,4660.354193 +0.500742,1410,4676.950871 +0.06249,1449,4692.86192 +0.330495,1579,4710.271813 +-0.165979,756,4719.008388 +0.67609,1092,4731.571342 +0.153043,1160,4744.356627 +0.507213,1769,4763.224887 +0.341876,1892,4784.71332 +0.38694,1734,4804.688559 +0.074139,1188,4817.979172 +0.608736,1297,4832.317007 +0.002229,1000,4843.680432 +0.303357,2236,4869.331269 +0.020225,982,4879.663092 +-0.100674,683,4888.047044 +0.156277,1171,4901.050472 +0.260378,1805,4921.355391 +0.242965,1601,4938.976165 +0.292153,1671,4957.888698 +0.355808,1558,4976.28055 +0.305404,1866,4996.815709 +0.599002,1525,5014.187954 +0.750671,613,5021.352951 +0.332737,1474,5037.54241 +-0.000598,1225,5051.718338 +0.285042,1406,5067.674268 +0.555885,1296,5082.223141 +0.50275,1552,5099.469465 +0.299206,1845,5120.692708 +0.506735,1425,5136.535833 +0.43794,1256,5150.114664 +0.578696,1158,5163.927621 +0.225692,1441,5180.057902 +0.134807,1520,5197.302735 +0.36597,1839,5218.016797 +0.59683,1122,5230.948768 +0.06787,878,5241.03489 +0.607352,968,5251.491529 +0.620794,1128,5264.491527 +0.311495,1560,5281.837031 +0.6762,1155,5294.862505 +0.660426,1196,5308.973192 +0.35194,1510,5325.637649 +0.111368,1075,5338.286309 +0.087668,1550,5356.084811 +0.597264,1197,5369.354034 +0.302153,1510,5386.739716 +0.603734,1388,5402.787124 +0.336737,1981,5424.599228 +0.256453,1540,5442.089227 +0.130314,1397,5457.858448 +0.200432,1219,5472.150734 +0.281863,1174,5485.305684 +0.501108,1822,5505.799871 +-0.118719,923,5516.010877 +0.327661,1806,5537.566486 +-0.036029,1004,5548.200141 +-0.013942,1149,5561.31324 +-0.17535,719,5569.867954 +0.154322,1175,5583.183243 +-0.277416,638,5590.416908 +-0.06285,1166,5603.345881 +0.715257,835,5613.160516 +0.167711,1614,5630.967031 +0.646107,1132,5644.042695 +0.123057,1483,5661.312487 +0.596154,969,5671.807124 +0.274799,1441,5689.217343 +0.331661,2206,5714.531322 +0.116059,1557,5732.312848 +0.311404,1311,5747.044209 +0.537694,1170,5760.297884 +0.719164,645,5767.58593 +0.798401,614,5774.725589 +0.603698,1381,5790.858826 +0.522784,1366,5806.648372 +0.198432,1081,5818.409772 +0.375401,1670,5837.600693 +0.282527,1381,5853.607599 +-0.077913,738,5862.295938 +0.114028,1389,5878.636159 +0.197557,1354,5893.666157 +0.333737,1799,5914.471128 +0.622763,1007,5926.421429 +-0.133312,1341,5942.56376 +0.467205,1179,5955.957608 +0.504547,1537,5973.325759 +0.587325,1334,5988.068171 +0.341773,1579,6006.933177 +0.535966,1509,6024.277776 +0.172396,1482,6042.246458 +0.333538,2382,6070.952747 +0.581868,1424,6087.850027 +0.051971,1279,6102.893193 +0.06687,929,6113.399901 +0.638541,908,6124.003356 +0.132807,1472,6142.057657 +0.260863,2115,6166.285251 +0.334538,1388,6182.578948 +0.684059,1048,6194.639165 +0.677762,1066,6206.79844 +0.35594,1785,6228.192719 +0.508585,1504,6246.454457 +0.214936,1641,6266.939761 +-0.15744,652,6275.018432 +0.200157,1344,6292.213231 +0.179059,1178,6306.165479 +0.632917,911,6317.231305 +0.262527,1853,6339.553693 +0.080139,1069,6353.140004 +-0.328,930,6364.024059 +-0.042282,1380,6380.80812 +0.485469,1427,6397.746279 +0.195432,1490,6415.34881 +0.197564,1128,6429.193975 +0.434468,1481,6447.99579 +0.306098,2226,6474.802272 +0.154921,1001,6486.887684 +0.640807,1373,6503.440043 +0.36897,1509,6521.593019 +0.537033,1032,6533.829602 +0.326699,1822,6555.076189 +0.327699,1540,6573.705403 +0.637196,1173,6587.657421 +0.578557,1252,6603.078999 +0.248688,1590,6621.519066 +0.122057,1521,6639.965294 +-0.098133,886,6650.719494 +-0.083603,1729,6672.084992 +0.191157,1498,6689.986636 +0.360843,1294,6705.330024 +0.000139,1189,6720.368173 +0.494344,1362,6735.87805 +0.610037,1336,6752.949919 +-0.154979,653,6760.927972 +0.449006,1646,6781.360311 +0.219297,1157,6795.790769 +-0.001598,1240,6810.390313 +0.120344,1432,6828.968647 +0.319495,1030,6841.565213 +0.58099,1230,6856.212749 +0.070305,1273,6871.61865 +0.198432,1852,6894.399262 +0.221384,1478,6911.535167 +-0.099603,1046,6924.034951 +0.119014,1288,6940.521145 +0.06587,969,6951.805575 +0.473224,1729,6973.354837 +0.589322,1391,6989.69553 +0.25122,1375,7006.817555 +0.476103,1516,7025.446081 +0.336773,1859,7048.60023 +0.331661,1557,7067.600586 +0.011225,1009,7079.900435 +0.526913,1022,7092.233732 +0.365876,1807,7114.286875 +0.101368,1118,7127.471768 +0.098703,1698,7149.218405 +0.184378,1274,7164.833793 +-0.16735,823,7174.381206 +0.178396,1248,7189.828539 +0.332737,1753,7211.636861 +0.105028,1030,7223.877858 +0.150711,1430,7241.017923 +-0.06906,1100,7253.652762 +0.525736,1297,7268.936737 diff --git a/006_rgb_stack_ram_based_reward_time_reward_final_round/logs/PPO_1/events.out.tfevents.1680618622.DESKTOP-9E17TO7.22700.0 b/006_rgb_stack_ram_based_reward_time_reward_final_round/logs/PPO_1/events.out.tfevents.1680618622.DESKTOP-9E17TO7.22700.0 new file mode 100644 index 0000000..a8b65af Binary files /dev/null and b/006_rgb_stack_ram_based_reward_time_reward_final_round/logs/PPO_1/events.out.tfevents.1680618622.DESKTOP-9E17TO7.22700.0 differ diff --git a/006_rgb_stack_ram_based_reward_time_reward_final_round/logs/PPO_2/events.out.tfevents.1680625957.DESKTOP-9E17TO7.7636.0 b/006_rgb_stack_ram_based_reward_time_reward_final_round/logs/PPO_2/events.out.tfevents.1680625957.DESKTOP-9E17TO7.7636.0 new file mode 100644 index 0000000..15b68d7 Binary files /dev/null and b/006_rgb_stack_ram_based_reward_time_reward_final_round/logs/PPO_2/events.out.tfevents.1680625957.DESKTOP-9E17TO7.7636.0 differ diff --git a/006_rgb_stack_ram_based_reward_time_reward_final_round/logs/PPO_3/events.out.tfevents.1680626065.DESKTOP-9E17TO7.21108.0 b/006_rgb_stack_ram_based_reward_time_reward_final_round/logs/PPO_3/events.out.tfevents.1680626065.DESKTOP-9E17TO7.21108.0 new file mode 100644 index 0000000..cd37dfd Binary files /dev/null and b/006_rgb_stack_ram_based_reward_time_reward_final_round/logs/PPO_3/events.out.tfevents.1680626065.DESKTOP-9E17TO7.21108.0 differ diff --git a/006_rgb_stack_ram_based_reward_time_reward_final_round/logs/PPO_4/events.out.tfevents.1680659644.DESKTOP-9E17TO7.24732.0 b/006_rgb_stack_ram_based_reward_time_reward_final_round/logs/PPO_4/events.out.tfevents.1680659644.DESKTOP-9E17TO7.24732.0 new file mode 100644 index 0000000..cc2d9c0 Binary files /dev/null and b/006_rgb_stack_ram_based_reward_time_reward_final_round/logs/PPO_4/events.out.tfevents.1680659644.DESKTOP-9E17TO7.24732.0 differ diff --git a/006_rgb_stack_ram_based_reward_time_reward_final_round/logs/PPO_5/events.out.tfevents.1680661121.DESKTOP-9E17TO7.9644.0 b/006_rgb_stack_ram_based_reward_time_reward_final_round/logs/PPO_5/events.out.tfevents.1680661121.DESKTOP-9E17TO7.9644.0 new file mode 100644 index 0000000..e5791b9 Binary files /dev/null and b/006_rgb_stack_ram_based_reward_time_reward_final_round/logs/PPO_5/events.out.tfevents.1680661121.DESKTOP-9E17TO7.9644.0 differ diff --git a/006_rgb_stack_ram_based_reward_time_reward_final_round/logs/PPO_6/events.out.tfevents.1680662854.DESKTOP-9E17TO7.14232.0 b/006_rgb_stack_ram_based_reward_time_reward_final_round/logs/PPO_6/events.out.tfevents.1680662854.DESKTOP-9E17TO7.14232.0 new file mode 100644 index 0000000..a1be0da Binary files /dev/null and b/006_rgb_stack_ram_based_reward_time_reward_final_round/logs/PPO_6/events.out.tfevents.1680662854.DESKTOP-9E17TO7.14232.0 differ diff --git a/006_rgb_stack_ram_based_reward_time_reward_final_round/street_fighter_custom_wrapper.py b/006_rgb_stack_ram_based_reward_time_reward_final_round/street_fighter_custom_wrapper.py new file mode 100644 index 0000000..5834c4a --- /dev/null +++ b/006_rgb_stack_ram_based_reward_time_reward_final_round/street_fighter_custom_wrapper.py @@ -0,0 +1,92 @@ +import math +import collections + +import gym +import numpy as np + +# Custom environment wrapper +class StreetFighterCustomWrapper(gym.Wrapper): + def __init__(self, env, testing=False): + super(StreetFighterCustomWrapper, self).__init__(env) + self.env = env + + # Use a deque to store the last 4 frames + self.num_frames = 9 + self.frame_stack = collections.deque(maxlen=self.num_frames) + + self.reward_coeff = 1.0 + + self.total_timesteps = 0 + + self.full_hp = 176 + self.prev_player_health = self.full_hp + self.prev_oppont_health = self.full_hp + + # Update observation space to include stacked grayscale images + self.observation_space = gym.spaces.Box(low=0, high=255, shape=(100, 128, 3), dtype=np.uint8) + + self.testing = testing + + def _preprocess_observation(self, observation): + + # Stack the downsampled frames. + self.frame_stack.append(observation[::2, ::2, :]) + + # Stack the R, G, B channel of each frame and return the "image". + # return np.stack([frame[:, :, i] for i, frame in enumerate(self.frame_stack)], axis=-1) + stacked_image = np.stack([self.frame_stack[i * 3 + 2][:, :, i] for i in range(3)], axis=-1) + return stacked_image + + def reset(self): + observation = self.env.reset() + + self.prev_player_health = self.full_hp + self.prev_oppont_health = self.full_hp + + self.total_timesteps = 0 + + # Clear the frame stack and add the first observation [num_frames] times + self.frame_stack.clear() + for _ in range(self.num_frames): + self.frame_stack.append(observation[::2, ::2, :]) + + # return np.stack([frame[:, :, i] for i, frame in enumerate(self.frame_stack)], axis=-1) + return np.stack([self.frame_stack[i * 3 + 2][:, :, i] for i in range(3)], axis=-1) + + def step(self, action): + + obs, _reward, _done, info = self.env.step(action) + curr_player_health = info['agent_hp'] + curr_oppont_health = info['enemy_hp'] + + self.total_timesteps += 1 + + # Game is over and player loses. + if curr_player_health < 0: + custom_reward = -math.pow(self.full_hp, (curr_oppont_health + 1) / (self.full_hp + 1)) # Use the remaining health points of opponent as penalty. + # If the opponent also has negative health points, it's a even game and the reward is +1. + custom_done = True + + # Game is over and player wins. + elif curr_oppont_health < 0: + # custom_reward = curr_player_health * self.reward_coeff # Use the remaining health points of player as reward. + # Multiply by reward_coeff to make the reward larger than the penalty to avoid cowardice of agent. + + # custom_reward = math.pow(self.full_hp, (5940 - self.total_timesteps) / 5940) * self.reward_coeff # Use the remaining time steps as reward. + custom_reward = math.pow(self.full_hp, (curr_player_health + 1) / (self.full_hp + 1)) * self.reward_coeff + custom_done = True + + # While the fighting is still going on + else: + custom_reward = self.reward_coeff * (self.prev_oppont_health - curr_oppont_health) - (self.prev_player_health - curr_player_health) + self.prev_player_health = curr_player_health + self.prev_oppont_health = curr_oppont_health + custom_done = False + + # During testing, the session should always keep going. + if self.testing: + custom_done = False + + # Max reward is 2 * full_hp = 352 (damage + winning_reward) + return self._preprocess_observation(obs), 0.003 * custom_reward, custom_done, info # reward normalization + \ No newline at end of file diff --git a/006_rgb_stack_ram_based_reward_time_reward_final_round/test.py b/006_rgb_stack_ram_based_reward_time_reward_final_round/test.py new file mode 100644 index 0000000..a0cebcb --- /dev/null +++ b/006_rgb_stack_ram_based_reward_time_reward_final_round/test.py @@ -0,0 +1,61 @@ +import time + +import retro +from stable_baselines3 import PPO + +from street_fighter_custom_wrapper import StreetFighterCustomWrapper + +def make_env(game, state): + def _init(): + env = retro.make( + game=game, + state=state, + use_restricted_actions=retro.Actions.FILTERED, + obs_type=retro.Observations.IMAGE + ) + env = StreetFighterCustomWrapper(env) + return env + return _init + +game = "StreetFighterIISpecialChampionEdition-Genesis" + +env = make_env(game, state="Champion.Level12.RyuVsBison")() + +model = PPO( + "CnnPolicy", + env, + verbose=1 +) +model_path = r"trained_models_ryu_vs_bison_finetune/ppo_ryu_9500000_steps.zip" +model.load(model_path) + +# obs = env.reset() +done = False + +num_episodes = 100 +episode_reward_sum = 0 +num_victory = 0 +for _ in range(num_episodes): + done = False + obs = env.reset() + total_reward = 0 + while not done: + # while True: + timestamp = time.time() + action, _states = model.predict(obs) + obs, reward, done, info = env.step(action) + + if reward != 0: + total_reward += reward + print("Reward: {}, playerHP: {}, enemyHP:{}".format(reward, info['agent_hp'], info['enemy_hp'])) + env.render() + # time.sleep(0.002) + if info['enemy_hp'] < 0: + print("Victory!") + num_victory += 1 + print("Total reward: {}".format(total_reward)) + episode_reward_sum += total_reward + +env.close() +print("Winning rate: {}".format(1.0 * num_victory / num_episodes)) +print("Average reward for {}: {}".format(model_path, episode_reward_sum/num_episodes)) \ No newline at end of file diff --git a/006_rgb_stack_ram_based_reward_time_reward_final_round/train.py b/006_rgb_stack_ram_based_reward_time_reward_final_round/train.py new file mode 100644 index 0000000..fb978dd --- /dev/null +++ b/006_rgb_stack_ram_based_reward_time_reward_final_round/train.py @@ -0,0 +1,116 @@ +import os +import sys + +import retro +from stable_baselines3 import PPO +from stable_baselines3.common.monitor import Monitor +from stable_baselines3.common.callbacks import CheckpointCallback +from stable_baselines3.common.vec_env import DummyVecEnv, SubprocVecEnv + +from street_fighter_custom_wrapper import StreetFighterCustomWrapper + +NUM_ENV = 16 +LOG_DIR = 'logs' +os.makedirs(LOG_DIR, exist_ok=True) + +# Linear scheduler +def linear_schedule(initial_value, final_value=0.0): + + if isinstance(initial_value, str): + initial_value = float(initial_value) + final_value = float(final_value) + assert (initial_value > 0.0) + + def scheduler(progress): + return final_value + progress * (initial_value - final_value) + + return scheduler + +def make_env(game, state, seed=0): + def _init(): + env = retro.make( + game=game, + state=state, + use_restricted_actions=retro.Actions.FILTERED, + obs_type=retro.Observations.IMAGE + ) + env = StreetFighterCustomWrapper(env) + # Create log directory + env_log_dir = os.path.join(LOG_DIR, str(seed+100)) # +100 to avoid conflict with other log dirs when fine-tuning + os.makedirs(env_log_dir, exist_ok=True) + env = Monitor(env, env_log_dir) + env.seed(seed) + return env + return _init + +def main(): + # Set up the environment and model + game = "StreetFighterIISpecialChampionEdition-Genesis" + env = SubprocVecEnv([make_env(game, state="Champion.Level12.RyuVsBison", seed=i) for i in range(NUM_ENV)]) + + # Set linear schedule for learning rate + # Start + lr_schedule = linear_schedule(2.5e-4, 2.5e-6) + + # fine-tune + # lr_schedule = linear_schedule(5.0e-5, 2.5e-6) + + # Set linear scheduler for clip range + # Start + clip_range_schedule = linear_schedule(0.15, 0.025) + + # fine-tune + # clip_range_schedule = linear_schedule(0.075, 0.025) + + model = PPO( + "CnnPolicy", + env, + device="cuda", + verbose=1, + n_steps=128, + batch_size=256, + n_epochs=4, + gamma=0.94, + learning_rate=lr_schedule, + clip_range=clip_range_schedule, + tensorboard_log="logs" + ) + + # Set the save directory + save_dir = "trained_models_ryu_vs_bison_no_coef_no_time_reward_9_frame" + os.makedirs(save_dir, exist_ok=True) + + # Load the model from file + # model_path = "trained_models_ryu_vs_bison_finetune/ppo_ryu_10000000_steps.zip" + + # Load model and modify the learning rate and entropy coefficient + # custom_objects = { + # "learning_rate": lr_schedule, + # "clip_range": clip_range_schedule, + # } + # model = PPO.load(model_path, env=env, device="cuda", custom_objects=custom_objects) + + # Set up callbacks + checkpoint_interval = 31250 # checkpoint_interval * num_envs = total_steps_per_checkpoint + checkpoint_callback = CheckpointCallback(save_freq=checkpoint_interval, save_path=save_dir, name_prefix="ppo_ryu") + + # Writing the training logs from stdout to a file + original_stdout = sys.stdout + log_file_path = os.path.join(save_dir, "training_log.txt") + with open(log_file_path, 'w') as log_file: + sys.stdout = log_file + + model.learn( + total_timesteps=int(100000000), # total_timesteps = stage_interval * num_envs * num_stages (1120 rounds) + callback=[checkpoint_callback]#, stage_increase_callback] + ) + env.close() + + # Restore stdout + sys.stdout = original_stdout + + # Save the final model + model.save(os.path.join(save_dir, "ppo_sf2_ryu_final.zip")) + +if __name__ == "__main__": + main() diff --git a/006_rgb_stack_ram_based_reward_time_reward_final_round/trained_models_ryu_vs_bison/training_log.txt b/006_rgb_stack_ram_based_reward_time_reward_final_round/trained_models_ryu_vs_bison/training_log.txt new file mode 100644 index 0000000..e0d8a6e --- /dev/null +++ b/006_rgb_stack_ram_based_reward_time_reward_final_round/trained_models_ryu_vs_bison/training_log.txt @@ -0,0 +1,102518 @@ +Logging to logs\PPO_1 +----------------------------- +| time/ | | +| fps | 525 | +| iterations | 1 | +| time_elapsed | 3 | +| total_timesteps | 2048 | +----------------------------- +------------------------------------------ +| time/ | | +| fps | 710 | +| iterations | 2 | +| time_elapsed | 5 | +| total_timesteps | 4096 | +| train/ | | +| approx_kl | 0.0023034564 | +| clip_fraction | 0.0139 | +| clip_range | 0.15 | +| entropy_loss | -8.32 | +| explained_variance | -3.77 | +| learning_rate | 0.0002 | +| loss | -0.00986 | +| n_updates | 4 | +| policy_gradient_loss | -0.00231 | +| value_loss | 0.589 | +------------------------------------------ +------------------------------------------ +| time/ | | +| fps | 822 | +| iterations | 3 | +| time_elapsed | 7 | +| total_timesteps | 6144 | +| train/ | | +| approx_kl | 0.0017787362 | +| clip_fraction | 0.00232 | +| clip_range | 0.15 | +| entropy_loss | -8.32 | +| explained_variance | -2.61 | +| learning_rate | 0.0002 | +| loss | -0.00572 | +| n_updates | 8 | +| policy_gradient_loss | -0.00424 | +| value_loss | 0.00148 | +------------------------------------------ +----------------------------------------- +| time/ | | +| fps | 903 | +| iterations | 4 | +| time_elapsed | 9 | +| total_timesteps | 8192 | +| train/ | | +| approx_kl | 0.003459771 | +| clip_fraction | 0.0562 | +| clip_range | 0.15 | +| entropy_loss | -8.31 | +| explained_variance | -2.39 | +| learning_rate | 0.0002 | +| loss | -0.03 | +| n_updates | 12 | +| policy_gradient_loss | -0.0131 | +| value_loss | 0.00133 | +----------------------------------------- +----------------------------------------- +| time/ | | +| fps | 951 | +| iterations | 5 | +| time_elapsed | 10 | +| total_timesteps | 10240 | +| train/ | | +| approx_kl | 0.005811909 | +| clip_fraction | 0.099 | +| clip_range | 0.15 | +| entropy_loss | -8.31 | +| explained_variance | -2.91 | +| learning_rate | 0.0002 | +| loss | -0.0545 | +| n_updates | 16 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.00171 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 747 | +| ep_rew_mean | -0.125 | +| time/ | | +| fps | 992 | +| iterations | 6 | +| time_elapsed | 12 | +| total_timesteps | 12288 | +| train/ | | +| approx_kl | 0.00870607 | +| clip_fraction | 0.148 | +| clip_range | 0.15 | +| entropy_loss | -8.3 | +| explained_variance | -8.86 | +| learning_rate | 0.0002 | +| loss | -0.0509 | +| n_updates | 20 | +| policy_gradient_loss | -0.0291 | +| value_loss | 0.00355 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 772 | +| ep_rew_mean | -0.167 | +| time/ | | +| fps | 1020 | +| iterations | 7 | +| time_elapsed | 14 | +| total_timesteps | 14336 | +| train/ | | +| approx_kl | 0.006628432 | +| clip_fraction | 0.173 | +| clip_range | 0.15 | +| entropy_loss | -8.29 | +| explained_variance | -3.28 | +| learning_rate | 0.0002 | +| loss | -0.0514 | +| n_updates | 24 | +| policy_gradient_loss | -0.0258 | +| value_loss | 0.00442 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 819 | +| ep_rew_mean | -0.113 | +| time/ | | +| fps | 1044 | +| iterations | 8 | +| time_elapsed | 15 | +| total_timesteps | 16384 | +| train/ | | +| approx_kl | 0.009171742 | +| clip_fraction | 0.17 | +| clip_range | 0.15 | +| entropy_loss | -8.29 | +| explained_variance | -4.68 | +| learning_rate | 0.0002 | +| loss | -0.0593 | +| n_updates | 28 | +| policy_gradient_loss | -0.0279 | +| value_loss | 0.0022 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 876 | +| ep_rew_mean | -0.0794 | +| time/ | | +| fps | 1064 | +| iterations | 9 | +| time_elapsed | 17 | +| total_timesteps | 18432 | +| train/ | | +| approx_kl | 0.011487776 | +| clip_fraction | 0.215 | +| clip_range | 0.15 | +| entropy_loss | -8.27 | +| explained_variance | -4.68 | +| learning_rate | 0.0002 | +| loss | -0.065 | +| n_updates | 32 | +| policy_gradient_loss | -0.0322 | +| value_loss | 0.00268 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 944 | +| ep_rew_mean | 0.0242 | +| time/ | | +| fps | 1088 | +| iterations | 10 | +| time_elapsed | 18 | +| total_timesteps | 20480 | +| train/ | | +| approx_kl | 0.011953829 | +| clip_fraction | 0.202 | +| clip_range | 0.15 | +| entropy_loss | -8.27 | +| explained_variance | -4.16 | +| learning_rate | 0.0002 | +| loss | -0.06 | +| n_updates | 36 | +| policy_gradient_loss | -0.0327 | +| value_loss | 0.00239 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.12e+03 | +| ep_rew_mean | 0.168 | +| time/ | | +| fps | 1110 | +| iterations | 11 | +| time_elapsed | 20 | +| total_timesteps | 22528 | +| train/ | | +| approx_kl | 0.013348581 | +| clip_fraction | 0.235 | +| clip_range | 0.15 | +| entropy_loss | -8.26 | +| explained_variance | -4.23 | +| learning_rate | 0.0002 | +| loss | -0.0661 | +| n_updates | 40 | +| policy_gradient_loss | -0.0352 | +| value_loss | 0.00235 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.165 | +| time/ | | +| fps | 1128 | +| iterations | 12 | +| time_elapsed | 21 | +| total_timesteps | 24576 | +| train/ | | +| approx_kl | 0.012902839 | +| clip_fraction | 0.21 | +| clip_range | 0.15 | +| entropy_loss | -8.27 | +| explained_variance | -5.97 | +| learning_rate | 0.0002 | +| loss | -0.0647 | +| n_updates | 44 | +| policy_gradient_loss | -0.0372 | +| value_loss | 0.00228 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.148 | +| time/ | | +| fps | 1141 | +| iterations | 13 | +| time_elapsed | 23 | +| total_timesteps | 26624 | +| train/ | | +| approx_kl | 0.012756407 | +| clip_fraction | 0.242 | +| clip_range | 0.15 | +| entropy_loss | -8.25 | +| explained_variance | -3.42 | +| learning_rate | 0.0002 | +| loss | -0.0731 | +| n_updates | 48 | +| policy_gradient_loss | -0.0389 | +| value_loss | 0.00283 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.185 | +| time/ | | +| fps | 1153 | +| iterations | 14 | +| time_elapsed | 24 | +| total_timesteps | 28672 | +| train/ | | +| approx_kl | 0.014143985 | +| clip_fraction | 0.236 | +| clip_range | 0.15 | +| entropy_loss | -8.26 | +| explained_variance | -4.43 | +| learning_rate | 0.000199 | +| loss | -0.0697 | +| n_updates | 52 | +| policy_gradient_loss | -0.0398 | +| value_loss | 0.00294 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.192 | +| time/ | | +| fps | 1165 | +| iterations | 15 | +| time_elapsed | 26 | +| total_timesteps | 30720 | +| train/ | | +| approx_kl | 0.013052795 | +| clip_fraction | 0.218 | +| clip_range | 0.15 | +| entropy_loss | -8.26 | +| explained_variance | -4.58 | +| learning_rate | 0.000199 | +| loss | -0.0737 | +| n_updates | 56 | +| policy_gradient_loss | -0.037 | +| value_loss | 0.00216 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.219 | +| time/ | | +| fps | 1176 | +| iterations | 16 | +| time_elapsed | 27 | +| total_timesteps | 32768 | +| train/ | | +| approx_kl | 0.014827853 | +| clip_fraction | 0.257 | +| clip_range | 0.15 | +| entropy_loss | -8.24 | +| explained_variance | -6.39 | +| learning_rate | 0.000199 | +| loss | -0.063 | +| n_updates | 60 | +| policy_gradient_loss | -0.0399 | +| value_loss | 0.00222 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.204 | +| time/ | | +| fps | 1184 | +| iterations | 17 | +| time_elapsed | 29 | +| total_timesteps | 34816 | +| train/ | | +| approx_kl | 0.014895564 | +| clip_fraction | 0.245 | +| clip_range | 0.15 | +| entropy_loss | -8.24 | +| explained_variance | -3.57 | +| learning_rate | 0.000199 | +| loss | -0.0749 | +| n_updates | 64 | +| policy_gradient_loss | -0.0368 | +| value_loss | 0.00217 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.177 | +| time/ | | +| fps | 1191 | +| iterations | 18 | +| time_elapsed | 30 | +| total_timesteps | 36864 | +| train/ | | +| approx_kl | 0.015618007 | +| clip_fraction | 0.262 | +| clip_range | 0.15 | +| entropy_loss | -8.24 | +| explained_variance | -5.26 | +| learning_rate | 0.000199 | +| loss | -0.0827 | +| n_updates | 68 | +| policy_gradient_loss | -0.0418 | +| value_loss | 0.00204 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.181 | +| time/ | | +| fps | 1199 | +| iterations | 19 | +| time_elapsed | 32 | +| total_timesteps | 38912 | +| train/ | | +| approx_kl | 0.016106365 | +| clip_fraction | 0.248 | +| clip_range | 0.15 | +| entropy_loss | -8.24 | +| explained_variance | -5.77 | +| learning_rate | 0.000199 | +| loss | -0.0857 | +| n_updates | 72 | +| policy_gradient_loss | -0.0435 | +| value_loss | 0.00216 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.18 | +| time/ | | +| fps | 1206 | +| iterations | 20 | +| time_elapsed | 33 | +| total_timesteps | 40960 | +| train/ | | +| approx_kl | 0.016067507 | +| clip_fraction | 0.28 | +| clip_range | 0.15 | +| entropy_loss | -8.24 | +| explained_variance | -4.73 | +| learning_rate | 0.000199 | +| loss | -0.0777 | +| n_updates | 76 | +| policy_gradient_loss | -0.041 | +| value_loss | 0.00218 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.163 | +| time/ | | +| fps | 1210 | +| iterations | 21 | +| time_elapsed | 35 | +| total_timesteps | 43008 | +| train/ | | +| approx_kl | 0.01869861 | +| clip_fraction | 0.281 | +| clip_range | 0.149 | +| entropy_loss | -8.23 | +| explained_variance | -3.79 | +| learning_rate | 0.000199 | +| loss | -0.0768 | +| n_updates | 80 | +| policy_gradient_loss | -0.0445 | +| value_loss | 0.00226 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.183 | +| time/ | | +| fps | 1215 | +| iterations | 22 | +| time_elapsed | 37 | +| total_timesteps | 45056 | +| train/ | | +| approx_kl | 0.015725356 | +| clip_fraction | 0.262 | +| clip_range | 0.149 | +| entropy_loss | -8.23 | +| explained_variance | -5.87 | +| learning_rate | 0.000199 | +| loss | -0.0687 | +| n_updates | 84 | +| policy_gradient_loss | -0.0397 | +| value_loss | 0.00213 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.183 | +| time/ | | +| fps | 1221 | +| iterations | 23 | +| time_elapsed | 38 | +| total_timesteps | 47104 | +| train/ | | +| approx_kl | 0.01754017 | +| clip_fraction | 0.295 | +| clip_range | 0.149 | +| entropy_loss | -8.23 | +| explained_variance | -3.24 | +| learning_rate | 0.000199 | +| loss | -0.07 | +| n_updates | 88 | +| policy_gradient_loss | -0.0414 | +| value_loss | 0.00199 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.191 | +| time/ | | +| fps | 1224 | +| iterations | 24 | +| time_elapsed | 40 | +| total_timesteps | 49152 | +| train/ | | +| approx_kl | 0.016526088 | +| clip_fraction | 0.276 | +| clip_range | 0.149 | +| entropy_loss | -8.21 | +| explained_variance | -6.18 | +| learning_rate | 0.000199 | +| loss | -0.0748 | +| n_updates | 92 | +| policy_gradient_loss | -0.0404 | +| value_loss | 0.00171 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.195 | +| time/ | | +| fps | 1229 | +| iterations | 25 | +| time_elapsed | 41 | +| total_timesteps | 51200 | +| train/ | | +| approx_kl | 0.015763242 | +| clip_fraction | 0.276 | +| clip_range | 0.149 | +| entropy_loss | -8.18 | +| explained_variance | -3.72 | +| learning_rate | 0.000199 | +| loss | -0.0691 | +| n_updates | 96 | +| policy_gradient_loss | -0.0383 | +| value_loss | 0.00181 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.211 | +| time/ | | +| fps | 1232 | +| iterations | 26 | +| time_elapsed | 43 | +| total_timesteps | 53248 | +| train/ | | +| approx_kl | 0.017452933 | +| clip_fraction | 0.269 | +| clip_range | 0.149 | +| entropy_loss | -8.19 | +| explained_variance | -3.8 | +| learning_rate | 0.000199 | +| loss | -0.0844 | +| n_updates | 100 | +| policy_gradient_loss | -0.0455 | +| value_loss | 0.0017 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.207 | +| time/ | | +| fps | 1235 | +| iterations | 27 | +| time_elapsed | 44 | +| total_timesteps | 55296 | +| train/ | | +| approx_kl | 0.016468365 | +| clip_fraction | 0.273 | +| clip_range | 0.149 | +| entropy_loss | -8.22 | +| explained_variance | -3.24 | +| learning_rate | 0.000199 | +| loss | -0.0793 | +| n_updates | 104 | +| policy_gradient_loss | -0.0415 | +| value_loss | 0.00166 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.207 | +| time/ | | +| fps | 1239 | +| iterations | 28 | +| time_elapsed | 46 | +| total_timesteps | 57344 | +| train/ | | +| approx_kl | 0.017913572 | +| clip_fraction | 0.252 | +| clip_range | 0.149 | +| entropy_loss | -8.21 | +| explained_variance | -4.54 | +| learning_rate | 0.000199 | +| loss | -0.0751 | +| n_updates | 108 | +| policy_gradient_loss | -0.0434 | +| value_loss | 0.00189 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.208 | +| time/ | | +| fps | 1242 | +| iterations | 29 | +| time_elapsed | 47 | +| total_timesteps | 59392 | +| train/ | | +| approx_kl | 0.018923875 | +| clip_fraction | 0.288 | +| clip_range | 0.149 | +| entropy_loss | -8.22 | +| explained_variance | -4.19 | +| learning_rate | 0.000199 | +| loss | -0.0772 | +| n_updates | 112 | +| policy_gradient_loss | -0.0459 | +| value_loss | 0.00171 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.215 | +| time/ | | +| fps | 1244 | +| iterations | 30 | +| time_elapsed | 49 | +| total_timesteps | 61440 | +| train/ | | +| approx_kl | 0.019275615 | +| clip_fraction | 0.306 | +| clip_range | 0.149 | +| entropy_loss | -8.19 | +| explained_variance | -4.07 | +| learning_rate | 0.000199 | +| loss | -0.0827 | +| n_updates | 116 | +| policy_gradient_loss | -0.0445 | +| value_loss | 0.00172 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.215 | +| time/ | | +| fps | 1245 | +| iterations | 31 | +| time_elapsed | 50 | +| total_timesteps | 63488 | +| train/ | | +| approx_kl | 0.018144546 | +| clip_fraction | 0.289 | +| clip_range | 0.149 | +| entropy_loss | -8.19 | +| explained_variance | -4.8 | +| learning_rate | 0.000199 | +| loss | -0.0808 | +| n_updates | 120 | +| policy_gradient_loss | -0.0455 | +| value_loss | 0.00139 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.226 | +| time/ | | +| fps | 1248 | +| iterations | 32 | +| time_elapsed | 52 | +| total_timesteps | 65536 | +| train/ | | +| approx_kl | 0.018547468 | +| clip_fraction | 0.325 | +| clip_range | 0.149 | +| entropy_loss | -8.18 | +| explained_variance | -3.14 | +| learning_rate | 0.000199 | +| loss | -0.0813 | +| n_updates | 124 | +| policy_gradient_loss | -0.0453 | +| value_loss | 0.00158 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.239 | +| time/ | | +| fps | 1251 | +| iterations | 33 | +| time_elapsed | 53 | +| total_timesteps | 67584 | +| train/ | | +| approx_kl | 0.019265447 | +| clip_fraction | 0.309 | +| clip_range | 0.149 | +| entropy_loss | -8.19 | +| explained_variance | -2.87 | +| learning_rate | 0.000199 | +| loss | -0.0769 | +| n_updates | 128 | +| policy_gradient_loss | -0.0463 | +| value_loss | 0.00148 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.234 | +| time/ | | +| fps | 1254 | +| iterations | 34 | +| time_elapsed | 55 | +| total_timesteps | 69632 | +| train/ | | +| approx_kl | 0.018263469 | +| clip_fraction | 0.312 | +| clip_range | 0.149 | +| entropy_loss | -8.18 | +| explained_variance | -2.63 | +| learning_rate | 0.000199 | +| loss | -0.0725 | +| n_updates | 132 | +| policy_gradient_loss | -0.0389 | +| value_loss | 0.00134 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.236 | +| time/ | | +| fps | 1259 | +| iterations | 35 | +| time_elapsed | 56 | +| total_timesteps | 71680 | +| train/ | | +| approx_kl | 0.019021451 | +| clip_fraction | 0.305 | +| clip_range | 0.149 | +| entropy_loss | -8.18 | +| explained_variance | -3.71 | +| learning_rate | 0.000199 | +| loss | -0.0738 | +| n_updates | 136 | +| policy_gradient_loss | -0.043 | +| value_loss | 0.00134 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.231 | +| time/ | | +| fps | 1263 | +| iterations | 36 | +| time_elapsed | 58 | +| total_timesteps | 73728 | +| train/ | | +| approx_kl | 0.022730805 | +| clip_fraction | 0.334 | +| clip_range | 0.149 | +| entropy_loss | -8.19 | +| explained_variance | -5.15 | +| learning_rate | 0.000199 | +| loss | -0.0867 | +| n_updates | 140 | +| policy_gradient_loss | -0.0481 | +| value_loss | 0.00149 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.231 | +| time/ | | +| fps | 1265 | +| iterations | 37 | +| time_elapsed | 59 | +| total_timesteps | 75776 | +| train/ | | +| approx_kl | 0.021697767 | +| clip_fraction | 0.32 | +| clip_range | 0.149 | +| entropy_loss | -8.18 | +| explained_variance | -4.05 | +| learning_rate | 0.000199 | +| loss | -0.09 | +| n_updates | 144 | +| policy_gradient_loss | -0.0457 | +| value_loss | 0.00141 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.231 | +| time/ | | +| fps | 1267 | +| iterations | 38 | +| time_elapsed | 61 | +| total_timesteps | 77824 | +| train/ | | +| approx_kl | 0.023985995 | +| clip_fraction | 0.331 | +| clip_range | 0.149 | +| entropy_loss | -8.18 | +| explained_variance | -3.73 | +| learning_rate | 0.000198 | +| loss | -0.0814 | +| n_updates | 148 | +| policy_gradient_loss | -0.0479 | +| value_loss | 0.00129 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.23 | +| time/ | | +| fps | 1269 | +| iterations | 39 | +| time_elapsed | 62 | +| total_timesteps | 79872 | +| train/ | | +| approx_kl | 0.021651214 | +| clip_fraction | 0.334 | +| clip_range | 0.149 | +| entropy_loss | -8.17 | +| explained_variance | -5.18 | +| learning_rate | 0.000198 | +| loss | -0.0877 | +| n_updates | 152 | +| policy_gradient_loss | -0.0445 | +| value_loss | 0.00129 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.235 | +| time/ | | +| fps | 1271 | +| iterations | 40 | +| time_elapsed | 64 | +| total_timesteps | 81920 | +| train/ | | +| approx_kl | 0.021763973 | +| clip_fraction | 0.341 | +| clip_range | 0.149 | +| entropy_loss | -8.15 | +| explained_variance | -2.92 | +| learning_rate | 0.000198 | +| loss | -0.081 | +| n_updates | 156 | +| policy_gradient_loss | -0.0449 | +| value_loss | 0.00149 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.24 | +| time/ | | +| fps | 1273 | +| iterations | 41 | +| time_elapsed | 65 | +| total_timesteps | 83968 | +| train/ | | +| approx_kl | 0.022051297 | +| clip_fraction | 0.317 | +| clip_range | 0.149 | +| entropy_loss | -8.16 | +| explained_variance | -3.07 | +| learning_rate | 0.000198 | +| loss | -0.0803 | +| n_updates | 160 | +| policy_gradient_loss | -0.0463 | +| value_loss | 0.00144 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.24 | +| time/ | | +| fps | 1277 | +| iterations | 42 | +| time_elapsed | 67 | +| total_timesteps | 86016 | +| train/ | | +| approx_kl | 0.02278192 | +| clip_fraction | 0.334 | +| clip_range | 0.149 | +| entropy_loss | -8.15 | +| explained_variance | -3.71 | +| learning_rate | 0.000198 | +| loss | -0.0889 | +| n_updates | 164 | +| policy_gradient_loss | -0.0467 | +| value_loss | 0.00127 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.243 | +| time/ | | +| fps | 1278 | +| iterations | 43 | +| time_elapsed | 68 | +| total_timesteps | 88064 | +| train/ | | +| approx_kl | 0.02457624 | +| clip_fraction | 0.349 | +| clip_range | 0.149 | +| entropy_loss | -8.14 | +| explained_variance | -4.25 | +| learning_rate | 0.000198 | +| loss | -0.0762 | +| n_updates | 168 | +| policy_gradient_loss | -0.0448 | +| value_loss | 0.00125 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.243 | +| time/ | | +| fps | 1280 | +| iterations | 44 | +| time_elapsed | 70 | +| total_timesteps | 90112 | +| train/ | | +| approx_kl | 0.023369892 | +| clip_fraction | 0.339 | +| clip_range | 0.149 | +| entropy_loss | -8.12 | +| explained_variance | -4.5 | +| learning_rate | 0.000198 | +| loss | -0.076 | +| n_updates | 172 | +| policy_gradient_loss | -0.0473 | +| value_loss | 0.00111 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.249 | +| time/ | | +| fps | 1280 | +| iterations | 45 | +| time_elapsed | 71 | +| total_timesteps | 92160 | +| train/ | | +| approx_kl | 0.0293312 | +| clip_fraction | 0.346 | +| clip_range | 0.149 | +| entropy_loss | -8.11 | +| explained_variance | -4.46 | +| learning_rate | 0.000198 | +| loss | -0.084 | +| n_updates | 176 | +| policy_gradient_loss | -0.0508 | +| value_loss | 0.00133 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.248 | +| time/ | | +| fps | 1281 | +| iterations | 46 | +| time_elapsed | 73 | +| total_timesteps | 94208 | +| train/ | | +| approx_kl | 0.025099806 | +| clip_fraction | 0.353 | +| clip_range | 0.149 | +| entropy_loss | -8.08 | +| explained_variance | -3.14 | +| learning_rate | 0.000198 | +| loss | -0.0707 | +| n_updates | 180 | +| policy_gradient_loss | -0.046 | +| value_loss | 0.00137 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.248 | +| time/ | | +| fps | 1282 | +| iterations | 47 | +| time_elapsed | 75 | +| total_timesteps | 96256 | +| train/ | | +| approx_kl | 0.024417238 | +| clip_fraction | 0.372 | +| clip_range | 0.149 | +| entropy_loss | -8.1 | +| explained_variance | -2.88 | +| learning_rate | 0.000198 | +| loss | -0.0798 | +| n_updates | 184 | +| policy_gradient_loss | -0.0427 | +| value_loss | 0.0014 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.247 | +| time/ | | +| fps | 1283 | +| iterations | 48 | +| time_elapsed | 76 | +| total_timesteps | 98304 | +| train/ | | +| approx_kl | 0.024198793 | +| clip_fraction | 0.334 | +| clip_range | 0.149 | +| entropy_loss | -8.07 | +| explained_variance | -2.58 | +| learning_rate | 0.000198 | +| loss | -0.079 | +| n_updates | 188 | +| policy_gradient_loss | -0.0441 | +| value_loss | 0.00128 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.243 | +| time/ | | +| fps | 1283 | +| iterations | 49 | +| time_elapsed | 78 | +| total_timesteps | 100352 | +| train/ | | +| approx_kl | 0.02514217 | +| clip_fraction | 0.373 | +| clip_range | 0.149 | +| entropy_loss | -8.05 | +| explained_variance | -2.83 | +| learning_rate | 0.000198 | +| loss | -0.0685 | +| n_updates | 192 | +| policy_gradient_loss | -0.0419 | +| value_loss | 0.0014 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.243 | +| time/ | | +| fps | 1282 | +| iterations | 50 | +| time_elapsed | 79 | +| total_timesteps | 102400 | +| train/ | | +| approx_kl | 0.02328499 | +| clip_fraction | 0.352 | +| clip_range | 0.149 | +| entropy_loss | -8.07 | +| explained_variance | -2.73 | +| learning_rate | 0.000198 | +| loss | -0.0709 | +| n_updates | 196 | +| policy_gradient_loss | -0.0465 | +| value_loss | 0.00104 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.245 | +| time/ | | +| fps | 1283 | +| iterations | 51 | +| time_elapsed | 81 | +| total_timesteps | 104448 | +| train/ | | +| approx_kl | 0.028550671 | +| clip_fraction | 0.369 | +| clip_range | 0.149 | +| entropy_loss | -8.07 | +| explained_variance | -3.35 | +| learning_rate | 0.000198 | +| loss | -0.0762 | +| n_updates | 200 | +| policy_gradient_loss | -0.0458 | +| value_loss | 0.00106 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.241 | +| time/ | | +| fps | 1283 | +| iterations | 52 | +| time_elapsed | 82 | +| total_timesteps | 106496 | +| train/ | | +| approx_kl | 0.02634365 | +| clip_fraction | 0.354 | +| clip_range | 0.149 | +| entropy_loss | -8.08 | +| explained_variance | -4.47 | +| learning_rate | 0.000198 | +| loss | -0.0847 | +| n_updates | 204 | +| policy_gradient_loss | -0.0465 | +| value_loss | 0.00105 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.246 | +| time/ | | +| fps | 1283 | +| iterations | 53 | +| time_elapsed | 84 | +| total_timesteps | 108544 | +| train/ | | +| approx_kl | 0.024551589 | +| clip_fraction | 0.344 | +| clip_range | 0.149 | +| entropy_loss | -8.08 | +| explained_variance | -3.72 | +| learning_rate | 0.000198 | +| loss | -0.078 | +| n_updates | 208 | +| policy_gradient_loss | -0.043 | +| value_loss | 0.000852 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.245 | +| time/ | | +| fps | 1283 | +| iterations | 54 | +| time_elapsed | 86 | +| total_timesteps | 110592 | +| train/ | | +| approx_kl | 0.024023306 | +| clip_fraction | 0.341 | +| clip_range | 0.149 | +| entropy_loss | -8.1 | +| explained_variance | -2.28 | +| learning_rate | 0.000198 | +| loss | -0.0751 | +| n_updates | 212 | +| policy_gradient_loss | -0.0421 | +| value_loss | 0.000974 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.249 | +| time/ | | +| fps | 1283 | +| iterations | 55 | +| time_elapsed | 87 | +| total_timesteps | 112640 | +| train/ | | +| approx_kl | 0.024215724 | +| clip_fraction | 0.349 | +| clip_range | 0.149 | +| entropy_loss | -8.1 | +| explained_variance | -3.05 | +| learning_rate | 0.000198 | +| loss | -0.0821 | +| n_updates | 216 | +| policy_gradient_loss | -0.0454 | +| value_loss | 0.0009 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.245 | +| time/ | | +| fps | 1283 | +| iterations | 56 | +| time_elapsed | 89 | +| total_timesteps | 114688 | +| train/ | | +| approx_kl | 0.027463894 | +| clip_fraction | 0.352 | +| clip_range | 0.149 | +| entropy_loss | -8.06 | +| explained_variance | -1.85 | +| learning_rate | 0.000198 | +| loss | -0.0764 | +| n_updates | 220 | +| policy_gradient_loss | -0.0481 | +| value_loss | 0.00098 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.245 | +| time/ | | +| fps | 1284 | +| iterations | 57 | +| time_elapsed | 90 | +| total_timesteps | 116736 | +| train/ | | +| approx_kl | 0.026263863 | +| clip_fraction | 0.37 | +| clip_range | 0.149 | +| entropy_loss | -8.06 | +| explained_variance | -2.86 | +| learning_rate | 0.000198 | +| loss | -0.0854 | +| n_updates | 224 | +| policy_gradient_loss | -0.0494 | +| value_loss | 0.000925 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.246 | +| time/ | | +| fps | 1285 | +| iterations | 58 | +| time_elapsed | 92 | +| total_timesteps | 118784 | +| train/ | | +| approx_kl | 0.025646739 | +| clip_fraction | 0.343 | +| clip_range | 0.149 | +| entropy_loss | -8.05 | +| explained_variance | -2.74 | +| learning_rate | 0.000198 | +| loss | -0.0881 | +| n_updates | 228 | +| policy_gradient_loss | -0.0465 | +| value_loss | 0.00081 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.246 | +| time/ | | +| fps | 1286 | +| iterations | 59 | +| time_elapsed | 93 | +| total_timesteps | 120832 | +| train/ | | +| approx_kl | 0.026193324 | +| clip_fraction | 0.348 | +| clip_range | 0.149 | +| entropy_loss | -8.02 | +| explained_variance | -2.49 | +| learning_rate | 0.000198 | +| loss | -0.0785 | +| n_updates | 232 | +| policy_gradient_loss | -0.0454 | +| value_loss | 0.000907 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.236 | +| time/ | | +| fps | 1287 | +| iterations | 60 | +| time_elapsed | 95 | +| total_timesteps | 122880 | +| train/ | | +| approx_kl | 0.021912325 | +| clip_fraction | 0.343 | +| clip_range | 0.148 | +| entropy_loss | -8.01 | +| explained_variance | -2.94 | +| learning_rate | 0.000198 | +| loss | -0.0814 | +| n_updates | 236 | +| policy_gradient_loss | -0.044 | +| value_loss | 0.000814 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.237 | +| time/ | | +| fps | 1287 | +| iterations | 61 | +| time_elapsed | 97 | +| total_timesteps | 124928 | +| train/ | | +| approx_kl | 0.02107079 | +| clip_fraction | 0.332 | +| clip_range | 0.148 | +| entropy_loss | -8 | +| explained_variance | -1.76 | +| learning_rate | 0.000198 | +| loss | -0.0649 | +| n_updates | 240 | +| policy_gradient_loss | -0.041 | +| value_loss | 0.00085 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.242 | +| time/ | | +| fps | 1288 | +| iterations | 62 | +| time_elapsed | 98 | +| total_timesteps | 126976 | +| train/ | | +| approx_kl | 0.026245618 | +| clip_fraction | 0.374 | +| clip_range | 0.148 | +| entropy_loss | -8.03 | +| explained_variance | -4.65 | +| learning_rate | 0.000198 | +| loss | -0.0814 | +| n_updates | 244 | +| policy_gradient_loss | -0.046 | +| value_loss | 0.000783 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.246 | +| time/ | | +| fps | 1289 | +| iterations | 63 | +| time_elapsed | 100 | +| total_timesteps | 129024 | +| train/ | | +| approx_kl | 0.027412707 | +| clip_fraction | 0.361 | +| clip_range | 0.148 | +| entropy_loss | -8.04 | +| explained_variance | -2.38 | +| learning_rate | 0.000197 | +| loss | -0.0783 | +| n_updates | 248 | +| policy_gradient_loss | -0.047 | +| value_loss | 0.000873 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.251 | +| time/ | | +| fps | 1290 | +| iterations | 64 | +| time_elapsed | 101 | +| total_timesteps | 131072 | +| train/ | | +| approx_kl | 0.028355025 | +| clip_fraction | 0.367 | +| clip_range | 0.148 | +| entropy_loss | -8.02 | +| explained_variance | -1.46 | +| learning_rate | 0.000197 | +| loss | -0.0803 | +| n_updates | 252 | +| policy_gradient_loss | -0.0451 | +| value_loss | 0.000931 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.251 | +| time/ | | +| fps | 1290 | +| iterations | 65 | +| time_elapsed | 103 | +| total_timesteps | 133120 | +| train/ | | +| approx_kl | 0.028502405 | +| clip_fraction | 0.379 | +| clip_range | 0.148 | +| entropy_loss | -7.98 | +| explained_variance | -2.27 | +| learning_rate | 0.000197 | +| loss | -0.0816 | +| n_updates | 256 | +| policy_gradient_loss | -0.0444 | +| value_loss | 0.000951 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.252 | +| time/ | | +| fps | 1291 | +| iterations | 66 | +| time_elapsed | 104 | +| total_timesteps | 135168 | +| train/ | | +| approx_kl | 0.0271139 | +| clip_fraction | 0.373 | +| clip_range | 0.148 | +| entropy_loss | -7.87 | +| explained_variance | -3.54 | +| learning_rate | 0.000197 | +| loss | -0.08 | +| n_updates | 260 | +| policy_gradient_loss | -0.0448 | +| value_loss | 0.000676 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.253 | +| time/ | | +| fps | 1291 | +| iterations | 67 | +| time_elapsed | 106 | +| total_timesteps | 137216 | +| train/ | | +| approx_kl | 0.029537773 | +| clip_fraction | 0.391 | +| clip_range | 0.148 | +| entropy_loss | -7.91 | +| explained_variance | -3.04 | +| learning_rate | 0.000197 | +| loss | -0.0688 | +| n_updates | 264 | +| policy_gradient_loss | -0.0417 | +| value_loss | 0.000752 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.242 | +| time/ | | +| fps | 1291 | +| iterations | 68 | +| time_elapsed | 107 | +| total_timesteps | 139264 | +| train/ | | +| approx_kl | 0.02633812 | +| clip_fraction | 0.372 | +| clip_range | 0.148 | +| entropy_loss | -7.86 | +| explained_variance | -2.8 | +| learning_rate | 0.000197 | +| loss | -0.0768 | +| n_updates | 268 | +| policy_gradient_loss | -0.0454 | +| value_loss | 0.000706 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.242 | +| time/ | | +| fps | 1293 | +| iterations | 69 | +| time_elapsed | 109 | +| total_timesteps | 141312 | +| train/ | | +| approx_kl | 0.025965981 | +| clip_fraction | 0.374 | +| clip_range | 0.148 | +| entropy_loss | -7.75 | +| explained_variance | -2.04 | +| learning_rate | 0.000197 | +| loss | -0.0862 | +| n_updates | 272 | +| policy_gradient_loss | -0.0422 | +| value_loss | 0.000806 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.241 | +| time/ | | +| fps | 1293 | +| iterations | 70 | +| time_elapsed | 110 | +| total_timesteps | 143360 | +| train/ | | +| approx_kl | 0.028686434 | +| clip_fraction | 0.388 | +| clip_range | 0.148 | +| entropy_loss | -7.86 | +| explained_variance | -2.28 | +| learning_rate | 0.000197 | +| loss | -0.0781 | +| n_updates | 276 | +| policy_gradient_loss | -0.0439 | +| value_loss | 0.000661 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.238 | +| time/ | | +| fps | 1293 | +| iterations | 71 | +| time_elapsed | 112 | +| total_timesteps | 145408 | +| train/ | | +| approx_kl | 0.02778894 | +| clip_fraction | 0.373 | +| clip_range | 0.148 | +| entropy_loss | -7.79 | +| explained_variance | -2.46 | +| learning_rate | 0.000197 | +| loss | -0.0812 | +| n_updates | 280 | +| policy_gradient_loss | -0.0459 | +| value_loss | 0.000836 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.241 | +| time/ | | +| fps | 1294 | +| iterations | 72 | +| time_elapsed | 113 | +| total_timesteps | 147456 | +| train/ | | +| approx_kl | 0.027977245 | +| clip_fraction | 0.38 | +| clip_range | 0.148 | +| entropy_loss | -7.82 | +| explained_variance | -4.49 | +| learning_rate | 0.000197 | +| loss | -0.0853 | +| n_updates | 284 | +| policy_gradient_loss | -0.0476 | +| value_loss | 0.000749 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.244 | +| time/ | | +| fps | 1294 | +| iterations | 73 | +| time_elapsed | 115 | +| total_timesteps | 149504 | +| train/ | | +| approx_kl | 0.029430067 | +| clip_fraction | 0.374 | +| clip_range | 0.148 | +| entropy_loss | -7.88 | +| explained_variance | -2.04 | +| learning_rate | 0.000197 | +| loss | -0.0698 | +| n_updates | 288 | +| policy_gradient_loss | -0.0459 | +| value_loss | 0.000729 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.249 | +| time/ | | +| fps | 1295 | +| iterations | 74 | +| time_elapsed | 117 | +| total_timesteps | 151552 | +| train/ | | +| approx_kl | 0.028543912 | +| clip_fraction | 0.353 | +| clip_range | 0.148 | +| entropy_loss | -7.97 | +| explained_variance | -4.23 | +| learning_rate | 0.000197 | +| loss | -0.0905 | +| n_updates | 292 | +| policy_gradient_loss | -0.0505 | +| value_loss | 0.000646 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.244 | +| time/ | | +| fps | 1295 | +| iterations | 75 | +| time_elapsed | 118 | +| total_timesteps | 153600 | +| train/ | | +| approx_kl | 0.02893899 | +| clip_fraction | 0.358 | +| clip_range | 0.148 | +| entropy_loss | -7.94 | +| explained_variance | -1.74 | +| learning_rate | 0.000197 | +| loss | -0.0757 | +| n_updates | 296 | +| policy_gradient_loss | -0.0461 | +| value_loss | 0.000818 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.243 | +| time/ | | +| fps | 1296 | +| iterations | 76 | +| time_elapsed | 120 | +| total_timesteps | 155648 | +| train/ | | +| approx_kl | 0.02626829 | +| clip_fraction | 0.347 | +| clip_range | 0.148 | +| entropy_loss | -7.94 | +| explained_variance | -2.44 | +| learning_rate | 0.000197 | +| loss | -0.0803 | +| n_updates | 300 | +| policy_gradient_loss | -0.0468 | +| value_loss | 0.000642 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.245 | +| time/ | | +| fps | 1296 | +| iterations | 77 | +| time_elapsed | 121 | +| total_timesteps | 157696 | +| train/ | | +| approx_kl | 0.027784385 | +| clip_fraction | 0.344 | +| clip_range | 0.148 | +| entropy_loss | -7.91 | +| explained_variance | -1.64 | +| learning_rate | 0.000197 | +| loss | -0.0879 | +| n_updates | 304 | +| policy_gradient_loss | -0.0465 | +| value_loss | 0.000607 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.253 | +| time/ | | +| fps | 1296 | +| iterations | 78 | +| time_elapsed | 123 | +| total_timesteps | 159744 | +| train/ | | +| approx_kl | 0.02708536 | +| clip_fraction | 0.369 | +| clip_range | 0.148 | +| entropy_loss | -7.99 | +| explained_variance | -1.62 | +| learning_rate | 0.000197 | +| loss | -0.0824 | +| n_updates | 308 | +| policy_gradient_loss | -0.0458 | +| value_loss | 0.000673 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.25 | +| time/ | | +| fps | 1296 | +| iterations | 79 | +| time_elapsed | 124 | +| total_timesteps | 161792 | +| train/ | | +| approx_kl | 0.028601777 | +| clip_fraction | 0.381 | +| clip_range | 0.148 | +| entropy_loss | -7.93 | +| explained_variance | -2.32 | +| learning_rate | 0.000197 | +| loss | -0.0778 | +| n_updates | 312 | +| policy_gradient_loss | -0.0464 | +| value_loss | 0.000625 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.248 | +| time/ | | +| fps | 1297 | +| iterations | 80 | +| time_elapsed | 126 | +| total_timesteps | 163840 | +| train/ | | +| approx_kl | 0.028461121 | +| clip_fraction | 0.387 | +| clip_range | 0.148 | +| entropy_loss | -7.97 | +| explained_variance | -2.92 | +| learning_rate | 0.000197 | +| loss | -0.0787 | +| n_updates | 316 | +| policy_gradient_loss | -0.0469 | +| value_loss | 0.000535 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.248 | +| time/ | | +| fps | 1297 | +| iterations | 81 | +| time_elapsed | 127 | +| total_timesteps | 165888 | +| train/ | | +| approx_kl | 0.02675296 | +| clip_fraction | 0.39 | +| clip_range | 0.148 | +| entropy_loss | -7.94 | +| explained_variance | -2.28 | +| learning_rate | 0.000197 | +| loss | -0.0675 | +| n_updates | 320 | +| policy_gradient_loss | -0.042 | +| value_loss | 0.000563 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.248 | +| time/ | | +| fps | 1297 | +| iterations | 82 | +| time_elapsed | 129 | +| total_timesteps | 167936 | +| train/ | | +| approx_kl | 0.026965816 | +| clip_fraction | 0.339 | +| clip_range | 0.148 | +| entropy_loss | -7.97 | +| explained_variance | -2.41 | +| learning_rate | 0.000197 | +| loss | -0.0871 | +| n_updates | 324 | +| policy_gradient_loss | -0.0492 | +| value_loss | 0.000578 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.238 | +| time/ | | +| fps | 1298 | +| iterations | 83 | +| time_elapsed | 130 | +| total_timesteps | 169984 | +| train/ | | +| approx_kl | 0.027893174 | +| clip_fraction | 0.363 | +| clip_range | 0.148 | +| entropy_loss | -7.97 | +| explained_variance | -2.4 | +| learning_rate | 0.000197 | +| loss | -0.0844 | +| n_updates | 328 | +| policy_gradient_loss | -0.049 | +| value_loss | 0.000562 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.247 | +| time/ | | +| fps | 1298 | +| iterations | 84 | +| time_elapsed | 132 | +| total_timesteps | 172032 | +| train/ | | +| approx_kl | 0.029422872 | +| clip_fraction | 0.36 | +| clip_range | 0.148 | +| entropy_loss | -7.97 | +| explained_variance | -2.39 | +| learning_rate | 0.000197 | +| loss | -0.0909 | +| n_updates | 332 | +| policy_gradient_loss | -0.0516 | +| value_loss | 0.000537 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.251 | +| time/ | | +| fps | 1298 | +| iterations | 85 | +| time_elapsed | 134 | +| total_timesteps | 174080 | +| train/ | | +| approx_kl | 0.028607663 | +| clip_fraction | 0.368 | +| clip_range | 0.148 | +| entropy_loss | -7.92 | +| explained_variance | -1.66 | +| learning_rate | 0.000197 | +| loss | -0.0719 | +| n_updates | 336 | +| policy_gradient_loss | -0.045 | +| value_loss | 0.000571 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.257 | +| time/ | | +| fps | 1299 | +| iterations | 86 | +| time_elapsed | 135 | +| total_timesteps | 176128 | +| train/ | | +| approx_kl | 0.031833068 | +| clip_fraction | 0.372 | +| clip_range | 0.148 | +| entropy_loss | -7.91 | +| explained_variance | -2.91 | +| learning_rate | 0.000197 | +| loss | -0.0906 | +| n_updates | 340 | +| policy_gradient_loss | -0.0523 | +| value_loss | 0.000465 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.257 | +| time/ | | +| fps | 1299 | +| iterations | 87 | +| time_elapsed | 137 | +| total_timesteps | 178176 | +| train/ | | +| approx_kl | 0.030585153 | +| clip_fraction | 0.354 | +| clip_range | 0.148 | +| entropy_loss | -7.9 | +| explained_variance | -1.86 | +| learning_rate | 0.000197 | +| loss | -0.0938 | +| n_updates | 344 | +| policy_gradient_loss | -0.0505 | +| value_loss | 0.000496 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.253 | +| time/ | | +| fps | 1300 | +| iterations | 88 | +| time_elapsed | 138 | +| total_timesteps | 180224 | +| train/ | | +| approx_kl | 0.029565912 | +| clip_fraction | 0.37 | +| clip_range | 0.148 | +| entropy_loss | -7.93 | +| explained_variance | -2.03 | +| learning_rate | 0.000196 | +| loss | -0.0808 | +| n_updates | 348 | +| policy_gradient_loss | -0.0459 | +| value_loss | 0.000512 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.253 | +| time/ | | +| fps | 1300 | +| iterations | 89 | +| time_elapsed | 140 | +| total_timesteps | 182272 | +| train/ | | +| approx_kl | 0.029113472 | +| clip_fraction | 0.385 | +| clip_range | 0.148 | +| entropy_loss | -7.9 | +| explained_variance | -2.37 | +| learning_rate | 0.000196 | +| loss | -0.0793 | +| n_updates | 352 | +| policy_gradient_loss | -0.0481 | +| value_loss | 0.000525 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.248 | +| time/ | | +| fps | 1301 | +| iterations | 90 | +| time_elapsed | 141 | +| total_timesteps | 184320 | +| train/ | | +| approx_kl | 0.026508436 | +| clip_fraction | 0.371 | +| clip_range | 0.148 | +| entropy_loss | -7.86 | +| explained_variance | -3.03 | +| learning_rate | 0.000196 | +| loss | -0.0808 | +| n_updates | 356 | +| policy_gradient_loss | -0.0453 | +| value_loss | 0.000423 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.251 | +| time/ | | +| fps | 1301 | +| iterations | 91 | +| time_elapsed | 143 | +| total_timesteps | 186368 | +| train/ | | +| approx_kl | 0.027255837 | +| clip_fraction | 0.373 | +| clip_range | 0.148 | +| entropy_loss | -7.85 | +| explained_variance | -2.41 | +| learning_rate | 0.000196 | +| loss | -0.0761 | +| n_updates | 360 | +| policy_gradient_loss | -0.0419 | +| value_loss | 0.000409 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.243 | +| time/ | | +| fps | 1301 | +| iterations | 92 | +| time_elapsed | 144 | +| total_timesteps | 188416 | +| train/ | | +| approx_kl | 0.026925068 | +| clip_fraction | 0.375 | +| clip_range | 0.148 | +| entropy_loss | -7.93 | +| explained_variance | -0.992 | +| learning_rate | 0.000196 | +| loss | -0.0688 | +| n_updates | 364 | +| policy_gradient_loss | -0.0407 | +| value_loss | 0.000481 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.243 | +| time/ | | +| fps | 1301 | +| iterations | 93 | +| time_elapsed | 146 | +| total_timesteps | 190464 | +| train/ | | +| approx_kl | 0.028407885 | +| clip_fraction | 0.365 | +| clip_range | 0.148 | +| entropy_loss | -7.87 | +| explained_variance | -2.97 | +| learning_rate | 0.000196 | +| loss | -0.0719 | +| n_updates | 368 | +| policy_gradient_loss | -0.0451 | +| value_loss | 0.000341 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.239 | +| time/ | | +| fps | 1301 | +| iterations | 94 | +| time_elapsed | 147 | +| total_timesteps | 192512 | +| train/ | | +| approx_kl | 0.032619447 | +| clip_fraction | 0.385 | +| clip_range | 0.148 | +| entropy_loss | -7.86 | +| explained_variance | -1.5 | +| learning_rate | 0.000196 | +| loss | -0.0869 | +| n_updates | 372 | +| policy_gradient_loss | -0.047 | +| value_loss | 0.000405 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.239 | +| time/ | | +| fps | 1302 | +| iterations | 95 | +| time_elapsed | 149 | +| total_timesteps | 194560 | +| train/ | | +| approx_kl | 0.026862292 | +| clip_fraction | 0.375 | +| clip_range | 0.148 | +| entropy_loss | -7.85 | +| explained_variance | -1.44 | +| learning_rate | 0.000196 | +| loss | -0.0787 | +| n_updates | 376 | +| policy_gradient_loss | -0.0447 | +| value_loss | 0.000474 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.242 | +| time/ | | +| fps | 1302 | +| iterations | 96 | +| time_elapsed | 150 | +| total_timesteps | 196608 | +| train/ | | +| approx_kl | 0.02667341 | +| clip_fraction | 0.389 | +| clip_range | 0.148 | +| entropy_loss | -7.87 | +| explained_variance | -2.24 | +| learning_rate | 0.000196 | +| loss | -0.0801 | +| n_updates | 380 | +| policy_gradient_loss | -0.0468 | +| value_loss | 0.000396 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.237 | +| time/ | | +| fps | 1303 | +| iterations | 97 | +| time_elapsed | 152 | +| total_timesteps | 198656 | +| train/ | | +| approx_kl | 0.02971786 | +| clip_fraction | 0.366 | +| clip_range | 0.148 | +| entropy_loss | -7.83 | +| explained_variance | -1.97 | +| learning_rate | 0.000196 | +| loss | -0.0733 | +| n_updates | 384 | +| policy_gradient_loss | -0.0421 | +| value_loss | 0.000411 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.226 | +| time/ | | +| fps | 1303 | +| iterations | 98 | +| time_elapsed | 154 | +| total_timesteps | 200704 | +| train/ | | +| approx_kl | 0.03050574 | +| clip_fraction | 0.392 | +| clip_range | 0.148 | +| entropy_loss | -7.84 | +| explained_variance | -1.46 | +| learning_rate | 0.000196 | +| loss | -0.0785 | +| n_updates | 388 | +| policy_gradient_loss | -0.0475 | +| value_loss | 0.000407 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.217 | +| time/ | | +| fps | 1303 | +| iterations | 99 | +| time_elapsed | 155 | +| total_timesteps | 202752 | +| train/ | | +| approx_kl | 0.03028958 | +| clip_fraction | 0.398 | +| clip_range | 0.147 | +| entropy_loss | -7.84 | +| explained_variance | -1.15 | +| learning_rate | 0.000196 | +| loss | -0.0849 | +| n_updates | 392 | +| policy_gradient_loss | -0.0482 | +| value_loss | 0.0004 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.218 | +| time/ | | +| fps | 1303 | +| iterations | 100 | +| time_elapsed | 157 | +| total_timesteps | 204800 | +| train/ | | +| approx_kl | 0.030716313 | +| clip_fraction | 0.375 | +| clip_range | 0.147 | +| entropy_loss | -7.81 | +| explained_variance | -1.28 | +| learning_rate | 0.000196 | +| loss | -0.0678 | +| n_updates | 396 | +| policy_gradient_loss | -0.0439 | +| value_loss | 0.000478 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.218 | +| time/ | | +| fps | 1303 | +| iterations | 101 | +| time_elapsed | 158 | +| total_timesteps | 206848 | +| train/ | | +| approx_kl | 0.02874367 | +| clip_fraction | 0.382 | +| clip_range | 0.147 | +| entropy_loss | -7.89 | +| explained_variance | -0.696 | +| learning_rate | 0.000196 | +| loss | -0.0801 | +| n_updates | 400 | +| policy_gradient_loss | -0.0436 | +| value_loss | 0.000503 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.218 | +| time/ | | +| fps | 1303 | +| iterations | 102 | +| time_elapsed | 160 | +| total_timesteps | 208896 | +| train/ | | +| approx_kl | 0.028564315 | +| clip_fraction | 0.361 | +| clip_range | 0.147 | +| entropy_loss | -7.89 | +| explained_variance | -0.767 | +| learning_rate | 0.000196 | +| loss | -0.0779 | +| n_updates | 404 | +| policy_gradient_loss | -0.0473 | +| value_loss | 0.000503 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.212 | +| time/ | | +| fps | 1303 | +| iterations | 103 | +| time_elapsed | 161 | +| total_timesteps | 210944 | +| train/ | | +| approx_kl | 0.02870024 | +| clip_fraction | 0.384 | +| clip_range | 0.147 | +| entropy_loss | -7.91 | +| explained_variance | -1.38 | +| learning_rate | 0.000196 | +| loss | -0.0827 | +| n_updates | 408 | +| policy_gradient_loss | -0.044 | +| value_loss | 0.000346 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.212 | +| time/ | | +| fps | 1303 | +| iterations | 104 | +| time_elapsed | 163 | +| total_timesteps | 212992 | +| train/ | | +| approx_kl | 0.02733484 | +| clip_fraction | 0.347 | +| clip_range | 0.147 | +| entropy_loss | -7.85 | +| explained_variance | -0.798 | +| learning_rate | 0.000196 | +| loss | -0.0708 | +| n_updates | 412 | +| policy_gradient_loss | -0.0449 | +| value_loss | 0.000375 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.213 | +| time/ | | +| fps | 1304 | +| iterations | 105 | +| time_elapsed | 164 | +| total_timesteps | 215040 | +| train/ | | +| approx_kl | 0.02861998 | +| clip_fraction | 0.361 | +| clip_range | 0.147 | +| entropy_loss | -7.82 | +| explained_variance | -1.58 | +| learning_rate | 0.000196 | +| loss | -0.0702 | +| n_updates | 416 | +| policy_gradient_loss | -0.045 | +| value_loss | 0.000318 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.213 | +| time/ | | +| fps | 1304 | +| iterations | 106 | +| time_elapsed | 166 | +| total_timesteps | 217088 | +| train/ | | +| approx_kl | 0.02735208 | +| clip_fraction | 0.372 | +| clip_range | 0.147 | +| entropy_loss | -7.84 | +| explained_variance | -0.878 | +| learning_rate | 0.000196 | +| loss | -0.0698 | +| n_updates | 420 | +| policy_gradient_loss | -0.0424 | +| value_loss | 0.000353 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.209 | +| time/ | | +| fps | 1304 | +| iterations | 107 | +| time_elapsed | 167 | +| total_timesteps | 219136 | +| train/ | | +| approx_kl | 0.030691441 | +| clip_fraction | 0.368 | +| clip_range | 0.147 | +| entropy_loss | -7.83 | +| explained_variance | -2.05 | +| learning_rate | 0.000196 | +| loss | -0.0858 | +| n_updates | 424 | +| policy_gradient_loss | -0.0528 | +| value_loss | 0.000267 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.209 | +| time/ | | +| fps | 1305 | +| iterations | 108 | +| time_elapsed | 169 | +| total_timesteps | 221184 | +| train/ | | +| approx_kl | 0.028229035 | +| clip_fraction | 0.385 | +| clip_range | 0.147 | +| entropy_loss | -7.8 | +| explained_variance | -0.681 | +| learning_rate | 0.000196 | +| loss | -0.0826 | +| n_updates | 428 | +| policy_gradient_loss | -0.0412 | +| value_loss | 0.000374 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.209 | +| time/ | | +| fps | 1306 | +| iterations | 109 | +| time_elapsed | 170 | +| total_timesteps | 223232 | +| train/ | | +| approx_kl | 0.025877021 | +| clip_fraction | 0.361 | +| clip_range | 0.147 | +| entropy_loss | -7.82 | +| explained_variance | -0.826 | +| learning_rate | 0.000196 | +| loss | -0.0652 | +| n_updates | 432 | +| policy_gradient_loss | -0.0388 | +| value_loss | 0.000428 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.211 | +| time/ | | +| fps | 1306 | +| iterations | 110 | +| time_elapsed | 172 | +| total_timesteps | 225280 | +| train/ | | +| approx_kl | 0.028640274 | +| clip_fraction | 0.377 | +| clip_range | 0.147 | +| entropy_loss | -7.86 | +| explained_variance | -0.927 | +| learning_rate | 0.000196 | +| loss | -0.0798 | +| n_updates | 436 | +| policy_gradient_loss | -0.0437 | +| value_loss | 0.000348 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.212 | +| time/ | | +| fps | 1306 | +| iterations | 111 | +| time_elapsed | 174 | +| total_timesteps | 227328 | +| train/ | | +| approx_kl | 0.029502664 | +| clip_fraction | 0.377 | +| clip_range | 0.147 | +| entropy_loss | -7.87 | +| explained_variance | -0.751 | +| learning_rate | 0.000196 | +| loss | -0.0777 | +| n_updates | 440 | +| policy_gradient_loss | -0.0408 | +| value_loss | 0.000415 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.212 | +| time/ | | +| fps | 1305 | +| iterations | 112 | +| time_elapsed | 175 | +| total_timesteps | 229376 | +| train/ | | +| approx_kl | 0.029755782 | +| clip_fraction | 0.393 | +| clip_range | 0.147 | +| entropy_loss | -7.88 | +| explained_variance | -2.04 | +| learning_rate | 0.000195 | +| loss | -0.0804 | +| n_updates | 444 | +| policy_gradient_loss | -0.0473 | +| value_loss | 0.000291 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.21 | +| time/ | | +| fps | 1306 | +| iterations | 113 | +| time_elapsed | 177 | +| total_timesteps | 231424 | +| train/ | | +| approx_kl | 0.030229509 | +| clip_fraction | 0.362 | +| clip_range | 0.147 | +| entropy_loss | -7.8 | +| explained_variance | -0.749 | +| learning_rate | 0.000195 | +| loss | -0.078 | +| n_updates | 448 | +| policy_gradient_loss | -0.047 | +| value_loss | 0.000301 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.21 | +| time/ | | +| fps | 1306 | +| iterations | 114 | +| time_elapsed | 178 | +| total_timesteps | 233472 | +| train/ | | +| approx_kl | 0.029557193 | +| clip_fraction | 0.373 | +| clip_range | 0.147 | +| entropy_loss | -7.79 | +| explained_variance | -0.878 | +| learning_rate | 0.000195 | +| loss | -0.0733 | +| n_updates | 452 | +| policy_gradient_loss | -0.0444 | +| value_loss | 0.000292 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.212 | +| time/ | | +| fps | 1307 | +| iterations | 115 | +| time_elapsed | 180 | +| total_timesteps | 235520 | +| train/ | | +| approx_kl | 0.032803275 | +| clip_fraction | 0.382 | +| clip_range | 0.147 | +| entropy_loss | -7.77 | +| explained_variance | -0.898 | +| learning_rate | 0.000195 | +| loss | -0.0759 | +| n_updates | 456 | +| policy_gradient_loss | -0.0452 | +| value_loss | 0.000382 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.212 | +| time/ | | +| fps | 1307 | +| iterations | 116 | +| time_elapsed | 181 | +| total_timesteps | 237568 | +| train/ | | +| approx_kl | 0.032863185 | +| clip_fraction | 0.393 | +| clip_range | 0.147 | +| entropy_loss | -7.74 | +| explained_variance | -0.874 | +| learning_rate | 0.000195 | +| loss | -0.0818 | +| n_updates | 460 | +| policy_gradient_loss | -0.0451 | +| value_loss | 0.000301 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.206 | +| time/ | | +| fps | 1307 | +| iterations | 117 | +| time_elapsed | 183 | +| total_timesteps | 239616 | +| train/ | | +| approx_kl | 0.030505981 | +| clip_fraction | 0.392 | +| clip_range | 0.147 | +| entropy_loss | -7.74 | +| explained_variance | -1.89 | +| learning_rate | 0.000195 | +| loss | -0.0754 | +| n_updates | 464 | +| policy_gradient_loss | -0.0458 | +| value_loss | 0.000272 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.207 | +| time/ | | +| fps | 1307 | +| iterations | 118 | +| time_elapsed | 184 | +| total_timesteps | 241664 | +| train/ | | +| approx_kl | 0.033183176 | +| clip_fraction | 0.414 | +| clip_range | 0.147 | +| entropy_loss | -7.71 | +| explained_variance | -1.86 | +| learning_rate | 0.000195 | +| loss | -0.0796 | +| n_updates | 468 | +| policy_gradient_loss | -0.0466 | +| value_loss | 0.000296 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.207 | +| time/ | | +| fps | 1308 | +| iterations | 119 | +| time_elapsed | 186 | +| total_timesteps | 243712 | +| train/ | | +| approx_kl | 0.030834528 | +| clip_fraction | 0.379 | +| clip_range | 0.147 | +| entropy_loss | -7.74 | +| explained_variance | -0.875 | +| learning_rate | 0.000195 | +| loss | -0.0728 | +| n_updates | 472 | +| policy_gradient_loss | -0.044 | +| value_loss | 0.000256 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.207 | +| time/ | | +| fps | 1308 | +| iterations | 120 | +| time_elapsed | 187 | +| total_timesteps | 245760 | +| train/ | | +| approx_kl | 0.032852046 | +| clip_fraction | 0.377 | +| clip_range | 0.147 | +| entropy_loss | -7.76 | +| explained_variance | -1 | +| learning_rate | 0.000195 | +| loss | -0.0815 | +| n_updates | 476 | +| policy_gradient_loss | -0.046 | +| value_loss | 0.0003 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.204 | +| time/ | | +| fps | 1309 | +| iterations | 121 | +| time_elapsed | 189 | +| total_timesteps | 247808 | +| train/ | | +| approx_kl | 0.031040823 | +| clip_fraction | 0.373 | +| clip_range | 0.147 | +| entropy_loss | -7.8 | +| explained_variance | -1.08 | +| learning_rate | 0.000195 | +| loss | -0.0705 | +| n_updates | 480 | +| policy_gradient_loss | -0.0441 | +| value_loss | 0.00027 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.206 | +| time/ | | +| fps | 1309 | +| iterations | 122 | +| time_elapsed | 190 | +| total_timesteps | 249856 | +| train/ | | +| approx_kl | 0.03533555 | +| clip_fraction | 0.369 | +| clip_range | 0.147 | +| entropy_loss | -7.77 | +| explained_variance | -1.11 | +| learning_rate | 0.000195 | +| loss | -0.0762 | +| n_updates | 484 | +| policy_gradient_loss | -0.0427 | +| value_loss | 0.000272 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.209 | +| time/ | | +| fps | 1309 | +| iterations | 123 | +| time_elapsed | 192 | +| total_timesteps | 251904 | +| train/ | | +| approx_kl | 0.03387157 | +| clip_fraction | 0.386 | +| clip_range | 0.147 | +| entropy_loss | -7.74 | +| explained_variance | -1.08 | +| learning_rate | 0.000195 | +| loss | -0.0836 | +| n_updates | 488 | +| policy_gradient_loss | -0.0439 | +| value_loss | 0.000247 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.199 | +| time/ | | +| fps | 1309 | +| iterations | 124 | +| time_elapsed | 193 | +| total_timesteps | 253952 | +| train/ | | +| approx_kl | 0.032717757 | +| clip_fraction | 0.407 | +| clip_range | 0.147 | +| entropy_loss | -7.75 | +| explained_variance | -1.47 | +| learning_rate | 0.000195 | +| loss | -0.0705 | +| n_updates | 492 | +| policy_gradient_loss | -0.0457 | +| value_loss | 0.000202 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.209 | +| time/ | | +| fps | 1309 | +| iterations | 125 | +| time_elapsed | 195 | +| total_timesteps | 256000 | +| train/ | | +| approx_kl | 0.03333991 | +| clip_fraction | 0.386 | +| clip_range | 0.147 | +| entropy_loss | -7.76 | +| explained_variance | -0.559 | +| learning_rate | 0.000195 | +| loss | -0.0732 | +| n_updates | 496 | +| policy_gradient_loss | -0.0414 | +| value_loss | 0.000318 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.21 | +| time/ | | +| fps | 1309 | +| iterations | 126 | +| time_elapsed | 197 | +| total_timesteps | 258048 | +| train/ | | +| approx_kl | 0.034591753 | +| clip_fraction | 0.402 | +| clip_range | 0.147 | +| entropy_loss | -7.76 | +| explained_variance | -0.698 | +| learning_rate | 0.000195 | +| loss | -0.0636 | +| n_updates | 500 | +| policy_gradient_loss | -0.0423 | +| value_loss | 0.000283 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.21 | +| time/ | | +| fps | 1309 | +| iterations | 127 | +| time_elapsed | 198 | +| total_timesteps | 260096 | +| train/ | | +| approx_kl | 0.028530123 | +| clip_fraction | 0.379 | +| clip_range | 0.147 | +| entropy_loss | -7.76 | +| explained_variance | -0.315 | +| learning_rate | 0.000195 | +| loss | -0.0714 | +| n_updates | 504 | +| policy_gradient_loss | -0.0347 | +| value_loss | 0.000273 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.204 | +| time/ | | +| fps | 1309 | +| iterations | 128 | +| time_elapsed | 200 | +| total_timesteps | 262144 | +| train/ | | +| approx_kl | 0.031399965 | +| clip_fraction | 0.387 | +| clip_range | 0.147 | +| entropy_loss | -7.76 | +| explained_variance | -0.552 | +| learning_rate | 0.000195 | +| loss | -0.0686 | +| n_updates | 508 | +| policy_gradient_loss | -0.0408 | +| value_loss | 0.000271 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.202 | +| time/ | | +| fps | 1309 | +| iterations | 129 | +| time_elapsed | 201 | +| total_timesteps | 264192 | +| train/ | | +| approx_kl | 0.030194959 | +| clip_fraction | 0.39 | +| clip_range | 0.147 | +| entropy_loss | -7.79 | +| explained_variance | -0.736 | +| learning_rate | 0.000195 | +| loss | -0.0722 | +| n_updates | 512 | +| policy_gradient_loss | -0.0421 | +| value_loss | 0.000217 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.198 | +| time/ | | +| fps | 1309 | +| iterations | 130 | +| time_elapsed | 203 | +| total_timesteps | 266240 | +| train/ | | +| approx_kl | 0.030800283 | +| clip_fraction | 0.398 | +| clip_range | 0.147 | +| entropy_loss | -7.73 | +| explained_variance | -0.823 | +| learning_rate | 0.000195 | +| loss | -0.0695 | +| n_updates | 516 | +| policy_gradient_loss | -0.038 | +| value_loss | 0.000216 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.2 | +| time/ | | +| fps | 1309 | +| iterations | 131 | +| time_elapsed | 204 | +| total_timesteps | 268288 | +| train/ | | +| approx_kl | 0.030072164 | +| clip_fraction | 0.389 | +| clip_range | 0.147 | +| entropy_loss | -7.76 | +| explained_variance | -0.401 | +| learning_rate | 0.000195 | +| loss | -0.0692 | +| n_updates | 520 | +| policy_gradient_loss | -0.0419 | +| value_loss | 0.00023 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.2 | +| time/ | | +| fps | 1309 | +| iterations | 132 | +| time_elapsed | 206 | +| total_timesteps | 270336 | +| train/ | | +| approx_kl | 0.03130545 | +| clip_fraction | 0.374 | +| clip_range | 0.147 | +| entropy_loss | -7.81 | +| explained_variance | -0.529 | +| learning_rate | 0.000195 | +| loss | -0.0735 | +| n_updates | 524 | +| policy_gradient_loss | -0.0451 | +| value_loss | 0.000283 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.197 | +| time/ | | +| fps | 1309 | +| iterations | 133 | +| time_elapsed | 208 | +| total_timesteps | 272384 | +| train/ | | +| approx_kl | 0.03146836 | +| clip_fraction | 0.388 | +| clip_range | 0.147 | +| entropy_loss | -7.78 | +| explained_variance | -0.572 | +| learning_rate | 0.000195 | +| loss | -0.0693 | +| n_updates | 528 | +| policy_gradient_loss | -0.0382 | +| value_loss | 0.000244 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.213 | +| time/ | | +| fps | 1309 | +| iterations | 134 | +| time_elapsed | 209 | +| total_timesteps | 274432 | +| train/ | | +| approx_kl | 0.026967755 | +| clip_fraction | 0.394 | +| clip_range | 0.147 | +| entropy_loss | -7.71 | +| explained_variance | -0.387 | +| learning_rate | 0.000195 | +| loss | -0.0653 | +| n_updates | 532 | +| policy_gradient_loss | -0.0363 | +| value_loss | 0.00033 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.213 | +| time/ | | +| fps | 1310 | +| iterations | 135 | +| time_elapsed | 211 | +| total_timesteps | 276480 | +| train/ | | +| approx_kl | 0.031982422 | +| clip_fraction | 0.377 | +| clip_range | 0.147 | +| entropy_loss | -7.7 | +| explained_variance | -0.274 | +| learning_rate | 0.000195 | +| loss | -0.0587 | +| n_updates | 536 | +| policy_gradient_loss | -0.0356 | +| value_loss | 0.000338 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.216 | +| time/ | | +| fps | 1310 | +| iterations | 136 | +| time_elapsed | 212 | +| total_timesteps | 278528 | +| train/ | | +| approx_kl | 0.031853467 | +| clip_fraction | 0.397 | +| clip_range | 0.147 | +| entropy_loss | -7.74 | +| explained_variance | -1.03 | +| learning_rate | 0.000195 | +| loss | -0.0757 | +| n_updates | 540 | +| policy_gradient_loss | -0.044 | +| value_loss | 0.000208 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.221 | +| time/ | | +| fps | 1310 | +| iterations | 137 | +| time_elapsed | 214 | +| total_timesteps | 280576 | +| train/ | | +| approx_kl | 0.030523745 | +| clip_fraction | 0.403 | +| clip_range | 0.147 | +| entropy_loss | -7.67 | +| explained_variance | -0.482 | +| learning_rate | 0.000194 | +| loss | -0.0708 | +| n_updates | 544 | +| policy_gradient_loss | -0.0406 | +| value_loss | 0.000276 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.219 | +| time/ | | +| fps | 1311 | +| iterations | 138 | +| time_elapsed | 215 | +| total_timesteps | 282624 | +| train/ | | +| approx_kl | 0.030540958 | +| clip_fraction | 0.388 | +| clip_range | 0.146 | +| entropy_loss | -7.65 | +| explained_variance | -1.28 | +| learning_rate | 0.000194 | +| loss | -0.0724 | +| n_updates | 548 | +| policy_gradient_loss | -0.0439 | +| value_loss | 0.000169 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.218 | +| time/ | | +| fps | 1311 | +| iterations | 139 | +| time_elapsed | 217 | +| total_timesteps | 284672 | +| train/ | | +| approx_kl | 0.03449373 | +| clip_fraction | 0.427 | +| clip_range | 0.146 | +| entropy_loss | -7.74 | +| explained_variance | -0.469 | +| learning_rate | 0.000194 | +| loss | -0.0783 | +| n_updates | 552 | +| policy_gradient_loss | -0.0373 | +| value_loss | 0.000256 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.209 | +| time/ | | +| fps | 1311 | +| iterations | 140 | +| time_elapsed | 218 | +| total_timesteps | 286720 | +| train/ | | +| approx_kl | 0.03180156 | +| clip_fraction | 0.371 | +| clip_range | 0.146 | +| entropy_loss | -7.79 | +| explained_variance | -0.635 | +| learning_rate | 0.000194 | +| loss | -0.0794 | +| n_updates | 556 | +| policy_gradient_loss | -0.0437 | +| value_loss | 0.000214 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.217 | +| time/ | | +| fps | 1311 | +| iterations | 141 | +| time_elapsed | 220 | +| total_timesteps | 288768 | +| train/ | | +| approx_kl | 0.036210373 | +| clip_fraction | 0.387 | +| clip_range | 0.146 | +| entropy_loss | -7.67 | +| explained_variance | -0.856 | +| learning_rate | 0.000194 | +| loss | -0.0786 | +| n_updates | 560 | +| policy_gradient_loss | -0.0471 | +| value_loss | 0.000153 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.217 | +| time/ | | +| fps | 1311 | +| iterations | 142 | +| time_elapsed | 221 | +| total_timesteps | 290816 | +| train/ | | +| approx_kl | 0.035610024 | +| clip_fraction | 0.404 | +| clip_range | 0.146 | +| entropy_loss | -7.66 | +| explained_variance | -1.11 | +| learning_rate | 0.000194 | +| loss | -0.0732 | +| n_updates | 564 | +| policy_gradient_loss | -0.0435 | +| value_loss | 0.000175 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.216 | +| time/ | | +| fps | 1312 | +| iterations | 143 | +| time_elapsed | 223 | +| total_timesteps | 292864 | +| train/ | | +| approx_kl | 0.034133293 | +| clip_fraction | 0.401 | +| clip_range | 0.146 | +| entropy_loss | -7.67 | +| explained_variance | -1.09 | +| learning_rate | 0.000194 | +| loss | -0.0825 | +| n_updates | 568 | +| policy_gradient_loss | -0.0472 | +| value_loss | 0.00016 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.215 | +| time/ | | +| fps | 1312 | +| iterations | 144 | +| time_elapsed | 224 | +| total_timesteps | 294912 | +| train/ | | +| approx_kl | 0.031138647 | +| clip_fraction | 0.388 | +| clip_range | 0.146 | +| entropy_loss | -7.59 | +| explained_variance | -0.241 | +| learning_rate | 0.000194 | +| loss | -0.0624 | +| n_updates | 572 | +| policy_gradient_loss | -0.0351 | +| value_loss | 0.000212 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.205 | +| time/ | | +| fps | 1313 | +| iterations | 145 | +| time_elapsed | 226 | +| total_timesteps | 296960 | +| train/ | | +| approx_kl | 0.029310662 | +| clip_fraction | 0.376 | +| clip_range | 0.146 | +| entropy_loss | -7.71 | +| explained_variance | -0.532 | +| learning_rate | 0.000194 | +| loss | -0.0667 | +| n_updates | 576 | +| policy_gradient_loss | -0.0387 | +| value_loss | 0.000274 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.204 | +| time/ | | +| fps | 1313 | +| iterations | 146 | +| time_elapsed | 227 | +| total_timesteps | 299008 | +| train/ | | +| approx_kl | 0.033321775 | +| clip_fraction | 0.407 | +| clip_range | 0.146 | +| entropy_loss | -7.6 | +| explained_variance | -0.564 | +| learning_rate | 0.000194 | +| loss | -0.0717 | +| n_updates | 580 | +| policy_gradient_loss | -0.043 | +| value_loss | 0.000135 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.204 | +| time/ | | +| fps | 1312 | +| iterations | 147 | +| time_elapsed | 229 | +| total_timesteps | 301056 | +| train/ | | +| approx_kl | 0.032889962 | +| clip_fraction | 0.397 | +| clip_range | 0.146 | +| entropy_loss | -7.56 | +| explained_variance | -0.398 | +| learning_rate | 0.000194 | +| loss | -0.046 | +| n_updates | 584 | +| policy_gradient_loss | -0.0368 | +| value_loss | 0.000205 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.206 | +| time/ | | +| fps | 1313 | +| iterations | 148 | +| time_elapsed | 230 | +| total_timesteps | 303104 | +| train/ | | +| approx_kl | 0.034324326 | +| clip_fraction | 0.396 | +| clip_range | 0.146 | +| entropy_loss | -7.61 | +| explained_variance | -0.317 | +| learning_rate | 0.000194 | +| loss | -0.0771 | +| n_updates | 588 | +| policy_gradient_loss | -0.0409 | +| value_loss | 0.000194 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.206 | +| time/ | | +| fps | 1313 | +| iterations | 149 | +| time_elapsed | 232 | +| total_timesteps | 305152 | +| train/ | | +| approx_kl | 0.03536784 | +| clip_fraction | 0.387 | +| clip_range | 0.146 | +| entropy_loss | -7.63 | +| explained_variance | -0.361 | +| learning_rate | 0.000194 | +| loss | -0.0679 | +| n_updates | 592 | +| policy_gradient_loss | -0.0362 | +| value_loss | 0.000183 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.207 | +| time/ | | +| fps | 1312 | +| iterations | 150 | +| time_elapsed | 233 | +| total_timesteps | 307200 | +| train/ | | +| approx_kl | 0.033618093 | +| clip_fraction | 0.384 | +| clip_range | 0.146 | +| entropy_loss | -7.6 | +| explained_variance | -0.551 | +| learning_rate | 0.000194 | +| loss | -0.0636 | +| n_updates | 596 | +| policy_gradient_loss | -0.0378 | +| value_loss | 0.000212 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.202 | +| time/ | | +| fps | 1313 | +| iterations | 151 | +| time_elapsed | 235 | +| total_timesteps | 309248 | +| train/ | | +| approx_kl | 0.03613372 | +| clip_fraction | 0.394 | +| clip_range | 0.146 | +| entropy_loss | -7.58 | +| explained_variance | -0.708 | +| learning_rate | 0.000194 | +| loss | -0.067 | +| n_updates | 600 | +| policy_gradient_loss | -0.0393 | +| value_loss | 0.000156 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.205 | +| time/ | | +| fps | 1313 | +| iterations | 152 | +| time_elapsed | 237 | +| total_timesteps | 311296 | +| train/ | | +| approx_kl | 0.032482322 | +| clip_fraction | 0.375 | +| clip_range | 0.146 | +| entropy_loss | -7.66 | +| explained_variance | -0.5 | +| learning_rate | 0.000194 | +| loss | -0.0717 | +| n_updates | 604 | +| policy_gradient_loss | -0.0392 | +| value_loss | 0.000217 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.2 | +| time/ | | +| fps | 1313 | +| iterations | 153 | +| time_elapsed | 238 | +| total_timesteps | 313344 | +| train/ | | +| approx_kl | 0.03947894 | +| clip_fraction | 0.41 | +| clip_range | 0.146 | +| entropy_loss | -7.68 | +| explained_variance | -0.642 | +| learning_rate | 0.000194 | +| loss | -0.0784 | +| n_updates | 608 | +| policy_gradient_loss | -0.0427 | +| value_loss | 0.000112 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.2 | +| time/ | | +| fps | 1313 | +| iterations | 154 | +| time_elapsed | 240 | +| total_timesteps | 315392 | +| train/ | | +| approx_kl | 0.034090232 | +| clip_fraction | 0.412 | +| clip_range | 0.146 | +| entropy_loss | -7.57 | +| explained_variance | -0.308 | +| learning_rate | 0.000194 | +| loss | -0.048 | +| n_updates | 612 | +| policy_gradient_loss | -0.036 | +| value_loss | 0.000207 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.195 | +| time/ | | +| fps | 1314 | +| iterations | 155 | +| time_elapsed | 241 | +| total_timesteps | 317440 | +| train/ | | +| approx_kl | 0.034481883 | +| clip_fraction | 0.398 | +| clip_range | 0.146 | +| entropy_loss | -7.62 | +| explained_variance | -0.387 | +| learning_rate | 0.000194 | +| loss | -0.054 | +| n_updates | 616 | +| policy_gradient_loss | -0.0332 | +| value_loss | 0.000212 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.197 | +| time/ | | +| fps | 1314 | +| iterations | 156 | +| time_elapsed | 243 | +| total_timesteps | 319488 | +| train/ | | +| approx_kl | 0.037088525 | +| clip_fraction | 0.416 | +| clip_range | 0.146 | +| entropy_loss | -7.61 | +| explained_variance | -0.692 | +| learning_rate | 0.000194 | +| loss | -0.0769 | +| n_updates | 620 | +| policy_gradient_loss | -0.0418 | +| value_loss | 0.000104 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.203 | +| time/ | | +| fps | 1314 | +| iterations | 157 | +| time_elapsed | 244 | +| total_timesteps | 321536 | +| train/ | | +| approx_kl | 0.039195865 | +| clip_fraction | 0.439 | +| clip_range | 0.146 | +| entropy_loss | -7.58 | +| explained_variance | -0.181 | +| learning_rate | 0.000194 | +| loss | -0.0658 | +| n_updates | 624 | +| policy_gradient_loss | -0.0314 | +| value_loss | 0.000201 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.203 | +| time/ | | +| fps | 1315 | +| iterations | 158 | +| time_elapsed | 246 | +| total_timesteps | 323584 | +| train/ | | +| approx_kl | 0.032833718 | +| clip_fraction | 0.4 | +| clip_range | 0.146 | +| entropy_loss | -7.57 | +| explained_variance | -0.186 | +| learning_rate | 0.000194 | +| loss | -0.0601 | +| n_updates | 628 | +| policy_gradient_loss | -0.031 | +| value_loss | 0.000208 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.202 | +| time/ | | +| fps | 1314 | +| iterations | 159 | +| time_elapsed | 247 | +| total_timesteps | 325632 | +| train/ | | +| approx_kl | 0.03454147 | +| clip_fraction | 0.379 | +| clip_range | 0.146 | +| entropy_loss | -7.63 | +| explained_variance | -0.496 | +| learning_rate | 0.000194 | +| loss | -0.069 | +| n_updates | 632 | +| policy_gradient_loss | -0.0345 | +| value_loss | 0.000141 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.197 | +| time/ | | +| fps | 1314 | +| iterations | 160 | +| time_elapsed | 249 | +| total_timesteps | 327680 | +| train/ | | +| approx_kl | 0.034945004 | +| clip_fraction | 0.398 | +| clip_range | 0.146 | +| entropy_loss | -7.51 | +| explained_variance | -0.154 | +| learning_rate | 0.000194 | +| loss | -0.0689 | +| n_updates | 636 | +| policy_gradient_loss | -0.0352 | +| value_loss | 0.000194 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.195 | +| time/ | | +| fps | 1314 | +| iterations | 161 | +| time_elapsed | 250 | +| total_timesteps | 329728 | +| train/ | | +| approx_kl | 0.039453335 | +| clip_fraction | 0.404 | +| clip_range | 0.146 | +| entropy_loss | -7.47 | +| explained_variance | -0.246 | +| learning_rate | 0.000194 | +| loss | -0.0565 | +| n_updates | 640 | +| policy_gradient_loss | -0.0343 | +| value_loss | 0.000163 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.195 | +| time/ | | +| fps | 1315 | +| iterations | 162 | +| time_elapsed | 252 | +| total_timesteps | 331776 | +| train/ | | +| approx_kl | 0.038238816 | +| clip_fraction | 0.4 | +| clip_range | 0.146 | +| entropy_loss | -7.4 | +| explained_variance | -0.199 | +| learning_rate | 0.000193 | +| loss | -0.0555 | +| n_updates | 644 | +| policy_gradient_loss | -0.0346 | +| value_loss | 0.000124 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.202 | +| time/ | | +| fps | 1314 | +| iterations | 163 | +| time_elapsed | 253 | +| total_timesteps | 333824 | +| train/ | | +| approx_kl | 0.032607995 | +| clip_fraction | 0.389 | +| clip_range | 0.146 | +| entropy_loss | -7.45 | +| explained_variance | -0.358 | +| learning_rate | 0.000193 | +| loss | -0.0547 | +| n_updates | 648 | +| policy_gradient_loss | -0.0345 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.207 | +| time/ | | +| fps | 1314 | +| iterations | 164 | +| time_elapsed | 255 | +| total_timesteps | 335872 | +| train/ | | +| approx_kl | 0.031956077 | +| clip_fraction | 0.373 | +| clip_range | 0.146 | +| entropy_loss | -7.57 | +| explained_variance | -0.0795 | +| learning_rate | 0.000193 | +| loss | -0.0694 | +| n_updates | 652 | +| policy_gradient_loss | -0.0339 | +| value_loss | 0.00034 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.209 | +| time/ | | +| fps | 1314 | +| iterations | 165 | +| time_elapsed | 257 | +| total_timesteps | 337920 | +| train/ | | +| approx_kl | 0.03075451 | +| clip_fraction | 0.35 | +| clip_range | 0.146 | +| entropy_loss | -7.53 | +| explained_variance | -0.134 | +| learning_rate | 0.000193 | +| loss | -0.067 | +| n_updates | 656 | +| policy_gradient_loss | -0.0386 | +| value_loss | 0.000181 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.209 | +| time/ | | +| fps | 1314 | +| iterations | 166 | +| time_elapsed | 258 | +| total_timesteps | 339968 | +| train/ | | +| approx_kl | 0.03061781 | +| clip_fraction | 0.362 | +| clip_range | 0.146 | +| entropy_loss | -7.52 | +| explained_variance | -0.354 | +| learning_rate | 0.000193 | +| loss | -0.066 | +| n_updates | 660 | +| policy_gradient_loss | -0.0323 | +| value_loss | 0.000164 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.214 | +| time/ | | +| fps | 1314 | +| iterations | 167 | +| time_elapsed | 260 | +| total_timesteps | 342016 | +| train/ | | +| approx_kl | 0.03532315 | +| clip_fraction | 0.373 | +| clip_range | 0.146 | +| entropy_loss | -7.55 | +| explained_variance | -0.0803 | +| learning_rate | 0.000193 | +| loss | -0.0664 | +| n_updates | 664 | +| policy_gradient_loss | -0.0382 | +| value_loss | 0.000217 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.211 | +| time/ | | +| fps | 1313 | +| iterations | 168 | +| time_elapsed | 261 | +| total_timesteps | 344064 | +| train/ | | +| approx_kl | 0.03295938 | +| clip_fraction | 0.361 | +| clip_range | 0.146 | +| entropy_loss | -7.55 | +| explained_variance | -0.0847 | +| learning_rate | 0.000193 | +| loss | -0.0513 | +| n_updates | 668 | +| policy_gradient_loss | -0.0332 | +| value_loss | 0.00029 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.215 | +| time/ | | +| fps | 1313 | +| iterations | 169 | +| time_elapsed | 263 | +| total_timesteps | 346112 | +| train/ | | +| approx_kl | 0.031234117 | +| clip_fraction | 0.396 | +| clip_range | 0.146 | +| entropy_loss | -7.53 | +| explained_variance | -0.664 | +| learning_rate | 0.000193 | +| loss | -0.0557 | +| n_updates | 672 | +| policy_gradient_loss | -0.0357 | +| value_loss | 0.000123 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.221 | +| time/ | | +| fps | 1313 | +| iterations | 170 | +| time_elapsed | 265 | +| total_timesteps | 348160 | +| train/ | | +| approx_kl | 0.030360378 | +| clip_fraction | 0.331 | +| clip_range | 0.146 | +| entropy_loss | -7.49 | +| explained_variance | -0.285 | +| learning_rate | 0.000193 | +| loss | -0.0566 | +| n_updates | 676 | +| policy_gradient_loss | -0.0315 | +| value_loss | 0.000215 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.221 | +| time/ | | +| fps | 1313 | +| iterations | 171 | +| time_elapsed | 266 | +| total_timesteps | 350208 | +| train/ | | +| approx_kl | 0.03398284 | +| clip_fraction | 0.376 | +| clip_range | 0.146 | +| entropy_loss | -7.53 | +| explained_variance | -0.32 | +| learning_rate | 0.000193 | +| loss | -0.0655 | +| n_updates | 680 | +| policy_gradient_loss | -0.0356 | +| value_loss | 0.0002 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.22 | +| time/ | | +| fps | 1313 | +| iterations | 172 | +| time_elapsed | 268 | +| total_timesteps | 352256 | +| train/ | | +| approx_kl | 0.033337273 | +| clip_fraction | 0.368 | +| clip_range | 0.146 | +| entropy_loss | -7.54 | +| explained_variance | -0.747 | +| learning_rate | 0.000193 | +| loss | -0.0805 | +| n_updates | 684 | +| policy_gradient_loss | -0.043 | +| value_loss | 8.53e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.216 | +| time/ | | +| fps | 1314 | +| iterations | 173 | +| time_elapsed | 269 | +| total_timesteps | 354304 | +| train/ | | +| approx_kl | 0.03326168 | +| clip_fraction | 0.373 | +| clip_range | 0.146 | +| entropy_loss | -7.54 | +| explained_variance | -0.226 | +| learning_rate | 0.000193 | +| loss | -0.0649 | +| n_updates | 688 | +| policy_gradient_loss | -0.0375 | +| value_loss | 0.000131 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.218 | +| time/ | | +| fps | 1314 | +| iterations | 174 | +| time_elapsed | 271 | +| total_timesteps | 356352 | +| train/ | | +| approx_kl | 0.035040773 | +| clip_fraction | 0.378 | +| clip_range | 0.146 | +| entropy_loss | -7.54 | +| explained_variance | -0.141 | +| learning_rate | 0.000193 | +| loss | -0.0574 | +| n_updates | 692 | +| policy_gradient_loss | -0.0303 | +| value_loss | 0.000137 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.205 | +| time/ | | +| fps | 1314 | +| iterations | 175 | +| time_elapsed | 272 | +| total_timesteps | 358400 | +| train/ | | +| approx_kl | 0.030477164 | +| clip_fraction | 0.358 | +| clip_range | 0.146 | +| entropy_loss | -7.5 | +| explained_variance | -0.269 | +| learning_rate | 0.000193 | +| loss | -0.0519 | +| n_updates | 696 | +| policy_gradient_loss | -0.034 | +| value_loss | 0.000197 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.205 | +| time/ | | +| fps | 1314 | +| iterations | 176 | +| time_elapsed | 274 | +| total_timesteps | 360448 | +| train/ | | +| approx_kl | 0.031965666 | +| clip_fraction | 0.379 | +| clip_range | 0.146 | +| entropy_loss | -7.38 | +| explained_variance | -0.235 | +| learning_rate | 0.000193 | +| loss | -0.0614 | +| n_updates | 700 | +| policy_gradient_loss | -0.0339 | +| value_loss | 0.000157 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.205 | +| time/ | | +| fps | 1315 | +| iterations | 177 | +| time_elapsed | 275 | +| total_timesteps | 362496 | +| train/ | | +| approx_kl | 0.032165095 | +| clip_fraction | 0.395 | +| clip_range | 0.145 | +| entropy_loss | -7.38 | +| explained_variance | -0.141 | +| learning_rate | 0.000193 | +| loss | -0.0559 | +| n_updates | 704 | +| policy_gradient_loss | -0.0295 | +| value_loss | 0.000144 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.205 | +| time/ | | +| fps | 1315 | +| iterations | 178 | +| time_elapsed | 277 | +| total_timesteps | 364544 | +| train/ | | +| approx_kl | 0.040031616 | +| clip_fraction | 0.417 | +| clip_range | 0.145 | +| entropy_loss | -7.34 | +| explained_variance | -0.0111 | +| learning_rate | 0.000193 | +| loss | -0.0579 | +| n_updates | 708 | +| policy_gradient_loss | -0.0314 | +| value_loss | 0.000187 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.212 | +| time/ | | +| fps | 1316 | +| iterations | 179 | +| time_elapsed | 278 | +| total_timesteps | 366592 | +| train/ | | +| approx_kl | 0.03322337 | +| clip_fraction | 0.411 | +| clip_range | 0.145 | +| entropy_loss | -7.31 | +| explained_variance | -0.0307 | +| learning_rate | 0.000193 | +| loss | -0.058 | +| n_updates | 712 | +| policy_gradient_loss | -0.032 | +| value_loss | 0.000168 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.213 | +| time/ | | +| fps | 1316 | +| iterations | 180 | +| time_elapsed | 280 | +| total_timesteps | 368640 | +| train/ | | +| approx_kl | 0.029856613 | +| clip_fraction | 0.349 | +| clip_range | 0.145 | +| entropy_loss | -7.26 | +| explained_variance | -0.102 | +| learning_rate | 0.000193 | +| loss | -0.0534 | +| n_updates | 716 | +| policy_gradient_loss | -0.0305 | +| value_loss | 0.000192 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.212 | +| time/ | | +| fps | 1316 | +| iterations | 181 | +| time_elapsed | 281 | +| total_timesteps | 370688 | +| train/ | | +| approx_kl | 0.03328598 | +| clip_fraction | 0.367 | +| clip_range | 0.145 | +| entropy_loss | -7.29 | +| explained_variance | -0.171 | +| learning_rate | 0.000193 | +| loss | -0.0651 | +| n_updates | 720 | +| policy_gradient_loss | -0.033 | +| value_loss | 0.000176 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.216 | +| time/ | | +| fps | 1316 | +| iterations | 182 | +| time_elapsed | 283 | +| total_timesteps | 372736 | +| train/ | | +| approx_kl | 0.03782944 | +| clip_fraction | 0.372 | +| clip_range | 0.145 | +| entropy_loss | -7.35 | +| explained_variance | -0.276 | +| learning_rate | 0.000193 | +| loss | -0.071 | +| n_updates | 724 | +| policy_gradient_loss | -0.0347 | +| value_loss | 0.000128 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.216 | +| time/ | | +| fps | 1316 | +| iterations | 183 | +| time_elapsed | 284 | +| total_timesteps | 374784 | +| train/ | | +| approx_kl | 0.03632043 | +| clip_fraction | 0.397 | +| clip_range | 0.145 | +| entropy_loss | -7.37 | +| explained_variance | -0.0738 | +| learning_rate | 0.000193 | +| loss | -0.0494 | +| n_updates | 728 | +| policy_gradient_loss | -0.0278 | +| value_loss | 0.000217 | +---------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.212 | +| time/ | | +| fps | 1316 | +| iterations | 184 | +| time_elapsed | 286 | +| total_timesteps | 376832 | +| train/ | | +| approx_kl | 0.0302343 | +| clip_fraction | 0.395 | +| clip_range | 0.145 | +| entropy_loss | -7.45 | +| explained_variance | 0.139 | +| learning_rate | 0.000193 | +| loss | -0.0506 | +| n_updates | 732 | +| policy_gradient_loss | -0.0243 | +| value_loss | 0.000231 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.215 | +| time/ | | +| fps | 1316 | +| iterations | 185 | +| time_elapsed | 287 | +| total_timesteps | 378880 | +| train/ | | +| approx_kl | 0.026567416 | +| clip_fraction | 0.362 | +| clip_range | 0.145 | +| entropy_loss | -7.45 | +| explained_variance | -0.0435 | +| learning_rate | 0.000193 | +| loss | -0.0578 | +| n_updates | 736 | +| policy_gradient_loss | -0.0294 | +| value_loss | 0.000143 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.217 | +| time/ | | +| fps | 1317 | +| iterations | 186 | +| time_elapsed | 289 | +| total_timesteps | 380928 | +| train/ | | +| approx_kl | 0.030720811 | +| clip_fraction | 0.359 | +| clip_range | 0.145 | +| entropy_loss | -7.46 | +| explained_variance | -0.14 | +| learning_rate | 0.000192 | +| loss | -0.0538 | +| n_updates | 740 | +| policy_gradient_loss | -0.0291 | +| value_loss | 0.000311 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.222 | +| time/ | | +| fps | 1317 | +| iterations | 187 | +| time_elapsed | 290 | +| total_timesteps | 382976 | +| train/ | | +| approx_kl | 0.03336578 | +| clip_fraction | 0.367 | +| clip_range | 0.145 | +| entropy_loss | -7.45 | +| explained_variance | -0.0537 | +| learning_rate | 0.000192 | +| loss | -0.0681 | +| n_updates | 744 | +| policy_gradient_loss | -0.0355 | +| value_loss | 0.000198 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.227 | +| time/ | | +| fps | 1317 | +| iterations | 188 | +| time_elapsed | 292 | +| total_timesteps | 385024 | +| train/ | | +| approx_kl | 0.031785402 | +| clip_fraction | 0.39 | +| clip_range | 0.145 | +| entropy_loss | -7.43 | +| explained_variance | 0.0267 | +| learning_rate | 0.000192 | +| loss | -0.0634 | +| n_updates | 748 | +| policy_gradient_loss | -0.0324 | +| value_loss | 0.00029 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.237 | +| time/ | | +| fps | 1317 | +| iterations | 189 | +| time_elapsed | 293 | +| total_timesteps | 387072 | +| train/ | | +| approx_kl | 0.03672681 | +| clip_fraction | 0.393 | +| clip_range | 0.145 | +| entropy_loss | -7.31 | +| explained_variance | -0.151 | +| learning_rate | 0.000192 | +| loss | -0.0594 | +| n_updates | 752 | +| policy_gradient_loss | -0.0336 | +| value_loss | 0.000148 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.236 | +| time/ | | +| fps | 1317 | +| iterations | 190 | +| time_elapsed | 295 | +| total_timesteps | 389120 | +| train/ | | +| approx_kl | 0.03399978 | +| clip_fraction | 0.364 | +| clip_range | 0.145 | +| entropy_loss | -7.34 | +| explained_variance | -0.0205 | +| learning_rate | 0.000192 | +| loss | -0.0498 | +| n_updates | 756 | +| policy_gradient_loss | -0.0275 | +| value_loss | 0.000209 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.237 | +| time/ | | +| fps | 1317 | +| iterations | 191 | +| time_elapsed | 296 | +| total_timesteps | 391168 | +| train/ | | +| approx_kl | 0.03751424 | +| clip_fraction | 0.397 | +| clip_range | 0.145 | +| entropy_loss | -7.29 | +| explained_variance | -0.331 | +| learning_rate | 0.000192 | +| loss | -0.0696 | +| n_updates | 760 | +| policy_gradient_loss | -0.0351 | +| value_loss | 0.000124 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.226 | +| time/ | | +| fps | 1317 | +| iterations | 192 | +| time_elapsed | 298 | +| total_timesteps | 393216 | +| train/ | | +| approx_kl | 0.03972488 | +| clip_fraction | 0.374 | +| clip_range | 0.145 | +| entropy_loss | -7.22 | +| explained_variance | -0.0163 | +| learning_rate | 0.000192 | +| loss | -0.0453 | +| n_updates | 764 | +| policy_gradient_loss | -0.0306 | +| value_loss | 0.000275 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.227 | +| time/ | | +| fps | 1317 | +| iterations | 193 | +| time_elapsed | 300 | +| total_timesteps | 395264 | +| train/ | | +| approx_kl | 0.03402134 | +| clip_fraction | 0.4 | +| clip_range | 0.145 | +| entropy_loss | -7.35 | +| explained_variance | -0.0754 | +| learning_rate | 0.000192 | +| loss | -0.05 | +| n_updates | 768 | +| policy_gradient_loss | -0.0302 | +| value_loss | 0.000255 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.22 | +| time/ | | +| fps | 1317 | +| iterations | 194 | +| time_elapsed | 301 | +| total_timesteps | 397312 | +| train/ | | +| approx_kl | 0.031136563 | +| clip_fraction | 0.388 | +| clip_range | 0.145 | +| entropy_loss | -7.51 | +| explained_variance | 0.0945 | +| learning_rate | 0.000192 | +| loss | -0.0591 | +| n_updates | 772 | +| policy_gradient_loss | -0.0319 | +| value_loss | 0.000157 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.223 | +| time/ | | +| fps | 1317 | +| iterations | 195 | +| time_elapsed | 303 | +| total_timesteps | 399360 | +| train/ | | +| approx_kl | 0.032382704 | +| clip_fraction | 0.373 | +| clip_range | 0.145 | +| entropy_loss | -7.42 | +| explained_variance | -0.091 | +| learning_rate | 0.000192 | +| loss | -0.0529 | +| n_updates | 776 | +| policy_gradient_loss | -0.0376 | +| value_loss | 0.000115 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.229 | +| time/ | | +| fps | 1316 | +| iterations | 196 | +| time_elapsed | 304 | +| total_timesteps | 401408 | +| train/ | | +| approx_kl | 0.028287005 | +| clip_fraction | 0.38 | +| clip_range | 0.145 | +| entropy_loss | -7.46 | +| explained_variance | -0.18 | +| learning_rate | 0.000192 | +| loss | -0.0652 | +| n_updates | 780 | +| policy_gradient_loss | -0.0344 | +| value_loss | 9.09e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.225 | +| time/ | | +| fps | 1316 | +| iterations | 197 | +| time_elapsed | 306 | +| total_timesteps | 403456 | +| train/ | | +| approx_kl | 0.031541586 | +| clip_fraction | 0.372 | +| clip_range | 0.145 | +| entropy_loss | -7.5 | +| explained_variance | -0.0489 | +| learning_rate | 0.000192 | +| loss | -0.0619 | +| n_updates | 784 | +| policy_gradient_loss | -0.0285 | +| value_loss | 0.000295 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.224 | +| time/ | | +| fps | 1316 | +| iterations | 198 | +| time_elapsed | 307 | +| total_timesteps | 405504 | +| train/ | | +| approx_kl | 0.031510893 | +| clip_fraction | 0.351 | +| clip_range | 0.145 | +| entropy_loss | -7.52 | +| explained_variance | -0.151 | +| learning_rate | 0.000192 | +| loss | -0.0615 | +| n_updates | 788 | +| policy_gradient_loss | -0.033 | +| value_loss | 0.000197 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.223 | +| time/ | | +| fps | 1317 | +| iterations | 199 | +| time_elapsed | 309 | +| total_timesteps | 407552 | +| train/ | | +| approx_kl | 0.039286587 | +| clip_fraction | 0.389 | +| clip_range | 0.145 | +| entropy_loss | -7.5 | +| explained_variance | -0.00168 | +| learning_rate | 0.000192 | +| loss | -0.0617 | +| n_updates | 792 | +| policy_gradient_loss | -0.035 | +| value_loss | 0.000189 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.219 | +| time/ | | +| fps | 1317 | +| iterations | 200 | +| time_elapsed | 310 | +| total_timesteps | 409600 | +| train/ | | +| approx_kl | 0.030461913 | +| clip_fraction | 0.359 | +| clip_range | 0.145 | +| entropy_loss | -7.44 | +| explained_variance | -0.235 | +| learning_rate | 0.000192 | +| loss | -0.0607 | +| n_updates | 796 | +| policy_gradient_loss | -0.035 | +| value_loss | 0.000119 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.219 | +| time/ | | +| fps | 1317 | +| iterations | 201 | +| time_elapsed | 312 | +| total_timesteps | 411648 | +| train/ | | +| approx_kl | 0.034028135 | +| clip_fraction | 0.388 | +| clip_range | 0.145 | +| entropy_loss | -7.54 | +| explained_variance | -0.103 | +| learning_rate | 0.000192 | +| loss | -0.0584 | +| n_updates | 800 | +| policy_gradient_loss | -0.0274 | +| value_loss | 0.000178 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.216 | +| time/ | | +| fps | 1317 | +| iterations | 202 | +| time_elapsed | 314 | +| total_timesteps | 413696 | +| train/ | | +| approx_kl | 0.031806886 | +| clip_fraction | 0.369 | +| clip_range | 0.145 | +| entropy_loss | -7.57 | +| explained_variance | -0.258 | +| learning_rate | 0.000192 | +| loss | -0.0595 | +| n_updates | 804 | +| policy_gradient_loss | -0.0325 | +| value_loss | 9.68e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.218 | +| time/ | | +| fps | 1317 | +| iterations | 203 | +| time_elapsed | 315 | +| total_timesteps | 415744 | +| train/ | | +| approx_kl | 0.030040931 | +| clip_fraction | 0.332 | +| clip_range | 0.145 | +| entropy_loss | -7.51 | +| explained_variance | -0.122 | +| learning_rate | 0.000192 | +| loss | -0.0544 | +| n_updates | 808 | +| policy_gradient_loss | -0.0323 | +| value_loss | 0.000149 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.223 | +| time/ | | +| fps | 1317 | +| iterations | 204 | +| time_elapsed | 317 | +| total_timesteps | 417792 | +| train/ | | +| approx_kl | 0.032373138 | +| clip_fraction | 0.371 | +| clip_range | 0.145 | +| entropy_loss | -7.49 | +| explained_variance | 0.00831 | +| learning_rate | 0.000192 | +| loss | -0.0458 | +| n_updates | 812 | +| policy_gradient_loss | -0.0283 | +| value_loss | 0.000206 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.218 | +| time/ | | +| fps | 1317 | +| iterations | 205 | +| time_elapsed | 318 | +| total_timesteps | 419840 | +| train/ | | +| approx_kl | 0.03310746 | +| clip_fraction | 0.37 | +| clip_range | 0.145 | +| entropy_loss | -7.41 | +| explained_variance | -0.1 | +| learning_rate | 0.000192 | +| loss | -0.0505 | +| n_updates | 816 | +| policy_gradient_loss | -0.0321 | +| value_loss | 0.000165 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.218 | +| time/ | | +| fps | 1317 | +| iterations | 206 | +| time_elapsed | 320 | +| total_timesteps | 421888 | +| train/ | | +| approx_kl | 0.030027537 | +| clip_fraction | 0.359 | +| clip_range | 0.145 | +| entropy_loss | -7.41 | +| explained_variance | -0.179 | +| learning_rate | 0.000192 | +| loss | -0.0537 | +| n_updates | 820 | +| policy_gradient_loss | -0.0313 | +| value_loss | 0.000152 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.215 | +| time/ | | +| fps | 1317 | +| iterations | 207 | +| time_elapsed | 321 | +| total_timesteps | 423936 | +| train/ | | +| approx_kl | 0.032444708 | +| clip_fraction | 0.357 | +| clip_range | 0.145 | +| entropy_loss | -7.44 | +| explained_variance | -0.2 | +| learning_rate | 0.000192 | +| loss | -0.0462 | +| n_updates | 824 | +| policy_gradient_loss | -0.0316 | +| value_loss | 0.000154 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.215 | +| time/ | | +| fps | 1317 | +| iterations | 208 | +| time_elapsed | 323 | +| total_timesteps | 425984 | +| train/ | | +| approx_kl | 0.030903168 | +| clip_fraction | 0.365 | +| clip_range | 0.145 | +| entropy_loss | -7.47 | +| explained_variance | -0.143 | +| learning_rate | 0.000192 | +| loss | -0.0672 | +| n_updates | 828 | +| policy_gradient_loss | -0.0356 | +| value_loss | 0.000109 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.216 | +| time/ | | +| fps | 1317 | +| iterations | 209 | +| time_elapsed | 324 | +| total_timesteps | 428032 | +| train/ | | +| approx_kl | 0.03225661 | +| clip_fraction | 0.359 | +| clip_range | 0.145 | +| entropy_loss | -7.32 | +| explained_variance | -0.487 | +| learning_rate | 0.000192 | +| loss | -0.0627 | +| n_updates | 832 | +| policy_gradient_loss | -0.0347 | +| value_loss | 9.17e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.228 | +| time/ | | +| fps | 1317 | +| iterations | 210 | +| time_elapsed | 326 | +| total_timesteps | 430080 | +| train/ | | +| approx_kl | 0.033882983 | +| clip_fraction | 0.352 | +| clip_range | 0.145 | +| entropy_loss | -7.31 | +| explained_variance | -0.232 | +| learning_rate | 0.000192 | +| loss | -0.0685 | +| n_updates | 836 | +| policy_gradient_loss | -0.0345 | +| value_loss | 0.000153 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.228 | +| time/ | | +| fps | 1317 | +| iterations | 211 | +| time_elapsed | 327 | +| total_timesteps | 432128 | +| train/ | | +| approx_kl | 0.028582308 | +| clip_fraction | 0.344 | +| clip_range | 0.145 | +| entropy_loss | -7.33 | +| explained_variance | -0.242 | +| learning_rate | 0.000191 | +| loss | -0.0647 | +| n_updates | 840 | +| policy_gradient_loss | -0.0309 | +| value_loss | 0.000159 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.223 | +| time/ | | +| fps | 1317 | +| iterations | 212 | +| time_elapsed | 329 | +| total_timesteps | 434176 | +| train/ | | +| approx_kl | 0.03612067 | +| clip_fraction | 0.351 | +| clip_range | 0.145 | +| entropy_loss | -7.31 | +| explained_variance | -0.105 | +| learning_rate | 0.000191 | +| loss | -0.0534 | +| n_updates | 844 | +| policy_gradient_loss | -0.0327 | +| value_loss | 0.000259 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.219 | +| time/ | | +| fps | 1318 | +| iterations | 213 | +| time_elapsed | 330 | +| total_timesteps | 436224 | +| train/ | | +| approx_kl | 0.035995696 | +| clip_fraction | 0.41 | +| clip_range | 0.145 | +| entropy_loss | -7.28 | +| explained_variance | -0.392 | +| learning_rate | 0.000191 | +| loss | -0.064 | +| n_updates | 848 | +| policy_gradient_loss | -0.0341 | +| value_loss | 0.000124 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.217 | +| time/ | | +| fps | 1318 | +| iterations | 214 | +| time_elapsed | 332 | +| total_timesteps | 438272 | +| train/ | | +| approx_kl | 0.032337092 | +| clip_fraction | 0.377 | +| clip_range | 0.145 | +| entropy_loss | -7.32 | +| explained_variance | -0.23 | +| learning_rate | 0.000191 | +| loss | -0.0513 | +| n_updates | 852 | +| policy_gradient_loss | -0.0347 | +| value_loss | 0.000193 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.217 | +| time/ | | +| fps | 1318 | +| iterations | 215 | +| time_elapsed | 334 | +| total_timesteps | 440320 | +| train/ | | +| approx_kl | 0.032097135 | +| clip_fraction | 0.378 | +| clip_range | 0.145 | +| entropy_loss | -7.28 | +| explained_variance | -0.228 | +| learning_rate | 0.000191 | +| loss | -0.0613 | +| n_updates | 856 | +| policy_gradient_loss | -0.034 | +| value_loss | 0.000194 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.217 | +| time/ | | +| fps | 1317 | +| iterations | 216 | +| time_elapsed | 335 | +| total_timesteps | 442368 | +| train/ | | +| approx_kl | 0.033345133 | +| clip_fraction | 0.393 | +| clip_range | 0.144 | +| entropy_loss | -7.29 | +| explained_variance | -0.337 | +| learning_rate | 0.000191 | +| loss | -0.0602 | +| n_updates | 860 | +| policy_gradient_loss | -0.0373 | +| value_loss | 0.000105 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.217 | +| time/ | | +| fps | 1318 | +| iterations | 217 | +| time_elapsed | 337 | +| total_timesteps | 444416 | +| train/ | | +| approx_kl | 0.03962717 | +| clip_fraction | 0.41 | +| clip_range | 0.144 | +| entropy_loss | -7.33 | +| explained_variance | -0.553 | +| learning_rate | 0.000191 | +| loss | -0.0598 | +| n_updates | 864 | +| policy_gradient_loss | -0.0403 | +| value_loss | 8.9e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.226 | +| time/ | | +| fps | 1318 | +| iterations | 218 | +| time_elapsed | 338 | +| total_timesteps | 446464 | +| train/ | | +| approx_kl | 0.032679718 | +| clip_fraction | 0.41 | +| clip_range | 0.144 | +| entropy_loss | -7.34 | +| explained_variance | -0.183 | +| learning_rate | 0.000191 | +| loss | -0.0625 | +| n_updates | 868 | +| policy_gradient_loss | -0.0331 | +| value_loss | 0.000137 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.227 | +| time/ | | +| fps | 1318 | +| iterations | 219 | +| time_elapsed | 340 | +| total_timesteps | 448512 | +| train/ | | +| approx_kl | 0.03221353 | +| clip_fraction | 0.341 | +| clip_range | 0.144 | +| entropy_loss | -7.29 | +| explained_variance | -0.0787 | +| learning_rate | 0.000191 | +| loss | -0.053 | +| n_updates | 872 | +| policy_gradient_loss | -0.0293 | +| value_loss | 0.000226 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.229 | +| time/ | | +| fps | 1317 | +| iterations | 220 | +| time_elapsed | 341 | +| total_timesteps | 450560 | +| train/ | | +| approx_kl | 0.03764499 | +| clip_fraction | 0.398 | +| clip_range | 0.144 | +| entropy_loss | -7.27 | +| explained_variance | -0.328 | +| learning_rate | 0.000191 | +| loss | -0.0552 | +| n_updates | 876 | +| policy_gradient_loss | -0.0339 | +| value_loss | 0.000116 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.229 | +| time/ | | +| fps | 1318 | +| iterations | 221 | +| time_elapsed | 343 | +| total_timesteps | 452608 | +| train/ | | +| approx_kl | 0.033435866 | +| clip_fraction | 0.377 | +| clip_range | 0.144 | +| entropy_loss | -7.31 | +| explained_variance | -0.0551 | +| learning_rate | 0.000191 | +| loss | -0.0586 | +| n_updates | 880 | +| policy_gradient_loss | -0.0321 | +| value_loss | 0.000116 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.228 | +| time/ | | +| fps | 1318 | +| iterations | 222 | +| time_elapsed | 344 | +| total_timesteps | 454656 | +| train/ | | +| approx_kl | 0.033285387 | +| clip_fraction | 0.36 | +| clip_range | 0.144 | +| entropy_loss | -7.27 | +| explained_variance | -0.111 | +| learning_rate | 0.000191 | +| loss | -0.0472 | +| n_updates | 884 | +| policy_gradient_loss | -0.0288 | +| value_loss | 0.000182 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.228 | +| time/ | | +| fps | 1318 | +| iterations | 223 | +| time_elapsed | 346 | +| total_timesteps | 456704 | +| train/ | | +| approx_kl | 0.03959688 | +| clip_fraction | 0.387 | +| clip_range | 0.144 | +| entropy_loss | -7.26 | +| explained_variance | -0.0329 | +| learning_rate | 0.000191 | +| loss | -0.0473 | +| n_updates | 888 | +| policy_gradient_loss | -0.0233 | +| value_loss | 0.000255 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.228 | +| time/ | | +| fps | 1318 | +| iterations | 224 | +| time_elapsed | 347 | +| total_timesteps | 458752 | +| train/ | | +| approx_kl | 0.03335233 | +| clip_fraction | 0.377 | +| clip_range | 0.144 | +| entropy_loss | -7.42 | +| explained_variance | -0.244 | +| learning_rate | 0.000191 | +| loss | -0.0666 | +| n_updates | 892 | +| policy_gradient_loss | -0.0373 | +| value_loss | 0.000101 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.23 | +| time/ | | +| fps | 1318 | +| iterations | 225 | +| time_elapsed | 349 | +| total_timesteps | 460800 | +| train/ | | +| approx_kl | 0.030290725 | +| clip_fraction | 0.35 | +| clip_range | 0.144 | +| entropy_loss | -7.37 | +| explained_variance | -0.221 | +| learning_rate | 0.000191 | +| loss | -0.0575 | +| n_updates | 896 | +| policy_gradient_loss | -0.0317 | +| value_loss | 0.000113 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.235 | +| time/ | | +| fps | 1318 | +| iterations | 226 | +| time_elapsed | 351 | +| total_timesteps | 462848 | +| train/ | | +| approx_kl | 0.027392741 | +| clip_fraction | 0.363 | +| clip_range | 0.144 | +| entropy_loss | -7.47 | +| explained_variance | -0.0996 | +| learning_rate | 0.000191 | +| loss | -0.0485 | +| n_updates | 900 | +| policy_gradient_loss | -0.0328 | +| value_loss | 8.48e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.235 | +| time/ | | +| fps | 1318 | +| iterations | 227 | +| time_elapsed | 352 | +| total_timesteps | 464896 | +| train/ | | +| approx_kl | 0.028952427 | +| clip_fraction | 0.331 | +| clip_range | 0.144 | +| entropy_loss | -7.41 | +| explained_variance | -0.172 | +| learning_rate | 0.000191 | +| loss | -0.0609 | +| n_updates | 904 | +| policy_gradient_loss | -0.0326 | +| value_loss | 8.3e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.236 | +| time/ | | +| fps | 1318 | +| iterations | 228 | +| time_elapsed | 354 | +| total_timesteps | 466944 | +| train/ | | +| approx_kl | 0.032920387 | +| clip_fraction | 0.352 | +| clip_range | 0.144 | +| entropy_loss | -7.46 | +| explained_variance | -0.0595 | +| learning_rate | 0.000191 | +| loss | -0.0462 | +| n_updates | 908 | +| policy_gradient_loss | -0.0316 | +| value_loss | 0.000174 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.235 | +| time/ | | +| fps | 1318 | +| iterations | 229 | +| time_elapsed | 355 | +| total_timesteps | 468992 | +| train/ | | +| approx_kl | 0.03335058 | +| clip_fraction | 0.356 | +| clip_range | 0.144 | +| entropy_loss | -7.53 | +| explained_variance | -0.0842 | +| learning_rate | 0.000191 | +| loss | -0.0616 | +| n_updates | 912 | +| policy_gradient_loss | -0.034 | +| value_loss | 0.000159 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.239 | +| time/ | | +| fps | 1318 | +| iterations | 230 | +| time_elapsed | 357 | +| total_timesteps | 471040 | +| train/ | | +| approx_kl | 0.031952053 | +| clip_fraction | 0.327 | +| clip_range | 0.144 | +| entropy_loss | -7.49 | +| explained_variance | -0.189 | +| learning_rate | 0.000191 | +| loss | -0.0581 | +| n_updates | 916 | +| policy_gradient_loss | -0.0346 | +| value_loss | 0.000194 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.234 | +| time/ | | +| fps | 1318 | +| iterations | 231 | +| time_elapsed | 358 | +| total_timesteps | 473088 | +| train/ | | +| approx_kl | 0.030381408 | +| clip_fraction | 0.325 | +| clip_range | 0.144 | +| entropy_loss | -7.41 | +| explained_variance | -0.0575 | +| learning_rate | 0.000191 | +| loss | -0.0522 | +| n_updates | 920 | +| policy_gradient_loss | -0.0319 | +| value_loss | 0.000158 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.233 | +| time/ | | +| fps | 1318 | +| iterations | 232 | +| time_elapsed | 360 | +| total_timesteps | 475136 | +| train/ | | +| approx_kl | 0.032275073 | +| clip_fraction | 0.352 | +| clip_range | 0.144 | +| entropy_loss | -7.49 | +| explained_variance | -0.0953 | +| learning_rate | 0.000191 | +| loss | -0.0399 | +| n_updates | 924 | +| policy_gradient_loss | -0.027 | +| value_loss | 0.000155 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.233 | +| time/ | | +| fps | 1319 | +| iterations | 233 | +| time_elapsed | 361 | +| total_timesteps | 477184 | +| train/ | | +| approx_kl | 0.039931364 | +| clip_fraction | 0.366 | +| clip_range | 0.144 | +| entropy_loss | -7.51 | +| explained_variance | 0.000651 | +| learning_rate | 0.000191 | +| loss | -0.0677 | +| n_updates | 928 | +| policy_gradient_loss | -0.0374 | +| value_loss | 0.000136 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.233 | +| time/ | | +| fps | 1319 | +| iterations | 234 | +| time_elapsed | 363 | +| total_timesteps | 479232 | +| train/ | | +| approx_kl | 0.02721711 | +| clip_fraction | 0.36 | +| clip_range | 0.144 | +| entropy_loss | -7.46 | +| explained_variance | -0.379 | +| learning_rate | 0.000191 | +| loss | -0.0578 | +| n_updates | 932 | +| policy_gradient_loss | -0.0352 | +| value_loss | 6.58e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.227 | +| time/ | | +| fps | 1319 | +| iterations | 235 | +| time_elapsed | 364 | +| total_timesteps | 481280 | +| train/ | | +| approx_kl | 0.030727472 | +| clip_fraction | 0.371 | +| clip_range | 0.144 | +| entropy_loss | -7.46 | +| explained_variance | -0.217 | +| learning_rate | 0.000191 | +| loss | -0.0528 | +| n_updates | 936 | +| policy_gradient_loss | -0.0321 | +| value_loss | 8.37e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.225 | +| time/ | | +| fps | 1318 | +| iterations | 236 | +| time_elapsed | 366 | +| total_timesteps | 483328 | +| train/ | | +| approx_kl | 0.03242491 | +| clip_fraction | 0.373 | +| clip_range | 0.144 | +| entropy_loss | -7.41 | +| explained_variance | -0.124 | +| learning_rate | 0.00019 | +| loss | -0.0549 | +| n_updates | 940 | +| policy_gradient_loss | -0.0328 | +| value_loss | 0.000169 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.224 | +| time/ | | +| fps | 1318 | +| iterations | 237 | +| time_elapsed | 367 | +| total_timesteps | 485376 | +| train/ | | +| approx_kl | 0.03306511 | +| clip_fraction | 0.361 | +| clip_range | 0.144 | +| entropy_loss | -7.41 | +| explained_variance | -0.171 | +| learning_rate | 0.00019 | +| loss | -0.0586 | +| n_updates | 944 | +| policy_gradient_loss | -0.0342 | +| value_loss | 0.000176 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.222 | +| time/ | | +| fps | 1319 | +| iterations | 238 | +| time_elapsed | 369 | +| total_timesteps | 487424 | +| train/ | | +| approx_kl | 0.032734495 | +| clip_fraction | 0.357 | +| clip_range | 0.144 | +| entropy_loss | -7.45 | +| explained_variance | -0.124 | +| learning_rate | 0.00019 | +| loss | -0.0582 | +| n_updates | 948 | +| policy_gradient_loss | -0.038 | +| value_loss | 8.35e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.22 | +| time/ | | +| fps | 1319 | +| iterations | 239 | +| time_elapsed | 371 | +| total_timesteps | 489472 | +| train/ | | +| approx_kl | 0.03371606 | +| clip_fraction | 0.332 | +| clip_range | 0.144 | +| entropy_loss | -7.5 | +| explained_variance | -0.0957 | +| learning_rate | 0.00019 | +| loss | -0.0594 | +| n_updates | 952 | +| policy_gradient_loss | -0.0319 | +| value_loss | 0.000185 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.222 | +| time/ | | +| fps | 1319 | +| iterations | 240 | +| time_elapsed | 372 | +| total_timesteps | 491520 | +| train/ | | +| approx_kl | 0.029103369 | +| clip_fraction | 0.34 | +| clip_range | 0.144 | +| entropy_loss | -7.57 | +| explained_variance | -0.0929 | +| learning_rate | 0.00019 | +| loss | -0.0525 | +| n_updates | 956 | +| policy_gradient_loss | -0.0322 | +| value_loss | 0.000186 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.231 | +| time/ | | +| fps | 1319 | +| iterations | 241 | +| time_elapsed | 374 | +| total_timesteps | 493568 | +| train/ | | +| approx_kl | 0.02950788 | +| clip_fraction | 0.354 | +| clip_range | 0.144 | +| entropy_loss | -7.51 | +| explained_variance | -0.204 | +| learning_rate | 0.00019 | +| loss | -0.0552 | +| n_updates | 960 | +| policy_gradient_loss | -0.0346 | +| value_loss | 0.000187 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.234 | +| time/ | | +| fps | 1319 | +| iterations | 242 | +| time_elapsed | 375 | +| total_timesteps | 495616 | +| train/ | | +| approx_kl | 0.032433204 | +| clip_fraction | 0.38 | +| clip_range | 0.144 | +| entropy_loss | -7.45 | +| explained_variance | -0.125 | +| learning_rate | 0.00019 | +| loss | -0.0477 | +| n_updates | 964 | +| policy_gradient_loss | -0.0298 | +| value_loss | 0.00022 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.234 | +| time/ | | +| fps | 1319 | +| iterations | 243 | +| time_elapsed | 377 | +| total_timesteps | 497664 | +| train/ | | +| approx_kl | 0.031200495 | +| clip_fraction | 0.381 | +| clip_range | 0.144 | +| entropy_loss | -7.44 | +| explained_variance | -0.132 | +| learning_rate | 0.00019 | +| loss | -0.057 | +| n_updates | 968 | +| policy_gradient_loss | -0.0321 | +| value_loss | 0.000135 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.23 | +| time/ | | +| fps | 1319 | +| iterations | 244 | +| time_elapsed | 378 | +| total_timesteps | 499712 | +| train/ | | +| approx_kl | 0.027702756 | +| clip_fraction | 0.36 | +| clip_range | 0.144 | +| entropy_loss | -7.3 | +| explained_variance | 0.105 | +| learning_rate | 0.00019 | +| loss | -0.0499 | +| n_updates | 972 | +| policy_gradient_loss | -0.0311 | +| value_loss | 0.000133 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.229 | +| time/ | | +| fps | 1319 | +| iterations | 245 | +| time_elapsed | 380 | +| total_timesteps | 501760 | +| train/ | | +| approx_kl | 0.028371645 | +| clip_fraction | 0.327 | +| clip_range | 0.144 | +| entropy_loss | -7.26 | +| explained_variance | 0.0511 | +| learning_rate | 0.00019 | +| loss | -0.0591 | +| n_updates | 976 | +| policy_gradient_loss | -0.0264 | +| value_loss | 0.000255 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.23 | +| time/ | | +| fps | 1319 | +| iterations | 246 | +| time_elapsed | 381 | +| total_timesteps | 503808 | +| train/ | | +| approx_kl | 0.02763199 | +| clip_fraction | 0.35 | +| clip_range | 0.144 | +| entropy_loss | -7.35 | +| explained_variance | -0.0127 | +| learning_rate | 0.00019 | +| loss | -0.0487 | +| n_updates | 980 | +| policy_gradient_loss | -0.0275 | +| value_loss | 0.000357 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.235 | +| time/ | | +| fps | 1319 | +| iterations | 247 | +| time_elapsed | 383 | +| total_timesteps | 505856 | +| train/ | | +| approx_kl | 0.026332967 | +| clip_fraction | 0.364 | +| clip_range | 0.144 | +| entropy_loss | -7.48 | +| explained_variance | 0.068 | +| learning_rate | 0.00019 | +| loss | -0.054 | +| n_updates | 984 | +| policy_gradient_loss | -0.03 | +| value_loss | 0.000184 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.235 | +| time/ | | +| fps | 1319 | +| iterations | 248 | +| time_elapsed | 384 | +| total_timesteps | 507904 | +| train/ | | +| approx_kl | 0.029113699 | +| clip_fraction | 0.342 | +| clip_range | 0.144 | +| entropy_loss | -7.48 | +| explained_variance | 0.0351 | +| learning_rate | 0.00019 | +| loss | -0.0609 | +| n_updates | 988 | +| policy_gradient_loss | -0.0306 | +| value_loss | 0.000256 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.232 | +| time/ | | +| fps | 1319 | +| iterations | 249 | +| time_elapsed | 386 | +| total_timesteps | 509952 | +| train/ | | +| approx_kl | 0.031728845 | +| clip_fraction | 0.32 | +| clip_range | 0.144 | +| entropy_loss | -7.45 | +| explained_variance | -0.129 | +| learning_rate | 0.00019 | +| loss | -0.0625 | +| n_updates | 992 | +| policy_gradient_loss | -0.0369 | +| value_loss | 0.000175 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.234 | +| time/ | | +| fps | 1319 | +| iterations | 250 | +| time_elapsed | 387 | +| total_timesteps | 512000 | +| train/ | | +| approx_kl | 0.030465359 | +| clip_fraction | 0.348 | +| clip_range | 0.144 | +| entropy_loss | -7.41 | +| explained_variance | -0.0767 | +| learning_rate | 0.00019 | +| loss | -0.0528 | +| n_updates | 996 | +| policy_gradient_loss | -0.0302 | +| value_loss | 0.000203 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.237 | +| time/ | | +| fps | 1320 | +| iterations | 251 | +| time_elapsed | 389 | +| total_timesteps | 514048 | +| train/ | | +| approx_kl | 0.031597182 | +| clip_fraction | 0.363 | +| clip_range | 0.144 | +| entropy_loss | -7.35 | +| explained_variance | -0.0639 | +| learning_rate | 0.00019 | +| loss | -0.0542 | +| n_updates | 1000 | +| policy_gradient_loss | -0.032 | +| value_loss | 0.000203 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.237 | +| time/ | | +| fps | 1320 | +| iterations | 252 | +| time_elapsed | 390 | +| total_timesteps | 516096 | +| train/ | | +| approx_kl | 0.03763834 | +| clip_fraction | 0.381 | +| clip_range | 0.144 | +| entropy_loss | -7.34 | +| explained_variance | -0.398 | +| learning_rate | 0.00019 | +| loss | -0.0671 | +| n_updates | 1004 | +| policy_gradient_loss | -0.0376 | +| value_loss | 9.95e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.232 | +| time/ | | +| fps | 1320 | +| iterations | 253 | +| time_elapsed | 392 | +| total_timesteps | 518144 | +| train/ | | +| approx_kl | 0.037023626 | +| clip_fraction | 0.363 | +| clip_range | 0.144 | +| entropy_loss | -7.37 | +| explained_variance | -0.158 | +| learning_rate | 0.00019 | +| loss | -0.0519 | +| n_updates | 1008 | +| policy_gradient_loss | -0.033 | +| value_loss | 0.000177 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.225 | +| time/ | | +| fps | 1320 | +| iterations | 254 | +| time_elapsed | 393 | +| total_timesteps | 520192 | +| train/ | | +| approx_kl | 0.033282474 | +| clip_fraction | 0.379 | +| clip_range | 0.144 | +| entropy_loss | -7.37 | +| explained_variance | -0.154 | +| learning_rate | 0.00019 | +| loss | -0.0611 | +| n_updates | 1012 | +| policy_gradient_loss | -0.036 | +| value_loss | 8.66e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.224 | +| time/ | | +| fps | 1320 | +| iterations | 255 | +| time_elapsed | 395 | +| total_timesteps | 522240 | +| train/ | | +| approx_kl | 0.030821333 | +| clip_fraction | 0.365 | +| clip_range | 0.143 | +| entropy_loss | -7.32 | +| explained_variance | 0.0133 | +| learning_rate | 0.00019 | +| loss | -0.0498 | +| n_updates | 1016 | +| policy_gradient_loss | -0.0309 | +| value_loss | 0.00015 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.221 | +| time/ | | +| fps | 1321 | +| iterations | 256 | +| time_elapsed | 396 | +| total_timesteps | 524288 | +| train/ | | +| approx_kl | 0.037665587 | +| clip_fraction | 0.394 | +| clip_range | 0.143 | +| entropy_loss | -7.37 | +| explained_variance | 0.0115 | +| learning_rate | 0.00019 | +| loss | -0.0528 | +| n_updates | 1020 | +| policy_gradient_loss | -0.0318 | +| value_loss | 0.000231 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.215 | +| time/ | | +| fps | 1321 | +| iterations | 257 | +| time_elapsed | 398 | +| total_timesteps | 526336 | +| train/ | | +| approx_kl | 0.031408086 | +| clip_fraction | 0.374 | +| clip_range | 0.143 | +| entropy_loss | -7.38 | +| explained_variance | -0.12 | +| learning_rate | 0.00019 | +| loss | -0.0597 | +| n_updates | 1024 | +| policy_gradient_loss | -0.0347 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.215 | +| time/ | | +| fps | 1321 | +| iterations | 258 | +| time_elapsed | 399 | +| total_timesteps | 528384 | +| train/ | | +| approx_kl | 0.034112588 | +| clip_fraction | 0.361 | +| clip_range | 0.143 | +| entropy_loss | -7.3 | +| explained_variance | -0.211 | +| learning_rate | 0.00019 | +| loss | -0.0416 | +| n_updates | 1028 | +| policy_gradient_loss | -0.0323 | +| value_loss | 9.61e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.223 | +| time/ | | +| fps | 1321 | +| iterations | 259 | +| time_elapsed | 401 | +| total_timesteps | 530432 | +| train/ | | +| approx_kl | 0.033873945 | +| clip_fraction | 0.37 | +| clip_range | 0.143 | +| entropy_loss | -7.24 | +| explained_variance | -0.0818 | +| learning_rate | 0.00019 | +| loss | -0.0561 | +| n_updates | 1032 | +| policy_gradient_loss | -0.0331 | +| value_loss | 0.000121 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.227 | +| time/ | | +| fps | 1321 | +| iterations | 260 | +| time_elapsed | 403 | +| total_timesteps | 532480 | +| train/ | | +| approx_kl | 0.03274847 | +| clip_fraction | 0.373 | +| clip_range | 0.143 | +| entropy_loss | -7.3 | +| explained_variance | 0.0148 | +| learning_rate | 0.000189 | +| loss | -0.0538 | +| n_updates | 1036 | +| policy_gradient_loss | -0.0284 | +| value_loss | 0.000127 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.23 | +| time/ | | +| fps | 1321 | +| iterations | 261 | +| time_elapsed | 404 | +| total_timesteps | 534528 | +| train/ | | +| approx_kl | 0.037610024 | +| clip_fraction | 0.36 | +| clip_range | 0.143 | +| entropy_loss | -7.32 | +| explained_variance | -0.101 | +| learning_rate | 0.000189 | +| loss | -0.0608 | +| n_updates | 1040 | +| policy_gradient_loss | -0.036 | +| value_loss | 9.92e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.23 | +| time/ | | +| fps | 1321 | +| iterations | 262 | +| time_elapsed | 406 | +| total_timesteps | 536576 | +| train/ | | +| approx_kl | 0.031590436 | +| clip_fraction | 0.35 | +| clip_range | 0.143 | +| entropy_loss | -7.33 | +| explained_variance | -0.198 | +| learning_rate | 0.000189 | +| loss | -0.0461 | +| n_updates | 1044 | +| policy_gradient_loss | -0.0321 | +| value_loss | 0.000118 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.223 | +| time/ | | +| fps | 1321 | +| iterations | 263 | +| time_elapsed | 407 | +| total_timesteps | 538624 | +| train/ | | +| approx_kl | 0.0342096 | +| clip_fraction | 0.379 | +| clip_range | 0.143 | +| entropy_loss | -7.23 | +| explained_variance | 0.00631 | +| learning_rate | 0.000189 | +| loss | -0.0486 | +| n_updates | 1048 | +| policy_gradient_loss | -0.0296 | +| value_loss | 0.00013 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.224 | +| time/ | | +| fps | 1321 | +| iterations | 264 | +| time_elapsed | 409 | +| total_timesteps | 540672 | +| train/ | | +| approx_kl | 0.034981295 | +| clip_fraction | 0.394 | +| clip_range | 0.143 | +| entropy_loss | -7.22 | +| explained_variance | -0.0664 | +| learning_rate | 0.000189 | +| loss | -0.0573 | +| n_updates | 1052 | +| policy_gradient_loss | -0.0327 | +| value_loss | 0.000192 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.22 | +| time/ | | +| fps | 1321 | +| iterations | 265 | +| time_elapsed | 410 | +| total_timesteps | 542720 | +| train/ | | +| approx_kl | 0.03447011 | +| clip_fraction | 0.394 | +| clip_range | 0.143 | +| entropy_loss | -7.21 | +| explained_variance | -0.21 | +| learning_rate | 0.000189 | +| loss | -0.0508 | +| n_updates | 1056 | +| policy_gradient_loss | -0.0324 | +| value_loss | 0.000158 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.223 | +| time/ | | +| fps | 1322 | +| iterations | 266 | +| time_elapsed | 412 | +| total_timesteps | 544768 | +| train/ | | +| approx_kl | 0.03505467 | +| clip_fraction | 0.373 | +| clip_range | 0.143 | +| entropy_loss | -7.16 | +| explained_variance | -0.22 | +| learning_rate | 0.000189 | +| loss | -0.0605 | +| n_updates | 1060 | +| policy_gradient_loss | -0.039 | +| value_loss | 0.000109 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.223 | +| time/ | | +| fps | 1321 | +| iterations | 267 | +| time_elapsed | 413 | +| total_timesteps | 546816 | +| train/ | | +| approx_kl | 0.036866345 | +| clip_fraction | 0.398 | +| clip_range | 0.143 | +| entropy_loss | -7.26 | +| explained_variance | -0.18 | +| learning_rate | 0.000189 | +| loss | -0.0551 | +| n_updates | 1064 | +| policy_gradient_loss | -0.0367 | +| value_loss | 0.000129 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.223 | +| time/ | | +| fps | 1321 | +| iterations | 268 | +| time_elapsed | 415 | +| total_timesteps | 548864 | +| train/ | | +| approx_kl | 0.03196412 | +| clip_fraction | 0.385 | +| clip_range | 0.143 | +| entropy_loss | -7.33 | +| explained_variance | -0.0542 | +| learning_rate | 0.000189 | +| loss | -0.055 | +| n_updates | 1068 | +| policy_gradient_loss | -0.0285 | +| value_loss | 0.00015 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.22 | +| time/ | | +| fps | 1321 | +| iterations | 269 | +| time_elapsed | 416 | +| total_timesteps | 550912 | +| train/ | | +| approx_kl | 0.038793936 | +| clip_fraction | 0.368 | +| clip_range | 0.143 | +| entropy_loss | -7.33 | +| explained_variance | -0.0623 | +| learning_rate | 0.000189 | +| loss | -0.0548 | +| n_updates | 1072 | +| policy_gradient_loss | -0.0321 | +| value_loss | 0.00016 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.225 | +| time/ | | +| fps | 1322 | +| iterations | 270 | +| time_elapsed | 418 | +| total_timesteps | 552960 | +| train/ | | +| approx_kl | 0.032086775 | +| clip_fraction | 0.37 | +| clip_range | 0.143 | +| entropy_loss | -7.37 | +| explained_variance | -0.156 | +| learning_rate | 0.000189 | +| loss | -0.0678 | +| n_updates | 1076 | +| policy_gradient_loss | -0.0341 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.221 | +| time/ | | +| fps | 1322 | +| iterations | 271 | +| time_elapsed | 419 | +| total_timesteps | 555008 | +| train/ | | +| approx_kl | 0.028723115 | +| clip_fraction | 0.326 | +| clip_range | 0.143 | +| entropy_loss | -7.43 | +| explained_variance | -0.00266 | +| learning_rate | 0.000189 | +| loss | -0.0457 | +| n_updates | 1080 | +| policy_gradient_loss | -0.0284 | +| value_loss | 0.000152 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.221 | +| time/ | | +| fps | 1322 | +| iterations | 272 | +| time_elapsed | 421 | +| total_timesteps | 557056 | +| train/ | | +| approx_kl | 0.03245481 | +| clip_fraction | 0.364 | +| clip_range | 0.143 | +| entropy_loss | -7.47 | +| explained_variance | -0.17 | +| learning_rate | 0.000189 | +| loss | -0.0654 | +| n_updates | 1084 | +| policy_gradient_loss | -0.0364 | +| value_loss | 9.21e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.221 | +| time/ | | +| fps | 1322 | +| iterations | 273 | +| time_elapsed | 422 | +| total_timesteps | 559104 | +| train/ | | +| approx_kl | 0.031922765 | +| clip_fraction | 0.388 | +| clip_range | 0.143 | +| entropy_loss | -7.4 | +| explained_variance | -0.0799 | +| learning_rate | 0.000189 | +| loss | -0.0473 | +| n_updates | 1088 | +| policy_gradient_loss | -0.0286 | +| value_loss | 0.000153 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.221 | +| time/ | | +| fps | 1322 | +| iterations | 274 | +| time_elapsed | 424 | +| total_timesteps | 561152 | +| train/ | | +| approx_kl | 0.035321128 | +| clip_fraction | 0.372 | +| clip_range | 0.143 | +| entropy_loss | -7.31 | +| explained_variance | -0.112 | +| learning_rate | 0.000189 | +| loss | -0.048 | +| n_updates | 1092 | +| policy_gradient_loss | -0.0323 | +| value_loss | 0.000153 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.221 | +| time/ | | +| fps | 1322 | +| iterations | 275 | +| time_elapsed | 425 | +| total_timesteps | 563200 | +| train/ | | +| approx_kl | 0.035002705 | +| clip_fraction | 0.376 | +| clip_range | 0.143 | +| entropy_loss | -7.43 | +| explained_variance | -0.199 | +| learning_rate | 0.000189 | +| loss | -0.0632 | +| n_updates | 1096 | +| policy_gradient_loss | -0.0337 | +| value_loss | 0.0001 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.216 | +| time/ | | +| fps | 1322 | +| iterations | 276 | +| time_elapsed | 427 | +| total_timesteps | 565248 | +| train/ | | +| approx_kl | 0.040040076 | +| clip_fraction | 0.387 | +| clip_range | 0.143 | +| entropy_loss | -7.42 | +| explained_variance | -0.112 | +| learning_rate | 0.000189 | +| loss | -0.0504 | +| n_updates | 1100 | +| policy_gradient_loss | -0.0306 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.221 | +| time/ | | +| fps | 1322 | +| iterations | 277 | +| time_elapsed | 428 | +| total_timesteps | 567296 | +| train/ | | +| approx_kl | 0.032345727 | +| clip_fraction | 0.379 | +| clip_range | 0.143 | +| entropy_loss | -7.46 | +| explained_variance | -0.175 | +| learning_rate | 0.000189 | +| loss | -0.0497 | +| n_updates | 1104 | +| policy_gradient_loss | -0.0316 | +| value_loss | 0.000198 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.222 | +| time/ | | +| fps | 1322 | +| iterations | 278 | +| time_elapsed | 430 | +| total_timesteps | 569344 | +| train/ | | +| approx_kl | 0.033616763 | +| clip_fraction | 0.386 | +| clip_range | 0.143 | +| entropy_loss | -7.27 | +| explained_variance | -0.0845 | +| learning_rate | 0.000189 | +| loss | -0.057 | +| n_updates | 1108 | +| policy_gradient_loss | -0.0329 | +| value_loss | 0.000156 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.227 | +| time/ | | +| fps | 1322 | +| iterations | 279 | +| time_elapsed | 431 | +| total_timesteps | 571392 | +| train/ | | +| approx_kl | 0.031759553 | +| clip_fraction | 0.378 | +| clip_range | 0.143 | +| entropy_loss | -7.34 | +| explained_variance | -0.125 | +| learning_rate | 0.000189 | +| loss | -0.0496 | +| n_updates | 1112 | +| policy_gradient_loss | -0.0257 | +| value_loss | 0.000151 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.225 | +| time/ | | +| fps | 1323 | +| iterations | 280 | +| time_elapsed | 433 | +| total_timesteps | 573440 | +| train/ | | +| approx_kl | 0.04130472 | +| clip_fraction | 0.4 | +| clip_range | 0.143 | +| entropy_loss | -7.24 | +| explained_variance | -0.107 | +| learning_rate | 0.000189 | +| loss | -0.0652 | +| n_updates | 1116 | +| policy_gradient_loss | -0.0338 | +| value_loss | 0.000229 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.22 | +| time/ | | +| fps | 1323 | +| iterations | 281 | +| time_elapsed | 434 | +| total_timesteps | 575488 | +| train/ | | +| approx_kl | 0.030650374 | +| clip_fraction | 0.365 | +| clip_range | 0.143 | +| entropy_loss | -7.22 | +| explained_variance | -0.0793 | +| learning_rate | 0.000189 | +| loss | -0.0583 | +| n_updates | 1120 | +| policy_gradient_loss | -0.0317 | +| value_loss | 0.000177 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.217 | +| time/ | | +| fps | 1323 | +| iterations | 282 | +| time_elapsed | 436 | +| total_timesteps | 577536 | +| train/ | | +| approx_kl | 0.037860014 | +| clip_fraction | 0.368 | +| clip_range | 0.143 | +| entropy_loss | -7.34 | +| explained_variance | 0.0351 | +| learning_rate | 0.000189 | +| loss | -0.0628 | +| n_updates | 1124 | +| policy_gradient_loss | -0.0345 | +| value_loss | 0.000178 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.217 | +| time/ | | +| fps | 1323 | +| iterations | 283 | +| time_elapsed | 437 | +| total_timesteps | 579584 | +| train/ | | +| approx_kl | 0.036510475 | +| clip_fraction | 0.39 | +| clip_range | 0.143 | +| entropy_loss | -7.34 | +| explained_variance | -0.127 | +| learning_rate | 0.000189 | +| loss | -0.0594 | +| n_updates | 1128 | +| policy_gradient_loss | -0.0315 | +| value_loss | 0.000175 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.219 | +| time/ | | +| fps | 1323 | +| iterations | 284 | +| time_elapsed | 439 | +| total_timesteps | 581632 | +| train/ | | +| approx_kl | 0.034863546 | +| clip_fraction | 0.371 | +| clip_range | 0.143 | +| entropy_loss | -7.34 | +| explained_variance | -0.232 | +| learning_rate | 0.000189 | +| loss | -0.0636 | +| n_updates | 1132 | +| policy_gradient_loss | -0.0344 | +| value_loss | 0.000106 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.22 | +| time/ | | +| fps | 1323 | +| iterations | 285 | +| time_elapsed | 441 | +| total_timesteps | 583680 | +| train/ | | +| approx_kl | 0.037011743 | +| clip_fraction | 0.363 | +| clip_range | 0.143 | +| entropy_loss | -7.31 | +| explained_variance | -0.0508 | +| learning_rate | 0.000188 | +| loss | -0.0499 | +| n_updates | 1136 | +| policy_gradient_loss | -0.0256 | +| value_loss | 0.000189 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.217 | +| time/ | | +| fps | 1323 | +| iterations | 286 | +| time_elapsed | 442 | +| total_timesteps | 585728 | +| train/ | | +| approx_kl | 0.036959447 | +| clip_fraction | 0.373 | +| clip_range | 0.143 | +| entropy_loss | -7.36 | +| explained_variance | -0.235 | +| learning_rate | 0.000188 | +| loss | -0.0543 | +| n_updates | 1140 | +| policy_gradient_loss | -0.0341 | +| value_loss | 9.79e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.218 | +| time/ | | +| fps | 1323 | +| iterations | 287 | +| time_elapsed | 444 | +| total_timesteps | 587776 | +| train/ | | +| approx_kl | 0.03854119 | +| clip_fraction | 0.387 | +| clip_range | 0.143 | +| entropy_loss | -7.27 | +| explained_variance | -0.0584 | +| learning_rate | 0.000188 | +| loss | -0.0547 | +| n_updates | 1144 | +| policy_gradient_loss | -0.0283 | +| value_loss | 0.000138 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.218 | +| time/ | | +| fps | 1323 | +| iterations | 288 | +| time_elapsed | 445 | +| total_timesteps | 589824 | +| train/ | | +| approx_kl | 0.040844716 | +| clip_fraction | 0.402 | +| clip_range | 0.143 | +| entropy_loss | -7.33 | +| explained_variance | -0.126 | +| learning_rate | 0.000188 | +| loss | -0.0512 | +| n_updates | 1148 | +| policy_gradient_loss | -0.0327 | +| value_loss | 0.000159 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.219 | +| time/ | | +| fps | 1323 | +| iterations | 289 | +| time_elapsed | 447 | +| total_timesteps | 591872 | +| train/ | | +| approx_kl | 0.036591306 | +| clip_fraction | 0.371 | +| clip_range | 0.143 | +| entropy_loss | -7.44 | +| explained_variance | -0.165 | +| learning_rate | 0.000188 | +| loss | -0.0559 | +| n_updates | 1152 | +| policy_gradient_loss | -0.0325 | +| value_loss | 0.0002 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.214 | +| time/ | | +| fps | 1323 | +| iterations | 290 | +| time_elapsed | 448 | +| total_timesteps | 593920 | +| train/ | | +| approx_kl | 0.03837025 | +| clip_fraction | 0.42 | +| clip_range | 0.143 | +| entropy_loss | -7.42 | +| explained_variance | -0.176 | +| learning_rate | 0.000188 | +| loss | -0.065 | +| n_updates | 1156 | +| policy_gradient_loss | -0.0362 | +| value_loss | 9.76e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.212 | +| time/ | | +| fps | 1323 | +| iterations | 291 | +| time_elapsed | 450 | +| total_timesteps | 595968 | +| train/ | | +| approx_kl | 0.033483196 | +| clip_fraction | 0.386 | +| clip_range | 0.143 | +| entropy_loss | -7.39 | +| explained_variance | -0.0458 | +| learning_rate | 0.000188 | +| loss | -0.0594 | +| n_updates | 1160 | +| policy_gradient_loss | -0.0318 | +| value_loss | 0.000169 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.214 | +| time/ | | +| fps | 1323 | +| iterations | 292 | +| time_elapsed | 451 | +| total_timesteps | 598016 | +| train/ | | +| approx_kl | 0.032416884 | +| clip_fraction | 0.371 | +| clip_range | 0.143 | +| entropy_loss | -7.24 | +| explained_variance | -0.152 | +| learning_rate | 0.000188 | +| loss | -0.0482 | +| n_updates | 1164 | +| policy_gradient_loss | -0.0305 | +| value_loss | 0.000178 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.213 | +| time/ | | +| fps | 1323 | +| iterations | 293 | +| time_elapsed | 453 | +| total_timesteps | 600064 | +| train/ | | +| approx_kl | 0.041186567 | +| clip_fraction | 0.395 | +| clip_range | 0.143 | +| entropy_loss | -7.3 | +| explained_variance | -0.0494 | +| learning_rate | 0.000188 | +| loss | -0.0588 | +| n_updates | 1168 | +| policy_gradient_loss | -0.0348 | +| value_loss | 0.000146 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.208 | +| time/ | | +| fps | 1323 | +| iterations | 294 | +| time_elapsed | 454 | +| total_timesteps | 602112 | +| train/ | | +| approx_kl | 0.040835746 | +| clip_fraction | 0.386 | +| clip_range | 0.142 | +| entropy_loss | -7.46 | +| explained_variance | -0.14 | +| learning_rate | 0.000188 | +| loss | -0.0482 | +| n_updates | 1172 | +| policy_gradient_loss | -0.0298 | +| value_loss | 0.000125 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.215 | +| time/ | | +| fps | 1323 | +| iterations | 295 | +| time_elapsed | 456 | +| total_timesteps | 604160 | +| train/ | | +| approx_kl | 0.04018998 | +| clip_fraction | 0.377 | +| clip_range | 0.142 | +| entropy_loss | -7.41 | +| explained_variance | 0.0154 | +| learning_rate | 0.000188 | +| loss | -0.0548 | +| n_updates | 1176 | +| policy_gradient_loss | -0.0297 | +| value_loss | 0.000186 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.216 | +| time/ | | +| fps | 1323 | +| iterations | 296 | +| time_elapsed | 458 | +| total_timesteps | 606208 | +| train/ | | +| approx_kl | 0.037378374 | +| clip_fraction | 0.369 | +| clip_range | 0.142 | +| entropy_loss | -7.46 | +| explained_variance | -0.103 | +| learning_rate | 0.000188 | +| loss | -0.0513 | +| n_updates | 1180 | +| policy_gradient_loss | -0.027 | +| value_loss | 0.000179 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.217 | +| time/ | | +| fps | 1323 | +| iterations | 297 | +| time_elapsed | 459 | +| total_timesteps | 608256 | +| train/ | | +| approx_kl | 0.036078423 | +| clip_fraction | 0.361 | +| clip_range | 0.142 | +| entropy_loss | -7.49 | +| explained_variance | -0.336 | +| learning_rate | 0.000188 | +| loss | -0.0633 | +| n_updates | 1184 | +| policy_gradient_loss | -0.0336 | +| value_loss | 0.000167 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.217 | +| time/ | | +| fps | 1323 | +| iterations | 298 | +| time_elapsed | 461 | +| total_timesteps | 610304 | +| train/ | | +| approx_kl | 0.039871715 | +| clip_fraction | 0.414 | +| clip_range | 0.142 | +| entropy_loss | -7.33 | +| explained_variance | -0.0444 | +| learning_rate | 0.000188 | +| loss | -0.0498 | +| n_updates | 1188 | +| policy_gradient_loss | -0.0286 | +| value_loss | 0.000141 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.217 | +| time/ | | +| fps | 1323 | +| iterations | 299 | +| time_elapsed | 462 | +| total_timesteps | 612352 | +| train/ | | +| approx_kl | 0.02987858 | +| clip_fraction | 0.341 | +| clip_range | 0.142 | +| entropy_loss | -7.46 | +| explained_variance | -0.0506 | +| learning_rate | 0.000188 | +| loss | -0.0529 | +| n_updates | 1192 | +| policy_gradient_loss | -0.0311 | +| value_loss | 0.000161 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.217 | +| time/ | | +| fps | 1323 | +| iterations | 300 | +| time_elapsed | 464 | +| total_timesteps | 614400 | +| train/ | | +| approx_kl | 0.031270552 | +| clip_fraction | 0.345 | +| clip_range | 0.142 | +| entropy_loss | -7.49 | +| explained_variance | -0.0531 | +| learning_rate | 0.000188 | +| loss | -0.0515 | +| n_updates | 1196 | +| policy_gradient_loss | -0.0319 | +| value_loss | 0.000146 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.222 | +| time/ | | +| fps | 1323 | +| iterations | 301 | +| time_elapsed | 465 | +| total_timesteps | 616448 | +| train/ | | +| approx_kl | 0.03514859 | +| clip_fraction | 0.357 | +| clip_range | 0.142 | +| entropy_loss | -7.45 | +| explained_variance | -0.121 | +| learning_rate | 0.000188 | +| loss | -0.0488 | +| n_updates | 1200 | +| policy_gradient_loss | -0.0312 | +| value_loss | 0.000161 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.222 | +| time/ | | +| fps | 1323 | +| iterations | 302 | +| time_elapsed | 467 | +| total_timesteps | 618496 | +| train/ | | +| approx_kl | 0.03360046 | +| clip_fraction | 0.362 | +| clip_range | 0.142 | +| entropy_loss | -7.45 | +| explained_variance | -0.0621 | +| learning_rate | 0.000188 | +| loss | -0.0514 | +| n_updates | 1204 | +| policy_gradient_loss | -0.0296 | +| value_loss | 0.000158 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.228 | +| time/ | | +| fps | 1323 | +| iterations | 303 | +| time_elapsed | 468 | +| total_timesteps | 620544 | +| train/ | | +| approx_kl | 0.029308598 | +| clip_fraction | 0.329 | +| clip_range | 0.142 | +| entropy_loss | -7.59 | +| explained_variance | 0.0577 | +| learning_rate | 0.000188 | +| loss | -0.0529 | +| n_updates | 1208 | +| policy_gradient_loss | -0.0272 | +| value_loss | 0.000227 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.23 | +| time/ | | +| fps | 1323 | +| iterations | 304 | +| time_elapsed | 470 | +| total_timesteps | 622592 | +| train/ | | +| approx_kl | 0.028337382 | +| clip_fraction | 0.315 | +| clip_range | 0.142 | +| entropy_loss | -7.69 | +| explained_variance | 0.0635 | +| learning_rate | 0.000188 | +| loss | -0.05 | +| n_updates | 1212 | +| policy_gradient_loss | -0.0325 | +| value_loss | 0.000236 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.233 | +| time/ | | +| fps | 1323 | +| iterations | 305 | +| time_elapsed | 471 | +| total_timesteps | 624640 | +| train/ | | +| approx_kl | 0.02607742 | +| clip_fraction | 0.349 | +| clip_range | 0.142 | +| entropy_loss | -7.6 | +| explained_variance | -0.25 | +| learning_rate | 0.000188 | +| loss | -0.0549 | +| n_updates | 1216 | +| policy_gradient_loss | -0.0356 | +| value_loss | 0.000133 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.226 | +| time/ | | +| fps | 1323 | +| iterations | 306 | +| time_elapsed | 473 | +| total_timesteps | 626688 | +| train/ | | +| approx_kl | 0.028892146 | +| clip_fraction | 0.331 | +| clip_range | 0.142 | +| entropy_loss | -7.55 | +| explained_variance | -0.0585 | +| learning_rate | 0.000188 | +| loss | -0.0514 | +| n_updates | 1220 | +| policy_gradient_loss | -0.0305 | +| value_loss | 0.00019 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.235 | +| time/ | | +| fps | 1323 | +| iterations | 307 | +| time_elapsed | 474 | +| total_timesteps | 628736 | +| train/ | | +| approx_kl | 0.030479461 | +| clip_fraction | 0.336 | +| clip_range | 0.142 | +| entropy_loss | -7.63 | +| explained_variance | -0.137 | +| learning_rate | 0.000188 | +| loss | -0.052 | +| n_updates | 1224 | +| policy_gradient_loss | -0.0335 | +| value_loss | 0.000215 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.233 | +| time/ | | +| fps | 1323 | +| iterations | 308 | +| time_elapsed | 476 | +| total_timesteps | 630784 | +| train/ | | +| approx_kl | 0.037391573 | +| clip_fraction | 0.361 | +| clip_range | 0.142 | +| entropy_loss | -7.68 | +| explained_variance | -0.114 | +| learning_rate | 0.000188 | +| loss | -0.0643 | +| n_updates | 1228 | +| policy_gradient_loss | -0.0329 | +| value_loss | 0.000312 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.233 | +| time/ | | +| fps | 1323 | +| iterations | 309 | +| time_elapsed | 477 | +| total_timesteps | 632832 | +| train/ | | +| approx_kl | 0.031680293 | +| clip_fraction | 0.358 | +| clip_range | 0.142 | +| entropy_loss | -7.52 | +| explained_variance | -0.0306 | +| learning_rate | 0.000188 | +| loss | -0.0589 | +| n_updates | 1232 | +| policy_gradient_loss | -0.0328 | +| value_loss | 0.000236 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.236 | +| time/ | | +| fps | 1323 | +| iterations | 310 | +| time_elapsed | 479 | +| total_timesteps | 634880 | +| train/ | | +| approx_kl | 0.030396648 | +| clip_fraction | 0.364 | +| clip_range | 0.142 | +| entropy_loss | -7.55 | +| explained_variance | -0.0997 | +| learning_rate | 0.000187 | +| loss | -0.0678 | +| n_updates | 1236 | +| policy_gradient_loss | -0.0354 | +| value_loss | 0.000106 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.239 | +| time/ | | +| fps | 1323 | +| iterations | 311 | +| time_elapsed | 481 | +| total_timesteps | 636928 | +| train/ | | +| approx_kl | 0.027016943 | +| clip_fraction | 0.312 | +| clip_range | 0.142 | +| entropy_loss | -7.66 | +| explained_variance | 0.0244 | +| learning_rate | 0.000187 | +| loss | -0.0462 | +| n_updates | 1240 | +| policy_gradient_loss | -0.0267 | +| value_loss | 0.000243 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.233 | +| time/ | | +| fps | 1323 | +| iterations | 312 | +| time_elapsed | 482 | +| total_timesteps | 638976 | +| train/ | | +| approx_kl | 0.03574348 | +| clip_fraction | 0.341 | +| clip_range | 0.142 | +| entropy_loss | -7.6 | +| explained_variance | 0.0429 | +| learning_rate | 0.000187 | +| loss | -0.0492 | +| n_updates | 1244 | +| policy_gradient_loss | -0.0334 | +| value_loss | 0.000277 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.237 | +| time/ | | +| fps | 1323 | +| iterations | 313 | +| time_elapsed | 484 | +| total_timesteps | 641024 | +| train/ | | +| approx_kl | 0.027746525 | +| clip_fraction | 0.359 | +| clip_range | 0.142 | +| entropy_loss | -7.57 | +| explained_variance | -0.133 | +| learning_rate | 0.000187 | +| loss | -0.0606 | +| n_updates | 1248 | +| policy_gradient_loss | -0.0341 | +| value_loss | 0.00012 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.241 | +| time/ | | +| fps | 1323 | +| iterations | 314 | +| time_elapsed | 485 | +| total_timesteps | 643072 | +| train/ | | +| approx_kl | 0.030675072 | +| clip_fraction | 0.381 | +| clip_range | 0.142 | +| entropy_loss | -7.48 | +| explained_variance | -0.132 | +| learning_rate | 0.000187 | +| loss | -0.0449 | +| n_updates | 1252 | +| policy_gradient_loss | -0.0265 | +| value_loss | 0.00025 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.241 | +| time/ | | +| fps | 1323 | +| iterations | 315 | +| time_elapsed | 487 | +| total_timesteps | 645120 | +| train/ | | +| approx_kl | 0.031737797 | +| clip_fraction | 0.362 | +| clip_range | 0.142 | +| entropy_loss | -7.59 | +| explained_variance | -0.125 | +| learning_rate | 0.000187 | +| loss | -0.0496 | +| n_updates | 1256 | +| policy_gradient_loss | -0.0276 | +| value_loss | 0.000155 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.235 | +| time/ | | +| fps | 1323 | +| iterations | 316 | +| time_elapsed | 488 | +| total_timesteps | 647168 | +| train/ | | +| approx_kl | 0.03135874 | +| clip_fraction | 0.368 | +| clip_range | 0.142 | +| entropy_loss | -7.63 | +| explained_variance | -0.082 | +| learning_rate | 0.000187 | +| loss | -0.0646 | +| n_updates | 1260 | +| policy_gradient_loss | -0.0331 | +| value_loss | 0.000139 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.242 | +| time/ | | +| fps | 1323 | +| iterations | 317 | +| time_elapsed | 490 | +| total_timesteps | 649216 | +| train/ | | +| approx_kl | 0.032458734 | +| clip_fraction | 0.364 | +| clip_range | 0.142 | +| entropy_loss | -7.49 | +| explained_variance | -0.235 | +| learning_rate | 0.000187 | +| loss | -0.0582 | +| n_updates | 1264 | +| policy_gradient_loss | -0.0332 | +| value_loss | 0.00015 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.242 | +| time/ | | +| fps | 1323 | +| iterations | 318 | +| time_elapsed | 492 | +| total_timesteps | 651264 | +| train/ | | +| approx_kl | 0.04007291 | +| clip_fraction | 0.35 | +| clip_range | 0.142 | +| entropy_loss | -7.6 | +| explained_variance | -0.0489 | +| learning_rate | 0.000187 | +| loss | -0.0599 | +| n_updates | 1268 | +| policy_gradient_loss | -0.0334 | +| value_loss | 0.000292 | +---------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.242 | +| time/ | | +| fps | 1323 | +| iterations | 319 | +| time_elapsed | 493 | +| total_timesteps | 653312 | +| train/ | | +| approx_kl | 0.0335548 | +| clip_fraction | 0.369 | +| clip_range | 0.142 | +| entropy_loss | -7.55 | +| explained_variance | -0.292 | +| learning_rate | 0.000187 | +| loss | -0.066 | +| n_updates | 1272 | +| policy_gradient_loss | -0.0361 | +| value_loss | 0.000158 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.233 | +| time/ | | +| fps | 1323 | +| iterations | 320 | +| time_elapsed | 495 | +| total_timesteps | 655360 | +| train/ | | +| approx_kl | 0.032563668 | +| clip_fraction | 0.348 | +| clip_range | 0.142 | +| entropy_loss | -7.65 | +| explained_variance | -0.00485 | +| learning_rate | 0.000187 | +| loss | -0.0626 | +| n_updates | 1276 | +| policy_gradient_loss | -0.0341 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.233 | +| time/ | | +| fps | 1323 | +| iterations | 321 | +| time_elapsed | 496 | +| total_timesteps | 657408 | +| train/ | | +| approx_kl | 0.031881634 | +| clip_fraction | 0.339 | +| clip_range | 0.142 | +| entropy_loss | -7.68 | +| explained_variance | -0.0948 | +| learning_rate | 0.000187 | +| loss | -0.0558 | +| n_updates | 1280 | +| policy_gradient_loss | -0.0272 | +| value_loss | 9.23e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.235 | +| time/ | | +| fps | 1323 | +| iterations | 322 | +| time_elapsed | 498 | +| total_timesteps | 659456 | +| train/ | | +| approx_kl | 0.032502122 | +| clip_fraction | 0.375 | +| clip_range | 0.142 | +| entropy_loss | -7.69 | +| explained_variance | -0.191 | +| learning_rate | 0.000187 | +| loss | -0.0518 | +| n_updates | 1284 | +| policy_gradient_loss | -0.0354 | +| value_loss | 7.89e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.236 | +| time/ | | +| fps | 1323 | +| iterations | 323 | +| time_elapsed | 499 | +| total_timesteps | 661504 | +| train/ | | +| approx_kl | 0.035404563 | +| clip_fraction | 0.355 | +| clip_range | 0.142 | +| entropy_loss | -7.67 | +| explained_variance | -0.0751 | +| learning_rate | 0.000187 | +| loss | -0.0526 | +| n_updates | 1288 | +| policy_gradient_loss | -0.0311 | +| value_loss | 0.000133 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.233 | +| time/ | | +| fps | 1323 | +| iterations | 324 | +| time_elapsed | 501 | +| total_timesteps | 663552 | +| train/ | | +| approx_kl | 0.029201616 | +| clip_fraction | 0.298 | +| clip_range | 0.142 | +| entropy_loss | -7.68 | +| explained_variance | -0.112 | +| learning_rate | 0.000187 | +| loss | -0.0513 | +| n_updates | 1292 | +| policy_gradient_loss | -0.0306 | +| value_loss | 0.000285 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.235 | +| time/ | | +| fps | 1323 | +| iterations | 325 | +| time_elapsed | 502 | +| total_timesteps | 665600 | +| train/ | | +| approx_kl | 0.033813544 | +| clip_fraction | 0.324 | +| clip_range | 0.142 | +| entropy_loss | -7.62 | +| explained_variance | -0.0749 | +| learning_rate | 0.000187 | +| loss | -0.0573 | +| n_updates | 1296 | +| policy_gradient_loss | -0.0383 | +| value_loss | 0.000159 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.241 | +| time/ | | +| fps | 1323 | +| iterations | 326 | +| time_elapsed | 504 | +| total_timesteps | 667648 | +| train/ | | +| approx_kl | 0.028224513 | +| clip_fraction | 0.36 | +| clip_range | 0.142 | +| entropy_loss | -7.64 | +| explained_variance | -0.125 | +| learning_rate | 0.000187 | +| loss | -0.0513 | +| n_updates | 1300 | +| policy_gradient_loss | -0.0293 | +| value_loss | 0.000168 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.241 | +| time/ | | +| fps | 1323 | +| iterations | 327 | +| time_elapsed | 505 | +| total_timesteps | 669696 | +| train/ | | +| approx_kl | 0.027970113 | +| clip_fraction | 0.312 | +| clip_range | 0.142 | +| entropy_loss | -7.63 | +| explained_variance | -0.0437 | +| learning_rate | 0.000187 | +| loss | -0.057 | +| n_updates | 1304 | +| policy_gradient_loss | -0.0312 | +| value_loss | 0.000343 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.241 | +| time/ | | +| fps | 1323 | +| iterations | 328 | +| time_elapsed | 507 | +| total_timesteps | 671744 | +| train/ | | +| approx_kl | 0.030631263 | +| clip_fraction | 0.352 | +| clip_range | 0.142 | +| entropy_loss | -7.63 | +| explained_variance | -0.205 | +| learning_rate | 0.000187 | +| loss | -0.063 | +| n_updates | 1308 | +| policy_gradient_loss | -0.037 | +| value_loss | 0.000147 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.239 | +| time/ | | +| fps | 1323 | +| iterations | 329 | +| time_elapsed | 509 | +| total_timesteps | 673792 | +| train/ | | +| approx_kl | 0.028649766 | +| clip_fraction | 0.346 | +| clip_range | 0.142 | +| entropy_loss | -7.61 | +| explained_variance | -0.123 | +| learning_rate | 0.000187 | +| loss | -0.0664 | +| n_updates | 1312 | +| policy_gradient_loss | -0.036 | +| value_loss | 0.000175 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.237 | +| time/ | | +| fps | 1323 | +| iterations | 330 | +| time_elapsed | 510 | +| total_timesteps | 675840 | +| train/ | | +| approx_kl | 0.027568184 | +| clip_fraction | 0.361 | +| clip_range | 0.142 | +| entropy_loss | -7.62 | +| explained_variance | -0.359 | +| learning_rate | 0.000187 | +| loss | -0.0739 | +| n_updates | 1316 | +| policy_gradient_loss | -0.0363 | +| value_loss | 0.00014 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.243 | +| time/ | | +| fps | 1323 | +| iterations | 331 | +| time_elapsed | 512 | +| total_timesteps | 677888 | +| train/ | | +| approx_kl | 0.025302883 | +| clip_fraction | 0.316 | +| clip_range | 0.142 | +| entropy_loss | -7.64 | +| explained_variance | -0.0761 | +| learning_rate | 0.000187 | +| loss | -0.0529 | +| n_updates | 1320 | +| policy_gradient_loss | -0.0318 | +| value_loss | 0.000149 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.241 | +| time/ | | +| fps | 1323 | +| iterations | 332 | +| time_elapsed | 513 | +| total_timesteps | 679936 | +| train/ | | +| approx_kl | 0.029116262 | +| clip_fraction | 0.331 | +| clip_range | 0.142 | +| entropy_loss | -7.54 | +| explained_variance | 0.0253 | +| learning_rate | 0.000187 | +| loss | -0.0439 | +| n_updates | 1324 | +| policy_gradient_loss | -0.0298 | +| value_loss | 0.000158 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.245 | +| time/ | | +| fps | 1323 | +| iterations | 333 | +| time_elapsed | 515 | +| total_timesteps | 681984 | +| train/ | | +| approx_kl | 0.030844936 | +| clip_fraction | 0.349 | +| clip_range | 0.142 | +| entropy_loss | -7.57 | +| explained_variance | -0.157 | +| learning_rate | 0.000187 | +| loss | -0.0657 | +| n_updates | 1328 | +| policy_gradient_loss | -0.0363 | +| value_loss | 0.0002 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.243 | +| time/ | | +| fps | 1323 | +| iterations | 334 | +| time_elapsed | 516 | +| total_timesteps | 684032 | +| train/ | | +| approx_kl | 0.033364013 | +| clip_fraction | 0.333 | +| clip_range | 0.141 | +| entropy_loss | -7.51 | +| explained_variance | -0.0121 | +| learning_rate | 0.000186 | +| loss | -0.0519 | +| n_updates | 1332 | +| policy_gradient_loss | -0.0326 | +| value_loss | 0.00024 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.243 | +| time/ | | +| fps | 1323 | +| iterations | 335 | +| time_elapsed | 518 | +| total_timesteps | 686080 | +| train/ | | +| approx_kl | 0.032202616 | +| clip_fraction | 0.338 | +| clip_range | 0.141 | +| entropy_loss | -7.49 | +| explained_variance | -0.0678 | +| learning_rate | 0.000186 | +| loss | -0.0647 | +| n_updates | 1336 | +| policy_gradient_loss | -0.034 | +| value_loss | 0.000182 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.243 | +| time/ | | +| fps | 1323 | +| iterations | 336 | +| time_elapsed | 519 | +| total_timesteps | 688128 | +| train/ | | +| approx_kl | 0.033856437 | +| clip_fraction | 0.372 | +| clip_range | 0.141 | +| entropy_loss | -7.69 | +| explained_variance | -0.321 | +| learning_rate | 0.000186 | +| loss | -0.0687 | +| n_updates | 1340 | +| policy_gradient_loss | -0.0399 | +| value_loss | 9.87e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.243 | +| time/ | | +| fps | 1323 | +| iterations | 337 | +| time_elapsed | 521 | +| total_timesteps | 690176 | +| train/ | | +| approx_kl | 0.030740088 | +| clip_fraction | 0.362 | +| clip_range | 0.141 | +| entropy_loss | -7.66 | +| explained_variance | -0.172 | +| learning_rate | 0.000186 | +| loss | -0.0484 | +| n_updates | 1344 | +| policy_gradient_loss | -0.0288 | +| value_loss | 0.000108 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.237 | +| time/ | | +| fps | 1323 | +| iterations | 338 | +| time_elapsed | 522 | +| total_timesteps | 692224 | +| train/ | | +| approx_kl | 0.031920314 | +| clip_fraction | 0.333 | +| clip_range | 0.141 | +| entropy_loss | -7.64 | +| explained_variance | -0.0168 | +| learning_rate | 0.000186 | +| loss | -0.0621 | +| n_updates | 1348 | +| policy_gradient_loss | -0.035 | +| value_loss | 0.000182 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.243 | +| time/ | | +| fps | 1323 | +| iterations | 339 | +| time_elapsed | 524 | +| total_timesteps | 694272 | +| train/ | | +| approx_kl | 0.035042897 | +| clip_fraction | 0.363 | +| clip_range | 0.141 | +| entropy_loss | -7.67 | +| explained_variance | -0.0748 | +| learning_rate | 0.000186 | +| loss | -0.0641 | +| n_updates | 1352 | +| policy_gradient_loss | -0.0334 | +| value_loss | 0.000161 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.245 | +| time/ | | +| fps | 1323 | +| iterations | 340 | +| time_elapsed | 526 | +| total_timesteps | 696320 | +| train/ | | +| approx_kl | 0.02423569 | +| clip_fraction | 0.346 | +| clip_range | 0.141 | +| entropy_loss | -7.64 | +| explained_variance | -0.111 | +| learning_rate | 0.000186 | +| loss | -0.0589 | +| n_updates | 1356 | +| policy_gradient_loss | -0.0244 | +| value_loss | 0.000234 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.246 | +| time/ | | +| fps | 1323 | +| iterations | 341 | +| time_elapsed | 527 | +| total_timesteps | 698368 | +| train/ | | +| approx_kl | 0.03192813 | +| clip_fraction | 0.37 | +| clip_range | 0.141 | +| entropy_loss | -7.58 | +| explained_variance | -0.397 | +| learning_rate | 0.000186 | +| loss | -0.0677 | +| n_updates | 1360 | +| policy_gradient_loss | -0.0386 | +| value_loss | 0.000121 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.244 | +| time/ | | +| fps | 1323 | +| iterations | 342 | +| time_elapsed | 529 | +| total_timesteps | 700416 | +| train/ | | +| approx_kl | 0.03320563 | +| clip_fraction | 0.366 | +| clip_range | 0.141 | +| entropy_loss | -7.58 | +| explained_variance | -0.153 | +| learning_rate | 0.000186 | +| loss | -0.0534 | +| n_updates | 1364 | +| policy_gradient_loss | -0.0342 | +| value_loss | 0.000135 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.242 | +| time/ | | +| fps | 1323 | +| iterations | 343 | +| time_elapsed | 530 | +| total_timesteps | 702464 | +| train/ | | +| approx_kl | 0.036944058 | +| clip_fraction | 0.378 | +| clip_range | 0.141 | +| entropy_loss | -7.49 | +| explained_variance | -0.0789 | +| learning_rate | 0.000186 | +| loss | -0.0519 | +| n_updates | 1368 | +| policy_gradient_loss | -0.0342 | +| value_loss | 0.000164 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.246 | +| time/ | | +| fps | 1323 | +| iterations | 344 | +| time_elapsed | 532 | +| total_timesteps | 704512 | +| train/ | | +| approx_kl | 0.03775733 | +| clip_fraction | 0.37 | +| clip_range | 0.141 | +| entropy_loss | -7.47 | +| explained_variance | 0.0657 | +| learning_rate | 0.000186 | +| loss | -0.0624 | +| n_updates | 1372 | +| policy_gradient_loss | -0.0355 | +| value_loss | 9.84e-05 | +---------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.246 | +| time/ | | +| fps | 1323 | +| iterations | 345 | +| time_elapsed | 533 | +| total_timesteps | 706560 | +| train/ | | +| approx_kl | 0.039147 | +| clip_fraction | 0.377 | +| clip_range | 0.141 | +| entropy_loss | -7.47 | +| explained_variance | -0.0913 | +| learning_rate | 0.000186 | +| loss | -0.0601 | +| n_updates | 1376 | +| policy_gradient_loss | -0.0384 | +| value_loss | 9.1e-05 | +-------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.248 | +| time/ | | +| fps | 1323 | +| iterations | 346 | +| time_elapsed | 535 | +| total_timesteps | 708608 | +| train/ | | +| approx_kl | 0.037046008 | +| clip_fraction | 0.373 | +| clip_range | 0.141 | +| entropy_loss | -7.52 | +| explained_variance | -0.0615 | +| learning_rate | 0.000186 | +| loss | -0.0484 | +| n_updates | 1380 | +| policy_gradient_loss | -0.0345 | +| value_loss | 0.000127 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.243 | +| time/ | | +| fps | 1323 | +| iterations | 347 | +| time_elapsed | 536 | +| total_timesteps | 710656 | +| train/ | | +| approx_kl | 0.03170659 | +| clip_fraction | 0.359 | +| clip_range | 0.141 | +| entropy_loss | -7.4 | +| explained_variance | -0.0344 | +| learning_rate | 0.000186 | +| loss | -0.0538 | +| n_updates | 1384 | +| policy_gradient_loss | -0.034 | +| value_loss | 0.000166 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.245 | +| time/ | | +| fps | 1323 | +| iterations | 348 | +| time_elapsed | 538 | +| total_timesteps | 712704 | +| train/ | | +| approx_kl | 0.03597741 | +| clip_fraction | 0.361 | +| clip_range | 0.141 | +| entropy_loss | -7.5 | +| explained_variance | -0.0731 | +| learning_rate | 0.000186 | +| loss | -0.0556 | +| n_updates | 1388 | +| policy_gradient_loss | -0.0348 | +| value_loss | 0.000127 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.245 | +| time/ | | +| fps | 1323 | +| iterations | 349 | +| time_elapsed | 539 | +| total_timesteps | 714752 | +| train/ | | +| approx_kl | 0.032237705 | +| clip_fraction | 0.352 | +| clip_range | 0.141 | +| entropy_loss | -7.55 | +| explained_variance | -0.0882 | +| learning_rate | 0.000186 | +| loss | -0.0517 | +| n_updates | 1392 | +| policy_gradient_loss | -0.0316 | +| value_loss | 0.000234 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.237 | +| time/ | | +| fps | 1323 | +| iterations | 350 | +| time_elapsed | 541 | +| total_timesteps | 716800 | +| train/ | | +| approx_kl | 0.031030837 | +| clip_fraction | 0.371 | +| clip_range | 0.141 | +| entropy_loss | -7.46 | +| explained_variance | -0.208 | +| learning_rate | 0.000186 | +| loss | -0.0623 | +| n_updates | 1396 | +| policy_gradient_loss | -0.0353 | +| value_loss | 0.000161 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.237 | +| time/ | | +| fps | 1323 | +| iterations | 351 | +| time_elapsed | 542 | +| total_timesteps | 718848 | +| train/ | | +| approx_kl | 0.033411577 | +| clip_fraction | 0.372 | +| clip_range | 0.141 | +| entropy_loss | -7.38 | +| explained_variance | -0.17 | +| learning_rate | 0.000186 | +| loss | -0.062 | +| n_updates | 1400 | +| policy_gradient_loss | -0.037 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.237 | +| time/ | | +| fps | 1323 | +| iterations | 352 | +| time_elapsed | 544 | +| total_timesteps | 720896 | +| train/ | | +| approx_kl | 0.033053808 | +| clip_fraction | 0.352 | +| clip_range | 0.141 | +| entropy_loss | -7.44 | +| explained_variance | -0.0563 | +| learning_rate | 0.000186 | +| loss | -0.0717 | +| n_updates | 1404 | +| policy_gradient_loss | -0.0384 | +| value_loss | 6.09e-05 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.24 | +| time/ | | +| fps | 1323 | +| iterations | 353 | +| time_elapsed | 546 | +| total_timesteps | 722944 | +| train/ | | +| approx_kl | 0.0343548 | +| clip_fraction | 0.383 | +| clip_range | 0.141 | +| entropy_loss | -7.39 | +| explained_variance | -0.159 | +| learning_rate | 0.000186 | +| loss | -0.0532 | +| n_updates | 1408 | +| policy_gradient_loss | -0.0318 | +| value_loss | 0.000104 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.237 | +| time/ | | +| fps | 1324 | +| iterations | 354 | +| time_elapsed | 547 | +| total_timesteps | 724992 | +| train/ | | +| approx_kl | 0.041670963 | +| clip_fraction | 0.359 | +| clip_range | 0.141 | +| entropy_loss | -7.38 | +| explained_variance | -0.0573 | +| learning_rate | 0.000186 | +| loss | -0.0609 | +| n_updates | 1412 | +| policy_gradient_loss | -0.0307 | +| value_loss | 0.000264 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.23 | +| time/ | | +| fps | 1324 | +| iterations | 355 | +| time_elapsed | 549 | +| total_timesteps | 727040 | +| train/ | | +| approx_kl | 0.036593508 | +| clip_fraction | 0.377 | +| clip_range | 0.141 | +| entropy_loss | -7.33 | +| explained_variance | -0.56 | +| learning_rate | 0.000186 | +| loss | -0.074 | +| n_updates | 1416 | +| policy_gradient_loss | -0.042 | +| value_loss | 6.57e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.233 | +| time/ | | +| fps | 1324 | +| iterations | 356 | +| time_elapsed | 550 | +| total_timesteps | 729088 | +| train/ | | +| approx_kl | 0.038843703 | +| clip_fraction | 0.39 | +| clip_range | 0.141 | +| entropy_loss | -7.4 | +| explained_variance | -0.0884 | +| learning_rate | 0.000186 | +| loss | -0.0499 | +| n_updates | 1420 | +| policy_gradient_loss | -0.03 | +| value_loss | 0.000248 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.233 | +| time/ | | +| fps | 1324 | +| iterations | 357 | +| time_elapsed | 552 | +| total_timesteps | 731136 | +| train/ | | +| approx_kl | 0.03662137 | +| clip_fraction | 0.35 | +| clip_range | 0.141 | +| entropy_loss | -7.36 | +| explained_variance | -0.265 | +| learning_rate | 0.000186 | +| loss | -0.0614 | +| n_updates | 1424 | +| policy_gradient_loss | -0.0334 | +| value_loss | 0.000126 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.24 | +| time/ | | +| fps | 1324 | +| iterations | 358 | +| time_elapsed | 553 | +| total_timesteps | 733184 | +| train/ | | +| approx_kl | 0.037136808 | +| clip_fraction | 0.372 | +| clip_range | 0.141 | +| entropy_loss | -7.47 | +| explained_variance | -0.13 | +| learning_rate | 0.000186 | +| loss | -0.0564 | +| n_updates | 1428 | +| policy_gradient_loss | -0.034 | +| value_loss | 0.000172 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.24 | +| time/ | | +| fps | 1323 | +| iterations | 359 | +| time_elapsed | 555 | +| total_timesteps | 735232 | +| train/ | | +| approx_kl | 0.034000605 | +| clip_fraction | 0.397 | +| clip_range | 0.141 | +| entropy_loss | -7.31 | +| explained_variance | -0.165 | +| learning_rate | 0.000185 | +| loss | -0.0578 | +| n_updates | 1432 | +| policy_gradient_loss | -0.0349 | +| value_loss | 0.000128 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.227 | +| time/ | | +| fps | 1324 | +| iterations | 360 | +| time_elapsed | 556 | +| total_timesteps | 737280 | +| train/ | | +| approx_kl | 0.0404499 | +| clip_fraction | 0.412 | +| clip_range | 0.141 | +| entropy_loss | -7.46 | +| explained_variance | -0.122 | +| learning_rate | 0.000185 | +| loss | -0.049 | +| n_updates | 1436 | +| policy_gradient_loss | -0.0283 | +| value_loss | 0.000138 | +--------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.225 | +| time/ | | +| fps | 1324 | +| iterations | 361 | +| time_elapsed | 558 | +| total_timesteps | 739328 | +| train/ | | +| approx_kl | 0.03912695 | +| clip_fraction | 0.413 | +| clip_range | 0.141 | +| entropy_loss | -7.4 | +| explained_variance | -0.051 | +| learning_rate | 0.000185 | +| loss | -0.0484 | +| n_updates | 1440 | +| policy_gradient_loss | -0.0323 | +| value_loss | 0.000275 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.228 | +| time/ | | +| fps | 1324 | +| iterations | 362 | +| time_elapsed | 559 | +| total_timesteps | 741376 | +| train/ | | +| approx_kl | 0.04190614 | +| clip_fraction | 0.378 | +| clip_range | 0.141 | +| entropy_loss | -7.45 | +| explained_variance | -0.0547 | +| learning_rate | 0.000185 | +| loss | -0.0595 | +| n_updates | 1444 | +| policy_gradient_loss | -0.0349 | +| value_loss | 0.000153 | +---------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.235 | +| time/ | | +| fps | 1324 | +| iterations | 363 | +| time_elapsed | 561 | +| total_timesteps | 743424 | +| train/ | | +| approx_kl | 0.0411546 | +| clip_fraction | 0.406 | +| clip_range | 0.141 | +| entropy_loss | -7.47 | +| explained_variance | 0.0264 | +| learning_rate | 0.000185 | +| loss | -0.0568 | +| n_updates | 1448 | +| policy_gradient_loss | -0.0361 | +| value_loss | 0.000169 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.234 | +| time/ | | +| fps | 1324 | +| iterations | 364 | +| time_elapsed | 562 | +| total_timesteps | 745472 | +| train/ | | +| approx_kl | 0.041020613 | +| clip_fraction | 0.405 | +| clip_range | 0.141 | +| entropy_loss | -7.49 | +| explained_variance | -0.297 | +| learning_rate | 0.000185 | +| loss | -0.0683 | +| n_updates | 1452 | +| policy_gradient_loss | -0.0412 | +| value_loss | 0.000124 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.234 | +| time/ | | +| fps | 1324 | +| iterations | 365 | +| time_elapsed | 564 | +| total_timesteps | 747520 | +| train/ | | +| approx_kl | 0.04279858 | +| clip_fraction | 0.358 | +| clip_range | 0.141 | +| entropy_loss | -7.39 | +| explained_variance | -0.0922 | +| learning_rate | 0.000185 | +| loss | -0.0545 | +| n_updates | 1456 | +| policy_gradient_loss | -0.0349 | +| value_loss | 0.000139 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.236 | +| time/ | | +| fps | 1324 | +| iterations | 366 | +| time_elapsed | 565 | +| total_timesteps | 749568 | +| train/ | | +| approx_kl | 0.042114206 | +| clip_fraction | 0.375 | +| clip_range | 0.141 | +| entropy_loss | -7.5 | +| explained_variance | -0.0602 | +| learning_rate | 0.000185 | +| loss | -0.0542 | +| n_updates | 1460 | +| policy_gradient_loss | -0.0367 | +| value_loss | 0.000166 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.231 | +| time/ | | +| fps | 1324 | +| iterations | 367 | +| time_elapsed | 567 | +| total_timesteps | 751616 | +| train/ | | +| approx_kl | 0.036618866 | +| clip_fraction | 0.377 | +| clip_range | 0.141 | +| entropy_loss | -7.34 | +| explained_variance | -0.418 | +| learning_rate | 0.000185 | +| loss | -0.0747 | +| n_updates | 1464 | +| policy_gradient_loss | -0.0429 | +| value_loss | 8.26e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.231 | +| time/ | | +| fps | 1324 | +| iterations | 368 | +| time_elapsed | 568 | +| total_timesteps | 753664 | +| train/ | | +| approx_kl | 0.040460512 | +| clip_fraction | 0.377 | +| clip_range | 0.141 | +| entropy_loss | -7.23 | +| explained_variance | -0.13 | +| learning_rate | 0.000185 | +| loss | -0.0646 | +| n_updates | 1468 | +| policy_gradient_loss | -0.0374 | +| value_loss | 9.39e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.212 | +| time/ | | +| fps | 1324 | +| iterations | 369 | +| time_elapsed | 570 | +| total_timesteps | 755712 | +| train/ | | +| approx_kl | 0.035669513 | +| clip_fraction | 0.379 | +| clip_range | 0.141 | +| entropy_loss | -7.22 | +| explained_variance | -0.066 | +| learning_rate | 0.000185 | +| loss | -0.0524 | +| n_updates | 1472 | +| policy_gradient_loss | -0.0351 | +| value_loss | 0.000102 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.212 | +| time/ | | +| fps | 1325 | +| iterations | 370 | +| time_elapsed | 571 | +| total_timesteps | 757760 | +| train/ | | +| approx_kl | 0.036147848 | +| clip_fraction | 0.358 | +| clip_range | 0.141 | +| entropy_loss | -7.33 | +| explained_variance | 0.0688 | +| learning_rate | 0.000185 | +| loss | -0.0492 | +| n_updates | 1476 | +| policy_gradient_loss | -0.0285 | +| value_loss | 0.000197 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.212 | +| time/ | | +| fps | 1325 | +| iterations | 371 | +| time_elapsed | 573 | +| total_timesteps | 759808 | +| train/ | | +| approx_kl | 0.043524254 | +| clip_fraction | 0.389 | +| clip_range | 0.141 | +| entropy_loss | -7.36 | +| explained_variance | -0.185 | +| learning_rate | 0.000185 | +| loss | -0.0474 | +| n_updates | 1480 | +| policy_gradient_loss | -0.0312 | +| value_loss | 0.000194 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.208 | +| time/ | | +| fps | 1325 | +| iterations | 372 | +| time_elapsed | 574 | +| total_timesteps | 761856 | +| train/ | | +| approx_kl | 0.03772885 | +| clip_fraction | 0.382 | +| clip_range | 0.141 | +| entropy_loss | -7.19 | +| explained_variance | -0.0721 | +| learning_rate | 0.000185 | +| loss | -0.0556 | +| n_updates | 1484 | +| policy_gradient_loss | -0.0352 | +| value_loss | 0.000186 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.208 | +| time/ | | +| fps | 1325 | +| iterations | 373 | +| time_elapsed | 576 | +| total_timesteps | 763904 | +| train/ | | +| approx_kl | 0.040774994 | +| clip_fraction | 0.385 | +| clip_range | 0.14 | +| entropy_loss | -7.28 | +| explained_variance | -0.058 | +| learning_rate | 0.000185 | +| loss | -0.0534 | +| n_updates | 1488 | +| policy_gradient_loss | -0.0347 | +| value_loss | 0.000157 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.21 | +| time/ | | +| fps | 1325 | +| iterations | 374 | +| time_elapsed | 577 | +| total_timesteps | 765952 | +| train/ | | +| approx_kl | 0.0439373 | +| clip_fraction | 0.39 | +| clip_range | 0.14 | +| entropy_loss | -7.34 | +| explained_variance | -0.0705 | +| learning_rate | 0.000185 | +| loss | -0.0443 | +| n_updates | 1492 | +| policy_gradient_loss | -0.0288 | +| value_loss | 0.000216 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.209 | +| time/ | | +| fps | 1325 | +| iterations | 375 | +| time_elapsed | 579 | +| total_timesteps | 768000 | +| train/ | | +| approx_kl | 0.039386213 | +| clip_fraction | 0.375 | +| clip_range | 0.14 | +| entropy_loss | -7.26 | +| explained_variance | -0.214 | +| learning_rate | 0.000185 | +| loss | -0.0617 | +| n_updates | 1496 | +| policy_gradient_loss | -0.0393 | +| value_loss | 0.000145 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.209 | +| time/ | | +| fps | 1325 | +| iterations | 376 | +| time_elapsed | 581 | +| total_timesteps | 770048 | +| train/ | | +| approx_kl | 0.034374237 | +| clip_fraction | 0.381 | +| clip_range | 0.14 | +| entropy_loss | -7.23 | +| explained_variance | -0.181 | +| learning_rate | 0.000185 | +| loss | -0.0548 | +| n_updates | 1500 | +| policy_gradient_loss | -0.0343 | +| value_loss | 0.000159 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.206 | +| time/ | | +| fps | 1325 | +| iterations | 377 | +| time_elapsed | 582 | +| total_timesteps | 772096 | +| train/ | | +| approx_kl | 0.037633248 | +| clip_fraction | 0.39 | +| clip_range | 0.14 | +| entropy_loss | -7.37 | +| explained_variance | -0.0858 | +| learning_rate | 0.000185 | +| loss | -0.0603 | +| n_updates | 1504 | +| policy_gradient_loss | -0.0302 | +| value_loss | 0.00014 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.206 | +| time/ | | +| fps | 1325 | +| iterations | 378 | +| time_elapsed | 584 | +| total_timesteps | 774144 | +| train/ | | +| approx_kl | 0.03310587 | +| clip_fraction | 0.379 | +| clip_range | 0.14 | +| entropy_loss | -7.32 | +| explained_variance | 0.0458 | +| learning_rate | 0.000185 | +| loss | -0.0539 | +| n_updates | 1508 | +| policy_gradient_loss | -0.0283 | +| value_loss | 0.000184 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.211 | +| time/ | | +| fps | 1325 | +| iterations | 379 | +| time_elapsed | 585 | +| total_timesteps | 776192 | +| train/ | | +| approx_kl | 0.032213017 | +| clip_fraction | 0.387 | +| clip_range | 0.14 | +| entropy_loss | -7.3 | +| explained_variance | -0.307 | +| learning_rate | 0.000185 | +| loss | -0.0707 | +| n_updates | 1512 | +| policy_gradient_loss | -0.0359 | +| value_loss | 0.000142 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.206 | +| time/ | | +| fps | 1325 | +| iterations | 380 | +| time_elapsed | 587 | +| total_timesteps | 778240 | +| train/ | | +| approx_kl | 0.029907878 | +| clip_fraction | 0.343 | +| clip_range | 0.14 | +| entropy_loss | -7.34 | +| explained_variance | -0.0886 | +| learning_rate | 0.000185 | +| loss | -0.0475 | +| n_updates | 1516 | +| policy_gradient_loss | -0.0282 | +| value_loss | 0.000308 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.209 | +| time/ | | +| fps | 1325 | +| iterations | 381 | +| time_elapsed | 588 | +| total_timesteps | 780288 | +| train/ | | +| approx_kl | 0.034243174 | +| clip_fraction | 0.333 | +| clip_range | 0.14 | +| entropy_loss | -7.29 | +| explained_variance | -0.138 | +| learning_rate | 0.000185 | +| loss | -0.0598 | +| n_updates | 1520 | +| policy_gradient_loss | -0.0372 | +| value_loss | 0.000228 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.202 | +| time/ | | +| fps | 1325 | +| iterations | 382 | +| time_elapsed | 590 | +| total_timesteps | 782336 | +| train/ | | +| approx_kl | 0.033030916 | +| clip_fraction | 0.384 | +| clip_range | 0.14 | +| entropy_loss | -7.37 | +| explained_variance | -0.172 | +| learning_rate | 0.000185 | +| loss | -0.0607 | +| n_updates | 1524 | +| policy_gradient_loss | -0.0347 | +| value_loss | 0.000131 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.201 | +| time/ | | +| fps | 1325 | +| iterations | 383 | +| time_elapsed | 591 | +| total_timesteps | 784384 | +| train/ | | +| approx_kl | 0.036765955 | +| clip_fraction | 0.36 | +| clip_range | 0.14 | +| entropy_loss | -7.39 | +| explained_variance | -0.541 | +| learning_rate | 0.000185 | +| loss | -0.0631 | +| n_updates | 1528 | +| policy_gradient_loss | -0.0367 | +| value_loss | 9.46e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.202 | +| time/ | | +| fps | 1325 | +| iterations | 384 | +| time_elapsed | 593 | +| total_timesteps | 786432 | +| train/ | | +| approx_kl | 0.03762362 | +| clip_fraction | 0.399 | +| clip_range | 0.14 | +| entropy_loss | -7.28 | +| explained_variance | -0.335 | +| learning_rate | 0.000184 | +| loss | -0.0598 | +| n_updates | 1532 | +| policy_gradient_loss | -0.0351 | +| value_loss | 9e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.205 | +| time/ | | +| fps | 1325 | +| iterations | 385 | +| time_elapsed | 594 | +| total_timesteps | 788480 | +| train/ | | +| approx_kl | 0.036051877 | +| clip_fraction | 0.365 | +| clip_range | 0.14 | +| entropy_loss | -7.25 | +| explained_variance | -0.141 | +| learning_rate | 0.000184 | +| loss | -0.0466 | +| n_updates | 1536 | +| policy_gradient_loss | -0.0264 | +| value_loss | 0.000116 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.208 | +| time/ | | +| fps | 1325 | +| iterations | 386 | +| time_elapsed | 596 | +| total_timesteps | 790528 | +| train/ | | +| approx_kl | 0.036674827 | +| clip_fraction | 0.385 | +| clip_range | 0.14 | +| entropy_loss | -7.23 | +| explained_variance | -0.00604 | +| learning_rate | 0.000184 | +| loss | -0.0514 | +| n_updates | 1540 | +| policy_gradient_loss | -0.0315 | +| value_loss | 0.000146 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.206 | +| time/ | | +| fps | 1325 | +| iterations | 387 | +| time_elapsed | 597 | +| total_timesteps | 792576 | +| train/ | | +| approx_kl | 0.03721017 | +| clip_fraction | 0.358 | +| clip_range | 0.14 | +| entropy_loss | -7.34 | +| explained_variance | -0.0296 | +| learning_rate | 0.000184 | +| loss | -0.0461 | +| n_updates | 1544 | +| policy_gradient_loss | -0.0327 | +| value_loss | 0.000172 | +---------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.212 | +| time/ | | +| fps | 1326 | +| iterations | 388 | +| time_elapsed | 599 | +| total_timesteps | 794624 | +| train/ | | +| approx_kl | 0.0398952 | +| clip_fraction | 0.385 | +| clip_range | 0.14 | +| entropy_loss | -7.23 | +| explained_variance | -0.141 | +| learning_rate | 0.000184 | +| loss | -0.0496 | +| n_updates | 1548 | +| policy_gradient_loss | -0.0294 | +| value_loss | 0.000156 | +--------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.212 | +| time/ | | +| fps | 1326 | +| iterations | 389 | +| time_elapsed | 600 | +| total_timesteps | 796672 | +| train/ | | +| approx_kl | 0.03512621 | +| clip_fraction | 0.367 | +| clip_range | 0.14 | +| entropy_loss | -7.28 | +| explained_variance | -0.0494 | +| learning_rate | 0.000184 | +| loss | -0.0565 | +| n_updates | 1552 | +| policy_gradient_loss | -0.0294 | +| value_loss | 0.000172 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.212 | +| time/ | | +| fps | 1326 | +| iterations | 390 | +| time_elapsed | 602 | +| total_timesteps | 798720 | +| train/ | | +| approx_kl | 0.033534817 | +| clip_fraction | 0.37 | +| clip_range | 0.14 | +| entropy_loss | -7.22 | +| explained_variance | -0.137 | +| learning_rate | 0.000184 | +| loss | -0.054 | +| n_updates | 1556 | +| policy_gradient_loss | -0.0287 | +| value_loss | 0.000161 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.212 | +| time/ | | +| fps | 1325 | +| iterations | 391 | +| time_elapsed | 603 | +| total_timesteps | 800768 | +| train/ | | +| approx_kl | 0.039796136 | +| clip_fraction | 0.405 | +| clip_range | 0.14 | +| entropy_loss | -7.29 | +| explained_variance | 0.0301 | +| learning_rate | 0.000184 | +| loss | -0.0545 | +| n_updates | 1560 | +| policy_gradient_loss | -0.0318 | +| value_loss | 0.00016 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.213 | +| time/ | | +| fps | 1325 | +| iterations | 392 | +| time_elapsed | 605 | +| total_timesteps | 802816 | +| train/ | | +| approx_kl | 0.030000787 | +| clip_fraction | 0.345 | +| clip_range | 0.14 | +| entropy_loss | -7.32 | +| explained_variance | -0.132 | +| learning_rate | 0.000184 | +| loss | -0.0583 | +| n_updates | 1564 | +| policy_gradient_loss | -0.0294 | +| value_loss | 0.000198 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.207 | +| time/ | | +| fps | 1325 | +| iterations | 393 | +| time_elapsed | 607 | +| total_timesteps | 804864 | +| train/ | | +| approx_kl | 0.036434587 | +| clip_fraction | 0.382 | +| clip_range | 0.14 | +| entropy_loss | -7.33 | +| explained_variance | -0.241 | +| learning_rate | 0.000184 | +| loss | -0.0585 | +| n_updates | 1568 | +| policy_gradient_loss | -0.0346 | +| value_loss | 0.000147 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.21 | +| time/ | | +| fps | 1326 | +| iterations | 394 | +| time_elapsed | 608 | +| total_timesteps | 806912 | +| train/ | | +| approx_kl | 0.039225742 | +| clip_fraction | 0.393 | +| clip_range | 0.14 | +| entropy_loss | -7.23 | +| explained_variance | -0.0701 | +| learning_rate | 0.000184 | +| loss | -0.0599 | +| n_updates | 1572 | +| policy_gradient_loss | -0.0324 | +| value_loss | 0.000153 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.21 | +| time/ | | +| fps | 1326 | +| iterations | 395 | +| time_elapsed | 610 | +| total_timesteps | 808960 | +| train/ | | +| approx_kl | 0.03729364 | +| clip_fraction | 0.384 | +| clip_range | 0.14 | +| entropy_loss | -7.32 | +| explained_variance | -0.056 | +| learning_rate | 0.000184 | +| loss | -0.0556 | +| n_updates | 1576 | +| policy_gradient_loss | -0.0318 | +| value_loss | 0.000237 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.21 | +| time/ | | +| fps | 1326 | +| iterations | 396 | +| time_elapsed | 611 | +| total_timesteps | 811008 | +| train/ | | +| approx_kl | 0.03877905 | +| clip_fraction | 0.386 | +| clip_range | 0.14 | +| entropy_loss | -7.31 | +| explained_variance | -0.135 | +| learning_rate | 0.000184 | +| loss | -0.0448 | +| n_updates | 1580 | +| policy_gradient_loss | -0.0309 | +| value_loss | 0.000227 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.208 | +| time/ | | +| fps | 1326 | +| iterations | 397 | +| time_elapsed | 613 | +| total_timesteps | 813056 | +| train/ | | +| approx_kl | 0.030879801 | +| clip_fraction | 0.338 | +| clip_range | 0.14 | +| entropy_loss | -7.28 | +| explained_variance | -0.0645 | +| learning_rate | 0.000184 | +| loss | -0.0605 | +| n_updates | 1584 | +| policy_gradient_loss | -0.0344 | +| value_loss | 9.76e-05 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.208 | +| time/ | | +| fps | 1326 | +| iterations | 398 | +| time_elapsed | 614 | +| total_timesteps | 815104 | +| train/ | | +| approx_kl | 0.0329255 | +| clip_fraction | 0.367 | +| clip_range | 0.14 | +| entropy_loss | -7.21 | +| explained_variance | -0.192 | +| learning_rate | 0.000184 | +| loss | -0.0682 | +| n_updates | 1588 | +| policy_gradient_loss | -0.0365 | +| value_loss | 8.66e-05 | +--------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.21 | +| time/ | | +| fps | 1326 | +| iterations | 399 | +| time_elapsed | 616 | +| total_timesteps | 817152 | +| train/ | | +| approx_kl | 0.03656498 | +| clip_fraction | 0.369 | +| clip_range | 0.14 | +| entropy_loss | -7.05 | +| explained_variance | -0.1 | +| learning_rate | 0.000184 | +| loss | -0.0534 | +| n_updates | 1592 | +| policy_gradient_loss | -0.0297 | +| value_loss | 0.000157 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.204 | +| time/ | | +| fps | 1325 | +| iterations | 400 | +| time_elapsed | 617 | +| total_timesteps | 819200 | +| train/ | | +| approx_kl | 0.037618402 | +| clip_fraction | 0.353 | +| clip_range | 0.14 | +| entropy_loss | -7.35 | +| explained_variance | -0.065 | +| learning_rate | 0.000184 | +| loss | -0.0559 | +| n_updates | 1596 | +| policy_gradient_loss | -0.0345 | +| value_loss | 0.000115 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.204 | +| time/ | | +| fps | 1325 | +| iterations | 401 | +| time_elapsed | 619 | +| total_timesteps | 821248 | +| train/ | | +| approx_kl | 0.034565225 | +| clip_fraction | 0.359 | +| clip_range | 0.14 | +| entropy_loss | -7.38 | +| explained_variance | -0.0557 | +| learning_rate | 0.000184 | +| loss | -0.0558 | +| n_updates | 1600 | +| policy_gradient_loss | -0.0344 | +| value_loss | 0.000118 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.21 | +| time/ | | +| fps | 1325 | +| iterations | 402 | +| time_elapsed | 621 | +| total_timesteps | 823296 | +| train/ | | +| approx_kl | 0.031861775 | +| clip_fraction | 0.355 | +| clip_range | 0.14 | +| entropy_loss | -7.32 | +| explained_variance | -0.11 | +| learning_rate | 0.000184 | +| loss | -0.0506 | +| n_updates | 1604 | +| policy_gradient_loss | -0.0317 | +| value_loss | 0.000125 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.215 | +| time/ | | +| fps | 1325 | +| iterations | 403 | +| time_elapsed | 622 | +| total_timesteps | 825344 | +| train/ | | +| approx_kl | 0.032498304 | +| clip_fraction | 0.364 | +| clip_range | 0.14 | +| entropy_loss | -7.36 | +| explained_variance | 0.0141 | +| learning_rate | 0.000184 | +| loss | -0.0521 | +| n_updates | 1608 | +| policy_gradient_loss | -0.0335 | +| value_loss | 0.000228 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.214 | +| time/ | | +| fps | 1325 | +| iterations | 404 | +| time_elapsed | 624 | +| total_timesteps | 827392 | +| train/ | | +| approx_kl | 0.035890855 | +| clip_fraction | 0.386 | +| clip_range | 0.14 | +| entropy_loss | -7.21 | +| explained_variance | -0.227 | +| learning_rate | 0.000184 | +| loss | -0.061 | +| n_updates | 1612 | +| policy_gradient_loss | -0.0381 | +| value_loss | 0.000144 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.218 | +| time/ | | +| fps | 1325 | +| iterations | 405 | +| time_elapsed | 625 | +| total_timesteps | 829440 | +| train/ | | +| approx_kl | 0.03367512 | +| clip_fraction | 0.349 | +| clip_range | 0.14 | +| entropy_loss | -7.24 | +| explained_variance | 0.0173 | +| learning_rate | 0.000184 | +| loss | -0.0585 | +| n_updates | 1616 | +| policy_gradient_loss | -0.0345 | +| value_loss | 0.000223 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.212 | +| time/ | | +| fps | 1325 | +| iterations | 406 | +| time_elapsed | 627 | +| total_timesteps | 831488 | +| train/ | | +| approx_kl | 0.036056936 | +| clip_fraction | 0.371 | +| clip_range | 0.14 | +| entropy_loss | -7.22 | +| explained_variance | 0.0828 | +| learning_rate | 0.000184 | +| loss | -0.0562 | +| n_updates | 1620 | +| policy_gradient_loss | -0.0338 | +| value_loss | 0.000102 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.215 | +| time/ | | +| fps | 1325 | +| iterations | 407 | +| time_elapsed | 628 | +| total_timesteps | 833536 | +| train/ | | +| approx_kl | 0.039140917 | +| clip_fraction | 0.371 | +| clip_range | 0.14 | +| entropy_loss | -7.08 | +| explained_variance | -0.12 | +| learning_rate | 0.000184 | +| loss | -0.0635 | +| n_updates | 1624 | +| policy_gradient_loss | -0.0336 | +| value_loss | 0.000168 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.21 | +| time/ | | +| fps | 1325 | +| iterations | 408 | +| time_elapsed | 630 | +| total_timesteps | 835584 | +| train/ | | +| approx_kl | 0.030770462 | +| clip_fraction | 0.377 | +| clip_range | 0.14 | +| entropy_loss | -7.22 | +| explained_variance | -0.139 | +| learning_rate | 0.000183 | +| loss | -0.052 | +| n_updates | 1628 | +| policy_gradient_loss | -0.0303 | +| value_loss | 0.000179 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.211 | +| time/ | | +| fps | 1325 | +| iterations | 409 | +| time_elapsed | 631 | +| total_timesteps | 837632 | +| train/ | | +| approx_kl | 0.03668031 | +| clip_fraction | 0.357 | +| clip_range | 0.14 | +| entropy_loss | -7.18 | +| explained_variance | -0.088 | +| learning_rate | 0.000183 | +| loss | -0.0562 | +| n_updates | 1632 | +| policy_gradient_loss | -0.0311 | +| value_loss | 0.000232 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.202 | +| time/ | | +| fps | 1325 | +| iterations | 410 | +| time_elapsed | 633 | +| total_timesteps | 839680 | +| train/ | | +| approx_kl | 0.03659059 | +| clip_fraction | 0.375 | +| clip_range | 0.14 | +| entropy_loss | -7.13 | +| explained_variance | -0.124 | +| learning_rate | 0.000183 | +| loss | -0.0455 | +| n_updates | 1636 | +| policy_gradient_loss | -0.0305 | +| value_loss | 0.000208 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.202 | +| time/ | | +| fps | 1325 | +| iterations | 411 | +| time_elapsed | 634 | +| total_timesteps | 841728 | +| train/ | | +| approx_kl | 0.038688667 | +| clip_fraction | 0.37 | +| clip_range | 0.14 | +| entropy_loss | -7.18 | +| explained_variance | -0.0129 | +| learning_rate | 0.000183 | +| loss | -0.0516 | +| n_updates | 1640 | +| policy_gradient_loss | -0.0308 | +| value_loss | 0.000252 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.207 | +| time/ | | +| fps | 1325 | +| iterations | 412 | +| time_elapsed | 636 | +| total_timesteps | 843776 | +| train/ | | +| approx_kl | 0.03488727 | +| clip_fraction | 0.395 | +| clip_range | 0.139 | +| entropy_loss | -7.21 | +| explained_variance | -0.00223 | +| learning_rate | 0.000183 | +| loss | -0.0473 | +| n_updates | 1644 | +| policy_gradient_loss | -0.0329 | +| value_loss | 0.000125 | +---------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.207 | +| time/ | | +| fps | 1325 | +| iterations | 413 | +| time_elapsed | 638 | +| total_timesteps | 845824 | +| train/ | | +| approx_kl | 0.0393658 | +| clip_fraction | 0.392 | +| clip_range | 0.139 | +| entropy_loss | -7.09 | +| explained_variance | -0.321 | +| learning_rate | 0.000183 | +| loss | -0.0588 | +| n_updates | 1648 | +| policy_gradient_loss | -0.0346 | +| value_loss | 9.87e-05 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.212 | +| time/ | | +| fps | 1325 | +| iterations | 414 | +| time_elapsed | 639 | +| total_timesteps | 847872 | +| train/ | | +| approx_kl | 0.034845307 | +| clip_fraction | 0.363 | +| clip_range | 0.139 | +| entropy_loss | -7.17 | +| explained_variance | -0.12 | +| learning_rate | 0.000183 | +| loss | -0.0554 | +| n_updates | 1652 | +| policy_gradient_loss | -0.0337 | +| value_loss | 0.000192 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.212 | +| time/ | | +| fps | 1325 | +| iterations | 415 | +| time_elapsed | 641 | +| total_timesteps | 849920 | +| train/ | | +| approx_kl | 0.0411126 | +| clip_fraction | 0.384 | +| clip_range | 0.139 | +| entropy_loss | -7.04 | +| explained_variance | 0.013 | +| learning_rate | 0.000183 | +| loss | -0.0547 | +| n_updates | 1656 | +| policy_gradient_loss | -0.0314 | +| value_loss | 0.000161 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.212 | +| time/ | | +| fps | 1325 | +| iterations | 416 | +| time_elapsed | 642 | +| total_timesteps | 851968 | +| train/ | | +| approx_kl | 0.036117606 | +| clip_fraction | 0.379 | +| clip_range | 0.139 | +| entropy_loss | -7.22 | +| explained_variance | -0.25 | +| learning_rate | 0.000183 | +| loss | -0.051 | +| n_updates | 1660 | +| policy_gradient_loss | -0.0319 | +| value_loss | 0.000107 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.212 | +| time/ | | +| fps | 1325 | +| iterations | 417 | +| time_elapsed | 644 | +| total_timesteps | 854016 | +| train/ | | +| approx_kl | 0.03446854 | +| clip_fraction | 0.375 | +| clip_range | 0.139 | +| entropy_loss | -7.19 | +| explained_variance | -0.116 | +| learning_rate | 0.000183 | +| loss | -0.0594 | +| n_updates | 1664 | +| policy_gradient_loss | -0.029 | +| value_loss | 0.000168 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.218 | +| time/ | | +| fps | 1325 | +| iterations | 418 | +| time_elapsed | 645 | +| total_timesteps | 856064 | +| train/ | | +| approx_kl | 0.031864688 | +| clip_fraction | 0.385 | +| clip_range | 0.139 | +| entropy_loss | -7.18 | +| explained_variance | -0.0836 | +| learning_rate | 0.000183 | +| loss | -0.0627 | +| n_updates | 1668 | +| policy_gradient_loss | -0.0309 | +| value_loss | 0.000139 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.222 | +| time/ | | +| fps | 1325 | +| iterations | 419 | +| time_elapsed | 647 | +| total_timesteps | 858112 | +| train/ | | +| approx_kl | 0.032785427 | +| clip_fraction | 0.361 | +| clip_range | 0.139 | +| entropy_loss | -7.13 | +| explained_variance | -0.0315 | +| learning_rate | 0.000183 | +| loss | -0.0424 | +| n_updates | 1672 | +| policy_gradient_loss | -0.0235 | +| value_loss | 0.00018 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.223 | +| time/ | | +| fps | 1325 | +| iterations | 420 | +| time_elapsed | 649 | +| total_timesteps | 860160 | +| train/ | | +| approx_kl | 0.030380182 | +| clip_fraction | 0.349 | +| clip_range | 0.139 | +| entropy_loss | -7.21 | +| explained_variance | -0.16 | +| learning_rate | 0.000183 | +| loss | -0.0676 | +| n_updates | 1676 | +| policy_gradient_loss | -0.0315 | +| value_loss | 0.000146 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.22 | +| time/ | | +| fps | 1325 | +| iterations | 421 | +| time_elapsed | 650 | +| total_timesteps | 862208 | +| train/ | | +| approx_kl | 0.038106896 | +| clip_fraction | 0.382 | +| clip_range | 0.139 | +| entropy_loss | -7.28 | +| explained_variance | -0.122 | +| learning_rate | 0.000183 | +| loss | -0.0615 | +| n_updates | 1680 | +| policy_gradient_loss | -0.031 | +| value_loss | 0.000166 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.224 | +| time/ | | +| fps | 1325 | +| iterations | 422 | +| time_elapsed | 652 | +| total_timesteps | 864256 | +| train/ | | +| approx_kl | 0.03464716 | +| clip_fraction | 0.34 | +| clip_range | 0.139 | +| entropy_loss | -7.37 | +| explained_variance | -0.0799 | +| learning_rate | 0.000183 | +| loss | -0.0521 | +| n_updates | 1684 | +| policy_gradient_loss | -0.033 | +| value_loss | 0.000135 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.228 | +| time/ | | +| fps | 1325 | +| iterations | 423 | +| time_elapsed | 653 | +| total_timesteps | 866304 | +| train/ | | +| approx_kl | 0.038514204 | +| clip_fraction | 0.361 | +| clip_range | 0.139 | +| entropy_loss | -7.26 | +| explained_variance | -0.157 | +| learning_rate | 0.000183 | +| loss | -0.0743 | +| n_updates | 1688 | +| policy_gradient_loss | -0.04 | +| value_loss | 5.46e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.227 | +| time/ | | +| fps | 1325 | +| iterations | 424 | +| time_elapsed | 655 | +| total_timesteps | 868352 | +| train/ | | +| approx_kl | 0.034190334 | +| clip_fraction | 0.376 | +| clip_range | 0.139 | +| entropy_loss | -7.15 | +| explained_variance | 0.00882 | +| learning_rate | 0.000183 | +| loss | -0.0717 | +| n_updates | 1692 | +| policy_gradient_loss | -0.0333 | +| value_loss | 9.78e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.231 | +| time/ | | +| fps | 1325 | +| iterations | 425 | +| time_elapsed | 656 | +| total_timesteps | 870400 | +| train/ | | +| approx_kl | 0.02853603 | +| clip_fraction | 0.331 | +| clip_range | 0.139 | +| entropy_loss | -7.23 | +| explained_variance | -0.163 | +| learning_rate | 0.000183 | +| loss | -0.0515 | +| n_updates | 1696 | +| policy_gradient_loss | -0.0294 | +| value_loss | 0.000131 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.227 | +| time/ | | +| fps | 1325 | +| iterations | 426 | +| time_elapsed | 658 | +| total_timesteps | 872448 | +| train/ | | +| approx_kl | 0.035817962 | +| clip_fraction | 0.364 | +| clip_range | 0.139 | +| entropy_loss | -7.24 | +| explained_variance | -0.0434 | +| learning_rate | 0.000183 | +| loss | -0.0533 | +| n_updates | 1700 | +| policy_gradient_loss | -0.033 | +| value_loss | 0.000162 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.218 | +| time/ | | +| fps | 1325 | +| iterations | 427 | +| time_elapsed | 659 | +| total_timesteps | 874496 | +| train/ | | +| approx_kl | 0.033051368 | +| clip_fraction | 0.38 | +| clip_range | 0.139 | +| entropy_loss | -7.3 | +| explained_variance | -0.0768 | +| learning_rate | 0.000183 | +| loss | -0.0501 | +| n_updates | 1704 | +| policy_gradient_loss | -0.0337 | +| value_loss | 8e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.218 | +| time/ | | +| fps | 1325 | +| iterations | 428 | +| time_elapsed | 661 | +| total_timesteps | 876544 | +| train/ | | +| approx_kl | 0.03583175 | +| clip_fraction | 0.369 | +| clip_range | 0.139 | +| entropy_loss | -7.25 | +| explained_variance | -0.00892 | +| learning_rate | 0.000183 | +| loss | -0.0582 | +| n_updates | 1708 | +| policy_gradient_loss | -0.0314 | +| value_loss | 0.000275 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.216 | +| time/ | | +| fps | 1325 | +| iterations | 429 | +| time_elapsed | 663 | +| total_timesteps | 878592 | +| train/ | | +| approx_kl | 0.033585757 | +| clip_fraction | 0.366 | +| clip_range | 0.139 | +| entropy_loss | -7.4 | +| explained_variance | -0.289 | +| learning_rate | 0.000183 | +| loss | -0.068 | +| n_updates | 1712 | +| policy_gradient_loss | -0.0379 | +| value_loss | 9.18e-05 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.22 | +| time/ | | +| fps | 1324 | +| iterations | 430 | +| time_elapsed | 664 | +| total_timesteps | 880640 | +| train/ | | +| approx_kl | 0.0386722 | +| clip_fraction | 0.361 | +| clip_range | 0.139 | +| entropy_loss | -7.39 | +| explained_variance | -0.102 | +| learning_rate | 0.000183 | +| loss | -0.0639 | +| n_updates | 1716 | +| policy_gradient_loss | -0.0358 | +| value_loss | 0.000201 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.219 | +| time/ | | +| fps | 1324 | +| iterations | 431 | +| time_elapsed | 666 | +| total_timesteps | 882688 | +| train/ | | +| approx_kl | 0.030328799 | +| clip_fraction | 0.344 | +| clip_range | 0.139 | +| entropy_loss | -7.44 | +| explained_variance | -0.0169 | +| learning_rate | 0.000183 | +| loss | -0.0359 | +| n_updates | 1720 | +| policy_gradient_loss | -0.0251 | +| value_loss | 0.000277 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.216 | +| time/ | | +| fps | 1324 | +| iterations | 432 | +| time_elapsed | 667 | +| total_timesteps | 884736 | +| train/ | | +| approx_kl | 0.038675122 | +| clip_fraction | 0.362 | +| clip_range | 0.139 | +| entropy_loss | -7.39 | +| explained_variance | -0.445 | +| learning_rate | 0.000183 | +| loss | -0.0644 | +| n_updates | 1724 | +| policy_gradient_loss | -0.0366 | +| value_loss | 0.000106 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.216 | +| time/ | | +| fps | 1324 | +| iterations | 433 | +| time_elapsed | 669 | +| total_timesteps | 886784 | +| train/ | | +| approx_kl | 0.039188527 | +| clip_fraction | 0.379 | +| clip_range | 0.139 | +| entropy_loss | -7.18 | +| explained_variance | -0.0865 | +| learning_rate | 0.000182 | +| loss | -0.0498 | +| n_updates | 1728 | +| policy_gradient_loss | -0.0322 | +| value_loss | 0.00015 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.216 | +| time/ | | +| fps | 1324 | +| iterations | 434 | +| time_elapsed | 670 | +| total_timesteps | 888832 | +| train/ | | +| approx_kl | 0.041332822 | +| clip_fraction | 0.381 | +| clip_range | 0.139 | +| entropy_loss | -7.26 | +| explained_variance | -0.197 | +| learning_rate | 0.000182 | +| loss | -0.0547 | +| n_updates | 1732 | +| policy_gradient_loss | -0.0323 | +| value_loss | 0.000129 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.216 | +| time/ | | +| fps | 1324 | +| iterations | 435 | +| time_elapsed | 672 | +| total_timesteps | 890880 | +| train/ | | +| approx_kl | 0.042606566 | +| clip_fraction | 0.372 | +| clip_range | 0.139 | +| entropy_loss | -7.34 | +| explained_variance | -0.0107 | +| learning_rate | 0.000182 | +| loss | -0.0574 | +| n_updates | 1736 | +| policy_gradient_loss | -0.0326 | +| value_loss | 0.000144 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.216 | +| time/ | | +| fps | 1324 | +| iterations | 436 | +| time_elapsed | 673 | +| total_timesteps | 892928 | +| train/ | | +| approx_kl | 0.043998115 | +| clip_fraction | 0.385 | +| clip_range | 0.139 | +| entropy_loss | -7.37 | +| explained_variance | -0.186 | +| learning_rate | 0.000182 | +| loss | -0.0571 | +| n_updates | 1740 | +| policy_gradient_loss | -0.0352 | +| value_loss | 0.000145 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.231 | +| time/ | | +| fps | 1324 | +| iterations | 437 | +| time_elapsed | 675 | +| total_timesteps | 894976 | +| train/ | | +| approx_kl | 0.036090624 | +| clip_fraction | 0.399 | +| clip_range | 0.139 | +| entropy_loss | -7.48 | +| explained_variance | -0.0947 | +| learning_rate | 0.000182 | +| loss | -0.0648 | +| n_updates | 1744 | +| policy_gradient_loss | -0.0372 | +| value_loss | 7.14e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.237 | +| time/ | | +| fps | 1324 | +| iterations | 438 | +| time_elapsed | 677 | +| total_timesteps | 897024 | +| train/ | | +| approx_kl | 0.03509559 | +| clip_fraction | 0.387 | +| clip_range | 0.139 | +| entropy_loss | -7.4 | +| explained_variance | -0.00336 | +| learning_rate | 0.000182 | +| loss | -0.0558 | +| n_updates | 1748 | +| policy_gradient_loss | -0.0303 | +| value_loss | 0.000214 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.237 | +| time/ | | +| fps | 1324 | +| iterations | 439 | +| time_elapsed | 678 | +| total_timesteps | 899072 | +| train/ | | +| approx_kl | 0.04056503 | +| clip_fraction | 0.372 | +| clip_range | 0.139 | +| entropy_loss | -7.42 | +| explained_variance | -0.0203 | +| learning_rate | 0.000182 | +| loss | -0.0651 | +| n_updates | 1752 | +| policy_gradient_loss | -0.0331 | +| value_loss | 0.000178 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.24 | +| time/ | | +| fps | 1324 | +| iterations | 440 | +| time_elapsed | 680 | +| total_timesteps | 901120 | +| train/ | | +| approx_kl | 0.034633435 | +| clip_fraction | 0.392 | +| clip_range | 0.139 | +| entropy_loss | -7.46 | +| explained_variance | -0.117 | +| learning_rate | 0.000182 | +| loss | -0.0673 | +| n_updates | 1756 | +| policy_gradient_loss | -0.0398 | +| value_loss | 0.000116 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.236 | +| time/ | | +| fps | 1324 | +| iterations | 441 | +| time_elapsed | 681 | +| total_timesteps | 903168 | +| train/ | | +| approx_kl | 0.03723532 | +| clip_fraction | 0.372 | +| clip_range | 0.139 | +| entropy_loss | -7.22 | +| explained_variance | -0.0167 | +| learning_rate | 0.000182 | +| loss | -0.0614 | +| n_updates | 1760 | +| policy_gradient_loss | -0.0319 | +| value_loss | 0.000195 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.233 | +| time/ | | +| fps | 1324 | +| iterations | 442 | +| time_elapsed | 683 | +| total_timesteps | 905216 | +| train/ | | +| approx_kl | 0.03636503 | +| clip_fraction | 0.378 | +| clip_range | 0.139 | +| entropy_loss | -7.22 | +| explained_variance | -0.151 | +| learning_rate | 0.000182 | +| loss | -0.0577 | +| n_updates | 1764 | +| policy_gradient_loss | -0.0349 | +| value_loss | 0.000116 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.233 | +| time/ | | +| fps | 1324 | +| iterations | 443 | +| time_elapsed | 685 | +| total_timesteps | 907264 | +| train/ | | +| approx_kl | 0.045774885 | +| clip_fraction | 0.412 | +| clip_range | 0.139 | +| entropy_loss | -7.34 | +| explained_variance | -0.11 | +| learning_rate | 0.000182 | +| loss | -0.0511 | +| n_updates | 1768 | +| policy_gradient_loss | -0.0338 | +| value_loss | 0.0001 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.228 | +| time/ | | +| fps | 1324 | +| iterations | 444 | +| time_elapsed | 686 | +| total_timesteps | 909312 | +| train/ | | +| approx_kl | 0.041437298 | +| clip_fraction | 0.405 | +| clip_range | 0.139 | +| entropy_loss | -7.33 | +| explained_variance | 0.105 | +| learning_rate | 0.000182 | +| loss | -0.061 | +| n_updates | 1772 | +| policy_gradient_loss | -0.0348 | +| value_loss | 0.000103 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.228 | +| time/ | | +| fps | 1324 | +| iterations | 445 | +| time_elapsed | 688 | +| total_timesteps | 911360 | +| train/ | | +| approx_kl | 0.03695348 | +| clip_fraction | 0.38 | +| clip_range | 0.139 | +| entropy_loss | -7.31 | +| explained_variance | -0.0476 | +| learning_rate | 0.000182 | +| loss | -0.0531 | +| n_updates | 1776 | +| policy_gradient_loss | -0.0292 | +| value_loss | 0.000231 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.228 | +| time/ | | +| fps | 1324 | +| iterations | 446 | +| time_elapsed | 689 | +| total_timesteps | 913408 | +| train/ | | +| approx_kl | 0.037957467 | +| clip_fraction | 0.366 | +| clip_range | 0.139 | +| entropy_loss | -7.21 | +| explained_variance | 0.00773 | +| learning_rate | 0.000182 | +| loss | -0.0596 | +| n_updates | 1780 | +| policy_gradient_loss | -0.0323 | +| value_loss | 0.000144 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.228 | +| time/ | | +| fps | 1324 | +| iterations | 447 | +| time_elapsed | 691 | +| total_timesteps | 915456 | +| train/ | | +| approx_kl | 0.033522476 | +| clip_fraction | 0.38 | +| clip_range | 0.139 | +| entropy_loss | -7.28 | +| explained_variance | -0.349 | +| learning_rate | 0.000182 | +| loss | -0.0728 | +| n_updates | 1784 | +| policy_gradient_loss | -0.0355 | +| value_loss | 6.98e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.23 | +| time/ | | +| fps | 1324 | +| iterations | 448 | +| time_elapsed | 692 | +| total_timesteps | 917504 | +| train/ | | +| approx_kl | 0.039456308 | +| clip_fraction | 0.362 | +| clip_range | 0.139 | +| entropy_loss | -7.23 | +| explained_variance | -0.0766 | +| learning_rate | 0.000182 | +| loss | -0.0603 | +| n_updates | 1788 | +| policy_gradient_loss | -0.0355 | +| value_loss | 0.000117 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.225 | +| time/ | | +| fps | 1324 | +| iterations | 449 | +| time_elapsed | 694 | +| total_timesteps | 919552 | +| train/ | | +| approx_kl | 0.03938023 | +| clip_fraction | 0.37 | +| clip_range | 0.139 | +| entropy_loss | -7.36 | +| explained_variance | -0.191 | +| learning_rate | 0.000182 | +| loss | -0.0494 | +| n_updates | 1792 | +| policy_gradient_loss | -0.0299 | +| value_loss | 9.43e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.224 | +| time/ | | +| fps | 1324 | +| iterations | 450 | +| time_elapsed | 695 | +| total_timesteps | 921600 | +| train/ | | +| approx_kl | 0.040213026 | +| clip_fraction | 0.381 | +| clip_range | 0.139 | +| entropy_loss | -7.17 | +| explained_variance | 0.0214 | +| learning_rate | 0.000182 | +| loss | -0.052 | +| n_updates | 1796 | +| policy_gradient_loss | -0.032 | +| value_loss | 0.000125 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.226 | +| time/ | | +| fps | 1324 | +| iterations | 451 | +| time_elapsed | 697 | +| total_timesteps | 923648 | +| train/ | | +| approx_kl | 0.035686214 | +| clip_fraction | 0.367 | +| clip_range | 0.138 | +| entropy_loss | -7.25 | +| explained_variance | 0.0463 | +| learning_rate | 0.000182 | +| loss | -0.0631 | +| n_updates | 1800 | +| policy_gradient_loss | -0.0358 | +| value_loss | 0.000185 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.226 | +| time/ | | +| fps | 1324 | +| iterations | 452 | +| time_elapsed | 699 | +| total_timesteps | 925696 | +| train/ | | +| approx_kl | 0.034445442 | +| clip_fraction | 0.371 | +| clip_range | 0.138 | +| entropy_loss | -7.37 | +| explained_variance | -0.0667 | +| learning_rate | 0.000182 | +| loss | -0.0458 | +| n_updates | 1804 | +| policy_gradient_loss | -0.0304 | +| value_loss | 0.000192 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.231 | +| time/ | | +| fps | 1324 | +| iterations | 453 | +| time_elapsed | 700 | +| total_timesteps | 927744 | +| train/ | | +| approx_kl | 0.043863922 | +| clip_fraction | 0.392 | +| clip_range | 0.138 | +| entropy_loss | -7.25 | +| explained_variance | -0.207 | +| learning_rate | 0.000182 | +| loss | -0.0658 | +| n_updates | 1808 | +| policy_gradient_loss | -0.0393 | +| value_loss | 0.000141 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.229 | +| time/ | | +| fps | 1324 | +| iterations | 454 | +| time_elapsed | 702 | +| total_timesteps | 929792 | +| train/ | | +| approx_kl | 0.038803775 | +| clip_fraction | 0.369 | +| clip_range | 0.138 | +| entropy_loss | -7.26 | +| explained_variance | 0.0104 | +| learning_rate | 0.000182 | +| loss | -0.055 | +| n_updates | 1812 | +| policy_gradient_loss | -0.0323 | +| value_loss | 0.000255 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.223 | +| time/ | | +| fps | 1324 | +| iterations | 455 | +| time_elapsed | 703 | +| total_timesteps | 931840 | +| train/ | | +| approx_kl | 0.038842425 | +| clip_fraction | 0.377 | +| clip_range | 0.138 | +| entropy_loss | -7.32 | +| explained_variance | 0.018 | +| learning_rate | 0.000182 | +| loss | -0.0617 | +| n_updates | 1816 | +| policy_gradient_loss | -0.0336 | +| value_loss | 0.000131 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.223 | +| time/ | | +| fps | 1324 | +| iterations | 456 | +| time_elapsed | 705 | +| total_timesteps | 933888 | +| train/ | | +| approx_kl | 0.03547906 | +| clip_fraction | 0.372 | +| clip_range | 0.138 | +| entropy_loss | -7.31 | +| explained_variance | -0.19 | +| learning_rate | 0.000182 | +| loss | -0.0542 | +| n_updates | 1820 | +| policy_gradient_loss | -0.0351 | +| value_loss | 0.000141 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.222 | +| time/ | | +| fps | 1324 | +| iterations | 457 | +| time_elapsed | 706 | +| total_timesteps | 935936 | +| train/ | | +| approx_kl | 0.052867465 | +| clip_fraction | 0.401 | +| clip_range | 0.138 | +| entropy_loss | -7.23 | +| explained_variance | -0.0283 | +| learning_rate | 0.000182 | +| loss | -0.0591 | +| n_updates | 1824 | +| policy_gradient_loss | -0.0345 | +| value_loss | 0.000123 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.214 | +| time/ | | +| fps | 1324 | +| iterations | 458 | +| time_elapsed | 708 | +| total_timesteps | 937984 | +| train/ | | +| approx_kl | 0.040281236 | +| clip_fraction | 0.393 | +| clip_range | 0.138 | +| entropy_loss | -7.21 | +| explained_variance | -0.292 | +| learning_rate | 0.000181 | +| loss | -0.0559 | +| n_updates | 1828 | +| policy_gradient_loss | -0.0346 | +| value_loss | 8.21e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.212 | +| time/ | | +| fps | 1324 | +| iterations | 459 | +| time_elapsed | 709 | +| total_timesteps | 940032 | +| train/ | | +| approx_kl | 0.04064711 | +| clip_fraction | 0.375 | +| clip_range | 0.138 | +| entropy_loss | -7.14 | +| explained_variance | -0.0196 | +| learning_rate | 0.000181 | +| loss | -0.0505 | +| n_updates | 1832 | +| policy_gradient_loss | -0.0335 | +| value_loss | 0.000118 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.22 | +| time/ | | +| fps | 1324 | +| iterations | 460 | +| time_elapsed | 711 | +| total_timesteps | 942080 | +| train/ | | +| approx_kl | 0.038932838 | +| clip_fraction | 0.373 | +| clip_range | 0.138 | +| entropy_loss | -7.23 | +| explained_variance | -0.0963 | +| learning_rate | 0.000181 | +| loss | -0.0591 | +| n_updates | 1836 | +| policy_gradient_loss | -0.0339 | +| value_loss | 0.000208 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.223 | +| time/ | | +| fps | 1324 | +| iterations | 461 | +| time_elapsed | 713 | +| total_timesteps | 944128 | +| train/ | | +| approx_kl | 0.03803695 | +| clip_fraction | 0.375 | +| clip_range | 0.138 | +| entropy_loss | -7.15 | +| explained_variance | -0.0311 | +| learning_rate | 0.000181 | +| loss | -0.0493 | +| n_updates | 1840 | +| policy_gradient_loss | -0.0309 | +| value_loss | 0.000275 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.223 | +| time/ | | +| fps | 1324 | +| iterations | 462 | +| time_elapsed | 714 | +| total_timesteps | 946176 | +| train/ | | +| approx_kl | 0.036475588 | +| clip_fraction | 0.384 | +| clip_range | 0.138 | +| entropy_loss | -7.25 | +| explained_variance | -0.077 | +| learning_rate | 0.000181 | +| loss | -0.0666 | +| n_updates | 1844 | +| policy_gradient_loss | -0.036 | +| value_loss | 0.000146 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.225 | +| time/ | | +| fps | 1324 | +| iterations | 463 | +| time_elapsed | 716 | +| total_timesteps | 948224 | +| train/ | | +| approx_kl | 0.03904534 | +| clip_fraction | 0.395 | +| clip_range | 0.138 | +| entropy_loss | -7.18 | +| explained_variance | -0.28 | +| learning_rate | 0.000181 | +| loss | -0.0629 | +| n_updates | 1848 | +| policy_gradient_loss | -0.0358 | +| value_loss | 0.000133 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.229 | +| time/ | | +| fps | 1324 | +| iterations | 464 | +| time_elapsed | 717 | +| total_timesteps | 950272 | +| train/ | | +| approx_kl | 0.043683182 | +| clip_fraction | 0.385 | +| clip_range | 0.138 | +| entropy_loss | -7.09 | +| explained_variance | -0.0336 | +| learning_rate | 0.000181 | +| loss | -0.0474 | +| n_updates | 1852 | +| policy_gradient_loss | -0.0283 | +| value_loss | 0.00027 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.234 | +| time/ | | +| fps | 1324 | +| iterations | 465 | +| time_elapsed | 719 | +| total_timesteps | 952320 | +| train/ | | +| approx_kl | 0.0327538 | +| clip_fraction | 0.417 | +| clip_range | 0.138 | +| entropy_loss | -7.17 | +| explained_variance | 0.0293 | +| learning_rate | 0.000181 | +| loss | -0.0514 | +| n_updates | 1856 | +| policy_gradient_loss | -0.0324 | +| value_loss | 0.000169 | +--------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.237 | +| time/ | | +| fps | 1324 | +| iterations | 466 | +| time_elapsed | 720 | +| total_timesteps | 954368 | +| train/ | | +| approx_kl | 0.04508648 | +| clip_fraction | 0.408 | +| clip_range | 0.138 | +| entropy_loss | -7.03 | +| explained_variance | -0.274 | +| learning_rate | 0.000181 | +| loss | -0.0705 | +| n_updates | 1860 | +| policy_gradient_loss | -0.0379 | +| value_loss | 0.000131 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.237 | +| time/ | | +| fps | 1324 | +| iterations | 467 | +| time_elapsed | 722 | +| total_timesteps | 956416 | +| train/ | | +| approx_kl | 0.036080558 | +| clip_fraction | 0.402 | +| clip_range | 0.138 | +| entropy_loss | -7.02 | +| explained_variance | 0.00488 | +| learning_rate | 0.000181 | +| loss | -0.0568 | +| n_updates | 1864 | +| policy_gradient_loss | -0.0337 | +| value_loss | 0.000234 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.237 | +| time/ | | +| fps | 1324 | +| iterations | 468 | +| time_elapsed | 723 | +| total_timesteps | 958464 | +| train/ | | +| approx_kl | 0.040123835 | +| clip_fraction | 0.403 | +| clip_range | 0.138 | +| entropy_loss | -6.99 | +| explained_variance | -0.0916 | +| learning_rate | 0.000181 | +| loss | -0.0624 | +| n_updates | 1868 | +| policy_gradient_loss | -0.0362 | +| value_loss | 0.000141 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.237 | +| time/ | | +| fps | 1324 | +| iterations | 469 | +| time_elapsed | 725 | +| total_timesteps | 960512 | +| train/ | | +| approx_kl | 0.0400945 | +| clip_fraction | 0.425 | +| clip_range | 0.138 | +| entropy_loss | -6.97 | +| explained_variance | -0.163 | +| learning_rate | 0.000181 | +| loss | -0.0498 | +| n_updates | 1872 | +| policy_gradient_loss | -0.0308 | +| value_loss | 0.000106 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.238 | +| time/ | | +| fps | 1324 | +| iterations | 470 | +| time_elapsed | 726 | +| total_timesteps | 962560 | +| train/ | | +| approx_kl | 0.039718457 | +| clip_fraction | 0.382 | +| clip_range | 0.138 | +| entropy_loss | -7 | +| explained_variance | -0.0421 | +| learning_rate | 0.000181 | +| loss | -0.0655 | +| n_updates | 1876 | +| policy_gradient_loss | -0.0332 | +| value_loss | 0.00014 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.229 | +| time/ | | +| fps | 1324 | +| iterations | 471 | +| time_elapsed | 728 | +| total_timesteps | 964608 | +| train/ | | +| approx_kl | 0.037438694 | +| clip_fraction | 0.382 | +| clip_range | 0.138 | +| entropy_loss | -7 | +| explained_variance | -0.235 | +| learning_rate | 0.000181 | +| loss | -0.0629 | +| n_updates | 1880 | +| policy_gradient_loss | -0.0323 | +| value_loss | 8.58e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.239 | +| time/ | | +| fps | 1324 | +| iterations | 472 | +| time_elapsed | 729 | +| total_timesteps | 966656 | +| train/ | | +| approx_kl | 0.03725655 | +| clip_fraction | 0.356 | +| clip_range | 0.138 | +| entropy_loss | -7.01 | +| explained_variance | -0.0497 | +| learning_rate | 0.000181 | +| loss | -0.0527 | +| n_updates | 1884 | +| policy_gradient_loss | -0.0294 | +| value_loss | 0.000157 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.241 | +| time/ | | +| fps | 1324 | +| iterations | 473 | +| time_elapsed | 731 | +| total_timesteps | 968704 | +| train/ | | +| approx_kl | 0.041775957 | +| clip_fraction | 0.424 | +| clip_range | 0.138 | +| entropy_loss | -7.04 | +| explained_variance | -0.0259 | +| learning_rate | 0.000181 | +| loss | -0.0436 | +| n_updates | 1888 | +| policy_gradient_loss | -0.0279 | +| value_loss | 0.000309 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.243 | +| time/ | | +| fps | 1324 | +| iterations | 474 | +| time_elapsed | 732 | +| total_timesteps | 970752 | +| train/ | | +| approx_kl | 0.038604017 | +| clip_fraction | 0.357 | +| clip_range | 0.138 | +| entropy_loss | -7.14 | +| explained_variance | 0.0268 | +| learning_rate | 0.000181 | +| loss | -0.0703 | +| n_updates | 1892 | +| policy_gradient_loss | -0.0362 | +| value_loss | 0.00011 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.241 | +| time/ | | +| fps | 1324 | +| iterations | 475 | +| time_elapsed | 734 | +| total_timesteps | 972800 | +| train/ | | +| approx_kl | 0.031197008 | +| clip_fraction | 0.391 | +| clip_range | 0.138 | +| entropy_loss | -7.09 | +| explained_variance | -0.0942 | +| learning_rate | 0.000181 | +| loss | -0.0509 | +| n_updates | 1896 | +| policy_gradient_loss | -0.0277 | +| value_loss | 0.00016 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.249 | +| time/ | | +| fps | 1324 | +| iterations | 476 | +| time_elapsed | 736 | +| total_timesteps | 974848 | +| train/ | | +| approx_kl | 0.037193537 | +| clip_fraction | 0.394 | +| clip_range | 0.138 | +| entropy_loss | -6.96 | +| explained_variance | -0.25 | +| learning_rate | 0.000181 | +| loss | -0.0538 | +| n_updates | 1900 | +| policy_gradient_loss | -0.0323 | +| value_loss | 0.000115 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.249 | +| time/ | | +| fps | 1324 | +| iterations | 477 | +| time_elapsed | 737 | +| total_timesteps | 976896 | +| train/ | | +| approx_kl | 0.038174428 | +| clip_fraction | 0.387 | +| clip_range | 0.138 | +| entropy_loss | -6.92 | +| explained_variance | -0.0302 | +| learning_rate | 0.000181 | +| loss | -0.057 | +| n_updates | 1904 | +| policy_gradient_loss | -0.0346 | +| value_loss | 0.000318 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.249 | +| time/ | | +| fps | 1324 | +| iterations | 478 | +| time_elapsed | 739 | +| total_timesteps | 978944 | +| train/ | | +| approx_kl | 0.038282864 | +| clip_fraction | 0.393 | +| clip_range | 0.138 | +| entropy_loss | -7.02 | +| explained_variance | -0.253 | +| learning_rate | 0.000181 | +| loss | -0.0625 | +| n_updates | 1908 | +| policy_gradient_loss | -0.0359 | +| value_loss | 0.000134 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.249 | +| time/ | | +| fps | 1324 | +| iterations | 479 | +| time_elapsed | 740 | +| total_timesteps | 980992 | +| train/ | | +| approx_kl | 0.033767775 | +| clip_fraction | 0.359 | +| clip_range | 0.138 | +| entropy_loss | -6.99 | +| explained_variance | -0.0679 | +| learning_rate | 0.000181 | +| loss | -0.0527 | +| n_updates | 1912 | +| policy_gradient_loss | -0.0323 | +| value_loss | 0.000221 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.249 | +| time/ | | +| fps | 1324 | +| iterations | 480 | +| time_elapsed | 742 | +| total_timesteps | 983040 | +| train/ | | +| approx_kl | 0.03330607 | +| clip_fraction | 0.383 | +| clip_range | 0.138 | +| entropy_loss | -6.89 | +| explained_variance | -0.0343 | +| learning_rate | 0.000181 | +| loss | -0.0526 | +| n_updates | 1916 | +| policy_gradient_loss | -0.0307 | +| value_loss | 0.000228 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.252 | +| time/ | | +| fps | 1324 | +| iterations | 481 | +| time_elapsed | 743 | +| total_timesteps | 985088 | +| train/ | | +| approx_kl | 0.045167133 | +| clip_fraction | 0.401 | +| clip_range | 0.138 | +| entropy_loss | -6.84 | +| explained_variance | -0.142 | +| learning_rate | 0.000181 | +| loss | -0.0519 | +| n_updates | 1920 | +| policy_gradient_loss | -0.0329 | +| value_loss | 0.000156 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.253 | +| time/ | | +| fps | 1324 | +| iterations | 482 | +| time_elapsed | 745 | +| total_timesteps | 987136 | +| train/ | | +| approx_kl | 0.03377254 | +| clip_fraction | 0.387 | +| clip_range | 0.138 | +| entropy_loss | -6.96 | +| explained_variance | -0.0924 | +| learning_rate | 0.00018 | +| loss | -0.0462 | +| n_updates | 1924 | +| policy_gradient_loss | -0.0336 | +| value_loss | 0.000119 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.25 | +| time/ | | +| fps | 1324 | +| iterations | 483 | +| time_elapsed | 746 | +| total_timesteps | 989184 | +| train/ | | +| approx_kl | 0.030226534 | +| clip_fraction | 0.38 | +| clip_range | 0.138 | +| entropy_loss | -6.78 | +| explained_variance | 0.00404 | +| learning_rate | 0.00018 | +| loss | -0.0508 | +| n_updates | 1928 | +| policy_gradient_loss | -0.0273 | +| value_loss | 0.000274 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.245 | +| time/ | | +| fps | 1324 | +| iterations | 484 | +| time_elapsed | 748 | +| total_timesteps | 991232 | +| train/ | | +| approx_kl | 0.03728776 | +| clip_fraction | 0.417 | +| clip_range | 0.138 | +| entropy_loss | -6.79 | +| explained_variance | -0.0411 | +| learning_rate | 0.00018 | +| loss | -0.0645 | +| n_updates | 1932 | +| policy_gradient_loss | -0.0326 | +| value_loss | 0.000165 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.249 | +| time/ | | +| fps | 1324 | +| iterations | 485 | +| time_elapsed | 750 | +| total_timesteps | 993280 | +| train/ | | +| approx_kl | 0.03591028 | +| clip_fraction | 0.343 | +| clip_range | 0.138 | +| entropy_loss | -6.86 | +| explained_variance | -0.0491 | +| learning_rate | 0.00018 | +| loss | -0.0531 | +| n_updates | 1936 | +| policy_gradient_loss | -0.0329 | +| value_loss | 0.000189 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.249 | +| time/ | | +| fps | 1324 | +| iterations | 486 | +| time_elapsed | 751 | +| total_timesteps | 995328 | +| train/ | | +| approx_kl | 0.03996642 | +| clip_fraction | 0.369 | +| clip_range | 0.138 | +| entropy_loss | -7.01 | +| explained_variance | -0.218 | +| learning_rate | 0.00018 | +| loss | -0.0544 | +| n_updates | 1940 | +| policy_gradient_loss | -0.0308 | +| value_loss | 0.00015 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.251 | +| time/ | | +| fps | 1324 | +| iterations | 487 | +| time_elapsed | 753 | +| total_timesteps | 997376 | +| train/ | | +| approx_kl | 0.04534325 | +| clip_fraction | 0.398 | +| clip_range | 0.138 | +| entropy_loss | -6.92 | +| explained_variance | -0.18 | +| learning_rate | 0.00018 | +| loss | -0.0485 | +| n_updates | 1944 | +| policy_gradient_loss | -0.0356 | +| value_loss | 0.000127 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.248 | +| time/ | | +| fps | 1324 | +| iterations | 488 | +| time_elapsed | 754 | +| total_timesteps | 999424 | +| train/ | | +| approx_kl | 0.036520306 | +| clip_fraction | 0.399 | +| clip_range | 0.138 | +| entropy_loss | -6.79 | +| explained_variance | -0.0743 | +| learning_rate | 0.00018 | +| loss | -0.0436 | +| n_updates | 1948 | +| policy_gradient_loss | -0.0318 | +| value_loss | 9.44e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.249 | +| time/ | | +| fps | 1324 | +| iterations | 489 | +| time_elapsed | 756 | +| total_timesteps | 1001472 | +| train/ | | +| approx_kl | 0.03519459 | +| clip_fraction | 0.407 | +| clip_range | 0.138 | +| entropy_loss | -6.77 | +| explained_variance | -0.0971 | +| learning_rate | 0.00018 | +| loss | -0.0505 | +| n_updates | 1952 | +| policy_gradient_loss | -0.0301 | +| value_loss | 0.000114 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.249 | +| time/ | | +| fps | 1324 | +| iterations | 490 | +| time_elapsed | 757 | +| total_timesteps | 1003520 | +| train/ | | +| approx_kl | 0.036696833 | +| clip_fraction | 0.404 | +| clip_range | 0.137 | +| entropy_loss | -6.8 | +| explained_variance | -0.138 | +| learning_rate | 0.00018 | +| loss | -0.0571 | +| n_updates | 1956 | +| policy_gradient_loss | -0.0304 | +| value_loss | 0.000103 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.249 | +| time/ | | +| fps | 1324 | +| iterations | 491 | +| time_elapsed | 759 | +| total_timesteps | 1005568 | +| train/ | | +| approx_kl | 0.03849771 | +| clip_fraction | 0.396 | +| clip_range | 0.137 | +| entropy_loss | -6.85 | +| explained_variance | 0.0166 | +| learning_rate | 0.00018 | +| loss | -0.0494 | +| n_updates | 1960 | +| policy_gradient_loss | -0.031 | +| value_loss | 0.000126 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.249 | +| time/ | | +| fps | 1324 | +| iterations | 492 | +| time_elapsed | 760 | +| total_timesteps | 1007616 | +| train/ | | +| approx_kl | 0.045636714 | +| clip_fraction | 0.424 | +| clip_range | 0.137 | +| entropy_loss | -6.84 | +| explained_variance | -0.228 | +| learning_rate | 0.00018 | +| loss | -0.0505 | +| n_updates | 1964 | +| policy_gradient_loss | -0.0306 | +| value_loss | 0.000133 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.257 | +| time/ | | +| fps | 1324 | +| iterations | 493 | +| time_elapsed | 762 | +| total_timesteps | 1009664 | +| train/ | | +| approx_kl | 0.040150873 | +| clip_fraction | 0.389 | +| clip_range | 0.137 | +| entropy_loss | -6.9 | +| explained_variance | -0.14 | +| learning_rate | 0.00018 | +| loss | -0.0551 | +| n_updates | 1968 | +| policy_gradient_loss | -0.0337 | +| value_loss | 6.11e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.262 | +| time/ | | +| fps | 1324 | +| iterations | 494 | +| time_elapsed | 764 | +| total_timesteps | 1011712 | +| train/ | | +| approx_kl | 0.043752924 | +| clip_fraction | 0.379 | +| clip_range | 0.137 | +| entropy_loss | -6.84 | +| explained_variance | -0.0418 | +| learning_rate | 0.00018 | +| loss | -0.041 | +| n_updates | 1972 | +| policy_gradient_loss | -0.0256 | +| value_loss | 0.000215 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.262 | +| time/ | | +| fps | 1323 | +| iterations | 495 | +| time_elapsed | 765 | +| total_timesteps | 1013760 | +| train/ | | +| approx_kl | 0.041017167 | +| clip_fraction | 0.422 | +| clip_range | 0.137 | +| entropy_loss | -6.79 | +| explained_variance | -0.266 | +| learning_rate | 0.00018 | +| loss | -0.0606 | +| n_updates | 1976 | +| policy_gradient_loss | -0.0336 | +| value_loss | 0.000154 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.264 | +| time/ | | +| fps | 1323 | +| iterations | 496 | +| time_elapsed | 767 | +| total_timesteps | 1015808 | +| train/ | | +| approx_kl | 0.041257128 | +| clip_fraction | 0.4 | +| clip_range | 0.137 | +| entropy_loss | -6.79 | +| explained_variance | -0.104 | +| learning_rate | 0.00018 | +| loss | -0.0581 | +| n_updates | 1980 | +| policy_gradient_loss | -0.0326 | +| value_loss | 0.000238 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.264 | +| time/ | | +| fps | 1323 | +| iterations | 497 | +| time_elapsed | 768 | +| total_timesteps | 1017856 | +| train/ | | +| approx_kl | 0.04183017 | +| clip_fraction | 0.392 | +| clip_range | 0.137 | +| entropy_loss | -6.82 | +| explained_variance | -0.194 | +| learning_rate | 0.00018 | +| loss | -0.0621 | +| n_updates | 1984 | +| policy_gradient_loss | -0.0344 | +| value_loss | 8.32e-05 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.251 | +| time/ | | +| fps | 1323 | +| iterations | 498 | +| time_elapsed | 770 | +| total_timesteps | 1019904 | +| train/ | | +| approx_kl | 0.04290753 | +| clip_fraction | 0.375 | +| clip_range | 0.137 | +| entropy_loss | -6.83 | +| explained_variance | -0.139 | +| learning_rate | 0.00018 | +| loss | -0.0698 | +| n_updates | 1988 | +| policy_gradient_loss | -0.0379 | +| value_loss | 6.52e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.247 | +| time/ | | +| fps | 1323 | +| iterations | 499 | +| time_elapsed | 771 | +| total_timesteps | 1021952 | +| train/ | | +| approx_kl | 0.044690594 | +| clip_fraction | 0.411 | +| clip_range | 0.137 | +| entropy_loss | -6.82 | +| explained_variance | -0.151 | +| learning_rate | 0.00018 | +| loss | -0.0625 | +| n_updates | 1992 | +| policy_gradient_loss | -0.0364 | +| value_loss | 0.000117 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.248 | +| time/ | | +| fps | 1323 | +| iterations | 500 | +| time_elapsed | 773 | +| total_timesteps | 1024000 | +| train/ | | +| approx_kl | 0.043467056 | +| clip_fraction | 0.365 | +| clip_range | 0.137 | +| entropy_loss | -6.78 | +| explained_variance | -0.112 | +| learning_rate | 0.00018 | +| loss | -0.0572 | +| n_updates | 1996 | +| policy_gradient_loss | -0.0317 | +| value_loss | 0.000124 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.246 | +| time/ | | +| fps | 1323 | +| iterations | 501 | +| time_elapsed | 775 | +| total_timesteps | 1026048 | +| train/ | | +| approx_kl | 0.047341507 | +| clip_fraction | 0.452 | +| clip_range | 0.137 | +| entropy_loss | -6.81 | +| explained_variance | -0.158 | +| learning_rate | 0.00018 | +| loss | -0.055 | +| n_updates | 2000 | +| policy_gradient_loss | -0.033 | +| value_loss | 6.26e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.246 | +| time/ | | +| fps | 1323 | +| iterations | 502 | +| time_elapsed | 776 | +| total_timesteps | 1028096 | +| train/ | | +| approx_kl | 0.046221107 | +| clip_fraction | 0.405 | +| clip_range | 0.137 | +| entropy_loss | -6.71 | +| explained_variance | -0.0674 | +| learning_rate | 0.00018 | +| loss | -0.0644 | +| n_updates | 2004 | +| policy_gradient_loss | -0.0354 | +| value_loss | 0.000242 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.244 | +| time/ | | +| fps | 1324 | +| iterations | 503 | +| time_elapsed | 778 | +| total_timesteps | 1030144 | +| train/ | | +| approx_kl | 0.040339928 | +| clip_fraction | 0.416 | +| clip_range | 0.137 | +| entropy_loss | -6.79 | +| explained_variance | -0.218 | +| learning_rate | 0.00018 | +| loss | -0.0604 | +| n_updates | 2008 | +| policy_gradient_loss | -0.0374 | +| value_loss | 0.000157 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.245 | +| time/ | | +| fps | 1324 | +| iterations | 504 | +| time_elapsed | 779 | +| total_timesteps | 1032192 | +| train/ | | +| approx_kl | 0.045155488 | +| clip_fraction | 0.418 | +| clip_range | 0.137 | +| entropy_loss | -6.84 | +| explained_variance | -0.0717 | +| learning_rate | 0.00018 | +| loss | -0.0579 | +| n_updates | 2012 | +| policy_gradient_loss | -0.0385 | +| value_loss | 0.000131 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.243 | +| time/ | | +| fps | 1324 | +| iterations | 505 | +| time_elapsed | 781 | +| total_timesteps | 1034240 | +| train/ | | +| approx_kl | 0.04100118 | +| clip_fraction | 0.428 | +| clip_range | 0.137 | +| entropy_loss | -6.81 | +| explained_variance | -0.0268 | +| learning_rate | 0.00018 | +| loss | -0.0593 | +| n_updates | 2016 | +| policy_gradient_loss | -0.0324 | +| value_loss | 0.000186 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.246 | +| time/ | | +| fps | 1324 | +| iterations | 506 | +| time_elapsed | 782 | +| total_timesteps | 1036288 | +| train/ | | +| approx_kl | 0.043779157 | +| clip_fraction | 0.409 | +| clip_range | 0.137 | +| entropy_loss | -6.77 | +| explained_variance | -0.075 | +| learning_rate | 0.00018 | +| loss | -0.0428 | +| n_updates | 2020 | +| policy_gradient_loss | -0.0302 | +| value_loss | 0.000161 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.243 | +| time/ | | +| fps | 1324 | +| iterations | 507 | +| time_elapsed | 784 | +| total_timesteps | 1038336 | +| train/ | | +| approx_kl | 0.03733225 | +| clip_fraction | 0.396 | +| clip_range | 0.137 | +| entropy_loss | -6.85 | +| explained_variance | -0.116 | +| learning_rate | 0.000179 | +| loss | -0.0472 | +| n_updates | 2024 | +| policy_gradient_loss | -0.0287 | +| value_loss | 0.00014 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.246 | +| time/ | | +| fps | 1324 | +| iterations | 508 | +| time_elapsed | 785 | +| total_timesteps | 1040384 | +| train/ | | +| approx_kl | 0.03963561 | +| clip_fraction | 0.368 | +| clip_range | 0.137 | +| entropy_loss | -6.76 | +| explained_variance | -0.179 | +| learning_rate | 0.000179 | +| loss | -0.0609 | +| n_updates | 2028 | +| policy_gradient_loss | -0.0344 | +| value_loss | 0.000116 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.246 | +| time/ | | +| fps | 1324 | +| iterations | 509 | +| time_elapsed | 787 | +| total_timesteps | 1042432 | +| train/ | | +| approx_kl | 0.044134498 | +| clip_fraction | 0.362 | +| clip_range | 0.137 | +| entropy_loss | -6.8 | +| explained_variance | -0.0204 | +| learning_rate | 0.000179 | +| loss | -0.0475 | +| n_updates | 2032 | +| policy_gradient_loss | -0.0294 | +| value_loss | 0.000226 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.242 | +| time/ | | +| fps | 1324 | +| iterations | 510 | +| time_elapsed | 788 | +| total_timesteps | 1044480 | +| train/ | | +| approx_kl | 0.044276398 | +| clip_fraction | 0.403 | +| clip_range | 0.137 | +| entropy_loss | -6.78 | +| explained_variance | -0.0799 | +| learning_rate | 0.000179 | +| loss | -0.0657 | +| n_updates | 2036 | +| policy_gradient_loss | -0.0358 | +| value_loss | 0.000154 | +----------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.242 | +| time/ | | +| fps | 1324 | +| iterations | 511 | +| time_elapsed | 790 | +| total_timesteps | 1046528 | +| train/ | | +| approx_kl | 0.036749 | +| clip_fraction | 0.37 | +| clip_range | 0.137 | +| entropy_loss | -6.79 | +| explained_variance | -0.254 | +| learning_rate | 0.000179 | +| loss | -0.0614 | +| n_updates | 2040 | +| policy_gradient_loss | -0.0381 | +| value_loss | 8.6e-05 | +-------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.244 | +| time/ | | +| fps | 1324 | +| iterations | 512 | +| time_elapsed | 791 | +| total_timesteps | 1048576 | +| train/ | | +| approx_kl | 0.050464973 | +| clip_fraction | 0.406 | +| clip_range | 0.137 | +| entropy_loss | -6.85 | +| explained_variance | -0.144 | +| learning_rate | 0.000179 | +| loss | -0.0504 | +| n_updates | 2044 | +| policy_gradient_loss | -0.0329 | +| value_loss | 0.000148 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.239 | +| time/ | | +| fps | 1324 | +| iterations | 513 | +| time_elapsed | 793 | +| total_timesteps | 1050624 | +| train/ | | +| approx_kl | 0.03962288 | +| clip_fraction | 0.413 | +| clip_range | 0.137 | +| entropy_loss | -6.85 | +| explained_variance | -0.136 | +| learning_rate | 0.000179 | +| loss | -0.0622 | +| n_updates | 2048 | +| policy_gradient_loss | -0.0349 | +| value_loss | 0.0001 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.237 | +| time/ | | +| fps | 1324 | +| iterations | 514 | +| time_elapsed | 794 | +| total_timesteps | 1052672 | +| train/ | | +| approx_kl | 0.04482959 | +| clip_fraction | 0.386 | +| clip_range | 0.137 | +| entropy_loss | -6.8 | +| explained_variance | -0.0599 | +| learning_rate | 0.000179 | +| loss | -0.0547 | +| n_updates | 2052 | +| policy_gradient_loss | -0.0334 | +| value_loss | 9.46e-05 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.24 | +| time/ | | +| fps | 1324 | +| iterations | 515 | +| time_elapsed | 796 | +| total_timesteps | 1054720 | +| train/ | | +| approx_kl | 0.03891128 | +| clip_fraction | 0.407 | +| clip_range | 0.137 | +| entropy_loss | -6.99 | +| explained_variance | -0.058 | +| learning_rate | 0.000179 | +| loss | -0.0487 | +| n_updates | 2056 | +| policy_gradient_loss | -0.0271 | +| value_loss | 0.000125 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.242 | +| time/ | | +| fps | 1324 | +| iterations | 516 | +| time_elapsed | 798 | +| total_timesteps | 1056768 | +| train/ | | +| approx_kl | 0.04748683 | +| clip_fraction | 0.422 | +| clip_range | 0.137 | +| entropy_loss | -6.9 | +| explained_variance | -0.0132 | +| learning_rate | 0.000179 | +| loss | -0.0605 | +| n_updates | 2060 | +| policy_gradient_loss | -0.0366 | +| value_loss | 0.000115 | +---------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.245 | +| time/ | | +| fps | 1324 | +| iterations | 517 | +| time_elapsed | 799 | +| total_timesteps | 1058816 | +| train/ | | +| approx_kl | 0.0404681 | +| clip_fraction | 0.375 | +| clip_range | 0.137 | +| entropy_loss | -6.85 | +| explained_variance | -0.0635 | +| learning_rate | 0.000179 | +| loss | -0.0533 | +| n_updates | 2064 | +| policy_gradient_loss | -0.031 | +| value_loss | 0.00019 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.241 | +| time/ | | +| fps | 1324 | +| iterations | 518 | +| time_elapsed | 801 | +| total_timesteps | 1060864 | +| train/ | | +| approx_kl | 0.044583384 | +| clip_fraction | 0.424 | +| clip_range | 0.137 | +| entropy_loss | -6.79 | +| explained_variance | -0.316 | +| learning_rate | 0.000179 | +| loss | -0.0641 | +| n_updates | 2068 | +| policy_gradient_loss | -0.0352 | +| value_loss | 9.27e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.241 | +| time/ | | +| fps | 1324 | +| iterations | 519 | +| time_elapsed | 802 | +| total_timesteps | 1062912 | +| train/ | | +| approx_kl | 0.041461438 | +| clip_fraction | 0.413 | +| clip_range | 0.137 | +| entropy_loss | -6.76 | +| explained_variance | -0.112 | +| learning_rate | 0.000179 | +| loss | -0.0603 | +| n_updates | 2072 | +| policy_gradient_loss | -0.0329 | +| value_loss | 0.000139 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.24 | +| time/ | | +| fps | 1324 | +| iterations | 520 | +| time_elapsed | 804 | +| total_timesteps | 1064960 | +| train/ | | +| approx_kl | 0.043367933 | +| clip_fraction | 0.407 | +| clip_range | 0.137 | +| entropy_loss | -6.66 | +| explained_variance | -0.119 | +| learning_rate | 0.000179 | +| loss | -0.0488 | +| n_updates | 2076 | +| policy_gradient_loss | -0.0332 | +| value_loss | 0.000161 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.24 | +| time/ | | +| fps | 1323 | +| iterations | 521 | +| time_elapsed | 805 | +| total_timesteps | 1067008 | +| train/ | | +| approx_kl | 0.04171395 | +| clip_fraction | 0.404 | +| clip_range | 0.137 | +| entropy_loss | -6.76 | +| explained_variance | 0.00308 | +| learning_rate | 0.000179 | +| loss | -0.0509 | +| n_updates | 2080 | +| policy_gradient_loss | -0.0311 | +| value_loss | 0.000215 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.244 | +| time/ | | +| fps | 1324 | +| iterations | 522 | +| time_elapsed | 807 | +| total_timesteps | 1069056 | +| train/ | | +| approx_kl | 0.048984673 | +| clip_fraction | 0.402 | +| clip_range | 0.137 | +| entropy_loss | -6.76 | +| explained_variance | -0.705 | +| learning_rate | 0.000179 | +| loss | -0.0644 | +| n_updates | 2084 | +| policy_gradient_loss | -0.0397 | +| value_loss | 6.2e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.245 | +| time/ | | +| fps | 1324 | +| iterations | 523 | +| time_elapsed | 808 | +| total_timesteps | 1071104 | +| train/ | | +| approx_kl | 0.036332637 | +| clip_fraction | 0.397 | +| clip_range | 0.137 | +| entropy_loss | -6.63 | +| explained_variance | -0.0563 | +| learning_rate | 0.000179 | +| loss | -0.048 | +| n_updates | 2088 | +| policy_gradient_loss | -0.0277 | +| value_loss | 0.000147 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.242 | +| time/ | | +| fps | 1323 | +| iterations | 524 | +| time_elapsed | 810 | +| total_timesteps | 1073152 | +| train/ | | +| approx_kl | 0.043401666 | +| clip_fraction | 0.397 | +| clip_range | 0.137 | +| entropy_loss | -6.69 | +| explained_variance | -0.127 | +| learning_rate | 0.000179 | +| loss | -0.0534 | +| n_updates | 2092 | +| policy_gradient_loss | -0.0317 | +| value_loss | 9.58e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.242 | +| time/ | | +| fps | 1323 | +| iterations | 525 | +| time_elapsed | 812 | +| total_timesteps | 1075200 | +| train/ | | +| approx_kl | 0.04680033 | +| clip_fraction | 0.405 | +| clip_range | 0.137 | +| entropy_loss | -6.64 | +| explained_variance | -0.23 | +| learning_rate | 0.000179 | +| loss | -0.0546 | +| n_updates | 2096 | +| policy_gradient_loss | -0.035 | +| value_loss | 0.000107 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.242 | +| time/ | | +| fps | 1324 | +| iterations | 526 | +| time_elapsed | 813 | +| total_timesteps | 1077248 | +| train/ | | +| approx_kl | 0.042139836 | +| clip_fraction | 0.438 | +| clip_range | 0.137 | +| entropy_loss | -6.61 | +| explained_variance | -0.0882 | +| learning_rate | 0.000179 | +| loss | -0.0525 | +| n_updates | 2100 | +| policy_gradient_loss | -0.0299 | +| value_loss | 0.000128 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.248 | +| time/ | | +| fps | 1324 | +| iterations | 527 | +| time_elapsed | 815 | +| total_timesteps | 1079296 | +| train/ | | +| approx_kl | 0.037972078 | +| clip_fraction | 0.403 | +| clip_range | 0.137 | +| entropy_loss | -6.7 | +| explained_variance | -0.197 | +| learning_rate | 0.000179 | +| loss | -0.0553 | +| n_updates | 2104 | +| policy_gradient_loss | -0.0314 | +| value_loss | 0.000108 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.247 | +| time/ | | +| fps | 1324 | +| iterations | 528 | +| time_elapsed | 816 | +| total_timesteps | 1081344 | +| train/ | | +| approx_kl | 0.039674252 | +| clip_fraction | 0.435 | +| clip_range | 0.137 | +| entropy_loss | -6.75 | +| explained_variance | 0.0553 | +| learning_rate | 0.000179 | +| loss | -0.0488 | +| n_updates | 2108 | +| policy_gradient_loss | -0.025 | +| value_loss | 0.000124 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.242 | +| time/ | | +| fps | 1324 | +| iterations | 529 | +| time_elapsed | 818 | +| total_timesteps | 1083392 | +| train/ | | +| approx_kl | 0.040549982 | +| clip_fraction | 0.395 | +| clip_range | 0.136 | +| entropy_loss | -6.71 | +| explained_variance | 0.049 | +| learning_rate | 0.000179 | +| loss | -0.045 | +| n_updates | 2112 | +| policy_gradient_loss | -0.0276 | +| value_loss | 0.000114 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.236 | +| time/ | | +| fps | 1323 | +| iterations | 530 | +| time_elapsed | 819 | +| total_timesteps | 1085440 | +| train/ | | +| approx_kl | 0.045524523 | +| clip_fraction | 0.403 | +| clip_range | 0.136 | +| entropy_loss | -6.71 | +| explained_variance | -0.132 | +| learning_rate | 0.000179 | +| loss | -0.065 | +| n_updates | 2116 | +| policy_gradient_loss | -0.04 | +| value_loss | 0.000173 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.236 | +| time/ | | +| fps | 1324 | +| iterations | 531 | +| time_elapsed | 821 | +| total_timesteps | 1087488 | +| train/ | | +| approx_kl | 0.049635783 | +| clip_fraction | 0.416 | +| clip_range | 0.136 | +| entropy_loss | -6.74 | +| explained_variance | -0.0168 | +| learning_rate | 0.000179 | +| loss | -0.0622 | +| n_updates | 2120 | +| policy_gradient_loss | -0.0343 | +| value_loss | 0.00017 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.241 | +| time/ | | +| fps | 1324 | +| iterations | 532 | +| time_elapsed | 822 | +| total_timesteps | 1089536 | +| train/ | | +| approx_kl | 0.045522586 | +| clip_fraction | 0.414 | +| clip_range | 0.136 | +| entropy_loss | -6.8 | +| explained_variance | -0.495 | +| learning_rate | 0.000178 | +| loss | -0.0638 | +| n_updates | 2124 | +| policy_gradient_loss | -0.0422 | +| value_loss | 7.3e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.241 | +| time/ | | +| fps | 1323 | +| iterations | 533 | +| time_elapsed | 824 | +| total_timesteps | 1091584 | +| train/ | | +| approx_kl | 0.052781865 | +| clip_fraction | 0.418 | +| clip_range | 0.136 | +| entropy_loss | -6.84 | +| explained_variance | 0.00124 | +| learning_rate | 0.000178 | +| loss | -0.0513 | +| n_updates | 2128 | +| policy_gradient_loss | -0.0308 | +| value_loss | 0.000257 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.243 | +| time/ | | +| fps | 1323 | +| iterations | 534 | +| time_elapsed | 826 | +| total_timesteps | 1093632 | +| train/ | | +| approx_kl | 0.044970423 | +| clip_fraction | 0.417 | +| clip_range | 0.136 | +| entropy_loss | -6.79 | +| explained_variance | -0.461 | +| learning_rate | 0.000178 | +| loss | -0.0665 | +| n_updates | 2132 | +| policy_gradient_loss | -0.0401 | +| value_loss | 6.72e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.24 | +| time/ | | +| fps | 1323 | +| iterations | 535 | +| time_elapsed | 827 | +| total_timesteps | 1095680 | +| train/ | | +| approx_kl | 0.039455675 | +| clip_fraction | 0.412 | +| clip_range | 0.136 | +| entropy_loss | -6.78 | +| explained_variance | -0.546 | +| learning_rate | 0.000178 | +| loss | -0.0543 | +| n_updates | 2136 | +| policy_gradient_loss | -0.0341 | +| value_loss | 4.26e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.234 | +| time/ | | +| fps | 1323 | +| iterations | 536 | +| time_elapsed | 829 | +| total_timesteps | 1097728 | +| train/ | | +| approx_kl | 0.043014467 | +| clip_fraction | 0.392 | +| clip_range | 0.136 | +| entropy_loss | -6.69 | +| explained_variance | -0.0894 | +| learning_rate | 0.000178 | +| loss | -0.0646 | +| n_updates | 2140 | +| policy_gradient_loss | -0.0354 | +| value_loss | 7.37e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.233 | +| time/ | | +| fps | 1323 | +| iterations | 537 | +| time_elapsed | 830 | +| total_timesteps | 1099776 | +| train/ | | +| approx_kl | 0.040377505 | +| clip_fraction | 0.396 | +| clip_range | 0.136 | +| entropy_loss | -6.74 | +| explained_variance | -0.051 | +| learning_rate | 0.000178 | +| loss | -0.0486 | +| n_updates | 2144 | +| policy_gradient_loss | -0.0309 | +| value_loss | 0.00019 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.233 | +| time/ | | +| fps | 1323 | +| iterations | 538 | +| time_elapsed | 832 | +| total_timesteps | 1101824 | +| train/ | | +| approx_kl | 0.04055824 | +| clip_fraction | 0.366 | +| clip_range | 0.136 | +| entropy_loss | -6.84 | +| explained_variance | -0.0776 | +| learning_rate | 0.000178 | +| loss | -0.0585 | +| n_updates | 2148 | +| policy_gradient_loss | -0.0331 | +| value_loss | 0.000141 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.233 | +| time/ | | +| fps | 1323 | +| iterations | 539 | +| time_elapsed | 834 | +| total_timesteps | 1103872 | +| train/ | | +| approx_kl | 0.044406593 | +| clip_fraction | 0.406 | +| clip_range | 0.136 | +| entropy_loss | -6.82 | +| explained_variance | -0.0896 | +| learning_rate | 0.000178 | +| loss | -0.0743 | +| n_updates | 2152 | +| policy_gradient_loss | -0.0377 | +| value_loss | 9.09e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.222 | +| time/ | | +| fps | 1323 | +| iterations | 540 | +| time_elapsed | 835 | +| total_timesteps | 1105920 | +| train/ | | +| approx_kl | 0.03796513 | +| clip_fraction | 0.361 | +| clip_range | 0.136 | +| entropy_loss | -6.82 | +| explained_variance | -0.13 | +| learning_rate | 0.000178 | +| loss | -0.0512 | +| n_updates | 2156 | +| policy_gradient_loss | -0.0316 | +| value_loss | 0.000111 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.217 | +| time/ | | +| fps | 1323 | +| iterations | 541 | +| time_elapsed | 837 | +| total_timesteps | 1107968 | +| train/ | | +| approx_kl | 0.03552161 | +| clip_fraction | 0.377 | +| clip_range | 0.136 | +| entropy_loss | -6.83 | +| explained_variance | -0.0579 | +| learning_rate | 0.000178 | +| loss | -0.0508 | +| n_updates | 2160 | +| policy_gradient_loss | -0.028 | +| value_loss | 0.000173 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.22 | +| time/ | | +| fps | 1323 | +| iterations | 542 | +| time_elapsed | 838 | +| total_timesteps | 1110016 | +| train/ | | +| approx_kl | 0.04052953 | +| clip_fraction | 0.4 | +| clip_range | 0.136 | +| entropy_loss | -6.95 | +| explained_variance | 0.033 | +| learning_rate | 0.000178 | +| loss | -0.0602 | +| n_updates | 2164 | +| policy_gradient_loss | -0.0357 | +| value_loss | 0.000144 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.214 | +| time/ | | +| fps | 1323 | +| iterations | 543 | +| time_elapsed | 840 | +| total_timesteps | 1112064 | +| train/ | | +| approx_kl | 0.036605872 | +| clip_fraction | 0.411 | +| clip_range | 0.136 | +| entropy_loss | -6.89 | +| explained_variance | 0.0162 | +| learning_rate | 0.000178 | +| loss | -0.0473 | +| n_updates | 2168 | +| policy_gradient_loss | -0.0322 | +| value_loss | 0.000111 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.209 | +| time/ | | +| fps | 1323 | +| iterations | 544 | +| time_elapsed | 841 | +| total_timesteps | 1114112 | +| train/ | | +| approx_kl | 0.031306233 | +| clip_fraction | 0.389 | +| clip_range | 0.136 | +| entropy_loss | -6.98 | +| explained_variance | -0.137 | +| learning_rate | 0.000178 | +| loss | -0.0575 | +| n_updates | 2172 | +| policy_gradient_loss | -0.0342 | +| value_loss | 0.000117 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.212 | +| time/ | | +| fps | 1323 | +| iterations | 545 | +| time_elapsed | 843 | +| total_timesteps | 1116160 | +| train/ | | +| approx_kl | 0.034686387 | +| clip_fraction | 0.379 | +| clip_range | 0.136 | +| entropy_loss | -7.06 | +| explained_variance | -0.00514 | +| learning_rate | 0.000178 | +| loss | -0.063 | +| n_updates | 2176 | +| policy_gradient_loss | -0.0367 | +| value_loss | 0.000107 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.206 | +| time/ | | +| fps | 1323 | +| iterations | 546 | +| time_elapsed | 845 | +| total_timesteps | 1118208 | +| train/ | | +| approx_kl | 0.03688153 | +| clip_fraction | 0.374 | +| clip_range | 0.136 | +| entropy_loss | -7.03 | +| explained_variance | -0.192 | +| learning_rate | 0.000178 | +| loss | -0.0537 | +| n_updates | 2180 | +| policy_gradient_loss | -0.0336 | +| value_loss | 0.000173 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.212 | +| time/ | | +| fps | 1323 | +| iterations | 547 | +| time_elapsed | 846 | +| total_timesteps | 1120256 | +| train/ | | +| approx_kl | 0.04269673 | +| clip_fraction | 0.377 | +| clip_range | 0.136 | +| entropy_loss | -6.96 | +| explained_variance | -0.192 | +| learning_rate | 0.000178 | +| loss | -0.0634 | +| n_updates | 2184 | +| policy_gradient_loss | -0.0354 | +| value_loss | 0.000112 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.201 | +| time/ | | +| fps | 1323 | +| iterations | 548 | +| time_elapsed | 848 | +| total_timesteps | 1122304 | +| train/ | | +| approx_kl | 0.037773043 | +| clip_fraction | 0.351 | +| clip_range | 0.136 | +| entropy_loss | -7.06 | +| explained_variance | -0.0173 | +| learning_rate | 0.000178 | +| loss | -0.0485 | +| n_updates | 2188 | +| policy_gradient_loss | -0.0317 | +| value_loss | 0.000229 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.201 | +| time/ | | +| fps | 1323 | +| iterations | 549 | +| time_elapsed | 849 | +| total_timesteps | 1124352 | +| train/ | | +| approx_kl | 0.03807593 | +| clip_fraction | 0.361 | +| clip_range | 0.136 | +| entropy_loss | -6.93 | +| explained_variance | 0.00851 | +| learning_rate | 0.000178 | +| loss | -0.0466 | +| n_updates | 2192 | +| policy_gradient_loss | -0.0326 | +| value_loss | 0.000239 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.196 | +| time/ | | +| fps | 1323 | +| iterations | 550 | +| time_elapsed | 851 | +| total_timesteps | 1126400 | +| train/ | | +| approx_kl | 0.038819067 | +| clip_fraction | 0.397 | +| clip_range | 0.136 | +| entropy_loss | -7.06 | +| explained_variance | -0.233 | +| learning_rate | 0.000178 | +| loss | -0.057 | +| n_updates | 2196 | +| policy_gradient_loss | -0.0364 | +| value_loss | 0.000103 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.196 | +| time/ | | +| fps | 1322 | +| iterations | 551 | +| time_elapsed | 852 | +| total_timesteps | 1128448 | +| train/ | | +| approx_kl | 0.033809297 | +| clip_fraction | 0.372 | +| clip_range | 0.136 | +| entropy_loss | -7.1 | +| explained_variance | -0.153 | +| learning_rate | 0.000178 | +| loss | -0.0604 | +| n_updates | 2200 | +| policy_gradient_loss | -0.0309 | +| value_loss | 0.000123 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.197 | +| time/ | | +| fps | 1323 | +| iterations | 552 | +| time_elapsed | 854 | +| total_timesteps | 1130496 | +| train/ | | +| approx_kl | 0.042088438 | +| clip_fraction | 0.381 | +| clip_range | 0.136 | +| entropy_loss | -7.07 | +| explained_variance | -0.0386 | +| learning_rate | 0.000178 | +| loss | -0.0602 | +| n_updates | 2204 | +| policy_gradient_loss | -0.0348 | +| value_loss | 0.000104 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.201 | +| time/ | | +| fps | 1323 | +| iterations | 553 | +| time_elapsed | 855 | +| total_timesteps | 1132544 | +| train/ | | +| approx_kl | 0.037923843 | +| clip_fraction | 0.37 | +| clip_range | 0.136 | +| entropy_loss | -7.05 | +| explained_variance | -0.0175 | +| learning_rate | 0.000178 | +| loss | -0.05 | +| n_updates | 2208 | +| policy_gradient_loss | -0.0312 | +| value_loss | 0.000137 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.194 | +| time/ | | +| fps | 1323 | +| iterations | 554 | +| time_elapsed | 857 | +| total_timesteps | 1134592 | +| train/ | | +| approx_kl | 0.037254903 | +| clip_fraction | 0.378 | +| clip_range | 0.136 | +| entropy_loss | -7.16 | +| explained_variance | -0.0951 | +| learning_rate | 0.000178 | +| loss | -0.0592 | +| n_updates | 2212 | +| policy_gradient_loss | -0.0331 | +| value_loss | 0.000128 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.191 | +| time/ | | +| fps | 1323 | +| iterations | 555 | +| time_elapsed | 859 | +| total_timesteps | 1136640 | +| train/ | | +| approx_kl | 0.035914317 | +| clip_fraction | 0.382 | +| clip_range | 0.136 | +| entropy_loss | -7.15 | +| explained_variance | 0.0339 | +| learning_rate | 0.000178 | +| loss | -0.0677 | +| n_updates | 2216 | +| policy_gradient_loss | -0.0363 | +| value_loss | 9.31e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.195 | +| time/ | | +| fps | 1323 | +| iterations | 556 | +| time_elapsed | 860 | +| total_timesteps | 1138688 | +| train/ | | +| approx_kl | 0.037247203 | +| clip_fraction | 0.357 | +| clip_range | 0.136 | +| entropy_loss | -7.11 | +| explained_variance | -0.164 | +| learning_rate | 0.000177 | +| loss | -0.052 | +| n_updates | 2220 | +| policy_gradient_loss | -0.0372 | +| value_loss | 0.000111 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.195 | +| time/ | | +| fps | 1322 | +| iterations | 557 | +| time_elapsed | 862 | +| total_timesteps | 1140736 | +| train/ | | +| approx_kl | 0.040942006 | +| clip_fraction | 0.368 | +| clip_range | 0.136 | +| entropy_loss | -7.09 | +| explained_variance | -0.0223 | +| learning_rate | 0.000177 | +| loss | -0.0541 | +| n_updates | 2224 | +| policy_gradient_loss | -0.0328 | +| value_loss | 0.000193 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.195 | +| time/ | | +| fps | 1322 | +| iterations | 558 | +| time_elapsed | 863 | +| total_timesteps | 1142784 | +| train/ | | +| approx_kl | 0.03944481 | +| clip_fraction | 0.371 | +| clip_range | 0.136 | +| entropy_loss | -7.23 | +| explained_variance | -0.182 | +| learning_rate | 0.000177 | +| loss | -0.0581 | +| n_updates | 2228 | +| policy_gradient_loss | -0.0389 | +| value_loss | 0.000108 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.197 | +| time/ | | +| fps | 1322 | +| iterations | 559 | +| time_elapsed | 865 | +| total_timesteps | 1144832 | +| train/ | | +| approx_kl | 0.042244226 | +| clip_fraction | 0.395 | +| clip_range | 0.136 | +| entropy_loss | -7.15 | +| explained_variance | -0.53 | +| learning_rate | 0.000177 | +| loss | -0.0714 | +| n_updates | 2232 | +| policy_gradient_loss | -0.0419 | +| value_loss | 5.45e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.191 | +| time/ | | +| fps | 1322 | +| iterations | 560 | +| time_elapsed | 866 | +| total_timesteps | 1146880 | +| train/ | | +| approx_kl | 0.037455708 | +| clip_fraction | 0.386 | +| clip_range | 0.136 | +| entropy_loss | -7.17 | +| explained_variance | -0.148 | +| learning_rate | 0.000177 | +| loss | -0.046 | +| n_updates | 2236 | +| policy_gradient_loss | -0.0308 | +| value_loss | 0.000101 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.19 | +| time/ | | +| fps | 1322 | +| iterations | 561 | +| time_elapsed | 868 | +| total_timesteps | 1148928 | +| train/ | | +| approx_kl | 0.039682094 | +| clip_fraction | 0.371 | +| clip_range | 0.136 | +| entropy_loss | -7.14 | +| explained_variance | -0.22 | +| learning_rate | 0.000177 | +| loss | -0.0603 | +| n_updates | 2240 | +| policy_gradient_loss | -0.037 | +| value_loss | 5.38e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.189 | +| time/ | | +| fps | 1322 | +| iterations | 562 | +| time_elapsed | 869 | +| total_timesteps | 1150976 | +| train/ | | +| approx_kl | 0.03919369 | +| clip_fraction | 0.36 | +| clip_range | 0.136 | +| entropy_loss | -7.23 | +| explained_variance | 0.00843 | +| learning_rate | 0.000177 | +| loss | -0.0595 | +| n_updates | 2244 | +| policy_gradient_loss | -0.0328 | +| value_loss | 0.000132 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.186 | +| time/ | | +| fps | 1322 | +| iterations | 563 | +| time_elapsed | 871 | +| total_timesteps | 1153024 | +| train/ | | +| approx_kl | 0.045257177 | +| clip_fraction | 0.386 | +| clip_range | 0.136 | +| entropy_loss | -7.15 | +| explained_variance | -0.108 | +| learning_rate | 0.000177 | +| loss | -0.0564 | +| n_updates | 2248 | +| policy_gradient_loss | -0.036 | +| value_loss | 7.07e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.194 | +| time/ | | +| fps | 1323 | +| iterations | 564 | +| time_elapsed | 873 | +| total_timesteps | 1155072 | +| train/ | | +| approx_kl | 0.044507414 | +| clip_fraction | 0.385 | +| clip_range | 0.136 | +| entropy_loss | -7.08 | +| explained_variance | -0.0551 | +| learning_rate | 0.000177 | +| loss | -0.0584 | +| n_updates | 2252 | +| policy_gradient_loss | -0.0331 | +| value_loss | 0.000168 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.194 | +| time/ | | +| fps | 1323 | +| iterations | 565 | +| time_elapsed | 874 | +| total_timesteps | 1157120 | +| train/ | | +| approx_kl | 0.043447323 | +| clip_fraction | 0.381 | +| clip_range | 0.136 | +| entropy_loss | -7.23 | +| explained_variance | -0.185 | +| learning_rate | 0.000177 | +| loss | -0.058 | +| n_updates | 2256 | +| policy_gradient_loss | -0.037 | +| value_loss | 0.000158 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.195 | +| time/ | | +| fps | 1323 | +| iterations | 566 | +| time_elapsed | 876 | +| total_timesteps | 1159168 | +| train/ | | +| approx_kl | 0.048074126 | +| clip_fraction | 0.387 | +| clip_range | 0.136 | +| entropy_loss | -7.26 | +| explained_variance | -0.0171 | +| learning_rate | 0.000177 | +| loss | -0.0678 | +| n_updates | 2260 | +| policy_gradient_loss | -0.0367 | +| value_loss | 0.000114 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.195 | +| time/ | | +| fps | 1323 | +| iterations | 567 | +| time_elapsed | 877 | +| total_timesteps | 1161216 | +| train/ | | +| approx_kl | 0.033486515 | +| clip_fraction | 0.381 | +| clip_range | 0.136 | +| entropy_loss | -7.16 | +| explained_variance | -0.0764 | +| learning_rate | 0.000177 | +| loss | -0.0504 | +| n_updates | 2264 | +| policy_gradient_loss | -0.0319 | +| value_loss | 0.000154 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.191 | +| time/ | | +| fps | 1322 | +| iterations | 568 | +| time_elapsed | 879 | +| total_timesteps | 1163264 | +| train/ | | +| approx_kl | 0.049424388 | +| clip_fraction | 0.376 | +| clip_range | 0.135 | +| entropy_loss | -7.23 | +| explained_variance | -0.0165 | +| learning_rate | 0.000177 | +| loss | -0.0529 | +| n_updates | 2268 | +| policy_gradient_loss | -0.0312 | +| value_loss | 0.000169 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.188 | +| time/ | | +| fps | 1322 | +| iterations | 569 | +| time_elapsed | 880 | +| total_timesteps | 1165312 | +| train/ | | +| approx_kl | 0.038356155 | +| clip_fraction | 0.354 | +| clip_range | 0.135 | +| entropy_loss | -7.34 | +| explained_variance | -0.0971 | +| learning_rate | 0.000177 | +| loss | -0.0553 | +| n_updates | 2272 | +| policy_gradient_loss | -0.0366 | +| value_loss | 0.000147 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.188 | +| time/ | | +| fps | 1323 | +| iterations | 570 | +| time_elapsed | 882 | +| total_timesteps | 1167360 | +| train/ | | +| approx_kl | 0.038306795 | +| clip_fraction | 0.372 | +| clip_range | 0.135 | +| entropy_loss | -7.27 | +| explained_variance | -0.0234 | +| learning_rate | 0.000177 | +| loss | -0.0537 | +| n_updates | 2276 | +| policy_gradient_loss | -0.0324 | +| value_loss | 0.000195 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.19 | +| time/ | | +| fps | 1322 | +| iterations | 571 | +| time_elapsed | 883 | +| total_timesteps | 1169408 | +| train/ | | +| approx_kl | 0.037835505 | +| clip_fraction | 0.371 | +| clip_range | 0.135 | +| entropy_loss | -7.31 | +| explained_variance | -0.135 | +| learning_rate | 0.000177 | +| loss | -0.0589 | +| n_updates | 2280 | +| policy_gradient_loss | -0.0354 | +| value_loss | 0.000134 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.19 | +| time/ | | +| fps | 1322 | +| iterations | 572 | +| time_elapsed | 885 | +| total_timesteps | 1171456 | +| train/ | | +| approx_kl | 0.027624486 | +| clip_fraction | 0.336 | +| clip_range | 0.135 | +| entropy_loss | -7.22 | +| explained_variance | -0.0471 | +| learning_rate | 0.000177 | +| loss | -0.0386 | +| n_updates | 2284 | +| policy_gradient_loss | -0.0257 | +| value_loss | 0.000317 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.188 | +| time/ | | +| fps | 1322 | +| iterations | 573 | +| time_elapsed | 887 | +| total_timesteps | 1173504 | +| train/ | | +| approx_kl | 0.034954883 | +| clip_fraction | 0.365 | +| clip_range | 0.135 | +| entropy_loss | -7.15 | +| explained_variance | -0.128 | +| learning_rate | 0.000177 | +| loss | -0.0562 | +| n_updates | 2288 | +| policy_gradient_loss | -0.0321 | +| value_loss | 0.000222 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.188 | +| time/ | | +| fps | 1322 | +| iterations | 574 | +| time_elapsed | 888 | +| total_timesteps | 1175552 | +| train/ | | +| approx_kl | 0.039455503 | +| clip_fraction | 0.367 | +| clip_range | 0.135 | +| entropy_loss | -7.19 | +| explained_variance | -0.242 | +| learning_rate | 0.000177 | +| loss | -0.0629 | +| n_updates | 2292 | +| policy_gradient_loss | -0.038 | +| value_loss | 0.000116 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.194 | +| time/ | | +| fps | 1323 | +| iterations | 575 | +| time_elapsed | 890 | +| total_timesteps | 1177600 | +| train/ | | +| approx_kl | 0.044924065 | +| clip_fraction | 0.356 | +| clip_range | 0.135 | +| entropy_loss | -7.27 | +| explained_variance | -0.0814 | +| learning_rate | 0.000177 | +| loss | -0.0588 | +| n_updates | 2296 | +| policy_gradient_loss | -0.0338 | +| value_loss | 0.00014 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.195 | +| time/ | | +| fps | 1323 | +| iterations | 576 | +| time_elapsed | 891 | +| total_timesteps | 1179648 | +| train/ | | +| approx_kl | 0.04078102 | +| clip_fraction | 0.379 | +| clip_range | 0.135 | +| entropy_loss | -7.17 | +| explained_variance | -0.0999 | +| learning_rate | 0.000177 | +| loss | -0.0614 | +| n_updates | 2300 | +| policy_gradient_loss | -0.0379 | +| value_loss | 0.000134 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.199 | +| time/ | | +| fps | 1323 | +| iterations | 577 | +| time_elapsed | 893 | +| total_timesteps | 1181696 | +| train/ | | +| approx_kl | 0.038181342 | +| clip_fraction | 0.378 | +| clip_range | 0.135 | +| entropy_loss | -7.18 | +| explained_variance | -0.16 | +| learning_rate | 0.000177 | +| loss | -0.0633 | +| n_updates | 2304 | +| policy_gradient_loss | -0.0372 | +| value_loss | 0.000142 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.199 | +| time/ | | +| fps | 1323 | +| iterations | 578 | +| time_elapsed | 894 | +| total_timesteps | 1183744 | +| train/ | | +| approx_kl | 0.036927827 | +| clip_fraction | 0.36 | +| clip_range | 0.135 | +| entropy_loss | -7.16 | +| explained_variance | 0.00566 | +| learning_rate | 0.000177 | +| loss | -0.0479 | +| n_updates | 2308 | +| policy_gradient_loss | -0.0258 | +| value_loss | 0.000241 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.199 | +| time/ | | +| fps | 1323 | +| iterations | 579 | +| time_elapsed | 896 | +| total_timesteps | 1185792 | +| train/ | | +| approx_kl | 0.038066424 | +| clip_fraction | 0.385 | +| clip_range | 0.135 | +| entropy_loss | -7.26 | +| explained_variance | -0.326 | +| learning_rate | 0.000177 | +| loss | -0.0548 | +| n_updates | 2312 | +| policy_gradient_loss | -0.0368 | +| value_loss | 0.000123 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.197 | +| time/ | | +| fps | 1323 | +| iterations | 580 | +| time_elapsed | 897 | +| total_timesteps | 1187840 | +| train/ | | +| approx_kl | 0.040913038 | +| clip_fraction | 0.379 | +| clip_range | 0.135 | +| entropy_loss | -7.15 | +| explained_variance | -0.14 | +| learning_rate | 0.000177 | +| loss | -0.0505 | +| n_updates | 2316 | +| policy_gradient_loss | -0.0346 | +| value_loss | 0.000144 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.198 | +| time/ | | +| fps | 1323 | +| iterations | 581 | +| time_elapsed | 899 | +| total_timesteps | 1189888 | +| train/ | | +| approx_kl | 0.04613648 | +| clip_fraction | 0.419 | +| clip_range | 0.135 | +| entropy_loss | -7.22 | +| explained_variance | -0.182 | +| learning_rate | 0.000176 | +| loss | -0.0603 | +| n_updates | 2320 | +| policy_gradient_loss | -0.0386 | +| value_loss | 8.72e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.202 | +| time/ | | +| fps | 1323 | +| iterations | 582 | +| time_elapsed | 900 | +| total_timesteps | 1191936 | +| train/ | | +| approx_kl | 0.042395804 | +| clip_fraction | 0.397 | +| clip_range | 0.135 | +| entropy_loss | -7.28 | +| explained_variance | -0.122 | +| learning_rate | 0.000176 | +| loss | -0.0518 | +| n_updates | 2324 | +| policy_gradient_loss | -0.0332 | +| value_loss | 0.000152 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.203 | +| time/ | | +| fps | 1323 | +| iterations | 583 | +| time_elapsed | 902 | +| total_timesteps | 1193984 | +| train/ | | +| approx_kl | 0.037603956 | +| clip_fraction | 0.372 | +| clip_range | 0.135 | +| entropy_loss | -7.29 | +| explained_variance | -0.113 | +| learning_rate | 0.000176 | +| loss | -0.059 | +| n_updates | 2328 | +| policy_gradient_loss | -0.0357 | +| value_loss | 0.000199 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.207 | +| time/ | | +| fps | 1323 | +| iterations | 584 | +| time_elapsed | 903 | +| total_timesteps | 1196032 | +| train/ | | +| approx_kl | 0.041843742 | +| clip_fraction | 0.418 | +| clip_range | 0.135 | +| entropy_loss | -7.2 | +| explained_variance | -0.186 | +| learning_rate | 0.000176 | +| loss | -0.0633 | +| n_updates | 2332 | +| policy_gradient_loss | -0.0344 | +| value_loss | 9.45e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.2 | +| time/ | | +| fps | 1323 | +| iterations | 585 | +| time_elapsed | 905 | +| total_timesteps | 1198080 | +| train/ | | +| approx_kl | 0.03354098 | +| clip_fraction | 0.374 | +| clip_range | 0.135 | +| entropy_loss | -7.25 | +| explained_variance | -0.101 | +| learning_rate | 0.000176 | +| loss | -0.0449 | +| n_updates | 2336 | +| policy_gradient_loss | -0.0295 | +| value_loss | 0.000151 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.2 | +| time/ | | +| fps | 1323 | +| iterations | 586 | +| time_elapsed | 906 | +| total_timesteps | 1200128 | +| train/ | | +| approx_kl | 0.043928754 | +| clip_fraction | 0.379 | +| clip_range | 0.135 | +| entropy_loss | -7.19 | +| explained_variance | -0.00734 | +| learning_rate | 0.000176 | +| loss | -0.0635 | +| n_updates | 2340 | +| policy_gradient_loss | -0.0365 | +| value_loss | 0.000121 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.2 | +| time/ | | +| fps | 1323 | +| iterations | 587 | +| time_elapsed | 908 | +| total_timesteps | 1202176 | +| train/ | | +| approx_kl | 0.036682487 | +| clip_fraction | 0.38 | +| clip_range | 0.135 | +| entropy_loss | -7.14 | +| explained_variance | -0.292 | +| learning_rate | 0.000176 | +| loss | -0.0646 | +| n_updates | 2344 | +| policy_gradient_loss | -0.0383 | +| value_loss | 6.4e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.199 | +| time/ | | +| fps | 1323 | +| iterations | 588 | +| time_elapsed | 909 | +| total_timesteps | 1204224 | +| train/ | | +| approx_kl | 0.047630765 | +| clip_fraction | 0.396 | +| clip_range | 0.135 | +| entropy_loss | -7.18 | +| explained_variance | -0.127 | +| learning_rate | 0.000176 | +| loss | -0.0543 | +| n_updates | 2348 | +| policy_gradient_loss | -0.0364 | +| value_loss | 0.000185 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.196 | +| time/ | | +| fps | 1323 | +| iterations | 589 | +| time_elapsed | 911 | +| total_timesteps | 1206272 | +| train/ | | +| approx_kl | 0.040724277 | +| clip_fraction | 0.372 | +| clip_range | 0.135 | +| entropy_loss | -7.22 | +| explained_variance | -0.0598 | +| learning_rate | 0.000176 | +| loss | -0.0585 | +| n_updates | 2352 | +| policy_gradient_loss | -0.0358 | +| value_loss | 0.000182 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.194 | +| time/ | | +| fps | 1323 | +| iterations | 590 | +| time_elapsed | 912 | +| total_timesteps | 1208320 | +| train/ | | +| approx_kl | 0.043654837 | +| clip_fraction | 0.399 | +| clip_range | 0.135 | +| entropy_loss | -7.18 | +| explained_variance | -0.0449 | +| learning_rate | 0.000176 | +| loss | -0.0639 | +| n_updates | 2356 | +| policy_gradient_loss | -0.0379 | +| value_loss | 0.000132 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.194 | +| time/ | | +| fps | 1323 | +| iterations | 591 | +| time_elapsed | 914 | +| total_timesteps | 1210368 | +| train/ | | +| approx_kl | 0.040525608 | +| clip_fraction | 0.379 | +| clip_range | 0.135 | +| entropy_loss | -7.16 | +| explained_variance | -0.206 | +| learning_rate | 0.000176 | +| loss | -0.0676 | +| n_updates | 2360 | +| policy_gradient_loss | -0.0399 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.194 | +| time/ | | +| fps | 1323 | +| iterations | 592 | +| time_elapsed | 915 | +| total_timesteps | 1212416 | +| train/ | | +| approx_kl | 0.039688744 | +| clip_fraction | 0.379 | +| clip_range | 0.135 | +| entropy_loss | -7.21 | +| explained_variance | -0.179 | +| learning_rate | 0.000176 | +| loss | -0.0626 | +| n_updates | 2364 | +| policy_gradient_loss | -0.0361 | +| value_loss | 0.000136 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.191 | +| time/ | | +| fps | 1323 | +| iterations | 593 | +| time_elapsed | 917 | +| total_timesteps | 1214464 | +| train/ | | +| approx_kl | 0.03586345 | +| clip_fraction | 0.387 | +| clip_range | 0.135 | +| entropy_loss | -7.25 | +| explained_variance | -0.0713 | +| learning_rate | 0.000176 | +| loss | -0.0528 | +| n_updates | 2368 | +| policy_gradient_loss | -0.0342 | +| value_loss | 0.000145 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.191 | +| time/ | | +| fps | 1323 | +| iterations | 594 | +| time_elapsed | 919 | +| total_timesteps | 1216512 | +| train/ | | +| approx_kl | 0.03587035 | +| clip_fraction | 0.368 | +| clip_range | 0.135 | +| entropy_loss | -7.18 | +| explained_variance | -0.16 | +| learning_rate | 0.000176 | +| loss | -0.0736 | +| n_updates | 2372 | +| policy_gradient_loss | -0.0363 | +| value_loss | 9e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.195 | +| time/ | | +| fps | 1323 | +| iterations | 595 | +| time_elapsed | 920 | +| total_timesteps | 1218560 | +| train/ | | +| approx_kl | 0.039438307 | +| clip_fraction | 0.374 | +| clip_range | 0.135 | +| entropy_loss | -7.16 | +| explained_variance | -0.134 | +| learning_rate | 0.000176 | +| loss | -0.0614 | +| n_updates | 2376 | +| policy_gradient_loss | -0.0329 | +| value_loss | 0.000133 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.191 | +| time/ | | +| fps | 1324 | +| iterations | 596 | +| time_elapsed | 921 | +| total_timesteps | 1220608 | +| train/ | | +| approx_kl | 0.038816635 | +| clip_fraction | 0.393 | +| clip_range | 0.135 | +| entropy_loss | -7.12 | +| explained_variance | -0.0799 | +| learning_rate | 0.000176 | +| loss | -0.0621 | +| n_updates | 2380 | +| policy_gradient_loss | -0.0306 | +| value_loss | 0.000164 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.185 | +| time/ | | +| fps | 1324 | +| iterations | 597 | +| time_elapsed | 923 | +| total_timesteps | 1222656 | +| train/ | | +| approx_kl | 0.03341011 | +| clip_fraction | 0.363 | +| clip_range | 0.135 | +| entropy_loss | -7.09 | +| explained_variance | -0.0325 | +| learning_rate | 0.000176 | +| loss | -0.0536 | +| n_updates | 2384 | +| policy_gradient_loss | -0.0338 | +| value_loss | 9.7e-05 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.188 | +| time/ | | +| fps | 1324 | +| iterations | 598 | +| time_elapsed | 924 | +| total_timesteps | 1224704 | +| train/ | | +| approx_kl | 0.03996573 | +| clip_fraction | 0.419 | +| clip_range | 0.135 | +| entropy_loss | -7.12 | +| explained_variance | -0.18 | +| learning_rate | 0.000176 | +| loss | -0.0599 | +| n_updates | 2388 | +| policy_gradient_loss | -0.0384 | +| value_loss | 9.37e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.191 | +| time/ | | +| fps | 1324 | +| iterations | 599 | +| time_elapsed | 926 | +| total_timesteps | 1226752 | +| train/ | | +| approx_kl | 0.043517888 | +| clip_fraction | 0.399 | +| clip_range | 0.135 | +| entropy_loss | -7.17 | +| explained_variance | 0.0428 | +| learning_rate | 0.000176 | +| loss | -0.0569 | +| n_updates | 2392 | +| policy_gradient_loss | -0.0289 | +| value_loss | 0.000227 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.191 | +| time/ | | +| fps | 1324 | +| iterations | 600 | +| time_elapsed | 927 | +| total_timesteps | 1228800 | +| train/ | | +| approx_kl | 0.039170235 | +| clip_fraction | 0.389 | +| clip_range | 0.135 | +| entropy_loss | -7.23 | +| explained_variance | -0.0727 | +| learning_rate | 0.000176 | +| loss | -0.0626 | +| n_updates | 2396 | +| policy_gradient_loss | -0.0393 | +| value_loss | 0.00019 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.189 | +| time/ | | +| fps | 1324 | +| iterations | 601 | +| time_elapsed | 929 | +| total_timesteps | 1230848 | +| train/ | | +| approx_kl | 0.038127124 | +| clip_fraction | 0.397 | +| clip_range | 0.135 | +| entropy_loss | -7.25 | +| explained_variance | -0.137 | +| learning_rate | 0.000176 | +| loss | -0.0555 | +| n_updates | 2400 | +| policy_gradient_loss | -0.034 | +| value_loss | 0.000177 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.189 | +| time/ | | +| fps | 1324 | +| iterations | 602 | +| time_elapsed | 930 | +| total_timesteps | 1232896 | +| train/ | | +| approx_kl | 0.03441062 | +| clip_fraction | 0.36 | +| clip_range | 0.135 | +| entropy_loss | -7.21 | +| explained_variance | -0.0995 | +| learning_rate | 0.000176 | +| loss | -0.0558 | +| n_updates | 2404 | +| policy_gradient_loss | -0.0319 | +| value_loss | 0.000152 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.189 | +| time/ | | +| fps | 1324 | +| iterations | 603 | +| time_elapsed | 932 | +| total_timesteps | 1234944 | +| train/ | | +| approx_kl | 0.037582513 | +| clip_fraction | 0.384 | +| clip_range | 0.135 | +| entropy_loss | -7.2 | +| explained_variance | -0.388 | +| learning_rate | 0.000176 | +| loss | -0.0636 | +| n_updates | 2408 | +| policy_gradient_loss | -0.0398 | +| value_loss | 9.3e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.189 | +| time/ | | +| fps | 1324 | +| iterations | 604 | +| time_elapsed | 933 | +| total_timesteps | 1236992 | +| train/ | | +| approx_kl | 0.04550463 | +| clip_fraction | 0.425 | +| clip_range | 0.135 | +| entropy_loss | -7.27 | +| explained_variance | -0.195 | +| learning_rate | 0.000176 | +| loss | -0.0576 | +| n_updates | 2412 | +| policy_gradient_loss | -0.04 | +| value_loss | 7.84e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.19 | +| time/ | | +| fps | 1324 | +| iterations | 605 | +| time_elapsed | 935 | +| total_timesteps | 1239040 | +| train/ | | +| approx_kl | 0.036142156 | +| clip_fraction | 0.366 | +| clip_range | 0.135 | +| entropy_loss | -7.2 | +| explained_variance | -0.109 | +| learning_rate | 0.000176 | +| loss | -0.0641 | +| n_updates | 2416 | +| policy_gradient_loss | -0.0336 | +| value_loss | 0.000131 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.199 | +| time/ | | +| fps | 1324 | +| iterations | 606 | +| time_elapsed | 937 | +| total_timesteps | 1241088 | +| train/ | | +| approx_kl | 0.032907747 | +| clip_fraction | 0.365 | +| clip_range | 0.135 | +| entropy_loss | -7.23 | +| explained_variance | -0.111 | +| learning_rate | 0.000175 | +| loss | -0.0502 | +| n_updates | 2420 | +| policy_gradient_loss | -0.032 | +| value_loss | 0.000196 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.2 | +| time/ | | +| fps | 1324 | +| iterations | 607 | +| time_elapsed | 938 | +| total_timesteps | 1243136 | +| train/ | | +| approx_kl | 0.034326285 | +| clip_fraction | 0.344 | +| clip_range | 0.134 | +| entropy_loss | -7.24 | +| explained_variance | -0.176 | +| learning_rate | 0.000175 | +| loss | -0.0635 | +| n_updates | 2424 | +| policy_gradient_loss | -0.0333 | +| value_loss | 0.000106 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.198 | +| time/ | | +| fps | 1324 | +| iterations | 608 | +| time_elapsed | 939 | +| total_timesteps | 1245184 | +| train/ | | +| approx_kl | 0.04101271 | +| clip_fraction | 0.379 | +| clip_range | 0.134 | +| entropy_loss | -7.23 | +| explained_variance | -0.00426 | +| learning_rate | 0.000175 | +| loss | -0.0517 | +| n_updates | 2428 | +| policy_gradient_loss | -0.0318 | +| value_loss | 0.000227 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.201 | +| time/ | | +| fps | 1324 | +| iterations | 609 | +| time_elapsed | 941 | +| total_timesteps | 1247232 | +| train/ | | +| approx_kl | 0.043005966 | +| clip_fraction | 0.378 | +| clip_range | 0.134 | +| entropy_loss | -7.32 | +| explained_variance | -0.398 | +| learning_rate | 0.000175 | +| loss | -0.077 | +| n_updates | 2432 | +| policy_gradient_loss | -0.0458 | +| value_loss | 7.14e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.201 | +| time/ | | +| fps | 1324 | +| iterations | 610 | +| time_elapsed | 943 | +| total_timesteps | 1249280 | +| train/ | | +| approx_kl | 0.043455686 | +| clip_fraction | 0.377 | +| clip_range | 0.134 | +| entropy_loss | -7.36 | +| explained_variance | -0.0786 | +| learning_rate | 0.000175 | +| loss | -0.0658 | +| n_updates | 2436 | +| policy_gradient_loss | -0.0379 | +| value_loss | 0.000119 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.2 | +| time/ | | +| fps | 1324 | +| iterations | 611 | +| time_elapsed | 944 | +| total_timesteps | 1251328 | +| train/ | | +| approx_kl | 0.03832666 | +| clip_fraction | 0.38 | +| clip_range | 0.134 | +| entropy_loss | -7.28 | +| explained_variance | -0.185 | +| learning_rate | 0.000175 | +| loss | -0.0635 | +| n_updates | 2440 | +| policy_gradient_loss | -0.0417 | +| value_loss | 6.8e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.203 | +| time/ | | +| fps | 1324 | +| iterations | 612 | +| time_elapsed | 946 | +| total_timesteps | 1253376 | +| train/ | | +| approx_kl | 0.039736897 | +| clip_fraction | 0.385 | +| clip_range | 0.134 | +| entropy_loss | -7.25 | +| explained_variance | -0.0716 | +| learning_rate | 0.000175 | +| loss | -0.0565 | +| n_updates | 2444 | +| policy_gradient_loss | -0.0335 | +| value_loss | 0.000114 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.203 | +| time/ | | +| fps | 1324 | +| iterations | 613 | +| time_elapsed | 947 | +| total_timesteps | 1255424 | +| train/ | | +| approx_kl | 0.0316264 | +| clip_fraction | 0.367 | +| clip_range | 0.134 | +| entropy_loss | -7.21 | +| explained_variance | -0.0345 | +| learning_rate | 0.000175 | +| loss | -0.0557 | +| n_updates | 2448 | +| policy_gradient_loss | -0.0326 | +| value_loss | 0.000114 | +--------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.202 | +| time/ | | +| fps | 1324 | +| iterations | 614 | +| time_elapsed | 949 | +| total_timesteps | 1257472 | +| train/ | | +| approx_kl | 0.03470987 | +| clip_fraction | 0.349 | +| clip_range | 0.134 | +| entropy_loss | -7.25 | +| explained_variance | -0.141 | +| learning_rate | 0.000175 | +| loss | -0.0593 | +| n_updates | 2452 | +| policy_gradient_loss | -0.0327 | +| value_loss | 0.000105 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.202 | +| time/ | | +| fps | 1324 | +| iterations | 615 | +| time_elapsed | 950 | +| total_timesteps | 1259520 | +| train/ | | +| approx_kl | 0.033352427 | +| clip_fraction | 0.376 | +| clip_range | 0.134 | +| entropy_loss | -7.21 | +| explained_variance | -0.224 | +| learning_rate | 0.000175 | +| loss | -0.0596 | +| n_updates | 2456 | +| policy_gradient_loss | -0.0343 | +| value_loss | 0.000113 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.199 | +| time/ | | +| fps | 1324 | +| iterations | 616 | +| time_elapsed | 952 | +| total_timesteps | 1261568 | +| train/ | | +| approx_kl | 0.044130176 | +| clip_fraction | 0.381 | +| clip_range | 0.134 | +| entropy_loss | -7.19 | +| explained_variance | -0.0608 | +| learning_rate | 0.000175 | +| loss | -0.0565 | +| n_updates | 2460 | +| policy_gradient_loss | -0.0328 | +| value_loss | 0.0002 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.201 | +| time/ | | +| fps | 1324 | +| iterations | 617 | +| time_elapsed | 954 | +| total_timesteps | 1263616 | +| train/ | | +| approx_kl | 0.032601483 | +| clip_fraction | 0.331 | +| clip_range | 0.134 | +| entropy_loss | -7.28 | +| explained_variance | -0.064 | +| learning_rate | 0.000175 | +| loss | -0.052 | +| n_updates | 2464 | +| policy_gradient_loss | -0.0297 | +| value_loss | 0.000214 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.202 | +| time/ | | +| fps | 1324 | +| iterations | 618 | +| time_elapsed | 955 | +| total_timesteps | 1265664 | +| train/ | | +| approx_kl | 0.03588897 | +| clip_fraction | 0.383 | +| clip_range | 0.134 | +| entropy_loss | -7.25 | +| explained_variance | -0.169 | +| learning_rate | 0.000175 | +| loss | -0.0651 | +| n_updates | 2468 | +| policy_gradient_loss | -0.0356 | +| value_loss | 0.000106 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.207 | +| time/ | | +| fps | 1324 | +| iterations | 619 | +| time_elapsed | 957 | +| total_timesteps | 1267712 | +| train/ | | +| approx_kl | 0.04581358 | +| clip_fraction | 0.396 | +| clip_range | 0.134 | +| entropy_loss | -7.26 | +| explained_variance | -0.0093 | +| learning_rate | 0.000175 | +| loss | -0.0523 | +| n_updates | 2472 | +| policy_gradient_loss | -0.0305 | +| value_loss | 0.00014 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.211 | +| time/ | | +| fps | 1324 | +| iterations | 620 | +| time_elapsed | 958 | +| total_timesteps | 1269760 | +| train/ | | +| approx_kl | 0.04394928 | +| clip_fraction | 0.373 | +| clip_range | 0.134 | +| entropy_loss | -7.25 | +| explained_variance | -0.0672 | +| learning_rate | 0.000175 | +| loss | -0.0668 | +| n_updates | 2476 | +| policy_gradient_loss | -0.0354 | +| value_loss | 0.000174 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.21 | +| time/ | | +| fps | 1324 | +| iterations | 621 | +| time_elapsed | 960 | +| total_timesteps | 1271808 | +| train/ | | +| approx_kl | 0.041128375 | +| clip_fraction | 0.379 | +| clip_range | 0.134 | +| entropy_loss | -7.37 | +| explained_variance | -0.029 | +| learning_rate | 0.000175 | +| loss | -0.0614 | +| n_updates | 2480 | +| policy_gradient_loss | -0.0344 | +| value_loss | 0.000237 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.21 | +| time/ | | +| fps | 1324 | +| iterations | 622 | +| time_elapsed | 961 | +| total_timesteps | 1273856 | +| train/ | | +| approx_kl | 0.038513053 | +| clip_fraction | 0.402 | +| clip_range | 0.134 | +| entropy_loss | -7.37 | +| explained_variance | -0.115 | +| learning_rate | 0.000175 | +| loss | -0.0575 | +| n_updates | 2484 | +| policy_gradient_loss | -0.0362 | +| value_loss | 0.000218 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.212 | +| time/ | | +| fps | 1324 | +| iterations | 623 | +| time_elapsed | 963 | +| total_timesteps | 1275904 | +| train/ | | +| approx_kl | 0.028977683 | +| clip_fraction | 0.381 | +| clip_range | 0.134 | +| entropy_loss | -7.22 | +| explained_variance | -0.192 | +| learning_rate | 0.000175 | +| loss | -0.0445 | +| n_updates | 2488 | +| policy_gradient_loss | -0.0298 | +| value_loss | 0.000182 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.214 | +| time/ | | +| fps | 1324 | +| iterations | 624 | +| time_elapsed | 964 | +| total_timesteps | 1277952 | +| train/ | | +| approx_kl | 0.03467461 | +| clip_fraction | 0.373 | +| clip_range | 0.134 | +| entropy_loss | -7.28 | +| explained_variance | -0.158 | +| learning_rate | 0.000175 | +| loss | -0.0631 | +| n_updates | 2492 | +| policy_gradient_loss | -0.0364 | +| value_loss | 0.000104 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.214 | +| time/ | | +| fps | 1324 | +| iterations | 625 | +| time_elapsed | 966 | +| total_timesteps | 1280000 | +| train/ | | +| approx_kl | 0.03833299 | +| clip_fraction | 0.373 | +| clip_range | 0.134 | +| entropy_loss | -7.31 | +| explained_variance | 0.0107 | +| learning_rate | 0.000175 | +| loss | -0.0618 | +| n_updates | 2496 | +| policy_gradient_loss | -0.0316 | +| value_loss | 0.000234 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.214 | +| time/ | | +| fps | 1324 | +| iterations | 626 | +| time_elapsed | 967 | +| total_timesteps | 1282048 | +| train/ | | +| approx_kl | 0.03784062 | +| clip_fraction | 0.407 | +| clip_range | 0.134 | +| entropy_loss | -7.3 | +| explained_variance | -0.51 | +| learning_rate | 0.000175 | +| loss | -0.0604 | +| n_updates | 2500 | +| policy_gradient_loss | -0.0405 | +| value_loss | 9e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.215 | +| time/ | | +| fps | 1324 | +| iterations | 627 | +| time_elapsed | 969 | +| total_timesteps | 1284096 | +| train/ | | +| approx_kl | 0.037568733 | +| clip_fraction | 0.376 | +| clip_range | 0.134 | +| entropy_loss | -7.22 | +| explained_variance | -0.113 | +| learning_rate | 0.000175 | +| loss | -0.0602 | +| n_updates | 2504 | +| policy_gradient_loss | -0.0369 | +| value_loss | 0.00011 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.22 | +| time/ | | +| fps | 1324 | +| iterations | 628 | +| time_elapsed | 970 | +| total_timesteps | 1286144 | +| train/ | | +| approx_kl | 0.041173384 | +| clip_fraction | 0.362 | +| clip_range | 0.134 | +| entropy_loss | -7.21 | +| explained_variance | -0.0823 | +| learning_rate | 0.000175 | +| loss | -0.0501 | +| n_updates | 2508 | +| policy_gradient_loss | -0.0335 | +| value_loss | 9.91e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.215 | +| time/ | | +| fps | 1324 | +| iterations | 629 | +| time_elapsed | 972 | +| total_timesteps | 1288192 | +| train/ | | +| approx_kl | 0.035222027 | +| clip_fraction | 0.361 | +| clip_range | 0.134 | +| entropy_loss | -7.12 | +| explained_variance | 0.0639 | +| learning_rate | 0.000175 | +| loss | -0.0498 | +| n_updates | 2512 | +| policy_gradient_loss | -0.0294 | +| value_loss | 0.000125 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.22 | +| time/ | | +| fps | 1324 | +| iterations | 630 | +| time_elapsed | 974 | +| total_timesteps | 1290240 | +| train/ | | +| approx_kl | 0.03692822 | +| clip_fraction | 0.379 | +| clip_range | 0.134 | +| entropy_loss | -7.24 | +| explained_variance | -0.132 | +| learning_rate | 0.000174 | +| loss | -0.0592 | +| n_updates | 2516 | +| policy_gradient_loss | -0.0344 | +| value_loss | 0.000119 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.219 | +| time/ | | +| fps | 1324 | +| iterations | 631 | +| time_elapsed | 975 | +| total_timesteps | 1292288 | +| train/ | | +| approx_kl | 0.037662037 | +| clip_fraction | 0.36 | +| clip_range | 0.134 | +| entropy_loss | -7.36 | +| explained_variance | -0.0784 | +| learning_rate | 0.000174 | +| loss | -0.0563 | +| n_updates | 2520 | +| policy_gradient_loss | -0.0337 | +| value_loss | 0.000116 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.219 | +| time/ | | +| fps | 1324 | +| iterations | 632 | +| time_elapsed | 977 | +| total_timesteps | 1294336 | +| train/ | | +| approx_kl | 0.042830564 | +| clip_fraction | 0.35 | +| clip_range | 0.134 | +| entropy_loss | -7.33 | +| explained_variance | 0.0209 | +| learning_rate | 0.000174 | +| loss | -0.0576 | +| n_updates | 2524 | +| policy_gradient_loss | -0.0374 | +| value_loss | 0.000122 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.223 | +| time/ | | +| fps | 1324 | +| iterations | 633 | +| time_elapsed | 978 | +| total_timesteps | 1296384 | +| train/ | | +| approx_kl | 0.035640262 | +| clip_fraction | 0.379 | +| clip_range | 0.134 | +| entropy_loss | -7.39 | +| explained_variance | -0.0486 | +| learning_rate | 0.000174 | +| loss | -0.0496 | +| n_updates | 2528 | +| policy_gradient_loss | -0.0323 | +| value_loss | 0.000126 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.22 | +| time/ | | +| fps | 1324 | +| iterations | 634 | +| time_elapsed | 980 | +| total_timesteps | 1298432 | +| train/ | | +| approx_kl | 0.034864433 | +| clip_fraction | 0.345 | +| clip_range | 0.134 | +| entropy_loss | -7.35 | +| explained_variance | -0.117 | +| learning_rate | 0.000174 | +| loss | -0.0644 | +| n_updates | 2532 | +| policy_gradient_loss | -0.0329 | +| value_loss | 0.000171 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.217 | +| time/ | | +| fps | 1324 | +| iterations | 635 | +| time_elapsed | 981 | +| total_timesteps | 1300480 | +| train/ | | +| approx_kl | 0.037572034 | +| clip_fraction | 0.393 | +| clip_range | 0.134 | +| entropy_loss | -7.46 | +| explained_variance | -0.192 | +| learning_rate | 0.000174 | +| loss | -0.0706 | +| n_updates | 2536 | +| policy_gradient_loss | -0.0354 | +| value_loss | 0.00011 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.221 | +| time/ | | +| fps | 1324 | +| iterations | 636 | +| time_elapsed | 983 | +| total_timesteps | 1302528 | +| train/ | | +| approx_kl | 0.037196446 | +| clip_fraction | 0.375 | +| clip_range | 0.134 | +| entropy_loss | -7.28 | +| explained_variance | -0.0154 | +| learning_rate | 0.000174 | +| loss | -0.0558 | +| n_updates | 2540 | +| policy_gradient_loss | -0.0348 | +| value_loss | 0.000176 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.217 | +| time/ | | +| fps | 1324 | +| iterations | 637 | +| time_elapsed | 985 | +| total_timesteps | 1304576 | +| train/ | | +| approx_kl | 0.03651898 | +| clip_fraction | 0.401 | +| clip_range | 0.134 | +| entropy_loss | -7.27 | +| explained_variance | -0.165 | +| learning_rate | 0.000174 | +| loss | -0.0654 | +| n_updates | 2544 | +| policy_gradient_loss | -0.038 | +| value_loss | 0.000125 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.217 | +| time/ | | +| fps | 1324 | +| iterations | 638 | +| time_elapsed | 986 | +| total_timesteps | 1306624 | +| train/ | | +| approx_kl | 0.038935144 | +| clip_fraction | 0.384 | +| clip_range | 0.134 | +| entropy_loss | -7.38 | +| explained_variance | -0.505 | +| learning_rate | 0.000174 | +| loss | -0.0685 | +| n_updates | 2548 | +| policy_gradient_loss | -0.0421 | +| value_loss | 6.66e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.217 | +| time/ | | +| fps | 1324 | +| iterations | 639 | +| time_elapsed | 988 | +| total_timesteps | 1308672 | +| train/ | | +| approx_kl | 0.03741765 | +| clip_fraction | 0.391 | +| clip_range | 0.134 | +| entropy_loss | -7.31 | +| explained_variance | -0.149 | +| learning_rate | 0.000174 | +| loss | -0.0544 | +| n_updates | 2552 | +| policy_gradient_loss | -0.031 | +| value_loss | 0.000135 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.22 | +| time/ | | +| fps | 1324 | +| iterations | 640 | +| time_elapsed | 989 | +| total_timesteps | 1310720 | +| train/ | | +| approx_kl | 0.033945188 | +| clip_fraction | 0.385 | +| clip_range | 0.134 | +| entropy_loss | -7.16 | +| explained_variance | -0.121 | +| learning_rate | 0.000174 | +| loss | -0.059 | +| n_updates | 2556 | +| policy_gradient_loss | -0.0315 | +| value_loss | 0.000114 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.214 | +| time/ | | +| fps | 1324 | +| iterations | 641 | +| time_elapsed | 991 | +| total_timesteps | 1312768 | +| train/ | | +| approx_kl | 0.03866354 | +| clip_fraction | 0.394 | +| clip_range | 0.134 | +| entropy_loss | -7.22 | +| explained_variance | -0.219 | +| learning_rate | 0.000174 | +| loss | -0.0544 | +| n_updates | 2560 | +| policy_gradient_loss | -0.0313 | +| value_loss | 7.21e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.213 | +| time/ | | +| fps | 1324 | +| iterations | 642 | +| time_elapsed | 993 | +| total_timesteps | 1314816 | +| train/ | | +| approx_kl | 0.034391686 | +| clip_fraction | 0.343 | +| clip_range | 0.134 | +| entropy_loss | -7.23 | +| explained_variance | -0.203 | +| learning_rate | 0.000174 | +| loss | -0.0609 | +| n_updates | 2564 | +| policy_gradient_loss | -0.0311 | +| value_loss | 0.000119 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.208 | +| time/ | | +| fps | 1323 | +| iterations | 643 | +| time_elapsed | 994 | +| total_timesteps | 1316864 | +| train/ | | +| approx_kl | 0.035007678 | +| clip_fraction | 0.386 | +| clip_range | 0.134 | +| entropy_loss | -7.36 | +| explained_variance | -0.0866 | +| learning_rate | 0.000174 | +| loss | -0.0577 | +| n_updates | 2568 | +| policy_gradient_loss | -0.0327 | +| value_loss | 6.13e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.208 | +| time/ | | +| fps | 1323 | +| iterations | 644 | +| time_elapsed | 996 | +| total_timesteps | 1318912 | +| train/ | | +| approx_kl | 0.039877202 | +| clip_fraction | 0.348 | +| clip_range | 0.134 | +| entropy_loss | -7.25 | +| explained_variance | 0.0458 | +| learning_rate | 0.000174 | +| loss | -0.055 | +| n_updates | 2572 | +| policy_gradient_loss | -0.0331 | +| value_loss | 0.000177 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.199 | +| time/ | | +| fps | 1323 | +| iterations | 645 | +| time_elapsed | 997 | +| total_timesteps | 1320960 | +| train/ | | +| approx_kl | 0.039202463 | +| clip_fraction | 0.366 | +| clip_range | 0.134 | +| entropy_loss | -7.34 | +| explained_variance | -0.0102 | +| learning_rate | 0.000174 | +| loss | -0.0536 | +| n_updates | 2576 | +| policy_gradient_loss | -0.0335 | +| value_loss | 0.000151 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.199 | +| time/ | | +| fps | 1323 | +| iterations | 646 | +| time_elapsed | 999 | +| total_timesteps | 1323008 | +| train/ | | +| approx_kl | 0.041432686 | +| clip_fraction | 0.396 | +| clip_range | 0.133 | +| entropy_loss | -7.36 | +| explained_variance | -0.244 | +| learning_rate | 0.000174 | +| loss | -0.0699 | +| n_updates | 2580 | +| policy_gradient_loss | -0.0387 | +| value_loss | 0.000176 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.198 | +| time/ | | +| fps | 1323 | +| iterations | 647 | +| time_elapsed | 1001 | +| total_timesteps | 1325056 | +| train/ | | +| approx_kl | 0.03598696 | +| clip_fraction | 0.375 | +| clip_range | 0.133 | +| entropy_loss | -7.31 | +| explained_variance | 0.0278 | +| learning_rate | 0.000174 | +| loss | -0.0523 | +| n_updates | 2584 | +| policy_gradient_loss | -0.0324 | +| value_loss | 0.000146 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.198 | +| time/ | | +| fps | 1323 | +| iterations | 648 | +| time_elapsed | 1002 | +| total_timesteps | 1327104 | +| train/ | | +| approx_kl | 0.040845186 | +| clip_fraction | 0.34 | +| clip_range | 0.133 | +| entropy_loss | -7.15 | +| explained_variance | -0.0663 | +| learning_rate | 0.000174 | +| loss | -0.0591 | +| n_updates | 2588 | +| policy_gradient_loss | -0.0348 | +| value_loss | 0.000112 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.195 | +| time/ | | +| fps | 1323 | +| iterations | 649 | +| time_elapsed | 1004 | +| total_timesteps | 1329152 | +| train/ | | +| approx_kl | 0.04166856 | +| clip_fraction | 0.384 | +| clip_range | 0.133 | +| entropy_loss | -7.22 | +| explained_variance | -0.136 | +| learning_rate | 0.000174 | +| loss | -0.0574 | +| n_updates | 2592 | +| policy_gradient_loss | -0.0349 | +| value_loss | 0.000181 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.201 | +| time/ | | +| fps | 1323 | +| iterations | 650 | +| time_elapsed | 1005 | +| total_timesteps | 1331200 | +| train/ | | +| approx_kl | 0.038811266 | +| clip_fraction | 0.381 | +| clip_range | 0.133 | +| entropy_loss | -7.11 | +| explained_variance | -0.111 | +| learning_rate | 0.000174 | +| loss | -0.0615 | +| n_updates | 2596 | +| policy_gradient_loss | -0.0356 | +| value_loss | 0.000139 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.2 | +| time/ | | +| fps | 1323 | +| iterations | 651 | +| time_elapsed | 1007 | +| total_timesteps | 1333248 | +| train/ | | +| approx_kl | 0.027862761 | +| clip_fraction | 0.352 | +| clip_range | 0.133 | +| entropy_loss | -7.21 | +| explained_variance | 0.092 | +| learning_rate | 0.000174 | +| loss | -0.0433 | +| n_updates | 2600 | +| policy_gradient_loss | -0.0278 | +| value_loss | 0.000256 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.203 | +| time/ | | +| fps | 1323 | +| iterations | 652 | +| time_elapsed | 1009 | +| total_timesteps | 1335296 | +| train/ | | +| approx_kl | 0.038992286 | +| clip_fraction | 0.428 | +| clip_range | 0.133 | +| entropy_loss | -7.24 | +| explained_variance | 0.000691 | +| learning_rate | 0.000174 | +| loss | -0.0734 | +| n_updates | 2604 | +| policy_gradient_loss | -0.0419 | +| value_loss | 0.000104 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.205 | +| time/ | | +| fps | 1323 | +| iterations | 653 | +| time_elapsed | 1010 | +| total_timesteps | 1337344 | +| train/ | | +| approx_kl | 0.041858494 | +| clip_fraction | 0.404 | +| clip_range | 0.133 | +| entropy_loss | -7.06 | +| explained_variance | -0.107 | +| learning_rate | 0.000174 | +| loss | -0.0539 | +| n_updates | 2608 | +| policy_gradient_loss | -0.0362 | +| value_loss | 0.000169 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.207 | +| time/ | | +| fps | 1323 | +| iterations | 654 | +| time_elapsed | 1012 | +| total_timesteps | 1339392 | +| train/ | | +| approx_kl | 0.040981606 | +| clip_fraction | 0.39 | +| clip_range | 0.133 | +| entropy_loss | -6.92 | +| explained_variance | -0.0807 | +| learning_rate | 0.000174 | +| loss | -0.0495 | +| n_updates | 2612 | +| policy_gradient_loss | -0.0323 | +| value_loss | 0.000108 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.204 | +| time/ | | +| fps | 1322 | +| iterations | 655 | +| time_elapsed | 1013 | +| total_timesteps | 1341440 | +| train/ | | +| approx_kl | 0.038870957 | +| clip_fraction | 0.377 | +| clip_range | 0.133 | +| entropy_loss | -7.07 | +| explained_variance | -0.086 | +| learning_rate | 0.000173 | +| loss | -0.0647 | +| n_updates | 2616 | +| policy_gradient_loss | -0.0336 | +| value_loss | 0.000196 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.209 | +| time/ | | +| fps | 1322 | +| iterations | 656 | +| time_elapsed | 1015 | +| total_timesteps | 1343488 | +| train/ | | +| approx_kl | 0.03891956 | +| clip_fraction | 0.366 | +| clip_range | 0.133 | +| entropy_loss | -7.15 | +| explained_variance | -0.094 | +| learning_rate | 0.000173 | +| loss | -0.0586 | +| n_updates | 2620 | +| policy_gradient_loss | -0.0289 | +| value_loss | 0.000314 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.21 | +| time/ | | +| fps | 1323 | +| iterations | 657 | +| time_elapsed | 1017 | +| total_timesteps | 1345536 | +| train/ | | +| approx_kl | 0.043784566 | +| clip_fraction | 0.412 | +| clip_range | 0.133 | +| entropy_loss | -7.09 | +| explained_variance | -0.0925 | +| learning_rate | 0.000173 | +| loss | -0.0634 | +| n_updates | 2624 | +| policy_gradient_loss | -0.0402 | +| value_loss | 0.000187 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.214 | +| time/ | | +| fps | 1323 | +| iterations | 658 | +| time_elapsed | 1018 | +| total_timesteps | 1347584 | +| train/ | | +| approx_kl | 0.044036414 | +| clip_fraction | 0.41 | +| clip_range | 0.133 | +| entropy_loss | -7.19 | +| explained_variance | -0.183 | +| learning_rate | 0.000173 | +| loss | -0.064 | +| n_updates | 2628 | +| policy_gradient_loss | -0.0407 | +| value_loss | 0.000151 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.211 | +| time/ | | +| fps | 1323 | +| iterations | 659 | +| time_elapsed | 1020 | +| total_timesteps | 1349632 | +| train/ | | +| approx_kl | 0.04796405 | +| clip_fraction | 0.403 | +| clip_range | 0.133 | +| entropy_loss | -7.25 | +| explained_variance | -0.121 | +| learning_rate | 0.000173 | +| loss | -0.0519 | +| n_updates | 2632 | +| policy_gradient_loss | -0.0335 | +| value_loss | 0.000248 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.211 | +| time/ | | +| fps | 1323 | +| iterations | 660 | +| time_elapsed | 1021 | +| total_timesteps | 1351680 | +| train/ | | +| approx_kl | 0.04229572 | +| clip_fraction | 0.425 | +| clip_range | 0.133 | +| entropy_loss | -7.19 | +| explained_variance | -0.149 | +| learning_rate | 0.000173 | +| loss | -0.0638 | +| n_updates | 2636 | +| policy_gradient_loss | -0.0422 | +| value_loss | 0.00011 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.215 | +| time/ | | +| fps | 1323 | +| iterations | 661 | +| time_elapsed | 1023 | +| total_timesteps | 1353728 | +| train/ | | +| approx_kl | 0.04518158 | +| clip_fraction | 0.435 | +| clip_range | 0.133 | +| entropy_loss | -7.03 | +| explained_variance | -0.792 | +| learning_rate | 0.000173 | +| loss | -0.0697 | +| n_updates | 2640 | +| policy_gradient_loss | -0.0473 | +| value_loss | 5.83e-05 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.214 | +| time/ | | +| fps | 1323 | +| iterations | 662 | +| time_elapsed | 1024 | +| total_timesteps | 1355776 | +| train/ | | +| approx_kl | 0.04364737 | +| clip_fraction | 0.4 | +| clip_range | 0.133 | +| entropy_loss | -6.97 | +| explained_variance | -0.182 | +| learning_rate | 0.000173 | +| loss | -0.0613 | +| n_updates | 2644 | +| policy_gradient_loss | -0.0353 | +| value_loss | 0.000178 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.209 | +| time/ | | +| fps | 1322 | +| iterations | 663 | +| time_elapsed | 1026 | +| total_timesteps | 1357824 | +| train/ | | +| approx_kl | 0.042465217 | +| clip_fraction | 0.379 | +| clip_range | 0.133 | +| entropy_loss | -7.02 | +| explained_variance | -0.136 | +| learning_rate | 0.000173 | +| loss | -0.0486 | +| n_updates | 2648 | +| policy_gradient_loss | -0.0337 | +| value_loss | 0.000113 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.21 | +| time/ | | +| fps | 1322 | +| iterations | 664 | +| time_elapsed | 1028 | +| total_timesteps | 1359872 | +| train/ | | +| approx_kl | 0.047212135 | +| clip_fraction | 0.402 | +| clip_range | 0.133 | +| entropy_loss | -7 | +| explained_variance | -0.0754 | +| learning_rate | 0.000173 | +| loss | -0.0533 | +| n_updates | 2652 | +| policy_gradient_loss | -0.0328 | +| value_loss | 0.000232 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.211 | +| time/ | | +| fps | 1322 | +| iterations | 665 | +| time_elapsed | 1029 | +| total_timesteps | 1361920 | +| train/ | | +| approx_kl | 0.042829625 | +| clip_fraction | 0.412 | +| clip_range | 0.133 | +| entropy_loss | -7.18 | +| explained_variance | -0.188 | +| learning_rate | 0.000173 | +| loss | -0.0569 | +| n_updates | 2656 | +| policy_gradient_loss | -0.0379 | +| value_loss | 8.16e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.202 | +| time/ | | +| fps | 1322 | +| iterations | 666 | +| time_elapsed | 1031 | +| total_timesteps | 1363968 | +| train/ | | +| approx_kl | 0.047433034 | +| clip_fraction | 0.403 | +| clip_range | 0.133 | +| entropy_loss | -7.19 | +| explained_variance | -0.122 | +| learning_rate | 0.000173 | +| loss | -0.0594 | +| n_updates | 2660 | +| policy_gradient_loss | -0.0393 | +| value_loss | 0.000116 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.202 | +| time/ | | +| fps | 1322 | +| iterations | 667 | +| time_elapsed | 1032 | +| total_timesteps | 1366016 | +| train/ | | +| approx_kl | 0.039750762 | +| clip_fraction | 0.383 | +| clip_range | 0.133 | +| entropy_loss | -7.26 | +| explained_variance | -0.0629 | +| learning_rate | 0.000173 | +| loss | -0.0545 | +| n_updates | 2664 | +| policy_gradient_loss | -0.0367 | +| value_loss | 8.4e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.202 | +| time/ | | +| fps | 1322 | +| iterations | 668 | +| time_elapsed | 1034 | +| total_timesteps | 1368064 | +| train/ | | +| approx_kl | 0.04682052 | +| clip_fraction | 0.373 | +| clip_range | 0.133 | +| entropy_loss | -7.1 | +| explained_variance | -0.0864 | +| learning_rate | 0.000173 | +| loss | -0.0479 | +| n_updates | 2668 | +| policy_gradient_loss | -0.0324 | +| value_loss | 0.000216 | +---------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.202 | +| time/ | | +| fps | 1322 | +| iterations | 669 | +| time_elapsed | 1035 | +| total_timesteps | 1370112 | +| train/ | | +| approx_kl | 0.0469367 | +| clip_fraction | 0.389 | +| clip_range | 0.133 | +| entropy_loss | -7.22 | +| explained_variance | -0.193 | +| learning_rate | 0.000173 | +| loss | -0.0652 | +| n_updates | 2672 | +| policy_gradient_loss | -0.0397 | +| value_loss | 8.48e-05 | +--------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.204 | +| time/ | | +| fps | 1322 | +| iterations | 670 | +| time_elapsed | 1037 | +| total_timesteps | 1372160 | +| train/ | | +| approx_kl | 0.03898451 | +| clip_fraction | 0.39 | +| clip_range | 0.133 | +| entropy_loss | -7.31 | +| explained_variance | -0.0429 | +| learning_rate | 0.000173 | +| loss | -0.0601 | +| n_updates | 2676 | +| policy_gradient_loss | -0.033 | +| value_loss | 0.000199 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.204 | +| time/ | | +| fps | 1322 | +| iterations | 671 | +| time_elapsed | 1039 | +| total_timesteps | 1374208 | +| train/ | | +| approx_kl | 0.04041264 | +| clip_fraction | 0.394 | +| clip_range | 0.133 | +| entropy_loss | -7.28 | +| explained_variance | -0.0876 | +| learning_rate | 0.000173 | +| loss | -0.0647 | +| n_updates | 2680 | +| policy_gradient_loss | -0.0359 | +| value_loss | 8.57e-05 | +---------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.208 | +| time/ | | +| fps | 1322 | +| iterations | 672 | +| time_elapsed | 1040 | +| total_timesteps | 1376256 | +| train/ | | +| approx_kl | 0.0383325 | +| clip_fraction | 0.356 | +| clip_range | 0.133 | +| entropy_loss | -7.16 | +| explained_variance | -0.116 | +| learning_rate | 0.000173 | +| loss | -0.0546 | +| n_updates | 2684 | +| policy_gradient_loss | -0.0323 | +| value_loss | 0.000169 | +--------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.21 | +| time/ | | +| fps | 1322 | +| iterations | 673 | +| time_elapsed | 1042 | +| total_timesteps | 1378304 | +| train/ | | +| approx_kl | 0.03609089 | +| clip_fraction | 0.387 | +| clip_range | 0.133 | +| entropy_loss | -7.19 | +| explained_variance | -0.306 | +| learning_rate | 0.000173 | +| loss | -0.058 | +| n_updates | 2688 | +| policy_gradient_loss | -0.037 | +| value_loss | 9.11e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.208 | +| time/ | | +| fps | 1322 | +| iterations | 674 | +| time_elapsed | 1043 | +| total_timesteps | 1380352 | +| train/ | | +| approx_kl | 0.041881572 | +| clip_fraction | 0.404 | +| clip_range | 0.133 | +| entropy_loss | -7.32 | +| explained_variance | -0.0301 | +| learning_rate | 0.000173 | +| loss | -0.0487 | +| n_updates | 2692 | +| policy_gradient_loss | -0.0291 | +| value_loss | 0.000272 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.208 | +| time/ | | +| fps | 1322 | +| iterations | 675 | +| time_elapsed | 1045 | +| total_timesteps | 1382400 | +| train/ | | +| approx_kl | 0.043000855 | +| clip_fraction | 0.393 | +| clip_range | 0.133 | +| entropy_loss | -7.24 | +| explained_variance | -0.407 | +| learning_rate | 0.000173 | +| loss | -0.0536 | +| n_updates | 2696 | +| policy_gradient_loss | -0.0379 | +| value_loss | 0.000109 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.206 | +| time/ | | +| fps | 1322 | +| iterations | 676 | +| time_elapsed | 1046 | +| total_timesteps | 1384448 | +| train/ | | +| approx_kl | 0.04593686 | +| clip_fraction | 0.37 | +| clip_range | 0.133 | +| entropy_loss | -7.15 | +| explained_variance | -0.173 | +| learning_rate | 0.000173 | +| loss | -0.0512 | +| n_updates | 2700 | +| policy_gradient_loss | -0.0307 | +| value_loss | 0.00014 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.213 | +| time/ | | +| fps | 1322 | +| iterations | 677 | +| time_elapsed | 1048 | +| total_timesteps | 1386496 | +| train/ | | +| approx_kl | 0.044744685 | +| clip_fraction | 0.385 | +| clip_range | 0.133 | +| entropy_loss | -7.24 | +| explained_variance | -0.0184 | +| learning_rate | 0.000173 | +| loss | -0.0629 | +| n_updates | 2704 | +| policy_gradient_loss | -0.0369 | +| value_loss | 7.88e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.214 | +| time/ | | +| fps | 1322 | +| iterations | 678 | +| time_elapsed | 1049 | +| total_timesteps | 1388544 | +| train/ | | +| approx_kl | 0.03738147 | +| clip_fraction | 0.389 | +| clip_range | 0.133 | +| entropy_loss | -7.33 | +| explained_variance | -0.138 | +| learning_rate | 0.000173 | +| loss | -0.0467 | +| n_updates | 2708 | +| policy_gradient_loss | -0.0322 | +| value_loss | 0.000211 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.219 | +| time/ | | +| fps | 1322 | +| iterations | 679 | +| time_elapsed | 1051 | +| total_timesteps | 1390592 | +| train/ | | +| approx_kl | 0.041137792 | +| clip_fraction | 0.387 | +| clip_range | 0.133 | +| entropy_loss | -7.24 | +| explained_variance | -0.139 | +| learning_rate | 0.000173 | +| loss | -0.07 | +| n_updates | 2712 | +| policy_gradient_loss | -0.0383 | +| value_loss | 8.31e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.216 | +| time/ | | +| fps | 1322 | +| iterations | 680 | +| time_elapsed | 1052 | +| total_timesteps | 1392640 | +| train/ | | +| approx_kl | 0.044989094 | +| clip_fraction | 0.39 | +| clip_range | 0.133 | +| entropy_loss | -7.32 | +| explained_variance | -0.18 | +| learning_rate | 0.000172 | +| loss | -0.0594 | +| n_updates | 2716 | +| policy_gradient_loss | -0.0403 | +| value_loss | 6.72e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.217 | +| time/ | | +| fps | 1322 | +| iterations | 681 | +| time_elapsed | 1054 | +| total_timesteps | 1394688 | +| train/ | | +| approx_kl | 0.04302441 | +| clip_fraction | 0.396 | +| clip_range | 0.133 | +| entropy_loss | -7.3 | +| explained_variance | -0.101 | +| learning_rate | 0.000172 | +| loss | -0.0567 | +| n_updates | 2720 | +| policy_gradient_loss | -0.0359 | +| value_loss | 7.21e-05 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.219 | +| time/ | | +| fps | 1322 | +| iterations | 682 | +| time_elapsed | 1056 | +| total_timesteps | 1396736 | +| train/ | | +| approx_kl | 0.04614435 | +| clip_fraction | 0.396 | +| clip_range | 0.133 | +| entropy_loss | -7.27 | +| explained_variance | -0.108 | +| learning_rate | 0.000172 | +| loss | -0.0693 | +| n_updates | 2724 | +| policy_gradient_loss | -0.0375 | +| value_loss | 7.59e-05 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.225 | +| time/ | | +| fps | 1322 | +| iterations | 683 | +| time_elapsed | 1057 | +| total_timesteps | 1398784 | +| train/ | | +| approx_kl | 0.04492741 | +| clip_fraction | 0.386 | +| clip_range | 0.133 | +| entropy_loss | -7.25 | +| explained_variance | -0.067 | +| learning_rate | 0.000172 | +| loss | -0.0545 | +| n_updates | 2728 | +| policy_gradient_loss | -0.0312 | +| value_loss | 0.000175 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.218 | +| time/ | | +| fps | 1322 | +| iterations | 684 | +| time_elapsed | 1059 | +| total_timesteps | 1400832 | +| train/ | | +| approx_kl | 0.042589188 | +| clip_fraction | 0.374 | +| clip_range | 0.133 | +| entropy_loss | -7.29 | +| explained_variance | -0.0818 | +| learning_rate | 0.000172 | +| loss | -0.056 | +| n_updates | 2732 | +| policy_gradient_loss | -0.0332 | +| value_loss | 0.000214 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.21 | +| time/ | | +| fps | 1322 | +| iterations | 685 | +| time_elapsed | 1060 | +| total_timesteps | 1402880 | +| train/ | | +| approx_kl | 0.03676583 | +| clip_fraction | 0.372 | +| clip_range | 0.132 | +| entropy_loss | -7.28 | +| explained_variance | -0.115 | +| learning_rate | 0.000172 | +| loss | -0.0641 | +| n_updates | 2736 | +| policy_gradient_loss | -0.0348 | +| value_loss | 0.000183 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.204 | +| time/ | | +| fps | 1322 | +| iterations | 686 | +| time_elapsed | 1062 | +| total_timesteps | 1404928 | +| train/ | | +| approx_kl | 0.041383155 | +| clip_fraction | 0.404 | +| clip_range | 0.132 | +| entropy_loss | -7.45 | +| explained_variance | -0.107 | +| learning_rate | 0.000172 | +| loss | -0.0619 | +| n_updates | 2740 | +| policy_gradient_loss | -0.0391 | +| value_loss | 0.000145 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.202 | +| time/ | | +| fps | 1322 | +| iterations | 687 | +| time_elapsed | 1063 | +| total_timesteps | 1406976 | +| train/ | | +| approx_kl | 0.04628769 | +| clip_fraction | 0.411 | +| clip_range | 0.132 | +| entropy_loss | -7.46 | +| explained_variance | -0.101 | +| learning_rate | 0.000172 | +| loss | -0.0616 | +| n_updates | 2744 | +| policy_gradient_loss | -0.0373 | +| value_loss | 0.000155 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.202 | +| time/ | | +| fps | 1322 | +| iterations | 688 | +| time_elapsed | 1065 | +| total_timesteps | 1409024 | +| train/ | | +| approx_kl | 0.046536155 | +| clip_fraction | 0.411 | +| clip_range | 0.132 | +| entropy_loss | -7.31 | +| explained_variance | -0.0218 | +| learning_rate | 0.000172 | +| loss | -0.0642 | +| n_updates | 2748 | +| policy_gradient_loss | -0.0377 | +| value_loss | 0.000193 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.203 | +| time/ | | +| fps | 1322 | +| iterations | 689 | +| time_elapsed | 1067 | +| total_timesteps | 1411072 | +| train/ | | +| approx_kl | 0.041068185 | +| clip_fraction | 0.4 | +| clip_range | 0.132 | +| entropy_loss | -7.31 | +| explained_variance | -0.0797 | +| learning_rate | 0.000172 | +| loss | -0.0605 | +| n_updates | 2752 | +| policy_gradient_loss | -0.0397 | +| value_loss | 0.00013 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.203 | +| time/ | | +| fps | 1322 | +| iterations | 690 | +| time_elapsed | 1068 | +| total_timesteps | 1413120 | +| train/ | | +| approx_kl | 0.03628323 | +| clip_fraction | 0.386 | +| clip_range | 0.132 | +| entropy_loss | -7.24 | +| explained_variance | -0.321 | +| learning_rate | 0.000172 | +| loss | -0.0689 | +| n_updates | 2756 | +| policy_gradient_loss | -0.036 | +| value_loss | 8.86e-05 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.203 | +| time/ | | +| fps | 1322 | +| iterations | 691 | +| time_elapsed | 1070 | +| total_timesteps | 1415168 | +| train/ | | +| approx_kl | 0.03910788 | +| clip_fraction | 0.391 | +| clip_range | 0.132 | +| entropy_loss | -7.25 | +| explained_variance | -0.0728 | +| learning_rate | 0.000172 | +| loss | -0.0631 | +| n_updates | 2760 | +| policy_gradient_loss | -0.035 | +| value_loss | 0.00012 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.195 | +| time/ | | +| fps | 1322 | +| iterations | 692 | +| time_elapsed | 1071 | +| total_timesteps | 1417216 | +| train/ | | +| approx_kl | 0.03891903 | +| clip_fraction | 0.385 | +| clip_range | 0.132 | +| entropy_loss | -7.31 | +| explained_variance | -0.118 | +| learning_rate | 0.000172 | +| loss | -0.0567 | +| n_updates | 2764 | +| policy_gradient_loss | -0.033 | +| value_loss | 0.000146 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.194 | +| time/ | | +| fps | 1322 | +| iterations | 693 | +| time_elapsed | 1073 | +| total_timesteps | 1419264 | +| train/ | | +| approx_kl | 0.03961243 | +| clip_fraction | 0.397 | +| clip_range | 0.132 | +| entropy_loss | -7.33 | +| explained_variance | -0.021 | +| learning_rate | 0.000172 | +| loss | -0.0471 | +| n_updates | 2768 | +| policy_gradient_loss | -0.0312 | +| value_loss | 0.000176 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.197 | +| time/ | | +| fps | 1322 | +| iterations | 694 | +| time_elapsed | 1074 | +| total_timesteps | 1421312 | +| train/ | | +| approx_kl | 0.041191034 | +| clip_fraction | 0.379 | +| clip_range | 0.132 | +| entropy_loss | -7.36 | +| explained_variance | -0.221 | +| learning_rate | 0.000172 | +| loss | -0.0565 | +| n_updates | 2772 | +| policy_gradient_loss | -0.0331 | +| value_loss | 0.000133 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.202 | +| time/ | | +| fps | 1322 | +| iterations | 695 | +| time_elapsed | 1076 | +| total_timesteps | 1423360 | +| train/ | | +| approx_kl | 0.048521385 | +| clip_fraction | 0.418 | +| clip_range | 0.132 | +| entropy_loss | -7.3 | +| explained_variance | -0.307 | +| learning_rate | 0.000172 | +| loss | -0.0687 | +| n_updates | 2776 | +| policy_gradient_loss | -0.0414 | +| value_loss | 7.56e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.202 | +| time/ | | +| fps | 1322 | +| iterations | 696 | +| time_elapsed | 1077 | +| total_timesteps | 1425408 | +| train/ | | +| approx_kl | 0.051814996 | +| clip_fraction | 0.398 | +| clip_range | 0.132 | +| entropy_loss | -7.34 | +| explained_variance | -0.06 | +| learning_rate | 0.000172 | +| loss | -0.0635 | +| n_updates | 2780 | +| policy_gradient_loss | -0.0318 | +| value_loss | 0.000153 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.202 | +| time/ | | +| fps | 1322 | +| iterations | 697 | +| time_elapsed | 1079 | +| total_timesteps | 1427456 | +| train/ | | +| approx_kl | 0.04451845 | +| clip_fraction | 0.411 | +| clip_range | 0.132 | +| entropy_loss | -7.24 | +| explained_variance | -0.14 | +| learning_rate | 0.000172 | +| loss | -0.0552 | +| n_updates | 2784 | +| policy_gradient_loss | -0.0338 | +| value_loss | 0.000117 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.202 | +| time/ | | +| fps | 1322 | +| iterations | 698 | +| time_elapsed | 1080 | +| total_timesteps | 1429504 | +| train/ | | +| approx_kl | 0.04390611 | +| clip_fraction | 0.397 | +| clip_range | 0.132 | +| entropy_loss | -7.18 | +| explained_variance | -0.0242 | +| learning_rate | 0.000172 | +| loss | -0.0572 | +| n_updates | 2788 | +| policy_gradient_loss | -0.0334 | +| value_loss | 0.000134 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.198 | +| time/ | | +| fps | 1322 | +| iterations | 699 | +| time_elapsed | 1082 | +| total_timesteps | 1431552 | +| train/ | | +| approx_kl | 0.04454031 | +| clip_fraction | 0.42 | +| clip_range | 0.132 | +| entropy_loss | -7.18 | +| explained_variance | -0.307 | +| learning_rate | 0.000172 | +| loss | -0.0608 | +| n_updates | 2792 | +| policy_gradient_loss | -0.0385 | +| value_loss | 6.62e-05 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.192 | +| time/ | | +| fps | 1322 | +| iterations | 700 | +| time_elapsed | 1083 | +| total_timesteps | 1433600 | +| train/ | | +| approx_kl | 0.04474312 | +| clip_fraction | 0.419 | +| clip_range | 0.132 | +| entropy_loss | -7.17 | +| explained_variance | -0.0624 | +| learning_rate | 0.000172 | +| loss | -0.059 | +| n_updates | 2796 | +| policy_gradient_loss | -0.0381 | +| value_loss | 6.96e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.192 | +| time/ | | +| fps | 1322 | +| iterations | 701 | +| time_elapsed | 1085 | +| total_timesteps | 1435648 | +| train/ | | +| approx_kl | 0.043772705 | +| clip_fraction | 0.395 | +| clip_range | 0.132 | +| entropy_loss | -7.16 | +| explained_variance | 0.0268 | +| learning_rate | 0.000172 | +| loss | -0.0626 | +| n_updates | 2800 | +| policy_gradient_loss | -0.0335 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.194 | +| time/ | | +| fps | 1322 | +| iterations | 702 | +| time_elapsed | 1086 | +| total_timesteps | 1437696 | +| train/ | | +| approx_kl | 0.050546825 | +| clip_fraction | 0.405 | +| clip_range | 0.132 | +| entropy_loss | -7.11 | +| explained_variance | -0.274 | +| learning_rate | 0.000172 | +| loss | -0.0622 | +| n_updates | 2804 | +| policy_gradient_loss | -0.0378 | +| value_loss | 6.57e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.189 | +| time/ | | +| fps | 1322 | +| iterations | 703 | +| time_elapsed | 1088 | +| total_timesteps | 1439744 | +| train/ | | +| approx_kl | 0.050554395 | +| clip_fraction | 0.404 | +| clip_range | 0.132 | +| entropy_loss | -7.13 | +| explained_variance | -0.0742 | +| learning_rate | 0.000172 | +| loss | -0.0538 | +| n_updates | 2808 | +| policy_gradient_loss | -0.0348 | +| value_loss | 0.000117 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.191 | +| time/ | | +| fps | 1322 | +| iterations | 704 | +| time_elapsed | 1090 | +| total_timesteps | 1441792 | +| train/ | | +| approx_kl | 0.045573976 | +| clip_fraction | 0.395 | +| clip_range | 0.132 | +| entropy_loss | -7.19 | +| explained_variance | -0.0188 | +| learning_rate | 0.000171 | +| loss | -0.0575 | +| n_updates | 2812 | +| policy_gradient_loss | -0.0377 | +| value_loss | 0.000164 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.188 | +| time/ | | +| fps | 1322 | +| iterations | 705 | +| time_elapsed | 1091 | +| total_timesteps | 1443840 | +| train/ | | +| approx_kl | 0.04763747 | +| clip_fraction | 0.406 | +| clip_range | 0.132 | +| entropy_loss | -7.14 | +| explained_variance | -0.116 | +| learning_rate | 0.000171 | +| loss | -0.0676 | +| n_updates | 2816 | +| policy_gradient_loss | -0.0358 | +| value_loss | 0.000126 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.187 | +| time/ | | +| fps | 1322 | +| iterations | 706 | +| time_elapsed | 1093 | +| total_timesteps | 1445888 | +| train/ | | +| approx_kl | 0.044185195 | +| clip_fraction | 0.401 | +| clip_range | 0.132 | +| entropy_loss | -6.96 | +| explained_variance | -0.172 | +| learning_rate | 0.000171 | +| loss | -0.0604 | +| n_updates | 2820 | +| policy_gradient_loss | -0.038 | +| value_loss | 0.000123 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.187 | +| time/ | | +| fps | 1322 | +| iterations | 707 | +| time_elapsed | 1094 | +| total_timesteps | 1447936 | +| train/ | | +| approx_kl | 0.0384731 | +| clip_fraction | 0.41 | +| clip_range | 0.132 | +| entropy_loss | -7.13 | +| explained_variance | -0.229 | +| learning_rate | 0.000171 | +| loss | -0.0673 | +| n_updates | 2824 | +| policy_gradient_loss | -0.033 | +| value_loss | 0.000144 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.187 | +| time/ | | +| fps | 1322 | +| iterations | 708 | +| time_elapsed | 1096 | +| total_timesteps | 1449984 | +| train/ | | +| approx_kl | 0.047723304 | +| clip_fraction | 0.404 | +| clip_range | 0.132 | +| entropy_loss | -7.03 | +| explained_variance | -0.0696 | +| learning_rate | 0.000171 | +| loss | -0.0533 | +| n_updates | 2828 | +| policy_gradient_loss | -0.0341 | +| value_loss | 0.000189 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.194 | +| time/ | | +| fps | 1322 | +| iterations | 709 | +| time_elapsed | 1097 | +| total_timesteps | 1452032 | +| train/ | | +| approx_kl | 0.045151796 | +| clip_fraction | 0.391 | +| clip_range | 0.132 | +| entropy_loss | -6.94 | +| explained_variance | -0.265 | +| learning_rate | 0.000171 | +| loss | -0.067 | +| n_updates | 2832 | +| policy_gradient_loss | -0.0359 | +| value_loss | 0.000126 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.192 | +| time/ | | +| fps | 1323 | +| iterations | 710 | +| time_elapsed | 1099 | +| total_timesteps | 1454080 | +| train/ | | +| approx_kl | 0.040442713 | +| clip_fraction | 0.399 | +| clip_range | 0.132 | +| entropy_loss | -7.02 | +| explained_variance | -0.0705 | +| learning_rate | 0.000171 | +| loss | -0.0492 | +| n_updates | 2836 | +| policy_gradient_loss | -0.03 | +| value_loss | 0.000191 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.192 | +| time/ | | +| fps | 1323 | +| iterations | 711 | +| time_elapsed | 1100 | +| total_timesteps | 1456128 | +| train/ | | +| approx_kl | 0.03828897 | +| clip_fraction | 0.392 | +| clip_range | 0.132 | +| entropy_loss | -6.93 | +| explained_variance | -0.015 | +| learning_rate | 0.000171 | +| loss | -0.0464 | +| n_updates | 2840 | +| policy_gradient_loss | -0.0292 | +| value_loss | 0.000303 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.197 | +| time/ | | +| fps | 1323 | +| iterations | 712 | +| time_elapsed | 1102 | +| total_timesteps | 1458176 | +| train/ | | +| approx_kl | 0.041535188 | +| clip_fraction | 0.418 | +| clip_range | 0.132 | +| entropy_loss | -7.09 | +| explained_variance | -0.143 | +| learning_rate | 0.000171 | +| loss | -0.0632 | +| n_updates | 2844 | +| policy_gradient_loss | -0.0336 | +| value_loss | 0.000161 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.207 | +| time/ | | +| fps | 1323 | +| iterations | 713 | +| time_elapsed | 1103 | +| total_timesteps | 1460224 | +| train/ | | +| approx_kl | 0.039496265 | +| clip_fraction | 0.417 | +| clip_range | 0.132 | +| entropy_loss | -7.08 | +| explained_variance | -0.182 | +| learning_rate | 0.000171 | +| loss | -0.058 | +| n_updates | 2848 | +| policy_gradient_loss | -0.0363 | +| value_loss | 0.000178 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.21 | +| time/ | | +| fps | 1323 | +| iterations | 714 | +| time_elapsed | 1105 | +| total_timesteps | 1462272 | +| train/ | | +| approx_kl | 0.04160148 | +| clip_fraction | 0.398 | +| clip_range | 0.132 | +| entropy_loss | -6.88 | +| explained_variance | -0.209 | +| learning_rate | 0.000171 | +| loss | -0.0573 | +| n_updates | 2852 | +| policy_gradient_loss | -0.0347 | +| value_loss | 0.000111 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.206 | +| time/ | | +| fps | 1323 | +| iterations | 715 | +| time_elapsed | 1106 | +| total_timesteps | 1464320 | +| train/ | | +| approx_kl | 0.03671905 | +| clip_fraction | 0.376 | +| clip_range | 0.132 | +| entropy_loss | -6.95 | +| explained_variance | 0.00953 | +| learning_rate | 0.000171 | +| loss | -0.0514 | +| n_updates | 2856 | +| policy_gradient_loss | -0.0301 | +| value_loss | 0.000227 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.207 | +| time/ | | +| fps | 1323 | +| iterations | 716 | +| time_elapsed | 1108 | +| total_timesteps | 1466368 | +| train/ | | +| approx_kl | 0.040689953 | +| clip_fraction | 0.403 | +| clip_range | 0.132 | +| entropy_loss | -7.23 | +| explained_variance | -0.316 | +| learning_rate | 0.000171 | +| loss | -0.0644 | +| n_updates | 2860 | +| policy_gradient_loss | -0.0388 | +| value_loss | 0.000103 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.207 | +| time/ | | +| fps | 1323 | +| iterations | 717 | +| time_elapsed | 1109 | +| total_timesteps | 1468416 | +| train/ | | +| approx_kl | 0.045728408 | +| clip_fraction | 0.422 | +| clip_range | 0.132 | +| entropy_loss | -7.28 | +| explained_variance | -0.227 | +| learning_rate | 0.000171 | +| loss | -0.0707 | +| n_updates | 2864 | +| policy_gradient_loss | -0.0388 | +| value_loss | 8.83e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.202 | +| time/ | | +| fps | 1323 | +| iterations | 718 | +| time_elapsed | 1111 | +| total_timesteps | 1470464 | +| train/ | | +| approx_kl | 0.04301223 | +| clip_fraction | 0.398 | +| clip_range | 0.132 | +| entropy_loss | -7.11 | +| explained_variance | -0.0961 | +| learning_rate | 0.000171 | +| loss | -0.0547 | +| n_updates | 2868 | +| policy_gradient_loss | -0.0316 | +| value_loss | 0.000165 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.202 | +| time/ | | +| fps | 1323 | +| iterations | 719 | +| time_elapsed | 1112 | +| total_timesteps | 1472512 | +| train/ | | +| approx_kl | 0.041843407 | +| clip_fraction | 0.376 | +| clip_range | 0.132 | +| entropy_loss | -6.98 | +| explained_variance | -0.0685 | +| learning_rate | 0.000171 | +| loss | -0.0541 | +| n_updates | 2872 | +| policy_gradient_loss | -0.0321 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.203 | +| time/ | | +| fps | 1323 | +| iterations | 720 | +| time_elapsed | 1114 | +| total_timesteps | 1474560 | +| train/ | | +| approx_kl | 0.043482102 | +| clip_fraction | 0.416 | +| clip_range | 0.132 | +| entropy_loss | -6.93 | +| explained_variance | -0.161 | +| learning_rate | 0.000171 | +| loss | -0.0558 | +| n_updates | 2876 | +| policy_gradient_loss | -0.0326 | +| value_loss | 0.000123 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.202 | +| time/ | | +| fps | 1323 | +| iterations | 721 | +| time_elapsed | 1115 | +| total_timesteps | 1476608 | +| train/ | | +| approx_kl | 0.04511751 | +| clip_fraction | 0.42 | +| clip_range | 0.132 | +| entropy_loss | -7.04 | +| explained_variance | -0.287 | +| learning_rate | 0.000171 | +| loss | -0.0562 | +| n_updates | 2880 | +| policy_gradient_loss | -0.0332 | +| value_loss | 0.000144 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.204 | +| time/ | | +| fps | 1323 | +| iterations | 722 | +| time_elapsed | 1117 | +| total_timesteps | 1478656 | +| train/ | | +| approx_kl | 0.03547755 | +| clip_fraction | 0.378 | +| clip_range | 0.132 | +| entropy_loss | -7.05 | +| explained_variance | -0.0397 | +| learning_rate | 0.000171 | +| loss | -0.058 | +| n_updates | 2884 | +| policy_gradient_loss | -0.032 | +| value_loss | 0.000213 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.208 | +| time/ | | +| fps | 1323 | +| iterations | 723 | +| time_elapsed | 1118 | +| total_timesteps | 1480704 | +| train/ | | +| approx_kl | 0.05048202 | +| clip_fraction | 0.407 | +| clip_range | 0.132 | +| entropy_loss | -7.15 | +| explained_variance | -0.108 | +| learning_rate | 0.000171 | +| loss | -0.0561 | +| n_updates | 2888 | +| policy_gradient_loss | -0.0349 | +| value_loss | 0.000173 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.205 | +| time/ | | +| fps | 1323 | +| iterations | 724 | +| time_elapsed | 1120 | +| total_timesteps | 1482752 | +| train/ | | +| approx_kl | 0.04240822 | +| clip_fraction | 0.413 | +| clip_range | 0.131 | +| entropy_loss | -7.13 | +| explained_variance | -0.0799 | +| learning_rate | 0.000171 | +| loss | -0.0619 | +| n_updates | 2892 | +| policy_gradient_loss | -0.0386 | +| value_loss | 0.000188 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.201 | +| time/ | | +| fps | 1323 | +| iterations | 725 | +| time_elapsed | 1121 | +| total_timesteps | 1484800 | +| train/ | | +| approx_kl | 0.048855443 | +| clip_fraction | 0.41 | +| clip_range | 0.131 | +| entropy_loss | -7.21 | +| explained_variance | -0.212 | +| learning_rate | 0.000171 | +| loss | -0.0619 | +| n_updates | 2896 | +| policy_gradient_loss | -0.0409 | +| value_loss | 9.91e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.201 | +| time/ | | +| fps | 1323 | +| iterations | 726 | +| time_elapsed | 1123 | +| total_timesteps | 1486848 | +| train/ | | +| approx_kl | 0.05244919 | +| clip_fraction | 0.415 | +| clip_range | 0.131 | +| entropy_loss | -7.14 | +| explained_variance | -0.117 | +| learning_rate | 0.000171 | +| loss | -0.0647 | +| n_updates | 2900 | +| policy_gradient_loss | -0.0389 | +| value_loss | 0.000101 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.201 | +| time/ | | +| fps | 1323 | +| iterations | 727 | +| time_elapsed | 1124 | +| total_timesteps | 1488896 | +| train/ | | +| approx_kl | 0.04998055 | +| clip_fraction | 0.419 | +| clip_range | 0.131 | +| entropy_loss | -7.14 | +| explained_variance | -0.111 | +| learning_rate | 0.000171 | +| loss | -0.0456 | +| n_updates | 2904 | +| policy_gradient_loss | -0.0359 | +| value_loss | 0.000166 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.202 | +| time/ | | +| fps | 1323 | +| iterations | 728 | +| time_elapsed | 1126 | +| total_timesteps | 1490944 | +| train/ | | +| approx_kl | 0.04096648 | +| clip_fraction | 0.404 | +| clip_range | 0.131 | +| entropy_loss | -7.06 | +| explained_variance | -0.151 | +| learning_rate | 0.000171 | +| loss | -0.052 | +| n_updates | 2908 | +| policy_gradient_loss | -0.0334 | +| value_loss | 9.93e-05 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.202 | +| time/ | | +| fps | 1323 | +| iterations | 729 | +| time_elapsed | 1128 | +| total_timesteps | 1492992 | +| train/ | | +| approx_kl | 0.03422941 | +| clip_fraction | 0.372 | +| clip_range | 0.131 | +| entropy_loss | -7.05 | +| explained_variance | 0.00301 | +| learning_rate | 0.00017 | +| loss | -0.0475 | +| n_updates | 2912 | +| policy_gradient_loss | -0.0293 | +| value_loss | 0.000206 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.202 | +| time/ | | +| fps | 1323 | +| iterations | 730 | +| time_elapsed | 1129 | +| total_timesteps | 1495040 | +| train/ | | +| approx_kl | 0.037754856 | +| clip_fraction | 0.419 | +| clip_range | 0.131 | +| entropy_loss | -6.93 | +| explained_variance | -0.0979 | +| learning_rate | 0.00017 | +| loss | -0.0576 | +| n_updates | 2916 | +| policy_gradient_loss | -0.0328 | +| value_loss | 0.00013 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.205 | +| time/ | | +| fps | 1323 | +| iterations | 731 | +| time_elapsed | 1131 | +| total_timesteps | 1497088 | +| train/ | | +| approx_kl | 0.038806446 | +| clip_fraction | 0.409 | +| clip_range | 0.131 | +| entropy_loss | -6.84 | +| explained_variance | -0.0884 | +| learning_rate | 0.00017 | +| loss | -0.0509 | +| n_updates | 2920 | +| policy_gradient_loss | -0.0295 | +| value_loss | 0.000129 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.204 | +| time/ | | +| fps | 1323 | +| iterations | 732 | +| time_elapsed | 1132 | +| total_timesteps | 1499136 | +| train/ | | +| approx_kl | 0.035241652 | +| clip_fraction | 0.393 | +| clip_range | 0.131 | +| entropy_loss | -6.78 | +| explained_variance | -0.174 | +| learning_rate | 0.00017 | +| loss | -0.0584 | +| n_updates | 2924 | +| policy_gradient_loss | -0.037 | +| value_loss | 8.98e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.214 | +| time/ | | +| fps | 1323 | +| iterations | 733 | +| time_elapsed | 1134 | +| total_timesteps | 1501184 | +| train/ | | +| approx_kl | 0.044093795 | +| clip_fraction | 0.403 | +| clip_range | 0.131 | +| entropy_loss | -6.91 | +| explained_variance | -0.00112 | +| learning_rate | 0.00017 | +| loss | -0.0518 | +| n_updates | 2928 | +| policy_gradient_loss | -0.0305 | +| value_loss | 0.000133 | +----------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.217 | +| time/ | | +| fps | 1323 | +| iterations | 734 | +| time_elapsed | 1135 | +| total_timesteps | 1503232 | +| train/ | | +| approx_kl | 0.043927 | +| clip_fraction | 0.398 | +| clip_range | 0.131 | +| entropy_loss | -6.99 | +| explained_variance | -0.123 | +| learning_rate | 0.00017 | +| loss | -0.0616 | +| n_updates | 2932 | +| policy_gradient_loss | -0.0315 | +| value_loss | 0.000125 | +-------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.217 | +| time/ | | +| fps | 1323 | +| iterations | 735 | +| time_elapsed | 1137 | +| total_timesteps | 1505280 | +| train/ | | +| approx_kl | 0.046236154 | +| clip_fraction | 0.399 | +| clip_range | 0.131 | +| entropy_loss | -6.99 | +| explained_variance | -0.142 | +| learning_rate | 0.00017 | +| loss | -0.0584 | +| n_updates | 2936 | +| policy_gradient_loss | -0.0378 | +| value_loss | 9.55e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.217 | +| time/ | | +| fps | 1323 | +| iterations | 736 | +| time_elapsed | 1138 | +| total_timesteps | 1507328 | +| train/ | | +| approx_kl | 0.044458933 | +| clip_fraction | 0.411 | +| clip_range | 0.131 | +| entropy_loss | -6.89 | +| explained_variance | -0.29 | +| learning_rate | 0.00017 | +| loss | -0.0636 | +| n_updates | 2940 | +| policy_gradient_loss | -0.0403 | +| value_loss | 5.56e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.21 | +| time/ | | +| fps | 1323 | +| iterations | 737 | +| time_elapsed | 1140 | +| total_timesteps | 1509376 | +| train/ | | +| approx_kl | 0.04672678 | +| clip_fraction | 0.395 | +| clip_range | 0.131 | +| entropy_loss | -6.83 | +| explained_variance | -0.0556 | +| learning_rate | 0.00017 | +| loss | -0.0483 | +| n_updates | 2944 | +| policy_gradient_loss | -0.0318 | +| value_loss | 0.000116 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.21 | +| time/ | | +| fps | 1323 | +| iterations | 738 | +| time_elapsed | 1142 | +| total_timesteps | 1511424 | +| train/ | | +| approx_kl | 0.042012617 | +| clip_fraction | 0.397 | +| clip_range | 0.131 | +| entropy_loss | -6.82 | +| explained_variance | 0.0063 | +| learning_rate | 0.00017 | +| loss | -0.051 | +| n_updates | 2948 | +| policy_gradient_loss | -0.0285 | +| value_loss | 0.000201 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.216 | +| time/ | | +| fps | 1323 | +| iterations | 739 | +| time_elapsed | 1143 | +| total_timesteps | 1513472 | +| train/ | | +| approx_kl | 0.041933432 | +| clip_fraction | 0.439 | +| clip_range | 0.131 | +| entropy_loss | -6.89 | +| explained_variance | -0.516 | +| learning_rate | 0.00017 | +| loss | -0.0716 | +| n_updates | 2952 | +| policy_gradient_loss | -0.0437 | +| value_loss | 5.22e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.214 | +| time/ | | +| fps | 1323 | +| iterations | 740 | +| time_elapsed | 1145 | +| total_timesteps | 1515520 | +| train/ | | +| approx_kl | 0.04329379 | +| clip_fraction | 0.404 | +| clip_range | 0.131 | +| entropy_loss | -6.88 | +| explained_variance | -0.147 | +| learning_rate | 0.00017 | +| loss | -0.0573 | +| n_updates | 2956 | +| policy_gradient_loss | -0.0342 | +| value_loss | 0.000122 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.21 | +| time/ | | +| fps | 1323 | +| iterations | 741 | +| time_elapsed | 1146 | +| total_timesteps | 1517568 | +| train/ | | +| approx_kl | 0.04005851 | +| clip_fraction | 0.395 | +| clip_range | 0.131 | +| entropy_loss | -7.02 | +| explained_variance | -0.0955 | +| learning_rate | 0.00017 | +| loss | -0.056 | +| n_updates | 2960 | +| policy_gradient_loss | -0.0311 | +| value_loss | 0.000127 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.205 | +| time/ | | +| fps | 1323 | +| iterations | 742 | +| time_elapsed | 1148 | +| total_timesteps | 1519616 | +| train/ | | +| approx_kl | 0.036113463 | +| clip_fraction | 0.382 | +| clip_range | 0.131 | +| entropy_loss | -7.05 | +| explained_variance | -0.19 | +| learning_rate | 0.00017 | +| loss | -0.0489 | +| n_updates | 2964 | +| policy_gradient_loss | -0.0304 | +| value_loss | 0.000123 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.201 | +| time/ | | +| fps | 1323 | +| iterations | 743 | +| time_elapsed | 1149 | +| total_timesteps | 1521664 | +| train/ | | +| approx_kl | 0.036026023 | +| clip_fraction | 0.387 | +| clip_range | 0.131 | +| entropy_loss | -7.12 | +| explained_variance | -0.0718 | +| learning_rate | 0.00017 | +| loss | -0.0547 | +| n_updates | 2968 | +| policy_gradient_loss | -0.031 | +| value_loss | 0.000151 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.203 | +| time/ | | +| fps | 1323 | +| iterations | 744 | +| time_elapsed | 1151 | +| total_timesteps | 1523712 | +| train/ | | +| approx_kl | 0.043696582 | +| clip_fraction | 0.398 | +| clip_range | 0.131 | +| entropy_loss | -7.14 | +| explained_variance | -0.124 | +| learning_rate | 0.00017 | +| loss | -0.0593 | +| n_updates | 2972 | +| policy_gradient_loss | -0.0316 | +| value_loss | 0.000114 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.203 | +| time/ | | +| fps | 1323 | +| iterations | 745 | +| time_elapsed | 1152 | +| total_timesteps | 1525760 | +| train/ | | +| approx_kl | 0.03999546 | +| clip_fraction | 0.396 | +| clip_range | 0.131 | +| entropy_loss | -7.09 | +| explained_variance | -0.112 | +| learning_rate | 0.00017 | +| loss | -0.0537 | +| n_updates | 2976 | +| policy_gradient_loss | -0.0337 | +| value_loss | 0.00012 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.204 | +| time/ | | +| fps | 1323 | +| iterations | 746 | +| time_elapsed | 1154 | +| total_timesteps | 1527808 | +| train/ | | +| approx_kl | 0.03315451 | +| clip_fraction | 0.376 | +| clip_range | 0.131 | +| entropy_loss | -7.03 | +| explained_variance | -0.123 | +| learning_rate | 0.00017 | +| loss | -0.0559 | +| n_updates | 2980 | +| policy_gradient_loss | -0.0353 | +| value_loss | 0.000146 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.198 | +| time/ | | +| fps | 1323 | +| iterations | 747 | +| time_elapsed | 1155 | +| total_timesteps | 1529856 | +| train/ | | +| approx_kl | 0.038737446 | +| clip_fraction | 0.381 | +| clip_range | 0.131 | +| entropy_loss | -7.07 | +| explained_variance | -0.149 | +| learning_rate | 0.00017 | +| loss | -0.0509 | +| n_updates | 2984 | +| policy_gradient_loss | -0.0295 | +| value_loss | 9.48e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.2 | +| time/ | | +| fps | 1323 | +| iterations | 748 | +| time_elapsed | 1157 | +| total_timesteps | 1531904 | +| train/ | | +| approx_kl | 0.038754035 | +| clip_fraction | 0.357 | +| clip_range | 0.131 | +| entropy_loss | -7.07 | +| explained_variance | -0.0241 | +| learning_rate | 0.00017 | +| loss | -0.0533 | +| n_updates | 2988 | +| policy_gradient_loss | -0.0292 | +| value_loss | 0.000185 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.201 | +| time/ | | +| fps | 1323 | +| iterations | 749 | +| time_elapsed | 1159 | +| total_timesteps | 1533952 | +| train/ | | +| approx_kl | 0.047860056 | +| clip_fraction | 0.39 | +| clip_range | 0.131 | +| entropy_loss | -6.98 | +| explained_variance | -0.0776 | +| learning_rate | 0.00017 | +| loss | -0.0628 | +| n_updates | 2992 | +| policy_gradient_loss | -0.036 | +| value_loss | 0.000102 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.197 | +| time/ | | +| fps | 1323 | +| iterations | 750 | +| time_elapsed | 1160 | +| total_timesteps | 1536000 | +| train/ | | +| approx_kl | 0.040892445 | +| clip_fraction | 0.4 | +| clip_range | 0.131 | +| entropy_loss | -7.02 | +| explained_variance | -0.0818 | +| learning_rate | 0.00017 | +| loss | -0.0466 | +| n_updates | 2996 | +| policy_gradient_loss | -0.0297 | +| value_loss | 0.000155 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.197 | +| time/ | | +| fps | 1323 | +| iterations | 751 | +| time_elapsed | 1162 | +| total_timesteps | 1538048 | +| train/ | | +| approx_kl | 0.043728653 | +| clip_fraction | 0.408 | +| clip_range | 0.131 | +| entropy_loss | -7.06 | +| explained_variance | -0.0662 | +| learning_rate | 0.00017 | +| loss | -0.064 | +| n_updates | 3000 | +| policy_gradient_loss | -0.0353 | +| value_loss | 0.000124 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.202 | +| time/ | | +| fps | 1323 | +| iterations | 752 | +| time_elapsed | 1163 | +| total_timesteps | 1540096 | +| train/ | | +| approx_kl | 0.04299824 | +| clip_fraction | 0.411 | +| clip_range | 0.131 | +| entropy_loss | -7.21 | +| explained_variance | -0.141 | +| learning_rate | 0.00017 | +| loss | -0.0556 | +| n_updates | 3004 | +| policy_gradient_loss | -0.0348 | +| value_loss | 0.000137 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.208 | +| time/ | | +| fps | 1323 | +| iterations | 753 | +| time_elapsed | 1165 | +| total_timesteps | 1542144 | +| train/ | | +| approx_kl | 0.044688217 | +| clip_fraction | 0.379 | +| clip_range | 0.131 | +| entropy_loss | -7.31 | +| explained_variance | -0.146 | +| learning_rate | 0.00017 | +| loss | -0.0599 | +| n_updates | 3008 | +| policy_gradient_loss | -0.0327 | +| value_loss | 0.000167 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.214 | +| time/ | | +| fps | 1323 | +| iterations | 754 | +| time_elapsed | 1167 | +| total_timesteps | 1544192 | +| train/ | | +| approx_kl | 0.045883834 | +| clip_fraction | 0.399 | +| clip_range | 0.131 | +| entropy_loss | -7.21 | +| explained_variance | -0.134 | +| learning_rate | 0.000169 | +| loss | -0.0552 | +| n_updates | 3012 | +| policy_gradient_loss | -0.0359 | +| value_loss | 0.000105 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.216 | +| time/ | | +| fps | 1323 | +| iterations | 755 | +| time_elapsed | 1168 | +| total_timesteps | 1546240 | +| train/ | | +| approx_kl | 0.032311387 | +| clip_fraction | 0.359 | +| clip_range | 0.131 | +| entropy_loss | -7.06 | +| explained_variance | -0.0346 | +| learning_rate | 0.000169 | +| loss | -0.0395 | +| n_updates | 3016 | +| policy_gradient_loss | -0.027 | +| value_loss | 0.000349 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.21 | +| time/ | | +| fps | 1323 | +| iterations | 756 | +| time_elapsed | 1170 | +| total_timesteps | 1548288 | +| train/ | | +| approx_kl | 0.044125877 | +| clip_fraction | 0.394 | +| clip_range | 0.131 | +| entropy_loss | -7.23 | +| explained_variance | -0.239 | +| learning_rate | 0.000169 | +| loss | -0.064 | +| n_updates | 3020 | +| policy_gradient_loss | -0.0376 | +| value_loss | 7.64e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.211 | +| time/ | | +| fps | 1323 | +| iterations | 757 | +| time_elapsed | 1171 | +| total_timesteps | 1550336 | +| train/ | | +| approx_kl | 0.037625834 | +| clip_fraction | 0.383 | +| clip_range | 0.131 | +| entropy_loss | -7.06 | +| explained_variance | -0.183 | +| learning_rate | 0.000169 | +| loss | -0.0629 | +| n_updates | 3024 | +| policy_gradient_loss | -0.0331 | +| value_loss | 0.000151 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.207 | +| time/ | | +| fps | 1322 | +| iterations | 758 | +| time_elapsed | 1173 | +| total_timesteps | 1552384 | +| train/ | | +| approx_kl | 0.04229237 | +| clip_fraction | 0.396 | +| clip_range | 0.131 | +| entropy_loss | -7.04 | +| explained_variance | -0.0699 | +| learning_rate | 0.000169 | +| loss | -0.0601 | +| n_updates | 3028 | +| policy_gradient_loss | -0.0374 | +| value_loss | 8.58e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.207 | +| time/ | | +| fps | 1322 | +| iterations | 759 | +| time_elapsed | 1174 | +| total_timesteps | 1554432 | +| train/ | | +| approx_kl | 0.040985487 | +| clip_fraction | 0.383 | +| clip_range | 0.131 | +| entropy_loss | -7.04 | +| explained_variance | -0.0624 | +| learning_rate | 0.000169 | +| loss | -0.0536 | +| n_updates | 3032 | +| policy_gradient_loss | -0.0324 | +| value_loss | 0.000179 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.207 | +| time/ | | +| fps | 1323 | +| iterations | 760 | +| time_elapsed | 1176 | +| total_timesteps | 1556480 | +| train/ | | +| approx_kl | 0.04385186 | +| clip_fraction | 0.389 | +| clip_range | 0.131 | +| entropy_loss | -7.17 | +| explained_variance | -0.0487 | +| learning_rate | 0.000169 | +| loss | -0.055 | +| n_updates | 3036 | +| policy_gradient_loss | -0.0353 | +| value_loss | 0.000147 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.208 | +| time/ | | +| fps | 1323 | +| iterations | 761 | +| time_elapsed | 1178 | +| total_timesteps | 1558528 | +| train/ | | +| approx_kl | 0.03975442 | +| clip_fraction | 0.362 | +| clip_range | 0.131 | +| entropy_loss | -7.16 | +| explained_variance | -0.0372 | +| learning_rate | 0.000169 | +| loss | -0.0561 | +| n_updates | 3040 | +| policy_gradient_loss | -0.0343 | +| value_loss | 0.0002 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.212 | +| time/ | | +| fps | 1323 | +| iterations | 762 | +| time_elapsed | 1179 | +| total_timesteps | 1560576 | +| train/ | | +| approx_kl | 0.034683835 | +| clip_fraction | 0.372 | +| clip_range | 0.131 | +| entropy_loss | -7.05 | +| explained_variance | -0.0969 | +| learning_rate | 0.000169 | +| loss | -0.0589 | +| n_updates | 3044 | +| policy_gradient_loss | -0.0337 | +| value_loss | 0.000138 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.207 | +| time/ | | +| fps | 1323 | +| iterations | 763 | +| time_elapsed | 1181 | +| total_timesteps | 1562624 | +| train/ | | +| approx_kl | 0.03588054 | +| clip_fraction | 0.382 | +| clip_range | 0.13 | +| entropy_loss | -7.11 | +| explained_variance | 0.0338 | +| learning_rate | 0.000169 | +| loss | -0.0569 | +| n_updates | 3048 | +| policy_gradient_loss | -0.0307 | +| value_loss | 0.000206 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.208 | +| time/ | | +| fps | 1322 | +| iterations | 764 | +| time_elapsed | 1182 | +| total_timesteps | 1564672 | +| train/ | | +| approx_kl | 0.042340517 | +| clip_fraction | 0.411 | +| clip_range | 0.13 | +| entropy_loss | -7.16 | +| explained_variance | -0.123 | +| learning_rate | 0.000169 | +| loss | -0.0519 | +| n_updates | 3052 | +| policy_gradient_loss | -0.0376 | +| value_loss | 0.000199 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.209 | +| time/ | | +| fps | 1322 | +| iterations | 765 | +| time_elapsed | 1184 | +| total_timesteps | 1566720 | +| train/ | | +| approx_kl | 0.03605064 | +| clip_fraction | 0.359 | +| clip_range | 0.13 | +| entropy_loss | -7.15 | +| explained_variance | 0.0291 | +| learning_rate | 0.000169 | +| loss | -0.0474 | +| n_updates | 3056 | +| policy_gradient_loss | -0.0318 | +| value_loss | 0.000227 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.209 | +| time/ | | +| fps | 1322 | +| iterations | 766 | +| time_elapsed | 1185 | +| total_timesteps | 1568768 | +| train/ | | +| approx_kl | 0.037343074 | +| clip_fraction | 0.391 | +| clip_range | 0.13 | +| entropy_loss | -7.13 | +| explained_variance | 0.0894 | +| learning_rate | 0.000169 | +| loss | -0.065 | +| n_updates | 3060 | +| policy_gradient_loss | -0.0406 | +| value_loss | 0.000114 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.217 | +| time/ | | +| fps | 1322 | +| iterations | 767 | +| time_elapsed | 1187 | +| total_timesteps | 1570816 | +| train/ | | +| approx_kl | 0.04176283 | +| clip_fraction | 0.394 | +| clip_range | 0.13 | +| entropy_loss | -7.15 | +| explained_variance | -0.196 | +| learning_rate | 0.000169 | +| loss | -0.0598 | +| n_updates | 3064 | +| policy_gradient_loss | -0.0373 | +| value_loss | 9.89e-05 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.225 | +| time/ | | +| fps | 1322 | +| iterations | 768 | +| time_elapsed | 1188 | +| total_timesteps | 1572864 | +| train/ | | +| approx_kl | 0.04525486 | +| clip_fraction | 0.399 | +| clip_range | 0.13 | +| entropy_loss | -7.05 | +| explained_variance | -0.149 | +| learning_rate | 0.000169 | +| loss | -0.054 | +| n_updates | 3068 | +| policy_gradient_loss | -0.0349 | +| value_loss | 0.000105 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.23 | +| time/ | | +| fps | 1322 | +| iterations | 769 | +| time_elapsed | 1190 | +| total_timesteps | 1574912 | +| train/ | | +| approx_kl | 0.035229355 | +| clip_fraction | 0.361 | +| clip_range | 0.13 | +| entropy_loss | -7 | +| explained_variance | -0.0336 | +| learning_rate | 0.000169 | +| loss | -0.0536 | +| n_updates | 3072 | +| policy_gradient_loss | -0.0302 | +| value_loss | 0.000253 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.23 | +| time/ | | +| fps | 1322 | +| iterations | 770 | +| time_elapsed | 1192 | +| total_timesteps | 1576960 | +| train/ | | +| approx_kl | 0.034310322 | +| clip_fraction | 0.394 | +| clip_range | 0.13 | +| entropy_loss | -6.92 | +| explained_variance | 0.0467 | +| learning_rate | 0.000169 | +| loss | -0.0447 | +| n_updates | 3076 | +| policy_gradient_loss | -0.0336 | +| value_loss | 0.000208 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.232 | +| time/ | | +| fps | 1322 | +| iterations | 771 | +| time_elapsed | 1193 | +| total_timesteps | 1579008 | +| train/ | | +| approx_kl | 0.034659438 | +| clip_fraction | 0.402 | +| clip_range | 0.13 | +| entropy_loss | -6.91 | +| explained_variance | -0.392 | +| learning_rate | 0.000169 | +| loss | -0.0564 | +| n_updates | 3080 | +| policy_gradient_loss | -0.0333 | +| value_loss | 0.00013 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.238 | +| time/ | | +| fps | 1322 | +| iterations | 772 | +| time_elapsed | 1195 | +| total_timesteps | 1581056 | +| train/ | | +| approx_kl | 0.040551107 | +| clip_fraction | 0.403 | +| clip_range | 0.13 | +| entropy_loss | -6.99 | +| explained_variance | -0.259 | +| learning_rate | 0.000169 | +| loss | -0.0593 | +| n_updates | 3084 | +| policy_gradient_loss | -0.038 | +| value_loss | 0.000106 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.238 | +| time/ | | +| fps | 1322 | +| iterations | 773 | +| time_elapsed | 1196 | +| total_timesteps | 1583104 | +| train/ | | +| approx_kl | 0.036992524 | +| clip_fraction | 0.37 | +| clip_range | 0.13 | +| entropy_loss | -6.93 | +| explained_variance | -0.0063 | +| learning_rate | 0.000169 | +| loss | -0.0483 | +| n_updates | 3088 | +| policy_gradient_loss | -0.0318 | +| value_loss | 0.000286 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.239 | +| time/ | | +| fps | 1322 | +| iterations | 774 | +| time_elapsed | 1198 | +| total_timesteps | 1585152 | +| train/ | | +| approx_kl | 0.038342115 | +| clip_fraction | 0.358 | +| clip_range | 0.13 | +| entropy_loss | -6.92 | +| explained_variance | 0.0686 | +| learning_rate | 0.000169 | +| loss | -0.056 | +| n_updates | 3092 | +| policy_gradient_loss | -0.0354 | +| value_loss | 0.000182 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.234 | +| time/ | | +| fps | 1322 | +| iterations | 775 | +| time_elapsed | 1199 | +| total_timesteps | 1587200 | +| train/ | | +| approx_kl | 0.033931334 | +| clip_fraction | 0.36 | +| clip_range | 0.13 | +| entropy_loss | -7.03 | +| explained_variance | -0.203 | +| learning_rate | 0.000169 | +| loss | -0.0524 | +| n_updates | 3096 | +| policy_gradient_loss | -0.0321 | +| value_loss | 0.000119 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.234 | +| time/ | | +| fps | 1322 | +| iterations | 776 | +| time_elapsed | 1201 | +| total_timesteps | 1589248 | +| train/ | | +| approx_kl | 0.035821345 | +| clip_fraction | 0.403 | +| clip_range | 0.13 | +| entropy_loss | -6.95 | +| explained_variance | -0.143 | +| learning_rate | 0.000169 | +| loss | -0.0735 | +| n_updates | 3100 | +| policy_gradient_loss | -0.0421 | +| value_loss | 5.24e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.237 | +| time/ | | +| fps | 1322 | +| iterations | 777 | +| time_elapsed | 1203 | +| total_timesteps | 1591296 | +| train/ | | +| approx_kl | 0.04186546 | +| clip_fraction | 0.368 | +| clip_range | 0.13 | +| entropy_loss | -6.89 | +| explained_variance | -0.127 | +| learning_rate | 0.000169 | +| loss | -0.0493 | +| n_updates | 3104 | +| policy_gradient_loss | -0.0286 | +| value_loss | 0.000151 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.237 | +| time/ | | +| fps | 1322 | +| iterations | 778 | +| time_elapsed | 1204 | +| total_timesteps | 1593344 | +| train/ | | +| approx_kl | 0.03655883 | +| clip_fraction | 0.407 | +| clip_range | 0.13 | +| entropy_loss | -6.74 | +| explained_variance | -0.0807 | +| learning_rate | 0.000168 | +| loss | -0.0526 | +| n_updates | 3108 | +| policy_gradient_loss | -0.0297 | +| value_loss | 0.000138 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.232 | +| time/ | | +| fps | 1322 | +| iterations | 779 | +| time_elapsed | 1206 | +| total_timesteps | 1595392 | +| train/ | | +| approx_kl | 0.035893366 | +| clip_fraction | 0.408 | +| clip_range | 0.13 | +| entropy_loss | -6.74 | +| explained_variance | -0.0543 | +| learning_rate | 0.000168 | +| loss | -0.0616 | +| n_updates | 3112 | +| policy_gradient_loss | -0.0319 | +| value_loss | 0.000174 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.231 | +| time/ | | +| fps | 1322 | +| iterations | 780 | +| time_elapsed | 1207 | +| total_timesteps | 1597440 | +| train/ | | +| approx_kl | 0.043470252 | +| clip_fraction | 0.435 | +| clip_range | 0.13 | +| entropy_loss | -6.88 | +| explained_variance | -0.109 | +| learning_rate | 0.000168 | +| loss | -0.0654 | +| n_updates | 3116 | +| policy_gradient_loss | -0.0391 | +| value_loss | 7.84e-05 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.23 | +| time/ | | +| fps | 1322 | +| iterations | 781 | +| time_elapsed | 1209 | +| total_timesteps | 1599488 | +| train/ | | +| approx_kl | 0.0358319 | +| clip_fraction | 0.391 | +| clip_range | 0.13 | +| entropy_loss | -6.97 | +| explained_variance | 0.0422 | +| learning_rate | 0.000168 | +| loss | -0.0483 | +| n_updates | 3120 | +| policy_gradient_loss | -0.0316 | +| value_loss | 0.000182 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.226 | +| time/ | | +| fps | 1322 | +| iterations | 782 | +| time_elapsed | 1211 | +| total_timesteps | 1601536 | +| train/ | | +| approx_kl | 0.041846417 | +| clip_fraction | 0.372 | +| clip_range | 0.13 | +| entropy_loss | -6.97 | +| explained_variance | -0.00434 | +| learning_rate | 0.000168 | +| loss | -0.0602 | +| n_updates | 3124 | +| policy_gradient_loss | -0.0334 | +| value_loss | 0.000163 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.218 | +| time/ | | +| fps | 1322 | +| iterations | 783 | +| time_elapsed | 1212 | +| total_timesteps | 1603584 | +| train/ | | +| approx_kl | 0.044013187 | +| clip_fraction | 0.407 | +| clip_range | 0.13 | +| entropy_loss | -6.93 | +| explained_variance | -0.3 | +| learning_rate | 0.000168 | +| loss | -0.0743 | +| n_updates | 3128 | +| policy_gradient_loss | -0.0401 | +| value_loss | 7.48e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.223 | +| time/ | | +| fps | 1322 | +| iterations | 784 | +| time_elapsed | 1214 | +| total_timesteps | 1605632 | +| train/ | | +| approx_kl | 0.03939284 | +| clip_fraction | 0.4 | +| clip_range | 0.13 | +| entropy_loss | -6.74 | +| explained_variance | -0.107 | +| learning_rate | 0.000168 | +| loss | -0.061 | +| n_updates | 3132 | +| policy_gradient_loss | -0.0341 | +| value_loss | 0.000138 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.227 | +| time/ | | +| fps | 1322 | +| iterations | 785 | +| time_elapsed | 1215 | +| total_timesteps | 1607680 | +| train/ | | +| approx_kl | 0.044044495 | +| clip_fraction | 0.432 | +| clip_range | 0.13 | +| entropy_loss | -6.85 | +| explained_variance | 0.0209 | +| learning_rate | 0.000168 | +| loss | -0.036 | +| n_updates | 3136 | +| policy_gradient_loss | -0.0309 | +| value_loss | 0.000125 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.227 | +| time/ | | +| fps | 1322 | +| iterations | 786 | +| time_elapsed | 1217 | +| total_timesteps | 1609728 | +| train/ | | +| approx_kl | 0.03624419 | +| clip_fraction | 0.403 | +| clip_range | 0.13 | +| entropy_loss | -6.99 | +| explained_variance | -0.0199 | +| learning_rate | 0.000168 | +| loss | -0.0412 | +| n_updates | 3140 | +| policy_gradient_loss | -0.0297 | +| value_loss | 0.000291 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.223 | +| time/ | | +| fps | 1322 | +| iterations | 787 | +| time_elapsed | 1218 | +| total_timesteps | 1611776 | +| train/ | | +| approx_kl | 0.047828406 | +| clip_fraction | 0.415 | +| clip_range | 0.13 | +| entropy_loss | -7.11 | +| explained_variance | -0.37 | +| learning_rate | 0.000168 | +| loss | -0.0703 | +| n_updates | 3144 | +| policy_gradient_loss | -0.0409 | +| value_loss | 0.000122 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.222 | +| time/ | | +| fps | 1322 | +| iterations | 788 | +| time_elapsed | 1220 | +| total_timesteps | 1613824 | +| train/ | | +| approx_kl | 0.04289443 | +| clip_fraction | 0.393 | +| clip_range | 0.13 | +| entropy_loss | -6.95 | +| explained_variance | -0.177 | +| learning_rate | 0.000168 | +| loss | -0.0576 | +| n_updates | 3148 | +| policy_gradient_loss | -0.0347 | +| value_loss | 9.05e-05 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.213 | +| time/ | | +| fps | 1322 | +| iterations | 789 | +| time_elapsed | 1221 | +| total_timesteps | 1615872 | +| train/ | | +| approx_kl | 0.04731702 | +| clip_fraction | 0.393 | +| clip_range | 0.13 | +| entropy_loss | -6.9 | +| explained_variance | 0.00184 | +| learning_rate | 0.000168 | +| loss | -0.0514 | +| n_updates | 3152 | +| policy_gradient_loss | -0.036 | +| value_loss | 0.000278 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.215 | +| time/ | | +| fps | 1322 | +| iterations | 790 | +| time_elapsed | 1223 | +| total_timesteps | 1617920 | +| train/ | | +| approx_kl | 0.046311997 | +| clip_fraction | 0.391 | +| clip_range | 0.13 | +| entropy_loss | -6.95 | +| explained_variance | -0.155 | +| learning_rate | 0.000168 | +| loss | -0.0634 | +| n_updates | 3156 | +| policy_gradient_loss | -0.0376 | +| value_loss | 0.00017 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.219 | +| time/ | | +| fps | 1322 | +| iterations | 791 | +| time_elapsed | 1224 | +| total_timesteps | 1619968 | +| train/ | | +| approx_kl | 0.04452707 | +| clip_fraction | 0.406 | +| clip_range | 0.13 | +| entropy_loss | -6.98 | +| explained_variance | -0.103 | +| learning_rate | 0.000168 | +| loss | -0.0638 | +| n_updates | 3160 | +| policy_gradient_loss | -0.036 | +| value_loss | 0.000121 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.221 | +| time/ | | +| fps | 1322 | +| iterations | 792 | +| time_elapsed | 1226 | +| total_timesteps | 1622016 | +| train/ | | +| approx_kl | 0.044966433 | +| clip_fraction | 0.398 | +| clip_range | 0.13 | +| entropy_loss | -6.99 | +| explained_variance | -0.128 | +| learning_rate | 0.000168 | +| loss | -0.0583 | +| n_updates | 3164 | +| policy_gradient_loss | -0.0335 | +| value_loss | 0.000238 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.221 | +| time/ | | +| fps | 1322 | +| iterations | 793 | +| time_elapsed | 1228 | +| total_timesteps | 1624064 | +| train/ | | +| approx_kl | 0.039988913 | +| clip_fraction | 0.371 | +| clip_range | 0.13 | +| entropy_loss | -7.02 | +| explained_variance | -0.097 | +| learning_rate | 0.000168 | +| loss | -0.0447 | +| n_updates | 3168 | +| policy_gradient_loss | -0.0298 | +| value_loss | 0.000219 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.222 | +| time/ | | +| fps | 1322 | +| iterations | 794 | +| time_elapsed | 1229 | +| total_timesteps | 1626112 | +| train/ | | +| approx_kl | 0.037101787 | +| clip_fraction | 0.372 | +| clip_range | 0.13 | +| entropy_loss | -7 | +| explained_variance | -0.273 | +| learning_rate | 0.000168 | +| loss | -0.0565 | +| n_updates | 3172 | +| policy_gradient_loss | -0.0352 | +| value_loss | 0.000105 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.228 | +| time/ | | +| fps | 1322 | +| iterations | 795 | +| time_elapsed | 1231 | +| total_timesteps | 1628160 | +| train/ | | +| approx_kl | 0.042911503 | +| clip_fraction | 0.396 | +| clip_range | 0.13 | +| entropy_loss | -7.04 | +| explained_variance | -0.101 | +| learning_rate | 0.000168 | +| loss | -0.0536 | +| n_updates | 3176 | +| policy_gradient_loss | -0.03 | +| value_loss | 0.000179 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.228 | +| time/ | | +| fps | 1322 | +| iterations | 796 | +| time_elapsed | 1232 | +| total_timesteps | 1630208 | +| train/ | | +| approx_kl | 0.035551816 | +| clip_fraction | 0.375 | +| clip_range | 0.13 | +| entropy_loss | -7.17 | +| explained_variance | 0.00441 | +| learning_rate | 0.000168 | +| loss | -0.0352 | +| n_updates | 3180 | +| policy_gradient_loss | -0.0264 | +| value_loss | 0.000374 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.22 | +| time/ | | +| fps | 1322 | +| iterations | 797 | +| time_elapsed | 1234 | +| total_timesteps | 1632256 | +| train/ | | +| approx_kl | 0.038520537 | +| clip_fraction | 0.405 | +| clip_range | 0.13 | +| entropy_loss | -7.11 | +| explained_variance | -0.374 | +| learning_rate | 0.000168 | +| loss | -0.071 | +| n_updates | 3184 | +| policy_gradient_loss | -0.0427 | +| value_loss | 9.74e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.214 | +| time/ | | +| fps | 1322 | +| iterations | 798 | +| time_elapsed | 1235 | +| total_timesteps | 1634304 | +| train/ | | +| approx_kl | 0.03664695 | +| clip_fraction | 0.383 | +| clip_range | 0.13 | +| entropy_loss | -7.01 | +| explained_variance | -0.0371 | +| learning_rate | 0.000168 | +| loss | -0.0715 | +| n_updates | 3188 | +| policy_gradient_loss | -0.0383 | +| value_loss | 0.000139 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.214 | +| time/ | | +| fps | 1322 | +| iterations | 799 | +| time_elapsed | 1237 | +| total_timesteps | 1636352 | +| train/ | | +| approx_kl | 0.038891125 | +| clip_fraction | 0.393 | +| clip_range | 0.13 | +| entropy_loss | -7.02 | +| explained_variance | 0.0232 | +| learning_rate | 0.000168 | +| loss | -0.0672 | +| n_updates | 3192 | +| policy_gradient_loss | -0.0386 | +| value_loss | 0.000127 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.217 | +| time/ | | +| fps | 1322 | +| iterations | 800 | +| time_elapsed | 1238 | +| total_timesteps | 1638400 | +| train/ | | +| approx_kl | 0.03610341 | +| clip_fraction | 0.38 | +| clip_range | 0.13 | +| entropy_loss | -7.1 | +| explained_variance | -0.0885 | +| learning_rate | 0.000168 | +| loss | -0.0482 | +| n_updates | 3196 | +| policy_gradient_loss | -0.0318 | +| value_loss | 0.000172 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.217 | +| time/ | | +| fps | 1322 | +| iterations | 801 | +| time_elapsed | 1240 | +| total_timesteps | 1640448 | +| train/ | | +| approx_kl | 0.03549575 | +| clip_fraction | 0.391 | +| clip_range | 0.13 | +| entropy_loss | -7.11 | +| explained_variance | -0.00424 | +| learning_rate | 0.000168 | +| loss | -0.0612 | +| n_updates | 3200 | +| policy_gradient_loss | -0.0362 | +| value_loss | 0.000106 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.214 | +| time/ | | +| fps | 1322 | +| iterations | 802 | +| time_elapsed | 1241 | +| total_timesteps | 1642496 | +| train/ | | +| approx_kl | 0.029660398 | +| clip_fraction | 0.369 | +| clip_range | 0.129 | +| entropy_loss | -7.11 | +| explained_variance | -0.131 | +| learning_rate | 0.000168 | +| loss | -0.0575 | +| n_updates | 3204 | +| policy_gradient_loss | -0.0348 | +| value_loss | 0.000134 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.208 | +| time/ | | +| fps | 1322 | +| iterations | 803 | +| time_elapsed | 1243 | +| total_timesteps | 1644544 | +| train/ | | +| approx_kl | 0.029347803 | +| clip_fraction | 0.365 | +| clip_range | 0.129 | +| entropy_loss | -7.06 | +| explained_variance | -0.105 | +| learning_rate | 0.000167 | +| loss | -0.0469 | +| n_updates | 3208 | +| policy_gradient_loss | -0.0286 | +| value_loss | 0.000138 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.208 | +| time/ | | +| fps | 1322 | +| iterations | 804 | +| time_elapsed | 1245 | +| total_timesteps | 1646592 | +| train/ | | +| approx_kl | 0.03008483 | +| clip_fraction | 0.36 | +| clip_range | 0.129 | +| entropy_loss | -7.03 | +| explained_variance | -0.0124 | +| learning_rate | 0.000167 | +| loss | -0.0484 | +| n_updates | 3212 | +| policy_gradient_loss | -0.0313 | +| value_loss | 0.000145 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.208 | +| time/ | | +| fps | 1322 | +| iterations | 805 | +| time_elapsed | 1246 | +| total_timesteps | 1648640 | +| train/ | | +| approx_kl | 0.032512695 | +| clip_fraction | 0.372 | +| clip_range | 0.129 | +| entropy_loss | -7.13 | +| explained_variance | 0.0205 | +| learning_rate | 0.000167 | +| loss | -0.0584 | +| n_updates | 3216 | +| policy_gradient_loss | -0.0301 | +| value_loss | 0.000158 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.212 | +| time/ | | +| fps | 1322 | +| iterations | 806 | +| time_elapsed | 1248 | +| total_timesteps | 1650688 | +| train/ | | +| approx_kl | 0.035581715 | +| clip_fraction | 0.359 | +| clip_range | 0.129 | +| entropy_loss | -7.14 | +| explained_variance | -0.044 | +| learning_rate | 0.000167 | +| loss | -0.0383 | +| n_updates | 3220 | +| policy_gradient_loss | -0.0294 | +| value_loss | 0.000152 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.202 | +| time/ | | +| fps | 1322 | +| iterations | 807 | +| time_elapsed | 1249 | +| total_timesteps | 1652736 | +| train/ | | +| approx_kl | 0.035330616 | +| clip_fraction | 0.362 | +| clip_range | 0.129 | +| entropy_loss | -7.24 | +| explained_variance | -0.00626 | +| learning_rate | 0.000167 | +| loss | -0.0531 | +| n_updates | 3224 | +| policy_gradient_loss | -0.0324 | +| value_loss | 0.000121 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.202 | +| time/ | | +| fps | 1322 | +| iterations | 808 | +| time_elapsed | 1251 | +| total_timesteps | 1654784 | +| train/ | | +| approx_kl | 0.0320345 | +| clip_fraction | 0.354 | +| clip_range | 0.129 | +| entropy_loss | -7.19 | +| explained_variance | -0.168 | +| learning_rate | 0.000167 | +| loss | -0.0402 | +| n_updates | 3228 | +| policy_gradient_loss | -0.0299 | +| value_loss | 0.000129 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.211 | +| time/ | | +| fps | 1322 | +| iterations | 809 | +| time_elapsed | 1252 | +| total_timesteps | 1656832 | +| train/ | | +| approx_kl | 0.0401486 | +| clip_fraction | 0.36 | +| clip_range | 0.129 | +| entropy_loss | -7.29 | +| explained_variance | -0.125 | +| learning_rate | 0.000167 | +| loss | -0.0679 | +| n_updates | 3232 | +| policy_gradient_loss | -0.0374 | +| value_loss | 9.51e-05 | +--------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.211 | +| time/ | | +| fps | 1322 | +| iterations | 810 | +| time_elapsed | 1254 | +| total_timesteps | 1658880 | +| train/ | | +| approx_kl | 0.03350667 | +| clip_fraction | 0.368 | +| clip_range | 0.129 | +| entropy_loss | -7.13 | +| explained_variance | -0.205 | +| learning_rate | 0.000167 | +| loss | -0.0519 | +| n_updates | 3236 | +| policy_gradient_loss | -0.0347 | +| value_loss | 0.000113 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.211 | +| time/ | | +| fps | 1322 | +| iterations | 811 | +| time_elapsed | 1255 | +| total_timesteps | 1660928 | +| train/ | | +| approx_kl | 0.03583522 | +| clip_fraction | 0.361 | +| clip_range | 0.129 | +| entropy_loss | -7.17 | +| explained_variance | 0.0208 | +| learning_rate | 0.000167 | +| loss | -0.0647 | +| n_updates | 3240 | +| policy_gradient_loss | -0.034 | +| value_loss | 0.000157 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.205 | +| time/ | | +| fps | 1322 | +| iterations | 812 | +| time_elapsed | 1257 | +| total_timesteps | 1662976 | +| train/ | | +| approx_kl | 0.03761833 | +| clip_fraction | 0.382 | +| clip_range | 0.129 | +| entropy_loss | -7.12 | +| explained_variance | -0.212 | +| learning_rate | 0.000167 | +| loss | -0.0553 | +| n_updates | 3244 | +| policy_gradient_loss | -0.0311 | +| value_loss | 0.000197 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.205 | +| time/ | | +| fps | 1322 | +| iterations | 813 | +| time_elapsed | 1258 | +| total_timesteps | 1665024 | +| train/ | | +| approx_kl | 0.035176784 | +| clip_fraction | 0.365 | +| clip_range | 0.129 | +| entropy_loss | -7.21 | +| explained_variance | -0.0793 | +| learning_rate | 0.000167 | +| loss | -0.0599 | +| n_updates | 3248 | +| policy_gradient_loss | -0.0315 | +| value_loss | 0.000202 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.206 | +| time/ | | +| fps | 1322 | +| iterations | 814 | +| time_elapsed | 1260 | +| total_timesteps | 1667072 | +| train/ | | +| approx_kl | 0.032037284 | +| clip_fraction | 0.389 | +| clip_range | 0.129 | +| entropy_loss | -7.17 | +| explained_variance | -0.239 | +| learning_rate | 0.000167 | +| loss | -0.0657 | +| n_updates | 3252 | +| policy_gradient_loss | -0.0394 | +| value_loss | 7.17e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.204 | +| time/ | | +| fps | 1322 | +| iterations | 815 | +| time_elapsed | 1261 | +| total_timesteps | 1669120 | +| train/ | | +| approx_kl | 0.031831004 | +| clip_fraction | 0.337 | +| clip_range | 0.129 | +| entropy_loss | -7.18 | +| explained_variance | -0.0823 | +| learning_rate | 0.000167 | +| loss | -0.0562 | +| n_updates | 3256 | +| policy_gradient_loss | -0.0311 | +| value_loss | 0.000177 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.206 | +| time/ | | +| fps | 1322 | +| iterations | 816 | +| time_elapsed | 1263 | +| total_timesteps | 1671168 | +| train/ | | +| approx_kl | 0.03471595 | +| clip_fraction | 0.363 | +| clip_range | 0.129 | +| entropy_loss | -7.09 | +| explained_variance | -0.126 | +| learning_rate | 0.000167 | +| loss | -0.0579 | +| n_updates | 3260 | +| policy_gradient_loss | -0.0345 | +| value_loss | 0.000157 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.203 | +| time/ | | +| fps | 1322 | +| iterations | 817 | +| time_elapsed | 1265 | +| total_timesteps | 1673216 | +| train/ | | +| approx_kl | 0.03576481 | +| clip_fraction | 0.36 | +| clip_range | 0.129 | +| entropy_loss | -7.13 | +| explained_variance | 0.0335 | +| learning_rate | 0.000167 | +| loss | -0.038 | +| n_updates | 3264 | +| policy_gradient_loss | -0.0276 | +| value_loss | 0.000214 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.2 | +| time/ | | +| fps | 1322 | +| iterations | 818 | +| time_elapsed | 1266 | +| total_timesteps | 1675264 | +| train/ | | +| approx_kl | 0.03833333 | +| clip_fraction | 0.382 | +| clip_range | 0.129 | +| entropy_loss | -7.31 | +| explained_variance | -0.098 | +| learning_rate | 0.000167 | +| loss | -0.0657 | +| n_updates | 3268 | +| policy_gradient_loss | -0.0369 | +| value_loss | 0.00013 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.2 | +| time/ | | +| fps | 1322 | +| iterations | 819 | +| time_elapsed | 1268 | +| total_timesteps | 1677312 | +| train/ | | +| approx_kl | 0.042191364 | +| clip_fraction | 0.386 | +| clip_range | 0.129 | +| entropy_loss | -7.18 | +| explained_variance | -0.37 | +| learning_rate | 0.000167 | +| loss | -0.0474 | +| n_updates | 3272 | +| policy_gradient_loss | -0.0361 | +| value_loss | 9.03e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.204 | +| time/ | | +| fps | 1322 | +| iterations | 820 | +| time_elapsed | 1269 | +| total_timesteps | 1679360 | +| train/ | | +| approx_kl | 0.039572738 | +| clip_fraction | 0.385 | +| clip_range | 0.129 | +| entropy_loss | -7.22 | +| explained_variance | -0.1 | +| learning_rate | 0.000167 | +| loss | -0.0712 | +| n_updates | 3276 | +| policy_gradient_loss | -0.0375 | +| value_loss | 0.000112 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.205 | +| time/ | | +| fps | 1322 | +| iterations | 821 | +| time_elapsed | 1271 | +| total_timesteps | 1681408 | +| train/ | | +| approx_kl | 0.03392162 | +| clip_fraction | 0.381 | +| clip_range | 0.129 | +| entropy_loss | -7.07 | +| explained_variance | -0.187 | +| learning_rate | 0.000167 | +| loss | -0.0546 | +| n_updates | 3280 | +| policy_gradient_loss | -0.0325 | +| value_loss | 0.000128 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.218 | +| time/ | | +| fps | 1322 | +| iterations | 822 | +| time_elapsed | 1272 | +| total_timesteps | 1683456 | +| train/ | | +| approx_kl | 0.039642096 | +| clip_fraction | 0.389 | +| clip_range | 0.129 | +| entropy_loss | -7.08 | +| explained_variance | 0.0222 | +| learning_rate | 0.000167 | +| loss | -0.0622 | +| n_updates | 3284 | +| policy_gradient_loss | -0.0358 | +| value_loss | 9.36e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.218 | +| time/ | | +| fps | 1322 | +| iterations | 823 | +| time_elapsed | 1274 | +| total_timesteps | 1685504 | +| train/ | | +| approx_kl | 0.039532457 | +| clip_fraction | 0.372 | +| clip_range | 0.129 | +| entropy_loss | -6.99 | +| explained_variance | -0.117 | +| learning_rate | 0.000167 | +| loss | -0.0581 | +| n_updates | 3288 | +| policy_gradient_loss | -0.0285 | +| value_loss | 0.000142 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.217 | +| time/ | | +| fps | 1322 | +| iterations | 824 | +| time_elapsed | 1275 | +| total_timesteps | 1687552 | +| train/ | | +| approx_kl | 0.0379181 | +| clip_fraction | 0.377 | +| clip_range | 0.129 | +| entropy_loss | -7.02 | +| explained_variance | -0.275 | +| learning_rate | 0.000167 | +| loss | -0.0611 | +| n_updates | 3292 | +| policy_gradient_loss | -0.0354 | +| value_loss | 0.000124 | +--------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.21 | +| time/ | | +| fps | 1322 | +| iterations | 825 | +| time_elapsed | 1277 | +| total_timesteps | 1689600 | +| train/ | | +| approx_kl | 0.04011246 | +| clip_fraction | 0.392 | +| clip_range | 0.129 | +| entropy_loss | -7.15 | +| explained_variance | -0.267 | +| learning_rate | 0.000167 | +| loss | -0.0665 | +| n_updates | 3296 | +| policy_gradient_loss | -0.0356 | +| value_loss | 6.9e-05 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.212 | +| time/ | | +| fps | 1322 | +| iterations | 826 | +| time_elapsed | 1278 | +| total_timesteps | 1691648 | +| train/ | | +| approx_kl | 0.03680706 | +| clip_fraction | 0.423 | +| clip_range | 0.129 | +| entropy_loss | -7.16 | +| explained_variance | -0.0627 | +| learning_rate | 0.000167 | +| loss | -0.0605 | +| n_updates | 3300 | +| policy_gradient_loss | -0.0308 | +| value_loss | 0.000127 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.208 | +| time/ | | +| fps | 1322 | +| iterations | 827 | +| time_elapsed | 1280 | +| total_timesteps | 1693696 | +| train/ | | +| approx_kl | 0.040547658 | +| clip_fraction | 0.384 | +| clip_range | 0.129 | +| entropy_loss | -7.06 | +| explained_variance | -0.234 | +| learning_rate | 0.000167 | +| loss | -0.0722 | +| n_updates | 3304 | +| policy_gradient_loss | -0.0346 | +| value_loss | 9.32e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.204 | +| time/ | | +| fps | 1322 | +| iterations | 828 | +| time_elapsed | 1282 | +| total_timesteps | 1695744 | +| train/ | | +| approx_kl | 0.038977247 | +| clip_fraction | 0.369 | +| clip_range | 0.129 | +| entropy_loss | -7.21 | +| explained_variance | -0.0576 | +| learning_rate | 0.000166 | +| loss | -0.0451 | +| n_updates | 3308 | +| policy_gradient_loss | -0.0284 | +| value_loss | 0.000223 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.206 | +| time/ | | +| fps | 1322 | +| iterations | 829 | +| time_elapsed | 1283 | +| total_timesteps | 1697792 | +| train/ | | +| approx_kl | 0.040493056 | +| clip_fraction | 0.398 | +| clip_range | 0.129 | +| entropy_loss | -7.28 | +| explained_variance | -0.182 | +| learning_rate | 0.000166 | +| loss | -0.0546 | +| n_updates | 3312 | +| policy_gradient_loss | -0.0342 | +| value_loss | 0.000147 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.201 | +| time/ | | +| fps | 1322 | +| iterations | 830 | +| time_elapsed | 1285 | +| total_timesteps | 1699840 | +| train/ | | +| approx_kl | 0.044069253 | +| clip_fraction | 0.387 | +| clip_range | 0.129 | +| entropy_loss | -7.14 | +| explained_variance | -0.0774 | +| learning_rate | 0.000166 | +| loss | -0.0492 | +| n_updates | 3316 | +| policy_gradient_loss | -0.0311 | +| value_loss | 0.000227 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.199 | +| time/ | | +| fps | 1322 | +| iterations | 831 | +| time_elapsed | 1286 | +| total_timesteps | 1701888 | +| train/ | | +| approx_kl | 0.04190205 | +| clip_fraction | 0.391 | +| clip_range | 0.129 | +| entropy_loss | -7.18 | +| explained_variance | -0.161 | +| learning_rate | 0.000166 | +| loss | -0.0778 | +| n_updates | 3320 | +| policy_gradient_loss | -0.0398 | +| value_loss | 0.000124 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.199 | +| time/ | | +| fps | 1322 | +| iterations | 832 | +| time_elapsed | 1288 | +| total_timesteps | 1703936 | +| train/ | | +| approx_kl | 0.05406306 | +| clip_fraction | 0.415 | +| clip_range | 0.129 | +| entropy_loss | -7.22 | +| explained_variance | -0.0193 | +| learning_rate | 0.000166 | +| loss | -0.0643 | +| n_updates | 3324 | +| policy_gradient_loss | -0.0363 | +| value_loss | 0.000152 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.189 | +| time/ | | +| fps | 1322 | +| iterations | 833 | +| time_elapsed | 1289 | +| total_timesteps | 1705984 | +| train/ | | +| approx_kl | 0.042136565 | +| clip_fraction | 0.407 | +| clip_range | 0.129 | +| entropy_loss | -7.12 | +| explained_variance | -0.199 | +| learning_rate | 0.000166 | +| loss | -0.0646 | +| n_updates | 3328 | +| policy_gradient_loss | -0.0352 | +| value_loss | 0.000183 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.189 | +| time/ | | +| fps | 1322 | +| iterations | 834 | +| time_elapsed | 1291 | +| total_timesteps | 1708032 | +| train/ | | +| approx_kl | 0.038508285 | +| clip_fraction | 0.414 | +| clip_range | 0.129 | +| entropy_loss | -7.08 | +| explained_variance | -0.441 | +| learning_rate | 0.000166 | +| loss | -0.0592 | +| n_updates | 3332 | +| policy_gradient_loss | -0.0388 | +| value_loss | 8.94e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.189 | +| time/ | | +| fps | 1322 | +| iterations | 835 | +| time_elapsed | 1292 | +| total_timesteps | 1710080 | +| train/ | | +| approx_kl | 0.04580328 | +| clip_fraction | 0.376 | +| clip_range | 0.129 | +| entropy_loss | -7.18 | +| explained_variance | -0.0919 | +| learning_rate | 0.000166 | +| loss | -0.0498 | +| n_updates | 3336 | +| policy_gradient_loss | -0.0331 | +| value_loss | 0.000219 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.196 | +| time/ | | +| fps | 1322 | +| iterations | 836 | +| time_elapsed | 1294 | +| total_timesteps | 1712128 | +| train/ | | +| approx_kl | 0.04487915 | +| clip_fraction | 0.403 | +| clip_range | 0.129 | +| entropy_loss | -7.25 | +| explained_variance | -0.058 | +| learning_rate | 0.000166 | +| loss | -0.0574 | +| n_updates | 3340 | +| policy_gradient_loss | -0.0378 | +| value_loss | 0.000147 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.194 | +| time/ | | +| fps | 1322 | +| iterations | 837 | +| time_elapsed | 1296 | +| total_timesteps | 1714176 | +| train/ | | +| approx_kl | 0.039976984 | +| clip_fraction | 0.391 | +| clip_range | 0.129 | +| entropy_loss | -7.01 | +| explained_variance | -0.123 | +| learning_rate | 0.000166 | +| loss | -0.0469 | +| n_updates | 3344 | +| policy_gradient_loss | -0.0347 | +| value_loss | 0.000137 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.19 | +| time/ | | +| fps | 1322 | +| iterations | 838 | +| time_elapsed | 1297 | +| total_timesteps | 1716224 | +| train/ | | +| approx_kl | 0.040992297 | +| clip_fraction | 0.404 | +| clip_range | 0.129 | +| entropy_loss | -6.93 | +| explained_variance | -0.0305 | +| learning_rate | 0.000166 | +| loss | -0.0522 | +| n_updates | 3348 | +| policy_gradient_loss | -0.0326 | +| value_loss | 0.000268 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.191 | +| time/ | | +| fps | 1322 | +| iterations | 839 | +| time_elapsed | 1299 | +| total_timesteps | 1718272 | +| train/ | | +| approx_kl | 0.037099816 | +| clip_fraction | 0.382 | +| clip_range | 0.129 | +| entropy_loss | -7.05 | +| explained_variance | -0.235 | +| learning_rate | 0.000166 | +| loss | -0.0627 | +| n_updates | 3352 | +| policy_gradient_loss | -0.0358 | +| value_loss | 0.00016 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.191 | +| time/ | | +| fps | 1322 | +| iterations | 840 | +| time_elapsed | 1300 | +| total_timesteps | 1720320 | +| train/ | | +| approx_kl | 0.043203168 | +| clip_fraction | 0.398 | +| clip_range | 0.129 | +| entropy_loss | -6.99 | +| explained_variance | -0.136 | +| learning_rate | 0.000166 | +| loss | -0.0562 | +| n_updates | 3356 | +| policy_gradient_loss | -0.0352 | +| value_loss | 0.000134 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.198 | +| time/ | | +| fps | 1322 | +| iterations | 841 | +| time_elapsed | 1302 | +| total_timesteps | 1722368 | +| train/ | | +| approx_kl | 0.036539763 | +| clip_fraction | 0.397 | +| clip_range | 0.128 | +| entropy_loss | -7.04 | +| explained_variance | -0.243 | +| learning_rate | 0.000166 | +| loss | -0.0629 | +| n_updates | 3360 | +| policy_gradient_loss | -0.0412 | +| value_loss | 5.82e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.198 | +| time/ | | +| fps | 1322 | +| iterations | 842 | +| time_elapsed | 1304 | +| total_timesteps | 1724416 | +| train/ | | +| approx_kl | 0.03609117 | +| clip_fraction | 0.394 | +| clip_range | 0.128 | +| entropy_loss | -7.21 | +| explained_variance | -0.0719 | +| learning_rate | 0.000166 | +| loss | -0.0399 | +| n_updates | 3364 | +| policy_gradient_loss | -0.0324 | +| value_loss | 0.000166 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.189 | +| time/ | | +| fps | 1322 | +| iterations | 843 | +| time_elapsed | 1305 | +| total_timesteps | 1726464 | +| train/ | | +| approx_kl | 0.042702176 | +| clip_fraction | 0.378 | +| clip_range | 0.128 | +| entropy_loss | -7.3 | +| explained_variance | -0.0523 | +| learning_rate | 0.000166 | +| loss | -0.0529 | +| n_updates | 3368 | +| policy_gradient_loss | -0.0308 | +| value_loss | 0.00019 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.194 | +| time/ | | +| fps | 1322 | +| iterations | 844 | +| time_elapsed | 1307 | +| total_timesteps | 1728512 | +| train/ | | +| approx_kl | 0.039029352 | +| clip_fraction | 0.38 | +| clip_range | 0.128 | +| entropy_loss | -7.19 | +| explained_variance | -0.297 | +| learning_rate | 0.000166 | +| loss | -0.0519 | +| n_updates | 3372 | +| policy_gradient_loss | -0.0314 | +| value_loss | 0.000139 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.193 | +| time/ | | +| fps | 1322 | +| iterations | 845 | +| time_elapsed | 1308 | +| total_timesteps | 1730560 | +| train/ | | +| approx_kl | 0.036789354 | +| clip_fraction | 0.364 | +| clip_range | 0.128 | +| entropy_loss | -7.29 | +| explained_variance | -0.0255 | +| learning_rate | 0.000166 | +| loss | -0.0544 | +| n_updates | 3376 | +| policy_gradient_loss | -0.0326 | +| value_loss | 0.000198 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.201 | +| time/ | | +| fps | 1322 | +| iterations | 846 | +| time_elapsed | 1310 | +| total_timesteps | 1732608 | +| train/ | | +| approx_kl | 0.035556983 | +| clip_fraction | 0.355 | +| clip_range | 0.128 | +| entropy_loss | -7.35 | +| explained_variance | -0.133 | +| learning_rate | 0.000166 | +| loss | -0.0516 | +| n_updates | 3380 | +| policy_gradient_loss | -0.0298 | +| value_loss | 0.000269 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.203 | +| time/ | | +| fps | 1322 | +| iterations | 847 | +| time_elapsed | 1311 | +| total_timesteps | 1734656 | +| train/ | | +| approx_kl | 0.04076115 | +| clip_fraction | 0.39 | +| clip_range | 0.128 | +| entropy_loss | -7.3 | +| explained_variance | -0.147 | +| learning_rate | 0.000166 | +| loss | -0.0568 | +| n_updates | 3384 | +| policy_gradient_loss | -0.0355 | +| value_loss | 0.000154 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.196 | +| time/ | | +| fps | 1322 | +| iterations | 848 | +| time_elapsed | 1313 | +| total_timesteps | 1736704 | +| train/ | | +| approx_kl | 0.038683668 | +| clip_fraction | 0.36 | +| clip_range | 0.128 | +| entropy_loss | -7.08 | +| explained_variance | -0.494 | +| learning_rate | 0.000166 | +| loss | -0.0567 | +| n_updates | 3388 | +| policy_gradient_loss | -0.0372 | +| value_loss | 8.51e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.196 | +| time/ | | +| fps | 1322 | +| iterations | 849 | +| time_elapsed | 1314 | +| total_timesteps | 1738752 | +| train/ | | +| approx_kl | 0.04073832 | +| clip_fraction | 0.379 | +| clip_range | 0.128 | +| entropy_loss | -7.22 | +| explained_variance | -0.00634 | +| learning_rate | 0.000166 | +| loss | -0.0417 | +| n_updates | 3392 | +| policy_gradient_loss | -0.0285 | +| value_loss | 0.000251 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.196 | +| time/ | | +| fps | 1322 | +| iterations | 850 | +| time_elapsed | 1316 | +| total_timesteps | 1740800 | +| train/ | | +| approx_kl | 0.04804245 | +| clip_fraction | 0.406 | +| clip_range | 0.128 | +| entropy_loss | -7.26 | +| explained_variance | -0.158 | +| learning_rate | 0.000166 | +| loss | -0.0611 | +| n_updates | 3396 | +| policy_gradient_loss | -0.0364 | +| value_loss | 0.000112 | +---------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.196 | +| time/ | | +| fps | 1322 | +| iterations | 851 | +| time_elapsed | 1318 | +| total_timesteps | 1742848 | +| train/ | | +| approx_kl | 0.0380096 | +| clip_fraction | 0.396 | +| clip_range | 0.128 | +| entropy_loss | -7.22 | +| explained_variance | -0.0867 | +| learning_rate | 0.000166 | +| loss | -0.0625 | +| n_updates | 3400 | +| policy_gradient_loss | -0.0354 | +| value_loss | 0.000143 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.207 | +| time/ | | +| fps | 1322 | +| iterations | 852 | +| time_elapsed | 1319 | +| total_timesteps | 1744896 | +| train/ | | +| approx_kl | 0.034648824 | +| clip_fraction | 0.37 | +| clip_range | 0.128 | +| entropy_loss | -7.26 | +| explained_variance | -0.0815 | +| learning_rate | 0.000165 | +| loss | -0.0622 | +| n_updates | 3404 | +| policy_gradient_loss | -0.0326 | +| value_loss | 0.000125 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.202 | +| time/ | | +| fps | 1322 | +| iterations | 853 | +| time_elapsed | 1321 | +| total_timesteps | 1746944 | +| train/ | | +| approx_kl | 0.032105293 | +| clip_fraction | 0.364 | +| clip_range | 0.128 | +| entropy_loss | -7.19 | +| explained_variance | -0.0503 | +| learning_rate | 0.000165 | +| loss | -0.0378 | +| n_updates | 3408 | +| policy_gradient_loss | -0.0311 | +| value_loss | 0.000256 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.199 | +| time/ | | +| fps | 1322 | +| iterations | 854 | +| time_elapsed | 1322 | +| total_timesteps | 1748992 | +| train/ | | +| approx_kl | 0.039154287 | +| clip_fraction | 0.386 | +| clip_range | 0.128 | +| entropy_loss | -7.16 | +| explained_variance | -0.156 | +| learning_rate | 0.000165 | +| loss | -0.0613 | +| n_updates | 3412 | +| policy_gradient_loss | -0.0379 | +| value_loss | 0.000164 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.193 | +| time/ | | +| fps | 1322 | +| iterations | 855 | +| time_elapsed | 1324 | +| total_timesteps | 1751040 | +| train/ | | +| approx_kl | 0.043230504 | +| clip_fraction | 0.366 | +| clip_range | 0.128 | +| entropy_loss | -7.18 | +| explained_variance | -0.273 | +| learning_rate | 0.000165 | +| loss | -0.0675 | +| n_updates | 3416 | +| policy_gradient_loss | -0.0366 | +| value_loss | 0.000118 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.193 | +| time/ | | +| fps | 1322 | +| iterations | 856 | +| time_elapsed | 1325 | +| total_timesteps | 1753088 | +| train/ | | +| approx_kl | 0.048750225 | +| clip_fraction | 0.38 | +| clip_range | 0.128 | +| entropy_loss | -7.2 | +| explained_variance | -0.0368 | +| learning_rate | 0.000165 | +| loss | -0.0599 | +| n_updates | 3420 | +| policy_gradient_loss | -0.0354 | +| value_loss | 0.000162 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.193 | +| time/ | | +| fps | 1322 | +| iterations | 857 | +| time_elapsed | 1327 | +| total_timesteps | 1755136 | +| train/ | | +| approx_kl | 0.037096594 | +| clip_fraction | 0.374 | +| clip_range | 0.128 | +| entropy_loss | -7.29 | +| explained_variance | -0.103 | +| learning_rate | 0.000165 | +| loss | -0.048 | +| n_updates | 3424 | +| policy_gradient_loss | -0.033 | +| value_loss | 0.000157 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.186 | +| time/ | | +| fps | 1322 | +| iterations | 858 | +| time_elapsed | 1328 | +| total_timesteps | 1757184 | +| train/ | | +| approx_kl | 0.035757877 | +| clip_fraction | 0.379 | +| clip_range | 0.128 | +| entropy_loss | -7.25 | +| explained_variance | -0.0324 | +| learning_rate | 0.000165 | +| loss | -0.055 | +| n_updates | 3428 | +| policy_gradient_loss | -0.0333 | +| value_loss | 0.000108 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.187 | +| time/ | | +| fps | 1322 | +| iterations | 859 | +| time_elapsed | 1330 | +| total_timesteps | 1759232 | +| train/ | | +| approx_kl | 0.040026806 | +| clip_fraction | 0.377 | +| clip_range | 0.128 | +| entropy_loss | -7.31 | +| explained_variance | -0.162 | +| learning_rate | 0.000165 | +| loss | -0.0511 | +| n_updates | 3432 | +| policy_gradient_loss | -0.0333 | +| value_loss | 0.000156 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.185 | +| time/ | | +| fps | 1322 | +| iterations | 860 | +| time_elapsed | 1331 | +| total_timesteps | 1761280 | +| train/ | | +| approx_kl | 0.03707744 | +| clip_fraction | 0.352 | +| clip_range | 0.128 | +| entropy_loss | -7.31 | +| explained_variance | -0.0923 | +| learning_rate | 0.000165 | +| loss | -0.0513 | +| n_updates | 3436 | +| policy_gradient_loss | -0.0291 | +| value_loss | 0.00018 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.185 | +| time/ | | +| fps | 1322 | +| iterations | 861 | +| time_elapsed | 1333 | +| total_timesteps | 1763328 | +| train/ | | +| approx_kl | 0.03715331 | +| clip_fraction | 0.38 | +| clip_range | 0.128 | +| entropy_loss | -7.43 | +| explained_variance | -0.0215 | +| learning_rate | 0.000165 | +| loss | -0.0577 | +| n_updates | 3440 | +| policy_gradient_loss | -0.0352 | +| value_loss | 0.000182 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.189 | +| time/ | | +| fps | 1322 | +| iterations | 862 | +| time_elapsed | 1334 | +| total_timesteps | 1765376 | +| train/ | | +| approx_kl | 0.035260435 | +| clip_fraction | 0.396 | +| clip_range | 0.128 | +| entropy_loss | -7.28 | +| explained_variance | -0.537 | +| learning_rate | 0.000165 | +| loss | -0.0667 | +| n_updates | 3444 | +| policy_gradient_loss | -0.043 | +| value_loss | 4.81e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.197 | +| time/ | | +| fps | 1322 | +| iterations | 863 | +| time_elapsed | 1336 | +| total_timesteps | 1767424 | +| train/ | | +| approx_kl | 0.03359069 | +| clip_fraction | 0.359 | +| clip_range | 0.128 | +| entropy_loss | -7.24 | +| explained_variance | -0.0687 | +| learning_rate | 0.000165 | +| loss | -0.0564 | +| n_updates | 3448 | +| policy_gradient_loss | -0.0286 | +| value_loss | 0.000187 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.201 | +| time/ | | +| fps | 1322 | +| iterations | 864 | +| time_elapsed | 1338 | +| total_timesteps | 1769472 | +| train/ | | +| approx_kl | 0.045076746 | +| clip_fraction | 0.374 | +| clip_range | 0.128 | +| entropy_loss | -7.33 | +| explained_variance | -0.209 | +| learning_rate | 0.000165 | +| loss | -0.0504 | +| n_updates | 3452 | +| policy_gradient_loss | -0.0347 | +| value_loss | 0.000152 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.203 | +| time/ | | +| fps | 1322 | +| iterations | 865 | +| time_elapsed | 1339 | +| total_timesteps | 1771520 | +| train/ | | +| approx_kl | 0.035096332 | +| clip_fraction | 0.346 | +| clip_range | 0.128 | +| entropy_loss | -7.28 | +| explained_variance | 0.0538 | +| learning_rate | 0.000165 | +| loss | -0.0657 | +| n_updates | 3456 | +| policy_gradient_loss | -0.0357 | +| value_loss | 0.000156 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.203 | +| time/ | | +| fps | 1322 | +| iterations | 866 | +| time_elapsed | 1341 | +| total_timesteps | 1773568 | +| train/ | | +| approx_kl | 0.035679378 | +| clip_fraction | 0.372 | +| clip_range | 0.128 | +| entropy_loss | -7.24 | +| explained_variance | 0.0132 | +| learning_rate | 0.000165 | +| loss | -0.0675 | +| n_updates | 3460 | +| policy_gradient_loss | -0.0348 | +| value_loss | 0.000156 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.214 | +| time/ | | +| fps | 1322 | +| iterations | 867 | +| time_elapsed | 1342 | +| total_timesteps | 1775616 | +| train/ | | +| approx_kl | 0.037141725 | +| clip_fraction | 0.381 | +| clip_range | 0.128 | +| entropy_loss | -7.28 | +| explained_variance | -0.266 | +| learning_rate | 0.000165 | +| loss | -0.0537 | +| n_updates | 3464 | +| policy_gradient_loss | -0.0296 | +| value_loss | 0.000181 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.211 | +| time/ | | +| fps | 1322 | +| iterations | 868 | +| time_elapsed | 1344 | +| total_timesteps | 1777664 | +| train/ | | +| approx_kl | 0.039801918 | +| clip_fraction | 0.37 | +| clip_range | 0.128 | +| entropy_loss | -7.28 | +| explained_variance | -0.0908 | +| learning_rate | 0.000165 | +| loss | -0.0586 | +| n_updates | 3468 | +| policy_gradient_loss | -0.0345 | +| value_loss | 0.000141 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.211 | +| time/ | | +| fps | 1322 | +| iterations | 869 | +| time_elapsed | 1345 | +| total_timesteps | 1779712 | +| train/ | | +| approx_kl | 0.039879974 | +| clip_fraction | 0.373 | +| clip_range | 0.128 | +| entropy_loss | -7.24 | +| explained_variance | -0.0528 | +| learning_rate | 0.000165 | +| loss | -0.0494 | +| n_updates | 3472 | +| policy_gradient_loss | -0.038 | +| value_loss | 9.84e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.208 | +| time/ | | +| fps | 1322 | +| iterations | 870 | +| time_elapsed | 1347 | +| total_timesteps | 1781760 | +| train/ | | +| approx_kl | 0.034660116 | +| clip_fraction | 0.387 | +| clip_range | 0.128 | +| entropy_loss | -7.4 | +| explained_variance | -0.124 | +| learning_rate | 0.000165 | +| loss | -0.0508 | +| n_updates | 3476 | +| policy_gradient_loss | -0.0315 | +| value_loss | 0.000151 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.212 | +| time/ | | +| fps | 1322 | +| iterations | 871 | +| time_elapsed | 1348 | +| total_timesteps | 1783808 | +| train/ | | +| approx_kl | 0.035822824 | +| clip_fraction | 0.371 | +| clip_range | 0.128 | +| entropy_loss | -7.35 | +| explained_variance | -0.193 | +| learning_rate | 0.000165 | +| loss | -0.047 | +| n_updates | 3480 | +| policy_gradient_loss | -0.0304 | +| value_loss | 0.000134 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.213 | +| time/ | | +| fps | 1322 | +| iterations | 872 | +| time_elapsed | 1350 | +| total_timesteps | 1785856 | +| train/ | | +| approx_kl | 0.03229304 | +| clip_fraction | 0.356 | +| clip_range | 0.128 | +| entropy_loss | -7.3 | +| explained_variance | -0.0465 | +| learning_rate | 0.000165 | +| loss | -0.0576 | +| n_updates | 3484 | +| policy_gradient_loss | -0.0293 | +| value_loss | 0.000158 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.213 | +| time/ | | +| fps | 1322 | +| iterations | 873 | +| time_elapsed | 1351 | +| total_timesteps | 1787904 | +| train/ | | +| approx_kl | 0.029607717 | +| clip_fraction | 0.343 | +| clip_range | 0.128 | +| entropy_loss | -7.47 | +| explained_variance | -0.287 | +| learning_rate | 0.000165 | +| loss | -0.0364 | +| n_updates | 3488 | +| policy_gradient_loss | -0.0324 | +| value_loss | 0.00016 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.211 | +| time/ | | +| fps | 1322 | +| iterations | 874 | +| time_elapsed | 1353 | +| total_timesteps | 1789952 | +| train/ | | +| approx_kl | 0.0384626 | +| clip_fraction | 0.351 | +| clip_range | 0.128 | +| entropy_loss | -7.36 | +| explained_variance | -0.0325 | +| learning_rate | 0.000165 | +| loss | -0.0557 | +| n_updates | 3492 | +| policy_gradient_loss | -0.03 | +| value_loss | 0.000143 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.214 | +| time/ | | +| fps | 1322 | +| iterations | 875 | +| time_elapsed | 1354 | +| total_timesteps | 1792000 | +| train/ | | +| approx_kl | 0.036849618 | +| clip_fraction | 0.387 | +| clip_range | 0.128 | +| entropy_loss | -7.24 | +| explained_variance | -0.14 | +| learning_rate | 0.000165 | +| loss | -0.0531 | +| n_updates | 3496 | +| policy_gradient_loss | -0.0305 | +| value_loss | 0.000153 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.214 | +| time/ | | +| fps | 1322 | +| iterations | 876 | +| time_elapsed | 1356 | +| total_timesteps | 1794048 | +| train/ | | +| approx_kl | 0.036534823 | +| clip_fraction | 0.392 | +| clip_range | 0.128 | +| entropy_loss | -7.44 | +| explained_variance | -0.106 | +| learning_rate | 0.000165 | +| loss | -0.0468 | +| n_updates | 3500 | +| policy_gradient_loss | -0.033 | +| value_loss | 0.000181 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.219 | +| time/ | | +| fps | 1322 | +| iterations | 877 | +| time_elapsed | 1358 | +| total_timesteps | 1796096 | +| train/ | | +| approx_kl | 0.04018728 | +| clip_fraction | 0.38 | +| clip_range | 0.128 | +| entropy_loss | -7.37 | +| explained_variance | -0.244 | +| learning_rate | 0.000164 | +| loss | -0.0668 | +| n_updates | 3504 | +| policy_gradient_loss | -0.0385 | +| value_loss | 9.3e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.219 | +| time/ | | +| fps | 1322 | +| iterations | 878 | +| time_elapsed | 1359 | +| total_timesteps | 1798144 | +| train/ | | +| approx_kl | 0.042329885 | +| clip_fraction | 0.366 | +| clip_range | 0.128 | +| entropy_loss | -7.36 | +| explained_variance | -0.105 | +| learning_rate | 0.000164 | +| loss | -0.057 | +| n_updates | 3508 | +| policy_gradient_loss | -0.0324 | +| value_loss | 0.000159 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.219 | +| time/ | | +| fps | 1322 | +| iterations | 879 | +| time_elapsed | 1361 | +| total_timesteps | 1800192 | +| train/ | | +| approx_kl | 0.040926576 | +| clip_fraction | 0.402 | +| clip_range | 0.128 | +| entropy_loss | -7.33 | +| explained_variance | -0.00405 | +| learning_rate | 0.000164 | +| loss | -0.0581 | +| n_updates | 3512 | +| policy_gradient_loss | -0.0355 | +| value_loss | 0.000137 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.215 | +| time/ | | +| fps | 1322 | +| iterations | 880 | +| time_elapsed | 1362 | +| total_timesteps | 1802240 | +| train/ | | +| approx_kl | 0.039375857 | +| clip_fraction | 0.387 | +| clip_range | 0.127 | +| entropy_loss | -7.36 | +| explained_variance | -0.128 | +| learning_rate | 0.000164 | +| loss | -0.057 | +| n_updates | 3516 | +| policy_gradient_loss | -0.0371 | +| value_loss | 0.000118 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.208 | +| time/ | | +| fps | 1322 | +| iterations | 881 | +| time_elapsed | 1364 | +| total_timesteps | 1804288 | +| train/ | | +| approx_kl | 0.031821504 | +| clip_fraction | 0.38 | +| clip_range | 0.127 | +| entropy_loss | -7.32 | +| explained_variance | -0.0602 | +| learning_rate | 0.000164 | +| loss | -0.0556 | +| n_updates | 3520 | +| policy_gradient_loss | -0.0304 | +| value_loss | 0.000133 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.213 | +| time/ | | +| fps | 1322 | +| iterations | 882 | +| time_elapsed | 1365 | +| total_timesteps | 1806336 | +| train/ | | +| approx_kl | 0.035168123 | +| clip_fraction | 0.349 | +| clip_range | 0.127 | +| entropy_loss | -7.38 | +| explained_variance | -0.102 | +| learning_rate | 0.000164 | +| loss | -0.0539 | +| n_updates | 3524 | +| policy_gradient_loss | -0.0292 | +| value_loss | 0.000141 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.213 | +| time/ | | +| fps | 1322 | +| iterations | 883 | +| time_elapsed | 1367 | +| total_timesteps | 1808384 | +| train/ | | +| approx_kl | 0.04129777 | +| clip_fraction | 0.36 | +| clip_range | 0.127 | +| entropy_loss | -7.3 | +| explained_variance | 0.0141 | +| learning_rate | 0.000164 | +| loss | -0.0512 | +| n_updates | 3528 | +| policy_gradient_loss | -0.0344 | +| value_loss | 0.000231 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.213 | +| time/ | | +| fps | 1322 | +| iterations | 884 | +| time_elapsed | 1369 | +| total_timesteps | 1810432 | +| train/ | | +| approx_kl | 0.032273255 | +| clip_fraction | 0.377 | +| clip_range | 0.127 | +| entropy_loss | -7.25 | +| explained_variance | -0.02 | +| learning_rate | 0.000164 | +| loss | -0.053 | +| n_updates | 3532 | +| policy_gradient_loss | -0.033 | +| value_loss | 0.000184 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.211 | +| time/ | | +| fps | 1322 | +| iterations | 885 | +| time_elapsed | 1370 | +| total_timesteps | 1812480 | +| train/ | | +| approx_kl | 0.039251424 | +| clip_fraction | 0.372 | +| clip_range | 0.127 | +| entropy_loss | -7.44 | +| explained_variance | -0.298 | +| learning_rate | 0.000164 | +| loss | -0.0518 | +| n_updates | 3536 | +| policy_gradient_loss | -0.037 | +| value_loss | 0.00016 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.21 | +| time/ | | +| fps | 1322 | +| iterations | 886 | +| time_elapsed | 1372 | +| total_timesteps | 1814528 | +| train/ | | +| approx_kl | 0.033244625 | +| clip_fraction | 0.383 | +| clip_range | 0.127 | +| entropy_loss | -7.42 | +| explained_variance | -0.0658 | +| learning_rate | 0.000164 | +| loss | -0.0584 | +| n_updates | 3540 | +| policy_gradient_loss | -0.0356 | +| value_loss | 0.000184 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.212 | +| time/ | | +| fps | 1322 | +| iterations | 887 | +| time_elapsed | 1373 | +| total_timesteps | 1816576 | +| train/ | | +| approx_kl | 0.036365278 | +| clip_fraction | 0.356 | +| clip_range | 0.127 | +| entropy_loss | -7.39 | +| explained_variance | -0.0464 | +| learning_rate | 0.000164 | +| loss | -0.0593 | +| n_updates | 3544 | +| policy_gradient_loss | -0.0364 | +| value_loss | 0.000136 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.216 | +| time/ | | +| fps | 1322 | +| iterations | 888 | +| time_elapsed | 1375 | +| total_timesteps | 1818624 | +| train/ | | +| approx_kl | 0.03324172 | +| clip_fraction | 0.376 | +| clip_range | 0.127 | +| entropy_loss | -7.43 | +| explained_variance | -0.0978 | +| learning_rate | 0.000164 | +| loss | -0.0622 | +| n_updates | 3548 | +| policy_gradient_loss | -0.037 | +| value_loss | 9.47e-05 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.217 | +| time/ | | +| fps | 1322 | +| iterations | 889 | +| time_elapsed | 1376 | +| total_timesteps | 1820672 | +| train/ | | +| approx_kl | 0.03784678 | +| clip_fraction | 0.382 | +| clip_range | 0.127 | +| entropy_loss | -7.36 | +| explained_variance | -0.0211 | +| learning_rate | 0.000164 | +| loss | -0.0471 | +| n_updates | 3552 | +| policy_gradient_loss | -0.0348 | +| value_loss | 0.000147 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.228 | +| time/ | | +| fps | 1322 | +| iterations | 890 | +| time_elapsed | 1378 | +| total_timesteps | 1822720 | +| train/ | | +| approx_kl | 0.04146929 | +| clip_fraction | 0.373 | +| clip_range | 0.127 | +| entropy_loss | -7.41 | +| explained_variance | -0.142 | +| learning_rate | 0.000164 | +| loss | -0.0618 | +| n_updates | 3556 | +| policy_gradient_loss | -0.0376 | +| value_loss | 0.000156 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.23 | +| time/ | | +| fps | 1322 | +| iterations | 891 | +| time_elapsed | 1380 | +| total_timesteps | 1824768 | +| train/ | | +| approx_kl | 0.035933416 | +| clip_fraction | 0.386 | +| clip_range | 0.127 | +| entropy_loss | -7.44 | +| explained_variance | -0.363 | +| learning_rate | 0.000164 | +| loss | -0.0685 | +| n_updates | 3560 | +| policy_gradient_loss | -0.0414 | +| value_loss | 7.09e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.22 | +| time/ | | +| fps | 1322 | +| iterations | 892 | +| time_elapsed | 1381 | +| total_timesteps | 1826816 | +| train/ | | +| approx_kl | 0.030429669 | +| clip_fraction | 0.377 | +| clip_range | 0.127 | +| entropy_loss | -7.38 | +| explained_variance | 0.0945 | +| learning_rate | 0.000164 | +| loss | -0.0387 | +| n_updates | 3564 | +| policy_gradient_loss | -0.0277 | +| value_loss | 0.000173 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.217 | +| time/ | | +| fps | 1322 | +| iterations | 893 | +| time_elapsed | 1383 | +| total_timesteps | 1828864 | +| train/ | | +| approx_kl | 0.036444534 | +| clip_fraction | 0.386 | +| clip_range | 0.127 | +| entropy_loss | -7.47 | +| explained_variance | -0.0744 | +| learning_rate | 0.000164 | +| loss | -0.0682 | +| n_updates | 3568 | +| policy_gradient_loss | -0.0375 | +| value_loss | 0.000128 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.214 | +| time/ | | +| fps | 1322 | +| iterations | 894 | +| time_elapsed | 1384 | +| total_timesteps | 1830912 | +| train/ | | +| approx_kl | 0.036768578 | +| clip_fraction | 0.369 | +| clip_range | 0.127 | +| entropy_loss | -7.49 | +| explained_variance | -0.0402 | +| learning_rate | 0.000164 | +| loss | -0.0588 | +| n_updates | 3572 | +| policy_gradient_loss | -0.0343 | +| value_loss | 0.000213 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.215 | +| time/ | | +| fps | 1322 | +| iterations | 895 | +| time_elapsed | 1386 | +| total_timesteps | 1832960 | +| train/ | | +| approx_kl | 0.03549021 | +| clip_fraction | 0.368 | +| clip_range | 0.127 | +| entropy_loss | -7.52 | +| explained_variance | -0.116 | +| learning_rate | 0.000164 | +| loss | -0.0637 | +| n_updates | 3576 | +| policy_gradient_loss | -0.0363 | +| value_loss | 0.000145 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.215 | +| time/ | | +| fps | 1322 | +| iterations | 896 | +| time_elapsed | 1388 | +| total_timesteps | 1835008 | +| train/ | | +| approx_kl | 0.03451787 | +| clip_fraction | 0.36 | +| clip_range | 0.127 | +| entropy_loss | -7.53 | +| explained_variance | -0.235 | +| learning_rate | 0.000164 | +| loss | -0.0681 | +| n_updates | 3580 | +| policy_gradient_loss | -0.039 | +| value_loss | 0.000122 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.215 | +| time/ | | +| fps | 1321 | +| iterations | 897 | +| time_elapsed | 1389 | +| total_timesteps | 1837056 | +| train/ | | +| approx_kl | 0.032251187 | +| clip_fraction | 0.365 | +| clip_range | 0.127 | +| entropy_loss | -7.53 | +| explained_variance | -0.108 | +| learning_rate | 0.000164 | +| loss | -0.0545 | +| n_updates | 3584 | +| policy_gradient_loss | -0.032 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.222 | +| time/ | | +| fps | 1321 | +| iterations | 898 | +| time_elapsed | 1391 | +| total_timesteps | 1839104 | +| train/ | | +| approx_kl | 0.031856664 | +| clip_fraction | 0.352 | +| clip_range | 0.127 | +| entropy_loss | -7.45 | +| explained_variance | -0.151 | +| learning_rate | 0.000164 | +| loss | -0.0539 | +| n_updates | 3588 | +| policy_gradient_loss | -0.0326 | +| value_loss | 0.000209 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.218 | +| time/ | | +| fps | 1321 | +| iterations | 899 | +| time_elapsed | 1392 | +| total_timesteps | 1841152 | +| train/ | | +| approx_kl | 0.028431281 | +| clip_fraction | 0.337 | +| clip_range | 0.127 | +| entropy_loss | -7.54 | +| explained_variance | -0.0324 | +| learning_rate | 0.000164 | +| loss | -0.0467 | +| n_updates | 3592 | +| policy_gradient_loss | -0.0289 | +| value_loss | 0.000194 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.221 | +| time/ | | +| fps | 1321 | +| iterations | 900 | +| time_elapsed | 1394 | +| total_timesteps | 1843200 | +| train/ | | +| approx_kl | 0.031135513 | +| clip_fraction | 0.357 | +| clip_range | 0.127 | +| entropy_loss | -7.5 | +| explained_variance | -0.133 | +| learning_rate | 0.000164 | +| loss | -0.0632 | +| n_updates | 3596 | +| policy_gradient_loss | -0.0381 | +| value_loss | 0.000111 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.22 | +| time/ | | +| fps | 1321 | +| iterations | 901 | +| time_elapsed | 1396 | +| total_timesteps | 1845248 | +| train/ | | +| approx_kl | 0.04089935 | +| clip_fraction | 0.366 | +| clip_range | 0.127 | +| entropy_loss | -7.5 | +| explained_variance | 0.0604 | +| learning_rate | 0.000164 | +| loss | -0.0558 | +| n_updates | 3600 | +| policy_gradient_loss | -0.0339 | +| value_loss | 0.000269 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.222 | +| time/ | | +| fps | 1321 | +| iterations | 902 | +| time_elapsed | 1397 | +| total_timesteps | 1847296 | +| train/ | | +| approx_kl | 0.03900426 | +| clip_fraction | 0.362 | +| clip_range | 0.127 | +| entropy_loss | -7.53 | +| explained_variance | -0.0689 | +| learning_rate | 0.000163 | +| loss | -0.0645 | +| n_updates | 3604 | +| policy_gradient_loss | -0.0341 | +| value_loss | 0.000162 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.222 | +| time/ | | +| fps | 1321 | +| iterations | 903 | +| time_elapsed | 1399 | +| total_timesteps | 1849344 | +| train/ | | +| approx_kl | 0.03608529 | +| clip_fraction | 0.335 | +| clip_range | 0.127 | +| entropy_loss | -7.5 | +| explained_variance | -0.225 | +| learning_rate | 0.000163 | +| loss | -0.0687 | +| n_updates | 3608 | +| policy_gradient_loss | -0.0372 | +| value_loss | 0.000202 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.221 | +| time/ | | +| fps | 1321 | +| iterations | 904 | +| time_elapsed | 1400 | +| total_timesteps | 1851392 | +| train/ | | +| approx_kl | 0.031809483 | +| clip_fraction | 0.358 | +| clip_range | 0.127 | +| entropy_loss | -7.55 | +| explained_variance | -0.245 | +| learning_rate | 0.000163 | +| loss | -0.0575 | +| n_updates | 3612 | +| policy_gradient_loss | -0.0368 | +| value_loss | 0.000118 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.221 | +| time/ | | +| fps | 1321 | +| iterations | 905 | +| time_elapsed | 1402 | +| total_timesteps | 1853440 | +| train/ | | +| approx_kl | 0.037069723 | +| clip_fraction | 0.353 | +| clip_range | 0.127 | +| entropy_loss | -7.52 | +| explained_variance | -0.182 | +| learning_rate | 0.000163 | +| loss | -0.0586 | +| n_updates | 3616 | +| policy_gradient_loss | -0.0361 | +| value_loss | 0.000146 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.225 | +| time/ | | +| fps | 1321 | +| iterations | 906 | +| time_elapsed | 1404 | +| total_timesteps | 1855488 | +| train/ | | +| approx_kl | 0.03877219 | +| clip_fraction | 0.39 | +| clip_range | 0.127 | +| entropy_loss | -7.48 | +| explained_variance | -0.175 | +| learning_rate | 0.000163 | +| loss | -0.0565 | +| n_updates | 3620 | +| policy_gradient_loss | -0.0345 | +| value_loss | 0.000156 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.225 | +| time/ | | +| fps | 1321 | +| iterations | 907 | +| time_elapsed | 1405 | +| total_timesteps | 1857536 | +| train/ | | +| approx_kl | 0.03637448 | +| clip_fraction | 0.337 | +| clip_range | 0.127 | +| entropy_loss | -7.55 | +| explained_variance | -0.169 | +| learning_rate | 0.000163 | +| loss | -0.0434 | +| n_updates | 3624 | +| policy_gradient_loss | -0.0336 | +| value_loss | 0.000148 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.227 | +| time/ | | +| fps | 1321 | +| iterations | 908 | +| time_elapsed | 1407 | +| total_timesteps | 1859584 | +| train/ | | +| approx_kl | 0.032182835 | +| clip_fraction | 0.349 | +| clip_range | 0.127 | +| entropy_loss | -7.54 | +| explained_variance | -0.0185 | +| learning_rate | 0.000163 | +| loss | -0.0617 | +| n_updates | 3628 | +| policy_gradient_loss | -0.0362 | +| value_loss | 0.000183 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.228 | +| time/ | | +| fps | 1321 | +| iterations | 909 | +| time_elapsed | 1408 | +| total_timesteps | 1861632 | +| train/ | | +| approx_kl | 0.024946157 | +| clip_fraction | 0.359 | +| clip_range | 0.127 | +| entropy_loss | -7.4 | +| explained_variance | -0.0825 | +| learning_rate | 0.000163 | +| loss | -0.0632 | +| n_updates | 3632 | +| policy_gradient_loss | -0.0335 | +| value_loss | 0.000159 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.222 | +| time/ | | +| fps | 1321 | +| iterations | 910 | +| time_elapsed | 1410 | +| total_timesteps | 1863680 | +| train/ | | +| approx_kl | 0.029879345 | +| clip_fraction | 0.358 | +| clip_range | 0.127 | +| entropy_loss | -7.44 | +| explained_variance | -0.355 | +| learning_rate | 0.000163 | +| loss | -0.0497 | +| n_updates | 3636 | +| policy_gradient_loss | -0.0319 | +| value_loss | 0.000107 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.228 | +| time/ | | +| fps | 1321 | +| iterations | 911 | +| time_elapsed | 1412 | +| total_timesteps | 1865728 | +| train/ | | +| approx_kl | 0.036052704 | +| clip_fraction | 0.345 | +| clip_range | 0.127 | +| entropy_loss | -7.49 | +| explained_variance | -0.098 | +| learning_rate | 0.000163 | +| loss | -0.059 | +| n_updates | 3640 | +| policy_gradient_loss | -0.0347 | +| value_loss | 0.000146 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.223 | +| time/ | | +| fps | 1321 | +| iterations | 912 | +| time_elapsed | 1413 | +| total_timesteps | 1867776 | +| train/ | | +| approx_kl | 0.03278765 | +| clip_fraction | 0.359 | +| clip_range | 0.127 | +| entropy_loss | -7.51 | +| explained_variance | -0.0168 | +| learning_rate | 0.000163 | +| loss | -0.0544 | +| n_updates | 3644 | +| policy_gradient_loss | -0.0306 | +| value_loss | 0.000274 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.223 | +| time/ | | +| fps | 1321 | +| iterations | 913 | +| time_elapsed | 1415 | +| total_timesteps | 1869824 | +| train/ | | +| approx_kl | 0.04084763 | +| clip_fraction | 0.364 | +| clip_range | 0.127 | +| entropy_loss | -7.44 | +| explained_variance | -0.101 | +| learning_rate | 0.000163 | +| loss | -0.0709 | +| n_updates | 3648 | +| policy_gradient_loss | -0.0399 | +| value_loss | 0.000134 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.228 | +| time/ | | +| fps | 1321 | +| iterations | 914 | +| time_elapsed | 1416 | +| total_timesteps | 1871872 | +| train/ | | +| approx_kl | 0.034870476 | +| clip_fraction | 0.388 | +| clip_range | 0.127 | +| entropy_loss | -7.43 | +| explained_variance | 0.0214 | +| learning_rate | 0.000163 | +| loss | -0.0656 | +| n_updates | 3652 | +| policy_gradient_loss | -0.0379 | +| value_loss | 8.68e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.231 | +| time/ | | +| fps | 1321 | +| iterations | 915 | +| time_elapsed | 1418 | +| total_timesteps | 1873920 | +| train/ | | +| approx_kl | 0.038247585 | +| clip_fraction | 0.375 | +| clip_range | 0.127 | +| entropy_loss | -7.41 | +| explained_variance | 0.0234 | +| learning_rate | 0.000163 | +| loss | -0.0592 | +| n_updates | 3656 | +| policy_gradient_loss | -0.0334 | +| value_loss | 0.000205 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.227 | +| time/ | | +| fps | 1321 | +| iterations | 916 | +| time_elapsed | 1419 | +| total_timesteps | 1875968 | +| train/ | | +| approx_kl | 0.03546577 | +| clip_fraction | 0.39 | +| clip_range | 0.127 | +| entropy_loss | -7.37 | +| explained_variance | -0.398 | +| learning_rate | 0.000163 | +| loss | -0.0737 | +| n_updates | 3660 | +| policy_gradient_loss | -0.0397 | +| value_loss | 9.38e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.228 | +| time/ | | +| fps | 1321 | +| iterations | 917 | +| time_elapsed | 1421 | +| total_timesteps | 1878016 | +| train/ | | +| approx_kl | 0.033202857 | +| clip_fraction | 0.345 | +| clip_range | 0.127 | +| entropy_loss | -7.3 | +| explained_variance | 0.0159 | +| learning_rate | 0.000163 | +| loss | -0.0494 | +| n_updates | 3664 | +| policy_gradient_loss | -0.0319 | +| value_loss | 0.000208 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.228 | +| time/ | | +| fps | 1321 | +| iterations | 918 | +| time_elapsed | 1423 | +| total_timesteps | 1880064 | +| train/ | | +| approx_kl | 0.041678447 | +| clip_fraction | 0.376 | +| clip_range | 0.127 | +| entropy_loss | -7.46 | +| explained_variance | -0.132 | +| learning_rate | 0.000163 | +| loss | -0.0693 | +| n_updates | 3668 | +| policy_gradient_loss | -0.0398 | +| value_loss | 0.000205 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.246 | +| time/ | | +| fps | 1321 | +| iterations | 919 | +| time_elapsed | 1424 | +| total_timesteps | 1882112 | +| train/ | | +| approx_kl | 0.043441225 | +| clip_fraction | 0.371 | +| clip_range | 0.126 | +| entropy_loss | -7.55 | +| explained_variance | -0.154 | +| learning_rate | 0.000163 | +| loss | -0.0663 | +| n_updates | 3672 | +| policy_gradient_loss | -0.0393 | +| value_loss | 8.83e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.248 | +| time/ | | +| fps | 1321 | +| iterations | 920 | +| time_elapsed | 1426 | +| total_timesteps | 1884160 | +| train/ | | +| approx_kl | 0.03136526 | +| clip_fraction | 0.347 | +| clip_range | 0.126 | +| entropy_loss | -7.41 | +| explained_variance | -0.013 | +| learning_rate | 0.000163 | +| loss | -0.0417 | +| n_updates | 3676 | +| policy_gradient_loss | -0.0286 | +| value_loss | 0.000431 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.248 | +| time/ | | +| fps | 1321 | +| iterations | 921 | +| time_elapsed | 1427 | +| total_timesteps | 1886208 | +| train/ | | +| approx_kl | 0.039735794 | +| clip_fraction | 0.37 | +| clip_range | 0.126 | +| entropy_loss | -7.55 | +| explained_variance | -0.192 | +| learning_rate | 0.000163 | +| loss | -0.0695 | +| n_updates | 3680 | +| policy_gradient_loss | -0.0378 | +| value_loss | 0.000169 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.251 | +| time/ | | +| fps | 1321 | +| iterations | 922 | +| time_elapsed | 1429 | +| total_timesteps | 1888256 | +| train/ | | +| approx_kl | 0.043510906 | +| clip_fraction | 0.395 | +| clip_range | 0.126 | +| entropy_loss | -7.52 | +| explained_variance | -0.255 | +| learning_rate | 0.000163 | +| loss | -0.0654 | +| n_updates | 3684 | +| policy_gradient_loss | -0.0409 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.25 | +| time/ | | +| fps | 1321 | +| iterations | 923 | +| time_elapsed | 1430 | +| total_timesteps | 1890304 | +| train/ | | +| approx_kl | 0.039263226 | +| clip_fraction | 0.363 | +| clip_range | 0.126 | +| entropy_loss | -7.32 | +| explained_variance | -0.138 | +| learning_rate | 0.000163 | +| loss | -0.0546 | +| n_updates | 3688 | +| policy_gradient_loss | -0.0351 | +| value_loss | 0.000174 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.248 | +| time/ | | +| fps | 1321 | +| iterations | 924 | +| time_elapsed | 1432 | +| total_timesteps | 1892352 | +| train/ | | +| approx_kl | 0.044087663 | +| clip_fraction | 0.379 | +| clip_range | 0.126 | +| entropy_loss | -7.41 | +| explained_variance | -0.176 | +| learning_rate | 0.000163 | +| loss | -0.0548 | +| n_updates | 3692 | +| policy_gradient_loss | -0.0358 | +| value_loss | 0.000145 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.248 | +| time/ | | +| fps | 1321 | +| iterations | 925 | +| time_elapsed | 1433 | +| total_timesteps | 1894400 | +| train/ | | +| approx_kl | 0.04032481 | +| clip_fraction | 0.416 | +| clip_range | 0.126 | +| entropy_loss | -7.26 | +| explained_variance | -0.215 | +| learning_rate | 0.000163 | +| loss | -0.0606 | +| n_updates | 3696 | +| policy_gradient_loss | -0.0317 | +| value_loss | 0.000173 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.248 | +| time/ | | +| fps | 1321 | +| iterations | 926 | +| time_elapsed | 1435 | +| total_timesteps | 1896448 | +| train/ | | +| approx_kl | 0.042611577 | +| clip_fraction | 0.397 | +| clip_range | 0.126 | +| entropy_loss | -7.38 | +| explained_variance | -0.307 | +| learning_rate | 0.000162 | +| loss | -0.0564 | +| n_updates | 3700 | +| policy_gradient_loss | -0.0387 | +| value_loss | 0.000103 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.243 | +| time/ | | +| fps | 1321 | +| iterations | 927 | +| time_elapsed | 1436 | +| total_timesteps | 1898496 | +| train/ | | +| approx_kl | 0.039230585 | +| clip_fraction | 0.37 | +| clip_range | 0.126 | +| entropy_loss | -7.43 | +| explained_variance | -0.168 | +| learning_rate | 0.000162 | +| loss | -0.0556 | +| n_updates | 3704 | +| policy_gradient_loss | -0.0334 | +| value_loss | 0.000118 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.242 | +| time/ | | +| fps | 1321 | +| iterations | 928 | +| time_elapsed | 1438 | +| total_timesteps | 1900544 | +| train/ | | +| approx_kl | 0.03979689 | +| clip_fraction | 0.421 | +| clip_range | 0.126 | +| entropy_loss | -7.36 | +| explained_variance | -0.153 | +| learning_rate | 0.000162 | +| loss | -0.0731 | +| n_updates | 3708 | +| policy_gradient_loss | -0.034 | +| value_loss | 0.000144 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.243 | +| time/ | | +| fps | 1321 | +| iterations | 929 | +| time_elapsed | 1440 | +| total_timesteps | 1902592 | +| train/ | | +| approx_kl | 0.036463544 | +| clip_fraction | 0.363 | +| clip_range | 0.126 | +| entropy_loss | -7.35 | +| explained_variance | -3.04e-05 | +| learning_rate | 0.000162 | +| loss | -0.054 | +| n_updates | 3712 | +| policy_gradient_loss | -0.0334 | +| value_loss | 0.000227 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.247 | +| time/ | | +| fps | 1321 | +| iterations | 930 | +| time_elapsed | 1441 | +| total_timesteps | 1904640 | +| train/ | | +| approx_kl | 0.041778684 | +| clip_fraction | 0.403 | +| clip_range | 0.126 | +| entropy_loss | -7.49 | +| explained_variance | -0.0885 | +| learning_rate | 0.000162 | +| loss | -0.0598 | +| n_updates | 3716 | +| policy_gradient_loss | -0.0361 | +| value_loss | 0.000186 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.247 | +| time/ | | +| fps | 1321 | +| iterations | 931 | +| time_elapsed | 1443 | +| total_timesteps | 1906688 | +| train/ | | +| approx_kl | 0.03409387 | +| clip_fraction | 0.387 | +| clip_range | 0.126 | +| entropy_loss | -7.41 | +| explained_variance | -0.268 | +| learning_rate | 0.000162 | +| loss | -0.0646 | +| n_updates | 3720 | +| policy_gradient_loss | -0.0383 | +| value_loss | 0.000153 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.248 | +| time/ | | +| fps | 1321 | +| iterations | 932 | +| time_elapsed | 1444 | +| total_timesteps | 1908736 | +| train/ | | +| approx_kl | 0.043406915 | +| clip_fraction | 0.374 | +| clip_range | 0.126 | +| entropy_loss | -7.46 | +| explained_variance | -0.0794 | +| learning_rate | 0.000162 | +| loss | -0.0559 | +| n_updates | 3724 | +| policy_gradient_loss | -0.0355 | +| value_loss | 0.000148 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.248 | +| time/ | | +| fps | 1321 | +| iterations | 933 | +| time_elapsed | 1446 | +| total_timesteps | 1910784 | +| train/ | | +| approx_kl | 0.036133844 | +| clip_fraction | 0.381 | +| clip_range | 0.126 | +| entropy_loss | -7.55 | +| explained_variance | -0.153 | +| learning_rate | 0.000162 | +| loss | -0.0642 | +| n_updates | 3728 | +| policy_gradient_loss | -0.0365 | +| value_loss | 9.41e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.244 | +| time/ | | +| fps | 1321 | +| iterations | 934 | +| time_elapsed | 1447 | +| total_timesteps | 1912832 | +| train/ | | +| approx_kl | 0.037552737 | +| clip_fraction | 0.37 | +| clip_range | 0.126 | +| entropy_loss | -7.52 | +| explained_variance | 0.0271 | +| learning_rate | 0.000162 | +| loss | -0.0564 | +| n_updates | 3732 | +| policy_gradient_loss | -0.0361 | +| value_loss | 0.000106 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.24 | +| time/ | | +| fps | 1321 | +| iterations | 935 | +| time_elapsed | 1449 | +| total_timesteps | 1914880 | +| train/ | | +| approx_kl | 0.039641194 | +| clip_fraction | 0.367 | +| clip_range | 0.126 | +| entropy_loss | -7.51 | +| explained_variance | -0.219 | +| learning_rate | 0.000162 | +| loss | -0.0358 | +| n_updates | 3736 | +| policy_gradient_loss | -0.0317 | +| value_loss | 0.000147 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.25 | +| time/ | | +| fps | 1321 | +| iterations | 936 | +| time_elapsed | 1450 | +| total_timesteps | 1916928 | +| train/ | | +| approx_kl | 0.036127847 | +| clip_fraction | 0.401 | +| clip_range | 0.126 | +| entropy_loss | -7.52 | +| explained_variance | -0.297 | +| learning_rate | 0.000162 | +| loss | -0.0563 | +| n_updates | 3740 | +| policy_gradient_loss | -0.036 | +| value_loss | 6.52e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.247 | +| time/ | | +| fps | 1321 | +| iterations | 937 | +| time_elapsed | 1452 | +| total_timesteps | 1918976 | +| train/ | | +| approx_kl | 0.04467738 | +| clip_fraction | 0.361 | +| clip_range | 0.126 | +| entropy_loss | -7.45 | +| explained_variance | -0.245 | +| learning_rate | 0.000162 | +| loss | -0.0594 | +| n_updates | 3744 | +| policy_gradient_loss | -0.0352 | +| value_loss | 9.29e-05 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.244 | +| time/ | | +| fps | 1321 | +| iterations | 938 | +| time_elapsed | 1453 | +| total_timesteps | 1921024 | +| train/ | | +| approx_kl | 0.03609319 | +| clip_fraction | 0.392 | +| clip_range | 0.126 | +| entropy_loss | -7.5 | +| explained_variance | -0.126 | +| learning_rate | 0.000162 | +| loss | -0.0616 | +| n_updates | 3748 | +| policy_gradient_loss | -0.0329 | +| value_loss | 0.000168 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.245 | +| time/ | | +| fps | 1321 | +| iterations | 939 | +| time_elapsed | 1455 | +| total_timesteps | 1923072 | +| train/ | | +| approx_kl | 0.041806392 | +| clip_fraction | 0.385 | +| clip_range | 0.126 | +| entropy_loss | -7.48 | +| explained_variance | -0.0404 | +| learning_rate | 0.000162 | +| loss | -0.0579 | +| n_updates | 3752 | +| policy_gradient_loss | -0.0355 | +| value_loss | 0.000136 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.248 | +| time/ | | +| fps | 1321 | +| iterations | 940 | +| time_elapsed | 1457 | +| total_timesteps | 1925120 | +| train/ | | +| approx_kl | 0.03177111 | +| clip_fraction | 0.35 | +| clip_range | 0.126 | +| entropy_loss | -7.43 | +| explained_variance | -0.0418 | +| learning_rate | 0.000162 | +| loss | -0.055 | +| n_updates | 3756 | +| policy_gradient_loss | -0.031 | +| value_loss | 0.000153 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.247 | +| time/ | | +| fps | 1321 | +| iterations | 941 | +| time_elapsed | 1458 | +| total_timesteps | 1927168 | +| train/ | | +| approx_kl | 0.032171614 | +| clip_fraction | 0.369 | +| clip_range | 0.126 | +| entropy_loss | -7.44 | +| explained_variance | -0.321 | +| learning_rate | 0.000162 | +| loss | -0.0657 | +| n_updates | 3760 | +| policy_gradient_loss | -0.0391 | +| value_loss | 0.000101 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.249 | +| time/ | | +| fps | 1321 | +| iterations | 942 | +| time_elapsed | 1460 | +| total_timesteps | 1929216 | +| train/ | | +| approx_kl | 0.037780073 | +| clip_fraction | 0.365 | +| clip_range | 0.126 | +| entropy_loss | -7.42 | +| explained_variance | -0.201 | +| learning_rate | 0.000162 | +| loss | -0.0518 | +| n_updates | 3764 | +| policy_gradient_loss | -0.0337 | +| value_loss | 0.000123 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.251 | +| time/ | | +| fps | 1321 | +| iterations | 943 | +| time_elapsed | 1461 | +| total_timesteps | 1931264 | +| train/ | | +| approx_kl | 0.038703755 | +| clip_fraction | 0.372 | +| clip_range | 0.126 | +| entropy_loss | -7.46 | +| explained_variance | -0.181 | +| learning_rate | 0.000162 | +| loss | -0.057 | +| n_updates | 3768 | +| policy_gradient_loss | -0.034 | +| value_loss | 0.000153 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.246 | +| time/ | | +| fps | 1321 | +| iterations | 944 | +| time_elapsed | 1463 | +| total_timesteps | 1933312 | +| train/ | | +| approx_kl | 0.042551447 | +| clip_fraction | 0.375 | +| clip_range | 0.126 | +| entropy_loss | -7.46 | +| explained_variance | -0.135 | +| learning_rate | 0.000162 | +| loss | -0.0615 | +| n_updates | 3772 | +| policy_gradient_loss | -0.033 | +| value_loss | 0.000206 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.246 | +| time/ | | +| fps | 1321 | +| iterations | 945 | +| time_elapsed | 1464 | +| total_timesteps | 1935360 | +| train/ | | +| approx_kl | 0.032946207 | +| clip_fraction | 0.355 | +| clip_range | 0.126 | +| entropy_loss | -7.41 | +| explained_variance | -0.0226 | +| learning_rate | 0.000162 | +| loss | -0.0467 | +| n_updates | 3776 | +| policy_gradient_loss | -0.0311 | +| value_loss | 0.000145 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.244 | +| time/ | | +| fps | 1321 | +| iterations | 946 | +| time_elapsed | 1466 | +| total_timesteps | 1937408 | +| train/ | | +| approx_kl | 0.036277734 | +| clip_fraction | 0.371 | +| clip_range | 0.126 | +| entropy_loss | -7.48 | +| explained_variance | -0.136 | +| learning_rate | 0.000162 | +| loss | -0.0588 | +| n_updates | 3780 | +| policy_gradient_loss | -0.0356 | +| value_loss | 0.000152 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.244 | +| time/ | | +| fps | 1321 | +| iterations | 947 | +| time_elapsed | 1467 | +| total_timesteps | 1939456 | +| train/ | | +| approx_kl | 0.040408865 | +| clip_fraction | 0.399 | +| clip_range | 0.126 | +| entropy_loss | -7.45 | +| explained_variance | -0.108 | +| learning_rate | 0.000162 | +| loss | -0.0681 | +| n_updates | 3784 | +| policy_gradient_loss | -0.0346 | +| value_loss | 9.65e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.245 | +| time/ | | +| fps | 1321 | +| iterations | 948 | +| time_elapsed | 1469 | +| total_timesteps | 1941504 | +| train/ | | +| approx_kl | 0.04148595 | +| clip_fraction | 0.413 | +| clip_range | 0.126 | +| entropy_loss | -7.59 | +| explained_variance | -0.185 | +| learning_rate | 0.000162 | +| loss | -0.0582 | +| n_updates | 3788 | +| policy_gradient_loss | -0.0345 | +| value_loss | 0.000112 | +---------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.242 | +| time/ | | +| fps | 1321 | +| iterations | 949 | +| time_elapsed | 1470 | +| total_timesteps | 1943552 | +| train/ | | +| approx_kl | 0.0355433 | +| clip_fraction | 0.378 | +| clip_range | 0.126 | +| entropy_loss | -7.38 | +| explained_variance | -0.12 | +| learning_rate | 0.000162 | +| loss | -0.0472 | +| n_updates | 3792 | +| policy_gradient_loss | -0.0295 | +| value_loss | 0.000186 | +--------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.242 | +| time/ | | +| fps | 1321 | +| iterations | 950 | +| time_elapsed | 1472 | +| total_timesteps | 1945600 | +| train/ | | +| approx_kl | 0.04213861 | +| clip_fraction | 0.376 | +| clip_range | 0.126 | +| entropy_loss | -7.33 | +| explained_variance | -0.124 | +| learning_rate | 0.000162 | +| loss | -0.0515 | +| n_updates | 3796 | +| policy_gradient_loss | -0.0326 | +| value_loss | 0.000316 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.236 | +| time/ | | +| fps | 1321 | +| iterations | 951 | +| time_elapsed | 1473 | +| total_timesteps | 1947648 | +| train/ | | +| approx_kl | 0.044821855 | +| clip_fraction | 0.401 | +| clip_range | 0.126 | +| entropy_loss | -7.3 | +| explained_variance | -0.348 | +| learning_rate | 0.000161 | +| loss | -0.055 | +| n_updates | 3800 | +| policy_gradient_loss | -0.0405 | +| value_loss | 0.000159 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.236 | +| time/ | | +| fps | 1321 | +| iterations | 952 | +| time_elapsed | 1475 | +| total_timesteps | 1949696 | +| train/ | | +| approx_kl | 0.040464457 | +| clip_fraction | 0.379 | +| clip_range | 0.126 | +| entropy_loss | -7.35 | +| explained_variance | -0.167 | +| learning_rate | 0.000161 | +| loss | -0.058 | +| n_updates | 3804 | +| policy_gradient_loss | -0.0371 | +| value_loss | 0.000145 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.236 | +| time/ | | +| fps | 1321 | +| iterations | 953 | +| time_elapsed | 1476 | +| total_timesteps | 1951744 | +| train/ | | +| approx_kl | 0.041063815 | +| clip_fraction | 0.39 | +| clip_range | 0.126 | +| entropy_loss | -7.5 | +| explained_variance | -0.091 | +| learning_rate | 0.000161 | +| loss | -0.0557 | +| n_updates | 3808 | +| policy_gradient_loss | -0.0375 | +| value_loss | 0.00011 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.233 | +| time/ | | +| fps | 1321 | +| iterations | 954 | +| time_elapsed | 1478 | +| total_timesteps | 1953792 | +| train/ | | +| approx_kl | 0.043226115 | +| clip_fraction | 0.399 | +| clip_range | 0.126 | +| entropy_loss | -7.38 | +| explained_variance | -0.211 | +| learning_rate | 0.000161 | +| loss | -0.0604 | +| n_updates | 3812 | +| policy_gradient_loss | -0.0395 | +| value_loss | 8.85e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.235 | +| time/ | | +| fps | 1321 | +| iterations | 955 | +| time_elapsed | 1480 | +| total_timesteps | 1955840 | +| train/ | | +| approx_kl | 0.036382757 | +| clip_fraction | 0.366 | +| clip_range | 0.126 | +| entropy_loss | -7.45 | +| explained_variance | -0.0592 | +| learning_rate | 0.000161 | +| loss | -0.0459 | +| n_updates | 3816 | +| policy_gradient_loss | -0.0307 | +| value_loss | 0.000188 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.233 | +| time/ | | +| fps | 1321 | +| iterations | 956 | +| time_elapsed | 1481 | +| total_timesteps | 1957888 | +| train/ | | +| approx_kl | 0.034984358 | +| clip_fraction | 0.397 | +| clip_range | 0.126 | +| entropy_loss | -7.4 | +| explained_variance | -0.17 | +| learning_rate | 0.000161 | +| loss | -0.0592 | +| n_updates | 3820 | +| policy_gradient_loss | -0.0353 | +| value_loss | 0.000171 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.232 | +| time/ | | +| fps | 1321 | +| iterations | 957 | +| time_elapsed | 1483 | +| total_timesteps | 1959936 | +| train/ | | +| approx_kl | 0.039057862 | +| clip_fraction | 0.411 | +| clip_range | 0.126 | +| entropy_loss | -7.41 | +| explained_variance | 0.00645 | +| learning_rate | 0.000161 | +| loss | -0.0686 | +| n_updates | 3824 | +| policy_gradient_loss | -0.0392 | +| value_loss | 8.25e-05 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.235 | +| time/ | | +| fps | 1321 | +| iterations | 958 | +| time_elapsed | 1484 | +| total_timesteps | 1961984 | +| train/ | | +| approx_kl | 0.0412516 | +| clip_fraction | 0.421 | +| clip_range | 0.126 | +| entropy_loss | -7.42 | +| explained_variance | 0.0384 | +| learning_rate | 0.000161 | +| loss | -0.0669 | +| n_updates | 3828 | +| policy_gradient_loss | -0.0395 | +| value_loss | 7.63e-05 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.235 | +| time/ | | +| fps | 1321 | +| iterations | 959 | +| time_elapsed | 1486 | +| total_timesteps | 1964032 | +| train/ | | +| approx_kl | 0.043783814 | +| clip_fraction | 0.396 | +| clip_range | 0.125 | +| entropy_loss | -7.46 | +| explained_variance | -0.0212 | +| learning_rate | 0.000161 | +| loss | -0.0607 | +| n_updates | 3832 | +| policy_gradient_loss | -0.036 | +| value_loss | 0.00018 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.234 | +| time/ | | +| fps | 1321 | +| iterations | 960 | +| time_elapsed | 1487 | +| total_timesteps | 1966080 | +| train/ | | +| approx_kl | 0.041002475 | +| clip_fraction | 0.393 | +| clip_range | 0.125 | +| entropy_loss | -7.51 | +| explained_variance | -0.24 | +| learning_rate | 0.000161 | +| loss | -0.0694 | +| n_updates | 3836 | +| policy_gradient_loss | -0.0365 | +| value_loss | 0.000113 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.245 | +| time/ | | +| fps | 1321 | +| iterations | 961 | +| time_elapsed | 1489 | +| total_timesteps | 1968128 | +| train/ | | +| approx_kl | 0.04343889 | +| clip_fraction | 0.414 | +| clip_range | 0.125 | +| entropy_loss | -7.45 | +| explained_variance | -0.0799 | +| learning_rate | 0.000161 | +| loss | -0.056 | +| n_updates | 3840 | +| policy_gradient_loss | -0.0354 | +| value_loss | 0.000128 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.248 | +| time/ | | +| fps | 1321 | +| iterations | 962 | +| time_elapsed | 1490 | +| total_timesteps | 1970176 | +| train/ | | +| approx_kl | 0.04342448 | +| clip_fraction | 0.406 | +| clip_range | 0.125 | +| entropy_loss | -7.37 | +| explained_variance | -0.058 | +| learning_rate | 0.000161 | +| loss | -0.0499 | +| n_updates | 3844 | +| policy_gradient_loss | -0.0339 | +| value_loss | 0.00015 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.251 | +| time/ | | +| fps | 1321 | +| iterations | 963 | +| time_elapsed | 1492 | +| total_timesteps | 1972224 | +| train/ | | +| approx_kl | 0.03862789 | +| clip_fraction | 0.389 | +| clip_range | 0.125 | +| entropy_loss | -7.43 | +| explained_variance | -0.0552 | +| learning_rate | 0.000161 | +| loss | -0.0527 | +| n_updates | 3848 | +| policy_gradient_loss | -0.0313 | +| value_loss | 0.000193 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.251 | +| time/ | | +| fps | 1321 | +| iterations | 964 | +| time_elapsed | 1494 | +| total_timesteps | 1974272 | +| train/ | | +| approx_kl | 0.044006355 | +| clip_fraction | 0.395 | +| clip_range | 0.125 | +| entropy_loss | -7.41 | +| explained_variance | -0.28 | +| learning_rate | 0.000161 | +| loss | -0.0553 | +| n_updates | 3852 | +| policy_gradient_loss | -0.0376 | +| value_loss | 0.000109 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.243 | +| time/ | | +| fps | 1321 | +| iterations | 965 | +| time_elapsed | 1495 | +| total_timesteps | 1976320 | +| train/ | | +| approx_kl | 0.05034878 | +| clip_fraction | 0.396 | +| clip_range | 0.125 | +| entropy_loss | -7.39 | +| explained_variance | -0.0812 | +| learning_rate | 0.000161 | +| loss | -0.0498 | +| n_updates | 3856 | +| policy_gradient_loss | -0.0345 | +| value_loss | 0.000155 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.244 | +| time/ | | +| fps | 1321 | +| iterations | 966 | +| time_elapsed | 1497 | +| total_timesteps | 1978368 | +| train/ | | +| approx_kl | 0.042168975 | +| clip_fraction | 0.425 | +| clip_range | 0.125 | +| entropy_loss | -7.39 | +| explained_variance | -0.222 | +| learning_rate | 0.000161 | +| loss | -0.0682 | +| n_updates | 3860 | +| policy_gradient_loss | -0.0387 | +| value_loss | 0.000102 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.244 | +| time/ | | +| fps | 1321 | +| iterations | 967 | +| time_elapsed | 1498 | +| total_timesteps | 1980416 | +| train/ | | +| approx_kl | 0.045217246 | +| clip_fraction | 0.376 | +| clip_range | 0.125 | +| entropy_loss | -7.33 | +| explained_variance | -0.189 | +| learning_rate | 0.000161 | +| loss | -0.0534 | +| n_updates | 3864 | +| policy_gradient_loss | -0.0332 | +| value_loss | 0.000144 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.247 | +| time/ | | +| fps | 1321 | +| iterations | 968 | +| time_elapsed | 1500 | +| total_timesteps | 1982464 | +| train/ | | +| approx_kl | 0.038487356 | +| clip_fraction | 0.411 | +| clip_range | 0.125 | +| entropy_loss | -7.39 | +| explained_variance | -0.109 | +| learning_rate | 0.000161 | +| loss | -0.0557 | +| n_updates | 3868 | +| policy_gradient_loss | -0.032 | +| value_loss | 0.000141 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.247 | +| time/ | | +| fps | 1321 | +| iterations | 969 | +| time_elapsed | 1501 | +| total_timesteps | 1984512 | +| train/ | | +| approx_kl | 0.042201843 | +| clip_fraction | 0.376 | +| clip_range | 0.125 | +| entropy_loss | -7.46 | +| explained_variance | -0.164 | +| learning_rate | 0.000161 | +| loss | -0.0496 | +| n_updates | 3872 | +| policy_gradient_loss | -0.0333 | +| value_loss | 0.000125 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.249 | +| time/ | | +| fps | 1321 | +| iterations | 970 | +| time_elapsed | 1503 | +| total_timesteps | 1986560 | +| train/ | | +| approx_kl | 0.040148634 | +| clip_fraction | 0.377 | +| clip_range | 0.125 | +| entropy_loss | -7.4 | +| explained_variance | -0.0701 | +| learning_rate | 0.000161 | +| loss | -0.06 | +| n_updates | 3876 | +| policy_gradient_loss | -0.0348 | +| value_loss | 0.000312 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.249 | +| time/ | | +| fps | 1321 | +| iterations | 971 | +| time_elapsed | 1504 | +| total_timesteps | 1988608 | +| train/ | | +| approx_kl | 0.036019277 | +| clip_fraction | 0.401 | +| clip_range | 0.125 | +| entropy_loss | -7.37 | +| explained_variance | -0.359 | +| learning_rate | 0.000161 | +| loss | -0.0581 | +| n_updates | 3880 | +| policy_gradient_loss | -0.0358 | +| value_loss | 0.000104 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.252 | +| time/ | | +| fps | 1321 | +| iterations | 972 | +| time_elapsed | 1506 | +| total_timesteps | 1990656 | +| train/ | | +| approx_kl | 0.039829534 | +| clip_fraction | 0.367 | +| clip_range | 0.125 | +| entropy_loss | -7.34 | +| explained_variance | -0.156 | +| learning_rate | 0.000161 | +| loss | -0.0568 | +| n_updates | 3884 | +| policy_gradient_loss | -0.0319 | +| value_loss | 0.000217 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.249 | +| time/ | | +| fps | 1321 | +| iterations | 973 | +| time_elapsed | 1507 | +| total_timesteps | 1992704 | +| train/ | | +| approx_kl | 0.03576801 | +| clip_fraction | 0.379 | +| clip_range | 0.125 | +| entropy_loss | -7.55 | +| explained_variance | -0.221 | +| learning_rate | 0.000161 | +| loss | -0.0582 | +| n_updates | 3888 | +| policy_gradient_loss | -0.036 | +| value_loss | 0.000104 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.252 | +| time/ | | +| fps | 1321 | +| iterations | 974 | +| time_elapsed | 1509 | +| total_timesteps | 1994752 | +| train/ | | +| approx_kl | 0.03686972 | +| clip_fraction | 0.38 | +| clip_range | 0.125 | +| entropy_loss | -7.47 | +| explained_variance | -0.144 | +| learning_rate | 0.000161 | +| loss | -0.0572 | +| n_updates | 3892 | +| policy_gradient_loss | -0.0335 | +| value_loss | 0.000162 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.252 | +| time/ | | +| fps | 1321 | +| iterations | 975 | +| time_elapsed | 1510 | +| total_timesteps | 1996800 | +| train/ | | +| approx_kl | 0.03338651 | +| clip_fraction | 0.359 | +| clip_range | 0.125 | +| entropy_loss | -7.42 | +| explained_variance | -0.0324 | +| learning_rate | 0.000161 | +| loss | -0.0532 | +| n_updates | 3896 | +| policy_gradient_loss | -0.0318 | +| value_loss | 0.000224 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.254 | +| time/ | | +| fps | 1321 | +| iterations | 976 | +| time_elapsed | 1512 | +| total_timesteps | 1998848 | +| train/ | | +| approx_kl | 0.03978149 | +| clip_fraction | 0.405 | +| clip_range | 0.125 | +| entropy_loss | -7.45 | +| explained_variance | -0.0999 | +| learning_rate | 0.00016 | +| loss | -0.0576 | +| n_updates | 3900 | +| policy_gradient_loss | -0.0364 | +| value_loss | 0.000207 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.261 | +| time/ | | +| fps | 1321 | +| iterations | 977 | +| time_elapsed | 1513 | +| total_timesteps | 2000896 | +| train/ | | +| approx_kl | 0.039490588 | +| clip_fraction | 0.39 | +| clip_range | 0.125 | +| entropy_loss | -7.42 | +| explained_variance | -0.0591 | +| learning_rate | 0.00016 | +| loss | -0.0601 | +| n_updates | 3904 | +| policy_gradient_loss | -0.0367 | +| value_loss | 0.000295 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.261 | +| time/ | | +| fps | 1321 | +| iterations | 978 | +| time_elapsed | 1515 | +| total_timesteps | 2002944 | +| train/ | | +| approx_kl | 0.03981691 | +| clip_fraction | 0.376 | +| clip_range | 0.125 | +| entropy_loss | -7.4 | +| explained_variance | -0.127 | +| learning_rate | 0.00016 | +| loss | -0.0591 | +| n_updates | 3908 | +| policy_gradient_loss | -0.0292 | +| value_loss | 0.00025 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.254 | +| time/ | | +| fps | 1321 | +| iterations | 979 | +| time_elapsed | 1517 | +| total_timesteps | 2004992 | +| train/ | | +| approx_kl | 0.039957505 | +| clip_fraction | 0.433 | +| clip_range | 0.125 | +| entropy_loss | -7.29 | +| explained_variance | -0.206 | +| learning_rate | 0.00016 | +| loss | -0.0633 | +| n_updates | 3912 | +| policy_gradient_loss | -0.0392 | +| value_loss | 0.000128 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.251 | +| time/ | | +| fps | 1321 | +| iterations | 980 | +| time_elapsed | 1518 | +| total_timesteps | 2007040 | +| train/ | | +| approx_kl | 0.041041948 | +| clip_fraction | 0.415 | +| clip_range | 0.125 | +| entropy_loss | -7.37 | +| explained_variance | -0.189 | +| learning_rate | 0.00016 | +| loss | -0.0614 | +| n_updates | 3916 | +| policy_gradient_loss | -0.0371 | +| value_loss | 0.000112 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.25 | +| time/ | | +| fps | 1321 | +| iterations | 981 | +| time_elapsed | 1520 | +| total_timesteps | 2009088 | +| train/ | | +| approx_kl | 0.042084552 | +| clip_fraction | 0.396 | +| clip_range | 0.125 | +| entropy_loss | -7.31 | +| explained_variance | -0.159 | +| learning_rate | 0.00016 | +| loss | -0.0579 | +| n_updates | 3920 | +| policy_gradient_loss | -0.035 | +| value_loss | 0.000154 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.25 | +| time/ | | +| fps | 1321 | +| iterations | 982 | +| time_elapsed | 1521 | +| total_timesteps | 2011136 | +| train/ | | +| approx_kl | 0.04159777 | +| clip_fraction | 0.403 | +| clip_range | 0.125 | +| entropy_loss | -7.39 | +| explained_variance | -0.0309 | +| learning_rate | 0.00016 | +| loss | -0.0571 | +| n_updates | 3924 | +| policy_gradient_loss | -0.0337 | +| value_loss | 0.000165 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.254 | +| time/ | | +| fps | 1321 | +| iterations | 983 | +| time_elapsed | 1523 | +| total_timesteps | 2013184 | +| train/ | | +| approx_kl | 0.036944024 | +| clip_fraction | 0.371 | +| clip_range | 0.125 | +| entropy_loss | -7.46 | +| explained_variance | -0.3 | +| learning_rate | 0.00016 | +| loss | -0.0535 | +| n_updates | 3928 | +| policy_gradient_loss | -0.0364 | +| value_loss | 0.000122 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.258 | +| time/ | | +| fps | 1321 | +| iterations | 984 | +| time_elapsed | 1525 | +| total_timesteps | 2015232 | +| train/ | | +| approx_kl | 0.038327448 | +| clip_fraction | 0.373 | +| clip_range | 0.125 | +| entropy_loss | -7.37 | +| explained_variance | -0.0669 | +| learning_rate | 0.00016 | +| loss | -0.0529 | +| n_updates | 3932 | +| policy_gradient_loss | -0.0327 | +| value_loss | 0.000232 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.255 | +| time/ | | +| fps | 1321 | +| iterations | 985 | +| time_elapsed | 1526 | +| total_timesteps | 2017280 | +| train/ | | +| approx_kl | 0.037576735 | +| clip_fraction | 0.378 | +| clip_range | 0.125 | +| entropy_loss | -7.45 | +| explained_variance | -0.0968 | +| learning_rate | 0.00016 | +| loss | -0.0632 | +| n_updates | 3936 | +| policy_gradient_loss | -0.0357 | +| value_loss | 0.000155 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.252 | +| time/ | | +| fps | 1321 | +| iterations | 986 | +| time_elapsed | 1528 | +| total_timesteps | 2019328 | +| train/ | | +| approx_kl | 0.036317423 | +| clip_fraction | 0.37 | +| clip_range | 0.125 | +| entropy_loss | -7.45 | +| explained_variance | -0.0587 | +| learning_rate | 0.00016 | +| loss | -0.0538 | +| n_updates | 3940 | +| policy_gradient_loss | -0.0337 | +| value_loss | 0.000153 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.247 | +| time/ | | +| fps | 1321 | +| iterations | 987 | +| time_elapsed | 1529 | +| total_timesteps | 2021376 | +| train/ | | +| approx_kl | 0.041442297 | +| clip_fraction | 0.399 | +| clip_range | 0.125 | +| entropy_loss | -7.35 | +| explained_variance | -0.0558 | +| learning_rate | 0.00016 | +| loss | -0.0632 | +| n_updates | 3944 | +| policy_gradient_loss | -0.0352 | +| value_loss | 0.000135 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.243 | +| time/ | | +| fps | 1321 | +| iterations | 988 | +| time_elapsed | 1531 | +| total_timesteps | 2023424 | +| train/ | | +| approx_kl | 0.040764403 | +| clip_fraction | 0.386 | +| clip_range | 0.125 | +| entropy_loss | -7.35 | +| explained_variance | -0.0353 | +| learning_rate | 0.00016 | +| loss | -0.0529 | +| n_updates | 3948 | +| policy_gradient_loss | -0.0316 | +| value_loss | 0.000192 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.238 | +| time/ | | +| fps | 1321 | +| iterations | 989 | +| time_elapsed | 1532 | +| total_timesteps | 2025472 | +| train/ | | +| approx_kl | 0.037042968 | +| clip_fraction | 0.39 | +| clip_range | 0.125 | +| entropy_loss | -7.41 | +| explained_variance | -0.171 | +| learning_rate | 0.00016 | +| loss | -0.0577 | +| n_updates | 3952 | +| policy_gradient_loss | -0.0358 | +| value_loss | 0.000185 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.241 | +| time/ | | +| fps | 1321 | +| iterations | 990 | +| time_elapsed | 1534 | +| total_timesteps | 2027520 | +| train/ | | +| approx_kl | 0.042450547 | +| clip_fraction | 0.419 | +| clip_range | 0.125 | +| entropy_loss | -7.33 | +| explained_variance | -0.302 | +| learning_rate | 0.00016 | +| loss | -0.0657 | +| n_updates | 3956 | +| policy_gradient_loss | -0.0426 | +| value_loss | 8.88e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.243 | +| time/ | | +| fps | 1321 | +| iterations | 991 | +| time_elapsed | 1535 | +| total_timesteps | 2029568 | +| train/ | | +| approx_kl | 0.035660602 | +| clip_fraction | 0.384 | +| clip_range | 0.125 | +| entropy_loss | -7.38 | +| explained_variance | -0.0476 | +| learning_rate | 0.00016 | +| loss | -0.0569 | +| n_updates | 3960 | +| policy_gradient_loss | -0.0308 | +| value_loss | 0.000224 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.24 | +| time/ | | +| fps | 1321 | +| iterations | 992 | +| time_elapsed | 1537 | +| total_timesteps | 2031616 | +| train/ | | +| approx_kl | 0.041771207 | +| clip_fraction | 0.379 | +| clip_range | 0.125 | +| entropy_loss | -7.41 | +| explained_variance | -0.15 | +| learning_rate | 0.00016 | +| loss | -0.0507 | +| n_updates | 3964 | +| policy_gradient_loss | -0.0346 | +| value_loss | 0.000283 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.238 | +| time/ | | +| fps | 1321 | +| iterations | 993 | +| time_elapsed | 1539 | +| total_timesteps | 2033664 | +| train/ | | +| approx_kl | 0.040784113 | +| clip_fraction | 0.372 | +| clip_range | 0.125 | +| entropy_loss | -7.37 | +| explained_variance | -0.111 | +| learning_rate | 0.00016 | +| loss | -0.0601 | +| n_updates | 3968 | +| policy_gradient_loss | -0.034 | +| value_loss | 0.000205 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.237 | +| time/ | | +| fps | 1321 | +| iterations | 994 | +| time_elapsed | 1540 | +| total_timesteps | 2035712 | +| train/ | | +| approx_kl | 0.04163737 | +| clip_fraction | 0.396 | +| clip_range | 0.125 | +| entropy_loss | -7.42 | +| explained_variance | 0.0125 | +| learning_rate | 0.00016 | +| loss | -0.0634 | +| n_updates | 3972 | +| policy_gradient_loss | -0.0374 | +| value_loss | 0.000168 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.237 | +| time/ | | +| fps | 1321 | +| iterations | 995 | +| time_elapsed | 1542 | +| total_timesteps | 2037760 | +| train/ | | +| approx_kl | 0.044174828 | +| clip_fraction | 0.375 | +| clip_range | 0.125 | +| entropy_loss | -7.47 | +| explained_variance | -0.105 | +| learning_rate | 0.00016 | +| loss | -0.062 | +| n_updates | 3976 | +| policy_gradient_loss | -0.0362 | +| value_loss | 0.000215 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.239 | +| time/ | | +| fps | 1321 | +| iterations | 996 | +| time_elapsed | 1544 | +| total_timesteps | 2039808 | +| train/ | | +| approx_kl | 0.040207386 | +| clip_fraction | 0.374 | +| clip_range | 0.125 | +| entropy_loss | -7.46 | +| explained_variance | -0.0819 | +| learning_rate | 0.00016 | +| loss | -0.0561 | +| n_updates | 3980 | +| policy_gradient_loss | -0.0308 | +| value_loss | 0.000164 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.241 | +| time/ | | +| fps | 1320 | +| iterations | 997 | +| time_elapsed | 1545 | +| total_timesteps | 2041856 | +| train/ | | +| approx_kl | 0.038594525 | +| clip_fraction | 0.389 | +| clip_range | 0.125 | +| entropy_loss | -7.44 | +| explained_variance | -0.0837 | +| learning_rate | 0.00016 | +| loss | -0.043 | +| n_updates | 3984 | +| policy_gradient_loss | -0.0289 | +| value_loss | 0.000337 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.241 | +| time/ | | +| fps | 1320 | +| iterations | 998 | +| time_elapsed | 1547 | +| total_timesteps | 2043904 | +| train/ | | +| approx_kl | 0.038038176 | +| clip_fraction | 0.364 | +| clip_range | 0.124 | +| entropy_loss | -7.31 | +| explained_variance | -0.182 | +| learning_rate | 0.00016 | +| loss | -0.0545 | +| n_updates | 3988 | +| policy_gradient_loss | -0.0335 | +| value_loss | 0.000277 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.248 | +| time/ | | +| fps | 1320 | +| iterations | 999 | +| time_elapsed | 1549 | +| total_timesteps | 2045952 | +| train/ | | +| approx_kl | 0.041730843 | +| clip_fraction | 0.408 | +| clip_range | 0.124 | +| entropy_loss | -7.46 | +| explained_variance | -0.156 | +| learning_rate | 0.00016 | +| loss | -0.0571 | +| n_updates | 3992 | +| policy_gradient_loss | -0.036 | +| value_loss | 0.00016 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.247 | +| time/ | | +| fps | 1320 | +| iterations | 1000 | +| time_elapsed | 1550 | +| total_timesteps | 2048000 | +| train/ | | +| approx_kl | 0.035245094 | +| clip_fraction | 0.394 | +| clip_range | 0.124 | +| entropy_loss | -7.22 | +| explained_variance | -0.122 | +| learning_rate | 0.000159 | +| loss | -0.0471 | +| n_updates | 3996 | +| policy_gradient_loss | -0.0294 | +| value_loss | 0.000185 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.251 | +| time/ | | +| fps | 1320 | +| iterations | 1001 | +| time_elapsed | 1552 | +| total_timesteps | 2050048 | +| train/ | | +| approx_kl | 0.040717613 | +| clip_fraction | 0.419 | +| clip_range | 0.124 | +| entropy_loss | -7.31 | +| explained_variance | -0.21 | +| learning_rate | 0.000159 | +| loss | -0.0527 | +| n_updates | 4000 | +| policy_gradient_loss | -0.0345 | +| value_loss | 0.000193 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.257 | +| time/ | | +| fps | 1320 | +| iterations | 1002 | +| time_elapsed | 1553 | +| total_timesteps | 2052096 | +| train/ | | +| approx_kl | 0.042417306 | +| clip_fraction | 0.389 | +| clip_range | 0.124 | +| entropy_loss | -7.34 | +| explained_variance | -0.15 | +| learning_rate | 0.000159 | +| loss | -0.0538 | +| n_updates | 4004 | +| policy_gradient_loss | -0.0326 | +| value_loss | 0.000202 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.257 | +| time/ | | +| fps | 1320 | +| iterations | 1003 | +| time_elapsed | 1555 | +| total_timesteps | 2054144 | +| train/ | | +| approx_kl | 0.038216703 | +| clip_fraction | 0.354 | +| clip_range | 0.124 | +| entropy_loss | -7.35 | +| explained_variance | 0.0281 | +| learning_rate | 0.000159 | +| loss | -0.0593 | +| n_updates | 4008 | +| policy_gradient_loss | -0.0298 | +| value_loss | 0.000207 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.256 | +| time/ | | +| fps | 1320 | +| iterations | 1004 | +| time_elapsed | 1557 | +| total_timesteps | 2056192 | +| train/ | | +| approx_kl | 0.03556218 | +| clip_fraction | 0.395 | +| clip_range | 0.124 | +| entropy_loss | -7.36 | +| explained_variance | 0.0597 | +| learning_rate | 0.000159 | +| loss | -0.0636 | +| n_updates | 4012 | +| policy_gradient_loss | -0.0423 | +| value_loss | 8.24e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.254 | +| time/ | | +| fps | 1320 | +| iterations | 1005 | +| time_elapsed | 1559 | +| total_timesteps | 2058240 | +| train/ | | +| approx_kl | 0.040309466 | +| clip_fraction | 0.385 | +| clip_range | 0.124 | +| entropy_loss | -7.44 | +| explained_variance | -0.187 | +| learning_rate | 0.000159 | +| loss | -0.058 | +| n_updates | 4016 | +| policy_gradient_loss | -0.0342 | +| value_loss | 0.000156 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.254 | +| time/ | | +| fps | 1320 | +| iterations | 1006 | +| time_elapsed | 1560 | +| total_timesteps | 2060288 | +| train/ | | +| approx_kl | 0.034879357 | +| clip_fraction | 0.381 | +| clip_range | 0.124 | +| entropy_loss | -7.39 | +| explained_variance | -0.0798 | +| learning_rate | 0.000159 | +| loss | -0.0483 | +| n_updates | 4020 | +| policy_gradient_loss | -0.0344 | +| value_loss | 0.000215 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.254 | +| time/ | | +| fps | 1320 | +| iterations | 1007 | +| time_elapsed | 1562 | +| total_timesteps | 2062336 | +| train/ | | +| approx_kl | 0.038229622 | +| clip_fraction | 0.386 | +| clip_range | 0.124 | +| entropy_loss | -7.44 | +| explained_variance | -0.0766 | +| learning_rate | 0.000159 | +| loss | -0.0554 | +| n_updates | 4024 | +| policy_gradient_loss | -0.0344 | +| value_loss | 0.000128 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.253 | +| time/ | | +| fps | 1320 | +| iterations | 1008 | +| time_elapsed | 1563 | +| total_timesteps | 2064384 | +| train/ | | +| approx_kl | 0.036425017 | +| clip_fraction | 0.386 | +| clip_range | 0.124 | +| entropy_loss | -7.43 | +| explained_variance | -0.218 | +| learning_rate | 0.000159 | +| loss | -0.0679 | +| n_updates | 4028 | +| policy_gradient_loss | -0.0371 | +| value_loss | 9.21e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.258 | +| time/ | | +| fps | 1319 | +| iterations | 1009 | +| time_elapsed | 1565 | +| total_timesteps | 2066432 | +| train/ | | +| approx_kl | 0.037604235 | +| clip_fraction | 0.371 | +| clip_range | 0.124 | +| entropy_loss | -7.39 | +| explained_variance | -0.0783 | +| learning_rate | 0.000159 | +| loss | -0.0469 | +| n_updates | 4032 | +| policy_gradient_loss | -0.029 | +| value_loss | 0.000293 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.265 | +| time/ | | +| fps | 1319 | +| iterations | 1010 | +| time_elapsed | 1567 | +| total_timesteps | 2068480 | +| train/ | | +| approx_kl | 0.035562113 | +| clip_fraction | 0.386 | +| clip_range | 0.124 | +| entropy_loss | -7.36 | +| explained_variance | -0.124 | +| learning_rate | 0.000159 | +| loss | -0.06 | +| n_updates | 4036 | +| policy_gradient_loss | -0.0338 | +| value_loss | 0.000171 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.264 | +| time/ | | +| fps | 1319 | +| iterations | 1011 | +| time_elapsed | 1568 | +| total_timesteps | 2070528 | +| train/ | | +| approx_kl | 0.042735066 | +| clip_fraction | 0.41 | +| clip_range | 0.124 | +| entropy_loss | -7.29 | +| explained_variance | -0.0365 | +| learning_rate | 0.000159 | +| loss | -0.0576 | +| n_updates | 4040 | +| policy_gradient_loss | -0.0328 | +| value_loss | 0.000262 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.267 | +| time/ | | +| fps | 1319 | +| iterations | 1012 | +| time_elapsed | 1570 | +| total_timesteps | 2072576 | +| train/ | | +| approx_kl | 0.03934324 | +| clip_fraction | 0.405 | +| clip_range | 0.124 | +| entropy_loss | -7.31 | +| explained_variance | -0.336 | +| learning_rate | 0.000159 | +| loss | -0.0624 | +| n_updates | 4044 | +| policy_gradient_loss | -0.0329 | +| value_loss | 0.00013 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.265 | +| time/ | | +| fps | 1319 | +| iterations | 1013 | +| time_elapsed | 1572 | +| total_timesteps | 2074624 | +| train/ | | +| approx_kl | 0.041446805 | +| clip_fraction | 0.398 | +| clip_range | 0.124 | +| entropy_loss | -7.42 | +| explained_variance | -0.123 | +| learning_rate | 0.000159 | +| loss | -0.0714 | +| n_updates | 4048 | +| policy_gradient_loss | -0.0339 | +| value_loss | 0.000177 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.264 | +| time/ | | +| fps | 1319 | +| iterations | 1014 | +| time_elapsed | 1573 | +| total_timesteps | 2076672 | +| train/ | | +| approx_kl | 0.048989657 | +| clip_fraction | 0.398 | +| clip_range | 0.124 | +| entropy_loss | -7.38 | +| explained_variance | -0.208 | +| learning_rate | 0.000159 | +| loss | -0.065 | +| n_updates | 4052 | +| policy_gradient_loss | -0.0386 | +| value_loss | 0.000101 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.258 | +| time/ | | +| fps | 1319 | +| iterations | 1015 | +| time_elapsed | 1575 | +| total_timesteps | 2078720 | +| train/ | | +| approx_kl | 0.044326186 | +| clip_fraction | 0.407 | +| clip_range | 0.124 | +| entropy_loss | -7.34 | +| explained_variance | -0.265 | +| learning_rate | 0.000159 | +| loss | -0.0625 | +| n_updates | 4056 | +| policy_gradient_loss | -0.0366 | +| value_loss | 9.82e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.261 | +| time/ | | +| fps | 1319 | +| iterations | 1016 | +| time_elapsed | 1577 | +| total_timesteps | 2080768 | +| train/ | | +| approx_kl | 0.041041188 | +| clip_fraction | 0.413 | +| clip_range | 0.124 | +| entropy_loss | -7.29 | +| explained_variance | -0.231 | +| learning_rate | 0.000159 | +| loss | -0.0478 | +| n_updates | 4060 | +| policy_gradient_loss | -0.0343 | +| value_loss | 0.000159 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.259 | +| time/ | | +| fps | 1319 | +| iterations | 1017 | +| time_elapsed | 1578 | +| total_timesteps | 2082816 | +| train/ | | +| approx_kl | 0.04289996 | +| clip_fraction | 0.404 | +| clip_range | 0.124 | +| entropy_loss | -7.38 | +| explained_variance | -0.159 | +| learning_rate | 0.000159 | +| loss | -0.0486 | +| n_updates | 4064 | +| policy_gradient_loss | -0.0308 | +| value_loss | 0.000148 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.266 | +| time/ | | +| fps | 1319 | +| iterations | 1018 | +| time_elapsed | 1580 | +| total_timesteps | 2084864 | +| train/ | | +| approx_kl | 0.040997084 | +| clip_fraction | 0.404 | +| clip_range | 0.124 | +| entropy_loss | -7.37 | +| explained_variance | -0.0824 | +| learning_rate | 0.000159 | +| loss | -0.0559 | +| n_updates | 4068 | +| policy_gradient_loss | -0.0326 | +| value_loss | 0.000188 | +----------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.261 | +| time/ | | +| fps | 1319 | +| iterations | 1019 | +| time_elapsed | 1582 | +| total_timesteps | 2086912 | +| train/ | | +| approx_kl | 0.040434 | +| clip_fraction | 0.364 | +| clip_range | 0.124 | +| entropy_loss | -7.31 | +| explained_variance | -0.235 | +| learning_rate | 0.000159 | +| loss | -0.0516 | +| n_updates | 4072 | +| policy_gradient_loss | -0.0313 | +| value_loss | 0.000169 | +-------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.266 | +| time/ | | +| fps | 1318 | +| iterations | 1020 | +| time_elapsed | 1583 | +| total_timesteps | 2088960 | +| train/ | | +| approx_kl | 0.04637115 | +| clip_fraction | 0.415 | +| clip_range | 0.124 | +| entropy_loss | -7.31 | +| explained_variance | -0.49 | +| learning_rate | 0.000159 | +| loss | -0.0758 | +| n_updates | 4076 | +| policy_gradient_loss | -0.0413 | +| value_loss | 8.74e-05 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.263 | +| time/ | | +| fps | 1318 | +| iterations | 1021 | +| time_elapsed | 1585 | +| total_timesteps | 2091008 | +| train/ | | +| approx_kl | 0.04123395 | +| clip_fraction | 0.398 | +| clip_range | 0.124 | +| entropy_loss | -7.28 | +| explained_variance | -0.118 | +| learning_rate | 0.000159 | +| loss | -0.0564 | +| n_updates | 4080 | +| policy_gradient_loss | -0.0334 | +| value_loss | 0.000202 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.26 | +| time/ | | +| fps | 1318 | +| iterations | 1022 | +| time_elapsed | 1587 | +| total_timesteps | 2093056 | +| train/ | | +| approx_kl | 0.04447364 | +| clip_fraction | 0.4 | +| clip_range | 0.124 | +| entropy_loss | -7.38 | +| explained_variance | -0.0365 | +| learning_rate | 0.000159 | +| loss | -0.056 | +| n_updates | 4084 | +| policy_gradient_loss | -0.0346 | +| value_loss | 0.000172 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.259 | +| time/ | | +| fps | 1318 | +| iterations | 1023 | +| time_elapsed | 1588 | +| total_timesteps | 2095104 | +| train/ | | +| approx_kl | 0.04612416 | +| clip_fraction | 0.416 | +| clip_range | 0.124 | +| entropy_loss | -7.24 | +| explained_variance | -0.129 | +| learning_rate | 0.000159 | +| loss | -0.0651 | +| n_updates | 4088 | +| policy_gradient_loss | -0.0388 | +| value_loss | 0.000112 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.256 | +| time/ | | +| fps | 1318 | +| iterations | 1024 | +| time_elapsed | 1590 | +| total_timesteps | 2097152 | +| train/ | | +| approx_kl | 0.046713494 | +| clip_fraction | 0.385 | +| clip_range | 0.124 | +| entropy_loss | -7.25 | +| explained_variance | -0.193 | +| learning_rate | 0.000159 | +| loss | -0.0666 | +| n_updates | 4092 | +| policy_gradient_loss | -0.0354 | +| value_loss | 0.000121 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.25 | +| time/ | | +| fps | 1318 | +| iterations | 1025 | +| time_elapsed | 1591 | +| total_timesteps | 2099200 | +| train/ | | +| approx_kl | 0.04815641 | +| clip_fraction | 0.416 | +| clip_range | 0.124 | +| entropy_loss | -7.32 | +| explained_variance | -0.166 | +| learning_rate | 0.000158 | +| loss | -0.0583 | +| n_updates | 4096 | +| policy_gradient_loss | -0.0368 | +| value_loss | 9.64e-05 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.25 | +| time/ | | +| fps | 1318 | +| iterations | 1026 | +| time_elapsed | 1593 | +| total_timesteps | 2101248 | +| train/ | | +| approx_kl | 0.05802089 | +| clip_fraction | 0.387 | +| clip_range | 0.124 | +| entropy_loss | -7.29 | +| explained_variance | -0.0742 | +| learning_rate | 0.000158 | +| loss | -0.0575 | +| n_updates | 4100 | +| policy_gradient_loss | -0.0344 | +| value_loss | 0.000156 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.25 | +| time/ | | +| fps | 1318 | +| iterations | 1027 | +| time_elapsed | 1595 | +| total_timesteps | 2103296 | +| train/ | | +| approx_kl | 0.04912381 | +| clip_fraction | 0.414 | +| clip_range | 0.124 | +| entropy_loss | -7.35 | +| explained_variance | -0.185 | +| learning_rate | 0.000158 | +| loss | -0.0585 | +| n_updates | 4104 | +| policy_gradient_loss | -0.0345 | +| value_loss | 0.000116 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.254 | +| time/ | | +| fps | 1318 | +| iterations | 1028 | +| time_elapsed | 1596 | +| total_timesteps | 2105344 | +| train/ | | +| approx_kl | 0.04021671 | +| clip_fraction | 0.398 | +| clip_range | 0.124 | +| entropy_loss | -7.31 | +| explained_variance | -0.125 | +| learning_rate | 0.000158 | +| loss | -0.0557 | +| n_updates | 4108 | +| policy_gradient_loss | -0.031 | +| value_loss | 0.000152 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.254 | +| time/ | | +| fps | 1318 | +| iterations | 1029 | +| time_elapsed | 1597 | +| total_timesteps | 2107392 | +| train/ | | +| approx_kl | 0.04842349 | +| clip_fraction | 0.396 | +| clip_range | 0.124 | +| entropy_loss | -7.28 | +| explained_variance | -0.0237 | +| learning_rate | 0.000158 | +| loss | -0.0396 | +| n_updates | 4112 | +| policy_gradient_loss | -0.0288 | +| value_loss | 0.000245 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.255 | +| time/ | | +| fps | 1318 | +| iterations | 1030 | +| time_elapsed | 1599 | +| total_timesteps | 2109440 | +| train/ | | +| approx_kl | 0.04380036 | +| clip_fraction | 0.409 | +| clip_range | 0.124 | +| entropy_loss | -7.35 | +| explained_variance | -0.205 | +| learning_rate | 0.000158 | +| loss | -0.0589 | +| n_updates | 4116 | +| policy_gradient_loss | -0.0382 | +| value_loss | 0.000121 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.254 | +| time/ | | +| fps | 1318 | +| iterations | 1031 | +| time_elapsed | 1600 | +| total_timesteps | 2111488 | +| train/ | | +| approx_kl | 0.04280281 | +| clip_fraction | 0.406 | +| clip_range | 0.124 | +| entropy_loss | -7.27 | +| explained_variance | -0.307 | +| learning_rate | 0.000158 | +| loss | -0.0606 | +| n_updates | 4120 | +| policy_gradient_loss | -0.035 | +| value_loss | 0.000155 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.249 | +| time/ | | +| fps | 1318 | +| iterations | 1032 | +| time_elapsed | 1602 | +| total_timesteps | 2113536 | +| train/ | | +| approx_kl | 0.04668112 | +| clip_fraction | 0.459 | +| clip_range | 0.124 | +| entropy_loss | -7.18 | +| explained_variance | -0.35 | +| learning_rate | 0.000158 | +| loss | -0.0675 | +| n_updates | 4124 | +| policy_gradient_loss | -0.04 | +| value_loss | 8.81e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.252 | +| time/ | | +| fps | 1319 | +| iterations | 1033 | +| time_elapsed | 1603 | +| total_timesteps | 2115584 | +| train/ | | +| approx_kl | 0.045200393 | +| clip_fraction | 0.405 | +| clip_range | 0.124 | +| entropy_loss | -7.32 | +| explained_variance | -0.141 | +| learning_rate | 0.000158 | +| loss | -0.0551 | +| n_updates | 4128 | +| policy_gradient_loss | -0.0356 | +| value_loss | 0.000119 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.253 | +| time/ | | +| fps | 1319 | +| iterations | 1034 | +| time_elapsed | 1605 | +| total_timesteps | 2117632 | +| train/ | | +| approx_kl | 0.0449728 | +| clip_fraction | 0.374 | +| clip_range | 0.124 | +| entropy_loss | -7.23 | +| explained_variance | -0.116 | +| learning_rate | 0.000158 | +| loss | -0.061 | +| n_updates | 4132 | +| policy_gradient_loss | -0.035 | +| value_loss | 0.000119 | +--------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.252 | +| time/ | | +| fps | 1319 | +| iterations | 1035 | +| time_elapsed | 1606 | +| total_timesteps | 2119680 | +| train/ | | +| approx_kl | 0.03923644 | +| clip_fraction | 0.398 | +| clip_range | 0.124 | +| entropy_loss | -7.37 | +| explained_variance | -0.143 | +| learning_rate | 0.000158 | +| loss | -0.0512 | +| n_updates | 4136 | +| policy_gradient_loss | -0.0345 | +| value_loss | 8.25e-05 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.246 | +| time/ | | +| fps | 1319 | +| iterations | 1036 | +| time_elapsed | 1608 | +| total_timesteps | 2121728 | +| train/ | | +| approx_kl | 0.04148359 | +| clip_fraction | 0.397 | +| clip_range | 0.124 | +| entropy_loss | -7.29 | +| explained_variance | -0.0451 | +| learning_rate | 0.000158 | +| loss | -0.047 | +| n_updates | 4140 | +| policy_gradient_loss | -0.033 | +| value_loss | 0.000217 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.246 | +| time/ | | +| fps | 1319 | +| iterations | 1037 | +| time_elapsed | 1609 | +| total_timesteps | 2123776 | +| train/ | | +| approx_kl | 0.040112033 | +| clip_fraction | 0.403 | +| clip_range | 0.123 | +| entropy_loss | -7.34 | +| explained_variance | -0.2 | +| learning_rate | 0.000158 | +| loss | -0.0555 | +| n_updates | 4144 | +| policy_gradient_loss | -0.0348 | +| value_loss | 0.000209 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.246 | +| time/ | | +| fps | 1319 | +| iterations | 1038 | +| time_elapsed | 1611 | +| total_timesteps | 2125824 | +| train/ | | +| approx_kl | 0.04251806 | +| clip_fraction | 0.366 | +| clip_range | 0.123 | +| entropy_loss | -7.41 | +| explained_variance | -0.108 | +| learning_rate | 0.000158 | +| loss | -0.0591 | +| n_updates | 4148 | +| policy_gradient_loss | -0.0346 | +| value_loss | 0.000161 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.246 | +| time/ | | +| fps | 1319 | +| iterations | 1039 | +| time_elapsed | 1612 | +| total_timesteps | 2127872 | +| train/ | | +| approx_kl | 0.042824388 | +| clip_fraction | 0.396 | +| clip_range | 0.123 | +| entropy_loss | -7.39 | +| explained_variance | -0.232 | +| learning_rate | 0.000158 | +| loss | -0.0583 | +| n_updates | 4152 | +| policy_gradient_loss | -0.0367 | +| value_loss | 9.65e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.245 | +| time/ | | +| fps | 1319 | +| iterations | 1040 | +| time_elapsed | 1614 | +| total_timesteps | 2129920 | +| train/ | | +| approx_kl | 0.041516714 | +| clip_fraction | 0.401 | +| clip_range | 0.123 | +| entropy_loss | -7.4 | +| explained_variance | -0.195 | +| learning_rate | 0.000158 | +| loss | -0.0576 | +| n_updates | 4156 | +| policy_gradient_loss | -0.0347 | +| value_loss | 0.000116 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.243 | +| time/ | | +| fps | 1319 | +| iterations | 1041 | +| time_elapsed | 1615 | +| total_timesteps | 2131968 | +| train/ | | +| approx_kl | 0.04029345 | +| clip_fraction | 0.37 | +| clip_range | 0.123 | +| entropy_loss | -7.36 | +| explained_variance | -0.275 | +| learning_rate | 0.000158 | +| loss | -0.0584 | +| n_updates | 4160 | +| policy_gradient_loss | -0.0351 | +| value_loss | 9.53e-05 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.241 | +| time/ | | +| fps | 1319 | +| iterations | 1042 | +| time_elapsed | 1617 | +| total_timesteps | 2134016 | +| train/ | | +| approx_kl | 0.04054024 | +| clip_fraction | 0.393 | +| clip_range | 0.123 | +| entropy_loss | -7.33 | +| explained_variance | -0.127 | +| learning_rate | 0.000158 | +| loss | -0.0493 | +| n_updates | 4164 | +| policy_gradient_loss | -0.0317 | +| value_loss | 8.2e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.237 | +| time/ | | +| fps | 1319 | +| iterations | 1043 | +| time_elapsed | 1618 | +| total_timesteps | 2136064 | +| train/ | | +| approx_kl | 0.036280744 | +| clip_fraction | 0.373 | +| clip_range | 0.123 | +| entropy_loss | -7.43 | +| explained_variance | -0.0601 | +| learning_rate | 0.000158 | +| loss | -0.0539 | +| n_updates | 4168 | +| policy_gradient_loss | -0.032 | +| value_loss | 0.000101 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.239 | +| time/ | | +| fps | 1319 | +| iterations | 1044 | +| time_elapsed | 1620 | +| total_timesteps | 2138112 | +| train/ | | +| approx_kl | 0.034427233 | +| clip_fraction | 0.385 | +| clip_range | 0.123 | +| entropy_loss | -7.33 | +| explained_variance | -0.0578 | +| learning_rate | 0.000158 | +| loss | -0.0535 | +| n_updates | 4172 | +| policy_gradient_loss | -0.0327 | +| value_loss | 0.00011 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.246 | +| time/ | | +| fps | 1319 | +| iterations | 1045 | +| time_elapsed | 1621 | +| total_timesteps | 2140160 | +| train/ | | +| approx_kl | 0.041521613 | +| clip_fraction | 0.385 | +| clip_range | 0.123 | +| entropy_loss | -7.36 | +| explained_variance | -0.0358 | +| learning_rate | 0.000158 | +| loss | -0.0494 | +| n_updates | 4176 | +| policy_gradient_loss | -0.0306 | +| value_loss | 0.000218 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.243 | +| time/ | | +| fps | 1319 | +| iterations | 1046 | +| time_elapsed | 1622 | +| total_timesteps | 2142208 | +| train/ | | +| approx_kl | 0.039221324 | +| clip_fraction | 0.397 | +| clip_range | 0.123 | +| entropy_loss | -7.43 | +| explained_variance | -0.0669 | +| learning_rate | 0.000158 | +| loss | -0.0589 | +| n_updates | 4180 | +| policy_gradient_loss | -0.0331 | +| value_loss | 0.000314 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.243 | +| time/ | | +| fps | 1320 | +| iterations | 1047 | +| time_elapsed | 1624 | +| total_timesteps | 2144256 | +| train/ | | +| approx_kl | 0.035666548 | +| clip_fraction | 0.403 | +| clip_range | 0.123 | +| entropy_loss | -7.38 | +| explained_variance | -0.0578 | +| learning_rate | 0.000158 | +| loss | -0.0562 | +| n_updates | 4184 | +| policy_gradient_loss | -0.0326 | +| value_loss | 0.000191 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.244 | +| time/ | | +| fps | 1320 | +| iterations | 1048 | +| time_elapsed | 1625 | +| total_timesteps | 2146304 | +| train/ | | +| approx_kl | 0.03588267 | +| clip_fraction | 0.381 | +| clip_range | 0.123 | +| entropy_loss | -7.47 | +| explained_variance | -0.0776 | +| learning_rate | 0.000158 | +| loss | -0.0597 | +| n_updates | 4188 | +| policy_gradient_loss | -0.0362 | +| value_loss | 0.000157 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.244 | +| time/ | | +| fps | 1320 | +| iterations | 1049 | +| time_elapsed | 1627 | +| total_timesteps | 2148352 | +| train/ | | +| approx_kl | 0.036702633 | +| clip_fraction | 0.385 | +| clip_range | 0.123 | +| entropy_loss | -7.55 | +| explained_variance | -0.0583 | +| learning_rate | 0.000158 | +| loss | -0.0559 | +| n_updates | 4192 | +| policy_gradient_loss | -0.0342 | +| value_loss | 0.000156 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.237 | +| time/ | | +| fps | 1320 | +| iterations | 1050 | +| time_elapsed | 1628 | +| total_timesteps | 2150400 | +| train/ | | +| approx_kl | 0.031001406 | +| clip_fraction | 0.394 | +| clip_range | 0.123 | +| entropy_loss | -7.41 | +| explained_variance | -0.318 | +| learning_rate | 0.000157 | +| loss | -0.064 | +| n_updates | 4196 | +| policy_gradient_loss | -0.0348 | +| value_loss | 0.00012 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.241 | +| time/ | | +| fps | 1320 | +| iterations | 1051 | +| time_elapsed | 1630 | +| total_timesteps | 2152448 | +| train/ | | +| approx_kl | 0.03827213 | +| clip_fraction | 0.378 | +| clip_range | 0.123 | +| entropy_loss | -7.38 | +| explained_variance | -0.0896 | +| learning_rate | 0.000157 | +| loss | -0.0503 | +| n_updates | 4200 | +| policy_gradient_loss | -0.031 | +| value_loss | 0.000185 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.235 | +| time/ | | +| fps | 1320 | +| iterations | 1052 | +| time_elapsed | 1631 | +| total_timesteps | 2154496 | +| train/ | | +| approx_kl | 0.035291817 | +| clip_fraction | 0.386 | +| clip_range | 0.123 | +| entropy_loss | -7.46 | +| explained_variance | -0.199 | +| learning_rate | 0.000157 | +| loss | -0.0596 | +| n_updates | 4204 | +| policy_gradient_loss | -0.0365 | +| value_loss | 0.000104 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.235 | +| time/ | | +| fps | 1320 | +| iterations | 1053 | +| time_elapsed | 1633 | +| total_timesteps | 2156544 | +| train/ | | +| approx_kl | 0.034833364 | +| clip_fraction | 0.391 | +| clip_range | 0.123 | +| entropy_loss | -7.33 | +| explained_variance | -0.049 | +| learning_rate | 0.000157 | +| loss | -0.0472 | +| n_updates | 4208 | +| policy_gradient_loss | -0.0303 | +| value_loss | 0.000216 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.235 | +| time/ | | +| fps | 1320 | +| iterations | 1054 | +| time_elapsed | 1634 | +| total_timesteps | 2158592 | +| train/ | | +| approx_kl | 0.039242033 | +| clip_fraction | 0.371 | +| clip_range | 0.123 | +| entropy_loss | -7.49 | +| explained_variance | -0.266 | +| learning_rate | 0.000157 | +| loss | -0.0566 | +| n_updates | 4212 | +| policy_gradient_loss | -0.0374 | +| value_loss | 9.5e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.237 | +| time/ | | +| fps | 1320 | +| iterations | 1055 | +| time_elapsed | 1636 | +| total_timesteps | 2160640 | +| train/ | | +| approx_kl | 0.03524309 | +| clip_fraction | 0.378 | +| clip_range | 0.123 | +| entropy_loss | -7.5 | +| explained_variance | -0.0569 | +| learning_rate | 0.000157 | +| loss | -0.0555 | +| n_updates | 4216 | +| policy_gradient_loss | -0.0361 | +| value_loss | 0.00011 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.235 | +| time/ | | +| fps | 1320 | +| iterations | 1056 | +| time_elapsed | 1637 | +| total_timesteps | 2162688 | +| train/ | | +| approx_kl | 0.03488072 | +| clip_fraction | 0.371 | +| clip_range | 0.123 | +| entropy_loss | -7.48 | +| explained_variance | -0.00423 | +| learning_rate | 0.000157 | +| loss | -0.054 | +| n_updates | 4220 | +| policy_gradient_loss | -0.0305 | +| value_loss | 0.000149 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.233 | +| time/ | | +| fps | 1320 | +| iterations | 1057 | +| time_elapsed | 1638 | +| total_timesteps | 2164736 | +| train/ | | +| approx_kl | 0.03326153 | +| clip_fraction | 0.39 | +| clip_range | 0.123 | +| entropy_loss | -7.55 | +| explained_variance | -0.155 | +| learning_rate | 0.000157 | +| loss | -0.054 | +| n_updates | 4224 | +| policy_gradient_loss | -0.0356 | +| value_loss | 9.67e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.232 | +| time/ | | +| fps | 1320 | +| iterations | 1058 | +| time_elapsed | 1640 | +| total_timesteps | 2166784 | +| train/ | | +| approx_kl | 0.035456687 | +| clip_fraction | 0.371 | +| clip_range | 0.123 | +| entropy_loss | -7.49 | +| explained_variance | -0.14 | +| learning_rate | 0.000157 | +| loss | -0.0632 | +| n_updates | 4228 | +| policy_gradient_loss | -0.0366 | +| value_loss | 8.44e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.236 | +| time/ | | +| fps | 1320 | +| iterations | 1059 | +| time_elapsed | 1641 | +| total_timesteps | 2168832 | +| train/ | | +| approx_kl | 0.035993565 | +| clip_fraction | 0.372 | +| clip_range | 0.123 | +| entropy_loss | -7.49 | +| explained_variance | -0.0412 | +| learning_rate | 0.000157 | +| loss | -0.0574 | +| n_updates | 4232 | +| policy_gradient_loss | -0.0355 | +| value_loss | 9.64e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.233 | +| time/ | | +| fps | 1320 | +| iterations | 1060 | +| time_elapsed | 1643 | +| total_timesteps | 2170880 | +| train/ | | +| approx_kl | 0.030594183 | +| clip_fraction | 0.354 | +| clip_range | 0.123 | +| entropy_loss | -7.48 | +| explained_variance | -0.108 | +| learning_rate | 0.000157 | +| loss | -0.0479 | +| n_updates | 4236 | +| policy_gradient_loss | -0.0302 | +| value_loss | 0.000149 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.233 | +| time/ | | +| fps | 1320 | +| iterations | 1061 | +| time_elapsed | 1644 | +| total_timesteps | 2172928 | +| train/ | | +| approx_kl | 0.036288634 | +| clip_fraction | 0.375 | +| clip_range | 0.123 | +| entropy_loss | -7.43 | +| explained_variance | -0.164 | +| learning_rate | 0.000157 | +| loss | -0.0578 | +| n_updates | 4240 | +| policy_gradient_loss | -0.0369 | +| value_loss | 0.000199 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.229 | +| time/ | | +| fps | 1321 | +| iterations | 1062 | +| time_elapsed | 1646 | +| total_timesteps | 2174976 | +| train/ | | +| approx_kl | 0.04368163 | +| clip_fraction | 0.405 | +| clip_range | 0.123 | +| entropy_loss | -7.55 | +| explained_variance | -0.373 | +| learning_rate | 0.000157 | +| loss | -0.0707 | +| n_updates | 4244 | +| policy_gradient_loss | -0.0428 | +| value_loss | 9.02e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.228 | +| time/ | | +| fps | 1321 | +| iterations | 1063 | +| time_elapsed | 1647 | +| total_timesteps | 2177024 | +| train/ | | +| approx_kl | 0.034308746 | +| clip_fraction | 0.372 | +| clip_range | 0.123 | +| entropy_loss | -7.36 | +| explained_variance | -0.115 | +| learning_rate | 0.000157 | +| loss | -0.0581 | +| n_updates | 4248 | +| policy_gradient_loss | -0.0362 | +| value_loss | 0.000123 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.227 | +| time/ | | +| fps | 1321 | +| iterations | 1064 | +| time_elapsed | 1649 | +| total_timesteps | 2179072 | +| train/ | | +| approx_kl | 0.033015326 | +| clip_fraction | 0.375 | +| clip_range | 0.123 | +| entropy_loss | -7.39 | +| explained_variance | -0.144 | +| learning_rate | 0.000157 | +| loss | -0.0628 | +| n_updates | 4252 | +| policy_gradient_loss | -0.0331 | +| value_loss | 0.000183 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.224 | +| time/ | | +| fps | 1321 | +| iterations | 1065 | +| time_elapsed | 1651 | +| total_timesteps | 2181120 | +| train/ | | +| approx_kl | 0.03808167 | +| clip_fraction | 0.392 | +| clip_range | 0.123 | +| entropy_loss | -7.47 | +| explained_variance | -0.14 | +| learning_rate | 0.000157 | +| loss | -0.0596 | +| n_updates | 4256 | +| policy_gradient_loss | -0.0349 | +| value_loss | 0.000126 | +---------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.224 | +| time/ | | +| fps | 1321 | +| iterations | 1066 | +| time_elapsed | 1652 | +| total_timesteps | 2183168 | +| train/ | | +| approx_kl | 0.0421848 | +| clip_fraction | 0.414 | +| clip_range | 0.123 | +| entropy_loss | -7.47 | +| explained_variance | -0.113 | +| learning_rate | 0.000157 | +| loss | -0.0538 | +| n_updates | 4260 | +| policy_gradient_loss | -0.0364 | +| value_loss | 0.00012 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.22 | +| time/ | | +| fps | 1321 | +| iterations | 1067 | +| time_elapsed | 1654 | +| total_timesteps | 2185216 | +| train/ | | +| approx_kl | 0.042451896 | +| clip_fraction | 0.378 | +| clip_range | 0.123 | +| entropy_loss | -7.4 | +| explained_variance | -0.0718 | +| learning_rate | 0.000157 | +| loss | -0.0473 | +| n_updates | 4264 | +| policy_gradient_loss | -0.0321 | +| value_loss | 0.000147 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.216 | +| time/ | | +| fps | 1321 | +| iterations | 1068 | +| time_elapsed | 1655 | +| total_timesteps | 2187264 | +| train/ | | +| approx_kl | 0.037470795 | +| clip_fraction | 0.417 | +| clip_range | 0.123 | +| entropy_loss | -7.39 | +| explained_variance | -0.051 | +| learning_rate | 0.000157 | +| loss | -0.0594 | +| n_updates | 4268 | +| policy_gradient_loss | -0.0364 | +| value_loss | 0.000166 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.216 | +| time/ | | +| fps | 1321 | +| iterations | 1069 | +| time_elapsed | 1656 | +| total_timesteps | 2189312 | +| train/ | | +| approx_kl | 0.03887161 | +| clip_fraction | 0.368 | +| clip_range | 0.123 | +| entropy_loss | -7.45 | +| explained_variance | -0.195 | +| learning_rate | 0.000157 | +| loss | -0.0624 | +| n_updates | 4272 | +| policy_gradient_loss | -0.0376 | +| value_loss | 0.000114 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.215 | +| time/ | | +| fps | 1321 | +| iterations | 1070 | +| time_elapsed | 1658 | +| total_timesteps | 2191360 | +| train/ | | +| approx_kl | 0.03755761 | +| clip_fraction | 0.368 | +| clip_range | 0.123 | +| entropy_loss | -7.53 | +| explained_variance | -0.225 | +| learning_rate | 0.000157 | +| loss | -0.0546 | +| n_updates | 4276 | +| policy_gradient_loss | -0.0347 | +| value_loss | 0.000119 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.219 | +| time/ | | +| fps | 1321 | +| iterations | 1071 | +| time_elapsed | 1659 | +| total_timesteps | 2193408 | +| train/ | | +| approx_kl | 0.029035587 | +| clip_fraction | 0.36 | +| clip_range | 0.123 | +| entropy_loss | -7.53 | +| explained_variance | -0.113 | +| learning_rate | 0.000157 | +| loss | -0.0573 | +| n_updates | 4280 | +| policy_gradient_loss | -0.0288 | +| value_loss | 0.000134 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.219 | +| time/ | | +| fps | 1321 | +| iterations | 1072 | +| time_elapsed | 1661 | +| total_timesteps | 2195456 | +| train/ | | +| approx_kl | 0.033780023 | +| clip_fraction | 0.352 | +| clip_range | 0.123 | +| entropy_loss | -7.41 | +| explained_variance | 0.0483 | +| learning_rate | 0.000157 | +| loss | -0.0625 | +| n_updates | 4284 | +| policy_gradient_loss | -0.0331 | +| value_loss | 0.000269 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.224 | +| time/ | | +| fps | 1321 | +| iterations | 1073 | +| time_elapsed | 1662 | +| total_timesteps | 2197504 | +| train/ | | +| approx_kl | 0.035238735 | +| clip_fraction | 0.372 | +| clip_range | 0.123 | +| entropy_loss | -7.43 | +| explained_variance | -0.132 | +| learning_rate | 0.000157 | +| loss | -0.0654 | +| n_updates | 4288 | +| policy_gradient_loss | -0.0356 | +| value_loss | 0.000123 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.23 | +| time/ | | +| fps | 1321 | +| iterations | 1074 | +| time_elapsed | 1664 | +| total_timesteps | 2199552 | +| train/ | | +| approx_kl | 0.038864903 | +| clip_fraction | 0.368 | +| clip_range | 0.123 | +| entropy_loss | -7.52 | +| explained_variance | 0.00577 | +| learning_rate | 0.000156 | +| loss | -0.0516 | +| n_updates | 4292 | +| policy_gradient_loss | -0.0303 | +| value_loss | 0.000204 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.224 | +| time/ | | +| fps | 1321 | +| iterations | 1075 | +| time_elapsed | 1665 | +| total_timesteps | 2201600 | +| train/ | | +| approx_kl | 0.038772188 | +| clip_fraction | 0.397 | +| clip_range | 0.123 | +| entropy_loss | -7.53 | +| explained_variance | 0.0235 | +| learning_rate | 0.000156 | +| loss | -0.0488 | +| n_updates | 4296 | +| policy_gradient_loss | -0.035 | +| value_loss | 0.000303 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.225 | +| time/ | | +| fps | 1321 | +| iterations | 1076 | +| time_elapsed | 1667 | +| total_timesteps | 2203648 | +| train/ | | +| approx_kl | 0.042660065 | +| clip_fraction | 0.43 | +| clip_range | 0.122 | +| entropy_loss | -7.48 | +| explained_variance | -0.265 | +| learning_rate | 0.000156 | +| loss | -0.0702 | +| n_updates | 4300 | +| policy_gradient_loss | -0.0403 | +| value_loss | 0.000122 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.221 | +| time/ | | +| fps | 1321 | +| iterations | 1077 | +| time_elapsed | 1668 | +| total_timesteps | 2205696 | +| train/ | | +| approx_kl | 0.04116243 | +| clip_fraction | 0.411 | +| clip_range | 0.122 | +| entropy_loss | -7.38 | +| explained_variance | -0.313 | +| learning_rate | 0.000156 | +| loss | -0.066 | +| n_updates | 4304 | +| policy_gradient_loss | -0.0378 | +| value_loss | 9.48e-05 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.223 | +| time/ | | +| fps | 1322 | +| iterations | 1078 | +| time_elapsed | 1669 | +| total_timesteps | 2207744 | +| train/ | | +| approx_kl | 0.04015235 | +| clip_fraction | 0.39 | +| clip_range | 0.122 | +| entropy_loss | -7.36 | +| explained_variance | -0.0297 | +| learning_rate | 0.000156 | +| loss | -0.048 | +| n_updates | 4308 | +| policy_gradient_loss | -0.0347 | +| value_loss | 0.000386 | +---------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.216 | +| time/ | | +| fps | 1322 | +| iterations | 1079 | +| time_elapsed | 1671 | +| total_timesteps | 2209792 | +| train/ | | +| approx_kl | 0.0339434 | +| clip_fraction | 0.375 | +| clip_range | 0.122 | +| entropy_loss | -7.42 | +| explained_variance | -0.221 | +| learning_rate | 0.000156 | +| loss | -0.0543 | +| n_updates | 4312 | +| policy_gradient_loss | -0.034 | +| value_loss | 0.000204 | +--------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.218 | +| time/ | | +| fps | 1322 | +| iterations | 1080 | +| time_elapsed | 1672 | +| total_timesteps | 2211840 | +| train/ | | +| approx_kl | 0.03678344 | +| clip_fraction | 0.408 | +| clip_range | 0.122 | +| entropy_loss | -7.29 | +| explained_variance | -0.244 | +| learning_rate | 0.000156 | +| loss | -0.0751 | +| n_updates | 4316 | +| policy_gradient_loss | -0.0367 | +| value_loss | 0.00013 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.226 | +| time/ | | +| fps | 1322 | +| iterations | 1081 | +| time_elapsed | 1674 | +| total_timesteps | 2213888 | +| train/ | | +| approx_kl | 0.039828386 | +| clip_fraction | 0.377 | +| clip_range | 0.122 | +| entropy_loss | -7.39 | +| explained_variance | -0.166 | +| learning_rate | 0.000156 | +| loss | -0.0621 | +| n_updates | 4320 | +| policy_gradient_loss | -0.0349 | +| value_loss | 0.000204 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.226 | +| time/ | | +| fps | 1322 | +| iterations | 1082 | +| time_elapsed | 1675 | +| total_timesteps | 2215936 | +| train/ | | +| approx_kl | 0.036041208 | +| clip_fraction | 0.361 | +| clip_range | 0.122 | +| entropy_loss | -7.35 | +| explained_variance | -0.0642 | +| learning_rate | 0.000156 | +| loss | -0.0514 | +| n_updates | 4324 | +| policy_gradient_loss | -0.0296 | +| value_loss | 0.000174 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.219 | +| time/ | | +| fps | 1322 | +| iterations | 1083 | +| time_elapsed | 1677 | +| total_timesteps | 2217984 | +| train/ | | +| approx_kl | 0.04679195 | +| clip_fraction | 0.398 | +| clip_range | 0.122 | +| entropy_loss | -7.41 | +| explained_variance | -0.151 | +| learning_rate | 0.000156 | +| loss | -0.0657 | +| n_updates | 4328 | +| policy_gradient_loss | -0.0397 | +| value_loss | 0.000141 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.227 | +| time/ | | +| fps | 1322 | +| iterations | 1084 | +| time_elapsed | 1678 | +| total_timesteps | 2220032 | +| train/ | | +| approx_kl | 0.040370744 | +| clip_fraction | 0.398 | +| clip_range | 0.122 | +| entropy_loss | -7.37 | +| explained_variance | -0.0772 | +| learning_rate | 0.000156 | +| loss | -0.0634 | +| n_updates | 4332 | +| policy_gradient_loss | -0.0377 | +| value_loss | 9.61e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.219 | +| time/ | | +| fps | 1322 | +| iterations | 1085 | +| time_elapsed | 1680 | +| total_timesteps | 2222080 | +| train/ | | +| approx_kl | 0.035403304 | +| clip_fraction | 0.391 | +| clip_range | 0.122 | +| entropy_loss | -7.19 | +| explained_variance | -0.131 | +| learning_rate | 0.000156 | +| loss | -0.0526 | +| n_updates | 4336 | +| policy_gradient_loss | -0.0285 | +| value_loss | 0.000168 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.222 | +| time/ | | +| fps | 1322 | +| iterations | 1086 | +| time_elapsed | 1681 | +| total_timesteps | 2224128 | +| train/ | | +| approx_kl | 0.037669994 | +| clip_fraction | 0.402 | +| clip_range | 0.122 | +| entropy_loss | -7.23 | +| explained_variance | -0.0785 | +| learning_rate | 0.000156 | +| loss | -0.058 | +| n_updates | 4340 | +| policy_gradient_loss | -0.0331 | +| value_loss | 0.000194 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.223 | +| time/ | | +| fps | 1322 | +| iterations | 1087 | +| time_elapsed | 1683 | +| total_timesteps | 2226176 | +| train/ | | +| approx_kl | 0.042618502 | +| clip_fraction | 0.382 | +| clip_range | 0.122 | +| entropy_loss | -7.31 | +| explained_variance | -0.0901 | +| learning_rate | 0.000156 | +| loss | -0.0582 | +| n_updates | 4344 | +| policy_gradient_loss | -0.0363 | +| value_loss | 0.00012 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.227 | +| time/ | | +| fps | 1322 | +| iterations | 1088 | +| time_elapsed | 1684 | +| total_timesteps | 2228224 | +| train/ | | +| approx_kl | 0.03649128 | +| clip_fraction | 0.403 | +| clip_range | 0.122 | +| entropy_loss | -7.25 | +| explained_variance | -0.192 | +| learning_rate | 0.000156 | +| loss | -0.0564 | +| n_updates | 4348 | +| policy_gradient_loss | -0.0357 | +| value_loss | 0.000123 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.234 | +| time/ | | +| fps | 1322 | +| iterations | 1089 | +| time_elapsed | 1685 | +| total_timesteps | 2230272 | +| train/ | | +| approx_kl | 0.04649744 | +| clip_fraction | 0.422 | +| clip_range | 0.122 | +| entropy_loss | -7.27 | +| explained_variance | -0.0999 | +| learning_rate | 0.000156 | +| loss | -0.0601 | +| n_updates | 4352 | +| policy_gradient_loss | -0.0358 | +| value_loss | 0.000115 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.234 | +| time/ | | +| fps | 1322 | +| iterations | 1090 | +| time_elapsed | 1687 | +| total_timesteps | 2232320 | +| train/ | | +| approx_kl | 0.041935034 | +| clip_fraction | 0.394 | +| clip_range | 0.122 | +| entropy_loss | -7.3 | +| explained_variance | -0.114 | +| learning_rate | 0.000156 | +| loss | -0.0505 | +| n_updates | 4356 | +| policy_gradient_loss | -0.0326 | +| value_loss | 0.000165 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.234 | +| time/ | | +| fps | 1322 | +| iterations | 1091 | +| time_elapsed | 1688 | +| total_timesteps | 2234368 | +| train/ | | +| approx_kl | 0.045301653 | +| clip_fraction | 0.406 | +| clip_range | 0.122 | +| entropy_loss | -7.25 | +| explained_variance | -0.27 | +| learning_rate | 0.000156 | +| loss | -0.058 | +| n_updates | 4360 | +| policy_gradient_loss | -0.0359 | +| value_loss | 0.00014 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.231 | +| time/ | | +| fps | 1323 | +| iterations | 1092 | +| time_elapsed | 1690 | +| total_timesteps | 2236416 | +| train/ | | +| approx_kl | 0.041427314 | +| clip_fraction | 0.429 | +| clip_range | 0.122 | +| entropy_loss | -7.34 | +| explained_variance | -0.173 | +| learning_rate | 0.000156 | +| loss | -0.0663 | +| n_updates | 4364 | +| policy_gradient_loss | -0.0355 | +| value_loss | 6.8e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.228 | +| time/ | | +| fps | 1323 | +| iterations | 1093 | +| time_elapsed | 1691 | +| total_timesteps | 2238464 | +| train/ | | +| approx_kl | 0.03908754 | +| clip_fraction | 0.386 | +| clip_range | 0.122 | +| entropy_loss | -7.28 | +| explained_variance | -0.0897 | +| learning_rate | 0.000156 | +| loss | -0.0544 | +| n_updates | 4368 | +| policy_gradient_loss | -0.0262 | +| value_loss | 0.000136 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.223 | +| time/ | | +| fps | 1323 | +| iterations | 1094 | +| time_elapsed | 1693 | +| total_timesteps | 2240512 | +| train/ | | +| approx_kl | 0.040474124 | +| clip_fraction | 0.398 | +| clip_range | 0.122 | +| entropy_loss | -7.29 | +| explained_variance | -0.0432 | +| learning_rate | 0.000156 | +| loss | -0.0648 | +| n_updates | 4372 | +| policy_gradient_loss | -0.0338 | +| value_loss | 0.000137 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.226 | +| time/ | | +| fps | 1323 | +| iterations | 1095 | +| time_elapsed | 1694 | +| total_timesteps | 2242560 | +| train/ | | +| approx_kl | 0.039944064 | +| clip_fraction | 0.402 | +| clip_range | 0.122 | +| entropy_loss | -7.18 | +| explained_variance | -0.36 | +| learning_rate | 0.000156 | +| loss | -0.0634 | +| n_updates | 4376 | +| policy_gradient_loss | -0.0368 | +| value_loss | 0.000128 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.23 | +| time/ | | +| fps | 1323 | +| iterations | 1096 | +| time_elapsed | 1696 | +| total_timesteps | 2244608 | +| train/ | | +| approx_kl | 0.03752032 | +| clip_fraction | 0.372 | +| clip_range | 0.122 | +| entropy_loss | -7.23 | +| explained_variance | -0.0365 | +| learning_rate | 0.000156 | +| loss | -0.052 | +| n_updates | 4380 | +| policy_gradient_loss | -0.0317 | +| value_loss | 0.000241 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.229 | +| time/ | | +| fps | 1323 | +| iterations | 1097 | +| time_elapsed | 1697 | +| total_timesteps | 2246656 | +| train/ | | +| approx_kl | 0.036767058 | +| clip_fraction | 0.41 | +| clip_range | 0.122 | +| entropy_loss | -7.26 | +| explained_variance | -0.192 | +| learning_rate | 0.000156 | +| loss | -0.0558 | +| n_updates | 4384 | +| policy_gradient_loss | -0.0328 | +| value_loss | 0.000201 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.217 | +| time/ | | +| fps | 1323 | +| iterations | 1098 | +| time_elapsed | 1699 | +| total_timesteps | 2248704 | +| train/ | | +| approx_kl | 0.044593334 | +| clip_fraction | 0.413 | +| clip_range | 0.122 | +| entropy_loss | -7.29 | +| explained_variance | -0.211 | +| learning_rate | 0.000156 | +| loss | -0.0621 | +| n_updates | 4388 | +| policy_gradient_loss | -0.0392 | +| value_loss | 0.000108 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.214 | +| time/ | | +| fps | 1323 | +| iterations | 1099 | +| time_elapsed | 1700 | +| total_timesteps | 2250752 | +| train/ | | +| approx_kl | 0.037840888 | +| clip_fraction | 0.419 | +| clip_range | 0.122 | +| entropy_loss | -7.39 | +| explained_variance | -0.381 | +| learning_rate | 0.000155 | +| loss | -0.0599 | +| n_updates | 4392 | +| policy_gradient_loss | -0.0343 | +| value_loss | 0.000117 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.214 | +| time/ | | +| fps | 1323 | +| iterations | 1100 | +| time_elapsed | 1702 | +| total_timesteps | 2252800 | +| train/ | | +| approx_kl | 0.038966827 | +| clip_fraction | 0.393 | +| clip_range | 0.122 | +| entropy_loss | -7.27 | +| explained_variance | -0.196 | +| learning_rate | 0.000155 | +| loss | -0.0557 | +| n_updates | 4396 | +| policy_gradient_loss | -0.0336 | +| value_loss | 0.000101 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.222 | +| time/ | | +| fps | 1323 | +| iterations | 1101 | +| time_elapsed | 1704 | +| total_timesteps | 2254848 | +| train/ | | +| approx_kl | 0.04153471 | +| clip_fraction | 0.382 | +| clip_range | 0.122 | +| entropy_loss | -7.33 | +| explained_variance | -0.0714 | +| learning_rate | 0.000155 | +| loss | -0.0573 | +| n_updates | 4400 | +| policy_gradient_loss | -0.034 | +| value_loss | 9.15e-05 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.214 | +| time/ | | +| fps | 1323 | +| iterations | 1102 | +| time_elapsed | 1705 | +| total_timesteps | 2256896 | +| train/ | | +| approx_kl | 0.04037312 | +| clip_fraction | 0.392 | +| clip_range | 0.122 | +| entropy_loss | -7.23 | +| explained_variance | -0.197 | +| learning_rate | 0.000155 | +| loss | -0.0553 | +| n_updates | 4404 | +| policy_gradient_loss | -0.0347 | +| value_loss | 8e-05 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.204 | +| time/ | | +| fps | 1323 | +| iterations | 1103 | +| time_elapsed | 1707 | +| total_timesteps | 2258944 | +| train/ | | +| approx_kl | 0.04219774 | +| clip_fraction | 0.422 | +| clip_range | 0.122 | +| entropy_loss | -7.22 | +| explained_variance | -0.11 | +| learning_rate | 0.000155 | +| loss | -0.0558 | +| n_updates | 4408 | +| policy_gradient_loss | -0.0335 | +| value_loss | 0.000134 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.204 | +| time/ | | +| fps | 1323 | +| iterations | 1104 | +| time_elapsed | 1708 | +| total_timesteps | 2260992 | +| train/ | | +| approx_kl | 0.044189446 | +| clip_fraction | 0.41 | +| clip_range | 0.122 | +| entropy_loss | -7.28 | +| explained_variance | -0.124 | +| learning_rate | 0.000155 | +| loss | -0.0519 | +| n_updates | 4412 | +| policy_gradient_loss | -0.0309 | +| value_loss | 0.000129 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.207 | +| time/ | | +| fps | 1323 | +| iterations | 1105 | +| time_elapsed | 1710 | +| total_timesteps | 2263040 | +| train/ | | +| approx_kl | 0.04465697 | +| clip_fraction | 0.405 | +| clip_range | 0.122 | +| entropy_loss | -7.34 | +| explained_variance | -0.167 | +| learning_rate | 0.000155 | +| loss | -0.0607 | +| n_updates | 4416 | +| policy_gradient_loss | -0.0358 | +| value_loss | 0.000113 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.199 | +| time/ | | +| fps | 1323 | +| iterations | 1106 | +| time_elapsed | 1711 | +| total_timesteps | 2265088 | +| train/ | | +| approx_kl | 0.03961477 | +| clip_fraction | 0.372 | +| clip_range | 0.122 | +| entropy_loss | -7.39 | +| explained_variance | -0.106 | +| learning_rate | 0.000155 | +| loss | -0.0615 | +| n_updates | 4420 | +| policy_gradient_loss | -0.0322 | +| value_loss | 0.000132 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.199 | +| time/ | | +| fps | 1323 | +| iterations | 1107 | +| time_elapsed | 1713 | +| total_timesteps | 2267136 | +| train/ | | +| approx_kl | 0.03717676 | +| clip_fraction | 0.362 | +| clip_range | 0.122 | +| entropy_loss | -7.27 | +| explained_variance | -0.105 | +| learning_rate | 0.000155 | +| loss | -0.055 | +| n_updates | 4424 | +| policy_gradient_loss | -0.0344 | +| value_loss | 0.000175 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.2 | +| time/ | | +| fps | 1323 | +| iterations | 1108 | +| time_elapsed | 1714 | +| total_timesteps | 2269184 | +| train/ | | +| approx_kl | 0.037859373 | +| clip_fraction | 0.381 | +| clip_range | 0.122 | +| entropy_loss | -7.26 | +| explained_variance | -0.13 | +| learning_rate | 0.000155 | +| loss | -0.0553 | +| n_updates | 4428 | +| policy_gradient_loss | -0.0355 | +| value_loss | 0.000108 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.194 | +| time/ | | +| fps | 1323 | +| iterations | 1109 | +| time_elapsed | 1716 | +| total_timesteps | 2271232 | +| train/ | | +| approx_kl | 0.03606525 | +| clip_fraction | 0.392 | +| clip_range | 0.122 | +| entropy_loss | -7.2 | +| explained_variance | -0.0956 | +| learning_rate | 0.000155 | +| loss | -0.0542 | +| n_updates | 4432 | +| policy_gradient_loss | -0.0323 | +| value_loss | 0.000186 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.189 | +| time/ | | +| fps | 1323 | +| iterations | 1110 | +| time_elapsed | 1717 | +| total_timesteps | 2273280 | +| train/ | | +| approx_kl | 0.035985336 | +| clip_fraction | 0.396 | +| clip_range | 0.122 | +| entropy_loss | -7.1 | +| explained_variance | -0.21 | +| learning_rate | 0.000155 | +| loss | -0.064 | +| n_updates | 4436 | +| policy_gradient_loss | -0.0347 | +| value_loss | 0.000116 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.196 | +| time/ | | +| fps | 1323 | +| iterations | 1111 | +| time_elapsed | 1719 | +| total_timesteps | 2275328 | +| train/ | | +| approx_kl | 0.037947323 | +| clip_fraction | 0.389 | +| clip_range | 0.122 | +| entropy_loss | -7.24 | +| explained_variance | -0.0787 | +| learning_rate | 0.000155 | +| loss | -0.0522 | +| n_updates | 4440 | +| policy_gradient_loss | -0.0326 | +| value_loss | 0.000188 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.196 | +| time/ | | +| fps | 1323 | +| iterations | 1112 | +| time_elapsed | 1720 | +| total_timesteps | 2277376 | +| train/ | | +| approx_kl | 0.028706558 | +| clip_fraction | 0.35 | +| clip_range | 0.122 | +| entropy_loss | -7.26 | +| explained_variance | 0.00393 | +| learning_rate | 0.000155 | +| loss | -0.0386 | +| n_updates | 4444 | +| policy_gradient_loss | -0.0251 | +| value_loss | 0.000494 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.198 | +| time/ | | +| fps | 1323 | +| iterations | 1113 | +| time_elapsed | 1721 | +| total_timesteps | 2279424 | +| train/ | | +| approx_kl | 0.037042197 | +| clip_fraction | 0.413 | +| clip_range | 0.122 | +| entropy_loss | -7.23 | +| explained_variance | -0.156 | +| learning_rate | 0.000155 | +| loss | -0.0534 | +| n_updates | 4448 | +| policy_gradient_loss | -0.0358 | +| value_loss | 0.000258 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.198 | +| time/ | | +| fps | 1323 | +| iterations | 1114 | +| time_elapsed | 1723 | +| total_timesteps | 2281472 | +| train/ | | +| approx_kl | 0.039748512 | +| clip_fraction | 0.416 | +| clip_range | 0.122 | +| entropy_loss | -7.36 | +| explained_variance | -0.423 | +| learning_rate | 0.000155 | +| loss | -0.0702 | +| n_updates | 4452 | +| policy_gradient_loss | -0.0431 | +| value_loss | 7.68e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.196 | +| time/ | | +| fps | 1323 | +| iterations | 1115 | +| time_elapsed | 1724 | +| total_timesteps | 2283520 | +| train/ | | +| approx_kl | 0.043988127 | +| clip_fraction | 0.399 | +| clip_range | 0.121 | +| entropy_loss | -7.32 | +| explained_variance | -0.0917 | +| learning_rate | 0.000155 | +| loss | -0.0606 | +| n_updates | 4456 | +| policy_gradient_loss | -0.0338 | +| value_loss | 0.000132 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.199 | +| time/ | | +| fps | 1323 | +| iterations | 1116 | +| time_elapsed | 1726 | +| total_timesteps | 2285568 | +| train/ | | +| approx_kl | 0.033907074 | +| clip_fraction | 0.382 | +| clip_range | 0.121 | +| entropy_loss | -7.28 | +| explained_variance | -0.0389 | +| learning_rate | 0.000155 | +| loss | -0.0502 | +| n_updates | 4460 | +| policy_gradient_loss | -0.0295 | +| value_loss | 0.000163 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.201 | +| time/ | | +| fps | 1324 | +| iterations | 1117 | +| time_elapsed | 1727 | +| total_timesteps | 2287616 | +| train/ | | +| approx_kl | 0.040221427 | +| clip_fraction | 0.408 | +| clip_range | 0.121 | +| entropy_loss | -7.27 | +| explained_variance | -0.0513 | +| learning_rate | 0.000155 | +| loss | -0.0539 | +| n_updates | 4464 | +| policy_gradient_loss | -0.031 | +| value_loss | 0.000239 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.208 | +| time/ | | +| fps | 1324 | +| iterations | 1118 | +| time_elapsed | 1729 | +| total_timesteps | 2289664 | +| train/ | | +| approx_kl | 0.039268337 | +| clip_fraction | 0.401 | +| clip_range | 0.121 | +| entropy_loss | -7.21 | +| explained_variance | -0.348 | +| learning_rate | 0.000155 | +| loss | -0.0611 | +| n_updates | 4468 | +| policy_gradient_loss | -0.0383 | +| value_loss | 0.00011 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.197 | +| time/ | | +| fps | 1324 | +| iterations | 1119 | +| time_elapsed | 1730 | +| total_timesteps | 2291712 | +| train/ | | +| approx_kl | 0.044157088 | +| clip_fraction | 0.382 | +| clip_range | 0.121 | +| entropy_loss | -7.23 | +| explained_variance | -0.0972 | +| learning_rate | 0.000155 | +| loss | -0.0553 | +| n_updates | 4472 | +| policy_gradient_loss | -0.0325 | +| value_loss | 0.00019 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.194 | +| time/ | | +| fps | 1324 | +| iterations | 1120 | +| time_elapsed | 1732 | +| total_timesteps | 2293760 | +| train/ | | +| approx_kl | 0.03693662 | +| clip_fraction | 0.389 | +| clip_range | 0.121 | +| entropy_loss | -7.14 | +| explained_variance | -0.19 | +| learning_rate | 0.000155 | +| loss | -0.0665 | +| n_updates | 4476 | +| policy_gradient_loss | -0.0381 | +| value_loss | 0.000133 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.194 | +| time/ | | +| fps | 1324 | +| iterations | 1121 | +| time_elapsed | 1733 | +| total_timesteps | 2295808 | +| train/ | | +| approx_kl | 0.042038124 | +| clip_fraction | 0.42 | +| clip_range | 0.121 | +| entropy_loss | -7.13 | +| explained_variance | -0.503 | +| learning_rate | 0.000155 | +| loss | -0.0721 | +| n_updates | 4480 | +| policy_gradient_loss | -0.0415 | +| value_loss | 7.53e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.19 | +| time/ | | +| fps | 1324 | +| iterations | 1122 | +| time_elapsed | 1735 | +| total_timesteps | 2297856 | +| train/ | | +| approx_kl | 0.044637047 | +| clip_fraction | 0.401 | +| clip_range | 0.121 | +| entropy_loss | -7.25 | +| explained_variance | -0.171 | +| learning_rate | 0.000155 | +| loss | -0.0552 | +| n_updates | 4484 | +| policy_gradient_loss | -0.029 | +| value_loss | 0.000185 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.193 | +| time/ | | +| fps | 1324 | +| iterations | 1123 | +| time_elapsed | 1736 | +| total_timesteps | 2299904 | +| train/ | | +| approx_kl | 0.04127873 | +| clip_fraction | 0.405 | +| clip_range | 0.121 | +| entropy_loss | -7.17 | +| explained_variance | -0.0596 | +| learning_rate | 0.000155 | +| loss | -0.0559 | +| n_updates | 4488 | +| policy_gradient_loss | -0.0337 | +| value_loss | 0.000136 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.193 | +| time/ | | +| fps | 1324 | +| iterations | 1124 | +| time_elapsed | 1738 | +| total_timesteps | 2301952 | +| train/ | | +| approx_kl | 0.043453053 | +| clip_fraction | 0.401 | +| clip_range | 0.121 | +| entropy_loss | -7.33 | +| explained_variance | -0.071 | +| learning_rate | 0.000154 | +| loss | -0.0644 | +| n_updates | 4492 | +| policy_gradient_loss | -0.0313 | +| value_loss | 0.000292 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.193 | +| time/ | | +| fps | 1324 | +| iterations | 1125 | +| time_elapsed | 1739 | +| total_timesteps | 2304000 | +| train/ | | +| approx_kl | 0.040773302 | +| clip_fraction | 0.408 | +| clip_range | 0.121 | +| entropy_loss | -7.15 | +| explained_variance | -0.272 | +| learning_rate | 0.000154 | +| loss | -0.0588 | +| n_updates | 4496 | +| policy_gradient_loss | -0.0411 | +| value_loss | 0.000109 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.197 | +| time/ | | +| fps | 1324 | +| iterations | 1126 | +| time_elapsed | 1740 | +| total_timesteps | 2306048 | +| train/ | | +| approx_kl | 0.035970405 | +| clip_fraction | 0.4 | +| clip_range | 0.121 | +| entropy_loss | -7.12 | +| explained_variance | -0.427 | +| learning_rate | 0.000154 | +| loss | -0.0563 | +| n_updates | 4500 | +| policy_gradient_loss | -0.0378 | +| value_loss | 0.000164 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.198 | +| time/ | | +| fps | 1324 | +| iterations | 1127 | +| time_elapsed | 1742 | +| total_timesteps | 2308096 | +| train/ | | +| approx_kl | 0.03522855 | +| clip_fraction | 0.391 | +| clip_range | 0.121 | +| entropy_loss | -6.98 | +| explained_variance | -0.0586 | +| learning_rate | 0.000154 | +| loss | -0.0558 | +| n_updates | 4504 | +| policy_gradient_loss | -0.0321 | +| value_loss | 0.000215 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.197 | +| time/ | | +| fps | 1324 | +| iterations | 1128 | +| time_elapsed | 1743 | +| total_timesteps | 2310144 | +| train/ | | +| approx_kl | 0.037520103 | +| clip_fraction | 0.434 | +| clip_range | 0.121 | +| entropy_loss | -7.14 | +| explained_variance | -0.0853 | +| learning_rate | 0.000154 | +| loss | -0.0512 | +| n_updates | 4508 | +| policy_gradient_loss | -0.0398 | +| value_loss | 7.64e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.203 | +| time/ | | +| fps | 1324 | +| iterations | 1129 | +| time_elapsed | 1745 | +| total_timesteps | 2312192 | +| train/ | | +| approx_kl | 0.040631425 | +| clip_fraction | 0.416 | +| clip_range | 0.121 | +| entropy_loss | -7.22 | +| explained_variance | -0.329 | +| learning_rate | 0.000154 | +| loss | -0.0603 | +| n_updates | 4512 | +| policy_gradient_loss | -0.0354 | +| value_loss | 7.06e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.205 | +| time/ | | +| fps | 1324 | +| iterations | 1130 | +| time_elapsed | 1746 | +| total_timesteps | 2314240 | +| train/ | | +| approx_kl | 0.042061593 | +| clip_fraction | 0.391 | +| clip_range | 0.121 | +| entropy_loss | -7.14 | +| explained_variance | -0.0363 | +| learning_rate | 0.000154 | +| loss | -0.055 | +| n_updates | 4516 | +| policy_gradient_loss | -0.0314 | +| value_loss | 0.000284 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.2 | +| time/ | | +| fps | 1324 | +| iterations | 1131 | +| time_elapsed | 1748 | +| total_timesteps | 2316288 | +| train/ | | +| approx_kl | 0.03933737 | +| clip_fraction | 0.401 | +| clip_range | 0.121 | +| entropy_loss | -7.26 | +| explained_variance | -0.0969 | +| learning_rate | 0.000154 | +| loss | -0.0516 | +| n_updates | 4520 | +| policy_gradient_loss | -0.0324 | +| value_loss | 0.000295 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.201 | +| time/ | | +| fps | 1324 | +| iterations | 1132 | +| time_elapsed | 1749 | +| total_timesteps | 2318336 | +| train/ | | +| approx_kl | 0.03788314 | +| clip_fraction | 0.405 | +| clip_range | 0.121 | +| entropy_loss | -7.28 | +| explained_variance | -0.0258 | +| learning_rate | 0.000154 | +| loss | -0.0577 | +| n_updates | 4524 | +| policy_gradient_loss | -0.0335 | +| value_loss | 0.000224 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.203 | +| time/ | | +| fps | 1324 | +| iterations | 1133 | +| time_elapsed | 1751 | +| total_timesteps | 2320384 | +| train/ | | +| approx_kl | 0.040438578 | +| clip_fraction | 0.4 | +| clip_range | 0.121 | +| entropy_loss | -7.24 | +| explained_variance | -0.0798 | +| learning_rate | 0.000154 | +| loss | -0.0691 | +| n_updates | 4528 | +| policy_gradient_loss | -0.036 | +| value_loss | 0.000298 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.203 | +| time/ | | +| fps | 1324 | +| iterations | 1134 | +| time_elapsed | 1752 | +| total_timesteps | 2322432 | +| train/ | | +| approx_kl | 0.040036857 | +| clip_fraction | 0.355 | +| clip_range | 0.121 | +| entropy_loss | -7.34 | +| explained_variance | -0.157 | +| learning_rate | 0.000154 | +| loss | -0.0573 | +| n_updates | 4532 | +| policy_gradient_loss | -0.0343 | +| value_loss | 0.000247 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.209 | +| time/ | | +| fps | 1325 | +| iterations | 1135 | +| time_elapsed | 1754 | +| total_timesteps | 2324480 | +| train/ | | +| approx_kl | 0.037868187 | +| clip_fraction | 0.397 | +| clip_range | 0.121 | +| entropy_loss | -7.4 | +| explained_variance | -0.22 | +| learning_rate | 0.000154 | +| loss | -0.0584 | +| n_updates | 4536 | +| policy_gradient_loss | -0.0392 | +| value_loss | 0.000156 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.202 | +| time/ | | +| fps | 1325 | +| iterations | 1136 | +| time_elapsed | 1755 | +| total_timesteps | 2326528 | +| train/ | | +| approx_kl | 0.04326684 | +| clip_fraction | 0.423 | +| clip_range | 0.121 | +| entropy_loss | -7.3 | +| explained_variance | -0.0969 | +| learning_rate | 0.000154 | +| loss | -0.0439 | +| n_updates | 4540 | +| policy_gradient_loss | -0.0344 | +| value_loss | 0.000274 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.206 | +| time/ | | +| fps | 1325 | +| iterations | 1137 | +| time_elapsed | 1757 | +| total_timesteps | 2328576 | +| train/ | | +| approx_kl | 0.042531885 | +| clip_fraction | 0.427 | +| clip_range | 0.121 | +| entropy_loss | -7.33 | +| explained_variance | -0.16 | +| learning_rate | 0.000154 | +| loss | -0.0538 | +| n_updates | 4544 | +| policy_gradient_loss | -0.0367 | +| value_loss | 0.000173 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.206 | +| time/ | | +| fps | 1325 | +| iterations | 1138 | +| time_elapsed | 1758 | +| total_timesteps | 2330624 | +| train/ | | +| approx_kl | 0.0403489 | +| clip_fraction | 0.398 | +| clip_range | 0.121 | +| entropy_loss | -7.34 | +| explained_variance | -0.12 | +| learning_rate | 0.000154 | +| loss | -0.0448 | +| n_updates | 4548 | +| policy_gradient_loss | -0.0286 | +| value_loss | 0.000326 | +--------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.205 | +| time/ | | +| fps | 1325 | +| iterations | 1139 | +| time_elapsed | 1760 | +| total_timesteps | 2332672 | +| train/ | | +| approx_kl | 0.04588476 | +| clip_fraction | 0.406 | +| clip_range | 0.121 | +| entropy_loss | -7.37 | +| explained_variance | -0.114 | +| learning_rate | 0.000154 | +| loss | -0.0604 | +| n_updates | 4552 | +| policy_gradient_loss | -0.0384 | +| value_loss | 0.000166 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.205 | +| time/ | | +| fps | 1325 | +| iterations | 1140 | +| time_elapsed | 1761 | +| total_timesteps | 2334720 | +| train/ | | +| approx_kl | 0.039615996 | +| clip_fraction | 0.394 | +| clip_range | 0.121 | +| entropy_loss | -7.24 | +| explained_variance | -0.12 | +| learning_rate | 0.000154 | +| loss | -0.0643 | +| n_updates | 4556 | +| policy_gradient_loss | -0.0371 | +| value_loss | 0.000187 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.204 | +| time/ | | +| fps | 1325 | +| iterations | 1141 | +| time_elapsed | 1763 | +| total_timesteps | 2336768 | +| train/ | | +| approx_kl | 0.042530403 | +| clip_fraction | 0.401 | +| clip_range | 0.121 | +| entropy_loss | -7.26 | +| explained_variance | -0.178 | +| learning_rate | 0.000154 | +| loss | -0.0623 | +| n_updates | 4560 | +| policy_gradient_loss | -0.0417 | +| value_loss | 7.84e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.222 | +| time/ | | +| fps | 1325 | +| iterations | 1142 | +| time_elapsed | 1764 | +| total_timesteps | 2338816 | +| train/ | | +| approx_kl | 0.040633064 | +| clip_fraction | 0.41 | +| clip_range | 0.121 | +| entropy_loss | -7.14 | +| explained_variance | -0.0988 | +| learning_rate | 0.000154 | +| loss | -0.061 | +| n_updates | 4564 | +| policy_gradient_loss | -0.0353 | +| value_loss | 0.000214 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.225 | +| time/ | | +| fps | 1325 | +| iterations | 1143 | +| time_elapsed | 1766 | +| total_timesteps | 2340864 | +| train/ | | +| approx_kl | 0.038612895 | +| clip_fraction | 0.382 | +| clip_range | 0.121 | +| entropy_loss | -7.23 | +| explained_variance | -0.1 | +| learning_rate | 0.000154 | +| loss | -0.0521 | +| n_updates | 4568 | +| policy_gradient_loss | -0.0306 | +| value_loss | 0.000212 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.22 | +| time/ | | +| fps | 1325 | +| iterations | 1144 | +| time_elapsed | 1767 | +| total_timesteps | 2342912 | +| train/ | | +| approx_kl | 0.03994281 | +| clip_fraction | 0.409 | +| clip_range | 0.121 | +| entropy_loss | -7.3 | +| explained_variance | -0.133 | +| learning_rate | 0.000154 | +| loss | -0.0476 | +| n_updates | 4572 | +| policy_gradient_loss | -0.033 | +| value_loss | 0.000161 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.22 | +| time/ | | +| fps | 1325 | +| iterations | 1145 | +| time_elapsed | 1769 | +| total_timesteps | 2344960 | +| train/ | | +| approx_kl | 0.037714783 | +| clip_fraction | 0.403 | +| clip_range | 0.121 | +| entropy_loss | -7.23 | +| explained_variance | -0.0757 | +| learning_rate | 0.000154 | +| loss | -0.0616 | +| n_updates | 4576 | +| policy_gradient_loss | -0.0353 | +| value_loss | 0.000169 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.224 | +| time/ | | +| fps | 1325 | +| iterations | 1146 | +| time_elapsed | 1770 | +| total_timesteps | 2347008 | +| train/ | | +| approx_kl | 0.039840076 | +| clip_fraction | 0.375 | +| clip_range | 0.121 | +| entropy_loss | -7.3 | +| explained_variance | -0.125 | +| learning_rate | 0.000154 | +| loss | -0.0596 | +| n_updates | 4580 | +| policy_gradient_loss | -0.0322 | +| value_loss | 0.000155 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.224 | +| time/ | | +| fps | 1325 | +| iterations | 1147 | +| time_elapsed | 1772 | +| total_timesteps | 2349056 | +| train/ | | +| approx_kl | 0.036005184 | +| clip_fraction | 0.372 | +| clip_range | 0.121 | +| entropy_loss | -7.3 | +| explained_variance | 0.00542 | +| learning_rate | 0.000154 | +| loss | -0.0592 | +| n_updates | 4584 | +| policy_gradient_loss | -0.033 | +| value_loss | 0.000166 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.224 | +| time/ | | +| fps | 1325 | +| iterations | 1148 | +| time_elapsed | 1773 | +| total_timesteps | 2351104 | +| train/ | | +| approx_kl | 0.036644906 | +| clip_fraction | 0.406 | +| clip_range | 0.121 | +| entropy_loss | -7.29 | +| explained_variance | -0.0831 | +| learning_rate | 0.000153 | +| loss | -0.053 | +| n_updates | 4588 | +| policy_gradient_loss | -0.0341 | +| value_loss | 0.000201 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.232 | +| time/ | | +| fps | 1325 | +| iterations | 1149 | +| time_elapsed | 1775 | +| total_timesteps | 2353152 | +| train/ | | +| approx_kl | 0.030256432 | +| clip_fraction | 0.397 | +| clip_range | 0.121 | +| entropy_loss | -7.26 | +| explained_variance | -0.12 | +| learning_rate | 0.000153 | +| loss | -0.0565 | +| n_updates | 4592 | +| policy_gradient_loss | -0.0333 | +| value_loss | 0.000235 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.229 | +| time/ | | +| fps | 1325 | +| iterations | 1150 | +| time_elapsed | 1776 | +| total_timesteps | 2355200 | +| train/ | | +| approx_kl | 0.02559841 | +| clip_fraction | 0.349 | +| clip_range | 0.121 | +| entropy_loss | -7.33 | +| explained_variance | -0.00212 | +| learning_rate | 0.000153 | +| loss | -0.0389 | +| n_updates | 4596 | +| policy_gradient_loss | -0.0239 | +| value_loss | 0.00034 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.229 | +| time/ | | +| fps | 1325 | +| iterations | 1151 | +| time_elapsed | 1778 | +| total_timesteps | 2357248 | +| train/ | | +| approx_kl | 0.033885423 | +| clip_fraction | 0.38 | +| clip_range | 0.121 | +| entropy_loss | -7.16 | +| explained_variance | -0.0548 | +| learning_rate | 0.000153 | +| loss | -0.0505 | +| n_updates | 4600 | +| policy_gradient_loss | -0.0308 | +| value_loss | 0.000183 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.229 | +| time/ | | +| fps | 1325 | +| iterations | 1152 | +| time_elapsed | 1779 | +| total_timesteps | 2359296 | +| train/ | | +| approx_kl | 0.036021274 | +| clip_fraction | 0.352 | +| clip_range | 0.121 | +| entropy_loss | -7.34 | +| explained_variance | -0.165 | +| learning_rate | 0.000153 | +| loss | -0.0548 | +| n_updates | 4604 | +| policy_gradient_loss | -0.0305 | +| value_loss | 0.00026 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.238 | +| time/ | | +| fps | 1325 | +| iterations | 1153 | +| time_elapsed | 1781 | +| total_timesteps | 2361344 | +| train/ | | +| approx_kl | 0.041778497 | +| clip_fraction | 0.393 | +| clip_range | 0.121 | +| entropy_loss | -7.4 | +| explained_variance | -0.0913 | +| learning_rate | 0.000153 | +| loss | -0.0595 | +| n_updates | 4608 | +| policy_gradient_loss | -0.0377 | +| value_loss | 0.000204 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.239 | +| time/ | | +| fps | 1325 | +| iterations | 1154 | +| time_elapsed | 1782 | +| total_timesteps | 2363392 | +| train/ | | +| approx_kl | 0.041440792 | +| clip_fraction | 0.376 | +| clip_range | 0.12 | +| entropy_loss | -7.31 | +| explained_variance | -0.223 | +| learning_rate | 0.000153 | +| loss | -0.0532 | +| n_updates | 4612 | +| policy_gradient_loss | -0.0334 | +| value_loss | 0.000237 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.244 | +| time/ | | +| fps | 1325 | +| iterations | 1155 | +| time_elapsed | 1784 | +| total_timesteps | 2365440 | +| train/ | | +| approx_kl | 0.038401607 | +| clip_fraction | 0.401 | +| clip_range | 0.12 | +| entropy_loss | -7.25 | +| explained_variance | -0.171 | +| learning_rate | 0.000153 | +| loss | -0.0557 | +| n_updates | 4616 | +| policy_gradient_loss | -0.0373 | +| value_loss | 0.000126 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.24 | +| time/ | | +| fps | 1325 | +| iterations | 1156 | +| time_elapsed | 1785 | +| total_timesteps | 2367488 | +| train/ | | +| approx_kl | 0.03594423 | +| clip_fraction | 0.385 | +| clip_range | 0.12 | +| entropy_loss | -7.34 | +| explained_variance | -0.124 | +| learning_rate | 0.000153 | +| loss | -0.0501 | +| n_updates | 4620 | +| policy_gradient_loss | -0.0349 | +| value_loss | 0.000185 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.24 | +| time/ | | +| fps | 1325 | +| iterations | 1157 | +| time_elapsed | 1787 | +| total_timesteps | 2369536 | +| train/ | | +| approx_kl | 0.036355093 | +| clip_fraction | 0.366 | +| clip_range | 0.12 | +| entropy_loss | -7.3 | +| explained_variance | -0.0617 | +| learning_rate | 0.000153 | +| loss | -0.0386 | +| n_updates | 4624 | +| policy_gradient_loss | -0.0287 | +| value_loss | 0.000245 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.245 | +| time/ | | +| fps | 1325 | +| iterations | 1158 | +| time_elapsed | 1788 | +| total_timesteps | 2371584 | +| train/ | | +| approx_kl | 0.038384516 | +| clip_fraction | 0.392 | +| clip_range | 0.12 | +| entropy_loss | -7.28 | +| explained_variance | -0.148 | +| learning_rate | 0.000153 | +| loss | -0.0552 | +| n_updates | 4628 | +| policy_gradient_loss | -0.0387 | +| value_loss | 0.000107 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.245 | +| time/ | | +| fps | 1325 | +| iterations | 1159 | +| time_elapsed | 1790 | +| total_timesteps | 2373632 | +| train/ | | +| approx_kl | 0.028780565 | +| clip_fraction | 0.362 | +| clip_range | 0.12 | +| entropy_loss | -7.19 | +| explained_variance | -0.00573 | +| learning_rate | 0.000153 | +| loss | -0.0555 | +| n_updates | 4632 | +| policy_gradient_loss | -0.0294 | +| value_loss | 0.000366 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.251 | +| time/ | | +| fps | 1326 | +| iterations | 1160 | +| time_elapsed | 1791 | +| total_timesteps | 2375680 | +| train/ | | +| approx_kl | 0.030688612 | +| clip_fraction | 0.383 | +| clip_range | 0.12 | +| entropy_loss | -7.36 | +| explained_variance | -0.265 | +| learning_rate | 0.000153 | +| loss | -0.0597 | +| n_updates | 4636 | +| policy_gradient_loss | -0.0344 | +| value_loss | 0.000157 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.248 | +| time/ | | +| fps | 1326 | +| iterations | 1161 | +| time_elapsed | 1792 | +| total_timesteps | 2377728 | +| train/ | | +| approx_kl | 0.035300337 | +| clip_fraction | 0.373 | +| clip_range | 0.12 | +| entropy_loss | -7.28 | +| explained_variance | -0.258 | +| learning_rate | 0.000153 | +| loss | -0.0616 | +| n_updates | 4640 | +| policy_gradient_loss | -0.0356 | +| value_loss | 0.000138 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.251 | +| time/ | | +| fps | 1326 | +| iterations | 1162 | +| time_elapsed | 1794 | +| total_timesteps | 2379776 | +| train/ | | +| approx_kl | 0.03471906 | +| clip_fraction | 0.394 | +| clip_range | 0.12 | +| entropy_loss | -7.3 | +| explained_variance | -0.0653 | +| learning_rate | 0.000153 | +| loss | -0.0477 | +| n_updates | 4644 | +| policy_gradient_loss | -0.0306 | +| value_loss | 0.000159 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.251 | +| time/ | | +| fps | 1326 | +| iterations | 1163 | +| time_elapsed | 1795 | +| total_timesteps | 2381824 | +| train/ | | +| approx_kl | 0.04066755 | +| clip_fraction | 0.381 | +| clip_range | 0.12 | +| entropy_loss | -7.24 | +| explained_variance | -0.193 | +| learning_rate | 0.000153 | +| loss | -0.0566 | +| n_updates | 4648 | +| policy_gradient_loss | -0.0349 | +| value_loss | 0.000245 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.256 | +| time/ | | +| fps | 1326 | +| iterations | 1164 | +| time_elapsed | 1797 | +| total_timesteps | 2383872 | +| train/ | | +| approx_kl | 0.03705833 | +| clip_fraction | 0.379 | +| clip_range | 0.12 | +| entropy_loss | -7.29 | +| explained_variance | -0.344 | +| learning_rate | 0.000153 | +| loss | -0.0625 | +| n_updates | 4652 | +| policy_gradient_loss | -0.0366 | +| value_loss | 0.000147 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.264 | +| time/ | | +| fps | 1326 | +| iterations | 1165 | +| time_elapsed | 1798 | +| total_timesteps | 2385920 | +| train/ | | +| approx_kl | 0.037700653 | +| clip_fraction | 0.43 | +| clip_range | 0.12 | +| entropy_loss | -7.15 | +| explained_variance | -0.0878 | +| learning_rate | 0.000153 | +| loss | -0.0518 | +| n_updates | 4656 | +| policy_gradient_loss | -0.0348 | +| value_loss | 0.000115 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.264 | +| time/ | | +| fps | 1326 | +| iterations | 1166 | +| time_elapsed | 1800 | +| total_timesteps | 2387968 | +| train/ | | +| approx_kl | 0.041568004 | +| clip_fraction | 0.424 | +| clip_range | 0.12 | +| entropy_loss | -7.15 | +| explained_variance | -0.153 | +| learning_rate | 0.000153 | +| loss | -0.0528 | +| n_updates | 4660 | +| policy_gradient_loss | -0.033 | +| value_loss | 0.000135 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.263 | +| time/ | | +| fps | 1326 | +| iterations | 1167 | +| time_elapsed | 1801 | +| total_timesteps | 2390016 | +| train/ | | +| approx_kl | 0.032888133 | +| clip_fraction | 0.362 | +| clip_range | 0.12 | +| entropy_loss | -7.24 | +| explained_variance | -0.0764 | +| learning_rate | 0.000153 | +| loss | -0.0578 | +| n_updates | 4664 | +| policy_gradient_loss | -0.0314 | +| value_loss | 0.000161 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.266 | +| time/ | | +| fps | 1326 | +| iterations | 1168 | +| time_elapsed | 1803 | +| total_timesteps | 2392064 | +| train/ | | +| approx_kl | 0.03608089 | +| clip_fraction | 0.418 | +| clip_range | 0.12 | +| entropy_loss | -7.31 | +| explained_variance | -0.204 | +| learning_rate | 0.000153 | +| loss | -0.0517 | +| n_updates | 4668 | +| policy_gradient_loss | -0.0356 | +| value_loss | 0.000118 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.266 | +| time/ | | +| fps | 1326 | +| iterations | 1169 | +| time_elapsed | 1804 | +| total_timesteps | 2394112 | +| train/ | | +| approx_kl | 0.03258244 | +| clip_fraction | 0.345 | +| clip_range | 0.12 | +| entropy_loss | -7.25 | +| explained_variance | -0.183 | +| learning_rate | 0.000153 | +| loss | -0.0459 | +| n_updates | 4672 | +| policy_gradient_loss | -0.0265 | +| value_loss | 0.000227 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.266 | +| time/ | | +| fps | 1326 | +| iterations | 1170 | +| time_elapsed | 1806 | +| total_timesteps | 2396160 | +| train/ | | +| approx_kl | 0.04099593 | +| clip_fraction | 0.411 | +| clip_range | 0.12 | +| entropy_loss | -7.34 | +| explained_variance | -0.113 | +| learning_rate | 0.000153 | +| loss | -0.0595 | +| n_updates | 4676 | +| policy_gradient_loss | -0.0346 | +| value_loss | 0.000242 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.267 | +| time/ | | +| fps | 1326 | +| iterations | 1171 | +| time_elapsed | 1807 | +| total_timesteps | 2398208 | +| train/ | | +| approx_kl | 0.038361546 | +| clip_fraction | 0.402 | +| clip_range | 0.12 | +| entropy_loss | -7.21 | +| explained_variance | -0.33 | +| learning_rate | 0.000153 | +| loss | -0.0486 | +| n_updates | 4680 | +| policy_gradient_loss | -0.0347 | +| value_loss | 0.00015 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.277 | +| time/ | | +| fps | 1326 | +| iterations | 1172 | +| time_elapsed | 1809 | +| total_timesteps | 2400256 | +| train/ | | +| approx_kl | 0.041560084 | +| clip_fraction | 0.405 | +| clip_range | 0.12 | +| entropy_loss | -7.26 | +| explained_variance | -0.0359 | +| learning_rate | 0.000153 | +| loss | -0.0594 | +| n_updates | 4684 | +| policy_gradient_loss | -0.0338 | +| value_loss | 0.000136 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.267 | +| time/ | | +| fps | 1326 | +| iterations | 1173 | +| time_elapsed | 1810 | +| total_timesteps | 2402304 | +| train/ | | +| approx_kl | 0.035966933 | +| clip_fraction | 0.386 | +| clip_range | 0.12 | +| entropy_loss | -7.21 | +| explained_variance | -0.0703 | +| learning_rate | 0.000152 | +| loss | -0.0592 | +| n_updates | 4688 | +| policy_gradient_loss | -0.033 | +| value_loss | 0.000266 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.267 | +| time/ | | +| fps | 1326 | +| iterations | 1174 | +| time_elapsed | 1812 | +| total_timesteps | 2404352 | +| train/ | | +| approx_kl | 0.035625543 | +| clip_fraction | 0.408 | +| clip_range | 0.12 | +| entropy_loss | -7.15 | +| explained_variance | -0.121 | +| learning_rate | 0.000152 | +| loss | -0.0604 | +| n_updates | 4692 | +| policy_gradient_loss | -0.031 | +| value_loss | 0.000281 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.267 | +| time/ | | +| fps | 1326 | +| iterations | 1175 | +| time_elapsed | 1813 | +| total_timesteps | 2406400 | +| train/ | | +| approx_kl | 0.038059674 | +| clip_fraction | 0.41 | +| clip_range | 0.12 | +| entropy_loss | -7.07 | +| explained_variance | -0.351 | +| learning_rate | 0.000152 | +| loss | -0.0705 | +| n_updates | 4696 | +| policy_gradient_loss | -0.04 | +| value_loss | 0.000131 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.267 | +| time/ | | +| fps | 1326 | +| iterations | 1176 | +| time_elapsed | 1814 | +| total_timesteps | 2408448 | +| train/ | | +| approx_kl | 0.040259838 | +| clip_fraction | 0.405 | +| clip_range | 0.12 | +| entropy_loss | -7.04 | +| explained_variance | -0.572 | +| learning_rate | 0.000152 | +| loss | -0.0588 | +| n_updates | 4700 | +| policy_gradient_loss | -0.0374 | +| value_loss | 0.000104 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.271 | +| time/ | | +| fps | 1327 | +| iterations | 1177 | +| time_elapsed | 1816 | +| total_timesteps | 2410496 | +| train/ | | +| approx_kl | 0.03574159 | +| clip_fraction | 0.401 | +| clip_range | 0.12 | +| entropy_loss | -7.09 | +| explained_variance | -0.176 | +| learning_rate | 0.000152 | +| loss | -0.0548 | +| n_updates | 4704 | +| policy_gradient_loss | -0.0333 | +| value_loss | 0.000153 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.273 | +| time/ | | +| fps | 1327 | +| iterations | 1178 | +| time_elapsed | 1817 | +| total_timesteps | 2412544 | +| train/ | | +| approx_kl | 0.030645125 | +| clip_fraction | 0.395 | +| clip_range | 0.12 | +| entropy_loss | -7.04 | +| explained_variance | -0.0388 | +| learning_rate | 0.000152 | +| loss | -0.0503 | +| n_updates | 4708 | +| policy_gradient_loss | -0.0266 | +| value_loss | 0.000164 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.284 | +| time/ | | +| fps | 1327 | +| iterations | 1179 | +| time_elapsed | 1819 | +| total_timesteps | 2414592 | +| train/ | | +| approx_kl | 0.038548023 | +| clip_fraction | 0.413 | +| clip_range | 0.12 | +| entropy_loss | -7.08 | +| explained_variance | -0.137 | +| learning_rate | 0.000152 | +| loss | -0.0619 | +| n_updates | 4712 | +| policy_gradient_loss | -0.0334 | +| value_loss | 0.000166 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 1327 | +| iterations | 1180 | +| time_elapsed | 1820 | +| total_timesteps | 2416640 | +| train/ | | +| approx_kl | 0.034551293 | +| clip_fraction | 0.38 | +| clip_range | 0.12 | +| entropy_loss | -7.21 | +| explained_variance | -0.0495 | +| learning_rate | 0.000152 | +| loss | -0.0445 | +| n_updates | 4716 | +| policy_gradient_loss | -0.0289 | +| value_loss | 0.000198 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.28 | +| time/ | | +| fps | 1327 | +| iterations | 1181 | +| time_elapsed | 1822 | +| total_timesteps | 2418688 | +| train/ | | +| approx_kl | 0.040241733 | +| clip_fraction | 0.403 | +| clip_range | 0.12 | +| entropy_loss | -7.23 | +| explained_variance | -0.132 | +| learning_rate | 0.000152 | +| loss | -0.0721 | +| n_updates | 4720 | +| policy_gradient_loss | -0.0358 | +| value_loss | 0.000107 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.285 | +| time/ | | +| fps | 1327 | +| iterations | 1182 | +| time_elapsed | 1823 | +| total_timesteps | 2420736 | +| train/ | | +| approx_kl | 0.04594978 | +| clip_fraction | 0.395 | +| clip_range | 0.12 | +| entropy_loss | -7.07 | +| explained_variance | -0.165 | +| learning_rate | 0.000152 | +| loss | -0.0464 | +| n_updates | 4724 | +| policy_gradient_loss | -0.0322 | +| value_loss | 0.000175 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.29 | +| time/ | | +| fps | 1327 | +| iterations | 1183 | +| time_elapsed | 1825 | +| total_timesteps | 2422784 | +| train/ | | +| approx_kl | 0.046200067 | +| clip_fraction | 0.413 | +| clip_range | 0.12 | +| entropy_loss | -7.17 | +| explained_variance | -0.237 | +| learning_rate | 0.000152 | +| loss | -0.0626 | +| n_updates | 4728 | +| policy_gradient_loss | -0.0368 | +| value_loss | 0.000146 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.29 | +| time/ | | +| fps | 1327 | +| iterations | 1184 | +| time_elapsed | 1826 | +| total_timesteps | 2424832 | +| train/ | | +| approx_kl | 0.04475829 | +| clip_fraction | 0.406 | +| clip_range | 0.12 | +| entropy_loss | -7.15 | +| explained_variance | -0.14 | +| learning_rate | 0.000152 | +| loss | -0.0546 | +| n_updates | 4732 | +| policy_gradient_loss | -0.0313 | +| value_loss | 0.00026 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.291 | +| time/ | | +| fps | 1327 | +| iterations | 1185 | +| time_elapsed | 1828 | +| total_timesteps | 2426880 | +| train/ | | +| approx_kl | 0.043811932 | +| clip_fraction | 0.392 | +| clip_range | 0.12 | +| entropy_loss | -7.14 | +| explained_variance | -0.238 | +| learning_rate | 0.000152 | +| loss | -0.062 | +| n_updates | 4736 | +| policy_gradient_loss | -0.0348 | +| value_loss | 0.000174 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.294 | +| time/ | | +| fps | 1327 | +| iterations | 1186 | +| time_elapsed | 1829 | +| total_timesteps | 2428928 | +| train/ | | +| approx_kl | 0.041355293 | +| clip_fraction | 0.437 | +| clip_range | 0.12 | +| entropy_loss | -7.06 | +| explained_variance | -0.22 | +| learning_rate | 0.000152 | +| loss | -0.0647 | +| n_updates | 4740 | +| policy_gradient_loss | -0.0348 | +| value_loss | 0.000126 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.289 | +| time/ | | +| fps | 1327 | +| iterations | 1187 | +| time_elapsed | 1831 | +| total_timesteps | 2430976 | +| train/ | | +| approx_kl | 0.038421266 | +| clip_fraction | 0.417 | +| clip_range | 0.12 | +| entropy_loss | -7.07 | +| explained_variance | -0.00254 | +| learning_rate | 0.000152 | +| loss | -0.0507 | +| n_updates | 4744 | +| policy_gradient_loss | -0.0314 | +| value_loss | 0.00028 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 1327 | +| iterations | 1188 | +| time_elapsed | 1832 | +| total_timesteps | 2433024 | +| train/ | | +| approx_kl | 0.047331057 | +| clip_fraction | 0.44 | +| clip_range | 0.12 | +| entropy_loss | -7.05 | +| explained_variance | -0.196 | +| learning_rate | 0.000152 | +| loss | -0.0694 | +| n_updates | 4748 | +| policy_gradient_loss | -0.0413 | +| value_loss | 9.96e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 1327 | +| iterations | 1189 | +| time_elapsed | 1834 | +| total_timesteps | 2435072 | +| train/ | | +| approx_kl | 0.04584803 | +| clip_fraction | 0.407 | +| clip_range | 0.12 | +| entropy_loss | -7.04 | +| explained_variance | -0.0241 | +| learning_rate | 0.000152 | +| loss | -0.0481 | +| n_updates | 4752 | +| policy_gradient_loss | -0.0306 | +| value_loss | 0.000274 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 1327 | +| iterations | 1190 | +| time_elapsed | 1835 | +| total_timesteps | 2437120 | +| train/ | | +| approx_kl | 0.040953375 | +| clip_fraction | 0.417 | +| clip_range | 0.12 | +| entropy_loss | -7.14 | +| explained_variance | -0.147 | +| learning_rate | 0.000152 | +| loss | -0.0488 | +| n_updates | 4756 | +| policy_gradient_loss | -0.0354 | +| value_loss | 0.00016 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.281 | +| time/ | | +| fps | 1327 | +| iterations | 1191 | +| time_elapsed | 1836 | +| total_timesteps | 2439168 | +| train/ | | +| approx_kl | 0.040776275 | +| clip_fraction | 0.41 | +| clip_range | 0.12 | +| entropy_loss | -7.06 | +| explained_variance | -0.337 | +| learning_rate | 0.000152 | +| loss | -0.0665 | +| n_updates | 4760 | +| policy_gradient_loss | -0.0399 | +| value_loss | 8.56e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.278 | +| time/ | | +| fps | 1327 | +| iterations | 1192 | +| time_elapsed | 1838 | +| total_timesteps | 2441216 | +| train/ | | +| approx_kl | 0.03712997 | +| clip_fraction | 0.387 | +| clip_range | 0.12 | +| entropy_loss | -6.97 | +| explained_variance | -0.159 | +| learning_rate | 0.000152 | +| loss | -0.0546 | +| n_updates | 4764 | +| policy_gradient_loss | -0.0326 | +| value_loss | 0.000223 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.278 | +| time/ | | +| fps | 1328 | +| iterations | 1193 | +| time_elapsed | 1839 | +| total_timesteps | 2443264 | +| train/ | | +| approx_kl | 0.038906824 | +| clip_fraction | 0.414 | +| clip_range | 0.119 | +| entropy_loss | -7.02 | +| explained_variance | -0.167 | +| learning_rate | 0.000152 | +| loss | -0.0556 | +| n_updates | 4768 | +| policy_gradient_loss | -0.0349 | +| value_loss | 0.00015 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.28 | +| time/ | | +| fps | 1328 | +| iterations | 1194 | +| time_elapsed | 1841 | +| total_timesteps | 2445312 | +| train/ | | +| approx_kl | 0.04130637 | +| clip_fraction | 0.42 | +| clip_range | 0.119 | +| entropy_loss | -7.09 | +| explained_variance | -0.166 | +| learning_rate | 0.000152 | +| loss | -0.0533 | +| n_updates | 4772 | +| policy_gradient_loss | -0.0323 | +| value_loss | 0.000195 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.28 | +| time/ | | +| fps | 1328 | +| iterations | 1195 | +| time_elapsed | 1842 | +| total_timesteps | 2447360 | +| train/ | | +| approx_kl | 0.03987645 | +| clip_fraction | 0.397 | +| clip_range | 0.119 | +| entropy_loss | -7.14 | +| explained_variance | -0.0864 | +| learning_rate | 0.000152 | +| loss | -0.0465 | +| n_updates | 4776 | +| policy_gradient_loss | -0.0267 | +| value_loss | 0.00025 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 1328 | +| iterations | 1196 | +| time_elapsed | 1844 | +| total_timesteps | 2449408 | +| train/ | | +| approx_kl | 0.043640025 | +| clip_fraction | 0.415 | +| clip_range | 0.119 | +| entropy_loss | -7.14 | +| explained_variance | -0.258 | +| learning_rate | 0.000152 | +| loss | -0.0531 | +| n_updates | 4780 | +| policy_gradient_loss | -0.0343 | +| value_loss | 0.000189 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.274 | +| time/ | | +| fps | 1328 | +| iterations | 1197 | +| time_elapsed | 1845 | +| total_timesteps | 2451456 | +| train/ | | +| approx_kl | 0.049062565 | +| clip_fraction | 0.435 | +| clip_range | 0.119 | +| entropy_loss | -7.01 | +| explained_variance | -0.268 | +| learning_rate | 0.000152 | +| loss | -0.059 | +| n_updates | 4784 | +| policy_gradient_loss | -0.0398 | +| value_loss | 9.89e-05 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.274 | +| time/ | | +| fps | 1328 | +| iterations | 1198 | +| time_elapsed | 1847 | +| total_timesteps | 2453504 | +| train/ | | +| approx_kl | 0.0397724 | +| clip_fraction | 0.455 | +| clip_range | 0.119 | +| entropy_loss | -7.02 | +| explained_variance | -0.074 | +| learning_rate | 0.000151 | +| loss | -0.052 | +| n_updates | 4788 | +| policy_gradient_loss | -0.0322 | +| value_loss | 0.000121 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.266 | +| time/ | | +| fps | 1328 | +| iterations | 1199 | +| time_elapsed | 1848 | +| total_timesteps | 2455552 | +| train/ | | +| approx_kl | 0.045451507 | +| clip_fraction | 0.406 | +| clip_range | 0.119 | +| entropy_loss | -6.98 | +| explained_variance | -0.145 | +| learning_rate | 0.000151 | +| loss | -0.0568 | +| n_updates | 4792 | +| policy_gradient_loss | -0.0336 | +| value_loss | 0.00025 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.266 | +| time/ | | +| fps | 1328 | +| iterations | 1200 | +| time_elapsed | 1849 | +| total_timesteps | 2457600 | +| train/ | | +| approx_kl | 0.040861495 | +| clip_fraction | 0.414 | +| clip_range | 0.119 | +| entropy_loss | -7.06 | +| explained_variance | -0.0714 | +| learning_rate | 0.000151 | +| loss | -0.0648 | +| n_updates | 4796 | +| policy_gradient_loss | -0.032 | +| value_loss | 0.000165 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.268 | +| time/ | | +| fps | 1328 | +| iterations | 1201 | +| time_elapsed | 1851 | +| total_timesteps | 2459648 | +| train/ | | +| approx_kl | 0.04288576 | +| clip_fraction | 0.411 | +| clip_range | 0.119 | +| entropy_loss | -7.23 | +| explained_variance | -0.223 | +| learning_rate | 0.000151 | +| loss | -0.054 | +| n_updates | 4800 | +| policy_gradient_loss | -0.037 | +| value_loss | 0.000131 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.268 | +| time/ | | +| fps | 1328 | +| iterations | 1202 | +| time_elapsed | 1852 | +| total_timesteps | 2461696 | +| train/ | | +| approx_kl | 0.03485153 | +| clip_fraction | 0.389 | +| clip_range | 0.119 | +| entropy_loss | -7.25 | +| explained_variance | -0.191 | +| learning_rate | 0.000151 | +| loss | -0.0509 | +| n_updates | 4804 | +| policy_gradient_loss | -0.0333 | +| value_loss | 0.000142 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.267 | +| time/ | | +| fps | 1328 | +| iterations | 1203 | +| time_elapsed | 1854 | +| total_timesteps | 2463744 | +| train/ | | +| approx_kl | 0.032155097 | +| clip_fraction | 0.387 | +| clip_range | 0.119 | +| entropy_loss | -7.13 | +| explained_variance | -0.19 | +| learning_rate | 0.000151 | +| loss | -0.0481 | +| n_updates | 4808 | +| policy_gradient_loss | -0.0279 | +| value_loss | 0.000172 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.266 | +| time/ | | +| fps | 1328 | +| iterations | 1204 | +| time_elapsed | 1855 | +| total_timesteps | 2465792 | +| train/ | | +| approx_kl | 0.04131262 | +| clip_fraction | 0.39 | +| clip_range | 0.119 | +| entropy_loss | -7.16 | +| explained_variance | 0.00267 | +| learning_rate | 0.000151 | +| loss | -0.0528 | +| n_updates | 4812 | +| policy_gradient_loss | -0.0361 | +| value_loss | 9.22e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.265 | +| time/ | | +| fps | 1328 | +| iterations | 1205 | +| time_elapsed | 1857 | +| total_timesteps | 2467840 | +| train/ | | +| approx_kl | 0.039050955 | +| clip_fraction | 0.366 | +| clip_range | 0.119 | +| entropy_loss | -7.1 | +| explained_variance | -0.0721 | +| learning_rate | 0.000151 | +| loss | -0.0542 | +| n_updates | 4816 | +| policy_gradient_loss | -0.0317 | +| value_loss | 0.000143 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.262 | +| time/ | | +| fps | 1328 | +| iterations | 1206 | +| time_elapsed | 1858 | +| total_timesteps | 2469888 | +| train/ | | +| approx_kl | 0.041611075 | +| clip_fraction | 0.403 | +| clip_range | 0.119 | +| entropy_loss | -7.15 | +| explained_variance | -0.0862 | +| learning_rate | 0.000151 | +| loss | -0.053 | +| n_updates | 4820 | +| policy_gradient_loss | -0.0336 | +| value_loss | 0.000198 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.268 | +| time/ | | +| fps | 1328 | +| iterations | 1207 | +| time_elapsed | 1860 | +| total_timesteps | 2471936 | +| train/ | | +| approx_kl | 0.03625398 | +| clip_fraction | 0.382 | +| clip_range | 0.119 | +| entropy_loss | -7.03 | +| explained_variance | -0.00415 | +| learning_rate | 0.000151 | +| loss | -0.0503 | +| n_updates | 4824 | +| policy_gradient_loss | -0.032 | +| value_loss | 0.000309 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.268 | +| time/ | | +| fps | 1328 | +| iterations | 1208 | +| time_elapsed | 1861 | +| total_timesteps | 2473984 | +| train/ | | +| approx_kl | 0.039046954 | +| clip_fraction | 0.415 | +| clip_range | 0.119 | +| entropy_loss | -7.17 | +| explained_variance | -0.355 | +| learning_rate | 0.000151 | +| loss | -0.0608 | +| n_updates | 4828 | +| policy_gradient_loss | -0.0341 | +| value_loss | 0.000282 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.269 | +| time/ | | +| fps | 1329 | +| iterations | 1209 | +| time_elapsed | 1863 | +| total_timesteps | 2476032 | +| train/ | | +| approx_kl | 0.04993722 | +| clip_fraction | 0.427 | +| clip_range | 0.119 | +| entropy_loss | -7.25 | +| explained_variance | -0.158 | +| learning_rate | 0.000151 | +| loss | -0.0662 | +| n_updates | 4832 | +| policy_gradient_loss | -0.0371 | +| value_loss | 0.000133 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.274 | +| time/ | | +| fps | 1329 | +| iterations | 1210 | +| time_elapsed | 1864 | +| total_timesteps | 2478080 | +| train/ | | +| approx_kl | 0.042564727 | +| clip_fraction | 0.37 | +| clip_range | 0.119 | +| entropy_loss | -7.25 | +| explained_variance | -0.0928 | +| learning_rate | 0.000151 | +| loss | -0.0545 | +| n_updates | 4836 | +| policy_gradient_loss | -0.0318 | +| value_loss | 0.000282 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.269 | +| time/ | | +| fps | 1329 | +| iterations | 1211 | +| time_elapsed | 1866 | +| total_timesteps | 2480128 | +| train/ | | +| approx_kl | 0.0362944 | +| clip_fraction | 0.376 | +| clip_range | 0.119 | +| entropy_loss | -7.19 | +| explained_variance | -0.143 | +| learning_rate | 0.000151 | +| loss | -0.0494 | +| n_updates | 4840 | +| policy_gradient_loss | -0.0324 | +| value_loss | 0.000312 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 1329 | +| iterations | 1212 | +| time_elapsed | 1867 | +| total_timesteps | 2482176 | +| train/ | | +| approx_kl | 0.038139507 | +| clip_fraction | 0.4 | +| clip_range | 0.119 | +| entropy_loss | -7.26 | +| explained_variance | -0.3 | +| learning_rate | 0.000151 | +| loss | -0.0575 | +| n_updates | 4844 | +| policy_gradient_loss | -0.042 | +| value_loss | 0.000105 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.264 | +| time/ | | +| fps | 1329 | +| iterations | 1213 | +| time_elapsed | 1868 | +| total_timesteps | 2484224 | +| train/ | | +| approx_kl | 0.035774123 | +| clip_fraction | 0.386 | +| clip_range | 0.119 | +| entropy_loss | -7.04 | +| explained_variance | 0.0102 | +| learning_rate | 0.000151 | +| loss | -0.0266 | +| n_updates | 4848 | +| policy_gradient_loss | -0.0253 | +| value_loss | 0.000366 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.265 | +| time/ | | +| fps | 1329 | +| iterations | 1214 | +| time_elapsed | 1870 | +| total_timesteps | 2486272 | +| train/ | | +| approx_kl | 0.034905165 | +| clip_fraction | 0.407 | +| clip_range | 0.119 | +| entropy_loss | -7.03 | +| explained_variance | -0.355 | +| learning_rate | 0.000151 | +| loss | -0.0615 | +| n_updates | 4852 | +| policy_gradient_loss | -0.0386 | +| value_loss | 0.000187 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.265 | +| time/ | | +| fps | 1329 | +| iterations | 1215 | +| time_elapsed | 1871 | +| total_timesteps | 2488320 | +| train/ | | +| approx_kl | 0.04200238 | +| clip_fraction | 0.392 | +| clip_range | 0.119 | +| entropy_loss | -7.17 | +| explained_variance | -0.19 | +| learning_rate | 0.000151 | +| loss | -0.058 | +| n_updates | 4856 | +| policy_gradient_loss | -0.033 | +| value_loss | 0.000181 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.269 | +| time/ | | +| fps | 1329 | +| iterations | 1216 | +| time_elapsed | 1873 | +| total_timesteps | 2490368 | +| train/ | | +| approx_kl | 0.041088346 | +| clip_fraction | 0.427 | +| clip_range | 0.119 | +| entropy_loss | -7.17 | +| explained_variance | -0.0826 | +| learning_rate | 0.000151 | +| loss | -0.0577 | +| n_updates | 4860 | +| policy_gradient_loss | -0.0342 | +| value_loss | 0.000136 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.261 | +| time/ | | +| fps | 1329 | +| iterations | 1217 | +| time_elapsed | 1874 | +| total_timesteps | 2492416 | +| train/ | | +| approx_kl | 0.039543144 | +| clip_fraction | 0.411 | +| clip_range | 0.119 | +| entropy_loss | -7.13 | +| explained_variance | -0.143 | +| learning_rate | 0.000151 | +| loss | -0.0626 | +| n_updates | 4864 | +| policy_gradient_loss | -0.0371 | +| value_loss | 8.27e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.262 | +| time/ | | +| fps | 1329 | +| iterations | 1218 | +| time_elapsed | 1876 | +| total_timesteps | 2494464 | +| train/ | | +| approx_kl | 0.04437186 | +| clip_fraction | 0.378 | +| clip_range | 0.119 | +| entropy_loss | -7.12 | +| explained_variance | -0.0206 | +| learning_rate | 0.000151 | +| loss | -0.0492 | +| n_updates | 4868 | +| policy_gradient_loss | -0.0294 | +| value_loss | 0.000247 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.265 | +| time/ | | +| fps | 1329 | +| iterations | 1219 | +| time_elapsed | 1877 | +| total_timesteps | 2496512 | +| train/ | | +| approx_kl | 0.041573398 | +| clip_fraction | 0.412 | +| clip_range | 0.119 | +| entropy_loss | -7.06 | +| explained_variance | -0.145 | +| learning_rate | 0.000151 | +| loss | -0.0583 | +| n_updates | 4872 | +| policy_gradient_loss | -0.0344 | +| value_loss | 0.000242 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.265 | +| time/ | | +| fps | 1329 | +| iterations | 1220 | +| time_elapsed | 1879 | +| total_timesteps | 2498560 | +| train/ | | +| approx_kl | 0.040413167 | +| clip_fraction | 0.408 | +| clip_range | 0.119 | +| entropy_loss | -7.14 | +| explained_variance | -0.0123 | +| learning_rate | 0.000151 | +| loss | -0.0696 | +| n_updates | 4876 | +| policy_gradient_loss | -0.0355 | +| value_loss | 0.000227 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.263 | +| time/ | | +| fps | 1329 | +| iterations | 1221 | +| time_elapsed | 1880 | +| total_timesteps | 2500608 | +| train/ | | +| approx_kl | 0.044013575 | +| clip_fraction | 0.429 | +| clip_range | 0.119 | +| entropy_loss | -7.11 | +| explained_variance | -0.291 | +| learning_rate | 0.000151 | +| loss | -0.0556 | +| n_updates | 4880 | +| policy_gradient_loss | -0.0406 | +| value_loss | 9.63e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.266 | +| time/ | | +| fps | 1329 | +| iterations | 1222 | +| time_elapsed | 1881 | +| total_timesteps | 2502656 | +| train/ | | +| approx_kl | 0.03692671 | +| clip_fraction | 0.41 | +| clip_range | 0.119 | +| entropy_loss | -7.04 | +| explained_variance | -0.0567 | +| learning_rate | 0.00015 | +| loss | -0.0489 | +| n_updates | 4884 | +| policy_gradient_loss | -0.0303 | +| value_loss | 0.000264 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.264 | +| time/ | | +| fps | 1329 | +| iterations | 1223 | +| time_elapsed | 1883 | +| total_timesteps | 2504704 | +| train/ | | +| approx_kl | 0.040366836 | +| clip_fraction | 0.408 | +| clip_range | 0.119 | +| entropy_loss | -7.13 | +| explained_variance | -0.166 | +| learning_rate | 0.00015 | +| loss | -0.0578 | +| n_updates | 4888 | +| policy_gradient_loss | -0.0373 | +| value_loss | 0.000227 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.264 | +| time/ | | +| fps | 1329 | +| iterations | 1224 | +| time_elapsed | 1884 | +| total_timesteps | 2506752 | +| train/ | | +| approx_kl | 0.04221419 | +| clip_fraction | 0.396 | +| clip_range | 0.119 | +| entropy_loss | -7.1 | +| explained_variance | -0.128 | +| learning_rate | 0.00015 | +| loss | -0.0582 | +| n_updates | 4892 | +| policy_gradient_loss | -0.0342 | +| value_loss | 0.000219 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.278 | +| time/ | | +| fps | 1329 | +| iterations | 1225 | +| time_elapsed | 1886 | +| total_timesteps | 2508800 | +| train/ | | +| approx_kl | 0.045631565 | +| clip_fraction | 0.406 | +| clip_range | 0.119 | +| entropy_loss | -7.19 | +| explained_variance | -0.133 | +| learning_rate | 0.00015 | +| loss | -0.0512 | +| n_updates | 4896 | +| policy_gradient_loss | -0.0326 | +| value_loss | 0.000163 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.274 | +| time/ | | +| fps | 1329 | +| iterations | 1226 | +| time_elapsed | 1887 | +| total_timesteps | 2510848 | +| train/ | | +| approx_kl | 0.04144623 | +| clip_fraction | 0.422 | +| clip_range | 0.119 | +| entropy_loss | -7.14 | +| explained_variance | -0.129 | +| learning_rate | 0.00015 | +| loss | -0.0435 | +| n_updates | 4900 | +| policy_gradient_loss | -0.0309 | +| value_loss | 0.000209 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.273 | +| time/ | | +| fps | 1330 | +| iterations | 1227 | +| time_elapsed | 1889 | +| total_timesteps | 2512896 | +| train/ | | +| approx_kl | 0.041527763 | +| clip_fraction | 0.375 | +| clip_range | 0.119 | +| entropy_loss | -7.2 | +| explained_variance | -0.117 | +| learning_rate | 0.00015 | +| loss | -0.0532 | +| n_updates | 4904 | +| policy_gradient_loss | -0.0331 | +| value_loss | 0.000271 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.273 | +| time/ | | +| fps | 1330 | +| iterations | 1228 | +| time_elapsed | 1890 | +| total_timesteps | 2514944 | +| train/ | | +| approx_kl | 0.044065356 | +| clip_fraction | 0.395 | +| clip_range | 0.119 | +| entropy_loss | -7.16 | +| explained_variance | -0.169 | +| learning_rate | 0.00015 | +| loss | -0.0532 | +| n_updates | 4908 | +| policy_gradient_loss | -0.036 | +| value_loss | 0.000166 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.276 | +| time/ | | +| fps | 1330 | +| iterations | 1229 | +| time_elapsed | 1892 | +| total_timesteps | 2516992 | +| train/ | | +| approx_kl | 0.039790116 | +| clip_fraction | 0.413 | +| clip_range | 0.119 | +| entropy_loss | -7.33 | +| explained_variance | -0.329 | +| learning_rate | 0.00015 | +| loss | -0.0548 | +| n_updates | 4912 | +| policy_gradient_loss | -0.0339 | +| value_loss | 0.00015 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.274 | +| time/ | | +| fps | 1330 | +| iterations | 1230 | +| time_elapsed | 1893 | +| total_timesteps | 2519040 | +| train/ | | +| approx_kl | 0.04263409 | +| clip_fraction | 0.409 | +| clip_range | 0.119 | +| entropy_loss | -7.21 | +| explained_variance | -0.0352 | +| learning_rate | 0.00015 | +| loss | -0.0595 | +| n_updates | 4916 | +| policy_gradient_loss | -0.0371 | +| value_loss | 0.000131 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.278 | +| time/ | | +| fps | 1330 | +| iterations | 1231 | +| time_elapsed | 1895 | +| total_timesteps | 2521088 | +| train/ | | +| approx_kl | 0.048367187 | +| clip_fraction | 0.404 | +| clip_range | 0.119 | +| entropy_loss | -7.22 | +| explained_variance | -0.28 | +| learning_rate | 0.00015 | +| loss | -0.0523 | +| n_updates | 4920 | +| policy_gradient_loss | -0.0345 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.278 | +| time/ | | +| fps | 1330 | +| iterations | 1232 | +| time_elapsed | 1896 | +| total_timesteps | 2523136 | +| train/ | | +| approx_kl | 0.044799477 | +| clip_fraction | 0.376 | +| clip_range | 0.118 | +| entropy_loss | -7.22 | +| explained_variance | -0.0604 | +| learning_rate | 0.00015 | +| loss | -0.0588 | +| n_updates | 4924 | +| policy_gradient_loss | -0.0317 | +| value_loss | 0.000338 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.281 | +| time/ | | +| fps | 1330 | +| iterations | 1233 | +| time_elapsed | 1898 | +| total_timesteps | 2525184 | +| train/ | | +| approx_kl | 0.043442074 | +| clip_fraction | 0.4 | +| clip_range | 0.118 | +| entropy_loss | -7.21 | +| explained_variance | -0.176 | +| learning_rate | 0.00015 | +| loss | -0.0521 | +| n_updates | 4928 | +| policy_gradient_loss | -0.0349 | +| value_loss | 0.000164 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.288 | +| time/ | | +| fps | 1330 | +| iterations | 1234 | +| time_elapsed | 1899 | +| total_timesteps | 2527232 | +| train/ | | +| approx_kl | 0.038921237 | +| clip_fraction | 0.398 | +| clip_range | 0.118 | +| entropy_loss | -7.31 | +| explained_variance | -0.126 | +| learning_rate | 0.00015 | +| loss | -0.0565 | +| n_updates | 4932 | +| policy_gradient_loss | -0.0337 | +| value_loss | 0.000223 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 1330 | +| iterations | 1235 | +| time_elapsed | 1901 | +| total_timesteps | 2529280 | +| train/ | | +| approx_kl | 0.035661396 | +| clip_fraction | 0.402 | +| clip_range | 0.118 | +| entropy_loss | -7.31 | +| explained_variance | -0.122 | +| learning_rate | 0.00015 | +| loss | -0.0589 | +| n_updates | 4936 | +| policy_gradient_loss | -0.036 | +| value_loss | 0.000131 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.28 | +| time/ | | +| fps | 1330 | +| iterations | 1236 | +| time_elapsed | 1902 | +| total_timesteps | 2531328 | +| train/ | | +| approx_kl | 0.03352144 | +| clip_fraction | 0.362 | +| clip_range | 0.118 | +| entropy_loss | -7.32 | +| explained_variance | -0.00549 | +| learning_rate | 0.00015 | +| loss | -0.0538 | +| n_updates | 4940 | +| policy_gradient_loss | -0.032 | +| value_loss | 0.000285 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.28 | +| time/ | | +| fps | 1330 | +| iterations | 1237 | +| time_elapsed | 1904 | +| total_timesteps | 2533376 | +| train/ | | +| approx_kl | 0.042909227 | +| clip_fraction | 0.403 | +| clip_range | 0.118 | +| entropy_loss | -7.33 | +| explained_variance | -0.197 | +| learning_rate | 0.00015 | +| loss | -0.0625 | +| n_updates | 4944 | +| policy_gradient_loss | -0.0386 | +| value_loss | 0.000188 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 1330 | +| iterations | 1238 | +| time_elapsed | 1905 | +| total_timesteps | 2535424 | +| train/ | | +| approx_kl | 0.038056474 | +| clip_fraction | 0.38 | +| clip_range | 0.118 | +| entropy_loss | -7.38 | +| explained_variance | -0.0329 | +| learning_rate | 0.00015 | +| loss | -0.0568 | +| n_updates | 4948 | +| policy_gradient_loss | -0.0343 | +| value_loss | 0.000194 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.29 | +| time/ | | +| fps | 1330 | +| iterations | 1239 | +| time_elapsed | 1907 | +| total_timesteps | 2537472 | +| train/ | | +| approx_kl | 0.03753801 | +| clip_fraction | 0.354 | +| clip_range | 0.118 | +| entropy_loss | -7.32 | +| explained_variance | -0.139 | +| learning_rate | 0.00015 | +| loss | -0.0454 | +| n_updates | 4952 | +| policy_gradient_loss | -0.033 | +| value_loss | 0.000173 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.29 | +| time/ | | +| fps | 1330 | +| iterations | 1240 | +| time_elapsed | 1908 | +| total_timesteps | 2539520 | +| train/ | | +| approx_kl | 0.035313554 | +| clip_fraction | 0.376 | +| clip_range | 0.118 | +| entropy_loss | -7.23 | +| explained_variance | 0.0092 | +| learning_rate | 0.00015 | +| loss | -0.0503 | +| n_updates | 4956 | +| policy_gradient_loss | -0.0276 | +| value_loss | 0.000356 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.29 | +| time/ | | +| fps | 1330 | +| iterations | 1241 | +| time_elapsed | 1910 | +| total_timesteps | 2541568 | +| train/ | | +| approx_kl | 0.039515685 | +| clip_fraction | 0.408 | +| clip_range | 0.118 | +| entropy_loss | -7.26 | +| explained_variance | -0.398 | +| learning_rate | 0.00015 | +| loss | -0.0666 | +| n_updates | 4960 | +| policy_gradient_loss | -0.0395 | +| value_loss | 0.000173 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.286 | +| time/ | | +| fps | 1330 | +| iterations | 1242 | +| time_elapsed | 1911 | +| total_timesteps | 2543616 | +| train/ | | +| approx_kl | 0.036959253 | +| clip_fraction | 0.391 | +| clip_range | 0.118 | +| entropy_loss | -7.12 | +| explained_variance | -0.273 | +| learning_rate | 0.00015 | +| loss | -0.0582 | +| n_updates | 4964 | +| policy_gradient_loss | -0.0362 | +| value_loss | 0.000101 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.286 | +| time/ | | +| fps | 1330 | +| iterations | 1243 | +| time_elapsed | 1913 | +| total_timesteps | 2545664 | +| train/ | | +| approx_kl | 0.041535158 | +| clip_fraction | 0.394 | +| clip_range | 0.118 | +| entropy_loss | -7.24 | +| explained_variance | -0.153 | +| learning_rate | 0.00015 | +| loss | -0.0599 | +| n_updates | 4968 | +| policy_gradient_loss | -0.0337 | +| value_loss | 0.000172 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.291 | +| time/ | | +| fps | 1330 | +| iterations | 1244 | +| time_elapsed | 1914 | +| total_timesteps | 2547712 | +| train/ | | +| approx_kl | 0.043040127 | +| clip_fraction | 0.392 | +| clip_range | 0.118 | +| entropy_loss | -7.23 | +| explained_variance | -0.101 | +| learning_rate | 0.00015 | +| loss | -0.0604 | +| n_updates | 4972 | +| policy_gradient_loss | -0.035 | +| value_loss | 0.000123 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.292 | +| time/ | | +| fps | 1330 | +| iterations | 1245 | +| time_elapsed | 1916 | +| total_timesteps | 2549760 | +| train/ | | +| approx_kl | 0.039048977 | +| clip_fraction | 0.4 | +| clip_range | 0.118 | +| entropy_loss | -7.19 | +| explained_variance | 0.0192 | +| learning_rate | 0.00015 | +| loss | -0.054 | +| n_updates | 4976 | +| policy_gradient_loss | -0.0362 | +| value_loss | 0.000243 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.292 | +| time/ | | +| fps | 1330 | +| iterations | 1246 | +| time_elapsed | 1917 | +| total_timesteps | 2551808 | +| train/ | | +| approx_kl | 0.03832963 | +| clip_fraction | 0.396 | +| clip_range | 0.118 | +| entropy_loss | -7.26 | +| explained_variance | -0.128 | +| learning_rate | 0.00015 | +| loss | -0.0557 | +| n_updates | 4980 | +| policy_gradient_loss | -0.0354 | +| value_loss | 0.000251 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 1330 | +| iterations | 1247 | +| time_elapsed | 1919 | +| total_timesteps | 2553856 | +| train/ | | +| approx_kl | 0.040578075 | +| clip_fraction | 0.406 | +| clip_range | 0.118 | +| entropy_loss | -7.26 | +| explained_variance | -0.332 | +| learning_rate | 0.000149 | +| loss | -0.0476 | +| n_updates | 4984 | +| policy_gradient_loss | -0.0345 | +| value_loss | 0.000118 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.289 | +| time/ | | +| fps | 1330 | +| iterations | 1248 | +| time_elapsed | 1920 | +| total_timesteps | 2555904 | +| train/ | | +| approx_kl | 0.03721613 | +| clip_fraction | 0.37 | +| clip_range | 0.118 | +| entropy_loss | -7.27 | +| explained_variance | -0.178 | +| learning_rate | 0.000149 | +| loss | -0.0535 | +| n_updates | 4988 | +| policy_gradient_loss | -0.0343 | +| value_loss | 0.00018 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.289 | +| time/ | | +| fps | 1330 | +| iterations | 1249 | +| time_elapsed | 1922 | +| total_timesteps | 2557952 | +| train/ | | +| approx_kl | 0.038404703 | +| clip_fraction | 0.374 | +| clip_range | 0.118 | +| entropy_loss | -7.38 | +| explained_variance | -0.137 | +| learning_rate | 0.000149 | +| loss | -0.0494 | +| n_updates | 4992 | +| policy_gradient_loss | -0.0333 | +| value_loss | 0.000185 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.293 | +| time/ | | +| fps | 1330 | +| iterations | 1250 | +| time_elapsed | 1923 | +| total_timesteps | 2560000 | +| train/ | | +| approx_kl | 0.04041058 | +| clip_fraction | 0.393 | +| clip_range | 0.118 | +| entropy_loss | -7.32 | +| explained_variance | -0.0825 | +| learning_rate | 0.000149 | +| loss | -0.0606 | +| n_updates | 4996 | +| policy_gradient_loss | -0.0354 | +| value_loss | 9.42e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.287 | +| time/ | | +| fps | 1330 | +| iterations | 1251 | +| time_elapsed | 1924 | +| total_timesteps | 2562048 | +| train/ | | +| approx_kl | 0.039781854 | +| clip_fraction | 0.403 | +| clip_range | 0.118 | +| entropy_loss | -7.24 | +| explained_variance | -0.0501 | +| learning_rate | 0.000149 | +| loss | -0.0553 | +| n_updates | 5000 | +| policy_gradient_loss | -0.0349 | +| value_loss | 0.000133 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.287 | +| time/ | | +| fps | 1330 | +| iterations | 1252 | +| time_elapsed | 1926 | +| total_timesteps | 2564096 | +| train/ | | +| approx_kl | 0.04047039 | +| clip_fraction | 0.38 | +| clip_range | 0.118 | +| entropy_loss | -7.22 | +| explained_variance | -0.00225 | +| learning_rate | 0.000149 | +| loss | -0.0593 | +| n_updates | 5004 | +| policy_gradient_loss | -0.035 | +| value_loss | 0.000237 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.289 | +| time/ | | +| fps | 1331 | +| iterations | 1253 | +| time_elapsed | 1927 | +| total_timesteps | 2566144 | +| train/ | | +| approx_kl | 0.036164492 | +| clip_fraction | 0.363 | +| clip_range | 0.118 | +| entropy_loss | -7.38 | +| explained_variance | -0.102 | +| learning_rate | 0.000149 | +| loss | -0.0553 | +| n_updates | 5008 | +| policy_gradient_loss | -0.0317 | +| value_loss | 0.00019 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 1331 | +| iterations | 1254 | +| time_elapsed | 1929 | +| total_timesteps | 2568192 | +| train/ | | +| approx_kl | 0.03444281 | +| clip_fraction | 0.406 | +| clip_range | 0.118 | +| entropy_loss | -7.27 | +| explained_variance | -0.104 | +| learning_rate | 0.000149 | +| loss | -0.0556 | +| n_updates | 5012 | +| policy_gradient_loss | -0.0396 | +| value_loss | 0.000102 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.304 | +| time/ | | +| fps | 1331 | +| iterations | 1255 | +| time_elapsed | 1930 | +| total_timesteps | 2570240 | +| train/ | | +| approx_kl | 0.03831982 | +| clip_fraction | 0.365 | +| clip_range | 0.118 | +| entropy_loss | -7.21 | +| explained_variance | 0.00476 | +| learning_rate | 0.000149 | +| loss | -0.0442 | +| n_updates | 5016 | +| policy_gradient_loss | -0.0298 | +| value_loss | 0.00018 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1331 | +| iterations | 1256 | +| time_elapsed | 1932 | +| total_timesteps | 2572288 | +| train/ | | +| approx_kl | 0.032460816 | +| clip_fraction | 0.406 | +| clip_range | 0.118 | +| entropy_loss | -7.19 | +| explained_variance | -0.00488 | +| learning_rate | 0.000149 | +| loss | -0.0465 | +| n_updates | 5020 | +| policy_gradient_loss | -0.0311 | +| value_loss | 0.00024 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1331 | +| iterations | 1257 | +| time_elapsed | 1933 | +| total_timesteps | 2574336 | +| train/ | | +| approx_kl | 0.03463227 | +| clip_fraction | 0.375 | +| clip_range | 0.118 | +| entropy_loss | -7.28 | +| explained_variance | -0.109 | +| learning_rate | 0.000149 | +| loss | -0.0499 | +| n_updates | 5024 | +| policy_gradient_loss | -0.0318 | +| value_loss | 0.000291 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.315 | +| time/ | | +| fps | 1331 | +| iterations | 1258 | +| time_elapsed | 1935 | +| total_timesteps | 2576384 | +| train/ | | +| approx_kl | 0.03631032 | +| clip_fraction | 0.394 | +| clip_range | 0.118 | +| entropy_loss | -7.27 | +| explained_variance | -0.492 | +| learning_rate | 0.000149 | +| loss | -0.0557 | +| n_updates | 5028 | +| policy_gradient_loss | -0.0356 | +| value_loss | 0.0001 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.315 | +| time/ | | +| fps | 1331 | +| iterations | 1259 | +| time_elapsed | 1936 | +| total_timesteps | 2578432 | +| train/ | | +| approx_kl | 0.037523434 | +| clip_fraction | 0.391 | +| clip_range | 0.118 | +| entropy_loss | -7.27 | +| explained_variance | -0.116 | +| learning_rate | 0.000149 | +| loss | -0.0658 | +| n_updates | 5032 | +| policy_gradient_loss | -0.0373 | +| value_loss | 0.000293 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1331 | +| iterations | 1260 | +| time_elapsed | 1938 | +| total_timesteps | 2580480 | +| train/ | | +| approx_kl | 0.03829655 | +| clip_fraction | 0.409 | +| clip_range | 0.118 | +| entropy_loss | -7.2 | +| explained_variance | -0.313 | +| learning_rate | 0.000149 | +| loss | -0.0621 | +| n_updates | 5036 | +| policy_gradient_loss | -0.0366 | +| value_loss | 0.00011 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1331 | +| iterations | 1261 | +| time_elapsed | 1939 | +| total_timesteps | 2582528 | +| train/ | | +| approx_kl | 0.04167507 | +| clip_fraction | 0.389 | +| clip_range | 0.118 | +| entropy_loss | -7.12 | +| explained_variance | -0.158 | +| learning_rate | 0.000149 | +| loss | -0.0605 | +| n_updates | 5040 | +| policy_gradient_loss | -0.0339 | +| value_loss | 0.000117 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1331 | +| iterations | 1262 | +| time_elapsed | 1941 | +| total_timesteps | 2584576 | +| train/ | | +| approx_kl | 0.037741803 | +| clip_fraction | 0.404 | +| clip_range | 0.118 | +| entropy_loss | -7.07 | +| explained_variance | -0.257 | +| learning_rate | 0.000149 | +| loss | -0.064 | +| n_updates | 5044 | +| policy_gradient_loss | -0.0344 | +| value_loss | 9.05e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1331 | +| iterations | 1263 | +| time_elapsed | 1942 | +| total_timesteps | 2586624 | +| train/ | | +| approx_kl | 0.038126398 | +| clip_fraction | 0.376 | +| clip_range | 0.118 | +| entropy_loss | -7.18 | +| explained_variance | -0.00697 | +| learning_rate | 0.000149 | +| loss | -0.0442 | +| n_updates | 5048 | +| policy_gradient_loss | -0.0297 | +| value_loss | 0.000277 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1331 | +| iterations | 1264 | +| time_elapsed | 1944 | +| total_timesteps | 2588672 | +| train/ | | +| approx_kl | 0.04444155 | +| clip_fraction | 0.382 | +| clip_range | 0.118 | +| entropy_loss | -7.19 | +| explained_variance | -0.0489 | +| learning_rate | 0.000149 | +| loss | -0.0596 | +| n_updates | 5052 | +| policy_gradient_loss | -0.0338 | +| value_loss | 0.000229 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1331 | +| iterations | 1265 | +| time_elapsed | 1945 | +| total_timesteps | 2590720 | +| train/ | | +| approx_kl | 0.041350644 | +| clip_fraction | 0.417 | +| clip_range | 0.118 | +| entropy_loss | -7.26 | +| explained_variance | -0.766 | +| learning_rate | 0.000149 | +| loss | -0.0756 | +| n_updates | 5056 | +| policy_gradient_loss | -0.0417 | +| value_loss | 0.000133 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1331 | +| iterations | 1266 | +| time_elapsed | 1947 | +| total_timesteps | 2592768 | +| train/ | | +| approx_kl | 0.041390803 | +| clip_fraction | 0.43 | +| clip_range | 0.118 | +| entropy_loss | -7.2 | +| explained_variance | -0.187 | +| learning_rate | 0.000149 | +| loss | -0.058 | +| n_updates | 5060 | +| policy_gradient_loss | -0.0325 | +| value_loss | 0.000157 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1331 | +| iterations | 1267 | +| time_elapsed | 1948 | +| total_timesteps | 2594816 | +| train/ | | +| approx_kl | 0.034646817 | +| clip_fraction | 0.371 | +| clip_range | 0.118 | +| entropy_loss | -7.15 | +| explained_variance | -0.1 | +| learning_rate | 0.000149 | +| loss | -0.054 | +| n_updates | 5064 | +| policy_gradient_loss | -0.0323 | +| value_loss | 0.000206 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.315 | +| time/ | | +| fps | 1331 | +| iterations | 1268 | +| time_elapsed | 1950 | +| total_timesteps | 2596864 | +| train/ | | +| approx_kl | 0.03826805 | +| clip_fraction | 0.389 | +| clip_range | 0.118 | +| entropy_loss | -7.05 | +| explained_variance | 0.028 | +| learning_rate | 0.000149 | +| loss | -0.0515 | +| n_updates | 5068 | +| policy_gradient_loss | -0.0326 | +| value_loss | 0.000174 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.315 | +| time/ | | +| fps | 1331 | +| iterations | 1269 | +| time_elapsed | 1951 | +| total_timesteps | 2598912 | +| train/ | | +| approx_kl | 0.034377746 | +| clip_fraction | 0.38 | +| clip_range | 0.118 | +| entropy_loss | -7 | +| explained_variance | -0.0908 | +| learning_rate | 0.000149 | +| loss | -0.0527 | +| n_updates | 5072 | +| policy_gradient_loss | -0.0317 | +| value_loss | 0.000315 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1331 | +| iterations | 1270 | +| time_elapsed | 1953 | +| total_timesteps | 2600960 | +| train/ | | +| approx_kl | 0.042186365 | +| clip_fraction | 0.409 | +| clip_range | 0.118 | +| entropy_loss | -7.05 | +| explained_variance | 0.0868 | +| learning_rate | 0.000149 | +| loss | -0.0493 | +| n_updates | 5076 | +| policy_gradient_loss | -0.0323 | +| value_loss | 0.000194 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1331 | +| iterations | 1271 | +| time_elapsed | 1954 | +| total_timesteps | 2603008 | +| train/ | | +| approx_kl | 0.034136407 | +| clip_fraction | 0.383 | +| clip_range | 0.117 | +| entropy_loss | -7.11 | +| explained_variance | -0.256 | +| learning_rate | 0.000149 | +| loss | -0.0542 | +| n_updates | 5080 | +| policy_gradient_loss | -0.0303 | +| value_loss | 0.000231 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1331 | +| iterations | 1272 | +| time_elapsed | 1956 | +| total_timesteps | 2605056 | +| train/ | | +| approx_kl | 0.034201164 | +| clip_fraction | 0.402 | +| clip_range | 0.117 | +| entropy_loss | -7.04 | +| explained_variance | -0.151 | +| learning_rate | 0.000148 | +| loss | -0.055 | +| n_updates | 5084 | +| policy_gradient_loss | -0.0315 | +| value_loss | 0.000151 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1331 | +| iterations | 1273 | +| time_elapsed | 1957 | +| total_timesteps | 2607104 | +| train/ | | +| approx_kl | 0.036817864 | +| clip_fraction | 0.396 | +| clip_range | 0.117 | +| entropy_loss | -7.06 | +| explained_variance | -0.141 | +| learning_rate | 0.000148 | +| loss | -0.056 | +| n_updates | 5088 | +| policy_gradient_loss | -0.0338 | +| value_loss | 0.000159 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1331 | +| iterations | 1274 | +| time_elapsed | 1959 | +| total_timesteps | 2609152 | +| train/ | | +| approx_kl | 0.033641562 | +| clip_fraction | 0.379 | +| clip_range | 0.117 | +| entropy_loss | -7.04 | +| explained_variance | -0.0711 | +| learning_rate | 0.000148 | +| loss | -0.0501 | +| n_updates | 5092 | +| policy_gradient_loss | -0.0295 | +| value_loss | 0.0003 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1331 | +| iterations | 1275 | +| time_elapsed | 1960 | +| total_timesteps | 2611200 | +| train/ | | +| approx_kl | 0.03515904 | +| clip_fraction | 0.368 | +| clip_range | 0.117 | +| entropy_loss | -7.15 | +| explained_variance | -0.165 | +| learning_rate | 0.000148 | +| loss | -0.0535 | +| n_updates | 5096 | +| policy_gradient_loss | -0.0327 | +| value_loss | 0.000225 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.315 | +| time/ | | +| fps | 1331 | +| iterations | 1276 | +| time_elapsed | 1961 | +| total_timesteps | 2613248 | +| train/ | | +| approx_kl | 0.033009574 | +| clip_fraction | 0.389 | +| clip_range | 0.117 | +| entropy_loss | -7.21 | +| explained_variance | -0.122 | +| learning_rate | 0.000148 | +| loss | -0.0633 | +| n_updates | 5100 | +| policy_gradient_loss | -0.0352 | +| value_loss | 0.000113 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1331 | +| iterations | 1277 | +| time_elapsed | 1963 | +| total_timesteps | 2615296 | +| train/ | | +| approx_kl | 0.043087207 | +| clip_fraction | 0.39 | +| clip_range | 0.117 | +| entropy_loss | -7.15 | +| explained_variance | 0.0571 | +| learning_rate | 0.000148 | +| loss | -0.0532 | +| n_updates | 5104 | +| policy_gradient_loss | -0.0292 | +| value_loss | 0.000266 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1331 | +| iterations | 1278 | +| time_elapsed | 1964 | +| total_timesteps | 2617344 | +| train/ | | +| approx_kl | 0.040710963 | +| clip_fraction | 0.389 | +| clip_range | 0.117 | +| entropy_loss | -7.29 | +| explained_variance | 0.0631 | +| learning_rate | 0.000148 | +| loss | -0.0526 | +| n_updates | 5108 | +| policy_gradient_loss | -0.0341 | +| value_loss | 0.000216 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1332 | +| iterations | 1279 | +| time_elapsed | 1966 | +| total_timesteps | 2619392 | +| train/ | | +| approx_kl | 0.036604244 | +| clip_fraction | 0.391 | +| clip_range | 0.117 | +| entropy_loss | -7.18 | +| explained_variance | 0.00471 | +| learning_rate | 0.000148 | +| loss | -0.062 | +| n_updates | 5112 | +| policy_gradient_loss | -0.0319 | +| value_loss | 0.000211 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1332 | +| iterations | 1280 | +| time_elapsed | 1967 | +| total_timesteps | 2621440 | +| train/ | | +| approx_kl | 0.03531692 | +| clip_fraction | 0.388 | +| clip_range | 0.117 | +| entropy_loss | -7.15 | +| explained_variance | 0.0193 | +| learning_rate | 0.000148 | +| loss | -0.0514 | +| n_updates | 5116 | +| policy_gradient_loss | -0.0345 | +| value_loss | 0.000468 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1332 | +| iterations | 1281 | +| time_elapsed | 1969 | +| total_timesteps | 2623488 | +| train/ | | +| approx_kl | 0.03811352 | +| clip_fraction | 0.438 | +| clip_range | 0.117 | +| entropy_loss | -7.13 | +| explained_variance | -0.494 | +| learning_rate | 0.000148 | +| loss | -0.0773 | +| n_updates | 5120 | +| policy_gradient_loss | -0.0449 | +| value_loss | 0.00013 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1332 | +| iterations | 1282 | +| time_elapsed | 1970 | +| total_timesteps | 2625536 | +| train/ | | +| approx_kl | 0.039531104 | +| clip_fraction | 0.427 | +| clip_range | 0.117 | +| entropy_loss | -7.2 | +| explained_variance | -0.292 | +| learning_rate | 0.000148 | +| loss | -0.0614 | +| n_updates | 5124 | +| policy_gradient_loss | -0.0368 | +| value_loss | 0.000159 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1332 | +| iterations | 1283 | +| time_elapsed | 1972 | +| total_timesteps | 2627584 | +| train/ | | +| approx_kl | 0.03305267 | +| clip_fraction | 0.397 | +| clip_range | 0.117 | +| entropy_loss | -7.21 | +| explained_variance | -0.127 | +| learning_rate | 0.000148 | +| loss | -0.054 | +| n_updates | 5128 | +| policy_gradient_loss | -0.034 | +| value_loss | 0.000142 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1332 | +| iterations | 1284 | +| time_elapsed | 1973 | +| total_timesteps | 2629632 | +| train/ | | +| approx_kl | 0.042641453 | +| clip_fraction | 0.404 | +| clip_range | 0.117 | +| entropy_loss | -7.24 | +| explained_variance | -0.132 | +| learning_rate | 0.000148 | +| loss | -0.0576 | +| n_updates | 5132 | +| policy_gradient_loss | -0.0348 | +| value_loss | 0.000112 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1332 | +| iterations | 1285 | +| time_elapsed | 1975 | +| total_timesteps | 2631680 | +| train/ | | +| approx_kl | 0.043482166 | +| clip_fraction | 0.41 | +| clip_range | 0.117 | +| entropy_loss | -7.27 | +| explained_variance | 0.00908 | +| learning_rate | 0.000148 | +| loss | -0.0419 | +| n_updates | 5136 | +| policy_gradient_loss | -0.0305 | +| value_loss | 0.000174 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1332 | +| iterations | 1286 | +| time_elapsed | 1977 | +| total_timesteps | 2633728 | +| train/ | | +| approx_kl | 0.040282995 | +| clip_fraction | 0.394 | +| clip_range | 0.117 | +| entropy_loss | -7.21 | +| explained_variance | -0.249 | +| learning_rate | 0.000148 | +| loss | -0.062 | +| n_updates | 5140 | +| policy_gradient_loss | -0.0355 | +| value_loss | 0.000103 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1332 | +| iterations | 1287 | +| time_elapsed | 1978 | +| total_timesteps | 2635776 | +| train/ | | +| approx_kl | 0.03749915 | +| clip_fraction | 0.395 | +| clip_range | 0.117 | +| entropy_loss | -7.34 | +| explained_variance | -0.0261 | +| learning_rate | 0.000148 | +| loss | -0.0539 | +| n_updates | 5144 | +| policy_gradient_loss | -0.034 | +| value_loss | 0.000152 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1332 | +| iterations | 1288 | +| time_elapsed | 1979 | +| total_timesteps | 2637824 | +| train/ | | +| approx_kl | 0.044071138 | +| clip_fraction | 0.349 | +| clip_range | 0.117 | +| entropy_loss | -7.39 | +| explained_variance | -0.0567 | +| learning_rate | 0.000148 | +| loss | -0.0473 | +| n_updates | 5148 | +| policy_gradient_loss | -0.0291 | +| value_loss | 0.000254 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1332 | +| iterations | 1289 | +| time_elapsed | 1981 | +| total_timesteps | 2639872 | +| train/ | | +| approx_kl | 0.041518707 | +| clip_fraction | 0.414 | +| clip_range | 0.117 | +| entropy_loss | -7.32 | +| explained_variance | -0.13 | +| learning_rate | 0.000148 | +| loss | -0.0589 | +| n_updates | 5152 | +| policy_gradient_loss | -0.0377 | +| value_loss | 0.000153 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1332 | +| iterations | 1290 | +| time_elapsed | 1983 | +| total_timesteps | 2641920 | +| train/ | | +| approx_kl | 0.0331407 | +| clip_fraction | 0.369 | +| clip_range | 0.117 | +| entropy_loss | -7.23 | +| explained_variance | 0.0238 | +| learning_rate | 0.000148 | +| loss | -0.05 | +| n_updates | 5156 | +| policy_gradient_loss | -0.0299 | +| value_loss | 0.000216 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1332 | +| iterations | 1291 | +| time_elapsed | 1984 | +| total_timesteps | 2643968 | +| train/ | | +| approx_kl | 0.038504098 | +| clip_fraction | 0.384 | +| clip_range | 0.117 | +| entropy_loss | -7.22 | +| explained_variance | -0.0503 | +| learning_rate | 0.000148 | +| loss | -0.061 | +| n_updates | 5160 | +| policy_gradient_loss | -0.0332 | +| value_loss | 0.000202 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1332 | +| iterations | 1292 | +| time_elapsed | 1985 | +| total_timesteps | 2646016 | +| train/ | | +| approx_kl | 0.040278167 | +| clip_fraction | 0.405 | +| clip_range | 0.117 | +| entropy_loss | -7.15 | +| explained_variance | -0.163 | +| learning_rate | 0.000148 | +| loss | -0.0581 | +| n_updates | 5164 | +| policy_gradient_loss | -0.0358 | +| value_loss | 0.00019 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1332 | +| iterations | 1293 | +| time_elapsed | 1987 | +| total_timesteps | 2648064 | +| train/ | | +| approx_kl | 0.03982967 | +| clip_fraction | 0.424 | +| clip_range | 0.117 | +| entropy_loss | -7.27 | +| explained_variance | -0.173 | +| learning_rate | 0.000148 | +| loss | -0.0573 | +| n_updates | 5168 | +| policy_gradient_loss | -0.038 | +| value_loss | 0.000122 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1332 | +| iterations | 1294 | +| time_elapsed | 1988 | +| total_timesteps | 2650112 | +| train/ | | +| approx_kl | 0.042906415 | +| clip_fraction | 0.412 | +| clip_range | 0.117 | +| entropy_loss | -7.26 | +| explained_variance | -0.17 | +| learning_rate | 0.000148 | +| loss | -0.0648 | +| n_updates | 5172 | +| policy_gradient_loss | -0.0366 | +| value_loss | 0.000116 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1332 | +| iterations | 1295 | +| time_elapsed | 1990 | +| total_timesteps | 2652160 | +| train/ | | +| approx_kl | 0.05006057 | +| clip_fraction | 0.416 | +| clip_range | 0.117 | +| entropy_loss | -7.27 | +| explained_variance | -0.16 | +| learning_rate | 0.000148 | +| loss | -0.0529 | +| n_updates | 5176 | +| policy_gradient_loss | -0.0338 | +| value_loss | 0.000127 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1332 | +| iterations | 1296 | +| time_elapsed | 1991 | +| total_timesteps | 2654208 | +| train/ | | +| approx_kl | 0.04362213 | +| clip_fraction | 0.39 | +| clip_range | 0.117 | +| entropy_loss | -7.27 | +| explained_variance | -0.064 | +| learning_rate | 0.000147 | +| loss | -0.0453 | +| n_updates | 5180 | +| policy_gradient_loss | -0.0281 | +| value_loss | 0.000257 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.315 | +| time/ | | +| fps | 1332 | +| iterations | 1297 | +| time_elapsed | 1993 | +| total_timesteps | 2656256 | +| train/ | | +| approx_kl | 0.040195897 | +| clip_fraction | 0.403 | +| clip_range | 0.117 | +| entropy_loss | -7.26 | +| explained_variance | -0.0773 | +| learning_rate | 0.000147 | +| loss | -0.0588 | +| n_updates | 5184 | +| policy_gradient_loss | -0.0342 | +| value_loss | 0.000203 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1332 | +| iterations | 1298 | +| time_elapsed | 1995 | +| total_timesteps | 2658304 | +| train/ | | +| approx_kl | 0.04183348 | +| clip_fraction | 0.438 | +| clip_range | 0.117 | +| entropy_loss | -7.13 | +| explained_variance | -0.482 | +| learning_rate | 0.000147 | +| loss | -0.0616 | +| n_updates | 5188 | +| policy_gradient_loss | -0.0408 | +| value_loss | 8.09e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1332 | +| iterations | 1299 | +| time_elapsed | 1996 | +| total_timesteps | 2660352 | +| train/ | | +| approx_kl | 0.045877174 | +| clip_fraction | 0.399 | +| clip_range | 0.117 | +| entropy_loss | -7.2 | +| explained_variance | -0.0277 | +| learning_rate | 0.000147 | +| loss | -0.0514 | +| n_updates | 5192 | +| policy_gradient_loss | -0.031 | +| value_loss | 0.000226 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1332 | +| iterations | 1300 | +| time_elapsed | 1998 | +| total_timesteps | 2662400 | +| train/ | | +| approx_kl | 0.04054843 | +| clip_fraction | 0.421 | +| clip_range | 0.117 | +| entropy_loss | -7.33 | +| explained_variance | -0.0472 | +| learning_rate | 0.000147 | +| loss | -0.0548 | +| n_updates | 5196 | +| policy_gradient_loss | -0.0331 | +| value_loss | 0.00024 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1332 | +| iterations | 1301 | +| time_elapsed | 2000 | +| total_timesteps | 2664448 | +| train/ | | +| approx_kl | 0.044479392 | +| clip_fraction | 0.433 | +| clip_range | 0.117 | +| entropy_loss | -7.24 | +| explained_variance | -0.288 | +| learning_rate | 0.000147 | +| loss | -0.0622 | +| n_updates | 5200 | +| policy_gradient_loss | -0.04 | +| value_loss | 0.00016 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1332 | +| iterations | 1302 | +| time_elapsed | 2001 | +| total_timesteps | 2666496 | +| train/ | | +| approx_kl | 0.034699894 | +| clip_fraction | 0.375 | +| clip_range | 0.117 | +| entropy_loss | -7.21 | +| explained_variance | -0.0281 | +| learning_rate | 0.000147 | +| loss | -0.0498 | +| n_updates | 5204 | +| policy_gradient_loss | -0.0303 | +| value_loss | 0.000213 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1331 | +| iterations | 1303 | +| time_elapsed | 2003 | +| total_timesteps | 2668544 | +| train/ | | +| approx_kl | 0.030829687 | +| clip_fraction | 0.39 | +| clip_range | 0.117 | +| entropy_loss | -7.12 | +| explained_variance | -0.144 | +| learning_rate | 0.000147 | +| loss | -0.0486 | +| n_updates | 5208 | +| policy_gradient_loss | -0.0281 | +| value_loss | 0.000234 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1331 | +| iterations | 1304 | +| time_elapsed | 2005 | +| total_timesteps | 2670592 | +| train/ | | +| approx_kl | 0.03623913 | +| clip_fraction | 0.426 | +| clip_range | 0.117 | +| entropy_loss | -7.25 | +| explained_variance | -0.0637 | +| learning_rate | 0.000147 | +| loss | -0.0492 | +| n_updates | 5212 | +| policy_gradient_loss | -0.0304 | +| value_loss | 0.000208 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1331 | +| iterations | 1305 | +| time_elapsed | 2006 | +| total_timesteps | 2672640 | +| train/ | | +| approx_kl | 0.042925455 | +| clip_fraction | 0.429 | +| clip_range | 0.117 | +| entropy_loss | -7.19 | +| explained_variance | -0.045 | +| learning_rate | 0.000147 | +| loss | -0.0453 | +| n_updates | 5216 | +| policy_gradient_loss | -0.034 | +| value_loss | 0.000143 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1331 | +| iterations | 1306 | +| time_elapsed | 2008 | +| total_timesteps | 2674688 | +| train/ | | +| approx_kl | 0.047941964 | +| clip_fraction | 0.383 | +| clip_range | 0.117 | +| entropy_loss | -7.36 | +| explained_variance | 0.00745 | +| learning_rate | 0.000147 | +| loss | -0.0529 | +| n_updates | 5220 | +| policy_gradient_loss | -0.0331 | +| value_loss | 0.000193 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1331 | +| iterations | 1307 | +| time_elapsed | 2010 | +| total_timesteps | 2676736 | +| train/ | | +| approx_kl | 0.041089993 | +| clip_fraction | 0.391 | +| clip_range | 0.117 | +| entropy_loss | -7.16 | +| explained_variance | 0.0311 | +| learning_rate | 0.000147 | +| loss | -0.0504 | +| n_updates | 5224 | +| policy_gradient_loss | -0.0314 | +| value_loss | 0.000177 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.3 | +| time/ | | +| fps | 1331 | +| iterations | 1308 | +| time_elapsed | 2011 | +| total_timesteps | 2678784 | +| train/ | | +| approx_kl | 0.044358037 | +| clip_fraction | 0.431 | +| clip_range | 0.117 | +| entropy_loss | -7.3 | +| explained_variance | -0.26 | +| learning_rate | 0.000147 | +| loss | -0.0679 | +| n_updates | 5228 | +| policy_gradient_loss | -0.0389 | +| value_loss | 0.000102 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.304 | +| time/ | | +| fps | 1331 | +| iterations | 1309 | +| time_elapsed | 2013 | +| total_timesteps | 2680832 | +| train/ | | +| approx_kl | 0.03907367 | +| clip_fraction | 0.435 | +| clip_range | 0.117 | +| entropy_loss | -7.22 | +| explained_variance | -0.0649 | +| learning_rate | 0.000147 | +| loss | -0.0531 | +| n_updates | 5232 | +| policy_gradient_loss | -0.0324 | +| value_loss | 0.000126 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.3 | +| time/ | | +| fps | 1331 | +| iterations | 1310 | +| time_elapsed | 2015 | +| total_timesteps | 2682880 | +| train/ | | +| approx_kl | 0.040435992 | +| clip_fraction | 0.427 | +| clip_range | 0.116 | +| entropy_loss | -7.08 | +| explained_variance | -0.0488 | +| learning_rate | 0.000147 | +| loss | -0.0518 | +| n_updates | 5236 | +| policy_gradient_loss | -0.0308 | +| value_loss | 0.000237 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 1331 | +| iterations | 1311 | +| time_elapsed | 2016 | +| total_timesteps | 2684928 | +| train/ | | +| approx_kl | 0.043956496 | +| clip_fraction | 0.42 | +| clip_range | 0.116 | +| entropy_loss | -7.25 | +| explained_variance | 0.0619 | +| learning_rate | 0.000147 | +| loss | -0.0522 | +| n_updates | 5240 | +| policy_gradient_loss | -0.0318 | +| value_loss | 0.00017 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 1331 | +| iterations | 1312 | +| time_elapsed | 2018 | +| total_timesteps | 2686976 | +| train/ | | +| approx_kl | 0.042074107 | +| clip_fraction | 0.384 | +| clip_range | 0.116 | +| entropy_loss | -7.08 | +| explained_variance | -0.0339 | +| learning_rate | 0.000147 | +| loss | -0.0547 | +| n_updates | 5244 | +| policy_gradient_loss | -0.0332 | +| value_loss | 0.000173 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.302 | +| time/ | | +| fps | 1331 | +| iterations | 1313 | +| time_elapsed | 2019 | +| total_timesteps | 2689024 | +| train/ | | +| approx_kl | 0.036877964 | +| clip_fraction | 0.434 | +| clip_range | 0.116 | +| entropy_loss | -7.25 | +| explained_variance | -0.107 | +| learning_rate | 0.000147 | +| loss | -0.0639 | +| n_updates | 5248 | +| policy_gradient_loss | -0.0345 | +| value_loss | 0.000131 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1331 | +| iterations | 1314 | +| time_elapsed | 2021 | +| total_timesteps | 2691072 | +| train/ | | +| approx_kl | 0.039708205 | +| clip_fraction | 0.401 | +| clip_range | 0.116 | +| entropy_loss | -7.18 | +| explained_variance | -0.169 | +| learning_rate | 0.000147 | +| loss | -0.0549 | +| n_updates | 5252 | +| policy_gradient_loss | -0.0357 | +| value_loss | 0.000152 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.3 | +| time/ | | +| fps | 1331 | +| iterations | 1315 | +| time_elapsed | 2023 | +| total_timesteps | 2693120 | +| train/ | | +| approx_kl | 0.044807687 | +| clip_fraction | 0.417 | +| clip_range | 0.116 | +| entropy_loss | -7.04 | +| explained_variance | -0.0867 | +| learning_rate | 0.000147 | +| loss | -0.0565 | +| n_updates | 5256 | +| policy_gradient_loss | -0.0312 | +| value_loss | 0.000386 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.3 | +| time/ | | +| fps | 1331 | +| iterations | 1316 | +| time_elapsed | 2024 | +| total_timesteps | 2695168 | +| train/ | | +| approx_kl | 0.040377133 | +| clip_fraction | 0.423 | +| clip_range | 0.116 | +| entropy_loss | -7.11 | +| explained_variance | -0.278 | +| learning_rate | 0.000147 | +| loss | -0.0605 | +| n_updates | 5260 | +| policy_gradient_loss | -0.038 | +| value_loss | 0.000148 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.295 | +| time/ | | +| fps | 1330 | +| iterations | 1317 | +| time_elapsed | 2026 | +| total_timesteps | 2697216 | +| train/ | | +| approx_kl | 0.0478461 | +| clip_fraction | 0.405 | +| clip_range | 0.116 | +| entropy_loss | -7.15 | +| explained_variance | 0.00424 | +| learning_rate | 0.000147 | +| loss | -0.0539 | +| n_updates | 5264 | +| policy_gradient_loss | -0.0339 | +| value_loss | 0.000192 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.295 | +| time/ | | +| fps | 1330 | +| iterations | 1318 | +| time_elapsed | 2028 | +| total_timesteps | 2699264 | +| train/ | | +| approx_kl | 0.045442462 | +| clip_fraction | 0.42 | +| clip_range | 0.116 | +| entropy_loss | -7.13 | +| explained_variance | -0.112 | +| learning_rate | 0.000147 | +| loss | -0.0583 | +| n_updates | 5268 | +| policy_gradient_loss | -0.0336 | +| value_loss | 0.000191 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.295 | +| time/ | | +| fps | 1330 | +| iterations | 1319 | +| time_elapsed | 2029 | +| total_timesteps | 2701312 | +| train/ | | +| approx_kl | 0.038514033 | +| clip_fraction | 0.41 | +| clip_range | 0.116 | +| entropy_loss | -7.19 | +| explained_variance | -0.0527 | +| learning_rate | 0.000147 | +| loss | -0.0614 | +| n_updates | 5272 | +| policy_gradient_loss | -0.0307 | +| value_loss | 0.000305 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.29 | +| time/ | | +| fps | 1330 | +| iterations | 1320 | +| time_elapsed | 2031 | +| total_timesteps | 2703360 | +| train/ | | +| approx_kl | 0.045129955 | +| clip_fraction | 0.42 | +| clip_range | 0.116 | +| entropy_loss | -7.19 | +| explained_variance | -0.33 | +| learning_rate | 0.000147 | +| loss | -0.0579 | +| n_updates | 5276 | +| policy_gradient_loss | -0.0362 | +| value_loss | 0.00014 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.29 | +| time/ | | +| fps | 1330 | +| iterations | 1321 | +| time_elapsed | 2033 | +| total_timesteps | 2705408 | +| train/ | | +| approx_kl | 0.038860504 | +| clip_fraction | 0.425 | +| clip_range | 0.116 | +| entropy_loss | -7.18 | +| explained_variance | -0.0838 | +| learning_rate | 0.000146 | +| loss | -0.0554 | +| n_updates | 5280 | +| policy_gradient_loss | -0.034 | +| value_loss | 0.00012 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.294 | +| time/ | | +| fps | 1330 | +| iterations | 1322 | +| time_elapsed | 2034 | +| total_timesteps | 2707456 | +| train/ | | +| approx_kl | 0.041568555 | +| clip_fraction | 0.401 | +| clip_range | 0.116 | +| entropy_loss | -7.26 | +| explained_variance | -0.209 | +| learning_rate | 0.000146 | +| loss | -0.0466 | +| n_updates | 5284 | +| policy_gradient_loss | -0.0312 | +| value_loss | 0.000121 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.294 | +| time/ | | +| fps | 1330 | +| iterations | 1323 | +| time_elapsed | 2036 | +| total_timesteps | 2709504 | +| train/ | | +| approx_kl | 0.040246166 | +| clip_fraction | 0.394 | +| clip_range | 0.116 | +| entropy_loss | -7.2 | +| explained_variance | -0.0794 | +| learning_rate | 0.000146 | +| loss | -0.0538 | +| n_updates | 5288 | +| policy_gradient_loss | -0.0292 | +| value_loss | 0.000205 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.294 | +| time/ | | +| fps | 1330 | +| iterations | 1324 | +| time_elapsed | 2038 | +| total_timesteps | 2711552 | +| train/ | | +| approx_kl | 0.04123235 | +| clip_fraction | 0.393 | +| clip_range | 0.116 | +| entropy_loss | -7.26 | +| explained_variance | -0.0872 | +| learning_rate | 0.000146 | +| loss | -0.0623 | +| n_updates | 5292 | +| policy_gradient_loss | -0.0374 | +| value_loss | 0.000177 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.297 | +| time/ | | +| fps | 1330 | +| iterations | 1325 | +| time_elapsed | 2039 | +| total_timesteps | 2713600 | +| train/ | | +| approx_kl | 0.040858164 | +| clip_fraction | 0.429 | +| clip_range | 0.116 | +| entropy_loss | -7.23 | +| explained_variance | -0.34 | +| learning_rate | 0.000146 | +| loss | -0.0604 | +| n_updates | 5296 | +| policy_gradient_loss | -0.0366 | +| value_loss | 0.000131 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.292 | +| time/ | | +| fps | 1330 | +| iterations | 1326 | +| time_elapsed | 2041 | +| total_timesteps | 2715648 | +| train/ | | +| approx_kl | 0.034773286 | +| clip_fraction | 0.375 | +| clip_range | 0.116 | +| entropy_loss | -7.19 | +| explained_variance | -0.0439 | +| learning_rate | 0.000146 | +| loss | -0.052 | +| n_updates | 5300 | +| policy_gradient_loss | -0.0294 | +| value_loss | 0.000244 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 1330 | +| iterations | 1327 | +| time_elapsed | 2042 | +| total_timesteps | 2717696 | +| train/ | | +| approx_kl | 0.04391706 | +| clip_fraction | 0.403 | +| clip_range | 0.116 | +| entropy_loss | -7.12 | +| explained_variance | -0.25 | +| learning_rate | 0.000146 | +| loss | -0.0563 | +| n_updates | 5304 | +| policy_gradient_loss | -0.0316 | +| value_loss | 0.000202 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.302 | +| time/ | | +| fps | 1330 | +| iterations | 1328 | +| time_elapsed | 2043 | +| total_timesteps | 2719744 | +| train/ | | +| approx_kl | 0.042575184 | +| clip_fraction | 0.446 | +| clip_range | 0.116 | +| entropy_loss | -7.11 | +| explained_variance | -0.355 | +| learning_rate | 0.000146 | +| loss | -0.055 | +| n_updates | 5308 | +| policy_gradient_loss | -0.0384 | +| value_loss | 0.000124 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 1330 | +| iterations | 1329 | +| time_elapsed | 2045 | +| total_timesteps | 2721792 | +| train/ | | +| approx_kl | 0.041620143 | +| clip_fraction | 0.411 | +| clip_range | 0.116 | +| entropy_loss | -7.15 | +| explained_variance | -0.407 | +| learning_rate | 0.000146 | +| loss | -0.0586 | +| n_updates | 5312 | +| policy_gradient_loss | -0.0374 | +| value_loss | 9.1e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1330 | +| iterations | 1330 | +| time_elapsed | 2046 | +| total_timesteps | 2723840 | +| train/ | | +| approx_kl | 0.04148949 | +| clip_fraction | 0.422 | +| clip_range | 0.116 | +| entropy_loss | -7.08 | +| explained_variance | -0.0547 | +| learning_rate | 0.000146 | +| loss | -0.0512 | +| n_updates | 5316 | +| policy_gradient_loss | -0.0326 | +| value_loss | 0.000147 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 1330 | +| iterations | 1331 | +| time_elapsed | 2048 | +| total_timesteps | 2725888 | +| train/ | | +| approx_kl | 0.043556064 | +| clip_fraction | 0.405 | +| clip_range | 0.116 | +| entropy_loss | -7.11 | +| explained_variance | -0.0544 | +| learning_rate | 0.000146 | +| loss | -0.0583 | +| n_updates | 5320 | +| policy_gradient_loss | -0.0336 | +| value_loss | 0.000224 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 1331 | +| iterations | 1332 | +| time_elapsed | 2049 | +| total_timesteps | 2727936 | +| train/ | | +| approx_kl | 0.04201769 | +| clip_fraction | 0.412 | +| clip_range | 0.116 | +| entropy_loss | -7.03 | +| explained_variance | -0.146 | +| learning_rate | 0.000146 | +| loss | -0.057 | +| n_updates | 5324 | +| policy_gradient_loss | -0.0353 | +| value_loss | 0.000153 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.3 | +| time/ | | +| fps | 1331 | +| iterations | 1333 | +| time_elapsed | 2050 | +| total_timesteps | 2729984 | +| train/ | | +| approx_kl | 0.04479985 | +| clip_fraction | 0.421 | +| clip_range | 0.116 | +| entropy_loss | -6.98 | +| explained_variance | -0.0898 | +| learning_rate | 0.000146 | +| loss | -0.0527 | +| n_updates | 5328 | +| policy_gradient_loss | -0.0342 | +| value_loss | 0.000146 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 1331 | +| iterations | 1334 | +| time_elapsed | 2052 | +| total_timesteps | 2732032 | +| train/ | | +| approx_kl | 0.036389112 | +| clip_fraction | 0.43 | +| clip_range | 0.116 | +| entropy_loss | -7.06 | +| explained_variance | -0.0137 | +| learning_rate | 0.000146 | +| loss | -0.052 | +| n_updates | 5332 | +| policy_gradient_loss | -0.0327 | +| value_loss | 0.000261 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 1331 | +| iterations | 1335 | +| time_elapsed | 2054 | +| total_timesteps | 2734080 | +| train/ | | +| approx_kl | 0.036416348 | +| clip_fraction | 0.392 | +| clip_range | 0.116 | +| entropy_loss | -7.09 | +| explained_variance | 0.0168 | +| learning_rate | 0.000146 | +| loss | -0.0494 | +| n_updates | 5336 | +| policy_gradient_loss | -0.0271 | +| value_loss | 0.000283 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.297 | +| time/ | | +| fps | 1331 | +| iterations | 1336 | +| time_elapsed | 2055 | +| total_timesteps | 2736128 | +| train/ | | +| approx_kl | 0.0402283 | +| clip_fraction | 0.393 | +| clip_range | 0.116 | +| entropy_loss | -7.19 | +| explained_variance | -0.0722 | +| learning_rate | 0.000146 | +| loss | -0.0655 | +| n_updates | 5340 | +| policy_gradient_loss | -0.034 | +| value_loss | 0.000201 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 1331 | +| iterations | 1337 | +| time_elapsed | 2056 | +| total_timesteps | 2738176 | +| train/ | | +| approx_kl | 0.039266035 | +| clip_fraction | 0.413 | +| clip_range | 0.116 | +| entropy_loss | -7.15 | +| explained_variance | -0.217 | +| learning_rate | 0.000146 | +| loss | -0.0526 | +| n_updates | 5344 | +| policy_gradient_loss | -0.0318 | +| value_loss | 0.000179 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 1331 | +| iterations | 1338 | +| time_elapsed | 2058 | +| total_timesteps | 2740224 | +| train/ | | +| approx_kl | 0.045029342 | +| clip_fraction | 0.396 | +| clip_range | 0.116 | +| entropy_loss | -7.23 | +| explained_variance | -0.156 | +| learning_rate | 0.000146 | +| loss | -0.0484 | +| n_updates | 5348 | +| policy_gradient_loss | -0.0362 | +| value_loss | 0.000104 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.293 | +| time/ | | +| fps | 1331 | +| iterations | 1339 | +| time_elapsed | 2059 | +| total_timesteps | 2742272 | +| train/ | | +| approx_kl | 0.03879016 | +| clip_fraction | 0.389 | +| clip_range | 0.116 | +| entropy_loss | -7.26 | +| explained_variance | -0.151 | +| learning_rate | 0.000146 | +| loss | -0.0471 | +| n_updates | 5352 | +| policy_gradient_loss | -0.0292 | +| value_loss | 0.000162 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.294 | +| time/ | | +| fps | 1331 | +| iterations | 1340 | +| time_elapsed | 2061 | +| total_timesteps | 2744320 | +| train/ | | +| approx_kl | 0.040439308 | +| clip_fraction | 0.385 | +| clip_range | 0.116 | +| entropy_loss | -7.15 | +| explained_variance | -0.125 | +| learning_rate | 0.000146 | +| loss | -0.0533 | +| n_updates | 5356 | +| policy_gradient_loss | -0.0318 | +| value_loss | 0.000135 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.292 | +| time/ | | +| fps | 1331 | +| iterations | 1341 | +| time_elapsed | 2062 | +| total_timesteps | 2746368 | +| train/ | | +| approx_kl | 0.043044187 | +| clip_fraction | 0.408 | +| clip_range | 0.116 | +| entropy_loss | -7.2 | +| explained_variance | -0.269 | +| learning_rate | 0.000146 | +| loss | -0.052 | +| n_updates | 5360 | +| policy_gradient_loss | -0.0322 | +| value_loss | 0.00016 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.291 | +| time/ | | +| fps | 1331 | +| iterations | 1342 | +| time_elapsed | 2064 | +| total_timesteps | 2748416 | +| train/ | | +| approx_kl | 0.045776084 | +| clip_fraction | 0.423 | +| clip_range | 0.116 | +| entropy_loss | -7.03 | +| explained_variance | -0.104 | +| learning_rate | 0.000146 | +| loss | -0.0485 | +| n_updates | 5364 | +| policy_gradient_loss | -0.0309 | +| value_loss | 0.000153 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.292 | +| time/ | | +| fps | 1331 | +| iterations | 1343 | +| time_elapsed | 2065 | +| total_timesteps | 2750464 | +| train/ | | +| approx_kl | 0.050005708 | +| clip_fraction | 0.414 | +| clip_range | 0.116 | +| entropy_loss | -7.15 | +| explained_variance | -0.0199 | +| learning_rate | 0.000146 | +| loss | -0.0606 | +| n_updates | 5368 | +| policy_gradient_loss | -0.0324 | +| value_loss | 0.000139 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.274 | +| time/ | | +| fps | 1331 | +| iterations | 1344 | +| time_elapsed | 2066 | +| total_timesteps | 2752512 | +| train/ | | +| approx_kl | 0.041640166 | +| clip_fraction | 0.415 | +| clip_range | 0.116 | +| entropy_loss | -7.01 | +| explained_variance | -0.1 | +| learning_rate | 0.000146 | +| loss | -0.0495 | +| n_updates | 5372 | +| policy_gradient_loss | -0.0292 | +| value_loss | 0.000232 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.284 | +| time/ | | +| fps | 1331 | +| iterations | 1345 | +| time_elapsed | 2068 | +| total_timesteps | 2754560 | +| train/ | | +| approx_kl | 0.041516956 | +| clip_fraction | 0.408 | +| clip_range | 0.116 | +| entropy_loss | -6.99 | +| explained_variance | -0.196 | +| learning_rate | 0.000146 | +| loss | -0.0504 | +| n_updates | 5376 | +| policy_gradient_loss | -0.0354 | +| value_loss | 0.000269 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.283 | +| time/ | | +| fps | 1331 | +| iterations | 1346 | +| time_elapsed | 2069 | +| total_timesteps | 2756608 | +| train/ | | +| approx_kl | 0.049647585 | +| clip_fraction | 0.432 | +| clip_range | 0.116 | +| entropy_loss | -7.07 | +| explained_variance | -0.148 | +| learning_rate | 0.000145 | +| loss | -0.0514 | +| n_updates | 5380 | +| policy_gradient_loss | -0.0352 | +| value_loss | 0.000262 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.284 | +| time/ | | +| fps | 1331 | +| iterations | 1347 | +| time_elapsed | 2071 | +| total_timesteps | 2758656 | +| train/ | | +| approx_kl | 0.040661015 | +| clip_fraction | 0.42 | +| clip_range | 0.116 | +| entropy_loss | -7.03 | +| explained_variance | -0.232 | +| learning_rate | 0.000145 | +| loss | -0.0492 | +| n_updates | 5384 | +| policy_gradient_loss | -0.0364 | +| value_loss | 0.000242 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.294 | +| time/ | | +| fps | 1331 | +| iterations | 1348 | +| time_elapsed | 2072 | +| total_timesteps | 2760704 | +| train/ | | +| approx_kl | 0.04305435 | +| clip_fraction | 0.441 | +| clip_range | 0.116 | +| entropy_loss | -6.99 | +| explained_variance | -0.681 | +| learning_rate | 0.000145 | +| loss | -0.0676 | +| n_updates | 5388 | +| policy_gradient_loss | -0.0395 | +| value_loss | 0.00011 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.294 | +| time/ | | +| fps | 1331 | +| iterations | 1349 | +| time_elapsed | 2074 | +| total_timesteps | 2762752 | +| train/ | | +| approx_kl | 0.037507035 | +| clip_fraction | 0.41 | +| clip_range | 0.115 | +| entropy_loss | -6.97 | +| explained_variance | -0.102 | +| learning_rate | 0.000145 | +| loss | -0.0503 | +| n_updates | 5392 | +| policy_gradient_loss | -0.0281 | +| value_loss | 0.000166 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.292 | +| time/ | | +| fps | 1332 | +| iterations | 1350 | +| time_elapsed | 2075 | +| total_timesteps | 2764800 | +| train/ | | +| approx_kl | 0.046008166 | +| clip_fraction | 0.423 | +| clip_range | 0.115 | +| entropy_loss | -7.01 | +| explained_variance | -0.0727 | +| learning_rate | 0.000145 | +| loss | -0.0533 | +| n_updates | 5396 | +| policy_gradient_loss | -0.0334 | +| value_loss | 0.000165 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.292 | +| time/ | | +| fps | 1332 | +| iterations | 1351 | +| time_elapsed | 2077 | +| total_timesteps | 2766848 | +| train/ | | +| approx_kl | 0.042068087 | +| clip_fraction | 0.452 | +| clip_range | 0.115 | +| entropy_loss | -7.13 | +| explained_variance | -0.498 | +| learning_rate | 0.000145 | +| loss | -0.0656 | +| n_updates | 5400 | +| policy_gradient_loss | -0.0391 | +| value_loss | 8.4e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.287 | +| time/ | | +| fps | 1332 | +| iterations | 1352 | +| time_elapsed | 2078 | +| total_timesteps | 2768896 | +| train/ | | +| approx_kl | 0.047242887 | +| clip_fraction | 0.425 | +| clip_range | 0.115 | +| entropy_loss | -7.14 | +| explained_variance | -0.0899 | +| learning_rate | 0.000145 | +| loss | -0.0511 | +| n_updates | 5404 | +| policy_gradient_loss | -0.0333 | +| value_loss | 0.000223 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.284 | +| time/ | | +| fps | 1332 | +| iterations | 1353 | +| time_elapsed | 2080 | +| total_timesteps | 2770944 | +| train/ | | +| approx_kl | 0.040087026 | +| clip_fraction | 0.394 | +| clip_range | 0.115 | +| entropy_loss | -7.02 | +| explained_variance | -0.0408 | +| learning_rate | 0.000145 | +| loss | -0.0476 | +| n_updates | 5408 | +| policy_gradient_loss | -0.029 | +| value_loss | 0.000241 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.29 | +| time/ | | +| fps | 1332 | +| iterations | 1354 | +| time_elapsed | 2081 | +| total_timesteps | 2772992 | +| train/ | | +| approx_kl | 0.042107154 | +| clip_fraction | 0.404 | +| clip_range | 0.115 | +| entropy_loss | -6.94 | +| explained_variance | -0.163 | +| learning_rate | 0.000145 | +| loss | -0.0577 | +| n_updates | 5412 | +| policy_gradient_loss | -0.034 | +| value_loss | 0.00019 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.293 | +| time/ | | +| fps | 1332 | +| iterations | 1355 | +| time_elapsed | 2082 | +| total_timesteps | 2775040 | +| train/ | | +| approx_kl | 0.04254737 | +| clip_fraction | 0.401 | +| clip_range | 0.115 | +| entropy_loss | -7.05 | +| explained_variance | -0.0941 | +| learning_rate | 0.000145 | +| loss | -0.0372 | +| n_updates | 5416 | +| policy_gradient_loss | -0.0318 | +| value_loss | 0.000227 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.293 | +| time/ | | +| fps | 1332 | +| iterations | 1356 | +| time_elapsed | 2084 | +| total_timesteps | 2777088 | +| train/ | | +| approx_kl | 0.044963107 | +| clip_fraction | 0.405 | +| clip_range | 0.115 | +| entropy_loss | -7.08 | +| explained_variance | -0.073 | +| learning_rate | 0.000145 | +| loss | -0.047 | +| n_updates | 5420 | +| policy_gradient_loss | -0.0324 | +| value_loss | 0.000252 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.293 | +| time/ | | +| fps | 1332 | +| iterations | 1357 | +| time_elapsed | 2085 | +| total_timesteps | 2779136 | +| train/ | | +| approx_kl | 0.04530402 | +| clip_fraction | 0.422 | +| clip_range | 0.115 | +| entropy_loss | -7.05 | +| explained_variance | -0.019 | +| learning_rate | 0.000145 | +| loss | -0.0531 | +| n_updates | 5424 | +| policy_gradient_loss | -0.0374 | +| value_loss | 0.000178 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.292 | +| time/ | | +| fps | 1332 | +| iterations | 1358 | +| time_elapsed | 2087 | +| total_timesteps | 2781184 | +| train/ | | +| approx_kl | 0.03996057 | +| clip_fraction | 0.407 | +| clip_range | 0.115 | +| entropy_loss | -7.23 | +| explained_variance | -0.103 | +| learning_rate | 0.000145 | +| loss | -0.0597 | +| n_updates | 5428 | +| policy_gradient_loss | -0.0339 | +| value_loss | 0.000174 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 1332 | +| iterations | 1359 | +| time_elapsed | 2088 | +| total_timesteps | 2783232 | +| train/ | | +| approx_kl | 0.042456217 | +| clip_fraction | 0.41 | +| clip_range | 0.115 | +| entropy_loss | -7.18 | +| explained_variance | -0.237 | +| learning_rate | 0.000145 | +| loss | -0.056 | +| n_updates | 5432 | +| policy_gradient_loss | -0.035 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 1332 | +| iterations | 1360 | +| time_elapsed | 2089 | +| total_timesteps | 2785280 | +| train/ | | +| approx_kl | 0.036832605 | +| clip_fraction | 0.413 | +| clip_range | 0.115 | +| entropy_loss | -6.9 | +| explained_variance | 0.0106 | +| learning_rate | 0.000145 | +| loss | -0.0492 | +| n_updates | 5436 | +| policy_gradient_loss | -0.0306 | +| value_loss | 0.000304 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 1332 | +| iterations | 1361 | +| time_elapsed | 2091 | +| total_timesteps | 2787328 | +| train/ | | +| approx_kl | 0.045027982 | +| clip_fraction | 0.464 | +| clip_range | 0.115 | +| entropy_loss | -6.99 | +| explained_variance | -0.385 | +| learning_rate | 0.000145 | +| loss | -0.0528 | +| n_updates | 5440 | +| policy_gradient_loss | -0.0383 | +| value_loss | 0.000141 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 1332 | +| iterations | 1362 | +| time_elapsed | 2092 | +| total_timesteps | 2789376 | +| train/ | | +| approx_kl | 0.046831973 | +| clip_fraction | 0.434 | +| clip_range | 0.115 | +| entropy_loss | -7.01 | +| explained_variance | -0.0664 | +| learning_rate | 0.000145 | +| loss | -0.053 | +| n_updates | 5444 | +| policy_gradient_loss | -0.0347 | +| value_loss | 0.000185 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 1332 | +| iterations | 1363 | +| time_elapsed | 2094 | +| total_timesteps | 2791424 | +| train/ | | +| approx_kl | 0.040412456 | +| clip_fraction | 0.374 | +| clip_range | 0.115 | +| entropy_loss | -7.01 | +| explained_variance | -0.0293 | +| learning_rate | 0.000145 | +| loss | -0.0528 | +| n_updates | 5448 | +| policy_gradient_loss | -0.0314 | +| value_loss | 0.00033 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 1333 | +| iterations | 1364 | +| time_elapsed | 2095 | +| total_timesteps | 2793472 | +| train/ | | +| approx_kl | 0.0441538 | +| clip_fraction | 0.425 | +| clip_range | 0.115 | +| entropy_loss | -7.05 | +| explained_variance | -0.352 | +| learning_rate | 0.000145 | +| loss | -0.0593 | +| n_updates | 5452 | +| policy_gradient_loss | -0.037 | +| value_loss | 0.000111 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 1333 | +| iterations | 1365 | +| time_elapsed | 2097 | +| total_timesteps | 2795520 | +| train/ | | +| approx_kl | 0.042978182 | +| clip_fraction | 0.411 | +| clip_range | 0.115 | +| entropy_loss | -7.08 | +| explained_variance | -0.218 | +| learning_rate | 0.000145 | +| loss | -0.0587 | +| n_updates | 5456 | +| policy_gradient_loss | -0.0348 | +| value_loss | 0.000157 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.302 | +| time/ | | +| fps | 1333 | +| iterations | 1366 | +| time_elapsed | 2098 | +| total_timesteps | 2797568 | +| train/ | | +| approx_kl | 0.05069483 | +| clip_fraction | 0.447 | +| clip_range | 0.115 | +| entropy_loss | -7.19 | +| explained_variance | -0.15 | +| learning_rate | 0.000145 | +| loss | -0.0598 | +| n_updates | 5460 | +| policy_gradient_loss | -0.0358 | +| value_loss | 0.000113 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 1333 | +| iterations | 1367 | +| time_elapsed | 2099 | +| total_timesteps | 2799616 | +| train/ | | +| approx_kl | 0.04510382 | +| clip_fraction | 0.403 | +| clip_range | 0.115 | +| entropy_loss | -7.08 | +| explained_variance | -0.0993 | +| learning_rate | 0.000145 | +| loss | -0.044 | +| n_updates | 5464 | +| policy_gradient_loss | -0.0305 | +| value_loss | 0.000166 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 1333 | +| iterations | 1368 | +| time_elapsed | 2101 | +| total_timesteps | 2801664 | +| train/ | | +| approx_kl | 0.04558309 | +| clip_fraction | 0.399 | +| clip_range | 0.115 | +| entropy_loss | -7.05 | +| explained_variance | -0.115 | +| learning_rate | 0.000145 | +| loss | -0.0514 | +| n_updates | 5468 | +| policy_gradient_loss | -0.0337 | +| value_loss | 0.000136 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 1333 | +| iterations | 1369 | +| time_elapsed | 2102 | +| total_timesteps | 2803712 | +| train/ | | +| approx_kl | 0.03427985 | +| clip_fraction | 0.396 | +| clip_range | 0.115 | +| entropy_loss | -7.09 | +| explained_variance | -0.0595 | +| learning_rate | 0.000145 | +| loss | -0.0431 | +| n_updates | 5472 | +| policy_gradient_loss | -0.0312 | +| value_loss | 0.000242 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.304 | +| time/ | | +| fps | 1333 | +| iterations | 1370 | +| time_elapsed | 2104 | +| total_timesteps | 2805760 | +| train/ | | +| approx_kl | 0.035744637 | +| clip_fraction | 0.406 | +| clip_range | 0.115 | +| entropy_loss | -6.98 | +| explained_variance | -0.2 | +| learning_rate | 0.000144 | +| loss | -0.063 | +| n_updates | 5476 | +| policy_gradient_loss | -0.0344 | +| value_loss | 0.000182 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 1333 | +| iterations | 1371 | +| time_elapsed | 2105 | +| total_timesteps | 2807808 | +| train/ | | +| approx_kl | 0.034463815 | +| clip_fraction | 0.407 | +| clip_range | 0.115 | +| entropy_loss | -7.03 | +| explained_variance | 0.0148 | +| learning_rate | 0.000144 | +| loss | -0.0567 | +| n_updates | 5480 | +| policy_gradient_loss | -0.0288 | +| value_loss | 0.000343 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 1333 | +| iterations | 1372 | +| time_elapsed | 2107 | +| total_timesteps | 2809856 | +| train/ | | +| approx_kl | 0.044172563 | +| clip_fraction | 0.415 | +| clip_range | 0.115 | +| entropy_loss | -7.08 | +| explained_variance | -0.416 | +| learning_rate | 0.000144 | +| loss | -0.0642 | +| n_updates | 5484 | +| policy_gradient_loss | -0.0371 | +| value_loss | 0.000126 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 1333 | +| iterations | 1373 | +| time_elapsed | 2108 | +| total_timesteps | 2811904 | +| train/ | | +| approx_kl | 0.036573697 | +| clip_fraction | 0.421 | +| clip_range | 0.115 | +| entropy_loss | -7.19 | +| explained_variance | -0.145 | +| learning_rate | 0.000144 | +| loss | -0.0588 | +| n_updates | 5488 | +| policy_gradient_loss | -0.0353 | +| value_loss | 0.000144 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.304 | +| time/ | | +| fps | 1333 | +| iterations | 1374 | +| time_elapsed | 2110 | +| total_timesteps | 2813952 | +| train/ | | +| approx_kl | 0.03738353 | +| clip_fraction | 0.419 | +| clip_range | 0.115 | +| entropy_loss | -7.04 | +| explained_variance | -0.0113 | +| learning_rate | 0.000144 | +| loss | -0.0557 | +| n_updates | 5492 | +| policy_gradient_loss | -0.0326 | +| value_loss | 0.000192 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.304 | +| time/ | | +| fps | 1333 | +| iterations | 1375 | +| time_elapsed | 2111 | +| total_timesteps | 2816000 | +| train/ | | +| approx_kl | 0.03545384 | +| clip_fraction | 0.398 | +| clip_range | 0.115 | +| entropy_loss | -7.07 | +| explained_variance | -0.0528 | +| learning_rate | 0.000144 | +| loss | -0.0597 | +| n_updates | 5496 | +| policy_gradient_loss | -0.0274 | +| value_loss | 0.000316 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.29 | +| time/ | | +| fps | 1333 | +| iterations | 1376 | +| time_elapsed | 2112 | +| total_timesteps | 2818048 | +| train/ | | +| approx_kl | 0.04550009 | +| clip_fraction | 0.409 | +| clip_range | 0.115 | +| entropy_loss | -7.09 | +| explained_variance | -0.201 | +| learning_rate | 0.000144 | +| loss | -0.0531 | +| n_updates | 5500 | +| policy_gradient_loss | -0.0339 | +| value_loss | 0.000142 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.287 | +| time/ | | +| fps | 1333 | +| iterations | 1377 | +| time_elapsed | 2114 | +| total_timesteps | 2820096 | +| train/ | | +| approx_kl | 0.039745346 | +| clip_fraction | 0.401 | +| clip_range | 0.115 | +| entropy_loss | -7 | +| explained_variance | 0.0259 | +| learning_rate | 0.000144 | +| loss | -0.0445 | +| n_updates | 5504 | +| policy_gradient_loss | -0.0307 | +| value_loss | 0.000215 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.292 | +| time/ | | +| fps | 1333 | +| iterations | 1378 | +| time_elapsed | 2115 | +| total_timesteps | 2822144 | +| train/ | | +| approx_kl | 0.037895292 | +| clip_fraction | 0.395 | +| clip_range | 0.115 | +| entropy_loss | -7.03 | +| explained_variance | -0.0794 | +| learning_rate | 0.000144 | +| loss | -0.0496 | +| n_updates | 5508 | +| policy_gradient_loss | -0.0319 | +| value_loss | 0.000159 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.292 | +| time/ | | +| fps | 1333 | +| iterations | 1379 | +| time_elapsed | 2117 | +| total_timesteps | 2824192 | +| train/ | | +| approx_kl | 0.04498797 | +| clip_fraction | 0.423 | +| clip_range | 0.115 | +| entropy_loss | -7.12 | +| explained_variance | -0.179 | +| learning_rate | 0.000144 | +| loss | -0.0595 | +| n_updates | 5512 | +| policy_gradient_loss | -0.0353 | +| value_loss | 0.000168 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.294 | +| time/ | | +| fps | 1333 | +| iterations | 1380 | +| time_elapsed | 2118 | +| total_timesteps | 2826240 | +| train/ | | +| approx_kl | 0.04302591 | +| clip_fraction | 0.437 | +| clip_range | 0.115 | +| entropy_loss | -7.06 | +| explained_variance | -0.27 | +| learning_rate | 0.000144 | +| loss | -0.0669 | +| n_updates | 5516 | +| policy_gradient_loss | -0.0398 | +| value_loss | 0.000104 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.294 | +| time/ | | +| fps | 1333 | +| iterations | 1381 | +| time_elapsed | 2120 | +| total_timesteps | 2828288 | +| train/ | | +| approx_kl | 0.040083446 | +| clip_fraction | 0.418 | +| clip_range | 0.115 | +| entropy_loss | -6.99 | +| explained_variance | -0.128 | +| learning_rate | 0.000144 | +| loss | -0.0524 | +| n_updates | 5520 | +| policy_gradient_loss | -0.0293 | +| value_loss | 0.000185 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 1334 | +| iterations | 1382 | +| time_elapsed | 2121 | +| total_timesteps | 2830336 | +| train/ | | +| approx_kl | 0.04028177 | +| clip_fraction | 0.404 | +| clip_range | 0.115 | +| entropy_loss | -7.08 | +| explained_variance | -0.158 | +| learning_rate | 0.000144 | +| loss | -0.047 | +| n_updates | 5524 | +| policy_gradient_loss | -0.0303 | +| value_loss | 0.000165 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.292 | +| time/ | | +| fps | 1334 | +| iterations | 1383 | +| time_elapsed | 2123 | +| total_timesteps | 2832384 | +| train/ | | +| approx_kl | 0.038249835 | +| clip_fraction | 0.39 | +| clip_range | 0.115 | +| entropy_loss | -7.09 | +| explained_variance | -0.0178 | +| learning_rate | 0.000144 | +| loss | -0.0566 | +| n_updates | 5528 | +| policy_gradient_loss | -0.0306 | +| value_loss | 0.000153 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.292 | +| time/ | | +| fps | 1334 | +| iterations | 1384 | +| time_elapsed | 2124 | +| total_timesteps | 2834432 | +| train/ | | +| approx_kl | 0.041326657 | +| clip_fraction | 0.413 | +| clip_range | 0.115 | +| entropy_loss | -7.02 | +| explained_variance | -0.258 | +| learning_rate | 0.000144 | +| loss | -0.0539 | +| n_updates | 5532 | +| policy_gradient_loss | -0.0364 | +| value_loss | 0.000119 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.289 | +| time/ | | +| fps | 1334 | +| iterations | 1385 | +| time_elapsed | 2126 | +| total_timesteps | 2836480 | +| train/ | | +| approx_kl | 0.043804772 | +| clip_fraction | 0.411 | +| clip_range | 0.115 | +| entropy_loss | -7.12 | +| explained_variance | -0.0533 | +| learning_rate | 0.000144 | +| loss | -0.057 | +| n_updates | 5536 | +| policy_gradient_loss | -0.0316 | +| value_loss | 0.000158 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.286 | +| time/ | | +| fps | 1334 | +| iterations | 1386 | +| time_elapsed | 2127 | +| total_timesteps | 2838528 | +| train/ | | +| approx_kl | 0.041321483 | +| clip_fraction | 0.445 | +| clip_range | 0.115 | +| entropy_loss | -7.1 | +| explained_variance | -0.136 | +| learning_rate | 0.000144 | +| loss | -0.0547 | +| n_updates | 5540 | +| policy_gradient_loss | -0.0347 | +| value_loss | 0.000131 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.286 | +| time/ | | +| fps | 1334 | +| iterations | 1387 | +| time_elapsed | 2128 | +| total_timesteps | 2840576 | +| train/ | | +| approx_kl | 0.04674477 | +| clip_fraction | 0.407 | +| clip_range | 0.115 | +| entropy_loss | -7.12 | +| explained_variance | -0.0329 | +| learning_rate | 0.000144 | +| loss | -0.0509 | +| n_updates | 5544 | +| policy_gradient_loss | -0.0319 | +| value_loss | 0.000195 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 1334 | +| iterations | 1388 | +| time_elapsed | 2130 | +| total_timesteps | 2842624 | +| train/ | | +| approx_kl | 0.043964878 | +| clip_fraction | 0.417 | +| clip_range | 0.114 | +| entropy_loss | -7.13 | +| explained_variance | -0.041 | +| learning_rate | 0.000144 | +| loss | -0.0579 | +| n_updates | 5548 | +| policy_gradient_loss | -0.0344 | +| value_loss | 0.000243 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.283 | +| time/ | | +| fps | 1334 | +| iterations | 1389 | +| time_elapsed | 2131 | +| total_timesteps | 2844672 | +| train/ | | +| approx_kl | 0.039701536 | +| clip_fraction | 0.412 | +| clip_range | 0.114 | +| entropy_loss | -7.12 | +| explained_variance | -0.0756 | +| learning_rate | 0.000144 | +| loss | -0.058 | +| n_updates | 5552 | +| policy_gradient_loss | -0.0345 | +| value_loss | 0.000153 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 1334 | +| iterations | 1390 | +| time_elapsed | 2133 | +| total_timesteps | 2846720 | +| train/ | | +| approx_kl | 0.04414669 | +| clip_fraction | 0.398 | +| clip_range | 0.114 | +| entropy_loss | -7.02 | +| explained_variance | -0.154 | +| learning_rate | 0.000144 | +| loss | -0.0515 | +| n_updates | 5556 | +| policy_gradient_loss | -0.0336 | +| value_loss | 0.000175 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.281 | +| time/ | | +| fps | 1334 | +| iterations | 1391 | +| time_elapsed | 2134 | +| total_timesteps | 2848768 | +| train/ | | +| approx_kl | 0.04569525 | +| clip_fraction | 0.417 | +| clip_range | 0.114 | +| entropy_loss | -6.96 | +| explained_variance | -0.129 | +| learning_rate | 0.000144 | +| loss | -0.0557 | +| n_updates | 5560 | +| policy_gradient_loss | -0.0336 | +| value_loss | 0.000183 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.277 | +| time/ | | +| fps | 1334 | +| iterations | 1392 | +| time_elapsed | 2136 | +| total_timesteps | 2850816 | +| train/ | | +| approx_kl | 0.046915576 | +| clip_fraction | 0.401 | +| clip_range | 0.114 | +| entropy_loss | -7.14 | +| explained_variance | -0.201 | +| learning_rate | 0.000144 | +| loss | -0.0557 | +| n_updates | 5564 | +| policy_gradient_loss | -0.0333 | +| value_loss | 0.000124 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.28 | +| time/ | | +| fps | 1334 | +| iterations | 1393 | +| time_elapsed | 2137 | +| total_timesteps | 2852864 | +| train/ | | +| approx_kl | 0.03823624 | +| clip_fraction | 0.405 | +| clip_range | 0.114 | +| entropy_loss | -7.04 | +| explained_variance | -0.0635 | +| learning_rate | 0.000144 | +| loss | -0.0521 | +| n_updates | 5568 | +| policy_gradient_loss | -0.032 | +| value_loss | 0.000159 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.287 | +| time/ | | +| fps | 1334 | +| iterations | 1394 | +| time_elapsed | 2139 | +| total_timesteps | 2854912 | +| train/ | | +| approx_kl | 0.03822741 | +| clip_fraction | 0.41 | +| clip_range | 0.114 | +| entropy_loss | -7.17 | +| explained_variance | -0.011 | +| learning_rate | 0.000144 | +| loss | -0.0518 | +| n_updates | 5572 | +| policy_gradient_loss | -0.027 | +| value_loss | 0.000323 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.287 | +| time/ | | +| fps | 1334 | +| iterations | 1395 | +| time_elapsed | 2140 | +| total_timesteps | 2856960 | +| train/ | | +| approx_kl | 0.03971606 | +| clip_fraction | 0.426 | +| clip_range | 0.114 | +| entropy_loss | -7.1 | +| explained_variance | -0.2 | +| learning_rate | 0.000143 | +| loss | -0.0632 | +| n_updates | 5576 | +| policy_gradient_loss | -0.0368 | +| value_loss | 0.000153 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.287 | +| time/ | | +| fps | 1334 | +| iterations | 1396 | +| time_elapsed | 2141 | +| total_timesteps | 2859008 | +| train/ | | +| approx_kl | 0.04074602 | +| clip_fraction | 0.406 | +| clip_range | 0.114 | +| entropy_loss | -7.18 | +| explained_variance | -0.0756 | +| learning_rate | 0.000143 | +| loss | -0.0522 | +| n_updates | 5580 | +| policy_gradient_loss | -0.0348 | +| value_loss | 0.000186 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.287 | +| time/ | | +| fps | 1334 | +| iterations | 1397 | +| time_elapsed | 2143 | +| total_timesteps | 2861056 | +| train/ | | +| approx_kl | 0.04022124 | +| clip_fraction | 0.428 | +| clip_range | 0.114 | +| entropy_loss | -7.27 | +| explained_variance | -0.586 | +| learning_rate | 0.000143 | +| loss | -0.0599 | +| n_updates | 5584 | +| policy_gradient_loss | -0.0421 | +| value_loss | 7.22e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.285 | +| time/ | | +| fps | 1334 | +| iterations | 1398 | +| time_elapsed | 2144 | +| total_timesteps | 2863104 | +| train/ | | +| approx_kl | 0.040926002 | +| clip_fraction | 0.39 | +| clip_range | 0.114 | +| entropy_loss | -7.03 | +| explained_variance | -0.0585 | +| learning_rate | 0.000143 | +| loss | -0.053 | +| n_updates | 5588 | +| policy_gradient_loss | -0.0265 | +| value_loss | 0.000169 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.281 | +| time/ | | +| fps | 1335 | +| iterations | 1399 | +| time_elapsed | 2146 | +| total_timesteps | 2865152 | +| train/ | | +| approx_kl | 0.041559048 | +| clip_fraction | 0.395 | +| clip_range | 0.114 | +| entropy_loss | -7.06 | +| explained_variance | -0.129 | +| learning_rate | 0.000143 | +| loss | -0.0614 | +| n_updates | 5592 | +| policy_gradient_loss | -0.0328 | +| value_loss | 0.00015 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.281 | +| time/ | | +| fps | 1335 | +| iterations | 1400 | +| time_elapsed | 2147 | +| total_timesteps | 2867200 | +| train/ | | +| approx_kl | 0.039292328 | +| clip_fraction | 0.431 | +| clip_range | 0.114 | +| entropy_loss | -7.09 | +| explained_variance | 0.0111 | +| learning_rate | 0.000143 | +| loss | -0.0541 | +| n_updates | 5596 | +| policy_gradient_loss | -0.0337 | +| value_loss | 0.000151 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.281 | +| time/ | | +| fps | 1335 | +| iterations | 1401 | +| time_elapsed | 2148 | +| total_timesteps | 2869248 | +| train/ | | +| approx_kl | 0.048223484 | +| clip_fraction | 0.419 | +| clip_range | 0.114 | +| entropy_loss | -7.17 | +| explained_variance | -0.163 | +| learning_rate | 0.000143 | +| loss | -0.0554 | +| n_updates | 5600 | +| policy_gradient_loss | -0.0359 | +| value_loss | 0.000151 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.28 | +| time/ | | +| fps | 1335 | +| iterations | 1402 | +| time_elapsed | 2150 | +| total_timesteps | 2871296 | +| train/ | | +| approx_kl | 0.041905902 | +| clip_fraction | 0.425 | +| clip_range | 0.114 | +| entropy_loss | -7.21 | +| explained_variance | -0.158 | +| learning_rate | 0.000143 | +| loss | -0.0574 | +| n_updates | 5604 | +| policy_gradient_loss | -0.0349 | +| value_loss | 0.000112 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.28 | +| time/ | | +| fps | 1335 | +| iterations | 1403 | +| time_elapsed | 2151 | +| total_timesteps | 2873344 | +| train/ | | +| approx_kl | 0.0460908 | +| clip_fraction | 0.426 | +| clip_range | 0.114 | +| entropy_loss | -7.1 | +| explained_variance | -0.0646 | +| learning_rate | 0.000143 | +| loss | -0.0529 | +| n_updates | 5608 | +| policy_gradient_loss | -0.0355 | +| value_loss | 7.39e-05 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 1335 | +| iterations | 1404 | +| time_elapsed | 2153 | +| total_timesteps | 2875392 | +| train/ | | +| approx_kl | 0.040639658 | +| clip_fraction | 0.426 | +| clip_range | 0.114 | +| entropy_loss | -7.13 | +| explained_variance | -0.159 | +| learning_rate | 0.000143 | +| loss | -0.0398 | +| n_updates | 5612 | +| policy_gradient_loss | -0.0294 | +| value_loss | 0.000122 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.29 | +| time/ | | +| fps | 1335 | +| iterations | 1405 | +| time_elapsed | 2154 | +| total_timesteps | 2877440 | +| train/ | | +| approx_kl | 0.04161924 | +| clip_fraction | 0.397 | +| clip_range | 0.114 | +| entropy_loss | -7.02 | +| explained_variance | -0.0942 | +| learning_rate | 0.000143 | +| loss | -0.0495 | +| n_updates | 5616 | +| policy_gradient_loss | -0.0299 | +| value_loss | 0.000191 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.292 | +| time/ | | +| fps | 1335 | +| iterations | 1406 | +| time_elapsed | 2156 | +| total_timesteps | 2879488 | +| train/ | | +| approx_kl | 0.03658392 | +| clip_fraction | 0.411 | +| clip_range | 0.114 | +| entropy_loss | -7.09 | +| explained_variance | -0.0335 | +| learning_rate | 0.000143 | +| loss | -0.0449 | +| n_updates | 5620 | +| policy_gradient_loss | -0.0287 | +| value_loss | 0.000195 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.289 | +| time/ | | +| fps | 1335 | +| iterations | 1407 | +| time_elapsed | 2157 | +| total_timesteps | 2881536 | +| train/ | | +| approx_kl | 0.042510618 | +| clip_fraction | 0.409 | +| clip_range | 0.114 | +| entropy_loss | -7.08 | +| explained_variance | -0.142 | +| learning_rate | 0.000143 | +| loss | -0.0643 | +| n_updates | 5624 | +| policy_gradient_loss | -0.034 | +| value_loss | 0.000124 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.288 | +| time/ | | +| fps | 1335 | +| iterations | 1408 | +| time_elapsed | 2158 | +| total_timesteps | 2883584 | +| train/ | | +| approx_kl | 0.04868161 | +| clip_fraction | 0.402 | +| clip_range | 0.114 | +| entropy_loss | -7.02 | +| explained_variance | -0.142 | +| learning_rate | 0.000143 | +| loss | -0.0507 | +| n_updates | 5628 | +| policy_gradient_loss | -0.0325 | +| value_loss | 0.000198 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.288 | +| time/ | | +| fps | 1335 | +| iterations | 1409 | +| time_elapsed | 2160 | +| total_timesteps | 2885632 | +| train/ | | +| approx_kl | 0.039022923 | +| clip_fraction | 0.413 | +| clip_range | 0.114 | +| entropy_loss | -7 | +| explained_variance | -0.116 | +| learning_rate | 0.000143 | +| loss | -0.0589 | +| n_updates | 5632 | +| policy_gradient_loss | -0.0333 | +| value_loss | 0.000221 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.294 | +| time/ | | +| fps | 1335 | +| iterations | 1410 | +| time_elapsed | 2161 | +| total_timesteps | 2887680 | +| train/ | | +| approx_kl | 0.043662235 | +| clip_fraction | 0.406 | +| clip_range | 0.114 | +| entropy_loss | -7.08 | +| explained_variance | -0.0517 | +| learning_rate | 0.000143 | +| loss | -0.0524 | +| n_updates | 5636 | +| policy_gradient_loss | -0.0358 | +| value_loss | 0.000175 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.294 | +| time/ | | +| fps | 1335 | +| iterations | 1411 | +| time_elapsed | 2163 | +| total_timesteps | 2889728 | +| train/ | | +| approx_kl | 0.044115163 | +| clip_fraction | 0.397 | +| clip_range | 0.114 | +| entropy_loss | -7.04 | +| explained_variance | -0.0296 | +| learning_rate | 0.000143 | +| loss | -0.0547 | +| n_updates | 5640 | +| policy_gradient_loss | -0.0319 | +| value_loss | 0.000197 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.286 | +| time/ | | +| fps | 1335 | +| iterations | 1412 | +| time_elapsed | 2164 | +| total_timesteps | 2891776 | +| train/ | | +| approx_kl | 0.04421326 | +| clip_fraction | 0.4 | +| clip_range | 0.114 | +| entropy_loss | -7.15 | +| explained_variance | -0.234 | +| learning_rate | 0.000143 | +| loss | -0.0439 | +| n_updates | 5644 | +| policy_gradient_loss | -0.0295 | +| value_loss | 0.000223 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.286 | +| time/ | | +| fps | 1336 | +| iterations | 1413 | +| time_elapsed | 2166 | +| total_timesteps | 2893824 | +| train/ | | +| approx_kl | 0.04228192 | +| clip_fraction | 0.405 | +| clip_range | 0.114 | +| entropy_loss | -7 | +| explained_variance | -0.154 | +| learning_rate | 0.000143 | +| loss | -0.0583 | +| n_updates | 5648 | +| policy_gradient_loss | -0.0343 | +| value_loss | 0.000223 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.29 | +| time/ | | +| fps | 1336 | +| iterations | 1414 | +| time_elapsed | 2167 | +| total_timesteps | 2895872 | +| train/ | | +| approx_kl | 0.045037784 | +| clip_fraction | 0.405 | +| clip_range | 0.114 | +| entropy_loss | -7.17 | +| explained_variance | -0.0756 | +| learning_rate | 0.000143 | +| loss | -0.0455 | +| n_updates | 5652 | +| policy_gradient_loss | -0.0311 | +| value_loss | 0.000198 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.29 | +| time/ | | +| fps | 1336 | +| iterations | 1415 | +| time_elapsed | 2168 | +| total_timesteps | 2897920 | +| train/ | | +| approx_kl | 0.037843965 | +| clip_fraction | 0.418 | +| clip_range | 0.114 | +| entropy_loss | -7.05 | +| explained_variance | -0.163 | +| learning_rate | 0.000143 | +| loss | -0.0537 | +| n_updates | 5656 | +| policy_gradient_loss | -0.0313 | +| value_loss | 0.000205 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.295 | +| time/ | | +| fps | 1336 | +| iterations | 1416 | +| time_elapsed | 2170 | +| total_timesteps | 2899968 | +| train/ | | +| approx_kl | 0.049143568 | +| clip_fraction | 0.4 | +| clip_range | 0.114 | +| entropy_loss | -7.11 | +| explained_variance | -0.288 | +| learning_rate | 0.000143 | +| loss | -0.0584 | +| n_updates | 5660 | +| policy_gradient_loss | -0.0329 | +| value_loss | 0.000139 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 1336 | +| iterations | 1417 | +| time_elapsed | 2171 | +| total_timesteps | 2902016 | +| train/ | | +| approx_kl | 0.043348167 | +| clip_fraction | 0.41 | +| clip_range | 0.114 | +| entropy_loss | -7.08 | +| explained_variance | -0.0234 | +| learning_rate | 0.000143 | +| loss | -0.0539 | +| n_updates | 5664 | +| policy_gradient_loss | -0.031 | +| value_loss | 0.000255 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 1336 | +| iterations | 1418 | +| time_elapsed | 2173 | +| total_timesteps | 2904064 | +| train/ | | +| approx_kl | 0.037259758 | +| clip_fraction | 0.414 | +| clip_range | 0.114 | +| entropy_loss | -7.09 | +| explained_variance | -0.26 | +| learning_rate | 0.000143 | +| loss | -0.0515 | +| n_updates | 5668 | +| policy_gradient_loss | -0.0321 | +| value_loss | 0.000148 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 1336 | +| iterations | 1419 | +| time_elapsed | 2174 | +| total_timesteps | 2906112 | +| train/ | | +| approx_kl | 0.03858436 | +| clip_fraction | 0.415 | +| clip_range | 0.114 | +| entropy_loss | -7.15 | +| explained_variance | -0.0298 | +| learning_rate | 0.000142 | +| loss | -0.0546 | +| n_updates | 5672 | +| policy_gradient_loss | -0.0303 | +| value_loss | 0.000219 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 1336 | +| iterations | 1420 | +| time_elapsed | 2175 | +| total_timesteps | 2908160 | +| train/ | | +| approx_kl | 0.041014723 | +| clip_fraction | 0.44 | +| clip_range | 0.114 | +| entropy_loss | -7.05 | +| explained_variance | -0.159 | +| learning_rate | 0.000142 | +| loss | -0.0534 | +| n_updates | 5676 | +| policy_gradient_loss | -0.0346 | +| value_loss | 0.000215 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.298 | +| time/ | | +| fps | 1336 | +| iterations | 1421 | +| time_elapsed | 2177 | +| total_timesteps | 2910208 | +| train/ | | +| approx_kl | 0.03790237 | +| clip_fraction | 0.423 | +| clip_range | 0.114 | +| entropy_loss | -7.1 | +| explained_variance | -0.36 | +| learning_rate | 0.000142 | +| loss | -0.0671 | +| n_updates | 5680 | +| policy_gradient_loss | -0.0376 | +| value_loss | 0.00012 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 1336 | +| iterations | 1422 | +| time_elapsed | 2178 | +| total_timesteps | 2912256 | +| train/ | | +| approx_kl | 0.04910571 | +| clip_fraction | 0.411 | +| clip_range | 0.114 | +| entropy_loss | -7.07 | +| explained_variance | -0.247 | +| learning_rate | 0.000142 | +| loss | -0.0545 | +| n_updates | 5684 | +| policy_gradient_loss | -0.0347 | +| value_loss | 0.000144 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.291 | +| time/ | | +| fps | 1336 | +| iterations | 1423 | +| time_elapsed | 2180 | +| total_timesteps | 2914304 | +| train/ | | +| approx_kl | 0.04777319 | +| clip_fraction | 0.432 | +| clip_range | 0.114 | +| entropy_loss | -7.11 | +| explained_variance | -0.0655 | +| learning_rate | 0.000142 | +| loss | -0.0514 | +| n_updates | 5688 | +| policy_gradient_loss | -0.0348 | +| value_loss | 0.000106 | +---------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.278 | +| time/ | | +| fps | 1336 | +| iterations | 1424 | +| time_elapsed | 2181 | +| total_timesteps | 2916352 | +| train/ | | +| approx_kl | 0.0396612 | +| clip_fraction | 0.404 | +| clip_range | 0.114 | +| entropy_loss | -7.04 | +| explained_variance | 0.0745 | +| learning_rate | 0.000142 | +| loss | -0.0469 | +| n_updates | 5692 | +| policy_gradient_loss | -0.0297 | +| value_loss | 0.000137 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.276 | +| time/ | | +| fps | 1336 | +| iterations | 1425 | +| time_elapsed | 2182 | +| total_timesteps | 2918400 | +| train/ | | +| approx_kl | 0.032418385 | +| clip_fraction | 0.376 | +| clip_range | 0.114 | +| entropy_loss | -6.99 | +| explained_variance | -0.11 | +| learning_rate | 0.000142 | +| loss | -0.0459 | +| n_updates | 5696 | +| policy_gradient_loss | -0.0267 | +| value_loss | 0.000338 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.278 | +| time/ | | +| fps | 1336 | +| iterations | 1426 | +| time_elapsed | 2184 | +| total_timesteps | 2920448 | +| train/ | | +| approx_kl | 0.045780707 | +| clip_fraction | 0.435 | +| clip_range | 0.114 | +| entropy_loss | -7.04 | +| explained_variance | -0.344 | +| learning_rate | 0.000142 | +| loss | -0.0598 | +| n_updates | 5700 | +| policy_gradient_loss | -0.0382 | +| value_loss | 0.000131 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 1336 | +| iterations | 1427 | +| time_elapsed | 2185 | +| total_timesteps | 2922496 | +| train/ | | +| approx_kl | 0.037576098 | +| clip_fraction | 0.438 | +| clip_range | 0.113 | +| entropy_loss | -7.03 | +| explained_variance | -0.194 | +| learning_rate | 0.000142 | +| loss | -0.0588 | +| n_updates | 5704 | +| policy_gradient_loss | -0.0356 | +| value_loss | 0.000125 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 1337 | +| iterations | 1428 | +| time_elapsed | 2187 | +| total_timesteps | 2924544 | +| train/ | | +| approx_kl | 0.04474552 | +| clip_fraction | 0.428 | +| clip_range | 0.113 | +| entropy_loss | -7.18 | +| explained_variance | -0.115 | +| learning_rate | 0.000142 | +| loss | -0.0601 | +| n_updates | 5708 | +| policy_gradient_loss | -0.033 | +| value_loss | 0.000177 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 1337 | +| iterations | 1429 | +| time_elapsed | 2188 | +| total_timesteps | 2926592 | +| train/ | | +| approx_kl | 0.045719415 | +| clip_fraction | 0.443 | +| clip_range | 0.113 | +| entropy_loss | -6.95 | +| explained_variance | -0.0675 | +| learning_rate | 0.000142 | +| loss | -0.0539 | +| n_updates | 5712 | +| policy_gradient_loss | -0.0358 | +| value_loss | 0.000168 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.278 | +| time/ | | +| fps | 1337 | +| iterations | 1430 | +| time_elapsed | 2190 | +| total_timesteps | 2928640 | +| train/ | | +| approx_kl | 0.048754822 | +| clip_fraction | 0.435 | +| clip_range | 0.113 | +| entropy_loss | -7.05 | +| explained_variance | -0.427 | +| learning_rate | 0.000142 | +| loss | -0.0662 | +| n_updates | 5716 | +| policy_gradient_loss | -0.0388 | +| value_loss | 0.000115 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 1337 | +| iterations | 1431 | +| time_elapsed | 2191 | +| total_timesteps | 2930688 | +| train/ | | +| approx_kl | 0.046580475 | +| clip_fraction | 0.409 | +| clip_range | 0.113 | +| entropy_loss | -7.06 | +| explained_variance | -0.0995 | +| learning_rate | 0.000142 | +| loss | -0.048 | +| n_updates | 5720 | +| policy_gradient_loss | -0.0327 | +| value_loss | 0.000209 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.271 | +| time/ | | +| fps | 1337 | +| iterations | 1432 | +| time_elapsed | 2193 | +| total_timesteps | 2932736 | +| train/ | | +| approx_kl | 0.044215005 | +| clip_fraction | 0.443 | +| clip_range | 0.113 | +| entropy_loss | -7.09 | +| explained_variance | -0.222 | +| learning_rate | 0.000142 | +| loss | -0.0651 | +| n_updates | 5724 | +| policy_gradient_loss | -0.0435 | +| value_loss | 6.96e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.264 | +| time/ | | +| fps | 1337 | +| iterations | 1433 | +| time_elapsed | 2194 | +| total_timesteps | 2934784 | +| train/ | | +| approx_kl | 0.043844275 | +| clip_fraction | 0.405 | +| clip_range | 0.113 | +| entropy_loss | -6.98 | +| explained_variance | -0.0159 | +| learning_rate | 0.000142 | +| loss | -0.0487 | +| n_updates | 5728 | +| policy_gradient_loss | -0.0314 | +| value_loss | 0.000144 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.261 | +| time/ | | +| fps | 1337 | +| iterations | 1434 | +| time_elapsed | 2195 | +| total_timesteps | 2936832 | +| train/ | | +| approx_kl | 0.04407951 | +| clip_fraction | 0.404 | +| clip_range | 0.113 | +| entropy_loss | -7.15 | +| explained_variance | -0.294 | +| learning_rate | 0.000142 | +| loss | -0.0569 | +| n_updates | 5732 | +| policy_gradient_loss | -0.0365 | +| value_loss | 0.000115 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.26 | +| time/ | | +| fps | 1337 | +| iterations | 1435 | +| time_elapsed | 2197 | +| total_timesteps | 2938880 | +| train/ | | +| approx_kl | 0.044900127 | +| clip_fraction | 0.404 | +| clip_range | 0.113 | +| entropy_loss | -7.02 | +| explained_variance | -0.023 | +| learning_rate | 0.000142 | +| loss | -0.055 | +| n_updates | 5736 | +| policy_gradient_loss | -0.0316 | +| value_loss | 0.000186 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.256 | +| time/ | | +| fps | 1337 | +| iterations | 1436 | +| time_elapsed | 2198 | +| total_timesteps | 2940928 | +| train/ | | +| approx_kl | 0.041073278 | +| clip_fraction | 0.402 | +| clip_range | 0.113 | +| entropy_loss | -7.06 | +| explained_variance | -0.0114 | +| learning_rate | 0.000142 | +| loss | -0.0557 | +| n_updates | 5740 | +| policy_gradient_loss | -0.0331 | +| value_loss | 0.000172 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.256 | +| time/ | | +| fps | 1337 | +| iterations | 1437 | +| time_elapsed | 2200 | +| total_timesteps | 2942976 | +| train/ | | +| approx_kl | 0.046193242 | +| clip_fraction | 0.415 | +| clip_range | 0.113 | +| entropy_loss | -7.13 | +| explained_variance | -0.0243 | +| learning_rate | 0.000142 | +| loss | -0.0537 | +| n_updates | 5744 | +| policy_gradient_loss | -0.036 | +| value_loss | 0.000186 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.257 | +| time/ | | +| fps | 1337 | +| iterations | 1438 | +| time_elapsed | 2201 | +| total_timesteps | 2945024 | +| train/ | | +| approx_kl | 0.03696326 | +| clip_fraction | 0.425 | +| clip_range | 0.113 | +| entropy_loss | -7.18 | +| explained_variance | -0.585 | +| learning_rate | 0.000142 | +| loss | -0.0521 | +| n_updates | 5748 | +| policy_gradient_loss | -0.0337 | +| value_loss | 0.000112 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.257 | +| time/ | | +| fps | 1337 | +| iterations | 1439 | +| time_elapsed | 2202 | +| total_timesteps | 2947072 | +| train/ | | +| approx_kl | 0.050227135 | +| clip_fraction | 0.404 | +| clip_range | 0.113 | +| entropy_loss | -7.23 | +| explained_variance | -0.063 | +| learning_rate | 0.000142 | +| loss | -0.05 | +| n_updates | 5752 | +| policy_gradient_loss | -0.0305 | +| value_loss | 0.000162 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.261 | +| time/ | | +| fps | 1337 | +| iterations | 1440 | +| time_elapsed | 2204 | +| total_timesteps | 2949120 | +| train/ | | +| approx_kl | 0.044896137 | +| clip_fraction | 0.411 | +| clip_range | 0.113 | +| entropy_loss | -7.21 | +| explained_variance | -0.0194 | +| learning_rate | 0.000142 | +| loss | -0.0541 | +| n_updates | 5756 | +| policy_gradient_loss | -0.0347 | +| value_loss | 0.000167 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.261 | +| time/ | | +| fps | 1337 | +| iterations | 1441 | +| time_elapsed | 2205 | +| total_timesteps | 2951168 | +| train/ | | +| approx_kl | 0.03498939 | +| clip_fraction | 0.408 | +| clip_range | 0.113 | +| entropy_loss | -7.25 | +| explained_variance | -0.103 | +| learning_rate | 0.000142 | +| loss | -0.0505 | +| n_updates | 5760 | +| policy_gradient_loss | -0.0325 | +| value_loss | 0.000155 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.262 | +| time/ | | +| fps | 1337 | +| iterations | 1442 | +| time_elapsed | 2207 | +| total_timesteps | 2953216 | +| train/ | | +| approx_kl | 0.035327613 | +| clip_fraction | 0.433 | +| clip_range | 0.113 | +| entropy_loss | -7.22 | +| explained_variance | -0.394 | +| learning_rate | 0.000142 | +| loss | -0.0585 | +| n_updates | 5764 | +| policy_gradient_loss | -0.0376 | +| value_loss | 7.19e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.261 | +| time/ | | +| fps | 1338 | +| iterations | 1443 | +| time_elapsed | 2208 | +| total_timesteps | 2955264 | +| train/ | | +| approx_kl | 0.04138695 | +| clip_fraction | 0.388 | +| clip_range | 0.113 | +| entropy_loss | -7.18 | +| explained_variance | -0.107 | +| learning_rate | 0.000142 | +| loss | -0.0562 | +| n_updates | 5768 | +| policy_gradient_loss | -0.0331 | +| value_loss | 9.2e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.267 | +| time/ | | +| fps | 1338 | +| iterations | 1444 | +| time_elapsed | 2210 | +| total_timesteps | 2957312 | +| train/ | | +| approx_kl | 0.035451442 | +| clip_fraction | 0.415 | +| clip_range | 0.113 | +| entropy_loss | -7.01 | +| explained_variance | 0.0741 | +| learning_rate | 0.000141 | +| loss | -0.0493 | +| n_updates | 5772 | +| policy_gradient_loss | -0.0277 | +| value_loss | 0.000117 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.267 | +| time/ | | +| fps | 1338 | +| iterations | 1445 | +| time_elapsed | 2211 | +| total_timesteps | 2959360 | +| train/ | | +| approx_kl | 0.038007893 | +| clip_fraction | 0.383 | +| clip_range | 0.113 | +| entropy_loss | -7.05 | +| explained_variance | 0.00563 | +| learning_rate | 0.000141 | +| loss | -0.053 | +| n_updates | 5776 | +| policy_gradient_loss | -0.0299 | +| value_loss | 0.000247 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 1338 | +| iterations | 1446 | +| time_elapsed | 2212 | +| total_timesteps | 2961408 | +| train/ | | +| approx_kl | 0.046415143 | +| clip_fraction | 0.441 | +| clip_range | 0.113 | +| entropy_loss | -7.15 | +| explained_variance | -0.42 | +| learning_rate | 0.000141 | +| loss | -0.0622 | +| n_updates | 5780 | +| policy_gradient_loss | -0.0398 | +| value_loss | 0.000111 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.284 | +| time/ | | +| fps | 1338 | +| iterations | 1447 | +| time_elapsed | 2214 | +| total_timesteps | 2963456 | +| train/ | | +| approx_kl | 0.04503192 | +| clip_fraction | 0.393 | +| clip_range | 0.113 | +| entropy_loss | -6.9 | +| explained_variance | -0.19 | +| learning_rate | 0.000141 | +| loss | -0.0524 | +| n_updates | 5784 | +| policy_gradient_loss | -0.0341 | +| value_loss | 0.00017 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.284 | +| time/ | | +| fps | 1338 | +| iterations | 1448 | +| time_elapsed | 2215 | +| total_timesteps | 2965504 | +| train/ | | +| approx_kl | 0.048364278 | +| clip_fraction | 0.423 | +| clip_range | 0.113 | +| entropy_loss | -6.85 | +| explained_variance | -0.0964 | +| learning_rate | 0.000141 | +| loss | -0.0453 | +| n_updates | 5788 | +| policy_gradient_loss | -0.031 | +| value_loss | 0.000206 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.281 | +| time/ | | +| fps | 1338 | +| iterations | 1449 | +| time_elapsed | 2217 | +| total_timesteps | 2967552 | +| train/ | | +| approx_kl | 0.045839585 | +| clip_fraction | 0.393 | +| clip_range | 0.113 | +| entropy_loss | -7.01 | +| explained_variance | -0.153 | +| learning_rate | 0.000141 | +| loss | -0.0539 | +| n_updates | 5792 | +| policy_gradient_loss | -0.0359 | +| value_loss | 0.000179 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.281 | +| time/ | | +| fps | 1338 | +| iterations | 1450 | +| time_elapsed | 2218 | +| total_timesteps | 2969600 | +| train/ | | +| approx_kl | 0.04319995 | +| clip_fraction | 0.412 | +| clip_range | 0.113 | +| entropy_loss | -7.07 | +| explained_variance | -0.0184 | +| learning_rate | 0.000141 | +| loss | -0.0539 | +| n_updates | 5796 | +| policy_gradient_loss | -0.0337 | +| value_loss | 0.000166 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.28 | +| time/ | | +| fps | 1338 | +| iterations | 1451 | +| time_elapsed | 2219 | +| total_timesteps | 2971648 | +| train/ | | +| approx_kl | 0.044666857 | +| clip_fraction | 0.432 | +| clip_range | 0.113 | +| entropy_loss | -7.11 | +| explained_variance | -0.315 | +| learning_rate | 0.000141 | +| loss | -0.0509 | +| n_updates | 5800 | +| policy_gradient_loss | -0.0345 | +| value_loss | 9.76e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.271 | +| time/ | | +| fps | 1338 | +| iterations | 1452 | +| time_elapsed | 2221 | +| total_timesteps | 2973696 | +| train/ | | +| approx_kl | 0.04289577 | +| clip_fraction | 0.412 | +| clip_range | 0.113 | +| entropy_loss | -6.81 | +| explained_variance | -0.254 | +| learning_rate | 0.000141 | +| loss | -0.0556 | +| n_updates | 5804 | +| policy_gradient_loss | -0.0317 | +| value_loss | 0.000124 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.271 | +| time/ | | +| fps | 1338 | +| iterations | 1453 | +| time_elapsed | 2222 | +| total_timesteps | 2975744 | +| train/ | | +| approx_kl | 0.042209912 | +| clip_fraction | 0.402 | +| clip_range | 0.113 | +| entropy_loss | -6.89 | +| explained_variance | -0.072 | +| learning_rate | 0.000141 | +| loss | -0.0469 | +| n_updates | 5808 | +| policy_gradient_loss | -0.0316 | +| value_loss | 0.000206 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.272 | +| time/ | | +| fps | 1338 | +| iterations | 1454 | +| time_elapsed | 2224 | +| total_timesteps | 2977792 | +| train/ | | +| approx_kl | 0.0341927 | +| clip_fraction | 0.402 | +| clip_range | 0.113 | +| entropy_loss | -7.09 | +| explained_variance | -0.161 | +| learning_rate | 0.000141 | +| loss | -0.0479 | +| n_updates | 5812 | +| policy_gradient_loss | -0.0298 | +| value_loss | 0.000216 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 1338 | +| iterations | 1455 | +| time_elapsed | 2225 | +| total_timesteps | 2979840 | +| train/ | | +| approx_kl | 0.042372115 | +| clip_fraction | 0.414 | +| clip_range | 0.113 | +| entropy_loss | -7.12 | +| explained_variance | -0.13 | +| learning_rate | 0.000141 | +| loss | -0.0606 | +| n_updates | 5816 | +| policy_gradient_loss | -0.0332 | +| value_loss | 0.00012 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 1338 | +| iterations | 1456 | +| time_elapsed | 2227 | +| total_timesteps | 2981888 | +| train/ | | +| approx_kl | 0.03637072 | +| clip_fraction | 0.419 | +| clip_range | 0.113 | +| entropy_loss | -7.19 | +| explained_variance | -0.0392 | +| learning_rate | 0.000141 | +| loss | -0.0569 | +| n_updates | 5820 | +| policy_gradient_loss | -0.0341 | +| value_loss | 0.000172 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.273 | +| time/ | | +| fps | 1338 | +| iterations | 1457 | +| time_elapsed | 2228 | +| total_timesteps | 2983936 | +| train/ | | +| approx_kl | 0.042352945 | +| clip_fraction | 0.436 | +| clip_range | 0.113 | +| entropy_loss | -7.15 | +| explained_variance | -0.0685 | +| learning_rate | 0.000141 | +| loss | -0.0444 | +| n_updates | 5824 | +| policy_gradient_loss | -0.0331 | +| value_loss | 0.00023 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.272 | +| time/ | | +| fps | 1339 | +| iterations | 1458 | +| time_elapsed | 2229 | +| total_timesteps | 2985984 | +| train/ | | +| approx_kl | 0.04000942 | +| clip_fraction | 0.409 | +| clip_range | 0.113 | +| entropy_loss | -7.05 | +| explained_variance | -0.16 | +| learning_rate | 0.000141 | +| loss | -0.0583 | +| n_updates | 5828 | +| policy_gradient_loss | -0.0348 | +| value_loss | 0.000109 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.273 | +| time/ | | +| fps | 1339 | +| iterations | 1459 | +| time_elapsed | 2231 | +| total_timesteps | 2988032 | +| train/ | | +| approx_kl | 0.044658456 | +| clip_fraction | 0.436 | +| clip_range | 0.113 | +| entropy_loss | -6.9 | +| explained_variance | -0.00423 | +| learning_rate | 0.000141 | +| loss | -0.0464 | +| n_updates | 5832 | +| policy_gradient_loss | -0.0328 | +| value_loss | 0.000188 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.273 | +| time/ | | +| fps | 1339 | +| iterations | 1460 | +| time_elapsed | 2232 | +| total_timesteps | 2990080 | +| train/ | | +| approx_kl | 0.04763888 | +| clip_fraction | 0.416 | +| clip_range | 0.113 | +| entropy_loss | -7.26 | +| explained_variance | -0.14 | +| learning_rate | 0.000141 | +| loss | -0.0549 | +| n_updates | 5836 | +| policy_gradient_loss | -0.038 | +| value_loss | 0.000146 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.277 | +| time/ | | +| fps | 1339 | +| iterations | 1461 | +| time_elapsed | 2234 | +| total_timesteps | 2992128 | +| train/ | | +| approx_kl | 0.044841126 | +| clip_fraction | 0.415 | +| clip_range | 0.113 | +| entropy_loss | -7.15 | +| explained_variance | -0.218 | +| learning_rate | 0.000141 | +| loss | -0.0548 | +| n_updates | 5840 | +| policy_gradient_loss | -0.0322 | +| value_loss | 0.000156 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.276 | +| time/ | | +| fps | 1339 | +| iterations | 1462 | +| time_elapsed | 2235 | +| total_timesteps | 2994176 | +| train/ | | +| approx_kl | 0.044420294 | +| clip_fraction | 0.375 | +| clip_range | 0.113 | +| entropy_loss | -7.1 | +| explained_variance | 0.0156 | +| learning_rate | 0.000141 | +| loss | -0.0389 | +| n_updates | 5844 | +| policy_gradient_loss | -0.0295 | +| value_loss | 0.000291 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.278 | +| time/ | | +| fps | 1339 | +| iterations | 1463 | +| time_elapsed | 2237 | +| total_timesteps | 2996224 | +| train/ | | +| approx_kl | 0.0382881 | +| clip_fraction | 0.393 | +| clip_range | 0.113 | +| entropy_loss | -7.01 | +| explained_variance | 0.0202 | +| learning_rate | 0.000141 | +| loss | -0.056 | +| n_updates | 5848 | +| policy_gradient_loss | -0.0357 | +| value_loss | 0.00024 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.28 | +| time/ | | +| fps | 1339 | +| iterations | 1464 | +| time_elapsed | 2238 | +| total_timesteps | 2998272 | +| train/ | | +| approx_kl | 0.039374076 | +| clip_fraction | 0.406 | +| clip_range | 0.113 | +| entropy_loss | -7.09 | +| explained_variance | -0.103 | +| learning_rate | 0.000141 | +| loss | -0.0574 | +| n_updates | 5852 | +| policy_gradient_loss | -0.0357 | +| value_loss | 0.000226 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 1339 | +| iterations | 1465 | +| time_elapsed | 2239 | +| total_timesteps | 3000320 | +| train/ | | +| approx_kl | 0.03768971 | +| clip_fraction | 0.4 | +| clip_range | 0.113 | +| entropy_loss | -7.13 | +| explained_variance | -0.0192 | +| learning_rate | 0.000141 | +| loss | -0.0526 | +| n_updates | 5856 | +| policy_gradient_loss | -0.0325 | +| value_loss | 0.000312 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 1339 | +| iterations | 1466 | +| time_elapsed | 2241 | +| total_timesteps | 3002368 | +| train/ | | +| approx_kl | 0.038696405 | +| clip_fraction | 0.406 | +| clip_range | 0.112 | +| entropy_loss | -7.22 | +| explained_variance | 0.00982 | +| learning_rate | 0.000141 | +| loss | -0.0633 | +| n_updates | 5860 | +| policy_gradient_loss | -0.0375 | +| value_loss | 0.000142 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.294 | +| time/ | | +| fps | 1339 | +| iterations | 1467 | +| time_elapsed | 2242 | +| total_timesteps | 3004416 | +| train/ | | +| approx_kl | 0.032316618 | +| clip_fraction | 0.392 | +| clip_range | 0.112 | +| entropy_loss | -7.24 | +| explained_variance | 0.075 | +| learning_rate | 0.000141 | +| loss | -0.0624 | +| n_updates | 5864 | +| policy_gradient_loss | -0.0348 | +| value_loss | 0.000169 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.295 | +| time/ | | +| fps | 1339 | +| iterations | 1468 | +| time_elapsed | 2244 | +| total_timesteps | 3006464 | +| train/ | | +| approx_kl | 0.041202858 | +| clip_fraction | 0.4 | +| clip_range | 0.112 | +| entropy_loss | -7 | +| explained_variance | -0.151 | +| learning_rate | 0.000141 | +| loss | -0.0579 | +| n_updates | 5868 | +| policy_gradient_loss | -0.0334 | +| value_loss | 0.000426 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.295 | +| time/ | | +| fps | 1339 | +| iterations | 1469 | +| time_elapsed | 2245 | +| total_timesteps | 3008512 | +| train/ | | +| approx_kl | 0.037098087 | +| clip_fraction | 0.387 | +| clip_range | 0.112 | +| entropy_loss | -6.92 | +| explained_variance | -0.0597 | +| learning_rate | 0.00014 | +| loss | -0.0435 | +| n_updates | 5872 | +| policy_gradient_loss | -0.0304 | +| value_loss | 0.000428 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.295 | +| time/ | | +| fps | 1339 | +| iterations | 1470 | +| time_elapsed | 2247 | +| total_timesteps | 3010560 | +| train/ | | +| approx_kl | 0.043842413 | +| clip_fraction | 0.461 | +| clip_range | 0.112 | +| entropy_loss | -7.25 | +| explained_variance | -1.18 | +| learning_rate | 0.00014 | +| loss | -0.0639 | +| n_updates | 5876 | +| policy_gradient_loss | -0.0449 | +| value_loss | 0.000121 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.295 | +| time/ | | +| fps | 1339 | +| iterations | 1471 | +| time_elapsed | 2248 | +| total_timesteps | 3012608 | +| train/ | | +| approx_kl | 0.045666203 | +| clip_fraction | 0.452 | +| clip_range | 0.112 | +| entropy_loss | -7.27 | +| explained_variance | -0.291 | +| learning_rate | 0.00014 | +| loss | -0.0544 | +| n_updates | 5880 | +| policy_gradient_loss | -0.0361 | +| value_loss | 0.000168 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.295 | +| time/ | | +| fps | 1339 | +| iterations | 1472 | +| time_elapsed | 2249 | +| total_timesteps | 3014656 | +| train/ | | +| approx_kl | 0.048375927 | +| clip_fraction | 0.446 | +| clip_range | 0.112 | +| entropy_loss | -7.19 | +| explained_variance | -0.47 | +| learning_rate | 0.00014 | +| loss | -0.0569 | +| n_updates | 5884 | +| policy_gradient_loss | -0.0389 | +| value_loss | 0.000145 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.285 | +| time/ | | +| fps | 1339 | +| iterations | 1473 | +| time_elapsed | 2251 | +| total_timesteps | 3016704 | +| train/ | | +| approx_kl | 0.03951422 | +| clip_fraction | 0.419 | +| clip_range | 0.112 | +| entropy_loss | -7.14 | +| explained_variance | -0.28 | +| learning_rate | 0.00014 | +| loss | -0.0535 | +| n_updates | 5888 | +| policy_gradient_loss | -0.0352 | +| value_loss | 9.17e-05 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.286 | +| time/ | | +| fps | 1339 | +| iterations | 1474 | +| time_elapsed | 2252 | +| total_timesteps | 3018752 | +| train/ | | +| approx_kl | 0.03961143 | +| clip_fraction | 0.397 | +| clip_range | 0.112 | +| entropy_loss | -7.1 | +| explained_variance | -0.197 | +| learning_rate | 0.00014 | +| loss | -0.0554 | +| n_updates | 5892 | +| policy_gradient_loss | -0.0332 | +| value_loss | 0.000117 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.292 | +| time/ | | +| fps | 1340 | +| iterations | 1475 | +| time_elapsed | 2254 | +| total_timesteps | 3020800 | +| train/ | | +| approx_kl | 0.039968453 | +| clip_fraction | 0.369 | +| clip_range | 0.112 | +| entropy_loss | -7.17 | +| explained_variance | -0.12 | +| learning_rate | 0.00014 | +| loss | -0.047 | +| n_updates | 5896 | +| policy_gradient_loss | -0.0284 | +| value_loss | 0.000175 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.287 | +| time/ | | +| fps | 1340 | +| iterations | 1476 | +| time_elapsed | 2255 | +| total_timesteps | 3022848 | +| train/ | | +| approx_kl | 0.03880289 | +| clip_fraction | 0.39 | +| clip_range | 0.112 | +| entropy_loss | -7.09 | +| explained_variance | -0.0469 | +| learning_rate | 0.00014 | +| loss | -0.0447 | +| n_updates | 5900 | +| policy_gradient_loss | -0.0297 | +| value_loss | 0.000288 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.288 | +| time/ | | +| fps | 1340 | +| iterations | 1477 | +| time_elapsed | 2257 | +| total_timesteps | 3024896 | +| train/ | | +| approx_kl | 0.04299476 | +| clip_fraction | 0.404 | +| clip_range | 0.112 | +| entropy_loss | -7.26 | +| explained_variance | -0.169 | +| learning_rate | 0.00014 | +| loss | -0.0554 | +| n_updates | 5904 | +| policy_gradient_loss | -0.0362 | +| value_loss | 0.00024 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.294 | +| time/ | | +| fps | 1340 | +| iterations | 1478 | +| time_elapsed | 2258 | +| total_timesteps | 3026944 | +| train/ | | +| approx_kl | 0.041452892 | +| clip_fraction | 0.429 | +| clip_range | 0.112 | +| entropy_loss | -7.24 | +| explained_variance | -0.172 | +| learning_rate | 0.00014 | +| loss | -0.0527 | +| n_updates | 5908 | +| policy_gradient_loss | -0.0353 | +| value_loss | 0.000127 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.294 | +| time/ | | +| fps | 1340 | +| iterations | 1479 | +| time_elapsed | 2260 | +| total_timesteps | 3028992 | +| train/ | | +| approx_kl | 0.03625284 | +| clip_fraction | 0.369 | +| clip_range | 0.112 | +| entropy_loss | -7.08 | +| explained_variance | 0.0554 | +| learning_rate | 0.00014 | +| loss | -0.0551 | +| n_updates | 5912 | +| policy_gradient_loss | -0.0313 | +| value_loss | 0.000182 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 1340 | +| iterations | 1480 | +| time_elapsed | 2261 | +| total_timesteps | 3031040 | +| train/ | | +| approx_kl | 0.041963123 | +| clip_fraction | 0.41 | +| clip_range | 0.112 | +| entropy_loss | -7.27 | +| explained_variance | -0.326 | +| learning_rate | 0.00014 | +| loss | -0.0622 | +| n_updates | 5916 | +| policy_gradient_loss | -0.0344 | +| value_loss | 0.000164 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.295 | +| time/ | | +| fps | 1340 | +| iterations | 1481 | +| time_elapsed | 2262 | +| total_timesteps | 3033088 | +| train/ | | +| approx_kl | 0.03762938 | +| clip_fraction | 0.347 | +| clip_range | 0.112 | +| entropy_loss | -7.23 | +| explained_variance | -0.0768 | +| learning_rate | 0.00014 | +| loss | -0.0402 | +| n_updates | 5920 | +| policy_gradient_loss | -0.023 | +| value_loss | 0.000448 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.28 | +| time/ | | +| fps | 1340 | +| iterations | 1482 | +| time_elapsed | 2264 | +| total_timesteps | 3035136 | +| train/ | | +| approx_kl | 0.039275385 | +| clip_fraction | 0.439 | +| clip_range | 0.112 | +| entropy_loss | -7.1 | +| explained_variance | -0.0415 | +| learning_rate | 0.00014 | +| loss | -0.0557 | +| n_updates | 5924 | +| policy_gradient_loss | -0.0382 | +| value_loss | 0.000148 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.28 | +| time/ | | +| fps | 1340 | +| iterations | 1483 | +| time_elapsed | 2265 | +| total_timesteps | 3037184 | +| train/ | | +| approx_kl | 0.03802162 | +| clip_fraction | 0.387 | +| clip_range | 0.112 | +| entropy_loss | -7.19 | +| explained_variance | -0.0716 | +| learning_rate | 0.00014 | +| loss | -0.0501 | +| n_updates | 5928 | +| policy_gradient_loss | -0.0308 | +| value_loss | 0.00021 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.28 | +| time/ | | +| fps | 1340 | +| iterations | 1484 | +| time_elapsed | 2267 | +| total_timesteps | 3039232 | +| train/ | | +| approx_kl | 0.046409328 | +| clip_fraction | 0.398 | +| clip_range | 0.112 | +| entropy_loss | -7.24 | +| explained_variance | -0.34 | +| learning_rate | 0.00014 | +| loss | -0.0634 | +| n_updates | 5932 | +| policy_gradient_loss | -0.0372 | +| value_loss | 9.76e-05 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.278 | +| time/ | | +| fps | 1340 | +| iterations | 1485 | +| time_elapsed | 2268 | +| total_timesteps | 3041280 | +| train/ | | +| approx_kl | 0.0355194 | +| clip_fraction | 0.406 | +| clip_range | 0.112 | +| entropy_loss | -7.24 | +| explained_variance | -0.101 | +| learning_rate | 0.00014 | +| loss | -0.0481 | +| n_updates | 5936 | +| policy_gradient_loss | -0.0319 | +| value_loss | 0.000154 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 1340 | +| iterations | 1486 | +| time_elapsed | 2270 | +| total_timesteps | 3043328 | +| train/ | | +| approx_kl | 0.046385568 | +| clip_fraction | 0.416 | +| clip_range | 0.112 | +| entropy_loss | -7.1 | +| explained_variance | -0.128 | +| learning_rate | 0.00014 | +| loss | -0.0523 | +| n_updates | 5940 | +| policy_gradient_loss | -0.0333 | +| value_loss | 0.000155 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.278 | +| time/ | | +| fps | 1340 | +| iterations | 1487 | +| time_elapsed | 2271 | +| total_timesteps | 3045376 | +| train/ | | +| approx_kl | 0.043196216 | +| clip_fraction | 0.407 | +| clip_range | 0.112 | +| entropy_loss | -7.08 | +| explained_variance | -0.212 | +| learning_rate | 0.00014 | +| loss | -0.0498 | +| n_updates | 5944 | +| policy_gradient_loss | -0.0339 | +| value_loss | 9.81e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.28 | +| time/ | | +| fps | 1340 | +| iterations | 1488 | +| time_elapsed | 2272 | +| total_timesteps | 3047424 | +| train/ | | +| approx_kl | 0.04109673 | +| clip_fraction | 0.409 | +| clip_range | 0.112 | +| entropy_loss | -7.16 | +| explained_variance | -0.0741 | +| learning_rate | 0.00014 | +| loss | -0.0531 | +| n_updates | 5948 | +| policy_gradient_loss | -0.0328 | +| value_loss | 0.000176 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 1340 | +| iterations | 1489 | +| time_elapsed | 2274 | +| total_timesteps | 3049472 | +| train/ | | +| approx_kl | 0.03883143 | +| clip_fraction | 0.374 | +| clip_range | 0.112 | +| entropy_loss | -7.27 | +| explained_variance | 0.0277 | +| learning_rate | 0.00014 | +| loss | -0.052 | +| n_updates | 5952 | +| policy_gradient_loss | -0.0307 | +| value_loss | 0.000211 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.285 | +| time/ | | +| fps | 1340 | +| iterations | 1490 | +| time_elapsed | 2275 | +| total_timesteps | 3051520 | +| train/ | | +| approx_kl | 0.038545877 | +| clip_fraction | 0.418 | +| clip_range | 0.112 | +| entropy_loss | -7.2 | +| explained_variance | -0.33 | +| learning_rate | 0.00014 | +| loss | -0.0665 | +| n_updates | 5956 | +| policy_gradient_loss | -0.0372 | +| value_loss | 0.000111 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.29 | +| time/ | | +| fps | 1340 | +| iterations | 1491 | +| time_elapsed | 2277 | +| total_timesteps | 3053568 | +| train/ | | +| approx_kl | 0.034744333 | +| clip_fraction | 0.411 | +| clip_range | 0.112 | +| entropy_loss | -7.11 | +| explained_variance | -0.166 | +| learning_rate | 0.00014 | +| loss | -0.0382 | +| n_updates | 5960 | +| policy_gradient_loss | -0.0283 | +| value_loss | 0.000143 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.29 | +| time/ | | +| fps | 1340 | +| iterations | 1492 | +| time_elapsed | 2278 | +| total_timesteps | 3055616 | +| train/ | | +| approx_kl | 0.048325107 | +| clip_fraction | 0.411 | +| clip_range | 0.112 | +| entropy_loss | -7.21 | +| explained_variance | -0.223 | +| learning_rate | 0.00014 | +| loss | -0.0573 | +| n_updates | 5964 | +| policy_gradient_loss | -0.0345 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.289 | +| time/ | | +| fps | 1341 | +| iterations | 1493 | +| time_elapsed | 2280 | +| total_timesteps | 3057664 | +| train/ | | +| approx_kl | 0.047722954 | +| clip_fraction | 0.398 | +| clip_range | 0.112 | +| entropy_loss | -7.27 | +| explained_variance | -0.0115 | +| learning_rate | 0.000139 | +| loss | -0.0448 | +| n_updates | 5968 | +| policy_gradient_loss | -0.0297 | +| value_loss | 0.000274 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.289 | +| time/ | | +| fps | 1341 | +| iterations | 1494 | +| time_elapsed | 2281 | +| total_timesteps | 3059712 | +| train/ | | +| approx_kl | 0.036968984 | +| clip_fraction | 0.386 | +| clip_range | 0.112 | +| entropy_loss | -7.23 | +| explained_variance | -0.201 | +| learning_rate | 0.000139 | +| loss | -0.0492 | +| n_updates | 5972 | +| policy_gradient_loss | -0.0336 | +| value_loss | 0.000197 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.284 | +| time/ | | +| fps | 1341 | +| iterations | 1495 | +| time_elapsed | 2282 | +| total_timesteps | 3061760 | +| train/ | | +| approx_kl | 0.038789395 | +| clip_fraction | 0.402 | +| clip_range | 0.112 | +| entropy_loss | -7.21 | +| explained_variance | -0.17 | +| learning_rate | 0.000139 | +| loss | -0.0584 | +| n_updates | 5976 | +| policy_gradient_loss | -0.0352 | +| value_loss | 0.000158 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.287 | +| time/ | | +| fps | 1341 | +| iterations | 1496 | +| time_elapsed | 2284 | +| total_timesteps | 3063808 | +| train/ | | +| approx_kl | 0.038195893 | +| clip_fraction | 0.42 | +| clip_range | 0.112 | +| entropy_loss | -7.21 | +| explained_variance | -0.0479 | +| learning_rate | 0.000139 | +| loss | -0.0597 | +| n_updates | 5980 | +| policy_gradient_loss | -0.0362 | +| value_loss | 0.000174 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 1341 | +| iterations | 1497 | +| time_elapsed | 2285 | +| total_timesteps | 3065856 | +| train/ | | +| approx_kl | 0.039726846 | +| clip_fraction | 0.398 | +| clip_range | 0.112 | +| entropy_loss | -7.2 | +| explained_variance | -0.054 | +| learning_rate | 0.000139 | +| loss | -0.0549 | +| n_updates | 5984 | +| policy_gradient_loss | -0.0333 | +| value_loss | 0.000171 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 1341 | +| iterations | 1498 | +| time_elapsed | 2287 | +| total_timesteps | 3067904 | +| train/ | | +| approx_kl | 0.038791828 | +| clip_fraction | 0.41 | +| clip_range | 0.112 | +| entropy_loss | -7.27 | +| explained_variance | -0.0172 | +| learning_rate | 0.000139 | +| loss | -0.0605 | +| n_updates | 5988 | +| policy_gradient_loss | -0.0341 | +| value_loss | 0.000116 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.287 | +| time/ | | +| fps | 1341 | +| iterations | 1499 | +| time_elapsed | 2288 | +| total_timesteps | 3069952 | +| train/ | | +| approx_kl | 0.040195487 | +| clip_fraction | 0.412 | +| clip_range | 0.112 | +| entropy_loss | -7.24 | +| explained_variance | -0.236 | +| learning_rate | 0.000139 | +| loss | -0.0583 | +| n_updates | 5992 | +| policy_gradient_loss | -0.0397 | +| value_loss | 7.95e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.295 | +| time/ | | +| fps | 1341 | +| iterations | 1500 | +| time_elapsed | 2290 | +| total_timesteps | 3072000 | +| train/ | | +| approx_kl | 0.03556535 | +| clip_fraction | 0.383 | +| clip_range | 0.112 | +| entropy_loss | -7.28 | +| explained_variance | -0.0393 | +| learning_rate | 0.000139 | +| loss | -0.056 | +| n_updates | 5996 | +| policy_gradient_loss | -0.0324 | +| value_loss | 0.000251 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.293 | +| time/ | | +| fps | 1341 | +| iterations | 1501 | +| time_elapsed | 2291 | +| total_timesteps | 3074048 | +| train/ | | +| approx_kl | 0.035839982 | +| clip_fraction | 0.378 | +| clip_range | 0.112 | +| entropy_loss | -7.11 | +| explained_variance | -0.0934 | +| learning_rate | 0.000139 | +| loss | -0.0487 | +| n_updates | 6000 | +| policy_gradient_loss | -0.0335 | +| value_loss | 0.000169 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1341 | +| iterations | 1502 | +| time_elapsed | 2292 | +| total_timesteps | 3076096 | +| train/ | | +| approx_kl | 0.036767125 | +| clip_fraction | 0.425 | +| clip_range | 0.112 | +| entropy_loss | -7.2 | +| explained_variance | -0.387 | +| learning_rate | 0.000139 | +| loss | -0.0564 | +| n_updates | 6004 | +| policy_gradient_loss | -0.0345 | +| value_loss | 0.000132 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 1341 | +| iterations | 1503 | +| time_elapsed | 2294 | +| total_timesteps | 3078144 | +| train/ | | +| approx_kl | 0.03401714 | +| clip_fraction | 0.38 | +| clip_range | 0.112 | +| entropy_loss | -7.33 | +| explained_variance | 0.0409 | +| learning_rate | 0.000139 | +| loss | -0.0424 | +| n_updates | 6008 | +| policy_gradient_loss | -0.0257 | +| value_loss | 0.000255 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.306 | +| time/ | | +| fps | 1341 | +| iterations | 1504 | +| time_elapsed | 2295 | +| total_timesteps | 3080192 | +| train/ | | +| approx_kl | 0.043379724 | +| clip_fraction | 0.429 | +| clip_range | 0.112 | +| entropy_loss | -7.15 | +| explained_variance | -0.104 | +| learning_rate | 0.000139 | +| loss | -0.0489 | +| n_updates | 6012 | +| policy_gradient_loss | -0.0356 | +| value_loss | 0.0003 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 1341 | +| iterations | 1505 | +| time_elapsed | 2297 | +| total_timesteps | 3082240 | +| train/ | | +| approx_kl | 0.0373282 | +| clip_fraction | 0.402 | +| clip_range | 0.111 | +| entropy_loss | -7.26 | +| explained_variance | -0.232 | +| learning_rate | 0.000139 | +| loss | -0.0518 | +| n_updates | 6016 | +| policy_gradient_loss | -0.0324 | +| value_loss | 0.000189 | +--------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 1341 | +| iterations | 1506 | +| time_elapsed | 2298 | +| total_timesteps | 3084288 | +| train/ | | +| approx_kl | 0.04004969 | +| clip_fraction | 0.431 | +| clip_range | 0.111 | +| entropy_loss | -7.23 | +| explained_variance | -0.204 | +| learning_rate | 0.000139 | +| loss | -0.0706 | +| n_updates | 6020 | +| policy_gradient_loss | -0.0387 | +| value_loss | 0.0001 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.295 | +| time/ | | +| fps | 1341 | +| iterations | 1507 | +| time_elapsed | 2300 | +| total_timesteps | 3086336 | +| train/ | | +| approx_kl | 0.043640405 | +| clip_fraction | 0.424 | +| clip_range | 0.111 | +| entropy_loss | -7.32 | +| explained_variance | -0.0708 | +| learning_rate | 0.000139 | +| loss | -0.0583 | +| n_updates | 6024 | +| policy_gradient_loss | -0.0345 | +| value_loss | 0.000169 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.291 | +| time/ | | +| fps | 1341 | +| iterations | 1508 | +| time_elapsed | 2301 | +| total_timesteps | 3088384 | +| train/ | | +| approx_kl | 0.041795257 | +| clip_fraction | 0.417 | +| clip_range | 0.111 | +| entropy_loss | -7.19 | +| explained_variance | -0.249 | +| learning_rate | 0.000139 | +| loss | -0.0577 | +| n_updates | 6028 | +| policy_gradient_loss | -0.0329 | +| value_loss | 0.000119 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.291 | +| time/ | | +| fps | 1341 | +| iterations | 1509 | +| time_elapsed | 2302 | +| total_timesteps | 3090432 | +| train/ | | +| approx_kl | 0.037858028 | +| clip_fraction | 0.397 | +| clip_range | 0.111 | +| entropy_loss | -7.16 | +| explained_variance | -0.0474 | +| learning_rate | 0.000139 | +| loss | -0.0541 | +| n_updates | 6032 | +| policy_gradient_loss | -0.0333 | +| value_loss | 0.000239 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.292 | +| time/ | | +| fps | 1341 | +| iterations | 1510 | +| time_elapsed | 2304 | +| total_timesteps | 3092480 | +| train/ | | +| approx_kl | 0.037562653 | +| clip_fraction | 0.403 | +| clip_range | 0.111 | +| entropy_loss | -7.27 | +| explained_variance | -0.0152 | +| learning_rate | 0.000139 | +| loss | -0.0548 | +| n_updates | 6036 | +| policy_gradient_loss | -0.0306 | +| value_loss | 0.000133 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.291 | +| time/ | | +| fps | 1342 | +| iterations | 1511 | +| time_elapsed | 2305 | +| total_timesteps | 3094528 | +| train/ | | +| approx_kl | 0.034233507 | +| clip_fraction | 0.401 | +| clip_range | 0.111 | +| entropy_loss | -7.22 | +| explained_variance | -0.223 | +| learning_rate | 0.000139 | +| loss | -0.0611 | +| n_updates | 6040 | +| policy_gradient_loss | -0.0352 | +| value_loss | 0.000102 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.292 | +| time/ | | +| fps | 1342 | +| iterations | 1512 | +| time_elapsed | 2307 | +| total_timesteps | 3096576 | +| train/ | | +| approx_kl | 0.04345246 | +| clip_fraction | 0.414 | +| clip_range | 0.111 | +| entropy_loss | -7.13 | +| explained_variance | -0.0418 | +| learning_rate | 0.000139 | +| loss | -0.0511 | +| n_updates | 6044 | +| policy_gradient_loss | -0.0287 | +| value_loss | 0.000275 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.291 | +| time/ | | +| fps | 1342 | +| iterations | 1513 | +| time_elapsed | 2308 | +| total_timesteps | 3098624 | +| train/ | | +| approx_kl | 0.03984225 | +| clip_fraction | 0.39 | +| clip_range | 0.111 | +| entropy_loss | -7.21 | +| explained_variance | -0.163 | +| learning_rate | 0.000139 | +| loss | -0.0507 | +| n_updates | 6048 | +| policy_gradient_loss | -0.0321 | +| value_loss | 0.000189 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.287 | +| time/ | | +| fps | 1342 | +| iterations | 1514 | +| time_elapsed | 2310 | +| total_timesteps | 3100672 | +| train/ | | +| approx_kl | 0.038751464 | +| clip_fraction | 0.381 | +| clip_range | 0.111 | +| entropy_loss | -7.29 | +| explained_variance | -0.0785 | +| learning_rate | 0.000139 | +| loss | -0.047 | +| n_updates | 6052 | +| policy_gradient_loss | -0.0329 | +| value_loss | 0.000207 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.286 | +| time/ | | +| fps | 1342 | +| iterations | 1515 | +| time_elapsed | 2311 | +| total_timesteps | 3102720 | +| train/ | | +| approx_kl | 0.040847786 | +| clip_fraction | 0.375 | +| clip_range | 0.111 | +| entropy_loss | -7.29 | +| explained_variance | -0.157 | +| learning_rate | 0.000139 | +| loss | -0.0506 | +| n_updates | 6056 | +| policy_gradient_loss | -0.0292 | +| value_loss | 0.000174 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 1342 | +| iterations | 1516 | +| time_elapsed | 2313 | +| total_timesteps | 3104768 | +| train/ | | +| approx_kl | 0.039230064 | +| clip_fraction | 0.416 | +| clip_range | 0.111 | +| entropy_loss | -7.23 | +| explained_variance | -0.117 | +| learning_rate | 0.000139 | +| loss | -0.051 | +| n_updates | 6060 | +| policy_gradient_loss | -0.0338 | +| value_loss | 0.00019 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.293 | +| time/ | | +| fps | 1342 | +| iterations | 1517 | +| time_elapsed | 2314 | +| total_timesteps | 3106816 | +| train/ | | +| approx_kl | 0.032336555 | +| clip_fraction | 0.386 | +| clip_range | 0.111 | +| entropy_loss | -7.31 | +| explained_variance | -0.0128 | +| learning_rate | 0.000139 | +| loss | -0.0507 | +| n_updates | 6064 | +| policy_gradient_loss | -0.0305 | +| value_loss | 0.000269 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.293 | +| time/ | | +| fps | 1342 | +| iterations | 1518 | +| time_elapsed | 2315 | +| total_timesteps | 3108864 | +| train/ | | +| approx_kl | 0.039835565 | +| clip_fraction | 0.392 | +| clip_range | 0.111 | +| entropy_loss | -7.27 | +| explained_variance | -0.166 | +| learning_rate | 0.000138 | +| loss | -0.0553 | +| n_updates | 6068 | +| policy_gradient_loss | -0.034 | +| value_loss | 0.000154 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 1342 | +| iterations | 1519 | +| time_elapsed | 2317 | +| total_timesteps | 3110912 | +| train/ | | +| approx_kl | 0.042189226 | +| clip_fraction | 0.423 | +| clip_range | 0.111 | +| entropy_loss | -7.3 | +| explained_variance | -0.286 | +| learning_rate | 0.000138 | +| loss | -0.0455 | +| n_updates | 6072 | +| policy_gradient_loss | -0.038 | +| value_loss | 0.000107 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.298 | +| time/ | | +| fps | 1342 | +| iterations | 1520 | +| time_elapsed | 2318 | +| total_timesteps | 3112960 | +| train/ | | +| approx_kl | 0.04375161 | +| clip_fraction | 0.408 | +| clip_range | 0.111 | +| entropy_loss | -7.42 | +| explained_variance | -0.207 | +| learning_rate | 0.000138 | +| loss | -0.054 | +| n_updates | 6076 | +| policy_gradient_loss | -0.036 | +| value_loss | 0.000108 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.298 | +| time/ | | +| fps | 1342 | +| iterations | 1521 | +| time_elapsed | 2320 | +| total_timesteps | 3115008 | +| train/ | | +| approx_kl | 0.036340296 | +| clip_fraction | 0.384 | +| clip_range | 0.111 | +| entropy_loss | -7.44 | +| explained_variance | -0.0474 | +| learning_rate | 0.000138 | +| loss | -0.0467 | +| n_updates | 6080 | +| policy_gradient_loss | -0.0301 | +| value_loss | 0.000214 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.295 | +| time/ | | +| fps | 1342 | +| iterations | 1522 | +| time_elapsed | 2321 | +| total_timesteps | 3117056 | +| train/ | | +| approx_kl | 0.04572852 | +| clip_fraction | 0.387 | +| clip_range | 0.111 | +| entropy_loss | -7.31 | +| explained_variance | -0.265 | +| learning_rate | 0.000138 | +| loss | -0.0605 | +| n_updates | 6084 | +| policy_gradient_loss | -0.0372 | +| value_loss | 0.000116 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.291 | +| time/ | | +| fps | 1342 | +| iterations | 1523 | +| time_elapsed | 2322 | +| total_timesteps | 3119104 | +| train/ | | +| approx_kl | 0.043825936 | +| clip_fraction | 0.4 | +| clip_range | 0.111 | +| entropy_loss | -7.16 | +| explained_variance | -0.141 | +| learning_rate | 0.000138 | +| loss | -0.0548 | +| n_updates | 6088 | +| policy_gradient_loss | -0.0333 | +| value_loss | 0.000186 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.29 | +| time/ | | +| fps | 1342 | +| iterations | 1524 | +| time_elapsed | 2324 | +| total_timesteps | 3121152 | +| train/ | | +| approx_kl | 0.04751043 | +| clip_fraction | 0.379 | +| clip_range | 0.111 | +| entropy_loss | -7.33 | +| explained_variance | -0.254 | +| learning_rate | 0.000138 | +| loss | -0.0515 | +| n_updates | 6092 | +| policy_gradient_loss | -0.0341 | +| value_loss | 0.000131 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.289 | +| time/ | | +| fps | 1342 | +| iterations | 1525 | +| time_elapsed | 2325 | +| total_timesteps | 3123200 | +| train/ | | +| approx_kl | 0.038203422 | +| clip_fraction | 0.38 | +| clip_range | 0.111 | +| entropy_loss | -7.22 | +| explained_variance | -0.0571 | +| learning_rate | 0.000138 | +| loss | -0.0568 | +| n_updates | 6096 | +| policy_gradient_loss | -0.0338 | +| value_loss | 0.0002 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 1342 | +| iterations | 1526 | +| time_elapsed | 2327 | +| total_timesteps | 3125248 | +| train/ | | +| approx_kl | 0.03807134 | +| clip_fraction | 0.43 | +| clip_range | 0.111 | +| entropy_loss | -7.27 | +| explained_variance | -0.191 | +| learning_rate | 0.000138 | +| loss | -0.0529 | +| n_updates | 6100 | +| policy_gradient_loss | -0.033 | +| value_loss | 0.000127 | +---------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 1342 | +| iterations | 1527 | +| time_elapsed | 2328 | +| total_timesteps | 3127296 | +| train/ | | +| approx_kl | 0.0340171 | +| clip_fraction | 0.387 | +| clip_range | 0.111 | +| entropy_loss | -7.11 | +| explained_variance | -0.169 | +| learning_rate | 0.000138 | +| loss | -0.0379 | +| n_updates | 6104 | +| policy_gradient_loss | -0.0296 | +| value_loss | 0.000237 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.27 | +| time/ | | +| fps | 1343 | +| iterations | 1528 | +| time_elapsed | 2330 | +| total_timesteps | 3129344 | +| train/ | | +| approx_kl | 0.034804884 | +| clip_fraction | 0.408 | +| clip_range | 0.111 | +| entropy_loss | -7.26 | +| explained_variance | -0.203 | +| learning_rate | 0.000138 | +| loss | -0.0553 | +| n_updates | 6108 | +| policy_gradient_loss | -0.0344 | +| value_loss | 0.000154 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.273 | +| time/ | | +| fps | 1343 | +| iterations | 1529 | +| time_elapsed | 2331 | +| total_timesteps | 3131392 | +| train/ | | +| approx_kl | 0.037405573 | +| clip_fraction | 0.392 | +| clip_range | 0.111 | +| entropy_loss | -7.28 | +| explained_variance | -0.047 | +| learning_rate | 0.000138 | +| loss | -0.0582 | +| n_updates | 6112 | +| policy_gradient_loss | -0.0338 | +| value_loss | 0.000207 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.276 | +| time/ | | +| fps | 1343 | +| iterations | 1530 | +| time_elapsed | 2333 | +| total_timesteps | 3133440 | +| train/ | | +| approx_kl | 0.04107657 | +| clip_fraction | 0.393 | +| clip_range | 0.111 | +| entropy_loss | -7.41 | +| explained_variance | -0.0796 | +| learning_rate | 0.000138 | +| loss | -0.0407 | +| n_updates | 6116 | +| policy_gradient_loss | -0.0274 | +| value_loss | 0.000263 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.271 | +| time/ | | +| fps | 1343 | +| iterations | 1531 | +| time_elapsed | 2334 | +| total_timesteps | 3135488 | +| train/ | | +| approx_kl | 0.034677062 | +| clip_fraction | 0.392 | +| clip_range | 0.111 | +| entropy_loss | -7.34 | +| explained_variance | -0.138 | +| learning_rate | 0.000138 | +| loss | -0.0511 | +| n_updates | 6120 | +| policy_gradient_loss | -0.0313 | +| value_loss | 0.000284 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.271 | +| time/ | | +| fps | 1343 | +| iterations | 1532 | +| time_elapsed | 2335 | +| total_timesteps | 3137536 | +| train/ | | +| approx_kl | 0.04093521 | +| clip_fraction | 0.421 | +| clip_range | 0.111 | +| entropy_loss | -7.28 | +| explained_variance | -0.251 | +| learning_rate | 0.000138 | +| loss | -0.0553 | +| n_updates | 6124 | +| policy_gradient_loss | -0.0349 | +| value_loss | 0.00013 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.271 | +| time/ | | +| fps | 1343 | +| iterations | 1533 | +| time_elapsed | 2337 | +| total_timesteps | 3139584 | +| train/ | | +| approx_kl | 0.037772797 | +| clip_fraction | 0.422 | +| clip_range | 0.111 | +| entropy_loss | -7.31 | +| explained_variance | -0.0334 | +| learning_rate | 0.000138 | +| loss | -0.0495 | +| n_updates | 6128 | +| policy_gradient_loss | -0.0321 | +| value_loss | 0.000163 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.276 | +| time/ | | +| fps | 1343 | +| iterations | 1534 | +| time_elapsed | 2338 | +| total_timesteps | 3141632 | +| train/ | | +| approx_kl | 0.046846986 | +| clip_fraction | 0.401 | +| clip_range | 0.111 | +| entropy_loss | -7.37 | +| explained_variance | -0.29 | +| learning_rate | 0.000138 | +| loss | -0.0562 | +| n_updates | 6132 | +| policy_gradient_loss | -0.0319 | +| value_loss | 0.000126 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.274 | +| time/ | | +| fps | 1343 | +| iterations | 1535 | +| time_elapsed | 2340 | +| total_timesteps | 3143680 | +| train/ | | +| approx_kl | 0.02928849 | +| clip_fraction | 0.389 | +| clip_range | 0.111 | +| entropy_loss | -7.19 | +| explained_variance | -0.0646 | +| learning_rate | 0.000138 | +| loss | -0.0434 | +| n_updates | 6136 | +| policy_gradient_loss | -0.0259 | +| value_loss | 0.00028 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.273 | +| time/ | | +| fps | 1343 | +| iterations | 1536 | +| time_elapsed | 2341 | +| total_timesteps | 3145728 | +| train/ | | +| approx_kl | 0.042263523 | +| clip_fraction | 0.382 | +| clip_range | 0.111 | +| entropy_loss | -7.34 | +| explained_variance | -0.17 | +| learning_rate | 0.000138 | +| loss | -0.0504 | +| n_updates | 6140 | +| policy_gradient_loss | -0.0313 | +| value_loss | 0.000137 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.27 | +| time/ | | +| fps | 1343 | +| iterations | 1537 | +| time_elapsed | 2342 | +| total_timesteps | 3147776 | +| train/ | | +| approx_kl | 0.034008063 | +| clip_fraction | 0.395 | +| clip_range | 0.111 | +| entropy_loss | -7.3 | +| explained_variance | -0.161 | +| learning_rate | 0.000138 | +| loss | -0.0605 | +| n_updates | 6144 | +| policy_gradient_loss | -0.0342 | +| value_loss | 0.000111 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.271 | +| time/ | | +| fps | 1343 | +| iterations | 1538 | +| time_elapsed | 2344 | +| total_timesteps | 3149824 | +| train/ | | +| approx_kl | 0.03400258 | +| clip_fraction | 0.377 | +| clip_range | 0.111 | +| entropy_loss | -7.25 | +| explained_variance | -0.0522 | +| learning_rate | 0.000138 | +| loss | -0.0459 | +| n_updates | 6148 | +| policy_gradient_loss | -0.03 | +| value_loss | 0.000202 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.269 | +| time/ | | +| fps | 1343 | +| iterations | 1539 | +| time_elapsed | 2345 | +| total_timesteps | 3151872 | +| train/ | | +| approx_kl | 0.038832176 | +| clip_fraction | 0.382 | +| clip_range | 0.111 | +| entropy_loss | -7.26 | +| explained_variance | -0.169 | +| learning_rate | 0.000138 | +| loss | -0.0524 | +| n_updates | 6152 | +| policy_gradient_loss | -0.0294 | +| value_loss | 0.000176 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.264 | +| time/ | | +| fps | 1343 | +| iterations | 1540 | +| time_elapsed | 2347 | +| total_timesteps | 3153920 | +| train/ | | +| approx_kl | 0.035801142 | +| clip_fraction | 0.387 | +| clip_range | 0.111 | +| entropy_loss | -7.24 | +| explained_variance | -0.149 | +| learning_rate | 0.000138 | +| loss | -0.0519 | +| n_updates | 6156 | +| policy_gradient_loss | -0.0298 | +| value_loss | 0.00023 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.264 | +| time/ | | +| fps | 1343 | +| iterations | 1541 | +| time_elapsed | 2348 | +| total_timesteps | 3155968 | +| train/ | | +| approx_kl | 0.039266355 | +| clip_fraction | 0.397 | +| clip_range | 0.111 | +| entropy_loss | -7.27 | +| explained_variance | -0.0506 | +| learning_rate | 0.000138 | +| loss | -0.0482 | +| n_updates | 6160 | +| policy_gradient_loss | -0.0319 | +| value_loss | 0.000253 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.264 | +| time/ | | +| fps | 1343 | +| iterations | 1542 | +| time_elapsed | 2350 | +| total_timesteps | 3158016 | +| train/ | | +| approx_kl | 0.03400415 | +| clip_fraction | 0.384 | +| clip_range | 0.111 | +| entropy_loss | -7.33 | +| explained_variance | -0.213 | +| learning_rate | 0.000138 | +| loss | -0.0536 | +| n_updates | 6164 | +| policy_gradient_loss | -0.0359 | +| value_loss | 0.000171 | +---------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.257 | +| time/ | | +| fps | 1343 | +| iterations | 1543 | +| time_elapsed | 2351 | +| total_timesteps | 3160064 | +| train/ | | +| approx_kl | 0.0378254 | +| clip_fraction | 0.398 | +| clip_range | 0.111 | +| entropy_loss | -7.34 | +| explained_variance | -0.264 | +| learning_rate | 0.000137 | +| loss | -0.0529 | +| n_updates | 6168 | +| policy_gradient_loss | -0.0333 | +| value_loss | 0.000141 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.257 | +| time/ | | +| fps | 1343 | +| iterations | 1544 | +| time_elapsed | 2352 | +| total_timesteps | 3162112 | +| train/ | | +| approx_kl | 0.033342596 | +| clip_fraction | 0.38 | +| clip_range | 0.11 | +| entropy_loss | -7.21 | +| explained_variance | -0.0537 | +| learning_rate | 0.000137 | +| loss | -0.0427 | +| n_updates | 6172 | +| policy_gradient_loss | -0.0284 | +| value_loss | 0.000266 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.257 | +| time/ | | +| fps | 1343 | +| iterations | 1545 | +| time_elapsed | 2354 | +| total_timesteps | 3164160 | +| train/ | | +| approx_kl | 0.033175603 | +| clip_fraction | 0.408 | +| clip_range | 0.11 | +| entropy_loss | -7.3 | +| explained_variance | -0.0984 | +| learning_rate | 0.000137 | +| loss | -0.0514 | +| n_updates | 6176 | +| policy_gradient_loss | -0.0342 | +| value_loss | 0.000224 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.269 | +| time/ | | +| fps | 1344 | +| iterations | 1546 | +| time_elapsed | 2355 | +| total_timesteps | 3166208 | +| train/ | | +| approx_kl | 0.03273232 | +| clip_fraction | 0.37 | +| clip_range | 0.11 | +| entropy_loss | -7.33 | +| explained_variance | -0.0849 | +| learning_rate | 0.000137 | +| loss | -0.048 | +| n_updates | 6180 | +| policy_gradient_loss | -0.032 | +| value_loss | 0.000219 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.265 | +| time/ | | +| fps | 1344 | +| iterations | 1547 | +| time_elapsed | 2357 | +| total_timesteps | 3168256 | +| train/ | | +| approx_kl | 0.031401828 | +| clip_fraction | 0.38 | +| clip_range | 0.11 | +| entropy_loss | -7.23 | +| explained_variance | -0.0506 | +| learning_rate | 0.000137 | +| loss | -0.0431 | +| n_updates | 6184 | +| policy_gradient_loss | -0.0282 | +| value_loss | 0.000343 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.265 | +| time/ | | +| fps | 1344 | +| iterations | 1548 | +| time_elapsed | 2358 | +| total_timesteps | 3170304 | +| train/ | | +| approx_kl | 0.03241528 | +| clip_fraction | 0.409 | +| clip_range | 0.11 | +| entropy_loss | -7.18 | +| explained_variance | -0.179 | +| learning_rate | 0.000137 | +| loss | -0.06 | +| n_updates | 6188 | +| policy_gradient_loss | -0.0358 | +| value_loss | 0.000128 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.265 | +| time/ | | +| fps | 1344 | +| iterations | 1549 | +| time_elapsed | 2360 | +| total_timesteps | 3172352 | +| train/ | | +| approx_kl | 0.038306803 | +| clip_fraction | 0.402 | +| clip_range | 0.11 | +| entropy_loss | -7.37 | +| explained_variance | -0.108 | +| learning_rate | 0.000137 | +| loss | -0.0547 | +| n_updates | 6192 | +| policy_gradient_loss | -0.0339 | +| value_loss | 0.000208 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.265 | +| time/ | | +| fps | 1344 | +| iterations | 1550 | +| time_elapsed | 2361 | +| total_timesteps | 3174400 | +| train/ | | +| approx_kl | 0.038979888 | +| clip_fraction | 0.404 | +| clip_range | 0.11 | +| entropy_loss | -7.36 | +| explained_variance | -0.158 | +| learning_rate | 0.000137 | +| loss | -0.0495 | +| n_updates | 6196 | +| policy_gradient_loss | -0.032 | +| value_loss | 0.000241 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.264 | +| time/ | | +| fps | 1344 | +| iterations | 1551 | +| time_elapsed | 2362 | +| total_timesteps | 3176448 | +| train/ | | +| approx_kl | 0.03538666 | +| clip_fraction | 0.404 | +| clip_range | 0.11 | +| entropy_loss | -7.34 | +| explained_variance | -0.196 | +| learning_rate | 0.000137 | +| loss | -0.0363 | +| n_updates | 6200 | +| policy_gradient_loss | -0.0328 | +| value_loss | 0.000177 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.264 | +| time/ | | +| fps | 1344 | +| iterations | 1552 | +| time_elapsed | 2364 | +| total_timesteps | 3178496 | +| train/ | | +| approx_kl | 0.034169193 | +| clip_fraction | 0.395 | +| clip_range | 0.11 | +| entropy_loss | -7.33 | +| explained_variance | -0.21 | +| learning_rate | 0.000137 | +| loss | -0.0487 | +| n_updates | 6204 | +| policy_gradient_loss | -0.0354 | +| value_loss | 0.000144 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.269 | +| time/ | | +| fps | 1344 | +| iterations | 1553 | +| time_elapsed | 2365 | +| total_timesteps | 3180544 | +| train/ | | +| approx_kl | 0.035835378 | +| clip_fraction | 0.421 | +| clip_range | 0.11 | +| entropy_loss | -7.24 | +| explained_variance | -0.182 | +| learning_rate | 0.000137 | +| loss | -0.047 | +| n_updates | 6208 | +| policy_gradient_loss | -0.033 | +| value_loss | 8.72e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.269 | +| time/ | | +| fps | 1344 | +| iterations | 1554 | +| time_elapsed | 2367 | +| total_timesteps | 3182592 | +| train/ | | +| approx_kl | 0.03382215 | +| clip_fraction | 0.385 | +| clip_range | 0.11 | +| entropy_loss | -7.22 | +| explained_variance | -0.153 | +| learning_rate | 0.000137 | +| loss | -0.044 | +| n_updates | 6212 | +| policy_gradient_loss | -0.0284 | +| value_loss | 0.000155 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.266 | +| time/ | | +| fps | 1344 | +| iterations | 1555 | +| time_elapsed | 2368 | +| total_timesteps | 3184640 | +| train/ | | +| approx_kl | 0.03480661 | +| clip_fraction | 0.37 | +| clip_range | 0.11 | +| entropy_loss | -7.37 | +| explained_variance | -0.0672 | +| learning_rate | 0.000137 | +| loss | -0.045 | +| n_updates | 6216 | +| policy_gradient_loss | -0.0306 | +| value_loss | 0.000137 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.27 | +| time/ | | +| fps | 1344 | +| iterations | 1556 | +| time_elapsed | 2370 | +| total_timesteps | 3186688 | +| train/ | | +| approx_kl | 0.03336833 | +| clip_fraction | 0.402 | +| clip_range | 0.11 | +| entropy_loss | -7.23 | +| explained_variance | -0.174 | +| learning_rate | 0.000137 | +| loss | -0.0497 | +| n_updates | 6220 | +| policy_gradient_loss | -0.0334 | +| value_loss | 0.000114 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 1344 | +| iterations | 1557 | +| time_elapsed | 2371 | +| total_timesteps | 3188736 | +| train/ | | +| approx_kl | 0.035244763 | +| clip_fraction | 0.391 | +| clip_range | 0.11 | +| entropy_loss | -7.21 | +| explained_variance | -0.0505 | +| learning_rate | 0.000137 | +| loss | -0.0444 | +| n_updates | 6224 | +| policy_gradient_loss | -0.0301 | +| value_loss | 0.000268 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 1344 | +| iterations | 1558 | +| time_elapsed | 2373 | +| total_timesteps | 3190784 | +| train/ | | +| approx_kl | 0.03384094 | +| clip_fraction | 0.408 | +| clip_range | 0.11 | +| entropy_loss | -7.29 | +| explained_variance | -0.147 | +| learning_rate | 0.000137 | +| loss | -0.0572 | +| n_updates | 6228 | +| policy_gradient_loss | -0.0322 | +| value_loss | 0.00016 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 1344 | +| iterations | 1559 | +| time_elapsed | 2374 | +| total_timesteps | 3192832 | +| train/ | | +| approx_kl | 0.039997928 | +| clip_fraction | 0.408 | +| clip_range | 0.11 | +| entropy_loss | -7.4 | +| explained_variance | -0.132 | +| learning_rate | 0.000137 | +| loss | -0.05 | +| n_updates | 6232 | +| policy_gradient_loss | -0.0347 | +| value_loss | 0.000117 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.281 | +| time/ | | +| fps | 1344 | +| iterations | 1560 | +| time_elapsed | 2375 | +| total_timesteps | 3194880 | +| train/ | | +| approx_kl | 0.040380523 | +| clip_fraction | 0.397 | +| clip_range | 0.11 | +| entropy_loss | -7.4 | +| explained_variance | -0.0353 | +| learning_rate | 0.000137 | +| loss | -0.0494 | +| n_updates | 6236 | +| policy_gradient_loss | -0.0335 | +| value_loss | 0.000231 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 1344 | +| iterations | 1561 | +| time_elapsed | 2377 | +| total_timesteps | 3196928 | +| train/ | | +| approx_kl | 0.0390497 | +| clip_fraction | 0.389 | +| clip_range | 0.11 | +| entropy_loss | -7.31 | +| explained_variance | -0.111 | +| learning_rate | 0.000137 | +| loss | -0.0492 | +| n_updates | 6240 | +| policy_gradient_loss | -0.0326 | +| value_loss | 0.000179 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.276 | +| time/ | | +| fps | 1344 | +| iterations | 1562 | +| time_elapsed | 2378 | +| total_timesteps | 3198976 | +| train/ | | +| approx_kl | 0.035643447 | +| clip_fraction | 0.408 | +| clip_range | 0.11 | +| entropy_loss | -7.3 | +| explained_variance | -0.227 | +| learning_rate | 0.000137 | +| loss | -0.0465 | +| n_updates | 6244 | +| policy_gradient_loss | -0.0317 | +| value_loss | 0.000117 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.276 | +| time/ | | +| fps | 1344 | +| iterations | 1563 | +| time_elapsed | 2380 | +| total_timesteps | 3201024 | +| train/ | | +| approx_kl | 0.039740525 | +| clip_fraction | 0.409 | +| clip_range | 0.11 | +| entropy_loss | -7.38 | +| explained_variance | -0.115 | +| learning_rate | 0.000137 | +| loss | -0.0541 | +| n_updates | 6248 | +| policy_gradient_loss | -0.0348 | +| value_loss | 0.000129 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.272 | +| time/ | | +| fps | 1344 | +| iterations | 1564 | +| time_elapsed | 2381 | +| total_timesteps | 3203072 | +| train/ | | +| approx_kl | 0.041091137 | +| clip_fraction | 0.414 | +| clip_range | 0.11 | +| entropy_loss | -7.45 | +| explained_variance | -0.229 | +| learning_rate | 0.000137 | +| loss | -0.0557 | +| n_updates | 6252 | +| policy_gradient_loss | -0.0337 | +| value_loss | 0.000122 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.27 | +| time/ | | +| fps | 1344 | +| iterations | 1565 | +| time_elapsed | 2383 | +| total_timesteps | 3205120 | +| train/ | | +| approx_kl | 0.039993305 | +| clip_fraction | 0.38 | +| clip_range | 0.11 | +| entropy_loss | -7.21 | +| explained_variance | -0.0976 | +| learning_rate | 0.000137 | +| loss | -0.053 | +| n_updates | 6256 | +| policy_gradient_loss | -0.0319 | +| value_loss | 0.00011 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.27 | +| time/ | | +| fps | 1345 | +| iterations | 1566 | +| time_elapsed | 2384 | +| total_timesteps | 3207168 | +| train/ | | +| approx_kl | 0.03502947 | +| clip_fraction | 0.373 | +| clip_range | 0.11 | +| entropy_loss | -7.23 | +| explained_variance | -0.0151 | +| learning_rate | 0.000137 | +| loss | -0.0479 | +| n_updates | 6260 | +| policy_gradient_loss | -0.0302 | +| value_loss | 0.000162 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.272 | +| time/ | | +| fps | 1345 | +| iterations | 1567 | +| time_elapsed | 2385 | +| total_timesteps | 3209216 | +| train/ | | +| approx_kl | 0.03580696 | +| clip_fraction | 0.383 | +| clip_range | 0.11 | +| entropy_loss | -7.2 | +| explained_variance | 0.0158 | +| learning_rate | 0.000136 | +| loss | -0.0478 | +| n_updates | 6264 | +| policy_gradient_loss | -0.029 | +| value_loss | 0.000241 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.276 | +| time/ | | +| fps | 1345 | +| iterations | 1568 | +| time_elapsed | 2387 | +| total_timesteps | 3211264 | +| train/ | | +| approx_kl | 0.04213643 | +| clip_fraction | 0.399 | +| clip_range | 0.11 | +| entropy_loss | -7.42 | +| explained_variance | -0.336 | +| learning_rate | 0.000136 | +| loss | -0.0524 | +| n_updates | 6268 | +| policy_gradient_loss | -0.0343 | +| value_loss | 0.000112 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 1345 | +| iterations | 1569 | +| time_elapsed | 2388 | +| total_timesteps | 3213312 | +| train/ | | +| approx_kl | 0.032754596 | +| clip_fraction | 0.377 | +| clip_range | 0.11 | +| entropy_loss | -7.38 | +| explained_variance | -0.129 | +| learning_rate | 0.000136 | +| loss | -0.048 | +| n_updates | 6272 | +| policy_gradient_loss | -0.029 | +| value_loss | 0.000222 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 1345 | +| iterations | 1570 | +| time_elapsed | 2390 | +| total_timesteps | 3215360 | +| train/ | | +| approx_kl | 0.0345242 | +| clip_fraction | 0.401 | +| clip_range | 0.11 | +| entropy_loss | -7.5 | +| explained_variance | -0.0457 | +| learning_rate | 0.000136 | +| loss | -0.0625 | +| n_updates | 6276 | +| policy_gradient_loss | -0.0343 | +| value_loss | 0.000127 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 1345 | +| iterations | 1571 | +| time_elapsed | 2391 | +| total_timesteps | 3217408 | +| train/ | | +| approx_kl | 0.041355096 | +| clip_fraction | 0.383 | +| clip_range | 0.11 | +| entropy_loss | -7.4 | +| explained_variance | -0.0845 | +| learning_rate | 0.000136 | +| loss | -0.0548 | +| n_updates | 6280 | +| policy_gradient_loss | -0.0341 | +| value_loss | 0.000235 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 1345 | +| iterations | 1572 | +| time_elapsed | 2392 | +| total_timesteps | 3219456 | +| train/ | | +| approx_kl | 0.041587446 | +| clip_fraction | 0.413 | +| clip_range | 0.11 | +| entropy_loss | -7.38 | +| explained_variance | -0.181 | +| learning_rate | 0.000136 | +| loss | -0.0496 | +| n_updates | 6284 | +| policy_gradient_loss | -0.0321 | +| value_loss | 0.000202 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.273 | +| time/ | | +| fps | 1345 | +| iterations | 1573 | +| time_elapsed | 2394 | +| total_timesteps | 3221504 | +| train/ | | +| approx_kl | 0.04457121 | +| clip_fraction | 0.431 | +| clip_range | 0.11 | +| entropy_loss | -7.32 | +| explained_variance | -0.136 | +| learning_rate | 0.000136 | +| loss | -0.0526 | +| n_updates | 6288 | +| policy_gradient_loss | -0.0341 | +| value_loss | 0.000135 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 1345 | +| iterations | 1574 | +| time_elapsed | 2395 | +| total_timesteps | 3223552 | +| train/ | | +| approx_kl | 0.05284309 | +| clip_fraction | 0.41 | +| clip_range | 0.11 | +| entropy_loss | -7.33 | +| explained_variance | -0.402 | +| learning_rate | 0.000136 | +| loss | -0.0619 | +| n_updates | 6292 | +| policy_gradient_loss | -0.0336 | +| value_loss | 9.2e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.268 | +| time/ | | +| fps | 1345 | +| iterations | 1575 | +| time_elapsed | 2397 | +| total_timesteps | 3225600 | +| train/ | | +| approx_kl | 0.033538558 | +| clip_fraction | 0.401 | +| clip_range | 0.11 | +| entropy_loss | -7.23 | +| explained_variance | -0.064 | +| learning_rate | 0.000136 | +| loss | -0.0431 | +| n_updates | 6296 | +| policy_gradient_loss | -0.0272 | +| value_loss | 0.000213 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.268 | +| time/ | | +| fps | 1345 | +| iterations | 1576 | +| time_elapsed | 2398 | +| total_timesteps | 3227648 | +| train/ | | +| approx_kl | 0.04006545 | +| clip_fraction | 0.379 | +| clip_range | 0.11 | +| entropy_loss | -7.28 | +| explained_variance | -0.208 | +| learning_rate | 0.000136 | +| loss | -0.0538 | +| n_updates | 6300 | +| policy_gradient_loss | -0.0323 | +| value_loss | 0.000183 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.265 | +| time/ | | +| fps | 1345 | +| iterations | 1577 | +| time_elapsed | 2400 | +| total_timesteps | 3229696 | +| train/ | | +| approx_kl | 0.041370995 | +| clip_fraction | 0.413 | +| clip_range | 0.11 | +| entropy_loss | -7.33 | +| explained_variance | -0.232 | +| learning_rate | 0.000136 | +| loss | -0.0557 | +| n_updates | 6304 | +| policy_gradient_loss | -0.0357 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.274 | +| time/ | | +| fps | 1345 | +| iterations | 1578 | +| time_elapsed | 2401 | +| total_timesteps | 3231744 | +| train/ | | +| approx_kl | 0.038245734 | +| clip_fraction | 0.4 | +| clip_range | 0.11 | +| entropy_loss | -7.32 | +| explained_variance | -0.0691 | +| learning_rate | 0.000136 | +| loss | -0.054 | +| n_updates | 6308 | +| policy_gradient_loss | -0.0337 | +| value_loss | 9.47e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.277 | +| time/ | | +| fps | 1345 | +| iterations | 1579 | +| time_elapsed | 2402 | +| total_timesteps | 3233792 | +| train/ | | +| approx_kl | 0.038013503 | +| clip_fraction | 0.377 | +| clip_range | 0.11 | +| entropy_loss | -7.37 | +| explained_variance | -0.0148 | +| learning_rate | 0.000136 | +| loss | -0.0497 | +| n_updates | 6312 | +| policy_gradient_loss | -0.0304 | +| value_loss | 0.000255 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.28 | +| time/ | | +| fps | 1345 | +| iterations | 1580 | +| time_elapsed | 2404 | +| total_timesteps | 3235840 | +| train/ | | +| approx_kl | 0.033405416 | +| clip_fraction | 0.393 | +| clip_range | 0.11 | +| entropy_loss | -7.28 | +| explained_variance | -0.143 | +| learning_rate | 0.000136 | +| loss | -0.0469 | +| n_updates | 6316 | +| policy_gradient_loss | -0.0309 | +| value_loss | 0.000276 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.278 | +| time/ | | +| fps | 1345 | +| iterations | 1581 | +| time_elapsed | 2405 | +| total_timesteps | 3237888 | +| train/ | | +| approx_kl | 0.036888383 | +| clip_fraction | 0.37 | +| clip_range | 0.11 | +| entropy_loss | -7.34 | +| explained_variance | -0.0587 | +| learning_rate | 0.000136 | +| loss | -0.0431 | +| n_updates | 6320 | +| policy_gradient_loss | -0.029 | +| value_loss | 0.000319 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.277 | +| time/ | | +| fps | 1345 | +| iterations | 1582 | +| time_elapsed | 2407 | +| total_timesteps | 3239936 | +| train/ | | +| approx_kl | 0.035533316 | +| clip_fraction | 0.442 | +| clip_range | 0.11 | +| entropy_loss | -7.38 | +| explained_variance | -0.491 | +| learning_rate | 0.000136 | +| loss | -0.0633 | +| n_updates | 6324 | +| policy_gradient_loss | -0.0381 | +| value_loss | 0.000148 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.277 | +| time/ | | +| fps | 1345 | +| iterations | 1583 | +| time_elapsed | 2408 | +| total_timesteps | 3241984 | +| train/ | | +| approx_kl | 0.0356471 | +| clip_fraction | 0.393 | +| clip_range | 0.11 | +| entropy_loss | -7.37 | +| explained_variance | -0.122 | +| learning_rate | 0.000136 | +| loss | -0.0506 | +| n_updates | 6328 | +| policy_gradient_loss | -0.0323 | +| value_loss | 0.00016 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.277 | +| time/ | | +| fps | 1346 | +| iterations | 1584 | +| time_elapsed | 2410 | +| total_timesteps | 3244032 | +| train/ | | +| approx_kl | 0.039812192 | +| clip_fraction | 0.422 | +| clip_range | 0.109 | +| entropy_loss | -7.29 | +| explained_variance | -0.287 | +| learning_rate | 0.000136 | +| loss | -0.0594 | +| n_updates | 6332 | +| policy_gradient_loss | -0.0373 | +| value_loss | 0.00012 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 1346 | +| iterations | 1585 | +| time_elapsed | 2411 | +| total_timesteps | 3246080 | +| train/ | | +| approx_kl | 0.033541597 | +| clip_fraction | 0.361 | +| clip_range | 0.109 | +| entropy_loss | -7.42 | +| explained_variance | -0.16 | +| learning_rate | 0.000136 | +| loss | -0.0439 | +| n_updates | 6336 | +| policy_gradient_loss | -0.0301 | +| value_loss | 0.000199 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 1346 | +| iterations | 1586 | +| time_elapsed | 2412 | +| total_timesteps | 3248128 | +| train/ | | +| approx_kl | 0.034161642 | +| clip_fraction | 0.388 | +| clip_range | 0.109 | +| entropy_loss | -7.26 | +| explained_variance | -0.0529 | +| learning_rate | 0.000136 | +| loss | -0.0453 | +| n_updates | 6340 | +| policy_gradient_loss | -0.0325 | +| value_loss | 0.000203 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.283 | +| time/ | | +| fps | 1346 | +| iterations | 1587 | +| time_elapsed | 2414 | +| total_timesteps | 3250176 | +| train/ | | +| approx_kl | 0.035825416 | +| clip_fraction | 0.384 | +| clip_range | 0.109 | +| entropy_loss | -7.35 | +| explained_variance | -0.0468 | +| learning_rate | 0.000136 | +| loss | -0.0536 | +| n_updates | 6344 | +| policy_gradient_loss | -0.0323 | +| value_loss | 0.000162 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.283 | +| time/ | | +| fps | 1346 | +| iterations | 1588 | +| time_elapsed | 2415 | +| total_timesteps | 3252224 | +| train/ | | +| approx_kl | 0.03445057 | +| clip_fraction | 0.394 | +| clip_range | 0.109 | +| entropy_loss | -7.26 | +| explained_variance | -0.0701 | +| learning_rate | 0.000136 | +| loss | -0.0556 | +| n_updates | 6348 | +| policy_gradient_loss | -0.0299 | +| value_loss | 0.000248 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 1346 | +| iterations | 1589 | +| time_elapsed | 2417 | +| total_timesteps | 3254272 | +| train/ | | +| approx_kl | 0.035645977 | +| clip_fraction | 0.389 | +| clip_range | 0.109 | +| entropy_loss | -7.41 | +| explained_variance | -0.0369 | +| learning_rate | 0.000136 | +| loss | -0.054 | +| n_updates | 6352 | +| policy_gradient_loss | -0.0323 | +| value_loss | 0.000217 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.286 | +| time/ | | +| fps | 1346 | +| iterations | 1590 | +| time_elapsed | 2418 | +| total_timesteps | 3256320 | +| train/ | | +| approx_kl | 0.03949655 | +| clip_fraction | 0.412 | +| clip_range | 0.109 | +| entropy_loss | -7.41 | +| explained_variance | -0.119 | +| learning_rate | 0.000136 | +| loss | -0.0591 | +| n_updates | 6356 | +| policy_gradient_loss | -0.0334 | +| value_loss | 0.000204 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.292 | +| time/ | | +| fps | 1346 | +| iterations | 1591 | +| time_elapsed | 2419 | +| total_timesteps | 3258368 | +| train/ | | +| approx_kl | 0.035450786 | +| clip_fraction | 0.386 | +| clip_range | 0.109 | +| entropy_loss | -7.3 | +| explained_variance | -0.111 | +| learning_rate | 0.000136 | +| loss | -0.0439 | +| n_updates | 6360 | +| policy_gradient_loss | -0.0299 | +| value_loss | 0.000154 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.286 | +| time/ | | +| fps | 1346 | +| iterations | 1592 | +| time_elapsed | 2421 | +| total_timesteps | 3260416 | +| train/ | | +| approx_kl | 0.03511096 | +| clip_fraction | 0.412 | +| clip_range | 0.109 | +| entropy_loss | -7.21 | +| explained_variance | -0.219 | +| learning_rate | 0.000135 | +| loss | -0.0556 | +| n_updates | 6364 | +| policy_gradient_loss | -0.0341 | +| value_loss | 0.000103 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.286 | +| time/ | | +| fps | 1346 | +| iterations | 1593 | +| time_elapsed | 2422 | +| total_timesteps | 3262464 | +| train/ | | +| approx_kl | 0.03440003 | +| clip_fraction | 0.404 | +| clip_range | 0.109 | +| entropy_loss | -7.28 | +| explained_variance | -0.115 | +| learning_rate | 0.000135 | +| loss | -0.0496 | +| n_updates | 6368 | +| policy_gradient_loss | -0.0327 | +| value_loss | 0.000232 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.29 | +| time/ | | +| fps | 1346 | +| iterations | 1594 | +| time_elapsed | 2424 | +| total_timesteps | 3264512 | +| train/ | | +| approx_kl | 0.030699493 | +| clip_fraction | 0.395 | +| clip_range | 0.109 | +| entropy_loss | -7.28 | +| explained_variance | -0.158 | +| learning_rate | 0.000135 | +| loss | -0.0442 | +| n_updates | 6372 | +| policy_gradient_loss | -0.0301 | +| value_loss | 0.000114 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.287 | +| time/ | | +| fps | 1346 | +| iterations | 1595 | +| time_elapsed | 2425 | +| total_timesteps | 3266560 | +| train/ | | +| approx_kl | 0.032525003 | +| clip_fraction | 0.387 | +| clip_range | 0.109 | +| entropy_loss | -7.3 | +| explained_variance | -0.0784 | +| learning_rate | 0.000135 | +| loss | -0.0507 | +| n_updates | 6376 | +| policy_gradient_loss | -0.0293 | +| value_loss | 0.000269 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.286 | +| time/ | | +| fps | 1346 | +| iterations | 1596 | +| time_elapsed | 2427 | +| total_timesteps | 3268608 | +| train/ | | +| approx_kl | 0.034626618 | +| clip_fraction | 0.368 | +| clip_range | 0.109 | +| entropy_loss | -7.25 | +| explained_variance | -0.141 | +| learning_rate | 0.000135 | +| loss | -0.0518 | +| n_updates | 6380 | +| policy_gradient_loss | -0.0309 | +| value_loss | 0.000267 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.286 | +| time/ | | +| fps | 1346 | +| iterations | 1597 | +| time_elapsed | 2428 | +| total_timesteps | 3270656 | +| train/ | | +| approx_kl | 0.03736929 | +| clip_fraction | 0.389 | +| clip_range | 0.109 | +| entropy_loss | -7.32 | +| explained_variance | -0.279 | +| learning_rate | 0.000135 | +| loss | -0.0607 | +| n_updates | 6384 | +| policy_gradient_loss | -0.0348 | +| value_loss | 0.000144 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 1346 | +| iterations | 1598 | +| time_elapsed | 2429 | +| total_timesteps | 3272704 | +| train/ | | +| approx_kl | 0.03958313 | +| clip_fraction | 0.411 | +| clip_range | 0.109 | +| entropy_loss | -7.35 | +| explained_variance | -0.122 | +| learning_rate | 0.000135 | +| loss | -0.0577 | +| n_updates | 6388 | +| policy_gradient_loss | -0.0332 | +| value_loss | 0.000169 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.277 | +| time/ | | +| fps | 1346 | +| iterations | 1599 | +| time_elapsed | 2431 | +| total_timesteps | 3274752 | +| train/ | | +| approx_kl | 0.03436024 | +| clip_fraction | 0.407 | +| clip_range | 0.109 | +| entropy_loss | -7.37 | +| explained_variance | -0.101 | +| learning_rate | 0.000135 | +| loss | -0.0563 | +| n_updates | 6392 | +| policy_gradient_loss | -0.0294 | +| value_loss | 0.000196 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 1346 | +| iterations | 1600 | +| time_elapsed | 2432 | +| total_timesteps | 3276800 | +| train/ | | +| approx_kl | 0.034670494 | +| clip_fraction | 0.398 | +| clip_range | 0.109 | +| entropy_loss | -7.22 | +| explained_variance | -0.164 | +| learning_rate | 0.000135 | +| loss | -0.0589 | +| n_updates | 6396 | +| policy_gradient_loss | -0.0333 | +| value_loss | 0.000152 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.284 | +| time/ | | +| fps | 1347 | +| iterations | 1601 | +| time_elapsed | 2434 | +| total_timesteps | 3278848 | +| train/ | | +| approx_kl | 0.035807665 | +| clip_fraction | 0.408 | +| clip_range | 0.109 | +| entropy_loss | -7.31 | +| explained_variance | -0.13 | +| learning_rate | 0.000135 | +| loss | -0.0471 | +| n_updates | 6400 | +| policy_gradient_loss | -0.0333 | +| value_loss | 0.000155 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.28 | +| time/ | | +| fps | 1347 | +| iterations | 1602 | +| time_elapsed | 2435 | +| total_timesteps | 3280896 | +| train/ | | +| approx_kl | 0.03424526 | +| clip_fraction | 0.4 | +| clip_range | 0.109 | +| entropy_loss | -7.16 | +| explained_variance | -0.248 | +| learning_rate | 0.000135 | +| loss | -0.0588 | +| n_updates | 6404 | +| policy_gradient_loss | -0.0334 | +| value_loss | 0.00013 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.281 | +| time/ | | +| fps | 1347 | +| iterations | 1603 | +| time_elapsed | 2437 | +| total_timesteps | 3282944 | +| train/ | | +| approx_kl | 0.039925896 | +| clip_fraction | 0.412 | +| clip_range | 0.109 | +| entropy_loss | -7.34 | +| explained_variance | -0.0648 | +| learning_rate | 0.000135 | +| loss | -0.0601 | +| n_updates | 6408 | +| policy_gradient_loss | -0.0354 | +| value_loss | 0.000139 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.281 | +| time/ | | +| fps | 1347 | +| iterations | 1604 | +| time_elapsed | 2438 | +| total_timesteps | 3284992 | +| train/ | | +| approx_kl | 0.031982865 | +| clip_fraction | 0.404 | +| clip_range | 0.109 | +| entropy_loss | -7.3 | +| explained_variance | -0.248 | +| learning_rate | 0.000135 | +| loss | -0.0603 | +| n_updates | 6412 | +| policy_gradient_loss | -0.0347 | +| value_loss | 7.45e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.278 | +| time/ | | +| fps | 1347 | +| iterations | 1605 | +| time_elapsed | 2440 | +| total_timesteps | 3287040 | +| train/ | | +| approx_kl | 0.040638067 | +| clip_fraction | 0.389 | +| clip_range | 0.109 | +| entropy_loss | -7.18 | +| explained_variance | -0.11 | +| learning_rate | 0.000135 | +| loss | -0.0511 | +| n_updates | 6416 | +| policy_gradient_loss | -0.0323 | +| value_loss | 0.000211 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.286 | +| time/ | | +| fps | 1347 | +| iterations | 1606 | +| time_elapsed | 2441 | +| total_timesteps | 3289088 | +| train/ | | +| approx_kl | 0.0353235 | +| clip_fraction | 0.428 | +| clip_range | 0.109 | +| entropy_loss | -7.11 | +| explained_variance | -0.322 | +| learning_rate | 0.000135 | +| loss | -0.0665 | +| n_updates | 6420 | +| policy_gradient_loss | -0.0381 | +| value_loss | 8.96e-05 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.283 | +| time/ | | +| fps | 1347 | +| iterations | 1607 | +| time_elapsed | 2443 | +| total_timesteps | 3291136 | +| train/ | | +| approx_kl | 0.041422628 | +| clip_fraction | 0.421 | +| clip_range | 0.109 | +| entropy_loss | -7.24 | +| explained_variance | -0.151 | +| learning_rate | 0.000135 | +| loss | -0.0517 | +| n_updates | 6424 | +| policy_gradient_loss | -0.0309 | +| value_loss | 0.0002 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.283 | +| time/ | | +| fps | 1347 | +| iterations | 1608 | +| time_elapsed | 2444 | +| total_timesteps | 3293184 | +| train/ | | +| approx_kl | 0.038692653 | +| clip_fraction | 0.429 | +| clip_range | 0.109 | +| entropy_loss | -7.23 | +| explained_variance | -0.561 | +| learning_rate | 0.000135 | +| loss | -0.0504 | +| n_updates | 6428 | +| policy_gradient_loss | -0.0383 | +| value_loss | 7.88e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.283 | +| time/ | | +| fps | 1347 | +| iterations | 1609 | +| time_elapsed | 2445 | +| total_timesteps | 3295232 | +| train/ | | +| approx_kl | 0.032776464 | +| clip_fraction | 0.373 | +| clip_range | 0.109 | +| entropy_loss | -7.29 | +| explained_variance | -0.0433 | +| learning_rate | 0.000135 | +| loss | -0.0496 | +| n_updates | 6432 | +| policy_gradient_loss | -0.0286 | +| value_loss | 0.000224 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.283 | +| time/ | | +| fps | 1347 | +| iterations | 1610 | +| time_elapsed | 2447 | +| total_timesteps | 3297280 | +| train/ | | +| approx_kl | 0.036091324 | +| clip_fraction | 0.389 | +| clip_range | 0.109 | +| entropy_loss | -7.33 | +| explained_variance | -0.155 | +| learning_rate | 0.000135 | +| loss | -0.046 | +| n_updates | 6436 | +| policy_gradient_loss | -0.0317 | +| value_loss | 0.000168 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.287 | +| time/ | | +| fps | 1347 | +| iterations | 1611 | +| time_elapsed | 2448 | +| total_timesteps | 3299328 | +| train/ | | +| approx_kl | 0.038531974 | +| clip_fraction | 0.401 | +| clip_range | 0.109 | +| entropy_loss | -7.21 | +| explained_variance | -0.295 | +| learning_rate | 0.000135 | +| loss | -0.0509 | +| n_updates | 6440 | +| policy_gradient_loss | -0.0346 | +| value_loss | 0.000152 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.277 | +| time/ | | +| fps | 1347 | +| iterations | 1612 | +| time_elapsed | 2450 | +| total_timesteps | 3301376 | +| train/ | | +| approx_kl | 0.039961442 | +| clip_fraction | 0.418 | +| clip_range | 0.109 | +| entropy_loss | -7.25 | +| explained_variance | -0.253 | +| learning_rate | 0.000135 | +| loss | -0.0558 | +| n_updates | 6444 | +| policy_gradient_loss | -0.0326 | +| value_loss | 9.63e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.274 | +| time/ | | +| fps | 1347 | +| iterations | 1613 | +| time_elapsed | 2451 | +| total_timesteps | 3303424 | +| train/ | | +| approx_kl | 0.03389137 | +| clip_fraction | 0.384 | +| clip_range | 0.109 | +| entropy_loss | -7.35 | +| explained_variance | -0.117 | +| learning_rate | 0.000135 | +| loss | -0.0418 | +| n_updates | 6448 | +| policy_gradient_loss | -0.0283 | +| value_loss | 0.000163 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.274 | +| time/ | | +| fps | 1347 | +| iterations | 1614 | +| time_elapsed | 2453 | +| total_timesteps | 3305472 | +| train/ | | +| approx_kl | 0.041202582 | +| clip_fraction | 0.413 | +| clip_range | 0.109 | +| entropy_loss | -7.29 | +| explained_variance | -0.248 | +| learning_rate | 0.000135 | +| loss | -0.0559 | +| n_updates | 6452 | +| policy_gradient_loss | -0.0371 | +| value_loss | 9.72e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.274 | +| time/ | | +| fps | 1347 | +| iterations | 1615 | +| time_elapsed | 2454 | +| total_timesteps | 3307520 | +| train/ | | +| approx_kl | 0.03827556 | +| clip_fraction | 0.379 | +| clip_range | 0.109 | +| entropy_loss | -7.28 | +| explained_variance | -0.239 | +| learning_rate | 0.000135 | +| loss | -0.0506 | +| n_updates | 6456 | +| policy_gradient_loss | -0.0326 | +| value_loss | 7.2e-05 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 1347 | +| iterations | 1616 | +| time_elapsed | 2455 | +| total_timesteps | 3309568 | +| train/ | | +| approx_kl | 0.04090666 | +| clip_fraction | 0.416 | +| clip_range | 0.109 | +| entropy_loss | -7.29 | +| explained_variance | 0.0128 | +| learning_rate | 0.000135 | +| loss | -0.0441 | +| n_updates | 6460 | +| policy_gradient_loss | -0.0292 | +| value_loss | 0.000143 | +---------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.283 | +| time/ | | +| fps | 1347 | +| iterations | 1617 | +| time_elapsed | 2457 | +| total_timesteps | 3311616 | +| train/ | | +| approx_kl | 0.0368901 | +| clip_fraction | 0.408 | +| clip_range | 0.109 | +| entropy_loss | -7.3 | +| explained_variance | -0.0495 | +| learning_rate | 0.000134 | +| loss | -0.0526 | +| n_updates | 6464 | +| policy_gradient_loss | -0.0314 | +| value_loss | 0.000352 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 1347 | +| iterations | 1618 | +| time_elapsed | 2458 | +| total_timesteps | 3313664 | +| train/ | | +| approx_kl | 0.030338012 | +| clip_fraction | 0.367 | +| clip_range | 0.109 | +| entropy_loss | -7.4 | +| explained_variance | -0.0711 | +| learning_rate | 0.000134 | +| loss | -0.0531 | +| n_updates | 6468 | +| policy_gradient_loss | -0.0323 | +| value_loss | 0.000234 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 1347 | +| iterations | 1619 | +| time_elapsed | 2460 | +| total_timesteps | 3315712 | +| train/ | | +| approx_kl | 0.042678565 | +| clip_fraction | 0.407 | +| clip_range | 0.109 | +| entropy_loss | -7.25 | +| explained_variance | -0.364 | +| learning_rate | 0.000134 | +| loss | -0.0526 | +| n_updates | 6472 | +| policy_gradient_loss | -0.0353 | +| value_loss | 0.000158 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.283 | +| time/ | | +| fps | 1347 | +| iterations | 1620 | +| time_elapsed | 2461 | +| total_timesteps | 3317760 | +| train/ | | +| approx_kl | 0.041105904 | +| clip_fraction | 0.434 | +| clip_range | 0.109 | +| entropy_loss | -7.25 | +| explained_variance | -0.146 | +| learning_rate | 0.000134 | +| loss | -0.051 | +| n_updates | 6476 | +| policy_gradient_loss | -0.0341 | +| value_loss | 0.000146 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.283 | +| time/ | | +| fps | 1347 | +| iterations | 1621 | +| time_elapsed | 2463 | +| total_timesteps | 3319808 | +| train/ | | +| approx_kl | 0.03734873 | +| clip_fraction | 0.383 | +| clip_range | 0.109 | +| entropy_loss | -7.31 | +| explained_variance | -0.0503 | +| learning_rate | 0.000134 | +| loss | -0.0435 | +| n_updates | 6480 | +| policy_gradient_loss | -0.0293 | +| value_loss | 0.000273 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.284 | +| time/ | | +| fps | 1347 | +| iterations | 1622 | +| time_elapsed | 2464 | +| total_timesteps | 3321856 | +| train/ | | +| approx_kl | 0.040519975 | +| clip_fraction | 0.392 | +| clip_range | 0.109 | +| entropy_loss | -7.51 | +| explained_variance | -0.0134 | +| learning_rate | 0.000134 | +| loss | -0.0582 | +| n_updates | 6484 | +| policy_gradient_loss | -0.0342 | +| value_loss | 0.000227 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.283 | +| time/ | | +| fps | 1347 | +| iterations | 1623 | +| time_elapsed | 2465 | +| total_timesteps | 3323904 | +| train/ | | +| approx_kl | 0.03903713 | +| clip_fraction | 0.405 | +| clip_range | 0.108 | +| entropy_loss | -7.34 | +| explained_variance | -0.377 | +| learning_rate | 0.000134 | +| loss | -0.0674 | +| n_updates | 6488 | +| policy_gradient_loss | -0.0401 | +| value_loss | 8.77e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.284 | +| time/ | | +| fps | 1347 | +| iterations | 1624 | +| time_elapsed | 2467 | +| total_timesteps | 3325952 | +| train/ | | +| approx_kl | 0.034543704 | +| clip_fraction | 0.388 | +| clip_range | 0.108 | +| entropy_loss | -7.38 | +| explained_variance | -0.219 | +| learning_rate | 0.000134 | +| loss | -0.058 | +| n_updates | 6492 | +| policy_gradient_loss | -0.032 | +| value_loss | 0.000126 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.288 | +| time/ | | +| fps | 1347 | +| iterations | 1625 | +| time_elapsed | 2468 | +| total_timesteps | 3328000 | +| train/ | | +| approx_kl | 0.040686496 | +| clip_fraction | 0.39 | +| clip_range | 0.108 | +| entropy_loss | -7.32 | +| explained_variance | -0.103 | +| learning_rate | 0.000134 | +| loss | -0.0494 | +| n_updates | 6496 | +| policy_gradient_loss | -0.0306 | +| value_loss | 0.000131 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.29 | +| time/ | | +| fps | 1348 | +| iterations | 1626 | +| time_elapsed | 2470 | +| total_timesteps | 3330048 | +| train/ | | +| approx_kl | 0.0337401 | +| clip_fraction | 0.397 | +| clip_range | 0.108 | +| entropy_loss | -7.25 | +| explained_variance | -0.0398 | +| learning_rate | 0.000134 | +| loss | -0.0488 | +| n_updates | 6500 | +| policy_gradient_loss | -0.0313 | +| value_loss | 0.000382 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.29 | +| time/ | | +| fps | 1348 | +| iterations | 1627 | +| time_elapsed | 2471 | +| total_timesteps | 3332096 | +| train/ | | +| approx_kl | 0.039022334 | +| clip_fraction | 0.401 | +| clip_range | 0.108 | +| entropy_loss | -7.28 | +| explained_variance | -0.267 | +| learning_rate | 0.000134 | +| loss | -0.0646 | +| n_updates | 6504 | +| policy_gradient_loss | -0.0342 | +| value_loss | 0.000237 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.287 | +| time/ | | +| fps | 1348 | +| iterations | 1628 | +| time_elapsed | 2473 | +| total_timesteps | 3334144 | +| train/ | | +| approx_kl | 0.03498172 | +| clip_fraction | 0.385 | +| clip_range | 0.108 | +| entropy_loss | -7.43 | +| explained_variance | -0.129 | +| learning_rate | 0.000134 | +| loss | -0.0635 | +| n_updates | 6508 | +| policy_gradient_loss | -0.0346 | +| value_loss | 0.000225 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.294 | +| time/ | | +| fps | 1348 | +| iterations | 1629 | +| time_elapsed | 2474 | +| total_timesteps | 3336192 | +| train/ | | +| approx_kl | 0.034729328 | +| clip_fraction | 0.387 | +| clip_range | 0.108 | +| entropy_loss | -7.42 | +| explained_variance | -0.13 | +| learning_rate | 0.000134 | +| loss | -0.0505 | +| n_updates | 6512 | +| policy_gradient_loss | -0.0323 | +| value_loss | 0.000229 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 1348 | +| iterations | 1630 | +| time_elapsed | 2475 | +| total_timesteps | 3338240 | +| train/ | | +| approx_kl | 0.030690387 | +| clip_fraction | 0.396 | +| clip_range | 0.108 | +| entropy_loss | -7.29 | +| explained_variance | -0.384 | +| learning_rate | 0.000134 | +| loss | -0.0545 | +| n_updates | 6516 | +| policy_gradient_loss | -0.0343 | +| value_loss | 0.000188 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 1348 | +| iterations | 1631 | +| time_elapsed | 2477 | +| total_timesteps | 3340288 | +| train/ | | +| approx_kl | 0.029305484 | +| clip_fraction | 0.402 | +| clip_range | 0.108 | +| entropy_loss | -7.27 | +| explained_variance | -0.102 | +| learning_rate | 0.000134 | +| loss | -0.0555 | +| n_updates | 6520 | +| policy_gradient_loss | -0.0317 | +| value_loss | 0.000179 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.3 | +| time/ | | +| fps | 1348 | +| iterations | 1632 | +| time_elapsed | 2478 | +| total_timesteps | 3342336 | +| train/ | | +| approx_kl | 0.035992756 | +| clip_fraction | 0.367 | +| clip_range | 0.108 | +| entropy_loss | -7.39 | +| explained_variance | -0.086 | +| learning_rate | 0.000134 | +| loss | -0.0557 | +| n_updates | 6524 | +| policy_gradient_loss | -0.0282 | +| value_loss | 0.000314 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 1348 | +| iterations | 1633 | +| time_elapsed | 2480 | +| total_timesteps | 3344384 | +| train/ | | +| approx_kl | 0.038543083 | +| clip_fraction | 0.402 | +| clip_range | 0.108 | +| entropy_loss | -7.5 | +| explained_variance | -0.697 | +| learning_rate | 0.000134 | +| loss | -0.0578 | +| n_updates | 6528 | +| policy_gradient_loss | -0.0386 | +| value_loss | 9.92e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 1348 | +| iterations | 1634 | +| time_elapsed | 2481 | +| total_timesteps | 3346432 | +| train/ | | +| approx_kl | 0.038814947 | +| clip_fraction | 0.396 | +| clip_range | 0.108 | +| entropy_loss | -7.34 | +| explained_variance | -0.128 | +| learning_rate | 0.000134 | +| loss | -0.0398 | +| n_updates | 6532 | +| policy_gradient_loss | -0.0331 | +| value_loss | 0.000186 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 1348 | +| iterations | 1635 | +| time_elapsed | 2483 | +| total_timesteps | 3348480 | +| train/ | | +| approx_kl | 0.034635946 | +| clip_fraction | 0.381 | +| clip_range | 0.108 | +| entropy_loss | -7.27 | +| explained_variance | -0.143 | +| learning_rate | 0.000134 | +| loss | -0.0533 | +| n_updates | 6536 | +| policy_gradient_loss | -0.0321 | +| value_loss | 0.000173 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 1348 | +| iterations | 1636 | +| time_elapsed | 2484 | +| total_timesteps | 3350528 | +| train/ | | +| approx_kl | 0.03542841 | +| clip_fraction | 0.399 | +| clip_range | 0.108 | +| entropy_loss | -7.29 | +| explained_variance | -0.154 | +| learning_rate | 0.000134 | +| loss | -0.0522 | +| n_updates | 6540 | +| policy_gradient_loss | -0.034 | +| value_loss | 0.000125 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 1348 | +| iterations | 1637 | +| time_elapsed | 2486 | +| total_timesteps | 3352576 | +| train/ | | +| approx_kl | 0.03518162 | +| clip_fraction | 0.369 | +| clip_range | 0.108 | +| entropy_loss | -7.44 | +| explained_variance | -0.034 | +| learning_rate | 0.000134 | +| loss | -0.054 | +| n_updates | 6544 | +| policy_gradient_loss | -0.0316 | +| value_loss | 0.000208 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 1348 | +| iterations | 1638 | +| time_elapsed | 2487 | +| total_timesteps | 3354624 | +| train/ | | +| approx_kl | 0.039462693 | +| clip_fraction | 0.381 | +| clip_range | 0.108 | +| entropy_loss | -7.3 | +| explained_variance | -0.0797 | +| learning_rate | 0.000134 | +| loss | -0.0561 | +| n_updates | 6548 | +| policy_gradient_loss | -0.0316 | +| value_loss | 0.000177 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.293 | +| time/ | | +| fps | 1348 | +| iterations | 1639 | +| time_elapsed | 2488 | +| total_timesteps | 3356672 | +| train/ | | +| approx_kl | 0.035291895 | +| clip_fraction | 0.409 | +| clip_range | 0.108 | +| entropy_loss | -7.33 | +| explained_variance | -0.15 | +| learning_rate | 0.000134 | +| loss | -0.0496 | +| n_updates | 6552 | +| policy_gradient_loss | -0.033 | +| value_loss | 0.000144 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.293 | +| time/ | | +| fps | 1348 | +| iterations | 1640 | +| time_elapsed | 2490 | +| total_timesteps | 3358720 | +| train/ | | +| approx_kl | 0.03748075 | +| clip_fraction | 0.424 | +| clip_range | 0.108 | +| entropy_loss | -7.31 | +| explained_variance | -0.231 | +| learning_rate | 0.000134 | +| loss | -0.0525 | +| n_updates | 6556 | +| policy_gradient_loss | -0.0328 | +| value_loss | 0.000104 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.292 | +| time/ | | +| fps | 1348 | +| iterations | 1641 | +| time_elapsed | 2491 | +| total_timesteps | 3360768 | +| train/ | | +| approx_kl | 0.03443729 | +| clip_fraction | 0.382 | +| clip_range | 0.108 | +| entropy_loss | -7.28 | +| explained_variance | -0.0691 | +| learning_rate | 0.000133 | +| loss | -0.052 | +| n_updates | 6560 | +| policy_gradient_loss | -0.0306 | +| value_loss | 0.000178 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 1348 | +| iterations | 1642 | +| time_elapsed | 2493 | +| total_timesteps | 3362816 | +| train/ | | +| approx_kl | 0.030978978 | +| clip_fraction | 0.399 | +| clip_range | 0.108 | +| entropy_loss | -7.33 | +| explained_variance | -0.0679 | +| learning_rate | 0.000133 | +| loss | -0.0564 | +| n_updates | 6564 | +| policy_gradient_loss | -0.0324 | +| value_loss | 0.000195 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 1348 | +| iterations | 1643 | +| time_elapsed | 2494 | +| total_timesteps | 3364864 | +| train/ | | +| approx_kl | 0.038032223 | +| clip_fraction | 0.413 | +| clip_range | 0.108 | +| entropy_loss | -7.28 | +| explained_variance | -0.217 | +| learning_rate | 0.000133 | +| loss | -0.0341 | +| n_updates | 6568 | +| policy_gradient_loss | -0.0314 | +| value_loss | 0.000112 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 1348 | +| iterations | 1644 | +| time_elapsed | 2496 | +| total_timesteps | 3366912 | +| train/ | | +| approx_kl | 0.037190527 | +| clip_fraction | 0.398 | +| clip_range | 0.108 | +| entropy_loss | -7.23 | +| explained_variance | -0.0454 | +| learning_rate | 0.000133 | +| loss | -0.0502 | +| n_updates | 6572 | +| policy_gradient_loss | -0.0308 | +| value_loss | 0.000214 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.294 | +| time/ | | +| fps | 1348 | +| iterations | 1645 | +| time_elapsed | 2497 | +| total_timesteps | 3368960 | +| train/ | | +| approx_kl | 0.034029312 | +| clip_fraction | 0.412 | +| clip_range | 0.108 | +| entropy_loss | -7.37 | +| explained_variance | -0.192 | +| learning_rate | 0.000133 | +| loss | -0.0635 | +| n_updates | 6576 | +| policy_gradient_loss | -0.0383 | +| value_loss | 0.000115 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.293 | +| time/ | | +| fps | 1348 | +| iterations | 1646 | +| time_elapsed | 2499 | +| total_timesteps | 3371008 | +| train/ | | +| approx_kl | 0.03767079 | +| clip_fraction | 0.397 | +| clip_range | 0.108 | +| entropy_loss | -7.43 | +| explained_variance | -0.094 | +| learning_rate | 0.000133 | +| loss | -0.055 | +| n_updates | 6580 | +| policy_gradient_loss | -0.0322 | +| value_loss | 0.000154 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.293 | +| time/ | | +| fps | 1349 | +| iterations | 1647 | +| time_elapsed | 2500 | +| total_timesteps | 3373056 | +| train/ | | +| approx_kl | 0.038339745 | +| clip_fraction | 0.396 | +| clip_range | 0.108 | +| entropy_loss | -7.07 | +| explained_variance | -0.108 | +| learning_rate | 0.000133 | +| loss | -0.047 | +| n_updates | 6584 | +| policy_gradient_loss | -0.0295 | +| value_loss | 0.000222 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 1349 | +| iterations | 1648 | +| time_elapsed | 2501 | +| total_timesteps | 3375104 | +| train/ | | +| approx_kl | 0.040059134 | +| clip_fraction | 0.401 | +| clip_range | 0.108 | +| entropy_loss | -7.28 | +| explained_variance | -0.141 | +| learning_rate | 0.000133 | +| loss | -0.0551 | +| n_updates | 6588 | +| policy_gradient_loss | -0.0312 | +| value_loss | 0.000182 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.3 | +| time/ | | +| fps | 1349 | +| iterations | 1649 | +| time_elapsed | 2503 | +| total_timesteps | 3377152 | +| train/ | | +| approx_kl | 0.0421971 | +| clip_fraction | 0.4 | +| clip_range | 0.108 | +| entropy_loss | -7.18 | +| explained_variance | -0.292 | +| learning_rate | 0.000133 | +| loss | -0.0534 | +| n_updates | 6592 | +| policy_gradient_loss | -0.0328 | +| value_loss | 0.000184 | +--------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.291 | +| time/ | | +| fps | 1349 | +| iterations | 1650 | +| time_elapsed | 2504 | +| total_timesteps | 3379200 | +| train/ | | +| approx_kl | 0.03200692 | +| clip_fraction | 0.391 | +| clip_range | 0.108 | +| entropy_loss | -7.25 | +| explained_variance | -0.0979 | +| learning_rate | 0.000133 | +| loss | -0.0398 | +| n_updates | 6596 | +| policy_gradient_loss | -0.0255 | +| value_loss | 0.000243 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.287 | +| time/ | | +| fps | 1349 | +| iterations | 1651 | +| time_elapsed | 2506 | +| total_timesteps | 3381248 | +| train/ | | +| approx_kl | 0.03954432 | +| clip_fraction | 0.377 | +| clip_range | 0.108 | +| entropy_loss | -7.34 | +| explained_variance | -0.129 | +| learning_rate | 0.000133 | +| loss | -0.0395 | +| n_updates | 6600 | +| policy_gradient_loss | -0.0285 | +| value_loss | 0.000216 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.287 | +| time/ | | +| fps | 1349 | +| iterations | 1652 | +| time_elapsed | 2507 | +| total_timesteps | 3383296 | +| train/ | | +| approx_kl | 0.039641716 | +| clip_fraction | 0.426 | +| clip_range | 0.108 | +| entropy_loss | -7.21 | +| explained_variance | -0.342 | +| learning_rate | 0.000133 | +| loss | -0.0556 | +| n_updates | 6604 | +| policy_gradient_loss | -0.0358 | +| value_loss | 0.000157 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.286 | +| time/ | | +| fps | 1349 | +| iterations | 1653 | +| time_elapsed | 2508 | +| total_timesteps | 3385344 | +| train/ | | +| approx_kl | 0.040598575 | +| clip_fraction | 0.405 | +| clip_range | 0.108 | +| entropy_loss | -7.3 | +| explained_variance | -0.191 | +| learning_rate | 0.000133 | +| loss | -0.051 | +| n_updates | 6608 | +| policy_gradient_loss | -0.0333 | +| value_loss | 0.000163 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.29 | +| time/ | | +| fps | 1349 | +| iterations | 1654 | +| time_elapsed | 2510 | +| total_timesteps | 3387392 | +| train/ | | +| approx_kl | 0.0310986 | +| clip_fraction | 0.384 | +| clip_range | 0.108 | +| entropy_loss | -7.3 | +| explained_variance | -0.0829 | +| learning_rate | 0.000133 | +| loss | -0.0473 | +| n_updates | 6612 | +| policy_gradient_loss | -0.0312 | +| value_loss | 0.000215 | +--------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.288 | +| time/ | | +| fps | 1349 | +| iterations | 1655 | +| time_elapsed | 2511 | +| total_timesteps | 3389440 | +| train/ | | +| approx_kl | 0.03711474 | +| clip_fraction | 0.407 | +| clip_range | 0.108 | +| entropy_loss | -7.08 | +| explained_variance | -0.0304 | +| learning_rate | 0.000133 | +| loss | -0.0455 | +| n_updates | 6616 | +| policy_gradient_loss | -0.0322 | +| value_loss | 0.000205 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.289 | +| time/ | | +| fps | 1349 | +| iterations | 1656 | +| time_elapsed | 2513 | +| total_timesteps | 3391488 | +| train/ | | +| approx_kl | 0.04054819 | +| clip_fraction | 0.426 | +| clip_range | 0.108 | +| entropy_loss | -7.19 | +| explained_variance | -0.23 | +| learning_rate | 0.000133 | +| loss | -0.0544 | +| n_updates | 6620 | +| policy_gradient_loss | -0.033 | +| value_loss | 0.000177 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.289 | +| time/ | | +| fps | 1349 | +| iterations | 1657 | +| time_elapsed | 2514 | +| total_timesteps | 3393536 | +| train/ | | +| approx_kl | 0.036268864 | +| clip_fraction | 0.415 | +| clip_range | 0.108 | +| entropy_loss | -7.29 | +| explained_variance | -0.1 | +| learning_rate | 0.000133 | +| loss | -0.0553 | +| n_updates | 6624 | +| policy_gradient_loss | -0.0347 | +| value_loss | 0.000179 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.286 | +| time/ | | +| fps | 1349 | +| iterations | 1658 | +| time_elapsed | 2516 | +| total_timesteps | 3395584 | +| train/ | | +| approx_kl | 0.043534234 | +| clip_fraction | 0.423 | +| clip_range | 0.108 | +| entropy_loss | -7.3 | +| explained_variance | -0.149 | +| learning_rate | 0.000133 | +| loss | -0.0578 | +| n_updates | 6628 | +| policy_gradient_loss | -0.0351 | +| value_loss | 0.000117 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.286 | +| time/ | | +| fps | 1349 | +| iterations | 1659 | +| time_elapsed | 2517 | +| total_timesteps | 3397632 | +| train/ | | +| approx_kl | 0.036278673 | +| clip_fraction | 0.409 | +| clip_range | 0.108 | +| entropy_loss | -7.26 | +| explained_variance | -0.451 | +| learning_rate | 0.000133 | +| loss | -0.0577 | +| n_updates | 6632 | +| policy_gradient_loss | -0.0377 | +| value_loss | 5.85e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.286 | +| time/ | | +| fps | 1349 | +| iterations | 1660 | +| time_elapsed | 2518 | +| total_timesteps | 3399680 | +| train/ | | +| approx_kl | 0.040942706 | +| clip_fraction | 0.417 | +| clip_range | 0.108 | +| entropy_loss | -7.18 | +| explained_variance | -0.0699 | +| learning_rate | 0.000133 | +| loss | -0.0542 | +| n_updates | 6636 | +| policy_gradient_loss | -0.0318 | +| value_loss | 0.000153 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.285 | +| time/ | | +| fps | 1349 | +| iterations | 1661 | +| time_elapsed | 2520 | +| total_timesteps | 3401728 | +| train/ | | +| approx_kl | 0.040425286 | +| clip_fraction | 0.429 | +| clip_range | 0.108 | +| entropy_loss | -7.28 | +| explained_variance | -0.0717 | +| learning_rate | 0.000133 | +| loss | -0.0543 | +| n_updates | 6640 | +| policy_gradient_loss | -0.0328 | +| value_loss | 0.000124 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.281 | +| time/ | | +| fps | 1349 | +| iterations | 1662 | +| time_elapsed | 2521 | +| total_timesteps | 3403776 | +| train/ | | +| approx_kl | 0.03903865 | +| clip_fraction | 0.419 | +| clip_range | 0.107 | +| entropy_loss | -7.24 | +| explained_variance | -0.11 | +| learning_rate | 0.000133 | +| loss | -0.0555 | +| n_updates | 6644 | +| policy_gradient_loss | -0.0319 | +| value_loss | 0.000174 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.281 | +| time/ | | +| fps | 1349 | +| iterations | 1663 | +| time_elapsed | 2523 | +| total_timesteps | 3405824 | +| train/ | | +| approx_kl | 0.035847243 | +| clip_fraction | 0.427 | +| clip_range | 0.107 | +| entropy_loss | -7.19 | +| explained_variance | -0.105 | +| learning_rate | 0.000133 | +| loss | -0.0527 | +| n_updates | 6648 | +| policy_gradient_loss | -0.0307 | +| value_loss | 0.00012 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 1349 | +| iterations | 1664 | +| time_elapsed | 2524 | +| total_timesteps | 3407872 | +| train/ | | +| approx_kl | 0.0314224 | +| clip_fraction | 0.42 | +| clip_range | 0.107 | +| entropy_loss | -7.17 | +| explained_variance | -0.208 | +| learning_rate | 0.000133 | +| loss | -0.0526 | +| n_updates | 6652 | +| policy_gradient_loss | -0.0292 | +| value_loss | 0.000148 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.291 | +| time/ | | +| fps | 1349 | +| iterations | 1665 | +| time_elapsed | 2526 | +| total_timesteps | 3409920 | +| train/ | | +| approx_kl | 0.0321744 | +| clip_fraction | 0.415 | +| clip_range | 0.107 | +| entropy_loss | -7.21 | +| explained_variance | -0.00729 | +| learning_rate | 0.000133 | +| loss | -0.0571 | +| n_updates | 6656 | +| policy_gradient_loss | -0.0309 | +| value_loss | 0.000129 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.298 | +| time/ | | +| fps | 1349 | +| iterations | 1666 | +| time_elapsed | 2527 | +| total_timesteps | 3411968 | +| train/ | | +| approx_kl | 0.030111566 | +| clip_fraction | 0.396 | +| clip_range | 0.107 | +| entropy_loss | -7.26 | +| explained_variance | -0.00625 | +| learning_rate | 0.000132 | +| loss | -0.035 | +| n_updates | 6660 | +| policy_gradient_loss | -0.0242 | +| value_loss | 0.00027 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 1349 | +| iterations | 1667 | +| time_elapsed | 2528 | +| total_timesteps | 3414016 | +| train/ | | +| approx_kl | 0.037522413 | +| clip_fraction | 0.393 | +| clip_range | 0.107 | +| entropy_loss | -6.97 | +| explained_variance | -0.0522 | +| learning_rate | 0.000132 | +| loss | -0.0542 | +| n_updates | 6664 | +| policy_gradient_loss | -0.0314 | +| value_loss | 0.000216 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 1349 | +| iterations | 1668 | +| time_elapsed | 2530 | +| total_timesteps | 3416064 | +| train/ | | +| approx_kl | 0.047236294 | +| clip_fraction | 0.451 | +| clip_range | 0.107 | +| entropy_loss | -7.13 | +| explained_variance | -0.174 | +| learning_rate | 0.000132 | +| loss | -0.0588 | +| n_updates | 6668 | +| policy_gradient_loss | -0.036 | +| value_loss | 0.000174 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.302 | +| time/ | | +| fps | 1350 | +| iterations | 1669 | +| time_elapsed | 2531 | +| total_timesteps | 3418112 | +| train/ | | +| approx_kl | 0.045919497 | +| clip_fraction | 0.422 | +| clip_range | 0.107 | +| entropy_loss | -7.24 | +| explained_variance | -0.159 | +| learning_rate | 0.000132 | +| loss | -0.0541 | +| n_updates | 6672 | +| policy_gradient_loss | -0.034 | +| value_loss | 0.000201 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 1350 | +| iterations | 1670 | +| time_elapsed | 2533 | +| total_timesteps | 3420160 | +| train/ | | +| approx_kl | 0.05199819 | +| clip_fraction | 0.425 | +| clip_range | 0.107 | +| entropy_loss | -7.14 | +| explained_variance | -0.238 | +| learning_rate | 0.000132 | +| loss | -0.052 | +| n_updates | 6676 | +| policy_gradient_loss | -0.0317 | +| value_loss | 0.000176 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.293 | +| time/ | | +| fps | 1350 | +| iterations | 1671 | +| time_elapsed | 2534 | +| total_timesteps | 3422208 | +| train/ | | +| approx_kl | 0.04065318 | +| clip_fraction | 0.405 | +| clip_range | 0.107 | +| entropy_loss | -7.23 | +| explained_variance | -0.152 | +| learning_rate | 0.000132 | +| loss | -0.0487 | +| n_updates | 6680 | +| policy_gradient_loss | -0.0313 | +| value_loss | 0.000194 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.293 | +| time/ | | +| fps | 1350 | +| iterations | 1672 | +| time_elapsed | 2536 | +| total_timesteps | 3424256 | +| train/ | | +| approx_kl | 0.038548727 | +| clip_fraction | 0.401 | +| clip_range | 0.107 | +| entropy_loss | -7.17 | +| explained_variance | -0.114 | +| learning_rate | 0.000132 | +| loss | -0.0514 | +| n_updates | 6684 | +| policy_gradient_loss | -0.0297 | +| value_loss | 0.000236 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.293 | +| time/ | | +| fps | 1350 | +| iterations | 1673 | +| time_elapsed | 2537 | +| total_timesteps | 3426304 | +| train/ | | +| approx_kl | 0.03711213 | +| clip_fraction | 0.396 | +| clip_range | 0.107 | +| entropy_loss | -7.14 | +| explained_variance | -0.118 | +| learning_rate | 0.000132 | +| loss | -0.0468 | +| n_updates | 6688 | +| policy_gradient_loss | -0.0301 | +| value_loss | 0.000223 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.293 | +| time/ | | +| fps | 1350 | +| iterations | 1674 | +| time_elapsed | 2538 | +| total_timesteps | 3428352 | +| train/ | | +| approx_kl | 0.038270928 | +| clip_fraction | 0.419 | +| clip_range | 0.107 | +| entropy_loss | -7.13 | +| explained_variance | -0.249 | +| learning_rate | 0.000132 | +| loss | -0.0496 | +| n_updates | 6692 | +| policy_gradient_loss | -0.0339 | +| value_loss | 0.000139 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.294 | +| time/ | | +| fps | 1350 | +| iterations | 1675 | +| time_elapsed | 2540 | +| total_timesteps | 3430400 | +| train/ | | +| approx_kl | 0.037590478 | +| clip_fraction | 0.423 | +| clip_range | 0.107 | +| entropy_loss | -7.28 | +| explained_variance | -0.105 | +| learning_rate | 0.000132 | +| loss | -0.0506 | +| n_updates | 6696 | +| policy_gradient_loss | -0.0347 | +| value_loss | 0.00012 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.302 | +| time/ | | +| fps | 1350 | +| iterations | 1676 | +| time_elapsed | 2541 | +| total_timesteps | 3432448 | +| train/ | | +| approx_kl | 0.03721556 | +| clip_fraction | 0.413 | +| clip_range | 0.107 | +| entropy_loss | -7.21 | +| explained_variance | -0.0331 | +| learning_rate | 0.000132 | +| loss | -0.0557 | +| n_updates | 6700 | +| policy_gradient_loss | -0.0314 | +| value_loss | 0.000129 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 1350 | +| iterations | 1677 | +| time_elapsed | 2543 | +| total_timesteps | 3434496 | +| train/ | | +| approx_kl | 0.03688103 | +| clip_fraction | 0.409 | +| clip_range | 0.107 | +| entropy_loss | -7.04 | +| explained_variance | 0.0326 | +| learning_rate | 0.000132 | +| loss | -0.0487 | +| n_updates | 6704 | +| policy_gradient_loss | -0.0261 | +| value_loss | 0.000292 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 1350 | +| iterations | 1678 | +| time_elapsed | 2544 | +| total_timesteps | 3436544 | +| train/ | | +| approx_kl | 0.03930977 | +| clip_fraction | 0.41 | +| clip_range | 0.107 | +| entropy_loss | -7.22 | +| explained_variance | -0.0842 | +| learning_rate | 0.000132 | +| loss | -0.0539 | +| n_updates | 6708 | +| policy_gradient_loss | -0.0324 | +| value_loss | 0.000162 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1350 | +| iterations | 1679 | +| time_elapsed | 2545 | +| total_timesteps | 3438592 | +| train/ | | +| approx_kl | 0.044834614 | +| clip_fraction | 0.406 | +| clip_range | 0.107 | +| entropy_loss | -7.19 | +| explained_variance | -0.287 | +| learning_rate | 0.000132 | +| loss | -0.0514 | +| n_updates | 6712 | +| policy_gradient_loss | -0.0326 | +| value_loss | 0.000156 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1350 | +| iterations | 1680 | +| time_elapsed | 2547 | +| total_timesteps | 3440640 | +| train/ | | +| approx_kl | 0.037793823 | +| clip_fraction | 0.408 | +| clip_range | 0.107 | +| entropy_loss | -7.26 | +| explained_variance | -0.244 | +| learning_rate | 0.000132 | +| loss | -0.055 | +| n_updates | 6716 | +| policy_gradient_loss | -0.0315 | +| value_loss | 0.000183 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1350 | +| iterations | 1681 | +| time_elapsed | 2548 | +| total_timesteps | 3442688 | +| train/ | | +| approx_kl | 0.03416656 | +| clip_fraction | 0.413 | +| clip_range | 0.107 | +| entropy_loss | -7.25 | +| explained_variance | -0.154 | +| learning_rate | 0.000132 | +| loss | -0.0469 | +| n_updates | 6720 | +| policy_gradient_loss | -0.0284 | +| value_loss | 0.000203 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1350 | +| iterations | 1682 | +| time_elapsed | 2550 | +| total_timesteps | 3444736 | +| train/ | | +| approx_kl | 0.038327854 | +| clip_fraction | 0.422 | +| clip_range | 0.107 | +| entropy_loss | -7.28 | +| explained_variance | -0.311 | +| learning_rate | 0.000132 | +| loss | -0.0564 | +| n_updates | 6724 | +| policy_gradient_loss | -0.0338 | +| value_loss | 0.000148 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1350 | +| iterations | 1683 | +| time_elapsed | 2551 | +| total_timesteps | 3446784 | +| train/ | | +| approx_kl | 0.029390559 | +| clip_fraction | 0.382 | +| clip_range | 0.107 | +| entropy_loss | -7.35 | +| explained_variance | -0.0559 | +| learning_rate | 0.000132 | +| loss | -0.0423 | +| n_updates | 6728 | +| policy_gradient_loss | -0.025 | +| value_loss | 0.000232 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1350 | +| iterations | 1684 | +| time_elapsed | 2553 | +| total_timesteps | 3448832 | +| train/ | | +| approx_kl | 0.04108592 | +| clip_fraction | 0.412 | +| clip_range | 0.107 | +| entropy_loss | -7.37 | +| explained_variance | -0.155 | +| learning_rate | 0.000132 | +| loss | -0.0561 | +| n_updates | 6732 | +| policy_gradient_loss | -0.03 | +| value_loss | 0.000333 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1350 | +| iterations | 1685 | +| time_elapsed | 2554 | +| total_timesteps | 3450880 | +| train/ | | +| approx_kl | 0.034402747 | +| clip_fraction | 0.425 | +| clip_range | 0.107 | +| entropy_loss | -7.26 | +| explained_variance | -0.00166 | +| learning_rate | 0.000132 | +| loss | -0.0473 | +| n_updates | 6736 | +| policy_gradient_loss | -0.0347 | +| value_loss | 0.000276 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1350 | +| iterations | 1686 | +| time_elapsed | 2555 | +| total_timesteps | 3452928 | +| train/ | | +| approx_kl | 0.039021783 | +| clip_fraction | 0.44 | +| clip_range | 0.107 | +| entropy_loss | -7.29 | +| explained_variance | -0.769 | +| learning_rate | 0.000132 | +| loss | -0.0682 | +| n_updates | 6740 | +| policy_gradient_loss | -0.0387 | +| value_loss | 0.000113 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1350 | +| iterations | 1687 | +| time_elapsed | 2557 | +| total_timesteps | 3454976 | +| train/ | | +| approx_kl | 0.039871123 | +| clip_fraction | 0.416 | +| clip_range | 0.107 | +| entropy_loss | -7.29 | +| explained_variance | -0.092 | +| learning_rate | 0.000132 | +| loss | -0.0543 | +| n_updates | 6744 | +| policy_gradient_loss | -0.0309 | +| value_loss | 0.000198 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1351 | +| iterations | 1688 | +| time_elapsed | 2558 | +| total_timesteps | 3457024 | +| train/ | | +| approx_kl | 0.03829807 | +| clip_fraction | 0.411 | +| clip_range | 0.107 | +| entropy_loss | -7.19 | +| explained_variance | -0.147 | +| learning_rate | 0.000132 | +| loss | -0.0516 | +| n_updates | 6748 | +| policy_gradient_loss | -0.0303 | +| value_loss | 0.000163 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1351 | +| iterations | 1689 | +| time_elapsed | 2560 | +| total_timesteps | 3459072 | +| train/ | | +| approx_kl | 0.044335503 | +| clip_fraction | 0.432 | +| clip_range | 0.107 | +| entropy_loss | -7.23 | +| explained_variance | -0.135 | +| learning_rate | 0.000132 | +| loss | -0.0569 | +| n_updates | 6752 | +| policy_gradient_loss | -0.0333 | +| value_loss | 0.000173 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1351 | +| iterations | 1690 | +| time_elapsed | 2561 | +| total_timesteps | 3461120 | +| train/ | | +| approx_kl | 0.03901182 | +| clip_fraction | 0.433 | +| clip_range | 0.107 | +| entropy_loss | -7.17 | +| explained_variance | -0.401 | +| learning_rate | 0.000132 | +| loss | -0.0585 | +| n_updates | 6756 | +| policy_gradient_loss | -0.0336 | +| value_loss | 0.000103 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.3 | +| time/ | | +| fps | 1351 | +| iterations | 1691 | +| time_elapsed | 2563 | +| total_timesteps | 3463168 | +| train/ | | +| approx_kl | 0.03796702 | +| clip_fraction | 0.418 | +| clip_range | 0.107 | +| entropy_loss | -7.32 | +| explained_variance | -0.0725 | +| learning_rate | 0.000131 | +| loss | -0.0489 | +| n_updates | 6760 | +| policy_gradient_loss | -0.0302 | +| value_loss | 0.000158 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.298 | +| time/ | | +| fps | 1351 | +| iterations | 1692 | +| time_elapsed | 2564 | +| total_timesteps | 3465216 | +| train/ | | +| approx_kl | 0.032978103 | +| clip_fraction | 0.376 | +| clip_range | 0.107 | +| entropy_loss | -7.35 | +| explained_variance | -0.156 | +| learning_rate | 0.000131 | +| loss | -0.0447 | +| n_updates | 6764 | +| policy_gradient_loss | -0.0283 | +| value_loss | 0.0002 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.297 | +| time/ | | +| fps | 1351 | +| iterations | 1693 | +| time_elapsed | 2565 | +| total_timesteps | 3467264 | +| train/ | | +| approx_kl | 0.03912645 | +| clip_fraction | 0.417 | +| clip_range | 0.107 | +| entropy_loss | -7.28 | +| explained_variance | -0.171 | +| learning_rate | 0.000131 | +| loss | -0.0517 | +| n_updates | 6768 | +| policy_gradient_loss | -0.0318 | +| value_loss | 0.000175 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 1351 | +| iterations | 1694 | +| time_elapsed | 2567 | +| total_timesteps | 3469312 | +| train/ | | +| approx_kl | 0.045453288 | +| clip_fraction | 0.413 | +| clip_range | 0.107 | +| entropy_loss | -7.29 | +| explained_variance | -0.123 | +| learning_rate | 0.000131 | +| loss | -0.053 | +| n_updates | 6772 | +| policy_gradient_loss | -0.0321 | +| value_loss | 0.000122 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.298 | +| time/ | | +| fps | 1351 | +| iterations | 1695 | +| time_elapsed | 2568 | +| total_timesteps | 3471360 | +| train/ | | +| approx_kl | 0.035886593 | +| clip_fraction | 0.424 | +| clip_range | 0.107 | +| entropy_loss | -7.23 | +| explained_variance | -0.177 | +| learning_rate | 0.000131 | +| loss | -0.0513 | +| n_updates | 6776 | +| policy_gradient_loss | -0.0305 | +| value_loss | 0.000218 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.294 | +| time/ | | +| fps | 1351 | +| iterations | 1696 | +| time_elapsed | 2570 | +| total_timesteps | 3473408 | +| train/ | | +| approx_kl | 0.038775247 | +| clip_fraction | 0.414 | +| clip_range | 0.107 | +| entropy_loss | -7.27 | +| explained_variance | -0.161 | +| learning_rate | 0.000131 | +| loss | -0.0602 | +| n_updates | 6780 | +| policy_gradient_loss | -0.0337 | +| value_loss | 0.000147 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.294 | +| time/ | | +| fps | 1351 | +| iterations | 1697 | +| time_elapsed | 2571 | +| total_timesteps | 3475456 | +| train/ | | +| approx_kl | 0.03807039 | +| clip_fraction | 0.418 | +| clip_range | 0.107 | +| entropy_loss | -7.15 | +| explained_variance | -0.107 | +| learning_rate | 0.000131 | +| loss | -0.0522 | +| n_updates | 6784 | +| policy_gradient_loss | -0.0323 | +| value_loss | 0.00013 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.293 | +| time/ | | +| fps | 1351 | +| iterations | 1698 | +| time_elapsed | 2572 | +| total_timesteps | 3477504 | +| train/ | | +| approx_kl | 0.036542267 | +| clip_fraction | 0.403 | +| clip_range | 0.107 | +| entropy_loss | -7.29 | +| explained_variance | -0.0187 | +| learning_rate | 0.000131 | +| loss | -0.0455 | +| n_updates | 6788 | +| policy_gradient_loss | -0.0299 | +| value_loss | 0.00017 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.3 | +| time/ | | +| fps | 1351 | +| iterations | 1699 | +| time_elapsed | 2574 | +| total_timesteps | 3479552 | +| train/ | | +| approx_kl | 0.04112177 | +| clip_fraction | 0.433 | +| clip_range | 0.107 | +| entropy_loss | -7.18 | +| explained_variance | -0.0695 | +| learning_rate | 0.000131 | +| loss | -0.0545 | +| n_updates | 6792 | +| policy_gradient_loss | -0.0331 | +| value_loss | 0.000148 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.293 | +| time/ | | +| fps | 1351 | +| iterations | 1700 | +| time_elapsed | 2575 | +| total_timesteps | 3481600 | +| train/ | | +| approx_kl | 0.040386084 | +| clip_fraction | 0.408 | +| clip_range | 0.107 | +| entropy_loss | -7.12 | +| explained_variance | -0.0906 | +| learning_rate | 0.000131 | +| loss | -0.0485 | +| n_updates | 6796 | +| policy_gradient_loss | -0.0292 | +| value_loss | 0.000288 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.287 | +| time/ | | +| fps | 1351 | +| iterations | 1701 | +| time_elapsed | 2577 | +| total_timesteps | 3483648 | +| train/ | | +| approx_kl | 0.046761617 | +| clip_fraction | 0.441 | +| clip_range | 0.106 | +| entropy_loss | -7.11 | +| explained_variance | -0.292 | +| learning_rate | 0.000131 | +| loss | -0.0509 | +| n_updates | 6800 | +| policy_gradient_loss | -0.036 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.287 | +| time/ | | +| fps | 1351 | +| iterations | 1702 | +| time_elapsed | 2578 | +| total_timesteps | 3485696 | +| train/ | | +| approx_kl | 0.039250422 | +| clip_fraction | 0.43 | +| clip_range | 0.106 | +| entropy_loss | -7.09 | +| explained_variance | -0.207 | +| learning_rate | 0.000131 | +| loss | -0.0505 | +| n_updates | 6804 | +| policy_gradient_loss | -0.0323 | +| value_loss | 0.000118 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.298 | +| time/ | | +| fps | 1351 | +| iterations | 1703 | +| time_elapsed | 2579 | +| total_timesteps | 3487744 | +| train/ | | +| approx_kl | 0.041221034 | +| clip_fraction | 0.442 | +| clip_range | 0.106 | +| entropy_loss | -7.11 | +| explained_variance | -0.0623 | +| learning_rate | 0.000131 | +| loss | -0.0507 | +| n_updates | 6808 | +| policy_gradient_loss | -0.0301 | +| value_loss | 0.00013 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.298 | +| time/ | | +| fps | 1351 | +| iterations | 1704 | +| time_elapsed | 2581 | +| total_timesteps | 3489792 | +| train/ | | +| approx_kl | 0.042042498 | +| clip_fraction | 0.425 | +| clip_range | 0.106 | +| entropy_loss | -7.12 | +| explained_variance | -0.0158 | +| learning_rate | 0.000131 | +| loss | -0.0405 | +| n_updates | 6812 | +| policy_gradient_loss | -0.029 | +| value_loss | 0.000216 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 1352 | +| iterations | 1705 | +| time_elapsed | 2582 | +| total_timesteps | 3491840 | +| train/ | | +| approx_kl | 0.038264807 | +| clip_fraction | 0.391 | +| clip_range | 0.106 | +| entropy_loss | -7.18 | +| explained_variance | -0.178 | +| learning_rate | 0.000131 | +| loss | -0.0511 | +| n_updates | 6816 | +| policy_gradient_loss | -0.0331 | +| value_loss | 0.000215 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.298 | +| time/ | | +| fps | 1352 | +| iterations | 1706 | +| time_elapsed | 2584 | +| total_timesteps | 3493888 | +| train/ | | +| approx_kl | 0.042123422 | +| clip_fraction | 0.422 | +| clip_range | 0.106 | +| entropy_loss | -7.24 | +| explained_variance | -0.381 | +| learning_rate | 0.000131 | +| loss | -0.0459 | +| n_updates | 6820 | +| policy_gradient_loss | -0.032 | +| value_loss | 9.17e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.298 | +| time/ | | +| fps | 1352 | +| iterations | 1707 | +| time_elapsed | 2585 | +| total_timesteps | 3495936 | +| train/ | | +| approx_kl | 0.04737062 | +| clip_fraction | 0.436 | +| clip_range | 0.106 | +| entropy_loss | -7.12 | +| explained_variance | -0.0779 | +| learning_rate | 0.000131 | +| loss | -0.0542 | +| n_updates | 6824 | +| policy_gradient_loss | -0.0336 | +| value_loss | 0.000281 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 1352 | +| iterations | 1708 | +| time_elapsed | 2586 | +| total_timesteps | 3497984 | +| train/ | | +| approx_kl | 0.04013253 | +| clip_fraction | 0.424 | +| clip_range | 0.106 | +| entropy_loss | -7.29 | +| explained_variance | -0.142 | +| learning_rate | 0.000131 | +| loss | -0.0556 | +| n_updates | 6828 | +| policy_gradient_loss | -0.0342 | +| value_loss | 0.000151 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.304 | +| time/ | | +| fps | 1352 | +| iterations | 1709 | +| time_elapsed | 2588 | +| total_timesteps | 3500032 | +| train/ | | +| approx_kl | 0.037090033 | +| clip_fraction | 0.403 | +| clip_range | 0.106 | +| entropy_loss | -7.3 | +| explained_variance | -0.0911 | +| learning_rate | 0.000131 | +| loss | -0.0493 | +| n_updates | 6832 | +| policy_gradient_loss | -0.0315 | +| value_loss | 0.000187 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 1352 | +| iterations | 1710 | +| time_elapsed | 2590 | +| total_timesteps | 3502080 | +| train/ | | +| approx_kl | 0.03701985 | +| clip_fraction | 0.416 | +| clip_range | 0.106 | +| entropy_loss | -7.38 | +| explained_variance | -0.0525 | +| learning_rate | 0.000131 | +| loss | -0.0531 | +| n_updates | 6836 | +| policy_gradient_loss | -0.0307 | +| value_loss | 0.00028 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 1352 | +| iterations | 1711 | +| time_elapsed | 2591 | +| total_timesteps | 3504128 | +| train/ | | +| approx_kl | 0.04269091 | +| clip_fraction | 0.454 | +| clip_range | 0.106 | +| entropy_loss | -7.25 | +| explained_variance | -0.171 | +| learning_rate | 0.000131 | +| loss | -0.0677 | +| n_updates | 6840 | +| policy_gradient_loss | -0.0385 | +| value_loss | 0.000118 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 1352 | +| iterations | 1712 | +| time_elapsed | 2592 | +| total_timesteps | 3506176 | +| train/ | | +| approx_kl | 0.042127047 | +| clip_fraction | 0.431 | +| clip_range | 0.106 | +| entropy_loss | -7.29 | +| explained_variance | -0.189 | +| learning_rate | 0.000131 | +| loss | -0.059 | +| n_updates | 6844 | +| policy_gradient_loss | -0.0359 | +| value_loss | 9.87e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.306 | +| time/ | | +| fps | 1352 | +| iterations | 1713 | +| time_elapsed | 2594 | +| total_timesteps | 3508224 | +| train/ | | +| approx_kl | 0.03334122 | +| clip_fraction | 0.396 | +| clip_range | 0.106 | +| entropy_loss | -7.15 | +| explained_variance | -0.0977 | +| learning_rate | 0.000131 | +| loss | -0.0454 | +| n_updates | 6848 | +| policy_gradient_loss | -0.0297 | +| value_loss | 0.00027 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 1352 | +| iterations | 1714 | +| time_elapsed | 2595 | +| total_timesteps | 3510272 | +| train/ | | +| approx_kl | 0.030029103 | +| clip_fraction | 0.399 | +| clip_range | 0.106 | +| entropy_loss | -7.36 | +| explained_variance | -0.0738 | +| learning_rate | 0.000131 | +| loss | -0.0505 | +| n_updates | 6852 | +| policy_gradient_loss | -0.0302 | +| value_loss | 0.000302 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 1352 | +| iterations | 1715 | +| time_elapsed | 2597 | +| total_timesteps | 3512320 | +| train/ | | +| approx_kl | 0.041963317 | +| clip_fraction | 0.439 | +| clip_range | 0.106 | +| entropy_loss | -7.27 | +| explained_variance | -0.308 | +| learning_rate | 0.00013 | +| loss | -0.0678 | +| n_updates | 6856 | +| policy_gradient_loss | -0.0365 | +| value_loss | 0.00012 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 1352 | +| iterations | 1716 | +| time_elapsed | 2598 | +| total_timesteps | 3514368 | +| train/ | | +| approx_kl | 0.03574879 | +| clip_fraction | 0.38 | +| clip_range | 0.106 | +| entropy_loss | -7.22 | +| explained_variance | -0.133 | +| learning_rate | 0.00013 | +| loss | -0.0489 | +| n_updates | 6860 | +| policy_gradient_loss | -0.0269 | +| value_loss | 0.000202 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.298 | +| time/ | | +| fps | 1352 | +| iterations | 1717 | +| time_elapsed | 2599 | +| total_timesteps | 3516416 | +| train/ | | +| approx_kl | 0.04621631 | +| clip_fraction | 0.417 | +| clip_range | 0.106 | +| entropy_loss | -7.28 | +| explained_variance | -0.0848 | +| learning_rate | 0.00013 | +| loss | -0.058 | +| n_updates | 6864 | +| policy_gradient_loss | -0.0331 | +| value_loss | 0.00015 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.3 | +| time/ | | +| fps | 1352 | +| iterations | 1718 | +| time_elapsed | 2601 | +| total_timesteps | 3518464 | +| train/ | | +| approx_kl | 0.043302774 | +| clip_fraction | 0.434 | +| clip_range | 0.106 | +| entropy_loss | -7.23 | +| explained_variance | -0.0103 | +| learning_rate | 0.00013 | +| loss | -0.0601 | +| n_updates | 6868 | +| policy_gradient_loss | -0.0336 | +| value_loss | 0.000141 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.3 | +| time/ | | +| fps | 1352 | +| iterations | 1719 | +| time_elapsed | 2602 | +| total_timesteps | 3520512 | +| train/ | | +| approx_kl | 0.037925426 | +| clip_fraction | 0.415 | +| clip_range | 0.106 | +| entropy_loss | -7.22 | +| explained_variance | -0.22 | +| learning_rate | 0.00013 | +| loss | -0.0525 | +| n_updates | 6872 | +| policy_gradient_loss | -0.0339 | +| value_loss | 9.16e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 1352 | +| iterations | 1720 | +| time_elapsed | 2604 | +| total_timesteps | 3522560 | +| train/ | | +| approx_kl | 0.036406606 | +| clip_fraction | 0.412 | +| clip_range | 0.106 | +| entropy_loss | -7.34 | +| explained_variance | -0.0706 | +| learning_rate | 0.00013 | +| loss | -0.0478 | +| n_updates | 6876 | +| policy_gradient_loss | -0.0311 | +| value_loss | 0.000163 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 1352 | +| iterations | 1721 | +| time_elapsed | 2605 | +| total_timesteps | 3524608 | +| train/ | | +| approx_kl | 0.03976845 | +| clip_fraction | 0.44 | +| clip_range | 0.106 | +| entropy_loss | -7.16 | +| explained_variance | -0.32 | +| learning_rate | 0.00013 | +| loss | -0.0575 | +| n_updates | 6880 | +| policy_gradient_loss | -0.0394 | +| value_loss | 6.45e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 1352 | +| iterations | 1722 | +| time_elapsed | 2606 | +| total_timesteps | 3526656 | +| train/ | | +| approx_kl | 0.037945934 | +| clip_fraction | 0.42 | +| clip_range | 0.106 | +| entropy_loss | -7.26 | +| explained_variance | -0.11 | +| learning_rate | 0.00013 | +| loss | -0.0409 | +| n_updates | 6884 | +| policy_gradient_loss | -0.0298 | +| value_loss | 0.000261 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.295 | +| time/ | | +| fps | 1352 | +| iterations | 1723 | +| time_elapsed | 2608 | +| total_timesteps | 3528704 | +| train/ | | +| approx_kl | 0.037563764 | +| clip_fraction | 0.403 | +| clip_range | 0.106 | +| entropy_loss | -7.37 | +| explained_variance | -0.102 | +| learning_rate | 0.00013 | +| loss | -0.0544 | +| n_updates | 6888 | +| policy_gradient_loss | -0.0327 | +| value_loss | 0.000144 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.3 | +| time/ | | +| fps | 1352 | +| iterations | 1724 | +| time_elapsed | 2609 | +| total_timesteps | 3530752 | +| train/ | | +| approx_kl | 0.039520483 | +| clip_fraction | 0.415 | +| clip_range | 0.106 | +| entropy_loss | -7.19 | +| explained_variance | -0.262 | +| learning_rate | 0.00013 | +| loss | -0.0535 | +| n_updates | 6892 | +| policy_gradient_loss | -0.0314 | +| value_loss | 0.00014 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.298 | +| time/ | | +| fps | 1352 | +| iterations | 1725 | +| time_elapsed | 2611 | +| total_timesteps | 3532800 | +| train/ | | +| approx_kl | 0.03559476 | +| clip_fraction | 0.407 | +| clip_range | 0.106 | +| entropy_loss | -7.32 | +| explained_variance | -0.0353 | +| learning_rate | 0.00013 | +| loss | -0.0393 | +| n_updates | 6896 | +| policy_gradient_loss | -0.0274 | +| value_loss | 0.000249 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.302 | +| time/ | | +| fps | 1352 | +| iterations | 1726 | +| time_elapsed | 2612 | +| total_timesteps | 3534848 | +| train/ | | +| approx_kl | 0.035583857 | +| clip_fraction | 0.41 | +| clip_range | 0.106 | +| entropy_loss | -7.21 | +| explained_variance | -0.144 | +| learning_rate | 0.00013 | +| loss | -0.0515 | +| n_updates | 6900 | +| policy_gradient_loss | -0.0308 | +| value_loss | 0.000223 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.29 | +| time/ | | +| fps | 1352 | +| iterations | 1727 | +| time_elapsed | 2614 | +| total_timesteps | 3536896 | +| train/ | | +| approx_kl | 0.033642083 | +| clip_fraction | 0.376 | +| clip_range | 0.106 | +| entropy_loss | -7.44 | +| explained_variance | -0.0619 | +| learning_rate | 0.00013 | +| loss | -0.0559 | +| n_updates | 6904 | +| policy_gradient_loss | -0.029 | +| value_loss | 0.000312 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.29 | +| time/ | | +| fps | 1353 | +| iterations | 1728 | +| time_elapsed | 2615 | +| total_timesteps | 3538944 | +| train/ | | +| approx_kl | 0.043845635 | +| clip_fraction | 0.441 | +| clip_range | 0.106 | +| entropy_loss | -7.22 | +| explained_variance | -0.0901 | +| learning_rate | 0.00013 | +| loss | -0.058 | +| n_updates | 6908 | +| policy_gradient_loss | -0.037 | +| value_loss | 0.000147 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.287 | +| time/ | | +| fps | 1353 | +| iterations | 1729 | +| time_elapsed | 2617 | +| total_timesteps | 3540992 | +| train/ | | +| approx_kl | 0.034723558 | +| clip_fraction | 0.448 | +| clip_range | 0.106 | +| entropy_loss | -7.36 | +| explained_variance | -0.23 | +| learning_rate | 0.00013 | +| loss | -0.0547 | +| n_updates | 6912 | +| policy_gradient_loss | -0.0339 | +| value_loss | 0.000121 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.288 | +| time/ | | +| fps | 1353 | +| iterations | 1730 | +| time_elapsed | 2618 | +| total_timesteps | 3543040 | +| train/ | | +| approx_kl | 0.038596228 | +| clip_fraction | 0.417 | +| clip_range | 0.106 | +| entropy_loss | -7.12 | +| explained_variance | -0.0711 | +| learning_rate | 0.00013 | +| loss | -0.044 | +| n_updates | 6916 | +| policy_gradient_loss | -0.0296 | +| value_loss | 0.000341 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.288 | +| time/ | | +| fps | 1353 | +| iterations | 1731 | +| time_elapsed | 2619 | +| total_timesteps | 3545088 | +| train/ | | +| approx_kl | 0.036298193 | +| clip_fraction | 0.419 | +| clip_range | 0.106 | +| entropy_loss | -7.31 | +| explained_variance | -0.0254 | +| learning_rate | 0.00013 | +| loss | -0.0609 | +| n_updates | 6920 | +| policy_gradient_loss | -0.0319 | +| value_loss | 0.000328 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.286 | +| time/ | | +| fps | 1353 | +| iterations | 1732 | +| time_elapsed | 2621 | +| total_timesteps | 3547136 | +| train/ | | +| approx_kl | 0.040111296 | +| clip_fraction | 0.454 | +| clip_range | 0.106 | +| entropy_loss | -7.35 | +| explained_variance | -0.518 | +| learning_rate | 0.00013 | +| loss | -0.0627 | +| n_updates | 6924 | +| policy_gradient_loss | -0.0397 | +| value_loss | 9.82e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 1353 | +| iterations | 1733 | +| time_elapsed | 2622 | +| total_timesteps | 3549184 | +| train/ | | +| approx_kl | 0.040785335 | +| clip_fraction | 0.448 | +| clip_range | 0.106 | +| entropy_loss | -7.34 | +| explained_variance | -0.235 | +| learning_rate | 0.00013 | +| loss | -0.0649 | +| n_updates | 6928 | +| policy_gradient_loss | -0.0396 | +| value_loss | 6.87e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 1353 | +| iterations | 1734 | +| time_elapsed | 2624 | +| total_timesteps | 3551232 | +| train/ | | +| approx_kl | 0.037744477 | +| clip_fraction | 0.413 | +| clip_range | 0.106 | +| entropy_loss | -7.29 | +| explained_variance | -0.283 | +| learning_rate | 0.00013 | +| loss | -0.0503 | +| n_updates | 6932 | +| policy_gradient_loss | -0.0324 | +| value_loss | 0.00012 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 1353 | +| iterations | 1735 | +| time_elapsed | 2625 | +| total_timesteps | 3553280 | +| train/ | | +| approx_kl | 0.03387882 | +| clip_fraction | 0.422 | +| clip_range | 0.106 | +| entropy_loss | -7.18 | +| explained_variance | -0.143 | +| learning_rate | 0.00013 | +| loss | -0.0415 | +| n_updates | 6936 | +| policy_gradient_loss | -0.029 | +| value_loss | 0.000155 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.281 | +| time/ | | +| fps | 1353 | +| iterations | 1736 | +| time_elapsed | 2627 | +| total_timesteps | 3555328 | +| train/ | | +| approx_kl | 0.03760595 | +| clip_fraction | 0.406 | +| clip_range | 0.106 | +| entropy_loss | -7.2 | +| explained_variance | -0.0726 | +| learning_rate | 0.00013 | +| loss | -0.0421 | +| n_updates | 6940 | +| policy_gradient_loss | -0.0302 | +| value_loss | 0.000168 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.281 | +| time/ | | +| fps | 1353 | +| iterations | 1737 | +| time_elapsed | 2628 | +| total_timesteps | 3557376 | +| train/ | | +| approx_kl | 0.039224736 | +| clip_fraction | 0.406 | +| clip_range | 0.106 | +| entropy_loss | -7.2 | +| explained_variance | -0.0662 | +| learning_rate | 0.00013 | +| loss | -0.0449 | +| n_updates | 6944 | +| policy_gradient_loss | -0.0296 | +| value_loss | 0.000232 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 1353 | +| iterations | 1738 | +| time_elapsed | 2629 | +| total_timesteps | 3559424 | +| train/ | | +| approx_kl | 0.037185565 | +| clip_fraction | 0.412 | +| clip_range | 0.106 | +| entropy_loss | -7.34 | +| explained_variance | -0.189 | +| learning_rate | 0.00013 | +| loss | -0.0474 | +| n_updates | 6948 | +| policy_gradient_loss | -0.0302 | +| value_loss | 0.000165 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.271 | +| time/ | | +| fps | 1353 | +| iterations | 1739 | +| time_elapsed | 2631 | +| total_timesteps | 3561472 | +| train/ | | +| approx_kl | 0.041888278 | +| clip_fraction | 0.443 | +| clip_range | 0.106 | +| entropy_loss | -7.27 | +| explained_variance | -0.264 | +| learning_rate | 0.00013 | +| loss | -0.0491 | +| n_updates | 6952 | +| policy_gradient_loss | -0.0347 | +| value_loss | 0.000134 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.27 | +| time/ | | +| fps | 1353 | +| iterations | 1740 | +| time_elapsed | 2632 | +| total_timesteps | 3563520 | +| train/ | | +| approx_kl | 0.045905113 | +| clip_fraction | 0.446 | +| clip_range | 0.105 | +| entropy_loss | -7.16 | +| explained_variance | -0.216 | +| learning_rate | 0.000129 | +| loss | -0.0598 | +| n_updates | 6956 | +| policy_gradient_loss | -0.0353 | +| value_loss | 0.000156 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.27 | +| time/ | | +| fps | 1353 | +| iterations | 1741 | +| time_elapsed | 2634 | +| total_timesteps | 3565568 | +| train/ | | +| approx_kl | 0.03729973 | +| clip_fraction | 0.422 | +| clip_range | 0.105 | +| entropy_loss | -7.33 | +| explained_variance | -0.279 | +| learning_rate | 0.000129 | +| loss | -0.0486 | +| n_updates | 6960 | +| policy_gradient_loss | -0.0305 | +| value_loss | 0.000145 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.263 | +| time/ | | +| fps | 1353 | +| iterations | 1742 | +| time_elapsed | 2635 | +| total_timesteps | 3567616 | +| train/ | | +| approx_kl | 0.036375724 | +| clip_fraction | 0.412 | +| clip_range | 0.105 | +| entropy_loss | -7.33 | +| explained_variance | -0.122 | +| learning_rate | 0.000129 | +| loss | -0.0501 | +| n_updates | 6964 | +| policy_gradient_loss | -0.0321 | +| value_loss | 0.000215 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.264 | +| time/ | | +| fps | 1353 | +| iterations | 1743 | +| time_elapsed | 2636 | +| total_timesteps | 3569664 | +| train/ | | +| approx_kl | 0.039672192 | +| clip_fraction | 0.433 | +| clip_range | 0.105 | +| entropy_loss | -7.37 | +| explained_variance | -0.104 | +| learning_rate | 0.000129 | +| loss | -0.0403 | +| n_updates | 6968 | +| policy_gradient_loss | -0.0285 | +| value_loss | 0.000162 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.258 | +| time/ | | +| fps | 1353 | +| iterations | 1744 | +| time_elapsed | 2638 | +| total_timesteps | 3571712 | +| train/ | | +| approx_kl | 0.048378967 | +| clip_fraction | 0.437 | +| clip_range | 0.105 | +| entropy_loss | -7.21 | +| explained_variance | -0.169 | +| learning_rate | 0.000129 | +| loss | -0.0515 | +| n_updates | 6972 | +| policy_gradient_loss | -0.0326 | +| value_loss | 0.000143 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.248 | +| time/ | | +| fps | 1353 | +| iterations | 1745 | +| time_elapsed | 2639 | +| total_timesteps | 3573760 | +| train/ | | +| approx_kl | 0.04060881 | +| clip_fraction | 0.396 | +| clip_range | 0.105 | +| entropy_loss | -7.21 | +| explained_variance | -0.106 | +| learning_rate | 0.000129 | +| loss | -0.0529 | +| n_updates | 6976 | +| policy_gradient_loss | -0.0304 | +| value_loss | 0.000151 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.248 | +| time/ | | +| fps | 1353 | +| iterations | 1746 | +| time_elapsed | 2641 | +| total_timesteps | 3575808 | +| train/ | | +| approx_kl | 0.04182437 | +| clip_fraction | 0.443 | +| clip_range | 0.105 | +| entropy_loss | -7.07 | +| explained_variance | -0.024 | +| learning_rate | 0.000129 | +| loss | -0.0599 | +| n_updates | 6980 | +| policy_gradient_loss | -0.035 | +| value_loss | 0.000127 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.248 | +| time/ | | +| fps | 1353 | +| iterations | 1747 | +| time_elapsed | 2642 | +| total_timesteps | 3577856 | +| train/ | | +| approx_kl | 0.043204114 | +| clip_fraction | 0.43 | +| clip_range | 0.105 | +| entropy_loss | -7.29 | +| explained_variance | -0.161 | +| learning_rate | 0.000129 | +| loss | -0.0552 | +| n_updates | 6984 | +| policy_gradient_loss | -0.0332 | +| value_loss | 0.00016 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.256 | +| time/ | | +| fps | 1353 | +| iterations | 1748 | +| time_elapsed | 2644 | +| total_timesteps | 3579904 | +| train/ | | +| approx_kl | 0.04116363 | +| clip_fraction | 0.391 | +| clip_range | 0.105 | +| entropy_loss | -7.38 | +| explained_variance | -0.0749 | +| learning_rate | 0.000129 | +| loss | -0.0577 | +| n_updates | 6988 | +| policy_gradient_loss | -0.032 | +| value_loss | 0.000148 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.262 | +| time/ | | +| fps | 1353 | +| iterations | 1749 | +| time_elapsed | 2645 | +| total_timesteps | 3581952 | +| train/ | | +| approx_kl | 0.030783445 | +| clip_fraction | 0.399 | +| clip_range | 0.105 | +| entropy_loss | -7.23 | +| explained_variance | -0.134 | +| learning_rate | 0.000129 | +| loss | -0.0497 | +| n_updates | 6992 | +| policy_gradient_loss | -0.029 | +| value_loss | 0.000255 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.257 | +| time/ | | +| fps | 1354 | +| iterations | 1750 | +| time_elapsed | 2646 | +| total_timesteps | 3584000 | +| train/ | | +| approx_kl | 0.035183534 | +| clip_fraction | 0.405 | +| clip_range | 0.105 | +| entropy_loss | -7.27 | +| explained_variance | -0.108 | +| learning_rate | 0.000129 | +| loss | -0.0401 | +| n_updates | 6996 | +| policy_gradient_loss | -0.027 | +| value_loss | 0.000305 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.257 | +| time/ | | +| fps | 1354 | +| iterations | 1751 | +| time_elapsed | 2648 | +| total_timesteps | 3586048 | +| train/ | | +| approx_kl | 0.040239383 | +| clip_fraction | 0.415 | +| clip_range | 0.105 | +| entropy_loss | -7.3 | +| explained_variance | -0.299 | +| learning_rate | 0.000129 | +| loss | -0.0475 | +| n_updates | 7000 | +| policy_gradient_loss | -0.0324 | +| value_loss | 0.000159 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.258 | +| time/ | | +| fps | 1354 | +| iterations | 1752 | +| time_elapsed | 2649 | +| total_timesteps | 3588096 | +| train/ | | +| approx_kl | 0.044957705 | +| clip_fraction | 0.441 | +| clip_range | 0.105 | +| entropy_loss | -7.31 | +| explained_variance | -0.16 | +| learning_rate | 0.000129 | +| loss | -0.0562 | +| n_updates | 7004 | +| policy_gradient_loss | -0.034 | +| value_loss | 0.000135 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.264 | +| time/ | | +| fps | 1354 | +| iterations | 1753 | +| time_elapsed | 2651 | +| total_timesteps | 3590144 | +| train/ | | +| approx_kl | 0.035229366 | +| clip_fraction | 0.393 | +| clip_range | 0.105 | +| entropy_loss | -7.39 | +| explained_variance | -0.0793 | +| learning_rate | 0.000129 | +| loss | -0.0416 | +| n_updates | 7008 | +| policy_gradient_loss | -0.0258 | +| value_loss | 0.000212 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.256 | +| time/ | | +| fps | 1354 | +| iterations | 1754 | +| time_elapsed | 2652 | +| total_timesteps | 3592192 | +| train/ | | +| approx_kl | 0.033901345 | +| clip_fraction | 0.402 | +| clip_range | 0.105 | +| entropy_loss | -7.23 | +| explained_variance | -0.258 | +| learning_rate | 0.000129 | +| loss | -0.0473 | +| n_updates | 7012 | +| policy_gradient_loss | -0.032 | +| value_loss | 0.000162 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.254 | +| time/ | | +| fps | 1354 | +| iterations | 1755 | +| time_elapsed | 2654 | +| total_timesteps | 3594240 | +| train/ | | +| approx_kl | 0.04304304 | +| clip_fraction | 0.437 | +| clip_range | 0.105 | +| entropy_loss | -7.21 | +| explained_variance | -0.0936 | +| learning_rate | 0.000129 | +| loss | -0.0404 | +| n_updates | 7016 | +| policy_gradient_loss | -0.0305 | +| value_loss | 0.000165 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.254 | +| time/ | | +| fps | 1354 | +| iterations | 1756 | +| time_elapsed | 2655 | +| total_timesteps | 3596288 | +| train/ | | +| approx_kl | 0.044036828 | +| clip_fraction | 0.435 | +| clip_range | 0.105 | +| entropy_loss | -7.25 | +| explained_variance | -0.143 | +| learning_rate | 0.000129 | +| loss | -0.06 | +| n_updates | 7020 | +| policy_gradient_loss | -0.0365 | +| value_loss | 0.000128 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.25 | +| time/ | | +| fps | 1354 | +| iterations | 1757 | +| time_elapsed | 2656 | +| total_timesteps | 3598336 | +| train/ | | +| approx_kl | 0.043020032 | +| clip_fraction | 0.436 | +| clip_range | 0.105 | +| entropy_loss | -7.33 | +| explained_variance | -0.12 | +| learning_rate | 0.000129 | +| loss | -0.0564 | +| n_updates | 7024 | +| policy_gradient_loss | -0.0327 | +| value_loss | 0.000127 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.25 | +| time/ | | +| fps | 1354 | +| iterations | 1758 | +| time_elapsed | 2658 | +| total_timesteps | 3600384 | +| train/ | | +| approx_kl | 0.0384124 | +| clip_fraction | 0.403 | +| clip_range | 0.105 | +| entropy_loss | -7.29 | +| explained_variance | -0.0281 | +| learning_rate | 0.000129 | +| loss | -0.0532 | +| n_updates | 7028 | +| policy_gradient_loss | -0.0314 | +| value_loss | 0.000237 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.249 | +| time/ | | +| fps | 1354 | +| iterations | 1759 | +| time_elapsed | 2659 | +| total_timesteps | 3602432 | +| train/ | | +| approx_kl | 0.039198257 | +| clip_fraction | 0.418 | +| clip_range | 0.105 | +| entropy_loss | -7.33 | +| explained_variance | -0.106 | +| learning_rate | 0.000129 | +| loss | -0.0576 | +| n_updates | 7032 | +| policy_gradient_loss | -0.035 | +| value_loss | 0.000134 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.25 | +| time/ | | +| fps | 1354 | +| iterations | 1760 | +| time_elapsed | 2661 | +| total_timesteps | 3604480 | +| train/ | | +| approx_kl | 0.034836818 | +| clip_fraction | 0.427 | +| clip_range | 0.105 | +| entropy_loss | -7.32 | +| explained_variance | -0.565 | +| learning_rate | 0.000129 | +| loss | -0.0653 | +| n_updates | 7036 | +| policy_gradient_loss | -0.0392 | +| value_loss | 6.62e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.25 | +| time/ | | +| fps | 1354 | +| iterations | 1761 | +| time_elapsed | 2662 | +| total_timesteps | 3606528 | +| train/ | | +| approx_kl | 0.03551094 | +| clip_fraction | 0.432 | +| clip_range | 0.105 | +| entropy_loss | -7.13 | +| explained_variance | 0.00434 | +| learning_rate | 0.000129 | +| loss | -0.0532 | +| n_updates | 7040 | +| policy_gradient_loss | -0.0335 | +| value_loss | 0.000133 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.253 | +| time/ | | +| fps | 1354 | +| iterations | 1762 | +| time_elapsed | 2664 | +| total_timesteps | 3608576 | +| train/ | | +| approx_kl | 0.035312038 | +| clip_fraction | 0.407 | +| clip_range | 0.105 | +| entropy_loss | -7.36 | +| explained_variance | -0.126 | +| learning_rate | 0.000129 | +| loss | -0.0479 | +| n_updates | 7044 | +| policy_gradient_loss | -0.029 | +| value_loss | 0.000106 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.256 | +| time/ | | +| fps | 1354 | +| iterations | 1763 | +| time_elapsed | 2665 | +| total_timesteps | 3610624 | +| train/ | | +| approx_kl | 0.028350277 | +| clip_fraction | 0.392 | +| clip_range | 0.105 | +| entropy_loss | -7.33 | +| explained_variance | -0.0752 | +| learning_rate | 0.000129 | +| loss | -0.0438 | +| n_updates | 7048 | +| policy_gradient_loss | -0.0245 | +| value_loss | 0.000219 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.259 | +| time/ | | +| fps | 1354 | +| iterations | 1764 | +| time_elapsed | 2667 | +| total_timesteps | 3612672 | +| train/ | | +| approx_kl | 0.036755577 | +| clip_fraction | 0.405 | +| clip_range | 0.105 | +| entropy_loss | -7.28 | +| explained_variance | -0.0809 | +| learning_rate | 0.000129 | +| loss | -0.0433 | +| n_updates | 7052 | +| policy_gradient_loss | -0.0261 | +| value_loss | 0.000159 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.259 | +| time/ | | +| fps | 1354 | +| iterations | 1765 | +| time_elapsed | 2668 | +| total_timesteps | 3614720 | +| train/ | | +| approx_kl | 0.03647138 | +| clip_fraction | 0.439 | +| clip_range | 0.105 | +| entropy_loss | -7.29 | +| explained_variance | -0.181 | +| learning_rate | 0.000128 | +| loss | -0.0611 | +| n_updates | 7056 | +| policy_gradient_loss | -0.0356 | +| value_loss | 7.71e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.255 | +| time/ | | +| fps | 1354 | +| iterations | 1766 | +| time_elapsed | 2669 | +| total_timesteps | 3616768 | +| train/ | | +| approx_kl | 0.031902853 | +| clip_fraction | 0.407 | +| clip_range | 0.105 | +| entropy_loss | -7.32 | +| explained_variance | 0.00155 | +| learning_rate | 0.000128 | +| loss | -0.0515 | +| n_updates | 7060 | +| policy_gradient_loss | -0.0288 | +| value_loss | 0.0002 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.255 | +| time/ | | +| fps | 1354 | +| iterations | 1767 | +| time_elapsed | 2671 | +| total_timesteps | 3618816 | +| train/ | | +| approx_kl | 0.029357433 | +| clip_fraction | 0.378 | +| clip_range | 0.105 | +| entropy_loss | -7.21 | +| explained_variance | -0.0109 | +| learning_rate | 0.000128 | +| loss | -0.0505 | +| n_updates | 7064 | +| policy_gradient_loss | -0.0305 | +| value_loss | 0.000235 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.26 | +| time/ | | +| fps | 1354 | +| iterations | 1768 | +| time_elapsed | 2672 | +| total_timesteps | 3620864 | +| train/ | | +| approx_kl | 0.034120493 | +| clip_fraction | 0.409 | +| clip_range | 0.105 | +| entropy_loss | -7.41 | +| explained_variance | -0.246 | +| learning_rate | 0.000128 | +| loss | -0.0552 | +| n_updates | 7068 | +| policy_gradient_loss | -0.0333 | +| value_loss | 0.00016 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.254 | +| time/ | | +| fps | 1354 | +| iterations | 1769 | +| time_elapsed | 2674 | +| total_timesteps | 3622912 | +| train/ | | +| approx_kl | 0.036283165 | +| clip_fraction | 0.412 | +| clip_range | 0.105 | +| entropy_loss | -7.23 | +| explained_variance | -0.0669 | +| learning_rate | 0.000128 | +| loss | -0.0389 | +| n_updates | 7072 | +| policy_gradient_loss | -0.0296 | +| value_loss | 0.000222 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.254 | +| time/ | | +| fps | 1354 | +| iterations | 1770 | +| time_elapsed | 2675 | +| total_timesteps | 3624960 | +| train/ | | +| approx_kl | 0.040359467 | +| clip_fraction | 0.436 | +| clip_range | 0.105 | +| entropy_loss | -7.33 | +| explained_variance | -0.255 | +| learning_rate | 0.000128 | +| loss | -0.0523 | +| n_updates | 7076 | +| policy_gradient_loss | -0.036 | +| value_loss | 0.000157 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.256 | +| time/ | | +| fps | 1354 | +| iterations | 1771 | +| time_elapsed | 2676 | +| total_timesteps | 3627008 | +| train/ | | +| approx_kl | 0.04202299 | +| clip_fraction | 0.414 | +| clip_range | 0.105 | +| entropy_loss | -7.33 | +| explained_variance | -0.129 | +| learning_rate | 0.000128 | +| loss | -0.0464 | +| n_updates | 7080 | +| policy_gradient_loss | -0.0292 | +| value_loss | 0.000125 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.251 | +| time/ | | +| fps | 1354 | +| iterations | 1772 | +| time_elapsed | 2678 | +| total_timesteps | 3629056 | +| train/ | | +| approx_kl | 0.038274933 | +| clip_fraction | 0.406 | +| clip_range | 0.105 | +| entropy_loss | -7.27 | +| explained_variance | -0.149 | +| learning_rate | 0.000128 | +| loss | -0.0506 | +| n_updates | 7084 | +| policy_gradient_loss | -0.0317 | +| value_loss | 0.000178 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.244 | +| time/ | | +| fps | 1355 | +| iterations | 1773 | +| time_elapsed | 2679 | +| total_timesteps | 3631104 | +| train/ | | +| approx_kl | 0.04275047 | +| clip_fraction | 0.439 | +| clip_range | 0.105 | +| entropy_loss | -7.11 | +| explained_variance | -0.0575 | +| learning_rate | 0.000128 | +| loss | -0.0536 | +| n_updates | 7088 | +| policy_gradient_loss | -0.0315 | +| value_loss | 0.000141 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.247 | +| time/ | | +| fps | 1355 | +| iterations | 1774 | +| time_elapsed | 2681 | +| total_timesteps | 3633152 | +| train/ | | +| approx_kl | 0.03936999 | +| clip_fraction | 0.419 | +| clip_range | 0.105 | +| entropy_loss | -7.13 | +| explained_variance | -0.51 | +| learning_rate | 0.000128 | +| loss | -0.0598 | +| n_updates | 7092 | +| policy_gradient_loss | -0.0351 | +| value_loss | 7.86e-05 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.241 | +| time/ | | +| fps | 1355 | +| iterations | 1775 | +| time_elapsed | 2682 | +| total_timesteps | 3635200 | +| train/ | | +| approx_kl | 0.03873088 | +| clip_fraction | 0.439 | +| clip_range | 0.105 | +| entropy_loss | -7.27 | +| explained_variance | -0.0857 | +| learning_rate | 0.000128 | +| loss | -0.0501 | +| n_updates | 7096 | +| policy_gradient_loss | -0.0287 | +| value_loss | 0.000121 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.239 | +| time/ | | +| fps | 1355 | +| iterations | 1776 | +| time_elapsed | 2684 | +| total_timesteps | 3637248 | +| train/ | | +| approx_kl | 0.035694696 | +| clip_fraction | 0.409 | +| clip_range | 0.105 | +| entropy_loss | -7.28 | +| explained_variance | -0.0216 | +| learning_rate | 0.000128 | +| loss | -0.0445 | +| n_updates | 7100 | +| policy_gradient_loss | -0.0315 | +| value_loss | 0.000234 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.239 | +| time/ | | +| fps | 1355 | +| iterations | 1777 | +| time_elapsed | 2685 | +| total_timesteps | 3639296 | +| train/ | | +| approx_kl | 0.0391135 | +| clip_fraction | 0.409 | +| clip_range | 0.105 | +| entropy_loss | -7.27 | +| explained_variance | -0.0559 | +| learning_rate | 0.000128 | +| loss | -0.0522 | +| n_updates | 7104 | +| policy_gradient_loss | -0.0311 | +| value_loss | 0.000119 | +--------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.242 | +| time/ | | +| fps | 1355 | +| iterations | 1778 | +| time_elapsed | 2686 | +| total_timesteps | 3641344 | +| train/ | | +| approx_kl | 0.04125903 | +| clip_fraction | 0.436 | +| clip_range | 0.105 | +| entropy_loss | -7.32 | +| explained_variance | -0.237 | +| learning_rate | 0.000128 | +| loss | -0.0538 | +| n_updates | 7108 | +| policy_gradient_loss | -0.0338 | +| value_loss | 0.000113 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.245 | +| time/ | | +| fps | 1355 | +| iterations | 1779 | +| time_elapsed | 2688 | +| total_timesteps | 3643392 | +| train/ | | +| approx_kl | 0.040421538 | +| clip_fraction | 0.413 | +| clip_range | 0.104 | +| entropy_loss | -7.38 | +| explained_variance | -0.143 | +| learning_rate | 0.000128 | +| loss | -0.0587 | +| n_updates | 7112 | +| policy_gradient_loss | -0.032 | +| value_loss | 0.000181 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.245 | +| time/ | | +| fps | 1355 | +| iterations | 1780 | +| time_elapsed | 2689 | +| total_timesteps | 3645440 | +| train/ | | +| approx_kl | 0.040489588 | +| clip_fraction | 0.413 | +| clip_range | 0.104 | +| entropy_loss | -7.4 | +| explained_variance | -0.199 | +| learning_rate | 0.000128 | +| loss | -0.0498 | +| n_updates | 7116 | +| policy_gradient_loss | -0.0335 | +| value_loss | 0.000139 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.254 | +| time/ | | +| fps | 1355 | +| iterations | 1781 | +| time_elapsed | 2691 | +| total_timesteps | 3647488 | +| train/ | | +| approx_kl | 0.032010183 | +| clip_fraction | 0.401 | +| clip_range | 0.104 | +| entropy_loss | -7.21 | +| explained_variance | -0.0611 | +| learning_rate | 0.000128 | +| loss | -0.0527 | +| n_updates | 7120 | +| policy_gradient_loss | -0.0318 | +| value_loss | 0.000131 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.251 | +| time/ | | +| fps | 1355 | +| iterations | 1782 | +| time_elapsed | 2692 | +| total_timesteps | 3649536 | +| train/ | | +| approx_kl | 0.032981314 | +| clip_fraction | 0.422 | +| clip_range | 0.104 | +| entropy_loss | -7.16 | +| explained_variance | -0.107 | +| learning_rate | 0.000128 | +| loss | -0.0512 | +| n_updates | 7124 | +| policy_gradient_loss | -0.031 | +| value_loss | 0.000217 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.249 | +| time/ | | +| fps | 1355 | +| iterations | 1783 | +| time_elapsed | 2693 | +| total_timesteps | 3651584 | +| train/ | | +| approx_kl | 0.03837525 | +| clip_fraction | 0.438 | +| clip_range | 0.104 | +| entropy_loss | -7.27 | +| explained_variance | -0.248 | +| learning_rate | 0.000128 | +| loss | -0.0457 | +| n_updates | 7128 | +| policy_gradient_loss | -0.0291 | +| value_loss | 0.000139 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.252 | +| time/ | | +| fps | 1355 | +| iterations | 1784 | +| time_elapsed | 2695 | +| total_timesteps | 3653632 | +| train/ | | +| approx_kl | 0.034201585 | +| clip_fraction | 0.417 | +| clip_range | 0.104 | +| entropy_loss | -7.31 | +| explained_variance | -0.102 | +| learning_rate | 0.000128 | +| loss | -0.0464 | +| n_updates | 7132 | +| policy_gradient_loss | -0.0314 | +| value_loss | 0.000164 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.252 | +| time/ | | +| fps | 1355 | +| iterations | 1785 | +| time_elapsed | 2696 | +| total_timesteps | 3655680 | +| train/ | | +| approx_kl | 0.034289606 | +| clip_fraction | 0.39 | +| clip_range | 0.104 | +| entropy_loss | -7.43 | +| explained_variance | -0.181 | +| learning_rate | 0.000128 | +| loss | -0.0528 | +| n_updates | 7136 | +| policy_gradient_loss | -0.031 | +| value_loss | 0.000183 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.255 | +| time/ | | +| fps | 1355 | +| iterations | 1786 | +| time_elapsed | 2698 | +| total_timesteps | 3657728 | +| train/ | | +| approx_kl | 0.04566299 | +| clip_fraction | 0.419 | +| clip_range | 0.104 | +| entropy_loss | -7.37 | +| explained_variance | -0.262 | +| learning_rate | 0.000128 | +| loss | -0.0529 | +| n_updates | 7140 | +| policy_gradient_loss | -0.0346 | +| value_loss | 0.000142 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.261 | +| time/ | | +| fps | 1355 | +| iterations | 1787 | +| time_elapsed | 2699 | +| total_timesteps | 3659776 | +| train/ | | +| approx_kl | 0.038014483 | +| clip_fraction | 0.402 | +| clip_range | 0.104 | +| entropy_loss | -7.19 | +| explained_variance | -0.175 | +| learning_rate | 0.000128 | +| loss | -0.0419 | +| n_updates | 7144 | +| policy_gradient_loss | -0.0291 | +| value_loss | 0.000196 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.263 | +| time/ | | +| fps | 1355 | +| iterations | 1788 | +| time_elapsed | 2701 | +| total_timesteps | 3661824 | +| train/ | | +| approx_kl | 0.03539273 | +| clip_fraction | 0.429 | +| clip_range | 0.104 | +| entropy_loss | -7.4 | +| explained_variance | -0.249 | +| learning_rate | 0.000128 | +| loss | -0.0406 | +| n_updates | 7148 | +| policy_gradient_loss | -0.0311 | +| value_loss | 0.000138 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.259 | +| time/ | | +| fps | 1355 | +| iterations | 1789 | +| time_elapsed | 2702 | +| total_timesteps | 3663872 | +| train/ | | +| approx_kl | 0.03383897 | +| clip_fraction | 0.392 | +| clip_range | 0.104 | +| entropy_loss | -7.27 | +| explained_variance | 0.0435 | +| learning_rate | 0.000127 | +| loss | -0.0483 | +| n_updates | 7152 | +| policy_gradient_loss | -0.0289 | +| value_loss | 0.000218 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.261 | +| time/ | | +| fps | 1355 | +| iterations | 1790 | +| time_elapsed | 2703 | +| total_timesteps | 3665920 | +| train/ | | +| approx_kl | 0.035636786 | +| clip_fraction | 0.414 | +| clip_range | 0.104 | +| entropy_loss | -7.38 | +| explained_variance | -0.365 | +| learning_rate | 0.000127 | +| loss | -0.0567 | +| n_updates | 7156 | +| policy_gradient_loss | -0.035 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.258 | +| time/ | | +| fps | 1355 | +| iterations | 1791 | +| time_elapsed | 2705 | +| total_timesteps | 3667968 | +| train/ | | +| approx_kl | 0.032485835 | +| clip_fraction | 0.386 | +| clip_range | 0.104 | +| entropy_loss | -7.41 | +| explained_variance | -0.146 | +| learning_rate | 0.000127 | +| loss | -0.0505 | +| n_updates | 7160 | +| policy_gradient_loss | -0.0285 | +| value_loss | 0.000182 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.249 | +| time/ | | +| fps | 1355 | +| iterations | 1792 | +| time_elapsed | 2706 | +| total_timesteps | 3670016 | +| train/ | | +| approx_kl | 0.04074853 | +| clip_fraction | 0.418 | +| clip_range | 0.104 | +| entropy_loss | -7.29 | +| explained_variance | -0.1 | +| learning_rate | 0.000127 | +| loss | -0.0487 | +| n_updates | 7164 | +| policy_gradient_loss | -0.0293 | +| value_loss | 0.000185 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.25 | +| time/ | | +| fps | 1355 | +| iterations | 1793 | +| time_elapsed | 2708 | +| total_timesteps | 3672064 | +| train/ | | +| approx_kl | 0.036600247 | +| clip_fraction | 0.403 | +| clip_range | 0.104 | +| entropy_loss | -7.35 | +| explained_variance | -0.177 | +| learning_rate | 0.000127 | +| loss | -0.0455 | +| n_updates | 7168 | +| policy_gradient_loss | -0.0307 | +| value_loss | 0.000216 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.25 | +| time/ | | +| fps | 1356 | +| iterations | 1794 | +| time_elapsed | 2709 | +| total_timesteps | 3674112 | +| train/ | | +| approx_kl | 0.038742647 | +| clip_fraction | 0.434 | +| clip_range | 0.104 | +| entropy_loss | -7.34 | +| explained_variance | -0.354 | +| learning_rate | 0.000127 | +| loss | -0.0555 | +| n_updates | 7172 | +| policy_gradient_loss | -0.0367 | +| value_loss | 0.000136 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.252 | +| time/ | | +| fps | 1356 | +| iterations | 1795 | +| time_elapsed | 2710 | +| total_timesteps | 3676160 | +| train/ | | +| approx_kl | 0.044321474 | +| clip_fraction | 0.433 | +| clip_range | 0.104 | +| entropy_loss | -7.4 | +| explained_variance | -0.0934 | +| learning_rate | 0.000127 | +| loss | -0.0476 | +| n_updates | 7176 | +| policy_gradient_loss | -0.0326 | +| value_loss | 0.000135 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.247 | +| time/ | | +| fps | 1356 | +| iterations | 1796 | +| time_elapsed | 2712 | +| total_timesteps | 3678208 | +| train/ | | +| approx_kl | 0.04002183 | +| clip_fraction | 0.417 | +| clip_range | 0.104 | +| entropy_loss | -7.35 | +| explained_variance | -0.159 | +| learning_rate | 0.000127 | +| loss | -0.0529 | +| n_updates | 7180 | +| policy_gradient_loss | -0.0335 | +| value_loss | 0.000104 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.246 | +| time/ | | +| fps | 1356 | +| iterations | 1797 | +| time_elapsed | 2713 | +| total_timesteps | 3680256 | +| train/ | | +| approx_kl | 0.03741835 | +| clip_fraction | 0.42 | +| clip_range | 0.104 | +| entropy_loss | -7.41 | +| explained_variance | -0.206 | +| learning_rate | 0.000127 | +| loss | -0.0516 | +| n_updates | 7184 | +| policy_gradient_loss | -0.0319 | +| value_loss | 9.72e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.248 | +| time/ | | +| fps | 1356 | +| iterations | 1798 | +| time_elapsed | 2715 | +| total_timesteps | 3682304 | +| train/ | | +| approx_kl | 0.037708975 | +| clip_fraction | 0.424 | +| clip_range | 0.104 | +| entropy_loss | -7.18 | +| explained_variance | -0.107 | +| learning_rate | 0.000127 | +| loss | -0.045 | +| n_updates | 7188 | +| policy_gradient_loss | -0.0304 | +| value_loss | 0.000157 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.251 | +| time/ | | +| fps | 1356 | +| iterations | 1799 | +| time_elapsed | 2716 | +| total_timesteps | 3684352 | +| train/ | | +| approx_kl | 0.044622574 | +| clip_fraction | 0.432 | +| clip_range | 0.104 | +| entropy_loss | -7.29 | +| explained_variance | -0.133 | +| learning_rate | 0.000127 | +| loss | -0.0521 | +| n_updates | 7192 | +| policy_gradient_loss | -0.0338 | +| value_loss | 0.000188 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.251 | +| time/ | | +| fps | 1356 | +| iterations | 1800 | +| time_elapsed | 2717 | +| total_timesteps | 3686400 | +| train/ | | +| approx_kl | 0.04013201 | +| clip_fraction | 0.436 | +| clip_range | 0.104 | +| entropy_loss | -7.37 | +| explained_variance | -0.083 | +| learning_rate | 0.000127 | +| loss | -0.0481 | +| n_updates | 7196 | +| policy_gradient_loss | -0.0322 | +| value_loss | 0.000185 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.251 | +| time/ | | +| fps | 1356 | +| iterations | 1801 | +| time_elapsed | 2719 | +| total_timesteps | 3688448 | +| train/ | | +| approx_kl | 0.03938451 | +| clip_fraction | 0.414 | +| clip_range | 0.104 | +| entropy_loss | -7.35 | +| explained_variance | -0.0479 | +| learning_rate | 0.000127 | +| loss | -0.055 | +| n_updates | 7200 | +| policy_gradient_loss | -0.0339 | +| value_loss | 0.000135 | +---------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.255 | +| time/ | | +| fps | 1356 | +| iterations | 1802 | +| time_elapsed | 2720 | +| total_timesteps | 3690496 | +| train/ | | +| approx_kl | 0.0458569 | +| clip_fraction | 0.417 | +| clip_range | 0.104 | +| entropy_loss | -7.35 | +| explained_variance | -0.287 | +| learning_rate | 0.000127 | +| loss | -0.0569 | +| n_updates | 7204 | +| policy_gradient_loss | -0.0351 | +| value_loss | 0.000106 | +--------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.256 | +| time/ | | +| fps | 1356 | +| iterations | 1803 | +| time_elapsed | 2722 | +| total_timesteps | 3692544 | +| train/ | | +| approx_kl | 0.03551977 | +| clip_fraction | 0.388 | +| clip_range | 0.104 | +| entropy_loss | -7.31 | +| explained_variance | -0.0593 | +| learning_rate | 0.000127 | +| loss | -0.0478 | +| n_updates | 7208 | +| policy_gradient_loss | -0.0294 | +| value_loss | 0.00023 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.257 | +| time/ | | +| fps | 1356 | +| iterations | 1804 | +| time_elapsed | 2723 | +| total_timesteps | 3694592 | +| train/ | | +| approx_kl | 0.02853368 | +| clip_fraction | 0.394 | +| clip_range | 0.104 | +| entropy_loss | -7.36 | +| explained_variance | -0.204 | +| learning_rate | 0.000127 | +| loss | -0.0487 | +| n_updates | 7212 | +| policy_gradient_loss | -0.0297 | +| value_loss | 0.000206 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.266 | +| time/ | | +| fps | 1356 | +| iterations | 1805 | +| time_elapsed | 2725 | +| total_timesteps | 3696640 | +| train/ | | +| approx_kl | 0.039065517 | +| clip_fraction | 0.412 | +| clip_range | 0.104 | +| entropy_loss | -7.37 | +| explained_variance | -0.129 | +| learning_rate | 0.000127 | +| loss | -0.0394 | +| n_updates | 7216 | +| policy_gradient_loss | -0.0282 | +| value_loss | 0.000207 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.274 | +| time/ | | +| fps | 1356 | +| iterations | 1806 | +| time_elapsed | 2726 | +| total_timesteps | 3698688 | +| train/ | | +| approx_kl | 0.03859865 | +| clip_fraction | 0.4 | +| clip_range | 0.104 | +| entropy_loss | -7.2 | +| explained_variance | -0.199 | +| learning_rate | 0.000127 | +| loss | -0.0568 | +| n_updates | 7220 | +| policy_gradient_loss | -0.0303 | +| value_loss | 0.00019 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.28 | +| time/ | | +| fps | 1356 | +| iterations | 1807 | +| time_elapsed | 2728 | +| total_timesteps | 3700736 | +| train/ | | +| approx_kl | 0.042432025 | +| clip_fraction | 0.431 | +| clip_range | 0.104 | +| entropy_loss | -7.33 | +| explained_variance | -0.0738 | +| learning_rate | 0.000127 | +| loss | -0.05 | +| n_updates | 7224 | +| policy_gradient_loss | -0.0344 | +| value_loss | 0.000236 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.286 | +| time/ | | +| fps | 1356 | +| iterations | 1808 | +| time_elapsed | 2729 | +| total_timesteps | 3702784 | +| train/ | | +| approx_kl | 0.040373154 | +| clip_fraction | 0.394 | +| clip_range | 0.104 | +| entropy_loss | -7.3 | +| explained_variance | -0.0951 | +| learning_rate | 0.000127 | +| loss | -0.0362 | +| n_updates | 7228 | +| policy_gradient_loss | -0.0287 | +| value_loss | 0.000181 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.284 | +| time/ | | +| fps | 1356 | +| iterations | 1809 | +| time_elapsed | 2730 | +| total_timesteps | 3704832 | +| train/ | | +| approx_kl | 0.037132394 | +| clip_fraction | 0.39 | +| clip_range | 0.104 | +| entropy_loss | -7.14 | +| explained_variance | -0.0796 | +| learning_rate | 0.000127 | +| loss | -0.0507 | +| n_updates | 7232 | +| policy_gradient_loss | -0.0305 | +| value_loss | 0.000305 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.28 | +| time/ | | +| fps | 1356 | +| iterations | 1810 | +| time_elapsed | 2732 | +| total_timesteps | 3706880 | +| train/ | | +| approx_kl | 0.037889495 | +| clip_fraction | 0.417 | +| clip_range | 0.104 | +| entropy_loss | -7.39 | +| explained_variance | -0.144 | +| learning_rate | 0.000127 | +| loss | -0.0611 | +| n_updates | 7236 | +| policy_gradient_loss | -0.0345 | +| value_loss | 0.000157 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.28 | +| time/ | | +| fps | 1356 | +| iterations | 1811 | +| time_elapsed | 2733 | +| total_timesteps | 3708928 | +| train/ | | +| approx_kl | 0.04075236 | +| clip_fraction | 0.41 | +| clip_range | 0.104 | +| entropy_loss | -7.23 | +| explained_variance | -0.163 | +| learning_rate | 0.000127 | +| loss | -0.0566 | +| n_updates | 7240 | +| policy_gradient_loss | -0.0342 | +| value_loss | 0.000195 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.28 | +| time/ | | +| fps | 1356 | +| iterations | 1812 | +| time_elapsed | 2735 | +| total_timesteps | 3710976 | +| train/ | | +| approx_kl | 0.04171951 | +| clip_fraction | 0.442 | +| clip_range | 0.104 | +| entropy_loss | -7.35 | +| explained_variance | -0.183 | +| learning_rate | 0.000127 | +| loss | -0.0575 | +| n_updates | 7244 | +| policy_gradient_loss | -0.0327 | +| value_loss | 0.000173 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.28 | +| time/ | | +| fps | 1356 | +| iterations | 1813 | +| time_elapsed | 2736 | +| total_timesteps | 3713024 | +| train/ | | +| approx_kl | 0.035375588 | +| clip_fraction | 0.435 | +| clip_range | 0.104 | +| entropy_loss | -7.36 | +| explained_variance | -0.275 | +| learning_rate | 0.000127 | +| loss | -0.0518 | +| n_updates | 7248 | +| policy_gradient_loss | -0.0343 | +| value_loss | 0.000115 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.28 | +| time/ | | +| fps | 1356 | +| iterations | 1814 | +| time_elapsed | 2738 | +| total_timesteps | 3715072 | +| train/ | | +| approx_kl | 0.04357806 | +| clip_fraction | 0.412 | +| clip_range | 0.104 | +| entropy_loss | -7.3 | +| explained_variance | -0.147 | +| learning_rate | 0.000126 | +| loss | -0.0527 | +| n_updates | 7252 | +| policy_gradient_loss | -0.0334 | +| value_loss | 0.000136 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.28 | +| time/ | | +| fps | 1356 | +| iterations | 1815 | +| time_elapsed | 2739 | +| total_timesteps | 3717120 | +| train/ | | +| approx_kl | 0.044243805 | +| clip_fraction | 0.448 | +| clip_range | 0.104 | +| entropy_loss | -7.3 | +| explained_variance | -0.0907 | +| learning_rate | 0.000126 | +| loss | -0.0479 | +| n_updates | 7256 | +| policy_gradient_loss | -0.033 | +| value_loss | 0.00013 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.276 | +| time/ | | +| fps | 1356 | +| iterations | 1816 | +| time_elapsed | 2740 | +| total_timesteps | 3719168 | +| train/ | | +| approx_kl | 0.038626045 | +| clip_fraction | 0.389 | +| clip_range | 0.104 | +| entropy_loss | -7.32 | +| explained_variance | -0.147 | +| learning_rate | 0.000126 | +| loss | -0.0488 | +| n_updates | 7260 | +| policy_gradient_loss | -0.0258 | +| value_loss | 0.000211 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.271 | +| time/ | | +| fps | 1356 | +| iterations | 1817 | +| time_elapsed | 2742 | +| total_timesteps | 3721216 | +| train/ | | +| approx_kl | 0.039377104 | +| clip_fraction | 0.43 | +| clip_range | 0.104 | +| entropy_loss | -7.3 | +| explained_variance | -0.146 | +| learning_rate | 0.000126 | +| loss | -0.0613 | +| n_updates | 7264 | +| policy_gradient_loss | -0.0355 | +| value_loss | 7.98e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.271 | +| time/ | | +| fps | 1356 | +| iterations | 1818 | +| time_elapsed | 2743 | +| total_timesteps | 3723264 | +| train/ | | +| approx_kl | 0.043339893 | +| clip_fraction | 0.413 | +| clip_range | 0.103 | +| entropy_loss | -7.34 | +| explained_variance | -0.0962 | +| learning_rate | 0.000126 | +| loss | -0.0503 | +| n_updates | 7268 | +| policy_gradient_loss | -0.0312 | +| value_loss | 0.000106 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.274 | +| time/ | | +| fps | 1357 | +| iterations | 1819 | +| time_elapsed | 2745 | +| total_timesteps | 3725312 | +| train/ | | +| approx_kl | 0.04104761 | +| clip_fraction | 0.413 | +| clip_range | 0.103 | +| entropy_loss | -7.25 | +| explained_variance | -0.115 | +| learning_rate | 0.000126 | +| loss | -0.0513 | +| n_updates | 7272 | +| policy_gradient_loss | -0.0341 | +| value_loss | 0.000169 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.274 | +| time/ | | +| fps | 1357 | +| iterations | 1820 | +| time_elapsed | 2746 | +| total_timesteps | 3727360 | +| train/ | | +| approx_kl | 0.03973394 | +| clip_fraction | 0.422 | +| clip_range | 0.103 | +| entropy_loss | -7.32 | +| explained_variance | -0.222 | +| learning_rate | 0.000126 | +| loss | -0.0485 | +| n_updates | 7276 | +| policy_gradient_loss | -0.0313 | +| value_loss | 0.000151 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.267 | +| time/ | | +| fps | 1357 | +| iterations | 1821 | +| time_elapsed | 2748 | +| total_timesteps | 3729408 | +| train/ | | +| approx_kl | 0.041342147 | +| clip_fraction | 0.402 | +| clip_range | 0.103 | +| entropy_loss | -7.4 | +| explained_variance | -0.136 | +| learning_rate | 0.000126 | +| loss | -0.0465 | +| n_updates | 7280 | +| policy_gradient_loss | -0.0301 | +| value_loss | 0.000182 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.273 | +| time/ | | +| fps | 1357 | +| iterations | 1822 | +| time_elapsed | 2749 | +| total_timesteps | 3731456 | +| train/ | | +| approx_kl | 0.033610642 | +| clip_fraction | 0.412 | +| clip_range | 0.103 | +| entropy_loss | -7.45 | +| explained_variance | -0.157 | +| learning_rate | 0.000126 | +| loss | -0.0489 | +| n_updates | 7284 | +| policy_gradient_loss | -0.0326 | +| value_loss | 9.69e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.278 | +| time/ | | +| fps | 1357 | +| iterations | 1823 | +| time_elapsed | 2750 | +| total_timesteps | 3733504 | +| train/ | | +| approx_kl | 0.040721327 | +| clip_fraction | 0.405 | +| clip_range | 0.103 | +| entropy_loss | -7.39 | +| explained_variance | -0.0365 | +| learning_rate | 0.000126 | +| loss | -0.0476 | +| n_updates | 7288 | +| policy_gradient_loss | -0.0311 | +| value_loss | 0.00018 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.278 | +| time/ | | +| fps | 1357 | +| iterations | 1824 | +| time_elapsed | 2752 | +| total_timesteps | 3735552 | +| train/ | | +| approx_kl | 0.04472565 | +| clip_fraction | 0.407 | +| clip_range | 0.103 | +| entropy_loss | -7.29 | +| explained_variance | -0.119 | +| learning_rate | 0.000126 | +| loss | -0.0444 | +| n_updates | 7292 | +| policy_gradient_loss | -0.0314 | +| value_loss | 0.000146 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.283 | +| time/ | | +| fps | 1357 | +| iterations | 1825 | +| time_elapsed | 2753 | +| total_timesteps | 3737600 | +| train/ | | +| approx_kl | 0.03919217 | +| clip_fraction | 0.417 | +| clip_range | 0.103 | +| entropy_loss | -7.4 | +| explained_variance | -0.195 | +| learning_rate | 0.000126 | +| loss | -0.0645 | +| n_updates | 7296 | +| policy_gradient_loss | -0.032 | +| value_loss | 9.84e-05 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.281 | +| time/ | | +| fps | 1357 | +| iterations | 1826 | +| time_elapsed | 2755 | +| total_timesteps | 3739648 | +| train/ | | +| approx_kl | 0.03595799 | +| clip_fraction | 0.427 | +| clip_range | 0.103 | +| entropy_loss | -7.29 | +| explained_variance | -0.0626 | +| learning_rate | 0.000126 | +| loss | -0.0416 | +| n_updates | 7300 | +| policy_gradient_loss | -0.0303 | +| value_loss | 0.000192 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.281 | +| time/ | | +| fps | 1357 | +| iterations | 1827 | +| time_elapsed | 2756 | +| total_timesteps | 3741696 | +| train/ | | +| approx_kl | 0.035845146 | +| clip_fraction | 0.397 | +| clip_range | 0.103 | +| entropy_loss | -7.36 | +| explained_variance | -0.229 | +| learning_rate | 0.000126 | +| loss | -0.047 | +| n_updates | 7304 | +| policy_gradient_loss | -0.0297 | +| value_loss | 0.000246 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 1357 | +| iterations | 1828 | +| time_elapsed | 2757 | +| total_timesteps | 3743744 | +| train/ | | +| approx_kl | 0.047630217 | +| clip_fraction | 0.431 | +| clip_range | 0.103 | +| entropy_loss | -7.38 | +| explained_variance | -0.224 | +| learning_rate | 0.000126 | +| loss | -0.0476 | +| n_updates | 7308 | +| policy_gradient_loss | -0.0323 | +| value_loss | 0.000276 | +----------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 1357 | +| iterations | 1829 | +| time_elapsed | 2759 | +| total_timesteps | 3745792 | +| train/ | | +| approx_kl | 0.034888 | +| clip_fraction | 0.435 | +| clip_range | 0.103 | +| entropy_loss | -7.27 | +| explained_variance | -0.0897 | +| learning_rate | 0.000126 | +| loss | -0.0558 | +| n_updates | 7312 | +| policy_gradient_loss | -0.0337 | +| value_loss | 0.000151 | +-------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.268 | +| time/ | | +| fps | 1357 | +| iterations | 1830 | +| time_elapsed | 2760 | +| total_timesteps | 3747840 | +| train/ | | +| approx_kl | 0.04263954 | +| clip_fraction | 0.443 | +| clip_range | 0.103 | +| entropy_loss | -7.14 | +| explained_variance | -0.133 | +| learning_rate | 0.000126 | +| loss | -0.0546 | +| n_updates | 7316 | +| policy_gradient_loss | -0.0313 | +| value_loss | 0.000184 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.268 | +| time/ | | +| fps | 1357 | +| iterations | 1831 | +| time_elapsed | 2762 | +| total_timesteps | 3749888 | +| train/ | | +| approx_kl | 0.035163406 | +| clip_fraction | 0.41 | +| clip_range | 0.103 | +| entropy_loss | -7.31 | +| explained_variance | -0.0259 | +| learning_rate | 0.000126 | +| loss | -0.0487 | +| n_updates | 7320 | +| policy_gradient_loss | -0.0308 | +| value_loss | 0.00026 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.272 | +| time/ | | +| fps | 1357 | +| iterations | 1832 | +| time_elapsed | 2763 | +| total_timesteps | 3751936 | +| train/ | | +| approx_kl | 0.037871115 | +| clip_fraction | 0.428 | +| clip_range | 0.103 | +| entropy_loss | -7.37 | +| explained_variance | -0.369 | +| learning_rate | 0.000126 | +| loss | -0.0549 | +| n_updates | 7324 | +| policy_gradient_loss | -0.0332 | +| value_loss | 0.000201 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 1357 | +| iterations | 1833 | +| time_elapsed | 2764 | +| total_timesteps | 3753984 | +| train/ | | +| approx_kl | 0.0394814 | +| clip_fraction | 0.414 | +| clip_range | 0.103 | +| entropy_loss | -7.3 | +| explained_variance | -0.317 | +| learning_rate | 0.000126 | +| loss | -0.0496 | +| n_updates | 7328 | +| policy_gradient_loss | -0.0315 | +| value_loss | 0.000182 | +--------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.274 | +| time/ | | +| fps | 1357 | +| iterations | 1834 | +| time_elapsed | 2766 | +| total_timesteps | 3756032 | +| train/ | | +| approx_kl | 0.03935804 | +| clip_fraction | 0.406 | +| clip_range | 0.103 | +| entropy_loss | -7.14 | +| explained_variance | -0.0716 | +| learning_rate | 0.000126 | +| loss | -0.0371 | +| n_updates | 7332 | +| policy_gradient_loss | -0.0276 | +| value_loss | 0.000192 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.27 | +| time/ | | +| fps | 1357 | +| iterations | 1835 | +| time_elapsed | 2767 | +| total_timesteps | 3758080 | +| train/ | | +| approx_kl | 0.04280734 | +| clip_fraction | 0.445 | +| clip_range | 0.103 | +| entropy_loss | -7.26 | +| explained_variance | -0.059 | +| learning_rate | 0.000126 | +| loss | -0.0523 | +| n_updates | 7336 | +| policy_gradient_loss | -0.0352 | +| value_loss | 0.00016 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.271 | +| time/ | | +| fps | 1357 | +| iterations | 1836 | +| time_elapsed | 2769 | +| total_timesteps | 3760128 | +| train/ | | +| approx_kl | 0.038852163 | +| clip_fraction | 0.423 | +| clip_range | 0.103 | +| entropy_loss | -7.28 | +| explained_variance | -0.213 | +| learning_rate | 0.000126 | +| loss | -0.0495 | +| n_updates | 7340 | +| policy_gradient_loss | -0.0315 | +| value_loss | 0.000211 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.267 | +| time/ | | +| fps | 1357 | +| iterations | 1837 | +| time_elapsed | 2770 | +| total_timesteps | 3762176 | +| train/ | | +| approx_kl | 0.040274132 | +| clip_fraction | 0.415 | +| clip_range | 0.103 | +| entropy_loss | -7.27 | +| explained_variance | -0.163 | +| learning_rate | 0.000126 | +| loss | -0.0507 | +| n_updates | 7344 | +| policy_gradient_loss | -0.0328 | +| value_loss | 0.000153 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.268 | +| time/ | | +| fps | 1357 | +| iterations | 1838 | +| time_elapsed | 2772 | +| total_timesteps | 3764224 | +| train/ | | +| approx_kl | 0.03815274 | +| clip_fraction | 0.418 | +| clip_range | 0.103 | +| entropy_loss | -7.25 | +| explained_variance | -0.291 | +| learning_rate | 0.000126 | +| loss | -0.0564 | +| n_updates | 7348 | +| policy_gradient_loss | -0.0328 | +| value_loss | 0.000132 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.268 | +| time/ | | +| fps | 1357 | +| iterations | 1839 | +| time_elapsed | 2773 | +| total_timesteps | 3766272 | +| train/ | | +| approx_kl | 0.036696836 | +| clip_fraction | 0.38 | +| clip_range | 0.103 | +| entropy_loss | -7.18 | +| explained_variance | -0.101 | +| learning_rate | 0.000125 | +| loss | -0.0443 | +| n_updates | 7352 | +| policy_gradient_loss | -0.0287 | +| value_loss | 0.000139 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.265 | +| time/ | | +| fps | 1357 | +| iterations | 1840 | +| time_elapsed | 2775 | +| total_timesteps | 3768320 | +| train/ | | +| approx_kl | 0.033758316 | +| clip_fraction | 0.402 | +| clip_range | 0.103 | +| entropy_loss | -7.31 | +| explained_variance | -0.146 | +| learning_rate | 0.000125 | +| loss | -0.0468 | +| n_updates | 7356 | +| policy_gradient_loss | -0.0279 | +| value_loss | 0.000147 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.259 | +| time/ | | +| fps | 1357 | +| iterations | 1841 | +| time_elapsed | 2776 | +| total_timesteps | 3770368 | +| train/ | | +| approx_kl | 0.037626587 | +| clip_fraction | 0.459 | +| clip_range | 0.103 | +| entropy_loss | -7.28 | +| explained_variance | -0.598 | +| learning_rate | 0.000125 | +| loss | -0.0618 | +| n_updates | 7360 | +| policy_gradient_loss | -0.0395 | +| value_loss | 5.35e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.255 | +| time/ | | +| fps | 1357 | +| iterations | 1842 | +| time_elapsed | 2777 | +| total_timesteps | 3772416 | +| train/ | | +| approx_kl | 0.03270044 | +| clip_fraction | 0.414 | +| clip_range | 0.103 | +| entropy_loss | -7.2 | +| explained_variance | -0.124 | +| learning_rate | 0.000125 | +| loss | -0.0439 | +| n_updates | 7364 | +| policy_gradient_loss | -0.0287 | +| value_loss | 0.000127 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.251 | +| time/ | | +| fps | 1358 | +| iterations | 1843 | +| time_elapsed | 2779 | +| total_timesteps | 3774464 | +| train/ | | +| approx_kl | 0.036547873 | +| clip_fraction | 0.429 | +| clip_range | 0.103 | +| entropy_loss | -7.3 | +| explained_variance | -0.166 | +| learning_rate | 0.000125 | +| loss | -0.0496 | +| n_updates | 7368 | +| policy_gradient_loss | -0.03 | +| value_loss | 0.000207 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.251 | +| time/ | | +| fps | 1358 | +| iterations | 1844 | +| time_elapsed | 2780 | +| total_timesteps | 3776512 | +| train/ | | +| approx_kl | 0.03604272 | +| clip_fraction | 0.401 | +| clip_range | 0.103 | +| entropy_loss | -7.2 | +| explained_variance | -0.0231 | +| learning_rate | 0.000125 | +| loss | -0.0505 | +| n_updates | 7372 | +| policy_gradient_loss | -0.0301 | +| value_loss | 0.000192 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.252 | +| time/ | | +| fps | 1358 | +| iterations | 1845 | +| time_elapsed | 2782 | +| total_timesteps | 3778560 | +| train/ | | +| approx_kl | 0.037917476 | +| clip_fraction | 0.418 | +| clip_range | 0.103 | +| entropy_loss | -7.33 | +| explained_variance | -0.0252 | +| learning_rate | 0.000125 | +| loss | -0.0548 | +| n_updates | 7376 | +| policy_gradient_loss | -0.0346 | +| value_loss | 0.000122 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.258 | +| time/ | | +| fps | 1358 | +| iterations | 1846 | +| time_elapsed | 2783 | +| total_timesteps | 3780608 | +| train/ | | +| approx_kl | 0.03828706 | +| clip_fraction | 0.433 | +| clip_range | 0.103 | +| entropy_loss | -7.36 | +| explained_variance | -0.094 | +| learning_rate | 0.000125 | +| loss | -0.0515 | +| n_updates | 7380 | +| policy_gradient_loss | -0.0334 | +| value_loss | 0.000119 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.258 | +| time/ | | +| fps | 1358 | +| iterations | 1847 | +| time_elapsed | 2785 | +| total_timesteps | 3782656 | +| train/ | | +| approx_kl | 0.034485146 | +| clip_fraction | 0.425 | +| clip_range | 0.103 | +| entropy_loss | -7.33 | +| explained_variance | -0.00189 | +| learning_rate | 0.000125 | +| loss | -0.0493 | +| n_updates | 7384 | +| policy_gradient_loss | -0.0281 | +| value_loss | 0.000227 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.258 | +| time/ | | +| fps | 1358 | +| iterations | 1848 | +| time_elapsed | 2786 | +| total_timesteps | 3784704 | +| train/ | | +| approx_kl | 0.03667464 | +| clip_fraction | 0.42 | +| clip_range | 0.103 | +| entropy_loss | -7.37 | +| explained_variance | -0.178 | +| learning_rate | 0.000125 | +| loss | -0.0483 | +| n_updates | 7388 | +| policy_gradient_loss | -0.0338 | +| value_loss | 0.000207 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.253 | +| time/ | | +| fps | 1358 | +| iterations | 1849 | +| time_elapsed | 2787 | +| total_timesteps | 3786752 | +| train/ | | +| approx_kl | 0.036702327 | +| clip_fraction | 0.412 | +| clip_range | 0.103 | +| entropy_loss | -7.41 | +| explained_variance | -0.0732 | +| learning_rate | 0.000125 | +| loss | -0.0547 | +| n_updates | 7392 | +| policy_gradient_loss | -0.0304 | +| value_loss | 0.000177 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.253 | +| time/ | | +| fps | 1358 | +| iterations | 1850 | +| time_elapsed | 2789 | +| total_timesteps | 3788800 | +| train/ | | +| approx_kl | 0.03254843 | +| clip_fraction | 0.417 | +| clip_range | 0.103 | +| entropy_loss | -7.34 | +| explained_variance | -0.453 | +| learning_rate | 0.000125 | +| loss | -0.0573 | +| n_updates | 7396 | +| policy_gradient_loss | -0.0348 | +| value_loss | 0.000131 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.257 | +| time/ | | +| fps | 1358 | +| iterations | 1851 | +| time_elapsed | 2790 | +| total_timesteps | 3790848 | +| train/ | | +| approx_kl | 0.03766053 | +| clip_fraction | 0.422 | +| clip_range | 0.103 | +| entropy_loss | -7.4 | +| explained_variance | -0.131 | +| learning_rate | 0.000125 | +| loss | -0.0573 | +| n_updates | 7400 | +| policy_gradient_loss | -0.0326 | +| value_loss | 0.000109 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.255 | +| time/ | | +| fps | 1358 | +| iterations | 1852 | +| time_elapsed | 2792 | +| total_timesteps | 3792896 | +| train/ | | +| approx_kl | 0.034197796 | +| clip_fraction | 0.406 | +| clip_range | 0.103 | +| entropy_loss | -7.25 | +| explained_variance | -0.021 | +| learning_rate | 0.000125 | +| loss | -0.0444 | +| n_updates | 7404 | +| policy_gradient_loss | -0.0274 | +| value_loss | 0.000353 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.257 | +| time/ | | +| fps | 1358 | +| iterations | 1853 | +| time_elapsed | 2793 | +| total_timesteps | 3794944 | +| train/ | | +| approx_kl | 0.0346435 | +| clip_fraction | 0.41 | +| clip_range | 0.103 | +| entropy_loss | -7.4 | +| explained_variance | 0.05 | +| learning_rate | 0.000125 | +| loss | -0.062 | +| n_updates | 7408 | +| policy_gradient_loss | -0.0353 | +| value_loss | 0.000191 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.257 | +| time/ | | +| fps | 1358 | +| iterations | 1854 | +| time_elapsed | 2795 | +| total_timesteps | 3796992 | +| train/ | | +| approx_kl | 0.034336396 | +| clip_fraction | 0.412 | +| clip_range | 0.103 | +| entropy_loss | -7.39 | +| explained_variance | -0.159 | +| learning_rate | 0.000125 | +| loss | -0.0536 | +| n_updates | 7412 | +| policy_gradient_loss | -0.0333 | +| value_loss | 0.000154 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.255 | +| time/ | | +| fps | 1358 | +| iterations | 1855 | +| time_elapsed | 2796 | +| total_timesteps | 3799040 | +| train/ | | +| approx_kl | 0.03523204 | +| clip_fraction | 0.411 | +| clip_range | 0.103 | +| entropy_loss | -7.47 | +| explained_variance | -0.035 | +| learning_rate | 0.000125 | +| loss | -0.0497 | +| n_updates | 7416 | +| policy_gradient_loss | -0.0316 | +| value_loss | 0.000183 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.277 | +| time/ | | +| fps | 1358 | +| iterations | 1856 | +| time_elapsed | 2797 | +| total_timesteps | 3801088 | +| train/ | | +| approx_kl | 0.035390303 | +| clip_fraction | 0.418 | +| clip_range | 0.103 | +| entropy_loss | -7.44 | +| explained_variance | -0.0835 | +| learning_rate | 0.000125 | +| loss | -0.0508 | +| n_updates | 7420 | +| policy_gradient_loss | -0.0309 | +| value_loss | 0.000234 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 1358 | +| iterations | 1857 | +| time_elapsed | 2799 | +| total_timesteps | 3803136 | +| train/ | | +| approx_kl | 0.028732488 | +| clip_fraction | 0.389 | +| clip_range | 0.102 | +| entropy_loss | -7.36 | +| explained_variance | 0.0636 | +| learning_rate | 0.000125 | +| loss | -0.0389 | +| n_updates | 7424 | +| policy_gradient_loss | -0.0272 | +| value_loss | 0.000483 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.283 | +| time/ | | +| fps | 1358 | +| iterations | 1858 | +| time_elapsed | 2800 | +| total_timesteps | 3805184 | +| train/ | | +| approx_kl | 0.032357927 | +| clip_fraction | 0.436 | +| clip_range | 0.102 | +| entropy_loss | -7.34 | +| explained_variance | -0.243 | +| learning_rate | 0.000125 | +| loss | -0.0562 | +| n_updates | 7428 | +| policy_gradient_loss | -0.0353 | +| value_loss | 0.000152 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.283 | +| time/ | | +| fps | 1358 | +| iterations | 1859 | +| time_elapsed | 2802 | +| total_timesteps | 3807232 | +| train/ | | +| approx_kl | 0.0386563 | +| clip_fraction | 0.421 | +| clip_range | 0.102 | +| entropy_loss | -7.36 | +| explained_variance | 0.0955 | +| learning_rate | 0.000125 | +| loss | -0.0494 | +| n_updates | 7432 | +| policy_gradient_loss | -0.0318 | +| value_loss | 0.00025 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.283 | +| time/ | | +| fps | 1358 | +| iterations | 1860 | +| time_elapsed | 2803 | +| total_timesteps | 3809280 | +| train/ | | +| approx_kl | 0.033757567 | +| clip_fraction | 0.422 | +| clip_range | 0.102 | +| entropy_loss | -7.29 | +| explained_variance | -0.11 | +| learning_rate | 0.000125 | +| loss | -0.0476 | +| n_updates | 7436 | +| policy_gradient_loss | -0.0338 | +| value_loss | 0.000199 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.283 | +| time/ | | +| fps | 1358 | +| iterations | 1861 | +| time_elapsed | 2805 | +| total_timesteps | 3811328 | +| train/ | | +| approx_kl | 0.03442217 | +| clip_fraction | 0.433 | +| clip_range | 0.102 | +| entropy_loss | -7.36 | +| explained_variance | -0.199 | +| learning_rate | 0.000125 | +| loss | -0.05 | +| n_updates | 7440 | +| policy_gradient_loss | -0.0359 | +| value_loss | 0.000161 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.283 | +| time/ | | +| fps | 1358 | +| iterations | 1862 | +| time_elapsed | 2806 | +| total_timesteps | 3813376 | +| train/ | | +| approx_kl | 0.029020708 | +| clip_fraction | 0.409 | +| clip_range | 0.102 | +| entropy_loss | -7.44 | +| explained_variance | -0.0635 | +| learning_rate | 0.000125 | +| loss | -0.046 | +| n_updates | 7444 | +| policy_gradient_loss | -0.0286 | +| value_loss | 0.000212 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.287 | +| time/ | | +| fps | 1358 | +| iterations | 1863 | +| time_elapsed | 2808 | +| total_timesteps | 3815424 | +| train/ | | +| approx_kl | 0.02593214 | +| clip_fraction | 0.375 | +| clip_range | 0.102 | +| entropy_loss | -7.43 | +| explained_variance | -0.13 | +| learning_rate | 0.000124 | +| loss | -0.0493 | +| n_updates | 7448 | +| policy_gradient_loss | -0.0261 | +| value_loss | 0.000263 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.291 | +| time/ | | +| fps | 1358 | +| iterations | 1864 | +| time_elapsed | 2809 | +| total_timesteps | 3817472 | +| train/ | | +| approx_kl | 0.035024863 | +| clip_fraction | 0.41 | +| clip_range | 0.102 | +| entropy_loss | -7.42 | +| explained_variance | -0.112 | +| learning_rate | 0.000124 | +| loss | -0.0525 | +| n_updates | 7452 | +| policy_gradient_loss | -0.0321 | +| value_loss | 0.000187 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.29 | +| time/ | | +| fps | 1358 | +| iterations | 1865 | +| time_elapsed | 2811 | +| total_timesteps | 3819520 | +| train/ | | +| approx_kl | 0.039702352 | +| clip_fraction | 0.423 | +| clip_range | 0.102 | +| entropy_loss | -7.24 | +| explained_variance | -0.0625 | +| learning_rate | 0.000124 | +| loss | -0.0481 | +| n_updates | 7456 | +| policy_gradient_loss | -0.0318 | +| value_loss | 0.000155 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.285 | +| time/ | | +| fps | 1358 | +| iterations | 1866 | +| time_elapsed | 2812 | +| total_timesteps | 3821568 | +| train/ | | +| approx_kl | 0.033907343 | +| clip_fraction | 0.427 | +| clip_range | 0.102 | +| entropy_loss | -7.39 | +| explained_variance | -0.17 | +| learning_rate | 0.000124 | +| loss | -0.0549 | +| n_updates | 7460 | +| policy_gradient_loss | -0.0293 | +| value_loss | 0.000188 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.287 | +| time/ | | +| fps | 1358 | +| iterations | 1867 | +| time_elapsed | 2813 | +| total_timesteps | 3823616 | +| train/ | | +| approx_kl | 0.04001091 | +| clip_fraction | 0.438 | +| clip_range | 0.102 | +| entropy_loss | -7.35 | +| explained_variance | -0.697 | +| learning_rate | 0.000124 | +| loss | -0.0657 | +| n_updates | 7464 | +| policy_gradient_loss | -0.0389 | +| value_loss | 6.37e-05 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.285 | +| time/ | | +| fps | 1358 | +| iterations | 1868 | +| time_elapsed | 2815 | +| total_timesteps | 3825664 | +| train/ | | +| approx_kl | 0.03910201 | +| clip_fraction | 0.412 | +| clip_range | 0.102 | +| entropy_loss | -7.41 | +| explained_variance | -0.0469 | +| learning_rate | 0.000124 | +| loss | -0.0433 | +| n_updates | 7468 | +| policy_gradient_loss | -0.0272 | +| value_loss | 0.000244 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.285 | +| time/ | | +| fps | 1358 | +| iterations | 1869 | +| time_elapsed | 2816 | +| total_timesteps | 3827712 | +| train/ | | +| approx_kl | 0.030522503 | +| clip_fraction | 0.418 | +| clip_range | 0.102 | +| entropy_loss | -7.32 | +| explained_variance | -0.264 | +| learning_rate | 0.000124 | +| loss | -0.0397 | +| n_updates | 7472 | +| policy_gradient_loss | -0.0304 | +| value_loss | 0.00014 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.281 | +| time/ | | +| fps | 1358 | +| iterations | 1870 | +| time_elapsed | 2818 | +| total_timesteps | 3829760 | +| train/ | | +| approx_kl | 0.03653321 | +| clip_fraction | 0.439 | +| clip_range | 0.102 | +| entropy_loss | -7.4 | +| explained_variance | -0.129 | +| learning_rate | 0.000124 | +| loss | -0.0527 | +| n_updates | 7476 | +| policy_gradient_loss | -0.0332 | +| value_loss | 0.000125 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.28 | +| time/ | | +| fps | 1359 | +| iterations | 1871 | +| time_elapsed | 2819 | +| total_timesteps | 3831808 | +| train/ | | +| approx_kl | 0.032041106 | +| clip_fraction | 0.409 | +| clip_range | 0.102 | +| entropy_loss | -7.4 | +| explained_variance | 0.0297 | +| learning_rate | 0.000124 | +| loss | -0.0475 | +| n_updates | 7480 | +| policy_gradient_loss | -0.0294 | +| value_loss | 0.000187 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 1359 | +| iterations | 1872 | +| time_elapsed | 2820 | +| total_timesteps | 3833856 | +| train/ | | +| approx_kl | 0.03224211 | +| clip_fraction | 0.387 | +| clip_range | 0.102 | +| entropy_loss | -7.42 | +| explained_variance | -0.156 | +| learning_rate | 0.000124 | +| loss | -0.0488 | +| n_updates | 7484 | +| policy_gradient_loss | -0.0286 | +| value_loss | 0.000215 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.283 | +| time/ | | +| fps | 1359 | +| iterations | 1873 | +| time_elapsed | 2822 | +| total_timesteps | 3835904 | +| train/ | | +| approx_kl | 0.031113759 | +| clip_fraction | 0.382 | +| clip_range | 0.102 | +| entropy_loss | -7.35 | +| explained_variance | -0.00894 | +| learning_rate | 0.000124 | +| loss | -0.0439 | +| n_updates | 7488 | +| policy_gradient_loss | -0.03 | +| value_loss | 0.000198 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 1359 | +| iterations | 1874 | +| time_elapsed | 2823 | +| total_timesteps | 3837952 | +| train/ | | +| approx_kl | 0.034406018 | +| clip_fraction | 0.42 | +| clip_range | 0.102 | +| entropy_loss | -7.42 | +| explained_variance | -0.31 | +| learning_rate | 0.000124 | +| loss | -0.0513 | +| n_updates | 7492 | +| policy_gradient_loss | -0.0341 | +| value_loss | 0.00015 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 1359 | +| iterations | 1875 | +| time_elapsed | 2825 | +| total_timesteps | 3840000 | +| train/ | | +| approx_kl | 0.032065958 | +| clip_fraction | 0.408 | +| clip_range | 0.102 | +| entropy_loss | -7.43 | +| explained_variance | -0.133 | +| learning_rate | 0.000124 | +| loss | -0.0517 | +| n_updates | 7496 | +| policy_gradient_loss | -0.0322 | +| value_loss | 0.000113 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 1359 | +| iterations | 1876 | +| time_elapsed | 2826 | +| total_timesteps | 3842048 | +| train/ | | +| approx_kl | 0.034861546 | +| clip_fraction | 0.4 | +| clip_range | 0.102 | +| entropy_loss | -7.35 | +| explained_variance | -0.0401 | +| learning_rate | 0.000124 | +| loss | -0.0512 | +| n_updates | 7500 | +| policy_gradient_loss | -0.0316 | +| value_loss | 0.000124 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.283 | +| time/ | | +| fps | 1359 | +| iterations | 1877 | +| time_elapsed | 2828 | +| total_timesteps | 3844096 | +| train/ | | +| approx_kl | 0.035362735 | +| clip_fraction | 0.402 | +| clip_range | 0.102 | +| entropy_loss | -7.48 | +| explained_variance | -0.125 | +| learning_rate | 0.000124 | +| loss | -0.0581 | +| n_updates | 7504 | +| policy_gradient_loss | -0.0339 | +| value_loss | 7.52e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.286 | +| time/ | | +| fps | 1359 | +| iterations | 1878 | +| time_elapsed | 2829 | +| total_timesteps | 3846144 | +| train/ | | +| approx_kl | 0.02842791 | +| clip_fraction | 0.398 | +| clip_range | 0.102 | +| entropy_loss | -7.44 | +| explained_variance | -0.204 | +| learning_rate | 0.000124 | +| loss | -0.0523 | +| n_updates | 7508 | +| policy_gradient_loss | -0.0299 | +| value_loss | 0.000136 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.287 | +| time/ | | +| fps | 1359 | +| iterations | 1879 | +| time_elapsed | 2830 | +| total_timesteps | 3848192 | +| train/ | | +| approx_kl | 0.03592981 | +| clip_fraction | 0.4 | +| clip_range | 0.102 | +| entropy_loss | -7.41 | +| explained_variance | -0.118 | +| learning_rate | 0.000124 | +| loss | -0.048 | +| n_updates | 7512 | +| policy_gradient_loss | -0.0299 | +| value_loss | 0.000109 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 1359 | +| iterations | 1880 | +| time_elapsed | 2832 | +| total_timesteps | 3850240 | +| train/ | | +| approx_kl | 0.032248013 | +| clip_fraction | 0.401 | +| clip_range | 0.102 | +| entropy_loss | -7.44 | +| explained_variance | -0.164 | +| learning_rate | 0.000124 | +| loss | -0.0433 | +| n_updates | 7516 | +| policy_gradient_loss | -0.0282 | +| value_loss | 0.00015 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.285 | +| time/ | | +| fps | 1359 | +| iterations | 1881 | +| time_elapsed | 2833 | +| total_timesteps | 3852288 | +| train/ | | +| approx_kl | 0.03810411 | +| clip_fraction | 0.417 | +| clip_range | 0.102 | +| entropy_loss | -7.44 | +| explained_variance | -0.262 | +| learning_rate | 0.000124 | +| loss | -0.0516 | +| n_updates | 7520 | +| policy_gradient_loss | -0.0331 | +| value_loss | 0.000122 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 1359 | +| iterations | 1882 | +| time_elapsed | 2835 | +| total_timesteps | 3854336 | +| train/ | | +| approx_kl | 0.029776836 | +| clip_fraction | 0.398 | +| clip_range | 0.102 | +| entropy_loss | -7.41 | +| explained_variance | -0.148 | +| learning_rate | 0.000124 | +| loss | -0.0479 | +| n_updates | 7524 | +| policy_gradient_loss | -0.03 | +| value_loss | 0.000172 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.272 | +| time/ | | +| fps | 1359 | +| iterations | 1883 | +| time_elapsed | 2836 | +| total_timesteps | 3856384 | +| train/ | | +| approx_kl | 0.03081023 | +| clip_fraction | 0.408 | +| clip_range | 0.102 | +| entropy_loss | -7.34 | +| explained_variance | -0.681 | +| learning_rate | 0.000124 | +| loss | -0.0522 | +| n_updates | 7528 | +| policy_gradient_loss | -0.0356 | +| value_loss | 6.85e-05 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.272 | +| time/ | | +| fps | 1359 | +| iterations | 1884 | +| time_elapsed | 2838 | +| total_timesteps | 3858432 | +| train/ | | +| approx_kl | 0.03460189 | +| clip_fraction | 0.398 | +| clip_range | 0.102 | +| entropy_loss | -7.2 | +| explained_variance | 0.0188 | +| learning_rate | 0.000124 | +| loss | -0.0493 | +| n_updates | 7532 | +| policy_gradient_loss | -0.03 | +| value_loss | 0.000203 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.272 | +| time/ | | +| fps | 1359 | +| iterations | 1885 | +| time_elapsed | 2839 | +| total_timesteps | 3860480 | +| train/ | | +| approx_kl | 0.033925295 | +| clip_fraction | 0.42 | +| clip_range | 0.102 | +| entropy_loss | -7.41 | +| explained_variance | -0.315 | +| learning_rate | 0.000124 | +| loss | -0.0507 | +| n_updates | 7536 | +| policy_gradient_loss | -0.0322 | +| value_loss | 0.00011 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.272 | +| time/ | | +| fps | 1359 | +| iterations | 1886 | +| time_elapsed | 2840 | +| total_timesteps | 3862528 | +| train/ | | +| approx_kl | 0.033693586 | +| clip_fraction | 0.392 | +| clip_range | 0.102 | +| entropy_loss | -7.39 | +| explained_variance | -0.0947 | +| learning_rate | 0.000124 | +| loss | -0.0478 | +| n_updates | 7540 | +| policy_gradient_loss | -0.0301 | +| value_loss | 0.000129 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.258 | +| time/ | | +| fps | 1359 | +| iterations | 1887 | +| time_elapsed | 2842 | +| total_timesteps | 3864576 | +| train/ | | +| approx_kl | 0.032441117 | +| clip_fraction | 0.385 | +| clip_range | 0.102 | +| entropy_loss | -7.45 | +| explained_variance | -0.153 | +| learning_rate | 0.000124 | +| loss | -0.0506 | +| n_updates | 7544 | +| policy_gradient_loss | -0.0303 | +| value_loss | 0.000131 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.251 | +| time/ | | +| fps | 1359 | +| iterations | 1888 | +| time_elapsed | 2843 | +| total_timesteps | 3866624 | +| train/ | | +| approx_kl | 0.03280522 | +| clip_fraction | 0.37 | +| clip_range | 0.102 | +| entropy_loss | -7.32 | +| explained_variance | -0.102 | +| learning_rate | 0.000123 | +| loss | -0.0486 | +| n_updates | 7548 | +| policy_gradient_loss | -0.0264 | +| value_loss | 0.000173 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.264 | +| time/ | | +| fps | 1359 | +| iterations | 1889 | +| time_elapsed | 2845 | +| total_timesteps | 3868672 | +| train/ | | +| approx_kl | 0.035000097 | +| clip_fraction | 0.368 | +| clip_range | 0.102 | +| entropy_loss | -7.38 | +| explained_variance | -0.189 | +| learning_rate | 0.000123 | +| loss | -0.0402 | +| n_updates | 7552 | +| policy_gradient_loss | -0.0286 | +| value_loss | 0.000239 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.268 | +| time/ | | +| fps | 1359 | +| iterations | 1890 | +| time_elapsed | 2846 | +| total_timesteps | 3870720 | +| train/ | | +| approx_kl | 0.035109576 | +| clip_fraction | 0.393 | +| clip_range | 0.102 | +| entropy_loss | -7.47 | +| explained_variance | -0.12 | +| learning_rate | 0.000123 | +| loss | -0.0341 | +| n_updates | 7556 | +| policy_gradient_loss | -0.0283 | +| value_loss | 0.000238 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.268 | +| time/ | | +| fps | 1359 | +| iterations | 1891 | +| time_elapsed | 2848 | +| total_timesteps | 3872768 | +| train/ | | +| approx_kl | 0.031046815 | +| clip_fraction | 0.393 | +| clip_range | 0.102 | +| entropy_loss | -7.36 | +| explained_variance | -0.113 | +| learning_rate | 0.000123 | +| loss | -0.0423 | +| n_updates | 7560 | +| policy_gradient_loss | -0.0296 | +| value_loss | 0.000266 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.268 | +| time/ | | +| fps | 1359 | +| iterations | 1892 | +| time_elapsed | 2849 | +| total_timesteps | 3874816 | +| train/ | | +| approx_kl | 0.030180268 | +| clip_fraction | 0.385 | +| clip_range | 0.102 | +| entropy_loss | -7.48 | +| explained_variance | -0.0491 | +| learning_rate | 0.000123 | +| loss | -0.0485 | +| n_updates | 7564 | +| policy_gradient_loss | -0.0293 | +| value_loss | 0.000171 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.265 | +| time/ | | +| fps | 1359 | +| iterations | 1893 | +| time_elapsed | 2850 | +| total_timesteps | 3876864 | +| train/ | | +| approx_kl | 0.03441532 | +| clip_fraction | 0.418 | +| clip_range | 0.102 | +| entropy_loss | -7.54 | +| explained_variance | -0.363 | +| learning_rate | 0.000123 | +| loss | -0.0521 | +| n_updates | 7568 | +| policy_gradient_loss | -0.0329 | +| value_loss | 0.000123 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.27 | +| time/ | | +| fps | 1359 | +| iterations | 1894 | +| time_elapsed | 2852 | +| total_timesteps | 3878912 | +| train/ | | +| approx_kl | 0.031964265 | +| clip_fraction | 0.391 | +| clip_range | 0.102 | +| entropy_loss | -7.39 | +| explained_variance | -0.184 | +| learning_rate | 0.000123 | +| loss | -0.0489 | +| n_updates | 7572 | +| policy_gradient_loss | -0.0298 | +| value_loss | 0.000146 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.276 | +| time/ | | +| fps | 1359 | +| iterations | 1895 | +| time_elapsed | 2853 | +| total_timesteps | 3880960 | +| train/ | | +| approx_kl | 0.031511337 | +| clip_fraction | 0.411 | +| clip_range | 0.102 | +| entropy_loss | -7.42 | +| explained_variance | -0.125 | +| learning_rate | 0.000123 | +| loss | -0.0437 | +| n_updates | 7576 | +| policy_gradient_loss | -0.03 | +| value_loss | 0.000105 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.276 | +| time/ | | +| fps | 1359 | +| iterations | 1896 | +| time_elapsed | 2855 | +| total_timesteps | 3883008 | +| train/ | | +| approx_kl | 0.03183857 | +| clip_fraction | 0.41 | +| clip_range | 0.101 | +| entropy_loss | -7.28 | +| explained_variance | 0.00206 | +| learning_rate | 0.000123 | +| loss | -0.0496 | +| n_updates | 7580 | +| policy_gradient_loss | -0.0331 | +| value_loss | 0.00022 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.273 | +| time/ | | +| fps | 1359 | +| iterations | 1897 | +| time_elapsed | 2856 | +| total_timesteps | 3885056 | +| train/ | | +| approx_kl | 0.03493586 | +| clip_fraction | 0.41 | +| clip_range | 0.101 | +| entropy_loss | -7.34 | +| explained_variance | -0.194 | +| learning_rate | 0.000123 | +| loss | -0.0579 | +| n_updates | 7584 | +| policy_gradient_loss | -0.033 | +| value_loss | 0.000124 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.273 | +| time/ | | +| fps | 1359 | +| iterations | 1898 | +| time_elapsed | 2858 | +| total_timesteps | 3887104 | +| train/ | | +| approx_kl | 0.035823263 | +| clip_fraction | 0.414 | +| clip_range | 0.101 | +| entropy_loss | -7.51 | +| explained_variance | -0.349 | +| learning_rate | 0.000123 | +| loss | -0.0618 | +| n_updates | 7588 | +| policy_gradient_loss | -0.0344 | +| value_loss | 9.65e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.266 | +| time/ | | +| fps | 1359 | +| iterations | 1899 | +| time_elapsed | 2859 | +| total_timesteps | 3889152 | +| train/ | | +| approx_kl | 0.041800864 | +| clip_fraction | 0.41 | +| clip_range | 0.101 | +| entropy_loss | -7.49 | +| explained_variance | -0.0732 | +| learning_rate | 0.000123 | +| loss | -0.0578 | +| n_updates | 7592 | +| policy_gradient_loss | -0.0329 | +| value_loss | 0.00014 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.268 | +| time/ | | +| fps | 1360 | +| iterations | 1900 | +| time_elapsed | 2861 | +| total_timesteps | 3891200 | +| train/ | | +| approx_kl | 0.03372148 | +| clip_fraction | 0.395 | +| clip_range | 0.101 | +| entropy_loss | -7.49 | +| explained_variance | -0.151 | +| learning_rate | 0.000123 | +| loss | -0.026 | +| n_updates | 7596 | +| policy_gradient_loss | -0.0296 | +| value_loss | 0.000141 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.268 | +| time/ | | +| fps | 1360 | +| iterations | 1901 | +| time_elapsed | 2862 | +| total_timesteps | 3893248 | +| train/ | | +| approx_kl | 0.027015796 | +| clip_fraction | 0.396 | +| clip_range | 0.101 | +| entropy_loss | -7.46 | +| explained_variance | -0.0847 | +| learning_rate | 0.000123 | +| loss | -0.0554 | +| n_updates | 7600 | +| policy_gradient_loss | -0.0295 | +| value_loss | 0.000144 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.272 | +| time/ | | +| fps | 1360 | +| iterations | 1902 | +| time_elapsed | 2863 | +| total_timesteps | 3895296 | +| train/ | | +| approx_kl | 0.029574756 | +| clip_fraction | 0.372 | +| clip_range | 0.101 | +| entropy_loss | -7.5 | +| explained_variance | -0.0674 | +| learning_rate | 0.000123 | +| loss | -0.0506 | +| n_updates | 7604 | +| policy_gradient_loss | -0.0286 | +| value_loss | 0.000187 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.272 | +| time/ | | +| fps | 1360 | +| iterations | 1903 | +| time_elapsed | 2865 | +| total_timesteps | 3897344 | +| train/ | | +| approx_kl | 0.034027085 | +| clip_fraction | 0.411 | +| clip_range | 0.101 | +| entropy_loss | -7.36 | +| explained_variance | -0.125 | +| learning_rate | 0.000123 | +| loss | -0.0504 | +| n_updates | 7608 | +| policy_gradient_loss | -0.0301 | +| value_loss | 0.000249 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.272 | +| time/ | | +| fps | 1360 | +| iterations | 1904 | +| time_elapsed | 2866 | +| total_timesteps | 3899392 | +| train/ | | +| approx_kl | 0.028572375 | +| clip_fraction | 0.386 | +| clip_range | 0.101 | +| entropy_loss | -7.42 | +| explained_variance | -0.269 | +| learning_rate | 0.000123 | +| loss | -0.0549 | +| n_updates | 7612 | +| policy_gradient_loss | -0.0329 | +| value_loss | 0.000169 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.28 | +| time/ | | +| fps | 1360 | +| iterations | 1905 | +| time_elapsed | 2868 | +| total_timesteps | 3901440 | +| train/ | | +| approx_kl | 0.028699469 | +| clip_fraction | 0.395 | +| clip_range | 0.101 | +| entropy_loss | -7.51 | +| explained_variance | -0.391 | +| learning_rate | 0.000123 | +| loss | -0.0482 | +| n_updates | 7616 | +| policy_gradient_loss | -0.0307 | +| value_loss | 9.77e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.281 | +| time/ | | +| fps | 1360 | +| iterations | 1906 | +| time_elapsed | 2869 | +| total_timesteps | 3903488 | +| train/ | | +| approx_kl | 0.028868727 | +| clip_fraction | 0.398 | +| clip_range | 0.101 | +| entropy_loss | -7.43 | +| explained_variance | -0.118 | +| learning_rate | 0.000123 | +| loss | -0.0429 | +| n_updates | 7620 | +| policy_gradient_loss | -0.0293 | +| value_loss | 0.000244 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.281 | +| time/ | | +| fps | 1360 | +| iterations | 1907 | +| time_elapsed | 2871 | +| total_timesteps | 3905536 | +| train/ | | +| approx_kl | 0.035084303 | +| clip_fraction | 0.392 | +| clip_range | 0.101 | +| entropy_loss | -7.39 | +| explained_variance | -0.0883 | +| learning_rate | 0.000123 | +| loss | -0.0474 | +| n_updates | 7624 | +| policy_gradient_loss | -0.0318 | +| value_loss | 0.000157 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.284 | +| time/ | | +| fps | 1360 | +| iterations | 1908 | +| time_elapsed | 2872 | +| total_timesteps | 3907584 | +| train/ | | +| approx_kl | 0.02907966 | +| clip_fraction | 0.398 | +| clip_range | 0.101 | +| entropy_loss | -7.38 | +| explained_variance | -0.26 | +| learning_rate | 0.000123 | +| loss | -0.0638 | +| n_updates | 7628 | +| policy_gradient_loss | -0.0325 | +| value_loss | 9.07e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.294 | +| time/ | | +| fps | 1360 | +| iterations | 1909 | +| time_elapsed | 2874 | +| total_timesteps | 3909632 | +| train/ | | +| approx_kl | 0.034569662 | +| clip_fraction | 0.413 | +| clip_range | 0.101 | +| entropy_loss | -7.29 | +| explained_variance | -0.0675 | +| learning_rate | 0.000123 | +| loss | -0.0446 | +| n_updates | 7632 | +| policy_gradient_loss | -0.0295 | +| value_loss | 0.000169 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.294 | +| time/ | | +| fps | 1360 | +| iterations | 1910 | +| time_elapsed | 2875 | +| total_timesteps | 3911680 | +| train/ | | +| approx_kl | 0.02714899 | +| clip_fraction | 0.376 | +| clip_range | 0.101 | +| entropy_loss | -7.29 | +| explained_variance | -0.0218 | +| learning_rate | 0.000123 | +| loss | -0.0395 | +| n_updates | 7636 | +| policy_gradient_loss | -0.0281 | +| value_loss | 0.000303 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.294 | +| time/ | | +| fps | 1360 | +| iterations | 1911 | +| time_elapsed | 2876 | +| total_timesteps | 3913728 | +| train/ | | +| approx_kl | 0.03251978 | +| clip_fraction | 0.413 | +| clip_range | 0.101 | +| entropy_loss | -7.47 | +| explained_variance | -0.488 | +| learning_rate | 0.000123 | +| loss | -0.0631 | +| n_updates | 7640 | +| policy_gradient_loss | -0.0373 | +| value_loss | 0.000111 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.294 | +| time/ | | +| fps | 1360 | +| iterations | 1912 | +| time_elapsed | 2878 | +| total_timesteps | 3915776 | +| train/ | | +| approx_kl | 0.03886149 | +| clip_fraction | 0.41 | +| clip_range | 0.101 | +| entropy_loss | -7.47 | +| explained_variance | -0.228 | +| learning_rate | 0.000123 | +| loss | -0.0526 | +| n_updates | 7644 | +| policy_gradient_loss | -0.0327 | +| value_loss | 0.000122 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.29 | +| time/ | | +| fps | 1360 | +| iterations | 1913 | +| time_elapsed | 2879 | +| total_timesteps | 3917824 | +| train/ | | +| approx_kl | 0.033312958 | +| clip_fraction | 0.409 | +| clip_range | 0.101 | +| entropy_loss | -7.49 | +| explained_variance | -0.126 | +| learning_rate | 0.000122 | +| loss | -0.0365 | +| n_updates | 7648 | +| policy_gradient_loss | -0.0283 | +| value_loss | 0.000134 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.293 | +| time/ | | +| fps | 1360 | +| iterations | 1914 | +| time_elapsed | 2881 | +| total_timesteps | 3919872 | +| train/ | | +| approx_kl | 0.029412009 | +| clip_fraction | 0.391 | +| clip_range | 0.101 | +| entropy_loss | -7.34 | +| explained_variance | -0.0431 | +| learning_rate | 0.000122 | +| loss | -0.05 | +| n_updates | 7652 | +| policy_gradient_loss | -0.0304 | +| value_loss | 0.000135 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.293 | +| time/ | | +| fps | 1360 | +| iterations | 1915 | +| time_elapsed | 2882 | +| total_timesteps | 3921920 | +| train/ | | +| approx_kl | 0.03282812 | +| clip_fraction | 0.375 | +| clip_range | 0.101 | +| entropy_loss | -7.44 | +| explained_variance | -0.102 | +| learning_rate | 0.000122 | +| loss | -0.0447 | +| n_updates | 7656 | +| policy_gradient_loss | -0.028 | +| value_loss | 0.000218 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.293 | +| time/ | | +| fps | 1360 | +| iterations | 1916 | +| time_elapsed | 2884 | +| total_timesteps | 3923968 | +| train/ | | +| approx_kl | 0.034519847 | +| clip_fraction | 0.405 | +| clip_range | 0.101 | +| entropy_loss | -7.51 | +| explained_variance | -0.144 | +| learning_rate | 0.000122 | +| loss | -0.043 | +| n_updates | 7660 | +| policy_gradient_loss | -0.0307 | +| value_loss | 0.000207 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.298 | +| time/ | | +| fps | 1360 | +| iterations | 1917 | +| time_elapsed | 2885 | +| total_timesteps | 3926016 | +| train/ | | +| approx_kl | 0.033828814 | +| clip_fraction | 0.414 | +| clip_range | 0.101 | +| entropy_loss | -7.54 | +| explained_variance | -0.296 | +| learning_rate | 0.000122 | +| loss | -0.0497 | +| n_updates | 7664 | +| policy_gradient_loss | -0.0336 | +| value_loss | 0.000139 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.288 | +| time/ | | +| fps | 1360 | +| iterations | 1918 | +| time_elapsed | 2886 | +| total_timesteps | 3928064 | +| train/ | | +| approx_kl | 0.025713708 | +| clip_fraction | 0.389 | +| clip_range | 0.101 | +| entropy_loss | -7.48 | +| explained_variance | -0.078 | +| learning_rate | 0.000122 | +| loss | -0.0446 | +| n_updates | 7668 | +| policy_gradient_loss | -0.0278 | +| value_loss | 0.000229 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.292 | +| time/ | | +| fps | 1360 | +| iterations | 1919 | +| time_elapsed | 2888 | +| total_timesteps | 3930112 | +| train/ | | +| approx_kl | 0.033543166 | +| clip_fraction | 0.39 | +| clip_range | 0.101 | +| entropy_loss | -7.32 | +| explained_variance | -0.118 | +| learning_rate | 0.000122 | +| loss | -0.0517 | +| n_updates | 7672 | +| policy_gradient_loss | -0.0311 | +| value_loss | 0.000156 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.29 | +| time/ | | +| fps | 1360 | +| iterations | 1920 | +| time_elapsed | 2889 | +| total_timesteps | 3932160 | +| train/ | | +| approx_kl | 0.03084239 | +| clip_fraction | 0.388 | +| clip_range | 0.101 | +| entropy_loss | -7.36 | +| explained_variance | -0.101 | +| learning_rate | 0.000122 | +| loss | -0.0335 | +| n_updates | 7676 | +| policy_gradient_loss | -0.0244 | +| value_loss | 0.000258 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.29 | +| time/ | | +| fps | 1360 | +| iterations | 1921 | +| time_elapsed | 2891 | +| total_timesteps | 3934208 | +| train/ | | +| approx_kl | 0.029956628 | +| clip_fraction | 0.409 | +| clip_range | 0.101 | +| entropy_loss | -7.34 | +| explained_variance | -0.151 | +| learning_rate | 0.000122 | +| loss | -0.0496 | +| n_updates | 7680 | +| policy_gradient_loss | -0.0297 | +| value_loss | 0.000191 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.287 | +| time/ | | +| fps | 1360 | +| iterations | 1922 | +| time_elapsed | 2892 | +| total_timesteps | 3936256 | +| train/ | | +| approx_kl | 0.03701274 | +| clip_fraction | 0.441 | +| clip_range | 0.101 | +| entropy_loss | -7.47 | +| explained_variance | -0.642 | +| learning_rate | 0.000122 | +| loss | -0.0512 | +| n_updates | 7684 | +| policy_gradient_loss | -0.0368 | +| value_loss | 7.35e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.283 | +| time/ | | +| fps | 1360 | +| iterations | 1923 | +| time_elapsed | 2894 | +| total_timesteps | 3938304 | +| train/ | | +| approx_kl | 0.027412444 | +| clip_fraction | 0.396 | +| clip_range | 0.101 | +| entropy_loss | -7.44 | +| explained_variance | -0.0788 | +| learning_rate | 0.000122 | +| loss | -0.0384 | +| n_updates | 7688 | +| policy_gradient_loss | -0.026 | +| value_loss | 0.000277 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.283 | +| time/ | | +| fps | 1360 | +| iterations | 1924 | +| time_elapsed | 2895 | +| total_timesteps | 3940352 | +| train/ | | +| approx_kl | 0.03332729 | +| clip_fraction | 0.415 | +| clip_range | 0.101 | +| entropy_loss | -7.45 | +| explained_variance | -0.227 | +| learning_rate | 0.000122 | +| loss | -0.0468 | +| n_updates | 7692 | +| policy_gradient_loss | -0.0305 | +| value_loss | 0.000249 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.276 | +| time/ | | +| fps | 1360 | +| iterations | 1925 | +| time_elapsed | 2896 | +| total_timesteps | 3942400 | +| train/ | | +| approx_kl | 0.028867118 | +| clip_fraction | 0.398 | +| clip_range | 0.101 | +| entropy_loss | -7.62 | +| explained_variance | -0.234 | +| learning_rate | 0.000122 | +| loss | -0.0494 | +| n_updates | 7696 | +| policy_gradient_loss | -0.0323 | +| value_loss | 0.00013 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.271 | +| time/ | | +| fps | 1360 | +| iterations | 1926 | +| time_elapsed | 2898 | +| total_timesteps | 3944448 | +| train/ | | +| approx_kl | 0.030443238 | +| clip_fraction | 0.4 | +| clip_range | 0.101 | +| entropy_loss | -7.49 | +| explained_variance | -0.358 | +| learning_rate | 0.000122 | +| loss | -0.0493 | +| n_updates | 7700 | +| policy_gradient_loss | -0.0316 | +| value_loss | 9.04e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.271 | +| time/ | | +| fps | 1360 | +| iterations | 1927 | +| time_elapsed | 2899 | +| total_timesteps | 3946496 | +| train/ | | +| approx_kl | 0.029902825 | +| clip_fraction | 0.413 | +| clip_range | 0.101 | +| entropy_loss | -7.48 | +| explained_variance | -0.231 | +| learning_rate | 0.000122 | +| loss | -0.049 | +| n_updates | 7704 | +| policy_gradient_loss | -0.0305 | +| value_loss | 7.71e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.266 | +| time/ | | +| fps | 1361 | +| iterations | 1928 | +| time_elapsed | 2901 | +| total_timesteps | 3948544 | +| train/ | | +| approx_kl | 0.03228135 | +| clip_fraction | 0.398 | +| clip_range | 0.101 | +| entropy_loss | -7.45 | +| explained_variance | -0.0477 | +| learning_rate | 0.000122 | +| loss | -0.0462 | +| n_updates | 7708 | +| policy_gradient_loss | -0.0304 | +| value_loss | 0.000125 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.273 | +| time/ | | +| fps | 1361 | +| iterations | 1929 | +| time_elapsed | 2902 | +| total_timesteps | 3950592 | +| train/ | | +| approx_kl | 0.030172251 | +| clip_fraction | 0.383 | +| clip_range | 0.101 | +| entropy_loss | -7.49 | +| explained_variance | -0.289 | +| learning_rate | 0.000122 | +| loss | -0.0525 | +| n_updates | 7712 | +| policy_gradient_loss | -0.0315 | +| value_loss | 0.000106 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.263 | +| time/ | | +| fps | 1361 | +| iterations | 1930 | +| time_elapsed | 2904 | +| total_timesteps | 3952640 | +| train/ | | +| approx_kl | 0.03255055 | +| clip_fraction | 0.414 | +| clip_range | 0.101 | +| entropy_loss | -7.43 | +| explained_variance | -0.226 | +| learning_rate | 0.000122 | +| loss | -0.0478 | +| n_updates | 7716 | +| policy_gradient_loss | -0.0305 | +| value_loss | 0.000107 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.266 | +| time/ | | +| fps | 1361 | +| iterations | 1931 | +| time_elapsed | 2905 | +| total_timesteps | 3954688 | +| train/ | | +| approx_kl | 0.03185731 | +| clip_fraction | 0.423 | +| clip_range | 0.101 | +| entropy_loss | -7.32 | +| explained_variance | -0.21 | +| learning_rate | 0.000122 | +| loss | -0.0491 | +| n_updates | 7720 | +| policy_gradient_loss | -0.0322 | +| value_loss | 0.000101 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.264 | +| time/ | | +| fps | 1361 | +| iterations | 1932 | +| time_elapsed | 2906 | +| total_timesteps | 3956736 | +| train/ | | +| approx_kl | 0.033065803 | +| clip_fraction | 0.38 | +| clip_range | 0.101 | +| entropy_loss | -7.24 | +| explained_variance | 0.0259 | +| learning_rate | 0.000122 | +| loss | -0.0425 | +| n_updates | 7724 | +| policy_gradient_loss | -0.0264 | +| value_loss | 0.000256 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.261 | +| time/ | | +| fps | 1361 | +| iterations | 1933 | +| time_elapsed | 2908 | +| total_timesteps | 3958784 | +| train/ | | +| approx_kl | 0.035263017 | +| clip_fraction | 0.413 | +| clip_range | 0.101 | +| entropy_loss | -7.46 | +| explained_variance | -0.0863 | +| learning_rate | 0.000122 | +| loss | -0.05 | +| n_updates | 7728 | +| policy_gradient_loss | -0.0339 | +| value_loss | 8e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.252 | +| time/ | | +| fps | 1361 | +| iterations | 1934 | +| time_elapsed | 2909 | +| total_timesteps | 3960832 | +| train/ | | +| approx_kl | 0.03101306 | +| clip_fraction | 0.421 | +| clip_range | 0.101 | +| entropy_loss | -7.42 | +| explained_variance | -0.00475 | +| learning_rate | 0.000122 | +| loss | -0.0522 | +| n_updates | 7732 | +| policy_gradient_loss | -0.0316 | +| value_loss | 0.000125 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.252 | +| time/ | | +| fps | 1361 | +| iterations | 1935 | +| time_elapsed | 2911 | +| total_timesteps | 3962880 | +| train/ | | +| approx_kl | 0.029274404 | +| clip_fraction | 0.382 | +| clip_range | 0.1 | +| entropy_loss | -7.37 | +| explained_variance | 0.112 | +| learning_rate | 0.000122 | +| loss | -0.0486 | +| n_updates | 7736 | +| policy_gradient_loss | -0.0302 | +| value_loss | 0.000194 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.252 | +| time/ | | +| fps | 1361 | +| iterations | 1936 | +| time_elapsed | 2912 | +| total_timesteps | 3964928 | +| train/ | | +| approx_kl | 0.025200289 | +| clip_fraction | 0.372 | +| clip_range | 0.1 | +| entropy_loss | -7.6 | +| explained_variance | -0.0153 | +| learning_rate | 0.000122 | +| loss | -0.0428 | +| n_updates | 7740 | +| policy_gradient_loss | -0.0285 | +| value_loss | 0.000139 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.253 | +| time/ | | +| fps | 1361 | +| iterations | 1937 | +| time_elapsed | 2914 | +| total_timesteps | 3966976 | +| train/ | | +| approx_kl | 0.03068536 | +| clip_fraction | 0.414 | +| clip_range | 0.1 | +| entropy_loss | -7.61 | +| explained_variance | -0.437 | +| learning_rate | 0.000121 | +| loss | -0.0559 | +| n_updates | 7744 | +| policy_gradient_loss | -0.0317 | +| value_loss | 0.000116 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.25 | +| time/ | | +| fps | 1361 | +| iterations | 1938 | +| time_elapsed | 2915 | +| total_timesteps | 3969024 | +| train/ | | +| approx_kl | 0.033314433 | +| clip_fraction | 0.383 | +| clip_range | 0.1 | +| entropy_loss | -7.54 | +| explained_variance | -0.184 | +| learning_rate | 0.000121 | +| loss | -0.0451 | +| n_updates | 7748 | +| policy_gradient_loss | -0.0301 | +| value_loss | 0.000124 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.244 | +| time/ | | +| fps | 1361 | +| iterations | 1939 | +| time_elapsed | 2916 | +| total_timesteps | 3971072 | +| train/ | | +| approx_kl | 0.031798095 | +| clip_fraction | 0.38 | +| clip_range | 0.1 | +| entropy_loss | -7.5 | +| explained_variance | -0.202 | +| learning_rate | 0.000121 | +| loss | -0.054 | +| n_updates | 7752 | +| policy_gradient_loss | -0.0293 | +| value_loss | 0.000123 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.242 | +| time/ | | +| fps | 1361 | +| iterations | 1940 | +| time_elapsed | 2918 | +| total_timesteps | 3973120 | +| train/ | | +| approx_kl | 0.03271316 | +| clip_fraction | 0.397 | +| clip_range | 0.1 | +| entropy_loss | -7.26 | +| explained_variance | -0.211 | +| learning_rate | 0.000121 | +| loss | -0.0524 | +| n_updates | 7756 | +| policy_gradient_loss | -0.0304 | +| value_loss | 0.000147 | +---------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.242 | +| time/ | | +| fps | 1361 | +| iterations | 1941 | +| time_elapsed | 2919 | +| total_timesteps | 3975168 | +| train/ | | +| approx_kl | 0.0333111 | +| clip_fraction | 0.387 | +| clip_range | 0.1 | +| entropy_loss | -7.41 | +| explained_variance | -0.0655 | +| learning_rate | 0.000121 | +| loss | -0.0421 | +| n_updates | 7760 | +| policy_gradient_loss | -0.0269 | +| value_loss | 0.000141 | +--------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.244 | +| time/ | | +| fps | 1361 | +| iterations | 1942 | +| time_elapsed | 2921 | +| total_timesteps | 3977216 | +| train/ | | +| approx_kl | 0.02721589 | +| clip_fraction | 0.372 | +| clip_range | 0.1 | +| entropy_loss | -7.39 | +| explained_variance | -0.0909 | +| learning_rate | 0.000121 | +| loss | -0.0433 | +| n_updates | 7764 | +| policy_gradient_loss | -0.0295 | +| value_loss | 0.000156 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.244 | +| time/ | | +| fps | 1361 | +| iterations | 1943 | +| time_elapsed | 2922 | +| total_timesteps | 3979264 | +| train/ | | +| approx_kl | 0.026728498 | +| clip_fraction | 0.385 | +| clip_range | 0.1 | +| entropy_loss | -7.4 | +| explained_variance | -0.14 | +| learning_rate | 0.000121 | +| loss | -0.035 | +| n_updates | 7768 | +| policy_gradient_loss | -0.0277 | +| value_loss | 0.000133 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.244 | +| time/ | | +| fps | 1361 | +| iterations | 1944 | +| time_elapsed | 2923 | +| total_timesteps | 3981312 | +| train/ | | +| approx_kl | 0.03483055 | +| clip_fraction | 0.426 | +| clip_range | 0.1 | +| entropy_loss | -7.41 | +| explained_variance | -0.136 | +| learning_rate | 0.000121 | +| loss | -0.0453 | +| n_updates | 7772 | +| policy_gradient_loss | -0.0311 | +| value_loss | 0.00018 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.238 | +| time/ | | +| fps | 1361 | +| iterations | 1945 | +| time_elapsed | 2925 | +| total_timesteps | 3983360 | +| train/ | | +| approx_kl | 0.039205343 | +| clip_fraction | 0.405 | +| clip_range | 0.1 | +| entropy_loss | -7.44 | +| explained_variance | -0.0934 | +| learning_rate | 0.000121 | +| loss | -0.046 | +| n_updates | 7776 | +| policy_gradient_loss | -0.0292 | +| value_loss | 0.000148 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.243 | +| time/ | | +| fps | 1361 | +| iterations | 1946 | +| time_elapsed | 2926 | +| total_timesteps | 3985408 | +| train/ | | +| approx_kl | 0.02844028 | +| clip_fraction | 0.387 | +| clip_range | 0.1 | +| entropy_loss | -7.47 | +| explained_variance | -0.109 | +| learning_rate | 0.000121 | +| loss | -0.0394 | +| n_updates | 7780 | +| policy_gradient_loss | -0.0265 | +| value_loss | 0.000189 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.242 | +| time/ | | +| fps | 1361 | +| iterations | 1947 | +| time_elapsed | 2928 | +| total_timesteps | 3987456 | +| train/ | | +| approx_kl | 0.031651422 | +| clip_fraction | 0.403 | +| clip_range | 0.1 | +| entropy_loss | -7.43 | +| explained_variance | -0.0434 | +| learning_rate | 0.000121 | +| loss | -0.0471 | +| n_updates | 7784 | +| policy_gradient_loss | -0.0294 | +| value_loss | 0.000318 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.249 | +| time/ | | +| fps | 1361 | +| iterations | 1948 | +| time_elapsed | 2929 | +| total_timesteps | 3989504 | +| train/ | | +| approx_kl | 0.028997589 | +| clip_fraction | 0.414 | +| clip_range | 0.1 | +| entropy_loss | -7.55 | +| explained_variance | -0.167 | +| learning_rate | 0.000121 | +| loss | -0.0467 | +| n_updates | 7788 | +| policy_gradient_loss | -0.0289 | +| value_loss | 0.000147 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.249 | +| time/ | | +| fps | 1361 | +| iterations | 1949 | +| time_elapsed | 2930 | +| total_timesteps | 3991552 | +| train/ | | +| approx_kl | 0.03062759 | +| clip_fraction | 0.405 | +| clip_range | 0.1 | +| entropy_loss | -7.48 | +| explained_variance | -0.189 | +| learning_rate | 0.000121 | +| loss | -0.0526 | +| n_updates | 7792 | +| policy_gradient_loss | -0.0318 | +| value_loss | 0.000198 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.254 | +| time/ | | +| fps | 1361 | +| iterations | 1950 | +| time_elapsed | 2932 | +| total_timesteps | 3993600 | +| train/ | | +| approx_kl | 0.033697143 | +| clip_fraction | 0.375 | +| clip_range | 0.1 | +| entropy_loss | -7.46 | +| explained_variance | -0.126 | +| learning_rate | 0.000121 | +| loss | -0.0504 | +| n_updates | 7796 | +| policy_gradient_loss | -0.0315 | +| value_loss | 0.000143 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.252 | +| time/ | | +| fps | 1361 | +| iterations | 1951 | +| time_elapsed | 2933 | +| total_timesteps | 3995648 | +| train/ | | +| approx_kl | 0.026096623 | +| clip_fraction | 0.387 | +| clip_range | 0.1 | +| entropy_loss | -7.38 | +| explained_variance | -0.0577 | +| learning_rate | 0.000121 | +| loss | -0.0581 | +| n_updates | 7800 | +| policy_gradient_loss | -0.0285 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.252 | +| time/ | | +| fps | 1362 | +| iterations | 1952 | +| time_elapsed | 2935 | +| total_timesteps | 3997696 | +| train/ | | +| approx_kl | 0.035125233 | +| clip_fraction | 0.398 | +| clip_range | 0.1 | +| entropy_loss | -7.34 | +| explained_variance | -0.0888 | +| learning_rate | 0.000121 | +| loss | -0.0543 | +| n_updates | 7804 | +| policy_gradient_loss | -0.0318 | +| value_loss | 0.000154 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.249 | +| time/ | | +| fps | 1362 | +| iterations | 1953 | +| time_elapsed | 2936 | +| total_timesteps | 3999744 | +| train/ | | +| approx_kl | 0.03311824 | +| clip_fraction | 0.401 | +| clip_range | 0.1 | +| entropy_loss | -7.44 | +| explained_variance | -0.0787 | +| learning_rate | 0.000121 | +| loss | -0.0522 | +| n_updates | 7808 | +| policy_gradient_loss | -0.0325 | +| value_loss | 0.000106 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.255 | +| time/ | | +| fps | 1362 | +| iterations | 1954 | +| time_elapsed | 2938 | +| total_timesteps | 4001792 | +| train/ | | +| approx_kl | 0.027226254 | +| clip_fraction | 0.378 | +| clip_range | 0.1 | +| entropy_loss | -7.41 | +| explained_variance | -0.0966 | +| learning_rate | 0.000121 | +| loss | -0.0507 | +| n_updates | 7812 | +| policy_gradient_loss | -0.0303 | +| value_loss | 0.000107 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.255 | +| time/ | | +| fps | 1362 | +| iterations | 1955 | +| time_elapsed | 2939 | +| total_timesteps | 4003840 | +| train/ | | +| approx_kl | 0.030273862 | +| clip_fraction | 0.402 | +| clip_range | 0.1 | +| entropy_loss | -7.34 | +| explained_variance | 0.0381 | +| learning_rate | 0.000121 | +| loss | -0.0428 | +| n_updates | 7816 | +| policy_gradient_loss | -0.0275 | +| value_loss | 0.000174 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.256 | +| time/ | | +| fps | 1362 | +| iterations | 1956 | +| time_elapsed | 2940 | +| total_timesteps | 4005888 | +| train/ | | +| approx_kl | 0.031584527 | +| clip_fraction | 0.417 | +| clip_range | 0.1 | +| entropy_loss | -7.46 | +| explained_variance | -0.185 | +| learning_rate | 0.000121 | +| loss | -0.0456 | +| n_updates | 7820 | +| policy_gradient_loss | -0.0298 | +| value_loss | 0.000218 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.254 | +| time/ | | +| fps | 1362 | +| iterations | 1957 | +| time_elapsed | 2942 | +| total_timesteps | 4007936 | +| train/ | | +| approx_kl | 0.029776622 | +| clip_fraction | 0.402 | +| clip_range | 0.0999 | +| entropy_loss | -7.38 | +| explained_variance | -0.106 | +| learning_rate | 0.000121 | +| loss | -0.0467 | +| n_updates | 7824 | +| policy_gradient_loss | -0.0278 | +| value_loss | 0.000268 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.254 | +| time/ | | +| fps | 1362 | +| iterations | 1958 | +| time_elapsed | 2943 | +| total_timesteps | 4009984 | +| train/ | | +| approx_kl | 0.032881312 | +| clip_fraction | 0.4 | +| clip_range | 0.0999 | +| entropy_loss | -7.3 | +| explained_variance | -0.173 | +| learning_rate | 0.000121 | +| loss | -0.0443 | +| n_updates | 7828 | +| policy_gradient_loss | -0.0314 | +| value_loss | 0.000143 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.256 | +| time/ | | +| fps | 1362 | +| iterations | 1959 | +| time_elapsed | 2945 | +| total_timesteps | 4012032 | +| train/ | | +| approx_kl | 0.028217193 | +| clip_fraction | 0.407 | +| clip_range | 0.0999 | +| entropy_loss | -7.45 | +| explained_variance | -0.382 | +| learning_rate | 0.000121 | +| loss | -0.0525 | +| n_updates | 7832 | +| policy_gradient_loss | -0.0331 | +| value_loss | 0.000122 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.253 | +| time/ | | +| fps | 1362 | +| iterations | 1960 | +| time_elapsed | 2946 | +| total_timesteps | 4014080 | +| train/ | | +| approx_kl | 0.03111784 | +| clip_fraction | 0.421 | +| clip_range | 0.0998 | +| entropy_loss | -7.5 | +| explained_variance | -0.0962 | +| learning_rate | 0.000121 | +| loss | -0.0383 | +| n_updates | 7836 | +| policy_gradient_loss | -0.0258 | +| value_loss | 0.00018 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.25 | +| time/ | | +| fps | 1362 | +| iterations | 1961 | +| time_elapsed | 2948 | +| total_timesteps | 4016128 | +| train/ | | +| approx_kl | 0.033400416 | +| clip_fraction | 0.384 | +| clip_range | 0.0998 | +| entropy_loss | -7.34 | +| explained_variance | -0.0481 | +| learning_rate | 0.000121 | +| loss | -0.0504 | +| n_updates | 7840 | +| policy_gradient_loss | -0.0274 | +| value_loss | 0.000175 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.251 | +| time/ | | +| fps | 1362 | +| iterations | 1962 | +| time_elapsed | 2949 | +| total_timesteps | 4018176 | +| train/ | | +| approx_kl | 0.034200516 | +| clip_fraction | 0.422 | +| clip_range | 0.0998 | +| entropy_loss | -7.3 | +| explained_variance | -0.218 | +| learning_rate | 0.00012 | +| loss | -0.053 | +| n_updates | 7844 | +| policy_gradient_loss | -0.0331 | +| value_loss | 0.000116 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.255 | +| time/ | | +| fps | 1362 | +| iterations | 1963 | +| time_elapsed | 2950 | +| total_timesteps | 4020224 | +| train/ | | +| approx_kl | 0.028154887 | +| clip_fraction | 0.38 | +| clip_range | 0.0998 | +| entropy_loss | -7.25 | +| explained_variance | -0.0801 | +| learning_rate | 0.00012 | +| loss | -0.0491 | +| n_updates | 7848 | +| policy_gradient_loss | -0.0271 | +| value_loss | 0.000331 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.26 | +| time/ | | +| fps | 1362 | +| iterations | 1964 | +| time_elapsed | 2952 | +| total_timesteps | 4022272 | +| train/ | | +| approx_kl | 0.035033025 | +| clip_fraction | 0.393 | +| clip_range | 0.0997 | +| entropy_loss | -7.31 | +| explained_variance | -0.0707 | +| learning_rate | 0.00012 | +| loss | -0.0459 | +| n_updates | 7852 | +| policy_gradient_loss | -0.0301 | +| value_loss | 0.000229 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.257 | +| time/ | | +| fps | 1362 | +| iterations | 1965 | +| time_elapsed | 2953 | +| total_timesteps | 4024320 | +| train/ | | +| approx_kl | 0.027434563 | +| clip_fraction | 0.378 | +| clip_range | 0.0997 | +| entropy_loss | -7.52 | +| explained_variance | -0.0504 | +| learning_rate | 0.00012 | +| loss | -0.0446 | +| n_updates | 7856 | +| policy_gradient_loss | -0.0306 | +| value_loss | 0.000259 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.264 | +| time/ | | +| fps | 1362 | +| iterations | 1966 | +| time_elapsed | 2955 | +| total_timesteps | 4026368 | +| train/ | | +| approx_kl | 0.032847665 | +| clip_fraction | 0.403 | +| clip_range | 0.0997 | +| entropy_loss | -7.43 | +| explained_variance | -0.037 | +| learning_rate | 0.00012 | +| loss | -0.0462 | +| n_updates | 7860 | +| policy_gradient_loss | -0.0316 | +| value_loss | 0.000314 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.259 | +| time/ | | +| fps | 1362 | +| iterations | 1967 | +| time_elapsed | 2956 | +| total_timesteps | 4028416 | +| train/ | | +| approx_kl | 0.032085992 | +| clip_fraction | 0.41 | +| clip_range | 0.0997 | +| entropy_loss | -7.36 | +| explained_variance | -0.0653 | +| learning_rate | 0.00012 | +| loss | -0.0388 | +| n_updates | 7864 | +| policy_gradient_loss | -0.03 | +| value_loss | 0.000411 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.259 | +| time/ | | +| fps | 1362 | +| iterations | 1968 | +| time_elapsed | 2958 | +| total_timesteps | 4030464 | +| train/ | | +| approx_kl | 0.03214754 | +| clip_fraction | 0.393 | +| clip_range | 0.0996 | +| entropy_loss | -7.42 | +| explained_variance | -0.182 | +| learning_rate | 0.00012 | +| loss | -0.0495 | +| n_updates | 7868 | +| policy_gradient_loss | -0.0336 | +| value_loss | 0.000206 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.262 | +| time/ | | +| fps | 1362 | +| iterations | 1969 | +| time_elapsed | 2959 | +| total_timesteps | 4032512 | +| train/ | | +| approx_kl | 0.025964964 | +| clip_fraction | 0.379 | +| clip_range | 0.0996 | +| entropy_loss | -7.43 | +| explained_variance | -0.123 | +| learning_rate | 0.00012 | +| loss | -0.052 | +| n_updates | 7872 | +| policy_gradient_loss | -0.0278 | +| value_loss | 0.000256 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.267 | +| time/ | | +| fps | 1362 | +| iterations | 1970 | +| time_elapsed | 2960 | +| total_timesteps | 4034560 | +| train/ | | +| approx_kl | 0.032974757 | +| clip_fraction | 0.444 | +| clip_range | 0.0996 | +| entropy_loss | -7.28 | +| explained_variance | -0.168 | +| learning_rate | 0.00012 | +| loss | -0.0546 | +| n_updates | 7876 | +| policy_gradient_loss | -0.0339 | +| value_loss | 0.000161 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.269 | +| time/ | | +| fps | 1362 | +| iterations | 1971 | +| time_elapsed | 2962 | +| total_timesteps | 4036608 | +| train/ | | +| approx_kl | 0.02785546 | +| clip_fraction | 0.402 | +| clip_range | 0.0996 | +| entropy_loss | -7.35 | +| explained_variance | -0.0822 | +| learning_rate | 0.00012 | +| loss | -0.0535 | +| n_updates | 7880 | +| policy_gradient_loss | -0.0283 | +| value_loss | 0.000202 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.264 | +| time/ | | +| fps | 1362 | +| iterations | 1972 | +| time_elapsed | 2963 | +| total_timesteps | 4038656 | +| train/ | | +| approx_kl | 0.025304336 | +| clip_fraction | 0.39 | +| clip_range | 0.0995 | +| entropy_loss | -7.48 | +| explained_variance | -0.0634 | +| learning_rate | 0.00012 | +| loss | -0.0424 | +| n_updates | 7884 | +| policy_gradient_loss | -0.0285 | +| value_loss | 0.000225 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.256 | +| time/ | | +| fps | 1362 | +| iterations | 1973 | +| time_elapsed | 2965 | +| total_timesteps | 4040704 | +| train/ | | +| approx_kl | 0.03342063 | +| clip_fraction | 0.381 | +| clip_range | 0.0995 | +| entropy_loss | -7.35 | +| explained_variance | -0.136 | +| learning_rate | 0.00012 | +| loss | -0.0524 | +| n_updates | 7888 | +| policy_gradient_loss | -0.0314 | +| value_loss | 0.000201 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.256 | +| time/ | | +| fps | 1362 | +| iterations | 1974 | +| time_elapsed | 2966 | +| total_timesteps | 4042752 | +| train/ | | +| approx_kl | 0.033773426 | +| clip_fraction | 0.402 | +| clip_range | 0.0995 | +| entropy_loss | -7.3 | +| explained_variance | -0.112 | +| learning_rate | 0.00012 | +| loss | -0.0442 | +| n_updates | 7892 | +| policy_gradient_loss | -0.0281 | +| value_loss | 0.000296 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.254 | +| time/ | | +| fps | 1362 | +| iterations | 1975 | +| time_elapsed | 2967 | +| total_timesteps | 4044800 | +| train/ | | +| approx_kl | 0.03535784 | +| clip_fraction | 0.419 | +| clip_range | 0.0995 | +| entropy_loss | -7.38 | +| explained_variance | -0.202 | +| learning_rate | 0.00012 | +| loss | -0.0561 | +| n_updates | 7896 | +| policy_gradient_loss | -0.0328 | +| value_loss | 0.000146 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.256 | +| time/ | | +| fps | 1362 | +| iterations | 1976 | +| time_elapsed | 2969 | +| total_timesteps | 4046848 | +| train/ | | +| approx_kl | 0.03416583 | +| clip_fraction | 0.422 | +| clip_range | 0.0994 | +| entropy_loss | -7.36 | +| explained_variance | -0.108 | +| learning_rate | 0.00012 | +| loss | -0.0522 | +| n_updates | 7900 | +| policy_gradient_loss | -0.0343 | +| value_loss | 0.000131 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.256 | +| time/ | | +| fps | 1362 | +| iterations | 1977 | +| time_elapsed | 2970 | +| total_timesteps | 4048896 | +| train/ | | +| approx_kl | 0.034000855 | +| clip_fraction | 0.421 | +| clip_range | 0.0994 | +| entropy_loss | -7.26 | +| explained_variance | -0.105 | +| learning_rate | 0.00012 | +| loss | -0.0533 | +| n_updates | 7904 | +| policy_gradient_loss | -0.0332 | +| value_loss | 0.000112 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.256 | +| time/ | | +| fps | 1362 | +| iterations | 1978 | +| time_elapsed | 2972 | +| total_timesteps | 4050944 | +| train/ | | +| approx_kl | 0.03127917 | +| clip_fraction | 0.4 | +| clip_range | 0.0994 | +| entropy_loss | -7.34 | +| explained_variance | -0.211 | +| learning_rate | 0.00012 | +| loss | -0.0504 | +| n_updates | 7908 | +| policy_gradient_loss | -0.0296 | +| value_loss | 0.000142 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.258 | +| time/ | | +| fps | 1363 | +| iterations | 1979 | +| time_elapsed | 2973 | +| total_timesteps | 4052992 | +| train/ | | +| approx_kl | 0.02714765 | +| clip_fraction | 0.412 | +| clip_range | 0.0994 | +| entropy_loss | -7.32 | +| explained_variance | -0.111 | +| learning_rate | 0.00012 | +| loss | -0.0462 | +| n_updates | 7912 | +| policy_gradient_loss | -0.0277 | +| value_loss | 0.000229 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.264 | +| time/ | | +| fps | 1363 | +| iterations | 1980 | +| time_elapsed | 2974 | +| total_timesteps | 4055040 | +| train/ | | +| approx_kl | 0.030637406 | +| clip_fraction | 0.411 | +| clip_range | 0.0993 | +| entropy_loss | -7.26 | +| explained_variance | 0.0144 | +| learning_rate | 0.00012 | +| loss | -0.0543 | +| n_updates | 7916 | +| policy_gradient_loss | -0.0304 | +| value_loss | 0.000243 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.265 | +| time/ | | +| fps | 1363 | +| iterations | 1981 | +| time_elapsed | 2976 | +| total_timesteps | 4057088 | +| train/ | | +| approx_kl | 0.027903296 | +| clip_fraction | 0.386 | +| clip_range | 0.0993 | +| entropy_loss | -7.46 | +| explained_variance | -0.0108 | +| learning_rate | 0.00012 | +| loss | -0.0483 | +| n_updates | 7920 | +| policy_gradient_loss | -0.0283 | +| value_loss | 0.000314 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.265 | +| time/ | | +| fps | 1363 | +| iterations | 1982 | +| time_elapsed | 2977 | +| total_timesteps | 4059136 | +| train/ | | +| approx_kl | 0.03253617 | +| clip_fraction | 0.406 | +| clip_range | 0.0993 | +| entropy_loss | -7.36 | +| explained_variance | -0.0452 | +| learning_rate | 0.00012 | +| loss | -0.0536 | +| n_updates | 7924 | +| policy_gradient_loss | -0.0325 | +| value_loss | 0.00022 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.26 | +| time/ | | +| fps | 1363 | +| iterations | 1983 | +| time_elapsed | 2979 | +| total_timesteps | 4061184 | +| train/ | | +| approx_kl | 0.028859634 | +| clip_fraction | 0.403 | +| clip_range | 0.0993 | +| entropy_loss | -7.48 | +| explained_variance | -0.245 | +| learning_rate | 0.00012 | +| loss | -0.0546 | +| n_updates | 7928 | +| policy_gradient_loss | -0.0309 | +| value_loss | 0.000201 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.269 | +| time/ | | +| fps | 1363 | +| iterations | 1984 | +| time_elapsed | 2980 | +| total_timesteps | 4063232 | +| train/ | | +| approx_kl | 0.029313866 | +| clip_fraction | 0.396 | +| clip_range | 0.0992 | +| entropy_loss | -7.39 | +| explained_variance | 0.0899 | +| learning_rate | 0.00012 | +| loss | -0.0466 | +| n_updates | 7932 | +| policy_gradient_loss | -0.0313 | +| value_loss | 0.000142 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.257 | +| time/ | | +| fps | 1363 | +| iterations | 1985 | +| time_elapsed | 2982 | +| total_timesteps | 4065280 | +| train/ | | +| approx_kl | 0.03311809 | +| clip_fraction | 0.388 | +| clip_range | 0.0992 | +| entropy_loss | -7.23 | +| explained_variance | -0.0735 | +| learning_rate | 0.00012 | +| loss | -0.0388 | +| n_updates | 7936 | +| policy_gradient_loss | -0.0265 | +| value_loss | 0.000348 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.257 | +| time/ | | +| fps | 1363 | +| iterations | 1986 | +| time_elapsed | 2983 | +| total_timesteps | 4067328 | +| train/ | | +| approx_kl | 0.028348967 | +| clip_fraction | 0.42 | +| clip_range | 0.0992 | +| entropy_loss | -7.26 | +| explained_variance | -0.17 | +| learning_rate | 0.00012 | +| loss | -0.0559 | +| n_updates | 7940 | +| policy_gradient_loss | -0.0313 | +| value_loss | 0.000171 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.257 | +| time/ | | +| fps | 1363 | +| iterations | 1987 | +| time_elapsed | 2984 | +| total_timesteps | 4069376 | +| train/ | | +| approx_kl | 0.033532158 | +| clip_fraction | 0.424 | +| clip_range | 0.0992 | +| entropy_loss | -7.34 | +| explained_variance | -0.352 | +| learning_rate | 0.000119 | +| loss | -0.0569 | +| n_updates | 7944 | +| policy_gradient_loss | -0.0369 | +| value_loss | 9.65e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.257 | +| time/ | | +| fps | 1363 | +| iterations | 1988 | +| time_elapsed | 2986 | +| total_timesteps | 4071424 | +| train/ | | +| approx_kl | 0.031609762 | +| clip_fraction | 0.419 | +| clip_range | 0.0991 | +| entropy_loss | -7.39 | +| explained_variance | -0.22 | +| learning_rate | 0.000119 | +| loss | -0.0529 | +| n_updates | 7948 | +| policy_gradient_loss | -0.0299 | +| value_loss | 0.000147 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.26 | +| time/ | | +| fps | 1363 | +| iterations | 1989 | +| time_elapsed | 2987 | +| total_timesteps | 4073472 | +| train/ | | +| approx_kl | 0.031727128 | +| clip_fraction | 0.406 | +| clip_range | 0.0991 | +| entropy_loss | -7.39 | +| explained_variance | 0.0279 | +| learning_rate | 0.000119 | +| loss | -0.0478 | +| n_updates | 7952 | +| policy_gradient_loss | -0.028 | +| value_loss | 0.000162 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.263 | +| time/ | | +| fps | 1363 | +| iterations | 1990 | +| time_elapsed | 2989 | +| total_timesteps | 4075520 | +| train/ | | +| approx_kl | 0.029184567 | +| clip_fraction | 0.405 | +| clip_range | 0.0991 | +| entropy_loss | -7.37 | +| explained_variance | -0.275 | +| learning_rate | 0.000119 | +| loss | -0.0437 | +| n_updates | 7956 | +| policy_gradient_loss | -0.0299 | +| value_loss | 0.000146 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.263 | +| time/ | | +| fps | 1363 | +| iterations | 1991 | +| time_elapsed | 2990 | +| total_timesteps | 4077568 | +| train/ | | +| approx_kl | 0.033368863 | +| clip_fraction | 0.41 | +| clip_range | 0.0991 | +| entropy_loss | -7.47 | +| explained_variance | -0.171 | +| learning_rate | 0.000119 | +| loss | -0.0495 | +| n_updates | 7960 | +| policy_gradient_loss | -0.0291 | +| value_loss | 0.000137 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.26 | +| time/ | | +| fps | 1363 | +| iterations | 1992 | +| time_elapsed | 2992 | +| total_timesteps | 4079616 | +| train/ | | +| approx_kl | 0.028207976 | +| clip_fraction | 0.379 | +| clip_range | 0.099 | +| entropy_loss | -7.3 | +| explained_variance | -0.194 | +| learning_rate | 0.000119 | +| loss | -0.0447 | +| n_updates | 7964 | +| policy_gradient_loss | -0.0278 | +| value_loss | 0.000177 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.261 | +| time/ | | +| fps | 1363 | +| iterations | 1993 | +| time_elapsed | 2993 | +| total_timesteps | 4081664 | +| train/ | | +| approx_kl | 0.027618969 | +| clip_fraction | 0.376 | +| clip_range | 0.099 | +| entropy_loss | -7.36 | +| explained_variance | -0.00889 | +| learning_rate | 0.000119 | +| loss | -0.0434 | +| n_updates | 7968 | +| policy_gradient_loss | -0.0273 | +| value_loss | 0.000173 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.261 | +| time/ | | +| fps | 1363 | +| iterations | 1994 | +| time_elapsed | 2995 | +| total_timesteps | 4083712 | +| train/ | | +| approx_kl | 0.03285196 | +| clip_fraction | 0.421 | +| clip_range | 0.099 | +| entropy_loss | -7.25 | +| explained_variance | 0.0193 | +| learning_rate | 0.000119 | +| loss | -0.0456 | +| n_updates | 7972 | +| policy_gradient_loss | -0.0298 | +| value_loss | 0.000193 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.261 | +| time/ | | +| fps | 1363 | +| iterations | 1995 | +| time_elapsed | 2996 | +| total_timesteps | 4085760 | +| train/ | | +| approx_kl | 0.037040442 | +| clip_fraction | 0.416 | +| clip_range | 0.099 | +| entropy_loss | -7.37 | +| explained_variance | -0.0764 | +| learning_rate | 0.000119 | +| loss | -0.0521 | +| n_updates | 7976 | +| policy_gradient_loss | -0.0316 | +| value_loss | 0.000191 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.261 | +| time/ | | +| fps | 1363 | +| iterations | 1996 | +| time_elapsed | 2997 | +| total_timesteps | 4087808 | +| train/ | | +| approx_kl | 0.03304483 | +| clip_fraction | 0.391 | +| clip_range | 0.0989 | +| entropy_loss | -7.31 | +| explained_variance | -0.302 | +| learning_rate | 0.000119 | +| loss | -0.0469 | +| n_updates | 7980 | +| policy_gradient_loss | -0.0294 | +| value_loss | 0.000164 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.265 | +| time/ | | +| fps | 1363 | +| iterations | 1997 | +| time_elapsed | 2999 | +| total_timesteps | 4089856 | +| train/ | | +| approx_kl | 0.032152064 | +| clip_fraction | 0.419 | +| clip_range | 0.0989 | +| entropy_loss | -7.44 | +| explained_variance | -0.115 | +| learning_rate | 0.000119 | +| loss | -0.049 | +| n_updates | 7984 | +| policy_gradient_loss | -0.031 | +| value_loss | 0.000237 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.27 | +| time/ | | +| fps | 1363 | +| iterations | 1998 | +| time_elapsed | 3000 | +| total_timesteps | 4091904 | +| train/ | | +| approx_kl | 0.03147518 | +| clip_fraction | 0.387 | +| clip_range | 0.0989 | +| entropy_loss | -7.45 | +| explained_variance | -0.122 | +| learning_rate | 0.000119 | +| loss | -0.0437 | +| n_updates | 7988 | +| policy_gradient_loss | -0.0296 | +| value_loss | 0.000153 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.269 | +| time/ | | +| fps | 1363 | +| iterations | 1999 | +| time_elapsed | 3002 | +| total_timesteps | 4093952 | +| train/ | | +| approx_kl | 0.026651584 | +| clip_fraction | 0.387 | +| clip_range | 0.0989 | +| entropy_loss | -7.34 | +| explained_variance | -0.111 | +| learning_rate | 0.000119 | +| loss | -0.0524 | +| n_updates | 7992 | +| policy_gradient_loss | -0.0253 | +| value_loss | 0.000214 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.269 | +| time/ | | +| fps | 1363 | +| iterations | 2000 | +| time_elapsed | 3003 | +| total_timesteps | 4096000 | +| train/ | | +| approx_kl | 0.027806886 | +| clip_fraction | 0.396 | +| clip_range | 0.0988 | +| entropy_loss | -7.46 | +| explained_variance | -0.0428 | +| learning_rate | 0.000119 | +| loss | -0.053 | +| n_updates | 7996 | +| policy_gradient_loss | -0.0289 | +| value_loss | 0.000176 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.269 | +| time/ | | +| fps | 1363 | +| iterations | 2001 | +| time_elapsed | 3005 | +| total_timesteps | 4098048 | +| train/ | | +| approx_kl | 0.033957727 | +| clip_fraction | 0.412 | +| clip_range | 0.0988 | +| entropy_loss | -7.37 | +| explained_variance | -0.232 | +| learning_rate | 0.000119 | +| loss | -0.0515 | +| n_updates | 8000 | +| policy_gradient_loss | -0.0327 | +| value_loss | 9.39e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.266 | +| time/ | | +| fps | 1363 | +| iterations | 2002 | +| time_elapsed | 3006 | +| total_timesteps | 4100096 | +| train/ | | +| approx_kl | 0.030189829 | +| clip_fraction | 0.398 | +| clip_range | 0.0988 | +| entropy_loss | -7.5 | +| explained_variance | -0.203 | +| learning_rate | 0.000119 | +| loss | -0.0464 | +| n_updates | 8004 | +| policy_gradient_loss | -0.0291 | +| value_loss | 0.000187 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.273 | +| time/ | | +| fps | 1363 | +| iterations | 2003 | +| time_elapsed | 3008 | +| total_timesteps | 4102144 | +| train/ | | +| approx_kl | 0.028951943 | +| clip_fraction | 0.407 | +| clip_range | 0.0987 | +| entropy_loss | -7.36 | +| explained_variance | -0.139 | +| learning_rate | 0.000119 | +| loss | -0.0447 | +| n_updates | 8008 | +| policy_gradient_loss | -0.0265 | +| value_loss | 0.000213 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.277 | +| time/ | | +| fps | 1363 | +| iterations | 2004 | +| time_elapsed | 3009 | +| total_timesteps | 4104192 | +| train/ | | +| approx_kl | 0.031338032 | +| clip_fraction | 0.409 | +| clip_range | 0.0987 | +| entropy_loss | -7.35 | +| explained_variance | -0.00793 | +| learning_rate | 0.000119 | +| loss | -0.0504 | +| n_updates | 8012 | +| policy_gradient_loss | -0.0321 | +| value_loss | 0.000165 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.278 | +| time/ | | +| fps | 1363 | +| iterations | 2005 | +| time_elapsed | 3010 | +| total_timesteps | 4106240 | +| train/ | | +| approx_kl | 0.029869085 | +| clip_fraction | 0.388 | +| clip_range | 0.0987 | +| entropy_loss | -7.22 | +| explained_variance | -0.104 | +| learning_rate | 0.000119 | +| loss | -0.0445 | +| n_updates | 8016 | +| policy_gradient_loss | -0.0311 | +| value_loss | 0.000149 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 1363 | +| iterations | 2006 | +| time_elapsed | 3012 | +| total_timesteps | 4108288 | +| train/ | | +| approx_kl | 0.028007578 | +| clip_fraction | 0.377 | +| clip_range | 0.0987 | +| entropy_loss | -7.35 | +| explained_variance | -0.079 | +| learning_rate | 0.000119 | +| loss | -0.0511 | +| n_updates | 8020 | +| policy_gradient_loss | -0.0278 | +| value_loss | 0.000211 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 1363 | +| iterations | 2007 | +| time_elapsed | 3013 | +| total_timesteps | 4110336 | +| train/ | | +| approx_kl | 0.028692145 | +| clip_fraction | 0.378 | +| clip_range | 0.0986 | +| entropy_loss | -7.46 | +| explained_variance | 0.00674 | +| learning_rate | 0.000119 | +| loss | -0.0412 | +| n_updates | 8024 | +| policy_gradient_loss | -0.0277 | +| value_loss | 0.000241 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 1363 | +| iterations | 2008 | +| time_elapsed | 3015 | +| total_timesteps | 4112384 | +| train/ | | +| approx_kl | 0.03222931 | +| clip_fraction | 0.401 | +| clip_range | 0.0986 | +| entropy_loss | -7.55 | +| explained_variance | -0.301 | +| learning_rate | 0.000119 | +| loss | -0.054 | +| n_updates | 8028 | +| policy_gradient_loss | -0.0311 | +| value_loss | 0.000175 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 1363 | +| iterations | 2009 | +| time_elapsed | 3016 | +| total_timesteps | 4114432 | +| train/ | | +| approx_kl | 0.028843576 | +| clip_fraction | 0.407 | +| clip_range | 0.0986 | +| entropy_loss | -7.5 | +| explained_variance | -0.243 | +| learning_rate | 0.000119 | +| loss | -0.0458 | +| n_updates | 8032 | +| policy_gradient_loss | -0.0306 | +| value_loss | 0.000157 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.274 | +| time/ | | +| fps | 1363 | +| iterations | 2010 | +| time_elapsed | 3018 | +| total_timesteps | 4116480 | +| train/ | | +| approx_kl | 0.031565502 | +| clip_fraction | 0.406 | +| clip_range | 0.0986 | +| entropy_loss | -7.53 | +| explained_variance | -0.342 | +| learning_rate | 0.000119 | +| loss | -0.046 | +| n_updates | 8036 | +| policy_gradient_loss | -0.0315 | +| value_loss | 0.000104 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.28 | +| time/ | | +| fps | 1363 | +| iterations | 2011 | +| time_elapsed | 3019 | +| total_timesteps | 4118528 | +| train/ | | +| approx_kl | 0.029830966 | +| clip_fraction | 0.393 | +| clip_range | 0.0985 | +| entropy_loss | -7.4 | +| explained_variance | -0.0727 | +| learning_rate | 0.000118 | +| loss | -0.0429 | +| n_updates | 8040 | +| policy_gradient_loss | -0.0255 | +| value_loss | 0.000145 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.277 | +| time/ | | +| fps | 1363 | +| iterations | 2012 | +| time_elapsed | 3020 | +| total_timesteps | 4120576 | +| train/ | | +| approx_kl | 0.026615456 | +| clip_fraction | 0.373 | +| clip_range | 0.0985 | +| entropy_loss | -7.29 | +| explained_variance | -0.0962 | +| learning_rate | 0.000118 | +| loss | -0.0499 | +| n_updates | 8044 | +| policy_gradient_loss | -0.0274 | +| value_loss | 0.000212 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.283 | +| time/ | | +| fps | 1364 | +| iterations | 2013 | +| time_elapsed | 3022 | +| total_timesteps | 4122624 | +| train/ | | +| approx_kl | 0.03335806 | +| clip_fraction | 0.411 | +| clip_range | 0.0985 | +| entropy_loss | -7.25 | +| explained_variance | -0.407 | +| learning_rate | 0.000118 | +| loss | -0.0532 | +| n_updates | 8048 | +| policy_gradient_loss | -0.0324 | +| value_loss | 8.82e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.283 | +| time/ | | +| fps | 1363 | +| iterations | 2014 | +| time_elapsed | 3023 | +| total_timesteps | 4124672 | +| train/ | | +| approx_kl | 0.034828085 | +| clip_fraction | 0.372 | +| clip_range | 0.0985 | +| entropy_loss | -7.18 | +| explained_variance | -0.0651 | +| learning_rate | 0.000118 | +| loss | -0.0444 | +| n_updates | 8052 | +| policy_gradient_loss | -0.0268 | +| value_loss | 0.000278 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.284 | +| time/ | | +| fps | 1364 | +| iterations | 2015 | +| time_elapsed | 3025 | +| total_timesteps | 4126720 | +| train/ | | +| approx_kl | 0.03440637 | +| clip_fraction | 0.427 | +| clip_range | 0.0984 | +| entropy_loss | -7.36 | +| explained_variance | -0.761 | +| learning_rate | 0.000118 | +| loss | -0.0647 | +| n_updates | 8056 | +| policy_gradient_loss | -0.037 | +| value_loss | 7.79e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.288 | +| time/ | | +| fps | 1364 | +| iterations | 2016 | +| time_elapsed | 3026 | +| total_timesteps | 4128768 | +| train/ | | +| approx_kl | 0.038378023 | +| clip_fraction | 0.424 | +| clip_range | 0.0984 | +| entropy_loss | -7.38 | +| explained_variance | -0.0788 | +| learning_rate | 0.000118 | +| loss | -0.0568 | +| n_updates | 8060 | +| policy_gradient_loss | -0.0333 | +| value_loss | 8.3e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.289 | +| time/ | | +| fps | 1364 | +| iterations | 2017 | +| time_elapsed | 3028 | +| total_timesteps | 4130816 | +| train/ | | +| approx_kl | 0.029563643 | +| clip_fraction | 0.379 | +| clip_range | 0.0984 | +| entropy_loss | -7.34 | +| explained_variance | -0.107 | +| learning_rate | 0.000118 | +| loss | -0.048 | +| n_updates | 8064 | +| policy_gradient_loss | -0.0256 | +| value_loss | 0.000164 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.294 | +| time/ | | +| fps | 1364 | +| iterations | 2018 | +| time_elapsed | 3029 | +| total_timesteps | 4132864 | +| train/ | | +| approx_kl | 0.027388373 | +| clip_fraction | 0.384 | +| clip_range | 0.0984 | +| entropy_loss | -7.24 | +| explained_variance | -0.358 | +| learning_rate | 0.000118 | +| loss | -0.0398 | +| n_updates | 8068 | +| policy_gradient_loss | -0.0271 | +| value_loss | 0.000122 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.292 | +| time/ | | +| fps | 1364 | +| iterations | 2019 | +| time_elapsed | 3031 | +| total_timesteps | 4134912 | +| train/ | | +| approx_kl | 0.032942064 | +| clip_fraction | 0.397 | +| clip_range | 0.0983 | +| entropy_loss | -7.25 | +| explained_variance | -0.252 | +| learning_rate | 0.000118 | +| loss | -0.045 | +| n_updates | 8072 | +| policy_gradient_loss | -0.0305 | +| value_loss | 0.000118 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.292 | +| time/ | | +| fps | 1364 | +| iterations | 2020 | +| time_elapsed | 3032 | +| total_timesteps | 4136960 | +| train/ | | +| approx_kl | 0.033169165 | +| clip_fraction | 0.388 | +| clip_range | 0.0983 | +| entropy_loss | -7.4 | +| explained_variance | -0.0808 | +| learning_rate | 0.000118 | +| loss | -0.0475 | +| n_updates | 8076 | +| policy_gradient_loss | -0.0304 | +| value_loss | 0.000196 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.292 | +| time/ | | +| fps | 1364 | +| iterations | 2021 | +| time_elapsed | 3034 | +| total_timesteps | 4139008 | +| train/ | | +| approx_kl | 0.029525738 | +| clip_fraction | 0.41 | +| clip_range | 0.0983 | +| entropy_loss | -7.4 | +| explained_variance | -0.304 | +| learning_rate | 0.000118 | +| loss | -0.0415 | +| n_updates | 8080 | +| policy_gradient_loss | -0.0289 | +| value_loss | 0.000181 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.285 | +| time/ | | +| fps | 1364 | +| iterations | 2022 | +| time_elapsed | 3035 | +| total_timesteps | 4141056 | +| train/ | | +| approx_kl | 0.032276556 | +| clip_fraction | 0.406 | +| clip_range | 0.0983 | +| entropy_loss | -7.49 | +| explained_variance | -0.138 | +| learning_rate | 0.000118 | +| loss | -0.0488 | +| n_updates | 8084 | +| policy_gradient_loss | -0.029 | +| value_loss | 0.000163 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 1364 | +| iterations | 2023 | +| time_elapsed | 3036 | +| total_timesteps | 4143104 | +| train/ | | +| approx_kl | 0.029748946 | +| clip_fraction | 0.386 | +| clip_range | 0.0982 | +| entropy_loss | -7.34 | +| explained_variance | -0.309 | +| learning_rate | 0.000118 | +| loss | -0.0487 | +| n_updates | 8088 | +| policy_gradient_loss | -0.0309 | +| value_loss | 9.69e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.281 | +| time/ | | +| fps | 1364 | +| iterations | 2024 | +| time_elapsed | 3038 | +| total_timesteps | 4145152 | +| train/ | | +| approx_kl | 0.033792455 | +| clip_fraction | 0.399 | +| clip_range | 0.0982 | +| entropy_loss | -7.25 | +| explained_variance | 0.0252 | +| learning_rate | 0.000118 | +| loss | -0.0477 | +| n_updates | 8092 | +| policy_gradient_loss | -0.0284 | +| value_loss | 0.000104 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.277 | +| time/ | | +| fps | 1364 | +| iterations | 2025 | +| time_elapsed | 3039 | +| total_timesteps | 4147200 | +| train/ | | +| approx_kl | 0.029307174 | +| clip_fraction | 0.419 | +| clip_range | 0.0982 | +| entropy_loss | -7.24 | +| explained_variance | -0.131 | +| learning_rate | 0.000118 | +| loss | -0.0564 | +| n_updates | 8096 | +| policy_gradient_loss | -0.0287 | +| value_loss | 8.49e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.271 | +| time/ | | +| fps | 1364 | +| iterations | 2026 | +| time_elapsed | 3041 | +| total_timesteps | 4149248 | +| train/ | | +| approx_kl | 0.033033215 | +| clip_fraction | 0.407 | +| clip_range | 0.0982 | +| entropy_loss | -7.31 | +| explained_variance | -0.197 | +| learning_rate | 0.000118 | +| loss | -0.0459 | +| n_updates | 8100 | +| policy_gradient_loss | -0.0293 | +| value_loss | 0.00011 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.262 | +| time/ | | +| fps | 1364 | +| iterations | 2027 | +| time_elapsed | 3042 | +| total_timesteps | 4151296 | +| train/ | | +| approx_kl | 0.02793952 | +| clip_fraction | 0.418 | +| clip_range | 0.0981 | +| entropy_loss | -7.2 | +| explained_variance | -0.0961 | +| learning_rate | 0.000118 | +| loss | -0.0459 | +| n_updates | 8104 | +| policy_gradient_loss | -0.0308 | +| value_loss | 0.000126 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.262 | +| time/ | | +| fps | 1364 | +| iterations | 2028 | +| time_elapsed | 3043 | +| total_timesteps | 4153344 | +| train/ | | +| approx_kl | 0.030799894 | +| clip_fraction | 0.394 | +| clip_range | 0.0981 | +| entropy_loss | -7.05 | +| explained_variance | -0.0254 | +| learning_rate | 0.000118 | +| loss | -0.0431 | +| n_updates | 8108 | +| policy_gradient_loss | -0.0265 | +| value_loss | 0.000229 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.268 | +| time/ | | +| fps | 1364 | +| iterations | 2029 | +| time_elapsed | 3045 | +| total_timesteps | 4155392 | +| train/ | | +| approx_kl | 0.033225197 | +| clip_fraction | 0.392 | +| clip_range | 0.0981 | +| entropy_loss | -7.45 | +| explained_variance | -0.15 | +| learning_rate | 0.000118 | +| loss | -0.0527 | +| n_updates | 8112 | +| policy_gradient_loss | -0.0308 | +| value_loss | 0.000194 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.268 | +| time/ | | +| fps | 1364 | +| iterations | 2030 | +| time_elapsed | 3046 | +| total_timesteps | 4157440 | +| train/ | | +| approx_kl | 0.027557503 | +| clip_fraction | 0.372 | +| clip_range | 0.0981 | +| entropy_loss | -7.42 | +| explained_variance | -0.0378 | +| learning_rate | 0.000118 | +| loss | -0.0493 | +| n_updates | 8116 | +| policy_gradient_loss | -0.0286 | +| value_loss | 0.000206 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.272 | +| time/ | | +| fps | 1364 | +| iterations | 2031 | +| time_elapsed | 3048 | +| total_timesteps | 4159488 | +| train/ | | +| approx_kl | 0.03342568 | +| clip_fraction | 0.402 | +| clip_range | 0.098 | +| entropy_loss | -7.5 | +| explained_variance | -0.208 | +| learning_rate | 0.000118 | +| loss | -0.0478 | +| n_updates | 8120 | +| policy_gradient_loss | -0.0307 | +| value_loss | 0.000162 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.27 | +| time/ | | +| fps | 1364 | +| iterations | 2032 | +| time_elapsed | 3049 | +| total_timesteps | 4161536 | +| train/ | | +| approx_kl | 0.035855275 | +| clip_fraction | 0.389 | +| clip_range | 0.098 | +| entropy_loss | -7.37 | +| explained_variance | -0.0573 | +| learning_rate | 0.000118 | +| loss | -0.0447 | +| n_updates | 8124 | +| policy_gradient_loss | -0.0263 | +| value_loss | 0.000295 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 1364 | +| iterations | 2033 | +| time_elapsed | 3050 | +| total_timesteps | 4163584 | +| train/ | | +| approx_kl | 0.030919284 | +| clip_fraction | 0.419 | +| clip_range | 0.098 | +| entropy_loss | -7.44 | +| explained_variance | -0.316 | +| learning_rate | 0.000118 | +| loss | -0.0391 | +| n_updates | 8128 | +| policy_gradient_loss | -0.0332 | +| value_loss | 0.000132 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.269 | +| time/ | | +| fps | 1364 | +| iterations | 2034 | +| time_elapsed | 3052 | +| total_timesteps | 4165632 | +| train/ | | +| approx_kl | 0.02730855 | +| clip_fraction | 0.383 | +| clip_range | 0.098 | +| entropy_loss | -7.37 | +| explained_variance | -0.00777 | +| learning_rate | 0.000118 | +| loss | -0.0491 | +| n_updates | 8132 | +| policy_gradient_loss | -0.0292 | +| value_loss | 0.000215 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 1364 | +| iterations | 2035 | +| time_elapsed | 3053 | +| total_timesteps | 4167680 | +| train/ | | +| approx_kl | 0.026322724 | +| clip_fraction | 0.377 | +| clip_range | 0.0979 | +| entropy_loss | -7.18 | +| explained_variance | 0.0257 | +| learning_rate | 0.000118 | +| loss | -0.0471 | +| n_updates | 8136 | +| policy_gradient_loss | -0.0259 | +| value_loss | 0.000199 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.29 | +| time/ | | +| fps | 1364 | +| iterations | 2036 | +| time_elapsed | 3055 | +| total_timesteps | 4169728 | +| train/ | | +| approx_kl | 0.027612602 | +| clip_fraction | 0.395 | +| clip_range | 0.0979 | +| entropy_loss | -7.27 | +| explained_variance | 0.00482 | +| learning_rate | 0.000117 | +| loss | -0.0375 | +| n_updates | 8140 | +| policy_gradient_loss | -0.023 | +| value_loss | 0.000396 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.29 | +| time/ | | +| fps | 1364 | +| iterations | 2037 | +| time_elapsed | 3056 | +| total_timesteps | 4171776 | +| train/ | | +| approx_kl | 0.02681639 | +| clip_fraction | 0.381 | +| clip_range | 0.0979 | +| entropy_loss | -7.21 | +| explained_variance | -0.155 | +| learning_rate | 0.000117 | +| loss | -0.0425 | +| n_updates | 8144 | +| policy_gradient_loss | -0.0275 | +| value_loss | 0.000262 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.29 | +| time/ | | +| fps | 1364 | +| iterations | 2038 | +| time_elapsed | 3058 | +| total_timesteps | 4173824 | +| train/ | | +| approx_kl | 0.02872114 | +| clip_fraction | 0.427 | +| clip_range | 0.0979 | +| entropy_loss | -7.37 | +| explained_variance | -0.474 | +| learning_rate | 0.000117 | +| loss | -0.0512 | +| n_updates | 8148 | +| policy_gradient_loss | -0.0327 | +| value_loss | 0.000154 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.284 | +| time/ | | +| fps | 1364 | +| iterations | 2039 | +| time_elapsed | 3059 | +| total_timesteps | 4175872 | +| train/ | | +| approx_kl | 0.03453882 | +| clip_fraction | 0.431 | +| clip_range | 0.0978 | +| entropy_loss | -7.38 | +| explained_variance | -0.258 | +| learning_rate | 0.000117 | +| loss | -0.0543 | +| n_updates | 8152 | +| policy_gradient_loss | -0.0326 | +| value_loss | 0.00012 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.288 | +| time/ | | +| fps | 1364 | +| iterations | 2040 | +| time_elapsed | 3061 | +| total_timesteps | 4177920 | +| train/ | | +| approx_kl | 0.03413566 | +| clip_fraction | 0.415 | +| clip_range | 0.0978 | +| entropy_loss | -7.33 | +| explained_variance | -0.268 | +| learning_rate | 0.000117 | +| loss | -0.0571 | +| n_updates | 8156 | +| policy_gradient_loss | -0.0339 | +| value_loss | 0.000114 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.284 | +| time/ | | +| fps | 1364 | +| iterations | 2041 | +| time_elapsed | 3062 | +| total_timesteps | 4179968 | +| train/ | | +| approx_kl | 0.029645085 | +| clip_fraction | 0.427 | +| clip_range | 0.0978 | +| entropy_loss | -7.25 | +| explained_variance | -0.0892 | +| learning_rate | 0.000117 | +| loss | -0.0485 | +| n_updates | 8160 | +| policy_gradient_loss | -0.0315 | +| value_loss | 0.000135 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.283 | +| time/ | | +| fps | 1364 | +| iterations | 2042 | +| time_elapsed | 3063 | +| total_timesteps | 4182016 | +| train/ | | +| approx_kl | 0.029246042 | +| clip_fraction | 0.384 | +| clip_range | 0.0978 | +| entropy_loss | -7.44 | +| explained_variance | -0.0818 | +| learning_rate | 0.000117 | +| loss | -0.0421 | +| n_updates | 8164 | +| policy_gradient_loss | -0.0263 | +| value_loss | 0.000168 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.272 | +| time/ | | +| fps | 1364 | +| iterations | 2043 | +| time_elapsed | 3065 | +| total_timesteps | 4184064 | +| train/ | | +| approx_kl | 0.027613843 | +| clip_fraction | 0.388 | +| clip_range | 0.0977 | +| entropy_loss | -7.33 | +| explained_variance | -0.152 | +| learning_rate | 0.000117 | +| loss | -0.0458 | +| n_updates | 8168 | +| policy_gradient_loss | -0.0295 | +| value_loss | 0.000234 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.274 | +| time/ | | +| fps | 1364 | +| iterations | 2044 | +| time_elapsed | 3066 | +| total_timesteps | 4186112 | +| train/ | | +| approx_kl | 0.03007942 | +| clip_fraction | 0.409 | +| clip_range | 0.0977 | +| entropy_loss | -7.24 | +| explained_variance | -0.147 | +| learning_rate | 0.000117 | +| loss | -0.0572 | +| n_updates | 8172 | +| policy_gradient_loss | -0.0314 | +| value_loss | 0.000126 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.274 | +| time/ | | +| fps | 1365 | +| iterations | 2045 | +| time_elapsed | 3068 | +| total_timesteps | 4188160 | +| train/ | | +| approx_kl | 0.02559101 | +| clip_fraction | 0.348 | +| clip_range | 0.0977 | +| entropy_loss | -7.33 | +| explained_variance | -0.0915 | +| learning_rate | 0.000117 | +| loss | -0.026 | +| n_updates | 8176 | +| policy_gradient_loss | -0.022 | +| value_loss | 0.000342 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.272 | +| time/ | | +| fps | 1365 | +| iterations | 2046 | +| time_elapsed | 3069 | +| total_timesteps | 4190208 | +| train/ | | +| approx_kl | 0.029520044 | +| clip_fraction | 0.38 | +| clip_range | 0.0976 | +| entropy_loss | -7.51 | +| explained_variance | -0.187 | +| learning_rate | 0.000117 | +| loss | -0.0471 | +| n_updates | 8180 | +| policy_gradient_loss | -0.029 | +| value_loss | 0.000218 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.27 | +| time/ | | +| fps | 1365 | +| iterations | 2047 | +| time_elapsed | 3071 | +| total_timesteps | 4192256 | +| train/ | | +| approx_kl | 0.024210893 | +| clip_fraction | 0.406 | +| clip_range | 0.0976 | +| entropy_loss | -7.44 | +| explained_variance | -0.443 | +| learning_rate | 0.000117 | +| loss | -0.0516 | +| n_updates | 8184 | +| policy_gradient_loss | -0.0308 | +| value_loss | 0.000112 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.266 | +| time/ | | +| fps | 1365 | +| iterations | 2048 | +| time_elapsed | 3072 | +| total_timesteps | 4194304 | +| train/ | | +| approx_kl | 0.03156279 | +| clip_fraction | 0.417 | +| clip_range | 0.0976 | +| entropy_loss | -7.34 | +| explained_variance | -0.206 | +| learning_rate | 0.000117 | +| loss | -0.0462 | +| n_updates | 8188 | +| policy_gradient_loss | -0.0279 | +| value_loss | 0.000186 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.271 | +| time/ | | +| fps | 1365 | +| iterations | 2049 | +| time_elapsed | 3073 | +| total_timesteps | 4196352 | +| train/ | | +| approx_kl | 0.028747866 | +| clip_fraction | 0.39 | +| clip_range | 0.0976 | +| entropy_loss | -7.45 | +| explained_variance | -0.0585 | +| learning_rate | 0.000117 | +| loss | -0.0444 | +| n_updates | 8192 | +| policy_gradient_loss | -0.0269 | +| value_loss | 0.000187 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.271 | +| time/ | | +| fps | 1365 | +| iterations | 2050 | +| time_elapsed | 3075 | +| total_timesteps | 4198400 | +| train/ | | +| approx_kl | 0.026644386 | +| clip_fraction | 0.373 | +| clip_range | 0.0975 | +| entropy_loss | -7.45 | +| explained_variance | -0.0592 | +| learning_rate | 0.000117 | +| loss | -0.045 | +| n_updates | 8196 | +| policy_gradient_loss | -0.0291 | +| value_loss | 0.000211 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.281 | +| time/ | | +| fps | 1365 | +| iterations | 2051 | +| time_elapsed | 3076 | +| total_timesteps | 4200448 | +| train/ | | +| approx_kl | 0.032456633 | +| clip_fraction | 0.412 | +| clip_range | 0.0975 | +| entropy_loss | -7.4 | +| explained_variance | -0.0957 | +| learning_rate | 0.000117 | +| loss | -0.049 | +| n_updates | 8200 | +| policy_gradient_loss | -0.0319 | +| value_loss | 0.000124 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.283 | +| time/ | | +| fps | 1365 | +| iterations | 2052 | +| time_elapsed | 3078 | +| total_timesteps | 4202496 | +| train/ | | +| approx_kl | 0.028366968 | +| clip_fraction | 0.395 | +| clip_range | 0.0975 | +| entropy_loss | -7.39 | +| explained_variance | 0.00619 | +| learning_rate | 0.000117 | +| loss | -0.0436 | +| n_updates | 8204 | +| policy_gradient_loss | -0.0265 | +| value_loss | 0.00027 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.285 | +| time/ | | +| fps | 1365 | +| iterations | 2053 | +| time_elapsed | 3079 | +| total_timesteps | 4204544 | +| train/ | | +| approx_kl | 0.02984656 | +| clip_fraction | 0.384 | +| clip_range | 0.0975 | +| entropy_loss | -7.46 | +| explained_variance | -0.158 | +| learning_rate | 0.000117 | +| loss | -0.0455 | +| n_updates | 8208 | +| policy_gradient_loss | -0.03 | +| value_loss | 0.000173 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.285 | +| time/ | | +| fps | 1365 | +| iterations | 2054 | +| time_elapsed | 3081 | +| total_timesteps | 4206592 | +| train/ | | +| approx_kl | 0.02862445 | +| clip_fraction | 0.4 | +| clip_range | 0.0974 | +| entropy_loss | -7.34 | +| explained_variance | -0.107 | +| learning_rate | 0.000117 | +| loss | -0.0464 | +| n_updates | 8212 | +| policy_gradient_loss | -0.0287 | +| value_loss | 0.000166 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.285 | +| time/ | | +| fps | 1365 | +| iterations | 2055 | +| time_elapsed | 3082 | +| total_timesteps | 4208640 | +| train/ | | +| approx_kl | 0.028846046 | +| clip_fraction | 0.407 | +| clip_range | 0.0974 | +| entropy_loss | -7.46 | +| explained_variance | -0.0912 | +| learning_rate | 0.000117 | +| loss | -0.0483 | +| n_updates | 8216 | +| policy_gradient_loss | -0.0284 | +| value_loss | 0.000183 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.281 | +| time/ | | +| fps | 1365 | +| iterations | 2056 | +| time_elapsed | 3083 | +| total_timesteps | 4210688 | +| train/ | | +| approx_kl | 0.027690936 | +| clip_fraction | 0.374 | +| clip_range | 0.0974 | +| entropy_loss | -7.52 | +| explained_variance | -0.0935 | +| learning_rate | 0.000117 | +| loss | -0.0496 | +| n_updates | 8220 | +| policy_gradient_loss | -0.0283 | +| value_loss | 0.000151 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.29 | +| time/ | | +| fps | 1365 | +| iterations | 2057 | +| time_elapsed | 3085 | +| total_timesteps | 4212736 | +| train/ | | +| approx_kl | 0.027316842 | +| clip_fraction | 0.417 | +| clip_range | 0.0974 | +| entropy_loss | -7.41 | +| explained_variance | -0.687 | +| learning_rate | 0.000117 | +| loss | -0.0601 | +| n_updates | 8224 | +| policy_gradient_loss | -0.0362 | +| value_loss | 7.1e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 1365 | +| iterations | 2058 | +| time_elapsed | 3086 | +| total_timesteps | 4214784 | +| train/ | | +| approx_kl | 0.032099493 | +| clip_fraction | 0.382 | +| clip_range | 0.0973 | +| entropy_loss | -7.3 | +| explained_variance | -0.0274 | +| learning_rate | 0.000117 | +| loss | -0.0494 | +| n_updates | 8228 | +| policy_gradient_loss | -0.03 | +| value_loss | 9.3e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.287 | +| time/ | | +| fps | 1365 | +| iterations | 2059 | +| time_elapsed | 3088 | +| total_timesteps | 4216832 | +| train/ | | +| approx_kl | 0.030069087 | +| clip_fraction | 0.409 | +| clip_range | 0.0973 | +| entropy_loss | -7.15 | +| explained_variance | 0.0182 | +| learning_rate | 0.000117 | +| loss | -0.042 | +| n_updates | 8232 | +| policy_gradient_loss | -0.0285 | +| value_loss | 0.000164 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.287 | +| time/ | | +| fps | 1365 | +| iterations | 2060 | +| time_elapsed | 3089 | +| total_timesteps | 4218880 | +| train/ | | +| approx_kl | 0.031955827 | +| clip_fraction | 0.366 | +| clip_range | 0.0973 | +| entropy_loss | -7.36 | +| explained_variance | -0.0313 | +| learning_rate | 0.000117 | +| loss | -0.0477 | +| n_updates | 8236 | +| policy_gradient_loss | -0.0275 | +| value_loss | 0.000224 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.288 | +| time/ | | +| fps | 1365 | +| iterations | 2061 | +| time_elapsed | 3091 | +| total_timesteps | 4220928 | +| train/ | | +| approx_kl | 0.028540201 | +| clip_fraction | 0.368 | +| clip_range | 0.0973 | +| entropy_loss | -7.44 | +| explained_variance | -0.213 | +| learning_rate | 0.000116 | +| loss | -0.0466 | +| n_updates | 8240 | +| policy_gradient_loss | -0.0274 | +| value_loss | 0.000202 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.288 | +| time/ | | +| fps | 1365 | +| iterations | 2062 | +| time_elapsed | 3092 | +| total_timesteps | 4222976 | +| train/ | | +| approx_kl | 0.032685444 | +| clip_fraction | 0.394 | +| clip_range | 0.0972 | +| entropy_loss | -7.41 | +| explained_variance | -0.214 | +| learning_rate | 0.000116 | +| loss | -0.0443 | +| n_updates | 8244 | +| policy_gradient_loss | -0.0271 | +| value_loss | 0.000186 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.281 | +| time/ | | +| fps | 1365 | +| iterations | 2063 | +| time_elapsed | 3093 | +| total_timesteps | 4225024 | +| train/ | | +| approx_kl | 0.032410145 | +| clip_fraction | 0.405 | +| clip_range | 0.0972 | +| entropy_loss | -7.49 | +| explained_variance | -0.161 | +| learning_rate | 0.000116 | +| loss | -0.0503 | +| n_updates | 8248 | +| policy_gradient_loss | -0.0287 | +| value_loss | 0.000194 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.281 | +| time/ | | +| fps | 1365 | +| iterations | 2064 | +| time_elapsed | 3095 | +| total_timesteps | 4227072 | +| train/ | | +| approx_kl | 0.032777436 | +| clip_fraction | 0.406 | +| clip_range | 0.0972 | +| entropy_loss | -7.22 | +| explained_variance | -0.103 | +| learning_rate | 0.000116 | +| loss | -0.0496 | +| n_updates | 8252 | +| policy_gradient_loss | -0.0319 | +| value_loss | 0.000139 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.285 | +| time/ | | +| fps | 1365 | +| iterations | 2065 | +| time_elapsed | 3096 | +| total_timesteps | 4229120 | +| train/ | | +| approx_kl | 0.03156557 | +| clip_fraction | 0.411 | +| clip_range | 0.0972 | +| entropy_loss | -7.44 | +| explained_variance | -0.171 | +| learning_rate | 0.000116 | +| loss | -0.0456 | +| n_updates | 8256 | +| policy_gradient_loss | -0.0331 | +| value_loss | 0.0001 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 1365 | +| iterations | 2066 | +| time_elapsed | 3098 | +| total_timesteps | 4231168 | +| train/ | | +| approx_kl | 0.028441245 | +| clip_fraction | 0.378 | +| clip_range | 0.0971 | +| entropy_loss | -7.34 | +| explained_variance | -0.0855 | +| learning_rate | 0.000116 | +| loss | -0.042 | +| n_updates | 8260 | +| policy_gradient_loss | -0.0299 | +| value_loss | 0.000105 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.28 | +| time/ | | +| fps | 1365 | +| iterations | 2067 | +| time_elapsed | 3099 | +| total_timesteps | 4233216 | +| train/ | | +| approx_kl | 0.030835427 | +| clip_fraction | 0.397 | +| clip_range | 0.0971 | +| entropy_loss | -7.29 | +| explained_variance | -0.0523 | +| learning_rate | 0.000116 | +| loss | -0.0385 | +| n_updates | 8264 | +| policy_gradient_loss | -0.0277 | +| value_loss | 0.000241 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 1365 | +| iterations | 2068 | +| time_elapsed | 3101 | +| total_timesteps | 4235264 | +| train/ | | +| approx_kl | 0.033273056 | +| clip_fraction | 0.429 | +| clip_range | 0.0971 | +| entropy_loss | -7.13 | +| explained_variance | -0.236 | +| learning_rate | 0.000116 | +| loss | -0.0573 | +| n_updates | 8268 | +| policy_gradient_loss | -0.0322 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 1365 | +| iterations | 2069 | +| time_elapsed | 3102 | +| total_timesteps | 4237312 | +| train/ | | +| approx_kl | 0.030567847 | +| clip_fraction | 0.399 | +| clip_range | 0.0971 | +| entropy_loss | -7.39 | +| explained_variance | -0.068 | +| learning_rate | 0.000116 | +| loss | -0.0411 | +| n_updates | 8272 | +| policy_gradient_loss | -0.0245 | +| value_loss | 0.000356 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.281 | +| time/ | | +| fps | 1365 | +| iterations | 2070 | +| time_elapsed | 3103 | +| total_timesteps | 4239360 | +| train/ | | +| approx_kl | 0.03146572 | +| clip_fraction | 0.411 | +| clip_range | 0.097 | +| entropy_loss | -7.45 | +| explained_variance | -0.232 | +| learning_rate | 0.000116 | +| loss | -0.0497 | +| n_updates | 8276 | +| policy_gradient_loss | -0.0308 | +| value_loss | 0.000137 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 1365 | +| iterations | 2071 | +| time_elapsed | 3105 | +| total_timesteps | 4241408 | +| train/ | | +| approx_kl | 0.036254644 | +| clip_fraction | 0.394 | +| clip_range | 0.097 | +| entropy_loss | -7.4 | +| explained_variance | -0.243 | +| learning_rate | 0.000116 | +| loss | -0.0457 | +| n_updates | 8280 | +| policy_gradient_loss | -0.0303 | +| value_loss | 9.46e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 1365 | +| iterations | 2072 | +| time_elapsed | 3106 | +| total_timesteps | 4243456 | +| train/ | | +| approx_kl | 0.025009222 | +| clip_fraction | 0.37 | +| clip_range | 0.097 | +| entropy_loss | -7.36 | +| explained_variance | 0.017 | +| learning_rate | 0.000116 | +| loss | -0.0437 | +| n_updates | 8284 | +| policy_gradient_loss | -0.0277 | +| value_loss | 0.000185 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.272 | +| time/ | | +| fps | 1365 | +| iterations | 2073 | +| time_elapsed | 3108 | +| total_timesteps | 4245504 | +| train/ | | +| approx_kl | 0.026290402 | +| clip_fraction | 0.398 | +| clip_range | 0.097 | +| entropy_loss | -7.35 | +| explained_variance | -0.129 | +| learning_rate | 0.000116 | +| loss | -0.0464 | +| n_updates | 8288 | +| policy_gradient_loss | -0.0283 | +| value_loss | 0.000143 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.276 | +| time/ | | +| fps | 1365 | +| iterations | 2074 | +| time_elapsed | 3109 | +| total_timesteps | 4247552 | +| train/ | | +| approx_kl | 0.025254447 | +| clip_fraction | 0.392 | +| clip_range | 0.0969 | +| entropy_loss | -7.41 | +| explained_variance | 0.0456 | +| learning_rate | 0.000116 | +| loss | -0.0481 | +| n_updates | 8292 | +| policy_gradient_loss | -0.0276 | +| value_loss | 0.000248 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.264 | +| time/ | | +| fps | 1366 | +| iterations | 2075 | +| time_elapsed | 3110 | +| total_timesteps | 4249600 | +| train/ | | +| approx_kl | 0.026308723 | +| clip_fraction | 0.397 | +| clip_range | 0.0969 | +| entropy_loss | -7.41 | +| explained_variance | -0.124 | +| learning_rate | 0.000116 | +| loss | -0.0438 | +| n_updates | 8296 | +| policy_gradient_loss | -0.028 | +| value_loss | 0.000197 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.265 | +| time/ | | +| fps | 1366 | +| iterations | 2076 | +| time_elapsed | 3112 | +| total_timesteps | 4251648 | +| train/ | | +| approx_kl | 0.026936993 | +| clip_fraction | 0.379 | +| clip_range | 0.0969 | +| entropy_loss | -7.22 | +| explained_variance | -0.0329 | +| learning_rate | 0.000116 | +| loss | -0.0435 | +| n_updates | 8300 | +| policy_gradient_loss | -0.0265 | +| value_loss | 0.000309 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.269 | +| time/ | | +| fps | 1366 | +| iterations | 2077 | +| time_elapsed | 3113 | +| total_timesteps | 4253696 | +| train/ | | +| approx_kl | 0.029227734 | +| clip_fraction | 0.411 | +| clip_range | 0.0969 | +| entropy_loss | -7.16 | +| explained_variance | -0.0615 | +| learning_rate | 0.000116 | +| loss | -0.0548 | +| n_updates | 8304 | +| policy_gradient_loss | -0.0358 | +| value_loss | 7.97e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.269 | +| time/ | | +| fps | 1366 | +| iterations | 2078 | +| time_elapsed | 3115 | +| total_timesteps | 4255744 | +| train/ | | +| approx_kl | 0.030175645 | +| clip_fraction | 0.407 | +| clip_range | 0.0968 | +| entropy_loss | -7.32 | +| explained_variance | -0.131 | +| learning_rate | 0.000116 | +| loss | -0.0441 | +| n_updates | 8308 | +| policy_gradient_loss | -0.0311 | +| value_loss | 0.000171 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.264 | +| time/ | | +| fps | 1366 | +| iterations | 2079 | +| time_elapsed | 3116 | +| total_timesteps | 4257792 | +| train/ | | +| approx_kl | 0.03589153 | +| clip_fraction | 0.409 | +| clip_range | 0.0968 | +| entropy_loss | -7.36 | +| explained_variance | -0.131 | +| learning_rate | 0.000116 | +| loss | -0.0426 | +| n_updates | 8312 | +| policy_gradient_loss | -0.0303 | +| value_loss | 0.000162 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.266 | +| time/ | | +| fps | 1366 | +| iterations | 2080 | +| time_elapsed | 3117 | +| total_timesteps | 4259840 | +| train/ | | +| approx_kl | 0.027926594 | +| clip_fraction | 0.383 | +| clip_range | 0.0968 | +| entropy_loss | -7.39 | +| explained_variance | 0.0355 | +| learning_rate | 0.000116 | +| loss | -0.0516 | +| n_updates | 8316 | +| policy_gradient_loss | -0.0288 | +| value_loss | 0.000176 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.266 | +| time/ | | +| fps | 1366 | +| iterations | 2081 | +| time_elapsed | 3119 | +| total_timesteps | 4261888 | +| train/ | | +| approx_kl | 0.028553754 | +| clip_fraction | 0.38 | +| clip_range | 0.0968 | +| entropy_loss | -7.45 | +| explained_variance | -0.121 | +| learning_rate | 0.000116 | +| loss | -0.0469 | +| n_updates | 8320 | +| policy_gradient_loss | -0.0296 | +| value_loss | 0.000244 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.285 | +| time/ | | +| fps | 1366 | +| iterations | 2082 | +| time_elapsed | 3120 | +| total_timesteps | 4263936 | +| train/ | | +| approx_kl | 0.026662525 | +| clip_fraction | 0.392 | +| clip_range | 0.0967 | +| entropy_loss | -7.4 | +| explained_variance | -0.128 | +| learning_rate | 0.000116 | +| loss | -0.0448 | +| n_updates | 8324 | +| policy_gradient_loss | -0.0291 | +| value_loss | 0.000201 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.283 | +| time/ | | +| fps | 1366 | +| iterations | 2083 | +| time_elapsed | 3122 | +| total_timesteps | 4265984 | +| train/ | | +| approx_kl | 0.023776744 | +| clip_fraction | 0.361 | +| clip_range | 0.0967 | +| entropy_loss | -7.3 | +| explained_variance | -0.13 | +| learning_rate | 0.000116 | +| loss | -0.0343 | +| n_updates | 8328 | +| policy_gradient_loss | -0.0238 | +| value_loss | 0.00041 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.283 | +| time/ | | +| fps | 1366 | +| iterations | 2084 | +| time_elapsed | 3123 | +| total_timesteps | 4268032 | +| train/ | | +| approx_kl | 0.03346028 | +| clip_fraction | 0.404 | +| clip_range | 0.0967 | +| entropy_loss | -7.31 | +| explained_variance | -0.228 | +| learning_rate | 0.000116 | +| loss | -0.0517 | +| n_updates | 8332 | +| policy_gradient_loss | -0.0316 | +| value_loss | 0.000203 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.286 | +| time/ | | +| fps | 1366 | +| iterations | 2085 | +| time_elapsed | 3125 | +| total_timesteps | 4270080 | +| train/ | | +| approx_kl | 0.030505084 | +| clip_fraction | 0.424 | +| clip_range | 0.0966 | +| entropy_loss | -7.48 | +| explained_variance | -0.287 | +| learning_rate | 0.000115 | +| loss | -0.0505 | +| n_updates | 8336 | +| policy_gradient_loss | -0.0349 | +| value_loss | 0.000118 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.286 | +| time/ | | +| fps | 1366 | +| iterations | 2086 | +| time_elapsed | 3126 | +| total_timesteps | 4272128 | +| train/ | | +| approx_kl | 0.030586207 | +| clip_fraction | 0.391 | +| clip_range | 0.0966 | +| entropy_loss | -7.4 | +| explained_variance | -0.308 | +| learning_rate | 0.000115 | +| loss | -0.0483 | +| n_updates | 8340 | +| policy_gradient_loss | -0.0272 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.285 | +| time/ | | +| fps | 1366 | +| iterations | 2087 | +| time_elapsed | 3128 | +| total_timesteps | 4274176 | +| train/ | | +| approx_kl | 0.033518873 | +| clip_fraction | 0.407 | +| clip_range | 0.0966 | +| entropy_loss | -7.41 | +| explained_variance | -0.0615 | +| learning_rate | 0.000115 | +| loss | -0.0503 | +| n_updates | 8344 | +| policy_gradient_loss | -0.0331 | +| value_loss | 0.000109 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 1366 | +| iterations | 2088 | +| time_elapsed | 3129 | +| total_timesteps | 4276224 | +| train/ | | +| approx_kl | 0.029617768 | +| clip_fraction | 0.384 | +| clip_range | 0.0966 | +| entropy_loss | -7.42 | +| explained_variance | -0.291 | +| learning_rate | 0.000115 | +| loss | -0.0411 | +| n_updates | 8348 | +| policy_gradient_loss | -0.0269 | +| value_loss | 0.000129 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 1366 | +| iterations | 2089 | +| time_elapsed | 3130 | +| total_timesteps | 4278272 | +| train/ | | +| approx_kl | 0.029033888 | +| clip_fraction | 0.382 | +| clip_range | 0.0965 | +| entropy_loss | -7.41 | +| explained_variance | -0.178 | +| learning_rate | 0.000115 | +| loss | -0.0454 | +| n_updates | 8352 | +| policy_gradient_loss | -0.0287 | +| value_loss | 0.000161 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.302 | +| time/ | | +| fps | 1366 | +| iterations | 2090 | +| time_elapsed | 3132 | +| total_timesteps | 4280320 | +| train/ | | +| approx_kl | 0.031967722 | +| clip_fraction | 0.414 | +| clip_range | 0.0965 | +| entropy_loss | -7.31 | +| explained_variance | -0.0258 | +| learning_rate | 0.000115 | +| loss | -0.0461 | +| n_updates | 8356 | +| policy_gradient_loss | -0.0315 | +| value_loss | 0.000215 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.298 | +| time/ | | +| fps | 1366 | +| iterations | 2091 | +| time_elapsed | 3133 | +| total_timesteps | 4282368 | +| train/ | | +| approx_kl | 0.031819493 | +| clip_fraction | 0.415 | +| clip_range | 0.0965 | +| entropy_loss | -7.32 | +| explained_variance | -0.298 | +| learning_rate | 0.000115 | +| loss | -0.0562 | +| n_updates | 8360 | +| policy_gradient_loss | -0.0344 | +| value_loss | 0.00011 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.306 | +| time/ | | +| fps | 1366 | +| iterations | 2092 | +| time_elapsed | 3135 | +| total_timesteps | 4284416 | +| train/ | | +| approx_kl | 0.029360376 | +| clip_fraction | 0.395 | +| clip_range | 0.0965 | +| entropy_loss | -7.47 | +| explained_variance | -0.32 | +| learning_rate | 0.000115 | +| loss | -0.0377 | +| n_updates | 8364 | +| policy_gradient_loss | -0.0283 | +| value_loss | 0.000105 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 1366 | +| iterations | 2093 | +| time_elapsed | 3136 | +| total_timesteps | 4286464 | +| train/ | | +| approx_kl | 0.030003123 | +| clip_fraction | 0.404 | +| clip_range | 0.0964 | +| entropy_loss | -7.27 | +| explained_variance | -0.0139 | +| learning_rate | 0.000115 | +| loss | -0.0386 | +| n_updates | 8368 | +| policy_gradient_loss | -0.0282 | +| value_loss | 0.000177 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.298 | +| time/ | | +| fps | 1366 | +| iterations | 2094 | +| time_elapsed | 3138 | +| total_timesteps | 4288512 | +| train/ | | +| approx_kl | 0.026110766 | +| clip_fraction | 0.381 | +| clip_range | 0.0964 | +| entropy_loss | -7.37 | +| explained_variance | -0.0723 | +| learning_rate | 0.000115 | +| loss | -0.0468 | +| n_updates | 8372 | +| policy_gradient_loss | -0.0307 | +| value_loss | 0.000167 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 1366 | +| iterations | 2095 | +| time_elapsed | 3139 | +| total_timesteps | 4290560 | +| train/ | | +| approx_kl | 0.025418982 | +| clip_fraction | 0.399 | +| clip_range | 0.0964 | +| entropy_loss | -7.45 | +| explained_variance | -0.0505 | +| learning_rate | 0.000115 | +| loss | -0.0525 | +| n_updates | 8376 | +| policy_gradient_loss | -0.0279 | +| value_loss | 0.000146 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 1366 | +| iterations | 2096 | +| time_elapsed | 3140 | +| total_timesteps | 4292608 | +| train/ | | +| approx_kl | 0.027368978 | +| clip_fraction | 0.392 | +| clip_range | 0.0964 | +| entropy_loss | -7.27 | +| explained_variance | 0.115 | +| learning_rate | 0.000115 | +| loss | -0.043 | +| n_updates | 8380 | +| policy_gradient_loss | -0.0275 | +| value_loss | 0.000243 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.298 | +| time/ | | +| fps | 1366 | +| iterations | 2097 | +| time_elapsed | 3142 | +| total_timesteps | 4294656 | +| train/ | | +| approx_kl | 0.03153311 | +| clip_fraction | 0.375 | +| clip_range | 0.0963 | +| entropy_loss | -7.41 | +| explained_variance | -0.295 | +| learning_rate | 0.000115 | +| loss | -0.0476 | +| n_updates | 8384 | +| policy_gradient_loss | -0.0309 | +| value_loss | 0.00016 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.298 | +| time/ | | +| fps | 1366 | +| iterations | 2098 | +| time_elapsed | 3143 | +| total_timesteps | 4296704 | +| train/ | | +| approx_kl | 0.028355137 | +| clip_fraction | 0.415 | +| clip_range | 0.0963 | +| entropy_loss | -7.33 | +| explained_variance | 0.214 | +| learning_rate | 0.000115 | +| loss | -0.0479 | +| n_updates | 8388 | +| policy_gradient_loss | -0.0315 | +| value_loss | 0.000132 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.294 | +| time/ | | +| fps | 1366 | +| iterations | 2099 | +| time_elapsed | 3145 | +| total_timesteps | 4298752 | +| train/ | | +| approx_kl | 0.028420016 | +| clip_fraction | 0.39 | +| clip_range | 0.0963 | +| entropy_loss | -7.34 | +| explained_variance | 0.0204 | +| learning_rate | 0.000115 | +| loss | -0.0456 | +| n_updates | 8392 | +| policy_gradient_loss | -0.0274 | +| value_loss | 0.000185 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.294 | +| time/ | | +| fps | 1366 | +| iterations | 2100 | +| time_elapsed | 3146 | +| total_timesteps | 4300800 | +| train/ | | +| approx_kl | 0.026506506 | +| clip_fraction | 0.386 | +| clip_range | 0.0963 | +| entropy_loss | -7.38 | +| explained_variance | -0.324 | +| learning_rate | 0.000115 | +| loss | -0.0477 | +| n_updates | 8396 | +| policy_gradient_loss | -0.0283 | +| value_loss | 0.000217 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.289 | +| time/ | | +| fps | 1366 | +| iterations | 2101 | +| time_elapsed | 3148 | +| total_timesteps | 4302848 | +| train/ | | +| approx_kl | 0.032695808 | +| clip_fraction | 0.429 | +| clip_range | 0.0962 | +| entropy_loss | -7.43 | +| explained_variance | -0.0225 | +| learning_rate | 0.000115 | +| loss | -0.0451 | +| n_updates | 8400 | +| policy_gradient_loss | -0.0315 | +| value_loss | 0.000144 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.292 | +| time/ | | +| fps | 1366 | +| iterations | 2102 | +| time_elapsed | 3149 | +| total_timesteps | 4304896 | +| train/ | | +| approx_kl | 0.026474006 | +| clip_fraction | 0.408 | +| clip_range | 0.0962 | +| entropy_loss | -7.44 | +| explained_variance | -0.0594 | +| learning_rate | 0.000115 | +| loss | -0.0438 | +| n_updates | 8404 | +| policy_gradient_loss | -0.0299 | +| value_loss | 0.000175 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.283 | +| time/ | | +| fps | 1366 | +| iterations | 2103 | +| time_elapsed | 3150 | +| total_timesteps | 4306944 | +| train/ | | +| approx_kl | 0.031587116 | +| clip_fraction | 0.4 | +| clip_range | 0.0962 | +| entropy_loss | -7.47 | +| explained_variance | 0.0914 | +| learning_rate | 0.000115 | +| loss | -0.0499 | +| n_updates | 8408 | +| policy_gradient_loss | -0.0293 | +| value_loss | 0.000184 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.285 | +| time/ | | +| fps | 1366 | +| iterations | 2104 | +| time_elapsed | 3152 | +| total_timesteps | 4308992 | +| train/ | | +| approx_kl | 0.029350873 | +| clip_fraction | 0.403 | +| clip_range | 0.0962 | +| entropy_loss | -7.18 | +| explained_variance | -0.103 | +| learning_rate | 0.000115 | +| loss | -0.044 | +| n_updates | 8412 | +| policy_gradient_loss | -0.028 | +| value_loss | 0.000182 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.285 | +| time/ | | +| fps | 1366 | +| iterations | 2105 | +| time_elapsed | 3153 | +| total_timesteps | 4311040 | +| train/ | | +| approx_kl | 0.025140427 | +| clip_fraction | 0.382 | +| clip_range | 0.0961 | +| entropy_loss | -7.5 | +| explained_variance | -0.0965 | +| learning_rate | 0.000115 | +| loss | -0.0417 | +| n_updates | 8416 | +| policy_gradient_loss | -0.0242 | +| value_loss | 0.000236 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.289 | +| time/ | | +| fps | 1366 | +| iterations | 2106 | +| time_elapsed | 3155 | +| total_timesteps | 4313088 | +| train/ | | +| approx_kl | 0.030869283 | +| clip_fraction | 0.42 | +| clip_range | 0.0961 | +| entropy_loss | -7.42 | +| explained_variance | -0.683 | +| learning_rate | 0.000115 | +| loss | -0.0556 | +| n_updates | 8420 | +| policy_gradient_loss | -0.0362 | +| value_loss | 7.48e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.294 | +| time/ | | +| fps | 1366 | +| iterations | 2107 | +| time_elapsed | 3156 | +| total_timesteps | 4315136 | +| train/ | | +| approx_kl | 0.026713617 | +| clip_fraction | 0.397 | +| clip_range | 0.0961 | +| entropy_loss | -7.4 | +| explained_variance | -0.0541 | +| learning_rate | 0.000115 | +| loss | -0.0499 | +| n_updates | 8424 | +| policy_gradient_loss | -0.028 | +| value_loss | 0.000111 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.291 | +| time/ | | +| fps | 1366 | +| iterations | 2108 | +| time_elapsed | 3158 | +| total_timesteps | 4317184 | +| train/ | | +| approx_kl | 0.028932853 | +| clip_fraction | 0.369 | +| clip_range | 0.0961 | +| entropy_loss | -7.4 | +| explained_variance | 0.0314 | +| learning_rate | 0.000115 | +| loss | -0.0415 | +| n_updates | 8428 | +| policy_gradient_loss | -0.0266 | +| value_loss | 0.000198 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.286 | +| time/ | | +| fps | 1367 | +| iterations | 2109 | +| time_elapsed | 3159 | +| total_timesteps | 4319232 | +| train/ | | +| approx_kl | 0.027202511 | +| clip_fraction | 0.367 | +| clip_range | 0.096 | +| entropy_loss | -7.32 | +| explained_variance | -0.0807 | +| learning_rate | 0.000115 | +| loss | -0.048 | +| n_updates | 8432 | +| policy_gradient_loss | -0.0291 | +| value_loss | 0.000193 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.287 | +| time/ | | +| fps | 1367 | +| iterations | 2110 | +| time_elapsed | 3161 | +| total_timesteps | 4321280 | +| train/ | | +| approx_kl | 0.029187959 | +| clip_fraction | 0.373 | +| clip_range | 0.096 | +| entropy_loss | -7.41 | +| explained_variance | -0.136 | +| learning_rate | 0.000114 | +| loss | -0.0434 | +| n_updates | 8436 | +| policy_gradient_loss | -0.0284 | +| value_loss | 0.000238 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 1367 | +| iterations | 2111 | +| time_elapsed | 3162 | +| total_timesteps | 4323328 | +| train/ | | +| approx_kl | 0.029374756 | +| clip_fraction | 0.389 | +| clip_range | 0.096 | +| entropy_loss | -7.5 | +| explained_variance | -0.0721 | +| learning_rate | 0.000114 | +| loss | -0.0426 | +| n_updates | 8440 | +| policy_gradient_loss | -0.0279 | +| value_loss | 0.000182 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 1367 | +| iterations | 2112 | +| time_elapsed | 3163 | +| total_timesteps | 4325376 | +| train/ | | +| approx_kl | 0.022190128 | +| clip_fraction | 0.378 | +| clip_range | 0.096 | +| entropy_loss | -7.52 | +| explained_variance | -0.0729 | +| learning_rate | 0.000114 | +| loss | -0.0456 | +| n_updates | 8444 | +| policy_gradient_loss | -0.0254 | +| value_loss | 0.000208 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.283 | +| time/ | | +| fps | 1367 | +| iterations | 2113 | +| time_elapsed | 3165 | +| total_timesteps | 4327424 | +| train/ | | +| approx_kl | 0.029595602 | +| clip_fraction | 0.384 | +| clip_range | 0.0959 | +| entropy_loss | -7.49 | +| explained_variance | -0.0432 | +| learning_rate | 0.000114 | +| loss | -0.0475 | +| n_updates | 8448 | +| policy_gradient_loss | -0.0294 | +| value_loss | 0.000156 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.28 | +| time/ | | +| fps | 1367 | +| iterations | 2114 | +| time_elapsed | 3166 | +| total_timesteps | 4329472 | +| train/ | | +| approx_kl | 0.024875738 | +| clip_fraction | 0.349 | +| clip_range | 0.0959 | +| entropy_loss | -7.29 | +| explained_variance | -0.0978 | +| learning_rate | 0.000114 | +| loss | -0.0387 | +| n_updates | 8452 | +| policy_gradient_loss | -0.0252 | +| value_loss | 0.000368 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.281 | +| time/ | | +| fps | 1367 | +| iterations | 2115 | +| time_elapsed | 3168 | +| total_timesteps | 4331520 | +| train/ | | +| approx_kl | 0.025066901 | +| clip_fraction | 0.391 | +| clip_range | 0.0959 | +| entropy_loss | -7.53 | +| explained_variance | -0.259 | +| learning_rate | 0.000114 | +| loss | -0.0551 | +| n_updates | 8456 | +| policy_gradient_loss | -0.0299 | +| value_loss | 0.000108 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.276 | +| time/ | | +| fps | 1367 | +| iterations | 2116 | +| time_elapsed | 3169 | +| total_timesteps | 4333568 | +| train/ | | +| approx_kl | 0.024704386 | +| clip_fraction | 0.378 | +| clip_range | 0.0959 | +| entropy_loss | -7.55 | +| explained_variance | -0.139 | +| learning_rate | 0.000114 | +| loss | -0.0418 | +| n_updates | 8460 | +| policy_gradient_loss | -0.031 | +| value_loss | 0.000157 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.276 | +| time/ | | +| fps | 1367 | +| iterations | 2117 | +| time_elapsed | 3171 | +| total_timesteps | 4335616 | +| train/ | | +| approx_kl | 0.027711257 | +| clip_fraction | 0.361 | +| clip_range | 0.0958 | +| entropy_loss | -7.27 | +| explained_variance | -0.0546 | +| learning_rate | 0.000114 | +| loss | -0.0446 | +| n_updates | 8464 | +| policy_gradient_loss | -0.0241 | +| value_loss | 0.000273 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.278 | +| time/ | | +| fps | 1367 | +| iterations | 2118 | +| time_elapsed | 3172 | +| total_timesteps | 4337664 | +| train/ | | +| approx_kl | 0.026600452 | +| clip_fraction | 0.387 | +| clip_range | 0.0958 | +| entropy_loss | -7.51 | +| explained_variance | -0.0655 | +| learning_rate | 0.000114 | +| loss | -0.0444 | +| n_updates | 8468 | +| policy_gradient_loss | -0.0299 | +| value_loss | 0.000137 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.278 | +| time/ | | +| fps | 1367 | +| iterations | 2119 | +| time_elapsed | 3174 | +| total_timesteps | 4339712 | +| train/ | | +| approx_kl | 0.021611739 | +| clip_fraction | 0.371 | +| clip_range | 0.0958 | +| entropy_loss | -7.55 | +| explained_variance | -0.00856 | +| learning_rate | 0.000114 | +| loss | -0.0457 | +| n_updates | 8472 | +| policy_gradient_loss | -0.0292 | +| value_loss | 0.000183 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.278 | +| time/ | | +| fps | 1367 | +| iterations | 2120 | +| time_elapsed | 3175 | +| total_timesteps | 4341760 | +| train/ | | +| approx_kl | 0.022399487 | +| clip_fraction | 0.365 | +| clip_range | 0.0958 | +| entropy_loss | -7.57 | +| explained_variance | -0.198 | +| learning_rate | 0.000114 | +| loss | -0.0507 | +| n_updates | 8476 | +| policy_gradient_loss | -0.0264 | +| value_loss | 0.00012 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.28 | +| time/ | | +| fps | 1367 | +| iterations | 2121 | +| time_elapsed | 3176 | +| total_timesteps | 4343808 | +| train/ | | +| approx_kl | 0.025165586 | +| clip_fraction | 0.396 | +| clip_range | 0.0957 | +| entropy_loss | -7.51 | +| explained_variance | -0.182 | +| learning_rate | 0.000114 | +| loss | -0.0507 | +| n_updates | 8480 | +| policy_gradient_loss | -0.0301 | +| value_loss | 0.000108 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 1367 | +| iterations | 2122 | +| time_elapsed | 3178 | +| total_timesteps | 4345856 | +| train/ | | +| approx_kl | 0.027349044 | +| clip_fraction | 0.372 | +| clip_range | 0.0957 | +| entropy_loss | -7.33 | +| explained_variance | -0.0688 | +| learning_rate | 0.000114 | +| loss | -0.0378 | +| n_updates | 8484 | +| policy_gradient_loss | -0.025 | +| value_loss | 0.000184 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.276 | +| time/ | | +| fps | 1367 | +| iterations | 2123 | +| time_elapsed | 3179 | +| total_timesteps | 4347904 | +| train/ | | +| approx_kl | 0.027838487 | +| clip_fraction | 0.386 | +| clip_range | 0.0957 | +| entropy_loss | -7.44 | +| explained_variance | -0.21 | +| learning_rate | 0.000114 | +| loss | -0.0491 | +| n_updates | 8488 | +| policy_gradient_loss | -0.0291 | +| value_loss | 0.00012 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 1367 | +| iterations | 2124 | +| time_elapsed | 3181 | +| total_timesteps | 4349952 | +| train/ | | +| approx_kl | 0.032359898 | +| clip_fraction | 0.368 | +| clip_range | 0.0957 | +| entropy_loss | -7.51 | +| explained_variance | -0.113 | +| learning_rate | 0.000114 | +| loss | -0.043 | +| n_updates | 8492 | +| policy_gradient_loss | -0.0256 | +| value_loss | 0.000185 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 1367 | +| iterations | 2125 | +| time_elapsed | 3182 | +| total_timesteps | 4352000 | +| train/ | | +| approx_kl | 0.02994468 | +| clip_fraction | 0.37 | +| clip_range | 0.0956 | +| entropy_loss | -7.37 | +| explained_variance | -0.0359 | +| learning_rate | 0.000114 | +| loss | -0.0337 | +| n_updates | 8496 | +| policy_gradient_loss | -0.0251 | +| value_loss | 0.000192 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.281 | +| time/ | | +| fps | 1367 | +| iterations | 2126 | +| time_elapsed | 3184 | +| total_timesteps | 4354048 | +| train/ | | +| approx_kl | 0.033079833 | +| clip_fraction | 0.41 | +| clip_range | 0.0956 | +| entropy_loss | -7.32 | +| explained_variance | -0.136 | +| learning_rate | 0.000114 | +| loss | -0.0444 | +| n_updates | 8500 | +| policy_gradient_loss | -0.03 | +| value_loss | 0.000142 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.284 | +| time/ | | +| fps | 1367 | +| iterations | 2127 | +| time_elapsed | 3185 | +| total_timesteps | 4356096 | +| train/ | | +| approx_kl | 0.02824958 | +| clip_fraction | 0.372 | +| clip_range | 0.0956 | +| entropy_loss | -7.31 | +| explained_variance | -0.141 | +| learning_rate | 0.000114 | +| loss | -0.0477 | +| n_updates | 8504 | +| policy_gradient_loss | -0.0274 | +| value_loss | 0.000252 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 1367 | +| iterations | 2128 | +| time_elapsed | 3187 | +| total_timesteps | 4358144 | +| train/ | | +| approx_kl | 0.03489746 | +| clip_fraction | 0.385 | +| clip_range | 0.0955 | +| entropy_loss | -7.32 | +| explained_variance | -0.288 | +| learning_rate | 0.000114 | +| loss | -0.0475 | +| n_updates | 8508 | +| policy_gradient_loss | -0.0303 | +| value_loss | 8.38e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.28 | +| time/ | | +| fps | 1367 | +| iterations | 2129 | +| time_elapsed | 3188 | +| total_timesteps | 4360192 | +| train/ | | +| approx_kl | 0.034246042 | +| clip_fraction | 0.384 | +| clip_range | 0.0955 | +| entropy_loss | -7.48 | +| explained_variance | -0.214 | +| learning_rate | 0.000114 | +| loss | -0.0474 | +| n_updates | 8512 | +| policy_gradient_loss | -0.0295 | +| value_loss | 0.000125 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.28 | +| time/ | | +| fps | 1367 | +| iterations | 2130 | +| time_elapsed | 3190 | +| total_timesteps | 4362240 | +| train/ | | +| approx_kl | 0.028896874 | +| clip_fraction | 0.372 | +| clip_range | 0.0955 | +| entropy_loss | -7.32 | +| explained_variance | -0.173 | +| learning_rate | 0.000114 | +| loss | -0.0397 | +| n_updates | 8516 | +| policy_gradient_loss | -0.0275 | +| value_loss | 0.000153 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.28 | +| time/ | | +| fps | 1367 | +| iterations | 2131 | +| time_elapsed | 3191 | +| total_timesteps | 4364288 | +| train/ | | +| approx_kl | 0.027746636 | +| clip_fraction | 0.381 | +| clip_range | 0.0955 | +| entropy_loss | -7.49 | +| explained_variance | -0.0931 | +| learning_rate | 0.000114 | +| loss | -0.0453 | +| n_updates | 8520 | +| policy_gradient_loss | -0.03 | +| value_loss | 0.000114 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.281 | +| time/ | | +| fps | 1367 | +| iterations | 2132 | +| time_elapsed | 3193 | +| total_timesteps | 4366336 | +| train/ | | +| approx_kl | 0.027624762 | +| clip_fraction | 0.346 | +| clip_range | 0.0954 | +| entropy_loss | -7.47 | +| explained_variance | -0.0962 | +| learning_rate | 0.000114 | +| loss | -0.0471 | +| n_updates | 8524 | +| policy_gradient_loss | -0.0254 | +| value_loss | 0.000171 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.285 | +| time/ | | +| fps | 1367 | +| iterations | 2133 | +| time_elapsed | 3194 | +| total_timesteps | 4368384 | +| train/ | | +| approx_kl | 0.02739219 | +| clip_fraction | 0.364 | +| clip_range | 0.0954 | +| entropy_loss | -7.4 | +| explained_variance | -0.131 | +| learning_rate | 0.000114 | +| loss | -0.0439 | +| n_updates | 8528 | +| policy_gradient_loss | -0.0274 | +| value_loss | 0.000141 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.272 | +| time/ | | +| fps | 1367 | +| iterations | 2134 | +| time_elapsed | 3196 | +| total_timesteps | 4370432 | +| train/ | | +| approx_kl | 0.025662377 | +| clip_fraction | 0.367 | +| clip_range | 0.0954 | +| entropy_loss | -7.44 | +| explained_variance | 0.0229 | +| learning_rate | 0.000114 | +| loss | -0.0333 | +| n_updates | 8532 | +| policy_gradient_loss | -0.0228 | +| value_loss | 0.000261 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.273 | +| time/ | | +| fps | 1367 | +| iterations | 2135 | +| time_elapsed | 3197 | +| total_timesteps | 4372480 | +| train/ | | +| approx_kl | 0.03045449 | +| clip_fraction | 0.385 | +| clip_range | 0.0954 | +| entropy_loss | -7.52 | +| explained_variance | -0.212 | +| learning_rate | 0.000113 | +| loss | -0.0547 | +| n_updates | 8536 | +| policy_gradient_loss | -0.033 | +| value_loss | 0.000154 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.272 | +| time/ | | +| fps | 1367 | +| iterations | 2136 | +| time_elapsed | 3199 | +| total_timesteps | 4374528 | +| train/ | | +| approx_kl | 0.028566252 | +| clip_fraction | 0.383 | +| clip_range | 0.0953 | +| entropy_loss | -7.39 | +| explained_variance | -0.176 | +| learning_rate | 0.000113 | +| loss | -0.056 | +| n_updates | 8540 | +| policy_gradient_loss | -0.0287 | +| value_loss | 0.000139 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.267 | +| time/ | | +| fps | 1367 | +| iterations | 2137 | +| time_elapsed | 3200 | +| total_timesteps | 4376576 | +| train/ | | +| approx_kl | 0.028430056 | +| clip_fraction | 0.423 | +| clip_range | 0.0953 | +| entropy_loss | -7.47 | +| explained_variance | -0.851 | +| learning_rate | 0.000113 | +| loss | -0.0565 | +| n_updates | 8544 | +| policy_gradient_loss | -0.0387 | +| value_loss | 4.18e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.269 | +| time/ | | +| fps | 1367 | +| iterations | 2138 | +| time_elapsed | 3202 | +| total_timesteps | 4378624 | +| train/ | | +| approx_kl | 0.030949017 | +| clip_fraction | 0.377 | +| clip_range | 0.0953 | +| entropy_loss | -7.57 | +| explained_variance | -0.208 | +| learning_rate | 0.000113 | +| loss | -0.0494 | +| n_updates | 8548 | +| policy_gradient_loss | -0.0304 | +| value_loss | 0.000101 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.269 | +| time/ | | +| fps | 1367 | +| iterations | 2139 | +| time_elapsed | 3203 | +| total_timesteps | 4380672 | +| train/ | | +| approx_kl | 0.031599477 | +| clip_fraction | 0.35 | +| clip_range | 0.0953 | +| entropy_loss | -7.39 | +| explained_variance | -0.0458 | +| learning_rate | 0.000113 | +| loss | -0.0422 | +| n_updates | 8552 | +| policy_gradient_loss | -0.0261 | +| value_loss | 0.000187 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.271 | +| time/ | | +| fps | 1367 | +| iterations | 2140 | +| time_elapsed | 3205 | +| total_timesteps | 4382720 | +| train/ | | +| approx_kl | 0.027639136 | +| clip_fraction | 0.401 | +| clip_range | 0.0952 | +| entropy_loss | -7.52 | +| explained_variance | -0.387 | +| learning_rate | 0.000113 | +| loss | -0.0519 | +| n_updates | 8556 | +| policy_gradient_loss | -0.0332 | +| value_loss | 8.2e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 1367 | +| iterations | 2141 | +| time_elapsed | 3206 | +| total_timesteps | 4384768 | +| train/ | | +| approx_kl | 0.02614228 | +| clip_fraction | 0.368 | +| clip_range | 0.0952 | +| entropy_loss | -7.57 | +| explained_variance | -0.0446 | +| learning_rate | 0.000113 | +| loss | -0.0414 | +| n_updates | 8560 | +| policy_gradient_loss | -0.0266 | +| value_loss | 0.000187 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.277 | +| time/ | | +| fps | 1367 | +| iterations | 2142 | +| time_elapsed | 3208 | +| total_timesteps | 4386816 | +| train/ | | +| approx_kl | 0.018714111 | +| clip_fraction | 0.354 | +| clip_range | 0.0952 | +| entropy_loss | -7.44 | +| explained_variance | -0.183 | +| learning_rate | 0.000113 | +| loss | -0.039 | +| n_updates | 8564 | +| policy_gradient_loss | -0.0269 | +| value_loss | 0.000218 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.277 | +| time/ | | +| fps | 1367 | +| iterations | 2143 | +| time_elapsed | 3209 | +| total_timesteps | 4388864 | +| train/ | | +| approx_kl | 0.025762536 | +| clip_fraction | 0.367 | +| clip_range | 0.0952 | +| entropy_loss | -7.46 | +| explained_variance | -0.105 | +| learning_rate | 0.000113 | +| loss | -0.0436 | +| n_updates | 8568 | +| policy_gradient_loss | -0.0279 | +| value_loss | 0.000153 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.276 | +| time/ | | +| fps | 1367 | +| iterations | 2144 | +| time_elapsed | 3210 | +| total_timesteps | 4390912 | +| train/ | | +| approx_kl | 0.024310954 | +| clip_fraction | 0.374 | +| clip_range | 0.0951 | +| entropy_loss | -7.52 | +| explained_variance | -0.114 | +| learning_rate | 0.000113 | +| loss | -0.0469 | +| n_updates | 8572 | +| policy_gradient_loss | -0.0295 | +| value_loss | 0.000205 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 1367 | +| iterations | 2145 | +| time_elapsed | 3212 | +| total_timesteps | 4392960 | +| train/ | | +| approx_kl | 0.019072358 | +| clip_fraction | 0.353 | +| clip_range | 0.0951 | +| entropy_loss | -7.42 | +| explained_variance | -0.117 | +| learning_rate | 0.000113 | +| loss | -0.0374 | +| n_updates | 8576 | +| policy_gradient_loss | -0.0263 | +| value_loss | 0.00015 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.271 | +| time/ | | +| fps | 1367 | +| iterations | 2146 | +| time_elapsed | 3213 | +| total_timesteps | 4395008 | +| train/ | | +| approx_kl | 0.02610583 | +| clip_fraction | 0.395 | +| clip_range | 0.0951 | +| entropy_loss | -7.21 | +| explained_variance | -0.145 | +| learning_rate | 0.000113 | +| loss | -0.0498 | +| n_updates | 8580 | +| policy_gradient_loss | -0.029 | +| value_loss | 0.00011 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.266 | +| time/ | | +| fps | 1367 | +| iterations | 2147 | +| time_elapsed | 3215 | +| total_timesteps | 4397056 | +| train/ | | +| approx_kl | 0.02713907 | +| clip_fraction | 0.359 | +| clip_range | 0.0951 | +| entropy_loss | -7.34 | +| explained_variance | 0.00959 | +| learning_rate | 0.000113 | +| loss | -0.0383 | +| n_updates | 8584 | +| policy_gradient_loss | -0.0246 | +| value_loss | 0.00018 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.265 | +| time/ | | +| fps | 1367 | +| iterations | 2148 | +| time_elapsed | 3216 | +| total_timesteps | 4399104 | +| train/ | | +| approx_kl | 0.026134543 | +| clip_fraction | 0.361 | +| clip_range | 0.095 | +| entropy_loss | -7.44 | +| explained_variance | -0.0449 | +| learning_rate | 0.000113 | +| loss | -0.042 | +| n_updates | 8588 | +| policy_gradient_loss | -0.028 | +| value_loss | 0.000173 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.265 | +| time/ | | +| fps | 1367 | +| iterations | 2149 | +| time_elapsed | 3218 | +| total_timesteps | 4401152 | +| train/ | | +| approx_kl | 0.024937946 | +| clip_fraction | 0.365 | +| clip_range | 0.095 | +| entropy_loss | -7.53 | +| explained_variance | -0.177 | +| learning_rate | 0.000113 | +| loss | -0.0372 | +| n_updates | 8592 | +| policy_gradient_loss | -0.0265 | +| value_loss | 0.000166 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.264 | +| time/ | | +| fps | 1367 | +| iterations | 2150 | +| time_elapsed | 3219 | +| total_timesteps | 4403200 | +| train/ | | +| approx_kl | 0.03100832 | +| clip_fraction | 0.36 | +| clip_range | 0.095 | +| entropy_loss | -7.54 | +| explained_variance | -0.0935 | +| learning_rate | 0.000113 | +| loss | -0.0448 | +| n_updates | 8596 | +| policy_gradient_loss | -0.0257 | +| value_loss | 0.000202 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.26 | +| time/ | | +| fps | 1367 | +| iterations | 2151 | +| time_elapsed | 3221 | +| total_timesteps | 4405248 | +| train/ | | +| approx_kl | 0.024471743 | +| clip_fraction | 0.371 | +| clip_range | 0.095 | +| entropy_loss | -7.52 | +| explained_variance | 0.0219 | +| learning_rate | 0.000113 | +| loss | -0.0448 | +| n_updates | 8600 | +| policy_gradient_loss | -0.0274 | +| value_loss | 0.000267 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.261 | +| time/ | | +| fps | 1367 | +| iterations | 2152 | +| time_elapsed | 3222 | +| total_timesteps | 4407296 | +| train/ | | +| approx_kl | 0.026785638 | +| clip_fraction | 0.379 | +| clip_range | 0.0949 | +| entropy_loss | -7.41 | +| explained_variance | -0.136 | +| learning_rate | 0.000113 | +| loss | -0.0546 | +| n_updates | 8604 | +| policy_gradient_loss | -0.0319 | +| value_loss | 0.000172 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.265 | +| time/ | | +| fps | 1367 | +| iterations | 2153 | +| time_elapsed | 3224 | +| total_timesteps | 4409344 | +| train/ | | +| approx_kl | 0.027752288 | +| clip_fraction | 0.375 | +| clip_range | 0.0949 | +| entropy_loss | -7.33 | +| explained_variance | -0.184 | +| learning_rate | 0.000113 | +| loss | -0.0508 | +| n_updates | 8608 | +| policy_gradient_loss | -0.029 | +| value_loss | 0.000216 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.263 | +| time/ | | +| fps | 1367 | +| iterations | 2154 | +| time_elapsed | 3225 | +| total_timesteps | 4411392 | +| train/ | | +| approx_kl | 0.028114544 | +| clip_fraction | 0.376 | +| clip_range | 0.0949 | +| entropy_loss | -7.38 | +| explained_variance | -0.236 | +| learning_rate | 0.000113 | +| loss | -0.0408 | +| n_updates | 8612 | +| policy_gradient_loss | -0.0279 | +| value_loss | 0.000289 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.258 | +| time/ | | +| fps | 1367 | +| iterations | 2155 | +| time_elapsed | 3227 | +| total_timesteps | 4413440 | +| train/ | | +| approx_kl | 0.028402314 | +| clip_fraction | 0.405 | +| clip_range | 0.0949 | +| entropy_loss | -7.44 | +| explained_variance | -0.348 | +| learning_rate | 0.000113 | +| loss | -0.0517 | +| n_updates | 8616 | +| policy_gradient_loss | -0.0338 | +| value_loss | 0.000135 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.261 | +| time/ | | +| fps | 1367 | +| iterations | 2156 | +| time_elapsed | 3228 | +| total_timesteps | 4415488 | +| train/ | | +| approx_kl | 0.027935471 | +| clip_fraction | 0.428 | +| clip_range | 0.0948 | +| entropy_loss | -7.62 | +| explained_variance | -0.255 | +| learning_rate | 0.000113 | +| loss | -0.0519 | +| n_updates | 8620 | +| policy_gradient_loss | -0.0322 | +| value_loss | 0.00012 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.259 | +| time/ | | +| fps | 1367 | +| iterations | 2157 | +| time_elapsed | 3230 | +| total_timesteps | 4417536 | +| train/ | | +| approx_kl | 0.024894182 | +| clip_fraction | 0.368 | +| clip_range | 0.0948 | +| entropy_loss | -7.39 | +| explained_variance | -0.188 | +| learning_rate | 0.000113 | +| loss | -0.0463 | +| n_updates | 8624 | +| policy_gradient_loss | -0.0268 | +| value_loss | 0.000191 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.261 | +| time/ | | +| fps | 1367 | +| iterations | 2158 | +| time_elapsed | 3231 | +| total_timesteps | 4419584 | +| train/ | | +| approx_kl | 0.024055645 | +| clip_fraction | 0.354 | +| clip_range | 0.0948 | +| entropy_loss | -7.32 | +| explained_variance | -0.0758 | +| learning_rate | 0.000113 | +| loss | -0.0473 | +| n_updates | 8628 | +| policy_gradient_loss | -0.0266 | +| value_loss | 0.000196 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.254 | +| time/ | | +| fps | 1367 | +| iterations | 2159 | +| time_elapsed | 3233 | +| total_timesteps | 4421632 | +| train/ | | +| approx_kl | 0.031212296 | +| clip_fraction | 0.385 | +| clip_range | 0.0948 | +| entropy_loss | -7.38 | +| explained_variance | -0.412 | +| learning_rate | 0.000112 | +| loss | -0.044 | +| n_updates | 8632 | +| policy_gradient_loss | -0.0309 | +| value_loss | 0.000132 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.251 | +| time/ | | +| fps | 1367 | +| iterations | 2160 | +| time_elapsed | 3234 | +| total_timesteps | 4423680 | +| train/ | | +| approx_kl | 0.03104427 | +| clip_fraction | 0.378 | +| clip_range | 0.0947 | +| entropy_loss | -7.42 | +| explained_variance | -0.0791 | +| learning_rate | 0.000112 | +| loss | -0.0445 | +| n_updates | 8636 | +| policy_gradient_loss | -0.0282 | +| value_loss | 0.000213 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.254 | +| time/ | | +| fps | 1367 | +| iterations | 2161 | +| time_elapsed | 3236 | +| total_timesteps | 4425728 | +| train/ | | +| approx_kl | 0.028597426 | +| clip_fraction | 0.401 | +| clip_range | 0.0947 | +| entropy_loss | -7.39 | +| explained_variance | -0.178 | +| learning_rate | 0.000112 | +| loss | -0.0492 | +| n_updates | 8640 | +| policy_gradient_loss | -0.032 | +| value_loss | 0.00013 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.254 | +| time/ | | +| fps | 1367 | +| iterations | 2162 | +| time_elapsed | 3237 | +| total_timesteps | 4427776 | +| train/ | | +| approx_kl | 0.027786583 | +| clip_fraction | 0.371 | +| clip_range | 0.0947 | +| entropy_loss | -7.49 | +| explained_variance | -0.0419 | +| learning_rate | 0.000112 | +| loss | -0.0436 | +| n_updates | 8644 | +| policy_gradient_loss | -0.0281 | +| value_loss | 0.000236 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.243 | +| time/ | | +| fps | 1367 | +| iterations | 2163 | +| time_elapsed | 3238 | +| total_timesteps | 4429824 | +| train/ | | +| approx_kl | 0.025302589 | +| clip_fraction | 0.411 | +| clip_range | 0.0947 | +| entropy_loss | -7.49 | +| explained_variance | -0.151 | +| learning_rate | 0.000112 | +| loss | -0.0534 | +| n_updates | 8648 | +| policy_gradient_loss | -0.0304 | +| value_loss | 0.000125 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.244 | +| time/ | | +| fps | 1367 | +| iterations | 2164 | +| time_elapsed | 3240 | +| total_timesteps | 4431872 | +| train/ | | +| approx_kl | 0.028199604 | +| clip_fraction | 0.404 | +| clip_range | 0.0946 | +| entropy_loss | -7.36 | +| explained_variance | -0.0914 | +| learning_rate | 0.000112 | +| loss | -0.0445 | +| n_updates | 8652 | +| policy_gradient_loss | -0.0293 | +| value_loss | 0.000189 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.248 | +| time/ | | +| fps | 1367 | +| iterations | 2165 | +| time_elapsed | 3241 | +| total_timesteps | 4433920 | +| train/ | | +| approx_kl | 0.029659662 | +| clip_fraction | 0.375 | +| clip_range | 0.0946 | +| entropy_loss | -7.45 | +| explained_variance | -0.168 | +| learning_rate | 0.000112 | +| loss | -0.0402 | +| n_updates | 8656 | +| policy_gradient_loss | -0.0271 | +| value_loss | 0.000187 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.248 | +| time/ | | +| fps | 1367 | +| iterations | 2166 | +| time_elapsed | 3243 | +| total_timesteps | 4435968 | +| train/ | | +| approx_kl | 0.023784883 | +| clip_fraction | 0.375 | +| clip_range | 0.0946 | +| entropy_loss | -7.31 | +| explained_variance | 0.0581 | +| learning_rate | 0.000112 | +| loss | -0.0405 | +| n_updates | 8660 | +| policy_gradient_loss | -0.0239 | +| value_loss | 0.00031 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.252 | +| time/ | | +| fps | 1367 | +| iterations | 2167 | +| time_elapsed | 3244 | +| total_timesteps | 4438016 | +| train/ | | +| approx_kl | 0.026940377 | +| clip_fraction | 0.386 | +| clip_range | 0.0946 | +| entropy_loss | -7.38 | +| explained_variance | -0.214 | +| learning_rate | 0.000112 | +| loss | -0.0471 | +| n_updates | 8664 | +| policy_gradient_loss | -0.0314 | +| value_loss | 0.000222 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.255 | +| time/ | | +| fps | 1367 | +| iterations | 2168 | +| time_elapsed | 3246 | +| total_timesteps | 4440064 | +| train/ | | +| approx_kl | 0.025099322 | +| clip_fraction | 0.389 | +| clip_range | 0.0945 | +| entropy_loss | -7.4 | +| explained_variance | -0.146 | +| learning_rate | 0.000112 | +| loss | -0.0473 | +| n_updates | 8668 | +| policy_gradient_loss | -0.0262 | +| value_loss | 0.000337 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.262 | +| time/ | | +| fps | 1367 | +| iterations | 2169 | +| time_elapsed | 3247 | +| total_timesteps | 4442112 | +| train/ | | +| approx_kl | 0.026323888 | +| clip_fraction | 0.4 | +| clip_range | 0.0945 | +| entropy_loss | -7.42 | +| explained_variance | -0.271 | +| learning_rate | 0.000112 | +| loss | -0.0394 | +| n_updates | 8672 | +| policy_gradient_loss | -0.0287 | +| value_loss | 0.000217 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.266 | +| time/ | | +| fps | 1367 | +| iterations | 2170 | +| time_elapsed | 3249 | +| total_timesteps | 4444160 | +| train/ | | +| approx_kl | 0.027984746 | +| clip_fraction | 0.407 | +| clip_range | 0.0945 | +| entropy_loss | -7.34 | +| explained_variance | -0.0842 | +| learning_rate | 0.000112 | +| loss | -0.049 | +| n_updates | 8676 | +| policy_gradient_loss | -0.0278 | +| value_loss | 0.000266 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.262 | +| time/ | | +| fps | 1367 | +| iterations | 2171 | +| time_elapsed | 3250 | +| total_timesteps | 4446208 | +| train/ | | +| approx_kl | 0.02702858 | +| clip_fraction | 0.405 | +| clip_range | 0.0944 | +| entropy_loss | -7.33 | +| explained_variance | -0.23 | +| learning_rate | 0.000112 | +| loss | -0.0606 | +| n_updates | 8680 | +| policy_gradient_loss | -0.0337 | +| value_loss | 0.000142 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.256 | +| time/ | | +| fps | 1367 | +| iterations | 2172 | +| time_elapsed | 3252 | +| total_timesteps | 4448256 | +| train/ | | +| approx_kl | 0.026837265 | +| clip_fraction | 0.408 | +| clip_range | 0.0944 | +| entropy_loss | -7.36 | +| explained_variance | -0.129 | +| learning_rate | 0.000112 | +| loss | -0.0509 | +| n_updates | 8684 | +| policy_gradient_loss | -0.0319 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.259 | +| time/ | | +| fps | 1367 | +| iterations | 2173 | +| time_elapsed | 3253 | +| total_timesteps | 4450304 | +| train/ | | +| approx_kl | 0.026505925 | +| clip_fraction | 0.38 | +| clip_range | 0.0944 | +| entropy_loss | -7.41 | +| explained_variance | -0.227 | +| learning_rate | 0.000112 | +| loss | -0.0531 | +| n_updates | 8688 | +| policy_gradient_loss | -0.0309 | +| value_loss | 8.95e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.262 | +| time/ | | +| fps | 1367 | +| iterations | 2174 | +| time_elapsed | 3255 | +| total_timesteps | 4452352 | +| train/ | | +| approx_kl | 0.025426097 | +| clip_fraction | 0.378 | +| clip_range | 0.0944 | +| entropy_loss | -7.39 | +| explained_variance | -0.0709 | +| learning_rate | 0.000112 | +| loss | -0.0409 | +| n_updates | 8692 | +| policy_gradient_loss | -0.0257 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.265 | +| time/ | | +| fps | 1367 | +| iterations | 2175 | +| time_elapsed | 3256 | +| total_timesteps | 4454400 | +| train/ | | +| approx_kl | 0.025187762 | +| clip_fraction | 0.366 | +| clip_range | 0.0943 | +| entropy_loss | -7.28 | +| explained_variance | -0.0525 | +| learning_rate | 0.000112 | +| loss | -0.0407 | +| n_updates | 8696 | +| policy_gradient_loss | -0.0255 | +| value_loss | 0.000281 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.263 | +| time/ | | +| fps | 1367 | +| iterations | 2176 | +| time_elapsed | 3258 | +| total_timesteps | 4456448 | +| train/ | | +| approx_kl | 0.023314541 | +| clip_fraction | 0.362 | +| clip_range | 0.0943 | +| entropy_loss | -7.47 | +| explained_variance | -0.0241 | +| learning_rate | 0.000112 | +| loss | -0.0424 | +| n_updates | 8700 | +| policy_gradient_loss | -0.0263 | +| value_loss | 0.000254 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.268 | +| time/ | | +| fps | 1367 | +| iterations | 2177 | +| time_elapsed | 3259 | +| total_timesteps | 4458496 | +| train/ | | +| approx_kl | 0.031734675 | +| clip_fraction | 0.389 | +| clip_range | 0.0943 | +| entropy_loss | -7.41 | +| explained_variance | -0.246 | +| learning_rate | 0.000112 | +| loss | -0.0491 | +| n_updates | 8704 | +| policy_gradient_loss | -0.0307 | +| value_loss | 0.00015 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.258 | +| time/ | | +| fps | 1367 | +| iterations | 2178 | +| time_elapsed | 3260 | +| total_timesteps | 4460544 | +| train/ | | +| approx_kl | 0.029089151 | +| clip_fraction | 0.384 | +| clip_range | 0.0943 | +| entropy_loss | -7.61 | +| explained_variance | -0.0474 | +| learning_rate | 0.000112 | +| loss | -0.028 | +| n_updates | 8708 | +| policy_gradient_loss | -0.0263 | +| value_loss | 0.000272 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.258 | +| time/ | | +| fps | 1367 | +| iterations | 2179 | +| time_elapsed | 3262 | +| total_timesteps | 4462592 | +| train/ | | +| approx_kl | 0.026426528 | +| clip_fraction | 0.367 | +| clip_range | 0.0942 | +| entropy_loss | -7.39 | +| explained_variance | -0.232 | +| learning_rate | 0.000112 | +| loss | -0.0497 | +| n_updates | 8712 | +| policy_gradient_loss | -0.0297 | +| value_loss | 0.000162 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.258 | +| time/ | | +| fps | 1367 | +| iterations | 2180 | +| time_elapsed | 3263 | +| total_timesteps | 4464640 | +| train/ | | +| approx_kl | 0.027940385 | +| clip_fraction | 0.406 | +| clip_range | 0.0942 | +| entropy_loss | -7.49 | +| explained_variance | -0.247 | +| learning_rate | 0.000112 | +| loss | -0.0572 | +| n_updates | 8716 | +| policy_gradient_loss | -0.0327 | +| value_loss | 8.3e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.264 | +| time/ | | +| fps | 1367 | +| iterations | 2181 | +| time_elapsed | 3265 | +| total_timesteps | 4466688 | +| train/ | | +| approx_kl | 0.02544599 | +| clip_fraction | 0.352 | +| clip_range | 0.0942 | +| entropy_loss | -7.6 | +| explained_variance | -0.108 | +| learning_rate | 0.000112 | +| loss | -0.0416 | +| n_updates | 8720 | +| policy_gradient_loss | -0.0263 | +| value_loss | 0.000172 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.26 | +| time/ | | +| fps | 1367 | +| iterations | 2182 | +| time_elapsed | 3266 | +| total_timesteps | 4468736 | +| train/ | | +| approx_kl | 0.024791304 | +| clip_fraction | 0.338 | +| clip_range | 0.0942 | +| entropy_loss | -7.7 | +| explained_variance | -0.0626 | +| learning_rate | 0.000112 | +| loss | -0.041 | +| n_updates | 8724 | +| policy_gradient_loss | -0.026 | +| value_loss | 0.0003 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.259 | +| time/ | | +| fps | 1367 | +| iterations | 2183 | +| time_elapsed | 3268 | +| total_timesteps | 4470784 | +| train/ | | +| approx_kl | 0.028737199 | +| clip_fraction | 0.407 | +| clip_range | 0.0941 | +| entropy_loss | -7.43 | +| explained_variance | -0.311 | +| learning_rate | 0.000112 | +| loss | -0.0601 | +| n_updates | 8728 | +| policy_gradient_loss | -0.0353 | +| value_loss | 9.89e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.253 | +| time/ | | +| fps | 1368 | +| iterations | 2184 | +| time_elapsed | 3269 | +| total_timesteps | 4472832 | +| train/ | | +| approx_kl | 0.026596148 | +| clip_fraction | 0.397 | +| clip_range | 0.0941 | +| entropy_loss | -7.5 | +| explained_variance | -0.155 | +| learning_rate | 0.000111 | +| loss | -0.0463 | +| n_updates | 8732 | +| policy_gradient_loss | -0.0298 | +| value_loss | 0.000169 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.252 | +| time/ | | +| fps | 1368 | +| iterations | 2185 | +| time_elapsed | 3271 | +| total_timesteps | 4474880 | +| train/ | | +| approx_kl | 0.025185969 | +| clip_fraction | 0.374 | +| clip_range | 0.0941 | +| entropy_loss | -7.46 | +| explained_variance | -0.0921 | +| learning_rate | 0.000111 | +| loss | -0.0452 | +| n_updates | 8736 | +| policy_gradient_loss | -0.0288 | +| value_loss | 0.000118 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.252 | +| time/ | | +| fps | 1368 | +| iterations | 2186 | +| time_elapsed | 3272 | +| total_timesteps | 4476928 | +| train/ | | +| approx_kl | 0.023463702 | +| clip_fraction | 0.359 | +| clip_range | 0.0941 | +| entropy_loss | -7.47 | +| explained_variance | -0.0214 | +| learning_rate | 0.000111 | +| loss | -0.0418 | +| n_updates | 8740 | +| policy_gradient_loss | -0.0248 | +| value_loss | 0.000263 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.252 | +| time/ | | +| fps | 1367 | +| iterations | 2187 | +| time_elapsed | 3274 | +| total_timesteps | 4478976 | +| train/ | | +| approx_kl | 0.027445719 | +| clip_fraction | 0.394 | +| clip_range | 0.094 | +| entropy_loss | -7.6 | +| explained_variance | -0.0427 | +| learning_rate | 0.000111 | +| loss | -0.0506 | +| n_updates | 8744 | +| policy_gradient_loss | -0.0319 | +| value_loss | 0.000128 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.246 | +| time/ | | +| fps | 1368 | +| iterations | 2188 | +| time_elapsed | 3275 | +| total_timesteps | 4481024 | +| train/ | | +| approx_kl | 0.027852643 | +| clip_fraction | 0.37 | +| clip_range | 0.094 | +| entropy_loss | -7.63 | +| explained_variance | -0.262 | +| learning_rate | 0.000111 | +| loss | -0.0577 | +| n_updates | 8748 | +| policy_gradient_loss | -0.0329 | +| value_loss | 0.000121 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.247 | +| time/ | | +| fps | 1368 | +| iterations | 2189 | +| time_elapsed | 3277 | +| total_timesteps | 4483072 | +| train/ | | +| approx_kl | 0.027526438 | +| clip_fraction | 0.372 | +| clip_range | 0.094 | +| entropy_loss | -7.44 | +| explained_variance | -0.326 | +| learning_rate | 0.000111 | +| loss | -0.046 | +| n_updates | 8752 | +| policy_gradient_loss | -0.0306 | +| value_loss | 7.2e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.252 | +| time/ | | +| fps | 1368 | +| iterations | 2190 | +| time_elapsed | 3278 | +| total_timesteps | 4485120 | +| train/ | | +| approx_kl | 0.030093122 | +| clip_fraction | 0.376 | +| clip_range | 0.094 | +| entropy_loss | -7.44 | +| explained_variance | -0.115 | +| learning_rate | 0.000111 | +| loss | -0.0473 | +| n_updates | 8756 | +| policy_gradient_loss | -0.0288 | +| value_loss | 9.08e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.25 | +| time/ | | +| fps | 1367 | +| iterations | 2191 | +| time_elapsed | 3280 | +| total_timesteps | 4487168 | +| train/ | | +| approx_kl | 0.024729887 | +| clip_fraction | 0.354 | +| clip_range | 0.0939 | +| entropy_loss | -7.43 | +| explained_variance | -0.11 | +| learning_rate | 0.000111 | +| loss | -0.0422 | +| n_updates | 8760 | +| policy_gradient_loss | -0.0274 | +| value_loss | 0.000202 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.255 | +| time/ | | +| fps | 1368 | +| iterations | 2192 | +| time_elapsed | 3281 | +| total_timesteps | 4489216 | +| train/ | | +| approx_kl | 0.025474187 | +| clip_fraction | 0.386 | +| clip_range | 0.0939 | +| entropy_loss | -7.35 | +| explained_variance | -0.358 | +| learning_rate | 0.000111 | +| loss | -0.053 | +| n_updates | 8764 | +| policy_gradient_loss | -0.0286 | +| value_loss | 0.000148 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.255 | +| time/ | | +| fps | 1368 | +| iterations | 2193 | +| time_elapsed | 3283 | +| total_timesteps | 4491264 | +| train/ | | +| approx_kl | 0.0341034 | +| clip_fraction | 0.376 | +| clip_range | 0.0939 | +| entropy_loss | -7.42 | +| explained_variance | -0.0958 | +| learning_rate | 0.000111 | +| loss | -0.0496 | +| n_updates | 8768 | +| policy_gradient_loss | -0.0287 | +| value_loss | 0.000108 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.255 | +| time/ | | +| fps | 1368 | +| iterations | 2194 | +| time_elapsed | 3284 | +| total_timesteps | 4493312 | +| train/ | | +| approx_kl | 0.022574116 | +| clip_fraction | 0.368 | +| clip_range | 0.0939 | +| entropy_loss | -7.55 | +| explained_variance | 0.0659 | +| learning_rate | 0.000111 | +| loss | -0.0443 | +| n_updates | 8772 | +| policy_gradient_loss | -0.0266 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.255 | +| time/ | | +| fps | 1368 | +| iterations | 2195 | +| time_elapsed | 3286 | +| total_timesteps | 4495360 | +| train/ | | +| approx_kl | 0.026471805 | +| clip_fraction | 0.343 | +| clip_range | 0.0938 | +| entropy_loss | -7.58 | +| explained_variance | -0.103 | +| learning_rate | 0.000111 | +| loss | -0.0494 | +| n_updates | 8776 | +| policy_gradient_loss | -0.028 | +| value_loss | 0.000166 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.257 | +| time/ | | +| fps | 1368 | +| iterations | 2196 | +| time_elapsed | 3287 | +| total_timesteps | 4497408 | +| train/ | | +| approx_kl | 0.026577646 | +| clip_fraction | 0.392 | +| clip_range | 0.0938 | +| entropy_loss | -7.5 | +| explained_variance | -0.0932 | +| learning_rate | 0.000111 | +| loss | -0.0505 | +| n_updates | 8780 | +| policy_gradient_loss | -0.0303 | +| value_loss | 0.000156 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.261 | +| time/ | | +| fps | 1368 | +| iterations | 2197 | +| time_elapsed | 3288 | +| total_timesteps | 4499456 | +| train/ | | +| approx_kl | 0.025306247 | +| clip_fraction | 0.384 | +| clip_range | 0.0938 | +| entropy_loss | -7.47 | +| explained_variance | -0.206 | +| learning_rate | 0.000111 | +| loss | -0.0505 | +| n_updates | 8784 | +| policy_gradient_loss | -0.0312 | +| value_loss | 8.33e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.261 | +| time/ | | +| fps | 1368 | +| iterations | 2198 | +| time_elapsed | 3290 | +| total_timesteps | 4501504 | +| train/ | | +| approx_kl | 0.02244658 | +| clip_fraction | 0.371 | +| clip_range | 0.0938 | +| entropy_loss | -7.48 | +| explained_variance | -0.0664 | +| learning_rate | 0.000111 | +| loss | -0.0403 | +| n_updates | 8788 | +| policy_gradient_loss | -0.0261 | +| value_loss | 0.000255 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.261 | +| time/ | | +| fps | 1368 | +| iterations | 2199 | +| time_elapsed | 3291 | +| total_timesteps | 4503552 | +| train/ | | +| approx_kl | 0.023467334 | +| clip_fraction | 0.396 | +| clip_range | 0.0937 | +| entropy_loss | -7.58 | +| explained_variance | -0.0446 | +| learning_rate | 0.000111 | +| loss | -0.0459 | +| n_updates | 8792 | +| policy_gradient_loss | -0.0321 | +| value_loss | 0.000134 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.261 | +| time/ | | +| fps | 1368 | +| iterations | 2200 | +| time_elapsed | 3293 | +| total_timesteps | 4505600 | +| train/ | | +| approx_kl | 0.025332648 | +| clip_fraction | 0.359 | +| clip_range | 0.0937 | +| entropy_loss | -7.64 | +| explained_variance | -0.099 | +| learning_rate | 0.000111 | +| loss | -0.0407 | +| n_updates | 8796 | +| policy_gradient_loss | -0.0257 | +| value_loss | 0.000228 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.268 | +| time/ | | +| fps | 1368 | +| iterations | 2201 | +| time_elapsed | 3294 | +| total_timesteps | 4507648 | +| train/ | | +| approx_kl | 0.022692248 | +| clip_fraction | 0.407 | +| clip_range | 0.0937 | +| entropy_loss | -7.59 | +| explained_variance | -0.157 | +| learning_rate | 0.000111 | +| loss | -0.0485 | +| n_updates | 8800 | +| policy_gradient_loss | -0.0291 | +| value_loss | 0.000109 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.263 | +| time/ | | +| fps | 1368 | +| iterations | 2202 | +| time_elapsed | 3296 | +| total_timesteps | 4509696 | +| train/ | | +| approx_kl | 0.022157196 | +| clip_fraction | 0.361 | +| clip_range | 0.0937 | +| entropy_loss | -7.36 | +| explained_variance | -0.0606 | +| learning_rate | 0.000111 | +| loss | -0.0307 | +| n_updates | 8804 | +| policy_gradient_loss | -0.024 | +| value_loss | 0.000284 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.264 | +| time/ | | +| fps | 1368 | +| iterations | 2203 | +| time_elapsed | 3297 | +| total_timesteps | 4511744 | +| train/ | | +| approx_kl | 0.024312865 | +| clip_fraction | 0.376 | +| clip_range | 0.0936 | +| entropy_loss | -7.18 | +| explained_variance | -0.0953 | +| learning_rate | 0.000111 | +| loss | -0.0401 | +| n_updates | 8808 | +| policy_gradient_loss | -0.0249 | +| value_loss | 0.000183 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.264 | +| time/ | | +| fps | 1368 | +| iterations | 2204 | +| time_elapsed | 3299 | +| total_timesteps | 4513792 | +| train/ | | +| approx_kl | 0.027861655 | +| clip_fraction | 0.384 | +| clip_range | 0.0936 | +| entropy_loss | -7.36 | +| explained_variance | -0.0779 | +| learning_rate | 0.000111 | +| loss | -0.0464 | +| n_updates | 8812 | +| policy_gradient_loss | -0.0288 | +| value_loss | 0.000235 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.267 | +| time/ | | +| fps | 1368 | +| iterations | 2205 | +| time_elapsed | 3300 | +| total_timesteps | 4515840 | +| train/ | | +| approx_kl | 0.024109691 | +| clip_fraction | 0.391 | +| clip_range | 0.0936 | +| entropy_loss | -7.6 | +| explained_variance | -0.429 | +| learning_rate | 0.000111 | +| loss | -0.0498 | +| n_updates | 8816 | +| policy_gradient_loss | -0.0308 | +| value_loss | 9.77e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.271 | +| time/ | | +| fps | 1368 | +| iterations | 2206 | +| time_elapsed | 3302 | +| total_timesteps | 4517888 | +| train/ | | +| approx_kl | 0.022352416 | +| clip_fraction | 0.38 | +| clip_range | 0.0936 | +| entropy_loss | -7.58 | +| explained_variance | -0.112 | +| learning_rate | 0.000111 | +| loss | -0.0447 | +| n_updates | 8820 | +| policy_gradient_loss | -0.0257 | +| value_loss | 0.00019 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.27 | +| time/ | | +| fps | 1368 | +| iterations | 2207 | +| time_elapsed | 3303 | +| total_timesteps | 4519936 | +| train/ | | +| approx_kl | 0.026720477 | +| clip_fraction | 0.375 | +| clip_range | 0.0935 | +| entropy_loss | -7.37 | +| explained_variance | -0.0801 | +| learning_rate | 0.000111 | +| loss | -0.0447 | +| n_updates | 8824 | +| policy_gradient_loss | -0.0263 | +| value_loss | 0.000239 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.27 | +| time/ | | +| fps | 1368 | +| iterations | 2208 | +| time_elapsed | 3305 | +| total_timesteps | 4521984 | +| train/ | | +| approx_kl | 0.022592612 | +| clip_fraction | 0.371 | +| clip_range | 0.0935 | +| entropy_loss | -7.54 | +| explained_variance | -0.0995 | +| learning_rate | 0.000111 | +| loss | -0.0412 | +| n_updates | 8828 | +| policy_gradient_loss | -0.0277 | +| value_loss | 0.00023 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.277 | +| time/ | | +| fps | 1368 | +| iterations | 2209 | +| time_elapsed | 3306 | +| total_timesteps | 4524032 | +| train/ | | +| approx_kl | 0.02422655 | +| clip_fraction | 0.386 | +| clip_range | 0.0935 | +| entropy_loss | -7.61 | +| explained_variance | -0.192 | +| learning_rate | 0.00011 | +| loss | -0.0407 | +| n_updates | 8832 | +| policy_gradient_loss | -0.0282 | +| value_loss | 0.000166 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.277 | +| time/ | | +| fps | 1368 | +| iterations | 2210 | +| time_elapsed | 3308 | +| total_timesteps | 4526080 | +| train/ | | +| approx_kl | 0.02195281 | +| clip_fraction | 0.344 | +| clip_range | 0.0934 | +| entropy_loss | -7.55 | +| explained_variance | -0.0921 | +| learning_rate | 0.00011 | +| loss | -0.0335 | +| n_updates | 8836 | +| policy_gradient_loss | -0.0231 | +| value_loss | 0.000279 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 1368 | +| iterations | 2211 | +| time_elapsed | 3309 | +| total_timesteps | 4528128 | +| train/ | | +| approx_kl | 0.02211624 | +| clip_fraction | 0.384 | +| clip_range | 0.0934 | +| entropy_loss | -7.61 | +| explained_variance | -0.105 | +| learning_rate | 0.00011 | +| loss | -0.0448 | +| n_updates | 8840 | +| policy_gradient_loss | -0.0298 | +| value_loss | 0.000143 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.278 | +| time/ | | +| fps | 1368 | +| iterations | 2212 | +| time_elapsed | 3311 | +| total_timesteps | 4530176 | +| train/ | | +| approx_kl | 0.023426875 | +| clip_fraction | 0.354 | +| clip_range | 0.0934 | +| entropy_loss | -7.37 | +| explained_variance | -0.0975 | +| learning_rate | 0.00011 | +| loss | -0.0482 | +| n_updates | 8844 | +| policy_gradient_loss | -0.0254 | +| value_loss | 0.000234 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.278 | +| time/ | | +| fps | 1367 | +| iterations | 2213 | +| time_elapsed | 3313 | +| total_timesteps | 4532224 | +| train/ | | +| approx_kl | 0.025845718 | +| clip_fraction | 0.394 | +| clip_range | 0.0934 | +| entropy_loss | -7.49 | +| explained_variance | -0.224 | +| learning_rate | 0.00011 | +| loss | -0.0477 | +| n_updates | 8848 | +| policy_gradient_loss | -0.0293 | +| value_loss | 0.000171 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.285 | +| time/ | | +| fps | 1367 | +| iterations | 2214 | +| time_elapsed | 3314 | +| total_timesteps | 4534272 | +| train/ | | +| approx_kl | 0.023975525 | +| clip_fraction | 0.4 | +| clip_range | 0.0933 | +| entropy_loss | -7.44 | +| explained_variance | -0.288 | +| learning_rate | 0.00011 | +| loss | -0.0424 | +| n_updates | 8852 | +| policy_gradient_loss | -0.0306 | +| value_loss | 8.71e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.281 | +| time/ | | +| fps | 1367 | +| iterations | 2215 | +| time_elapsed | 3316 | +| total_timesteps | 4536320 | +| train/ | | +| approx_kl | 0.020742014 | +| clip_fraction | 0.343 | +| clip_range | 0.0933 | +| entropy_loss | -7.24 | +| explained_variance | -0.0369 | +| learning_rate | 0.00011 | +| loss | -0.0412 | +| n_updates | 8856 | +| policy_gradient_loss | -0.023 | +| value_loss | 0.000208 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.268 | +| time/ | | +| fps | 1367 | +| iterations | 2216 | +| time_elapsed | 3317 | +| total_timesteps | 4538368 | +| train/ | | +| approx_kl | 0.029014658 | +| clip_fraction | 0.401 | +| clip_range | 0.0933 | +| entropy_loss | -7.49 | +| explained_variance | -0.113 | +| learning_rate | 0.00011 | +| loss | -0.0441 | +| n_updates | 8860 | +| policy_gradient_loss | -0.0304 | +| value_loss | 0.00016 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.277 | +| time/ | | +| fps | 1367 | +| iterations | 2217 | +| time_elapsed | 3319 | +| total_timesteps | 4540416 | +| train/ | | +| approx_kl | 0.026685756 | +| clip_fraction | 0.379 | +| clip_range | 0.0933 | +| entropy_loss | -7.36 | +| explained_variance | -0.0533 | +| learning_rate | 0.00011 | +| loss | -0.0377 | +| n_updates | 8864 | +| policy_gradient_loss | -0.0279 | +| value_loss | 0.000163 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.277 | +| time/ | | +| fps | 1367 | +| iterations | 2218 | +| time_elapsed | 3320 | +| total_timesteps | 4542464 | +| train/ | | +| approx_kl | 0.022986965 | +| clip_fraction | 0.391 | +| clip_range | 0.0932 | +| entropy_loss | -7.4 | +| explained_variance | 0.00369 | +| learning_rate | 0.00011 | +| loss | -0.0444 | +| n_updates | 8868 | +| policy_gradient_loss | -0.0304 | +| value_loss | 0.00013 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.268 | +| time/ | | +| fps | 1367 | +| iterations | 2219 | +| time_elapsed | 3322 | +| total_timesteps | 4544512 | +| train/ | | +| approx_kl | 0.02350648 | +| clip_fraction | 0.38 | +| clip_range | 0.0932 | +| entropy_loss | -7.55 | +| explained_variance | -0.00311 | +| learning_rate | 0.00011 | +| loss | -0.0405 | +| n_updates | 8872 | +| policy_gradient_loss | -0.0282 | +| value_loss | 0.000135 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.264 | +| time/ | | +| fps | 1367 | +| iterations | 2220 | +| time_elapsed | 3324 | +| total_timesteps | 4546560 | +| train/ | | +| approx_kl | 0.020929474 | +| clip_fraction | 0.322 | +| clip_range | 0.0932 | +| entropy_loss | -7.43 | +| explained_variance | -0.0362 | +| learning_rate | 0.00011 | +| loss | -0.0383 | +| n_updates | 8876 | +| policy_gradient_loss | -0.0227 | +| value_loss | 0.000218 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.261 | +| time/ | | +| fps | 1367 | +| iterations | 2221 | +| time_elapsed | 3325 | +| total_timesteps | 4548608 | +| train/ | | +| approx_kl | 0.024465136 | +| clip_fraction | 0.401 | +| clip_range | 0.0932 | +| entropy_loss | -7.55 | +| explained_variance | -0.438 | +| learning_rate | 0.00011 | +| loss | -0.0613 | +| n_updates | 8880 | +| policy_gradient_loss | -0.0342 | +| value_loss | 8.01e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.261 | +| time/ | | +| fps | 1367 | +| iterations | 2222 | +| time_elapsed | 3327 | +| total_timesteps | 4550656 | +| train/ | | +| approx_kl | 0.02518843 | +| clip_fraction | 0.375 | +| clip_range | 0.0931 | +| entropy_loss | -7.5 | +| explained_variance | -0.146 | +| learning_rate | 0.00011 | +| loss | -0.0482 | +| n_updates | 8884 | +| policy_gradient_loss | -0.0302 | +| value_loss | 0.00017 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.265 | +| time/ | | +| fps | 1367 | +| iterations | 2223 | +| time_elapsed | 3328 | +| total_timesteps | 4552704 | +| train/ | | +| approx_kl | 0.022022419 | +| clip_fraction | 0.375 | +| clip_range | 0.0931 | +| entropy_loss | -7.53 | +| explained_variance | -0.0235 | +| learning_rate | 0.00011 | +| loss | -0.0418 | +| n_updates | 8888 | +| policy_gradient_loss | -0.027 | +| value_loss | 0.000143 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.27 | +| time/ | | +| fps | 1367 | +| iterations | 2224 | +| time_elapsed | 3330 | +| total_timesteps | 4554752 | +| train/ | | +| approx_kl | 0.021442052 | +| clip_fraction | 0.375 | +| clip_range | 0.0931 | +| entropy_loss | -7.49 | +| explained_variance | 0.0326 | +| learning_rate | 0.00011 | +| loss | -0.0341 | +| n_updates | 8892 | +| policy_gradient_loss | -0.0261 | +| value_loss | 0.000281 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.271 | +| time/ | | +| fps | 1367 | +| iterations | 2225 | +| time_elapsed | 3331 | +| total_timesteps | 4556800 | +| train/ | | +| approx_kl | 0.021216068 | +| clip_fraction | 0.385 | +| clip_range | 0.0931 | +| entropy_loss | -7.57 | +| explained_variance | -0.261 | +| learning_rate | 0.00011 | +| loss | -0.0465 | +| n_updates | 8896 | +| policy_gradient_loss | -0.0286 | +| value_loss | 0.00014 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.274 | +| time/ | | +| fps | 1367 | +| iterations | 2226 | +| time_elapsed | 3333 | +| total_timesteps | 4558848 | +| train/ | | +| approx_kl | 0.02176389 | +| clip_fraction | 0.354 | +| clip_range | 0.093 | +| entropy_loss | -7.51 | +| explained_variance | -0.108 | +| learning_rate | 0.00011 | +| loss | -0.0458 | +| n_updates | 8900 | +| policy_gradient_loss | -0.0271 | +| value_loss | 0.000168 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.274 | +| time/ | | +| fps | 1367 | +| iterations | 2227 | +| time_elapsed | 3334 | +| total_timesteps | 4560896 | +| train/ | | +| approx_kl | 0.024101311 | +| clip_fraction | 0.36 | +| clip_range | 0.093 | +| entropy_loss | -7.52 | +| explained_variance | -0.0962 | +| learning_rate | 0.00011 | +| loss | -0.0451 | +| n_updates | 8904 | +| policy_gradient_loss | -0.0283 | +| value_loss | 0.000145 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.274 | +| time/ | | +| fps | 1367 | +| iterations | 2228 | +| time_elapsed | 3336 | +| total_timesteps | 4562944 | +| train/ | | +| approx_kl | 0.023937497 | +| clip_fraction | 0.383 | +| clip_range | 0.093 | +| entropy_loss | -7.3 | +| explained_variance | 0.0713 | +| learning_rate | 0.00011 | +| loss | -0.0555 | +| n_updates | 8908 | +| policy_gradient_loss | -0.0296 | +| value_loss | 9.23e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.27 | +| time/ | | +| fps | 1367 | +| iterations | 2229 | +| time_elapsed | 3337 | +| total_timesteps | 4564992 | +| train/ | | +| approx_kl | 0.024729034 | +| clip_fraction | 0.357 | +| clip_range | 0.093 | +| entropy_loss | -7.61 | +| explained_variance | -0.243 | +| learning_rate | 0.00011 | +| loss | -0.0504 | +| n_updates | 8912 | +| policy_gradient_loss | -0.0276 | +| value_loss | 0.000105 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.27 | +| time/ | | +| fps | 1367 | +| iterations | 2230 | +| time_elapsed | 3339 | +| total_timesteps | 4567040 | +| train/ | | +| approx_kl | 0.026324917 | +| clip_fraction | 0.354 | +| clip_range | 0.0929 | +| entropy_loss | -7.4 | +| explained_variance | -0.0606 | +| learning_rate | 0.00011 | +| loss | -0.0443 | +| n_updates | 8916 | +| policy_gradient_loss | -0.0273 | +| value_loss | 0.000161 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.274 | +| time/ | | +| fps | 1367 | +| iterations | 2231 | +| time_elapsed | 3340 | +| total_timesteps | 4569088 | +| train/ | | +| approx_kl | 0.029833358 | +| clip_fraction | 0.364 | +| clip_range | 0.0929 | +| entropy_loss | -7.6 | +| explained_variance | -0.311 | +| learning_rate | 0.00011 | +| loss | -0.0434 | +| n_updates | 8920 | +| policy_gradient_loss | -0.0278 | +| value_loss | 0.000113 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.272 | +| time/ | | +| fps | 1367 | +| iterations | 2232 | +| time_elapsed | 3342 | +| total_timesteps | 4571136 | +| train/ | | +| approx_kl | 0.023742933 | +| clip_fraction | 0.367 | +| clip_range | 0.0929 | +| entropy_loss | -7.61 | +| explained_variance | -0.0711 | +| learning_rate | 0.00011 | +| loss | -0.042 | +| n_updates | 8924 | +| policy_gradient_loss | -0.0263 | +| value_loss | 0.000332 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.269 | +| time/ | | +| fps | 1367 | +| iterations | 2233 | +| time_elapsed | 3344 | +| total_timesteps | 4573184 | +| train/ | | +| approx_kl | 0.02603778 | +| clip_fraction | 0.374 | +| clip_range | 0.0929 | +| entropy_loss | -7.57 | +| explained_variance | -0.273 | +| learning_rate | 0.000109 | +| loss | -0.0482 | +| n_updates | 8928 | +| policy_gradient_loss | -0.0305 | +| value_loss | 0.000153 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.263 | +| time/ | | +| fps | 1367 | +| iterations | 2234 | +| time_elapsed | 3345 | +| total_timesteps | 4575232 | +| train/ | | +| approx_kl | 0.02554234 | +| clip_fraction | 0.398 | +| clip_range | 0.0928 | +| entropy_loss | -7.48 | +| explained_variance | -0.264 | +| learning_rate | 0.000109 | +| loss | -0.0522 | +| n_updates | 8932 | +| policy_gradient_loss | -0.0324 | +| value_loss | 8.73e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.259 | +| time/ | | +| fps | 1367 | +| iterations | 2235 | +| time_elapsed | 3347 | +| total_timesteps | 4577280 | +| train/ | | +| approx_kl | 0.026980363 | +| clip_fraction | 0.38 | +| clip_range | 0.0928 | +| entropy_loss | -7.43 | +| explained_variance | -0.0522 | +| learning_rate | 0.000109 | +| loss | -0.0469 | +| n_updates | 8936 | +| policy_gradient_loss | -0.029 | +| value_loss | 0.000122 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.262 | +| time/ | | +| fps | 1367 | +| iterations | 2236 | +| time_elapsed | 3348 | +| total_timesteps | 4579328 | +| train/ | | +| approx_kl | 0.026316134 | +| clip_fraction | 0.414 | +| clip_range | 0.0928 | +| entropy_loss | -7.48 | +| explained_variance | -0.0405 | +| learning_rate | 0.000109 | +| loss | -0.0439 | +| n_updates | 8940 | +| policy_gradient_loss | -0.029 | +| value_loss | 0.000113 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.265 | +| time/ | | +| fps | 1367 | +| iterations | 2237 | +| time_elapsed | 3350 | +| total_timesteps | 4581376 | +| train/ | | +| approx_kl | 0.027605347 | +| clip_fraction | 0.36 | +| clip_range | 0.0928 | +| entropy_loss | -7.53 | +| explained_variance | -0.0204 | +| learning_rate | 0.000109 | +| loss | -0.0358 | +| n_updates | 8944 | +| policy_gradient_loss | -0.0234 | +| value_loss | 0.000205 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.269 | +| time/ | | +| fps | 1367 | +| iterations | 2238 | +| time_elapsed | 3351 | +| total_timesteps | 4583424 | +| train/ | | +| approx_kl | 0.025083836 | +| clip_fraction | 0.374 | +| clip_range | 0.0927 | +| entropy_loss | -7.43 | +| explained_variance | -0.175 | +| learning_rate | 0.000109 | +| loss | -0.0412 | +| n_updates | 8948 | +| policy_gradient_loss | -0.0283 | +| value_loss | 0.000183 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.269 | +| time/ | | +| fps | 1367 | +| iterations | 2239 | +| time_elapsed | 3353 | +| total_timesteps | 4585472 | +| train/ | | +| approx_kl | 0.022189658 | +| clip_fraction | 0.372 | +| clip_range | 0.0927 | +| entropy_loss | -7.54 | +| explained_variance | -0.141 | +| learning_rate | 0.000109 | +| loss | -0.0392 | +| n_updates | 8952 | +| policy_gradient_loss | -0.0269 | +| value_loss | 0.000304 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.274 | +| time/ | | +| fps | 1367 | +| iterations | 2240 | +| time_elapsed | 3354 | +| total_timesteps | 4587520 | +| train/ | | +| approx_kl | 0.026242599 | +| clip_fraction | 0.4 | +| clip_range | 0.0927 | +| entropy_loss | -7.58 | +| explained_variance | -0.146 | +| learning_rate | 0.000109 | +| loss | -0.0531 | +| n_updates | 8956 | +| policy_gradient_loss | -0.0334 | +| value_loss | 0.000137 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.273 | +| time/ | | +| fps | 1367 | +| iterations | 2241 | +| time_elapsed | 3356 | +| total_timesteps | 4589568 | +| train/ | | +| approx_kl | 0.024437182 | +| clip_fraction | 0.385 | +| clip_range | 0.0927 | +| entropy_loss | -7.49 | +| explained_variance | -0.333 | +| learning_rate | 0.000109 | +| loss | -0.0362 | +| n_updates | 8960 | +| policy_gradient_loss | -0.0278 | +| value_loss | 0.000152 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.271 | +| time/ | | +| fps | 1367 | +| iterations | 2242 | +| time_elapsed | 3358 | +| total_timesteps | 4591616 | +| train/ | | +| approx_kl | 0.023765778 | +| clip_fraction | 0.363 | +| clip_range | 0.0926 | +| entropy_loss | -7.54 | +| explained_variance | -0.0742 | +| learning_rate | 0.000109 | +| loss | -0.0414 | +| n_updates | 8964 | +| policy_gradient_loss | -0.0283 | +| value_loss | 0.00014 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.269 | +| time/ | | +| fps | 1367 | +| iterations | 2243 | +| time_elapsed | 3359 | +| total_timesteps | 4593664 | +| train/ | | +| approx_kl | 0.023245418 | +| clip_fraction | 0.369 | +| clip_range | 0.0926 | +| entropy_loss | -7.46 | +| explained_variance | -0.0329 | +| learning_rate | 0.000109 | +| loss | -0.0375 | +| n_updates | 8968 | +| policy_gradient_loss | -0.0273 | +| value_loss | 0.000422 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.268 | +| time/ | | +| fps | 1367 | +| iterations | 2244 | +| time_elapsed | 3361 | +| total_timesteps | 4595712 | +| train/ | | +| approx_kl | 0.023955535 | +| clip_fraction | 0.373 | +| clip_range | 0.0926 | +| entropy_loss | -7.55 | +| explained_variance | -0.183 | +| learning_rate | 0.000109 | +| loss | -0.0476 | +| n_updates | 8972 | +| policy_gradient_loss | -0.0291 | +| value_loss | 0.000241 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.269 | +| time/ | | +| fps | 1367 | +| iterations | 2245 | +| time_elapsed | 3362 | +| total_timesteps | 4597760 | +| train/ | | +| approx_kl | 0.025758015 | +| clip_fraction | 0.371 | +| clip_range | 0.0926 | +| entropy_loss | -7.52 | +| explained_variance | -0.167 | +| learning_rate | 0.000109 | +| loss | -0.0442 | +| n_updates | 8976 | +| policy_gradient_loss | -0.0254 | +| value_loss | 0.000235 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.276 | +| time/ | | +| fps | 1367 | +| iterations | 2246 | +| time_elapsed | 3364 | +| total_timesteps | 4599808 | +| train/ | | +| approx_kl | 0.022353511 | +| clip_fraction | 0.373 | +| clip_range | 0.0925 | +| entropy_loss | -7.49 | +| explained_variance | -0.188 | +| learning_rate | 0.000109 | +| loss | -0.0467 | +| n_updates | 8980 | +| policy_gradient_loss | -0.0277 | +| value_loss | 0.000213 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 1367 | +| iterations | 2247 | +| time_elapsed | 3365 | +| total_timesteps | 4601856 | +| train/ | | +| approx_kl | 0.023340922 | +| clip_fraction | 0.362 | +| clip_range | 0.0925 | +| entropy_loss | -7.57 | +| explained_variance | -0.0315 | +| learning_rate | 0.000109 | +| loss | -0.0388 | +| n_updates | 8984 | +| policy_gradient_loss | -0.026 | +| value_loss | 0.000288 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.274 | +| time/ | | +| fps | 1367 | +| iterations | 2248 | +| time_elapsed | 3367 | +| total_timesteps | 4603904 | +| train/ | | +| approx_kl | 0.022791607 | +| clip_fraction | 0.365 | +| clip_range | 0.0925 | +| entropy_loss | -7.4 | +| explained_variance | -0.148 | +| learning_rate | 0.000109 | +| loss | -0.0351 | +| n_updates | 8988 | +| policy_gradient_loss | -0.0267 | +| value_loss | 0.000179 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.274 | +| time/ | | +| fps | 1367 | +| iterations | 2249 | +| time_elapsed | 3368 | +| total_timesteps | 4605952 | +| train/ | | +| approx_kl | 0.026651155 | +| clip_fraction | 0.364 | +| clip_range | 0.0925 | +| entropy_loss | -7.6 | +| explained_variance | -0.089 | +| learning_rate | 0.000109 | +| loss | -0.0432 | +| n_updates | 8992 | +| policy_gradient_loss | -0.0283 | +| value_loss | 0.000175 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.274 | +| time/ | | +| fps | 1367 | +| iterations | 2250 | +| time_elapsed | 3370 | +| total_timesteps | 4608000 | +| train/ | | +| approx_kl | 0.025112977 | +| clip_fraction | 0.376 | +| clip_range | 0.0924 | +| entropy_loss | -7.56 | +| explained_variance | -0.213 | +| learning_rate | 0.000109 | +| loss | -0.0534 | +| n_updates | 8996 | +| policy_gradient_loss | -0.0301 | +| value_loss | 0.000111 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 1367 | +| iterations | 2251 | +| time_elapsed | 3371 | +| total_timesteps | 4610048 | +| train/ | | +| approx_kl | 0.023026206 | +| clip_fraction | 0.367 | +| clip_range | 0.0924 | +| entropy_loss | -7.48 | +| explained_variance | -0.0935 | +| learning_rate | 0.000109 | +| loss | -0.047 | +| n_updates | 9000 | +| policy_gradient_loss | -0.0267 | +| value_loss | 0.000176 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.285 | +| time/ | | +| fps | 1367 | +| iterations | 2252 | +| time_elapsed | 3373 | +| total_timesteps | 4612096 | +| train/ | | +| approx_kl | 0.024203869 | +| clip_fraction | 0.357 | +| clip_range | 0.0924 | +| entropy_loss | -7.47 | +| explained_variance | -0.0222 | +| learning_rate | 0.000109 | +| loss | -0.0405 | +| n_updates | 9004 | +| policy_gradient_loss | -0.0259 | +| value_loss | 0.000323 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.288 | +| time/ | | +| fps | 1367 | +| iterations | 2253 | +| time_elapsed | 3374 | +| total_timesteps | 4614144 | +| train/ | | +| approx_kl | 0.026473131 | +| clip_fraction | 0.392 | +| clip_range | 0.0923 | +| entropy_loss | -7.31 | +| explained_variance | -0.226 | +| learning_rate | 0.000109 | +| loss | -0.0445 | +| n_updates | 9008 | +| policy_gradient_loss | -0.0305 | +| value_loss | 0.000277 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.288 | +| time/ | | +| fps | 1367 | +| iterations | 2254 | +| time_elapsed | 3376 | +| total_timesteps | 4616192 | +| train/ | | +| approx_kl | 0.02435765 | +| clip_fraction | 0.365 | +| clip_range | 0.0923 | +| entropy_loss | -7.52 | +| explained_variance | -0.234 | +| learning_rate | 0.000109 | +| loss | -0.0426 | +| n_updates | 9012 | +| policy_gradient_loss | -0.0261 | +| value_loss | 0.000229 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.288 | +| time/ | | +| fps | 1367 | +| iterations | 2255 | +| time_elapsed | 3378 | +| total_timesteps | 4618240 | +| train/ | | +| approx_kl | 0.023925766 | +| clip_fraction | 0.376 | +| clip_range | 0.0923 | +| entropy_loss | -7.58 | +| explained_variance | -0.216 | +| learning_rate | 0.000109 | +| loss | -0.0467 | +| n_updates | 9016 | +| policy_gradient_loss | -0.0298 | +| value_loss | 0.000165 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.29 | +| time/ | | +| fps | 1367 | +| iterations | 2256 | +| time_elapsed | 3379 | +| total_timesteps | 4620288 | +| train/ | | +| approx_kl | 0.028635152 | +| clip_fraction | 0.375 | +| clip_range | 0.0923 | +| entropy_loss | -7.58 | +| explained_variance | -0.0916 | +| learning_rate | 0.000109 | +| loss | -0.0435 | +| n_updates | 9020 | +| policy_gradient_loss | -0.0278 | +| value_loss | 0.00022 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.293 | +| time/ | | +| fps | 1367 | +| iterations | 2257 | +| time_elapsed | 3381 | +| total_timesteps | 4622336 | +| train/ | | +| approx_kl | 0.025256965 | +| clip_fraction | 0.386 | +| clip_range | 0.0922 | +| entropy_loss | -7.53 | +| explained_variance | -0.306 | +| learning_rate | 0.000109 | +| loss | -0.0474 | +| n_updates | 9024 | +| policy_gradient_loss | -0.0291 | +| value_loss | 0.00012 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.293 | +| time/ | | +| fps | 1367 | +| iterations | 2258 | +| time_elapsed | 3382 | +| total_timesteps | 4624384 | +| train/ | | +| approx_kl | 0.024473272 | +| clip_fraction | 0.368 | +| clip_range | 0.0922 | +| entropy_loss | -7.55 | +| explained_variance | -0.114 | +| learning_rate | 0.000108 | +| loss | -0.0404 | +| n_updates | 9028 | +| policy_gradient_loss | -0.0262 | +| value_loss | 0.000186 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 1367 | +| iterations | 2259 | +| time_elapsed | 3384 | +| total_timesteps | 4626432 | +| train/ | | +| approx_kl | 0.025611116 | +| clip_fraction | 0.387 | +| clip_range | 0.0922 | +| entropy_loss | -7.56 | +| explained_variance | -0.229 | +| learning_rate | 0.000108 | +| loss | -0.0517 | +| n_updates | 9032 | +| policy_gradient_loss | -0.0303 | +| value_loss | 0.00011 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.294 | +| time/ | | +| fps | 1367 | +| iterations | 2260 | +| time_elapsed | 3385 | +| total_timesteps | 4628480 | +| train/ | | +| approx_kl | 0.028916232 | +| clip_fraction | 0.373 | +| clip_range | 0.0922 | +| entropy_loss | -7.64 | +| explained_variance | -0.0715 | +| learning_rate | 0.000108 | +| loss | -0.0503 | +| n_updates | 9036 | +| policy_gradient_loss | -0.0267 | +| value_loss | 0.000184 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.295 | +| time/ | | +| fps | 1366 | +| iterations | 2261 | +| time_elapsed | 3387 | +| total_timesteps | 4630528 | +| train/ | | +| approx_kl | 0.022859942 | +| clip_fraction | 0.36 | +| clip_range | 0.0921 | +| entropy_loss | -7.16 | +| explained_variance | 0.0239 | +| learning_rate | 0.000108 | +| loss | -0.0419 | +| n_updates | 9040 | +| policy_gradient_loss | -0.0227 | +| value_loss | 0.000223 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.295 | +| time/ | | +| fps | 1366 | +| iterations | 2262 | +| time_elapsed | 3388 | +| total_timesteps | 4632576 | +| train/ | | +| approx_kl | 0.029677996 | +| clip_fraction | 0.412 | +| clip_range | 0.0921 | +| entropy_loss | -7.36 | +| explained_variance | -0.262 | +| learning_rate | 0.000108 | +| loss | -0.047 | +| n_updates | 9044 | +| policy_gradient_loss | -0.0297 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.297 | +| time/ | | +| fps | 1366 | +| iterations | 2263 | +| time_elapsed | 3390 | +| total_timesteps | 4634624 | +| train/ | | +| approx_kl | 0.025800783 | +| clip_fraction | 0.381 | +| clip_range | 0.0921 | +| entropy_loss | -7.59 | +| explained_variance | -0.12 | +| learning_rate | 0.000108 | +| loss | -0.053 | +| n_updates | 9048 | +| policy_gradient_loss | -0.0305 | +| value_loss | 0.000145 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 1366 | +| iterations | 2264 | +| time_elapsed | 3392 | +| total_timesteps | 4636672 | +| train/ | | +| approx_kl | 0.019606635 | +| clip_fraction | 0.366 | +| clip_range | 0.0921 | +| entropy_loss | -7.52 | +| explained_variance | -0.0251 | +| learning_rate | 0.000108 | +| loss | -0.0363 | +| n_updates | 9052 | +| policy_gradient_loss | -0.025 | +| value_loss | 0.000191 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 1366 | +| iterations | 2265 | +| time_elapsed | 3393 | +| total_timesteps | 4638720 | +| train/ | | +| approx_kl | 0.02338981 | +| clip_fraction | 0.344 | +| clip_range | 0.092 | +| entropy_loss | -7.59 | +| explained_variance | 0.00486 | +| learning_rate | 0.000108 | +| loss | -0.0402 | +| n_updates | 9056 | +| policy_gradient_loss | -0.0223 | +| value_loss | 0.000251 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.3 | +| time/ | | +| fps | 1366 | +| iterations | 2266 | +| time_elapsed | 3395 | +| total_timesteps | 4640768 | +| train/ | | +| approx_kl | 0.027623516 | +| clip_fraction | 0.382 | +| clip_range | 0.092 | +| entropy_loss | -7.51 | +| explained_variance | -0.2 | +| learning_rate | 0.000108 | +| loss | -0.0447 | +| n_updates | 9060 | +| policy_gradient_loss | -0.03 | +| value_loss | 0.000231 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.302 | +| time/ | | +| fps | 1366 | +| iterations | 2267 | +| time_elapsed | 3396 | +| total_timesteps | 4642816 | +| train/ | | +| approx_kl | 0.026739396 | +| clip_fraction | 0.381 | +| clip_range | 0.092 | +| entropy_loss | -7.58 | +| explained_variance | -0.161 | +| learning_rate | 0.000108 | +| loss | -0.0421 | +| n_updates | 9064 | +| policy_gradient_loss | -0.0278 | +| value_loss | 0.000165 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.306 | +| time/ | | +| fps | 1366 | +| iterations | 2268 | +| time_elapsed | 3398 | +| total_timesteps | 4644864 | +| train/ | | +| approx_kl | 0.023017261 | +| clip_fraction | 0.364 | +| clip_range | 0.092 | +| entropy_loss | -7.53 | +| explained_variance | -0.139 | +| learning_rate | 0.000108 | +| loss | -0.0441 | +| n_updates | 9068 | +| policy_gradient_loss | -0.0279 | +| value_loss | 0.000163 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 1366 | +| iterations | 2269 | +| time_elapsed | 3399 | +| total_timesteps | 4646912 | +| train/ | | +| approx_kl | 0.024078757 | +| clip_fraction | 0.363 | +| clip_range | 0.0919 | +| entropy_loss | -7.42 | +| explained_variance | -0.0747 | +| learning_rate | 0.000108 | +| loss | -0.0383 | +| n_updates | 9072 | +| policy_gradient_loss | -0.0249 | +| value_loss | 0.000239 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 1366 | +| iterations | 2270 | +| time_elapsed | 3401 | +| total_timesteps | 4648960 | +| train/ | | +| approx_kl | 0.02753382 | +| clip_fraction | 0.406 | +| clip_range | 0.0919 | +| entropy_loss | -7.49 | +| explained_variance | -0.182 | +| learning_rate | 0.000108 | +| loss | -0.0507 | +| n_updates | 9076 | +| policy_gradient_loss | -0.032 | +| value_loss | 0.000119 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.295 | +| time/ | | +| fps | 1366 | +| iterations | 2271 | +| time_elapsed | 3402 | +| total_timesteps | 4651008 | +| train/ | | +| approx_kl | 0.025044508 | +| clip_fraction | 0.351 | +| clip_range | 0.0919 | +| entropy_loss | -7.46 | +| explained_variance | -0.0699 | +| learning_rate | 0.000108 | +| loss | -0.0406 | +| n_updates | 9080 | +| policy_gradient_loss | -0.0259 | +| value_loss | 0.000238 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.295 | +| time/ | | +| fps | 1366 | +| iterations | 2272 | +| time_elapsed | 3404 | +| total_timesteps | 4653056 | +| train/ | | +| approx_kl | 0.02525985 | +| clip_fraction | 0.383 | +| clip_range | 0.0919 | +| entropy_loss | -7.44 | +| explained_variance | -0.0596 | +| learning_rate | 0.000108 | +| loss | -0.0423 | +| n_updates | 9084 | +| policy_gradient_loss | -0.0269 | +| value_loss | 0.000234 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.295 | +| time/ | | +| fps | 1366 | +| iterations | 2273 | +| time_elapsed | 3405 | +| total_timesteps | 4655104 | +| train/ | | +| approx_kl | 0.024513962 | +| clip_fraction | 0.387 | +| clip_range | 0.0918 | +| entropy_loss | -7.49 | +| explained_variance | -0.172 | +| learning_rate | 0.000108 | +| loss | -0.0431 | +| n_updates | 9088 | +| policy_gradient_loss | -0.0282 | +| value_loss | 0.000198 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.295 | +| time/ | | +| fps | 1366 | +| iterations | 2274 | +| time_elapsed | 3407 | +| total_timesteps | 4657152 | +| train/ | | +| approx_kl | 0.025348205 | +| clip_fraction | 0.387 | +| clip_range | 0.0918 | +| entropy_loss | -7.66 | +| explained_variance | -0.198 | +| learning_rate | 0.000108 | +| loss | -0.0472 | +| n_updates | 9092 | +| policy_gradient_loss | -0.0314 | +| value_loss | 0.000122 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.295 | +| time/ | | +| fps | 1366 | +| iterations | 2275 | +| time_elapsed | 3408 | +| total_timesteps | 4659200 | +| train/ | | +| approx_kl | 0.02215102 | +| clip_fraction | 0.371 | +| clip_range | 0.0918 | +| entropy_loss | -7.76 | +| explained_variance | -0.162 | +| learning_rate | 0.000108 | +| loss | -0.0447 | +| n_updates | 9096 | +| policy_gradient_loss | -0.0282 | +| value_loss | 0.000239 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 1366 | +| iterations | 2276 | +| time_elapsed | 3410 | +| total_timesteps | 4661248 | +| train/ | | +| approx_kl | 0.025881588 | +| clip_fraction | 0.388 | +| clip_range | 0.0918 | +| entropy_loss | -7.63 | +| explained_variance | -0.159 | +| learning_rate | 0.000108 | +| loss | -0.0538 | +| n_updates | 9100 | +| policy_gradient_loss | -0.0288 | +| value_loss | 0.000105 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.302 | +| time/ | | +| fps | 1366 | +| iterations | 2277 | +| time_elapsed | 3411 | +| total_timesteps | 4663296 | +| train/ | | +| approx_kl | 0.022118524 | +| clip_fraction | 0.37 | +| clip_range | 0.0917 | +| entropy_loss | -7.53 | +| explained_variance | 0.0261 | +| learning_rate | 0.000108 | +| loss | -0.0417 | +| n_updates | 9104 | +| policy_gradient_loss | -0.025 | +| value_loss | 0.000221 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.295 | +| time/ | | +| fps | 1366 | +| iterations | 2278 | +| time_elapsed | 3413 | +| total_timesteps | 4665344 | +| train/ | | +| approx_kl | 0.018399999 | +| clip_fraction | 0.35 | +| clip_range | 0.0917 | +| entropy_loss | -7.52 | +| explained_variance | 0.00772 | +| learning_rate | 0.000108 | +| loss | -0.0371 | +| n_updates | 9108 | +| policy_gradient_loss | -0.0225 | +| value_loss | 0.000272 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.295 | +| time/ | | +| fps | 1366 | +| iterations | 2279 | +| time_elapsed | 3414 | +| total_timesteps | 4667392 | +| train/ | | +| approx_kl | 0.022513866 | +| clip_fraction | 0.38 | +| clip_range | 0.0917 | +| entropy_loss | -7.19 | +| explained_variance | 0.0542 | +| learning_rate | 0.000108 | +| loss | -0.045 | +| n_updates | 9112 | +| policy_gradient_loss | -0.0277 | +| value_loss | 0.000258 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.297 | +| time/ | | +| fps | 1366 | +| iterations | 2280 | +| time_elapsed | 3416 | +| total_timesteps | 4669440 | +| train/ | | +| approx_kl | 0.025611434 | +| clip_fraction | 0.401 | +| clip_range | 0.0917 | +| entropy_loss | -7.53 | +| explained_variance | -0.187 | +| learning_rate | 0.000108 | +| loss | -0.0498 | +| n_updates | 9116 | +| policy_gradient_loss | -0.0291 | +| value_loss | 0.000223 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.302 | +| time/ | | +| fps | 1366 | +| iterations | 2281 | +| time_elapsed | 3417 | +| total_timesteps | 4671488 | +| train/ | | +| approx_kl | 0.023235567 | +| clip_fraction | 0.383 | +| clip_range | 0.0916 | +| entropy_loss | -7.67 | +| explained_variance | -0.0843 | +| learning_rate | 0.000108 | +| loss | -0.0449 | +| n_updates | 9120 | +| policy_gradient_loss | -0.0279 | +| value_loss | 0.000201 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 1366 | +| iterations | 2282 | +| time_elapsed | 3419 | +| total_timesteps | 4673536 | +| train/ | | +| approx_kl | 0.02497458 | +| clip_fraction | 0.378 | +| clip_range | 0.0916 | +| entropy_loss | -7.57 | +| explained_variance | -0.13 | +| learning_rate | 0.000108 | +| loss | -0.055 | +| n_updates | 9124 | +| policy_gradient_loss | -0.0304 | +| value_loss | 0.000147 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.302 | +| time/ | | +| fps | 1366 | +| iterations | 2283 | +| time_elapsed | 3421 | +| total_timesteps | 4675584 | +| train/ | | +| approx_kl | 0.018864749 | +| clip_fraction | 0.331 | +| clip_range | 0.0916 | +| entropy_loss | -7.62 | +| explained_variance | 0.00978 | +| learning_rate | 0.000107 | +| loss | -0.0413 | +| n_updates | 9128 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000434 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.302 | +| time/ | | +| fps | 1366 | +| iterations | 2284 | +| time_elapsed | 3422 | +| total_timesteps | 4677632 | +| train/ | | +| approx_kl | 0.023050657 | +| clip_fraction | 0.381 | +| clip_range | 0.0916 | +| entropy_loss | -7.54 | +| explained_variance | -0.479 | +| learning_rate | 0.000107 | +| loss | -0.0483 | +| n_updates | 9132 | +| policy_gradient_loss | -0.0312 | +| value_loss | 0.000124 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1366 | +| iterations | 2285 | +| time_elapsed | 3424 | +| total_timesteps | 4679680 | +| train/ | | +| approx_kl | 0.025174705 | +| clip_fraction | 0.389 | +| clip_range | 0.0915 | +| entropy_loss | -7.61 | +| explained_variance | -0.141 | +| learning_rate | 0.000107 | +| loss | -0.0429 | +| n_updates | 9136 | +| policy_gradient_loss | -0.0291 | +| value_loss | 0.000178 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1366 | +| iterations | 2286 | +| time_elapsed | 3425 | +| total_timesteps | 4681728 | +| train/ | | +| approx_kl | 0.02832627 | +| clip_fraction | 0.392 | +| clip_range | 0.0915 | +| entropy_loss | -7.38 | +| explained_variance | -0.152 | +| learning_rate | 0.000107 | +| loss | -0.0342 | +| n_updates | 9140 | +| policy_gradient_loss | -0.0275 | +| value_loss | 0.000186 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 1366 | +| iterations | 2287 | +| time_elapsed | 3427 | +| total_timesteps | 4683776 | +| train/ | | +| approx_kl | 0.02695454 | +| clip_fraction | 0.395 | +| clip_range | 0.0915 | +| entropy_loss | -7.53 | +| explained_variance | -0.143 | +| learning_rate | 0.000107 | +| loss | -0.0463 | +| n_updates | 9144 | +| policy_gradient_loss | -0.0297 | +| value_loss | 0.000158 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.3 | +| time/ | | +| fps | 1366 | +| iterations | 2288 | +| time_elapsed | 3428 | +| total_timesteps | 4685824 | +| train/ | | +| approx_kl | 0.025742892 | +| clip_fraction | 0.356 | +| clip_range | 0.0915 | +| entropy_loss | -7.61 | +| explained_variance | -0.136 | +| learning_rate | 0.000107 | +| loss | -0.045 | +| n_updates | 9148 | +| policy_gradient_loss | -0.0277 | +| value_loss | 0.000167 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 1366 | +| iterations | 2289 | +| time_elapsed | 3430 | +| total_timesteps | 4687872 | +| train/ | | +| approx_kl | 0.024461681 | +| clip_fraction | 0.375 | +| clip_range | 0.0914 | +| entropy_loss | -7.46 | +| explained_variance | -0.267 | +| learning_rate | 0.000107 | +| loss | -0.0482 | +| n_updates | 9152 | +| policy_gradient_loss | -0.028 | +| value_loss | 0.00014 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 1366 | +| iterations | 2290 | +| time_elapsed | 3431 | +| total_timesteps | 4689920 | +| train/ | | +| approx_kl | 0.023098797 | +| clip_fraction | 0.397 | +| clip_range | 0.0914 | +| entropy_loss | -7.61 | +| explained_variance | -0.156 | +| learning_rate | 0.000107 | +| loss | -0.0443 | +| n_updates | 9156 | +| policy_gradient_loss | -0.0306 | +| value_loss | 0.000133 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1366 | +| iterations | 2291 | +| time_elapsed | 3433 | +| total_timesteps | 4691968 | +| train/ | | +| approx_kl | 0.019837957 | +| clip_fraction | 0.35 | +| clip_range | 0.0914 | +| entropy_loss | -7.63 | +| explained_variance | -0.0339 | +| learning_rate | 0.000107 | +| loss | -0.035 | +| n_updates | 9160 | +| policy_gradient_loss | -0.0241 | +| value_loss | 0.000176 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1366 | +| iterations | 2292 | +| time_elapsed | 3434 | +| total_timesteps | 4694016 | +| train/ | | +| approx_kl | 0.024892021 | +| clip_fraction | 0.359 | +| clip_range | 0.0914 | +| entropy_loss | -7.7 | +| explained_variance | -0.0704 | +| learning_rate | 0.000107 | +| loss | -0.0396 | +| n_updates | 9164 | +| policy_gradient_loss | -0.0251 | +| value_loss | 0.000177 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1366 | +| iterations | 2293 | +| time_elapsed | 3436 | +| total_timesteps | 4696064 | +| train/ | | +| approx_kl | 0.02562514 | +| clip_fraction | 0.367 | +| clip_range | 0.0913 | +| entropy_loss | -7.66 | +| explained_variance | -0.0986 | +| learning_rate | 0.000107 | +| loss | -0.0388 | +| n_updates | 9168 | +| policy_gradient_loss | -0.0268 | +| value_loss | 0.00017 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 1366 | +| iterations | 2294 | +| time_elapsed | 3438 | +| total_timesteps | 4698112 | +| train/ | | +| approx_kl | 0.027684662 | +| clip_fraction | 0.367 | +| clip_range | 0.0913 | +| entropy_loss | -7.57 | +| explained_variance | 0.00104 | +| learning_rate | 0.000107 | +| loss | -0.0428 | +| n_updates | 9172 | +| policy_gradient_loss | -0.0275 | +| value_loss | 0.000125 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.306 | +| time/ | | +| fps | 1366 | +| iterations | 2295 | +| time_elapsed | 3439 | +| total_timesteps | 4700160 | +| train/ | | +| approx_kl | 0.027022688 | +| clip_fraction | 0.392 | +| clip_range | 0.0913 | +| entropy_loss | -7.52 | +| explained_variance | -0.0653 | +| learning_rate | 0.000107 | +| loss | -0.0488 | +| n_updates | 9176 | +| policy_gradient_loss | -0.029 | +| value_loss | 0.00013 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.306 | +| time/ | | +| fps | 1366 | +| iterations | 2296 | +| time_elapsed | 3441 | +| total_timesteps | 4702208 | +| train/ | | +| approx_kl | 0.023955151 | +| clip_fraction | 0.354 | +| clip_range | 0.0912 | +| entropy_loss | -7.56 | +| explained_variance | -0.108 | +| learning_rate | 0.000107 | +| loss | -0.0454 | +| n_updates | 9180 | +| policy_gradient_loss | -0.0257 | +| value_loss | 0.000158 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 1366 | +| iterations | 2297 | +| time_elapsed | 3442 | +| total_timesteps | 4704256 | +| train/ | | +| approx_kl | 0.022997156 | +| clip_fraction | 0.355 | +| clip_range | 0.0912 | +| entropy_loss | -7.63 | +| explained_variance | -0.161 | +| learning_rate | 0.000107 | +| loss | -0.0447 | +| n_updates | 9184 | +| policy_gradient_loss | -0.0259 | +| value_loss | 0.000121 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1366 | +| iterations | 2298 | +| time_elapsed | 3444 | +| total_timesteps | 4706304 | +| train/ | | +| approx_kl | 0.022711616 | +| clip_fraction | 0.361 | +| clip_range | 0.0912 | +| entropy_loss | -7.53 | +| explained_variance | -0.272 | +| learning_rate | 0.000107 | +| loss | -0.0454 | +| n_updates | 9188 | +| policy_gradient_loss | -0.0281 | +| value_loss | 8.11e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 1366 | +| iterations | 2299 | +| time_elapsed | 3445 | +| total_timesteps | 4708352 | +| train/ | | +| approx_kl | 0.019291304 | +| clip_fraction | 0.353 | +| clip_range | 0.0912 | +| entropy_loss | -7.53 | +| explained_variance | -0.121 | +| learning_rate | 0.000107 | +| loss | -0.0369 | +| n_updates | 9192 | +| policy_gradient_loss | -0.0249 | +| value_loss | 0.000158 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.3 | +| time/ | | +| fps | 1366 | +| iterations | 2300 | +| time_elapsed | 3447 | +| total_timesteps | 4710400 | +| train/ | | +| approx_kl | 0.023645364 | +| clip_fraction | 0.365 | +| clip_range | 0.0911 | +| entropy_loss | -7.45 | +| explained_variance | -0.0506 | +| learning_rate | 0.000107 | +| loss | -0.0395 | +| n_updates | 9196 | +| policy_gradient_loss | -0.0265 | +| value_loss | 0.000175 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.3 | +| time/ | | +| fps | 1366 | +| iterations | 2301 | +| time_elapsed | 3449 | +| total_timesteps | 4712448 | +| train/ | | +| approx_kl | 0.024056636 | +| clip_fraction | 0.405 | +| clip_range | 0.0911 | +| entropy_loss | -7.48 | +| explained_variance | -0.122 | +| learning_rate | 0.000107 | +| loss | -0.0485 | +| n_updates | 9200 | +| policy_gradient_loss | -0.0317 | +| value_loss | 8.15e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.3 | +| time/ | | +| fps | 1366 | +| iterations | 2302 | +| time_elapsed | 3450 | +| total_timesteps | 4714496 | +| train/ | | +| approx_kl | 0.022264691 | +| clip_fraction | 0.381 | +| clip_range | 0.0911 | +| entropy_loss | -7.46 | +| explained_variance | -0.0448 | +| learning_rate | 0.000107 | +| loss | -0.0433 | +| n_updates | 9204 | +| policy_gradient_loss | -0.026 | +| value_loss | 0.000129 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.295 | +| time/ | | +| fps | 1366 | +| iterations | 2303 | +| time_elapsed | 3452 | +| total_timesteps | 4716544 | +| train/ | | +| approx_kl | 0.026509155 | +| clip_fraction | 0.36 | +| clip_range | 0.0911 | +| entropy_loss | -7.56 | +| explained_variance | -0.128 | +| learning_rate | 0.000107 | +| loss | -0.0388 | +| n_updates | 9208 | +| policy_gradient_loss | -0.0257 | +| value_loss | 0.000187 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.287 | +| time/ | | +| fps | 1366 | +| iterations | 2304 | +| time_elapsed | 3453 | +| total_timesteps | 4718592 | +| train/ | | +| approx_kl | 0.02188109 | +| clip_fraction | 0.371 | +| clip_range | 0.091 | +| entropy_loss | -7.54 | +| explained_variance | -0.214 | +| learning_rate | 0.000107 | +| loss | -0.0385 | +| n_updates | 9212 | +| policy_gradient_loss | -0.0243 | +| value_loss | 0.000167 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.285 | +| time/ | | +| fps | 1366 | +| iterations | 2305 | +| time_elapsed | 3455 | +| total_timesteps | 4720640 | +| train/ | | +| approx_kl | 0.02113679 | +| clip_fraction | 0.362 | +| clip_range | 0.091 | +| entropy_loss | -7.56 | +| explained_variance | -0.179 | +| learning_rate | 0.000107 | +| loss | -0.0409 | +| n_updates | 9216 | +| policy_gradient_loss | -0.0255 | +| value_loss | 0.000155 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.288 | +| time/ | | +| fps | 1366 | +| iterations | 2306 | +| time_elapsed | 3456 | +| total_timesteps | 4722688 | +| train/ | | +| approx_kl | 0.026023678 | +| clip_fraction | 0.339 | +| clip_range | 0.091 | +| entropy_loss | -7.56 | +| explained_variance | -0.113 | +| learning_rate | 0.000107 | +| loss | -0.0395 | +| n_updates | 9220 | +| policy_gradient_loss | -0.0261 | +| value_loss | 0.000187 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.285 | +| time/ | | +| fps | 1366 | +| iterations | 2307 | +| time_elapsed | 3458 | +| total_timesteps | 4724736 | +| train/ | | +| approx_kl | 0.024795588 | +| clip_fraction | 0.354 | +| clip_range | 0.091 | +| entropy_loss | -7.55 | +| explained_variance | -0.0736 | +| learning_rate | 0.000106 | +| loss | -0.0379 | +| n_updates | 9224 | +| policy_gradient_loss | -0.0253 | +| value_loss | 0.000189 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.283 | +| time/ | | +| fps | 1366 | +| iterations | 2308 | +| time_elapsed | 3459 | +| total_timesteps | 4726784 | +| train/ | | +| approx_kl | 0.025312908 | +| clip_fraction | 0.383 | +| clip_range | 0.0909 | +| entropy_loss | -7.48 | +| explained_variance | -0.188 | +| learning_rate | 0.000106 | +| loss | -0.0385 | +| n_updates | 9228 | +| policy_gradient_loss | -0.0272 | +| value_loss | 0.000181 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.271 | +| time/ | | +| fps | 1366 | +| iterations | 2309 | +| time_elapsed | 3461 | +| total_timesteps | 4728832 | +| train/ | | +| approx_kl | 0.022965785 | +| clip_fraction | 0.387 | +| clip_range | 0.0909 | +| entropy_loss | -7.61 | +| explained_variance | -0.191 | +| learning_rate | 0.000106 | +| loss | -0.0451 | +| n_updates | 9232 | +| policy_gradient_loss | -0.0254 | +| value_loss | 0.000115 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.271 | +| time/ | | +| fps | 1366 | +| iterations | 2310 | +| time_elapsed | 3462 | +| total_timesteps | 4730880 | +| train/ | | +| approx_kl | 0.01935685 | +| clip_fraction | 0.376 | +| clip_range | 0.0909 | +| entropy_loss | -7.46 | +| explained_variance | -0.0624 | +| learning_rate | 0.000106 | +| loss | -0.0459 | +| n_updates | 9236 | +| policy_gradient_loss | -0.0274 | +| value_loss | 0.000115 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.276 | +| time/ | | +| fps | 1366 | +| iterations | 2311 | +| time_elapsed | 3464 | +| total_timesteps | 4732928 | +| train/ | | +| approx_kl | 0.022189237 | +| clip_fraction | 0.359 | +| clip_range | 0.0909 | +| entropy_loss | -7.59 | +| explained_variance | -0.0897 | +| learning_rate | 0.000106 | +| loss | -0.0435 | +| n_updates | 9240 | +| policy_gradient_loss | -0.0251 | +| value_loss | 0.000119 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.276 | +| time/ | | +| fps | 1366 | +| iterations | 2312 | +| time_elapsed | 3465 | +| total_timesteps | 4734976 | +| train/ | | +| approx_kl | 0.022803329 | +| clip_fraction | 0.372 | +| clip_range | 0.0908 | +| entropy_loss | -7.5 | +| explained_variance | 0.0224 | +| learning_rate | 0.000106 | +| loss | -0.0438 | +| n_updates | 9244 | +| policy_gradient_loss | -0.0269 | +| value_loss | 0.000243 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 1366 | +| iterations | 2313 | +| time_elapsed | 3467 | +| total_timesteps | 4737024 | +| train/ | | +| approx_kl | 0.024924941 | +| clip_fraction | 0.38 | +| clip_range | 0.0908 | +| entropy_loss | -7.49 | +| explained_variance | 0.0673 | +| learning_rate | 0.000106 | +| loss | -0.0495 | +| n_updates | 9248 | +| policy_gradient_loss | -0.029 | +| value_loss | 0.000135 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 1366 | +| iterations | 2314 | +| time_elapsed | 3468 | +| total_timesteps | 4739072 | +| train/ | | +| approx_kl | 0.02716596 | +| clip_fraction | 0.407 | +| clip_range | 0.0908 | +| entropy_loss | -7.52 | +| explained_variance | -0.242 | +| learning_rate | 0.000106 | +| loss | -0.0578 | +| n_updates | 9252 | +| policy_gradient_loss | -0.0337 | +| value_loss | 8.67e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 1366 | +| iterations | 2315 | +| time_elapsed | 3470 | +| total_timesteps | 4741120 | +| train/ | | +| approx_kl | 0.025977485 | +| clip_fraction | 0.383 | +| clip_range | 0.0908 | +| entropy_loss | -7.61 | +| explained_variance | -0.00576 | +| learning_rate | 0.000106 | +| loss | -0.0394 | +| n_updates | 9256 | +| policy_gradient_loss | -0.0279 | +| value_loss | 0.000154 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.284 | +| time/ | | +| fps | 1366 | +| iterations | 2316 | +| time_elapsed | 3472 | +| total_timesteps | 4743168 | +| train/ | | +| approx_kl | 0.022327937 | +| clip_fraction | 0.389 | +| clip_range | 0.0907 | +| entropy_loss | -7.69 | +| explained_variance | -0.0877 | +| learning_rate | 0.000106 | +| loss | -0.0379 | +| n_updates | 9260 | +| policy_gradient_loss | -0.0245 | +| value_loss | 0.00013 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.284 | +| time/ | | +| fps | 1366 | +| iterations | 2317 | +| time_elapsed | 3473 | +| total_timesteps | 4745216 | +| train/ | | +| approx_kl | 0.02568042 | +| clip_fraction | 0.363 | +| clip_range | 0.0907 | +| entropy_loss | -7.53 | +| explained_variance | -0.00722 | +| learning_rate | 0.000106 | +| loss | -0.0393 | +| n_updates | 9264 | +| policy_gradient_loss | -0.0264 | +| value_loss | 0.000191 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.284 | +| time/ | | +| fps | 1366 | +| iterations | 2318 | +| time_elapsed | 3475 | +| total_timesteps | 4747264 | +| train/ | | +| approx_kl | 0.021295445 | +| clip_fraction | 0.361 | +| clip_range | 0.0907 | +| entropy_loss | -7.65 | +| explained_variance | -0.102 | +| learning_rate | 0.000106 | +| loss | -0.0442 | +| n_updates | 9268 | +| policy_gradient_loss | -0.0261 | +| value_loss | 0.00014 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.276 | +| time/ | | +| fps | 1366 | +| iterations | 2319 | +| time_elapsed | 3476 | +| total_timesteps | 4749312 | +| train/ | | +| approx_kl | 0.028410062 | +| clip_fraction | 0.372 | +| clip_range | 0.0907 | +| entropy_loss | -7.49 | +| explained_variance | 0.00264 | +| learning_rate | 0.000106 | +| loss | -0.0379 | +| n_updates | 9272 | +| policy_gradient_loss | -0.0258 | +| value_loss | 0.000287 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.269 | +| time/ | | +| fps | 1366 | +| iterations | 2320 | +| time_elapsed | 3478 | +| total_timesteps | 4751360 | +| train/ | | +| approx_kl | 0.025611691 | +| clip_fraction | 0.37 | +| clip_range | 0.0906 | +| entropy_loss | -7.51 | +| explained_variance | -0.272 | +| learning_rate | 0.000106 | +| loss | -0.0464 | +| n_updates | 9276 | +| policy_gradient_loss | -0.0299 | +| value_loss | 0.00017 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.266 | +| time/ | | +| fps | 1366 | +| iterations | 2321 | +| time_elapsed | 3479 | +| total_timesteps | 4753408 | +| train/ | | +| approx_kl | 0.023384016 | +| clip_fraction | 0.365 | +| clip_range | 0.0906 | +| entropy_loss | -7.44 | +| explained_variance | -0.0923 | +| learning_rate | 0.000106 | +| loss | -0.0468 | +| n_updates | 9280 | +| policy_gradient_loss | -0.0276 | +| value_loss | 0.000171 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.263 | +| time/ | | +| fps | 1365 | +| iterations | 2322 | +| time_elapsed | 3481 | +| total_timesteps | 4755456 | +| train/ | | +| approx_kl | 0.022820953 | +| clip_fraction | 0.368 | +| clip_range | 0.0906 | +| entropy_loss | -7.59 | +| explained_variance | -0.17 | +| learning_rate | 0.000106 | +| loss | -0.0402 | +| n_updates | 9284 | +| policy_gradient_loss | -0.0281 | +| value_loss | 0.000184 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.263 | +| time/ | | +| fps | 1365 | +| iterations | 2323 | +| time_elapsed | 3482 | +| total_timesteps | 4757504 | +| train/ | | +| approx_kl | 0.024514321 | +| clip_fraction | 0.377 | +| clip_range | 0.0906 | +| entropy_loss | -7.61 | +| explained_variance | -0.156 | +| learning_rate | 0.000106 | +| loss | -0.0467 | +| n_updates | 9288 | +| policy_gradient_loss | -0.0274 | +| value_loss | 0.000182 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.26 | +| time/ | | +| fps | 1365 | +| iterations | 2324 | +| time_elapsed | 3484 | +| total_timesteps | 4759552 | +| train/ | | +| approx_kl | 0.026102278 | +| clip_fraction | 0.403 | +| clip_range | 0.0905 | +| entropy_loss | -7.61 | +| explained_variance | -0.265 | +| learning_rate | 0.000106 | +| loss | -0.052 | +| n_updates | 9292 | +| policy_gradient_loss | -0.0314 | +| value_loss | 6.42e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.259 | +| time/ | | +| fps | 1365 | +| iterations | 2325 | +| time_elapsed | 3485 | +| total_timesteps | 4761600 | +| train/ | | +| approx_kl | 0.024787601 | +| clip_fraction | 0.359 | +| clip_range | 0.0905 | +| entropy_loss | -7.59 | +| explained_variance | 0.00172 | +| learning_rate | 0.000106 | +| loss | -0.04 | +| n_updates | 9296 | +| policy_gradient_loss | -0.0241 | +| value_loss | 0.000157 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.262 | +| time/ | | +| fps | 1365 | +| iterations | 2326 | +| time_elapsed | 3487 | +| total_timesteps | 4763648 | +| train/ | | +| approx_kl | 0.021271672 | +| clip_fraction | 0.362 | +| clip_range | 0.0905 | +| entropy_loss | -7.58 | +| explained_variance | -0.211 | +| learning_rate | 0.000106 | +| loss | -0.0413 | +| n_updates | 9300 | +| policy_gradient_loss | -0.0257 | +| value_loss | 0.000178 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.263 | +| time/ | | +| fps | 1365 | +| iterations | 2327 | +| time_elapsed | 3489 | +| total_timesteps | 4765696 | +| train/ | | +| approx_kl | 0.021857262 | +| clip_fraction | 0.375 | +| clip_range | 0.0905 | +| entropy_loss | -7.62 | +| explained_variance | -0.062 | +| learning_rate | 0.000106 | +| loss | -0.0456 | +| n_updates | 9304 | +| policy_gradient_loss | -0.0282 | +| value_loss | 0.000147 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.257 | +| time/ | | +| fps | 1365 | +| iterations | 2328 | +| time_elapsed | 3490 | +| total_timesteps | 4767744 | +| train/ | | +| approx_kl | 0.020903518 | +| clip_fraction | 0.349 | +| clip_range | 0.0904 | +| entropy_loss | -7.62 | +| explained_variance | -0.000654 | +| learning_rate | 0.000106 | +| loss | -0.0447 | +| n_updates | 9308 | +| policy_gradient_loss | -0.0262 | +| value_loss | 0.000154 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.257 | +| time/ | | +| fps | 1365 | +| iterations | 2329 | +| time_elapsed | 3492 | +| total_timesteps | 4769792 | +| train/ | | +| approx_kl | 0.020725252 | +| clip_fraction | 0.345 | +| clip_range | 0.0904 | +| entropy_loss | -7.54 | +| explained_variance | -0.0223 | +| learning_rate | 0.000106 | +| loss | -0.0383 | +| n_updates | 9312 | +| policy_gradient_loss | -0.0265 | +| value_loss | 0.000214 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.261 | +| time/ | | +| fps | 1365 | +| iterations | 2330 | +| time_elapsed | 3493 | +| total_timesteps | 4771840 | +| train/ | | +| approx_kl | 0.024740009 | +| clip_fraction | 0.362 | +| clip_range | 0.0904 | +| entropy_loss | -7.6 | +| explained_variance | -0.0131 | +| learning_rate | 0.000106 | +| loss | -0.0442 | +| n_updates | 9316 | +| policy_gradient_loss | -0.0278 | +| value_loss | 0.00022 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.257 | +| time/ | | +| fps | 1365 | +| iterations | 2331 | +| time_elapsed | 3495 | +| total_timesteps | 4773888 | +| train/ | | +| approx_kl | 0.020938113 | +| clip_fraction | 0.373 | +| clip_range | 0.0904 | +| entropy_loss | -7.57 | +| explained_variance | -0.199 | +| learning_rate | 0.000106 | +| loss | -0.0385 | +| n_updates | 9320 | +| policy_gradient_loss | -0.0264 | +| value_loss | 0.00015 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.259 | +| time/ | | +| fps | 1365 | +| iterations | 2332 | +| time_elapsed | 3496 | +| total_timesteps | 4775936 | +| train/ | | +| approx_kl | 0.024002105 | +| clip_fraction | 0.376 | +| clip_range | 0.0903 | +| entropy_loss | -7.58 | +| explained_variance | -0.185 | +| learning_rate | 0.000105 | +| loss | -0.044 | +| n_updates | 9324 | +| policy_gradient_loss | -0.0282 | +| value_loss | 0.000154 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.26 | +| time/ | | +| fps | 1365 | +| iterations | 2333 | +| time_elapsed | 3498 | +| total_timesteps | 4777984 | +| train/ | | +| approx_kl | 0.024069572 | +| clip_fraction | 0.37 | +| clip_range | 0.0903 | +| entropy_loss | -7.41 | +| explained_variance | -0.0722 | +| learning_rate | 0.000105 | +| loss | -0.0406 | +| n_updates | 9328 | +| policy_gradient_loss | -0.0266 | +| value_loss | 0.000252 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.263 | +| time/ | | +| fps | 1365 | +| iterations | 2334 | +| time_elapsed | 3499 | +| total_timesteps | 4780032 | +| train/ | | +| approx_kl | 0.027555235 | +| clip_fraction | 0.401 | +| clip_range | 0.0903 | +| entropy_loss | -7.55 | +| explained_variance | -0.0766 | +| learning_rate | 0.000105 | +| loss | -0.0453 | +| n_updates | 9332 | +| policy_gradient_loss | -0.0293 | +| value_loss | 0.000146 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.261 | +| time/ | | +| fps | 1365 | +| iterations | 2335 | +| time_elapsed | 3501 | +| total_timesteps | 4782080 | +| train/ | | +| approx_kl | 0.025755491 | +| clip_fraction | 0.395 | +| clip_range | 0.0902 | +| entropy_loss | -7.51 | +| explained_variance | -0.0579 | +| learning_rate | 0.000105 | +| loss | -0.0426 | +| n_updates | 9336 | +| policy_gradient_loss | -0.0284 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.25 | +| time/ | | +| fps | 1365 | +| iterations | 2336 | +| time_elapsed | 3502 | +| total_timesteps | 4784128 | +| train/ | | +| approx_kl | 0.019458473 | +| clip_fraction | 0.348 | +| clip_range | 0.0902 | +| entropy_loss | -7.45 | +| explained_variance | -0.102 | +| learning_rate | 0.000105 | +| loss | -0.0354 | +| n_updates | 9340 | +| policy_gradient_loss | -0.0219 | +| value_loss | 0.00034 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.25 | +| time/ | | +| fps | 1365 | +| iterations | 2337 | +| time_elapsed | 3504 | +| total_timesteps | 4786176 | +| train/ | | +| approx_kl | 0.02555941 | +| clip_fraction | 0.398 | +| clip_range | 0.0902 | +| entropy_loss | -7.48 | +| explained_variance | -0.34 | +| learning_rate | 0.000105 | +| loss | -0.0519 | +| n_updates | 9344 | +| policy_gradient_loss | -0.0312 | +| value_loss | 0.00014 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.25 | +| time/ | | +| fps | 1365 | +| iterations | 2338 | +| time_elapsed | 3505 | +| total_timesteps | 4788224 | +| train/ | | +| approx_kl | 0.026183512 | +| clip_fraction | 0.388 | +| clip_range | 0.0902 | +| entropy_loss | -7.57 | +| explained_variance | -0.13 | +| learning_rate | 0.000105 | +| loss | -0.042 | +| n_updates | 9348 | +| policy_gradient_loss | -0.0261 | +| value_loss | 0.000205 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.249 | +| time/ | | +| fps | 1365 | +| iterations | 2339 | +| time_elapsed | 3507 | +| total_timesteps | 4790272 | +| train/ | | +| approx_kl | 0.028678352 | +| clip_fraction | 0.384 | +| clip_range | 0.0901 | +| entropy_loss | -7.58 | +| explained_variance | -0.12 | +| learning_rate | 0.000105 | +| loss | -0.0469 | +| n_updates | 9352 | +| policy_gradient_loss | -0.0293 | +| value_loss | 0.000113 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.249 | +| time/ | | +| fps | 1365 | +| iterations | 2340 | +| time_elapsed | 3509 | +| total_timesteps | 4792320 | +| train/ | | +| approx_kl | 0.020120159 | +| clip_fraction | 0.383 | +| clip_range | 0.0901 | +| entropy_loss | -7.55 | +| explained_variance | -0.0422 | +| learning_rate | 0.000105 | +| loss | -0.0441 | +| n_updates | 9356 | +| policy_gradient_loss | -0.0261 | +| value_loss | 0.000253 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.252 | +| time/ | | +| fps | 1365 | +| iterations | 2341 | +| time_elapsed | 3510 | +| total_timesteps | 4794368 | +| train/ | | +| approx_kl | 0.02129225 | +| clip_fraction | 0.35 | +| clip_range | 0.0901 | +| entropy_loss | -7.45 | +| explained_variance | -0.0112 | +| learning_rate | 0.000105 | +| loss | -0.0404 | +| n_updates | 9360 | +| policy_gradient_loss | -0.0228 | +| value_loss | 0.000407 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.259 | +| time/ | | +| fps | 1365 | +| iterations | 2342 | +| time_elapsed | 3512 | +| total_timesteps | 4796416 | +| train/ | | +| approx_kl | 0.01894174 | +| clip_fraction | 0.376 | +| clip_range | 0.0901 | +| entropy_loss | -7.55 | +| explained_variance | -0.0402 | +| learning_rate | 0.000105 | +| loss | -0.047 | +| n_updates | 9364 | +| policy_gradient_loss | -0.0264 | +| value_loss | 0.000267 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.255 | +| time/ | | +| fps | 1365 | +| iterations | 2343 | +| time_elapsed | 3513 | +| total_timesteps | 4798464 | +| train/ | | +| approx_kl | 0.024763495 | +| clip_fraction | 0.377 | +| clip_range | 0.09 | +| entropy_loss | -7.43 | +| explained_variance | -0.192 | +| learning_rate | 0.000105 | +| loss | -0.0428 | +| n_updates | 9368 | +| policy_gradient_loss | -0.0264 | +| value_loss | 0.000171 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.253 | +| time/ | | +| fps | 1365 | +| iterations | 2344 | +| time_elapsed | 3515 | +| total_timesteps | 4800512 | +| train/ | | +| approx_kl | 0.022788875 | +| clip_fraction | 0.385 | +| clip_range | 0.09 | +| entropy_loss | -7.52 | +| explained_variance | -0.516 | +| learning_rate | 0.000105 | +| loss | -0.0427 | +| n_updates | 9372 | +| policy_gradient_loss | -0.0293 | +| value_loss | 0.00011 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.253 | +| time/ | | +| fps | 1365 | +| iterations | 2345 | +| time_elapsed | 3516 | +| total_timesteps | 4802560 | +| train/ | | +| approx_kl | 0.022206917 | +| clip_fraction | 0.375 | +| clip_range | 0.09 | +| entropy_loss | -7.56 | +| explained_variance | -0.0909 | +| learning_rate | 0.000105 | +| loss | -0.0376 | +| n_updates | 9376 | +| policy_gradient_loss | -0.0269 | +| value_loss | 0.000183 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.254 | +| time/ | | +| fps | 1365 | +| iterations | 2346 | +| time_elapsed | 3518 | +| total_timesteps | 4804608 | +| train/ | | +| approx_kl | 0.02385196 | +| clip_fraction | 0.403 | +| clip_range | 0.09 | +| entropy_loss | -7.56 | +| explained_variance | -0.064 | +| learning_rate | 0.000105 | +| loss | -0.0445 | +| n_updates | 9380 | +| policy_gradient_loss | -0.0272 | +| value_loss | 0.000129 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.244 | +| time/ | | +| fps | 1365 | +| iterations | 2347 | +| time_elapsed | 3520 | +| total_timesteps | 4806656 | +| train/ | | +| approx_kl | 0.024852559 | +| clip_fraction | 0.369 | +| clip_range | 0.0899 | +| entropy_loss | -7.57 | +| explained_variance | -0.0742 | +| learning_rate | 0.000105 | +| loss | -0.0342 | +| n_updates | 9384 | +| policy_gradient_loss | -0.0251 | +| value_loss | 0.000169 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.245 | +| time/ | | +| fps | 1365 | +| iterations | 2348 | +| time_elapsed | 3521 | +| total_timesteps | 4808704 | +| train/ | | +| approx_kl | 0.021613063 | +| clip_fraction | 0.371 | +| clip_range | 0.0899 | +| entropy_loss | -7.52 | +| explained_variance | -0.242 | +| learning_rate | 0.000105 | +| loss | -0.0343 | +| n_updates | 9388 | +| policy_gradient_loss | -0.0256 | +| value_loss | 0.000177 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.245 | +| time/ | | +| fps | 1365 | +| iterations | 2349 | +| time_elapsed | 3523 | +| total_timesteps | 4810752 | +| train/ | | +| approx_kl | 0.024756998 | +| clip_fraction | 0.354 | +| clip_range | 0.0899 | +| entropy_loss | -7.49 | +| explained_variance | -0.0874 | +| learning_rate | 0.000105 | +| loss | -0.0423 | +| n_updates | 9392 | +| policy_gradient_loss | -0.0265 | +| value_loss | 0.000235 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.251 | +| time/ | | +| fps | 1365 | +| iterations | 2350 | +| time_elapsed | 3524 | +| total_timesteps | 4812800 | +| train/ | | +| approx_kl | 0.026093982 | +| clip_fraction | 0.341 | +| clip_range | 0.0899 | +| entropy_loss | -7.41 | +| explained_variance | -0.101 | +| learning_rate | 0.000105 | +| loss | -0.0363 | +| n_updates | 9396 | +| policy_gradient_loss | -0.0236 | +| value_loss | 0.000255 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.251 | +| time/ | | +| fps | 1365 | +| iterations | 2351 | +| time_elapsed | 3526 | +| total_timesteps | 4814848 | +| train/ | | +| approx_kl | 0.023664404 | +| clip_fraction | 0.398 | +| clip_range | 0.0898 | +| entropy_loss | -7.52 | +| explained_variance | -0.0777 | +| learning_rate | 0.000105 | +| loss | -0.0406 | +| n_updates | 9400 | +| policy_gradient_loss | -0.0287 | +| value_loss | 0.00021 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.248 | +| time/ | | +| fps | 1365 | +| iterations | 2352 | +| time_elapsed | 3527 | +| total_timesteps | 4816896 | +| train/ | | +| approx_kl | 0.023302896 | +| clip_fraction | 0.374 | +| clip_range | 0.0898 | +| entropy_loss | -7.65 | +| explained_variance | -0.157 | +| learning_rate | 0.000105 | +| loss | -0.0501 | +| n_updates | 9404 | +| policy_gradient_loss | -0.0289 | +| value_loss | 0.000107 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.256 | +| time/ | | +| fps | 1365 | +| iterations | 2353 | +| time_elapsed | 3529 | +| total_timesteps | 4818944 | +| train/ | | +| approx_kl | 0.02262538 | +| clip_fraction | 0.362 | +| clip_range | 0.0898 | +| entropy_loss | -7.59 | +| explained_variance | -0.248 | +| learning_rate | 0.000105 | +| loss | -0.0427 | +| n_updates | 9408 | +| policy_gradient_loss | -0.0258 | +| value_loss | 0.000167 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.256 | +| time/ | | +| fps | 1365 | +| iterations | 2354 | +| time_elapsed | 3530 | +| total_timesteps | 4820992 | +| train/ | | +| approx_kl | 0.022612646 | +| clip_fraction | 0.346 | +| clip_range | 0.0898 | +| entropy_loss | -7.44 | +| explained_variance | -0.114 | +| learning_rate | 0.000105 | +| loss | -0.0446 | +| n_updates | 9412 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000264 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.257 | +| time/ | | +| fps | 1365 | +| iterations | 2355 | +| time_elapsed | 3532 | +| total_timesteps | 4823040 | +| train/ | | +| approx_kl | 0.019666594 | +| clip_fraction | 0.361 | +| clip_range | 0.0897 | +| entropy_loss | -7.6 | +| explained_variance | -0.124 | +| learning_rate | 0.000105 | +| loss | -0.0392 | +| n_updates | 9416 | +| policy_gradient_loss | -0.0248 | +| value_loss | 0.000217 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.261 | +| time/ | | +| fps | 1365 | +| iterations | 2356 | +| time_elapsed | 3533 | +| total_timesteps | 4825088 | +| train/ | | +| approx_kl | 0.02384311 | +| clip_fraction | 0.364 | +| clip_range | 0.0897 | +| entropy_loss | -7.67 | +| explained_variance | -0.0323 | +| learning_rate | 0.000105 | +| loss | -0.0432 | +| n_updates | 9420 | +| policy_gradient_loss | -0.0246 | +| value_loss | 0.000216 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.249 | +| time/ | | +| fps | 1365 | +| iterations | 2357 | +| time_elapsed | 3535 | +| total_timesteps | 4827136 | +| train/ | | +| approx_kl | 0.022294508 | +| clip_fraction | 0.346 | +| clip_range | 0.0897 | +| entropy_loss | -7.57 | +| explained_variance | -0.103 | +| learning_rate | 0.000104 | +| loss | -0.047 | +| n_updates | 9424 | +| policy_gradient_loss | -0.025 | +| value_loss | 0.000248 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.239 | +| time/ | | +| fps | 1365 | +| iterations | 2358 | +| time_elapsed | 3536 | +| total_timesteps | 4829184 | +| train/ | | +| approx_kl | 0.024642425 | +| clip_fraction | 0.366 | +| clip_range | 0.0897 | +| entropy_loss | -7.49 | +| explained_variance | -0.101 | +| learning_rate | 0.000104 | +| loss | -0.0374 | +| n_updates | 9428 | +| policy_gradient_loss | -0.0265 | +| value_loss | 0.000239 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.243 | +| time/ | | +| fps | 1365 | +| iterations | 2359 | +| time_elapsed | 3538 | +| total_timesteps | 4831232 | +| train/ | | +| approx_kl | 0.026123598 | +| clip_fraction | 0.414 | +| clip_range | 0.0896 | +| entropy_loss | -7.46 | +| explained_variance | -0.12 | +| learning_rate | 0.000104 | +| loss | -0.0382 | +| n_updates | 9432 | +| policy_gradient_loss | -0.0267 | +| value_loss | 0.00016 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.243 | +| time/ | | +| fps | 1365 | +| iterations | 2360 | +| time_elapsed | 3539 | +| total_timesteps | 4833280 | +| train/ | | +| approx_kl | 0.027146358 | +| clip_fraction | 0.392 | +| clip_range | 0.0896 | +| entropy_loss | -7.32 | +| explained_variance | -0.22 | +| learning_rate | 0.000104 | +| loss | -0.0477 | +| n_updates | 9436 | +| policy_gradient_loss | -0.0275 | +| value_loss | 0.000167 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.243 | +| time/ | | +| fps | 1365 | +| iterations | 2361 | +| time_elapsed | 3541 | +| total_timesteps | 4835328 | +| train/ | | +| approx_kl | 0.023087416 | +| clip_fraction | 0.404 | +| clip_range | 0.0896 | +| entropy_loss | -7.62 | +| explained_variance | -0.348 | +| learning_rate | 0.000104 | +| loss | -0.055 | +| n_updates | 9440 | +| policy_gradient_loss | -0.0321 | +| value_loss | 6.83e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.245 | +| time/ | | +| fps | 1365 | +| iterations | 2362 | +| time_elapsed | 3542 | +| total_timesteps | 4837376 | +| train/ | | +| approx_kl | 0.022229457 | +| clip_fraction | 0.388 | +| clip_range | 0.0896 | +| entropy_loss | -7.63 | +| explained_variance | -0.0516 | +| learning_rate | 0.000104 | +| loss | -0.0439 | +| n_updates | 9444 | +| policy_gradient_loss | -0.0278 | +| value_loss | 0.000377 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.245 | +| time/ | | +| fps | 1365 | +| iterations | 2363 | +| time_elapsed | 3544 | +| total_timesteps | 4839424 | +| train/ | | +| approx_kl | 0.026138013 | +| clip_fraction | 0.392 | +| clip_range | 0.0895 | +| entropy_loss | -7.56 | +| explained_variance | -0.114 | +| learning_rate | 0.000104 | +| loss | -0.0441 | +| n_updates | 9448 | +| policy_gradient_loss | -0.0295 | +| value_loss | 0.000158 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.243 | +| time/ | | +| fps | 1365 | +| iterations | 2364 | +| time_elapsed | 3545 | +| total_timesteps | 4841472 | +| train/ | | +| approx_kl | 0.024855088 | +| clip_fraction | 0.391 | +| clip_range | 0.0895 | +| entropy_loss | -7.56 | +| explained_variance | -0.172 | +| learning_rate | 0.000104 | +| loss | -0.0505 | +| n_updates | 9452 | +| policy_gradient_loss | -0.0302 | +| value_loss | 0.000133 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.239 | +| time/ | | +| fps | 1365 | +| iterations | 2365 | +| time_elapsed | 3547 | +| total_timesteps | 4843520 | +| train/ | | +| approx_kl | 0.020917447 | +| clip_fraction | 0.364 | +| clip_range | 0.0895 | +| entropy_loss | -7.54 | +| explained_variance | -0.127 | +| learning_rate | 0.000104 | +| loss | -0.0461 | +| n_updates | 9456 | +| policy_gradient_loss | -0.0262 | +| value_loss | 0.000193 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.242 | +| time/ | | +| fps | 1365 | +| iterations | 2366 | +| time_elapsed | 3548 | +| total_timesteps | 4845568 | +| train/ | | +| approx_kl | 0.019294463 | +| clip_fraction | 0.363 | +| clip_range | 0.0895 | +| entropy_loss | -7.55 | +| explained_variance | -0.0717 | +| learning_rate | 0.000104 | +| loss | -0.0424 | +| n_updates | 9460 | +| policy_gradient_loss | -0.0238 | +| value_loss | 0.000181 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.248 | +| time/ | | +| fps | 1365 | +| iterations | 2367 | +| time_elapsed | 3550 | +| total_timesteps | 4847616 | +| train/ | | +| approx_kl | 0.02223058 | +| clip_fraction | 0.39 | +| clip_range | 0.0894 | +| entropy_loss | -7.55 | +| explained_variance | -0.29 | +| learning_rate | 0.000104 | +| loss | -0.044 | +| n_updates | 9464 | +| policy_gradient_loss | -0.0298 | +| value_loss | 6.19e-05 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.249 | +| time/ | | +| fps | 1365 | +| iterations | 2368 | +| time_elapsed | 3551 | +| total_timesteps | 4849664 | +| train/ | | +| approx_kl | 0.02439579 | +| clip_fraction | 0.399 | +| clip_range | 0.0894 | +| entropy_loss | -7.48 | +| explained_variance | -0.094 | +| learning_rate | 0.000104 | +| loss | -0.0421 | +| n_updates | 9468 | +| policy_gradient_loss | -0.027 | +| value_loss | 0.000172 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.246 | +| time/ | | +| fps | 1365 | +| iterations | 2369 | +| time_elapsed | 3552 | +| total_timesteps | 4851712 | +| train/ | | +| approx_kl | 0.023876633 | +| clip_fraction | 0.381 | +| clip_range | 0.0894 | +| entropy_loss | -7.5 | +| explained_variance | -0.157 | +| learning_rate | 0.000104 | +| loss | -0.0391 | +| n_updates | 9472 | +| policy_gradient_loss | -0.0251 | +| value_loss | 0.000142 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.25 | +| time/ | | +| fps | 1365 | +| iterations | 2370 | +| time_elapsed | 3554 | +| total_timesteps | 4853760 | +| train/ | | +| approx_kl | 0.019732492 | +| clip_fraction | 0.359 | +| clip_range | 0.0894 | +| entropy_loss | -7.53 | +| explained_variance | 0.0079 | +| learning_rate | 0.000104 | +| loss | -0.0432 | +| n_updates | 9476 | +| policy_gradient_loss | -0.025 | +| value_loss | 0.00019 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.255 | +| time/ | | +| fps | 1365 | +| iterations | 2371 | +| time_elapsed | 3555 | +| total_timesteps | 4855808 | +| train/ | | +| approx_kl | 0.02493969 | +| clip_fraction | 0.372 | +| clip_range | 0.0893 | +| entropy_loss | -7.48 | +| explained_variance | -0.13 | +| learning_rate | 0.000104 | +| loss | -0.0439 | +| n_updates | 9480 | +| policy_gradient_loss | -0.0257 | +| value_loss | 0.000259 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.26 | +| time/ | | +| fps | 1365 | +| iterations | 2372 | +| time_elapsed | 3557 | +| total_timesteps | 4857856 | +| train/ | | +| approx_kl | 0.028213304 | +| clip_fraction | 0.392 | +| clip_range | 0.0893 | +| entropy_loss | -7.57 | +| explained_variance | -0.119 | +| learning_rate | 0.000104 | +| loss | -0.0367 | +| n_updates | 9484 | +| policy_gradient_loss | -0.0278 | +| value_loss | 0.000231 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.26 | +| time/ | | +| fps | 1365 | +| iterations | 2373 | +| time_elapsed | 3558 | +| total_timesteps | 4859904 | +| train/ | | +| approx_kl | 0.0223325 | +| clip_fraction | 0.376 | +| clip_range | 0.0893 | +| entropy_loss | -7.55 | +| explained_variance | -0.118 | +| learning_rate | 0.000104 | +| loss | -0.0487 | +| n_updates | 9488 | +| policy_gradient_loss | -0.0286 | +| value_loss | 0.000128 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.26 | +| time/ | | +| fps | 1365 | +| iterations | 2374 | +| time_elapsed | 3560 | +| total_timesteps | 4861952 | +| train/ | | +| approx_kl | 0.025251882 | +| clip_fraction | 0.389 | +| clip_range | 0.0893 | +| entropy_loss | -7.54 | +| explained_variance | -0.226 | +| learning_rate | 0.000104 | +| loss | -0.04 | +| n_updates | 9492 | +| policy_gradient_loss | -0.0273 | +| value_loss | 0.000147 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.26 | +| time/ | | +| fps | 1365 | +| iterations | 2375 | +| time_elapsed | 3561 | +| total_timesteps | 4864000 | +| train/ | | +| approx_kl | 0.023476072 | +| clip_fraction | 0.363 | +| clip_range | 0.0892 | +| entropy_loss | -7.55 | +| explained_variance | -0.108 | +| learning_rate | 0.000104 | +| loss | -0.0389 | +| n_updates | 9496 | +| policy_gradient_loss | -0.0254 | +| value_loss | 0.000157 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.265 | +| time/ | | +| fps | 1365 | +| iterations | 2376 | +| time_elapsed | 3563 | +| total_timesteps | 4866048 | +| train/ | | +| approx_kl | 0.022342477 | +| clip_fraction | 0.358 | +| clip_range | 0.0892 | +| entropy_loss | -7.61 | +| explained_variance | -0.174 | +| learning_rate | 0.000104 | +| loss | -0.0437 | +| n_updates | 9500 | +| policy_gradient_loss | -0.0257 | +| value_loss | 0.000136 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.267 | +| time/ | | +| fps | 1365 | +| iterations | 2377 | +| time_elapsed | 3564 | +| total_timesteps | 4868096 | +| train/ | | +| approx_kl | 0.025241353 | +| clip_fraction | 0.354 | +| clip_range | 0.0892 | +| entropy_loss | -7.58 | +| explained_variance | -0.05 | +| learning_rate | 0.000104 | +| loss | -0.0372 | +| n_updates | 9504 | +| policy_gradient_loss | -0.0238 | +| value_loss | 0.000332 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.268 | +| time/ | | +| fps | 1365 | +| iterations | 2378 | +| time_elapsed | 3565 | +| total_timesteps | 4870144 | +| train/ | | +| approx_kl | 0.023136161 | +| clip_fraction | 0.349 | +| clip_range | 0.0891 | +| entropy_loss | -7.46 | +| explained_variance | -0.104 | +| learning_rate | 0.000104 | +| loss | -0.04 | +| n_updates | 9508 | +| policy_gradient_loss | -0.0264 | +| value_loss | 0.000253 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.268 | +| time/ | | +| fps | 1365 | +| iterations | 2379 | +| time_elapsed | 3567 | +| total_timesteps | 4872192 | +| train/ | | +| approx_kl | 0.026622623 | +| clip_fraction | 0.396 | +| clip_range | 0.0891 | +| entropy_loss | -7.57 | +| explained_variance | -0.207 | +| learning_rate | 0.000104 | +| loss | -0.056 | +| n_updates | 9512 | +| policy_gradient_loss | -0.0315 | +| value_loss | 0.000165 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.259 | +| time/ | | +| fps | 1365 | +| iterations | 2380 | +| time_elapsed | 3568 | +| total_timesteps | 4874240 | +| train/ | | +| approx_kl | 0.026956588 | +| clip_fraction | 0.411 | +| clip_range | 0.0891 | +| entropy_loss | -7.62 | +| explained_variance | -0.566 | +| learning_rate | 0.000104 | +| loss | -0.0463 | +| n_updates | 9516 | +| policy_gradient_loss | -0.0325 | +| value_loss | 9.65e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.254 | +| time/ | | +| fps | 1365 | +| iterations | 2381 | +| time_elapsed | 3570 | +| total_timesteps | 4876288 | +| train/ | | +| approx_kl | 0.022035243 | +| clip_fraction | 0.375 | +| clip_range | 0.0891 | +| entropy_loss | -7.57 | +| explained_variance | -0.076 | +| learning_rate | 0.000103 | +| loss | -0.0413 | +| n_updates | 9520 | +| policy_gradient_loss | -0.0263 | +| value_loss | 0.000172 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.256 | +| time/ | | +| fps | 1365 | +| iterations | 2382 | +| time_elapsed | 3571 | +| total_timesteps | 4878336 | +| train/ | | +| approx_kl | 0.024863534 | +| clip_fraction | 0.384 | +| clip_range | 0.089 | +| entropy_loss | -7.37 | +| explained_variance | 0.0218 | +| learning_rate | 0.000103 | +| loss | -0.0436 | +| n_updates | 9524 | +| policy_gradient_loss | -0.0283 | +| value_loss | 0.000184 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.263 | +| time/ | | +| fps | 1365 | +| iterations | 2383 | +| time_elapsed | 3573 | +| total_timesteps | 4880384 | +| train/ | | +| approx_kl | 0.0243192 | +| clip_fraction | 0.399 | +| clip_range | 0.089 | +| entropy_loss | -7.57 | +| explained_variance | -0.165 | +| learning_rate | 0.000103 | +| loss | -0.047 | +| n_updates | 9528 | +| policy_gradient_loss | -0.0287 | +| value_loss | 0.000183 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.268 | +| time/ | | +| fps | 1365 | +| iterations | 2384 | +| time_elapsed | 3574 | +| total_timesteps | 4882432 | +| train/ | | +| approx_kl | 0.028327797 | +| clip_fraction | 0.373 | +| clip_range | 0.089 | +| entropy_loss | -7.49 | +| explained_variance | -0.113 | +| learning_rate | 0.000103 | +| loss | -0.0351 | +| n_updates | 9532 | +| policy_gradient_loss | -0.0253 | +| value_loss | 0.000246 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.266 | +| time/ | | +| fps | 1365 | +| iterations | 2385 | +| time_elapsed | 3576 | +| total_timesteps | 4884480 | +| train/ | | +| approx_kl | 0.02600509 | +| clip_fraction | 0.399 | +| clip_range | 0.089 | +| entropy_loss | -7.4 | +| explained_variance | -0.243 | +| learning_rate | 0.000103 | +| loss | -0.0414 | +| n_updates | 9536 | +| policy_gradient_loss | -0.0286 | +| value_loss | 0.0002 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.266 | +| time/ | | +| fps | 1365 | +| iterations | 2386 | +| time_elapsed | 3577 | +| total_timesteps | 4886528 | +| train/ | | +| approx_kl | 0.027425608 | +| clip_fraction | 0.393 | +| clip_range | 0.0889 | +| entropy_loss | -7.38 | +| explained_variance | -0.119 | +| learning_rate | 0.000103 | +| loss | -0.0377 | +| n_updates | 9540 | +| policy_gradient_loss | -0.0273 | +| value_loss | 0.000187 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.272 | +| time/ | | +| fps | 1365 | +| iterations | 2387 | +| time_elapsed | 3579 | +| total_timesteps | 4888576 | +| train/ | | +| approx_kl | 0.025190495 | +| clip_fraction | 0.391 | +| clip_range | 0.0889 | +| entropy_loss | -7.59 | +| explained_variance | -0.305 | +| learning_rate | 0.000103 | +| loss | -0.0422 | +| n_updates | 9544 | +| policy_gradient_loss | -0.0279 | +| value_loss | 0.000126 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.27 | +| time/ | | +| fps | 1365 | +| iterations | 2388 | +| time_elapsed | 3580 | +| total_timesteps | 4890624 | +| train/ | | +| approx_kl | 0.024849601 | +| clip_fraction | 0.369 | +| clip_range | 0.0889 | +| entropy_loss | -7.48 | +| explained_variance | -0.056 | +| learning_rate | 0.000103 | +| loss | -0.0438 | +| n_updates | 9548 | +| policy_gradient_loss | -0.0245 | +| value_loss | 0.000203 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.271 | +| time/ | | +| fps | 1365 | +| iterations | 2389 | +| time_elapsed | 3582 | +| total_timesteps | 4892672 | +| train/ | | +| approx_kl | 0.021342125 | +| clip_fraction | 0.356 | +| clip_range | 0.0889 | +| entropy_loss | -7.58 | +| explained_variance | -0.0909 | +| learning_rate | 0.000103 | +| loss | -0.0442 | +| n_updates | 9552 | +| policy_gradient_loss | -0.025 | +| value_loss | 0.000211 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.273 | +| time/ | | +| fps | 1365 | +| iterations | 2390 | +| time_elapsed | 3583 | +| total_timesteps | 4894720 | +| train/ | | +| approx_kl | 0.019072328 | +| clip_fraction | 0.352 | +| clip_range | 0.0888 | +| entropy_loss | -7.41 | +| explained_variance | -0.0307 | +| learning_rate | 0.000103 | +| loss | -0.036 | +| n_updates | 9556 | +| policy_gradient_loss | -0.0222 | +| value_loss | 0.00032 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.273 | +| time/ | | +| fps | 1365 | +| iterations | 2391 | +| time_elapsed | 3584 | +| total_timesteps | 4896768 | +| train/ | | +| approx_kl | 0.023730382 | +| clip_fraction | 0.396 | +| clip_range | 0.0888 | +| entropy_loss | -7.4 | +| explained_variance | -0.0938 | +| learning_rate | 0.000103 | +| loss | -0.0441 | +| n_updates | 9560 | +| policy_gradient_loss | -0.0272 | +| value_loss | 0.000225 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.271 | +| time/ | | +| fps | 1365 | +| iterations | 2392 | +| time_elapsed | 3586 | +| total_timesteps | 4898816 | +| train/ | | +| approx_kl | 0.024854477 | +| clip_fraction | 0.384 | +| clip_range | 0.0888 | +| entropy_loss | -7.56 | +| explained_variance | -0.167 | +| learning_rate | 0.000103 | +| loss | -0.041 | +| n_updates | 9564 | +| policy_gradient_loss | -0.0283 | +| value_loss | 0.000192 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.265 | +| time/ | | +| fps | 1365 | +| iterations | 2393 | +| time_elapsed | 3587 | +| total_timesteps | 4900864 | +| train/ | | +| approx_kl | 0.022709649 | +| clip_fraction | 0.359 | +| clip_range | 0.0888 | +| entropy_loss | -7.51 | +| explained_variance | -0.0723 | +| learning_rate | 0.000103 | +| loss | -0.0487 | +| n_updates | 9568 | +| policy_gradient_loss | -0.0269 | +| value_loss | 0.000202 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.264 | +| time/ | | +| fps | 1365 | +| iterations | 2394 | +| time_elapsed | 3589 | +| total_timesteps | 4902912 | +| train/ | | +| approx_kl | 0.025599398 | +| clip_fraction | 0.386 | +| clip_range | 0.0887 | +| entropy_loss | -7.53 | +| explained_variance | -0.1 | +| learning_rate | 0.000103 | +| loss | -0.0401 | +| n_updates | 9572 | +| policy_gradient_loss | -0.0281 | +| value_loss | 0.000165 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.262 | +| time/ | | +| fps | 1366 | +| iterations | 2395 | +| time_elapsed | 3590 | +| total_timesteps | 4904960 | +| train/ | | +| approx_kl | 0.022121014 | +| clip_fraction | 0.373 | +| clip_range | 0.0887 | +| entropy_loss | -7.55 | +| explained_variance | -0.259 | +| learning_rate | 0.000103 | +| loss | -0.0421 | +| n_updates | 9576 | +| policy_gradient_loss | -0.0278 | +| value_loss | 0.000168 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.267 | +| time/ | | +| fps | 1366 | +| iterations | 2396 | +| time_elapsed | 3592 | +| total_timesteps | 4907008 | +| train/ | | +| approx_kl | 0.023244675 | +| clip_fraction | 0.355 | +| clip_range | 0.0887 | +| entropy_loss | -7.56 | +| explained_variance | -0.143 | +| learning_rate | 0.000103 | +| loss | -0.0492 | +| n_updates | 9580 | +| policy_gradient_loss | -0.0264 | +| value_loss | 0.000151 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.267 | +| time/ | | +| fps | 1366 | +| iterations | 2397 | +| time_elapsed | 3593 | +| total_timesteps | 4909056 | +| train/ | | +| approx_kl | 0.025223628 | +| clip_fraction | 0.378 | +| clip_range | 0.0887 | +| entropy_loss | -7.43 | +| explained_variance | -0.111 | +| learning_rate | 0.000103 | +| loss | -0.0391 | +| n_updates | 9584 | +| policy_gradient_loss | -0.0248 | +| value_loss | 0.000315 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.269 | +| time/ | | +| fps | 1366 | +| iterations | 2398 | +| time_elapsed | 3594 | +| total_timesteps | 4911104 | +| train/ | | +| approx_kl | 0.024806548 | +| clip_fraction | 0.365 | +| clip_range | 0.0886 | +| entropy_loss | -7.58 | +| explained_variance | -0.219 | +| learning_rate | 0.000103 | +| loss | -0.0436 | +| n_updates | 9588 | +| policy_gradient_loss | -0.0267 | +| value_loss | 0.000147 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.259 | +| time/ | | +| fps | 1366 | +| iterations | 2399 | +| time_elapsed | 3596 | +| total_timesteps | 4913152 | +| train/ | | +| approx_kl | 0.027684486 | +| clip_fraction | 0.388 | +| clip_range | 0.0886 | +| entropy_loss | -7.56 | +| explained_variance | -0.231 | +| learning_rate | 0.000103 | +| loss | -0.039 | +| n_updates | 9592 | +| policy_gradient_loss | -0.0279 | +| value_loss | 9.96e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.259 | +| time/ | | +| fps | 1366 | +| iterations | 2400 | +| time_elapsed | 3597 | +| total_timesteps | 4915200 | +| train/ | | +| approx_kl | 0.027126942 | +| clip_fraction | 0.387 | +| clip_range | 0.0886 | +| entropy_loss | -7.46 | +| explained_variance | -0.149 | +| learning_rate | 0.000103 | +| loss | -0.0499 | +| n_updates | 9596 | +| policy_gradient_loss | -0.029 | +| value_loss | 7.57e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.264 | +| time/ | | +| fps | 1366 | +| iterations | 2401 | +| time_elapsed | 3599 | +| total_timesteps | 4917248 | +| train/ | | +| approx_kl | 0.025460562 | +| clip_fraction | 0.387 | +| clip_range | 0.0886 | +| entropy_loss | -7.47 | +| explained_variance | -0.0685 | +| learning_rate | 0.000103 | +| loss | -0.0356 | +| n_updates | 9600 | +| policy_gradient_loss | -0.0251 | +| value_loss | 0.000153 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.271 | +| time/ | | +| fps | 1366 | +| iterations | 2402 | +| time_elapsed | 3600 | +| total_timesteps | 4919296 | +| train/ | | +| approx_kl | 0.02386916 | +| clip_fraction | 0.39 | +| clip_range | 0.0885 | +| entropy_loss | -7.41 | +| explained_variance | -0.0304 | +| learning_rate | 0.000103 | +| loss | -0.0407 | +| n_updates | 9604 | +| policy_gradient_loss | -0.0254 | +| value_loss | 0.00017 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.271 | +| time/ | | +| fps | 1366 | +| iterations | 2403 | +| time_elapsed | 3602 | +| total_timesteps | 4921344 | +| train/ | | +| approx_kl | 0.022215277 | +| clip_fraction | 0.391 | +| clip_range | 0.0885 | +| entropy_loss | -7.63 | +| explained_variance | -0.0515 | +| learning_rate | 0.000103 | +| loss | -0.044 | +| n_updates | 9608 | +| policy_gradient_loss | -0.0261 | +| value_loss | 0.000158 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.271 | +| time/ | | +| fps | 1366 | +| iterations | 2404 | +| time_elapsed | 3603 | +| total_timesteps | 4923392 | +| train/ | | +| approx_kl | 0.023426024 | +| clip_fraction | 0.406 | +| clip_range | 0.0885 | +| entropy_loss | -7.36 | +| explained_variance | 0.00164 | +| learning_rate | 0.000103 | +| loss | -0.0436 | +| n_updates | 9612 | +| policy_gradient_loss | -0.0266 | +| value_loss | 0.00015 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.26 | +| time/ | | +| fps | 1366 | +| iterations | 2405 | +| time_elapsed | 3605 | +| total_timesteps | 4925440 | +| train/ | | +| approx_kl | 0.024149314 | +| clip_fraction | 0.361 | +| clip_range | 0.0885 | +| entropy_loss | -7.56 | +| explained_variance | -0.166 | +| learning_rate | 0.000103 | +| loss | -0.0421 | +| n_updates | 9616 | +| policy_gradient_loss | -0.0271 | +| value_loss | 0.000154 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.26 | +| time/ | | +| fps | 1366 | +| iterations | 2406 | +| time_elapsed | 3606 | +| total_timesteps | 4927488 | +| train/ | | +| approx_kl | 0.024320763 | +| clip_fraction | 0.375 | +| clip_range | 0.0884 | +| entropy_loss | -7.45 | +| explained_variance | -0.152 | +| learning_rate | 0.000102 | +| loss | -0.0389 | +| n_updates | 9620 | +| policy_gradient_loss | -0.0276 | +| value_loss | 0.000121 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.258 | +| time/ | | +| fps | 1366 | +| iterations | 2407 | +| time_elapsed | 3607 | +| total_timesteps | 4929536 | +| train/ | | +| approx_kl | 0.026335116 | +| clip_fraction | 0.396 | +| clip_range | 0.0884 | +| entropy_loss | -7.31 | +| explained_variance | 0.00419 | +| learning_rate | 0.000102 | +| loss | -0.0485 | +| n_updates | 9624 | +| policy_gradient_loss | -0.0281 | +| value_loss | 0.000114 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.256 | +| time/ | | +| fps | 1366 | +| iterations | 2408 | +| time_elapsed | 3609 | +| total_timesteps | 4931584 | +| train/ | | +| approx_kl | 0.02580783 | +| clip_fraction | 0.405 | +| clip_range | 0.0884 | +| entropy_loss | -7.25 | +| explained_variance | -0.22 | +| learning_rate | 0.000102 | +| loss | -0.0402 | +| n_updates | 9628 | +| policy_gradient_loss | -0.0249 | +| value_loss | 0.000165 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.256 | +| time/ | | +| fps | 1366 | +| iterations | 2409 | +| time_elapsed | 3610 | +| total_timesteps | 4933632 | +| train/ | | +| approx_kl | 0.029143736 | +| clip_fraction | 0.425 | +| clip_range | 0.0884 | +| entropy_loss | -7.42 | +| explained_variance | -0.277 | +| learning_rate | 0.000102 | +| loss | -0.0518 | +| n_updates | 9632 | +| policy_gradient_loss | -0.0309 | +| value_loss | 8.79e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.262 | +| time/ | | +| fps | 1366 | +| iterations | 2410 | +| time_elapsed | 3612 | +| total_timesteps | 4935680 | +| train/ | | +| approx_kl | 0.028679976 | +| clip_fraction | 0.408 | +| clip_range | 0.0883 | +| entropy_loss | -7.5 | +| explained_variance | -0.112 | +| learning_rate | 0.000102 | +| loss | -0.0385 | +| n_updates | 9636 | +| policy_gradient_loss | -0.0263 | +| value_loss | 0.000188 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.262 | +| time/ | | +| fps | 1366 | +| iterations | 2411 | +| time_elapsed | 3613 | +| total_timesteps | 4937728 | +| train/ | | +| approx_kl | 0.029056102 | +| clip_fraction | 0.382 | +| clip_range | 0.0883 | +| entropy_loss | -7.33 | +| explained_variance | -0.0663 | +| learning_rate | 0.000102 | +| loss | -0.0372 | +| n_updates | 9640 | +| policy_gradient_loss | -0.0252 | +| value_loss | 0.000225 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.266 | +| time/ | | +| fps | 1366 | +| iterations | 2412 | +| time_elapsed | 3615 | +| total_timesteps | 4939776 | +| train/ | | +| approx_kl | 0.02847284 | +| clip_fraction | 0.414 | +| clip_range | 0.0883 | +| entropy_loss | -7.37 | +| explained_variance | -0.202 | +| learning_rate | 0.000102 | +| loss | -0.0481 | +| n_updates | 9644 | +| policy_gradient_loss | -0.0298 | +| value_loss | 0.00014 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.266 | +| time/ | | +| fps | 1366 | +| iterations | 2413 | +| time_elapsed | 3616 | +| total_timesteps | 4941824 | +| train/ | | +| approx_kl | 0.027445506 | +| clip_fraction | 0.398 | +| clip_range | 0.0883 | +| entropy_loss | -7.36 | +| explained_variance | -0.0471 | +| learning_rate | 0.000102 | +| loss | -0.0416 | +| n_updates | 9648 | +| policy_gradient_loss | -0.0269 | +| value_loss | 0.000165 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.272 | +| time/ | | +| fps | 1366 | +| iterations | 2414 | +| time_elapsed | 3617 | +| total_timesteps | 4943872 | +| train/ | | +| approx_kl | 0.026151285 | +| clip_fraction | 0.407 | +| clip_range | 0.0882 | +| entropy_loss | -7.31 | +| explained_variance | 0.00235 | +| learning_rate | 0.000102 | +| loss | -0.0488 | +| n_updates | 9652 | +| policy_gradient_loss | -0.0265 | +| value_loss | 0.000255 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.277 | +| time/ | | +| fps | 1366 | +| iterations | 2415 | +| time_elapsed | 3619 | +| total_timesteps | 4945920 | +| train/ | | +| approx_kl | 0.02711844 | +| clip_fraction | 0.393 | +| clip_range | 0.0882 | +| entropy_loss | -7.4 | +| explained_variance | -0.115 | +| learning_rate | 0.000102 | +| loss | -0.046 | +| n_updates | 9656 | +| policy_gradient_loss | -0.0271 | +| value_loss | 0.000271 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 1366 | +| iterations | 2416 | +| time_elapsed | 3620 | +| total_timesteps | 4947968 | +| train/ | | +| approx_kl | 0.029553222 | +| clip_fraction | 0.438 | +| clip_range | 0.0882 | +| entropy_loss | -7.29 | +| explained_variance | -0.0519 | +| learning_rate | 0.000102 | +| loss | -0.0466 | +| n_updates | 9660 | +| policy_gradient_loss | -0.0318 | +| value_loss | 9.37e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.271 | +| time/ | | +| fps | 1366 | +| iterations | 2417 | +| time_elapsed | 3622 | +| total_timesteps | 4950016 | +| train/ | | +| approx_kl | 0.027907547 | +| clip_fraction | 0.408 | +| clip_range | 0.0882 | +| entropy_loss | -7.4 | +| explained_variance | -0.242 | +| learning_rate | 0.000102 | +| loss | -0.0444 | +| n_updates | 9664 | +| policy_gradient_loss | -0.027 | +| value_loss | 0.000127 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.266 | +| time/ | | +| fps | 1366 | +| iterations | 2418 | +| time_elapsed | 3623 | +| total_timesteps | 4952064 | +| train/ | | +| approx_kl | 0.03003193 | +| clip_fraction | 0.405 | +| clip_range | 0.0881 | +| entropy_loss | -7.35 | +| explained_variance | -0.166 | +| learning_rate | 0.000102 | +| loss | -0.042 | +| n_updates | 9668 | +| policy_gradient_loss | -0.0275 | +| value_loss | 0.00017 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.256 | +| time/ | | +| fps | 1366 | +| iterations | 2419 | +| time_elapsed | 3625 | +| total_timesteps | 4954112 | +| train/ | | +| approx_kl | 0.029707104 | +| clip_fraction | 0.394 | +| clip_range | 0.0881 | +| entropy_loss | -7.32 | +| explained_variance | -0.0937 | +| learning_rate | 0.000102 | +| loss | -0.0425 | +| n_updates | 9672 | +| policy_gradient_loss | -0.0251 | +| value_loss | 0.000195 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.255 | +| time/ | | +| fps | 1366 | +| iterations | 2420 | +| time_elapsed | 3626 | +| total_timesteps | 4956160 | +| train/ | | +| approx_kl | 0.026399147 | +| clip_fraction | 0.409 | +| clip_range | 0.0881 | +| entropy_loss | -7.41 | +| explained_variance | -0.188 | +| learning_rate | 0.000102 | +| loss | -0.0496 | +| n_updates | 9676 | +| policy_gradient_loss | -0.0302 | +| value_loss | 8.39e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.251 | +| time/ | | +| fps | 1366 | +| iterations | 2421 | +| time_elapsed | 3627 | +| total_timesteps | 4958208 | +| train/ | | +| approx_kl | 0.027655676 | +| clip_fraction | 0.413 | +| clip_range | 0.088 | +| entropy_loss | -7.29 | +| explained_variance | -0.0871 | +| learning_rate | 0.000102 | +| loss | -0.0402 | +| n_updates | 9680 | +| policy_gradient_loss | -0.0236 | +| value_loss | 0.000162 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.257 | +| time/ | | +| fps | 1366 | +| iterations | 2422 | +| time_elapsed | 3629 | +| total_timesteps | 4960256 | +| train/ | | +| approx_kl | 0.023985526 | +| clip_fraction | 0.396 | +| clip_range | 0.088 | +| entropy_loss | -7.49 | +| explained_variance | -0.0871 | +| learning_rate | 0.000102 | +| loss | -0.038 | +| n_updates | 9684 | +| policy_gradient_loss | -0.0258 | +| value_loss | 0.000166 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.257 | +| time/ | | +| fps | 1366 | +| iterations | 2423 | +| time_elapsed | 3630 | +| total_timesteps | 4962304 | +| train/ | | +| approx_kl | 0.023507044 | +| clip_fraction | 0.39 | +| clip_range | 0.088 | +| entropy_loss | -7.37 | +| explained_variance | -0.101 | +| learning_rate | 0.000102 | +| loss | -0.0415 | +| n_updates | 9688 | +| policy_gradient_loss | -0.0268 | +| value_loss | 0.000134 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.262 | +| time/ | | +| fps | 1366 | +| iterations | 2424 | +| time_elapsed | 3632 | +| total_timesteps | 4964352 | +| train/ | | +| approx_kl | 0.0293135 | +| clip_fraction | 0.416 | +| clip_range | 0.088 | +| entropy_loss | -7.32 | +| explained_variance | -0.234 | +| learning_rate | 0.000102 | +| loss | -0.0441 | +| n_updates | 9692 | +| policy_gradient_loss | -0.0285 | +| value_loss | 0.000136 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.271 | +| time/ | | +| fps | 1366 | +| iterations | 2425 | +| time_elapsed | 3633 | +| total_timesteps | 4966400 | +| train/ | | +| approx_kl | 0.023796491 | +| clip_fraction | 0.425 | +| clip_range | 0.0879 | +| entropy_loss | -7.3 | +| explained_variance | -0.0211 | +| learning_rate | 0.000102 | +| loss | -0.0437 | +| n_updates | 9696 | +| policy_gradient_loss | -0.0264 | +| value_loss | 0.000198 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.269 | +| time/ | | +| fps | 1366 | +| iterations | 2426 | +| time_elapsed | 3635 | +| total_timesteps | 4968448 | +| train/ | | +| approx_kl | 0.025449306 | +| clip_fraction | 0.377 | +| clip_range | 0.0879 | +| entropy_loss | -7.39 | +| explained_variance | -0.0691 | +| learning_rate | 0.000102 | +| loss | -0.0443 | +| n_updates | 9700 | +| policy_gradient_loss | -0.0263 | +| value_loss | 0.000181 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.266 | +| time/ | | +| fps | 1366 | +| iterations | 2427 | +| time_elapsed | 3636 | +| total_timesteps | 4970496 | +| train/ | | +| approx_kl | 0.029202867 | +| clip_fraction | 0.416 | +| clip_range | 0.0879 | +| entropy_loss | -7.24 | +| explained_variance | -0.124 | +| learning_rate | 0.000102 | +| loss | -0.0432 | +| n_updates | 9704 | +| policy_gradient_loss | -0.0303 | +| value_loss | 0.000163 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.263 | +| time/ | | +| fps | 1366 | +| iterations | 2428 | +| time_elapsed | 3637 | +| total_timesteps | 4972544 | +| train/ | | +| approx_kl | 0.020247098 | +| clip_fraction | 0.378 | +| clip_range | 0.0879 | +| entropy_loss | -7.13 | +| explained_variance | -0.00458 | +| learning_rate | 0.000102 | +| loss | -0.0346 | +| n_updates | 9708 | +| policy_gradient_loss | -0.0241 | +| value_loss | 0.000215 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.263 | +| time/ | | +| fps | 1366 | +| iterations | 2429 | +| time_elapsed | 3639 | +| total_timesteps | 4974592 | +| train/ | | +| approx_kl | 0.026248515 | +| clip_fraction | 0.413 | +| clip_range | 0.0878 | +| entropy_loss | -7.25 | +| explained_variance | 0.00477 | +| learning_rate | 0.000102 | +| loss | -0.0515 | +| n_updates | 9712 | +| policy_gradient_loss | -0.0319 | +| value_loss | 9.6e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.263 | +| time/ | | +| fps | 1366 | +| iterations | 2430 | +| time_elapsed | 3640 | +| total_timesteps | 4976640 | +| train/ | | +| approx_kl | 0.023680696 | +| clip_fraction | 0.406 | +| clip_range | 0.0878 | +| entropy_loss | -7.31 | +| explained_variance | -0.0413 | +| learning_rate | 0.000102 | +| loss | -0.0445 | +| n_updates | 9716 | +| policy_gradient_loss | -0.0249 | +| value_loss | 0.000162 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.263 | +| time/ | | +| fps | 1366 | +| iterations | 2431 | +| time_elapsed | 3642 | +| total_timesteps | 4978688 | +| train/ | | +| approx_kl | 0.027419083 | +| clip_fraction | 0.375 | +| clip_range | 0.0878 | +| entropy_loss | -7.46 | +| explained_variance | -0.164 | +| learning_rate | 0.000101 | +| loss | -0.036 | +| n_updates | 9720 | +| policy_gradient_loss | -0.0247 | +| value_loss | 0.000154 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.266 | +| time/ | | +| fps | 1366 | +| iterations | 2432 | +| time_elapsed | 3643 | +| total_timesteps | 4980736 | +| train/ | | +| approx_kl | 0.025995303 | +| clip_fraction | 0.376 | +| clip_range | 0.0878 | +| entropy_loss | -7.45 | +| explained_variance | -0.157 | +| learning_rate | 0.000101 | +| loss | -0.0419 | +| n_updates | 9724 | +| policy_gradient_loss | -0.0252 | +| value_loss | 0.000188 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.263 | +| time/ | | +| fps | 1366 | +| iterations | 2433 | +| time_elapsed | 3645 | +| total_timesteps | 4982784 | +| train/ | | +| approx_kl | 0.025676932 | +| clip_fraction | 0.385 | +| clip_range | 0.0877 | +| entropy_loss | -7.46 | +| explained_variance | -0.0372 | +| learning_rate | 0.000101 | +| loss | -0.0421 | +| n_updates | 9728 | +| policy_gradient_loss | -0.0269 | +| value_loss | 0.000201 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.26 | +| time/ | | +| fps | 1366 | +| iterations | 2434 | +| time_elapsed | 3646 | +| total_timesteps | 4984832 | +| train/ | | +| approx_kl | 0.026643194 | +| clip_fraction | 0.421 | +| clip_range | 0.0877 | +| entropy_loss | -7.41 | +| explained_variance | -0.199 | +| learning_rate | 0.000101 | +| loss | -0.0448 | +| n_updates | 9732 | +| policy_gradient_loss | -0.0307 | +| value_loss | 0.000146 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.256 | +| time/ | | +| fps | 1366 | +| iterations | 2435 | +| time_elapsed | 3648 | +| total_timesteps | 4986880 | +| train/ | | +| approx_kl | 0.023880463 | +| clip_fraction | 0.407 | +| clip_range | 0.0877 | +| entropy_loss | -7.42 | +| explained_variance | -0.0211 | +| learning_rate | 0.000101 | +| loss | -0.0325 | +| n_updates | 9736 | +| policy_gradient_loss | -0.0243 | +| value_loss | 0.000197 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.264 | +| time/ | | +| fps | 1367 | +| iterations | 2436 | +| time_elapsed | 3649 | +| total_timesteps | 4988928 | +| train/ | | +| approx_kl | 0.02437807 | +| clip_fraction | 0.39 | +| clip_range | 0.0877 | +| entropy_loss | -7.31 | +| explained_variance | -0.181 | +| learning_rate | 0.000101 | +| loss | -0.049 | +| n_updates | 9740 | +| policy_gradient_loss | -0.0262 | +| value_loss | 0.000166 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.26 | +| time/ | | +| fps | 1367 | +| iterations | 2437 | +| time_elapsed | 3650 | +| total_timesteps | 4990976 | +| train/ | | +| approx_kl | 0.02040175 | +| clip_fraction | 0.353 | +| clip_range | 0.0876 | +| entropy_loss | -7.02 | +| explained_variance | -0.14 | +| learning_rate | 0.000101 | +| loss | -0.0324 | +| n_updates | 9744 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000334 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.26 | +| time/ | | +| fps | 1367 | +| iterations | 2438 | +| time_elapsed | 3652 | +| total_timesteps | 4993024 | +| train/ | | +| approx_kl | 0.027906416 | +| clip_fraction | 0.423 | +| clip_range | 0.0876 | +| entropy_loss | -7.21 | +| explained_variance | -0.124 | +| learning_rate | 0.000101 | +| loss | -0.0369 | +| n_updates | 9748 | +| policy_gradient_loss | -0.0266 | +| value_loss | 0.000195 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.26 | +| time/ | | +| fps | 1367 | +| iterations | 2439 | +| time_elapsed | 3653 | +| total_timesteps | 4995072 | +| train/ | | +| approx_kl | 0.027989995 | +| clip_fraction | 0.43 | +| clip_range | 0.0876 | +| entropy_loss | -7.39 | +| explained_variance | -0.376 | +| learning_rate | 0.000101 | +| loss | -0.0464 | +| n_updates | 9752 | +| policy_gradient_loss | -0.0307 | +| value_loss | 9.98e-05 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.262 | +| time/ | | +| fps | 1367 | +| iterations | 2440 | +| time_elapsed | 3655 | +| total_timesteps | 4997120 | +| train/ | | +| approx_kl | 0.0301693 | +| clip_fraction | 0.407 | +| clip_range | 0.0876 | +| entropy_loss | -7.39 | +| explained_variance | -0.126 | +| learning_rate | 0.000101 | +| loss | -0.0452 | +| n_updates | 9756 | +| policy_gradient_loss | -0.0259 | +| value_loss | 0.000186 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.262 | +| time/ | | +| fps | 1367 | +| iterations | 2441 | +| time_elapsed | 3656 | +| total_timesteps | 4999168 | +| train/ | | +| approx_kl | 0.027188443 | +| clip_fraction | 0.383 | +| clip_range | 0.0875 | +| entropy_loss | -7.31 | +| explained_variance | -0.202 | +| learning_rate | 0.000101 | +| loss | -0.0337 | +| n_updates | 9760 | +| policy_gradient_loss | -0.0231 | +| value_loss | 0.000183 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.262 | +| time/ | | +| fps | 1367 | +| iterations | 2442 | +| time_elapsed | 3658 | +| total_timesteps | 5001216 | +| train/ | | +| approx_kl | 0.02442524 | +| clip_fraction | 0.402 | +| clip_range | 0.0875 | +| entropy_loss | -7.37 | +| explained_variance | -0.015 | +| learning_rate | 0.000101 | +| loss | -0.0389 | +| n_updates | 9764 | +| policy_gradient_loss | -0.0256 | +| value_loss | 0.000151 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.26 | +| time/ | | +| fps | 1367 | +| iterations | 2443 | +| time_elapsed | 3659 | +| total_timesteps | 5003264 | +| train/ | | +| approx_kl | 0.020040385 | +| clip_fraction | 0.381 | +| clip_range | 0.0875 | +| entropy_loss | -7.33 | +| explained_variance | 0.00279 | +| learning_rate | 0.000101 | +| loss | -0.0357 | +| n_updates | 9768 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.0003 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.238 | +| time/ | | +| fps | 1367 | +| iterations | 2444 | +| time_elapsed | 3661 | +| total_timesteps | 5005312 | +| train/ | | +| approx_kl | 0.0234154 | +| clip_fraction | 0.41 | +| clip_range | 0.0875 | +| entropy_loss | -7.24 | +| explained_variance | -0.146 | +| learning_rate | 0.000101 | +| loss | -0.0413 | +| n_updates | 9772 | +| policy_gradient_loss | -0.0285 | +| value_loss | 0.000177 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.237 | +| time/ | | +| fps | 1367 | +| iterations | 2445 | +| time_elapsed | 3662 | +| total_timesteps | 5007360 | +| train/ | | +| approx_kl | 0.026858576 | +| clip_fraction | 0.423 | +| clip_range | 0.0874 | +| entropy_loss | -7.17 | +| explained_variance | -0.0451 | +| learning_rate | 0.000101 | +| loss | -0.0495 | +| n_updates | 9776 | +| policy_gradient_loss | -0.0301 | +| value_loss | 0.000124 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.237 | +| time/ | | +| fps | 1367 | +| iterations | 2446 | +| time_elapsed | 3663 | +| total_timesteps | 5009408 | +| train/ | | +| approx_kl | 0.026597194 | +| clip_fraction | 0.422 | +| clip_range | 0.0874 | +| entropy_loss | -7.13 | +| explained_variance | -0.0432 | +| learning_rate | 0.000101 | +| loss | -0.0328 | +| n_updates | 9780 | +| policy_gradient_loss | -0.0229 | +| value_loss | 0.000329 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.237 | +| time/ | | +| fps | 1367 | +| iterations | 2447 | +| time_elapsed | 3665 | +| total_timesteps | 5011456 | +| train/ | | +| approx_kl | 0.024174966 | +| clip_fraction | 0.414 | +| clip_range | 0.0874 | +| entropy_loss | -7.3 | +| explained_variance | -0.295 | +| learning_rate | 0.000101 | +| loss | -0.0421 | +| n_updates | 9784 | +| policy_gradient_loss | -0.0281 | +| value_loss | 0.000171 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.236 | +| time/ | | +| fps | 1367 | +| iterations | 2448 | +| time_elapsed | 3666 | +| total_timesteps | 5013504 | +| train/ | | +| approx_kl | 0.029916931 | +| clip_fraction | 0.432 | +| clip_range | 0.0874 | +| entropy_loss | -7.3 | +| explained_variance | -0.0587 | +| learning_rate | 0.000101 | +| loss | -0.0394 | +| n_updates | 9788 | +| policy_gradient_loss | -0.0278 | +| value_loss | 0.000182 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.236 | +| time/ | | +| fps | 1367 | +| iterations | 2449 | +| time_elapsed | 3668 | +| total_timesteps | 5015552 | +| train/ | | +| approx_kl | 0.02877023 | +| clip_fraction | 0.412 | +| clip_range | 0.0873 | +| entropy_loss | -7.14 | +| explained_variance | -0.0729 | +| learning_rate | 0.000101 | +| loss | -0.0402 | +| n_updates | 9792 | +| policy_gradient_loss | -0.0237 | +| value_loss | 0.000268 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.243 | +| time/ | | +| fps | 1367 | +| iterations | 2450 | +| time_elapsed | 3669 | +| total_timesteps | 5017600 | +| train/ | | +| approx_kl | 0.027856424 | +| clip_fraction | 0.418 | +| clip_range | 0.0873 | +| entropy_loss | -7.38 | +| explained_variance | -0.269 | +| learning_rate | 0.000101 | +| loss | -0.0502 | +| n_updates | 9796 | +| policy_gradient_loss | -0.0304 | +| value_loss | 0.000123 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.233 | +| time/ | | +| fps | 1367 | +| iterations | 2451 | +| time_elapsed | 3670 | +| total_timesteps | 5019648 | +| train/ | | +| approx_kl | 0.027770242 | +| clip_fraction | 0.423 | +| clip_range | 0.0873 | +| entropy_loss | -7.25 | +| explained_variance | -0.389 | +| learning_rate | 0.000101 | +| loss | -0.0442 | +| n_updates | 9800 | +| policy_gradient_loss | -0.0292 | +| value_loss | 0.000113 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.227 | +| time/ | | +| fps | 1367 | +| iterations | 2452 | +| time_elapsed | 3672 | +| total_timesteps | 5021696 | +| train/ | | +| approx_kl | 0.028820641 | +| clip_fraction | 0.382 | +| clip_range | 0.0873 | +| entropy_loss | -7.19 | +| explained_variance | -4.77e-05 | +| learning_rate | 0.000101 | +| loss | -0.0392 | +| n_updates | 9804 | +| policy_gradient_loss | -0.0253 | +| value_loss | 0.00026 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.219 | +| time/ | | +| fps | 1367 | +| iterations | 2453 | +| time_elapsed | 3673 | +| total_timesteps | 5023744 | +| train/ | | +| approx_kl | 0.022530198 | +| clip_fraction | 0.389 | +| clip_range | 0.0872 | +| entropy_loss | -7.15 | +| explained_variance | -0.0828 | +| learning_rate | 0.000101 | +| loss | -0.0395 | +| n_updates | 9808 | +| policy_gradient_loss | -0.0253 | +| value_loss | 0.000303 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.222 | +| time/ | | +| fps | 1367 | +| iterations | 2454 | +| time_elapsed | 3675 | +| total_timesteps | 5025792 | +| train/ | | +| approx_kl | 0.029977744 | +| clip_fraction | 0.41 | +| clip_range | 0.0872 | +| entropy_loss | -7.24 | +| explained_variance | -0.328 | +| learning_rate | 0.000101 | +| loss | -0.0501 | +| n_updates | 9812 | +| policy_gradient_loss | -0.03 | +| value_loss | 0.000129 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.223 | +| time/ | | +| fps | 1367 | +| iterations | 2455 | +| time_elapsed | 3676 | +| total_timesteps | 5027840 | +| train/ | | +| approx_kl | 0.027269658 | +| clip_fraction | 0.401 | +| clip_range | 0.0872 | +| entropy_loss | -7.28 | +| explained_variance | -0.0897 | +| learning_rate | 0.0001 | +| loss | -0.038 | +| n_updates | 9816 | +| policy_gradient_loss | -0.0262 | +| value_loss | 0.000162 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.222 | +| time/ | | +| fps | 1367 | +| iterations | 2456 | +| time_elapsed | 3678 | +| total_timesteps | 5029888 | +| train/ | | +| approx_kl | 0.024521694 | +| clip_fraction | 0.4 | +| clip_range | 0.0872 | +| entropy_loss | -7.28 | +| explained_variance | -0.11 | +| learning_rate | 0.0001 | +| loss | -0.0434 | +| n_updates | 9820 | +| policy_gradient_loss | -0.0248 | +| value_loss | 0.000178 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.22 | +| time/ | | +| fps | 1367 | +| iterations | 2457 | +| time_elapsed | 3679 | +| total_timesteps | 5031936 | +| train/ | | +| approx_kl | 0.024334965 | +| clip_fraction | 0.397 | +| clip_range | 0.0871 | +| entropy_loss | -7.15 | +| explained_variance | -0.169 | +| learning_rate | 0.0001 | +| loss | -0.0361 | +| n_updates | 9824 | +| policy_gradient_loss | -0.0256 | +| value_loss | 0.00016 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.22 | +| time/ | | +| fps | 1367 | +| iterations | 2458 | +| time_elapsed | 3680 | +| total_timesteps | 5033984 | +| train/ | | +| approx_kl | 0.029895239 | +| clip_fraction | 0.406 | +| clip_range | 0.0871 | +| entropy_loss | -7.21 | +| explained_variance | -0.0133 | +| learning_rate | 0.0001 | +| loss | -0.0435 | +| n_updates | 9828 | +| policy_gradient_loss | -0.0271 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.218 | +| time/ | | +| fps | 1367 | +| iterations | 2459 | +| time_elapsed | 3682 | +| total_timesteps | 5036032 | +| train/ | | +| approx_kl | 0.024339652 | +| clip_fraction | 0.412 | +| clip_range | 0.0871 | +| entropy_loss | -7.15 | +| explained_variance | 0.0196 | +| learning_rate | 0.0001 | +| loss | -0.0447 | +| n_updates | 9832 | +| policy_gradient_loss | -0.0279 | +| value_loss | 0.000137 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.222 | +| time/ | | +| fps | 1367 | +| iterations | 2460 | +| time_elapsed | 3683 | +| total_timesteps | 5038080 | +| train/ | | +| approx_kl | 0.024520855 | +| clip_fraction | 0.394 | +| clip_range | 0.087 | +| entropy_loss | -7.29 | +| explained_variance | 0.0325 | +| learning_rate | 0.0001 | +| loss | -0.048 | +| n_updates | 9836 | +| policy_gradient_loss | -0.0282 | +| value_loss | 0.000155 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.221 | +| time/ | | +| fps | 1367 | +| iterations | 2461 | +| time_elapsed | 3685 | +| total_timesteps | 5040128 | +| train/ | | +| approx_kl | 0.025440108 | +| clip_fraction | 0.391 | +| clip_range | 0.087 | +| entropy_loss | -7.34 | +| explained_variance | -0.183 | +| learning_rate | 0.0001 | +| loss | -0.0439 | +| n_updates | 9840 | +| policy_gradient_loss | -0.0267 | +| value_loss | 0.000188 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.221 | +| time/ | | +| fps | 1367 | +| iterations | 2462 | +| time_elapsed | 3686 | +| total_timesteps | 5042176 | +| train/ | | +| approx_kl | 0.023828683 | +| clip_fraction | 0.416 | +| clip_range | 0.087 | +| entropy_loss | -7.3 | +| explained_variance | -0.279 | +| learning_rate | 0.0001 | +| loss | -0.0397 | +| n_updates | 9844 | +| policy_gradient_loss | -0.0277 | +| value_loss | 9.36e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.221 | +| time/ | | +| fps | 1367 | +| iterations | 2463 | +| time_elapsed | 3688 | +| total_timesteps | 5044224 | +| train/ | | +| approx_kl | 0.026781823 | +| clip_fraction | 0.384 | +| clip_range | 0.087 | +| entropy_loss | -7.3 | +| explained_variance | -0.0124 | +| learning_rate | 0.0001 | +| loss | -0.0431 | +| n_updates | 9848 | +| policy_gradient_loss | -0.026 | +| value_loss | 0.000113 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.221 | +| time/ | | +| fps | 1367 | +| iterations | 2464 | +| time_elapsed | 3689 | +| total_timesteps | 5046272 | +| train/ | | +| approx_kl | 0.025859568 | +| clip_fraction | 0.401 | +| clip_range | 0.0869 | +| entropy_loss | -7.36 | +| explained_variance | -0.0206 | +| learning_rate | 0.0001 | +| loss | -0.0395 | +| n_updates | 9852 | +| policy_gradient_loss | -0.0277 | +| value_loss | 8.68e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.215 | +| time/ | | +| fps | 1367 | +| iterations | 2465 | +| time_elapsed | 3690 | +| total_timesteps | 5048320 | +| train/ | | +| approx_kl | 0.027217695 | +| clip_fraction | 0.367 | +| clip_range | 0.0869 | +| entropy_loss | -7.31 | +| explained_variance | -0.0455 | +| learning_rate | 0.0001 | +| loss | -0.0461 | +| n_updates | 9856 | +| policy_gradient_loss | -0.0228 | +| value_loss | 0.00013 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.216 | +| time/ | | +| fps | 1367 | +| iterations | 2466 | +| time_elapsed | 3692 | +| total_timesteps | 5050368 | +| train/ | | +| approx_kl | 0.024710394 | +| clip_fraction | 0.401 | +| clip_range | 0.0869 | +| entropy_loss | -7.13 | +| explained_variance | -0.24 | +| learning_rate | 0.0001 | +| loss | -0.0448 | +| n_updates | 9860 | +| policy_gradient_loss | -0.0248 | +| value_loss | 0.000115 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.219 | +| time/ | | +| fps | 1367 | +| iterations | 2467 | +| time_elapsed | 3693 | +| total_timesteps | 5052416 | +| train/ | | +| approx_kl | 0.026353534 | +| clip_fraction | 0.39 | +| clip_range | 0.0869 | +| entropy_loss | -7.23 | +| explained_variance | -0.066 | +| learning_rate | 0.0001 | +| loss | -0.0421 | +| n_updates | 9864 | +| policy_gradient_loss | -0.0255 | +| value_loss | 0.000196 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.217 | +| time/ | | +| fps | 1367 | +| iterations | 2468 | +| time_elapsed | 3695 | +| total_timesteps | 5054464 | +| train/ | | +| approx_kl | 0.022908263 | +| clip_fraction | 0.408 | +| clip_range | 0.0868 | +| entropy_loss | -7.13 | +| explained_variance | -0.203 | +| learning_rate | 0.0001 | +| loss | -0.0426 | +| n_updates | 9868 | +| policy_gradient_loss | -0.0277 | +| value_loss | 0.000102 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.218 | +| time/ | | +| fps | 1367 | +| iterations | 2469 | +| time_elapsed | 3696 | +| total_timesteps | 5056512 | +| train/ | | +| approx_kl | 0.03057073 | +| clip_fraction | 0.394 | +| clip_range | 0.0868 | +| entropy_loss | -7.31 | +| explained_variance | -0.0206 | +| learning_rate | 9.99e-05 | +| loss | -0.0359 | +| n_updates | 9872 | +| policy_gradient_loss | -0.0251 | +| value_loss | 0.000164 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.218 | +| time/ | | +| fps | 1367 | +| iterations | 2470 | +| time_elapsed | 3698 | +| total_timesteps | 5058560 | +| train/ | | +| approx_kl | 0.027009023 | +| clip_fraction | 0.404 | +| clip_range | 0.0868 | +| entropy_loss | -7.33 | +| explained_variance | -0.025 | +| learning_rate | 9.99e-05 | +| loss | -0.0496 | +| n_updates | 9876 | +| policy_gradient_loss | -0.0275 | +| value_loss | 9.17e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.217 | +| time/ | | +| fps | 1367 | +| iterations | 2471 | +| time_elapsed | 3699 | +| total_timesteps | 5060608 | +| train/ | | +| approx_kl | 0.02400596 | +| clip_fraction | 0.392 | +| clip_range | 0.0868 | +| entropy_loss | -7.36 | +| explained_variance | -0.118 | +| learning_rate | 9.98e-05 | +| loss | -0.0443 | +| n_updates | 9880 | +| policy_gradient_loss | -0.0249 | +| value_loss | 0.000205 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.219 | +| time/ | | +| fps | 1367 | +| iterations | 2472 | +| time_elapsed | 3700 | +| total_timesteps | 5062656 | +| train/ | | +| approx_kl | 0.024073191 | +| clip_fraction | 0.376 | +| clip_range | 0.0867 | +| entropy_loss | -7.43 | +| explained_variance | -0.0875 | +| learning_rate | 9.98e-05 | +| loss | -0.0476 | +| n_updates | 9884 | +| policy_gradient_loss | -0.0236 | +| value_loss | 0.000216 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.214 | +| time/ | | +| fps | 1367 | +| iterations | 2473 | +| time_elapsed | 3702 | +| total_timesteps | 5064704 | +| train/ | | +| approx_kl | 0.023203783 | +| clip_fraction | 0.368 | +| clip_range | 0.0867 | +| entropy_loss | -7.11 | +| explained_variance | -0.0811 | +| learning_rate | 9.98e-05 | +| loss | -0.035 | +| n_updates | 9888 | +| policy_gradient_loss | -0.0248 | +| value_loss | 0.000311 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.213 | +| time/ | | +| fps | 1367 | +| iterations | 2474 | +| time_elapsed | 3703 | +| total_timesteps | 5066752 | +| train/ | | +| approx_kl | 0.027528677 | +| clip_fraction | 0.415 | +| clip_range | 0.0867 | +| entropy_loss | -7.17 | +| explained_variance | -0.333 | +| learning_rate | 9.97e-05 | +| loss | -0.0504 | +| n_updates | 9892 | +| policy_gradient_loss | -0.0299 | +| value_loss | 0.000105 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.213 | +| time/ | | +| fps | 1368 | +| iterations | 2475 | +| time_elapsed | 3705 | +| total_timesteps | 5068800 | +| train/ | | +| approx_kl | 0.026398815 | +| clip_fraction | 0.402 | +| clip_range | 0.0867 | +| entropy_loss | -7.29 | +| explained_variance | -0.0627 | +| learning_rate | 9.97e-05 | +| loss | -0.0395 | +| n_updates | 9896 | +| policy_gradient_loss | -0.0253 | +| value_loss | 0.000146 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.212 | +| time/ | | +| fps | 1368 | +| iterations | 2476 | +| time_elapsed | 3706 | +| total_timesteps | 5070848 | +| train/ | | +| approx_kl | 0.025429506 | +| clip_fraction | 0.375 | +| clip_range | 0.0866 | +| entropy_loss | -7.41 | +| explained_variance | -0.075 | +| learning_rate | 9.96e-05 | +| loss | -0.041 | +| n_updates | 9900 | +| policy_gradient_loss | -0.026 | +| value_loss | 0.000251 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.207 | +| time/ | | +| fps | 1368 | +| iterations | 2477 | +| time_elapsed | 3708 | +| total_timesteps | 5072896 | +| train/ | | +| approx_kl | 0.02859104 | +| clip_fraction | 0.407 | +| clip_range | 0.0866 | +| entropy_loss | -7.31 | +| explained_variance | -0.139 | +| learning_rate | 9.96e-05 | +| loss | -0.0481 | +| n_updates | 9904 | +| policy_gradient_loss | -0.0285 | +| value_loss | 0.000136 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.214 | +| time/ | | +| fps | 1368 | +| iterations | 2478 | +| time_elapsed | 3709 | +| total_timesteps | 5074944 | +| train/ | | +| approx_kl | 0.028888404 | +| clip_fraction | 0.431 | +| clip_range | 0.0866 | +| entropy_loss | -7.3 | +| explained_variance | -0.648 | +| learning_rate | 9.96e-05 | +| loss | -0.0518 | +| n_updates | 9908 | +| policy_gradient_loss | -0.0331 | +| value_loss | 7.55e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.215 | +| time/ | | +| fps | 1368 | +| iterations | 2479 | +| time_elapsed | 3711 | +| total_timesteps | 5076992 | +| train/ | | +| approx_kl | 0.023700733 | +| clip_fraction | 0.383 | +| clip_range | 0.0866 | +| entropy_loss | -7.14 | +| explained_variance | -0.0396 | +| learning_rate | 9.95e-05 | +| loss | -0.0457 | +| n_updates | 9912 | +| policy_gradient_loss | -0.026 | +| value_loss | 0.000255 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.217 | +| time/ | | +| fps | 1368 | +| iterations | 2480 | +| time_elapsed | 3712 | +| total_timesteps | 5079040 | +| train/ | | +| approx_kl | 0.026820552 | +| clip_fraction | 0.406 | +| clip_range | 0.0865 | +| entropy_loss | -7.23 | +| explained_variance | -0.245 | +| learning_rate | 9.95e-05 | +| loss | -0.0466 | +| n_updates | 9916 | +| policy_gradient_loss | -0.0282 | +| value_loss | 0.000114 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.212 | +| time/ | | +| fps | 1368 | +| iterations | 2481 | +| time_elapsed | 3714 | +| total_timesteps | 5081088 | +| train/ | | +| approx_kl | 0.026825301 | +| clip_fraction | 0.398 | +| clip_range | 0.0865 | +| entropy_loss | -7.3 | +| explained_variance | -0.191 | +| learning_rate | 9.94e-05 | +| loss | -0.0372 | +| n_updates | 9920 | +| policy_gradient_loss | -0.0282 | +| value_loss | 0.000188 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.212 | +| time/ | | +| fps | 1368 | +| iterations | 2482 | +| time_elapsed | 3715 | +| total_timesteps | 5083136 | +| train/ | | +| approx_kl | 0.025470223 | +| clip_fraction | 0.385 | +| clip_range | 0.0865 | +| entropy_loss | -7.2 | +| explained_variance | -0.179 | +| learning_rate | 9.94e-05 | +| loss | -0.0452 | +| n_updates | 9924 | +| policy_gradient_loss | -0.0257 | +| value_loss | 0.000167 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.22 | +| time/ | | +| fps | 1368 | +| iterations | 2483 | +| time_elapsed | 3716 | +| total_timesteps | 5085184 | +| train/ | | +| approx_kl | 0.02480136 | +| clip_fraction | 0.415 | +| clip_range | 0.0865 | +| entropy_loss | -7.26 | +| explained_variance | 0.0887 | +| learning_rate | 9.94e-05 | +| loss | -0.0437 | +| n_updates | 9928 | +| policy_gradient_loss | -0.0261 | +| value_loss | 0.000125 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.227 | +| time/ | | +| fps | 1368 | +| iterations | 2484 | +| time_elapsed | 3718 | +| total_timesteps | 5087232 | +| train/ | | +| approx_kl | 0.023148885 | +| clip_fraction | 0.378 | +| clip_range | 0.0864 | +| entropy_loss | -7.2 | +| explained_variance | 0.046 | +| learning_rate | 9.93e-05 | +| loss | -0.0426 | +| n_updates | 9932 | +| policy_gradient_loss | -0.0246 | +| value_loss | 0.000164 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.227 | +| time/ | | +| fps | 1368 | +| iterations | 2485 | +| time_elapsed | 3719 | +| total_timesteps | 5089280 | +| train/ | | +| approx_kl | 0.026497252 | +| clip_fraction | 0.402 | +| clip_range | 0.0864 | +| entropy_loss | -7.28 | +| explained_variance | 0.0673 | +| learning_rate | 9.93e-05 | +| loss | -0.0404 | +| n_updates | 9936 | +| policy_gradient_loss | -0.0272 | +| value_loss | 0.0002 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.23 | +| time/ | | +| fps | 1368 | +| iterations | 2486 | +| time_elapsed | 3721 | +| total_timesteps | 5091328 | +| train/ | | +| approx_kl | 0.026495779 | +| clip_fraction | 0.427 | +| clip_range | 0.0864 | +| entropy_loss | -7.23 | +| explained_variance | -0.406 | +| learning_rate | 9.92e-05 | +| loss | -0.0494 | +| n_updates | 9940 | +| policy_gradient_loss | -0.0318 | +| value_loss | 0.000157 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.233 | +| time/ | | +| fps | 1368 | +| iterations | 2487 | +| time_elapsed | 3722 | +| total_timesteps | 5093376 | +| train/ | | +| approx_kl | 0.026703354 | +| clip_fraction | 0.379 | +| clip_range | 0.0864 | +| entropy_loss | -7.19 | +| explained_variance | -0.0761 | +| learning_rate | 9.92e-05 | +| loss | -0.0393 | +| n_updates | 9944 | +| policy_gradient_loss | -0.0233 | +| value_loss | 0.000251 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.24 | +| time/ | | +| fps | 1368 | +| iterations | 2488 | +| time_elapsed | 3724 | +| total_timesteps | 5095424 | +| train/ | | +| approx_kl | 0.025767472 | +| clip_fraction | 0.402 | +| clip_range | 0.0863 | +| entropy_loss | -7.3 | +| explained_variance | -0.0982 | +| learning_rate | 9.92e-05 | +| loss | -0.0339 | +| n_updates | 9948 | +| policy_gradient_loss | -0.0227 | +| value_loss | 0.00028 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.24 | +| time/ | | +| fps | 1368 | +| iterations | 2489 | +| time_elapsed | 3725 | +| total_timesteps | 5097472 | +| train/ | | +| approx_kl | 0.025771905 | +| clip_fraction | 0.384 | +| clip_range | 0.0863 | +| entropy_loss | -6.98 | +| explained_variance | -0.000879 | +| learning_rate | 9.91e-05 | +| loss | -0.0428 | +| n_updates | 9952 | +| policy_gradient_loss | -0.0244 | +| value_loss | 0.000324 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.24 | +| time/ | | +| fps | 1368 | +| iterations | 2490 | +| time_elapsed | 3726 | +| total_timesteps | 5099520 | +| train/ | | +| approx_kl | 0.032344148 | +| clip_fraction | 0.424 | +| clip_range | 0.0863 | +| entropy_loss | -7.26 | +| explained_variance | -0.306 | +| learning_rate | 9.91e-05 | +| loss | -0.0441 | +| n_updates | 9956 | +| policy_gradient_loss | -0.0295 | +| value_loss | 0.000131 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.239 | +| time/ | | +| fps | 1368 | +| iterations | 2491 | +| time_elapsed | 3728 | +| total_timesteps | 5101568 | +| train/ | | +| approx_kl | 0.02287754 | +| clip_fraction | 0.393 | +| clip_range | 0.0863 | +| entropy_loss | -7.23 | +| explained_variance | -0.212 | +| learning_rate | 9.9e-05 | +| loss | -0.0372 | +| n_updates | 9960 | +| policy_gradient_loss | -0.028 | +| value_loss | 0.000154 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.238 | +| time/ | | +| fps | 1368 | +| iterations | 2492 | +| time_elapsed | 3730 | +| total_timesteps | 5103616 | +| train/ | | +| approx_kl | 0.027687877 | +| clip_fraction | 0.398 | +| clip_range | 0.0862 | +| entropy_loss | -7.2 | +| explained_variance | -0.258 | +| learning_rate | 9.9e-05 | +| loss | -0.0431 | +| n_updates | 9964 | +| policy_gradient_loss | -0.0269 | +| value_loss | 0.000221 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.238 | +| time/ | | +| fps | 1368 | +| iterations | 2493 | +| time_elapsed | 3731 | +| total_timesteps | 5105664 | +| train/ | | +| approx_kl | 0.024647785 | +| clip_fraction | 0.389 | +| clip_range | 0.0862 | +| entropy_loss | -7.4 | +| explained_variance | -0.243 | +| learning_rate | 9.89e-05 | +| loss | -0.0454 | +| n_updates | 9968 | +| policy_gradient_loss | -0.0287 | +| value_loss | 0.000125 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.234 | +| time/ | | +| fps | 1368 | +| iterations | 2494 | +| time_elapsed | 3732 | +| total_timesteps | 5107712 | +| train/ | | +| approx_kl | 0.023995478 | +| clip_fraction | 0.42 | +| clip_range | 0.0862 | +| entropy_loss | -7.4 | +| explained_variance | 0.0319 | +| learning_rate | 9.89e-05 | +| loss | -0.0378 | +| n_updates | 9972 | +| policy_gradient_loss | -0.0267 | +| value_loss | 0.000197 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.234 | +| time/ | | +| fps | 1368 | +| iterations | 2495 | +| time_elapsed | 3734 | +| total_timesteps | 5109760 | +| train/ | | +| approx_kl | 0.027431918 | +| clip_fraction | 0.427 | +| clip_range | 0.0862 | +| entropy_loss | -7.22 | +| explained_variance | -0.209 | +| learning_rate | 9.89e-05 | +| loss | -0.0474 | +| n_updates | 9976 | +| policy_gradient_loss | -0.0259 | +| value_loss | 0.000184 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.237 | +| time/ | | +| fps | 1368 | +| iterations | 2496 | +| time_elapsed | 3735 | +| total_timesteps | 5111808 | +| train/ | | +| approx_kl | 0.02903708 | +| clip_fraction | 0.414 | +| clip_range | 0.0861 | +| entropy_loss | -7.25 | +| explained_variance | -0.19 | +| learning_rate | 9.88e-05 | +| loss | -0.0423 | +| n_updates | 9980 | +| policy_gradient_loss | -0.0283 | +| value_loss | 9.96e-05 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.237 | +| time/ | | +| fps | 1368 | +| iterations | 2497 | +| time_elapsed | 3737 | +| total_timesteps | 5113856 | +| train/ | | +| approx_kl | 0.02624373 | +| clip_fraction | 0.4 | +| clip_range | 0.0861 | +| entropy_loss | -7.41 | +| explained_variance | -0.195 | +| learning_rate | 9.88e-05 | +| loss | -0.0491 | +| n_updates | 9984 | +| policy_gradient_loss | -0.0285 | +| value_loss | 8.65e-05 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.233 | +| time/ | | +| fps | 1368 | +| iterations | 2498 | +| time_elapsed | 3738 | +| total_timesteps | 5115904 | +| train/ | | +| approx_kl | 0.02536517 | +| clip_fraction | 0.389 | +| clip_range | 0.0861 | +| entropy_loss | -7.16 | +| explained_variance | -0.0815 | +| learning_rate | 9.87e-05 | +| loss | -0.0365 | +| n_updates | 9988 | +| policy_gradient_loss | -0.0246 | +| value_loss | 0.00014 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.233 | +| time/ | | +| fps | 1368 | +| iterations | 2499 | +| time_elapsed | 3740 | +| total_timesteps | 5117952 | +| train/ | | +| approx_kl | 0.02179198 | +| clip_fraction | 0.387 | +| clip_range | 0.0861 | +| entropy_loss | -7.21 | +| explained_variance | 0.0331 | +| learning_rate | 9.87e-05 | +| loss | -0.0298 | +| n_updates | 9992 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000239 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.229 | +| time/ | | +| fps | 1368 | +| iterations | 2500 | +| time_elapsed | 3741 | +| total_timesteps | 5120000 | +| train/ | | +| approx_kl | 0.027856357 | +| clip_fraction | 0.396 | +| clip_range | 0.086 | +| entropy_loss | -7.08 | +| explained_variance | -0.117 | +| learning_rate | 9.87e-05 | +| loss | -0.0393 | +| n_updates | 9996 | +| policy_gradient_loss | -0.0266 | +| value_loss | 0.000171 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.225 | +| time/ | | +| fps | 1368 | +| iterations | 2501 | +| time_elapsed | 3743 | +| total_timesteps | 5122048 | +| train/ | | +| approx_kl | 0.026670022 | +| clip_fraction | 0.387 | +| clip_range | 0.086 | +| entropy_loss | -7.08 | +| explained_variance | -0.0838 | +| learning_rate | 9.86e-05 | +| loss | -0.0417 | +| n_updates | 10000 | +| policy_gradient_loss | -0.0253 | +| value_loss | 0.000183 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.225 | +| time/ | | +| fps | 1368 | +| iterations | 2502 | +| time_elapsed | 3744 | +| total_timesteps | 5124096 | +| train/ | | +| approx_kl | 0.027174091 | +| clip_fraction | 0.419 | +| clip_range | 0.086 | +| entropy_loss | -7.25 | +| explained_variance | -0.119 | +| learning_rate | 9.86e-05 | +| loss | -0.0378 | +| n_updates | 10004 | +| policy_gradient_loss | -0.0246 | +| value_loss | 0.000152 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.219 | +| time/ | | +| fps | 1368 | +| iterations | 2503 | +| time_elapsed | 3745 | +| total_timesteps | 5126144 | +| train/ | | +| approx_kl | 0.030316338 | +| clip_fraction | 0.404 | +| clip_range | 0.0859 | +| entropy_loss | -7.35 | +| explained_variance | 0.0192 | +| learning_rate | 9.85e-05 | +| loss | -0.0413 | +| n_updates | 10008 | +| policy_gradient_loss | -0.0265 | +| value_loss | 0.000124 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.216 | +| time/ | | +| fps | 1368 | +| iterations | 2504 | +| time_elapsed | 3747 | +| total_timesteps | 5128192 | +| train/ | | +| approx_kl | 0.027115066 | +| clip_fraction | 0.405 | +| clip_range | 0.0859 | +| entropy_loss | -7.45 | +| explained_variance | 0.00116 | +| learning_rate | 9.85e-05 | +| loss | -0.0481 | +| n_updates | 10012 | +| policy_gradient_loss | -0.0263 | +| value_loss | 0.00021 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.225 | +| time/ | | +| fps | 1368 | +| iterations | 2505 | +| time_elapsed | 3748 | +| total_timesteps | 5130240 | +| train/ | | +| approx_kl | 0.027328437 | +| clip_fraction | 0.407 | +| clip_range | 0.0859 | +| entropy_loss | -7.22 | +| explained_variance | -0.288 | +| learning_rate | 9.85e-05 | +| loss | -0.05 | +| n_updates | 10016 | +| policy_gradient_loss | -0.0287 | +| value_loss | 0.00017 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.222 | +| time/ | | +| fps | 1368 | +| iterations | 2506 | +| time_elapsed | 3750 | +| total_timesteps | 5132288 | +| train/ | | +| approx_kl | 0.026197052 | +| clip_fraction | 0.41 | +| clip_range | 0.0859 | +| entropy_loss | -7.37 | +| explained_variance | -0.0898 | +| learning_rate | 9.84e-05 | +| loss | -0.0348 | +| n_updates | 10020 | +| policy_gradient_loss | -0.025 | +| value_loss | 0.00014 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.221 | +| time/ | | +| fps | 1368 | +| iterations | 2507 | +| time_elapsed | 3751 | +| total_timesteps | 5134336 | +| train/ | | +| approx_kl | 0.023633461 | +| clip_fraction | 0.393 | +| clip_range | 0.0858 | +| entropy_loss | -7.19 | +| explained_variance | -0.426 | +| learning_rate | 9.84e-05 | +| loss | -0.0421 | +| n_updates | 10024 | +| policy_gradient_loss | -0.0259 | +| value_loss | 0.00011 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.229 | +| time/ | | +| fps | 1368 | +| iterations | 2508 | +| time_elapsed | 3753 | +| total_timesteps | 5136384 | +| train/ | | +| approx_kl | 0.026617363 | +| clip_fraction | 0.401 | +| clip_range | 0.0858 | +| entropy_loss | -7.35 | +| explained_variance | -0.108 | +| learning_rate | 9.83e-05 | +| loss | -0.0352 | +| n_updates | 10028 | +| policy_gradient_loss | -0.0247 | +| value_loss | 0.000171 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.229 | +| time/ | | +| fps | 1368 | +| iterations | 2509 | +| time_elapsed | 3754 | +| total_timesteps | 5138432 | +| train/ | | +| approx_kl | 0.02855125 | +| clip_fraction | 0.394 | +| clip_range | 0.0858 | +| entropy_loss | -7.24 | +| explained_variance | -0.0459 | +| learning_rate | 9.83e-05 | +| loss | -0.0393 | +| n_updates | 10032 | +| policy_gradient_loss | -0.0234 | +| value_loss | 0.000223 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.234 | +| time/ | | +| fps | 1368 | +| iterations | 2510 | +| time_elapsed | 3756 | +| total_timesteps | 5140480 | +| train/ | | +| approx_kl | 0.025130311 | +| clip_fraction | 0.416 | +| clip_range | 0.0858 | +| entropy_loss | -7.28 | +| explained_variance | -0.147 | +| learning_rate | 9.83e-05 | +| loss | -0.0393 | +| n_updates | 10036 | +| policy_gradient_loss | -0.0271 | +| value_loss | 0.000176 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.234 | +| time/ | | +| fps | 1368 | +| iterations | 2511 | +| time_elapsed | 3757 | +| total_timesteps | 5142528 | +| train/ | | +| approx_kl | 0.029563896 | +| clip_fraction | 0.393 | +| clip_range | 0.0857 | +| entropy_loss | -7.31 | +| explained_variance | -0.0972 | +| learning_rate | 9.82e-05 | +| loss | -0.0396 | +| n_updates | 10040 | +| policy_gradient_loss | -0.0259 | +| value_loss | 0.000243 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.227 | +| time/ | | +| fps | 1368 | +| iterations | 2512 | +| time_elapsed | 3759 | +| total_timesteps | 5144576 | +| train/ | | +| approx_kl | 0.028038142 | +| clip_fraction | 0.409 | +| clip_range | 0.0857 | +| entropy_loss | -7.42 | +| explained_variance | -0.173 | +| learning_rate | 9.82e-05 | +| loss | -0.044 | +| n_updates | 10044 | +| policy_gradient_loss | -0.0268 | +| value_loss | 0.000123 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.229 | +| time/ | | +| fps | 1368 | +| iterations | 2513 | +| time_elapsed | 3760 | +| total_timesteps | 5146624 | +| train/ | | +| approx_kl | 0.029476136 | +| clip_fraction | 0.369 | +| clip_range | 0.0857 | +| entropy_loss | -7.07 | +| explained_variance | -0.0133 | +| learning_rate | 9.81e-05 | +| loss | -0.0365 | +| n_updates | 10048 | +| policy_gradient_loss | -0.0241 | +| value_loss | 0.000196 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.229 | +| time/ | | +| fps | 1368 | +| iterations | 2514 | +| time_elapsed | 3761 | +| total_timesteps | 5148672 | +| train/ | | +| approx_kl | 0.025437394 | +| clip_fraction | 0.416 | +| clip_range | 0.0857 | +| entropy_loss | -7.3 | +| explained_variance | -0.176 | +| learning_rate | 9.81e-05 | +| loss | -0.0462 | +| n_updates | 10052 | +| policy_gradient_loss | -0.0295 | +| value_loss | 0.000115 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.235 | +| time/ | | +| fps | 1368 | +| iterations | 2515 | +| time_elapsed | 3763 | +| total_timesteps | 5150720 | +| train/ | | +| approx_kl | 0.023681412 | +| clip_fraction | 0.414 | +| clip_range | 0.0856 | +| entropy_loss | -7.39 | +| explained_variance | -0.367 | +| learning_rate | 9.81e-05 | +| loss | -0.0412 | +| n_updates | 10056 | +| policy_gradient_loss | -0.0267 | +| value_loss | 0.000114 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.246 | +| time/ | | +| fps | 1368 | +| iterations | 2516 | +| time_elapsed | 3764 | +| total_timesteps | 5152768 | +| train/ | | +| approx_kl | 0.019799992 | +| clip_fraction | 0.378 | +| clip_range | 0.0856 | +| entropy_loss | -7.28 | +| explained_variance | -0.00661 | +| learning_rate | 9.8e-05 | +| loss | -0.035 | +| n_updates | 10060 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000272 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.25 | +| time/ | | +| fps | 1368 | +| iterations | 2517 | +| time_elapsed | 3766 | +| total_timesteps | 5154816 | +| train/ | | +| approx_kl | 0.021172974 | +| clip_fraction | 0.405 | +| clip_range | 0.0856 | +| entropy_loss | -7.16 | +| explained_variance | -0.0811 | +| learning_rate | 9.8e-05 | +| loss | -0.0357 | +| n_updates | 10064 | +| policy_gradient_loss | -0.0224 | +| value_loss | 0.000262 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.242 | +| time/ | | +| fps | 1368 | +| iterations | 2518 | +| time_elapsed | 3767 | +| total_timesteps | 5156864 | +| train/ | | +| approx_kl | 0.02938379 | +| clip_fraction | 0.419 | +| clip_range | 0.0856 | +| entropy_loss | -7.09 | +| explained_variance | -0.285 | +| learning_rate | 9.79e-05 | +| loss | -0.0482 | +| n_updates | 10068 | +| policy_gradient_loss | -0.0309 | +| value_loss | 0.000114 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.244 | +| time/ | | +| fps | 1368 | +| iterations | 2519 | +| time_elapsed | 3769 | +| total_timesteps | 5158912 | +| train/ | | +| approx_kl | 0.022523113 | +| clip_fraction | 0.386 | +| clip_range | 0.0855 | +| entropy_loss | -7.16 | +| explained_variance | -0.00948 | +| learning_rate | 9.79e-05 | +| loss | -0.0324 | +| n_updates | 10072 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000368 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.245 | +| time/ | | +| fps | 1368 | +| iterations | 2520 | +| time_elapsed | 3770 | +| total_timesteps | 5160960 | +| train/ | | +| approx_kl | 0.026978258 | +| clip_fraction | 0.415 | +| clip_range | 0.0855 | +| entropy_loss | -7.06 | +| explained_variance | -0.211 | +| learning_rate | 9.79e-05 | +| loss | -0.042 | +| n_updates | 10076 | +| policy_gradient_loss | -0.0281 | +| value_loss | 0.000224 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.24 | +| time/ | | +| fps | 1368 | +| iterations | 2521 | +| time_elapsed | 3772 | +| total_timesteps | 5163008 | +| train/ | | +| approx_kl | 0.02708472 | +| clip_fraction | 0.41 | +| clip_range | 0.0855 | +| entropy_loss | -7.17 | +| explained_variance | -0.345 | +| learning_rate | 9.78e-05 | +| loss | -0.0451 | +| n_updates | 10080 | +| policy_gradient_loss | -0.0269 | +| value_loss | 0.000179 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.236 | +| time/ | | +| fps | 1368 | +| iterations | 2522 | +| time_elapsed | 3773 | +| total_timesteps | 5165056 | +| train/ | | +| approx_kl | 0.025001397 | +| clip_fraction | 0.424 | +| clip_range | 0.0855 | +| entropy_loss | -7.2 | +| explained_variance | -0.232 | +| learning_rate | 9.78e-05 | +| loss | -0.0423 | +| n_updates | 10084 | +| policy_gradient_loss | -0.0277 | +| value_loss | 0.000151 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.236 | +| time/ | | +| fps | 1368 | +| iterations | 2523 | +| time_elapsed | 3774 | +| total_timesteps | 5167104 | +| train/ | | +| approx_kl | 0.025503919 | +| clip_fraction | 0.421 | +| clip_range | 0.0854 | +| entropy_loss | -7.26 | +| explained_variance | -0.0862 | +| learning_rate | 9.77e-05 | +| loss | -0.0384 | +| n_updates | 10088 | +| policy_gradient_loss | -0.0261 | +| value_loss | 0.000228 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.237 | +| time/ | | +| fps | 1368 | +| iterations | 2524 | +| time_elapsed | 3776 | +| total_timesteps | 5169152 | +| train/ | | +| approx_kl | 0.020661453 | +| clip_fraction | 0.388 | +| clip_range | 0.0854 | +| entropy_loss | -7.25 | +| explained_variance | -0.0765 | +| learning_rate | 9.77e-05 | +| loss | -0.0392 | +| n_updates | 10092 | +| policy_gradient_loss | -0.0229 | +| value_loss | 0.000272 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.248 | +| time/ | | +| fps | 1368 | +| iterations | 2525 | +| time_elapsed | 3777 | +| total_timesteps | 5171200 | +| train/ | | +| approx_kl | 0.020233678 | +| clip_fraction | 0.393 | +| clip_range | 0.0854 | +| entropy_loss | -7.28 | +| explained_variance | -0.054 | +| learning_rate | 9.77e-05 | +| loss | -0.0357 | +| n_updates | 10096 | +| policy_gradient_loss | -0.0252 | +| value_loss | 0.000301 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.251 | +| time/ | | +| fps | 1368 | +| iterations | 2526 | +| time_elapsed | 3779 | +| total_timesteps | 5173248 | +| train/ | | +| approx_kl | 0.023264822 | +| clip_fraction | 0.423 | +| clip_range | 0.0854 | +| entropy_loss | -7.23 | +| explained_variance | -0.0459 | +| learning_rate | 9.76e-05 | +| loss | -0.0354 | +| n_updates | 10100 | +| policy_gradient_loss | -0.0243 | +| value_loss | 0.000297 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.259 | +| time/ | | +| fps | 1368 | +| iterations | 2527 | +| time_elapsed | 3780 | +| total_timesteps | 5175296 | +| train/ | | +| approx_kl | 0.022969542 | +| clip_fraction | 0.396 | +| clip_range | 0.0853 | +| entropy_loss | -7.2 | +| explained_variance | 0.0335 | +| learning_rate | 9.76e-05 | +| loss | -0.0454 | +| n_updates | 10104 | +| policy_gradient_loss | -0.0238 | +| value_loss | 0.000287 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.255 | +| time/ | | +| fps | 1368 | +| iterations | 2528 | +| time_elapsed | 3782 | +| total_timesteps | 5177344 | +| train/ | | +| approx_kl | 0.023386203 | +| clip_fraction | 0.391 | +| clip_range | 0.0853 | +| entropy_loss | -7.31 | +| explained_variance | 0.00124 | +| learning_rate | 9.75e-05 | +| loss | -0.0355 | +| n_updates | 10108 | +| policy_gradient_loss | -0.0243 | +| value_loss | 0.000257 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.257 | +| time/ | | +| fps | 1368 | +| iterations | 2529 | +| time_elapsed | 3783 | +| total_timesteps | 5179392 | +| train/ | | +| approx_kl | 0.028197378 | +| clip_fraction | 0.417 | +| clip_range | 0.0853 | +| entropy_loss | -7.3 | +| explained_variance | -0.152 | +| learning_rate | 9.75e-05 | +| loss | -0.0444 | +| n_updates | 10112 | +| policy_gradient_loss | -0.0274 | +| value_loss | 0.000224 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.257 | +| time/ | | +| fps | 1368 | +| iterations | 2530 | +| time_elapsed | 3784 | +| total_timesteps | 5181440 | +| train/ | | +| approx_kl | 0.024046868 | +| clip_fraction | 0.421 | +| clip_range | 0.0853 | +| entropy_loss | -7.19 | +| explained_variance | -0.202 | +| learning_rate | 9.74e-05 | +| loss | -0.0439 | +| n_updates | 10116 | +| policy_gradient_loss | -0.0304 | +| value_loss | 0.00013 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.256 | +| time/ | | +| fps | 1368 | +| iterations | 2531 | +| time_elapsed | 3786 | +| total_timesteps | 5183488 | +| train/ | | +| approx_kl | 0.02874437 | +| clip_fraction | 0.459 | +| clip_range | 0.0852 | +| entropy_loss | -7.29 | +| explained_variance | -0.917 | +| learning_rate | 9.74e-05 | +| loss | -0.0558 | +| n_updates | 10120 | +| policy_gradient_loss | -0.0365 | +| value_loss | 5.15e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.259 | +| time/ | | +| fps | 1368 | +| iterations | 2532 | +| time_elapsed | 3787 | +| total_timesteps | 5185536 | +| train/ | | +| approx_kl | 0.020285537 | +| clip_fraction | 0.389 | +| clip_range | 0.0852 | +| entropy_loss | -7.24 | +| explained_variance | -0.057 | +| learning_rate | 9.74e-05 | +| loss | -0.043 | +| n_updates | 10124 | +| policy_gradient_loss | -0.0238 | +| value_loss | 0.000218 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.268 | +| time/ | | +| fps | 1369 | +| iterations | 2533 | +| time_elapsed | 3789 | +| total_timesteps | 5187584 | +| train/ | | +| approx_kl | 0.023601096 | +| clip_fraction | 0.386 | +| clip_range | 0.0852 | +| entropy_loss | -7.3 | +| explained_variance | -0.0657 | +| learning_rate | 9.73e-05 | +| loss | -0.0319 | +| n_updates | 10128 | +| policy_gradient_loss | -0.0233 | +| value_loss | 0.000233 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.264 | +| time/ | | +| fps | 1369 | +| iterations | 2534 | +| time_elapsed | 3790 | +| total_timesteps | 5189632 | +| train/ | | +| approx_kl | 0.026921533 | +| clip_fraction | 0.4 | +| clip_range | 0.0852 | +| entropy_loss | -7.25 | +| explained_variance | -0.194 | +| learning_rate | 9.73e-05 | +| loss | -0.0417 | +| n_updates | 10132 | +| policy_gradient_loss | -0.0266 | +| value_loss | 0.000144 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.263 | +| time/ | | +| fps | 1369 | +| iterations | 2535 | +| time_elapsed | 3792 | +| total_timesteps | 5191680 | +| train/ | | +| approx_kl | 0.022757022 | +| clip_fraction | 0.409 | +| clip_range | 0.0851 | +| entropy_loss | -7.24 | +| explained_variance | -0.176 | +| learning_rate | 9.72e-05 | +| loss | -0.0424 | +| n_updates | 10136 | +| policy_gradient_loss | -0.0272 | +| value_loss | 0.000117 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.261 | +| time/ | | +| fps | 1369 | +| iterations | 2536 | +| time_elapsed | 3793 | +| total_timesteps | 5193728 | +| train/ | | +| approx_kl | 0.024140112 | +| clip_fraction | 0.402 | +| clip_range | 0.0851 | +| entropy_loss | -7.28 | +| explained_variance | -0.2 | +| learning_rate | 9.72e-05 | +| loss | -0.0417 | +| n_updates | 10140 | +| policy_gradient_loss | -0.0271 | +| value_loss | 9.82e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.261 | +| time/ | | +| fps | 1369 | +| iterations | 2537 | +| time_elapsed | 3795 | +| total_timesteps | 5195776 | +| train/ | | +| approx_kl | 0.024705715 | +| clip_fraction | 0.404 | +| clip_range | 0.0851 | +| entropy_loss | -7.3 | +| explained_variance | -0.0759 | +| learning_rate | 9.72e-05 | +| loss | -0.0396 | +| n_updates | 10144 | +| policy_gradient_loss | -0.0247 | +| value_loss | 0.000144 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.256 | +| time/ | | +| fps | 1369 | +| iterations | 2538 | +| time_elapsed | 3796 | +| total_timesteps | 5197824 | +| train/ | | +| approx_kl | 0.02497121 | +| clip_fraction | 0.391 | +| clip_range | 0.0851 | +| entropy_loss | -7.26 | +| explained_variance | -0.148 | +| learning_rate | 9.71e-05 | +| loss | -0.0409 | +| n_updates | 10148 | +| policy_gradient_loss | -0.0252 | +| value_loss | 0.000143 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.256 | +| time/ | | +| fps | 1369 | +| iterations | 2539 | +| time_elapsed | 3798 | +| total_timesteps | 5199872 | +| train/ | | +| approx_kl | 0.022578418 | +| clip_fraction | 0.392 | +| clip_range | 0.085 | +| entropy_loss | -7.3 | +| explained_variance | -0.0674 | +| learning_rate | 9.71e-05 | +| loss | -0.0352 | +| n_updates | 10152 | +| policy_gradient_loss | -0.0231 | +| value_loss | 0.000165 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.255 | +| time/ | | +| fps | 1369 | +| iterations | 2540 | +| time_elapsed | 3799 | +| total_timesteps | 5201920 | +| train/ | | +| approx_kl | 0.023885194 | +| clip_fraction | 0.388 | +| clip_range | 0.085 | +| entropy_loss | -7.24 | +| explained_variance | -0.0576 | +| learning_rate | 9.7e-05 | +| loss | -0.0423 | +| n_updates | 10156 | +| policy_gradient_loss | -0.0253 | +| value_loss | 0.000167 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.255 | +| time/ | | +| fps | 1369 | +| iterations | 2541 | +| time_elapsed | 3800 | +| total_timesteps | 5203968 | +| train/ | | +| approx_kl | 0.021491177 | +| clip_fraction | 0.4 | +| clip_range | 0.085 | +| entropy_loss | -7.15 | +| explained_variance | -0.0238 | +| learning_rate | 9.7e-05 | +| loss | -0.0379 | +| n_updates | 10160 | +| policy_gradient_loss | -0.0238 | +| value_loss | 0.000215 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.254 | +| time/ | | +| fps | 1369 | +| iterations | 2542 | +| time_elapsed | 3802 | +| total_timesteps | 5206016 | +| train/ | | +| approx_kl | 0.02040127 | +| clip_fraction | 0.395 | +| clip_range | 0.085 | +| entropy_loss | -7.27 | +| explained_variance | -0.00467 | +| learning_rate | 9.7e-05 | +| loss | -0.0427 | +| n_updates | 10164 | +| policy_gradient_loss | -0.0249 | +| value_loss | 0.000177 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.26 | +| time/ | | +| fps | 1369 | +| iterations | 2543 | +| time_elapsed | 3803 | +| total_timesteps | 5208064 | +| train/ | | +| approx_kl | 0.027847927 | +| clip_fraction | 0.412 | +| clip_range | 0.0849 | +| entropy_loss | -7.31 | +| explained_variance | -0.128 | +| learning_rate | 9.69e-05 | +| loss | -0.0408 | +| n_updates | 10168 | +| policy_gradient_loss | -0.0268 | +| value_loss | 0.000125 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.26 | +| time/ | | +| fps | 1369 | +| iterations | 2544 | +| time_elapsed | 3805 | +| total_timesteps | 5210112 | +| train/ | | +| approx_kl | 0.023099983 | +| clip_fraction | 0.373 | +| clip_range | 0.0849 | +| entropy_loss | -7.23 | +| explained_variance | -0.0525 | +| learning_rate | 9.69e-05 | +| loss | -0.0374 | +| n_updates | 10172 | +| policy_gradient_loss | -0.0244 | +| value_loss | 0.000198 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.26 | +| time/ | | +| fps | 1369 | +| iterations | 2545 | +| time_elapsed | 3806 | +| total_timesteps | 5212160 | +| train/ | | +| approx_kl | 0.019572439 | +| clip_fraction | 0.367 | +| clip_range | 0.0849 | +| entropy_loss | -7.41 | +| explained_variance | -0.0626 | +| learning_rate | 9.68e-05 | +| loss | -0.0419 | +| n_updates | 10176 | +| policy_gradient_loss | -0.0222 | +| value_loss | 0.00018 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.267 | +| time/ | | +| fps | 1369 | +| iterations | 2546 | +| time_elapsed | 3808 | +| total_timesteps | 5214208 | +| train/ | | +| approx_kl | 0.024404187 | +| clip_fraction | 0.417 | +| clip_range | 0.0848 | +| entropy_loss | -7.42 | +| explained_variance | -0.425 | +| learning_rate | 9.68e-05 | +| loss | -0.0473 | +| n_updates | 10180 | +| policy_gradient_loss | -0.0325 | +| value_loss | 7.43e-05 | +----------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.262 | +| time/ | | +| fps | 1369 | +| iterations | 2547 | +| time_elapsed | 3809 | +| total_timesteps | 5216256 | +| train/ | | +| approx_kl | 0.027821 | +| clip_fraction | 0.388 | +| clip_range | 0.0848 | +| entropy_loss | -7.29 | +| explained_variance | -0.0202 | +| learning_rate | 9.68e-05 | +| loss | -0.0392 | +| n_updates | 10184 | +| policy_gradient_loss | -0.0232 | +| value_loss | 0.000314 | +-------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.263 | +| time/ | | +| fps | 1369 | +| iterations | 2548 | +| time_elapsed | 3811 | +| total_timesteps | 5218304 | +| train/ | | +| approx_kl | 0.024222296 | +| clip_fraction | 0.412 | +| clip_range | 0.0848 | +| entropy_loss | -7.11 | +| explained_variance | -0.681 | +| learning_rate | 9.67e-05 | +| loss | -0.0543 | +| n_updates | 10188 | +| policy_gradient_loss | -0.0314 | +| value_loss | 8.82e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.263 | +| time/ | | +| fps | 1369 | +| iterations | 2549 | +| time_elapsed | 3812 | +| total_timesteps | 5220352 | +| train/ | | +| approx_kl | 0.025352169 | +| clip_fraction | 0.418 | +| clip_range | 0.0848 | +| entropy_loss | -7.28 | +| explained_variance | -0.0202 | +| learning_rate | 9.67e-05 | +| loss | -0.0345 | +| n_updates | 10192 | +| policy_gradient_loss | -0.0246 | +| value_loss | 0.000162 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.263 | +| time/ | | +| fps | 1369 | +| iterations | 2550 | +| time_elapsed | 3813 | +| total_timesteps | 5222400 | +| train/ | | +| approx_kl | 0.023257816 | +| clip_fraction | 0.4 | +| clip_range | 0.0847 | +| entropy_loss | -7.3 | +| explained_variance | -0.0266 | +| learning_rate | 9.66e-05 | +| loss | -0.0394 | +| n_updates | 10196 | +| policy_gradient_loss | -0.0256 | +| value_loss | 0.00013 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.255 | +| time/ | | +| fps | 1369 | +| iterations | 2551 | +| time_elapsed | 3815 | +| total_timesteps | 5224448 | +| train/ | | +| approx_kl | 0.025111105 | +| clip_fraction | 0.377 | +| clip_range | 0.0847 | +| entropy_loss | -7.24 | +| explained_variance | -0.148 | +| learning_rate | 9.66e-05 | +| loss | -0.0403 | +| n_updates | 10200 | +| policy_gradient_loss | -0.0232 | +| value_loss | 0.000171 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.253 | +| time/ | | +| fps | 1369 | +| iterations | 2552 | +| time_elapsed | 3816 | +| total_timesteps | 5226496 | +| train/ | | +| approx_kl | 0.021702806 | +| clip_fraction | 0.401 | +| clip_range | 0.0847 | +| entropy_loss | -7.34 | +| explained_variance | -0.0945 | +| learning_rate | 9.66e-05 | +| loss | -0.0355 | +| n_updates | 10204 | +| policy_gradient_loss | -0.0225 | +| value_loss | 0.000172 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.253 | +| time/ | | +| fps | 1369 | +| iterations | 2553 | +| time_elapsed | 3818 | +| total_timesteps | 5228544 | +| train/ | | +| approx_kl | 0.02357499 | +| clip_fraction | 0.403 | +| clip_range | 0.0847 | +| entropy_loss | -7.19 | +| explained_variance | -0.207 | +| learning_rate | 9.65e-05 | +| loss | -0.0333 | +| n_updates | 10208 | +| policy_gradient_loss | -0.0263 | +| value_loss | 0.000147 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.259 | +| time/ | | +| fps | 1369 | +| iterations | 2554 | +| time_elapsed | 3819 | +| total_timesteps | 5230592 | +| train/ | | +| approx_kl | 0.025368268 | +| clip_fraction | 0.4 | +| clip_range | 0.0846 | +| entropy_loss | -7.36 | +| explained_variance | -0.0949 | +| learning_rate | 9.65e-05 | +| loss | -0.047 | +| n_updates | 10212 | +| policy_gradient_loss | -0.028 | +| value_loss | 0.000217 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.264 | +| time/ | | +| fps | 1369 | +| iterations | 2555 | +| time_elapsed | 3820 | +| total_timesteps | 5232640 | +| train/ | | +| approx_kl | 0.024942761 | +| clip_fraction | 0.418 | +| clip_range | 0.0846 | +| entropy_loss | -7.25 | +| explained_variance | -0.0982 | +| learning_rate | 9.64e-05 | +| loss | -0.0377 | +| n_updates | 10216 | +| policy_gradient_loss | -0.0278 | +| value_loss | 9.37e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.268 | +| time/ | | +| fps | 1369 | +| iterations | 2556 | +| time_elapsed | 3822 | +| total_timesteps | 5234688 | +| train/ | | +| approx_kl | 0.026268963 | +| clip_fraction | 0.377 | +| clip_range | 0.0846 | +| entropy_loss | -7.19 | +| explained_variance | -0.0059 | +| learning_rate | 9.64e-05 | +| loss | -0.0388 | +| n_updates | 10220 | +| policy_gradient_loss | -0.0249 | +| value_loss | 0.000319 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.273 | +| time/ | | +| fps | 1369 | +| iterations | 2557 | +| time_elapsed | 3823 | +| total_timesteps | 5236736 | +| train/ | | +| approx_kl | 0.024006281 | +| clip_fraction | 0.382 | +| clip_range | 0.0846 | +| entropy_loss | -7.26 | +| explained_variance | -0.151 | +| learning_rate | 9.64e-05 | +| loss | -0.0371 | +| n_updates | 10224 | +| policy_gradient_loss | -0.0248 | +| value_loss | 0.000224 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.27 | +| time/ | | +| fps | 1369 | +| iterations | 2558 | +| time_elapsed | 3825 | +| total_timesteps | 5238784 | +| train/ | | +| approx_kl | 0.024256164 | +| clip_fraction | 0.382 | +| clip_range | 0.0845 | +| entropy_loss | -7.22 | +| explained_variance | -0.149 | +| learning_rate | 9.63e-05 | +| loss | -0.0409 | +| n_updates | 10228 | +| policy_gradient_loss | -0.0265 | +| value_loss | 0.000185 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.27 | +| time/ | | +| fps | 1369 | +| iterations | 2559 | +| time_elapsed | 3826 | +| total_timesteps | 5240832 | +| train/ | | +| approx_kl | 0.02467775 | +| clip_fraction | 0.387 | +| clip_range | 0.0845 | +| entropy_loss | -7.26 | +| explained_variance | -0.0666 | +| learning_rate | 9.63e-05 | +| loss | -0.0391 | +| n_updates | 10232 | +| policy_gradient_loss | -0.024 | +| value_loss | 0.00019 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.269 | +| time/ | | +| fps | 1369 | +| iterations | 2560 | +| time_elapsed | 3828 | +| total_timesteps | 5242880 | +| train/ | | +| approx_kl | 0.023801398 | +| clip_fraction | 0.414 | +| clip_range | 0.0845 | +| entropy_loss | -7.41 | +| explained_variance | -0.338 | +| learning_rate | 9.62e-05 | +| loss | -0.0384 | +| n_updates | 10236 | +| policy_gradient_loss | -0.0276 | +| value_loss | 0.000117 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.269 | +| time/ | | +| fps | 1369 | +| iterations | 2561 | +| time_elapsed | 3829 | +| total_timesteps | 5244928 | +| train/ | | +| approx_kl | 0.023916688 | +| clip_fraction | 0.379 | +| clip_range | 0.0845 | +| entropy_loss | -7.34 | +| explained_variance | -0.178 | +| learning_rate | 9.62e-05 | +| loss | -0.0338 | +| n_updates | 10240 | +| policy_gradient_loss | -0.0236 | +| value_loss | 0.000165 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.268 | +| time/ | | +| fps | 1369 | +| iterations | 2562 | +| time_elapsed | 3831 | +| total_timesteps | 5246976 | +| train/ | | +| approx_kl | 0.021457765 | +| clip_fraction | 0.373 | +| clip_range | 0.0844 | +| entropy_loss | -7.36 | +| explained_variance | -0.146 | +| learning_rate | 9.62e-05 | +| loss | -0.0409 | +| n_updates | 10244 | +| policy_gradient_loss | -0.0249 | +| value_loss | 0.000168 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.267 | +| time/ | | +| fps | 1369 | +| iterations | 2563 | +| time_elapsed | 3832 | +| total_timesteps | 5249024 | +| train/ | | +| approx_kl | 0.023246381 | +| clip_fraction | 0.4 | +| clip_range | 0.0844 | +| entropy_loss | -7.24 | +| explained_variance | -0.0759 | +| learning_rate | 9.61e-05 | +| loss | -0.0406 | +| n_updates | 10248 | +| policy_gradient_loss | -0.0255 | +| value_loss | 0.00014 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.265 | +| time/ | | +| fps | 1369 | +| iterations | 2564 | +| time_elapsed | 3833 | +| total_timesteps | 5251072 | +| train/ | | +| approx_kl | 0.023320526 | +| clip_fraction | 0.388 | +| clip_range | 0.0844 | +| entropy_loss | -7.39 | +| explained_variance | -0.0738 | +| learning_rate | 9.61e-05 | +| loss | -0.038 | +| n_updates | 10252 | +| policy_gradient_loss | -0.024 | +| value_loss | 0.000142 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.27 | +| time/ | | +| fps | 1369 | +| iterations | 2565 | +| time_elapsed | 3835 | +| total_timesteps | 5253120 | +| train/ | | +| approx_kl | 0.02269641 | +| clip_fraction | 0.404 | +| clip_range | 0.0844 | +| entropy_loss | -7.31 | +| explained_variance | -0.0637 | +| learning_rate | 9.6e-05 | +| loss | -0.0381 | +| n_updates | 10256 | +| policy_gradient_loss | -0.0257 | +| value_loss | 0.000146 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 1369 | +| iterations | 2566 | +| time_elapsed | 3836 | +| total_timesteps | 5255168 | +| train/ | | +| approx_kl | 0.02341811 | +| clip_fraction | 0.395 | +| clip_range | 0.0843 | +| entropy_loss | -7.16 | +| explained_variance | 0.0151 | +| learning_rate | 9.6e-05 | +| loss | -0.0188 | +| n_updates | 10260 | +| policy_gradient_loss | -0.022 | +| value_loss | 0.000223 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 1369 | +| iterations | 2567 | +| time_elapsed | 3838 | +| total_timesteps | 5257216 | +| train/ | | +| approx_kl | 0.024854235 | +| clip_fraction | 0.394 | +| clip_range | 0.0843 | +| entropy_loss | -6.98 | +| explained_variance | -0.319 | +| learning_rate | 9.59e-05 | +| loss | -0.0405 | +| n_updates | 10264 | +| policy_gradient_loss | -0.0235 | +| value_loss | 0.000162 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 1369 | +| iterations | 2568 | +| time_elapsed | 3839 | +| total_timesteps | 5259264 | +| train/ | | +| approx_kl | 0.024085015 | +| clip_fraction | 0.386 | +| clip_range | 0.0843 | +| entropy_loss | -7.34 | +| explained_variance | -0.0807 | +| learning_rate | 9.59e-05 | +| loss | -0.0376 | +| n_updates | 10268 | +| policy_gradient_loss | -0.0244 | +| value_loss | 0.00023 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.28 | +| time/ | | +| fps | 1369 | +| iterations | 2569 | +| time_elapsed | 3841 | +| total_timesteps | 5261312 | +| train/ | | +| approx_kl | 0.024099102 | +| clip_fraction | 0.412 | +| clip_range | 0.0843 | +| entropy_loss | -7.31 | +| explained_variance | -0.165 | +| learning_rate | 9.59e-05 | +| loss | -0.0492 | +| n_updates | 10272 | +| policy_gradient_loss | -0.0272 | +| value_loss | 0.000159 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.277 | +| time/ | | +| fps | 1369 | +| iterations | 2570 | +| time_elapsed | 3842 | +| total_timesteps | 5263360 | +| train/ | | +| approx_kl | 0.021835323 | +| clip_fraction | 0.375 | +| clip_range | 0.0842 | +| entropy_loss | -7.38 | +| explained_variance | -0.16 | +| learning_rate | 9.58e-05 | +| loss | -0.0382 | +| n_updates | 10276 | +| policy_gradient_loss | -0.025 | +| value_loss | 0.000169 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.277 | +| time/ | | +| fps | 1369 | +| iterations | 2571 | +| time_elapsed | 3843 | +| total_timesteps | 5265408 | +| train/ | | +| approx_kl | 0.02504669 | +| clip_fraction | 0.413 | +| clip_range | 0.0842 | +| entropy_loss | -7.31 | +| explained_variance | -0.263 | +| learning_rate | 9.58e-05 | +| loss | -0.0486 | +| n_updates | 10280 | +| policy_gradient_loss | -0.0276 | +| value_loss | 0.000106 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.277 | +| time/ | | +| fps | 1369 | +| iterations | 2572 | +| time_elapsed | 3845 | +| total_timesteps | 5267456 | +| train/ | | +| approx_kl | 0.021696713 | +| clip_fraction | 0.432 | +| clip_range | 0.0842 | +| entropy_loss | -7.24 | +| explained_variance | -0.172 | +| learning_rate | 9.57e-05 | +| loss | -0.0448 | +| n_updates | 10284 | +| policy_gradient_loss | -0.0295 | +| value_loss | 6.9e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.276 | +| time/ | | +| fps | 1369 | +| iterations | 2573 | +| time_elapsed | 3846 | +| total_timesteps | 5269504 | +| train/ | | +| approx_kl | 0.025669038 | +| clip_fraction | 0.385 | +| clip_range | 0.0842 | +| entropy_loss | -7.38 | +| explained_variance | -0.0607 | +| learning_rate | 9.57e-05 | +| loss | -0.0323 | +| n_updates | 10288 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000154 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.277 | +| time/ | | +| fps | 1369 | +| iterations | 2574 | +| time_elapsed | 3848 | +| total_timesteps | 5271552 | +| train/ | | +| approx_kl | 0.022874814 | +| clip_fraction | 0.37 | +| clip_range | 0.0841 | +| entropy_loss | -7.29 | +| explained_variance | -0.0525 | +| learning_rate | 9.57e-05 | +| loss | -0.0347 | +| n_updates | 10292 | +| policy_gradient_loss | -0.022 | +| value_loss | 0.000223 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 1369 | +| iterations | 2575 | +| time_elapsed | 3849 | +| total_timesteps | 5273600 | +| train/ | | +| approx_kl | 0.025668424 | +| clip_fraction | 0.39 | +| clip_range | 0.0841 | +| entropy_loss | -7.17 | +| explained_variance | -0.0655 | +| learning_rate | 9.56e-05 | +| loss | -0.0364 | +| n_updates | 10296 | +| policy_gradient_loss | -0.0257 | +| value_loss | 0.000109 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.281 | +| time/ | | +| fps | 1369 | +| iterations | 2576 | +| time_elapsed | 3850 | +| total_timesteps | 5275648 | +| train/ | | +| approx_kl | 0.020594144 | +| clip_fraction | 0.379 | +| clip_range | 0.0841 | +| entropy_loss | -7.34 | +| explained_variance | -0.0976 | +| learning_rate | 9.56e-05 | +| loss | -0.043 | +| n_updates | 10300 | +| policy_gradient_loss | -0.0243 | +| value_loss | 0.000168 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.277 | +| time/ | | +| fps | 1369 | +| iterations | 2577 | +| time_elapsed | 3852 | +| total_timesteps | 5277696 | +| train/ | | +| approx_kl | 0.019328307 | +| clip_fraction | 0.399 | +| clip_range | 0.0841 | +| entropy_loss | -7.17 | +| explained_variance | 0.00705 | +| learning_rate | 9.55e-05 | +| loss | -0.0418 | +| n_updates | 10304 | +| policy_gradient_loss | -0.0232 | +| value_loss | 0.000147 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.274 | +| time/ | | +| fps | 1369 | +| iterations | 2578 | +| time_elapsed | 3853 | +| total_timesteps | 5279744 | +| train/ | | +| approx_kl | 0.025261085 | +| clip_fraction | 0.409 | +| clip_range | 0.084 | +| entropy_loss | -7.2 | +| explained_variance | -0.0644 | +| learning_rate | 9.55e-05 | +| loss | -0.043 | +| n_updates | 10308 | +| policy_gradient_loss | -0.0256 | +| value_loss | 0.0002 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.267 | +| time/ | | +| fps | 1369 | +| iterations | 2579 | +| time_elapsed | 3855 | +| total_timesteps | 5281792 | +| train/ | | +| approx_kl | 0.02387163 | +| clip_fraction | 0.403 | +| clip_range | 0.084 | +| entropy_loss | -7.35 | +| explained_variance | -0.173 | +| learning_rate | 9.55e-05 | +| loss | -0.0408 | +| n_updates | 10312 | +| policy_gradient_loss | -0.0247 | +| value_loss | 0.000163 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.27 | +| time/ | | +| fps | 1369 | +| iterations | 2580 | +| time_elapsed | 3856 | +| total_timesteps | 5283840 | +| train/ | | +| approx_kl | 0.02208727 | +| clip_fraction | 0.372 | +| clip_range | 0.084 | +| entropy_loss | -7.27 | +| explained_variance | -0.0707 | +| learning_rate | 9.54e-05 | +| loss | -0.0435 | +| n_updates | 10316 | +| policy_gradient_loss | -0.0263 | +| value_loss | 0.000189 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.269 | +| time/ | | +| fps | 1369 | +| iterations | 2581 | +| time_elapsed | 3858 | +| total_timesteps | 5285888 | +| train/ | | +| approx_kl | 0.019491352 | +| clip_fraction | 0.383 | +| clip_range | 0.084 | +| entropy_loss | -7.31 | +| explained_variance | -0.0708 | +| learning_rate | 9.54e-05 | +| loss | -0.0401 | +| n_updates | 10320 | +| policy_gradient_loss | -0.024 | +| value_loss | 0.000272 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.269 | +| time/ | | +| fps | 1369 | +| iterations | 2582 | +| time_elapsed | 3859 | +| total_timesteps | 5287936 | +| train/ | | +| approx_kl | 0.024858521 | +| clip_fraction | 0.435 | +| clip_range | 0.0839 | +| entropy_loss | -7.28 | +| explained_variance | -0.264 | +| learning_rate | 9.53e-05 | +| loss | -0.0514 | +| n_updates | 10324 | +| policy_gradient_loss | -0.0297 | +| value_loss | 0.000129 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.271 | +| time/ | | +| fps | 1370 | +| iterations | 2583 | +| time_elapsed | 3861 | +| total_timesteps | 5289984 | +| train/ | | +| approx_kl | 0.021752745 | +| clip_fraction | 0.388 | +| clip_range | 0.0839 | +| entropy_loss | -7.47 | +| explained_variance | -0.2 | +| learning_rate | 9.53e-05 | +| loss | -0.0478 | +| n_updates | 10328 | +| policy_gradient_loss | -0.0261 | +| value_loss | 0.000153 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 1370 | +| iterations | 2584 | +| time_elapsed | 3862 | +| total_timesteps | 5292032 | +| train/ | | +| approx_kl | 0.02087545 | +| clip_fraction | 0.404 | +| clip_range | 0.0839 | +| entropy_loss | -7.3 | +| explained_variance | -0.166 | +| learning_rate | 9.53e-05 | +| loss | -0.034 | +| n_updates | 10332 | +| policy_gradient_loss | -0.0253 | +| value_loss | 0.000175 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.285 | +| time/ | | +| fps | 1370 | +| iterations | 2585 | +| time_elapsed | 3864 | +| total_timesteps | 5294080 | +| train/ | | +| approx_kl | 0.021246828 | +| clip_fraction | 0.394 | +| clip_range | 0.0838 | +| entropy_loss | -7.32 | +| explained_variance | 0.0284 | +| learning_rate | 9.52e-05 | +| loss | -0.0356 | +| n_updates | 10336 | +| policy_gradient_loss | -0.0229 | +| value_loss | 0.000245 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.283 | +| time/ | | +| fps | 1370 | +| iterations | 2586 | +| time_elapsed | 3865 | +| total_timesteps | 5296128 | +| train/ | | +| approx_kl | 0.022442427 | +| clip_fraction | 0.399 | +| clip_range | 0.0838 | +| entropy_loss | -7.24 | +| explained_variance | -0.105 | +| learning_rate | 9.52e-05 | +| loss | -0.0499 | +| n_updates | 10340 | +| policy_gradient_loss | -0.0285 | +| value_loss | 0.000161 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.285 | +| time/ | | +| fps | 1370 | +| iterations | 2587 | +| time_elapsed | 3867 | +| total_timesteps | 5298176 | +| train/ | | +| approx_kl | 0.021137584 | +| clip_fraction | 0.373 | +| clip_range | 0.0838 | +| entropy_loss | -7.42 | +| explained_variance | -0.135 | +| learning_rate | 9.51e-05 | +| loss | -0.0398 | +| n_updates | 10344 | +| policy_gradient_loss | -0.0259 | +| value_loss | 0.000159 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 1370 | +| iterations | 2588 | +| time_elapsed | 3868 | +| total_timesteps | 5300224 | +| train/ | | +| approx_kl | 0.025052074 | +| clip_fraction | 0.407 | +| clip_range | 0.0838 | +| entropy_loss | -7.32 | +| explained_variance | -0.107 | +| learning_rate | 9.51e-05 | +| loss | -0.0452 | +| n_updates | 10348 | +| policy_gradient_loss | -0.0289 | +| value_loss | 8.08e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.27 | +| time/ | | +| fps | 1370 | +| iterations | 2589 | +| time_elapsed | 3869 | +| total_timesteps | 5302272 | +| train/ | | +| approx_kl | 0.022478608 | +| clip_fraction | 0.384 | +| clip_range | 0.0837 | +| entropy_loss | -7.15 | +| explained_variance | -0.0101 | +| learning_rate | 9.51e-05 | +| loss | -0.0381 | +| n_updates | 10352 | +| policy_gradient_loss | -0.0231 | +| value_loss | 0.000121 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.274 | +| time/ | | +| fps | 1370 | +| iterations | 2590 | +| time_elapsed | 3871 | +| total_timesteps | 5304320 | +| train/ | | +| approx_kl | 0.023011662 | +| clip_fraction | 0.374 | +| clip_range | 0.0837 | +| entropy_loss | -7.22 | +| explained_variance | -0.0586 | +| learning_rate | 9.5e-05 | +| loss | -0.0388 | +| n_updates | 10356 | +| policy_gradient_loss | -0.0236 | +| value_loss | 0.000221 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.267 | +| time/ | | +| fps | 1370 | +| iterations | 2591 | +| time_elapsed | 3872 | +| total_timesteps | 5306368 | +| train/ | | +| approx_kl | 0.023859197 | +| clip_fraction | 0.367 | +| clip_range | 0.0837 | +| entropy_loss | -7.45 | +| explained_variance | -0.0263 | +| learning_rate | 9.5e-05 | +| loss | -0.0388 | +| n_updates | 10360 | +| policy_gradient_loss | -0.0238 | +| value_loss | 0.000312 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.267 | +| time/ | | +| fps | 1370 | +| iterations | 2592 | +| time_elapsed | 3874 | +| total_timesteps | 5308416 | +| train/ | | +| approx_kl | 0.024028033 | +| clip_fraction | 0.413 | +| clip_range | 0.0837 | +| entropy_loss | -7.42 | +| explained_variance | -0.464 | +| learning_rate | 9.49e-05 | +| loss | -0.0476 | +| n_updates | 10364 | +| policy_gradient_loss | -0.0287 | +| value_loss | 0.00014 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.265 | +| time/ | | +| fps | 1370 | +| iterations | 2593 | +| time_elapsed | 3875 | +| total_timesteps | 5310464 | +| train/ | | +| approx_kl | 0.022019979 | +| clip_fraction | 0.373 | +| clip_range | 0.0836 | +| entropy_loss | -7.26 | +| explained_variance | -0.0971 | +| learning_rate | 9.49e-05 | +| loss | -0.0434 | +| n_updates | 10368 | +| policy_gradient_loss | -0.0239 | +| value_loss | 0.00027 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.266 | +| time/ | | +| fps | 1370 | +| iterations | 2594 | +| time_elapsed | 3876 | +| total_timesteps | 5312512 | +| train/ | | +| approx_kl | 0.018638508 | +| clip_fraction | 0.4 | +| clip_range | 0.0836 | +| entropy_loss | -7.38 | +| explained_variance | -0.0234 | +| learning_rate | 9.49e-05 | +| loss | -0.0432 | +| n_updates | 10372 | +| policy_gradient_loss | -0.0263 | +| value_loss | 0.00013 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.264 | +| time/ | | +| fps | 1370 | +| iterations | 2595 | +| time_elapsed | 3878 | +| total_timesteps | 5314560 | +| train/ | | +| approx_kl | 0.022558678 | +| clip_fraction | 0.401 | +| clip_range | 0.0836 | +| entropy_loss | -7.35 | +| explained_variance | -0.172 | +| learning_rate | 9.48e-05 | +| loss | -0.0458 | +| n_updates | 10376 | +| policy_gradient_loss | -0.0266 | +| value_loss | 0.000146 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.263 | +| time/ | | +| fps | 1370 | +| iterations | 2596 | +| time_elapsed | 3879 | +| total_timesteps | 5316608 | +| train/ | | +| approx_kl | 0.023252435 | +| clip_fraction | 0.392 | +| clip_range | 0.0836 | +| entropy_loss | -7.37 | +| explained_variance | -0.027 | +| learning_rate | 9.48e-05 | +| loss | -0.0435 | +| n_updates | 10380 | +| policy_gradient_loss | -0.0257 | +| value_loss | 0.000203 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.263 | +| time/ | | +| fps | 1370 | +| iterations | 2597 | +| time_elapsed | 3881 | +| total_timesteps | 5318656 | +| train/ | | +| approx_kl | 0.018719856 | +| clip_fraction | 0.402 | +| clip_range | 0.0835 | +| entropy_loss | -7.42 | +| explained_variance | -0.394 | +| learning_rate | 9.47e-05 | +| loss | -0.0397 | +| n_updates | 10384 | +| policy_gradient_loss | -0.0266 | +| value_loss | 8.99e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.264 | +| time/ | | +| fps | 1370 | +| iterations | 2598 | +| time_elapsed | 3882 | +| total_timesteps | 5320704 | +| train/ | | +| approx_kl | 0.022486385 | +| clip_fraction | 0.373 | +| clip_range | 0.0835 | +| entropy_loss | -7.4 | +| explained_variance | -0.0506 | +| learning_rate | 9.47e-05 | +| loss | -0.0385 | +| n_updates | 10388 | +| policy_gradient_loss | -0.0237 | +| value_loss | 0.000137 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.265 | +| time/ | | +| fps | 1370 | +| iterations | 2599 | +| time_elapsed | 3884 | +| total_timesteps | 5322752 | +| train/ | | +| approx_kl | 0.023962673 | +| clip_fraction | 0.369 | +| clip_range | 0.0835 | +| entropy_loss | -7.29 | +| explained_variance | -0.135 | +| learning_rate | 9.47e-05 | +| loss | -0.03 | +| n_updates | 10392 | +| policy_gradient_loss | -0.0222 | +| value_loss | 0.00029 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.266 | +| time/ | | +| fps | 1370 | +| iterations | 2600 | +| time_elapsed | 3885 | +| total_timesteps | 5324800 | +| train/ | | +| approx_kl | 0.02406155 | +| clip_fraction | 0.411 | +| clip_range | 0.0835 | +| entropy_loss | -7.29 | +| explained_variance | -0.264 | +| learning_rate | 9.46e-05 | +| loss | -0.0461 | +| n_updates | 10396 | +| policy_gradient_loss | -0.0314 | +| value_loss | 6.67e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.264 | +| time/ | | +| fps | 1370 | +| iterations | 2601 | +| time_elapsed | 3886 | +| total_timesteps | 5326848 | +| train/ | | +| approx_kl | 0.022471977 | +| clip_fraction | 0.369 | +| clip_range | 0.0834 | +| entropy_loss | -7.35 | +| explained_variance | 0.00782 | +| learning_rate | 9.46e-05 | +| loss | -0.036 | +| n_updates | 10400 | +| policy_gradient_loss | -0.0228 | +| value_loss | 0.000199 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.264 | +| time/ | | +| fps | 1370 | +| iterations | 2602 | +| time_elapsed | 3888 | +| total_timesteps | 5328896 | +| train/ | | +| approx_kl | 0.0218172 | +| clip_fraction | 0.409 | +| clip_range | 0.0834 | +| entropy_loss | -7.38 | +| explained_variance | -0.277 | +| learning_rate | 9.45e-05 | +| loss | -0.0376 | +| n_updates | 10404 | +| policy_gradient_loss | -0.0276 | +| value_loss | 7.85e-05 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.264 | +| time/ | | +| fps | 1370 | +| iterations | 2603 | +| time_elapsed | 3889 | +| total_timesteps | 5330944 | +| train/ | | +| approx_kl | 0.025122965 | +| clip_fraction | 0.395 | +| clip_range | 0.0834 | +| entropy_loss | -7.44 | +| explained_variance | -0.0301 | +| learning_rate | 9.45e-05 | +| loss | -0.0357 | +| n_updates | 10408 | +| policy_gradient_loss | -0.0239 | +| value_loss | 0.000168 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.266 | +| time/ | | +| fps | 1370 | +| iterations | 2604 | +| time_elapsed | 3891 | +| total_timesteps | 5332992 | +| train/ | | +| approx_kl | 0.022596586 | +| clip_fraction | 0.392 | +| clip_range | 0.0834 | +| entropy_loss | -7.5 | +| explained_variance | -0.299 | +| learning_rate | 9.44e-05 | +| loss | -0.0422 | +| n_updates | 10412 | +| policy_gradient_loss | -0.0283 | +| value_loss | 0.000108 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.26 | +| time/ | | +| fps | 1370 | +| iterations | 2605 | +| time_elapsed | 3892 | +| total_timesteps | 5335040 | +| train/ | | +| approx_kl | 0.020752788 | +| clip_fraction | 0.394 | +| clip_range | 0.0833 | +| entropy_loss | -7.17 | +| explained_variance | -0.126 | +| learning_rate | 9.44e-05 | +| loss | -0.04 | +| n_updates | 10416 | +| policy_gradient_loss | -0.0256 | +| value_loss | 0.0001 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.258 | +| time/ | | +| fps | 1370 | +| iterations | 2606 | +| time_elapsed | 3894 | +| total_timesteps | 5337088 | +| train/ | | +| approx_kl | 0.022294402 | +| clip_fraction | 0.391 | +| clip_range | 0.0833 | +| entropy_loss | -7.1 | +| explained_variance | -0.0468 | +| learning_rate | 9.44e-05 | +| loss | -0.0353 | +| n_updates | 10420 | +| policy_gradient_loss | -0.0226 | +| value_loss | 0.000159 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.259 | +| time/ | | +| fps | 1370 | +| iterations | 2607 | +| time_elapsed | 3895 | +| total_timesteps | 5339136 | +| train/ | | +| approx_kl | 0.02343921 | +| clip_fraction | 0.392 | +| clip_range | 0.0833 | +| entropy_loss | -7.4 | +| explained_variance | -0.158 | +| learning_rate | 9.43e-05 | +| loss | -0.0346 | +| n_updates | 10424 | +| policy_gradient_loss | -0.0246 | +| value_loss | 0.000164 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.255 | +| time/ | | +| fps | 1370 | +| iterations | 2608 | +| time_elapsed | 3897 | +| total_timesteps | 5341184 | +| train/ | | +| approx_kl | 0.02376282 | +| clip_fraction | 0.396 | +| clip_range | 0.0833 | +| entropy_loss | -7.24 | +| explained_variance | -0.149 | +| learning_rate | 9.43e-05 | +| loss | -0.0431 | +| n_updates | 10428 | +| policy_gradient_loss | -0.0267 | +| value_loss | 0.00019 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.255 | +| time/ | | +| fps | 1370 | +| iterations | 2609 | +| time_elapsed | 3898 | +| total_timesteps | 5343232 | +| train/ | | +| approx_kl | 0.023103286 | +| clip_fraction | 0.381 | +| clip_range | 0.0832 | +| entropy_loss | -7.29 | +| explained_variance | -0.159 | +| learning_rate | 9.42e-05 | +| loss | -0.0381 | +| n_updates | 10432 | +| policy_gradient_loss | -0.0246 | +| value_loss | 0.000174 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.255 | +| time/ | | +| fps | 1370 | +| iterations | 2610 | +| time_elapsed | 3900 | +| total_timesteps | 5345280 | +| train/ | | +| approx_kl | 0.02495157 | +| clip_fraction | 0.39 | +| clip_range | 0.0832 | +| entropy_loss | -7.52 | +| explained_variance | -0.219 | +| learning_rate | 9.42e-05 | +| loss | -0.0459 | +| n_updates | 10436 | +| policy_gradient_loss | -0.0267 | +| value_loss | 0.000257 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.255 | +| time/ | | +| fps | 1370 | +| iterations | 2611 | +| time_elapsed | 3901 | +| total_timesteps | 5347328 | +| train/ | | +| approx_kl | 0.018942751 | +| clip_fraction | 0.364 | +| clip_range | 0.0832 | +| entropy_loss | -7.3 | +| explained_variance | -0.0741 | +| learning_rate | 9.42e-05 | +| loss | -0.0429 | +| n_updates | 10440 | +| policy_gradient_loss | -0.0224 | +| value_loss | 0.000353 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.257 | +| time/ | | +| fps | 1370 | +| iterations | 2612 | +| time_elapsed | 3902 | +| total_timesteps | 5349376 | +| train/ | | +| approx_kl | 0.023173086 | +| clip_fraction | 0.427 | +| clip_range | 0.0832 | +| entropy_loss | -7.33 | +| explained_variance | -0.425 | +| learning_rate | 9.41e-05 | +| loss | -0.0439 | +| n_updates | 10444 | +| policy_gradient_loss | -0.0279 | +| value_loss | 0.000102 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.259 | +| time/ | | +| fps | 1370 | +| iterations | 2613 | +| time_elapsed | 3904 | +| total_timesteps | 5351424 | +| train/ | | +| approx_kl | 0.021678554 | +| clip_fraction | 0.387 | +| clip_range | 0.0831 | +| entropy_loss | -7.34 | +| explained_variance | -0.0161 | +| learning_rate | 9.41e-05 | +| loss | -0.0315 | +| n_updates | 10448 | +| policy_gradient_loss | -0.0228 | +| value_loss | 0.000365 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.256 | +| time/ | | +| fps | 1370 | +| iterations | 2614 | +| time_elapsed | 3905 | +| total_timesteps | 5353472 | +| train/ | | +| approx_kl | 0.023347523 | +| clip_fraction | 0.399 | +| clip_range | 0.0831 | +| entropy_loss | -7.2 | +| explained_variance | -0.193 | +| learning_rate | 9.4e-05 | +| loss | -0.0472 | +| n_updates | 10452 | +| policy_gradient_loss | -0.0293 | +| value_loss | 0.000175 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.256 | +| time/ | | +| fps | 1370 | +| iterations | 2615 | +| time_elapsed | 3907 | +| total_timesteps | 5355520 | +| train/ | | +| approx_kl | 0.022424374 | +| clip_fraction | 0.383 | +| clip_range | 0.0831 | +| entropy_loss | -7.37 | +| explained_variance | -0.201 | +| learning_rate | 9.4e-05 | +| loss | -0.0497 | +| n_updates | 10456 | +| policy_gradient_loss | -0.0273 | +| value_loss | 0.000167 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.256 | +| time/ | | +| fps | 1370 | +| iterations | 2616 | +| time_elapsed | 3908 | +| total_timesteps | 5357568 | +| train/ | | +| approx_kl | 0.02012339 | +| clip_fraction | 0.388 | +| clip_range | 0.0831 | +| entropy_loss | -7.43 | +| explained_variance | -0.0479 | +| learning_rate | 9.4e-05 | +| loss | -0.0335 | +| n_updates | 10460 | +| policy_gradient_loss | -0.0245 | +| value_loss | 0.000125 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.251 | +| time/ | | +| fps | 1370 | +| iterations | 2617 | +| time_elapsed | 3910 | +| total_timesteps | 5359616 | +| train/ | | +| approx_kl | 0.022066468 | +| clip_fraction | 0.378 | +| clip_range | 0.083 | +| entropy_loss | -7.36 | +| explained_variance | -0.0713 | +| learning_rate | 9.39e-05 | +| loss | -0.038 | +| n_updates | 10464 | +| policy_gradient_loss | -0.0239 | +| value_loss | 0.000187 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.247 | +| time/ | | +| fps | 1370 | +| iterations | 2618 | +| time_elapsed | 3911 | +| total_timesteps | 5361664 | +| train/ | | +| approx_kl | 0.023024734 | +| clip_fraction | 0.393 | +| clip_range | 0.083 | +| entropy_loss | -7.46 | +| explained_variance | -0.267 | +| learning_rate | 9.39e-05 | +| loss | -0.0409 | +| n_updates | 10468 | +| policy_gradient_loss | -0.0274 | +| value_loss | 0.000108 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.244 | +| time/ | | +| fps | 1370 | +| iterations | 2619 | +| time_elapsed | 3912 | +| total_timesteps | 5363712 | +| train/ | | +| approx_kl | 0.022990242 | +| clip_fraction | 0.363 | +| clip_range | 0.083 | +| entropy_loss | -7.41 | +| explained_variance | -0.19 | +| learning_rate | 9.38e-05 | +| loss | -0.0404 | +| n_updates | 10472 | +| policy_gradient_loss | -0.023 | +| value_loss | 0.000223 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.248 | +| time/ | | +| fps | 1370 | +| iterations | 2620 | +| time_elapsed | 3914 | +| total_timesteps | 5365760 | +| train/ | | +| approx_kl | 0.02189507 | +| clip_fraction | 0.381 | +| clip_range | 0.083 | +| entropy_loss | -7.25 | +| explained_variance | -0.106 | +| learning_rate | 9.38e-05 | +| loss | -0.0371 | +| n_updates | 10476 | +| policy_gradient_loss | -0.0254 | +| value_loss | 0.000168 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.248 | +| time/ | | +| fps | 1370 | +| iterations | 2621 | +| time_elapsed | 3915 | +| total_timesteps | 5367808 | +| train/ | | +| approx_kl | 0.024960708 | +| clip_fraction | 0.375 | +| clip_range | 0.0829 | +| entropy_loss | -7.38 | +| explained_variance | -0.0606 | +| learning_rate | 9.38e-05 | +| loss | -0.0453 | +| n_updates | 10480 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000246 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.246 | +| time/ | | +| fps | 1370 | +| iterations | 2622 | +| time_elapsed | 3917 | +| total_timesteps | 5369856 | +| train/ | | +| approx_kl | 0.023444263 | +| clip_fraction | 0.393 | +| clip_range | 0.0829 | +| entropy_loss | -7.36 | +| explained_variance | -0.291 | +| learning_rate | 9.37e-05 | +| loss | -0.0445 | +| n_updates | 10484 | +| policy_gradient_loss | -0.0264 | +| value_loss | 0.00014 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.252 | +| time/ | | +| fps | 1370 | +| iterations | 2623 | +| time_elapsed | 3918 | +| total_timesteps | 5371904 | +| train/ | | +| approx_kl | 0.022753306 | +| clip_fraction | 0.387 | +| clip_range | 0.0829 | +| entropy_loss | -7.33 | +| explained_variance | -0.191 | +| learning_rate | 9.37e-05 | +| loss | -0.0452 | +| n_updates | 10488 | +| policy_gradient_loss | -0.0272 | +| value_loss | 0.000109 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.253 | +| time/ | | +| fps | 1370 | +| iterations | 2624 | +| time_elapsed | 3919 | +| total_timesteps | 5373952 | +| train/ | | +| approx_kl | 0.022321448 | +| clip_fraction | 0.377 | +| clip_range | 0.0829 | +| entropy_loss | -7.26 | +| explained_variance | -0.0436 | +| learning_rate | 9.36e-05 | +| loss | -0.0308 | +| n_updates | 10492 | +| policy_gradient_loss | -0.023 | +| value_loss | 0.000173 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.253 | +| time/ | | +| fps | 1370 | +| iterations | 2625 | +| time_elapsed | 3921 | +| total_timesteps | 5376000 | +| train/ | | +| approx_kl | 0.024501111 | +| clip_fraction | 0.395 | +| clip_range | 0.0828 | +| entropy_loss | -7.35 | +| explained_variance | -0.222 | +| learning_rate | 9.36e-05 | +| loss | -0.046 | +| n_updates | 10496 | +| policy_gradient_loss | -0.0265 | +| value_loss | 0.000115 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.253 | +| time/ | | +| fps | 1370 | +| iterations | 2626 | +| time_elapsed | 3922 | +| total_timesteps | 5378048 | +| train/ | | +| approx_kl | 0.025735606 | +| clip_fraction | 0.384 | +| clip_range | 0.0828 | +| entropy_loss | -7.5 | +| explained_variance | -0.0187 | +| learning_rate | 9.36e-05 | +| loss | -0.0371 | +| n_updates | 10500 | +| policy_gradient_loss | -0.0253 | +| value_loss | 0.000175 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.251 | +| time/ | | +| fps | 1370 | +| iterations | 2627 | +| time_elapsed | 3924 | +| total_timesteps | 5380096 | +| train/ | | +| approx_kl | 0.023168303 | +| clip_fraction | 0.415 | +| clip_range | 0.0828 | +| entropy_loss | -7.53 | +| explained_variance | -0.554 | +| learning_rate | 9.35e-05 | +| loss | -0.0491 | +| n_updates | 10504 | +| policy_gradient_loss | -0.0288 | +| value_loss | 5.79e-05 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.251 | +| time/ | | +| fps | 1371 | +| iterations | 2628 | +| time_elapsed | 3925 | +| total_timesteps | 5382144 | +| train/ | | +| approx_kl | 0.0224674 | +| clip_fraction | 0.374 | +| clip_range | 0.0827 | +| entropy_loss | -7.35 | +| explained_variance | 0.0217 | +| learning_rate | 9.35e-05 | +| loss | -0.0383 | +| n_updates | 10508 | +| policy_gradient_loss | -0.0235 | +| value_loss | 0.000232 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.251 | +| time/ | | +| fps | 1371 | +| iterations | 2629 | +| time_elapsed | 3927 | +| total_timesteps | 5384192 | +| train/ | | +| approx_kl | 0.022027206 | +| clip_fraction | 0.383 | +| clip_range | 0.0827 | +| entropy_loss | -7.36 | +| explained_variance | -0.0438 | +| learning_rate | 9.34e-05 | +| loss | -0.0431 | +| n_updates | 10512 | +| policy_gradient_loss | -0.025 | +| value_loss | 0.000205 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.25 | +| time/ | | +| fps | 1371 | +| iterations | 2630 | +| time_elapsed | 3928 | +| total_timesteps | 5386240 | +| train/ | | +| approx_kl | 0.021319268 | +| clip_fraction | 0.381 | +| clip_range | 0.0827 | +| entropy_loss | -7.49 | +| explained_variance | -0.0742 | +| learning_rate | 9.34e-05 | +| loss | -0.0388 | +| n_updates | 10516 | +| policy_gradient_loss | -0.0255 | +| value_loss | 0.000187 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.249 | +| time/ | | +| fps | 1371 | +| iterations | 2631 | +| time_elapsed | 3929 | +| total_timesteps | 5388288 | +| train/ | | +| approx_kl | 0.021001225 | +| clip_fraction | 0.375 | +| clip_range | 0.0827 | +| entropy_loss | -7.22 | +| explained_variance | 0.00919 | +| learning_rate | 9.34e-05 | +| loss | -0.034 | +| n_updates | 10520 | +| policy_gradient_loss | -0.0223 | +| value_loss | 0.000314 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.249 | +| time/ | | +| fps | 1371 | +| iterations | 2632 | +| time_elapsed | 3931 | +| total_timesteps | 5390336 | +| train/ | | +| approx_kl | 0.023225151 | +| clip_fraction | 0.426 | +| clip_range | 0.0826 | +| entropy_loss | -7.04 | +| explained_variance | -0.397 | +| learning_rate | 9.33e-05 | +| loss | -0.0488 | +| n_updates | 10524 | +| policy_gradient_loss | -0.0293 | +| value_loss | 0.000171 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.249 | +| time/ | | +| fps | 1371 | +| iterations | 2633 | +| time_elapsed | 3932 | +| total_timesteps | 5392384 | +| train/ | | +| approx_kl | 0.022061637 | +| clip_fraction | 0.415 | +| clip_range | 0.0826 | +| entropy_loss | -7.34 | +| explained_variance | -0.0326 | +| learning_rate | 9.33e-05 | +| loss | -0.0462 | +| n_updates | 10528 | +| policy_gradient_loss | -0.0278 | +| value_loss | 0.000112 | +----------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.254 | +| time/ | | +| fps | 1371 | +| iterations | 2634 | +| time_elapsed | 3934 | +| total_timesteps | 5394432 | +| train/ | | +| approx_kl | 0.022844 | +| clip_fraction | 0.405 | +| clip_range | 0.0826 | +| entropy_loss | -7.3 | +| explained_variance | 0.00229 | +| learning_rate | 9.32e-05 | +| loss | -0.0406 | +| n_updates | 10532 | +| policy_gradient_loss | -0.0252 | +| value_loss | 0.000183 | +-------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.259 | +| time/ | | +| fps | 1371 | +| iterations | 2635 | +| time_elapsed | 3935 | +| total_timesteps | 5396480 | +| train/ | | +| approx_kl | 0.020621292 | +| clip_fraction | 0.371 | +| clip_range | 0.0826 | +| entropy_loss | -7.34 | +| explained_variance | -0.0429 | +| learning_rate | 9.32e-05 | +| loss | -0.0387 | +| n_updates | 10536 | +| policy_gradient_loss | -0.0233 | +| value_loss | 0.000141 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.256 | +| time/ | | +| fps | 1371 | +| iterations | 2636 | +| time_elapsed | 3937 | +| total_timesteps | 5398528 | +| train/ | | +| approx_kl | 0.018965773 | +| clip_fraction | 0.383 | +| clip_range | 0.0825 | +| entropy_loss | -7.33 | +| explained_variance | -0.087 | +| learning_rate | 9.31e-05 | +| loss | -0.0382 | +| n_updates | 10540 | +| policy_gradient_loss | -0.0235 | +| value_loss | 0.000238 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.266 | +| time/ | | +| fps | 1371 | +| iterations | 2637 | +| time_elapsed | 3938 | +| total_timesteps | 5400576 | +| train/ | | +| approx_kl | 0.020956064 | +| clip_fraction | 0.401 | +| clip_range | 0.0825 | +| entropy_loss | -7.28 | +| explained_variance | -0.325 | +| learning_rate | 9.31e-05 | +| loss | -0.043 | +| n_updates | 10544 | +| policy_gradient_loss | -0.0278 | +| value_loss | 0.000101 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.268 | +| time/ | | +| fps | 1371 | +| iterations | 2638 | +| time_elapsed | 3940 | +| total_timesteps | 5402624 | +| train/ | | +| approx_kl | 0.0150999725 | +| clip_fraction | 0.355 | +| clip_range | 0.0825 | +| entropy_loss | -7.38 | +| explained_variance | 0.0397 | +| learning_rate | 9.31e-05 | +| loss | -0.0288 | +| n_updates | 10548 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000252 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.267 | +| time/ | | +| fps | 1371 | +| iterations | 2639 | +| time_elapsed | 3941 | +| total_timesteps | 5404672 | +| train/ | | +| approx_kl | 0.021643357 | +| clip_fraction | 0.396 | +| clip_range | 0.0825 | +| entropy_loss | -7.34 | +| explained_variance | 0.106 | +| learning_rate | 9.3e-05 | +| loss | -0.043 | +| n_updates | 10552 | +| policy_gradient_loss | -0.0244 | +| value_loss | 0.000175 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.268 | +| time/ | | +| fps | 1371 | +| iterations | 2640 | +| time_elapsed | 3942 | +| total_timesteps | 5406720 | +| train/ | | +| approx_kl | 0.01939123 | +| clip_fraction | 0.374 | +| clip_range | 0.0824 | +| entropy_loss | -7.43 | +| explained_variance | -0.108 | +| learning_rate | 9.3e-05 | +| loss | -0.0418 | +| n_updates | 10556 | +| policy_gradient_loss | -0.0248 | +| value_loss | 0.000344 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.27 | +| time/ | | +| fps | 1371 | +| iterations | 2641 | +| time_elapsed | 3944 | +| total_timesteps | 5408768 | +| train/ | | +| approx_kl | 0.018730242 | +| clip_fraction | 0.394 | +| clip_range | 0.0824 | +| entropy_loss | -7.27 | +| explained_variance | -0.227 | +| learning_rate | 9.29e-05 | +| loss | -0.0433 | +| n_updates | 10560 | +| policy_gradient_loss | -0.0276 | +| value_loss | 0.000167 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.265 | +| time/ | | +| fps | 1371 | +| iterations | 2642 | +| time_elapsed | 3945 | +| total_timesteps | 5410816 | +| train/ | | +| approx_kl | 0.01896019 | +| clip_fraction | 0.38 | +| clip_range | 0.0824 | +| entropy_loss | -7.39 | +| explained_variance | 0.00167 | +| learning_rate | 9.29e-05 | +| loss | -0.0392 | +| n_updates | 10564 | +| policy_gradient_loss | -0.0244 | +| value_loss | 0.000248 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.259 | +| time/ | | +| fps | 1371 | +| iterations | 2643 | +| time_elapsed | 3947 | +| total_timesteps | 5412864 | +| train/ | | +| approx_kl | 0.022341907 | +| clip_fraction | 0.378 | +| clip_range | 0.0824 | +| entropy_loss | -7.25 | +| explained_variance | -0.188 | +| learning_rate | 9.29e-05 | +| loss | -0.0397 | +| n_updates | 10568 | +| policy_gradient_loss | -0.0237 | +| value_loss | 0.000221 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.259 | +| time/ | | +| fps | 1371 | +| iterations | 2644 | +| time_elapsed | 3948 | +| total_timesteps | 5414912 | +| train/ | | +| approx_kl | 0.023431638 | +| clip_fraction | 0.382 | +| clip_range | 0.0823 | +| entropy_loss | -7.17 | +| explained_variance | -0.129 | +| learning_rate | 9.28e-05 | +| loss | -0.0384 | +| n_updates | 10572 | +| policy_gradient_loss | -0.0245 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.259 | +| time/ | | +| fps | 1371 | +| iterations | 2645 | +| time_elapsed | 3950 | +| total_timesteps | 5416960 | +| train/ | | +| approx_kl | 0.024125656 | +| clip_fraction | 0.411 | +| clip_range | 0.0823 | +| entropy_loss | -7.41 | +| explained_variance | -0.0594 | +| learning_rate | 9.28e-05 | +| loss | -0.0463 | +| n_updates | 10576 | +| policy_gradient_loss | -0.0277 | +| value_loss | 0.000231 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.259 | +| time/ | | +| fps | 1371 | +| iterations | 2646 | +| time_elapsed | 3951 | +| total_timesteps | 5419008 | +| train/ | | +| approx_kl | 0.021569047 | +| clip_fraction | 0.416 | +| clip_range | 0.0823 | +| entropy_loss | -7.42 | +| explained_variance | -0.343 | +| learning_rate | 9.27e-05 | +| loss | -0.047 | +| n_updates | 10580 | +| policy_gradient_loss | -0.0286 | +| value_loss | 0.000122 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.244 | +| time/ | | +| fps | 1371 | +| iterations | 2647 | +| time_elapsed | 3952 | +| total_timesteps | 5421056 | +| train/ | | +| approx_kl | 0.019296434 | +| clip_fraction | 0.38 | +| clip_range | 0.0823 | +| entropy_loss | -7.4 | +| explained_variance | -0.113 | +| learning_rate | 9.27e-05 | +| loss | -0.0365 | +| n_updates | 10584 | +| policy_gradient_loss | -0.0233 | +| value_loss | 0.000207 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.244 | +| time/ | | +| fps | 1371 | +| iterations | 2648 | +| time_elapsed | 3954 | +| total_timesteps | 5423104 | +| train/ | | +| approx_kl | 0.022976276 | +| clip_fraction | 0.395 | +| clip_range | 0.0822 | +| entropy_loss | -7.17 | +| explained_variance | -0.241 | +| learning_rate | 9.27e-05 | +| loss | -0.0416 | +| n_updates | 10588 | +| policy_gradient_loss | -0.0258 | +| value_loss | 0.000137 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.252 | +| time/ | | +| fps | 1371 | +| iterations | 2649 | +| time_elapsed | 3955 | +| total_timesteps | 5425152 | +| train/ | | +| approx_kl | 0.023914207 | +| clip_fraction | 0.396 | +| clip_range | 0.0822 | +| entropy_loss | -7.38 | +| explained_variance | -0.19 | +| learning_rate | 9.26e-05 | +| loss | -0.0417 | +| n_updates | 10592 | +| policy_gradient_loss | -0.026 | +| value_loss | 0.000158 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.252 | +| time/ | | +| fps | 1371 | +| iterations | 2650 | +| time_elapsed | 3957 | +| total_timesteps | 5427200 | +| train/ | | +| approx_kl | 0.017390076 | +| clip_fraction | 0.355 | +| clip_range | 0.0822 | +| entropy_loss | -7.29 | +| explained_variance | 0.00347 | +| learning_rate | 9.26e-05 | +| loss | -0.0279 | +| n_updates | 10596 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000227 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.253 | +| time/ | | +| fps | 1371 | +| iterations | 2651 | +| time_elapsed | 3958 | +| total_timesteps | 5429248 | +| train/ | | +| approx_kl | 0.021126576 | +| clip_fraction | 0.376 | +| clip_range | 0.0822 | +| entropy_loss | -7.33 | +| explained_variance | -0.197 | +| learning_rate | 9.25e-05 | +| loss | -0.0471 | +| n_updates | 10600 | +| policy_gradient_loss | -0.0257 | +| value_loss | 0.000144 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.25 | +| time/ | | +| fps | 1371 | +| iterations | 2652 | +| time_elapsed | 3959 | +| total_timesteps | 5431296 | +| train/ | | +| approx_kl | 0.022254542 | +| clip_fraction | 0.399 | +| clip_range | 0.0821 | +| entropy_loss | -6.95 | +| explained_variance | -0.062 | +| learning_rate | 9.25e-05 | +| loss | -0.0412 | +| n_updates | 10604 | +| policy_gradient_loss | -0.0278 | +| value_loss | 0.00014 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.251 | +| time/ | | +| fps | 1371 | +| iterations | 2653 | +| time_elapsed | 3961 | +| total_timesteps | 5433344 | +| train/ | | +| approx_kl | 0.021506779 | +| clip_fraction | 0.392 | +| clip_range | 0.0821 | +| entropy_loss | -7.38 | +| explained_variance | -0.219 | +| learning_rate | 9.25e-05 | +| loss | -0.0421 | +| n_updates | 10608 | +| policy_gradient_loss | -0.025 | +| value_loss | 0.000105 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.247 | +| time/ | | +| fps | 1371 | +| iterations | 2654 | +| time_elapsed | 3962 | +| total_timesteps | 5435392 | +| train/ | | +| approx_kl | 0.021342034 | +| clip_fraction | 0.353 | +| clip_range | 0.0821 | +| entropy_loss | -7.28 | +| explained_variance | -0.0514 | +| learning_rate | 9.24e-05 | +| loss | -0.0351 | +| n_updates | 10612 | +| policy_gradient_loss | -0.0239 | +| value_loss | 0.00019 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.247 | +| time/ | | +| fps | 1371 | +| iterations | 2655 | +| time_elapsed | 3964 | +| total_timesteps | 5437440 | +| train/ | | +| approx_kl | 0.02113313 | +| clip_fraction | 0.377 | +| clip_range | 0.0821 | +| entropy_loss | -7.34 | +| explained_variance | -0.159 | +| learning_rate | 9.24e-05 | +| loss | -0.0394 | +| n_updates | 10616 | +| policy_gradient_loss | -0.025 | +| value_loss | 0.000211 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.245 | +| time/ | | +| fps | 1371 | +| iterations | 2656 | +| time_elapsed | 3965 | +| total_timesteps | 5439488 | +| train/ | | +| approx_kl | 0.021978296 | +| clip_fraction | 0.391 | +| clip_range | 0.082 | +| entropy_loss | -7.47 | +| explained_variance | -0.0531 | +| learning_rate | 9.23e-05 | +| loss | -0.04 | +| n_updates | 10620 | +| policy_gradient_loss | -0.0244 | +| value_loss | 0.00023 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.243 | +| time/ | | +| fps | 1371 | +| iterations | 2657 | +| time_elapsed | 3967 | +| total_timesteps | 5441536 | +| train/ | | +| approx_kl | 0.019968461 | +| clip_fraction | 0.367 | +| clip_range | 0.082 | +| entropy_loss | -7.43 | +| explained_variance | -0.327 | +| learning_rate | 9.23e-05 | +| loss | -0.0363 | +| n_updates | 10624 | +| policy_gradient_loss | -0.0234 | +| value_loss | 0.000172 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.245 | +| time/ | | +| fps | 1371 | +| iterations | 2658 | +| time_elapsed | 3968 | +| total_timesteps | 5443584 | +| train/ | | +| approx_kl | 0.020916682 | +| clip_fraction | 0.389 | +| clip_range | 0.082 | +| entropy_loss | -7.41 | +| explained_variance | 0.00362 | +| learning_rate | 9.23e-05 | +| loss | -0.0459 | +| n_updates | 10628 | +| policy_gradient_loss | -0.0271 | +| value_loss | 0.000192 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.256 | +| time/ | | +| fps | 1371 | +| iterations | 2659 | +| time_elapsed | 3969 | +| total_timesteps | 5445632 | +| train/ | | +| approx_kl | 0.020442814 | +| clip_fraction | 0.4 | +| clip_range | 0.082 | +| entropy_loss | -7.34 | +| explained_variance | -0.276 | +| learning_rate | 9.22e-05 | +| loss | -0.0454 | +| n_updates | 10632 | +| policy_gradient_loss | -0.0256 | +| value_loss | 0.000161 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.245 | +| time/ | | +| fps | 1371 | +| iterations | 2660 | +| time_elapsed | 3971 | +| total_timesteps | 5447680 | +| train/ | | +| approx_kl | 0.019135576 | +| clip_fraction | 0.381 | +| clip_range | 0.0819 | +| entropy_loss | -7.34 | +| explained_variance | -0.091 | +| learning_rate | 9.22e-05 | +| loss | -0.0361 | +| n_updates | 10636 | +| policy_gradient_loss | -0.0224 | +| value_loss | 0.000225 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.245 | +| time/ | | +| fps | 1371 | +| iterations | 2661 | +| time_elapsed | 3972 | +| total_timesteps | 5449728 | +| train/ | | +| approx_kl | 0.022284897 | +| clip_fraction | 0.39 | +| clip_range | 0.0819 | +| entropy_loss | -7.29 | +| explained_variance | -0.188 | +| learning_rate | 9.21e-05 | +| loss | -0.0444 | +| n_updates | 10640 | +| policy_gradient_loss | -0.0282 | +| value_loss | 0.000153 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.241 | +| time/ | | +| fps | 1371 | +| iterations | 2662 | +| time_elapsed | 3974 | +| total_timesteps | 5451776 | +| train/ | | +| approx_kl | 0.023062691 | +| clip_fraction | 0.416 | +| clip_range | 0.0819 | +| entropy_loss | -7.42 | +| explained_variance | -0.44 | +| learning_rate | 9.21e-05 | +| loss | -0.0439 | +| n_updates | 10644 | +| policy_gradient_loss | -0.0302 | +| value_loss | 6.52e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.241 | +| time/ | | +| fps | 1371 | +| iterations | 2663 | +| time_elapsed | 3975 | +| total_timesteps | 5453824 | +| train/ | | +| approx_kl | 0.023387067 | +| clip_fraction | 0.391 | +| clip_range | 0.0819 | +| entropy_loss | -7.38 | +| explained_variance | -0.0375 | +| learning_rate | 9.21e-05 | +| loss | -0.0393 | +| n_updates | 10648 | +| policy_gradient_loss | -0.0248 | +| value_loss | 0.000192 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.24 | +| time/ | | +| fps | 1371 | +| iterations | 2664 | +| time_elapsed | 3977 | +| total_timesteps | 5455872 | +| train/ | | +| approx_kl | 0.021814771 | +| clip_fraction | 0.39 | +| clip_range | 0.0818 | +| entropy_loss | -7.45 | +| explained_variance | 0.038 | +| learning_rate | 9.2e-05 | +| loss | -0.0394 | +| n_updates | 10652 | +| policy_gradient_loss | -0.0257 | +| value_loss | 8.31e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.239 | +| time/ | | +| fps | 1371 | +| iterations | 2665 | +| time_elapsed | 3978 | +| total_timesteps | 5457920 | +| train/ | | +| approx_kl | 0.019583678 | +| clip_fraction | 0.36 | +| clip_range | 0.0818 | +| entropy_loss | -7.42 | +| explained_variance | -0.0887 | +| learning_rate | 9.2e-05 | +| loss | -0.0415 | +| n_updates | 10656 | +| policy_gradient_loss | -0.0244 | +| value_loss | 0.000146 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.239 | +| time/ | | +| fps | 1371 | +| iterations | 2666 | +| time_elapsed | 3979 | +| total_timesteps | 5459968 | +| train/ | | +| approx_kl | 0.019044043 | +| clip_fraction | 0.371 | +| clip_range | 0.0818 | +| entropy_loss | -7.38 | +| explained_variance | 0.0378 | +| learning_rate | 9.19e-05 | +| loss | -0.0388 | +| n_updates | 10660 | +| policy_gradient_loss | -0.0226 | +| value_loss | 0.000131 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.244 | +| time/ | | +| fps | 1371 | +| iterations | 2667 | +| time_elapsed | 3981 | +| total_timesteps | 5462016 | +| train/ | | +| approx_kl | 0.02054439 | +| clip_fraction | 0.414 | +| clip_range | 0.0818 | +| entropy_loss | -7.44 | +| explained_variance | -0.436 | +| learning_rate | 9.19e-05 | +| loss | -0.0434 | +| n_updates | 10664 | +| policy_gradient_loss | -0.0286 | +| value_loss | 7.59e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.252 | +| time/ | | +| fps | 1371 | +| iterations | 2668 | +| time_elapsed | 3982 | +| total_timesteps | 5464064 | +| train/ | | +| approx_kl | 0.020808168 | +| clip_fraction | 0.372 | +| clip_range | 0.0817 | +| entropy_loss | -7.38 | +| explained_variance | -0.096 | +| learning_rate | 9.19e-05 | +| loss | -0.0371 | +| n_updates | 10668 | +| policy_gradient_loss | -0.0238 | +| value_loss | 0.000211 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.255 | +| time/ | | +| fps | 1371 | +| iterations | 2669 | +| time_elapsed | 3984 | +| total_timesteps | 5466112 | +| train/ | | +| approx_kl | 0.021591669 | +| clip_fraction | 0.379 | +| clip_range | 0.0817 | +| entropy_loss | -7.48 | +| explained_variance | -0.0649 | +| learning_rate | 9.18e-05 | +| loss | -0.0432 | +| n_updates | 10672 | +| policy_gradient_loss | -0.0247 | +| value_loss | 0.000156 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.258 | +| time/ | | +| fps | 1372 | +| iterations | 2670 | +| time_elapsed | 3985 | +| total_timesteps | 5468160 | +| train/ | | +| approx_kl | 0.019639842 | +| clip_fraction | 0.364 | +| clip_range | 0.0817 | +| entropy_loss | -7.2 | +| explained_variance | -0.122 | +| learning_rate | 9.18e-05 | +| loss | -0.0418 | +| n_updates | 10676 | +| policy_gradient_loss | -0.0223 | +| value_loss | 0.000294 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.257 | +| time/ | | +| fps | 1372 | +| iterations | 2671 | +| time_elapsed | 3986 | +| total_timesteps | 5470208 | +| train/ | | +| approx_kl | 0.020009536 | +| clip_fraction | 0.372 | +| clip_range | 0.0816 | +| entropy_loss | -7.29 | +| explained_variance | -0.0319 | +| learning_rate | 9.17e-05 | +| loss | -0.0441 | +| n_updates | 10680 | +| policy_gradient_loss | -0.0261 | +| value_loss | 0.000255 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.252 | +| time/ | | +| fps | 1372 | +| iterations | 2672 | +| time_elapsed | 3988 | +| total_timesteps | 5472256 | +| train/ | | +| approx_kl | 0.020746887 | +| clip_fraction | 0.404 | +| clip_range | 0.0816 | +| entropy_loss | -7.39 | +| explained_variance | -0.508 | +| learning_rate | 9.17e-05 | +| loss | -0.0508 | +| n_updates | 10684 | +| policy_gradient_loss | -0.0298 | +| value_loss | 9.48e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.257 | +| time/ | | +| fps | 1372 | +| iterations | 2673 | +| time_elapsed | 3989 | +| total_timesteps | 5474304 | +| train/ | | +| approx_kl | 0.01995808 | +| clip_fraction | 0.373 | +| clip_range | 0.0816 | +| entropy_loss | -7.23 | +| explained_variance | 0.00648 | +| learning_rate | 9.16e-05 | +| loss | -0.0371 | +| n_updates | 10688 | +| policy_gradient_loss | -0.024 | +| value_loss | 0.000243 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.257 | +| time/ | | +| fps | 1372 | +| iterations | 2674 | +| time_elapsed | 3991 | +| total_timesteps | 5476352 | +| train/ | | +| approx_kl | 0.019722149 | +| clip_fraction | 0.411 | +| clip_range | 0.0816 | +| entropy_loss | -7.4 | +| explained_variance | -0.328 | +| learning_rate | 9.16e-05 | +| loss | -0.0463 | +| n_updates | 10692 | +| policy_gradient_loss | -0.0277 | +| value_loss | 8.19e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.254 | +| time/ | | +| fps | 1372 | +| iterations | 2675 | +| time_elapsed | 3992 | +| total_timesteps | 5478400 | +| train/ | | +| approx_kl | 0.020742998 | +| clip_fraction | 0.369 | +| clip_range | 0.0815 | +| entropy_loss | -7.58 | +| explained_variance | -0.0869 | +| learning_rate | 9.16e-05 | +| loss | -0.0416 | +| n_updates | 10696 | +| policy_gradient_loss | -0.0238 | +| value_loss | 0.000113 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.256 | +| time/ | | +| fps | 1372 | +| iterations | 2676 | +| time_elapsed | 3993 | +| total_timesteps | 5480448 | +| train/ | | +| approx_kl | 0.016564947 | +| clip_fraction | 0.358 | +| clip_range | 0.0815 | +| entropy_loss | -7.46 | +| explained_variance | -0.0763 | +| learning_rate | 9.15e-05 | +| loss | -0.0382 | +| n_updates | 10700 | +| policy_gradient_loss | -0.0225 | +| value_loss | 0.000313 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.256 | +| time/ | | +| fps | 1372 | +| iterations | 2677 | +| time_elapsed | 3995 | +| total_timesteps | 5482496 | +| train/ | | +| approx_kl | 0.018783368 | +| clip_fraction | 0.365 | +| clip_range | 0.0815 | +| entropy_loss | -7.26 | +| explained_variance | -0.0312 | +| learning_rate | 9.15e-05 | +| loss | -0.0393 | +| n_updates | 10704 | +| policy_gradient_loss | -0.0251 | +| value_loss | 0.000188 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.26 | +| time/ | | +| fps | 1372 | +| iterations | 2678 | +| time_elapsed | 3996 | +| total_timesteps | 5484544 | +| train/ | | +| approx_kl | 0.021625206 | +| clip_fraction | 0.377 | +| clip_range | 0.0815 | +| entropy_loss | -7.29 | +| explained_variance | -0.295 | +| learning_rate | 9.14e-05 | +| loss | -0.0423 | +| n_updates | 10708 | +| policy_gradient_loss | -0.0254 | +| value_loss | 0.000177 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.26 | +| time/ | | +| fps | 1372 | +| iterations | 2679 | +| time_elapsed | 3998 | +| total_timesteps | 5486592 | +| train/ | | +| approx_kl | 0.018949421 | +| clip_fraction | 0.364 | +| clip_range | 0.0814 | +| entropy_loss | -7.34 | +| explained_variance | -0.0927 | +| learning_rate | 9.14e-05 | +| loss | -0.0359 | +| n_updates | 10712 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000292 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.26 | +| time/ | | +| fps | 1372 | +| iterations | 2680 | +| time_elapsed | 3999 | +| total_timesteps | 5488640 | +| train/ | | +| approx_kl | 0.021681976 | +| clip_fraction | 0.409 | +| clip_range | 0.0814 | +| entropy_loss | -7.43 | +| explained_variance | -0.159 | +| learning_rate | 9.14e-05 | +| loss | -0.0436 | +| n_updates | 10716 | +| policy_gradient_loss | -0.0284 | +| value_loss | 0.000169 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.256 | +| time/ | | +| fps | 1372 | +| iterations | 2681 | +| time_elapsed | 4000 | +| total_timesteps | 5490688 | +| train/ | | +| approx_kl | 0.022658164 | +| clip_fraction | 0.371 | +| clip_range | 0.0814 | +| entropy_loss | -7.51 | +| explained_variance | -0.0282 | +| learning_rate | 9.13e-05 | +| loss | -0.0421 | +| n_updates | 10720 | +| policy_gradient_loss | -0.0257 | +| value_loss | 0.000196 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.261 | +| time/ | | +| fps | 1372 | +| iterations | 2682 | +| time_elapsed | 4002 | +| total_timesteps | 5492736 | +| train/ | | +| approx_kl | 0.019894456 | +| clip_fraction | 0.382 | +| clip_range | 0.0814 | +| entropy_loss | -7.38 | +| explained_variance | -0.134 | +| learning_rate | 9.13e-05 | +| loss | -0.0391 | +| n_updates | 10724 | +| policy_gradient_loss | -0.0259 | +| value_loss | 0.000132 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.253 | +| time/ | | +| fps | 1372 | +| iterations | 2683 | +| time_elapsed | 4003 | +| total_timesteps | 5494784 | +| train/ | | +| approx_kl | 0.021232318 | +| clip_fraction | 0.377 | +| clip_range | 0.0813 | +| entropy_loss | -7.35 | +| explained_variance | -0.227 | +| learning_rate | 9.12e-05 | +| loss | -0.0373 | +| n_updates | 10728 | +| policy_gradient_loss | -0.0246 | +| value_loss | 0.00018 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.259 | +| time/ | | +| fps | 1372 | +| iterations | 2684 | +| time_elapsed | 4005 | +| total_timesteps | 5496832 | +| train/ | | +| approx_kl | 0.02126373 | +| clip_fraction | 0.384 | +| clip_range | 0.0813 | +| entropy_loss | -7.38 | +| explained_variance | -0.208 | +| learning_rate | 9.12e-05 | +| loss | -0.0373 | +| n_updates | 10732 | +| policy_gradient_loss | -0.026 | +| value_loss | 0.00016 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.259 | +| time/ | | +| fps | 1372 | +| iterations | 2685 | +| time_elapsed | 4006 | +| total_timesteps | 5498880 | +| train/ | | +| approx_kl | 0.019395476 | +| clip_fraction | 0.357 | +| clip_range | 0.0813 | +| entropy_loss | -7.39 | +| explained_variance | -0.0542 | +| learning_rate | 9.12e-05 | +| loss | -0.039 | +| n_updates | 10736 | +| policy_gradient_loss | -0.0237 | +| value_loss | 0.000176 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.257 | +| time/ | | +| fps | 1372 | +| iterations | 2686 | +| time_elapsed | 4008 | +| total_timesteps | 5500928 | +| train/ | | +| approx_kl | 0.01974922 | +| clip_fraction | 0.371 | +| clip_range | 0.0813 | +| entropy_loss | -7.33 | +| explained_variance | -0.077 | +| learning_rate | 9.11e-05 | +| loss | -0.0381 | +| n_updates | 10740 | +| policy_gradient_loss | -0.0231 | +| value_loss | 0.000187 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.257 | +| time/ | | +| fps | 1372 | +| iterations | 2687 | +| time_elapsed | 4009 | +| total_timesteps | 5502976 | +| train/ | | +| approx_kl | 0.017952237 | +| clip_fraction | 0.39 | +| clip_range | 0.0812 | +| entropy_loss | -7.44 | +| explained_variance | -0.0263 | +| learning_rate | 9.11e-05 | +| loss | -0.0397 | +| n_updates | 10744 | +| policy_gradient_loss | -0.0266 | +| value_loss | 0.000193 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.263 | +| time/ | | +| fps | 1372 | +| iterations | 2688 | +| time_elapsed | 4011 | +| total_timesteps | 5505024 | +| train/ | | +| approx_kl | 0.018512677 | +| clip_fraction | 0.388 | +| clip_range | 0.0812 | +| entropy_loss | -7.38 | +| explained_variance | -0.0125 | +| learning_rate | 9.1e-05 | +| loss | -0.0375 | +| n_updates | 10748 | +| policy_gradient_loss | -0.0256 | +| value_loss | 0.000167 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.265 | +| time/ | | +| fps | 1372 | +| iterations | 2689 | +| time_elapsed | 4012 | +| total_timesteps | 5507072 | +| train/ | | +| approx_kl | 0.018803475 | +| clip_fraction | 0.38 | +| clip_range | 0.0812 | +| entropy_loss | -7.31 | +| explained_variance | 0.0378 | +| learning_rate | 9.1e-05 | +| loss | -0.0496 | +| n_updates | 10752 | +| policy_gradient_loss | -0.0257 | +| value_loss | 0.000141 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.262 | +| time/ | | +| fps | 1372 | +| iterations | 2690 | +| time_elapsed | 4013 | +| total_timesteps | 5509120 | +| train/ | | +| approx_kl | 0.018717978 | +| clip_fraction | 0.365 | +| clip_range | 0.0812 | +| entropy_loss | -7.31 | +| explained_variance | -0.0413 | +| learning_rate | 9.1e-05 | +| loss | -0.038 | +| n_updates | 10756 | +| policy_gradient_loss | -0.0234 | +| value_loss | 0.000246 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.261 | +| time/ | | +| fps | 1372 | +| iterations | 2691 | +| time_elapsed | 4015 | +| total_timesteps | 5511168 | +| train/ | | +| approx_kl | 0.01959246 | +| clip_fraction | 0.37 | +| clip_range | 0.0811 | +| entropy_loss | -7.21 | +| explained_variance | -0.13 | +| learning_rate | 9.09e-05 | +| loss | -0.0331 | +| n_updates | 10760 | +| policy_gradient_loss | -0.0248 | +| value_loss | 0.000212 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.26 | +| time/ | | +| fps | 1372 | +| iterations | 2692 | +| time_elapsed | 4016 | +| total_timesteps | 5513216 | +| train/ | | +| approx_kl | 0.02213477 | +| clip_fraction | 0.409 | +| clip_range | 0.0811 | +| entropy_loss | -7.3 | +| explained_variance | -0.149 | +| learning_rate | 9.09e-05 | +| loss | -0.0481 | +| n_updates | 10764 | +| policy_gradient_loss | -0.0292 | +| value_loss | 0.000109 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.263 | +| time/ | | +| fps | 1372 | +| iterations | 2693 | +| time_elapsed | 4018 | +| total_timesteps | 5515264 | +| train/ | | +| approx_kl | 0.01989359 | +| clip_fraction | 0.372 | +| clip_range | 0.0811 | +| entropy_loss | -7.41 | +| explained_variance | -0.189 | +| learning_rate | 9.08e-05 | +| loss | -0.0347 | +| n_updates | 10768 | +| policy_gradient_loss | -0.0232 | +| value_loss | 0.000181 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.263 | +| time/ | | +| fps | 1372 | +| iterations | 2694 | +| time_elapsed | 4019 | +| total_timesteps | 5517312 | +| train/ | | +| approx_kl | 0.018835269 | +| clip_fraction | 0.344 | +| clip_range | 0.0811 | +| entropy_loss | -7.39 | +| explained_variance | -0.0739 | +| learning_rate | 9.08e-05 | +| loss | -0.0395 | +| n_updates | 10772 | +| policy_gradient_loss | -0.0228 | +| value_loss | 0.000246 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.258 | +| time/ | | +| fps | 1372 | +| iterations | 2695 | +| time_elapsed | 4020 | +| total_timesteps | 5519360 | +| train/ | | +| approx_kl | 0.020426003 | +| clip_fraction | 0.361 | +| clip_range | 0.081 | +| entropy_loss | -7.5 | +| explained_variance | -0.0332 | +| learning_rate | 9.08e-05 | +| loss | -0.0353 | +| n_updates | 10776 | +| policy_gradient_loss | -0.0238 | +| value_loss | 0.000271 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.258 | +| time/ | | +| fps | 1372 | +| iterations | 2696 | +| time_elapsed | 4022 | +| total_timesteps | 5521408 | +| train/ | | +| approx_kl | 0.018910684 | +| clip_fraction | 0.351 | +| clip_range | 0.081 | +| entropy_loss | -7.23 | +| explained_variance | 0.0108 | +| learning_rate | 9.07e-05 | +| loss | -0.0292 | +| n_updates | 10780 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000492 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.258 | +| time/ | | +| fps | 1372 | +| iterations | 2697 | +| time_elapsed | 4023 | +| total_timesteps | 5523456 | +| train/ | | +| approx_kl | 0.020233862 | +| clip_fraction | 0.412 | +| clip_range | 0.081 | +| entropy_loss | -7.32 | +| explained_variance | -0.326 | +| learning_rate | 9.07e-05 | +| loss | -0.0491 | +| n_updates | 10784 | +| policy_gradient_loss | -0.0289 | +| value_loss | 0.000201 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.26 | +| time/ | | +| fps | 1372 | +| iterations | 2698 | +| time_elapsed | 4025 | +| total_timesteps | 5525504 | +| train/ | | +| approx_kl | 0.017176054 | +| clip_fraction | 0.396 | +| clip_range | 0.081 | +| entropy_loss | -7.5 | +| explained_variance | -0.165 | +| learning_rate | 9.06e-05 | +| loss | -0.0461 | +| n_updates | 10788 | +| policy_gradient_loss | -0.0274 | +| value_loss | 0.000186 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.256 | +| time/ | | +| fps | 1372 | +| iterations | 2699 | +| time_elapsed | 4026 | +| total_timesteps | 5527552 | +| train/ | | +| approx_kl | 0.018401314 | +| clip_fraction | 0.38 | +| clip_range | 0.0809 | +| entropy_loss | -7.44 | +| explained_variance | -0.157 | +| learning_rate | 9.06e-05 | +| loss | -0.0405 | +| n_updates | 10792 | +| policy_gradient_loss | -0.0258 | +| value_loss | 0.000187 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.257 | +| time/ | | +| fps | 1372 | +| iterations | 2700 | +| time_elapsed | 4028 | +| total_timesteps | 5529600 | +| train/ | | +| approx_kl | 0.015872754 | +| clip_fraction | 0.358 | +| clip_range | 0.0809 | +| entropy_loss | -7.16 | +| explained_variance | -0.0842 | +| learning_rate | 9.06e-05 | +| loss | -0.0359 | +| n_updates | 10796 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000362 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.257 | +| time/ | | +| fps | 1372 | +| iterations | 2701 | +| time_elapsed | 4029 | +| total_timesteps | 5531648 | +| train/ | | +| approx_kl | 0.020363005 | +| clip_fraction | 0.399 | +| clip_range | 0.0809 | +| entropy_loss | -7.35 | +| explained_variance | -0.051 | +| learning_rate | 9.05e-05 | +| loss | -0.0359 | +| n_updates | 10800 | +| policy_gradient_loss | -0.0252 | +| value_loss | 0.000197 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.26 | +| time/ | | +| fps | 1372 | +| iterations | 2702 | +| time_elapsed | 4030 | +| total_timesteps | 5533696 | +| train/ | | +| approx_kl | 0.019676369 | +| clip_fraction | 0.408 | +| clip_range | 0.0809 | +| entropy_loss | -7.39 | +| explained_variance | -0.653 | +| learning_rate | 9.05e-05 | +| loss | -0.0438 | +| n_updates | 10804 | +| policy_gradient_loss | -0.0285 | +| value_loss | 0.000113 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.253 | +| time/ | | +| fps | 1372 | +| iterations | 2703 | +| time_elapsed | 4032 | +| total_timesteps | 5535744 | +| train/ | | +| approx_kl | 0.020253312 | +| clip_fraction | 0.392 | +| clip_range | 0.0808 | +| entropy_loss | -7.31 | +| explained_variance | -0.132 | +| learning_rate | 9.04e-05 | +| loss | -0.0411 | +| n_updates | 10808 | +| policy_gradient_loss | -0.0242 | +| value_loss | 0.000173 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.25 | +| time/ | | +| fps | 1372 | +| iterations | 2704 | +| time_elapsed | 4033 | +| total_timesteps | 5537792 | +| train/ | | +| approx_kl | 0.019959144 | +| clip_fraction | 0.394 | +| clip_range | 0.0808 | +| entropy_loss | -7.34 | +| explained_variance | -0.174 | +| learning_rate | 9.04e-05 | +| loss | -0.041 | +| n_updates | 10812 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000212 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.256 | +| time/ | | +| fps | 1372 | +| iterations | 2705 | +| time_elapsed | 4035 | +| total_timesteps | 5539840 | +| train/ | | +| approx_kl | 0.02127287 | +| clip_fraction | 0.378 | +| clip_range | 0.0808 | +| entropy_loss | -7.29 | +| explained_variance | -0.2 | +| learning_rate | 9.04e-05 | +| loss | -0.0352 | +| n_updates | 10816 | +| policy_gradient_loss | -0.0241 | +| value_loss | 0.000127 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.253 | +| time/ | | +| fps | 1372 | +| iterations | 2706 | +| time_elapsed | 4036 | +| total_timesteps | 5541888 | +| train/ | | +| approx_kl | 0.01987246 | +| clip_fraction | 0.38 | +| clip_range | 0.0808 | +| entropy_loss | -7.28 | +| explained_variance | -0.084 | +| learning_rate | 9.03e-05 | +| loss | -0.0347 | +| n_updates | 10820 | +| policy_gradient_loss | -0.023 | +| value_loss | 0.000184 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.253 | +| time/ | | +| fps | 1372 | +| iterations | 2707 | +| time_elapsed | 4037 | +| total_timesteps | 5543936 | +| train/ | | +| approx_kl | 0.01755644 | +| clip_fraction | 0.354 | +| clip_range | 0.0807 | +| entropy_loss | -7.3 | +| explained_variance | 0.0278 | +| learning_rate | 9.03e-05 | +| loss | -0.0408 | +| n_updates | 10824 | +| policy_gradient_loss | -0.0239 | +| value_loss | 0.000199 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.257 | +| time/ | | +| fps | 1372 | +| iterations | 2708 | +| time_elapsed | 4039 | +| total_timesteps | 5545984 | +| train/ | | +| approx_kl | 0.019217921 | +| clip_fraction | 0.382 | +| clip_range | 0.0807 | +| entropy_loss | -7.47 | +| explained_variance | -0.317 | +| learning_rate | 9.02e-05 | +| loss | -0.0413 | +| n_updates | 10828 | +| policy_gradient_loss | -0.0277 | +| value_loss | 0.00015 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.257 | +| time/ | | +| fps | 1372 | +| iterations | 2709 | +| time_elapsed | 4040 | +| total_timesteps | 5548032 | +| train/ | | +| approx_kl | 0.019976884 | +| clip_fraction | 0.371 | +| clip_range | 0.0807 | +| entropy_loss | -7.44 | +| explained_variance | -0.216 | +| learning_rate | 9.02e-05 | +| loss | -0.043 | +| n_updates | 10832 | +| policy_gradient_loss | -0.0255 | +| value_loss | 0.000115 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.262 | +| time/ | | +| fps | 1372 | +| iterations | 2710 | +| time_elapsed | 4042 | +| total_timesteps | 5550080 | +| train/ | | +| approx_kl | 0.019037522 | +| clip_fraction | 0.362 | +| clip_range | 0.0806 | +| entropy_loss | -7.47 | +| explained_variance | -0.111 | +| learning_rate | 9.01e-05 | +| loss | -0.0344 | +| n_updates | 10836 | +| policy_gradient_loss | -0.024 | +| value_loss | 0.000239 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.262 | +| time/ | | +| fps | 1373 | +| iterations | 2711 | +| time_elapsed | 4043 | +| total_timesteps | 5552128 | +| train/ | | +| approx_kl | 0.019031264 | +| clip_fraction | 0.403 | +| clip_range | 0.0806 | +| entropy_loss | -7.43 | +| explained_variance | -0.158 | +| learning_rate | 9.01e-05 | +| loss | -0.0267 | +| n_updates | 10840 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000249 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.266 | +| time/ | | +| fps | 1372 | +| iterations | 2712 | +| time_elapsed | 4045 | +| total_timesteps | 5554176 | +| train/ | | +| approx_kl | 0.01907467 | +| clip_fraction | 0.365 | +| clip_range | 0.0806 | +| entropy_loss | -7.41 | +| explained_variance | -0.129 | +| learning_rate | 9.01e-05 | +| loss | -0.0437 | +| n_updates | 10844 | +| policy_gradient_loss | -0.0248 | +| value_loss | 0.000171 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.264 | +| time/ | | +| fps | 1373 | +| iterations | 2713 | +| time_elapsed | 4046 | +| total_timesteps | 5556224 | +| train/ | | +| approx_kl | 0.01661043 | +| clip_fraction | 0.353 | +| clip_range | 0.0806 | +| entropy_loss | -7.54 | +| explained_variance | -0.214 | +| learning_rate | 9e-05 | +| loss | -0.0373 | +| n_updates | 10848 | +| policy_gradient_loss | -0.0237 | +| value_loss | 0.000129 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.27 | +| time/ | | +| fps | 1373 | +| iterations | 2714 | +| time_elapsed | 4048 | +| total_timesteps | 5558272 | +| train/ | | +| approx_kl | 0.016197897 | +| clip_fraction | 0.343 | +| clip_range | 0.0805 | +| entropy_loss | -7.27 | +| explained_variance | -0.116 | +| learning_rate | 9e-05 | +| loss | -0.0419 | +| n_updates | 10852 | +| policy_gradient_loss | -0.0231 | +| value_loss | 0.000131 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 1373 | +| iterations | 2715 | +| time_elapsed | 4049 | +| total_timesteps | 5560320 | +| train/ | | +| approx_kl | 0.01677639 | +| clip_fraction | 0.343 | +| clip_range | 0.0805 | +| entropy_loss | -7.21 | +| explained_variance | -0.136 | +| learning_rate | 8.99e-05 | +| loss | -0.0301 | +| n_updates | 10856 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000253 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 1373 | +| iterations | 2716 | +| time_elapsed | 4050 | +| total_timesteps | 5562368 | +| train/ | | +| approx_kl | 0.020883866 | +| clip_fraction | 0.376 | +| clip_range | 0.0805 | +| entropy_loss | -7.24 | +| explained_variance | -0.111 | +| learning_rate | 8.99e-05 | +| loss | -0.0387 | +| n_updates | 10860 | +| policy_gradient_loss | -0.0236 | +| value_loss | 0.000198 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.287 | +| time/ | | +| fps | 1373 | +| iterations | 2717 | +| time_elapsed | 4052 | +| total_timesteps | 5564416 | +| train/ | | +| approx_kl | 0.020151647 | +| clip_fraction | 0.395 | +| clip_range | 0.0805 | +| entropy_loss | -7.5 | +| explained_variance | -0.196 | +| learning_rate | 8.99e-05 | +| loss | -0.035 | +| n_updates | 10864 | +| policy_gradient_loss | -0.0238 | +| value_loss | 0.000119 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.29 | +| time/ | | +| fps | 1373 | +| iterations | 2718 | +| time_elapsed | 4053 | +| total_timesteps | 5566464 | +| train/ | | +| approx_kl | 0.019556738 | +| clip_fraction | 0.368 | +| clip_range | 0.0804 | +| entropy_loss | -7.22 | +| explained_variance | -0.0305 | +| learning_rate | 8.98e-05 | +| loss | -0.0383 | +| n_updates | 10868 | +| policy_gradient_loss | -0.0232 | +| value_loss | 0.00024 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.288 | +| time/ | | +| fps | 1373 | +| iterations | 2719 | +| time_elapsed | 4055 | +| total_timesteps | 5568512 | +| train/ | | +| approx_kl | 0.02215858 | +| clip_fraction | 0.369 | +| clip_range | 0.0804 | +| entropy_loss | -7.44 | +| explained_variance | -0.241 | +| learning_rate | 8.98e-05 | +| loss | -0.0444 | +| n_updates | 10872 | +| policy_gradient_loss | -0.0244 | +| value_loss | 0.000237 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.288 | +| time/ | | +| fps | 1373 | +| iterations | 2720 | +| time_elapsed | 4056 | +| total_timesteps | 5570560 | +| train/ | | +| approx_kl | 0.017393917 | +| clip_fraction | 0.381 | +| clip_range | 0.0804 | +| entropy_loss | -7.4 | +| explained_variance | -0.0713 | +| learning_rate | 8.97e-05 | +| loss | -0.0403 | +| n_updates | 10876 | +| policy_gradient_loss | -0.0254 | +| value_loss | 0.000167 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.288 | +| time/ | | +| fps | 1373 | +| iterations | 2721 | +| time_elapsed | 4058 | +| total_timesteps | 5572608 | +| train/ | | +| approx_kl | 0.017128171 | +| clip_fraction | 0.385 | +| clip_range | 0.0804 | +| entropy_loss | -7.48 | +| explained_variance | -0.0482 | +| learning_rate | 8.97e-05 | +| loss | -0.0378 | +| n_updates | 10880 | +| policy_gradient_loss | -0.0219 | +| value_loss | 0.000215 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.286 | +| time/ | | +| fps | 1373 | +| iterations | 2722 | +| time_elapsed | 4059 | +| total_timesteps | 5574656 | +| train/ | | +| approx_kl | 0.019949004 | +| clip_fraction | 0.35 | +| clip_range | 0.0803 | +| entropy_loss | -7.61 | +| explained_variance | -0.00985 | +| learning_rate | 8.97e-05 | +| loss | -0.0418 | +| n_updates | 10884 | +| policy_gradient_loss | -0.0247 | +| value_loss | 0.00032 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.283 | +| time/ | | +| fps | 1373 | +| iterations | 2723 | +| time_elapsed | 4060 | +| total_timesteps | 5576704 | +| train/ | | +| approx_kl | 0.019043155 | +| clip_fraction | 0.372 | +| clip_range | 0.0803 | +| entropy_loss | -7.43 | +| explained_variance | -0.103 | +| learning_rate | 8.96e-05 | +| loss | -0.0399 | +| n_updates | 10888 | +| policy_gradient_loss | -0.0235 | +| value_loss | 0.000187 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.295 | +| time/ | | +| fps | 1373 | +| iterations | 2724 | +| time_elapsed | 4062 | +| total_timesteps | 5578752 | +| train/ | | +| approx_kl | 0.019817652 | +| clip_fraction | 0.372 | +| clip_range | 0.0803 | +| entropy_loss | -7.37 | +| explained_variance | -0.108 | +| learning_rate | 8.96e-05 | +| loss | -0.0413 | +| n_updates | 10892 | +| policy_gradient_loss | -0.0251 | +| value_loss | 0.000209 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.298 | +| time/ | | +| fps | 1373 | +| iterations | 2725 | +| time_elapsed | 4063 | +| total_timesteps | 5580800 | +| train/ | | +| approx_kl | 0.019489467 | +| clip_fraction | 0.373 | +| clip_range | 0.0803 | +| entropy_loss | -7.23 | +| explained_variance | -0.0276 | +| learning_rate | 8.95e-05 | +| loss | -0.0327 | +| n_updates | 10896 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000227 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.304 | +| time/ | | +| fps | 1373 | +| iterations | 2726 | +| time_elapsed | 4065 | +| total_timesteps | 5582848 | +| train/ | | +| approx_kl | 0.02035312 | +| clip_fraction | 0.387 | +| clip_range | 0.0802 | +| entropy_loss | -7.38 | +| explained_variance | -0.0195 | +| learning_rate | 8.95e-05 | +| loss | -0.0394 | +| n_updates | 10900 | +| policy_gradient_loss | -0.0235 | +| value_loss | 0.00027 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1373 | +| iterations | 2727 | +| time_elapsed | 4066 | +| total_timesteps | 5584896 | +| train/ | | +| approx_kl | 0.020096697 | +| clip_fraction | 0.372 | +| clip_range | 0.0802 | +| entropy_loss | -7.33 | +| explained_variance | -0.142 | +| learning_rate | 8.95e-05 | +| loss | -0.0407 | +| n_updates | 10904 | +| policy_gradient_loss | -0.0249 | +| value_loss | 0.000234 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1373 | +| iterations | 2728 | +| time_elapsed | 4068 | +| total_timesteps | 5586944 | +| train/ | | +| approx_kl | 0.020633753 | +| clip_fraction | 0.377 | +| clip_range | 0.0802 | +| entropy_loss | -7.28 | +| explained_variance | -0.0108 | +| learning_rate | 8.94e-05 | +| loss | -0.0411 | +| n_updates | 10908 | +| policy_gradient_loss | -0.024 | +| value_loss | 0.000321 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1373 | +| iterations | 2729 | +| time_elapsed | 4069 | +| total_timesteps | 5588992 | +| train/ | | +| approx_kl | 0.020174297 | +| clip_fraction | 0.399 | +| clip_range | 0.0802 | +| entropy_loss | -7.46 | +| explained_variance | -0.21 | +| learning_rate | 8.94e-05 | +| loss | -0.044 | +| n_updates | 10912 | +| policy_gradient_loss | -0.0262 | +| value_loss | 0.000153 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1373 | +| iterations | 2730 | +| time_elapsed | 4070 | +| total_timesteps | 5591040 | +| train/ | | +| approx_kl | 0.021791387 | +| clip_fraction | 0.365 | +| clip_range | 0.0801 | +| entropy_loss | -7.43 | +| explained_variance | -0.0696 | +| learning_rate | 8.93e-05 | +| loss | -0.037 | +| n_updates | 10916 | +| policy_gradient_loss | -0.0237 | +| value_loss | 0.000253 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 1373 | +| iterations | 2731 | +| time_elapsed | 4072 | +| total_timesteps | 5593088 | +| train/ | | +| approx_kl | 0.020817827 | +| clip_fraction | 0.392 | +| clip_range | 0.0801 | +| entropy_loss | -7.32 | +| explained_variance | -0.366 | +| learning_rate | 8.93e-05 | +| loss | -0.0404 | +| n_updates | 10920 | +| policy_gradient_loss | -0.0265 | +| value_loss | 0.000165 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1373 | +| iterations | 2732 | +| time_elapsed | 4073 | +| total_timesteps | 5595136 | +| train/ | | +| approx_kl | 0.01666001 | +| clip_fraction | 0.35 | +| clip_range | 0.0801 | +| entropy_loss | -7.33 | +| explained_variance | -0.0204 | +| learning_rate | 8.93e-05 | +| loss | -0.0292 | +| n_updates | 10924 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000298 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 1373 | +| iterations | 2733 | +| time_elapsed | 4075 | +| total_timesteps | 5597184 | +| train/ | | +| approx_kl | 0.01729034 | +| clip_fraction | 0.364 | +| clip_range | 0.0801 | +| entropy_loss | -7.4 | +| explained_variance | -0.157 | +| learning_rate | 8.92e-05 | +| loss | -0.0331 | +| n_updates | 10928 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000229 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 1373 | +| iterations | 2734 | +| time_elapsed | 4076 | +| total_timesteps | 5599232 | +| train/ | | +| approx_kl | 0.016202793 | +| clip_fraction | 0.38 | +| clip_range | 0.08 | +| entropy_loss | -7.4 | +| explained_variance | -0.105 | +| learning_rate | 8.92e-05 | +| loss | -0.0366 | +| n_updates | 10932 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000258 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.302 | +| time/ | | +| fps | 1373 | +| iterations | 2735 | +| time_elapsed | 4078 | +| total_timesteps | 5601280 | +| train/ | | +| approx_kl | 0.01970077 | +| clip_fraction | 0.381 | +| clip_range | 0.08 | +| entropy_loss | -7.23 | +| explained_variance | -0.247 | +| learning_rate | 8.91e-05 | +| loss | -0.0464 | +| n_updates | 10936 | +| policy_gradient_loss | -0.0242 | +| value_loss | 0.000165 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.302 | +| time/ | | +| fps | 1373 | +| iterations | 2736 | +| time_elapsed | 4079 | +| total_timesteps | 5603328 | +| train/ | | +| approx_kl | 0.018031333 | +| clip_fraction | 0.371 | +| clip_range | 0.08 | +| entropy_loss | -7.44 | +| explained_variance | -0.104 | +| learning_rate | 8.91e-05 | +| loss | -0.0441 | +| n_updates | 10940 | +| policy_gradient_loss | -0.0221 | +| value_loss | 0.000145 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.302 | +| time/ | | +| fps | 1373 | +| iterations | 2737 | +| time_elapsed | 4081 | +| total_timesteps | 5605376 | +| train/ | | +| approx_kl | 0.016707048 | +| clip_fraction | 0.365 | +| clip_range | 0.08 | +| entropy_loss | -7.51 | +| explained_variance | -0.189 | +| learning_rate | 8.91e-05 | +| loss | -0.0367 | +| n_updates | 10944 | +| policy_gradient_loss | -0.0241 | +| value_loss | 0.000159 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.302 | +| time/ | | +| fps | 1373 | +| iterations | 2738 | +| time_elapsed | 4082 | +| total_timesteps | 5607424 | +| train/ | | +| approx_kl | 0.020023882 | +| clip_fraction | 0.356 | +| clip_range | 0.0799 | +| entropy_loss | -7.45 | +| explained_variance | -0.0787 | +| learning_rate | 8.9e-05 | +| loss | -0.0384 | +| n_updates | 10948 | +| policy_gradient_loss | -0.0244 | +| value_loss | 0.000255 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 1373 | +| iterations | 2739 | +| time_elapsed | 4083 | +| total_timesteps | 5609472 | +| train/ | | +| approx_kl | 0.018291632 | +| clip_fraction | 0.353 | +| clip_range | 0.0799 | +| entropy_loss | -7.44 | +| explained_variance | -0.0986 | +| learning_rate | 8.9e-05 | +| loss | -0.0407 | +| n_updates | 10952 | +| policy_gradient_loss | -0.0242 | +| value_loss | 0.000158 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 1373 | +| iterations | 2740 | +| time_elapsed | 4085 | +| total_timesteps | 5611520 | +| train/ | | +| approx_kl | 0.019533264 | +| clip_fraction | 0.369 | +| clip_range | 0.0799 | +| entropy_loss | -7.37 | +| explained_variance | -0.0332 | +| learning_rate | 8.89e-05 | +| loss | -0.0401 | +| n_updates | 10956 | +| policy_gradient_loss | -0.0233 | +| value_loss | 0.000152 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.295 | +| time/ | | +| fps | 1373 | +| iterations | 2741 | +| time_elapsed | 4086 | +| total_timesteps | 5613568 | +| train/ | | +| approx_kl | 0.015768602 | +| clip_fraction | 0.348 | +| clip_range | 0.0799 | +| entropy_loss | -7.48 | +| explained_variance | -0.0602 | +| learning_rate | 8.89e-05 | +| loss | -0.0314 | +| n_updates | 10960 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000275 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.297 | +| time/ | | +| fps | 1373 | +| iterations | 2742 | +| time_elapsed | 4088 | +| total_timesteps | 5615616 | +| train/ | | +| approx_kl | 0.016409215 | +| clip_fraction | 0.362 | +| clip_range | 0.0798 | +| entropy_loss | -7.34 | +| explained_variance | 0.00449 | +| learning_rate | 8.89e-05 | +| loss | -0.0361 | +| n_updates | 10964 | +| policy_gradient_loss | -0.0224 | +| value_loss | 0.000248 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 1373 | +| iterations | 2743 | +| time_elapsed | 4089 | +| total_timesteps | 5617664 | +| train/ | | +| approx_kl | 0.015756851 | +| clip_fraction | 0.355 | +| clip_range | 0.0798 | +| entropy_loss | -7.4 | +| explained_variance | -0.0854 | +| learning_rate | 8.88e-05 | +| loss | -0.0402 | +| n_updates | 10968 | +| policy_gradient_loss | -0.0236 | +| value_loss | 0.000239 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 1373 | +| iterations | 2744 | +| time_elapsed | 4091 | +| total_timesteps | 5619712 | +| train/ | | +| approx_kl | 0.017678116 | +| clip_fraction | 0.368 | +| clip_range | 0.0798 | +| entropy_loss | -7.4 | +| explained_variance | -0.108 | +| learning_rate | 8.88e-05 | +| loss | -0.0394 | +| n_updates | 10972 | +| policy_gradient_loss | -0.0256 | +| value_loss | 0.000187 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 1373 | +| iterations | 2745 | +| time_elapsed | 4092 | +| total_timesteps | 5621760 | +| train/ | | +| approx_kl | 0.020595085 | +| clip_fraction | 0.387 | +| clip_range | 0.0798 | +| entropy_loss | -7.57 | +| explained_variance | -0.379 | +| learning_rate | 8.87e-05 | +| loss | -0.045 | +| n_updates | 10976 | +| policy_gradient_loss | -0.0288 | +| value_loss | 9.74e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.302 | +| time/ | | +| fps | 1373 | +| iterations | 2746 | +| time_elapsed | 4094 | +| total_timesteps | 5623808 | +| train/ | | +| approx_kl | 0.02003227 | +| clip_fraction | 0.365 | +| clip_range | 0.0797 | +| entropy_loss | -7.59 | +| explained_variance | -0.0804 | +| learning_rate | 8.87e-05 | +| loss | -0.0347 | +| n_updates | 10980 | +| policy_gradient_loss | -0.0233 | +| value_loss | 0.000198 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 1373 | +| iterations | 2747 | +| time_elapsed | 4095 | +| total_timesteps | 5625856 | +| train/ | | +| approx_kl | 0.017344156 | +| clip_fraction | 0.346 | +| clip_range | 0.0797 | +| entropy_loss | -7.45 | +| explained_variance | 0.00879 | +| learning_rate | 8.86e-05 | +| loss | -0.0289 | +| n_updates | 10984 | +| policy_gradient_loss | -0.0224 | +| value_loss | 0.000121 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 1373 | +| iterations | 2748 | +| time_elapsed | 4096 | +| total_timesteps | 5627904 | +| train/ | | +| approx_kl | 0.016990405 | +| clip_fraction | 0.362 | +| clip_range | 0.0797 | +| entropy_loss | -7.35 | +| explained_variance | 0.0578 | +| learning_rate | 8.86e-05 | +| loss | -0.0358 | +| n_updates | 10988 | +| policy_gradient_loss | -0.0248 | +| value_loss | 7.64e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.302 | +| time/ | | +| fps | 1373 | +| iterations | 2749 | +| time_elapsed | 4098 | +| total_timesteps | 5629952 | +| train/ | | +| approx_kl | 0.019275082 | +| clip_fraction | 0.366 | +| clip_range | 0.0797 | +| entropy_loss | -7.37 | +| explained_variance | -0.157 | +| learning_rate | 8.86e-05 | +| loss | -0.0343 | +| n_updates | 10992 | +| policy_gradient_loss | -0.0237 | +| value_loss | 0.000201 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 1373 | +| iterations | 2750 | +| time_elapsed | 4100 | +| total_timesteps | 5632000 | +| train/ | | +| approx_kl | 0.016519682 | +| clip_fraction | 0.338 | +| clip_range | 0.0796 | +| entropy_loss | -7.39 | +| explained_variance | -0.0506 | +| learning_rate | 8.85e-05 | +| loss | -0.0396 | +| n_updates | 10996 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000189 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 1373 | +| iterations | 2751 | +| time_elapsed | 4101 | +| total_timesteps | 5634048 | +| train/ | | +| approx_kl | 0.018898077 | +| clip_fraction | 0.362 | +| clip_range | 0.0796 | +| entropy_loss | -7.54 | +| explained_variance | 0.0433 | +| learning_rate | 8.85e-05 | +| loss | -0.0353 | +| n_updates | 11000 | +| policy_gradient_loss | -0.0229 | +| value_loss | 0.000236 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.298 | +| time/ | | +| fps | 1373 | +| iterations | 2752 | +| time_elapsed | 4103 | +| total_timesteps | 5636096 | +| train/ | | +| approx_kl | 0.016783182 | +| clip_fraction | 0.333 | +| clip_range | 0.0796 | +| entropy_loss | -7.41 | +| explained_variance | -0.239 | +| learning_rate | 8.84e-05 | +| loss | -0.036 | +| n_updates | 11004 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000257 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.295 | +| time/ | | +| fps | 1373 | +| iterations | 2753 | +| time_elapsed | 4104 | +| total_timesteps | 5638144 | +| train/ | | +| approx_kl | 0.018583383 | +| clip_fraction | 0.362 | +| clip_range | 0.0795 | +| entropy_loss | -7.51 | +| explained_variance | -0.168 | +| learning_rate | 8.84e-05 | +| loss | -0.0378 | +| n_updates | 11008 | +| policy_gradient_loss | -0.0232 | +| value_loss | 0.000233 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.295 | +| time/ | | +| fps | 1373 | +| iterations | 2754 | +| time_elapsed | 4106 | +| total_timesteps | 5640192 | +| train/ | | +| approx_kl | 0.016771901 | +| clip_fraction | 0.358 | +| clip_range | 0.0795 | +| entropy_loss | -7.52 | +| explained_variance | -0.112 | +| learning_rate | 8.84e-05 | +| loss | -0.0369 | +| n_updates | 11012 | +| policy_gradient_loss | -0.0238 | +| value_loss | 0.000209 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.295 | +| time/ | | +| fps | 1373 | +| iterations | 2755 | +| time_elapsed | 4107 | +| total_timesteps | 5642240 | +| train/ | | +| approx_kl | 0.018612562 | +| clip_fraction | 0.36 | +| clip_range | 0.0795 | +| entropy_loss | -7.4 | +| explained_variance | -0.194 | +| learning_rate | 8.83e-05 | +| loss | -0.0412 | +| n_updates | 11016 | +| policy_gradient_loss | -0.0254 | +| value_loss | 0.000101 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 1373 | +| iterations | 2756 | +| time_elapsed | 4108 | +| total_timesteps | 5644288 | +| train/ | | +| approx_kl | 0.016290892 | +| clip_fraction | 0.35 | +| clip_range | 0.0795 | +| entropy_loss | -7.57 | +| explained_variance | -0.144 | +| learning_rate | 8.83e-05 | +| loss | -0.0408 | +| n_updates | 11020 | +| policy_gradient_loss | -0.023 | +| value_loss | 0.000166 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 1373 | +| iterations | 2757 | +| time_elapsed | 4110 | +| total_timesteps | 5646336 | +| train/ | | +| approx_kl | 0.015496486 | +| clip_fraction | 0.363 | +| clip_range | 0.0794 | +| entropy_loss | -7.28 | +| explained_variance | -0.0114 | +| learning_rate | 8.82e-05 | +| loss | -0.0363 | +| n_updates | 11024 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000174 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.304 | +| time/ | | +| fps | 1373 | +| iterations | 2758 | +| time_elapsed | 4111 | +| total_timesteps | 5648384 | +| train/ | | +| approx_kl | 0.01651306 | +| clip_fraction | 0.341 | +| clip_range | 0.0794 | +| entropy_loss | -7.41 | +| explained_variance | -0.0129 | +| learning_rate | 8.82e-05 | +| loss | -0.0323 | +| n_updates | 11028 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000147 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.3 | +| time/ | | +| fps | 1373 | +| iterations | 2759 | +| time_elapsed | 4113 | +| total_timesteps | 5650432 | +| train/ | | +| approx_kl | 0.015586311 | +| clip_fraction | 0.336 | +| clip_range | 0.0794 | +| entropy_loss | -7.36 | +| explained_variance | -0.023 | +| learning_rate | 8.82e-05 | +| loss | -0.0382 | +| n_updates | 11032 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000276 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.297 | +| time/ | | +| fps | 1373 | +| iterations | 2760 | +| time_elapsed | 4114 | +| total_timesteps | 5652480 | +| train/ | | +| approx_kl | 0.018837444 | +| clip_fraction | 0.35 | +| clip_range | 0.0794 | +| entropy_loss | -7.44 | +| explained_variance | -0.12 | +| learning_rate | 8.81e-05 | +| loss | -0.0407 | +| n_updates | 11036 | +| policy_gradient_loss | -0.0231 | +| value_loss | 0.000257 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 1373 | +| iterations | 2761 | +| time_elapsed | 4116 | +| total_timesteps | 5654528 | +| train/ | | +| approx_kl | 0.015729293 | +| clip_fraction | 0.363 | +| clip_range | 0.0793 | +| entropy_loss | -7.41 | +| explained_variance | -0.0243 | +| learning_rate | 8.81e-05 | +| loss | -0.0408 | +| n_updates | 11040 | +| policy_gradient_loss | -0.0224 | +| value_loss | 0.000217 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.298 | +| time/ | | +| fps | 1373 | +| iterations | 2762 | +| time_elapsed | 4117 | +| total_timesteps | 5656576 | +| train/ | | +| approx_kl | 0.018661886 | +| clip_fraction | 0.379 | +| clip_range | 0.0793 | +| entropy_loss | -7.42 | +| explained_variance | -0.119 | +| learning_rate | 8.8e-05 | +| loss | -0.0462 | +| n_updates | 11044 | +| policy_gradient_loss | -0.0263 | +| value_loss | 8.82e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.298 | +| time/ | | +| fps | 1373 | +| iterations | 2763 | +| time_elapsed | 4119 | +| total_timesteps | 5658624 | +| train/ | | +| approx_kl | 0.018560367 | +| clip_fraction | 0.355 | +| clip_range | 0.0793 | +| entropy_loss | -7.39 | +| explained_variance | -0.0712 | +| learning_rate | 8.8e-05 | +| loss | -0.0355 | +| n_updates | 11048 | +| policy_gradient_loss | -0.0227 | +| value_loss | 0.000272 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.298 | +| time/ | | +| fps | 1373 | +| iterations | 2764 | +| time_elapsed | 4120 | +| total_timesteps | 5660672 | +| train/ | | +| approx_kl | 0.018368155 | +| clip_fraction | 0.39 | +| clip_range | 0.0793 | +| entropy_loss | -7.52 | +| explained_variance | -0.151 | +| learning_rate | 8.8e-05 | +| loss | -0.0425 | +| n_updates | 11052 | +| policy_gradient_loss | -0.0276 | +| value_loss | 0.000107 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.298 | +| time/ | | +| fps | 1373 | +| iterations | 2765 | +| time_elapsed | 4122 | +| total_timesteps | 5662720 | +| train/ | | +| approx_kl | 0.015333687 | +| clip_fraction | 0.34 | +| clip_range | 0.0792 | +| entropy_loss | -7.6 | +| explained_variance | -0.0673 | +| learning_rate | 8.79e-05 | +| loss | -0.0412 | +| n_updates | 11056 | +| policy_gradient_loss | -0.0242 | +| value_loss | 0.000167 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.295 | +| time/ | | +| fps | 1373 | +| iterations | 2766 | +| time_elapsed | 4123 | +| total_timesteps | 5664768 | +| train/ | | +| approx_kl | 0.018350482 | +| clip_fraction | 0.367 | +| clip_range | 0.0792 | +| entropy_loss | -7.61 | +| explained_variance | -0.131 | +| learning_rate | 8.79e-05 | +| loss | -0.0449 | +| n_updates | 11060 | +| policy_gradient_loss | -0.0276 | +| value_loss | 7.83e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.3 | +| time/ | | +| fps | 1373 | +| iterations | 2767 | +| time_elapsed | 4125 | +| total_timesteps | 5666816 | +| train/ | | +| approx_kl | 0.020053744 | +| clip_fraction | 0.367 | +| clip_range | 0.0792 | +| entropy_loss | -7.45 | +| explained_variance | 0.0523 | +| learning_rate | 8.78e-05 | +| loss | -0.0409 | +| n_updates | 11064 | +| policy_gradient_loss | -0.0238 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 1373 | +| iterations | 2768 | +| time_elapsed | 4126 | +| total_timesteps | 5668864 | +| train/ | | +| approx_kl | 0.019645408 | +| clip_fraction | 0.339 | +| clip_range | 0.0792 | +| entropy_loss | -7.37 | +| explained_variance | -0.152 | +| learning_rate | 8.78e-05 | +| loss | -0.0373 | +| n_updates | 11068 | +| policy_gradient_loss | -0.0219 | +| value_loss | 0.00016 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1373 | +| iterations | 2769 | +| time_elapsed | 4127 | +| total_timesteps | 5670912 | +| train/ | | +| approx_kl | 0.019028489 | +| clip_fraction | 0.357 | +| clip_range | 0.0791 | +| entropy_loss | -7.43 | +| explained_variance | -0.0476 | +| learning_rate | 8.78e-05 | +| loss | -0.0375 | +| n_updates | 11072 | +| policy_gradient_loss | -0.0231 | +| value_loss | 0.000283 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1373 | +| iterations | 2770 | +| time_elapsed | 4129 | +| total_timesteps | 5672960 | +| train/ | | +| approx_kl | 0.017592663 | +| clip_fraction | 0.365 | +| clip_range | 0.0791 | +| entropy_loss | -7.4 | +| explained_variance | -0.127 | +| learning_rate | 8.77e-05 | +| loss | -0.0414 | +| n_updates | 11076 | +| policy_gradient_loss | -0.0254 | +| value_loss | 0.000203 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 1373 | +| iterations | 2771 | +| time_elapsed | 4130 | +| total_timesteps | 5675008 | +| train/ | | +| approx_kl | 0.016289717 | +| clip_fraction | 0.356 | +| clip_range | 0.0791 | +| entropy_loss | -7.51 | +| explained_variance | 0.0191 | +| learning_rate | 8.77e-05 | +| loss | -0.0339 | +| n_updates | 11080 | +| policy_gradient_loss | -0.0233 | +| value_loss | 0.000261 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 1373 | +| iterations | 2772 | +| time_elapsed | 4132 | +| total_timesteps | 5677056 | +| train/ | | +| approx_kl | 0.016570706 | +| clip_fraction | 0.362 | +| clip_range | 0.0791 | +| entropy_loss | -7.52 | +| explained_variance | -0.184 | +| learning_rate | 8.76e-05 | +| loss | -0.0333 | +| n_updates | 11084 | +| policy_gradient_loss | -0.0241 | +| value_loss | 0.000172 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1373 | +| iterations | 2773 | +| time_elapsed | 4133 | +| total_timesteps | 5679104 | +| train/ | | +| approx_kl | 0.015726492 | +| clip_fraction | 0.354 | +| clip_range | 0.079 | +| entropy_loss | -7.54 | +| explained_variance | -0.0196 | +| learning_rate | 8.76e-05 | +| loss | -0.0381 | +| n_updates | 11088 | +| policy_gradient_loss | -0.0233 | +| value_loss | 0.000128 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.315 | +| time/ | | +| fps | 1373 | +| iterations | 2774 | +| time_elapsed | 4135 | +| total_timesteps | 5681152 | +| train/ | | +| approx_kl | 0.015751377 | +| clip_fraction | 0.342 | +| clip_range | 0.079 | +| entropy_loss | -7.43 | +| explained_variance | -0.0302 | +| learning_rate | 8.76e-05 | +| loss | -0.0324 | +| n_updates | 11092 | +| policy_gradient_loss | -0.0229 | +| value_loss | 0.000223 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.315 | +| time/ | | +| fps | 1373 | +| iterations | 2775 | +| time_elapsed | 4136 | +| total_timesteps | 5683200 | +| train/ | | +| approx_kl | 0.013942535 | +| clip_fraction | 0.341 | +| clip_range | 0.079 | +| entropy_loss | -7.38 | +| explained_variance | -0.0377 | +| learning_rate | 8.75e-05 | +| loss | -0.0372 | +| n_updates | 11096 | +| policy_gradient_loss | -0.0223 | +| value_loss | 0.000356 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1373 | +| iterations | 2776 | +| time_elapsed | 4138 | +| total_timesteps | 5685248 | +| train/ | | +| approx_kl | 0.015963253 | +| clip_fraction | 0.357 | +| clip_range | 0.079 | +| entropy_loss | -7.55 | +| explained_variance | -0.244 | +| learning_rate | 8.75e-05 | +| loss | -0.0326 | +| n_updates | 11100 | +| policy_gradient_loss | -0.0261 | +| value_loss | 0.000123 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1373 | +| iterations | 2777 | +| time_elapsed | 4139 | +| total_timesteps | 5687296 | +| train/ | | +| approx_kl | 0.015675299 | +| clip_fraction | 0.373 | +| clip_range | 0.0789 | +| entropy_loss | -7.53 | +| explained_variance | -0.129 | +| learning_rate | 8.74e-05 | +| loss | -0.0407 | +| n_updates | 11104 | +| policy_gradient_loss | -0.0265 | +| value_loss | 0.000158 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1373 | +| iterations | 2778 | +| time_elapsed | 4140 | +| total_timesteps | 5689344 | +| train/ | | +| approx_kl | 0.015145521 | +| clip_fraction | 0.335 | +| clip_range | 0.0789 | +| entropy_loss | -7.47 | +| explained_variance | -0.00596 | +| learning_rate | 8.74e-05 | +| loss | -0.0332 | +| n_updates | 11108 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000173 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1373 | +| iterations | 2779 | +| time_elapsed | 4142 | +| total_timesteps | 5691392 | +| train/ | | +| approx_kl | 0.017434891 | +| clip_fraction | 0.386 | +| clip_range | 0.0789 | +| entropy_loss | -7.36 | +| explained_variance | 0.0924 | +| learning_rate | 8.74e-05 | +| loss | -0.0467 | +| n_updates | 11112 | +| policy_gradient_loss | -0.0264 | +| value_loss | 0.000128 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1373 | +| iterations | 2780 | +| time_elapsed | 4143 | +| total_timesteps | 5693440 | +| train/ | | +| approx_kl | 0.016406316 | +| clip_fraction | 0.335 | +| clip_range | 0.0789 | +| entropy_loss | -7.59 | +| explained_variance | -0.0107 | +| learning_rate | 8.73e-05 | +| loss | -0.0342 | +| n_updates | 11116 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000202 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 1373 | +| iterations | 2781 | +| time_elapsed | 4145 | +| total_timesteps | 5695488 | +| train/ | | +| approx_kl | 0.015541657 | +| clip_fraction | 0.354 | +| clip_range | 0.0788 | +| entropy_loss | -7.49 | +| explained_variance | -0.0877 | +| learning_rate | 8.73e-05 | +| loss | -0.0349 | +| n_updates | 11120 | +| policy_gradient_loss | -0.0231 | +| value_loss | 0.000302 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 1373 | +| iterations | 2782 | +| time_elapsed | 4146 | +| total_timesteps | 5697536 | +| train/ | | +| approx_kl | 0.017551433 | +| clip_fraction | 0.38 | +| clip_range | 0.0788 | +| entropy_loss | -7.41 | +| explained_variance | -0.0557 | +| learning_rate | 8.72e-05 | +| loss | -0.0451 | +| n_updates | 11124 | +| policy_gradient_loss | -0.0252 | +| value_loss | 0.000121 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1373 | +| iterations | 2783 | +| time_elapsed | 4148 | +| total_timesteps | 5699584 | +| train/ | | +| approx_kl | 0.017414635 | +| clip_fraction | 0.362 | +| clip_range | 0.0788 | +| entropy_loss | -7.6 | +| explained_variance | -0.0132 | +| learning_rate | 8.72e-05 | +| loss | -0.0367 | +| n_updates | 11128 | +| policy_gradient_loss | -0.024 | +| value_loss | 0.000197 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1373 | +| iterations | 2784 | +| time_elapsed | 4149 | +| total_timesteps | 5701632 | +| train/ | | +| approx_kl | 0.015296224 | +| clip_fraction | 0.34 | +| clip_range | 0.0788 | +| entropy_loss | -7.41 | +| explained_variance | -0.0775 | +| learning_rate | 8.71e-05 | +| loss | -0.0306 | +| n_updates | 11132 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000329 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1373 | +| iterations | 2785 | +| time_elapsed | 4151 | +| total_timesteps | 5703680 | +| train/ | | +| approx_kl | 0.017631726 | +| clip_fraction | 0.425 | +| clip_range | 0.0787 | +| entropy_loss | -7.57 | +| explained_variance | -0.832 | +| learning_rate | 8.71e-05 | +| loss | -0.0562 | +| n_updates | 11136 | +| policy_gradient_loss | -0.0334 | +| value_loss | 8.39e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1373 | +| iterations | 2786 | +| time_elapsed | 4152 | +| total_timesteps | 5705728 | +| train/ | | +| approx_kl | 0.01775589 | +| clip_fraction | 0.341 | +| clip_range | 0.0787 | +| entropy_loss | -7.6 | +| explained_variance | -0.132 | +| learning_rate | 8.71e-05 | +| loss | -0.0401 | +| n_updates | 11140 | +| policy_gradient_loss | -0.0227 | +| value_loss | 0.000168 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1373 | +| iterations | 2787 | +| time_elapsed | 4154 | +| total_timesteps | 5707776 | +| train/ | | +| approx_kl | 0.016005386 | +| clip_fraction | 0.367 | +| clip_range | 0.0787 | +| entropy_loss | -7.67 | +| explained_variance | -0.275 | +| learning_rate | 8.7e-05 | +| loss | -0.0353 | +| n_updates | 11144 | +| policy_gradient_loss | -0.0241 | +| value_loss | 0.000106 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.304 | +| time/ | | +| fps | 1373 | +| iterations | 2788 | +| time_elapsed | 4155 | +| total_timesteps | 5709824 | +| train/ | | +| approx_kl | 0.014361154 | +| clip_fraction | 0.32 | +| clip_range | 0.0787 | +| entropy_loss | -7.58 | +| explained_variance | -0.0313 | +| learning_rate | 8.7e-05 | +| loss | -0.0351 | +| n_updates | 11148 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000201 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.3 | +| time/ | | +| fps | 1373 | +| iterations | 2789 | +| time_elapsed | 4157 | +| total_timesteps | 5711872 | +| train/ | | +| approx_kl | 0.016664732 | +| clip_fraction | 0.359 | +| clip_range | 0.0786 | +| entropy_loss | -7.59 | +| explained_variance | 0.00483 | +| learning_rate | 8.69e-05 | +| loss | -0.035 | +| n_updates | 11152 | +| policy_gradient_loss | -0.0231 | +| value_loss | 0.000147 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.289 | +| time/ | | +| fps | 1373 | +| iterations | 2790 | +| time_elapsed | 4158 | +| total_timesteps | 5713920 | +| train/ | | +| approx_kl | 0.019418804 | +| clip_fraction | 0.377 | +| clip_range | 0.0786 | +| entropy_loss | -7.51 | +| explained_variance | -0.223 | +| learning_rate | 8.69e-05 | +| loss | -0.0436 | +| n_updates | 11156 | +| policy_gradient_loss | -0.025 | +| value_loss | 0.000108 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 1373 | +| iterations | 2791 | +| time_elapsed | 4160 | +| total_timesteps | 5715968 | +| train/ | | +| approx_kl | 0.01614286 | +| clip_fraction | 0.354 | +| clip_range | 0.0786 | +| entropy_loss | -7.44 | +| explained_variance | -0.0637 | +| learning_rate | 8.69e-05 | +| loss | -0.0318 | +| n_updates | 11160 | +| policy_gradient_loss | -0.022 | +| value_loss | 0.000139 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 1373 | +| iterations | 2792 | +| time_elapsed | 4161 | +| total_timesteps | 5718016 | +| train/ | | +| approx_kl | 0.016559534 | +| clip_fraction | 0.364 | +| clip_range | 0.0786 | +| entropy_loss | -7.37 | +| explained_variance | -0.00865 | +| learning_rate | 8.68e-05 | +| loss | -0.0391 | +| n_updates | 11164 | +| policy_gradient_loss | -0.0229 | +| value_loss | 0.00015 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 1374 | +| iterations | 2793 | +| time_elapsed | 4163 | +| total_timesteps | 5720064 | +| train/ | | +| approx_kl | 0.01654896 | +| clip_fraction | 0.337 | +| clip_range | 0.0785 | +| entropy_loss | -7.51 | +| explained_variance | -0.148 | +| learning_rate | 8.68e-05 | +| loss | -0.0317 | +| n_updates | 11168 | +| policy_gradient_loss | -0.022 | +| value_loss | 0.000226 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.277 | +| time/ | | +| fps | 1374 | +| iterations | 2794 | +| time_elapsed | 4164 | +| total_timesteps | 5722112 | +| train/ | | +| approx_kl | 0.016815934 | +| clip_fraction | 0.36 | +| clip_range | 0.0785 | +| entropy_loss | -7.44 | +| explained_variance | -0.157 | +| learning_rate | 8.67e-05 | +| loss | -0.0374 | +| n_updates | 11172 | +| policy_gradient_loss | -0.0229 | +| value_loss | 0.000141 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.277 | +| time/ | | +| fps | 1374 | +| iterations | 2795 | +| time_elapsed | 4165 | +| total_timesteps | 5724160 | +| train/ | | +| approx_kl | 0.014605518 | +| clip_fraction | 0.328 | +| clip_range | 0.0785 | +| entropy_loss | -7.49 | +| explained_variance | -0.0159 | +| learning_rate | 8.67e-05 | +| loss | -0.0372 | +| n_updates | 11176 | +| policy_gradient_loss | -0.0229 | +| value_loss | 0.000194 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.273 | +| time/ | | +| fps | 1374 | +| iterations | 2796 | +| time_elapsed | 4167 | +| total_timesteps | 5726208 | +| train/ | | +| approx_kl | 0.016992103 | +| clip_fraction | 0.367 | +| clip_range | 0.0784 | +| entropy_loss | -7.58 | +| explained_variance | -0.0626 | +| learning_rate | 8.67e-05 | +| loss | -0.0348 | +| n_updates | 11180 | +| policy_gradient_loss | -0.0227 | +| value_loss | 0.000135 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.273 | +| time/ | | +| fps | 1374 | +| iterations | 2797 | +| time_elapsed | 4168 | +| total_timesteps | 5728256 | +| train/ | | +| approx_kl | 0.014923362 | +| clip_fraction | 0.359 | +| clip_range | 0.0784 | +| entropy_loss | -7.56 | +| explained_variance | 0.0212 | +| learning_rate | 8.66e-05 | +| loss | -0.0401 | +| n_updates | 11184 | +| policy_gradient_loss | -0.0243 | +| value_loss | 0.000249 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.27 | +| time/ | | +| fps | 1374 | +| iterations | 2798 | +| time_elapsed | 4170 | +| total_timesteps | 5730304 | +| train/ | | +| approx_kl | 0.014918949 | +| clip_fraction | 0.342 | +| clip_range | 0.0784 | +| entropy_loss | -7.57 | +| explained_variance | -0.0709 | +| learning_rate | 8.66e-05 | +| loss | -0.0387 | +| n_updates | 11188 | +| policy_gradient_loss | -0.0236 | +| value_loss | 0.000256 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.28 | +| time/ | | +| fps | 1374 | +| iterations | 2799 | +| time_elapsed | 4171 | +| total_timesteps | 5732352 | +| train/ | | +| approx_kl | 0.013752426 | +| clip_fraction | 0.328 | +| clip_range | 0.0784 | +| entropy_loss | -7.56 | +| explained_variance | -0.1 | +| learning_rate | 8.65e-05 | +| loss | -0.0333 | +| n_updates | 11192 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000323 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 1374 | +| iterations | 2800 | +| time_elapsed | 4173 | +| total_timesteps | 5734400 | +| train/ | | +| approx_kl | 0.016913883 | +| clip_fraction | 0.343 | +| clip_range | 0.0783 | +| entropy_loss | -7.51 | +| explained_variance | -0.0743 | +| learning_rate | 8.65e-05 | +| loss | -0.0397 | +| n_updates | 11196 | +| policy_gradient_loss | -0.0228 | +| value_loss | 0.000196 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.302 | +| time/ | | +| fps | 1374 | +| iterations | 2801 | +| time_elapsed | 4174 | +| total_timesteps | 5736448 | +| train/ | | +| approx_kl | 0.01567099 | +| clip_fraction | 0.349 | +| clip_range | 0.0783 | +| entropy_loss | -7.49 | +| explained_variance | -0.0877 | +| learning_rate | 8.65e-05 | +| loss | -0.0312 | +| n_updates | 11200 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000272 | +---------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.304 | +| time/ | | +| fps | 1374 | +| iterations | 2802 | +| time_elapsed | 4176 | +| total_timesteps | 5738496 | +| train/ | | +| approx_kl | 0.016518 | +| clip_fraction | 0.355 | +| clip_range | 0.0783 | +| entropy_loss | -7.39 | +| explained_variance | -0.124 | +| learning_rate | 8.64e-05 | +| loss | -0.0409 | +| n_updates | 11204 | +| policy_gradient_loss | -0.0256 | +| value_loss | 0.000222 | +-------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 1374 | +| iterations | 2803 | +| time_elapsed | 4177 | +| total_timesteps | 5740544 | +| train/ | | +| approx_kl | 0.016223757 | +| clip_fraction | 0.355 | +| clip_range | 0.0783 | +| entropy_loss | -7.47 | +| explained_variance | -0.137 | +| learning_rate | 8.64e-05 | +| loss | -0.0349 | +| n_updates | 11208 | +| policy_gradient_loss | -0.0241 | +| value_loss | 0.000303 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 1374 | +| iterations | 2804 | +| time_elapsed | 4179 | +| total_timesteps | 5742592 | +| train/ | | +| approx_kl | 0.017448913 | +| clip_fraction | 0.375 | +| clip_range | 0.0782 | +| entropy_loss | -7.51 | +| explained_variance | -0.401 | +| learning_rate | 8.63e-05 | +| loss | -0.0453 | +| n_updates | 11212 | +| policy_gradient_loss | -0.027 | +| value_loss | 0.000123 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 1374 | +| iterations | 2805 | +| time_elapsed | 4180 | +| total_timesteps | 5744640 | +| train/ | | +| approx_kl | 0.01649815 | +| clip_fraction | 0.34 | +| clip_range | 0.0782 | +| entropy_loss | -7.65 | +| explained_variance | -0.131 | +| learning_rate | 8.63e-05 | +| loss | -0.0343 | +| n_updates | 11216 | +| policy_gradient_loss | -0.0236 | +| value_loss | 0.000229 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 1374 | +| iterations | 2806 | +| time_elapsed | 4181 | +| total_timesteps | 5746688 | +| train/ | | +| approx_kl | 0.013435183 | +| clip_fraction | 0.328 | +| clip_range | 0.0782 | +| entropy_loss | -7.57 | +| explained_variance | -0.0456 | +| learning_rate | 8.63e-05 | +| loss | -0.032 | +| n_updates | 11220 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000421 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1374 | +| iterations | 2807 | +| time_elapsed | 4183 | +| total_timesteps | 5748736 | +| train/ | | +| approx_kl | 0.012967406 | +| clip_fraction | 0.352 | +| clip_range | 0.0782 | +| entropy_loss | -7.7 | +| explained_variance | -0.14 | +| learning_rate | 8.62e-05 | +| loss | -0.0399 | +| n_updates | 11224 | +| policy_gradient_loss | -0.0241 | +| value_loss | 0.000207 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 1374 | +| iterations | 2808 | +| time_elapsed | 4184 | +| total_timesteps | 5750784 | +| train/ | | +| approx_kl | 0.015390158 | +| clip_fraction | 0.367 | +| clip_range | 0.0781 | +| entropy_loss | -7.46 | +| explained_variance | -0.11 | +| learning_rate | 8.62e-05 | +| loss | -0.041 | +| n_updates | 11228 | +| policy_gradient_loss | -0.0236 | +| value_loss | 0.000161 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1374 | +| iterations | 2809 | +| time_elapsed | 4186 | +| total_timesteps | 5752832 | +| train/ | | +| approx_kl | 0.014302799 | +| clip_fraction | 0.364 | +| clip_range | 0.0781 | +| entropy_loss | -7.56 | +| explained_variance | -0.0111 | +| learning_rate | 8.61e-05 | +| loss | -0.0282 | +| n_updates | 11232 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000247 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1374 | +| iterations | 2810 | +| time_elapsed | 4187 | +| total_timesteps | 5754880 | +| train/ | | +| approx_kl | 0.014667727 | +| clip_fraction | 0.375 | +| clip_range | 0.0781 | +| entropy_loss | -7.33 | +| explained_variance | 0.0458 | +| learning_rate | 8.61e-05 | +| loss | -0.0368 | +| n_updates | 11236 | +| policy_gradient_loss | -0.0234 | +| value_loss | 0.000156 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 1374 | +| iterations | 2811 | +| time_elapsed | 4189 | +| total_timesteps | 5756928 | +| train/ | | +| approx_kl | 0.014826076 | +| clip_fraction | 0.358 | +| clip_range | 0.0781 | +| entropy_loss | -7.5 | +| explained_variance | -0.0694 | +| learning_rate | 8.61e-05 | +| loss | -0.0417 | +| n_updates | 11240 | +| policy_gradient_loss | -0.0229 | +| value_loss | 0.000201 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 1374 | +| iterations | 2812 | +| time_elapsed | 4190 | +| total_timesteps | 5758976 | +| train/ | | +| approx_kl | 0.018320456 | +| clip_fraction | 0.388 | +| clip_range | 0.078 | +| entropy_loss | -7.46 | +| explained_variance | -0.00298 | +| learning_rate | 8.6e-05 | +| loss | -0.0395 | +| n_updates | 11244 | +| policy_gradient_loss | -0.026 | +| value_loss | 0.000132 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 1374 | +| iterations | 2813 | +| time_elapsed | 4192 | +| total_timesteps | 5761024 | +| train/ | | +| approx_kl | 0.016706608 | +| clip_fraction | 0.37 | +| clip_range | 0.078 | +| entropy_loss | -7.62 | +| explained_variance | -0.226 | +| learning_rate | 8.6e-05 | +| loss | -0.0344 | +| n_updates | 11248 | +| policy_gradient_loss | -0.0234 | +| value_loss | 0.000194 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 1374 | +| iterations | 2814 | +| time_elapsed | 4193 | +| total_timesteps | 5763072 | +| train/ | | +| approx_kl | 0.016279181 | +| clip_fraction | 0.356 | +| clip_range | 0.078 | +| entropy_loss | -7.46 | +| explained_variance | -0.212 | +| learning_rate | 8.59e-05 | +| loss | -0.0329 | +| n_updates | 11252 | +| policy_gradient_loss | -0.0234 | +| value_loss | 0.000103 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 1374 | +| iterations | 2815 | +| time_elapsed | 4195 | +| total_timesteps | 5765120 | +| train/ | | +| approx_kl | 0.016414758 | +| clip_fraction | 0.357 | +| clip_range | 0.078 | +| entropy_loss | -7.48 | +| explained_variance | -0.0781 | +| learning_rate | 8.59e-05 | +| loss | -0.0396 | +| n_updates | 11256 | +| policy_gradient_loss | -0.0232 | +| value_loss | 0.000103 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 1374 | +| iterations | 2816 | +| time_elapsed | 4196 | +| total_timesteps | 5767168 | +| train/ | | +| approx_kl | 0.016443115 | +| clip_fraction | 0.357 | +| clip_range | 0.0779 | +| entropy_loss | -7.63 | +| explained_variance | -0.066 | +| learning_rate | 8.59e-05 | +| loss | -0.0345 | +| n_updates | 11260 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000169 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.291 | +| time/ | | +| fps | 1374 | +| iterations | 2817 | +| time_elapsed | 4198 | +| total_timesteps | 5769216 | +| train/ | | +| approx_kl | 0.016907936 | +| clip_fraction | 0.342 | +| clip_range | 0.0779 | +| entropy_loss | -7.65 | +| explained_variance | -0.152 | +| learning_rate | 8.58e-05 | +| loss | -0.0401 | +| n_updates | 11264 | +| policy_gradient_loss | -0.0238 | +| value_loss | 0.000145 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.288 | +| time/ | | +| fps | 1374 | +| iterations | 2818 | +| time_elapsed | 4199 | +| total_timesteps | 5771264 | +| train/ | | +| approx_kl | 0.016011383 | +| clip_fraction | 0.33 | +| clip_range | 0.0779 | +| entropy_loss | -7.47 | +| explained_variance | -0.0267 | +| learning_rate | 8.58e-05 | +| loss | -0.038 | +| n_updates | 11268 | +| policy_gradient_loss | -0.0222 | +| value_loss | 0.000261 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.286 | +| time/ | | +| fps | 1374 | +| iterations | 2819 | +| time_elapsed | 4201 | +| total_timesteps | 5773312 | +| train/ | | +| approx_kl | 0.014820374 | +| clip_fraction | 0.339 | +| clip_range | 0.0779 | +| entropy_loss | -7.5 | +| explained_variance | 0.0822 | +| learning_rate | 8.57e-05 | +| loss | -0.0373 | +| n_updates | 11272 | +| policy_gradient_loss | -0.0231 | +| value_loss | 0.000214 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.284 | +| time/ | | +| fps | 1374 | +| iterations | 2820 | +| time_elapsed | 4202 | +| total_timesteps | 5775360 | +| train/ | | +| approx_kl | 0.01645687 | +| clip_fraction | 0.354 | +| clip_range | 0.0778 | +| entropy_loss | -7.51 | +| explained_variance | -0.271 | +| learning_rate | 8.57e-05 | +| loss | -0.0372 | +| n_updates | 11276 | +| policy_gradient_loss | -0.0236 | +| value_loss | 0.000137 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.284 | +| time/ | | +| fps | 1374 | +| iterations | 2821 | +| time_elapsed | 4203 | +| total_timesteps | 5777408 | +| train/ | | +| approx_kl | 0.01686459 | +| clip_fraction | 0.358 | +| clip_range | 0.0778 | +| entropy_loss | -7.44 | +| explained_variance | -0.0762 | +| learning_rate | 8.56e-05 | +| loss | -0.0324 | +| n_updates | 11280 | +| policy_gradient_loss | -0.0224 | +| value_loss | 0.000171 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.289 | +| time/ | | +| fps | 1374 | +| iterations | 2822 | +| time_elapsed | 4205 | +| total_timesteps | 5779456 | +| train/ | | +| approx_kl | 0.016132526 | +| clip_fraction | 0.357 | +| clip_range | 0.0778 | +| entropy_loss | -7.49 | +| explained_variance | -0.169 | +| learning_rate | 8.56e-05 | +| loss | -0.0359 | +| n_updates | 11284 | +| policy_gradient_loss | -0.0227 | +| value_loss | 0.000159 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 1374 | +| iterations | 2823 | +| time_elapsed | 4206 | +| total_timesteps | 5781504 | +| train/ | | +| approx_kl | 0.017056521 | +| clip_fraction | 0.369 | +| clip_range | 0.0778 | +| entropy_loss | -7.45 | +| explained_variance | -0.0987 | +| learning_rate | 8.56e-05 | +| loss | -0.0321 | +| n_updates | 11288 | +| policy_gradient_loss | -0.0237 | +| value_loss | 0.000124 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.284 | +| time/ | | +| fps | 1374 | +| iterations | 2824 | +| time_elapsed | 4208 | +| total_timesteps | 5783552 | +| train/ | | +| approx_kl | 0.014881257 | +| clip_fraction | 0.323 | +| clip_range | 0.0777 | +| entropy_loss | -7.48 | +| explained_variance | -0.073 | +| learning_rate | 8.55e-05 | +| loss | -0.0287 | +| n_updates | 11292 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000244 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.284 | +| time/ | | +| fps | 1374 | +| iterations | 2825 | +| time_elapsed | 4209 | +| total_timesteps | 5785600 | +| train/ | | +| approx_kl | 0.0144581795 | +| clip_fraction | 0.343 | +| clip_range | 0.0777 | +| entropy_loss | -7.51 | +| explained_variance | -0.023 | +| learning_rate | 8.55e-05 | +| loss | -0.0378 | +| n_updates | 11296 | +| policy_gradient_loss | -0.022 | +| value_loss | 0.000361 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.29 | +| time/ | | +| fps | 1374 | +| iterations | 2826 | +| time_elapsed | 4211 | +| total_timesteps | 5787648 | +| train/ | | +| approx_kl | 0.018186748 | +| clip_fraction | 0.363 | +| clip_range | 0.0777 | +| entropy_loss | -7.55 | +| explained_variance | -0.203 | +| learning_rate | 8.54e-05 | +| loss | -0.0455 | +| n_updates | 11300 | +| policy_gradient_loss | -0.0259 | +| value_loss | 0.000131 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.29 | +| time/ | | +| fps | 1374 | +| iterations | 2827 | +| time_elapsed | 4212 | +| total_timesteps | 5789696 | +| train/ | | +| approx_kl | 0.01663719 | +| clip_fraction | 0.357 | +| clip_range | 0.0777 | +| entropy_loss | -7.49 | +| explained_variance | -0.0128 | +| learning_rate | 8.54e-05 | +| loss | -0.04 | +| n_updates | 11304 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000245 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.286 | +| time/ | | +| fps | 1374 | +| iterations | 2828 | +| time_elapsed | 4213 | +| total_timesteps | 5791744 | +| train/ | | +| approx_kl | 0.016800763 | +| clip_fraction | 0.367 | +| clip_range | 0.0776 | +| entropy_loss | -7.61 | +| explained_variance | -0.0764 | +| learning_rate | 8.54e-05 | +| loss | -0.0387 | +| n_updates | 11308 | +| policy_gradient_loss | -0.0248 | +| value_loss | 0.000149 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.286 | +| time/ | | +| fps | 1374 | +| iterations | 2829 | +| time_elapsed | 4215 | +| total_timesteps | 5793792 | +| train/ | | +| approx_kl | 0.015555747 | +| clip_fraction | 0.333 | +| clip_range | 0.0776 | +| entropy_loss | -7.55 | +| explained_variance | -0.0937 | +| learning_rate | 8.53e-05 | +| loss | -0.033 | +| n_updates | 11312 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000191 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.283 | +| time/ | | +| fps | 1374 | +| iterations | 2830 | +| time_elapsed | 4216 | +| total_timesteps | 5795840 | +| train/ | | +| approx_kl | 0.013354737 | +| clip_fraction | 0.333 | +| clip_range | 0.0776 | +| entropy_loss | -7.42 | +| explained_variance | -0.0707 | +| learning_rate | 8.53e-05 | +| loss | -0.0254 | +| n_updates | 11316 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.00025 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.281 | +| time/ | | +| fps | 1374 | +| iterations | 2831 | +| time_elapsed | 4218 | +| total_timesteps | 5797888 | +| train/ | | +| approx_kl | 0.018547978 | +| clip_fraction | 0.362 | +| clip_range | 0.0776 | +| entropy_loss | -7.48 | +| explained_variance | -0.112 | +| learning_rate | 8.52e-05 | +| loss | -0.038 | +| n_updates | 11320 | +| policy_gradient_loss | -0.0252 | +| value_loss | 0.000127 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 1374 | +| iterations | 2832 | +| time_elapsed | 4219 | +| total_timesteps | 5799936 | +| train/ | | +| approx_kl | 0.01781471 | +| clip_fraction | 0.397 | +| clip_range | 0.0775 | +| entropy_loss | -7.49 | +| explained_variance | -0.121 | +| learning_rate | 8.52e-05 | +| loss | -0.0415 | +| n_updates | 11324 | +| policy_gradient_loss | -0.0238 | +| value_loss | 0.000169 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.28 | +| time/ | | +| fps | 1374 | +| iterations | 2833 | +| time_elapsed | 4221 | +| total_timesteps | 5801984 | +| train/ | | +| approx_kl | 0.014923515 | +| clip_fraction | 0.34 | +| clip_range | 0.0775 | +| entropy_loss | -7.53 | +| explained_variance | -0.0311 | +| learning_rate | 8.52e-05 | +| loss | -0.0341 | +| n_updates | 11328 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000197 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 1374 | +| iterations | 2834 | +| time_elapsed | 4222 | +| total_timesteps | 5804032 | +| train/ | | +| approx_kl | 0.016715944 | +| clip_fraction | 0.382 | +| clip_range | 0.0775 | +| entropy_loss | -7.51 | +| explained_variance | -0.142 | +| learning_rate | 8.51e-05 | +| loss | -0.043 | +| n_updates | 11332 | +| policy_gradient_loss | -0.0258 | +| value_loss | 9.71e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.284 | +| time/ | | +| fps | 1374 | +| iterations | 2835 | +| time_elapsed | 4224 | +| total_timesteps | 5806080 | +| train/ | | +| approx_kl | 0.016075857 | +| clip_fraction | 0.379 | +| clip_range | 0.0774 | +| entropy_loss | -7.44 | +| explained_variance | -0.0704 | +| learning_rate | 8.51e-05 | +| loss | -0.0349 | +| n_updates | 11336 | +| policy_gradient_loss | -0.024 | +| value_loss | 0.000111 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.281 | +| time/ | | +| fps | 1374 | +| iterations | 2836 | +| time_elapsed | 4225 | +| total_timesteps | 5808128 | +| train/ | | +| approx_kl | 0.017520793 | +| clip_fraction | 0.358 | +| clip_range | 0.0774 | +| entropy_loss | -7.38 | +| explained_variance | -0.164 | +| learning_rate | 8.5e-05 | +| loss | -0.0347 | +| n_updates | 11340 | +| policy_gradient_loss | -0.0236 | +| value_loss | 0.000126 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.276 | +| time/ | | +| fps | 1374 | +| iterations | 2837 | +| time_elapsed | 4227 | +| total_timesteps | 5810176 | +| train/ | | +| approx_kl | 0.016414242 | +| clip_fraction | 0.35 | +| clip_range | 0.0774 | +| entropy_loss | -7.39 | +| explained_variance | -0.164 | +| learning_rate | 8.5e-05 | +| loss | -0.0351 | +| n_updates | 11344 | +| policy_gradient_loss | -0.023 | +| value_loss | 0.00015 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.273 | +| time/ | | +| fps | 1374 | +| iterations | 2838 | +| time_elapsed | 4228 | +| total_timesteps | 5812224 | +| train/ | | +| approx_kl | 0.018234175 | +| clip_fraction | 0.367 | +| clip_range | 0.0774 | +| entropy_loss | -7.42 | +| explained_variance | -0.143 | +| learning_rate | 8.5e-05 | +| loss | -0.0389 | +| n_updates | 11348 | +| policy_gradient_loss | -0.0242 | +| value_loss | 0.000132 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.272 | +| time/ | | +| fps | 1374 | +| iterations | 2839 | +| time_elapsed | 4230 | +| total_timesteps | 5814272 | +| train/ | | +| approx_kl | 0.016543942 | +| clip_fraction | 0.369 | +| clip_range | 0.0773 | +| entropy_loss | -7.33 | +| explained_variance | -0.0828 | +| learning_rate | 8.49e-05 | +| loss | -0.0415 | +| n_updates | 11352 | +| policy_gradient_loss | -0.0243 | +| value_loss | 0.000118 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.268 | +| time/ | | +| fps | 1374 | +| iterations | 2840 | +| time_elapsed | 4231 | +| total_timesteps | 5816320 | +| train/ | | +| approx_kl | 0.016366743 | +| clip_fraction | 0.365 | +| clip_range | 0.0773 | +| entropy_loss | -7.56 | +| explained_variance | -0.0468 | +| learning_rate | 8.49e-05 | +| loss | -0.036 | +| n_updates | 11356 | +| policy_gradient_loss | -0.0223 | +| value_loss | 0.000157 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.268 | +| time/ | | +| fps | 1374 | +| iterations | 2841 | +| time_elapsed | 4233 | +| total_timesteps | 5818368 | +| train/ | | +| approx_kl | 0.017831549 | +| clip_fraction | 0.381 | +| clip_range | 0.0773 | +| entropy_loss | -7.5 | +| explained_variance | -0.216 | +| learning_rate | 8.48e-05 | +| loss | -0.0402 | +| n_updates | 11360 | +| policy_gradient_loss | -0.0253 | +| value_loss | 9.43e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.259 | +| time/ | | +| fps | 1374 | +| iterations | 2842 | +| time_elapsed | 4234 | +| total_timesteps | 5820416 | +| train/ | | +| approx_kl | 0.017817885 | +| clip_fraction | 0.349 | +| clip_range | 0.0773 | +| entropy_loss | -7.53 | +| explained_variance | -0.0394 | +| learning_rate | 8.48e-05 | +| loss | -0.0351 | +| n_updates | 11364 | +| policy_gradient_loss | -0.0221 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.259 | +| time/ | | +| fps | 1374 | +| iterations | 2843 | +| time_elapsed | 4235 | +| total_timesteps | 5822464 | +| train/ | | +| approx_kl | 0.015915837 | +| clip_fraction | 0.35 | +| clip_range | 0.0772 | +| entropy_loss | -7.42 | +| explained_variance | -0.0756 | +| learning_rate | 8.48e-05 | +| loss | -0.0361 | +| n_updates | 11368 | +| policy_gradient_loss | -0.0229 | +| value_loss | 0.000225 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.26 | +| time/ | | +| fps | 1374 | +| iterations | 2844 | +| time_elapsed | 4237 | +| total_timesteps | 5824512 | +| train/ | | +| approx_kl | 0.016655827 | +| clip_fraction | 0.376 | +| clip_range | 0.0772 | +| entropy_loss | -7.44 | +| explained_variance | -0.0479 | +| learning_rate | 8.47e-05 | +| loss | -0.0353 | +| n_updates | 11372 | +| policy_gradient_loss | -0.0223 | +| value_loss | 0.000214 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.266 | +| time/ | | +| fps | 1374 | +| iterations | 2845 | +| time_elapsed | 4238 | +| total_timesteps | 5826560 | +| train/ | | +| approx_kl | 0.017151032 | +| clip_fraction | 0.35 | +| clip_range | 0.0772 | +| entropy_loss | -7.43 | +| explained_variance | -0.0758 | +| learning_rate | 8.47e-05 | +| loss | -0.0403 | +| n_updates | 11376 | +| policy_gradient_loss | -0.0235 | +| value_loss | 0.000164 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.266 | +| time/ | | +| fps | 1374 | +| iterations | 2846 | +| time_elapsed | 4240 | +| total_timesteps | 5828608 | +| train/ | | +| approx_kl | 0.016490728 | +| clip_fraction | 0.354 | +| clip_range | 0.0772 | +| entropy_loss | -7.52 | +| explained_variance | -0.0945 | +| learning_rate | 8.46e-05 | +| loss | -0.0388 | +| n_updates | 11380 | +| policy_gradient_loss | -0.023 | +| value_loss | 0.000223 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.27 | +| time/ | | +| fps | 1374 | +| iterations | 2847 | +| time_elapsed | 4241 | +| total_timesteps | 5830656 | +| train/ | | +| approx_kl | 0.018113777 | +| clip_fraction | 0.381 | +| clip_range | 0.0771 | +| entropy_loss | -7.57 | +| explained_variance | -0.0952 | +| learning_rate | 8.46e-05 | +| loss | -0.0347 | +| n_updates | 11384 | +| policy_gradient_loss | -0.0252 | +| value_loss | 0.000154 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.27 | +| time/ | | +| fps | 1374 | +| iterations | 2848 | +| time_elapsed | 4243 | +| total_timesteps | 5832704 | +| train/ | | +| approx_kl | 0.015134433 | +| clip_fraction | 0.374 | +| clip_range | 0.0771 | +| entropy_loss | -7.36 | +| explained_variance | 0.019 | +| learning_rate | 8.46e-05 | +| loss | -0.0386 | +| n_updates | 11388 | +| policy_gradient_loss | -0.0234 | +| value_loss | 0.000311 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.27 | +| time/ | | +| fps | 1374 | +| iterations | 2849 | +| time_elapsed | 4244 | +| total_timesteps | 5834752 | +| train/ | | +| approx_kl | 0.016616683 | +| clip_fraction | 0.367 | +| clip_range | 0.0771 | +| entropy_loss | -7.41 | +| explained_variance | -0.0567 | +| learning_rate | 8.45e-05 | +| loss | -0.0327 | +| n_updates | 11392 | +| policy_gradient_loss | -0.0251 | +| value_loss | 0.000148 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.272 | +| time/ | | +| fps | 1374 | +| iterations | 2850 | +| time_elapsed | 4246 | +| total_timesteps | 5836800 | +| train/ | | +| approx_kl | 0.017980505 | +| clip_fraction | 0.377 | +| clip_range | 0.0771 | +| entropy_loss | -7.5 | +| explained_variance | -0.211 | +| learning_rate | 8.45e-05 | +| loss | -0.0418 | +| n_updates | 11396 | +| policy_gradient_loss | -0.0236 | +| value_loss | 0.000149 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.287 | +| time/ | | +| fps | 1374 | +| iterations | 2851 | +| time_elapsed | 4247 | +| total_timesteps | 5838848 | +| train/ | | +| approx_kl | 0.018996986 | +| clip_fraction | 0.346 | +| clip_range | 0.077 | +| entropy_loss | -7.51 | +| explained_variance | -0.107 | +| learning_rate | 8.44e-05 | +| loss | -0.0334 | +| n_updates | 11400 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000237 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.289 | +| time/ | | +| fps | 1374 | +| iterations | 2852 | +| time_elapsed | 4249 | +| total_timesteps | 5840896 | +| train/ | | +| approx_kl | 0.015704269 | +| clip_fraction | 0.354 | +| clip_range | 0.077 | +| entropy_loss | -7.28 | +| explained_variance | 0.018 | +| learning_rate | 8.44e-05 | +| loss | -0.0262 | +| n_updates | 11404 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000401 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.29 | +| time/ | | +| fps | 1374 | +| iterations | 2853 | +| time_elapsed | 4250 | +| total_timesteps | 5842944 | +| train/ | | +| approx_kl | 0.017949246 | +| clip_fraction | 0.352 | +| clip_range | 0.077 | +| entropy_loss | -7.5 | +| explained_variance | -0.187 | +| learning_rate | 8.44e-05 | +| loss | -0.0355 | +| n_updates | 11408 | +| policy_gradient_loss | -0.0229 | +| value_loss | 0.000167 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.291 | +| time/ | | +| fps | 1374 | +| iterations | 2854 | +| time_elapsed | 4252 | +| total_timesteps | 5844992 | +| train/ | | +| approx_kl | 0.01779696 | +| clip_fraction | 0.381 | +| clip_range | 0.077 | +| entropy_loss | -7.43 | +| explained_variance | -0.0554 | +| learning_rate | 8.43e-05 | +| loss | -0.0389 | +| n_updates | 11412 | +| policy_gradient_loss | -0.0246 | +| value_loss | 0.00024 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.287 | +| time/ | | +| fps | 1374 | +| iterations | 2855 | +| time_elapsed | 4253 | +| total_timesteps | 5847040 | +| train/ | | +| approx_kl | 0.01874205 | +| clip_fraction | 0.396 | +| clip_range | 0.0769 | +| entropy_loss | -7.37 | +| explained_variance | -0.0864 | +| learning_rate | 8.43e-05 | +| loss | -0.0446 | +| n_updates | 11416 | +| policy_gradient_loss | -0.0271 | +| value_loss | 0.000131 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.286 | +| time/ | | +| fps | 1374 | +| iterations | 2856 | +| time_elapsed | 4254 | +| total_timesteps | 5849088 | +| train/ | | +| approx_kl | 0.016398374 | +| clip_fraction | 0.37 | +| clip_range | 0.0769 | +| entropy_loss | -7.4 | +| explained_variance | 0.077 | +| learning_rate | 8.42e-05 | +| loss | -0.0391 | +| n_updates | 11420 | +| policy_gradient_loss | -0.0249 | +| value_loss | 0.000164 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.289 | +| time/ | | +| fps | 1374 | +| iterations | 2857 | +| time_elapsed | 4256 | +| total_timesteps | 5851136 | +| train/ | | +| approx_kl | 0.015717497 | +| clip_fraction | 0.374 | +| clip_range | 0.0769 | +| entropy_loss | -7.39 | +| explained_variance | -0.176 | +| learning_rate | 8.42e-05 | +| loss | -0.0477 | +| n_updates | 11424 | +| policy_gradient_loss | -0.0253 | +| value_loss | 0.000125 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.293 | +| time/ | | +| fps | 1374 | +| iterations | 2858 | +| time_elapsed | 4257 | +| total_timesteps | 5853184 | +| train/ | | +| approx_kl | 0.014727652 | +| clip_fraction | 0.386 | +| clip_range | 0.0769 | +| entropy_loss | -7.46 | +| explained_variance | -0.0474 | +| learning_rate | 8.41e-05 | +| loss | -0.04 | +| n_updates | 11428 | +| policy_gradient_loss | -0.0236 | +| value_loss | 0.000187 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.295 | +| time/ | | +| fps | 1374 | +| iterations | 2859 | +| time_elapsed | 4259 | +| total_timesteps | 5855232 | +| train/ | | +| approx_kl | 0.014800963 | +| clip_fraction | 0.343 | +| clip_range | 0.0768 | +| entropy_loss | -7.42 | +| explained_variance | 0.00557 | +| learning_rate | 8.41e-05 | +| loss | -0.0296 | +| n_updates | 11432 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000289 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.29 | +| time/ | | +| fps | 1374 | +| iterations | 2860 | +| time_elapsed | 4260 | +| total_timesteps | 5857280 | +| train/ | | +| approx_kl | 0.016186241 | +| clip_fraction | 0.365 | +| clip_range | 0.0768 | +| entropy_loss | -7.37 | +| explained_variance | -0.13 | +| learning_rate | 8.41e-05 | +| loss | -0.0324 | +| n_updates | 11436 | +| policy_gradient_loss | -0.0219 | +| value_loss | 0.000294 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.29 | +| time/ | | +| fps | 1374 | +| iterations | 2861 | +| time_elapsed | 4262 | +| total_timesteps | 5859328 | +| train/ | | +| approx_kl | 0.017295796 | +| clip_fraction | 0.364 | +| clip_range | 0.0768 | +| entropy_loss | -7.44 | +| explained_variance | -0.158 | +| learning_rate | 8.4e-05 | +| loss | -0.0362 | +| n_updates | 11440 | +| policy_gradient_loss | -0.0245 | +| value_loss | 0.000297 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.291 | +| time/ | | +| fps | 1374 | +| iterations | 2862 | +| time_elapsed | 4263 | +| total_timesteps | 5861376 | +| train/ | | +| approx_kl | 0.016927622 | +| clip_fraction | 0.38 | +| clip_range | 0.0768 | +| entropy_loss | -7.54 | +| explained_variance | -0.241 | +| learning_rate | 8.4e-05 | +| loss | -0.0354 | +| n_updates | 11444 | +| policy_gradient_loss | -0.0234 | +| value_loss | 0.000235 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.288 | +| time/ | | +| fps | 1374 | +| iterations | 2863 | +| time_elapsed | 4265 | +| total_timesteps | 5863424 | +| train/ | | +| approx_kl | 0.017359577 | +| clip_fraction | 0.372 | +| clip_range | 0.0767 | +| entropy_loss | -7.5 | +| explained_variance | -0.155 | +| learning_rate | 8.39e-05 | +| loss | -0.033 | +| n_updates | 11448 | +| policy_gradient_loss | -0.0242 | +| value_loss | 0.000167 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.287 | +| time/ | | +| fps | 1374 | +| iterations | 2864 | +| time_elapsed | 4266 | +| total_timesteps | 5865472 | +| train/ | | +| approx_kl | 0.017664878 | +| clip_fraction | 0.381 | +| clip_range | 0.0767 | +| entropy_loss | -7.43 | +| explained_variance | -0.0269 | +| learning_rate | 8.39e-05 | +| loss | -0.036 | +| n_updates | 11452 | +| policy_gradient_loss | -0.0237 | +| value_loss | 0.000149 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.289 | +| time/ | | +| fps | 1374 | +| iterations | 2865 | +| time_elapsed | 4268 | +| total_timesteps | 5867520 | +| train/ | | +| approx_kl | 0.01740643 | +| clip_fraction | 0.377 | +| clip_range | 0.0767 | +| entropy_loss | -7.53 | +| explained_variance | -0.221 | +| learning_rate | 8.39e-05 | +| loss | -0.0396 | +| n_updates | 11456 | +| policy_gradient_loss | -0.0233 | +| value_loss | 0.000159 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.285 | +| time/ | | +| fps | 1374 | +| iterations | 2866 | +| time_elapsed | 4269 | +| total_timesteps | 5869568 | +| train/ | | +| approx_kl | 0.016235767 | +| clip_fraction | 0.383 | +| clip_range | 0.0767 | +| entropy_loss | -7.51 | +| explained_variance | -0.225 | +| learning_rate | 8.38e-05 | +| loss | -0.046 | +| n_updates | 11460 | +| policy_gradient_loss | -0.0252 | +| value_loss | 9.48e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.285 | +| time/ | | +| fps | 1374 | +| iterations | 2867 | +| time_elapsed | 4271 | +| total_timesteps | 5871616 | +| train/ | | +| approx_kl | 0.015413696 | +| clip_fraction | 0.355 | +| clip_range | 0.0766 | +| entropy_loss | -7.36 | +| explained_variance | -0.0439 | +| learning_rate | 8.38e-05 | +| loss | -0.0302 | +| n_updates | 11464 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000316 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.286 | +| time/ | | +| fps | 1374 | +| iterations | 2868 | +| time_elapsed | 4272 | +| total_timesteps | 5873664 | +| train/ | | +| approx_kl | 0.017054863 | +| clip_fraction | 0.358 | +| clip_range | 0.0766 | +| entropy_loss | -7.57 | +| explained_variance | 0.0087 | +| learning_rate | 8.37e-05 | +| loss | -0.0384 | +| n_updates | 11468 | +| policy_gradient_loss | -0.0244 | +| value_loss | 0.000178 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.285 | +| time/ | | +| fps | 1374 | +| iterations | 2869 | +| time_elapsed | 4274 | +| total_timesteps | 5875712 | +| train/ | | +| approx_kl | 0.018720973 | +| clip_fraction | 0.392 | +| clip_range | 0.0766 | +| entropy_loss | -7.52 | +| explained_variance | -0.213 | +| learning_rate | 8.37e-05 | +| loss | -0.0455 | +| n_updates | 11472 | +| policy_gradient_loss | -0.027 | +| value_loss | 8.78e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.286 | +| time/ | | +| fps | 1374 | +| iterations | 2870 | +| time_elapsed | 4275 | +| total_timesteps | 5877760 | +| train/ | | +| approx_kl | 0.015756406 | +| clip_fraction | 0.361 | +| clip_range | 0.0766 | +| entropy_loss | -7.49 | +| explained_variance | -0.0625 | +| learning_rate | 8.37e-05 | +| loss | -0.0346 | +| n_updates | 11476 | +| policy_gradient_loss | -0.0229 | +| value_loss | 0.000175 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.277 | +| time/ | | +| fps | 1374 | +| iterations | 2871 | +| time_elapsed | 4276 | +| total_timesteps | 5879808 | +| train/ | | +| approx_kl | 0.015773414 | +| clip_fraction | 0.374 | +| clip_range | 0.0765 | +| entropy_loss | -7.4 | +| explained_variance | 0.0787 | +| learning_rate | 8.36e-05 | +| loss | -0.0394 | +| n_updates | 11480 | +| policy_gradient_loss | -0.0254 | +| value_loss | 0.000122 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.28 | +| time/ | | +| fps | 1374 | +| iterations | 2872 | +| time_elapsed | 4278 | +| total_timesteps | 5881856 | +| train/ | | +| approx_kl | 0.017295016 | +| clip_fraction | 0.37 | +| clip_range | 0.0765 | +| entropy_loss | -7.41 | +| explained_variance | 0.126 | +| learning_rate | 8.36e-05 | +| loss | -0.0395 | +| n_updates | 11484 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000162 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.28 | +| time/ | | +| fps | 1374 | +| iterations | 2873 | +| time_elapsed | 4279 | +| total_timesteps | 5883904 | +| train/ | | +| approx_kl | 0.015422782 | +| clip_fraction | 0.379 | +| clip_range | 0.0765 | +| entropy_loss | -7.48 | +| explained_variance | -0.0843 | +| learning_rate | 8.35e-05 | +| loss | -0.0332 | +| n_updates | 11488 | +| policy_gradient_loss | -0.0234 | +| value_loss | 0.000237 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 1374 | +| iterations | 2874 | +| time_elapsed | 4281 | +| total_timesteps | 5885952 | +| train/ | | +| approx_kl | 0.014821747 | +| clip_fraction | 0.387 | +| clip_range | 0.0765 | +| entropy_loss | -7.6 | +| explained_variance | -0.277 | +| learning_rate | 8.35e-05 | +| loss | -0.0397 | +| n_updates | 11492 | +| policy_gradient_loss | -0.0248 | +| value_loss | 0.000111 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.276 | +| time/ | | +| fps | 1374 | +| iterations | 2875 | +| time_elapsed | 4282 | +| total_timesteps | 5888000 | +| train/ | | +| approx_kl | 0.015137487 | +| clip_fraction | 0.35 | +| clip_range | 0.0764 | +| entropy_loss | -7.54 | +| explained_variance | -0.0676 | +| learning_rate | 8.35e-05 | +| loss | -0.0351 | +| n_updates | 11496 | +| policy_gradient_loss | -0.0239 | +| value_loss | 0.000118 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.274 | +| time/ | | +| fps | 1374 | +| iterations | 2876 | +| time_elapsed | 4284 | +| total_timesteps | 5890048 | +| train/ | | +| approx_kl | 0.015778944 | +| clip_fraction | 0.367 | +| clip_range | 0.0764 | +| entropy_loss | -7.26 | +| explained_variance | -0.0268 | +| learning_rate | 8.34e-05 | +| loss | -0.043 | +| n_updates | 11500 | +| policy_gradient_loss | -0.0254 | +| value_loss | 7.37e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.278 | +| time/ | | +| fps | 1374 | +| iterations | 2877 | +| time_elapsed | 4285 | +| total_timesteps | 5892096 | +| train/ | | +| approx_kl | 0.020176651 | +| clip_fraction | 0.364 | +| clip_range | 0.0764 | +| entropy_loss | -7.43 | +| explained_variance | 0.0957 | +| learning_rate | 8.34e-05 | +| loss | -0.0361 | +| n_updates | 11504 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000125 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.278 | +| time/ | | +| fps | 1374 | +| iterations | 2878 | +| time_elapsed | 4286 | +| total_timesteps | 5894144 | +| train/ | | +| approx_kl | 0.015602299 | +| clip_fraction | 0.369 | +| clip_range | 0.0763 | +| entropy_loss | -7.43 | +| explained_variance | -0.0444 | +| learning_rate | 8.33e-05 | +| loss | -0.0323 | +| n_updates | 11508 | +| policy_gradient_loss | -0.0223 | +| value_loss | 0.000196 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.272 | +| time/ | | +| fps | 1374 | +| iterations | 2879 | +| time_elapsed | 4288 | +| total_timesteps | 5896192 | +| train/ | | +| approx_kl | 0.014227606 | +| clip_fraction | 0.368 | +| clip_range | 0.0763 | +| entropy_loss | -7.54 | +| explained_variance | 0.0946 | +| learning_rate | 8.33e-05 | +| loss | -0.0387 | +| n_updates | 11512 | +| policy_gradient_loss | -0.0239 | +| value_loss | 0.000129 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.278 | +| time/ | | +| fps | 1374 | +| iterations | 2880 | +| time_elapsed | 4289 | +| total_timesteps | 5898240 | +| train/ | | +| approx_kl | 0.016903788 | +| clip_fraction | 0.364 | +| clip_range | 0.0763 | +| entropy_loss | -7.6 | +| explained_variance | -0.252 | +| learning_rate | 8.33e-05 | +| loss | -0.0379 | +| n_updates | 11516 | +| policy_gradient_loss | -0.0236 | +| value_loss | 0.000113 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.278 | +| time/ | | +| fps | 1374 | +| iterations | 2881 | +| time_elapsed | 4291 | +| total_timesteps | 5900288 | +| train/ | | +| approx_kl | 0.01543526 | +| clip_fraction | 0.344 | +| clip_range | 0.0763 | +| entropy_loss | -7.38 | +| explained_variance | 0.0694 | +| learning_rate | 8.32e-05 | +| loss | -0.0337 | +| n_updates | 11520 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000198 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.278 | +| time/ | | +| fps | 1374 | +| iterations | 2882 | +| time_elapsed | 4292 | +| total_timesteps | 5902336 | +| train/ | | +| approx_kl | 0.015855648 | +| clip_fraction | 0.376 | +| clip_range | 0.0762 | +| entropy_loss | -7.62 | +| explained_variance | -0.215 | +| learning_rate | 8.32e-05 | +| loss | -0.0364 | +| n_updates | 11524 | +| policy_gradient_loss | -0.0228 | +| value_loss | 0.000144 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 1374 | +| iterations | 2883 | +| time_elapsed | 4294 | +| total_timesteps | 5904384 | +| train/ | | +| approx_kl | 0.015218205 | +| clip_fraction | 0.346 | +| clip_range | 0.0762 | +| entropy_loss | -7.5 | +| explained_variance | -0.0347 | +| learning_rate | 8.31e-05 | +| loss | -0.0377 | +| n_updates | 11528 | +| policy_gradient_loss | -0.022 | +| value_loss | 0.000161 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.286 | +| time/ | | +| fps | 1374 | +| iterations | 2884 | +| time_elapsed | 4295 | +| total_timesteps | 5906432 | +| train/ | | +| approx_kl | 0.015299695 | +| clip_fraction | 0.365 | +| clip_range | 0.0762 | +| entropy_loss | -7.46 | +| explained_variance | 0.00535 | +| learning_rate | 8.31e-05 | +| loss | -0.0368 | +| n_updates | 11532 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000278 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.283 | +| time/ | | +| fps | 1374 | +| iterations | 2885 | +| time_elapsed | 4297 | +| total_timesteps | 5908480 | +| train/ | | +| approx_kl | 0.014989691 | +| clip_fraction | 0.347 | +| clip_range | 0.0762 | +| entropy_loss | -7.51 | +| explained_variance | 0.05 | +| learning_rate | 8.31e-05 | +| loss | -0.0413 | +| n_updates | 11536 | +| policy_gradient_loss | -0.0219 | +| value_loss | 0.000237 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.283 | +| time/ | | +| fps | 1374 | +| iterations | 2886 | +| time_elapsed | 4298 | +| total_timesteps | 5910528 | +| train/ | | +| approx_kl | 0.0152670285 | +| clip_fraction | 0.355 | +| clip_range | 0.0761 | +| entropy_loss | -7.36 | +| explained_variance | -0.189 | +| learning_rate | 8.3e-05 | +| loss | -0.0399 | +| n_updates | 11540 | +| policy_gradient_loss | -0.0237 | +| value_loss | 0.00019 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.283 | +| time/ | | +| fps | 1374 | +| iterations | 2887 | +| time_elapsed | 4300 | +| total_timesteps | 5912576 | +| train/ | | +| approx_kl | 0.016869128 | +| clip_fraction | 0.399 | +| clip_range | 0.0761 | +| entropy_loss | -7.44 | +| explained_variance | -0.162 | +| learning_rate | 8.3e-05 | +| loss | -0.0413 | +| n_updates | 11544 | +| policy_gradient_loss | -0.026 | +| value_loss | 0.000175 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.288 | +| time/ | | +| fps | 1374 | +| iterations | 2888 | +| time_elapsed | 4301 | +| total_timesteps | 5914624 | +| train/ | | +| approx_kl | 0.018358426 | +| clip_fraction | 0.375 | +| clip_range | 0.0761 | +| entropy_loss | -7.5 | +| explained_variance | -0.113 | +| learning_rate | 8.29e-05 | +| loss | -0.0425 | +| n_updates | 11548 | +| policy_gradient_loss | -0.0254 | +| value_loss | 0.000113 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.288 | +| time/ | | +| fps | 1375 | +| iterations | 2889 | +| time_elapsed | 4303 | +| total_timesteps | 5916672 | +| train/ | | +| approx_kl | 0.014433646 | +| clip_fraction | 0.367 | +| clip_range | 0.0761 | +| entropy_loss | -7.45 | +| explained_variance | -0.0463 | +| learning_rate | 8.29e-05 | +| loss | -0.035 | +| n_updates | 11552 | +| policy_gradient_loss | -0.0228 | +| value_loss | 0.000315 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.288 | +| time/ | | +| fps | 1375 | +| iterations | 2890 | +| time_elapsed | 4304 | +| total_timesteps | 5918720 | +| train/ | | +| approx_kl | 0.017443858 | +| clip_fraction | 0.392 | +| clip_range | 0.076 | +| entropy_loss | -7.56 | +| explained_variance | -0.066 | +| learning_rate | 8.28e-05 | +| loss | -0.0414 | +| n_updates | 11556 | +| policy_gradient_loss | -0.0254 | +| value_loss | 0.000156 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.281 | +| time/ | | +| fps | 1375 | +| iterations | 2891 | +| time_elapsed | 4305 | +| total_timesteps | 5920768 | +| train/ | | +| approx_kl | 0.014050458 | +| clip_fraction | 0.354 | +| clip_range | 0.076 | +| entropy_loss | -7.7 | +| explained_variance | -0.13 | +| learning_rate | 8.28e-05 | +| loss | -0.0321 | +| n_updates | 11560 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000176 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.287 | +| time/ | | +| fps | 1375 | +| iterations | 2892 | +| time_elapsed | 4307 | +| total_timesteps | 5922816 | +| train/ | | +| approx_kl | 0.015155082 | +| clip_fraction | 0.355 | +| clip_range | 0.076 | +| entropy_loss | -7.6 | +| explained_variance | -0.362 | +| learning_rate | 8.28e-05 | +| loss | -0.0448 | +| n_updates | 11564 | +| policy_gradient_loss | -0.0237 | +| value_loss | 0.000104 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.283 | +| time/ | | +| fps | 1375 | +| iterations | 2893 | +| time_elapsed | 4308 | +| total_timesteps | 5924864 | +| train/ | | +| approx_kl | 0.016470794 | +| clip_fraction | 0.358 | +| clip_range | 0.076 | +| entropy_loss | -7.28 | +| explained_variance | 0.0427 | +| learning_rate | 8.27e-05 | +| loss | -0.0354 | +| n_updates | 11568 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.00018 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 1375 | +| iterations | 2894 | +| time_elapsed | 4310 | +| total_timesteps | 5926912 | +| train/ | | +| approx_kl | 0.017257161 | +| clip_fraction | 0.362 | +| clip_range | 0.0759 | +| entropy_loss | -7.45 | +| explained_variance | -0.287 | +| learning_rate | 8.27e-05 | +| loss | -0.0374 | +| n_updates | 11572 | +| policy_gradient_loss | -0.0233 | +| value_loss | 0.000121 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.285 | +| time/ | | +| fps | 1375 | +| iterations | 2895 | +| time_elapsed | 4311 | +| total_timesteps | 5928960 | +| train/ | | +| approx_kl | 0.015845893 | +| clip_fraction | 0.366 | +| clip_range | 0.0759 | +| entropy_loss | -7.46 | +| explained_variance | -0.0949 | +| learning_rate | 8.26e-05 | +| loss | -0.0358 | +| n_updates | 11576 | +| policy_gradient_loss | -0.0224 | +| value_loss | 0.000329 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.285 | +| time/ | | +| fps | 1375 | +| iterations | 2896 | +| time_elapsed | 4313 | +| total_timesteps | 5931008 | +| train/ | | +| approx_kl | 0.014994176 | +| clip_fraction | 0.377 | +| clip_range | 0.0759 | +| entropy_loss | -7.38 | +| explained_variance | -0.0789 | +| learning_rate | 8.26e-05 | +| loss | -0.0395 | +| n_updates | 11580 | +| policy_gradient_loss | -0.0224 | +| value_loss | 0.000331 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.285 | +| time/ | | +| fps | 1375 | +| iterations | 2897 | +| time_elapsed | 4314 | +| total_timesteps | 5933056 | +| train/ | | +| approx_kl | 0.017778862 | +| clip_fraction | 0.396 | +| clip_range | 0.0759 | +| entropy_loss | -7.6 | +| explained_variance | -0.188 | +| learning_rate | 8.26e-05 | +| loss | -0.0399 | +| n_updates | 11584 | +| policy_gradient_loss | -0.0249 | +| value_loss | 0.000152 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.287 | +| time/ | | +| fps | 1375 | +| iterations | 2898 | +| time_elapsed | 4315 | +| total_timesteps | 5935104 | +| train/ | | +| approx_kl | 0.018833958 | +| clip_fraction | 0.386 | +| clip_range | 0.0758 | +| entropy_loss | -7.53 | +| explained_variance | -0.101 | +| learning_rate | 8.25e-05 | +| loss | -0.0427 | +| n_updates | 11588 | +| policy_gradient_loss | -0.0261 | +| value_loss | 0.000105 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.289 | +| time/ | | +| fps | 1375 | +| iterations | 2899 | +| time_elapsed | 4317 | +| total_timesteps | 5937152 | +| train/ | | +| approx_kl | 0.016991396 | +| clip_fraction | 0.353 | +| clip_range | 0.0758 | +| entropy_loss | -7.59 | +| explained_variance | -0.0955 | +| learning_rate | 8.25e-05 | +| loss | -0.0316 | +| n_updates | 11592 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000312 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.289 | +| time/ | | +| fps | 1375 | +| iterations | 2900 | +| time_elapsed | 4318 | +| total_timesteps | 5939200 | +| train/ | | +| approx_kl | 0.015394258 | +| clip_fraction | 0.357 | +| clip_range | 0.0758 | +| entropy_loss | -7.43 | +| explained_variance | -0.14 | +| learning_rate | 8.24e-05 | +| loss | -0.037 | +| n_updates | 11596 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000238 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.291 | +| time/ | | +| fps | 1375 | +| iterations | 2901 | +| time_elapsed | 4320 | +| total_timesteps | 5941248 | +| train/ | | +| approx_kl | 0.015468826 | +| clip_fraction | 0.362 | +| clip_range | 0.0758 | +| entropy_loss | -7.57 | +| explained_variance | -0.13 | +| learning_rate | 8.24e-05 | +| loss | -0.033 | +| n_updates | 11600 | +| policy_gradient_loss | -0.0248 | +| value_loss | 0.000101 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.295 | +| time/ | | +| fps | 1375 | +| iterations | 2902 | +| time_elapsed | 4321 | +| total_timesteps | 5943296 | +| train/ | | +| approx_kl | 0.015392763 | +| clip_fraction | 0.333 | +| clip_range | 0.0757 | +| entropy_loss | -7.42 | +| explained_variance | 0.00159 | +| learning_rate | 8.24e-05 | +| loss | -0.035 | +| n_updates | 11604 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.00026 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.298 | +| time/ | | +| fps | 1375 | +| iterations | 2903 | +| time_elapsed | 4323 | +| total_timesteps | 5945344 | +| train/ | | +| approx_kl | 0.014777508 | +| clip_fraction | 0.368 | +| clip_range | 0.0757 | +| entropy_loss | -7.42 | +| explained_variance | 0.0737 | +| learning_rate | 8.23e-05 | +| loss | -0.0392 | +| n_updates | 11608 | +| policy_gradient_loss | -0.0225 | +| value_loss | 0.000149 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.3 | +| time/ | | +| fps | 1375 | +| iterations | 2904 | +| time_elapsed | 4324 | +| total_timesteps | 5947392 | +| train/ | | +| approx_kl | 0.016556906 | +| clip_fraction | 0.363 | +| clip_range | 0.0757 | +| entropy_loss | -7.53 | +| explained_variance | -0.153 | +| learning_rate | 8.23e-05 | +| loss | -0.0389 | +| n_updates | 11612 | +| policy_gradient_loss | -0.0233 | +| value_loss | 0.000148 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.306 | +| time/ | | +| fps | 1375 | +| iterations | 2905 | +| time_elapsed | 4325 | +| total_timesteps | 5949440 | +| train/ | | +| approx_kl | 0.016364852 | +| clip_fraction | 0.369 | +| clip_range | 0.0757 | +| entropy_loss | -7.41 | +| explained_variance | 0.0198 | +| learning_rate | 8.22e-05 | +| loss | -0.038 | +| n_updates | 11616 | +| policy_gradient_loss | -0.0227 | +| value_loss | 0.000181 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 1375 | +| iterations | 2906 | +| time_elapsed | 4327 | +| total_timesteps | 5951488 | +| train/ | | +| approx_kl | 0.014985455 | +| clip_fraction | 0.333 | +| clip_range | 0.0756 | +| entropy_loss | -7.39 | +| explained_variance | 0.00891 | +| learning_rate | 8.22e-05 | +| loss | -0.0355 | +| n_updates | 11620 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000308 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1375 | +| iterations | 2907 | +| time_elapsed | 4328 | +| total_timesteps | 5953536 | +| train/ | | +| approx_kl | 0.015701214 | +| clip_fraction | 0.365 | +| clip_range | 0.0756 | +| entropy_loss | -7.55 | +| explained_variance | -0.0082 | +| learning_rate | 8.22e-05 | +| loss | -0.0414 | +| n_updates | 11624 | +| policy_gradient_loss | -0.025 | +| value_loss | 0.00015 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1375 | +| iterations | 2908 | +| time_elapsed | 4330 | +| total_timesteps | 5955584 | +| train/ | | +| approx_kl | 0.016683634 | +| clip_fraction | 0.385 | +| clip_range | 0.0756 | +| entropy_loss | -7.36 | +| explained_variance | 0.0281 | +| learning_rate | 8.21e-05 | +| loss | -0.0377 | +| n_updates | 11628 | +| policy_gradient_loss | -0.0241 | +| value_loss | 0.000164 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1375 | +| iterations | 2909 | +| time_elapsed | 4331 | +| total_timesteps | 5957632 | +| train/ | | +| approx_kl | 0.017578369 | +| clip_fraction | 0.369 | +| clip_range | 0.0756 | +| entropy_loss | -7.53 | +| explained_variance | -0.0562 | +| learning_rate | 8.21e-05 | +| loss | -0.0349 | +| n_updates | 11632 | +| policy_gradient_loss | -0.0225 | +| value_loss | 0.000191 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1375 | +| iterations | 2910 | +| time_elapsed | 4332 | +| total_timesteps | 5959680 | +| train/ | | +| approx_kl | 0.014431461 | +| clip_fraction | 0.365 | +| clip_range | 0.0755 | +| entropy_loss | -7.48 | +| explained_variance | -0.0364 | +| learning_rate | 8.2e-05 | +| loss | -0.0332 | +| n_updates | 11636 | +| policy_gradient_loss | -0.0231 | +| value_loss | 0.000183 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1375 | +| iterations | 2911 | +| time_elapsed | 4334 | +| total_timesteps | 5961728 | +| train/ | | +| approx_kl | 0.015111523 | +| clip_fraction | 0.356 | +| clip_range | 0.0755 | +| entropy_loss | -7.46 | +| explained_variance | -0.056 | +| learning_rate | 8.2e-05 | +| loss | -0.0369 | +| n_updates | 11640 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000209 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1375 | +| iterations | 2912 | +| time_elapsed | 4335 | +| total_timesteps | 5963776 | +| train/ | | +| approx_kl | 0.016645333 | +| clip_fraction | 0.373 | +| clip_range | 0.0755 | +| entropy_loss | -7.57 | +| explained_variance | -0.212 | +| learning_rate | 8.2e-05 | +| loss | -0.0413 | +| n_updates | 11644 | +| policy_gradient_loss | -0.0251 | +| value_loss | 0.000132 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1375 | +| iterations | 2913 | +| time_elapsed | 4337 | +| total_timesteps | 5965824 | +| train/ | | +| approx_kl | 0.013044087 | +| clip_fraction | 0.326 | +| clip_range | 0.0755 | +| entropy_loss | -7.48 | +| explained_variance | -0.00966 | +| learning_rate | 8.19e-05 | +| loss | -0.0319 | +| n_updates | 11648 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000158 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 1375 | +| iterations | 2914 | +| time_elapsed | 4338 | +| total_timesteps | 5967872 | +| train/ | | +| approx_kl | 0.015246497 | +| clip_fraction | 0.353 | +| clip_range | 0.0754 | +| entropy_loss | -7.46 | +| explained_variance | -0.011 | +| learning_rate | 8.19e-05 | +| loss | -0.0373 | +| n_updates | 11652 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000202 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 1375 | +| iterations | 2915 | +| time_elapsed | 4340 | +| total_timesteps | 5969920 | +| train/ | | +| approx_kl | 0.014881587 | +| clip_fraction | 0.387 | +| clip_range | 0.0754 | +| entropy_loss | -7.52 | +| explained_variance | -0.124 | +| learning_rate | 8.18e-05 | +| loss | -0.0267 | +| n_updates | 11656 | +| policy_gradient_loss | -0.0251 | +| value_loss | 9.5e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 1375 | +| iterations | 2916 | +| time_elapsed | 4341 | +| total_timesteps | 5971968 | +| train/ | | +| approx_kl | 0.01768431 | +| clip_fraction | 0.375 | +| clip_range | 0.0754 | +| entropy_loss | -7.38 | +| explained_variance | -0.0499 | +| learning_rate | 8.18e-05 | +| loss | -0.0372 | +| n_updates | 11660 | +| policy_gradient_loss | -0.0241 | +| value_loss | 0.000228 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.297 | +| time/ | | +| fps | 1375 | +| iterations | 2917 | +| time_elapsed | 4343 | +| total_timesteps | 5974016 | +| train/ | | +| approx_kl | 0.012947874 | +| clip_fraction | 0.345 | +| clip_range | 0.0754 | +| entropy_loss | -7.5 | +| explained_variance | 0.0235 | +| learning_rate | 8.18e-05 | +| loss | -0.0322 | +| n_updates | 11664 | +| policy_gradient_loss | -0.023 | +| value_loss | 0.00019 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.297 | +| time/ | | +| fps | 1375 | +| iterations | 2918 | +| time_elapsed | 4344 | +| total_timesteps | 5976064 | +| train/ | | +| approx_kl | 0.015488092 | +| clip_fraction | 0.381 | +| clip_range | 0.0753 | +| entropy_loss | -7.41 | +| explained_variance | -0.231 | +| learning_rate | 8.17e-05 | +| loss | -0.0331 | +| n_updates | 11668 | +| policy_gradient_loss | -0.0242 | +| value_loss | 0.000128 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1375 | +| iterations | 2919 | +| time_elapsed | 4345 | +| total_timesteps | 5978112 | +| train/ | | +| approx_kl | 0.018964555 | +| clip_fraction | 0.393 | +| clip_range | 0.0753 | +| entropy_loss | -7.47 | +| explained_variance | -0.233 | +| learning_rate | 8.17e-05 | +| loss | -0.0349 | +| n_updates | 11672 | +| policy_gradient_loss | -0.025 | +| value_loss | 0.000116 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1375 | +| iterations | 2920 | +| time_elapsed | 4347 | +| total_timesteps | 5980160 | +| train/ | | +| approx_kl | 0.015823625 | +| clip_fraction | 0.357 | +| clip_range | 0.0753 | +| entropy_loss | -7.29 | +| explained_variance | -0.0876 | +| learning_rate | 8.16e-05 | +| loss | -0.0363 | +| n_updates | 11676 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000189 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 1375 | +| iterations | 2921 | +| time_elapsed | 4348 | +| total_timesteps | 5982208 | +| train/ | | +| approx_kl | 0.018336017 | +| clip_fraction | 0.381 | +| clip_range | 0.0752 | +| entropy_loss | -7.33 | +| explained_variance | -0.0532 | +| learning_rate | 8.16e-05 | +| loss | -0.0378 | +| n_updates | 11680 | +| policy_gradient_loss | -0.0225 | +| value_loss | 0.000194 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 1375 | +| iterations | 2922 | +| time_elapsed | 4350 | +| total_timesteps | 5984256 | +| train/ | | +| approx_kl | 0.017824847 | +| clip_fraction | 0.361 | +| clip_range | 0.0752 | +| entropy_loss | -7.48 | +| explained_variance | -0.303 | +| learning_rate | 8.16e-05 | +| loss | -0.0372 | +| n_updates | 11684 | +| policy_gradient_loss | -0.023 | +| value_loss | 0.000163 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.294 | +| time/ | | +| fps | 1375 | +| iterations | 2923 | +| time_elapsed | 4351 | +| total_timesteps | 5986304 | +| train/ | | +| approx_kl | 0.016503805 | +| clip_fraction | 0.364 | +| clip_range | 0.0752 | +| entropy_loss | -7.33 | +| explained_variance | -0.0518 | +| learning_rate | 8.15e-05 | +| loss | -0.0358 | +| n_updates | 11688 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000234 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.294 | +| time/ | | +| fps | 1375 | +| iterations | 2924 | +| time_elapsed | 4353 | +| total_timesteps | 5988352 | +| train/ | | +| approx_kl | 0.020504449 | +| clip_fraction | 0.385 | +| clip_range | 0.0752 | +| entropy_loss | -7.25 | +| explained_variance | 0.0987 | +| learning_rate | 8.15e-05 | +| loss | -0.0463 | +| n_updates | 11692 | +| policy_gradient_loss | -0.0255 | +| value_loss | 0.000145 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.294 | +| time/ | | +| fps | 1375 | +| iterations | 2925 | +| time_elapsed | 4354 | +| total_timesteps | 5990400 | +| train/ | | +| approx_kl | 0.01865903 | +| clip_fraction | 0.368 | +| clip_range | 0.0751 | +| entropy_loss | -7.42 | +| explained_variance | -0.0694 | +| learning_rate | 8.14e-05 | +| loss | -0.0336 | +| n_updates | 11696 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000217 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.291 | +| time/ | | +| fps | 1375 | +| iterations | 2926 | +| time_elapsed | 4355 | +| total_timesteps | 5992448 | +| train/ | | +| approx_kl | 0.015401413 | +| clip_fraction | 0.349 | +| clip_range | 0.0751 | +| entropy_loss | -7.55 | +| explained_variance | -0.126 | +| learning_rate | 8.14e-05 | +| loss | -0.0306 | +| n_updates | 11700 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000211 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.288 | +| time/ | | +| fps | 1375 | +| iterations | 2927 | +| time_elapsed | 4357 | +| total_timesteps | 5994496 | +| train/ | | +| approx_kl | 0.016780684 | +| clip_fraction | 0.381 | +| clip_range | 0.0751 | +| entropy_loss | -7.47 | +| explained_variance | -0.342 | +| learning_rate | 8.13e-05 | +| loss | -0.0349 | +| n_updates | 11704 | +| policy_gradient_loss | -0.0236 | +| value_loss | 0.000126 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.293 | +| time/ | | +| fps | 1375 | +| iterations | 2928 | +| time_elapsed | 4358 | +| total_timesteps | 5996544 | +| train/ | | +| approx_kl | 0.01757168 | +| clip_fraction | 0.381 | +| clip_range | 0.0751 | +| entropy_loss | -7.31 | +| explained_variance | -0.059 | +| learning_rate | 8.13e-05 | +| loss | -0.0338 | +| n_updates | 11708 | +| policy_gradient_loss | -0.0231 | +| value_loss | 0.000201 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.293 | +| time/ | | +| fps | 1375 | +| iterations | 2929 | +| time_elapsed | 4360 | +| total_timesteps | 5998592 | +| train/ | | +| approx_kl | 0.017821874 | +| clip_fraction | 0.388 | +| clip_range | 0.075 | +| entropy_loss | -7.25 | +| explained_variance | -0.0604 | +| learning_rate | 8.13e-05 | +| loss | -0.037 | +| n_updates | 11712 | +| policy_gradient_loss | -0.0223 | +| value_loss | 0.000355 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.293 | +| time/ | | +| fps | 1375 | +| iterations | 2930 | +| time_elapsed | 4361 | +| total_timesteps | 6000640 | +| train/ | | +| approx_kl | 0.017429162 | +| clip_fraction | 0.375 | +| clip_range | 0.075 | +| entropy_loss | -7.38 | +| explained_variance | -0.0439 | +| learning_rate | 8.12e-05 | +| loss | -0.0358 | +| n_updates | 11716 | +| policy_gradient_loss | -0.022 | +| value_loss | 0.000211 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.292 | +| time/ | | +| fps | 1375 | +| iterations | 2931 | +| time_elapsed | 4363 | +| total_timesteps | 6002688 | +| train/ | | +| approx_kl | 0.018316355 | +| clip_fraction | 0.383 | +| clip_range | 0.075 | +| entropy_loss | -7.53 | +| explained_variance | -0.288 | +| learning_rate | 8.12e-05 | +| loss | -0.0366 | +| n_updates | 11720 | +| policy_gradient_loss | -0.0252 | +| value_loss | 0.000134 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.294 | +| time/ | | +| fps | 1375 | +| iterations | 2932 | +| time_elapsed | 4364 | +| total_timesteps | 6004736 | +| train/ | | +| approx_kl | 0.014158996 | +| clip_fraction | 0.369 | +| clip_range | 0.075 | +| entropy_loss | -7.46 | +| explained_variance | -0.0872 | +| learning_rate | 8.11e-05 | +| loss | -0.0304 | +| n_updates | 11724 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000216 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.288 | +| time/ | | +| fps | 1375 | +| iterations | 2933 | +| time_elapsed | 4366 | +| total_timesteps | 6006784 | +| train/ | | +| approx_kl | 0.01703211 | +| clip_fraction | 0.364 | +| clip_range | 0.0749 | +| entropy_loss | -7.46 | +| explained_variance | -0.115 | +| learning_rate | 8.11e-05 | +| loss | -0.0403 | +| n_updates | 11728 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000158 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.292 | +| time/ | | +| fps | 1375 | +| iterations | 2934 | +| time_elapsed | 4367 | +| total_timesteps | 6008832 | +| train/ | | +| approx_kl | 0.016269527 | +| clip_fraction | 0.358 | +| clip_range | 0.0749 | +| entropy_loss | -7.45 | +| explained_variance | -0.116 | +| learning_rate | 8.11e-05 | +| loss | -0.0331 | +| n_updates | 11732 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000175 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.3 | +| time/ | | +| fps | 1375 | +| iterations | 2935 | +| time_elapsed | 4368 | +| total_timesteps | 6010880 | +| train/ | | +| approx_kl | 0.014482943 | +| clip_fraction | 0.377 | +| clip_range | 0.0749 | +| entropy_loss | -7.52 | +| explained_variance | -0.000347 | +| learning_rate | 8.1e-05 | +| loss | -0.0296 | +| n_updates | 11736 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000258 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 1375 | +| iterations | 2936 | +| time_elapsed | 4370 | +| total_timesteps | 6012928 | +| train/ | | +| approx_kl | 0.01663465 | +| clip_fraction | 0.39 | +| clip_range | 0.0749 | +| entropy_loss | -7.5 | +| explained_variance | -0.0513 | +| learning_rate | 8.1e-05 | +| loss | -0.0296 | +| n_updates | 11740 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000163 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.297 | +| time/ | | +| fps | 1375 | +| iterations | 2937 | +| time_elapsed | 4371 | +| total_timesteps | 6014976 | +| train/ | | +| approx_kl | 0.016860677 | +| clip_fraction | 0.374 | +| clip_range | 0.0748 | +| entropy_loss | -7.34 | +| explained_variance | -0.189 | +| learning_rate | 8.09e-05 | +| loss | -0.0368 | +| n_updates | 11744 | +| policy_gradient_loss | -0.0242 | +| value_loss | 0.000148 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.297 | +| time/ | | +| fps | 1375 | +| iterations | 2938 | +| time_elapsed | 4373 | +| total_timesteps | 6017024 | +| train/ | | +| approx_kl | 0.016680066 | +| clip_fraction | 0.373 | +| clip_range | 0.0748 | +| entropy_loss | -7.42 | +| explained_variance | -0.0662 | +| learning_rate | 8.09e-05 | +| loss | -0.0383 | +| n_updates | 11748 | +| policy_gradient_loss | -0.0231 | +| value_loss | 0.000192 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.3 | +| time/ | | +| fps | 1375 | +| iterations | 2939 | +| time_elapsed | 4374 | +| total_timesteps | 6019072 | +| train/ | | +| approx_kl | 0.015223102 | +| clip_fraction | 0.387 | +| clip_range | 0.0748 | +| entropy_loss | -7.49 | +| explained_variance | -0.0286 | +| learning_rate | 8.09e-05 | +| loss | -0.0356 | +| n_updates | 11752 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000175 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1375 | +| iterations | 2940 | +| time_elapsed | 4376 | +| total_timesteps | 6021120 | +| train/ | | +| approx_kl | 0.015786959 | +| clip_fraction | 0.379 | +| clip_range | 0.0748 | +| entropy_loss | -7.43 | +| explained_variance | -0.237 | +| learning_rate | 8.08e-05 | +| loss | -0.0368 | +| n_updates | 11756 | +| policy_gradient_loss | -0.0244 | +| value_loss | 0.000116 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1375 | +| iterations | 2941 | +| time_elapsed | 4377 | +| total_timesteps | 6023168 | +| train/ | | +| approx_kl | 0.014410734 | +| clip_fraction | 0.356 | +| clip_range | 0.0747 | +| entropy_loss | -7.5 | +| explained_variance | 0.0272 | +| learning_rate | 8.08e-05 | +| loss | -0.0327 | +| n_updates | 11760 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000351 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1375 | +| iterations | 2942 | +| time_elapsed | 4378 | +| total_timesteps | 6025216 | +| train/ | | +| approx_kl | 0.017770046 | +| clip_fraction | 0.355 | +| clip_range | 0.0747 | +| entropy_loss | -7.56 | +| explained_variance | -0.158 | +| learning_rate | 8.07e-05 | +| loss | -0.0342 | +| n_updates | 11764 | +| policy_gradient_loss | -0.023 | +| value_loss | 0.000226 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1376 | +| iterations | 2943 | +| time_elapsed | 4380 | +| total_timesteps | 6027264 | +| train/ | | +| approx_kl | 0.015524184 | +| clip_fraction | 0.399 | +| clip_range | 0.0747 | +| entropy_loss | -7.53 | +| explained_variance | -0.52 | +| learning_rate | 8.07e-05 | +| loss | -0.0407 | +| n_updates | 11768 | +| policy_gradient_loss | -0.0276 | +| value_loss | 0.000129 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1376 | +| iterations | 2944 | +| time_elapsed | 4381 | +| total_timesteps | 6029312 | +| train/ | | +| approx_kl | 0.016830524 | +| clip_fraction | 0.36 | +| clip_range | 0.0747 | +| entropy_loss | -7.5 | +| explained_variance | -0.0741 | +| learning_rate | 8.07e-05 | +| loss | -0.0364 | +| n_updates | 11772 | +| policy_gradient_loss | -0.0233 | +| value_loss | 0.000133 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1376 | +| iterations | 2945 | +| time_elapsed | 4383 | +| total_timesteps | 6031360 | +| train/ | | +| approx_kl | 0.015557745 | +| clip_fraction | 0.362 | +| clip_range | 0.0746 | +| entropy_loss | -7.43 | +| explained_variance | -0.135 | +| learning_rate | 8.06e-05 | +| loss | -0.035 | +| n_updates | 11776 | +| policy_gradient_loss | -0.0231 | +| value_loss | 0.000169 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1376 | +| iterations | 2946 | +| time_elapsed | 4384 | +| total_timesteps | 6033408 | +| train/ | | +| approx_kl | 0.018042207 | +| clip_fraction | 0.368 | +| clip_range | 0.0746 | +| entropy_loss | -7.37 | +| explained_variance | -0.0294 | +| learning_rate | 8.06e-05 | +| loss | -0.034 | +| n_updates | 11780 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000176 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1376 | +| iterations | 2947 | +| time_elapsed | 4385 | +| total_timesteps | 6035456 | +| train/ | | +| approx_kl | 0.01581118 | +| clip_fraction | 0.363 | +| clip_range | 0.0746 | +| entropy_loss | -7.42 | +| explained_variance | -0.105 | +| learning_rate | 8.05e-05 | +| loss | -0.0369 | +| n_updates | 11784 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000162 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1376 | +| iterations | 2948 | +| time_elapsed | 4387 | +| total_timesteps | 6037504 | +| train/ | | +| approx_kl | 0.017905379 | +| clip_fraction | 0.351 | +| clip_range | 0.0746 | +| entropy_loss | -7.34 | +| explained_variance | 0.128 | +| learning_rate | 8.05e-05 | +| loss | -0.034 | +| n_updates | 11788 | +| policy_gradient_loss | -0.022 | +| value_loss | 0.000143 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1376 | +| iterations | 2949 | +| time_elapsed | 4388 | +| total_timesteps | 6039552 | +| train/ | | +| approx_kl | 0.016483523 | +| clip_fraction | 0.331 | +| clip_range | 0.0745 | +| entropy_loss | -7.33 | +| explained_variance | 0.00733 | +| learning_rate | 8.05e-05 | +| loss | -0.033 | +| n_updates | 11792 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000253 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1376 | +| iterations | 2950 | +| time_elapsed | 4390 | +| total_timesteps | 6041600 | +| train/ | | +| approx_kl | 0.01778579 | +| clip_fraction | 0.39 | +| clip_range | 0.0745 | +| entropy_loss | -7.46 | +| explained_variance | -0.114 | +| learning_rate | 8.04e-05 | +| loss | -0.0396 | +| n_updates | 11796 | +| policy_gradient_loss | -0.0255 | +| value_loss | 0.00011 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1376 | +| iterations | 2951 | +| time_elapsed | 4391 | +| total_timesteps | 6043648 | +| train/ | | +| approx_kl | 0.020950291 | +| clip_fraction | 0.397 | +| clip_range | 0.0745 | +| entropy_loss | -7.4 | +| explained_variance | -0.447 | +| learning_rate | 8.04e-05 | +| loss | -0.0394 | +| n_updates | 11800 | +| policy_gradient_loss | -0.0266 | +| value_loss | 7.48e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1376 | +| iterations | 2952 | +| time_elapsed | 4393 | +| total_timesteps | 6045696 | +| train/ | | +| approx_kl | 0.01597797 | +| clip_fraction | 0.348 | +| clip_range | 0.0745 | +| entropy_loss | -7.55 | +| explained_variance | -0.0884 | +| learning_rate | 8.03e-05 | +| loss | -0.0319 | +| n_updates | 11804 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.00018 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1376 | +| iterations | 2953 | +| time_elapsed | 4394 | +| total_timesteps | 6047744 | +| train/ | | +| approx_kl | 0.01511235 | +| clip_fraction | 0.349 | +| clip_range | 0.0744 | +| entropy_loss | -7.5 | +| explained_variance | -0.077 | +| learning_rate | 8.03e-05 | +| loss | -0.0363 | +| n_updates | 11808 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000205 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1376 | +| iterations | 2954 | +| time_elapsed | 4395 | +| total_timesteps | 6049792 | +| train/ | | +| approx_kl | 0.015354788 | +| clip_fraction | 0.391 | +| clip_range | 0.0744 | +| entropy_loss | -7.53 | +| explained_variance | -0.277 | +| learning_rate | 8.03e-05 | +| loss | -0.0428 | +| n_updates | 11812 | +| policy_gradient_loss | -0.0249 | +| value_loss | 9.63e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1376 | +| iterations | 2955 | +| time_elapsed | 4397 | +| total_timesteps | 6051840 | +| train/ | | +| approx_kl | 0.014556136 | +| clip_fraction | 0.347 | +| clip_range | 0.0744 | +| entropy_loss | -7.35 | +| explained_variance | -0.001 | +| learning_rate | 8.02e-05 | +| loss | -0.0219 | +| n_updates | 11816 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000233 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 1376 | +| iterations | 2956 | +| time_elapsed | 4398 | +| total_timesteps | 6053888 | +| train/ | | +| approx_kl | 0.017361043 | +| clip_fraction | 0.351 | +| clip_range | 0.0744 | +| entropy_loss | -7.52 | +| explained_variance | -0.00854 | +| learning_rate | 8.02e-05 | +| loss | -0.0337 | +| n_updates | 11820 | +| policy_gradient_loss | -0.0223 | +| value_loss | 0.000112 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 1376 | +| iterations | 2957 | +| time_elapsed | 4400 | +| total_timesteps | 6055936 | +| train/ | | +| approx_kl | 0.016033072 | +| clip_fraction | 0.358 | +| clip_range | 0.0743 | +| entropy_loss | -7.3 | +| explained_variance | -0.175 | +| learning_rate | 8.01e-05 | +| loss | -0.0335 | +| n_updates | 11824 | +| policy_gradient_loss | -0.0222 | +| value_loss | 0.000215 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 1376 | +| iterations | 2958 | +| time_elapsed | 4401 | +| total_timesteps | 6057984 | +| train/ | | +| approx_kl | 0.015234752 | +| clip_fraction | 0.387 | +| clip_range | 0.0743 | +| entropy_loss | -7.48 | +| explained_variance | -0.109 | +| learning_rate | 8.01e-05 | +| loss | -0.0365 | +| n_updates | 11828 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000129 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1376 | +| iterations | 2959 | +| time_elapsed | 4403 | +| total_timesteps | 6060032 | +| train/ | | +| approx_kl | 0.017929813 | +| clip_fraction | 0.345 | +| clip_range | 0.0743 | +| entropy_loss | -7.38 | +| explained_variance | -0.00126 | +| learning_rate | 8.01e-05 | +| loss | -0.035 | +| n_updates | 11832 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000197 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.304 | +| time/ | | +| fps | 1376 | +| iterations | 2960 | +| time_elapsed | 4404 | +| total_timesteps | 6062080 | +| train/ | | +| approx_kl | 0.017875522 | +| clip_fraction | 0.36 | +| clip_range | 0.0742 | +| entropy_loss | -7.51 | +| explained_variance | 0.0556 | +| learning_rate | 8e-05 | +| loss | -0.04 | +| n_updates | 11836 | +| policy_gradient_loss | -0.0223 | +| value_loss | 0.000155 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 1376 | +| iterations | 2961 | +| time_elapsed | 4406 | +| total_timesteps | 6064128 | +| train/ | | +| approx_kl | 0.015502966 | +| clip_fraction | 0.355 | +| clip_range | 0.0742 | +| entropy_loss | -7.44 | +| explained_variance | -0.144 | +| learning_rate | 8e-05 | +| loss | -0.036 | +| n_updates | 11840 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000245 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 1376 | +| iterations | 2962 | +| time_elapsed | 4407 | +| total_timesteps | 6066176 | +| train/ | | +| approx_kl | 0.01812977 | +| clip_fraction | 0.384 | +| clip_range | 0.0742 | +| entropy_loss | -7.45 | +| explained_variance | -0.178 | +| learning_rate | 7.99e-05 | +| loss | -0.0414 | +| n_updates | 11844 | +| policy_gradient_loss | -0.0252 | +| value_loss | 0.000199 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.3 | +| time/ | | +| fps | 1376 | +| iterations | 2963 | +| time_elapsed | 4408 | +| total_timesteps | 6068224 | +| train/ | | +| approx_kl | 0.01788207 | +| clip_fraction | 0.375 | +| clip_range | 0.0742 | +| entropy_loss | -7.48 | +| explained_variance | -0.322 | +| learning_rate | 7.99e-05 | +| loss | -0.0409 | +| n_updates | 11848 | +| policy_gradient_loss | -0.0229 | +| value_loss | 0.000134 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 1376 | +| iterations | 2964 | +| time_elapsed | 4410 | +| total_timesteps | 6070272 | +| train/ | | +| approx_kl | 0.015240526 | +| clip_fraction | 0.357 | +| clip_range | 0.0741 | +| entropy_loss | -7.53 | +| explained_variance | -0.0873 | +| learning_rate | 7.98e-05 | +| loss | -0.0294 | +| n_updates | 11852 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000229 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 1376 | +| iterations | 2965 | +| time_elapsed | 4411 | +| total_timesteps | 6072320 | +| train/ | | +| approx_kl | 0.013754236 | +| clip_fraction | 0.375 | +| clip_range | 0.0741 | +| entropy_loss | -7.39 | +| explained_variance | -0.176 | +| learning_rate | 7.98e-05 | +| loss | -0.0346 | +| n_updates | 11856 | +| policy_gradient_loss | -0.0231 | +| value_loss | 0.000167 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1376 | +| iterations | 2966 | +| time_elapsed | 4413 | +| total_timesteps | 6074368 | +| train/ | | +| approx_kl | 0.01987033 | +| clip_fraction | 0.371 | +| clip_range | 0.0741 | +| entropy_loss | -7.53 | +| explained_variance | -0.137 | +| learning_rate | 7.98e-05 | +| loss | -0.0293 | +| n_updates | 11860 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000154 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1376 | +| iterations | 2967 | +| time_elapsed | 4414 | +| total_timesteps | 6076416 | +| train/ | | +| approx_kl | 0.013319328 | +| clip_fraction | 0.343 | +| clip_range | 0.0741 | +| entropy_loss | -7.43 | +| explained_variance | -0.0291 | +| learning_rate | 7.97e-05 | +| loss | -0.0329 | +| n_updates | 11864 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000255 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 1376 | +| iterations | 2968 | +| time_elapsed | 4416 | +| total_timesteps | 6078464 | +| train/ | | +| approx_kl | 0.015370671 | +| clip_fraction | 0.364 | +| clip_range | 0.074 | +| entropy_loss | -7.54 | +| explained_variance | -0.267 | +| learning_rate | 7.97e-05 | +| loss | -0.0384 | +| n_updates | 11868 | +| policy_gradient_loss | -0.0226 | +| value_loss | 0.000136 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.302 | +| time/ | | +| fps | 1376 | +| iterations | 2969 | +| time_elapsed | 4417 | +| total_timesteps | 6080512 | +| train/ | | +| approx_kl | 0.014580045 | +| clip_fraction | 0.363 | +| clip_range | 0.074 | +| entropy_loss | -7.54 | +| explained_variance | -0.151 | +| learning_rate | 7.96e-05 | +| loss | -0.0384 | +| n_updates | 11872 | +| policy_gradient_loss | -0.0223 | +| value_loss | 0.000188 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.302 | +| time/ | | +| fps | 1376 | +| iterations | 2970 | +| time_elapsed | 4418 | +| total_timesteps | 6082560 | +| train/ | | +| approx_kl | 0.01409879 | +| clip_fraction | 0.376 | +| clip_range | 0.074 | +| entropy_loss | -7.33 | +| explained_variance | -0.0962 | +| learning_rate | 7.96e-05 | +| loss | -0.0312 | +| n_updates | 11876 | +| policy_gradient_loss | -0.0209 | +| value_loss | 9.96e-05 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.304 | +| time/ | | +| fps | 1376 | +| iterations | 2971 | +| time_elapsed | 4420 | +| total_timesteps | 6084608 | +| train/ | | +| approx_kl | 0.01645099 | +| clip_fraction | 0.373 | +| clip_range | 0.074 | +| entropy_loss | -7.45 | +| explained_variance | -0.251 | +| learning_rate | 7.96e-05 | +| loss | -0.0361 | +| n_updates | 11880 | +| policy_gradient_loss | -0.0226 | +| value_loss | 8.56e-05 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1376 | +| iterations | 2972 | +| time_elapsed | 4421 | +| total_timesteps | 6086656 | +| train/ | | +| approx_kl | 0.01513875 | +| clip_fraction | 0.336 | +| clip_range | 0.0739 | +| entropy_loss | -7.57 | +| explained_variance | -0.101 | +| learning_rate | 7.95e-05 | +| loss | -0.0336 | +| n_updates | 11884 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000176 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1376 | +| iterations | 2973 | +| time_elapsed | 4423 | +| total_timesteps | 6088704 | +| train/ | | +| approx_kl | 0.015288661 | +| clip_fraction | 0.367 | +| clip_range | 0.0739 | +| entropy_loss | -7.54 | +| explained_variance | -0.191 | +| learning_rate | 7.95e-05 | +| loss | -0.0351 | +| n_updates | 11888 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000122 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.3 | +| time/ | | +| fps | 1376 | +| iterations | 2974 | +| time_elapsed | 4424 | +| total_timesteps | 6090752 | +| train/ | | +| approx_kl | 0.013858275 | +| clip_fraction | 0.342 | +| clip_range | 0.0739 | +| entropy_loss | -7.56 | +| explained_variance | -0.16 | +| learning_rate | 7.94e-05 | +| loss | -0.039 | +| n_updates | 11892 | +| policy_gradient_loss | -0.0227 | +| value_loss | 0.000107 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.293 | +| time/ | | +| fps | 1376 | +| iterations | 2975 | +| time_elapsed | 4426 | +| total_timesteps | 6092800 | +| train/ | | +| approx_kl | 0.013393203 | +| clip_fraction | 0.313 | +| clip_range | 0.0739 | +| entropy_loss | -7.46 | +| explained_variance | -0.081 | +| learning_rate | 7.94e-05 | +| loss | -0.0278 | +| n_updates | 11896 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.00021 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.293 | +| time/ | | +| fps | 1376 | +| iterations | 2976 | +| time_elapsed | 4427 | +| total_timesteps | 6094848 | +| train/ | | +| approx_kl | 0.012963164 | +| clip_fraction | 0.332 | +| clip_range | 0.0738 | +| entropy_loss | -7.48 | +| explained_variance | -0.0342 | +| learning_rate | 7.94e-05 | +| loss | -0.032 | +| n_updates | 11900 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000218 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.287 | +| time/ | | +| fps | 1376 | +| iterations | 2977 | +| time_elapsed | 4429 | +| total_timesteps | 6096896 | +| train/ | | +| approx_kl | 0.0152341155 | +| clip_fraction | 0.362 | +| clip_range | 0.0738 | +| entropy_loss | -7.46 | +| explained_variance | -0.0918 | +| learning_rate | 7.93e-05 | +| loss | -0.0329 | +| n_updates | 11904 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.00011 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.281 | +| time/ | | +| fps | 1376 | +| iterations | 2978 | +| time_elapsed | 4430 | +| total_timesteps | 6098944 | +| train/ | | +| approx_kl | 0.016156359 | +| clip_fraction | 0.35 | +| clip_range | 0.0738 | +| entropy_loss | -7.49 | +| explained_variance | -0.17 | +| learning_rate | 7.93e-05 | +| loss | -0.034 | +| n_updates | 11908 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000112 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 1376 | +| iterations | 2979 | +| time_elapsed | 4432 | +| total_timesteps | 6100992 | +| train/ | | +| approx_kl | 0.015984388 | +| clip_fraction | 0.357 | +| clip_range | 0.0738 | +| entropy_loss | -7.49 | +| explained_variance | -0.0737 | +| learning_rate | 7.92e-05 | +| loss | -0.0328 | +| n_updates | 11912 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000137 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 1376 | +| iterations | 2980 | +| time_elapsed | 4433 | +| total_timesteps | 6103040 | +| train/ | | +| approx_kl | 0.013869058 | +| clip_fraction | 0.316 | +| clip_range | 0.0737 | +| entropy_loss | -7.43 | +| explained_variance | -0.0893 | +| learning_rate | 7.92e-05 | +| loss | -0.0223 | +| n_updates | 11916 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000341 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 1376 | +| iterations | 2981 | +| time_elapsed | 4435 | +| total_timesteps | 6105088 | +| train/ | | +| approx_kl | 0.01664267 | +| clip_fraction | 0.372 | +| clip_range | 0.0737 | +| entropy_loss | -7.25 | +| explained_variance | -0.0775 | +| learning_rate | 7.92e-05 | +| loss | -0.0345 | +| n_updates | 11920 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000157 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 1376 | +| iterations | 2982 | +| time_elapsed | 4436 | +| total_timesteps | 6107136 | +| train/ | | +| approx_kl | 0.016922377 | +| clip_fraction | 0.377 | +| clip_range | 0.0737 | +| entropy_loss | -7.38 | +| explained_variance | -0.159 | +| learning_rate | 7.91e-05 | +| loss | -0.0375 | +| n_updates | 11924 | +| policy_gradient_loss | -0.0227 | +| value_loss | 0.000227 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 1376 | +| iterations | 2983 | +| time_elapsed | 4437 | +| total_timesteps | 6109184 | +| train/ | | +| approx_kl | 0.016767297 | +| clip_fraction | 0.376 | +| clip_range | 0.0737 | +| entropy_loss | -7.61 | +| explained_variance | -0.129 | +| learning_rate | 7.91e-05 | +| loss | -0.0375 | +| n_updates | 11928 | +| policy_gradient_loss | -0.0248 | +| value_loss | 0.000212 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 1376 | +| iterations | 2984 | +| time_elapsed | 4439 | +| total_timesteps | 6111232 | +| train/ | | +| approx_kl | 0.016781703 | +| clip_fraction | 0.354 | +| clip_range | 0.0736 | +| entropy_loss | -7.64 | +| explained_variance | -0.133 | +| learning_rate | 7.9e-05 | +| loss | -0.0435 | +| n_updates | 11932 | +| policy_gradient_loss | -0.0239 | +| value_loss | 0.000115 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.274 | +| time/ | | +| fps | 1376 | +| iterations | 2985 | +| time_elapsed | 4440 | +| total_timesteps | 6113280 | +| train/ | | +| approx_kl | 0.017031547 | +| clip_fraction | 0.356 | +| clip_range | 0.0736 | +| entropy_loss | -7.56 | +| explained_variance | -0.2 | +| learning_rate | 7.9e-05 | +| loss | -0.0354 | +| n_updates | 11936 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000163 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.28 | +| time/ | | +| fps | 1376 | +| iterations | 2986 | +| time_elapsed | 4442 | +| total_timesteps | 6115328 | +| train/ | | +| approx_kl | 0.016369158 | +| clip_fraction | 0.341 | +| clip_range | 0.0736 | +| entropy_loss | -7.53 | +| explained_variance | -0.0438 | +| learning_rate | 7.9e-05 | +| loss | -0.0337 | +| n_updates | 11940 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000211 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.28 | +| time/ | | +| fps | 1376 | +| iterations | 2987 | +| time_elapsed | 4443 | +| total_timesteps | 6117376 | +| train/ | | +| approx_kl | 0.018432293 | +| clip_fraction | 0.344 | +| clip_range | 0.0736 | +| entropy_loss | -7.38 | +| explained_variance | -0.13 | +| learning_rate | 7.89e-05 | +| loss | -0.0274 | +| n_updates | 11944 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000277 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.281 | +| time/ | | +| fps | 1376 | +| iterations | 2988 | +| time_elapsed | 4445 | +| total_timesteps | 6119424 | +| train/ | | +| approx_kl | 0.015437326 | +| clip_fraction | 0.368 | +| clip_range | 0.0735 | +| entropy_loss | -7.56 | +| explained_variance | -0.149 | +| learning_rate | 7.89e-05 | +| loss | -0.0404 | +| n_updates | 11948 | +| policy_gradient_loss | -0.024 | +| value_loss | 0.000163 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.284 | +| time/ | | +| fps | 1376 | +| iterations | 2989 | +| time_elapsed | 4446 | +| total_timesteps | 6121472 | +| train/ | | +| approx_kl | 0.012074673 | +| clip_fraction | 0.358 | +| clip_range | 0.0735 | +| entropy_loss | -7.51 | +| explained_variance | 0.0115 | +| learning_rate | 7.88e-05 | +| loss | -0.0331 | +| n_updates | 11952 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000302 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.283 | +| time/ | | +| fps | 1376 | +| iterations | 2990 | +| time_elapsed | 4448 | +| total_timesteps | 6123520 | +| train/ | | +| approx_kl | 0.015173404 | +| clip_fraction | 0.355 | +| clip_range | 0.0735 | +| entropy_loss | -7.41 | +| explained_variance | 0.0298 | +| learning_rate | 7.88e-05 | +| loss | -0.0301 | +| n_updates | 11956 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000175 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.289 | +| time/ | | +| fps | 1376 | +| iterations | 2991 | +| time_elapsed | 4449 | +| total_timesteps | 6125568 | +| train/ | | +| approx_kl | 0.015425878 | +| clip_fraction | 0.347 | +| clip_range | 0.0735 | +| entropy_loss | -7.52 | +| explained_variance | -0.268 | +| learning_rate | 7.88e-05 | +| loss | -0.0289 | +| n_updates | 11960 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000225 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.289 | +| time/ | | +| fps | 1376 | +| iterations | 2992 | +| time_elapsed | 4450 | +| total_timesteps | 6127616 | +| train/ | | +| approx_kl | 0.014839329 | +| clip_fraction | 0.377 | +| clip_range | 0.0734 | +| entropy_loss | -7.59 | +| explained_variance | -0.224 | +| learning_rate | 7.87e-05 | +| loss | -0.0416 | +| n_updates | 11964 | +| policy_gradient_loss | -0.023 | +| value_loss | 0.000128 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.289 | +| time/ | | +| fps | 1376 | +| iterations | 2993 | +| time_elapsed | 4452 | +| total_timesteps | 6129664 | +| train/ | | +| approx_kl | 0.014893224 | +| clip_fraction | 0.363 | +| clip_range | 0.0734 | +| entropy_loss | -7.53 | +| explained_variance | -0.123 | +| learning_rate | 7.87e-05 | +| loss | -0.035 | +| n_updates | 11968 | +| policy_gradient_loss | -0.0222 | +| value_loss | 0.00015 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.285 | +| time/ | | +| fps | 1376 | +| iterations | 2994 | +| time_elapsed | 4453 | +| total_timesteps | 6131712 | +| train/ | | +| approx_kl | 0.014355237 | +| clip_fraction | 0.363 | +| clip_range | 0.0734 | +| entropy_loss | -7.61 | +| explained_variance | -0.0877 | +| learning_rate | 7.86e-05 | +| loss | -0.0371 | +| n_updates | 11972 | +| policy_gradient_loss | -0.023 | +| value_loss | 0.000183 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.285 | +| time/ | | +| fps | 1376 | +| iterations | 2995 | +| time_elapsed | 4455 | +| total_timesteps | 6133760 | +| train/ | | +| approx_kl | 0.014766386 | +| clip_fraction | 0.323 | +| clip_range | 0.0734 | +| entropy_loss | -7.54 | +| explained_variance | -0.154 | +| learning_rate | 7.86e-05 | +| loss | -0.0372 | +| n_updates | 11976 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000129 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.284 | +| time/ | | +| fps | 1376 | +| iterations | 2996 | +| time_elapsed | 4456 | +| total_timesteps | 6135808 | +| train/ | | +| approx_kl | 0.014667824 | +| clip_fraction | 0.349 | +| clip_range | 0.0733 | +| entropy_loss | -7.58 | +| explained_variance | -0.0356 | +| learning_rate | 7.86e-05 | +| loss | -0.034 | +| n_updates | 11980 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000178 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 1376 | +| iterations | 2997 | +| time_elapsed | 4458 | +| total_timesteps | 6137856 | +| train/ | | +| approx_kl | 0.012182444 | +| clip_fraction | 0.338 | +| clip_range | 0.0733 | +| entropy_loss | -7.57 | +| explained_variance | -0.0307 | +| learning_rate | 7.85e-05 | +| loss | -0.0297 | +| n_updates | 11984 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000206 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.274 | +| time/ | | +| fps | 1376 | +| iterations | 2998 | +| time_elapsed | 4459 | +| total_timesteps | 6139904 | +| train/ | | +| approx_kl | 0.012425641 | +| clip_fraction | 0.316 | +| clip_range | 0.0733 | +| entropy_loss | -7.34 | +| explained_variance | -0.136 | +| learning_rate | 7.85e-05 | +| loss | -0.0318 | +| n_updates | 11988 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000305 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 1376 | +| iterations | 2999 | +| time_elapsed | 4461 | +| total_timesteps | 6141952 | +| train/ | | +| approx_kl | 0.01789971 | +| clip_fraction | 0.392 | +| clip_range | 0.0733 | +| entropy_loss | -7.27 | +| explained_variance | -0.0444 | +| learning_rate | 7.84e-05 | +| loss | -0.0335 | +| n_updates | 11992 | +| policy_gradient_loss | -0.0228 | +| value_loss | 0.00032 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 1376 | +| iterations | 3000 | +| time_elapsed | 4462 | +| total_timesteps | 6144000 | +| train/ | | +| approx_kl | 0.018330034 | +| clip_fraction | 0.399 | +| clip_range | 0.0732 | +| entropy_loss | -7.38 | +| explained_variance | -0.295 | +| learning_rate | 7.84e-05 | +| loss | -0.0433 | +| n_updates | 11996 | +| policy_gradient_loss | -0.0244 | +| value_loss | 0.00016 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 1376 | +| iterations | 3001 | +| time_elapsed | 4463 | +| total_timesteps | 6146048 | +| train/ | | +| approx_kl | 0.016410802 | +| clip_fraction | 0.379 | +| clip_range | 0.0732 | +| entropy_loss | -7.56 | +| explained_variance | -0.0934 | +| learning_rate | 7.83e-05 | +| loss | -0.0401 | +| n_updates | 12000 | +| policy_gradient_loss | -0.0234 | +| value_loss | 0.000188 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 1376 | +| iterations | 3002 | +| time_elapsed | 4465 | +| total_timesteps | 6148096 | +| train/ | | +| approx_kl | 0.016783526 | +| clip_fraction | 0.391 | +| clip_range | 0.0732 | +| entropy_loss | -7.59 | +| explained_variance | -0.361 | +| learning_rate | 7.83e-05 | +| loss | -0.0392 | +| n_updates | 12004 | +| policy_gradient_loss | -0.0253 | +| value_loss | 0.000101 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.276 | +| time/ | | +| fps | 1376 | +| iterations | 3003 | +| time_elapsed | 4466 | +| total_timesteps | 6150144 | +| train/ | | +| approx_kl | 0.014710813 | +| clip_fraction | 0.334 | +| clip_range | 0.0731 | +| entropy_loss | -7.63 | +| explained_variance | -0.112 | +| learning_rate | 7.83e-05 | +| loss | -0.0316 | +| n_updates | 12008 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000151 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.276 | +| time/ | | +| fps | 1376 | +| iterations | 3004 | +| time_elapsed | 4468 | +| total_timesteps | 6152192 | +| train/ | | +| approx_kl | 0.016791001 | +| clip_fraction | 0.358 | +| clip_range | 0.0731 | +| entropy_loss | -7.52 | +| explained_variance | -0.0591 | +| learning_rate | 7.82e-05 | +| loss | -0.0318 | +| n_updates | 12012 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000205 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 1376 | +| iterations | 3005 | +| time_elapsed | 4469 | +| total_timesteps | 6154240 | +| train/ | | +| approx_kl | 0.015603573 | +| clip_fraction | 0.338 | +| clip_range | 0.0731 | +| entropy_loss | -7.6 | +| explained_variance | -0.117 | +| learning_rate | 7.82e-05 | +| loss | -0.037 | +| n_updates | 12016 | +| policy_gradient_loss | -0.0228 | +| value_loss | 0.000108 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.266 | +| time/ | | +| fps | 1376 | +| iterations | 3006 | +| time_elapsed | 4471 | +| total_timesteps | 6156288 | +| train/ | | +| approx_kl | 0.015921744 | +| clip_fraction | 0.353 | +| clip_range | 0.0731 | +| entropy_loss | -7.59 | +| explained_variance | -0.119 | +| learning_rate | 7.81e-05 | +| loss | -0.0341 | +| n_updates | 12020 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000125 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.264 | +| time/ | | +| fps | 1376 | +| iterations | 3007 | +| time_elapsed | 4472 | +| total_timesteps | 6158336 | +| train/ | | +| approx_kl | 0.016805679 | +| clip_fraction | 0.342 | +| clip_range | 0.073 | +| entropy_loss | -7.5 | +| explained_variance | -0.16 | +| learning_rate | 7.81e-05 | +| loss | -0.0292 | +| n_updates | 12024 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000125 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.269 | +| time/ | | +| fps | 1376 | +| iterations | 3008 | +| time_elapsed | 4473 | +| total_timesteps | 6160384 | +| train/ | | +| approx_kl | 0.014089409 | +| clip_fraction | 0.351 | +| clip_range | 0.073 | +| entropy_loss | -7.36 | +| explained_variance | -0.0272 | +| learning_rate | 7.81e-05 | +| loss | -0.0265 | +| n_updates | 12028 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000208 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.268 | +| time/ | | +| fps | 1376 | +| iterations | 3009 | +| time_elapsed | 4475 | +| total_timesteps | 6162432 | +| train/ | | +| approx_kl | 0.013439645 | +| clip_fraction | 0.358 | +| clip_range | 0.073 | +| entropy_loss | -7.44 | +| explained_variance | -0.0317 | +| learning_rate | 7.8e-05 | +| loss | -0.0344 | +| n_updates | 12032 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000274 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.268 | +| time/ | | +| fps | 1376 | +| iterations | 3010 | +| time_elapsed | 4476 | +| total_timesteps | 6164480 | +| train/ | | +| approx_kl | 0.012299057 | +| clip_fraction | 0.359 | +| clip_range | 0.073 | +| entropy_loss | -7.53 | +| explained_variance | -0.0283 | +| learning_rate | 7.8e-05 | +| loss | -0.0372 | +| n_updates | 12036 | +| policy_gradient_loss | -0.0234 | +| value_loss | 0.000169 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.27 | +| time/ | | +| fps | 1376 | +| iterations | 3011 | +| time_elapsed | 4478 | +| total_timesteps | 6166528 | +| train/ | | +| approx_kl | 0.013532996 | +| clip_fraction | 0.389 | +| clip_range | 0.0729 | +| entropy_loss | -7.5 | +| explained_variance | -0.122 | +| learning_rate | 7.79e-05 | +| loss | -0.04 | +| n_updates | 12040 | +| policy_gradient_loss | -0.0222 | +| value_loss | 0.000221 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.272 | +| time/ | | +| fps | 1377 | +| iterations | 3012 | +| time_elapsed | 4479 | +| total_timesteps | 6168576 | +| train/ | | +| approx_kl | 0.015920429 | +| clip_fraction | 0.346 | +| clip_range | 0.0729 | +| entropy_loss | -7.54 | +| explained_variance | -0.382 | +| learning_rate | 7.79e-05 | +| loss | -0.0349 | +| n_updates | 12044 | +| policy_gradient_loss | -0.0225 | +| value_loss | 0.000125 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.267 | +| time/ | | +| fps | 1377 | +| iterations | 3013 | +| time_elapsed | 4481 | +| total_timesteps | 6170624 | +| train/ | | +| approx_kl | 0.014096937 | +| clip_fraction | 0.345 | +| clip_range | 0.0729 | +| entropy_loss | -7.42 | +| explained_variance | -0.00288 | +| learning_rate | 7.79e-05 | +| loss | -0.0303 | +| n_updates | 12048 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000313 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.265 | +| time/ | | +| fps | 1377 | +| iterations | 3014 | +| time_elapsed | 4482 | +| total_timesteps | 6172672 | +| train/ | | +| approx_kl | 0.015857087 | +| clip_fraction | 0.369 | +| clip_range | 0.0729 | +| entropy_loss | -7.54 | +| explained_variance | -0.365 | +| learning_rate | 7.78e-05 | +| loss | -0.0386 | +| n_updates | 12052 | +| policy_gradient_loss | -0.026 | +| value_loss | 0.000108 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.273 | +| time/ | | +| fps | 1377 | +| iterations | 3015 | +| time_elapsed | 4483 | +| total_timesteps | 6174720 | +| train/ | | +| approx_kl | 0.014142392 | +| clip_fraction | 0.37 | +| clip_range | 0.0728 | +| entropy_loss | -7.44 | +| explained_variance | -0.264 | +| learning_rate | 7.78e-05 | +| loss | -0.0324 | +| n_updates | 12056 | +| policy_gradient_loss | -0.0239 | +| value_loss | 9.03e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.28 | +| time/ | | +| fps | 1377 | +| iterations | 3016 | +| time_elapsed | 4485 | +| total_timesteps | 6176768 | +| train/ | | +| approx_kl | 0.014021399 | +| clip_fraction | 0.343 | +| clip_range | 0.0728 | +| entropy_loss | -7.49 | +| explained_variance | -0.0147 | +| learning_rate | 7.77e-05 | +| loss | -0.0298 | +| n_updates | 12060 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000273 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 1377 | +| iterations | 3017 | +| time_elapsed | 4486 | +| total_timesteps | 6178816 | +| train/ | | +| approx_kl | 0.0130683575 | +| clip_fraction | 0.343 | +| clip_range | 0.0728 | +| entropy_loss | -7.41 | +| explained_variance | -0.0504 | +| learning_rate | 7.77e-05 | +| loss | -0.0285 | +| n_updates | 12064 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000276 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.277 | +| time/ | | +| fps | 1377 | +| iterations | 3018 | +| time_elapsed | 4488 | +| total_timesteps | 6180864 | +| train/ | | +| approx_kl | 0.015203988 | +| clip_fraction | 0.359 | +| clip_range | 0.0728 | +| entropy_loss | -7.46 | +| explained_variance | -0.0811 | +| learning_rate | 7.77e-05 | +| loss | -0.0406 | +| n_updates | 12068 | +| policy_gradient_loss | -0.0226 | +| value_loss | 0.000208 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 1377 | +| iterations | 3019 | +| time_elapsed | 4489 | +| total_timesteps | 6182912 | +| train/ | | +| approx_kl | 0.013501809 | +| clip_fraction | 0.368 | +| clip_range | 0.0727 | +| entropy_loss | -7.55 | +| explained_variance | -0.0646 | +| learning_rate | 7.76e-05 | +| loss | -0.0342 | +| n_updates | 12072 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000196 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 1377 | +| iterations | 3020 | +| time_elapsed | 4491 | +| total_timesteps | 6184960 | +| train/ | | +| approx_kl | 0.017082406 | +| clip_fraction | 0.391 | +| clip_range | 0.0727 | +| entropy_loss | -7.58 | +| explained_variance | -0.133 | +| learning_rate | 7.76e-05 | +| loss | -0.0398 | +| n_updates | 12076 | +| policy_gradient_loss | -0.0245 | +| value_loss | 0.000152 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.286 | +| time/ | | +| fps | 1377 | +| iterations | 3021 | +| time_elapsed | 4492 | +| total_timesteps | 6187008 | +| train/ | | +| approx_kl | 0.016210882 | +| clip_fraction | 0.366 | +| clip_range | 0.0727 | +| entropy_loss | -7.53 | +| explained_variance | -0.0475 | +| learning_rate | 7.75e-05 | +| loss | -0.0394 | +| n_updates | 12080 | +| policy_gradient_loss | -0.0237 | +| value_loss | 0.000144 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 1377 | +| iterations | 3022 | +| time_elapsed | 4493 | +| total_timesteps | 6189056 | +| train/ | | +| approx_kl | 0.01495547 | +| clip_fraction | 0.358 | +| clip_range | 0.0727 | +| entropy_loss | -7.44 | +| explained_variance | -0.134 | +| learning_rate | 7.75e-05 | +| loss | -0.0343 | +| n_updates | 12084 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000148 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 1377 | +| iterations | 3023 | +| time_elapsed | 4495 | +| total_timesteps | 6191104 | +| train/ | | +| approx_kl | 0.011312608 | +| clip_fraction | 0.321 | +| clip_range | 0.0726 | +| entropy_loss | -7.45 | +| explained_variance | -0.133 | +| learning_rate | 7.75e-05 | +| loss | -0.0272 | +| n_updates | 12088 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000247 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 1377 | +| iterations | 3024 | +| time_elapsed | 4496 | +| total_timesteps | 6193152 | +| train/ | | +| approx_kl | 0.014893971 | +| clip_fraction | 0.388 | +| clip_range | 0.0726 | +| entropy_loss | -7.51 | +| explained_variance | -0.225 | +| learning_rate | 7.74e-05 | +| loss | -0.0463 | +| n_updates | 12092 | +| policy_gradient_loss | -0.0238 | +| value_loss | 7.67e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.276 | +| time/ | | +| fps | 1377 | +| iterations | 3025 | +| time_elapsed | 4498 | +| total_timesteps | 6195200 | +| train/ | | +| approx_kl | 0.01841252 | +| clip_fraction | 0.378 | +| clip_range | 0.0726 | +| entropy_loss | -7.58 | +| explained_variance | -0.121 | +| learning_rate | 7.74e-05 | +| loss | -0.0349 | +| n_updates | 12096 | +| policy_gradient_loss | -0.0219 | +| value_loss | 0.000169 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.276 | +| time/ | | +| fps | 1377 | +| iterations | 3026 | +| time_elapsed | 4499 | +| total_timesteps | 6197248 | +| train/ | | +| approx_kl | 0.016753482 | +| clip_fraction | 0.367 | +| clip_range | 0.0726 | +| entropy_loss | -7.52 | +| explained_variance | -0.075 | +| learning_rate | 7.73e-05 | +| loss | -0.0316 | +| n_updates | 12100 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000179 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.277 | +| time/ | | +| fps | 1377 | +| iterations | 3027 | +| time_elapsed | 4501 | +| total_timesteps | 6199296 | +| train/ | | +| approx_kl | 0.014746103 | +| clip_fraction | 0.357 | +| clip_range | 0.0725 | +| entropy_loss | -7.6 | +| explained_variance | -0.24 | +| learning_rate | 7.73e-05 | +| loss | -0.0366 | +| n_updates | 12104 | +| policy_gradient_loss | -0.0231 | +| value_loss | 0.00011 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 1377 | +| iterations | 3028 | +| time_elapsed | 4502 | +| total_timesteps | 6201344 | +| train/ | | +| approx_kl | 0.015924763 | +| clip_fraction | 0.368 | +| clip_range | 0.0725 | +| entropy_loss | -7.39 | +| explained_variance | -0.0334 | +| learning_rate | 7.73e-05 | +| loss | -0.0349 | +| n_updates | 12108 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000175 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.267 | +| time/ | | +| fps | 1377 | +| iterations | 3029 | +| time_elapsed | 4504 | +| total_timesteps | 6203392 | +| train/ | | +| approx_kl | 0.01889298 | +| clip_fraction | 0.401 | +| clip_range | 0.0725 | +| entropy_loss | -7.48 | +| explained_variance | -0.0839 | +| learning_rate | 7.72e-05 | +| loss | -0.0398 | +| n_updates | 12112 | +| policy_gradient_loss | -0.0238 | +| value_loss | 0.000186 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.267 | +| time/ | | +| fps | 1377 | +| iterations | 3030 | +| time_elapsed | 4505 | +| total_timesteps | 6205440 | +| train/ | | +| approx_kl | 0.017737616 | +| clip_fraction | 0.368 | +| clip_range | 0.0725 | +| entropy_loss | -7.36 | +| explained_variance | 0.0295 | +| learning_rate | 7.72e-05 | +| loss | -0.0326 | +| n_updates | 12116 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000215 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.267 | +| time/ | | +| fps | 1377 | +| iterations | 3031 | +| time_elapsed | 4506 | +| total_timesteps | 6207488 | +| train/ | | +| approx_kl | 0.016613636 | +| clip_fraction | 0.367 | +| clip_range | 0.0724 | +| entropy_loss | -7.54 | +| explained_variance | -0.167 | +| learning_rate | 7.71e-05 | +| loss | -0.034 | +| n_updates | 12120 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000156 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.27 | +| time/ | | +| fps | 1377 | +| iterations | 3032 | +| time_elapsed | 4508 | +| total_timesteps | 6209536 | +| train/ | | +| approx_kl | 0.016871784 | +| clip_fraction | 0.349 | +| clip_range | 0.0724 | +| entropy_loss | -7.52 | +| explained_variance | -0.0421 | +| learning_rate | 7.71e-05 | +| loss | -0.0356 | +| n_updates | 12124 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000238 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.27 | +| time/ | | +| fps | 1377 | +| iterations | 3033 | +| time_elapsed | 4509 | +| total_timesteps | 6211584 | +| train/ | | +| approx_kl | 0.017380912 | +| clip_fraction | 0.353 | +| clip_range | 0.0724 | +| entropy_loss | -7.5 | +| explained_variance | -0.144 | +| learning_rate | 7.71e-05 | +| loss | -0.0306 | +| n_updates | 12128 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000239 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.272 | +| time/ | | +| fps | 1377 | +| iterations | 3034 | +| time_elapsed | 4511 | +| total_timesteps | 6213632 | +| train/ | | +| approx_kl | 0.0154671045 | +| clip_fraction | 0.382 | +| clip_range | 0.0724 | +| entropy_loss | -7.54 | +| explained_variance | -0.0876 | +| learning_rate | 7.7e-05 | +| loss | -0.0374 | +| n_updates | 12132 | +| policy_gradient_loss | -0.0249 | +| value_loss | 0.000136 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.263 | +| time/ | | +| fps | 1377 | +| iterations | 3035 | +| time_elapsed | 4512 | +| total_timesteps | 6215680 | +| train/ | | +| approx_kl | 0.01379912 | +| clip_fraction | 0.346 | +| clip_range | 0.0723 | +| entropy_loss | -7.43 | +| explained_variance | 0.0563 | +| learning_rate | 7.7e-05 | +| loss | -0.0305 | +| n_updates | 12136 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000274 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.268 | +| time/ | | +| fps | 1377 | +| iterations | 3036 | +| time_elapsed | 4514 | +| total_timesteps | 6217728 | +| train/ | | +| approx_kl | 0.015110544 | +| clip_fraction | 0.383 | +| clip_range | 0.0723 | +| entropy_loss | -7.55 | +| explained_variance | -0.638 | +| learning_rate | 7.69e-05 | +| loss | -0.0452 | +| n_updates | 12140 | +| policy_gradient_loss | -0.0274 | +| value_loss | 6.88e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.274 | +| time/ | | +| fps | 1377 | +| iterations | 3037 | +| time_elapsed | 4515 | +| total_timesteps | 6219776 | +| train/ | | +| approx_kl | 0.014993679 | +| clip_fraction | 0.354 | +| clip_range | 0.0723 | +| entropy_loss | -7.3 | +| explained_variance | -0.114 | +| learning_rate | 7.69e-05 | +| loss | -0.025 | +| n_updates | 12144 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000228 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.274 | +| time/ | | +| fps | 1377 | +| iterations | 3038 | +| time_elapsed | 4516 | +| total_timesteps | 6221824 | +| train/ | | +| approx_kl | 0.01635261 | +| clip_fraction | 0.375 | +| clip_range | 0.0723 | +| entropy_loss | -7.35 | +| explained_variance | -0.144 | +| learning_rate | 7.68e-05 | +| loss | -0.036 | +| n_updates | 12148 | +| policy_gradient_loss | -0.0229 | +| value_loss | 0.000166 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.274 | +| time/ | | +| fps | 1377 | +| iterations | 3039 | +| time_elapsed | 4518 | +| total_timesteps | 6223872 | +| train/ | | +| approx_kl | 0.016927142 | +| clip_fraction | 0.368 | +| clip_range | 0.0722 | +| entropy_loss | -7.52 | +| explained_variance | -0.0915 | +| learning_rate | 7.68e-05 | +| loss | -0.0376 | +| n_updates | 12152 | +| policy_gradient_loss | -0.0221 | +| value_loss | 0.000181 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.274 | +| time/ | | +| fps | 1377 | +| iterations | 3040 | +| time_elapsed | 4519 | +| total_timesteps | 6225920 | +| train/ | | +| approx_kl | 0.017182913 | +| clip_fraction | 0.402 | +| clip_range | 0.0722 | +| entropy_loss | -7.55 | +| explained_variance | -0.301 | +| learning_rate | 7.68e-05 | +| loss | -0.0342 | +| n_updates | 12156 | +| policy_gradient_loss | -0.0232 | +| value_loss | 0.000112 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.271 | +| time/ | | +| fps | 1377 | +| iterations | 3041 | +| time_elapsed | 4521 | +| total_timesteps | 6227968 | +| train/ | | +| approx_kl | 0.015174031 | +| clip_fraction | 0.377 | +| clip_range | 0.0722 | +| entropy_loss | -7.48 | +| explained_variance | -0.135 | +| learning_rate | 7.67e-05 | +| loss | -0.0358 | +| n_updates | 12160 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000141 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.266 | +| time/ | | +| fps | 1377 | +| iterations | 3042 | +| time_elapsed | 4522 | +| total_timesteps | 6230016 | +| train/ | | +| approx_kl | 0.01529219 | +| clip_fraction | 0.373 | +| clip_range | 0.0722 | +| entropy_loss | -7.4 | +| explained_variance | -0.137 | +| learning_rate | 7.67e-05 | +| loss | -0.0351 | +| n_updates | 12164 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000193 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.267 | +| time/ | | +| fps | 1377 | +| iterations | 3043 | +| time_elapsed | 4524 | +| total_timesteps | 6232064 | +| train/ | | +| approx_kl | 0.016787507 | +| clip_fraction | 0.319 | +| clip_range | 0.0721 | +| entropy_loss | -7.51 | +| explained_variance | -0.19 | +| learning_rate | 7.66e-05 | +| loss | -0.0269 | +| n_updates | 12168 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000196 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.265 | +| time/ | | +| fps | 1377 | +| iterations | 3044 | +| time_elapsed | 4525 | +| total_timesteps | 6234112 | +| train/ | | +| approx_kl | 0.013955305 | +| clip_fraction | 0.374 | +| clip_range | 0.0721 | +| entropy_loss | -7.42 | +| explained_variance | -0.114 | +| learning_rate | 7.66e-05 | +| loss | -0.0354 | +| n_updates | 12172 | +| policy_gradient_loss | -0.0225 | +| value_loss | 0.000326 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.274 | +| time/ | | +| fps | 1377 | +| iterations | 3045 | +| time_elapsed | 4527 | +| total_timesteps | 6236160 | +| train/ | | +| approx_kl | 0.016151827 | +| clip_fraction | 0.395 | +| clip_range | 0.0721 | +| entropy_loss | -7.25 | +| explained_variance | -0.134 | +| learning_rate | 7.66e-05 | +| loss | -0.0362 | +| n_updates | 12176 | +| policy_gradient_loss | -0.0228 | +| value_loss | 0.000279 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.276 | +| time/ | | +| fps | 1377 | +| iterations | 3046 | +| time_elapsed | 4528 | +| total_timesteps | 6238208 | +| train/ | | +| approx_kl | 0.012965223 | +| clip_fraction | 0.343 | +| clip_range | 0.072 | +| entropy_loss | -7.41 | +| explained_variance | -0.0253 | +| learning_rate | 7.65e-05 | +| loss | -0.0319 | +| n_updates | 12180 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000388 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.277 | +| time/ | | +| fps | 1377 | +| iterations | 3047 | +| time_elapsed | 4529 | +| total_timesteps | 6240256 | +| train/ | | +| approx_kl | 0.013211316 | +| clip_fraction | 0.381 | +| clip_range | 0.072 | +| entropy_loss | -7.36 | +| explained_variance | -0.219 | +| learning_rate | 7.65e-05 | +| loss | -0.0313 | +| n_updates | 12184 | +| policy_gradient_loss | -0.0223 | +| value_loss | 0.000284 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.28 | +| time/ | | +| fps | 1377 | +| iterations | 3048 | +| time_elapsed | 4531 | +| total_timesteps | 6242304 | +| train/ | | +| approx_kl | 0.015740369 | +| clip_fraction | 0.376 | +| clip_range | 0.072 | +| entropy_loss | -7.36 | +| explained_variance | -0.0581 | +| learning_rate | 7.64e-05 | +| loss | -0.036 | +| n_updates | 12188 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000194 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.278 | +| time/ | | +| fps | 1377 | +| iterations | 3049 | +| time_elapsed | 4532 | +| total_timesteps | 6244352 | +| train/ | | +| approx_kl | 0.014910482 | +| clip_fraction | 0.351 | +| clip_range | 0.072 | +| entropy_loss | -7.33 | +| explained_variance | 0.0266 | +| learning_rate | 7.64e-05 | +| loss | -0.0295 | +| n_updates | 12192 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000279 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.278 | +| time/ | | +| fps | 1377 | +| iterations | 3050 | +| time_elapsed | 4534 | +| total_timesteps | 6246400 | +| train/ | | +| approx_kl | 0.0153451525 | +| clip_fraction | 0.355 | +| clip_range | 0.0719 | +| entropy_loss | -7.45 | +| explained_variance | -0.307 | +| learning_rate | 7.64e-05 | +| loss | -0.0356 | +| n_updates | 12196 | +| policy_gradient_loss | -0.0223 | +| value_loss | 0.000209 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 1377 | +| iterations | 3051 | +| time_elapsed | 4535 | +| total_timesteps | 6248448 | +| train/ | | +| approx_kl | 0.014567794 | +| clip_fraction | 0.369 | +| clip_range | 0.0719 | +| entropy_loss | -7.47 | +| explained_variance | -0.15 | +| learning_rate | 7.63e-05 | +| loss | -0.0336 | +| n_updates | 12200 | +| policy_gradient_loss | -0.0235 | +| value_loss | 0.000128 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 1377 | +| iterations | 3052 | +| time_elapsed | 4537 | +| total_timesteps | 6250496 | +| train/ | | +| approx_kl | 0.017406434 | +| clip_fraction | 0.383 | +| clip_range | 0.0719 | +| entropy_loss | -7.44 | +| explained_variance | -0.084 | +| learning_rate | 7.63e-05 | +| loss | -0.0338 | +| n_updates | 12204 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000244 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.283 | +| time/ | | +| fps | 1377 | +| iterations | 3053 | +| time_elapsed | 4538 | +| total_timesteps | 6252544 | +| train/ | | +| approx_kl | 0.015631951 | +| clip_fraction | 0.384 | +| clip_range | 0.0719 | +| entropy_loss | -7.49 | +| explained_variance | -0.185 | +| learning_rate | 7.62e-05 | +| loss | -0.0363 | +| n_updates | 12208 | +| policy_gradient_loss | -0.0225 | +| value_loss | 0.000124 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.283 | +| time/ | | +| fps | 1377 | +| iterations | 3054 | +| time_elapsed | 4539 | +| total_timesteps | 6254592 | +| train/ | | +| approx_kl | 0.01690789 | +| clip_fraction | 0.376 | +| clip_range | 0.0718 | +| entropy_loss | -7.44 | +| explained_variance | -0.16 | +| learning_rate | 7.62e-05 | +| loss | -0.0329 | +| n_updates | 12212 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000195 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.283 | +| time/ | | +| fps | 1377 | +| iterations | 3055 | +| time_elapsed | 4541 | +| total_timesteps | 6256640 | +| train/ | | +| approx_kl | 0.015662719 | +| clip_fraction | 0.386 | +| clip_range | 0.0718 | +| entropy_loss | -7.46 | +| explained_variance | -0.208 | +| learning_rate | 7.62e-05 | +| loss | -0.034 | +| n_updates | 12216 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.00013 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.284 | +| time/ | | +| fps | 1377 | +| iterations | 3056 | +| time_elapsed | 4542 | +| total_timesteps | 6258688 | +| train/ | | +| approx_kl | 0.015727703 | +| clip_fraction | 0.362 | +| clip_range | 0.0718 | +| entropy_loss | -7.5 | +| explained_variance | -0.0913 | +| learning_rate | 7.61e-05 | +| loss | -0.0304 | +| n_updates | 12220 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000215 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.284 | +| time/ | | +| fps | 1377 | +| iterations | 3057 | +| time_elapsed | 4544 | +| total_timesteps | 6260736 | +| train/ | | +| approx_kl | 0.013449095 | +| clip_fraction | 0.39 | +| clip_range | 0.0718 | +| entropy_loss | -7.42 | +| explained_variance | -0.00488 | +| learning_rate | 7.61e-05 | +| loss | -0.0326 | +| n_updates | 12224 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000153 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 1377 | +| iterations | 3058 | +| time_elapsed | 4545 | +| total_timesteps | 6262784 | +| train/ | | +| approx_kl | 0.017527469 | +| clip_fraction | 0.39 | +| clip_range | 0.0717 | +| entropy_loss | -7.41 | +| explained_variance | -0.248 | +| learning_rate | 7.6e-05 | +| loss | -0.0324 | +| n_updates | 12228 | +| policy_gradient_loss | -0.0233 | +| value_loss | 0.00014 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.286 | +| time/ | | +| fps | 1377 | +| iterations | 3059 | +| time_elapsed | 4547 | +| total_timesteps | 6264832 | +| train/ | | +| approx_kl | 0.015899822 | +| clip_fraction | 0.357 | +| clip_range | 0.0717 | +| entropy_loss | -7.36 | +| explained_variance | 0.021 | +| learning_rate | 7.6e-05 | +| loss | -0.0316 | +| n_updates | 12232 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000204 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.286 | +| time/ | | +| fps | 1377 | +| iterations | 3060 | +| time_elapsed | 4548 | +| total_timesteps | 6266880 | +| train/ | | +| approx_kl | 0.013714392 | +| clip_fraction | 0.377 | +| clip_range | 0.0717 | +| entropy_loss | -7.39 | +| explained_variance | -0.0633 | +| learning_rate | 7.6e-05 | +| loss | -0.0314 | +| n_updates | 12236 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000182 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.284 | +| time/ | | +| fps | 1377 | +| iterations | 3061 | +| time_elapsed | 4549 | +| total_timesteps | 6268928 | +| train/ | | +| approx_kl | 0.01524237 | +| clip_fraction | 0.372 | +| clip_range | 0.0717 | +| entropy_loss | -7.51 | +| explained_variance | -0.286 | +| learning_rate | 7.59e-05 | +| loss | -0.0397 | +| n_updates | 12240 | +| policy_gradient_loss | -0.0247 | +| value_loss | 9.12e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.284 | +| time/ | | +| fps | 1377 | +| iterations | 3062 | +| time_elapsed | 4551 | +| total_timesteps | 6270976 | +| train/ | | +| approx_kl | 0.012534152 | +| clip_fraction | 0.391 | +| clip_range | 0.0716 | +| entropy_loss | -7.49 | +| explained_variance | -0.1 | +| learning_rate | 7.59e-05 | +| loss | -0.0324 | +| n_updates | 12244 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000114 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.278 | +| time/ | | +| fps | 1377 | +| iterations | 3063 | +| time_elapsed | 4552 | +| total_timesteps | 6273024 | +| train/ | | +| approx_kl | 0.012437342 | +| clip_fraction | 0.353 | +| clip_range | 0.0716 | +| entropy_loss | -7.48 | +| explained_variance | -0.0713 | +| learning_rate | 7.58e-05 | +| loss | -0.0364 | +| n_updates | 12248 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000163 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.276 | +| time/ | | +| fps | 1377 | +| iterations | 3064 | +| time_elapsed | 4554 | +| total_timesteps | 6275072 | +| train/ | | +| approx_kl | 0.014293785 | +| clip_fraction | 0.36 | +| clip_range | 0.0716 | +| entropy_loss | -7.45 | +| explained_variance | -0.0207 | +| learning_rate | 7.58e-05 | +| loss | -0.033 | +| n_updates | 12252 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000273 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.276 | +| time/ | | +| fps | 1377 | +| iterations | 3065 | +| time_elapsed | 4555 | +| total_timesteps | 6277120 | +| train/ | | +| approx_kl | 0.013714909 | +| clip_fraction | 0.379 | +| clip_range | 0.0716 | +| entropy_loss | -7.39 | +| explained_variance | -0.251 | +| learning_rate | 7.58e-05 | +| loss | -0.0308 | +| n_updates | 12256 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.284 | +| time/ | | +| fps | 1377 | +| iterations | 3066 | +| time_elapsed | 4557 | +| total_timesteps | 6279168 | +| train/ | | +| approx_kl | 0.013330974 | +| clip_fraction | 0.361 | +| clip_range | 0.0715 | +| entropy_loss | -7.53 | +| explained_variance | -0.00281 | +| learning_rate | 7.57e-05 | +| loss | -0.0308 | +| n_updates | 12260 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000166 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 1377 | +| iterations | 3067 | +| time_elapsed | 4558 | +| total_timesteps | 6281216 | +| train/ | | +| approx_kl | 0.012925288 | +| clip_fraction | 0.382 | +| clip_range | 0.0715 | +| entropy_loss | -7.51 | +| explained_variance | -0.0355 | +| learning_rate | 7.57e-05 | +| loss | -0.0301 | +| n_updates | 12264 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.00029 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.302 | +| time/ | | +| fps | 1377 | +| iterations | 3068 | +| time_elapsed | 4559 | +| total_timesteps | 6283264 | +| train/ | | +| approx_kl | 0.012696216 | +| clip_fraction | 0.355 | +| clip_range | 0.0715 | +| entropy_loss | -7.4 | +| explained_variance | -0.124 | +| learning_rate | 7.56e-05 | +| loss | -0.0366 | +| n_updates | 12268 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000363 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 1377 | +| iterations | 3069 | +| time_elapsed | 4561 | +| total_timesteps | 6285312 | +| train/ | | +| approx_kl | 0.012749317 | +| clip_fraction | 0.359 | +| clip_range | 0.0715 | +| entropy_loss | -7.57 | +| explained_variance | -0.202 | +| learning_rate | 7.56e-05 | +| loss | -0.0375 | +| n_updates | 12272 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000188 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 1377 | +| iterations | 3070 | +| time_elapsed | 4562 | +| total_timesteps | 6287360 | +| train/ | | +| approx_kl | 0.011500188 | +| clip_fraction | 0.339 | +| clip_range | 0.0714 | +| entropy_loss | -7.51 | +| explained_variance | -0.0732 | +| learning_rate | 7.56e-05 | +| loss | -0.0326 | +| n_updates | 12276 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000264 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.298 | +| time/ | | +| fps | 1377 | +| iterations | 3071 | +| time_elapsed | 4564 | +| total_timesteps | 6289408 | +| train/ | | +| approx_kl | 0.014322826 | +| clip_fraction | 0.384 | +| clip_range | 0.0714 | +| entropy_loss | -7.61 | +| explained_variance | -0.324 | +| learning_rate | 7.55e-05 | +| loss | -0.034 | +| n_updates | 12280 | +| policy_gradient_loss | -0.0232 | +| value_loss | 0.000142 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.298 | +| time/ | | +| fps | 1378 | +| iterations | 3072 | +| time_elapsed | 4565 | +| total_timesteps | 6291456 | +| train/ | | +| approx_kl | 0.014555922 | +| clip_fraction | 0.373 | +| clip_range | 0.0714 | +| entropy_loss | -7.53 | +| explained_variance | -0.129 | +| learning_rate | 7.55e-05 | +| loss | -0.0327 | +| n_updates | 12284 | +| policy_gradient_loss | -0.0221 | +| value_loss | 0.000141 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 1378 | +| iterations | 3073 | +| time_elapsed | 4567 | +| total_timesteps | 6293504 | +| train/ | | +| approx_kl | 0.012534686 | +| clip_fraction | 0.355 | +| clip_range | 0.0714 | +| entropy_loss | -7.59 | +| explained_variance | -0.109 | +| learning_rate | 7.54e-05 | +| loss | -0.0332 | +| n_updates | 12288 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000194 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.294 | +| time/ | | +| fps | 1378 | +| iterations | 3074 | +| time_elapsed | 4568 | +| total_timesteps | 6295552 | +| train/ | | +| approx_kl | 0.015060926 | +| clip_fraction | 0.35 | +| clip_range | 0.0713 | +| entropy_loss | -7.59 | +| explained_variance | -0.0109 | +| learning_rate | 7.54e-05 | +| loss | -0.0298 | +| n_updates | 12292 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.00023 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.286 | +| time/ | | +| fps | 1378 | +| iterations | 3075 | +| time_elapsed | 4569 | +| total_timesteps | 6297600 | +| train/ | | +| approx_kl | 0.013988641 | +| clip_fraction | 0.355 | +| clip_range | 0.0713 | +| entropy_loss | -7.51 | +| explained_variance | -0.124 | +| learning_rate | 7.53e-05 | +| loss | -0.0281 | +| n_updates | 12296 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000196 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.286 | +| time/ | | +| fps | 1378 | +| iterations | 3076 | +| time_elapsed | 4571 | +| total_timesteps | 6299648 | +| train/ | | +| approx_kl | 0.014159012 | +| clip_fraction | 0.387 | +| clip_range | 0.0713 | +| entropy_loss | -7.4 | +| explained_variance | -0.0758 | +| learning_rate | 7.53e-05 | +| loss | -0.0384 | +| n_updates | 12300 | +| policy_gradient_loss | -0.0248 | +| value_loss | 0.000121 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.284 | +| time/ | | +| fps | 1378 | +| iterations | 3077 | +| time_elapsed | 4572 | +| total_timesteps | 6301696 | +| train/ | | +| approx_kl | 0.01260812 | +| clip_fraction | 0.357 | +| clip_range | 0.0713 | +| entropy_loss | -7.65 | +| explained_variance | -0.199 | +| learning_rate | 7.53e-05 | +| loss | -0.0384 | +| n_updates | 12304 | +| policy_gradient_loss | -0.022 | +| value_loss | 9.65e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.286 | +| time/ | | +| fps | 1378 | +| iterations | 3078 | +| time_elapsed | 4574 | +| total_timesteps | 6303744 | +| train/ | | +| approx_kl | 0.015462281 | +| clip_fraction | 0.375 | +| clip_range | 0.0712 | +| entropy_loss | -7.45 | +| explained_variance | -0.0637 | +| learning_rate | 7.52e-05 | +| loss | -0.0307 | +| n_updates | 12308 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000141 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.286 | +| time/ | | +| fps | 1378 | +| iterations | 3079 | +| time_elapsed | 4575 | +| total_timesteps | 6305792 | +| train/ | | +| approx_kl | 0.017761938 | +| clip_fraction | 0.371 | +| clip_range | 0.0712 | +| entropy_loss | -7.54 | +| explained_variance | 0.0139 | +| learning_rate | 7.52e-05 | +| loss | -0.0342 | +| n_updates | 12312 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000176 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.284 | +| time/ | | +| fps | 1378 | +| iterations | 3080 | +| time_elapsed | 4577 | +| total_timesteps | 6307840 | +| train/ | | +| approx_kl | 0.0157521 | +| clip_fraction | 0.378 | +| clip_range | 0.0712 | +| entropy_loss | -7.51 | +| explained_variance | -0.0992 | +| learning_rate | 7.51e-05 | +| loss | -0.0382 | +| n_updates | 12316 | +| policy_gradient_loss | -0.0231 | +| value_loss | 0.000162 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.285 | +| time/ | | +| fps | 1378 | +| iterations | 3081 | +| time_elapsed | 4578 | +| total_timesteps | 6309888 | +| train/ | | +| approx_kl | 0.014040995 | +| clip_fraction | 0.355 | +| clip_range | 0.0712 | +| entropy_loss | -7.61 | +| explained_variance | -0.255 | +| learning_rate | 7.51e-05 | +| loss | -0.0315 | +| n_updates | 12320 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000188 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.285 | +| time/ | | +| fps | 1378 | +| iterations | 3082 | +| time_elapsed | 4580 | +| total_timesteps | 6311936 | +| train/ | | +| approx_kl | 0.014245714 | +| clip_fraction | 0.354 | +| clip_range | 0.0711 | +| entropy_loss | -7.45 | +| explained_variance | -0.0662 | +| learning_rate | 7.51e-05 | +| loss | -0.0276 | +| n_updates | 12324 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000276 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 1378 | +| iterations | 3083 | +| time_elapsed | 4581 | +| total_timesteps | 6313984 | +| train/ | | +| approx_kl | 0.013143078 | +| clip_fraction | 0.341 | +| clip_range | 0.0711 | +| entropy_loss | -7.58 | +| explained_variance | -0.155 | +| learning_rate | 7.5e-05 | +| loss | -0.0295 | +| n_updates | 12328 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000164 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.281 | +| time/ | | +| fps | 1378 | +| iterations | 3084 | +| time_elapsed | 4582 | +| total_timesteps | 6316032 | +| train/ | | +| approx_kl | 0.012476526 | +| clip_fraction | 0.362 | +| clip_range | 0.0711 | +| entropy_loss | -7.56 | +| explained_variance | -0.0687 | +| learning_rate | 7.5e-05 | +| loss | -0.0374 | +| n_updates | 12332 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000368 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.288 | +| time/ | | +| fps | 1378 | +| iterations | 3085 | +| time_elapsed | 4584 | +| total_timesteps | 6318080 | +| train/ | | +| approx_kl | 0.012735511 | +| clip_fraction | 0.386 | +| clip_range | 0.071 | +| entropy_loss | -7.55 | +| explained_variance | -0.315 | +| learning_rate | 7.49e-05 | +| loss | -0.0362 | +| n_updates | 12336 | +| policy_gradient_loss | -0.0241 | +| value_loss | 0.000144 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.288 | +| time/ | | +| fps | 1378 | +| iterations | 3086 | +| time_elapsed | 4586 | +| total_timesteps | 6320128 | +| train/ | | +| approx_kl | 0.01280861 | +| clip_fraction | 0.357 | +| clip_range | 0.071 | +| entropy_loss | -7.54 | +| explained_variance | -0.178 | +| learning_rate | 7.49e-05 | +| loss | -0.036 | +| n_updates | 12340 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000149 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 1378 | +| iterations | 3087 | +| time_elapsed | 4587 | +| total_timesteps | 6322176 | +| train/ | | +| approx_kl | 0.014194302 | +| clip_fraction | 0.336 | +| clip_range | 0.071 | +| entropy_loss | -7.67 | +| explained_variance | -0.0182 | +| learning_rate | 7.49e-05 | +| loss | -0.0338 | +| n_updates | 12344 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000201 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.294 | +| time/ | | +| fps | 1378 | +| iterations | 3088 | +| time_elapsed | 4589 | +| total_timesteps | 6324224 | +| train/ | | +| approx_kl | 0.011899223 | +| clip_fraction | 0.333 | +| clip_range | 0.071 | +| entropy_loss | -7.51 | +| explained_variance | 0.0126 | +| learning_rate | 7.48e-05 | +| loss | -0.0348 | +| n_updates | 12348 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000276 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.294 | +| time/ | | +| fps | 1378 | +| iterations | 3089 | +| time_elapsed | 4590 | +| total_timesteps | 6326272 | +| train/ | | +| approx_kl | 0.0147294765 | +| clip_fraction | 0.406 | +| clip_range | 0.0709 | +| entropy_loss | -7.4 | +| explained_variance | -0.4 | +| learning_rate | 7.48e-05 | +| loss | -0.0433 | +| n_updates | 12352 | +| policy_gradient_loss | -0.0276 | +| value_loss | 6.92e-05 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.292 | +| time/ | | +| fps | 1378 | +| iterations | 3090 | +| time_elapsed | 4591 | +| total_timesteps | 6328320 | +| train/ | | +| approx_kl | 0.0149258785 | +| clip_fraction | 0.384 | +| clip_range | 0.0709 | +| entropy_loss | -7.57 | +| explained_variance | -0.0306 | +| learning_rate | 7.47e-05 | +| loss | -0.041 | +| n_updates | 12356 | +| policy_gradient_loss | -0.0228 | +| value_loss | 0.000199 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.292 | +| time/ | | +| fps | 1378 | +| iterations | 3091 | +| time_elapsed | 4593 | +| total_timesteps | 6330368 | +| train/ | | +| approx_kl | 0.013580145 | +| clip_fraction | 0.352 | +| clip_range | 0.0709 | +| entropy_loss | -7.51 | +| explained_variance | 0.0373 | +| learning_rate | 7.47e-05 | +| loss | -0.0304 | +| n_updates | 12360 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000124 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.293 | +| time/ | | +| fps | 1378 | +| iterations | 3092 | +| time_elapsed | 4594 | +| total_timesteps | 6332416 | +| train/ | | +| approx_kl | 0.014006417 | +| clip_fraction | 0.369 | +| clip_range | 0.0709 | +| entropy_loss | -7.52 | +| explained_variance | 0.111 | +| learning_rate | 7.47e-05 | +| loss | -0.0337 | +| n_updates | 12364 | +| policy_gradient_loss | -0.0228 | +| value_loss | 0.000144 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.293 | +| time/ | | +| fps | 1378 | +| iterations | 3093 | +| time_elapsed | 4596 | +| total_timesteps | 6334464 | +| train/ | | +| approx_kl | 0.013305208 | +| clip_fraction | 0.357 | +| clip_range | 0.0708 | +| entropy_loss | -7.6 | +| explained_variance | -0.161 | +| learning_rate | 7.46e-05 | +| loss | -0.0373 | +| n_updates | 12368 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.00012 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.293 | +| time/ | | +| fps | 1378 | +| iterations | 3094 | +| time_elapsed | 4597 | +| total_timesteps | 6336512 | +| train/ | | +| approx_kl | 0.011954201 | +| clip_fraction | 0.342 | +| clip_range | 0.0708 | +| entropy_loss | -7.48 | +| explained_variance | 0.0077 | +| learning_rate | 7.46e-05 | +| loss | -0.0313 | +| n_updates | 12372 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000164 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.294 | +| time/ | | +| fps | 1378 | +| iterations | 3095 | +| time_elapsed | 4599 | +| total_timesteps | 6338560 | +| train/ | | +| approx_kl | 0.012395419 | +| clip_fraction | 0.349 | +| clip_range | 0.0708 | +| entropy_loss | -7.6 | +| explained_variance | -0.072 | +| learning_rate | 7.45e-05 | +| loss | -0.0309 | +| n_updates | 12376 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000152 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.294 | +| time/ | | +| fps | 1378 | +| iterations | 3096 | +| time_elapsed | 4600 | +| total_timesteps | 6340608 | +| train/ | | +| approx_kl | 0.013900722 | +| clip_fraction | 0.345 | +| clip_range | 0.0708 | +| entropy_loss | -7.57 | +| explained_variance | -0.00518 | +| learning_rate | 7.45e-05 | +| loss | -0.0286 | +| n_updates | 12380 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.00017 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.289 | +| time/ | | +| fps | 1378 | +| iterations | 3097 | +| time_elapsed | 4601 | +| total_timesteps | 6342656 | +| train/ | | +| approx_kl | 0.014118874 | +| clip_fraction | 0.357 | +| clip_range | 0.0707 | +| entropy_loss | -7.53 | +| explained_variance | -0.206 | +| learning_rate | 7.45e-05 | +| loss | -0.0274 | +| n_updates | 12384 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000121 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.294 | +| time/ | | +| fps | 1378 | +| iterations | 3098 | +| time_elapsed | 4603 | +| total_timesteps | 6344704 | +| train/ | | +| approx_kl | 0.014030213 | +| clip_fraction | 0.352 | +| clip_range | 0.0707 | +| entropy_loss | -7.54 | +| explained_variance | -0.107 | +| learning_rate | 7.44e-05 | +| loss | -0.0348 | +| n_updates | 12388 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000133 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.292 | +| time/ | | +| fps | 1378 | +| iterations | 3099 | +| time_elapsed | 4604 | +| total_timesteps | 6346752 | +| train/ | | +| approx_kl | 0.0153242415 | +| clip_fraction | 0.364 | +| clip_range | 0.0707 | +| entropy_loss | -7.55 | +| explained_variance | -0.151 | +| learning_rate | 7.44e-05 | +| loss | -0.0327 | +| n_updates | 12392 | +| policy_gradient_loss | -0.0226 | +| value_loss | 7.87e-05 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.294 | +| time/ | | +| fps | 1378 | +| iterations | 3100 | +| time_elapsed | 4606 | +| total_timesteps | 6348800 | +| train/ | | +| approx_kl | 0.0131486785 | +| clip_fraction | 0.335 | +| clip_range | 0.0707 | +| entropy_loss | -7.47 | +| explained_variance | -0.064 | +| learning_rate | 7.43e-05 | +| loss | -0.0351 | +| n_updates | 12396 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.0002 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.294 | +| time/ | | +| fps | 1378 | +| iterations | 3101 | +| time_elapsed | 4607 | +| total_timesteps | 6350848 | +| train/ | | +| approx_kl | 0.016291553 | +| clip_fraction | 0.371 | +| clip_range | 0.0706 | +| entropy_loss | -7.52 | +| explained_variance | -0.237 | +| learning_rate | 7.43e-05 | +| loss | -0.0361 | +| n_updates | 12400 | +| policy_gradient_loss | -0.024 | +| value_loss | 7.7e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.294 | +| time/ | | +| fps | 1378 | +| iterations | 3102 | +| time_elapsed | 4609 | +| total_timesteps | 6352896 | +| train/ | | +| approx_kl | 0.012832728 | +| clip_fraction | 0.338 | +| clip_range | 0.0706 | +| entropy_loss | -7.58 | +| explained_variance | -0.132 | +| learning_rate | 7.43e-05 | +| loss | -0.0306 | +| n_updates | 12404 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000108 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.287 | +| time/ | | +| fps | 1378 | +| iterations | 3103 | +| time_elapsed | 4610 | +| total_timesteps | 6354944 | +| train/ | | +| approx_kl | 0.012008041 | +| clip_fraction | 0.342 | +| clip_range | 0.0706 | +| entropy_loss | -7.66 | +| explained_variance | -0.0591 | +| learning_rate | 7.42e-05 | +| loss | -0.0351 | +| n_updates | 12408 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000116 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.287 | +| time/ | | +| fps | 1378 | +| iterations | 3104 | +| time_elapsed | 4612 | +| total_timesteps | 6356992 | +| train/ | | +| approx_kl | 0.01407947 | +| clip_fraction | 0.36 | +| clip_range | 0.0706 | +| entropy_loss | -7.46 | +| explained_variance | -0.177 | +| learning_rate | 7.42e-05 | +| loss | -0.0364 | +| n_updates | 12412 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000181 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.287 | +| time/ | | +| fps | 1378 | +| iterations | 3105 | +| time_elapsed | 4613 | +| total_timesteps | 6359040 | +| train/ | | +| approx_kl | 0.014608919 | +| clip_fraction | 0.352 | +| clip_range | 0.0705 | +| entropy_loss | -7.64 | +| explained_variance | -0.101 | +| learning_rate | 7.41e-05 | +| loss | -0.0304 | +| n_updates | 12416 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.287 | +| time/ | | +| fps | 1378 | +| iterations | 3106 | +| time_elapsed | 4615 | +| total_timesteps | 6361088 | +| train/ | | +| approx_kl | 0.014166132 | +| clip_fraction | 0.342 | +| clip_range | 0.0705 | +| entropy_loss | -7.51 | +| explained_variance | -0.162 | +| learning_rate | 7.41e-05 | +| loss | -0.0326 | +| n_updates | 12420 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000188 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.292 | +| time/ | | +| fps | 1378 | +| iterations | 3107 | +| time_elapsed | 4616 | +| total_timesteps | 6363136 | +| train/ | | +| approx_kl | 0.013547037 | +| clip_fraction | 0.348 | +| clip_range | 0.0705 | +| entropy_loss | -7.66 | +| explained_variance | -0.168 | +| learning_rate | 7.41e-05 | +| loss | -0.0344 | +| n_updates | 12424 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000147 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 1378 | +| iterations | 3108 | +| time_elapsed | 4617 | +| total_timesteps | 6365184 | +| train/ | | +| approx_kl | 0.011614174 | +| clip_fraction | 0.338 | +| clip_range | 0.0705 | +| entropy_loss | -7.55 | +| explained_variance | -0.104 | +| learning_rate | 7.4e-05 | +| loss | -0.0262 | +| n_updates | 12428 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000238 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 1378 | +| iterations | 3109 | +| time_elapsed | 4619 | +| total_timesteps | 6367232 | +| train/ | | +| approx_kl | 0.011802701 | +| clip_fraction | 0.347 | +| clip_range | 0.0704 | +| entropy_loss | -7.56 | +| explained_variance | -0.0423 | +| learning_rate | 7.4e-05 | +| loss | -0.031 | +| n_updates | 12432 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000232 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 1378 | +| iterations | 3110 | +| time_elapsed | 4620 | +| total_timesteps | 6369280 | +| train/ | | +| approx_kl | 0.013330285 | +| clip_fraction | 0.366 | +| clip_range | 0.0704 | +| entropy_loss | -7.53 | +| explained_variance | -0.148 | +| learning_rate | 7.39e-05 | +| loss | -0.0336 | +| n_updates | 12436 | +| policy_gradient_loss | -0.0228 | +| value_loss | 7.22e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.293 | +| time/ | | +| fps | 1378 | +| iterations | 3111 | +| time_elapsed | 4622 | +| total_timesteps | 6371328 | +| train/ | | +| approx_kl | 0.011827989 | +| clip_fraction | 0.332 | +| clip_range | 0.0704 | +| entropy_loss | -7.53 | +| explained_variance | -0.161 | +| learning_rate | 7.39e-05 | +| loss | -0.0289 | +| n_updates | 12440 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000247 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.292 | +| time/ | | +| fps | 1378 | +| iterations | 3112 | +| time_elapsed | 4623 | +| total_timesteps | 6373376 | +| train/ | | +| approx_kl | 0.011528527 | +| clip_fraction | 0.366 | +| clip_range | 0.0704 | +| entropy_loss | -7.64 | +| explained_variance | -0.0936 | +| learning_rate | 7.38e-05 | +| loss | -0.0324 | +| n_updates | 12444 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000204 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.294 | +| time/ | | +| fps | 1378 | +| iterations | 3113 | +| time_elapsed | 4625 | +| total_timesteps | 6375424 | +| train/ | | +| approx_kl | 0.011610822 | +| clip_fraction | 0.362 | +| clip_range | 0.0703 | +| entropy_loss | -7.67 | +| explained_variance | -0.0675 | +| learning_rate | 7.38e-05 | +| loss | -0.0259 | +| n_updates | 12448 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000148 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.294 | +| time/ | | +| fps | 1378 | +| iterations | 3114 | +| time_elapsed | 4626 | +| total_timesteps | 6377472 | +| train/ | | +| approx_kl | 0.01199515 | +| clip_fraction | 0.351 | +| clip_range | 0.0703 | +| entropy_loss | -7.72 | +| explained_variance | -0.0668 | +| learning_rate | 7.38e-05 | +| loss | -0.0346 | +| n_updates | 12452 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000114 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 1378 | +| iterations | 3115 | +| time_elapsed | 4628 | +| total_timesteps | 6379520 | +| train/ | | +| approx_kl | 0.01347715 | +| clip_fraction | 0.373 | +| clip_range | 0.0703 | +| entropy_loss | -7.64 | +| explained_variance | -0.241 | +| learning_rate | 7.37e-05 | +| loss | -0.0385 | +| n_updates | 12456 | +| policy_gradient_loss | -0.0211 | +| value_loss | 8e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 1378 | +| iterations | 3116 | +| time_elapsed | 4629 | +| total_timesteps | 6381568 | +| train/ | | +| approx_kl | 0.013208172 | +| clip_fraction | 0.351 | +| clip_range | 0.0703 | +| entropy_loss | -7.55 | +| explained_variance | -0.000979 | +| learning_rate | 7.37e-05 | +| loss | -0.0345 | +| n_updates | 12460 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000303 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.298 | +| time/ | | +| fps | 1378 | +| iterations | 3117 | +| time_elapsed | 4630 | +| total_timesteps | 6383616 | +| train/ | | +| approx_kl | 0.0127167385 | +| clip_fraction | 0.349 | +| clip_range | 0.0702 | +| entropy_loss | -7.53 | +| explained_variance | -0.0319 | +| learning_rate | 7.36e-05 | +| loss | -0.0339 | +| n_updates | 12464 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000164 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.292 | +| time/ | | +| fps | 1378 | +| iterations | 3118 | +| time_elapsed | 4632 | +| total_timesteps | 6385664 | +| train/ | | +| approx_kl | 0.013385236 | +| clip_fraction | 0.361 | +| clip_range | 0.0702 | +| entropy_loss | -7.54 | +| explained_variance | -0.0971 | +| learning_rate | 7.36e-05 | +| loss | -0.0367 | +| n_updates | 12468 | +| policy_gradient_loss | -0.0221 | +| value_loss | 0.000118 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.294 | +| time/ | | +| fps | 1378 | +| iterations | 3119 | +| time_elapsed | 4633 | +| total_timesteps | 6387712 | +| train/ | | +| approx_kl | 0.013645634 | +| clip_fraction | 0.345 | +| clip_range | 0.0702 | +| entropy_loss | -7.54 | +| explained_variance | -0.0338 | +| learning_rate | 7.36e-05 | +| loss | -0.0334 | +| n_updates | 12472 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.00024 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.293 | +| time/ | | +| fps | 1378 | +| iterations | 3120 | +| time_elapsed | 4635 | +| total_timesteps | 6389760 | +| train/ | | +| approx_kl | 0.0115170665 | +| clip_fraction | 0.351 | +| clip_range | 0.0702 | +| entropy_loss | -7.55 | +| explained_variance | 0.0206 | +| learning_rate | 7.35e-05 | +| loss | -0.0351 | +| n_updates | 12476 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000222 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.293 | +| time/ | | +| fps | 1378 | +| iterations | 3121 | +| time_elapsed | 4636 | +| total_timesteps | 6391808 | +| train/ | | +| approx_kl | 0.01300462 | +| clip_fraction | 0.359 | +| clip_range | 0.0701 | +| entropy_loss | -7.59 | +| explained_variance | -0.183 | +| learning_rate | 7.35e-05 | +| loss | -0.0321 | +| n_updates | 12480 | +| policy_gradient_loss | -0.0222 | +| value_loss | 0.000187 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.292 | +| time/ | | +| fps | 1378 | +| iterations | 3122 | +| time_elapsed | 4638 | +| total_timesteps | 6393856 | +| train/ | | +| approx_kl | 0.013265498 | +| clip_fraction | 0.342 | +| clip_range | 0.0701 | +| entropy_loss | -7.61 | +| explained_variance | -0.0535 | +| learning_rate | 7.34e-05 | +| loss | -0.0283 | +| n_updates | 12484 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000129 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.292 | +| time/ | | +| fps | 1378 | +| iterations | 3123 | +| time_elapsed | 4639 | +| total_timesteps | 6395904 | +| train/ | | +| approx_kl | 0.011970038 | +| clip_fraction | 0.342 | +| clip_range | 0.0701 | +| entropy_loss | -7.64 | +| explained_variance | -0.0732 | +| learning_rate | 7.34e-05 | +| loss | -0.0325 | +| n_updates | 12488 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000213 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 1378 | +| iterations | 3124 | +| time_elapsed | 4641 | +| total_timesteps | 6397952 | +| train/ | | +| approx_kl | 0.011642782 | +| clip_fraction | 0.36 | +| clip_range | 0.0701 | +| entropy_loss | -7.65 | +| explained_variance | -0.00797 | +| learning_rate | 7.34e-05 | +| loss | -0.0335 | +| n_updates | 12492 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000122 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 1378 | +| iterations | 3125 | +| time_elapsed | 4642 | +| total_timesteps | 6400000 | +| train/ | | +| approx_kl | 0.011656474 | +| clip_fraction | 0.348 | +| clip_range | 0.07 | +| entropy_loss | -7.51 | +| explained_variance | 0.0329 | +| learning_rate | 7.33e-05 | +| loss | -0.0298 | +| n_updates | 12496 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.00027 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.298 | +| time/ | | +| fps | 1378 | +| iterations | 3126 | +| time_elapsed | 4644 | +| total_timesteps | 6402048 | +| train/ | | +| approx_kl | 0.0128211435 | +| clip_fraction | 0.363 | +| clip_range | 0.07 | +| entropy_loss | -7.64 | +| explained_variance | -0.113 | +| learning_rate | 7.33e-05 | +| loss | -0.0378 | +| n_updates | 12500 | +| policy_gradient_loss | -0.0227 | +| value_loss | 0.000189 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 1378 | +| iterations | 3127 | +| time_elapsed | 4645 | +| total_timesteps | 6404096 | +| train/ | | +| approx_kl | 0.011969262 | +| clip_fraction | 0.34 | +| clip_range | 0.07 | +| entropy_loss | -7.65 | +| explained_variance | -0.153 | +| learning_rate | 7.32e-05 | +| loss | -0.0308 | +| n_updates | 12504 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000218 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1378 | +| iterations | 3128 | +| time_elapsed | 4647 | +| total_timesteps | 6406144 | +| train/ | | +| approx_kl | 0.011965592 | +| clip_fraction | 0.328 | +| clip_range | 0.0699 | +| entropy_loss | -7.54 | +| explained_variance | 0.00242 | +| learning_rate | 7.32e-05 | +| loss | -0.027 | +| n_updates | 12508 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.00028 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1378 | +| iterations | 3129 | +| time_elapsed | 4648 | +| total_timesteps | 6408192 | +| train/ | | +| approx_kl | 0.012779249 | +| clip_fraction | 0.352 | +| clip_range | 0.0699 | +| entropy_loss | -7.51 | +| explained_variance | -0.0761 | +| learning_rate | 7.32e-05 | +| loss | -0.0377 | +| n_updates | 12512 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000132 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1378 | +| iterations | 3130 | +| time_elapsed | 4650 | +| total_timesteps | 6410240 | +| train/ | | +| approx_kl | 0.013150131 | +| clip_fraction | 0.364 | +| clip_range | 0.0699 | +| entropy_loss | -7.63 | +| explained_variance | -0.0996 | +| learning_rate | 7.31e-05 | +| loss | -0.0341 | +| n_updates | 12516 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1378 | +| iterations | 3131 | +| time_elapsed | 4651 | +| total_timesteps | 6412288 | +| train/ | | +| approx_kl | 0.013436539 | +| clip_fraction | 0.366 | +| clip_range | 0.0699 | +| entropy_loss | -7.69 | +| explained_variance | -0.145 | +| learning_rate | 7.31e-05 | +| loss | -0.0348 | +| n_updates | 12520 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000133 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1378 | +| iterations | 3132 | +| time_elapsed | 4653 | +| total_timesteps | 6414336 | +| train/ | | +| approx_kl | 0.013272699 | +| clip_fraction | 0.339 | +| clip_range | 0.0698 | +| entropy_loss | -7.58 | +| explained_variance | -0.00195 | +| learning_rate | 7.3e-05 | +| loss | -0.0316 | +| n_updates | 12524 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000123 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 1378 | +| iterations | 3133 | +| time_elapsed | 4654 | +| total_timesteps | 6416384 | +| train/ | | +| approx_kl | 0.012059029 | +| clip_fraction | 0.355 | +| clip_range | 0.0698 | +| entropy_loss | -7.62 | +| explained_variance | -0.0329 | +| learning_rate | 7.3e-05 | +| loss | -0.0276 | +| n_updates | 12528 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000239 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.291 | +| time/ | | +| fps | 1378 | +| iterations | 3134 | +| time_elapsed | 4655 | +| total_timesteps | 6418432 | +| train/ | | +| approx_kl | 0.013827185 | +| clip_fraction | 0.381 | +| clip_range | 0.0698 | +| entropy_loss | -7.57 | +| explained_variance | -0.0895 | +| learning_rate | 7.3e-05 | +| loss | -0.0371 | +| n_updates | 12532 | +| policy_gradient_loss | -0.024 | +| value_loss | 0.000121 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.289 | +| time/ | | +| fps | 1378 | +| iterations | 3135 | +| time_elapsed | 4657 | +| total_timesteps | 6420480 | +| train/ | | +| approx_kl | 0.010571657 | +| clip_fraction | 0.34 | +| clip_range | 0.0698 | +| entropy_loss | -7.62 | +| explained_variance | -0.218 | +| learning_rate | 7.29e-05 | +| loss | -0.0321 | +| n_updates | 12536 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000168 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.29 | +| time/ | | +| fps | 1378 | +| iterations | 3136 | +| time_elapsed | 4658 | +| total_timesteps | 6422528 | +| train/ | | +| approx_kl | 0.012696888 | +| clip_fraction | 0.362 | +| clip_range | 0.0697 | +| entropy_loss | -7.59 | +| explained_variance | -0.261 | +| learning_rate | 7.29e-05 | +| loss | -0.0344 | +| n_updates | 12540 | +| policy_gradient_loss | -0.0225 | +| value_loss | 0.000116 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.288 | +| time/ | | +| fps | 1378 | +| iterations | 3137 | +| time_elapsed | 4660 | +| total_timesteps | 6424576 | +| train/ | | +| approx_kl | 0.011413768 | +| clip_fraction | 0.34 | +| clip_range | 0.0697 | +| entropy_loss | -7.6 | +| explained_variance | -0.077 | +| learning_rate | 7.28e-05 | +| loss | -0.032 | +| n_updates | 12544 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000253 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.284 | +| time/ | | +| fps | 1378 | +| iterations | 3138 | +| time_elapsed | 4661 | +| total_timesteps | 6426624 | +| train/ | | +| approx_kl | 0.014383032 | +| clip_fraction | 0.368 | +| clip_range | 0.0697 | +| entropy_loss | -7.54 | +| explained_variance | -0.364 | +| learning_rate | 7.28e-05 | +| loss | -0.038 | +| n_updates | 12548 | +| policy_gradient_loss | -0.0242 | +| value_loss | 7.28e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.29 | +| time/ | | +| fps | 1378 | +| iterations | 3139 | +| time_elapsed | 4663 | +| total_timesteps | 6428672 | +| train/ | | +| approx_kl | 0.011715602 | +| clip_fraction | 0.339 | +| clip_range | 0.0697 | +| entropy_loss | -7.46 | +| explained_variance | -0.134 | +| learning_rate | 7.28e-05 | +| loss | -0.0329 | +| n_updates | 12552 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000209 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.29 | +| time/ | | +| fps | 1378 | +| iterations | 3140 | +| time_elapsed | 4664 | +| total_timesteps | 6430720 | +| train/ | | +| approx_kl | 0.015174689 | +| clip_fraction | 0.38 | +| clip_range | 0.0696 | +| entropy_loss | -7.43 | +| explained_variance | -0.229 | +| learning_rate | 7.27e-05 | +| loss | -0.0393 | +| n_updates | 12556 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000168 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.29 | +| time/ | | +| fps | 1378 | +| iterations | 3141 | +| time_elapsed | 4666 | +| total_timesteps | 6432768 | +| train/ | | +| approx_kl | 0.011813025 | +| clip_fraction | 0.344 | +| clip_range | 0.0696 | +| entropy_loss | -7.67 | +| explained_variance | -0.112 | +| learning_rate | 7.27e-05 | +| loss | -0.0273 | +| n_updates | 12560 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000202 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.294 | +| time/ | | +| fps | 1378 | +| iterations | 3142 | +| time_elapsed | 4667 | +| total_timesteps | 6434816 | +| train/ | | +| approx_kl | 0.012341011 | +| clip_fraction | 0.355 | +| clip_range | 0.0696 | +| entropy_loss | -7.65 | +| explained_variance | -0.135 | +| learning_rate | 7.26e-05 | +| loss | -0.035 | +| n_updates | 12564 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000137 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.293 | +| time/ | | +| fps | 1378 | +| iterations | 3143 | +| time_elapsed | 4668 | +| total_timesteps | 6436864 | +| train/ | | +| approx_kl | 0.012288867 | +| clip_fraction | 0.356 | +| clip_range | 0.0696 | +| entropy_loss | -7.48 | +| explained_variance | -0.145 | +| learning_rate | 7.26e-05 | +| loss | -0.0338 | +| n_updates | 12568 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000135 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.295 | +| time/ | | +| fps | 1378 | +| iterations | 3144 | +| time_elapsed | 4670 | +| total_timesteps | 6438912 | +| train/ | | +| approx_kl | 0.01227948 | +| clip_fraction | 0.351 | +| clip_range | 0.0695 | +| entropy_loss | -7.58 | +| explained_variance | -0.409 | +| learning_rate | 7.26e-05 | +| loss | -0.0311 | +| n_updates | 12572 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000116 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.291 | +| time/ | | +| fps | 1378 | +| iterations | 3145 | +| time_elapsed | 4671 | +| total_timesteps | 6440960 | +| train/ | | +| approx_kl | 0.014514282 | +| clip_fraction | 0.328 | +| clip_range | 0.0695 | +| entropy_loss | -7.63 | +| explained_variance | -0.0555 | +| learning_rate | 7.25e-05 | +| loss | -0.0296 | +| n_updates | 12576 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000214 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.287 | +| time/ | | +| fps | 1378 | +| iterations | 3146 | +| time_elapsed | 4673 | +| total_timesteps | 6443008 | +| train/ | | +| approx_kl | 0.012010514 | +| clip_fraction | 0.314 | +| clip_range | 0.0695 | +| entropy_loss | -7.51 | +| explained_variance | -0.0722 | +| learning_rate | 7.25e-05 | +| loss | -0.0305 | +| n_updates | 12580 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000343 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.29 | +| time/ | | +| fps | 1378 | +| iterations | 3147 | +| time_elapsed | 4674 | +| total_timesteps | 6445056 | +| train/ | | +| approx_kl | 0.013120668 | +| clip_fraction | 0.361 | +| clip_range | 0.0695 | +| entropy_loss | -7.53 | +| explained_variance | -0.131 | +| learning_rate | 7.24e-05 | +| loss | -0.0369 | +| n_updates | 12584 | +| policy_gradient_loss | -0.0223 | +| value_loss | 0.000144 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.295 | +| time/ | | +| fps | 1378 | +| iterations | 3148 | +| time_elapsed | 4675 | +| total_timesteps | 6447104 | +| train/ | | +| approx_kl | 0.012098562 | +| clip_fraction | 0.323 | +| clip_range | 0.0694 | +| entropy_loss | -7.48 | +| explained_variance | -0.149 | +| learning_rate | 7.24e-05 | +| loss | -0.0306 | +| n_updates | 12588 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000189 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.295 | +| time/ | | +| fps | 1378 | +| iterations | 3149 | +| time_elapsed | 4677 | +| total_timesteps | 6449152 | +| train/ | | +| approx_kl | 0.013660091 | +| clip_fraction | 0.354 | +| clip_range | 0.0694 | +| entropy_loss | -7.62 | +| explained_variance | -0.0215 | +| learning_rate | 7.23e-05 | +| loss | -0.0316 | +| n_updates | 12592 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000192 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.295 | +| time/ | | +| fps | 1378 | +| iterations | 3150 | +| time_elapsed | 4678 | +| total_timesteps | 6451200 | +| train/ | | +| approx_kl | 0.013125908 | +| clip_fraction | 0.357 | +| clip_range | 0.0694 | +| entropy_loss | -7.67 | +| explained_variance | -0.257 | +| learning_rate | 7.23e-05 | +| loss | -0.0307 | +| n_updates | 12596 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000135 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.29 | +| time/ | | +| fps | 1378 | +| iterations | 3151 | +| time_elapsed | 4680 | +| total_timesteps | 6453248 | +| train/ | | +| approx_kl | 0.013010504 | +| clip_fraction | 0.358 | +| clip_range | 0.0694 | +| entropy_loss | -7.63 | +| explained_variance | -0.181 | +| learning_rate | 7.23e-05 | +| loss | -0.0318 | +| n_updates | 12600 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000105 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.291 | +| time/ | | +| fps | 1378 | +| iterations | 3152 | +| time_elapsed | 4681 | +| total_timesteps | 6455296 | +| train/ | | +| approx_kl | 0.012087864 | +| clip_fraction | 0.351 | +| clip_range | 0.0693 | +| entropy_loss | -7.56 | +| explained_variance | -0.143 | +| learning_rate | 7.22e-05 | +| loss | -0.0308 | +| n_updates | 12604 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000122 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.283 | +| time/ | | +| fps | 1378 | +| iterations | 3153 | +| time_elapsed | 4683 | +| total_timesteps | 6457344 | +| train/ | | +| approx_kl | 0.012582387 | +| clip_fraction | 0.358 | +| clip_range | 0.0693 | +| entropy_loss | -7.55 | +| explained_variance | -0.0808 | +| learning_rate | 7.22e-05 | +| loss | -0.0282 | +| n_updates | 12608 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000129 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.281 | +| time/ | | +| fps | 1378 | +| iterations | 3154 | +| time_elapsed | 4684 | +| total_timesteps | 6459392 | +| train/ | | +| approx_kl | 0.012735862 | +| clip_fraction | 0.338 | +| clip_range | 0.0693 | +| entropy_loss | -7.69 | +| explained_variance | -0.105 | +| learning_rate | 7.21e-05 | +| loss | -0.0357 | +| n_updates | 12612 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000143 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.284 | +| time/ | | +| fps | 1378 | +| iterations | 3155 | +| time_elapsed | 4685 | +| total_timesteps | 6461440 | +| train/ | | +| approx_kl | 0.012342688 | +| clip_fraction | 0.372 | +| clip_range | 0.0693 | +| entropy_loss | -7.54 | +| explained_variance | -0.129 | +| learning_rate | 7.21e-05 | +| loss | -0.0298 | +| n_updates | 12616 | +| policy_gradient_loss | -0.0203 | +| value_loss | 9.69e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.288 | +| time/ | | +| fps | 1378 | +| iterations | 3156 | +| time_elapsed | 4687 | +| total_timesteps | 6463488 | +| train/ | | +| approx_kl | 0.013149067 | +| clip_fraction | 0.349 | +| clip_range | 0.0692 | +| entropy_loss | -7.61 | +| explained_variance | -0.0761 | +| learning_rate | 7.21e-05 | +| loss | -0.0262 | +| n_updates | 12620 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.00028 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.289 | +| time/ | | +| fps | 1378 | +| iterations | 3157 | +| time_elapsed | 4688 | +| total_timesteps | 6465536 | +| train/ | | +| approx_kl | 0.013770528 | +| clip_fraction | 0.35 | +| clip_range | 0.0692 | +| entropy_loss | -7.45 | +| explained_variance | -0.124 | +| learning_rate | 7.2e-05 | +| loss | -0.0336 | +| n_updates | 12624 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000143 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.293 | +| time/ | | +| fps | 1378 | +| iterations | 3158 | +| time_elapsed | 4690 | +| total_timesteps | 6467584 | +| train/ | | +| approx_kl | 0.014843835 | +| clip_fraction | 0.355 | +| clip_range | 0.0692 | +| entropy_loss | -7.53 | +| explained_variance | -0.127 | +| learning_rate | 7.2e-05 | +| loss | -0.0347 | +| n_updates | 12628 | +| policy_gradient_loss | -0.0221 | +| value_loss | 9.08e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.293 | +| time/ | | +| fps | 1378 | +| iterations | 3159 | +| time_elapsed | 4691 | +| total_timesteps | 6469632 | +| train/ | | +| approx_kl | 0.012583444 | +| clip_fraction | 0.354 | +| clip_range | 0.0692 | +| entropy_loss | -7.68 | +| explained_variance | -0.0572 | +| learning_rate | 7.19e-05 | +| loss | -0.0305 | +| n_updates | 12632 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000212 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.293 | +| time/ | | +| fps | 1378 | +| iterations | 3160 | +| time_elapsed | 4693 | +| total_timesteps | 6471680 | +| train/ | | +| approx_kl | 0.012610422 | +| clip_fraction | 0.344 | +| clip_range | 0.0691 | +| entropy_loss | -7.47 | +| explained_variance | -0.16 | +| learning_rate | 7.19e-05 | +| loss | -0.035 | +| n_updates | 12636 | +| policy_gradient_loss | -0.0225 | +| value_loss | 0.000114 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.292 | +| time/ | | +| fps | 1379 | +| iterations | 3161 | +| time_elapsed | 4694 | +| total_timesteps | 6473728 | +| train/ | | +| approx_kl | 0.012072084 | +| clip_fraction | 0.379 | +| clip_range | 0.0691 | +| entropy_loss | -7.66 | +| explained_variance | -0.0822 | +| learning_rate | 7.19e-05 | +| loss | -0.0324 | +| n_updates | 12640 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000147 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.293 | +| time/ | | +| fps | 1379 | +| iterations | 3162 | +| time_elapsed | 4695 | +| total_timesteps | 6475776 | +| train/ | | +| approx_kl | 0.009154601 | +| clip_fraction | 0.308 | +| clip_range | 0.0691 | +| entropy_loss | -7.53 | +| explained_variance | -0.0405 | +| learning_rate | 7.18e-05 | +| loss | -0.0217 | +| n_updates | 12644 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000359 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.298 | +| time/ | | +| fps | 1379 | +| iterations | 3163 | +| time_elapsed | 4697 | +| total_timesteps | 6477824 | +| train/ | | +| approx_kl | 0.011368595 | +| clip_fraction | 0.373 | +| clip_range | 0.0691 | +| entropy_loss | -7.56 | +| explained_variance | -0.11 | +| learning_rate | 7.18e-05 | +| loss | -0.0366 | +| n_updates | 12648 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000136 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 1379 | +| iterations | 3164 | +| time_elapsed | 4698 | +| total_timesteps | 6479872 | +| train/ | | +| approx_kl | 0.012264909 | +| clip_fraction | 0.343 | +| clip_range | 0.069 | +| entropy_loss | -7.49 | +| explained_variance | -0.0524 | +| learning_rate | 7.17e-05 | +| loss | -0.0253 | +| n_updates | 12652 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000285 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.298 | +| time/ | | +| fps | 1379 | +| iterations | 3165 | +| time_elapsed | 4700 | +| total_timesteps | 6481920 | +| train/ | | +| approx_kl | 0.015421486 | +| clip_fraction | 0.352 | +| clip_range | 0.069 | +| entropy_loss | -7.53 | +| explained_variance | -0.0859 | +| learning_rate | 7.17e-05 | +| loss | -0.033 | +| n_updates | 12656 | +| policy_gradient_loss | -0.0221 | +| value_loss | 0.000158 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.295 | +| time/ | | +| fps | 1379 | +| iterations | 3166 | +| time_elapsed | 4701 | +| total_timesteps | 6483968 | +| train/ | | +| approx_kl | 0.011797003 | +| clip_fraction | 0.349 | +| clip_range | 0.069 | +| entropy_loss | -7.59 | +| explained_variance | -0.141 | +| learning_rate | 7.17e-05 | +| loss | -0.0365 | +| n_updates | 12660 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000176 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.3 | +| time/ | | +| fps | 1379 | +| iterations | 3167 | +| time_elapsed | 4703 | +| total_timesteps | 6486016 | +| train/ | | +| approx_kl | 0.013355969 | +| clip_fraction | 0.346 | +| clip_range | 0.069 | +| entropy_loss | -7.63 | +| explained_variance | -0.0534 | +| learning_rate | 7.16e-05 | +| loss | -0.0288 | +| n_updates | 12664 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.00023 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.3 | +| time/ | | +| fps | 1379 | +| iterations | 3168 | +| time_elapsed | 4704 | +| total_timesteps | 6488064 | +| train/ | | +| approx_kl | 0.01083125 | +| clip_fraction | 0.321 | +| clip_range | 0.0689 | +| entropy_loss | -7.53 | +| explained_variance | -0.144 | +| learning_rate | 7.16e-05 | +| loss | -0.0312 | +| n_updates | 12668 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000237 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.3 | +| time/ | | +| fps | 1379 | +| iterations | 3169 | +| time_elapsed | 4706 | +| total_timesteps | 6490112 | +| train/ | | +| approx_kl | 0.01396174 | +| clip_fraction | 0.358 | +| clip_range | 0.0689 | +| entropy_loss | -7.59 | +| explained_variance | 0.0432 | +| learning_rate | 7.15e-05 | +| loss | -0.0348 | +| n_updates | 12672 | +| policy_gradient_loss | -0.0221 | +| value_loss | 0.000138 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 1379 | +| iterations | 3170 | +| time_elapsed | 4707 | +| total_timesteps | 6492160 | +| train/ | | +| approx_kl | 0.013559025 | +| clip_fraction | 0.367 | +| clip_range | 0.0689 | +| entropy_loss | -7.55 | +| explained_variance | -0.0935 | +| learning_rate | 7.15e-05 | +| loss | -0.0403 | +| n_updates | 12676 | +| policy_gradient_loss | -0.0238 | +| value_loss | 0.00011 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 1379 | +| iterations | 3171 | +| time_elapsed | 4708 | +| total_timesteps | 6494208 | +| train/ | | +| approx_kl | 0.01075425 | +| clip_fraction | 0.341 | +| clip_range | 0.0688 | +| entropy_loss | -7.55 | +| explained_variance | -0.101 | +| learning_rate | 7.15e-05 | +| loss | -0.0304 | +| n_updates | 12680 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000225 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1379 | +| iterations | 3172 | +| time_elapsed | 4710 | +| total_timesteps | 6496256 | +| train/ | | +| approx_kl | 0.012903141 | +| clip_fraction | 0.377 | +| clip_range | 0.0688 | +| entropy_loss | -7.45 | +| explained_variance | -0.379 | +| learning_rate | 7.14e-05 | +| loss | -0.0406 | +| n_updates | 12684 | +| policy_gradient_loss | -0.0244 | +| value_loss | 6.97e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 1379 | +| iterations | 3173 | +| time_elapsed | 4711 | +| total_timesteps | 6498304 | +| train/ | | +| approx_kl | 0.012382677 | +| clip_fraction | 0.345 | +| clip_range | 0.0688 | +| entropy_loss | -7.51 | +| explained_variance | -0.189 | +| learning_rate | 7.14e-05 | +| loss | -0.0352 | +| n_updates | 12688 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.00016 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.286 | +| time/ | | +| fps | 1379 | +| iterations | 3174 | +| time_elapsed | 4713 | +| total_timesteps | 6500352 | +| train/ | | +| approx_kl | 0.013203159 | +| clip_fraction | 0.38 | +| clip_range | 0.0688 | +| entropy_loss | -7.62 | +| explained_variance | -0.193 | +| learning_rate | 7.13e-05 | +| loss | -0.0391 | +| n_updates | 12692 | +| policy_gradient_loss | -0.0233 | +| value_loss | 8.88e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.287 | +| time/ | | +| fps | 1379 | +| iterations | 3175 | +| time_elapsed | 4714 | +| total_timesteps | 6502400 | +| train/ | | +| approx_kl | 0.010959951 | +| clip_fraction | 0.361 | +| clip_range | 0.0687 | +| entropy_loss | -7.34 | +| explained_variance | -0.0115 | +| learning_rate | 7.13e-05 | +| loss | -0.0311 | +| n_updates | 12696 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.00022 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.286 | +| time/ | | +| fps | 1379 | +| iterations | 3176 | +| time_elapsed | 4716 | +| total_timesteps | 6504448 | +| train/ | | +| approx_kl | 0.013641572 | +| clip_fraction | 0.369 | +| clip_range | 0.0687 | +| entropy_loss | -7.53 | +| explained_variance | -0.00672 | +| learning_rate | 7.13e-05 | +| loss | -0.0391 | +| n_updates | 12700 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000142 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 1379 | +| iterations | 3177 | +| time_elapsed | 4717 | +| total_timesteps | 6506496 | +| train/ | | +| approx_kl | 0.013735288 | +| clip_fraction | 0.372 | +| clip_range | 0.0687 | +| entropy_loss | -7.57 | +| explained_variance | -0.133 | +| learning_rate | 7.12e-05 | +| loss | -0.0366 | +| n_updates | 12704 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000185 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 1379 | +| iterations | 3178 | +| time_elapsed | 4718 | +| total_timesteps | 6508544 | +| train/ | | +| approx_kl | 0.012033168 | +| clip_fraction | 0.325 | +| clip_range | 0.0687 | +| entropy_loss | -7.46 | +| explained_variance | -0.0543 | +| learning_rate | 7.12e-05 | +| loss | -0.0291 | +| n_updates | 12708 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000265 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.276 | +| time/ | | +| fps | 1379 | +| iterations | 3179 | +| time_elapsed | 4720 | +| total_timesteps | 6510592 | +| train/ | | +| approx_kl | 0.013817097 | +| clip_fraction | 0.377 | +| clip_range | 0.0686 | +| entropy_loss | -7.56 | +| explained_variance | -0.203 | +| learning_rate | 7.11e-05 | +| loss | -0.0342 | +| n_updates | 12712 | +| policy_gradient_loss | -0.0225 | +| value_loss | 0.000144 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.272 | +| time/ | | +| fps | 1379 | +| iterations | 3180 | +| time_elapsed | 4721 | +| total_timesteps | 6512640 | +| train/ | | +| approx_kl | 0.012071006 | +| clip_fraction | 0.367 | +| clip_range | 0.0686 | +| entropy_loss | -7.56 | +| explained_variance | -0.137 | +| learning_rate | 7.11e-05 | +| loss | -0.034 | +| n_updates | 12716 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000126 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.272 | +| time/ | | +| fps | 1379 | +| iterations | 3181 | +| time_elapsed | 4723 | +| total_timesteps | 6514688 | +| train/ | | +| approx_kl | 0.012358881 | +| clip_fraction | 0.346 | +| clip_range | 0.0686 | +| entropy_loss | -7.61 | +| explained_variance | -0.048 | +| learning_rate | 7.1e-05 | +| loss | -0.032 | +| n_updates | 12720 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000103 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.273 | +| time/ | | +| fps | 1379 | +| iterations | 3182 | +| time_elapsed | 4724 | +| total_timesteps | 6516736 | +| train/ | | +| approx_kl | 0.012636282 | +| clip_fraction | 0.323 | +| clip_range | 0.0686 | +| entropy_loss | -7.69 | +| explained_variance | -0.156 | +| learning_rate | 7.1e-05 | +| loss | -0.0313 | +| n_updates | 12724 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000166 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 1379 | +| iterations | 3183 | +| time_elapsed | 4726 | +| total_timesteps | 6518784 | +| train/ | | +| approx_kl | 0.009605505 | +| clip_fraction | 0.312 | +| clip_range | 0.0685 | +| entropy_loss | -7.53 | +| explained_variance | -0.0658 | +| learning_rate | 7.1e-05 | +| loss | -0.0267 | +| n_updates | 12728 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000262 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.268 | +| time/ | | +| fps | 1379 | +| iterations | 3184 | +| time_elapsed | 4727 | +| total_timesteps | 6520832 | +| train/ | | +| approx_kl | 0.011542777 | +| clip_fraction | 0.351 | +| clip_range | 0.0685 | +| entropy_loss | -7.56 | +| explained_variance | -0.145 | +| learning_rate | 7.09e-05 | +| loss | -0.0349 | +| n_updates | 12732 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000117 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.272 | +| time/ | | +| fps | 1379 | +| iterations | 3185 | +| time_elapsed | 4728 | +| total_timesteps | 6522880 | +| train/ | | +| approx_kl | 0.0111415405 | +| clip_fraction | 0.304 | +| clip_range | 0.0685 | +| entropy_loss | -7.55 | +| explained_variance | -0.00387 | +| learning_rate | 7.09e-05 | +| loss | -0.0308 | +| n_updates | 12736 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000289 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 1379 | +| iterations | 3186 | +| time_elapsed | 4730 | +| total_timesteps | 6524928 | +| train/ | | +| approx_kl | 0.009818487 | +| clip_fraction | 0.309 | +| clip_range | 0.0685 | +| entropy_loss | -7.61 | +| explained_variance | -0.131 | +| learning_rate | 7.08e-05 | +| loss | -0.02 | +| n_updates | 12740 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000284 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.28 | +| time/ | | +| fps | 1379 | +| iterations | 3187 | +| time_elapsed | 4731 | +| total_timesteps | 6526976 | +| train/ | | +| approx_kl | 0.013194926 | +| clip_fraction | 0.328 | +| clip_range | 0.0684 | +| entropy_loss | -7.46 | +| explained_variance | -0.111 | +| learning_rate | 7.08e-05 | +| loss | -0.0369 | +| n_updates | 12744 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000206 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 1379 | +| iterations | 3188 | +| time_elapsed | 4733 | +| total_timesteps | 6529024 | +| train/ | | +| approx_kl | 0.010998417 | +| clip_fraction | 0.341 | +| clip_range | 0.0684 | +| entropy_loss | -7.59 | +| explained_variance | -0.147 | +| learning_rate | 7.08e-05 | +| loss | -0.0321 | +| n_updates | 12748 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000277 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 1379 | +| iterations | 3189 | +| time_elapsed | 4734 | +| total_timesteps | 6531072 | +| train/ | | +| approx_kl | 0.011798061 | +| clip_fraction | 0.345 | +| clip_range | 0.0684 | +| entropy_loss | -7.44 | +| explained_variance | 0.023 | +| learning_rate | 7.07e-05 | +| loss | -0.027 | +| n_updates | 12752 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000278 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.27 | +| time/ | | +| fps | 1379 | +| iterations | 3190 | +| time_elapsed | 4736 | +| total_timesteps | 6533120 | +| train/ | | +| approx_kl | 0.010688238 | +| clip_fraction | 0.347 | +| clip_range | 0.0684 | +| entropy_loss | -7.61 | +| explained_variance | -0.248 | +| learning_rate | 7.07e-05 | +| loss | -0.0347 | +| n_updates | 12756 | +| policy_gradient_loss | -0.0221 | +| value_loss | 0.000124 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.268 | +| time/ | | +| fps | 1379 | +| iterations | 3191 | +| time_elapsed | 4737 | +| total_timesteps | 6535168 | +| train/ | | +| approx_kl | 0.011451286 | +| clip_fraction | 0.334 | +| clip_range | 0.0683 | +| entropy_loss | -7.64 | +| explained_variance | -0.115 | +| learning_rate | 7.06e-05 | +| loss | -0.0299 | +| n_updates | 12760 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000206 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.268 | +| time/ | | +| fps | 1379 | +| iterations | 3192 | +| time_elapsed | 4738 | +| total_timesteps | 6537216 | +| train/ | | +| approx_kl | 0.01024006 | +| clip_fraction | 0.312 | +| clip_range | 0.0683 | +| entropy_loss | -7.64 | +| explained_variance | -0.0308 | +| learning_rate | 7.06e-05 | +| loss | -0.029 | +| n_updates | 12764 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000206 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.266 | +| time/ | | +| fps | 1379 | +| iterations | 3193 | +| time_elapsed | 4740 | +| total_timesteps | 6539264 | +| train/ | | +| approx_kl | 0.010968627 | +| clip_fraction | 0.367 | +| clip_range | 0.0683 | +| entropy_loss | -7.59 | +| explained_variance | -0.0376 | +| learning_rate | 7.06e-05 | +| loss | -0.0336 | +| n_updates | 12768 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000192 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.268 | +| time/ | | +| fps | 1379 | +| iterations | 3194 | +| time_elapsed | 4741 | +| total_timesteps | 6541312 | +| train/ | | +| approx_kl | 0.011927182 | +| clip_fraction | 0.339 | +| clip_range | 0.0683 | +| entropy_loss | -7.56 | +| explained_variance | -0.118 | +| learning_rate | 7.05e-05 | +| loss | -0.0387 | +| n_updates | 12772 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000151 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.269 | +| time/ | | +| fps | 1379 | +| iterations | 3195 | +| time_elapsed | 4743 | +| total_timesteps | 6543360 | +| train/ | | +| approx_kl | 0.012641326 | +| clip_fraction | 0.345 | +| clip_range | 0.0682 | +| entropy_loss | -7.64 | +| explained_variance | -0.116 | +| learning_rate | 7.05e-05 | +| loss | -0.0303 | +| n_updates | 12776 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000156 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.273 | +| time/ | | +| fps | 1379 | +| iterations | 3196 | +| time_elapsed | 4744 | +| total_timesteps | 6545408 | +| train/ | | +| approx_kl | 0.010069901 | +| clip_fraction | 0.356 | +| clip_range | 0.0682 | +| entropy_loss | -7.61 | +| explained_variance | -0.158 | +| learning_rate | 7.04e-05 | +| loss | -0.0346 | +| n_updates | 12780 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000175 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.281 | +| time/ | | +| fps | 1379 | +| iterations | 3197 | +| time_elapsed | 4745 | +| total_timesteps | 6547456 | +| train/ | | +| approx_kl | 0.012739222 | +| clip_fraction | 0.348 | +| clip_range | 0.0682 | +| entropy_loss | -7.51 | +| explained_variance | 0.0187 | +| learning_rate | 7.04e-05 | +| loss | -0.0274 | +| n_updates | 12784 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000157 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 1379 | +| iterations | 3198 | +| time_elapsed | 4747 | +| total_timesteps | 6549504 | +| train/ | | +| approx_kl | 0.014444169 | +| clip_fraction | 0.354 | +| clip_range | 0.0682 | +| entropy_loss | -7.55 | +| explained_variance | -0.0707 | +| learning_rate | 7.04e-05 | +| loss | -0.0341 | +| n_updates | 12788 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000247 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.277 | +| time/ | | +| fps | 1379 | +| iterations | 3199 | +| time_elapsed | 4748 | +| total_timesteps | 6551552 | +| train/ | | +| approx_kl | 0.0113483835 | +| clip_fraction | 0.344 | +| clip_range | 0.0681 | +| entropy_loss | -7.58 | +| explained_variance | -0.195 | +| learning_rate | 7.03e-05 | +| loss | -0.0332 | +| n_updates | 12792 | +| policy_gradient_loss | -0.0219 | +| value_loss | 0.00014 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.277 | +| time/ | | +| fps | 1379 | +| iterations | 3200 | +| time_elapsed | 4750 | +| total_timesteps | 6553600 | +| train/ | | +| approx_kl | 0.011687746 | +| clip_fraction | 0.345 | +| clip_range | 0.0681 | +| entropy_loss | -7.56 | +| explained_variance | -0.11 | +| learning_rate | 7.03e-05 | +| loss | -0.0312 | +| n_updates | 12796 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000216 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.277 | +| time/ | | +| fps | 1379 | +| iterations | 3201 | +| time_elapsed | 4751 | +| total_timesteps | 6555648 | +| train/ | | +| approx_kl | 0.012568574 | +| clip_fraction | 0.357 | +| clip_range | 0.0681 | +| entropy_loss | -7.57 | +| explained_variance | -0.228 | +| learning_rate | 7.02e-05 | +| loss | -0.033 | +| n_updates | 12800 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000106 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.278 | +| time/ | | +| fps | 1379 | +| iterations | 3202 | +| time_elapsed | 4753 | +| total_timesteps | 6557696 | +| train/ | | +| approx_kl | 0.011712035 | +| clip_fraction | 0.336 | +| clip_range | 0.0681 | +| entropy_loss | -7.56 | +| explained_variance | -0.129 | +| learning_rate | 7.02e-05 | +| loss | -0.0321 | +| n_updates | 12804 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.00024 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.273 | +| time/ | | +| fps | 1379 | +| iterations | 3203 | +| time_elapsed | 4754 | +| total_timesteps | 6559744 | +| train/ | | +| approx_kl | 0.012077314 | +| clip_fraction | 0.344 | +| clip_range | 0.068 | +| entropy_loss | -7.65 | +| explained_variance | -0.0907 | +| learning_rate | 7.02e-05 | +| loss | -0.0338 | +| n_updates | 12808 | +| policy_gradient_loss | -0.0208 | +| value_loss | 9.74e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.276 | +| time/ | | +| fps | 1379 | +| iterations | 3204 | +| time_elapsed | 4755 | +| total_timesteps | 6561792 | +| train/ | | +| approx_kl | 0.0105702095 | +| clip_fraction | 0.339 | +| clip_range | 0.068 | +| entropy_loss | -7.61 | +| explained_variance | -0.107 | +| learning_rate | 7.01e-05 | +| loss | -0.032 | +| n_updates | 12812 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000186 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.281 | +| time/ | | +| fps | 1379 | +| iterations | 3205 | +| time_elapsed | 4757 | +| total_timesteps | 6563840 | +| train/ | | +| approx_kl | 0.010189094 | +| clip_fraction | 0.336 | +| clip_range | 0.068 | +| entropy_loss | -7.55 | +| explained_variance | -0.0041 | +| learning_rate | 7.01e-05 | +| loss | -0.031 | +| n_updates | 12816 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000141 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 1379 | +| iterations | 3206 | +| time_elapsed | 4758 | +| total_timesteps | 6565888 | +| train/ | | +| approx_kl | 0.013932297 | +| clip_fraction | 0.326 | +| clip_range | 0.068 | +| entropy_loss | -7.63 | +| explained_variance | -0.0866 | +| learning_rate | 7e-05 | +| loss | -0.0319 | +| n_updates | 12820 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000187 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.283 | +| time/ | | +| fps | 1379 | +| iterations | 3207 | +| time_elapsed | 4760 | +| total_timesteps | 6567936 | +| train/ | | +| approx_kl | 0.012530969 | +| clip_fraction | 0.353 | +| clip_range | 0.0679 | +| entropy_loss | -7.53 | +| explained_variance | -0.15 | +| learning_rate | 7e-05 | +| loss | -0.0255 | +| n_updates | 12824 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000211 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.292 | +| time/ | | +| fps | 1379 | +| iterations | 3208 | +| time_elapsed | 4761 | +| total_timesteps | 6569984 | +| train/ | | +| approx_kl | 0.012842417 | +| clip_fraction | 0.339 | +| clip_range | 0.0679 | +| entropy_loss | -7.59 | +| explained_variance | -0.0518 | +| learning_rate | 7e-05 | +| loss | -0.0321 | +| n_updates | 12828 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000202 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.292 | +| time/ | | +| fps | 1379 | +| iterations | 3209 | +| time_elapsed | 4763 | +| total_timesteps | 6572032 | +| train/ | | +| approx_kl | 0.011366651 | +| clip_fraction | 0.326 | +| clip_range | 0.0679 | +| entropy_loss | -7.55 | +| explained_variance | 0.0123 | +| learning_rate | 6.99e-05 | +| loss | -0.0364 | +| n_updates | 12832 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000307 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.29 | +| time/ | | +| fps | 1379 | +| iterations | 3210 | +| time_elapsed | 4764 | +| total_timesteps | 6574080 | +| train/ | | +| approx_kl | 0.011746658 | +| clip_fraction | 0.357 | +| clip_range | 0.0678 | +| entropy_loss | -7.59 | +| explained_variance | -0.1 | +| learning_rate | 6.99e-05 | +| loss | -0.0341 | +| n_updates | 12836 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000207 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.288 | +| time/ | | +| fps | 1379 | +| iterations | 3211 | +| time_elapsed | 4765 | +| total_timesteps | 6576128 | +| train/ | | +| approx_kl | 0.008890199 | +| clip_fraction | 0.307 | +| clip_range | 0.0678 | +| entropy_loss | -7.76 | +| explained_variance | -0.0439 | +| learning_rate | 6.98e-05 | +| loss | -0.0315 | +| n_updates | 12840 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000168 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.291 | +| time/ | | +| fps | 1379 | +| iterations | 3212 | +| time_elapsed | 4767 | +| total_timesteps | 6578176 | +| train/ | | +| approx_kl | 0.009487681 | +| clip_fraction | 0.341 | +| clip_range | 0.0678 | +| entropy_loss | -7.59 | +| explained_variance | 0.0266 | +| learning_rate | 6.98e-05 | +| loss | -0.0277 | +| n_updates | 12844 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000296 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.295 | +| time/ | | +| fps | 1379 | +| iterations | 3213 | +| time_elapsed | 4768 | +| total_timesteps | 6580224 | +| train/ | | +| approx_kl | 0.010084985 | +| clip_fraction | 0.331 | +| clip_range | 0.0678 | +| entropy_loss | -7.66 | +| explained_variance | -0.172 | +| learning_rate | 6.98e-05 | +| loss | -0.0321 | +| n_updates | 12848 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000159 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.298 | +| time/ | | +| fps | 1379 | +| iterations | 3214 | +| time_elapsed | 4770 | +| total_timesteps | 6582272 | +| train/ | | +| approx_kl | 0.010438441 | +| clip_fraction | 0.346 | +| clip_range | 0.0677 | +| entropy_loss | -7.48 | +| explained_variance | -0.0307 | +| learning_rate | 6.97e-05 | +| loss | -0.0355 | +| n_updates | 12852 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000277 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.302 | +| time/ | | +| fps | 1379 | +| iterations | 3215 | +| time_elapsed | 4771 | +| total_timesteps | 6584320 | +| train/ | | +| approx_kl | 0.009324695 | +| clip_fraction | 0.309 | +| clip_range | 0.0677 | +| entropy_loss | -7.56 | +| explained_variance | 0.139 | +| learning_rate | 6.97e-05 | +| loss | -0.0286 | +| n_updates | 12856 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000258 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.302 | +| time/ | | +| fps | 1379 | +| iterations | 3216 | +| time_elapsed | 4773 | +| total_timesteps | 6586368 | +| train/ | | +| approx_kl | 0.01085265 | +| clip_fraction | 0.363 | +| clip_range | 0.0677 | +| entropy_loss | -7.58 | +| explained_variance | -0.377 | +| learning_rate | 6.96e-05 | +| loss | -0.0376 | +| n_updates | 12860 | +| policy_gradient_loss | -0.0224 | +| value_loss | 0.000111 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1379 | +| iterations | 3217 | +| time_elapsed | 4774 | +| total_timesteps | 6588416 | +| train/ | | +| approx_kl | 0.012188784 | +| clip_fraction | 0.346 | +| clip_range | 0.0677 | +| entropy_loss | -7.67 | +| explained_variance | -0.224 | +| learning_rate | 6.96e-05 | +| loss | -0.0342 | +| n_updates | 12864 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000113 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.302 | +| time/ | | +| fps | 1379 | +| iterations | 3218 | +| time_elapsed | 4776 | +| total_timesteps | 6590464 | +| train/ | | +| approx_kl | 0.008084584 | +| clip_fraction | 0.308 | +| clip_range | 0.0676 | +| entropy_loss | -7.76 | +| explained_variance | 0.0398 | +| learning_rate | 6.95e-05 | +| loss | -0.0305 | +| n_updates | 12868 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.00034 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.302 | +| time/ | | +| fps | 1379 | +| iterations | 3219 | +| time_elapsed | 4777 | +| total_timesteps | 6592512 | +| train/ | | +| approx_kl | 0.011102722 | +| clip_fraction | 0.336 | +| clip_range | 0.0676 | +| entropy_loss | -7.51 | +| explained_variance | -0.263 | +| learning_rate | 6.95e-05 | +| loss | -0.0329 | +| n_updates | 12872 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000165 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.304 | +| time/ | | +| fps | 1379 | +| iterations | 3220 | +| time_elapsed | 4778 | +| total_timesteps | 6594560 | +| train/ | | +| approx_kl | 0.011865966 | +| clip_fraction | 0.348 | +| clip_range | 0.0676 | +| entropy_loss | -7.76 | +| explained_variance | -0.144 | +| learning_rate | 6.95e-05 | +| loss | -0.0348 | +| n_updates | 12876 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000141 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 1379 | +| iterations | 3221 | +| time_elapsed | 4780 | +| total_timesteps | 6596608 | +| train/ | | +| approx_kl | 0.011618488 | +| clip_fraction | 0.317 | +| clip_range | 0.0676 | +| entropy_loss | -7.69 | +| explained_variance | -0.0936 | +| learning_rate | 6.94e-05 | +| loss | -0.0346 | +| n_updates | 12880 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000119 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 1380 | +| iterations | 3222 | +| time_elapsed | 4781 | +| total_timesteps | 6598656 | +| train/ | | +| approx_kl | 0.009616202 | +| clip_fraction | 0.319 | +| clip_range | 0.0675 | +| entropy_loss | -7.66 | +| explained_variance | -0.141 | +| learning_rate | 6.94e-05 | +| loss | -0.0305 | +| n_updates | 12884 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000201 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 1379 | +| iterations | 3223 | +| time_elapsed | 4783 | +| total_timesteps | 6600704 | +| train/ | | +| approx_kl | 0.011222053 | +| clip_fraction | 0.323 | +| clip_range | 0.0675 | +| entropy_loss | -7.73 | +| explained_variance | -0.0966 | +| learning_rate | 6.93e-05 | +| loss | -0.0318 | +| n_updates | 12888 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000202 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.3 | +| time/ | | +| fps | 1379 | +| iterations | 3224 | +| time_elapsed | 4784 | +| total_timesteps | 6602752 | +| train/ | | +| approx_kl | 0.012696196 | +| clip_fraction | 0.36 | +| clip_range | 0.0675 | +| entropy_loss | -7.5 | +| explained_variance | -0.125 | +| learning_rate | 6.93e-05 | +| loss | -0.0297 | +| n_updates | 12892 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000101 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.3 | +| time/ | | +| fps | 1380 | +| iterations | 3225 | +| time_elapsed | 4786 | +| total_timesteps | 6604800 | +| train/ | | +| approx_kl | 0.01285307 | +| clip_fraction | 0.328 | +| clip_range | 0.0675 | +| entropy_loss | -7.62 | +| explained_variance | -0.0438 | +| learning_rate | 6.93e-05 | +| loss | -0.0295 | +| n_updates | 12896 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000206 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.297 | +| time/ | | +| fps | 1380 | +| iterations | 3226 | +| time_elapsed | 4787 | +| total_timesteps | 6606848 | +| train/ | | +| approx_kl | 0.010482142 | +| clip_fraction | 0.334 | +| clip_range | 0.0674 | +| entropy_loss | -7.41 | +| explained_variance | -0.142 | +| learning_rate | 6.92e-05 | +| loss | -0.0311 | +| n_updates | 12900 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000136 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.297 | +| time/ | | +| fps | 1380 | +| iterations | 3227 | +| time_elapsed | 4788 | +| total_timesteps | 6608896 | +| train/ | | +| approx_kl | 0.011393104 | +| clip_fraction | 0.333 | +| clip_range | 0.0674 | +| entropy_loss | -7.67 | +| explained_variance | -0.158 | +| learning_rate | 6.92e-05 | +| loss | -0.0311 | +| n_updates | 12904 | +| policy_gradient_loss | -0.0207 | +| value_loss | 9.51e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.29 | +| time/ | | +| fps | 1380 | +| iterations | 3228 | +| time_elapsed | 4790 | +| total_timesteps | 6610944 | +| train/ | | +| approx_kl | 0.011692388 | +| clip_fraction | 0.32 | +| clip_range | 0.0674 | +| entropy_loss | -7.69 | +| explained_variance | -0.0699 | +| learning_rate | 6.91e-05 | +| loss | -0.03 | +| n_updates | 12908 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000116 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 1380 | +| iterations | 3229 | +| time_elapsed | 4791 | +| total_timesteps | 6612992 | +| train/ | | +| approx_kl | 0.010410631 | +| clip_fraction | 0.325 | +| clip_range | 0.0674 | +| entropy_loss | -7.55 | +| explained_variance | -0.145 | +| learning_rate | 6.91e-05 | +| loss | -0.0289 | +| n_updates | 12912 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000153 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 1380 | +| iterations | 3230 | +| time_elapsed | 4793 | +| total_timesteps | 6615040 | +| train/ | | +| approx_kl | 0.010224141 | +| clip_fraction | 0.327 | +| clip_range | 0.0673 | +| entropy_loss | -7.64 | +| explained_variance | -0.0821 | +| learning_rate | 6.91e-05 | +| loss | -0.0281 | +| n_updates | 12916 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000222 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 1380 | +| iterations | 3231 | +| time_elapsed | 4794 | +| total_timesteps | 6617088 | +| train/ | | +| approx_kl | 0.011506885 | +| clip_fraction | 0.345 | +| clip_range | 0.0673 | +| entropy_loss | -7.61 | +| explained_variance | -0.0738 | +| learning_rate | 6.9e-05 | +| loss | -0.0315 | +| n_updates | 12920 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.00021 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.277 | +| time/ | | +| fps | 1380 | +| iterations | 3232 | +| time_elapsed | 4796 | +| total_timesteps | 6619136 | +| train/ | | +| approx_kl | 0.011877356 | +| clip_fraction | 0.34 | +| clip_range | 0.0673 | +| entropy_loss | -7.66 | +| explained_variance | -0.0573 | +| learning_rate | 6.9e-05 | +| loss | -0.03 | +| n_updates | 12924 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000167 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.277 | +| time/ | | +| fps | 1380 | +| iterations | 3233 | +| time_elapsed | 4797 | +| total_timesteps | 6621184 | +| train/ | | +| approx_kl | 0.011762209 | +| clip_fraction | 0.321 | +| clip_range | 0.0673 | +| entropy_loss | -7.7 | +| explained_variance | -0.13 | +| learning_rate | 6.89e-05 | +| loss | -0.0317 | +| n_updates | 12928 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.0002 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.276 | +| time/ | | +| fps | 1380 | +| iterations | 3234 | +| time_elapsed | 4799 | +| total_timesteps | 6623232 | +| train/ | | +| approx_kl | 0.011885974 | +| clip_fraction | 0.337 | +| clip_range | 0.0672 | +| entropy_loss | -7.73 | +| explained_variance | -0.106 | +| learning_rate | 6.89e-05 | +| loss | -0.0357 | +| n_updates | 12932 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000144 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 1380 | +| iterations | 3235 | +| time_elapsed | 4800 | +| total_timesteps | 6625280 | +| train/ | | +| approx_kl | 0.009007502 | +| clip_fraction | 0.31 | +| clip_range | 0.0672 | +| entropy_loss | -7.63 | +| explained_variance | -0.0358 | +| learning_rate | 6.89e-05 | +| loss | -0.0309 | +| n_updates | 12936 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000139 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 1380 | +| iterations | 3236 | +| time_elapsed | 4801 | +| total_timesteps | 6627328 | +| train/ | | +| approx_kl | 0.010257889 | +| clip_fraction | 0.325 | +| clip_range | 0.0672 | +| entropy_loss | -7.52 | +| explained_variance | -0.0699 | +| learning_rate | 6.88e-05 | +| loss | -0.0259 | +| n_updates | 12940 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000164 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.281 | +| time/ | | +| fps | 1380 | +| iterations | 3237 | +| time_elapsed | 4803 | +| total_timesteps | 6629376 | +| train/ | | +| approx_kl | 0.010972867 | +| clip_fraction | 0.324 | +| clip_range | 0.0672 | +| entropy_loss | -7.7 | +| explained_variance | -0.149 | +| learning_rate | 6.88e-05 | +| loss | -0.0355 | +| n_updates | 12944 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000162 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.295 | +| time/ | | +| fps | 1380 | +| iterations | 3238 | +| time_elapsed | 4804 | +| total_timesteps | 6631424 | +| train/ | | +| approx_kl | 0.011585288 | +| clip_fraction | 0.316 | +| clip_range | 0.0671 | +| entropy_loss | -7.6 | +| explained_variance | -0.188 | +| learning_rate | 6.87e-05 | +| loss | -0.0306 | +| n_updates | 12948 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000119 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.295 | +| time/ | | +| fps | 1380 | +| iterations | 3239 | +| time_elapsed | 4806 | +| total_timesteps | 6633472 | +| train/ | | +| approx_kl | 0.0124667715 | +| clip_fraction | 0.324 | +| clip_range | 0.0671 | +| entropy_loss | -7.55 | +| explained_variance | -0.0608 | +| learning_rate | 6.87e-05 | +| loss | -0.0326 | +| n_updates | 12952 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000276 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.294 | +| time/ | | +| fps | 1380 | +| iterations | 3240 | +| time_elapsed | 4807 | +| total_timesteps | 6635520 | +| train/ | | +| approx_kl | 0.011223123 | +| clip_fraction | 0.329 | +| clip_range | 0.0671 | +| entropy_loss | -7.64 | +| explained_variance | 0.00671 | +| learning_rate | 6.87e-05 | +| loss | -0.0292 | +| n_updates | 12956 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000151 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.298 | +| time/ | | +| fps | 1380 | +| iterations | 3241 | +| time_elapsed | 4809 | +| total_timesteps | 6637568 | +| train/ | | +| approx_kl | 0.011501232 | +| clip_fraction | 0.348 | +| clip_range | 0.0671 | +| entropy_loss | -7.73 | +| explained_variance | 0.0223 | +| learning_rate | 6.86e-05 | +| loss | -0.0312 | +| n_updates | 12960 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000174 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 1380 | +| iterations | 3242 | +| time_elapsed | 4810 | +| total_timesteps | 6639616 | +| train/ | | +| approx_kl | 0.009942165 | +| clip_fraction | 0.311 | +| clip_range | 0.067 | +| entropy_loss | -7.65 | +| explained_variance | -0.0377 | +| learning_rate | 6.86e-05 | +| loss | -0.0314 | +| n_updates | 12964 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000227 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 1380 | +| iterations | 3243 | +| time_elapsed | 4812 | +| total_timesteps | 6641664 | +| train/ | | +| approx_kl | 0.010133409 | +| clip_fraction | 0.332 | +| clip_range | 0.067 | +| entropy_loss | -7.68 | +| explained_variance | -0.0915 | +| learning_rate | 6.85e-05 | +| loss | -0.0261 | +| n_updates | 12968 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000198 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 1380 | +| iterations | 3244 | +| time_elapsed | 4813 | +| total_timesteps | 6643712 | +| train/ | | +| approx_kl | 0.009037275 | +| clip_fraction | 0.324 | +| clip_range | 0.067 | +| entropy_loss | -7.69 | +| explained_variance | -0.0137 | +| learning_rate | 6.85e-05 | +| loss | -0.0293 | +| n_updates | 12972 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000309 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 1380 | +| iterations | 3245 | +| time_elapsed | 4815 | +| total_timesteps | 6645760 | +| train/ | | +| approx_kl | 0.010179024 | +| clip_fraction | 0.342 | +| clip_range | 0.067 | +| entropy_loss | -7.71 | +| explained_variance | -0.296 | +| learning_rate | 6.85e-05 | +| loss | -0.0338 | +| n_updates | 12976 | +| policy_gradient_loss | -0.0233 | +| value_loss | 7.66e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 1380 | +| iterations | 3246 | +| time_elapsed | 4816 | +| total_timesteps | 6647808 | +| train/ | | +| approx_kl | 0.009346509 | +| clip_fraction | 0.335 | +| clip_range | 0.0669 | +| entropy_loss | -7.52 | +| explained_variance | -0.168 | +| learning_rate | 6.84e-05 | +| loss | -0.0333 | +| n_updates | 12980 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000133 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 1380 | +| iterations | 3247 | +| time_elapsed | 4817 | +| total_timesteps | 6649856 | +| train/ | | +| approx_kl | 0.010881422 | +| clip_fraction | 0.348 | +| clip_range | 0.0669 | +| entropy_loss | -7.32 | +| explained_variance | -0.0122 | +| learning_rate | 6.84e-05 | +| loss | -0.0309 | +| n_updates | 12984 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000402 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.298 | +| time/ | | +| fps | 1380 | +| iterations | 3248 | +| time_elapsed | 4819 | +| total_timesteps | 6651904 | +| train/ | | +| approx_kl | 0.010643729 | +| clip_fraction | 0.336 | +| clip_range | 0.0669 | +| entropy_loss | -7.64 | +| explained_variance | -0.0937 | +| learning_rate | 6.83e-05 | +| loss | -0.0343 | +| n_updates | 12988 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000184 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.298 | +| time/ | | +| fps | 1380 | +| iterations | 3249 | +| time_elapsed | 4820 | +| total_timesteps | 6653952 | +| train/ | | +| approx_kl | 0.011551499 | +| clip_fraction | 0.367 | +| clip_range | 0.0669 | +| entropy_loss | -7.62 | +| explained_variance | -0.177 | +| learning_rate | 6.83e-05 | +| loss | -0.0369 | +| n_updates | 12992 | +| policy_gradient_loss | -0.0224 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.298 | +| time/ | | +| fps | 1380 | +| iterations | 3250 | +| time_elapsed | 4822 | +| total_timesteps | 6656000 | +| train/ | | +| approx_kl | 0.011139493 | +| clip_fraction | 0.343 | +| clip_range | 0.0668 | +| entropy_loss | -7.68 | +| explained_variance | -0.0178 | +| learning_rate | 6.83e-05 | +| loss | -0.0335 | +| n_updates | 12996 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000192 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 1380 | +| iterations | 3251 | +| time_elapsed | 4823 | +| total_timesteps | 6658048 | +| train/ | | +| approx_kl | 0.01127906 | +| clip_fraction | 0.336 | +| clip_range | 0.0668 | +| entropy_loss | -7.68 | +| explained_variance | -0.105 | +| learning_rate | 6.82e-05 | +| loss | -0.0349 | +| n_updates | 13000 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000148 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.294 | +| time/ | | +| fps | 1380 | +| iterations | 3252 | +| time_elapsed | 4825 | +| total_timesteps | 6660096 | +| train/ | | +| approx_kl | 0.010218378 | +| clip_fraction | 0.36 | +| clip_range | 0.0668 | +| entropy_loss | -7.67 | +| explained_variance | -0.0098 | +| learning_rate | 6.82e-05 | +| loss | -0.0305 | +| n_updates | 13004 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000184 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.283 | +| time/ | | +| fps | 1380 | +| iterations | 3253 | +| time_elapsed | 4826 | +| total_timesteps | 6662144 | +| train/ | | +| approx_kl | 0.007938225 | +| clip_fraction | 0.298 | +| clip_range | 0.0667 | +| entropy_loss | -7.6 | +| explained_variance | -0.033 | +| learning_rate | 6.81e-05 | +| loss | -0.0252 | +| n_updates | 13008 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000326 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.297 | +| time/ | | +| fps | 1380 | +| iterations | 3254 | +| time_elapsed | 4827 | +| total_timesteps | 6664192 | +| train/ | | +| approx_kl | 0.011131392 | +| clip_fraction | 0.355 | +| clip_range | 0.0667 | +| entropy_loss | -7.59 | +| explained_variance | -0.182 | +| learning_rate | 6.81e-05 | +| loss | -0.0348 | +| n_updates | 13012 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000186 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.294 | +| time/ | | +| fps | 1380 | +| iterations | 3255 | +| time_elapsed | 4829 | +| total_timesteps | 6666240 | +| train/ | | +| approx_kl | 0.009837365 | +| clip_fraction | 0.345 | +| clip_range | 0.0667 | +| entropy_loss | -7.53 | +| explained_variance | -0.157 | +| learning_rate | 6.8e-05 | +| loss | -0.033 | +| n_updates | 13016 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000221 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.3 | +| time/ | | +| fps | 1380 | +| iterations | 3256 | +| time_elapsed | 4830 | +| total_timesteps | 6668288 | +| train/ | | +| approx_kl | 0.011316356 | +| clip_fraction | 0.352 | +| clip_range | 0.0667 | +| entropy_loss | -7.51 | +| explained_variance | -0.168 | +| learning_rate | 6.8e-05 | +| loss | -0.0312 | +| n_updates | 13020 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000132 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.3 | +| time/ | | +| fps | 1380 | +| iterations | 3257 | +| time_elapsed | 4832 | +| total_timesteps | 6670336 | +| train/ | | +| approx_kl | 0.010630135 | +| clip_fraction | 0.341 | +| clip_range | 0.0666 | +| entropy_loss | -7.59 | +| explained_variance | -0.0539 | +| learning_rate | 6.8e-05 | +| loss | -0.0298 | +| n_updates | 13024 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000296 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.3 | +| time/ | | +| fps | 1380 | +| iterations | 3258 | +| time_elapsed | 4833 | +| total_timesteps | 6672384 | +| train/ | | +| approx_kl | 0.010970408 | +| clip_fraction | 0.372 | +| clip_range | 0.0666 | +| entropy_loss | -7.67 | +| explained_variance | -0.377 | +| learning_rate | 6.79e-05 | +| loss | -0.0323 | +| n_updates | 13028 | +| policy_gradient_loss | -0.023 | +| value_loss | 9.66e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 1380 | +| iterations | 3259 | +| time_elapsed | 4835 | +| total_timesteps | 6674432 | +| train/ | | +| approx_kl | 0.010083975 | +| clip_fraction | 0.344 | +| clip_range | 0.0666 | +| entropy_loss | -7.73 | +| explained_variance | -0.0124 | +| learning_rate | 6.79e-05 | +| loss | -0.034 | +| n_updates | 13032 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000314 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.3 | +| time/ | | +| fps | 1380 | +| iterations | 3260 | +| time_elapsed | 4836 | +| total_timesteps | 6676480 | +| train/ | | +| approx_kl | 0.010205688 | +| clip_fraction | 0.319 | +| clip_range | 0.0666 | +| entropy_loss | -7.63 | +| explained_variance | -0.107 | +| learning_rate | 6.78e-05 | +| loss | -0.0291 | +| n_updates | 13036 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.00013 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 1380 | +| iterations | 3261 | +| time_elapsed | 4838 | +| total_timesteps | 6678528 | +| train/ | | +| approx_kl | 0.011011831 | +| clip_fraction | 0.33 | +| clip_range | 0.0665 | +| entropy_loss | -7.58 | +| explained_variance | 0.0219 | +| learning_rate | 6.78e-05 | +| loss | -0.0265 | +| n_updates | 13040 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000246 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.304 | +| time/ | | +| fps | 1380 | +| iterations | 3262 | +| time_elapsed | 4839 | +| total_timesteps | 6680576 | +| train/ | | +| approx_kl | 0.00988235 | +| clip_fraction | 0.327 | +| clip_range | 0.0665 | +| entropy_loss | -7.62 | +| explained_variance | -0.139 | +| learning_rate | 6.78e-05 | +| loss | -0.0326 | +| n_updates | 13044 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.00023 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 1380 | +| iterations | 3263 | +| time_elapsed | 4840 | +| total_timesteps | 6682624 | +| train/ | | +| approx_kl | 0.011189633 | +| clip_fraction | 0.333 | +| clip_range | 0.0665 | +| entropy_loss | -7.51 | +| explained_variance | -0.102 | +| learning_rate | 6.77e-05 | +| loss | -0.0262 | +| n_updates | 13048 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000286 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 1380 | +| iterations | 3264 | +| time_elapsed | 4842 | +| total_timesteps | 6684672 | +| train/ | | +| approx_kl | 0.010784077 | +| clip_fraction | 0.307 | +| clip_range | 0.0665 | +| entropy_loss | -7.64 | +| explained_variance | -0.15 | +| learning_rate | 6.77e-05 | +| loss | -0.0205 | +| n_updates | 13052 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.00021 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 1380 | +| iterations | 3265 | +| time_elapsed | 4843 | +| total_timesteps | 6686720 | +| train/ | | +| approx_kl | 0.012068417 | +| clip_fraction | 0.316 | +| clip_range | 0.0664 | +| entropy_loss | -7.14 | +| explained_variance | -0.0508 | +| learning_rate | 6.76e-05 | +| loss | -0.0328 | +| n_updates | 13056 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000297 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.306 | +| time/ | | +| fps | 1380 | +| iterations | 3266 | +| time_elapsed | 4845 | +| total_timesteps | 6688768 | +| train/ | | +| approx_kl | 0.011970175 | +| clip_fraction | 0.37 | +| clip_range | 0.0664 | +| entropy_loss | -7.56 | +| explained_variance | -0.0747 | +| learning_rate | 6.76e-05 | +| loss | -0.0325 | +| n_updates | 13060 | +| policy_gradient_loss | -0.0226 | +| value_loss | 0.000144 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.306 | +| time/ | | +| fps | 1380 | +| iterations | 3267 | +| time_elapsed | 4846 | +| total_timesteps | 6690816 | +| train/ | | +| approx_kl | 0.01222671 | +| clip_fraction | 0.348 | +| clip_range | 0.0664 | +| entropy_loss | -7.66 | +| explained_variance | -0.127 | +| learning_rate | 6.76e-05 | +| loss | -0.033 | +| n_updates | 13064 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000166 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.306 | +| time/ | | +| fps | 1380 | +| iterations | 3268 | +| time_elapsed | 4848 | +| total_timesteps | 6692864 | +| train/ | | +| approx_kl | 0.011525633 | +| clip_fraction | 0.345 | +| clip_range | 0.0664 | +| entropy_loss | -7.76 | +| explained_variance | -0.125 | +| learning_rate | 6.75e-05 | +| loss | -0.0344 | +| n_updates | 13068 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000126 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 1380 | +| iterations | 3269 | +| time_elapsed | 4849 | +| total_timesteps | 6694912 | +| train/ | | +| approx_kl | 0.010726115 | +| clip_fraction | 0.361 | +| clip_range | 0.0663 | +| entropy_loss | -7.7 | +| explained_variance | -0.118 | +| learning_rate | 6.75e-05 | +| loss | -0.0278 | +| n_updates | 13072 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000119 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.298 | +| time/ | | +| fps | 1380 | +| iterations | 3270 | +| time_elapsed | 4850 | +| total_timesteps | 6696960 | +| train/ | | +| approx_kl | 0.011451447 | +| clip_fraction | 0.32 | +| clip_range | 0.0663 | +| entropy_loss | -7.59 | +| explained_variance | -0.035 | +| learning_rate | 6.74e-05 | +| loss | -0.0331 | +| n_updates | 13076 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000196 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.298 | +| time/ | | +| fps | 1380 | +| iterations | 3271 | +| time_elapsed | 4852 | +| total_timesteps | 6699008 | +| train/ | | +| approx_kl | 0.010255162 | +| clip_fraction | 0.322 | +| clip_range | 0.0663 | +| entropy_loss | -7.55 | +| explained_variance | -0.0539 | +| learning_rate | 6.74e-05 | +| loss | -0.0342 | +| n_updates | 13080 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000167 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.3 | +| time/ | | +| fps | 1380 | +| iterations | 3272 | +| time_elapsed | 4853 | +| total_timesteps | 6701056 | +| train/ | | +| approx_kl | 0.01029976 | +| clip_fraction | 0.333 | +| clip_range | 0.0663 | +| entropy_loss | -7.66 | +| explained_variance | -0.0358 | +| learning_rate | 6.74e-05 | +| loss | -0.0306 | +| n_updates | 13084 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000179 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.3 | +| time/ | | +| fps | 1380 | +| iterations | 3273 | +| time_elapsed | 4855 | +| total_timesteps | 6703104 | +| train/ | | +| approx_kl | 0.010295538 | +| clip_fraction | 0.317 | +| clip_range | 0.0662 | +| entropy_loss | -7.56 | +| explained_variance | -0.0116 | +| learning_rate | 6.73e-05 | +| loss | -0.0246 | +| n_updates | 13088 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000222 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.293 | +| time/ | | +| fps | 1380 | +| iterations | 3274 | +| time_elapsed | 4856 | +| total_timesteps | 6705152 | +| train/ | | +| approx_kl | 0.0104452 | +| clip_fraction | 0.311 | +| clip_range | 0.0662 | +| entropy_loss | -7.63 | +| explained_variance | -0.0718 | +| learning_rate | 6.73e-05 | +| loss | -0.0297 | +| n_updates | 13092 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000198 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 1380 | +| iterations | 3275 | +| time_elapsed | 4858 | +| total_timesteps | 6707200 | +| train/ | | +| approx_kl | 0.010958597 | +| clip_fraction | 0.345 | +| clip_range | 0.0662 | +| entropy_loss | -7.54 | +| explained_variance | -0.0177 | +| learning_rate | 6.72e-05 | +| loss | -0.0355 | +| n_updates | 13096 | +| policy_gradient_loss | -0.0205 | +| value_loss | 8.96e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.297 | +| time/ | | +| fps | 1380 | +| iterations | 3276 | +| time_elapsed | 4859 | +| total_timesteps | 6709248 | +| train/ | | +| approx_kl | 0.010959936 | +| clip_fraction | 0.337 | +| clip_range | 0.0662 | +| entropy_loss | -7.52 | +| explained_variance | -0.106 | +| learning_rate | 6.72e-05 | +| loss | -0.0224 | +| n_updates | 13100 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.00021 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.297 | +| time/ | | +| fps | 1380 | +| iterations | 3277 | +| time_elapsed | 4861 | +| total_timesteps | 6711296 | +| train/ | | +| approx_kl | 0.011327207 | +| clip_fraction | 0.34 | +| clip_range | 0.0661 | +| entropy_loss | -7.52 | +| explained_variance | -0.0682 | +| learning_rate | 6.72e-05 | +| loss | -0.0304 | +| n_updates | 13104 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000119 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.297 | +| time/ | | +| fps | 1380 | +| iterations | 3278 | +| time_elapsed | 4862 | +| total_timesteps | 6713344 | +| train/ | | +| approx_kl | 0.010728578 | +| clip_fraction | 0.326 | +| clip_range | 0.0661 | +| entropy_loss | -7.68 | +| explained_variance | -0.0447 | +| learning_rate | 6.71e-05 | +| loss | -0.0291 | +| n_updates | 13108 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.00024 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 1380 | +| iterations | 3279 | +| time_elapsed | 4863 | +| total_timesteps | 6715392 | +| train/ | | +| approx_kl | 0.010025188 | +| clip_fraction | 0.358 | +| clip_range | 0.0661 | +| entropy_loss | -7.58 | +| explained_variance | -0.108 | +| learning_rate | 6.71e-05 | +| loss | -0.0356 | +| n_updates | 13112 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000155 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 1380 | +| iterations | 3280 | +| time_elapsed | 4865 | +| total_timesteps | 6717440 | +| train/ | | +| approx_kl | 0.010598579 | +| clip_fraction | 0.337 | +| clip_range | 0.0661 | +| entropy_loss | -7.63 | +| explained_variance | -0.0987 | +| learning_rate | 6.7e-05 | +| loss | -0.0229 | +| n_updates | 13116 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000208 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.295 | +| time/ | | +| fps | 1380 | +| iterations | 3281 | +| time_elapsed | 4866 | +| total_timesteps | 6719488 | +| train/ | | +| approx_kl | 0.0113632055 | +| clip_fraction | 0.358 | +| clip_range | 0.066 | +| entropy_loss | -7.61 | +| explained_variance | -0.039 | +| learning_rate | 6.7e-05 | +| loss | -0.03 | +| n_updates | 13120 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000118 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.289 | +| time/ | | +| fps | 1380 | +| iterations | 3282 | +| time_elapsed | 4868 | +| total_timesteps | 6721536 | +| train/ | | +| approx_kl | 0.010607478 | +| clip_fraction | 0.36 | +| clip_range | 0.066 | +| entropy_loss | -7.61 | +| explained_variance | -0.0324 | +| learning_rate | 6.7e-05 | +| loss | -0.0343 | +| n_updates | 13124 | +| policy_gradient_loss | -0.0222 | +| value_loss | 6.9e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.289 | +| time/ | | +| fps | 1380 | +| iterations | 3283 | +| time_elapsed | 4869 | +| total_timesteps | 6723584 | +| train/ | | +| approx_kl | 0.01041194 | +| clip_fraction | 0.339 | +| clip_range | 0.066 | +| entropy_loss | -7.53 | +| explained_variance | -0.0145 | +| learning_rate | 6.69e-05 | +| loss | -0.0329 | +| n_updates | 13128 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000197 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.29 | +| time/ | | +| fps | 1380 | +| iterations | 3284 | +| time_elapsed | 4871 | +| total_timesteps | 6725632 | +| train/ | | +| approx_kl | 0.010552125 | +| clip_fraction | 0.344 | +| clip_range | 0.066 | +| entropy_loss | -7.68 | +| explained_variance | -0.337 | +| learning_rate | 6.69e-05 | +| loss | -0.0395 | +| n_updates | 13132 | +| policy_gradient_loss | -0.0225 | +| value_loss | 7.63e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.287 | +| time/ | | +| fps | 1380 | +| iterations | 3285 | +| time_elapsed | 4872 | +| total_timesteps | 6727680 | +| train/ | | +| approx_kl | 0.011675943 | +| clip_fraction | 0.329 | +| clip_range | 0.0659 | +| entropy_loss | -7.49 | +| explained_variance | 0.0665 | +| learning_rate | 6.68e-05 | +| loss | -0.0297 | +| n_updates | 13136 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000113 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.284 | +| time/ | | +| fps | 1380 | +| iterations | 3286 | +| time_elapsed | 4873 | +| total_timesteps | 6729728 | +| train/ | | +| approx_kl | 0.01033371 | +| clip_fraction | 0.338 | +| clip_range | 0.0659 | +| entropy_loss | -7.57 | +| explained_variance | -0.0653 | +| learning_rate | 6.68e-05 | +| loss | -0.0328 | +| n_updates | 13140 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000145 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.281 | +| time/ | | +| fps | 1380 | +| iterations | 3287 | +| time_elapsed | 4875 | +| total_timesteps | 6731776 | +| train/ | | +| approx_kl | 0.010872478 | +| clip_fraction | 0.338 | +| clip_range | 0.0659 | +| entropy_loss | -7.52 | +| explained_variance | -0.107 | +| learning_rate | 6.68e-05 | +| loss | -0.0236 | +| n_updates | 13144 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000159 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 1380 | +| iterations | 3288 | +| time_elapsed | 4876 | +| total_timesteps | 6733824 | +| train/ | | +| approx_kl | 0.010148963 | +| clip_fraction | 0.358 | +| clip_range | 0.0659 | +| entropy_loss | -7.6 | +| explained_variance | 0.034 | +| learning_rate | 6.67e-05 | +| loss | -0.032 | +| n_updates | 13148 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000163 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.278 | +| time/ | | +| fps | 1380 | +| iterations | 3289 | +| time_elapsed | 4878 | +| total_timesteps | 6735872 | +| train/ | | +| approx_kl | 0.010521613 | +| clip_fraction | 0.319 | +| clip_range | 0.0658 | +| entropy_loss | -7.53 | +| explained_variance | -0.0207 | +| learning_rate | 6.67e-05 | +| loss | -0.0303 | +| n_updates | 13152 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000207 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.284 | +| time/ | | +| fps | 1380 | +| iterations | 3290 | +| time_elapsed | 4879 | +| total_timesteps | 6737920 | +| train/ | | +| approx_kl | 0.0111127 | +| clip_fraction | 0.348 | +| clip_range | 0.0658 | +| entropy_loss | -7.46 | +| explained_variance | 0.0276 | +| learning_rate | 6.66e-05 | +| loss | -0.0277 | +| n_updates | 13156 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000111 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.284 | +| time/ | | +| fps | 1380 | +| iterations | 3291 | +| time_elapsed | 4881 | +| total_timesteps | 6739968 | +| train/ | | +| approx_kl | 0.007671405 | +| clip_fraction | 0.279 | +| clip_range | 0.0658 | +| entropy_loss | -7.62 | +| explained_variance | 0.0278 | +| learning_rate | 6.66e-05 | +| loss | -0.029 | +| n_updates | 13160 | +| policy_gradient_loss | -0.0143 | +| value_loss | 0.000326 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.284 | +| time/ | | +| fps | 1380 | +| iterations | 3292 | +| time_elapsed | 4882 | +| total_timesteps | 6742016 | +| train/ | | +| approx_kl | 0.009756532 | +| clip_fraction | 0.342 | +| clip_range | 0.0658 | +| entropy_loss | -7.67 | +| explained_variance | -0.0674 | +| learning_rate | 6.65e-05 | +| loss | -0.0334 | +| n_updates | 13164 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.00017 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.289 | +| time/ | | +| fps | 1380 | +| iterations | 3293 | +| time_elapsed | 4884 | +| total_timesteps | 6744064 | +| train/ | | +| approx_kl | 0.010700099 | +| clip_fraction | 0.36 | +| clip_range | 0.0657 | +| entropy_loss | -7.51 | +| explained_variance | -0.397 | +| learning_rate | 6.65e-05 | +| loss | -0.0391 | +| n_updates | 13168 | +| policy_gradient_loss | -0.0233 | +| value_loss | 5.28e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 1380 | +| iterations | 3294 | +| time_elapsed | 4885 | +| total_timesteps | 6746112 | +| train/ | | +| approx_kl | 0.010999233 | +| clip_fraction | 0.382 | +| clip_range | 0.0657 | +| entropy_loss | -7.41 | +| explained_variance | 0.0949 | +| learning_rate | 6.65e-05 | +| loss | -0.0322 | +| n_updates | 13172 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000117 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.297 | +| time/ | | +| fps | 1380 | +| iterations | 3295 | +| time_elapsed | 4886 | +| total_timesteps | 6748160 | +| train/ | | +| approx_kl | 0.010564502 | +| clip_fraction | 0.359 | +| clip_range | 0.0657 | +| entropy_loss | -7.48 | +| explained_variance | 0.0147 | +| learning_rate | 6.64e-05 | +| loss | -0.0273 | +| n_updates | 13176 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000163 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.294 | +| time/ | | +| fps | 1380 | +| iterations | 3296 | +| time_elapsed | 4888 | +| total_timesteps | 6750208 | +| train/ | | +| approx_kl | 0.010959116 | +| clip_fraction | 0.366 | +| clip_range | 0.0656 | +| entropy_loss | -7.59 | +| explained_variance | -0.122 | +| learning_rate | 6.64e-05 | +| loss | -0.031 | +| n_updates | 13180 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000145 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.294 | +| time/ | | +| fps | 1380 | +| iterations | 3297 | +| time_elapsed | 4889 | +| total_timesteps | 6752256 | +| train/ | | +| approx_kl | 0.011083974 | +| clip_fraction | 0.336 | +| clip_range | 0.0656 | +| entropy_loss | -7.52 | +| explained_variance | -0.137 | +| learning_rate | 6.63e-05 | +| loss | -0.0317 | +| n_updates | 13184 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000151 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.294 | +| time/ | | +| fps | 1380 | +| iterations | 3298 | +| time_elapsed | 4891 | +| total_timesteps | 6754304 | +| train/ | | +| approx_kl | 0.011231521 | +| clip_fraction | 0.346 | +| clip_range | 0.0656 | +| entropy_loss | -7.63 | +| explained_variance | 0.0125 | +| learning_rate | 6.63e-05 | +| loss | -0.0325 | +| n_updates | 13188 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.00014 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 1380 | +| iterations | 3299 | +| time_elapsed | 4892 | +| total_timesteps | 6756352 | +| train/ | | +| approx_kl | 0.012069564 | +| clip_fraction | 0.353 | +| clip_range | 0.0656 | +| entropy_loss | -7.57 | +| explained_variance | -0.12 | +| learning_rate | 6.63e-05 | +| loss | -0.0302 | +| n_updates | 13192 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000154 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.297 | +| time/ | | +| fps | 1380 | +| iterations | 3300 | +| time_elapsed | 4894 | +| total_timesteps | 6758400 | +| train/ | | +| approx_kl | 0.008191325 | +| clip_fraction | 0.328 | +| clip_range | 0.0655 | +| entropy_loss | -7.62 | +| explained_variance | -0.14 | +| learning_rate | 6.62e-05 | +| loss | -0.0287 | +| n_updates | 13196 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000142 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1380 | +| iterations | 3301 | +| time_elapsed | 4895 | +| total_timesteps | 6760448 | +| train/ | | +| approx_kl | 0.008871511 | +| clip_fraction | 0.33 | +| clip_range | 0.0655 | +| entropy_loss | -7.58 | +| explained_variance | 0.0829 | +| learning_rate | 6.62e-05 | +| loss | -0.0236 | +| n_updates | 13200 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000208 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1380 | +| iterations | 3302 | +| time_elapsed | 4896 | +| total_timesteps | 6762496 | +| train/ | | +| approx_kl | 0.01016745 | +| clip_fraction | 0.323 | +| clip_range | 0.0655 | +| entropy_loss | -7.25 | +| explained_variance | -0.0176 | +| learning_rate | 6.61e-05 | +| loss | -0.0236 | +| n_updates | 13204 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000386 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1380 | +| iterations | 3303 | +| time_elapsed | 4898 | +| total_timesteps | 6764544 | +| train/ | | +| approx_kl | 0.011782221 | +| clip_fraction | 0.364 | +| clip_range | 0.0655 | +| entropy_loss | -7.58 | +| explained_variance | -0.339 | +| learning_rate | 6.61e-05 | +| loss | -0.0353 | +| n_updates | 13208 | +| policy_gradient_loss | -0.0226 | +| value_loss | 8.92e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 1380 | +| iterations | 3304 | +| time_elapsed | 4899 | +| total_timesteps | 6766592 | +| train/ | | +| approx_kl | 0.010953019 | +| clip_fraction | 0.362 | +| clip_range | 0.0654 | +| entropy_loss | -7.57 | +| explained_variance | -0.0903 | +| learning_rate | 6.61e-05 | +| loss | -0.0328 | +| n_updates | 13212 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000201 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.304 | +| time/ | | +| fps | 1380 | +| iterations | 3305 | +| time_elapsed | 4901 | +| total_timesteps | 6768640 | +| train/ | | +| approx_kl | 0.010827564 | +| clip_fraction | 0.332 | +| clip_range | 0.0654 | +| entropy_loss | -7.38 | +| explained_variance | -0.0614 | +| learning_rate | 6.6e-05 | +| loss | -0.032 | +| n_updates | 13216 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000187 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.294 | +| time/ | | +| fps | 1381 | +| iterations | 3306 | +| time_elapsed | 4902 | +| total_timesteps | 6770688 | +| train/ | | +| approx_kl | 0.011113204 | +| clip_fraction | 0.32 | +| clip_range | 0.0654 | +| entropy_loss | -7.5 | +| explained_variance | -0.073 | +| learning_rate | 6.6e-05 | +| loss | -0.0285 | +| n_updates | 13220 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000168 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.294 | +| time/ | | +| fps | 1381 | +| iterations | 3307 | +| time_elapsed | 4904 | +| total_timesteps | 6772736 | +| train/ | | +| approx_kl | 0.010585068 | +| clip_fraction | 0.326 | +| clip_range | 0.0654 | +| entropy_loss | -7.56 | +| explained_variance | -0.148 | +| learning_rate | 6.59e-05 | +| loss | -0.0265 | +| n_updates | 13224 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000241 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.294 | +| time/ | | +| fps | 1381 | +| iterations | 3308 | +| time_elapsed | 4905 | +| total_timesteps | 6774784 | +| train/ | | +| approx_kl | 0.01225562 | +| clip_fraction | 0.369 | +| clip_range | 0.0653 | +| entropy_loss | -7.42 | +| explained_variance | -0.102 | +| learning_rate | 6.59e-05 | +| loss | -0.0353 | +| n_updates | 13228 | +| policy_gradient_loss | -0.0224 | +| value_loss | 0.000136 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.294 | +| time/ | | +| fps | 1381 | +| iterations | 3309 | +| time_elapsed | 4907 | +| total_timesteps | 6776832 | +| train/ | | +| approx_kl | 0.010552868 | +| clip_fraction | 0.335 | +| clip_range | 0.0653 | +| entropy_loss | -7.62 | +| explained_variance | -0.292 | +| learning_rate | 6.59e-05 | +| loss | -0.0304 | +| n_updates | 13232 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000152 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.292 | +| time/ | | +| fps | 1381 | +| iterations | 3310 | +| time_elapsed | 4908 | +| total_timesteps | 6778880 | +| train/ | | +| approx_kl | 0.010655734 | +| clip_fraction | 0.348 | +| clip_range | 0.0653 | +| entropy_loss | -7.63 | +| explained_variance | -0.085 | +| learning_rate | 6.58e-05 | +| loss | -0.0331 | +| n_updates | 13236 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.00013 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.293 | +| time/ | | +| fps | 1381 | +| iterations | 3311 | +| time_elapsed | 4909 | +| total_timesteps | 6780928 | +| train/ | | +| approx_kl | 0.0096432585 | +| clip_fraction | 0.315 | +| clip_range | 0.0653 | +| entropy_loss | -7.49 | +| explained_variance | -0.00809 | +| learning_rate | 6.58e-05 | +| loss | -0.024 | +| n_updates | 13240 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000202 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.294 | +| time/ | | +| fps | 1381 | +| iterations | 3312 | +| time_elapsed | 4911 | +| total_timesteps | 6782976 | +| train/ | | +| approx_kl | 0.010069869 | +| clip_fraction | 0.348 | +| clip_range | 0.0652 | +| entropy_loss | -7.53 | +| explained_variance | -0.325 | +| learning_rate | 6.57e-05 | +| loss | -0.0347 | +| n_updates | 13244 | +| policy_gradient_loss | -0.0212 | +| value_loss | 8.66e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.288 | +| time/ | | +| fps | 1381 | +| iterations | 3313 | +| time_elapsed | 4912 | +| total_timesteps | 6785024 | +| train/ | | +| approx_kl | 0.009832841 | +| clip_fraction | 0.307 | +| clip_range | 0.0652 | +| entropy_loss | -7.61 | +| explained_variance | -0.0385 | +| learning_rate | 6.57e-05 | +| loss | -0.0239 | +| n_updates | 13248 | +| policy_gradient_loss | -0.0135 | +| value_loss | 0.000213 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.289 | +| time/ | | +| fps | 1381 | +| iterations | 3314 | +| time_elapsed | 4914 | +| total_timesteps | 6787072 | +| train/ | | +| approx_kl | 0.010245403 | +| clip_fraction | 0.333 | +| clip_range | 0.0652 | +| entropy_loss | -7.53 | +| explained_variance | -0.0551 | +| learning_rate | 6.57e-05 | +| loss | -0.0328 | +| n_updates | 13252 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000228 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.29 | +| time/ | | +| fps | 1381 | +| iterations | 3315 | +| time_elapsed | 4915 | +| total_timesteps | 6789120 | +| train/ | | +| approx_kl | 0.01060623 | +| clip_fraction | 0.357 | +| clip_range | 0.0652 | +| entropy_loss | -7.49 | +| explained_variance | -0.0969 | +| learning_rate | 6.56e-05 | +| loss | -0.0301 | +| n_updates | 13256 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000164 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.285 | +| time/ | | +| fps | 1381 | +| iterations | 3316 | +| time_elapsed | 4917 | +| total_timesteps | 6791168 | +| train/ | | +| approx_kl | 0.010115284 | +| clip_fraction | 0.351 | +| clip_range | 0.0651 | +| entropy_loss | -7.45 | +| explained_variance | -0.0393 | +| learning_rate | 6.56e-05 | +| loss | -0.0264 | +| n_updates | 13260 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000318 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.284 | +| time/ | | +| fps | 1381 | +| iterations | 3317 | +| time_elapsed | 4918 | +| total_timesteps | 6793216 | +| train/ | | +| approx_kl | 0.01107712 | +| clip_fraction | 0.36 | +| clip_range | 0.0651 | +| entropy_loss | -7.52 | +| explained_variance | -0.301 | +| learning_rate | 6.55e-05 | +| loss | -0.0347 | +| n_updates | 13264 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.00015 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 1381 | +| iterations | 3318 | +| time_elapsed | 4920 | +| total_timesteps | 6795264 | +| train/ | | +| approx_kl | 0.010152768 | +| clip_fraction | 0.345 | +| clip_range | 0.0651 | +| entropy_loss | -7.55 | +| explained_variance | -0.152 | +| learning_rate | 6.55e-05 | +| loss | -0.0333 | +| n_updates | 13268 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.00014 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 1381 | +| iterations | 3319 | +| time_elapsed | 4921 | +| total_timesteps | 6797312 | +| train/ | | +| approx_kl | 0.009874024 | +| clip_fraction | 0.325 | +| clip_range | 0.0651 | +| entropy_loss | -7.34 | +| explained_variance | -0.0305 | +| learning_rate | 6.55e-05 | +| loss | -0.0301 | +| n_updates | 13272 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000231 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 1381 | +| iterations | 3320 | +| time_elapsed | 4922 | +| total_timesteps | 6799360 | +| train/ | | +| approx_kl | 0.009824796 | +| clip_fraction | 0.336 | +| clip_range | 0.065 | +| entropy_loss | -7.55 | +| explained_variance | -0.151 | +| learning_rate | 6.54e-05 | +| loss | -0.0293 | +| n_updates | 13276 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000175 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 1381 | +| iterations | 3321 | +| time_elapsed | 4924 | +| total_timesteps | 6801408 | +| train/ | | +| approx_kl | 0.010912492 | +| clip_fraction | 0.328 | +| clip_range | 0.065 | +| entropy_loss | -7.66 | +| explained_variance | -0.0699 | +| learning_rate | 6.54e-05 | +| loss | -0.0314 | +| n_updates | 13280 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000151 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 1381 | +| iterations | 3322 | +| time_elapsed | 4925 | +| total_timesteps | 6803456 | +| train/ | | +| approx_kl | 0.011527896 | +| clip_fraction | 0.336 | +| clip_range | 0.065 | +| entropy_loss | -7.64 | +| explained_variance | -0.0182 | +| learning_rate | 6.53e-05 | +| loss | -0.0287 | +| n_updates | 13284 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000159 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.276 | +| time/ | | +| fps | 1381 | +| iterations | 3323 | +| time_elapsed | 4927 | +| total_timesteps | 6805504 | +| train/ | | +| approx_kl | 0.009127994 | +| clip_fraction | 0.328 | +| clip_range | 0.065 | +| entropy_loss | -7.58 | +| explained_variance | -0.125 | +| learning_rate | 6.53e-05 | +| loss | -0.0298 | +| n_updates | 13288 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000199 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.278 | +| time/ | | +| fps | 1381 | +| iterations | 3324 | +| time_elapsed | 4928 | +| total_timesteps | 6807552 | +| train/ | | +| approx_kl | 0.0077238604 | +| clip_fraction | 0.324 | +| clip_range | 0.0649 | +| entropy_loss | -7.59 | +| explained_variance | 0.0715 | +| learning_rate | 6.53e-05 | +| loss | -0.0261 | +| n_updates | 13292 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000286 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.277 | +| time/ | | +| fps | 1381 | +| iterations | 3325 | +| time_elapsed | 4930 | +| total_timesteps | 6809600 | +| train/ | | +| approx_kl | 0.0095575405 | +| clip_fraction | 0.334 | +| clip_range | 0.0649 | +| entropy_loss | -7.62 | +| explained_variance | -0.122 | +| learning_rate | 6.52e-05 | +| loss | -0.0311 | +| n_updates | 13296 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000163 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.274 | +| time/ | | +| fps | 1381 | +| iterations | 3326 | +| time_elapsed | 4931 | +| total_timesteps | 6811648 | +| train/ | | +| approx_kl | 0.00889843 | +| clip_fraction | 0.316 | +| clip_range | 0.0649 | +| entropy_loss | -7.47 | +| explained_variance | -0.166 | +| learning_rate | 6.52e-05 | +| loss | -0.0261 | +| n_updates | 13300 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000204 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.277 | +| time/ | | +| fps | 1381 | +| iterations | 3327 | +| time_elapsed | 4933 | +| total_timesteps | 6813696 | +| train/ | | +| approx_kl | 0.010772057 | +| clip_fraction | 0.333 | +| clip_range | 0.0649 | +| entropy_loss | -7.64 | +| explained_variance | -0.0629 | +| learning_rate | 6.51e-05 | +| loss | -0.0336 | +| n_updates | 13304 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000223 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 1381 | +| iterations | 3328 | +| time_elapsed | 4934 | +| total_timesteps | 6815744 | +| train/ | | +| approx_kl | 0.010603679 | +| clip_fraction | 0.335 | +| clip_range | 0.0648 | +| entropy_loss | -7.38 | +| explained_variance | -0.0175 | +| learning_rate | 6.51e-05 | +| loss | -0.0329 | +| n_updates | 13308 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000193 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 1381 | +| iterations | 3329 | +| time_elapsed | 4935 | +| total_timesteps | 6817792 | +| train/ | | +| approx_kl | 0.012035072 | +| clip_fraction | 0.336 | +| clip_range | 0.0648 | +| entropy_loss | -7.58 | +| explained_variance | -0.211 | +| learning_rate | 6.5e-05 | +| loss | -0.0322 | +| n_updates | 13312 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000117 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.284 | +| time/ | | +| fps | 1381 | +| iterations | 3330 | +| time_elapsed | 4937 | +| total_timesteps | 6819840 | +| train/ | | +| approx_kl | 0.01016137 | +| clip_fraction | 0.34 | +| clip_range | 0.0648 | +| entropy_loss | -7.56 | +| explained_variance | -0.0611 | +| learning_rate | 6.5e-05 | +| loss | -0.0306 | +| n_updates | 13316 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000248 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.277 | +| time/ | | +| fps | 1381 | +| iterations | 3331 | +| time_elapsed | 4938 | +| total_timesteps | 6821888 | +| train/ | | +| approx_kl | 0.0103034545 | +| clip_fraction | 0.343 | +| clip_range | 0.0648 | +| entropy_loss | -7.57 | +| explained_variance | -0.0058 | +| learning_rate | 6.5e-05 | +| loss | -0.0332 | +| n_updates | 13320 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000114 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.277 | +| time/ | | +| fps | 1381 | +| iterations | 3332 | +| time_elapsed | 4940 | +| total_timesteps | 6823936 | +| train/ | | +| approx_kl | 0.008551624 | +| clip_fraction | 0.328 | +| clip_range | 0.0647 | +| entropy_loss | -7.64 | +| explained_variance | -0.00663 | +| learning_rate | 6.49e-05 | +| loss | -0.0325 | +| n_updates | 13324 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000173 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.277 | +| time/ | | +| fps | 1381 | +| iterations | 3333 | +| time_elapsed | 4941 | +| total_timesteps | 6825984 | +| train/ | | +| approx_kl | 0.009635797 | +| clip_fraction | 0.322 | +| clip_range | 0.0647 | +| entropy_loss | -7.55 | +| explained_variance | -0.102 | +| learning_rate | 6.49e-05 | +| loss | -0.0328 | +| n_updates | 13328 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000239 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.29 | +| time/ | | +| fps | 1381 | +| iterations | 3334 | +| time_elapsed | 4943 | +| total_timesteps | 6828032 | +| train/ | | +| approx_kl | 0.008593574 | +| clip_fraction | 0.311 | +| clip_range | 0.0647 | +| entropy_loss | -7.58 | +| explained_variance | 0.0566 | +| learning_rate | 6.48e-05 | +| loss | -0.0274 | +| n_updates | 13332 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000272 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.28 | +| time/ | | +| fps | 1381 | +| iterations | 3335 | +| time_elapsed | 4944 | +| total_timesteps | 6830080 | +| train/ | | +| approx_kl | 0.010254381 | +| clip_fraction | 0.322 | +| clip_range | 0.0646 | +| entropy_loss | -7.37 | +| explained_variance | -0.0673 | +| learning_rate | 6.48e-05 | +| loss | -0.0243 | +| n_updates | 13336 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000385 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.276 | +| time/ | | +| fps | 1381 | +| iterations | 3336 | +| time_elapsed | 4946 | +| total_timesteps | 6832128 | +| train/ | | +| approx_kl | 0.010372845 | +| clip_fraction | 0.35 | +| clip_range | 0.0646 | +| entropy_loss | -7.6 | +| explained_variance | -0.0993 | +| learning_rate | 6.48e-05 | +| loss | -0.0299 | +| n_updates | 13340 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000219 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.284 | +| time/ | | +| fps | 1381 | +| iterations | 3337 | +| time_elapsed | 4947 | +| total_timesteps | 6834176 | +| train/ | | +| approx_kl | 0.010829127 | +| clip_fraction | 0.376 | +| clip_range | 0.0646 | +| entropy_loss | -7.64 | +| explained_variance | -0.171 | +| learning_rate | 6.47e-05 | +| loss | -0.0372 | +| n_updates | 13344 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000139 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.28 | +| time/ | | +| fps | 1381 | +| iterations | 3338 | +| time_elapsed | 4949 | +| total_timesteps | 6836224 | +| train/ | | +| approx_kl | 0.009179002 | +| clip_fraction | 0.318 | +| clip_range | 0.0646 | +| entropy_loss | -7.5 | +| explained_variance | -0.108 | +| learning_rate | 6.47e-05 | +| loss | -0.029 | +| n_updates | 13348 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000327 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.28 | +| time/ | | +| fps | 1381 | +| iterations | 3339 | +| time_elapsed | 4950 | +| total_timesteps | 6838272 | +| train/ | | +| approx_kl | 0.010685038 | +| clip_fraction | 0.317 | +| clip_range | 0.0645 | +| entropy_loss | -7.46 | +| explained_variance | -0.131 | +| learning_rate | 6.46e-05 | +| loss | -0.0318 | +| n_updates | 13352 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000179 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.269 | +| time/ | | +| fps | 1381 | +| iterations | 3340 | +| time_elapsed | 4951 | +| total_timesteps | 6840320 | +| train/ | | +| approx_kl | 0.011494896 | +| clip_fraction | 0.342 | +| clip_range | 0.0645 | +| entropy_loss | -7.69 | +| explained_variance | -0.0543 | +| learning_rate | 6.46e-05 | +| loss | -0.0319 | +| n_updates | 13356 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000192 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.265 | +| time/ | | +| fps | 1381 | +| iterations | 3341 | +| time_elapsed | 4953 | +| total_timesteps | 6842368 | +| train/ | | +| approx_kl | 0.010799395 | +| clip_fraction | 0.354 | +| clip_range | 0.0645 | +| entropy_loss | -7.53 | +| explained_variance | -0.152 | +| learning_rate | 6.46e-05 | +| loss | -0.0335 | +| n_updates | 13360 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000135 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.265 | +| time/ | | +| fps | 1381 | +| iterations | 3342 | +| time_elapsed | 4954 | +| total_timesteps | 6844416 | +| train/ | | +| approx_kl | 0.010027159 | +| clip_fraction | 0.337 | +| clip_range | 0.0645 | +| entropy_loss | -7.51 | +| explained_variance | -0.0418 | +| learning_rate | 6.45e-05 | +| loss | -0.0305 | +| n_updates | 13364 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000219 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.265 | +| time/ | | +| fps | 1381 | +| iterations | 3343 | +| time_elapsed | 4956 | +| total_timesteps | 6846464 | +| train/ | | +| approx_kl | 0.00941849 | +| clip_fraction | 0.328 | +| clip_range | 0.0644 | +| entropy_loss | -7.76 | +| explained_variance | -0.0254 | +| learning_rate | 6.45e-05 | +| loss | -0.0272 | +| n_updates | 13368 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000156 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.264 | +| time/ | | +| fps | 1381 | +| iterations | 3344 | +| time_elapsed | 4957 | +| total_timesteps | 6848512 | +| train/ | | +| approx_kl | 0.009752821 | +| clip_fraction | 0.346 | +| clip_range | 0.0644 | +| entropy_loss | -7.63 | +| explained_variance | -0.138 | +| learning_rate | 6.44e-05 | +| loss | -0.0265 | +| n_updates | 13372 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.00016 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.261 | +| time/ | | +| fps | 1381 | +| iterations | 3345 | +| time_elapsed | 4959 | +| total_timesteps | 6850560 | +| train/ | | +| approx_kl | 0.010207863 | +| clip_fraction | 0.338 | +| clip_range | 0.0644 | +| entropy_loss | -7.61 | +| explained_variance | -0.0383 | +| learning_rate | 6.44e-05 | +| loss | -0.032 | +| n_updates | 13376 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.00014 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.271 | +| time/ | | +| fps | 1381 | +| iterations | 3346 | +| time_elapsed | 4960 | +| total_timesteps | 6852608 | +| train/ | | +| approx_kl | 0.008859995 | +| clip_fraction | 0.33 | +| clip_range | 0.0644 | +| entropy_loss | -7.59 | +| explained_variance | -0.0724 | +| learning_rate | 6.44e-05 | +| loss | -0.0279 | +| n_updates | 13380 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000264 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.274 | +| time/ | | +| fps | 1381 | +| iterations | 3347 | +| time_elapsed | 4962 | +| total_timesteps | 6854656 | +| train/ | | +| approx_kl | 0.008614376 | +| clip_fraction | 0.319 | +| clip_range | 0.0643 | +| entropy_loss | -7.58 | +| explained_variance | -0.0234 | +| learning_rate | 6.43e-05 | +| loss | -0.0295 | +| n_updates | 13384 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000194 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.28 | +| time/ | | +| fps | 1381 | +| iterations | 3348 | +| time_elapsed | 4963 | +| total_timesteps | 6856704 | +| train/ | | +| approx_kl | 0.013005251 | +| clip_fraction | 0.344 | +| clip_range | 0.0643 | +| entropy_loss | -7.65 | +| explained_variance | -0.084 | +| learning_rate | 6.43e-05 | +| loss | -0.0303 | +| n_updates | 13388 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.00018 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.278 | +| time/ | | +| fps | 1381 | +| iterations | 3349 | +| time_elapsed | 4965 | +| total_timesteps | 6858752 | +| train/ | | +| approx_kl | 0.010188997 | +| clip_fraction | 0.332 | +| clip_range | 0.0643 | +| entropy_loss | -7.64 | +| explained_variance | -0.154 | +| learning_rate | 6.42e-05 | +| loss | -0.0274 | +| n_updates | 13392 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000179 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.283 | +| time/ | | +| fps | 1381 | +| iterations | 3350 | +| time_elapsed | 4966 | +| total_timesteps | 6860800 | +| train/ | | +| approx_kl | 0.011760469 | +| clip_fraction | 0.359 | +| clip_range | 0.0643 | +| entropy_loss | -7.62 | +| explained_variance | -0.272 | +| learning_rate | 6.42e-05 | +| loss | -0.0357 | +| n_updates | 13396 | +| policy_gradient_loss | -0.021 | +| value_loss | 9.87e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.283 | +| time/ | | +| fps | 1381 | +| iterations | 3351 | +| time_elapsed | 4967 | +| total_timesteps | 6862848 | +| train/ | | +| approx_kl | 0.010316594 | +| clip_fraction | 0.332 | +| clip_range | 0.0642 | +| entropy_loss | -7.55 | +| explained_variance | -0.0622 | +| learning_rate | 6.42e-05 | +| loss | -0.0245 | +| n_updates | 13400 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000188 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.278 | +| time/ | | +| fps | 1381 | +| iterations | 3352 | +| time_elapsed | 4969 | +| total_timesteps | 6864896 | +| train/ | | +| approx_kl | 0.01028748 | +| clip_fraction | 0.346 | +| clip_range | 0.0642 | +| entropy_loss | -7.67 | +| explained_variance | -0.231 | +| learning_rate | 6.41e-05 | +| loss | -0.0246 | +| n_updates | 13404 | +| policy_gradient_loss | -0.02 | +| value_loss | 9.85e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.276 | +| time/ | | +| fps | 1381 | +| iterations | 3353 | +| time_elapsed | 4970 | +| total_timesteps | 6866944 | +| train/ | | +| approx_kl | 0.009000177 | +| clip_fraction | 0.345 | +| clip_range | 0.0642 | +| entropy_loss | -7.61 | +| explained_variance | -0.0639 | +| learning_rate | 6.41e-05 | +| loss | -0.0288 | +| n_updates | 13408 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000174 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 1381 | +| iterations | 3354 | +| time_elapsed | 4972 | +| total_timesteps | 6868992 | +| train/ | | +| approx_kl | 0.010020662 | +| clip_fraction | 0.323 | +| clip_range | 0.0642 | +| entropy_loss | -7.57 | +| explained_variance | -0.049 | +| learning_rate | 6.4e-05 | +| loss | -0.0253 | +| n_updates | 13412 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000184 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.271 | +| time/ | | +| fps | 1381 | +| iterations | 3355 | +| time_elapsed | 4973 | +| total_timesteps | 6871040 | +| train/ | | +| approx_kl | 0.009958062 | +| clip_fraction | 0.309 | +| clip_range | 0.0641 | +| entropy_loss | -7.44 | +| explained_variance | 0.0435 | +| learning_rate | 6.4e-05 | +| loss | -0.0238 | +| n_updates | 13416 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000216 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.273 | +| time/ | | +| fps | 1381 | +| iterations | 3356 | +| time_elapsed | 4975 | +| total_timesteps | 6873088 | +| train/ | | +| approx_kl | 0.011356195 | +| clip_fraction | 0.342 | +| clip_range | 0.0641 | +| entropy_loss | -7.61 | +| explained_variance | -0.104 | +| learning_rate | 6.4e-05 | +| loss | -0.0312 | +| n_updates | 13420 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000242 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.272 | +| time/ | | +| fps | 1381 | +| iterations | 3357 | +| time_elapsed | 4976 | +| total_timesteps | 6875136 | +| train/ | | +| approx_kl | 0.012006316 | +| clip_fraction | 0.363 | +| clip_range | 0.0641 | +| entropy_loss | -7.41 | +| explained_variance | -0.287 | +| learning_rate | 6.39e-05 | +| loss | -0.0291 | +| n_updates | 13424 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000144 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.272 | +| time/ | | +| fps | 1381 | +| iterations | 3358 | +| time_elapsed | 4977 | +| total_timesteps | 6877184 | +| train/ | | +| approx_kl | 0.012105396 | +| clip_fraction | 0.359 | +| clip_range | 0.0641 | +| entropy_loss | -7.56 | +| explained_variance | -0.126 | +| learning_rate | 6.39e-05 | +| loss | -0.0356 | +| n_updates | 13428 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000189 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.272 | +| time/ | | +| fps | 1381 | +| iterations | 3359 | +| time_elapsed | 4979 | +| total_timesteps | 6879232 | +| train/ | | +| approx_kl | 0.012292108 | +| clip_fraction | 0.349 | +| clip_range | 0.064 | +| entropy_loss | -7.6 | +| explained_variance | -0.156 | +| learning_rate | 6.38e-05 | +| loss | -0.0318 | +| n_updates | 13432 | +| policy_gradient_loss | -0.0204 | +| value_loss | 9.4e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.272 | +| time/ | | +| fps | 1381 | +| iterations | 3360 | +| time_elapsed | 4980 | +| total_timesteps | 6881280 | +| train/ | | +| approx_kl | 0.009907736 | +| clip_fraction | 0.336 | +| clip_range | 0.064 | +| entropy_loss | -7.75 | +| explained_variance | -0.111 | +| learning_rate | 6.38e-05 | +| loss | -0.0296 | +| n_updates | 13436 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000136 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.269 | +| time/ | | +| fps | 1381 | +| iterations | 3361 | +| time_elapsed | 4982 | +| total_timesteps | 6883328 | +| train/ | | +| approx_kl | 0.009615707 | +| clip_fraction | 0.365 | +| clip_range | 0.064 | +| entropy_loss | -7.64 | +| explained_variance | -0.0341 | +| learning_rate | 6.38e-05 | +| loss | -0.0286 | +| n_updates | 13440 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000233 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.266 | +| time/ | | +| fps | 1381 | +| iterations | 3362 | +| time_elapsed | 4983 | +| total_timesteps | 6885376 | +| train/ | | +| approx_kl | 0.009879363 | +| clip_fraction | 0.358 | +| clip_range | 0.064 | +| entropy_loss | -7.63 | +| explained_variance | -0.0143 | +| learning_rate | 6.37e-05 | +| loss | -0.0293 | +| n_updates | 13444 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000148 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.265 | +| time/ | | +| fps | 1381 | +| iterations | 3363 | +| time_elapsed | 4985 | +| total_timesteps | 6887424 | +| train/ | | +| approx_kl | 0.010246595 | +| clip_fraction | 0.346 | +| clip_range | 0.0639 | +| entropy_loss | -7.54 | +| explained_variance | -0.157 | +| learning_rate | 6.37e-05 | +| loss | -0.0311 | +| n_updates | 13448 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000115 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.26 | +| time/ | | +| fps | 1381 | +| iterations | 3364 | +| time_elapsed | 4986 | +| total_timesteps | 6889472 | +| train/ | | +| approx_kl | 0.009337109 | +| clip_fraction | 0.322 | +| clip_range | 0.0639 | +| entropy_loss | -7.59 | +| explained_variance | -0.00839 | +| learning_rate | 6.36e-05 | +| loss | -0.0248 | +| n_updates | 13452 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000291 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.252 | +| time/ | | +| fps | 1381 | +| iterations | 3365 | +| time_elapsed | 4987 | +| total_timesteps | 6891520 | +| train/ | | +| approx_kl | 0.011209767 | +| clip_fraction | 0.347 | +| clip_range | 0.0639 | +| entropy_loss | -7.42 | +| explained_variance | -0.124 | +| learning_rate | 6.36e-05 | +| loss | -0.037 | +| n_updates | 13456 | +| policy_gradient_loss | -0.0193 | +| value_loss | 9.85e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.256 | +| time/ | | +| fps | 1381 | +| iterations | 3366 | +| time_elapsed | 4989 | +| total_timesteps | 6893568 | +| train/ | | +| approx_kl | 0.013026951 | +| clip_fraction | 0.393 | +| clip_range | 0.0639 | +| entropy_loss | -7.54 | +| explained_variance | -0.384 | +| learning_rate | 6.35e-05 | +| loss | -0.0324 | +| n_updates | 13460 | +| policy_gradient_loss | -0.0226 | +| value_loss | 6.4e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.256 | +| time/ | | +| fps | 1381 | +| iterations | 3367 | +| time_elapsed | 4991 | +| total_timesteps | 6895616 | +| train/ | | +| approx_kl | 0.009448617 | +| clip_fraction | 0.297 | +| clip_range | 0.0638 | +| entropy_loss | -7.54 | +| explained_variance | 0.00894 | +| learning_rate | 6.35e-05 | +| loss | -0.0267 | +| n_updates | 13464 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000136 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.252 | +| time/ | | +| fps | 1381 | +| iterations | 3368 | +| time_elapsed | 4992 | +| total_timesteps | 6897664 | +| train/ | | +| approx_kl | 0.009466508 | +| clip_fraction | 0.323 | +| clip_range | 0.0638 | +| entropy_loss | -7.75 | +| explained_variance | 0.0554 | +| learning_rate | 6.35e-05 | +| loss | -0.0306 | +| n_updates | 13468 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000186 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.251 | +| time/ | | +| fps | 1381 | +| iterations | 3369 | +| time_elapsed | 4993 | +| total_timesteps | 6899712 | +| train/ | | +| approx_kl | 0.010470462 | +| clip_fraction | 0.332 | +| clip_range | 0.0638 | +| entropy_loss | -7.63 | +| explained_variance | -0.117 | +| learning_rate | 6.34e-05 | +| loss | -0.0309 | +| n_updates | 13472 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000168 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.263 | +| time/ | | +| fps | 1381 | +| iterations | 3370 | +| time_elapsed | 4995 | +| total_timesteps | 6901760 | +| train/ | | +| approx_kl | 0.011282466 | +| clip_fraction | 0.356 | +| clip_range | 0.0638 | +| entropy_loss | -7.6 | +| explained_variance | -0.0882 | +| learning_rate | 6.34e-05 | +| loss | -0.03 | +| n_updates | 13476 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000153 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.266 | +| time/ | | +| fps | 1381 | +| iterations | 3371 | +| time_elapsed | 4996 | +| total_timesteps | 6903808 | +| train/ | | +| approx_kl | 0.010600937 | +| clip_fraction | 0.335 | +| clip_range | 0.0637 | +| entropy_loss | -7.49 | +| explained_variance | -0.0303 | +| learning_rate | 6.33e-05 | +| loss | -0.027 | +| n_updates | 13480 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000204 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.263 | +| time/ | | +| fps | 1381 | +| iterations | 3372 | +| time_elapsed | 4998 | +| total_timesteps | 6905856 | +| train/ | | +| approx_kl | 0.008938026 | +| clip_fraction | 0.319 | +| clip_range | 0.0637 | +| entropy_loss | -7.57 | +| explained_variance | 0.0631 | +| learning_rate | 6.33e-05 | +| loss | -0.027 | +| n_updates | 13484 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000255 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.258 | +| time/ | | +| fps | 1381 | +| iterations | 3373 | +| time_elapsed | 4999 | +| total_timesteps | 6907904 | +| train/ | | +| approx_kl | 0.01189411 | +| clip_fraction | 0.335 | +| clip_range | 0.0637 | +| entropy_loss | -7.63 | +| explained_variance | -0.084 | +| learning_rate | 6.33e-05 | +| loss | -0.0269 | +| n_updates | 13488 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000182 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.255 | +| time/ | | +| fps | 1381 | +| iterations | 3374 | +| time_elapsed | 5001 | +| total_timesteps | 6909952 | +| train/ | | +| approx_kl | 0.011124623 | +| clip_fraction | 0.363 | +| clip_range | 0.0637 | +| entropy_loss | -7.48 | +| explained_variance | -0.336 | +| learning_rate | 6.32e-05 | +| loss | -0.031 | +| n_updates | 13492 | +| policy_gradient_loss | -0.0219 | +| value_loss | 9.91e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.255 | +| time/ | | +| fps | 1381 | +| iterations | 3375 | +| time_elapsed | 5002 | +| total_timesteps | 6912000 | +| train/ | | +| approx_kl | 0.00991452 | +| clip_fraction | 0.33 | +| clip_range | 0.0636 | +| entropy_loss | -7.53 | +| explained_variance | -0.135 | +| learning_rate | 6.32e-05 | +| loss | -0.0308 | +| n_updates | 13496 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000161 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.26 | +| time/ | | +| fps | 1381 | +| iterations | 3376 | +| time_elapsed | 5003 | +| total_timesteps | 6914048 | +| train/ | | +| approx_kl | 0.0103756925 | +| clip_fraction | 0.335 | +| clip_range | 0.0636 | +| entropy_loss | -7.45 | +| explained_variance | -0.0743 | +| learning_rate | 6.31e-05 | +| loss | -0.0244 | +| n_updates | 13500 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000208 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.26 | +| time/ | | +| fps | 1381 | +| iterations | 3377 | +| time_elapsed | 5005 | +| total_timesteps | 6916096 | +| train/ | | +| approx_kl | 0.011268729 | +| clip_fraction | 0.348 | +| clip_range | 0.0636 | +| entropy_loss | -7.53 | +| explained_variance | -0.0236 | +| learning_rate | 6.31e-05 | +| loss | -0.0291 | +| n_updates | 13504 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000113 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.26 | +| time/ | | +| fps | 1381 | +| iterations | 3378 | +| time_elapsed | 5006 | +| total_timesteps | 6918144 | +| train/ | | +| approx_kl | 0.009234876 | +| clip_fraction | 0.331 | +| clip_range | 0.0635 | +| entropy_loss | -7.65 | +| explained_variance | -0.0426 | +| learning_rate | 6.31e-05 | +| loss | -0.0286 | +| n_updates | 13508 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000143 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.257 | +| time/ | | +| fps | 1381 | +| iterations | 3379 | +| time_elapsed | 5008 | +| total_timesteps | 6920192 | +| train/ | | +| approx_kl | 0.009466228 | +| clip_fraction | 0.348 | +| clip_range | 0.0635 | +| entropy_loss | -7.71 | +| explained_variance | -0.0695 | +| learning_rate | 6.3e-05 | +| loss | -0.0315 | +| n_updates | 13512 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000103 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.257 | +| time/ | | +| fps | 1381 | +| iterations | 3380 | +| time_elapsed | 5009 | +| total_timesteps | 6922240 | +| train/ | | +| approx_kl | 0.010018924 | +| clip_fraction | 0.336 | +| clip_range | 0.0635 | +| entropy_loss | -7.66 | +| explained_variance | -0.104 | +| learning_rate | 6.3e-05 | +| loss | -0.0289 | +| n_updates | 13516 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000119 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.265 | +| time/ | | +| fps | 1381 | +| iterations | 3381 | +| time_elapsed | 5011 | +| total_timesteps | 6924288 | +| train/ | | +| approx_kl | 0.0075490302 | +| clip_fraction | 0.32 | +| clip_range | 0.0635 | +| entropy_loss | -7.65 | +| explained_variance | -0.0239 | +| learning_rate | 6.29e-05 | +| loss | -0.0245 | +| n_updates | 13520 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000229 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.266 | +| time/ | | +| fps | 1381 | +| iterations | 3382 | +| time_elapsed | 5012 | +| total_timesteps | 6926336 | +| train/ | | +| approx_kl | 0.00883598 | +| clip_fraction | 0.334 | +| clip_range | 0.0634 | +| entropy_loss | -7.5 | +| explained_variance | -0.113 | +| learning_rate | 6.29e-05 | +| loss | -0.0208 | +| n_updates | 13524 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000139 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.267 | +| time/ | | +| fps | 1381 | +| iterations | 3383 | +| time_elapsed | 5014 | +| total_timesteps | 6928384 | +| train/ | | +| approx_kl | 0.0104067605 | +| clip_fraction | 0.331 | +| clip_range | 0.0634 | +| entropy_loss | -7.5 | +| explained_variance | -0.0239 | +| learning_rate | 6.29e-05 | +| loss | -0.0284 | +| n_updates | 13528 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000179 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.269 | +| time/ | | +| fps | 1381 | +| iterations | 3384 | +| time_elapsed | 5015 | +| total_timesteps | 6930432 | +| train/ | | +| approx_kl | 0.0106937215 | +| clip_fraction | 0.34 | +| clip_range | 0.0634 | +| entropy_loss | -7.6 | +| explained_variance | -0.0538 | +| learning_rate | 6.28e-05 | +| loss | -0.0337 | +| n_updates | 13532 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000248 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.265 | +| time/ | | +| fps | 1381 | +| iterations | 3385 | +| time_elapsed | 5017 | +| total_timesteps | 6932480 | +| train/ | | +| approx_kl | 0.008743441 | +| clip_fraction | 0.364 | +| clip_range | 0.0634 | +| entropy_loss | -7.58 | +| explained_variance | -0.306 | +| learning_rate | 6.28e-05 | +| loss | -0.0336 | +| n_updates | 13536 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.00016 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.263 | +| time/ | | +| fps | 1381 | +| iterations | 3386 | +| time_elapsed | 5018 | +| total_timesteps | 6934528 | +| train/ | | +| approx_kl | 0.009536793 | +| clip_fraction | 0.345 | +| clip_range | 0.0633 | +| entropy_loss | -7.57 | +| explained_variance | -0.0327 | +| learning_rate | 6.27e-05 | +| loss | -0.0311 | +| n_updates | 13540 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000147 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.268 | +| time/ | | +| fps | 1381 | +| iterations | 3387 | +| time_elapsed | 5020 | +| total_timesteps | 6936576 | +| train/ | | +| approx_kl | 0.00907715 | +| clip_fraction | 0.316 | +| clip_range | 0.0633 | +| entropy_loss | -7.6 | +| explained_variance | 0.00768 | +| learning_rate | 6.27e-05 | +| loss | -0.0279 | +| n_updates | 13544 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.00019 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.264 | +| time/ | | +| fps | 1381 | +| iterations | 3388 | +| time_elapsed | 5021 | +| total_timesteps | 6938624 | +| train/ | | +| approx_kl | 0.007999599 | +| clip_fraction | 0.316 | +| clip_range | 0.0633 | +| entropy_loss | -7.59 | +| explained_variance | 0.0464 | +| learning_rate | 6.27e-05 | +| loss | -0.0275 | +| n_updates | 13548 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000314 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.264 | +| time/ | | +| fps | 1381 | +| iterations | 3389 | +| time_elapsed | 5022 | +| total_timesteps | 6940672 | +| train/ | | +| approx_kl | 0.009525084 | +| clip_fraction | 0.355 | +| clip_range | 0.0633 | +| entropy_loss | -7.64 | +| explained_variance | -0.177 | +| learning_rate | 6.26e-05 | +| loss | -0.0287 | +| n_updates | 13552 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.00017 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.26 | +| time/ | | +| fps | 1381 | +| iterations | 3390 | +| time_elapsed | 5024 | +| total_timesteps | 6942720 | +| train/ | | +| approx_kl | 0.011792228 | +| clip_fraction | 0.356 | +| clip_range | 0.0632 | +| entropy_loss | -7.54 | +| explained_variance | -0.158 | +| learning_rate | 6.26e-05 | +| loss | -0.032 | +| n_updates | 13556 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000173 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.263 | +| time/ | | +| fps | 1381 | +| iterations | 3391 | +| time_elapsed | 5025 | +| total_timesteps | 6944768 | +| train/ | | +| approx_kl | 0.010334412 | +| clip_fraction | 0.338 | +| clip_range | 0.0632 | +| entropy_loss | -7.68 | +| explained_variance | -0.282 | +| learning_rate | 6.25e-05 | +| loss | -0.0286 | +| n_updates | 13560 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000134 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.26 | +| time/ | | +| fps | 1381 | +| iterations | 3392 | +| time_elapsed | 5027 | +| total_timesteps | 6946816 | +| train/ | | +| approx_kl | 0.009739241 | +| clip_fraction | 0.329 | +| clip_range | 0.0632 | +| entropy_loss | -7.67 | +| explained_variance | -0.0345 | +| learning_rate | 6.25e-05 | +| loss | -0.0282 | +| n_updates | 13564 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.00013 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.257 | +| time/ | | +| fps | 1381 | +| iterations | 3393 | +| time_elapsed | 5028 | +| total_timesteps | 6948864 | +| train/ | | +| approx_kl | 0.008807878 | +| clip_fraction | 0.345 | +| clip_range | 0.0632 | +| entropy_loss | -7.51 | +| explained_variance | -0.101 | +| learning_rate | 6.25e-05 | +| loss | -0.0315 | +| n_updates | 13568 | +| policy_gradient_loss | -0.0185 | +| value_loss | 5.61e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.256 | +| time/ | | +| fps | 1381 | +| iterations | 3394 | +| time_elapsed | 5030 | +| total_timesteps | 6950912 | +| train/ | | +| approx_kl | 0.008635866 | +| clip_fraction | 0.332 | +| clip_range | 0.0631 | +| entropy_loss | -7.68 | +| explained_variance | -0.0994 | +| learning_rate | 6.24e-05 | +| loss | -0.0261 | +| n_updates | 13572 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000199 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.255 | +| time/ | | +| fps | 1381 | +| iterations | 3395 | +| time_elapsed | 5031 | +| total_timesteps | 6952960 | +| train/ | | +| approx_kl | 0.009231302 | +| clip_fraction | 0.324 | +| clip_range | 0.0631 | +| entropy_loss | -7.62 | +| explained_variance | 0.0384 | +| learning_rate | 6.24e-05 | +| loss | -0.0294 | +| n_updates | 13576 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000134 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.254 | +| time/ | | +| fps | 1381 | +| iterations | 3396 | +| time_elapsed | 5033 | +| total_timesteps | 6955008 | +| train/ | | +| approx_kl | 0.009691024 | +| clip_fraction | 0.353 | +| clip_range | 0.0631 | +| entropy_loss | -7.43 | +| explained_variance | 0.0111 | +| learning_rate | 6.23e-05 | +| loss | -0.0294 | +| n_updates | 13580 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000113 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.251 | +| time/ | | +| fps | 1381 | +| iterations | 3397 | +| time_elapsed | 5034 | +| total_timesteps | 6957056 | +| train/ | | +| approx_kl | 0.009914924 | +| clip_fraction | 0.355 | +| clip_range | 0.0631 | +| entropy_loss | -7.52 | +| explained_variance | -0.0788 | +| learning_rate | 6.23e-05 | +| loss | -0.0249 | +| n_updates | 13584 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000157 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.252 | +| time/ | | +| fps | 1381 | +| iterations | 3398 | +| time_elapsed | 5036 | +| total_timesteps | 6959104 | +| train/ | | +| approx_kl | 0.010185387 | +| clip_fraction | 0.341 | +| clip_range | 0.063 | +| entropy_loss | -7.61 | +| explained_variance | -0.112 | +| learning_rate | 6.23e-05 | +| loss | -0.0317 | +| n_updates | 13588 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000161 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.25 | +| time/ | | +| fps | 1381 | +| iterations | 3399 | +| time_elapsed | 5037 | +| total_timesteps | 6961152 | +| train/ | | +| approx_kl | 0.010649914 | +| clip_fraction | 0.34 | +| clip_range | 0.063 | +| entropy_loss | -7.68 | +| explained_variance | -0.0568 | +| learning_rate | 6.22e-05 | +| loss | -0.0303 | +| n_updates | 13592 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000119 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.248 | +| time/ | | +| fps | 1381 | +| iterations | 3400 | +| time_elapsed | 5038 | +| total_timesteps | 6963200 | +| train/ | | +| approx_kl | 0.009548578 | +| clip_fraction | 0.32 | +| clip_range | 0.063 | +| entropy_loss | -7.55 | +| explained_variance | -0.0513 | +| learning_rate | 6.22e-05 | +| loss | -0.0284 | +| n_updates | 13596 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000128 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.236 | +| time/ | | +| fps | 1381 | +| iterations | 3401 | +| time_elapsed | 5040 | +| total_timesteps | 6965248 | +| train/ | | +| approx_kl | 0.010658829 | +| clip_fraction | 0.368 | +| clip_range | 0.063 | +| entropy_loss | -7.59 | +| explained_variance | -0.418 | +| learning_rate | 6.21e-05 | +| loss | -0.0349 | +| n_updates | 13600 | +| policy_gradient_loss | -0.019 | +| value_loss | 8.78e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.236 | +| time/ | | +| fps | 1381 | +| iterations | 3402 | +| time_elapsed | 5041 | +| total_timesteps | 6967296 | +| train/ | | +| approx_kl | 0.009806061 | +| clip_fraction | 0.327 | +| clip_range | 0.0629 | +| entropy_loss | -7.37 | +| explained_variance | -0.0355 | +| learning_rate | 6.21e-05 | +| loss | -0.0295 | +| n_updates | 13604 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.00018 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.237 | +| time/ | | +| fps | 1381 | +| iterations | 3403 | +| time_elapsed | 5043 | +| total_timesteps | 6969344 | +| train/ | | +| approx_kl | 0.01003344 | +| clip_fraction | 0.349 | +| clip_range | 0.0629 | +| entropy_loss | -7.67 | +| explained_variance | -0.0664 | +| learning_rate | 6.2e-05 | +| loss | -0.0286 | +| n_updates | 13608 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000125 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.237 | +| time/ | | +| fps | 1381 | +| iterations | 3404 | +| time_elapsed | 5044 | +| total_timesteps | 6971392 | +| train/ | | +| approx_kl | 0.008188885 | +| clip_fraction | 0.341 | +| clip_range | 0.0629 | +| entropy_loss | -7.65 | +| explained_variance | -0.0143 | +| learning_rate | 6.2e-05 | +| loss | -0.0295 | +| n_updates | 13612 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000215 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.241 | +| time/ | | +| fps | 1381 | +| iterations | 3405 | +| time_elapsed | 5046 | +| total_timesteps | 6973440 | +| train/ | | +| approx_kl | 0.009337854 | +| clip_fraction | 0.329 | +| clip_range | 0.0629 | +| entropy_loss | -7.6 | +| explained_variance | -0.0345 | +| learning_rate | 6.2e-05 | +| loss | -0.0293 | +| n_updates | 13616 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000139 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.24 | +| time/ | | +| fps | 1381 | +| iterations | 3406 | +| time_elapsed | 5047 | +| total_timesteps | 6975488 | +| train/ | | +| approx_kl | 0.010300076 | +| clip_fraction | 0.333 | +| clip_range | 0.0628 | +| entropy_loss | -7.6 | +| explained_variance | 0.0134 | +| learning_rate | 6.19e-05 | +| loss | -0.0284 | +| n_updates | 13620 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000176 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.24 | +| time/ | | +| fps | 1381 | +| iterations | 3407 | +| time_elapsed | 5048 | +| total_timesteps | 6977536 | +| train/ | | +| approx_kl | 0.009972442 | +| clip_fraction | 0.327 | +| clip_range | 0.0628 | +| entropy_loss | -7.62 | +| explained_variance | -0.207 | +| learning_rate | 6.19e-05 | +| loss | -0.0224 | +| n_updates | 13624 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000153 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.237 | +| time/ | | +| fps | 1381 | +| iterations | 3408 | +| time_elapsed | 5050 | +| total_timesteps | 6979584 | +| train/ | | +| approx_kl | 0.009945435 | +| clip_fraction | 0.333 | +| clip_range | 0.0628 | +| entropy_loss | -7.68 | +| explained_variance | -0.0117 | +| learning_rate | 6.18e-05 | +| loss | -0.0267 | +| n_updates | 13628 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000214 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.241 | +| time/ | | +| fps | 1381 | +| iterations | 3409 | +| time_elapsed | 5051 | +| total_timesteps | 6981632 | +| train/ | | +| approx_kl | 0.008895393 | +| clip_fraction | 0.322 | +| clip_range | 0.0628 | +| entropy_loss | -7.68 | +| explained_variance | -0.0552 | +| learning_rate | 6.18e-05 | +| loss | -0.0312 | +| n_updates | 13632 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000177 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.245 | +| time/ | | +| fps | 1381 | +| iterations | 3410 | +| time_elapsed | 5053 | +| total_timesteps | 6983680 | +| train/ | | +| approx_kl | 0.008759867 | +| clip_fraction | 0.364 | +| clip_range | 0.0627 | +| entropy_loss | -7.54 | +| explained_variance | -0.0623 | +| learning_rate | 6.18e-05 | +| loss | -0.0296 | +| n_updates | 13636 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.245 | +| time/ | | +| fps | 1381 | +| iterations | 3411 | +| time_elapsed | 5054 | +| total_timesteps | 6985728 | +| train/ | | +| approx_kl | 0.009366516 | +| clip_fraction | 0.332 | +| clip_range | 0.0627 | +| entropy_loss | -7.56 | +| explained_variance | -0.025 | +| learning_rate | 6.17e-05 | +| loss | -0.0275 | +| n_updates | 13640 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000271 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.241 | +| time/ | | +| fps | 1382 | +| iterations | 3412 | +| time_elapsed | 5056 | +| total_timesteps | 6987776 | +| train/ | | +| approx_kl | 0.010042769 | +| clip_fraction | 0.348 | +| clip_range | 0.0627 | +| entropy_loss | -7.62 | +| explained_variance | -0.133 | +| learning_rate | 6.17e-05 | +| loss | -0.0288 | +| n_updates | 13644 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000135 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.239 | +| time/ | | +| fps | 1382 | +| iterations | 3413 | +| time_elapsed | 5057 | +| total_timesteps | 6989824 | +| train/ | | +| approx_kl | 0.008192159 | +| clip_fraction | 0.323 | +| clip_range | 0.0627 | +| entropy_loss | -7.55 | +| explained_variance | -0.000781 | +| learning_rate | 6.16e-05 | +| loss | -0.0316 | +| n_updates | 13648 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000244 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.248 | +| time/ | | +| fps | 1382 | +| iterations | 3414 | +| time_elapsed | 5059 | +| total_timesteps | 6991872 | +| train/ | | +| approx_kl | 0.009314499 | +| clip_fraction | 0.332 | +| clip_range | 0.0626 | +| entropy_loss | -7.68 | +| explained_variance | -0.139 | +| learning_rate | 6.16e-05 | +| loss | -0.0265 | +| n_updates | 13652 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.00025 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.247 | +| time/ | | +| fps | 1382 | +| iterations | 3415 | +| time_elapsed | 5060 | +| total_timesteps | 6993920 | +| train/ | | +| approx_kl | 0.0073266495 | +| clip_fraction | 0.295 | +| clip_range | 0.0626 | +| entropy_loss | -7.63 | +| explained_variance | 0.063 | +| learning_rate | 6.16e-05 | +| loss | -0.0327 | +| n_updates | 13656 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000202 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.247 | +| time/ | | +| fps | 1382 | +| iterations | 3416 | +| time_elapsed | 5061 | +| total_timesteps | 6995968 | +| train/ | | +| approx_kl | 0.009170961 | +| clip_fraction | 0.349 | +| clip_range | 0.0626 | +| entropy_loss | -7.5 | +| explained_variance | -0.147 | +| learning_rate | 6.15e-05 | +| loss | -0.0343 | +| n_updates | 13660 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000208 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.246 | +| time/ | | +| fps | 1382 | +| iterations | 3417 | +| time_elapsed | 5063 | +| total_timesteps | 6998016 | +| train/ | | +| approx_kl | 0.010294759 | +| clip_fraction | 0.344 | +| clip_range | 0.0626 | +| entropy_loss | -7.5 | +| explained_variance | -0.0631 | +| learning_rate | 6.15e-05 | +| loss | -0.0295 | +| n_updates | 13664 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000209 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.246 | +| time/ | | +| fps | 1382 | +| iterations | 3418 | +| time_elapsed | 5064 | +| total_timesteps | 7000064 | +| train/ | | +| approx_kl | 0.009673343 | +| clip_fraction | 0.362 | +| clip_range | 0.0625 | +| entropy_loss | -7.64 | +| explained_variance | -0.272 | +| learning_rate | 6.14e-05 | +| loss | -0.0313 | +| n_updates | 13668 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000116 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.252 | +| time/ | | +| fps | 1382 | +| iterations | 3419 | +| time_elapsed | 5066 | +| total_timesteps | 7002112 | +| train/ | | +| approx_kl | 0.009495341 | +| clip_fraction | 0.341 | +| clip_range | 0.0625 | +| entropy_loss | -7.73 | +| explained_variance | -0.0841 | +| learning_rate | 6.14e-05 | +| loss | -0.0288 | +| n_updates | 13672 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000126 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.245 | +| time/ | | +| fps | 1382 | +| iterations | 3420 | +| time_elapsed | 5067 | +| total_timesteps | 7004160 | +| train/ | | +| approx_kl | 0.008466614 | +| clip_fraction | 0.318 | +| clip_range | 0.0625 | +| entropy_loss | -7.58 | +| explained_variance | 0.0143 | +| learning_rate | 6.14e-05 | +| loss | -0.0298 | +| n_updates | 13676 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000153 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.252 | +| time/ | | +| fps | 1382 | +| iterations | 3421 | +| time_elapsed | 5069 | +| total_timesteps | 7006208 | +| train/ | | +| approx_kl | 0.008774012 | +| clip_fraction | 0.34 | +| clip_range | 0.0624 | +| entropy_loss | -7.69 | +| explained_variance | -0.237 | +| learning_rate | 6.13e-05 | +| loss | -0.0282 | +| n_updates | 13680 | +| policy_gradient_loss | -0.0189 | +| value_loss | 6.58e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.255 | +| time/ | | +| fps | 1382 | +| iterations | 3422 | +| time_elapsed | 5070 | +| total_timesteps | 7008256 | +| train/ | | +| approx_kl | 0.008263195 | +| clip_fraction | 0.33 | +| clip_range | 0.0624 | +| entropy_loss | -7.59 | +| explained_variance | -0.227 | +| learning_rate | 6.13e-05 | +| loss | -0.0283 | +| n_updates | 13684 | +| policy_gradient_loss | -0.0186 | +| value_loss | 7.55e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.255 | +| time/ | | +| fps | 1382 | +| iterations | 3423 | +| time_elapsed | 5072 | +| total_timesteps | 7010304 | +| train/ | | +| approx_kl | 0.00755944 | +| clip_fraction | 0.31 | +| clip_range | 0.0624 | +| entropy_loss | -7.55 | +| explained_variance | 0.0422 | +| learning_rate | 6.12e-05 | +| loss | -0.0232 | +| n_updates | 13688 | +| policy_gradient_loss | -0.0146 | +| value_loss | 0.000255 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.256 | +| time/ | | +| fps | 1382 | +| iterations | 3424 | +| time_elapsed | 5073 | +| total_timesteps | 7012352 | +| train/ | | +| approx_kl | 0.0078872405 | +| clip_fraction | 0.334 | +| clip_range | 0.0624 | +| entropy_loss | -7.7 | +| explained_variance | -0.0626 | +| learning_rate | 6.12e-05 | +| loss | -0.0292 | +| n_updates | 13692 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000152 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.256 | +| time/ | | +| fps | 1382 | +| iterations | 3425 | +| time_elapsed | 5075 | +| total_timesteps | 7014400 | +| train/ | | +| approx_kl | 0.008169303 | +| clip_fraction | 0.293 | +| clip_range | 0.0623 | +| entropy_loss | -7.67 | +| explained_variance | -0.0835 | +| learning_rate | 6.12e-05 | +| loss | -0.023 | +| n_updates | 13696 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.00025 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.26 | +| time/ | | +| fps | 1382 | +| iterations | 3426 | +| time_elapsed | 5076 | +| total_timesteps | 7016448 | +| train/ | | +| approx_kl | 0.008000897 | +| clip_fraction | 0.33 | +| clip_range | 0.0623 | +| entropy_loss | -7.75 | +| explained_variance | -0.0891 | +| learning_rate | 6.11e-05 | +| loss | -0.0263 | +| n_updates | 13700 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000205 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.27 | +| time/ | | +| fps | 1382 | +| iterations | 3427 | +| time_elapsed | 5077 | +| total_timesteps | 7018496 | +| train/ | | +| approx_kl | 0.0069601624 | +| clip_fraction | 0.321 | +| clip_range | 0.0623 | +| entropy_loss | -7.61 | +| explained_variance | -0.0715 | +| learning_rate | 6.11e-05 | +| loss | -0.0265 | +| n_updates | 13704 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000175 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.272 | +| time/ | | +| fps | 1382 | +| iterations | 3428 | +| time_elapsed | 5079 | +| total_timesteps | 7020544 | +| train/ | | +| approx_kl | 0.007736324 | +| clip_fraction | 0.3 | +| clip_range | 0.0623 | +| entropy_loss | -7.59 | +| explained_variance | 0.000452 | +| learning_rate | 6.1e-05 | +| loss | -0.0284 | +| n_updates | 13708 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000252 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.278 | +| time/ | | +| fps | 1382 | +| iterations | 3429 | +| time_elapsed | 5080 | +| total_timesteps | 7022592 | +| train/ | | +| approx_kl | 0.007970244 | +| clip_fraction | 0.313 | +| clip_range | 0.0622 | +| entropy_loss | -7.58 | +| explained_variance | 0.0345 | +| learning_rate | 6.1e-05 | +| loss | -0.0268 | +| n_updates | 13712 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.00028 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.278 | +| time/ | | +| fps | 1382 | +| iterations | 3430 | +| time_elapsed | 5082 | +| total_timesteps | 7024640 | +| train/ | | +| approx_kl | 0.0071392497 | +| clip_fraction | 0.317 | +| clip_range | 0.0622 | +| entropy_loss | -7.49 | +| explained_variance | -0.0446 | +| learning_rate | 6.1e-05 | +| loss | -0.0219 | +| n_updates | 13716 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.00035 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.277 | +| time/ | | +| fps | 1382 | +| iterations | 3431 | +| time_elapsed | 5083 | +| total_timesteps | 7026688 | +| train/ | | +| approx_kl | 0.008601273 | +| clip_fraction | 0.319 | +| clip_range | 0.0622 | +| entropy_loss | -7.76 | +| explained_variance | -0.144 | +| learning_rate | 6.09e-05 | +| loss | -0.0352 | +| n_updates | 13720 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000216 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.289 | +| time/ | | +| fps | 1382 | +| iterations | 3432 | +| time_elapsed | 5085 | +| total_timesteps | 7028736 | +| train/ | | +| approx_kl | 0.009634955 | +| clip_fraction | 0.335 | +| clip_range | 0.0622 | +| entropy_loss | -7.64 | +| explained_variance | -0.201 | +| learning_rate | 6.09e-05 | +| loss | -0.032 | +| n_updates | 13724 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000155 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.293 | +| time/ | | +| fps | 1382 | +| iterations | 3433 | +| time_elapsed | 5086 | +| total_timesteps | 7030784 | +| train/ | | +| approx_kl | 0.008792603 | +| clip_fraction | 0.346 | +| clip_range | 0.0621 | +| entropy_loss | -7.61 | +| explained_variance | -0.0957 | +| learning_rate | 6.08e-05 | +| loss | -0.0311 | +| n_updates | 13728 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000188 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.293 | +| time/ | | +| fps | 1382 | +| iterations | 3434 | +| time_elapsed | 5088 | +| total_timesteps | 7032832 | +| train/ | | +| approx_kl | 0.009324741 | +| clip_fraction | 0.321 | +| clip_range | 0.0621 | +| entropy_loss | -7.51 | +| explained_variance | -0.0232 | +| learning_rate | 6.08e-05 | +| loss | -0.0298 | +| n_updates | 13732 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000161 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.288 | +| time/ | | +| fps | 1382 | +| iterations | 3435 | +| time_elapsed | 5089 | +| total_timesteps | 7034880 | +| train/ | | +| approx_kl | 0.009273152 | +| clip_fraction | 0.33 | +| clip_range | 0.0621 | +| entropy_loss | -7.7 | +| explained_variance | 0.0195 | +| learning_rate | 6.07e-05 | +| loss | -0.0238 | +| n_updates | 13736 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000121 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.287 | +| time/ | | +| fps | 1382 | +| iterations | 3436 | +| time_elapsed | 5090 | +| total_timesteps | 7036928 | +| train/ | | +| approx_kl | 0.008211527 | +| clip_fraction | 0.328 | +| clip_range | 0.0621 | +| entropy_loss | -7.61 | +| explained_variance | -0.211 | +| learning_rate | 6.07e-05 | +| loss | -0.0286 | +| n_updates | 13740 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.00015 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.287 | +| time/ | | +| fps | 1382 | +| iterations | 3437 | +| time_elapsed | 5092 | +| total_timesteps | 7038976 | +| train/ | | +| approx_kl | 0.008613627 | +| clip_fraction | 0.319 | +| clip_range | 0.062 | +| entropy_loss | -7.63 | +| explained_variance | -0.027 | +| learning_rate | 6.07e-05 | +| loss | -0.0286 | +| n_updates | 13744 | +| policy_gradient_loss | -0.0187 | +| value_loss | 9.45e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.287 | +| time/ | | +| fps | 1382 | +| iterations | 3438 | +| time_elapsed | 5093 | +| total_timesteps | 7041024 | +| train/ | | +| approx_kl | 0.008215984 | +| clip_fraction | 0.319 | +| clip_range | 0.062 | +| entropy_loss | -7.77 | +| explained_variance | -0.161 | +| learning_rate | 6.06e-05 | +| loss | -0.0309 | +| n_updates | 13748 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000134 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.286 | +| time/ | | +| fps | 1382 | +| iterations | 3439 | +| time_elapsed | 5095 | +| total_timesteps | 7043072 | +| train/ | | +| approx_kl | 0.009151675 | +| clip_fraction | 0.333 | +| clip_range | 0.062 | +| entropy_loss | -7.71 | +| explained_variance | 0.0052 | +| learning_rate | 6.06e-05 | +| loss | -0.0297 | +| n_updates | 13752 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000192 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.292 | +| time/ | | +| fps | 1382 | +| iterations | 3440 | +| time_elapsed | 5096 | +| total_timesteps | 7045120 | +| train/ | | +| approx_kl | 0.008248897 | +| clip_fraction | 0.319 | +| clip_range | 0.062 | +| entropy_loss | -7.57 | +| explained_variance | -0.0264 | +| learning_rate | 6.05e-05 | +| loss | -0.0253 | +| n_updates | 13756 | +| policy_gradient_loss | -0.0143 | +| value_loss | 0.000229 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.306 | +| time/ | | +| fps | 1382 | +| iterations | 3441 | +| time_elapsed | 5098 | +| total_timesteps | 7047168 | +| train/ | | +| approx_kl | 0.0085497275 | +| clip_fraction | 0.319 | +| clip_range | 0.0619 | +| entropy_loss | -7.64 | +| explained_variance | -0.0314 | +| learning_rate | 6.05e-05 | +| loss | -0.0255 | +| n_updates | 13760 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000227 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 1382 | +| iterations | 3442 | +| time_elapsed | 5099 | +| total_timesteps | 7049216 | +| train/ | | +| approx_kl | 0.007738358 | +| clip_fraction | 0.314 | +| clip_range | 0.0619 | +| entropy_loss | -7.4 | +| explained_variance | 0.119 | +| learning_rate | 6.05e-05 | +| loss | -0.0288 | +| n_updates | 13764 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000258 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 1382 | +| iterations | 3443 | +| time_elapsed | 5100 | +| total_timesteps | 7051264 | +| train/ | | +| approx_kl | 0.0090323975 | +| clip_fraction | 0.339 | +| clip_range | 0.0619 | +| entropy_loss | -7.51 | +| explained_variance | -0.163 | +| learning_rate | 6.04e-05 | +| loss | -0.0312 | +| n_updates | 13768 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000203 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.306 | +| time/ | | +| fps | 1382 | +| iterations | 3444 | +| time_elapsed | 5102 | +| total_timesteps | 7053312 | +| train/ | | +| approx_kl | 0.010667985 | +| clip_fraction | 0.326 | +| clip_range | 0.0619 | +| entropy_loss | -7.72 | +| explained_variance | -0.205 | +| learning_rate | 6.04e-05 | +| loss | -0.0259 | +| n_updates | 13772 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.304 | +| time/ | | +| fps | 1382 | +| iterations | 3445 | +| time_elapsed | 5103 | +| total_timesteps | 7055360 | +| train/ | | +| approx_kl | 0.008933452 | +| clip_fraction | 0.303 | +| clip_range | 0.0618 | +| entropy_loss | -7.72 | +| explained_variance | -0.043 | +| learning_rate | 6.03e-05 | +| loss | -0.0263 | +| n_updates | 13776 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.00014 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1382 | +| iterations | 3446 | +| time_elapsed | 5105 | +| total_timesteps | 7057408 | +| train/ | | +| approx_kl | 0.008317461 | +| clip_fraction | 0.336 | +| clip_range | 0.0618 | +| entropy_loss | -7.61 | +| explained_variance | 0.105 | +| learning_rate | 6.03e-05 | +| loss | -0.0254 | +| n_updates | 13780 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000162 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1382 | +| iterations | 3447 | +| time_elapsed | 5106 | +| total_timesteps | 7059456 | +| train/ | | +| approx_kl | 0.00879536 | +| clip_fraction | 0.315 | +| clip_range | 0.0618 | +| entropy_loss | -7.66 | +| explained_variance | -0.187 | +| learning_rate | 6.03e-05 | +| loss | -0.0245 | +| n_updates | 13784 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000167 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 1382 | +| iterations | 3448 | +| time_elapsed | 5108 | +| total_timesteps | 7061504 | +| train/ | | +| approx_kl | 0.009262969 | +| clip_fraction | 0.312 | +| clip_range | 0.0618 | +| entropy_loss | -7.7 | +| explained_variance | -0.0746 | +| learning_rate | 6.02e-05 | +| loss | -0.0271 | +| n_updates | 13788 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000139 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 1382 | +| iterations | 3449 | +| time_elapsed | 5109 | +| total_timesteps | 7063552 | +| train/ | | +| approx_kl | 0.00824142 | +| clip_fraction | 0.318 | +| clip_range | 0.0617 | +| entropy_loss | -7.49 | +| explained_variance | -0.143 | +| learning_rate | 6.02e-05 | +| loss | -0.0278 | +| n_updates | 13792 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000153 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.304 | +| time/ | | +| fps | 1382 | +| iterations | 3450 | +| time_elapsed | 5111 | +| total_timesteps | 7065600 | +| train/ | | +| approx_kl | 0.0084468275 | +| clip_fraction | 0.324 | +| clip_range | 0.0617 | +| entropy_loss | -7.7 | +| explained_variance | -0.0598 | +| learning_rate | 6.01e-05 | +| loss | -0.0302 | +| n_updates | 13796 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000184 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 1382 | +| iterations | 3451 | +| time_elapsed | 5112 | +| total_timesteps | 7067648 | +| train/ | | +| approx_kl | 0.006585822 | +| clip_fraction | 0.301 | +| clip_range | 0.0617 | +| entropy_loss | -7.64 | +| explained_variance | -0.0786 | +| learning_rate | 6.01e-05 | +| loss | -0.0291 | +| n_updates | 13800 | +| policy_gradient_loss | -0.013 | +| value_loss | 0.000198 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.306 | +| time/ | | +| fps | 1382 | +| iterations | 3452 | +| time_elapsed | 5113 | +| total_timesteps | 7069696 | +| train/ | | +| approx_kl | 0.007917195 | +| clip_fraction | 0.322 | +| clip_range | 0.0617 | +| entropy_loss | -7.43 | +| explained_variance | -0.106 | +| learning_rate | 6.01e-05 | +| loss | -0.0319 | +| n_updates | 13804 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.00016 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.306 | +| time/ | | +| fps | 1382 | +| iterations | 3453 | +| time_elapsed | 5115 | +| total_timesteps | 7071744 | +| train/ | | +| approx_kl | 0.008538282 | +| clip_fraction | 0.328 | +| clip_range | 0.0616 | +| entropy_loss | -7.58 | +| explained_variance | -0.0811 | +| learning_rate | 6e-05 | +| loss | -0.0306 | +| n_updates | 13808 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000128 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 1382 | +| iterations | 3454 | +| time_elapsed | 5116 | +| total_timesteps | 7073792 | +| train/ | | +| approx_kl | 0.007994546 | +| clip_fraction | 0.323 | +| clip_range | 0.0616 | +| entropy_loss | -7.71 | +| explained_variance | -0.0458 | +| learning_rate | 6e-05 | +| loss | -0.0267 | +| n_updates | 13812 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000129 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.3 | +| time/ | | +| fps | 1382 | +| iterations | 3455 | +| time_elapsed | 5118 | +| total_timesteps | 7075840 | +| train/ | | +| approx_kl | 0.007686462 | +| clip_fraction | 0.296 | +| clip_range | 0.0616 | +| entropy_loss | -7.5 | +| explained_variance | 0.161 | +| learning_rate | 5.99e-05 | +| loss | -0.028 | +| n_updates | 13816 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000254 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.304 | +| time/ | | +| fps | 1382 | +| iterations | 3456 | +| time_elapsed | 5119 | +| total_timesteps | 7077888 | +| train/ | | +| approx_kl | 0.009426722 | +| clip_fraction | 0.337 | +| clip_range | 0.0616 | +| entropy_loss | -7.65 | +| explained_variance | -0.214 | +| learning_rate | 5.99e-05 | +| loss | -0.0331 | +| n_updates | 13820 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000206 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1382 | +| iterations | 3457 | +| time_elapsed | 5121 | +| total_timesteps | 7079936 | +| train/ | | +| approx_kl | 0.007834466 | +| clip_fraction | 0.309 | +| clip_range | 0.0615 | +| entropy_loss | -7.66 | +| explained_variance | -0.00864 | +| learning_rate | 5.99e-05 | +| loss | -0.0234 | +| n_updates | 13824 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.000273 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 1382 | +| iterations | 3458 | +| time_elapsed | 5122 | +| total_timesteps | 7081984 | +| train/ | | +| approx_kl | 0.0073816264 | +| clip_fraction | 0.32 | +| clip_range | 0.0615 | +| entropy_loss | -7.53 | +| explained_variance | 0.0765 | +| learning_rate | 5.98e-05 | +| loss | -0.0254 | +| n_updates | 13828 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000208 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.304 | +| time/ | | +| fps | 1382 | +| iterations | 3459 | +| time_elapsed | 5123 | +| total_timesteps | 7084032 | +| train/ | | +| approx_kl | 0.008863479 | +| clip_fraction | 0.363 | +| clip_range | 0.0615 | +| entropy_loss | -7.62 | +| explained_variance | -0.262 | +| learning_rate | 5.98e-05 | +| loss | -0.0391 | +| n_updates | 13832 | +| policy_gradient_loss | -0.0223 | +| value_loss | 8.18e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 1382 | +| iterations | 3460 | +| time_elapsed | 5125 | +| total_timesteps | 7086080 | +| train/ | | +| approx_kl | 0.009205131 | +| clip_fraction | 0.344 | +| clip_range | 0.0614 | +| entropy_loss | -7.57 | +| explained_variance | 0.122 | +| learning_rate | 5.97e-05 | +| loss | -0.0275 | +| n_updates | 13836 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000118 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 1382 | +| iterations | 3461 | +| time_elapsed | 5126 | +| total_timesteps | 7088128 | +| train/ | | +| approx_kl | 0.009480571 | +| clip_fraction | 0.324 | +| clip_range | 0.0614 | +| entropy_loss | -7.64 | +| explained_variance | -0.16 | +| learning_rate | 5.97e-05 | +| loss | -0.0286 | +| n_updates | 13840 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.00017 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 1382 | +| iterations | 3462 | +| time_elapsed | 5128 | +| total_timesteps | 7090176 | +| train/ | | +| approx_kl | 0.0086783655 | +| clip_fraction | 0.334 | +| clip_range | 0.0614 | +| entropy_loss | -7.72 | +| explained_variance | -0.112 | +| learning_rate | 5.97e-05 | +| loss | -0.0307 | +| n_updates | 13844 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000129 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1382 | +| iterations | 3463 | +| time_elapsed | 5129 | +| total_timesteps | 7092224 | +| train/ | | +| approx_kl | 0.007841207 | +| clip_fraction | 0.297 | +| clip_range | 0.0614 | +| entropy_loss | -7.66 | +| explained_variance | 0.00186 | +| learning_rate | 5.96e-05 | +| loss | -0.0212 | +| n_updates | 13848 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000204 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 1382 | +| iterations | 3464 | +| time_elapsed | 5130 | +| total_timesteps | 7094272 | +| train/ | | +| approx_kl | 0.0067407945 | +| clip_fraction | 0.313 | +| clip_range | 0.0613 | +| entropy_loss | -7.66 | +| explained_variance | -0.107 | +| learning_rate | 5.96e-05 | +| loss | -0.0211 | +| n_updates | 13852 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000151 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 1382 | +| iterations | 3465 | +| time_elapsed | 5132 | +| total_timesteps | 7096320 | +| train/ | | +| approx_kl | 0.008943737 | +| clip_fraction | 0.297 | +| clip_range | 0.0613 | +| entropy_loss | -7.66 | +| explained_variance | 0.0296 | +| learning_rate | 5.95e-05 | +| loss | -0.0281 | +| n_updates | 13856 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000168 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 1382 | +| iterations | 3466 | +| time_elapsed | 5133 | +| total_timesteps | 7098368 | +| train/ | | +| approx_kl | 0.008231253 | +| clip_fraction | 0.317 | +| clip_range | 0.0613 | +| entropy_loss | -7.56 | +| explained_variance | -0.0972 | +| learning_rate | 5.95e-05 | +| loss | -0.0291 | +| n_updates | 13860 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000172 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1382 | +| iterations | 3467 | +| time_elapsed | 5135 | +| total_timesteps | 7100416 | +| train/ | | +| approx_kl | 0.008493802 | +| clip_fraction | 0.321 | +| clip_range | 0.0613 | +| entropy_loss | -7.65 | +| explained_variance | -0.0215 | +| learning_rate | 5.95e-05 | +| loss | -0.0301 | +| n_updates | 13864 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000141 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1382 | +| iterations | 3468 | +| time_elapsed | 5136 | +| total_timesteps | 7102464 | +| train/ | | +| approx_kl | 0.008623149 | +| clip_fraction | 0.3 | +| clip_range | 0.0612 | +| entropy_loss | -7.56 | +| explained_variance | -0.127 | +| learning_rate | 5.94e-05 | +| loss | -0.0225 | +| n_updates | 13868 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000212 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1382 | +| iterations | 3469 | +| time_elapsed | 5138 | +| total_timesteps | 7104512 | +| train/ | | +| approx_kl | 0.009460391 | +| clip_fraction | 0.332 | +| clip_range | 0.0612 | +| entropy_loss | -7.49 | +| explained_variance | -0.109 | +| learning_rate | 5.94e-05 | +| loss | -0.0284 | +| n_updates | 13872 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.00018 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1382 | +| iterations | 3470 | +| time_elapsed | 5139 | +| total_timesteps | 7106560 | +| train/ | | +| approx_kl | 0.008714144 | +| clip_fraction | 0.314 | +| clip_range | 0.0612 | +| entropy_loss | -7.43 | +| explained_variance | 0.0166 | +| learning_rate | 5.93e-05 | +| loss | -0.0277 | +| n_updates | 13876 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000148 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1382 | +| iterations | 3471 | +| time_elapsed | 5141 | +| total_timesteps | 7108608 | +| train/ | | +| approx_kl | 0.009965733 | +| clip_fraction | 0.345 | +| clip_range | 0.0612 | +| entropy_loss | -7.63 | +| explained_variance | -0.246 | +| learning_rate | 5.93e-05 | +| loss | -0.0281 | +| n_updates | 13880 | +| policy_gradient_loss | -0.0193 | +| value_loss | 9.85e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1382 | +| iterations | 3472 | +| time_elapsed | 5142 | +| total_timesteps | 7110656 | +| train/ | | +| approx_kl | 0.009276908 | +| clip_fraction | 0.335 | +| clip_range | 0.0611 | +| entropy_loss | -7.75 | +| explained_variance | -0.0469 | +| learning_rate | 5.92e-05 | +| loss | -0.0255 | +| n_updates | 13884 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000195 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1382 | +| iterations | 3473 | +| time_elapsed | 5144 | +| total_timesteps | 7112704 | +| train/ | | +| approx_kl | 0.007994002 | +| clip_fraction | 0.31 | +| clip_range | 0.0611 | +| entropy_loss | -7.63 | +| explained_variance | 0.101 | +| learning_rate | 5.92e-05 | +| loss | -0.0248 | +| n_updates | 13888 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000254 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1382 | +| iterations | 3474 | +| time_elapsed | 5145 | +| total_timesteps | 7114752 | +| train/ | | +| approx_kl | 0.0088848155 | +| clip_fraction | 0.362 | +| clip_range | 0.0611 | +| entropy_loss | -7.65 | +| explained_variance | -0.048 | +| learning_rate | 5.92e-05 | +| loss | -0.0323 | +| n_updates | 13892 | +| policy_gradient_loss | -0.0211 | +| value_loss | 8.92e-05 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1382 | +| iterations | 3475 | +| time_elapsed | 5147 | +| total_timesteps | 7116800 | +| train/ | | +| approx_kl | 0.0085082445 | +| clip_fraction | 0.347 | +| clip_range | 0.0611 | +| entropy_loss | -7.63 | +| explained_variance | -0.221 | +| learning_rate | 5.91e-05 | +| loss | -0.0365 | +| n_updates | 13896 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000115 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1382 | +| iterations | 3476 | +| time_elapsed | 5148 | +| total_timesteps | 7118848 | +| train/ | | +| approx_kl | 0.008729365 | +| clip_fraction | 0.318 | +| clip_range | 0.061 | +| entropy_loss | -7.6 | +| explained_variance | -0.117 | +| learning_rate | 5.91e-05 | +| loss | -0.0265 | +| n_updates | 13900 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000153 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 1382 | +| iterations | 3477 | +| time_elapsed | 5149 | +| total_timesteps | 7120896 | +| train/ | | +| approx_kl | 0.008151653 | +| clip_fraction | 0.318 | +| clip_range | 0.061 | +| entropy_loss | -7.6 | +| explained_variance | 0.00593 | +| learning_rate | 5.9e-05 | +| loss | -0.0238 | +| n_updates | 13904 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000189 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1382 | +| iterations | 3478 | +| time_elapsed | 5151 | +| total_timesteps | 7122944 | +| train/ | | +| approx_kl | 0.009940346 | +| clip_fraction | 0.313 | +| clip_range | 0.061 | +| entropy_loss | -7.48 | +| explained_variance | -0.0297 | +| learning_rate | 5.9e-05 | +| loss | -0.028 | +| n_updates | 13908 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000209 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1382 | +| iterations | 3479 | +| time_elapsed | 5152 | +| total_timesteps | 7124992 | +| train/ | | +| approx_kl | 0.008293752 | +| clip_fraction | 0.326 | +| clip_range | 0.061 | +| entropy_loss | -7.61 | +| explained_variance | -0.112 | +| learning_rate | 5.9e-05 | +| loss | -0.0244 | +| n_updates | 13912 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000278 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1382 | +| iterations | 3480 | +| time_elapsed | 5154 | +| total_timesteps | 7127040 | +| train/ | | +| approx_kl | 0.0080074 | +| clip_fraction | 0.372 | +| clip_range | 0.0609 | +| entropy_loss | -7.74 | +| explained_variance | -0.53 | +| learning_rate | 5.89e-05 | +| loss | -0.0407 | +| n_updates | 13916 | +| policy_gradient_loss | -0.0224 | +| value_loss | 9.48e-05 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1382 | +| iterations | 3481 | +| time_elapsed | 5155 | +| total_timesteps | 7129088 | +| train/ | | +| approx_kl | 0.008626362 | +| clip_fraction | 0.342 | +| clip_range | 0.0609 | +| entropy_loss | -7.67 | +| explained_variance | -0.139 | +| learning_rate | 5.89e-05 | +| loss | -0.0294 | +| n_updates | 13920 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000193 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1382 | +| iterations | 3482 | +| time_elapsed | 5157 | +| total_timesteps | 7131136 | +| train/ | | +| approx_kl | 0.007920237 | +| clip_fraction | 0.335 | +| clip_range | 0.0609 | +| entropy_loss | -7.72 | +| explained_variance | -0.0882 | +| learning_rate | 5.88e-05 | +| loss | -0.0286 | +| n_updates | 13924 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.00016 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1382 | +| iterations | 3483 | +| time_elapsed | 5158 | +| total_timesteps | 7133184 | +| train/ | | +| approx_kl | 0.0076937596 | +| clip_fraction | 0.321 | +| clip_range | 0.0609 | +| entropy_loss | -7.57 | +| explained_variance | -0.135 | +| learning_rate | 5.88e-05 | +| loss | -0.0235 | +| n_updates | 13928 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.00025 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1382 | +| iterations | 3484 | +| time_elapsed | 5160 | +| total_timesteps | 7135232 | +| train/ | | +| approx_kl | 0.0075162603 | +| clip_fraction | 0.305 | +| clip_range | 0.0608 | +| entropy_loss | -7.56 | +| explained_variance | 0.00345 | +| learning_rate | 5.88e-05 | +| loss | -0.0247 | +| n_updates | 13932 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000178 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 1382 | +| iterations | 3485 | +| time_elapsed | 5161 | +| total_timesteps | 7137280 | +| train/ | | +| approx_kl | 0.008034218 | +| clip_fraction | 0.302 | +| clip_range | 0.0608 | +| entropy_loss | -7.59 | +| explained_variance | -0.0804 | +| learning_rate | 5.87e-05 | +| loss | -0.0264 | +| n_updates | 13936 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000168 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1382 | +| iterations | 3486 | +| time_elapsed | 5162 | +| total_timesteps | 7139328 | +| train/ | | +| approx_kl | 0.008332431 | +| clip_fraction | 0.324 | +| clip_range | 0.0608 | +| entropy_loss | -7.54 | +| explained_variance | -0.0402 | +| learning_rate | 5.87e-05 | +| loss | -0.0287 | +| n_updates | 13940 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.00018 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1382 | +| iterations | 3487 | +| time_elapsed | 5164 | +| total_timesteps | 7141376 | +| train/ | | +| approx_kl | 0.010181029 | +| clip_fraction | 0.349 | +| clip_range | 0.0608 | +| entropy_loss | -7.58 | +| explained_variance | -0.0685 | +| learning_rate | 5.86e-05 | +| loss | -0.0301 | +| n_updates | 13944 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000199 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1382 | +| iterations | 3488 | +| time_elapsed | 5165 | +| total_timesteps | 7143424 | +| train/ | | +| approx_kl | 0.008538854 | +| clip_fraction | 0.33 | +| clip_range | 0.0607 | +| entropy_loss | -7.58 | +| explained_variance | -0.0729 | +| learning_rate | 5.86e-05 | +| loss | -0.0229 | +| n_updates | 13948 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000183 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1382 | +| iterations | 3489 | +| time_elapsed | 5167 | +| total_timesteps | 7145472 | +| train/ | | +| approx_kl | 0.008972503 | +| clip_fraction | 0.326 | +| clip_range | 0.0607 | +| entropy_loss | -7.67 | +| explained_variance | 0.00534 | +| learning_rate | 5.86e-05 | +| loss | -0.0302 | +| n_updates | 13952 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.00014 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1382 | +| iterations | 3490 | +| time_elapsed | 5168 | +| total_timesteps | 7147520 | +| train/ | | +| approx_kl | 0.007342565 | +| clip_fraction | 0.308 | +| clip_range | 0.0607 | +| entropy_loss | -7.52 | +| explained_variance | 0.0259 | +| learning_rate | 5.85e-05 | +| loss | -0.0289 | +| n_updates | 13956 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000285 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1382 | +| iterations | 3491 | +| time_elapsed | 5170 | +| total_timesteps | 7149568 | +| train/ | | +| approx_kl | 0.008168997 | +| clip_fraction | 0.319 | +| clip_range | 0.0607 | +| entropy_loss | -7.66 | +| explained_variance | 0.00686 | +| learning_rate | 5.85e-05 | +| loss | -0.0308 | +| n_updates | 13960 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.00014 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1382 | +| iterations | 3492 | +| time_elapsed | 5171 | +| total_timesteps | 7151616 | +| train/ | | +| approx_kl | 0.007799176 | +| clip_fraction | 0.336 | +| clip_range | 0.0606 | +| entropy_loss | -7.76 | +| explained_variance | -0.0506 | +| learning_rate | 5.84e-05 | +| loss | -0.0321 | +| n_updates | 13964 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000141 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1382 | +| iterations | 3493 | +| time_elapsed | 5172 | +| total_timesteps | 7153664 | +| train/ | | +| approx_kl | 0.008543733 | +| clip_fraction | 0.339 | +| clip_range | 0.0606 | +| entropy_loss | -7.69 | +| explained_variance | -0.0306 | +| learning_rate | 5.84e-05 | +| loss | -0.0294 | +| n_updates | 13968 | +| policy_gradient_loss | -0.0198 | +| value_loss | 7.82e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1382 | +| iterations | 3494 | +| time_elapsed | 5174 | +| total_timesteps | 7155712 | +| train/ | | +| approx_kl | 0.008027913 | +| clip_fraction | 0.317 | +| clip_range | 0.0606 | +| entropy_loss | -7.63 | +| explained_variance | -0.0624 | +| learning_rate | 5.84e-05 | +| loss | -0.0273 | +| n_updates | 13972 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000116 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1382 | +| iterations | 3495 | +| time_elapsed | 5175 | +| total_timesteps | 7157760 | +| train/ | | +| approx_kl | 0.008667784 | +| clip_fraction | 0.344 | +| clip_range | 0.0606 | +| entropy_loss | -7.7 | +| explained_variance | -0.201 | +| learning_rate | 5.83e-05 | +| loss | -0.0325 | +| n_updates | 13976 | +| policy_gradient_loss | -0.0219 | +| value_loss | 8.4e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1382 | +| iterations | 3496 | +| time_elapsed | 5177 | +| total_timesteps | 7159808 | +| train/ | | +| approx_kl | 0.006718103 | +| clip_fraction | 0.324 | +| clip_range | 0.0605 | +| entropy_loss | -7.57 | +| explained_variance | -0.0912 | +| learning_rate | 5.83e-05 | +| loss | -0.0272 | +| n_updates | 13980 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000121 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.306 | +| time/ | | +| fps | 1382 | +| iterations | 3497 | +| time_elapsed | 5178 | +| total_timesteps | 7161856 | +| train/ | | +| approx_kl | 0.008500138 | +| clip_fraction | 0.324 | +| clip_range | 0.0605 | +| entropy_loss | -7.67 | +| explained_variance | -0.132 | +| learning_rate | 5.82e-05 | +| loss | -0.0274 | +| n_updates | 13984 | +| policy_gradient_loss | -0.0167 | +| value_loss | 8.72e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 1382 | +| iterations | 3498 | +| time_elapsed | 5180 | +| total_timesteps | 7163904 | +| train/ | | +| approx_kl | 0.007260774 | +| clip_fraction | 0.316 | +| clip_range | 0.0605 | +| entropy_loss | -7.41 | +| explained_variance | 0.0288 | +| learning_rate | 5.82e-05 | +| loss | -0.0264 | +| n_updates | 13988 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000186 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 1382 | +| iterations | 3499 | +| time_elapsed | 5181 | +| total_timesteps | 7165952 | +| train/ | | +| approx_kl | 0.008788472 | +| clip_fraction | 0.348 | +| clip_range | 0.0605 | +| entropy_loss | -7.35 | +| explained_variance | 0.016 | +| learning_rate | 5.82e-05 | +| loss | -0.0297 | +| n_updates | 13992 | +| policy_gradient_loss | -0.0194 | +| value_loss | 7.33e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.295 | +| time/ | | +| fps | 1382 | +| iterations | 3500 | +| time_elapsed | 5183 | +| total_timesteps | 7168000 | +| train/ | | +| approx_kl | 0.008349695 | +| clip_fraction | 0.304 | +| clip_range | 0.0604 | +| entropy_loss | -7.67 | +| explained_variance | -0.0642 | +| learning_rate | 5.81e-05 | +| loss | -0.0243 | +| n_updates | 13996 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000172 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.294 | +| time/ | | +| fps | 1382 | +| iterations | 3501 | +| time_elapsed | 5184 | +| total_timesteps | 7170048 | +| train/ | | +| approx_kl | 0.008789324 | +| clip_fraction | 0.31 | +| clip_range | 0.0604 | +| entropy_loss | -7.57 | +| explained_variance | 0.0108 | +| learning_rate | 5.81e-05 | +| loss | -0.0264 | +| n_updates | 14000 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000129 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.29 | +| time/ | | +| fps | 1382 | +| iterations | 3502 | +| time_elapsed | 5185 | +| total_timesteps | 7172096 | +| train/ | | +| approx_kl | 0.008180546 | +| clip_fraction | 0.334 | +| clip_range | 0.0604 | +| entropy_loss | -7.61 | +| explained_variance | -0.228 | +| learning_rate | 5.8e-05 | +| loss | -0.0311 | +| n_updates | 14004 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000113 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.29 | +| time/ | | +| fps | 1382 | +| iterations | 3503 | +| time_elapsed | 5187 | +| total_timesteps | 7174144 | +| train/ | | +| approx_kl | 0.008434001 | +| clip_fraction | 0.303 | +| clip_range | 0.0603 | +| entropy_loss | -7.58 | +| explained_variance | 0.0766 | +| learning_rate | 5.8e-05 | +| loss | -0.0264 | +| n_updates | 14008 | +| policy_gradient_loss | -0.0148 | +| value_loss | 0.000141 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.284 | +| time/ | | +| fps | 1382 | +| iterations | 3504 | +| time_elapsed | 5188 | +| total_timesteps | 7176192 | +| train/ | | +| approx_kl | 0.009667803 | +| clip_fraction | 0.325 | +| clip_range | 0.0603 | +| entropy_loss | -7.63 | +| explained_variance | 0.0476 | +| learning_rate | 5.8e-05 | +| loss | -0.0339 | +| n_updates | 14012 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000155 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.289 | +| time/ | | +| fps | 1382 | +| iterations | 3505 | +| time_elapsed | 5190 | +| total_timesteps | 7178240 | +| train/ | | +| approx_kl | 0.007141683 | +| clip_fraction | 0.299 | +| clip_range | 0.0603 | +| entropy_loss | -7.6 | +| explained_variance | -0.13 | +| learning_rate | 5.79e-05 | +| loss | -0.0255 | +| n_updates | 14016 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.00017 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.289 | +| time/ | | +| fps | 1383 | +| iterations | 3506 | +| time_elapsed | 5191 | +| total_timesteps | 7180288 | +| train/ | | +| approx_kl | 0.0074820835 | +| clip_fraction | 0.307 | +| clip_range | 0.0603 | +| entropy_loss | -7.57 | +| explained_variance | -0.0229 | +| learning_rate | 5.79e-05 | +| loss | -0.0167 | +| n_updates | 14020 | +| policy_gradient_loss | -0.0147 | +| value_loss | 0.000443 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.284 | +| time/ | | +| fps | 1383 | +| iterations | 3507 | +| time_elapsed | 5193 | +| total_timesteps | 7182336 | +| train/ | | +| approx_kl | 0.007890665 | +| clip_fraction | 0.345 | +| clip_range | 0.0602 | +| entropy_loss | -7.73 | +| explained_variance | -0.188 | +| learning_rate | 5.78e-05 | +| loss | -0.0317 | +| n_updates | 14024 | +| policy_gradient_loss | -0.0197 | +| value_loss | 9.76e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.283 | +| time/ | | +| fps | 1383 | +| iterations | 3508 | +| time_elapsed | 5194 | +| total_timesteps | 7184384 | +| train/ | | +| approx_kl | 0.0065243402 | +| clip_fraction | 0.314 | +| clip_range | 0.0602 | +| entropy_loss | -7.67 | +| explained_variance | 0.0336 | +| learning_rate | 5.78e-05 | +| loss | -0.031 | +| n_updates | 14028 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000221 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.283 | +| time/ | | +| fps | 1383 | +| iterations | 3509 | +| time_elapsed | 5196 | +| total_timesteps | 7186432 | +| train/ | | +| approx_kl | 0.007163234 | +| clip_fraction | 0.316 | +| clip_range | 0.0602 | +| entropy_loss | -7.47 | +| explained_variance | 0.0245 | +| learning_rate | 5.77e-05 | +| loss | -0.0271 | +| n_updates | 14032 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000193 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.278 | +| time/ | | +| fps | 1383 | +| iterations | 3510 | +| time_elapsed | 5197 | +| total_timesteps | 7188480 | +| train/ | | +| approx_kl | 0.008039264 | +| clip_fraction | 0.307 | +| clip_range | 0.0602 | +| entropy_loss | -7.57 | +| explained_variance | 0.0561 | +| learning_rate | 5.77e-05 | +| loss | -0.0263 | +| n_updates | 14036 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000204 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.278 | +| time/ | | +| fps | 1383 | +| iterations | 3511 | +| time_elapsed | 5198 | +| total_timesteps | 7190528 | +| train/ | | +| approx_kl | 0.008586796 | +| clip_fraction | 0.32 | +| clip_range | 0.0601 | +| entropy_loss | -7.45 | +| explained_variance | 0.0766 | +| learning_rate | 5.77e-05 | +| loss | -0.0278 | +| n_updates | 14040 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000223 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.284 | +| time/ | | +| fps | 1383 | +| iterations | 3512 | +| time_elapsed | 5200 | +| total_timesteps | 7192576 | +| train/ | | +| approx_kl | 0.009014258 | +| clip_fraction | 0.352 | +| clip_range | 0.0601 | +| entropy_loss | -7.59 | +| explained_variance | -0.113 | +| learning_rate | 5.76e-05 | +| loss | -0.0291 | +| n_updates | 14044 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000233 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.281 | +| time/ | | +| fps | 1383 | +| iterations | 3513 | +| time_elapsed | 5201 | +| total_timesteps | 7194624 | +| train/ | | +| approx_kl | 0.009811673 | +| clip_fraction | 0.325 | +| clip_range | 0.0601 | +| entropy_loss | -7.47 | +| explained_variance | -0.09 | +| learning_rate | 5.76e-05 | +| loss | -0.029 | +| n_updates | 14048 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000211 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.283 | +| time/ | | +| fps | 1383 | +| iterations | 3514 | +| time_elapsed | 5203 | +| total_timesteps | 7196672 | +| train/ | | +| approx_kl | 0.008511636 | +| clip_fraction | 0.319 | +| clip_range | 0.0601 | +| entropy_loss | -7.57 | +| explained_variance | -0.0213 | +| learning_rate | 5.75e-05 | +| loss | -0.0295 | +| n_updates | 14052 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.00015 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.28 | +| time/ | | +| fps | 1383 | +| iterations | 3515 | +| time_elapsed | 5204 | +| total_timesteps | 7198720 | +| train/ | | +| approx_kl | 0.00851017 | +| clip_fraction | 0.322 | +| clip_range | 0.06 | +| entropy_loss | -7.63 | +| explained_variance | -0.0618 | +| learning_rate | 5.75e-05 | +| loss | -0.0263 | +| n_updates | 14056 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000295 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 1383 | +| iterations | 3516 | +| time_elapsed | 5206 | +| total_timesteps | 7200768 | +| train/ | | +| approx_kl | 0.008663947 | +| clip_fraction | 0.349 | +| clip_range | 0.06 | +| entropy_loss | -7.64 | +| explained_variance | -0.251 | +| learning_rate | 5.75e-05 | +| loss | -0.0301 | +| n_updates | 14060 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000156 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.287 | +| time/ | | +| fps | 1383 | +| iterations | 3517 | +| time_elapsed | 5207 | +| total_timesteps | 7202816 | +| train/ | | +| approx_kl | 0.008713748 | +| clip_fraction | 0.313 | +| clip_range | 0.06 | +| entropy_loss | -7.57 | +| explained_variance | -0.0654 | +| learning_rate | 5.74e-05 | +| loss | -0.0281 | +| n_updates | 14064 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000256 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.288 | +| time/ | | +| fps | 1383 | +| iterations | 3518 | +| time_elapsed | 5209 | +| total_timesteps | 7204864 | +| train/ | | +| approx_kl | 0.008115458 | +| clip_fraction | 0.313 | +| clip_range | 0.06 | +| entropy_loss | -7.52 | +| explained_variance | -0.0683 | +| learning_rate | 5.74e-05 | +| loss | -0.0224 | +| n_updates | 14068 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000221 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.288 | +| time/ | | +| fps | 1383 | +| iterations | 3519 | +| time_elapsed | 5210 | +| total_timesteps | 7206912 | +| train/ | | +| approx_kl | 0.008431431 | +| clip_fraction | 0.333 | +| clip_range | 0.0599 | +| entropy_loss | -7.45 | +| explained_variance | -0.0375 | +| learning_rate | 5.73e-05 | +| loss | -0.0295 | +| n_updates | 14072 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000165 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 1383 | +| iterations | 3520 | +| time_elapsed | 5212 | +| total_timesteps | 7208960 | +| train/ | | +| approx_kl | 0.00891272 | +| clip_fraction | 0.334 | +| clip_range | 0.0599 | +| entropy_loss | -7.71 | +| explained_variance | -0.127 | +| learning_rate | 5.73e-05 | +| loss | -0.0276 | +| n_updates | 14076 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000181 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.29 | +| time/ | | +| fps | 1383 | +| iterations | 3521 | +| time_elapsed | 5213 | +| total_timesteps | 7211008 | +| train/ | | +| approx_kl | 0.008472314 | +| clip_fraction | 0.337 | +| clip_range | 0.0599 | +| entropy_loss | -7.66 | +| explained_variance | -0.139 | +| learning_rate | 5.73e-05 | +| loss | -0.0274 | +| n_updates | 14080 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.00012 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.29 | +| time/ | | +| fps | 1383 | +| iterations | 3522 | +| time_elapsed | 5215 | +| total_timesteps | 7213056 | +| train/ | | +| approx_kl | 0.007973066 | +| clip_fraction | 0.316 | +| clip_range | 0.0599 | +| entropy_loss | -7.63 | +| explained_variance | -0.0512 | +| learning_rate | 5.72e-05 | +| loss | -0.0228 | +| n_updates | 14084 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.000217 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.284 | +| time/ | | +| fps | 1383 | +| iterations | 3523 | +| time_elapsed | 5216 | +| total_timesteps | 7215104 | +| train/ | | +| approx_kl | 0.008818276 | +| clip_fraction | 0.349 | +| clip_range | 0.0598 | +| entropy_loss | -7.61 | +| explained_variance | -0.0113 | +| learning_rate | 5.72e-05 | +| loss | -0.0299 | +| n_updates | 14088 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000207 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.286 | +| time/ | | +| fps | 1383 | +| iterations | 3524 | +| time_elapsed | 5218 | +| total_timesteps | 7217152 | +| train/ | | +| approx_kl | 0.009203821 | +| clip_fraction | 0.316 | +| clip_range | 0.0598 | +| entropy_loss | -7.46 | +| explained_variance | -0.0321 | +| learning_rate | 5.71e-05 | +| loss | -0.02 | +| n_updates | 14092 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000164 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.283 | +| time/ | | +| fps | 1383 | +| iterations | 3525 | +| time_elapsed | 5219 | +| total_timesteps | 7219200 | +| train/ | | +| approx_kl | 0.008308698 | +| clip_fraction | 0.32 | +| clip_range | 0.0598 | +| entropy_loss | -7.51 | +| explained_variance | -0.000295 | +| learning_rate | 5.71e-05 | +| loss | -0.0264 | +| n_updates | 14096 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000154 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.283 | +| time/ | | +| fps | 1383 | +| iterations | 3526 | +| time_elapsed | 5221 | +| total_timesteps | 7221248 | +| train/ | | +| approx_kl | 0.008989955 | +| clip_fraction | 0.331 | +| clip_range | 0.0598 | +| entropy_loss | -7.5 | +| explained_variance | -0.274 | +| learning_rate | 5.71e-05 | +| loss | -0.0268 | +| n_updates | 14100 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000154 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 1383 | +| iterations | 3527 | +| time_elapsed | 5222 | +| total_timesteps | 7223296 | +| train/ | | +| approx_kl | 0.0084425295 | +| clip_fraction | 0.298 | +| clip_range | 0.0597 | +| entropy_loss | -7.67 | +| explained_variance | -0.0944 | +| learning_rate | 5.7e-05 | +| loss | -0.0304 | +| n_updates | 14104 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000136 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 1383 | +| iterations | 3528 | +| time_elapsed | 5223 | +| total_timesteps | 7225344 | +| train/ | | +| approx_kl | 0.0071391864 | +| clip_fraction | 0.318 | +| clip_range | 0.0597 | +| entropy_loss | -7.58 | +| explained_variance | -0.0158 | +| learning_rate | 5.7e-05 | +| loss | -0.0226 | +| n_updates | 14108 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000257 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.295 | +| time/ | | +| fps | 1383 | +| iterations | 3529 | +| time_elapsed | 5225 | +| total_timesteps | 7227392 | +| train/ | | +| approx_kl | 0.006967617 | +| clip_fraction | 0.311 | +| clip_range | 0.0597 | +| entropy_loss | -7.73 | +| explained_variance | -0.282 | +| learning_rate | 5.69e-05 | +| loss | -0.028 | +| n_updates | 14112 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.00018 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.293 | +| time/ | | +| fps | 1383 | +| iterations | 3530 | +| time_elapsed | 5226 | +| total_timesteps | 7229440 | +| train/ | | +| approx_kl | 0.0086469 | +| clip_fraction | 0.323 | +| clip_range | 0.0597 | +| entropy_loss | -7.28 | +| explained_variance | 0.00461 | +| learning_rate | 5.69e-05 | +| loss | -0.0271 | +| n_updates | 14116 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000362 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.29 | +| time/ | | +| fps | 1383 | +| iterations | 3531 | +| time_elapsed | 5228 | +| total_timesteps | 7231488 | +| train/ | | +| approx_kl | 0.008501921 | +| clip_fraction | 0.345 | +| clip_range | 0.0596 | +| entropy_loss | -7.63 | +| explained_variance | -0.217 | +| learning_rate | 5.69e-05 | +| loss | -0.0297 | +| n_updates | 14120 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000112 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.291 | +| time/ | | +| fps | 1383 | +| iterations | 3532 | +| time_elapsed | 5229 | +| total_timesteps | 7233536 | +| train/ | | +| approx_kl | 0.008731054 | +| clip_fraction | 0.33 | +| clip_range | 0.0596 | +| entropy_loss | -7.7 | +| explained_variance | -0.131 | +| learning_rate | 5.68e-05 | +| loss | -0.0267 | +| n_updates | 14124 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000183 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.287 | +| time/ | | +| fps | 1383 | +| iterations | 3533 | +| time_elapsed | 5231 | +| total_timesteps | 7235584 | +| train/ | | +| approx_kl | 0.00722836 | +| clip_fraction | 0.297 | +| clip_range | 0.0596 | +| entropy_loss | -7.58 | +| explained_variance | -0.165 | +| learning_rate | 5.68e-05 | +| loss | -0.0219 | +| n_updates | 14128 | +| policy_gradient_loss | -0.0145 | +| value_loss | 0.000179 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.287 | +| time/ | | +| fps | 1383 | +| iterations | 3534 | +| time_elapsed | 5232 | +| total_timesteps | 7237632 | +| train/ | | +| approx_kl | 0.008951312 | +| clip_fraction | 0.337 | +| clip_range | 0.0596 | +| entropy_loss | -7.68 | +| explained_variance | -0.04 | +| learning_rate | 5.67e-05 | +| loss | -0.0287 | +| n_updates | 14132 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000177 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 1383 | +| iterations | 3535 | +| time_elapsed | 5234 | +| total_timesteps | 7239680 | +| train/ | | +| approx_kl | 0.0081124455 | +| clip_fraction | 0.316 | +| clip_range | 0.0595 | +| entropy_loss | -7.65 | +| explained_variance | -0.0675 | +| learning_rate | 5.67e-05 | +| loss | -0.0209 | +| n_updates | 14136 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000161 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 1383 | +| iterations | 3536 | +| time_elapsed | 5235 | +| total_timesteps | 7241728 | +| train/ | | +| approx_kl | 0.007039198 | +| clip_fraction | 0.311 | +| clip_range | 0.0595 | +| entropy_loss | -7.57 | +| explained_variance | -0.00919 | +| learning_rate | 5.67e-05 | +| loss | -0.0268 | +| n_updates | 14140 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.00039 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1383 | +| iterations | 3537 | +| time_elapsed | 5236 | +| total_timesteps | 7243776 | +| train/ | | +| approx_kl | 0.007372182 | +| clip_fraction | 0.345 | +| clip_range | 0.0595 | +| entropy_loss | -7.64 | +| explained_variance | -0.0609 | +| learning_rate | 5.66e-05 | +| loss | -0.0295 | +| n_updates | 14144 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000165 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.304 | +| time/ | | +| fps | 1383 | +| iterations | 3538 | +| time_elapsed | 5238 | +| total_timesteps | 7245824 | +| train/ | | +| approx_kl | 0.0071453443 | +| clip_fraction | 0.309 | +| clip_range | 0.0595 | +| entropy_loss | -7.63 | +| explained_variance | 0.0708 | +| learning_rate | 5.66e-05 | +| loss | -0.0202 | +| n_updates | 14148 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.00024 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1383 | +| iterations | 3539 | +| time_elapsed | 5239 | +| total_timesteps | 7247872 | +| train/ | | +| approx_kl | 0.007034448 | +| clip_fraction | 0.33 | +| clip_range | 0.0594 | +| entropy_loss | -7.57 | +| explained_variance | -0.168 | +| learning_rate | 5.65e-05 | +| loss | -0.0266 | +| n_updates | 14152 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000123 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1383 | +| iterations | 3540 | +| time_elapsed | 5241 | +| total_timesteps | 7249920 | +| train/ | | +| approx_kl | 0.0083100125 | +| clip_fraction | 0.317 | +| clip_range | 0.0594 | +| entropy_loss | -7.44 | +| explained_variance | -0.0714 | +| learning_rate | 5.65e-05 | +| loss | -0.0276 | +| n_updates | 14156 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000218 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1383 | +| iterations | 3541 | +| time_elapsed | 5242 | +| total_timesteps | 7251968 | +| train/ | | +| approx_kl | 0.007879094 | +| clip_fraction | 0.334 | +| clip_range | 0.0594 | +| entropy_loss | -7.61 | +| explained_variance | -0.021 | +| learning_rate | 5.65e-05 | +| loss | -0.0241 | +| n_updates | 14160 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000304 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 1383 | +| iterations | 3542 | +| time_elapsed | 5244 | +| total_timesteps | 7254016 | +| train/ | | +| approx_kl | 0.007994264 | +| clip_fraction | 0.302 | +| clip_range | 0.0594 | +| entropy_loss | -7.71 | +| explained_variance | -0.103 | +| learning_rate | 5.64e-05 | +| loss | -0.0281 | +| n_updates | 14164 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000155 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 1383 | +| iterations | 3543 | +| time_elapsed | 5245 | +| total_timesteps | 7256064 | +| train/ | | +| approx_kl | 0.007836049 | +| clip_fraction | 0.32 | +| clip_range | 0.0593 | +| entropy_loss | -7.48 | +| explained_variance | -0.301 | +| learning_rate | 5.64e-05 | +| loss | -0.0293 | +| n_updates | 14168 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000129 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 1383 | +| iterations | 3544 | +| time_elapsed | 5247 | +| total_timesteps | 7258112 | +| train/ | | +| approx_kl | 0.008773554 | +| clip_fraction | 0.328 | +| clip_range | 0.0593 | +| entropy_loss | -7.67 | +| explained_variance | -0.0311 | +| learning_rate | 5.63e-05 | +| loss | -0.027 | +| n_updates | 14172 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000214 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 1383 | +| iterations | 3545 | +| time_elapsed | 5248 | +| total_timesteps | 7260160 | +| train/ | | +| approx_kl | 0.007243854 | +| clip_fraction | 0.318 | +| clip_range | 0.0593 | +| entropy_loss | -7.73 | +| explained_variance | -0.0501 | +| learning_rate | 5.63e-05 | +| loss | -0.028 | +| n_updates | 14176 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000144 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.304 | +| time/ | | +| fps | 1383 | +| iterations | 3546 | +| time_elapsed | 5250 | +| total_timesteps | 7262208 | +| train/ | | +| approx_kl | 0.0062842695 | +| clip_fraction | 0.321 | +| clip_range | 0.0592 | +| entropy_loss | -7.61 | +| explained_variance | -0.0459 | +| learning_rate | 5.62e-05 | +| loss | -0.0281 | +| n_updates | 14180 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000189 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 1383 | +| iterations | 3547 | +| time_elapsed | 5251 | +| total_timesteps | 7264256 | +| train/ | | +| approx_kl | 0.0071198856 | +| clip_fraction | 0.297 | +| clip_range | 0.0592 | +| entropy_loss | -7.69 | +| explained_variance | -0.0605 | +| learning_rate | 5.62e-05 | +| loss | -0.0193 | +| n_updates | 14184 | +| policy_gradient_loss | -0.0145 | +| value_loss | 0.000204 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1383 | +| iterations | 3548 | +| time_elapsed | 5252 | +| total_timesteps | 7266304 | +| train/ | | +| approx_kl | 0.0073807575 | +| clip_fraction | 0.307 | +| clip_range | 0.0592 | +| entropy_loss | -7.52 | +| explained_variance | -0.035 | +| learning_rate | 5.62e-05 | +| loss | -0.0234 | +| n_updates | 14188 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000264 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1383 | +| iterations | 3549 | +| time_elapsed | 5254 | +| total_timesteps | 7268352 | +| train/ | | +| approx_kl | 0.0077726934 | +| clip_fraction | 0.335 | +| clip_range | 0.0592 | +| entropy_loss | -7.56 | +| explained_variance | -0.0445 | +| learning_rate | 5.61e-05 | +| loss | -0.0272 | +| n_updates | 14192 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000329 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1383 | +| iterations | 3550 | +| time_elapsed | 5255 | +| total_timesteps | 7270400 | +| train/ | | +| approx_kl | 0.007963452 | +| clip_fraction | 0.336 | +| clip_range | 0.0591 | +| entropy_loss | -7.71 | +| explained_variance | -0.412 | +| learning_rate | 5.61e-05 | +| loss | -0.0396 | +| n_updates | 14196 | +| policy_gradient_loss | -0.0199 | +| value_loss | 8.66e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1383 | +| iterations | 3551 | +| time_elapsed | 5257 | +| total_timesteps | 7272448 | +| train/ | | +| approx_kl | 0.0076806163 | +| clip_fraction | 0.328 | +| clip_range | 0.0591 | +| entropy_loss | -7.67 | +| explained_variance | -0.0764 | +| learning_rate | 5.6e-05 | +| loss | -0.028 | +| n_updates | 14200 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000207 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.315 | +| time/ | | +| fps | 1383 | +| iterations | 3552 | +| time_elapsed | 5258 | +| total_timesteps | 7274496 | +| train/ | | +| approx_kl | 0.0074917986 | +| clip_fraction | 0.322 | +| clip_range | 0.0591 | +| entropy_loss | -7.6 | +| explained_variance | -0.0151 | +| learning_rate | 5.6e-05 | +| loss | -0.0251 | +| n_updates | 14204 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000147 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.306 | +| time/ | | +| fps | 1383 | +| iterations | 3553 | +| time_elapsed | 5260 | +| total_timesteps | 7276544 | +| train/ | | +| approx_kl | 0.008551062 | +| clip_fraction | 0.325 | +| clip_range | 0.0591 | +| entropy_loss | -7.49 | +| explained_variance | -0.0318 | +| learning_rate | 5.6e-05 | +| loss | -0.0318 | +| n_updates | 14208 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000135 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 1383 | +| iterations | 3554 | +| time_elapsed | 5261 | +| total_timesteps | 7278592 | +| train/ | | +| approx_kl | 0.0078121386 | +| clip_fraction | 0.332 | +| clip_range | 0.059 | +| entropy_loss | -7.53 | +| explained_variance | 0.0028 | +| learning_rate | 5.59e-05 | +| loss | -0.029 | +| n_updates | 14212 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000153 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 1383 | +| iterations | 3555 | +| time_elapsed | 5263 | +| total_timesteps | 7280640 | +| train/ | | +| approx_kl | 0.0078078117 | +| clip_fraction | 0.318 | +| clip_range | 0.059 | +| entropy_loss | -7.57 | +| explained_variance | -0.0632 | +| learning_rate | 5.59e-05 | +| loss | -0.0253 | +| n_updates | 14216 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000154 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 1383 | +| iterations | 3556 | +| time_elapsed | 5264 | +| total_timesteps | 7282688 | +| train/ | | +| approx_kl | 0.0060138144 | +| clip_fraction | 0.288 | +| clip_range | 0.059 | +| entropy_loss | -7.56 | +| explained_variance | 0.104 | +| learning_rate | 5.58e-05 | +| loss | -0.0254 | +| n_updates | 14220 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.00028 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.3 | +| time/ | | +| fps | 1383 | +| iterations | 3557 | +| time_elapsed | 5265 | +| total_timesteps | 7284736 | +| train/ | | +| approx_kl | 0.007463201 | +| clip_fraction | 0.329 | +| clip_range | 0.059 | +| entropy_loss | -7.42 | +| explained_variance | 0.0152 | +| learning_rate | 5.58e-05 | +| loss | -0.0263 | +| n_updates | 14224 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000183 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.298 | +| time/ | | +| fps | 1383 | +| iterations | 3558 | +| time_elapsed | 5267 | +| total_timesteps | 7286784 | +| train/ | | +| approx_kl | 0.00787608 | +| clip_fraction | 0.345 | +| clip_range | 0.0589 | +| entropy_loss | -7.68 | +| explained_variance | 0.0485 | +| learning_rate | 5.58e-05 | +| loss | -0.0303 | +| n_updates | 14228 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000128 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.298 | +| time/ | | +| fps | 1383 | +| iterations | 3559 | +| time_elapsed | 5268 | +| total_timesteps | 7288832 | +| train/ | | +| approx_kl | 0.008086908 | +| clip_fraction | 0.341 | +| clip_range | 0.0589 | +| entropy_loss | -7.57 | +| explained_variance | 0.0437 | +| learning_rate | 5.57e-05 | +| loss | -0.0279 | +| n_updates | 14232 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000171 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.298 | +| time/ | | +| fps | 1383 | +| iterations | 3560 | +| time_elapsed | 5270 | +| total_timesteps | 7290880 | +| train/ | | +| approx_kl | 0.0076745865 | +| clip_fraction | 0.317 | +| clip_range | 0.0589 | +| entropy_loss | -7.7 | +| explained_variance | -0.0434 | +| learning_rate | 5.57e-05 | +| loss | -0.0278 | +| n_updates | 14236 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000171 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.298 | +| time/ | | +| fps | 1383 | +| iterations | 3561 | +| time_elapsed | 5271 | +| total_timesteps | 7292928 | +| train/ | | +| approx_kl | 0.006469858 | +| clip_fraction | 0.304 | +| clip_range | 0.0589 | +| entropy_loss | -7.75 | +| explained_variance | -0.242 | +| learning_rate | 5.56e-05 | +| loss | -0.0281 | +| n_updates | 14240 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000108 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 1383 | +| iterations | 3562 | +| time_elapsed | 5272 | +| total_timesteps | 7294976 | +| train/ | | +| approx_kl | 0.007104747 | +| clip_fraction | 0.307 | +| clip_range | 0.0588 | +| entropy_loss | -7.73 | +| explained_variance | -0.139 | +| learning_rate | 5.56e-05 | +| loss | -0.0271 | +| n_updates | 14244 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000101 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 1383 | +| iterations | 3563 | +| time_elapsed | 5274 | +| total_timesteps | 7297024 | +| train/ | | +| approx_kl | 0.0069022034 | +| clip_fraction | 0.304 | +| clip_range | 0.0588 | +| entropy_loss | -7.59 | +| explained_variance | -0.0111 | +| learning_rate | 5.56e-05 | +| loss | -0.0246 | +| n_updates | 14248 | +| policy_gradient_loss | -0.0141 | +| value_loss | 0.000253 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 1383 | +| iterations | 3564 | +| time_elapsed | 5275 | +| total_timesteps | 7299072 | +| train/ | | +| approx_kl | 0.006139879 | +| clip_fraction | 0.31 | +| clip_range | 0.0588 | +| entropy_loss | -7.33 | +| explained_variance | 0.0185 | +| learning_rate | 5.55e-05 | +| loss | -0.0265 | +| n_updates | 14252 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000161 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1383 | +| iterations | 3565 | +| time_elapsed | 5277 | +| total_timesteps | 7301120 | +| train/ | | +| approx_kl | 0.007488116 | +| clip_fraction | 0.325 | +| clip_range | 0.0588 | +| entropy_loss | -7.37 | +| explained_variance | 0.0462 | +| learning_rate | 5.55e-05 | +| loss | -0.0268 | +| n_updates | 14256 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000151 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1383 | +| iterations | 3566 | +| time_elapsed | 5278 | +| total_timesteps | 7303168 | +| train/ | | +| approx_kl | 0.00686198 | +| clip_fraction | 0.282 | +| clip_range | 0.0587 | +| entropy_loss | -7.49 | +| explained_variance | -0.0162 | +| learning_rate | 5.54e-05 | +| loss | -0.0241 | +| n_updates | 14260 | +| policy_gradient_loss | -0.0137 | +| value_loss | 0.000172 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.304 | +| time/ | | +| fps | 1383 | +| iterations | 3567 | +| time_elapsed | 5280 | +| total_timesteps | 7305216 | +| train/ | | +| approx_kl | 0.008104617 | +| clip_fraction | 0.332 | +| clip_range | 0.0587 | +| entropy_loss | -7.6 | +| explained_variance | 0.00825 | +| learning_rate | 5.54e-05 | +| loss | -0.0258 | +| n_updates | 14264 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000143 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.304 | +| time/ | | +| fps | 1383 | +| iterations | 3568 | +| time_elapsed | 5281 | +| total_timesteps | 7307264 | +| train/ | | +| approx_kl | 0.0072407695 | +| clip_fraction | 0.325 | +| clip_range | 0.0587 | +| entropy_loss | -7.51 | +| explained_variance | 0.0128 | +| learning_rate | 5.54e-05 | +| loss | -0.0251 | +| n_updates | 14268 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000138 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.304 | +| time/ | | +| fps | 1383 | +| iterations | 3569 | +| time_elapsed | 5283 | +| total_timesteps | 7309312 | +| train/ | | +| approx_kl | 0.008394807 | +| clip_fraction | 0.318 | +| clip_range | 0.0587 | +| entropy_loss | -7.58 | +| explained_variance | 0.0116 | +| learning_rate | 5.53e-05 | +| loss | -0.0243 | +| n_updates | 14272 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000191 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.304 | +| time/ | | +| fps | 1383 | +| iterations | 3570 | +| time_elapsed | 5284 | +| total_timesteps | 7311360 | +| train/ | | +| approx_kl | 0.008070624 | +| clip_fraction | 0.304 | +| clip_range | 0.0586 | +| entropy_loss | -7.67 | +| explained_variance | -0.135 | +| learning_rate | 5.53e-05 | +| loss | -0.0237 | +| n_updates | 14276 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000152 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 1383 | +| iterations | 3571 | +| time_elapsed | 5286 | +| total_timesteps | 7313408 | +| train/ | | +| approx_kl | 0.008168364 | +| clip_fraction | 0.331 | +| clip_range | 0.0586 | +| entropy_loss | -7.68 | +| explained_variance | -0.173 | +| learning_rate | 5.52e-05 | +| loss | -0.0288 | +| n_updates | 14280 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000127 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.298 | +| time/ | | +| fps | 1383 | +| iterations | 3572 | +| time_elapsed | 5287 | +| total_timesteps | 7315456 | +| train/ | | +| approx_kl | 0.0075627 | +| clip_fraction | 0.312 | +| clip_range | 0.0586 | +| entropy_loss | -7.71 | +| explained_variance | -0.144 | +| learning_rate | 5.52e-05 | +| loss | -0.0289 | +| n_updates | 14284 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000129 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 1383 | +| iterations | 3573 | +| time_elapsed | 5289 | +| total_timesteps | 7317504 | +| train/ | | +| approx_kl | 0.007496653 | +| clip_fraction | 0.311 | +| clip_range | 0.0586 | +| entropy_loss | -7.58 | +| explained_variance | -0.0193 | +| learning_rate | 5.52e-05 | +| loss | -0.0244 | +| n_updates | 14288 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000211 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1383 | +| iterations | 3574 | +| time_elapsed | 5290 | +| total_timesteps | 7319552 | +| train/ | | +| approx_kl | 0.0068952036 | +| clip_fraction | 0.312 | +| clip_range | 0.0585 | +| entropy_loss | -7.52 | +| explained_variance | -0.00574 | +| learning_rate | 5.51e-05 | +| loss | -0.0281 | +| n_updates | 14292 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000221 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1383 | +| iterations | 3575 | +| time_elapsed | 5291 | +| total_timesteps | 7321600 | +| train/ | | +| approx_kl | 0.00787449 | +| clip_fraction | 0.328 | +| clip_range | 0.0585 | +| entropy_loss | -7.42 | +| explained_variance | -0.16 | +| learning_rate | 5.51e-05 | +| loss | -0.0278 | +| n_updates | 14296 | +| policy_gradient_loss | -0.0147 | +| value_loss | 0.000177 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 1383 | +| iterations | 3576 | +| time_elapsed | 5293 | +| total_timesteps | 7323648 | +| train/ | | +| approx_kl | 0.007636699 | +| clip_fraction | 0.331 | +| clip_range | 0.0585 | +| entropy_loss | -7.51 | +| explained_variance | -0.0524 | +| learning_rate | 5.5e-05 | +| loss | -0.0308 | +| n_updates | 14300 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 1383 | +| iterations | 3577 | +| time_elapsed | 5294 | +| total_timesteps | 7325696 | +| train/ | | +| approx_kl | 0.007684135 | +| clip_fraction | 0.307 | +| clip_range | 0.0585 | +| entropy_loss | -7.39 | +| explained_variance | -0.0151 | +| learning_rate | 5.5e-05 | +| loss | -0.023 | +| n_updates | 14304 | +| policy_gradient_loss | -0.014 | +| value_loss | 0.000252 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 1383 | +| iterations | 3578 | +| time_elapsed | 5296 | +| total_timesteps | 7327744 | +| train/ | | +| approx_kl | 0.0085701365 | +| clip_fraction | 0.357 | +| clip_range | 0.0584 | +| entropy_loss | -7.5 | +| explained_variance | -0.0903 | +| learning_rate | 5.5e-05 | +| loss | -0.0269 | +| n_updates | 14308 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000163 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 1383 | +| iterations | 3579 | +| time_elapsed | 5297 | +| total_timesteps | 7329792 | +| train/ | | +| approx_kl | 0.0091828285 | +| clip_fraction | 0.329 | +| clip_range | 0.0584 | +| entropy_loss | -7.51 | +| explained_variance | -0.126 | +| learning_rate | 5.49e-05 | +| loss | -0.0277 | +| n_updates | 14312 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000207 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 1383 | +| iterations | 3580 | +| time_elapsed | 5299 | +| total_timesteps | 7331840 | +| train/ | | +| approx_kl | 0.008368825 | +| clip_fraction | 0.326 | +| clip_range | 0.0584 | +| entropy_loss | -7.7 | +| explained_variance | -0.223 | +| learning_rate | 5.49e-05 | +| loss | -0.0266 | +| n_updates | 14316 | +| policy_gradient_loss | -0.0173 | +| value_loss | 8.62e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 1383 | +| iterations | 3581 | +| time_elapsed | 5300 | +| total_timesteps | 7333888 | +| train/ | | +| approx_kl | 0.0073624714 | +| clip_fraction | 0.325 | +| clip_range | 0.0584 | +| entropy_loss | -7.56 | +| explained_variance | 0.0364 | +| learning_rate | 5.48e-05 | +| loss | -0.0293 | +| n_updates | 14320 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000126 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 1383 | +| iterations | 3582 | +| time_elapsed | 5302 | +| total_timesteps | 7335936 | +| train/ | | +| approx_kl | 0.0069964947 | +| clip_fraction | 0.333 | +| clip_range | 0.0583 | +| entropy_loss | -7.53 | +| explained_variance | 0.0514 | +| learning_rate | 5.48e-05 | +| loss | -0.0282 | +| n_updates | 14324 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000106 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 1383 | +| iterations | 3583 | +| time_elapsed | 5303 | +| total_timesteps | 7337984 | +| train/ | | +| approx_kl | 0.008343119 | +| clip_fraction | 0.318 | +| clip_range | 0.0583 | +| entropy_loss | -7.68 | +| explained_variance | -0.0592 | +| learning_rate | 5.47e-05 | +| loss | -0.0288 | +| n_updates | 14328 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000166 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.295 | +| time/ | | +| fps | 1383 | +| iterations | 3584 | +| time_elapsed | 5304 | +| total_timesteps | 7340032 | +| train/ | | +| approx_kl | 0.0076678535 | +| clip_fraction | 0.328 | +| clip_range | 0.0583 | +| entropy_loss | -7.58 | +| explained_variance | -0.279 | +| learning_rate | 5.47e-05 | +| loss | -0.0272 | +| n_updates | 14332 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000161 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 1383 | +| iterations | 3585 | +| time_elapsed | 5306 | +| total_timesteps | 7342080 | +| train/ | | +| approx_kl | 0.0071670106 | +| clip_fraction | 0.323 | +| clip_range | 0.0582 | +| entropy_loss | -7.61 | +| explained_variance | -0.0463 | +| learning_rate | 5.47e-05 | +| loss | -0.0301 | +| n_updates | 14336 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000176 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 1383 | +| iterations | 3586 | +| time_elapsed | 5307 | +| total_timesteps | 7344128 | +| train/ | | +| approx_kl | 0.008226816 | +| clip_fraction | 0.347 | +| clip_range | 0.0582 | +| entropy_loss | -7.58 | +| explained_variance | -0.237 | +| learning_rate | 5.46e-05 | +| loss | -0.0329 | +| n_updates | 14340 | +| policy_gradient_loss | -0.0181 | +| value_loss | 8.71e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.29 | +| time/ | | +| fps | 1383 | +| iterations | 3587 | +| time_elapsed | 5309 | +| total_timesteps | 7346176 | +| train/ | | +| approx_kl | 0.007816118 | +| clip_fraction | 0.302 | +| clip_range | 0.0582 | +| entropy_loss | -7.37 | +| explained_variance | -0.134 | +| learning_rate | 5.46e-05 | +| loss | -0.0266 | +| n_updates | 14344 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000234 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.297 | +| time/ | | +| fps | 1383 | +| iterations | 3588 | +| time_elapsed | 5310 | +| total_timesteps | 7348224 | +| train/ | | +| approx_kl | 0.0086332355 | +| clip_fraction | 0.307 | +| clip_range | 0.0582 | +| entropy_loss | -7.43 | +| explained_variance | -0.0311 | +| learning_rate | 5.45e-05 | +| loss | -0.0243 | +| n_updates | 14348 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000231 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.297 | +| time/ | | +| fps | 1383 | +| iterations | 3589 | +| time_elapsed | 5312 | +| total_timesteps | 7350272 | +| train/ | | +| approx_kl | 0.0072551076 | +| clip_fraction | 0.328 | +| clip_range | 0.0581 | +| entropy_loss | -7.45 | +| explained_variance | -0.0307 | +| learning_rate | 5.45e-05 | +| loss | -0.0229 | +| n_updates | 14352 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000152 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.297 | +| time/ | | +| fps | 1383 | +| iterations | 3590 | +| time_elapsed | 5313 | +| total_timesteps | 7352320 | +| train/ | | +| approx_kl | 0.008311806 | +| clip_fraction | 0.325 | +| clip_range | 0.0581 | +| entropy_loss | -7.67 | +| explained_variance | -0.0888 | +| learning_rate | 5.45e-05 | +| loss | -0.0294 | +| n_updates | 14356 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000122 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.298 | +| time/ | | +| fps | 1383 | +| iterations | 3591 | +| time_elapsed | 5315 | +| total_timesteps | 7354368 | +| train/ | | +| approx_kl | 0.007859269 | +| clip_fraction | 0.324 | +| clip_range | 0.0581 | +| entropy_loss | -7.71 | +| explained_variance | -0.0532 | +| learning_rate | 5.44e-05 | +| loss | -0.0261 | +| n_updates | 14360 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000211 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 1383 | +| iterations | 3592 | +| time_elapsed | 5316 | +| total_timesteps | 7356416 | +| train/ | | +| approx_kl | 0.0075659966 | +| clip_fraction | 0.311 | +| clip_range | 0.0581 | +| entropy_loss | -7.53 | +| explained_variance | -0.0641 | +| learning_rate | 5.44e-05 | +| loss | -0.0262 | +| n_updates | 14364 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000206 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.297 | +| time/ | | +| fps | 1383 | +| iterations | 3593 | +| time_elapsed | 5318 | +| total_timesteps | 7358464 | +| train/ | | +| approx_kl | 0.007545989 | +| clip_fraction | 0.332 | +| clip_range | 0.058 | +| entropy_loss | -7.54 | +| explained_variance | -0.0726 | +| learning_rate | 5.43e-05 | +| loss | -0.025 | +| n_updates | 14368 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000135 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.291 | +| time/ | | +| fps | 1383 | +| iterations | 3594 | +| time_elapsed | 5319 | +| total_timesteps | 7360512 | +| train/ | | +| approx_kl | 0.0076870946 | +| clip_fraction | 0.332 | +| clip_range | 0.058 | +| entropy_loss | -7.55 | +| explained_variance | -0.138 | +| learning_rate | 5.43e-05 | +| loss | -0.0254 | +| n_updates | 14372 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000109 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.29 | +| time/ | | +| fps | 1383 | +| iterations | 3595 | +| time_elapsed | 5321 | +| total_timesteps | 7362560 | +| train/ | | +| approx_kl | 0.0086961305 | +| clip_fraction | 0.312 | +| clip_range | 0.058 | +| entropy_loss | -7.64 | +| explained_variance | -0.0262 | +| learning_rate | 5.43e-05 | +| loss | -0.0255 | +| n_updates | 14376 | +| policy_gradient_loss | -0.0146 | +| value_loss | 0.000194 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.288 | +| time/ | | +| fps | 1383 | +| iterations | 3596 | +| time_elapsed | 5322 | +| total_timesteps | 7364608 | +| train/ | | +| approx_kl | 0.007316258 | +| clip_fraction | 0.337 | +| clip_range | 0.058 | +| entropy_loss | -7.62 | +| explained_variance | -0.0527 | +| learning_rate | 5.42e-05 | +| loss | -0.0303 | +| n_updates | 14380 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000111 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.292 | +| time/ | | +| fps | 1383 | +| iterations | 3597 | +| time_elapsed | 5324 | +| total_timesteps | 7366656 | +| train/ | | +| approx_kl | 0.007363413 | +| clip_fraction | 0.319 | +| clip_range | 0.0579 | +| entropy_loss | -7.56 | +| explained_variance | 0.033 | +| learning_rate | 5.42e-05 | +| loss | -0.0178 | +| n_updates | 14384 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000204 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.289 | +| time/ | | +| fps | 1383 | +| iterations | 3598 | +| time_elapsed | 5325 | +| total_timesteps | 7368704 | +| train/ | | +| approx_kl | 0.0063891467 | +| clip_fraction | 0.292 | +| clip_range | 0.0579 | +| entropy_loss | -7.59 | +| explained_variance | -0.0433 | +| learning_rate | 5.41e-05 | +| loss | -0.0269 | +| n_updates | 14388 | +| policy_gradient_loss | -0.0146 | +| value_loss | 0.000217 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.286 | +| time/ | | +| fps | 1383 | +| iterations | 3599 | +| time_elapsed | 5326 | +| total_timesteps | 7370752 | +| train/ | | +| approx_kl | 0.007703062 | +| clip_fraction | 0.339 | +| clip_range | 0.0579 | +| entropy_loss | -7.54 | +| explained_variance | -0.122 | +| learning_rate | 5.41e-05 | +| loss | -0.024 | +| n_updates | 14392 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000132 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.286 | +| time/ | | +| fps | 1383 | +| iterations | 3600 | +| time_elapsed | 5328 | +| total_timesteps | 7372800 | +| train/ | | +| approx_kl | 0.0067581963 | +| clip_fraction | 0.297 | +| clip_range | 0.0579 | +| entropy_loss | -7.47 | +| explained_variance | 0.027 | +| learning_rate | 5.41e-05 | +| loss | -0.0259 | +| n_updates | 14396 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000236 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.287 | +| time/ | | +| fps | 1383 | +| iterations | 3601 | +| time_elapsed | 5329 | +| total_timesteps | 7374848 | +| train/ | | +| approx_kl | 0.0076077906 | +| clip_fraction | 0.329 | +| clip_range | 0.0578 | +| entropy_loss | -7.65 | +| explained_variance | -0.185 | +| learning_rate | 5.4e-05 | +| loss | -0.0274 | +| n_updates | 14400 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000138 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.278 | +| time/ | | +| fps | 1383 | +| iterations | 3602 | +| time_elapsed | 5331 | +| total_timesteps | 7376896 | +| train/ | | +| approx_kl | 0.0069386647 | +| clip_fraction | 0.333 | +| clip_range | 0.0578 | +| entropy_loss | -7.67 | +| explained_variance | 0.0567 | +| learning_rate | 5.4e-05 | +| loss | -0.0226 | +| n_updates | 14404 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000169 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 1383 | +| iterations | 3603 | +| time_elapsed | 5332 | +| total_timesteps | 7378944 | +| train/ | | +| approx_kl | 0.0074841296 | +| clip_fraction | 0.309 | +| clip_range | 0.0578 | +| entropy_loss | -7.55 | +| explained_variance | -0.0631 | +| learning_rate | 5.39e-05 | +| loss | -0.025 | +| n_updates | 14408 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000216 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.281 | +| time/ | | +| fps | 1383 | +| iterations | 3604 | +| time_elapsed | 5334 | +| total_timesteps | 7380992 | +| train/ | | +| approx_kl | 0.0066551785 | +| clip_fraction | 0.33 | +| clip_range | 0.0578 | +| entropy_loss | -7.54 | +| explained_variance | -0.0127 | +| learning_rate | 5.39e-05 | +| loss | -0.0254 | +| n_updates | 14412 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000164 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 1383 | +| iterations | 3605 | +| time_elapsed | 5335 | +| total_timesteps | 7383040 | +| train/ | | +| approx_kl | 0.007603362 | +| clip_fraction | 0.323 | +| clip_range | 0.0577 | +| entropy_loss | -7.47 | +| explained_variance | -0.0394 | +| learning_rate | 5.39e-05 | +| loss | -0.0251 | +| n_updates | 14416 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000146 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.274 | +| time/ | | +| fps | 1383 | +| iterations | 3606 | +| time_elapsed | 5337 | +| total_timesteps | 7385088 | +| train/ | | +| approx_kl | 0.006344181 | +| clip_fraction | 0.298 | +| clip_range | 0.0577 | +| entropy_loss | -7.58 | +| explained_variance | -0.0281 | +| learning_rate | 5.38e-05 | +| loss | -0.0265 | +| n_updates | 14420 | +| policy_gradient_loss | -0.0147 | +| value_loss | 0.000357 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.274 | +| time/ | | +| fps | 1383 | +| iterations | 3607 | +| time_elapsed | 5338 | +| total_timesteps | 7387136 | +| train/ | | +| approx_kl | 0.008166907 | +| clip_fraction | 0.354 | +| clip_range | 0.0577 | +| entropy_loss | -7.44 | +| explained_variance | 0.00604 | +| learning_rate | 5.38e-05 | +| loss | -0.0317 | +| n_updates | 14424 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000187 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.277 | +| time/ | | +| fps | 1383 | +| iterations | 3608 | +| time_elapsed | 5339 | +| total_timesteps | 7389184 | +| train/ | | +| approx_kl | 0.007229048 | +| clip_fraction | 0.324 | +| clip_range | 0.0577 | +| entropy_loss | -7.68 | +| explained_variance | -0.163 | +| learning_rate | 5.37e-05 | +| loss | -0.0293 | +| n_updates | 14428 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000125 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 1383 | +| iterations | 3609 | +| time_elapsed | 5341 | +| total_timesteps | 7391232 | +| train/ | | +| approx_kl | 0.006805158 | +| clip_fraction | 0.349 | +| clip_range | 0.0576 | +| entropy_loss | -7.65 | +| explained_variance | -0.175 | +| learning_rate | 5.37e-05 | +| loss | -0.0286 | +| n_updates | 14432 | +| policy_gradient_loss | -0.0174 | +| value_loss | 7.8e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 1383 | +| iterations | 3610 | +| time_elapsed | 5342 | +| total_timesteps | 7393280 | +| train/ | | +| approx_kl | 0.0073141973 | +| clip_fraction | 0.307 | +| clip_range | 0.0576 | +| entropy_loss | -7.5 | +| explained_variance | 0.00263 | +| learning_rate | 5.37e-05 | +| loss | -0.0212 | +| n_updates | 14436 | +| policy_gradient_loss | -0.0136 | +| value_loss | 0.000203 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 1383 | +| iterations | 3611 | +| time_elapsed | 5344 | +| total_timesteps | 7395328 | +| train/ | | +| approx_kl | 0.0074982992 | +| clip_fraction | 0.334 | +| clip_range | 0.0576 | +| entropy_loss | -7.67 | +| explained_variance | -0.126 | +| learning_rate | 5.36e-05 | +| loss | -0.0272 | +| n_updates | 14440 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000121 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.274 | +| time/ | | +| fps | 1383 | +| iterations | 3612 | +| time_elapsed | 5345 | +| total_timesteps | 7397376 | +| train/ | | +| approx_kl | 0.0067709787 | +| clip_fraction | 0.322 | +| clip_range | 0.0576 | +| entropy_loss | -7.71 | +| explained_variance | -0.0332 | +| learning_rate | 5.36e-05 | +| loss | -0.0271 | +| n_updates | 14444 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.00027 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 1383 | +| iterations | 3613 | +| time_elapsed | 5347 | +| total_timesteps | 7399424 | +| train/ | | +| approx_kl | 0.0069120103 | +| clip_fraction | 0.34 | +| clip_range | 0.0575 | +| entropy_loss | -7.28 | +| explained_variance | 0.0175 | +| learning_rate | 5.35e-05 | +| loss | -0.0309 | +| n_updates | 14448 | +| policy_gradient_loss | -0.0184 | +| value_loss | 9.1e-05 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 1383 | +| iterations | 3614 | +| time_elapsed | 5348 | +| total_timesteps | 7401472 | +| train/ | | +| approx_kl | 0.0072966013 | +| clip_fraction | 0.347 | +| clip_range | 0.0575 | +| entropy_loss | -7.59 | +| explained_variance | -0.00941 | +| learning_rate | 5.35e-05 | +| loss | -0.0289 | +| n_updates | 14452 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000116 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 1383 | +| iterations | 3615 | +| time_elapsed | 5350 | +| total_timesteps | 7403520 | +| train/ | | +| approx_kl | 0.0072813877 | +| clip_fraction | 0.311 | +| clip_range | 0.0575 | +| entropy_loss | -7.71 | +| explained_variance | -0.0125 | +| learning_rate | 5.35e-05 | +| loss | -0.029 | +| n_updates | 14456 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000157 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.269 | +| time/ | | +| fps | 1383 | +| iterations | 3616 | +| time_elapsed | 5351 | +| total_timesteps | 7405568 | +| train/ | | +| approx_kl | 0.007150438 | +| clip_fraction | 0.344 | +| clip_range | 0.0575 | +| entropy_loss | -7.68 | +| explained_variance | -0.0965 | +| learning_rate | 5.34e-05 | +| loss | -0.0269 | +| n_updates | 14460 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.00016 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.269 | +| time/ | | +| fps | 1383 | +| iterations | 3617 | +| time_elapsed | 5353 | +| total_timesteps | 7407616 | +| train/ | | +| approx_kl | 0.0069962423 | +| clip_fraction | 0.322 | +| clip_range | 0.0574 | +| entropy_loss | -7.57 | +| explained_variance | -0.173 | +| learning_rate | 5.34e-05 | +| loss | -0.025 | +| n_updates | 14464 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000156 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.266 | +| time/ | | +| fps | 1383 | +| iterations | 3618 | +| time_elapsed | 5354 | +| total_timesteps | 7409664 | +| train/ | | +| approx_kl | 0.0069451625 | +| clip_fraction | 0.305 | +| clip_range | 0.0574 | +| entropy_loss | -7.67 | +| explained_variance | 0.0562 | +| learning_rate | 5.33e-05 | +| loss | -0.0237 | +| n_updates | 14468 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000173 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.266 | +| time/ | | +| fps | 1383 | +| iterations | 3619 | +| time_elapsed | 5356 | +| total_timesteps | 7411712 | +| train/ | | +| approx_kl | 0.0062824218 | +| clip_fraction | 0.318 | +| clip_range | 0.0574 | +| entropy_loss | -7.58 | +| explained_variance | -0.0817 | +| learning_rate | 5.33e-05 | +| loss | -0.0247 | +| n_updates | 14472 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000101 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.267 | +| time/ | | +| fps | 1383 | +| iterations | 3620 | +| time_elapsed | 5357 | +| total_timesteps | 7413760 | +| train/ | | +| approx_kl | 0.008099399 | +| clip_fraction | 0.316 | +| clip_range | 0.0574 | +| entropy_loss | -7.67 | +| explained_variance | -0.0559 | +| learning_rate | 5.32e-05 | +| loss | -0.0217 | +| n_updates | 14476 | +| policy_gradient_loss | -0.0147 | +| value_loss | 0.000161 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.274 | +| time/ | | +| fps | 1383 | +| iterations | 3621 | +| time_elapsed | 5359 | +| total_timesteps | 7415808 | +| train/ | | +| approx_kl | 0.0063892165 | +| clip_fraction | 0.318 | +| clip_range | 0.0573 | +| entropy_loss | -7.68 | +| explained_variance | -0.0539 | +| learning_rate | 5.32e-05 | +| loss | -0.0277 | +| n_updates | 14480 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000119 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.274 | +| time/ | | +| fps | 1383 | +| iterations | 3622 | +| time_elapsed | 5360 | +| total_timesteps | 7417856 | +| train/ | | +| approx_kl | 0.0065581715 | +| clip_fraction | 0.294 | +| clip_range | 0.0573 | +| entropy_loss | -7.5 | +| explained_variance | -0.0805 | +| learning_rate | 5.32e-05 | +| loss | -0.0251 | +| n_updates | 14484 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000157 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.271 | +| time/ | | +| fps | 1383 | +| iterations | 3623 | +| time_elapsed | 5361 | +| total_timesteps | 7419904 | +| train/ | | +| approx_kl | 0.007030246 | +| clip_fraction | 0.317 | +| clip_range | 0.0573 | +| entropy_loss | -7.74 | +| explained_variance | -0.089 | +| learning_rate | 5.31e-05 | +| loss | -0.0268 | +| n_updates | 14488 | +| policy_gradient_loss | -0.0166 | +| value_loss | 7.7e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.277 | +| time/ | | +| fps | 1383 | +| iterations | 3624 | +| time_elapsed | 5363 | +| total_timesteps | 7421952 | +| train/ | | +| approx_kl | 0.0056302785 | +| clip_fraction | 0.286 | +| clip_range | 0.0573 | +| entropy_loss | -7.61 | +| explained_variance | -0.0848 | +| learning_rate | 5.31e-05 | +| loss | -0.0213 | +| n_updates | 14492 | +| policy_gradient_loss | -0.0135 | +| value_loss | 0.000245 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.285 | +| time/ | | +| fps | 1383 | +| iterations | 3625 | +| time_elapsed | 5364 | +| total_timesteps | 7424000 | +| train/ | | +| approx_kl | 0.0063057025 | +| clip_fraction | 0.292 | +| clip_range | 0.0572 | +| entropy_loss | -7.45 | +| explained_variance | 0.0754 | +| learning_rate | 5.3e-05 | +| loss | -0.0251 | +| n_updates | 14496 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000204 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.285 | +| time/ | | +| fps | 1383 | +| iterations | 3626 | +| time_elapsed | 5366 | +| total_timesteps | 7426048 | +| train/ | | +| approx_kl | 0.0062677893 | +| clip_fraction | 0.311 | +| clip_range | 0.0572 | +| entropy_loss | -7.56 | +| explained_variance | -0.0238 | +| learning_rate | 5.3e-05 | +| loss | -0.0292 | +| n_updates | 14500 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000258 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 1383 | +| iterations | 3627 | +| time_elapsed | 5367 | +| total_timesteps | 7428096 | +| train/ | | +| approx_kl | 0.0069144946 | +| clip_fraction | 0.32 | +| clip_range | 0.0572 | +| entropy_loss | -7.75 | +| explained_variance | 0.0265 | +| learning_rate | 5.3e-05 | +| loss | -0.0295 | +| n_updates | 14504 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000115 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.278 | +| time/ | | +| fps | 1383 | +| iterations | 3628 | +| time_elapsed | 5369 | +| total_timesteps | 7430144 | +| train/ | | +| approx_kl | 0.0060870447 | +| clip_fraction | 0.291 | +| clip_range | 0.0571 | +| entropy_loss | -7.64 | +| explained_variance | 0.0588 | +| learning_rate | 5.29e-05 | +| loss | -0.0214 | +| n_updates | 14508 | +| policy_gradient_loss | -0.0146 | +| value_loss | 0.000336 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.287 | +| time/ | | +| fps | 1383 | +| iterations | 3629 | +| time_elapsed | 5370 | +| total_timesteps | 7432192 | +| train/ | | +| approx_kl | 0.006000353 | +| clip_fraction | 0.319 | +| clip_range | 0.0571 | +| entropy_loss | -7.69 | +| explained_variance | -0.147 | +| learning_rate | 5.29e-05 | +| loss | -0.0265 | +| n_updates | 14512 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000231 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 1383 | +| iterations | 3630 | +| time_elapsed | 5372 | +| total_timesteps | 7434240 | +| train/ | | +| approx_kl | 0.005868922 | +| clip_fraction | 0.294 | +| clip_range | 0.0571 | +| entropy_loss | -7.58 | +| explained_variance | -0.0492 | +| learning_rate | 5.28e-05 | +| loss | -0.0237 | +| n_updates | 14516 | +| policy_gradient_loss | -0.0148 | +| value_loss | 0.000219 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 1383 | +| iterations | 3631 | +| time_elapsed | 5373 | +| total_timesteps | 7436288 | +| train/ | | +| approx_kl | 0.0073121744 | +| clip_fraction | 0.332 | +| clip_range | 0.0571 | +| entropy_loss | -7.64 | +| explained_variance | -0.358 | +| learning_rate | 5.28e-05 | +| loss | -0.0273 | +| n_updates | 14520 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000119 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.277 | +| time/ | | +| fps | 1383 | +| iterations | 3632 | +| time_elapsed | 5375 | +| total_timesteps | 7438336 | +| train/ | | +| approx_kl | 0.007348778 | +| clip_fraction | 0.321 | +| clip_range | 0.057 | +| entropy_loss | -7.49 | +| explained_variance | 0.0508 | +| learning_rate | 5.28e-05 | +| loss | -0.0268 | +| n_updates | 14524 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000161 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.281 | +| time/ | | +| fps | 1383 | +| iterations | 3633 | +| time_elapsed | 5376 | +| total_timesteps | 7440384 | +| train/ | | +| approx_kl | 0.0067106187 | +| clip_fraction | 0.319 | +| clip_range | 0.057 | +| entropy_loss | -7.57 | +| explained_variance | -0.035 | +| learning_rate | 5.27e-05 | +| loss | -0.029 | +| n_updates | 14528 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000171 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.281 | +| time/ | | +| fps | 1383 | +| iterations | 3634 | +| time_elapsed | 5378 | +| total_timesteps | 7442432 | +| train/ | | +| approx_kl | 0.0075093997 | +| clip_fraction | 0.323 | +| clip_range | 0.057 | +| entropy_loss | -7.64 | +| explained_variance | -0.0995 | +| learning_rate | 5.27e-05 | +| loss | -0.0246 | +| n_updates | 14532 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000118 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.281 | +| time/ | | +| fps | 1383 | +| iterations | 3635 | +| time_elapsed | 5379 | +| total_timesteps | 7444480 | +| train/ | | +| approx_kl | 0.007814825 | +| clip_fraction | 0.328 | +| clip_range | 0.057 | +| entropy_loss | -7.7 | +| explained_variance | -0.0487 | +| learning_rate | 5.26e-05 | +| loss | -0.0258 | +| n_updates | 14536 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000163 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.285 | +| time/ | | +| fps | 1383 | +| iterations | 3636 | +| time_elapsed | 5381 | +| total_timesteps | 7446528 | +| train/ | | +| approx_kl | 0.008237304 | +| clip_fraction | 0.323 | +| clip_range | 0.0569 | +| entropy_loss | -7.7 | +| explained_variance | -0.0969 | +| learning_rate | 5.26e-05 | +| loss | -0.0316 | +| n_updates | 14540 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000111 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.289 | +| time/ | | +| fps | 1383 | +| iterations | 3637 | +| time_elapsed | 5382 | +| total_timesteps | 7448576 | +| train/ | | +| approx_kl | 0.0057989922 | +| clip_fraction | 0.298 | +| clip_range | 0.0569 | +| entropy_loss | -7.61 | +| explained_variance | -0.0121 | +| learning_rate | 5.26e-05 | +| loss | -0.0225 | +| n_updates | 14544 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.000192 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.287 | +| time/ | | +| fps | 1383 | +| iterations | 3638 | +| time_elapsed | 5383 | +| total_timesteps | 7450624 | +| train/ | | +| approx_kl | 0.007412513 | +| clip_fraction | 0.324 | +| clip_range | 0.0569 | +| entropy_loss | -7.51 | +| explained_variance | 0.0395 | +| learning_rate | 5.25e-05 | +| loss | -0.0267 | +| n_updates | 14548 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000132 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 1383 | +| iterations | 3639 | +| time_elapsed | 5385 | +| total_timesteps | 7452672 | +| train/ | | +| approx_kl | 0.0070427284 | +| clip_fraction | 0.33 | +| clip_range | 0.0569 | +| entropy_loss | -7.59 | +| explained_variance | -0.0353 | +| learning_rate | 5.25e-05 | +| loss | -0.0261 | +| n_updates | 14552 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000158 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 1383 | +| iterations | 3640 | +| time_elapsed | 5386 | +| total_timesteps | 7454720 | +| train/ | | +| approx_kl | 0.007147521 | +| clip_fraction | 0.318 | +| clip_range | 0.0568 | +| entropy_loss | -7.52 | +| explained_variance | 0.0388 | +| learning_rate | 5.24e-05 | +| loss | -0.0243 | +| n_updates | 14556 | +| policy_gradient_loss | -0.0148 | +| value_loss | 0.000177 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.27 | +| time/ | | +| fps | 1383 | +| iterations | 3641 | +| time_elapsed | 5388 | +| total_timesteps | 7456768 | +| train/ | | +| approx_kl | 0.007282679 | +| clip_fraction | 0.329 | +| clip_range | 0.0568 | +| entropy_loss | -7.56 | +| explained_variance | 0.0795 | +| learning_rate | 5.24e-05 | +| loss | -0.027 | +| n_updates | 14560 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.00013 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.272 | +| time/ | | +| fps | 1383 | +| iterations | 3642 | +| time_elapsed | 5389 | +| total_timesteps | 7458816 | +| train/ | | +| approx_kl | 0.0058970875 | +| clip_fraction | 0.322 | +| clip_range | 0.0568 | +| entropy_loss | -7.63 | +| explained_variance | -0.0585 | +| learning_rate | 5.24e-05 | +| loss | -0.0269 | +| n_updates | 14564 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000188 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.264 | +| time/ | | +| fps | 1383 | +| iterations | 3643 | +| time_elapsed | 5391 | +| total_timesteps | 7460864 | +| train/ | | +| approx_kl | 0.005734913 | +| clip_fraction | 0.296 | +| clip_range | 0.0568 | +| entropy_loss | -7.62 | +| explained_variance | -0.0887 | +| learning_rate | 5.23e-05 | +| loss | -0.0219 | +| n_updates | 14568 | +| policy_gradient_loss | -0.0146 | +| value_loss | 0.000165 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.264 | +| time/ | | +| fps | 1383 | +| iterations | 3644 | +| time_elapsed | 5392 | +| total_timesteps | 7462912 | +| train/ | | +| approx_kl | 0.0075316885 | +| clip_fraction | 0.32 | +| clip_range | 0.0567 | +| entropy_loss | -7.58 | +| explained_variance | 0.0483 | +| learning_rate | 5.23e-05 | +| loss | -0.0239 | +| n_updates | 14572 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000117 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.277 | +| time/ | | +| fps | 1383 | +| iterations | 3645 | +| time_elapsed | 5394 | +| total_timesteps | 7464960 | +| train/ | | +| approx_kl | 0.008599289 | +| clip_fraction | 0.341 | +| clip_range | 0.0567 | +| entropy_loss | -7.62 | +| explained_variance | -0.135 | +| learning_rate | 5.22e-05 | +| loss | -0.0226 | +| n_updates | 14576 | +| policy_gradient_loss | -0.0166 | +| value_loss | 7.82e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.277 | +| time/ | | +| fps | 1383 | +| iterations | 3646 | +| time_elapsed | 5395 | +| total_timesteps | 7467008 | +| train/ | | +| approx_kl | 0.0074863606 | +| clip_fraction | 0.322 | +| clip_range | 0.0567 | +| entropy_loss | -7.37 | +| explained_variance | 0.0427 | +| learning_rate | 5.22e-05 | +| loss | -0.0269 | +| n_updates | 14580 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000266 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.277 | +| time/ | | +| fps | 1383 | +| iterations | 3647 | +| time_elapsed | 5397 | +| total_timesteps | 7469056 | +| train/ | | +| approx_kl | 0.00795773 | +| clip_fraction | 0.325 | +| clip_range | 0.0567 | +| entropy_loss | -7.63 | +| explained_variance | -0.26 | +| learning_rate | 5.22e-05 | +| loss | -0.0224 | +| n_updates | 14584 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.0001 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.274 | +| time/ | | +| fps | 1383 | +| iterations | 3648 | +| time_elapsed | 5398 | +| total_timesteps | 7471104 | +| train/ | | +| approx_kl | 0.0072090863 | +| clip_fraction | 0.311 | +| clip_range | 0.0566 | +| entropy_loss | -7.72 | +| explained_variance | -0.0753 | +| learning_rate | 5.21e-05 | +| loss | -0.0262 | +| n_updates | 14588 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000159 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.274 | +| time/ | | +| fps | 1383 | +| iterations | 3649 | +| time_elapsed | 5400 | +| total_timesteps | 7473152 | +| train/ | | +| approx_kl | 0.0068852925 | +| clip_fraction | 0.324 | +| clip_range | 0.0566 | +| entropy_loss | -7.69 | +| explained_variance | -0.139 | +| learning_rate | 5.21e-05 | +| loss | -0.026 | +| n_updates | 14592 | +| policy_gradient_loss | -0.0186 | +| value_loss | 8.54e-05 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.284 | +| time/ | | +| fps | 1383 | +| iterations | 3650 | +| time_elapsed | 5401 | +| total_timesteps | 7475200 | +| train/ | | +| approx_kl | 0.0072809453 | +| clip_fraction | 0.338 | +| clip_range | 0.0566 | +| entropy_loss | -7.57 | +| explained_variance | -0.0496 | +| learning_rate | 5.2e-05 | +| loss | -0.028 | +| n_updates | 14596 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000139 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.284 | +| time/ | | +| fps | 1383 | +| iterations | 3651 | +| time_elapsed | 5402 | +| total_timesteps | 7477248 | +| train/ | | +| approx_kl | 0.0064213774 | +| clip_fraction | 0.303 | +| clip_range | 0.0566 | +| entropy_loss | -7.37 | +| explained_variance | -0.0516 | +| learning_rate | 5.2e-05 | +| loss | -0.0247 | +| n_updates | 14600 | +| policy_gradient_loss | -0.0147 | +| value_loss | 0.000172 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.284 | +| time/ | | +| fps | 1383 | +| iterations | 3652 | +| time_elapsed | 5404 | +| total_timesteps | 7479296 | +| train/ | | +| approx_kl | 0.0066610156 | +| clip_fraction | 0.333 | +| clip_range | 0.0565 | +| entropy_loss | -7.55 | +| explained_variance | 0.0128 | +| learning_rate | 5.2e-05 | +| loss | -0.0259 | +| n_updates | 14604 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.00023 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.278 | +| time/ | | +| fps | 1383 | +| iterations | 3653 | +| time_elapsed | 5405 | +| total_timesteps | 7481344 | +| train/ | | +| approx_kl | 0.008167564 | +| clip_fraction | 0.378 | +| clip_range | 0.0565 | +| entropy_loss | -7.75 | +| explained_variance | -0.587 | +| learning_rate | 5.19e-05 | +| loss | -0.0345 | +| n_updates | 14608 | +| policy_gradient_loss | -0.0224 | +| value_loss | 4.51e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.281 | +| time/ | | +| fps | 1383 | +| iterations | 3654 | +| time_elapsed | 5407 | +| total_timesteps | 7483392 | +| train/ | | +| approx_kl | 0.0074472018 | +| clip_fraction | 0.331 | +| clip_range | 0.0565 | +| entropy_loss | -7.6 | +| explained_variance | -0.0694 | +| learning_rate | 5.19e-05 | +| loss | -0.0262 | +| n_updates | 14612 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000109 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 1383 | +| iterations | 3655 | +| time_elapsed | 5408 | +| total_timesteps | 7485440 | +| train/ | | +| approx_kl | 0.0066210674 | +| clip_fraction | 0.296 | +| clip_range | 0.0565 | +| entropy_loss | -7.63 | +| explained_variance | -0.0382 | +| learning_rate | 5.18e-05 | +| loss | -0.02 | +| n_updates | 14616 | +| policy_gradient_loss | -0.0135 | +| value_loss | 0.00016 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 1383 | +| iterations | 3656 | +| time_elapsed | 5410 | +| total_timesteps | 7487488 | +| train/ | | +| approx_kl | 0.0061679455 | +| clip_fraction | 0.316 | +| clip_range | 0.0564 | +| entropy_loss | -7.59 | +| explained_variance | -0.0219 | +| learning_rate | 5.18e-05 | +| loss | -0.026 | +| n_updates | 14620 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000139 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.283 | +| time/ | | +| fps | 1384 | +| iterations | 3657 | +| time_elapsed | 5411 | +| total_timesteps | 7489536 | +| train/ | | +| approx_kl | 0.00837907 | +| clip_fraction | 0.33 | +| clip_range | 0.0564 | +| entropy_loss | -7.58 | +| explained_variance | -0.0594 | +| learning_rate | 5.17e-05 | +| loss | -0.0229 | +| n_updates | 14624 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.000203 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.283 | +| time/ | | +| fps | 1384 | +| iterations | 3658 | +| time_elapsed | 5412 | +| total_timesteps | 7491584 | +| train/ | | +| approx_kl | 0.008050466 | +| clip_fraction | 0.333 | +| clip_range | 0.0564 | +| entropy_loss | -7.63 | +| explained_variance | -0.0435 | +| learning_rate | 5.17e-05 | +| loss | -0.0258 | +| n_updates | 14628 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000185 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 1384 | +| iterations | 3659 | +| time_elapsed | 5414 | +| total_timesteps | 7493632 | +| train/ | | +| approx_kl | 0.007244329 | +| clip_fraction | 0.336 | +| clip_range | 0.0564 | +| entropy_loss | -7.56 | +| explained_variance | -0.255 | +| learning_rate | 5.17e-05 | +| loss | -0.0297 | +| n_updates | 14632 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000113 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.285 | +| time/ | | +| fps | 1384 | +| iterations | 3660 | +| time_elapsed | 5415 | +| total_timesteps | 7495680 | +| train/ | | +| approx_kl | 0.007733807 | +| clip_fraction | 0.316 | +| clip_range | 0.0563 | +| entropy_loss | -7.49 | +| explained_variance | 0.0748 | +| learning_rate | 5.16e-05 | +| loss | -0.0232 | +| n_updates | 14636 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.00012 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.289 | +| time/ | | +| fps | 1384 | +| iterations | 3661 | +| time_elapsed | 5417 | +| total_timesteps | 7497728 | +| train/ | | +| approx_kl | 0.006453276 | +| clip_fraction | 0.298 | +| clip_range | 0.0563 | +| entropy_loss | -7.31 | +| explained_variance | -0.0619 | +| learning_rate | 5.16e-05 | +| loss | -0.0231 | +| n_updates | 14640 | +| policy_gradient_loss | -0.0139 | +| value_loss | 0.000229 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.29 | +| time/ | | +| fps | 1384 | +| iterations | 3662 | +| time_elapsed | 5418 | +| total_timesteps | 7499776 | +| train/ | | +| approx_kl | 0.0070030233 | +| clip_fraction | 0.355 | +| clip_range | 0.0563 | +| entropy_loss | -7.5 | +| explained_variance | -0.0537 | +| learning_rate | 5.15e-05 | +| loss | -0.0308 | +| n_updates | 14644 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000253 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.29 | +| time/ | | +| fps | 1384 | +| iterations | 3663 | +| time_elapsed | 5420 | +| total_timesteps | 7501824 | +| train/ | | +| approx_kl | 0.0066689197 | +| clip_fraction | 0.326 | +| clip_range | 0.0563 | +| entropy_loss | -7.56 | +| explained_variance | -0.0769 | +| learning_rate | 5.15e-05 | +| loss | -0.022 | +| n_updates | 14648 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000289 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.294 | +| time/ | | +| fps | 1384 | +| iterations | 3664 | +| time_elapsed | 5421 | +| total_timesteps | 7503872 | +| train/ | | +| approx_kl | 0.0074980548 | +| clip_fraction | 0.331 | +| clip_range | 0.0562 | +| entropy_loss | -7.62 | +| explained_variance | -0.2 | +| learning_rate | 5.15e-05 | +| loss | -0.0292 | +| n_updates | 14652 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000177 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 1384 | +| iterations | 3665 | +| time_elapsed | 5423 | +| total_timesteps | 7505920 | +| train/ | | +| approx_kl | 0.0073098163 | +| clip_fraction | 0.313 | +| clip_range | 0.0562 | +| entropy_loss | -7.57 | +| explained_variance | 0.114 | +| learning_rate | 5.14e-05 | +| loss | -0.0257 | +| n_updates | 14656 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000195 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.292 | +| time/ | | +| fps | 1384 | +| iterations | 3666 | +| time_elapsed | 5424 | +| total_timesteps | 7507968 | +| train/ | | +| approx_kl | 0.007344729 | +| clip_fraction | 0.321 | +| clip_range | 0.0562 | +| entropy_loss | -7.59 | +| explained_variance | 0.0193 | +| learning_rate | 5.14e-05 | +| loss | -0.0226 | +| n_updates | 14660 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000137 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.287 | +| time/ | | +| fps | 1384 | +| iterations | 3667 | +| time_elapsed | 5426 | +| total_timesteps | 7510016 | +| train/ | | +| approx_kl | 0.007498171 | +| clip_fraction | 0.325 | +| clip_range | 0.0562 | +| entropy_loss | -7.57 | +| explained_variance | -0.129 | +| learning_rate | 5.13e-05 | +| loss | -0.0254 | +| n_updates | 14664 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000192 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.284 | +| time/ | | +| fps | 1384 | +| iterations | 3668 | +| time_elapsed | 5427 | +| total_timesteps | 7512064 | +| train/ | | +| approx_kl | 0.007289203 | +| clip_fraction | 0.311 | +| clip_range | 0.0561 | +| entropy_loss | -7.6 | +| explained_variance | -0.0434 | +| learning_rate | 5.13e-05 | +| loss | -0.0218 | +| n_updates | 14668 | +| policy_gradient_loss | -0.0145 | +| value_loss | 0.000171 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.291 | +| time/ | | +| fps | 1384 | +| iterations | 3669 | +| time_elapsed | 5429 | +| total_timesteps | 7514112 | +| train/ | | +| approx_kl | 0.006737974 | +| clip_fraction | 0.341 | +| clip_range | 0.0561 | +| entropy_loss | -7.6 | +| explained_variance | -0.152 | +| learning_rate | 5.13e-05 | +| loss | -0.0255 | +| n_updates | 14672 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.00015 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.294 | +| time/ | | +| fps | 1384 | +| iterations | 3670 | +| time_elapsed | 5430 | +| total_timesteps | 7516160 | +| train/ | | +| approx_kl | 0.0063554375 | +| clip_fraction | 0.321 | +| clip_range | 0.0561 | +| entropy_loss | -7.46 | +| explained_variance | -0.0361 | +| learning_rate | 5.12e-05 | +| loss | -0.0227 | +| n_updates | 14676 | +| policy_gradient_loss | -0.0139 | +| value_loss | 0.000309 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.294 | +| time/ | | +| fps | 1384 | +| iterations | 3671 | +| time_elapsed | 5432 | +| total_timesteps | 7518208 | +| train/ | | +| approx_kl | 0.0067773154 | +| clip_fraction | 0.332 | +| clip_range | 0.056 | +| entropy_loss | -7.3 | +| explained_variance | 0.00597 | +| learning_rate | 5.12e-05 | +| loss | -0.0239 | +| n_updates | 14680 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.00023 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 1384 | +| iterations | 3672 | +| time_elapsed | 5433 | +| total_timesteps | 7520256 | +| train/ | | +| approx_kl | 0.006917037 | +| clip_fraction | 0.35 | +| clip_range | 0.056 | +| entropy_loss | -7.68 | +| explained_variance | -0.299 | +| learning_rate | 5.11e-05 | +| loss | -0.031 | +| n_updates | 14684 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000172 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 1384 | +| iterations | 3673 | +| time_elapsed | 5434 | +| total_timesteps | 7522304 | +| train/ | | +| approx_kl | 0.007863249 | +| clip_fraction | 0.346 | +| clip_range | 0.056 | +| entropy_loss | -7.6 | +| explained_variance | -0.0874 | +| learning_rate | 5.11e-05 | +| loss | -0.0342 | +| n_updates | 14688 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000131 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.293 | +| time/ | | +| fps | 1384 | +| iterations | 3674 | +| time_elapsed | 5436 | +| total_timesteps | 7524352 | +| train/ | | +| approx_kl | 0.007902174 | +| clip_fraction | 0.321 | +| clip_range | 0.056 | +| entropy_loss | -7.52 | +| explained_variance | -0.0272 | +| learning_rate | 5.11e-05 | +| loss | -0.0276 | +| n_updates | 14692 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.000159 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.293 | +| time/ | | +| fps | 1384 | +| iterations | 3675 | +| time_elapsed | 5437 | +| total_timesteps | 7526400 | +| train/ | | +| approx_kl | 0.0073742135 | +| clip_fraction | 0.316 | +| clip_range | 0.0559 | +| entropy_loss | -7.6 | +| explained_variance | -0.108 | +| learning_rate | 5.1e-05 | +| loss | -0.0246 | +| n_updates | 14696 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000187 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.293 | +| time/ | | +| fps | 1384 | +| iterations | 3676 | +| time_elapsed | 5439 | +| total_timesteps | 7528448 | +| train/ | | +| approx_kl | 0.0056456923 | +| clip_fraction | 0.3 | +| clip_range | 0.0559 | +| entropy_loss | -7.63 | +| explained_variance | 0.021 | +| learning_rate | 5.1e-05 | +| loss | -0.0278 | +| n_updates | 14700 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000271 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.291 | +| time/ | | +| fps | 1384 | +| iterations | 3677 | +| time_elapsed | 5440 | +| total_timesteps | 7530496 | +| train/ | | +| approx_kl | 0.005302202 | +| clip_fraction | 0.306 | +| clip_range | 0.0559 | +| entropy_loss | -7.53 | +| explained_variance | -0.00482 | +| learning_rate | 5.09e-05 | +| loss | -0.0238 | +| n_updates | 14704 | +| policy_gradient_loss | -0.0144 | +| value_loss | 0.000354 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 1384 | +| iterations | 3678 | +| time_elapsed | 5442 | +| total_timesteps | 7532544 | +| train/ | | +| approx_kl | 0.0068595675 | +| clip_fraction | 0.359 | +| clip_range | 0.0559 | +| entropy_loss | -7.63 | +| explained_variance | -0.294 | +| learning_rate | 5.09e-05 | +| loss | -0.0324 | +| n_updates | 14708 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000124 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 1384 | +| iterations | 3679 | +| time_elapsed | 5443 | +| total_timesteps | 7534592 | +| train/ | | +| approx_kl | 0.007821774 | +| clip_fraction | 0.313 | +| clip_range | 0.0558 | +| entropy_loss | -7.42 | +| explained_variance | -0.0634 | +| learning_rate | 5.09e-05 | +| loss | -0.0246 | +| n_updates | 14712 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000212 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.297 | +| time/ | | +| fps | 1384 | +| iterations | 3680 | +| time_elapsed | 5444 | +| total_timesteps | 7536640 | +| train/ | | +| approx_kl | 0.0077064694 | +| clip_fraction | 0.328 | +| clip_range | 0.0558 | +| entropy_loss | -7.63 | +| explained_variance | -0.0744 | +| learning_rate | 5.08e-05 | +| loss | -0.0244 | +| n_updates | 14716 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000129 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.297 | +| time/ | | +| fps | 1384 | +| iterations | 3681 | +| time_elapsed | 5446 | +| total_timesteps | 7538688 | +| train/ | | +| approx_kl | 0.0064312527 | +| clip_fraction | 0.341 | +| clip_range | 0.0558 | +| entropy_loss | -7.46 | +| explained_variance | -0.123 | +| learning_rate | 5.08e-05 | +| loss | -0.0264 | +| n_updates | 14720 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000129 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 1384 | +| iterations | 3682 | +| time_elapsed | 5447 | +| total_timesteps | 7540736 | +| train/ | | +| approx_kl | 0.006936524 | +| clip_fraction | 0.323 | +| clip_range | 0.0558 | +| entropy_loss | -7.59 | +| explained_variance | -0.0266 | +| learning_rate | 5.07e-05 | +| loss | -0.0259 | +| n_updates | 14724 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000164 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.298 | +| time/ | | +| fps | 1384 | +| iterations | 3683 | +| time_elapsed | 5449 | +| total_timesteps | 7542784 | +| train/ | | +| approx_kl | 0.0064990306 | +| clip_fraction | 0.322 | +| clip_range | 0.0557 | +| entropy_loss | -7.64 | +| explained_variance | 0.0201 | +| learning_rate | 5.07e-05 | +| loss | -0.0254 | +| n_updates | 14728 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000123 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.298 | +| time/ | | +| fps | 1384 | +| iterations | 3684 | +| time_elapsed | 5450 | +| total_timesteps | 7544832 | +| train/ | | +| approx_kl | 0.0069705667 | +| clip_fraction | 0.341 | +| clip_range | 0.0557 | +| entropy_loss | -7.39 | +| explained_variance | -0.0663 | +| learning_rate | 5.07e-05 | +| loss | -0.0261 | +| n_updates | 14732 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.00012 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.298 | +| time/ | | +| fps | 1384 | +| iterations | 3685 | +| time_elapsed | 5452 | +| total_timesteps | 7546880 | +| train/ | | +| approx_kl | 0.00754877 | +| clip_fraction | 0.337 | +| clip_range | 0.0557 | +| entropy_loss | -7.55 | +| explained_variance | 0.0253 | +| learning_rate | 5.06e-05 | +| loss | -0.0285 | +| n_updates | 14736 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000131 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.298 | +| time/ | | +| fps | 1384 | +| iterations | 3686 | +| time_elapsed | 5453 | +| total_timesteps | 7548928 | +| train/ | | +| approx_kl | 0.00679892 | +| clip_fraction | 0.317 | +| clip_range | 0.0557 | +| entropy_loss | -7.59 | +| explained_variance | -0.0322 | +| learning_rate | 5.06e-05 | +| loss | -0.0261 | +| n_updates | 14740 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000192 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 1384 | +| iterations | 3687 | +| time_elapsed | 5454 | +| total_timesteps | 7550976 | +| train/ | | +| approx_kl | 0.0070992545 | +| clip_fraction | 0.313 | +| clip_range | 0.0556 | +| entropy_loss | -7.59 | +| explained_variance | -0.0523 | +| learning_rate | 5.05e-05 | +| loss | -0.0268 | +| n_updates | 14744 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000229 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.298 | +| time/ | | +| fps | 1384 | +| iterations | 3688 | +| time_elapsed | 5456 | +| total_timesteps | 7553024 | +| train/ | | +| approx_kl | 0.0070363376 | +| clip_fraction | 0.314 | +| clip_range | 0.0556 | +| entropy_loss | -7.46 | +| explained_variance | 0.0157 | +| learning_rate | 5.05e-05 | +| loss | -0.0229 | +| n_updates | 14748 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000226 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 1384 | +| iterations | 3689 | +| time_elapsed | 5457 | +| total_timesteps | 7555072 | +| train/ | | +| approx_kl | 0.0064662565 | +| clip_fraction | 0.317 | +| clip_range | 0.0556 | +| entropy_loss | -7.52 | +| explained_variance | -0.0902 | +| learning_rate | 5.05e-05 | +| loss | -0.0252 | +| n_updates | 14752 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000286 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 1384 | +| iterations | 3690 | +| time_elapsed | 5459 | +| total_timesteps | 7557120 | +| train/ | | +| approx_kl | 0.0060662823 | +| clip_fraction | 0.324 | +| clip_range | 0.0556 | +| entropy_loss | -7.44 | +| explained_variance | 0.0836 | +| learning_rate | 5.04e-05 | +| loss | -0.0275 | +| n_updates | 14756 | +| policy_gradient_loss | -0.0148 | +| value_loss | 0.000242 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.294 | +| time/ | | +| fps | 1384 | +| iterations | 3691 | +| time_elapsed | 5460 | +| total_timesteps | 7559168 | +| train/ | | +| approx_kl | 0.0074162316 | +| clip_fraction | 0.323 | +| clip_range | 0.0555 | +| entropy_loss | -7.59 | +| explained_variance | -0.0692 | +| learning_rate | 5.04e-05 | +| loss | -0.0302 | +| n_updates | 14760 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000188 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.3 | +| time/ | | +| fps | 1384 | +| iterations | 3692 | +| time_elapsed | 5462 | +| total_timesteps | 7561216 | +| train/ | | +| approx_kl | 0.0068401364 | +| clip_fraction | 0.336 | +| clip_range | 0.0555 | +| entropy_loss | -7.62 | +| explained_variance | -0.0936 | +| learning_rate | 5.03e-05 | +| loss | -0.0252 | +| n_updates | 14764 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000195 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.298 | +| time/ | | +| fps | 1384 | +| iterations | 3693 | +| time_elapsed | 5463 | +| total_timesteps | 7563264 | +| train/ | | +| approx_kl | 0.006140217 | +| clip_fraction | 0.322 | +| clip_range | 0.0555 | +| entropy_loss | -7.54 | +| explained_variance | -0.00753 | +| learning_rate | 5.03e-05 | +| loss | -0.0315 | +| n_updates | 14768 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000169 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.288 | +| time/ | | +| fps | 1384 | +| iterations | 3694 | +| time_elapsed | 5465 | +| total_timesteps | 7565312 | +| train/ | | +| approx_kl | 0.0066072065 | +| clip_fraction | 0.319 | +| clip_range | 0.0555 | +| entropy_loss | -7.61 | +| explained_variance | 0.0501 | +| learning_rate | 5.02e-05 | +| loss | -0.0291 | +| n_updates | 14772 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000177 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.289 | +| time/ | | +| fps | 1384 | +| iterations | 3695 | +| time_elapsed | 5466 | +| total_timesteps | 7567360 | +| train/ | | +| approx_kl | 0.005818328 | +| clip_fraction | 0.322 | +| clip_range | 0.0554 | +| entropy_loss | -7.48 | +| explained_variance | -0.24 | +| learning_rate | 5.02e-05 | +| loss | -0.0292 | +| n_updates | 14776 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000122 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.289 | +| time/ | | +| fps | 1384 | +| iterations | 3696 | +| time_elapsed | 5467 | +| total_timesteps | 7569408 | +| train/ | | +| approx_kl | 0.0063274065 | +| clip_fraction | 0.295 | +| clip_range | 0.0554 | +| entropy_loss | -7.61 | +| explained_variance | -0.0729 | +| learning_rate | 5.02e-05 | +| loss | -0.0234 | +| n_updates | 14780 | +| policy_gradient_loss | -0.0142 | +| value_loss | 0.000232 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.289 | +| time/ | | +| fps | 1384 | +| iterations | 3697 | +| time_elapsed | 5469 | +| total_timesteps | 7571456 | +| train/ | | +| approx_kl | 0.0067120623 | +| clip_fraction | 0.309 | +| clip_range | 0.0554 | +| entropy_loss | -7.59 | +| explained_variance | -0.14 | +| learning_rate | 5.01e-05 | +| loss | -0.0261 | +| n_updates | 14784 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000129 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.288 | +| time/ | | +| fps | 1384 | +| iterations | 3698 | +| time_elapsed | 5470 | +| total_timesteps | 7573504 | +| train/ | | +| approx_kl | 0.0073135346 | +| clip_fraction | 0.327 | +| clip_range | 0.0554 | +| entropy_loss | -7.69 | +| explained_variance | -0.113 | +| learning_rate | 5.01e-05 | +| loss | -0.0264 | +| n_updates | 14788 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000119 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.292 | +| time/ | | +| fps | 1384 | +| iterations | 3699 | +| time_elapsed | 5472 | +| total_timesteps | 7575552 | +| train/ | | +| approx_kl | 0.006506042 | +| clip_fraction | 0.295 | +| clip_range | 0.0553 | +| entropy_loss | -7.51 | +| explained_variance | 0.00611 | +| learning_rate | 5e-05 | +| loss | -0.0236 | +| n_updates | 14792 | +| policy_gradient_loss | -0.0147 | +| value_loss | 0.000196 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.289 | +| time/ | | +| fps | 1384 | +| iterations | 3700 | +| time_elapsed | 5473 | +| total_timesteps | 7577600 | +| train/ | | +| approx_kl | 0.0071799 | +| clip_fraction | 0.317 | +| clip_range | 0.0553 | +| entropy_loss | -7.62 | +| explained_variance | -0.023 | +| learning_rate | 5e-05 | +| loss | -0.0241 | +| n_updates | 14796 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000285 | +--------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.289 | +| time/ | | +| fps | 1384 | +| iterations | 3701 | +| time_elapsed | 5475 | +| total_timesteps | 7579648 | +| train/ | | +| approx_kl | 0.0063164136 | +| clip_fraction | 0.322 | +| clip_range | 0.0553 | +| entropy_loss | -7.65 | +| explained_variance | 0.0468 | +| learning_rate | 5e-05 | +| loss | -0.0272 | +| n_updates | 14800 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000213 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.306 | +| time/ | | +| fps | 1384 | +| iterations | 3702 | +| time_elapsed | 5476 | +| total_timesteps | 7581696 | +| train/ | | +| approx_kl | 0.0069676964 | +| clip_fraction | 0.34 | +| clip_range | 0.0553 | +| entropy_loss | -7.59 | +| explained_variance | -0.061 | +| learning_rate | 4.99e-05 | +| loss | -0.0279 | +| n_updates | 14804 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.00012 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1384 | +| iterations | 3703 | +| time_elapsed | 5478 | +| total_timesteps | 7583744 | +| train/ | | +| approx_kl | 0.0063749896 | +| clip_fraction | 0.293 | +| clip_range | 0.0552 | +| entropy_loss | -7.3 | +| explained_variance | 0.0537 | +| learning_rate | 4.99e-05 | +| loss | -0.0193 | +| n_updates | 14808 | +| policy_gradient_loss | -0.0131 | +| value_loss | 0.000326 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1384 | +| iterations | 3704 | +| time_elapsed | 5479 | +| total_timesteps | 7585792 | +| train/ | | +| approx_kl | 0.0073636244 | +| clip_fraction | 0.337 | +| clip_range | 0.0552 | +| entropy_loss | -7.47 | +| explained_variance | 0.0878 | +| learning_rate | 4.98e-05 | +| loss | -0.0256 | +| n_updates | 14812 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000204 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1384 | +| iterations | 3705 | +| time_elapsed | 5481 | +| total_timesteps | 7587840 | +| train/ | | +| approx_kl | 0.0075259074 | +| clip_fraction | 0.345 | +| clip_range | 0.0552 | +| entropy_loss | -7.58 | +| explained_variance | -0.0883 | +| learning_rate | 4.98e-05 | +| loss | -0.0262 | +| n_updates | 14816 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000155 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1384 | +| iterations | 3706 | +| time_elapsed | 5482 | +| total_timesteps | 7589888 | +| train/ | | +| approx_kl | 0.0054631545 | +| clip_fraction | 0.334 | +| clip_range | 0.0552 | +| entropy_loss | -7.66 | +| explained_variance | -0.133 | +| learning_rate | 4.98e-05 | +| loss | -0.0267 | +| n_updates | 14820 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000171 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1384 | +| iterations | 3707 | +| time_elapsed | 5483 | +| total_timesteps | 7591936 | +| train/ | | +| approx_kl | 0.007194278 | +| clip_fraction | 0.344 | +| clip_range | 0.0551 | +| entropy_loss | -7.6 | +| explained_variance | -0.0596 | +| learning_rate | 4.97e-05 | +| loss | -0.0268 | +| n_updates | 14824 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000157 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1384 | +| iterations | 3708 | +| time_elapsed | 5485 | +| total_timesteps | 7593984 | +| train/ | | +| approx_kl | 0.0061467444 | +| clip_fraction | 0.323 | +| clip_range | 0.0551 | +| entropy_loss | -7.52 | +| explained_variance | -0.0411 | +| learning_rate | 4.97e-05 | +| loss | -0.0254 | +| n_updates | 14828 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.00023 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1384 | +| iterations | 3709 | +| time_elapsed | 5486 | +| total_timesteps | 7596032 | +| train/ | | +| approx_kl | 0.0066927355 | +| clip_fraction | 0.309 | +| clip_range | 0.0551 | +| entropy_loss | -7.51 | +| explained_variance | 0.0405 | +| learning_rate | 4.96e-05 | +| loss | -0.0193 | +| n_updates | 14832 | +| policy_gradient_loss | -0.0145 | +| value_loss | 0.000241 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1384 | +| iterations | 3710 | +| time_elapsed | 5488 | +| total_timesteps | 7598080 | +| train/ | | +| approx_kl | 0.007058489 | +| clip_fraction | 0.296 | +| clip_range | 0.055 | +| entropy_loss | -7.55 | +| explained_variance | -0.128 | +| learning_rate | 4.96e-05 | +| loss | -0.0193 | +| n_updates | 14836 | +| policy_gradient_loss | -0.0145 | +| value_loss | 0.000246 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1384 | +| iterations | 3711 | +| time_elapsed | 5489 | +| total_timesteps | 7600128 | +| train/ | | +| approx_kl | 0.0073147574 | +| clip_fraction | 0.327 | +| clip_range | 0.055 | +| entropy_loss | -7.33 | +| explained_variance | -0.0389 | +| learning_rate | 4.96e-05 | +| loss | -0.0237 | +| n_updates | 14840 | +| policy_gradient_loss | -0.0145 | +| value_loss | 0.000249 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1384 | +| iterations | 3712 | +| time_elapsed | 5491 | +| total_timesteps | 7602176 | +| train/ | | +| approx_kl | 0.0068436116 | +| clip_fraction | 0.324 | +| clip_range | 0.055 | +| entropy_loss | -7.41 | +| explained_variance | 0.0123 | +| learning_rate | 4.95e-05 | +| loss | -0.0296 | +| n_updates | 14844 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000294 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1384 | +| iterations | 3713 | +| time_elapsed | 5492 | +| total_timesteps | 7604224 | +| train/ | | +| approx_kl | 0.0071864994 | +| clip_fraction | 0.35 | +| clip_range | 0.055 | +| entropy_loss | -7.65 | +| explained_variance | -0.0663 | +| learning_rate | 4.95e-05 | +| loss | -0.0305 | +| n_updates | 14848 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000161 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1384 | +| iterations | 3714 | +| time_elapsed | 5494 | +| total_timesteps | 7606272 | +| train/ | | +| approx_kl | 0.0070599504 | +| clip_fraction | 0.353 | +| clip_range | 0.0549 | +| entropy_loss | -7.62 | +| explained_variance | 0.0448 | +| learning_rate | 4.94e-05 | +| loss | -0.0275 | +| n_updates | 14852 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000232 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1384 | +| iterations | 3715 | +| time_elapsed | 5495 | +| total_timesteps | 7608320 | +| train/ | | +| approx_kl | 0.005628428 | +| clip_fraction | 0.306 | +| clip_range | 0.0549 | +| entropy_loss | -7.72 | +| explained_variance | -0.191 | +| learning_rate | 4.94e-05 | +| loss | -0.0261 | +| n_updates | 14856 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000167 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1384 | +| iterations | 3716 | +| time_elapsed | 5496 | +| total_timesteps | 7610368 | +| train/ | | +| approx_kl | 0.0076521765 | +| clip_fraction | 0.333 | +| clip_range | 0.0549 | +| entropy_loss | -7.69 | +| explained_variance | -0.0518 | +| learning_rate | 4.94e-05 | +| loss | -0.0244 | +| n_updates | 14860 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000185 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1384 | +| iterations | 3717 | +| time_elapsed | 5498 | +| total_timesteps | 7612416 | +| train/ | | +| approx_kl | 0.006700241 | +| clip_fraction | 0.337 | +| clip_range | 0.0549 | +| entropy_loss | -7.46 | +| explained_variance | -0.1 | +| learning_rate | 4.93e-05 | +| loss | -0.0235 | +| n_updates | 14864 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000134 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1384 | +| iterations | 3718 | +| time_elapsed | 5499 | +| total_timesteps | 7614464 | +| train/ | | +| approx_kl | 0.007152604 | +| clip_fraction | 0.35 | +| clip_range | 0.0548 | +| entropy_loss | -7.49 | +| explained_variance | 0.0118 | +| learning_rate | 4.93e-05 | +| loss | -0.0307 | +| n_updates | 14868 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000112 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1384 | +| iterations | 3719 | +| time_elapsed | 5501 | +| total_timesteps | 7616512 | +| train/ | | +| approx_kl | 0.006152371 | +| clip_fraction | 0.314 | +| clip_range | 0.0548 | +| entropy_loss | -7.58 | +| explained_variance | -0.0656 | +| learning_rate | 4.92e-05 | +| loss | -0.0204 | +| n_updates | 14872 | +| policy_gradient_loss | -0.0141 | +| value_loss | 0.000181 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1384 | +| iterations | 3720 | +| time_elapsed | 5502 | +| total_timesteps | 7618560 | +| train/ | | +| approx_kl | 0.006155298 | +| clip_fraction | 0.325 | +| clip_range | 0.0548 | +| entropy_loss | -7.45 | +| explained_variance | -0.124 | +| learning_rate | 4.92e-05 | +| loss | -0.0241 | +| n_updates | 14876 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000103 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1384 | +| iterations | 3721 | +| time_elapsed | 5504 | +| total_timesteps | 7620608 | +| train/ | | +| approx_kl | 0.0073198583 | +| clip_fraction | 0.333 | +| clip_range | 0.0548 | +| entropy_loss | -7.48 | +| explained_variance | -0.0443 | +| learning_rate | 4.92e-05 | +| loss | -0.0228 | +| n_updates | 14880 | +| policy_gradient_loss | -0.0146 | +| value_loss | 0.000154 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1384 | +| iterations | 3722 | +| time_elapsed | 5505 | +| total_timesteps | 7622656 | +| train/ | | +| approx_kl | 0.0056851166 | +| clip_fraction | 0.313 | +| clip_range | 0.0547 | +| entropy_loss | -7.47 | +| explained_variance | -0.0164 | +| learning_rate | 4.91e-05 | +| loss | -0.0249 | +| n_updates | 14884 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000214 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1384 | +| iterations | 3723 | +| time_elapsed | 5507 | +| total_timesteps | 7624704 | +| train/ | | +| approx_kl | 0.0067942347 | +| clip_fraction | 0.317 | +| clip_range | 0.0547 | +| entropy_loss | -7.5 | +| explained_variance | -0.12 | +| learning_rate | 4.91e-05 | +| loss | -0.0237 | +| n_updates | 14888 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000141 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1384 | +| iterations | 3724 | +| time_elapsed | 5508 | +| total_timesteps | 7626752 | +| train/ | | +| approx_kl | 0.0070910407 | +| clip_fraction | 0.32 | +| clip_range | 0.0547 | +| entropy_loss | -7.61 | +| explained_variance | -0.0736 | +| learning_rate | 4.9e-05 | +| loss | -0.0256 | +| n_updates | 14892 | +| policy_gradient_loss | -0.0148 | +| value_loss | 0.000174 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1384 | +| iterations | 3725 | +| time_elapsed | 5510 | +| total_timesteps | 7628800 | +| train/ | | +| approx_kl | 0.006615081 | +| clip_fraction | 0.348 | +| clip_range | 0.0547 | +| entropy_loss | -7.55 | +| explained_variance | -0.225 | +| learning_rate | 4.9e-05 | +| loss | -0.0214 | +| n_updates | 14896 | +| policy_gradient_loss | -0.0161 | +| value_loss | 6.28e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1384 | +| iterations | 3726 | +| time_elapsed | 5511 | +| total_timesteps | 7630848 | +| train/ | | +| approx_kl | 0.0074830586 | +| clip_fraction | 0.332 | +| clip_range | 0.0546 | +| entropy_loss | -7.48 | +| explained_variance | 0.0595 | +| learning_rate | 4.89e-05 | +| loss | -0.0211 | +| n_updates | 14900 | +| policy_gradient_loss | -0.0147 | +| value_loss | 0.000237 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1384 | +| iterations | 3727 | +| time_elapsed | 5512 | +| total_timesteps | 7632896 | +| train/ | | +| approx_kl | 0.007097273 | +| clip_fraction | 0.324 | +| clip_range | 0.0546 | +| entropy_loss | -7.42 | +| explained_variance | -0.0114 | +| learning_rate | 4.89e-05 | +| loss | -0.0279 | +| n_updates | 14904 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000244 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1384 | +| iterations | 3728 | +| time_elapsed | 5514 | +| total_timesteps | 7634944 | +| train/ | | +| approx_kl | 0.006576707 | +| clip_fraction | 0.333 | +| clip_range | 0.0546 | +| entropy_loss | -7.56 | +| explained_variance | 0.0707 | +| learning_rate | 4.89e-05 | +| loss | -0.0256 | +| n_updates | 14908 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000154 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1384 | +| iterations | 3729 | +| time_elapsed | 5515 | +| total_timesteps | 7636992 | +| train/ | | +| approx_kl | 0.0075031416 | +| clip_fraction | 0.342 | +| clip_range | 0.0546 | +| entropy_loss | -7.44 | +| explained_variance | -0.0407 | +| learning_rate | 4.88e-05 | +| loss | -0.0311 | +| n_updates | 14912 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000133 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1384 | +| iterations | 3730 | +| time_elapsed | 5517 | +| total_timesteps | 7639040 | +| train/ | | +| approx_kl | 0.0072198524 | +| clip_fraction | 0.345 | +| clip_range | 0.0545 | +| entropy_loss | -7.55 | +| explained_variance | 0.138 | +| learning_rate | 4.88e-05 | +| loss | -0.0261 | +| n_updates | 14916 | +| policy_gradient_loss | -0.017 | +| value_loss | 7.38e-05 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1384 | +| iterations | 3731 | +| time_elapsed | 5518 | +| total_timesteps | 7641088 | +| train/ | | +| approx_kl | 0.0073077222 | +| clip_fraction | 0.324 | +| clip_range | 0.0545 | +| entropy_loss | -7.61 | +| explained_variance | 0.00404 | +| learning_rate | 4.87e-05 | +| loss | -0.0259 | +| n_updates | 14920 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000221 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1384 | +| iterations | 3732 | +| time_elapsed | 5520 | +| total_timesteps | 7643136 | +| train/ | | +| approx_kl | 0.005935127 | +| clip_fraction | 0.314 | +| clip_range | 0.0545 | +| entropy_loss | -7.49 | +| explained_variance | 0.0265 | +| learning_rate | 4.87e-05 | +| loss | -0.0225 | +| n_updates | 14924 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000194 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1384 | +| iterations | 3733 | +| time_elapsed | 5521 | +| total_timesteps | 7645184 | +| train/ | | +| approx_kl | 0.007189815 | +| clip_fraction | 0.318 | +| clip_range | 0.0545 | +| entropy_loss | -7.63 | +| explained_variance | -0.105 | +| learning_rate | 4.87e-05 | +| loss | -0.0207 | +| n_updates | 14928 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000152 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1384 | +| iterations | 3734 | +| time_elapsed | 5523 | +| total_timesteps | 7647232 | +| train/ | | +| approx_kl | 0.0065575885 | +| clip_fraction | 0.312 | +| clip_range | 0.0544 | +| entropy_loss | -7.44 | +| explained_variance | -0.0365 | +| learning_rate | 4.86e-05 | +| loss | -0.0222 | +| n_updates | 14932 | +| policy_gradient_loss | -0.0142 | +| value_loss | 0.000212 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1384 | +| iterations | 3735 | +| time_elapsed | 5524 | +| total_timesteps | 7649280 | +| train/ | | +| approx_kl | 0.006805989 | +| clip_fraction | 0.32 | +| clip_range | 0.0544 | +| entropy_loss | -7.5 | +| explained_variance | 0.0794 | +| learning_rate | 4.86e-05 | +| loss | -0.0271 | +| n_updates | 14936 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000166 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1384 | +| iterations | 3736 | +| time_elapsed | 5526 | +| total_timesteps | 7651328 | +| train/ | | +| approx_kl | 0.007839173 | +| clip_fraction | 0.308 | +| clip_range | 0.0544 | +| entropy_loss | -7.41 | +| explained_variance | -0.0361 | +| learning_rate | 4.85e-05 | +| loss | -0.022 | +| n_updates | 14940 | +| policy_gradient_loss | -0.0135 | +| value_loss | 0.000344 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1384 | +| iterations | 3737 | +| time_elapsed | 5527 | +| total_timesteps | 7653376 | +| train/ | | +| approx_kl | 0.007215864 | +| clip_fraction | 0.323 | +| clip_range | 0.0544 | +| entropy_loss | -7.56 | +| explained_variance | -0.169 | +| learning_rate | 4.85e-05 | +| loss | -0.0259 | +| n_updates | 14944 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000204 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1384 | +| iterations | 3738 | +| time_elapsed | 5529 | +| total_timesteps | 7655424 | +| train/ | | +| approx_kl | 0.006732225 | +| clip_fraction | 0.325 | +| clip_range | 0.0543 | +| entropy_loss | -7.52 | +| explained_variance | 0.0217 | +| learning_rate | 4.85e-05 | +| loss | -0.0251 | +| n_updates | 14948 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000274 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1384 | +| iterations | 3739 | +| time_elapsed | 5530 | +| total_timesteps | 7657472 | +| train/ | | +| approx_kl | 0.0049828673 | +| clip_fraction | 0.303 | +| clip_range | 0.0543 | +| entropy_loss | -7.7 | +| explained_variance | -0.129 | +| learning_rate | 4.84e-05 | +| loss | -0.025 | +| n_updates | 14952 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000149 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1384 | +| iterations | 3740 | +| time_elapsed | 5531 | +| total_timesteps | 7659520 | +| train/ | | +| approx_kl | 0.005663017 | +| clip_fraction | 0.303 | +| clip_range | 0.0543 | +| entropy_loss | -7.61 | +| explained_variance | -0.0254 | +| learning_rate | 4.84e-05 | +| loss | -0.0196 | +| n_updates | 14956 | +| policy_gradient_loss | -0.0124 | +| value_loss | 0.000366 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1384 | +| iterations | 3741 | +| time_elapsed | 5533 | +| total_timesteps | 7661568 | +| train/ | | +| approx_kl | 0.006151788 | +| clip_fraction | 0.302 | +| clip_range | 0.0543 | +| entropy_loss | -7.52 | +| explained_variance | -0.204 | +| learning_rate | 4.83e-05 | +| loss | -0.0247 | +| n_updates | 14960 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000117 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1384 | +| iterations | 3742 | +| time_elapsed | 5534 | +| total_timesteps | 7663616 | +| train/ | | +| approx_kl | 0.0064248303 | +| clip_fraction | 0.32 | +| clip_range | 0.0542 | +| entropy_loss | -7.54 | +| explained_variance | -0.0964 | +| learning_rate | 4.83e-05 | +| loss | -0.0236 | +| n_updates | 14964 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000218 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1384 | +| iterations | 3743 | +| time_elapsed | 5536 | +| total_timesteps | 7665664 | +| train/ | | +| approx_kl | 0.0059520435 | +| clip_fraction | 0.326 | +| clip_range | 0.0542 | +| entropy_loss | -7.67 | +| explained_variance | -0.135 | +| learning_rate | 4.83e-05 | +| loss | -0.0297 | +| n_updates | 14968 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000122 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1384 | +| iterations | 3744 | +| time_elapsed | 5537 | +| total_timesteps | 7667712 | +| train/ | | +| approx_kl | 0.006721139 | +| clip_fraction | 0.316 | +| clip_range | 0.0542 | +| entropy_loss | -7.6 | +| explained_variance | -0.0513 | +| learning_rate | 4.82e-05 | +| loss | -0.0214 | +| n_updates | 14972 | +| policy_gradient_loss | -0.0142 | +| value_loss | 0.000147 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1384 | +| iterations | 3745 | +| time_elapsed | 5539 | +| total_timesteps | 7669760 | +| train/ | | +| approx_kl | 0.0064707818 | +| clip_fraction | 0.312 | +| clip_range | 0.0542 | +| entropy_loss | -7.53 | +| explained_variance | -0.0116 | +| learning_rate | 4.82e-05 | +| loss | -0.0249 | +| n_updates | 14976 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.000264 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1384 | +| iterations | 3746 | +| time_elapsed | 5540 | +| total_timesteps | 7671808 | +| train/ | | +| approx_kl | 0.00576982 | +| clip_fraction | 0.304 | +| clip_range | 0.0541 | +| entropy_loss | -7.44 | +| explained_variance | 0.061 | +| learning_rate | 4.81e-05 | +| loss | -0.0219 | +| n_updates | 14980 | +| policy_gradient_loss | -0.0148 | +| value_loss | 0.000206 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1384 | +| iterations | 3747 | +| time_elapsed | 5542 | +| total_timesteps | 7673856 | +| train/ | | +| approx_kl | 0.0064052353 | +| clip_fraction | 0.334 | +| clip_range | 0.0541 | +| entropy_loss | -7.51 | +| explained_variance | -0.0763 | +| learning_rate | 4.81e-05 | +| loss | -0.0264 | +| n_updates | 14984 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000131 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1384 | +| iterations | 3748 | +| time_elapsed | 5543 | +| total_timesteps | 7675904 | +| train/ | | +| approx_kl | 0.0073562884 | +| clip_fraction | 0.334 | +| clip_range | 0.0541 | +| entropy_loss | -7.65 | +| explained_variance | -0.122 | +| learning_rate | 4.81e-05 | +| loss | -0.0263 | +| n_updates | 14988 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000179 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1384 | +| iterations | 3749 | +| time_elapsed | 5545 | +| total_timesteps | 7677952 | +| train/ | | +| approx_kl | 0.0075562997 | +| clip_fraction | 0.328 | +| clip_range | 0.0541 | +| entropy_loss | -7.61 | +| explained_variance | -0.231 | +| learning_rate | 4.8e-05 | +| loss | -0.0273 | +| n_updates | 14992 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000107 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1384 | +| iterations | 3750 | +| time_elapsed | 5546 | +| total_timesteps | 7680000 | +| train/ | | +| approx_kl | 0.0066430364 | +| clip_fraction | 0.307 | +| clip_range | 0.054 | +| entropy_loss | -7.59 | +| explained_variance | -0.0245 | +| learning_rate | 4.8e-05 | +| loss | -0.0222 | +| n_updates | 14996 | +| policy_gradient_loss | -0.0143 | +| value_loss | 0.000168 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1384 | +| iterations | 3751 | +| time_elapsed | 5548 | +| total_timesteps | 7682048 | +| train/ | | +| approx_kl | 0.0058235545 | +| clip_fraction | 0.305 | +| clip_range | 0.054 | +| entropy_loss | -7.5 | +| explained_variance | -0.08 | +| learning_rate | 4.79e-05 | +| loss | -0.0253 | +| n_updates | 15000 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000126 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1384 | +| iterations | 3752 | +| time_elapsed | 5549 | +| total_timesteps | 7684096 | +| train/ | | +| approx_kl | 0.00663188 | +| clip_fraction | 0.318 | +| clip_range | 0.054 | +| entropy_loss | -7.22 | +| explained_variance | -0.0536 | +| learning_rate | 4.79e-05 | +| loss | -0.0195 | +| n_updates | 15004 | +| policy_gradient_loss | -0.0147 | +| value_loss | 0.000161 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1384 | +| iterations | 3753 | +| time_elapsed | 5551 | +| total_timesteps | 7686144 | +| train/ | | +| approx_kl | 0.0057578576 | +| clip_fraction | 0.285 | +| clip_range | 0.0539 | +| entropy_loss | -7.55 | +| explained_variance | -0.00571 | +| learning_rate | 4.79e-05 | +| loss | -0.0199 | +| n_updates | 15008 | +| policy_gradient_loss | -0.0143 | +| value_loss | 0.000188 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1384 | +| iterations | 3754 | +| time_elapsed | 5552 | +| total_timesteps | 7688192 | +| train/ | | +| approx_kl | 0.007821705 | +| clip_fraction | 0.313 | +| clip_range | 0.0539 | +| entropy_loss | -7.61 | +| explained_variance | -0.083 | +| learning_rate | 4.78e-05 | +| loss | -0.022 | +| n_updates | 15012 | +| policy_gradient_loss | -0.0142 | +| value_loss | 0.000252 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1384 | +| iterations | 3755 | +| time_elapsed | 5553 | +| total_timesteps | 7690240 | +| train/ | | +| approx_kl | 0.007443806 | +| clip_fraction | 0.353 | +| clip_range | 0.0539 | +| entropy_loss | -7.5 | +| explained_variance | -0.369 | +| learning_rate | 4.78e-05 | +| loss | -0.0317 | +| n_updates | 15016 | +| policy_gradient_loss | -0.0181 | +| value_loss | 7.83e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1384 | +| iterations | 3756 | +| time_elapsed | 5555 | +| total_timesteps | 7692288 | +| train/ | | +| approx_kl | 0.005707582 | +| clip_fraction | 0.315 | +| clip_range | 0.0539 | +| entropy_loss | -7.62 | +| explained_variance | -0.132 | +| learning_rate | 4.77e-05 | +| loss | -0.0193 | +| n_updates | 15020 | +| policy_gradient_loss | -0.0129 | +| value_loss | 0.000143 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1384 | +| iterations | 3757 | +| time_elapsed | 5556 | +| total_timesteps | 7694336 | +| train/ | | +| approx_kl | 0.0059725763 | +| clip_fraction | 0.302 | +| clip_range | 0.0538 | +| entropy_loss | -7.67 | +| explained_variance | -0.0914 | +| learning_rate | 4.77e-05 | +| loss | -0.0251 | +| n_updates | 15024 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000221 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.315 | +| time/ | | +| fps | 1384 | +| iterations | 3758 | +| time_elapsed | 5558 | +| total_timesteps | 7696384 | +| train/ | | +| approx_kl | 0.006138634 | +| clip_fraction | 0.336 | +| clip_range | 0.0538 | +| entropy_loss | -7.52 | +| explained_variance | -0.0809 | +| learning_rate | 4.77e-05 | +| loss | -0.026 | +| n_updates | 15028 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000159 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1384 | +| iterations | 3759 | +| time_elapsed | 5559 | +| total_timesteps | 7698432 | +| train/ | | +| approx_kl | 0.006002425 | +| clip_fraction | 0.312 | +| clip_range | 0.0538 | +| entropy_loss | -7.62 | +| explained_variance | -0.0372 | +| learning_rate | 4.76e-05 | +| loss | -0.0199 | +| n_updates | 15032 | +| policy_gradient_loss | -0.0141 | +| value_loss | 0.000133 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1384 | +| iterations | 3760 | +| time_elapsed | 5561 | +| total_timesteps | 7700480 | +| train/ | | +| approx_kl | 0.005520328 | +| clip_fraction | 0.314 | +| clip_range | 0.0538 | +| entropy_loss | -7.37 | +| explained_variance | -0.052 | +| learning_rate | 4.76e-05 | +| loss | -0.0198 | +| n_updates | 15036 | +| policy_gradient_loss | -0.0137 | +| value_loss | 0.000386 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1384 | +| iterations | 3761 | +| time_elapsed | 5562 | +| total_timesteps | 7702528 | +| train/ | | +| approx_kl | 0.0067098597 | +| clip_fraction | 0.329 | +| clip_range | 0.0537 | +| entropy_loss | -7.53 | +| explained_variance | -0.134 | +| learning_rate | 4.75e-05 | +| loss | -0.0288 | +| n_updates | 15040 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000118 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1384 | +| iterations | 3762 | +| time_elapsed | 5564 | +| total_timesteps | 7704576 | +| train/ | | +| approx_kl | 0.005775107 | +| clip_fraction | 0.288 | +| clip_range | 0.0537 | +| entropy_loss | -7.52 | +| explained_variance | -0.0161 | +| learning_rate | 4.75e-05 | +| loss | -0.025 | +| n_updates | 15044 | +| policy_gradient_loss | -0.0146 | +| value_loss | 0.000179 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1384 | +| iterations | 3763 | +| time_elapsed | 5565 | +| total_timesteps | 7706624 | +| train/ | | +| approx_kl | 0.0060805157 | +| clip_fraction | 0.331 | +| clip_range | 0.0537 | +| entropy_loss | -7.65 | +| explained_variance | -0.0744 | +| learning_rate | 4.74e-05 | +| loss | -0.023 | +| n_updates | 15048 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000235 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1384 | +| iterations | 3764 | +| time_elapsed | 5567 | +| total_timesteps | 7708672 | +| train/ | | +| approx_kl | 0.006391732 | +| clip_fraction | 0.318 | +| clip_range | 0.0537 | +| entropy_loss | -7.63 | +| explained_variance | -0.0664 | +| learning_rate | 4.74e-05 | +| loss | -0.0233 | +| n_updates | 15052 | +| policy_gradient_loss | -0.0147 | +| value_loss | 0.000174 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.315 | +| time/ | | +| fps | 1384 | +| iterations | 3765 | +| time_elapsed | 5568 | +| total_timesteps | 7710720 | +| train/ | | +| approx_kl | 0.0064358255 | +| clip_fraction | 0.311 | +| clip_range | 0.0536 | +| entropy_loss | -7.54 | +| explained_variance | -0.039 | +| learning_rate | 4.74e-05 | +| loss | -0.0243 | +| n_updates | 15056 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.000189 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1384 | +| iterations | 3766 | +| time_elapsed | 5569 | +| total_timesteps | 7712768 | +| train/ | | +| approx_kl | 0.0068113264 | +| clip_fraction | 0.313 | +| clip_range | 0.0536 | +| entropy_loss | -7.45 | +| explained_variance | 0.0385 | +| learning_rate | 4.73e-05 | +| loss | -0.023 | +| n_updates | 15060 | +| policy_gradient_loss | -0.0143 | +| value_loss | 0.000268 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1384 | +| iterations | 3767 | +| time_elapsed | 5571 | +| total_timesteps | 7714816 | +| train/ | | +| approx_kl | 0.006175015 | +| clip_fraction | 0.36 | +| clip_range | 0.0536 | +| entropy_loss | -7.48 | +| explained_variance | -0.283 | +| learning_rate | 4.73e-05 | +| loss | -0.0271 | +| n_updates | 15064 | +| policy_gradient_loss | -0.018 | +| value_loss | 9.33e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1384 | +| iterations | 3768 | +| time_elapsed | 5573 | +| total_timesteps | 7716864 | +| train/ | | +| approx_kl | 0.0069527896 | +| clip_fraction | 0.322 | +| clip_range | 0.0536 | +| entropy_loss | -7.56 | +| explained_variance | -0.00609 | +| learning_rate | 4.72e-05 | +| loss | -0.0261 | +| n_updates | 15068 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000167 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1384 | +| iterations | 3769 | +| time_elapsed | 5574 | +| total_timesteps | 7718912 | +| train/ | | +| approx_kl | 0.007017555 | +| clip_fraction | 0.327 | +| clip_range | 0.0535 | +| entropy_loss | -7.63 | +| explained_variance | -0.0525 | +| learning_rate | 4.72e-05 | +| loss | -0.0242 | +| n_updates | 15072 | +| policy_gradient_loss | -0.016 | +| value_loss | 9.15e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 1384 | +| iterations | 3770 | +| time_elapsed | 5575 | +| total_timesteps | 7720960 | +| train/ | | +| approx_kl | 0.0067920713 | +| clip_fraction | 0.316 | +| clip_range | 0.0535 | +| entropy_loss | -7.69 | +| explained_variance | -0.0594 | +| learning_rate | 4.72e-05 | +| loss | -0.0263 | +| n_updates | 15076 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000173 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 1384 | +| iterations | 3771 | +| time_elapsed | 5577 | +| total_timesteps | 7723008 | +| train/ | | +| approx_kl | 0.006579471 | +| clip_fraction | 0.323 | +| clip_range | 0.0535 | +| entropy_loss | -7.47 | +| explained_variance | -0.0353 | +| learning_rate | 4.71e-05 | +| loss | -0.0259 | +| n_updates | 15080 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000167 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.302 | +| time/ | | +| fps | 1384 | +| iterations | 3772 | +| time_elapsed | 5578 | +| total_timesteps | 7725056 | +| train/ | | +| approx_kl | 0.005428734 | +| clip_fraction | 0.305 | +| clip_range | 0.0535 | +| entropy_loss | -7.73 | +| explained_variance | -0.0611 | +| learning_rate | 4.71e-05 | +| loss | -0.0302 | +| n_updates | 15084 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000105 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.302 | +| time/ | | +| fps | 1384 | +| iterations | 3773 | +| time_elapsed | 5580 | +| total_timesteps | 7727104 | +| train/ | | +| approx_kl | 0.005325917 | +| clip_fraction | 0.328 | +| clip_range | 0.0534 | +| entropy_loss | -7.65 | +| explained_variance | -0.048 | +| learning_rate | 4.7e-05 | +| loss | -0.0234 | +| n_updates | 15088 | +| policy_gradient_loss | -0.0141 | +| value_loss | 0.000222 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 1384 | +| iterations | 3774 | +| time_elapsed | 5581 | +| total_timesteps | 7729152 | +| train/ | | +| approx_kl | 0.005304815 | +| clip_fraction | 0.312 | +| clip_range | 0.0534 | +| entropy_loss | -7.32 | +| explained_variance | 0.0247 | +| learning_rate | 4.7e-05 | +| loss | -0.0243 | +| n_updates | 15092 | +| policy_gradient_loss | -0.0147 | +| value_loss | 0.00021 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 1384 | +| iterations | 3775 | +| time_elapsed | 5583 | +| total_timesteps | 7731200 | +| train/ | | +| approx_kl | 0.0064839004 | +| clip_fraction | 0.344 | +| clip_range | 0.0534 | +| entropy_loss | -7.42 | +| explained_variance | -0.119 | +| learning_rate | 4.7e-05 | +| loss | -0.0227 | +| n_updates | 15096 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000108 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.298 | +| time/ | | +| fps | 1384 | +| iterations | 3776 | +| time_elapsed | 5584 | +| total_timesteps | 7733248 | +| train/ | | +| approx_kl | 0.006726697 | +| clip_fraction | 0.322 | +| clip_range | 0.0534 | +| entropy_loss | -7.72 | +| explained_variance | -0.227 | +| learning_rate | 4.69e-05 | +| loss | -0.027 | +| n_updates | 15100 | +| policy_gradient_loss | -0.0161 | +| value_loss | 8.87e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 1384 | +| iterations | 3777 | +| time_elapsed | 5586 | +| total_timesteps | 7735296 | +| train/ | | +| approx_kl | 0.0060700355 | +| clip_fraction | 0.301 | +| clip_range | 0.0533 | +| entropy_loss | -7.54 | +| explained_variance | -0.0638 | +| learning_rate | 4.69e-05 | +| loss | -0.0215 | +| n_updates | 15104 | +| policy_gradient_loss | -0.0139 | +| value_loss | 0.00017 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 1384 | +| iterations | 3778 | +| time_elapsed | 5587 | +| total_timesteps | 7737344 | +| train/ | | +| approx_kl | 0.0065705236 | +| clip_fraction | 0.294 | +| clip_range | 0.0533 | +| entropy_loss | -7.64 | +| explained_variance | -0.125 | +| learning_rate | 4.68e-05 | +| loss | -0.0226 | +| n_updates | 15108 | +| policy_gradient_loss | -0.0147 | +| value_loss | 0.000124 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.287 | +| time/ | | +| fps | 1384 | +| iterations | 3779 | +| time_elapsed | 5588 | +| total_timesteps | 7739392 | +| train/ | | +| approx_kl | 0.0064944695 | +| clip_fraction | 0.312 | +| clip_range | 0.0533 | +| entropy_loss | -7.51 | +| explained_variance | -0.0665 | +| learning_rate | 4.68e-05 | +| loss | -0.0224 | +| n_updates | 15112 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000182 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.283 | +| time/ | | +| fps | 1384 | +| iterations | 3780 | +| time_elapsed | 5590 | +| total_timesteps | 7741440 | +| train/ | | +| approx_kl | 0.006570287 | +| clip_fraction | 0.307 | +| clip_range | 0.0533 | +| entropy_loss | -7.54 | +| explained_variance | -0.198 | +| learning_rate | 4.68e-05 | +| loss | -0.0257 | +| n_updates | 15116 | +| policy_gradient_loss | -0.0144 | +| value_loss | 0.00011 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.283 | +| time/ | | +| fps | 1384 | +| iterations | 3781 | +| time_elapsed | 5591 | +| total_timesteps | 7743488 | +| train/ | | +| approx_kl | 0.006657128 | +| clip_fraction | 0.319 | +| clip_range | 0.0532 | +| entropy_loss | -7.51 | +| explained_variance | -0.122 | +| learning_rate | 4.67e-05 | +| loss | -0.0223 | +| n_updates | 15120 | +| policy_gradient_loss | -0.0143 | +| value_loss | 0.000116 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.283 | +| time/ | | +| fps | 1384 | +| iterations | 3782 | +| time_elapsed | 5593 | +| total_timesteps | 7745536 | +| train/ | | +| approx_kl | 0.0068303137 | +| clip_fraction | 0.335 | +| clip_range | 0.0532 | +| entropy_loss | -7.6 | +| explained_variance | 0.00381 | +| learning_rate | 4.67e-05 | +| loss | -0.0271 | +| n_updates | 15124 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000219 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.287 | +| time/ | | +| fps | 1384 | +| iterations | 3783 | +| time_elapsed | 5594 | +| total_timesteps | 7747584 | +| train/ | | +| approx_kl | 0.005720648 | +| clip_fraction | 0.315 | +| clip_range | 0.0532 | +| entropy_loss | -7.73 | +| explained_variance | -0.0269 | +| learning_rate | 4.66e-05 | +| loss | -0.0224 | +| n_updates | 15128 | +| policy_gradient_loss | -0.0144 | +| value_loss | 0.000199 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.287 | +| time/ | | +| fps | 1384 | +| iterations | 3784 | +| time_elapsed | 5596 | +| total_timesteps | 7749632 | +| train/ | | +| approx_kl | 0.00581195 | +| clip_fraction | 0.311 | +| clip_range | 0.0532 | +| entropy_loss | -7.62 | +| explained_variance | -0.0292 | +| learning_rate | 4.66e-05 | +| loss | -0.0251 | +| n_updates | 15132 | +| policy_gradient_loss | -0.0147 | +| value_loss | 0.000192 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.29 | +| time/ | | +| fps | 1384 | +| iterations | 3785 | +| time_elapsed | 5597 | +| total_timesteps | 7751680 | +| train/ | | +| approx_kl | 0.0069007576 | +| clip_fraction | 0.3 | +| clip_range | 0.0531 | +| entropy_loss | -7.55 | +| explained_variance | -0.126 | +| learning_rate | 4.66e-05 | +| loss | -0.0264 | +| n_updates | 15136 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.000175 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.288 | +| time/ | | +| fps | 1384 | +| iterations | 3786 | +| time_elapsed | 5598 | +| total_timesteps | 7753728 | +| train/ | | +| approx_kl | 0.005746904 | +| clip_fraction | 0.309 | +| clip_range | 0.0531 | +| entropy_loss | -7.65 | +| explained_variance | -0.00845 | +| learning_rate | 4.65e-05 | +| loss | -0.0249 | +| n_updates | 15140 | +| policy_gradient_loss | -0.0148 | +| value_loss | 0.0002 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.286 | +| time/ | | +| fps | 1384 | +| iterations | 3787 | +| time_elapsed | 5600 | +| total_timesteps | 7755776 | +| train/ | | +| approx_kl | 0.0053470396 | +| clip_fraction | 0.295 | +| clip_range | 0.0531 | +| entropy_loss | -7.51 | +| explained_variance | -0.0555 | +| learning_rate | 4.65e-05 | +| loss | -0.0228 | +| n_updates | 15144 | +| policy_gradient_loss | -0.0141 | +| value_loss | 0.000282 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 1384 | +| iterations | 3788 | +| time_elapsed | 5601 | +| total_timesteps | 7757824 | +| train/ | | +| approx_kl | 0.006292114 | +| clip_fraction | 0.332 | +| clip_range | 0.0531 | +| entropy_loss | -7.53 | +| explained_variance | -0.0396 | +| learning_rate | 4.64e-05 | +| loss | -0.0256 | +| n_updates | 15148 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000158 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.287 | +| time/ | | +| fps | 1384 | +| iterations | 3789 | +| time_elapsed | 5603 | +| total_timesteps | 7759872 | +| train/ | | +| approx_kl | 0.004892368 | +| clip_fraction | 0.281 | +| clip_range | 0.053 | +| entropy_loss | -7.67 | +| explained_variance | -0.0549 | +| learning_rate | 4.64e-05 | +| loss | -0.0232 | +| n_updates | 15152 | +| policy_gradient_loss | -0.0125 | +| value_loss | 0.000173 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.286 | +| time/ | | +| fps | 1384 | +| iterations | 3790 | +| time_elapsed | 5604 | +| total_timesteps | 7761920 | +| train/ | | +| approx_kl | 0.006537943 | +| clip_fraction | 0.292 | +| clip_range | 0.053 | +| entropy_loss | -7.48 | +| explained_variance | -0.0176 | +| learning_rate | 4.64e-05 | +| loss | -0.0225 | +| n_updates | 15156 | +| policy_gradient_loss | -0.0135 | +| value_loss | 0.000226 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.286 | +| time/ | | +| fps | 1384 | +| iterations | 3791 | +| time_elapsed | 5606 | +| total_timesteps | 7763968 | +| train/ | | +| approx_kl | 0.0068049217 | +| clip_fraction | 0.367 | +| clip_range | 0.053 | +| entropy_loss | -7.48 | +| explained_variance | 0.0438 | +| learning_rate | 4.63e-05 | +| loss | -0.0285 | +| n_updates | 15160 | +| policy_gradient_loss | -0.0184 | +| value_loss | 6.34e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.295 | +| time/ | | +| fps | 1384 | +| iterations | 3792 | +| time_elapsed | 5607 | +| total_timesteps | 7766016 | +| train/ | | +| approx_kl | 0.006315194 | +| clip_fraction | 0.323 | +| clip_range | 0.053 | +| entropy_loss | -7.67 | +| explained_variance | -0.046 | +| learning_rate | 4.63e-05 | +| loss | -0.0214 | +| n_updates | 15164 | +| policy_gradient_loss | -0.0136 | +| value_loss | 0.000204 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.292 | +| time/ | | +| fps | 1384 | +| iterations | 3793 | +| time_elapsed | 5609 | +| total_timesteps | 7768064 | +| train/ | | +| approx_kl | 0.006597564 | +| clip_fraction | 0.317 | +| clip_range | 0.0529 | +| entropy_loss | -7.59 | +| explained_variance | 0.0788 | +| learning_rate | 4.62e-05 | +| loss | -0.0227 | +| n_updates | 15168 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000195 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.292 | +| time/ | | +| fps | 1384 | +| iterations | 3794 | +| time_elapsed | 5610 | +| total_timesteps | 7770112 | +| train/ | | +| approx_kl | 0.0057807043 | +| clip_fraction | 0.306 | +| clip_range | 0.0529 | +| entropy_loss | -7.55 | +| explained_variance | 0.0176 | +| learning_rate | 4.62e-05 | +| loss | -0.0222 | +| n_updates | 15172 | +| policy_gradient_loss | -0.0131 | +| value_loss | 0.000164 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 1384 | +| iterations | 3795 | +| time_elapsed | 5611 | +| total_timesteps | 7772160 | +| train/ | | +| approx_kl | 0.0065731644 | +| clip_fraction | 0.333 | +| clip_range | 0.0529 | +| entropy_loss | -7.62 | +| explained_variance | -0.143 | +| learning_rate | 4.62e-05 | +| loss | -0.0238 | +| n_updates | 15176 | +| policy_gradient_loss | -0.0148 | +| value_loss | 0.000171 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.304 | +| time/ | | +| fps | 1384 | +| iterations | 3796 | +| time_elapsed | 5613 | +| total_timesteps | 7774208 | +| train/ | | +| approx_kl | 0.006688989 | +| clip_fraction | 0.312 | +| clip_range | 0.0528 | +| entropy_loss | -7.59 | +| explained_variance | 0.00793 | +| learning_rate | 4.61e-05 | +| loss | -0.02 | +| n_updates | 15180 | +| policy_gradient_loss | -0.0137 | +| value_loss | 0.00038 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 1384 | +| iterations | 3797 | +| time_elapsed | 5614 | +| total_timesteps | 7776256 | +| train/ | | +| approx_kl | 0.005377657 | +| clip_fraction | 0.311 | +| clip_range | 0.0528 | +| entropy_loss | -7.54 | +| explained_variance | -0.159 | +| learning_rate | 4.61e-05 | +| loss | -0.0205 | +| n_updates | 15184 | +| policy_gradient_loss | -0.0143 | +| value_loss | 0.000226 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1384 | +| iterations | 3798 | +| time_elapsed | 5616 | +| total_timesteps | 7778304 | +| train/ | | +| approx_kl | 0.00623725 | +| clip_fraction | 0.311 | +| clip_range | 0.0528 | +| entropy_loss | -7.55 | +| explained_variance | -0.174 | +| learning_rate | 4.6e-05 | +| loss | -0.0272 | +| n_updates | 15188 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000216 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1384 | +| iterations | 3799 | +| time_elapsed | 5617 | +| total_timesteps | 7780352 | +| train/ | | +| approx_kl | 0.0053065326 | +| clip_fraction | 0.309 | +| clip_range | 0.0528 | +| entropy_loss | -7.46 | +| explained_variance | 0.0171 | +| learning_rate | 4.6e-05 | +| loss | -0.026 | +| n_updates | 15192 | +| policy_gradient_loss | -0.0131 | +| value_loss | 0.00033 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1384 | +| iterations | 3800 | +| time_elapsed | 5619 | +| total_timesteps | 7782400 | +| train/ | | +| approx_kl | 0.006878004 | +| clip_fraction | 0.305 | +| clip_range | 0.0527 | +| entropy_loss | -7.51 | +| explained_variance | -0.0765 | +| learning_rate | 4.59e-05 | +| loss | -0.025 | +| n_updates | 15196 | +| policy_gradient_loss | -0.0147 | +| value_loss | 0.000198 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1384 | +| iterations | 3801 | +| time_elapsed | 5620 | +| total_timesteps | 7784448 | +| train/ | | +| approx_kl | 0.0065648993 | +| clip_fraction | 0.33 | +| clip_range | 0.0527 | +| entropy_loss | -7.63 | +| explained_variance | -0.0402 | +| learning_rate | 4.59e-05 | +| loss | -0.0244 | +| n_updates | 15200 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000136 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1384 | +| iterations | 3802 | +| time_elapsed | 5622 | +| total_timesteps | 7786496 | +| train/ | | +| approx_kl | 0.005694189 | +| clip_fraction | 0.323 | +| clip_range | 0.0527 | +| entropy_loss | -7.61 | +| explained_variance | -0.0909 | +| learning_rate | 4.59e-05 | +| loss | -0.0218 | +| n_updates | 15204 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000164 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1384 | +| iterations | 3803 | +| time_elapsed | 5623 | +| total_timesteps | 7788544 | +| train/ | | +| approx_kl | 0.0054702708 | +| clip_fraction | 0.301 | +| clip_range | 0.0527 | +| entropy_loss | -7.61 | +| explained_variance | -0.115 | +| learning_rate | 4.58e-05 | +| loss | -0.0207 | +| n_updates | 15208 | +| policy_gradient_loss | -0.0137 | +| value_loss | 0.000293 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1384 | +| iterations | 3804 | +| time_elapsed | 5625 | +| total_timesteps | 7790592 | +| train/ | | +| approx_kl | 0.0057952935 | +| clip_fraction | 0.3 | +| clip_range | 0.0526 | +| entropy_loss | -7.55 | +| explained_variance | -0.122 | +| learning_rate | 4.58e-05 | +| loss | -0.0233 | +| n_updates | 15212 | +| policy_gradient_loss | -0.0148 | +| value_loss | 0.000178 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1384 | +| iterations | 3805 | +| time_elapsed | 5626 | +| total_timesteps | 7792640 | +| train/ | | +| approx_kl | 0.005193014 | +| clip_fraction | 0.3 | +| clip_range | 0.0526 | +| entropy_loss | -7.57 | +| explained_variance | -0.066 | +| learning_rate | 4.57e-05 | +| loss | -0.023 | +| n_updates | 15216 | +| policy_gradient_loss | -0.0138 | +| value_loss | 0.000198 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1385 | +| iterations | 3806 | +| time_elapsed | 5627 | +| total_timesteps | 7794688 | +| train/ | | +| approx_kl | 0.0066469726 | +| clip_fraction | 0.332 | +| clip_range | 0.0526 | +| entropy_loss | -7.55 | +| explained_variance | 0.0259 | +| learning_rate | 4.57e-05 | +| loss | -0.0249 | +| n_updates | 15220 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000187 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1385 | +| iterations | 3807 | +| time_elapsed | 5629 | +| total_timesteps | 7796736 | +| train/ | | +| approx_kl | 0.00557682 | +| clip_fraction | 0.312 | +| clip_range | 0.0526 | +| entropy_loss | -7.75 | +| explained_variance | 0.04 | +| learning_rate | 4.57e-05 | +| loss | -0.0265 | +| n_updates | 15224 | +| policy_gradient_loss | -0.0167 | +| value_loss | 9.61e-05 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 1385 | +| iterations | 3808 | +| time_elapsed | 5630 | +| total_timesteps | 7798784 | +| train/ | | +| approx_kl | 0.00622497 | +| clip_fraction | 0.308 | +| clip_range | 0.0525 | +| entropy_loss | -7.6 | +| explained_variance | -0.0477 | +| learning_rate | 4.56e-05 | +| loss | -0.0229 | +| n_updates | 15228 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000201 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 1384 | +| iterations | 3809 | +| time_elapsed | 5632 | +| total_timesteps | 7800832 | +| train/ | | +| approx_kl | 0.004924658 | +| clip_fraction | 0.294 | +| clip_range | 0.0525 | +| entropy_loss | -7.47 | +| explained_variance | 0.0316 | +| learning_rate | 4.56e-05 | +| loss | -0.0268 | +| n_updates | 15232 | +| policy_gradient_loss | -0.0145 | +| value_loss | 0.0002 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1385 | +| iterations | 3810 | +| time_elapsed | 5633 | +| total_timesteps | 7802880 | +| train/ | | +| approx_kl | 0.0057793595 | +| clip_fraction | 0.306 | +| clip_range | 0.0525 | +| entropy_loss | -7.5 | +| explained_variance | 0.12 | +| learning_rate | 4.55e-05 | +| loss | -0.0252 | +| n_updates | 15236 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.00011 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1385 | +| iterations | 3811 | +| time_elapsed | 5635 | +| total_timesteps | 7804928 | +| train/ | | +| approx_kl | 0.00568934 | +| clip_fraction | 0.308 | +| clip_range | 0.0525 | +| entropy_loss | -7.5 | +| explained_variance | -0.0342 | +| learning_rate | 4.55e-05 | +| loss | -0.0189 | +| n_updates | 15240 | +| policy_gradient_loss | -0.0141 | +| value_loss | 0.00026 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1385 | +| iterations | 3812 | +| time_elapsed | 5636 | +| total_timesteps | 7806976 | +| train/ | | +| approx_kl | 0.0053598275 | +| clip_fraction | 0.302 | +| clip_range | 0.0524 | +| entropy_loss | -7.65 | +| explained_variance | -0.0525 | +| learning_rate | 4.55e-05 | +| loss | -0.0255 | +| n_updates | 15244 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000233 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1385 | +| iterations | 3813 | +| time_elapsed | 5638 | +| total_timesteps | 7809024 | +| train/ | | +| approx_kl | 0.006432183 | +| clip_fraction | 0.314 | +| clip_range | 0.0524 | +| entropy_loss | -7.61 | +| explained_variance | -0.0338 | +| learning_rate | 4.54e-05 | +| loss | -0.0256 | +| n_updates | 15248 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000165 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1385 | +| iterations | 3814 | +| time_elapsed | 5639 | +| total_timesteps | 7811072 | +| train/ | | +| approx_kl | 0.0057805004 | +| clip_fraction | 0.318 | +| clip_range | 0.0524 | +| entropy_loss | -7.49 | +| explained_variance | -0.0531 | +| learning_rate | 4.54e-05 | +| loss | -0.0218 | +| n_updates | 15252 | +| policy_gradient_loss | -0.0136 | +| value_loss | 0.000235 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1385 | +| iterations | 3815 | +| time_elapsed | 5641 | +| total_timesteps | 7813120 | +| train/ | | +| approx_kl | 0.0063436916 | +| clip_fraction | 0.318 | +| clip_range | 0.0524 | +| entropy_loss | -7.73 | +| explained_variance | -0.061 | +| learning_rate | 4.53e-05 | +| loss | -0.0243 | +| n_updates | 15256 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.00015 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1385 | +| iterations | 3816 | +| time_elapsed | 5642 | +| total_timesteps | 7815168 | +| train/ | | +| approx_kl | 0.005585637 | +| clip_fraction | 0.32 | +| clip_range | 0.0523 | +| entropy_loss | -7.65 | +| explained_variance | -0.18 | +| learning_rate | 4.53e-05 | +| loss | -0.0235 | +| n_updates | 15260 | +| policy_gradient_loss | -0.0167 | +| value_loss | 9.84e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1385 | +| iterations | 3817 | +| time_elapsed | 5644 | +| total_timesteps | 7817216 | +| train/ | | +| approx_kl | 0.0049356627 | +| clip_fraction | 0.288 | +| clip_range | 0.0523 | +| entropy_loss | -7.61 | +| explained_variance | -0.0746 | +| learning_rate | 4.53e-05 | +| loss | -0.023 | +| n_updates | 15264 | +| policy_gradient_loss | -0.0132 | +| value_loss | 0.000231 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1385 | +| iterations | 3818 | +| time_elapsed | 5645 | +| total_timesteps | 7819264 | +| train/ | | +| approx_kl | 0.0053171064 | +| clip_fraction | 0.287 | +| clip_range | 0.0523 | +| entropy_loss | -7.4 | +| explained_variance | 0.0202 | +| learning_rate | 4.52e-05 | +| loss | -0.0199 | +| n_updates | 15268 | +| policy_gradient_loss | -0.0128 | +| value_loss | 0.000271 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1385 | +| iterations | 3819 | +| time_elapsed | 5646 | +| total_timesteps | 7821312 | +| train/ | | +| approx_kl | 0.0054680817 | +| clip_fraction | 0.308 | +| clip_range | 0.0523 | +| entropy_loss | -7.55 | +| explained_variance | 0.0395 | +| learning_rate | 4.52e-05 | +| loss | -0.024 | +| n_updates | 15272 | +| policy_gradient_loss | -0.0144 | +| value_loss | 0.000237 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1385 | +| iterations | 3820 | +| time_elapsed | 5648 | +| total_timesteps | 7823360 | +| train/ | | +| approx_kl | 0.0056983065 | +| clip_fraction | 0.311 | +| clip_range | 0.0522 | +| entropy_loss | -7.31 | +| explained_variance | 0.0216 | +| learning_rate | 4.51e-05 | +| loss | -0.0222 | +| n_updates | 15276 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000297 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1385 | +| iterations | 3821 | +| time_elapsed | 5649 | +| total_timesteps | 7825408 | +| train/ | | +| approx_kl | 0.0063496605 | +| clip_fraction | 0.33 | +| clip_range | 0.0522 | +| entropy_loss | -7.58 | +| explained_variance | -0.104 | +| learning_rate | 4.51e-05 | +| loss | -0.0283 | +| n_updates | 15280 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000191 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1385 | +| iterations | 3822 | +| time_elapsed | 5651 | +| total_timesteps | 7827456 | +| train/ | | +| approx_kl | 0.00560882 | +| clip_fraction | 0.296 | +| clip_range | 0.0522 | +| entropy_loss | -7.56 | +| explained_variance | 0.0626 | +| learning_rate | 4.51e-05 | +| loss | -0.0222 | +| n_updates | 15284 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000214 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1385 | +| iterations | 3823 | +| time_elapsed | 5652 | +| total_timesteps | 7829504 | +| train/ | | +| approx_kl | 0.0048795193 | +| clip_fraction | 0.315 | +| clip_range | 0.0522 | +| entropy_loss | -7.65 | +| explained_variance | -0.0539 | +| learning_rate | 4.5e-05 | +| loss | -0.0275 | +| n_updates | 15288 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000122 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1385 | +| iterations | 3824 | +| time_elapsed | 5654 | +| total_timesteps | 7831552 | +| train/ | | +| approx_kl | 0.005031692 | +| clip_fraction | 0.288 | +| clip_range | 0.0521 | +| entropy_loss | -7.66 | +| explained_variance | -0.186 | +| learning_rate | 4.5e-05 | +| loss | -0.0241 | +| n_updates | 15292 | +| policy_gradient_loss | -0.014 | +| value_loss | 0.000216 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1385 | +| iterations | 3825 | +| time_elapsed | 5655 | +| total_timesteps | 7833600 | +| train/ | | +| approx_kl | 0.005067086 | +| clip_fraction | 0.27 | +| clip_range | 0.0521 | +| entropy_loss | -7.67 | +| explained_variance | -0.0995 | +| learning_rate | 4.49e-05 | +| loss | -0.018 | +| n_updates | 15296 | +| policy_gradient_loss | -0.0115 | +| value_loss | 0.000262 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1385 | +| iterations | 3826 | +| time_elapsed | 5657 | +| total_timesteps | 7835648 | +| train/ | | +| approx_kl | 0.00558836 | +| clip_fraction | 0.294 | +| clip_range | 0.0521 | +| entropy_loss | -7.67 | +| explained_variance | -0.0142 | +| learning_rate | 4.49e-05 | +| loss | -0.0252 | +| n_updates | 15300 | +| policy_gradient_loss | -0.0145 | +| value_loss | 0.000172 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1385 | +| iterations | 3827 | +| time_elapsed | 5658 | +| total_timesteps | 7837696 | +| train/ | | +| approx_kl | 0.0054980232 | +| clip_fraction | 0.32 | +| clip_range | 0.0521 | +| entropy_loss | -7.48 | +| explained_variance | 0.0545 | +| learning_rate | 4.49e-05 | +| loss | -0.0241 | +| n_updates | 15304 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.000137 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1385 | +| iterations | 3828 | +| time_elapsed | 5660 | +| total_timesteps | 7839744 | +| train/ | | +| approx_kl | 0.0054550855 | +| clip_fraction | 0.3 | +| clip_range | 0.052 | +| entropy_loss | -7.61 | +| explained_variance | -0.0817 | +| learning_rate | 4.48e-05 | +| loss | -0.0253 | +| n_updates | 15308 | +| policy_gradient_loss | -0.0142 | +| value_loss | 0.000211 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1385 | +| iterations | 3829 | +| time_elapsed | 5661 | +| total_timesteps | 7841792 | +| train/ | | +| approx_kl | 0.0056307525 | +| clip_fraction | 0.283 | +| clip_range | 0.052 | +| entropy_loss | -7.49 | +| explained_variance | -0.0207 | +| learning_rate | 4.48e-05 | +| loss | -0.023 | +| n_updates | 15312 | +| policy_gradient_loss | -0.0131 | +| value_loss | 0.000233 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1385 | +| iterations | 3830 | +| time_elapsed | 5663 | +| total_timesteps | 7843840 | +| train/ | | +| approx_kl | 0.005536504 | +| clip_fraction | 0.322 | +| clip_range | 0.052 | +| entropy_loss | -7.57 | +| explained_variance | -0.00594 | +| learning_rate | 4.47e-05 | +| loss | -0.0206 | +| n_updates | 15316 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.000114 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1385 | +| iterations | 3831 | +| time_elapsed | 5664 | +| total_timesteps | 7845888 | +| train/ | | +| approx_kl | 0.004685757 | +| clip_fraction | 0.304 | +| clip_range | 0.052 | +| entropy_loss | -7.55 | +| explained_variance | -0.00956 | +| learning_rate | 4.47e-05 | +| loss | -0.0213 | +| n_updates | 15320 | +| policy_gradient_loss | -0.0142 | +| value_loss | 0.000239 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1385 | +| iterations | 3832 | +| time_elapsed | 5665 | +| total_timesteps | 7847936 | +| train/ | | +| approx_kl | 0.005590339 | +| clip_fraction | 0.295 | +| clip_range | 0.0519 | +| entropy_loss | -7.58 | +| explained_variance | -0.0429 | +| learning_rate | 4.47e-05 | +| loss | -0.026 | +| n_updates | 15324 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000151 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1385 | +| iterations | 3833 | +| time_elapsed | 5667 | +| total_timesteps | 7849984 | +| train/ | | +| approx_kl | 0.005151104 | +| clip_fraction | 0.291 | +| clip_range | 0.0519 | +| entropy_loss | -7.59 | +| explained_variance | 0.034 | +| learning_rate | 4.46e-05 | +| loss | -0.0152 | +| n_updates | 15328 | +| policy_gradient_loss | -0.0128 | +| value_loss | 0.000252 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1385 | +| iterations | 3834 | +| time_elapsed | 5668 | +| total_timesteps | 7852032 | +| train/ | | +| approx_kl | 0.0057907435 | +| clip_fraction | 0.287 | +| clip_range | 0.0519 | +| entropy_loss | -7.7 | +| explained_variance | -0.117 | +| learning_rate | 4.46e-05 | +| loss | -0.023 | +| n_updates | 15332 | +| policy_gradient_loss | -0.0142 | +| value_loss | 0.000154 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1385 | +| iterations | 3835 | +| time_elapsed | 5670 | +| total_timesteps | 7854080 | +| train/ | | +| approx_kl | 0.005492598 | +| clip_fraction | 0.307 | +| clip_range | 0.0518 | +| entropy_loss | -7.6 | +| explained_variance | 0.043 | +| learning_rate | 4.45e-05 | +| loss | -0.0247 | +| n_updates | 15336 | +| policy_gradient_loss | -0.0142 | +| value_loss | 0.000121 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1385 | +| iterations | 3836 | +| time_elapsed | 5671 | +| total_timesteps | 7856128 | +| train/ | | +| approx_kl | 0.0052394625 | +| clip_fraction | 0.307 | +| clip_range | 0.0518 | +| entropy_loss | -7.59 | +| explained_variance | -0.0709 | +| learning_rate | 4.45e-05 | +| loss | -0.0194 | +| n_updates | 15340 | +| policy_gradient_loss | -0.0133 | +| value_loss | 0.000301 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1385 | +| iterations | 3837 | +| time_elapsed | 5673 | +| total_timesteps | 7858176 | +| train/ | | +| approx_kl | 0.0055626435 | +| clip_fraction | 0.319 | +| clip_range | 0.0518 | +| entropy_loss | -7.4 | +| explained_variance | 0.0682 | +| learning_rate | 4.44e-05 | +| loss | -0.024 | +| n_updates | 15344 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000141 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1385 | +| iterations | 3838 | +| time_elapsed | 5674 | +| total_timesteps | 7860224 | +| train/ | | +| approx_kl | 0.0051407698 | +| clip_fraction | 0.306 | +| clip_range | 0.0518 | +| entropy_loss | -7.39 | +| explained_variance | 0.0572 | +| learning_rate | 4.44e-05 | +| loss | -0.0209 | +| n_updates | 15348 | +| policy_gradient_loss | -0.013 | +| value_loss | 0.000273 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1385 | +| iterations | 3839 | +| time_elapsed | 5676 | +| total_timesteps | 7862272 | +| train/ | | +| approx_kl | 0.0054931855 | +| clip_fraction | 0.306 | +| clip_range | 0.0517 | +| entropy_loss | -7.54 | +| explained_variance | -0.119 | +| learning_rate | 4.44e-05 | +| loss | -0.0221 | +| n_updates | 15352 | +| policy_gradient_loss | -0.0144 | +| value_loss | 0.000181 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1385 | +| iterations | 3840 | +| time_elapsed | 5677 | +| total_timesteps | 7864320 | +| train/ | | +| approx_kl | 0.0051901294 | +| clip_fraction | 0.31 | +| clip_range | 0.0517 | +| entropy_loss | -7.74 | +| explained_variance | -0.0296 | +| learning_rate | 4.43e-05 | +| loss | -0.0249 | +| n_updates | 15356 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000139 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1385 | +| iterations | 3841 | +| time_elapsed | 5679 | +| total_timesteps | 7866368 | +| train/ | | +| approx_kl | 0.0049372823 | +| clip_fraction | 0.287 | +| clip_range | 0.0517 | +| entropy_loss | -7.61 | +| explained_variance | -0.132 | +| learning_rate | 4.43e-05 | +| loss | -0.0185 | +| n_updates | 15360 | +| policy_gradient_loss | -0.0125 | +| value_loss | 0.000261 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1385 | +| iterations | 3842 | +| time_elapsed | 5680 | +| total_timesteps | 7868416 | +| train/ | | +| approx_kl | 0.005396151 | +| clip_fraction | 0.321 | +| clip_range | 0.0517 | +| entropy_loss | -7.49 | +| explained_variance | 0.0587 | +| learning_rate | 4.42e-05 | +| loss | -0.0236 | +| n_updates | 15364 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000155 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1385 | +| iterations | 3843 | +| time_elapsed | 5682 | +| total_timesteps | 7870464 | +| train/ | | +| approx_kl | 0.0051754657 | +| clip_fraction | 0.305 | +| clip_range | 0.0516 | +| entropy_loss | -7.55 | +| explained_variance | -0.0625 | +| learning_rate | 4.42e-05 | +| loss | -0.0247 | +| n_updates | 15368 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000202 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1385 | +| iterations | 3844 | +| time_elapsed | 5683 | +| total_timesteps | 7872512 | +| train/ | | +| approx_kl | 0.005881353 | +| clip_fraction | 0.298 | +| clip_range | 0.0516 | +| entropy_loss | -7.69 | +| explained_variance | -0.0354 | +| learning_rate | 4.42e-05 | +| loss | -0.0221 | +| n_updates | 15372 | +| policy_gradient_loss | -0.0147 | +| value_loss | 0.000103 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1385 | +| iterations | 3845 | +| time_elapsed | 5685 | +| total_timesteps | 7874560 | +| train/ | | +| approx_kl | 0.005154294 | +| clip_fraction | 0.299 | +| clip_range | 0.0516 | +| entropy_loss | -7.58 | +| explained_variance | -0.0131 | +| learning_rate | 4.41e-05 | +| loss | -0.0234 | +| n_updates | 15376 | +| policy_gradient_loss | -0.0131 | +| value_loss | 0.000219 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1385 | +| iterations | 3846 | +| time_elapsed | 5686 | +| total_timesteps | 7876608 | +| train/ | | +| approx_kl | 0.0050031575 | +| clip_fraction | 0.277 | +| clip_range | 0.0516 | +| entropy_loss | -7.73 | +| explained_variance | 0.0632 | +| learning_rate | 4.41e-05 | +| loss | -0.0225 | +| n_updates | 15380 | +| policy_gradient_loss | -0.0127 | +| value_loss | 0.000269 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1385 | +| iterations | 3847 | +| time_elapsed | 5688 | +| total_timesteps | 7878656 | +| train/ | | +| approx_kl | 0.0051296437 | +| clip_fraction | 0.308 | +| clip_range | 0.0515 | +| entropy_loss | -7.59 | +| explained_variance | -0.155 | +| learning_rate | 4.4e-05 | +| loss | -0.0229 | +| n_updates | 15384 | +| policy_gradient_loss | -0.0141 | +| value_loss | 0.000183 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1385 | +| iterations | 3848 | +| time_elapsed | 5689 | +| total_timesteps | 7880704 | +| train/ | | +| approx_kl | 0.0056607854 | +| clip_fraction | 0.313 | +| clip_range | 0.0515 | +| entropy_loss | -7.41 | +| explained_variance | 0.0299 | +| learning_rate | 4.4e-05 | +| loss | -0.0213 | +| n_updates | 15388 | +| policy_gradient_loss | -0.0145 | +| value_loss | 0.000334 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1385 | +| iterations | 3849 | +| time_elapsed | 5690 | +| total_timesteps | 7882752 | +| train/ | | +| approx_kl | 0.0059125293 | +| clip_fraction | 0.316 | +| clip_range | 0.0515 | +| entropy_loss | -7.52 | +| explained_variance | 0.0301 | +| learning_rate | 4.4e-05 | +| loss | -0.0276 | +| n_updates | 15392 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000145 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1385 | +| iterations | 3850 | +| time_elapsed | 5692 | +| total_timesteps | 7884800 | +| train/ | | +| approx_kl | 0.0055632163 | +| clip_fraction | 0.31 | +| clip_range | 0.0515 | +| entropy_loss | -7.53 | +| explained_variance | -0.0351 | +| learning_rate | 4.39e-05 | +| loss | -0.0214 | +| n_updates | 15396 | +| policy_gradient_loss | -0.0139 | +| value_loss | 0.000179 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1385 | +| iterations | 3851 | +| time_elapsed | 5693 | +| total_timesteps | 7886848 | +| train/ | | +| approx_kl | 0.0058366223 | +| clip_fraction | 0.313 | +| clip_range | 0.0514 | +| entropy_loss | -7.59 | +| explained_variance | -0.0205 | +| learning_rate | 4.39e-05 | +| loss | -0.023 | +| n_updates | 15400 | +| policy_gradient_loss | -0.0146 | +| value_loss | 0.00012 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1385 | +| iterations | 3852 | +| time_elapsed | 5695 | +| total_timesteps | 7888896 | +| train/ | | +| approx_kl | 0.0055263145 | +| clip_fraction | 0.315 | +| clip_range | 0.0514 | +| entropy_loss | -7.67 | +| explained_variance | -0.0767 | +| learning_rate | 4.38e-05 | +| loss | -0.0262 | +| n_updates | 15404 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000156 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1385 | +| iterations | 3853 | +| time_elapsed | 5696 | +| total_timesteps | 7890944 | +| train/ | | +| approx_kl | 0.0060459506 | +| clip_fraction | 0.304 | +| clip_range | 0.0514 | +| entropy_loss | -7.58 | +| explained_variance | -0.0982 | +| learning_rate | 4.38e-05 | +| loss | -0.0194 | +| n_updates | 15408 | +| policy_gradient_loss | -0.0135 | +| value_loss | 0.000197 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1385 | +| iterations | 3854 | +| time_elapsed | 5698 | +| total_timesteps | 7892992 | +| train/ | | +| approx_kl | 0.0058930535 | +| clip_fraction | 0.284 | +| clip_range | 0.0514 | +| entropy_loss | -7.69 | +| explained_variance | -0.0251 | +| learning_rate | 4.38e-05 | +| loss | -0.0217 | +| n_updates | 15412 | +| policy_gradient_loss | -0.0136 | +| value_loss | 0.000138 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1385 | +| iterations | 3855 | +| time_elapsed | 5699 | +| total_timesteps | 7895040 | +| train/ | | +| approx_kl | 0.005822601 | +| clip_fraction | 0.305 | +| clip_range | 0.0513 | +| entropy_loss | -7.71 | +| explained_variance | -0.107 | +| learning_rate | 4.37e-05 | +| loss | -0.0246 | +| n_updates | 15416 | +| policy_gradient_loss | -0.0148 | +| value_loss | 0.000124 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1385 | +| iterations | 3856 | +| time_elapsed | 5701 | +| total_timesteps | 7897088 | +| train/ | | +| approx_kl | 0.0053839083 | +| clip_fraction | 0.294 | +| clip_range | 0.0513 | +| entropy_loss | -7.43 | +| explained_variance | 0.0636 | +| learning_rate | 4.37e-05 | +| loss | -0.0227 | +| n_updates | 15420 | +| policy_gradient_loss | -0.0138 | +| value_loss | 0.000154 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1385 | +| iterations | 3857 | +| time_elapsed | 5702 | +| total_timesteps | 7899136 | +| train/ | | +| approx_kl | 0.0051739477 | +| clip_fraction | 0.305 | +| clip_range | 0.0513 | +| entropy_loss | -7.6 | +| explained_variance | 0.0469 | +| learning_rate | 4.36e-05 | +| loss | -0.0213 | +| n_updates | 15424 | +| policy_gradient_loss | -0.0135 | +| value_loss | 0.000225 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1385 | +| iterations | 3858 | +| time_elapsed | 5704 | +| total_timesteps | 7901184 | +| train/ | | +| approx_kl | 0.0056180703 | +| clip_fraction | 0.334 | +| clip_range | 0.0513 | +| entropy_loss | -7.72 | +| explained_variance | -0.054 | +| learning_rate | 4.36e-05 | +| loss | -0.0269 | +| n_updates | 15428 | +| policy_gradient_loss | -0.0159 | +| value_loss | 9.48e-05 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1385 | +| iterations | 3859 | +| time_elapsed | 5705 | +| total_timesteps | 7903232 | +| train/ | | +| approx_kl | 0.0045807636 | +| clip_fraction | 0.303 | +| clip_range | 0.0512 | +| entropy_loss | -7.64 | +| explained_variance | 0.0201 | +| learning_rate | 4.36e-05 | +| loss | -0.022 | +| n_updates | 15432 | +| policy_gradient_loss | -0.0138 | +| value_loss | 0.000111 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1385 | +| iterations | 3860 | +| time_elapsed | 5707 | +| total_timesteps | 7905280 | +| train/ | | +| approx_kl | 0.0052375607 | +| clip_fraction | 0.316 | +| clip_range | 0.0512 | +| entropy_loss | -7.41 | +| explained_variance | -0.0413 | +| learning_rate | 4.35e-05 | +| loss | -0.0245 | +| n_updates | 15436 | +| policy_gradient_loss | -0.0145 | +| value_loss | 0.000167 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1385 | +| iterations | 3861 | +| time_elapsed | 5708 | +| total_timesteps | 7907328 | +| train/ | | +| approx_kl | 0.0045075617 | +| clip_fraction | 0.296 | +| clip_range | 0.0512 | +| entropy_loss | -7.74 | +| explained_variance | 0.00167 | +| learning_rate | 4.35e-05 | +| loss | -0.0234 | +| n_updates | 15440 | +| policy_gradient_loss | -0.0137 | +| value_loss | 0.000155 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1385 | +| iterations | 3862 | +| time_elapsed | 5710 | +| total_timesteps | 7909376 | +| train/ | | +| approx_kl | 0.0039526317 | +| clip_fraction | 0.272 | +| clip_range | 0.0512 | +| entropy_loss | -7.5 | +| explained_variance | 0.0145 | +| learning_rate | 4.34e-05 | +| loss | -0.0182 | +| n_updates | 15444 | +| policy_gradient_loss | -0.0122 | +| value_loss | 0.000389 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1385 | +| iterations | 3863 | +| time_elapsed | 5711 | +| total_timesteps | 7911424 | +| train/ | | +| approx_kl | 0.004545475 | +| clip_fraction | 0.29 | +| clip_range | 0.0511 | +| entropy_loss | -7.5 | +| explained_variance | -0.272 | +| learning_rate | 4.34e-05 | +| loss | -0.0235 | +| n_updates | 15448 | +| policy_gradient_loss | -0.0148 | +| value_loss | 0.000136 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1385 | +| iterations | 3864 | +| time_elapsed | 5713 | +| total_timesteps | 7913472 | +| train/ | | +| approx_kl | 0.0063061733 | +| clip_fraction | 0.326 | +| clip_range | 0.0511 | +| entropy_loss | -7.67 | +| explained_variance | -0.13 | +| learning_rate | 4.34e-05 | +| loss | -0.0232 | +| n_updates | 15452 | +| policy_gradient_loss | -0.0166 | +| value_loss | 9.92e-05 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1385 | +| iterations | 3865 | +| time_elapsed | 5714 | +| total_timesteps | 7915520 | +| train/ | | +| approx_kl | 0.0042721042 | +| clip_fraction | 0.27 | +| clip_range | 0.0511 | +| entropy_loss | -7.64 | +| explained_variance | 0.00809 | +| learning_rate | 4.33e-05 | +| loss | -0.0187 | +| n_updates | 15456 | +| policy_gradient_loss | -0.0116 | +| value_loss | 0.000142 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1385 | +| iterations | 3866 | +| time_elapsed | 5716 | +| total_timesteps | 7917568 | +| train/ | | +| approx_kl | 0.0048653753 | +| clip_fraction | 0.258 | +| clip_range | 0.0511 | +| entropy_loss | -7.67 | +| explained_variance | -0.0115 | +| learning_rate | 4.33e-05 | +| loss | -0.0227 | +| n_updates | 15460 | +| policy_gradient_loss | -0.0126 | +| value_loss | 0.000201 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1385 | +| iterations | 3867 | +| time_elapsed | 5717 | +| total_timesteps | 7919616 | +| train/ | | +| approx_kl | 0.0048985397 | +| clip_fraction | 0.267 | +| clip_range | 0.051 | +| entropy_loss | -7.62 | +| explained_variance | -0.00938 | +| learning_rate | 4.32e-05 | +| loss | -0.0203 | +| n_updates | 15464 | +| policy_gradient_loss | -0.0123 | +| value_loss | 0.000325 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1385 | +| iterations | 3868 | +| time_elapsed | 5719 | +| total_timesteps | 7921664 | +| train/ | | +| approx_kl | 0.004945674 | +| clip_fraction | 0.303 | +| clip_range | 0.051 | +| entropy_loss | -7.47 | +| explained_variance | -0.0648 | +| learning_rate | 4.32e-05 | +| loss | -0.0233 | +| n_updates | 15468 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000176 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1385 | +| iterations | 3869 | +| time_elapsed | 5720 | +| total_timesteps | 7923712 | +| train/ | | +| approx_kl | 0.004711333 | +| clip_fraction | 0.287 | +| clip_range | 0.051 | +| entropy_loss | -7.76 | +| explained_variance | -0.171 | +| learning_rate | 4.32e-05 | +| loss | -0.025 | +| n_updates | 15472 | +| policy_gradient_loss | -0.0141 | +| value_loss | 0.000158 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1385 | +| iterations | 3870 | +| time_elapsed | 5722 | +| total_timesteps | 7925760 | +| train/ | | +| approx_kl | 0.005358819 | +| clip_fraction | 0.289 | +| clip_range | 0.051 | +| entropy_loss | -7.63 | +| explained_variance | 0.0345 | +| learning_rate | 4.31e-05 | +| loss | -0.0211 | +| n_updates | 15476 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.000123 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1385 | +| iterations | 3871 | +| time_elapsed | 5723 | +| total_timesteps | 7927808 | +| train/ | | +| approx_kl | 0.00531367 | +| clip_fraction | 0.313 | +| clip_range | 0.0509 | +| entropy_loss | -7.59 | +| explained_variance | -0.0457 | +| learning_rate | 4.31e-05 | +| loss | -0.021 | +| n_updates | 15480 | +| policy_gradient_loss | -0.0141 | +| value_loss | 0.000127 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1385 | +| iterations | 3872 | +| time_elapsed | 5724 | +| total_timesteps | 7929856 | +| train/ | | +| approx_kl | 0.0055560507 | +| clip_fraction | 0.307 | +| clip_range | 0.0509 | +| entropy_loss | -7.51 | +| explained_variance | -0.117 | +| learning_rate | 4.3e-05 | +| loss | -0.021 | +| n_updates | 15484 | +| policy_gradient_loss | -0.0148 | +| value_loss | 0.000222 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1385 | +| iterations | 3873 | +| time_elapsed | 5726 | +| total_timesteps | 7931904 | +| train/ | | +| approx_kl | 0.0043381387 | +| clip_fraction | 0.285 | +| clip_range | 0.0509 | +| entropy_loss | -7.61 | +| explained_variance | 0.014 | +| learning_rate | 4.3e-05 | +| loss | -0.019 | +| n_updates | 15488 | +| policy_gradient_loss | -0.0126 | +| value_loss | 0.000199 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1385 | +| iterations | 3874 | +| time_elapsed | 5727 | +| total_timesteps | 7933952 | +| train/ | | +| approx_kl | 0.004767776 | +| clip_fraction | 0.274 | +| clip_range | 0.0509 | +| entropy_loss | -7.53 | +| explained_variance | -0.0132 | +| learning_rate | 4.29e-05 | +| loss | -0.023 | +| n_updates | 15492 | +| policy_gradient_loss | -0.0133 | +| value_loss | 0.000186 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1385 | +| iterations | 3875 | +| time_elapsed | 5729 | +| total_timesteps | 7936000 | +| train/ | | +| approx_kl | 0.005198505 | +| clip_fraction | 0.321 | +| clip_range | 0.0508 | +| entropy_loss | -7.65 | +| explained_variance | 0.00857 | +| learning_rate | 4.29e-05 | +| loss | -0.022 | +| n_updates | 15496 | +| policy_gradient_loss | -0.0145 | +| value_loss | 0.000245 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1385 | +| iterations | 3876 | +| time_elapsed | 5730 | +| total_timesteps | 7938048 | +| train/ | | +| approx_kl | 0.0047187936 | +| clip_fraction | 0.3 | +| clip_range | 0.0508 | +| entropy_loss | -7.5 | +| explained_variance | -0.0778 | +| learning_rate | 4.29e-05 | +| loss | -0.023 | +| n_updates | 15500 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000412 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1385 | +| iterations | 3877 | +| time_elapsed | 5732 | +| total_timesteps | 7940096 | +| train/ | | +| approx_kl | 0.004928353 | +| clip_fraction | 0.28 | +| clip_range | 0.0508 | +| entropy_loss | -7.68 | +| explained_variance | 0.014 | +| learning_rate | 4.28e-05 | +| loss | -0.0214 | +| n_updates | 15504 | +| policy_gradient_loss | -0.0135 | +| value_loss | 0.000199 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1385 | +| iterations | 3878 | +| time_elapsed | 5733 | +| total_timesteps | 7942144 | +| train/ | | +| approx_kl | 0.005516053 | +| clip_fraction | 0.3 | +| clip_range | 0.0507 | +| entropy_loss | -7.61 | +| explained_variance | -0.0488 | +| learning_rate | 4.28e-05 | +| loss | -0.0207 | +| n_updates | 15508 | +| policy_gradient_loss | -0.014 | +| value_loss | 0.00015 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1385 | +| iterations | 3879 | +| time_elapsed | 5735 | +| total_timesteps | 7944192 | +| train/ | | +| approx_kl | 0.004749191 | +| clip_fraction | 0.279 | +| clip_range | 0.0507 | +| entropy_loss | -7.57 | +| explained_variance | -0.0735 | +| learning_rate | 4.27e-05 | +| loss | -0.0231 | +| n_updates | 15512 | +| policy_gradient_loss | -0.013 | +| value_loss | 0.000262 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1385 | +| iterations | 3880 | +| time_elapsed | 5736 | +| total_timesteps | 7946240 | +| train/ | | +| approx_kl | 0.0043401886 | +| clip_fraction | 0.291 | +| clip_range | 0.0507 | +| entropy_loss | -7.68 | +| explained_variance | -0.0749 | +| learning_rate | 4.27e-05 | +| loss | -0.0254 | +| n_updates | 15516 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000112 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1385 | +| iterations | 3881 | +| time_elapsed | 5738 | +| total_timesteps | 7948288 | +| train/ | | +| approx_kl | 0.0038462828 | +| clip_fraction | 0.275 | +| clip_range | 0.0507 | +| entropy_loss | -7.6 | +| explained_variance | -0.0134 | +| learning_rate | 4.27e-05 | +| loss | -0.0214 | +| n_updates | 15520 | +| policy_gradient_loss | -0.0119 | +| value_loss | 0.000395 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1385 | +| iterations | 3882 | +| time_elapsed | 5739 | +| total_timesteps | 7950336 | +| train/ | | +| approx_kl | 0.0050448836 | +| clip_fraction | 0.307 | +| clip_range | 0.0506 | +| entropy_loss | -7.59 | +| explained_variance | -0.116 | +| learning_rate | 4.26e-05 | +| loss | -0.0285 | +| n_updates | 15524 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.000142 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1385 | +| iterations | 3883 | +| time_elapsed | 5741 | +| total_timesteps | 7952384 | +| train/ | | +| approx_kl | 0.0045302855 | +| clip_fraction | 0.301 | +| clip_range | 0.0506 | +| entropy_loss | -7.62 | +| explained_variance | -0.0258 | +| learning_rate | 4.26e-05 | +| loss | -0.021 | +| n_updates | 15528 | +| policy_gradient_loss | -0.0133 | +| value_loss | 0.000306 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.315 | +| time/ | | +| fps | 1385 | +| iterations | 3884 | +| time_elapsed | 5742 | +| total_timesteps | 7954432 | +| train/ | | +| approx_kl | 0.004844335 | +| clip_fraction | 0.304 | +| clip_range | 0.0506 | +| entropy_loss | -7.5 | +| explained_variance | -0.00354 | +| learning_rate | 4.25e-05 | +| loss | -0.0154 | +| n_updates | 15532 | +| policy_gradient_loss | -0.0125 | +| value_loss | 0.000316 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1385 | +| iterations | 3885 | +| time_elapsed | 5744 | +| total_timesteps | 7956480 | +| train/ | | +| approx_kl | 0.004542436 | +| clip_fraction | 0.286 | +| clip_range | 0.0506 | +| entropy_loss | -7.61 | +| explained_variance | 0.105 | +| learning_rate | 4.25e-05 | +| loss | -0.0247 | +| n_updates | 15536 | +| policy_gradient_loss | -0.0145 | +| value_loss | 0.000177 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1385 | +| iterations | 3886 | +| time_elapsed | 5745 | +| total_timesteps | 7958528 | +| train/ | | +| approx_kl | 0.0047305664 | +| clip_fraction | 0.31 | +| clip_range | 0.0505 | +| entropy_loss | -7.67 | +| explained_variance | 0.0277 | +| learning_rate | 4.25e-05 | +| loss | -0.0246 | +| n_updates | 15540 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.000114 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1385 | +| iterations | 3887 | +| time_elapsed | 5747 | +| total_timesteps | 7960576 | +| train/ | | +| approx_kl | 0.0051476317 | +| clip_fraction | 0.302 | +| clip_range | 0.0505 | +| entropy_loss | -7.58 | +| explained_variance | 0.00879 | +| learning_rate | 4.24e-05 | +| loss | -0.0247 | +| n_updates | 15544 | +| policy_gradient_loss | -0.0145 | +| value_loss | 0.000165 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1385 | +| iterations | 3888 | +| time_elapsed | 5748 | +| total_timesteps | 7962624 | +| train/ | | +| approx_kl | 0.004950964 | +| clip_fraction | 0.288 | +| clip_range | 0.0505 | +| entropy_loss | -7.62 | +| explained_variance | -0.058 | +| learning_rate | 4.24e-05 | +| loss | -0.0225 | +| n_updates | 15548 | +| policy_gradient_loss | -0.014 | +| value_loss | 0.000224 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1385 | +| iterations | 3889 | +| time_elapsed | 5749 | +| total_timesteps | 7964672 | +| train/ | | +| approx_kl | 0.005413724 | +| clip_fraction | 0.301 | +| clip_range | 0.0505 | +| entropy_loss | -7.65 | +| explained_variance | -0.0446 | +| learning_rate | 4.23e-05 | +| loss | -0.0255 | +| n_updates | 15552 | +| policy_gradient_loss | -0.014 | +| value_loss | 0.000199 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1385 | +| iterations | 3890 | +| time_elapsed | 5751 | +| total_timesteps | 7966720 | +| train/ | | +| approx_kl | 0.0050935317 | +| clip_fraction | 0.312 | +| clip_range | 0.0504 | +| entropy_loss | -7.7 | +| explained_variance | -0.291 | +| learning_rate | 4.23e-05 | +| loss | -0.0214 | +| n_updates | 15556 | +| policy_gradient_loss | -0.0159 | +| value_loss | 8.5e-05 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1385 | +| iterations | 3891 | +| time_elapsed | 5752 | +| total_timesteps | 7968768 | +| train/ | | +| approx_kl | 0.0046622604 | +| clip_fraction | 0.291 | +| clip_range | 0.0504 | +| entropy_loss | -7.59 | +| explained_variance | -0.0716 | +| learning_rate | 4.23e-05 | +| loss | -0.022 | +| n_updates | 15560 | +| policy_gradient_loss | -0.0148 | +| value_loss | 0.000171 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1385 | +| iterations | 3892 | +| time_elapsed | 5754 | +| total_timesteps | 7970816 | +| train/ | | +| approx_kl | 0.0046847905 | +| clip_fraction | 0.297 | +| clip_range | 0.0504 | +| entropy_loss | -7.6 | +| explained_variance | 0.0392 | +| learning_rate | 4.22e-05 | +| loss | -0.0247 | +| n_updates | 15564 | +| policy_gradient_loss | -0.0139 | +| value_loss | 0.000272 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1385 | +| iterations | 3893 | +| time_elapsed | 5755 | +| total_timesteps | 7972864 | +| train/ | | +| approx_kl | 0.0050650225 | +| clip_fraction | 0.331 | +| clip_range | 0.0504 | +| entropy_loss | -7.64 | +| explained_variance | -0.38 | +| learning_rate | 4.22e-05 | +| loss | -0.0238 | +| n_updates | 15568 | +| policy_gradient_loss | -0.0165 | +| value_loss | 8.66e-05 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1385 | +| iterations | 3894 | +| time_elapsed | 5757 | +| total_timesteps | 7974912 | +| train/ | | +| approx_kl | 0.0056858743 | +| clip_fraction | 0.301 | +| clip_range | 0.0503 | +| entropy_loss | -7.69 | +| explained_variance | -0.27 | +| learning_rate | 4.21e-05 | +| loss | -0.023 | +| n_updates | 15572 | +| policy_gradient_loss | -0.0155 | +| value_loss | 9.1e-05 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1385 | +| iterations | 3895 | +| time_elapsed | 5758 | +| total_timesteps | 7976960 | +| train/ | | +| approx_kl | 0.0039600707 | +| clip_fraction | 0.255 | +| clip_range | 0.0503 | +| entropy_loss | -7.56 | +| explained_variance | 0.00882 | +| learning_rate | 4.21e-05 | +| loss | -0.0151 | +| n_updates | 15576 | +| policy_gradient_loss | -0.0112 | +| value_loss | 0.000311 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1385 | +| iterations | 3896 | +| time_elapsed | 5760 | +| total_timesteps | 7979008 | +| train/ | | +| approx_kl | 0.004735297 | +| clip_fraction | 0.299 | +| clip_range | 0.0503 | +| entropy_loss | -7.52 | +| explained_variance | 0.0925 | +| learning_rate | 4.21e-05 | +| loss | -0.0247 | +| n_updates | 15580 | +| policy_gradient_loss | -0.0146 | +| value_loss | 0.000261 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1385 | +| iterations | 3897 | +| time_elapsed | 5761 | +| total_timesteps | 7981056 | +| train/ | | +| approx_kl | 0.004570804 | +| clip_fraction | 0.297 | +| clip_range | 0.0503 | +| entropy_loss | -7.44 | +| explained_variance | 0.0603 | +| learning_rate | 4.2e-05 | +| loss | -0.0217 | +| n_updates | 15584 | +| policy_gradient_loss | -0.0141 | +| value_loss | 0.000236 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1385 | +| iterations | 3898 | +| time_elapsed | 5763 | +| total_timesteps | 7983104 | +| train/ | | +| approx_kl | 0.004857992 | +| clip_fraction | 0.306 | +| clip_range | 0.0502 | +| entropy_loss | -7.5 | +| explained_variance | -0.0332 | +| learning_rate | 4.2e-05 | +| loss | -0.0229 | +| n_updates | 15588 | +| policy_gradient_loss | -0.0146 | +| value_loss | 0.000263 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1385 | +| iterations | 3899 | +| time_elapsed | 5764 | +| total_timesteps | 7985152 | +| train/ | | +| approx_kl | 0.0045651533 | +| clip_fraction | 0.303 | +| clip_range | 0.0502 | +| entropy_loss | -7.76 | +| explained_variance | -0.0223 | +| learning_rate | 4.19e-05 | +| loss | -0.0259 | +| n_updates | 15592 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.000224 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1385 | +| iterations | 3900 | +| time_elapsed | 5765 | +| total_timesteps | 7987200 | +| train/ | | +| approx_kl | 0.0042396104 | +| clip_fraction | 0.307 | +| clip_range | 0.0502 | +| entropy_loss | -7.62 | +| explained_variance | -0.0355 | +| learning_rate | 4.19e-05 | +| loss | -0.0212 | +| n_updates | 15596 | +| policy_gradient_loss | -0.0136 | +| value_loss | 0.000251 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1385 | +| iterations | 3901 | +| time_elapsed | 5767 | +| total_timesteps | 7989248 | +| train/ | | +| approx_kl | 0.005396546 | +| clip_fraction | 0.285 | +| clip_range | 0.0502 | +| entropy_loss | -7.51 | +| explained_variance | -0.0414 | +| learning_rate | 4.19e-05 | +| loss | -0.0196 | +| n_updates | 15600 | +| policy_gradient_loss | -0.0121 | +| value_loss | 0.000353 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1385 | +| iterations | 3902 | +| time_elapsed | 5768 | +| total_timesteps | 7991296 | +| train/ | | +| approx_kl | 0.004774646 | +| clip_fraction | 0.29 | +| clip_range | 0.0501 | +| entropy_loss | -7.5 | +| explained_variance | -0.0964 | +| learning_rate | 4.18e-05 | +| loss | -0.0229 | +| n_updates | 15604 | +| policy_gradient_loss | -0.0143 | +| value_loss | 0.000253 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1385 | +| iterations | 3903 | +| time_elapsed | 5770 | +| total_timesteps | 7993344 | +| train/ | | +| approx_kl | 0.0045679174 | +| clip_fraction | 0.29 | +| clip_range | 0.0501 | +| entropy_loss | -7.67 | +| explained_variance | -0.0088 | +| learning_rate | 4.18e-05 | +| loss | -0.0247 | +| n_updates | 15608 | +| policy_gradient_loss | -0.0138 | +| value_loss | 0.000233 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1385 | +| iterations | 3904 | +| time_elapsed | 5771 | +| total_timesteps | 7995392 | +| train/ | | +| approx_kl | 0.004734053 | +| clip_fraction | 0.308 | +| clip_range | 0.0501 | +| entropy_loss | -7.76 | +| explained_variance | -0.094 | +| learning_rate | 4.17e-05 | +| loss | -0.0207 | +| n_updates | 15612 | +| policy_gradient_loss | -0.0142 | +| value_loss | 0.000158 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1385 | +| iterations | 3905 | +| time_elapsed | 5773 | +| total_timesteps | 7997440 | +| train/ | | +| approx_kl | 0.00438701 | +| clip_fraction | 0.268 | +| clip_range | 0.0501 | +| entropy_loss | -7.6 | +| explained_variance | -0.101 | +| learning_rate | 4.17e-05 | +| loss | -0.0199 | +| n_updates | 15616 | +| policy_gradient_loss | -0.0131 | +| value_loss | 0.000179 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1385 | +| iterations | 3906 | +| time_elapsed | 5774 | +| total_timesteps | 7999488 | +| train/ | | +| approx_kl | 0.0046819197 | +| clip_fraction | 0.297 | +| clip_range | 0.05 | +| entropy_loss | -7.6 | +| explained_variance | -0.0401 | +| learning_rate | 4.17e-05 | +| loss | -0.0181 | +| n_updates | 15620 | +| policy_gradient_loss | -0.0132 | +| value_loss | 0.000414 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1385 | +| iterations | 3907 | +| time_elapsed | 5776 | +| total_timesteps | 8001536 | +| train/ | | +| approx_kl | 0.004262835 | +| clip_fraction | 0.288 | +| clip_range | 0.05 | +| entropy_loss | -7.69 | +| explained_variance | -0.139 | +| learning_rate | 4.16e-05 | +| loss | -0.022 | +| n_updates | 15624 | +| policy_gradient_loss | -0.013 | +| value_loss | 0.000205 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1385 | +| iterations | 3908 | +| time_elapsed | 5777 | +| total_timesteps | 8003584 | +| train/ | | +| approx_kl | 0.00459271 | +| clip_fraction | 0.301 | +| clip_range | 0.05 | +| entropy_loss | -7.74 | +| explained_variance | -0.0592 | +| learning_rate | 4.16e-05 | +| loss | -0.0251 | +| n_updates | 15628 | +| policy_gradient_loss | -0.0145 | +| value_loss | 0.000161 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1385 | +| iterations | 3909 | +| time_elapsed | 5779 | +| total_timesteps | 8005632 | +| train/ | | +| approx_kl | 0.0041647083 | +| clip_fraction | 0.299 | +| clip_range | 0.05 | +| entropy_loss | -7.64 | +| explained_variance | 0.0115 | +| learning_rate | 4.15e-05 | +| loss | -0.0226 | +| n_updates | 15632 | +| policy_gradient_loss | -0.0131 | +| value_loss | 0.000124 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1385 | +| iterations | 3910 | +| time_elapsed | 5780 | +| total_timesteps | 8007680 | +| train/ | | +| approx_kl | 0.00494784 | +| clip_fraction | 0.287 | +| clip_range | 0.0499 | +| entropy_loss | -7.48 | +| explained_variance | 0.0759 | +| learning_rate | 4.15e-05 | +| loss | -0.0236 | +| n_updates | 15636 | +| policy_gradient_loss | -0.014 | +| value_loss | 0.000161 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1385 | +| iterations | 3911 | +| time_elapsed | 5782 | +| total_timesteps | 8009728 | +| train/ | | +| approx_kl | 0.004649645 | +| clip_fraction | 0.305 | +| clip_range | 0.0499 | +| entropy_loss | -7.47 | +| explained_variance | 0.0385 | +| learning_rate | 4.14e-05 | +| loss | -0.0229 | +| n_updates | 15640 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.000294 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1385 | +| iterations | 3912 | +| time_elapsed | 5783 | +| total_timesteps | 8011776 | +| train/ | | +| approx_kl | 0.0049054064 | +| clip_fraction | 0.317 | +| clip_range | 0.0499 | +| entropy_loss | -7.64 | +| explained_variance | -0.0512 | +| learning_rate | 4.14e-05 | +| loss | -0.0197 | +| n_updates | 15644 | +| policy_gradient_loss | -0.0144 | +| value_loss | 0.000147 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1385 | +| iterations | 3913 | +| time_elapsed | 5784 | +| total_timesteps | 8013824 | +| train/ | | +| approx_kl | 0.00472735 | +| clip_fraction | 0.287 | +| clip_range | 0.0499 | +| entropy_loss | -7.77 | +| explained_variance | 0.0674 | +| learning_rate | 4.14e-05 | +| loss | -0.025 | +| n_updates | 15648 | +| policy_gradient_loss | -0.0143 | +| value_loss | 0.0002 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1385 | +| iterations | 3914 | +| time_elapsed | 5786 | +| total_timesteps | 8015872 | +| train/ | | +| approx_kl | 0.0052065738 | +| clip_fraction | 0.296 | +| clip_range | 0.0498 | +| entropy_loss | -7.71 | +| explained_variance | -0.017 | +| learning_rate | 4.13e-05 | +| loss | -0.021 | +| n_updates | 15652 | +| policy_gradient_loss | -0.014 | +| value_loss | 0.000241 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1385 | +| iterations | 3915 | +| time_elapsed | 5787 | +| total_timesteps | 8017920 | +| train/ | | +| approx_kl | 0.004044074 | +| clip_fraction | 0.265 | +| clip_range | 0.0498 | +| entropy_loss | -7.64 | +| explained_variance | 0.0326 | +| learning_rate | 4.13e-05 | +| loss | -0.0174 | +| n_updates | 15656 | +| policy_gradient_loss | -0.0122 | +| value_loss | 0.000272 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1385 | +| iterations | 3916 | +| time_elapsed | 5789 | +| total_timesteps | 8019968 | +| train/ | | +| approx_kl | 0.0046557286 | +| clip_fraction | 0.275 | +| clip_range | 0.0498 | +| entropy_loss | -7.56 | +| explained_variance | -0.0995 | +| learning_rate | 4.12e-05 | +| loss | -0.0222 | +| n_updates | 15660 | +| policy_gradient_loss | -0.0137 | +| value_loss | 0.000148 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1385 | +| iterations | 3917 | +| time_elapsed | 5790 | +| total_timesteps | 8022016 | +| train/ | | +| approx_kl | 0.0043815044 | +| clip_fraction | 0.297 | +| clip_range | 0.0498 | +| entropy_loss | -7.51 | +| explained_variance | 0.1 | +| learning_rate | 4.12e-05 | +| loss | -0.0229 | +| n_updates | 15664 | +| policy_gradient_loss | -0.0137 | +| value_loss | 0.000205 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1385 | +| iterations | 3918 | +| time_elapsed | 5792 | +| total_timesteps | 8024064 | +| train/ | | +| approx_kl | 0.005366779 | +| clip_fraction | 0.3 | +| clip_range | 0.0497 | +| entropy_loss | -7.51 | +| explained_variance | 0.0486 | +| learning_rate | 4.12e-05 | +| loss | -0.0229 | +| n_updates | 15668 | +| policy_gradient_loss | -0.0142 | +| value_loss | 0.000166 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1385 | +| iterations | 3919 | +| time_elapsed | 5793 | +| total_timesteps | 8026112 | +| train/ | | +| approx_kl | 0.004586947 | +| clip_fraction | 0.311 | +| clip_range | 0.0497 | +| entropy_loss | -7.72 | +| explained_variance | -0.0927 | +| learning_rate | 4.11e-05 | +| loss | -0.0236 | +| n_updates | 15672 | +| policy_gradient_loss | -0.0142 | +| value_loss | 0.000204 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1385 | +| iterations | 3920 | +| time_elapsed | 5795 | +| total_timesteps | 8028160 | +| train/ | | +| approx_kl | 0.004135466 | +| clip_fraction | 0.281 | +| clip_range | 0.0497 | +| entropy_loss | -7.69 | +| explained_variance | -0.0414 | +| learning_rate | 4.11e-05 | +| loss | -0.0217 | +| n_updates | 15676 | +| policy_gradient_loss | -0.0135 | +| value_loss | 0.000168 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1385 | +| iterations | 3921 | +| time_elapsed | 5796 | +| total_timesteps | 8030208 | +| train/ | | +| approx_kl | 0.0038920718 | +| clip_fraction | 0.29 | +| clip_range | 0.0496 | +| entropy_loss | -7.44 | +| explained_variance | 0.00539 | +| learning_rate | 4.1e-05 | +| loss | -0.0191 | +| n_updates | 15680 | +| policy_gradient_loss | -0.013 | +| value_loss | 0.000459 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1385 | +| iterations | 3922 | +| time_elapsed | 5798 | +| total_timesteps | 8032256 | +| train/ | | +| approx_kl | 0.004333367 | +| clip_fraction | 0.3 | +| clip_range | 0.0496 | +| entropy_loss | -7.62 | +| explained_variance | -0.0613 | +| learning_rate | 4.1e-05 | +| loss | -0.0232 | +| n_updates | 15684 | +| policy_gradient_loss | -0.0142 | +| value_loss | 0.000181 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1385 | +| iterations | 3923 | +| time_elapsed | 5799 | +| total_timesteps | 8034304 | +| train/ | | +| approx_kl | 0.0034098006 | +| clip_fraction | 0.246 | +| clip_range | 0.0496 | +| entropy_loss | -7.64 | +| explained_variance | -0.0142 | +| learning_rate | 4.1e-05 | +| loss | -0.0161 | +| n_updates | 15688 | +| policy_gradient_loss | -0.0109 | +| value_loss | 0.000277 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1385 | +| iterations | 3924 | +| time_elapsed | 5801 | +| total_timesteps | 8036352 | +| train/ | | +| approx_kl | 0.004419012 | +| clip_fraction | 0.287 | +| clip_range | 0.0496 | +| entropy_loss | -7.61 | +| explained_variance | -0.105 | +| learning_rate | 4.09e-05 | +| loss | -0.021 | +| n_updates | 15692 | +| policy_gradient_loss | -0.0137 | +| value_loss | 0.000159 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1385 | +| iterations | 3925 | +| time_elapsed | 5802 | +| total_timesteps | 8038400 | +| train/ | | +| approx_kl | 0.004257015 | +| clip_fraction | 0.303 | +| clip_range | 0.0495 | +| entropy_loss | -7.67 | +| explained_variance | -0.272 | +| learning_rate | 4.09e-05 | +| loss | -0.023 | +| n_updates | 15696 | +| policy_gradient_loss | -0.0139 | +| value_loss | 0.000179 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1385 | +| iterations | 3926 | +| time_elapsed | 5803 | +| total_timesteps | 8040448 | +| train/ | | +| approx_kl | 0.004828225 | +| clip_fraction | 0.277 | +| clip_range | 0.0495 | +| entropy_loss | -7.8 | +| explained_variance | -0.253 | +| learning_rate | 4.08e-05 | +| loss | -0.0232 | +| n_updates | 15700 | +| policy_gradient_loss | -0.0142 | +| value_loss | 9.83e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1385 | +| iterations | 3927 | +| time_elapsed | 5805 | +| total_timesteps | 8042496 | +| train/ | | +| approx_kl | 0.0041869944 | +| clip_fraction | 0.25 | +| clip_range | 0.0495 | +| entropy_loss | -7.56 | +| explained_variance | -0.0136 | +| learning_rate | 4.08e-05 | +| loss | -0.0235 | +| n_updates | 15704 | +| policy_gradient_loss | -0.0127 | +| value_loss | 0.000317 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1385 | +| iterations | 3928 | +| time_elapsed | 5806 | +| total_timesteps | 8044544 | +| train/ | | +| approx_kl | 0.0043660454 | +| clip_fraction | 0.291 | +| clip_range | 0.0495 | +| entropy_loss | -7.44 | +| explained_variance | 0.1 | +| learning_rate | 4.08e-05 | +| loss | -0.024 | +| n_updates | 15708 | +| policy_gradient_loss | -0.0137 | +| value_loss | 0.000219 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1385 | +| iterations | 3929 | +| time_elapsed | 5808 | +| total_timesteps | 8046592 | +| train/ | | +| approx_kl | 0.0044118296 | +| clip_fraction | 0.296 | +| clip_range | 0.0494 | +| entropy_loss | -7.7 | +| explained_variance | -0.0897 | +| learning_rate | 4.07e-05 | +| loss | -0.0224 | +| n_updates | 15712 | +| policy_gradient_loss | -0.0142 | +| value_loss | 0.000127 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1385 | +| iterations | 3930 | +| time_elapsed | 5809 | +| total_timesteps | 8048640 | +| train/ | | +| approx_kl | 0.0038007824 | +| clip_fraction | 0.27 | +| clip_range | 0.0494 | +| entropy_loss | -7.66 | +| explained_variance | 0.000793 | +| learning_rate | 4.07e-05 | +| loss | -0.0165 | +| n_updates | 15716 | +| policy_gradient_loss | -0.0119 | +| value_loss | 0.000314 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1385 | +| iterations | 3931 | +| time_elapsed | 5811 | +| total_timesteps | 8050688 | +| train/ | | +| approx_kl | 0.0049121473 | +| clip_fraction | 0.28 | +| clip_range | 0.0494 | +| entropy_loss | -7.52 | +| explained_variance | -0.0881 | +| learning_rate | 4.06e-05 | +| loss | -0.022 | +| n_updates | 15720 | +| policy_gradient_loss | -0.0135 | +| value_loss | 0.000161 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1385 | +| iterations | 3932 | +| time_elapsed | 5812 | +| total_timesteps | 8052736 | +| train/ | | +| approx_kl | 0.004716475 | +| clip_fraction | 0.288 | +| clip_range | 0.0494 | +| entropy_loss | -7.67 | +| explained_variance | -0.136 | +| learning_rate | 4.06e-05 | +| loss | -0.0237 | +| n_updates | 15724 | +| policy_gradient_loss | -0.0139 | +| value_loss | 0.000153 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1385 | +| iterations | 3933 | +| time_elapsed | 5814 | +| total_timesteps | 8054784 | +| train/ | | +| approx_kl | 0.0042222766 | +| clip_fraction | 0.286 | +| clip_range | 0.0493 | +| entropy_loss | -7.58 | +| explained_variance | 0.0268 | +| learning_rate | 4.06e-05 | +| loss | -0.0227 | +| n_updates | 15728 | +| policy_gradient_loss | -0.0133 | +| value_loss | 0.000192 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1385 | +| iterations | 3934 | +| time_elapsed | 5815 | +| total_timesteps | 8056832 | +| train/ | | +| approx_kl | 0.0041736206 | +| clip_fraction | 0.28 | +| clip_range | 0.0493 | +| entropy_loss | -7.8 | +| explained_variance | -0.0441 | +| learning_rate | 4.05e-05 | +| loss | -0.0218 | +| n_updates | 15732 | +| policy_gradient_loss | -0.0132 | +| value_loss | 0.00022 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1385 | +| iterations | 3935 | +| time_elapsed | 5816 | +| total_timesteps | 8058880 | +| train/ | | +| approx_kl | 0.0042278096 | +| clip_fraction | 0.286 | +| clip_range | 0.0493 | +| entropy_loss | -7.77 | +| explained_variance | -0.29 | +| learning_rate | 4.05e-05 | +| loss | -0.025 | +| n_updates | 15736 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.000103 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1385 | +| iterations | 3936 | +| time_elapsed | 5818 | +| total_timesteps | 8060928 | +| train/ | | +| approx_kl | 0.0041684387 | +| clip_fraction | 0.278 | +| clip_range | 0.0493 | +| entropy_loss | -7.44 | +| explained_variance | 0.0708 | +| learning_rate | 4.04e-05 | +| loss | -0.0165 | +| n_updates | 15740 | +| policy_gradient_loss | -0.0118 | +| value_loss | 0.000244 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1385 | +| iterations | 3937 | +| time_elapsed | 5819 | +| total_timesteps | 8062976 | +| train/ | | +| approx_kl | 0.0046540564 | +| clip_fraction | 0.283 | +| clip_range | 0.0492 | +| entropy_loss | -7.58 | +| explained_variance | 0.0312 | +| learning_rate | 4.04e-05 | +| loss | -0.0226 | +| n_updates | 15744 | +| policy_gradient_loss | -0.0141 | +| value_loss | 0.000177 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1385 | +| iterations | 3938 | +| time_elapsed | 5821 | +| total_timesteps | 8065024 | +| train/ | | +| approx_kl | 0.0048143947 | +| clip_fraction | 0.313 | +| clip_range | 0.0492 | +| entropy_loss | -7.61 | +| explained_variance | 0.088 | +| learning_rate | 4.04e-05 | +| loss | -0.0249 | +| n_updates | 15748 | +| policy_gradient_loss | -0.0166 | +| value_loss | 6.92e-05 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1385 | +| iterations | 3939 | +| time_elapsed | 5822 | +| total_timesteps | 8067072 | +| train/ | | +| approx_kl | 0.0050682444 | +| clip_fraction | 0.287 | +| clip_range | 0.0492 | +| entropy_loss | -7.63 | +| explained_variance | 0.0273 | +| learning_rate | 4.03e-05 | +| loss | -0.0205 | +| n_updates | 15752 | +| policy_gradient_loss | -0.0134 | +| value_loss | 0.000142 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1385 | +| iterations | 3940 | +| time_elapsed | 5824 | +| total_timesteps | 8069120 | +| train/ | | +| approx_kl | 0.0042315684 | +| clip_fraction | 0.272 | +| clip_range | 0.0492 | +| entropy_loss | -7.41 | +| explained_variance | 0.0597 | +| learning_rate | 4.03e-05 | +| loss | -0.023 | +| n_updates | 15756 | +| policy_gradient_loss | -0.0126 | +| value_loss | 0.000173 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1385 | +| iterations | 3941 | +| time_elapsed | 5825 | +| total_timesteps | 8071168 | +| train/ | | +| approx_kl | 0.0038184584 | +| clip_fraction | 0.269 | +| clip_range | 0.0491 | +| entropy_loss | -7.74 | +| explained_variance | 0.0571 | +| learning_rate | 4.02e-05 | +| loss | -0.0225 | +| n_updates | 15760 | +| policy_gradient_loss | -0.0132 | +| value_loss | 0.000183 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1385 | +| iterations | 3942 | +| time_elapsed | 5827 | +| total_timesteps | 8073216 | +| train/ | | +| approx_kl | 0.004411203 | +| clip_fraction | 0.268 | +| clip_range | 0.0491 | +| entropy_loss | -7.73 | +| explained_variance | -0.167 | +| learning_rate | 4.02e-05 | +| loss | -0.0232 | +| n_updates | 15764 | +| policy_gradient_loss | -0.0131 | +| value_loss | 0.000117 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1385 | +| iterations | 3943 | +| time_elapsed | 5828 | +| total_timesteps | 8075264 | +| train/ | | +| approx_kl | 0.0042544995 | +| clip_fraction | 0.258 | +| clip_range | 0.0491 | +| entropy_loss | -7.69 | +| explained_variance | -0.0513 | +| learning_rate | 4.02e-05 | +| loss | -0.0198 | +| n_updates | 15768 | +| policy_gradient_loss | -0.0111 | +| value_loss | 0.000215 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1385 | +| iterations | 3944 | +| time_elapsed | 5830 | +| total_timesteps | 8077312 | +| train/ | | +| approx_kl | 0.004274276 | +| clip_fraction | 0.276 | +| clip_range | 0.0491 | +| entropy_loss | -7.78 | +| explained_variance | -0.0437 | +| learning_rate | 4.01e-05 | +| loss | -0.021 | +| n_updates | 15772 | +| policy_gradient_loss | -0.0131 | +| value_loss | 0.000197 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1385 | +| iterations | 3945 | +| time_elapsed | 5831 | +| total_timesteps | 8079360 | +| train/ | | +| approx_kl | 0.0042483723 | +| clip_fraction | 0.269 | +| clip_range | 0.049 | +| entropy_loss | -7.64 | +| explained_variance | -0.0603 | +| learning_rate | 4.01e-05 | +| loss | -0.0202 | +| n_updates | 15776 | +| policy_gradient_loss | -0.0131 | +| value_loss | 9.87e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1385 | +| iterations | 3946 | +| time_elapsed | 5833 | +| total_timesteps | 8081408 | +| train/ | | +| approx_kl | 0.004265485 | +| clip_fraction | 0.261 | +| clip_range | 0.049 | +| entropy_loss | -7.66 | +| explained_variance | -0.0859 | +| learning_rate | 4e-05 | +| loss | -0.0174 | +| n_updates | 15780 | +| policy_gradient_loss | -0.0118 | +| value_loss | 0.000227 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1385 | +| iterations | 3947 | +| time_elapsed | 5834 | +| total_timesteps | 8083456 | +| train/ | | +| approx_kl | 0.0040207827 | +| clip_fraction | 0.265 | +| clip_range | 0.049 | +| entropy_loss | -7.65 | +| explained_variance | 0.0766 | +| learning_rate | 4e-05 | +| loss | -0.0222 | +| n_updates | 15784 | +| policy_gradient_loss | -0.0134 | +| value_loss | 0.00013 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1385 | +| iterations | 3948 | +| time_elapsed | 5836 | +| total_timesteps | 8085504 | +| train/ | | +| approx_kl | 0.0042262217 | +| clip_fraction | 0.275 | +| clip_range | 0.049 | +| entropy_loss | -7.56 | +| explained_variance | -0.111 | +| learning_rate | 3.99e-05 | +| loss | -0.0255 | +| n_updates | 15788 | +| policy_gradient_loss | -0.0124 | +| value_loss | 0.000184 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1385 | +| iterations | 3949 | +| time_elapsed | 5837 | +| total_timesteps | 8087552 | +| train/ | | +| approx_kl | 0.00397632 | +| clip_fraction | 0.253 | +| clip_range | 0.0489 | +| entropy_loss | -7.6 | +| explained_variance | 0.00853 | +| learning_rate | 3.99e-05 | +| loss | -0.0229 | +| n_updates | 15792 | +| policy_gradient_loss | -0.0128 | +| value_loss | 0.000184 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1385 | +| iterations | 3950 | +| time_elapsed | 5839 | +| total_timesteps | 8089600 | +| train/ | | +| approx_kl | 0.0043599065 | +| clip_fraction | 0.292 | +| clip_range | 0.0489 | +| entropy_loss | -7.79 | +| explained_variance | -0.00745 | +| learning_rate | 3.99e-05 | +| loss | -0.0218 | +| n_updates | 15796 | +| policy_gradient_loss | -0.0137 | +| value_loss | 0.000168 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1385 | +| iterations | 3951 | +| time_elapsed | 5840 | +| total_timesteps | 8091648 | +| train/ | | +| approx_kl | 0.0041698758 | +| clip_fraction | 0.266 | +| clip_range | 0.0489 | +| entropy_loss | -7.68 | +| explained_variance | -0.0467 | +| learning_rate | 3.98e-05 | +| loss | -0.0225 | +| n_updates | 15800 | +| policy_gradient_loss | -0.0127 | +| value_loss | 0.000253 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1385 | +| iterations | 3952 | +| time_elapsed | 5842 | +| total_timesteps | 8093696 | +| train/ | | +| approx_kl | 0.0042789793 | +| clip_fraction | 0.299 | +| clip_range | 0.0489 | +| entropy_loss | -7.72 | +| explained_variance | -0.133 | +| learning_rate | 3.98e-05 | +| loss | -0.0192 | +| n_updates | 15804 | +| policy_gradient_loss | -0.0134 | +| value_loss | 0.000106 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1385 | +| iterations | 3953 | +| time_elapsed | 5843 | +| total_timesteps | 8095744 | +| train/ | | +| approx_kl | 0.0044944827 | +| clip_fraction | 0.261 | +| clip_range | 0.0488 | +| entropy_loss | -7.81 | +| explained_variance | -0.0859 | +| learning_rate | 3.97e-05 | +| loss | -0.0197 | +| n_updates | 15808 | +| policy_gradient_loss | -0.0125 | +| value_loss | 0.000201 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1385 | +| iterations | 3954 | +| time_elapsed | 5844 | +| total_timesteps | 8097792 | +| train/ | | +| approx_kl | 0.003173604 | +| clip_fraction | 0.259 | +| clip_range | 0.0488 | +| entropy_loss | -7.66 | +| explained_variance | 0.0418 | +| learning_rate | 3.97e-05 | +| loss | -0.0174 | +| n_updates | 15812 | +| policy_gradient_loss | -0.012 | +| value_loss | 0.000151 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1385 | +| iterations | 3955 | +| time_elapsed | 5846 | +| total_timesteps | 8099840 | +| train/ | | +| approx_kl | 0.004261135 | +| clip_fraction | 0.266 | +| clip_range | 0.0488 | +| entropy_loss | -7.64 | +| explained_variance | -0.143 | +| learning_rate | 3.97e-05 | +| loss | -0.0181 | +| n_updates | 15816 | +| policy_gradient_loss | -0.0118 | +| value_loss | 0.000145 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1385 | +| iterations | 3956 | +| time_elapsed | 5847 | +| total_timesteps | 8101888 | +| train/ | | +| approx_kl | 0.0044706548 | +| clip_fraction | 0.281 | +| clip_range | 0.0488 | +| entropy_loss | -7.63 | +| explained_variance | -0.0994 | +| learning_rate | 3.96e-05 | +| loss | -0.0229 | +| n_updates | 15820 | +| policy_gradient_loss | -0.0138 | +| value_loss | 0.000157 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1385 | +| iterations | 3957 | +| time_elapsed | 5849 | +| total_timesteps | 8103936 | +| train/ | | +| approx_kl | 0.004218668 | +| clip_fraction | 0.278 | +| clip_range | 0.0487 | +| entropy_loss | -7.77 | +| explained_variance | -0.112 | +| learning_rate | 3.96e-05 | +| loss | -0.0221 | +| n_updates | 15824 | +| policy_gradient_loss | -0.0137 | +| value_loss | 0.000105 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1385 | +| iterations | 3958 | +| time_elapsed | 5850 | +| total_timesteps | 8105984 | +| train/ | | +| approx_kl | 0.0042834366 | +| clip_fraction | 0.29 | +| clip_range | 0.0487 | +| entropy_loss | -7.68 | +| explained_variance | 0.0158 | +| learning_rate | 3.95e-05 | +| loss | -0.0259 | +| n_updates | 15828 | +| policy_gradient_loss | -0.015 | +| value_loss | 6.18e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1385 | +| iterations | 3959 | +| time_elapsed | 5852 | +| total_timesteps | 8108032 | +| train/ | | +| approx_kl | 0.004222464 | +| clip_fraction | 0.269 | +| clip_range | 0.0487 | +| entropy_loss | -7.64 | +| explained_variance | 0.0241 | +| learning_rate | 3.95e-05 | +| loss | -0.0197 | +| n_updates | 15832 | +| policy_gradient_loss | -0.0118 | +| value_loss | 0.000113 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1385 | +| iterations | 3960 | +| time_elapsed | 5853 | +| total_timesteps | 8110080 | +| train/ | | +| approx_kl | 0.004278976 | +| clip_fraction | 0.264 | +| clip_range | 0.0486 | +| entropy_loss | -7.52 | +| explained_variance | 0.0572 | +| learning_rate | 3.95e-05 | +| loss | -0.0232 | +| n_updates | 15836 | +| policy_gradient_loss | -0.013 | +| value_loss | 0.000152 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1385 | +| iterations | 3961 | +| time_elapsed | 5855 | +| total_timesteps | 8112128 | +| train/ | | +| approx_kl | 0.004484765 | +| clip_fraction | 0.291 | +| clip_range | 0.0486 | +| entropy_loss | -7.57 | +| explained_variance | 0.145 | +| learning_rate | 3.94e-05 | +| loss | -0.023 | +| n_updates | 15840 | +| policy_gradient_loss | -0.0147 | +| value_loss | 8.55e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1385 | +| iterations | 3962 | +| time_elapsed | 5856 | +| total_timesteps | 8114176 | +| train/ | | +| approx_kl | 0.004130785 | +| clip_fraction | 0.254 | +| clip_range | 0.0486 | +| entropy_loss | -7.82 | +| explained_variance | -0.0394 | +| learning_rate | 3.94e-05 | +| loss | -0.0219 | +| n_updates | 15844 | +| policy_gradient_loss | -0.0121 | +| value_loss | 0.000213 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1385 | +| iterations | 3963 | +| time_elapsed | 5858 | +| total_timesteps | 8116224 | +| train/ | | +| approx_kl | 0.003961739 | +| clip_fraction | 0.274 | +| clip_range | 0.0486 | +| entropy_loss | -7.77 | +| explained_variance | -0.246 | +| learning_rate | 3.93e-05 | +| loss | -0.0227 | +| n_updates | 15848 | +| policy_gradient_loss | -0.0145 | +| value_loss | 6.05e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1385 | +| iterations | 3964 | +| time_elapsed | 5859 | +| total_timesteps | 8118272 | +| train/ | | +| approx_kl | 0.004030892 | +| clip_fraction | 0.267 | +| clip_range | 0.0485 | +| entropy_loss | -7.68 | +| explained_variance | -0.127 | +| learning_rate | 3.93e-05 | +| loss | -0.0217 | +| n_updates | 15852 | +| policy_gradient_loss | -0.0133 | +| value_loss | 0.000131 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1385 | +| iterations | 3965 | +| time_elapsed | 5861 | +| total_timesteps | 8120320 | +| train/ | | +| approx_kl | 0.003758376 | +| clip_fraction | 0.273 | +| clip_range | 0.0485 | +| entropy_loss | -7.51 | +| explained_variance | 0.0942 | +| learning_rate | 3.93e-05 | +| loss | -0.0198 | +| n_updates | 15856 | +| policy_gradient_loss | -0.0131 | +| value_loss | 0.000182 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1385 | +| iterations | 3966 | +| time_elapsed | 5862 | +| total_timesteps | 8122368 | +| train/ | | +| approx_kl | 0.0036256863 | +| clip_fraction | 0.258 | +| clip_range | 0.0485 | +| entropy_loss | -7.52 | +| explained_variance | 0.0325 | +| learning_rate | 3.92e-05 | +| loss | -0.016 | +| n_updates | 15860 | +| policy_gradient_loss | -0.0108 | +| value_loss | 0.000293 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.315 | +| time/ | | +| fps | 1385 | +| iterations | 3967 | +| time_elapsed | 5864 | +| total_timesteps | 8124416 | +| train/ | | +| approx_kl | 0.0046184734 | +| clip_fraction | 0.276 | +| clip_range | 0.0485 | +| entropy_loss | -7.74 | +| explained_variance | -0.0725 | +| learning_rate | 3.92e-05 | +| loss | -0.0211 | +| n_updates | 15864 | +| policy_gradient_loss | -0.0137 | +| value_loss | 0.000173 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1385 | +| iterations | 3968 | +| time_elapsed | 5865 | +| total_timesteps | 8126464 | +| train/ | | +| approx_kl | 0.00421215 | +| clip_fraction | 0.29 | +| clip_range | 0.0484 | +| entropy_loss | -7.63 | +| explained_variance | 0.0233 | +| learning_rate | 3.91e-05 | +| loss | -0.0216 | +| n_updates | 15868 | +| policy_gradient_loss | -0.0131 | +| value_loss | 0.000104 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1385 | +| iterations | 3969 | +| time_elapsed | 5867 | +| total_timesteps | 8128512 | +| train/ | | +| approx_kl | 0.0038071072 | +| clip_fraction | 0.285 | +| clip_range | 0.0484 | +| entropy_loss | -7.67 | +| explained_variance | 0.0468 | +| learning_rate | 3.91e-05 | +| loss | -0.0216 | +| n_updates | 15872 | +| policy_gradient_loss | -0.0135 | +| value_loss | 0.000187 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1385 | +| iterations | 3970 | +| time_elapsed | 5868 | +| total_timesteps | 8130560 | +| train/ | | +| approx_kl | 0.0036906109 | +| clip_fraction | 0.281 | +| clip_range | 0.0484 | +| entropy_loss | -7.76 | +| explained_variance | -0.0261 | +| learning_rate | 3.91e-05 | +| loss | -0.0213 | +| n_updates | 15876 | +| policy_gradient_loss | -0.0128 | +| value_loss | 0.000166 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1385 | +| iterations | 3971 | +| time_elapsed | 5870 | +| total_timesteps | 8132608 | +| train/ | | +| approx_kl | 0.0043169274 | +| clip_fraction | 0.294 | +| clip_range | 0.0484 | +| entropy_loss | -7.77 | +| explained_variance | -0.149 | +| learning_rate | 3.9e-05 | +| loss | -0.0227 | +| n_updates | 15880 | +| policy_gradient_loss | -0.0144 | +| value_loss | 9.06e-05 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.306 | +| time/ | | +| fps | 1385 | +| iterations | 3972 | +| time_elapsed | 5871 | +| total_timesteps | 8134656 | +| train/ | | +| approx_kl | 0.0037957262 | +| clip_fraction | 0.279 | +| clip_range | 0.0483 | +| entropy_loss | -7.71 | +| explained_variance | -0.131 | +| learning_rate | 3.9e-05 | +| loss | -0.0222 | +| n_updates | 15884 | +| policy_gradient_loss | -0.0136 | +| value_loss | 0.000135 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1385 | +| iterations | 3973 | +| time_elapsed | 5873 | +| total_timesteps | 8136704 | +| train/ | | +| approx_kl | 0.0037555462 | +| clip_fraction | 0.28 | +| clip_range | 0.0483 | +| entropy_loss | -7.69 | +| explained_variance | 0.00511 | +| learning_rate | 3.89e-05 | +| loss | -0.0208 | +| n_updates | 15888 | +| policy_gradient_loss | -0.0123 | +| value_loss | 0.000158 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1385 | +| iterations | 3974 | +| time_elapsed | 5874 | +| total_timesteps | 8138752 | +| train/ | | +| approx_kl | 0.003961903 | +| clip_fraction | 0.262 | +| clip_range | 0.0483 | +| entropy_loss | -7.65 | +| explained_variance | -0.0236 | +| learning_rate | 3.89e-05 | +| loss | -0.0184 | +| n_updates | 15892 | +| policy_gradient_loss | -0.0118 | +| value_loss | 0.000261 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 1385 | +| iterations | 3975 | +| time_elapsed | 5875 | +| total_timesteps | 8140800 | +| train/ | | +| approx_kl | 0.004268994 | +| clip_fraction | 0.3 | +| clip_range | 0.0483 | +| entropy_loss | -7.83 | +| explained_variance | -0.173 | +| learning_rate | 3.89e-05 | +| loss | -0.0227 | +| n_updates | 15896 | +| policy_gradient_loss | -0.0139 | +| value_loss | 8.41e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.306 | +| time/ | | +| fps | 1385 | +| iterations | 3976 | +| time_elapsed | 5877 | +| total_timesteps | 8142848 | +| train/ | | +| approx_kl | 0.0040854327 | +| clip_fraction | 0.286 | +| clip_range | 0.0482 | +| entropy_loss | -7.61 | +| explained_variance | 0.0301 | +| learning_rate | 3.88e-05 | +| loss | -0.0233 | +| n_updates | 15900 | +| policy_gradient_loss | -0.0138 | +| value_loss | 0.00023 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 1385 | +| iterations | 3977 | +| time_elapsed | 5878 | +| total_timesteps | 8144896 | +| train/ | | +| approx_kl | 0.0041163135 | +| clip_fraction | 0.292 | +| clip_range | 0.0482 | +| entropy_loss | -7.72 | +| explained_variance | -0.0405 | +| learning_rate | 3.88e-05 | +| loss | -0.021 | +| n_updates | 15904 | +| policy_gradient_loss | -0.0135 | +| value_loss | 0.000109 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.3 | +| time/ | | +| fps | 1385 | +| iterations | 3978 | +| time_elapsed | 5880 | +| total_timesteps | 8146944 | +| train/ | | +| approx_kl | 0.0048115044 | +| clip_fraction | 0.287 | +| clip_range | 0.0482 | +| entropy_loss | -7.6 | +| explained_variance | 0.0713 | +| learning_rate | 3.87e-05 | +| loss | -0.0217 | +| n_updates | 15908 | +| policy_gradient_loss | -0.0136 | +| value_loss | 0.000133 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 1385 | +| iterations | 3979 | +| time_elapsed | 5881 | +| total_timesteps | 8148992 | +| train/ | | +| approx_kl | 0.0040627364 | +| clip_fraction | 0.294 | +| clip_range | 0.0482 | +| entropy_loss | -7.72 | +| explained_variance | 0.0123 | +| learning_rate | 3.87e-05 | +| loss | -0.0205 | +| n_updates | 15912 | +| policy_gradient_loss | -0.0123 | +| value_loss | 0.000133 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 1385 | +| iterations | 3980 | +| time_elapsed | 5883 | +| total_timesteps | 8151040 | +| train/ | | +| approx_kl | 0.0039009387 | +| clip_fraction | 0.289 | +| clip_range | 0.0481 | +| entropy_loss | -7.78 | +| explained_variance | -0.0964 | +| learning_rate | 3.86e-05 | +| loss | -0.0182 | +| n_updates | 15916 | +| policy_gradient_loss | -0.0132 | +| value_loss | 8.59e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.3 | +| time/ | | +| fps | 1385 | +| iterations | 3981 | +| time_elapsed | 5884 | +| total_timesteps | 8153088 | +| train/ | | +| approx_kl | 0.003967599 | +| clip_fraction | 0.276 | +| clip_range | 0.0481 | +| entropy_loss | -7.7 | +| explained_variance | -0.0715 | +| learning_rate | 3.86e-05 | +| loss | -0.0192 | +| n_updates | 15920 | +| policy_gradient_loss | -0.0129 | +| value_loss | 0.000203 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.3 | +| time/ | | +| fps | 1385 | +| iterations | 3982 | +| time_elapsed | 5886 | +| total_timesteps | 8155136 | +| train/ | | +| approx_kl | 0.0042408155 | +| clip_fraction | 0.298 | +| clip_range | 0.0481 | +| entropy_loss | -7.71 | +| explained_variance | -0.112 | +| learning_rate | 3.86e-05 | +| loss | -0.0204 | +| n_updates | 15924 | +| policy_gradient_loss | -0.0128 | +| value_loss | 0.00011 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 1385 | +| iterations | 3983 | +| time_elapsed | 5887 | +| total_timesteps | 8157184 | +| train/ | | +| approx_kl | 0.00473762 | +| clip_fraction | 0.283 | +| clip_range | 0.0481 | +| entropy_loss | -7.57 | +| explained_variance | -0.0022 | +| learning_rate | 3.85e-05 | +| loss | -0.0203 | +| n_updates | 15928 | +| policy_gradient_loss | -0.0135 | +| value_loss | 0.000127 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.306 | +| time/ | | +| fps | 1385 | +| iterations | 3984 | +| time_elapsed | 5889 | +| total_timesteps | 8159232 | +| train/ | | +| approx_kl | 0.0038210247 | +| clip_fraction | 0.241 | +| clip_range | 0.048 | +| entropy_loss | -7.6 | +| explained_variance | 0.0202 | +| learning_rate | 3.85e-05 | +| loss | -0.0198 | +| n_updates | 15932 | +| policy_gradient_loss | -0.0105 | +| value_loss | 0.000198 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.306 | +| time/ | | +| fps | 1385 | +| iterations | 3985 | +| time_elapsed | 5890 | +| total_timesteps | 8161280 | +| train/ | | +| approx_kl | 0.003378598 | +| clip_fraction | 0.275 | +| clip_range | 0.048 | +| entropy_loss | -7.74 | +| explained_variance | -0.0463 | +| learning_rate | 3.84e-05 | +| loss | -0.017 | +| n_updates | 15936 | +| policy_gradient_loss | -0.0112 | +| value_loss | 0.000249 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.295 | +| time/ | | +| fps | 1385 | +| iterations | 3986 | +| time_elapsed | 5892 | +| total_timesteps | 8163328 | +| train/ | | +| approx_kl | 0.0039733103 | +| clip_fraction | 0.278 | +| clip_range | 0.048 | +| entropy_loss | -7.83 | +| explained_variance | -0.0506 | +| learning_rate | 3.84e-05 | +| loss | -0.0225 | +| n_updates | 15940 | +| policy_gradient_loss | -0.0129 | +| value_loss | 0.000192 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.295 | +| time/ | | +| fps | 1385 | +| iterations | 3987 | +| time_elapsed | 5893 | +| total_timesteps | 8165376 | +| train/ | | +| approx_kl | 0.004155838 | +| clip_fraction | 0.287 | +| clip_range | 0.048 | +| entropy_loss | -7.55 | +| explained_variance | -0.337 | +| learning_rate | 3.84e-05 | +| loss | -0.0246 | +| n_updates | 15944 | +| policy_gradient_loss | -0.0145 | +| value_loss | 0.00012 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.292 | +| time/ | | +| fps | 1385 | +| iterations | 3988 | +| time_elapsed | 5895 | +| total_timesteps | 8167424 | +| train/ | | +| approx_kl | 0.0041453517 | +| clip_fraction | 0.271 | +| clip_range | 0.0479 | +| entropy_loss | -7.72 | +| explained_variance | -0.0534 | +| learning_rate | 3.83e-05 | +| loss | -0.0206 | +| n_updates | 15948 | +| policy_gradient_loss | -0.0125 | +| value_loss | 0.000169 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.287 | +| time/ | | +| fps | 1385 | +| iterations | 3989 | +| time_elapsed | 5896 | +| total_timesteps | 8169472 | +| train/ | | +| approx_kl | 0.0036844404 | +| clip_fraction | 0.272 | +| clip_range | 0.0479 | +| entropy_loss | -7.69 | +| explained_variance | -0.0491 | +| learning_rate | 3.83e-05 | +| loss | -0.0197 | +| n_updates | 15952 | +| policy_gradient_loss | -0.0121 | +| value_loss | 0.000155 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.287 | +| time/ | | +| fps | 1385 | +| iterations | 3990 | +| time_elapsed | 5898 | +| total_timesteps | 8171520 | +| train/ | | +| approx_kl | 0.003789501 | +| clip_fraction | 0.271 | +| clip_range | 0.0479 | +| entropy_loss | -7.6 | +| explained_variance | -0.0366 | +| learning_rate | 3.82e-05 | +| loss | -0.0227 | +| n_updates | 15956 | +| policy_gradient_loss | -0.0135 | +| value_loss | 0.000153 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.288 | +| time/ | | +| fps | 1385 | +| iterations | 3991 | +| time_elapsed | 5899 | +| total_timesteps | 8173568 | +| train/ | | +| approx_kl | 0.0039460436 | +| clip_fraction | 0.29 | +| clip_range | 0.0479 | +| entropy_loss | -7.74 | +| explained_variance | -0.214 | +| learning_rate | 3.82e-05 | +| loss | -0.0243 | +| n_updates | 15960 | +| policy_gradient_loss | -0.0141 | +| value_loss | 6.68e-05 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.284 | +| time/ | | +| fps | 1385 | +| iterations | 3992 | +| time_elapsed | 5901 | +| total_timesteps | 8175616 | +| train/ | | +| approx_kl | 0.0038655428 | +| clip_fraction | 0.266 | +| clip_range | 0.0478 | +| entropy_loss | -7.74 | +| explained_variance | -0.0333 | +| learning_rate | 3.82e-05 | +| loss | -0.0189 | +| n_updates | 15964 | +| policy_gradient_loss | -0.012 | +| value_loss | 0.000115 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.286 | +| time/ | | +| fps | 1385 | +| iterations | 3993 | +| time_elapsed | 5902 | +| total_timesteps | 8177664 | +| train/ | | +| approx_kl | 0.0034539176 | +| clip_fraction | 0.267 | +| clip_range | 0.0478 | +| entropy_loss | -7.41 | +| explained_variance | -0.00853 | +| learning_rate | 3.81e-05 | +| loss | -0.0214 | +| n_updates | 15968 | +| policy_gradient_loss | -0.0125 | +| value_loss | 0.000206 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.278 | +| time/ | | +| fps | 1385 | +| iterations | 3994 | +| time_elapsed | 5904 | +| total_timesteps | 8179712 | +| train/ | | +| approx_kl | 0.003570792 | +| clip_fraction | 0.274 | +| clip_range | 0.0478 | +| entropy_loss | -7.68 | +| explained_variance | -0.0909 | +| learning_rate | 3.81e-05 | +| loss | -0.0187 | +| n_updates | 15972 | +| policy_gradient_loss | -0.0116 | +| value_loss | 0.000177 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.281 | +| time/ | | +| fps | 1385 | +| iterations | 3995 | +| time_elapsed | 5905 | +| total_timesteps | 8181760 | +| train/ | | +| approx_kl | 0.0038215024 | +| clip_fraction | 0.27 | +| clip_range | 0.0478 | +| entropy_loss | -7.59 | +| explained_variance | -0.105 | +| learning_rate | 3.8e-05 | +| loss | -0.0235 | +| n_updates | 15976 | +| policy_gradient_loss | -0.0129 | +| value_loss | 0.000165 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.281 | +| time/ | | +| fps | 1385 | +| iterations | 3996 | +| time_elapsed | 5907 | +| total_timesteps | 8183808 | +| train/ | | +| approx_kl | 0.0037601243 | +| clip_fraction | 0.286 | +| clip_range | 0.0477 | +| entropy_loss | -7.73 | +| explained_variance | -0.0438 | +| learning_rate | 3.8e-05 | +| loss | -0.0219 | +| n_updates | 15980 | +| policy_gradient_loss | -0.0142 | +| value_loss | 0.000218 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.277 | +| time/ | | +| fps | 1385 | +| iterations | 3997 | +| time_elapsed | 5908 | +| total_timesteps | 8185856 | +| train/ | | +| approx_kl | 0.0033800695 | +| clip_fraction | 0.251 | +| clip_range | 0.0477 | +| entropy_loss | -7.82 | +| explained_variance | -0.0589 | +| learning_rate | 3.8e-05 | +| loss | -0.0218 | +| n_updates | 15984 | +| policy_gradient_loss | -0.0127 | +| value_loss | 9.85e-05 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.283 | +| time/ | | +| fps | 1385 | +| iterations | 3998 | +| time_elapsed | 5910 | +| total_timesteps | 8187904 | +| train/ | | +| approx_kl | 0.0037796274 | +| clip_fraction | 0.286 | +| clip_range | 0.0477 | +| entropy_loss | -7.72 | +| explained_variance | -0.0368 | +| learning_rate | 3.79e-05 | +| loss | -0.0205 | +| n_updates | 15988 | +| policy_gradient_loss | -0.0129 | +| value_loss | 0.000146 | +------------------------------------------ +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.283 | +| time/ | | +| fps | 1385 | +| iterations | 3999 | +| time_elapsed | 5911 | +| total_timesteps | 8189952 | +| train/ | | +| approx_kl | 0.0035855 | +| clip_fraction | 0.277 | +| clip_range | 0.0477 | +| entropy_loss | -7.62 | +| explained_variance | -0.191 | +| learning_rate | 3.79e-05 | +| loss | -0.0226 | +| n_updates | 15992 | +| policy_gradient_loss | -0.0131 | +| value_loss | 6.06e-05 | +--------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.278 | +| time/ | | +| fps | 1385 | +| iterations | 4000 | +| time_elapsed | 5912 | +| total_timesteps | 8192000 | +| train/ | | +| approx_kl | 0.0034516691 | +| clip_fraction | 0.265 | +| clip_range | 0.0476 | +| entropy_loss | -7.7 | +| explained_variance | -0.0273 | +| learning_rate | 3.78e-05 | +| loss | -0.0187 | +| n_updates | 15996 | +| policy_gradient_loss | -0.0124 | +| value_loss | 0.000154 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.278 | +| time/ | | +| fps | 1385 | +| iterations | 4001 | +| time_elapsed | 5914 | +| total_timesteps | 8194048 | +| train/ | | +| approx_kl | 0.003649481 | +| clip_fraction | 0.247 | +| clip_range | 0.0476 | +| entropy_loss | -7.57 | +| explained_variance | -0.0128 | +| learning_rate | 3.78e-05 | +| loss | -0.0196 | +| n_updates | 16000 | +| policy_gradient_loss | -0.0121 | +| value_loss | 0.000153 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.271 | +| time/ | | +| fps | 1385 | +| iterations | 4002 | +| time_elapsed | 5915 | +| total_timesteps | 8196096 | +| train/ | | +| approx_kl | 0.0036801815 | +| clip_fraction | 0.27 | +| clip_range | 0.0476 | +| entropy_loss | -7.61 | +| explained_variance | -0.00891 | +| learning_rate | 3.78e-05 | +| loss | -0.0185 | +| n_updates | 16004 | +| policy_gradient_loss | -0.0128 | +| value_loss | 0.000126 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.271 | +| time/ | | +| fps | 1385 | +| iterations | 4003 | +| time_elapsed | 5917 | +| total_timesteps | 8198144 | +| train/ | | +| approx_kl | 0.0037568624 | +| clip_fraction | 0.272 | +| clip_range | 0.0475 | +| entropy_loss | -7.69 | +| explained_variance | -0.0774 | +| learning_rate | 3.77e-05 | +| loss | -0.018 | +| n_updates | 16008 | +| policy_gradient_loss | -0.0116 | +| value_loss | 0.000237 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.276 | +| time/ | | +| fps | 1385 | +| iterations | 4004 | +| time_elapsed | 5918 | +| total_timesteps | 8200192 | +| train/ | | +| approx_kl | 0.0038603365 | +| clip_fraction | 0.249 | +| clip_range | 0.0475 | +| entropy_loss | -7.67 | +| explained_variance | -0.0136 | +| learning_rate | 3.77e-05 | +| loss | -0.021 | +| n_updates | 16012 | +| policy_gradient_loss | -0.012 | +| value_loss | 0.000189 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.276 | +| time/ | | +| fps | 1385 | +| iterations | 4005 | +| time_elapsed | 5920 | +| total_timesteps | 8202240 | +| train/ | | +| approx_kl | 0.004231966 | +| clip_fraction | 0.279 | +| clip_range | 0.0475 | +| entropy_loss | -7.61 | +| explained_variance | -0.0482 | +| learning_rate | 3.76e-05 | +| loss | -0.0193 | +| n_updates | 16016 | +| policy_gradient_loss | -0.0125 | +| value_loss | 0.000134 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 1385 | +| iterations | 4006 | +| time_elapsed | 5921 | +| total_timesteps | 8204288 | +| train/ | | +| approx_kl | 0.0038470146 | +| clip_fraction | 0.26 | +| clip_range | 0.0475 | +| entropy_loss | -7.79 | +| explained_variance | 0.0207 | +| learning_rate | 3.76e-05 | +| loss | -0.0172 | +| n_updates | 16020 | +| policy_gradient_loss | -0.0113 | +| value_loss | 0.000215 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.284 | +| time/ | | +| fps | 1385 | +| iterations | 4007 | +| time_elapsed | 5923 | +| total_timesteps | 8206336 | +| train/ | | +| approx_kl | 0.0036722235 | +| clip_fraction | 0.266 | +| clip_range | 0.0474 | +| entropy_loss | -7.55 | +| explained_variance | 0.105 | +| learning_rate | 3.76e-05 | +| loss | -0.0214 | +| n_updates | 16024 | +| policy_gradient_loss | -0.0127 | +| value_loss | 0.000172 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.288 | +| time/ | | +| fps | 1385 | +| iterations | 4008 | +| time_elapsed | 5925 | +| total_timesteps | 8208384 | +| train/ | | +| approx_kl | 0.0036918696 | +| clip_fraction | 0.251 | +| clip_range | 0.0474 | +| entropy_loss | -7.55 | +| explained_variance | 0.0571 | +| learning_rate | 3.75e-05 | +| loss | -0.02 | +| n_updates | 16028 | +| policy_gradient_loss | -0.0122 | +| value_loss | 0.00019 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.288 | +| time/ | | +| fps | 1385 | +| iterations | 4009 | +| time_elapsed | 5926 | +| total_timesteps | 8210432 | +| train/ | | +| approx_kl | 0.0030572559 | +| clip_fraction | 0.244 | +| clip_range | 0.0474 | +| entropy_loss | -7.62 | +| explained_variance | 0.0381 | +| learning_rate | 3.75e-05 | +| loss | -0.0171 | +| n_updates | 16032 | +| policy_gradient_loss | -0.0114 | +| value_loss | 0.000304 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 1385 | +| iterations | 4010 | +| time_elapsed | 5928 | +| total_timesteps | 8212480 | +| train/ | | +| approx_kl | 0.0041085677 | +| clip_fraction | 0.309 | +| clip_range | 0.0474 | +| entropy_loss | -7.61 | +| explained_variance | -0.0286 | +| learning_rate | 3.74e-05 | +| loss | -0.0228 | +| n_updates | 16036 | +| policy_gradient_loss | -0.0144 | +| value_loss | 9.62e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 1385 | +| iterations | 4011 | +| time_elapsed | 5929 | +| total_timesteps | 8214528 | +| train/ | | +| approx_kl | 0.003790586 | +| clip_fraction | 0.268 | +| clip_range | 0.0473 | +| entropy_loss | -7.59 | +| explained_variance | -0.0188 | +| learning_rate | 3.74e-05 | +| loss | -0.0216 | +| n_updates | 16040 | +| policy_gradient_loss | -0.0128 | +| value_loss | 0.000254 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.272 | +| time/ | | +| fps | 1385 | +| iterations | 4012 | +| time_elapsed | 5931 | +| total_timesteps | 8216576 | +| train/ | | +| approx_kl | 0.0036025275 | +| clip_fraction | 0.275 | +| clip_range | 0.0473 | +| entropy_loss | -7.78 | +| explained_variance | -0.031 | +| learning_rate | 3.74e-05 | +| loss | -0.0197 | +| n_updates | 16044 | +| policy_gradient_loss | -0.0124 | +| value_loss | 0.000198 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.272 | +| time/ | | +| fps | 1385 | +| iterations | 4013 | +| time_elapsed | 5932 | +| total_timesteps | 8218624 | +| train/ | | +| approx_kl | 0.0041170856 | +| clip_fraction | 0.266 | +| clip_range | 0.0473 | +| entropy_loss | -7.78 | +| explained_variance | -0.101 | +| learning_rate | 3.73e-05 | +| loss | -0.023 | +| n_updates | 16048 | +| policy_gradient_loss | -0.0136 | +| value_loss | 0.000111 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.274 | +| time/ | | +| fps | 1385 | +| iterations | 4014 | +| time_elapsed | 5933 | +| total_timesteps | 8220672 | +| train/ | | +| approx_kl | 0.004034187 | +| clip_fraction | 0.288 | +| clip_range | 0.0473 | +| entropy_loss | -7.75 | +| explained_variance | -0.17 | +| learning_rate | 3.73e-05 | +| loss | -0.0234 | +| n_updates | 16052 | +| policy_gradient_loss | -0.0143 | +| value_loss | 0.000103 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.27 | +| time/ | | +| fps | 1385 | +| iterations | 4015 | +| time_elapsed | 5935 | +| total_timesteps | 8222720 | +| train/ | | +| approx_kl | 0.0034529339 | +| clip_fraction | 0.268 | +| clip_range | 0.0472 | +| entropy_loss | -7.71 | +| explained_variance | 0.0406 | +| learning_rate | 3.72e-05 | +| loss | -0.0193 | +| n_updates | 16056 | +| policy_gradient_loss | -0.0119 | +| value_loss | 0.000272 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.265 | +| time/ | | +| fps | 1385 | +| iterations | 4016 | +| time_elapsed | 5936 | +| total_timesteps | 8224768 | +| train/ | | +| approx_kl | 0.0035344553 | +| clip_fraction | 0.279 | +| clip_range | 0.0472 | +| entropy_loss | -7.64 | +| explained_variance | -0.138 | +| learning_rate | 3.72e-05 | +| loss | -0.0255 | +| n_updates | 16060 | +| policy_gradient_loss | -0.0139 | +| value_loss | 8.47e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.263 | +| time/ | | +| fps | 1385 | +| iterations | 4017 | +| time_elapsed | 5938 | +| total_timesteps | 8226816 | +| train/ | | +| approx_kl | 0.004000707 | +| clip_fraction | 0.261 | +| clip_range | 0.0472 | +| entropy_loss | -7.65 | +| explained_variance | 0.0204 | +| learning_rate | 3.71e-05 | +| loss | -0.0193 | +| n_updates | 16064 | +| policy_gradient_loss | -0.0115 | +| value_loss | 0.000163 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.265 | +| time/ | | +| fps | 1385 | +| iterations | 4018 | +| time_elapsed | 5939 | +| total_timesteps | 8228864 | +| train/ | | +| approx_kl | 0.0037397686 | +| clip_fraction | 0.27 | +| clip_range | 0.0472 | +| entropy_loss | -7.71 | +| explained_variance | -0.0385 | +| learning_rate | 3.71e-05 | +| loss | -0.02 | +| n_updates | 16068 | +| policy_gradient_loss | -0.0121 | +| value_loss | 0.000213 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.274 | +| time/ | | +| fps | 1385 | +| iterations | 4019 | +| time_elapsed | 5941 | +| total_timesteps | 8230912 | +| train/ | | +| approx_kl | 0.004183739 | +| clip_fraction | 0.275 | +| clip_range | 0.0471 | +| entropy_loss | -7.6 | +| explained_variance | -0.0799 | +| learning_rate | 3.71e-05 | +| loss | -0.0205 | +| n_updates | 16072 | +| policy_gradient_loss | -0.0124 | +| value_loss | 0.000353 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.281 | +| time/ | | +| fps | 1385 | +| iterations | 4020 | +| time_elapsed | 5942 | +| total_timesteps | 8232960 | +| train/ | | +| approx_kl | 0.003868182 | +| clip_fraction | 0.275 | +| clip_range | 0.0471 | +| entropy_loss | -7.36 | +| explained_variance | -0.00575 | +| learning_rate | 3.7e-05 | +| loss | -0.0181 | +| n_updates | 16076 | +| policy_gradient_loss | -0.0125 | +| value_loss | 0.00034 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.281 | +| time/ | | +| fps | 1385 | +| iterations | 4021 | +| time_elapsed | 5944 | +| total_timesteps | 8235008 | +| train/ | | +| approx_kl | 0.0034738565 | +| clip_fraction | 0.278 | +| clip_range | 0.0471 | +| entropy_loss | -7.62 | +| explained_variance | -0.021 | +| learning_rate | 3.7e-05 | +| loss | -0.0177 | +| n_updates | 16080 | +| policy_gradient_loss | -0.0105 | +| value_loss | 0.000315 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.285 | +| time/ | | +| fps | 1385 | +| iterations | 4022 | +| time_elapsed | 5945 | +| total_timesteps | 8237056 | +| train/ | | +| approx_kl | 0.0041177524 | +| clip_fraction | 0.271 | +| clip_range | 0.0471 | +| entropy_loss | -7.76 | +| explained_variance | -0.214 | +| learning_rate | 3.69e-05 | +| loss | -0.0225 | +| n_updates | 16084 | +| policy_gradient_loss | -0.0128 | +| value_loss | 0.000171 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.285 | +| time/ | | +| fps | 1385 | +| iterations | 4023 | +| time_elapsed | 5947 | +| total_timesteps | 8239104 | +| train/ | | +| approx_kl | 0.00364711 | +| clip_fraction | 0.275 | +| clip_range | 0.047 | +| entropy_loss | -7.74 | +| explained_variance | 0.00621 | +| learning_rate | 3.69e-05 | +| loss | -0.0203 | +| n_updates | 16088 | +| policy_gradient_loss | -0.012 | +| value_loss | 0.000281 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.284 | +| time/ | | +| fps | 1385 | +| iterations | 4024 | +| time_elapsed | 5948 | +| total_timesteps | 8241152 | +| train/ | | +| approx_kl | 0.0040318673 | +| clip_fraction | 0.27 | +| clip_range | 0.047 | +| entropy_loss | -7.86 | +| explained_variance | -0.0495 | +| learning_rate | 3.69e-05 | +| loss | -0.0203 | +| n_updates | 16092 | +| policy_gradient_loss | -0.0128 | +| value_loss | 0.000219 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.287 | +| time/ | | +| fps | 1385 | +| iterations | 4025 | +| time_elapsed | 5950 | +| total_timesteps | 8243200 | +| train/ | | +| approx_kl | 0.0041767033 | +| clip_fraction | 0.284 | +| clip_range | 0.047 | +| entropy_loss | -7.73 | +| explained_variance | -0.131 | +| learning_rate | 3.68e-05 | +| loss | -0.0225 | +| n_updates | 16096 | +| policy_gradient_loss | -0.0136 | +| value_loss | 0.00015 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.291 | +| time/ | | +| fps | 1385 | +| iterations | 4026 | +| time_elapsed | 5951 | +| total_timesteps | 8245248 | +| train/ | | +| approx_kl | 0.003365123 | +| clip_fraction | 0.252 | +| clip_range | 0.047 | +| entropy_loss | -7.67 | +| explained_variance | 0.0219 | +| learning_rate | 3.68e-05 | +| loss | -0.0161 | +| n_updates | 16100 | +| policy_gradient_loss | -0.0117 | +| value_loss | 0.000227 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.294 | +| time/ | | +| fps | 1385 | +| iterations | 4027 | +| time_elapsed | 5953 | +| total_timesteps | 8247296 | +| train/ | | +| approx_kl | 0.0039927093 | +| clip_fraction | 0.271 | +| clip_range | 0.0469 | +| entropy_loss | -7.78 | +| explained_variance | -0.0384 | +| learning_rate | 3.67e-05 | +| loss | -0.0201 | +| n_updates | 16104 | +| policy_gradient_loss | -0.0128 | +| value_loss | 0.000219 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.302 | +| time/ | | +| fps | 1385 | +| iterations | 4028 | +| time_elapsed | 5954 | +| total_timesteps | 8249344 | +| train/ | | +| approx_kl | 0.0036310507 | +| clip_fraction | 0.243 | +| clip_range | 0.0469 | +| entropy_loss | -7.63 | +| explained_variance | -0.0775 | +| learning_rate | 3.67e-05 | +| loss | -0.0215 | +| n_updates | 16108 | +| policy_gradient_loss | -0.0117 | +| value_loss | 0.000201 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.306 | +| time/ | | +| fps | 1385 | +| iterations | 4029 | +| time_elapsed | 5956 | +| total_timesteps | 8251392 | +| train/ | | +| approx_kl | 0.00376622 | +| clip_fraction | 0.259 | +| clip_range | 0.0469 | +| entropy_loss | -7.35 | +| explained_variance | -0.00638 | +| learning_rate | 3.67e-05 | +| loss | -0.0162 | +| n_updates | 16112 | +| policy_gradient_loss | -0.012 | +| value_loss | 0.000201 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.306 | +| time/ | | +| fps | 1385 | +| iterations | 4030 | +| time_elapsed | 5957 | +| total_timesteps | 8253440 | +| train/ | | +| approx_kl | 0.0034429552 | +| clip_fraction | 0.267 | +| clip_range | 0.0469 | +| entropy_loss | -7.67 | +| explained_variance | -0.00848 | +| learning_rate | 3.66e-05 | +| loss | -0.0135 | +| n_updates | 16116 | +| policy_gradient_loss | -0.0106 | +| value_loss | 0.000388 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1385 | +| iterations | 4031 | +| time_elapsed | 5959 | +| total_timesteps | 8255488 | +| train/ | | +| approx_kl | 0.0045184297 | +| clip_fraction | 0.299 | +| clip_range | 0.0468 | +| entropy_loss | -7.8 | +| explained_variance | -0.0928 | +| learning_rate | 3.66e-05 | +| loss | -0.0269 | +| n_updates | 16120 | +| policy_gradient_loss | -0.014 | +| value_loss | 0.000135 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1385 | +| iterations | 4032 | +| time_elapsed | 5960 | +| total_timesteps | 8257536 | +| train/ | | +| approx_kl | 0.0029883394 | +| clip_fraction | 0.252 | +| clip_range | 0.0468 | +| entropy_loss | -7.75 | +| explained_variance | -0.0376 | +| learning_rate | 3.65e-05 | +| loss | -0.0145 | +| n_updates | 16124 | +| policy_gradient_loss | -0.0118 | +| value_loss | 0.00019 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 1385 | +| iterations | 4033 | +| time_elapsed | 5961 | +| total_timesteps | 8259584 | +| train/ | | +| approx_kl | 0.0037926065 | +| clip_fraction | 0.275 | +| clip_range | 0.0468 | +| entropy_loss | -7.83 | +| explained_variance | -0.0927 | +| learning_rate | 3.65e-05 | +| loss | -0.0247 | +| n_updates | 16128 | +| policy_gradient_loss | -0.0129 | +| value_loss | 0.000144 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.306 | +| time/ | | +| fps | 1385 | +| iterations | 4034 | +| time_elapsed | 5963 | +| total_timesteps | 8261632 | +| train/ | | +| approx_kl | 0.0038416241 | +| clip_fraction | 0.279 | +| clip_range | 0.0468 | +| entropy_loss | -7.58 | +| explained_variance | 0.0975 | +| learning_rate | 3.65e-05 | +| loss | -0.0211 | +| n_updates | 16132 | +| policy_gradient_loss | -0.0134 | +| value_loss | 0.000136 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1385 | +| iterations | 4035 | +| time_elapsed | 5964 | +| total_timesteps | 8263680 | +| train/ | | +| approx_kl | 0.0036538676 | +| clip_fraction | 0.264 | +| clip_range | 0.0467 | +| entropy_loss | -7.49 | +| explained_variance | 0.0389 | +| learning_rate | 3.64e-05 | +| loss | -0.0171 | +| n_updates | 16136 | +| policy_gradient_loss | -0.0107 | +| value_loss | 0.00032 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1385 | +| iterations | 4036 | +| time_elapsed | 5966 | +| total_timesteps | 8265728 | +| train/ | | +| approx_kl | 0.0032606656 | +| clip_fraction | 0.263 | +| clip_range | 0.0467 | +| entropy_loss | -7.72 | +| explained_variance | 0.0227 | +| learning_rate | 3.64e-05 | +| loss | -0.0218 | +| n_updates | 16140 | +| policy_gradient_loss | -0.0123 | +| value_loss | 0.000326 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.304 | +| time/ | | +| fps | 1385 | +| iterations | 4037 | +| time_elapsed | 5967 | +| total_timesteps | 8267776 | +| train/ | | +| approx_kl | 0.0040188255 | +| clip_fraction | 0.294 | +| clip_range | 0.0467 | +| entropy_loss | -7.61 | +| explained_variance | 0.025 | +| learning_rate | 3.63e-05 | +| loss | -0.0201 | +| n_updates | 16144 | +| policy_gradient_loss | -0.0137 | +| value_loss | 0.000119 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 1385 | +| iterations | 4038 | +| time_elapsed | 5969 | +| total_timesteps | 8269824 | +| train/ | | +| approx_kl | 0.0036715567 | +| clip_fraction | 0.282 | +| clip_range | 0.0467 | +| entropy_loss | -7.61 | +| explained_variance | -0.008 | +| learning_rate | 3.63e-05 | +| loss | -0.0225 | +| n_updates | 16148 | +| policy_gradient_loss | -0.0139 | +| value_loss | 0.000219 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1385 | +| iterations | 4039 | +| time_elapsed | 5970 | +| total_timesteps | 8271872 | +| train/ | | +| approx_kl | 0.0034110704 | +| clip_fraction | 0.274 | +| clip_range | 0.0466 | +| entropy_loss | -7.67 | +| explained_variance | -0.0182 | +| learning_rate | 3.63e-05 | +| loss | -0.0214 | +| n_updates | 16152 | +| policy_gradient_loss | -0.0131 | +| value_loss | 0.000204 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1385 | +| iterations | 4040 | +| time_elapsed | 5972 | +| total_timesteps | 8273920 | +| train/ | | +| approx_kl | 0.003532459 | +| clip_fraction | 0.26 | +| clip_range | 0.0466 | +| entropy_loss | -7.6 | +| explained_variance | 0.0445 | +| learning_rate | 3.62e-05 | +| loss | -0.0157 | +| n_updates | 16156 | +| policy_gradient_loss | -0.0111 | +| value_loss | 0.000532 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1385 | +| iterations | 4041 | +| time_elapsed | 5973 | +| total_timesteps | 8275968 | +| train/ | | +| approx_kl | 0.0033207587 | +| clip_fraction | 0.277 | +| clip_range | 0.0466 | +| entropy_loss | -7.65 | +| explained_variance | -0.107 | +| learning_rate | 3.62e-05 | +| loss | -0.0216 | +| n_updates | 16160 | +| policy_gradient_loss | -0.0136 | +| value_loss | 0.000125 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1385 | +| iterations | 4042 | +| time_elapsed | 5975 | +| total_timesteps | 8278016 | +| train/ | | +| approx_kl | 0.0037064077 | +| clip_fraction | 0.281 | +| clip_range | 0.0466 | +| entropy_loss | -7.71 | +| explained_variance | -0.0905 | +| learning_rate | 3.61e-05 | +| loss | -0.02 | +| n_updates | 16164 | +| policy_gradient_loss | -0.0123 | +| value_loss | 0.000214 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1385 | +| iterations | 4043 | +| time_elapsed | 5976 | +| total_timesteps | 8280064 | +| train/ | | +| approx_kl | 0.0035194894 | +| clip_fraction | 0.276 | +| clip_range | 0.0465 | +| entropy_loss | -7.75 | +| explained_variance | -0.169 | +| learning_rate | 3.61e-05 | +| loss | -0.019 | +| n_updates | 16168 | +| policy_gradient_loss | -0.0132 | +| value_loss | 0.000134 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1385 | +| iterations | 4044 | +| time_elapsed | 5977 | +| total_timesteps | 8282112 | +| train/ | | +| approx_kl | 0.003819407 | +| clip_fraction | 0.268 | +| clip_range | 0.0465 | +| entropy_loss | -7.59 | +| explained_variance | -0.0458 | +| learning_rate | 3.61e-05 | +| loss | -0.0194 | +| n_updates | 16172 | +| policy_gradient_loss | -0.0119 | +| value_loss | 0.000202 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1385 | +| iterations | 4045 | +| time_elapsed | 5979 | +| total_timesteps | 8284160 | +| train/ | | +| approx_kl | 0.0036994554 | +| clip_fraction | 0.266 | +| clip_range | 0.0465 | +| entropy_loss | -7.77 | +| explained_variance | -0.0468 | +| learning_rate | 3.6e-05 | +| loss | -0.019 | +| n_updates | 16176 | +| policy_gradient_loss | -0.0123 | +| value_loss | 0.000174 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1385 | +| iterations | 4046 | +| time_elapsed | 5980 | +| total_timesteps | 8286208 | +| train/ | | +| approx_kl | 0.0033332522 | +| clip_fraction | 0.259 | +| clip_range | 0.0464 | +| entropy_loss | -7.65 | +| explained_variance | 0.00187 | +| learning_rate | 3.6e-05 | +| loss | -0.0196 | +| n_updates | 16180 | +| policy_gradient_loss | -0.0125 | +| value_loss | 0.000203 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 1385 | +| iterations | 4047 | +| time_elapsed | 5982 | +| total_timesteps | 8288256 | +| train/ | | +| approx_kl | 0.0030612666 | +| clip_fraction | 0.275 | +| clip_range | 0.0464 | +| entropy_loss | -7.85 | +| explained_variance | -0.15 | +| learning_rate | 3.59e-05 | +| loss | -0.0179 | +| n_updates | 16184 | +| policy_gradient_loss | -0.0118 | +| value_loss | 9.9e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1385 | +| iterations | 4048 | +| time_elapsed | 5983 | +| total_timesteps | 8290304 | +| train/ | | +| approx_kl | 0.003405328 | +| clip_fraction | 0.258 | +| clip_range | 0.0464 | +| entropy_loss | -7.62 | +| explained_variance | 0.0222 | +| learning_rate | 3.59e-05 | +| loss | -0.0185 | +| n_updates | 16188 | +| policy_gradient_loss | -0.0124 | +| value_loss | 0.000164 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1385 | +| iterations | 4049 | +| time_elapsed | 5985 | +| total_timesteps | 8292352 | +| train/ | | +| approx_kl | 0.0035304122 | +| clip_fraction | 0.239 | +| clip_range | 0.0464 | +| entropy_loss | -7.58 | +| explained_variance | 0.0839 | +| learning_rate | 3.59e-05 | +| loss | -0.02 | +| n_updates | 16192 | +| policy_gradient_loss | -0.0121 | +| value_loss | 0.000225 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1385 | +| iterations | 4050 | +| time_elapsed | 5986 | +| total_timesteps | 8294400 | +| train/ | | +| approx_kl | 0.0036826998 | +| clip_fraction | 0.276 | +| clip_range | 0.0463 | +| entropy_loss | -7.64 | +| explained_variance | -0.169 | +| learning_rate | 3.58e-05 | +| loss | -0.0224 | +| n_updates | 16196 | +| policy_gradient_loss | -0.0136 | +| value_loss | 0.000121 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1385 | +| iterations | 4051 | +| time_elapsed | 5988 | +| total_timesteps | 8296448 | +| train/ | | +| approx_kl | 0.003676311 | +| clip_fraction | 0.251 | +| clip_range | 0.0463 | +| entropy_loss | -7.63 | +| explained_variance | 0.0156 | +| learning_rate | 3.58e-05 | +| loss | -0.0177 | +| n_updates | 16200 | +| policy_gradient_loss | -0.0106 | +| value_loss | 0.000167 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1385 | +| iterations | 4052 | +| time_elapsed | 5989 | +| total_timesteps | 8298496 | +| train/ | | +| approx_kl | 0.0034245683 | +| clip_fraction | 0.252 | +| clip_range | 0.0463 | +| entropy_loss | -7.81 | +| explained_variance | -0.144 | +| learning_rate | 3.57e-05 | +| loss | -0.0209 | +| n_updates | 16204 | +| policy_gradient_loss | -0.0124 | +| value_loss | 0.000128 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1385 | +| iterations | 4053 | +| time_elapsed | 5991 | +| total_timesteps | 8300544 | +| train/ | | +| approx_kl | 0.0036618817 | +| clip_fraction | 0.259 | +| clip_range | 0.0463 | +| entropy_loss | -7.65 | +| explained_variance | -0.0977 | +| learning_rate | 3.57e-05 | +| loss | -0.0206 | +| n_updates | 16208 | +| policy_gradient_loss | -0.0124 | +| value_loss | 0.000137 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1385 | +| iterations | 4054 | +| time_elapsed | 5992 | +| total_timesteps | 8302592 | +| train/ | | +| approx_kl | 0.0033480064 | +| clip_fraction | 0.25 | +| clip_range | 0.0462 | +| entropy_loss | -7.69 | +| explained_variance | -0.0268 | +| learning_rate | 3.56e-05 | +| loss | -0.0218 | +| n_updates | 16212 | +| policy_gradient_loss | -0.0119 | +| value_loss | 0.000146 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1385 | +| iterations | 4055 | +| time_elapsed | 5994 | +| total_timesteps | 8304640 | +| train/ | | +| approx_kl | 0.0032511682 | +| clip_fraction | 0.275 | +| clip_range | 0.0462 | +| entropy_loss | -7.73 | +| explained_variance | -0.0118 | +| learning_rate | 3.56e-05 | +| loss | -0.0204 | +| n_updates | 16216 | +| policy_gradient_loss | -0.0123 | +| value_loss | 0.000271 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1385 | +| iterations | 4056 | +| time_elapsed | 5995 | +| total_timesteps | 8306688 | +| train/ | | +| approx_kl | 0.0031496976 | +| clip_fraction | 0.249 | +| clip_range | 0.0462 | +| entropy_loss | -7.57 | +| explained_variance | 0.0515 | +| learning_rate | 3.56e-05 | +| loss | -0.0198 | +| n_updates | 16220 | +| policy_gradient_loss | -0.0113 | +| value_loss | 0.00026 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1385 | +| iterations | 4057 | +| time_elapsed | 5996 | +| total_timesteps | 8308736 | +| train/ | | +| approx_kl | 0.003272654 | +| clip_fraction | 0.267 | +| clip_range | 0.0462 | +| entropy_loss | -7.65 | +| explained_variance | -0.109 | +| learning_rate | 3.55e-05 | +| loss | -0.0194 | +| n_updates | 16224 | +| policy_gradient_loss | -0.0123 | +| value_loss | 0.000221 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1385 | +| iterations | 4058 | +| time_elapsed | 5998 | +| total_timesteps | 8310784 | +| train/ | | +| approx_kl | 0.0032520166 | +| clip_fraction | 0.251 | +| clip_range | 0.0461 | +| entropy_loss | -7.84 | +| explained_variance | -0.0721 | +| learning_rate | 3.55e-05 | +| loss | -0.0194 | +| n_updates | 16228 | +| policy_gradient_loss | -0.0129 | +| value_loss | 0.000254 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.315 | +| time/ | | +| fps | 1385 | +| iterations | 4059 | +| time_elapsed | 5999 | +| total_timesteps | 8312832 | +| train/ | | +| approx_kl | 0.0029716324 | +| clip_fraction | 0.257 | +| clip_range | 0.0461 | +| entropy_loss | -7.78 | +| explained_variance | -0.0995 | +| learning_rate | 3.54e-05 | +| loss | -0.0239 | +| n_updates | 16232 | +| policy_gradient_loss | -0.0121 | +| value_loss | 0.000104 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1385 | +| iterations | 4060 | +| time_elapsed | 6001 | +| total_timesteps | 8314880 | +| train/ | | +| approx_kl | 0.0035053005 | +| clip_fraction | 0.278 | +| clip_range | 0.0461 | +| entropy_loss | -7.68 | +| explained_variance | -0.0437 | +| learning_rate | 3.54e-05 | +| loss | -0.0186 | +| n_updates | 16236 | +| policy_gradient_loss | -0.0135 | +| value_loss | 0.000117 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1385 | +| iterations | 4061 | +| time_elapsed | 6002 | +| total_timesteps | 8316928 | +| train/ | | +| approx_kl | 0.0026991656 | +| clip_fraction | 0.237 | +| clip_range | 0.0461 | +| entropy_loss | -7.71 | +| explained_variance | -0.0536 | +| learning_rate | 3.54e-05 | +| loss | -0.0161 | +| n_updates | 16240 | +| policy_gradient_loss | -0.0108 | +| value_loss | 0.000154 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1385 | +| iterations | 4062 | +| time_elapsed | 6004 | +| total_timesteps | 8318976 | +| train/ | | +| approx_kl | 0.0034425785 | +| clip_fraction | 0.253 | +| clip_range | 0.046 | +| entropy_loss | -7.75 | +| explained_variance | 0.0313 | +| learning_rate | 3.53e-05 | +| loss | -0.015 | +| n_updates | 16244 | +| policy_gradient_loss | -0.0109 | +| value_loss | 0.000187 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1385 | +| iterations | 4063 | +| time_elapsed | 6005 | +| total_timesteps | 8321024 | +| train/ | | +| approx_kl | 0.003442159 | +| clip_fraction | 0.256 | +| clip_range | 0.046 | +| entropy_loss | -7.53 | +| explained_variance | -0.0198 | +| learning_rate | 3.53e-05 | +| loss | -0.0153 | +| n_updates | 16248 | +| policy_gradient_loss | -0.0123 | +| value_loss | 0.000124 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.315 | +| time/ | | +| fps | 1385 | +| iterations | 4064 | +| time_elapsed | 6007 | +| total_timesteps | 8323072 | +| train/ | | +| approx_kl | 0.0034886491 | +| clip_fraction | 0.286 | +| clip_range | 0.046 | +| entropy_loss | -7.68 | +| explained_variance | 0.0616 | +| learning_rate | 3.52e-05 | +| loss | -0.0163 | +| n_updates | 16252 | +| policy_gradient_loss | -0.012 | +| value_loss | 0.000179 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.315 | +| time/ | | +| fps | 1385 | +| iterations | 4065 | +| time_elapsed | 6008 | +| total_timesteps | 8325120 | +| train/ | | +| approx_kl | 0.003819772 | +| clip_fraction | 0.268 | +| clip_range | 0.046 | +| entropy_loss | -7.72 | +| explained_variance | -0.14 | +| learning_rate | 3.52e-05 | +| loss | -0.0193 | +| n_updates | 16256 | +| policy_gradient_loss | -0.0113 | +| value_loss | 0.000135 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1385 | +| iterations | 4066 | +| time_elapsed | 6010 | +| total_timesteps | 8327168 | +| train/ | | +| approx_kl | 0.0037604154 | +| clip_fraction | 0.288 | +| clip_range | 0.0459 | +| entropy_loss | -7.74 | +| explained_variance | -0.0661 | +| learning_rate | 3.52e-05 | +| loss | -0.0222 | +| n_updates | 16260 | +| policy_gradient_loss | -0.0128 | +| value_loss | 0.000164 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.315 | +| time/ | | +| fps | 1385 | +| iterations | 4067 | +| time_elapsed | 6011 | +| total_timesteps | 8329216 | +| train/ | | +| approx_kl | 0.003457643 | +| clip_fraction | 0.275 | +| clip_range | 0.0459 | +| entropy_loss | -7.71 | +| explained_variance | -0.0389 | +| learning_rate | 3.51e-05 | +| loss | -0.0184 | +| n_updates | 16264 | +| policy_gradient_loss | -0.0129 | +| value_loss | 0.000269 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.315 | +| time/ | | +| fps | 1385 | +| iterations | 4068 | +| time_elapsed | 6013 | +| total_timesteps | 8331264 | +| train/ | | +| approx_kl | 0.0028618113 | +| clip_fraction | 0.241 | +| clip_range | 0.0459 | +| entropy_loss | -7.86 | +| explained_variance | -0.0433 | +| learning_rate | 3.51e-05 | +| loss | -0.0197 | +| n_updates | 16268 | +| policy_gradient_loss | -0.0119 | +| value_loss | 0.000206 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1385 | +| iterations | 4069 | +| time_elapsed | 6014 | +| total_timesteps | 8333312 | +| train/ | | +| approx_kl | 0.0031544412 | +| clip_fraction | 0.254 | +| clip_range | 0.0459 | +| entropy_loss | -7.79 | +| explained_variance | -0.0483 | +| learning_rate | 3.5e-05 | +| loss | -0.0223 | +| n_updates | 16272 | +| policy_gradient_loss | -0.0121 | +| value_loss | 0.000247 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1385 | +| iterations | 4070 | +| time_elapsed | 6016 | +| total_timesteps | 8335360 | +| train/ | | +| approx_kl | 0.0036059048 | +| clip_fraction | 0.259 | +| clip_range | 0.0458 | +| entropy_loss | -7.77 | +| explained_variance | -0.135 | +| learning_rate | 3.5e-05 | +| loss | -0.0168 | +| n_updates | 16276 | +| policy_gradient_loss | -0.0121 | +| value_loss | 0.000143 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1385 | +| iterations | 4071 | +| time_elapsed | 6017 | +| total_timesteps | 8337408 | +| train/ | | +| approx_kl | 0.0031399848 | +| clip_fraction | 0.247 | +| clip_range | 0.0458 | +| entropy_loss | -7.64 | +| explained_variance | -0.0915 | +| learning_rate | 3.5e-05 | +| loss | -0.0205 | +| n_updates | 16280 | +| policy_gradient_loss | -0.0116 | +| value_loss | 0.000242 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1385 | +| iterations | 4072 | +| time_elapsed | 6019 | +| total_timesteps | 8339456 | +| train/ | | +| approx_kl | 0.0031162607 | +| clip_fraction | 0.252 | +| clip_range | 0.0458 | +| entropy_loss | -7.61 | +| explained_variance | -0.026 | +| learning_rate | 3.49e-05 | +| loss | -0.0197 | +| n_updates | 16284 | +| policy_gradient_loss | -0.011 | +| value_loss | 0.000253 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1385 | +| iterations | 4073 | +| time_elapsed | 6021 | +| total_timesteps | 8341504 | +| train/ | | +| approx_kl | 0.003135729 | +| clip_fraction | 0.263 | +| clip_range | 0.0458 | +| entropy_loss | -7.57 | +| explained_variance | 0.0462 | +| learning_rate | 3.49e-05 | +| loss | -0.022 | +| n_updates | 16288 | +| policy_gradient_loss | -0.0121 | +| value_loss | 0.00018 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1385 | +| iterations | 4074 | +| time_elapsed | 6022 | +| total_timesteps | 8343552 | +| train/ | | +| approx_kl | 0.0032466855 | +| clip_fraction | 0.263 | +| clip_range | 0.0457 | +| entropy_loss | -7.58 | +| explained_variance | 0.0519 | +| learning_rate | 3.48e-05 | +| loss | -0.0199 | +| n_updates | 16292 | +| policy_gradient_loss | -0.012 | +| value_loss | 0.000167 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1385 | +| iterations | 4075 | +| time_elapsed | 6024 | +| total_timesteps | 8345600 | +| train/ | | +| approx_kl | 0.0031586494 | +| clip_fraction | 0.247 | +| clip_range | 0.0457 | +| entropy_loss | -7.74 | +| explained_variance | -0.0686 | +| learning_rate | 3.48e-05 | +| loss | -0.0175 | +| n_updates | 16296 | +| policy_gradient_loss | -0.011 | +| value_loss | 0.000266 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1385 | +| iterations | 4076 | +| time_elapsed | 6025 | +| total_timesteps | 8347648 | +| train/ | | +| approx_kl | 0.0035269246 | +| clip_fraction | 0.266 | +| clip_range | 0.0457 | +| entropy_loss | -7.64 | +| explained_variance | -0.0764 | +| learning_rate | 3.48e-05 | +| loss | -0.0213 | +| n_updates | 16300 | +| policy_gradient_loss | -0.0127 | +| value_loss | 0.000248 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1385 | +| iterations | 4077 | +| time_elapsed | 6027 | +| total_timesteps | 8349696 | +| train/ | | +| approx_kl | 0.0031321729 | +| clip_fraction | 0.265 | +| clip_range | 0.0457 | +| entropy_loss | -7.8 | +| explained_variance | -0.119 | +| learning_rate | 3.47e-05 | +| loss | -0.0184 | +| n_updates | 16304 | +| policy_gradient_loss | -0.0122 | +| value_loss | 0.000107 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1385 | +| iterations | 4078 | +| time_elapsed | 6028 | +| total_timesteps | 8351744 | +| train/ | | +| approx_kl | 0.0038249171 | +| clip_fraction | 0.289 | +| clip_range | 0.0456 | +| entropy_loss | -7.8 | +| explained_variance | -0.0912 | +| learning_rate | 3.47e-05 | +| loss | -0.0211 | +| n_updates | 16308 | +| policy_gradient_loss | -0.0133 | +| value_loss | 0.000168 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1385 | +| iterations | 4079 | +| time_elapsed | 6030 | +| total_timesteps | 8353792 | +| train/ | | +| approx_kl | 0.003714996 | +| clip_fraction | 0.249 | +| clip_range | 0.0456 | +| entropy_loss | -7.8 | +| explained_variance | -0.0485 | +| learning_rate | 3.46e-05 | +| loss | -0.0189 | +| n_updates | 16312 | +| policy_gradient_loss | -0.0119 | +| value_loss | 0.00016 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1385 | +| iterations | 4080 | +| time_elapsed | 6031 | +| total_timesteps | 8355840 | +| train/ | | +| approx_kl | 0.0032165796 | +| clip_fraction | 0.27 | +| clip_range | 0.0456 | +| entropy_loss | -7.84 | +| explained_variance | -0.117 | +| learning_rate | 3.46e-05 | +| loss | -0.0193 | +| n_updates | 16316 | +| policy_gradient_loss | -0.0116 | +| value_loss | 9.3e-05 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1385 | +| iterations | 4081 | +| time_elapsed | 6033 | +| total_timesteps | 8357888 | +| train/ | | +| approx_kl | 0.00332484 | +| clip_fraction | 0.267 | +| clip_range | 0.0456 | +| entropy_loss | -7.8 | +| explained_variance | -0.0738 | +| learning_rate | 3.46e-05 | +| loss | -0.0201 | +| n_updates | 16320 | +| policy_gradient_loss | -0.0125 | +| value_loss | 0.000291 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1385 | +| iterations | 4082 | +| time_elapsed | 6034 | +| total_timesteps | 8359936 | +| train/ | | +| approx_kl | 0.00323198 | +| clip_fraction | 0.276 | +| clip_range | 0.0455 | +| entropy_loss | -7.67 | +| explained_variance | 0.0705 | +| learning_rate | 3.45e-05 | +| loss | -0.0203 | +| n_updates | 16324 | +| policy_gradient_loss | -0.0134 | +| value_loss | 8.01e-05 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1385 | +| iterations | 4083 | +| time_elapsed | 6036 | +| total_timesteps | 8361984 | +| train/ | | +| approx_kl | 0.0032153267 | +| clip_fraction | 0.274 | +| clip_range | 0.0455 | +| entropy_loss | -7.58 | +| explained_variance | 0.0174 | +| learning_rate | 3.45e-05 | +| loss | -0.0235 | +| n_updates | 16328 | +| policy_gradient_loss | -0.0121 | +| value_loss | 0.000144 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1385 | +| iterations | 4084 | +| time_elapsed | 6037 | +| total_timesteps | 8364032 | +| train/ | | +| approx_kl | 0.0031163068 | +| clip_fraction | 0.244 | +| clip_range | 0.0455 | +| entropy_loss | -7.76 | +| explained_variance | -0.044 | +| learning_rate | 3.44e-05 | +| loss | -0.0152 | +| n_updates | 16332 | +| policy_gradient_loss | -0.0106 | +| value_loss | 0.000146 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1385 | +| iterations | 4085 | +| time_elapsed | 6039 | +| total_timesteps | 8366080 | +| train/ | | +| approx_kl | 0.003537332 | +| clip_fraction | 0.257 | +| clip_range | 0.0454 | +| entropy_loss | -7.39 | +| explained_variance | -0.00763 | +| learning_rate | 3.44e-05 | +| loss | -0.0172 | +| n_updates | 16336 | +| policy_gradient_loss | -0.0111 | +| value_loss | 0.000278 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1385 | +| iterations | 4086 | +| time_elapsed | 6040 | +| total_timesteps | 8368128 | +| train/ | | +| approx_kl | 0.0033546959 | +| clip_fraction | 0.27 | +| clip_range | 0.0454 | +| entropy_loss | -7.73 | +| explained_variance | -0.0907 | +| learning_rate | 3.44e-05 | +| loss | -0.0179 | +| n_updates | 16340 | +| policy_gradient_loss | -0.0115 | +| value_loss | 0.000113 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1385 | +| iterations | 4087 | +| time_elapsed | 6042 | +| total_timesteps | 8370176 | +| train/ | | +| approx_kl | 0.0033668813 | +| clip_fraction | 0.247 | +| clip_range | 0.0454 | +| entropy_loss | -7.64 | +| explained_variance | -0.0371 | +| learning_rate | 3.43e-05 | +| loss | -0.0179 | +| n_updates | 16344 | +| policy_gradient_loss | -0.0105 | +| value_loss | 0.000185 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1385 | +| iterations | 4088 | +| time_elapsed | 6044 | +| total_timesteps | 8372224 | +| train/ | | +| approx_kl | 0.003259382 | +| clip_fraction | 0.276 | +| clip_range | 0.0454 | +| entropy_loss | -7.83 | +| explained_variance | -0.0303 | +| learning_rate | 3.43e-05 | +| loss | -0.0189 | +| n_updates | 16348 | +| policy_gradient_loss | -0.0122 | +| value_loss | 0.000124 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1385 | +| iterations | 4089 | +| time_elapsed | 6045 | +| total_timesteps | 8374272 | +| train/ | | +| approx_kl | 0.0031331284 | +| clip_fraction | 0.268 | +| clip_range | 0.0453 | +| entropy_loss | -7.83 | +| explained_variance | -0.0862 | +| learning_rate | 3.42e-05 | +| loss | -0.0193 | +| n_updates | 16352 | +| policy_gradient_loss | -0.0112 | +| value_loss | 0.000161 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1385 | +| iterations | 4090 | +| time_elapsed | 6047 | +| total_timesteps | 8376320 | +| train/ | | +| approx_kl | 0.0032056496 | +| clip_fraction | 0.238 | +| clip_range | 0.0453 | +| entropy_loss | -7.7 | +| explained_variance | -0.0919 | +| learning_rate | 3.42e-05 | +| loss | -0.0193 | +| n_updates | 16356 | +| policy_gradient_loss | -0.0118 | +| value_loss | 0.000234 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1385 | +| iterations | 4091 | +| time_elapsed | 6048 | +| total_timesteps | 8378368 | +| train/ | | +| approx_kl | 0.0030235988 | +| clip_fraction | 0.248 | +| clip_range | 0.0453 | +| entropy_loss | -7.63 | +| explained_variance | 0.0458 | +| learning_rate | 3.41e-05 | +| loss | -0.0168 | +| n_updates | 16360 | +| policy_gradient_loss | -0.0105 | +| value_loss | 0.00017 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1385 | +| iterations | 4092 | +| time_elapsed | 6050 | +| total_timesteps | 8380416 | +| train/ | | +| approx_kl | 0.0035759797 | +| clip_fraction | 0.26 | +| clip_range | 0.0453 | +| entropy_loss | -7.79 | +| explained_variance | -0.0856 | +| learning_rate | 3.41e-05 | +| loss | -0.0191 | +| n_updates | 16364 | +| policy_gradient_loss | -0.0121 | +| value_loss | 0.000125 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1385 | +| iterations | 4093 | +| time_elapsed | 6051 | +| total_timesteps | 8382464 | +| train/ | | +| approx_kl | 0.0033438653 | +| clip_fraction | 0.254 | +| clip_range | 0.0452 | +| entropy_loss | -7.75 | +| explained_variance | -0.0076 | +| learning_rate | 3.41e-05 | +| loss | -0.0185 | +| n_updates | 16368 | +| policy_gradient_loss | -0.0123 | +| value_loss | 0.000117 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1385 | +| iterations | 4094 | +| time_elapsed | 6053 | +| total_timesteps | 8384512 | +| train/ | | +| approx_kl | 0.002929387 | +| clip_fraction | 0.251 | +| clip_range | 0.0452 | +| entropy_loss | -7.6 | +| explained_variance | -0.0282 | +| learning_rate | 3.4e-05 | +| loss | -0.0177 | +| n_updates | 16372 | +| policy_gradient_loss | -0.0115 | +| value_loss | 0.000279 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1385 | +| iterations | 4095 | +| time_elapsed | 6054 | +| total_timesteps | 8386560 | +| train/ | | +| approx_kl | 0.0034120595 | +| clip_fraction | 0.263 | +| clip_range | 0.0452 | +| entropy_loss | -7.71 | +| explained_variance | -0.0342 | +| learning_rate | 3.4e-05 | +| loss | -0.0222 | +| n_updates | 16376 | +| policy_gradient_loss | -0.0115 | +| value_loss | 0.000109 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1385 | +| iterations | 4096 | +| time_elapsed | 6056 | +| total_timesteps | 8388608 | +| train/ | | +| approx_kl | 0.003106879 | +| clip_fraction | 0.255 | +| clip_range | 0.0452 | +| entropy_loss | -7.78 | +| explained_variance | -0.00244 | +| learning_rate | 3.39e-05 | +| loss | -0.0181 | +| n_updates | 16380 | +| policy_gradient_loss | -0.0123 | +| value_loss | 0.000188 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1385 | +| iterations | 4097 | +| time_elapsed | 6057 | +| total_timesteps | 8390656 | +| train/ | | +| approx_kl | 0.0028461972 | +| clip_fraction | 0.256 | +| clip_range | 0.0451 | +| entropy_loss | -7.83 | +| explained_variance | 0.0239 | +| learning_rate | 3.39e-05 | +| loss | -0.0178 | +| n_updates | 16384 | +| policy_gradient_loss | -0.0107 | +| value_loss | 0.000114 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1385 | +| iterations | 4098 | +| time_elapsed | 6059 | +| total_timesteps | 8392704 | +| train/ | | +| approx_kl | 0.002713487 | +| clip_fraction | 0.231 | +| clip_range | 0.0451 | +| entropy_loss | -7.63 | +| explained_variance | -0.0768 | +| learning_rate | 3.39e-05 | +| loss | -0.0177 | +| n_updates | 16388 | +| policy_gradient_loss | -0.0103 | +| value_loss | 0.000174 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1385 | +| iterations | 4099 | +| time_elapsed | 6060 | +| total_timesteps | 8394752 | +| train/ | | +| approx_kl | 0.003094679 | +| clip_fraction | 0.26 | +| clip_range | 0.0451 | +| entropy_loss | -7.66 | +| explained_variance | -0.043 | +| learning_rate | 3.38e-05 | +| loss | -0.0198 | +| n_updates | 16392 | +| policy_gradient_loss | -0.0124 | +| value_loss | 0.000236 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1385 | +| iterations | 4100 | +| time_elapsed | 6062 | +| total_timesteps | 8396800 | +| train/ | | +| approx_kl | 0.0028362565 | +| clip_fraction | 0.227 | +| clip_range | 0.0451 | +| entropy_loss | -7.73 | +| explained_variance | 0.00929 | +| learning_rate | 3.38e-05 | +| loss | -0.021 | +| n_updates | 16396 | +| policy_gradient_loss | -0.0111 | +| value_loss | 0.000197 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1385 | +| iterations | 4101 | +| time_elapsed | 6063 | +| total_timesteps | 8398848 | +| train/ | | +| approx_kl | 0.0029359441 | +| clip_fraction | 0.241 | +| clip_range | 0.045 | +| entropy_loss | -7.44 | +| explained_variance | 0.0697 | +| learning_rate | 3.37e-05 | +| loss | -0.0188 | +| n_updates | 16400 | +| policy_gradient_loss | -0.0112 | +| value_loss | 0.000247 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1385 | +| iterations | 4102 | +| time_elapsed | 6065 | +| total_timesteps | 8400896 | +| train/ | | +| approx_kl | 0.003019871 | +| clip_fraction | 0.242 | +| clip_range | 0.045 | +| entropy_loss | -7.72 | +| explained_variance | -0.0479 | +| learning_rate | 3.37e-05 | +| loss | -0.0198 | +| n_updates | 16404 | +| policy_gradient_loss | -0.0106 | +| value_loss | 0.000187 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1385 | +| iterations | 4103 | +| time_elapsed | 6066 | +| total_timesteps | 8402944 | +| train/ | | +| approx_kl | 0.0034452365 | +| clip_fraction | 0.28 | +| clip_range | 0.045 | +| entropy_loss | -7.78 | +| explained_variance | -0.145 | +| learning_rate | 3.37e-05 | +| loss | -0.0201 | +| n_updates | 16408 | +| policy_gradient_loss | -0.0138 | +| value_loss | 7.8e-05 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1385 | +| iterations | 4104 | +| time_elapsed | 6068 | +| total_timesteps | 8404992 | +| train/ | | +| approx_kl | 0.0030225054 | +| clip_fraction | 0.239 | +| clip_range | 0.045 | +| entropy_loss | -7.87 | +| explained_variance | -0.0646 | +| learning_rate | 3.36e-05 | +| loss | -0.0191 | +| n_updates | 16412 | +| policy_gradient_loss | -0.0108 | +| value_loss | 0.000178 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1385 | +| iterations | 4105 | +| time_elapsed | 6069 | +| total_timesteps | 8407040 | +| train/ | | +| approx_kl | 0.002859154 | +| clip_fraction | 0.25 | +| clip_range | 0.0449 | +| entropy_loss | -7.82 | +| explained_variance | -0.0957 | +| learning_rate | 3.36e-05 | +| loss | -0.0195 | +| n_updates | 16416 | +| policy_gradient_loss | -0.0112 | +| value_loss | 0.000104 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.315 | +| time/ | | +| fps | 1385 | +| iterations | 4106 | +| time_elapsed | 6071 | +| total_timesteps | 8409088 | +| train/ | | +| approx_kl | 0.0029455433 | +| clip_fraction | 0.234 | +| clip_range | 0.0449 | +| entropy_loss | -7.62 | +| explained_variance | -0.00296 | +| learning_rate | 3.35e-05 | +| loss | -0.02 | +| n_updates | 16420 | +| policy_gradient_loss | -0.0111 | +| value_loss | 0.000197 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.315 | +| time/ | | +| fps | 1385 | +| iterations | 4107 | +| time_elapsed | 6072 | +| total_timesteps | 8411136 | +| train/ | | +| approx_kl | 0.0031452822 | +| clip_fraction | 0.246 | +| clip_range | 0.0449 | +| entropy_loss | -7.75 | +| explained_variance | -0.0397 | +| learning_rate | 3.35e-05 | +| loss | -0.0171 | +| n_updates | 16424 | +| policy_gradient_loss | -0.0111 | +| value_loss | 0.000196 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1385 | +| iterations | 4108 | +| time_elapsed | 6074 | +| total_timesteps | 8413184 | +| train/ | | +| approx_kl | 0.0030999822 | +| clip_fraction | 0.26 | +| clip_range | 0.0449 | +| entropy_loss | -7.82 | +| explained_variance | 0.00592 | +| learning_rate | 3.35e-05 | +| loss | -0.0188 | +| n_updates | 16428 | +| policy_gradient_loss | -0.0115 | +| value_loss | 0.000133 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 1385 | +| iterations | 4109 | +| time_elapsed | 6075 | +| total_timesteps | 8415232 | +| train/ | | +| approx_kl | 0.0027747098 | +| clip_fraction | 0.245 | +| clip_range | 0.0448 | +| entropy_loss | -7.67 | +| explained_variance | 0.067 | +| learning_rate | 3.34e-05 | +| loss | -0.0196 | +| n_updates | 16432 | +| policy_gradient_loss | -0.0119 | +| value_loss | 0.000231 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.306 | +| time/ | | +| fps | 1384 | +| iterations | 4110 | +| time_elapsed | 6077 | +| total_timesteps | 8417280 | +| train/ | | +| approx_kl | 0.0029271534 | +| clip_fraction | 0.261 | +| clip_range | 0.0448 | +| entropy_loss | -7.64 | +| explained_variance | -0.142 | +| learning_rate | 3.34e-05 | +| loss | -0.0201 | +| n_updates | 16436 | +| policy_gradient_loss | -0.0116 | +| value_loss | 0.000168 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 1384 | +| iterations | 4111 | +| time_elapsed | 6079 | +| total_timesteps | 8419328 | +| train/ | | +| approx_kl | 0.0033807682 | +| clip_fraction | 0.258 | +| clip_range | 0.0448 | +| entropy_loss | -7.59 | +| explained_variance | 0.0282 | +| learning_rate | 3.33e-05 | +| loss | -0.0178 | +| n_updates | 16440 | +| policy_gradient_loss | -0.0117 | +| value_loss | 0.000137 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 1384 | +| iterations | 4112 | +| time_elapsed | 6080 | +| total_timesteps | 8421376 | +| train/ | | +| approx_kl | 0.003037461 | +| clip_fraction | 0.249 | +| clip_range | 0.0448 | +| entropy_loss | -7.83 | +| explained_variance | -0.0568 | +| learning_rate | 3.33e-05 | +| loss | -0.0187 | +| n_updates | 16444 | +| policy_gradient_loss | -0.0111 | +| value_loss | 0.000122 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1384 | +| iterations | 4113 | +| time_elapsed | 6082 | +| total_timesteps | 8423424 | +| train/ | | +| approx_kl | 0.0037734653 | +| clip_fraction | 0.27 | +| clip_range | 0.0447 | +| entropy_loss | -7.65 | +| explained_variance | 0.0484 | +| learning_rate | 3.33e-05 | +| loss | -0.019 | +| n_updates | 16448 | +| policy_gradient_loss | -0.0121 | +| value_loss | 0.000161 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1384 | +| iterations | 4114 | +| time_elapsed | 6083 | +| total_timesteps | 8425472 | +| train/ | | +| approx_kl | 0.0031098835 | +| clip_fraction | 0.246 | +| clip_range | 0.0447 | +| entropy_loss | -7.71 | +| explained_variance | -0.0272 | +| learning_rate | 3.32e-05 | +| loss | -0.0211 | +| n_updates | 16452 | +| policy_gradient_loss | -0.0117 | +| value_loss | 0.000195 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1384 | +| iterations | 4115 | +| time_elapsed | 6085 | +| total_timesteps | 8427520 | +| train/ | | +| approx_kl | 0.0030052532 | +| clip_fraction | 0.242 | +| clip_range | 0.0447 | +| entropy_loss | -7.87 | +| explained_variance | -0.0801 | +| learning_rate | 3.32e-05 | +| loss | -0.0202 | +| n_updates | 16456 | +| policy_gradient_loss | -0.0119 | +| value_loss | 0.000145 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1384 | +| iterations | 4116 | +| time_elapsed | 6086 | +| total_timesteps | 8429568 | +| train/ | | +| approx_kl | 0.0029234253 | +| clip_fraction | 0.245 | +| clip_range | 0.0447 | +| entropy_loss | -7.75 | +| explained_variance | -0.0956 | +| learning_rate | 3.31e-05 | +| loss | -0.0151 | +| n_updates | 16460 | +| policy_gradient_loss | -0.0106 | +| value_loss | 0.0002 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1384 | +| iterations | 4117 | +| time_elapsed | 6088 | +| total_timesteps | 8431616 | +| train/ | | +| approx_kl | 0.0029564092 | +| clip_fraction | 0.246 | +| clip_range | 0.0446 | +| entropy_loss | -7.44 | +| explained_variance | 0.0966 | +| learning_rate | 3.31e-05 | +| loss | -0.0167 | +| n_updates | 16464 | +| policy_gradient_loss | -0.0112 | +| value_loss | 0.000355 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1384 | +| iterations | 4118 | +| time_elapsed | 6089 | +| total_timesteps | 8433664 | +| train/ | | +| approx_kl | 0.0032203556 | +| clip_fraction | 0.282 | +| clip_range | 0.0446 | +| entropy_loss | -7.62 | +| explained_variance | 0.087 | +| learning_rate | 3.31e-05 | +| loss | -0.0209 | +| n_updates | 16468 | +| policy_gradient_loss | -0.0134 | +| value_loss | 0.000207 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1384 | +| iterations | 4119 | +| time_elapsed | 6091 | +| total_timesteps | 8435712 | +| train/ | | +| approx_kl | 0.003331663 | +| clip_fraction | 0.258 | +| clip_range | 0.0446 | +| entropy_loss | -7.84 | +| explained_variance | -0.0803 | +| learning_rate | 3.3e-05 | +| loss | -0.0195 | +| n_updates | 16472 | +| policy_gradient_loss | -0.0125 | +| value_loss | 0.000121 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1384 | +| iterations | 4120 | +| time_elapsed | 6092 | +| total_timesteps | 8437760 | +| train/ | | +| approx_kl | 0.0030467203 | +| clip_fraction | 0.248 | +| clip_range | 0.0446 | +| entropy_loss | -7.83 | +| explained_variance | 0.0566 | +| learning_rate | 3.3e-05 | +| loss | -0.0209 | +| n_updates | 16476 | +| policy_gradient_loss | -0.0124 | +| value_loss | 0.000301 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1384 | +| iterations | 4121 | +| time_elapsed | 6094 | +| total_timesteps | 8439808 | +| train/ | | +| approx_kl | 0.0032990421 | +| clip_fraction | 0.267 | +| clip_range | 0.0445 | +| entropy_loss | -7.84 | +| explained_variance | 0.0314 | +| learning_rate | 3.29e-05 | +| loss | -0.02 | +| n_updates | 16480 | +| policy_gradient_loss | -0.0129 | +| value_loss | 0.000165 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1384 | +| iterations | 4122 | +| time_elapsed | 6095 | +| total_timesteps | 8441856 | +| train/ | | +| approx_kl | 0.0026201108 | +| clip_fraction | 0.234 | +| clip_range | 0.0445 | +| entropy_loss | -7.78 | +| explained_variance | -0.225 | +| learning_rate | 3.29e-05 | +| loss | -0.0189 | +| n_updates | 16484 | +| policy_gradient_loss | -0.0118 | +| value_loss | 0.000135 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1384 | +| iterations | 4123 | +| time_elapsed | 6097 | +| total_timesteps | 8443904 | +| train/ | | +| approx_kl | 0.0023963996 | +| clip_fraction | 0.225 | +| clip_range | 0.0445 | +| entropy_loss | -7.68 | +| explained_variance | 0.0481 | +| learning_rate | 3.29e-05 | +| loss | -0.0163 | +| n_updates | 16488 | +| policy_gradient_loss | -0.0101 | +| value_loss | 0.000351 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1384 | +| iterations | 4124 | +| time_elapsed | 6098 | +| total_timesteps | 8445952 | +| train/ | | +| approx_kl | 0.0028783313 | +| clip_fraction | 0.228 | +| clip_range | 0.0445 | +| entropy_loss | -7.77 | +| explained_variance | -0.218 | +| learning_rate | 3.28e-05 | +| loss | -0.0196 | +| n_updates | 16492 | +| policy_gradient_loss | -0.0112 | +| value_loss | 0.000181 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1384 | +| iterations | 4125 | +| time_elapsed | 6100 | +| total_timesteps | 8448000 | +| train/ | | +| approx_kl | 0.0030677496 | +| clip_fraction | 0.249 | +| clip_range | 0.0444 | +| entropy_loss | -7.7 | +| explained_variance | -0.0377 | +| learning_rate | 3.28e-05 | +| loss | -0.0161 | +| n_updates | 16496 | +| policy_gradient_loss | -0.0103 | +| value_loss | 0.000321 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1384 | +| iterations | 4126 | +| time_elapsed | 6101 | +| total_timesteps | 8450048 | +| train/ | | +| approx_kl | 0.0031030779 | +| clip_fraction | 0.262 | +| clip_range | 0.0444 | +| entropy_loss | -7.73 | +| explained_variance | -0.198 | +| learning_rate | 3.27e-05 | +| loss | -0.0181 | +| n_updates | 16500 | +| policy_gradient_loss | -0.0126 | +| value_loss | 0.000117 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1384 | +| iterations | 4127 | +| time_elapsed | 6103 | +| total_timesteps | 8452096 | +| train/ | | +| approx_kl | 0.0032430426 | +| clip_fraction | 0.28 | +| clip_range | 0.0444 | +| entropy_loss | -7.49 | +| explained_variance | -0.0471 | +| learning_rate | 3.27e-05 | +| loss | -0.0222 | +| n_updates | 16504 | +| policy_gradient_loss | -0.0124 | +| value_loss | 0.000109 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1384 | +| iterations | 4128 | +| time_elapsed | 6104 | +| total_timesteps | 8454144 | +| train/ | | +| approx_kl | 0.0030880237 | +| clip_fraction | 0.251 | +| clip_range | 0.0443 | +| entropy_loss | -7.7 | +| explained_variance | 0.00561 | +| learning_rate | 3.26e-05 | +| loss | -0.0201 | +| n_updates | 16508 | +| policy_gradient_loss | -0.0122 | +| value_loss | 0.000179 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1384 | +| iterations | 4129 | +| time_elapsed | 6106 | +| total_timesteps | 8456192 | +| train/ | | +| approx_kl | 0.0027316657 | +| clip_fraction | 0.262 | +| clip_range | 0.0443 | +| entropy_loss | -7.69 | +| explained_variance | 0.0736 | +| learning_rate | 3.26e-05 | +| loss | -0.0188 | +| n_updates | 16512 | +| policy_gradient_loss | -0.0112 | +| value_loss | 0.000177 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1384 | +| iterations | 4130 | +| time_elapsed | 6107 | +| total_timesteps | 8458240 | +| train/ | | +| approx_kl | 0.0028973618 | +| clip_fraction | 0.248 | +| clip_range | 0.0443 | +| entropy_loss | -7.86 | +| explained_variance | -0.204 | +| learning_rate | 3.26e-05 | +| loss | -0.0193 | +| n_updates | 16516 | +| policy_gradient_loss | -0.0123 | +| value_loss | 0.000114 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1384 | +| iterations | 4131 | +| time_elapsed | 6109 | +| total_timesteps | 8460288 | +| train/ | | +| approx_kl | 0.002626835 | +| clip_fraction | 0.24 | +| clip_range | 0.0443 | +| entropy_loss | -7.72 | +| explained_variance | 0.0203 | +| learning_rate | 3.25e-05 | +| loss | -0.019 | +| n_updates | 16520 | +| policy_gradient_loss | -0.0113 | +| value_loss | 0.000214 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1384 | +| iterations | 4132 | +| time_elapsed | 6110 | +| total_timesteps | 8462336 | +| train/ | | +| approx_kl | 0.0026805417 | +| clip_fraction | 0.229 | +| clip_range | 0.0442 | +| entropy_loss | -7.79 | +| explained_variance | 0.00895 | +| learning_rate | 3.25e-05 | +| loss | -0.0192 | +| n_updates | 16524 | +| policy_gradient_loss | -0.0106 | +| value_loss | 0.000228 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1384 | +| iterations | 4133 | +| time_elapsed | 6112 | +| total_timesteps | 8464384 | +| train/ | | +| approx_kl | 0.0025613764 | +| clip_fraction | 0.24 | +| clip_range | 0.0442 | +| entropy_loss | -7.88 | +| explained_variance | -0.15 | +| learning_rate | 3.24e-05 | +| loss | -0.022 | +| n_updates | 16528 | +| policy_gradient_loss | -0.0122 | +| value_loss | 9.21e-05 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1384 | +| iterations | 4134 | +| time_elapsed | 6113 | +| total_timesteps | 8466432 | +| train/ | | +| approx_kl | 0.0022741957 | +| clip_fraction | 0.222 | +| clip_range | 0.0442 | +| entropy_loss | -7.67 | +| explained_variance | 3.21e-05 | +| learning_rate | 3.24e-05 | +| loss | -0.0178 | +| n_updates | 16532 | +| policy_gradient_loss | -0.00974 | +| value_loss | 0.000283 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1384 | +| iterations | 4135 | +| time_elapsed | 6115 | +| total_timesteps | 8468480 | +| train/ | | +| approx_kl | 0.002895901 | +| clip_fraction | 0.28 | +| clip_range | 0.0442 | +| entropy_loss | -7.63 | +| explained_variance | -0.0976 | +| learning_rate | 3.24e-05 | +| loss | -0.0224 | +| n_updates | 16536 | +| policy_gradient_loss | -0.0144 | +| value_loss | 6.81e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1384 | +| iterations | 4136 | +| time_elapsed | 6116 | +| total_timesteps | 8470528 | +| train/ | | +| approx_kl | 0.0030645211 | +| clip_fraction | 0.242 | +| clip_range | 0.0441 | +| entropy_loss | -7.7 | +| explained_variance | -0.0683 | +| learning_rate | 3.23e-05 | +| loss | -0.0192 | +| n_updates | 16540 | +| policy_gradient_loss | -0.0114 | +| value_loss | 0.000159 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1384 | +| iterations | 4137 | +| time_elapsed | 6118 | +| total_timesteps | 8472576 | +| train/ | | +| approx_kl | 0.0031034686 | +| clip_fraction | 0.255 | +| clip_range | 0.0441 | +| entropy_loss | -7.81 | +| explained_variance | -0.0572 | +| learning_rate | 3.23e-05 | +| loss | -0.0192 | +| n_updates | 16544 | +| policy_gradient_loss | -0.0115 | +| value_loss | 0.000147 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1384 | +| iterations | 4138 | +| time_elapsed | 6119 | +| total_timesteps | 8474624 | +| train/ | | +| approx_kl | 0.0029851208 | +| clip_fraction | 0.263 | +| clip_range | 0.0441 | +| entropy_loss | -7.82 | +| explained_variance | -0.0538 | +| learning_rate | 3.22e-05 | +| loss | -0.019 | +| n_updates | 16548 | +| policy_gradient_loss | -0.0121 | +| value_loss | 0.000189 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1384 | +| iterations | 4139 | +| time_elapsed | 6121 | +| total_timesteps | 8476672 | +| train/ | | +| approx_kl | 0.002795963 | +| clip_fraction | 0.219 | +| clip_range | 0.0441 | +| entropy_loss | -7.53 | +| explained_variance | 0.00163 | +| learning_rate | 3.22e-05 | +| loss | -0.0144 | +| n_updates | 16552 | +| policy_gradient_loss | -0.0103 | +| value_loss | 0.00015 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1384 | +| iterations | 4140 | +| time_elapsed | 6122 | +| total_timesteps | 8478720 | +| train/ | | +| approx_kl | 0.0027144519 | +| clip_fraction | 0.249 | +| clip_range | 0.044 | +| entropy_loss | -7.61 | +| explained_variance | -0.0794 | +| learning_rate | 3.22e-05 | +| loss | -0.0168 | +| n_updates | 16556 | +| policy_gradient_loss | -0.0103 | +| value_loss | 0.000231 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1384 | +| iterations | 4141 | +| time_elapsed | 6124 | +| total_timesteps | 8480768 | +| train/ | | +| approx_kl | 0.0029197212 | +| clip_fraction | 0.252 | +| clip_range | 0.044 | +| entropy_loss | -7.65 | +| explained_variance | -0.025 | +| learning_rate | 3.21e-05 | +| loss | -0.0209 | +| n_updates | 16560 | +| policy_gradient_loss | -0.0116 | +| value_loss | 0.000325 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1384 | +| iterations | 4142 | +| time_elapsed | 6125 | +| total_timesteps | 8482816 | +| train/ | | +| approx_kl | 0.0026646033 | +| clip_fraction | 0.238 | +| clip_range | 0.044 | +| entropy_loss | -7.86 | +| explained_variance | 0.0187 | +| learning_rate | 3.21e-05 | +| loss | -0.0199 | +| n_updates | 16564 | +| policy_gradient_loss | -0.0116 | +| value_loss | 0.000229 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1384 | +| iterations | 4143 | +| time_elapsed | 6127 | +| total_timesteps | 8484864 | +| train/ | | +| approx_kl | 0.0025314614 | +| clip_fraction | 0.26 | +| clip_range | 0.044 | +| entropy_loss | -7.73 | +| explained_variance | -0.0227 | +| learning_rate | 3.2e-05 | +| loss | -0.0206 | +| n_updates | 16568 | +| policy_gradient_loss | -0.0124 | +| value_loss | 0.000124 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1384 | +| iterations | 4144 | +| time_elapsed | 6128 | +| total_timesteps | 8486912 | +| train/ | | +| approx_kl | 0.0024265014 | +| clip_fraction | 0.235 | +| clip_range | 0.0439 | +| entropy_loss | -7.8 | +| explained_variance | 0.0995 | +| learning_rate | 3.2e-05 | +| loss | -0.0211 | +| n_updates | 16572 | +| policy_gradient_loss | -0.0119 | +| value_loss | 0.000118 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1384 | +| iterations | 4145 | +| time_elapsed | 6130 | +| total_timesteps | 8488960 | +| train/ | | +| approx_kl | 0.0022594864 | +| clip_fraction | 0.225 | +| clip_range | 0.0439 | +| entropy_loss | -7.73 | +| explained_variance | 0.0287 | +| learning_rate | 3.2e-05 | +| loss | -0.0161 | +| n_updates | 16576 | +| policy_gradient_loss | -0.00999 | +| value_loss | 0.000245 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1384 | +| iterations | 4146 | +| time_elapsed | 6131 | +| total_timesteps | 8491008 | +| train/ | | +| approx_kl | 0.0026234451 | +| clip_fraction | 0.255 | +| clip_range | 0.0439 | +| entropy_loss | -7.76 | +| explained_variance | 0.135 | +| learning_rate | 3.19e-05 | +| loss | -0.0218 | +| n_updates | 16580 | +| policy_gradient_loss | -0.0113 | +| value_loss | 0.00011 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1384 | +| iterations | 4147 | +| time_elapsed | 6133 | +| total_timesteps | 8493056 | +| train/ | | +| approx_kl | 0.0026461175 | +| clip_fraction | 0.225 | +| clip_range | 0.0439 | +| entropy_loss | -7.82 | +| explained_variance | 0.00542 | +| learning_rate | 3.19e-05 | +| loss | -0.0184 | +| n_updates | 16584 | +| policy_gradient_loss | -0.0105 | +| value_loss | 0.000237 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1384 | +| iterations | 4148 | +| time_elapsed | 6134 | +| total_timesteps | 8495104 | +| train/ | | +| approx_kl | 0.0023627316 | +| clip_fraction | 0.243 | +| clip_range | 0.0438 | +| entropy_loss | -7.71 | +| explained_variance | -0.29 | +| learning_rate | 3.18e-05 | +| loss | -0.0173 | +| n_updates | 16588 | +| policy_gradient_loss | -0.0104 | +| value_loss | 7.71e-05 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1384 | +| iterations | 4149 | +| time_elapsed | 6136 | +| total_timesteps | 8497152 | +| train/ | | +| approx_kl | 0.0022975518 | +| clip_fraction | 0.23 | +| clip_range | 0.0438 | +| entropy_loss | -7.59 | +| explained_variance | 0.0269 | +| learning_rate | 3.18e-05 | +| loss | -0.0157 | +| n_updates | 16592 | +| policy_gradient_loss | -0.0105 | +| value_loss | 0.000341 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1384 | +| iterations | 4150 | +| time_elapsed | 6137 | +| total_timesteps | 8499200 | +| train/ | | +| approx_kl | 0.002660099 | +| clip_fraction | 0.237 | +| clip_range | 0.0438 | +| entropy_loss | -7.72 | +| explained_variance | 0.0488 | +| learning_rate | 3.18e-05 | +| loss | -0.0186 | +| n_updates | 16596 | +| policy_gradient_loss | -0.0108 | +| value_loss | 0.000308 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1384 | +| iterations | 4151 | +| time_elapsed | 6139 | +| total_timesteps | 8501248 | +| train/ | | +| approx_kl | 0.0024034197 | +| clip_fraction | 0.224 | +| clip_range | 0.0438 | +| entropy_loss | -7.73 | +| explained_variance | 0.0166 | +| learning_rate | 3.17e-05 | +| loss | -0.0167 | +| n_updates | 16600 | +| policy_gradient_loss | -0.0104 | +| value_loss | 0.000194 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1384 | +| iterations | 4152 | +| time_elapsed | 6140 | +| total_timesteps | 8503296 | +| train/ | | +| approx_kl | 0.0025342344 | +| clip_fraction | 0.224 | +| clip_range | 0.0437 | +| entropy_loss | -7.74 | +| explained_variance | 0.0508 | +| learning_rate | 3.17e-05 | +| loss | -0.0162 | +| n_updates | 16604 | +| policy_gradient_loss | -0.0107 | +| value_loss | 0.000291 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1384 | +| iterations | 4153 | +| time_elapsed | 6142 | +| total_timesteps | 8505344 | +| train/ | | +| approx_kl | 0.0024354018 | +| clip_fraction | 0.239 | +| clip_range | 0.0437 | +| entropy_loss | -7.62 | +| explained_variance | -0.084 | +| learning_rate | 3.16e-05 | +| loss | -0.0184 | +| n_updates | 16608 | +| policy_gradient_loss | -0.0117 | +| value_loss | 0.000168 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1384 | +| iterations | 4154 | +| time_elapsed | 6143 | +| total_timesteps | 8507392 | +| train/ | | +| approx_kl | 0.0024701785 | +| clip_fraction | 0.233 | +| clip_range | 0.0437 | +| entropy_loss | -7.84 | +| explained_variance | -0.0589 | +| learning_rate | 3.16e-05 | +| loss | -0.0211 | +| n_updates | 16612 | +| policy_gradient_loss | -0.0102 | +| value_loss | 0.000278 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1384 | +| iterations | 4155 | +| time_elapsed | 6145 | +| total_timesteps | 8509440 | +| train/ | | +| approx_kl | 0.0027583004 | +| clip_fraction | 0.244 | +| clip_range | 0.0437 | +| entropy_loss | -7.64 | +| explained_variance | -0.0297 | +| learning_rate | 3.16e-05 | +| loss | -0.0167 | +| n_updates | 16616 | +| policy_gradient_loss | -0.0119 | +| value_loss | 0.000152 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1384 | +| iterations | 4156 | +| time_elapsed | 6146 | +| total_timesteps | 8511488 | +| train/ | | +| approx_kl | 0.0026949681 | +| clip_fraction | 0.248 | +| clip_range | 0.0436 | +| entropy_loss | -7.85 | +| explained_variance | -0.0277 | +| learning_rate | 3.15e-05 | +| loss | -0.0228 | +| n_updates | 16620 | +| policy_gradient_loss | -0.0124 | +| value_loss | 0.000111 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1384 | +| iterations | 4157 | +| time_elapsed | 6148 | +| total_timesteps | 8513536 | +| train/ | | +| approx_kl | 0.0025817994 | +| clip_fraction | 0.248 | +| clip_range | 0.0436 | +| entropy_loss | -7.9 | +| explained_variance | -0.102 | +| learning_rate | 3.15e-05 | +| loss | -0.0198 | +| n_updates | 16624 | +| policy_gradient_loss | -0.0126 | +| value_loss | 0.000181 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1384 | +| iterations | 4158 | +| time_elapsed | 6149 | +| total_timesteps | 8515584 | +| train/ | | +| approx_kl | 0.0026070322 | +| clip_fraction | 0.231 | +| clip_range | 0.0436 | +| entropy_loss | -7.79 | +| explained_variance | -0.0341 | +| learning_rate | 3.14e-05 | +| loss | -0.0138 | +| n_updates | 16628 | +| policy_gradient_loss | -0.0102 | +| value_loss | 0.000107 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1384 | +| iterations | 4159 | +| time_elapsed | 6151 | +| total_timesteps | 8517632 | +| train/ | | +| approx_kl | 0.002937073 | +| clip_fraction | 0.226 | +| clip_range | 0.0436 | +| entropy_loss | -7.68 | +| explained_variance | -0.0787 | +| learning_rate | 3.14e-05 | +| loss | -0.017 | +| n_updates | 16632 | +| policy_gradient_loss | -0.0108 | +| value_loss | 0.000158 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1384 | +| iterations | 4160 | +| time_elapsed | 6152 | +| total_timesteps | 8519680 | +| train/ | | +| approx_kl | 0.002866299 | +| clip_fraction | 0.273 | +| clip_range | 0.0435 | +| entropy_loss | -7.72 | +| explained_variance | 0.153 | +| learning_rate | 3.14e-05 | +| loss | -0.0179 | +| n_updates | 16636 | +| policy_gradient_loss | -0.0121 | +| value_loss | 8.41e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1384 | +| iterations | 4161 | +| time_elapsed | 6154 | +| total_timesteps | 8521728 | +| train/ | | +| approx_kl | 0.0029191528 | +| clip_fraction | 0.255 | +| clip_range | 0.0435 | +| entropy_loss | -7.75 | +| explained_variance | -0.141 | +| learning_rate | 3.13e-05 | +| loss | -0.0171 | +| n_updates | 16640 | +| policy_gradient_loss | -0.011 | +| value_loss | 0.000124 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1384 | +| iterations | 4162 | +| time_elapsed | 6155 | +| total_timesteps | 8523776 | +| train/ | | +| approx_kl | 0.0021994966 | +| clip_fraction | 0.232 | +| clip_range | 0.0435 | +| entropy_loss | -7.66 | +| explained_variance | -0.116 | +| learning_rate | 3.13e-05 | +| loss | -0.0174 | +| n_updates | 16644 | +| policy_gradient_loss | -0.0104 | +| value_loss | 0.000227 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1384 | +| iterations | 4163 | +| time_elapsed | 6157 | +| total_timesteps | 8525824 | +| train/ | | +| approx_kl | 0.002712639 | +| clip_fraction | 0.24 | +| clip_range | 0.0435 | +| entropy_loss | -7.65 | +| explained_variance | 0.0764 | +| learning_rate | 3.12e-05 | +| loss | -0.0204 | +| n_updates | 16648 | +| policy_gradient_loss | -0.0117 | +| value_loss | 0.000133 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1384 | +| iterations | 4164 | +| time_elapsed | 6158 | +| total_timesteps | 8527872 | +| train/ | | +| approx_kl | 0.0027014003 | +| clip_fraction | 0.245 | +| clip_range | 0.0434 | +| entropy_loss | -7.63 | +| explained_variance | -0.103 | +| learning_rate | 3.12e-05 | +| loss | -0.0176 | +| n_updates | 16652 | +| policy_gradient_loss | -0.0108 | +| value_loss | 0.000116 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 1384 | +| iterations | 4165 | +| time_elapsed | 6160 | +| total_timesteps | 8529920 | +| train/ | | +| approx_kl | 0.0021818336 | +| clip_fraction | 0.216 | +| clip_range | 0.0434 | +| entropy_loss | -7.92 | +| explained_variance | -0.0462 | +| learning_rate | 3.11e-05 | +| loss | -0.0178 | +| n_updates | 16656 | +| policy_gradient_loss | -0.0109 | +| value_loss | 0.000181 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 1384 | +| iterations | 4166 | +| time_elapsed | 6161 | +| total_timesteps | 8531968 | +| train/ | | +| approx_kl | 0.0021301766 | +| clip_fraction | 0.222 | +| clip_range | 0.0434 | +| entropy_loss | -7.72 | +| explained_variance | -0.0936 | +| learning_rate | 3.11e-05 | +| loss | -0.0175 | +| n_updates | 16660 | +| policy_gradient_loss | -0.0108 | +| value_loss | 0.000132 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.304 | +| time/ | | +| fps | 1384 | +| iterations | 4167 | +| time_elapsed | 6163 | +| total_timesteps | 8534016 | +| train/ | | +| approx_kl | 0.0023350806 | +| clip_fraction | 0.213 | +| clip_range | 0.0434 | +| entropy_loss | -7.86 | +| explained_variance | -0.0881 | +| learning_rate | 3.11e-05 | +| loss | -0.0154 | +| n_updates | 16664 | +| policy_gradient_loss | -0.00971 | +| value_loss | 0.000146 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.294 | +| time/ | | +| fps | 1384 | +| iterations | 4168 | +| time_elapsed | 6164 | +| total_timesteps | 8536064 | +| train/ | | +| approx_kl | 0.0023724372 | +| clip_fraction | 0.223 | +| clip_range | 0.0433 | +| entropy_loss | -7.88 | +| explained_variance | 0.045 | +| learning_rate | 3.1e-05 | +| loss | -0.0157 | +| n_updates | 16668 | +| policy_gradient_loss | -0.00989 | +| value_loss | 0.000161 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.294 | +| time/ | | +| fps | 1384 | +| iterations | 4169 | +| time_elapsed | 6166 | +| total_timesteps | 8538112 | +| train/ | | +| approx_kl | 0.0027390448 | +| clip_fraction | 0.224 | +| clip_range | 0.0433 | +| entropy_loss | -7.45 | +| explained_variance | 0.0569 | +| learning_rate | 3.1e-05 | +| loss | -0.0157 | +| n_updates | 16672 | +| policy_gradient_loss | -0.0107 | +| value_loss | 0.000166 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 1384 | +| iterations | 4170 | +| time_elapsed | 6167 | +| total_timesteps | 8540160 | +| train/ | | +| approx_kl | 0.0025886751 | +| clip_fraction | 0.243 | +| clip_range | 0.0433 | +| entropy_loss | -7.76 | +| explained_variance | -0.0262 | +| learning_rate | 3.09e-05 | +| loss | -0.0195 | +| n_updates | 16676 | +| policy_gradient_loss | -0.0115 | +| value_loss | 0.000159 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.294 | +| time/ | | +| fps | 1384 | +| iterations | 4171 | +| time_elapsed | 6169 | +| total_timesteps | 8542208 | +| train/ | | +| approx_kl | 0.0026762735 | +| clip_fraction | 0.236 | +| clip_range | 0.0432 | +| entropy_loss | -7.69 | +| explained_variance | -0.0205 | +| learning_rate | 3.09e-05 | +| loss | -0.0139 | +| n_updates | 16680 | +| policy_gradient_loss | -0.0107 | +| value_loss | 0.000185 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.292 | +| time/ | | +| fps | 1384 | +| iterations | 4172 | +| time_elapsed | 6170 | +| total_timesteps | 8544256 | +| train/ | | +| approx_kl | 0.0025520185 | +| clip_fraction | 0.219 | +| clip_range | 0.0432 | +| entropy_loss | -7.77 | +| explained_variance | -0.0528 | +| learning_rate | 3.09e-05 | +| loss | -0.0158 | +| n_updates | 16684 | +| policy_gradient_loss | -0.0106 | +| value_loss | 0.000203 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.29 | +| time/ | | +| fps | 1384 | +| iterations | 4173 | +| time_elapsed | 6172 | +| total_timesteps | 8546304 | +| train/ | | +| approx_kl | 0.002693761 | +| clip_fraction | 0.236 | +| clip_range | 0.0432 | +| entropy_loss | -7.77 | +| explained_variance | -0.105 | +| learning_rate | 3.08e-05 | +| loss | -0.0196 | +| n_updates | 16688 | +| policy_gradient_loss | -0.0119 | +| value_loss | 0.000108 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.289 | +| time/ | | +| fps | 1384 | +| iterations | 4174 | +| time_elapsed | 6173 | +| total_timesteps | 8548352 | +| train/ | | +| approx_kl | 0.0025327373 | +| clip_fraction | 0.229 | +| clip_range | 0.0432 | +| entropy_loss | -7.79 | +| explained_variance | -0.0627 | +| learning_rate | 3.08e-05 | +| loss | -0.0212 | +| n_updates | 16692 | +| policy_gradient_loss | -0.0106 | +| value_loss | 5.97e-05 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.283 | +| time/ | | +| fps | 1384 | +| iterations | 4175 | +| time_elapsed | 6175 | +| total_timesteps | 8550400 | +| train/ | | +| approx_kl | 0.0024060453 | +| clip_fraction | 0.23 | +| clip_range | 0.0431 | +| entropy_loss | -7.68 | +| explained_variance | 0.0675 | +| learning_rate | 3.07e-05 | +| loss | -0.0166 | +| n_updates | 16696 | +| policy_gradient_loss | -0.011 | +| value_loss | 0.000284 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.276 | +| time/ | | +| fps | 1384 | +| iterations | 4176 | +| time_elapsed | 6176 | +| total_timesteps | 8552448 | +| train/ | | +| approx_kl | 0.0022359444 | +| clip_fraction | 0.242 | +| clip_range | 0.0431 | +| entropy_loss | -7.65 | +| explained_variance | 0.0206 | +| learning_rate | 3.07e-05 | +| loss | -0.016 | +| n_updates | 16700 | +| policy_gradient_loss | -0.0101 | +| value_loss | 0.000218 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.276 | +| time/ | | +| fps | 1384 | +| iterations | 4177 | +| time_elapsed | 6178 | +| total_timesteps | 8554496 | +| train/ | | +| approx_kl | 0.0024910364 | +| clip_fraction | 0.233 | +| clip_range | 0.0431 | +| entropy_loss | -7.68 | +| explained_variance | 0.0661 | +| learning_rate | 3.07e-05 | +| loss | -0.0187 | +| n_updates | 16704 | +| policy_gradient_loss | -0.0109 | +| value_loss | 0.000123 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.263 | +| time/ | | +| fps | 1384 | +| iterations | 4178 | +| time_elapsed | 6179 | +| total_timesteps | 8556544 | +| train/ | | +| approx_kl | 0.0025417383 | +| clip_fraction | 0.248 | +| clip_range | 0.0431 | +| entropy_loss | -7.92 | +| explained_variance | -0.191 | +| learning_rate | 3.06e-05 | +| loss | -0.017 | +| n_updates | 16708 | +| policy_gradient_loss | -0.0117 | +| value_loss | 0.000127 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.262 | +| time/ | | +| fps | 1384 | +| iterations | 4179 | +| time_elapsed | 6181 | +| total_timesteps | 8558592 | +| train/ | | +| approx_kl | 0.0026402904 | +| clip_fraction | 0.249 | +| clip_range | 0.043 | +| entropy_loss | -7.66 | +| explained_variance | 0.0885 | +| learning_rate | 3.06e-05 | +| loss | -0.0186 | +| n_updates | 16712 | +| policy_gradient_loss | -0.0107 | +| value_loss | 9.49e-05 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.262 | +| time/ | | +| fps | 1384 | +| iterations | 4180 | +| time_elapsed | 6182 | +| total_timesteps | 8560640 | +| train/ | | +| approx_kl | 0.0022098077 | +| clip_fraction | 0.215 | +| clip_range | 0.043 | +| entropy_loss | -7.65 | +| explained_variance | -0.173 | +| learning_rate | 3.05e-05 | +| loss | -0.015 | +| n_updates | 16716 | +| policy_gradient_loss | -0.0102 | +| value_loss | 0.000117 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.253 | +| time/ | | +| fps | 1384 | +| iterations | 4181 | +| time_elapsed | 6184 | +| total_timesteps | 8562688 | +| train/ | | +| approx_kl | 0.0025371753 | +| clip_fraction | 0.234 | +| clip_range | 0.043 | +| entropy_loss | -7.85 | +| explained_variance | -0.0177 | +| learning_rate | 3.05e-05 | +| loss | -0.016 | +| n_updates | 16720 | +| policy_gradient_loss | -0.0102 | +| value_loss | 0.000134 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.235 | +| time/ | | +| fps | 1384 | +| iterations | 4182 | +| time_elapsed | 6185 | +| total_timesteps | 8564736 | +| train/ | | +| approx_kl | 0.0024806797 | +| clip_fraction | 0.225 | +| clip_range | 0.043 | +| entropy_loss | -7.71 | +| explained_variance | -0.0356 | +| learning_rate | 3.05e-05 | +| loss | -0.0182 | +| n_updates | 16724 | +| policy_gradient_loss | -0.0103 | +| value_loss | 0.000194 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.235 | +| time/ | | +| fps | 1384 | +| iterations | 4183 | +| time_elapsed | 6187 | +| total_timesteps | 8566784 | +| train/ | | +| approx_kl | 0.0027012127 | +| clip_fraction | 0.234 | +| clip_range | 0.0429 | +| entropy_loss | -7.77 | +| explained_variance | 0.0179 | +| learning_rate | 3.04e-05 | +| loss | -0.0155 | +| n_updates | 16728 | +| policy_gradient_loss | -0.0105 | +| value_loss | 0.000222 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.234 | +| time/ | | +| fps | 1384 | +| iterations | 4184 | +| time_elapsed | 6188 | +| total_timesteps | 8568832 | +| train/ | | +| approx_kl | 0.0026637919 | +| clip_fraction | 0.241 | +| clip_range | 0.0429 | +| entropy_loss | -7.72 | +| explained_variance | 0.0736 | +| learning_rate | 3.04e-05 | +| loss | -0.0199 | +| n_updates | 16732 | +| policy_gradient_loss | -0.0123 | +| value_loss | 9.84e-05 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.231 | +| time/ | | +| fps | 1384 | +| iterations | 4185 | +| time_elapsed | 6190 | +| total_timesteps | 8570880 | +| train/ | | +| approx_kl | 0.0024266625 | +| clip_fraction | 0.25 | +| clip_range | 0.0429 | +| entropy_loss | -7.8 | +| explained_variance | -0.13 | +| learning_rate | 3.03e-05 | +| loss | -0.02 | +| n_updates | 16736 | +| policy_gradient_loss | -0.0117 | +| value_loss | 0.00013 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.232 | +| time/ | | +| fps | 1384 | +| iterations | 4186 | +| time_elapsed | 6191 | +| total_timesteps | 8572928 | +| train/ | | +| approx_kl | 0.00243898 | +| clip_fraction | 0.241 | +| clip_range | 0.0429 | +| entropy_loss | -7.84 | +| explained_variance | -0.0281 | +| learning_rate | 3.03e-05 | +| loss | -0.0202 | +| n_updates | 16740 | +| policy_gradient_loss | -0.012 | +| value_loss | 0.000172 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.24 | +| time/ | | +| fps | 1384 | +| iterations | 4187 | +| time_elapsed | 6193 | +| total_timesteps | 8574976 | +| train/ | | +| approx_kl | 0.0021505696 | +| clip_fraction | 0.218 | +| clip_range | 0.0428 | +| entropy_loss | -7.73 | +| explained_variance | -0.0779 | +| learning_rate | 3.03e-05 | +| loss | -0.0185 | +| n_updates | 16744 | +| policy_gradient_loss | -0.0109 | +| value_loss | 0.000251 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.244 | +| time/ | | +| fps | 1384 | +| iterations | 4188 | +| time_elapsed | 6194 | +| total_timesteps | 8577024 | +| train/ | | +| approx_kl | 0.0023428746 | +| clip_fraction | 0.218 | +| clip_range | 0.0428 | +| entropy_loss | -7.68 | +| explained_variance | -0.00982 | +| learning_rate | 3.02e-05 | +| loss | -0.0178 | +| n_updates | 16748 | +| policy_gradient_loss | -0.00938 | +| value_loss | 0.000246 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.235 | +| time/ | | +| fps | 1384 | +| iterations | 4189 | +| time_elapsed | 6196 | +| total_timesteps | 8579072 | +| train/ | | +| approx_kl | 0.0020871605 | +| clip_fraction | 0.235 | +| clip_range | 0.0428 | +| entropy_loss | -7.81 | +| explained_variance | -0.00706 | +| learning_rate | 3.02e-05 | +| loss | -0.0172 | +| n_updates | 16752 | +| policy_gradient_loss | -0.0102 | +| value_loss | 0.000222 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.227 | +| time/ | | +| fps | 1384 | +| iterations | 4190 | +| time_elapsed | 6197 | +| total_timesteps | 8581120 | +| train/ | | +| approx_kl | 0.0025969036 | +| clip_fraction | 0.236 | +| clip_range | 0.0428 | +| entropy_loss | -7.66 | +| explained_variance | 0.0378 | +| learning_rate | 3.01e-05 | +| loss | -0.0184 | +| n_updates | 16756 | +| policy_gradient_loss | -0.0115 | +| value_loss | 0.000188 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.227 | +| time/ | | +| fps | 1384 | +| iterations | 4191 | +| time_elapsed | 6199 | +| total_timesteps | 8583168 | +| train/ | | +| approx_kl | 0.0026655355 | +| clip_fraction | 0.24 | +| clip_range | 0.0427 | +| entropy_loss | -7.64 | +| explained_variance | 0.0101 | +| learning_rate | 3.01e-05 | +| loss | -0.0181 | +| n_updates | 16760 | +| policy_gradient_loss | -0.0118 | +| value_loss | 0.000147 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.226 | +| time/ | | +| fps | 1384 | +| iterations | 4192 | +| time_elapsed | 6200 | +| total_timesteps | 8585216 | +| train/ | | +| approx_kl | 0.002509356 | +| clip_fraction | 0.244 | +| clip_range | 0.0427 | +| entropy_loss | -7.8 | +| explained_variance | -0.0811 | +| learning_rate | 3.01e-05 | +| loss | -0.0168 | +| n_updates | 16764 | +| policy_gradient_loss | -0.0109 | +| value_loss | 0.00019 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.225 | +| time/ | | +| fps | 1384 | +| iterations | 4193 | +| time_elapsed | 6202 | +| total_timesteps | 8587264 | +| train/ | | +| approx_kl | 0.002193329 | +| clip_fraction | 0.225 | +| clip_range | 0.0427 | +| entropy_loss | -7.83 | +| explained_variance | 0.0339 | +| learning_rate | 3e-05 | +| loss | -0.0195 | +| n_updates | 16768 | +| policy_gradient_loss | -0.0106 | +| value_loss | 0.000124 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.222 | +| time/ | | +| fps | 1384 | +| iterations | 4194 | +| time_elapsed | 6203 | +| total_timesteps | 8589312 | +| train/ | | +| approx_kl | 0.002052383 | +| clip_fraction | 0.208 | +| clip_range | 0.0427 | +| entropy_loss | -7.91 | +| explained_variance | -0.00274 | +| learning_rate | 3e-05 | +| loss | -0.0173 | +| n_updates | 16772 | +| policy_gradient_loss | -0.00907 | +| value_loss | 0.000135 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.226 | +| time/ | | +| fps | 1384 | +| iterations | 4195 | +| time_elapsed | 6205 | +| total_timesteps | 8591360 | +| train/ | | +| approx_kl | 0.0023133722 | +| clip_fraction | 0.259 | +| clip_range | 0.0426 | +| entropy_loss | -7.75 | +| explained_variance | -0.0117 | +| learning_rate | 2.99e-05 | +| loss | -0.0164 | +| n_updates | 16776 | +| policy_gradient_loss | -0.0106 | +| value_loss | 0.000145 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.227 | +| time/ | | +| fps | 1384 | +| iterations | 4196 | +| time_elapsed | 6206 | +| total_timesteps | 8593408 | +| train/ | | +| approx_kl | 0.002255293 | +| clip_fraction | 0.196 | +| clip_range | 0.0426 | +| entropy_loss | -7.88 | +| explained_variance | -0.0357 | +| learning_rate | 2.99e-05 | +| loss | -0.0126 | +| n_updates | 16780 | +| policy_gradient_loss | -0.00885 | +| value_loss | 0.000238 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.232 | +| time/ | | +| fps | 1384 | +| iterations | 4197 | +| time_elapsed | 6208 | +| total_timesteps | 8595456 | +| train/ | | +| approx_kl | 0.0020156035 | +| clip_fraction | 0.222 | +| clip_range | 0.0426 | +| entropy_loss | -7.8 | +| explained_variance | 0.0236 | +| learning_rate | 2.99e-05 | +| loss | -0.0161 | +| n_updates | 16784 | +| policy_gradient_loss | -0.0107 | +| value_loss | 0.000201 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.231 | +| time/ | | +| fps | 1384 | +| iterations | 4198 | +| time_elapsed | 6209 | +| total_timesteps | 8597504 | +| train/ | | +| approx_kl | 0.00243028 | +| clip_fraction | 0.223 | +| clip_range | 0.0426 | +| entropy_loss | -7.73 | +| explained_variance | 0.0557 | +| learning_rate | 2.98e-05 | +| loss | -0.0175 | +| n_updates | 16788 | +| policy_gradient_loss | -0.0103 | +| value_loss | 0.000179 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.237 | +| time/ | | +| fps | 1384 | +| iterations | 4199 | +| time_elapsed | 6211 | +| total_timesteps | 8599552 | +| train/ | | +| approx_kl | 0.0022871224 | +| clip_fraction | 0.226 | +| clip_range | 0.0425 | +| entropy_loss | -7.46 | +| explained_variance | 0.0422 | +| learning_rate | 2.98e-05 | +| loss | -0.0169 | +| n_updates | 16792 | +| policy_gradient_loss | -0.00962 | +| value_loss | 0.000263 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.237 | +| time/ | | +| fps | 1384 | +| iterations | 4200 | +| time_elapsed | 6212 | +| total_timesteps | 8601600 | +| train/ | | +| approx_kl | 0.0026556607 | +| clip_fraction | 0.233 | +| clip_range | 0.0425 | +| entropy_loss | -7.66 | +| explained_variance | -0.0895 | +| learning_rate | 2.97e-05 | +| loss | -0.0179 | +| n_updates | 16796 | +| policy_gradient_loss | -0.0108 | +| value_loss | 0.000128 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.238 | +| time/ | | +| fps | 1384 | +| iterations | 4201 | +| time_elapsed | 6214 | +| total_timesteps | 8603648 | +| train/ | | +| approx_kl | 0.0025100647 | +| clip_fraction | 0.231 | +| clip_range | 0.0425 | +| entropy_loss | -7.73 | +| explained_variance | 0.0666 | +| learning_rate | 2.97e-05 | +| loss | -0.0172 | +| n_updates | 16800 | +| policy_gradient_loss | -0.0104 | +| value_loss | 0.000122 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.238 | +| time/ | | +| fps | 1384 | +| iterations | 4202 | +| time_elapsed | 6215 | +| total_timesteps | 8605696 | +| train/ | | +| approx_kl | 0.0023183422 | +| clip_fraction | 0.229 | +| clip_range | 0.0425 | +| entropy_loss | -7.64 | +| explained_variance | 0.0481 | +| learning_rate | 2.96e-05 | +| loss | -0.0189 | +| n_updates | 16804 | +| policy_gradient_loss | -0.011 | +| value_loss | 0.000174 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.243 | +| time/ | | +| fps | 1384 | +| iterations | 4203 | +| time_elapsed | 6217 | +| total_timesteps | 8607744 | +| train/ | | +| approx_kl | 0.0022827783 | +| clip_fraction | 0.227 | +| clip_range | 0.0424 | +| entropy_loss | -7.88 | +| explained_variance | 0.0231 | +| learning_rate | 2.96e-05 | +| loss | -0.0182 | +| n_updates | 16808 | +| policy_gradient_loss | -0.0111 | +| value_loss | 0.000203 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.243 | +| time/ | | +| fps | 1384 | +| iterations | 4204 | +| time_elapsed | 6218 | +| total_timesteps | 8609792 | +| train/ | | +| approx_kl | 0.0020596578 | +| clip_fraction | 0.231 | +| clip_range | 0.0424 | +| entropy_loss | -7.8 | +| explained_variance | 0.0544 | +| learning_rate | 2.96e-05 | +| loss | -0.0165 | +| n_updates | 16812 | +| policy_gradient_loss | -0.0102 | +| value_loss | 0.000245 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.232 | +| time/ | | +| fps | 1384 | +| iterations | 4205 | +| time_elapsed | 6220 | +| total_timesteps | 8611840 | +| train/ | | +| approx_kl | 0.0023972793 | +| clip_fraction | 0.251 | +| clip_range | 0.0424 | +| entropy_loss | -7.76 | +| explained_variance | -0.418 | +| learning_rate | 2.95e-05 | +| loss | -0.021 | +| n_updates | 16816 | +| policy_gradient_loss | -0.0118 | +| value_loss | 0.000109 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.232 | +| time/ | | +| fps | 1384 | +| iterations | 4206 | +| time_elapsed | 6221 | +| total_timesteps | 8613888 | +| train/ | | +| approx_kl | 0.0025987732 | +| clip_fraction | 0.231 | +| clip_range | 0.0424 | +| entropy_loss | -7.8 | +| explained_variance | -0.00515 | +| learning_rate | 2.95e-05 | +| loss | -0.019 | +| n_updates | 16820 | +| policy_gradient_loss | -0.0116 | +| value_loss | 0.00012 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.228 | +| time/ | | +| fps | 1384 | +| iterations | 4207 | +| time_elapsed | 6223 | +| total_timesteps | 8615936 | +| train/ | | +| approx_kl | 0.0021194234 | +| clip_fraction | 0.215 | +| clip_range | 0.0423 | +| entropy_loss | -7.74 | +| explained_variance | -0.00622 | +| learning_rate | 2.94e-05 | +| loss | -0.0156 | +| n_updates | 16824 | +| policy_gradient_loss | -0.00977 | +| value_loss | 0.000122 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.227 | +| time/ | | +| fps | 1384 | +| iterations | 4208 | +| time_elapsed | 6225 | +| total_timesteps | 8617984 | +| train/ | | +| approx_kl | 0.0024640562 | +| clip_fraction | 0.232 | +| clip_range | 0.0423 | +| entropy_loss | -7.71 | +| explained_variance | -0.1 | +| learning_rate | 2.94e-05 | +| loss | -0.0188 | +| n_updates | 16828 | +| policy_gradient_loss | -0.0112 | +| value_loss | 8.56e-05 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.22 | +| time/ | | +| fps | 1384 | +| iterations | 4209 | +| time_elapsed | 6226 | +| total_timesteps | 8620032 | +| train/ | | +| approx_kl | 0.0025236565 | +| clip_fraction | 0.232 | +| clip_range | 0.0423 | +| entropy_loss | -7.9 | +| explained_variance | -0.0126 | +| learning_rate | 2.94e-05 | +| loss | -0.0172 | +| n_updates | 16832 | +| policy_gradient_loss | -0.0111 | +| value_loss | 0.000127 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.214 | +| time/ | | +| fps | 1384 | +| iterations | 4210 | +| time_elapsed | 6228 | +| total_timesteps | 8622080 | +| train/ | | +| approx_kl | 0.002434524 | +| clip_fraction | 0.237 | +| clip_range | 0.0422 | +| entropy_loss | -7.62 | +| explained_variance | -0.00801 | +| learning_rate | 2.93e-05 | +| loss | -0.0176 | +| n_updates | 16836 | +| policy_gradient_loss | -0.0109 | +| value_loss | 0.000136 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.204 | +| time/ | | +| fps | 1384 | +| iterations | 4211 | +| time_elapsed | 6229 | +| total_timesteps | 8624128 | +| train/ | | +| approx_kl | 0.0023109564 | +| clip_fraction | 0.207 | +| clip_range | 0.0422 | +| entropy_loss | -7.68 | +| explained_variance | 0.0427 | +| learning_rate | 2.93e-05 | +| loss | -0.0161 | +| n_updates | 16840 | +| policy_gradient_loss | -0.0101 | +| value_loss | 0.000146 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.208 | +| time/ | | +| fps | 1384 | +| iterations | 4212 | +| time_elapsed | 6231 | +| total_timesteps | 8626176 | +| train/ | | +| approx_kl | 0.002486578 | +| clip_fraction | 0.222 | +| clip_range | 0.0422 | +| entropy_loss | -7.72 | +| explained_variance | -0.0353 | +| learning_rate | 2.92e-05 | +| loss | -0.0176 | +| n_updates | 16844 | +| policy_gradient_loss | -0.0107 | +| value_loss | 0.000165 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.208 | +| time/ | | +| fps | 1384 | +| iterations | 4213 | +| time_elapsed | 6232 | +| total_timesteps | 8628224 | +| train/ | | +| approx_kl | 0.0022188933 | +| clip_fraction | 0.218 | +| clip_range | 0.0422 | +| entropy_loss | -7.69 | +| explained_variance | 0.0186 | +| learning_rate | 2.92e-05 | +| loss | -0.0174 | +| n_updates | 16848 | +| policy_gradient_loss | -0.0102 | +| value_loss | 0.000135 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.209 | +| time/ | | +| fps | 1384 | +| iterations | 4214 | +| time_elapsed | 6234 | +| total_timesteps | 8630272 | +| train/ | | +| approx_kl | 0.001985901 | +| clip_fraction | 0.206 | +| clip_range | 0.0421 | +| entropy_loss | -7.82 | +| explained_variance | 0.0354 | +| learning_rate | 2.92e-05 | +| loss | -0.0147 | +| n_updates | 16852 | +| policy_gradient_loss | -0.00923 | +| value_loss | 0.000178 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.207 | +| time/ | | +| fps | 1384 | +| iterations | 4215 | +| time_elapsed | 6235 | +| total_timesteps | 8632320 | +| train/ | | +| approx_kl | 0.0020010965 | +| clip_fraction | 0.216 | +| clip_range | 0.0421 | +| entropy_loss | -7.74 | +| explained_variance | -0.0947 | +| learning_rate | 2.91e-05 | +| loss | -0.0184 | +| n_updates | 16856 | +| policy_gradient_loss | -0.0103 | +| value_loss | 0.000208 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.211 | +| time/ | | +| fps | 1384 | +| iterations | 4216 | +| time_elapsed | 6237 | +| total_timesteps | 8634368 | +| train/ | | +| approx_kl | 0.002501268 | +| clip_fraction | 0.231 | +| clip_range | 0.0421 | +| entropy_loss | -7.87 | +| explained_variance | -0.0416 | +| learning_rate | 2.91e-05 | +| loss | -0.0176 | +| n_updates | 16860 | +| policy_gradient_loss | -0.0106 | +| value_loss | 0.000154 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.208 | +| time/ | | +| fps | 1384 | +| iterations | 4217 | +| time_elapsed | 6238 | +| total_timesteps | 8636416 | +| train/ | | +| approx_kl | 0.0020032772 | +| clip_fraction | 0.202 | +| clip_range | 0.0421 | +| entropy_loss | -7.7 | +| explained_variance | 0.0537 | +| learning_rate | 2.9e-05 | +| loss | -0.0193 | +| n_updates | 16864 | +| policy_gradient_loss | -0.00954 | +| value_loss | 0.000338 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.208 | +| time/ | | +| fps | 1384 | +| iterations | 4218 | +| time_elapsed | 6240 | +| total_timesteps | 8638464 | +| train/ | | +| approx_kl | 0.0020853556 | +| clip_fraction | 0.221 | +| clip_range | 0.042 | +| entropy_loss | -7.81 | +| explained_variance | -0.00877 | +| learning_rate | 2.9e-05 | +| loss | -0.0148 | +| n_updates | 16868 | +| policy_gradient_loss | -0.00956 | +| value_loss | 0.000137 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.212 | +| time/ | | +| fps | 1384 | +| iterations | 4219 | +| time_elapsed | 6241 | +| total_timesteps | 8640512 | +| train/ | | +| approx_kl | 0.0025562625 | +| clip_fraction | 0.249 | +| clip_range | 0.042 | +| entropy_loss | -7.8 | +| explained_variance | -0.0756 | +| learning_rate | 2.9e-05 | +| loss | -0.0195 | +| n_updates | 16872 | +| policy_gradient_loss | -0.0118 | +| value_loss | 0.000134 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.215 | +| time/ | | +| fps | 1384 | +| iterations | 4220 | +| time_elapsed | 6243 | +| total_timesteps | 8642560 | +| train/ | | +| approx_kl | 0.0022217575 | +| clip_fraction | 0.216 | +| clip_range | 0.042 | +| entropy_loss | -7.82 | +| explained_variance | -0.0131 | +| learning_rate | 2.89e-05 | +| loss | -0.0186 | +| n_updates | 16876 | +| policy_gradient_loss | -0.0108 | +| value_loss | 0.000208 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.218 | +| time/ | | +| fps | 1384 | +| iterations | 4221 | +| time_elapsed | 6245 | +| total_timesteps | 8644608 | +| train/ | | +| approx_kl | 0.0021555617 | +| clip_fraction | 0.244 | +| clip_range | 0.042 | +| entropy_loss | -7.83 | +| explained_variance | -0.0945 | +| learning_rate | 2.89e-05 | +| loss | -0.0225 | +| n_updates | 16880 | +| policy_gradient_loss | -0.0112 | +| value_loss | 8.99e-05 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.223 | +| time/ | | +| fps | 1384 | +| iterations | 4222 | +| time_elapsed | 6246 | +| total_timesteps | 8646656 | +| train/ | | +| approx_kl | 0.0020526454 | +| clip_fraction | 0.231 | +| clip_range | 0.0419 | +| entropy_loss | -7.67 | +| explained_variance | 0.0307 | +| learning_rate | 2.88e-05 | +| loss | -0.0157 | +| n_updates | 16884 | +| policy_gradient_loss | -0.0102 | +| value_loss | 0.000143 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.223 | +| time/ | | +| fps | 1384 | +| iterations | 4223 | +| time_elapsed | 6248 | +| total_timesteps | 8648704 | +| train/ | | +| approx_kl | 0.0021719995 | +| clip_fraction | 0.227 | +| clip_range | 0.0419 | +| entropy_loss | -7.73 | +| explained_variance | -0.0126 | +| learning_rate | 2.88e-05 | +| loss | -0.015 | +| n_updates | 16888 | +| policy_gradient_loss | -0.0103 | +| value_loss | 0.000257 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.221 | +| time/ | | +| fps | 1384 | +| iterations | 4224 | +| time_elapsed | 6249 | +| total_timesteps | 8650752 | +| train/ | | +| approx_kl | 0.0018964934 | +| clip_fraction | 0.206 | +| clip_range | 0.0419 | +| entropy_loss | -7.85 | +| explained_variance | -0.0205 | +| learning_rate | 2.88e-05 | +| loss | -0.0125 | +| n_updates | 16892 | +| policy_gradient_loss | -0.00942 | +| value_loss | 0.000183 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.23 | +| time/ | | +| fps | 1384 | +| iterations | 4225 | +| time_elapsed | 6251 | +| total_timesteps | 8652800 | +| train/ | | +| approx_kl | 0.0021708363 | +| clip_fraction | 0.231 | +| clip_range | 0.0419 | +| entropy_loss | -7.78 | +| explained_variance | 0.0788 | +| learning_rate | 2.87e-05 | +| loss | -0.0162 | +| n_updates | 16896 | +| policy_gradient_loss | -0.01 | +| value_loss | 0.000145 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.233 | +| time/ | | +| fps | 1384 | +| iterations | 4226 | +| time_elapsed | 6253 | +| total_timesteps | 8654848 | +| train/ | | +| approx_kl | 0.002127371 | +| clip_fraction | 0.239 | +| clip_range | 0.0418 | +| entropy_loss | -7.56 | +| explained_variance | -0.0992 | +| learning_rate | 2.87e-05 | +| loss | -0.0168 | +| n_updates | 16900 | +| policy_gradient_loss | -0.0104 | +| value_loss | 0.000206 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.239 | +| time/ | | +| fps | 1384 | +| iterations | 4227 | +| time_elapsed | 6254 | +| total_timesteps | 8656896 | +| train/ | | +| approx_kl | 0.0019763506 | +| clip_fraction | 0.206 | +| clip_range | 0.0418 | +| entropy_loss | -7.77 | +| explained_variance | -0.009 | +| learning_rate | 2.86e-05 | +| loss | -0.0181 | +| n_updates | 16904 | +| policy_gradient_loss | -0.0102 | +| value_loss | 0.000218 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.245 | +| time/ | | +| fps | 1384 | +| iterations | 4228 | +| time_elapsed | 6256 | +| total_timesteps | 8658944 | +| train/ | | +| approx_kl | 0.002328467 | +| clip_fraction | 0.246 | +| clip_range | 0.0418 | +| entropy_loss | -7.73 | +| explained_variance | 0.017 | +| learning_rate | 2.86e-05 | +| loss | -0.0171 | +| n_updates | 16908 | +| policy_gradient_loss | -0.0105 | +| value_loss | 0.000317 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.249 | +| time/ | | +| fps | 1384 | +| iterations | 4229 | +| time_elapsed | 6257 | +| total_timesteps | 8660992 | +| train/ | | +| approx_kl | 0.0022555692 | +| clip_fraction | 0.215 | +| clip_range | 0.0418 | +| entropy_loss | -7.79 | +| explained_variance | 0.0189 | +| learning_rate | 2.86e-05 | +| loss | -0.0155 | +| n_updates | 16912 | +| policy_gradient_loss | -0.0106 | +| value_loss | 0.000144 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.249 | +| time/ | | +| fps | 1384 | +| iterations | 4230 | +| time_elapsed | 6259 | +| total_timesteps | 8663040 | +| train/ | | +| approx_kl | 0.002205004 | +| clip_fraction | 0.236 | +| clip_range | 0.0417 | +| entropy_loss | -7.79 | +| explained_variance | -0.016 | +| learning_rate | 2.85e-05 | +| loss | -0.0182 | +| n_updates | 16916 | +| policy_gradient_loss | -0.0105 | +| value_loss | 0.000307 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.25 | +| time/ | | +| fps | 1384 | +| iterations | 4231 | +| time_elapsed | 6260 | +| total_timesteps | 8665088 | +| train/ | | +| approx_kl | 0.0021184501 | +| clip_fraction | 0.233 | +| clip_range | 0.0417 | +| entropy_loss | -7.84 | +| explained_variance | -0.139 | +| learning_rate | 2.85e-05 | +| loss | -0.017 | +| n_updates | 16920 | +| policy_gradient_loss | -0.0109 | +| value_loss | 0.000119 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.254 | +| time/ | | +| fps | 1383 | +| iterations | 4232 | +| time_elapsed | 6262 | +| total_timesteps | 8667136 | +| train/ | | +| approx_kl | 0.0024956493 | +| clip_fraction | 0.222 | +| clip_range | 0.0417 | +| entropy_loss | -7.85 | +| explained_variance | -0.0965 | +| learning_rate | 2.84e-05 | +| loss | -0.0175 | +| n_updates | 16924 | +| policy_gradient_loss | -0.0111 | +| value_loss | 0.000162 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.259 | +| time/ | | +| fps | 1383 | +| iterations | 4233 | +| time_elapsed | 6264 | +| total_timesteps | 8669184 | +| train/ | | +| approx_kl | 0.0019089944 | +| clip_fraction | 0.201 | +| clip_range | 0.0417 | +| entropy_loss | -7.72 | +| explained_variance | -0.0571 | +| learning_rate | 2.84e-05 | +| loss | -0.0137 | +| n_updates | 16928 | +| policy_gradient_loss | -0.00961 | +| value_loss | 0.000133 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.256 | +| time/ | | +| fps | 1383 | +| iterations | 4234 | +| time_elapsed | 6265 | +| total_timesteps | 8671232 | +| train/ | | +| approx_kl | 0.0021303522 | +| clip_fraction | 0.239 | +| clip_range | 0.0416 | +| entropy_loss | -7.72 | +| explained_variance | 0.00662 | +| learning_rate | 2.84e-05 | +| loss | -0.0172 | +| n_updates | 16932 | +| policy_gradient_loss | -0.0104 | +| value_loss | 0.00033 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.256 | +| time/ | | +| fps | 1383 | +| iterations | 4235 | +| time_elapsed | 6267 | +| total_timesteps | 8673280 | +| train/ | | +| approx_kl | 0.0021472587 | +| clip_fraction | 0.244 | +| clip_range | 0.0416 | +| entropy_loss | -7.83 | +| explained_variance | -0.161 | +| learning_rate | 2.83e-05 | +| loss | -0.0164 | +| n_updates | 16936 | +| policy_gradient_loss | -0.0114 | +| value_loss | 8.9e-05 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.256 | +| time/ | | +| fps | 1383 | +| iterations | 4236 | +| time_elapsed | 6268 | +| total_timesteps | 8675328 | +| train/ | | +| approx_kl | 0.0020276005 | +| clip_fraction | 0.224 | +| clip_range | 0.0416 | +| entropy_loss | -7.92 | +| explained_variance | -0.00508 | +| learning_rate | 2.83e-05 | +| loss | -0.0195 | +| n_updates | 16940 | +| policy_gradient_loss | -0.0109 | +| value_loss | 0.000153 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.26 | +| time/ | | +| fps | 1383 | +| iterations | 4237 | +| time_elapsed | 6270 | +| total_timesteps | 8677376 | +| train/ | | +| approx_kl | 0.0020223684 | +| clip_fraction | 0.214 | +| clip_range | 0.0416 | +| entropy_loss | -7.84 | +| explained_variance | -0.039 | +| learning_rate | 2.82e-05 | +| loss | -0.0168 | +| n_updates | 16944 | +| policy_gradient_loss | -0.0101 | +| value_loss | 0.000143 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.264 | +| time/ | | +| fps | 1383 | +| iterations | 4238 | +| time_elapsed | 6272 | +| total_timesteps | 8679424 | +| train/ | | +| approx_kl | 0.0019718395 | +| clip_fraction | 0.227 | +| clip_range | 0.0415 | +| entropy_loss | -7.53 | +| explained_variance | 0.0134 | +| learning_rate | 2.82e-05 | +| loss | -0.0139 | +| n_updates | 16948 | +| policy_gradient_loss | -0.00899 | +| value_loss | 0.000204 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.263 | +| time/ | | +| fps | 1383 | +| iterations | 4239 | +| time_elapsed | 6273 | +| total_timesteps | 8681472 | +| train/ | | +| approx_kl | 0.0022955232 | +| clip_fraction | 0.211 | +| clip_range | 0.0415 | +| entropy_loss | -7.63 | +| explained_variance | -0.116 | +| learning_rate | 2.81e-05 | +| loss | -0.015 | +| n_updates | 16952 | +| policy_gradient_loss | -0.00992 | +| value_loss | 0.00016 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.263 | +| time/ | | +| fps | 1383 | +| iterations | 4240 | +| time_elapsed | 6275 | +| total_timesteps | 8683520 | +| train/ | | +| approx_kl | 0.0023887353 | +| clip_fraction | 0.224 | +| clip_range | 0.0415 | +| entropy_loss | -7.78 | +| explained_variance | 0.0577 | +| learning_rate | 2.81e-05 | +| loss | -0.017 | +| n_updates | 16956 | +| policy_gradient_loss | -0.00962 | +| value_loss | 0.000118 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.263 | +| time/ | | +| fps | 1383 | +| iterations | 4241 | +| time_elapsed | 6276 | +| total_timesteps | 8685568 | +| train/ | | +| approx_kl | 0.0024177034 | +| clip_fraction | 0.225 | +| clip_range | 0.0415 | +| entropy_loss | -7.84 | +| explained_variance | -0.0984 | +| learning_rate | 2.81e-05 | +| loss | -0.0171 | +| n_updates | 16960 | +| policy_gradient_loss | -0.0105 | +| value_loss | 0.000122 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.268 | +| time/ | | +| fps | 1383 | +| iterations | 4242 | +| time_elapsed | 6278 | +| total_timesteps | 8687616 | +| train/ | | +| approx_kl | 0.0022499664 | +| clip_fraction | 0.243 | +| clip_range | 0.0414 | +| entropy_loss | -7.89 | +| explained_variance | -0.0334 | +| learning_rate | 2.8e-05 | +| loss | -0.0178 | +| n_updates | 16964 | +| policy_gradient_loss | -0.0113 | +| value_loss | 0.000231 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.273 | +| time/ | | +| fps | 1383 | +| iterations | 4243 | +| time_elapsed | 6280 | +| total_timesteps | 8689664 | +| train/ | | +| approx_kl | 0.0016251919 | +| clip_fraction | 0.206 | +| clip_range | 0.0414 | +| entropy_loss | -7.73 | +| explained_variance | 0.12 | +| learning_rate | 2.8e-05 | +| loss | -0.0171 | +| n_updates | 16968 | +| policy_gradient_loss | -0.01 | +| value_loss | 0.000201 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.273 | +| time/ | | +| fps | 1383 | +| iterations | 4244 | +| time_elapsed | 6281 | +| total_timesteps | 8691712 | +| train/ | | +| approx_kl | 0.0016419912 | +| clip_fraction | 0.193 | +| clip_range | 0.0414 | +| entropy_loss | -7.69 | +| explained_variance | 0.03 | +| learning_rate | 2.79e-05 | +| loss | -0.0152 | +| n_updates | 16972 | +| policy_gradient_loss | -0.00838 | +| value_loss | 0.000265 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.283 | +| time/ | | +| fps | 1383 | +| iterations | 4245 | +| time_elapsed | 6283 | +| total_timesteps | 8693760 | +| train/ | | +| approx_kl | 0.002191143 | +| clip_fraction | 0.231 | +| clip_range | 0.0414 | +| entropy_loss | -7.72 | +| explained_variance | -0.0225 | +| learning_rate | 2.79e-05 | +| loss | -0.018 | +| n_updates | 16976 | +| policy_gradient_loss | -0.0106 | +| value_loss | 0.000133 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.286 | +| time/ | | +| fps | 1383 | +| iterations | 4246 | +| time_elapsed | 6284 | +| total_timesteps | 8695808 | +| train/ | | +| approx_kl | 0.0019355189 | +| clip_fraction | 0.21 | +| clip_range | 0.0413 | +| entropy_loss | -7.79 | +| explained_variance | 0.00354 | +| learning_rate | 2.79e-05 | +| loss | -0.0146 | +| n_updates | 16980 | +| policy_gradient_loss | -0.00994 | +| value_loss | 0.000165 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 1383 | +| iterations | 4247 | +| time_elapsed | 6286 | +| total_timesteps | 8697856 | +| train/ | | +| approx_kl | 0.002171556 | +| clip_fraction | 0.215 | +| clip_range | 0.0413 | +| entropy_loss | -7.78 | +| explained_variance | 0.00965 | +| learning_rate | 2.78e-05 | +| loss | -0.0164 | +| n_updates | 16984 | +| policy_gradient_loss | -0.0102 | +| value_loss | 0.000189 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.276 | +| time/ | | +| fps | 1383 | +| iterations | 4248 | +| time_elapsed | 6288 | +| total_timesteps | 8699904 | +| train/ | | +| approx_kl | 0.002413129 | +| clip_fraction | 0.226 | +| clip_range | 0.0413 | +| entropy_loss | -7.8 | +| explained_variance | -0.0666 | +| learning_rate | 2.78e-05 | +| loss | -0.0187 | +| n_updates | 16988 | +| policy_gradient_loss | -0.0117 | +| value_loss | 0.000107 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.276 | +| time/ | | +| fps | 1383 | +| iterations | 4249 | +| time_elapsed | 6289 | +| total_timesteps | 8701952 | +| train/ | | +| approx_kl | 0.0019500979 | +| clip_fraction | 0.204 | +| clip_range | 0.0413 | +| entropy_loss | -7.65 | +| explained_variance | 0.0488 | +| learning_rate | 2.77e-05 | +| loss | -0.0157 | +| n_updates | 16992 | +| policy_gradient_loss | -0.00833 | +| value_loss | 0.000188 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.264 | +| time/ | | +| fps | 1383 | +| iterations | 4250 | +| time_elapsed | 6291 | +| total_timesteps | 8704000 | +| train/ | | +| approx_kl | 0.0021717865 | +| clip_fraction | 0.225 | +| clip_range | 0.0412 | +| entropy_loss | -7.72 | +| explained_variance | -0.0198 | +| learning_rate | 2.77e-05 | +| loss | -0.0156 | +| n_updates | 16996 | +| policy_gradient_loss | -0.0104 | +| value_loss | 0.000188 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.262 | +| time/ | | +| fps | 1383 | +| iterations | 4251 | +| time_elapsed | 6292 | +| total_timesteps | 8706048 | +| train/ | | +| approx_kl | 0.0020255668 | +| clip_fraction | 0.198 | +| clip_range | 0.0412 | +| entropy_loss | -7.76 | +| explained_variance | -0.0419 | +| learning_rate | 2.77e-05 | +| loss | -0.0167 | +| n_updates | 17000 | +| policy_gradient_loss | -0.00907 | +| value_loss | 0.000137 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.262 | +| time/ | | +| fps | 1383 | +| iterations | 4252 | +| time_elapsed | 6294 | +| total_timesteps | 8708096 | +| train/ | | +| approx_kl | 0.00214381 | +| clip_fraction | 0.225 | +| clip_range | 0.0412 | +| entropy_loss | -7.87 | +| explained_variance | -0.0196 | +| learning_rate | 2.76e-05 | +| loss | -0.018 | +| n_updates | 17004 | +| policy_gradient_loss | -0.011 | +| value_loss | 0.000228 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.259 | +| time/ | | +| fps | 1383 | +| iterations | 4253 | +| time_elapsed | 6295 | +| total_timesteps | 8710144 | +| train/ | | +| approx_kl | 0.0021307818 | +| clip_fraction | 0.236 | +| clip_range | 0.0411 | +| entropy_loss | -7.79 | +| explained_variance | 0.00918 | +| learning_rate | 2.76e-05 | +| loss | -0.0157 | +| n_updates | 17008 | +| policy_gradient_loss | -0.00986 | +| value_loss | 0.000136 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.259 | +| time/ | | +| fps | 1383 | +| iterations | 4254 | +| time_elapsed | 6297 | +| total_timesteps | 8712192 | +| train/ | | +| approx_kl | 0.0019906703 | +| clip_fraction | 0.222 | +| clip_range | 0.0411 | +| entropy_loss | -7.92 | +| explained_variance | -0.168 | +| learning_rate | 2.75e-05 | +| loss | -0.0179 | +| n_updates | 17012 | +| policy_gradient_loss | -0.0107 | +| value_loss | 7.62e-05 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.257 | +| time/ | | +| fps | 1383 | +| iterations | 4255 | +| time_elapsed | 6298 | +| total_timesteps | 8714240 | +| train/ | | +| approx_kl | 0.0021179742 | +| clip_fraction | 0.194 | +| clip_range | 0.0411 | +| entropy_loss | -7.66 | +| explained_variance | -0.0384 | +| learning_rate | 2.75e-05 | +| loss | -0.0159 | +| n_updates | 17016 | +| policy_gradient_loss | -0.00982 | +| value_loss | 0.000157 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.269 | +| time/ | | +| fps | 1383 | +| iterations | 4256 | +| time_elapsed | 6300 | +| total_timesteps | 8716288 | +| train/ | | +| approx_kl | 0.001860345 | +| clip_fraction | 0.205 | +| clip_range | 0.0411 | +| entropy_loss | -7.75 | +| explained_variance | 0.0629 | +| learning_rate | 2.75e-05 | +| loss | -0.0179 | +| n_updates | 17020 | +| policy_gradient_loss | -0.00988 | +| value_loss | 0.000169 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.267 | +| time/ | | +| fps | 1383 | +| iterations | 4257 | +| time_elapsed | 6301 | +| total_timesteps | 8718336 | +| train/ | | +| approx_kl | 0.0017655722 | +| clip_fraction | 0.199 | +| clip_range | 0.041 | +| entropy_loss | -7.69 | +| explained_variance | 0.0561 | +| learning_rate | 2.74e-05 | +| loss | -0.0153 | +| n_updates | 17024 | +| policy_gradient_loss | -0.009 | +| value_loss | 0.000282 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.267 | +| time/ | | +| fps | 1383 | +| iterations | 4258 | +| time_elapsed | 6303 | +| total_timesteps | 8720384 | +| train/ | | +| approx_kl | 0.0021117702 | +| clip_fraction | 0.22 | +| clip_range | 0.041 | +| entropy_loss | -7.54 | +| explained_variance | 0.212 | +| learning_rate | 2.74e-05 | +| loss | -0.0154 | +| n_updates | 17028 | +| policy_gradient_loss | -0.00995 | +| value_loss | 0.000154 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.264 | +| time/ | | +| fps | 1383 | +| iterations | 4259 | +| time_elapsed | 6304 | +| total_timesteps | 8722432 | +| train/ | | +| approx_kl | 0.0021529738 | +| clip_fraction | 0.226 | +| clip_range | 0.041 | +| entropy_loss | -7.79 | +| explained_variance | -0.0945 | +| learning_rate | 2.73e-05 | +| loss | -0.0158 | +| n_updates | 17032 | +| policy_gradient_loss | -0.0107 | +| value_loss | 0.000103 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.264 | +| time/ | | +| fps | 1383 | +| iterations | 4260 | +| time_elapsed | 6306 | +| total_timesteps | 8724480 | +| train/ | | +| approx_kl | 0.0020926446 | +| clip_fraction | 0.231 | +| clip_range | 0.041 | +| entropy_loss | -7.8 | +| explained_variance | -0.0423 | +| learning_rate | 2.73e-05 | +| loss | -0.0182 | +| n_updates | 17036 | +| policy_gradient_loss | -0.0106 | +| value_loss | 0.00017 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.264 | +| time/ | | +| fps | 1383 | +| iterations | 4261 | +| time_elapsed | 6308 | +| total_timesteps | 8726528 | +| train/ | | +| approx_kl | 0.0020847358 | +| clip_fraction | 0.208 | +| clip_range | 0.0409 | +| entropy_loss | -7.81 | +| explained_variance | -0.123 | +| learning_rate | 2.73e-05 | +| loss | -0.017 | +| n_updates | 17040 | +| policy_gradient_loss | -0.0105 | +| value_loss | 0.000202 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.268 | +| time/ | | +| fps | 1383 | +| iterations | 4262 | +| time_elapsed | 6309 | +| total_timesteps | 8728576 | +| train/ | | +| approx_kl | 0.0019142508 | +| clip_fraction | 0.201 | +| clip_range | 0.0409 | +| entropy_loss | -7.91 | +| explained_variance | -0.0367 | +| learning_rate | 2.72e-05 | +| loss | -0.0165 | +| n_updates | 17044 | +| policy_gradient_loss | -0.0106 | +| value_loss | 0.000211 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.268 | +| time/ | | +| fps | 1383 | +| iterations | 4263 | +| time_elapsed | 6311 | +| total_timesteps | 8730624 | +| train/ | | +| approx_kl | 0.0021626605 | +| clip_fraction | 0.204 | +| clip_range | 0.0409 | +| entropy_loss | -7.64 | +| explained_variance | -0.0323 | +| learning_rate | 2.72e-05 | +| loss | -0.0153 | +| n_updates | 17048 | +| policy_gradient_loss | -0.0101 | +| value_loss | 0.000317 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.272 | +| time/ | | +| fps | 1383 | +| iterations | 4264 | +| time_elapsed | 6312 | +| total_timesteps | 8732672 | +| train/ | | +| approx_kl | 0.0021450934 | +| clip_fraction | 0.24 | +| clip_range | 0.0409 | +| entropy_loss | -7.82 | +| explained_variance | -0.0389 | +| learning_rate | 2.71e-05 | +| loss | -0.017 | +| n_updates | 17052 | +| policy_gradient_loss | -0.0113 | +| value_loss | 9.24e-05 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.268 | +| time/ | | +| fps | 1383 | +| iterations | 4265 | +| time_elapsed | 6314 | +| total_timesteps | 8734720 | +| train/ | | +| approx_kl | 0.0017461397 | +| clip_fraction | 0.21 | +| clip_range | 0.0408 | +| entropy_loss | -7.68 | +| explained_variance | -0.0395 | +| learning_rate | 2.71e-05 | +| loss | -0.0134 | +| n_updates | 17056 | +| policy_gradient_loss | -0.00876 | +| value_loss | 0.000163 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.272 | +| time/ | | +| fps | 1383 | +| iterations | 4266 | +| time_elapsed | 6315 | +| total_timesteps | 8736768 | +| train/ | | +| approx_kl | 0.0021996992 | +| clip_fraction | 0.236 | +| clip_range | 0.0408 | +| entropy_loss | -7.78 | +| explained_variance | 0.0631 | +| learning_rate | 2.71e-05 | +| loss | -0.0189 | +| n_updates | 17060 | +| policy_gradient_loss | -0.0109 | +| value_loss | 0.000129 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.261 | +| time/ | | +| fps | 1383 | +| iterations | 4267 | +| time_elapsed | 6317 | +| total_timesteps | 8738816 | +| train/ | | +| approx_kl | 0.0021118207 | +| clip_fraction | 0.189 | +| clip_range | 0.0408 | +| entropy_loss | -7.8 | +| explained_variance | -0.0103 | +| learning_rate | 2.7e-05 | +| loss | -0.0181 | +| n_updates | 17064 | +| policy_gradient_loss | -0.00946 | +| value_loss | 0.000383 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.265 | +| time/ | | +| fps | 1383 | +| iterations | 4268 | +| time_elapsed | 6319 | +| total_timesteps | 8740864 | +| train/ | | +| approx_kl | 0.001909572 | +| clip_fraction | 0.212 | +| clip_range | 0.0408 | +| entropy_loss | -7.71 | +| explained_variance | -0.047 | +| learning_rate | 2.7e-05 | +| loss | -0.0154 | +| n_updates | 17068 | +| policy_gradient_loss | -0.00975 | +| value_loss | 0.000159 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.267 | +| time/ | | +| fps | 1383 | +| iterations | 4269 | +| time_elapsed | 6320 | +| total_timesteps | 8742912 | +| train/ | | +| approx_kl | 0.002319571 | +| clip_fraction | 0.24 | +| clip_range | 0.0407 | +| entropy_loss | -7.79 | +| explained_variance | -0.148 | +| learning_rate | 2.69e-05 | +| loss | -0.0192 | +| n_updates | 17072 | +| policy_gradient_loss | -0.0112 | +| value_loss | 6.26e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.271 | +| time/ | | +| fps | 1383 | +| iterations | 4270 | +| time_elapsed | 6322 | +| total_timesteps | 8744960 | +| train/ | | +| approx_kl | 0.0018396265 | +| clip_fraction | 0.203 | +| clip_range | 0.0407 | +| entropy_loss | -7.88 | +| explained_variance | -0.0553 | +| learning_rate | 2.69e-05 | +| loss | -0.0172 | +| n_updates | 17076 | +| policy_gradient_loss | -0.00999 | +| value_loss | 0.000134 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.278 | +| time/ | | +| fps | 1383 | +| iterations | 4271 | +| time_elapsed | 6323 | +| total_timesteps | 8747008 | +| train/ | | +| approx_kl | 0.001969722 | +| clip_fraction | 0.216 | +| clip_range | 0.0407 | +| entropy_loss | -7.76 | +| explained_variance | 0.0502 | +| learning_rate | 2.68e-05 | +| loss | -0.0187 | +| n_updates | 17080 | +| policy_gradient_loss | -0.0109 | +| value_loss | 0.000223 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.281 | +| time/ | | +| fps | 1383 | +| iterations | 4272 | +| time_elapsed | 6325 | +| total_timesteps | 8749056 | +| train/ | | +| approx_kl | 0.0018816296 | +| clip_fraction | 0.212 | +| clip_range | 0.0407 | +| entropy_loss | -7.66 | +| explained_variance | -0.00504 | +| learning_rate | 2.68e-05 | +| loss | -0.014 | +| n_updates | 17084 | +| policy_gradient_loss | -0.00934 | +| value_loss | 0.000189 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.291 | +| time/ | | +| fps | 1383 | +| iterations | 4273 | +| time_elapsed | 6327 | +| total_timesteps | 8751104 | +| train/ | | +| approx_kl | 0.0018176727 | +| clip_fraction | 0.192 | +| clip_range | 0.0406 | +| entropy_loss | -7.81 | +| explained_variance | -0.118 | +| learning_rate | 2.68e-05 | +| loss | -0.0184 | +| n_updates | 17088 | +| policy_gradient_loss | -0.00915 | +| value_loss | 0.00016 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.286 | +| time/ | | +| fps | 1383 | +| iterations | 4274 | +| time_elapsed | 6328 | +| total_timesteps | 8753152 | +| train/ | | +| approx_kl | 0.0016677614 | +| clip_fraction | 0.184 | +| clip_range | 0.0406 | +| entropy_loss | -7.78 | +| explained_variance | -0.0793 | +| learning_rate | 2.67e-05 | +| loss | -0.0132 | +| n_updates | 17092 | +| policy_gradient_loss | -0.00784 | +| value_loss | 0.00036 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.289 | +| time/ | | +| fps | 1383 | +| iterations | 4275 | +| time_elapsed | 6330 | +| total_timesteps | 8755200 | +| train/ | | +| approx_kl | 0.001909039 | +| clip_fraction | 0.22 | +| clip_range | 0.0406 | +| entropy_loss | -7.55 | +| explained_variance | 0.0672 | +| learning_rate | 2.67e-05 | +| loss | -0.0182 | +| n_updates | 17096 | +| policy_gradient_loss | -0.0109 | +| value_loss | 0.000135 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.293 | +| time/ | | +| fps | 1383 | +| iterations | 4276 | +| time_elapsed | 6331 | +| total_timesteps | 8757248 | +| train/ | | +| approx_kl | 0.0018086731 | +| clip_fraction | 0.214 | +| clip_range | 0.0406 | +| entropy_loss | -7.78 | +| explained_variance | 0.092 | +| learning_rate | 2.66e-05 | +| loss | -0.0176 | +| n_updates | 17100 | +| policy_gradient_loss | -0.0101 | +| value_loss | 0.000111 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.285 | +| time/ | | +| fps | 1383 | +| iterations | 4277 | +| time_elapsed | 6333 | +| total_timesteps | 8759296 | +| train/ | | +| approx_kl | 0.0019133523 | +| clip_fraction | 0.187 | +| clip_range | 0.0405 | +| entropy_loss | -7.79 | +| explained_variance | -0.105 | +| learning_rate | 2.66e-05 | +| loss | -0.0171 | +| n_updates | 17104 | +| policy_gradient_loss | -0.00908 | +| value_loss | 0.000156 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.285 | +| time/ | | +| fps | 1383 | +| iterations | 4278 | +| time_elapsed | 6334 | +| total_timesteps | 8761344 | +| train/ | | +| approx_kl | 0.0018527664 | +| clip_fraction | 0.204 | +| clip_range | 0.0405 | +| entropy_loss | -7.63 | +| explained_variance | -0.000926 | +| learning_rate | 2.66e-05 | +| loss | -0.017 | +| n_updates | 17108 | +| policy_gradient_loss | -0.0105 | +| value_loss | 0.000199 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.285 | +| time/ | | +| fps | 1383 | +| iterations | 4279 | +| time_elapsed | 6336 | +| total_timesteps | 8763392 | +| train/ | | +| approx_kl | 0.0018886914 | +| clip_fraction | 0.224 | +| clip_range | 0.0405 | +| entropy_loss | -7.88 | +| explained_variance | -0.0333 | +| learning_rate | 2.65e-05 | +| loss | -0.0158 | +| n_updates | 17112 | +| policy_gradient_loss | -0.00983 | +| value_loss | 0.000125 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.285 | +| time/ | | +| fps | 1382 | +| iterations | 4280 | +| time_elapsed | 6338 | +| total_timesteps | 8765440 | +| train/ | | +| approx_kl | 0.0017278356 | +| clip_fraction | 0.215 | +| clip_range | 0.0405 | +| entropy_loss | -7.9 | +| explained_variance | -0.0187 | +| learning_rate | 2.65e-05 | +| loss | -0.0152 | +| n_updates | 17116 | +| policy_gradient_loss | -0.0102 | +| value_loss | 0.000156 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.284 | +| time/ | | +| fps | 1382 | +| iterations | 4281 | +| time_elapsed | 6339 | +| total_timesteps | 8767488 | +| train/ | | +| approx_kl | 0.001802797 | +| clip_fraction | 0.213 | +| clip_range | 0.0404 | +| entropy_loss | -7.82 | +| explained_variance | 0.0084 | +| learning_rate | 2.64e-05 | +| loss | -0.0165 | +| n_updates | 17120 | +| policy_gradient_loss | -0.00973 | +| value_loss | 0.00014 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 1382 | +| iterations | 4282 | +| time_elapsed | 6341 | +| total_timesteps | 8769536 | +| train/ | | +| approx_kl | 0.0017864329 | +| clip_fraction | 0.179 | +| clip_range | 0.0404 | +| entropy_loss | -7.78 | +| explained_variance | -0.102 | +| learning_rate | 2.64e-05 | +| loss | -0.0142 | +| n_updates | 17124 | +| policy_gradient_loss | -0.00903 | +| value_loss | 0.000149 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.285 | +| time/ | | +| fps | 1382 | +| iterations | 4283 | +| time_elapsed | 6342 | +| total_timesteps | 8771584 | +| train/ | | +| approx_kl | 0.0018655965 | +| clip_fraction | 0.222 | +| clip_range | 0.0404 | +| entropy_loss | -7.75 | +| explained_variance | 0.00155 | +| learning_rate | 2.64e-05 | +| loss | -0.0171 | +| n_updates | 17128 | +| policy_gradient_loss | -0.0108 | +| value_loss | 0.000172 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.292 | +| time/ | | +| fps | 1382 | +| iterations | 4284 | +| time_elapsed | 6344 | +| total_timesteps | 8773632 | +| train/ | | +| approx_kl | 0.0016828935 | +| clip_fraction | 0.183 | +| clip_range | 0.0404 | +| entropy_loss | -7.7 | +| explained_variance | -0.0248 | +| learning_rate | 2.63e-05 | +| loss | -0.0145 | +| n_updates | 17132 | +| policy_gradient_loss | -0.00861 | +| value_loss | 0.00021 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.292 | +| time/ | | +| fps | 1382 | +| iterations | 4285 | +| time_elapsed | 6345 | +| total_timesteps | 8775680 | +| train/ | | +| approx_kl | 0.0017521034 | +| clip_fraction | 0.218 | +| clip_range | 0.0403 | +| entropy_loss | -7.59 | +| explained_variance | 0.0657 | +| learning_rate | 2.63e-05 | +| loss | -0.0176 | +| n_updates | 17136 | +| policy_gradient_loss | -0.00993 | +| value_loss | 0.000382 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.292 | +| time/ | | +| fps | 1382 | +| iterations | 4286 | +| time_elapsed | 6347 | +| total_timesteps | 8777728 | +| train/ | | +| approx_kl | 0.002025923 | +| clip_fraction | 0.223 | +| clip_range | 0.0403 | +| entropy_loss | -7.79 | +| explained_variance | -0.0351 | +| learning_rate | 2.62e-05 | +| loss | -0.0153 | +| n_updates | 17140 | +| policy_gradient_loss | -0.0102 | +| value_loss | 0.000177 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.288 | +| time/ | | +| fps | 1382 | +| iterations | 4287 | +| time_elapsed | 6348 | +| total_timesteps | 8779776 | +| train/ | | +| approx_kl | 0.0021369988 | +| clip_fraction | 0.209 | +| clip_range | 0.0403 | +| entropy_loss | -7.94 | +| explained_variance | -0.0587 | +| learning_rate | 2.62e-05 | +| loss | -0.0163 | +| n_updates | 17144 | +| policy_gradient_loss | -0.0101 | +| value_loss | 0.000107 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.292 | +| time/ | | +| fps | 1382 | +| iterations | 4288 | +| time_elapsed | 6350 | +| total_timesteps | 8781824 | +| train/ | | +| approx_kl | 0.0019845054 | +| clip_fraction | 0.225 | +| clip_range | 0.0403 | +| entropy_loss | -7.83 | +| explained_variance | 0.0694 | +| learning_rate | 2.62e-05 | +| loss | -0.0196 | +| n_updates | 17148 | +| policy_gradient_loss | -0.0114 | +| value_loss | 0.000141 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.286 | +| time/ | | +| fps | 1382 | +| iterations | 4289 | +| time_elapsed | 6351 | +| total_timesteps | 8783872 | +| train/ | | +| approx_kl | 0.0019531023 | +| clip_fraction | 0.226 | +| clip_range | 0.0402 | +| entropy_loss | -7.69 | +| explained_variance | 0.0311 | +| learning_rate | 2.61e-05 | +| loss | -0.0141 | +| n_updates | 17152 | +| policy_gradient_loss | -0.00968 | +| value_loss | 0.000129 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.286 | +| time/ | | +| fps | 1382 | +| iterations | 4290 | +| time_elapsed | 6353 | +| total_timesteps | 8785920 | +| train/ | | +| approx_kl | 0.0018556572 | +| clip_fraction | 0.197 | +| clip_range | 0.0402 | +| entropy_loss | -7.79 | +| explained_variance | -0.0526 | +| learning_rate | 2.61e-05 | +| loss | -0.0162 | +| n_updates | 17156 | +| policy_gradient_loss | -0.0101 | +| value_loss | 0.000139 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.286 | +| time/ | | +| fps | 1382 | +| iterations | 4291 | +| time_elapsed | 6355 | +| total_timesteps | 8787968 | +| train/ | | +| approx_kl | 0.0017607166 | +| clip_fraction | 0.204 | +| clip_range | 0.0402 | +| entropy_loss | -7.75 | +| explained_variance | -0.00177 | +| learning_rate | 2.6e-05 | +| loss | -0.0168 | +| n_updates | 17160 | +| policy_gradient_loss | -0.0099 | +| value_loss | 0.000212 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 1382 | +| iterations | 4292 | +| time_elapsed | 6356 | +| total_timesteps | 8790016 | +| train/ | | +| approx_kl | 0.0020554438 | +| clip_fraction | 0.223 | +| clip_range | 0.0402 | +| entropy_loss | -7.83 | +| explained_variance | 0.0529 | +| learning_rate | 2.6e-05 | +| loss | -0.0158 | +| n_updates | 17164 | +| policy_gradient_loss | -0.0104 | +| value_loss | 0.000131 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.278 | +| time/ | | +| fps | 1382 | +| iterations | 4293 | +| time_elapsed | 6358 | +| total_timesteps | 8792064 | +| train/ | | +| approx_kl | 0.0017882716 | +| clip_fraction | 0.219 | +| clip_range | 0.0401 | +| entropy_loss | -7.75 | +| explained_variance | -0.0697 | +| learning_rate | 2.6e-05 | +| loss | -0.0156 | +| n_updates | 17168 | +| policy_gradient_loss | -0.0096 | +| value_loss | 0.000118 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 1382 | +| iterations | 4294 | +| time_elapsed | 6359 | +| total_timesteps | 8794112 | +| train/ | | +| approx_kl | 0.0014962554 | +| clip_fraction | 0.183 | +| clip_range | 0.0401 | +| entropy_loss | -7.87 | +| explained_variance | 0.0446 | +| learning_rate | 2.59e-05 | +| loss | -0.0144 | +| n_updates | 17172 | +| policy_gradient_loss | -0.00866 | +| value_loss | 0.00021 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.276 | +| time/ | | +| fps | 1382 | +| iterations | 4295 | +| time_elapsed | 6361 | +| total_timesteps | 8796160 | +| train/ | | +| approx_kl | 0.0015906771 | +| clip_fraction | 0.201 | +| clip_range | 0.0401 | +| entropy_loss | -7.7 | +| explained_variance | 0.0887 | +| learning_rate | 2.59e-05 | +| loss | -0.016 | +| n_updates | 17176 | +| policy_gradient_loss | -0.00966 | +| value_loss | 0.000219 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.272 | +| time/ | | +| fps | 1382 | +| iterations | 4296 | +| time_elapsed | 6362 | +| total_timesteps | 8798208 | +| train/ | | +| approx_kl | 0.0017710517 | +| clip_fraction | 0.221 | +| clip_range | 0.04 | +| entropy_loss | -7.83 | +| explained_variance | -0.0967 | +| learning_rate | 2.58e-05 | +| loss | -0.0164 | +| n_updates | 17180 | +| policy_gradient_loss | -0.0108 | +| value_loss | 9.99e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.268 | +| time/ | | +| fps | 1382 | +| iterations | 4297 | +| time_elapsed | 6364 | +| total_timesteps | 8800256 | +| train/ | | +| approx_kl | 0.001675977 | +| clip_fraction | 0.184 | +| clip_range | 0.04 | +| entropy_loss | -7.65 | +| explained_variance | 0.0309 | +| learning_rate | 2.58e-05 | +| loss | -0.0146 | +| n_updates | 17184 | +| policy_gradient_loss | -0.00853 | +| value_loss | 0.000264 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.27 | +| time/ | | +| fps | 1382 | +| iterations | 4298 | +| time_elapsed | 6365 | +| total_timesteps | 8802304 | +| train/ | | +| approx_kl | 0.0017394128 | +| clip_fraction | 0.195 | +| clip_range | 0.04 | +| entropy_loss | -7.79 | +| explained_variance | 0.0203 | +| learning_rate | 2.58e-05 | +| loss | -0.0169 | +| n_updates | 17188 | +| policy_gradient_loss | -0.0102 | +| value_loss | 0.000234 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.268 | +| time/ | | +| fps | 1382 | +| iterations | 4299 | +| time_elapsed | 6367 | +| total_timesteps | 8804352 | +| train/ | | +| approx_kl | 0.0016751228 | +| clip_fraction | 0.19 | +| clip_range | 0.04 | +| entropy_loss | -7.78 | +| explained_variance | -0.0604 | +| learning_rate | 2.57e-05 | +| loss | -0.017 | +| n_updates | 17192 | +| policy_gradient_loss | -0.00921 | +| value_loss | 0.000281 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.266 | +| time/ | | +| fps | 1382 | +| iterations | 4300 | +| time_elapsed | 6368 | +| total_timesteps | 8806400 | +| train/ | | +| approx_kl | 0.0018750512 | +| clip_fraction | 0.219 | +| clip_range | 0.0399 | +| entropy_loss | -7.84 | +| explained_variance | -0.0415 | +| learning_rate | 2.57e-05 | +| loss | -0.0163 | +| n_updates | 17196 | +| policy_gradient_loss | -0.00995 | +| value_loss | 0.00016 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.266 | +| time/ | | +| fps | 1382 | +| iterations | 4301 | +| time_elapsed | 6370 | +| total_timesteps | 8808448 | +| train/ | | +| approx_kl | 0.0020025198 | +| clip_fraction | 0.234 | +| clip_range | 0.0399 | +| entropy_loss | -7.77 | +| explained_variance | 0.00358 | +| learning_rate | 2.56e-05 | +| loss | -0.0164 | +| n_updates | 17200 | +| policy_gradient_loss | -0.0107 | +| value_loss | 0.000107 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.271 | +| time/ | | +| fps | 1382 | +| iterations | 4302 | +| time_elapsed | 6371 | +| total_timesteps | 8810496 | +| train/ | | +| approx_kl | 0.0018625568 | +| clip_fraction | 0.207 | +| clip_range | 0.0399 | +| entropy_loss | -7.87 | +| explained_variance | -0.0335 | +| learning_rate | 2.56e-05 | +| loss | -0.0156 | +| n_updates | 17204 | +| policy_gradient_loss | -0.00962 | +| value_loss | 0.000171 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.271 | +| time/ | | +| fps | 1382 | +| iterations | 4303 | +| time_elapsed | 6373 | +| total_timesteps | 8812544 | +| train/ | | +| approx_kl | 0.0018379112 | +| clip_fraction | 0.211 | +| clip_range | 0.0399 | +| entropy_loss | -7.83 | +| explained_variance | -0.00327 | +| learning_rate | 2.56e-05 | +| loss | -0.0175 | +| n_updates | 17208 | +| policy_gradient_loss | -0.00947 | +| value_loss | 0.000313 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.28 | +| time/ | | +| fps | 1382 | +| iterations | 4304 | +| time_elapsed | 6374 | +| total_timesteps | 8814592 | +| train/ | | +| approx_kl | 0.001876489 | +| clip_fraction | 0.21 | +| clip_range | 0.0398 | +| entropy_loss | -7.92 | +| explained_variance | -0.015 | +| learning_rate | 2.55e-05 | +| loss | -0.0191 | +| n_updates | 17212 | +| policy_gradient_loss | -0.0108 | +| value_loss | 0.000144 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.29 | +| time/ | | +| fps | 1382 | +| iterations | 4305 | +| time_elapsed | 6376 | +| total_timesteps | 8816640 | +| train/ | | +| approx_kl | 0.0016658152 | +| clip_fraction | 0.199 | +| clip_range | 0.0398 | +| entropy_loss | -7.8 | +| explained_variance | -0.0357 | +| learning_rate | 2.55e-05 | +| loss | -0.0146 | +| n_updates | 17216 | +| policy_gradient_loss | -0.00939 | +| value_loss | 0.000255 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.291 | +| time/ | | +| fps | 1382 | +| iterations | 4306 | +| time_elapsed | 6378 | +| total_timesteps | 8818688 | +| train/ | | +| approx_kl | 0.0018495029 | +| clip_fraction | 0.221 | +| clip_range | 0.0398 | +| entropy_loss | -7.64 | +| explained_variance | 0.0427 | +| learning_rate | 2.54e-05 | +| loss | -0.0182 | +| n_updates | 17220 | +| policy_gradient_loss | -0.0103 | +| value_loss | 0.000137 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.285 | +| time/ | | +| fps | 1382 | +| iterations | 4307 | +| time_elapsed | 6379 | +| total_timesteps | 8820736 | +| train/ | | +| approx_kl | 0.0019063978 | +| clip_fraction | 0.213 | +| clip_range | 0.0398 | +| entropy_loss | -7.74 | +| explained_variance | 0.00347 | +| learning_rate | 2.54e-05 | +| loss | -0.0167 | +| n_updates | 17224 | +| policy_gradient_loss | -0.0105 | +| value_loss | 0.0002 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.283 | +| time/ | | +| fps | 1382 | +| iterations | 4308 | +| time_elapsed | 6381 | +| total_timesteps | 8822784 | +| train/ | | +| approx_kl | 0.0019085647 | +| clip_fraction | 0.216 | +| clip_range | 0.0397 | +| entropy_loss | -7.81 | +| explained_variance | 0.0358 | +| learning_rate | 2.53e-05 | +| loss | -0.0169 | +| n_updates | 17228 | +| policy_gradient_loss | -0.0102 | +| value_loss | 0.00016 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.295 | +| time/ | | +| fps | 1382 | +| iterations | 4309 | +| time_elapsed | 6382 | +| total_timesteps | 8824832 | +| train/ | | +| approx_kl | 0.0018009729 | +| clip_fraction | 0.218 | +| clip_range | 0.0397 | +| entropy_loss | -7.83 | +| explained_variance | 0.00512 | +| learning_rate | 2.53e-05 | +| loss | -0.0159 | +| n_updates | 17232 | +| policy_gradient_loss | -0.00978 | +| value_loss | 0.000192 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.295 | +| time/ | | +| fps | 1382 | +| iterations | 4310 | +| time_elapsed | 6384 | +| total_timesteps | 8826880 | +| train/ | | +| approx_kl | 0.0015156087 | +| clip_fraction | 0.188 | +| clip_range | 0.0397 | +| entropy_loss | -7.76 | +| explained_variance | 0.0504 | +| learning_rate | 2.53e-05 | +| loss | -0.0141 | +| n_updates | 17236 | +| policy_gradient_loss | -0.00893 | +| value_loss | 0.000563 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.295 | +| time/ | | +| fps | 1382 | +| iterations | 4311 | +| time_elapsed | 6385 | +| total_timesteps | 8828928 | +| train/ | | +| approx_kl | 0.0018097069 | +| clip_fraction | 0.212 | +| clip_range | 0.0397 | +| entropy_loss | -7.83 | +| explained_variance | -0.096 | +| learning_rate | 2.52e-05 | +| loss | -0.0177 | +| n_updates | 17240 | +| policy_gradient_loss | -0.0108 | +| value_loss | 0.000141 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 1382 | +| iterations | 4312 | +| time_elapsed | 6387 | +| total_timesteps | 8830976 | +| train/ | | +| approx_kl | 0.0015982469 | +| clip_fraction | 0.205 | +| clip_range | 0.0396 | +| entropy_loss | -7.8 | +| explained_variance | -0.03 | +| learning_rate | 2.52e-05 | +| loss | -0.0184 | +| n_updates | 17244 | +| policy_gradient_loss | -0.0108 | +| value_loss | 0.000151 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 1382 | +| iterations | 4313 | +| time_elapsed | 6388 | +| total_timesteps | 8833024 | +| train/ | | +| approx_kl | 0.001581971 | +| clip_fraction | 0.18 | +| clip_range | 0.0396 | +| entropy_loss | -7.71 | +| explained_variance | -0.0709 | +| learning_rate | 2.51e-05 | +| loss | -0.0142 | +| n_updates | 17248 | +| policy_gradient_loss | -0.00801 | +| value_loss | 0.000297 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 1382 | +| iterations | 4314 | +| time_elapsed | 6390 | +| total_timesteps | 8835072 | +| train/ | | +| approx_kl | 0.0017818543 | +| clip_fraction | 0.216 | +| clip_range | 0.0396 | +| entropy_loss | -7.95 | +| explained_variance | -0.0386 | +| learning_rate | 2.51e-05 | +| loss | -0.0151 | +| n_updates | 17252 | +| policy_gradient_loss | -0.00934 | +| value_loss | 0.000179 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1382 | +| iterations | 4315 | +| time_elapsed | 6391 | +| total_timesteps | 8837120 | +| train/ | | +| approx_kl | 0.0016496201 | +| clip_fraction | 0.242 | +| clip_range | 0.0396 | +| entropy_loss | -7.93 | +| explained_variance | -0.216 | +| learning_rate | 2.51e-05 | +| loss | -0.0241 | +| n_updates | 17256 | +| policy_gradient_loss | -0.0121 | +| value_loss | 5.77e-05 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1382 | +| iterations | 4316 | +| time_elapsed | 6393 | +| total_timesteps | 8839168 | +| train/ | | +| approx_kl | 0.0018471284 | +| clip_fraction | 0.207 | +| clip_range | 0.0395 | +| entropy_loss | -7.72 | +| explained_variance | -0.0141 | +| learning_rate | 2.5e-05 | +| loss | -0.0162 | +| n_updates | 17260 | +| policy_gradient_loss | -0.00979 | +| value_loss | 9.34e-05 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1382 | +| iterations | 4317 | +| time_elapsed | 6394 | +| total_timesteps | 8841216 | +| train/ | | +| approx_kl | 0.0017059017 | +| clip_fraction | 0.197 | +| clip_range | 0.0395 | +| entropy_loss | -7.77 | +| explained_variance | 0.00659 | +| learning_rate | 2.5e-05 | +| loss | -0.0166 | +| n_updates | 17264 | +| policy_gradient_loss | -0.00937 | +| value_loss | 0.00024 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1382 | +| iterations | 4318 | +| time_elapsed | 6396 | +| total_timesteps | 8843264 | +| train/ | | +| approx_kl | 0.0017124602 | +| clip_fraction | 0.183 | +| clip_range | 0.0395 | +| entropy_loss | -7.79 | +| explained_variance | -0.024 | +| learning_rate | 2.49e-05 | +| loss | -0.0133 | +| n_updates | 17268 | +| policy_gradient_loss | -0.00798 | +| value_loss | 0.000288 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1382 | +| iterations | 4319 | +| time_elapsed | 6397 | +| total_timesteps | 8845312 | +| train/ | | +| approx_kl | 0.0016395092 | +| clip_fraction | 0.223 | +| clip_range | 0.0395 | +| entropy_loss | -7.73 | +| explained_variance | -0.0931 | +| learning_rate | 2.49e-05 | +| loss | -0.0166 | +| n_updates | 17272 | +| policy_gradient_loss | -0.00976 | +| value_loss | 0.000131 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1382 | +| iterations | 4320 | +| time_elapsed | 6399 | +| total_timesteps | 8847360 | +| train/ | | +| approx_kl | 0.0019121354 | +| clip_fraction | 0.22 | +| clip_range | 0.0394 | +| entropy_loss | -7.83 | +| explained_variance | -0.0548 | +| learning_rate | 2.49e-05 | +| loss | -0.0188 | +| n_updates | 17276 | +| policy_gradient_loss | -0.0104 | +| value_loss | 0.000242 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1382 | +| iterations | 4321 | +| time_elapsed | 6401 | +| total_timesteps | 8849408 | +| train/ | | +| approx_kl | 0.0016790862 | +| clip_fraction | 0.2 | +| clip_range | 0.0394 | +| entropy_loss | -7.7 | +| explained_variance | 0.0476 | +| learning_rate | 2.48e-05 | +| loss | -0.013 | +| n_updates | 17280 | +| policy_gradient_loss | -0.00879 | +| value_loss | 0.000128 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1382 | +| iterations | 4322 | +| time_elapsed | 6402 | +| total_timesteps | 8851456 | +| train/ | | +| approx_kl | 0.0017486752 | +| clip_fraction | 0.217 | +| clip_range | 0.0394 | +| entropy_loss | -7.76 | +| explained_variance | -0.0766 | +| learning_rate | 2.48e-05 | +| loss | -0.017 | +| n_updates | 17284 | +| policy_gradient_loss | -0.0104 | +| value_loss | 0.000124 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1382 | +| iterations | 4323 | +| time_elapsed | 6404 | +| total_timesteps | 8853504 | +| train/ | | +| approx_kl | 0.0017708754 | +| clip_fraction | 0.207 | +| clip_range | 0.0394 | +| entropy_loss | -7.83 | +| explained_variance | 0.0112 | +| learning_rate | 2.47e-05 | +| loss | -0.0149 | +| n_updates | 17288 | +| policy_gradient_loss | -0.00992 | +| value_loss | 9.66e-05 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1382 | +| iterations | 4324 | +| time_elapsed | 6405 | +| total_timesteps | 8855552 | +| train/ | | +| approx_kl | 0.0016357615 | +| clip_fraction | 0.189 | +| clip_range | 0.0393 | +| entropy_loss | -7.94 | +| explained_variance | -0.0208 | +| learning_rate | 2.47e-05 | +| loss | -0.0119 | +| n_updates | 17292 | +| policy_gradient_loss | -0.0093 | +| value_loss | 0.0002 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1382 | +| iterations | 4325 | +| time_elapsed | 6407 | +| total_timesteps | 8857600 | +| train/ | | +| approx_kl | 0.001667839 | +| clip_fraction | 0.193 | +| clip_range | 0.0393 | +| entropy_loss | -7.88 | +| explained_variance | -0.023 | +| learning_rate | 2.47e-05 | +| loss | -0.0153 | +| n_updates | 17296 | +| policy_gradient_loss | -0.00947 | +| value_loss | 0.000186 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1382 | +| iterations | 4326 | +| time_elapsed | 6408 | +| total_timesteps | 8859648 | +| train/ | | +| approx_kl | 0.0016737295 | +| clip_fraction | 0.202 | +| clip_range | 0.0393 | +| entropy_loss | -7.91 | +| explained_variance | 0.00819 | +| learning_rate | 2.46e-05 | +| loss | -0.0159 | +| n_updates | 17300 | +| policy_gradient_loss | -0.00951 | +| value_loss | 0.000142 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1382 | +| iterations | 4327 | +| time_elapsed | 6410 | +| total_timesteps | 8861696 | +| train/ | | +| approx_kl | 0.0015914541 | +| clip_fraction | 0.206 | +| clip_range | 0.0393 | +| entropy_loss | -7.77 | +| explained_variance | -0.073 | +| learning_rate | 2.46e-05 | +| loss | -0.0158 | +| n_updates | 17304 | +| policy_gradient_loss | -0.0101 | +| value_loss | 0.000134 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1382 | +| iterations | 4328 | +| time_elapsed | 6412 | +| total_timesteps | 8863744 | +| train/ | | +| approx_kl | 0.0016666595 | +| clip_fraction | 0.196 | +| clip_range | 0.0392 | +| entropy_loss | -7.85 | +| explained_variance | 0.0166 | +| learning_rate | 2.45e-05 | +| loss | -0.0116 | +| n_updates | 17308 | +| policy_gradient_loss | -0.00932 | +| value_loss | 0.000164 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 1382 | +| iterations | 4329 | +| time_elapsed | 6413 | +| total_timesteps | 8865792 | +| train/ | | +| approx_kl | 0.0015117474 | +| clip_fraction | 0.192 | +| clip_range | 0.0392 | +| entropy_loss | -7.87 | +| explained_variance | -0.144 | +| learning_rate | 2.45e-05 | +| loss | -0.0182 | +| n_updates | 17312 | +| policy_gradient_loss | -0.009 | +| value_loss | 8.79e-05 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.306 | +| time/ | | +| fps | 1382 | +| iterations | 4330 | +| time_elapsed | 6415 | +| total_timesteps | 8867840 | +| train/ | | +| approx_kl | 0.0014623693 | +| clip_fraction | 0.177 | +| clip_range | 0.0392 | +| entropy_loss | -7.85 | +| explained_variance | -0.0279 | +| learning_rate | 2.45e-05 | +| loss | -0.0146 | +| n_updates | 17316 | +| policy_gradient_loss | -0.00972 | +| value_loss | 9.22e-05 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 1382 | +| iterations | 4331 | +| time_elapsed | 6416 | +| total_timesteps | 8869888 | +| train/ | | +| approx_kl | 0.0016810597 | +| clip_fraction | 0.204 | +| clip_range | 0.0392 | +| entropy_loss | -7.65 | +| explained_variance | 0.0989 | +| learning_rate | 2.44e-05 | +| loss | -0.0149 | +| n_updates | 17320 | +| policy_gradient_loss | -0.00949 | +| value_loss | 0.000125 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 1382 | +| iterations | 4332 | +| time_elapsed | 6418 | +| total_timesteps | 8871936 | +| train/ | | +| approx_kl | 0.001740729 | +| clip_fraction | 0.203 | +| clip_range | 0.0391 | +| entropy_loss | -7.76 | +| explained_variance | -0.00445 | +| learning_rate | 2.44e-05 | +| loss | -0.0161 | +| n_updates | 17324 | +| policy_gradient_loss | -0.00947 | +| value_loss | 0.000235 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1382 | +| iterations | 4333 | +| time_elapsed | 6420 | +| total_timesteps | 8873984 | +| train/ | | +| approx_kl | 0.0015071847 | +| clip_fraction | 0.189 | +| clip_range | 0.0391 | +| entropy_loss | -7.72 | +| explained_variance | 0.0267 | +| learning_rate | 2.43e-05 | +| loss | -0.0124 | +| n_updates | 17328 | +| policy_gradient_loss | -0.00864 | +| value_loss | 0.00017 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1382 | +| iterations | 4334 | +| time_elapsed | 6421 | +| total_timesteps | 8876032 | +| train/ | | +| approx_kl | 0.0016656334 | +| clip_fraction | 0.207 | +| clip_range | 0.0391 | +| entropy_loss | -7.72 | +| explained_variance | 0.000163 | +| learning_rate | 2.43e-05 | +| loss | -0.0158 | +| n_updates | 17332 | +| policy_gradient_loss | -0.00984 | +| value_loss | 0.000442 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1382 | +| iterations | 4335 | +| time_elapsed | 6423 | +| total_timesteps | 8878080 | +| train/ | | +| approx_kl | 0.0015616545 | +| clip_fraction | 0.195 | +| clip_range | 0.039 | +| entropy_loss | -7.9 | +| explained_variance | -0.0136 | +| learning_rate | 2.43e-05 | +| loss | -0.0161 | +| n_updates | 17336 | +| policy_gradient_loss | -0.00987 | +| value_loss | 0.000182 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1382 | +| iterations | 4336 | +| time_elapsed | 6424 | +| total_timesteps | 8880128 | +| train/ | | +| approx_kl | 0.0017015802 | +| clip_fraction | 0.2 | +| clip_range | 0.039 | +| entropy_loss | -7.94 | +| explained_variance | 0.0211 | +| learning_rate | 2.42e-05 | +| loss | -0.0173 | +| n_updates | 17340 | +| policy_gradient_loss | -0.0101 | +| value_loss | 0.000221 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1382 | +| iterations | 4337 | +| time_elapsed | 6426 | +| total_timesteps | 8882176 | +| train/ | | +| approx_kl | 0.0012976476 | +| clip_fraction | 0.179 | +| clip_range | 0.039 | +| entropy_loss | -7.72 | +| explained_variance | -0.0255 | +| learning_rate | 2.42e-05 | +| loss | -0.0167 | +| n_updates | 17344 | +| policy_gradient_loss | -0.00814 | +| value_loss | 0.000301 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 1382 | +| iterations | 4338 | +| time_elapsed | 6427 | +| total_timesteps | 8884224 | +| train/ | | +| approx_kl | 0.001504287 | +| clip_fraction | 0.191 | +| clip_range | 0.039 | +| entropy_loss | -7.76 | +| explained_variance | -0.00645 | +| learning_rate | 2.41e-05 | +| loss | -0.0145 | +| n_updates | 17348 | +| policy_gradient_loss | -0.00913 | +| value_loss | 0.00017 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.302 | +| time/ | | +| fps | 1382 | +| iterations | 4339 | +| time_elapsed | 6429 | +| total_timesteps | 8886272 | +| train/ | | +| approx_kl | 0.0017071231 | +| clip_fraction | 0.203 | +| clip_range | 0.0389 | +| entropy_loss | -7.89 | +| explained_variance | -0.0218 | +| learning_rate | 2.41e-05 | +| loss | -0.0147 | +| n_updates | 17352 | +| policy_gradient_loss | -0.00956 | +| value_loss | 0.000127 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1382 | +| iterations | 4340 | +| time_elapsed | 6430 | +| total_timesteps | 8888320 | +| train/ | | +| approx_kl | 0.0013378854 | +| clip_fraction | 0.198 | +| clip_range | 0.0389 | +| entropy_loss | -7.92 | +| explained_variance | -0.0431 | +| learning_rate | 2.41e-05 | +| loss | -0.0153 | +| n_updates | 17356 | +| policy_gradient_loss | -0.00922 | +| value_loss | 0.000134 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1382 | +| iterations | 4341 | +| time_elapsed | 6432 | +| total_timesteps | 8890368 | +| train/ | | +| approx_kl | 0.0015586421 | +| clip_fraction | 0.197 | +| clip_range | 0.0389 | +| entropy_loss | -7.64 | +| explained_variance | 0.149 | +| learning_rate | 2.4e-05 | +| loss | -0.0161 | +| n_updates | 17360 | +| policy_gradient_loss | -0.00955 | +| value_loss | 0.000222 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1382 | +| iterations | 4342 | +| time_elapsed | 6433 | +| total_timesteps | 8892416 | +| train/ | | +| approx_kl | 0.0015593877 | +| clip_fraction | 0.225 | +| clip_range | 0.0389 | +| entropy_loss | -7.74 | +| explained_variance | 0.0606 | +| learning_rate | 2.4e-05 | +| loss | -0.0148 | +| n_updates | 17364 | +| policy_gradient_loss | -0.00935 | +| value_loss | 0.000131 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1382 | +| iterations | 4343 | +| time_elapsed | 6435 | +| total_timesteps | 8894464 | +| train/ | | +| approx_kl | 0.0014114653 | +| clip_fraction | 0.187 | +| clip_range | 0.0388 | +| entropy_loss | -7.86 | +| explained_variance | 0.00569 | +| learning_rate | 2.39e-05 | +| loss | -0.0167 | +| n_updates | 17368 | +| policy_gradient_loss | -0.00895 | +| value_loss | 0.00025 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1382 | +| iterations | 4344 | +| time_elapsed | 6436 | +| total_timesteps | 8896512 | +| train/ | | +| approx_kl | 0.0014886311 | +| clip_fraction | 0.183 | +| clip_range | 0.0388 | +| entropy_loss | -7.72 | +| explained_variance | 0.0649 | +| learning_rate | 2.39e-05 | +| loss | -0.0125 | +| n_updates | 17372 | +| policy_gradient_loss | -0.00913 | +| value_loss | 0.000275 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1382 | +| iterations | 4345 | +| time_elapsed | 6438 | +| total_timesteps | 8898560 | +| train/ | | +| approx_kl | 0.0015599299 | +| clip_fraction | 0.197 | +| clip_range | 0.0388 | +| entropy_loss | -7.9 | +| explained_variance | -0.0127 | +| learning_rate | 2.38e-05 | +| loss | -0.0162 | +| n_updates | 17376 | +| policy_gradient_loss | -0.0102 | +| value_loss | 0.000116 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1382 | +| iterations | 4346 | +| time_elapsed | 6440 | +| total_timesteps | 8900608 | +| train/ | | +| approx_kl | 0.0015753151 | +| clip_fraction | 0.2 | +| clip_range | 0.0388 | +| entropy_loss | -7.84 | +| explained_variance | 0.148 | +| learning_rate | 2.38e-05 | +| loss | -0.0185 | +| n_updates | 17380 | +| policy_gradient_loss | -0.0099 | +| value_loss | 0.000112 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1381 | +| iterations | 4347 | +| time_elapsed | 6441 | +| total_timesteps | 8902656 | +| train/ | | +| approx_kl | 0.0017447271 | +| clip_fraction | 0.219 | +| clip_range | 0.0387 | +| entropy_loss | -7.79 | +| explained_variance | -0.0301 | +| learning_rate | 2.38e-05 | +| loss | -0.016 | +| n_updates | 17384 | +| policy_gradient_loss | -0.0107 | +| value_loss | 0.000115 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1381 | +| iterations | 4348 | +| time_elapsed | 6443 | +| total_timesteps | 8904704 | +| train/ | | +| approx_kl | 0.001408082 | +| clip_fraction | 0.199 | +| clip_range | 0.0387 | +| entropy_loss | -7.83 | +| explained_variance | 0.0224 | +| learning_rate | 2.37e-05 | +| loss | -0.0135 | +| n_updates | 17388 | +| policy_gradient_loss | -0.00886 | +| value_loss | 0.000205 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1381 | +| iterations | 4349 | +| time_elapsed | 6445 | +| total_timesteps | 8906752 | +| train/ | | +| approx_kl | 0.0014516127 | +| clip_fraction | 0.217 | +| clip_range | 0.0387 | +| entropy_loss | -7.8 | +| explained_variance | -0.151 | +| learning_rate | 2.37e-05 | +| loss | -0.0215 | +| n_updates | 17392 | +| policy_gradient_loss | -0.011 | +| value_loss | 6.51e-05 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1381 | +| iterations | 4350 | +| time_elapsed | 6446 | +| total_timesteps | 8908800 | +| train/ | | +| approx_kl | 0.0014669294 | +| clip_fraction | 0.195 | +| clip_range | 0.0387 | +| entropy_loss | -7.9 | +| explained_variance | -0.00416 | +| learning_rate | 2.36e-05 | +| loss | -0.0148 | +| n_updates | 17396 | +| policy_gradient_loss | -0.00926 | +| value_loss | 0.000123 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1381 | +| iterations | 4351 | +| time_elapsed | 6448 | +| total_timesteps | 8910848 | +| train/ | | +| approx_kl | 0.0015253973 | +| clip_fraction | 0.196 | +| clip_range | 0.0386 | +| entropy_loss | -7.79 | +| explained_variance | -0.0269 | +| learning_rate | 2.36e-05 | +| loss | -0.0163 | +| n_updates | 17400 | +| policy_gradient_loss | -0.00911 | +| value_loss | 0.000162 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1381 | +| iterations | 4352 | +| time_elapsed | 6449 | +| total_timesteps | 8912896 | +| train/ | | +| approx_kl | 0.0015853503 | +| clip_fraction | 0.204 | +| clip_range | 0.0386 | +| entropy_loss | -7.82 | +| explained_variance | 0.0825 | +| learning_rate | 2.36e-05 | +| loss | -0.0148 | +| n_updates | 17404 | +| policy_gradient_loss | -0.0095 | +| value_loss | 0.000131 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1381 | +| iterations | 4353 | +| time_elapsed | 6451 | +| total_timesteps | 8914944 | +| train/ | | +| approx_kl | 0.0014138612 | +| clip_fraction | 0.186 | +| clip_range | 0.0386 | +| entropy_loss | -7.81 | +| explained_variance | -0.0576 | +| learning_rate | 2.35e-05 | +| loss | -0.0139 | +| n_updates | 17408 | +| policy_gradient_loss | -0.00842 | +| value_loss | 0.000142 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1381 | +| iterations | 4354 | +| time_elapsed | 6453 | +| total_timesteps | 8916992 | +| train/ | | +| approx_kl | 0.0014850895 | +| clip_fraction | 0.195 | +| clip_range | 0.0386 | +| entropy_loss | -7.7 | +| explained_variance | 0.102 | +| learning_rate | 2.35e-05 | +| loss | -0.0154 | +| n_updates | 17412 | +| policy_gradient_loss | -0.00874 | +| value_loss | 0.00019 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1381 | +| iterations | 4355 | +| time_elapsed | 6454 | +| total_timesteps | 8919040 | +| train/ | | +| approx_kl | 0.0016329645 | +| clip_fraction | 0.19 | +| clip_range | 0.0385 | +| entropy_loss | -7.84 | +| explained_variance | 0.117 | +| learning_rate | 2.34e-05 | +| loss | -0.0177 | +| n_updates | 17416 | +| policy_gradient_loss | -0.0097 | +| value_loss | 5.94e-05 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1381 | +| iterations | 4356 | +| time_elapsed | 6456 | +| total_timesteps | 8921088 | +| train/ | | +| approx_kl | 0.0014800101 | +| clip_fraction | 0.193 | +| clip_range | 0.0385 | +| entropy_loss | -7.68 | +| explained_variance | -0.0702 | +| learning_rate | 2.34e-05 | +| loss | -0.0129 | +| n_updates | 17420 | +| policy_gradient_loss | -0.00907 | +| value_loss | 0.000313 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1381 | +| iterations | 4357 | +| time_elapsed | 6457 | +| total_timesteps | 8923136 | +| train/ | | +| approx_kl | 0.0016345162 | +| clip_fraction | 0.212 | +| clip_range | 0.0385 | +| entropy_loss | -7.89 | +| explained_variance | 0.000802 | +| learning_rate | 2.34e-05 | +| loss | -0.0179 | +| n_updates | 17424 | +| policy_gradient_loss | -0.0103 | +| value_loss | 0.000196 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1381 | +| iterations | 4358 | +| time_elapsed | 6459 | +| total_timesteps | 8925184 | +| train/ | | +| approx_kl | 0.0016906619 | +| clip_fraction | 0.223 | +| clip_range | 0.0385 | +| entropy_loss | -7.8 | +| explained_variance | 0.0693 | +| learning_rate | 2.33e-05 | +| loss | -0.0168 | +| n_updates | 17428 | +| policy_gradient_loss | -0.0108 | +| value_loss | 0.000138 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1381 | +| iterations | 4359 | +| time_elapsed | 6461 | +| total_timesteps | 8927232 | +| train/ | | +| approx_kl | 0.0014074481 | +| clip_fraction | 0.185 | +| clip_range | 0.0384 | +| entropy_loss | -7.86 | +| explained_variance | -0.0546 | +| learning_rate | 2.33e-05 | +| loss | -0.0149 | +| n_updates | 17432 | +| policy_gradient_loss | -0.00934 | +| value_loss | 0.000189 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1381 | +| iterations | 4360 | +| time_elapsed | 6462 | +| total_timesteps | 8929280 | +| train/ | | +| approx_kl | 0.0013294021 | +| clip_fraction | 0.183 | +| clip_range | 0.0384 | +| entropy_loss | -7.93 | +| explained_variance | -0.0599 | +| learning_rate | 2.32e-05 | +| loss | -0.0142 | +| n_updates | 17436 | +| policy_gradient_loss | -0.00871 | +| value_loss | 0.000109 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1381 | +| iterations | 4361 | +| time_elapsed | 6464 | +| total_timesteps | 8931328 | +| train/ | | +| approx_kl | 0.0013720789 | +| clip_fraction | 0.165 | +| clip_range | 0.0384 | +| entropy_loss | -7.96 | +| explained_variance | 0.0125 | +| learning_rate | 2.32e-05 | +| loss | -0.0163 | +| n_updates | 17440 | +| policy_gradient_loss | -0.00876 | +| value_loss | 0.000215 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1381 | +| iterations | 4362 | +| time_elapsed | 6465 | +| total_timesteps | 8933376 | +| train/ | | +| approx_kl | 0.0015564775 | +| clip_fraction | 0.195 | +| clip_range | 0.0384 | +| entropy_loss | -7.88 | +| explained_variance | -0.0375 | +| learning_rate | 2.32e-05 | +| loss | -0.0172 | +| n_updates | 17444 | +| policy_gradient_loss | -0.00926 | +| value_loss | 0.000168 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1381 | +| iterations | 4363 | +| time_elapsed | 6467 | +| total_timesteps | 8935424 | +| train/ | | +| approx_kl | 0.0013944458 | +| clip_fraction | 0.171 | +| clip_range | 0.0383 | +| entropy_loss | -7.84 | +| explained_variance | -0.0963 | +| learning_rate | 2.31e-05 | +| loss | -0.0145 | +| n_updates | 17448 | +| policy_gradient_loss | -0.00846 | +| value_loss | 0.00012 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1381 | +| iterations | 4364 | +| time_elapsed | 6468 | +| total_timesteps | 8937472 | +| train/ | | +| approx_kl | 0.0014857217 | +| clip_fraction | 0.211 | +| clip_range | 0.0383 | +| entropy_loss | -7.53 | +| explained_variance | 0.051 | +| learning_rate | 2.31e-05 | +| loss | -0.0162 | +| n_updates | 17452 | +| policy_gradient_loss | -0.0102 | +| value_loss | 0.000425 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1381 | +| iterations | 4365 | +| time_elapsed | 6470 | +| total_timesteps | 8939520 | +| train/ | | +| approx_kl | 0.0016226422 | +| clip_fraction | 0.19 | +| clip_range | 0.0383 | +| entropy_loss | -7.83 | +| explained_variance | -0.112 | +| learning_rate | 2.3e-05 | +| loss | -0.0173 | +| n_updates | 17456 | +| policy_gradient_loss | -0.00951 | +| value_loss | 0.000115 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1381 | +| iterations | 4366 | +| time_elapsed | 6471 | +| total_timesteps | 8941568 | +| train/ | | +| approx_kl | 0.0013312415 | +| clip_fraction | 0.177 | +| clip_range | 0.0383 | +| entropy_loss | -7.89 | +| explained_variance | 0.0971 | +| learning_rate | 2.3e-05 | +| loss | -0.0152 | +| n_updates | 17460 | +| policy_gradient_loss | -0.00923 | +| value_loss | 0.000183 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1381 | +| iterations | 4367 | +| time_elapsed | 6473 | +| total_timesteps | 8943616 | +| train/ | | +| approx_kl | 0.0014135931 | +| clip_fraction | 0.173 | +| clip_range | 0.0382 | +| entropy_loss | -7.91 | +| explained_variance | -0.0744 | +| learning_rate | 2.3e-05 | +| loss | -0.0119 | +| n_updates | 17464 | +| policy_gradient_loss | -0.00789 | +| value_loss | 0.000165 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1381 | +| iterations | 4368 | +| time_elapsed | 6474 | +| total_timesteps | 8945664 | +| train/ | | +| approx_kl | 0.0012683462 | +| clip_fraction | 0.181 | +| clip_range | 0.0382 | +| entropy_loss | -7.71 | +| explained_variance | 0.147 | +| learning_rate | 2.29e-05 | +| loss | -0.0184 | +| n_updates | 17468 | +| policy_gradient_loss | -0.00831 | +| value_loss | 0.000133 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1381 | +| iterations | 4369 | +| time_elapsed | 6476 | +| total_timesteps | 8947712 | +| train/ | | +| approx_kl | 0.0015385048 | +| clip_fraction | 0.21 | +| clip_range | 0.0382 | +| entropy_loss | -7.86 | +| explained_variance | -0.24 | +| learning_rate | 2.29e-05 | +| loss | -0.0182 | +| n_updates | 17472 | +| policy_gradient_loss | -0.0112 | +| value_loss | 4.82e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1381 | +| iterations | 4370 | +| time_elapsed | 6477 | +| total_timesteps | 8949760 | +| train/ | | +| approx_kl | 0.001440077 | +| clip_fraction | 0.18 | +| clip_range | 0.0382 | +| entropy_loss | -7.87 | +| explained_variance | 0.118 | +| learning_rate | 2.28e-05 | +| loss | -0.013 | +| n_updates | 17476 | +| policy_gradient_loss | -0.00875 | +| value_loss | 0.000188 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1381 | +| iterations | 4371 | +| time_elapsed | 6479 | +| total_timesteps | 8951808 | +| train/ | | +| approx_kl | 0.001544237 | +| clip_fraction | 0.2 | +| clip_range | 0.0381 | +| entropy_loss | -7.73 | +| explained_variance | -0.0399 | +| learning_rate | 2.28e-05 | +| loss | -0.0133 | +| n_updates | 17480 | +| policy_gradient_loss | -0.00928 | +| value_loss | 0.000138 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1381 | +| iterations | 4372 | +| time_elapsed | 6480 | +| total_timesteps | 8953856 | +| train/ | | +| approx_kl | 0.0016984134 | +| clip_fraction | 0.205 | +| clip_range | 0.0381 | +| entropy_loss | -7.88 | +| explained_variance | -0.0892 | +| learning_rate | 2.28e-05 | +| loss | -0.0193 | +| n_updates | 17484 | +| policy_gradient_loss | -0.0103 | +| value_loss | 7.01e-05 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1381 | +| iterations | 4373 | +| time_elapsed | 6482 | +| total_timesteps | 8955904 | +| train/ | | +| approx_kl | 0.0015270008 | +| clip_fraction | 0.171 | +| clip_range | 0.0381 | +| entropy_loss | -7.85 | +| explained_variance | 0.00226 | +| learning_rate | 2.27e-05 | +| loss | -0.0122 | +| n_updates | 17488 | +| policy_gradient_loss | -0.00879 | +| value_loss | 0.00019 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1381 | +| iterations | 4374 | +| time_elapsed | 6483 | +| total_timesteps | 8957952 | +| train/ | | +| approx_kl | 0.0014361952 | +| clip_fraction | 0.158 | +| clip_range | 0.0381 | +| entropy_loss | -7.75 | +| explained_variance | -0.0109 | +| learning_rate | 2.27e-05 | +| loss | -0.0131 | +| n_updates | 17492 | +| policy_gradient_loss | -0.00782 | +| value_loss | 0.000234 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1381 | +| iterations | 4375 | +| time_elapsed | 6485 | +| total_timesteps | 8960000 | +| train/ | | +| approx_kl | 0.0014530407 | +| clip_fraction | 0.18 | +| clip_range | 0.038 | +| entropy_loss | -7.76 | +| explained_variance | -0.00579 | +| learning_rate | 2.26e-05 | +| loss | -0.0136 | +| n_updates | 17496 | +| policy_gradient_loss | -0.00915 | +| value_loss | 0.000158 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1381 | +| iterations | 4376 | +| time_elapsed | 6486 | +| total_timesteps | 8962048 | +| train/ | | +| approx_kl | 0.0017646817 | +| clip_fraction | 0.231 | +| clip_range | 0.038 | +| entropy_loss | -7.73 | +| explained_variance | 0.0245 | +| learning_rate | 2.26e-05 | +| loss | -0.0179 | +| n_updates | 17500 | +| policy_gradient_loss | -0.0105 | +| value_loss | 0.00015 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1381 | +| iterations | 4377 | +| time_elapsed | 6488 | +| total_timesteps | 8964096 | +| train/ | | +| approx_kl | 0.0015347747 | +| clip_fraction | 0.182 | +| clip_range | 0.038 | +| entropy_loss | -7.8 | +| explained_variance | -0.0131 | +| learning_rate | 2.26e-05 | +| loss | -0.0125 | +| n_updates | 17504 | +| policy_gradient_loss | -0.00855 | +| value_loss | 0.000117 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1381 | +| iterations | 4378 | +| time_elapsed | 6490 | +| total_timesteps | 8966144 | +| train/ | | +| approx_kl | 0.0017862438 | +| clip_fraction | 0.191 | +| clip_range | 0.0379 | +| entropy_loss | -7.85 | +| explained_variance | -0.0422 | +| learning_rate | 2.25e-05 | +| loss | -0.0174 | +| n_updates | 17508 | +| policy_gradient_loss | -0.00889 | +| value_loss | 0.000135 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 1381 | +| iterations | 4379 | +| time_elapsed | 6491 | +| total_timesteps | 8968192 | +| train/ | | +| approx_kl | 0.0014711089 | +| clip_fraction | 0.179 | +| clip_range | 0.0379 | +| entropy_loss | -7.78 | +| explained_variance | -0.0688 | +| learning_rate | 2.25e-05 | +| loss | -0.0143 | +| n_updates | 17512 | +| policy_gradient_loss | -0.00888 | +| value_loss | 0.000127 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1381 | +| iterations | 4380 | +| time_elapsed | 6493 | +| total_timesteps | 8970240 | +| train/ | | +| approx_kl | 0.0015955557 | +| clip_fraction | 0.187 | +| clip_range | 0.0379 | +| entropy_loss | -7.83 | +| explained_variance | -0.0595 | +| learning_rate | 2.24e-05 | +| loss | -0.016 | +| n_updates | 17516 | +| policy_gradient_loss | -0.00946 | +| value_loss | 0.000103 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.306 | +| time/ | | +| fps | 1381 | +| iterations | 4381 | +| time_elapsed | 6494 | +| total_timesteps | 8972288 | +| train/ | | +| approx_kl | 0.0011691987 | +| clip_fraction | 0.164 | +| clip_range | 0.0379 | +| entropy_loss | -7.82 | +| explained_variance | 0.041 | +| learning_rate | 2.24e-05 | +| loss | -0.0148 | +| n_updates | 17520 | +| policy_gradient_loss | -0.00817 | +| value_loss | 0.00031 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.306 | +| time/ | | +| fps | 1381 | +| iterations | 4382 | +| time_elapsed | 6496 | +| total_timesteps | 8974336 | +| train/ | | +| approx_kl | 0.0014673751 | +| clip_fraction | 0.189 | +| clip_range | 0.0378 | +| entropy_loss | -7.82 | +| explained_variance | 0.129 | +| learning_rate | 2.23e-05 | +| loss | -0.0137 | +| n_updates | 17524 | +| policy_gradient_loss | -0.00923 | +| value_loss | 0.000109 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.306 | +| time/ | | +| fps | 1381 | +| iterations | 4383 | +| time_elapsed | 6497 | +| total_timesteps | 8976384 | +| train/ | | +| approx_kl | 0.0013428784 | +| clip_fraction | 0.18 | +| clip_range | 0.0378 | +| entropy_loss | -7.81 | +| explained_variance | 0.0169 | +| learning_rate | 2.23e-05 | +| loss | -0.0131 | +| n_updates | 17528 | +| policy_gradient_loss | -0.00861 | +| value_loss | 0.000327 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1381 | +| iterations | 4384 | +| time_elapsed | 6499 | +| total_timesteps | 8978432 | +| train/ | | +| approx_kl | 0.0012656047 | +| clip_fraction | 0.173 | +| clip_range | 0.0378 | +| entropy_loss | -7.93 | +| explained_variance | -0.0886 | +| learning_rate | 2.23e-05 | +| loss | -0.0187 | +| n_updates | 17532 | +| policy_gradient_loss | -0.00905 | +| value_loss | 0.000128 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1381 | +| iterations | 4385 | +| time_elapsed | 6500 | +| total_timesteps | 8980480 | +| train/ | | +| approx_kl | 0.0014432635 | +| clip_fraction | 0.211 | +| clip_range | 0.0378 | +| entropy_loss | -7.74 | +| explained_variance | 0.141 | +| learning_rate | 2.22e-05 | +| loss | -0.0157 | +| n_updates | 17536 | +| policy_gradient_loss | -0.00985 | +| value_loss | 0.000163 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1381 | +| iterations | 4386 | +| time_elapsed | 6502 | +| total_timesteps | 8982528 | +| train/ | | +| approx_kl | 0.0012477415 | +| clip_fraction | 0.156 | +| clip_range | 0.0377 | +| entropy_loss | -7.87 | +| explained_variance | 0.00535 | +| learning_rate | 2.22e-05 | +| loss | -0.0143 | +| n_updates | 17540 | +| policy_gradient_loss | -0.00795 | +| value_loss | 0.000345 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1381 | +| iterations | 4387 | +| time_elapsed | 6503 | +| total_timesteps | 8984576 | +| train/ | | +| approx_kl | 0.0015492908 | +| clip_fraction | 0.186 | +| clip_range | 0.0377 | +| entropy_loss | -7.7 | +| explained_variance | -0.0253 | +| learning_rate | 2.21e-05 | +| loss | -0.0162 | +| n_updates | 17544 | +| policy_gradient_loss | -0.00873 | +| value_loss | 0.000183 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1381 | +| iterations | 4388 | +| time_elapsed | 6505 | +| total_timesteps | 8986624 | +| train/ | | +| approx_kl | 0.0013165041 | +| clip_fraction | 0.178 | +| clip_range | 0.0377 | +| entropy_loss | -7.84 | +| explained_variance | -0.052 | +| learning_rate | 2.21e-05 | +| loss | -0.0144 | +| n_updates | 17548 | +| policy_gradient_loss | -0.00847 | +| value_loss | 0.000147 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1381 | +| iterations | 4389 | +| time_elapsed | 6506 | +| total_timesteps | 8988672 | +| train/ | | +| approx_kl | 0.0013452782 | +| clip_fraction | 0.172 | +| clip_range | 0.0377 | +| entropy_loss | -7.93 | +| explained_variance | -0.00898 | +| learning_rate | 2.21e-05 | +| loss | -0.0136 | +| n_updates | 17552 | +| policy_gradient_loss | -0.00845 | +| value_loss | 0.000177 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1381 | +| iterations | 4390 | +| time_elapsed | 6508 | +| total_timesteps | 8990720 | +| train/ | | +| approx_kl | 0.0014793668 | +| clip_fraction | 0.209 | +| clip_range | 0.0376 | +| entropy_loss | -7.8 | +| explained_variance | 0.0522 | +| learning_rate | 2.2e-05 | +| loss | -0.0172 | +| n_updates | 17556 | +| policy_gradient_loss | -0.00993 | +| value_loss | 8.04e-05 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1381 | +| iterations | 4391 | +| time_elapsed | 6509 | +| total_timesteps | 8992768 | +| train/ | | +| approx_kl | 0.0010371874 | +| clip_fraction | 0.16 | +| clip_range | 0.0376 | +| entropy_loss | -7.82 | +| explained_variance | 0.0736 | +| learning_rate | 2.2e-05 | +| loss | -0.0113 | +| n_updates | 17560 | +| policy_gradient_loss | -0.0064 | +| value_loss | 0.0003 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1381 | +| iterations | 4392 | +| time_elapsed | 6511 | +| total_timesteps | 8994816 | +| train/ | | +| approx_kl | 0.0012434991 | +| clip_fraction | 0.173 | +| clip_range | 0.0376 | +| entropy_loss | -7.75 | +| explained_variance | -0.0269 | +| learning_rate | 2.19e-05 | +| loss | -0.016 | +| n_updates | 17564 | +| policy_gradient_loss | -0.00911 | +| value_loss | 0.000178 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1381 | +| iterations | 4393 | +| time_elapsed | 6512 | +| total_timesteps | 8996864 | +| train/ | | +| approx_kl | 0.0013274421 | +| clip_fraction | 0.184 | +| clip_range | 0.0376 | +| entropy_loss | -7.88 | +| explained_variance | -0.188 | +| learning_rate | 2.19e-05 | +| loss | -0.0162 | +| n_updates | 17568 | +| policy_gradient_loss | -0.00897 | +| value_loss | 9.45e-05 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1381 | +| iterations | 4394 | +| time_elapsed | 6514 | +| total_timesteps | 8998912 | +| train/ | | +| approx_kl | 0.0012807837 | +| clip_fraction | 0.183 | +| clip_range | 0.0375 | +| entropy_loss | -7.78 | +| explained_variance | -0.0564 | +| learning_rate | 2.19e-05 | +| loss | -0.0149 | +| n_updates | 17572 | +| policy_gradient_loss | -0.00946 | +| value_loss | 0.000144 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1381 | +| iterations | 4395 | +| time_elapsed | 6515 | +| total_timesteps | 9000960 | +| train/ | | +| approx_kl | 0.0013834257 | +| clip_fraction | 0.175 | +| clip_range | 0.0375 | +| entropy_loss | -7.88 | +| explained_variance | -0.0181 | +| learning_rate | 2.18e-05 | +| loss | -0.0138 | +| n_updates | 17576 | +| policy_gradient_loss | -0.00886 | +| value_loss | 0.000161 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.315 | +| time/ | | +| fps | 1381 | +| iterations | 4396 | +| time_elapsed | 6517 | +| total_timesteps | 9003008 | +| train/ | | +| approx_kl | 0.0012874333 | +| clip_fraction | 0.179 | +| clip_range | 0.0375 | +| entropy_loss | -7.82 | +| explained_variance | 0.0114 | +| learning_rate | 2.18e-05 | +| loss | -0.0173 | +| n_updates | 17580 | +| policy_gradient_loss | -0.00884 | +| value_loss | 0.00014 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.315 | +| time/ | | +| fps | 1381 | +| iterations | 4397 | +| time_elapsed | 6518 | +| total_timesteps | 9005056 | +| train/ | | +| approx_kl | 0.0011900589 | +| clip_fraction | 0.158 | +| clip_range | 0.0375 | +| entropy_loss | -7.82 | +| explained_variance | 0.00779 | +| learning_rate | 2.17e-05 | +| loss | -0.013 | +| n_updates | 17584 | +| policy_gradient_loss | -0.0071 | +| value_loss | 0.000189 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1381 | +| iterations | 4398 | +| time_elapsed | 6520 | +| total_timesteps | 9007104 | +| train/ | | +| approx_kl | 0.001401381 | +| clip_fraction | 0.18 | +| clip_range | 0.0374 | +| entropy_loss | -7.7 | +| explained_variance | -0.0343 | +| learning_rate | 2.17e-05 | +| loss | -0.0144 | +| n_updates | 17588 | +| policy_gradient_loss | -0.00863 | +| value_loss | 0.000209 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1381 | +| iterations | 4399 | +| time_elapsed | 6522 | +| total_timesteps | 9009152 | +| train/ | | +| approx_kl | 0.0012536019 | +| clip_fraction | 0.177 | +| clip_range | 0.0374 | +| entropy_loss | -7.88 | +| explained_variance | 0.000322 | +| learning_rate | 2.17e-05 | +| loss | -0.0137 | +| n_updates | 17592 | +| policy_gradient_loss | -0.00849 | +| value_loss | 0.00018 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.315 | +| time/ | | +| fps | 1381 | +| iterations | 4400 | +| time_elapsed | 6523 | +| total_timesteps | 9011200 | +| train/ | | +| approx_kl | 0.0013478461 | +| clip_fraction | 0.17 | +| clip_range | 0.0374 | +| entropy_loss | -7.87 | +| explained_variance | -0.0445 | +| learning_rate | 2.16e-05 | +| loss | -0.0159 | +| n_updates | 17596 | +| policy_gradient_loss | -0.00889 | +| value_loss | 0.000138 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1381 | +| iterations | 4401 | +| time_elapsed | 6525 | +| total_timesteps | 9013248 | +| train/ | | +| approx_kl | 0.0010135907 | +| clip_fraction | 0.149 | +| clip_range | 0.0374 | +| entropy_loss | -7.84 | +| explained_variance | -0.0463 | +| learning_rate | 2.16e-05 | +| loss | -0.0139 | +| n_updates | 17600 | +| policy_gradient_loss | -0.00849 | +| value_loss | 0.000173 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 1381 | +| iterations | 4402 | +| time_elapsed | 6526 | +| total_timesteps | 9015296 | +| train/ | | +| approx_kl | 0.0012816566 | +| clip_fraction | 0.197 | +| clip_range | 0.0373 | +| entropy_loss | -7.63 | +| explained_variance | 0.0559 | +| learning_rate | 2.15e-05 | +| loss | -0.0153 | +| n_updates | 17604 | +| policy_gradient_loss | -0.00945 | +| value_loss | 0.00016 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 1381 | +| iterations | 4403 | +| time_elapsed | 6528 | +| total_timesteps | 9017344 | +| train/ | | +| approx_kl | 0.0011998733 | +| clip_fraction | 0.164 | +| clip_range | 0.0373 | +| entropy_loss | -7.77 | +| explained_variance | -0.0243 | +| learning_rate | 2.15e-05 | +| loss | -0.0122 | +| n_updates | 17608 | +| policy_gradient_loss | -0.00784 | +| value_loss | 0.000199 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.306 | +| time/ | | +| fps | 1381 | +| iterations | 4404 | +| time_elapsed | 6529 | +| total_timesteps | 9019392 | +| train/ | | +| approx_kl | 0.0013290171 | +| clip_fraction | 0.179 | +| clip_range | 0.0373 | +| entropy_loss | -7.91 | +| explained_variance | -0.0286 | +| learning_rate | 2.15e-05 | +| loss | -0.0151 | +| n_updates | 17612 | +| policy_gradient_loss | -0.00896 | +| value_loss | 0.000167 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.306 | +| time/ | | +| fps | 1381 | +| iterations | 4405 | +| time_elapsed | 6531 | +| total_timesteps | 9021440 | +| train/ | | +| approx_kl | 0.001351865 | +| clip_fraction | 0.179 | +| clip_range | 0.0373 | +| entropy_loss | -7.86 | +| explained_variance | 0.0742 | +| learning_rate | 2.14e-05 | +| loss | -0.0113 | +| n_updates | 17616 | +| policy_gradient_loss | -0.00838 | +| value_loss | 0.000146 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1381 | +| iterations | 4406 | +| time_elapsed | 6532 | +| total_timesteps | 9023488 | +| train/ | | +| approx_kl | 0.0012080504 | +| clip_fraction | 0.185 | +| clip_range | 0.0372 | +| entropy_loss | -7.92 | +| explained_variance | -0.0508 | +| learning_rate | 2.14e-05 | +| loss | -0.0137 | +| n_updates | 17620 | +| policy_gradient_loss | -0.00835 | +| value_loss | 0.000148 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1381 | +| iterations | 4407 | +| time_elapsed | 6534 | +| total_timesteps | 9025536 | +| train/ | | +| approx_kl | 0.0012957125 | +| clip_fraction | 0.164 | +| clip_range | 0.0372 | +| entropy_loss | -7.82 | +| explained_variance | 0.0127 | +| learning_rate | 2.13e-05 | +| loss | -0.0141 | +| n_updates | 17624 | +| policy_gradient_loss | -0.00834 | +| value_loss | 0.000296 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1381 | +| iterations | 4408 | +| time_elapsed | 6535 | +| total_timesteps | 9027584 | +| train/ | | +| approx_kl | 0.0012696575 | +| clip_fraction | 0.17 | +| clip_range | 0.0372 | +| entropy_loss | -7.75 | +| explained_variance | -0.0928 | +| learning_rate | 2.13e-05 | +| loss | -0.0133 | +| n_updates | 17628 | +| policy_gradient_loss | -0.0088 | +| value_loss | 9.96e-05 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.306 | +| time/ | | +| fps | 1381 | +| iterations | 4409 | +| time_elapsed | 6537 | +| total_timesteps | 9029632 | +| train/ | | +| approx_kl | 0.0012708312 | +| clip_fraction | 0.169 | +| clip_range | 0.0372 | +| entropy_loss | -7.88 | +| explained_variance | -0.18 | +| learning_rate | 2.13e-05 | +| loss | -0.0149 | +| n_updates | 17632 | +| policy_gradient_loss | -0.00828 | +| value_loss | 8.63e-05 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.306 | +| time/ | | +| fps | 1381 | +| iterations | 4410 | +| time_elapsed | 6538 | +| total_timesteps | 9031680 | +| train/ | | +| approx_kl | 0.0012818592 | +| clip_fraction | 0.176 | +| clip_range | 0.0371 | +| entropy_loss | -7.79 | +| explained_variance | -0.0148 | +| learning_rate | 2.12e-05 | +| loss | -0.016 | +| n_updates | 17636 | +| policy_gradient_loss | -0.00858 | +| value_loss | 0.000154 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 1381 | +| iterations | 4411 | +| time_elapsed | 6540 | +| total_timesteps | 9033728 | +| train/ | | +| approx_kl | 0.0009665226 | +| clip_fraction | 0.164 | +| clip_range | 0.0371 | +| entropy_loss | -7.83 | +| explained_variance | 0.0424 | +| learning_rate | 2.12e-05 | +| loss | -0.0143 | +| n_updates | 17640 | +| policy_gradient_loss | -0.00783 | +| value_loss | 0.000143 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.294 | +| time/ | | +| fps | 1381 | +| iterations | 4412 | +| time_elapsed | 6541 | +| total_timesteps | 9035776 | +| train/ | | +| approx_kl | 0.0012465569 | +| clip_fraction | 0.178 | +| clip_range | 0.0371 | +| entropy_loss | -7.87 | +| explained_variance | -0.00417 | +| learning_rate | 2.11e-05 | +| loss | -0.0158 | +| n_updates | 17644 | +| policy_gradient_loss | -0.00864 | +| value_loss | 6.4e-05 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.297 | +| time/ | | +| fps | 1381 | +| iterations | 4413 | +| time_elapsed | 6543 | +| total_timesteps | 9037824 | +| train/ | | +| approx_kl | 0.0011488519 | +| clip_fraction | 0.146 | +| clip_range | 0.0371 | +| entropy_loss | -7.73 | +| explained_variance | -0.0466 | +| learning_rate | 2.11e-05 | +| loss | -0.0116 | +| n_updates | 17648 | +| policy_gradient_loss | -0.00759 | +| value_loss | 0.000127 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 1381 | +| iterations | 4414 | +| time_elapsed | 6544 | +| total_timesteps | 9039872 | +| train/ | | +| approx_kl | 0.0013007442 | +| clip_fraction | 0.186 | +| clip_range | 0.037 | +| entropy_loss | -7.82 | +| explained_variance | 0.0547 | +| learning_rate | 2.11e-05 | +| loss | -0.0137 | +| n_updates | 17652 | +| policy_gradient_loss | -0.00882 | +| value_loss | 0.000165 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.302 | +| time/ | | +| fps | 1381 | +| iterations | 4415 | +| time_elapsed | 6546 | +| total_timesteps | 9041920 | +| train/ | | +| approx_kl | 0.0012441932 | +| clip_fraction | 0.165 | +| clip_range | 0.037 | +| entropy_loss | -7.76 | +| explained_variance | 0.0957 | +| learning_rate | 2.1e-05 | +| loss | -0.0136 | +| n_updates | 17656 | +| policy_gradient_loss | -0.00866 | +| value_loss | 0.000173 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.298 | +| time/ | | +| fps | 1381 | +| iterations | 4416 | +| time_elapsed | 6547 | +| total_timesteps | 9043968 | +| train/ | | +| approx_kl | 0.0011262398 | +| clip_fraction | 0.173 | +| clip_range | 0.037 | +| entropy_loss | -7.82 | +| explained_variance | 0.0219 | +| learning_rate | 2.1e-05 | +| loss | -0.0134 | +| n_updates | 17660 | +| policy_gradient_loss | -0.00835 | +| value_loss | 0.000131 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.3 | +| time/ | | +| fps | 1381 | +| iterations | 4417 | +| time_elapsed | 6549 | +| total_timesteps | 9046016 | +| train/ | | +| approx_kl | 0.0012894771 | +| clip_fraction | 0.179 | +| clip_range | 0.037 | +| entropy_loss | -7.88 | +| explained_variance | -0.0641 | +| learning_rate | 2.09e-05 | +| loss | -0.0153 | +| n_updates | 17664 | +| policy_gradient_loss | -0.00921 | +| value_loss | 0.000242 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.298 | +| time/ | | +| fps | 1381 | +| iterations | 4418 | +| time_elapsed | 6550 | +| total_timesteps | 9048064 | +| train/ | | +| approx_kl | 0.001060605 | +| clip_fraction | 0.168 | +| clip_range | 0.0369 | +| entropy_loss | -7.83 | +| explained_variance | 0.0223 | +| learning_rate | 2.09e-05 | +| loss | -0.0131 | +| n_updates | 17668 | +| policy_gradient_loss | -0.00817 | +| value_loss | 0.000188 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 1381 | +| iterations | 4419 | +| time_elapsed | 6552 | +| total_timesteps | 9050112 | +| train/ | | +| approx_kl | 0.0013235668 | +| clip_fraction | 0.172 | +| clip_range | 0.0369 | +| entropy_loss | -7.86 | +| explained_variance | -0.0547 | +| learning_rate | 2.08e-05 | +| loss | -0.0119 | +| n_updates | 17672 | +| policy_gradient_loss | -0.00801 | +| value_loss | 0.000174 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 1381 | +| iterations | 4420 | +| time_elapsed | 6553 | +| total_timesteps | 9052160 | +| train/ | | +| approx_kl | 0.0010813738 | +| clip_fraction | 0.166 | +| clip_range | 0.0369 | +| entropy_loss | -7.87 | +| explained_variance | -0.0194 | +| learning_rate | 2.08e-05 | +| loss | -0.0115 | +| n_updates | 17676 | +| policy_gradient_loss | -0.00803 | +| value_loss | 0.000198 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.291 | +| time/ | | +| fps | 1381 | +| iterations | 4421 | +| time_elapsed | 6555 | +| total_timesteps | 9054208 | +| train/ | | +| approx_kl | 0.0011980068 | +| clip_fraction | 0.182 | +| clip_range | 0.0368 | +| entropy_loss | -7.73 | +| explained_variance | 0.15 | +| learning_rate | 2.08e-05 | +| loss | -0.0138 | +| n_updates | 17680 | +| policy_gradient_loss | -0.00891 | +| value_loss | 0.000144 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.29 | +| time/ | | +| fps | 1381 | +| iterations | 4422 | +| time_elapsed | 6556 | +| total_timesteps | 9056256 | +| train/ | | +| approx_kl | 0.0012683023 | +| clip_fraction | 0.178 | +| clip_range | 0.0368 | +| entropy_loss | -7.79 | +| explained_variance | -0.00783 | +| learning_rate | 2.07e-05 | +| loss | -0.0148 | +| n_updates | 17684 | +| policy_gradient_loss | -0.00855 | +| value_loss | 0.000137 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.292 | +| time/ | | +| fps | 1381 | +| iterations | 4423 | +| time_elapsed | 6558 | +| total_timesteps | 9058304 | +| train/ | | +| approx_kl | 0.0013313763 | +| clip_fraction | 0.195 | +| clip_range | 0.0368 | +| entropy_loss | -7.79 | +| explained_variance | -0.00589 | +| learning_rate | 2.07e-05 | +| loss | -0.0166 | +| n_updates | 17688 | +| policy_gradient_loss | -0.00966 | +| value_loss | 0.000322 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.29 | +| time/ | | +| fps | 1381 | +| iterations | 4424 | +| time_elapsed | 6560 | +| total_timesteps | 9060352 | +| train/ | | +| approx_kl | 0.0010836412 | +| clip_fraction | 0.158 | +| clip_range | 0.0368 | +| entropy_loss | -7.85 | +| explained_variance | -0.051 | +| learning_rate | 2.06e-05 | +| loss | -0.0105 | +| n_updates | 17692 | +| policy_gradient_loss | -0.00725 | +| value_loss | 0.000179 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.287 | +| time/ | | +| fps | 1381 | +| iterations | 4425 | +| time_elapsed | 6561 | +| total_timesteps | 9062400 | +| train/ | | +| approx_kl | 0.0010488515 | +| clip_fraction | 0.166 | +| clip_range | 0.0367 | +| entropy_loss | -7.8 | +| explained_variance | 0.0115 | +| learning_rate | 2.06e-05 | +| loss | -0.0132 | +| n_updates | 17696 | +| policy_gradient_loss | -0.00824 | +| value_loss | 0.000246 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.291 | +| time/ | | +| fps | 1381 | +| iterations | 4426 | +| time_elapsed | 6563 | +| total_timesteps | 9064448 | +| train/ | | +| approx_kl | 0.0011248975 | +| clip_fraction | 0.165 | +| clip_range | 0.0367 | +| entropy_loss | -7.89 | +| explained_variance | -0.0896 | +| learning_rate | 2.06e-05 | +| loss | -0.0166 | +| n_updates | 17700 | +| policy_gradient_loss | -0.00828 | +| value_loss | 0.000127 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.29 | +| time/ | | +| fps | 1381 | +| iterations | 4427 | +| time_elapsed | 6564 | +| total_timesteps | 9066496 | +| train/ | | +| approx_kl | 0.0012492018 | +| clip_fraction | 0.172 | +| clip_range | 0.0367 | +| entropy_loss | -7.8 | +| explained_variance | 0.0708 | +| learning_rate | 2.05e-05 | +| loss | -0.0133 | +| n_updates | 17704 | +| policy_gradient_loss | -0.00839 | +| value_loss | 0.000129 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.287 | +| time/ | | +| fps | 1381 | +| iterations | 4428 | +| time_elapsed | 6566 | +| total_timesteps | 9068544 | +| train/ | | +| approx_kl | 0.0012137071 | +| clip_fraction | 0.184 | +| clip_range | 0.0367 | +| entropy_loss | -7.88 | +| explained_variance | 0.027 | +| learning_rate | 2.05e-05 | +| loss | -0.0139 | +| n_updates | 17708 | +| policy_gradient_loss | -0.00805 | +| value_loss | 0.000255 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.286 | +| time/ | | +| fps | 1381 | +| iterations | 4429 | +| time_elapsed | 6567 | +| total_timesteps | 9070592 | +| train/ | | +| approx_kl | 0.0012103154 | +| clip_fraction | 0.183 | +| clip_range | 0.0366 | +| entropy_loss | -7.8 | +| explained_variance | -0.111 | +| learning_rate | 2.04e-05 | +| loss | -0.0153 | +| n_updates | 17712 | +| policy_gradient_loss | -0.00936 | +| value_loss | 9.15e-05 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.283 | +| time/ | | +| fps | 1381 | +| iterations | 4430 | +| time_elapsed | 6569 | +| total_timesteps | 9072640 | +| train/ | | +| approx_kl | 0.0012710625 | +| clip_fraction | 0.175 | +| clip_range | 0.0366 | +| entropy_loss | -7.88 | +| explained_variance | -0.101 | +| learning_rate | 2.04e-05 | +| loss | -0.0143 | +| n_updates | 17716 | +| policy_gradient_loss | -0.00934 | +| value_loss | 0.000167 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.28 | +| time/ | | +| fps | 1381 | +| iterations | 4431 | +| time_elapsed | 6570 | +| total_timesteps | 9074688 | +| train/ | | +| approx_kl | 0.0012036562 | +| clip_fraction | 0.173 | +| clip_range | 0.0366 | +| entropy_loss | -7.82 | +| explained_variance | -0.00502 | +| learning_rate | 2.04e-05 | +| loss | -0.0134 | +| n_updates | 17720 | +| policy_gradient_loss | -0.00779 | +| value_loss | 0.000121 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.281 | +| time/ | | +| fps | 1381 | +| iterations | 4432 | +| time_elapsed | 6572 | +| total_timesteps | 9076736 | +| train/ | | +| approx_kl | 0.0012014606 | +| clip_fraction | 0.183 | +| clip_range | 0.0366 | +| entropy_loss | -7.92 | +| explained_variance | -0.0982 | +| learning_rate | 2.03e-05 | +| loss | -0.0135 | +| n_updates | 17724 | +| policy_gradient_loss | -0.00874 | +| value_loss | 0.000124 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 1381 | +| iterations | 4433 | +| time_elapsed | 6573 | +| total_timesteps | 9078784 | +| train/ | | +| approx_kl | 0.0010365013 | +| clip_fraction | 0.16 | +| clip_range | 0.0365 | +| entropy_loss | -7.66 | +| explained_variance | -0.0173 | +| learning_rate | 2.03e-05 | +| loss | -0.0131 | +| n_updates | 17728 | +| policy_gradient_loss | -0.00735 | +| value_loss | 0.000284 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.278 | +| time/ | | +| fps | 1381 | +| iterations | 4434 | +| time_elapsed | 6575 | +| total_timesteps | 9080832 | +| train/ | | +| approx_kl | 0.0011070886 | +| clip_fraction | 0.158 | +| clip_range | 0.0365 | +| entropy_loss | -7.86 | +| explained_variance | 0.00136 | +| learning_rate | 2.02e-05 | +| loss | -0.0151 | +| n_updates | 17732 | +| policy_gradient_loss | -0.00769 | +| value_loss | 0.000101 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.28 | +| time/ | | +| fps | 1380 | +| iterations | 4435 | +| time_elapsed | 6577 | +| total_timesteps | 9082880 | +| train/ | | +| approx_kl | 0.0012955847 | +| clip_fraction | 0.175 | +| clip_range | 0.0365 | +| entropy_loss | -7.84 | +| explained_variance | -0.042 | +| learning_rate | 2.02e-05 | +| loss | -0.0137 | +| n_updates | 17736 | +| policy_gradient_loss | -0.00852 | +| value_loss | 0.00016 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.283 | +| time/ | | +| fps | 1380 | +| iterations | 4436 | +| time_elapsed | 6578 | +| total_timesteps | 9084928 | +| train/ | | +| approx_kl | 0.0011211048 | +| clip_fraction | 0.161 | +| clip_range | 0.0365 | +| entropy_loss | -7.94 | +| explained_variance | -0.0328 | +| learning_rate | 2.02e-05 | +| loss | -0.0149 | +| n_updates | 17740 | +| policy_gradient_loss | -0.00763 | +| value_loss | 0.000119 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.283 | +| time/ | | +| fps | 1380 | +| iterations | 4437 | +| time_elapsed | 6580 | +| total_timesteps | 9086976 | +| train/ | | +| approx_kl | 0.0012652148 | +| clip_fraction | 0.178 | +| clip_range | 0.0364 | +| entropy_loss | -7.75 | +| explained_variance | -0.0926 | +| learning_rate | 2.01e-05 | +| loss | -0.0142 | +| n_updates | 17744 | +| policy_gradient_loss | -0.00849 | +| value_loss | 9.64e-05 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.283 | +| time/ | | +| fps | 1380 | +| iterations | 4438 | +| time_elapsed | 6581 | +| total_timesteps | 9089024 | +| train/ | | +| approx_kl | 0.0011051528 | +| clip_fraction | 0.172 | +| clip_range | 0.0364 | +| entropy_loss | -7.89 | +| explained_variance | -0.025 | +| learning_rate | 2.01e-05 | +| loss | -0.0137 | +| n_updates | 17748 | +| policy_gradient_loss | -0.00765 | +| value_loss | 0.000149 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.284 | +| time/ | | +| fps | 1380 | +| iterations | 4439 | +| time_elapsed | 6583 | +| total_timesteps | 9091072 | +| train/ | | +| approx_kl | 0.0011466795 | +| clip_fraction | 0.158 | +| clip_range | 0.0364 | +| entropy_loss | -7.93 | +| explained_variance | 0.0105 | +| learning_rate | 2e-05 | +| loss | -0.0156 | +| n_updates | 17752 | +| policy_gradient_loss | -0.00869 | +| value_loss | 0.000252 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.286 | +| time/ | | +| fps | 1380 | +| iterations | 4440 | +| time_elapsed | 6584 | +| total_timesteps | 9093120 | +| train/ | | +| approx_kl | 0.001234404 | +| clip_fraction | 0.205 | +| clip_range | 0.0364 | +| entropy_loss | -7.84 | +| explained_variance | -0.107 | +| learning_rate | 2e-05 | +| loss | -0.0178 | +| n_updates | 17756 | +| policy_gradient_loss | -0.0107 | +| value_loss | 4.51e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.29 | +| time/ | | +| fps | 1380 | +| iterations | 4441 | +| time_elapsed | 6586 | +| total_timesteps | 9095168 | +| train/ | | +| approx_kl | 0.0010804634 | +| clip_fraction | 0.165 | +| clip_range | 0.0363 | +| entropy_loss | -7.74 | +| explained_variance | -0.0078 | +| learning_rate | 2e-05 | +| loss | -0.0136 | +| n_updates | 17760 | +| policy_gradient_loss | -0.00801 | +| value_loss | 0.000281 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.286 | +| time/ | | +| fps | 1380 | +| iterations | 4442 | +| time_elapsed | 6587 | +| total_timesteps | 9097216 | +| train/ | | +| approx_kl | 0.0010247456 | +| clip_fraction | 0.156 | +| clip_range | 0.0363 | +| entropy_loss | -7.61 | +| explained_variance | 0.019 | +| learning_rate | 1.99e-05 | +| loss | -0.012 | +| n_updates | 17764 | +| policy_gradient_loss | -0.00721 | +| value_loss | 0.000196 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.283 | +| time/ | | +| fps | 1380 | +| iterations | 4443 | +| time_elapsed | 6589 | +| total_timesteps | 9099264 | +| train/ | | +| approx_kl | 0.0010751948 | +| clip_fraction | 0.159 | +| clip_range | 0.0363 | +| entropy_loss | -7.77 | +| explained_variance | -0.0655 | +| learning_rate | 1.99e-05 | +| loss | -0.0138 | +| n_updates | 17768 | +| policy_gradient_loss | -0.00839 | +| value_loss | 0.000118 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.287 | +| time/ | | +| fps | 1380 | +| iterations | 4444 | +| time_elapsed | 6590 | +| total_timesteps | 9101312 | +| train/ | | +| approx_kl | 0.0013023092 | +| clip_fraction | 0.165 | +| clip_range | 0.0363 | +| entropy_loss | -7.89 | +| explained_variance | -0.0958 | +| learning_rate | 1.98e-05 | +| loss | -0.0164 | +| n_updates | 17772 | +| policy_gradient_loss | -0.00854 | +| value_loss | 9.7e-05 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.287 | +| time/ | | +| fps | 1380 | +| iterations | 4445 | +| time_elapsed | 6592 | +| total_timesteps | 9103360 | +| train/ | | +| approx_kl | 0.0010974293 | +| clip_fraction | 0.16 | +| clip_range | 0.0362 | +| entropy_loss | -7.8 | +| explained_variance | 0.0442 | +| learning_rate | 1.98e-05 | +| loss | -0.0116 | +| n_updates | 17776 | +| policy_gradient_loss | -0.00757 | +| value_loss | 0.000117 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.281 | +| time/ | | +| fps | 1380 | +| iterations | 4446 | +| time_elapsed | 6594 | +| total_timesteps | 9105408 | +| train/ | | +| approx_kl | 0.0011754137 | +| clip_fraction | 0.162 | +| clip_range | 0.0362 | +| entropy_loss | -7.94 | +| explained_variance | -0.0319 | +| learning_rate | 1.98e-05 | +| loss | -0.015 | +| n_updates | 17780 | +| policy_gradient_loss | -0.00859 | +| value_loss | 9.9e-05 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.278 | +| time/ | | +| fps | 1380 | +| iterations | 4447 | +| time_elapsed | 6595 | +| total_timesteps | 9107456 | +| train/ | | +| approx_kl | 0.0010741452 | +| clip_fraction | 0.16 | +| clip_range | 0.0362 | +| entropy_loss | -7.85 | +| explained_variance | -0.0333 | +| learning_rate | 1.97e-05 | +| loss | -0.0124 | +| n_updates | 17784 | +| policy_gradient_loss | -0.00802 | +| value_loss | 7.89e-05 | +------------------------------------------ +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.274 | +| time/ | | +| fps | 1380 | +| iterations | 4448 | +| time_elapsed | 6597 | +| total_timesteps | 9109504 | +| train/ | | +| approx_kl | 0.00090276357 | +| clip_fraction | 0.147 | +| clip_range | 0.0362 | +| entropy_loss | -7.86 | +| explained_variance | -0.0272 | +| learning_rate | 1.97e-05 | +| loss | -0.0098 | +| n_updates | 17788 | +| policy_gradient_loss | -0.0072 | +| value_loss | 0.00013 | +------------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.271 | +| time/ | | +| fps | 1380 | +| iterations | 4449 | +| time_elapsed | 6598 | +| total_timesteps | 9111552 | +| train/ | | +| approx_kl | 0.0011432471 | +| clip_fraction | 0.167 | +| clip_range | 0.0361 | +| entropy_loss | -7.68 | +| explained_variance | 0.105 | +| learning_rate | 1.96e-05 | +| loss | -0.0151 | +| n_updates | 17792 | +| policy_gradient_loss | -0.00873 | +| value_loss | 0.000289 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.271 | +| time/ | | +| fps | 1380 | +| iterations | 4450 | +| time_elapsed | 6600 | +| total_timesteps | 9113600 | +| train/ | | +| approx_kl | 0.0011006086 | +| clip_fraction | 0.17 | +| clip_range | 0.0361 | +| entropy_loss | -7.83 | +| explained_variance | 0.0212 | +| learning_rate | 1.96e-05 | +| loss | -0.0122 | +| n_updates | 17796 | +| policy_gradient_loss | -0.00762 | +| value_loss | 0.000101 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.271 | +| time/ | | +| fps | 1380 | +| iterations | 4451 | +| time_elapsed | 6601 | +| total_timesteps | 9115648 | +| train/ | | +| approx_kl | 0.0011786267 | +| clip_fraction | 0.143 | +| clip_range | 0.0361 | +| entropy_loss | -7.94 | +| explained_variance | -0.0205 | +| learning_rate | 1.96e-05 | +| loss | -0.0137 | +| n_updates | 17800 | +| policy_gradient_loss | -0.008 | +| value_loss | 0.000114 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.266 | +| time/ | | +| fps | 1380 | +| iterations | 4452 | +| time_elapsed | 6603 | +| total_timesteps | 9117696 | +| train/ | | +| approx_kl | 0.001093989 | +| clip_fraction | 0.176 | +| clip_range | 0.0361 | +| entropy_loss | -7.74 | +| explained_variance | -0.0575 | +| learning_rate | 1.95e-05 | +| loss | -0.0126 | +| n_updates | 17804 | +| policy_gradient_loss | -0.00843 | +| value_loss | 0.000164 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.266 | +| time/ | | +| fps | 1380 | +| iterations | 4453 | +| time_elapsed | 6604 | +| total_timesteps | 9119744 | +| train/ | | +| approx_kl | 0.0011095682 | +| clip_fraction | 0.167 | +| clip_range | 0.036 | +| entropy_loss | -7.67 | +| explained_variance | 0.0957 | +| learning_rate | 1.95e-05 | +| loss | -0.014 | +| n_updates | 17808 | +| policy_gradient_loss | -0.00826 | +| value_loss | 0.000174 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.253 | +| time/ | | +| fps | 1380 | +| iterations | 4454 | +| time_elapsed | 6606 | +| total_timesteps | 9121792 | +| train/ | | +| approx_kl | 0.0010734629 | +| clip_fraction | 0.182 | +| clip_range | 0.036 | +| entropy_loss | -7.85 | +| explained_variance | -0.111 | +| learning_rate | 1.94e-05 | +| loss | -0.018 | +| n_updates | 17812 | +| policy_gradient_loss | -0.00932 | +| value_loss | 5.52e-05 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.253 | +| time/ | | +| fps | 1380 | +| iterations | 4455 | +| time_elapsed | 6607 | +| total_timesteps | 9123840 | +| train/ | | +| approx_kl | 0.0012244527 | +| clip_fraction | 0.17 | +| clip_range | 0.036 | +| entropy_loss | -7.76 | +| explained_variance | -0.0224 | +| learning_rate | 1.94e-05 | +| loss | -0.0144 | +| n_updates | 17816 | +| policy_gradient_loss | -0.00848 | +| value_loss | 0.000146 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.253 | +| time/ | | +| fps | 1380 | +| iterations | 4456 | +| time_elapsed | 6609 | +| total_timesteps | 9125888 | +| train/ | | +| approx_kl | 0.0010012479 | +| clip_fraction | 0.167 | +| clip_range | 0.036 | +| entropy_loss | -7.87 | +| explained_variance | 0.0669 | +| learning_rate | 1.93e-05 | +| loss | -0.0143 | +| n_updates | 17820 | +| policy_gradient_loss | -0.00841 | +| value_loss | 0.000177 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.253 | +| time/ | | +| fps | 1380 | +| iterations | 4457 | +| time_elapsed | 6610 | +| total_timesteps | 9127936 | +| train/ | | +| approx_kl | 0.0009908514 | +| clip_fraction | 0.152 | +| clip_range | 0.0359 | +| entropy_loss | -7.94 | +| explained_variance | 0.000208 | +| learning_rate | 1.93e-05 | +| loss | -0.016 | +| n_updates | 17824 | +| policy_gradient_loss | -0.00848 | +| value_loss | 0.000145 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.258 | +| time/ | | +| fps | 1380 | +| iterations | 4458 | +| time_elapsed | 6612 | +| total_timesteps | 9129984 | +| train/ | | +| approx_kl | 0.0010024637 | +| clip_fraction | 0.163 | +| clip_range | 0.0359 | +| entropy_loss | -7.95 | +| explained_variance | 0.000634 | +| learning_rate | 1.93e-05 | +| loss | -0.0139 | +| n_updates | 17828 | +| policy_gradient_loss | -0.00769 | +| value_loss | 0.000134 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.264 | +| time/ | | +| fps | 1380 | +| iterations | 4459 | +| time_elapsed | 6613 | +| total_timesteps | 9132032 | +| train/ | | +| approx_kl | 0.0008952903 | +| clip_fraction | 0.136 | +| clip_range | 0.0359 | +| entropy_loss | -7.88 | +| explained_variance | -0.0314 | +| learning_rate | 1.92e-05 | +| loss | -0.0138 | +| n_updates | 17832 | +| policy_gradient_loss | -0.00686 | +| value_loss | 0.000142 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.259 | +| time/ | | +| fps | 1380 | +| iterations | 4460 | +| time_elapsed | 6615 | +| total_timesteps | 9134080 | +| train/ | | +| approx_kl | 0.0010823855 | +| clip_fraction | 0.178 | +| clip_range | 0.0358 | +| entropy_loss | -7.82 | +| explained_variance | -0.0697 | +| learning_rate | 1.92e-05 | +| loss | -0.0144 | +| n_updates | 17836 | +| policy_gradient_loss | -0.00827 | +| value_loss | 0.000191 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.259 | +| time/ | | +| fps | 1380 | +| iterations | 4461 | +| time_elapsed | 6616 | +| total_timesteps | 9136128 | +| train/ | | +| approx_kl | 0.0010550297 | +| clip_fraction | 0.136 | +| clip_range | 0.0358 | +| entropy_loss | -7.88 | +| explained_variance | 0.0496 | +| learning_rate | 1.91e-05 | +| loss | -0.0135 | +| n_updates | 17840 | +| policy_gradient_loss | -0.0081 | +| value_loss | 0.000174 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.26 | +| time/ | | +| fps | 1380 | +| iterations | 4462 | +| time_elapsed | 6618 | +| total_timesteps | 9138176 | +| train/ | | +| approx_kl | 0.000982301 | +| clip_fraction | 0.15 | +| clip_range | 0.0358 | +| entropy_loss | -7.93 | +| explained_variance | -0.0511 | +| learning_rate | 1.91e-05 | +| loss | -0.0117 | +| n_updates | 17844 | +| policy_gradient_loss | -0.00754 | +| value_loss | 7.73e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.262 | +| time/ | | +| fps | 1380 | +| iterations | 4463 | +| time_elapsed | 6620 | +| total_timesteps | 9140224 | +| train/ | | +| approx_kl | 0.0010472354 | +| clip_fraction | 0.171 | +| clip_range | 0.0358 | +| entropy_loss | -7.81 | +| explained_variance | 0.075 | +| learning_rate | 1.91e-05 | +| loss | -0.0147 | +| n_updates | 17848 | +| policy_gradient_loss | -0.00798 | +| value_loss | 7.73e-05 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.26 | +| time/ | | +| fps | 1380 | +| iterations | 4464 | +| time_elapsed | 6621 | +| total_timesteps | 9142272 | +| train/ | | +| approx_kl | 0.0011513757 | +| clip_fraction | 0.166 | +| clip_range | 0.0357 | +| entropy_loss | -7.67 | +| explained_variance | 0.0102 | +| learning_rate | 1.9e-05 | +| loss | -0.0129 | +| n_updates | 17852 | +| policy_gradient_loss | -0.00802 | +| value_loss | 0.000162 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.26 | +| time/ | | +| fps | 1380 | +| iterations | 4465 | +| time_elapsed | 6623 | +| total_timesteps | 9144320 | +| train/ | | +| approx_kl | 0.0008054424 | +| clip_fraction | 0.124 | +| clip_range | 0.0357 | +| entropy_loss | -7.81 | +| explained_variance | -0.076 | +| learning_rate | 1.9e-05 | +| loss | -0.0114 | +| n_updates | 17856 | +| policy_gradient_loss | -0.00704 | +| value_loss | 0.000192 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.255 | +| time/ | | +| fps | 1380 | +| iterations | 4466 | +| time_elapsed | 6624 | +| total_timesteps | 9146368 | +| train/ | | +| approx_kl | 0.0012180337 | +| clip_fraction | 0.172 | +| clip_range | 0.0357 | +| entropy_loss | -7.55 | +| explained_variance | -0.000895 | +| learning_rate | 1.89e-05 | +| loss | -0.0128 | +| n_updates | 17860 | +| policy_gradient_loss | -0.00816 | +| value_loss | 0.000188 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.255 | +| time/ | | +| fps | 1380 | +| iterations | 4467 | +| time_elapsed | 6626 | +| total_timesteps | 9148416 | +| train/ | | +| approx_kl | 0.0009867313 | +| clip_fraction | 0.144 | +| clip_range | 0.0357 | +| entropy_loss | -7.82 | +| explained_variance | -0.00929 | +| learning_rate | 1.89e-05 | +| loss | -0.0118 | +| n_updates | 17864 | +| policy_gradient_loss | -0.00765 | +| value_loss | 0.000151 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.255 | +| time/ | | +| fps | 1380 | +| iterations | 4468 | +| time_elapsed | 6627 | +| total_timesteps | 9150464 | +| train/ | | +| approx_kl | 0.0009974883 | +| clip_fraction | 0.173 | +| clip_range | 0.0356 | +| entropy_loss | -7.94 | +| explained_variance | 0.0298 | +| learning_rate | 1.89e-05 | +| loss | -0.0133 | +| n_updates | 17868 | +| policy_gradient_loss | -0.00849 | +| value_loss | 0.000213 | +------------------------------------------ +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.253 | +| time/ | | +| fps | 1380 | +| iterations | 4469 | +| time_elapsed | 6629 | +| total_timesteps | 9152512 | +| train/ | | +| approx_kl | 0.00094886473 | +| clip_fraction | 0.15 | +| clip_range | 0.0356 | +| entropy_loss | -7.97 | +| explained_variance | -0.069 | +| learning_rate | 1.88e-05 | +| loss | -0.0118 | +| n_updates | 17872 | +| policy_gradient_loss | -0.00729 | +| value_loss | 0.000168 | +------------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.257 | +| time/ | | +| fps | 1380 | +| iterations | 4470 | +| time_elapsed | 6630 | +| total_timesteps | 9154560 | +| train/ | | +| approx_kl | 0.0007537276 | +| clip_fraction | 0.115 | +| clip_range | 0.0356 | +| entropy_loss | -7.9 | +| explained_variance | 0.0332 | +| learning_rate | 1.88e-05 | +| loss | -0.0121 | +| n_updates | 17876 | +| policy_gradient_loss | -0.00663 | +| value_loss | 0.000314 | +------------------------------------------ +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.253 | +| time/ | | +| fps | 1380 | +| iterations | 4471 | +| time_elapsed | 6632 | +| total_timesteps | 9156608 | +| train/ | | +| approx_kl | 0.00094877055 | +| clip_fraction | 0.152 | +| clip_range | 0.0356 | +| entropy_loss | -7.76 | +| explained_variance | -0.0234 | +| learning_rate | 1.87e-05 | +| loss | -0.0143 | +| n_updates | 17880 | +| policy_gradient_loss | -0.00838 | +| value_loss | 0.000141 | +------------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.245 | +| time/ | | +| fps | 1380 | +| iterations | 4472 | +| time_elapsed | 6633 | +| total_timesteps | 9158656 | +| train/ | | +| approx_kl | 0.0009840254 | +| clip_fraction | 0.156 | +| clip_range | 0.0355 | +| entropy_loss | -7.8 | +| explained_variance | -0.118 | +| learning_rate | 1.87e-05 | +| loss | -0.013 | +| n_updates | 17884 | +| policy_gradient_loss | -0.00791 | +| value_loss | 8e-05 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.246 | +| time/ | | +| fps | 1380 | +| iterations | 4473 | +| time_elapsed | 6635 | +| total_timesteps | 9160704 | +| train/ | | +| approx_kl | 0.0010762947 | +| clip_fraction | 0.156 | +| clip_range | 0.0355 | +| entropy_loss | -7.86 | +| explained_variance | -0.0322 | +| learning_rate | 1.87e-05 | +| loss | -0.0122 | +| n_updates | 17888 | +| policy_gradient_loss | -0.0076 | +| value_loss | 0.000186 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.249 | +| time/ | | +| fps | 1380 | +| iterations | 4474 | +| time_elapsed | 6636 | +| total_timesteps | 9162752 | +| train/ | | +| approx_kl | 0.0009924795 | +| clip_fraction | 0.138 | +| clip_range | 0.0355 | +| entropy_loss | -7.83 | +| explained_variance | 0.0164 | +| learning_rate | 1.86e-05 | +| loss | -0.0137 | +| n_updates | 17892 | +| policy_gradient_loss | -0.00791 | +| value_loss | 0.00015 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.245 | +| time/ | | +| fps | 1380 | +| iterations | 4475 | +| time_elapsed | 6638 | +| total_timesteps | 9164800 | +| train/ | | +| approx_kl | 0.0009237432 | +| clip_fraction | 0.154 | +| clip_range | 0.0355 | +| entropy_loss | -7.65 | +| explained_variance | 0.0478 | +| learning_rate | 1.86e-05 | +| loss | -0.0141 | +| n_updates | 17896 | +| policy_gradient_loss | -0.00744 | +| value_loss | 0.000199 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.25 | +| time/ | | +| fps | 1380 | +| iterations | 4476 | +| time_elapsed | 6640 | +| total_timesteps | 9166848 | +| train/ | | +| approx_kl | 0.0011362974 | +| clip_fraction | 0.177 | +| clip_range | 0.0354 | +| entropy_loss | -7.84 | +| explained_variance | -0.0572 | +| learning_rate | 1.85e-05 | +| loss | -0.011 | +| n_updates | 17900 | +| policy_gradient_loss | -0.00846 | +| value_loss | 0.000154 | +------------------------------------------ +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.253 | +| time/ | | +| fps | 1380 | +| iterations | 4477 | +| time_elapsed | 6641 | +| total_timesteps | 9168896 | +| train/ | | +| approx_kl | 0.00093300245 | +| clip_fraction | 0.148 | +| clip_range | 0.0354 | +| entropy_loss | -7.8 | +| explained_variance | 0.027 | +| learning_rate | 1.85e-05 | +| loss | -0.0141 | +| n_updates | 17904 | +| policy_gradient_loss | -0.00774 | +| value_loss | 0.000195 | +------------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.249 | +| time/ | | +| fps | 1380 | +| iterations | 4478 | +| time_elapsed | 6643 | +| total_timesteps | 9170944 | +| train/ | | +| approx_kl | 0.0011122385 | +| clip_fraction | 0.172 | +| clip_range | 0.0354 | +| entropy_loss | -7.75 | +| explained_variance | -0.0393 | +| learning_rate | 1.85e-05 | +| loss | -0.014 | +| n_updates | 17908 | +| policy_gradient_loss | -0.00839 | +| value_loss | 0.000115 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.248 | +| time/ | | +| fps | 1380 | +| iterations | 4479 | +| time_elapsed | 6644 | +| total_timesteps | 9172992 | +| train/ | | +| approx_kl | 0.0010491128 | +| clip_fraction | 0.167 | +| clip_range | 0.0354 | +| entropy_loss | -7.86 | +| explained_variance | 0.00666 | +| learning_rate | 1.84e-05 | +| loss | -0.0137 | +| n_updates | 17912 | +| policy_gradient_loss | -0.00795 | +| value_loss | 8.81e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.242 | +| time/ | | +| fps | 1380 | +| iterations | 4480 | +| time_elapsed | 6646 | +| total_timesteps | 9175040 | +| train/ | | +| approx_kl | 0.000890572 | +| clip_fraction | 0.13 | +| clip_range | 0.0353 | +| entropy_loss | -7.9 | +| explained_variance | -0.0556 | +| learning_rate | 1.84e-05 | +| loss | -0.0139 | +| n_updates | 17916 | +| policy_gradient_loss | -0.00721 | +| value_loss | 0.000124 | +----------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.242 | +| time/ | | +| fps | 1380 | +| iterations | 4481 | +| time_elapsed | 6647 | +| total_timesteps | 9177088 | +| train/ | | +| approx_kl | 0.00083784346 | +| clip_fraction | 0.15 | +| clip_range | 0.0353 | +| entropy_loss | -7.82 | +| explained_variance | -0.0369 | +| learning_rate | 1.83e-05 | +| loss | -0.0134 | +| n_updates | 17920 | +| policy_gradient_loss | -0.00757 | +| value_loss | 0.000133 | +------------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.24 | +| time/ | | +| fps | 1380 | +| iterations | 4482 | +| time_elapsed | 6649 | +| total_timesteps | 9179136 | +| train/ | | +| approx_kl | 0.0009238212 | +| clip_fraction | 0.14 | +| clip_range | 0.0353 | +| entropy_loss | -7.82 | +| explained_variance | 0.0461 | +| learning_rate | 1.83e-05 | +| loss | -0.0155 | +| n_updates | 17924 | +| policy_gradient_loss | -0.00818 | +| value_loss | 9.69e-05 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.242 | +| time/ | | +| fps | 1380 | +| iterations | 4483 | +| time_elapsed | 6650 | +| total_timesteps | 9181184 | +| train/ | | +| approx_kl | 0.0009947354 | +| clip_fraction | 0.151 | +| clip_range | 0.0353 | +| entropy_loss | -7.89 | +| explained_variance | -0.00364 | +| learning_rate | 1.83e-05 | +| loss | -0.0127 | +| n_updates | 17928 | +| policy_gradient_loss | -0.00695 | +| value_loss | 0.000144 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.24 | +| time/ | | +| fps | 1380 | +| iterations | 4484 | +| time_elapsed | 6652 | +| total_timesteps | 9183232 | +| train/ | | +| approx_kl | 0.0009714151 | +| clip_fraction | 0.156 | +| clip_range | 0.0352 | +| entropy_loss | -7.84 | +| explained_variance | -0.00719 | +| learning_rate | 1.82e-05 | +| loss | -0.0115 | +| n_updates | 17932 | +| policy_gradient_loss | -0.0075 | +| value_loss | 0.000212 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.237 | +| time/ | | +| fps | 1380 | +| iterations | 4485 | +| time_elapsed | 6653 | +| total_timesteps | 9185280 | +| train/ | | +| approx_kl | 0.0009103937 | +| clip_fraction | 0.158 | +| clip_range | 0.0352 | +| entropy_loss | -7.73 | +| explained_variance | 0.0765 | +| learning_rate | 1.82e-05 | +| loss | -0.0111 | +| n_updates | 17936 | +| policy_gradient_loss | -0.00791 | +| value_loss | 6.83e-05 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.241 | +| time/ | | +| fps | 1380 | +| iterations | 4486 | +| time_elapsed | 6655 | +| total_timesteps | 9187328 | +| train/ | | +| approx_kl | 0.0009967808 | +| clip_fraction | 0.141 | +| clip_range | 0.0352 | +| entropy_loss | -7.91 | +| explained_variance | -0.0767 | +| learning_rate | 1.81e-05 | +| loss | -0.0115 | +| n_updates | 17940 | +| policy_gradient_loss | -0.00676 | +| value_loss | 0.000193 | +------------------------------------------ +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.25 | +| time/ | | +| fps | 1380 | +| iterations | 4487 | +| time_elapsed | 6656 | +| total_timesteps | 9189376 | +| train/ | | +| approx_kl | 0.00084617914 | +| clip_fraction | 0.138 | +| clip_range | 0.0352 | +| entropy_loss | -7.84 | +| explained_variance | 0.0422 | +| learning_rate | 1.81e-05 | +| loss | -0.0105 | +| n_updates | 17944 | +| policy_gradient_loss | -0.00687 | +| value_loss | 0.000241 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.25 | +| time/ | | +| fps | 1380 | +| iterations | 4488 | +| time_elapsed | 6658 | +| total_timesteps | 9191424 | +| train/ | | +| approx_kl | 0.00079670927 | +| clip_fraction | 0.14 | +| clip_range | 0.0351 | +| entropy_loss | -7.72 | +| explained_variance | 0.109 | +| learning_rate | 1.81e-05 | +| loss | -0.01 | +| n_updates | 17948 | +| policy_gradient_loss | -0.00711 | +| value_loss | 0.000216 | +------------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.25 | +| time/ | | +| fps | 1380 | +| iterations | 4489 | +| time_elapsed | 6660 | +| total_timesteps | 9193472 | +| train/ | | +| approx_kl | 0.0010273244 | +| clip_fraction | 0.154 | +| clip_range | 0.0351 | +| entropy_loss | -7.92 | +| explained_variance | -0.0189 | +| learning_rate | 1.8e-05 | +| loss | -0.0148 | +| n_updates | 17952 | +| policy_gradient_loss | -0.0083 | +| value_loss | 0.000146 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.25 | +| time/ | | +| fps | 1380 | +| iterations | 4490 | +| time_elapsed | 6661 | +| total_timesteps | 9195520 | +| train/ | | +| approx_kl | 0.0011158122 | +| clip_fraction | 0.191 | +| clip_range | 0.0351 | +| entropy_loss | -7.94 | +| explained_variance | -0.0719 | +| learning_rate | 1.8e-05 | +| loss | -0.0161 | +| n_updates | 17956 | +| policy_gradient_loss | -0.0101 | +| value_loss | 6.48e-05 | +------------------------------------------ +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.246 | +| time/ | | +| fps | 1380 | +| iterations | 4491 | +| time_elapsed | 6663 | +| total_timesteps | 9197568 | +| train/ | | +| approx_kl | 0.00079229416 | +| clip_fraction | 0.134 | +| clip_range | 0.0351 | +| entropy_loss | -7.96 | +| explained_variance | -0.0295 | +| learning_rate | 1.79e-05 | +| loss | -0.0114 | +| n_updates | 17960 | +| policy_gradient_loss | -0.00701 | +| value_loss | 0.000115 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.249 | +| time/ | | +| fps | 1380 | +| iterations | 4492 | +| time_elapsed | 6664 | +| total_timesteps | 9199616 | +| train/ | | +| approx_kl | 0.00077299285 | +| clip_fraction | 0.134 | +| clip_range | 0.035 | +| entropy_loss | -7.84 | +| explained_variance | -0.0102 | +| learning_rate | 1.79e-05 | +| loss | -0.0119 | +| n_updates | 17964 | +| policy_gradient_loss | -0.00685 | +| value_loss | 0.000169 | +------------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.246 | +| time/ | | +| fps | 1380 | +| iterations | 4493 | +| time_elapsed | 6666 | +| total_timesteps | 9201664 | +| train/ | | +| approx_kl | 0.0008899475 | +| clip_fraction | 0.148 | +| clip_range | 0.035 | +| entropy_loss | -7.7 | +| explained_variance | -0.00172 | +| learning_rate | 1.78e-05 | +| loss | -0.0108 | +| n_updates | 17968 | +| policy_gradient_loss | -0.00737 | +| value_loss | 0.000289 | +------------------------------------------ +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.241 | +| time/ | | +| fps | 1380 | +| iterations | 4494 | +| time_elapsed | 6667 | +| total_timesteps | 9203712 | +| train/ | | +| approx_kl | 0.00089314056 | +| clip_fraction | 0.153 | +| clip_range | 0.035 | +| entropy_loss | -7.8 | +| explained_variance | 0.0644 | +| learning_rate | 1.78e-05 | +| loss | -0.0146 | +| n_updates | 17972 | +| policy_gradient_loss | -0.00817 | +| value_loss | 0.000105 | +------------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.241 | +| time/ | | +| fps | 1380 | +| iterations | 4495 | +| time_elapsed | 6669 | +| total_timesteps | 9205760 | +| train/ | | +| approx_kl | 0.0009145947 | +| clip_fraction | 0.141 | +| clip_range | 0.035 | +| entropy_loss | -7.8 | +| explained_variance | -0.0387 | +| learning_rate | 1.78e-05 | +| loss | -0.013 | +| n_updates | 17976 | +| policy_gradient_loss | -0.00745 | +| value_loss | 0.000174 | +------------------------------------------ +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.246 | +| time/ | | +| fps | 1380 | +| iterations | 4496 | +| time_elapsed | 6670 | +| total_timesteps | 9207808 | +| train/ | | +| approx_kl | 0.00080176373 | +| clip_fraction | 0.145 | +| clip_range | 0.0349 | +| entropy_loss | -7.88 | +| explained_variance | 0.0133 | +| learning_rate | 1.77e-05 | +| loss | -0.0123 | +| n_updates | 17980 | +| policy_gradient_loss | -0.00761 | +| value_loss | 0.000192 | +------------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.244 | +| time/ | | +| fps | 1380 | +| iterations | 4497 | +| time_elapsed | 6672 | +| total_timesteps | 9209856 | +| train/ | | +| approx_kl | 0.0007584505 | +| clip_fraction | 0.125 | +| clip_range | 0.0349 | +| entropy_loss | -7.76 | +| explained_variance | -0.0852 | +| learning_rate | 1.77e-05 | +| loss | -0.0107 | +| n_updates | 17984 | +| policy_gradient_loss | -0.00665 | +| value_loss | 0.000192 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.244 | +| time/ | | +| fps | 1380 | +| iterations | 4498 | +| time_elapsed | 6674 | +| total_timesteps | 9211904 | +| train/ | | +| approx_kl | 0.0009525069 | +| clip_fraction | 0.159 | +| clip_range | 0.0349 | +| entropy_loss | -7.74 | +| explained_variance | 0.123 | +| learning_rate | 1.76e-05 | +| loss | -0.0137 | +| n_updates | 17988 | +| policy_gradient_loss | -0.00821 | +| value_loss | 0.000199 | +------------------------------------------ +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.246 | +| time/ | | +| fps | 1380 | +| iterations | 4499 | +| time_elapsed | 6675 | +| total_timesteps | 9213952 | +| train/ | | +| approx_kl | 0.00081750134 | +| clip_fraction | 0.131 | +| clip_range | 0.0349 | +| entropy_loss | -7.91 | +| explained_variance | 0.0264 | +| learning_rate | 1.76e-05 | +| loss | -0.0122 | +| n_updates | 17992 | +| policy_gradient_loss | -0.00686 | +| value_loss | 0.000161 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.242 | +| time/ | | +| fps | 1380 | +| iterations | 4500 | +| time_elapsed | 6677 | +| total_timesteps | 9216000 | +| train/ | | +| approx_kl | 0.00081980316 | +| clip_fraction | 0.135 | +| clip_range | 0.0348 | +| entropy_loss | -7.88 | +| explained_variance | 0.000566 | +| learning_rate | 1.76e-05 | +| loss | -0.0136 | +| n_updates | 17996 | +| policy_gradient_loss | -0.00749 | +| value_loss | 0.000276 | +------------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.25 | +| time/ | | +| fps | 1380 | +| iterations | 4501 | +| time_elapsed | 6678 | +| total_timesteps | 9218048 | +| train/ | | +| approx_kl | 0.0009030551 | +| clip_fraction | 0.151 | +| clip_range | 0.0348 | +| entropy_loss | -7.98 | +| explained_variance | -0.05 | +| learning_rate | 1.75e-05 | +| loss | -0.0125 | +| n_updates | 18000 | +| policy_gradient_loss | -0.00802 | +| value_loss | 0.000102 | +------------------------------------------ +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.248 | +| time/ | | +| fps | 1380 | +| iterations | 4502 | +| time_elapsed | 6680 | +| total_timesteps | 9220096 | +| train/ | | +| approx_kl | 0.00082904345 | +| clip_fraction | 0.143 | +| clip_range | 0.0348 | +| entropy_loss | -7.84 | +| explained_variance | 0.000105 | +| learning_rate | 1.75e-05 | +| loss | -0.0122 | +| n_updates | 18004 | +| policy_gradient_loss | -0.00656 | +| value_loss | 0.000196 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.25 | +| time/ | | +| fps | 1380 | +| iterations | 4503 | +| time_elapsed | 6682 | +| total_timesteps | 9222144 | +| train/ | | +| approx_kl | 0.00090362795 | +| clip_fraction | 0.153 | +| clip_range | 0.0347 | +| entropy_loss | -7.88 | +| explained_variance | 0.0106 | +| learning_rate | 1.74e-05 | +| loss | -0.014 | +| n_updates | 18008 | +| policy_gradient_loss | -0.00758 | +| value_loss | 0.000179 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.25 | +| time/ | | +| fps | 1380 | +| iterations | 4504 | +| time_elapsed | 6683 | +| total_timesteps | 9224192 | +| train/ | | +| approx_kl | 0.00095484237 | +| clip_fraction | 0.147 | +| clip_range | 0.0347 | +| entropy_loss | -7.92 | +| explained_variance | -0.0355 | +| learning_rate | 1.74e-05 | +| loss | -0.0135 | +| n_updates | 18012 | +| policy_gradient_loss | -0.00751 | +| value_loss | 0.000177 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.248 | +| time/ | | +| fps | 1380 | +| iterations | 4505 | +| time_elapsed | 6685 | +| total_timesteps | 9226240 | +| train/ | | +| approx_kl | 0.00090622203 | +| clip_fraction | 0.126 | +| clip_range | 0.0347 | +| entropy_loss | -7.88 | +| explained_variance | -0.00621 | +| learning_rate | 1.74e-05 | +| loss | -0.0111 | +| n_updates | 18016 | +| policy_gradient_loss | -0.00707 | +| value_loss | 0.000149 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.248 | +| time/ | | +| fps | 1380 | +| iterations | 4506 | +| time_elapsed | 6686 | +| total_timesteps | 9228288 | +| train/ | | +| approx_kl | 0.00093089644 | +| clip_fraction | 0.161 | +| clip_range | 0.0347 | +| entropy_loss | -7.58 | +| explained_variance | 0.0857 | +| learning_rate | 1.73e-05 | +| loss | -0.0139 | +| n_updates | 18020 | +| policy_gradient_loss | -0.0084 | +| value_loss | 0.000172 | +------------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.237 | +| time/ | | +| fps | 1380 | +| iterations | 4507 | +| time_elapsed | 6688 | +| total_timesteps | 9230336 | +| train/ | | +| approx_kl | 0.0007223014 | +| clip_fraction | 0.128 | +| clip_range | 0.0346 | +| entropy_loss | -7.86 | +| explained_variance | -0.0215 | +| learning_rate | 1.73e-05 | +| loss | -0.0117 | +| n_updates | 18024 | +| policy_gradient_loss | -0.00638 | +| value_loss | 0.000118 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.239 | +| time/ | | +| fps | 1380 | +| iterations | 4508 | +| time_elapsed | 6690 | +| total_timesteps | 9232384 | +| train/ | | +| approx_kl | 0.0007846866 | +| clip_fraction | 0.137 | +| clip_range | 0.0346 | +| entropy_loss | -7.73 | +| explained_variance | 0.133 | +| learning_rate | 1.72e-05 | +| loss | -0.0125 | +| n_updates | 18028 | +| policy_gradient_loss | -0.00702 | +| value_loss | 0.000116 | +------------------------------------------ +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.239 | +| time/ | | +| fps | 1380 | +| iterations | 4509 | +| time_elapsed | 6691 | +| total_timesteps | 9234432 | +| train/ | | +| approx_kl | 0.00079076225 | +| clip_fraction | 0.138 | +| clip_range | 0.0346 | +| entropy_loss | -7.74 | +| explained_variance | 0.0295 | +| learning_rate | 1.72e-05 | +| loss | -0.0128 | +| n_updates | 18032 | +| policy_gradient_loss | -0.00754 | +| value_loss | 0.000122 | +------------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.239 | +| time/ | | +| fps | 1380 | +| iterations | 4510 | +| time_elapsed | 6693 | +| total_timesteps | 9236480 | +| train/ | | +| approx_kl | 0.0009158486 | +| clip_fraction | 0.137 | +| clip_range | 0.0346 | +| entropy_loss | -7.94 | +| explained_variance | 0.0113 | +| learning_rate | 1.72e-05 | +| loss | -0.0125 | +| n_updates | 18036 | +| policy_gradient_loss | -0.00805 | +| value_loss | 0.000213 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.245 | +| time/ | | +| fps | 1380 | +| iterations | 4511 | +| time_elapsed | 6694 | +| total_timesteps | 9238528 | +| train/ | | +| approx_kl | 0.000889436 | +| clip_fraction | 0.143 | +| clip_range | 0.0345 | +| entropy_loss | -7.97 | +| explained_variance | -0.0496 | +| learning_rate | 1.71e-05 | +| loss | -0.0134 | +| n_updates | 18040 | +| policy_gradient_loss | -0.00774 | +| value_loss | 0.000119 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.245 | +| time/ | | +| fps | 1379 | +| iterations | 4512 | +| time_elapsed | 6696 | +| total_timesteps | 9240576 | +| train/ | | +| approx_kl | 0.000827099 | +| clip_fraction | 0.141 | +| clip_range | 0.0345 | +| entropy_loss | -7.94 | +| explained_variance | -0.0202 | +| learning_rate | 1.71e-05 | +| loss | -0.0126 | +| n_updates | 18044 | +| policy_gradient_loss | -0.00773 | +| value_loss | 0.000234 | +----------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.244 | +| time/ | | +| fps | 1379 | +| iterations | 4513 | +| time_elapsed | 6697 | +| total_timesteps | 9242624 | +| train/ | | +| approx_kl | 0.00084786245 | +| clip_fraction | 0.156 | +| clip_range | 0.0345 | +| entropy_loss | -7.91 | +| explained_variance | -0.0835 | +| learning_rate | 1.7e-05 | +| loss | -0.0123 | +| n_updates | 18048 | +| policy_gradient_loss | -0.00724 | +| value_loss | 7.22e-05 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.252 | +| time/ | | +| fps | 1379 | +| iterations | 4514 | +| time_elapsed | 6699 | +| total_timesteps | 9244672 | +| train/ | | +| approx_kl | 0.00075417676 | +| clip_fraction | 0.135 | +| clip_range | 0.0345 | +| entropy_loss | -7.68 | +| explained_variance | 0.0737 | +| learning_rate | 1.7e-05 | +| loss | -0.0114 | +| n_updates | 18052 | +| policy_gradient_loss | -0.00706 | +| value_loss | 0.000264 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.251 | +| time/ | | +| fps | 1379 | +| iterations | 4515 | +| time_elapsed | 6700 | +| total_timesteps | 9246720 | +| train/ | | +| approx_kl | 0.00093324936 | +| clip_fraction | 0.158 | +| clip_range | 0.0344 | +| entropy_loss | -7.72 | +| explained_variance | 0.146 | +| learning_rate | 1.7e-05 | +| loss | -0.0131 | +| n_updates | 18056 | +| policy_gradient_loss | -0.00804 | +| value_loss | 0.000125 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.251 | +| time/ | | +| fps | 1379 | +| iterations | 4516 | +| time_elapsed | 6702 | +| total_timesteps | 9248768 | +| train/ | | +| approx_kl | 0.00085564307 | +| clip_fraction | 0.141 | +| clip_range | 0.0344 | +| entropy_loss | -7.86 | +| explained_variance | 0.021 | +| learning_rate | 1.69e-05 | +| loss | -0.0129 | +| n_updates | 18060 | +| policy_gradient_loss | -0.00754 | +| value_loss | 0.000161 | +------------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.253 | +| time/ | | +| fps | 1379 | +| iterations | 4517 | +| time_elapsed | 6703 | +| total_timesteps | 9250816 | +| train/ | | +| approx_kl | 0.0008053322 | +| clip_fraction | 0.14 | +| clip_range | 0.0344 | +| entropy_loss | -7.81 | +| explained_variance | 0.093 | +| learning_rate | 1.69e-05 | +| loss | -0.011 | +| n_updates | 18064 | +| policy_gradient_loss | -0.00693 | +| value_loss | 0.000204 | +------------------------------------------ +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.264 | +| time/ | | +| fps | 1379 | +| iterations | 4518 | +| time_elapsed | 6705 | +| total_timesteps | 9252864 | +| train/ | | +| approx_kl | 0.00079592364 | +| clip_fraction | 0.146 | +| clip_range | 0.0344 | +| entropy_loss | -7.84 | +| explained_variance | -0.0375 | +| learning_rate | 1.68e-05 | +| loss | -0.0113 | +| n_updates | 18068 | +| policy_gradient_loss | -0.00685 | +| value_loss | 0.000128 | +------------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.263 | +| time/ | | +| fps | 1379 | +| iterations | 4519 | +| time_elapsed | 6706 | +| total_timesteps | 9254912 | +| train/ | | +| approx_kl | 0.000902166 | +| clip_fraction | 0.152 | +| clip_range | 0.0343 | +| entropy_loss | -7.66 | +| explained_variance | 0.0154 | +| learning_rate | 1.68e-05 | +| loss | -0.0127 | +| n_updates | 18072 | +| policy_gradient_loss | -0.00759 | +| value_loss | 0.000286 | +----------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.263 | +| time/ | | +| fps | 1379 | +| iterations | 4520 | +| time_elapsed | 6708 | +| total_timesteps | 9256960 | +| train/ | | +| approx_kl | 0.00091635983 | +| clip_fraction | 0.151 | +| clip_range | 0.0343 | +| entropy_loss | -7.84 | +| explained_variance | -0.105 | +| learning_rate | 1.68e-05 | +| loss | -0.0142 | +| n_updates | 18076 | +| policy_gradient_loss | -0.00843 | +| value_loss | 0.000121 | +------------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.263 | +| time/ | | +| fps | 1379 | +| iterations | 4521 | +| time_elapsed | 6709 | +| total_timesteps | 9259008 | +| train/ | | +| approx_kl | 0.0009618002 | +| clip_fraction | 0.158 | +| clip_range | 0.0343 | +| entropy_loss | -7.94 | +| explained_variance | -0.0393 | +| learning_rate | 1.67e-05 | +| loss | -0.0122 | +| n_updates | 18080 | +| policy_gradient_loss | -0.00784 | +| value_loss | 0.00013 | +------------------------------------------ +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.263 | +| time/ | | +| fps | 1379 | +| iterations | 4522 | +| time_elapsed | 6711 | +| total_timesteps | 9261056 | +| train/ | | +| approx_kl | 0.00083533616 | +| clip_fraction | 0.137 | +| clip_range | 0.0343 | +| entropy_loss | -7.96 | +| explained_variance | -0.0334 | +| learning_rate | 1.67e-05 | +| loss | -0.012 | +| n_updates | 18084 | +| policy_gradient_loss | -0.00777 | +| value_loss | 0.000163 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.264 | +| time/ | | +| fps | 1379 | +| iterations | 4523 | +| time_elapsed | 6712 | +| total_timesteps | 9263104 | +| train/ | | +| approx_kl | 0.00089493487 | +| clip_fraction | 0.132 | +| clip_range | 0.0342 | +| entropy_loss | -7.98 | +| explained_variance | -0.0448 | +| learning_rate | 1.66e-05 | +| loss | -0.0125 | +| n_updates | 18088 | +| policy_gradient_loss | -0.00704 | +| value_loss | 0.000109 | +------------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.278 | +| time/ | | +| fps | 1379 | +| iterations | 4524 | +| time_elapsed | 6714 | +| total_timesteps | 9265152 | +| train/ | | +| approx_kl | 0.0008008904 | +| clip_fraction | 0.14 | +| clip_range | 0.0342 | +| entropy_loss | -7.92 | +| explained_variance | 0.00561 | +| learning_rate | 1.66e-05 | +| loss | -0.0119 | +| n_updates | 18092 | +| policy_gradient_loss | -0.00701 | +| value_loss | 0.000142 | +------------------------------------------ +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.277 | +| time/ | | +| fps | 1379 | +| iterations | 4525 | +| time_elapsed | 6715 | +| total_timesteps | 9267200 | +| train/ | | +| approx_kl | 0.00073786115 | +| clip_fraction | 0.12 | +| clip_range | 0.0342 | +| entropy_loss | -7.8 | +| explained_variance | 0.0167 | +| learning_rate | 1.65e-05 | +| loss | -0.00932 | +| n_updates | 18096 | +| policy_gradient_loss | -0.00684 | +| value_loss | 0.000343 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.28 | +| time/ | | +| fps | 1379 | +| iterations | 4526 | +| time_elapsed | 6717 | +| total_timesteps | 9269248 | +| train/ | | +| approx_kl | 0.00084067904 | +| clip_fraction | 0.142 | +| clip_range | 0.0342 | +| entropy_loss | -7.72 | +| explained_variance | 0.0528 | +| learning_rate | 1.65e-05 | +| loss | -0.0125 | +| n_updates | 18100 | +| policy_gradient_loss | -0.00698 | +| value_loss | 0.000203 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.273 | +| time/ | | +| fps | 1379 | +| iterations | 4527 | +| time_elapsed | 6719 | +| total_timesteps | 9271296 | +| train/ | | +| approx_kl | 0.00095358654 | +| clip_fraction | 0.161 | +| clip_range | 0.0341 | +| entropy_loss | -7.62 | +| explained_variance | 0.201 | +| learning_rate | 1.65e-05 | +| loss | -0.0163 | +| n_updates | 18104 | +| policy_gradient_loss | -0.00842 | +| value_loss | 7.59e-05 | +------------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.271 | +| time/ | | +| fps | 1379 | +| iterations | 4528 | +| time_elapsed | 6720 | +| total_timesteps | 9273344 | +| train/ | | +| approx_kl | 0.0007871642 | +| clip_fraction | 0.14 | +| clip_range | 0.0341 | +| entropy_loss | -7.78 | +| explained_variance | 0.103 | +| learning_rate | 1.64e-05 | +| loss | -0.0128 | +| n_updates | 18108 | +| policy_gradient_loss | -0.00784 | +| value_loss | 0.000108 | +------------------------------------------ +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.276 | +| time/ | | +| fps | 1379 | +| iterations | 4529 | +| time_elapsed | 6722 | +| total_timesteps | 9275392 | +| train/ | | +| approx_kl | 0.00083439745 | +| clip_fraction | 0.146 | +| clip_range | 0.0341 | +| entropy_loss | -7.67 | +| explained_variance | 0.212 | +| learning_rate | 1.64e-05 | +| loss | -0.012 | +| n_updates | 18112 | +| policy_gradient_loss | -0.00763 | +| value_loss | 0.000152 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.276 | +| time/ | | +| fps | 1379 | +| iterations | 4530 | +| time_elapsed | 6723 | +| total_timesteps | 9277440 | +| train/ | | +| approx_kl | 0.00082093803 | +| clip_fraction | 0.143 | +| clip_range | 0.0341 | +| entropy_loss | -7.8 | +| explained_variance | -0.0421 | +| learning_rate | 1.63e-05 | +| loss | -0.0142 | +| n_updates | 18116 | +| policy_gradient_loss | -0.00785 | +| value_loss | 0.000182 | +------------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.269 | +| time/ | | +| fps | 1379 | +| iterations | 4531 | +| time_elapsed | 6725 | +| total_timesteps | 9279488 | +| train/ | | +| approx_kl | 0.0008721649 | +| clip_fraction | 0.138 | +| clip_range | 0.034 | +| entropy_loss | -7.97 | +| explained_variance | 0.021 | +| learning_rate | 1.63e-05 | +| loss | -0.0128 | +| n_updates | 18120 | +| policy_gradient_loss | -0.00731 | +| value_loss | 0.000145 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.268 | +| time/ | | +| fps | 1379 | +| iterations | 4532 | +| time_elapsed | 6726 | +| total_timesteps | 9281536 | +| train/ | | +| approx_kl | 0.0008561135 | +| clip_fraction | 0.14 | +| clip_range | 0.034 | +| entropy_loss | -7.87 | +| explained_variance | 0.088 | +| learning_rate | 1.63e-05 | +| loss | -0.0139 | +| n_updates | 18124 | +| policy_gradient_loss | -0.00792 | +| value_loss | 0.000113 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.263 | +| time/ | | +| fps | 1379 | +| iterations | 4533 | +| time_elapsed | 6728 | +| total_timesteps | 9283584 | +| train/ | | +| approx_kl | 0.0008164985 | +| clip_fraction | 0.144 | +| clip_range | 0.034 | +| entropy_loss | -7.87 | +| explained_variance | -0.0621 | +| learning_rate | 1.62e-05 | +| loss | -0.0114 | +| n_updates | 18128 | +| policy_gradient_loss | -0.00729 | +| value_loss | 0.000153 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.266 | +| time/ | | +| fps | 1379 | +| iterations | 4534 | +| time_elapsed | 6729 | +| total_timesteps | 9285632 | +| train/ | | +| approx_kl | 0.0006702506 | +| clip_fraction | 0.136 | +| clip_range | 0.034 | +| entropy_loss | -7.98 | +| explained_variance | -0.0274 | +| learning_rate | 1.62e-05 | +| loss | -0.0124 | +| n_updates | 18132 | +| policy_gradient_loss | -0.00743 | +| value_loss | 0.000202 | +------------------------------------------ +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.266 | +| time/ | | +| fps | 1379 | +| iterations | 4535 | +| time_elapsed | 6731 | +| total_timesteps | 9287680 | +| train/ | | +| approx_kl | 0.00074938446 | +| clip_fraction | 0.138 | +| clip_range | 0.0339 | +| entropy_loss | -7.69 | +| explained_variance | 0.344 | +| learning_rate | 1.61e-05 | +| loss | -0.0139 | +| n_updates | 18136 | +| policy_gradient_loss | -0.0075 | +| value_loss | 8.48e-05 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.266 | +| time/ | | +| fps | 1379 | +| iterations | 4536 | +| time_elapsed | 6732 | +| total_timesteps | 9289728 | +| train/ | | +| approx_kl | 0.00078439206 | +| clip_fraction | 0.131 | +| clip_range | 0.0339 | +| entropy_loss | -7.8 | +| explained_variance | -0.0199 | +| learning_rate | 1.61e-05 | +| loss | -0.0114 | +| n_updates | 18140 | +| policy_gradient_loss | -0.00674 | +| value_loss | 0.000208 | +------------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.267 | +| time/ | | +| fps | 1379 | +| iterations | 4537 | +| time_elapsed | 6734 | +| total_timesteps | 9291776 | +| train/ | | +| approx_kl | 0.0007545684 | +| clip_fraction | 0.126 | +| clip_range | 0.0339 | +| entropy_loss | -7.99 | +| explained_variance | 0.016 | +| learning_rate | 1.61e-05 | +| loss | -0.0102 | +| n_updates | 18144 | +| policy_gradient_loss | -0.00674 | +| value_loss | 0.000111 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 1379 | +| iterations | 4538 | +| time_elapsed | 6735 | +| total_timesteps | 9293824 | +| train/ | | +| approx_kl | 0.0006514993 | +| clip_fraction | 0.125 | +| clip_range | 0.0339 | +| entropy_loss | -7.96 | +| explained_variance | 0.0207 | +| learning_rate | 1.6e-05 | +| loss | -0.0108 | +| n_updates | 18148 | +| policy_gradient_loss | -0.00653 | +| value_loss | 0.000207 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.281 | +| time/ | | +| fps | 1379 | +| iterations | 4539 | +| time_elapsed | 6737 | +| total_timesteps | 9295872 | +| train/ | | +| approx_kl | 0.0007300384 | +| clip_fraction | 0.138 | +| clip_range | 0.0338 | +| entropy_loss | -7.67 | +| explained_variance | 0.0785 | +| learning_rate | 1.6e-05 | +| loss | -0.0123 | +| n_updates | 18152 | +| policy_gradient_loss | -0.0067 | +| value_loss | 0.000212 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.281 | +| time/ | | +| fps | 1379 | +| iterations | 4540 | +| time_elapsed | 6739 | +| total_timesteps | 9297920 | +| train/ | | +| approx_kl | 0.0008669004 | +| clip_fraction | 0.135 | +| clip_range | 0.0338 | +| entropy_loss | -7.76 | +| explained_variance | -0.106 | +| learning_rate | 1.59e-05 | +| loss | -0.0128 | +| n_updates | 18156 | +| policy_gradient_loss | -0.00789 | +| value_loss | 0.000118 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.277 | +| time/ | | +| fps | 1379 | +| iterations | 4541 | +| time_elapsed | 6740 | +| total_timesteps | 9299968 | +| train/ | | +| approx_kl | 0.0007756109 | +| clip_fraction | 0.136 | +| clip_range | 0.0338 | +| entropy_loss | -7.91 | +| explained_variance | 0.0196 | +| learning_rate | 1.59e-05 | +| loss | -0.0137 | +| n_updates | 18160 | +| policy_gradient_loss | -0.00752 | +| value_loss | 0.000134 | +------------------------------------------ +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.274 | +| time/ | | +| fps | 1379 | +| iterations | 4542 | +| time_elapsed | 6742 | +| total_timesteps | 9302016 | +| train/ | | +| approx_kl | 0.00080435956 | +| clip_fraction | 0.138 | +| clip_range | 0.0338 | +| entropy_loss | -7.88 | +| explained_variance | -0.0852 | +| learning_rate | 1.59e-05 | +| loss | -0.011 | +| n_updates | 18164 | +| policy_gradient_loss | -0.00665 | +| value_loss | 0.000141 | +------------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.274 | +| time/ | | +| fps | 1379 | +| iterations | 4543 | +| time_elapsed | 6743 | +| total_timesteps | 9304064 | +| train/ | | +| approx_kl | 0.0007438913 | +| clip_fraction | 0.126 | +| clip_range | 0.0337 | +| entropy_loss | -7.81 | +| explained_variance | 0.049 | +| learning_rate | 1.58e-05 | +| loss | -0.0128 | +| n_updates | 18168 | +| policy_gradient_loss | -0.00684 | +| value_loss | 0.000175 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.274 | +| time/ | | +| fps | 1379 | +| iterations | 4544 | +| time_elapsed | 6745 | +| total_timesteps | 9306112 | +| train/ | | +| approx_kl | 0.0007697985 | +| clip_fraction | 0.135 | +| clip_range | 0.0337 | +| entropy_loss | -7.89 | +| explained_variance | 0.108 | +| learning_rate | 1.58e-05 | +| loss | -0.0136 | +| n_updates | 18172 | +| policy_gradient_loss | -0.00801 | +| value_loss | 0.000165 | +------------------------------------------ +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.276 | +| time/ | | +| fps | 1379 | +| iterations | 4545 | +| time_elapsed | 6746 | +| total_timesteps | 9308160 | +| train/ | | +| approx_kl | 0.00066244835 | +| clip_fraction | 0.138 | +| clip_range | 0.0337 | +| entropy_loss | -7.84 | +| explained_variance | 0.00575 | +| learning_rate | 1.57e-05 | +| loss | -0.00897 | +| n_updates | 18176 | +| policy_gradient_loss | -0.00628 | +| value_loss | 0.000165 | +------------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.281 | +| time/ | | +| fps | 1379 | +| iterations | 4546 | +| time_elapsed | 6748 | +| total_timesteps | 9310208 | +| train/ | | +| approx_kl | 0.0006625369 | +| clip_fraction | 0.128 | +| clip_range | 0.0336 | +| entropy_loss | -7.87 | +| explained_variance | 0.0764 | +| learning_rate | 1.57e-05 | +| loss | -0.0125 | +| n_updates | 18180 | +| policy_gradient_loss | -0.00721 | +| value_loss | 0.000223 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 1379 | +| iterations | 4547 | +| time_elapsed | 6750 | +| total_timesteps | 9312256 | +| train/ | | +| approx_kl | 0.0007865721 | +| clip_fraction | 0.148 | +| clip_range | 0.0336 | +| entropy_loss | -7.82 | +| explained_variance | -0.101 | +| learning_rate | 1.57e-05 | +| loss | -0.0133 | +| n_updates | 18184 | +| policy_gradient_loss | -0.00747 | +| value_loss | 7.91e-05 | +------------------------------------------ +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.289 | +| time/ | | +| fps | 1379 | +| iterations | 4548 | +| time_elapsed | 6751 | +| total_timesteps | 9314304 | +| train/ | | +| approx_kl | 0.00073107565 | +| clip_fraction | 0.133 | +| clip_range | 0.0336 | +| entropy_loss | -7.89 | +| explained_variance | 0.0289 | +| learning_rate | 1.56e-05 | +| loss | -0.0118 | +| n_updates | 18188 | +| policy_gradient_loss | -0.00663 | +| value_loss | 9.27e-05 | +------------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.289 | +| time/ | | +| fps | 1379 | +| iterations | 4549 | +| time_elapsed | 6753 | +| total_timesteps | 9316352 | +| train/ | | +| approx_kl | 0.0008793274 | +| clip_fraction | 0.161 | +| clip_range | 0.0336 | +| entropy_loss | -7.82 | +| explained_variance | 0.055 | +| learning_rate | 1.56e-05 | +| loss | -0.0132 | +| n_updates | 18192 | +| policy_gradient_loss | -0.00821 | +| value_loss | 0.000236 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.288 | +| time/ | | +| fps | 1379 | +| iterations | 4550 | +| time_elapsed | 6754 | +| total_timesteps | 9318400 | +| train/ | | +| approx_kl | 0.0007032116 | +| clip_fraction | 0.116 | +| clip_range | 0.0335 | +| entropy_loss | -7.86 | +| explained_variance | 0.0273 | +| learning_rate | 1.55e-05 | +| loss | -0.0117 | +| n_updates | 18196 | +| policy_gradient_loss | -0.00652 | +| value_loss | 0.000175 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.298 | +| time/ | | +| fps | 1379 | +| iterations | 4551 | +| time_elapsed | 6756 | +| total_timesteps | 9320448 | +| train/ | | +| approx_kl | 0.0007119953 | +| clip_fraction | 0.114 | +| clip_range | 0.0335 | +| entropy_loss | -7.93 | +| explained_variance | 0.00378 | +| learning_rate | 1.55e-05 | +| loss | -0.0121 | +| n_updates | 18200 | +| policy_gradient_loss | -0.00676 | +| value_loss | 0.0002 | +------------------------------------------ +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 1379 | +| iterations | 4552 | +| time_elapsed | 6758 | +| total_timesteps | 9322496 | +| train/ | | +| approx_kl | 0.00074839627 | +| clip_fraction | 0.137 | +| clip_range | 0.0335 | +| entropy_loss | -7.86 | +| explained_variance | 0.0313 | +| learning_rate | 1.55e-05 | +| loss | -0.0149 | +| n_updates | 18204 | +| policy_gradient_loss | -0.00801 | +| value_loss | 0.000243 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.297 | +| time/ | | +| fps | 1379 | +| iterations | 4553 | +| time_elapsed | 6759 | +| total_timesteps | 9324544 | +| train/ | | +| approx_kl | 0.00077310833 | +| clip_fraction | 0.127 | +| clip_range | 0.0335 | +| entropy_loss | -7.79 | +| explained_variance | -0.108 | +| learning_rate | 1.54e-05 | +| loss | -0.0145 | +| n_updates | 18208 | +| policy_gradient_loss | -0.00677 | +| value_loss | 0.000214 | +------------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.291 | +| time/ | | +| fps | 1379 | +| iterations | 4554 | +| time_elapsed | 6761 | +| total_timesteps | 9326592 | +| train/ | | +| approx_kl | 0.000662248 | +| clip_fraction | 0.116 | +| clip_range | 0.0334 | +| entropy_loss | -7.82 | +| explained_variance | -0.0154 | +| learning_rate | 1.54e-05 | +| loss | -0.0136 | +| n_updates | 18212 | +| policy_gradient_loss | -0.00711 | +| value_loss | 0.000153 | +----------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.291 | +| time/ | | +| fps | 1379 | +| iterations | 4555 | +| time_elapsed | 6762 | +| total_timesteps | 9328640 | +| train/ | | +| approx_kl | 0.00075869536 | +| clip_fraction | 0.131 | +| clip_range | 0.0334 | +| entropy_loss | -7.74 | +| explained_variance | 0.126 | +| learning_rate | 1.53e-05 | +| loss | -0.0119 | +| n_updates | 18216 | +| policy_gradient_loss | -0.00702 | +| value_loss | 0.000166 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.285 | +| time/ | | +| fps | 1379 | +| iterations | 4556 | +| time_elapsed | 6764 | +| total_timesteps | 9330688 | +| train/ | | +| approx_kl | 0.00064754713 | +| clip_fraction | 0.117 | +| clip_range | 0.0334 | +| entropy_loss | -7.99 | +| explained_variance | -0.0159 | +| learning_rate | 1.53e-05 | +| loss | -0.0105 | +| n_updates | 18220 | +| policy_gradient_loss | -0.00672 | +| value_loss | 0.000154 | +------------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.285 | +| time/ | | +| fps | 1379 | +| iterations | 4557 | +| time_elapsed | 6765 | +| total_timesteps | 9332736 | +| train/ | | +| approx_kl | 0.0007837338 | +| clip_fraction | 0.133 | +| clip_range | 0.0334 | +| entropy_loss | -7.78 | +| explained_variance | -0.0119 | +| learning_rate | 1.53e-05 | +| loss | -0.0131 | +| n_updates | 18224 | +| policy_gradient_loss | -0.00787 | +| value_loss | 0.000109 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.29 | +| time/ | | +| fps | 1379 | +| iterations | 4558 | +| time_elapsed | 6767 | +| total_timesteps | 9334784 | +| train/ | | +| approx_kl | 0.0006901339 | +| clip_fraction | 0.126 | +| clip_range | 0.0333 | +| entropy_loss | -7.94 | +| explained_variance | -0.00426 | +| learning_rate | 1.52e-05 | +| loss | -0.0114 | +| n_updates | 18228 | +| policy_gradient_loss | -0.00709 | +| value_loss | 0.000164 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.291 | +| time/ | | +| fps | 1379 | +| iterations | 4559 | +| time_elapsed | 6769 | +| total_timesteps | 9336832 | +| train/ | | +| approx_kl | 0.000612609 | +| clip_fraction | 0.122 | +| clip_range | 0.0333 | +| entropy_loss | -7.77 | +| explained_variance | 0.045 | +| learning_rate | 1.52e-05 | +| loss | -0.00848 | +| n_updates | 18232 | +| policy_gradient_loss | -0.0058 | +| value_loss | 0.000188 | +----------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.293 | +| time/ | | +| fps | 1379 | +| iterations | 4560 | +| time_elapsed | 6770 | +| total_timesteps | 9338880 | +| train/ | | +| approx_kl | 0.00068214454 | +| clip_fraction | 0.129 | +| clip_range | 0.0333 | +| entropy_loss | -7.88 | +| explained_variance | 0.0193 | +| learning_rate | 1.51e-05 | +| loss | -0.0115 | +| n_updates | 18236 | +| policy_gradient_loss | -0.00681 | +| value_loss | 0.000204 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.295 | +| time/ | | +| fps | 1379 | +| iterations | 4561 | +| time_elapsed | 6772 | +| total_timesteps | 9340928 | +| train/ | | +| approx_kl | 0.00067715894 | +| clip_fraction | 0.129 | +| clip_range | 0.0333 | +| entropy_loss | -7.81 | +| explained_variance | -0.0634 | +| learning_rate | 1.51e-05 | +| loss | -0.0124 | +| n_updates | 18240 | +| policy_gradient_loss | -0.00703 | +| value_loss | 9.24e-05 | +------------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.297 | +| time/ | | +| fps | 1379 | +| iterations | 4562 | +| time_elapsed | 6773 | +| total_timesteps | 9342976 | +| train/ | | +| approx_kl | 0.0006030374 | +| clip_fraction | 0.118 | +| clip_range | 0.0332 | +| entropy_loss | -7.93 | +| explained_variance | 0.0429 | +| learning_rate | 1.5e-05 | +| loss | -0.00936 | +| n_updates | 18244 | +| policy_gradient_loss | -0.0062 | +| value_loss | 0.000163 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.297 | +| time/ | | +| fps | 1379 | +| iterations | 4563 | +| time_elapsed | 6775 | +| total_timesteps | 9345024 | +| train/ | | +| approx_kl | 0.000642216 | +| clip_fraction | 0.123 | +| clip_range | 0.0332 | +| entropy_loss | -7.96 | +| explained_variance | 0.0458 | +| learning_rate | 1.5e-05 | +| loss | -0.013 | +| n_updates | 18248 | +| policy_gradient_loss | -0.00706 | +| value_loss | 0.000328 | +----------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 1379 | +| iterations | 4564 | +| time_elapsed | 6776 | +| total_timesteps | 9347072 | +| train/ | | +| approx_kl | 0.00069158804 | +| clip_fraction | 0.129 | +| clip_range | 0.0332 | +| entropy_loss | -7.92 | +| explained_variance | -0.123 | +| learning_rate | 1.5e-05 | +| loss | -0.012 | +| n_updates | 18252 | +| policy_gradient_loss | -0.00712 | +| value_loss | 6.68e-05 | +------------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 1379 | +| iterations | 4565 | +| time_elapsed | 6778 | +| total_timesteps | 9349120 | +| train/ | | +| approx_kl | 0.0007495164 | +| clip_fraction | 0.118 | +| clip_range | 0.0332 | +| entropy_loss | -7.89 | +| explained_variance | -0.114 | +| learning_rate | 1.49e-05 | +| loss | -0.0136 | +| n_updates | 18256 | +| policy_gradient_loss | -0.00738 | +| value_loss | 0.000113 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.3 | +| time/ | | +| fps | 1379 | +| iterations | 4566 | +| time_elapsed | 6780 | +| total_timesteps | 9351168 | +| train/ | | +| approx_kl | 0.0007327673 | +| clip_fraction | 0.146 | +| clip_range | 0.0331 | +| entropy_loss | -7.79 | +| explained_variance | 0.0568 | +| learning_rate | 1.49e-05 | +| loss | -0.0143 | +| n_updates | 18260 | +| policy_gradient_loss | -0.00778 | +| value_loss | 0.000298 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 1379 | +| iterations | 4567 | +| time_elapsed | 6781 | +| total_timesteps | 9353216 | +| train/ | | +| approx_kl | 0.0006830035 | +| clip_fraction | 0.134 | +| clip_range | 0.0331 | +| entropy_loss | -7.7 | +| explained_variance | 7.58e-05 | +| learning_rate | 1.48e-05 | +| loss | -0.0123 | +| n_updates | 18264 | +| policy_gradient_loss | -0.00747 | +| value_loss | 0.000233 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.298 | +| time/ | | +| fps | 1379 | +| iterations | 4568 | +| time_elapsed | 6783 | +| total_timesteps | 9355264 | +| train/ | | +| approx_kl | 0.0006924006 | +| clip_fraction | 0.122 | +| clip_range | 0.0331 | +| entropy_loss | -7.87 | +| explained_variance | -0.0582 | +| learning_rate | 1.48e-05 | +| loss | -0.0125 | +| n_updates | 18268 | +| policy_gradient_loss | -0.00759 | +| value_loss | 0.000117 | +------------------------------------------ +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.297 | +| time/ | | +| fps | 1379 | +| iterations | 4569 | +| time_elapsed | 6784 | +| total_timesteps | 9357312 | +| train/ | | +| approx_kl | 0.00057960534 | +| clip_fraction | 0.107 | +| clip_range | 0.0331 | +| entropy_loss | -7.78 | +| explained_variance | 0.0458 | +| learning_rate | 1.48e-05 | +| loss | -0.0125 | +| n_updates | 18272 | +| policy_gradient_loss | -0.0063 | +| value_loss | 0.000163 | +------------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.297 | +| time/ | | +| fps | 1379 | +| iterations | 4570 | +| time_elapsed | 6786 | +| total_timesteps | 9359360 | +| train/ | | +| approx_kl | 0.0005984701 | +| clip_fraction | 0.102 | +| clip_range | 0.033 | +| entropy_loss | -7.83 | +| explained_variance | 0.00178 | +| learning_rate | 1.47e-05 | +| loss | -0.0106 | +| n_updates | 18276 | +| policy_gradient_loss | -0.00578 | +| value_loss | 0.000131 | +------------------------------------------ +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.291 | +| time/ | | +| fps | 1379 | +| iterations | 4571 | +| time_elapsed | 6788 | +| total_timesteps | 9361408 | +| train/ | | +| approx_kl | 0.00059579907 | +| clip_fraction | 0.119 | +| clip_range | 0.033 | +| entropy_loss | -7.97 | +| explained_variance | 0.059 | +| learning_rate | 1.47e-05 | +| loss | -0.01 | +| n_updates | 18280 | +| policy_gradient_loss | -0.00637 | +| value_loss | 0.000141 | +------------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.294 | +| time/ | | +| fps | 1379 | +| iterations | 4572 | +| time_elapsed | 6789 | +| total_timesteps | 9363456 | +| train/ | | +| approx_kl | 0.000618615 | +| clip_fraction | 0.114 | +| clip_range | 0.033 | +| entropy_loss | -7.96 | +| explained_variance | -0.0943 | +| learning_rate | 1.46e-05 | +| loss | -0.0122 | +| n_updates | 18284 | +| policy_gradient_loss | -0.00677 | +| value_loss | 0.000146 | +----------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 1379 | +| iterations | 4573 | +| time_elapsed | 6791 | +| total_timesteps | 9365504 | +| train/ | | +| approx_kl | 0.00062450813 | +| clip_fraction | 0.103 | +| clip_range | 0.033 | +| entropy_loss | -7.85 | +| explained_variance | 0.144 | +| learning_rate | 1.46e-05 | +| loss | -0.0118 | +| n_updates | 18288 | +| policy_gradient_loss | -0.0062 | +| value_loss | 0.000168 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 1379 | +| iterations | 4574 | +| time_elapsed | 6792 | +| total_timesteps | 9367552 | +| train/ | | +| approx_kl | 0.00059619884 | +| clip_fraction | 0.1 | +| clip_range | 0.0329 | +| entropy_loss | -7.79 | +| explained_variance | -0.0654 | +| learning_rate | 1.46e-05 | +| loss | -0.00972 | +| n_updates | 18292 | +| policy_gradient_loss | -0.00641 | +| value_loss | 0.000241 | +------------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 1378 | +| iterations | 4575 | +| time_elapsed | 6794 | +| total_timesteps | 9369600 | +| train/ | | +| approx_kl | 0.0006426101 | +| clip_fraction | 0.129 | +| clip_range | 0.0329 | +| entropy_loss | -7.91 | +| explained_variance | -0.0161 | +| learning_rate | 1.45e-05 | +| loss | -0.0125 | +| n_updates | 18296 | +| policy_gradient_loss | -0.00683 | +| value_loss | 0.000151 | +------------------------------------------ +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.294 | +| time/ | | +| fps | 1378 | +| iterations | 4576 | +| time_elapsed | 6796 | +| total_timesteps | 9371648 | +| train/ | | +| approx_kl | 0.00069764664 | +| clip_fraction | 0.134 | +| clip_range | 0.0329 | +| entropy_loss | -7.76 | +| explained_variance | -0.135 | +| learning_rate | 1.45e-05 | +| loss | -0.0126 | +| n_updates | 18300 | +| policy_gradient_loss | -0.00734 | +| value_loss | 9.56e-05 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 1378 | +| iterations | 4577 | +| time_elapsed | 6797 | +| total_timesteps | 9373696 | +| train/ | | +| approx_kl | 0.00058532786 | +| clip_fraction | 0.112 | +| clip_range | 0.0329 | +| entropy_loss | -7.73 | +| explained_variance | 0.0523 | +| learning_rate | 1.44e-05 | +| loss | -0.00873 | +| n_updates | 18304 | +| policy_gradient_loss | -0.00635 | +| value_loss | 0.00013 | +------------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 1378 | +| iterations | 4578 | +| time_elapsed | 6799 | +| total_timesteps | 9375744 | +| train/ | | +| approx_kl | 0.0007150309 | +| clip_fraction | 0.131 | +| clip_range | 0.0328 | +| entropy_loss | -7.79 | +| explained_variance | 0.0123 | +| learning_rate | 1.44e-05 | +| loss | -0.00997 | +| n_updates | 18308 | +| policy_gradient_loss | -0.00622 | +| value_loss | 0.000231 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 1378 | +| iterations | 4579 | +| time_elapsed | 6800 | +| total_timesteps | 9377792 | +| train/ | | +| approx_kl | 0.0006672274 | +| clip_fraction | 0.131 | +| clip_range | 0.0328 | +| entropy_loss | -7.87 | +| explained_variance | -0.122 | +| learning_rate | 1.44e-05 | +| loss | -0.0124 | +| n_updates | 18312 | +| policy_gradient_loss | -0.00699 | +| value_loss | 0.000106 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 1378 | +| iterations | 4580 | +| time_elapsed | 6802 | +| total_timesteps | 9379840 | +| train/ | | +| approx_kl | 0.0006607458 | +| clip_fraction | 0.127 | +| clip_range | 0.0328 | +| entropy_loss | -7.97 | +| explained_variance | -0.0169 | +| learning_rate | 1.43e-05 | +| loss | -0.0114 | +| n_updates | 18316 | +| policy_gradient_loss | -0.00766 | +| value_loss | 0.00019 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 1378 | +| iterations | 4581 | +| time_elapsed | 6803 | +| total_timesteps | 9381888 | +| train/ | | +| approx_kl | 0.0005733981 | +| clip_fraction | 0.122 | +| clip_range | 0.0328 | +| entropy_loss | -8.02 | +| explained_variance | 0.000435 | +| learning_rate | 1.43e-05 | +| loss | -0.0119 | +| n_updates | 18320 | +| policy_gradient_loss | -0.00714 | +| value_loss | 0.000231 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 1378 | +| iterations | 4582 | +| time_elapsed | 6805 | +| total_timesteps | 9383936 | +| train/ | | +| approx_kl | 0.0005876905 | +| clip_fraction | 0.114 | +| clip_range | 0.0327 | +| entropy_loss | -7.78 | +| explained_variance | 0.0765 | +| learning_rate | 1.42e-05 | +| loss | -0.0117 | +| n_updates | 18324 | +| policy_gradient_loss | -0.00687 | +| value_loss | 0.000212 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 1378 | +| iterations | 4583 | +| time_elapsed | 6807 | +| total_timesteps | 9385984 | +| train/ | | +| approx_kl | 0.0005553501 | +| clip_fraction | 0.104 | +| clip_range | 0.0327 | +| entropy_loss | -7.78 | +| explained_variance | 0.0576 | +| learning_rate | 1.42e-05 | +| loss | -0.00946 | +| n_updates | 18328 | +| policy_gradient_loss | -0.00587 | +| value_loss | 0.000275 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 1378 | +| iterations | 4584 | +| time_elapsed | 6808 | +| total_timesteps | 9388032 | +| train/ | | +| approx_kl | 0.0005369792 | +| clip_fraction | 0.0963 | +| clip_range | 0.0327 | +| entropy_loss | -7.91 | +| explained_variance | -8.38e-05 | +| learning_rate | 1.42e-05 | +| loss | -0.00837 | +| n_updates | 18332 | +| policy_gradient_loss | -0.00599 | +| value_loss | 0.00021 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.302 | +| time/ | | +| fps | 1378 | +| iterations | 4585 | +| time_elapsed | 6810 | +| total_timesteps | 9390080 | +| train/ | | +| approx_kl | 0.000658871 | +| clip_fraction | 0.128 | +| clip_range | 0.0326 | +| entropy_loss | -7.92 | +| explained_variance | -0.213 | +| learning_rate | 1.41e-05 | +| loss | -0.0123 | +| n_updates | 18336 | +| policy_gradient_loss | -0.00764 | +| value_loss | 9.64e-05 | +----------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.3 | +| time/ | | +| fps | 1378 | +| iterations | 4586 | +| time_elapsed | 6811 | +| total_timesteps | 9392128 | +| train/ | | +| approx_kl | 0.00058472133 | +| clip_fraction | 0.123 | +| clip_range | 0.0326 | +| entropy_loss | -7.71 | +| explained_variance | 0.0703 | +| learning_rate | 1.41e-05 | +| loss | -0.00878 | +| n_updates | 18340 | +| policy_gradient_loss | -0.00667 | +| value_loss | 0.000231 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.3 | +| time/ | | +| fps | 1378 | +| iterations | 4587 | +| time_elapsed | 6813 | +| total_timesteps | 9394176 | +| train/ | | +| approx_kl | 0.00063561025 | +| clip_fraction | 0.123 | +| clip_range | 0.0326 | +| entropy_loss | -7.81 | +| explained_variance | 0.124 | +| learning_rate | 1.4e-05 | +| loss | -0.0122 | +| n_updates | 18344 | +| policy_gradient_loss | -0.00737 | +| value_loss | 5.63e-05 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.293 | +| time/ | | +| fps | 1378 | +| iterations | 4588 | +| time_elapsed | 6815 | +| total_timesteps | 9396224 | +| train/ | | +| approx_kl | 0.00054817885 | +| clip_fraction | 0.103 | +| clip_range | 0.0326 | +| entropy_loss | -7.96 | +| explained_variance | -0.0932 | +| learning_rate | 1.4e-05 | +| loss | -0.0102 | +| n_updates | 18348 | +| policy_gradient_loss | -0.00661 | +| value_loss | 0.000109 | +------------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.287 | +| time/ | | +| fps | 1378 | +| iterations | 4589 | +| time_elapsed | 6816 | +| total_timesteps | 9398272 | +| train/ | | +| approx_kl | 0.0005684645 | +| clip_fraction | 0.12 | +| clip_range | 0.0325 | +| entropy_loss | -7.86 | +| explained_variance | 0.0234 | +| learning_rate | 1.4e-05 | +| loss | -0.0105 | +| n_updates | 18352 | +| policy_gradient_loss | -0.00683 | +| value_loss | 0.000163 | +------------------------------------------ +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.287 | +| time/ | | +| fps | 1378 | +| iterations | 4590 | +| time_elapsed | 6818 | +| total_timesteps | 9400320 | +| train/ | | +| approx_kl | 0.00065813115 | +| clip_fraction | 0.129 | +| clip_range | 0.0325 | +| entropy_loss | -7.84 | +| explained_variance | -0.0321 | +| learning_rate | 1.39e-05 | +| loss | -0.0126 | +| n_updates | 18356 | +| policy_gradient_loss | -0.00748 | +| value_loss | 0.00019 | +------------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.287 | +| time/ | | +| fps | 1378 | +| iterations | 4591 | +| time_elapsed | 6819 | +| total_timesteps | 9402368 | +| train/ | | +| approx_kl | 0.0005952853 | +| clip_fraction | 0.107 | +| clip_range | 0.0325 | +| entropy_loss | -7.94 | +| explained_variance | -0.0853 | +| learning_rate | 1.39e-05 | +| loss | -0.0133 | +| n_updates | 18360 | +| policy_gradient_loss | -0.00642 | +| value_loss | 9.29e-05 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.286 | +| time/ | | +| fps | 1378 | +| iterations | 4592 | +| time_elapsed | 6821 | +| total_timesteps | 9404416 | +| train/ | | +| approx_kl | 0.0006197654 | +| clip_fraction | 0.101 | +| clip_range | 0.0325 | +| entropy_loss | -7.9 | +| explained_variance | -0.0224 | +| learning_rate | 1.38e-05 | +| loss | -0.0103 | +| n_updates | 18364 | +| policy_gradient_loss | -0.00593 | +| value_loss | 0.000181 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.288 | +| time/ | | +| fps | 1378 | +| iterations | 4593 | +| time_elapsed | 6823 | +| total_timesteps | 9406464 | +| train/ | | +| approx_kl | 0.0005157982 | +| clip_fraction | 0.0897 | +| clip_range | 0.0324 | +| entropy_loss | -7.87 | +| explained_variance | 0.0221 | +| learning_rate | 1.38e-05 | +| loss | -0.0112 | +| n_updates | 18368 | +| policy_gradient_loss | -0.00583 | +| value_loss | 0.000197 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.293 | +| time/ | | +| fps | 1378 | +| iterations | 4594 | +| time_elapsed | 6824 | +| total_timesteps | 9408512 | +| train/ | | +| approx_kl | 0.0005944306 | +| clip_fraction | 0.104 | +| clip_range | 0.0324 | +| entropy_loss | -7.84 | +| explained_variance | -0.0859 | +| learning_rate | 1.38e-05 | +| loss | -0.00916 | +| n_updates | 18372 | +| policy_gradient_loss | -0.00562 | +| value_loss | 0.000124 | +------------------------------------------ +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.293 | +| time/ | | +| fps | 1378 | +| iterations | 4595 | +| time_elapsed | 6826 | +| total_timesteps | 9410560 | +| train/ | | +| approx_kl | 0.00058424694 | +| clip_fraction | 0.116 | +| clip_range | 0.0324 | +| entropy_loss | -7.75 | +| explained_variance | 0.024 | +| learning_rate | 1.37e-05 | +| loss | -0.0105 | +| n_updates | 18376 | +| policy_gradient_loss | -0.00649 | +| value_loss | 0.000228 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.291 | +| time/ | | +| fps | 1378 | +| iterations | 4596 | +| time_elapsed | 6827 | +| total_timesteps | 9412608 | +| train/ | | +| approx_kl | 0.00063040113 | +| clip_fraction | 0.113 | +| clip_range | 0.0324 | +| entropy_loss | -7.87 | +| explained_variance | 0.0893 | +| learning_rate | 1.37e-05 | +| loss | -0.0119 | +| n_updates | 18380 | +| policy_gradient_loss | -0.0072 | +| value_loss | 0.00012 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.297 | +| time/ | | +| fps | 1378 | +| iterations | 4597 | +| time_elapsed | 6829 | +| total_timesteps | 9414656 | +| train/ | | +| approx_kl | 0.00051672745 | +| clip_fraction | 0.118 | +| clip_range | 0.0323 | +| entropy_loss | -7.75 | +| explained_variance | 0.0847 | +| learning_rate | 1.36e-05 | +| loss | -0.0119 | +| n_updates | 18384 | +| policy_gradient_loss | -0.00593 | +| value_loss | 0.000172 | +------------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.294 | +| time/ | | +| fps | 1378 | +| iterations | 4598 | +| time_elapsed | 6830 | +| total_timesteps | 9416704 | +| train/ | | +| approx_kl | 0.0006162594 | +| clip_fraction | 0.119 | +| clip_range | 0.0323 | +| entropy_loss | -7.91 | +| explained_variance | -0.0308 | +| learning_rate | 1.36e-05 | +| loss | -0.0126 | +| n_updates | 18388 | +| policy_gradient_loss | -0.00725 | +| value_loss | 8.11e-05 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.293 | +| time/ | | +| fps | 1378 | +| iterations | 4599 | +| time_elapsed | 6832 | +| total_timesteps | 9418752 | +| train/ | | +| approx_kl | 0.0006335722 | +| clip_fraction | 0.109 | +| clip_range | 0.0323 | +| entropy_loss | -7.87 | +| explained_variance | -0.0724 | +| learning_rate | 1.35e-05 | +| loss | -0.0101 | +| n_updates | 18392 | +| policy_gradient_loss | -0.00672 | +| value_loss | 0.000149 | +------------------------------------------ +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.293 | +| time/ | | +| fps | 1378 | +| iterations | 4600 | +| time_elapsed | 6834 | +| total_timesteps | 9420800 | +| train/ | | +| approx_kl | 0.00061553146 | +| clip_fraction | 0.112 | +| clip_range | 0.0323 | +| entropy_loss | -7.79 | +| explained_variance | 0.00708 | +| learning_rate | 1.35e-05 | +| loss | -0.0109 | +| n_updates | 18396 | +| policy_gradient_loss | -0.00694 | +| value_loss | 0.000127 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.293 | +| time/ | | +| fps | 1378 | +| iterations | 4601 | +| time_elapsed | 6835 | +| total_timesteps | 9422848 | +| train/ | | +| approx_kl | 0.00056609337 | +| clip_fraction | 0.116 | +| clip_range | 0.0322 | +| entropy_loss | -7.87 | +| explained_variance | -0.0748 | +| learning_rate | 1.35e-05 | +| loss | -0.0106 | +| n_updates | 18400 | +| policy_gradient_loss | -0.0068 | +| value_loss | 0.000154 | +------------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 1378 | +| iterations | 4602 | +| time_elapsed | 6837 | +| total_timesteps | 9424896 | +| train/ | | +| approx_kl | 0.0005360883 | +| clip_fraction | 0.0967 | +| clip_range | 0.0322 | +| entropy_loss | -7.99 | +| explained_variance | -0.0151 | +| learning_rate | 1.34e-05 | +| loss | -0.0108 | +| n_updates | 18404 | +| policy_gradient_loss | -0.00658 | +| value_loss | 0.000104 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.278 | +| time/ | | +| fps | 1378 | +| iterations | 4603 | +| time_elapsed | 6838 | +| total_timesteps | 9426944 | +| train/ | | +| approx_kl | 0.0005541534 | +| clip_fraction | 0.0946 | +| clip_range | 0.0322 | +| entropy_loss | -7.81 | +| explained_variance | 0.00549 | +| learning_rate | 1.34e-05 | +| loss | -0.00994 | +| n_updates | 18408 | +| policy_gradient_loss | -0.00548 | +| value_loss | 0.000151 | +------------------------------------------ +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 1378 | +| iterations | 4604 | +| time_elapsed | 6840 | +| total_timesteps | 9428992 | +| train/ | | +| approx_kl | 0.00053429266 | +| clip_fraction | 0.112 | +| clip_range | 0.0322 | +| entropy_loss | -7.8 | +| explained_variance | 0.128 | +| learning_rate | 1.33e-05 | +| loss | -0.0116 | +| n_updates | 18412 | +| policy_gradient_loss | -0.00713 | +| value_loss | 0.000156 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.273 | +| time/ | | +| fps | 1378 | +| iterations | 4605 | +| time_elapsed | 6841 | +| total_timesteps | 9431040 | +| train/ | | +| approx_kl | 0.00060910813 | +| clip_fraction | 0.127 | +| clip_range | 0.0321 | +| entropy_loss | -7.72 | +| explained_variance | 0.289 | +| learning_rate | 1.33e-05 | +| loss | -0.0125 | +| n_updates | 18416 | +| policy_gradient_loss | -0.00672 | +| value_loss | 5.81e-05 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.274 | +| time/ | | +| fps | 1378 | +| iterations | 4606 | +| time_elapsed | 6843 | +| total_timesteps | 9433088 | +| train/ | | +| approx_kl | 0.00062719686 | +| clip_fraction | 0.118 | +| clip_range | 0.0321 | +| entropy_loss | -7.76 | +| explained_variance | -0.0249 | +| learning_rate | 1.33e-05 | +| loss | -0.012 | +| n_updates | 18420 | +| policy_gradient_loss | -0.00663 | +| value_loss | 0.000157 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.274 | +| time/ | | +| fps | 1378 | +| iterations | 4607 | +| time_elapsed | 6845 | +| total_timesteps | 9435136 | +| train/ | | +| approx_kl | 0.00062924146 | +| clip_fraction | 0.114 | +| clip_range | 0.0321 | +| entropy_loss | -7.92 | +| explained_variance | -0.0465 | +| learning_rate | 1.32e-05 | +| loss | -0.0125 | +| n_updates | 18424 | +| policy_gradient_loss | -0.00726 | +| value_loss | 0.000119 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 1378 | +| iterations | 4608 | +| time_elapsed | 6846 | +| total_timesteps | 9437184 | +| train/ | | +| approx_kl | 0.00050712645 | +| clip_fraction | 0.0961 | +| clip_range | 0.0321 | +| entropy_loss | -7.94 | +| explained_variance | 0.0916 | +| learning_rate | 1.32e-05 | +| loss | -0.0102 | +| n_updates | 18428 | +| policy_gradient_loss | -0.00572 | +| value_loss | 9.25e-05 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 1378 | +| iterations | 4609 | +| time_elapsed | 6848 | +| total_timesteps | 9439232 | +| train/ | | +| approx_kl | 0.00057926413 | +| clip_fraction | 0.122 | +| clip_range | 0.032 | +| entropy_loss | -7.9 | +| explained_variance | -0.0296 | +| learning_rate | 1.31e-05 | +| loss | -0.0117 | +| n_updates | 18432 | +| policy_gradient_loss | -0.00611 | +| value_loss | 0.000141 | +------------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.271 | +| time/ | | +| fps | 1378 | +| iterations | 4610 | +| time_elapsed | 6849 | +| total_timesteps | 9441280 | +| train/ | | +| approx_kl | 0.0005468661 | +| clip_fraction | 0.0983 | +| clip_range | 0.032 | +| entropy_loss | -7.99 | +| explained_variance | -0.017 | +| learning_rate | 1.31e-05 | +| loss | -0.0115 | +| n_updates | 18436 | +| policy_gradient_loss | -0.00637 | +| value_loss | 0.000252 | +------------------------------------------ +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.271 | +| time/ | | +| fps | 1378 | +| iterations | 4611 | +| time_elapsed | 6851 | +| total_timesteps | 9443328 | +| train/ | | +| approx_kl | 0.00054062495 | +| clip_fraction | 0.106 | +| clip_range | 0.032 | +| entropy_loss | -7.86 | +| explained_variance | 0.0498 | +| learning_rate | 1.31e-05 | +| loss | -0.011 | +| n_updates | 18440 | +| policy_gradient_loss | -0.00593 | +| value_loss | 0.000203 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.271 | +| time/ | | +| fps | 1378 | +| iterations | 4612 | +| time_elapsed | 6853 | +| total_timesteps | 9445376 | +| train/ | | +| approx_kl | 0.00042956503 | +| clip_fraction | 0.0791 | +| clip_range | 0.032 | +| entropy_loss | -7.92 | +| explained_variance | 0.0622 | +| learning_rate | 1.3e-05 | +| loss | -0.0111 | +| n_updates | 18444 | +| policy_gradient_loss | -0.00592 | +| value_loss | 0.000182 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.276 | +| time/ | | +| fps | 1378 | +| iterations | 4613 | +| time_elapsed | 6854 | +| total_timesteps | 9447424 | +| train/ | | +| approx_kl | 0.00050943013 | +| clip_fraction | 0.102 | +| clip_range | 0.0319 | +| entropy_loss | -7.8 | +| explained_variance | 0.306 | +| learning_rate | 1.3e-05 | +| loss | -0.0137 | +| n_updates | 18448 | +| policy_gradient_loss | -0.00683 | +| value_loss | 6.19e-05 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.274 | +| time/ | | +| fps | 1378 | +| iterations | 4614 | +| time_elapsed | 6856 | +| total_timesteps | 9449472 | +| train/ | | +| approx_kl | 0.00048598505 | +| clip_fraction | 0.102 | +| clip_range | 0.0319 | +| entropy_loss | -7.73 | +| explained_variance | -0.0606 | +| learning_rate | 1.29e-05 | +| loss | -0.00924 | +| n_updates | 18452 | +| policy_gradient_loss | -0.00557 | +| value_loss | 0.000214 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.272 | +| time/ | | +| fps | 1378 | +| iterations | 4615 | +| time_elapsed | 6857 | +| total_timesteps | 9451520 | +| train/ | | +| approx_kl | 0.00059872796 | +| clip_fraction | 0.117 | +| clip_range | 0.0319 | +| entropy_loss | -7.91 | +| explained_variance | -0.000936 | +| learning_rate | 1.29e-05 | +| loss | -0.011 | +| n_updates | 18456 | +| policy_gradient_loss | -0.00711 | +| value_loss | 9.78e-05 | +------------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.273 | +| time/ | | +| fps | 1378 | +| iterations | 4616 | +| time_elapsed | 6859 | +| total_timesteps | 9453568 | +| train/ | | +| approx_kl | 0.0005769669 | +| clip_fraction | 0.127 | +| clip_range | 0.0319 | +| entropy_loss | -7.86 | +| explained_variance | -0.0214 | +| learning_rate | 1.29e-05 | +| loss | -0.0132 | +| n_updates | 18460 | +| policy_gradient_loss | -0.00735 | +| value_loss | 0.000221 | +------------------------------------------ +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.273 | +| time/ | | +| fps | 1378 | +| iterations | 4617 | +| time_elapsed | 6860 | +| total_timesteps | 9455616 | +| train/ | | +| approx_kl | 0.00045871126 | +| clip_fraction | 0.0845 | +| clip_range | 0.0318 | +| entropy_loss | -7.99 | +| explained_variance | -0.095 | +| learning_rate | 1.28e-05 | +| loss | -0.00994 | +| n_updates | 18464 | +| policy_gradient_loss | -0.00613 | +| value_loss | 0.000101 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.278 | +| time/ | | +| fps | 1378 | +| iterations | 4618 | +| time_elapsed | 6862 | +| total_timesteps | 9457664 | +| train/ | | +| approx_kl | 0.00048255478 | +| clip_fraction | 0.104 | +| clip_range | 0.0318 | +| entropy_loss | -7.77 | +| explained_variance | 0.0328 | +| learning_rate | 1.28e-05 | +| loss | -0.0121 | +| n_updates | 18468 | +| policy_gradient_loss | -0.00661 | +| value_loss | 0.00028 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.278 | +| time/ | | +| fps | 1378 | +| iterations | 4619 | +| time_elapsed | 6863 | +| total_timesteps | 9459712 | +| train/ | | +| approx_kl | 0.00056356954 | +| clip_fraction | 0.109 | +| clip_range | 0.0318 | +| entropy_loss | -7.7 | +| explained_variance | 0.0813 | +| learning_rate | 1.27e-05 | +| loss | -0.0108 | +| n_updates | 18472 | +| policy_gradient_loss | -0.0059 | +| value_loss | 0.000205 | +------------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.278 | +| time/ | | +| fps | 1378 | +| iterations | 4620 | +| time_elapsed | 6865 | +| total_timesteps | 9461760 | +| train/ | | +| approx_kl | 0.00057272 | +| clip_fraction | 0.117 | +| clip_range | 0.0318 | +| entropy_loss | -7.84 | +| explained_variance | -0.0526 | +| learning_rate | 1.27e-05 | +| loss | -0.0121 | +| n_updates | 18476 | +| policy_gradient_loss | -0.00691 | +| value_loss | 0.000242 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.277 | +| time/ | | +| fps | 1378 | +| iterations | 4621 | +| time_elapsed | 6867 | +| total_timesteps | 9463808 | +| train/ | | +| approx_kl | 0.0005380321 | +| clip_fraction | 0.111 | +| clip_range | 0.0317 | +| entropy_loss | -7.96 | +| explained_variance | 0.0492 | +| learning_rate | 1.27e-05 | +| loss | -0.0126 | +| n_updates | 18480 | +| policy_gradient_loss | -0.00671 | +| value_loss | 0.000197 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.277 | +| time/ | | +| fps | 1378 | +| iterations | 4622 | +| time_elapsed | 6868 | +| total_timesteps | 9465856 | +| train/ | | +| approx_kl | 0.0004751427 | +| clip_fraction | 0.0917 | +| clip_range | 0.0317 | +| entropy_loss | -8 | +| explained_variance | 0.00551 | +| learning_rate | 1.26e-05 | +| loss | -0.0106 | +| n_updates | 18484 | +| policy_gradient_loss | -0.00615 | +| value_loss | 0.000179 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.273 | +| time/ | | +| fps | 1378 | +| iterations | 4623 | +| time_elapsed | 6870 | +| total_timesteps | 9467904 | +| train/ | | +| approx_kl | 0.0004781638 | +| clip_fraction | 0.104 | +| clip_range | 0.0317 | +| entropy_loss | -7.85 | +| explained_variance | 0.00774 | +| learning_rate | 1.26e-05 | +| loss | -0.0128 | +| n_updates | 18488 | +| policy_gradient_loss | -0.00651 | +| value_loss | 0.000169 | +------------------------------------------ +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.271 | +| time/ | | +| fps | 1378 | +| iterations | 4624 | +| time_elapsed | 6871 | +| total_timesteps | 9469952 | +| train/ | | +| approx_kl | 0.00049490394 | +| clip_fraction | 0.108 | +| clip_range | 0.0317 | +| entropy_loss | -7.76 | +| explained_variance | 0.106 | +| learning_rate | 1.25e-05 | +| loss | -0.011 | +| n_updates | 18492 | +| policy_gradient_loss | -0.00609 | +| value_loss | 8.42e-05 | +------------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.276 | +| time/ | | +| fps | 1378 | +| iterations | 4625 | +| time_elapsed | 6873 | +| total_timesteps | 9472000 | +| train/ | | +| approx_kl | 0.0004949217 | +| clip_fraction | 0.114 | +| clip_range | 0.0316 | +| entropy_loss | -7.89 | +| explained_variance | 0.0208 | +| learning_rate | 1.25e-05 | +| loss | -0.0112 | +| n_updates | 18496 | +| policy_gradient_loss | -0.00657 | +| value_loss | 0.000151 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.276 | +| time/ | | +| fps | 1378 | +| iterations | 4626 | +| time_elapsed | 6874 | +| total_timesteps | 9474048 | +| train/ | | +| approx_kl | 0.0004924453 | +| clip_fraction | 0.0916 | +| clip_range | 0.0316 | +| entropy_loss | -7.98 | +| explained_variance | -0.00874 | +| learning_rate | 1.25e-05 | +| loss | -0.0103 | +| n_updates | 18500 | +| policy_gradient_loss | -0.006 | +| value_loss | 0.000105 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.276 | +| time/ | | +| fps | 1378 | +| iterations | 4627 | +| time_elapsed | 6876 | +| total_timesteps | 9476096 | +| train/ | | +| approx_kl | 0.0005607292 | +| clip_fraction | 0.108 | +| clip_range | 0.0316 | +| entropy_loss | -7.78 | +| explained_variance | -0.0388 | +| learning_rate | 1.24e-05 | +| loss | -0.0109 | +| n_updates | 18504 | +| policy_gradient_loss | -0.00654 | +| value_loss | 0.000182 | +------------------------------------------ +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 1378 | +| iterations | 4628 | +| time_elapsed | 6877 | +| total_timesteps | 9478144 | +| train/ | | +| approx_kl | 0.00054676697 | +| clip_fraction | 0.107 | +| clip_range | 0.0315 | +| entropy_loss | -7.99 | +| explained_variance | -0.0683 | +| learning_rate | 1.24e-05 | +| loss | -0.0105 | +| n_updates | 18508 | +| policy_gradient_loss | -0.00675 | +| value_loss | 5.6e-05 | +------------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 1378 | +| iterations | 4629 | +| time_elapsed | 6879 | +| total_timesteps | 9480192 | +| train/ | | +| approx_kl | 0.0004733455 | +| clip_fraction | 0.095 | +| clip_range | 0.0315 | +| entropy_loss | -7.94 | +| explained_variance | -0.026 | +| learning_rate | 1.23e-05 | +| loss | -0.0103 | +| n_updates | 18512 | +| policy_gradient_loss | -0.00628 | +| value_loss | 0.000105 | +------------------------------------------ +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.276 | +| time/ | | +| fps | 1378 | +| iterations | 4630 | +| time_elapsed | 6880 | +| total_timesteps | 9482240 | +| train/ | | +| approx_kl | 0.00044033787 | +| clip_fraction | 0.0764 | +| clip_range | 0.0315 | +| entropy_loss | -7.93 | +| explained_variance | -0.0409 | +| learning_rate | 1.23e-05 | +| loss | -0.0102 | +| n_updates | 18516 | +| policy_gradient_loss | -0.00469 | +| value_loss | 0.000216 | +------------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 1378 | +| iterations | 4631 | +| time_elapsed | 6882 | +| total_timesteps | 9484288 | +| train/ | | +| approx_kl | 0.0004950705 | +| clip_fraction | 0.1 | +| clip_range | 0.0315 | +| entropy_loss | -7.78 | +| explained_variance | -0.00657 | +| learning_rate | 1.23e-05 | +| loss | -0.011 | +| n_updates | 18520 | +| policy_gradient_loss | -0.00599 | +| value_loss | 0.000147 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.271 | +| time/ | | +| fps | 1378 | +| iterations | 4632 | +| time_elapsed | 6884 | +| total_timesteps | 9486336 | +| train/ | | +| approx_kl | 0.0005646947 | +| clip_fraction | 0.122 | +| clip_range | 0.0314 | +| entropy_loss | -7.75 | +| explained_variance | 0.00191 | +| learning_rate | 1.22e-05 | +| loss | -0.0114 | +| n_updates | 18524 | +| policy_gradient_loss | -0.00678 | +| value_loss | 0.000132 | +------------------------------------------ +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.273 | +| time/ | | +| fps | 1378 | +| iterations | 4633 | +| time_elapsed | 6885 | +| total_timesteps | 9488384 | +| train/ | | +| approx_kl | 0.00051617477 | +| clip_fraction | 0.0897 | +| clip_range | 0.0314 | +| entropy_loss | -7.89 | +| explained_variance | -0.00637 | +| learning_rate | 1.22e-05 | +| loss | -0.00855 | +| n_updates | 18528 | +| policy_gradient_loss | -0.00558 | +| value_loss | 0.000183 | +------------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.273 | +| time/ | | +| fps | 1378 | +| iterations | 4634 | +| time_elapsed | 6887 | +| total_timesteps | 9490432 | +| train/ | | +| approx_kl | 0.0005255317 | +| clip_fraction | 0.106 | +| clip_range | 0.0314 | +| entropy_loss | -7.87 | +| explained_variance | 0.0444 | +| learning_rate | 1.21e-05 | +| loss | -0.0109 | +| n_updates | 18532 | +| policy_gradient_loss | -0.00614 | +| value_loss | 0.000175 | +------------------------------------------ +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 1377 | +| iterations | 4635 | +| time_elapsed | 6888 | +| total_timesteps | 9492480 | +| train/ | | +| approx_kl | 0.00042434526 | +| clip_fraction | 0.0884 | +| clip_range | 0.0314 | +| entropy_loss | -7.96 | +| explained_variance | -0.00187 | +| learning_rate | 1.21e-05 | +| loss | -0.0111 | +| n_updates | 18536 | +| policy_gradient_loss | -0.00589 | +| value_loss | 0.000159 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.272 | +| time/ | | +| fps | 1377 | +| iterations | 4636 | +| time_elapsed | 6890 | +| total_timesteps | 9494528 | +| train/ | | +| approx_kl | 0.00048219864 | +| clip_fraction | 0.0935 | +| clip_range | 0.0313 | +| entropy_loss | -8.02 | +| explained_variance | -0.0276 | +| learning_rate | 1.2e-05 | +| loss | -0.0119 | +| n_updates | 18540 | +| policy_gradient_loss | -0.00607 | +| value_loss | 0.000116 | +------------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.276 | +| time/ | | +| fps | 1377 | +| iterations | 4637 | +| time_elapsed | 6891 | +| total_timesteps | 9496576 | +| train/ | | +| approx_kl | 0.0004289284 | +| clip_fraction | 0.08 | +| clip_range | 0.0313 | +| entropy_loss | -7.84 | +| explained_variance | -0.0152 | +| learning_rate | 1.2e-05 | +| loss | -0.00961 | +| n_updates | 18544 | +| policy_gradient_loss | -0.00593 | +| value_loss | 0.000191 | +------------------------------------------ +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 1377 | +| iterations | 4638 | +| time_elapsed | 6893 | +| total_timesteps | 9498624 | +| train/ | | +| approx_kl | 0.00043251878 | +| clip_fraction | 0.0992 | +| clip_range | 0.0313 | +| entropy_loss | -7.7 | +| explained_variance | 0.0225 | +| learning_rate | 1.2e-05 | +| loss | -0.0104 | +| n_updates | 18548 | +| policy_gradient_loss | -0.00551 | +| value_loss | 0.000171 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.278 | +| time/ | | +| fps | 1377 | +| iterations | 4639 | +| time_elapsed | 6894 | +| total_timesteps | 9500672 | +| train/ | | +| approx_kl | 0.00047249597 | +| clip_fraction | 0.0917 | +| clip_range | 0.0313 | +| entropy_loss | -7.81 | +| explained_variance | -0.0251 | +| learning_rate | 1.19e-05 | +| loss | -0.0116 | +| n_updates | 18552 | +| policy_gradient_loss | -0.00572 | +| value_loss | 0.000237 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.281 | +| time/ | | +| fps | 1377 | +| iterations | 4640 | +| time_elapsed | 6896 | +| total_timesteps | 9502720 | +| train/ | | +| approx_kl | 0.00043706904 | +| clip_fraction | 0.0901 | +| clip_range | 0.0312 | +| entropy_loss | -7.84 | +| explained_variance | -0.00648 | +| learning_rate | 1.19e-05 | +| loss | -0.0101 | +| n_updates | 18556 | +| policy_gradient_loss | -0.00534 | +| value_loss | 0.000119 | +------------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.281 | +| time/ | | +| fps | 1377 | +| iterations | 4641 | +| time_elapsed | 6897 | +| total_timesteps | 9504768 | +| train/ | | +| approx_kl | 0.0004218171 | +| clip_fraction | 0.0892 | +| clip_range | 0.0312 | +| entropy_loss | -7.91 | +| explained_variance | 0.0065 | +| learning_rate | 1.18e-05 | +| loss | -0.00951 | +| n_updates | 18560 | +| policy_gradient_loss | -0.00602 | +| value_loss | 0.000244 | +------------------------------------------ +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.284 | +| time/ | | +| fps | 1377 | +| iterations | 4642 | +| time_elapsed | 6899 | +| total_timesteps | 9506816 | +| train/ | | +| approx_kl | 0.00042132143 | +| clip_fraction | 0.087 | +| clip_range | 0.0312 | +| entropy_loss | -7.93 | +| explained_variance | 0.103 | +| learning_rate | 1.18e-05 | +| loss | -0.0106 | +| n_updates | 18564 | +| policy_gradient_loss | -0.00618 | +| value_loss | 0.000123 | +------------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.289 | +| time/ | | +| fps | 1377 | +| iterations | 4643 | +| time_elapsed | 6901 | +| total_timesteps | 9508864 | +| train/ | | +| approx_kl | 0.0004113239 | +| clip_fraction | 0.0804 | +| clip_range | 0.0312 | +| entropy_loss | -7.91 | +| explained_variance | -0.0209 | +| learning_rate | 1.18e-05 | +| loss | -0.00935 | +| n_updates | 18568 | +| policy_gradient_loss | -0.00576 | +| value_loss | 0.000155 | +------------------------------------------ +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.283 | +| time/ | | +| fps | 1377 | +| iterations | 4644 | +| time_elapsed | 6902 | +| total_timesteps | 9510912 | +| train/ | | +| approx_kl | 0.00045830026 | +| clip_fraction | 0.0995 | +| clip_range | 0.0311 | +| entropy_loss | -7.75 | +| explained_variance | 0.0453 | +| learning_rate | 1.17e-05 | +| loss | -0.0116 | +| n_updates | 18572 | +| policy_gradient_loss | -0.00588 | +| value_loss | 0.000123 | +------------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.278 | +| time/ | | +| fps | 1377 | +| iterations | 4645 | +| time_elapsed | 6904 | +| total_timesteps | 9512960 | +| train/ | | +| approx_kl | 0.0005381779 | +| clip_fraction | 0.106 | +| clip_range | 0.0311 | +| entropy_loss | -7.67 | +| explained_variance | 0.0569 | +| learning_rate | 1.17e-05 | +| loss | -0.0111 | +| n_updates | 18576 | +| policy_gradient_loss | -0.00593 | +| value_loss | 0.000149 | +------------------------------------------ +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.278 | +| time/ | | +| fps | 1377 | +| iterations | 4646 | +| time_elapsed | 6905 | +| total_timesteps | 9515008 | +| train/ | | +| approx_kl | 0.00054153893 | +| clip_fraction | 0.102 | +| clip_range | 0.0311 | +| entropy_loss | -7.82 | +| explained_variance | 0.0106 | +| learning_rate | 1.16e-05 | +| loss | -0.0113 | +| n_updates | 18580 | +| policy_gradient_loss | -0.00646 | +| value_loss | 0.000102 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.278 | +| time/ | | +| fps | 1377 | +| iterations | 4647 | +| time_elapsed | 6907 | +| total_timesteps | 9517056 | +| train/ | | +| approx_kl | 0.00040476964 | +| clip_fraction | 0.0728 | +| clip_range | 0.0311 | +| entropy_loss | -7.93 | +| explained_variance | -0.0193 | +| learning_rate | 1.16e-05 | +| loss | -0.0106 | +| n_updates | 18584 | +| policy_gradient_loss | -0.00515 | +| value_loss | 8.79e-05 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.276 | +| time/ | | +| fps | 1377 | +| iterations | 4648 | +| time_elapsed | 6908 | +| total_timesteps | 9519104 | +| train/ | | +| approx_kl | 0.00047985755 | +| clip_fraction | 0.0917 | +| clip_range | 0.031 | +| entropy_loss | -7.98 | +| explained_variance | 0.0223 | +| learning_rate | 1.16e-05 | +| loss | -0.00797 | +| n_updates | 18588 | +| policy_gradient_loss | -0.00554 | +| value_loss | 0.000135 | +------------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.27 | +| time/ | | +| fps | 1377 | +| iterations | 4649 | +| time_elapsed | 6910 | +| total_timesteps | 9521152 | +| train/ | | +| approx_kl | 0.0003979339 | +| clip_fraction | 0.0801 | +| clip_range | 0.031 | +| entropy_loss | -7.89 | +| explained_variance | 0.0189 | +| learning_rate | 1.15e-05 | +| loss | -0.0123 | +| n_updates | 18592 | +| policy_gradient_loss | -0.00615 | +| value_loss | 0.000169 | +------------------------------------------ +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.263 | +| time/ | | +| fps | 1377 | +| iterations | 4650 | +| time_elapsed | 6911 | +| total_timesteps | 9523200 | +| train/ | | +| approx_kl | 0.00040383585 | +| clip_fraction | 0.0836 | +| clip_range | 0.031 | +| entropy_loss | -7.9 | +| explained_variance | -0.0298 | +| learning_rate | 1.15e-05 | +| loss | -0.00789 | +| n_updates | 18596 | +| policy_gradient_loss | -0.00558 | +| value_loss | 0.000128 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.262 | +| time/ | | +| fps | 1377 | +| iterations | 4651 | +| time_elapsed | 6913 | +| total_timesteps | 9525248 | +| train/ | | +| approx_kl | 0.00037144148 | +| clip_fraction | 0.0807 | +| clip_range | 0.031 | +| entropy_loss | -7.79 | +| explained_variance | -0.0354 | +| learning_rate | 1.14e-05 | +| loss | -0.011 | +| n_updates | 18600 | +| policy_gradient_loss | -0.00561 | +| value_loss | 0.000152 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.262 | +| time/ | | +| fps | 1377 | +| iterations | 4652 | +| time_elapsed | 6914 | +| total_timesteps | 9527296 | +| train/ | | +| approx_kl | 0.00042176404 | +| clip_fraction | 0.0858 | +| clip_range | 0.0309 | +| entropy_loss | -7.78 | +| explained_variance | 0.0853 | +| learning_rate | 1.14e-05 | +| loss | -0.0106 | +| n_updates | 18604 | +| policy_gradient_loss | -0.00632 | +| value_loss | 0.000161 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.255 | +| time/ | | +| fps | 1377 | +| iterations | 4653 | +| time_elapsed | 6916 | +| total_timesteps | 9529344 | +| train/ | | +| approx_kl | 0.00042981972 | +| clip_fraction | 0.092 | +| clip_range | 0.0309 | +| entropy_loss | -7.89 | +| explained_variance | 0.0102 | +| learning_rate | 1.14e-05 | +| loss | -0.00996 | +| n_updates | 18608 | +| policy_gradient_loss | -0.00592 | +| value_loss | 0.000142 | +------------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.259 | +| time/ | | +| fps | 1377 | +| iterations | 4654 | +| time_elapsed | 6917 | +| total_timesteps | 9531392 | +| train/ | | +| approx_kl | 0.0004763507 | +| clip_fraction | 0.094 | +| clip_range | 0.0309 | +| entropy_loss | -7.75 | +| explained_variance | 0.106 | +| learning_rate | 1.13e-05 | +| loss | -0.0113 | +| n_updates | 18612 | +| policy_gradient_loss | -0.00622 | +| value_loss | 9.06e-05 | +------------------------------------------ +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.26 | +| time/ | | +| fps | 1377 | +| iterations | 4655 | +| time_elapsed | 6919 | +| total_timesteps | 9533440 | +| train/ | | +| approx_kl | 0.00038081018 | +| clip_fraction | 0.076 | +| clip_range | 0.0309 | +| entropy_loss | -7.84 | +| explained_variance | 0.0357 | +| learning_rate | 1.13e-05 | +| loss | -0.00901 | +| n_updates | 18616 | +| policy_gradient_loss | -0.0056 | +| value_loss | 0.000234 | +------------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.256 | +| time/ | | +| fps | 1377 | +| iterations | 4656 | +| time_elapsed | 6920 | +| total_timesteps | 9535488 | +| train/ | | +| approx_kl | 0.000418346 | +| clip_fraction | 0.0842 | +| clip_range | 0.0308 | +| entropy_loss | -7.8 | +| explained_variance | 0.0221 | +| learning_rate | 1.12e-05 | +| loss | -0.0125 | +| n_updates | 18620 | +| policy_gradient_loss | -0.00576 | +| value_loss | 0.000262 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.254 | +| time/ | | +| fps | 1377 | +| iterations | 4657 | +| time_elapsed | 6922 | +| total_timesteps | 9537536 | +| train/ | | +| approx_kl | 0.0004464271 | +| clip_fraction | 0.0896 | +| clip_range | 0.0308 | +| entropy_loss | -7.86 | +| explained_variance | 0.0678 | +| learning_rate | 1.12e-05 | +| loss | -0.0113 | +| n_updates | 18624 | +| policy_gradient_loss | -0.00608 | +| value_loss | 9.28e-05 | +------------------------------------------ +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.254 | +| time/ | | +| fps | 1377 | +| iterations | 4658 | +| time_elapsed | 6923 | +| total_timesteps | 9539584 | +| train/ | | +| approx_kl | 0.00036196224 | +| clip_fraction | 0.0807 | +| clip_range | 0.0308 | +| entropy_loss | -7.89 | +| explained_variance | 0.102 | +| learning_rate | 1.12e-05 | +| loss | -0.0076 | +| n_updates | 18628 | +| policy_gradient_loss | -0.00504 | +| value_loss | 9.09e-05 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.25 | +| time/ | | +| fps | 1377 | +| iterations | 4659 | +| time_elapsed | 6925 | +| total_timesteps | 9541632 | +| train/ | | +| approx_kl | 0.00032524954 | +| clip_fraction | 0.0652 | +| clip_range | 0.0308 | +| entropy_loss | -7.76 | +| explained_variance | -0.0323 | +| learning_rate | 1.11e-05 | +| loss | -0.00764 | +| n_updates | 18632 | +| policy_gradient_loss | -0.00426 | +| value_loss | 0.000251 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.256 | +| time/ | | +| fps | 1377 | +| iterations | 4660 | +| time_elapsed | 6927 | +| total_timesteps | 9543680 | +| train/ | | +| approx_kl | 0.00033809507 | +| clip_fraction | 0.075 | +| clip_range | 0.0307 | +| entropy_loss | -7.76 | +| explained_variance | -0.0176 | +| learning_rate | 1.11e-05 | +| loss | -0.00948 | +| n_updates | 18636 | +| policy_gradient_loss | -0.0056 | +| value_loss | 0.000221 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.25 | +| time/ | | +| fps | 1377 | +| iterations | 4661 | +| time_elapsed | 6928 | +| total_timesteps | 9545728 | +| train/ | | +| approx_kl | 0.00031329892 | +| clip_fraction | 0.0713 | +| clip_range | 0.0307 | +| entropy_loss | -7.93 | +| explained_variance | 0.00877 | +| learning_rate | 1.1e-05 | +| loss | -0.00993 | +| n_updates | 18640 | +| policy_gradient_loss | -0.00484 | +| value_loss | 0.000287 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.252 | +| time/ | | +| fps | 1377 | +| iterations | 4662 | +| time_elapsed | 6930 | +| total_timesteps | 9547776 | +| train/ | | +| approx_kl | 0.00039219717 | +| clip_fraction | 0.0874 | +| clip_range | 0.0307 | +| entropy_loss | -7.93 | +| explained_variance | 0.0371 | +| learning_rate | 1.1e-05 | +| loss | -0.00929 | +| n_updates | 18644 | +| policy_gradient_loss | -0.006 | +| value_loss | 0.000134 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.254 | +| time/ | | +| fps | 1377 | +| iterations | 4663 | +| time_elapsed | 6931 | +| total_timesteps | 9549824 | +| train/ | | +| approx_kl | 0.00039322296 | +| clip_fraction | 0.0811 | +| clip_range | 0.0307 | +| entropy_loss | -7.94 | +| explained_variance | 0.105 | +| learning_rate | 1.1e-05 | +| loss | -0.011 | +| n_updates | 18648 | +| policy_gradient_loss | -0.0055 | +| value_loss | 0.000133 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.252 | +| time/ | | +| fps | 1377 | +| iterations | 4664 | +| time_elapsed | 6933 | +| total_timesteps | 9551872 | +| train/ | | +| approx_kl | 0.00039405478 | +| clip_fraction | 0.0869 | +| clip_range | 0.0306 | +| entropy_loss | -7.88 | +| explained_variance | 0.0634 | +| learning_rate | 1.09e-05 | +| loss | -0.0093 | +| n_updates | 18652 | +| policy_gradient_loss | -0.00506 | +| value_loss | 0.000172 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.252 | +| time/ | | +| fps | 1377 | +| iterations | 4665 | +| time_elapsed | 6934 | +| total_timesteps | 9553920 | +| train/ | | +| approx_kl | 0.00036309214 | +| clip_fraction | 0.0759 | +| clip_range | 0.0306 | +| entropy_loss | -7.78 | +| explained_variance | 0.108 | +| learning_rate | 1.09e-05 | +| loss | -0.011 | +| n_updates | 18656 | +| policy_gradient_loss | -0.00542 | +| value_loss | 8.28e-05 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.259 | +| time/ | | +| fps | 1377 | +| iterations | 4666 | +| time_elapsed | 6936 | +| total_timesteps | 9555968 | +| train/ | | +| approx_kl | 0.00039783696 | +| clip_fraction | 0.0846 | +| clip_range | 0.0306 | +| entropy_loss | -7.94 | +| explained_variance | 0.114 | +| learning_rate | 1.08e-05 | +| loss | -0.0108 | +| n_updates | 18660 | +| policy_gradient_loss | -0.00605 | +| value_loss | 0.00011 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.271 | +| time/ | | +| fps | 1377 | +| iterations | 4667 | +| time_elapsed | 6937 | +| total_timesteps | 9558016 | +| train/ | | +| approx_kl | 0.00042983046 | +| clip_fraction | 0.0953 | +| clip_range | 0.0306 | +| entropy_loss | -7.74 | +| explained_variance | -0.00229 | +| learning_rate | 1.08e-05 | +| loss | -0.00869 | +| n_updates | 18664 | +| policy_gradient_loss | -0.00572 | +| value_loss | 0.000252 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.268 | +| time/ | | +| fps | 1377 | +| iterations | 4668 | +| time_elapsed | 6939 | +| total_timesteps | 9560064 | +| train/ | | +| approx_kl | 0.00036486058 | +| clip_fraction | 0.0719 | +| clip_range | 0.0305 | +| entropy_loss | -7.81 | +| explained_variance | 0.0628 | +| learning_rate | 1.08e-05 | +| loss | -0.0093 | +| n_updates | 18668 | +| policy_gradient_loss | -0.0048 | +| value_loss | 0.000347 | +------------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.267 | +| time/ | | +| fps | 1377 | +| iterations | 4669 | +| time_elapsed | 6940 | +| total_timesteps | 9562112 | +| train/ | | +| approx_kl | 0.0003805916 | +| clip_fraction | 0.0803 | +| clip_range | 0.0305 | +| entropy_loss | -7.75 | +| explained_variance | 0.149 | +| learning_rate | 1.07e-05 | +| loss | -0.00934 | +| n_updates | 18672 | +| policy_gradient_loss | -0.006 | +| value_loss | 0.000193 | +------------------------------------------ +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.267 | +| time/ | | +| fps | 1377 | +| iterations | 4670 | +| time_elapsed | 6942 | +| total_timesteps | 9564160 | +| train/ | | +| approx_kl | 0.00039197446 | +| clip_fraction | 0.0797 | +| clip_range | 0.0305 | +| entropy_loss | -7.8 | +| explained_variance | 0.0923 | +| learning_rate | 1.07e-05 | +| loss | -0.0103 | +| n_updates | 18676 | +| policy_gradient_loss | -0.00601 | +| value_loss | 0.000156 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.267 | +| time/ | | +| fps | 1377 | +| iterations | 4671 | +| time_elapsed | 6944 | +| total_timesteps | 9566208 | +| train/ | | +| approx_kl | 0.00043890937 | +| clip_fraction | 0.0979 | +| clip_range | 0.0304 | +| entropy_loss | -7.99 | +| explained_variance | -0.000949 | +| learning_rate | 1.06e-05 | +| loss | -0.0114 | +| n_updates | 18680 | +| policy_gradient_loss | -0.00596 | +| value_loss | 0.000181 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.267 | +| time/ | | +| fps | 1377 | +| iterations | 4672 | +| time_elapsed | 6945 | +| total_timesteps | 9568256 | +| train/ | | +| approx_kl | 0.00033920654 | +| clip_fraction | 0.0811 | +| clip_range | 0.0304 | +| entropy_loss | -7.97 | +| explained_variance | -0.0288 | +| learning_rate | 1.06e-05 | +| loss | -0.0115 | +| n_updates | 18684 | +| policy_gradient_loss | -0.00588 | +| value_loss | 0.000135 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.276 | +| time/ | | +| fps | 1377 | +| iterations | 4673 | +| time_elapsed | 6947 | +| total_timesteps | 9570304 | +| train/ | | +| approx_kl | 0.00034099843 | +| clip_fraction | 0.0686 | +| clip_range | 0.0304 | +| entropy_loss | -7.99 | +| explained_variance | 0.0021 | +| learning_rate | 1.05e-05 | +| loss | -0.00832 | +| n_updates | 18688 | +| policy_gradient_loss | -0.00528 | +| value_loss | 0.000133 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.278 | +| time/ | | +| fps | 1377 | +| iterations | 4674 | +| time_elapsed | 6948 | +| total_timesteps | 9572352 | +| train/ | | +| approx_kl | 0.00040016684 | +| clip_fraction | 0.0881 | +| clip_range | 0.0304 | +| entropy_loss | -7.81 | +| explained_variance | 0.0468 | +| learning_rate | 1.05e-05 | +| loss | -0.00823 | +| n_updates | 18692 | +| policy_gradient_loss | -0.00539 | +| value_loss | 0.000224 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.271 | +| time/ | | +| fps | 1377 | +| iterations | 4675 | +| time_elapsed | 6950 | +| total_timesteps | 9574400 | +| train/ | | +| approx_kl | 0.00038075683 | +| clip_fraction | 0.0706 | +| clip_range | 0.0303 | +| entropy_loss | -7.83 | +| explained_variance | -0.00144 | +| learning_rate | 1.05e-05 | +| loss | -0.00805 | +| n_updates | 18696 | +| policy_gradient_loss | -0.00534 | +| value_loss | 0.00013 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 1377 | +| iterations | 4676 | +| time_elapsed | 6951 | +| total_timesteps | 9576448 | +| train/ | | +| approx_kl | 0.00037159366 | +| clip_fraction | 0.08 | +| clip_range | 0.0303 | +| entropy_loss | -7.86 | +| explained_variance | -0.0246 | +| learning_rate | 1.04e-05 | +| loss | -0.0108 | +| n_updates | 18700 | +| policy_gradient_loss | -0.00576 | +| value_loss | 0.000133 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.28 | +| time/ | | +| fps | 1377 | +| iterations | 4677 | +| time_elapsed | 6953 | +| total_timesteps | 9578496 | +| train/ | | +| approx_kl | 0.00041376884 | +| clip_fraction | 0.0813 | +| clip_range | 0.0303 | +| entropy_loss | -7.89 | +| explained_variance | -0.00775 | +| learning_rate | 1.04e-05 | +| loss | -0.0114 | +| n_updates | 18704 | +| policy_gradient_loss | -0.00588 | +| value_loss | 0.000243 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.277 | +| time/ | | +| fps | 1377 | +| iterations | 4678 | +| time_elapsed | 6955 | +| total_timesteps | 9580544 | +| train/ | | +| approx_kl | 0.00040474208 | +| clip_fraction | 0.0751 | +| clip_range | 0.0303 | +| entropy_loss | -7.82 | +| explained_variance | -0.0446 | +| learning_rate | 1.03e-05 | +| loss | -0.01 | +| n_updates | 18708 | +| policy_gradient_loss | -0.00574 | +| value_loss | 0.000237 | +------------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.272 | +| time/ | | +| fps | 1377 | +| iterations | 4679 | +| time_elapsed | 6956 | +| total_timesteps | 9582592 | +| train/ | | +| approx_kl | 0.0003902467 | +| clip_fraction | 0.0798 | +| clip_range | 0.0302 | +| entropy_loss | -7.78 | +| explained_variance | 0.0996 | +| learning_rate | 1.03e-05 | +| loss | -0.0109 | +| n_updates | 18712 | +| policy_gradient_loss | -0.00582 | +| value_loss | 6.66e-05 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.272 | +| time/ | | +| fps | 1377 | +| iterations | 4680 | +| time_elapsed | 6958 | +| total_timesteps | 9584640 | +| train/ | | +| approx_kl | 0.0003517034 | +| clip_fraction | 0.0663 | +| clip_range | 0.0302 | +| entropy_loss | -7.84 | +| explained_variance | 0.146 | +| learning_rate | 1.03e-05 | +| loss | -0.00988 | +| n_updates | 18716 | +| policy_gradient_loss | -0.00522 | +| value_loss | 0.000127 | +------------------------------------------ +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.263 | +| time/ | | +| fps | 1377 | +| iterations | 4681 | +| time_elapsed | 6959 | +| total_timesteps | 9586688 | +| train/ | | +| approx_kl | 0.00027719582 | +| clip_fraction | 0.0621 | +| clip_range | 0.0302 | +| entropy_loss | -7.87 | +| explained_variance | 0.128 | +| learning_rate | 1.02e-05 | +| loss | -0.00933 | +| n_updates | 18720 | +| policy_gradient_loss | -0.0053 | +| value_loss | 0.000165 | +------------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.263 | +| time/ | | +| fps | 1377 | +| iterations | 4682 | +| time_elapsed | 6961 | +| total_timesteps | 9588736 | +| train/ | | +| approx_kl | 0.0003844503 | +| clip_fraction | 0.0863 | +| clip_range | 0.0302 | +| entropy_loss | -7.74 | +| explained_variance | 0.0595 | +| learning_rate | 1.02e-05 | +| loss | -0.00869 | +| n_updates | 18724 | +| policy_gradient_loss | -0.0054 | +| value_loss | 0.000315 | +------------------------------------------ +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.261 | +| time/ | | +| fps | 1377 | +| iterations | 4683 | +| time_elapsed | 6962 | +| total_timesteps | 9590784 | +| train/ | | +| approx_kl | 0.00034189306 | +| clip_fraction | 0.0757 | +| clip_range | 0.0301 | +| entropy_loss | -7.9 | +| explained_variance | -0.0207 | +| learning_rate | 1.01e-05 | +| loss | -0.0091 | +| n_updates | 18728 | +| policy_gradient_loss | -0.00582 | +| value_loss | 0.000225 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.261 | +| time/ | | +| fps | 1377 | +| iterations | 4684 | +| time_elapsed | 6964 | +| total_timesteps | 9592832 | +| train/ | | +| approx_kl | 0.00037078123 | +| clip_fraction | 0.0876 | +| clip_range | 0.0301 | +| entropy_loss | -7.84 | +| explained_variance | 0.071 | +| learning_rate | 1.01e-05 | +| loss | -0.0105 | +| n_updates | 18732 | +| policy_gradient_loss | -0.00544 | +| value_loss | 0.000144 | +------------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.266 | +| time/ | | +| fps | 1377 | +| iterations | 4685 | +| time_elapsed | 6965 | +| total_timesteps | 9594880 | +| train/ | | +| approx_kl | 0.0003153686 | +| clip_fraction | 0.0752 | +| clip_range | 0.0301 | +| entropy_loss | -7.98 | +| explained_variance | -0.0148 | +| learning_rate | 1.01e-05 | +| loss | -0.0113 | +| n_updates | 18736 | +| policy_gradient_loss | -0.00585 | +| value_loss | 9.26e-05 | +------------------------------------------ +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.268 | +| time/ | | +| fps | 1377 | +| iterations | 4686 | +| time_elapsed | 6967 | +| total_timesteps | 9596928 | +| train/ | | +| approx_kl | 0.00038757734 | +| clip_fraction | 0.0922 | +| clip_range | 0.0301 | +| entropy_loss | -7.99 | +| explained_variance | -0.0698 | +| learning_rate | 1e-05 | +| loss | -0.0114 | +| n_updates | 18740 | +| policy_gradient_loss | -0.00591 | +| value_loss | 0.000211 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.268 | +| time/ | | +| fps | 1377 | +| iterations | 4687 | +| time_elapsed | 6969 | +| total_timesteps | 9598976 | +| train/ | | +| approx_kl | 0.00037705537 | +| clip_fraction | 0.0858 | +| clip_range | 0.03 | +| entropy_loss | -7.81 | +| explained_variance | 0.275 | +| learning_rate | 9.98e-06 | +| loss | -0.00871 | +| n_updates | 18744 | +| policy_gradient_loss | -0.00566 | +| value_loss | 8.88e-05 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.267 | +| time/ | | +| fps | 1377 | +| iterations | 4688 | +| time_elapsed | 6970 | +| total_timesteps | 9601024 | +| train/ | | +| approx_kl | 0.00030173417 | +| clip_fraction | 0.0618 | +| clip_range | 0.03 | +| entropy_loss | -7.96 | +| explained_variance | -0.0318 | +| learning_rate | 9.94e-06 | +| loss | -0.00848 | +| n_updates | 18748 | +| policy_gradient_loss | -0.00482 | +| value_loss | 6.89e-05 | +------------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.268 | +| time/ | | +| fps | 1377 | +| iterations | 4689 | +| time_elapsed | 6972 | +| total_timesteps | 9603072 | +| train/ | | +| approx_kl | 0.0003066486 | +| clip_fraction | 0.0717 | +| clip_range | 0.03 | +| entropy_loss | -7.9 | +| explained_variance | -0.00446 | +| learning_rate | 9.9e-06 | +| loss | -0.00884 | +| n_updates | 18752 | +| policy_gradient_loss | -0.00521 | +| value_loss | 0.000235 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.272 | +| time/ | | +| fps | 1377 | +| iterations | 4690 | +| time_elapsed | 6973 | +| total_timesteps | 9605120 | +| train/ | | +| approx_kl | 0.0002861889 | +| clip_fraction | 0.0721 | +| clip_range | 0.03 | +| entropy_loss | -7.79 | +| explained_variance | 0.115 | +| learning_rate | 9.86e-06 | +| loss | -0.00791 | +| n_updates | 18756 | +| policy_gradient_loss | -0.00496 | +| value_loss | 0.000134 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.271 | +| time/ | | +| fps | 1377 | +| iterations | 4691 | +| time_elapsed | 6975 | +| total_timesteps | 9607168 | +| train/ | | +| approx_kl | 0.0003514994 | +| clip_fraction | 0.0803 | +| clip_range | 0.0299 | +| entropy_loss | -7.83 | +| explained_variance | -0.126 | +| learning_rate | 9.82e-06 | +| loss | -0.00879 | +| n_updates | 18760 | +| policy_gradient_loss | -0.00548 | +| value_loss | 0.000121 | +------------------------------------------ +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.271 | +| time/ | | +| fps | 1377 | +| iterations | 4692 | +| time_elapsed | 6976 | +| total_timesteps | 9609216 | +| train/ | | +| approx_kl | 0.00031514277 | +| clip_fraction | 0.073 | +| clip_range | 0.0299 | +| entropy_loss | -7.69 | +| explained_variance | -0.0436 | +| learning_rate | 9.78e-06 | +| loss | -0.0113 | +| n_updates | 18764 | +| policy_gradient_loss | -0.00556 | +| value_loss | 0.000236 | +------------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.273 | +| time/ | | +| fps | 1377 | +| iterations | 4693 | +| time_elapsed | 6978 | +| total_timesteps | 9611264 | +| train/ | | +| approx_kl | 0.0003392457 | +| clip_fraction | 0.0717 | +| clip_range | 0.0299 | +| entropy_loss | -7.92 | +| explained_variance | -0.0156 | +| learning_rate | 9.74e-06 | +| loss | -0.0106 | +| n_updates | 18768 | +| policy_gradient_loss | -0.00562 | +| value_loss | 0.000172 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.274 | +| time/ | | +| fps | 1377 | +| iterations | 4694 | +| time_elapsed | 6980 | +| total_timesteps | 9613312 | +| train/ | | +| approx_kl | 0.0003282003 | +| clip_fraction | 0.0707 | +| clip_range | 0.0299 | +| entropy_loss | -7.9 | +| explained_variance | 0.0372 | +| learning_rate | 9.7e-06 | +| loss | -0.00892 | +| n_updates | 18772 | +| policy_gradient_loss | -0.00514 | +| value_loss | 0.000158 | +------------------------------------------ +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.267 | +| time/ | | +| fps | 1377 | +| iterations | 4695 | +| time_elapsed | 6981 | +| total_timesteps | 9615360 | +| train/ | | +| approx_kl | 0.00031326292 | +| clip_fraction | 0.0702 | +| clip_range | 0.0298 | +| entropy_loss | -7.88 | +| explained_variance | -0.0211 | +| learning_rate | 9.66e-06 | +| loss | -0.00878 | +| n_updates | 18776 | +| policy_gradient_loss | -0.00535 | +| value_loss | 0.000167 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.267 | +| time/ | | +| fps | 1377 | +| iterations | 4696 | +| time_elapsed | 6983 | +| total_timesteps | 9617408 | +| train/ | | +| approx_kl | 0.00035361852 | +| clip_fraction | 0.0757 | +| clip_range | 0.0298 | +| entropy_loss | -7.75 | +| explained_variance | 0.0889 | +| learning_rate | 9.62e-06 | +| loss | -0.00896 | +| n_updates | 18780 | +| policy_gradient_loss | -0.00543 | +| value_loss | 0.000154 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.267 | +| time/ | | +| fps | 1377 | +| iterations | 4697 | +| time_elapsed | 6984 | +| total_timesteps | 9619456 | +| train/ | | +| approx_kl | 0.00034556093 | +| clip_fraction | 0.0746 | +| clip_range | 0.0298 | +| entropy_loss | -7.96 | +| explained_variance | -0.0176 | +| learning_rate | 9.58e-06 | +| loss | -0.01 | +| n_updates | 18784 | +| policy_gradient_loss | -0.0056 | +| value_loss | 0.000124 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.267 | +| time/ | | +| fps | 1377 | +| iterations | 4698 | +| time_elapsed | 6986 | +| total_timesteps | 9621504 | +| train/ | | +| approx_kl | 0.00032083812 | +| clip_fraction | 0.0712 | +| clip_range | 0.0298 | +| entropy_loss | -7.8 | +| explained_variance | -0.0469 | +| learning_rate | 9.53e-06 | +| loss | -0.00927 | +| n_updates | 18788 | +| policy_gradient_loss | -0.00549 | +| value_loss | 0.000126 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.268 | +| time/ | | +| fps | 1377 | +| iterations | 4699 | +| time_elapsed | 6988 | +| total_timesteps | 9623552 | +| train/ | | +| approx_kl | 0.00029347304 | +| clip_fraction | 0.0605 | +| clip_range | 0.0297 | +| entropy_loss | -8.01 | +| explained_variance | -0.018 | +| learning_rate | 9.49e-06 | +| loss | -0.00992 | +| n_updates | 18792 | +| policy_gradient_loss | -0.00488 | +| value_loss | 0.000123 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.267 | +| time/ | | +| fps | 1377 | +| iterations | 4700 | +| time_elapsed | 6989 | +| total_timesteps | 9625600 | +| train/ | | +| approx_kl | 0.00033678574 | +| clip_fraction | 0.0682 | +| clip_range | 0.0297 | +| entropy_loss | -7.91 | +| explained_variance | -0.00793 | +| learning_rate | 9.45e-06 | +| loss | -0.00826 | +| n_updates | 18796 | +| policy_gradient_loss | -0.00475 | +| value_loss | 0.000197 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.259 | +| time/ | | +| fps | 1377 | +| iterations | 4701 | +| time_elapsed | 6991 | +| total_timesteps | 9627648 | +| train/ | | +| approx_kl | 0.00031851113 | +| clip_fraction | 0.0742 | +| clip_range | 0.0297 | +| entropy_loss | -7.85 | +| explained_variance | -0.0172 | +| learning_rate | 9.41e-06 | +| loss | -0.011 | +| n_updates | 18800 | +| policy_gradient_loss | -0.00544 | +| value_loss | 8.74e-05 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.264 | +| time/ | | +| fps | 1377 | +| iterations | 4702 | +| time_elapsed | 6992 | +| total_timesteps | 9629696 | +| train/ | | +| approx_kl | 0.00030017464 | +| clip_fraction | 0.0688 | +| clip_range | 0.0297 | +| entropy_loss | -7.76 | +| explained_variance | -0.035 | +| learning_rate | 9.37e-06 | +| loss | -0.00662 | +| n_updates | 18804 | +| policy_gradient_loss | -0.00475 | +| value_loss | 0.000207 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.264 | +| time/ | | +| fps | 1377 | +| iterations | 4703 | +| time_elapsed | 6994 | +| total_timesteps | 9631744 | +| train/ | | +| approx_kl | 0.00034118394 | +| clip_fraction | 0.0769 | +| clip_range | 0.0296 | +| entropy_loss | -7.82 | +| explained_variance | 0.0201 | +| learning_rate | 9.33e-06 | +| loss | -0.00893 | +| n_updates | 18808 | +| policy_gradient_loss | -0.00528 | +| value_loss | 0.000167 | +------------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.263 | +| time/ | | +| fps | 1377 | +| iterations | 4704 | +| time_elapsed | 6996 | +| total_timesteps | 9633792 | +| train/ | | +| approx_kl | 0.0003015872 | +| clip_fraction | 0.0635 | +| clip_range | 0.0296 | +| entropy_loss | -7.99 | +| explained_variance | -0.0749 | +| learning_rate | 9.29e-06 | +| loss | -0.00912 | +| n_updates | 18812 | +| policy_gradient_loss | -0.00535 | +| value_loss | 8.88e-05 | +------------------------------------------ +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.262 | +| time/ | | +| fps | 1377 | +| iterations | 4705 | +| time_elapsed | 6997 | +| total_timesteps | 9635840 | +| train/ | | +| approx_kl | 0.00024057843 | +| clip_fraction | 0.0529 | +| clip_range | 0.0296 | +| entropy_loss | -7.84 | +| explained_variance | 0.0524 | +| learning_rate | 9.25e-06 | +| loss | -0.00694 | +| n_updates | 18816 | +| policy_gradient_loss | -0.00453 | +| value_loss | 0.000246 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.26 | +| time/ | | +| fps | 1376 | +| iterations | 4706 | +| time_elapsed | 6999 | +| total_timesteps | 9637888 | +| train/ | | +| approx_kl | 0.00029827724 | +| clip_fraction | 0.0679 | +| clip_range | 0.0296 | +| entropy_loss | -7.92 | +| explained_variance | -0.0865 | +| learning_rate | 9.21e-06 | +| loss | -0.0101 | +| n_updates | 18820 | +| policy_gradient_loss | -0.00511 | +| value_loss | 6.3e-05 | +------------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.258 | +| time/ | | +| fps | 1376 | +| iterations | 4707 | +| time_elapsed | 7000 | +| total_timesteps | 9639936 | +| train/ | | +| approx_kl | 0.0003227851 | +| clip_fraction | 0.0706 | +| clip_range | 0.0295 | +| entropy_loss | -7.84 | +| explained_variance | -0.112 | +| learning_rate | 9.17e-06 | +| loss | -0.00782 | +| n_updates | 18824 | +| policy_gradient_loss | -0.00481 | +| value_loss | 0.000153 | +------------------------------------------ +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.257 | +| time/ | | +| fps | 1376 | +| iterations | 4708 | +| time_elapsed | 7002 | +| total_timesteps | 9641984 | +| train/ | | +| approx_kl | 0.00031382559 | +| clip_fraction | 0.0709 | +| clip_range | 0.0295 | +| entropy_loss | -7.93 | +| explained_variance | -0.0151 | +| learning_rate | 9.13e-06 | +| loss | -0.0107 | +| n_updates | 18828 | +| policy_gradient_loss | -0.00529 | +| value_loss | 0.000157 | +------------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.257 | +| time/ | | +| fps | 1376 | +| iterations | 4709 | +| time_elapsed | 7003 | +| total_timesteps | 9644032 | +| train/ | | +| approx_kl | 0.0003359211 | +| clip_fraction | 0.0771 | +| clip_range | 0.0295 | +| entropy_loss | -7.92 | +| explained_variance | -0.00561 | +| learning_rate | 9.09e-06 | +| loss | -0.0102 | +| n_updates | 18832 | +| policy_gradient_loss | -0.00575 | +| value_loss | 0.000202 | +------------------------------------------ +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.257 | +| time/ | | +| fps | 1376 | +| iterations | 4710 | +| time_elapsed | 7005 | +| total_timesteps | 9646080 | +| train/ | | +| approx_kl | 0.00028499283 | +| clip_fraction | 0.0686 | +| clip_range | 0.0294 | +| entropy_loss | -7.85 | +| explained_variance | -0.0048 | +| learning_rate | 9.05e-06 | +| loss | -0.00769 | +| n_updates | 18836 | +| policy_gradient_loss | -0.00502 | +| value_loss | 9.56e-05 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.249 | +| time/ | | +| fps | 1376 | +| iterations | 4711 | +| time_elapsed | 7006 | +| total_timesteps | 9648128 | +| train/ | | +| approx_kl | 0.00033127062 | +| clip_fraction | 0.085 | +| clip_range | 0.0294 | +| entropy_loss | -7.5 | +| explained_variance | 0.177 | +| learning_rate | 9.01e-06 | +| loss | -0.0102 | +| n_updates | 18840 | +| policy_gradient_loss | -0.00562 | +| value_loss | 0.000155 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.249 | +| time/ | | +| fps | 1376 | +| iterations | 4712 | +| time_elapsed | 7008 | +| total_timesteps | 9650176 | +| train/ | | +| approx_kl | 0.00032789377 | +| clip_fraction | 0.0768 | +| clip_range | 0.0294 | +| entropy_loss | -7.75 | +| explained_variance | -0.0081 | +| learning_rate | 8.97e-06 | +| loss | -0.0101 | +| n_updates | 18844 | +| policy_gradient_loss | -0.0057 | +| value_loss | 7.53e-05 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.253 | +| time/ | | +| fps | 1376 | +| iterations | 4713 | +| time_elapsed | 7010 | +| total_timesteps | 9652224 | +| train/ | | +| approx_kl | 0.00028183105 | +| clip_fraction | 0.0638 | +| clip_range | 0.0294 | +| entropy_loss | -7.92 | +| explained_variance | 0.00912 | +| learning_rate | 8.93e-06 | +| loss | -0.0102 | +| n_updates | 18848 | +| policy_gradient_loss | -0.00547 | +| value_loss | 0.000178 | +------------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.259 | +| time/ | | +| fps | 1376 | +| iterations | 4714 | +| time_elapsed | 7011 | +| total_timesteps | 9654272 | +| train/ | | +| approx_kl | 0.0002321476 | +| clip_fraction | 0.0483 | +| clip_range | 0.0293 | +| entropy_loss | -7.89 | +| explained_variance | 0.0846 | +| learning_rate | 8.89e-06 | +| loss | -0.00964 | +| n_updates | 18852 | +| policy_gradient_loss | -0.00463 | +| value_loss | 0.000163 | +------------------------------------------ +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.259 | +| time/ | | +| fps | 1376 | +| iterations | 4715 | +| time_elapsed | 7013 | +| total_timesteps | 9656320 | +| train/ | | +| approx_kl | 0.00030817412 | +| clip_fraction | 0.0691 | +| clip_range | 0.0293 | +| entropy_loss | -7.69 | +| explained_variance | 0.0981 | +| learning_rate | 8.85e-06 | +| loss | -0.00885 | +| n_updates | 18856 | +| policy_gradient_loss | -0.00539 | +| value_loss | 0.000273 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.259 | +| time/ | | +| fps | 1376 | +| iterations | 4716 | +| time_elapsed | 7014 | +| total_timesteps | 9658368 | +| train/ | | +| approx_kl | 0.00032858524 | +| clip_fraction | 0.0786 | +| clip_range | 0.0293 | +| entropy_loss | -7.86 | +| explained_variance | 0.0632 | +| learning_rate | 8.8e-06 | +| loss | -0.0092 | +| n_updates | 18860 | +| policy_gradient_loss | -0.00532 | +| value_loss | 0.000132 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.259 | +| time/ | | +| fps | 1376 | +| iterations | 4717 | +| time_elapsed | 7016 | +| total_timesteps | 9660416 | +| train/ | | +| approx_kl | 0.00033682204 | +| clip_fraction | 0.0712 | +| clip_range | 0.0293 | +| entropy_loss | -7.99 | +| explained_variance | -0.000594 | +| learning_rate | 8.76e-06 | +| loss | -0.00949 | +| n_updates | 18864 | +| policy_gradient_loss | -0.00514 | +| value_loss | 0.000205 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.26 | +| time/ | | +| fps | 1376 | +| iterations | 4718 | +| time_elapsed | 7017 | +| total_timesteps | 9662464 | +| train/ | | +| approx_kl | 0.00029899305 | +| clip_fraction | 0.068 | +| clip_range | 0.0292 | +| entropy_loss | -7.96 | +| explained_variance | -0.0428 | +| learning_rate | 8.72e-06 | +| loss | -0.00914 | +| n_updates | 18868 | +| policy_gradient_loss | -0.00531 | +| value_loss | 0.000121 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.263 | +| time/ | | +| fps | 1376 | +| iterations | 4719 | +| time_elapsed | 7019 | +| total_timesteps | 9664512 | +| train/ | | +| approx_kl | 0.00025680268 | +| clip_fraction | 0.0563 | +| clip_range | 0.0292 | +| entropy_loss | -7.94 | +| explained_variance | -0.024 | +| learning_rate | 8.68e-06 | +| loss | -0.00845 | +| n_updates | 18872 | +| policy_gradient_loss | -0.00469 | +| value_loss | 0.000117 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.268 | +| time/ | | +| fps | 1376 | +| iterations | 4720 | +| time_elapsed | 7020 | +| total_timesteps | 9666560 | +| train/ | | +| approx_kl | 0.00031081054 | +| clip_fraction | 0.0659 | +| clip_range | 0.0292 | +| entropy_loss | -7.88 | +| explained_variance | -0.0108 | +| learning_rate | 8.64e-06 | +| loss | -0.00902 | +| n_updates | 18876 | +| policy_gradient_loss | -0.00496 | +| value_loss | 0.00019 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.272 | +| time/ | | +| fps | 1376 | +| iterations | 4721 | +| time_elapsed | 7022 | +| total_timesteps | 9668608 | +| train/ | | +| approx_kl | 0.00026792634 | +| clip_fraction | 0.0658 | +| clip_range | 0.0292 | +| entropy_loss | -7.86 | +| explained_variance | 0.033 | +| learning_rate | 8.6e-06 | +| loss | -0.00808 | +| n_updates | 18880 | +| policy_gradient_loss | -0.00513 | +| value_loss | 0.000188 | +------------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.269 | +| time/ | | +| fps | 1376 | +| iterations | 4722 | +| time_elapsed | 7024 | +| total_timesteps | 9670656 | +| train/ | | +| approx_kl | 0.0002507684 | +| clip_fraction | 0.0596 | +| clip_range | 0.0291 | +| entropy_loss | -7.76 | +| explained_variance | 0.0028 | +| learning_rate | 8.56e-06 | +| loss | -0.00843 | +| n_updates | 18884 | +| policy_gradient_loss | -0.00491 | +| value_loss | 0.000154 | +------------------------------------------ +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.271 | +| time/ | | +| fps | 1376 | +| iterations | 4723 | +| time_elapsed | 7025 | +| total_timesteps | 9672704 | +| train/ | | +| approx_kl | 0.00032883242 | +| clip_fraction | 0.0769 | +| clip_range | 0.0291 | +| entropy_loss | -7.7 | +| explained_variance | 0.0588 | +| learning_rate | 8.52e-06 | +| loss | -0.00923 | +| n_updates | 18888 | +| policy_gradient_loss | -0.00554 | +| value_loss | 0.000179 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.274 | +| time/ | | +| fps | 1376 | +| iterations | 4724 | +| time_elapsed | 7027 | +| total_timesteps | 9674752 | +| train/ | | +| approx_kl | 0.00029159087 | +| clip_fraction | 0.0692 | +| clip_range | 0.0291 | +| entropy_loss | -7.83 | +| explained_variance | 0.0322 | +| learning_rate | 8.48e-06 | +| loss | -0.00961 | +| n_updates | 18892 | +| policy_gradient_loss | -0.00548 | +| value_loss | 0.000149 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.274 | +| time/ | | +| fps | 1376 | +| iterations | 4725 | +| time_elapsed | 7028 | +| total_timesteps | 9676800 | +| train/ | | +| approx_kl | 0.00031350728 | +| clip_fraction | 0.0725 | +| clip_range | 0.0291 | +| entropy_loss | -7.82 | +| explained_variance | 0.0581 | +| learning_rate | 8.44e-06 | +| loss | -0.012 | +| n_updates | 18896 | +| policy_gradient_loss | -0.0049 | +| value_loss | 3.32e-05 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.274 | +| time/ | | +| fps | 1376 | +| iterations | 4726 | +| time_elapsed | 7030 | +| total_timesteps | 9678848 | +| train/ | | +| approx_kl | 0.00027652955 | +| clip_fraction | 0.0718 | +| clip_range | 0.029 | +| entropy_loss | -7.9 | +| explained_variance | 0.0805 | +| learning_rate | 8.4e-06 | +| loss | -0.0087 | +| n_updates | 18900 | +| policy_gradient_loss | -0.00521 | +| value_loss | 9.96e-05 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.28 | +| time/ | | +| fps | 1376 | +| iterations | 4727 | +| time_elapsed | 7031 | +| total_timesteps | 9680896 | +| train/ | | +| approx_kl | 0.00028659852 | +| clip_fraction | 0.0696 | +| clip_range | 0.029 | +| entropy_loss | -7.94 | +| explained_variance | -0.00473 | +| learning_rate | 8.36e-06 | +| loss | -0.00723 | +| n_updates | 18904 | +| policy_gradient_loss | -0.00504 | +| value_loss | 0.000108 | +------------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.28 | +| time/ | | +| fps | 1376 | +| iterations | 4728 | +| time_elapsed | 7033 | +| total_timesteps | 9682944 | +| train/ | | +| approx_kl | 0.0003022636 | +| clip_fraction | 0.0779 | +| clip_range | 0.029 | +| entropy_loss | -7.83 | +| explained_variance | 0.0104 | +| learning_rate | 8.32e-06 | +| loss | -0.00934 | +| n_updates | 18908 | +| policy_gradient_loss | -0.00521 | +| value_loss | 0.000242 | +------------------------------------------ +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 1376 | +| iterations | 4729 | +| time_elapsed | 7035 | +| total_timesteps | 9684992 | +| train/ | | +| approx_kl | 0.00024289626 | +| clip_fraction | 0.0576 | +| clip_range | 0.029 | +| entropy_loss | -7.97 | +| explained_variance | 0.0156 | +| learning_rate | 8.28e-06 | +| loss | -0.00893 | +| n_updates | 18912 | +| policy_gradient_loss | -0.00534 | +| value_loss | 9.24e-05 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.285 | +| time/ | | +| fps | 1376 | +| iterations | 4730 | +| time_elapsed | 7036 | +| total_timesteps | 9687040 | +| train/ | | +| approx_kl | 0.00023522825 | +| clip_fraction | 0.0507 | +| clip_range | 0.0289 | +| entropy_loss | -7.84 | +| explained_variance | 0.0505 | +| learning_rate | 8.24e-06 | +| loss | -0.00766 | +| n_updates | 18916 | +| policy_gradient_loss | -0.00457 | +| value_loss | 0.000221 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 1376 | +| iterations | 4731 | +| time_elapsed | 7038 | +| total_timesteps | 9689088 | +| train/ | | +| approx_kl | 0.00023968838 | +| clip_fraction | 0.053 | +| clip_range | 0.0289 | +| entropy_loss | -7.77 | +| explained_variance | 0.131 | +| learning_rate | 8.2e-06 | +| loss | -0.00843 | +| n_updates | 18920 | +| policy_gradient_loss | -0.00461 | +| value_loss | 0.000202 | +------------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.278 | +| time/ | | +| fps | 1376 | +| iterations | 4732 | +| time_elapsed | 7039 | +| total_timesteps | 9691136 | +| train/ | | +| approx_kl | 0.0002977286 | +| clip_fraction | 0.0741 | +| clip_range | 0.0289 | +| entropy_loss | -7.86 | +| explained_variance | 0.141 | +| learning_rate | 8.16e-06 | +| loss | -0.0103 | +| n_updates | 18924 | +| policy_gradient_loss | -0.00547 | +| value_loss | 9.35e-05 | +------------------------------------------ +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 1376 | +| iterations | 4733 | +| time_elapsed | 7041 | +| total_timesteps | 9693184 | +| train/ | | +| approx_kl | 0.00024251975 | +| clip_fraction | 0.0525 | +| clip_range | 0.0289 | +| entropy_loss | -7.9 | +| explained_variance | -0.027 | +| learning_rate | 8.12e-06 | +| loss | -0.00852 | +| n_updates | 18928 | +| policy_gradient_loss | -0.00481 | +| value_loss | 0.000114 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.283 | +| time/ | | +| fps | 1376 | +| iterations | 4734 | +| time_elapsed | 7042 | +| total_timesteps | 9695232 | +| train/ | | +| approx_kl | 0.00026838452 | +| clip_fraction | 0.0651 | +| clip_range | 0.0288 | +| entropy_loss | -7.81 | +| explained_variance | -0.0196 | +| learning_rate | 8.07e-06 | +| loss | -0.00934 | +| n_updates | 18932 | +| policy_gradient_loss | -0.00533 | +| value_loss | 0.00023 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.291 | +| time/ | | +| fps | 1376 | +| iterations | 4735 | +| time_elapsed | 7044 | +| total_timesteps | 9697280 | +| train/ | | +| approx_kl | 0.00022244031 | +| clip_fraction | 0.0519 | +| clip_range | 0.0288 | +| entropy_loss | -7.89 | +| explained_variance | -0.0406 | +| learning_rate | 8.03e-06 | +| loss | -0.0103 | +| n_updates | 18936 | +| policy_gradient_loss | -0.00422 | +| value_loss | 0.000202 | +------------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.287 | +| time/ | | +| fps | 1376 | +| iterations | 4736 | +| time_elapsed | 7045 | +| total_timesteps | 9699328 | +| train/ | | +| approx_kl | 0.0002565268 | +| clip_fraction | 0.063 | +| clip_range | 0.0288 | +| entropy_loss | -7.83 | +| explained_variance | 0.0285 | +| learning_rate | 7.99e-06 | +| loss | -0.00974 | +| n_updates | 18940 | +| policy_gradient_loss | -0.00509 | +| value_loss | 0.00017 | +------------------------------------------ +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.289 | +| time/ | | +| fps | 1376 | +| iterations | 4737 | +| time_elapsed | 7047 | +| total_timesteps | 9701376 | +| train/ | | +| approx_kl | 0.00022435322 | +| clip_fraction | 0.0557 | +| clip_range | 0.0288 | +| entropy_loss | -7.8 | +| explained_variance | 0.0694 | +| learning_rate | 7.95e-06 | +| loss | -0.00728 | +| n_updates | 18944 | +| policy_gradient_loss | -0.00432 | +| value_loss | 0.000269 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.289 | +| time/ | | +| fps | 1376 | +| iterations | 4738 | +| time_elapsed | 7049 | +| total_timesteps | 9703424 | +| train/ | | +| approx_kl | 0.00027638715 | +| clip_fraction | 0.0778 | +| clip_range | 0.0287 | +| entropy_loss | -7.68 | +| explained_variance | 0.267 | +| learning_rate | 7.91e-06 | +| loss | -0.01 | +| n_updates | 18948 | +| policy_gradient_loss | -0.00562 | +| value_loss | 7.33e-05 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.285 | +| time/ | | +| fps | 1376 | +| iterations | 4739 | +| time_elapsed | 7050 | +| total_timesteps | 9705472 | +| train/ | | +| approx_kl | 0.00028449975 | +| clip_fraction | 0.0618 | +| clip_range | 0.0287 | +| entropy_loss | -7.93 | +| explained_variance | -0.0214 | +| learning_rate | 7.87e-06 | +| loss | -0.00908 | +| n_updates | 18952 | +| policy_gradient_loss | -0.00487 | +| value_loss | 0.000138 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.281 | +| time/ | | +| fps | 1376 | +| iterations | 4740 | +| time_elapsed | 7052 | +| total_timesteps | 9707520 | +| train/ | | +| approx_kl | 0.00022642018 | +| clip_fraction | 0.062 | +| clip_range | 0.0287 | +| entropy_loss | -7.87 | +| explained_variance | 0.0144 | +| learning_rate | 7.83e-06 | +| loss | -0.00962 | +| n_updates | 18956 | +| policy_gradient_loss | -0.00487 | +| value_loss | 0.000197 | +------------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.287 | +| time/ | | +| fps | 1376 | +| iterations | 4741 | +| time_elapsed | 7053 | +| total_timesteps | 9709568 | +| train/ | | +| approx_kl | 0.0002487767 | +| clip_fraction | 0.0656 | +| clip_range | 0.0287 | +| entropy_loss | -7.73 | +| explained_variance | -0.0469 | +| learning_rate | 7.79e-06 | +| loss | -0.00829 | +| n_updates | 18960 | +| policy_gradient_loss | -0.00514 | +| value_loss | 0.0002 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.287 | +| time/ | | +| fps | 1376 | +| iterations | 4742 | +| time_elapsed | 7055 | +| total_timesteps | 9711616 | +| train/ | | +| approx_kl | 0.0001930024 | +| clip_fraction | 0.048 | +| clip_range | 0.0286 | +| entropy_loss | -7.75 | +| explained_variance | 0.00836 | +| learning_rate | 7.75e-06 | +| loss | -0.00759 | +| n_updates | 18964 | +| policy_gradient_loss | -0.00445 | +| value_loss | 0.000164 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.287 | +| time/ | | +| fps | 1376 | +| iterations | 4743 | +| time_elapsed | 7056 | +| total_timesteps | 9713664 | +| train/ | | +| approx_kl | 0.0002451434 | +| clip_fraction | 0.0559 | +| clip_range | 0.0286 | +| entropy_loss | -7.88 | +| explained_variance | 0.0339 | +| learning_rate | 7.71e-06 | +| loss | -0.0092 | +| n_updates | 18968 | +| policy_gradient_loss | -0.00518 | +| value_loss | 0.000125 | +------------------------------------------ +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.283 | +| time/ | | +| fps | 1376 | +| iterations | 4744 | +| time_elapsed | 7058 | +| total_timesteps | 9715712 | +| train/ | | +| approx_kl | 0.00022808605 | +| clip_fraction | 0.0513 | +| clip_range | 0.0286 | +| entropy_loss | -7.88 | +| explained_variance | -0.0191 | +| learning_rate | 7.67e-06 | +| loss | -0.00838 | +| n_updates | 18972 | +| policy_gradient_loss | -0.00467 | +| value_loss | 0.000237 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 1376 | +| iterations | 4745 | +| time_elapsed | 7060 | +| total_timesteps | 9717760 | +| train/ | | +| approx_kl | 0.00021573523 | +| clip_fraction | 0.0509 | +| clip_range | 0.0286 | +| entropy_loss | -7.91 | +| explained_variance | 0.00959 | +| learning_rate | 7.63e-06 | +| loss | -0.00833 | +| n_updates | 18976 | +| policy_gradient_loss | -0.00475 | +| value_loss | 0.000195 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 1376 | +| iterations | 4746 | +| time_elapsed | 7061 | +| total_timesteps | 9719808 | +| train/ | | +| approx_kl | 0.00022241237 | +| clip_fraction | 0.0493 | +| clip_range | 0.0285 | +| entropy_loss | -7.82 | +| explained_variance | 0.0218 | +| learning_rate | 7.59e-06 | +| loss | -0.00742 | +| n_updates | 18980 | +| policy_gradient_loss | -0.00456 | +| value_loss | 0.000123 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 1376 | +| iterations | 4747 | +| time_elapsed | 7063 | +| total_timesteps | 9721856 | +| train/ | | +| approx_kl | 0.00021422663 | +| clip_fraction | 0.0525 | +| clip_range | 0.0285 | +| entropy_loss | -7.8 | +| explained_variance | 0.174 | +| learning_rate | 7.55e-06 | +| loss | -0.00917 | +| n_updates | 18984 | +| policy_gradient_loss | -0.00462 | +| value_loss | 0.000116 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 1376 | +| iterations | 4748 | +| time_elapsed | 7064 | +| total_timesteps | 9723904 | +| train/ | | +| approx_kl | 0.00024047184 | +| clip_fraction | 0.0592 | +| clip_range | 0.0285 | +| entropy_loss | -7.89 | +| explained_variance | 0.121 | +| learning_rate | 7.51e-06 | +| loss | -0.00926 | +| n_updates | 18988 | +| policy_gradient_loss | -0.00529 | +| value_loss | 8.16e-05 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.281 | +| time/ | | +| fps | 1376 | +| iterations | 4749 | +| time_elapsed | 7066 | +| total_timesteps | 9725952 | +| train/ | | +| approx_kl | 0.00020935066 | +| clip_fraction | 0.0496 | +| clip_range | 0.0285 | +| entropy_loss | -7.93 | +| explained_variance | -0.03 | +| learning_rate | 7.47e-06 | +| loss | -0.00743 | +| n_updates | 18992 | +| policy_gradient_loss | -0.00453 | +| value_loss | 0.000143 | +------------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 1376 | +| iterations | 4750 | +| time_elapsed | 7067 | +| total_timesteps | 9728000 | +| train/ | | +| approx_kl | 0.0002376168 | +| clip_fraction | 0.0533 | +| clip_range | 0.0284 | +| entropy_loss | -7.88 | +| explained_variance | -0.0823 | +| learning_rate | 7.43e-06 | +| loss | -0.0084 | +| n_updates | 18996 | +| policy_gradient_loss | -0.00493 | +| value_loss | 9.65e-05 | +------------------------------------------ +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.271 | +| time/ | | +| fps | 1376 | +| iterations | 4751 | +| time_elapsed | 7069 | +| total_timesteps | 9730048 | +| train/ | | +| approx_kl | 0.00022469477 | +| clip_fraction | 0.0594 | +| clip_range | 0.0284 | +| entropy_loss | -7.52 | +| explained_variance | 0.111 | +| learning_rate | 7.39e-06 | +| loss | -0.00662 | +| n_updates | 19000 | +| policy_gradient_loss | -0.00429 | +| value_loss | 0.000199 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.265 | +| time/ | | +| fps | 1376 | +| iterations | 4752 | +| time_elapsed | 7071 | +| total_timesteps | 9732096 | +| train/ | | +| approx_kl | 0.00022198903 | +| clip_fraction | 0.0552 | +| clip_range | 0.0284 | +| entropy_loss | -7.82 | +| explained_variance | 0.0217 | +| learning_rate | 7.35e-06 | +| loss | -0.00906 | +| n_updates | 19004 | +| policy_gradient_loss | -0.0053 | +| value_loss | 0.000224 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.262 | +| time/ | | +| fps | 1376 | +| iterations | 4753 | +| time_elapsed | 7072 | +| total_timesteps | 9734144 | +| train/ | | +| approx_kl | 0.00025045933 | +| clip_fraction | 0.0601 | +| clip_range | 0.0283 | +| entropy_loss | -7.89 | +| explained_variance | -0.0304 | +| learning_rate | 7.3e-06 | +| loss | -0.0107 | +| n_updates | 19008 | +| policy_gradient_loss | -0.00491 | +| value_loss | 9.55e-05 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.264 | +| time/ | | +| fps | 1376 | +| iterations | 4754 | +| time_elapsed | 7074 | +| total_timesteps | 9736192 | +| train/ | | +| approx_kl | 0.00022104266 | +| clip_fraction | 0.0559 | +| clip_range | 0.0283 | +| entropy_loss | -7.89 | +| explained_variance | -0.000626 | +| learning_rate | 7.26e-06 | +| loss | -0.00875 | +| n_updates | 19012 | +| policy_gradient_loss | -0.00534 | +| value_loss | 0.000274 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.263 | +| time/ | | +| fps | 1376 | +| iterations | 4755 | +| time_elapsed | 7075 | +| total_timesteps | 9738240 | +| train/ | | +| approx_kl | 0.00019386347 | +| clip_fraction | 0.043 | +| clip_range | 0.0283 | +| entropy_loss | -7.89 | +| explained_variance | 0.0109 | +| learning_rate | 7.22e-06 | +| loss | -0.009 | +| n_updates | 19016 | +| policy_gradient_loss | -0.00441 | +| value_loss | 0.000102 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.266 | +| time/ | | +| fps | 1376 | +| iterations | 4756 | +| time_elapsed | 7077 | +| total_timesteps | 9740288 | +| train/ | | +| approx_kl | 0.00023563558 | +| clip_fraction | 0.0536 | +| clip_range | 0.0283 | +| entropy_loss | -7.88 | +| explained_variance | -0.00997 | +| learning_rate | 7.18e-06 | +| loss | -0.00879 | +| n_updates | 19020 | +| policy_gradient_loss | -0.00462 | +| value_loss | 0.000188 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.263 | +| time/ | | +| fps | 1376 | +| iterations | 4757 | +| time_elapsed | 7078 | +| total_timesteps | 9742336 | +| train/ | | +| approx_kl | 0.00018643364 | +| clip_fraction | 0.0441 | +| clip_range | 0.0282 | +| entropy_loss | -7.83 | +| explained_variance | 0.0539 | +| learning_rate | 7.14e-06 | +| loss | -0.00909 | +| n_updates | 19024 | +| policy_gradient_loss | -0.00398 | +| value_loss | 0.000299 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.267 | +| time/ | | +| fps | 1376 | +| iterations | 4758 | +| time_elapsed | 7080 | +| total_timesteps | 9744384 | +| train/ | | +| approx_kl | 0.00020577246 | +| clip_fraction | 0.0468 | +| clip_range | 0.0282 | +| entropy_loss | -7.77 | +| explained_variance | 0.0787 | +| learning_rate | 7.1e-06 | +| loss | -0.0083 | +| n_updates | 19028 | +| policy_gradient_loss | -0.00465 | +| value_loss | 0.000171 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.267 | +| time/ | | +| fps | 1376 | +| iterations | 4759 | +| time_elapsed | 7081 | +| total_timesteps | 9746432 | +| train/ | | +| approx_kl | 0.00022578271 | +| clip_fraction | 0.0496 | +| clip_range | 0.0282 | +| entropy_loss | -7.88 | +| explained_variance | 0.016 | +| learning_rate | 7.06e-06 | +| loss | -0.00883 | +| n_updates | 19032 | +| policy_gradient_loss | -0.00416 | +| value_loss | 0.0002 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.266 | +| time/ | | +| fps | 1376 | +| iterations | 4760 | +| time_elapsed | 7083 | +| total_timesteps | 9748480 | +| train/ | | +| approx_kl | 0.00022774094 | +| clip_fraction | 0.0602 | +| clip_range | 0.0282 | +| entropy_loss | -7.78 | +| explained_variance | -0.0236 | +| learning_rate | 7.02e-06 | +| loss | -0.00721 | +| n_updates | 19036 | +| policy_gradient_loss | -0.00419 | +| value_loss | 0.000173 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.257 | +| time/ | | +| fps | 1376 | +| iterations | 4761 | +| time_elapsed | 7084 | +| total_timesteps | 9750528 | +| train/ | | +| approx_kl | 0.00020625602 | +| clip_fraction | 0.0513 | +| clip_range | 0.0281 | +| entropy_loss | -7.96 | +| explained_variance | -0.013 | +| learning_rate | 6.98e-06 | +| loss | -0.00683 | +| n_updates | 19040 | +| policy_gradient_loss | -0.0048 | +| value_loss | 0.000153 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.258 | +| time/ | | +| fps | 1376 | +| iterations | 4762 | +| time_elapsed | 7086 | +| total_timesteps | 9752576 | +| train/ | | +| approx_kl | 0.00024127998 | +| clip_fraction | 0.0558 | +| clip_range | 0.0281 | +| entropy_loss | -7.75 | +| explained_variance | 0.182 | +| learning_rate | 6.94e-06 | +| loss | -0.00922 | +| n_updates | 19044 | +| policy_gradient_loss | -0.00507 | +| value_loss | 7.46e-05 | +------------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.262 | +| time/ | | +| fps | 1376 | +| iterations | 4763 | +| time_elapsed | 7088 | +| total_timesteps | 9754624 | +| train/ | | +| approx_kl | 0.0002012504 | +| clip_fraction | 0.0513 | +| clip_range | 0.0281 | +| entropy_loss | -7.73 | +| explained_variance | 0.0893 | +| learning_rate | 6.9e-06 | +| loss | -0.00922 | +| n_updates | 19048 | +| policy_gradient_loss | -0.00479 | +| value_loss | 0.000108 | +------------------------------------------ +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.262 | +| time/ | | +| fps | 1376 | +| iterations | 4764 | +| time_elapsed | 7089 | +| total_timesteps | 9756672 | +| train/ | | +| approx_kl | 0.00020329354 | +| clip_fraction | 0.0479 | +| clip_range | 0.0281 | +| entropy_loss | -7.78 | +| explained_variance | 0.025 | +| learning_rate | 6.86e-06 | +| loss | -0.00866 | +| n_updates | 19052 | +| policy_gradient_loss | -0.00491 | +| value_loss | 0.000266 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.266 | +| time/ | | +| fps | 1376 | +| iterations | 4765 | +| time_elapsed | 7091 | +| total_timesteps | 9758720 | +| train/ | | +| approx_kl | 0.00019525687 | +| clip_fraction | 0.0432 | +| clip_range | 0.028 | +| entropy_loss | -7.95 | +| explained_variance | -0.029 | +| learning_rate | 6.82e-06 | +| loss | -0.009 | +| n_updates | 19056 | +| policy_gradient_loss | -0.00472 | +| value_loss | 0.000125 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.263 | +| time/ | | +| fps | 1376 | +| iterations | 4766 | +| time_elapsed | 7092 | +| total_timesteps | 9760768 | +| train/ | | +| approx_kl | 0.00019613153 | +| clip_fraction | 0.047 | +| clip_range | 0.028 | +| entropy_loss | -7.76 | +| explained_variance | -0.038 | +| learning_rate | 6.78e-06 | +| loss | -0.00834 | +| n_updates | 19060 | +| policy_gradient_loss | -0.00457 | +| value_loss | 0.000363 | +------------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.262 | +| time/ | | +| fps | 1376 | +| iterations | 4767 | +| time_elapsed | 7094 | +| total_timesteps | 9762816 | +| train/ | | +| approx_kl | 0.0002199226 | +| clip_fraction | 0.0502 | +| clip_range | 0.028 | +| entropy_loss | -7.8 | +| explained_variance | 0.0411 | +| learning_rate | 6.74e-06 | +| loss | -0.00909 | +| n_updates | 19064 | +| policy_gradient_loss | -0.00477 | +| value_loss | 0.000173 | +------------------------------------------ +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.265 | +| time/ | | +| fps | 1376 | +| iterations | 4768 | +| time_elapsed | 7095 | +| total_timesteps | 9764864 | +| train/ | | +| approx_kl | 0.00017743048 | +| clip_fraction | 0.0416 | +| clip_range | 0.028 | +| entropy_loss | -7.89 | +| explained_variance | 0.0257 | +| learning_rate | 6.7e-06 | +| loss | -0.00792 | +| n_updates | 19068 | +| policy_gradient_loss | -0.00444 | +| value_loss | 0.000389 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.265 | +| time/ | | +| fps | 1376 | +| iterations | 4769 | +| time_elapsed | 7097 | +| total_timesteps | 9766912 | +| train/ | | +| approx_kl | 0.00019476554 | +| clip_fraction | 0.0436 | +| clip_range | 0.0279 | +| entropy_loss | -7.87 | +| explained_variance | 0.00292 | +| learning_rate | 6.66e-06 | +| loss | -0.00705 | +| n_updates | 19072 | +| policy_gradient_loss | -0.00424 | +| value_loss | 0.00012 | +------------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.273 | +| time/ | | +| fps | 1376 | +| iterations | 4770 | +| time_elapsed | 7098 | +| total_timesteps | 9768960 | +| train/ | | +| approx_kl | 0.0001946252 | +| clip_fraction | 0.0453 | +| clip_range | 0.0279 | +| entropy_loss | -7.99 | +| explained_variance | -0.0309 | +| learning_rate | 6.62e-06 | +| loss | -0.00792 | +| n_updates | 19076 | +| policy_gradient_loss | -0.00463 | +| value_loss | 0.000135 | +------------------------------------------ +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.273 | +| time/ | | +| fps | 1376 | +| iterations | 4771 | +| time_elapsed | 7100 | +| total_timesteps | 9771008 | +| train/ | | +| approx_kl | 0.00017941314 | +| clip_fraction | 0.0391 | +| clip_range | 0.0279 | +| entropy_loss | -7.82 | +| explained_variance | -0.0327 | +| learning_rate | 6.57e-06 | +| loss | -0.00516 | +| n_updates | 19080 | +| policy_gradient_loss | -0.00397 | +| value_loss | 0.000188 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.278 | +| time/ | | +| fps | 1376 | +| iterations | 4772 | +| time_elapsed | 7101 | +| total_timesteps | 9773056 | +| train/ | | +| approx_kl | 0.00020521788 | +| clip_fraction | 0.048 | +| clip_range | 0.0279 | +| entropy_loss | -7.84 | +| explained_variance | 0.0631 | +| learning_rate | 6.53e-06 | +| loss | -0.00948 | +| n_updates | 19084 | +| policy_gradient_loss | -0.00475 | +| value_loss | 0.000127 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 1376 | +| iterations | 4773 | +| time_elapsed | 7103 | +| total_timesteps | 9775104 | +| train/ | | +| approx_kl | 0.00016991203 | +| clip_fraction | 0.0444 | +| clip_range | 0.0278 | +| entropy_loss | -7.98 | +| explained_variance | 0.0256 | +| learning_rate | 6.49e-06 | +| loss | -0.00633 | +| n_updates | 19088 | +| policy_gradient_loss | -0.00414 | +| value_loss | 0.000174 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.27 | +| time/ | | +| fps | 1376 | +| iterations | 4774 | +| time_elapsed | 7105 | +| total_timesteps | 9777152 | +| train/ | | +| approx_kl | 0.00019213773 | +| clip_fraction | 0.0464 | +| clip_range | 0.0278 | +| entropy_loss | -7.86 | +| explained_variance | -0.0203 | +| learning_rate | 6.45e-06 | +| loss | -0.00991 | +| n_updates | 19092 | +| policy_gradient_loss | -0.00473 | +| value_loss | 0.000142 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.277 | +| time/ | | +| fps | 1376 | +| iterations | 4775 | +| time_elapsed | 7106 | +| total_timesteps | 9779200 | +| train/ | | +| approx_kl | 0.00016796237 | +| clip_fraction | 0.0417 | +| clip_range | 0.0278 | +| entropy_loss | -7.88 | +| explained_variance | 0.00167 | +| learning_rate | 6.41e-06 | +| loss | -0.00711 | +| n_updates | 19096 | +| policy_gradient_loss | -0.00416 | +| value_loss | 0.000138 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.277 | +| time/ | | +| fps | 1376 | +| iterations | 4776 | +| time_elapsed | 7108 | +| total_timesteps | 9781248 | +| train/ | | +| approx_kl | 0.00017760445 | +| clip_fraction | 0.0446 | +| clip_range | 0.0278 | +| entropy_loss | -7.83 | +| explained_variance | 0.0255 | +| learning_rate | 6.37e-06 | +| loss | -0.00833 | +| n_updates | 19100 | +| policy_gradient_loss | -0.00447 | +| value_loss | 0.000203 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.28 | +| time/ | | +| fps | 1376 | +| iterations | 4777 | +| time_elapsed | 7109 | +| total_timesteps | 9783296 | +| train/ | | +| approx_kl | 0.00018581154 | +| clip_fraction | 0.0453 | +| clip_range | 0.0277 | +| entropy_loss | -7.93 | +| explained_variance | -0.00535 | +| learning_rate | 6.33e-06 | +| loss | -0.00936 | +| n_updates | 19104 | +| policy_gradient_loss | -0.00469 | +| value_loss | 0.000172 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 1375 | +| iterations | 4778 | +| time_elapsed | 7111 | +| total_timesteps | 9785344 | +| train/ | | +| approx_kl | 0.00016993217 | +| clip_fraction | 0.0404 | +| clip_range | 0.0277 | +| entropy_loss | -7.88 | +| explained_variance | -0.0273 | +| learning_rate | 6.29e-06 | +| loss | -0.00737 | +| n_updates | 19108 | +| policy_gradient_loss | -0.00399 | +| value_loss | 0.000166 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.288 | +| time/ | | +| fps | 1375 | +| iterations | 4779 | +| time_elapsed | 7113 | +| total_timesteps | 9787392 | +| train/ | | +| approx_kl | 0.00016239364 | +| clip_fraction | 0.0421 | +| clip_range | 0.0277 | +| entropy_loss | -7.92 | +| explained_variance | 0.0272 | +| learning_rate | 6.25e-06 | +| loss | -0.00758 | +| n_updates | 19112 | +| policy_gradient_loss | -0.00401 | +| value_loss | 0.000156 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.28 | +| time/ | | +| fps | 1375 | +| iterations | 4780 | +| time_elapsed | 7114 | +| total_timesteps | 9789440 | +| train/ | | +| approx_kl | 0.00020060546 | +| clip_fraction | 0.0482 | +| clip_range | 0.0277 | +| entropy_loss | -7.8 | +| explained_variance | 0.0296 | +| learning_rate | 6.21e-06 | +| loss | -0.00788 | +| n_updates | 19116 | +| policy_gradient_loss | -0.00445 | +| value_loss | 0.000172 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.276 | +| time/ | | +| fps | 1375 | +| iterations | 4781 | +| time_elapsed | 7116 | +| total_timesteps | 9791488 | +| train/ | | +| approx_kl | 0.00018328353 | +| clip_fraction | 0.0446 | +| clip_range | 0.0276 | +| entropy_loss | -7.72 | +| explained_variance | 0.0838 | +| learning_rate | 6.17e-06 | +| loss | -0.00815 | +| n_updates | 19120 | +| policy_gradient_loss | -0.00473 | +| value_loss | 0.000128 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.276 | +| time/ | | +| fps | 1375 | +| iterations | 4782 | +| time_elapsed | 7117 | +| total_timesteps | 9793536 | +| train/ | | +| approx_kl | 0.00016658338 | +| clip_fraction | 0.0397 | +| clip_range | 0.0276 | +| entropy_loss | -7.73 | +| explained_variance | -0.0499 | +| learning_rate | 6.13e-06 | +| loss | -0.00879 | +| n_updates | 19124 | +| policy_gradient_loss | -0.00441 | +| value_loss | 0.00012 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.28 | +| time/ | | +| fps | 1375 | +| iterations | 4783 | +| time_elapsed | 7119 | +| total_timesteps | 9795584 | +| train/ | | +| approx_kl | 0.00015587592 | +| clip_fraction | 0.0333 | +| clip_range | 0.0276 | +| entropy_loss | -7.81 | +| explained_variance | 0.0518 | +| learning_rate | 6.09e-06 | +| loss | -0.00637 | +| n_updates | 19128 | +| policy_gradient_loss | -0.00401 | +| value_loss | 0.000148 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.276 | +| time/ | | +| fps | 1375 | +| iterations | 4784 | +| time_elapsed | 7121 | +| total_timesteps | 9797632 | +| train/ | | +| approx_kl | 0.00013484563 | +| clip_fraction | 0.0302 | +| clip_range | 0.0276 | +| entropy_loss | -7.85 | +| explained_variance | -0.0204 | +| learning_rate | 6.05e-06 | +| loss | -0.00643 | +| n_updates | 19132 | +| policy_gradient_loss | -0.00403 | +| value_loss | 0.00019 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.276 | +| time/ | | +| fps | 1375 | +| iterations | 4785 | +| time_elapsed | 7122 | +| total_timesteps | 9799680 | +| train/ | | +| approx_kl | 0.00016733518 | +| clip_fraction | 0.0397 | +| clip_range | 0.0275 | +| entropy_loss | -7.72 | +| explained_variance | 0.052 | +| learning_rate | 6.01e-06 | +| loss | -0.00744 | +| n_updates | 19136 | +| policy_gradient_loss | -0.00422 | +| value_loss | 0.000192 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.276 | +| time/ | | +| fps | 1375 | +| iterations | 4786 | +| time_elapsed | 7124 | +| total_timesteps | 9801728 | +| train/ | | +| approx_kl | 0.00015800272 | +| clip_fraction | 0.0387 | +| clip_range | 0.0275 | +| entropy_loss | -7.91 | +| explained_variance | 0.0599 | +| learning_rate | 5.97e-06 | +| loss | -0.00809 | +| n_updates | 19140 | +| policy_gradient_loss | -0.00435 | +| value_loss | 0.000228 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.276 | +| time/ | | +| fps | 1375 | +| iterations | 4787 | +| time_elapsed | 7125 | +| total_timesteps | 9803776 | +| train/ | | +| approx_kl | 0.00015450123 | +| clip_fraction | 0.0366 | +| clip_range | 0.0275 | +| entropy_loss | -7.97 | +| explained_variance | -0.00216 | +| learning_rate | 5.93e-06 | +| loss | -0.00891 | +| n_updates | 19144 | +| policy_gradient_loss | -0.00438 | +| value_loss | 0.000206 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.274 | +| time/ | | +| fps | 1375 | +| iterations | 4788 | +| time_elapsed | 7127 | +| total_timesteps | 9805824 | +| train/ | | +| approx_kl | 0.00014147494 | +| clip_fraction | 0.0281 | +| clip_range | 0.0275 | +| entropy_loss | -7.9 | +| explained_variance | -0.0368 | +| learning_rate | 5.89e-06 | +| loss | -0.00632 | +| n_updates | 19148 | +| policy_gradient_loss | -0.00374 | +| value_loss | 9.78e-05 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 1375 | +| iterations | 4789 | +| time_elapsed | 7129 | +| total_timesteps | 9807872 | +| train/ | | +| approx_kl | 0.00013470365 | +| clip_fraction | 0.0311 | +| clip_range | 0.0274 | +| entropy_loss | -7.87 | +| explained_variance | -0.00981 | +| learning_rate | 5.84e-06 | +| loss | -0.00599 | +| n_updates | 19152 | +| policy_gradient_loss | -0.00347 | +| value_loss | 0.000138 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 1375 | +| iterations | 4790 | +| time_elapsed | 7130 | +| total_timesteps | 9809920 | +| train/ | | +| approx_kl | 0.00014350066 | +| clip_fraction | 0.0349 | +| clip_range | 0.0274 | +| entropy_loss | -7.75 | +| explained_variance | -0.00107 | +| learning_rate | 5.8e-06 | +| loss | -0.00776 | +| n_updates | 19156 | +| policy_gradient_loss | -0.00415 | +| value_loss | 0.000319 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.281 | +| time/ | | +| fps | 1375 | +| iterations | 4791 | +| time_elapsed | 7132 | +| total_timesteps | 9811968 | +| train/ | | +| approx_kl | 0.00016640834 | +| clip_fraction | 0.0385 | +| clip_range | 0.0274 | +| entropy_loss | -7.9 | +| explained_variance | 0.036 | +| learning_rate | 5.76e-06 | +| loss | -0.00891 | +| n_updates | 19160 | +| policy_gradient_loss | -0.00405 | +| value_loss | 0.000151 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.281 | +| time/ | | +| fps | 1375 | +| iterations | 4792 | +| time_elapsed | 7133 | +| total_timesteps | 9814016 | +| train/ | | +| approx_kl | 0.00015775845 | +| clip_fraction | 0.0396 | +| clip_range | 0.0274 | +| entropy_loss | -7.78 | +| explained_variance | 0.203 | +| learning_rate | 5.72e-06 | +| loss | -0.00851 | +| n_updates | 19164 | +| policy_gradient_loss | -0.00441 | +| value_loss | 0.000115 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.281 | +| time/ | | +| fps | 1375 | +| iterations | 4793 | +| time_elapsed | 7135 | +| total_timesteps | 9816064 | +| train/ | | +| approx_kl | 0.00014793745 | +| clip_fraction | 0.0328 | +| clip_range | 0.0273 | +| entropy_loss | -7.89 | +| explained_variance | 0.002 | +| learning_rate | 5.68e-06 | +| loss | -0.0071 | +| n_updates | 19168 | +| policy_gradient_loss | -0.004 | +| value_loss | 0.000129 | +------------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 1375 | +| iterations | 4794 | +| time_elapsed | 7137 | +| total_timesteps | 9818112 | +| train/ | | +| approx_kl | 0.0001538182 | +| clip_fraction | 0.0356 | +| clip_range | 0.0273 | +| entropy_loss | -7.96 | +| explained_variance | -0.0535 | +| learning_rate | 5.64e-06 | +| loss | -0.00703 | +| n_updates | 19172 | +| policy_gradient_loss | -0.00431 | +| value_loss | 8.12e-05 | +------------------------------------------ +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 1375 | +| iterations | 4795 | +| time_elapsed | 7138 | +| total_timesteps | 9820160 | +| train/ | | +| approx_kl | 0.00013147033 | +| clip_fraction | 0.0291 | +| clip_range | 0.0273 | +| entropy_loss | -7.92 | +| explained_variance | 0.0172 | +| learning_rate | 5.6e-06 | +| loss | -0.00699 | +| n_updates | 19176 | +| policy_gradient_loss | -0.00388 | +| value_loss | 0.000138 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.276 | +| time/ | | +| fps | 1375 | +| iterations | 4796 | +| time_elapsed | 7140 | +| total_timesteps | 9822208 | +| train/ | | +| approx_kl | 0.00014365498 | +| clip_fraction | 0.0333 | +| clip_range | 0.0272 | +| entropy_loss | -7.91 | +| explained_variance | -0.055 | +| learning_rate | 5.56e-06 | +| loss | -0.00697 | +| n_updates | 19180 | +| policy_gradient_loss | -0.00412 | +| value_loss | 0.000111 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.277 | +| time/ | | +| fps | 1375 | +| iterations | 4797 | +| time_elapsed | 7141 | +| total_timesteps | 9824256 | +| train/ | | +| approx_kl | 0.00012109583 | +| clip_fraction | 0.0286 | +| clip_range | 0.0272 | +| entropy_loss | -7.93 | +| explained_variance | 0.00633 | +| learning_rate | 5.52e-06 | +| loss | -0.00621 | +| n_updates | 19184 | +| policy_gradient_loss | -0.00389 | +| value_loss | 0.000129 | +------------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.278 | +| time/ | | +| fps | 1375 | +| iterations | 4798 | +| time_elapsed | 7143 | +| total_timesteps | 9826304 | +| train/ | | +| approx_kl | 0.0001235385 | +| clip_fraction | 0.0304 | +| clip_range | 0.0272 | +| entropy_loss | -7.7 | +| explained_variance | 0.265 | +| learning_rate | 5.48e-06 | +| loss | -0.00685 | +| n_updates | 19188 | +| policy_gradient_loss | -0.0038 | +| value_loss | 7.44e-05 | +------------------------------------------ +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 1375 | +| iterations | 4799 | +| time_elapsed | 7144 | +| total_timesteps | 9828352 | +| train/ | | +| approx_kl | 0.00013017424 | +| clip_fraction | 0.0306 | +| clip_range | 0.0272 | +| entropy_loss | -7.83 | +| explained_variance | 0.00607 | +| learning_rate | 5.44e-06 | +| loss | -0.00724 | +| n_updates | 19192 | +| policy_gradient_loss | -0.00382 | +| value_loss | 0.000194 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 1375 | +| iterations | 4800 | +| time_elapsed | 7146 | +| total_timesteps | 9830400 | +| train/ | | +| approx_kl | 0.00015618972 | +| clip_fraction | 0.0339 | +| clip_range | 0.0271 | +| entropy_loss | -7.83 | +| explained_variance | 0.0723 | +| learning_rate | 5.4e-06 | +| loss | -0.00811 | +| n_updates | 19196 | +| policy_gradient_loss | -0.00402 | +| value_loss | 0.000212 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.278 | +| time/ | | +| fps | 1375 | +| iterations | 4801 | +| time_elapsed | 7147 | +| total_timesteps | 9832448 | +| train/ | | +| approx_kl | 0.00012884586 | +| clip_fraction | 0.0291 | +| clip_range | 0.0271 | +| entropy_loss | -7.81 | +| explained_variance | 0.112 | +| learning_rate | 5.36e-06 | +| loss | -0.00701 | +| n_updates | 19200 | +| policy_gradient_loss | -0.00394 | +| value_loss | 0.000134 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.278 | +| time/ | | +| fps | 1375 | +| iterations | 4802 | +| time_elapsed | 7149 | +| total_timesteps | 9834496 | +| train/ | | +| approx_kl | 0.00012949947 | +| clip_fraction | 0.0294 | +| clip_range | 0.0271 | +| entropy_loss | -7.83 | +| explained_variance | -0.0238 | +| learning_rate | 5.32e-06 | +| loss | -0.00678 | +| n_updates | 19204 | +| policy_gradient_loss | -0.00394 | +| value_loss | 0.000242 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.277 | +| time/ | | +| fps | 1375 | +| iterations | 4803 | +| time_elapsed | 7151 | +| total_timesteps | 9836544 | +| train/ | | +| approx_kl | 0.00013654996 | +| clip_fraction | 0.0325 | +| clip_range | 0.0271 | +| entropy_loss | -7.78 | +| explained_variance | 0.0614 | +| learning_rate | 5.28e-06 | +| loss | -0.00708 | +| n_updates | 19208 | +| policy_gradient_loss | -0.00388 | +| value_loss | 7.12e-05 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 1375 | +| iterations | 4804 | +| time_elapsed | 7152 | +| total_timesteps | 9838592 | +| train/ | | +| approx_kl | 0.00013982857 | +| clip_fraction | 0.0319 | +| clip_range | 0.027 | +| entropy_loss | -7.79 | +| explained_variance | 0.121 | +| learning_rate | 5.24e-06 | +| loss | -0.00827 | +| n_updates | 19212 | +| policy_gradient_loss | -0.00422 | +| value_loss | 0.000151 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 1375 | +| iterations | 4805 | +| time_elapsed | 7154 | +| total_timesteps | 9840640 | +| train/ | | +| approx_kl | 0.00012700076 | +| clip_fraction | 0.0299 | +| clip_range | 0.027 | +| entropy_loss | -7.81 | +| explained_variance | -0.0154 | +| learning_rate | 5.2e-06 | +| loss | -0.00694 | +| n_updates | 19216 | +| policy_gradient_loss | -0.00364 | +| value_loss | 0.000157 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 1375 | +| iterations | 4806 | +| time_elapsed | 7155 | +| total_timesteps | 9842688 | +| train/ | | +| approx_kl | 0.00015059859 | +| clip_fraction | 0.0406 | +| clip_range | 0.027 | +| entropy_loss | -7.88 | +| explained_variance | -0.161 | +| learning_rate | 5.16e-06 | +| loss | -0.00884 | +| n_updates | 19220 | +| policy_gradient_loss | -0.00484 | +| value_loss | 4.85e-05 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 1375 | +| iterations | 4807 | +| time_elapsed | 7157 | +| total_timesteps | 9844736 | +| train/ | | +| approx_kl | 0.00014987573 | +| clip_fraction | 0.0383 | +| clip_range | 0.027 | +| entropy_loss | -7.82 | +| explained_variance | -0.0482 | +| learning_rate | 5.11e-06 | +| loss | -0.00578 | +| n_updates | 19224 | +| policy_gradient_loss | -0.00397 | +| value_loss | 0.000106 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 1375 | +| iterations | 4808 | +| time_elapsed | 7158 | +| total_timesteps | 9846784 | +| train/ | | +| approx_kl | 0.00014121688 | +| clip_fraction | 0.0367 | +| clip_range | 0.0269 | +| entropy_loss | -7.77 | +| explained_variance | 0.00121 | +| learning_rate | 5.07e-06 | +| loss | -0.00713 | +| n_updates | 19228 | +| policy_gradient_loss | -0.00388 | +| value_loss | 0.000326 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.287 | +| time/ | | +| fps | 1375 | +| iterations | 4809 | +| time_elapsed | 7160 | +| total_timesteps | 9848832 | +| train/ | | +| approx_kl | 0.00010737163 | +| clip_fraction | 0.0243 | +| clip_range | 0.0269 | +| entropy_loss | -7.68 | +| explained_variance | 0.059 | +| learning_rate | 5.03e-06 | +| loss | -0.00635 | +| n_updates | 19232 | +| policy_gradient_loss | -0.00317 | +| value_loss | 0.000268 | +------------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.286 | +| time/ | | +| fps | 1375 | +| iterations | 4810 | +| time_elapsed | 7162 | +| total_timesteps | 9850880 | +| train/ | | +| approx_kl | 9.316078e-05 | +| clip_fraction | 0.0214 | +| clip_range | 0.0269 | +| entropy_loss | -7.76 | +| explained_variance | 0.0631 | +| learning_rate | 4.99e-06 | +| loss | -0.00638 | +| n_updates | 19236 | +| policy_gradient_loss | -0.00333 | +| value_loss | 0.000184 | +------------------------------------------ +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.286 | +| time/ | | +| fps | 1375 | +| iterations | 4811 | +| time_elapsed | 7163 | +| total_timesteps | 9852928 | +| train/ | | +| approx_kl | 0.00011227105 | +| clip_fraction | 0.026 | +| clip_range | 0.0269 | +| entropy_loss | -7.91 | +| explained_variance | -0.0238 | +| learning_rate | 4.95e-06 | +| loss | -0.00753 | +| n_updates | 19240 | +| policy_gradient_loss | -0.00372 | +| value_loss | 0.000146 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 1375 | +| iterations | 4812 | +| time_elapsed | 7165 | +| total_timesteps | 9854976 | +| train/ | | +| approx_kl | 0.00011394327 | +| clip_fraction | 0.0254 | +| clip_range | 0.0268 | +| entropy_loss | -7.83 | +| explained_variance | 0.0186 | +| learning_rate | 4.91e-06 | +| loss | -0.00691 | +| n_updates | 19244 | +| policy_gradient_loss | -0.00374 | +| value_loss | 0.000184 | +------------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 1375 | +| iterations | 4813 | +| time_elapsed | 7166 | +| total_timesteps | 9857024 | +| train/ | | +| approx_kl | 0.0001229785 | +| clip_fraction | 0.0264 | +| clip_range | 0.0268 | +| entropy_loss | -7.95 | +| explained_variance | -0.00488 | +| learning_rate | 4.87e-06 | +| loss | -0.00783 | +| n_updates | 19248 | +| policy_gradient_loss | -0.00356 | +| value_loss | 0.000169 | +------------------------------------------ +-------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.286 | +| time/ | | +| fps | 1375 | +| iterations | 4814 | +| time_elapsed | 7168 | +| total_timesteps | 9859072 | +| train/ | | +| approx_kl | 0.000109432236 | +| clip_fraction | 0.0266 | +| clip_range | 0.0268 | +| entropy_loss | -7.61 | +| explained_variance | 0.118 | +| learning_rate | 4.83e-06 | +| loss | -0.00589 | +| n_updates | 19252 | +| policy_gradient_loss | -0.00341 | +| value_loss | 0.000388 | +-------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.286 | +| time/ | | +| fps | 1375 | +| iterations | 4815 | +| time_elapsed | 7169 | +| total_timesteps | 9861120 | +| train/ | | +| approx_kl | 0.00011228552 | +| clip_fraction | 0.025 | +| clip_range | 0.0268 | +| entropy_loss | -7.85 | +| explained_variance | -0.0643 | +| learning_rate | 4.79e-06 | +| loss | -0.00593 | +| n_updates | 19256 | +| policy_gradient_loss | -0.00351 | +| value_loss | 0.000125 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.284 | +| time/ | | +| fps | 1375 | +| iterations | 4816 | +| time_elapsed | 7171 | +| total_timesteps | 9863168 | +| train/ | | +| approx_kl | 0.00012012565 | +| clip_fraction | 0.0273 | +| clip_range | 0.0267 | +| entropy_loss | -7.98 | +| explained_variance | -0.00365 | +| learning_rate | 4.75e-06 | +| loss | -0.00569 | +| n_updates | 19260 | +| policy_gradient_loss | -0.00334 | +| value_loss | 0.000136 | +------------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.288 | +| time/ | | +| fps | 1375 | +| iterations | 4817 | +| time_elapsed | 7172 | +| total_timesteps | 9865216 | +| train/ | | +| approx_kl | 9.940367e-05 | +| clip_fraction | 0.0239 | +| clip_range | 0.0267 | +| entropy_loss | -7.84 | +| explained_variance | -0.0656 | +| learning_rate | 4.71e-06 | +| loss | -0.00679 | +| n_updates | 19264 | +| policy_gradient_loss | -0.00361 | +| value_loss | 0.000164 | +------------------------------------------ +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.288 | +| time/ | | +| fps | 1375 | +| iterations | 4818 | +| time_elapsed | 7174 | +| total_timesteps | 9867264 | +| train/ | | +| approx_kl | 0.00012501804 | +| clip_fraction | 0.0299 | +| clip_range | 0.0267 | +| entropy_loss | -7.84 | +| explained_variance | 0.00357 | +| learning_rate | 4.67e-06 | +| loss | -0.00632 | +| n_updates | 19268 | +| policy_gradient_loss | -0.00382 | +| value_loss | 0.00024 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.288 | +| time/ | | +| fps | 1375 | +| iterations | 4819 | +| time_elapsed | 7176 | +| total_timesteps | 9869312 | +| train/ | | +| approx_kl | 9.5044845e-05 | +| clip_fraction | 0.0198 | +| clip_range | 0.0267 | +| entropy_loss | -7.94 | +| explained_variance | -0.00528 | +| learning_rate | 4.63e-06 | +| loss | -0.00525 | +| n_updates | 19272 | +| policy_gradient_loss | -0.00339 | +| value_loss | 0.000143 | +------------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.287 | +| time/ | | +| fps | 1375 | +| iterations | 4820 | +| time_elapsed | 7177 | +| total_timesteps | 9871360 | +| train/ | | +| approx_kl | 0.0001059488 | +| clip_fraction | 0.0239 | +| clip_range | 0.0266 | +| entropy_loss | -7.97 | +| explained_variance | 0.0222 | +| learning_rate | 4.59e-06 | +| loss | -0.00796 | +| n_updates | 19276 | +| policy_gradient_loss | -0.00349 | +| value_loss | 0.000134 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.29 | +| time/ | | +| fps | 1375 | +| iterations | 4821 | +| time_elapsed | 7179 | +| total_timesteps | 9873408 | +| train/ | | +| approx_kl | 9.660903e-05 | +| clip_fraction | 0.0204 | +| clip_range | 0.0266 | +| entropy_loss | -7.76 | +| explained_variance | 0.116 | +| learning_rate | 4.55e-06 | +| loss | -0.00645 | +| n_updates | 19280 | +| policy_gradient_loss | -0.00343 | +| value_loss | 9.55e-05 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.288 | +| time/ | | +| fps | 1375 | +| iterations | 4822 | +| time_elapsed | 7180 | +| total_timesteps | 9875456 | +| train/ | | +| approx_kl | 9.900842e-05 | +| clip_fraction | 0.0238 | +| clip_range | 0.0266 | +| entropy_loss | -7.78 | +| explained_variance | 0.11 | +| learning_rate | 4.51e-06 | +| loss | -0.00657 | +| n_updates | 19284 | +| policy_gradient_loss | -0.00362 | +| value_loss | 0.000118 | +------------------------------------------ +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.295 | +| time/ | | +| fps | 1375 | +| iterations | 4823 | +| time_elapsed | 7182 | +| total_timesteps | 9877504 | +| train/ | | +| approx_kl | 8.9044974e-05 | +| clip_fraction | 0.0201 | +| clip_range | 0.0266 | +| entropy_loss | -7.85 | +| explained_variance | 0.00706 | +| learning_rate | 4.47e-06 | +| loss | -0.00533 | +| n_updates | 19288 | +| policy_gradient_loss | -0.00333 | +| value_loss | 0.000158 | +------------------------------------------- +-------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.293 | +| time/ | | +| fps | 1375 | +| iterations | 4824 | +| time_elapsed | 7183 | +| total_timesteps | 9879552 | +| train/ | | +| approx_kl | 0.000101139754 | +| clip_fraction | 0.0234 | +| clip_range | 0.0265 | +| entropy_loss | -7.81 | +| explained_variance | 0.0648 | +| learning_rate | 4.43e-06 | +| loss | -0.00558 | +| n_updates | 19292 | +| policy_gradient_loss | -0.00345 | +| value_loss | 0.000215 | +-------------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.287 | +| time/ | | +| fps | 1375 | +| iterations | 4825 | +| time_elapsed | 7185 | +| total_timesteps | 9881600 | +| train/ | | +| approx_kl | 8.992443e-05 | +| clip_fraction | 0.0209 | +| clip_range | 0.0265 | +| entropy_loss | -7.82 | +| explained_variance | 0.0961 | +| learning_rate | 4.38e-06 | +| loss | -0.00747 | +| n_updates | 19296 | +| policy_gradient_loss | -0.00355 | +| value_loss | 0.000156 | +------------------------------------------ +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.287 | +| time/ | | +| fps | 1375 | +| iterations | 4826 | +| time_elapsed | 7187 | +| total_timesteps | 9883648 | +| train/ | | +| approx_kl | 0.00011184924 | +| clip_fraction | 0.0281 | +| clip_range | 0.0265 | +| entropy_loss | -7.79 | +| explained_variance | -0.0345 | +| learning_rate | 4.34e-06 | +| loss | -0.0062 | +| n_updates | 19300 | +| policy_gradient_loss | -0.00377 | +| value_loss | 0.000109 | +------------------------------------------- +-------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.286 | +| time/ | | +| fps | 1375 | +| iterations | 4827 | +| time_elapsed | 7188 | +| total_timesteps | 9885696 | +| train/ | | +| approx_kl | 0.000112337264 | +| clip_fraction | 0.0281 | +| clip_range | 0.0265 | +| entropy_loss | -7.92 | +| explained_variance | -0.0209 | +| learning_rate | 4.3e-06 | +| loss | -0.00759 | +| n_updates | 19304 | +| policy_gradient_loss | -0.00406 | +| value_loss | 8.73e-05 | +-------------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.291 | +| time/ | | +| fps | 1375 | +| iterations | 4828 | +| time_elapsed | 7190 | +| total_timesteps | 9887744 | +| train/ | | +| approx_kl | 8.52918e-05 | +| clip_fraction | 0.0203 | +| clip_range | 0.0264 | +| entropy_loss | -7.89 | +| explained_variance | -0.0086 | +| learning_rate | 4.26e-06 | +| loss | -0.00514 | +| n_updates | 19308 | +| policy_gradient_loss | -0.00328 | +| value_loss | 9.37e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.295 | +| time/ | | +| fps | 1375 | +| iterations | 4829 | +| time_elapsed | 7191 | +| total_timesteps | 9889792 | +| train/ | | +| approx_kl | 8.680763e-05 | +| clip_fraction | 0.0203 | +| clip_range | 0.0264 | +| entropy_loss | -7.79 | +| explained_variance | 0.0745 | +| learning_rate | 4.22e-06 | +| loss | -0.00777 | +| n_updates | 19312 | +| policy_gradient_loss | -0.00342 | +| value_loss | 0.000231 | +------------------------------------------ +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.295 | +| time/ | | +| fps | 1375 | +| iterations | 4830 | +| time_elapsed | 7193 | +| total_timesteps | 9891840 | +| train/ | | +| approx_kl | 9.6593896e-05 | +| clip_fraction | 0.0259 | +| clip_range | 0.0264 | +| entropy_loss | -7.8 | +| explained_variance | 0.0287 | +| learning_rate | 4.18e-06 | +| loss | -0.00578 | +| n_updates | 19316 | +| policy_gradient_loss | -0.00349 | +| value_loss | 0.000107 | +------------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.295 | +| time/ | | +| fps | 1375 | +| iterations | 4831 | +| time_elapsed | 7194 | +| total_timesteps | 9893888 | +| train/ | | +| approx_kl | 8.551558e-05 | +| clip_fraction | 0.0199 | +| clip_range | 0.0264 | +| entropy_loss | -7.93 | +| explained_variance | 0.0336 | +| learning_rate | 4.14e-06 | +| loss | -0.00737 | +| n_updates | 19320 | +| policy_gradient_loss | -0.00352 | +| value_loss | 0.000126 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.292 | +| time/ | | +| fps | 1375 | +| iterations | 4832 | +| time_elapsed | 7196 | +| total_timesteps | 9895936 | +| train/ | | +| approx_kl | 9.228379e-05 | +| clip_fraction | 0.0217 | +| clip_range | 0.0263 | +| entropy_loss | -7.95 | +| explained_variance | 0.0166 | +| learning_rate | 4.1e-06 | +| loss | -0.00674 | +| n_updates | 19324 | +| policy_gradient_loss | -0.00336 | +| value_loss | 0.000125 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.289 | +| time/ | | +| fps | 1375 | +| iterations | 4833 | +| time_elapsed | 7197 | +| total_timesteps | 9897984 | +| train/ | | +| approx_kl | 9.933853e-05 | +| clip_fraction | 0.0225 | +| clip_range | 0.0263 | +| entropy_loss | -7.8 | +| explained_variance | 0.176 | +| learning_rate | 4.06e-06 | +| loss | -0.00658 | +| n_updates | 19328 | +| policy_gradient_loss | -0.0034 | +| value_loss | 0.000153 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 1375 | +| iterations | 4834 | +| time_elapsed | 7199 | +| total_timesteps | 9900032 | +| train/ | | +| approx_kl | 7.597734e-05 | +| clip_fraction | 0.0154 | +| clip_range | 0.0263 | +| entropy_loss | -7.81 | +| explained_variance | 0.0807 | +| learning_rate | 4.02e-06 | +| loss | -0.00524 | +| n_updates | 19332 | +| policy_gradient_loss | -0.00281 | +| value_loss | 0.000123 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.293 | +| time/ | | +| fps | 1375 | +| iterations | 4835 | +| time_elapsed | 7201 | +| total_timesteps | 9902080 | +| train/ | | +| approx_kl | 7.093967e-05 | +| clip_fraction | 0.0175 | +| clip_range | 0.0262 | +| entropy_loss | -7.87 | +| explained_variance | 0.0906 | +| learning_rate | 3.98e-06 | +| loss | -0.0054 | +| n_updates | 19336 | +| policy_gradient_loss | -0.00293 | +| value_loss | 0.000218 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.289 | +| time/ | | +| fps | 1375 | +| iterations | 4836 | +| time_elapsed | 7202 | +| total_timesteps | 9904128 | +| train/ | | +| approx_kl | 7.821302e-05 | +| clip_fraction | 0.0177 | +| clip_range | 0.0262 | +| entropy_loss | -7.8 | +| explained_variance | -0.016 | +| learning_rate | 3.94e-06 | +| loss | -0.00569 | +| n_updates | 19340 | +| policy_gradient_loss | -0.00315 | +| value_loss | 0.000286 | +------------------------------------------ +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.29 | +| time/ | | +| fps | 1375 | +| iterations | 4837 | +| time_elapsed | 7204 | +| total_timesteps | 9906176 | +| train/ | | +| approx_kl | 8.4955216e-05 | +| clip_fraction | 0.0198 | +| clip_range | 0.0262 | +| entropy_loss | -7.82 | +| explained_variance | 0.135 | +| learning_rate | 3.9e-06 | +| loss | -0.00776 | +| n_updates | 19344 | +| policy_gradient_loss | -0.00333 | +| value_loss | 0.000101 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.29 | +| time/ | | +| fps | 1375 | +| iterations | 4838 | +| time_elapsed | 7205 | +| total_timesteps | 9908224 | +| train/ | | +| approx_kl | 7.6082215e-05 | +| clip_fraction | 0.0186 | +| clip_range | 0.0262 | +| entropy_loss | -7.9 | +| explained_variance | -0.0111 | +| learning_rate | 3.86e-06 | +| loss | -0.00633 | +| n_updates | 19348 | +| policy_gradient_loss | -0.00318 | +| value_loss | 0.000184 | +------------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.286 | +| time/ | | +| fps | 1375 | +| iterations | 4839 | +| time_elapsed | 7207 | +| total_timesteps | 9910272 | +| train/ | | +| approx_kl | 8.673986e-05 | +| clip_fraction | 0.0205 | +| clip_range | 0.0261 | +| entropy_loss | -7.94 | +| explained_variance | 0.0143 | +| learning_rate | 3.82e-06 | +| loss | -0.0069 | +| n_updates | 19352 | +| policy_gradient_loss | -0.00333 | +| value_loss | 9.84e-05 | +------------------------------------------ +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.29 | +| time/ | | +| fps | 1374 | +| iterations | 4840 | +| time_elapsed | 7208 | +| total_timesteps | 9912320 | +| train/ | | +| approx_kl | 8.0011014e-05 | +| clip_fraction | 0.0195 | +| clip_range | 0.0261 | +| entropy_loss | -7.82 | +| explained_variance | 0.101 | +| learning_rate | 3.78e-06 | +| loss | -0.00534 | +| n_updates | 19356 | +| policy_gradient_loss | -0.00348 | +| value_loss | 0.000139 | +------------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.295 | +| time/ | | +| fps | 1374 | +| iterations | 4841 | +| time_elapsed | 7210 | +| total_timesteps | 9914368 | +| train/ | | +| approx_kl | 6.908062e-05 | +| clip_fraction | 0.0165 | +| clip_range | 0.0261 | +| entropy_loss | -7.78 | +| explained_variance | 0.0249 | +| learning_rate | 3.74e-06 | +| loss | -0.00635 | +| n_updates | 19360 | +| policy_gradient_loss | -0.00302 | +| value_loss | 0.00022 | +------------------------------------------ +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.3 | +| time/ | | +| fps | 1374 | +| iterations | 4842 | +| time_elapsed | 7212 | +| total_timesteps | 9916416 | +| train/ | | +| approx_kl | 6.6279346e-05 | +| clip_fraction | 0.0167 | +| clip_range | 0.0261 | +| entropy_loss | -7.73 | +| explained_variance | 0.102 | +| learning_rate | 3.7e-06 | +| loss | -0.00551 | +| n_updates | 19364 | +| policy_gradient_loss | -0.00294 | +| value_loss | 0.000277 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.3 | +| time/ | | +| fps | 1374 | +| iterations | 4843 | +| time_elapsed | 7213 | +| total_timesteps | 9918464 | +| train/ | | +| approx_kl | 6.9017784e-05 | +| clip_fraction | 0.0178 | +| clip_range | 0.026 | +| entropy_loss | -7.91 | +| explained_variance | -0.00685 | +| learning_rate | 3.65e-06 | +| loss | -0.0064 | +| n_updates | 19368 | +| policy_gradient_loss | -0.00325 | +| value_loss | 0.000206 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.298 | +| time/ | | +| fps | 1374 | +| iterations | 4844 | +| time_elapsed | 7215 | +| total_timesteps | 9920512 | +| train/ | | +| approx_kl | 9.1738446e-05 | +| clip_fraction | 0.0228 | +| clip_range | 0.026 | +| entropy_loss | -7.98 | +| explained_variance | -0.00981 | +| learning_rate | 3.61e-06 | +| loss | -0.00695 | +| n_updates | 19372 | +| policy_gradient_loss | -0.00343 | +| value_loss | 0.000139 | +------------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.298 | +| time/ | | +| fps | 1374 | +| iterations | 4845 | +| time_elapsed | 7216 | +| total_timesteps | 9922560 | +| train/ | | +| approx_kl | 8.320657e-05 | +| clip_fraction | 0.0187 | +| clip_range | 0.026 | +| entropy_loss | -7.92 | +| explained_variance | 0.0606 | +| learning_rate | 3.57e-06 | +| loss | -0.00562 | +| n_updates | 19376 | +| policy_gradient_loss | -0.00335 | +| value_loss | 0.000202 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.294 | +| time/ | | +| fps | 1374 | +| iterations | 4846 | +| time_elapsed | 7218 | +| total_timesteps | 9924608 | +| train/ | | +| approx_kl | 7.605099e-05 | +| clip_fraction | 0.016 | +| clip_range | 0.026 | +| entropy_loss | -7.92 | +| explained_variance | 0.0212 | +| learning_rate | 3.53e-06 | +| loss | -0.00624 | +| n_updates | 19380 | +| policy_gradient_loss | -0.00302 | +| value_loss | 0.000161 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.297 | +| time/ | | +| fps | 1374 | +| iterations | 4847 | +| time_elapsed | 7219 | +| total_timesteps | 9926656 | +| train/ | | +| approx_kl | 7.063459e-05 | +| clip_fraction | 0.0146 | +| clip_range | 0.0259 | +| entropy_loss | -7.69 | +| explained_variance | 0.181 | +| learning_rate | 3.49e-06 | +| loss | -0.00524 | +| n_updates | 19384 | +| policy_gradient_loss | -0.00288 | +| value_loss | 0.00018 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.294 | +| time/ | | +| fps | 1374 | +| iterations | 4848 | +| time_elapsed | 7221 | +| total_timesteps | 9928704 | +| train/ | | +| approx_kl | 8.899375e-05 | +| clip_fraction | 0.0204 | +| clip_range | 0.0259 | +| entropy_loss | -7.68 | +| explained_variance | 0.0596 | +| learning_rate | 3.45e-06 | +| loss | -0.00616 | +| n_updates | 19388 | +| policy_gradient_loss | -0.00345 | +| value_loss | 0.000187 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 1374 | +| iterations | 4849 | +| time_elapsed | 7222 | +| total_timesteps | 9930752 | +| train/ | | +| approx_kl | 6.301893e-05 | +| clip_fraction | 0.016 | +| clip_range | 0.0259 | +| entropy_loss | -7.85 | +| explained_variance | -0.04 | +| learning_rate | 3.41e-06 | +| loss | -0.00641 | +| n_updates | 19392 | +| policy_gradient_loss | -0.00311 | +| value_loss | 0.000129 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 1374 | +| iterations | 4850 | +| time_elapsed | 7224 | +| total_timesteps | 9932800 | +| train/ | | +| approx_kl | 6.961875e-05 | +| clip_fraction | 0.0181 | +| clip_range | 0.0259 | +| entropy_loss | -7.87 | +| explained_variance | -0.000273 | +| learning_rate | 3.37e-06 | +| loss | -0.00638 | +| n_updates | 19396 | +| policy_gradient_loss | -0.00327 | +| value_loss | 0.000115 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.297 | +| time/ | | +| fps | 1374 | +| iterations | 4851 | +| time_elapsed | 7225 | +| total_timesteps | 9934848 | +| train/ | | +| approx_kl | 7.239703e-05 | +| clip_fraction | 0.0179 | +| clip_range | 0.0258 | +| entropy_loss | -7.74 | +| explained_variance | 0.0114 | +| learning_rate | 3.33e-06 | +| loss | -0.00649 | +| n_updates | 19400 | +| policy_gradient_loss | -0.00326 | +| value_loss | 0.000197 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.297 | +| time/ | | +| fps | 1374 | +| iterations | 4852 | +| time_elapsed | 7227 | +| total_timesteps | 9936896 | +| train/ | | +| approx_kl | 7.426762e-05 | +| clip_fraction | 0.0166 | +| clip_range | 0.0258 | +| entropy_loss | -7.81 | +| explained_variance | 0.209 | +| learning_rate | 3.29e-06 | +| loss | -0.00502 | +| n_updates | 19404 | +| policy_gradient_loss | -0.00319 | +| value_loss | 0.000115 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.297 | +| time/ | | +| fps | 1374 | +| iterations | 4853 | +| time_elapsed | 7228 | +| total_timesteps | 9938944 | +| train/ | | +| approx_kl | 5.673297e-05 | +| clip_fraction | 0.0133 | +| clip_range | 0.0258 | +| entropy_loss | -7.73 | +| explained_variance | -0.0407 | +| learning_rate | 3.25e-06 | +| loss | -0.00542 | +| n_updates | 19408 | +| policy_gradient_loss | -0.00291 | +| value_loss | 0.000244 | +------------------------------------------ +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.295 | +| time/ | | +| fps | 1374 | +| iterations | 4854 | +| time_elapsed | 7230 | +| total_timesteps | 9940992 | +| train/ | | +| approx_kl | 6.4059685e-05 | +| clip_fraction | 0.0128 | +| clip_range | 0.0258 | +| entropy_loss | -7.96 | +| explained_variance | -0.0393 | +| learning_rate | 3.21e-06 | +| loss | -0.00588 | +| n_updates | 19412 | +| policy_gradient_loss | -0.00306 | +| value_loss | 8.12e-05 | +------------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.292 | +| time/ | | +| fps | 1374 | +| iterations | 4855 | +| time_elapsed | 7232 | +| total_timesteps | 9943040 | +| train/ | | +| approx_kl | 5.963433e-05 | +| clip_fraction | 0.0127 | +| clip_range | 0.0257 | +| entropy_loss | -7.84 | +| explained_variance | -0.00411 | +| learning_rate | 3.17e-06 | +| loss | -0.00551 | +| n_updates | 19416 | +| policy_gradient_loss | -0.00278 | +| value_loss | 0.00012 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.292 | +| time/ | | +| fps | 1374 | +| iterations | 4856 | +| time_elapsed | 7233 | +| total_timesteps | 9945088 | +| train/ | | +| approx_kl | 6.528874e-05 | +| clip_fraction | 0.0154 | +| clip_range | 0.0257 | +| entropy_loss | -7.91 | +| explained_variance | 0.0322 | +| learning_rate | 3.13e-06 | +| loss | -0.00614 | +| n_updates | 19420 | +| policy_gradient_loss | -0.00303 | +| value_loss | 8.87e-05 | +------------------------------------------ +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.292 | +| time/ | | +| fps | 1374 | +| iterations | 4857 | +| time_elapsed | 7235 | +| total_timesteps | 9947136 | +| train/ | | +| approx_kl | 5.6914374e-05 | +| clip_fraction | 0.0116 | +| clip_range | 0.0257 | +| entropy_loss | -7.89 | +| explained_variance | -0.0853 | +| learning_rate | 3.09e-06 | +| loss | -0.00582 | +| n_updates | 19424 | +| policy_gradient_loss | -0.00291 | +| value_loss | 4.7e-05 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.288 | +| time/ | | +| fps | 1374 | +| iterations | 4858 | +| time_elapsed | 7236 | +| total_timesteps | 9949184 | +| train/ | | +| approx_kl | 6.5908825e-05 | +| clip_fraction | 0.0135 | +| clip_range | 0.0257 | +| entropy_loss | -7.85 | +| explained_variance | -0.00783 | +| learning_rate | 3.05e-06 | +| loss | -0.00665 | +| n_updates | 19428 | +| policy_gradient_loss | -0.00305 | +| value_loss | 0.000214 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.281 | +| time/ | | +| fps | 1374 | +| iterations | 4859 | +| time_elapsed | 7238 | +| total_timesteps | 9951232 | +| train/ | | +| approx_kl | 5.3780954e-05 | +| clip_fraction | 0.0125 | +| clip_range | 0.0256 | +| entropy_loss | -7.67 | +| explained_variance | 0.0828 | +| learning_rate | 3.01e-06 | +| loss | -0.00446 | +| n_updates | 19432 | +| policy_gradient_loss | -0.00292 | +| value_loss | 0.000105 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.274 | +| time/ | | +| fps | 1374 | +| iterations | 4860 | +| time_elapsed | 7239 | +| total_timesteps | 9953280 | +| train/ | | +| approx_kl | 5.9469545e-05 | +| clip_fraction | 0.0122 | +| clip_range | 0.0256 | +| entropy_loss | -7.76 | +| explained_variance | 0.013 | +| learning_rate | 2.97e-06 | +| loss | -0.00522 | +| n_updates | 19436 | +| policy_gradient_loss | -0.00269 | +| value_loss | 8.82e-05 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.274 | +| time/ | | +| fps | 1374 | +| iterations | 4861 | +| time_elapsed | 7241 | +| total_timesteps | 9955328 | +| train/ | | +| approx_kl | 5.5122626e-05 | +| clip_fraction | 0.0126 | +| clip_range | 0.0256 | +| entropy_loss | -7.74 | +| explained_variance | 0.021 | +| learning_rate | 2.93e-06 | +| loss | -0.00714 | +| n_updates | 19440 | +| policy_gradient_loss | -0.0029 | +| value_loss | 0.000196 | +------------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.271 | +| time/ | | +| fps | 1374 | +| iterations | 4862 | +| time_elapsed | 7242 | +| total_timesteps | 9957376 | +| train/ | | +| approx_kl | 5.609839e-05 | +| clip_fraction | 0.0128 | +| clip_range | 0.0256 | +| entropy_loss | -7.8 | +| explained_variance | -0.00272 | +| learning_rate | 2.88e-06 | +| loss | -0.00535 | +| n_updates | 19444 | +| policy_gradient_loss | -0.00295 | +| value_loss | 0.000112 | +------------------------------------------ +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.271 | +| time/ | | +| fps | 1374 | +| iterations | 4863 | +| time_elapsed | 7244 | +| total_timesteps | 9959424 | +| train/ | | +| approx_kl | 4.4915025e-05 | +| clip_fraction | 0.00989 | +| clip_range | 0.0255 | +| entropy_loss | -7.84 | +| explained_variance | 0.0693 | +| learning_rate | 2.84e-06 | +| loss | -0.0056 | +| n_updates | 19448 | +| policy_gradient_loss | -0.00262 | +| value_loss | 0.000224 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.268 | +| time/ | | +| fps | 1374 | +| iterations | 4864 | +| time_elapsed | 7246 | +| total_timesteps | 9961472 | +| train/ | | +| approx_kl | 5.4627424e-05 | +| clip_fraction | 0.0123 | +| clip_range | 0.0255 | +| entropy_loss | -7.98 | +| explained_variance | -0.0147 | +| learning_rate | 2.8e-06 | +| loss | -0.00497 | +| n_updates | 19452 | +| policy_gradient_loss | -0.00279 | +| value_loss | 9.98e-05 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.268 | +| time/ | | +| fps | 1374 | +| iterations | 4865 | +| time_elapsed | 7247 | +| total_timesteps | 9963520 | +| train/ | | +| approx_kl | 4.4571207e-05 | +| clip_fraction | 0.00964 | +| clip_range | 0.0255 | +| entropy_loss | -7.92 | +| explained_variance | -0.0152 | +| learning_rate | 2.76e-06 | +| loss | -0.00551 | +| n_updates | 19456 | +| policy_gradient_loss | -0.00269 | +| value_loss | 0.000139 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.27 | +| time/ | | +| fps | 1374 | +| iterations | 4866 | +| time_elapsed | 7249 | +| total_timesteps | 9965568 | +| train/ | | +| approx_kl | 4.3057807e-05 | +| clip_fraction | 0.00964 | +| clip_range | 0.0255 | +| entropy_loss | -7.97 | +| explained_variance | 0.0071 | +| learning_rate | 2.72e-06 | +| loss | -0.00485 | +| n_updates | 19460 | +| policy_gradient_loss | -0.00265 | +| value_loss | 0.000129 | +------------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.258 | +| time/ | | +| fps | 1374 | +| iterations | 4867 | +| time_elapsed | 7250 | +| total_timesteps | 9967616 | +| train/ | | +| approx_kl | 4.031579e-05 | +| clip_fraction | 0.00903 | +| clip_range | 0.0254 | +| entropy_loss | -7.96 | +| explained_variance | -0.024 | +| learning_rate | 2.68e-06 | +| loss | -0.00408 | +| n_updates | 19464 | +| policy_gradient_loss | -0.00243 | +| value_loss | 0.000212 | +------------------------------------------ +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.256 | +| time/ | | +| fps | 1374 | +| iterations | 4868 | +| time_elapsed | 7252 | +| total_timesteps | 9969664 | +| train/ | | +| approx_kl | 4.3756096e-05 | +| clip_fraction | 0.00928 | +| clip_range | 0.0254 | +| entropy_loss | -7.82 | +| explained_variance | -0.045 | +| learning_rate | 2.64e-06 | +| loss | -0.00514 | +| n_updates | 19468 | +| policy_gradient_loss | -0.00247 | +| value_loss | 0.000124 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.256 | +| time/ | | +| fps | 1374 | +| iterations | 4869 | +| time_elapsed | 7253 | +| total_timesteps | 9971712 | +| train/ | | +| approx_kl | 5.1364797e-05 | +| clip_fraction | 0.0135 | +| clip_range | 0.0254 | +| entropy_loss | -7.57 | +| explained_variance | 0.393 | +| learning_rate | 2.6e-06 | +| loss | -0.00607 | +| n_updates | 19472 | +| policy_gradient_loss | -0.00269 | +| value_loss | 7.61e-05 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.26 | +| time/ | | +| fps | 1374 | +| iterations | 4870 | +| time_elapsed | 7255 | +| total_timesteps | 9973760 | +| train/ | | +| approx_kl | 3.6764555e-05 | +| clip_fraction | 0.00708 | +| clip_range | 0.0254 | +| entropy_loss | -7.81 | +| explained_variance | 0.00377 | +| learning_rate | 2.56e-06 | +| loss | -0.00522 | +| n_updates | 19476 | +| policy_gradient_loss | -0.00249 | +| value_loss | 0.000104 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.262 | +| time/ | | +| fps | 1374 | +| iterations | 4871 | +| time_elapsed | 7256 | +| total_timesteps | 9975808 | +| train/ | | +| approx_kl | 4.0256098e-05 | +| clip_fraction | 0.00879 | +| clip_range | 0.0253 | +| entropy_loss | -7.84 | +| explained_variance | 0.0591 | +| learning_rate | 2.52e-06 | +| loss | -0.00398 | +| n_updates | 19480 | +| policy_gradient_loss | -0.00256 | +| value_loss | 0.000201 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.267 | +| time/ | | +| fps | 1374 | +| iterations | 4872 | +| time_elapsed | 7258 | +| total_timesteps | 9977856 | +| train/ | | +| approx_kl | 3.8974977e-05 | +| clip_fraction | 0.00903 | +| clip_range | 0.0253 | +| entropy_loss | -7.92 | +| explained_variance | 0.0147 | +| learning_rate | 2.48e-06 | +| loss | -0.00443 | +| n_updates | 19484 | +| policy_gradient_loss | -0.00236 | +| value_loss | 0.000266 | +------------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.267 | +| time/ | | +| fps | 1374 | +| iterations | 4873 | +| time_elapsed | 7259 | +| total_timesteps | 9979904 | +| train/ | | +| approx_kl | 4.375406e-05 | +| clip_fraction | 0.00891 | +| clip_range | 0.0253 | +| entropy_loss | -7.74 | +| explained_variance | 0.145 | +| learning_rate | 2.44e-06 | +| loss | -0.0049 | +| n_updates | 19488 | +| policy_gradient_loss | -0.00257 | +| value_loss | 0.000119 | +------------------------------------------ +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.263 | +| time/ | | +| fps | 1374 | +| iterations | 4874 | +| time_elapsed | 7261 | +| total_timesteps | 9981952 | +| train/ | | +| approx_kl | 3.5946694e-05 | +| clip_fraction | 0.00781 | +| clip_range | 0.0253 | +| entropy_loss | -7.8 | +| explained_variance | -0.027 | +| learning_rate | 2.4e-06 | +| loss | -0.00527 | +| n_updates | 19492 | +| policy_gradient_loss | -0.00254 | +| value_loss | 0.00013 | +------------------------------------------- +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.263 | +| time/ | | +| fps | 1374 | +| iterations | 4875 | +| time_elapsed | 7262 | +| total_timesteps | 9984000 | +| train/ | | +| approx_kl | 3.1561387e-05 | +| clip_fraction | 0.00586 | +| clip_range | 0.0252 | +| entropy_loss | -7.86 | +| explained_variance | -0.0336 | +| learning_rate | 2.36e-06 | +| loss | -0.00506 | +| n_updates | 19496 | +| policy_gradient_loss | -0.0023 | +| value_loss | 0.000123 | +------------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.258 | +| time/ | | +| fps | 1374 | +| iterations | 4876 | +| time_elapsed | 7264 | +| total_timesteps | 9986048 | +| train/ | | +| approx_kl | 3.391155e-05 | +| clip_fraction | 0.00916 | +| clip_range | 0.0252 | +| entropy_loss | -7.99 | +| explained_variance | -0.00313 | +| learning_rate | 2.32e-06 | +| loss | -0.00437 | +| n_updates | 19500 | +| policy_gradient_loss | -0.00246 | +| value_loss | 0.000135 | +------------------------------------------ +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.256 | +| time/ | | +| fps | 1374 | +| iterations | 4877 | +| time_elapsed | 7265 | +| total_timesteps | 9988096 | +| train/ | | +| approx_kl | 3.3865508e-05 | +| clip_fraction | 0.00647 | +| clip_range | 0.0252 | +| entropy_loss | -7.97 | +| explained_variance | -0.00807 | +| learning_rate | 2.28e-06 | +| loss | -0.00308 | +| n_updates | 19504 | +| policy_gradient_loss | -0.0022 | +| value_loss | 0.000126 | +------------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.255 | +| time/ | | +| fps | 1374 | +| iterations | 4878 | +| time_elapsed | 7267 | +| total_timesteps | 9990144 | +| train/ | | +| approx_kl | 3.5423e-05 | +| clip_fraction | 0.00684 | +| clip_range | 0.0251 | +| entropy_loss | -7.81 | +| explained_variance | 0.0747 | +| learning_rate | 2.24e-06 | +| loss | -0.00325 | +| n_updates | 19508 | +| policy_gradient_loss | -0.00213 | +| value_loss | 0.000155 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.248 | +| time/ | | +| fps | 1374 | +| iterations | 4879 | +| time_elapsed | 7268 | +| total_timesteps | 9992192 | +| train/ | | +| approx_kl | 3.111751e-05 | +| clip_fraction | 0.00635 | +| clip_range | 0.0251 | +| entropy_loss | -7.63 | +| explained_variance | 0.14 | +| learning_rate | 2.2e-06 | +| loss | -0.00521 | +| n_updates | 19512 | +| policy_gradient_loss | -0.00203 | +| value_loss | 0.000117 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.257 | +| time/ | | +| fps | 1374 | +| iterations | 4880 | +| time_elapsed | 7270 | +| total_timesteps | 9994240 | +| train/ | | +| approx_kl | 3.538074e-05 | +| clip_fraction | 0.00659 | +| clip_range | 0.0251 | +| entropy_loss | -7.78 | +| explained_variance | 0.0172 | +| learning_rate | 2.15e-06 | +| loss | -0.00433 | +| n_updates | 19516 | +| policy_gradient_loss | -0.00235 | +| value_loss | 0.000144 | +------------------------------------------ +------------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.257 | +| time/ | | +| fps | 1374 | +| iterations | 4881 | +| time_elapsed | 7271 | +| total_timesteps | 9996288 | +| train/ | | +| approx_kl | 2.6151334e-05 | +| clip_fraction | 0.00525 | +| clip_range | 0.0251 | +| entropy_loss | -7.83 | +| explained_variance | 0.144 | +| learning_rate | 2.11e-06 | +| loss | -0.00548 | +| n_updates | 19520 | +| policy_gradient_loss | -0.00217 | +| value_loss | 0.000155 | +------------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.257 | +| time/ | | +| fps | 1374 | +| iterations | 4882 | +| time_elapsed | 7273 | +| total_timesteps | 9998336 | +| train/ | | +| approx_kl | 3.447701e-05 | +| clip_fraction | 0.00586 | +| clip_range | 0.025 | +| entropy_loss | -7.85 | +| explained_variance | 0.0326 | +| learning_rate | 2.07e-06 | +| loss | -0.0044 | +| n_updates | 19524 | +| policy_gradient_loss | -0.00231 | +| value_loss | 0.00025 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.253 | +| time/ | | +| fps | 1374 | +| iterations | 4883 | +| time_elapsed | 7275 | +| total_timesteps | 10000384 | +| train/ | | +| approx_kl | 2.644377e-05 | +| clip_fraction | 0.00476 | +| clip_range | 0.025 | +| entropy_loss | -7.97 | +| explained_variance | 0.0154 | +| learning_rate | 2.03e-06 | +| loss | -0.00363 | +| n_updates | 19528 | +| policy_gradient_loss | -0.00191 | +| value_loss | 0.000118 | +------------------------------------------ diff --git a/006_rgb_stack_ram_based_reward_time_reward_final_round/trained_models_ryu_vs_bison_finetune/training_log.txt b/006_rgb_stack_ram_based_reward_time_reward_final_round/trained_models_ryu_vs_bison_finetune/training_log.txt new file mode 100644 index 0000000..3546ab9 --- /dev/null +++ b/006_rgb_stack_ram_based_reward_time_reward_final_round/trained_models_ryu_vs_bison_finetune/training_log.txt @@ -0,0 +1,451349 @@ +Logging to logs\PPO_3 +----------------------------- +| time/ | | +| fps | 1182 | +| iterations | 1 | +| time_elapsed | 1 | +| total_timesteps | 2048 | +----------------------------- +------------------------------------------ +| time/ | | +| fps | 1266 | +| iterations | 2 | +| time_elapsed | 3 | +| total_timesteps | 4096 | +| train/ | | +| approx_kl | 0.0071797804 | +| clip_fraction | 0.254 | +| clip_range | 0.075 | +| entropy_loss | -6.36 | +| explained_variance | 0.298 | +| learning_rate | 5e-05 | +| loss | -0.0345 | +| n_updates | 15824 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000122 | +------------------------------------------ +----------------------------------------- +| time/ | | +| fps | 1302 | +| iterations | 3 | +| time_elapsed | 4 | +| total_timesteps | 6144 | +| train/ | | +| approx_kl | 0.008368006 | +| clip_fraction | 0.255 | +| clip_range | 0.075 | +| entropy_loss | -7.77 | +| explained_variance | 0.0205 | +| learning_rate | 5e-05 | +| loss | -0.0313 | +| n_updates | 15828 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000219 | +----------------------------------------- +----------------------------------------- +| time/ | | +| fps | 1307 | +| iterations | 4 | +| time_elapsed | 6 | +| total_timesteps | 8192 | +| train/ | | +| approx_kl | 0.008213628 | +| clip_fraction | 0.258 | +| clip_range | 0.075 | +| entropy_loss | -7.79 | +| explained_variance | -0.0604 | +| learning_rate | 5e-05 | +| loss | -0.0399 | +| n_updates | 15832 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000209 | +----------------------------------------- +------------------------------------------ +| time/ | | +| fps | 1319 | +| iterations | 5 | +| time_elapsed | 7 | +| total_timesteps | 10240 | +| train/ | | +| approx_kl | 0.0070577217 | +| clip_fraction | 0.214 | +| clip_range | 0.075 | +| entropy_loss | -7.87 | +| explained_variance | -0.177 | +| learning_rate | 5e-05 | +| loss | -0.0338 | +| n_updates | 15836 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000156 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 710 | +| ep_rew_mean | -0.168 | +| time/ | | +| fps | 1313 | +| iterations | 6 | +| time_elapsed | 9 | +| total_timesteps | 12288 | +| train/ | | +| approx_kl | 0.0073518422 | +| clip_fraction | 0.244 | +| clip_range | 0.075 | +| entropy_loss | -7.79 | +| explained_variance | -0.112 | +| learning_rate | 5e-05 | +| loss | -0.0364 | +| n_updates | 15840 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000185 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 765 | +| ep_rew_mean | 0.29 | +| time/ | | +| fps | 1316 | +| iterations | 7 | +| time_elapsed | 10 | +| total_timesteps | 14336 | +| train/ | | +| approx_kl | 0.0064083827 | +| clip_fraction | 0.242 | +| clip_range | 0.075 | +| entropy_loss | -7.68 | +| explained_variance | -0.0585 | +| learning_rate | 5e-05 | +| loss | -0.0326 | +| n_updates | 15844 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000109 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 881 | +| ep_rew_mean | 0.249 | +| time/ | | +| fps | 1318 | +| iterations | 8 | +| time_elapsed | 12 | +| total_timesteps | 16384 | +| train/ | | +| approx_kl | 0.0069423746 | +| clip_fraction | 0.23 | +| clip_range | 0.075 | +| entropy_loss | -7.72 | +| explained_variance | -0.034 | +| learning_rate | 5e-05 | +| loss | -0.0297 | +| n_updates | 15848 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000344 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 969 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1319 | +| iterations | 9 | +| time_elapsed | 13 | +| total_timesteps | 18432 | +| train/ | | +| approx_kl | 0.006948198 | +| clip_fraction | 0.262 | +| clip_range | 0.075 | +| entropy_loss | -7.7 | +| explained_variance | -0.299 | +| learning_rate | 5e-05 | +| loss | -0.032 | +| n_updates | 15852 | +| policy_gradient_loss | -0.0215 | +| value_loss | 9.46e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 1317 | +| iterations | 10 | +| time_elapsed | 15 | +| total_timesteps | 20480 | +| train/ | | +| approx_kl | 0.0068218466 | +| clip_fraction | 0.222 | +| clip_range | 0.075 | +| entropy_loss | -7.53 | +| explained_variance | 0.0262 | +| learning_rate | 5e-05 | +| loss | -0.0249 | +| n_updates | 15856 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000308 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.07e+03 | +| ep_rew_mean | 0.306 | +| time/ | | +| fps | 1318 | +| iterations | 11 | +| time_elapsed | 17 | +| total_timesteps | 22528 | +| train/ | | +| approx_kl | 0.008281439 | +| clip_fraction | 0.262 | +| clip_range | 0.075 | +| entropy_loss | -7.68 | +| explained_variance | -0.0753 | +| learning_rate | 5e-05 | +| loss | -0.0375 | +| n_updates | 15860 | +| policy_gradient_loss | -0.0215 | +| value_loss | 7.92e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.1e+03 | +| ep_rew_mean | 0.269 | +| time/ | | +| fps | 1320 | +| iterations | 12 | +| time_elapsed | 18 | +| total_timesteps | 24576 | +| train/ | | +| approx_kl | 0.006520345 | +| clip_fraction | 0.22 | +| clip_range | 0.075 | +| entropy_loss | -7.68 | +| explained_variance | -0.0307 | +| learning_rate | 5e-05 | +| loss | -0.0307 | +| n_updates | 15864 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000256 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.14e+03 | +| ep_rew_mean | 0.265 | +| time/ | | +| fps | 1322 | +| iterations | 13 | +| time_elapsed | 20 | +| total_timesteps | 26624 | +| train/ | | +| approx_kl | 0.0075504016 | +| clip_fraction | 0.248 | +| clip_range | 0.075 | +| entropy_loss | -7.53 | +| explained_variance | -0.0772 | +| learning_rate | 5e-05 | +| loss | -0.0339 | +| n_updates | 15868 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000176 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.264 | +| time/ | | +| fps | 1323 | +| iterations | 14 | +| time_elapsed | 21 | +| total_timesteps | 28672 | +| train/ | | +| approx_kl | 0.0075429017 | +| clip_fraction | 0.232 | +| clip_range | 0.075 | +| entropy_loss | -7.68 | +| explained_variance | -0.0537 | +| learning_rate | 5e-05 | +| loss | -0.0356 | +| n_updates | 15872 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000131 | +------------------------------------------ +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.264 | +| time/ | | +| fps | 1324 | +| iterations | 15 | +| time_elapsed | 23 | +| total_timesteps | 30720 | +| train/ | | +| approx_kl | 0.0069139 | +| clip_fraction | 0.244 | +| clip_range | 0.075 | +| entropy_loss | -7.62 | +| explained_variance | -0.0939 | +| learning_rate | 5e-05 | +| loss | -0.033 | +| n_updates | 15876 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000147 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.251 | +| time/ | | +| fps | 1325 | +| iterations | 16 | +| time_elapsed | 24 | +| total_timesteps | 32768 | +| train/ | | +| approx_kl | 0.007761387 | +| clip_fraction | 0.263 | +| clip_range | 0.075 | +| entropy_loss | -7.69 | +| explained_variance | -0.0193 | +| learning_rate | 5e-05 | +| loss | -0.0324 | +| n_updates | 15880 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000229 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.251 | +| time/ | | +| fps | 1326 | +| iterations | 17 | +| time_elapsed | 26 | +| total_timesteps | 34816 | +| train/ | | +| approx_kl | 0.007114633 | +| clip_fraction | 0.24 | +| clip_range | 0.075 | +| entropy_loss | -7.66 | +| explained_variance | -0.0599 | +| learning_rate | 5e-05 | +| loss | -0.0331 | +| n_updates | 15884 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000135 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.271 | +| time/ | | +| fps | 1326 | +| iterations | 18 | +| time_elapsed | 27 | +| total_timesteps | 36864 | +| train/ | | +| approx_kl | 0.0072207926 | +| clip_fraction | 0.233 | +| clip_range | 0.075 | +| entropy_loss | -7.72 | +| explained_variance | -0.0186 | +| learning_rate | 5e-05 | +| loss | -0.0333 | +| n_updates | 15888 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000148 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.26 | +| time/ | | +| fps | 1325 | +| iterations | 19 | +| time_elapsed | 29 | +| total_timesteps | 38912 | +| train/ | | +| approx_kl | 0.0062507736 | +| clip_fraction | 0.208 | +| clip_range | 0.075 | +| entropy_loss | -7.64 | +| explained_variance | 0.0996 | +| learning_rate | 5e-05 | +| loss | -0.0226 | +| n_updates | 15892 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000311 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.261 | +| time/ | | +| fps | 1325 | +| iterations | 20 | +| time_elapsed | 30 | +| total_timesteps | 40960 | +| train/ | | +| approx_kl | 0.007423601 | +| clip_fraction | 0.243 | +| clip_range | 0.075 | +| entropy_loss | -7.55 | +| explained_variance | -0.298 | +| learning_rate | 5e-05 | +| loss | -0.0336 | +| n_updates | 15896 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000122 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.261 | +| time/ | | +| fps | 1324 | +| iterations | 21 | +| time_elapsed | 32 | +| total_timesteps | 43008 | +| train/ | | +| approx_kl | 0.007502837 | +| clip_fraction | 0.254 | +| clip_range | 0.075 | +| entropy_loss | -7.67 | +| explained_variance | -0.119 | +| learning_rate | 5e-05 | +| loss | -0.0351 | +| n_updates | 15900 | +| policy_gradient_loss | -0.0212 | +| value_loss | 9.85e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.251 | +| time/ | | +| fps | 1323 | +| iterations | 22 | +| time_elapsed | 34 | +| total_timesteps | 45056 | +| train/ | | +| approx_kl | 0.006686108 | +| clip_fraction | 0.229 | +| clip_range | 0.075 | +| entropy_loss | -7.81 | +| explained_variance | -0.084 | +| learning_rate | 5e-05 | +| loss | -0.0344 | +| n_updates | 15904 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000145 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.251 | +| time/ | | +| fps | 1322 | +| iterations | 23 | +| time_elapsed | 35 | +| total_timesteps | 47104 | +| train/ | | +| approx_kl | 0.007022215 | +| clip_fraction | 0.227 | +| clip_range | 0.075 | +| entropy_loss | -7.58 | +| explained_variance | -0.0325 | +| learning_rate | 5e-05 | +| loss | -0.0303 | +| n_updates | 15908 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000269 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.25 | +| time/ | | +| fps | 1323 | +| iterations | 24 | +| time_elapsed | 37 | +| total_timesteps | 49152 | +| train/ | | +| approx_kl | 0.0069804695 | +| clip_fraction | 0.217 | +| clip_range | 0.075 | +| entropy_loss | -7.62 | +| explained_variance | -0.0204 | +| learning_rate | 5e-05 | +| loss | -0.0278 | +| n_updates | 15912 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000251 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.25 | +| time/ | | +| fps | 1323 | +| iterations | 25 | +| time_elapsed | 38 | +| total_timesteps | 51200 | +| train/ | | +| approx_kl | 0.008624889 | +| clip_fraction | 0.231 | +| clip_range | 0.075 | +| entropy_loss | -7.63 | +| explained_variance | 0.00164 | +| learning_rate | 5e-05 | +| loss | -0.0313 | +| n_updates | 15916 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000207 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.244 | +| time/ | | +| fps | 1323 | +| iterations | 26 | +| time_elapsed | 40 | +| total_timesteps | 53248 | +| train/ | | +| approx_kl | 0.007941107 | +| clip_fraction | 0.251 | +| clip_range | 0.075 | +| entropy_loss | -7.54 | +| explained_variance | -0.0939 | +| learning_rate | 5e-05 | +| loss | -0.0337 | +| n_updates | 15920 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.00013 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.25 | +| time/ | | +| fps | 1322 | +| iterations | 27 | +| time_elapsed | 41 | +| total_timesteps | 55296 | +| train/ | | +| approx_kl | 0.007019927 | +| clip_fraction | 0.227 | +| clip_range | 0.075 | +| entropy_loss | -7.73 | +| explained_variance | -0.12 | +| learning_rate | 5e-05 | +| loss | -0.0298 | +| n_updates | 15924 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000149 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.252 | +| time/ | | +| fps | 1321 | +| iterations | 28 | +| time_elapsed | 43 | +| total_timesteps | 57344 | +| train/ | | +| approx_kl | 0.0073438287 | +| clip_fraction | 0.214 | +| clip_range | 0.075 | +| entropy_loss | -7.69 | +| explained_variance | 0.00207 | +| learning_rate | 5e-05 | +| loss | -0.0309 | +| n_updates | 15928 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000176 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.252 | +| time/ | | +| fps | 1319 | +| iterations | 29 | +| time_elapsed | 44 | +| total_timesteps | 59392 | +| train/ | | +| approx_kl | 0.0066473903 | +| clip_fraction | 0.236 | +| clip_range | 0.075 | +| entropy_loss | -7.72 | +| explained_variance | -0.023 | +| learning_rate | 5e-05 | +| loss | -0.0325 | +| n_updates | 15932 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000124 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.254 | +| time/ | | +| fps | 1317 | +| iterations | 30 | +| time_elapsed | 46 | +| total_timesteps | 61440 | +| train/ | | +| approx_kl | 0.006458029 | +| clip_fraction | 0.234 | +| clip_range | 0.075 | +| entropy_loss | -7.76 | +| explained_variance | -0.0976 | +| learning_rate | 5e-05 | +| loss | -0.0328 | +| n_updates | 15936 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000172 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.257 | +| time/ | | +| fps | 1316 | +| iterations | 31 | +| time_elapsed | 48 | +| total_timesteps | 63488 | +| train/ | | +| approx_kl | 0.0074120723 | +| clip_fraction | 0.221 | +| clip_range | 0.075 | +| entropy_loss | -7.78 | +| explained_variance | -0.0479 | +| learning_rate | 5e-05 | +| loss | -0.0329 | +| n_updates | 15940 | +| policy_gradient_loss | -0.0182 | +| value_loss | 8.2e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.266 | +| time/ | | +| fps | 1315 | +| iterations | 32 | +| time_elapsed | 49 | +| total_timesteps | 65536 | +| train/ | | +| approx_kl | 0.006606139 | +| clip_fraction | 0.213 | +| clip_range | 0.075 | +| entropy_loss | -7.71 | +| explained_variance | 0.0327 | +| learning_rate | 5e-05 | +| loss | -0.0282 | +| n_updates | 15944 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000184 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.272 | +| time/ | | +| fps | 1313 | +| iterations | 33 | +| time_elapsed | 51 | +| total_timesteps | 67584 | +| train/ | | +| approx_kl | 0.006043234 | +| clip_fraction | 0.219 | +| clip_range | 0.075 | +| entropy_loss | -7.65 | +| explained_variance | -0.0374 | +| learning_rate | 5e-05 | +| loss | -0.0286 | +| n_updates | 15948 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.00017 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.266 | +| time/ | | +| fps | 1313 | +| iterations | 34 | +| time_elapsed | 53 | +| total_timesteps | 69632 | +| train/ | | +| approx_kl | 0.007304662 | +| clip_fraction | 0.255 | +| clip_range | 0.075 | +| entropy_loss | -7.56 | +| explained_variance | 0.0527 | +| learning_rate | 5e-05 | +| loss | -0.0302 | +| n_updates | 15952 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.00017 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.266 | +| time/ | | +| fps | 1313 | +| iterations | 35 | +| time_elapsed | 54 | +| total_timesteps | 71680 | +| train/ | | +| approx_kl | 0.00772138 | +| clip_fraction | 0.233 | +| clip_range | 0.075 | +| entropy_loss | -7.55 | +| explained_variance | -0.0344 | +| learning_rate | 5e-05 | +| loss | -0.0369 | +| n_updates | 15956 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000242 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.27 | +| time/ | | +| fps | 1313 | +| iterations | 36 | +| time_elapsed | 56 | +| total_timesteps | 73728 | +| train/ | | +| approx_kl | 0.007673794 | +| clip_fraction | 0.248 | +| clip_range | 0.075 | +| entropy_loss | -7.8 | +| explained_variance | -0.097 | +| learning_rate | 5e-05 | +| loss | -0.0346 | +| n_updates | 15960 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000162 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.272 | +| time/ | | +| fps | 1313 | +| iterations | 37 | +| time_elapsed | 57 | +| total_timesteps | 75776 | +| train/ | | +| approx_kl | 0.008618576 | +| clip_fraction | 0.245 | +| clip_range | 0.075 | +| entropy_loss | -7.61 | +| explained_variance | -0.065 | +| learning_rate | 5e-05 | +| loss | -0.0365 | +| n_updates | 15964 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000131 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.272 | +| time/ | | +| fps | 1312 | +| iterations | 38 | +| time_elapsed | 59 | +| total_timesteps | 77824 | +| train/ | | +| approx_kl | 0.008416356 | +| clip_fraction | 0.264 | +| clip_range | 0.075 | +| entropy_loss | -7.63 | +| explained_variance | -0.0705 | +| learning_rate | 5e-05 | +| loss | -0.0355 | +| n_updates | 15968 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000124 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.266 | +| time/ | | +| fps | 1313 | +| iterations | 39 | +| time_elapsed | 60 | +| total_timesteps | 79872 | +| train/ | | +| approx_kl | 0.007921735 | +| clip_fraction | 0.215 | +| clip_range | 0.075 | +| entropy_loss | -7.81 | +| explained_variance | 0.0123 | +| learning_rate | 5e-05 | +| loss | -0.0322 | +| n_updates | 15972 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000195 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.26 | +| time/ | | +| fps | 1313 | +| iterations | 40 | +| time_elapsed | 62 | +| total_timesteps | 81920 | +| train/ | | +| approx_kl | 0.006146336 | +| clip_fraction | 0.219 | +| clip_range | 0.075 | +| entropy_loss | -7.75 | +| explained_variance | -0.064 | +| learning_rate | 5e-05 | +| loss | -0.0319 | +| n_updates | 15976 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000182 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.252 | +| time/ | | +| fps | 1313 | +| iterations | 41 | +| time_elapsed | 63 | +| total_timesteps | 83968 | +| train/ | | +| approx_kl | 0.00726265 | +| clip_fraction | 0.223 | +| clip_range | 0.075 | +| entropy_loss | -7.67 | +| explained_variance | 0.0172 | +| learning_rate | 5e-05 | +| loss | -0.0332 | +| n_updates | 15980 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000217 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.258 | +| time/ | | +| fps | 1313 | +| iterations | 42 | +| time_elapsed | 65 | +| total_timesteps | 86016 | +| train/ | | +| approx_kl | 0.0065732747 | +| clip_fraction | 0.218 | +| clip_range | 0.075 | +| entropy_loss | -7.72 | +| explained_variance | -0.0304 | +| learning_rate | 5e-05 | +| loss | -0.0284 | +| n_updates | 15984 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000185 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.259 | +| time/ | | +| fps | 1313 | +| iterations | 43 | +| time_elapsed | 67 | +| total_timesteps | 88064 | +| train/ | | +| approx_kl | 0.005956216 | +| clip_fraction | 0.22 | +| clip_range | 0.075 | +| entropy_loss | -7.71 | +| explained_variance | 0.0523 | +| learning_rate | 5e-05 | +| loss | -0.0293 | +| n_updates | 15988 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000191 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.264 | +| time/ | | +| fps | 1314 | +| iterations | 44 | +| time_elapsed | 68 | +| total_timesteps | 90112 | +| train/ | | +| approx_kl | 0.0069131684 | +| clip_fraction | 0.223 | +| clip_range | 0.075 | +| entropy_loss | -7.58 | +| explained_variance | 0.141 | +| learning_rate | 5e-05 | +| loss | -0.0331 | +| n_updates | 15992 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000122 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.256 | +| time/ | | +| fps | 1314 | +| iterations | 45 | +| time_elapsed | 70 | +| total_timesteps | 92160 | +| train/ | | +| approx_kl | 0.007822602 | +| clip_fraction | 0.24 | +| clip_range | 0.075 | +| entropy_loss | -7.68 | +| explained_variance | -0.11 | +| learning_rate | 5e-05 | +| loss | -0.0298 | +| n_updates | 15996 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000167 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.256 | +| time/ | | +| fps | 1314 | +| iterations | 46 | +| time_elapsed | 71 | +| total_timesteps | 94208 | +| train/ | | +| approx_kl | 0.00774677 | +| clip_fraction | 0.231 | +| clip_range | 0.075 | +| entropy_loss | -7.3 | +| explained_variance | 0.239 | +| learning_rate | 5e-05 | +| loss | -0.0298 | +| n_updates | 16000 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000183 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.256 | +| time/ | | +| fps | 1314 | +| iterations | 47 | +| time_elapsed | 73 | +| total_timesteps | 96256 | +| train/ | | +| approx_kl | 0.007835238 | +| clip_fraction | 0.246 | +| clip_range | 0.075 | +| entropy_loss | -7.65 | +| explained_variance | -0.354 | +| learning_rate | 5e-05 | +| loss | -0.0355 | +| n_updates | 16004 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000196 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.252 | +| time/ | | +| fps | 1314 | +| iterations | 48 | +| time_elapsed | 74 | +| total_timesteps | 98304 | +| train/ | | +| approx_kl | 0.007986659 | +| clip_fraction | 0.239 | +| clip_range | 0.075 | +| entropy_loss | -7.73 | +| explained_variance | -0.0151 | +| learning_rate | 5e-05 | +| loss | -0.0325 | +| n_updates | 16008 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000181 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.255 | +| time/ | | +| fps | 1315 | +| iterations | 49 | +| time_elapsed | 76 | +| total_timesteps | 100352 | +| train/ | | +| approx_kl | 0.007709959 | +| clip_fraction | 0.253 | +| clip_range | 0.075 | +| entropy_loss | -7.73 | +| explained_variance | 0.00189 | +| learning_rate | 5e-05 | +| loss | -0.0387 | +| n_updates | 16012 | +| policy_gradient_loss | -0.0226 | +| value_loss | 0.000106 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.255 | +| time/ | | +| fps | 1315 | +| iterations | 50 | +| time_elapsed | 77 | +| total_timesteps | 102400 | +| train/ | | +| approx_kl | 0.0075767008 | +| clip_fraction | 0.222 | +| clip_range | 0.075 | +| entropy_loss | -7.72 | +| explained_variance | -0.0431 | +| learning_rate | 5e-05 | +| loss | -0.0289 | +| n_updates | 16016 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.00026 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.253 | +| time/ | | +| fps | 1314 | +| iterations | 51 | +| time_elapsed | 79 | +| total_timesteps | 104448 | +| train/ | | +| approx_kl | 0.008399475 | +| clip_fraction | 0.26 | +| clip_range | 0.075 | +| entropy_loss | -7.75 | +| explained_variance | -0.235 | +| learning_rate | 5e-05 | +| loss | -0.0398 | +| n_updates | 16020 | +| policy_gradient_loss | -0.0227 | +| value_loss | 6.66e-05 | +----------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.246 | +| time/ | | +| fps | 1314 | +| iterations | 52 | +| time_elapsed | 81 | +| total_timesteps | 106496 | +| train/ | | +| approx_kl | 0.007947 | +| clip_fraction | 0.251 | +| clip_range | 0.075 | +| entropy_loss | -7.79 | +| explained_variance | -0.0909 | +| learning_rate | 5e-05 | +| loss | -0.0292 | +| n_updates | 16024 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000173 | +-------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.249 | +| time/ | | +| fps | 1314 | +| iterations | 53 | +| time_elapsed | 82 | +| total_timesteps | 108544 | +| train/ | | +| approx_kl | 0.007828446 | +| clip_fraction | 0.233 | +| clip_range | 0.075 | +| entropy_loss | -7.53 | +| explained_variance | -0.0186 | +| learning_rate | 5e-05 | +| loss | -0.0258 | +| n_updates | 16028 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.00016 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.253 | +| time/ | | +| fps | 1314 | +| iterations | 54 | +| time_elapsed | 84 | +| total_timesteps | 110592 | +| train/ | | +| approx_kl | 0.007507663 | +| clip_fraction | 0.224 | +| clip_range | 0.075 | +| entropy_loss | -7.63 | +| explained_variance | -0.0282 | +| learning_rate | 5e-05 | +| loss | -0.0331 | +| n_updates | 16032 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000177 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.253 | +| time/ | | +| fps | 1315 | +| iterations | 55 | +| time_elapsed | 85 | +| total_timesteps | 112640 | +| train/ | | +| approx_kl | 0.007725842 | +| clip_fraction | 0.243 | +| clip_range | 0.075 | +| entropy_loss | -7.68 | +| explained_variance | -0.0496 | +| learning_rate | 5e-05 | +| loss | -0.0271 | +| n_updates | 16036 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.00016 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.258 | +| time/ | | +| fps | 1315 | +| iterations | 56 | +| time_elapsed | 87 | +| total_timesteps | 114688 | +| train/ | | +| approx_kl | 0.0072690058 | +| clip_fraction | 0.226 | +| clip_range | 0.075 | +| entropy_loss | -7.65 | +| explained_variance | -0.0428 | +| learning_rate | 5e-05 | +| loss | -0.0341 | +| n_updates | 16040 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000208 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.258 | +| time/ | | +| fps | 1315 | +| iterations | 57 | +| time_elapsed | 88 | +| total_timesteps | 116736 | +| train/ | | +| approx_kl | 0.007475662 | +| clip_fraction | 0.232 | +| clip_range | 0.075 | +| entropy_loss | -7.77 | +| explained_variance | -0.0573 | +| learning_rate | 5e-05 | +| loss | -0.028 | +| n_updates | 16044 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.00017 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.26 | +| time/ | | +| fps | 1315 | +| iterations | 58 | +| time_elapsed | 90 | +| total_timesteps | 118784 | +| train/ | | +| approx_kl | 0.006833263 | +| clip_fraction | 0.224 | +| clip_range | 0.075 | +| entropy_loss | -7.75 | +| explained_variance | -0.0325 | +| learning_rate | 5e-05 | +| loss | -0.0332 | +| n_updates | 16048 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000147 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.262 | +| time/ | | +| fps | 1315 | +| iterations | 59 | +| time_elapsed | 91 | +| total_timesteps | 120832 | +| train/ | | +| approx_kl | 0.006453001 | +| clip_fraction | 0.231 | +| clip_range | 0.075 | +| entropy_loss | -7.7 | +| explained_variance | 0.0308 | +| learning_rate | 5e-05 | +| loss | -0.0342 | +| n_updates | 16052 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000175 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.264 | +| time/ | | +| fps | 1315 | +| iterations | 60 | +| time_elapsed | 93 | +| total_timesteps | 122880 | +| train/ | | +| approx_kl | 0.0055728136 | +| clip_fraction | 0.22 | +| clip_range | 0.075 | +| entropy_loss | -7.61 | +| explained_variance | 0.049 | +| learning_rate | 5e-05 | +| loss | -0.028 | +| n_updates | 16056 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000229 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.264 | +| time/ | | +| fps | 1315 | +| iterations | 61 | +| time_elapsed | 94 | +| total_timesteps | 124928 | +| train/ | | +| approx_kl | 0.0074745524 | +| clip_fraction | 0.228 | +| clip_range | 0.075 | +| entropy_loss | -7.71 | +| explained_variance | -0.206 | +| learning_rate | 5e-05 | +| loss | -0.0399 | +| n_updates | 16060 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000146 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.263 | +| time/ | | +| fps | 1314 | +| iterations | 62 | +| time_elapsed | 96 | +| total_timesteps | 126976 | +| train/ | | +| approx_kl | 0.0062840874 | +| clip_fraction | 0.23 | +| clip_range | 0.075 | +| entropy_loss | -7.76 | +| explained_variance | 0.0156 | +| learning_rate | 5e-05 | +| loss | -0.0355 | +| n_updates | 16064 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000153 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.266 | +| time/ | | +| fps | 1314 | +| iterations | 63 | +| time_elapsed | 98 | +| total_timesteps | 129024 | +| train/ | | +| approx_kl | 0.0066607352 | +| clip_fraction | 0.24 | +| clip_range | 0.075 | +| entropy_loss | -7.73 | +| explained_variance | -0.0406 | +| learning_rate | 5e-05 | +| loss | -0.0309 | +| n_updates | 16068 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000173 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.268 | +| time/ | | +| fps | 1315 | +| iterations | 64 | +| time_elapsed | 99 | +| total_timesteps | 131072 | +| train/ | | +| approx_kl | 0.005952825 | +| clip_fraction | 0.209 | +| clip_range | 0.075 | +| entropy_loss | -7.63 | +| explained_variance | -0.0424 | +| learning_rate | 5e-05 | +| loss | -0.0289 | +| n_updates | 16072 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000171 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.271 | +| time/ | | +| fps | 1315 | +| iterations | 65 | +| time_elapsed | 101 | +| total_timesteps | 133120 | +| train/ | | +| approx_kl | 0.006868164 | +| clip_fraction | 0.228 | +| clip_range | 0.075 | +| entropy_loss | -7.81 | +| explained_variance | -0.0593 | +| learning_rate | 5e-05 | +| loss | -0.0329 | +| n_updates | 16076 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000147 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.276 | +| time/ | | +| fps | 1315 | +| iterations | 66 | +| time_elapsed | 102 | +| total_timesteps | 135168 | +| train/ | | +| approx_kl | 0.005919538 | +| clip_fraction | 0.213 | +| clip_range | 0.075 | +| entropy_loss | -7.7 | +| explained_variance | -0.0276 | +| learning_rate | 5e-05 | +| loss | -0.0281 | +| n_updates | 16080 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000279 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.273 | +| time/ | | +| fps | 1315 | +| iterations | 67 | +| time_elapsed | 104 | +| total_timesteps | 137216 | +| train/ | | +| approx_kl | 0.0064302376 | +| clip_fraction | 0.221 | +| clip_range | 0.075 | +| entropy_loss | -7.7 | +| explained_variance | -0.0934 | +| learning_rate | 5e-05 | +| loss | -0.0325 | +| n_updates | 16084 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000272 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.268 | +| time/ | | +| fps | 1315 | +| iterations | 68 | +| time_elapsed | 105 | +| total_timesteps | 139264 | +| train/ | | +| approx_kl | 0.006486023 | +| clip_fraction | 0.231 | +| clip_range | 0.075 | +| entropy_loss | -7.59 | +| explained_variance | 0.0264 | +| learning_rate | 5e-05 | +| loss | -0.0383 | +| n_updates | 16088 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.00018 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.272 | +| time/ | | +| fps | 1315 | +| iterations | 69 | +| time_elapsed | 107 | +| total_timesteps | 141312 | +| train/ | | +| approx_kl | 0.0067149466 | +| clip_fraction | 0.243 | +| clip_range | 0.075 | +| entropy_loss | -7.74 | +| explained_variance | 0.048 | +| learning_rate | 5e-05 | +| loss | -0.0308 | +| n_updates | 16092 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000122 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.273 | +| time/ | | +| fps | 1315 | +| iterations | 70 | +| time_elapsed | 108 | +| total_timesteps | 143360 | +| train/ | | +| approx_kl | 0.0066119614 | +| clip_fraction | 0.235 | +| clip_range | 0.075 | +| entropy_loss | -7.64 | +| explained_variance | 0.034 | +| learning_rate | 5e-05 | +| loss | -0.0297 | +| n_updates | 16096 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000332 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.273 | +| time/ | | +| fps | 1315 | +| iterations | 71 | +| time_elapsed | 110 | +| total_timesteps | 145408 | +| train/ | | +| approx_kl | 0.008039759 | +| clip_fraction | 0.25 | +| clip_range | 0.075 | +| entropy_loss | -7.71 | +| explained_variance | -0.178 | +| learning_rate | 5e-05 | +| loss | -0.0372 | +| n_updates | 16100 | +| policy_gradient_loss | -0.0227 | +| value_loss | 0.000118 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.273 | +| time/ | | +| fps | 1315 | +| iterations | 72 | +| time_elapsed | 112 | +| total_timesteps | 147456 | +| train/ | | +| approx_kl | 0.006990405 | +| clip_fraction | 0.237 | +| clip_range | 0.075 | +| entropy_loss | -7.66 | +| explained_variance | 0.00658 | +| learning_rate | 5e-05 | +| loss | -0.0323 | +| n_updates | 16104 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000178 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.273 | +| time/ | | +| fps | 1316 | +| iterations | 73 | +| time_elapsed | 113 | +| total_timesteps | 149504 | +| train/ | | +| approx_kl | 0.0076959995 | +| clip_fraction | 0.252 | +| clip_range | 0.075 | +| entropy_loss | -7.79 | +| explained_variance | -0.092 | +| learning_rate | 5e-05 | +| loss | -0.0354 | +| n_updates | 16108 | +| policy_gradient_loss | -0.0224 | +| value_loss | 0.000111 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 1316 | +| iterations | 74 | +| time_elapsed | 115 | +| total_timesteps | 151552 | +| train/ | | +| approx_kl | 0.0077757146 | +| clip_fraction | 0.247 | +| clip_range | 0.075 | +| entropy_loss | -7.84 | +| explained_variance | -0.362 | +| learning_rate | 5e-05 | +| loss | -0.0443 | +| n_updates | 16112 | +| policy_gradient_loss | -0.0221 | +| value_loss | 6.51e-05 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 1317 | +| iterations | 75 | +| time_elapsed | 116 | +| total_timesteps | 153600 | +| train/ | | +| approx_kl | 0.0070872623 | +| clip_fraction | 0.223 | +| clip_range | 0.075 | +| entropy_loss | -7.75 | +| explained_variance | -0.087 | +| learning_rate | 5e-05 | +| loss | -0.0285 | +| n_updates | 16116 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000229 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.266 | +| time/ | | +| fps | 1317 | +| iterations | 76 | +| time_elapsed | 118 | +| total_timesteps | 155648 | +| train/ | | +| approx_kl | 0.0072680986 | +| clip_fraction | 0.255 | +| clip_range | 0.075 | +| entropy_loss | -7.81 | +| explained_variance | -0.118 | +| learning_rate | 5e-05 | +| loss | -0.0367 | +| n_updates | 16120 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000135 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.266 | +| time/ | | +| fps | 1316 | +| iterations | 77 | +| time_elapsed | 119 | +| total_timesteps | 157696 | +| train/ | | +| approx_kl | 0.006603011 | +| clip_fraction | 0.245 | +| clip_range | 0.075 | +| entropy_loss | -7.61 | +| explained_variance | -0.182 | +| learning_rate | 5e-05 | +| loss | -0.0376 | +| n_updates | 16124 | +| policy_gradient_loss | -0.0202 | +| value_loss | 9.64e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.272 | +| time/ | | +| fps | 1316 | +| iterations | 78 | +| time_elapsed | 121 | +| total_timesteps | 159744 | +| train/ | | +| approx_kl | 0.007612428 | +| clip_fraction | 0.246 | +| clip_range | 0.075 | +| entropy_loss | -7.79 | +| explained_variance | -0.0402 | +| learning_rate | 5e-05 | +| loss | -0.0311 | +| n_updates | 16128 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000102 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.274 | +| time/ | | +| fps | 1315 | +| iterations | 79 | +| time_elapsed | 122 | +| total_timesteps | 161792 | +| train/ | | +| approx_kl | 0.00783723 | +| clip_fraction | 0.249 | +| clip_range | 0.075 | +| entropy_loss | -7.47 | +| explained_variance | 0.0554 | +| learning_rate | 5e-05 | +| loss | -0.0355 | +| n_updates | 16132 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000145 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.274 | +| time/ | | +| fps | 1315 | +| iterations | 80 | +| time_elapsed | 124 | +| total_timesteps | 163840 | +| train/ | | +| approx_kl | 0.0077015655 | +| clip_fraction | 0.252 | +| clip_range | 0.075 | +| entropy_loss | -7.51 | +| explained_variance | 0.0206 | +| learning_rate | 5e-05 | +| loss | -0.0352 | +| n_updates | 16136 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000185 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 1316 | +| iterations | 81 | +| time_elapsed | 126 | +| total_timesteps | 165888 | +| train/ | | +| approx_kl | 0.00857277 | +| clip_fraction | 0.253 | +| clip_range | 0.075 | +| entropy_loss | -7.71 | +| explained_variance | -0.084 | +| learning_rate | 5e-05 | +| loss | -0.0369 | +| n_updates | 16140 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000143 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.277 | +| time/ | | +| fps | 1315 | +| iterations | 82 | +| time_elapsed | 127 | +| total_timesteps | 167936 | +| train/ | | +| approx_kl | 0.006821814 | +| clip_fraction | 0.242 | +| clip_range | 0.075 | +| entropy_loss | -7.77 | +| explained_variance | 0.0471 | +| learning_rate | 5e-05 | +| loss | -0.0283 | +| n_updates | 16144 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000103 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.277 | +| time/ | | +| fps | 1316 | +| iterations | 83 | +| time_elapsed | 129 | +| total_timesteps | 169984 | +| train/ | | +| approx_kl | 0.0069940435 | +| clip_fraction | 0.225 | +| clip_range | 0.075 | +| entropy_loss | -7.66 | +| explained_variance | 0.039 | +| learning_rate | 5e-05 | +| loss | -0.0359 | +| n_updates | 16148 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000221 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.277 | +| time/ | | +| fps | 1315 | +| iterations | 84 | +| time_elapsed | 130 | +| total_timesteps | 172032 | +| train/ | | +| approx_kl | 0.0062277345 | +| clip_fraction | 0.214 | +| clip_range | 0.075 | +| entropy_loss | -7.82 | +| explained_variance | 0.0132 | +| learning_rate | 5e-05 | +| loss | -0.0295 | +| n_updates | 16152 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000198 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.281 | +| time/ | | +| fps | 1316 | +| iterations | 85 | +| time_elapsed | 132 | +| total_timesteps | 174080 | +| train/ | | +| approx_kl | 0.0072296313 | +| clip_fraction | 0.254 | +| clip_range | 0.075 | +| entropy_loss | -7.77 | +| explained_variance | -0.227 | +| learning_rate | 5e-05 | +| loss | -0.0383 | +| n_updates | 16156 | +| policy_gradient_loss | -0.0234 | +| value_loss | 6.74e-05 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.28 | +| time/ | | +| fps | 1316 | +| iterations | 86 | +| time_elapsed | 133 | +| total_timesteps | 176128 | +| train/ | | +| approx_kl | 0.0074318075 | +| clip_fraction | 0.235 | +| clip_range | 0.075 | +| entropy_loss | -7.75 | +| explained_variance | -0.121 | +| learning_rate | 5e-05 | +| loss | -0.0407 | +| n_updates | 16160 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000144 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.284 | +| time/ | | +| fps | 1316 | +| iterations | 87 | +| time_elapsed | 135 | +| total_timesteps | 178176 | +| train/ | | +| approx_kl | 0.006718582 | +| clip_fraction | 0.21 | +| clip_range | 0.075 | +| entropy_loss | -7.72 | +| explained_variance | -0.00798 | +| learning_rate | 5e-05 | +| loss | -0.0283 | +| n_updates | 16164 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000203 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.284 | +| time/ | | +| fps | 1316 | +| iterations | 88 | +| time_elapsed | 136 | +| total_timesteps | 180224 | +| train/ | | +| approx_kl | 0.0069048167 | +| clip_fraction | 0.247 | +| clip_range | 0.075 | +| entropy_loss | -7.71 | +| explained_variance | -0.178 | +| learning_rate | 5e-05 | +| loss | -0.035 | +| n_updates | 16168 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000118 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.284 | +| time/ | | +| fps | 1315 | +| iterations | 89 | +| time_elapsed | 138 | +| total_timesteps | 182272 | +| train/ | | +| approx_kl | 0.0072929366 | +| clip_fraction | 0.235 | +| clip_range | 0.075 | +| entropy_loss | -7.85 | +| explained_variance | -0.0926 | +| learning_rate | 5e-05 | +| loss | -0.032 | +| n_updates | 16172 | +| policy_gradient_loss | -0.0201 | +| value_loss | 8.82e-05 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.283 | +| time/ | | +| fps | 1315 | +| iterations | 90 | +| time_elapsed | 140 | +| total_timesteps | 184320 | +| train/ | | +| approx_kl | 0.0066520977 | +| clip_fraction | 0.233 | +| clip_range | 0.075 | +| entropy_loss | -7.79 | +| explained_variance | -0.108 | +| learning_rate | 5e-05 | +| loss | -0.0371 | +| n_updates | 16176 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000116 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 1315 | +| iterations | 91 | +| time_elapsed | 141 | +| total_timesteps | 186368 | +| train/ | | +| approx_kl | 0.007375219 | +| clip_fraction | 0.224 | +| clip_range | 0.075 | +| entropy_loss | -7.49 | +| explained_variance | 0.0802 | +| learning_rate | 5e-05 | +| loss | -0.0285 | +| n_updates | 16180 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000195 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.288 | +| time/ | | +| fps | 1314 | +| iterations | 92 | +| time_elapsed | 143 | +| total_timesteps | 188416 | +| train/ | | +| approx_kl | 0.007256044 | +| clip_fraction | 0.242 | +| clip_range | 0.075 | +| entropy_loss | -7.73 | +| explained_variance | -0.152 | +| learning_rate | 5e-05 | +| loss | -0.0315 | +| n_updates | 16184 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000108 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.288 | +| time/ | | +| fps | 1314 | +| iterations | 93 | +| time_elapsed | 144 | +| total_timesteps | 190464 | +| train/ | | +| approx_kl | 0.007286795 | +| clip_fraction | 0.229 | +| clip_range | 0.075 | +| entropy_loss | -7.47 | +| explained_variance | 0.0687 | +| learning_rate | 5e-05 | +| loss | -0.031 | +| n_updates | 16188 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000169 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.288 | +| time/ | | +| fps | 1314 | +| iterations | 94 | +| time_elapsed | 146 | +| total_timesteps | 192512 | +| train/ | | +| approx_kl | 0.0072285635 | +| clip_fraction | 0.248 | +| clip_range | 0.075 | +| entropy_loss | -7.55 | +| explained_variance | -0.0141 | +| learning_rate | 5e-05 | +| loss | -0.032 | +| n_updates | 16192 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.00019 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.43e+03 | +| ep_rew_mean | 0.29 | +| time/ | | +| fps | 1314 | +| iterations | 95 | +| time_elapsed | 147 | +| total_timesteps | 194560 | +| train/ | | +| approx_kl | 0.008335231 | +| clip_fraction | 0.234 | +| clip_range | 0.075 | +| entropy_loss | -7.83 | +| explained_variance | -0.0335 | +| learning_rate | 5e-05 | +| loss | -0.0333 | +| n_updates | 16196 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000119 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.287 | +| time/ | | +| fps | 1314 | +| iterations | 96 | +| time_elapsed | 149 | +| total_timesteps | 196608 | +| train/ | | +| approx_kl | 0.008041647 | +| clip_fraction | 0.267 | +| clip_range | 0.075 | +| entropy_loss | -7.71 | +| explained_variance | -0.318 | +| learning_rate | 5e-05 | +| loss | -0.0378 | +| n_updates | 16200 | +| policy_gradient_loss | -0.023 | +| value_loss | 8.42e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.287 | +| time/ | | +| fps | 1314 | +| iterations | 97 | +| time_elapsed | 151 | +| total_timesteps | 198656 | +| train/ | | +| approx_kl | 0.0076483516 | +| clip_fraction | 0.245 | +| clip_range | 0.075 | +| entropy_loss | -7.75 | +| explained_variance | -0.0273 | +| learning_rate | 5e-05 | +| loss | -0.0337 | +| n_updates | 16204 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000238 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.28 | +| time/ | | +| fps | 1314 | +| iterations | 98 | +| time_elapsed | 152 | +| total_timesteps | 200704 | +| train/ | | +| approx_kl | 0.0072378614 | +| clip_fraction | 0.239 | +| clip_range | 0.075 | +| entropy_loss | -7.84 | +| explained_variance | -0.126 | +| learning_rate | 5e-05 | +| loss | -0.0404 | +| n_updates | 16208 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000111 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.277 | +| time/ | | +| fps | 1314 | +| iterations | 99 | +| time_elapsed | 154 | +| total_timesteps | 202752 | +| train/ | | +| approx_kl | 0.007144833 | +| clip_fraction | 0.224 | +| clip_range | 0.0749 | +| entropy_loss | -7.48 | +| explained_variance | 0.0352 | +| learning_rate | 5e-05 | +| loss | -0.0286 | +| n_updates | 16212 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000223 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.277 | +| time/ | | +| fps | 1313 | +| iterations | 100 | +| time_elapsed | 155 | +| total_timesteps | 204800 | +| train/ | | +| approx_kl | 0.0066333497 | +| clip_fraction | 0.247 | +| clip_range | 0.0749 | +| entropy_loss | -7.72 | +| explained_variance | -0.0182 | +| learning_rate | 5e-05 | +| loss | -0.0327 | +| n_updates | 16216 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000154 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.278 | +| time/ | | +| fps | 1313 | +| iterations | 101 | +| time_elapsed | 157 | +| total_timesteps | 206848 | +| train/ | | +| approx_kl | 0.006994626 | +| clip_fraction | 0.248 | +| clip_range | 0.0749 | +| entropy_loss | -7.81 | +| explained_variance | -0.0596 | +| learning_rate | 5e-05 | +| loss | -0.0322 | +| n_updates | 16220 | +| policy_gradient_loss | -0.0207 | +| value_loss | 9.48e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.278 | +| time/ | | +| fps | 1313 | +| iterations | 102 | +| time_elapsed | 159 | +| total_timesteps | 208896 | +| train/ | | +| approx_kl | 0.006821936 | +| clip_fraction | 0.225 | +| clip_range | 0.0749 | +| entropy_loss | -7.63 | +| explained_variance | 0.0711 | +| learning_rate | 5e-05 | +| loss | -0.036 | +| n_updates | 16224 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000279 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.278 | +| time/ | | +| fps | 1313 | +| iterations | 103 | +| time_elapsed | 160 | +| total_timesteps | 210944 | +| train/ | | +| approx_kl | 0.0070400294 | +| clip_fraction | 0.262 | +| clip_range | 0.0749 | +| entropy_loss | -7.78 | +| explained_variance | -0.272 | +| learning_rate | 5e-05 | +| loss | -0.0363 | +| n_updates | 16228 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000127 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 1313 | +| iterations | 104 | +| time_elapsed | 162 | +| total_timesteps | 212992 | +| train/ | | +| approx_kl | 0.008371942 | +| clip_fraction | 0.259 | +| clip_range | 0.0749 | +| entropy_loss | -7.74 | +| explained_variance | -0.151 | +| learning_rate | 4.99e-05 | +| loss | -0.0363 | +| n_updates | 16232 | +| policy_gradient_loss | -0.0224 | +| value_loss | 0.000101 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.28 | +| time/ | | +| fps | 1313 | +| iterations | 105 | +| time_elapsed | 163 | +| total_timesteps | 215040 | +| train/ | | +| approx_kl | 0.007452171 | +| clip_fraction | 0.229 | +| clip_range | 0.0749 | +| entropy_loss | -7.75 | +| explained_variance | -0.195 | +| learning_rate | 4.99e-05 | +| loss | -0.0334 | +| n_updates | 16236 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000158 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 1313 | +| iterations | 106 | +| time_elapsed | 165 | +| total_timesteps | 217088 | +| train/ | | +| approx_kl | 0.0071128113 | +| clip_fraction | 0.241 | +| clip_range | 0.0749 | +| entropy_loss | -7.72 | +| explained_variance | -0.0122 | +| learning_rate | 4.99e-05 | +| loss | -0.0291 | +| n_updates | 16240 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.00014 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.284 | +| time/ | | +| fps | 1314 | +| iterations | 107 | +| time_elapsed | 166 | +| total_timesteps | 219136 | +| train/ | | +| approx_kl | 0.0069415346 | +| clip_fraction | 0.247 | +| clip_range | 0.0749 | +| entropy_loss | -7.64 | +| explained_variance | -0.0187 | +| learning_rate | 4.99e-05 | +| loss | -0.0291 | +| n_updates | 16244 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000147 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 1314 | +| iterations | 108 | +| time_elapsed | 168 | +| total_timesteps | 221184 | +| train/ | | +| approx_kl | 0.007070883 | +| clip_fraction | 0.208 | +| clip_range | 0.0749 | +| entropy_loss | -7.6 | +| explained_variance | -0.0833 | +| learning_rate | 4.99e-05 | +| loss | -0.0347 | +| n_updates | 16248 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000236 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.295 | +| time/ | | +| fps | 1312 | +| iterations | 109 | +| time_elapsed | 170 | +| total_timesteps | 223232 | +| train/ | | +| approx_kl | 0.007059255 | +| clip_fraction | 0.244 | +| clip_range | 0.0749 | +| entropy_loss | -7.57 | +| explained_variance | -0.0222 | +| learning_rate | 4.99e-05 | +| loss | -0.0335 | +| n_updates | 16252 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000224 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.297 | +| time/ | | +| fps | 1313 | +| iterations | 110 | +| time_elapsed | 171 | +| total_timesteps | 225280 | +| train/ | | +| approx_kl | 0.0070730695 | +| clip_fraction | 0.238 | +| clip_range | 0.0749 | +| entropy_loss | -7.63 | +| explained_variance | -0.14 | +| learning_rate | 4.99e-05 | +| loss | -0.0354 | +| n_updates | 16256 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000158 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.297 | +| time/ | | +| fps | 1313 | +| iterations | 111 | +| time_elapsed | 173 | +| total_timesteps | 227328 | +| train/ | | +| approx_kl | 0.0076802447 | +| clip_fraction | 0.249 | +| clip_range | 0.0749 | +| entropy_loss | -7.72 | +| explained_variance | -0.0788 | +| learning_rate | 4.99e-05 | +| loss | -0.029 | +| n_updates | 16260 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000254 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.295 | +| time/ | | +| fps | 1313 | +| iterations | 112 | +| time_elapsed | 174 | +| total_timesteps | 229376 | +| train/ | | +| approx_kl | 0.0072028106 | +| clip_fraction | 0.242 | +| clip_range | 0.0749 | +| entropy_loss | -7.86 | +| explained_variance | -0.0896 | +| learning_rate | 4.99e-05 | +| loss | -0.034 | +| n_updates | 16264 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000199 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.289 | +| time/ | | +| fps | 1313 | +| iterations | 113 | +| time_elapsed | 176 | +| total_timesteps | 231424 | +| train/ | | +| approx_kl | 0.007901313 | +| clip_fraction | 0.248 | +| clip_range | 0.0749 | +| entropy_loss | -7.62 | +| explained_variance | -0.00907 | +| learning_rate | 4.99e-05 | +| loss | -0.0355 | +| n_updates | 16268 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000278 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.287 | +| time/ | | +| fps | 1314 | +| iterations | 114 | +| time_elapsed | 177 | +| total_timesteps | 233472 | +| train/ | | +| approx_kl | 0.007485638 | +| clip_fraction | 0.253 | +| clip_range | 0.0749 | +| entropy_loss | -7.72 | +| explained_variance | 0.0285 | +| learning_rate | 4.99e-05 | +| loss | -0.0367 | +| n_updates | 16272 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000161 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.287 | +| time/ | | +| fps | 1314 | +| iterations | 115 | +| time_elapsed | 179 | +| total_timesteps | 235520 | +| train/ | | +| approx_kl | 0.008583883 | +| clip_fraction | 0.268 | +| clip_range | 0.0749 | +| entropy_loss | -7.73 | +| explained_variance | -0.348 | +| learning_rate | 4.99e-05 | +| loss | -0.0352 | +| n_updates | 16276 | +| policy_gradient_loss | -0.0234 | +| value_loss | 0.00012 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.287 | +| time/ | | +| fps | 1314 | +| iterations | 116 | +| time_elapsed | 180 | +| total_timesteps | 237568 | +| train/ | | +| approx_kl | 0.0076041277 | +| clip_fraction | 0.244 | +| clip_range | 0.0749 | +| entropy_loss | -7.79 | +| explained_variance | -0.0715 | +| learning_rate | 4.99e-05 | +| loss | -0.0304 | +| n_updates | 16280 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000143 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1314 | +| iterations | 117 | +| time_elapsed | 182 | +| total_timesteps | 239616 | +| train/ | | +| approx_kl | 0.006831366 | +| clip_fraction | 0.232 | +| clip_range | 0.0749 | +| entropy_loss | -7.86 | +| explained_variance | -0.052 | +| learning_rate | 4.99e-05 | +| loss | -0.0346 | +| n_updates | 16284 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000182 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1314 | +| iterations | 118 | +| time_elapsed | 183 | +| total_timesteps | 241664 | +| train/ | | +| approx_kl | 0.00753951 | +| clip_fraction | 0.25 | +| clip_range | 0.0749 | +| entropy_loss | -7.45 | +| explained_variance | -0.0285 | +| learning_rate | 4.99e-05 | +| loss | -0.029 | +| n_updates | 16288 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000384 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1313 | +| iterations | 119 | +| time_elapsed | 185 | +| total_timesteps | 243712 | +| train/ | | +| approx_kl | 0.008919647 | +| clip_fraction | 0.263 | +| clip_range | 0.0749 | +| entropy_loss | -7.41 | +| explained_variance | 0.0154 | +| learning_rate | 4.99e-05 | +| loss | -0.0321 | +| n_updates | 16292 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000302 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1313 | +| iterations | 120 | +| time_elapsed | 187 | +| total_timesteps | 245760 | +| train/ | | +| approx_kl | 0.007622725 | +| clip_fraction | 0.258 | +| clip_range | 0.0749 | +| entropy_loss | -7.6 | +| explained_variance | -0.0213 | +| learning_rate | 4.99e-05 | +| loss | -0.0366 | +| n_updates | 16296 | +| policy_gradient_loss | -0.0219 | +| value_loss | 0.000161 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.43e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1314 | +| iterations | 121 | +| time_elapsed | 188 | +| total_timesteps | 247808 | +| train/ | | +| approx_kl | 0.008667337 | +| clip_fraction | 0.265 | +| clip_range | 0.0749 | +| entropy_loss | -7.77 | +| explained_variance | -0.0535 | +| learning_rate | 4.99e-05 | +| loss | -0.0352 | +| n_updates | 16300 | +| policy_gradient_loss | -0.0223 | +| value_loss | 0.000157 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.43e+03 | +| ep_rew_mean | 0.315 | +| time/ | | +| fps | 1314 | +| iterations | 122 | +| time_elapsed | 190 | +| total_timesteps | 249856 | +| train/ | | +| approx_kl | 0.0076579237 | +| clip_fraction | 0.24 | +| clip_range | 0.0749 | +| entropy_loss | -7.66 | +| explained_variance | -0.116 | +| learning_rate | 4.99e-05 | +| loss | -0.034 | +| n_updates | 16304 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000141 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.43e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1314 | +| iterations | 123 | +| time_elapsed | 191 | +| total_timesteps | 251904 | +| train/ | | +| approx_kl | 0.008342309 | +| clip_fraction | 0.235 | +| clip_range | 0.0749 | +| entropy_loss | -7.73 | +| explained_variance | -0.0769 | +| learning_rate | 4.99e-05 | +| loss | -0.0301 | +| n_updates | 16308 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000236 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1314 | +| iterations | 124 | +| time_elapsed | 193 | +| total_timesteps | 253952 | +| train/ | | +| approx_kl | 0.006487609 | +| clip_fraction | 0.24 | +| clip_range | 0.0749 | +| entropy_loss | -7.71 | +| explained_variance | -0.0597 | +| learning_rate | 4.99e-05 | +| loss | -0.0352 | +| n_updates | 16312 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000184 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1314 | +| iterations | 125 | +| time_elapsed | 194 | +| total_timesteps | 256000 | +| train/ | | +| approx_kl | 0.0067184623 | +| clip_fraction | 0.22 | +| clip_range | 0.0749 | +| entropy_loss | -7.57 | +| explained_variance | -0.0578 | +| learning_rate | 4.99e-05 | +| loss | -0.0252 | +| n_updates | 16316 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000359 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1314 | +| iterations | 126 | +| time_elapsed | 196 | +| total_timesteps | 258048 | +| train/ | | +| approx_kl | 0.007447911 | +| clip_fraction | 0.257 | +| clip_range | 0.0749 | +| entropy_loss | -7.71 | +| explained_variance | -0.14 | +| learning_rate | 4.99e-05 | +| loss | -0.0278 | +| n_updates | 16320 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000169 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1314 | +| iterations | 127 | +| time_elapsed | 197 | +| total_timesteps | 260096 | +| train/ | | +| approx_kl | 0.0060658026 | +| clip_fraction | 0.239 | +| clip_range | 0.0749 | +| entropy_loss | -7.69 | +| explained_variance | -0.0845 | +| learning_rate | 4.99e-05 | +| loss | -0.0301 | +| n_updates | 16324 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000237 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1314 | +| iterations | 128 | +| time_elapsed | 199 | +| total_timesteps | 262144 | +| train/ | | +| approx_kl | 0.0079523735 | +| clip_fraction | 0.236 | +| clip_range | 0.0749 | +| entropy_loss | -7.75 | +| explained_variance | -0.16 | +| learning_rate | 4.99e-05 | +| loss | -0.0313 | +| n_updates | 16328 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000188 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1314 | +| iterations | 129 | +| time_elapsed | 201 | +| total_timesteps | 264192 | +| train/ | | +| approx_kl | 0.006713514 | +| clip_fraction | 0.238 | +| clip_range | 0.0749 | +| entropy_loss | -7.74 | +| explained_variance | -0.118 | +| learning_rate | 4.99e-05 | +| loss | -0.0377 | +| n_updates | 16332 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.00017 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1313 | +| iterations | 130 | +| time_elapsed | 202 | +| total_timesteps | 266240 | +| train/ | | +| approx_kl | 0.007532812 | +| clip_fraction | 0.261 | +| clip_range | 0.0749 | +| entropy_loss | -7.57 | +| explained_variance | -0.192 | +| learning_rate | 4.99e-05 | +| loss | -0.0328 | +| n_updates | 16336 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.0001 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1313 | +| iterations | 131 | +| time_elapsed | 204 | +| total_timesteps | 268288 | +| train/ | | +| approx_kl | 0.0076415506 | +| clip_fraction | 0.272 | +| clip_range | 0.0749 | +| entropy_loss | -7.58 | +| explained_variance | -0.0847 | +| learning_rate | 4.99e-05 | +| loss | -0.0307 | +| n_updates | 16340 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000259 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1313 | +| iterations | 132 | +| time_elapsed | 205 | +| total_timesteps | 270336 | +| train/ | | +| approx_kl | 0.008729403 | +| clip_fraction | 0.265 | +| clip_range | 0.0749 | +| entropy_loss | -7.73 | +| explained_variance | -0.134 | +| learning_rate | 4.99e-05 | +| loss | -0.0327 | +| n_updates | 16344 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000132 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1313 | +| iterations | 133 | +| time_elapsed | 207 | +| total_timesteps | 272384 | +| train/ | | +| approx_kl | 0.007104123 | +| clip_fraction | 0.223 | +| clip_range | 0.0749 | +| entropy_loss | -7.63 | +| explained_variance | 0.0215 | +| learning_rate | 4.99e-05 | +| loss | -0.0261 | +| n_updates | 16348 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000225 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1313 | +| iterations | 134 | +| time_elapsed | 208 | +| total_timesteps | 274432 | +| train/ | | +| approx_kl | 0.007391607 | +| clip_fraction | 0.258 | +| clip_range | 0.0749 | +| entropy_loss | -7.62 | +| explained_variance | -0.229 | +| learning_rate | 4.99e-05 | +| loss | -0.0343 | +| n_updates | 16352 | +| policy_gradient_loss | -0.0214 | +| value_loss | 7.32e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1313 | +| iterations | 135 | +| time_elapsed | 210 | +| total_timesteps | 276480 | +| train/ | | +| approx_kl | 0.008367344 | +| clip_fraction | 0.251 | +| clip_range | 0.0749 | +| entropy_loss | -7.62 | +| explained_variance | 0.0272 | +| learning_rate | 4.99e-05 | +| loss | -0.031 | +| n_updates | 16356 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000108 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1313 | +| iterations | 136 | +| time_elapsed | 212 | +| total_timesteps | 278528 | +| train/ | | +| approx_kl | 0.007092994 | +| clip_fraction | 0.232 | +| clip_range | 0.0749 | +| entropy_loss | -7.78 | +| explained_variance | 0.000234 | +| learning_rate | 4.99e-05 | +| loss | -0.0341 | +| n_updates | 16360 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000175 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1313 | +| iterations | 137 | +| time_elapsed | 213 | +| total_timesteps | 280576 | +| train/ | | +| approx_kl | 0.007944549 | +| clip_fraction | 0.256 | +| clip_range | 0.0749 | +| entropy_loss | -7.63 | +| explained_variance | -0.142 | +| learning_rate | 4.99e-05 | +| loss | -0.0301 | +| n_updates | 16364 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000123 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1314 | +| iterations | 138 | +| time_elapsed | 215 | +| total_timesteps | 282624 | +| train/ | | +| approx_kl | 0.007290867 | +| clip_fraction | 0.236 | +| clip_range | 0.0749 | +| entropy_loss | -7.76 | +| explained_variance | -0.0672 | +| learning_rate | 4.99e-05 | +| loss | -0.0329 | +| n_updates | 16368 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000252 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1314 | +| iterations | 139 | +| time_elapsed | 216 | +| total_timesteps | 284672 | +| train/ | | +| approx_kl | 0.0066706743 | +| clip_fraction | 0.237 | +| clip_range | 0.0749 | +| entropy_loss | -7.8 | +| explained_variance | -0.0897 | +| learning_rate | 4.99e-05 | +| loss | -0.0338 | +| n_updates | 16372 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000242 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1314 | +| iterations | 140 | +| time_elapsed | 218 | +| total_timesteps | 286720 | +| train/ | | +| approx_kl | 0.007434153 | +| clip_fraction | 0.261 | +| clip_range | 0.0749 | +| entropy_loss | -7.67 | +| explained_variance | -0.081 | +| learning_rate | 4.99e-05 | +| loss | -0.0314 | +| n_updates | 16376 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000178 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.43e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1314 | +| iterations | 141 | +| time_elapsed | 219 | +| total_timesteps | 288768 | +| train/ | | +| approx_kl | 0.008415563 | +| clip_fraction | 0.262 | +| clip_range | 0.0749 | +| entropy_loss | -7.6 | +| explained_variance | -0.0735 | +| learning_rate | 4.99e-05 | +| loss | -0.033 | +| n_updates | 16380 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000156 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.43e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1314 | +| iterations | 142 | +| time_elapsed | 221 | +| total_timesteps | 290816 | +| train/ | | +| approx_kl | 0.0086550135 | +| clip_fraction | 0.3 | +| clip_range | 0.0749 | +| entropy_loss | -7.69 | +| explained_variance | -0.514 | +| learning_rate | 4.99e-05 | +| loss | -0.0426 | +| n_updates | 16384 | +| policy_gradient_loss | -0.0257 | +| value_loss | 3.44e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.43e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1314 | +| iterations | 143 | +| time_elapsed | 222 | +| total_timesteps | 292864 | +| train/ | | +| approx_kl | 0.007831147 | +| clip_fraction | 0.259 | +| clip_range | 0.0749 | +| entropy_loss | -7.36 | +| explained_variance | 0.0597 | +| learning_rate | 4.99e-05 | +| loss | -0.0307 | +| n_updates | 16388 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000298 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.43e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1314 | +| iterations | 144 | +| time_elapsed | 224 | +| total_timesteps | 294912 | +| train/ | | +| approx_kl | 0.008318756 | +| clip_fraction | 0.259 | +| clip_range | 0.0749 | +| entropy_loss | -7.63 | +| explained_variance | 0.0567 | +| learning_rate | 4.99e-05 | +| loss | -0.037 | +| n_updates | 16392 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000183 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.44e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1314 | +| iterations | 145 | +| time_elapsed | 225 | +| total_timesteps | 296960 | +| train/ | | +| approx_kl | 0.0077511556 | +| clip_fraction | 0.256 | +| clip_range | 0.0749 | +| entropy_loss | -7.62 | +| explained_variance | -0.15 | +| learning_rate | 4.99e-05 | +| loss | -0.0336 | +| n_updates | 16396 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000172 | +------------------------------------------ +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.43e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1314 | +| iterations | 146 | +| time_elapsed | 227 | +| total_timesteps | 299008 | +| train/ | | +| approx_kl | 0.0083915 | +| clip_fraction | 0.267 | +| clip_range | 0.0749 | +| entropy_loss | -7.68 | +| explained_variance | -0.105 | +| learning_rate | 4.99e-05 | +| loss | -0.0315 | +| n_updates | 16400 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000144 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.43e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1313 | +| iterations | 147 | +| time_elapsed | 229 | +| total_timesteps | 301056 | +| train/ | | +| approx_kl | 0.008236896 | +| clip_fraction | 0.271 | +| clip_range | 0.0749 | +| entropy_loss | -7.5 | +| explained_variance | -0.144 | +| learning_rate | 4.99e-05 | +| loss | -0.0388 | +| n_updates | 16404 | +| policy_gradient_loss | -0.0225 | +| value_loss | 0.00012 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.43e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1313 | +| iterations | 148 | +| time_elapsed | 230 | +| total_timesteps | 303104 | +| train/ | | +| approx_kl | 0.0072921403 | +| clip_fraction | 0.269 | +| clip_range | 0.0749 | +| entropy_loss | -7.63 | +| explained_variance | -0.0782 | +| learning_rate | 4.99e-05 | +| loss | -0.0317 | +| n_updates | 16408 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000103 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1313 | +| iterations | 149 | +| time_elapsed | 232 | +| total_timesteps | 305152 | +| train/ | | +| approx_kl | 0.008460376 | +| clip_fraction | 0.261 | +| clip_range | 0.0749 | +| entropy_loss | -7.68 | +| explained_variance | 0.00229 | +| learning_rate | 4.99e-05 | +| loss | -0.0333 | +| n_updates | 16412 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000232 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1313 | +| iterations | 150 | +| time_elapsed | 233 | +| total_timesteps | 307200 | +| train/ | | +| approx_kl | 0.0074214153 | +| clip_fraction | 0.23 | +| clip_range | 0.0749 | +| entropy_loss | -7.71 | +| explained_variance | 0.0459 | +| learning_rate | 4.99e-05 | +| loss | -0.0242 | +| n_updates | 16416 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000342 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1314 | +| iterations | 151 | +| time_elapsed | 235 | +| total_timesteps | 309248 | +| train/ | | +| approx_kl | 0.007495983 | +| clip_fraction | 0.245 | +| clip_range | 0.0749 | +| entropy_loss | -7.74 | +| explained_variance | -0.129 | +| learning_rate | 4.99e-05 | +| loss | -0.0366 | +| n_updates | 16420 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.00021 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1314 | +| iterations | 152 | +| time_elapsed | 236 | +| total_timesteps | 311296 | +| train/ | | +| approx_kl | 0.007890943 | +| clip_fraction | 0.284 | +| clip_range | 0.0749 | +| entropy_loss | -7.52 | +| explained_variance | -0.169 | +| learning_rate | 4.99e-05 | +| loss | -0.0364 | +| n_updates | 16424 | +| policy_gradient_loss | -0.022 | +| value_loss | 0.000139 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1314 | +| iterations | 153 | +| time_elapsed | 238 | +| total_timesteps | 313344 | +| train/ | | +| approx_kl | 0.008123578 | +| clip_fraction | 0.265 | +| clip_range | 0.0749 | +| entropy_loss | -7.76 | +| explained_variance | -0.371 | +| learning_rate | 4.99e-05 | +| loss | -0.0411 | +| n_updates | 16428 | +| policy_gradient_loss | -0.0229 | +| value_loss | 7.69e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1314 | +| iterations | 154 | +| time_elapsed | 239 | +| total_timesteps | 315392 | +| train/ | | +| approx_kl | 0.008495145 | +| clip_fraction | 0.248 | +| clip_range | 0.0749 | +| entropy_loss | -7.71 | +| explained_variance | -0.049 | +| learning_rate | 4.99e-05 | +| loss | -0.0312 | +| n_updates | 16432 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000177 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1314 | +| iterations | 155 | +| time_elapsed | 241 | +| total_timesteps | 317440 | +| train/ | | +| approx_kl | 0.007575564 | +| clip_fraction | 0.27 | +| clip_range | 0.0749 | +| entropy_loss | -7.72 | +| explained_variance | -0.112 | +| learning_rate | 4.99e-05 | +| loss | -0.0356 | +| n_updates | 16436 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000115 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1314 | +| iterations | 156 | +| time_elapsed | 243 | +| total_timesteps | 319488 | +| train/ | | +| approx_kl | 0.0075068157 | +| clip_fraction | 0.232 | +| clip_range | 0.0749 | +| entropy_loss | -7.22 | +| explained_variance | 0.0204 | +| learning_rate | 4.99e-05 | +| loss | -0.0288 | +| n_updates | 16440 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000238 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1314 | +| iterations | 157 | +| time_elapsed | 244 | +| total_timesteps | 321536 | +| train/ | | +| approx_kl | 0.008283662 | +| clip_fraction | 0.238 | +| clip_range | 0.0749 | +| entropy_loss | -7.53 | +| explained_variance | -0.0278 | +| learning_rate | 4.99e-05 | +| loss | -0.0296 | +| n_updates | 16444 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000249 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1314 | +| iterations | 158 | +| time_elapsed | 246 | +| total_timesteps | 323584 | +| train/ | | +| approx_kl | 0.008449804 | +| clip_fraction | 0.266 | +| clip_range | 0.0749 | +| entropy_loss | -7.76 | +| explained_variance | -0.131 | +| learning_rate | 4.99e-05 | +| loss | -0.0357 | +| n_updates | 16448 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000128 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1314 | +| iterations | 159 | +| time_elapsed | 247 | +| total_timesteps | 325632 | +| train/ | | +| approx_kl | 0.008475322 | +| clip_fraction | 0.255 | +| clip_range | 0.0749 | +| entropy_loss | -7.62 | +| explained_variance | -0.0998 | +| learning_rate | 4.99e-05 | +| loss | -0.0376 | +| n_updates | 16452 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000204 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1314 | +| iterations | 160 | +| time_elapsed | 249 | +| total_timesteps | 327680 | +| train/ | | +| approx_kl | 0.009569883 | +| clip_fraction | 0.283 | +| clip_range | 0.0749 | +| entropy_loss | -7.73 | +| explained_variance | -0.148 | +| learning_rate | 4.99e-05 | +| loss | -0.0337 | +| n_updates | 16456 | +| policy_gradient_loss | -0.0221 | +| value_loss | 0.00011 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1314 | +| iterations | 161 | +| time_elapsed | 250 | +| total_timesteps | 329728 | +| train/ | | +| approx_kl | 0.0078074257 | +| clip_fraction | 0.242 | +| clip_range | 0.0749 | +| entropy_loss | -7.77 | +| explained_variance | -0.0882 | +| learning_rate | 4.99e-05 | +| loss | -0.0327 | +| n_updates | 16460 | +| policy_gradient_loss | -0.0207 | +| value_loss | 7.91e-05 | +------------------------------------------ +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1313 | +| iterations | 162 | +| time_elapsed | 252 | +| total_timesteps | 331776 | +| train/ | | +| approx_kl | 0.0071959 | +| clip_fraction | 0.268 | +| clip_range | 0.0749 | +| entropy_loss | -7.66 | +| explained_variance | -0.0537 | +| learning_rate | 4.99e-05 | +| loss | -0.0336 | +| n_updates | 16464 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000185 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1313 | +| iterations | 163 | +| time_elapsed | 254 | +| total_timesteps | 333824 | +| train/ | | +| approx_kl | 0.005172069 | +| clip_fraction | 0.213 | +| clip_range | 0.0749 | +| entropy_loss | -7.61 | +| explained_variance | -0.0428 | +| learning_rate | 4.99e-05 | +| loss | -0.0278 | +| n_updates | 16468 | +| policy_gradient_loss | -0.0148 | +| value_loss | 0.000259 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1313 | +| iterations | 164 | +| time_elapsed | 255 | +| total_timesteps | 335872 | +| train/ | | +| approx_kl | 0.007730483 | +| clip_fraction | 0.233 | +| clip_range | 0.0749 | +| entropy_loss | -7.6 | +| explained_variance | -0.115 | +| learning_rate | 4.99e-05 | +| loss | -0.0351 | +| n_updates | 16472 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000158 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1313 | +| iterations | 165 | +| time_elapsed | 257 | +| total_timesteps | 337920 | +| train/ | | +| approx_kl | 0.006789294 | +| clip_fraction | 0.236 | +| clip_range | 0.0749 | +| entropy_loss | -7.54 | +| explained_variance | -0.0748 | +| learning_rate | 4.99e-05 | +| loss | -0.0303 | +| n_updates | 16476 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.00035 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1313 | +| iterations | 166 | +| time_elapsed | 258 | +| total_timesteps | 339968 | +| train/ | | +| approx_kl | 0.0077829235 | +| clip_fraction | 0.258 | +| clip_range | 0.0749 | +| entropy_loss | -7.62 | +| explained_variance | 0.00667 | +| learning_rate | 4.99e-05 | +| loss | -0.0305 | +| n_updates | 16480 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000156 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1313 | +| iterations | 167 | +| time_elapsed | 260 | +| total_timesteps | 342016 | +| train/ | | +| approx_kl | 0.009365737 | +| clip_fraction | 0.28 | +| clip_range | 0.0749 | +| entropy_loss | -7.65 | +| explained_variance | -0.339 | +| learning_rate | 4.99e-05 | +| loss | -0.039 | +| n_updates | 16484 | +| policy_gradient_loss | -0.0232 | +| value_loss | 8.6e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1313 | +| iterations | 168 | +| time_elapsed | 261 | +| total_timesteps | 344064 | +| train/ | | +| approx_kl | 0.0072580655 | +| clip_fraction | 0.256 | +| clip_range | 0.0749 | +| entropy_loss | -7.52 | +| explained_variance | 0.0321 | +| learning_rate | 4.99e-05 | +| loss | -0.0332 | +| n_updates | 16488 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000314 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1313 | +| iterations | 169 | +| time_elapsed | 263 | +| total_timesteps | 346112 | +| train/ | | +| approx_kl | 0.009000597 | +| clip_fraction | 0.268 | +| clip_range | 0.0749 | +| entropy_loss | -7.62 | +| explained_variance | -0.391 | +| learning_rate | 4.99e-05 | +| loss | -0.0352 | +| n_updates | 16492 | +| policy_gradient_loss | -0.0231 | +| value_loss | 0.000116 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1312 | +| iterations | 170 | +| time_elapsed | 265 | +| total_timesteps | 348160 | +| train/ | | +| approx_kl | 0.0083757 | +| clip_fraction | 0.262 | +| clip_range | 0.0749 | +| entropy_loss | -7.63 | +| explained_variance | 0.0296 | +| learning_rate | 4.99e-05 | +| loss | -0.0381 | +| n_updates | 16496 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.00014 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1312 | +| iterations | 171 | +| time_elapsed | 266 | +| total_timesteps | 350208 | +| train/ | | +| approx_kl | 0.007839989 | +| clip_fraction | 0.252 | +| clip_range | 0.0749 | +| entropy_loss | -7.68 | +| explained_variance | -0.00579 | +| learning_rate | 4.99e-05 | +| loss | -0.0368 | +| n_updates | 16500 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000128 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1312 | +| iterations | 172 | +| time_elapsed | 268 | +| total_timesteps | 352256 | +| train/ | | +| approx_kl | 0.0077978773 | +| clip_fraction | 0.247 | +| clip_range | 0.0749 | +| entropy_loss | -7.7 | +| explained_variance | -0.141 | +| learning_rate | 4.99e-05 | +| loss | -0.0219 | +| n_updates | 16504 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000161 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1312 | +| iterations | 173 | +| time_elapsed | 269 | +| total_timesteps | 354304 | +| train/ | | +| approx_kl | 0.008449318 | +| clip_fraction | 0.237 | +| clip_range | 0.0749 | +| entropy_loss | -7.8 | +| explained_variance | -0.0574 | +| learning_rate | 4.99e-05 | +| loss | -0.0337 | +| n_updates | 16508 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000291 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1312 | +| iterations | 174 | +| time_elapsed | 271 | +| total_timesteps | 356352 | +| train/ | | +| approx_kl | 0.0075969053 | +| clip_fraction | 0.257 | +| clip_range | 0.0749 | +| entropy_loss | -7.66 | +| explained_variance | -0.154 | +| learning_rate | 4.99e-05 | +| loss | -0.0344 | +| n_updates | 16512 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000178 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1311 | +| iterations | 175 | +| time_elapsed | 273 | +| total_timesteps | 358400 | +| train/ | | +| approx_kl | 0.008102884 | +| clip_fraction | 0.254 | +| clip_range | 0.0749 | +| entropy_loss | -7.72 | +| explained_variance | -0.146 | +| learning_rate | 4.99e-05 | +| loss | -0.0334 | +| n_updates | 16516 | +| policy_gradient_loss | -0.022 | +| value_loss | 9.64e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1311 | +| iterations | 176 | +| time_elapsed | 274 | +| total_timesteps | 360448 | +| train/ | | +| approx_kl | 0.008231267 | +| clip_fraction | 0.254 | +| clip_range | 0.0749 | +| entropy_loss | -7.62 | +| explained_variance | -0.0491 | +| learning_rate | 4.99e-05 | +| loss | -0.0381 | +| n_updates | 16520 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000103 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 1312 | +| iterations | 177 | +| time_elapsed | 276 | +| total_timesteps | 362496 | +| train/ | | +| approx_kl | 0.007456229 | +| clip_fraction | 0.257 | +| clip_range | 0.0749 | +| entropy_loss | -7.53 | +| explained_variance | -0.00803 | +| learning_rate | 4.99e-05 | +| loss | -0.0327 | +| n_updates | 16524 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000189 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1312 | +| iterations | 178 | +| time_elapsed | 277 | +| total_timesteps | 364544 | +| train/ | | +| approx_kl | 0.00952845 | +| clip_fraction | 0.26 | +| clip_range | 0.0749 | +| entropy_loss | -7.59 | +| explained_variance | -0.141 | +| learning_rate | 4.99e-05 | +| loss | -0.0348 | +| n_updates | 16528 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000121 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1312 | +| iterations | 179 | +| time_elapsed | 279 | +| total_timesteps | 366592 | +| train/ | | +| approx_kl | 0.008699386 | +| clip_fraction | 0.246 | +| clip_range | 0.0749 | +| entropy_loss | -7.59 | +| explained_variance | -0.0566 | +| learning_rate | 4.99e-05 | +| loss | -0.0301 | +| n_updates | 16532 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000248 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1312 | +| iterations | 180 | +| time_elapsed | 280 | +| total_timesteps | 368640 | +| train/ | | +| approx_kl | 0.007213572 | +| clip_fraction | 0.253 | +| clip_range | 0.0749 | +| entropy_loss | -7.57 | +| explained_variance | 0.0165 | +| learning_rate | 4.99e-05 | +| loss | -0.0338 | +| n_updates | 16536 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000179 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 1312 | +| iterations | 181 | +| time_elapsed | 282 | +| total_timesteps | 370688 | +| train/ | | +| approx_kl | 0.00807542 | +| clip_fraction | 0.279 | +| clip_range | 0.0749 | +| entropy_loss | -7.5 | +| explained_variance | 0.028 | +| learning_rate | 4.99e-05 | +| loss | -0.0337 | +| n_updates | 16540 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000127 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1312 | +| iterations | 182 | +| time_elapsed | 284 | +| total_timesteps | 372736 | +| train/ | | +| approx_kl | 0.006870403 | +| clip_fraction | 0.24 | +| clip_range | 0.0749 | +| entropy_loss | -7.7 | +| explained_variance | -0.0189 | +| learning_rate | 4.99e-05 | +| loss | -0.0295 | +| n_updates | 16544 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000178 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1312 | +| iterations | 183 | +| time_elapsed | 285 | +| total_timesteps | 374784 | +| train/ | | +| approx_kl | 0.0072359955 | +| clip_fraction | 0.243 | +| clip_range | 0.0749 | +| entropy_loss | -7.63 | +| explained_variance | 0.0258 | +| learning_rate | 4.99e-05 | +| loss | -0.032 | +| n_updates | 16548 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000247 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.306 | +| time/ | | +| fps | 1312 | +| iterations | 184 | +| time_elapsed | 287 | +| total_timesteps | 376832 | +| train/ | | +| approx_kl | 0.0071215597 | +| clip_fraction | 0.256 | +| clip_range | 0.0749 | +| entropy_loss | -7.82 | +| explained_variance | -0.084 | +| learning_rate | 4.99e-05 | +| loss | -0.0368 | +| n_updates | 16552 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000118 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.304 | +| time/ | | +| fps | 1311 | +| iterations | 185 | +| time_elapsed | 288 | +| total_timesteps | 378880 | +| train/ | | +| approx_kl | 0.00753181 | +| clip_fraction | 0.247 | +| clip_range | 0.0749 | +| entropy_loss | -7.71 | +| explained_variance | -0.187 | +| learning_rate | 4.99e-05 | +| loss | -0.031 | +| n_updates | 16556 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000212 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.3 | +| time/ | | +| fps | 1311 | +| iterations | 186 | +| time_elapsed | 290 | +| total_timesteps | 380928 | +| train/ | | +| approx_kl | 0.0064218645 | +| clip_fraction | 0.234 | +| clip_range | 0.0749 | +| entropy_loss | -7.78 | +| explained_variance | -0.0256 | +| learning_rate | 4.99e-05 | +| loss | -0.0304 | +| n_updates | 16560 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000191 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 1311 | +| iterations | 187 | +| time_elapsed | 291 | +| total_timesteps | 382976 | +| train/ | | +| approx_kl | 0.007923463 | +| clip_fraction | 0.27 | +| clip_range | 0.0749 | +| entropy_loss | -7.67 | +| explained_variance | -0.121 | +| learning_rate | 4.99e-05 | +| loss | -0.0358 | +| n_updates | 16564 | +| policy_gradient_loss | -0.0242 | +| value_loss | 8.98e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 1312 | +| iterations | 188 | +| time_elapsed | 293 | +| total_timesteps | 385024 | +| train/ | | +| approx_kl | 0.0075006457 | +| clip_fraction | 0.241 | +| clip_range | 0.0749 | +| entropy_loss | -7.7 | +| explained_variance | -0.0317 | +| learning_rate | 4.99e-05 | +| loss | -0.0301 | +| n_updates | 16568 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000247 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 1312 | +| iterations | 189 | +| time_elapsed | 294 | +| total_timesteps | 387072 | +| train/ | | +| approx_kl | 0.007823404 | +| clip_fraction | 0.264 | +| clip_range | 0.0749 | +| entropy_loss | -7.69 | +| explained_variance | -0.215 | +| learning_rate | 4.99e-05 | +| loss | -0.0318 | +| n_updates | 16572 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000139 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.288 | +| time/ | | +| fps | 1312 | +| iterations | 190 | +| time_elapsed | 296 | +| total_timesteps | 389120 | +| train/ | | +| approx_kl | 0.006290973 | +| clip_fraction | 0.236 | +| clip_range | 0.0749 | +| entropy_loss | -7.56 | +| explained_variance | -0.0947 | +| learning_rate | 4.99e-05 | +| loss | -0.0311 | +| n_updates | 16576 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000124 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.288 | +| time/ | | +| fps | 1312 | +| iterations | 191 | +| time_elapsed | 297 | +| total_timesteps | 391168 | +| train/ | | +| approx_kl | 0.0080873305 | +| clip_fraction | 0.233 | +| clip_range | 0.0749 | +| entropy_loss | -7.55 | +| explained_variance | -0.0417 | +| learning_rate | 4.99e-05 | +| loss | -0.0346 | +| n_updates | 16580 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000102 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.285 | +| time/ | | +| fps | 1312 | +| iterations | 192 | +| time_elapsed | 299 | +| total_timesteps | 393216 | +| train/ | | +| approx_kl | 0.0075831274 | +| clip_fraction | 0.251 | +| clip_range | 0.0749 | +| entropy_loss | -7.6 | +| explained_variance | -0.0274 | +| learning_rate | 4.99e-05 | +| loss | -0.0343 | +| n_updates | 16584 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000185 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.285 | +| time/ | | +| fps | 1312 | +| iterations | 193 | +| time_elapsed | 301 | +| total_timesteps | 395264 | +| train/ | | +| approx_kl | 0.008254861 | +| clip_fraction | 0.251 | +| clip_range | 0.0749 | +| entropy_loss | -7.41 | +| explained_variance | 0.0128 | +| learning_rate | 4.99e-05 | +| loss | -0.0258 | +| n_updates | 16588 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000273 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.29 | +| time/ | | +| fps | 1312 | +| iterations | 194 | +| time_elapsed | 302 | +| total_timesteps | 397312 | +| train/ | | +| approx_kl | 0.0083974 | +| clip_fraction | 0.253 | +| clip_range | 0.0749 | +| entropy_loss | -7.75 | +| explained_variance | -0.146 | +| learning_rate | 4.99e-05 | +| loss | -0.0379 | +| n_updates | 16592 | +| policy_gradient_loss | -0.0225 | +| value_loss | 0.000123 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.29 | +| time/ | | +| fps | 1312 | +| iterations | 195 | +| time_elapsed | 304 | +| total_timesteps | 399360 | +| train/ | | +| approx_kl | 0.007613057 | +| clip_fraction | 0.248 | +| clip_range | 0.0749 | +| entropy_loss | -7.61 | +| explained_variance | -0.0476 | +| learning_rate | 4.99e-05 | +| loss | -0.0324 | +| n_updates | 16596 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000195 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.281 | +| time/ | | +| fps | 1313 | +| iterations | 196 | +| time_elapsed | 305 | +| total_timesteps | 401408 | +| train/ | | +| approx_kl | 0.008051813 | +| clip_fraction | 0.246 | +| clip_range | 0.0749 | +| entropy_loss | -7.82 | +| explained_variance | -0.122 | +| learning_rate | 4.99e-05 | +| loss | -0.0297 | +| n_updates | 16600 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000131 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 1313 | +| iterations | 197 | +| time_elapsed | 307 | +| total_timesteps | 403456 | +| train/ | | +| approx_kl | 0.008128353 | +| clip_fraction | 0.252 | +| clip_range | 0.0749 | +| entropy_loss | -7.67 | +| explained_variance | -0.129 | +| learning_rate | 4.99e-05 | +| loss | -0.0404 | +| n_updates | 16604 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000146 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 1313 | +| iterations | 198 | +| time_elapsed | 308 | +| total_timesteps | 405504 | +| train/ | | +| approx_kl | 0.007971359 | +| clip_fraction | 0.239 | +| clip_range | 0.0749 | +| entropy_loss | -7.74 | +| explained_variance | -0.0618 | +| learning_rate | 4.99e-05 | +| loss | -0.0329 | +| n_updates | 16608 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000162 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.272 | +| time/ | | +| fps | 1313 | +| iterations | 199 | +| time_elapsed | 310 | +| total_timesteps | 407552 | +| train/ | | +| approx_kl | 0.007656494 | +| clip_fraction | 0.257 | +| clip_range | 0.0749 | +| entropy_loss | -7.74 | +| explained_variance | -0.104 | +| learning_rate | 4.99e-05 | +| loss | -0.0349 | +| n_updates | 16612 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000125 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.273 | +| time/ | | +| fps | 1313 | +| iterations | 200 | +| time_elapsed | 311 | +| total_timesteps | 409600 | +| train/ | | +| approx_kl | 0.008224186 | +| clip_fraction | 0.278 | +| clip_range | 0.0749 | +| entropy_loss | -7.56 | +| explained_variance | -0.156 | +| learning_rate | 4.99e-05 | +| loss | -0.0386 | +| n_updates | 16616 | +| policy_gradient_loss | -0.0245 | +| value_loss | 5.7e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.274 | +| time/ | | +| fps | 1313 | +| iterations | 201 | +| time_elapsed | 313 | +| total_timesteps | 411648 | +| train/ | | +| approx_kl | 0.007942517 | +| clip_fraction | 0.25 | +| clip_range | 0.0749 | +| entropy_loss | -7.48 | +| explained_variance | -0.028 | +| learning_rate | 4.99e-05 | +| loss | -0.029 | +| n_updates | 16620 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000157 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.269 | +| time/ | | +| fps | 1313 | +| iterations | 202 | +| time_elapsed | 314 | +| total_timesteps | 413696 | +| train/ | | +| approx_kl | 0.00830721 | +| clip_fraction | 0.254 | +| clip_range | 0.0749 | +| entropy_loss | -7.51 | +| explained_variance | -0.0709 | +| learning_rate | 4.99e-05 | +| loss | -0.0322 | +| n_updates | 16624 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000127 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.271 | +| time/ | | +| fps | 1313 | +| iterations | 203 | +| time_elapsed | 316 | +| total_timesteps | 415744 | +| train/ | | +| approx_kl | 0.0077782115 | +| clip_fraction | 0.244 | +| clip_range | 0.0749 | +| entropy_loss | -7.54 | +| explained_variance | -0.0278 | +| learning_rate | 4.99e-05 | +| loss | -0.0346 | +| n_updates | 16628 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000145 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.273 | +| time/ | | +| fps | 1313 | +| iterations | 204 | +| time_elapsed | 318 | +| total_timesteps | 417792 | +| train/ | | +| approx_kl | 0.0065609394 | +| clip_fraction | 0.23 | +| clip_range | 0.0749 | +| entropy_loss | -7.7 | +| explained_variance | -0.0637 | +| learning_rate | 4.99e-05 | +| loss | -0.0301 | +| n_updates | 16632 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.00027 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.267 | +| time/ | | +| fps | 1313 | +| iterations | 205 | +| time_elapsed | 319 | +| total_timesteps | 419840 | +| train/ | | +| approx_kl | 0.007891906 | +| clip_fraction | 0.245 | +| clip_range | 0.0749 | +| entropy_loss | -7.63 | +| explained_variance | -0.118 | +| learning_rate | 4.99e-05 | +| loss | -0.036 | +| n_updates | 16636 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000159 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.263 | +| time/ | | +| fps | 1313 | +| iterations | 206 | +| time_elapsed | 321 | +| total_timesteps | 421888 | +| train/ | | +| approx_kl | 0.007074446 | +| clip_fraction | 0.221 | +| clip_range | 0.0749 | +| entropy_loss | -7.8 | +| explained_variance | -0.0334 | +| learning_rate | 4.99e-05 | +| loss | -0.0342 | +| n_updates | 16640 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000136 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.263 | +| time/ | | +| fps | 1313 | +| iterations | 207 | +| time_elapsed | 322 | +| total_timesteps | 423936 | +| train/ | | +| approx_kl | 0.008910436 | +| clip_fraction | 0.273 | +| clip_range | 0.0749 | +| entropy_loss | -7.6 | +| explained_variance | 0.0141 | +| learning_rate | 4.99e-05 | +| loss | -0.0308 | +| n_updates | 16644 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000169 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.26 | +| time/ | | +| fps | 1314 | +| iterations | 208 | +| time_elapsed | 324 | +| total_timesteps | 425984 | +| train/ | | +| approx_kl | 0.008201696 | +| clip_fraction | 0.249 | +| clip_range | 0.0749 | +| entropy_loss | -7.81 | +| explained_variance | -0.0601 | +| learning_rate | 4.99e-05 | +| loss | -0.0338 | +| n_updates | 16648 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000134 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.258 | +| time/ | | +| fps | 1314 | +| iterations | 209 | +| time_elapsed | 325 | +| total_timesteps | 428032 | +| train/ | | +| approx_kl | 0.007871337 | +| clip_fraction | 0.248 | +| clip_range | 0.0749 | +| entropy_loss | -7.62 | +| explained_variance | -0.0471 | +| learning_rate | 4.99e-05 | +| loss | -0.0355 | +| n_updates | 16652 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000156 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.26 | +| time/ | | +| fps | 1314 | +| iterations | 210 | +| time_elapsed | 327 | +| total_timesteps | 430080 | +| train/ | | +| approx_kl | 0.007848906 | +| clip_fraction | 0.232 | +| clip_range | 0.0749 | +| entropy_loss | -7.57 | +| explained_variance | -0.0141 | +| learning_rate | 4.99e-05 | +| loss | -0.0336 | +| n_updates | 16656 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000127 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.261 | +| time/ | | +| fps | 1314 | +| iterations | 211 | +| time_elapsed | 328 | +| total_timesteps | 432128 | +| train/ | | +| approx_kl | 0.0073935804 | +| clip_fraction | 0.216 | +| clip_range | 0.0749 | +| entropy_loss | -7.72 | +| explained_variance | -0.108 | +| learning_rate | 4.99e-05 | +| loss | -0.0251 | +| n_updates | 16660 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000226 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.261 | +| time/ | | +| fps | 1314 | +| iterations | 212 | +| time_elapsed | 330 | +| total_timesteps | 434176 | +| train/ | | +| approx_kl | 0.0070616677 | +| clip_fraction | 0.235 | +| clip_range | 0.0749 | +| entropy_loss | -7.71 | +| explained_variance | -0.0456 | +| learning_rate | 4.99e-05 | +| loss | -0.0317 | +| n_updates | 16664 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000163 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.255 | +| time/ | | +| fps | 1314 | +| iterations | 213 | +| time_elapsed | 331 | +| total_timesteps | 436224 | +| train/ | | +| approx_kl | 0.007437547 | +| clip_fraction | 0.242 | +| clip_range | 0.0749 | +| entropy_loss | -7.61 | +| explained_variance | -0.0975 | +| learning_rate | 4.99e-05 | +| loss | -0.0327 | +| n_updates | 16668 | +| policy_gradient_loss | -0.0211 | +| value_loss | 9.99e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.26 | +| time/ | | +| fps | 1314 | +| iterations | 214 | +| time_elapsed | 333 | +| total_timesteps | 438272 | +| train/ | | +| approx_kl | 0.006698503 | +| clip_fraction | 0.247 | +| clip_range | 0.0749 | +| entropy_loss | -7.63 | +| explained_variance | -0.149 | +| learning_rate | 4.99e-05 | +| loss | -0.0296 | +| n_updates | 16672 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000207 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.257 | +| time/ | | +| fps | 1314 | +| iterations | 215 | +| time_elapsed | 334 | +| total_timesteps | 440320 | +| train/ | | +| approx_kl | 0.007636086 | +| clip_fraction | 0.241 | +| clip_range | 0.0749 | +| entropy_loss | -7.53 | +| explained_variance | -0.0965 | +| learning_rate | 4.99e-05 | +| loss | -0.0333 | +| n_updates | 16676 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000174 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.257 | +| time/ | | +| fps | 1314 | +| iterations | 216 | +| time_elapsed | 336 | +| total_timesteps | 442368 | +| train/ | | +| approx_kl | 0.0075571863 | +| clip_fraction | 0.245 | +| clip_range | 0.0749 | +| entropy_loss | -7.44 | +| explained_variance | 0.0432 | +| learning_rate | 4.99e-05 | +| loss | -0.0328 | +| n_updates | 16680 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000126 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.257 | +| time/ | | +| fps | 1314 | +| iterations | 217 | +| time_elapsed | 337 | +| total_timesteps | 444416 | +| train/ | | +| approx_kl | 0.007589683 | +| clip_fraction | 0.257 | +| clip_range | 0.0749 | +| entropy_loss | -7.66 | +| explained_variance | -0.05 | +| learning_rate | 4.99e-05 | +| loss | -0.0328 | +| n_updates | 16684 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000178 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.257 | +| time/ | | +| fps | 1315 | +| iterations | 218 | +| time_elapsed | 339 | +| total_timesteps | 446464 | +| train/ | | +| approx_kl | 0.007646993 | +| clip_fraction | 0.258 | +| clip_range | 0.0749 | +| entropy_loss | -7.8 | +| explained_variance | 0.0322 | +| learning_rate | 4.99e-05 | +| loss | -0.0346 | +| n_updates | 16688 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000182 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.266 | +| time/ | | +| fps | 1315 | +| iterations | 219 | +| time_elapsed | 341 | +| total_timesteps | 448512 | +| train/ | | +| approx_kl | 0.006955293 | +| clip_fraction | 0.254 | +| clip_range | 0.0749 | +| entropy_loss | -7.82 | +| explained_variance | -0.0665 | +| learning_rate | 4.99e-05 | +| loss | -0.0345 | +| n_updates | 16692 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000196 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.265 | +| time/ | | +| fps | 1315 | +| iterations | 220 | +| time_elapsed | 342 | +| total_timesteps | 450560 | +| train/ | | +| approx_kl | 0.00699265 | +| clip_fraction | 0.231 | +| clip_range | 0.0749 | +| entropy_loss | -7.58 | +| explained_variance | -0.00398 | +| learning_rate | 4.99e-05 | +| loss | -0.0326 | +| n_updates | 16696 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.00029 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.258 | +| time/ | | +| fps | 1315 | +| iterations | 221 | +| time_elapsed | 344 | +| total_timesteps | 452608 | +| train/ | | +| approx_kl | 0.0069493614 | +| clip_fraction | 0.238 | +| clip_range | 0.0749 | +| entropy_loss | -7.69 | +| explained_variance | -0.595 | +| learning_rate | 4.99e-05 | +| loss | -0.0413 | +| n_updates | 16700 | +| policy_gradient_loss | -0.0219 | +| value_loss | 0.000121 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.261 | +| time/ | | +| fps | 1315 | +| iterations | 222 | +| time_elapsed | 345 | +| total_timesteps | 454656 | +| train/ | | +| approx_kl | 0.008319992 | +| clip_fraction | 0.237 | +| clip_range | 0.0749 | +| entropy_loss | -7.67 | +| explained_variance | -0.0314 | +| learning_rate | 4.99e-05 | +| loss | -0.0296 | +| n_updates | 16704 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000202 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.261 | +| time/ | | +| fps | 1315 | +| iterations | 223 | +| time_elapsed | 347 | +| total_timesteps | 456704 | +| train/ | | +| approx_kl | 0.0075187767 | +| clip_fraction | 0.259 | +| clip_range | 0.0749 | +| entropy_loss | -7.37 | +| explained_variance | -0.0609 | +| learning_rate | 4.99e-05 | +| loss | -0.0283 | +| n_updates | 16708 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000181 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.261 | +| time/ | | +| fps | 1315 | +| iterations | 224 | +| time_elapsed | 348 | +| total_timesteps | 458752 | +| train/ | | +| approx_kl | 0.007956798 | +| clip_fraction | 0.244 | +| clip_range | 0.0749 | +| entropy_loss | -7.78 | +| explained_variance | -0.117 | +| learning_rate | 4.99e-05 | +| loss | -0.0297 | +| n_updates | 16712 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.00018 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.264 | +| time/ | | +| fps | 1315 | +| iterations | 225 | +| time_elapsed | 350 | +| total_timesteps | 460800 | +| train/ | | +| approx_kl | 0.007984996 | +| clip_fraction | 0.247 | +| clip_range | 0.0749 | +| entropy_loss | -7.72 | +| explained_variance | -0.0173 | +| learning_rate | 4.99e-05 | +| loss | -0.0264 | +| n_updates | 16716 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.00016 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.266 | +| time/ | | +| fps | 1315 | +| iterations | 226 | +| time_elapsed | 351 | +| total_timesteps | 462848 | +| train/ | | +| approx_kl | 0.0080184145 | +| clip_fraction | 0.234 | +| clip_range | 0.0749 | +| entropy_loss | -7.55 | +| explained_variance | 0.0201 | +| learning_rate | 4.99e-05 | +| loss | -0.0261 | +| n_updates | 16720 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.00018 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.266 | +| time/ | | +| fps | 1316 | +| iterations | 227 | +| time_elapsed | 353 | +| total_timesteps | 464896 | +| train/ | | +| approx_kl | 0.007086088 | +| clip_fraction | 0.252 | +| clip_range | 0.0749 | +| entropy_loss | -7.61 | +| explained_variance | 0.0185 | +| learning_rate | 4.99e-05 | +| loss | -0.0262 | +| n_updates | 16724 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000266 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.26 | +| time/ | | +| fps | 1316 | +| iterations | 228 | +| time_elapsed | 354 | +| total_timesteps | 466944 | +| train/ | | +| approx_kl | 0.007468422 | +| clip_fraction | 0.234 | +| clip_range | 0.0749 | +| entropy_loss | -7.74 | +| explained_variance | 0.00235 | +| learning_rate | 4.99e-05 | +| loss | -0.0314 | +| n_updates | 16728 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000185 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.257 | +| time/ | | +| fps | 1316 | +| iterations | 229 | +| time_elapsed | 356 | +| total_timesteps | 468992 | +| train/ | | +| approx_kl | 0.008449317 | +| clip_fraction | 0.252 | +| clip_range | 0.0749 | +| entropy_loss | -7.67 | +| explained_variance | -0.214 | +| learning_rate | 4.99e-05 | +| loss | -0.0316 | +| n_updates | 16732 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000142 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.253 | +| time/ | | +| fps | 1316 | +| iterations | 230 | +| time_elapsed | 357 | +| total_timesteps | 471040 | +| train/ | | +| approx_kl | 0.008438649 | +| clip_fraction | 0.234 | +| clip_range | 0.0749 | +| entropy_loss | -7.48 | +| explained_variance | -0.0571 | +| learning_rate | 4.99e-05 | +| loss | -0.0309 | +| n_updates | 16736 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000181 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.25 | +| time/ | | +| fps | 1316 | +| iterations | 231 | +| time_elapsed | 359 | +| total_timesteps | 473088 | +| train/ | | +| approx_kl | 0.0074339667 | +| clip_fraction | 0.251 | +| clip_range | 0.0749 | +| entropy_loss | -7.72 | +| explained_variance | -0.0538 | +| learning_rate | 4.99e-05 | +| loss | -0.0297 | +| n_updates | 16740 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000302 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.252 | +| time/ | | +| fps | 1316 | +| iterations | 232 | +| time_elapsed | 360 | +| total_timesteps | 475136 | +| train/ | | +| approx_kl | 0.0074363006 | +| clip_fraction | 0.25 | +| clip_range | 0.0749 | +| entropy_loss | -7.38 | +| explained_variance | -0.0677 | +| learning_rate | 4.99e-05 | +| loss | -0.0328 | +| n_updates | 16744 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000216 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.258 | +| time/ | | +| fps | 1316 | +| iterations | 233 | +| time_elapsed | 362 | +| total_timesteps | 477184 | +| train/ | | +| approx_kl | 0.0070133447 | +| clip_fraction | 0.235 | +| clip_range | 0.0749 | +| entropy_loss | -7.63 | +| explained_variance | 0.0103 | +| learning_rate | 4.99e-05 | +| loss | -0.0289 | +| n_updates | 16748 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000213 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.259 | +| time/ | | +| fps | 1317 | +| iterations | 234 | +| time_elapsed | 363 | +| total_timesteps | 479232 | +| train/ | | +| approx_kl | 0.00678684 | +| clip_fraction | 0.226 | +| clip_range | 0.0749 | +| entropy_loss | -7.69 | +| explained_variance | 0.0655 | +| learning_rate | 4.99e-05 | +| loss | -0.0253 | +| n_updates | 16752 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000202 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 1317 | +| iterations | 235 | +| time_elapsed | 365 | +| total_timesteps | 481280 | +| train/ | | +| approx_kl | 0.0076073697 | +| clip_fraction | 0.265 | +| clip_range | 0.0749 | +| entropy_loss | -7.69 | +| explained_variance | -0.191 | +| learning_rate | 4.99e-05 | +| loss | -0.0338 | +| n_updates | 16756 | +| policy_gradient_loss | -0.0219 | +| value_loss | 0.000235 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 1317 | +| iterations | 236 | +| time_elapsed | 366 | +| total_timesteps | 483328 | +| train/ | | +| approx_kl | 0.0074073384 | +| clip_fraction | 0.249 | +| clip_range | 0.0749 | +| entropy_loss | -7.38 | +| explained_variance | -0.0266 | +| learning_rate | 4.99e-05 | +| loss | -0.0281 | +| n_updates | 16760 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000427 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 1317 | +| iterations | 237 | +| time_elapsed | 368 | +| total_timesteps | 485376 | +| train/ | | +| approx_kl | 0.0071468763 | +| clip_fraction | 0.263 | +| clip_range | 0.0749 | +| entropy_loss | -7.8 | +| explained_variance | -0.0011 | +| learning_rate | 4.99e-05 | +| loss | -0.0313 | +| n_updates | 16764 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000166 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 1317 | +| iterations | 238 | +| time_elapsed | 369 | +| total_timesteps | 487424 | +| train/ | | +| approx_kl | 0.00782394 | +| clip_fraction | 0.256 | +| clip_range | 0.0749 | +| entropy_loss | -7.66 | +| explained_variance | -0.132 | +| learning_rate | 4.99e-05 | +| loss | -0.0314 | +| n_updates | 16768 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.00015 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.272 | +| time/ | | +| fps | 1317 | +| iterations | 239 | +| time_elapsed | 371 | +| total_timesteps | 489472 | +| train/ | | +| approx_kl | 0.0067863804 | +| clip_fraction | 0.238 | +| clip_range | 0.0749 | +| entropy_loss | -7.61 | +| explained_variance | -0.00291 | +| learning_rate | 4.99e-05 | +| loss | -0.0281 | +| n_updates | 16772 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.00031 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.27 | +| time/ | | +| fps | 1318 | +| iterations | 240 | +| time_elapsed | 372 | +| total_timesteps | 491520 | +| train/ | | +| approx_kl | 0.0074650794 | +| clip_fraction | 0.253 | +| clip_range | 0.0749 | +| entropy_loss | -7.67 | +| explained_variance | -0.241 | +| learning_rate | 4.99e-05 | +| loss | -0.0352 | +| n_updates | 16776 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000121 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.267 | +| time/ | | +| fps | 1318 | +| iterations | 241 | +| time_elapsed | 374 | +| total_timesteps | 493568 | +| train/ | | +| approx_kl | 0.007664778 | +| clip_fraction | 0.251 | +| clip_range | 0.0749 | +| entropy_loss | -7.46 | +| explained_variance | -0.0762 | +| learning_rate | 4.99e-05 | +| loss | -0.0346 | +| n_updates | 16780 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000135 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.274 | +| time/ | | +| fps | 1318 | +| iterations | 242 | +| time_elapsed | 375 | +| total_timesteps | 495616 | +| train/ | | +| approx_kl | 0.007598155 | +| clip_fraction | 0.268 | +| clip_range | 0.0749 | +| entropy_loss | -7.6 | +| explained_variance | -0.0148 | +| learning_rate | 4.99e-05 | +| loss | -0.0272 | +| n_updates | 16784 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000234 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.269 | +| time/ | | +| fps | 1318 | +| iterations | 243 | +| time_elapsed | 377 | +| total_timesteps | 497664 | +| train/ | | +| approx_kl | 0.0071392604 | +| clip_fraction | 0.245 | +| clip_range | 0.0749 | +| entropy_loss | -7.69 | +| explained_variance | -0.00152 | +| learning_rate | 4.99e-05 | +| loss | -0.0317 | +| n_updates | 16788 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000239 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.268 | +| time/ | | +| fps | 1318 | +| iterations | 244 | +| time_elapsed | 379 | +| total_timesteps | 499712 | +| train/ | | +| approx_kl | 0.006650418 | +| clip_fraction | 0.24 | +| clip_range | 0.0749 | +| entropy_loss | -7.68 | +| explained_variance | -0.0268 | +| learning_rate | 4.99e-05 | +| loss | -0.0296 | +| n_updates | 16792 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.00023 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.264 | +| time/ | | +| fps | 1318 | +| iterations | 245 | +| time_elapsed | 380 | +| total_timesteps | 501760 | +| train/ | | +| approx_kl | 0.008430552 | +| clip_fraction | 0.278 | +| clip_range | 0.0749 | +| entropy_loss | -7.57 | +| explained_variance | -0.00418 | +| learning_rate | 4.99e-05 | +| loss | -0.0329 | +| n_updates | 16796 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000169 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.264 | +| time/ | | +| fps | 1318 | +| iterations | 246 | +| time_elapsed | 382 | +| total_timesteps | 503808 | +| train/ | | +| approx_kl | 0.007492379 | +| clip_fraction | 0.26 | +| clip_range | 0.0749 | +| entropy_loss | -7.76 | +| explained_variance | -0.13 | +| learning_rate | 4.99e-05 | +| loss | -0.0307 | +| n_updates | 16800 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000159 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.266 | +| time/ | | +| fps | 1318 | +| iterations | 247 | +| time_elapsed | 383 | +| total_timesteps | 505856 | +| train/ | | +| approx_kl | 0.008064314 | +| clip_fraction | 0.275 | +| clip_range | 0.0749 | +| entropy_loss | -7.69 | +| explained_variance | -0.137 | +| learning_rate | 4.99e-05 | +| loss | -0.032 | +| n_updates | 16804 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.00013 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.268 | +| time/ | | +| fps | 1318 | +| iterations | 248 | +| time_elapsed | 385 | +| total_timesteps | 507904 | +| train/ | | +| approx_kl | 0.008300534 | +| clip_fraction | 0.258 | +| clip_range | 0.0749 | +| entropy_loss | -7.59 | +| explained_variance | 0.00125 | +| learning_rate | 4.99e-05 | +| loss | -0.0226 | +| n_updates | 16808 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000339 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.273 | +| time/ | | +| fps | 1318 | +| iterations | 249 | +| time_elapsed | 386 | +| total_timesteps | 509952 | +| train/ | | +| approx_kl | 0.007682386 | +| clip_fraction | 0.248 | +| clip_range | 0.0749 | +| entropy_loss | -7.54 | +| explained_variance | -0.0781 | +| learning_rate | 4.99e-05 | +| loss | -0.031 | +| n_updates | 16812 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000241 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.273 | +| time/ | | +| fps | 1318 | +| iterations | 250 | +| time_elapsed | 388 | +| total_timesteps | 512000 | +| train/ | | +| approx_kl | 0.0072897496 | +| clip_fraction | 0.233 | +| clip_range | 0.0749 | +| entropy_loss | -7.58 | +| explained_variance | -0.103 | +| learning_rate | 4.99e-05 | +| loss | -0.0323 | +| n_updates | 16816 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000322 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.277 | +| time/ | | +| fps | 1318 | +| iterations | 251 | +| time_elapsed | 389 | +| total_timesteps | 514048 | +| train/ | | +| approx_kl | 0.009361647 | +| clip_fraction | 0.28 | +| clip_range | 0.0749 | +| entropy_loss | -7.69 | +| explained_variance | -0.219 | +| learning_rate | 4.99e-05 | +| loss | -0.041 | +| n_updates | 16820 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000124 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 1318 | +| iterations | 252 | +| time_elapsed | 391 | +| total_timesteps | 516096 | +| train/ | | +| approx_kl | 0.0074216817 | +| clip_fraction | 0.263 | +| clip_range | 0.0749 | +| entropy_loss | -7.63 | +| explained_variance | -0.0848 | +| learning_rate | 4.99e-05 | +| loss | -0.031 | +| n_updates | 16824 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000161 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 1318 | +| iterations | 253 | +| time_elapsed | 392 | +| total_timesteps | 518144 | +| train/ | | +| approx_kl | 0.007925937 | +| clip_fraction | 0.242 | +| clip_range | 0.0749 | +| entropy_loss | -7.69 | +| explained_variance | -0.0583 | +| learning_rate | 4.99e-05 | +| loss | -0.0381 | +| n_updates | 16828 | +| policy_gradient_loss | -0.0206 | +| value_loss | 9.64e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.272 | +| time/ | | +| fps | 1318 | +| iterations | 254 | +| time_elapsed | 394 | +| total_timesteps | 520192 | +| train/ | | +| approx_kl | 0.007881256 | +| clip_fraction | 0.249 | +| clip_range | 0.0749 | +| entropy_loss | -7.58 | +| explained_variance | -0.00432 | +| learning_rate | 4.99e-05 | +| loss | -0.0349 | +| n_updates | 16832 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000164 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.276 | +| time/ | | +| fps | 1318 | +| iterations | 255 | +| time_elapsed | 395 | +| total_timesteps | 522240 | +| train/ | | +| approx_kl | 0.008066136 | +| clip_fraction | 0.276 | +| clip_range | 0.0749 | +| entropy_loss | -7.68 | +| explained_variance | -0.0269 | +| learning_rate | 4.99e-05 | +| loss | -0.0366 | +| n_updates | 16836 | +| policy_gradient_loss | -0.022 | +| value_loss | 0.000103 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.276 | +| time/ | | +| fps | 1318 | +| iterations | 256 | +| time_elapsed | 397 | +| total_timesteps | 524288 | +| train/ | | +| approx_kl | 0.008517733 | +| clip_fraction | 0.25 | +| clip_range | 0.0749 | +| entropy_loss | -7.53 | +| explained_variance | -0.0324 | +| learning_rate | 4.99e-05 | +| loss | -0.0301 | +| n_updates | 16840 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000282 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.276 | +| time/ | | +| fps | 1319 | +| iterations | 257 | +| time_elapsed | 399 | +| total_timesteps | 526336 | +| train/ | | +| approx_kl | 0.008502013 | +| clip_fraction | 0.257 | +| clip_range | 0.0749 | +| entropy_loss | -7.77 | +| explained_variance | -0.0064 | +| learning_rate | 4.99e-05 | +| loss | -0.0364 | +| n_updates | 16844 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000172 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.276 | +| time/ | | +| fps | 1319 | +| iterations | 258 | +| time_elapsed | 400 | +| total_timesteps | 528384 | +| train/ | | +| approx_kl | 0.0076345876 | +| clip_fraction | 0.261 | +| clip_range | 0.0749 | +| entropy_loss | -7.82 | +| explained_variance | -0.179 | +| learning_rate | 4.99e-05 | +| loss | -0.0376 | +| n_updates | 16848 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000123 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.276 | +| time/ | | +| fps | 1319 | +| iterations | 259 | +| time_elapsed | 402 | +| total_timesteps | 530432 | +| train/ | | +| approx_kl | 0.007868178 | +| clip_fraction | 0.26 | +| clip_range | 0.0749 | +| entropy_loss | -7.8 | +| explained_variance | -0.132 | +| learning_rate | 4.99e-05 | +| loss | -0.0392 | +| n_updates | 16852 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000143 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 1319 | +| iterations | 260 | +| time_elapsed | 403 | +| total_timesteps | 532480 | +| train/ | | +| approx_kl | 0.0071949987 | +| clip_fraction | 0.237 | +| clip_range | 0.0749 | +| entropy_loss | -7.81 | +| explained_variance | -0.0492 | +| learning_rate | 4.99e-05 | +| loss | -0.0326 | +| n_updates | 16856 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.00022 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 1319 | +| iterations | 261 | +| time_elapsed | 405 | +| total_timesteps | 534528 | +| train/ | | +| approx_kl | 0.006510834 | +| clip_fraction | 0.225 | +| clip_range | 0.0749 | +| entropy_loss | -7.57 | +| explained_variance | -0.0355 | +| learning_rate | 4.99e-05 | +| loss | -0.0297 | +| n_updates | 16860 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000169 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 1319 | +| iterations | 262 | +| time_elapsed | 406 | +| total_timesteps | 536576 | +| train/ | | +| approx_kl | 0.008296996 | +| clip_fraction | 0.253 | +| clip_range | 0.0749 | +| entropy_loss | -7.54 | +| explained_variance | -0.0308 | +| learning_rate | 4.99e-05 | +| loss | -0.0284 | +| n_updates | 16864 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000311 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 1319 | +| iterations | 263 | +| time_elapsed | 408 | +| total_timesteps | 538624 | +| train/ | | +| approx_kl | 0.008361198 | +| clip_fraction | 0.268 | +| clip_range | 0.0749 | +| entropy_loss | -7.72 | +| explained_variance | -0.137 | +| learning_rate | 4.99e-05 | +| loss | -0.038 | +| n_updates | 16868 | +| policy_gradient_loss | -0.022 | +| value_loss | 9.55e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 1319 | +| iterations | 264 | +| time_elapsed | 409 | +| total_timesteps | 540672 | +| train/ | | +| approx_kl | 0.009044735 | +| clip_fraction | 0.288 | +| clip_range | 0.0749 | +| entropy_loss | -7.24 | +| explained_variance | -0.0928 | +| learning_rate | 4.99e-05 | +| loss | -0.0319 | +| n_updates | 16872 | +| policy_gradient_loss | -0.0223 | +| value_loss | 0.000178 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 1319 | +| iterations | 265 | +| time_elapsed | 411 | +| total_timesteps | 542720 | +| train/ | | +| approx_kl | 0.008629546 | +| clip_fraction | 0.273 | +| clip_range | 0.0749 | +| entropy_loss | -7.7 | +| explained_variance | -0.132 | +| learning_rate | 4.99e-05 | +| loss | -0.0349 | +| n_updates | 16876 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000125 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1319 | +| iterations | 266 | +| time_elapsed | 412 | +| total_timesteps | 544768 | +| train/ | | +| approx_kl | 0.007607227 | +| clip_fraction | 0.247 | +| clip_range | 0.0749 | +| entropy_loss | -7.63 | +| explained_variance | -0.0783 | +| learning_rate | 4.99e-05 | +| loss | -0.0309 | +| n_updates | 16880 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000199 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1319 | +| iterations | 267 | +| time_elapsed | 414 | +| total_timesteps | 546816 | +| train/ | | +| approx_kl | 0.008032555 | +| clip_fraction | 0.269 | +| clip_range | 0.0749 | +| entropy_loss | -7.59 | +| explained_variance | -0.000292 | +| learning_rate | 4.99e-05 | +| loss | -0.0249 | +| n_updates | 16884 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000272 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 1319 | +| iterations | 268 | +| time_elapsed | 415 | +| total_timesteps | 548864 | +| train/ | | +| approx_kl | 0.008181648 | +| clip_fraction | 0.256 | +| clip_range | 0.0749 | +| entropy_loss | -7.79 | +| explained_variance | -0.0707 | +| learning_rate | 4.99e-05 | +| loss | -0.0338 | +| n_updates | 16888 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000143 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 1319 | +| iterations | 269 | +| time_elapsed | 417 | +| total_timesteps | 550912 | +| train/ | | +| approx_kl | 0.009483152 | +| clip_fraction | 0.274 | +| clip_range | 0.0749 | +| entropy_loss | -7.7 | +| explained_variance | -0.109 | +| learning_rate | 4.99e-05 | +| loss | -0.0343 | +| n_updates | 16892 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000139 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1320 | +| iterations | 270 | +| time_elapsed | 418 | +| total_timesteps | 552960 | +| train/ | | +| approx_kl | 0.007792551 | +| clip_fraction | 0.241 | +| clip_range | 0.0749 | +| entropy_loss | -7.8 | +| explained_variance | -0.036 | +| learning_rate | 4.99e-05 | +| loss | -0.0318 | +| n_updates | 16896 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.00015 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 1320 | +| iterations | 271 | +| time_elapsed | 420 | +| total_timesteps | 555008 | +| train/ | | +| approx_kl | 0.007970387 | +| clip_fraction | 0.251 | +| clip_range | 0.0749 | +| entropy_loss | -7.72 | +| explained_variance | -0.0751 | +| learning_rate | 4.99e-05 | +| loss | -0.0359 | +| n_updates | 16900 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000145 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1320 | +| iterations | 272 | +| time_elapsed | 421 | +| total_timesteps | 557056 | +| train/ | | +| approx_kl | 0.0074109943 | +| clip_fraction | 0.243 | +| clip_range | 0.0749 | +| entropy_loss | -7.61 | +| explained_variance | 0.0331 | +| learning_rate | 4.99e-05 | +| loss | -0.0367 | +| n_updates | 16904 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000185 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.304 | +| time/ | | +| fps | 1320 | +| iterations | 273 | +| time_elapsed | 423 | +| total_timesteps | 559104 | +| train/ | | +| approx_kl | 0.0076105553 | +| clip_fraction | 0.235 | +| clip_range | 0.0749 | +| entropy_loss | -7.45 | +| explained_variance | 0.0594 | +| learning_rate | 4.99e-05 | +| loss | -0.03 | +| n_updates | 16908 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000191 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 1320 | +| iterations | 274 | +| time_elapsed | 424 | +| total_timesteps | 561152 | +| train/ | | +| approx_kl | 0.0076588807 | +| clip_fraction | 0.267 | +| clip_range | 0.0749 | +| entropy_loss | -7.55 | +| explained_variance | -0.0233 | +| learning_rate | 4.99e-05 | +| loss | -0.0378 | +| n_updates | 16912 | +| policy_gradient_loss | -0.0228 | +| value_loss | 0.000133 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 1320 | +| iterations | 275 | +| time_elapsed | 426 | +| total_timesteps | 563200 | +| train/ | | +| approx_kl | 0.008786707 | +| clip_fraction | 0.268 | +| clip_range | 0.0749 | +| entropy_loss | -7.61 | +| explained_variance | -0.228 | +| learning_rate | 4.99e-05 | +| loss | -0.0348 | +| n_updates | 16916 | +| policy_gradient_loss | -0.0218 | +| value_loss | 9.12e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 1320 | +| iterations | 276 | +| time_elapsed | 427 | +| total_timesteps | 565248 | +| train/ | | +| approx_kl | 0.007317426 | +| clip_fraction | 0.272 | +| clip_range | 0.0749 | +| entropy_loss | -7.66 | +| explained_variance | -0.0782 | +| learning_rate | 4.99e-05 | +| loss | -0.0351 | +| n_updates | 16920 | +| policy_gradient_loss | -0.023 | +| value_loss | 0.000115 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 1321 | +| iterations | 277 | +| time_elapsed | 429 | +| total_timesteps | 567296 | +| train/ | | +| approx_kl | 0.007601808 | +| clip_fraction | 0.27 | +| clip_range | 0.0749 | +| entropy_loss | -7.61 | +| explained_variance | -0.199 | +| learning_rate | 4.99e-05 | +| loss | -0.0345 | +| n_updates | 16924 | +| policy_gradient_loss | -0.0219 | +| value_loss | 6.48e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.295 | +| time/ | | +| fps | 1321 | +| iterations | 278 | +| time_elapsed | 430 | +| total_timesteps | 569344 | +| train/ | | +| approx_kl | 0.0073600914 | +| clip_fraction | 0.258 | +| clip_range | 0.0749 | +| entropy_loss | -7.73 | +| explained_variance | -0.0425 | +| learning_rate | 4.99e-05 | +| loss | -0.039 | +| n_updates | 16928 | +| policy_gradient_loss | -0.0199 | +| value_loss | 8.25e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 1321 | +| iterations | 279 | +| time_elapsed | 432 | +| total_timesteps | 571392 | +| train/ | | +| approx_kl | 0.006684323 | +| clip_fraction | 0.212 | +| clip_range | 0.0749 | +| entropy_loss | -7.59 | +| explained_variance | 0.00811 | +| learning_rate | 4.99e-05 | +| loss | -0.0288 | +| n_updates | 16932 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000231 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.29 | +| time/ | | +| fps | 1321 | +| iterations | 280 | +| time_elapsed | 434 | +| total_timesteps | 573440 | +| train/ | | +| approx_kl | 0.0068418025 | +| clip_fraction | 0.252 | +| clip_range | 0.0749 | +| entropy_loss | -7.46 | +| explained_variance | 0.0665 | +| learning_rate | 4.99e-05 | +| loss | -0.0298 | +| n_updates | 16936 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000308 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.288 | +| time/ | | +| fps | 1321 | +| iterations | 281 | +| time_elapsed | 435 | +| total_timesteps | 575488 | +| train/ | | +| approx_kl | 0.0072975466 | +| clip_fraction | 0.261 | +| clip_range | 0.0749 | +| entropy_loss | -7.53 | +| explained_variance | -0.356 | +| learning_rate | 4.99e-05 | +| loss | -0.0376 | +| n_updates | 16940 | +| policy_gradient_loss | -0.0228 | +| value_loss | 0.000105 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.285 | +| time/ | | +| fps | 1321 | +| iterations | 282 | +| time_elapsed | 437 | +| total_timesteps | 577536 | +| train/ | | +| approx_kl | 0.007860256 | +| clip_fraction | 0.263 | +| clip_range | 0.0749 | +| entropy_loss | -7.59 | +| explained_variance | -0.0395 | +| learning_rate | 4.99e-05 | +| loss | -0.0363 | +| n_updates | 16944 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000194 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.285 | +| time/ | | +| fps | 1321 | +| iterations | 283 | +| time_elapsed | 438 | +| total_timesteps | 579584 | +| train/ | | +| approx_kl | 0.0069842655 | +| clip_fraction | 0.241 | +| clip_range | 0.0749 | +| entropy_loss | -7.52 | +| explained_variance | 0.0261 | +| learning_rate | 4.99e-05 | +| loss | -0.0327 | +| n_updates | 16948 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000312 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.283 | +| time/ | | +| fps | 1321 | +| iterations | 284 | +| time_elapsed | 440 | +| total_timesteps | 581632 | +| train/ | | +| approx_kl | 0.0073692994 | +| clip_fraction | 0.247 | +| clip_range | 0.0749 | +| entropy_loss | -7.78 | +| explained_variance | -0.17 | +| learning_rate | 4.99e-05 | +| loss | -0.037 | +| n_updates | 16952 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000262 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.283 | +| time/ | | +| fps | 1321 | +| iterations | 285 | +| time_elapsed | 441 | +| total_timesteps | 583680 | +| train/ | | +| approx_kl | 0.008142951 | +| clip_fraction | 0.263 | +| clip_range | 0.0749 | +| entropy_loss | -7.46 | +| explained_variance | 0.00589 | +| learning_rate | 4.99e-05 | +| loss | -0.0313 | +| n_updates | 16956 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.00027 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.283 | +| time/ | | +| fps | 1321 | +| iterations | 286 | +| time_elapsed | 443 | +| total_timesteps | 585728 | +| train/ | | +| approx_kl | 0.007826375 | +| clip_fraction | 0.255 | +| clip_range | 0.0749 | +| entropy_loss | -7.66 | +| explained_variance | -0.0169 | +| learning_rate | 4.99e-05 | +| loss | -0.0376 | +| n_updates | 16960 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000186 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.287 | +| time/ | | +| fps | 1321 | +| iterations | 287 | +| time_elapsed | 444 | +| total_timesteps | 587776 | +| train/ | | +| approx_kl | 0.0070579234 | +| clip_fraction | 0.242 | +| clip_range | 0.0749 | +| entropy_loss | -7.69 | +| explained_variance | -0.127 | +| learning_rate | 4.99e-05 | +| loss | -0.0338 | +| n_updates | 16964 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000219 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 1321 | +| iterations | 288 | +| time_elapsed | 446 | +| total_timesteps | 589824 | +| train/ | | +| approx_kl | 0.00804936 | +| clip_fraction | 0.258 | +| clip_range | 0.0749 | +| entropy_loss | -7.58 | +| explained_variance | -0.0817 | +| learning_rate | 4.99e-05 | +| loss | -0.0316 | +| n_updates | 16968 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000167 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.278 | +| time/ | | +| fps | 1321 | +| iterations | 289 | +| time_elapsed | 447 | +| total_timesteps | 591872 | +| train/ | | +| approx_kl | 0.007876528 | +| clip_fraction | 0.253 | +| clip_range | 0.0749 | +| entropy_loss | -7.58 | +| explained_variance | -0.0407 | +| learning_rate | 4.99e-05 | +| loss | -0.031 | +| n_updates | 16972 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000196 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.285 | +| time/ | | +| fps | 1321 | +| iterations | 290 | +| time_elapsed | 449 | +| total_timesteps | 593920 | +| train/ | | +| approx_kl | 0.009191195 | +| clip_fraction | 0.268 | +| clip_range | 0.0749 | +| entropy_loss | -7.6 | +| explained_variance | -0.203 | +| learning_rate | 4.99e-05 | +| loss | -0.0317 | +| n_updates | 16976 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000148 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 1321 | +| iterations | 291 | +| time_elapsed | 450 | +| total_timesteps | 595968 | +| train/ | | +| approx_kl | 0.008706795 | +| clip_fraction | 0.27 | +| clip_range | 0.0749 | +| entropy_loss | -7.57 | +| explained_variance | -0.0359 | +| learning_rate | 4.99e-05 | +| loss | -0.0315 | +| n_updates | 16980 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000257 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 1322 | +| iterations | 292 | +| time_elapsed | 452 | +| total_timesteps | 598016 | +| train/ | | +| approx_kl | 0.009347489 | +| clip_fraction | 0.246 | +| clip_range | 0.0749 | +| entropy_loss | -7.47 | +| explained_variance | 0.00951 | +| learning_rate | 4.99e-05 | +| loss | -0.0344 | +| n_updates | 16984 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000364 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.291 | +| time/ | | +| fps | 1322 | +| iterations | 293 | +| time_elapsed | 453 | +| total_timesteps | 600064 | +| train/ | | +| approx_kl | 0.00809869 | +| clip_fraction | 0.264 | +| clip_range | 0.0749 | +| entropy_loss | -7.72 | +| explained_variance | -0.0962 | +| learning_rate | 4.99e-05 | +| loss | -0.0296 | +| n_updates | 16988 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000185 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.291 | +| time/ | | +| fps | 1322 | +| iterations | 294 | +| time_elapsed | 455 | +| total_timesteps | 602112 | +| train/ | | +| approx_kl | 0.009553842 | +| clip_fraction | 0.277 | +| clip_range | 0.0748 | +| entropy_loss | -7.63 | +| explained_variance | -0.186 | +| learning_rate | 4.99e-05 | +| loss | -0.0422 | +| n_updates | 16992 | +| policy_gradient_loss | -0.0235 | +| value_loss | 0.000114 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.297 | +| time/ | | +| fps | 1322 | +| iterations | 295 | +| time_elapsed | 456 | +| total_timesteps | 604160 | +| train/ | | +| approx_kl | 0.0074005304 | +| clip_fraction | 0.255 | +| clip_range | 0.0748 | +| entropy_loss | -7.71 | +| explained_variance | -0.111 | +| learning_rate | 4.99e-05 | +| loss | -0.0332 | +| n_updates | 16996 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000144 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.297 | +| time/ | | +| fps | 1322 | +| iterations | 296 | +| time_elapsed | 458 | +| total_timesteps | 606208 | +| train/ | | +| approx_kl | 0.008320072 | +| clip_fraction | 0.276 | +| clip_range | 0.0748 | +| entropy_loss | -7.43 | +| explained_variance | 0.021 | +| learning_rate | 4.99e-05 | +| loss | -0.0275 | +| n_updates | 17000 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000285 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.295 | +| time/ | | +| fps | 1322 | +| iterations | 297 | +| time_elapsed | 459 | +| total_timesteps | 608256 | +| train/ | | +| approx_kl | 0.007381788 | +| clip_fraction | 0.246 | +| clip_range | 0.0748 | +| entropy_loss | -7.74 | +| explained_variance | -0.113 | +| learning_rate | 4.99e-05 | +| loss | -0.0323 | +| n_updates | 17004 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.00011 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.292 | +| time/ | | +| fps | 1322 | +| iterations | 298 | +| time_elapsed | 461 | +| total_timesteps | 610304 | +| train/ | | +| approx_kl | 0.008173602 | +| clip_fraction | 0.264 | +| clip_range | 0.0748 | +| entropy_loss | -7.67 | +| explained_variance | 0.0166 | +| learning_rate | 4.99e-05 | +| loss | -0.0337 | +| n_updates | 17008 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000226 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.291 | +| time/ | | +| fps | 1322 | +| iterations | 299 | +| time_elapsed | 463 | +| total_timesteps | 612352 | +| train/ | | +| approx_kl | 0.009247042 | +| clip_fraction | 0.263 | +| clip_range | 0.0748 | +| entropy_loss | -7.68 | +| explained_variance | -0.0679 | +| learning_rate | 4.99e-05 | +| loss | -0.0406 | +| n_updates | 17012 | +| policy_gradient_loss | -0.0214 | +| value_loss | 8.93e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.293 | +| time/ | | +| fps | 1322 | +| iterations | 300 | +| time_elapsed | 464 | +| total_timesteps | 614400 | +| train/ | | +| approx_kl | 0.00824968 | +| clip_fraction | 0.263 | +| clip_range | 0.0748 | +| entropy_loss | -7.56 | +| explained_variance | -0.0814 | +| learning_rate | 4.99e-05 | +| loss | -0.037 | +| n_updates | 17016 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000208 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.293 | +| time/ | | +| fps | 1322 | +| iterations | 301 | +| time_elapsed | 466 | +| total_timesteps | 616448 | +| train/ | | +| approx_kl | 0.007937558 | +| clip_fraction | 0.254 | +| clip_range | 0.0748 | +| entropy_loss | -7.56 | +| explained_variance | -0.124 | +| learning_rate | 4.99e-05 | +| loss | -0.0296 | +| n_updates | 17020 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000238 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.306 | +| time/ | | +| fps | 1322 | +| iterations | 302 | +| time_elapsed | 467 | +| total_timesteps | 618496 | +| train/ | | +| approx_kl | 0.008302217 | +| clip_fraction | 0.266 | +| clip_range | 0.0748 | +| entropy_loss | -7.65 | +| explained_variance | 0.000494 | +| learning_rate | 4.99e-05 | +| loss | -0.0375 | +| n_updates | 17024 | +| policy_gradient_loss | -0.0223 | +| value_loss | 0.000196 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 1322 | +| iterations | 303 | +| time_elapsed | 469 | +| total_timesteps | 620544 | +| train/ | | +| approx_kl | 0.007691238 | +| clip_fraction | 0.247 | +| clip_range | 0.0748 | +| entropy_loss | -7.37 | +| explained_variance | 0.132 | +| learning_rate | 4.99e-05 | +| loss | -0.0327 | +| n_updates | 17028 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000172 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.306 | +| time/ | | +| fps | 1322 | +| iterations | 304 | +| time_elapsed | 470 | +| total_timesteps | 622592 | +| train/ | | +| approx_kl | 0.0085684955 | +| clip_fraction | 0.268 | +| clip_range | 0.0748 | +| entropy_loss | -7.49 | +| explained_variance | -0.106 | +| learning_rate | 4.99e-05 | +| loss | -0.0334 | +| n_updates | 17032 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000166 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1322 | +| iterations | 305 | +| time_elapsed | 472 | +| total_timesteps | 624640 | +| train/ | | +| approx_kl | 0.008908598 | +| clip_fraction | 0.268 | +| clip_range | 0.0748 | +| entropy_loss | -7.67 | +| explained_variance | -0.0608 | +| learning_rate | 4.99e-05 | +| loss | -0.0348 | +| n_updates | 17036 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000257 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.302 | +| time/ | | +| fps | 1322 | +| iterations | 306 | +| time_elapsed | 473 | +| total_timesteps | 626688 | +| train/ | | +| approx_kl | 0.008892473 | +| clip_fraction | 0.255 | +| clip_range | 0.0748 | +| entropy_loss | -7.69 | +| explained_variance | -0.1 | +| learning_rate | 4.99e-05 | +| loss | -0.0355 | +| n_updates | 17040 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.00012 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 1322 | +| iterations | 307 | +| time_elapsed | 475 | +| total_timesteps | 628736 | +| train/ | | +| approx_kl | 0.0069596535 | +| clip_fraction | 0.253 | +| clip_range | 0.0748 | +| entropy_loss | -7.53 | +| explained_variance | -0.0112 | +| learning_rate | 4.99e-05 | +| loss | -0.0334 | +| n_updates | 17044 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000172 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 1322 | +| iterations | 308 | +| time_elapsed | 476 | +| total_timesteps | 630784 | +| train/ | | +| approx_kl | 0.007197789 | +| clip_fraction | 0.235 | +| clip_range | 0.0748 | +| entropy_loss | -7.52 | +| explained_variance | -0.01 | +| learning_rate | 4.99e-05 | +| loss | -0.0294 | +| n_updates | 17048 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000289 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1322 | +| iterations | 309 | +| time_elapsed | 478 | +| total_timesteps | 632832 | +| train/ | | +| approx_kl | 0.0088002365 | +| clip_fraction | 0.264 | +| clip_range | 0.0748 | +| entropy_loss | -7.58 | +| explained_variance | -0.0661 | +| learning_rate | 4.99e-05 | +| loss | -0.0352 | +| n_updates | 17052 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000161 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1323 | +| iterations | 310 | +| time_elapsed | 479 | +| total_timesteps | 634880 | +| train/ | | +| approx_kl | 0.007902606 | +| clip_fraction | 0.248 | +| clip_range | 0.0748 | +| entropy_loss | -7.64 | +| explained_variance | 0.00493 | +| learning_rate | 4.98e-05 | +| loss | -0.0319 | +| n_updates | 17056 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.00023 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1322 | +| iterations | 311 | +| time_elapsed | 481 | +| total_timesteps | 636928 | +| train/ | | +| approx_kl | 0.007454823 | +| clip_fraction | 0.271 | +| clip_range | 0.0748 | +| entropy_loss | -7.64 | +| explained_variance | -0.26 | +| learning_rate | 4.98e-05 | +| loss | -0.0362 | +| n_updates | 17060 | +| policy_gradient_loss | -0.0228 | +| value_loss | 8.21e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.3 | +| time/ | | +| fps | 1322 | +| iterations | 312 | +| time_elapsed | 483 | +| total_timesteps | 638976 | +| train/ | | +| approx_kl | 0.008494038 | +| clip_fraction | 0.272 | +| clip_range | 0.0748 | +| entropy_loss | -7.67 | +| explained_variance | -0.144 | +| learning_rate | 4.98e-05 | +| loss | -0.0373 | +| n_updates | 17064 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000114 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.292 | +| time/ | | +| fps | 1322 | +| iterations | 313 | +| time_elapsed | 484 | +| total_timesteps | 641024 | +| train/ | | +| approx_kl | 0.0072242483 | +| clip_fraction | 0.255 | +| clip_range | 0.0748 | +| entropy_loss | -7.65 | +| explained_variance | -0.0261 | +| learning_rate | 4.98e-05 | +| loss | -0.0316 | +| n_updates | 17068 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000153 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.292 | +| time/ | | +| fps | 1322 | +| iterations | 314 | +| time_elapsed | 486 | +| total_timesteps | 643072 | +| train/ | | +| approx_kl | 0.009101013 | +| clip_fraction | 0.265 | +| clip_range | 0.0748 | +| entropy_loss | -7.58 | +| explained_variance | 0.0129 | +| learning_rate | 4.98e-05 | +| loss | -0.0374 | +| n_updates | 17072 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000125 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.293 | +| time/ | | +| fps | 1322 | +| iterations | 315 | +| time_elapsed | 487 | +| total_timesteps | 645120 | +| train/ | | +| approx_kl | 0.007841706 | +| clip_fraction | 0.256 | +| clip_range | 0.0748 | +| entropy_loss | -7.5 | +| explained_variance | 0.065 | +| learning_rate | 4.98e-05 | +| loss | -0.03 | +| n_updates | 17076 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000179 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 1322 | +| iterations | 316 | +| time_elapsed | 489 | +| total_timesteps | 647168 | +| train/ | | +| approx_kl | 0.007765009 | +| clip_fraction | 0.244 | +| clip_range | 0.0748 | +| entropy_loss | -7.54 | +| explained_variance | 0.117 | +| learning_rate | 4.98e-05 | +| loss | -0.0333 | +| n_updates | 17080 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000171 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.3 | +| time/ | | +| fps | 1322 | +| iterations | 317 | +| time_elapsed | 490 | +| total_timesteps | 649216 | +| train/ | | +| approx_kl | 0.008680295 | +| clip_fraction | 0.267 | +| clip_range | 0.0748 | +| entropy_loss | -7.38 | +| explained_variance | 0.0326 | +| learning_rate | 4.98e-05 | +| loss | -0.0362 | +| n_updates | 17084 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000168 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.3 | +| time/ | | +| fps | 1322 | +| iterations | 318 | +| time_elapsed | 492 | +| total_timesteps | 651264 | +| train/ | | +| approx_kl | 0.007942578 | +| clip_fraction | 0.256 | +| clip_range | 0.0748 | +| entropy_loss | -7.59 | +| explained_variance | -0.133 | +| learning_rate | 4.98e-05 | +| loss | -0.033 | +| n_updates | 17088 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000241 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.3 | +| time/ | | +| fps | 1322 | +| iterations | 319 | +| time_elapsed | 493 | +| total_timesteps | 653312 | +| train/ | | +| approx_kl | 0.008467798 | +| clip_fraction | 0.258 | +| clip_range | 0.0748 | +| entropy_loss | -7.7 | +| explained_variance | 0.0065 | +| learning_rate | 4.98e-05 | +| loss | -0.0336 | +| n_updates | 17092 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000187 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 1323 | +| iterations | 320 | +| time_elapsed | 495 | +| total_timesteps | 655360 | +| train/ | | +| approx_kl | 0.00855802 | +| clip_fraction | 0.259 | +| clip_range | 0.0748 | +| entropy_loss | -7.71 | +| explained_variance | -0.159 | +| learning_rate | 4.98e-05 | +| loss | -0.0325 | +| n_updates | 17096 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.00012 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.297 | +| time/ | | +| fps | 1323 | +| iterations | 321 | +| time_elapsed | 496 | +| total_timesteps | 657408 | +| train/ | | +| approx_kl | 0.007533862 | +| clip_fraction | 0.265 | +| clip_range | 0.0748 | +| entropy_loss | -7.73 | +| explained_variance | -0.216 | +| learning_rate | 4.98e-05 | +| loss | -0.0326 | +| n_updates | 17100 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000159 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 1323 | +| iterations | 322 | +| time_elapsed | 498 | +| total_timesteps | 659456 | +| train/ | | +| approx_kl | 0.008116765 | +| clip_fraction | 0.26 | +| clip_range | 0.0748 | +| entropy_loss | -7.57 | +| explained_variance | -0.0591 | +| learning_rate | 4.98e-05 | +| loss | -0.0365 | +| n_updates | 17104 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.00011 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.295 | +| time/ | | +| fps | 1323 | +| iterations | 323 | +| time_elapsed | 499 | +| total_timesteps | 661504 | +| train/ | | +| approx_kl | 0.007257079 | +| clip_fraction | 0.264 | +| clip_range | 0.0748 | +| entropy_loss | -7.64 | +| explained_variance | -0.0522 | +| learning_rate | 4.98e-05 | +| loss | -0.0293 | +| n_updates | 17108 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000265 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.289 | +| time/ | | +| fps | 1323 | +| iterations | 324 | +| time_elapsed | 501 | +| total_timesteps | 663552 | +| train/ | | +| approx_kl | 0.0073866015 | +| clip_fraction | 0.238 | +| clip_range | 0.0748 | +| entropy_loss | -7.47 | +| explained_variance | -0.0534 | +| learning_rate | 4.98e-05 | +| loss | -0.0316 | +| n_updates | 17112 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000167 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.297 | +| time/ | | +| fps | 1323 | +| iterations | 325 | +| time_elapsed | 502 | +| total_timesteps | 665600 | +| train/ | | +| approx_kl | 0.008588292 | +| clip_fraction | 0.281 | +| clip_range | 0.0748 | +| entropy_loss | -7.49 | +| explained_variance | 0.0756 | +| learning_rate | 4.98e-05 | +| loss | -0.0353 | +| n_updates | 17116 | +| policy_gradient_loss | -0.0229 | +| value_loss | 8.87e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.297 | +| time/ | | +| fps | 1323 | +| iterations | 326 | +| time_elapsed | 504 | +| total_timesteps | 667648 | +| train/ | | +| approx_kl | 0.007594801 | +| clip_fraction | 0.238 | +| clip_range | 0.0748 | +| entropy_loss | -7.51 | +| explained_variance | -0.102 | +| learning_rate | 4.98e-05 | +| loss | -0.0281 | +| n_updates | 17120 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000205 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 1323 | +| iterations | 327 | +| time_elapsed | 505 | +| total_timesteps | 669696 | +| train/ | | +| approx_kl | 0.007252354 | +| clip_fraction | 0.219 | +| clip_range | 0.0748 | +| entropy_loss | -7.64 | +| explained_variance | -0.0225 | +| learning_rate | 4.98e-05 | +| loss | -0.0334 | +| n_updates | 17124 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000295 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 1323 | +| iterations | 328 | +| time_elapsed | 507 | +| total_timesteps | 671744 | +| train/ | | +| approx_kl | 0.0091569275 | +| clip_fraction | 0.285 | +| clip_range | 0.0748 | +| entropy_loss | -7.43 | +| explained_variance | 0.0902 | +| learning_rate | 4.98e-05 | +| loss | -0.0336 | +| n_updates | 17128 | +| policy_gradient_loss | -0.0229 | +| value_loss | 0.000162 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 1323 | +| iterations | 329 | +| time_elapsed | 508 | +| total_timesteps | 673792 | +| train/ | | +| approx_kl | 0.008534692 | +| clip_fraction | 0.272 | +| clip_range | 0.0748 | +| entropy_loss | -7.72 | +| explained_variance | -0.0278 | +| learning_rate | 4.98e-05 | +| loss | -0.0399 | +| n_updates | 17132 | +| policy_gradient_loss | -0.0219 | +| value_loss | 0.000224 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.302 | +| time/ | | +| fps | 1323 | +| iterations | 330 | +| time_elapsed | 510 | +| total_timesteps | 675840 | +| train/ | | +| approx_kl | 0.007870342 | +| clip_fraction | 0.283 | +| clip_range | 0.0748 | +| entropy_loss | -7.74 | +| explained_variance | -0.174 | +| learning_rate | 4.98e-05 | +| loss | -0.0403 | +| n_updates | 17136 | +| policy_gradient_loss | -0.0225 | +| value_loss | 0.000146 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 1323 | +| iterations | 331 | +| time_elapsed | 512 | +| total_timesteps | 677888 | +| train/ | | +| approx_kl | 0.007408104 | +| clip_fraction | 0.264 | +| clip_range | 0.0748 | +| entropy_loss | -7.64 | +| explained_variance | 0.0107 | +| learning_rate | 4.98e-05 | +| loss | -0.0306 | +| n_updates | 17140 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000252 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 1324 | +| iterations | 332 | +| time_elapsed | 513 | +| total_timesteps | 679936 | +| train/ | | +| approx_kl | 0.007953036 | +| clip_fraction | 0.243 | +| clip_range | 0.0748 | +| entropy_loss | -7.63 | +| explained_variance | 0.0408 | +| learning_rate | 4.98e-05 | +| loss | -0.0346 | +| n_updates | 17144 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000193 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.302 | +| time/ | | +| fps | 1324 | +| iterations | 333 | +| time_elapsed | 514 | +| total_timesteps | 681984 | +| train/ | | +| approx_kl | 0.008287732 | +| clip_fraction | 0.28 | +| clip_range | 0.0748 | +| entropy_loss | -7.55 | +| explained_variance | -0.186 | +| learning_rate | 4.98e-05 | +| loss | -0.0331 | +| n_updates | 17148 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000133 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.302 | +| time/ | | +| fps | 1324 | +| iterations | 334 | +| time_elapsed | 516 | +| total_timesteps | 684032 | +| train/ | | +| approx_kl | 0.00796408 | +| clip_fraction | 0.285 | +| clip_range | 0.0748 | +| entropy_loss | -7.56 | +| explained_variance | -0.259 | +| learning_rate | 4.98e-05 | +| loss | -0.0397 | +| n_updates | 17152 | +| policy_gradient_loss | -0.0198 | +| value_loss | 6.96e-05 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.304 | +| time/ | | +| fps | 1324 | +| iterations | 335 | +| time_elapsed | 518 | +| total_timesteps | 686080 | +| train/ | | +| approx_kl | 0.00897611 | +| clip_fraction | 0.252 | +| clip_range | 0.0748 | +| entropy_loss | -7.64 | +| explained_variance | -0.0494 | +| learning_rate | 4.98e-05 | +| loss | -0.0351 | +| n_updates | 17156 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000127 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1324 | +| iterations | 336 | +| time_elapsed | 519 | +| total_timesteps | 688128 | +| train/ | | +| approx_kl | 0.008027321 | +| clip_fraction | 0.267 | +| clip_range | 0.0748 | +| entropy_loss | -7.44 | +| explained_variance | -0.0467 | +| learning_rate | 4.98e-05 | +| loss | -0.0352 | +| n_updates | 17160 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000114 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1324 | +| iterations | 337 | +| time_elapsed | 521 | +| total_timesteps | 690176 | +| train/ | | +| approx_kl | 0.008249905 | +| clip_fraction | 0.24 | +| clip_range | 0.0748 | +| entropy_loss | -7.47 | +| explained_variance | -0.0567 | +| learning_rate | 4.98e-05 | +| loss | -0.0272 | +| n_updates | 17164 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000297 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1324 | +| iterations | 338 | +| time_elapsed | 522 | +| total_timesteps | 692224 | +| train/ | | +| approx_kl | 0.007393088 | +| clip_fraction | 0.245 | +| clip_range | 0.0748 | +| entropy_loss | -7.6 | +| explained_variance | -0.0552 | +| learning_rate | 4.98e-05 | +| loss | -0.028 | +| n_updates | 17168 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000167 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1324 | +| iterations | 339 | +| time_elapsed | 524 | +| total_timesteps | 694272 | +| train/ | | +| approx_kl | 0.008177707 | +| clip_fraction | 0.257 | +| clip_range | 0.0748 | +| entropy_loss | -7.65 | +| explained_variance | -0.0115 | +| learning_rate | 4.98e-05 | +| loss | -0.0341 | +| n_updates | 17172 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000158 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1325 | +| iterations | 340 | +| time_elapsed | 525 | +| total_timesteps | 696320 | +| train/ | | +| approx_kl | 0.0077166827 | +| clip_fraction | 0.248 | +| clip_range | 0.0748 | +| entropy_loss | -7.73 | +| explained_variance | -0.079 | +| learning_rate | 4.98e-05 | +| loss | -0.0339 | +| n_updates | 17176 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000161 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1325 | +| iterations | 341 | +| time_elapsed | 526 | +| total_timesteps | 698368 | +| train/ | | +| approx_kl | 0.0076229046 | +| clip_fraction | 0.268 | +| clip_range | 0.0748 | +| entropy_loss | -7.47 | +| explained_variance | -0.0483 | +| learning_rate | 4.98e-05 | +| loss | -0.029 | +| n_updates | 17180 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000155 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1325 | +| iterations | 342 | +| time_elapsed | 528 | +| total_timesteps | 700416 | +| train/ | | +| approx_kl | 0.007649122 | +| clip_fraction | 0.271 | +| clip_range | 0.0748 | +| entropy_loss | -7.56 | +| explained_variance | -0.0446 | +| learning_rate | 4.98e-05 | +| loss | -0.0338 | +| n_updates | 17184 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000111 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1326 | +| iterations | 343 | +| time_elapsed | 529 | +| total_timesteps | 702464 | +| train/ | | +| approx_kl | 0.009629637 | +| clip_fraction | 0.277 | +| clip_range | 0.0748 | +| entropy_loss | -7.72 | +| explained_variance | -0.0857 | +| learning_rate | 4.98e-05 | +| loss | -0.0322 | +| n_updates | 17188 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000186 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1326 | +| iterations | 344 | +| time_elapsed | 531 | +| total_timesteps | 704512 | +| train/ | | +| approx_kl | 0.007758443 | +| clip_fraction | 0.267 | +| clip_range | 0.0748 | +| entropy_loss | -7.75 | +| explained_variance | -0.0376 | +| learning_rate | 4.98e-05 | +| loss | -0.036 | +| n_updates | 17192 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000249 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1326 | +| iterations | 345 | +| time_elapsed | 532 | +| total_timesteps | 706560 | +| train/ | | +| approx_kl | 0.008702869 | +| clip_fraction | 0.281 | +| clip_range | 0.0748 | +| entropy_loss | -7.51 | +| explained_variance | -0.153 | +| learning_rate | 4.98e-05 | +| loss | -0.035 | +| n_updates | 17196 | +| policy_gradient_loss | -0.0219 | +| value_loss | 7.92e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1326 | +| iterations | 346 | +| time_elapsed | 534 | +| total_timesteps | 708608 | +| train/ | | +| approx_kl | 0.007994259 | +| clip_fraction | 0.264 | +| clip_range | 0.0748 | +| entropy_loss | -7.44 | +| explained_variance | -0.0912 | +| learning_rate | 4.98e-05 | +| loss | -0.0347 | +| n_updates | 17200 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000286 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1326 | +| iterations | 347 | +| time_elapsed | 535 | +| total_timesteps | 710656 | +| train/ | | +| approx_kl | 0.007643511 | +| clip_fraction | 0.248 | +| clip_range | 0.0748 | +| entropy_loss | -7.73 | +| explained_variance | -0.0653 | +| learning_rate | 4.98e-05 | +| loss | -0.0336 | +| n_updates | 17204 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000296 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1326 | +| iterations | 348 | +| time_elapsed | 537 | +| total_timesteps | 712704 | +| train/ | | +| approx_kl | 0.00818922 | +| clip_fraction | 0.277 | +| clip_range | 0.0748 | +| entropy_loss | -7.47 | +| explained_variance | 0.0427 | +| learning_rate | 4.98e-05 | +| loss | -0.0333 | +| n_updates | 17208 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000306 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1327 | +| iterations | 349 | +| time_elapsed | 538 | +| total_timesteps | 714752 | +| train/ | | +| approx_kl | 0.009329803 | +| clip_fraction | 0.278 | +| clip_range | 0.0748 | +| entropy_loss | -7.53 | +| explained_variance | -0.233 | +| learning_rate | 4.98e-05 | +| loss | -0.0361 | +| n_updates | 17212 | +| policy_gradient_loss | -0.0223 | +| value_loss | 0.000174 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1327 | +| iterations | 350 | +| time_elapsed | 540 | +| total_timesteps | 716800 | +| train/ | | +| approx_kl | 0.0071518975 | +| clip_fraction | 0.254 | +| clip_range | 0.0748 | +| entropy_loss | -7.66 | +| explained_variance | -0.169 | +| learning_rate | 4.98e-05 | +| loss | -0.0336 | +| n_updates | 17216 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000203 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1327 | +| iterations | 351 | +| time_elapsed | 541 | +| total_timesteps | 718848 | +| train/ | | +| approx_kl | 0.00947194 | +| clip_fraction | 0.284 | +| clip_range | 0.0748 | +| entropy_loss | -7.65 | +| explained_variance | -0.0316 | +| learning_rate | 4.98e-05 | +| loss | -0.0329 | +| n_updates | 17220 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000304 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1327 | +| iterations | 352 | +| time_elapsed | 543 | +| total_timesteps | 720896 | +| train/ | | +| approx_kl | 0.008337912 | +| clip_fraction | 0.225 | +| clip_range | 0.0748 | +| entropy_loss | -7.59 | +| explained_variance | -0.101 | +| learning_rate | 4.98e-05 | +| loss | -0.0334 | +| n_updates | 17224 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000241 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1327 | +| iterations | 353 | +| time_elapsed | 544 | +| total_timesteps | 722944 | +| train/ | | +| approx_kl | 0.008820852 | +| clip_fraction | 0.276 | +| clip_range | 0.0748 | +| entropy_loss | -7.38 | +| explained_variance | -0.162 | +| learning_rate | 4.98e-05 | +| loss | -0.0335 | +| n_updates | 17228 | +| policy_gradient_loss | -0.0221 | +| value_loss | 0.000161 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1327 | +| iterations | 354 | +| time_elapsed | 545 | +| total_timesteps | 724992 | +| train/ | | +| approx_kl | 0.008561175 | +| clip_fraction | 0.275 | +| clip_range | 0.0748 | +| entropy_loss | -7.42 | +| explained_variance | -0.137 | +| learning_rate | 4.98e-05 | +| loss | -0.0282 | +| n_updates | 17232 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000136 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1328 | +| iterations | 355 | +| time_elapsed | 547 | +| total_timesteps | 727040 | +| train/ | | +| approx_kl | 0.008227697 | +| clip_fraction | 0.277 | +| clip_range | 0.0748 | +| entropy_loss | -7.58 | +| explained_variance | -0.148 | +| learning_rate | 4.98e-05 | +| loss | -0.0369 | +| n_updates | 17236 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000124 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1328 | +| iterations | 356 | +| time_elapsed | 548 | +| total_timesteps | 729088 | +| train/ | | +| approx_kl | 0.008659929 | +| clip_fraction | 0.243 | +| clip_range | 0.0748 | +| entropy_loss | -7.64 | +| explained_variance | -0.0885 | +| learning_rate | 4.98e-05 | +| loss | -0.0378 | +| n_updates | 17240 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000157 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1328 | +| iterations | 357 | +| time_elapsed | 550 | +| total_timesteps | 731136 | +| train/ | | +| approx_kl | 0.008025754 | +| clip_fraction | 0.252 | +| clip_range | 0.0748 | +| entropy_loss | -7.57 | +| explained_variance | -0.0905 | +| learning_rate | 4.98e-05 | +| loss | -0.034 | +| n_updates | 17244 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000173 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1328 | +| iterations | 358 | +| time_elapsed | 551 | +| total_timesteps | 733184 | +| train/ | | +| approx_kl | 0.007584292 | +| clip_fraction | 0.246 | +| clip_range | 0.0748 | +| entropy_loss | -7.53 | +| explained_variance | -0.0526 | +| learning_rate | 4.98e-05 | +| loss | -0.0317 | +| n_updates | 17248 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.00015 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1329 | +| iterations | 359 | +| time_elapsed | 553 | +| total_timesteps | 735232 | +| train/ | | +| approx_kl | 0.008318191 | +| clip_fraction | 0.262 | +| clip_range | 0.0748 | +| entropy_loss | -7.52 | +| explained_variance | -0.152 | +| learning_rate | 4.98e-05 | +| loss | -0.0341 | +| n_updates | 17252 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000146 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1329 | +| iterations | 360 | +| time_elapsed | 554 | +| total_timesteps | 737280 | +| train/ | | +| approx_kl | 0.008493071 | +| clip_fraction | 0.243 | +| clip_range | 0.0748 | +| entropy_loss | -7.51 | +| explained_variance | -0.0214 | +| learning_rate | 4.98e-05 | +| loss | -0.0305 | +| n_updates | 17256 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000168 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1329 | +| iterations | 361 | +| time_elapsed | 556 | +| total_timesteps | 739328 | +| train/ | | +| approx_kl | 0.008506751 | +| clip_fraction | 0.261 | +| clip_range | 0.0748 | +| entropy_loss | -7.58 | +| explained_variance | -0.0967 | +| learning_rate | 4.98e-05 | +| loss | -0.0368 | +| n_updates | 17260 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000115 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1329 | +| iterations | 362 | +| time_elapsed | 557 | +| total_timesteps | 741376 | +| train/ | | +| approx_kl | 0.008117782 | +| clip_fraction | 0.265 | +| clip_range | 0.0748 | +| entropy_loss | -7.39 | +| explained_variance | -0.125 | +| learning_rate | 4.98e-05 | +| loss | -0.0373 | +| n_updates | 17264 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000164 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1329 | +| iterations | 363 | +| time_elapsed | 559 | +| total_timesteps | 743424 | +| train/ | | +| approx_kl | 0.0087532485 | +| clip_fraction | 0.275 | +| clip_range | 0.0748 | +| entropy_loss | -7.6 | +| explained_variance | -0.0594 | +| learning_rate | 4.98e-05 | +| loss | -0.0331 | +| n_updates | 17268 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000151 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1329 | +| iterations | 364 | +| time_elapsed | 560 | +| total_timesteps | 745472 | +| train/ | | +| approx_kl | 0.008548998 | +| clip_fraction | 0.288 | +| clip_range | 0.0748 | +| entropy_loss | -7.6 | +| explained_variance | -0.0247 | +| learning_rate | 4.98e-05 | +| loss | -0.0393 | +| n_updates | 17272 | +| policy_gradient_loss | -0.0223 | +| value_loss | 0.000238 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1330 | +| iterations | 365 | +| time_elapsed | 561 | +| total_timesteps | 747520 | +| train/ | | +| approx_kl | 0.008811133 | +| clip_fraction | 0.27 | +| clip_range | 0.0748 | +| entropy_loss | -7.63 | +| explained_variance | -0.0695 | +| learning_rate | 4.98e-05 | +| loss | -0.0317 | +| n_updates | 17276 | +| policy_gradient_loss | -0.0211 | +| value_loss | 8.93e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1330 | +| iterations | 366 | +| time_elapsed | 563 | +| total_timesteps | 749568 | +| train/ | | +| approx_kl | 0.0076521705 | +| clip_fraction | 0.239 | +| clip_range | 0.0748 | +| entropy_loss | -7.51 | +| explained_variance | -0.0269 | +| learning_rate | 4.98e-05 | +| loss | -0.037 | +| n_updates | 17280 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000132 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1330 | +| iterations | 367 | +| time_elapsed | 564 | +| total_timesteps | 751616 | +| train/ | | +| approx_kl | 0.008291064 | +| clip_fraction | 0.252 | +| clip_range | 0.0748 | +| entropy_loss | -7.66 | +| explained_variance | -0.0328 | +| learning_rate | 4.98e-05 | +| loss | -0.0318 | +| n_updates | 17284 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000198 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1330 | +| iterations | 368 | +| time_elapsed | 566 | +| total_timesteps | 753664 | +| train/ | | +| approx_kl | 0.007431126 | +| clip_fraction | 0.257 | +| clip_range | 0.0748 | +| entropy_loss | -7.49 | +| explained_variance | -0.122 | +| learning_rate | 4.98e-05 | +| loss | -0.0362 | +| n_updates | 17288 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000232 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1330 | +| iterations | 369 | +| time_elapsed | 567 | +| total_timesteps | 755712 | +| train/ | | +| approx_kl | 0.008160314 | +| clip_fraction | 0.259 | +| clip_range | 0.0748 | +| entropy_loss | -7.59 | +| explained_variance | -0.132 | +| learning_rate | 4.98e-05 | +| loss | -0.0332 | +| n_updates | 17292 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000175 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1330 | +| iterations | 370 | +| time_elapsed | 569 | +| total_timesteps | 757760 | +| train/ | | +| approx_kl | 0.008718683 | +| clip_fraction | 0.255 | +| clip_range | 0.0748 | +| entropy_loss | -7.62 | +| explained_variance | -0.0159 | +| learning_rate | 4.98e-05 | +| loss | -0.0296 | +| n_updates | 17296 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000191 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1330 | +| iterations | 371 | +| time_elapsed | 570 | +| total_timesteps | 759808 | +| train/ | | +| approx_kl | 0.007688147 | +| clip_fraction | 0.242 | +| clip_range | 0.0748 | +| entropy_loss | -7.53 | +| explained_variance | -0.12 | +| learning_rate | 4.98e-05 | +| loss | -0.0311 | +| n_updates | 17300 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000141 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1330 | +| iterations | 372 | +| time_elapsed | 572 | +| total_timesteps | 761856 | +| train/ | | +| approx_kl | 0.007281883 | +| clip_fraction | 0.256 | +| clip_range | 0.0748 | +| entropy_loss | -7.57 | +| explained_variance | -0.00755 | +| learning_rate | 4.98e-05 | +| loss | -0.0375 | +| n_updates | 17304 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000185 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1330 | +| iterations | 373 | +| time_elapsed | 573 | +| total_timesteps | 763904 | +| train/ | | +| approx_kl | 0.006935753 | +| clip_fraction | 0.23 | +| clip_range | 0.0748 | +| entropy_loss | -7.64 | +| explained_variance | -0.103 | +| learning_rate | 4.98e-05 | +| loss | -0.0311 | +| n_updates | 17308 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000175 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1331 | +| iterations | 374 | +| time_elapsed | 575 | +| total_timesteps | 765952 | +| train/ | | +| approx_kl | 0.0065786624 | +| clip_fraction | 0.224 | +| clip_range | 0.0748 | +| entropy_loss | -7.52 | +| explained_variance | -0.0714 | +| learning_rate | 4.98e-05 | +| loss | -0.0243 | +| n_updates | 17312 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.00026 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1331 | +| iterations | 375 | +| time_elapsed | 576 | +| total_timesteps | 768000 | +| train/ | | +| approx_kl | 0.008686915 | +| clip_fraction | 0.256 | +| clip_range | 0.0748 | +| entropy_loss | -7.49 | +| explained_variance | -0.157 | +| learning_rate | 4.98e-05 | +| loss | -0.035 | +| n_updates | 17316 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000133 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1331 | +| iterations | 376 | +| time_elapsed | 578 | +| total_timesteps | 770048 | +| train/ | | +| approx_kl | 0.0077918367 | +| clip_fraction | 0.268 | +| clip_range | 0.0748 | +| entropy_loss | -7.7 | +| explained_variance | -0.151 | +| learning_rate | 4.98e-05 | +| loss | -0.0331 | +| n_updates | 17320 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000114 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1331 | +| iterations | 377 | +| time_elapsed | 579 | +| total_timesteps | 772096 | +| train/ | | +| approx_kl | 0.0073529053 | +| clip_fraction | 0.257 | +| clip_range | 0.0748 | +| entropy_loss | -7.37 | +| explained_variance | -0.0777 | +| learning_rate | 4.98e-05 | +| loss | -0.0252 | +| n_updates | 17324 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.00016 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1331 | +| iterations | 378 | +| time_elapsed | 581 | +| total_timesteps | 774144 | +| train/ | | +| approx_kl | 0.008473143 | +| clip_fraction | 0.264 | +| clip_range | 0.0748 | +| entropy_loss | -7.66 | +| explained_variance | -0.0717 | +| learning_rate | 4.98e-05 | +| loss | -0.0332 | +| n_updates | 17328 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.00021 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1332 | +| iterations | 379 | +| time_elapsed | 582 | +| total_timesteps | 776192 | +| train/ | | +| approx_kl | 0.008738032 | +| clip_fraction | 0.276 | +| clip_range | 0.0748 | +| entropy_loss | -7.66 | +| explained_variance | -0.07 | +| learning_rate | 4.98e-05 | +| loss | -0.0353 | +| n_updates | 17332 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000195 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1332 | +| iterations | 380 | +| time_elapsed | 584 | +| total_timesteps | 778240 | +| train/ | | +| approx_kl | 0.008030886 | +| clip_fraction | 0.244 | +| clip_range | 0.0748 | +| entropy_loss | -7.64 | +| explained_variance | -0.114 | +| learning_rate | 4.98e-05 | +| loss | -0.0359 | +| n_updates | 17336 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000198 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1332 | +| iterations | 381 | +| time_elapsed | 585 | +| total_timesteps | 780288 | +| train/ | | +| approx_kl | 0.007343358 | +| clip_fraction | 0.244 | +| clip_range | 0.0748 | +| entropy_loss | -7.49 | +| explained_variance | -0.154 | +| learning_rate | 4.98e-05 | +| loss | -0.0259 | +| n_updates | 17340 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000185 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1332 | +| iterations | 382 | +| time_elapsed | 587 | +| total_timesteps | 782336 | +| train/ | | +| approx_kl | 0.008758737 | +| clip_fraction | 0.266 | +| clip_range | 0.0748 | +| entropy_loss | -7.54 | +| explained_variance | -0.099 | +| learning_rate | 4.98e-05 | +| loss | -0.032 | +| n_updates | 17344 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000146 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1332 | +| iterations | 383 | +| time_elapsed | 588 | +| total_timesteps | 784384 | +| train/ | | +| approx_kl | 0.008440126 | +| clip_fraction | 0.279 | +| clip_range | 0.0748 | +| entropy_loss | -7.56 | +| explained_variance | -0.181 | +| learning_rate | 4.98e-05 | +| loss | -0.0373 | +| n_updates | 17348 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000183 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1332 | +| iterations | 384 | +| time_elapsed | 590 | +| total_timesteps | 786432 | +| train/ | | +| approx_kl | 0.0072416356 | +| clip_fraction | 0.248 | +| clip_range | 0.0748 | +| entropy_loss | -7.74 | +| explained_variance | -0.00251 | +| learning_rate | 4.98e-05 | +| loss | -0.0337 | +| n_updates | 17352 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000182 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1332 | +| iterations | 385 | +| time_elapsed | 591 | +| total_timesteps | 788480 | +| train/ | | +| approx_kl | 0.006962274 | +| clip_fraction | 0.223 | +| clip_range | 0.0748 | +| entropy_loss | -7.51 | +| explained_variance | -0.0121 | +| learning_rate | 4.98e-05 | +| loss | -0.0265 | +| n_updates | 17356 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000341 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1332 | +| iterations | 386 | +| time_elapsed | 593 | +| total_timesteps | 790528 | +| train/ | | +| approx_kl | 0.007831551 | +| clip_fraction | 0.248 | +| clip_range | 0.0748 | +| entropy_loss | -7.42 | +| explained_variance | 0.0159 | +| learning_rate | 4.98e-05 | +| loss | -0.031 | +| n_updates | 17360 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000328 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1332 | +| iterations | 387 | +| time_elapsed | 594 | +| total_timesteps | 792576 | +| train/ | | +| approx_kl | 0.0084319655 | +| clip_fraction | 0.273 | +| clip_range | 0.0748 | +| entropy_loss | -7.45 | +| explained_variance | -0.095 | +| learning_rate | 4.98e-05 | +| loss | -0.0377 | +| n_updates | 17364 | +| policy_gradient_loss | -0.0225 | +| value_loss | 0.000137 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1332 | +| iterations | 388 | +| time_elapsed | 596 | +| total_timesteps | 794624 | +| train/ | | +| approx_kl | 0.0089680925 | +| clip_fraction | 0.267 | +| clip_range | 0.0748 | +| entropy_loss | -7.73 | +| explained_variance | -0.0831 | +| learning_rate | 4.98e-05 | +| loss | -0.0352 | +| n_updates | 17368 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000196 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1332 | +| iterations | 389 | +| time_elapsed | 597 | +| total_timesteps | 796672 | +| train/ | | +| approx_kl | 0.008416545 | +| clip_fraction | 0.269 | +| clip_range | 0.0748 | +| entropy_loss | -7.38 | +| explained_variance | -0.182 | +| learning_rate | 4.98e-05 | +| loss | -0.0339 | +| n_updates | 17372 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000171 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1332 | +| iterations | 390 | +| time_elapsed | 599 | +| total_timesteps | 798720 | +| train/ | | +| approx_kl | 0.008542415 | +| clip_fraction | 0.272 | +| clip_range | 0.0748 | +| entropy_loss | -7.68 | +| explained_variance | -0.0551 | +| learning_rate | 4.98e-05 | +| loss | -0.0396 | +| n_updates | 17376 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000162 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1333 | +| iterations | 391 | +| time_elapsed | 600 | +| total_timesteps | 800768 | +| train/ | | +| approx_kl | 0.007730774 | +| clip_fraction | 0.243 | +| clip_range | 0.0748 | +| entropy_loss | -7.72 | +| explained_variance | -0.153 | +| learning_rate | 4.98e-05 | +| loss | -0.031 | +| n_updates | 17380 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000109 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1333 | +| iterations | 392 | +| time_elapsed | 602 | +| total_timesteps | 802816 | +| train/ | | +| approx_kl | 0.008240169 | +| clip_fraction | 0.254 | +| clip_range | 0.0748 | +| entropy_loss | -7.64 | +| explained_variance | -0.0379 | +| learning_rate | 4.98e-05 | +| loss | -0.0271 | +| n_updates | 17384 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000188 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1333 | +| iterations | 393 | +| time_elapsed | 603 | +| total_timesteps | 804864 | +| train/ | | +| approx_kl | 0.008635995 | +| clip_fraction | 0.234 | +| clip_range | 0.0748 | +| entropy_loss | -7.62 | +| explained_variance | -0.0225 | +| learning_rate | 4.98e-05 | +| loss | -0.0324 | +| n_updates | 17388 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000229 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 1333 | +| iterations | 394 | +| time_elapsed | 605 | +| total_timesteps | 806912 | +| train/ | | +| approx_kl | 0.008010441 | +| clip_fraction | 0.254 | +| clip_range | 0.0748 | +| entropy_loss | -7.43 | +| explained_variance | 0.0105 | +| learning_rate | 4.98e-05 | +| loss | -0.0352 | +| n_updates | 17392 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000173 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 1333 | +| iterations | 395 | +| time_elapsed | 606 | +| total_timesteps | 808960 | +| train/ | | +| approx_kl | 0.009326609 | +| clip_fraction | 0.296 | +| clip_range | 0.0748 | +| entropy_loss | -7.58 | +| explained_variance | -0.674 | +| learning_rate | 4.98e-05 | +| loss | -0.0432 | +| n_updates | 17396 | +| policy_gradient_loss | -0.0261 | +| value_loss | 8.15e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.295 | +| time/ | | +| fps | 1333 | +| iterations | 396 | +| time_elapsed | 608 | +| total_timesteps | 811008 | +| train/ | | +| approx_kl | 0.009141118 | +| clip_fraction | 0.258 | +| clip_range | 0.0748 | +| entropy_loss | -7.55 | +| explained_variance | -0.109 | +| learning_rate | 4.98e-05 | +| loss | -0.0306 | +| n_updates | 17400 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000138 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.295 | +| time/ | | +| fps | 1333 | +| iterations | 397 | +| time_elapsed | 609 | +| total_timesteps | 813056 | +| train/ | | +| approx_kl | 0.00930392 | +| clip_fraction | 0.259 | +| clip_range | 0.0748 | +| entropy_loss | -7.72 | +| explained_variance | -0.109 | +| learning_rate | 4.98e-05 | +| loss | -0.0251 | +| n_updates | 17404 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000174 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.295 | +| time/ | | +| fps | 1333 | +| iterations | 398 | +| time_elapsed | 611 | +| total_timesteps | 815104 | +| train/ | | +| approx_kl | 0.009384761 | +| clip_fraction | 0.273 | +| clip_range | 0.0748 | +| entropy_loss | -7.43 | +| explained_variance | -0.0323 | +| learning_rate | 4.98e-05 | +| loss | -0.0388 | +| n_updates | 17408 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000218 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 1334 | +| iterations | 399 | +| time_elapsed | 612 | +| total_timesteps | 817152 | +| train/ | | +| approx_kl | 0.007992579 | +| clip_fraction | 0.273 | +| clip_range | 0.0748 | +| entropy_loss | -7.67 | +| explained_variance | -0.108 | +| learning_rate | 4.98e-05 | +| loss | -0.0366 | +| n_updates | 17412 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 1334 | +| iterations | 400 | +| time_elapsed | 613 | +| total_timesteps | 819200 | +| train/ | | +| approx_kl | 0.007620506 | +| clip_fraction | 0.274 | +| clip_range | 0.0748 | +| entropy_loss | -7.45 | +| explained_variance | -0.0392 | +| learning_rate | 4.98e-05 | +| loss | -0.0337 | +| n_updates | 17416 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.00019 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.293 | +| time/ | | +| fps | 1334 | +| iterations | 401 | +| time_elapsed | 615 | +| total_timesteps | 821248 | +| train/ | | +| approx_kl | 0.007158905 | +| clip_fraction | 0.263 | +| clip_range | 0.0748 | +| entropy_loss | -7.76 | +| explained_variance | -0.00786 | +| learning_rate | 4.98e-05 | +| loss | -0.0348 | +| n_updates | 17420 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000179 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.29 | +| time/ | | +| fps | 1334 | +| iterations | 402 | +| time_elapsed | 616 | +| total_timesteps | 823296 | +| train/ | | +| approx_kl | 0.008346929 | +| clip_fraction | 0.251 | +| clip_range | 0.0748 | +| entropy_loss | -7.2 | +| explained_variance | -0.0438 | +| learning_rate | 4.98e-05 | +| loss | -0.0318 | +| n_updates | 17424 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000449 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.29 | +| time/ | | +| fps | 1334 | +| iterations | 403 | +| time_elapsed | 618 | +| total_timesteps | 825344 | +| train/ | | +| approx_kl | 0.008749392 | +| clip_fraction | 0.283 | +| clip_range | 0.0748 | +| entropy_loss | -7.47 | +| explained_variance | -0.13 | +| learning_rate | 4.98e-05 | +| loss | -0.0316 | +| n_updates | 17428 | +| policy_gradient_loss | -0.0222 | +| value_loss | 0.000143 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.291 | +| time/ | | +| fps | 1334 | +| iterations | 404 | +| time_elapsed | 619 | +| total_timesteps | 827392 | +| train/ | | +| approx_kl | 0.007825271 | +| clip_fraction | 0.269 | +| clip_range | 0.0748 | +| entropy_loss | -7.75 | +| explained_variance | -0.124 | +| learning_rate | 4.98e-05 | +| loss | -0.0309 | +| n_updates | 17432 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000161 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.29 | +| time/ | | +| fps | 1335 | +| iterations | 405 | +| time_elapsed | 621 | +| total_timesteps | 829440 | +| train/ | | +| approx_kl | 0.008376823 | +| clip_fraction | 0.254 | +| clip_range | 0.0748 | +| entropy_loss | -7.57 | +| explained_variance | -0.0386 | +| learning_rate | 4.98e-05 | +| loss | -0.0297 | +| n_updates | 17436 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000337 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.288 | +| time/ | | +| fps | 1335 | +| iterations | 406 | +| time_elapsed | 622 | +| total_timesteps | 831488 | +| train/ | | +| approx_kl | 0.008006633 | +| clip_fraction | 0.273 | +| clip_range | 0.0748 | +| entropy_loss | -7.56 | +| explained_variance | -0.15 | +| learning_rate | 4.98e-05 | +| loss | -0.0364 | +| n_updates | 17440 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000114 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.292 | +| time/ | | +| fps | 1335 | +| iterations | 407 | +| time_elapsed | 624 | +| total_timesteps | 833536 | +| train/ | | +| approx_kl | 0.008339148 | +| clip_fraction | 0.275 | +| clip_range | 0.0748 | +| entropy_loss | -7.45 | +| explained_variance | -0.257 | +| learning_rate | 4.98e-05 | +| loss | -0.0378 | +| n_updates | 17444 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000129 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 1335 | +| iterations | 408 | +| time_elapsed | 625 | +| total_timesteps | 835584 | +| train/ | | +| approx_kl | 0.0067070588 | +| clip_fraction | 0.241 | +| clip_range | 0.0748 | +| entropy_loss | -7.64 | +| explained_variance | -0.0059 | +| learning_rate | 4.98e-05 | +| loss | -0.0276 | +| n_updates | 17448 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000347 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.276 | +| time/ | | +| fps | 1335 | +| iterations | 409 | +| time_elapsed | 627 | +| total_timesteps | 837632 | +| train/ | | +| approx_kl | 0.0072606765 | +| clip_fraction | 0.235 | +| clip_range | 0.0748 | +| entropy_loss | -7.44 | +| explained_variance | -0.0506 | +| learning_rate | 4.98e-05 | +| loss | -0.0316 | +| n_updates | 17452 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000279 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.276 | +| time/ | | +| fps | 1335 | +| iterations | 410 | +| time_elapsed | 628 | +| total_timesteps | 839680 | +| train/ | | +| approx_kl | 0.006646934 | +| clip_fraction | 0.255 | +| clip_range | 0.0748 | +| entropy_loss | -7.58 | +| explained_variance | 0.036 | +| learning_rate | 4.98e-05 | +| loss | -0.0418 | +| n_updates | 17456 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000147 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.28 | +| time/ | | +| fps | 1335 | +| iterations | 411 | +| time_elapsed | 630 | +| total_timesteps | 841728 | +| train/ | | +| approx_kl | 0.008500211 | +| clip_fraction | 0.291 | +| clip_range | 0.0748 | +| entropy_loss | -7.73 | +| explained_variance | -0.291 | +| learning_rate | 4.98e-05 | +| loss | -0.0391 | +| n_updates | 17460 | +| policy_gradient_loss | -0.023 | +| value_loss | 9.38e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.28 | +| time/ | | +| fps | 1335 | +| iterations | 412 | +| time_elapsed | 631 | +| total_timesteps | 843776 | +| train/ | | +| approx_kl | 0.008525917 | +| clip_fraction | 0.232 | +| clip_range | 0.0748 | +| entropy_loss | -7.51 | +| explained_variance | 0.0564 | +| learning_rate | 4.98e-05 | +| loss | -0.0234 | +| n_updates | 17464 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000389 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.274 | +| time/ | | +| fps | 1336 | +| iterations | 413 | +| time_elapsed | 633 | +| total_timesteps | 845824 | +| train/ | | +| approx_kl | 0.009559651 | +| clip_fraction | 0.305 | +| clip_range | 0.0748 | +| entropy_loss | -7.55 | +| explained_variance | -0.29 | +| learning_rate | 4.98e-05 | +| loss | -0.0389 | +| n_updates | 17468 | +| policy_gradient_loss | -0.0239 | +| value_loss | 0.000171 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.276 | +| time/ | | +| fps | 1336 | +| iterations | 414 | +| time_elapsed | 634 | +| total_timesteps | 847872 | +| train/ | | +| approx_kl | 0.008690803 | +| clip_fraction | 0.304 | +| clip_range | 0.0748 | +| entropy_loss | -7.66 | +| explained_variance | -0.255 | +| learning_rate | 4.98e-05 | +| loss | -0.0433 | +| n_updates | 17472 | +| policy_gradient_loss | -0.0244 | +| value_loss | 6.95e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.276 | +| time/ | | +| fps | 1336 | +| iterations | 415 | +| time_elapsed | 635 | +| total_timesteps | 849920 | +| train/ | | +| approx_kl | 0.009313751 | +| clip_fraction | 0.271 | +| clip_range | 0.0748 | +| entropy_loss | -7.53 | +| explained_variance | -0.147 | +| learning_rate | 4.98e-05 | +| loss | -0.0342 | +| n_updates | 17476 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000134 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.278 | +| time/ | | +| fps | 1336 | +| iterations | 416 | +| time_elapsed | 637 | +| total_timesteps | 851968 | +| train/ | | +| approx_kl | 0.008890663 | +| clip_fraction | 0.259 | +| clip_range | 0.0748 | +| entropy_loss | -7.67 | +| explained_variance | -0.0223 | +| learning_rate | 4.98e-05 | +| loss | -0.0288 | +| n_updates | 17480 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000227 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.278 | +| time/ | | +| fps | 1336 | +| iterations | 417 | +| time_elapsed | 638 | +| total_timesteps | 854016 | +| train/ | | +| approx_kl | 0.007576089 | +| clip_fraction | 0.247 | +| clip_range | 0.0748 | +| entropy_loss | -7.52 | +| explained_variance | -0.0352 | +| learning_rate | 4.98e-05 | +| loss | -0.0296 | +| n_updates | 17484 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000288 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.278 | +| time/ | | +| fps | 1337 | +| iterations | 418 | +| time_elapsed | 640 | +| total_timesteps | 856064 | +| train/ | | +| approx_kl | 0.007769618 | +| clip_fraction | 0.267 | +| clip_range | 0.0748 | +| entropy_loss | -7.64 | +| explained_variance | -0.00502 | +| learning_rate | 4.98e-05 | +| loss | -0.0285 | +| n_updates | 17488 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000148 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.281 | +| time/ | | +| fps | 1337 | +| iterations | 419 | +| time_elapsed | 641 | +| total_timesteps | 858112 | +| train/ | | +| approx_kl | 0.009680204 | +| clip_fraction | 0.291 | +| clip_range | 0.0748 | +| entropy_loss | -7.71 | +| explained_variance | -0.136 | +| learning_rate | 4.98e-05 | +| loss | -0.0349 | +| n_updates | 17492 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.00013 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.271 | +| time/ | | +| fps | 1337 | +| iterations | 420 | +| time_elapsed | 643 | +| total_timesteps | 860160 | +| train/ | | +| approx_kl | 0.008251563 | +| clip_fraction | 0.265 | +| clip_range | 0.0748 | +| entropy_loss | -7.36 | +| explained_variance | -0.416 | +| learning_rate | 4.98e-05 | +| loss | -0.0347 | +| n_updates | 17496 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000112 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.274 | +| time/ | | +| fps | 1337 | +| iterations | 421 | +| time_elapsed | 644 | +| total_timesteps | 862208 | +| train/ | | +| approx_kl | 0.009788375 | +| clip_fraction | 0.264 | +| clip_range | 0.0748 | +| entropy_loss | -7.46 | +| explained_variance | -0.0248 | +| learning_rate | 4.98e-05 | +| loss | -0.0312 | +| n_updates | 17500 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000164 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 1338 | +| iterations | 422 | +| time_elapsed | 645 | +| total_timesteps | 864256 | +| train/ | | +| approx_kl | 0.008769853 | +| clip_fraction | 0.289 | +| clip_range | 0.0748 | +| entropy_loss | -7.47 | +| explained_variance | 0.0416 | +| learning_rate | 4.98e-05 | +| loss | -0.0357 | +| n_updates | 17504 | +| policy_gradient_loss | -0.0216 | +| value_loss | 8.97e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 1338 | +| iterations | 423 | +| time_elapsed | 647 | +| total_timesteps | 866304 | +| train/ | | +| approx_kl | 0.008442187 | +| clip_fraction | 0.254 | +| clip_range | 0.0748 | +| entropy_loss | -7.49 | +| explained_variance | 0.0159 | +| learning_rate | 4.98e-05 | +| loss | -0.0318 | +| n_updates | 17508 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000197 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.273 | +| time/ | | +| fps | 1338 | +| iterations | 424 | +| time_elapsed | 648 | +| total_timesteps | 868352 | +| train/ | | +| approx_kl | 0.008937172 | +| clip_fraction | 0.27 | +| clip_range | 0.0748 | +| entropy_loss | -7.56 | +| explained_variance | 0.0499 | +| learning_rate | 4.98e-05 | +| loss | -0.03 | +| n_updates | 17512 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000204 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.273 | +| time/ | | +| fps | 1338 | +| iterations | 425 | +| time_elapsed | 650 | +| total_timesteps | 870400 | +| train/ | | +| approx_kl | 0.0081346985 | +| clip_fraction | 0.271 | +| clip_range | 0.0748 | +| entropy_loss | -7.59 | +| explained_variance | -0.168 | +| learning_rate | 4.98e-05 | +| loss | -0.0332 | +| n_updates | 17516 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000161 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 1339 | +| iterations | 426 | +| time_elapsed | 651 | +| total_timesteps | 872448 | +| train/ | | +| approx_kl | 0.007864276 | +| clip_fraction | 0.267 | +| clip_range | 0.0748 | +| entropy_loss | -7.71 | +| explained_variance | -0.056 | +| learning_rate | 4.98e-05 | +| loss | -0.0376 | +| n_updates | 17520 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000141 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.284 | +| time/ | | +| fps | 1339 | +| iterations | 427 | +| time_elapsed | 653 | +| total_timesteps | 874496 | +| train/ | | +| approx_kl | 0.007053732 | +| clip_fraction | 0.246 | +| clip_range | 0.0748 | +| entropy_loss | -7.54 | +| explained_variance | 0.0387 | +| learning_rate | 4.98e-05 | +| loss | -0.0315 | +| n_updates | 17524 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000231 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.285 | +| time/ | | +| fps | 1339 | +| iterations | 428 | +| time_elapsed | 654 | +| total_timesteps | 876544 | +| train/ | | +| approx_kl | 0.0068690036 | +| clip_fraction | 0.249 | +| clip_range | 0.0748 | +| entropy_loss | -7.49 | +| explained_variance | -0.000906 | +| learning_rate | 4.98e-05 | +| loss | -0.0284 | +| n_updates | 17528 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000407 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 1339 | +| iterations | 429 | +| time_elapsed | 655 | +| total_timesteps | 878592 | +| train/ | | +| approx_kl | 0.0070245173 | +| clip_fraction | 0.251 | +| clip_range | 0.0748 | +| entropy_loss | -7.56 | +| explained_variance | -0.451 | +| learning_rate | 4.98e-05 | +| loss | -0.0311 | +| n_updates | 17532 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000136 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.281 | +| time/ | | +| fps | 1339 | +| iterations | 430 | +| time_elapsed | 657 | +| total_timesteps | 880640 | +| train/ | | +| approx_kl | 0.008247003 | +| clip_fraction | 0.277 | +| clip_range | 0.0748 | +| entropy_loss | -7.39 | +| explained_variance | 0.00956 | +| learning_rate | 4.98e-05 | +| loss | -0.0332 | +| n_updates | 17536 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000194 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.286 | +| time/ | | +| fps | 1339 | +| iterations | 431 | +| time_elapsed | 658 | +| total_timesteps | 882688 | +| train/ | | +| approx_kl | 0.008695954 | +| clip_fraction | 0.286 | +| clip_range | 0.0748 | +| entropy_loss | -7.53 | +| explained_variance | -0.161 | +| learning_rate | 4.98e-05 | +| loss | -0.0387 | +| n_updates | 17540 | +| policy_gradient_loss | -0.022 | +| value_loss | 0.000112 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.286 | +| time/ | | +| fps | 1340 | +| iterations | 432 | +| time_elapsed | 660 | +| total_timesteps | 884736 | +| train/ | | +| approx_kl | 0.009125583 | +| clip_fraction | 0.269 | +| clip_range | 0.0748 | +| entropy_loss | -7.63 | +| explained_variance | -0.0526 | +| learning_rate | 4.98e-05 | +| loss | -0.0328 | +| n_updates | 17544 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000181 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.286 | +| time/ | | +| fps | 1340 | +| iterations | 433 | +| time_elapsed | 661 | +| total_timesteps | 886784 | +| train/ | | +| approx_kl | 0.008864734 | +| clip_fraction | 0.276 | +| clip_range | 0.0748 | +| entropy_loss | -7.61 | +| explained_variance | -0.0706 | +| learning_rate | 4.98e-05 | +| loss | -0.0331 | +| n_updates | 17548 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000148 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.283 | +| time/ | | +| fps | 1340 | +| iterations | 434 | +| time_elapsed | 663 | +| total_timesteps | 888832 | +| train/ | | +| approx_kl | 0.008875314 | +| clip_fraction | 0.28 | +| clip_range | 0.0748 | +| entropy_loss | -7.67 | +| explained_variance | -0.336 | +| learning_rate | 4.98e-05 | +| loss | -0.0451 | +| n_updates | 17552 | +| policy_gradient_loss | -0.023 | +| value_loss | 7.25e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.283 | +| time/ | | +| fps | 1340 | +| iterations | 435 | +| time_elapsed | 664 | +| total_timesteps | 890880 | +| train/ | | +| approx_kl | 0.008988695 | +| clip_fraction | 0.257 | +| clip_range | 0.0748 | +| entropy_loss | -7.51 | +| explained_variance | 0.00484 | +| learning_rate | 4.98e-05 | +| loss | -0.0333 | +| n_updates | 17556 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000129 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.285 | +| time/ | | +| fps | 1340 | +| iterations | 436 | +| time_elapsed | 666 | +| total_timesteps | 892928 | +| train/ | | +| approx_kl | 0.00840163 | +| clip_fraction | 0.269 | +| clip_range | 0.0748 | +| entropy_loss | -7.58 | +| explained_variance | -0.0694 | +| learning_rate | 4.98e-05 | +| loss | -0.0309 | +| n_updates | 17560 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000204 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.284 | +| time/ | | +| fps | 1340 | +| iterations | 437 | +| time_elapsed | 667 | +| total_timesteps | 894976 | +| train/ | | +| approx_kl | 0.00750446 | +| clip_fraction | 0.264 | +| clip_range | 0.0748 | +| entropy_loss | -7.65 | +| explained_variance | -0.0536 | +| learning_rate | 4.98e-05 | +| loss | -0.0309 | +| n_updates | 17564 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000213 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 1341 | +| iterations | 438 | +| time_elapsed | 668 | +| total_timesteps | 897024 | +| train/ | | +| approx_kl | 0.008448532 | +| clip_fraction | 0.26 | +| clip_range | 0.0748 | +| entropy_loss | -7.53 | +| explained_variance | -0.0512 | +| learning_rate | 4.98e-05 | +| loss | -0.0297 | +| n_updates | 17568 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000244 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 1341 | +| iterations | 439 | +| time_elapsed | 670 | +| total_timesteps | 899072 | +| train/ | | +| approx_kl | 0.008507101 | +| clip_fraction | 0.255 | +| clip_range | 0.0748 | +| entropy_loss | -7.5 | +| explained_variance | -0.055 | +| learning_rate | 4.98e-05 | +| loss | -0.0348 | +| n_updates | 17572 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000167 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.277 | +| time/ | | +| fps | 1341 | +| iterations | 440 | +| time_elapsed | 671 | +| total_timesteps | 901120 | +| train/ | | +| approx_kl | 0.009069825 | +| clip_fraction | 0.272 | +| clip_range | 0.0748 | +| entropy_loss | -7.73 | +| explained_variance | -0.0204 | +| learning_rate | 4.98e-05 | +| loss | -0.0347 | +| n_updates | 17576 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000217 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.277 | +| time/ | | +| fps | 1341 | +| iterations | 441 | +| time_elapsed | 673 | +| total_timesteps | 903168 | +| train/ | | +| approx_kl | 0.008454691 | +| clip_fraction | 0.287 | +| clip_range | 0.0748 | +| entropy_loss | -7.31 | +| explained_variance | -0.188 | +| learning_rate | 4.98e-05 | +| loss | -0.0422 | +| n_updates | 17580 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000141 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.277 | +| time/ | | +| fps | 1341 | +| iterations | 442 | +| time_elapsed | 674 | +| total_timesteps | 905216 | +| train/ | | +| approx_kl | 0.0088159265 | +| clip_fraction | 0.258 | +| clip_range | 0.0748 | +| entropy_loss | -7.45 | +| explained_variance | 0.0794 | +| learning_rate | 4.98e-05 | +| loss | -0.0307 | +| n_updates | 17584 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000146 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.277 | +| time/ | | +| fps | 1342 | +| iterations | 443 | +| time_elapsed | 675 | +| total_timesteps | 907264 | +| train/ | | +| approx_kl | 0.009007308 | +| clip_fraction | 0.281 | +| clip_range | 0.0748 | +| entropy_loss | -7.5 | +| explained_variance | 0.147 | +| learning_rate | 4.98e-05 | +| loss | -0.0322 | +| n_updates | 17588 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.00018 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.278 | +| time/ | | +| fps | 1342 | +| iterations | 444 | +| time_elapsed | 677 | +| total_timesteps | 909312 | +| train/ | | +| approx_kl | 0.00899252 | +| clip_fraction | 0.277 | +| clip_range | 0.0748 | +| entropy_loss | -7.66 | +| explained_variance | -0.0863 | +| learning_rate | 4.98e-05 | +| loss | -0.0365 | +| n_updates | 17592 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000166 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 1342 | +| iterations | 445 | +| time_elapsed | 678 | +| total_timesteps | 911360 | +| train/ | | +| approx_kl | 0.009258589 | +| clip_fraction | 0.305 | +| clip_range | 0.0748 | +| entropy_loss | -7.59 | +| explained_variance | -0.121 | +| learning_rate | 4.98e-05 | +| loss | -0.0374 | +| n_updates | 17596 | +| policy_gradient_loss | -0.0224 | +| value_loss | 0.000101 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 1342 | +| iterations | 446 | +| time_elapsed | 680 | +| total_timesteps | 913408 | +| train/ | | +| approx_kl | 0.008346729 | +| clip_fraction | 0.248 | +| clip_range | 0.0748 | +| entropy_loss | -7.43 | +| explained_variance | 0.0585 | +| learning_rate | 4.98e-05 | +| loss | -0.0345 | +| n_updates | 17600 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000236 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 1342 | +| iterations | 447 | +| time_elapsed | 681 | +| total_timesteps | 915456 | +| train/ | | +| approx_kl | 0.009548262 | +| clip_fraction | 0.27 | +| clip_range | 0.0748 | +| entropy_loss | -7.7 | +| explained_variance | -0.0646 | +| learning_rate | 4.98e-05 | +| loss | -0.0357 | +| n_updates | 17604 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000121 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.276 | +| time/ | | +| fps | 1343 | +| iterations | 448 | +| time_elapsed | 683 | +| total_timesteps | 917504 | +| train/ | | +| approx_kl | 0.009237576 | +| clip_fraction | 0.279 | +| clip_range | 0.0748 | +| entropy_loss | -7.6 | +| explained_variance | -0.106 | +| learning_rate | 4.98e-05 | +| loss | -0.0355 | +| n_updates | 17608 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000115 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.273 | +| time/ | | +| fps | 1343 | +| iterations | 449 | +| time_elapsed | 684 | +| total_timesteps | 919552 | +| train/ | | +| approx_kl | 0.007314672 | +| clip_fraction | 0.259 | +| clip_range | 0.0748 | +| entropy_loss | -7.52 | +| explained_variance | 0.00485 | +| learning_rate | 4.98e-05 | +| loss | -0.0333 | +| n_updates | 17612 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.00017 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.273 | +| time/ | | +| fps | 1343 | +| iterations | 450 | +| time_elapsed | 685 | +| total_timesteps | 921600 | +| train/ | | +| approx_kl | 0.008844221 | +| clip_fraction | 0.275 | +| clip_range | 0.0748 | +| entropy_loss | -7.49 | +| explained_variance | 0.0241 | +| learning_rate | 4.98e-05 | +| loss | -0.0304 | +| n_updates | 17616 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000225 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.272 | +| time/ | | +| fps | 1343 | +| iterations | 451 | +| time_elapsed | 687 | +| total_timesteps | 923648 | +| train/ | | +| approx_kl | 0.007704295 | +| clip_fraction | 0.257 | +| clip_range | 0.0748 | +| entropy_loss | -7.32 | +| explained_variance | 0.0309 | +| learning_rate | 4.98e-05 | +| loss | -0.0255 | +| n_updates | 17620 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.00035 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 1343 | +| iterations | 452 | +| time_elapsed | 688 | +| total_timesteps | 925696 | +| train/ | | +| approx_kl | 0.009175859 | +| clip_fraction | 0.286 | +| clip_range | 0.0748 | +| entropy_loss | -7.44 | +| explained_variance | -0.142 | +| learning_rate | 4.98e-05 | +| loss | -0.0296 | +| n_updates | 17624 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000142 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 1344 | +| iterations | 453 | +| time_elapsed | 690 | +| total_timesteps | 927744 | +| train/ | | +| approx_kl | 0.008902734 | +| clip_fraction | 0.257 | +| clip_range | 0.0748 | +| entropy_loss | -7.55 | +| explained_variance | -0.0246 | +| learning_rate | 4.98e-05 | +| loss | -0.0288 | +| n_updates | 17628 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000168 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.277 | +| time/ | | +| fps | 1344 | +| iterations | 454 | +| time_elapsed | 691 | +| total_timesteps | 929792 | +| train/ | | +| approx_kl | 0.008963527 | +| clip_fraction | 0.28 | +| clip_range | 0.0748 | +| entropy_loss | -7.7 | +| explained_variance | 0.00603 | +| learning_rate | 4.98e-05 | +| loss | -0.036 | +| n_updates | 17632 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.00015 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 1344 | +| iterations | 455 | +| time_elapsed | 693 | +| total_timesteps | 931840 | +| train/ | | +| approx_kl | 0.007325068 | +| clip_fraction | 0.244 | +| clip_range | 0.0748 | +| entropy_loss | -7.46 | +| explained_variance | -0.0149 | +| learning_rate | 4.98e-05 | +| loss | -0.0302 | +| n_updates | 17636 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000261 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 1344 | +| iterations | 456 | +| time_elapsed | 694 | +| total_timesteps | 933888 | +| train/ | | +| approx_kl | 0.008871492 | +| clip_fraction | 0.265 | +| clip_range | 0.0748 | +| entropy_loss | -7.56 | +| explained_variance | 0.121 | +| learning_rate | 4.98e-05 | +| loss | -0.0362 | +| n_updates | 17640 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.00017 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.285 | +| time/ | | +| fps | 1344 | +| iterations | 457 | +| time_elapsed | 695 | +| total_timesteps | 935936 | +| train/ | | +| approx_kl | 0.007525604 | +| clip_fraction | 0.276 | +| clip_range | 0.0748 | +| entropy_loss | -7.67 | +| explained_variance | -0.0509 | +| learning_rate | 4.98e-05 | +| loss | -0.0379 | +| n_updates | 17644 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000158 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.285 | +| time/ | | +| fps | 1345 | +| iterations | 458 | +| time_elapsed | 697 | +| total_timesteps | 937984 | +| train/ | | +| approx_kl | 0.0074892724 | +| clip_fraction | 0.25 | +| clip_range | 0.0748 | +| entropy_loss | -7.52 | +| explained_variance | -0.0112 | +| learning_rate | 4.98e-05 | +| loss | -0.0268 | +| n_updates | 17648 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000264 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.289 | +| time/ | | +| fps | 1345 | +| iterations | 459 | +| time_elapsed | 698 | +| total_timesteps | 940032 | +| train/ | | +| approx_kl | 0.008227473 | +| clip_fraction | 0.237 | +| clip_range | 0.0748 | +| entropy_loss | -7.37 | +| explained_variance | -0.0781 | +| learning_rate | 4.98e-05 | +| loss | -0.0318 | +| n_updates | 17652 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000264 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.289 | +| time/ | | +| fps | 1345 | +| iterations | 460 | +| time_elapsed | 700 | +| total_timesteps | 942080 | +| train/ | | +| approx_kl | 0.008567274 | +| clip_fraction | 0.271 | +| clip_range | 0.0748 | +| entropy_loss | -7.32 | +| explained_variance | -0.0491 | +| learning_rate | 4.98e-05 | +| loss | -0.0302 | +| n_updates | 17656 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000269 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.29 | +| time/ | | +| fps | 1345 | +| iterations | 461 | +| time_elapsed | 701 | +| total_timesteps | 944128 | +| train/ | | +| approx_kl | 0.009972685 | +| clip_fraction | 0.31 | +| clip_range | 0.0748 | +| entropy_loss | -7.57 | +| explained_variance | -0.00598 | +| learning_rate | 4.98e-05 | +| loss | -0.0392 | +| n_updates | 17660 | +| policy_gradient_loss | -0.0223 | +| value_loss | 0.000137 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.285 | +| time/ | | +| fps | 1345 | +| iterations | 462 | +| time_elapsed | 703 | +| total_timesteps | 946176 | +| train/ | | +| approx_kl | 0.0087247975 | +| clip_fraction | 0.294 | +| clip_range | 0.0748 | +| entropy_loss | -7.63 | +| explained_variance | -0.17 | +| learning_rate | 4.98e-05 | +| loss | -0.0337 | +| n_updates | 17664 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000161 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.29 | +| time/ | | +| fps | 1345 | +| iterations | 463 | +| time_elapsed | 704 | +| total_timesteps | 948224 | +| train/ | | +| approx_kl | 0.008765315 | +| clip_fraction | 0.269 | +| clip_range | 0.0748 | +| entropy_loss | -7.51 | +| explained_variance | 0.144 | +| learning_rate | 4.98e-05 | +| loss | -0.036 | +| n_updates | 17668 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000123 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.288 | +| time/ | | +| fps | 1346 | +| iterations | 464 | +| time_elapsed | 705 | +| total_timesteps | 950272 | +| train/ | | +| approx_kl | 0.0068812734 | +| clip_fraction | 0.255 | +| clip_range | 0.0748 | +| entropy_loss | -7.36 | +| explained_variance | 0.0829 | +| learning_rate | 4.98e-05 | +| loss | -0.0332 | +| n_updates | 17672 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000411 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.284 | +| time/ | | +| fps | 1346 | +| iterations | 465 | +| time_elapsed | 707 | +| total_timesteps | 952320 | +| train/ | | +| approx_kl | 0.009795656 | +| clip_fraction | 0.298 | +| clip_range | 0.0748 | +| entropy_loss | -7.66 | +| explained_variance | -0.0487 | +| learning_rate | 4.98e-05 | +| loss | -0.0363 | +| n_updates | 17676 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000205 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.288 | +| time/ | | +| fps | 1346 | +| iterations | 466 | +| time_elapsed | 708 | +| total_timesteps | 954368 | +| train/ | | +| approx_kl | 0.008993373 | +| clip_fraction | 0.26 | +| clip_range | 0.0748 | +| entropy_loss | -7.34 | +| explained_variance | -0.00887 | +| learning_rate | 4.98e-05 | +| loss | -0.0327 | +| n_updates | 17680 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.00024 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.288 | +| time/ | | +| fps | 1346 | +| iterations | 467 | +| time_elapsed | 710 | +| total_timesteps | 956416 | +| train/ | | +| approx_kl | 0.008988645 | +| clip_fraction | 0.292 | +| clip_range | 0.0748 | +| entropy_loss | -7.6 | +| explained_variance | -0.0669 | +| learning_rate | 4.98e-05 | +| loss | -0.0385 | +| n_updates | 17684 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000214 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 1347 | +| iterations | 468 | +| time_elapsed | 711 | +| total_timesteps | 958464 | +| train/ | | +| approx_kl | 0.009297371 | +| clip_fraction | 0.298 | +| clip_range | 0.0748 | +| entropy_loss | -7.69 | +| explained_variance | -0.118 | +| learning_rate | 4.98e-05 | +| loss | -0.0338 | +| n_updates | 17688 | +| policy_gradient_loss | -0.0231 | +| value_loss | 0.000182 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.287 | +| time/ | | +| fps | 1347 | +| iterations | 469 | +| time_elapsed | 712 | +| total_timesteps | 960512 | +| train/ | | +| approx_kl | 0.008527246 | +| clip_fraction | 0.286 | +| clip_range | 0.0748 | +| entropy_loss | -7.48 | +| explained_variance | 0.0255 | +| learning_rate | 4.98e-05 | +| loss | -0.0396 | +| n_updates | 17692 | +| policy_gradient_loss | -0.0226 | +| value_loss | 0.000111 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.28 | +| time/ | | +| fps | 1347 | +| iterations | 470 | +| time_elapsed | 714 | +| total_timesteps | 962560 | +| train/ | | +| approx_kl | 0.0079924865 | +| clip_fraction | 0.254 | +| clip_range | 0.0748 | +| entropy_loss | -7.38 | +| explained_variance | -0.0456 | +| learning_rate | 4.98e-05 | +| loss | -0.0341 | +| n_updates | 17696 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000251 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.283 | +| time/ | | +| fps | 1347 | +| iterations | 471 | +| time_elapsed | 715 | +| total_timesteps | 964608 | +| train/ | | +| approx_kl | 0.009375093 | +| clip_fraction | 0.254 | +| clip_range | 0.0748 | +| entropy_loss | -7.42 | +| explained_variance | -0.084 | +| learning_rate | 4.98e-05 | +| loss | -0.0324 | +| n_updates | 17700 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.00021 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.283 | +| time/ | | +| fps | 1348 | +| iterations | 472 | +| time_elapsed | 717 | +| total_timesteps | 966656 | +| train/ | | +| approx_kl | 0.010332018 | +| clip_fraction | 0.287 | +| clip_range | 0.0748 | +| entropy_loss | -7.58 | +| explained_variance | -0.108 | +| learning_rate | 4.98e-05 | +| loss | -0.0359 | +| n_updates | 17704 | +| policy_gradient_loss | -0.0225 | +| value_loss | 0.000104 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.286 | +| time/ | | +| fps | 1348 | +| iterations | 473 | +| time_elapsed | 718 | +| total_timesteps | 968704 | +| train/ | | +| approx_kl | 0.00998595 | +| clip_fraction | 0.268 | +| clip_range | 0.0748 | +| entropy_loss | -7.59 | +| explained_variance | -0.129 | +| learning_rate | 4.98e-05 | +| loss | -0.0324 | +| n_updates | 17708 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000175 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.289 | +| time/ | | +| fps | 1348 | +| iterations | 474 | +| time_elapsed | 719 | +| total_timesteps | 970752 | +| train/ | | +| approx_kl | 0.009445043 | +| clip_fraction | 0.277 | +| clip_range | 0.0748 | +| entropy_loss | -7.58 | +| explained_variance | -0.127 | +| learning_rate | 4.98e-05 | +| loss | -0.0314 | +| n_updates | 17712 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000167 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.284 | +| time/ | | +| fps | 1348 | +| iterations | 475 | +| time_elapsed | 721 | +| total_timesteps | 972800 | +| train/ | | +| approx_kl | 0.008317552 | +| clip_fraction | 0.26 | +| clip_range | 0.0748 | +| entropy_loss | -7.59 | +| explained_variance | -0.0885 | +| learning_rate | 4.98e-05 | +| loss | -0.0326 | +| n_updates | 17716 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000234 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.285 | +| time/ | | +| fps | 1348 | +| iterations | 476 | +| time_elapsed | 722 | +| total_timesteps | 974848 | +| train/ | | +| approx_kl | 0.007386107 | +| clip_fraction | 0.265 | +| clip_range | 0.0748 | +| entropy_loss | -7.51 | +| explained_variance | -0.106 | +| learning_rate | 4.98e-05 | +| loss | -0.03 | +| n_updates | 17720 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000126 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.286 | +| time/ | | +| fps | 1348 | +| iterations | 477 | +| time_elapsed | 724 | +| total_timesteps | 976896 | +| train/ | | +| approx_kl | 0.00882218 | +| clip_fraction | 0.26 | +| clip_range | 0.0748 | +| entropy_loss | -7.62 | +| explained_variance | -0.0232 | +| learning_rate | 4.98e-05 | +| loss | -0.0341 | +| n_updates | 17724 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000162 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.285 | +| time/ | | +| fps | 1349 | +| iterations | 478 | +| time_elapsed | 725 | +| total_timesteps | 978944 | +| train/ | | +| approx_kl | 0.009656058 | +| clip_fraction | 0.287 | +| clip_range | 0.0748 | +| entropy_loss | -7.47 | +| explained_variance | -0.0446 | +| learning_rate | 4.98e-05 | +| loss | -0.0387 | +| n_updates | 17728 | +| policy_gradient_loss | -0.0222 | +| value_loss | 0.000115 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.284 | +| time/ | | +| fps | 1349 | +| iterations | 479 | +| time_elapsed | 727 | +| total_timesteps | 980992 | +| train/ | | +| approx_kl | 0.008120804 | +| clip_fraction | 0.26 | +| clip_range | 0.0748 | +| entropy_loss | -7.51 | +| explained_variance | -0.0342 | +| learning_rate | 4.98e-05 | +| loss | -0.0336 | +| n_updates | 17732 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000261 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.284 | +| time/ | | +| fps | 1349 | +| iterations | 480 | +| time_elapsed | 728 | +| total_timesteps | 983040 | +| train/ | | +| approx_kl | 0.008081126 | +| clip_fraction | 0.276 | +| clip_range | 0.0748 | +| entropy_loss | -7.53 | +| explained_variance | -0.0637 | +| learning_rate | 4.98e-05 | +| loss | -0.0272 | +| n_updates | 17736 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000198 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.287 | +| time/ | | +| fps | 1349 | +| iterations | 481 | +| time_elapsed | 729 | +| total_timesteps | 985088 | +| train/ | | +| approx_kl | 0.008402461 | +| clip_fraction | 0.284 | +| clip_range | 0.0748 | +| entropy_loss | -7.67 | +| explained_variance | -0.0837 | +| learning_rate | 4.98e-05 | +| loss | -0.0369 | +| n_updates | 17740 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.286 | +| time/ | | +| fps | 1349 | +| iterations | 482 | +| time_elapsed | 731 | +| total_timesteps | 987136 | +| train/ | | +| approx_kl | 0.008694404 | +| clip_fraction | 0.282 | +| clip_range | 0.0748 | +| entropy_loss | -7.69 | +| explained_variance | -0.0698 | +| learning_rate | 4.98e-05 | +| loss | -0.0363 | +| n_updates | 17744 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000144 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.283 | +| time/ | | +| fps | 1349 | +| iterations | 483 | +| time_elapsed | 732 | +| total_timesteps | 989184 | +| train/ | | +| approx_kl | 0.007999121 | +| clip_fraction | 0.255 | +| clip_range | 0.0748 | +| entropy_loss | -7.34 | +| explained_variance | -0.0601 | +| learning_rate | 4.98e-05 | +| loss | -0.0338 | +| n_updates | 17748 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000157 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.293 | +| time/ | | +| fps | 1349 | +| iterations | 484 | +| time_elapsed | 734 | +| total_timesteps | 991232 | +| train/ | | +| approx_kl | 0.010182185 | +| clip_fraction | 0.294 | +| clip_range | 0.0748 | +| entropy_loss | -7.43 | +| explained_variance | -0.0594 | +| learning_rate | 4.98e-05 | +| loss | -0.0348 | +| n_updates | 17752 | +| policy_gradient_loss | -0.0224 | +| value_loss | 7.44e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.285 | +| time/ | | +| fps | 1350 | +| iterations | 485 | +| time_elapsed | 735 | +| total_timesteps | 993280 | +| train/ | | +| approx_kl | 0.0099374065 | +| clip_fraction | 0.296 | +| clip_range | 0.0748 | +| entropy_loss | -7.38 | +| explained_variance | -0.037 | +| learning_rate | 4.98e-05 | +| loss | -0.0334 | +| n_updates | 17756 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000183 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.294 | +| time/ | | +| fps | 1350 | +| iterations | 486 | +| time_elapsed | 737 | +| total_timesteps | 995328 | +| train/ | | +| approx_kl | 0.007602739 | +| clip_fraction | 0.251 | +| clip_range | 0.0748 | +| entropy_loss | -7.4 | +| explained_variance | 0.0363 | +| learning_rate | 4.98e-05 | +| loss | -0.0322 | +| n_updates | 17760 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000143 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.294 | +| time/ | | +| fps | 1350 | +| iterations | 487 | +| time_elapsed | 738 | +| total_timesteps | 997376 | +| train/ | | +| approx_kl | 0.009019924 | +| clip_fraction | 0.273 | +| clip_range | 0.0748 | +| entropy_loss | -7.58 | +| explained_variance | -0.0678 | +| learning_rate | 4.98e-05 | +| loss | -0.0332 | +| n_updates | 17764 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000198 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.297 | +| time/ | | +| fps | 1350 | +| iterations | 488 | +| time_elapsed | 740 | +| total_timesteps | 999424 | +| train/ | | +| approx_kl | 0.008751407 | +| clip_fraction | 0.281 | +| clip_range | 0.0748 | +| entropy_loss | -7.44 | +| explained_variance | -0.273 | +| learning_rate | 4.98e-05 | +| loss | -0.0304 | +| n_updates | 17768 | +| policy_gradient_loss | -0.0224 | +| value_loss | 0.000106 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.284 | +| time/ | | +| fps | 1350 | +| iterations | 489 | +| time_elapsed | 741 | +| total_timesteps | 1001472 | +| train/ | | +| approx_kl | 0.009254847 | +| clip_fraction | 0.269 | +| clip_range | 0.0748 | +| entropy_loss | -7.68 | +| explained_variance | -0.0128 | +| learning_rate | 4.98e-05 | +| loss | -0.0335 | +| n_updates | 17772 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000198 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 1350 | +| iterations | 490 | +| time_elapsed | 743 | +| total_timesteps | 1003520 | +| train/ | | +| approx_kl | 0.007844249 | +| clip_fraction | 0.248 | +| clip_range | 0.0747 | +| entropy_loss | -7.29 | +| explained_variance | 0.0143 | +| learning_rate | 4.98e-05 | +| loss | -0.0302 | +| n_updates | 17776 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000198 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 1350 | +| iterations | 491 | +| time_elapsed | 744 | +| total_timesteps | 1005568 | +| train/ | | +| approx_kl | 0.008411274 | +| clip_fraction | 0.257 | +| clip_range | 0.0747 | +| entropy_loss | -7.64 | +| explained_variance | -0.0661 | +| learning_rate | 4.98e-05 | +| loss | -0.0345 | +| n_updates | 17780 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000241 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.28 | +| time/ | | +| fps | 1350 | +| iterations | 492 | +| time_elapsed | 745 | +| total_timesteps | 1007616 | +| train/ | | +| approx_kl | 0.009200219 | +| clip_fraction | 0.302 | +| clip_range | 0.0747 | +| entropy_loss | -7.63 | +| explained_variance | -0.256 | +| learning_rate | 4.98e-05 | +| loss | -0.0303 | +| n_updates | 17784 | +| policy_gradient_loss | -0.0221 | +| value_loss | 9.03e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.274 | +| time/ | | +| fps | 1351 | +| iterations | 493 | +| time_elapsed | 747 | +| total_timesteps | 1009664 | +| train/ | | +| approx_kl | 0.009061827 | +| clip_fraction | 0.276 | +| clip_range | 0.0747 | +| entropy_loss | -7.39 | +| explained_variance | -0.186 | +| learning_rate | 4.98e-05 | +| loss | -0.0358 | +| n_updates | 17788 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000166 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.274 | +| time/ | | +| fps | 1351 | +| iterations | 494 | +| time_elapsed | 748 | +| total_timesteps | 1011712 | +| train/ | | +| approx_kl | 0.008234723 | +| clip_fraction | 0.268 | +| clip_range | 0.0747 | +| entropy_loss | -7.51 | +| explained_variance | -0.0612 | +| learning_rate | 4.98e-05 | +| loss | -0.0341 | +| n_updates | 17792 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000107 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.274 | +| time/ | | +| fps | 1351 | +| iterations | 495 | +| time_elapsed | 750 | +| total_timesteps | 1013760 | +| train/ | | +| approx_kl | 0.008349565 | +| clip_fraction | 0.272 | +| clip_range | 0.0747 | +| entropy_loss | -7.38 | +| explained_variance | -0.0298 | +| learning_rate | 4.98e-05 | +| loss | -0.0306 | +| n_updates | 17796 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000274 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.273 | +| time/ | | +| fps | 1351 | +| iterations | 496 | +| time_elapsed | 751 | +| total_timesteps | 1015808 | +| train/ | | +| approx_kl | 0.00946847 | +| clip_fraction | 0.27 | +| clip_range | 0.0747 | +| entropy_loss | -7.47 | +| explained_variance | 0.076 | +| learning_rate | 4.98e-05 | +| loss | -0.0314 | +| n_updates | 17800 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000217 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.273 | +| time/ | | +| fps | 1351 | +| iterations | 497 | +| time_elapsed | 753 | +| total_timesteps | 1017856 | +| train/ | | +| approx_kl | 0.0095122205 | +| clip_fraction | 0.282 | +| clip_range | 0.0747 | +| entropy_loss | -7.54 | +| explained_variance | -0.226 | +| learning_rate | 4.98e-05 | +| loss | -0.0409 | +| n_updates | 17804 | +| policy_gradient_loss | -0.0231 | +| value_loss | 0.000131 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.266 | +| time/ | | +| fps | 1351 | +| iterations | 498 | +| time_elapsed | 754 | +| total_timesteps | 1019904 | +| train/ | | +| approx_kl | 0.008916937 | +| clip_fraction | 0.271 | +| clip_range | 0.0747 | +| entropy_loss | -7.72 | +| explained_variance | 0.0358 | +| learning_rate | 4.98e-05 | +| loss | -0.037 | +| n_updates | 17808 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000256 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.264 | +| time/ | | +| fps | 1351 | +| iterations | 499 | +| time_elapsed | 756 | +| total_timesteps | 1021952 | +| train/ | | +| approx_kl | 0.008683014 | +| clip_fraction | 0.256 | +| clip_range | 0.0747 | +| entropy_loss | -7.54 | +| explained_variance | 0.0135 | +| learning_rate | 4.98e-05 | +| loss | -0.038 | +| n_updates | 17812 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000222 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.273 | +| time/ | | +| fps | 1352 | +| iterations | 500 | +| time_elapsed | 757 | +| total_timesteps | 1024000 | +| train/ | | +| approx_kl | 0.009165613 | +| clip_fraction | 0.281 | +| clip_range | 0.0747 | +| entropy_loss | -7.49 | +| explained_variance | -0.0237 | +| learning_rate | 4.98e-05 | +| loss | -0.042 | +| n_updates | 17816 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000342 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.273 | +| time/ | | +| fps | 1352 | +| iterations | 501 | +| time_elapsed | 758 | +| total_timesteps | 1026048 | +| train/ | | +| approx_kl | 0.009492001 | +| clip_fraction | 0.294 | +| clip_range | 0.0747 | +| entropy_loss | -7.23 | +| explained_variance | 0.0274 | +| learning_rate | 4.98e-05 | +| loss | -0.0288 | +| n_updates | 17820 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000342 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.273 | +| time/ | | +| fps | 1352 | +| iterations | 502 | +| time_elapsed | 760 | +| total_timesteps | 1028096 | +| train/ | | +| approx_kl | 0.009817114 | +| clip_fraction | 0.294 | +| clip_range | 0.0747 | +| entropy_loss | -7.61 | +| explained_variance | -0.0756 | +| learning_rate | 4.98e-05 | +| loss | -0.041 | +| n_updates | 17824 | +| policy_gradient_loss | -0.0224 | +| value_loss | 0.000198 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.283 | +| time/ | | +| fps | 1352 | +| iterations | 503 | +| time_elapsed | 761 | +| total_timesteps | 1030144 | +| train/ | | +| approx_kl | 0.009951322 | +| clip_fraction | 0.309 | +| clip_range | 0.0747 | +| entropy_loss | -7.73 | +| explained_variance | -0.263 | +| learning_rate | 4.98e-05 | +| loss | -0.0394 | +| n_updates | 17828 | +| policy_gradient_loss | -0.0227 | +| value_loss | 0.00014 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 1352 | +| iterations | 504 | +| time_elapsed | 763 | +| total_timesteps | 1032192 | +| train/ | | +| approx_kl | 0.0071156416 | +| clip_fraction | 0.266 | +| clip_range | 0.0747 | +| entropy_loss | -7.29 | +| explained_variance | -0.153 | +| learning_rate | 4.98e-05 | +| loss | -0.0338 | +| n_updates | 17832 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000209 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 1352 | +| iterations | 505 | +| time_elapsed | 764 | +| total_timesteps | 1034240 | +| train/ | | +| approx_kl | 0.009605327 | +| clip_fraction | 0.289 | +| clip_range | 0.0747 | +| entropy_loss | -7.57 | +| explained_variance | -0.0817 | +| learning_rate | 4.98e-05 | +| loss | -0.0354 | +| n_updates | 17836 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000175 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.281 | +| time/ | | +| fps | 1352 | +| iterations | 506 | +| time_elapsed | 765 | +| total_timesteps | 1036288 | +| train/ | | +| approx_kl | 0.009323913 | +| clip_fraction | 0.272 | +| clip_range | 0.0747 | +| entropy_loss | -7.53 | +| explained_variance | -0.102 | +| learning_rate | 4.98e-05 | +| loss | -0.0285 | +| n_updates | 17840 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.00019 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.281 | +| time/ | | +| fps | 1353 | +| iterations | 507 | +| time_elapsed | 767 | +| total_timesteps | 1038336 | +| train/ | | +| approx_kl | 0.0075609325 | +| clip_fraction | 0.254 | +| clip_range | 0.0747 | +| entropy_loss | -7.32 | +| explained_variance | -0.00754 | +| learning_rate | 4.98e-05 | +| loss | -0.0295 | +| n_updates | 17844 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000253 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.286 | +| time/ | | +| fps | 1353 | +| iterations | 508 | +| time_elapsed | 768 | +| total_timesteps | 1040384 | +| train/ | | +| approx_kl | 0.007864915 | +| clip_fraction | 0.261 | +| clip_range | 0.0747 | +| entropy_loss | -7.43 | +| explained_variance | -0.0121 | +| learning_rate | 4.98e-05 | +| loss | -0.0328 | +| n_updates | 17848 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.0002 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.294 | +| time/ | | +| fps | 1353 | +| iterations | 509 | +| time_elapsed | 770 | +| total_timesteps | 1042432 | +| train/ | | +| approx_kl | 0.007529688 | +| clip_fraction | 0.266 | +| clip_range | 0.0747 | +| entropy_loss | -7.63 | +| explained_variance | -0.0735 | +| learning_rate | 4.98e-05 | +| loss | -0.0328 | +| n_updates | 17852 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000278 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.293 | +| time/ | | +| fps | 1353 | +| iterations | 510 | +| time_elapsed | 771 | +| total_timesteps | 1044480 | +| train/ | | +| approx_kl | 0.009920644 | +| clip_fraction | 0.294 | +| clip_range | 0.0747 | +| entropy_loss | -7.5 | +| explained_variance | -0.184 | +| learning_rate | 4.98e-05 | +| loss | -0.0274 | +| n_updates | 17856 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000123 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 1353 | +| iterations | 511 | +| time_elapsed | 773 | +| total_timesteps | 1046528 | +| train/ | | +| approx_kl | 0.008519176 | +| clip_fraction | 0.242 | +| clip_range | 0.0747 | +| entropy_loss | -7.29 | +| explained_variance | 0.033 | +| learning_rate | 4.98e-05 | +| loss | -0.0252 | +| n_updates | 17860 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000291 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.3 | +| time/ | | +| fps | 1353 | +| iterations | 512 | +| time_elapsed | 774 | +| total_timesteps | 1048576 | +| train/ | | +| approx_kl | 0.01013411 | +| clip_fraction | 0.284 | +| clip_range | 0.0747 | +| entropy_loss | -7.42 | +| explained_variance | 0.0187 | +| learning_rate | 4.98e-05 | +| loss | -0.0279 | +| n_updates | 17864 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000232 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.302 | +| time/ | | +| fps | 1353 | +| iterations | 513 | +| time_elapsed | 776 | +| total_timesteps | 1050624 | +| train/ | | +| approx_kl | 0.009263918 | +| clip_fraction | 0.293 | +| clip_range | 0.0747 | +| entropy_loss | -7.47 | +| explained_variance | 0.0905 | +| learning_rate | 4.98e-05 | +| loss | -0.0322 | +| n_updates | 17868 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000174 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 1353 | +| iterations | 514 | +| time_elapsed | 777 | +| total_timesteps | 1052672 | +| train/ | | +| approx_kl | 0.008916676 | +| clip_fraction | 0.28 | +| clip_range | 0.0747 | +| entropy_loss | -7.4 | +| explained_variance | 0.133 | +| learning_rate | 4.98e-05 | +| loss | -0.0344 | +| n_updates | 17872 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.00035 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.3 | +| time/ | | +| fps | 1353 | +| iterations | 515 | +| time_elapsed | 779 | +| total_timesteps | 1054720 | +| train/ | | +| approx_kl | 0.008669009 | +| clip_fraction | 0.273 | +| clip_range | 0.0747 | +| entropy_loss | -7.46 | +| explained_variance | -0.0889 | +| learning_rate | 4.97e-05 | +| loss | -0.0368 | +| n_updates | 17876 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000258 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.304 | +| time/ | | +| fps | 1354 | +| iterations | 516 | +| time_elapsed | 780 | +| total_timesteps | 1056768 | +| train/ | | +| approx_kl | 0.008616938 | +| clip_fraction | 0.285 | +| clip_range | 0.0747 | +| entropy_loss | -7.59 | +| explained_variance | -0.213 | +| learning_rate | 4.97e-05 | +| loss | -0.0232 | +| n_updates | 17880 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000194 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.304 | +| time/ | | +| fps | 1354 | +| iterations | 517 | +| time_elapsed | 781 | +| total_timesteps | 1058816 | +| train/ | | +| approx_kl | 0.008320367 | +| clip_fraction | 0.257 | +| clip_range | 0.0747 | +| entropy_loss | -7.46 | +| explained_variance | 0.0493 | +| learning_rate | 4.97e-05 | +| loss | -0.0307 | +| n_updates | 17884 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000439 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.294 | +| time/ | | +| fps | 1354 | +| iterations | 518 | +| time_elapsed | 783 | +| total_timesteps | 1060864 | +| train/ | | +| approx_kl | 0.010148698 | +| clip_fraction | 0.327 | +| clip_range | 0.0747 | +| entropy_loss | -7.7 | +| explained_variance | -0.104 | +| learning_rate | 4.97e-05 | +| loss | -0.0485 | +| n_updates | 17888 | +| policy_gradient_loss | -0.0261 | +| value_loss | 0.000126 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.302 | +| time/ | | +| fps | 1354 | +| iterations | 519 | +| time_elapsed | 784 | +| total_timesteps | 1062912 | +| train/ | | +| approx_kl | 0.007415791 | +| clip_fraction | 0.27 | +| clip_range | 0.0747 | +| entropy_loss | -7.37 | +| explained_variance | -0.457 | +| learning_rate | 4.97e-05 | +| loss | -0.0321 | +| n_updates | 17892 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000216 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 1354 | +| iterations | 520 | +| time_elapsed | 786 | +| total_timesteps | 1064960 | +| train/ | | +| approx_kl | 0.009260173 | +| clip_fraction | 0.288 | +| clip_range | 0.0747 | +| entropy_loss | -7.56 | +| explained_variance | -0.136 | +| learning_rate | 4.97e-05 | +| loss | -0.0442 | +| n_updates | 17896 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.00018 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.306 | +| time/ | | +| fps | 1354 | +| iterations | 521 | +| time_elapsed | 787 | +| total_timesteps | 1067008 | +| train/ | | +| approx_kl | 0.00963678 | +| clip_fraction | 0.261 | +| clip_range | 0.0747 | +| entropy_loss | -7.51 | +| explained_variance | -0.178 | +| learning_rate | 4.97e-05 | +| loss | -0.0384 | +| n_updates | 17900 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000191 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1354 | +| iterations | 522 | +| time_elapsed | 789 | +| total_timesteps | 1069056 | +| train/ | | +| approx_kl | 0.009787967 | +| clip_fraction | 0.296 | +| clip_range | 0.0747 | +| entropy_loss | -7.5 | +| explained_variance | -0.0905 | +| learning_rate | 4.97e-05 | +| loss | -0.0331 | +| n_updates | 17904 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000208 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1354 | +| iterations | 523 | +| time_elapsed | 790 | +| total_timesteps | 1071104 | +| train/ | | +| approx_kl | 0.0089315325 | +| clip_fraction | 0.293 | +| clip_range | 0.0747 | +| entropy_loss | -7.55 | +| explained_variance | -0.0334 | +| learning_rate | 4.97e-05 | +| loss | -0.038 | +| n_updates | 17908 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000168 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1354 | +| iterations | 524 | +| time_elapsed | 791 | +| total_timesteps | 1073152 | +| train/ | | +| approx_kl | 0.007916287 | +| clip_fraction | 0.267 | +| clip_range | 0.0747 | +| entropy_loss | -7.39 | +| explained_variance | 0.0237 | +| learning_rate | 4.97e-05 | +| loss | -0.0338 | +| n_updates | 17912 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000211 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1355 | +| iterations | 525 | +| time_elapsed | 793 | +| total_timesteps | 1075200 | +| train/ | | +| approx_kl | 0.009071832 | +| clip_fraction | 0.262 | +| clip_range | 0.0747 | +| entropy_loss | -7.49 | +| explained_variance | -0.0859 | +| learning_rate | 4.97e-05 | +| loss | -0.0278 | +| n_updates | 17916 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000178 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1355 | +| iterations | 526 | +| time_elapsed | 794 | +| total_timesteps | 1077248 | +| train/ | | +| approx_kl | 0.00940584 | +| clip_fraction | 0.272 | +| clip_range | 0.0747 | +| entropy_loss | -7.34 | +| explained_variance | -0.0203 | +| learning_rate | 4.97e-05 | +| loss | -0.0289 | +| n_updates | 17920 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000203 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1355 | +| iterations | 527 | +| time_elapsed | 796 | +| total_timesteps | 1079296 | +| train/ | | +| approx_kl | 0.010059977 | +| clip_fraction | 0.294 | +| clip_range | 0.0747 | +| entropy_loss | -7.59 | +| explained_variance | -0.0958 | +| learning_rate | 4.97e-05 | +| loss | -0.0324 | +| n_updates | 17924 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000246 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1355 | +| iterations | 528 | +| time_elapsed | 797 | +| total_timesteps | 1081344 | +| train/ | | +| approx_kl | 0.008424815 | +| clip_fraction | 0.255 | +| clip_range | 0.0747 | +| entropy_loss | -7.45 | +| explained_variance | -0.0515 | +| learning_rate | 4.97e-05 | +| loss | -0.0299 | +| n_updates | 17928 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.00028 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1355 | +| iterations | 529 | +| time_elapsed | 799 | +| total_timesteps | 1083392 | +| train/ | | +| approx_kl | 0.008557165 | +| clip_fraction | 0.254 | +| clip_range | 0.0747 | +| entropy_loss | -7.48 | +| explained_variance | -0.0457 | +| learning_rate | 4.97e-05 | +| loss | -0.0306 | +| n_updates | 17932 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000197 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1355 | +| iterations | 530 | +| time_elapsed | 800 | +| total_timesteps | 1085440 | +| train/ | | +| approx_kl | 0.008704374 | +| clip_fraction | 0.274 | +| clip_range | 0.0747 | +| entropy_loss | -7.55 | +| explained_variance | 0.0261 | +| learning_rate | 4.97e-05 | +| loss | -0.0339 | +| n_updates | 17936 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.00015 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1355 | +| iterations | 531 | +| time_elapsed | 802 | +| total_timesteps | 1087488 | +| train/ | | +| approx_kl | 0.009141029 | +| clip_fraction | 0.275 | +| clip_range | 0.0747 | +| entropy_loss | -7.65 | +| explained_variance | -0.0578 | +| learning_rate | 4.97e-05 | +| loss | -0.0372 | +| n_updates | 17940 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000176 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1355 | +| iterations | 532 | +| time_elapsed | 803 | +| total_timesteps | 1089536 | +| train/ | | +| approx_kl | 0.007224384 | +| clip_fraction | 0.259 | +| clip_range | 0.0747 | +| entropy_loss | -7.7 | +| explained_variance | 0.000906 | +| learning_rate | 4.97e-05 | +| loss | -0.0369 | +| n_updates | 17944 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000125 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1356 | +| iterations | 533 | +| time_elapsed | 804 | +| total_timesteps | 1091584 | +| train/ | | +| approx_kl | 0.009399861 | +| clip_fraction | 0.285 | +| clip_range | 0.0747 | +| entropy_loss | -7.31 | +| explained_variance | 0.0487 | +| learning_rate | 4.97e-05 | +| loss | -0.0305 | +| n_updates | 17948 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000293 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 1356 | +| iterations | 534 | +| time_elapsed | 806 | +| total_timesteps | 1093632 | +| train/ | | +| approx_kl | 0.0083765555 | +| clip_fraction | 0.264 | +| clip_range | 0.0747 | +| entropy_loss | -7.76 | +| explained_variance | -0.125 | +| learning_rate | 4.97e-05 | +| loss | -0.0333 | +| n_updates | 17952 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000179 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1356 | +| iterations | 535 | +| time_elapsed | 807 | +| total_timesteps | 1095680 | +| train/ | | +| approx_kl | 0.008331486 | +| clip_fraction | 0.28 | +| clip_range | 0.0747 | +| entropy_loss | -7.49 | +| explained_variance | -0.101 | +| learning_rate | 4.97e-05 | +| loss | -0.0321 | +| n_updates | 17956 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000185 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1356 | +| iterations | 536 | +| time_elapsed | 809 | +| total_timesteps | 1097728 | +| train/ | | +| approx_kl | 0.007975782 | +| clip_fraction | 0.273 | +| clip_range | 0.0747 | +| entropy_loss | -7.49 | +| explained_variance | -0.0262 | +| learning_rate | 4.97e-05 | +| loss | -0.0288 | +| n_updates | 17960 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000374 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1356 | +| iterations | 537 | +| time_elapsed | 810 | +| total_timesteps | 1099776 | +| train/ | | +| approx_kl | 0.009566059 | +| clip_fraction | 0.293 | +| clip_range | 0.0747 | +| entropy_loss | -7.33 | +| explained_variance | -0.122 | +| learning_rate | 4.97e-05 | +| loss | -0.037 | +| n_updates | 17964 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000268 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1356 | +| iterations | 538 | +| time_elapsed | 812 | +| total_timesteps | 1101824 | +| train/ | | +| approx_kl | 0.009491803 | +| clip_fraction | 0.298 | +| clip_range | 0.0747 | +| entropy_loss | -7.38 | +| explained_variance | -0.2 | +| learning_rate | 4.97e-05 | +| loss | -0.034 | +| n_updates | 17968 | +| policy_gradient_loss | -0.022 | +| value_loss | 0.000157 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1356 | +| iterations | 539 | +| time_elapsed | 813 | +| total_timesteps | 1103872 | +| train/ | | +| approx_kl | 0.010283602 | +| clip_fraction | 0.296 | +| clip_range | 0.0747 | +| entropy_loss | -7.43 | +| explained_variance | -0.109 | +| learning_rate | 4.97e-05 | +| loss | -0.0353 | +| n_updates | 17972 | +| policy_gradient_loss | -0.0222 | +| value_loss | 0.000134 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1356 | +| iterations | 540 | +| time_elapsed | 815 | +| total_timesteps | 1105920 | +| train/ | | +| approx_kl | 0.00892351 | +| clip_fraction | 0.267 | +| clip_range | 0.0747 | +| entropy_loss | -7.73 | +| explained_variance | -0.108 | +| learning_rate | 4.97e-05 | +| loss | -0.0304 | +| n_updates | 17976 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000253 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1357 | +| iterations | 541 | +| time_elapsed | 816 | +| total_timesteps | 1107968 | +| train/ | | +| approx_kl | 0.008749695 | +| clip_fraction | 0.27 | +| clip_range | 0.0747 | +| entropy_loss | -7.7 | +| explained_variance | -0.197 | +| learning_rate | 4.97e-05 | +| loss | -0.0359 | +| n_updates | 17980 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000166 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1357 | +| iterations | 542 | +| time_elapsed | 817 | +| total_timesteps | 1110016 | +| train/ | | +| approx_kl | 0.008265816 | +| clip_fraction | 0.252 | +| clip_range | 0.0747 | +| entropy_loss | -7.68 | +| explained_variance | -0.057 | +| learning_rate | 4.97e-05 | +| loss | -0.0336 | +| n_updates | 17984 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.00022 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1357 | +| iterations | 543 | +| time_elapsed | 819 | +| total_timesteps | 1112064 | +| train/ | | +| approx_kl | 0.008128626 | +| clip_fraction | 0.248 | +| clip_range | 0.0747 | +| entropy_loss | -7.62 | +| explained_variance | 0.015 | +| learning_rate | 4.97e-05 | +| loss | -0.0341 | +| n_updates | 17988 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000198 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.315 | +| time/ | | +| fps | 1357 | +| iterations | 544 | +| time_elapsed | 820 | +| total_timesteps | 1114112 | +| train/ | | +| approx_kl | 0.007767314 | +| clip_fraction | 0.283 | +| clip_range | 0.0747 | +| entropy_loss | -7.61 | +| explained_variance | -0.18 | +| learning_rate | 4.97e-05 | +| loss | -0.033 | +| n_updates | 17992 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000149 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1357 | +| iterations | 545 | +| time_elapsed | 822 | +| total_timesteps | 1116160 | +| train/ | | +| approx_kl | 0.007983397 | +| clip_fraction | 0.278 | +| clip_range | 0.0747 | +| entropy_loss | -7.59 | +| explained_variance | -0.175 | +| learning_rate | 4.97e-05 | +| loss | -0.033 | +| n_updates | 17996 | +| policy_gradient_loss | -0.0205 | +| value_loss | 9.1e-05 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1357 | +| iterations | 546 | +| time_elapsed | 823 | +| total_timesteps | 1118208 | +| train/ | | +| approx_kl | 0.0094715 | +| clip_fraction | 0.266 | +| clip_range | 0.0747 | +| entropy_loss | -7.21 | +| explained_variance | -0.00888 | +| learning_rate | 4.97e-05 | +| loss | -0.0267 | +| n_updates | 18000 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000263 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1357 | +| iterations | 547 | +| time_elapsed | 825 | +| total_timesteps | 1120256 | +| train/ | | +| approx_kl | 0.010417927 | +| clip_fraction | 0.3 | +| clip_range | 0.0747 | +| entropy_loss | -7.44 | +| explained_variance | -0.0431 | +| learning_rate | 4.97e-05 | +| loss | -0.0306 | +| n_updates | 18004 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000153 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1358 | +| iterations | 548 | +| time_elapsed | 826 | +| total_timesteps | 1122304 | +| train/ | | +| approx_kl | 0.009257199 | +| clip_fraction | 0.294 | +| clip_range | 0.0747 | +| entropy_loss | -7.57 | +| explained_variance | -0.194 | +| learning_rate | 4.97e-05 | +| loss | -0.0338 | +| n_updates | 18008 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000104 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1358 | +| iterations | 549 | +| time_elapsed | 827 | +| total_timesteps | 1124352 | +| train/ | | +| approx_kl | 0.010097543 | +| clip_fraction | 0.283 | +| clip_range | 0.0747 | +| entropy_loss | -7.32 | +| explained_variance | 0.0145 | +| learning_rate | 4.97e-05 | +| loss | -0.0331 | +| n_updates | 18012 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000233 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1358 | +| iterations | 550 | +| time_elapsed | 829 | +| total_timesteps | 1126400 | +| train/ | | +| approx_kl | 0.008753018 | +| clip_fraction | 0.277 | +| clip_range | 0.0747 | +| entropy_loss | -7.38 | +| explained_variance | -0.0499 | +| learning_rate | 4.97e-05 | +| loss | -0.0306 | +| n_updates | 18016 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000215 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1358 | +| iterations | 551 | +| time_elapsed | 830 | +| total_timesteps | 1128448 | +| train/ | | +| approx_kl | 0.010039385 | +| clip_fraction | 0.276 | +| clip_range | 0.0747 | +| entropy_loss | -7.31 | +| explained_variance | 0.102 | +| learning_rate | 4.97e-05 | +| loss | -0.03 | +| n_updates | 18020 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000133 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1358 | +| iterations | 552 | +| time_elapsed | 832 | +| total_timesteps | 1130496 | +| train/ | | +| approx_kl | 0.008893102 | +| clip_fraction | 0.29 | +| clip_range | 0.0747 | +| entropy_loss | -7.67 | +| explained_variance | -0.118 | +| learning_rate | 4.97e-05 | +| loss | -0.0369 | +| n_updates | 18024 | +| policy_gradient_loss | -0.023 | +| value_loss | 8.18e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1358 | +| iterations | 553 | +| time_elapsed | 833 | +| total_timesteps | 1132544 | +| train/ | | +| approx_kl | 0.008742405 | +| clip_fraction | 0.275 | +| clip_range | 0.0747 | +| entropy_loss | -7.71 | +| explained_variance | 0.00659 | +| learning_rate | 4.97e-05 | +| loss | -0.0289 | +| n_updates | 18028 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000205 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1358 | +| iterations | 554 | +| time_elapsed | 835 | +| total_timesteps | 1134592 | +| train/ | | +| approx_kl | 0.007955752 | +| clip_fraction | 0.262 | +| clip_range | 0.0747 | +| entropy_loss | -7.69 | +| explained_variance | -0.0881 | +| learning_rate | 4.97e-05 | +| loss | -0.0219 | +| n_updates | 18032 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000155 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1358 | +| iterations | 555 | +| time_elapsed | 836 | +| total_timesteps | 1136640 | +| train/ | | +| approx_kl | 0.009008016 | +| clip_fraction | 0.253 | +| clip_range | 0.0747 | +| entropy_loss | -7.59 | +| explained_variance | -0.0688 | +| learning_rate | 4.97e-05 | +| loss | -0.0321 | +| n_updates | 18036 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000117 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1358 | +| iterations | 556 | +| time_elapsed | 837 | +| total_timesteps | 1138688 | +| train/ | | +| approx_kl | 0.009545274 | +| clip_fraction | 0.271 | +| clip_range | 0.0747 | +| entropy_loss | -7.53 | +| explained_variance | -0.00189 | +| learning_rate | 4.97e-05 | +| loss | -0.0348 | +| n_updates | 18040 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000166 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1359 | +| iterations | 557 | +| time_elapsed | 839 | +| total_timesteps | 1140736 | +| train/ | | +| approx_kl | 0.008099448 | +| clip_fraction | 0.255 | +| clip_range | 0.0747 | +| entropy_loss | -7.56 | +| explained_variance | 0.00463 | +| learning_rate | 4.97e-05 | +| loss | -0.0321 | +| n_updates | 18044 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000124 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1359 | +| iterations | 558 | +| time_elapsed | 840 | +| total_timesteps | 1142784 | +| train/ | | +| approx_kl | 0.008040865 | +| clip_fraction | 0.258 | +| clip_range | 0.0747 | +| entropy_loss | -7.58 | +| explained_variance | 0.106 | +| learning_rate | 4.97e-05 | +| loss | -0.0305 | +| n_updates | 18048 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000164 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1359 | +| iterations | 559 | +| time_elapsed | 842 | +| total_timesteps | 1144832 | +| train/ | | +| approx_kl | 0.009723964 | +| clip_fraction | 0.277 | +| clip_range | 0.0747 | +| entropy_loss | -7.18 | +| explained_variance | 0.0539 | +| learning_rate | 4.97e-05 | +| loss | -0.0334 | +| n_updates | 18052 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000167 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1359 | +| iterations | 560 | +| time_elapsed | 843 | +| total_timesteps | 1146880 | +| train/ | | +| approx_kl | 0.00803393 | +| clip_fraction | 0.261 | +| clip_range | 0.0747 | +| entropy_loss | -7.56 | +| explained_variance | -0.016 | +| learning_rate | 4.97e-05 | +| loss | -0.0331 | +| n_updates | 18056 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000191 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1359 | +| iterations | 561 | +| time_elapsed | 845 | +| total_timesteps | 1148928 | +| train/ | | +| approx_kl | 0.008357135 | +| clip_fraction | 0.254 | +| clip_range | 0.0747 | +| entropy_loss | -7.45 | +| explained_variance | 0.0179 | +| learning_rate | 4.97e-05 | +| loss | -0.0314 | +| n_updates | 18060 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000148 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1359 | +| iterations | 562 | +| time_elapsed | 846 | +| total_timesteps | 1150976 | +| train/ | | +| approx_kl | 0.009300213 | +| clip_fraction | 0.287 | +| clip_range | 0.0747 | +| entropy_loss | -7.55 | +| explained_variance | -0.0292 | +| learning_rate | 4.97e-05 | +| loss | -0.0357 | +| n_updates | 18064 | +| policy_gradient_loss | -0.0224 | +| value_loss | 0.00013 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1359 | +| iterations | 563 | +| time_elapsed | 848 | +| total_timesteps | 1153024 | +| train/ | | +| approx_kl | 0.009116173 | +| clip_fraction | 0.273 | +| clip_range | 0.0747 | +| entropy_loss | -7.65 | +| explained_variance | 0.189 | +| learning_rate | 4.97e-05 | +| loss | -0.0332 | +| n_updates | 18068 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000115 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1359 | +| iterations | 564 | +| time_elapsed | 849 | +| total_timesteps | 1155072 | +| train/ | | +| approx_kl | 0.009123538 | +| clip_fraction | 0.279 | +| clip_range | 0.0747 | +| entropy_loss | -7.31 | +| explained_variance | 0.211 | +| learning_rate | 4.97e-05 | +| loss | -0.0303 | +| n_updates | 18072 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000161 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1359 | +| iterations | 565 | +| time_elapsed | 851 | +| total_timesteps | 1157120 | +| train/ | | +| approx_kl | 0.009584064 | +| clip_fraction | 0.276 | +| clip_range | 0.0747 | +| entropy_loss | -7.55 | +| explained_variance | 0.154 | +| learning_rate | 4.97e-05 | +| loss | -0.031 | +| n_updates | 18076 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000174 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1359 | +| iterations | 566 | +| time_elapsed | 852 | +| total_timesteps | 1159168 | +| train/ | | +| approx_kl | 0.009600202 | +| clip_fraction | 0.295 | +| clip_range | 0.0747 | +| entropy_loss | -7.36 | +| explained_variance | 0.241 | +| learning_rate | 4.97e-05 | +| loss | -0.0336 | +| n_updates | 18080 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000124 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1360 | +| iterations | 567 | +| time_elapsed | 853 | +| total_timesteps | 1161216 | +| train/ | | +| approx_kl | 0.008849465 | +| clip_fraction | 0.266 | +| clip_range | 0.0747 | +| entropy_loss | -7.37 | +| explained_variance | 0.152 | +| learning_rate | 4.97e-05 | +| loss | -0.0311 | +| n_updates | 18084 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000213 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1360 | +| iterations | 568 | +| time_elapsed | 855 | +| total_timesteps | 1163264 | +| train/ | | +| approx_kl | 0.009636929 | +| clip_fraction | 0.265 | +| clip_range | 0.0747 | +| entropy_loss | -7.55 | +| explained_variance | 0.0923 | +| learning_rate | 4.97e-05 | +| loss | -0.0329 | +| n_updates | 18088 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000264 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1360 | +| iterations | 569 | +| time_elapsed | 856 | +| total_timesteps | 1165312 | +| train/ | | +| approx_kl | 0.009820018 | +| clip_fraction | 0.294 | +| clip_range | 0.0747 | +| entropy_loss | -7.53 | +| explained_variance | -0.0661 | +| learning_rate | 4.97e-05 | +| loss | -0.0394 | +| n_updates | 18092 | +| policy_gradient_loss | -0.0227 | +| value_loss | 0.000315 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1360 | +| iterations | 570 | +| time_elapsed | 858 | +| total_timesteps | 1167360 | +| train/ | | +| approx_kl | 0.0090064 | +| clip_fraction | 0.311 | +| clip_range | 0.0747 | +| entropy_loss | -7.6 | +| explained_variance | -0.413 | +| learning_rate | 4.97e-05 | +| loss | -0.043 | +| n_updates | 18096 | +| policy_gradient_loss | -0.0237 | +| value_loss | 0.000109 | +--------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1360 | +| iterations | 571 | +| time_elapsed | 859 | +| total_timesteps | 1169408 | +| train/ | | +| approx_kl | 0.00854302 | +| clip_fraction | 0.297 | +| clip_range | 0.0747 | +| entropy_loss | -7.62 | +| explained_variance | -0.157 | +| learning_rate | 4.97e-05 | +| loss | -0.0332 | +| n_updates | 18100 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.00015 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1360 | +| iterations | 572 | +| time_elapsed | 860 | +| total_timesteps | 1171456 | +| train/ | | +| approx_kl | 0.00903693 | +| clip_fraction | 0.274 | +| clip_range | 0.0747 | +| entropy_loss | -7.63 | +| explained_variance | -0.0572 | +| learning_rate | 4.97e-05 | +| loss | -0.0289 | +| n_updates | 18104 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000197 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1360 | +| iterations | 573 | +| time_elapsed | 862 | +| total_timesteps | 1173504 | +| train/ | | +| approx_kl | 0.008889235 | +| clip_fraction | 0.247 | +| clip_range | 0.0747 | +| entropy_loss | -7.5 | +| explained_variance | -0.168 | +| learning_rate | 4.97e-05 | +| loss | -0.0321 | +| n_updates | 18108 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000266 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1360 | +| iterations | 574 | +| time_elapsed | 863 | +| total_timesteps | 1175552 | +| train/ | | +| approx_kl | 0.008358533 | +| clip_fraction | 0.28 | +| clip_range | 0.0747 | +| entropy_loss | -7.47 | +| explained_variance | 0.0181 | +| learning_rate | 4.97e-05 | +| loss | -0.0368 | +| n_updates | 18112 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000145 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1361 | +| iterations | 575 | +| time_elapsed | 865 | +| total_timesteps | 1177600 | +| train/ | | +| approx_kl | 0.008285408 | +| clip_fraction | 0.271 | +| clip_range | 0.0747 | +| entropy_loss | -7.48 | +| explained_variance | 0.0364 | +| learning_rate | 4.97e-05 | +| loss | -0.0297 | +| n_updates | 18116 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000261 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1361 | +| iterations | 576 | +| time_elapsed | 866 | +| total_timesteps | 1179648 | +| train/ | | +| approx_kl | 0.009263396 | +| clip_fraction | 0.278 | +| clip_range | 0.0747 | +| entropy_loss | -7.6 | +| explained_variance | -0.32 | +| learning_rate | 4.97e-05 | +| loss | -0.0339 | +| n_updates | 18120 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000155 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1361 | +| iterations | 577 | +| time_elapsed | 868 | +| total_timesteps | 1181696 | +| train/ | | +| approx_kl | 0.008951742 | +| clip_fraction | 0.268 | +| clip_range | 0.0747 | +| entropy_loss | -7.57 | +| explained_variance | 0.0788 | +| learning_rate | 4.97e-05 | +| loss | -0.0352 | +| n_updates | 18124 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000175 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1361 | +| iterations | 578 | +| time_elapsed | 869 | +| total_timesteps | 1183744 | +| train/ | | +| approx_kl | 0.008941383 | +| clip_fraction | 0.265 | +| clip_range | 0.0747 | +| entropy_loss | -7.28 | +| explained_variance | -0.0536 | +| learning_rate | 4.97e-05 | +| loss | -0.0339 | +| n_updates | 18128 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000172 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1361 | +| iterations | 579 | +| time_elapsed | 871 | +| total_timesteps | 1185792 | +| train/ | | +| approx_kl | 0.008946663 | +| clip_fraction | 0.282 | +| clip_range | 0.0747 | +| entropy_loss | -7.53 | +| explained_variance | -0.228 | +| learning_rate | 4.97e-05 | +| loss | -0.032 | +| n_updates | 18132 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000119 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1361 | +| iterations | 580 | +| time_elapsed | 872 | +| total_timesteps | 1187840 | +| train/ | | +| approx_kl | 0.009681443 | +| clip_fraction | 0.295 | +| clip_range | 0.0747 | +| entropy_loss | -7.41 | +| explained_variance | 0.00517 | +| learning_rate | 4.97e-05 | +| loss | -0.0357 | +| n_updates | 18136 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000188 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1361 | +| iterations | 581 | +| time_elapsed | 873 | +| total_timesteps | 1189888 | +| train/ | | +| approx_kl | 0.0076802573 | +| clip_fraction | 0.269 | +| clip_range | 0.0747 | +| entropy_loss | -7.49 | +| explained_variance | 0.00118 | +| learning_rate | 4.97e-05 | +| loss | -0.0304 | +| n_updates | 18140 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000233 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1361 | +| iterations | 582 | +| time_elapsed | 875 | +| total_timesteps | 1191936 | +| train/ | | +| approx_kl | 0.009075751 | +| clip_fraction | 0.274 | +| clip_range | 0.0747 | +| entropy_loss | -7.59 | +| explained_variance | -0.0349 | +| learning_rate | 4.97e-05 | +| loss | -0.0301 | +| n_updates | 18144 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000267 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1361 | +| iterations | 583 | +| time_elapsed | 876 | +| total_timesteps | 1193984 | +| train/ | | +| approx_kl | 0.00806645 | +| clip_fraction | 0.249 | +| clip_range | 0.0747 | +| entropy_loss | -7.72 | +| explained_variance | -0.105 | +| learning_rate | 4.97e-05 | +| loss | -0.0278 | +| n_updates | 18148 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000176 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1361 | +| iterations | 584 | +| time_elapsed | 878 | +| total_timesteps | 1196032 | +| train/ | | +| approx_kl | 0.008453371 | +| clip_fraction | 0.278 | +| clip_range | 0.0747 | +| entropy_loss | -7.71 | +| explained_variance | -0.201 | +| learning_rate | 4.97e-05 | +| loss | -0.0381 | +| n_updates | 18152 | +| policy_gradient_loss | -0.0222 | +| value_loss | 0.000106 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1361 | +| iterations | 585 | +| time_elapsed | 879 | +| total_timesteps | 1198080 | +| train/ | | +| approx_kl | 0.006859926 | +| clip_fraction | 0.225 | +| clip_range | 0.0747 | +| entropy_loss | -7.45 | +| explained_variance | 0.0275 | +| learning_rate | 4.97e-05 | +| loss | -0.0278 | +| n_updates | 18156 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000549 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.302 | +| time/ | | +| fps | 1362 | +| iterations | 586 | +| time_elapsed | 881 | +| total_timesteps | 1200128 | +| train/ | | +| approx_kl | 0.009034471 | +| clip_fraction | 0.283 | +| clip_range | 0.0747 | +| entropy_loss | -7.34 | +| explained_variance | -0.0196 | +| learning_rate | 4.97e-05 | +| loss | -0.0418 | +| n_updates | 18160 | +| policy_gradient_loss | -0.0228 | +| value_loss | 0.000206 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.302 | +| time/ | | +| fps | 1362 | +| iterations | 587 | +| time_elapsed | 882 | +| total_timesteps | 1202176 | +| train/ | | +| approx_kl | 0.009536024 | +| clip_fraction | 0.319 | +| clip_range | 0.0747 | +| entropy_loss | -7.32 | +| explained_variance | -0.291 | +| learning_rate | 4.97e-05 | +| loss | -0.0371 | +| n_updates | 18164 | +| policy_gradient_loss | -0.0255 | +| value_loss | 0.000107 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 1362 | +| iterations | 588 | +| time_elapsed | 884 | +| total_timesteps | 1204224 | +| train/ | | +| approx_kl | 0.010057588 | +| clip_fraction | 0.305 | +| clip_range | 0.0747 | +| entropy_loss | -7.61 | +| explained_variance | -0.0904 | +| learning_rate | 4.97e-05 | +| loss | -0.0338 | +| n_updates | 18168 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.00016 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 1362 | +| iterations | 589 | +| time_elapsed | 885 | +| total_timesteps | 1206272 | +| train/ | | +| approx_kl | 0.009944851 | +| clip_fraction | 0.273 | +| clip_range | 0.0747 | +| entropy_loss | -7.62 | +| explained_variance | -0.145 | +| learning_rate | 4.97e-05 | +| loss | -0.029 | +| n_updates | 18172 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000135 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 1362 | +| iterations | 590 | +| time_elapsed | 886 | +| total_timesteps | 1208320 | +| train/ | | +| approx_kl | 0.009936826 | +| clip_fraction | 0.285 | +| clip_range | 0.0747 | +| entropy_loss | -7.67 | +| explained_variance | -0.0256 | +| learning_rate | 4.97e-05 | +| loss | -0.0389 | +| n_updates | 18176 | +| policy_gradient_loss | -0.0226 | +| value_loss | 0.000137 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.302 | +| time/ | | +| fps | 1362 | +| iterations | 591 | +| time_elapsed | 888 | +| total_timesteps | 1210368 | +| train/ | | +| approx_kl | 0.008940625 | +| clip_fraction | 0.277 | +| clip_range | 0.0747 | +| entropy_loss | -7.75 | +| explained_variance | -0.0238 | +| learning_rate | 4.97e-05 | +| loss | -0.0272 | +| n_updates | 18180 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.00012 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.287 | +| time/ | | +| fps | 1362 | +| iterations | 592 | +| time_elapsed | 889 | +| total_timesteps | 1212416 | +| train/ | | +| approx_kl | 0.00816897 | +| clip_fraction | 0.274 | +| clip_range | 0.0747 | +| entropy_loss | -7.56 | +| explained_variance | -0.0904 | +| learning_rate | 4.97e-05 | +| loss | -0.0362 | +| n_updates | 18184 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000153 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.289 | +| time/ | | +| fps | 1362 | +| iterations | 593 | +| time_elapsed | 891 | +| total_timesteps | 1214464 | +| train/ | | +| approx_kl | 0.008425033 | +| clip_fraction | 0.254 | +| clip_range | 0.0747 | +| entropy_loss | -7.04 | +| explained_variance | 0.154 | +| learning_rate | 4.97e-05 | +| loss | -0.0305 | +| n_updates | 18188 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000181 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.289 | +| time/ | | +| fps | 1362 | +| iterations | 594 | +| time_elapsed | 892 | +| total_timesteps | 1216512 | +| train/ | | +| approx_kl | 0.0088897785 | +| clip_fraction | 0.272 | +| clip_range | 0.0747 | +| entropy_loss | -7.47 | +| explained_variance | -0.0447 | +| learning_rate | 4.97e-05 | +| loss | -0.0283 | +| n_updates | 18192 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.00015 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.289 | +| time/ | | +| fps | 1363 | +| iterations | 595 | +| time_elapsed | 893 | +| total_timesteps | 1218560 | +| train/ | | +| approx_kl | 0.009385558 | +| clip_fraction | 0.266 | +| clip_range | 0.0747 | +| entropy_loss | -7.5 | +| explained_variance | -0.153 | +| learning_rate | 4.97e-05 | +| loss | -0.0298 | +| n_updates | 18196 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000152 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.291 | +| time/ | | +| fps | 1363 | +| iterations | 596 | +| time_elapsed | 895 | +| total_timesteps | 1220608 | +| train/ | | +| approx_kl | 0.009234313 | +| clip_fraction | 0.279 | +| clip_range | 0.0747 | +| entropy_loss | -7.58 | +| explained_variance | -0.00234 | +| learning_rate | 4.97e-05 | +| loss | -0.0304 | +| n_updates | 18200 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000134 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.291 | +| time/ | | +| fps | 1363 | +| iterations | 597 | +| time_elapsed | 896 | +| total_timesteps | 1222656 | +| train/ | | +| approx_kl | 0.0073989774 | +| clip_fraction | 0.26 | +| clip_range | 0.0747 | +| entropy_loss | -7.43 | +| explained_variance | -0.071 | +| learning_rate | 4.97e-05 | +| loss | -0.0274 | +| n_updates | 18204 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000273 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.291 | +| time/ | | +| fps | 1363 | +| iterations | 598 | +| time_elapsed | 898 | +| total_timesteps | 1224704 | +| train/ | | +| approx_kl | 0.009492216 | +| clip_fraction | 0.3 | +| clip_range | 0.0747 | +| entropy_loss | -7.59 | +| explained_variance | -0.0826 | +| learning_rate | 4.97e-05 | +| loss | -0.0341 | +| n_updates | 18208 | +| policy_gradient_loss | -0.0228 | +| value_loss | 0.00012 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.29 | +| time/ | | +| fps | 1363 | +| iterations | 599 | +| time_elapsed | 899 | +| total_timesteps | 1226752 | +| train/ | | +| approx_kl | 0.0075137857 | +| clip_fraction | 0.247 | +| clip_range | 0.0747 | +| entropy_loss | -7.59 | +| explained_variance | -0.0598 | +| learning_rate | 4.97e-05 | +| loss | -0.0336 | +| n_updates | 18212 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000247 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.291 | +| time/ | | +| fps | 1363 | +| iterations | 600 | +| time_elapsed | 901 | +| total_timesteps | 1228800 | +| train/ | | +| approx_kl | 0.008731851 | +| clip_fraction | 0.259 | +| clip_range | 0.0747 | +| entropy_loss | -7.44 | +| explained_variance | 0.0606 | +| learning_rate | 4.97e-05 | +| loss | -0.0308 | +| n_updates | 18216 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000243 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.291 | +| time/ | | +| fps | 1363 | +| iterations | 601 | +| time_elapsed | 902 | +| total_timesteps | 1230848 | +| train/ | | +| approx_kl | 0.008220588 | +| clip_fraction | 0.25 | +| clip_range | 0.0747 | +| entropy_loss | -7.52 | +| explained_variance | -0.0185 | +| learning_rate | 4.97e-05 | +| loss | -0.0303 | +| n_updates | 18220 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.00028 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.286 | +| time/ | | +| fps | 1364 | +| iterations | 602 | +| time_elapsed | 903 | +| total_timesteps | 1232896 | +| train/ | | +| approx_kl | 0.0073264833 | +| clip_fraction | 0.261 | +| clip_range | 0.0747 | +| entropy_loss | -7.53 | +| explained_variance | -0.0501 | +| learning_rate | 4.97e-05 | +| loss | -0.025 | +| n_updates | 18224 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000182 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.289 | +| time/ | | +| fps | 1364 | +| iterations | 603 | +| time_elapsed | 905 | +| total_timesteps | 1234944 | +| train/ | | +| approx_kl | 0.009081342 | +| clip_fraction | 0.296 | +| clip_range | 0.0747 | +| entropy_loss | -7.56 | +| explained_variance | -0.0531 | +| learning_rate | 4.97e-05 | +| loss | -0.0372 | +| n_updates | 18228 | +| policy_gradient_loss | -0.0222 | +| value_loss | 0.000122 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.29 | +| time/ | | +| fps | 1364 | +| iterations | 604 | +| time_elapsed | 906 | +| total_timesteps | 1236992 | +| train/ | | +| approx_kl | 0.009772227 | +| clip_fraction | 0.285 | +| clip_range | 0.0747 | +| entropy_loss | -7.59 | +| explained_variance | -0.0221 | +| learning_rate | 4.97e-05 | +| loss | -0.0383 | +| n_updates | 18232 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.00018 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.285 | +| time/ | | +| fps | 1364 | +| iterations | 605 | +| time_elapsed | 908 | +| total_timesteps | 1239040 | +| train/ | | +| approx_kl | 0.008020047 | +| clip_fraction | 0.277 | +| clip_range | 0.0747 | +| entropy_loss | -7.55 | +| explained_variance | 0.022 | +| learning_rate | 4.97e-05 | +| loss | -0.0285 | +| n_updates | 18236 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000112 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 1364 | +| iterations | 606 | +| time_elapsed | 909 | +| total_timesteps | 1241088 | +| train/ | | +| approx_kl | 0.009718462 | +| clip_fraction | 0.266 | +| clip_range | 0.0747 | +| entropy_loss | -7.38 | +| explained_variance | -0.0562 | +| learning_rate | 4.97e-05 | +| loss | -0.0325 | +| n_updates | 18240 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.00021 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 1364 | +| iterations | 607 | +| time_elapsed | 910 | +| total_timesteps | 1243136 | +| train/ | | +| approx_kl | 0.009546351 | +| clip_fraction | 0.259 | +| clip_range | 0.0747 | +| entropy_loss | -7.53 | +| explained_variance | -0.0366 | +| learning_rate | 4.97e-05 | +| loss | -0.0351 | +| n_updates | 18244 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000168 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 1364 | +| iterations | 608 | +| time_elapsed | 912 | +| total_timesteps | 1245184 | +| train/ | | +| approx_kl | 0.008293646 | +| clip_fraction | 0.3 | +| clip_range | 0.0747 | +| entropy_loss | -7.36 | +| explained_variance | 0.0816 | +| learning_rate | 4.97e-05 | +| loss | -0.0358 | +| n_updates | 18248 | +| policy_gradient_loss | -0.022 | +| value_loss | 0.000152 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.272 | +| time/ | | +| fps | 1365 | +| iterations | 609 | +| time_elapsed | 913 | +| total_timesteps | 1247232 | +| train/ | | +| approx_kl | 0.009205681 | +| clip_fraction | 0.28 | +| clip_range | 0.0747 | +| entropy_loss | -7.7 | +| explained_variance | -0.0703 | +| learning_rate | 4.97e-05 | +| loss | -0.0351 | +| n_updates | 18252 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000126 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.272 | +| time/ | | +| fps | 1365 | +| iterations | 610 | +| time_elapsed | 915 | +| total_timesteps | 1249280 | +| train/ | | +| approx_kl | 0.008269021 | +| clip_fraction | 0.257 | +| clip_range | 0.0747 | +| entropy_loss | -7.64 | +| explained_variance | -0.107 | +| learning_rate | 4.97e-05 | +| loss | -0.0332 | +| n_updates | 18256 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000147 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.27 | +| time/ | | +| fps | 1365 | +| iterations | 611 | +| time_elapsed | 916 | +| total_timesteps | 1251328 | +| train/ | | +| approx_kl | 0.009184934 | +| clip_fraction | 0.277 | +| clip_range | 0.0747 | +| entropy_loss | -7.48 | +| explained_variance | -0.0599 | +| learning_rate | 4.97e-05 | +| loss | -0.0305 | +| n_updates | 18260 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000115 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.27 | +| time/ | | +| fps | 1365 | +| iterations | 612 | +| time_elapsed | 918 | +| total_timesteps | 1253376 | +| train/ | | +| approx_kl | 0.008667013 | +| clip_fraction | 0.277 | +| clip_range | 0.0747 | +| entropy_loss | -7.63 | +| explained_variance | -0.143 | +| learning_rate | 4.97e-05 | +| loss | -0.0294 | +| n_updates | 18264 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000144 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.269 | +| time/ | | +| fps | 1365 | +| iterations | 613 | +| time_elapsed | 919 | +| total_timesteps | 1255424 | +| train/ | | +| approx_kl | 0.008839962 | +| clip_fraction | 0.272 | +| clip_range | 0.0747 | +| entropy_loss | -7.62 | +| explained_variance | -0.0495 | +| learning_rate | 4.97e-05 | +| loss | -0.0325 | +| n_updates | 18268 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000195 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.266 | +| time/ | | +| fps | 1365 | +| iterations | 614 | +| time_elapsed | 920 | +| total_timesteps | 1257472 | +| train/ | | +| approx_kl | 0.00880588 | +| clip_fraction | 0.264 | +| clip_range | 0.0747 | +| entropy_loss | -7.51 | +| explained_variance | -0.00612 | +| learning_rate | 4.97e-05 | +| loss | -0.0348 | +| n_updates | 18272 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.00011 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.264 | +| time/ | | +| fps | 1365 | +| iterations | 615 | +| time_elapsed | 922 | +| total_timesteps | 1259520 | +| train/ | | +| approx_kl | 0.007980724 | +| clip_fraction | 0.265 | +| clip_range | 0.0747 | +| entropy_loss | -7.24 | +| explained_variance | 0.0112 | +| learning_rate | 4.97e-05 | +| loss | -0.028 | +| n_updates | 18276 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000245 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.265 | +| time/ | | +| fps | 1365 | +| iterations | 616 | +| time_elapsed | 923 | +| total_timesteps | 1261568 | +| train/ | | +| approx_kl | 0.008972039 | +| clip_fraction | 0.302 | +| clip_range | 0.0747 | +| entropy_loss | -7.59 | +| explained_variance | -0.307 | +| learning_rate | 4.97e-05 | +| loss | -0.0418 | +| n_updates | 18280 | +| policy_gradient_loss | -0.0227 | +| value_loss | 9.24e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.265 | +| time/ | | +| fps | 1365 | +| iterations | 617 | +| time_elapsed | 925 | +| total_timesteps | 1263616 | +| train/ | | +| approx_kl | 0.010188195 | +| clip_fraction | 0.304 | +| clip_range | 0.0747 | +| entropy_loss | -7.55 | +| explained_variance | -0.0969 | +| learning_rate | 4.97e-05 | +| loss | -0.0328 | +| n_updates | 18284 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000164 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.27 | +| time/ | | +| fps | 1365 | +| iterations | 618 | +| time_elapsed | 926 | +| total_timesteps | 1265664 | +| train/ | | +| approx_kl | 0.008757985 | +| clip_fraction | 0.272 | +| clip_range | 0.0747 | +| entropy_loss | -7.67 | +| explained_variance | -0.276 | +| learning_rate | 4.97e-05 | +| loss | -0.0319 | +| n_updates | 18288 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000101 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.271 | +| time/ | | +| fps | 1366 | +| iterations | 619 | +| time_elapsed | 928 | +| total_timesteps | 1267712 | +| train/ | | +| approx_kl | 0.008991656 | +| clip_fraction | 0.267 | +| clip_range | 0.0747 | +| entropy_loss | -7.5 | +| explained_variance | -0.0346 | +| learning_rate | 4.97e-05 | +| loss | -0.0295 | +| n_updates | 18292 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000188 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.265 | +| time/ | | +| fps | 1366 | +| iterations | 620 | +| time_elapsed | 929 | +| total_timesteps | 1269760 | +| train/ | | +| approx_kl | 0.010074589 | +| clip_fraction | 0.272 | +| clip_range | 0.0747 | +| entropy_loss | -7.58 | +| explained_variance | -0.183 | +| learning_rate | 4.97e-05 | +| loss | -0.0323 | +| n_updates | 18296 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000117 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.265 | +| time/ | | +| fps | 1366 | +| iterations | 621 | +| time_elapsed | 930 | +| total_timesteps | 1271808 | +| train/ | | +| approx_kl | 0.008556854 | +| clip_fraction | 0.274 | +| clip_range | 0.0747 | +| entropy_loss | -7.43 | +| explained_variance | -0.112 | +| learning_rate | 4.97e-05 | +| loss | -0.0329 | +| n_updates | 18300 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000178 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.26 | +| time/ | | +| fps | 1366 | +| iterations | 622 | +| time_elapsed | 932 | +| total_timesteps | 1273856 | +| train/ | | +| approx_kl | 0.00853762 | +| clip_fraction | 0.275 | +| clip_range | 0.0747 | +| entropy_loss | -7.7 | +| explained_variance | -0.0884 | +| learning_rate | 4.97e-05 | +| loss | -0.031 | +| n_updates | 18304 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000138 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.261 | +| time/ | | +| fps | 1366 | +| iterations | 623 | +| time_elapsed | 933 | +| total_timesteps | 1275904 | +| train/ | | +| approx_kl | 0.008047122 | +| clip_fraction | 0.261 | +| clip_range | 0.0747 | +| entropy_loss | -7.64 | +| explained_variance | 0.0411 | +| learning_rate | 4.97e-05 | +| loss | -0.0321 | +| n_updates | 18308 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000157 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.26 | +| time/ | | +| fps | 1366 | +| iterations | 624 | +| time_elapsed | 935 | +| total_timesteps | 1277952 | +| train/ | | +| approx_kl | 0.008491455 | +| clip_fraction | 0.272 | +| clip_range | 0.0747 | +| entropy_loss | -7.4 | +| explained_variance | -0.0215 | +| learning_rate | 4.97e-05 | +| loss | -0.0309 | +| n_updates | 18312 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000207 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.26 | +| time/ | | +| fps | 1366 | +| iterations | 625 | +| time_elapsed | 936 | +| total_timesteps | 1280000 | +| train/ | | +| approx_kl | 0.008026436 | +| clip_fraction | 0.264 | +| clip_range | 0.0747 | +| entropy_loss | -7.55 | +| explained_variance | -0.178 | +| learning_rate | 4.97e-05 | +| loss | -0.0268 | +| n_updates | 18316 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000147 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.265 | +| time/ | | +| fps | 1366 | +| iterations | 626 | +| time_elapsed | 938 | +| total_timesteps | 1282048 | +| train/ | | +| approx_kl | 0.00908082 | +| clip_fraction | 0.296 | +| clip_range | 0.0747 | +| entropy_loss | -7.68 | +| explained_variance | -0.0814 | +| learning_rate | 4.97e-05 | +| loss | -0.0309 | +| n_updates | 18320 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000141 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.265 | +| time/ | | +| fps | 1366 | +| iterations | 627 | +| time_elapsed | 939 | +| total_timesteps | 1284096 | +| train/ | | +| approx_kl | 0.008955488 | +| clip_fraction | 0.278 | +| clip_range | 0.0747 | +| entropy_loss | -7.59 | +| explained_variance | -0.105 | +| learning_rate | 4.97e-05 | +| loss | -0.0323 | +| n_updates | 18324 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.00018 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.267 | +| time/ | | +| fps | 1366 | +| iterations | 628 | +| time_elapsed | 940 | +| total_timesteps | 1286144 | +| train/ | | +| approx_kl | 0.00930722 | +| clip_fraction | 0.294 | +| clip_range | 0.0747 | +| entropy_loss | -7.35 | +| explained_variance | -0.155 | +| learning_rate | 4.97e-05 | +| loss | -0.0333 | +| n_updates | 18328 | +| policy_gradient_loss | -0.0217 | +| value_loss | 6.44e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.268 | +| time/ | | +| fps | 1366 | +| iterations | 629 | +| time_elapsed | 942 | +| total_timesteps | 1288192 | +| train/ | | +| approx_kl | 0.008845795 | +| clip_fraction | 0.259 | +| clip_range | 0.0747 | +| entropy_loss | -7.57 | +| explained_variance | 0.00936 | +| learning_rate | 4.97e-05 | +| loss | -0.0328 | +| n_updates | 18332 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000187 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.27 | +| time/ | | +| fps | 1367 | +| iterations | 630 | +| time_elapsed | 943 | +| total_timesteps | 1290240 | +| train/ | | +| approx_kl | 0.007874229 | +| clip_fraction | 0.263 | +| clip_range | 0.0747 | +| entropy_loss | -7.59 | +| explained_variance | 0.0185 | +| learning_rate | 4.97e-05 | +| loss | -0.03 | +| n_updates | 18336 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000272 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.28 | +| time/ | | +| fps | 1367 | +| iterations | 631 | +| time_elapsed | 945 | +| total_timesteps | 1292288 | +| train/ | | +| approx_kl | 0.009031586 | +| clip_fraction | 0.325 | +| clip_range | 0.0747 | +| entropy_loss | -7.62 | +| explained_variance | -0.383 | +| learning_rate | 4.97e-05 | +| loss | -0.0463 | +| n_updates | 18340 | +| policy_gradient_loss | -0.027 | +| value_loss | 6.62e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.284 | +| time/ | | +| fps | 1367 | +| iterations | 632 | +| time_elapsed | 946 | +| total_timesteps | 1294336 | +| train/ | | +| approx_kl | 0.009380123 | +| clip_fraction | 0.259 | +| clip_range | 0.0747 | +| entropy_loss | -7.43 | +| explained_variance | 0.0328 | +| learning_rate | 4.97e-05 | +| loss | -0.0258 | +| n_updates | 18344 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.00024 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.287 | +| time/ | | +| fps | 1367 | +| iterations | 633 | +| time_elapsed | 948 | +| total_timesteps | 1296384 | +| train/ | | +| approx_kl | 0.009753896 | +| clip_fraction | 0.286 | +| clip_range | 0.0747 | +| entropy_loss | -7.52 | +| explained_variance | -0.138 | +| learning_rate | 4.97e-05 | +| loss | -0.0321 | +| n_updates | 18348 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000211 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 1367 | +| iterations | 634 | +| time_elapsed | 949 | +| total_timesteps | 1298432 | +| train/ | | +| approx_kl | 0.00817458 | +| clip_fraction | 0.271 | +| clip_range | 0.0747 | +| entropy_loss | -7.55 | +| explained_variance | -0.164 | +| learning_rate | 4.97e-05 | +| loss | -0.0314 | +| n_updates | 18352 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000173 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 1367 | +| iterations | 635 | +| time_elapsed | 950 | +| total_timesteps | 1300480 | +| train/ | | +| approx_kl | 0.009272292 | +| clip_fraction | 0.284 | +| clip_range | 0.0747 | +| entropy_loss | -7.57 | +| explained_variance | -0.11 | +| learning_rate | 4.97e-05 | +| loss | -0.0324 | +| n_updates | 18356 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000182 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.282 | +| time/ | | +| fps | 1367 | +| iterations | 636 | +| time_elapsed | 952 | +| total_timesteps | 1302528 | +| train/ | | +| approx_kl | 0.010071655 | +| clip_fraction | 0.268 | +| clip_range | 0.0747 | +| entropy_loss | -7.57 | +| explained_variance | -0.0179 | +| learning_rate | 4.97e-05 | +| loss | -0.037 | +| n_updates | 18360 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.285 | +| time/ | | +| fps | 1367 | +| iterations | 637 | +| time_elapsed | 953 | +| total_timesteps | 1304576 | +| train/ | | +| approx_kl | 0.008692136 | +| clip_fraction | 0.263 | +| clip_range | 0.0747 | +| entropy_loss | -7.71 | +| explained_variance | -0.028 | +| learning_rate | 4.97e-05 | +| loss | -0.0339 | +| n_updates | 18364 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.00018 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.269 | +| time/ | | +| fps | 1367 | +| iterations | 638 | +| time_elapsed | 955 | +| total_timesteps | 1306624 | +| train/ | | +| approx_kl | 0.007643874 | +| clip_fraction | 0.245 | +| clip_range | 0.0747 | +| entropy_loss | -7.51 | +| explained_variance | -0.0944 | +| learning_rate | 4.97e-05 | +| loss | -0.0284 | +| n_updates | 18368 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000162 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.278 | +| time/ | | +| fps | 1367 | +| iterations | 639 | +| time_elapsed | 956 | +| total_timesteps | 1308672 | +| train/ | | +| approx_kl | 0.008948624 | +| clip_fraction | 0.279 | +| clip_range | 0.0747 | +| entropy_loss | -7.17 | +| explained_variance | 0.177 | +| learning_rate | 4.97e-05 | +| loss | -0.0276 | +| n_updates | 18372 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000202 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.278 | +| time/ | | +| fps | 1367 | +| iterations | 640 | +| time_elapsed | 958 | +| total_timesteps | 1310720 | +| train/ | | +| approx_kl | 0.010083631 | +| clip_fraction | 0.276 | +| clip_range | 0.0747 | +| entropy_loss | -7.26 | +| explained_variance | -0.0358 | +| learning_rate | 4.97e-05 | +| loss | -0.0325 | +| n_updates | 18376 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000195 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.278 | +| time/ | | +| fps | 1368 | +| iterations | 641 | +| time_elapsed | 959 | +| total_timesteps | 1312768 | +| train/ | | +| approx_kl | 0.010649271 | +| clip_fraction | 0.286 | +| clip_range | 0.0747 | +| entropy_loss | -7.49 | +| explained_variance | -0.0493 | +| learning_rate | 4.97e-05 | +| loss | -0.0362 | +| n_updates | 18380 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000182 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 1368 | +| iterations | 642 | +| time_elapsed | 961 | +| total_timesteps | 1314816 | +| train/ | | +| approx_kl | 0.010265079 | +| clip_fraction | 0.304 | +| clip_range | 0.0747 | +| entropy_loss | -7.72 | +| explained_variance | -0.31 | +| learning_rate | 4.97e-05 | +| loss | -0.0327 | +| n_updates | 18384 | +| policy_gradient_loss | -0.0232 | +| value_loss | 0.000124 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.278 | +| time/ | | +| fps | 1368 | +| iterations | 643 | +| time_elapsed | 962 | +| total_timesteps | 1316864 | +| train/ | | +| approx_kl | 0.00928692 | +| clip_fraction | 0.287 | +| clip_range | 0.0747 | +| entropy_loss | -7.5 | +| explained_variance | -0.054 | +| learning_rate | 4.97e-05 | +| loss | -0.0334 | +| n_updates | 18388 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000235 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.277 | +| time/ | | +| fps | 1368 | +| iterations | 644 | +| time_elapsed | 964 | +| total_timesteps | 1318912 | +| train/ | | +| approx_kl | 0.009314518 | +| clip_fraction | 0.273 | +| clip_range | 0.0747 | +| entropy_loss | -7.55 | +| explained_variance | -0.0367 | +| learning_rate | 4.97e-05 | +| loss | -0.0341 | +| n_updates | 18392 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000134 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.281 | +| time/ | | +| fps | 1368 | +| iterations | 645 | +| time_elapsed | 965 | +| total_timesteps | 1320960 | +| train/ | | +| approx_kl | 0.008861581 | +| clip_fraction | 0.285 | +| clip_range | 0.0747 | +| entropy_loss | -7.47 | +| explained_variance | 0.0649 | +| learning_rate | 4.97e-05 | +| loss | -0.0312 | +| n_updates | 18396 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.00018 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.281 | +| time/ | | +| fps | 1368 | +| iterations | 646 | +| time_elapsed | 966 | +| total_timesteps | 1323008 | +| train/ | | +| approx_kl | 0.008341214 | +| clip_fraction | 0.265 | +| clip_range | 0.0747 | +| entropy_loss | -7.61 | +| explained_variance | -0.068 | +| learning_rate | 4.97e-05 | +| loss | -0.0266 | +| n_updates | 18400 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.00019 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 1368 | +| iterations | 647 | +| time_elapsed | 968 | +| total_timesteps | 1325056 | +| train/ | | +| approx_kl | 0.009356976 | +| clip_fraction | 0.287 | +| clip_range | 0.0747 | +| entropy_loss | -7.61 | +| explained_variance | -0.0622 | +| learning_rate | 4.97e-05 | +| loss | -0.0346 | +| n_updates | 18404 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000154 | +----------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 1368 | +| iterations | 648 | +| time_elapsed | 969 | +| total_timesteps | 1327104 | +| train/ | | +| approx_kl | 0.008957 | +| clip_fraction | 0.278 | +| clip_range | 0.0747 | +| entropy_loss | -7.63 | +| explained_variance | -0.0176 | +| learning_rate | 4.97e-05 | +| loss | -0.0349 | +| n_updates | 18408 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000171 | +-------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 1368 | +| iterations | 649 | +| time_elapsed | 971 | +| total_timesteps | 1329152 | +| train/ | | +| approx_kl | 0.009291159 | +| clip_fraction | 0.277 | +| clip_range | 0.0747 | +| entropy_loss | -7.44 | +| explained_variance | -0.129 | +| learning_rate | 4.97e-05 | +| loss | -0.0326 | +| n_updates | 18412 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000194 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.274 | +| time/ | | +| fps | 1368 | +| iterations | 650 | +| time_elapsed | 972 | +| total_timesteps | 1331200 | +| train/ | | +| approx_kl | 0.009115327 | +| clip_fraction | 0.305 | +| clip_range | 0.0747 | +| entropy_loss | -7.7 | +| explained_variance | -0.417 | +| learning_rate | 4.97e-05 | +| loss | -0.0463 | +| n_updates | 18416 | +| policy_gradient_loss | -0.0258 | +| value_loss | 5.34e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 1368 | +| iterations | 651 | +| time_elapsed | 974 | +| total_timesteps | 1333248 | +| train/ | | +| approx_kl | 0.0076294416 | +| clip_fraction | 0.254 | +| clip_range | 0.0747 | +| entropy_loss | -7.29 | +| explained_variance | -0.0103 | +| learning_rate | 4.97e-05 | +| loss | -0.0302 | +| n_updates | 18420 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000171 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.275 | +| time/ | | +| fps | 1368 | +| iterations | 652 | +| time_elapsed | 975 | +| total_timesteps | 1335296 | +| train/ | | +| approx_kl | 0.008956613 | +| clip_fraction | 0.299 | +| clip_range | 0.0747 | +| entropy_loss | -7.57 | +| explained_variance | -0.135 | +| learning_rate | 4.97e-05 | +| loss | -0.0416 | +| n_updates | 18424 | +| policy_gradient_loss | -0.0213 | +| value_loss | 9.66e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.274 | +| time/ | | +| fps | 1368 | +| iterations | 653 | +| time_elapsed | 977 | +| total_timesteps | 1337344 | +| train/ | | +| approx_kl | 0.010740713 | +| clip_fraction | 0.318 | +| clip_range | 0.0747 | +| entropy_loss | -7.61 | +| explained_variance | 0.0626 | +| learning_rate | 4.97e-05 | +| loss | -0.0376 | +| n_updates | 18428 | +| policy_gradient_loss | -0.0241 | +| value_loss | 4.47e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.274 | +| time/ | | +| fps | 1368 | +| iterations | 654 | +| time_elapsed | 978 | +| total_timesteps | 1339392 | +| train/ | | +| approx_kl | 0.009318721 | +| clip_fraction | 0.292 | +| clip_range | 0.0747 | +| entropy_loss | -7.37 | +| explained_variance | -0.0262 | +| learning_rate | 4.97e-05 | +| loss | -0.0276 | +| n_updates | 18432 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000287 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.277 | +| time/ | | +| fps | 1369 | +| iterations | 655 | +| time_elapsed | 979 | +| total_timesteps | 1341440 | +| train/ | | +| approx_kl | 0.009975482 | +| clip_fraction | 0.305 | +| clip_range | 0.0747 | +| entropy_loss | -7.24 | +| explained_variance | -0.019 | +| learning_rate | 4.97e-05 | +| loss | -0.0389 | +| n_updates | 18436 | +| policy_gradient_loss | -0.0226 | +| value_loss | 0.000131 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.277 | +| time/ | | +| fps | 1369 | +| iterations | 656 | +| time_elapsed | 981 | +| total_timesteps | 1343488 | +| train/ | | +| approx_kl | 0.010285802 | +| clip_fraction | 0.288 | +| clip_range | 0.0747 | +| entropy_loss | -7.51 | +| explained_variance | 0.0371 | +| learning_rate | 4.97e-05 | +| loss | -0.0292 | +| n_updates | 18440 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000181 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.278 | +| time/ | | +| fps | 1369 | +| iterations | 657 | +| time_elapsed | 982 | +| total_timesteps | 1345536 | +| train/ | | +| approx_kl | 0.008841103 | +| clip_fraction | 0.281 | +| clip_range | 0.0747 | +| entropy_loss | -7.64 | +| explained_variance | -0.181 | +| learning_rate | 4.97e-05 | +| loss | -0.035 | +| n_updates | 18444 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000225 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 1369 | +| iterations | 658 | +| time_elapsed | 984 | +| total_timesteps | 1347584 | +| train/ | | +| approx_kl | 0.008911684 | +| clip_fraction | 0.297 | +| clip_range | 0.0747 | +| entropy_loss | -7.35 | +| explained_variance | -0.0296 | +| learning_rate | 4.97e-05 | +| loss | -0.0338 | +| n_updates | 18448 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000161 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.279 | +| time/ | | +| fps | 1369 | +| iterations | 659 | +| time_elapsed | 985 | +| total_timesteps | 1349632 | +| train/ | | +| approx_kl | 0.008934712 | +| clip_fraction | 0.284 | +| clip_range | 0.0747 | +| entropy_loss | -7.41 | +| explained_variance | -0.00896 | +| learning_rate | 4.97e-05 | +| loss | -0.0272 | +| n_updates | 18452 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000236 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.283 | +| time/ | | +| fps | 1369 | +| iterations | 660 | +| time_elapsed | 986 | +| total_timesteps | 1351680 | +| train/ | | +| approx_kl | 0.009343425 | +| clip_fraction | 0.289 | +| clip_range | 0.0747 | +| entropy_loss | -7.65 | +| explained_variance | -0.192 | +| learning_rate | 4.97e-05 | +| loss | -0.0348 | +| n_updates | 18456 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000106 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.288 | +| time/ | | +| fps | 1369 | +| iterations | 661 | +| time_elapsed | 988 | +| total_timesteps | 1353728 | +| train/ | | +| approx_kl | 0.009607827 | +| clip_fraction | 0.274 | +| clip_range | 0.0747 | +| entropy_loss | -7.49 | +| explained_variance | 0.0231 | +| learning_rate | 4.97e-05 | +| loss | -0.033 | +| n_updates | 18460 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000258 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.288 | +| time/ | | +| fps | 1369 | +| iterations | 662 | +| time_elapsed | 989 | +| total_timesteps | 1355776 | +| train/ | | +| approx_kl | 0.0072549055 | +| clip_fraction | 0.251 | +| clip_range | 0.0747 | +| entropy_loss | -7.62 | +| explained_variance | 0.0618 | +| learning_rate | 4.97e-05 | +| loss | -0.0328 | +| n_updates | 18464 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000215 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.289 | +| time/ | | +| fps | 1369 | +| iterations | 663 | +| time_elapsed | 991 | +| total_timesteps | 1357824 | +| train/ | | +| approx_kl | 0.009168388 | +| clip_fraction | 0.283 | +| clip_range | 0.0747 | +| entropy_loss | -7.53 | +| explained_variance | 0.00885 | +| learning_rate | 4.97e-05 | +| loss | -0.0357 | +| n_updates | 18468 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.0002 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.289 | +| time/ | | +| fps | 1369 | +| iterations | 664 | +| time_elapsed | 992 | +| total_timesteps | 1359872 | +| train/ | | +| approx_kl | 0.008039904 | +| clip_fraction | 0.271 | +| clip_range | 0.0747 | +| entropy_loss | -7.5 | +| explained_variance | 0.0485 | +| learning_rate | 4.97e-05 | +| loss | -0.0371 | +| n_updates | 18472 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000192 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.291 | +| time/ | | +| fps | 1369 | +| iterations | 665 | +| time_elapsed | 994 | +| total_timesteps | 1361920 | +| train/ | | +| approx_kl | 0.009212005 | +| clip_fraction | 0.299 | +| clip_range | 0.0747 | +| entropy_loss | -7.61 | +| explained_variance | -0.0148 | +| learning_rate | 4.97e-05 | +| loss | -0.0366 | +| n_updates | 18476 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000143 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.291 | +| time/ | | +| fps | 1369 | +| iterations | 666 | +| time_elapsed | 995 | +| total_timesteps | 1363968 | +| train/ | | +| approx_kl | 0.009093316 | +| clip_fraction | 0.27 | +| clip_range | 0.0747 | +| entropy_loss | -7.43 | +| explained_variance | 0.0368 | +| learning_rate | 4.97e-05 | +| loss | -0.0359 | +| n_updates | 18480 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000232 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.291 | +| time/ | | +| fps | 1369 | +| iterations | 667 | +| time_elapsed | 997 | +| total_timesteps | 1366016 | +| train/ | | +| approx_kl | 0.0074023637 | +| clip_fraction | 0.242 | +| clip_range | 0.0747 | +| entropy_loss | -7.3 | +| explained_variance | 0.184 | +| learning_rate | 4.97e-05 | +| loss | -0.035 | +| n_updates | 18484 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000289 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.286 | +| time/ | | +| fps | 1369 | +| iterations | 668 | +| time_elapsed | 998 | +| total_timesteps | 1368064 | +| train/ | | +| approx_kl | 0.008067713 | +| clip_fraction | 0.282 | +| clip_range | 0.0747 | +| entropy_loss | -7.6 | +| explained_variance | 0.155 | +| learning_rate | 4.97e-05 | +| loss | -0.0289 | +| n_updates | 18488 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000179 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.29 | +| time/ | | +| fps | 1370 | +| iterations | 669 | +| time_elapsed | 1000 | +| total_timesteps | 1370112 | +| train/ | | +| approx_kl | 0.008865301 | +| clip_fraction | 0.261 | +| clip_range | 0.0747 | +| entropy_loss | -7.46 | +| explained_variance | -0.0991 | +| learning_rate | 4.97e-05 | +| loss | -0.0304 | +| n_updates | 18492 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000199 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.289 | +| time/ | | +| fps | 1370 | +| iterations | 670 | +| time_elapsed | 1001 | +| total_timesteps | 1372160 | +| train/ | | +| approx_kl | 0.007343625 | +| clip_fraction | 0.267 | +| clip_range | 0.0747 | +| entropy_loss | -7.36 | +| explained_variance | 0.235 | +| learning_rate | 4.97e-05 | +| loss | -0.0284 | +| n_updates | 18496 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000315 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.287 | +| time/ | | +| fps | 1370 | +| iterations | 671 | +| time_elapsed | 1002 | +| total_timesteps | 1374208 | +| train/ | | +| approx_kl | 0.009415671 | +| clip_fraction | 0.279 | +| clip_range | 0.0747 | +| entropy_loss | -7.5 | +| explained_variance | -0.0246 | +| learning_rate | 4.97e-05 | +| loss | -0.0368 | +| n_updates | 18500 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000166 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.287 | +| time/ | | +| fps | 1370 | +| iterations | 672 | +| time_elapsed | 1004 | +| total_timesteps | 1376256 | +| train/ | | +| approx_kl | 0.008492164 | +| clip_fraction | 0.279 | +| clip_range | 0.0747 | +| entropy_loss | -7.58 | +| explained_variance | -0.149 | +| learning_rate | 4.97e-05 | +| loss | -0.0361 | +| n_updates | 18504 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000159 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.287 | +| time/ | | +| fps | 1370 | +| iterations | 673 | +| time_elapsed | 1005 | +| total_timesteps | 1378304 | +| train/ | | +| approx_kl | 0.009202266 | +| clip_fraction | 0.274 | +| clip_range | 0.0747 | +| entropy_loss | -7.66 | +| explained_variance | -0.221 | +| learning_rate | 4.97e-05 | +| loss | -0.0378 | +| n_updates | 18508 | +| policy_gradient_loss | -0.0219 | +| value_loss | 0.000143 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.287 | +| time/ | | +| fps | 1370 | +| iterations | 674 | +| time_elapsed | 1007 | +| total_timesteps | 1380352 | +| train/ | | +| approx_kl | 0.008559827 | +| clip_fraction | 0.274 | +| clip_range | 0.0747 | +| entropy_loss | -7.72 | +| explained_variance | -0.122 | +| learning_rate | 4.97e-05 | +| loss | -0.033 | +| n_updates | 18512 | +| policy_gradient_loss | -0.0211 | +| value_loss | 9.22e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.289 | +| time/ | | +| fps | 1370 | +| iterations | 675 | +| time_elapsed | 1008 | +| total_timesteps | 1382400 | +| train/ | | +| approx_kl | 0.007840915 | +| clip_fraction | 0.276 | +| clip_range | 0.0747 | +| entropy_loss | -7.77 | +| explained_variance | -0.0152 | +| learning_rate | 4.97e-05 | +| loss | -0.038 | +| n_updates | 18516 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000128 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.292 | +| time/ | | +| fps | 1370 | +| iterations | 676 | +| time_elapsed | 1009 | +| total_timesteps | 1384448 | +| train/ | | +| approx_kl | 0.008148731 | +| clip_fraction | 0.262 | +| clip_range | 0.0747 | +| entropy_loss | -7.1 | +| explained_variance | 0.0902 | +| learning_rate | 4.97e-05 | +| loss | -0.0286 | +| n_updates | 18520 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000143 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 1371 | +| iterations | 677 | +| time_elapsed | 1011 | +| total_timesteps | 1386496 | +| train/ | | +| approx_kl | 0.009662994 | +| clip_fraction | 0.285 | +| clip_range | 0.0747 | +| entropy_loss | -7.44 | +| explained_variance | -0.0569 | +| learning_rate | 4.97e-05 | +| loss | -0.0349 | +| n_updates | 18524 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000139 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 1371 | +| iterations | 678 | +| time_elapsed | 1012 | +| total_timesteps | 1388544 | +| train/ | | +| approx_kl | 0.009408932 | +| clip_fraction | 0.287 | +| clip_range | 0.0747 | +| entropy_loss | -7.09 | +| explained_variance | 0.0875 | +| learning_rate | 4.97e-05 | +| loss | -0.0292 | +| n_updates | 18528 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000368 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 1371 | +| iterations | 679 | +| time_elapsed | 1014 | +| total_timesteps | 1390592 | +| train/ | | +| approx_kl | 0.009559351 | +| clip_fraction | 0.277 | +| clip_range | 0.0747 | +| entropy_loss | -7.53 | +| explained_variance | -0.0986 | +| learning_rate | 4.97e-05 | +| loss | -0.0332 | +| n_updates | 18532 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000184 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 1371 | +| iterations | 680 | +| time_elapsed | 1015 | +| total_timesteps | 1392640 | +| train/ | | +| approx_kl | 0.009439137 | +| clip_fraction | 0.293 | +| clip_range | 0.0747 | +| entropy_loss | -7.74 | +| explained_variance | -0.197 | +| learning_rate | 4.97e-05 | +| loss | -0.0365 | +| n_updates | 18536 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000124 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 1371 | +| iterations | 681 | +| time_elapsed | 1017 | +| total_timesteps | 1394688 | +| train/ | | +| approx_kl | 0.007733922 | +| clip_fraction | 0.232 | +| clip_range | 0.0747 | +| entropy_loss | -7.33 | +| explained_variance | -0.0187 | +| learning_rate | 4.97e-05 | +| loss | -0.0272 | +| n_updates | 18540 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000417 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 1371 | +| iterations | 682 | +| time_elapsed | 1018 | +| total_timesteps | 1396736 | +| train/ | | +| approx_kl | 0.010297631 | +| clip_fraction | 0.284 | +| clip_range | 0.0747 | +| entropy_loss | -7.62 | +| explained_variance | -0.127 | +| learning_rate | 4.97e-05 | +| loss | -0.0314 | +| n_updates | 18544 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000174 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 1371 | +| iterations | 683 | +| time_elapsed | 1019 | +| total_timesteps | 1398784 | +| train/ | | +| approx_kl | 0.007610241 | +| clip_fraction | 0.268 | +| clip_range | 0.0747 | +| entropy_loss | -7.65 | +| explained_variance | -0.0418 | +| learning_rate | 4.97e-05 | +| loss | -0.0319 | +| n_updates | 18548 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000206 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1371 | +| iterations | 684 | +| time_elapsed | 1021 | +| total_timesteps | 1400832 | +| train/ | | +| approx_kl | 0.0075698695 | +| clip_fraction | 0.271 | +| clip_range | 0.0747 | +| entropy_loss | -7.63 | +| explained_variance | -0.108 | +| learning_rate | 4.97e-05 | +| loss | -0.0352 | +| n_updates | 18552 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000253 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1371 | +| iterations | 685 | +| time_elapsed | 1022 | +| total_timesteps | 1402880 | +| train/ | | +| approx_kl | 0.006803516 | +| clip_fraction | 0.239 | +| clip_range | 0.0746 | +| entropy_loss | -7.36 | +| explained_variance | 0.0805 | +| learning_rate | 4.97e-05 | +| loss | -0.0326 | +| n_updates | 18556 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000222 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 1371 | +| iterations | 686 | +| time_elapsed | 1024 | +| total_timesteps | 1404928 | +| train/ | | +| approx_kl | 0.008321766 | +| clip_fraction | 0.264 | +| clip_range | 0.0746 | +| entropy_loss | -7.69 | +| explained_variance | -0.0362 | +| learning_rate | 4.97e-05 | +| loss | -0.0343 | +| n_updates | 18560 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000158 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 1372 | +| iterations | 687 | +| time_elapsed | 1025 | +| total_timesteps | 1406976 | +| train/ | | +| approx_kl | 0.007932963 | +| clip_fraction | 0.296 | +| clip_range | 0.0746 | +| entropy_loss | -7.52 | +| explained_variance | -0.0451 | +| learning_rate | 4.97e-05 | +| loss | -0.0363 | +| n_updates | 18564 | +| policy_gradient_loss | -0.0218 | +| value_loss | 8.59e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1372 | +| iterations | 688 | +| time_elapsed | 1026 | +| total_timesteps | 1409024 | +| train/ | | +| approx_kl | 0.009068441 | +| clip_fraction | 0.262 | +| clip_range | 0.0746 | +| entropy_loss | -7.7 | +| explained_variance | -0.194 | +| learning_rate | 4.97e-05 | +| loss | -0.0318 | +| n_updates | 18568 | +| policy_gradient_loss | -0.0198 | +| value_loss | 9.91e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1372 | +| iterations | 689 | +| time_elapsed | 1028 | +| total_timesteps | 1411072 | +| train/ | | +| approx_kl | 0.007305463 | +| clip_fraction | 0.242 | +| clip_range | 0.0746 | +| entropy_loss | -7.04 | +| explained_variance | 0.089 | +| learning_rate | 4.97e-05 | +| loss | -0.0274 | +| n_updates | 18572 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000277 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1372 | +| iterations | 690 | +| time_elapsed | 1029 | +| total_timesteps | 1413120 | +| train/ | | +| approx_kl | 0.010532126 | +| clip_fraction | 0.287 | +| clip_range | 0.0746 | +| entropy_loss | -7.6 | +| explained_variance | -0.231 | +| learning_rate | 4.97e-05 | +| loss | -0.0372 | +| n_updates | 18576 | +| policy_gradient_loss | -0.0228 | +| value_loss | 0.000209 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1372 | +| iterations | 691 | +| time_elapsed | 1031 | +| total_timesteps | 1415168 | +| train/ | | +| approx_kl | 0.008645482 | +| clip_fraction | 0.267 | +| clip_range | 0.0746 | +| entropy_loss | -7.41 | +| explained_variance | -0.0644 | +| learning_rate | 4.97e-05 | +| loss | -0.0337 | +| n_updates | 18580 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000194 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1372 | +| iterations | 692 | +| time_elapsed | 1032 | +| total_timesteps | 1417216 | +| train/ | | +| approx_kl | 0.009227131 | +| clip_fraction | 0.257 | +| clip_range | 0.0746 | +| entropy_loss | -7.53 | +| explained_variance | 0.0373 | +| learning_rate | 4.97e-05 | +| loss | -0.0355 | +| n_updates | 18584 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000224 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1372 | +| iterations | 693 | +| time_elapsed | 1034 | +| total_timesteps | 1419264 | +| train/ | | +| approx_kl | 0.009668637 | +| clip_fraction | 0.284 | +| clip_range | 0.0746 | +| entropy_loss | -7.48 | +| explained_variance | -0.105 | +| learning_rate | 4.97e-05 | +| loss | -0.0362 | +| n_updates | 18588 | +| policy_gradient_loss | -0.0232 | +| value_loss | 0.000148 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 1372 | +| iterations | 694 | +| time_elapsed | 1035 | +| total_timesteps | 1421312 | +| train/ | | +| approx_kl | 0.008790843 | +| clip_fraction | 0.281 | +| clip_range | 0.0746 | +| entropy_loss | -7.54 | +| explained_variance | 0.125 | +| learning_rate | 4.97e-05 | +| loss | -0.0352 | +| n_updates | 18592 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000132 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 1372 | +| iterations | 695 | +| time_elapsed | 1036 | +| total_timesteps | 1423360 | +| train/ | | +| approx_kl | 0.009358352 | +| clip_fraction | 0.277 | +| clip_range | 0.0746 | +| entropy_loss | -7.46 | +| explained_variance | 0.0694 | +| learning_rate | 4.97e-05 | +| loss | -0.0349 | +| n_updates | 18596 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000115 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1372 | +| iterations | 696 | +| time_elapsed | 1038 | +| total_timesteps | 1425408 | +| train/ | | +| approx_kl | 0.009444327 | +| clip_fraction | 0.258 | +| clip_range | 0.0746 | +| entropy_loss | -7.69 | +| explained_variance | -0.0465 | +| learning_rate | 4.97e-05 | +| loss | -0.0332 | +| n_updates | 18600 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000193 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 1372 | +| iterations | 697 | +| time_elapsed | 1039 | +| total_timesteps | 1427456 | +| train/ | | +| approx_kl | 0.007915786 | +| clip_fraction | 0.246 | +| clip_range | 0.0746 | +| entropy_loss | -7.68 | +| explained_variance | -0.0484 | +| learning_rate | 4.97e-05 | +| loss | -0.0312 | +| n_updates | 18604 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000225 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1372 | +| iterations | 698 | +| time_elapsed | 1041 | +| total_timesteps | 1429504 | +| train/ | | +| approx_kl | 0.008933797 | +| clip_fraction | 0.275 | +| clip_range | 0.0746 | +| entropy_loss | -7.49 | +| explained_variance | 0.0867 | +| learning_rate | 4.97e-05 | +| loss | -0.0318 | +| n_updates | 18608 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.00021 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1373 | +| iterations | 699 | +| time_elapsed | 1042 | +| total_timesteps | 1431552 | +| train/ | | +| approx_kl | 0.0086627845 | +| clip_fraction | 0.29 | +| clip_range | 0.0746 | +| entropy_loss | -7.55 | +| explained_variance | -0.0462 | +| learning_rate | 4.97e-05 | +| loss | -0.0322 | +| n_updates | 18612 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000299 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1373 | +| iterations | 700 | +| time_elapsed | 1044 | +| total_timesteps | 1433600 | +| train/ | | +| approx_kl | 0.008279782 | +| clip_fraction | 0.26 | +| clip_range | 0.0746 | +| entropy_loss | -7.18 | +| explained_variance | -0.00842 | +| learning_rate | 4.97e-05 | +| loss | -0.0279 | +| n_updates | 18616 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000343 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 1373 | +| iterations | 701 | +| time_elapsed | 1045 | +| total_timesteps | 1435648 | +| train/ | | +| approx_kl | 0.01029317 | +| clip_fraction | 0.311 | +| clip_range | 0.0746 | +| entropy_loss | -7.5 | +| explained_variance | -0.0147 | +| learning_rate | 4.97e-05 | +| loss | -0.0382 | +| n_updates | 18620 | +| policy_gradient_loss | -0.023 | +| value_loss | 0.000144 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1373 | +| iterations | 702 | +| time_elapsed | 1046 | +| total_timesteps | 1437696 | +| train/ | | +| approx_kl | 0.0095938025 | +| clip_fraction | 0.287 | +| clip_range | 0.0746 | +| entropy_loss | -7.65 | +| explained_variance | -0.19 | +| learning_rate | 4.97e-05 | +| loss | -0.0358 | +| n_updates | 18624 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000145 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1373 | +| iterations | 703 | +| time_elapsed | 1048 | +| total_timesteps | 1439744 | +| train/ | | +| approx_kl | 0.008094434 | +| clip_fraction | 0.251 | +| clip_range | 0.0746 | +| entropy_loss | -7.56 | +| explained_variance | 0.022 | +| learning_rate | 4.97e-05 | +| loss | -0.0295 | +| n_updates | 18628 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000235 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1373 | +| iterations | 704 | +| time_elapsed | 1049 | +| total_timesteps | 1441792 | +| train/ | | +| approx_kl | 0.008289761 | +| clip_fraction | 0.275 | +| clip_range | 0.0746 | +| entropy_loss | -7.33 | +| explained_variance | 0.00168 | +| learning_rate | 4.97e-05 | +| loss | -0.0342 | +| n_updates | 18632 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000327 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1373 | +| iterations | 705 | +| time_elapsed | 1051 | +| total_timesteps | 1443840 | +| train/ | | +| approx_kl | 0.008007402 | +| clip_fraction | 0.265 | +| clip_range | 0.0746 | +| entropy_loss | -7.66 | +| explained_variance | -0.155 | +| learning_rate | 4.97e-05 | +| loss | -0.041 | +| n_updates | 18636 | +| policy_gradient_loss | -0.0224 | +| value_loss | 0.000188 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1373 | +| iterations | 706 | +| time_elapsed | 1052 | +| total_timesteps | 1445888 | +| train/ | | +| approx_kl | 0.007482747 | +| clip_fraction | 0.276 | +| clip_range | 0.0746 | +| entropy_loss | -7.74 | +| explained_variance | -0.117 | +| learning_rate | 4.97e-05 | +| loss | -0.0309 | +| n_updates | 18640 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000144 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.315 | +| time/ | | +| fps | 1373 | +| iterations | 707 | +| time_elapsed | 1053 | +| total_timesteps | 1447936 | +| train/ | | +| approx_kl | 0.009548544 | +| clip_fraction | 0.286 | +| clip_range | 0.0746 | +| entropy_loss | -7.55 | +| explained_variance | -0.0909 | +| learning_rate | 4.97e-05 | +| loss | -0.0306 | +| n_updates | 18644 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000189 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1373 | +| iterations | 708 | +| time_elapsed | 1055 | +| total_timesteps | 1449984 | +| train/ | | +| approx_kl | 0.008888608 | +| clip_fraction | 0.287 | +| clip_range | 0.0746 | +| entropy_loss | -7.6 | +| explained_variance | -0.123 | +| learning_rate | 4.97e-05 | +| loss | -0.0328 | +| n_updates | 18648 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000193 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1374 | +| iterations | 709 | +| time_elapsed | 1056 | +| total_timesteps | 1452032 | +| train/ | | +| approx_kl | 0.008485377 | +| clip_fraction | 0.267 | +| clip_range | 0.0746 | +| entropy_loss | -7.6 | +| explained_variance | -0.0614 | +| learning_rate | 4.97e-05 | +| loss | -0.0351 | +| n_updates | 18652 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.0002 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1374 | +| iterations | 710 | +| time_elapsed | 1058 | +| total_timesteps | 1454080 | +| train/ | | +| approx_kl | 0.008875362 | +| clip_fraction | 0.265 | +| clip_range | 0.0746 | +| entropy_loss | -7.45 | +| explained_variance | 0.0219 | +| learning_rate | 4.97e-05 | +| loss | -0.0308 | +| n_updates | 18656 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000168 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1374 | +| iterations | 711 | +| time_elapsed | 1059 | +| total_timesteps | 1456128 | +| train/ | | +| approx_kl | 0.007759755 | +| clip_fraction | 0.265 | +| clip_range | 0.0746 | +| entropy_loss | -7.23 | +| explained_variance | 0.0883 | +| learning_rate | 4.97e-05 | +| loss | -0.0278 | +| n_updates | 18660 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000429 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1374 | +| iterations | 712 | +| time_elapsed | 1061 | +| total_timesteps | 1458176 | +| train/ | | +| approx_kl | 0.008441816 | +| clip_fraction | 0.257 | +| clip_range | 0.0746 | +| entropy_loss | -7.66 | +| explained_variance | -0.0832 | +| learning_rate | 4.97e-05 | +| loss | -0.034 | +| n_updates | 18664 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.0002 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1374 | +| iterations | 713 | +| time_elapsed | 1062 | +| total_timesteps | 1460224 | +| train/ | | +| approx_kl | 0.00827731 | +| clip_fraction | 0.264 | +| clip_range | 0.0746 | +| entropy_loss | -7.6 | +| explained_variance | 0.00148 | +| learning_rate | 4.97e-05 | +| loss | -0.0346 | +| n_updates | 18668 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000228 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.315 | +| time/ | | +| fps | 1374 | +| iterations | 714 | +| time_elapsed | 1063 | +| total_timesteps | 1462272 | +| train/ | | +| approx_kl | 0.0087873675 | +| clip_fraction | 0.257 | +| clip_range | 0.0746 | +| entropy_loss | -7.49 | +| explained_variance | 0.106 | +| learning_rate | 4.97e-05 | +| loss | -0.0362 | +| n_updates | 18672 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.00017 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1374 | +| iterations | 715 | +| time_elapsed | 1065 | +| total_timesteps | 1464320 | +| train/ | | +| approx_kl | 0.008226445 | +| clip_fraction | 0.279 | +| clip_range | 0.0746 | +| entropy_loss | -7.59 | +| explained_variance | -0.0527 | +| learning_rate | 4.97e-05 | +| loss | -0.0369 | +| n_updates | 18676 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000109 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1374 | +| iterations | 716 | +| time_elapsed | 1066 | +| total_timesteps | 1466368 | +| train/ | | +| approx_kl | 0.0075472496 | +| clip_fraction | 0.264 | +| clip_range | 0.0746 | +| entropy_loss | -7.54 | +| explained_variance | 0.211 | +| learning_rate | 4.97e-05 | +| loss | -0.035 | +| n_updates | 18680 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000235 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1374 | +| iterations | 717 | +| time_elapsed | 1068 | +| total_timesteps | 1468416 | +| train/ | | +| approx_kl | 0.008559702 | +| clip_fraction | 0.263 | +| clip_range | 0.0746 | +| entropy_loss | -7.43 | +| explained_variance | 0.211 | +| learning_rate | 4.97e-05 | +| loss | -0.0336 | +| n_updates | 18684 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000347 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1374 | +| iterations | 718 | +| time_elapsed | 1069 | +| total_timesteps | 1470464 | +| train/ | | +| approx_kl | 0.008858343 | +| clip_fraction | 0.271 | +| clip_range | 0.0746 | +| entropy_loss | -7.69 | +| explained_variance | -0.0574 | +| learning_rate | 4.97e-05 | +| loss | -0.0346 | +| n_updates | 18688 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000205 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1374 | +| iterations | 719 | +| time_elapsed | 1071 | +| total_timesteps | 1472512 | +| train/ | | +| approx_kl | 0.0076602586 | +| clip_fraction | 0.281 | +| clip_range | 0.0746 | +| entropy_loss | -7.56 | +| explained_variance | 0.0723 | +| learning_rate | 4.97e-05 | +| loss | -0.0364 | +| n_updates | 18692 | +| policy_gradient_loss | -0.0224 | +| value_loss | 0.000116 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1374 | +| iterations | 720 | +| time_elapsed | 1072 | +| total_timesteps | 1474560 | +| train/ | | +| approx_kl | 0.009564621 | +| clip_fraction | 0.254 | +| clip_range | 0.0746 | +| entropy_loss | -7.52 | +| explained_variance | -0.00111 | +| learning_rate | 4.97e-05 | +| loss | -0.0306 | +| n_updates | 18696 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000171 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1374 | +| iterations | 721 | +| time_elapsed | 1074 | +| total_timesteps | 1476608 | +| train/ | | +| approx_kl | 0.009076033 | +| clip_fraction | 0.277 | +| clip_range | 0.0746 | +| entropy_loss | -7.46 | +| explained_variance | -0.236 | +| learning_rate | 4.96e-05 | +| loss | -0.0409 | +| n_updates | 18700 | +| policy_gradient_loss | -0.0217 | +| value_loss | 9.83e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1374 | +| iterations | 722 | +| time_elapsed | 1075 | +| total_timesteps | 1478656 | +| train/ | | +| approx_kl | 0.0071462104 | +| clip_fraction | 0.251 | +| clip_range | 0.0746 | +| entropy_loss | -7.54 | +| explained_variance | 0.0095 | +| learning_rate | 4.96e-05 | +| loss | -0.0268 | +| n_updates | 18704 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000292 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1375 | +| iterations | 723 | +| time_elapsed | 1076 | +| total_timesteps | 1480704 | +| train/ | | +| approx_kl | 0.006622905 | +| clip_fraction | 0.246 | +| clip_range | 0.0746 | +| entropy_loss | -7.13 | +| explained_variance | 0.0993 | +| learning_rate | 4.96e-05 | +| loss | -0.0286 | +| n_updates | 18708 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000203 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1375 | +| iterations | 724 | +| time_elapsed | 1078 | +| total_timesteps | 1482752 | +| train/ | | +| approx_kl | 0.009003914 | +| clip_fraction | 0.253 | +| clip_range | 0.0746 | +| entropy_loss | -7.53 | +| explained_variance | -0.0644 | +| learning_rate | 4.96e-05 | +| loss | -0.0355 | +| n_updates | 18712 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000179 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1375 | +| iterations | 725 | +| time_elapsed | 1079 | +| total_timesteps | 1484800 | +| train/ | | +| approx_kl | 0.007826818 | +| clip_fraction | 0.241 | +| clip_range | 0.0746 | +| entropy_loss | -7.5 | +| explained_variance | -0.197 | +| learning_rate | 4.96e-05 | +| loss | -0.0274 | +| n_updates | 18716 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000205 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1375 | +| iterations | 726 | +| time_elapsed | 1081 | +| total_timesteps | 1486848 | +| train/ | | +| approx_kl | 0.008595564 | +| clip_fraction | 0.269 | +| clip_range | 0.0746 | +| entropy_loss | -7.67 | +| explained_variance | -0.0522 | +| learning_rate | 4.96e-05 | +| loss | -0.0349 | +| n_updates | 18720 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000189 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1375 | +| iterations | 727 | +| time_elapsed | 1082 | +| total_timesteps | 1488896 | +| train/ | | +| approx_kl | 0.009770406 | +| clip_fraction | 0.275 | +| clip_range | 0.0746 | +| entropy_loss | -7.48 | +| explained_variance | -0.12 | +| learning_rate | 4.96e-05 | +| loss | -0.035 | +| n_updates | 18724 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000182 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1375 | +| iterations | 728 | +| time_elapsed | 1083 | +| total_timesteps | 1490944 | +| train/ | | +| approx_kl | 0.009860342 | +| clip_fraction | 0.286 | +| clip_range | 0.0746 | +| entropy_loss | -7.46 | +| explained_variance | -0.00152 | +| learning_rate | 4.96e-05 | +| loss | -0.0333 | +| n_updates | 18728 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000212 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1375 | +| iterations | 729 | +| time_elapsed | 1085 | +| total_timesteps | 1492992 | +| train/ | | +| approx_kl | 0.009360127 | +| clip_fraction | 0.3 | +| clip_range | 0.0746 | +| entropy_loss | -7.69 | +| explained_variance | -0.222 | +| learning_rate | 4.96e-05 | +| loss | -0.0392 | +| n_updates | 18732 | +| policy_gradient_loss | -0.0231 | +| value_loss | 7.87e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1375 | +| iterations | 730 | +| time_elapsed | 1086 | +| total_timesteps | 1495040 | +| train/ | | +| approx_kl | 0.009464599 | +| clip_fraction | 0.264 | +| clip_range | 0.0746 | +| entropy_loss | -7.6 | +| explained_variance | -0.0461 | +| learning_rate | 4.96e-05 | +| loss | -0.0354 | +| n_updates | 18736 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000228 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1375 | +| iterations | 731 | +| time_elapsed | 1088 | +| total_timesteps | 1497088 | +| train/ | | +| approx_kl | 0.0073479176 | +| clip_fraction | 0.245 | +| clip_range | 0.0746 | +| entropy_loss | -7.46 | +| explained_variance | -0.0196 | +| learning_rate | 4.96e-05 | +| loss | -0.0305 | +| n_updates | 18740 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000145 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1375 | +| iterations | 732 | +| time_elapsed | 1089 | +| total_timesteps | 1499136 | +| train/ | | +| approx_kl | 0.008699095 | +| clip_fraction | 0.275 | +| clip_range | 0.0746 | +| entropy_loss | -7.08 | +| explained_variance | 0.0687 | +| learning_rate | 4.96e-05 | +| loss | -0.029 | +| n_updates | 18744 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000487 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1375 | +| iterations | 733 | +| time_elapsed | 1091 | +| total_timesteps | 1501184 | +| train/ | | +| approx_kl | 0.008039689 | +| clip_fraction | 0.28 | +| clip_range | 0.0746 | +| entropy_loss | -7.23 | +| explained_variance | 0.0198 | +| learning_rate | 4.96e-05 | +| loss | -0.0286 | +| n_updates | 18748 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000237 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1375 | +| iterations | 734 | +| time_elapsed | 1092 | +| total_timesteps | 1503232 | +| train/ | | +| approx_kl | 0.00865774 | +| clip_fraction | 0.273 | +| clip_range | 0.0746 | +| entropy_loss | -7.36 | +| explained_variance | 0.109 | +| learning_rate | 4.96e-05 | +| loss | -0.0275 | +| n_updates | 18752 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000185 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1375 | +| iterations | 735 | +| time_elapsed | 1094 | +| total_timesteps | 1505280 | +| train/ | | +| approx_kl | 0.010214472 | +| clip_fraction | 0.297 | +| clip_range | 0.0746 | +| entropy_loss | -7.68 | +| explained_variance | -0.0301 | +| learning_rate | 4.96e-05 | +| loss | -0.0361 | +| n_updates | 18756 | +| policy_gradient_loss | -0.0228 | +| value_loss | 0.000204 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1375 | +| iterations | 736 | +| time_elapsed | 1095 | +| total_timesteps | 1507328 | +| train/ | | +| approx_kl | 0.007785645 | +| clip_fraction | 0.261 | +| clip_range | 0.0746 | +| entropy_loss | -7.67 | +| explained_variance | -0.0733 | +| learning_rate | 4.96e-05 | +| loss | -0.0251 | +| n_updates | 18760 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.00022 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1375 | +| iterations | 737 | +| time_elapsed | 1097 | +| total_timesteps | 1509376 | +| train/ | | +| approx_kl | 0.009459004 | +| clip_fraction | 0.298 | +| clip_range | 0.0746 | +| entropy_loss | -7.56 | +| explained_variance | -0.326 | +| learning_rate | 4.96e-05 | +| loss | -0.0378 | +| n_updates | 18764 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.00014 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1375 | +| iterations | 738 | +| time_elapsed | 1098 | +| total_timesteps | 1511424 | +| train/ | | +| approx_kl | 0.009347653 | +| clip_fraction | 0.278 | +| clip_range | 0.0746 | +| entropy_loss | -7.48 | +| explained_variance | -0.0277 | +| learning_rate | 4.96e-05 | +| loss | -0.031 | +| n_updates | 18768 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000209 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1375 | +| iterations | 739 | +| time_elapsed | 1100 | +| total_timesteps | 1513472 | +| train/ | | +| approx_kl | 0.008732317 | +| clip_fraction | 0.268 | +| clip_range | 0.0746 | +| entropy_loss | -7.49 | +| explained_variance | 0.269 | +| learning_rate | 4.96e-05 | +| loss | -0.0293 | +| n_updates | 18772 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000186 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1375 | +| iterations | 740 | +| time_elapsed | 1101 | +| total_timesteps | 1515520 | +| train/ | | +| approx_kl | 0.008148589 | +| clip_fraction | 0.263 | +| clip_range | 0.0746 | +| entropy_loss | -7.43 | +| explained_variance | 0.14 | +| learning_rate | 4.96e-05 | +| loss | -0.0296 | +| n_updates | 18776 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000319 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1375 | +| iterations | 741 | +| time_elapsed | 1103 | +| total_timesteps | 1517568 | +| train/ | | +| approx_kl | 0.009467155 | +| clip_fraction | 0.289 | +| clip_range | 0.0746 | +| entropy_loss | -7.37 | +| explained_variance | 0.162 | +| learning_rate | 4.96e-05 | +| loss | -0.0325 | +| n_updates | 18780 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000182 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1375 | +| iterations | 742 | +| time_elapsed | 1104 | +| total_timesteps | 1519616 | +| train/ | | +| approx_kl | 0.008325294 | +| clip_fraction | 0.279 | +| clip_range | 0.0746 | +| entropy_loss | -7.56 | +| explained_variance | 0.0341 | +| learning_rate | 4.96e-05 | +| loss | -0.0337 | +| n_updates | 18784 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.00024 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1375 | +| iterations | 743 | +| time_elapsed | 1105 | +| total_timesteps | 1521664 | +| train/ | | +| approx_kl | 0.009308545 | +| clip_fraction | 0.3 | +| clip_range | 0.0746 | +| entropy_loss | -7.3 | +| explained_variance | -0.172 | +| learning_rate | 4.96e-05 | +| loss | -0.0329 | +| n_updates | 18788 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000154 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1376 | +| iterations | 744 | +| time_elapsed | 1107 | +| total_timesteps | 1523712 | +| train/ | | +| approx_kl | 0.008768836 | +| clip_fraction | 0.283 | +| clip_range | 0.0746 | +| entropy_loss | -7.46 | +| explained_variance | 0.0386 | +| learning_rate | 4.96e-05 | +| loss | -0.0314 | +| n_updates | 18792 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000175 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1376 | +| iterations | 745 | +| time_elapsed | 1108 | +| total_timesteps | 1525760 | +| train/ | | +| approx_kl | 0.010073134 | +| clip_fraction | 0.298 | +| clip_range | 0.0746 | +| entropy_loss | -7.44 | +| explained_variance | -0.214 | +| learning_rate | 4.96e-05 | +| loss | -0.0342 | +| n_updates | 18796 | +| policy_gradient_loss | -0.0219 | +| value_loss | 9.13e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1376 | +| iterations | 746 | +| time_elapsed | 1110 | +| total_timesteps | 1527808 | +| train/ | | +| approx_kl | 0.010529479 | +| clip_fraction | 0.301 | +| clip_range | 0.0746 | +| entropy_loss | -7.62 | +| explained_variance | -0.0574 | +| learning_rate | 4.96e-05 | +| loss | -0.0342 | +| n_updates | 18800 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000208 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1376 | +| iterations | 747 | +| time_elapsed | 1111 | +| total_timesteps | 1529856 | +| train/ | | +| approx_kl | 0.010403575 | +| clip_fraction | 0.3 | +| clip_range | 0.0746 | +| entropy_loss | -7.42 | +| explained_variance | -0.0772 | +| learning_rate | 4.96e-05 | +| loss | -0.0383 | +| n_updates | 18804 | +| policy_gradient_loss | -0.0233 | +| value_loss | 7.05e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1376 | +| iterations | 748 | +| time_elapsed | 1113 | +| total_timesteps | 1531904 | +| train/ | | +| approx_kl | 0.00906611 | +| clip_fraction | 0.288 | +| clip_range | 0.0746 | +| entropy_loss | -7.42 | +| explained_variance | 0.126 | +| learning_rate | 4.96e-05 | +| loss | -0.0371 | +| n_updates | 18808 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000146 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1376 | +| iterations | 749 | +| time_elapsed | 1114 | +| total_timesteps | 1533952 | +| train/ | | +| approx_kl | 0.009604482 | +| clip_fraction | 0.286 | +| clip_range | 0.0746 | +| entropy_loss | -7.25 | +| explained_variance | 0.0199 | +| learning_rate | 4.96e-05 | +| loss | -0.0312 | +| n_updates | 18812 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000252 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1376 | +| iterations | 750 | +| time_elapsed | 1115 | +| total_timesteps | 1536000 | +| train/ | | +| approx_kl | 0.010934505 | +| clip_fraction | 0.272 | +| clip_range | 0.0746 | +| entropy_loss | -7.54 | +| explained_variance | -0.0325 | +| learning_rate | 4.96e-05 | +| loss | -0.0275 | +| n_updates | 18816 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000285 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1376 | +| iterations | 751 | +| time_elapsed | 1117 | +| total_timesteps | 1538048 | +| train/ | | +| approx_kl | 0.009382884 | +| clip_fraction | 0.275 | +| clip_range | 0.0746 | +| entropy_loss | -7.45 | +| explained_variance | 0.0754 | +| learning_rate | 4.96e-05 | +| loss | -0.0274 | +| n_updates | 18820 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000275 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1376 | +| iterations | 752 | +| time_elapsed | 1118 | +| total_timesteps | 1540096 | +| train/ | | +| approx_kl | 0.010285158 | +| clip_fraction | 0.292 | +| clip_range | 0.0746 | +| entropy_loss | -7.34 | +| explained_variance | 0.0449 | +| learning_rate | 4.96e-05 | +| loss | -0.0283 | +| n_updates | 18824 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000188 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1376 | +| iterations | 753 | +| time_elapsed | 1120 | +| total_timesteps | 1542144 | +| train/ | | +| approx_kl | 0.009724509 | +| clip_fraction | 0.287 | +| clip_range | 0.0746 | +| entropy_loss | -7.31 | +| explained_variance | 0.145 | +| learning_rate | 4.96e-05 | +| loss | -0.0318 | +| n_updates | 18828 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000257 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1376 | +| iterations | 754 | +| time_elapsed | 1121 | +| total_timesteps | 1544192 | +| train/ | | +| approx_kl | 0.0099382475 | +| clip_fraction | 0.265 | +| clip_range | 0.0746 | +| entropy_loss | -7.56 | +| explained_variance | -0.0273 | +| learning_rate | 4.96e-05 | +| loss | -0.0341 | +| n_updates | 18832 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000296 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1376 | +| iterations | 755 | +| time_elapsed | 1122 | +| total_timesteps | 1546240 | +| train/ | | +| approx_kl | 0.010942693 | +| clip_fraction | 0.292 | +| clip_range | 0.0746 | +| entropy_loss | -7.56 | +| explained_variance | -0.0246 | +| learning_rate | 4.96e-05 | +| loss | -0.033 | +| n_updates | 18836 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000157 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1376 | +| iterations | 756 | +| time_elapsed | 1124 | +| total_timesteps | 1548288 | +| train/ | | +| approx_kl | 0.007762355 | +| clip_fraction | 0.286 | +| clip_range | 0.0746 | +| entropy_loss | -7.71 | +| explained_variance | -0.0571 | +| learning_rate | 4.96e-05 | +| loss | -0.0309 | +| n_updates | 18840 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1377 | +| iterations | 757 | +| time_elapsed | 1125 | +| total_timesteps | 1550336 | +| train/ | | +| approx_kl | 0.008674787 | +| clip_fraction | 0.293 | +| clip_range | 0.0746 | +| entropy_loss | -7.52 | +| explained_variance | -0.1 | +| learning_rate | 4.96e-05 | +| loss | -0.0333 | +| n_updates | 18844 | +| policy_gradient_loss | -0.0224 | +| value_loss | 7.89e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1377 | +| iterations | 758 | +| time_elapsed | 1127 | +| total_timesteps | 1552384 | +| train/ | | +| approx_kl | 0.00946132 | +| clip_fraction | 0.293 | +| clip_range | 0.0746 | +| entropy_loss | -7.63 | +| explained_variance | -0.0845 | +| learning_rate | 4.96e-05 | +| loss | -0.039 | +| n_updates | 18848 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000123 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1377 | +| iterations | 759 | +| time_elapsed | 1128 | +| total_timesteps | 1554432 | +| train/ | | +| approx_kl | 0.008618233 | +| clip_fraction | 0.265 | +| clip_range | 0.0746 | +| entropy_loss | -7.55 | +| explained_variance | -0.0926 | +| learning_rate | 4.96e-05 | +| loss | -0.0301 | +| n_updates | 18852 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000133 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1377 | +| iterations | 760 | +| time_elapsed | 1130 | +| total_timesteps | 1556480 | +| train/ | | +| approx_kl | 0.007920094 | +| clip_fraction | 0.283 | +| clip_range | 0.0746 | +| entropy_loss | -7.37 | +| explained_variance | -0.0656 | +| learning_rate | 4.96e-05 | +| loss | -0.0285 | +| n_updates | 18856 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000272 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1377 | +| iterations | 761 | +| time_elapsed | 1131 | +| total_timesteps | 1558528 | +| train/ | | +| approx_kl | 0.008643293 | +| clip_fraction | 0.281 | +| clip_range | 0.0746 | +| entropy_loss | -7.38 | +| explained_variance | 0.0792 | +| learning_rate | 4.96e-05 | +| loss | -0.0342 | +| n_updates | 18860 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000338 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1377 | +| iterations | 762 | +| time_elapsed | 1132 | +| total_timesteps | 1560576 | +| train/ | | +| approx_kl | 0.007821385 | +| clip_fraction | 0.279 | +| clip_range | 0.0746 | +| entropy_loss | -7.17 | +| explained_variance | -0.0671 | +| learning_rate | 4.96e-05 | +| loss | -0.0331 | +| n_updates | 18864 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000196 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1377 | +| iterations | 763 | +| time_elapsed | 1134 | +| total_timesteps | 1562624 | +| train/ | | +| approx_kl | 0.009468468 | +| clip_fraction | 0.292 | +| clip_range | 0.0746 | +| entropy_loss | -7.38 | +| explained_variance | 0.0717 | +| learning_rate | 4.96e-05 | +| loss | -0.0321 | +| n_updates | 18868 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000144 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1377 | +| iterations | 764 | +| time_elapsed | 1135 | +| total_timesteps | 1564672 | +| train/ | | +| approx_kl | 0.008693194 | +| clip_fraction | 0.281 | +| clip_range | 0.0746 | +| entropy_loss | -7.33 | +| explained_variance | 0.131 | +| learning_rate | 4.96e-05 | +| loss | -0.0308 | +| n_updates | 18872 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000185 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1377 | +| iterations | 765 | +| time_elapsed | 1137 | +| total_timesteps | 1566720 | +| train/ | | +| approx_kl | 0.009787784 | +| clip_fraction | 0.261 | +| clip_range | 0.0746 | +| entropy_loss | -7.56 | +| explained_variance | -0.164 | +| learning_rate | 4.96e-05 | +| loss | -0.0327 | +| n_updates | 18876 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000154 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1377 | +| iterations | 766 | +| time_elapsed | 1138 | +| total_timesteps | 1568768 | +| train/ | | +| approx_kl | 0.00914961 | +| clip_fraction | 0.302 | +| clip_range | 0.0746 | +| entropy_loss | -7.71 | +| explained_variance | -0.0125 | +| learning_rate | 4.96e-05 | +| loss | -0.0322 | +| n_updates | 18880 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000115 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1377 | +| iterations | 767 | +| time_elapsed | 1140 | +| total_timesteps | 1570816 | +| train/ | | +| approx_kl | 0.009264299 | +| clip_fraction | 0.287 | +| clip_range | 0.0746 | +| entropy_loss | -7.63 | +| explained_variance | -0.0484 | +| learning_rate | 4.96e-05 | +| loss | -0.0335 | +| n_updates | 18884 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.00016 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1377 | +| iterations | 768 | +| time_elapsed | 1141 | +| total_timesteps | 1572864 | +| train/ | | +| approx_kl | 0.008320663 | +| clip_fraction | 0.266 | +| clip_range | 0.0746 | +| entropy_loss | -7.68 | +| explained_variance | -0.0367 | +| learning_rate | 4.96e-05 | +| loss | -0.0369 | +| n_updates | 18888 | +| policy_gradient_loss | -0.0214 | +| value_loss | 9.35e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1377 | +| iterations | 769 | +| time_elapsed | 1143 | +| total_timesteps | 1574912 | +| train/ | | +| approx_kl | 0.008906982 | +| clip_fraction | 0.266 | +| clip_range | 0.0746 | +| entropy_loss | -7.53 | +| explained_variance | -0.0782 | +| learning_rate | 4.96e-05 | +| loss | -0.0372 | +| n_updates | 18892 | +| policy_gradient_loss | -0.0201 | +| value_loss | 9.69e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1377 | +| iterations | 770 | +| time_elapsed | 1144 | +| total_timesteps | 1576960 | +| train/ | | +| approx_kl | 0.008590442 | +| clip_fraction | 0.255 | +| clip_range | 0.0746 | +| entropy_loss | -7.49 | +| explained_variance | 0.0489 | +| learning_rate | 4.96e-05 | +| loss | -0.0335 | +| n_updates | 18896 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000202 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1377 | +| iterations | 771 | +| time_elapsed | 1146 | +| total_timesteps | 1579008 | +| train/ | | +| approx_kl | 0.008992474 | +| clip_fraction | 0.265 | +| clip_range | 0.0746 | +| entropy_loss | -7.11 | +| explained_variance | 0.179 | +| learning_rate | 4.96e-05 | +| loss | -0.033 | +| n_updates | 18900 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000358 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1377 | +| iterations | 772 | +| time_elapsed | 1147 | +| total_timesteps | 1581056 | +| train/ | | +| approx_kl | 0.009752419 | +| clip_fraction | 0.314 | +| clip_range | 0.0746 | +| entropy_loss | -7.29 | +| explained_variance | 0.297 | +| learning_rate | 4.96e-05 | +| loss | -0.0403 | +| n_updates | 18904 | +| policy_gradient_loss | -0.0222 | +| value_loss | 9.81e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1377 | +| iterations | 773 | +| time_elapsed | 1148 | +| total_timesteps | 1583104 | +| train/ | | +| approx_kl | 0.009728645 | +| clip_fraction | 0.278 | +| clip_range | 0.0746 | +| entropy_loss | -7.5 | +| explained_variance | 0.0713 | +| learning_rate | 4.96e-05 | +| loss | -0.0323 | +| n_updates | 18908 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000269 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1377 | +| iterations | 774 | +| time_elapsed | 1150 | +| total_timesteps | 1585152 | +| train/ | | +| approx_kl | 0.0076150466 | +| clip_fraction | 0.265 | +| clip_range | 0.0746 | +| entropy_loss | -7.6 | +| explained_variance | -0.033 | +| learning_rate | 4.96e-05 | +| loss | -0.0289 | +| n_updates | 18912 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000329 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1378 | +| iterations | 775 | +| time_elapsed | 1151 | +| total_timesteps | 1587200 | +| train/ | | +| approx_kl | 0.00894049 | +| clip_fraction | 0.318 | +| clip_range | 0.0746 | +| entropy_loss | -7.59 | +| explained_variance | 0.0654 | +| learning_rate | 4.96e-05 | +| loss | -0.0392 | +| n_updates | 18916 | +| policy_gradient_loss | -0.0235 | +| value_loss | 0.000114 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1378 | +| iterations | 776 | +| time_elapsed | 1153 | +| total_timesteps | 1589248 | +| train/ | | +| approx_kl | 0.009845754 | +| clip_fraction | 0.302 | +| clip_range | 0.0746 | +| entropy_loss | -7.43 | +| explained_variance | -0.186 | +| learning_rate | 4.96e-05 | +| loss | -0.0378 | +| n_updates | 18920 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.00022 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1378 | +| iterations | 777 | +| time_elapsed | 1154 | +| total_timesteps | 1591296 | +| train/ | | +| approx_kl | 0.01120592 | +| clip_fraction | 0.296 | +| clip_range | 0.0746 | +| entropy_loss | -7.55 | +| explained_variance | -0.0678 | +| learning_rate | 4.96e-05 | +| loss | -0.038 | +| n_updates | 18924 | +| policy_gradient_loss | -0.0216 | +| value_loss | 9.05e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1378 | +| iterations | 778 | +| time_elapsed | 1156 | +| total_timesteps | 1593344 | +| train/ | | +| approx_kl | 0.008689282 | +| clip_fraction | 0.284 | +| clip_range | 0.0746 | +| entropy_loss | -7.36 | +| explained_variance | 0.0389 | +| learning_rate | 4.96e-05 | +| loss | -0.0345 | +| n_updates | 18928 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000324 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1378 | +| iterations | 779 | +| time_elapsed | 1157 | +| total_timesteps | 1595392 | +| train/ | | +| approx_kl | 0.00790324 | +| clip_fraction | 0.266 | +| clip_range | 0.0746 | +| entropy_loss | -7.66 | +| explained_variance | -0.148 | +| learning_rate | 4.96e-05 | +| loss | -0.0309 | +| n_updates | 18932 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000216 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1378 | +| iterations | 780 | +| time_elapsed | 1159 | +| total_timesteps | 1597440 | +| train/ | | +| approx_kl | 0.007647177 | +| clip_fraction | 0.266 | +| clip_range | 0.0746 | +| entropy_loss | -7.46 | +| explained_variance | 0.0646 | +| learning_rate | 4.96e-05 | +| loss | -0.0303 | +| n_updates | 18936 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.00021 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1378 | +| iterations | 781 | +| time_elapsed | 1160 | +| total_timesteps | 1599488 | +| train/ | | +| approx_kl | 0.009380206 | +| clip_fraction | 0.309 | +| clip_range | 0.0746 | +| entropy_loss | -7.42 | +| explained_variance | -0.0115 | +| learning_rate | 4.96e-05 | +| loss | -0.0358 | +| n_updates | 18940 | +| policy_gradient_loss | -0.0228 | +| value_loss | 0.000228 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1378 | +| iterations | 782 | +| time_elapsed | 1162 | +| total_timesteps | 1601536 | +| train/ | | +| approx_kl | 0.009553009 | +| clip_fraction | 0.276 | +| clip_range | 0.0746 | +| entropy_loss | -7.5 | +| explained_variance | 0.0455 | +| learning_rate | 4.96e-05 | +| loss | -0.0306 | +| n_updates | 18944 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000117 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1378 | +| iterations | 783 | +| time_elapsed | 1163 | +| total_timesteps | 1603584 | +| train/ | | +| approx_kl | 0.010081895 | +| clip_fraction | 0.297 | +| clip_range | 0.0746 | +| entropy_loss | -7.32 | +| explained_variance | 0.0697 | +| learning_rate | 4.96e-05 | +| loss | -0.0301 | +| n_updates | 18948 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000154 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1378 | +| iterations | 784 | +| time_elapsed | 1164 | +| total_timesteps | 1605632 | +| train/ | | +| approx_kl | 0.010066073 | +| clip_fraction | 0.28 | +| clip_range | 0.0746 | +| entropy_loss | -7.05 | +| explained_variance | 0.22 | +| learning_rate | 4.96e-05 | +| loss | -0.0382 | +| n_updates | 18952 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000271 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1378 | +| iterations | 785 | +| time_elapsed | 1166 | +| total_timesteps | 1607680 | +| train/ | | +| approx_kl | 0.010254113 | +| clip_fraction | 0.296 | +| clip_range | 0.0746 | +| entropy_loss | -7.53 | +| explained_variance | -0.188 | +| learning_rate | 4.96e-05 | +| loss | -0.0378 | +| n_updates | 18956 | +| policy_gradient_loss | -0.023 | +| value_loss | 0.000159 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1378 | +| iterations | 786 | +| time_elapsed | 1167 | +| total_timesteps | 1609728 | +| train/ | | +| approx_kl | 0.008841422 | +| clip_fraction | 0.258 | +| clip_range | 0.0746 | +| entropy_loss | -7.44 | +| explained_variance | -0.015 | +| learning_rate | 4.96e-05 | +| loss | -0.0296 | +| n_updates | 18960 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000424 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1378 | +| iterations | 787 | +| time_elapsed | 1169 | +| total_timesteps | 1611776 | +| train/ | | +| approx_kl | 0.00988831 | +| clip_fraction | 0.279 | +| clip_range | 0.0746 | +| entropy_loss | -7.5 | +| explained_variance | 0.0473 | +| learning_rate | 4.96e-05 | +| loss | -0.0308 | +| n_updates | 18964 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000259 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1378 | +| iterations | 788 | +| time_elapsed | 1170 | +| total_timesteps | 1613824 | +| train/ | | +| approx_kl | 0.009891406 | +| clip_fraction | 0.302 | +| clip_range | 0.0746 | +| entropy_loss | -7.65 | +| explained_variance | -0.352 | +| learning_rate | 4.96e-05 | +| loss | -0.0386 | +| n_updates | 18968 | +| policy_gradient_loss | -0.0231 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1378 | +| iterations | 789 | +| time_elapsed | 1172 | +| total_timesteps | 1615872 | +| train/ | | +| approx_kl | 0.008394834 | +| clip_fraction | 0.276 | +| clip_range | 0.0746 | +| entropy_loss | -7.11 | +| explained_variance | 0.106 | +| learning_rate | 4.96e-05 | +| loss | -0.0254 | +| n_updates | 18972 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.00054 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1378 | +| iterations | 790 | +| time_elapsed | 1173 | +| total_timesteps | 1617920 | +| train/ | | +| approx_kl | 0.008815214 | +| clip_fraction | 0.296 | +| clip_range | 0.0746 | +| entropy_loss | -7.32 | +| explained_variance | 0.0247 | +| learning_rate | 4.96e-05 | +| loss | -0.0334 | +| n_updates | 18976 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000195 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1378 | +| iterations | 791 | +| time_elapsed | 1174 | +| total_timesteps | 1619968 | +| train/ | | +| approx_kl | 0.00896657 | +| clip_fraction | 0.272 | +| clip_range | 0.0746 | +| entropy_loss | -7.32 | +| explained_variance | 0.123 | +| learning_rate | 4.96e-05 | +| loss | -0.0259 | +| n_updates | 18980 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000237 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1378 | +| iterations | 792 | +| time_elapsed | 1176 | +| total_timesteps | 1622016 | +| train/ | | +| approx_kl | 0.009819004 | +| clip_fraction | 0.331 | +| clip_range | 0.0746 | +| entropy_loss | -7.68 | +| explained_variance | -0.616 | +| learning_rate | 4.96e-05 | +| loss | -0.0415 | +| n_updates | 18984 | +| policy_gradient_loss | -0.0269 | +| value_loss | 7.98e-05 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1378 | +| iterations | 793 | +| time_elapsed | 1177 | +| total_timesteps | 1624064 | +| train/ | | +| approx_kl | 0.0088793 | +| clip_fraction | 0.284 | +| clip_range | 0.0746 | +| entropy_loss | -7.48 | +| explained_variance | -0.036 | +| learning_rate | 4.96e-05 | +| loss | -0.0287 | +| n_updates | 18988 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000327 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1378 | +| iterations | 794 | +| time_elapsed | 1179 | +| total_timesteps | 1626112 | +| train/ | | +| approx_kl | 0.009416037 | +| clip_fraction | 0.291 | +| clip_range | 0.0746 | +| entropy_loss | -7.3 | +| explained_variance | 0.0147 | +| learning_rate | 4.96e-05 | +| loss | -0.0355 | +| n_updates | 18992 | +| policy_gradient_loss | -0.0221 | +| value_loss | 0.000257 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1378 | +| iterations | 795 | +| time_elapsed | 1180 | +| total_timesteps | 1628160 | +| train/ | | +| approx_kl | 0.01041633 | +| clip_fraction | 0.316 | +| clip_range | 0.0746 | +| entropy_loss | -7.62 | +| explained_variance | -0.224 | +| learning_rate | 4.96e-05 | +| loss | -0.0329 | +| n_updates | 18996 | +| policy_gradient_loss | -0.0233 | +| value_loss | 0.000119 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1378 | +| iterations | 796 | +| time_elapsed | 1182 | +| total_timesteps | 1630208 | +| train/ | | +| approx_kl | 0.0082023395 | +| clip_fraction | 0.281 | +| clip_range | 0.0746 | +| entropy_loss | -7.3 | +| explained_variance | 0.159 | +| learning_rate | 4.96e-05 | +| loss | -0.0294 | +| n_updates | 19000 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000227 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1379 | +| iterations | 797 | +| time_elapsed | 1183 | +| total_timesteps | 1632256 | +| train/ | | +| approx_kl | 0.008602621 | +| clip_fraction | 0.28 | +| clip_range | 0.0746 | +| entropy_loss | -7.52 | +| explained_variance | -0.00959 | +| learning_rate | 4.96e-05 | +| loss | -0.0387 | +| n_updates | 19004 | +| policy_gradient_loss | -0.0226 | +| value_loss | 0.000142 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1379 | +| iterations | 798 | +| time_elapsed | 1185 | +| total_timesteps | 1634304 | +| train/ | | +| approx_kl | 0.0075560985 | +| clip_fraction | 0.261 | +| clip_range | 0.0746 | +| entropy_loss | -7.52 | +| explained_variance | 0.288 | +| learning_rate | 4.96e-05 | +| loss | -0.0329 | +| n_updates | 19008 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000249 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1379 | +| iterations | 799 | +| time_elapsed | 1186 | +| total_timesteps | 1636352 | +| train/ | | +| approx_kl | 0.009808481 | +| clip_fraction | 0.319 | +| clip_range | 0.0746 | +| entropy_loss | -7.48 | +| explained_variance | 0.364 | +| learning_rate | 4.96e-05 | +| loss | -0.0387 | +| n_updates | 19012 | +| policy_gradient_loss | -0.0236 | +| value_loss | 8.07e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1379 | +| iterations | 800 | +| time_elapsed | 1187 | +| total_timesteps | 1638400 | +| train/ | | +| approx_kl | 0.010650529 | +| clip_fraction | 0.318 | +| clip_range | 0.0746 | +| entropy_loss | -7.6 | +| explained_variance | -0.0681 | +| learning_rate | 4.96e-05 | +| loss | -0.0363 | +| n_updates | 19016 | +| policy_gradient_loss | -0.0233 | +| value_loss | 0.000142 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1379 | +| iterations | 801 | +| time_elapsed | 1189 | +| total_timesteps | 1640448 | +| train/ | | +| approx_kl | 0.008840147 | +| clip_fraction | 0.295 | +| clip_range | 0.0746 | +| entropy_loss | -7.49 | +| explained_variance | -0.0284 | +| learning_rate | 4.96e-05 | +| loss | -0.0335 | +| n_updates | 19020 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000253 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1379 | +| iterations | 802 | +| time_elapsed | 1190 | +| total_timesteps | 1642496 | +| train/ | | +| approx_kl | 0.008806767 | +| clip_fraction | 0.266 | +| clip_range | 0.0746 | +| entropy_loss | -7.24 | +| explained_variance | -0.04 | +| learning_rate | 4.96e-05 | +| loss | -0.0278 | +| n_updates | 19024 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000318 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1379 | +| iterations | 803 | +| time_elapsed | 1192 | +| total_timesteps | 1644544 | +| train/ | | +| approx_kl | 0.008868841 | +| clip_fraction | 0.296 | +| clip_range | 0.0746 | +| entropy_loss | -7.28 | +| explained_variance | 0.0161 | +| learning_rate | 4.96e-05 | +| loss | -0.0348 | +| n_updates | 19028 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000312 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1379 | +| iterations | 804 | +| time_elapsed | 1193 | +| total_timesteps | 1646592 | +| train/ | | +| approx_kl | 0.008212573 | +| clip_fraction | 0.29 | +| clip_range | 0.0746 | +| entropy_loss | -7.45 | +| explained_variance | 0.0144 | +| learning_rate | 4.96e-05 | +| loss | -0.0347 | +| n_updates | 19032 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000291 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1379 | +| iterations | 805 | +| time_elapsed | 1195 | +| total_timesteps | 1648640 | +| train/ | | +| approx_kl | 0.009561205 | +| clip_fraction | 0.309 | +| clip_range | 0.0746 | +| entropy_loss | -7.66 | +| explained_variance | -0.203 | +| learning_rate | 4.96e-05 | +| loss | -0.0373 | +| n_updates | 19036 | +| policy_gradient_loss | -0.0219 | +| value_loss | 0.000157 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1379 | +| iterations | 806 | +| time_elapsed | 1196 | +| total_timesteps | 1650688 | +| train/ | | +| approx_kl | 0.008677679 | +| clip_fraction | 0.263 | +| clip_range | 0.0746 | +| entropy_loss | -7.32 | +| explained_variance | -0.0414 | +| learning_rate | 4.96e-05 | +| loss | -0.0325 | +| n_updates | 19040 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000311 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1379 | +| iterations | 807 | +| time_elapsed | 1197 | +| total_timesteps | 1652736 | +| train/ | | +| approx_kl | 0.0096750725 | +| clip_fraction | 0.306 | +| clip_range | 0.0746 | +| entropy_loss | -7.56 | +| explained_variance | -0.0279 | +| learning_rate | 4.96e-05 | +| loss | -0.0343 | +| n_updates | 19044 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000199 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1379 | +| iterations | 808 | +| time_elapsed | 1199 | +| total_timesteps | 1654784 | +| train/ | | +| approx_kl | 0.00896747 | +| clip_fraction | 0.268 | +| clip_range | 0.0746 | +| entropy_loss | -7.65 | +| explained_variance | -0.0416 | +| learning_rate | 4.96e-05 | +| loss | -0.0356 | +| n_updates | 19048 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000376 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1379 | +| iterations | 809 | +| time_elapsed | 1200 | +| total_timesteps | 1656832 | +| train/ | | +| approx_kl | 0.009350643 | +| clip_fraction | 0.315 | +| clip_range | 0.0746 | +| entropy_loss | -7.49 | +| explained_variance | 0.158 | +| learning_rate | 4.96e-05 | +| loss | -0.039 | +| n_updates | 19052 | +| policy_gradient_loss | -0.0238 | +| value_loss | 0.000146 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1379 | +| iterations | 810 | +| time_elapsed | 1202 | +| total_timesteps | 1658880 | +| train/ | | +| approx_kl | 0.009436141 | +| clip_fraction | 0.302 | +| clip_range | 0.0746 | +| entropy_loss | -7.57 | +| explained_variance | -0.101 | +| learning_rate | 4.96e-05 | +| loss | -0.0334 | +| n_updates | 19056 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000179 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1379 | +| iterations | 811 | +| time_elapsed | 1203 | +| total_timesteps | 1660928 | +| train/ | | +| approx_kl | 0.0098099075 | +| clip_fraction | 0.291 | +| clip_range | 0.0746 | +| entropy_loss | -7.45 | +| explained_variance | -0.0765 | +| learning_rate | 4.96e-05 | +| loss | -0.0296 | +| n_updates | 19060 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000182 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1380 | +| iterations | 812 | +| time_elapsed | 1205 | +| total_timesteps | 1662976 | +| train/ | | +| approx_kl | 0.009855441 | +| clip_fraction | 0.28 | +| clip_range | 0.0746 | +| entropy_loss | -7.12 | +| explained_variance | 0.129 | +| learning_rate | 4.96e-05 | +| loss | -0.0309 | +| n_updates | 19064 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000341 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1380 | +| iterations | 813 | +| time_elapsed | 1206 | +| total_timesteps | 1665024 | +| train/ | | +| approx_kl | 0.009657716 | +| clip_fraction | 0.293 | +| clip_range | 0.0746 | +| entropy_loss | -7.47 | +| explained_variance | 0.0387 | +| learning_rate | 4.96e-05 | +| loss | -0.0336 | +| n_updates | 19068 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000227 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1380 | +| iterations | 814 | +| time_elapsed | 1208 | +| total_timesteps | 1667072 | +| train/ | | +| approx_kl | 0.009401903 | +| clip_fraction | 0.304 | +| clip_range | 0.0746 | +| entropy_loss | -7.62 | +| explained_variance | -0.226 | +| learning_rate | 4.96e-05 | +| loss | -0.0351 | +| n_updates | 19072 | +| policy_gradient_loss | -0.0229 | +| value_loss | 0.000157 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1380 | +| iterations | 815 | +| time_elapsed | 1209 | +| total_timesteps | 1669120 | +| train/ | | +| approx_kl | 0.009579405 | +| clip_fraction | 0.258 | +| clip_range | 0.0746 | +| entropy_loss | -7.41 | +| explained_variance | 0.0257 | +| learning_rate | 4.96e-05 | +| loss | -0.0392 | +| n_updates | 19076 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000196 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1380 | +| iterations | 816 | +| time_elapsed | 1210 | +| total_timesteps | 1671168 | +| train/ | | +| approx_kl | 0.009366171 | +| clip_fraction | 0.265 | +| clip_range | 0.0746 | +| entropy_loss | -7.26 | +| explained_variance | -0.0162 | +| learning_rate | 4.96e-05 | +| loss | -0.0294 | +| n_updates | 19080 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000179 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1380 | +| iterations | 817 | +| time_elapsed | 1212 | +| total_timesteps | 1673216 | +| train/ | | +| approx_kl | 0.010790365 | +| clip_fraction | 0.297 | +| clip_range | 0.0746 | +| entropy_loss | -7.65 | +| explained_variance | -0.0609 | +| learning_rate | 4.96e-05 | +| loss | -0.0363 | +| n_updates | 19084 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000169 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1380 | +| iterations | 818 | +| time_elapsed | 1213 | +| total_timesteps | 1675264 | +| train/ | | +| approx_kl | 0.00840829 | +| clip_fraction | 0.27 | +| clip_range | 0.0746 | +| entropy_loss | -7.48 | +| explained_variance | 0.00184 | +| learning_rate | 4.96e-05 | +| loss | -0.0253 | +| n_updates | 19088 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000275 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1380 | +| iterations | 819 | +| time_elapsed | 1215 | +| total_timesteps | 1677312 | +| train/ | | +| approx_kl | 0.008543789 | +| clip_fraction | 0.255 | +| clip_range | 0.0746 | +| entropy_loss | -7.3 | +| explained_variance | 0.0204 | +| learning_rate | 4.96e-05 | +| loss | -0.03 | +| n_updates | 19092 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000174 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1380 | +| iterations | 820 | +| time_elapsed | 1216 | +| total_timesteps | 1679360 | +| train/ | | +| approx_kl | 0.009231901 | +| clip_fraction | 0.273 | +| clip_range | 0.0746 | +| entropy_loss | -7.37 | +| explained_variance | 0.0976 | +| learning_rate | 4.96e-05 | +| loss | -0.0316 | +| n_updates | 19096 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.00018 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1380 | +| iterations | 821 | +| time_elapsed | 1218 | +| total_timesteps | 1681408 | +| train/ | | +| approx_kl | 0.009311765 | +| clip_fraction | 0.277 | +| clip_range | 0.0746 | +| entropy_loss | -7.31 | +| explained_variance | 0.00471 | +| learning_rate | 4.96e-05 | +| loss | -0.029 | +| n_updates | 19100 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000306 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1380 | +| iterations | 822 | +| time_elapsed | 1219 | +| total_timesteps | 1683456 | +| train/ | | +| approx_kl | 0.0109763695 | +| clip_fraction | 0.32 | +| clip_range | 0.0746 | +| entropy_loss | -7.48 | +| explained_variance | -0.284 | +| learning_rate | 4.96e-05 | +| loss | -0.0409 | +| n_updates | 19104 | +| policy_gradient_loss | -0.0255 | +| value_loss | 9.13e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1380 | +| iterations | 823 | +| time_elapsed | 1220 | +| total_timesteps | 1685504 | +| train/ | | +| approx_kl | 0.009508771 | +| clip_fraction | 0.297 | +| clip_range | 0.0746 | +| entropy_loss | -7.55 | +| explained_variance | -0.155 | +| learning_rate | 4.96e-05 | +| loss | -0.0361 | +| n_updates | 19108 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000159 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1380 | +| iterations | 824 | +| time_elapsed | 1222 | +| total_timesteps | 1687552 | +| train/ | | +| approx_kl | 0.00855281 | +| clip_fraction | 0.245 | +| clip_range | 0.0746 | +| entropy_loss | -7.29 | +| explained_variance | 0.0783 | +| learning_rate | 4.96e-05 | +| loss | -0.0263 | +| n_updates | 19112 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000337 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1380 | +| iterations | 825 | +| time_elapsed | 1223 | +| total_timesteps | 1689600 | +| train/ | | +| approx_kl | 0.009779757 | +| clip_fraction | 0.3 | +| clip_range | 0.0746 | +| entropy_loss | -7.32 | +| explained_variance | 0.116 | +| learning_rate | 4.96e-05 | +| loss | -0.0288 | +| n_updates | 19116 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000248 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1380 | +| iterations | 826 | +| time_elapsed | 1225 | +| total_timesteps | 1691648 | +| train/ | | +| approx_kl | 0.010472499 | +| clip_fraction | 0.28 | +| clip_range | 0.0746 | +| entropy_loss | -7.42 | +| explained_variance | 0.0962 | +| learning_rate | 4.96e-05 | +| loss | -0.037 | +| n_updates | 19120 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000204 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1380 | +| iterations | 827 | +| time_elapsed | 1226 | +| total_timesteps | 1693696 | +| train/ | | +| approx_kl | 0.009560656 | +| clip_fraction | 0.304 | +| clip_range | 0.0746 | +| entropy_loss | -7.63 | +| explained_variance | -0.308 | +| learning_rate | 4.96e-05 | +| loss | -0.0312 | +| n_updates | 19124 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000234 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1380 | +| iterations | 828 | +| time_elapsed | 1228 | +| total_timesteps | 1695744 | +| train/ | | +| approx_kl | 0.008937538 | +| clip_fraction | 0.3 | +| clip_range | 0.0746 | +| entropy_loss | -7.63 | +| explained_variance | -0.259 | +| learning_rate | 4.96e-05 | +| loss | -0.0351 | +| n_updates | 19128 | +| policy_gradient_loss | -0.0231 | +| value_loss | 0.00012 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1380 | +| iterations | 829 | +| time_elapsed | 1229 | +| total_timesteps | 1697792 | +| train/ | | +| approx_kl | 0.0091172885 | +| clip_fraction | 0.3 | +| clip_range | 0.0746 | +| entropy_loss | -7.63 | +| explained_variance | -0.0578 | +| learning_rate | 4.96e-05 | +| loss | -0.032 | +| n_updates | 19132 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000139 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1381 | +| iterations | 830 | +| time_elapsed | 1230 | +| total_timesteps | 1699840 | +| train/ | | +| approx_kl | 0.010333924 | +| clip_fraction | 0.289 | +| clip_range | 0.0746 | +| entropy_loss | -7.55 | +| explained_variance | -0.0326 | +| learning_rate | 4.96e-05 | +| loss | -0.0339 | +| n_updates | 19136 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000206 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1381 | +| iterations | 831 | +| time_elapsed | 1232 | +| total_timesteps | 1701888 | +| train/ | | +| approx_kl | 0.008945731 | +| clip_fraction | 0.277 | +| clip_range | 0.0746 | +| entropy_loss | -7.43 | +| explained_variance | 0.381 | +| learning_rate | 4.96e-05 | +| loss | -0.03 | +| n_updates | 19140 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.00012 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1381 | +| iterations | 832 | +| time_elapsed | 1233 | +| total_timesteps | 1703936 | +| train/ | | +| approx_kl | 0.008755967 | +| clip_fraction | 0.262 | +| clip_range | 0.0746 | +| entropy_loss | -7.73 | +| explained_variance | -0.132 | +| learning_rate | 4.96e-05 | +| loss | -0.0321 | +| n_updates | 19144 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000198 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1381 | +| iterations | 833 | +| time_elapsed | 1235 | +| total_timesteps | 1705984 | +| train/ | | +| approx_kl | 0.008632808 | +| clip_fraction | 0.28 | +| clip_range | 0.0746 | +| entropy_loss | -7.13 | +| explained_variance | 0.249 | +| learning_rate | 4.96e-05 | +| loss | -0.0296 | +| n_updates | 19148 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000186 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1381 | +| iterations | 834 | +| time_elapsed | 1236 | +| total_timesteps | 1708032 | +| train/ | | +| approx_kl | 0.008223256 | +| clip_fraction | 0.253 | +| clip_range | 0.0746 | +| entropy_loss | -7.07 | +| explained_variance | 0.128 | +| learning_rate | 4.96e-05 | +| loss | -0.0282 | +| n_updates | 19152 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000352 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1381 | +| iterations | 835 | +| time_elapsed | 1237 | +| total_timesteps | 1710080 | +| train/ | | +| approx_kl | 0.010311949 | +| clip_fraction | 0.28 | +| clip_range | 0.0746 | +| entropy_loss | -7.38 | +| explained_variance | 0.262 | +| learning_rate | 4.96e-05 | +| loss | -0.031 | +| n_updates | 19156 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000214 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1381 | +| iterations | 836 | +| time_elapsed | 1239 | +| total_timesteps | 1712128 | +| train/ | | +| approx_kl | 0.009652091 | +| clip_fraction | 0.292 | +| clip_range | 0.0746 | +| entropy_loss | -7.56 | +| explained_variance | -0.0786 | +| learning_rate | 4.96e-05 | +| loss | -0.0351 | +| n_updates | 19160 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000196 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1381 | +| iterations | 837 | +| time_elapsed | 1240 | +| total_timesteps | 1714176 | +| train/ | | +| approx_kl | 0.010701917 | +| clip_fraction | 0.313 | +| clip_range | 0.0746 | +| entropy_loss | -7.53 | +| explained_variance | -0.406 | +| learning_rate | 4.96e-05 | +| loss | -0.0331 | +| n_updates | 19164 | +| policy_gradient_loss | -0.0243 | +| value_loss | 0.000107 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1381 | +| iterations | 838 | +| time_elapsed | 1242 | +| total_timesteps | 1716224 | +| train/ | | +| approx_kl | 0.0088428445 | +| clip_fraction | 0.281 | +| clip_range | 0.0746 | +| entropy_loss | -7.71 | +| explained_variance | -0.0677 | +| learning_rate | 4.96e-05 | +| loss | -0.0375 | +| n_updates | 19168 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000258 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1381 | +| iterations | 839 | +| time_elapsed | 1243 | +| total_timesteps | 1718272 | +| train/ | | +| approx_kl | 0.0091130305 | +| clip_fraction | 0.268 | +| clip_range | 0.0746 | +| entropy_loss | -7.7 | +| explained_variance | -0.2 | +| learning_rate | 4.96e-05 | +| loss | -0.0315 | +| n_updates | 19172 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000158 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1381 | +| iterations | 840 | +| time_elapsed | 1244 | +| total_timesteps | 1720320 | +| train/ | | +| approx_kl | 0.008399022 | +| clip_fraction | 0.266 | +| clip_range | 0.0746 | +| entropy_loss | -7.53 | +| explained_variance | -0.0693 | +| learning_rate | 4.96e-05 | +| loss | -0.0376 | +| n_updates | 19176 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000308 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1381 | +| iterations | 841 | +| time_elapsed | 1246 | +| total_timesteps | 1722368 | +| train/ | | +| approx_kl | 0.011081085 | +| clip_fraction | 0.298 | +| clip_range | 0.0746 | +| entropy_loss | -7.57 | +| explained_variance | -0.166 | +| learning_rate | 4.96e-05 | +| loss | -0.0342 | +| n_updates | 19180 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000117 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1381 | +| iterations | 842 | +| time_elapsed | 1247 | +| total_timesteps | 1724416 | +| train/ | | +| approx_kl | 0.009922568 | +| clip_fraction | 0.322 | +| clip_range | 0.0746 | +| entropy_loss | -7.68 | +| explained_variance | -0.623 | +| learning_rate | 4.96e-05 | +| loss | -0.0457 | +| n_updates | 19184 | +| policy_gradient_loss | -0.0272 | +| value_loss | 5.95e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1381 | +| iterations | 843 | +| time_elapsed | 1249 | +| total_timesteps | 1726464 | +| train/ | | +| approx_kl | 0.009461846 | +| clip_fraction | 0.278 | +| clip_range | 0.0746 | +| entropy_loss | -7.39 | +| explained_variance | 0.0302 | +| learning_rate | 4.96e-05 | +| loss | -0.035 | +| n_updates | 19188 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000384 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1381 | +| iterations | 844 | +| time_elapsed | 1250 | +| total_timesteps | 1728512 | +| train/ | | +| approx_kl | 0.009702854 | +| clip_fraction | 0.302 | +| clip_range | 0.0746 | +| entropy_loss | -7.46 | +| explained_variance | -0.218 | +| learning_rate | 4.96e-05 | +| loss | -0.0386 | +| n_updates | 19192 | +| policy_gradient_loss | -0.0243 | +| value_loss | 9.04e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1381 | +| iterations | 845 | +| time_elapsed | 1252 | +| total_timesteps | 1730560 | +| train/ | | +| approx_kl | 0.009336214 | +| clip_fraction | 0.289 | +| clip_range | 0.0746 | +| entropy_loss | -7.34 | +| explained_variance | 0.171 | +| learning_rate | 4.96e-05 | +| loss | -0.0341 | +| n_updates | 19196 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.00026 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1382 | +| iterations | 846 | +| time_elapsed | 1253 | +| total_timesteps | 1732608 | +| train/ | | +| approx_kl | 0.0080404 | +| clip_fraction | 0.288 | +| clip_range | 0.0746 | +| entropy_loss | -7.42 | +| explained_variance | 0.196 | +| learning_rate | 4.96e-05 | +| loss | -0.0346 | +| n_updates | 19200 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000167 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1382 | +| iterations | 847 | +| time_elapsed | 1255 | +| total_timesteps | 1734656 | +| train/ | | +| approx_kl | 0.009205915 | +| clip_fraction | 0.299 | +| clip_range | 0.0746 | +| entropy_loss | -7.52 | +| explained_variance | -0.237 | +| learning_rate | 4.96e-05 | +| loss | -0.0364 | +| n_updates | 19204 | +| policy_gradient_loss | -0.0229 | +| value_loss | 0.000125 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1382 | +| iterations | 848 | +| time_elapsed | 1256 | +| total_timesteps | 1736704 | +| train/ | | +| approx_kl | 0.009288893 | +| clip_fraction | 0.288 | +| clip_range | 0.0746 | +| entropy_loss | -7.33 | +| explained_variance | 0.042 | +| learning_rate | 4.96e-05 | +| loss | -0.0311 | +| n_updates | 19208 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000231 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1382 | +| iterations | 849 | +| time_elapsed | 1257 | +| total_timesteps | 1738752 | +| train/ | | +| approx_kl | 0.010057504 | +| clip_fraction | 0.281 | +| clip_range | 0.0746 | +| entropy_loss | -7.47 | +| explained_variance | -0.0719 | +| learning_rate | 4.96e-05 | +| loss | -0.0352 | +| n_updates | 19212 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000156 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1382 | +| iterations | 850 | +| time_elapsed | 1259 | +| total_timesteps | 1740800 | +| train/ | | +| approx_kl | 0.009654786 | +| clip_fraction | 0.29 | +| clip_range | 0.0746 | +| entropy_loss | -7.54 | +| explained_variance | 0.162 | +| learning_rate | 4.96e-05 | +| loss | -0.0335 | +| n_updates | 19216 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000177 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1382 | +| iterations | 851 | +| time_elapsed | 1260 | +| total_timesteps | 1742848 | +| train/ | | +| approx_kl | 0.008782031 | +| clip_fraction | 0.289 | +| clip_range | 0.0746 | +| entropy_loss | -7.46 | +| explained_variance | 0.0208 | +| learning_rate | 4.96e-05 | +| loss | -0.0333 | +| n_updates | 19220 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000177 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1382 | +| iterations | 852 | +| time_elapsed | 1262 | +| total_timesteps | 1744896 | +| train/ | | +| approx_kl | 0.0081722485 | +| clip_fraction | 0.275 | +| clip_range | 0.0746 | +| entropy_loss | -7.43 | +| explained_variance | 0.147 | +| learning_rate | 4.96e-05 | +| loss | -0.0363 | +| n_updates | 19224 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000316 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1382 | +| iterations | 853 | +| time_elapsed | 1263 | +| total_timesteps | 1746944 | +| train/ | | +| approx_kl | 0.010467479 | +| clip_fraction | 0.305 | +| clip_range | 0.0746 | +| entropy_loss | -7.49 | +| explained_variance | -0.422 | +| learning_rate | 4.96e-05 | +| loss | -0.0365 | +| n_updates | 19228 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000197 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1382 | +| iterations | 854 | +| time_elapsed | 1264 | +| total_timesteps | 1748992 | +| train/ | | +| approx_kl | 0.009628251 | +| clip_fraction | 0.285 | +| clip_range | 0.0746 | +| entropy_loss | -7.69 | +| explained_variance | -0.0949 | +| learning_rate | 4.96e-05 | +| loss | -0.032 | +| n_updates | 19232 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000113 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1382 | +| iterations | 855 | +| time_elapsed | 1266 | +| total_timesteps | 1751040 | +| train/ | | +| approx_kl | 0.008019873 | +| clip_fraction | 0.266 | +| clip_range | 0.0746 | +| entropy_loss | -7.36 | +| explained_variance | 0.0602 | +| learning_rate | 4.96e-05 | +| loss | -0.0274 | +| n_updates | 19236 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000216 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1382 | +| iterations | 856 | +| time_elapsed | 1267 | +| total_timesteps | 1753088 | +| train/ | | +| approx_kl | 0.0078837415 | +| clip_fraction | 0.257 | +| clip_range | 0.0746 | +| entropy_loss | -7.35 | +| explained_variance | 0.0449 | +| learning_rate | 4.96e-05 | +| loss | -0.0254 | +| n_updates | 19240 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000246 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1382 | +| iterations | 857 | +| time_elapsed | 1269 | +| total_timesteps | 1755136 | +| train/ | | +| approx_kl | 0.010658519 | +| clip_fraction | 0.297 | +| clip_range | 0.0746 | +| entropy_loss | -7.56 | +| explained_variance | 0.0697 | +| learning_rate | 4.96e-05 | +| loss | -0.0325 | +| n_updates | 19244 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000141 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1382 | +| iterations | 858 | +| time_elapsed | 1270 | +| total_timesteps | 1757184 | +| train/ | | +| approx_kl | 0.010118904 | +| clip_fraction | 0.287 | +| clip_range | 0.0746 | +| entropy_loss | -7.42 | +| explained_variance | 0.0731 | +| learning_rate | 4.96e-05 | +| loss | -0.0348 | +| n_updates | 19248 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000169 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1382 | +| iterations | 859 | +| time_elapsed | 1272 | +| total_timesteps | 1759232 | +| train/ | | +| approx_kl | 0.011160913 | +| clip_fraction | 0.308 | +| clip_range | 0.0746 | +| entropy_loss | -7.39 | +| explained_variance | 0.33 | +| learning_rate | 4.96e-05 | +| loss | -0.0313 | +| n_updates | 19252 | +| policy_gradient_loss | -0.0223 | +| value_loss | 0.000112 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1382 | +| iterations | 860 | +| time_elapsed | 1273 | +| total_timesteps | 1761280 | +| train/ | | +| approx_kl | 0.009619043 | +| clip_fraction | 0.31 | +| clip_range | 0.0746 | +| entropy_loss | -7.66 | +| explained_variance | -0.142 | +| learning_rate | 4.96e-05 | +| loss | -0.0398 | +| n_updates | 19256 | +| policy_gradient_loss | -0.0209 | +| value_loss | 8.57e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1382 | +| iterations | 861 | +| time_elapsed | 1275 | +| total_timesteps | 1763328 | +| train/ | | +| approx_kl | 0.0092943385 | +| clip_fraction | 0.276 | +| clip_range | 0.0746 | +| entropy_loss | -7.69 | +| explained_variance | -0.156 | +| learning_rate | 4.96e-05 | +| loss | -0.0334 | +| n_updates | 19260 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000131 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1382 | +| iterations | 862 | +| time_elapsed | 1276 | +| total_timesteps | 1765376 | +| train/ | | +| approx_kl | 0.008023177 | +| clip_fraction | 0.258 | +| clip_range | 0.0746 | +| entropy_loss | -7.55 | +| explained_variance | 0.0808 | +| learning_rate | 4.96e-05 | +| loss | -0.0358 | +| n_updates | 19264 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.00022 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1383 | +| iterations | 863 | +| time_elapsed | 1277 | +| total_timesteps | 1767424 | +| train/ | | +| approx_kl | 0.007752895 | +| clip_fraction | 0.265 | +| clip_range | 0.0746 | +| entropy_loss | -7.24 | +| explained_variance | 0.295 | +| learning_rate | 4.96e-05 | +| loss | -0.0278 | +| n_updates | 19268 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000218 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1383 | +| iterations | 864 | +| time_elapsed | 1279 | +| total_timesteps | 1769472 | +| train/ | | +| approx_kl | 0.008005669 | +| clip_fraction | 0.249 | +| clip_range | 0.0746 | +| entropy_loss | -7.4 | +| explained_variance | 0.218 | +| learning_rate | 4.96e-05 | +| loss | -0.0306 | +| n_updates | 19272 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.00021 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1383 | +| iterations | 865 | +| time_elapsed | 1280 | +| total_timesteps | 1771520 | +| train/ | | +| approx_kl | 0.007096034 | +| clip_fraction | 0.253 | +| clip_range | 0.0746 | +| entropy_loss | -7.57 | +| explained_variance | -0.0157 | +| learning_rate | 4.96e-05 | +| loss | -0.0328 | +| n_updates | 19276 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000156 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1383 | +| iterations | 866 | +| time_elapsed | 1282 | +| total_timesteps | 1773568 | +| train/ | | +| approx_kl | 0.008836657 | +| clip_fraction | 0.278 | +| clip_range | 0.0746 | +| entropy_loss | -7.21 | +| explained_variance | 0.192 | +| learning_rate | 4.96e-05 | +| loss | -0.0314 | +| n_updates | 19280 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000313 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1383 | +| iterations | 867 | +| time_elapsed | 1283 | +| total_timesteps | 1775616 | +| train/ | | +| approx_kl | 0.009529405 | +| clip_fraction | 0.293 | +| clip_range | 0.0746 | +| entropy_loss | -7.52 | +| explained_variance | 0.116 | +| learning_rate | 4.96e-05 | +| loss | -0.0345 | +| n_updates | 19284 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000247 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1383 | +| iterations | 868 | +| time_elapsed | 1285 | +| total_timesteps | 1777664 | +| train/ | | +| approx_kl | 0.010911919 | +| clip_fraction | 0.264 | +| clip_range | 0.0746 | +| entropy_loss | -7.43 | +| explained_variance | -0.0682 | +| learning_rate | 4.96e-05 | +| loss | -0.036 | +| n_updates | 19288 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000277 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1383 | +| iterations | 869 | +| time_elapsed | 1286 | +| total_timesteps | 1779712 | +| train/ | | +| approx_kl | 0.0091413 | +| clip_fraction | 0.275 | +| clip_range | 0.0746 | +| entropy_loss | -7.54 | +| explained_variance | 0.0746 | +| learning_rate | 4.96e-05 | +| loss | -0.033 | +| n_updates | 19292 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000206 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1383 | +| iterations | 870 | +| time_elapsed | 1288 | +| total_timesteps | 1781760 | +| train/ | | +| approx_kl | 0.009636683 | +| clip_fraction | 0.276 | +| clip_range | 0.0746 | +| entropy_loss | -7.43 | +| explained_variance | -0.0494 | +| learning_rate | 4.96e-05 | +| loss | -0.0291 | +| n_updates | 19296 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000329 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1383 | +| iterations | 871 | +| time_elapsed | 1289 | +| total_timesteps | 1783808 | +| train/ | | +| approx_kl | 0.010032247 | +| clip_fraction | 0.302 | +| clip_range | 0.0746 | +| entropy_loss | -7.66 | +| explained_variance | -0.0442 | +| learning_rate | 4.96e-05 | +| loss | -0.0361 | +| n_updates | 19300 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000182 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1383 | +| iterations | 872 | +| time_elapsed | 1290 | +| total_timesteps | 1785856 | +| train/ | | +| approx_kl | 0.009778462 | +| clip_fraction | 0.288 | +| clip_range | 0.0746 | +| entropy_loss | -7.54 | +| explained_variance | -0.0856 | +| learning_rate | 4.96e-05 | +| loss | -0.0334 | +| n_updates | 19304 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000234 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1383 | +| iterations | 873 | +| time_elapsed | 1292 | +| total_timesteps | 1787904 | +| train/ | | +| approx_kl | 0.008280369 | +| clip_fraction | 0.285 | +| clip_range | 0.0746 | +| entropy_loss | -7.51 | +| explained_variance | -0.071 | +| learning_rate | 4.96e-05 | +| loss | -0.0365 | +| n_updates | 19308 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000187 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1383 | +| iterations | 874 | +| time_elapsed | 1293 | +| total_timesteps | 1789952 | +| train/ | | +| approx_kl | 0.008722181 | +| clip_fraction | 0.253 | +| clip_range | 0.0746 | +| entropy_loss | -7.18 | +| explained_variance | 0.0218 | +| learning_rate | 4.96e-05 | +| loss | -0.0309 | +| n_updates | 19312 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.00031 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1383 | +| iterations | 875 | +| time_elapsed | 1295 | +| total_timesteps | 1792000 | +| train/ | | +| approx_kl | 0.009494707 | +| clip_fraction | 0.27 | +| clip_range | 0.0746 | +| entropy_loss | -7.58 | +| explained_variance | 0.0778 | +| learning_rate | 4.96e-05 | +| loss | -0.0364 | +| n_updates | 19316 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000112 | +----------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1383 | +| iterations | 876 | +| time_elapsed | 1296 | +| total_timesteps | 1794048 | +| train/ | | +| approx_kl | 0.009729 | +| clip_fraction | 0.283 | +| clip_range | 0.0746 | +| entropy_loss | -7.48 | +| explained_variance | -0.021 | +| learning_rate | 4.96e-05 | +| loss | -0.0347 | +| n_updates | 19320 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000289 | +-------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1383 | +| iterations | 877 | +| time_elapsed | 1298 | +| total_timesteps | 1796096 | +| train/ | | +| approx_kl | 0.01053332 | +| clip_fraction | 0.289 | +| clip_range | 0.0746 | +| entropy_loss | -7.66 | +| explained_variance | -0.0919 | +| learning_rate | 4.96e-05 | +| loss | -0.0345 | +| n_updates | 19324 | +| policy_gradient_loss | -0.0223 | +| value_loss | 0.000198 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1383 | +| iterations | 878 | +| time_elapsed | 1299 | +| total_timesteps | 1798144 | +| train/ | | +| approx_kl | 0.008493227 | +| clip_fraction | 0.292 | +| clip_range | 0.0746 | +| entropy_loss | -7.44 | +| explained_variance | -0.141 | +| learning_rate | 4.96e-05 | +| loss | -0.028 | +| n_updates | 19328 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000117 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1383 | +| iterations | 879 | +| time_elapsed | 1300 | +| total_timesteps | 1800192 | +| train/ | | +| approx_kl | 0.010009968 | +| clip_fraction | 0.298 | +| clip_range | 0.0746 | +| entropy_loss | -7.41 | +| explained_variance | 0.0623 | +| learning_rate | 4.96e-05 | +| loss | -0.0298 | +| n_updates | 19332 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000245 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1383 | +| iterations | 880 | +| time_elapsed | 1302 | +| total_timesteps | 1802240 | +| train/ | | +| approx_kl | 0.010294385 | +| clip_fraction | 0.287 | +| clip_range | 0.0745 | +| entropy_loss | -7.51 | +| explained_variance | -0.0732 | +| learning_rate | 4.96e-05 | +| loss | -0.0294 | +| n_updates | 19336 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000184 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1383 | +| iterations | 881 | +| time_elapsed | 1303 | +| total_timesteps | 1804288 | +| train/ | | +| approx_kl | 0.008729797 | +| clip_fraction | 0.281 | +| clip_range | 0.0745 | +| entropy_loss | -7.27 | +| explained_variance | -0.039 | +| learning_rate | 4.96e-05 | +| loss | -0.0317 | +| n_updates | 19340 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000257 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1383 | +| iterations | 882 | +| time_elapsed | 1305 | +| total_timesteps | 1806336 | +| train/ | | +| approx_kl | 0.010832722 | +| clip_fraction | 0.314 | +| clip_range | 0.0745 | +| entropy_loss | -7.6 | +| explained_variance | -0.109 | +| learning_rate | 4.96e-05 | +| loss | -0.0354 | +| n_updates | 19344 | +| policy_gradient_loss | -0.0241 | +| value_loss | 0.000166 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1384 | +| iterations | 883 | +| time_elapsed | 1306 | +| total_timesteps | 1808384 | +| train/ | | +| approx_kl | 0.008986804 | +| clip_fraction | 0.287 | +| clip_range | 0.0745 | +| entropy_loss | -7.24 | +| explained_variance | 0.021 | +| learning_rate | 4.96e-05 | +| loss | -0.0352 | +| n_updates | 19348 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000187 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1383 | +| iterations | 884 | +| time_elapsed | 1308 | +| total_timesteps | 1810432 | +| train/ | | +| approx_kl | 0.008539259 | +| clip_fraction | 0.292 | +| clip_range | 0.0745 | +| entropy_loss | -7.33 | +| explained_variance | -0.0505 | +| learning_rate | 4.96e-05 | +| loss | -0.0285 | +| n_updates | 19352 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000309 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1384 | +| iterations | 885 | +| time_elapsed | 1309 | +| total_timesteps | 1812480 | +| train/ | | +| approx_kl | 0.0105949305 | +| clip_fraction | 0.289 | +| clip_range | 0.0745 | +| entropy_loss | -7.42 | +| explained_variance | 0.0515 | +| learning_rate | 4.96e-05 | +| loss | -0.0332 | +| n_updates | 19356 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000199 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1384 | +| iterations | 886 | +| time_elapsed | 1310 | +| total_timesteps | 1814528 | +| train/ | | +| approx_kl | 0.009365996 | +| clip_fraction | 0.282 | +| clip_range | 0.0745 | +| entropy_loss | -7.52 | +| explained_variance | -0.0913 | +| learning_rate | 4.96e-05 | +| loss | -0.0364 | +| n_updates | 19360 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000219 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1384 | +| iterations | 887 | +| time_elapsed | 1312 | +| total_timesteps | 1816576 | +| train/ | | +| approx_kl | 0.010383096 | +| clip_fraction | 0.298 | +| clip_range | 0.0745 | +| entropy_loss | -7.61 | +| explained_variance | -0.0824 | +| learning_rate | 4.96e-05 | +| loss | -0.0337 | +| n_updates | 19364 | +| policy_gradient_loss | -0.0231 | +| value_loss | 0.000127 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1384 | +| iterations | 888 | +| time_elapsed | 1313 | +| total_timesteps | 1818624 | +| train/ | | +| approx_kl | 0.0102087455 | +| clip_fraction | 0.292 | +| clip_range | 0.0745 | +| entropy_loss | -7.52 | +| explained_variance | -0.176 | +| learning_rate | 4.96e-05 | +| loss | -0.0396 | +| n_updates | 19368 | +| policy_gradient_loss | -0.0233 | +| value_loss | 0.00011 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1384 | +| iterations | 889 | +| time_elapsed | 1315 | +| total_timesteps | 1820672 | +| train/ | | +| approx_kl | 0.009431457 | +| clip_fraction | 0.307 | +| clip_range | 0.0745 | +| entropy_loss | -7.53 | +| explained_variance | -0.213 | +| learning_rate | 4.96e-05 | +| loss | -0.035 | +| n_updates | 19372 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000125 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1384 | +| iterations | 890 | +| time_elapsed | 1316 | +| total_timesteps | 1822720 | +| train/ | | +| approx_kl | 0.010157534 | +| clip_fraction | 0.299 | +| clip_range | 0.0745 | +| entropy_loss | -7.45 | +| explained_variance | -0.0372 | +| learning_rate | 4.96e-05 | +| loss | -0.0375 | +| n_updates | 19376 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.00017 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1384 | +| iterations | 891 | +| time_elapsed | 1318 | +| total_timesteps | 1824768 | +| train/ | | +| approx_kl | 0.007985681 | +| clip_fraction | 0.285 | +| clip_range | 0.0745 | +| entropy_loss | -7.64 | +| explained_variance | -0.0286 | +| learning_rate | 4.96e-05 | +| loss | -0.0332 | +| n_updates | 19380 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000122 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1384 | +| iterations | 892 | +| time_elapsed | 1319 | +| total_timesteps | 1826816 | +| train/ | | +| approx_kl | 0.0073702396 | +| clip_fraction | 0.266 | +| clip_range | 0.0745 | +| entropy_loss | -7.17 | +| explained_variance | 0.14 | +| learning_rate | 4.96e-05 | +| loss | -0.0302 | +| n_updates | 19384 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000235 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1384 | +| iterations | 893 | +| time_elapsed | 1321 | +| total_timesteps | 1828864 | +| train/ | | +| approx_kl | 0.0111027965 | +| clip_fraction | 0.318 | +| clip_range | 0.0745 | +| entropy_loss | -7.63 | +| explained_variance | -0.274 | +| learning_rate | 4.96e-05 | +| loss | -0.0473 | +| n_updates | 19388 | +| policy_gradient_loss | -0.0252 | +| value_loss | 7.37e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1384 | +| iterations | 894 | +| time_elapsed | 1322 | +| total_timesteps | 1830912 | +| train/ | | +| approx_kl | 0.008627199 | +| clip_fraction | 0.275 | +| clip_range | 0.0745 | +| entropy_loss | -7.32 | +| explained_variance | 0.213 | +| learning_rate | 4.96e-05 | +| loss | -0.0285 | +| n_updates | 19392 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000229 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1384 | +| iterations | 895 | +| time_elapsed | 1323 | +| total_timesteps | 1832960 | +| train/ | | +| approx_kl | 0.009083839 | +| clip_fraction | 0.276 | +| clip_range | 0.0745 | +| entropy_loss | -7.45 | +| explained_variance | 0.0344 | +| learning_rate | 4.96e-05 | +| loss | -0.0355 | +| n_updates | 19396 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000166 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1384 | +| iterations | 896 | +| time_elapsed | 1325 | +| total_timesteps | 1835008 | +| train/ | | +| approx_kl | 0.00930818 | +| clip_fraction | 0.264 | +| clip_range | 0.0745 | +| entropy_loss | -7.57 | +| explained_variance | 0.172 | +| learning_rate | 4.96e-05 | +| loss | -0.0344 | +| n_updates | 19400 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000155 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1384 | +| iterations | 897 | +| time_elapsed | 1326 | +| total_timesteps | 1837056 | +| train/ | | +| approx_kl | 0.008791639 | +| clip_fraction | 0.273 | +| clip_range | 0.0745 | +| entropy_loss | -7.52 | +| explained_variance | -0.0868 | +| learning_rate | 4.96e-05 | +| loss | -0.0351 | +| n_updates | 19404 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000245 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1384 | +| iterations | 898 | +| time_elapsed | 1328 | +| total_timesteps | 1839104 | +| train/ | | +| approx_kl | 0.010563807 | +| clip_fraction | 0.322 | +| clip_range | 0.0745 | +| entropy_loss | -7.36 | +| explained_variance | 0.149 | +| learning_rate | 4.96e-05 | +| loss | -0.0371 | +| n_updates | 19408 | +| policy_gradient_loss | -0.022 | +| value_loss | 0.000152 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1384 | +| iterations | 899 | +| time_elapsed | 1329 | +| total_timesteps | 1841152 | +| train/ | | +| approx_kl | 0.008997926 | +| clip_fraction | 0.287 | +| clip_range | 0.0745 | +| entropy_loss | -7.27 | +| explained_variance | 0.251 | +| learning_rate | 4.96e-05 | +| loss | -0.0332 | +| n_updates | 19412 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000227 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1384 | +| iterations | 900 | +| time_elapsed | 1331 | +| total_timesteps | 1843200 | +| train/ | | +| approx_kl | 0.009369138 | +| clip_fraction | 0.276 | +| clip_range | 0.0745 | +| entropy_loss | -7.36 | +| explained_variance | 0.336 | +| learning_rate | 4.96e-05 | +| loss | -0.0299 | +| n_updates | 19416 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000255 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1384 | +| iterations | 901 | +| time_elapsed | 1332 | +| total_timesteps | 1845248 | +| train/ | | +| approx_kl | 0.009647618 | +| clip_fraction | 0.279 | +| clip_range | 0.0745 | +| entropy_loss | -7.61 | +| explained_variance | -0.0834 | +| learning_rate | 4.96e-05 | +| loss | -0.0343 | +| n_updates | 19420 | +| policy_gradient_loss | -0.0224 | +| value_loss | 0.000174 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1384 | +| iterations | 902 | +| time_elapsed | 1333 | +| total_timesteps | 1847296 | +| train/ | | +| approx_kl | 0.007870196 | +| clip_fraction | 0.283 | +| clip_range | 0.0745 | +| entropy_loss | -7.02 | +| explained_variance | 0.349 | +| learning_rate | 4.96e-05 | +| loss | -0.0283 | +| n_updates | 19424 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000326 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1384 | +| iterations | 903 | +| time_elapsed | 1335 | +| total_timesteps | 1849344 | +| train/ | | +| approx_kl | 0.009464212 | +| clip_fraction | 0.288 | +| clip_range | 0.0745 | +| entropy_loss | -7.44 | +| explained_variance | 0.215 | +| learning_rate | 4.96e-05 | +| loss | -0.0346 | +| n_updates | 19428 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000157 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1384 | +| iterations | 904 | +| time_elapsed | 1336 | +| total_timesteps | 1851392 | +| train/ | | +| approx_kl | 0.009764156 | +| clip_fraction | 0.263 | +| clip_range | 0.0745 | +| entropy_loss | -7.42 | +| explained_variance | 0.0727 | +| learning_rate | 4.96e-05 | +| loss | -0.0293 | +| n_updates | 19432 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000434 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1384 | +| iterations | 905 | +| time_elapsed | 1338 | +| total_timesteps | 1853440 | +| train/ | | +| approx_kl | 0.010140007 | +| clip_fraction | 0.311 | +| clip_range | 0.0745 | +| entropy_loss | -7.62 | +| explained_variance | -0.183 | +| learning_rate | 4.96e-05 | +| loss | -0.0414 | +| n_updates | 19436 | +| policy_gradient_loss | -0.0246 | +| value_loss | 0.000109 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1385 | +| iterations | 906 | +| time_elapsed | 1339 | +| total_timesteps | 1855488 | +| train/ | | +| approx_kl | 0.010044562 | +| clip_fraction | 0.305 | +| clip_range | 0.0745 | +| entropy_loss | -7.24 | +| explained_variance | -0.0944 | +| learning_rate | 4.96e-05 | +| loss | -0.0389 | +| n_updates | 19440 | +| policy_gradient_loss | -0.0226 | +| value_loss | 0.000254 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1385 | +| iterations | 907 | +| time_elapsed | 1341 | +| total_timesteps | 1857536 | +| train/ | | +| approx_kl | 0.009219117 | +| clip_fraction | 0.279 | +| clip_range | 0.0745 | +| entropy_loss | -7.62 | +| explained_variance | -0.0689 | +| learning_rate | 4.96e-05 | +| loss | -0.0284 | +| n_updates | 19444 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000186 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1384 | +| iterations | 908 | +| time_elapsed | 1342 | +| total_timesteps | 1859584 | +| train/ | | +| approx_kl | 0.009574277 | +| clip_fraction | 0.244 | +| clip_range | 0.0745 | +| entropy_loss | -7.54 | +| explained_variance | 0.115 | +| learning_rate | 4.96e-05 | +| loss | -0.0291 | +| n_updates | 19448 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000376 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1384 | +| iterations | 909 | +| time_elapsed | 1344 | +| total_timesteps | 1861632 | +| train/ | | +| approx_kl | 0.010607374 | +| clip_fraction | 0.307 | +| clip_range | 0.0745 | +| entropy_loss | -7.34 | +| explained_variance | -0.0867 | +| learning_rate | 4.96e-05 | +| loss | -0.0321 | +| n_updates | 19452 | +| policy_gradient_loss | -0.0239 | +| value_loss | 0.000165 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1384 | +| iterations | 910 | +| time_elapsed | 1345 | +| total_timesteps | 1863680 | +| train/ | | +| approx_kl | 0.009964266 | +| clip_fraction | 0.286 | +| clip_range | 0.0745 | +| entropy_loss | -7.22 | +| explained_variance | 0.172 | +| learning_rate | 4.96e-05 | +| loss | -0.0263 | +| n_updates | 19456 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000268 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1385 | +| iterations | 911 | +| time_elapsed | 1347 | +| total_timesteps | 1865728 | +| train/ | | +| approx_kl | 0.0074325325 | +| clip_fraction | 0.264 | +| clip_range | 0.0745 | +| entropy_loss | -7.35 | +| explained_variance | 0.0869 | +| learning_rate | 4.96e-05 | +| loss | -0.0323 | +| n_updates | 19460 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.00029 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1385 | +| iterations | 912 | +| time_elapsed | 1348 | +| total_timesteps | 1867776 | +| train/ | | +| approx_kl | 0.009045404 | +| clip_fraction | 0.307 | +| clip_range | 0.0745 | +| entropy_loss | -7.63 | +| explained_variance | -0.262 | +| learning_rate | 4.96e-05 | +| loss | -0.0418 | +| n_updates | 19464 | +| policy_gradient_loss | -0.0224 | +| value_loss | 0.000193 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1385 | +| iterations | 913 | +| time_elapsed | 1349 | +| total_timesteps | 1869824 | +| train/ | | +| approx_kl | 0.008302849 | +| clip_fraction | 0.269 | +| clip_range | 0.0745 | +| entropy_loss | -7.22 | +| explained_variance | 0.191 | +| learning_rate | 4.96e-05 | +| loss | -0.0292 | +| n_updates | 19468 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000304 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1385 | +| iterations | 914 | +| time_elapsed | 1351 | +| total_timesteps | 1871872 | +| train/ | | +| approx_kl | 0.009500053 | +| clip_fraction | 0.3 | +| clip_range | 0.0745 | +| entropy_loss | -7.61 | +| explained_variance | -0.045 | +| learning_rate | 4.96e-05 | +| loss | -0.0388 | +| n_updates | 19472 | +| policy_gradient_loss | -0.0229 | +| value_loss | 0.000246 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1385 | +| iterations | 915 | +| time_elapsed | 1352 | +| total_timesteps | 1873920 | +| train/ | | +| approx_kl | 0.009544263 | +| clip_fraction | 0.306 | +| clip_range | 0.0745 | +| entropy_loss | -7.56 | +| explained_variance | 0.0832 | +| learning_rate | 4.96e-05 | +| loss | -0.0469 | +| n_updates | 19476 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.00019 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1385 | +| iterations | 916 | +| time_elapsed | 1354 | +| total_timesteps | 1875968 | +| train/ | | +| approx_kl | 0.0097361 | +| clip_fraction | 0.274 | +| clip_range | 0.0745 | +| entropy_loss | -7.24 | +| explained_variance | 0.317 | +| learning_rate | 4.96e-05 | +| loss | -0.0315 | +| n_updates | 19480 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000292 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1385 | +| iterations | 917 | +| time_elapsed | 1355 | +| total_timesteps | 1878016 | +| train/ | | +| approx_kl | 0.010444516 | +| clip_fraction | 0.312 | +| clip_range | 0.0745 | +| entropy_loss | -7.62 | +| explained_variance | -0.166 | +| learning_rate | 4.96e-05 | +| loss | -0.0393 | +| n_updates | 19484 | +| policy_gradient_loss | -0.0229 | +| value_loss | 0.000128 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1385 | +| iterations | 918 | +| time_elapsed | 1357 | +| total_timesteps | 1880064 | +| train/ | | +| approx_kl | 0.008379767 | +| clip_fraction | 0.28 | +| clip_range | 0.0745 | +| entropy_loss | -7.63 | +| explained_variance | -0.189 | +| learning_rate | 4.96e-05 | +| loss | -0.0368 | +| n_updates | 19488 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.00016 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1385 | +| iterations | 919 | +| time_elapsed | 1358 | +| total_timesteps | 1882112 | +| train/ | | +| approx_kl | 0.009097023 | +| clip_fraction | 0.267 | +| clip_range | 0.0745 | +| entropy_loss | -7.28 | +| explained_variance | 0.19 | +| learning_rate | 4.96e-05 | +| loss | -0.03 | +| n_updates | 19492 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000411 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1385 | +| iterations | 920 | +| time_elapsed | 1360 | +| total_timesteps | 1884160 | +| train/ | | +| approx_kl | 0.009881524 | +| clip_fraction | 0.29 | +| clip_range | 0.0745 | +| entropy_loss | -7.67 | +| explained_variance | -0.176 | +| learning_rate | 4.96e-05 | +| loss | -0.0392 | +| n_updates | 19496 | +| policy_gradient_loss | -0.0238 | +| value_loss | 0.000182 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1385 | +| iterations | 921 | +| time_elapsed | 1361 | +| total_timesteps | 1886208 | +| train/ | | +| approx_kl | 0.009216878 | +| clip_fraction | 0.301 | +| clip_range | 0.0745 | +| entropy_loss | -7.19 | +| explained_variance | 0.427 | +| learning_rate | 4.96e-05 | +| loss | -0.0348 | +| n_updates | 19500 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000194 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1385 | +| iterations | 922 | +| time_elapsed | 1362 | +| total_timesteps | 1888256 | +| train/ | | +| approx_kl | 0.009901083 | +| clip_fraction | 0.318 | +| clip_range | 0.0745 | +| entropy_loss | -7.24 | +| explained_variance | 0.522 | +| learning_rate | 4.96e-05 | +| loss | -0.0368 | +| n_updates | 19504 | +| policy_gradient_loss | -0.0247 | +| value_loss | 8.83e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1385 | +| iterations | 923 | +| time_elapsed | 1364 | +| total_timesteps | 1890304 | +| train/ | | +| approx_kl | 0.010223818 | +| clip_fraction | 0.309 | +| clip_range | 0.0745 | +| entropy_loss | -7.59 | +| explained_variance | -0.307 | +| learning_rate | 4.96e-05 | +| loss | -0.041 | +| n_updates | 19508 | +| policy_gradient_loss | -0.0244 | +| value_loss | 0.000113 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1385 | +| iterations | 924 | +| time_elapsed | 1365 | +| total_timesteps | 1892352 | +| train/ | | +| approx_kl | 0.0085515315 | +| clip_fraction | 0.285 | +| clip_range | 0.0745 | +| entropy_loss | -7.66 | +| explained_variance | -0.0376 | +| learning_rate | 4.96e-05 | +| loss | -0.0393 | +| n_updates | 19512 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000147 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1385 | +| iterations | 925 | +| time_elapsed | 1367 | +| total_timesteps | 1894400 | +| train/ | | +| approx_kl | 0.00904826 | +| clip_fraction | 0.288 | +| clip_range | 0.0745 | +| entropy_loss | -7.56 | +| explained_variance | 0.208 | +| learning_rate | 4.96e-05 | +| loss | -0.036 | +| n_updates | 19516 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000144 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1385 | +| iterations | 926 | +| time_elapsed | 1368 | +| total_timesteps | 1896448 | +| train/ | | +| approx_kl | 0.006752043 | +| clip_fraction | 0.238 | +| clip_range | 0.0745 | +| entropy_loss | -7.33 | +| explained_variance | 0.124 | +| learning_rate | 4.96e-05 | +| loss | -0.027 | +| n_updates | 19520 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000244 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1385 | +| iterations | 927 | +| time_elapsed | 1370 | +| total_timesteps | 1898496 | +| train/ | | +| approx_kl | 0.00878581 | +| clip_fraction | 0.278 | +| clip_range | 0.0745 | +| entropy_loss | -7.52 | +| explained_variance | 0.0865 | +| learning_rate | 4.95e-05 | +| loss | -0.0332 | +| n_updates | 19524 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000221 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1385 | +| iterations | 928 | +| time_elapsed | 1371 | +| total_timesteps | 1900544 | +| train/ | | +| approx_kl | 0.009117076 | +| clip_fraction | 0.285 | +| clip_range | 0.0745 | +| entropy_loss | -7.47 | +| explained_variance | 0.207 | +| learning_rate | 4.95e-05 | +| loss | -0.0338 | +| n_updates | 19528 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000187 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1385 | +| iterations | 929 | +| time_elapsed | 1372 | +| total_timesteps | 1902592 | +| train/ | | +| approx_kl | 0.009168211 | +| clip_fraction | 0.285 | +| clip_range | 0.0745 | +| entropy_loss | -7.14 | +| explained_variance | 0.25 | +| learning_rate | 4.95e-05 | +| loss | -0.0315 | +| n_updates | 19532 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.00029 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1385 | +| iterations | 930 | +| time_elapsed | 1374 | +| total_timesteps | 1904640 | +| train/ | | +| approx_kl | 0.010353893 | +| clip_fraction | 0.306 | +| clip_range | 0.0745 | +| entropy_loss | -7.54 | +| explained_variance | -0.146 | +| learning_rate | 4.95e-05 | +| loss | -0.0389 | +| n_updates | 19536 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000156 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1385 | +| iterations | 931 | +| time_elapsed | 1375 | +| total_timesteps | 1906688 | +| train/ | | +| approx_kl | 0.0106518995 | +| clip_fraction | 0.3 | +| clip_range | 0.0745 | +| entropy_loss | -7.35 | +| explained_variance | -0.00702 | +| learning_rate | 4.95e-05 | +| loss | -0.0309 | +| n_updates | 19540 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000162 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1385 | +| iterations | 932 | +| time_elapsed | 1377 | +| total_timesteps | 1908736 | +| train/ | | +| approx_kl | 0.010414533 | +| clip_fraction | 0.295 | +| clip_range | 0.0745 | +| entropy_loss | -7.46 | +| explained_variance | -0.155 | +| learning_rate | 4.95e-05 | +| loss | -0.0265 | +| n_updates | 19544 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000122 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1385 | +| iterations | 933 | +| time_elapsed | 1378 | +| total_timesteps | 1910784 | +| train/ | | +| approx_kl | 0.008787798 | +| clip_fraction | 0.281 | +| clip_range | 0.0745 | +| entropy_loss | -7.45 | +| explained_variance | 0.17 | +| learning_rate | 4.95e-05 | +| loss | -0.0365 | +| n_updates | 19548 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000122 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1385 | +| iterations | 934 | +| time_elapsed | 1380 | +| total_timesteps | 1912832 | +| train/ | | +| approx_kl | 0.011552319 | +| clip_fraction | 0.298 | +| clip_range | 0.0745 | +| entropy_loss | -7.44 | +| explained_variance | -0.232 | +| learning_rate | 4.95e-05 | +| loss | -0.0387 | +| n_updates | 19552 | +| policy_gradient_loss | -0.0222 | +| value_loss | 9.82e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1386 | +| iterations | 935 | +| time_elapsed | 1381 | +| total_timesteps | 1914880 | +| train/ | | +| approx_kl | 0.009797613 | +| clip_fraction | 0.279 | +| clip_range | 0.0745 | +| entropy_loss | -7.25 | +| explained_variance | 0.131 | +| learning_rate | 4.95e-05 | +| loss | -0.0321 | +| n_updates | 19556 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000285 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1386 | +| iterations | 936 | +| time_elapsed | 1382 | +| total_timesteps | 1916928 | +| train/ | | +| approx_kl | 0.0096811615 | +| clip_fraction | 0.29 | +| clip_range | 0.0745 | +| entropy_loss | -7.53 | +| explained_variance | -0.163 | +| learning_rate | 4.95e-05 | +| loss | -0.0324 | +| n_updates | 19560 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000215 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1386 | +| iterations | 937 | +| time_elapsed | 1384 | +| total_timesteps | 1918976 | +| train/ | | +| approx_kl | 0.008110412 | +| clip_fraction | 0.258 | +| clip_range | 0.0745 | +| entropy_loss | -7.43 | +| explained_variance | 0.0588 | +| learning_rate | 4.95e-05 | +| loss | -0.0366 | +| n_updates | 19564 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000193 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1386 | +| iterations | 938 | +| time_elapsed | 1385 | +| total_timesteps | 1921024 | +| train/ | | +| approx_kl | 0.009664931 | +| clip_fraction | 0.276 | +| clip_range | 0.0745 | +| entropy_loss | -7.48 | +| explained_variance | 0.216 | +| learning_rate | 4.95e-05 | +| loss | -0.0376 | +| n_updates | 19568 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.0002 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1386 | +| iterations | 939 | +| time_elapsed | 1387 | +| total_timesteps | 1923072 | +| train/ | | +| approx_kl | 0.009439018 | +| clip_fraction | 0.279 | +| clip_range | 0.0745 | +| entropy_loss | -7.57 | +| explained_variance | 0.211 | +| learning_rate | 4.95e-05 | +| loss | -0.0293 | +| n_updates | 19572 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000161 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1386 | +| iterations | 940 | +| time_elapsed | 1388 | +| total_timesteps | 1925120 | +| train/ | | +| approx_kl | 0.009597858 | +| clip_fraction | 0.282 | +| clip_range | 0.0745 | +| entropy_loss | -7.66 | +| explained_variance | -0.0664 | +| learning_rate | 4.95e-05 | +| loss | -0.0319 | +| n_updates | 19576 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000175 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1386 | +| iterations | 941 | +| time_elapsed | 1390 | +| total_timesteps | 1927168 | +| train/ | | +| approx_kl | 0.00796531 | +| clip_fraction | 0.273 | +| clip_range | 0.0745 | +| entropy_loss | -7.5 | +| explained_variance | 0.131 | +| learning_rate | 4.95e-05 | +| loss | -0.0338 | +| n_updates | 19580 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000287 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1386 | +| iterations | 942 | +| time_elapsed | 1391 | +| total_timesteps | 1929216 | +| train/ | | +| approx_kl | 0.009243118 | +| clip_fraction | 0.312 | +| clip_range | 0.0745 | +| entropy_loss | -7.44 | +| explained_variance | 0.18 | +| learning_rate | 4.95e-05 | +| loss | -0.0339 | +| n_updates | 19584 | +| policy_gradient_loss | -0.0225 | +| value_loss | 0.000124 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1386 | +| iterations | 943 | +| time_elapsed | 1393 | +| total_timesteps | 1931264 | +| train/ | | +| approx_kl | 0.011574409 | +| clip_fraction | 0.298 | +| clip_range | 0.0745 | +| entropy_loss | -7.36 | +| explained_variance | -0.0664 | +| learning_rate | 4.95e-05 | +| loss | -0.0323 | +| n_updates | 19588 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000165 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1386 | +| iterations | 944 | +| time_elapsed | 1394 | +| total_timesteps | 1933312 | +| train/ | | +| approx_kl | 0.009710515 | +| clip_fraction | 0.296 | +| clip_range | 0.0745 | +| entropy_loss | -7.41 | +| explained_variance | 0.25 | +| learning_rate | 4.95e-05 | +| loss | -0.037 | +| n_updates | 19592 | +| policy_gradient_loss | -0.0221 | +| value_loss | 0.000101 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1386 | +| iterations | 945 | +| time_elapsed | 1396 | +| total_timesteps | 1935360 | +| train/ | | +| approx_kl | 0.01078199 | +| clip_fraction | 0.303 | +| clip_range | 0.0745 | +| entropy_loss | -7.45 | +| explained_variance | 0.229 | +| learning_rate | 4.95e-05 | +| loss | -0.0332 | +| n_updates | 19596 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000172 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1386 | +| iterations | 946 | +| time_elapsed | 1397 | +| total_timesteps | 1937408 | +| train/ | | +| approx_kl | 0.009916956 | +| clip_fraction | 0.301 | +| clip_range | 0.0745 | +| entropy_loss | -7.59 | +| explained_variance | 0.112 | +| learning_rate | 4.95e-05 | +| loss | -0.0327 | +| n_updates | 19600 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000178 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1386 | +| iterations | 947 | +| time_elapsed | 1398 | +| total_timesteps | 1939456 | +| train/ | | +| approx_kl | 0.008364025 | +| clip_fraction | 0.286 | +| clip_range | 0.0745 | +| entropy_loss | -7.51 | +| explained_variance | 0.138 | +| learning_rate | 4.95e-05 | +| loss | -0.0326 | +| n_updates | 19604 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000218 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1386 | +| iterations | 948 | +| time_elapsed | 1400 | +| total_timesteps | 1941504 | +| train/ | | +| approx_kl | 0.007855718 | +| clip_fraction | 0.274 | +| clip_range | 0.0745 | +| entropy_loss | -7.48 | +| explained_variance | -0.198 | +| learning_rate | 4.95e-05 | +| loss | -0.0343 | +| n_updates | 19608 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000175 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1386 | +| iterations | 949 | +| time_elapsed | 1401 | +| total_timesteps | 1943552 | +| train/ | | +| approx_kl | 0.008585221 | +| clip_fraction | 0.29 | +| clip_range | 0.0745 | +| entropy_loss | -7.25 | +| explained_variance | 0.0616 | +| learning_rate | 4.95e-05 | +| loss | -0.0355 | +| n_updates | 19612 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000292 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1386 | +| iterations | 950 | +| time_elapsed | 1403 | +| total_timesteps | 1945600 | +| train/ | | +| approx_kl | 0.010270517 | +| clip_fraction | 0.324 | +| clip_range | 0.0745 | +| entropy_loss | -7.37 | +| explained_variance | -0.0272 | +| learning_rate | 4.95e-05 | +| loss | -0.0381 | +| n_updates | 19616 | +| policy_gradient_loss | -0.0246 | +| value_loss | 0.000131 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1386 | +| iterations | 951 | +| time_elapsed | 1404 | +| total_timesteps | 1947648 | +| train/ | | +| approx_kl | 0.0097402595 | +| clip_fraction | 0.294 | +| clip_range | 0.0745 | +| entropy_loss | -7.49 | +| explained_variance | -0.116 | +| learning_rate | 4.95e-05 | +| loss | -0.0377 | +| n_updates | 19620 | +| policy_gradient_loss | -0.022 | +| value_loss | 0.000126 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1386 | +| iterations | 952 | +| time_elapsed | 1406 | +| total_timesteps | 1949696 | +| train/ | | +| approx_kl | 0.00967239 | +| clip_fraction | 0.3 | +| clip_range | 0.0745 | +| entropy_loss | -7.53 | +| explained_variance | -0.0659 | +| learning_rate | 4.95e-05 | +| loss | -0.034 | +| n_updates | 19624 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000235 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1386 | +| iterations | 953 | +| time_elapsed | 1407 | +| total_timesteps | 1951744 | +| train/ | | +| approx_kl | 0.010232851 | +| clip_fraction | 0.274 | +| clip_range | 0.0745 | +| entropy_loss | -7.34 | +| explained_variance | 0.0747 | +| learning_rate | 4.95e-05 | +| loss | -0.0215 | +| n_updates | 19628 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000259 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1386 | +| iterations | 954 | +| time_elapsed | 1408 | +| total_timesteps | 1953792 | +| train/ | | +| approx_kl | 0.008820955 | +| clip_fraction | 0.294 | +| clip_range | 0.0745 | +| entropy_loss | -7.39 | +| explained_variance | -0.191 | +| learning_rate | 4.95e-05 | +| loss | -0.0327 | +| n_updates | 19632 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000224 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1386 | +| iterations | 955 | +| time_elapsed | 1410 | +| total_timesteps | 1955840 | +| train/ | | +| approx_kl | 0.009345705 | +| clip_fraction | 0.279 | +| clip_range | 0.0745 | +| entropy_loss | -7.18 | +| explained_variance | 0.15 | +| learning_rate | 4.95e-05 | +| loss | -0.03 | +| n_updates | 19636 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000221 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1386 | +| iterations | 956 | +| time_elapsed | 1411 | +| total_timesteps | 1957888 | +| train/ | | +| approx_kl | 0.012141477 | +| clip_fraction | 0.322 | +| clip_range | 0.0745 | +| entropy_loss | -7.57 | +| explained_variance | -0.0989 | +| learning_rate | 4.95e-05 | +| loss | -0.0415 | +| n_updates | 19640 | +| policy_gradient_loss | -0.0222 | +| value_loss | 0.000178 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1386 | +| iterations | 957 | +| time_elapsed | 1413 | +| total_timesteps | 1959936 | +| train/ | | +| approx_kl | 0.009524065 | +| clip_fraction | 0.303 | +| clip_range | 0.0745 | +| entropy_loss | -7.6 | +| explained_variance | -0.145 | +| learning_rate | 4.95e-05 | +| loss | -0.0349 | +| n_updates | 19644 | +| policy_gradient_loss | -0.0219 | +| value_loss | 0.000118 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1386 | +| iterations | 958 | +| time_elapsed | 1414 | +| total_timesteps | 1961984 | +| train/ | | +| approx_kl | 0.008695038 | +| clip_fraction | 0.274 | +| clip_range | 0.0745 | +| entropy_loss | -7.34 | +| explained_variance | 0.014 | +| learning_rate | 4.95e-05 | +| loss | -0.0305 | +| n_updates | 19648 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000235 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1386 | +| iterations | 959 | +| time_elapsed | 1416 | +| total_timesteps | 1964032 | +| train/ | | +| approx_kl | 0.008193803 | +| clip_fraction | 0.273 | +| clip_range | 0.0745 | +| entropy_loss | -7.4 | +| explained_variance | 0.0586 | +| learning_rate | 4.95e-05 | +| loss | -0.0315 | +| n_updates | 19652 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000263 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1386 | +| iterations | 960 | +| time_elapsed | 1417 | +| total_timesteps | 1966080 | +| train/ | | +| approx_kl | 0.009753416 | +| clip_fraction | 0.3 | +| clip_range | 0.0745 | +| entropy_loss | -7.49 | +| explained_variance | -0.0812 | +| learning_rate | 4.95e-05 | +| loss | -0.0354 | +| n_updates | 19656 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000134 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1386 | +| iterations | 961 | +| time_elapsed | 1419 | +| total_timesteps | 1968128 | +| train/ | | +| approx_kl | 0.009650509 | +| clip_fraction | 0.27 | +| clip_range | 0.0745 | +| entropy_loss | -7.49 | +| explained_variance | 0.153 | +| learning_rate | 4.95e-05 | +| loss | -0.0299 | +| n_updates | 19660 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1387 | +| iterations | 962 | +| time_elapsed | 1420 | +| total_timesteps | 1970176 | +| train/ | | +| approx_kl | 0.011926464 | +| clip_fraction | 0.31 | +| clip_range | 0.0745 | +| entropy_loss | -7.61 | +| explained_variance | -0.0937 | +| learning_rate | 4.95e-05 | +| loss | -0.0349 | +| n_updates | 19664 | +| policy_gradient_loss | -0.022 | +| value_loss | 0.000144 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1387 | +| iterations | 963 | +| time_elapsed | 1421 | +| total_timesteps | 1972224 | +| train/ | | +| approx_kl | 0.009672888 | +| clip_fraction | 0.266 | +| clip_range | 0.0745 | +| entropy_loss | -7.71 | +| explained_variance | -0.0175 | +| learning_rate | 4.95e-05 | +| loss | -0.0308 | +| n_updates | 19668 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000159 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1387 | +| iterations | 964 | +| time_elapsed | 1423 | +| total_timesteps | 1974272 | +| train/ | | +| approx_kl | 0.008966518 | +| clip_fraction | 0.287 | +| clip_range | 0.0745 | +| entropy_loss | -7.41 | +| explained_variance | 0.036 | +| learning_rate | 4.95e-05 | +| loss | -0.0337 | +| n_updates | 19672 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.00024 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1387 | +| iterations | 965 | +| time_elapsed | 1424 | +| total_timesteps | 1976320 | +| train/ | | +| approx_kl | 0.010143174 | +| clip_fraction | 0.301 | +| clip_range | 0.0745 | +| entropy_loss | -7.46 | +| explained_variance | -0.129 | +| learning_rate | 4.95e-05 | +| loss | -0.0378 | +| n_updates | 19676 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000141 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1387 | +| iterations | 966 | +| time_elapsed | 1426 | +| total_timesteps | 1978368 | +| train/ | | +| approx_kl | 0.009341587 | +| clip_fraction | 0.294 | +| clip_range | 0.0745 | +| entropy_loss | -7.19 | +| explained_variance | 0.00272 | +| learning_rate | 4.95e-05 | +| loss | -0.0331 | +| n_updates | 19680 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000301 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1387 | +| iterations | 967 | +| time_elapsed | 1427 | +| total_timesteps | 1980416 | +| train/ | | +| approx_kl | 0.010300552 | +| clip_fraction | 0.307 | +| clip_range | 0.0745 | +| entropy_loss | -7.42 | +| explained_variance | -0.0475 | +| learning_rate | 4.95e-05 | +| loss | -0.0373 | +| n_updates | 19684 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000146 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1387 | +| iterations | 968 | +| time_elapsed | 1429 | +| total_timesteps | 1982464 | +| train/ | | +| approx_kl | 0.009704246 | +| clip_fraction | 0.287 | +| clip_range | 0.0745 | +| entropy_loss | -7.32 | +| explained_variance | 0.255 | +| learning_rate | 4.95e-05 | +| loss | -0.0349 | +| n_updates | 19688 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.00015 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1387 | +| iterations | 969 | +| time_elapsed | 1430 | +| total_timesteps | 1984512 | +| train/ | | +| approx_kl | 0.010785793 | +| clip_fraction | 0.321 | +| clip_range | 0.0745 | +| entropy_loss | -7.63 | +| explained_variance | -0.112 | +| learning_rate | 4.95e-05 | +| loss | -0.0351 | +| n_updates | 19692 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000163 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1387 | +| iterations | 970 | +| time_elapsed | 1431 | +| total_timesteps | 1986560 | +| train/ | | +| approx_kl | 0.0109951105 | +| clip_fraction | 0.296 | +| clip_range | 0.0745 | +| entropy_loss | -7.58 | +| explained_variance | -0.0466 | +| learning_rate | 4.95e-05 | +| loss | -0.0388 | +| n_updates | 19696 | +| policy_gradient_loss | -0.0227 | +| value_loss | 0.000134 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1387 | +| iterations | 971 | +| time_elapsed | 1433 | +| total_timesteps | 1988608 | +| train/ | | +| approx_kl | 0.009756951 | +| clip_fraction | 0.312 | +| clip_range | 0.0745 | +| entropy_loss | -7.57 | +| explained_variance | -0.341 | +| learning_rate | 4.95e-05 | +| loss | -0.0284 | +| n_updates | 19700 | +| policy_gradient_loss | -0.0223 | +| value_loss | 0.000107 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1387 | +| iterations | 972 | +| time_elapsed | 1434 | +| total_timesteps | 1990656 | +| train/ | | +| approx_kl | 0.009649969 | +| clip_fraction | 0.308 | +| clip_range | 0.0745 | +| entropy_loss | -7.67 | +| explained_variance | -0.0454 | +| learning_rate | 4.95e-05 | +| loss | -0.0331 | +| n_updates | 19704 | +| policy_gradient_loss | -0.0226 | +| value_loss | 7.36e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1387 | +| iterations | 973 | +| time_elapsed | 1436 | +| total_timesteps | 1992704 | +| train/ | | +| approx_kl | 0.007236304 | +| clip_fraction | 0.238 | +| clip_range | 0.0745 | +| entropy_loss | -7.46 | +| explained_variance | 0.109 | +| learning_rate | 4.95e-05 | +| loss | -0.0265 | +| n_updates | 19708 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.00024 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1387 | +| iterations | 974 | +| time_elapsed | 1437 | +| total_timesteps | 1994752 | +| train/ | | +| approx_kl | 0.008581208 | +| clip_fraction | 0.278 | +| clip_range | 0.0745 | +| entropy_loss | -7.65 | +| explained_variance | -0.0845 | +| learning_rate | 4.95e-05 | +| loss | -0.0287 | +| n_updates | 19712 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000167 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1387 | +| iterations | 975 | +| time_elapsed | 1438 | +| total_timesteps | 1996800 | +| train/ | | +| approx_kl | 0.0089469645 | +| clip_fraction | 0.277 | +| clip_range | 0.0745 | +| entropy_loss | -7.27 | +| explained_variance | -0.0311 | +| learning_rate | 4.95e-05 | +| loss | -0.0306 | +| n_updates | 19716 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.00028 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1387 | +| iterations | 976 | +| time_elapsed | 1440 | +| total_timesteps | 1998848 | +| train/ | | +| approx_kl | 0.009100374 | +| clip_fraction | 0.284 | +| clip_range | 0.0745 | +| entropy_loss | -7.44 | +| explained_variance | -0.0958 | +| learning_rate | 4.95e-05 | +| loss | -0.03 | +| n_updates | 19720 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000219 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1387 | +| iterations | 977 | +| time_elapsed | 1441 | +| total_timesteps | 2000896 | +| train/ | | +| approx_kl | 0.009615641 | +| clip_fraction | 0.281 | +| clip_range | 0.0745 | +| entropy_loss | -7.25 | +| explained_variance | 0.0952 | +| learning_rate | 4.95e-05 | +| loss | -0.0324 | +| n_updates | 19724 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000353 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1387 | +| iterations | 978 | +| time_elapsed | 1443 | +| total_timesteps | 2002944 | +| train/ | | +| approx_kl | 0.010360271 | +| clip_fraction | 0.305 | +| clip_range | 0.0745 | +| entropy_loss | -7.43 | +| explained_variance | -0.102 | +| learning_rate | 4.95e-05 | +| loss | -0.0377 | +| n_updates | 19728 | +| policy_gradient_loss | -0.023 | +| value_loss | 0.000182 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1387 | +| iterations | 979 | +| time_elapsed | 1444 | +| total_timesteps | 2004992 | +| train/ | | +| approx_kl | 0.009407813 | +| clip_fraction | 0.275 | +| clip_range | 0.0745 | +| entropy_loss | -7.47 | +| explained_variance | -0.00804 | +| learning_rate | 4.95e-05 | +| loss | -0.0335 | +| n_updates | 19732 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000264 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1387 | +| iterations | 980 | +| time_elapsed | 1446 | +| total_timesteps | 2007040 | +| train/ | | +| approx_kl | 0.009945465 | +| clip_fraction | 0.28 | +| clip_range | 0.0745 | +| entropy_loss | -7.51 | +| explained_variance | -0.0293 | +| learning_rate | 4.95e-05 | +| loss | -0.0287 | +| n_updates | 19736 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000199 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1387 | +| iterations | 981 | +| time_elapsed | 1447 | +| total_timesteps | 2009088 | +| train/ | | +| approx_kl | 0.009472908 | +| clip_fraction | 0.315 | +| clip_range | 0.0745 | +| entropy_loss | -7.44 | +| explained_variance | 0.146 | +| learning_rate | 4.95e-05 | +| loss | -0.034 | +| n_updates | 19740 | +| policy_gradient_loss | -0.0227 | +| value_loss | 0.000134 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1387 | +| iterations | 982 | +| time_elapsed | 1449 | +| total_timesteps | 2011136 | +| train/ | | +| approx_kl | 0.010276426 | +| clip_fraction | 0.3 | +| clip_range | 0.0745 | +| entropy_loss | -7.38 | +| explained_variance | 0.136 | +| learning_rate | 4.95e-05 | +| loss | -0.0328 | +| n_updates | 19744 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000316 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1387 | +| iterations | 983 | +| time_elapsed | 1450 | +| total_timesteps | 2013184 | +| train/ | | +| approx_kl | 0.009520661 | +| clip_fraction | 0.285 | +| clip_range | 0.0745 | +| entropy_loss | -7.45 | +| explained_variance | 0.00069 | +| learning_rate | 4.95e-05 | +| loss | -0.0361 | +| n_updates | 19748 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.00015 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1387 | +| iterations | 984 | +| time_elapsed | 1451 | +| total_timesteps | 2015232 | +| train/ | | +| approx_kl | 0.009011221 | +| clip_fraction | 0.279 | +| clip_range | 0.0745 | +| entropy_loss | -7.43 | +| explained_variance | -0.0226 | +| learning_rate | 4.95e-05 | +| loss | -0.0295 | +| n_updates | 19752 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000267 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1388 | +| iterations | 985 | +| time_elapsed | 1453 | +| total_timesteps | 2017280 | +| train/ | | +| approx_kl | 0.00969333 | +| clip_fraction | 0.252 | +| clip_range | 0.0745 | +| entropy_loss | -7.52 | +| explained_variance | 0.012 | +| learning_rate | 4.95e-05 | +| loss | -0.0327 | +| n_updates | 19756 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000327 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1388 | +| iterations | 986 | +| time_elapsed | 1454 | +| total_timesteps | 2019328 | +| train/ | | +| approx_kl | 0.0096515715 | +| clip_fraction | 0.292 | +| clip_range | 0.0745 | +| entropy_loss | -7.4 | +| explained_variance | 0.218 | +| learning_rate | 4.95e-05 | +| loss | -0.0363 | +| n_updates | 19760 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000168 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1388 | +| iterations | 987 | +| time_elapsed | 1456 | +| total_timesteps | 2021376 | +| train/ | | +| approx_kl | 0.008359416 | +| clip_fraction | 0.263 | +| clip_range | 0.0745 | +| entropy_loss | -7.47 | +| explained_variance | 0.176 | +| learning_rate | 4.95e-05 | +| loss | -0.0394 | +| n_updates | 19764 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000182 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1388 | +| iterations | 988 | +| time_elapsed | 1457 | +| total_timesteps | 2023424 | +| train/ | | +| approx_kl | 0.010281519 | +| clip_fraction | 0.279 | +| clip_range | 0.0745 | +| entropy_loss | -7.4 | +| explained_variance | 0.0822 | +| learning_rate | 4.95e-05 | +| loss | -0.0309 | +| n_updates | 19768 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000226 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1388 | +| iterations | 989 | +| time_elapsed | 1459 | +| total_timesteps | 2025472 | +| train/ | | +| approx_kl | 0.010089656 | +| clip_fraction | 0.324 | +| clip_range | 0.0745 | +| entropy_loss | -7.6 | +| explained_variance | -0.0714 | +| learning_rate | 4.95e-05 | +| loss | -0.0405 | +| n_updates | 19772 | +| policy_gradient_loss | -0.0242 | +| value_loss | 0.000184 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1388 | +| iterations | 990 | +| time_elapsed | 1460 | +| total_timesteps | 2027520 | +| train/ | | +| approx_kl | 0.0074713486 | +| clip_fraction | 0.262 | +| clip_range | 0.0745 | +| entropy_loss | -7.71 | +| explained_variance | -0.131 | +| learning_rate | 4.95e-05 | +| loss | -0.0328 | +| n_updates | 19776 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000156 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1388 | +| iterations | 991 | +| time_elapsed | 1462 | +| total_timesteps | 2029568 | +| train/ | | +| approx_kl | 0.007862393 | +| clip_fraction | 0.255 | +| clip_range | 0.0745 | +| entropy_loss | -7.33 | +| explained_variance | 0.304 | +| learning_rate | 4.95e-05 | +| loss | -0.0301 | +| n_updates | 19780 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000228 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1388 | +| iterations | 992 | +| time_elapsed | 1463 | +| total_timesteps | 2031616 | +| train/ | | +| approx_kl | 0.008859915 | +| clip_fraction | 0.27 | +| clip_range | 0.0745 | +| entropy_loss | -7.53 | +| explained_variance | 0.188 | +| learning_rate | 4.95e-05 | +| loss | -0.0325 | +| n_updates | 19784 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000201 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1388 | +| iterations | 993 | +| time_elapsed | 1464 | +| total_timesteps | 2033664 | +| train/ | | +| approx_kl | 0.008016518 | +| clip_fraction | 0.289 | +| clip_range | 0.0745 | +| entropy_loss | -7.43 | +| explained_variance | -0.173 | +| learning_rate | 4.95e-05 | +| loss | -0.032 | +| n_updates | 19788 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.00022 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1388 | +| iterations | 994 | +| time_elapsed | 1466 | +| total_timesteps | 2035712 | +| train/ | | +| approx_kl | 0.008822897 | +| clip_fraction | 0.311 | +| clip_range | 0.0745 | +| entropy_loss | -7.6 | +| explained_variance | 0.114 | +| learning_rate | 4.95e-05 | +| loss | -0.0371 | +| n_updates | 19792 | +| policy_gradient_loss | -0.0221 | +| value_loss | 0.000135 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1388 | +| iterations | 995 | +| time_elapsed | 1467 | +| total_timesteps | 2037760 | +| train/ | | +| approx_kl | 0.0076607396 | +| clip_fraction | 0.261 | +| clip_range | 0.0745 | +| entropy_loss | -7.34 | +| explained_variance | -0.16 | +| learning_rate | 4.95e-05 | +| loss | -0.0338 | +| n_updates | 19796 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000261 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1388 | +| iterations | 996 | +| time_elapsed | 1469 | +| total_timesteps | 2039808 | +| train/ | | +| approx_kl | 0.0072008907 | +| clip_fraction | 0.252 | +| clip_range | 0.0745 | +| entropy_loss | -7.36 | +| explained_variance | 0.103 | +| learning_rate | 4.95e-05 | +| loss | -0.0264 | +| n_updates | 19800 | +| policy_gradient_loss | -0.0134 | +| value_loss | 0.000505 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1388 | +| iterations | 997 | +| time_elapsed | 1470 | +| total_timesteps | 2041856 | +| train/ | | +| approx_kl | 0.007904366 | +| clip_fraction | 0.274 | +| clip_range | 0.0745 | +| entropy_loss | -7.2 | +| explained_variance | 0.29 | +| learning_rate | 4.95e-05 | +| loss | -0.0323 | +| n_updates | 19804 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000251 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1388 | +| iterations | 998 | +| time_elapsed | 1472 | +| total_timesteps | 2043904 | +| train/ | | +| approx_kl | 0.009063331 | +| clip_fraction | 0.304 | +| clip_range | 0.0745 | +| entropy_loss | -7.3 | +| explained_variance | 0.288 | +| learning_rate | 4.95e-05 | +| loss | -0.0326 | +| n_updates | 19808 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.00017 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1388 | +| iterations | 999 | +| time_elapsed | 1473 | +| total_timesteps | 2045952 | +| train/ | | +| approx_kl | 0.009326974 | +| clip_fraction | 0.299 | +| clip_range | 0.0745 | +| entropy_loss | -7.57 | +| explained_variance | -0.0316 | +| learning_rate | 4.95e-05 | +| loss | -0.0358 | +| n_updates | 19812 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000217 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1388 | +| iterations | 1000 | +| time_elapsed | 1474 | +| total_timesteps | 2048000 | +| train/ | | +| approx_kl | 0.008622725 | +| clip_fraction | 0.282 | +| clip_range | 0.0745 | +| entropy_loss | -7.44 | +| explained_variance | 0.129 | +| learning_rate | 4.95e-05 | +| loss | -0.0272 | +| n_updates | 19816 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000423 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1388 | +| iterations | 1001 | +| time_elapsed | 1476 | +| total_timesteps | 2050048 | +| train/ | | +| approx_kl | 0.008410124 | +| clip_fraction | 0.282 | +| clip_range | 0.0745 | +| entropy_loss | -7.41 | +| explained_variance | 0.22 | +| learning_rate | 4.95e-05 | +| loss | -0.0345 | +| n_updates | 19820 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000285 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1388 | +| iterations | 1002 | +| time_elapsed | 1477 | +| total_timesteps | 2052096 | +| train/ | | +| approx_kl | 0.00947545 | +| clip_fraction | 0.292 | +| clip_range | 0.0745 | +| entropy_loss | -7.53 | +| explained_variance | 0.0756 | +| learning_rate | 4.95e-05 | +| loss | -0.0364 | +| n_updates | 19824 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000285 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1388 | +| iterations | 1003 | +| time_elapsed | 1479 | +| total_timesteps | 2054144 | +| train/ | | +| approx_kl | 0.010562753 | +| clip_fraction | 0.301 | +| clip_range | 0.0745 | +| entropy_loss | -7.54 | +| explained_variance | -0.466 | +| learning_rate | 4.95e-05 | +| loss | -0.0344 | +| n_updates | 19828 | +| policy_gradient_loss | -0.022 | +| value_loss | 0.000163 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1388 | +| iterations | 1004 | +| time_elapsed | 1480 | +| total_timesteps | 2056192 | +| train/ | | +| approx_kl | 0.009016937 | +| clip_fraction | 0.321 | +| clip_range | 0.0745 | +| entropy_loss | -7.58 | +| explained_variance | -0.313 | +| learning_rate | 4.95e-05 | +| loss | -0.0359 | +| n_updates | 19832 | +| policy_gradient_loss | -0.0221 | +| value_loss | 0.00025 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1388 | +| iterations | 1005 | +| time_elapsed | 1482 | +| total_timesteps | 2058240 | +| train/ | | +| approx_kl | 0.008258039 | +| clip_fraction | 0.272 | +| clip_range | 0.0745 | +| entropy_loss | -7.25 | +| explained_variance | -0.0276 | +| learning_rate | 4.95e-05 | +| loss | -0.0363 | +| n_updates | 19836 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000247 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1388 | +| iterations | 1006 | +| time_elapsed | 1483 | +| total_timesteps | 2060288 | +| train/ | | +| approx_kl | 0.008902395 | +| clip_fraction | 0.289 | +| clip_range | 0.0745 | +| entropy_loss | -7.46 | +| explained_variance | 0.00253 | +| learning_rate | 4.95e-05 | +| loss | -0.0337 | +| n_updates | 19840 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000163 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1388 | +| iterations | 1007 | +| time_elapsed | 1484 | +| total_timesteps | 2062336 | +| train/ | | +| approx_kl | 0.009361107 | +| clip_fraction | 0.299 | +| clip_range | 0.0745 | +| entropy_loss | -7.39 | +| explained_variance | 0.0784 | +| learning_rate | 4.95e-05 | +| loss | -0.03 | +| n_updates | 19844 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000175 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1388 | +| iterations | 1008 | +| time_elapsed | 1486 | +| total_timesteps | 2064384 | +| train/ | | +| approx_kl | 0.009254312 | +| clip_fraction | 0.304 | +| clip_range | 0.0745 | +| entropy_loss | -7.47 | +| explained_variance | 0.202 | +| learning_rate | 4.95e-05 | +| loss | -0.0387 | +| n_updates | 19848 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000141 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1388 | +| iterations | 1009 | +| time_elapsed | 1487 | +| total_timesteps | 2066432 | +| train/ | | +| approx_kl | 0.007779327 | +| clip_fraction | 0.26 | +| clip_range | 0.0745 | +| entropy_loss | -7.2 | +| explained_variance | 0.172 | +| learning_rate | 4.95e-05 | +| loss | -0.0292 | +| n_updates | 19852 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000233 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1388 | +| iterations | 1010 | +| time_elapsed | 1489 | +| total_timesteps | 2068480 | +| train/ | | +| approx_kl | 0.010251788 | +| clip_fraction | 0.293 | +| clip_range | 0.0745 | +| entropy_loss | -7.66 | +| explained_variance | -0.0399 | +| learning_rate | 4.95e-05 | +| loss | -0.0348 | +| n_updates | 19856 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.00018 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1388 | +| iterations | 1011 | +| time_elapsed | 1490 | +| total_timesteps | 2070528 | +| train/ | | +| approx_kl | 0.008917358 | +| clip_fraction | 0.267 | +| clip_range | 0.0745 | +| entropy_loss | -7.61 | +| explained_variance | 0.0338 | +| learning_rate | 4.95e-05 | +| loss | -0.0377 | +| n_updates | 19860 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000162 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1388 | +| iterations | 1012 | +| time_elapsed | 1492 | +| total_timesteps | 2072576 | +| train/ | | +| approx_kl | 0.008558149 | +| clip_fraction | 0.286 | +| clip_range | 0.0745 | +| entropy_loss | -7.69 | +| explained_variance | -0.0364 | +| learning_rate | 4.95e-05 | +| loss | -0.0363 | +| n_updates | 19864 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000145 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1389 | +| iterations | 1013 | +| time_elapsed | 1493 | +| total_timesteps | 2074624 | +| train/ | | +| approx_kl | 0.0075895777 | +| clip_fraction | 0.252 | +| clip_range | 0.0745 | +| entropy_loss | -7.21 | +| explained_variance | 0.199 | +| learning_rate | 4.95e-05 | +| loss | -0.0275 | +| n_updates | 19868 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000389 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1389 | +| iterations | 1014 | +| time_elapsed | 1495 | +| total_timesteps | 2076672 | +| train/ | | +| approx_kl | 0.009592905 | +| clip_fraction | 0.294 | +| clip_range | 0.0745 | +| entropy_loss | -7.17 | +| explained_variance | 0.247 | +| learning_rate | 4.95e-05 | +| loss | -0.0339 | +| n_updates | 19872 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000173 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.315 | +| time/ | | +| fps | 1389 | +| iterations | 1015 | +| time_elapsed | 1496 | +| total_timesteps | 2078720 | +| train/ | | +| approx_kl | 0.009590739 | +| clip_fraction | 0.298 | +| clip_range | 0.0745 | +| entropy_loss | -7.38 | +| explained_variance | 0.246 | +| learning_rate | 4.95e-05 | +| loss | -0.0356 | +| n_updates | 19876 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000239 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1389 | +| iterations | 1016 | +| time_elapsed | 1497 | +| total_timesteps | 2080768 | +| train/ | | +| approx_kl | 0.010175568 | +| clip_fraction | 0.309 | +| clip_range | 0.0745 | +| entropy_loss | -7.47 | +| explained_variance | 0.198 | +| learning_rate | 4.95e-05 | +| loss | -0.0341 | +| n_updates | 19880 | +| policy_gradient_loss | -0.0225 | +| value_loss | 0.000175 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1389 | +| iterations | 1017 | +| time_elapsed | 1499 | +| total_timesteps | 2082816 | +| train/ | | +| approx_kl | 0.008789728 | +| clip_fraction | 0.266 | +| clip_range | 0.0745 | +| entropy_loss | -7.57 | +| explained_variance | -0.209 | +| learning_rate | 4.95e-05 | +| loss | -0.0353 | +| n_updates | 19884 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000253 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1389 | +| iterations | 1018 | +| time_elapsed | 1500 | +| total_timesteps | 2084864 | +| train/ | | +| approx_kl | 0.009850727 | +| clip_fraction | 0.302 | +| clip_range | 0.0745 | +| entropy_loss | -7.43 | +| explained_variance | 0.187 | +| learning_rate | 4.95e-05 | +| loss | -0.0368 | +| n_updates | 19888 | +| policy_gradient_loss | -0.0226 | +| value_loss | 0.000209 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1389 | +| iterations | 1019 | +| time_elapsed | 1502 | +| total_timesteps | 2086912 | +| train/ | | +| approx_kl | 0.0113832 | +| clip_fraction | 0.294 | +| clip_range | 0.0745 | +| entropy_loss | -7.68 | +| explained_variance | -0.189 | +| learning_rate | 4.95e-05 | +| loss | -0.0368 | +| n_updates | 19892 | +| policy_gradient_loss | -0.023 | +| value_loss | 0.000156 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1389 | +| iterations | 1020 | +| time_elapsed | 1503 | +| total_timesteps | 2088960 | +| train/ | | +| approx_kl | 0.009914508 | +| clip_fraction | 0.297 | +| clip_range | 0.0745 | +| entropy_loss | -7.65 | +| explained_variance | -0.158 | +| learning_rate | 4.95e-05 | +| loss | -0.0345 | +| n_updates | 19896 | +| policy_gradient_loss | -0.0227 | +| value_loss | 0.000142 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1389 | +| iterations | 1021 | +| time_elapsed | 1505 | +| total_timesteps | 2091008 | +| train/ | | +| approx_kl | 0.010915064 | +| clip_fraction | 0.292 | +| clip_range | 0.0745 | +| entropy_loss | -7.55 | +| explained_variance | -0.0413 | +| learning_rate | 4.95e-05 | +| loss | -0.0386 | +| n_updates | 19900 | +| policy_gradient_loss | -0.0218 | +| value_loss | 9.47e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1389 | +| iterations | 1022 | +| time_elapsed | 1506 | +| total_timesteps | 2093056 | +| train/ | | +| approx_kl | 0.01051921 | +| clip_fraction | 0.293 | +| clip_range | 0.0745 | +| entropy_loss | -7.28 | +| explained_variance | 0.179 | +| learning_rate | 4.95e-05 | +| loss | -0.0285 | +| n_updates | 19904 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000188 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1389 | +| iterations | 1023 | +| time_elapsed | 1508 | +| total_timesteps | 2095104 | +| train/ | | +| approx_kl | 0.008421415 | +| clip_fraction | 0.267 | +| clip_range | 0.0745 | +| entropy_loss | -7.05 | +| explained_variance | 0.292 | +| learning_rate | 4.95e-05 | +| loss | -0.0269 | +| n_updates | 19908 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000293 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1389 | +| iterations | 1024 | +| time_elapsed | 1509 | +| total_timesteps | 2097152 | +| train/ | | +| approx_kl | 0.011873403 | +| clip_fraction | 0.302 | +| clip_range | 0.0745 | +| entropy_loss | -7.46 | +| explained_variance | -0.133 | +| learning_rate | 4.95e-05 | +| loss | -0.0275 | +| n_updates | 19912 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000124 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1389 | +| iterations | 1025 | +| time_elapsed | 1510 | +| total_timesteps | 2099200 | +| train/ | | +| approx_kl | 0.010547287 | +| clip_fraction | 0.283 | +| clip_range | 0.0745 | +| entropy_loss | -7.51 | +| explained_variance | -0.115 | +| learning_rate | 4.95e-05 | +| loss | -0.0351 | +| n_updates | 19916 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000158 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1389 | +| iterations | 1026 | +| time_elapsed | 1512 | +| total_timesteps | 2101248 | +| train/ | | +| approx_kl | 0.009513308 | +| clip_fraction | 0.266 | +| clip_range | 0.0745 | +| entropy_loss | -7.37 | +| explained_variance | -0.00389 | +| learning_rate | 4.95e-05 | +| loss | -0.0309 | +| n_updates | 19920 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000634 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1389 | +| iterations | 1027 | +| time_elapsed | 1513 | +| total_timesteps | 2103296 | +| train/ | | +| approx_kl | 0.009016797 | +| clip_fraction | 0.291 | +| clip_range | 0.0745 | +| entropy_loss | -7.27 | +| explained_variance | 0.107 | +| learning_rate | 4.95e-05 | +| loss | -0.0347 | +| n_updates | 19924 | +| policy_gradient_loss | -0.0223 | +| value_loss | 0.000259 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1389 | +| iterations | 1028 | +| time_elapsed | 1515 | +| total_timesteps | 2105344 | +| train/ | | +| approx_kl | 0.0098583065 | +| clip_fraction | 0.28 | +| clip_range | 0.0745 | +| entropy_loss | -7.66 | +| explained_variance | -0.0395 | +| learning_rate | 4.95e-05 | +| loss | -0.0322 | +| n_updates | 19928 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000252 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1389 | +| iterations | 1029 | +| time_elapsed | 1516 | +| total_timesteps | 2107392 | +| train/ | | +| approx_kl | 0.008169174 | +| clip_fraction | 0.296 | +| clip_range | 0.0745 | +| entropy_loss | -7.42 | +| explained_variance | 0.174 | +| learning_rate | 4.95e-05 | +| loss | -0.0381 | +| n_updates | 19932 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000131 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1389 | +| iterations | 1030 | +| time_elapsed | 1518 | +| total_timesteps | 2109440 | +| train/ | | +| approx_kl | 0.011059359 | +| clip_fraction | 0.308 | +| clip_range | 0.0745 | +| entropy_loss | -7.38 | +| explained_variance | 0.136 | +| learning_rate | 4.95e-05 | +| loss | -0.0386 | +| n_updates | 19936 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000224 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.315 | +| time/ | | +| fps | 1389 | +| iterations | 1031 | +| time_elapsed | 1519 | +| total_timesteps | 2111488 | +| train/ | | +| approx_kl | 0.010475256 | +| clip_fraction | 0.282 | +| clip_range | 0.0745 | +| entropy_loss | -7.67 | +| explained_variance | -0.156 | +| learning_rate | 4.95e-05 | +| loss | -0.0398 | +| n_updates | 19940 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.00016 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1389 | +| iterations | 1032 | +| time_elapsed | 1521 | +| total_timesteps | 2113536 | +| train/ | | +| approx_kl | 0.00955219 | +| clip_fraction | 0.271 | +| clip_range | 0.0745 | +| entropy_loss | -7.57 | +| explained_variance | 0.0231 | +| learning_rate | 4.95e-05 | +| loss | -0.0327 | +| n_updates | 19944 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000271 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1389 | +| iterations | 1033 | +| time_elapsed | 1522 | +| total_timesteps | 2115584 | +| train/ | | +| approx_kl | 0.009258477 | +| clip_fraction | 0.275 | +| clip_range | 0.0745 | +| entropy_loss | -7.51 | +| explained_variance | 0.112 | +| learning_rate | 4.95e-05 | +| loss | -0.0308 | +| n_updates | 19948 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000219 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1389 | +| iterations | 1034 | +| time_elapsed | 1524 | +| total_timesteps | 2117632 | +| train/ | | +| approx_kl | 0.00869346 | +| clip_fraction | 0.298 | +| clip_range | 0.0745 | +| entropy_loss | -7.5 | +| explained_variance | 0.139 | +| learning_rate | 4.95e-05 | +| loss | -0.0316 | +| n_updates | 19952 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000223 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1389 | +| iterations | 1035 | +| time_elapsed | 1525 | +| total_timesteps | 2119680 | +| train/ | | +| approx_kl | 0.008525423 | +| clip_fraction | 0.272 | +| clip_range | 0.0745 | +| entropy_loss | -7.44 | +| explained_variance | 0.0492 | +| learning_rate | 4.95e-05 | +| loss | -0.0279 | +| n_updates | 19956 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.0003 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1389 | +| iterations | 1036 | +| time_elapsed | 1526 | +| total_timesteps | 2121728 | +| train/ | | +| approx_kl | 0.009099854 | +| clip_fraction | 0.296 | +| clip_range | 0.0745 | +| entropy_loss | -7.24 | +| explained_variance | 0.171 | +| learning_rate | 4.95e-05 | +| loss | -0.0319 | +| n_updates | 19960 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000143 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1389 | +| iterations | 1037 | +| time_elapsed | 1528 | +| total_timesteps | 2123776 | +| train/ | | +| approx_kl | 0.008057555 | +| clip_fraction | 0.269 | +| clip_range | 0.0745 | +| entropy_loss | -7.42 | +| explained_variance | 0.0798 | +| learning_rate | 4.95e-05 | +| loss | -0.0279 | +| n_updates | 19964 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000376 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1389 | +| iterations | 1038 | +| time_elapsed | 1529 | +| total_timesteps | 2125824 | +| train/ | | +| approx_kl | 0.009076293 | +| clip_fraction | 0.286 | +| clip_range | 0.0745 | +| entropy_loss | -7.48 | +| explained_variance | 0.244 | +| learning_rate | 4.95e-05 | +| loss | -0.0407 | +| n_updates | 19968 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000143 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1389 | +| iterations | 1039 | +| time_elapsed | 1531 | +| total_timesteps | 2127872 | +| train/ | | +| approx_kl | 0.008517982 | +| clip_fraction | 0.279 | +| clip_range | 0.0745 | +| entropy_loss | -7.37 | +| explained_variance | 0.201 | +| learning_rate | 4.95e-05 | +| loss | -0.0311 | +| n_updates | 19972 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000254 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1389 | +| iterations | 1040 | +| time_elapsed | 1532 | +| total_timesteps | 2129920 | +| train/ | | +| approx_kl | 0.008777829 | +| clip_fraction | 0.296 | +| clip_range | 0.0745 | +| entropy_loss | -7.55 | +| explained_variance | 0.224 | +| learning_rate | 4.95e-05 | +| loss | -0.0355 | +| n_updates | 19976 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000164 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1389 | +| iterations | 1041 | +| time_elapsed | 1534 | +| total_timesteps | 2131968 | +| train/ | | +| approx_kl | 0.008375506 | +| clip_fraction | 0.299 | +| clip_range | 0.0745 | +| entropy_loss | -7.61 | +| explained_variance | -0.0281 | +| learning_rate | 4.95e-05 | +| loss | -0.0335 | +| n_updates | 19980 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000163 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1389 | +| iterations | 1042 | +| time_elapsed | 1535 | +| total_timesteps | 2134016 | +| train/ | | +| approx_kl | 0.009443337 | +| clip_fraction | 0.262 | +| clip_range | 0.0745 | +| entropy_loss | -7.39 | +| explained_variance | 0.363 | +| learning_rate | 4.95e-05 | +| loss | -0.0286 | +| n_updates | 19984 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000289 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1389 | +| iterations | 1043 | +| time_elapsed | 1536 | +| total_timesteps | 2136064 | +| train/ | | +| approx_kl | 0.008418585 | +| clip_fraction | 0.264 | +| clip_range | 0.0745 | +| entropy_loss | -7.4 | +| explained_variance | 0.106 | +| learning_rate | 4.95e-05 | +| loss | -0.0274 | +| n_updates | 19988 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000246 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1389 | +| iterations | 1044 | +| time_elapsed | 1538 | +| total_timesteps | 2138112 | +| train/ | | +| approx_kl | 0.0081359465 | +| clip_fraction | 0.289 | +| clip_range | 0.0745 | +| entropy_loss | -7.45 | +| explained_variance | 0.218 | +| learning_rate | 4.95e-05 | +| loss | -0.0347 | +| n_updates | 19992 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000178 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1389 | +| iterations | 1045 | +| time_elapsed | 1539 | +| total_timesteps | 2140160 | +| train/ | | +| approx_kl | 0.0094984155 | +| clip_fraction | 0.286 | +| clip_range | 0.0745 | +| entropy_loss | -7.55 | +| explained_variance | -0.0979 | +| learning_rate | 4.95e-05 | +| loss | -0.0348 | +| n_updates | 19996 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000228 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1389 | +| iterations | 1046 | +| time_elapsed | 1541 | +| total_timesteps | 2142208 | +| train/ | | +| approx_kl | 0.009333978 | +| clip_fraction | 0.271 | +| clip_range | 0.0745 | +| entropy_loss | -7.36 | +| explained_variance | 0.432 | +| learning_rate | 4.95e-05 | +| loss | -0.0307 | +| n_updates | 20000 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000144 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1389 | +| iterations | 1047 | +| time_elapsed | 1542 | +| total_timesteps | 2144256 | +| train/ | | +| approx_kl | 0.011299821 | +| clip_fraction | 0.307 | +| clip_range | 0.0745 | +| entropy_loss | -7.37 | +| explained_variance | 0.419 | +| learning_rate | 4.95e-05 | +| loss | -0.0349 | +| n_updates | 20004 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000156 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1390 | +| iterations | 1048 | +| time_elapsed | 1544 | +| total_timesteps | 2146304 | +| train/ | | +| approx_kl | 0.008870634 | +| clip_fraction | 0.253 | +| clip_range | 0.0745 | +| entropy_loss | -7.31 | +| explained_variance | 0.117 | +| learning_rate | 4.95e-05 | +| loss | -0.0307 | +| n_updates | 20008 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000389 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1390 | +| iterations | 1049 | +| time_elapsed | 1545 | +| total_timesteps | 2148352 | +| train/ | | +| approx_kl | 0.0092234 | +| clip_fraction | 0.315 | +| clip_range | 0.0745 | +| entropy_loss | -7.48 | +| explained_variance | 0.148 | +| learning_rate | 4.95e-05 | +| loss | -0.0351 | +| n_updates | 20012 | +| policy_gradient_loss | -0.0222 | +| value_loss | 0.000142 | +--------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1390 | +| iterations | 1050 | +| time_elapsed | 1546 | +| total_timesteps | 2150400 | +| train/ | | +| approx_kl | 0.0110642575 | +| clip_fraction | 0.29 | +| clip_range | 0.0745 | +| entropy_loss | -7.7 | +| explained_variance | -0.203 | +| learning_rate | 4.95e-05 | +| loss | -0.0361 | +| n_updates | 20016 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000167 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1390 | +| iterations | 1051 | +| time_elapsed | 1548 | +| total_timesteps | 2152448 | +| train/ | | +| approx_kl | 0.007909462 | +| clip_fraction | 0.28 | +| clip_range | 0.0745 | +| entropy_loss | -7.72 | +| explained_variance | -0.173 | +| learning_rate | 4.95e-05 | +| loss | -0.0326 | +| n_updates | 20020 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000148 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1390 | +| iterations | 1052 | +| time_elapsed | 1549 | +| total_timesteps | 2154496 | +| train/ | | +| approx_kl | 0.008882281 | +| clip_fraction | 0.272 | +| clip_range | 0.0745 | +| entropy_loss | -7.2 | +| explained_variance | 0.523 | +| learning_rate | 4.95e-05 | +| loss | -0.0208 | +| n_updates | 20024 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000206 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1390 | +| iterations | 1053 | +| time_elapsed | 1551 | +| total_timesteps | 2156544 | +| train/ | | +| approx_kl | 0.007971818 | +| clip_fraction | 0.277 | +| clip_range | 0.0745 | +| entropy_loss | -7.44 | +| explained_variance | 0.112 | +| learning_rate | 4.95e-05 | +| loss | -0.0331 | +| n_updates | 20028 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000259 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1390 | +| iterations | 1054 | +| time_elapsed | 1552 | +| total_timesteps | 2158592 | +| train/ | | +| approx_kl | 0.009544723 | +| clip_fraction | 0.303 | +| clip_range | 0.0745 | +| entropy_loss | -7.48 | +| explained_variance | 0.0895 | +| learning_rate | 4.95e-05 | +| loss | -0.0351 | +| n_updates | 20032 | +| policy_gradient_loss | -0.022 | +| value_loss | 0.000142 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1390 | +| iterations | 1055 | +| time_elapsed | 1554 | +| total_timesteps | 2160640 | +| train/ | | +| approx_kl | 0.008509068 | +| clip_fraction | 0.282 | +| clip_range | 0.0745 | +| entropy_loss | -7.42 | +| explained_variance | -0.136 | +| learning_rate | 4.95e-05 | +| loss | -0.0309 | +| n_updates | 20036 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000385 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1390 | +| iterations | 1056 | +| time_elapsed | 1555 | +| total_timesteps | 2162688 | +| train/ | | +| approx_kl | 0.009550668 | +| clip_fraction | 0.3 | +| clip_range | 0.0745 | +| entropy_loss | -7.42 | +| explained_variance | 0.055 | +| learning_rate | 4.95e-05 | +| loss | -0.0361 | +| n_updates | 20040 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000193 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1390 | +| iterations | 1057 | +| time_elapsed | 1557 | +| total_timesteps | 2164736 | +| train/ | | +| approx_kl | 0.010232367 | +| clip_fraction | 0.316 | +| clip_range | 0.0745 | +| entropy_loss | -7.51 | +| explained_variance | -0.156 | +| learning_rate | 4.95e-05 | +| loss | -0.04 | +| n_updates | 20044 | +| policy_gradient_loss | -0.0228 | +| value_loss | 0.000152 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1390 | +| iterations | 1058 | +| time_elapsed | 1558 | +| total_timesteps | 2166784 | +| train/ | | +| approx_kl | 0.008608073 | +| clip_fraction | 0.299 | +| clip_range | 0.0745 | +| entropy_loss | -7.53 | +| explained_variance | 0.121 | +| learning_rate | 4.95e-05 | +| loss | -0.0336 | +| n_updates | 20048 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000144 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1390 | +| iterations | 1059 | +| time_elapsed | 1559 | +| total_timesteps | 2168832 | +| train/ | | +| approx_kl | 0.009392694 | +| clip_fraction | 0.281 | +| clip_range | 0.0745 | +| entropy_loss | -7.12 | +| explained_variance | 0.252 | +| learning_rate | 4.95e-05 | +| loss | -0.0317 | +| n_updates | 20052 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000244 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1390 | +| iterations | 1060 | +| time_elapsed | 1561 | +| total_timesteps | 2170880 | +| train/ | | +| approx_kl | 0.008283851 | +| clip_fraction | 0.286 | +| clip_range | 0.0745 | +| entropy_loss | -7.48 | +| explained_variance | 0.185 | +| learning_rate | 4.95e-05 | +| loss | -0.0282 | +| n_updates | 20056 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000219 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1390 | +| iterations | 1061 | +| time_elapsed | 1562 | +| total_timesteps | 2172928 | +| train/ | | +| approx_kl | 0.010528535 | +| clip_fraction | 0.299 | +| clip_range | 0.0745 | +| entropy_loss | -7.58 | +| explained_variance | -0.138 | +| learning_rate | 4.95e-05 | +| loss | -0.0322 | +| n_updates | 20060 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000149 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1390 | +| iterations | 1062 | +| time_elapsed | 1564 | +| total_timesteps | 2174976 | +| train/ | | +| approx_kl | 0.008643479 | +| clip_fraction | 0.276 | +| clip_range | 0.0745 | +| entropy_loss | -7.42 | +| explained_variance | 0.113 | +| learning_rate | 4.95e-05 | +| loss | -0.0294 | +| n_updates | 20064 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000238 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1390 | +| iterations | 1063 | +| time_elapsed | 1565 | +| total_timesteps | 2177024 | +| train/ | | +| approx_kl | 0.010399615 | +| clip_fraction | 0.313 | +| clip_range | 0.0745 | +| entropy_loss | -7.61 | +| explained_variance | -0.334 | +| learning_rate | 4.95e-05 | +| loss | -0.0463 | +| n_updates | 20068 | +| policy_gradient_loss | -0.0238 | +| value_loss | 6.93e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1390 | +| iterations | 1064 | +| time_elapsed | 1566 | +| total_timesteps | 2179072 | +| train/ | | +| approx_kl | 0.010368988 | +| clip_fraction | 0.301 | +| clip_range | 0.0745 | +| entropy_loss | -7.58 | +| explained_variance | -0.0141 | +| learning_rate | 4.95e-05 | +| loss | -0.0363 | +| n_updates | 20072 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000145 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1390 | +| iterations | 1065 | +| time_elapsed | 1568 | +| total_timesteps | 2181120 | +| train/ | | +| approx_kl | 0.009952429 | +| clip_fraction | 0.298 | +| clip_range | 0.0745 | +| entropy_loss | -7.43 | +| explained_variance | 0.225 | +| learning_rate | 4.95e-05 | +| loss | -0.0326 | +| n_updates | 20076 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.00011 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1390 | +| iterations | 1066 | +| time_elapsed | 1569 | +| total_timesteps | 2183168 | +| train/ | | +| approx_kl | 0.009644106 | +| clip_fraction | 0.294 | +| clip_range | 0.0745 | +| entropy_loss | -7.35 | +| explained_variance | 0.282 | +| learning_rate | 4.95e-05 | +| loss | -0.0352 | +| n_updates | 20080 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000119 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1390 | +| iterations | 1067 | +| time_elapsed | 1571 | +| total_timesteps | 2185216 | +| train/ | | +| approx_kl | 0.009046419 | +| clip_fraction | 0.277 | +| clip_range | 0.0745 | +| entropy_loss | -7.26 | +| explained_variance | 0.0487 | +| learning_rate | 4.95e-05 | +| loss | -0.0293 | +| n_updates | 20084 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000242 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1390 | +| iterations | 1068 | +| time_elapsed | 1572 | +| total_timesteps | 2187264 | +| train/ | | +| approx_kl | 0.009512128 | +| clip_fraction | 0.315 | +| clip_range | 0.0745 | +| entropy_loss | -7.53 | +| explained_variance | 0.188 | +| learning_rate | 4.95e-05 | +| loss | -0.0316 | +| n_updates | 20088 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000108 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1390 | +| iterations | 1069 | +| time_elapsed | 1574 | +| total_timesteps | 2189312 | +| train/ | | +| approx_kl | 0.010569186 | +| clip_fraction | 0.311 | +| clip_range | 0.0745 | +| entropy_loss | -7.59 | +| explained_variance | 0.193 | +| learning_rate | 4.95e-05 | +| loss | -0.0352 | +| n_updates | 20092 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000144 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1390 | +| iterations | 1070 | +| time_elapsed | 1575 | +| total_timesteps | 2191360 | +| train/ | | +| approx_kl | 0.010043053 | +| clip_fraction | 0.291 | +| clip_range | 0.0745 | +| entropy_loss | -7.62 | +| explained_variance | -0.0502 | +| learning_rate | 4.95e-05 | +| loss | -0.0335 | +| n_updates | 20096 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1390 | +| iterations | 1071 | +| time_elapsed | 1576 | +| total_timesteps | 2193408 | +| train/ | | +| approx_kl | 0.010757059 | +| clip_fraction | 0.305 | +| clip_range | 0.0745 | +| entropy_loss | -7.5 | +| explained_variance | -0.42 | +| learning_rate | 4.95e-05 | +| loss | -0.0304 | +| n_updates | 20100 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000133 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1390 | +| iterations | 1072 | +| time_elapsed | 1578 | +| total_timesteps | 2195456 | +| train/ | | +| approx_kl | 0.009372863 | +| clip_fraction | 0.285 | +| clip_range | 0.0745 | +| entropy_loss | -7.13 | +| explained_variance | 0.185 | +| learning_rate | 4.95e-05 | +| loss | -0.033 | +| n_updates | 20104 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000199 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1391 | +| iterations | 1073 | +| time_elapsed | 1579 | +| total_timesteps | 2197504 | +| train/ | | +| approx_kl | 0.009604549 | +| clip_fraction | 0.306 | +| clip_range | 0.0745 | +| entropy_loss | -7.69 | +| explained_variance | -0.0419 | +| learning_rate | 4.95e-05 | +| loss | -0.0347 | +| n_updates | 20108 | +| policy_gradient_loss | -0.022 | +| value_loss | 0.000101 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1391 | +| iterations | 1074 | +| time_elapsed | 1581 | +| total_timesteps | 2199552 | +| train/ | | +| approx_kl | 0.008312396 | +| clip_fraction | 0.259 | +| clip_range | 0.0745 | +| entropy_loss | -7.08 | +| explained_variance | 0.143 | +| learning_rate | 4.95e-05 | +| loss | -0.022 | +| n_updates | 20112 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000239 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1391 | +| iterations | 1075 | +| time_elapsed | 1582 | +| total_timesteps | 2201600 | +| train/ | | +| approx_kl | 0.008894701 | +| clip_fraction | 0.277 | +| clip_range | 0.0745 | +| entropy_loss | -7.04 | +| explained_variance | 0.419 | +| learning_rate | 4.95e-05 | +| loss | -0.0289 | +| n_updates | 20116 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000276 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1391 | +| iterations | 1076 | +| time_elapsed | 1584 | +| total_timesteps | 2203648 | +| train/ | | +| approx_kl | 0.011266459 | +| clip_fraction | 0.304 | +| clip_range | 0.0744 | +| entropy_loss | -7.56 | +| explained_variance | -0.0375 | +| learning_rate | 4.95e-05 | +| loss | -0.0358 | +| n_updates | 20120 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000194 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1391 | +| iterations | 1077 | +| time_elapsed | 1585 | +| total_timesteps | 2205696 | +| train/ | | +| approx_kl | 0.009808631 | +| clip_fraction | 0.309 | +| clip_range | 0.0744 | +| entropy_loss | -7.62 | +| explained_variance | -0.14 | +| learning_rate | 4.95e-05 | +| loss | -0.0336 | +| n_updates | 20124 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000165 | +----------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1391 | +| iterations | 1078 | +| time_elapsed | 1586 | +| total_timesteps | 2207744 | +| train/ | | +| approx_kl | 0.008427 | +| clip_fraction | 0.283 | +| clip_range | 0.0744 | +| entropy_loss | -7.52 | +| explained_variance | -0.206 | +| learning_rate | 4.95e-05 | +| loss | -0.0323 | +| n_updates | 20128 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000191 | +-------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1391 | +| iterations | 1079 | +| time_elapsed | 1588 | +| total_timesteps | 2209792 | +| train/ | | +| approx_kl | 0.009911178 | +| clip_fraction | 0.339 | +| clip_range | 0.0744 | +| entropy_loss | -7.52 | +| explained_variance | -0.133 | +| learning_rate | 4.95e-05 | +| loss | -0.0381 | +| n_updates | 20132 | +| policy_gradient_loss | -0.0234 | +| value_loss | 0.000101 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1391 | +| iterations | 1080 | +| time_elapsed | 1589 | +| total_timesteps | 2211840 | +| train/ | | +| approx_kl | 0.00959309 | +| clip_fraction | 0.285 | +| clip_range | 0.0744 | +| entropy_loss | -7.3 | +| explained_variance | 0.329 | +| learning_rate | 4.95e-05 | +| loss | -0.0317 | +| n_updates | 20136 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000157 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1391 | +| iterations | 1081 | +| time_elapsed | 1591 | +| total_timesteps | 2213888 | +| train/ | | +| approx_kl | 0.009051455 | +| clip_fraction | 0.28 | +| clip_range | 0.0744 | +| entropy_loss | -7.43 | +| explained_variance | -0.0712 | +| learning_rate | 4.95e-05 | +| loss | -0.0354 | +| n_updates | 20140 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000251 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1391 | +| iterations | 1082 | +| time_elapsed | 1592 | +| total_timesteps | 2215936 | +| train/ | | +| approx_kl | 0.008977397 | +| clip_fraction | 0.296 | +| clip_range | 0.0744 | +| entropy_loss | -7.25 | +| explained_variance | 0.368 | +| learning_rate | 4.95e-05 | +| loss | -0.0361 | +| n_updates | 20144 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000156 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1391 | +| iterations | 1083 | +| time_elapsed | 1594 | +| total_timesteps | 2217984 | +| train/ | | +| approx_kl | 0.009932588 | +| clip_fraction | 0.295 | +| clip_range | 0.0744 | +| entropy_loss | -7.38 | +| explained_variance | -0.0468 | +| learning_rate | 4.95e-05 | +| loss | -0.0297 | +| n_updates | 20148 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000275 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1391 | +| iterations | 1084 | +| time_elapsed | 1595 | +| total_timesteps | 2220032 | +| train/ | | +| approx_kl | 0.010762623 | +| clip_fraction | 0.304 | +| clip_range | 0.0744 | +| entropy_loss | -7.26 | +| explained_variance | 0.164 | +| learning_rate | 4.95e-05 | +| loss | -0.0382 | +| n_updates | 20152 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000185 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1391 | +| iterations | 1085 | +| time_elapsed | 1597 | +| total_timesteps | 2222080 | +| train/ | | +| approx_kl | 0.009315156 | +| clip_fraction | 0.275 | +| clip_range | 0.0744 | +| entropy_loss | -7.31 | +| explained_variance | -0.114 | +| learning_rate | 4.95e-05 | +| loss | -0.0317 | +| n_updates | 20156 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000233 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1391 | +| iterations | 1086 | +| time_elapsed | 1598 | +| total_timesteps | 2224128 | +| train/ | | +| approx_kl | 0.009779884 | +| clip_fraction | 0.321 | +| clip_range | 0.0744 | +| entropy_loss | -7.28 | +| explained_variance | 0.25 | +| learning_rate | 4.95e-05 | +| loss | -0.0361 | +| n_updates | 20160 | +| policy_gradient_loss | -0.0225 | +| value_loss | 0.000155 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1391 | +| iterations | 1087 | +| time_elapsed | 1600 | +| total_timesteps | 2226176 | +| train/ | | +| approx_kl | 0.009673184 | +| clip_fraction | 0.311 | +| clip_range | 0.0744 | +| entropy_loss | -7.5 | +| explained_variance | -0.248 | +| learning_rate | 4.95e-05 | +| loss | -0.0409 | +| n_updates | 20164 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000172 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1391 | +| iterations | 1088 | +| time_elapsed | 1601 | +| total_timesteps | 2228224 | +| train/ | | +| approx_kl | 0.010449605 | +| clip_fraction | 0.303 | +| clip_range | 0.0744 | +| entropy_loss | -7.58 | +| explained_variance | -0.124 | +| learning_rate | 4.95e-05 | +| loss | -0.0299 | +| n_updates | 20168 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000163 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1391 | +| iterations | 1089 | +| time_elapsed | 1602 | +| total_timesteps | 2230272 | +| train/ | | +| approx_kl | 0.010171672 | +| clip_fraction | 0.269 | +| clip_range | 0.0744 | +| entropy_loss | -7.2 | +| explained_variance | 0.176 | +| learning_rate | 4.95e-05 | +| loss | -0.0286 | +| n_updates | 20172 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000291 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1391 | +| iterations | 1090 | +| time_elapsed | 1604 | +| total_timesteps | 2232320 | +| train/ | | +| approx_kl | 0.010423053 | +| clip_fraction | 0.316 | +| clip_range | 0.0744 | +| entropy_loss | -7.39 | +| explained_variance | 0.238 | +| learning_rate | 4.95e-05 | +| loss | -0.035 | +| n_updates | 20176 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000156 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1391 | +| iterations | 1091 | +| time_elapsed | 1605 | +| total_timesteps | 2234368 | +| train/ | | +| approx_kl | 0.010893745 | +| clip_fraction | 0.297 | +| clip_range | 0.0744 | +| entropy_loss | -7.51 | +| explained_variance | -0.112 | +| learning_rate | 4.95e-05 | +| loss | -0.0275 | +| n_updates | 20180 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.00024 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1391 | +| iterations | 1092 | +| time_elapsed | 1607 | +| total_timesteps | 2236416 | +| train/ | | +| approx_kl | 0.009546208 | +| clip_fraction | 0.293 | +| clip_range | 0.0744 | +| entropy_loss | -7.42 | +| explained_variance | 0.377 | +| learning_rate | 4.95e-05 | +| loss | -0.0303 | +| n_updates | 20184 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000161 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1391 | +| iterations | 1093 | +| time_elapsed | 1608 | +| total_timesteps | 2238464 | +| train/ | | +| approx_kl | 0.009771547 | +| clip_fraction | 0.314 | +| clip_range | 0.0744 | +| entropy_loss | -7.6 | +| explained_variance | -0.06 | +| learning_rate | 4.95e-05 | +| loss | -0.0367 | +| n_updates | 20188 | +| policy_gradient_loss | -0.022 | +| value_loss | 0.000206 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1391 | +| iterations | 1094 | +| time_elapsed | 1610 | +| total_timesteps | 2240512 | +| train/ | | +| approx_kl | 0.010467822 | +| clip_fraction | 0.318 | +| clip_range | 0.0744 | +| entropy_loss | -7.28 | +| explained_variance | 0.449 | +| learning_rate | 4.95e-05 | +| loss | -0.0369 | +| n_updates | 20192 | +| policy_gradient_loss | -0.0227 | +| value_loss | 9.93e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1391 | +| iterations | 1095 | +| time_elapsed | 1611 | +| total_timesteps | 2242560 | +| train/ | | +| approx_kl | 0.008889116 | +| clip_fraction | 0.279 | +| clip_range | 0.0744 | +| entropy_loss | -7.16 | +| explained_variance | 0.554 | +| learning_rate | 4.95e-05 | +| loss | -0.0299 | +| n_updates | 20196 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.00017 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1391 | +| iterations | 1096 | +| time_elapsed | 1612 | +| total_timesteps | 2244608 | +| train/ | | +| approx_kl | 0.010955026 | +| clip_fraction | 0.278 | +| clip_range | 0.0744 | +| entropy_loss | -7.51 | +| explained_variance | -0.0962 | +| learning_rate | 4.95e-05 | +| loss | -0.0293 | +| n_updates | 20200 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000186 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1391 | +| iterations | 1097 | +| time_elapsed | 1614 | +| total_timesteps | 2246656 | +| train/ | | +| approx_kl | 0.008604506 | +| clip_fraction | 0.275 | +| clip_range | 0.0744 | +| entropy_loss | -7.47 | +| explained_variance | -0.0668 | +| learning_rate | 4.95e-05 | +| loss | -0.0331 | +| n_updates | 20204 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000302 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1391 | +| iterations | 1098 | +| time_elapsed | 1615 | +| total_timesteps | 2248704 | +| train/ | | +| approx_kl | 0.009292811 | +| clip_fraction | 0.281 | +| clip_range | 0.0744 | +| entropy_loss | -7.41 | +| explained_variance | -0.0565 | +| learning_rate | 4.95e-05 | +| loss | -0.03 | +| n_updates | 20208 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000289 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1391 | +| iterations | 1099 | +| time_elapsed | 1617 | +| total_timesteps | 2250752 | +| train/ | | +| approx_kl | 0.010745376 | +| clip_fraction | 0.321 | +| clip_range | 0.0744 | +| entropy_loss | -7.62 | +| explained_variance | -0.206 | +| learning_rate | 4.95e-05 | +| loss | -0.0409 | +| n_updates | 20212 | +| policy_gradient_loss | -0.0238 | +| value_loss | 0.000143 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1391 | +| iterations | 1100 | +| time_elapsed | 1618 | +| total_timesteps | 2252800 | +| train/ | | +| approx_kl | 0.011556145 | +| clip_fraction | 0.325 | +| clip_range | 0.0744 | +| entropy_loss | -7.35 | +| explained_variance | 0.0869 | +| learning_rate | 4.95e-05 | +| loss | -0.0368 | +| n_updates | 20216 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000142 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1391 | +| iterations | 1101 | +| time_elapsed | 1620 | +| total_timesteps | 2254848 | +| train/ | | +| approx_kl | 0.010617003 | +| clip_fraction | 0.318 | +| clip_range | 0.0744 | +| entropy_loss | -7.38 | +| explained_variance | 0.196 | +| learning_rate | 4.95e-05 | +| loss | -0.0338 | +| n_updates | 20220 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000153 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1391 | +| iterations | 1102 | +| time_elapsed | 1621 | +| total_timesteps | 2256896 | +| train/ | | +| approx_kl | 0.009564256 | +| clip_fraction | 0.286 | +| clip_range | 0.0744 | +| entropy_loss | -7 | +| explained_variance | 0.609 | +| learning_rate | 4.95e-05 | +| loss | -0.0342 | +| n_updates | 20224 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000141 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1391 | +| iterations | 1103 | +| time_elapsed | 1622 | +| total_timesteps | 2258944 | +| train/ | | +| approx_kl | 0.010661291 | +| clip_fraction | 0.323 | +| clip_range | 0.0744 | +| entropy_loss | -7.46 | +| explained_variance | 0.309 | +| learning_rate | 4.95e-05 | +| loss | -0.0321 | +| n_updates | 20228 | +| policy_gradient_loss | -0.022 | +| value_loss | 0.000123 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1391 | +| iterations | 1104 | +| time_elapsed | 1624 | +| total_timesteps | 2260992 | +| train/ | | +| approx_kl | 0.011065973 | +| clip_fraction | 0.306 | +| clip_range | 0.0744 | +| entropy_loss | -7.38 | +| explained_variance | 0.0551 | +| learning_rate | 4.95e-05 | +| loss | -0.0317 | +| n_updates | 20232 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000177 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1391 | +| iterations | 1105 | +| time_elapsed | 1625 | +| total_timesteps | 2263040 | +| train/ | | +| approx_kl | 0.00978624 | +| clip_fraction | 0.303 | +| clip_range | 0.0744 | +| entropy_loss | -7.2 | +| explained_variance | 0.334 | +| learning_rate | 4.95e-05 | +| loss | -0.0313 | +| n_updates | 20236 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000208 | +---------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1392 | +| iterations | 1106 | +| time_elapsed | 1627 | +| total_timesteps | 2265088 | +| train/ | | +| approx_kl | 0.0109364 | +| clip_fraction | 0.315 | +| clip_range | 0.0744 | +| entropy_loss | -7.55 | +| explained_variance | -0.0924 | +| learning_rate | 4.95e-05 | +| loss | -0.0383 | +| n_updates | 20240 | +| policy_gradient_loss | -0.0226 | +| value_loss | 0.00011 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1392 | +| iterations | 1107 | +| time_elapsed | 1628 | +| total_timesteps | 2267136 | +| train/ | | +| approx_kl | 0.010777341 | +| clip_fraction | 0.285 | +| clip_range | 0.0744 | +| entropy_loss | -7.42 | +| explained_variance | 0.115 | +| learning_rate | 4.95e-05 | +| loss | -0.0319 | +| n_updates | 20244 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000231 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1392 | +| iterations | 1108 | +| time_elapsed | 1630 | +| total_timesteps | 2269184 | +| train/ | | +| approx_kl | 0.00912708 | +| clip_fraction | 0.299 | +| clip_range | 0.0744 | +| entropy_loss | -7.15 | +| explained_variance | 0.412 | +| learning_rate | 4.95e-05 | +| loss | -0.0325 | +| n_updates | 20248 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000188 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1392 | +| iterations | 1109 | +| time_elapsed | 1631 | +| total_timesteps | 2271232 | +| train/ | | +| approx_kl | 0.011178311 | +| clip_fraction | 0.353 | +| clip_range | 0.0744 | +| entropy_loss | -7.44 | +| explained_variance | 0.418 | +| learning_rate | 4.95e-05 | +| loss | -0.0375 | +| n_updates | 20252 | +| policy_gradient_loss | -0.0249 | +| value_loss | 7.2e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1392 | +| iterations | 1110 | +| time_elapsed | 1632 | +| total_timesteps | 2273280 | +| train/ | | +| approx_kl | 0.00916158 | +| clip_fraction | 0.286 | +| clip_range | 0.0744 | +| entropy_loss | -7.53 | +| explained_variance | -0.0246 | +| learning_rate | 4.95e-05 | +| loss | -0.0304 | +| n_updates | 20256 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000202 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.315 | +| time/ | | +| fps | 1392 | +| iterations | 1111 | +| time_elapsed | 1634 | +| total_timesteps | 2275328 | +| train/ | | +| approx_kl | 0.011241307 | +| clip_fraction | 0.335 | +| clip_range | 0.0744 | +| entropy_loss | -7.25 | +| explained_variance | 0.684 | +| learning_rate | 4.95e-05 | +| loss | -0.0399 | +| n_updates | 20260 | +| policy_gradient_loss | -0.0232 | +| value_loss | 9.72e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1392 | +| iterations | 1112 | +| time_elapsed | 1635 | +| total_timesteps | 2277376 | +| train/ | | +| approx_kl | 0.010449253 | +| clip_fraction | 0.322 | +| clip_range | 0.0744 | +| entropy_loss | -7.41 | +| explained_variance | 0.366 | +| learning_rate | 4.95e-05 | +| loss | -0.0311 | +| n_updates | 20264 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1392 | +| iterations | 1113 | +| time_elapsed | 1637 | +| total_timesteps | 2279424 | +| train/ | | +| approx_kl | 0.010727998 | +| clip_fraction | 0.317 | +| clip_range | 0.0744 | +| entropy_loss | -7.27 | +| explained_variance | 0.163 | +| learning_rate | 4.95e-05 | +| loss | -0.0308 | +| n_updates | 20268 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000233 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1392 | +| iterations | 1114 | +| time_elapsed | 1638 | +| total_timesteps | 2281472 | +| train/ | | +| approx_kl | 0.010796702 | +| clip_fraction | 0.306 | +| clip_range | 0.0744 | +| entropy_loss | -7.4 | +| explained_variance | 0.0317 | +| learning_rate | 4.95e-05 | +| loss | -0.0296 | +| n_updates | 20272 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000156 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.315 | +| time/ | | +| fps | 1392 | +| iterations | 1115 | +| time_elapsed | 1639 | +| total_timesteps | 2283520 | +| train/ | | +| approx_kl | 0.010202067 | +| clip_fraction | 0.28 | +| clip_range | 0.0744 | +| entropy_loss | -7.36 | +| explained_variance | 0.192 | +| learning_rate | 4.95e-05 | +| loss | -0.0302 | +| n_updates | 20276 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.00017 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.315 | +| time/ | | +| fps | 1392 | +| iterations | 1116 | +| time_elapsed | 1641 | +| total_timesteps | 2285568 | +| train/ | | +| approx_kl | 0.010633238 | +| clip_fraction | 0.3 | +| clip_range | 0.0744 | +| entropy_loss | -7.15 | +| explained_variance | 0.318 | +| learning_rate | 4.95e-05 | +| loss | -0.0316 | +| n_updates | 20280 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000187 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1392 | +| iterations | 1117 | +| time_elapsed | 1642 | +| total_timesteps | 2287616 | +| train/ | | +| approx_kl | 0.011430953 | +| clip_fraction | 0.312 | +| clip_range | 0.0744 | +| entropy_loss | -7.57 | +| explained_variance | -0.104 | +| learning_rate | 4.95e-05 | +| loss | -0.032 | +| n_updates | 20284 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000174 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1392 | +| iterations | 1118 | +| time_elapsed | 1644 | +| total_timesteps | 2289664 | +| train/ | | +| approx_kl | 0.012699328 | +| clip_fraction | 0.33 | +| clip_range | 0.0744 | +| entropy_loss | -7.41 | +| explained_variance | 0.241 | +| learning_rate | 4.95e-05 | +| loss | -0.0394 | +| n_updates | 20288 | +| policy_gradient_loss | -0.0233 | +| value_loss | 0.000128 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 1392 | +| iterations | 1119 | +| time_elapsed | 1645 | +| total_timesteps | 2291712 | +| train/ | | +| approx_kl | 0.011483047 | +| clip_fraction | 0.344 | +| clip_range | 0.0744 | +| entropy_loss | -7.37 | +| explained_variance | -0.208 | +| learning_rate | 4.95e-05 | +| loss | -0.0413 | +| n_updates | 20292 | +| policy_gradient_loss | -0.0255 | +| value_loss | 5.49e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.302 | +| time/ | | +| fps | 1392 | +| iterations | 1120 | +| time_elapsed | 1647 | +| total_timesteps | 2293760 | +| train/ | | +| approx_kl | 0.009920023 | +| clip_fraction | 0.303 | +| clip_range | 0.0744 | +| entropy_loss | -7.17 | +| explained_variance | 0.252 | +| learning_rate | 4.95e-05 | +| loss | -0.0345 | +| n_updates | 20296 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000155 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.302 | +| time/ | | +| fps | 1392 | +| iterations | 1121 | +| time_elapsed | 1648 | +| total_timesteps | 2295808 | +| train/ | | +| approx_kl | 0.009086553 | +| clip_fraction | 0.281 | +| clip_range | 0.0744 | +| entropy_loss | -7.06 | +| explained_variance | 0.231 | +| learning_rate | 4.95e-05 | +| loss | -0.0312 | +| n_updates | 20300 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000198 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 1392 | +| iterations | 1122 | +| time_elapsed | 1650 | +| total_timesteps | 2297856 | +| train/ | | +| approx_kl | 0.011427736 | +| clip_fraction | 0.314 | +| clip_range | 0.0744 | +| entropy_loss | -7.44 | +| explained_variance | 0.0334 | +| learning_rate | 4.95e-05 | +| loss | -0.0379 | +| n_updates | 20304 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000164 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 1392 | +| iterations | 1123 | +| time_elapsed | 1651 | +| total_timesteps | 2299904 | +| train/ | | +| approx_kl | 0.009620606 | +| clip_fraction | 0.29 | +| clip_range | 0.0744 | +| entropy_loss | -7.34 | +| explained_variance | 0.172 | +| learning_rate | 4.95e-05 | +| loss | -0.0343 | +| n_updates | 20308 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.00027 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.302 | +| time/ | | +| fps | 1392 | +| iterations | 1124 | +| time_elapsed | 1653 | +| total_timesteps | 2301952 | +| train/ | | +| approx_kl | 0.010937671 | +| clip_fraction | 0.312 | +| clip_range | 0.0744 | +| entropy_loss | -7.44 | +| explained_variance | -0.156 | +| learning_rate | 4.95e-05 | +| loss | -0.0333 | +| n_updates | 20312 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000142 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.302 | +| time/ | | +| fps | 1392 | +| iterations | 1125 | +| time_elapsed | 1654 | +| total_timesteps | 2304000 | +| train/ | | +| approx_kl | 0.009803078 | +| clip_fraction | 0.313 | +| clip_range | 0.0744 | +| entropy_loss | -7.34 | +| explained_variance | 0.398 | +| learning_rate | 4.95e-05 | +| loss | -0.0345 | +| n_updates | 20316 | +| policy_gradient_loss | -0.0238 | +| value_loss | 5.71e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.302 | +| time/ | | +| fps | 1392 | +| iterations | 1126 | +| time_elapsed | 1655 | +| total_timesteps | 2306048 | +| train/ | | +| approx_kl | 0.010667395 | +| clip_fraction | 0.325 | +| clip_range | 0.0744 | +| entropy_loss | -7.21 | +| explained_variance | 0.531 | +| learning_rate | 4.95e-05 | +| loss | -0.0338 | +| n_updates | 20320 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000126 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 1392 | +| iterations | 1127 | +| time_elapsed | 1657 | +| total_timesteps | 2308096 | +| train/ | | +| approx_kl | 0.011363841 | +| clip_fraction | 0.302 | +| clip_range | 0.0744 | +| entropy_loss | -7.56 | +| explained_variance | -0.105 | +| learning_rate | 4.95e-05 | +| loss | -0.0302 | +| n_updates | 20324 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000131 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 1392 | +| iterations | 1128 | +| time_elapsed | 1658 | +| total_timesteps | 2310144 | +| train/ | | +| approx_kl | 0.011230657 | +| clip_fraction | 0.307 | +| clip_range | 0.0744 | +| entropy_loss | -7.38 | +| explained_variance | 0.299 | +| learning_rate | 4.95e-05 | +| loss | -0.0332 | +| n_updates | 20328 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.00013 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 1392 | +| iterations | 1129 | +| time_elapsed | 1660 | +| total_timesteps | 2312192 | +| train/ | | +| approx_kl | 0.009435641 | +| clip_fraction | 0.295 | +| clip_range | 0.0744 | +| entropy_loss | -7.4 | +| explained_variance | 0.294 | +| learning_rate | 4.95e-05 | +| loss | -0.0289 | +| n_updates | 20332 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000139 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 1392 | +| iterations | 1130 | +| time_elapsed | 1661 | +| total_timesteps | 2314240 | +| train/ | | +| approx_kl | 0.010279131 | +| clip_fraction | 0.294 | +| clip_range | 0.0744 | +| entropy_loss | -7.48 | +| explained_variance | 0.243 | +| learning_rate | 4.95e-05 | +| loss | -0.0341 | +| n_updates | 20336 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000146 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1392 | +| iterations | 1131 | +| time_elapsed | 1663 | +| total_timesteps | 2316288 | +| train/ | | +| approx_kl | 0.010073792 | +| clip_fraction | 0.312 | +| clip_range | 0.0744 | +| entropy_loss | -7.52 | +| explained_variance | -0.0761 | +| learning_rate | 4.95e-05 | +| loss | -0.0312 | +| n_updates | 20340 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000163 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1392 | +| iterations | 1132 | +| time_elapsed | 1664 | +| total_timesteps | 2318336 | +| train/ | | +| approx_kl | 0.009986004 | +| clip_fraction | 0.299 | +| clip_range | 0.0744 | +| entropy_loss | -7.41 | +| explained_variance | 0.152 | +| learning_rate | 4.94e-05 | +| loss | -0.031 | +| n_updates | 20344 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000216 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1392 | +| iterations | 1133 | +| time_elapsed | 1665 | +| total_timesteps | 2320384 | +| train/ | | +| approx_kl | 0.009575546 | +| clip_fraction | 0.295 | +| clip_range | 0.0744 | +| entropy_loss | -7.26 | +| explained_variance | -0.145 | +| learning_rate | 4.94e-05 | +| loss | -0.0305 | +| n_updates | 20348 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000192 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1392 | +| iterations | 1134 | +| time_elapsed | 1667 | +| total_timesteps | 2322432 | +| train/ | | +| approx_kl | 0.009257359 | +| clip_fraction | 0.277 | +| clip_range | 0.0744 | +| entropy_loss | -6.83 | +| explained_variance | 0.212 | +| learning_rate | 4.94e-05 | +| loss | -0.0268 | +| n_updates | 20352 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000496 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.315 | +| time/ | | +| fps | 1392 | +| iterations | 1135 | +| time_elapsed | 1668 | +| total_timesteps | 2324480 | +| train/ | | +| approx_kl | 0.010234021 | +| clip_fraction | 0.34 | +| clip_range | 0.0744 | +| entropy_loss | -7.16 | +| explained_variance | 0.449 | +| learning_rate | 4.94e-05 | +| loss | -0.0388 | +| n_updates | 20356 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000161 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.315 | +| time/ | | +| fps | 1392 | +| iterations | 1136 | +| time_elapsed | 1670 | +| total_timesteps | 2326528 | +| train/ | | +| approx_kl | 0.0105412565 | +| clip_fraction | 0.352 | +| clip_range | 0.0744 | +| entropy_loss | -7.39 | +| explained_variance | 0.347 | +| learning_rate | 4.94e-05 | +| loss | -0.0406 | +| n_updates | 20360 | +| policy_gradient_loss | -0.0257 | +| value_loss | 8.29e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1392 | +| iterations | 1137 | +| time_elapsed | 1671 | +| total_timesteps | 2328576 | +| train/ | | +| approx_kl | 0.012083213 | +| clip_fraction | 0.33 | +| clip_range | 0.0744 | +| entropy_loss | -7.55 | +| explained_variance | -0.183 | +| learning_rate | 4.94e-05 | +| loss | -0.0376 | +| n_updates | 20364 | +| policy_gradient_loss | -0.0245 | +| value_loss | 7.55e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1392 | +| iterations | 1138 | +| time_elapsed | 1673 | +| total_timesteps | 2330624 | +| train/ | | +| approx_kl | 0.009502954 | +| clip_fraction | 0.317 | +| clip_range | 0.0744 | +| entropy_loss | -7.31 | +| explained_variance | -0.0937 | +| learning_rate | 4.94e-05 | +| loss | -0.0336 | +| n_updates | 20368 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000184 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1392 | +| iterations | 1139 | +| time_elapsed | 1674 | +| total_timesteps | 2332672 | +| train/ | | +| approx_kl | 0.010364588 | +| clip_fraction | 0.298 | +| clip_range | 0.0744 | +| entropy_loss | -7.45 | +| explained_variance | 0.302 | +| learning_rate | 4.94e-05 | +| loss | -0.0345 | +| n_updates | 20372 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000109 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1393 | +| iterations | 1140 | +| time_elapsed | 1676 | +| total_timesteps | 2334720 | +| train/ | | +| approx_kl | 0.012079864 | +| clip_fraction | 0.336 | +| clip_range | 0.0744 | +| entropy_loss | -7.4 | +| explained_variance | 0.353 | +| learning_rate | 4.94e-05 | +| loss | -0.0365 | +| n_updates | 20376 | +| policy_gradient_loss | -0.0222 | +| value_loss | 0.000113 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1393 | +| iterations | 1141 | +| time_elapsed | 1677 | +| total_timesteps | 2336768 | +| train/ | | +| approx_kl | 0.00876654 | +| clip_fraction | 0.273 | +| clip_range | 0.0744 | +| entropy_loss | -7.12 | +| explained_variance | 0.417 | +| learning_rate | 4.94e-05 | +| loss | -0.0236 | +| n_updates | 20380 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000189 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1393 | +| iterations | 1142 | +| time_elapsed | 1678 | +| total_timesteps | 2338816 | +| train/ | | +| approx_kl | 0.011021418 | +| clip_fraction | 0.32 | +| clip_range | 0.0744 | +| entropy_loss | -7.43 | +| explained_variance | -0.0866 | +| learning_rate | 4.94e-05 | +| loss | -0.0401 | +| n_updates | 20384 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000136 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1393 | +| iterations | 1143 | +| time_elapsed | 1680 | +| total_timesteps | 2340864 | +| train/ | | +| approx_kl | 0.009702671 | +| clip_fraction | 0.302 | +| clip_range | 0.0744 | +| entropy_loss | -7.47 | +| explained_variance | 0.3 | +| learning_rate | 4.94e-05 | +| loss | -0.0331 | +| n_updates | 20388 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.00014 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1393 | +| iterations | 1144 | +| time_elapsed | 1681 | +| total_timesteps | 2342912 | +| train/ | | +| approx_kl | 0.009038619 | +| clip_fraction | 0.284 | +| clip_range | 0.0744 | +| entropy_loss | -7.45 | +| explained_variance | -0.0966 | +| learning_rate | 4.94e-05 | +| loss | -0.0286 | +| n_updates | 20392 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000189 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1393 | +| iterations | 1145 | +| time_elapsed | 1683 | +| total_timesteps | 2344960 | +| train/ | | +| approx_kl | 0.008201711 | +| clip_fraction | 0.279 | +| clip_range | 0.0744 | +| entropy_loss | -7.09 | +| explained_variance | 0.23 | +| learning_rate | 4.94e-05 | +| loss | -0.0297 | +| n_updates | 20396 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000351 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1393 | +| iterations | 1146 | +| time_elapsed | 1684 | +| total_timesteps | 2347008 | +| train/ | | +| approx_kl | 0.01003455 | +| clip_fraction | 0.299 | +| clip_range | 0.0744 | +| entropy_loss | -7.13 | +| explained_variance | 0.503 | +| learning_rate | 4.94e-05 | +| loss | -0.0313 | +| n_updates | 20400 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000196 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1393 | +| iterations | 1147 | +| time_elapsed | 1686 | +| total_timesteps | 2349056 | +| train/ | | +| approx_kl | 0.010674406 | +| clip_fraction | 0.294 | +| clip_range | 0.0744 | +| entropy_loss | -7.28 | +| explained_variance | 0.18 | +| learning_rate | 4.94e-05 | +| loss | -0.0337 | +| n_updates | 20404 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000157 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1393 | +| iterations | 1148 | +| time_elapsed | 1687 | +| total_timesteps | 2351104 | +| train/ | | +| approx_kl | 0.013264822 | +| clip_fraction | 0.325 | +| clip_range | 0.0744 | +| entropy_loss | -7.37 | +| explained_variance | 0.268 | +| learning_rate | 4.94e-05 | +| loss | -0.0416 | +| n_updates | 20408 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000116 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1393 | +| iterations | 1149 | +| time_elapsed | 1688 | +| total_timesteps | 2353152 | +| train/ | | +| approx_kl | 0.009882224 | +| clip_fraction | 0.292 | +| clip_range | 0.0744 | +| entropy_loss | -7.28 | +| explained_variance | 0.308 | +| learning_rate | 4.94e-05 | +| loss | -0.033 | +| n_updates | 20412 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000173 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1393 | +| iterations | 1150 | +| time_elapsed | 1690 | +| total_timesteps | 2355200 | +| train/ | | +| approx_kl | 0.010162944 | +| clip_fraction | 0.295 | +| clip_range | 0.0744 | +| entropy_loss | -7.22 | +| explained_variance | 0.334 | +| learning_rate | 4.94e-05 | +| loss | -0.0323 | +| n_updates | 20416 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000266 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1393 | +| iterations | 1151 | +| time_elapsed | 1691 | +| total_timesteps | 2357248 | +| train/ | | +| approx_kl | 0.009738352 | +| clip_fraction | 0.298 | +| clip_range | 0.0744 | +| entropy_loss | -7.49 | +| explained_variance | -0.179 | +| learning_rate | 4.94e-05 | +| loss | -0.0329 | +| n_updates | 20420 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1393 | +| iterations | 1152 | +| time_elapsed | 1693 | +| total_timesteps | 2359296 | +| train/ | | +| approx_kl | 0.008188466 | +| clip_fraction | 0.278 | +| clip_range | 0.0744 | +| entropy_loss | -7.25 | +| explained_variance | 0.0363 | +| learning_rate | 4.94e-05 | +| loss | -0.0294 | +| n_updates | 20424 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000261 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1393 | +| iterations | 1153 | +| time_elapsed | 1694 | +| total_timesteps | 2361344 | +| train/ | | +| approx_kl | 0.009408269 | +| clip_fraction | 0.29 | +| clip_range | 0.0744 | +| entropy_loss | -7.5 | +| explained_variance | -0.0943 | +| learning_rate | 4.94e-05 | +| loss | -0.0324 | +| n_updates | 20428 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000155 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1393 | +| iterations | 1154 | +| time_elapsed | 1696 | +| total_timesteps | 2363392 | +| train/ | | +| approx_kl | 0.008577095 | +| clip_fraction | 0.285 | +| clip_range | 0.0744 | +| entropy_loss | -7.26 | +| explained_variance | 0.254 | +| learning_rate | 4.94e-05 | +| loss | -0.0236 | +| n_updates | 20432 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000211 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1393 | +| iterations | 1155 | +| time_elapsed | 1697 | +| total_timesteps | 2365440 | +| train/ | | +| approx_kl | 0.010849425 | +| clip_fraction | 0.329 | +| clip_range | 0.0744 | +| entropy_loss | -7.25 | +| explained_variance | 0.274 | +| learning_rate | 4.94e-05 | +| loss | -0.0279 | +| n_updates | 20436 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000145 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1393 | +| iterations | 1156 | +| time_elapsed | 1699 | +| total_timesteps | 2367488 | +| train/ | | +| approx_kl | 0.010002276 | +| clip_fraction | 0.301 | +| clip_range | 0.0744 | +| entropy_loss | -7.46 | +| explained_variance | -0.0229 | +| learning_rate | 4.94e-05 | +| loss | -0.0326 | +| n_updates | 20440 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000117 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1393 | +| iterations | 1157 | +| time_elapsed | 1700 | +| total_timesteps | 2369536 | +| train/ | | +| approx_kl | 0.009264814 | +| clip_fraction | 0.308 | +| clip_range | 0.0744 | +| entropy_loss | -7.3 | +| explained_variance | 0.466 | +| learning_rate | 4.94e-05 | +| loss | -0.0338 | +| n_updates | 20444 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000132 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1393 | +| iterations | 1158 | +| time_elapsed | 1701 | +| total_timesteps | 2371584 | +| train/ | | +| approx_kl | 0.009018434 | +| clip_fraction | 0.29 | +| clip_range | 0.0744 | +| entropy_loss | -7.56 | +| explained_variance | -0.045 | +| learning_rate | 4.94e-05 | +| loss | -0.0307 | +| n_updates | 20448 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000285 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1393 | +| iterations | 1159 | +| time_elapsed | 1703 | +| total_timesteps | 2373632 | +| train/ | | +| approx_kl | 0.008093579 | +| clip_fraction | 0.276 | +| clip_range | 0.0744 | +| entropy_loss | -7.37 | +| explained_variance | 0.149 | +| learning_rate | 4.94e-05 | +| loss | -0.0295 | +| n_updates | 20452 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000354 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1393 | +| iterations | 1160 | +| time_elapsed | 1704 | +| total_timesteps | 2375680 | +| train/ | | +| approx_kl | 0.0109034255 | +| clip_fraction | 0.319 | +| clip_range | 0.0744 | +| entropy_loss | -6.96 | +| explained_variance | 0.452 | +| learning_rate | 4.94e-05 | +| loss | -0.0278 | +| n_updates | 20456 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000312 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1393 | +| iterations | 1161 | +| time_elapsed | 1706 | +| total_timesteps | 2377728 | +| train/ | | +| approx_kl | 0.011203778 | +| clip_fraction | 0.333 | +| clip_range | 0.0744 | +| entropy_loss | -6.95 | +| explained_variance | 0.709 | +| learning_rate | 4.94e-05 | +| loss | -0.0377 | +| n_updates | 20460 | +| policy_gradient_loss | -0.0235 | +| value_loss | 0.00012 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1393 | +| iterations | 1162 | +| time_elapsed | 1707 | +| total_timesteps | 2379776 | +| train/ | | +| approx_kl | 0.010065606 | +| clip_fraction | 0.289 | +| clip_range | 0.0744 | +| entropy_loss | -7.53 | +| explained_variance | -0.116 | +| learning_rate | 4.94e-05 | +| loss | -0.0336 | +| n_updates | 20464 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000193 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1393 | +| iterations | 1163 | +| time_elapsed | 1709 | +| total_timesteps | 2381824 | +| train/ | | +| approx_kl | 0.00861367 | +| clip_fraction | 0.289 | +| clip_range | 0.0744 | +| entropy_loss | -7.44 | +| explained_variance | 0.194 | +| learning_rate | 4.94e-05 | +| loss | -0.0283 | +| n_updates | 20468 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000222 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1393 | +| iterations | 1164 | +| time_elapsed | 1710 | +| total_timesteps | 2383872 | +| train/ | | +| approx_kl | 0.010681474 | +| clip_fraction | 0.315 | +| clip_range | 0.0744 | +| entropy_loss | -7.2 | +| explained_variance | 0.0752 | +| learning_rate | 4.94e-05 | +| loss | -0.0372 | +| n_updates | 20472 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000124 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1393 | +| iterations | 1165 | +| time_elapsed | 1712 | +| total_timesteps | 2385920 | +| train/ | | +| approx_kl | 0.009437999 | +| clip_fraction | 0.308 | +| clip_range | 0.0744 | +| entropy_loss | -7.34 | +| explained_variance | 0.359 | +| learning_rate | 4.94e-05 | +| loss | -0.0377 | +| n_updates | 20476 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000162 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1393 | +| iterations | 1166 | +| time_elapsed | 1713 | +| total_timesteps | 2387968 | +| train/ | | +| approx_kl | 0.0096804015 | +| clip_fraction | 0.3 | +| clip_range | 0.0744 | +| entropy_loss | -7.28 | +| explained_variance | 0.297 | +| learning_rate | 4.94e-05 | +| loss | -0.0334 | +| n_updates | 20480 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000128 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1393 | +| iterations | 1167 | +| time_elapsed | 1715 | +| total_timesteps | 2390016 | +| train/ | | +| approx_kl | 0.009309266 | +| clip_fraction | 0.281 | +| clip_range | 0.0744 | +| entropy_loss | -7.32 | +| explained_variance | 0.286 | +| learning_rate | 4.94e-05 | +| loss | -0.0267 | +| n_updates | 20484 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000223 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1393 | +| iterations | 1168 | +| time_elapsed | 1716 | +| total_timesteps | 2392064 | +| train/ | | +| approx_kl | 0.011515148 | +| clip_fraction | 0.364 | +| clip_range | 0.0744 | +| entropy_loss | -7.55 | +| explained_variance | 0.402 | +| learning_rate | 4.94e-05 | +| loss | -0.0469 | +| n_updates | 20488 | +| policy_gradient_loss | -0.0295 | +| value_loss | 3.88e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1393 | +| iterations | 1169 | +| time_elapsed | 1718 | +| total_timesteps | 2394112 | +| train/ | | +| approx_kl | 0.00995858 | +| clip_fraction | 0.294 | +| clip_range | 0.0744 | +| entropy_loss | -7.41 | +| explained_variance | 0.229 | +| learning_rate | 4.94e-05 | +| loss | -0.0337 | +| n_updates | 20492 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000236 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1393 | +| iterations | 1170 | +| time_elapsed | 1719 | +| total_timesteps | 2396160 | +| train/ | | +| approx_kl | 0.008467174 | +| clip_fraction | 0.258 | +| clip_range | 0.0744 | +| entropy_loss | -7.17 | +| explained_variance | 0.154 | +| learning_rate | 4.94e-05 | +| loss | -0.0273 | +| n_updates | 20496 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000278 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1393 | +| iterations | 1171 | +| time_elapsed | 1720 | +| total_timesteps | 2398208 | +| train/ | | +| approx_kl | 0.01006451 | +| clip_fraction | 0.312 | +| clip_range | 0.0744 | +| entropy_loss | -7.44 | +| explained_variance | 0.185 | +| learning_rate | 4.94e-05 | +| loss | -0.0388 | +| n_updates | 20500 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.00019 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1393 | +| iterations | 1172 | +| time_elapsed | 1722 | +| total_timesteps | 2400256 | +| train/ | | +| approx_kl | 0.011581917 | +| clip_fraction | 0.311 | +| clip_range | 0.0744 | +| entropy_loss | -7.37 | +| explained_variance | 0.224 | +| learning_rate | 4.94e-05 | +| loss | -0.0362 | +| n_updates | 20504 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000177 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1393 | +| iterations | 1173 | +| time_elapsed | 1723 | +| total_timesteps | 2402304 | +| train/ | | +| approx_kl | 0.009799978 | +| clip_fraction | 0.292 | +| clip_range | 0.0744 | +| entropy_loss | -7.52 | +| explained_variance | -0.106 | +| learning_rate | 4.94e-05 | +| loss | -0.0296 | +| n_updates | 20508 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000212 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1393 | +| iterations | 1174 | +| time_elapsed | 1725 | +| total_timesteps | 2404352 | +| train/ | | +| approx_kl | 0.010267942 | +| clip_fraction | 0.309 | +| clip_range | 0.0744 | +| entropy_loss | -7.59 | +| explained_variance | -0.164 | +| learning_rate | 4.94e-05 | +| loss | -0.0337 | +| n_updates | 20512 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000123 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1393 | +| iterations | 1175 | +| time_elapsed | 1726 | +| total_timesteps | 2406400 | +| train/ | | +| approx_kl | 0.009402749 | +| clip_fraction | 0.294 | +| clip_range | 0.0744 | +| entropy_loss | -7.43 | +| explained_variance | -0.0701 | +| learning_rate | 4.94e-05 | +| loss | -0.0199 | +| n_updates | 20516 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.00024 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1393 | +| iterations | 1176 | +| time_elapsed | 1728 | +| total_timesteps | 2408448 | +| train/ | | +| approx_kl | 0.009760065 | +| clip_fraction | 0.296 | +| clip_range | 0.0744 | +| entropy_loss | -6.89 | +| explained_variance | 0.285 | +| learning_rate | 4.94e-05 | +| loss | -0.0313 | +| n_updates | 20520 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000238 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1393 | +| iterations | 1177 | +| time_elapsed | 1729 | +| total_timesteps | 2410496 | +| train/ | | +| approx_kl | 0.01041075 | +| clip_fraction | 0.325 | +| clip_range | 0.0744 | +| entropy_loss | -7.38 | +| explained_variance | 0.201 | +| learning_rate | 4.94e-05 | +| loss | -0.0376 | +| n_updates | 20524 | +| policy_gradient_loss | -0.0237 | +| value_loss | 0.000149 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1393 | +| iterations | 1178 | +| time_elapsed | 1730 | +| total_timesteps | 2412544 | +| train/ | | +| approx_kl | 0.010001434 | +| clip_fraction | 0.294 | +| clip_range | 0.0744 | +| entropy_loss | -7.26 | +| explained_variance | 0.16 | +| learning_rate | 4.94e-05 | +| loss | -0.0312 | +| n_updates | 20528 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000217 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1393 | +| iterations | 1179 | +| time_elapsed | 1732 | +| total_timesteps | 2414592 | +| train/ | | +| approx_kl | 0.00952792 | +| clip_fraction | 0.287 | +| clip_range | 0.0744 | +| entropy_loss | -7.25 | +| explained_variance | 0.203 | +| learning_rate | 4.94e-05 | +| loss | -0.0339 | +| n_updates | 20532 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000201 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1393 | +| iterations | 1180 | +| time_elapsed | 1733 | +| total_timesteps | 2416640 | +| train/ | | +| approx_kl | 0.010077213 | +| clip_fraction | 0.286 | +| clip_range | 0.0744 | +| entropy_loss | -7.43 | +| explained_variance | 0.126 | +| learning_rate | 4.94e-05 | +| loss | -0.0271 | +| n_updates | 20536 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.00023 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1393 | +| iterations | 1181 | +| time_elapsed | 1735 | +| total_timesteps | 2418688 | +| train/ | | +| approx_kl | 0.0093114935 | +| clip_fraction | 0.288 | +| clip_range | 0.0744 | +| entropy_loss | -7.32 | +| explained_variance | 0.0578 | +| learning_rate | 4.94e-05 | +| loss | -0.0312 | +| n_updates | 20540 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000229 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1393 | +| iterations | 1182 | +| time_elapsed | 1736 | +| total_timesteps | 2420736 | +| train/ | | +| approx_kl | 0.009868774 | +| clip_fraction | 0.313 | +| clip_range | 0.0744 | +| entropy_loss | -7.58 | +| explained_variance | -0.0916 | +| learning_rate | 4.94e-05 | +| loss | -0.0352 | +| n_updates | 20544 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000196 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1393 | +| iterations | 1183 | +| time_elapsed | 1738 | +| total_timesteps | 2422784 | +| train/ | | +| approx_kl | 0.009171389 | +| clip_fraction | 0.291 | +| clip_range | 0.0744 | +| entropy_loss | -7.38 | +| explained_variance | 0.00768 | +| learning_rate | 4.94e-05 | +| loss | -0.032 | +| n_updates | 20548 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000205 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1393 | +| iterations | 1184 | +| time_elapsed | 1739 | +| total_timesteps | 2424832 | +| train/ | | +| approx_kl | 0.0094477255 | +| clip_fraction | 0.307 | +| clip_range | 0.0744 | +| entropy_loss | -7.46 | +| explained_variance | 0.418 | +| learning_rate | 4.94e-05 | +| loss | -0.028 | +| n_updates | 20552 | +| policy_gradient_loss | -0.0212 | +| value_loss | 9.88e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1393 | +| iterations | 1185 | +| time_elapsed | 1740 | +| total_timesteps | 2426880 | +| train/ | | +| approx_kl | 0.011750199 | +| clip_fraction | 0.314 | +| clip_range | 0.0744 | +| entropy_loss | -7.36 | +| explained_variance | 0.165 | +| learning_rate | 4.94e-05 | +| loss | -0.0323 | +| n_updates | 20556 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000144 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1394 | +| iterations | 1186 | +| time_elapsed | 1742 | +| total_timesteps | 2428928 | +| train/ | | +| approx_kl | 0.011629418 | +| clip_fraction | 0.334 | +| clip_range | 0.0744 | +| entropy_loss | -7.4 | +| explained_variance | -0.122 | +| learning_rate | 4.94e-05 | +| loss | -0.035 | +| n_updates | 20560 | +| policy_gradient_loss | -0.0222 | +| value_loss | 0.000142 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1394 | +| iterations | 1187 | +| time_elapsed | 1743 | +| total_timesteps | 2430976 | +| train/ | | +| approx_kl | 0.009860213 | +| clip_fraction | 0.313 | +| clip_range | 0.0744 | +| entropy_loss | -7.25 | +| explained_variance | 0.0146 | +| learning_rate | 4.94e-05 | +| loss | -0.0297 | +| n_updates | 20564 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000195 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1394 | +| iterations | 1188 | +| time_elapsed | 1745 | +| total_timesteps | 2433024 | +| train/ | | +| approx_kl | 0.009805203 | +| clip_fraction | 0.305 | +| clip_range | 0.0744 | +| entropy_loss | -7.19 | +| explained_variance | 0.596 | +| learning_rate | 4.94e-05 | +| loss | -0.0372 | +| n_updates | 20568 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1394 | +| iterations | 1189 | +| time_elapsed | 1746 | +| total_timesteps | 2435072 | +| train/ | | +| approx_kl | 0.010047872 | +| clip_fraction | 0.283 | +| clip_range | 0.0744 | +| entropy_loss | -7.2 | +| explained_variance | 0.222 | +| learning_rate | 4.94e-05 | +| loss | -0.0318 | +| n_updates | 20572 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000188 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1394 | +| iterations | 1190 | +| time_elapsed | 1748 | +| total_timesteps | 2437120 | +| train/ | | +| approx_kl | 0.00988792 | +| clip_fraction | 0.277 | +| clip_range | 0.0744 | +| entropy_loss | -7.12 | +| explained_variance | 0.494 | +| learning_rate | 4.94e-05 | +| loss | -0.0256 | +| n_updates | 20576 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000208 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1394 | +| iterations | 1191 | +| time_elapsed | 1749 | +| total_timesteps | 2439168 | +| train/ | | +| approx_kl | 0.0112430975 | +| clip_fraction | 0.327 | +| clip_range | 0.0744 | +| entropy_loss | -7.38 | +| explained_variance | 0.407 | +| learning_rate | 4.94e-05 | +| loss | -0.036 | +| n_updates | 20580 | +| policy_gradient_loss | -0.0232 | +| value_loss | 0.000107 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1394 | +| iterations | 1192 | +| time_elapsed | 1750 | +| total_timesteps | 2441216 | +| train/ | | +| approx_kl | 0.0120462645 | +| clip_fraction | 0.325 | +| clip_range | 0.0744 | +| entropy_loss | -7.38 | +| explained_variance | -0.0961 | +| learning_rate | 4.94e-05 | +| loss | -0.0381 | +| n_updates | 20584 | +| policy_gradient_loss | -0.0243 | +| value_loss | 0.000103 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1394 | +| iterations | 1193 | +| time_elapsed | 1752 | +| total_timesteps | 2443264 | +| train/ | | +| approx_kl | 0.01063671 | +| clip_fraction | 0.292 | +| clip_range | 0.0744 | +| entropy_loss | -7.48 | +| explained_variance | -0.156 | +| learning_rate | 4.94e-05 | +| loss | -0.0318 | +| n_updates | 20588 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000162 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1394 | +| iterations | 1194 | +| time_elapsed | 1753 | +| total_timesteps | 2445312 | +| train/ | | +| approx_kl | 0.010107625 | +| clip_fraction | 0.305 | +| clip_range | 0.0744 | +| entropy_loss | -7.4 | +| explained_variance | -0.184 | +| learning_rate | 4.94e-05 | +| loss | -0.0347 | +| n_updates | 20592 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000155 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1394 | +| iterations | 1195 | +| time_elapsed | 1755 | +| total_timesteps | 2447360 | +| train/ | | +| approx_kl | 0.0083031915 | +| clip_fraction | 0.276 | +| clip_range | 0.0744 | +| entropy_loss | -7.24 | +| explained_variance | 0.188 | +| learning_rate | 4.94e-05 | +| loss | -0.0303 | +| n_updates | 20596 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000316 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1394 | +| iterations | 1196 | +| time_elapsed | 1756 | +| total_timesteps | 2449408 | +| train/ | | +| approx_kl | 0.008199642 | +| clip_fraction | 0.262 | +| clip_range | 0.0744 | +| entropy_loss | -6.9 | +| explained_variance | 0.248 | +| learning_rate | 4.94e-05 | +| loss | -0.0317 | +| n_updates | 20600 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000273 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1394 | +| iterations | 1197 | +| time_elapsed | 1758 | +| total_timesteps | 2451456 | +| train/ | | +| approx_kl | 0.01132922 | +| clip_fraction | 0.334 | +| clip_range | 0.0744 | +| entropy_loss | -7.15 | +| explained_variance | 0.449 | +| learning_rate | 4.94e-05 | +| loss | -0.0365 | +| n_updates | 20604 | +| policy_gradient_loss | -0.0229 | +| value_loss | 0.000121 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1394 | +| iterations | 1198 | +| time_elapsed | 1759 | +| total_timesteps | 2453504 | +| train/ | | +| approx_kl | 0.011307268 | +| clip_fraction | 0.329 | +| clip_range | 0.0744 | +| entropy_loss | -7.4 | +| explained_variance | 0.287 | +| learning_rate | 4.94e-05 | +| loss | -0.0326 | +| n_updates | 20608 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000146 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1394 | +| iterations | 1199 | +| time_elapsed | 1761 | +| total_timesteps | 2455552 | +| train/ | | +| approx_kl | 0.010487009 | +| clip_fraction | 0.279 | +| clip_range | 0.0744 | +| entropy_loss | -7.47 | +| explained_variance | -0.0974 | +| learning_rate | 4.94e-05 | +| loss | -0.0326 | +| n_updates | 20612 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000235 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1394 | +| iterations | 1200 | +| time_elapsed | 1762 | +| total_timesteps | 2457600 | +| train/ | | +| approx_kl | 0.010660866 | +| clip_fraction | 0.307 | +| clip_range | 0.0744 | +| entropy_loss | -7.28 | +| explained_variance | 0.231 | +| learning_rate | 4.94e-05 | +| loss | -0.0322 | +| n_updates | 20616 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000299 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1394 | +| iterations | 1201 | +| time_elapsed | 1763 | +| total_timesteps | 2459648 | +| train/ | | +| approx_kl | 0.009202439 | +| clip_fraction | 0.281 | +| clip_range | 0.0744 | +| entropy_loss | -7.48 | +| explained_variance | -0.0976 | +| learning_rate | 4.94e-05 | +| loss | -0.0348 | +| n_updates | 20620 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000227 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1394 | +| iterations | 1202 | +| time_elapsed | 1765 | +| total_timesteps | 2461696 | +| train/ | | +| approx_kl | 0.010243429 | +| clip_fraction | 0.321 | +| clip_range | 0.0744 | +| entropy_loss | -7.47 | +| explained_variance | -0.0224 | +| learning_rate | 4.94e-05 | +| loss | -0.0345 | +| n_updates | 20624 | +| policy_gradient_loss | -0.022 | +| value_loss | 0.000141 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1394 | +| iterations | 1203 | +| time_elapsed | 1766 | +| total_timesteps | 2463744 | +| train/ | | +| approx_kl | 0.010580712 | +| clip_fraction | 0.314 | +| clip_range | 0.0744 | +| entropy_loss | -7.43 | +| explained_variance | -0.237 | +| learning_rate | 4.94e-05 | +| loss | -0.0311 | +| n_updates | 20628 | +| policy_gradient_loss | -0.0222 | +| value_loss | 0.000129 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1394 | +| iterations | 1204 | +| time_elapsed | 1768 | +| total_timesteps | 2465792 | +| train/ | | +| approx_kl | 0.009363869 | +| clip_fraction | 0.289 | +| clip_range | 0.0744 | +| entropy_loss | -7.05 | +| explained_variance | 0.182 | +| learning_rate | 4.94e-05 | +| loss | -0.0317 | +| n_updates | 20632 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000388 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1394 | +| iterations | 1205 | +| time_elapsed | 1769 | +| total_timesteps | 2467840 | +| train/ | | +| approx_kl | 0.013053738 | +| clip_fraction | 0.344 | +| clip_range | 0.0744 | +| entropy_loss | -7.23 | +| explained_variance | 0.582 | +| learning_rate | 4.94e-05 | +| loss | -0.039 | +| n_updates | 20636 | +| policy_gradient_loss | -0.0242 | +| value_loss | 9.65e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1394 | +| iterations | 1206 | +| time_elapsed | 1771 | +| total_timesteps | 2469888 | +| train/ | | +| approx_kl | 0.009788584 | +| clip_fraction | 0.313 | +| clip_range | 0.0744 | +| entropy_loss | -7.4 | +| explained_variance | 0.316 | +| learning_rate | 4.94e-05 | +| loss | -0.0311 | +| n_updates | 20640 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000189 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1394 | +| iterations | 1207 | +| time_elapsed | 1772 | +| total_timesteps | 2471936 | +| train/ | | +| approx_kl | 0.009495189 | +| clip_fraction | 0.303 | +| clip_range | 0.0744 | +| entropy_loss | -7.53 | +| explained_variance | -0.183 | +| learning_rate | 4.94e-05 | +| loss | -0.0302 | +| n_updates | 20644 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000121 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1394 | +| iterations | 1208 | +| time_elapsed | 1773 | +| total_timesteps | 2473984 | +| train/ | | +| approx_kl | 0.008665718 | +| clip_fraction | 0.314 | +| clip_range | 0.0744 | +| entropy_loss | -7.27 | +| explained_variance | 0.319 | +| learning_rate | 4.94e-05 | +| loss | -0.0314 | +| n_updates | 20648 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000122 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1394 | +| iterations | 1209 | +| time_elapsed | 1775 | +| total_timesteps | 2476032 | +| train/ | | +| approx_kl | 0.010049089 | +| clip_fraction | 0.283 | +| clip_range | 0.0744 | +| entropy_loss | -7.31 | +| explained_variance | 0.278 | +| learning_rate | 4.94e-05 | +| loss | -0.0322 | +| n_updates | 20652 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000228 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1394 | +| iterations | 1210 | +| time_elapsed | 1776 | +| total_timesteps | 2478080 | +| train/ | | +| approx_kl | 0.008775223 | +| clip_fraction | 0.286 | +| clip_range | 0.0744 | +| entropy_loss | -7.54 | +| explained_variance | -0.0591 | +| learning_rate | 4.94e-05 | +| loss | -0.0315 | +| n_updates | 20656 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000219 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1394 | +| iterations | 1211 | +| time_elapsed | 1778 | +| total_timesteps | 2480128 | +| train/ | | +| approx_kl | 0.009884293 | +| clip_fraction | 0.307 | +| clip_range | 0.0744 | +| entropy_loss | -7.1 | +| explained_variance | 0.586 | +| learning_rate | 4.94e-05 | +| loss | -0.0362 | +| n_updates | 20660 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000156 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1394 | +| iterations | 1212 | +| time_elapsed | 1779 | +| total_timesteps | 2482176 | +| train/ | | +| approx_kl | 0.008743288 | +| clip_fraction | 0.275 | +| clip_range | 0.0744 | +| entropy_loss | -7.26 | +| explained_variance | -0.283 | +| learning_rate | 4.94e-05 | +| loss | -0.0287 | +| n_updates | 20664 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000253 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1394 | +| iterations | 1213 | +| time_elapsed | 1781 | +| total_timesteps | 2484224 | +| train/ | | +| approx_kl | 0.010103359 | +| clip_fraction | 0.304 | +| clip_range | 0.0744 | +| entropy_loss | -7.53 | +| explained_variance | -0.0783 | +| learning_rate | 4.94e-05 | +| loss | -0.0376 | +| n_updates | 20668 | +| policy_gradient_loss | -0.0222 | +| value_loss | 0.000152 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1394 | +| iterations | 1214 | +| time_elapsed | 1782 | +| total_timesteps | 2486272 | +| train/ | | +| approx_kl | 0.008269832 | +| clip_fraction | 0.27 | +| clip_range | 0.0744 | +| entropy_loss | -7.16 | +| explained_variance | 0.0627 | +| learning_rate | 4.94e-05 | +| loss | -0.0351 | +| n_updates | 20672 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000416 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1394 | +| iterations | 1215 | +| time_elapsed | 1783 | +| total_timesteps | 2488320 | +| train/ | | +| approx_kl | 0.009354053 | +| clip_fraction | 0.32 | +| clip_range | 0.0744 | +| entropy_loss | -7.34 | +| explained_variance | 0.243 | +| learning_rate | 4.94e-05 | +| loss | -0.0393 | +| n_updates | 20676 | +| policy_gradient_loss | -0.0226 | +| value_loss | 0.000242 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1394 | +| iterations | 1216 | +| time_elapsed | 1785 | +| total_timesteps | 2490368 | +| train/ | | +| approx_kl | 0.0105282385 | +| clip_fraction | 0.318 | +| clip_range | 0.0744 | +| entropy_loss | -7.21 | +| explained_variance | -0.198 | +| learning_rate | 4.94e-05 | +| loss | -0.0379 | +| n_updates | 20680 | +| policy_gradient_loss | -0.0233 | +| value_loss | 0.000121 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1394 | +| iterations | 1217 | +| time_elapsed | 1786 | +| total_timesteps | 2492416 | +| train/ | | +| approx_kl | 0.009048756 | +| clip_fraction | 0.294 | +| clip_range | 0.0744 | +| entropy_loss | -6.83 | +| explained_variance | 0.449 | +| learning_rate | 4.94e-05 | +| loss | -0.0321 | +| n_updates | 20684 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000229 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1395 | +| iterations | 1218 | +| time_elapsed | 1788 | +| total_timesteps | 2494464 | +| train/ | | +| approx_kl | 0.012018009 | +| clip_fraction | 0.346 | +| clip_range | 0.0744 | +| entropy_loss | -7.1 | +| explained_variance | 0.254 | +| learning_rate | 4.94e-05 | +| loss | -0.0308 | +| n_updates | 20688 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000339 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1394 | +| iterations | 1219 | +| time_elapsed | 1789 | +| total_timesteps | 2496512 | +| train/ | | +| approx_kl | 0.010611409 | +| clip_fraction | 0.335 | +| clip_range | 0.0744 | +| entropy_loss | -7.17 | +| explained_variance | 0.508 | +| learning_rate | 4.94e-05 | +| loss | -0.0412 | +| n_updates | 20692 | +| policy_gradient_loss | -0.0222 | +| value_loss | 0.000136 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1394 | +| iterations | 1220 | +| time_elapsed | 1791 | +| total_timesteps | 2498560 | +| train/ | | +| approx_kl | 0.012210722 | +| clip_fraction | 0.323 | +| clip_range | 0.0744 | +| entropy_loss | -7.39 | +| explained_variance | -0.0841 | +| learning_rate | 4.94e-05 | +| loss | -0.0339 | +| n_updates | 20696 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1394 | +| iterations | 1221 | +| time_elapsed | 1792 | +| total_timesteps | 2500608 | +| train/ | | +| approx_kl | 0.009293022 | +| clip_fraction | 0.304 | +| clip_range | 0.0744 | +| entropy_loss | -7.37 | +| explained_variance | 0.152 | +| learning_rate | 4.94e-05 | +| loss | -0.03 | +| n_updates | 20700 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000239 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1394 | +| iterations | 1222 | +| time_elapsed | 1794 | +| total_timesteps | 2502656 | +| train/ | | +| approx_kl | 0.011643529 | +| clip_fraction | 0.319 | +| clip_range | 0.0744 | +| entropy_loss | -7.52 | +| explained_variance | -0.168 | +| learning_rate | 4.94e-05 | +| loss | -0.0375 | +| n_updates | 20704 | +| policy_gradient_loss | -0.0219 | +| value_loss | 0.000172 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1395 | +| iterations | 1223 | +| time_elapsed | 1795 | +| total_timesteps | 2504704 | +| train/ | | +| approx_kl | 0.0104152635 | +| clip_fraction | 0.295 | +| clip_range | 0.0744 | +| entropy_loss | -7.24 | +| explained_variance | 0.424 | +| learning_rate | 4.94e-05 | +| loss | -0.0337 | +| n_updates | 20708 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000231 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1395 | +| iterations | 1224 | +| time_elapsed | 1796 | +| total_timesteps | 2506752 | +| train/ | | +| approx_kl | 0.010770852 | +| clip_fraction | 0.319 | +| clip_range | 0.0744 | +| entropy_loss | -7.53 | +| explained_variance | -0.19 | +| learning_rate | 4.94e-05 | +| loss | -0.042 | +| n_updates | 20712 | +| policy_gradient_loss | -0.0231 | +| value_loss | 0.00011 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1395 | +| iterations | 1225 | +| time_elapsed | 1798 | +| total_timesteps | 2508800 | +| train/ | | +| approx_kl | 0.011463372 | +| clip_fraction | 0.305 | +| clip_range | 0.0744 | +| entropy_loss | -7.54 | +| explained_variance | -0.0777 | +| learning_rate | 4.94e-05 | +| loss | -0.032 | +| n_updates | 20716 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000149 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1395 | +| iterations | 1226 | +| time_elapsed | 1799 | +| total_timesteps | 2510848 | +| train/ | | +| approx_kl | 0.0086341845 | +| clip_fraction | 0.276 | +| clip_range | 0.0744 | +| entropy_loss | -7.39 | +| explained_variance | 0.0209 | +| learning_rate | 4.94e-05 | +| loss | -0.0338 | +| n_updates | 20720 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000364 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1395 | +| iterations | 1227 | +| time_elapsed | 1801 | +| total_timesteps | 2512896 | +| train/ | | +| approx_kl | 0.011990681 | +| clip_fraction | 0.319 | +| clip_range | 0.0744 | +| entropy_loss | -7.09 | +| explained_variance | 0.321 | +| learning_rate | 4.94e-05 | +| loss | -0.0274 | +| n_updates | 20724 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000156 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1395 | +| iterations | 1228 | +| time_elapsed | 1802 | +| total_timesteps | 2514944 | +| train/ | | +| approx_kl | 0.010008985 | +| clip_fraction | 0.307 | +| clip_range | 0.0744 | +| entropy_loss | -7.44 | +| explained_variance | -0.104 | +| learning_rate | 4.94e-05 | +| loss | -0.0359 | +| n_updates | 20728 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000153 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1395 | +| iterations | 1229 | +| time_elapsed | 1804 | +| total_timesteps | 2516992 | +| train/ | | +| approx_kl | 0.009365921 | +| clip_fraction | 0.289 | +| clip_range | 0.0744 | +| entropy_loss | -6.86 | +| explained_variance | 0.427 | +| learning_rate | 4.94e-05 | +| loss | -0.0358 | +| n_updates | 20732 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000153 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1395 | +| iterations | 1230 | +| time_elapsed | 1805 | +| total_timesteps | 2519040 | +| train/ | | +| approx_kl | 0.011567241 | +| clip_fraction | 0.321 | +| clip_range | 0.0744 | +| entropy_loss | -7.26 | +| explained_variance | -0.0409 | +| learning_rate | 4.94e-05 | +| loss | -0.0339 | +| n_updates | 20736 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.00013 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1395 | +| iterations | 1231 | +| time_elapsed | 1806 | +| total_timesteps | 2521088 | +| train/ | | +| approx_kl | 0.01087546 | +| clip_fraction | 0.294 | +| clip_range | 0.0744 | +| entropy_loss | -7.4 | +| explained_variance | 0.149 | +| learning_rate | 4.94e-05 | +| loss | -0.0256 | +| n_updates | 20740 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000242 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1395 | +| iterations | 1232 | +| time_elapsed | 1808 | +| total_timesteps | 2523136 | +| train/ | | +| approx_kl | 0.011096273 | +| clip_fraction | 0.331 | +| clip_range | 0.0744 | +| entropy_loss | -7.26 | +| explained_variance | 0.237 | +| learning_rate | 4.94e-05 | +| loss | -0.0402 | +| n_updates | 20744 | +| policy_gradient_loss | -0.0232 | +| value_loss | 0.000142 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1395 | +| iterations | 1233 | +| time_elapsed | 1809 | +| total_timesteps | 2525184 | +| train/ | | +| approx_kl | 0.0116793 | +| clip_fraction | 0.313 | +| clip_range | 0.0744 | +| entropy_loss | -7.25 | +| explained_variance | 0.189 | +| learning_rate | 4.94e-05 | +| loss | -0.0348 | +| n_updates | 20748 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000198 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1395 | +| iterations | 1234 | +| time_elapsed | 1811 | +| total_timesteps | 2527232 | +| train/ | | +| approx_kl | 0.009498222 | +| clip_fraction | 0.297 | +| clip_range | 0.0744 | +| entropy_loss | -7.24 | +| explained_variance | 0.263 | +| learning_rate | 4.94e-05 | +| loss | -0.0314 | +| n_updates | 20752 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000172 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1395 | +| iterations | 1235 | +| time_elapsed | 1812 | +| total_timesteps | 2529280 | +| train/ | | +| approx_kl | 0.0082767755 | +| clip_fraction | 0.304 | +| clip_range | 0.0744 | +| entropy_loss | -7.21 | +| explained_variance | 0.287 | +| learning_rate | 4.94e-05 | +| loss | -0.0307 | +| n_updates | 20756 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000269 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1395 | +| iterations | 1236 | +| time_elapsed | 1814 | +| total_timesteps | 2531328 | +| train/ | | +| approx_kl | 0.009978801 | +| clip_fraction | 0.304 | +| clip_range | 0.0744 | +| entropy_loss | -7.43 | +| explained_variance | -0.293 | +| learning_rate | 4.94e-05 | +| loss | -0.0272 | +| n_updates | 20760 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000163 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1395 | +| iterations | 1237 | +| time_elapsed | 1815 | +| total_timesteps | 2533376 | +| train/ | | +| approx_kl | 0.010822166 | +| clip_fraction | 0.311 | +| clip_range | 0.0744 | +| entropy_loss | -7.14 | +| explained_variance | 0.491 | +| learning_rate | 4.94e-05 | +| loss | -0.0371 | +| n_updates | 20764 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000125 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1395 | +| iterations | 1238 | +| time_elapsed | 1816 | +| total_timesteps | 2535424 | +| train/ | | +| approx_kl | 0.010986226 | +| clip_fraction | 0.275 | +| clip_range | 0.0744 | +| entropy_loss | -7.21 | +| explained_variance | 0.151 | +| learning_rate | 4.94e-05 | +| loss | -0.0317 | +| n_updates | 20768 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000253 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1395 | +| iterations | 1239 | +| time_elapsed | 1818 | +| total_timesteps | 2537472 | +| train/ | | +| approx_kl | 0.010919379 | +| clip_fraction | 0.292 | +| clip_range | 0.0744 | +| entropy_loss | -7.17 | +| explained_variance | 0.166 | +| learning_rate | 4.94e-05 | +| loss | -0.03 | +| n_updates | 20772 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000267 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1395 | +| iterations | 1240 | +| time_elapsed | 1819 | +| total_timesteps | 2539520 | +| train/ | | +| approx_kl | 0.010183837 | +| clip_fraction | 0.326 | +| clip_range | 0.0744 | +| entropy_loss | -7.41 | +| explained_variance | 0.0438 | +| learning_rate | 4.94e-05 | +| loss | -0.0365 | +| n_updates | 20776 | +| policy_gradient_loss | -0.0227 | +| value_loss | 0.00016 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1395 | +| iterations | 1241 | +| time_elapsed | 1821 | +| total_timesteps | 2541568 | +| train/ | | +| approx_kl | 0.010110774 | +| clip_fraction | 0.314 | +| clip_range | 0.0744 | +| entropy_loss | -7.38 | +| explained_variance | -0.228 | +| learning_rate | 4.94e-05 | +| loss | -0.0419 | +| n_updates | 20780 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000109 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1395 | +| iterations | 1242 | +| time_elapsed | 1822 | +| total_timesteps | 2543616 | +| train/ | | +| approx_kl | 0.010517048 | +| clip_fraction | 0.297 | +| clip_range | 0.0744 | +| entropy_loss | -7.37 | +| explained_variance | 0.0115 | +| learning_rate | 4.94e-05 | +| loss | -0.03 | +| n_updates | 20784 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.00017 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1395 | +| iterations | 1243 | +| time_elapsed | 1824 | +| total_timesteps | 2545664 | +| train/ | | +| approx_kl | 0.009344006 | +| clip_fraction | 0.293 | +| clip_range | 0.0744 | +| entropy_loss | -7.11 | +| explained_variance | 0.262 | +| learning_rate | 4.94e-05 | +| loss | -0.0343 | +| n_updates | 20788 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000287 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1395 | +| iterations | 1244 | +| time_elapsed | 1825 | +| total_timesteps | 2547712 | +| train/ | | +| approx_kl | 0.008830685 | +| clip_fraction | 0.277 | +| clip_range | 0.0744 | +| entropy_loss | -7.22 | +| explained_variance | 0.313 | +| learning_rate | 4.94e-05 | +| loss | -0.0357 | +| n_updates | 20792 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.00029 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1395 | +| iterations | 1245 | +| time_elapsed | 1827 | +| total_timesteps | 2549760 | +| train/ | | +| approx_kl | 0.010863402 | +| clip_fraction | 0.32 | +| clip_range | 0.0744 | +| entropy_loss | -7.41 | +| explained_variance | -0.076 | +| learning_rate | 4.94e-05 | +| loss | -0.036 | +| n_updates | 20796 | +| policy_gradient_loss | -0.0219 | +| value_loss | 0.000196 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1395 | +| iterations | 1246 | +| time_elapsed | 1828 | +| total_timesteps | 2551808 | +| train/ | | +| approx_kl | 0.0104077235 | +| clip_fraction | 0.336 | +| clip_range | 0.0744 | +| entropy_loss | -7.22 | +| explained_variance | 0.392 | +| learning_rate | 4.94e-05 | +| loss | -0.0417 | +| n_updates | 20800 | +| policy_gradient_loss | -0.0236 | +| value_loss | 0.000115 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1395 | +| iterations | 1247 | +| time_elapsed | 1829 | +| total_timesteps | 2553856 | +| train/ | | +| approx_kl | 0.010929332 | +| clip_fraction | 0.307 | +| clip_range | 0.0744 | +| entropy_loss | -7.32 | +| explained_variance | 0.2 | +| learning_rate | 4.94e-05 | +| loss | -0.0357 | +| n_updates | 20804 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000221 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1395 | +| iterations | 1248 | +| time_elapsed | 1831 | +| total_timesteps | 2555904 | +| train/ | | +| approx_kl | 0.008853977 | +| clip_fraction | 0.312 | +| clip_range | 0.0744 | +| entropy_loss | -7.28 | +| explained_variance | 0.314 | +| learning_rate | 4.94e-05 | +| loss | -0.0367 | +| n_updates | 20808 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000143 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1395 | +| iterations | 1249 | +| time_elapsed | 1832 | +| total_timesteps | 2557952 | +| train/ | | +| approx_kl | 0.01179188 | +| clip_fraction | 0.308 | +| clip_range | 0.0744 | +| entropy_loss | -7.32 | +| explained_variance | -0.0129 | +| learning_rate | 4.94e-05 | +| loss | -0.0346 | +| n_updates | 20812 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000177 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1395 | +| iterations | 1250 | +| time_elapsed | 1834 | +| total_timesteps | 2560000 | +| train/ | | +| approx_kl | 0.010619968 | +| clip_fraction | 0.326 | +| clip_range | 0.0744 | +| entropy_loss | -7.48 | +| explained_variance | -0.102 | +| learning_rate | 4.94e-05 | +| loss | -0.0328 | +| n_updates | 20816 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000115 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1395 | +| iterations | 1251 | +| time_elapsed | 1835 | +| total_timesteps | 2562048 | +| train/ | | +| approx_kl | 0.011124091 | +| clip_fraction | 0.307 | +| clip_range | 0.0744 | +| entropy_loss | -7.4 | +| explained_variance | -0.105 | +| learning_rate | 4.94e-05 | +| loss | -0.034 | +| n_updates | 20820 | +| policy_gradient_loss | -0.0222 | +| value_loss | 9.71e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1395 | +| iterations | 1252 | +| time_elapsed | 1837 | +| total_timesteps | 2564096 | +| train/ | | +| approx_kl | 0.011660294 | +| clip_fraction | 0.325 | +| clip_range | 0.0744 | +| entropy_loss | -7.19 | +| explained_variance | 0.262 | +| learning_rate | 4.94e-05 | +| loss | -0.0367 | +| n_updates | 20824 | +| policy_gradient_loss | -0.0213 | +| value_loss | 7.89e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1395 | +| iterations | 1253 | +| time_elapsed | 1838 | +| total_timesteps | 2566144 | +| train/ | | +| approx_kl | 0.011872778 | +| clip_fraction | 0.35 | +| clip_range | 0.0744 | +| entropy_loss | -7.16 | +| explained_variance | -0.0445 | +| learning_rate | 4.94e-05 | +| loss | -0.0331 | +| n_updates | 20828 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.00013 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1395 | +| iterations | 1254 | +| time_elapsed | 1839 | +| total_timesteps | 2568192 | +| train/ | | +| approx_kl | 0.011546886 | +| clip_fraction | 0.289 | +| clip_range | 0.0744 | +| entropy_loss | -7.41 | +| explained_variance | 0.0169 | +| learning_rate | 4.94e-05 | +| loss | -0.0297 | +| n_updates | 20832 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000163 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1395 | +| iterations | 1255 | +| time_elapsed | 1841 | +| total_timesteps | 2570240 | +| train/ | | +| approx_kl | 0.0123357875 | +| clip_fraction | 0.334 | +| clip_range | 0.0744 | +| entropy_loss | -7.42 | +| explained_variance | 0.0596 | +| learning_rate | 4.94e-05 | +| loss | -0.033 | +| n_updates | 20836 | +| policy_gradient_loss | -0.023 | +| value_loss | 9.52e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1395 | +| iterations | 1256 | +| time_elapsed | 1842 | +| total_timesteps | 2572288 | +| train/ | | +| approx_kl | 0.011340544 | +| clip_fraction | 0.316 | +| clip_range | 0.0744 | +| entropy_loss | -7.45 | +| explained_variance | -0.191 | +| learning_rate | 4.94e-05 | +| loss | -0.0374 | +| n_updates | 20840 | +| policy_gradient_loss | -0.021 | +| value_loss | 7.54e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1395 | +| iterations | 1257 | +| time_elapsed | 1844 | +| total_timesteps | 2574336 | +| train/ | | +| approx_kl | 0.010672541 | +| clip_fraction | 0.311 | +| clip_range | 0.0744 | +| entropy_loss | -7.33 | +| explained_variance | 0.133 | +| learning_rate | 4.94e-05 | +| loss | -0.0337 | +| n_updates | 20844 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000129 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1395 | +| iterations | 1258 | +| time_elapsed | 1845 | +| total_timesteps | 2576384 | +| train/ | | +| approx_kl | 0.010498593 | +| clip_fraction | 0.341 | +| clip_range | 0.0744 | +| entropy_loss | -7.26 | +| explained_variance | 0.229 | +| learning_rate | 4.94e-05 | +| loss | -0.0395 | +| n_updates | 20848 | +| policy_gradient_loss | -0.0197 | +| value_loss | 9.78e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1395 | +| iterations | 1259 | +| time_elapsed | 1847 | +| total_timesteps | 2578432 | +| train/ | | +| approx_kl | 0.010638988 | +| clip_fraction | 0.285 | +| clip_range | 0.0744 | +| entropy_loss | -7.55 | +| explained_variance | -0.0675 | +| learning_rate | 4.94e-05 | +| loss | -0.0285 | +| n_updates | 20852 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000229 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1395 | +| iterations | 1260 | +| time_elapsed | 1848 | +| total_timesteps | 2580480 | +| train/ | | +| approx_kl | 0.00931617 | +| clip_fraction | 0.306 | +| clip_range | 0.0744 | +| entropy_loss | -7.35 | +| explained_variance | 0.0664 | +| learning_rate | 4.94e-05 | +| loss | -0.0273 | +| n_updates | 20856 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000196 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1395 | +| iterations | 1261 | +| time_elapsed | 1850 | +| total_timesteps | 2582528 | +| train/ | | +| approx_kl | 0.0103336815 | +| clip_fraction | 0.31 | +| clip_range | 0.0744 | +| entropy_loss | -6.8 | +| explained_variance | 0.571 | +| learning_rate | 4.94e-05 | +| loss | -0.0317 | +| n_updates | 20860 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000131 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1395 | +| iterations | 1262 | +| time_elapsed | 1851 | +| total_timesteps | 2584576 | +| train/ | | +| approx_kl | 0.010371656 | +| clip_fraction | 0.303 | +| clip_range | 0.0744 | +| entropy_loss | -7.34 | +| explained_variance | 0.101 | +| learning_rate | 4.94e-05 | +| loss | -0.0339 | +| n_updates | 20864 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1395 | +| iterations | 1263 | +| time_elapsed | 1852 | +| total_timesteps | 2586624 | +| train/ | | +| approx_kl | 0.011582454 | +| clip_fraction | 0.297 | +| clip_range | 0.0744 | +| entropy_loss | -7.42 | +| explained_variance | 0.0514 | +| learning_rate | 4.94e-05 | +| loss | -0.0327 | +| n_updates | 20868 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000164 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1396 | +| iterations | 1264 | +| time_elapsed | 1854 | +| total_timesteps | 2588672 | +| train/ | | +| approx_kl | 0.011129859 | +| clip_fraction | 0.297 | +| clip_range | 0.0744 | +| entropy_loss | -7.52 | +| explained_variance | -0.141 | +| learning_rate | 4.94e-05 | +| loss | -0.0334 | +| n_updates | 20872 | +| policy_gradient_loss | -0.0219 | +| value_loss | 0.00016 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1396 | +| iterations | 1265 | +| time_elapsed | 1855 | +| total_timesteps | 2590720 | +| train/ | | +| approx_kl | 0.010676931 | +| clip_fraction | 0.308 | +| clip_range | 0.0744 | +| entropy_loss | -7.24 | +| explained_variance | 0.247 | +| learning_rate | 4.94e-05 | +| loss | -0.0342 | +| n_updates | 20876 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.0001 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1396 | +| iterations | 1266 | +| time_elapsed | 1857 | +| total_timesteps | 2592768 | +| train/ | | +| approx_kl | 0.010219759 | +| clip_fraction | 0.304 | +| clip_range | 0.0744 | +| entropy_loss | -7.4 | +| explained_variance | 0.319 | +| learning_rate | 4.94e-05 | +| loss | -0.0329 | +| n_updates | 20880 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000132 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1396 | +| iterations | 1267 | +| time_elapsed | 1858 | +| total_timesteps | 2594816 | +| train/ | | +| approx_kl | 0.009956051 | +| clip_fraction | 0.289 | +| clip_range | 0.0744 | +| entropy_loss | -7.36 | +| explained_variance | 0.17 | +| learning_rate | 4.94e-05 | +| loss | -0.0321 | +| n_updates | 20884 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.00021 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1396 | +| iterations | 1268 | +| time_elapsed | 1859 | +| total_timesteps | 2596864 | +| train/ | | +| approx_kl | 0.0086880885 | +| clip_fraction | 0.267 | +| clip_range | 0.0744 | +| entropy_loss | -7.35 | +| explained_variance | 0.236 | +| learning_rate | 4.94e-05 | +| loss | -0.036 | +| n_updates | 20888 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000214 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1396 | +| iterations | 1269 | +| time_elapsed | 1861 | +| total_timesteps | 2598912 | +| train/ | | +| approx_kl | 0.00941121 | +| clip_fraction | 0.29 | +| clip_range | 0.0744 | +| entropy_loss | -6.94 | +| explained_variance | 0.346 | +| learning_rate | 4.94e-05 | +| loss | -0.0323 | +| n_updates | 20892 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.0004 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1396 | +| iterations | 1270 | +| time_elapsed | 1862 | +| total_timesteps | 2600960 | +| train/ | | +| approx_kl | 0.0105384365 | +| clip_fraction | 0.318 | +| clip_range | 0.0744 | +| entropy_loss | -7.3 | +| explained_variance | 0.499 | +| learning_rate | 4.94e-05 | +| loss | -0.0422 | +| n_updates | 20896 | +| policy_gradient_loss | -0.0234 | +| value_loss | 0.0001 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1396 | +| iterations | 1271 | +| time_elapsed | 1864 | +| total_timesteps | 2603008 | +| train/ | | +| approx_kl | 0.010029294 | +| clip_fraction | 0.288 | +| clip_range | 0.0743 | +| entropy_loss | -7.24 | +| explained_variance | 0.196 | +| learning_rate | 4.94e-05 | +| loss | -0.029 | +| n_updates | 20900 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000163 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1396 | +| iterations | 1272 | +| time_elapsed | 1865 | +| total_timesteps | 2605056 | +| train/ | | +| approx_kl | 0.010312524 | +| clip_fraction | 0.283 | +| clip_range | 0.0743 | +| entropy_loss | -7.48 | +| explained_variance | 0.172 | +| learning_rate | 4.94e-05 | +| loss | -0.032 | +| n_updates | 20904 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000154 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1396 | +| iterations | 1273 | +| time_elapsed | 1867 | +| total_timesteps | 2607104 | +| train/ | | +| approx_kl | 0.010415118 | +| clip_fraction | 0.289 | +| clip_range | 0.0743 | +| entropy_loss | -7.37 | +| explained_variance | -0.0338 | +| learning_rate | 4.94e-05 | +| loss | -0.0343 | +| n_updates | 20908 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000298 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1396 | +| iterations | 1274 | +| time_elapsed | 1868 | +| total_timesteps | 2609152 | +| train/ | | +| approx_kl | 0.0109798685 | +| clip_fraction | 0.338 | +| clip_range | 0.0743 | +| entropy_loss | -7.34 | +| explained_variance | 0.174 | +| learning_rate | 4.94e-05 | +| loss | -0.0347 | +| n_updates | 20912 | +| policy_gradient_loss | -0.022 | +| value_loss | 0.000169 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1396 | +| iterations | 1275 | +| time_elapsed | 1870 | +| total_timesteps | 2611200 | +| train/ | | +| approx_kl | 0.010301497 | +| clip_fraction | 0.282 | +| clip_range | 0.0743 | +| entropy_loss | -7.15 | +| explained_variance | 0.315 | +| learning_rate | 4.94e-05 | +| loss | -0.0349 | +| n_updates | 20916 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000237 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1396 | +| iterations | 1276 | +| time_elapsed | 1871 | +| total_timesteps | 2613248 | +| train/ | | +| approx_kl | 0.010484589 | +| clip_fraction | 0.321 | +| clip_range | 0.0743 | +| entropy_loss | -7.42 | +| explained_variance | 0.336 | +| learning_rate | 4.94e-05 | +| loss | -0.0315 | +| n_updates | 20920 | +| policy_gradient_loss | -0.0219 | +| value_loss | 0.00011 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1396 | +| iterations | 1277 | +| time_elapsed | 1873 | +| total_timesteps | 2615296 | +| train/ | | +| approx_kl | 0.010410466 | +| clip_fraction | 0.305 | +| clip_range | 0.0743 | +| entropy_loss | -7.34 | +| explained_variance | -0.0938 | +| learning_rate | 4.94e-05 | +| loss | -0.0389 | +| n_updates | 20924 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000109 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.387 | +| time/ | | +| fps | 1396 | +| iterations | 1278 | +| time_elapsed | 1874 | +| total_timesteps | 2617344 | +| train/ | | +| approx_kl | 0.010599536 | +| clip_fraction | 0.314 | +| clip_range | 0.0743 | +| entropy_loss | -7.34 | +| explained_variance | 0.154 | +| learning_rate | 4.94e-05 | +| loss | -0.0262 | +| n_updates | 20928 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000219 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.389 | +| time/ | | +| fps | 1396 | +| iterations | 1279 | +| time_elapsed | 1876 | +| total_timesteps | 2619392 | +| train/ | | +| approx_kl | 0.009153221 | +| clip_fraction | 0.286 | +| clip_range | 0.0743 | +| entropy_loss | -6.93 | +| explained_variance | 0.382 | +| learning_rate | 4.94e-05 | +| loss | -0.0288 | +| n_updates | 20932 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.00032 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.386 | +| time/ | | +| fps | 1396 | +| iterations | 1280 | +| time_elapsed | 1877 | +| total_timesteps | 2621440 | +| train/ | | +| approx_kl | 0.010612415 | +| clip_fraction | 0.308 | +| clip_range | 0.0743 | +| entropy_loss | -7.41 | +| explained_variance | 0.224 | +| learning_rate | 4.94e-05 | +| loss | -0.0321 | +| n_updates | 20936 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000112 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.386 | +| time/ | | +| fps | 1396 | +| iterations | 1281 | +| time_elapsed | 1879 | +| total_timesteps | 2623488 | +| train/ | | +| approx_kl | 0.008853264 | +| clip_fraction | 0.273 | +| clip_range | 0.0743 | +| entropy_loss | -7.05 | +| explained_variance | 0.392 | +| learning_rate | 4.94e-05 | +| loss | -0.0344 | +| n_updates | 20940 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000262 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.385 | +| time/ | | +| fps | 1396 | +| iterations | 1282 | +| time_elapsed | 1880 | +| total_timesteps | 2625536 | +| train/ | | +| approx_kl | 0.011667476 | +| clip_fraction | 0.34 | +| clip_range | 0.0743 | +| entropy_loss | -7.44 | +| explained_variance | -0.0104 | +| learning_rate | 4.94e-05 | +| loss | -0.0397 | +| n_updates | 20944 | +| policy_gradient_loss | -0.0259 | +| value_loss | 8.24e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.384 | +| time/ | | +| fps | 1396 | +| iterations | 1283 | +| time_elapsed | 1881 | +| total_timesteps | 2627584 | +| train/ | | +| approx_kl | 0.0106453635 | +| clip_fraction | 0.311 | +| clip_range | 0.0743 | +| entropy_loss | -7.23 | +| explained_variance | -0.464 | +| learning_rate | 4.94e-05 | +| loss | -0.0362 | +| n_updates | 20948 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000112 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1396 | +| iterations | 1284 | +| time_elapsed | 1883 | +| total_timesteps | 2629632 | +| train/ | | +| approx_kl | 0.009778627 | +| clip_fraction | 0.28 | +| clip_range | 0.0743 | +| entropy_loss | -7.39 | +| explained_variance | 0.036 | +| learning_rate | 4.94e-05 | +| loss | -0.0286 | +| n_updates | 20952 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000231 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1396 | +| iterations | 1285 | +| time_elapsed | 1884 | +| total_timesteps | 2631680 | +| train/ | | +| approx_kl | 0.010907755 | +| clip_fraction | 0.267 | +| clip_range | 0.0743 | +| entropy_loss | -6.95 | +| explained_variance | 0.223 | +| learning_rate | 4.94e-05 | +| loss | -0.0327 | +| n_updates | 20956 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000318 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1396 | +| iterations | 1286 | +| time_elapsed | 1886 | +| total_timesteps | 2633728 | +| train/ | | +| approx_kl | 0.011233076 | +| clip_fraction | 0.334 | +| clip_range | 0.0743 | +| entropy_loss | -7.35 | +| explained_variance | -0.00518 | +| learning_rate | 4.94e-05 | +| loss | -0.0391 | +| n_updates | 20960 | +| policy_gradient_loss | -0.0231 | +| value_loss | 0.000118 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1396 | +| iterations | 1287 | +| time_elapsed | 1887 | +| total_timesteps | 2635776 | +| train/ | | +| approx_kl | 0.011185208 | +| clip_fraction | 0.316 | +| clip_range | 0.0743 | +| entropy_loss | -7.55 | +| explained_variance | -0.142 | +| learning_rate | 4.94e-05 | +| loss | -0.035 | +| n_updates | 20964 | +| policy_gradient_loss | -0.0224 | +| value_loss | 0.00016 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1396 | +| iterations | 1288 | +| time_elapsed | 1889 | +| total_timesteps | 2637824 | +| train/ | | +| approx_kl | 0.009433869 | +| clip_fraction | 0.293 | +| clip_range | 0.0743 | +| entropy_loss | -7.21 | +| explained_variance | 0.222 | +| learning_rate | 4.94e-05 | +| loss | -0.0313 | +| n_updates | 20968 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000301 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1396 | +| iterations | 1289 | +| time_elapsed | 1890 | +| total_timesteps | 2639872 | +| train/ | | +| approx_kl | 0.008925726 | +| clip_fraction | 0.324 | +| clip_range | 0.0743 | +| entropy_loss | -7.18 | +| explained_variance | 0.259 | +| learning_rate | 4.94e-05 | +| loss | -0.0309 | +| n_updates | 20972 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000124 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1396 | +| iterations | 1290 | +| time_elapsed | 1891 | +| total_timesteps | 2641920 | +| train/ | | +| approx_kl | 0.010612428 | +| clip_fraction | 0.324 | +| clip_range | 0.0743 | +| entropy_loss | -7.1 | +| explained_variance | 0.342 | +| learning_rate | 4.94e-05 | +| loss | -0.0312 | +| n_updates | 20976 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000225 | +----------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1396 | +| iterations | 1291 | +| time_elapsed | 1893 | +| total_timesteps | 2643968 | +| train/ | | +| approx_kl | 0.011304 | +| clip_fraction | 0.327 | +| clip_range | 0.0743 | +| entropy_loss | -7.15 | +| explained_variance | 0.468 | +| learning_rate | 4.94e-05 | +| loss | -0.0345 | +| n_updates | 20980 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000132 | +-------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1396 | +| iterations | 1292 | +| time_elapsed | 1894 | +| total_timesteps | 2646016 | +| train/ | | +| approx_kl | 0.011853352 | +| clip_fraction | 0.35 | +| clip_range | 0.0743 | +| entropy_loss | -7.24 | +| explained_variance | 0.321 | +| learning_rate | 4.94e-05 | +| loss | -0.0341 | +| n_updates | 20984 | +| policy_gradient_loss | -0.0234 | +| value_loss | 0.000112 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1396 | +| iterations | 1293 | +| time_elapsed | 1896 | +| total_timesteps | 2648064 | +| train/ | | +| approx_kl | 0.0104569215 | +| clip_fraction | 0.311 | +| clip_range | 0.0743 | +| entropy_loss | -7.31 | +| explained_variance | 0.298 | +| learning_rate | 4.94e-05 | +| loss | -0.0347 | +| n_updates | 20988 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000155 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1396 | +| iterations | 1294 | +| time_elapsed | 1897 | +| total_timesteps | 2650112 | +| train/ | | +| approx_kl | 0.010653112 | +| clip_fraction | 0.304 | +| clip_range | 0.0743 | +| entropy_loss | -7.4 | +| explained_variance | -0.0509 | +| learning_rate | 4.94e-05 | +| loss | -0.0309 | +| n_updates | 20992 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000169 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1396 | +| iterations | 1295 | +| time_elapsed | 1899 | +| total_timesteps | 2652160 | +| train/ | | +| approx_kl | 0.0113015035 | +| clip_fraction | 0.302 | +| clip_range | 0.0743 | +| entropy_loss | -7.22 | +| explained_variance | 0.396 | +| learning_rate | 4.94e-05 | +| loss | -0.0291 | +| n_updates | 20996 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.00018 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1396 | +| iterations | 1296 | +| time_elapsed | 1900 | +| total_timesteps | 2654208 | +| train/ | | +| approx_kl | 0.010666104 | +| clip_fraction | 0.305 | +| clip_range | 0.0743 | +| entropy_loss | -7.39 | +| explained_variance | -0.105 | +| learning_rate | 4.94e-05 | +| loss | -0.0339 | +| n_updates | 21000 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000217 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1396 | +| iterations | 1297 | +| time_elapsed | 1902 | +| total_timesteps | 2656256 | +| train/ | | +| approx_kl | 0.009453196 | +| clip_fraction | 0.314 | +| clip_range | 0.0743 | +| entropy_loss | -7.1 | +| explained_variance | 0.542 | +| learning_rate | 4.94e-05 | +| loss | -0.0341 | +| n_updates | 21004 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000152 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1396 | +| iterations | 1298 | +| time_elapsed | 1903 | +| total_timesteps | 2658304 | +| train/ | | +| approx_kl | 0.00864218 | +| clip_fraction | 0.282 | +| clip_range | 0.0743 | +| entropy_loss | -7.45 | +| explained_variance | -0.109 | +| learning_rate | 4.94e-05 | +| loss | -0.027 | +| n_updates | 21008 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000221 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1396 | +| iterations | 1299 | +| time_elapsed | 1905 | +| total_timesteps | 2660352 | +| train/ | | +| approx_kl | 0.008592672 | +| clip_fraction | 0.286 | +| clip_range | 0.0743 | +| entropy_loss | -6.91 | +| explained_variance | 0.55 | +| learning_rate | 4.94e-05 | +| loss | -0.034 | +| n_updates | 21012 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000194 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1396 | +| iterations | 1300 | +| time_elapsed | 1906 | +| total_timesteps | 2662400 | +| train/ | | +| approx_kl | 0.0085748695 | +| clip_fraction | 0.265 | +| clip_range | 0.0743 | +| entropy_loss | -6.93 | +| explained_variance | 0.405 | +| learning_rate | 4.94e-05 | +| loss | -0.0227 | +| n_updates | 21016 | +| policy_gradient_loss | -0.0142 | +| value_loss | 0.000358 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1396 | +| iterations | 1301 | +| time_elapsed | 1907 | +| total_timesteps | 2664448 | +| train/ | | +| approx_kl | 0.011887424 | +| clip_fraction | 0.303 | +| clip_range | 0.0743 | +| entropy_loss | -7.21 | +| explained_variance | -0.167 | +| learning_rate | 4.94e-05 | +| loss | -0.0303 | +| n_updates | 21020 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000186 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1396 | +| iterations | 1302 | +| time_elapsed | 1909 | +| total_timesteps | 2666496 | +| train/ | | +| approx_kl | 0.011298339 | +| clip_fraction | 0.316 | +| clip_range | 0.0743 | +| entropy_loss | -7.52 | +| explained_variance | -0.144 | +| learning_rate | 4.94e-05 | +| loss | -0.034 | +| n_updates | 21024 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000235 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1396 | +| iterations | 1303 | +| time_elapsed | 1910 | +| total_timesteps | 2668544 | +| train/ | | +| approx_kl | 0.0096453745 | +| clip_fraction | 0.295 | +| clip_range | 0.0743 | +| entropy_loss | -7.29 | +| explained_variance | 0.0619 | +| learning_rate | 4.94e-05 | +| loss | -0.0232 | +| n_updates | 21028 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000365 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.386 | +| time/ | | +| fps | 1396 | +| iterations | 1304 | +| time_elapsed | 1912 | +| total_timesteps | 2670592 | +| train/ | | +| approx_kl | 0.013693323 | +| clip_fraction | 0.339 | +| clip_range | 0.0743 | +| entropy_loss | -7.37 | +| explained_variance | -0.255 | +| learning_rate | 4.94e-05 | +| loss | -0.038 | +| n_updates | 21032 | +| policy_gradient_loss | -0.0241 | +| value_loss | 0.000151 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1396 | +| iterations | 1305 | +| time_elapsed | 1913 | +| total_timesteps | 2672640 | +| train/ | | +| approx_kl | 0.010882176 | +| clip_fraction | 0.311 | +| clip_range | 0.0743 | +| entropy_loss | -7.19 | +| explained_variance | 0.208 | +| learning_rate | 4.94e-05 | +| loss | -0.0286 | +| n_updates | 21036 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000245 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1396 | +| iterations | 1306 | +| time_elapsed | 1915 | +| total_timesteps | 2674688 | +| train/ | | +| approx_kl | 0.012998957 | +| clip_fraction | 0.349 | +| clip_range | 0.0743 | +| entropy_loss | -7.29 | +| explained_variance | 0.371 | +| learning_rate | 4.94e-05 | +| loss | -0.0387 | +| n_updates | 21040 | +| policy_gradient_loss | -0.024 | +| value_loss | 0.000111 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1396 | +| iterations | 1307 | +| time_elapsed | 1916 | +| total_timesteps | 2676736 | +| train/ | | +| approx_kl | 0.009524252 | +| clip_fraction | 0.34 | +| clip_range | 0.0743 | +| entropy_loss | -7.32 | +| explained_variance | 0.358 | +| learning_rate | 4.94e-05 | +| loss | -0.0436 | +| n_updates | 21044 | +| policy_gradient_loss | -0.0243 | +| value_loss | 7.99e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1396 | +| iterations | 1308 | +| time_elapsed | 1918 | +| total_timesteps | 2678784 | +| train/ | | +| approx_kl | 0.012287499 | +| clip_fraction | 0.336 | +| clip_range | 0.0743 | +| entropy_loss | -7.44 | +| explained_variance | -0.208 | +| learning_rate | 4.94e-05 | +| loss | -0.0331 | +| n_updates | 21048 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000128 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1396 | +| iterations | 1309 | +| time_elapsed | 1919 | +| total_timesteps | 2680832 | +| train/ | | +| approx_kl | 0.008559947 | +| clip_fraction | 0.267 | +| clip_range | 0.0743 | +| entropy_loss | -7.16 | +| explained_variance | 0.375 | +| learning_rate | 4.94e-05 | +| loss | -0.0254 | +| n_updates | 21052 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000223 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1396 | +| iterations | 1310 | +| time_elapsed | 1920 | +| total_timesteps | 2682880 | +| train/ | | +| approx_kl | 0.0103824865 | +| clip_fraction | 0.299 | +| clip_range | 0.0743 | +| entropy_loss | -7.39 | +| explained_variance | -0.303 | +| learning_rate | 4.94e-05 | +| loss | -0.0286 | +| n_updates | 21056 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000144 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1396 | +| iterations | 1311 | +| time_elapsed | 1922 | +| total_timesteps | 2684928 | +| train/ | | +| approx_kl | 0.012876041 | +| clip_fraction | 0.307 | +| clip_range | 0.0743 | +| entropy_loss | -7.25 | +| explained_variance | -0.262 | +| learning_rate | 4.94e-05 | +| loss | -0.0334 | +| n_updates | 21060 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000107 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1396 | +| iterations | 1312 | +| time_elapsed | 1923 | +| total_timesteps | 2686976 | +| train/ | | +| approx_kl | 0.010836102 | +| clip_fraction | 0.31 | +| clip_range | 0.0743 | +| entropy_loss | -7.08 | +| explained_variance | 0.275 | +| learning_rate | 4.94e-05 | +| loss | -0.0297 | +| n_updates | 21064 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000214 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1396 | +| iterations | 1313 | +| time_elapsed | 1925 | +| total_timesteps | 2689024 | +| train/ | | +| approx_kl | 0.010733799 | +| clip_fraction | 0.33 | +| clip_range | 0.0743 | +| entropy_loss | -7.17 | +| explained_variance | 0.536 | +| learning_rate | 4.94e-05 | +| loss | -0.0337 | +| n_updates | 21068 | +| policy_gradient_loss | -0.0221 | +| value_loss | 9.22e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1396 | +| iterations | 1314 | +| time_elapsed | 1926 | +| total_timesteps | 2691072 | +| train/ | | +| approx_kl | 0.008464242 | +| clip_fraction | 0.293 | +| clip_range | 0.0743 | +| entropy_loss | -7.08 | +| explained_variance | 0.227 | +| learning_rate | 4.94e-05 | +| loss | -0.0234 | +| n_updates | 21072 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000161 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1396 | +| iterations | 1315 | +| time_elapsed | 1927 | +| total_timesteps | 2693120 | +| train/ | | +| approx_kl | 0.010251952 | +| clip_fraction | 0.307 | +| clip_range | 0.0743 | +| entropy_loss | -7.26 | +| explained_variance | 0.306 | +| learning_rate | 4.94e-05 | +| loss | -0.0314 | +| n_updates | 21076 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000125 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1396 | +| iterations | 1316 | +| time_elapsed | 1929 | +| total_timesteps | 2695168 | +| train/ | | +| approx_kl | 0.010042947 | +| clip_fraction | 0.321 | +| clip_range | 0.0743 | +| entropy_loss | -7.41 | +| explained_variance | -0.565 | +| learning_rate | 4.94e-05 | +| loss | -0.0357 | +| n_updates | 21080 | +| policy_gradient_loss | -0.0236 | +| value_loss | 6.09e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1396 | +| iterations | 1317 | +| time_elapsed | 1930 | +| total_timesteps | 2697216 | +| train/ | | +| approx_kl | 0.011101064 | +| clip_fraction | 0.285 | +| clip_range | 0.0743 | +| entropy_loss | -7.08 | +| explained_variance | 0.233 | +| learning_rate | 4.94e-05 | +| loss | -0.0297 | +| n_updates | 21084 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000211 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1396 | +| iterations | 1318 | +| time_elapsed | 1932 | +| total_timesteps | 2699264 | +| train/ | | +| approx_kl | 0.011043686 | +| clip_fraction | 0.308 | +| clip_range | 0.0743 | +| entropy_loss | -7.07 | +| explained_variance | 0.325 | +| learning_rate | 4.94e-05 | +| loss | -0.0327 | +| n_updates | 21088 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000101 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1396 | +| iterations | 1319 | +| time_elapsed | 1933 | +| total_timesteps | 2701312 | +| train/ | | +| approx_kl | 0.010869395 | +| clip_fraction | 0.34 | +| clip_range | 0.0743 | +| entropy_loss | -7.2 | +| explained_variance | 0.606 | +| learning_rate | 4.94e-05 | +| loss | -0.0331 | +| n_updates | 21092 | +| policy_gradient_loss | -0.0224 | +| value_loss | 7.46e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1396 | +| iterations | 1320 | +| time_elapsed | 1935 | +| total_timesteps | 2703360 | +| train/ | | +| approx_kl | 0.011853719 | +| clip_fraction | 0.332 | +| clip_range | 0.0743 | +| entropy_loss | -7.14 | +| explained_variance | 0.352 | +| learning_rate | 4.94e-05 | +| loss | -0.0276 | +| n_updates | 21096 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000225 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1396 | +| iterations | 1321 | +| time_elapsed | 1936 | +| total_timesteps | 2705408 | +| train/ | | +| approx_kl | 0.011253608 | +| clip_fraction | 0.296 | +| clip_range | 0.0743 | +| entropy_loss | -7.15 | +| explained_variance | 0.0823 | +| learning_rate | 4.94e-05 | +| loss | -0.0294 | +| n_updates | 21100 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000292 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1396 | +| iterations | 1322 | +| time_elapsed | 1938 | +| total_timesteps | 2707456 | +| train/ | | +| approx_kl | 0.011733878 | +| clip_fraction | 0.311 | +| clip_range | 0.0743 | +| entropy_loss | -7.04 | +| explained_variance | 0.33 | +| learning_rate | 4.94e-05 | +| loss | -0.0311 | +| n_updates | 21104 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000269 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1396 | +| iterations | 1323 | +| time_elapsed | 1939 | +| total_timesteps | 2709504 | +| train/ | | +| approx_kl | 0.012343092 | +| clip_fraction | 0.337 | +| clip_range | 0.0743 | +| entropy_loss | -7.33 | +| explained_variance | -0.06 | +| learning_rate | 4.94e-05 | +| loss | -0.0391 | +| n_updates | 21108 | +| policy_gradient_loss | -0.023 | +| value_loss | 0.000186 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1396 | +| iterations | 1324 | +| time_elapsed | 1941 | +| total_timesteps | 2711552 | +| train/ | | +| approx_kl | 0.0118933525 | +| clip_fraction | 0.312 | +| clip_range | 0.0743 | +| entropy_loss | -7.29 | +| explained_variance | -0.121 | +| learning_rate | 4.94e-05 | +| loss | -0.0358 | +| n_updates | 21112 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000193 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1396 | +| iterations | 1325 | +| time_elapsed | 1942 | +| total_timesteps | 2713600 | +| train/ | | +| approx_kl | 0.010887189 | +| clip_fraction | 0.325 | +| clip_range | 0.0743 | +| entropy_loss | -6.74 | +| explained_variance | 0.289 | +| learning_rate | 4.94e-05 | +| loss | -0.0247 | +| n_updates | 21116 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000313 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1396 | +| iterations | 1326 | +| time_elapsed | 1943 | +| total_timesteps | 2715648 | +| train/ | | +| approx_kl | 0.012811393 | +| clip_fraction | 0.347 | +| clip_range | 0.0743 | +| entropy_loss | -7.41 | +| explained_variance | -0.707 | +| learning_rate | 4.94e-05 | +| loss | -0.0437 | +| n_updates | 21120 | +| policy_gradient_loss | -0.0263 | +| value_loss | 9.45e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1396 | +| iterations | 1327 | +| time_elapsed | 1945 | +| total_timesteps | 2717696 | +| train/ | | +| approx_kl | 0.012547673 | +| clip_fraction | 0.327 | +| clip_range | 0.0743 | +| entropy_loss | -6.98 | +| explained_variance | 0.226 | +| learning_rate | 4.94e-05 | +| loss | -0.0302 | +| n_updates | 21124 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000289 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1397 | +| iterations | 1328 | +| time_elapsed | 1946 | +| total_timesteps | 2719744 | +| train/ | | +| approx_kl | 0.009804745 | +| clip_fraction | 0.287 | +| clip_range | 0.0743 | +| entropy_loss | -6.87 | +| explained_variance | 0.333 | +| learning_rate | 4.94e-05 | +| loss | -0.029 | +| n_updates | 21128 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000289 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1397 | +| iterations | 1329 | +| time_elapsed | 1948 | +| total_timesteps | 2721792 | +| train/ | | +| approx_kl | 0.010743657 | +| clip_fraction | 0.342 | +| clip_range | 0.0743 | +| entropy_loss | -7.17 | +| explained_variance | 0.17 | +| learning_rate | 4.94e-05 | +| loss | -0.0366 | +| n_updates | 21132 | +| policy_gradient_loss | -0.0226 | +| value_loss | 0.000321 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1397 | +| iterations | 1330 | +| time_elapsed | 1949 | +| total_timesteps | 2723840 | +| train/ | | +| approx_kl | 0.011254916 | +| clip_fraction | 0.327 | +| clip_range | 0.0743 | +| entropy_loss | -7.41 | +| explained_variance | -0.32 | +| learning_rate | 4.94e-05 | +| loss | -0.037 | +| n_updates | 21136 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1397 | +| iterations | 1331 | +| time_elapsed | 1951 | +| total_timesteps | 2725888 | +| train/ | | +| approx_kl | 0.010581767 | +| clip_fraction | 0.333 | +| clip_range | 0.0743 | +| entropy_loss | -7.48 | +| explained_variance | -0.128 | +| learning_rate | 4.94e-05 | +| loss | -0.0377 | +| n_updates | 21140 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000145 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1397 | +| iterations | 1332 | +| time_elapsed | 1952 | +| total_timesteps | 2727936 | +| train/ | | +| approx_kl | 0.0107902195 | +| clip_fraction | 0.299 | +| clip_range | 0.0743 | +| entropy_loss | -6.83 | +| explained_variance | 0.247 | +| learning_rate | 4.94e-05 | +| loss | -0.0286 | +| n_updates | 21144 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000453 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1397 | +| iterations | 1333 | +| time_elapsed | 1953 | +| total_timesteps | 2729984 | +| train/ | | +| approx_kl | 0.011614405 | +| clip_fraction | 0.334 | +| clip_range | 0.0743 | +| entropy_loss | -7.25 | +| explained_variance | 0.224 | +| learning_rate | 4.94e-05 | +| loss | -0.0342 | +| n_updates | 21148 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000186 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1397 | +| iterations | 1334 | +| time_elapsed | 1955 | +| total_timesteps | 2732032 | +| train/ | | +| approx_kl | 0.008822313 | +| clip_fraction | 0.285 | +| clip_range | 0.0743 | +| entropy_loss | -6.83 | +| explained_variance | 0.189 | +| learning_rate | 4.94e-05 | +| loss | -0.0292 | +| n_updates | 21152 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000461 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1397 | +| iterations | 1335 | +| time_elapsed | 1956 | +| total_timesteps | 2734080 | +| train/ | | +| approx_kl | 0.0133311255 | +| clip_fraction | 0.356 | +| clip_range | 0.0743 | +| entropy_loss | -7.23 | +| explained_variance | -0.487 | +| learning_rate | 4.94e-05 | +| loss | -0.0455 | +| n_updates | 21156 | +| policy_gradient_loss | -0.0255 | +| value_loss | 0.000121 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1397 | +| iterations | 1336 | +| time_elapsed | 1958 | +| total_timesteps | 2736128 | +| train/ | | +| approx_kl | 0.011902913 | +| clip_fraction | 0.32 | +| clip_range | 0.0743 | +| entropy_loss | -7.28 | +| explained_variance | -0.139 | +| learning_rate | 4.94e-05 | +| loss | -0.0357 | +| n_updates | 21160 | +| policy_gradient_loss | -0.0238 | +| value_loss | 0.000135 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1397 | +| iterations | 1337 | +| time_elapsed | 1959 | +| total_timesteps | 2738176 | +| train/ | | +| approx_kl | 0.011163762 | +| clip_fraction | 0.308 | +| clip_range | 0.0743 | +| entropy_loss | -7.06 | +| explained_variance | 0.189 | +| learning_rate | 4.94e-05 | +| loss | -0.0331 | +| n_updates | 21164 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000131 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1397 | +| iterations | 1338 | +| time_elapsed | 1961 | +| total_timesteps | 2740224 | +| train/ | | +| approx_kl | 0.009941612 | +| clip_fraction | 0.334 | +| clip_range | 0.0743 | +| entropy_loss | -6.99 | +| explained_variance | 0.613 | +| learning_rate | 4.93e-05 | +| loss | -0.0323 | +| n_updates | 21168 | +| policy_gradient_loss | -0.0204 | +| value_loss | 9.88e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1397 | +| iterations | 1339 | +| time_elapsed | 1962 | +| total_timesteps | 2742272 | +| train/ | | +| approx_kl | 0.0102633275 | +| clip_fraction | 0.293 | +| clip_range | 0.0743 | +| entropy_loss | -7.43 | +| explained_variance | -0.0636 | +| learning_rate | 4.93e-05 | +| loss | -0.0266 | +| n_updates | 21172 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000214 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1397 | +| iterations | 1340 | +| time_elapsed | 1963 | +| total_timesteps | 2744320 | +| train/ | | +| approx_kl | 0.010758098 | +| clip_fraction | 0.327 | +| clip_range | 0.0743 | +| entropy_loss | -7.28 | +| explained_variance | 0.301 | +| learning_rate | 4.93e-05 | +| loss | -0.0378 | +| n_updates | 21176 | +| policy_gradient_loss | -0.0226 | +| value_loss | 0.000124 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1397 | +| iterations | 1341 | +| time_elapsed | 1965 | +| total_timesteps | 2746368 | +| train/ | | +| approx_kl | 0.012321177 | +| clip_fraction | 0.336 | +| clip_range | 0.0743 | +| entropy_loss | -7.35 | +| explained_variance | -0.213 | +| learning_rate | 4.93e-05 | +| loss | -0.0449 | +| n_updates | 21180 | +| policy_gradient_loss | -0.0241 | +| value_loss | 7.4e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1397 | +| iterations | 1342 | +| time_elapsed | 1966 | +| total_timesteps | 2748416 | +| train/ | | +| approx_kl | 0.012080363 | +| clip_fraction | 0.324 | +| clip_range | 0.0743 | +| entropy_loss | -7.22 | +| explained_variance | 0.299 | +| learning_rate | 4.93e-05 | +| loss | -0.0327 | +| n_updates | 21184 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1397 | +| iterations | 1343 | +| time_elapsed | 1968 | +| total_timesteps | 2750464 | +| train/ | | +| approx_kl | 0.011066157 | +| clip_fraction | 0.289 | +| clip_range | 0.0743 | +| entropy_loss | -6.95 | +| explained_variance | 0.63 | +| learning_rate | 4.93e-05 | +| loss | -0.0299 | +| n_updates | 21188 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1397 | +| iterations | 1344 | +| time_elapsed | 1969 | +| total_timesteps | 2752512 | +| train/ | | +| approx_kl | 0.012287861 | +| clip_fraction | 0.301 | +| clip_range | 0.0743 | +| entropy_loss | -7.23 | +| explained_variance | -0.0237 | +| learning_rate | 4.93e-05 | +| loss | -0.0324 | +| n_updates | 21192 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000133 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1397 | +| iterations | 1345 | +| time_elapsed | 1970 | +| total_timesteps | 2754560 | +| train/ | | +| approx_kl | 0.010963993 | +| clip_fraction | 0.311 | +| clip_range | 0.0743 | +| entropy_loss | -7.17 | +| explained_variance | 0.288 | +| learning_rate | 4.93e-05 | +| loss | -0.0325 | +| n_updates | 21196 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000123 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1397 | +| iterations | 1346 | +| time_elapsed | 1972 | +| total_timesteps | 2756608 | +| train/ | | +| approx_kl | 0.010778172 | +| clip_fraction | 0.313 | +| clip_range | 0.0743 | +| entropy_loss | -6.89 | +| explained_variance | 0.467 | +| learning_rate | 4.93e-05 | +| loss | -0.0379 | +| n_updates | 21200 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000206 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1397 | +| iterations | 1347 | +| time_elapsed | 1973 | +| total_timesteps | 2758656 | +| train/ | | +| approx_kl | 0.010032436 | +| clip_fraction | 0.315 | +| clip_range | 0.0743 | +| entropy_loss | -7.42 | +| explained_variance | -0.0857 | +| learning_rate | 4.93e-05 | +| loss | -0.0426 | +| n_updates | 21204 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000109 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1397 | +| iterations | 1348 | +| time_elapsed | 1975 | +| total_timesteps | 2760704 | +| train/ | | +| approx_kl | 0.009028714 | +| clip_fraction | 0.308 | +| clip_range | 0.0743 | +| entropy_loss | -7.03 | +| explained_variance | 0.465 | +| learning_rate | 4.93e-05 | +| loss | -0.0345 | +| n_updates | 21208 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.00023 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1397 | +| iterations | 1349 | +| time_elapsed | 1976 | +| total_timesteps | 2762752 | +| train/ | | +| approx_kl | 0.0070985253 | +| clip_fraction | 0.284 | +| clip_range | 0.0743 | +| entropy_loss | -7.12 | +| explained_variance | 0.0292 | +| learning_rate | 4.93e-05 | +| loss | -0.0307 | +| n_updates | 21212 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000397 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1397 | +| iterations | 1350 | +| time_elapsed | 1978 | +| total_timesteps | 2764800 | +| train/ | | +| approx_kl | 0.009896012 | +| clip_fraction | 0.331 | +| clip_range | 0.0743 | +| entropy_loss | -7.11 | +| explained_variance | 0.148 | +| learning_rate | 4.93e-05 | +| loss | -0.0363 | +| n_updates | 21216 | +| policy_gradient_loss | -0.0222 | +| value_loss | 0.000159 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1397 | +| iterations | 1351 | +| time_elapsed | 1979 | +| total_timesteps | 2766848 | +| train/ | | +| approx_kl | 0.013149522 | +| clip_fraction | 0.33 | +| clip_range | 0.0743 | +| entropy_loss | -7.38 | +| explained_variance | -0.255 | +| learning_rate | 4.93e-05 | +| loss | -0.0329 | +| n_updates | 21220 | +| policy_gradient_loss | -0.0222 | +| value_loss | 0.00013 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1397 | +| iterations | 1352 | +| time_elapsed | 1981 | +| total_timesteps | 2768896 | +| train/ | | +| approx_kl | 0.010634968 | +| clip_fraction | 0.323 | +| clip_range | 0.0743 | +| entropy_loss | -7.25 | +| explained_variance | -0.0898 | +| learning_rate | 4.93e-05 | +| loss | -0.0345 | +| n_updates | 21224 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000183 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1397 | +| iterations | 1353 | +| time_elapsed | 1982 | +| total_timesteps | 2770944 | +| train/ | | +| approx_kl | 0.0101792365 | +| clip_fraction | 0.308 | +| clip_range | 0.0743 | +| entropy_loss | -7.02 | +| explained_variance | 0.348 | +| learning_rate | 4.93e-05 | +| loss | -0.0313 | +| n_updates | 21228 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000142 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1397 | +| iterations | 1354 | +| time_elapsed | 1983 | +| total_timesteps | 2772992 | +| train/ | | +| approx_kl | 0.012236908 | +| clip_fraction | 0.32 | +| clip_range | 0.0743 | +| entropy_loss | -7.04 | +| explained_variance | 0.571 | +| learning_rate | 4.93e-05 | +| loss | -0.0372 | +| n_updates | 21232 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.0001 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1397 | +| iterations | 1355 | +| time_elapsed | 1985 | +| total_timesteps | 2775040 | +| train/ | | +| approx_kl | 0.011660085 | +| clip_fraction | 0.344 | +| clip_range | 0.0743 | +| entropy_loss | -7.2 | +| explained_variance | 0.573 | +| learning_rate | 4.93e-05 | +| loss | -0.0413 | +| n_updates | 21236 | +| policy_gradient_loss | -0.0231 | +| value_loss | 6.86e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1397 | +| iterations | 1356 | +| time_elapsed | 1986 | +| total_timesteps | 2777088 | +| train/ | | +| approx_kl | 0.011131352 | +| clip_fraction | 0.302 | +| clip_range | 0.0743 | +| entropy_loss | -7.19 | +| explained_variance | 0.461 | +| learning_rate | 4.93e-05 | +| loss | -0.0367 | +| n_updates | 21240 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000182 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1397 | +| iterations | 1357 | +| time_elapsed | 1988 | +| total_timesteps | 2779136 | +| train/ | | +| approx_kl | 0.010584675 | +| clip_fraction | 0.294 | +| clip_range | 0.0743 | +| entropy_loss | -7.31 | +| explained_variance | 0.367 | +| learning_rate | 4.93e-05 | +| loss | -0.0323 | +| n_updates | 21244 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000133 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1397 | +| iterations | 1358 | +| time_elapsed | 1989 | +| total_timesteps | 2781184 | +| train/ | | +| approx_kl | 0.011511777 | +| clip_fraction | 0.335 | +| clip_range | 0.0743 | +| entropy_loss | -7.41 | +| explained_variance | -0.375 | +| learning_rate | 4.93e-05 | +| loss | -0.0385 | +| n_updates | 21248 | +| policy_gradient_loss | -0.0245 | +| value_loss | 7.16e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1397 | +| iterations | 1359 | +| time_elapsed | 1990 | +| total_timesteps | 2783232 | +| train/ | | +| approx_kl | 0.009318111 | +| clip_fraction | 0.295 | +| clip_range | 0.0743 | +| entropy_loss | -7.18 | +| explained_variance | 0.318 | +| learning_rate | 4.93e-05 | +| loss | -0.0262 | +| n_updates | 21252 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000267 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1397 | +| iterations | 1360 | +| time_elapsed | 1992 | +| total_timesteps | 2785280 | +| train/ | | +| approx_kl | 0.009741168 | +| clip_fraction | 0.296 | +| clip_range | 0.0743 | +| entropy_loss | -7.39 | +| explained_variance | -0.0946 | +| learning_rate | 4.93e-05 | +| loss | -0.0364 | +| n_updates | 21256 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.00012 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1397 | +| iterations | 1361 | +| time_elapsed | 1993 | +| total_timesteps | 2787328 | +| train/ | | +| approx_kl | 0.010921491 | +| clip_fraction | 0.317 | +| clip_range | 0.0743 | +| entropy_loss | -6.98 | +| explained_variance | 0.526 | +| learning_rate | 4.93e-05 | +| loss | -0.0307 | +| n_updates | 21260 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000136 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1398 | +| iterations | 1362 | +| time_elapsed | 1995 | +| total_timesteps | 2789376 | +| train/ | | +| approx_kl | 0.009982213 | +| clip_fraction | 0.301 | +| clip_range | 0.0743 | +| entropy_loss | -7.08 | +| explained_variance | 0.279 | +| learning_rate | 4.93e-05 | +| loss | -0.0246 | +| n_updates | 21264 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000188 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1398 | +| iterations | 1363 | +| time_elapsed | 1996 | +| total_timesteps | 2791424 | +| train/ | | +| approx_kl | 0.010705757 | +| clip_fraction | 0.317 | +| clip_range | 0.0743 | +| entropy_loss | -7.1 | +| explained_variance | 0.414 | +| learning_rate | 4.93e-05 | +| loss | -0.0372 | +| n_updates | 21268 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000161 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1398 | +| iterations | 1364 | +| time_elapsed | 1998 | +| total_timesteps | 2793472 | +| train/ | | +| approx_kl | 0.010984584 | +| clip_fraction | 0.318 | +| clip_range | 0.0743 | +| entropy_loss | -7.33 | +| explained_variance | 0.35 | +| learning_rate | 4.93e-05 | +| loss | -0.0334 | +| n_updates | 21272 | +| policy_gradient_loss | -0.0219 | +| value_loss | 0.000139 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1398 | +| iterations | 1365 | +| time_elapsed | 1999 | +| total_timesteps | 2795520 | +| train/ | | +| approx_kl | 0.00972154 | +| clip_fraction | 0.342 | +| clip_range | 0.0743 | +| entropy_loss | -7.38 | +| explained_variance | -0.193 | +| learning_rate | 4.93e-05 | +| loss | -0.0332 | +| n_updates | 21276 | +| policy_gradient_loss | -0.0225 | +| value_loss | 7.02e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1398 | +| iterations | 1366 | +| time_elapsed | 2001 | +| total_timesteps | 2797568 | +| train/ | | +| approx_kl | 0.011310184 | +| clip_fraction | 0.318 | +| clip_range | 0.0743 | +| entropy_loss | -7.23 | +| explained_variance | 0.264 | +| learning_rate | 4.93e-05 | +| loss | -0.0322 | +| n_updates | 21280 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000185 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1398 | +| iterations | 1367 | +| time_elapsed | 2002 | +| total_timesteps | 2799616 | +| train/ | | +| approx_kl | 0.009826299 | +| clip_fraction | 0.306 | +| clip_range | 0.0743 | +| entropy_loss | -7.32 | +| explained_variance | -0.0593 | +| learning_rate | 4.93e-05 | +| loss | -0.0388 | +| n_updates | 21284 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000199 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1398 | +| iterations | 1368 | +| time_elapsed | 2003 | +| total_timesteps | 2801664 | +| train/ | | +| approx_kl | 0.011261181 | +| clip_fraction | 0.319 | +| clip_range | 0.0743 | +| entropy_loss | -6.97 | +| explained_variance | 0.434 | +| learning_rate | 4.93e-05 | +| loss | -0.0358 | +| n_updates | 21288 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.00022 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1398 | +| iterations | 1369 | +| time_elapsed | 2005 | +| total_timesteps | 2803712 | +| train/ | | +| approx_kl | 0.01264632 | +| clip_fraction | 0.345 | +| clip_range | 0.0743 | +| entropy_loss | -7.08 | +| explained_variance | 0.623 | +| learning_rate | 4.93e-05 | +| loss | -0.0395 | +| n_updates | 21292 | +| policy_gradient_loss | -0.0234 | +| value_loss | 7.65e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1398 | +| iterations | 1370 | +| time_elapsed | 2006 | +| total_timesteps | 2805760 | +| train/ | | +| approx_kl | 0.011318919 | +| clip_fraction | 0.299 | +| clip_range | 0.0743 | +| entropy_loss | -7.02 | +| explained_variance | 0.43 | +| learning_rate | 4.93e-05 | +| loss | -0.032 | +| n_updates | 21296 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000202 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1398 | +| iterations | 1371 | +| time_elapsed | 2008 | +| total_timesteps | 2807808 | +| train/ | | +| approx_kl | 0.011047004 | +| clip_fraction | 0.324 | +| clip_range | 0.0743 | +| entropy_loss | -7.07 | +| explained_variance | 0.333 | +| learning_rate | 4.93e-05 | +| loss | -0.0359 | +| n_updates | 21300 | +| policy_gradient_loss | -0.0226 | +| value_loss | 0.000114 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1398 | +| iterations | 1372 | +| time_elapsed | 2009 | +| total_timesteps | 2809856 | +| train/ | | +| approx_kl | 0.012373237 | +| clip_fraction | 0.36 | +| clip_range | 0.0743 | +| entropy_loss | -7.29 | +| explained_variance | -0.417 | +| learning_rate | 4.93e-05 | +| loss | -0.0382 | +| n_updates | 21304 | +| policy_gradient_loss | -0.0242 | +| value_loss | 6e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1398 | +| iterations | 1373 | +| time_elapsed | 2011 | +| total_timesteps | 2811904 | +| train/ | | +| approx_kl | 0.011780655 | +| clip_fraction | 0.292 | +| clip_range | 0.0743 | +| entropy_loss | -7.24 | +| explained_variance | 0.000619 | +| learning_rate | 4.93e-05 | +| loss | -0.0368 | +| n_updates | 21308 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000171 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1398 | +| iterations | 1374 | +| time_elapsed | 2012 | +| total_timesteps | 2813952 | +| train/ | | +| approx_kl | 0.011043941 | +| clip_fraction | 0.333 | +| clip_range | 0.0743 | +| entropy_loss | -7.26 | +| explained_variance | 0.183 | +| learning_rate | 4.93e-05 | +| loss | -0.0367 | +| n_updates | 21312 | +| policy_gradient_loss | -0.0226 | +| value_loss | 0.000139 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1398 | +| iterations | 1375 | +| time_elapsed | 2013 | +| total_timesteps | 2816000 | +| train/ | | +| approx_kl | 0.010814913 | +| clip_fraction | 0.327 | +| clip_range | 0.0743 | +| entropy_loss | -7.21 | +| explained_variance | 0.399 | +| learning_rate | 4.93e-05 | +| loss | -0.0327 | +| n_updates | 21316 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000143 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1398 | +| iterations | 1376 | +| time_elapsed | 2015 | +| total_timesteps | 2818048 | +| train/ | | +| approx_kl | 0.010485789 | +| clip_fraction | 0.305 | +| clip_range | 0.0743 | +| entropy_loss | -6.96 | +| explained_variance | 0.457 | +| learning_rate | 4.93e-05 | +| loss | -0.0302 | +| n_updates | 21320 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.0002 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1398 | +| iterations | 1377 | +| time_elapsed | 2016 | +| total_timesteps | 2820096 | +| train/ | | +| approx_kl | 0.010796692 | +| clip_fraction | 0.313 | +| clip_range | 0.0743 | +| entropy_loss | -7.15 | +| explained_variance | -0.0215 | +| learning_rate | 4.93e-05 | +| loss | -0.0339 | +| n_updates | 21324 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000116 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1398 | +| iterations | 1378 | +| time_elapsed | 2018 | +| total_timesteps | 2822144 | +| train/ | | +| approx_kl | 0.009465445 | +| clip_fraction | 0.274 | +| clip_range | 0.0743 | +| entropy_loss | -6.88 | +| explained_variance | 0.23 | +| learning_rate | 4.93e-05 | +| loss | -0.0298 | +| n_updates | 21328 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000317 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1398 | +| iterations | 1379 | +| time_elapsed | 2019 | +| total_timesteps | 2824192 | +| train/ | | +| approx_kl | 0.011514946 | +| clip_fraction | 0.332 | +| clip_range | 0.0743 | +| entropy_loss | -7.09 | +| explained_variance | 0.199 | +| learning_rate | 4.93e-05 | +| loss | -0.032 | +| n_updates | 21332 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.00023 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1398 | +| iterations | 1380 | +| time_elapsed | 2020 | +| total_timesteps | 2826240 | +| train/ | | +| approx_kl | 0.0115740765 | +| clip_fraction | 0.345 | +| clip_range | 0.0743 | +| entropy_loss | -7.38 | +| explained_variance | -0.456 | +| learning_rate | 4.93e-05 | +| loss | -0.0407 | +| n_updates | 21336 | +| policy_gradient_loss | -0.0243 | +| value_loss | 0.000127 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1398 | +| iterations | 1381 | +| time_elapsed | 2022 | +| total_timesteps | 2828288 | +| train/ | | +| approx_kl | 0.010235091 | +| clip_fraction | 0.313 | +| clip_range | 0.0743 | +| entropy_loss | -7.43 | +| explained_variance | -0.173 | +| learning_rate | 4.93e-05 | +| loss | -0.0366 | +| n_updates | 21340 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000137 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1398 | +| iterations | 1382 | +| time_elapsed | 2023 | +| total_timesteps | 2830336 | +| train/ | | +| approx_kl | 0.010668224 | +| clip_fraction | 0.307 | +| clip_range | 0.0743 | +| entropy_loss | -7.28 | +| explained_variance | 0.279 | +| learning_rate | 4.93e-05 | +| loss | -0.0361 | +| n_updates | 21344 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000158 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1398 | +| iterations | 1383 | +| time_elapsed | 2025 | +| total_timesteps | 2832384 | +| train/ | | +| approx_kl | 0.008548642 | +| clip_fraction | 0.29 | +| clip_range | 0.0743 | +| entropy_loss | -7.09 | +| explained_variance | 0.618 | +| learning_rate | 4.93e-05 | +| loss | -0.0357 | +| n_updates | 21348 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000101 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1398 | +| iterations | 1384 | +| time_elapsed | 2026 | +| total_timesteps | 2834432 | +| train/ | | +| approx_kl | 0.010358327 | +| clip_fraction | 0.285 | +| clip_range | 0.0743 | +| entropy_loss | -7.23 | +| explained_variance | 0.248 | +| learning_rate | 4.93e-05 | +| loss | -0.0295 | +| n_updates | 21352 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000196 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1398 | +| iterations | 1385 | +| time_elapsed | 2028 | +| total_timesteps | 2836480 | +| train/ | | +| approx_kl | 0.008359676 | +| clip_fraction | 0.3 | +| clip_range | 0.0743 | +| entropy_loss | -6.94 | +| explained_variance | 0.438 | +| learning_rate | 4.93e-05 | +| loss | -0.0261 | +| n_updates | 21356 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000287 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1398 | +| iterations | 1386 | +| time_elapsed | 2029 | +| total_timesteps | 2838528 | +| train/ | | +| approx_kl | 0.009950364 | +| clip_fraction | 0.298 | +| clip_range | 0.0743 | +| entropy_loss | -7.04 | +| explained_variance | 0.368 | +| learning_rate | 4.93e-05 | +| loss | -0.0245 | +| n_updates | 21360 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000408 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1398 | +| iterations | 1387 | +| time_elapsed | 2030 | +| total_timesteps | 2840576 | +| train/ | | +| approx_kl | 0.0106783025 | +| clip_fraction | 0.326 | +| clip_range | 0.0743 | +| entropy_loss | -7.06 | +| explained_variance | 0.376 | +| learning_rate | 4.93e-05 | +| loss | -0.0374 | +| n_updates | 21364 | +| policy_gradient_loss | -0.0238 | +| value_loss | 0.000133 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1398 | +| iterations | 1388 | +| time_elapsed | 2032 | +| total_timesteps | 2842624 | +| train/ | | +| approx_kl | 0.010482155 | +| clip_fraction | 0.353 | +| clip_range | 0.0743 | +| entropy_loss | -7.41 | +| explained_variance | -0.0269 | +| learning_rate | 4.93e-05 | +| loss | -0.0338 | +| n_updates | 21368 | +| policy_gradient_loss | -0.0219 | +| value_loss | 0.000136 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1398 | +| iterations | 1389 | +| time_elapsed | 2033 | +| total_timesteps | 2844672 | +| train/ | | +| approx_kl | 0.009574725 | +| clip_fraction | 0.294 | +| clip_range | 0.0743 | +| entropy_loss | -7.39 | +| explained_variance | 0.0217 | +| learning_rate | 4.93e-05 | +| loss | -0.0315 | +| n_updates | 21372 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000169 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1398 | +| iterations | 1390 | +| time_elapsed | 2035 | +| total_timesteps | 2846720 | +| train/ | | +| approx_kl | 0.010309238 | +| clip_fraction | 0.312 | +| clip_range | 0.0743 | +| entropy_loss | -7.15 | +| explained_variance | 0.285 | +| learning_rate | 4.93e-05 | +| loss | -0.0323 | +| n_updates | 21376 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000267 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1398 | +| iterations | 1391 | +| time_elapsed | 2036 | +| total_timesteps | 2848768 | +| train/ | | +| approx_kl | 0.010119751 | +| clip_fraction | 0.33 | +| clip_range | 0.0743 | +| entropy_loss | -7.22 | +| explained_variance | -0.296 | +| learning_rate | 4.93e-05 | +| loss | -0.0357 | +| n_updates | 21380 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000125 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1398 | +| iterations | 1392 | +| time_elapsed | 2038 | +| total_timesteps | 2850816 | +| train/ | | +| approx_kl | 0.011332698 | +| clip_fraction | 0.302 | +| clip_range | 0.0743 | +| entropy_loss | -7.33 | +| explained_variance | 0.00634 | +| learning_rate | 4.93e-05 | +| loss | -0.0346 | +| n_updates | 21384 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.0002 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1398 | +| iterations | 1393 | +| time_elapsed | 2039 | +| total_timesteps | 2852864 | +| train/ | | +| approx_kl | 0.012279319 | +| clip_fraction | 0.322 | +| clip_range | 0.0743 | +| entropy_loss | -6.99 | +| explained_variance | 0.249 | +| learning_rate | 4.93e-05 | +| loss | -0.0334 | +| n_updates | 21388 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000282 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1398 | +| iterations | 1394 | +| time_elapsed | 2041 | +| total_timesteps | 2854912 | +| train/ | | +| approx_kl | 0.012014636 | +| clip_fraction | 0.333 | +| clip_range | 0.0743 | +| entropy_loss | -7.33 | +| explained_variance | -0.206 | +| learning_rate | 4.93e-05 | +| loss | -0.0384 | +| n_updates | 21392 | +| policy_gradient_loss | -0.0225 | +| value_loss | 0.000162 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1398 | +| iterations | 1395 | +| time_elapsed | 2042 | +| total_timesteps | 2856960 | +| train/ | | +| approx_kl | 0.009452243 | +| clip_fraction | 0.319 | +| clip_range | 0.0743 | +| entropy_loss | -7.08 | +| explained_variance | 0.204 | +| learning_rate | 4.93e-05 | +| loss | -0.0352 | +| n_updates | 21396 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000146 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1398 | +| iterations | 1396 | +| time_elapsed | 2043 | +| total_timesteps | 2859008 | +| train/ | | +| approx_kl | 0.00953052 | +| clip_fraction | 0.314 | +| clip_range | 0.0743 | +| entropy_loss | -7.05 | +| explained_variance | 0.467 | +| learning_rate | 4.93e-05 | +| loss | -0.033 | +| n_updates | 21400 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000104 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1398 | +| iterations | 1397 | +| time_elapsed | 2045 | +| total_timesteps | 2861056 | +| train/ | | +| approx_kl | 0.009922073 | +| clip_fraction | 0.302 | +| clip_range | 0.0743 | +| entropy_loss | -7.12 | +| explained_variance | 0.294 | +| learning_rate | 4.93e-05 | +| loss | -0.0301 | +| n_updates | 21404 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000165 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1398 | +| iterations | 1398 | +| time_elapsed | 2047 | +| total_timesteps | 2863104 | +| train/ | | +| approx_kl | 0.010870855 | +| clip_fraction | 0.309 | +| clip_range | 0.0743 | +| entropy_loss | -7.13 | +| explained_variance | 0.217 | +| learning_rate | 4.93e-05 | +| loss | -0.0287 | +| n_updates | 21408 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000205 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1398 | +| iterations | 1399 | +| time_elapsed | 2048 | +| total_timesteps | 2865152 | +| train/ | | +| approx_kl | 0.008511398 | +| clip_fraction | 0.304 | +| clip_range | 0.0743 | +| entropy_loss | -7.22 | +| explained_variance | 0.15 | +| learning_rate | 4.93e-05 | +| loss | -0.0295 | +| n_updates | 21412 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000309 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1398 | +| iterations | 1400 | +| time_elapsed | 2049 | +| total_timesteps | 2867200 | +| train/ | | +| approx_kl | 0.011951163 | +| clip_fraction | 0.324 | +| clip_range | 0.0743 | +| entropy_loss | -7.07 | +| explained_variance | 0.572 | +| learning_rate | 4.93e-05 | +| loss | -0.0305 | +| n_updates | 21416 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000136 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1398 | +| iterations | 1401 | +| time_elapsed | 2051 | +| total_timesteps | 2869248 | +| train/ | | +| approx_kl | 0.010093292 | +| clip_fraction | 0.303 | +| clip_range | 0.0743 | +| entropy_loss | -7.46 | +| explained_variance | -0.188 | +| learning_rate | 4.93e-05 | +| loss | -0.0385 | +| n_updates | 21420 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.00011 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1398 | +| iterations | 1402 | +| time_elapsed | 2052 | +| total_timesteps | 2871296 | +| train/ | | +| approx_kl | 0.009834173 | +| clip_fraction | 0.31 | +| clip_range | 0.0743 | +| entropy_loss | -7.41 | +| explained_variance | -0.0685 | +| learning_rate | 4.93e-05 | +| loss | -0.0281 | +| n_updates | 21424 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000182 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1398 | +| iterations | 1403 | +| time_elapsed | 2054 | +| total_timesteps | 2873344 | +| train/ | | +| approx_kl | 0.0099555245 | +| clip_fraction | 0.303 | +| clip_range | 0.0743 | +| entropy_loss | -7.18 | +| explained_variance | 0.379 | +| learning_rate | 4.93e-05 | +| loss | -0.03 | +| n_updates | 21428 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000172 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1398 | +| iterations | 1404 | +| time_elapsed | 2055 | +| total_timesteps | 2875392 | +| train/ | | +| approx_kl | 0.0100144455 | +| clip_fraction | 0.289 | +| clip_range | 0.0743 | +| entropy_loss | -6.9 | +| explained_variance | 0.356 | +| learning_rate | 4.93e-05 | +| loss | -0.0326 | +| n_updates | 21432 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000408 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1398 | +| iterations | 1405 | +| time_elapsed | 2057 | +| total_timesteps | 2877440 | +| train/ | | +| approx_kl | 0.011596672 | +| clip_fraction | 0.326 | +| clip_range | 0.0743 | +| entropy_loss | -7.27 | +| explained_variance | 0.0445 | +| learning_rate | 4.93e-05 | +| loss | -0.0342 | +| n_updates | 21436 | +| policy_gradient_loss | -0.0227 | +| value_loss | 0.000151 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1398 | +| iterations | 1406 | +| time_elapsed | 2058 | +| total_timesteps | 2879488 | +| train/ | | +| approx_kl | 0.008679297 | +| clip_fraction | 0.308 | +| clip_range | 0.0743 | +| entropy_loss | -7.26 | +| explained_variance | 0.265 | +| learning_rate | 4.93e-05 | +| loss | -0.0382 | +| n_updates | 21440 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000154 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1398 | +| iterations | 1407 | +| time_elapsed | 2060 | +| total_timesteps | 2881536 | +| train/ | | +| approx_kl | 0.009699629 | +| clip_fraction | 0.307 | +| clip_range | 0.0743 | +| entropy_loss | -7.18 | +| explained_variance | -0.0246 | +| learning_rate | 4.93e-05 | +| loss | -0.0259 | +| n_updates | 21444 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000244 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1398 | +| iterations | 1408 | +| time_elapsed | 2061 | +| total_timesteps | 2883584 | +| train/ | | +| approx_kl | 0.00972704 | +| clip_fraction | 0.302 | +| clip_range | 0.0743 | +| entropy_loss | -7.11 | +| explained_variance | 0.356 | +| learning_rate | 4.93e-05 | +| loss | -0.0392 | +| n_updates | 21448 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000174 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1398 | +| iterations | 1409 | +| time_elapsed | 2062 | +| total_timesteps | 2885632 | +| train/ | | +| approx_kl | 0.009434382 | +| clip_fraction | 0.307 | +| clip_range | 0.0743 | +| entropy_loss | -7.09 | +| explained_variance | 0.54 | +| learning_rate | 4.93e-05 | +| loss | -0.0312 | +| n_updates | 21452 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000167 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1398 | +| iterations | 1410 | +| time_elapsed | 2064 | +| total_timesteps | 2887680 | +| train/ | | +| approx_kl | 0.012983668 | +| clip_fraction | 0.331 | +| clip_range | 0.0743 | +| entropy_loss | -7.16 | +| explained_variance | 0.292 | +| learning_rate | 4.93e-05 | +| loss | -0.0279 | +| n_updates | 21456 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000184 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1398 | +| iterations | 1411 | +| time_elapsed | 2065 | +| total_timesteps | 2889728 | +| train/ | | +| approx_kl | 0.010635151 | +| clip_fraction | 0.295 | +| clip_range | 0.0743 | +| entropy_loss | -7.14 | +| explained_variance | 0.282 | +| learning_rate | 4.93e-05 | +| loss | -0.0256 | +| n_updates | 21460 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000192 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1398 | +| iterations | 1412 | +| time_elapsed | 2067 | +| total_timesteps | 2891776 | +| train/ | | +| approx_kl | 0.010650981 | +| clip_fraction | 0.329 | +| clip_range | 0.0743 | +| entropy_loss | -7.39 | +| explained_variance | 0.196 | +| learning_rate | 4.93e-05 | +| loss | -0.0387 | +| n_updates | 21464 | +| policy_gradient_loss | -0.0238 | +| value_loss | 0.000126 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1398 | +| iterations | 1413 | +| time_elapsed | 2068 | +| total_timesteps | 2893824 | +| train/ | | +| approx_kl | 0.010807617 | +| clip_fraction | 0.306 | +| clip_range | 0.0743 | +| entropy_loss | -7.35 | +| explained_variance | -0.0454 | +| learning_rate | 4.93e-05 | +| loss | -0.0354 | +| n_updates | 21468 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000177 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.30e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1398 | +| iterations | 1414 | +| time_elapsed | 2070 | +| total_timesteps | 2895872 | +| train/ | | +| approx_kl | 0.0133497305 | +| clip_fraction | 0.326 | +| clip_range | 0.0743 | +| entropy_loss | -7.09 | +| explained_variance | 0.42 | +| learning_rate | 4.93e-05 | +| loss | -0.0313 | +| n_updates | 21472 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.00015 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1399 | +| iterations | 1415 | +| time_elapsed | 2071 | +| total_timesteps | 2897920 | +| train/ | | +| approx_kl | 0.011528328 | +| clip_fraction | 0.292 | +| clip_range | 0.0743 | +| entropy_loss | -7.11 | +| explained_variance | 0.0823 | +| learning_rate | 4.93e-05 | +| loss | -0.0319 | +| n_updates | 21476 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000335 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1399 | +| iterations | 1416 | +| time_elapsed | 2072 | +| total_timesteps | 2899968 | +| train/ | | +| approx_kl | 0.010281308 | +| clip_fraction | 0.314 | +| clip_range | 0.0743 | +| entropy_loss | -7.26 | +| explained_variance | 0.0527 | +| learning_rate | 4.93e-05 | +| loss | -0.0259 | +| n_updates | 21480 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000185 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1399 | +| iterations | 1417 | +| time_elapsed | 2074 | +| total_timesteps | 2902016 | +| train/ | | +| approx_kl | 0.011268977 | +| clip_fraction | 0.34 | +| clip_range | 0.0743 | +| entropy_loss | -7.08 | +| explained_variance | 0.19 | +| learning_rate | 4.93e-05 | +| loss | -0.0352 | +| n_updates | 21484 | +| policy_gradient_loss | -0.0225 | +| value_loss | 0.000188 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1399 | +| iterations | 1418 | +| time_elapsed | 2075 | +| total_timesteps | 2904064 | +| train/ | | +| approx_kl | 0.012003254 | +| clip_fraction | 0.311 | +| clip_range | 0.0743 | +| entropy_loss | -7.16 | +| explained_variance | 0.19 | +| learning_rate | 4.93e-05 | +| loss | -0.0287 | +| n_updates | 21488 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000229 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1399 | +| iterations | 1419 | +| time_elapsed | 2077 | +| total_timesteps | 2906112 | +| train/ | | +| approx_kl | 0.011377047 | +| clip_fraction | 0.333 | +| clip_range | 0.0743 | +| entropy_loss | -7.25 | +| explained_variance | 0.157 | +| learning_rate | 4.93e-05 | +| loss | -0.0318 | +| n_updates | 21492 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.00013 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.386 | +| time/ | | +| fps | 1399 | +| iterations | 1420 | +| time_elapsed | 2078 | +| total_timesteps | 2908160 | +| train/ | | +| approx_kl | 0.011291229 | +| clip_fraction | 0.318 | +| clip_range | 0.0743 | +| entropy_loss | -7.34 | +| explained_variance | 0.11 | +| learning_rate | 4.93e-05 | +| loss | -0.0337 | +| n_updates | 21496 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000118 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.386 | +| time/ | | +| fps | 1399 | +| iterations | 1421 | +| time_elapsed | 2079 | +| total_timesteps | 2910208 | +| train/ | | +| approx_kl | 0.009458536 | +| clip_fraction | 0.264 | +| clip_range | 0.0743 | +| entropy_loss | -6.86 | +| explained_variance | 0.463 | +| learning_rate | 4.93e-05 | +| loss | -0.0285 | +| n_updates | 21500 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000253 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.385 | +| time/ | | +| fps | 1399 | +| iterations | 1422 | +| time_elapsed | 2081 | +| total_timesteps | 2912256 | +| train/ | | +| approx_kl | 0.010915296 | +| clip_fraction | 0.35 | +| clip_range | 0.0743 | +| entropy_loss | -7.3 | +| explained_variance | -0.0573 | +| learning_rate | 4.93e-05 | +| loss | -0.0296 | +| n_updates | 21504 | +| policy_gradient_loss | -0.0229 | +| value_loss | 0.000122 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1399 | +| iterations | 1423 | +| time_elapsed | 2082 | +| total_timesteps | 2914304 | +| train/ | | +| approx_kl | 0.010845755 | +| clip_fraction | 0.327 | +| clip_range | 0.0743 | +| entropy_loss | -7.25 | +| explained_variance | 0.409 | +| learning_rate | 4.93e-05 | +| loss | -0.0344 | +| n_updates | 21508 | +| policy_gradient_loss | -0.023 | +| value_loss | 9.07e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1399 | +| iterations | 1424 | +| time_elapsed | 2084 | +| total_timesteps | 2916352 | +| train/ | | +| approx_kl | 0.011211824 | +| clip_fraction | 0.298 | +| clip_range | 0.0743 | +| entropy_loss | -7.14 | +| explained_variance | 0.499 | +| learning_rate | 4.93e-05 | +| loss | -0.0308 | +| n_updates | 21512 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.00015 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1399 | +| iterations | 1425 | +| time_elapsed | 2085 | +| total_timesteps | 2918400 | +| train/ | | +| approx_kl | 0.011106297 | +| clip_fraction | 0.293 | +| clip_range | 0.0743 | +| entropy_loss | -6.95 | +| explained_variance | 0.615 | +| learning_rate | 4.93e-05 | +| loss | -0.028 | +| n_updates | 21516 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000141 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1399 | +| iterations | 1426 | +| time_elapsed | 2087 | +| total_timesteps | 2920448 | +| train/ | | +| approx_kl | 0.011268942 | +| clip_fraction | 0.326 | +| clip_range | 0.0743 | +| entropy_loss | -7.36 | +| explained_variance | -0.0112 | +| learning_rate | 4.93e-05 | +| loss | -0.038 | +| n_updates | 21520 | +| policy_gradient_loss | -0.0223 | +| value_loss | 8.66e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1399 | +| iterations | 1427 | +| time_elapsed | 2088 | +| total_timesteps | 2922496 | +| train/ | | +| approx_kl | 0.012189403 | +| clip_fraction | 0.325 | +| clip_range | 0.0743 | +| entropy_loss | -7.25 | +| explained_variance | 0.468 | +| learning_rate | 4.93e-05 | +| loss | -0.0391 | +| n_updates | 21524 | +| policy_gradient_loss | -0.0229 | +| value_loss | 7.85e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1399 | +| iterations | 1428 | +| time_elapsed | 2090 | +| total_timesteps | 2924544 | +| train/ | | +| approx_kl | 0.010523747 | +| clip_fraction | 0.305 | +| clip_range | 0.0743 | +| entropy_loss | -7.45 | +| explained_variance | -0.123 | +| learning_rate | 4.93e-05 | +| loss | -0.0328 | +| n_updates | 21528 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.00014 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1399 | +| iterations | 1429 | +| time_elapsed | 2091 | +| total_timesteps | 2926592 | +| train/ | | +| approx_kl | 0.009955497 | +| clip_fraction | 0.288 | +| clip_range | 0.0743 | +| entropy_loss | -7.25 | +| explained_variance | 0.328 | +| learning_rate | 4.93e-05 | +| loss | -0.0274 | +| n_updates | 21532 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000164 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1399 | +| iterations | 1430 | +| time_elapsed | 2092 | +| total_timesteps | 2928640 | +| train/ | | +| approx_kl | 0.010338042 | +| clip_fraction | 0.279 | +| clip_range | 0.0743 | +| entropy_loss | -6.9 | +| explained_variance | 0.25 | +| learning_rate | 4.93e-05 | +| loss | -0.0348 | +| n_updates | 21536 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000268 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1399 | +| iterations | 1431 | +| time_elapsed | 2094 | +| total_timesteps | 2930688 | +| train/ | | +| approx_kl | 0.012419434 | +| clip_fraction | 0.354 | +| clip_range | 0.0743 | +| entropy_loss | -6.92 | +| explained_variance | 0.69 | +| learning_rate | 4.93e-05 | +| loss | -0.0394 | +| n_updates | 21540 | +| policy_gradient_loss | -0.0243 | +| value_loss | 8.08e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1399 | +| iterations | 1432 | +| time_elapsed | 2095 | +| total_timesteps | 2932736 | +| train/ | | +| approx_kl | 0.010914659 | +| clip_fraction | 0.324 | +| clip_range | 0.0743 | +| entropy_loss | -7.08 | +| explained_variance | 0.544 | +| learning_rate | 4.93e-05 | +| loss | -0.0303 | +| n_updates | 21544 | +| policy_gradient_loss | -0.0221 | +| value_loss | 8.51e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1399 | +| iterations | 1433 | +| time_elapsed | 2097 | +| total_timesteps | 2934784 | +| train/ | | +| approx_kl | 0.011528587 | +| clip_fraction | 0.301 | +| clip_range | 0.0743 | +| entropy_loss | -7.13 | +| explained_variance | 0.351 | +| learning_rate | 4.93e-05 | +| loss | -0.0365 | +| n_updates | 21548 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000204 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1399 | +| iterations | 1434 | +| time_elapsed | 2098 | +| total_timesteps | 2936832 | +| train/ | | +| approx_kl | 0.012202459 | +| clip_fraction | 0.314 | +| clip_range | 0.0743 | +| entropy_loss | -7.14 | +| explained_variance | 0.458 | +| learning_rate | 4.93e-05 | +| loss | -0.0329 | +| n_updates | 21552 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000129 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1399 | +| iterations | 1435 | +| time_elapsed | 2100 | +| total_timesteps | 2938880 | +| train/ | | +| approx_kl | 0.01138198 | +| clip_fraction | 0.324 | +| clip_range | 0.0743 | +| entropy_loss | -7.02 | +| explained_variance | 0.554 | +| learning_rate | 4.93e-05 | +| loss | -0.0299 | +| n_updates | 21556 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000109 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1399 | +| iterations | 1436 | +| time_elapsed | 2101 | +| total_timesteps | 2940928 | +| train/ | | +| approx_kl | 0.010663806 | +| clip_fraction | 0.308 | +| clip_range | 0.0743 | +| entropy_loss | -7.18 | +| explained_variance | 0.363 | +| learning_rate | 4.93e-05 | +| loss | -0.0339 | +| n_updates | 21560 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000119 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1399 | +| iterations | 1437 | +| time_elapsed | 2103 | +| total_timesteps | 2942976 | +| train/ | | +| approx_kl | 0.010701849 | +| clip_fraction | 0.31 | +| clip_range | 0.0743 | +| entropy_loss | -7.2 | +| explained_variance | -0.0796 | +| learning_rate | 4.93e-05 | +| loss | -0.0316 | +| n_updates | 21564 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000175 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1399 | +| iterations | 1438 | +| time_elapsed | 2104 | +| total_timesteps | 2945024 | +| train/ | | +| approx_kl | 0.011448511 | +| clip_fraction | 0.297 | +| clip_range | 0.0743 | +| entropy_loss | -6.94 | +| explained_variance | 0.33 | +| learning_rate | 4.93e-05 | +| loss | -0.027 | +| n_updates | 21568 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000204 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1399 | +| iterations | 1439 | +| time_elapsed | 2106 | +| total_timesteps | 2947072 | +| train/ | | +| approx_kl | 0.012589531 | +| clip_fraction | 0.321 | +| clip_range | 0.0743 | +| entropy_loss | -7.29 | +| explained_variance | -0.083 | +| learning_rate | 4.93e-05 | +| loss | -0.0376 | +| n_updates | 21572 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1399 | +| iterations | 1440 | +| time_elapsed | 2107 | +| total_timesteps | 2949120 | +| train/ | | +| approx_kl | 0.013294283 | +| clip_fraction | 0.364 | +| clip_range | 0.0743 | +| entropy_loss | -7.15 | +| explained_variance | 0.556 | +| learning_rate | 4.93e-05 | +| loss | -0.038 | +| n_updates | 21576 | +| policy_gradient_loss | -0.0244 | +| value_loss | 9.28e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1399 | +| iterations | 1441 | +| time_elapsed | 2108 | +| total_timesteps | 2951168 | +| train/ | | +| approx_kl | 0.01057757 | +| clip_fraction | 0.313 | +| clip_range | 0.0743 | +| entropy_loss | -7.33 | +| explained_variance | 0.0136 | +| learning_rate | 4.93e-05 | +| loss | -0.0313 | +| n_updates | 21580 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000235 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1399 | +| iterations | 1442 | +| time_elapsed | 2110 | +| total_timesteps | 2953216 | +| train/ | | +| approx_kl | 0.011172775 | +| clip_fraction | 0.318 | +| clip_range | 0.0743 | +| entropy_loss | -7.18 | +| explained_variance | 0.332 | +| learning_rate | 4.93e-05 | +| loss | -0.0315 | +| n_updates | 21584 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000153 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1399 | +| iterations | 1443 | +| time_elapsed | 2111 | +| total_timesteps | 2955264 | +| train/ | | +| approx_kl | 0.012048621 | +| clip_fraction | 0.317 | +| clip_range | 0.0743 | +| entropy_loss | -7.13 | +| explained_variance | 0.411 | +| learning_rate | 4.93e-05 | +| loss | -0.0393 | +| n_updates | 21588 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000139 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1399 | +| iterations | 1444 | +| time_elapsed | 2113 | +| total_timesteps | 2957312 | +| train/ | | +| approx_kl | 0.011499447 | +| clip_fraction | 0.311 | +| clip_range | 0.0743 | +| entropy_loss | -7.16 | +| explained_variance | 0.353 | +| learning_rate | 4.93e-05 | +| loss | -0.0325 | +| n_updates | 21592 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000163 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1399 | +| iterations | 1445 | +| time_elapsed | 2114 | +| total_timesteps | 2959360 | +| train/ | | +| approx_kl | 0.010855239 | +| clip_fraction | 0.304 | +| clip_range | 0.0743 | +| entropy_loss | -6.84 | +| explained_variance | 0.466 | +| learning_rate | 4.93e-05 | +| loss | -0.0252 | +| n_updates | 21596 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000244 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1399 | +| iterations | 1446 | +| time_elapsed | 2115 | +| total_timesteps | 2961408 | +| train/ | | +| approx_kl | 0.011611382 | +| clip_fraction | 0.322 | +| clip_range | 0.0743 | +| entropy_loss | -7 | +| explained_variance | 0.432 | +| learning_rate | 4.93e-05 | +| loss | -0.0351 | +| n_updates | 21600 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000192 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1399 | +| iterations | 1447 | +| time_elapsed | 2117 | +| total_timesteps | 2963456 | +| train/ | | +| approx_kl | 0.012567433 | +| clip_fraction | 0.335 | +| clip_range | 0.0743 | +| entropy_loss | -7.2 | +| explained_variance | 0.463 | +| learning_rate | 4.93e-05 | +| loss | -0.0337 | +| n_updates | 21604 | +| policy_gradient_loss | -0.0226 | +| value_loss | 0.000149 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1399 | +| iterations | 1448 | +| time_elapsed | 2118 | +| total_timesteps | 2965504 | +| train/ | | +| approx_kl | 0.011597086 | +| clip_fraction | 0.333 | +| clip_range | 0.0743 | +| entropy_loss | -7.05 | +| explained_variance | 0.488 | +| learning_rate | 4.93e-05 | +| loss | -0.042 | +| n_updates | 21608 | +| policy_gradient_loss | -0.0227 | +| value_loss | 8.85e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1399 | +| iterations | 1449 | +| time_elapsed | 2120 | +| total_timesteps | 2967552 | +| train/ | | +| approx_kl | 0.009542827 | +| clip_fraction | 0.313 | +| clip_range | 0.0743 | +| entropy_loss | -7 | +| explained_variance | 0.302 | +| learning_rate | 4.93e-05 | +| loss | -0.0355 | +| n_updates | 21612 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000334 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1399 | +| iterations | 1450 | +| time_elapsed | 2121 | +| total_timesteps | 2969600 | +| train/ | | +| approx_kl | 0.011167909 | +| clip_fraction | 0.309 | +| clip_range | 0.0743 | +| entropy_loss | -7.05 | +| explained_variance | 0.215 | +| learning_rate | 4.93e-05 | +| loss | -0.0321 | +| n_updates | 21616 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000248 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1399 | +| iterations | 1451 | +| time_elapsed | 2123 | +| total_timesteps | 2971648 | +| train/ | | +| approx_kl | 0.012588331 | +| clip_fraction | 0.343 | +| clip_range | 0.0743 | +| entropy_loss | -7.29 | +| explained_variance | 0.127 | +| learning_rate | 4.93e-05 | +| loss | -0.0407 | +| n_updates | 21620 | +| policy_gradient_loss | -0.0233 | +| value_loss | 0.000136 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1399 | +| iterations | 1452 | +| time_elapsed | 2124 | +| total_timesteps | 2973696 | +| train/ | | +| approx_kl | 0.013115948 | +| clip_fraction | 0.344 | +| clip_range | 0.0743 | +| entropy_loss | -7.34 | +| explained_variance | -0.165 | +| learning_rate | 4.93e-05 | +| loss | -0.0416 | +| n_updates | 21624 | +| policy_gradient_loss | -0.0247 | +| value_loss | 0.000137 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1399 | +| iterations | 1453 | +| time_elapsed | 2126 | +| total_timesteps | 2975744 | +| train/ | | +| approx_kl | 0.012381898 | +| clip_fraction | 0.356 | +| clip_range | 0.0743 | +| entropy_loss | -7.37 | +| explained_variance | -0.212 | +| learning_rate | 4.93e-05 | +| loss | -0.0439 | +| n_updates | 21628 | +| policy_gradient_loss | -0.0241 | +| value_loss | 8.4e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1399 | +| iterations | 1454 | +| time_elapsed | 2127 | +| total_timesteps | 2977792 | +| train/ | | +| approx_kl | 0.011163612 | +| clip_fraction | 0.317 | +| clip_range | 0.0743 | +| entropy_loss | -7.11 | +| explained_variance | 0.0954 | +| learning_rate | 4.93e-05 | +| loss | -0.0306 | +| n_updates | 21632 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000246 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1399 | +| iterations | 1455 | +| time_elapsed | 2128 | +| total_timesteps | 2979840 | +| train/ | | +| approx_kl | 0.0101157995 | +| clip_fraction | 0.307 | +| clip_range | 0.0743 | +| entropy_loss | -6.68 | +| explained_variance | 0.526 | +| learning_rate | 4.93e-05 | +| loss | -0.0242 | +| n_updates | 21636 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000224 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1399 | +| iterations | 1456 | +| time_elapsed | 2130 | +| total_timesteps | 2981888 | +| train/ | | +| approx_kl | 0.010505377 | +| clip_fraction | 0.317 | +| clip_range | 0.0743 | +| entropy_loss | -7.24 | +| explained_variance | -0.0658 | +| learning_rate | 4.93e-05 | +| loss | -0.0313 | +| n_updates | 21640 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000245 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1399 | +| iterations | 1457 | +| time_elapsed | 2131 | +| total_timesteps | 2983936 | +| train/ | | +| approx_kl | 0.0119907325 | +| clip_fraction | 0.337 | +| clip_range | 0.0743 | +| entropy_loss | -7.02 | +| explained_variance | 0.338 | +| learning_rate | 4.93e-05 | +| loss | -0.0311 | +| n_updates | 21644 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000142 | +------------------------------------------ +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1399 | +| iterations | 1458 | +| time_elapsed | 2133 | +| total_timesteps | 2985984 | +| train/ | | +| approx_kl | 0.0123178 | +| clip_fraction | 0.328 | +| clip_range | 0.0743 | +| entropy_loss | -7.2 | +| explained_variance | 0.312 | +| learning_rate | 4.93e-05 | +| loss | -0.0356 | +| n_updates | 21648 | +| policy_gradient_loss | -0.0219 | +| value_loss | 0.000149 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1399 | +| iterations | 1459 | +| time_elapsed | 2134 | +| total_timesteps | 2988032 | +| train/ | | +| approx_kl | 0.011523663 | +| clip_fraction | 0.324 | +| clip_range | 0.0743 | +| entropy_loss | -7.36 | +| explained_variance | -0.0801 | +| learning_rate | 4.93e-05 | +| loss | -0.033 | +| n_updates | 21652 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000181 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1399 | +| iterations | 1460 | +| time_elapsed | 2135 | +| total_timesteps | 2990080 | +| train/ | | +| approx_kl | 0.011118571 | +| clip_fraction | 0.301 | +| clip_range | 0.0743 | +| entropy_loss | -6.94 | +| explained_variance | 0.352 | +| learning_rate | 4.93e-05 | +| loss | -0.0275 | +| n_updates | 21656 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.00017 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1399 | +| iterations | 1461 | +| time_elapsed | 2137 | +| total_timesteps | 2992128 | +| train/ | | +| approx_kl | 0.01286754 | +| clip_fraction | 0.36 | +| clip_range | 0.0743 | +| entropy_loss | -7.05 | +| explained_variance | 0.697 | +| learning_rate | 4.93e-05 | +| loss | -0.0381 | +| n_updates | 21660 | +| policy_gradient_loss | -0.0243 | +| value_loss | 6.4e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1399 | +| iterations | 1462 | +| time_elapsed | 2138 | +| total_timesteps | 2994176 | +| train/ | | +| approx_kl | 0.012490708 | +| clip_fraction | 0.301 | +| clip_range | 0.0743 | +| entropy_loss | -7.21 | +| explained_variance | 0.24 | +| learning_rate | 4.93e-05 | +| loss | -0.024 | +| n_updates | 21664 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.00022 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1399 | +| iterations | 1463 | +| time_elapsed | 2140 | +| total_timesteps | 2996224 | +| train/ | | +| approx_kl | 0.012221048 | +| clip_fraction | 0.292 | +| clip_range | 0.0743 | +| entropy_loss | -7.12 | +| explained_variance | 0.393 | +| learning_rate | 4.93e-05 | +| loss | -0.0316 | +| n_updates | 21668 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000169 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1399 | +| iterations | 1464 | +| time_elapsed | 2141 | +| total_timesteps | 2998272 | +| train/ | | +| approx_kl | 0.010428615 | +| clip_fraction | 0.303 | +| clip_range | 0.0743 | +| entropy_loss | -6.9 | +| explained_variance | 0.505 | +| learning_rate | 4.93e-05 | +| loss | -0.0337 | +| n_updates | 21672 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000206 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1399 | +| iterations | 1465 | +| time_elapsed | 2143 | +| total_timesteps | 3000320 | +| train/ | | +| approx_kl | 0.011610151 | +| clip_fraction | 0.338 | +| clip_range | 0.0743 | +| entropy_loss | -7.21 | +| explained_variance | 0.49 | +| learning_rate | 4.93e-05 | +| loss | -0.0337 | +| n_updates | 21676 | +| policy_gradient_loss | -0.0239 | +| value_loss | 6.67e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1400 | +| iterations | 1466 | +| time_elapsed | 2144 | +| total_timesteps | 3002368 | +| train/ | | +| approx_kl | 0.011892984 | +| clip_fraction | 0.325 | +| clip_range | 0.0742 | +| entropy_loss | -7.36 | +| explained_variance | -0.277 | +| learning_rate | 4.93e-05 | +| loss | -0.0341 | +| n_updates | 21680 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000104 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1400 | +| iterations | 1467 | +| time_elapsed | 2145 | +| total_timesteps | 3004416 | +| train/ | | +| approx_kl | 0.0104594 | +| clip_fraction | 0.321 | +| clip_range | 0.0742 | +| entropy_loss | -7.35 | +| explained_variance | -0.122 | +| learning_rate | 4.93e-05 | +| loss | -0.0372 | +| n_updates | 21684 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000113 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1400 | +| iterations | 1468 | +| time_elapsed | 2147 | +| total_timesteps | 3006464 | +| train/ | | +| approx_kl | 0.010937018 | +| clip_fraction | 0.286 | +| clip_range | 0.0742 | +| entropy_loss | -7.04 | +| explained_variance | 0.286 | +| learning_rate | 4.93e-05 | +| loss | -0.0275 | +| n_updates | 21688 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.00025 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1400 | +| iterations | 1469 | +| time_elapsed | 2148 | +| total_timesteps | 3008512 | +| train/ | | +| approx_kl | 0.009977108 | +| clip_fraction | 0.329 | +| clip_range | 0.0742 | +| entropy_loss | -7.1 | +| explained_variance | 0.308 | +| learning_rate | 4.93e-05 | +| loss | -0.0291 | +| n_updates | 21692 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000142 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1400 | +| iterations | 1470 | +| time_elapsed | 2150 | +| total_timesteps | 3010560 | +| train/ | | +| approx_kl | 0.009311641 | +| clip_fraction | 0.297 | +| clip_range | 0.0742 | +| entropy_loss | -7.09 | +| explained_variance | 0.335 | +| learning_rate | 4.93e-05 | +| loss | -0.0274 | +| n_updates | 21696 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000259 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1400 | +| iterations | 1471 | +| time_elapsed | 2151 | +| total_timesteps | 3012608 | +| train/ | | +| approx_kl | 0.011590245 | +| clip_fraction | 0.322 | +| clip_range | 0.0742 | +| entropy_loss | -7.09 | +| explained_variance | 0.526 | +| learning_rate | 4.93e-05 | +| loss | -0.0334 | +| n_updates | 21700 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000135 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1400 | +| iterations | 1472 | +| time_elapsed | 2153 | +| total_timesteps | 3014656 | +| train/ | | +| approx_kl | 0.008396119 | +| clip_fraction | 0.288 | +| clip_range | 0.0742 | +| entropy_loss | -6.81 | +| explained_variance | 0.421 | +| learning_rate | 4.93e-05 | +| loss | -0.0266 | +| n_updates | 21704 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000335 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1400 | +| iterations | 1473 | +| time_elapsed | 2154 | +| total_timesteps | 3016704 | +| train/ | | +| approx_kl | 0.010254018 | +| clip_fraction | 0.321 | +| clip_range | 0.0742 | +| entropy_loss | -7.32 | +| explained_variance | -0.248 | +| learning_rate | 4.93e-05 | +| loss | -0.0326 | +| n_updates | 21708 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000104 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1400 | +| iterations | 1474 | +| time_elapsed | 2155 | +| total_timesteps | 3018752 | +| train/ | | +| approx_kl | 0.009669515 | +| clip_fraction | 0.312 | +| clip_range | 0.0742 | +| entropy_loss | -7.09 | +| explained_variance | 0.317 | +| learning_rate | 4.93e-05 | +| loss | -0.0336 | +| n_updates | 21712 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000259 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1400 | +| iterations | 1475 | +| time_elapsed | 2157 | +| total_timesteps | 3020800 | +| train/ | | +| approx_kl | 0.011818174 | +| clip_fraction | 0.318 | +| clip_range | 0.0742 | +| entropy_loss | -7.31 | +| explained_variance | 0.346 | +| learning_rate | 4.93e-05 | +| loss | -0.0337 | +| n_updates | 21716 | +| policy_gradient_loss | -0.0222 | +| value_loss | 9.67e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1400 | +| iterations | 1476 | +| time_elapsed | 2158 | +| total_timesteps | 3022848 | +| train/ | | +| approx_kl | 0.012261304 | +| clip_fraction | 0.311 | +| clip_range | 0.0742 | +| entropy_loss | -7.29 | +| explained_variance | 0.147 | +| learning_rate | 4.93e-05 | +| loss | -0.0306 | +| n_updates | 21720 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000335 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1400 | +| iterations | 1477 | +| time_elapsed | 2160 | +| total_timesteps | 3024896 | +| train/ | | +| approx_kl | 0.010490024 | +| clip_fraction | 0.324 | +| clip_range | 0.0742 | +| entropy_loss | -7.14 | +| explained_variance | 0.0737 | +| learning_rate | 4.93e-05 | +| loss | -0.0314 | +| n_updates | 21724 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000331 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1400 | +| iterations | 1478 | +| time_elapsed | 2161 | +| total_timesteps | 3026944 | +| train/ | | +| approx_kl | 0.013589619 | +| clip_fraction | 0.349 | +| clip_range | 0.0742 | +| entropy_loss | -7.39 | +| explained_variance | -0.389 | +| learning_rate | 4.93e-05 | +| loss | -0.041 | +| n_updates | 21728 | +| policy_gradient_loss | -0.0259 | +| value_loss | 7.99e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1400 | +| iterations | 1479 | +| time_elapsed | 2163 | +| total_timesteps | 3028992 | +| train/ | | +| approx_kl | 0.010130636 | +| clip_fraction | 0.331 | +| clip_range | 0.0742 | +| entropy_loss | -6.74 | +| explained_variance | 0.139 | +| learning_rate | 4.93e-05 | +| loss | -0.0354 | +| n_updates | 21732 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000397 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1400 | +| iterations | 1480 | +| time_elapsed | 2164 | +| total_timesteps | 3031040 | +| train/ | | +| approx_kl | 0.012758796 | +| clip_fraction | 0.349 | +| clip_range | 0.0742 | +| entropy_loss | -7.4 | +| explained_variance | -0.0897 | +| learning_rate | 4.93e-05 | +| loss | -0.0397 | +| n_updates | 21736 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000126 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1400 | +| iterations | 1481 | +| time_elapsed | 2166 | +| total_timesteps | 3033088 | +| train/ | | +| approx_kl | 0.0117168445 | +| clip_fraction | 0.309 | +| clip_range | 0.0742 | +| entropy_loss | -7.48 | +| explained_variance | -0.0341 | +| learning_rate | 4.93e-05 | +| loss | -0.0344 | +| n_updates | 21740 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000209 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1400 | +| iterations | 1482 | +| time_elapsed | 2167 | +| total_timesteps | 3035136 | +| train/ | | +| approx_kl | 0.010444437 | +| clip_fraction | 0.317 | +| clip_range | 0.0742 | +| entropy_loss | -7.41 | +| explained_variance | -0.0945 | +| learning_rate | 4.93e-05 | +| loss | -0.0264 | +| n_updates | 21744 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000287 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1400 | +| iterations | 1483 | +| time_elapsed | 2168 | +| total_timesteps | 3037184 | +| train/ | | +| approx_kl | 0.011577336 | +| clip_fraction | 0.327 | +| clip_range | 0.0742 | +| entropy_loss | -6.97 | +| explained_variance | 0.372 | +| learning_rate | 4.93e-05 | +| loss | -0.0305 | +| n_updates | 21748 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000223 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1400 | +| iterations | 1484 | +| time_elapsed | 2170 | +| total_timesteps | 3039232 | +| train/ | | +| approx_kl | 0.013114179 | +| clip_fraction | 0.348 | +| clip_range | 0.0742 | +| entropy_loss | -7.03 | +| explained_variance | 0.509 | +| learning_rate | 4.93e-05 | +| loss | -0.0331 | +| n_updates | 21752 | +| policy_gradient_loss | -0.0223 | +| value_loss | 0.00014 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1400 | +| iterations | 1485 | +| time_elapsed | 2171 | +| total_timesteps | 3041280 | +| train/ | | +| approx_kl | 0.0130122155 | +| clip_fraction | 0.318 | +| clip_range | 0.0742 | +| entropy_loss | -7 | +| explained_variance | 0.214 | +| learning_rate | 4.93e-05 | +| loss | -0.033 | +| n_updates | 21756 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000217 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1400 | +| iterations | 1486 | +| time_elapsed | 2173 | +| total_timesteps | 3043328 | +| train/ | | +| approx_kl | 0.010913977 | +| clip_fraction | 0.327 | +| clip_range | 0.0742 | +| entropy_loss | -7.27 | +| explained_variance | 0.353 | +| learning_rate | 4.93e-05 | +| loss | -0.0292 | +| n_updates | 21760 | +| policy_gradient_loss | -0.0226 | +| value_loss | 0.000113 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1400 | +| iterations | 1487 | +| time_elapsed | 2174 | +| total_timesteps | 3045376 | +| train/ | | +| approx_kl | 0.011429181 | +| clip_fraction | 0.325 | +| clip_range | 0.0742 | +| entropy_loss | -7.18 | +| explained_variance | 0.208 | +| learning_rate | 4.93e-05 | +| loss | -0.0342 | +| n_updates | 21764 | +| policy_gradient_loss | -0.022 | +| value_loss | 0.000158 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1400 | +| iterations | 1488 | +| time_elapsed | 2175 | +| total_timesteps | 3047424 | +| train/ | | +| approx_kl | 0.011151364 | +| clip_fraction | 0.318 | +| clip_range | 0.0742 | +| entropy_loss | -7.17 | +| explained_variance | 0.325 | +| learning_rate | 4.93e-05 | +| loss | -0.0306 | +| n_updates | 21768 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000254 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1400 | +| iterations | 1489 | +| time_elapsed | 2177 | +| total_timesteps | 3049472 | +| train/ | | +| approx_kl | 0.012754964 | +| clip_fraction | 0.362 | +| clip_range | 0.0742 | +| entropy_loss | -7.28 | +| explained_variance | 0.0756 | +| learning_rate | 4.93e-05 | +| loss | -0.0435 | +| n_updates | 21772 | +| policy_gradient_loss | -0.0262 | +| value_loss | 6.77e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1400 | +| iterations | 1490 | +| time_elapsed | 2178 | +| total_timesteps | 3051520 | +| train/ | | +| approx_kl | 0.010695929 | +| clip_fraction | 0.319 | +| clip_range | 0.0742 | +| entropy_loss | -7.46 | +| explained_variance | -0.0529 | +| learning_rate | 4.93e-05 | +| loss | -0.0321 | +| n_updates | 21776 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000241 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1400 | +| iterations | 1491 | +| time_elapsed | 2180 | +| total_timesteps | 3053568 | +| train/ | | +| approx_kl | 0.013068401 | +| clip_fraction | 0.323 | +| clip_range | 0.0742 | +| entropy_loss | -7.19 | +| explained_variance | 0.201 | +| learning_rate | 4.93e-05 | +| loss | -0.0327 | +| n_updates | 21780 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000229 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1400 | +| iterations | 1492 | +| time_elapsed | 2181 | +| total_timesteps | 3055616 | +| train/ | | +| approx_kl | 0.010640283 | +| clip_fraction | 0.321 | +| clip_range | 0.0742 | +| entropy_loss | -7.26 | +| explained_variance | 0.102 | +| learning_rate | 4.93e-05 | +| loss | -0.0359 | +| n_updates | 21784 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000197 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1400 | +| iterations | 1493 | +| time_elapsed | 2183 | +| total_timesteps | 3057664 | +| train/ | | +| approx_kl | 0.011071388 | +| clip_fraction | 0.288 | +| clip_range | 0.0742 | +| entropy_loss | -6.83 | +| explained_variance | 0.351 | +| learning_rate | 4.93e-05 | +| loss | -0.03 | +| n_updates | 21788 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000231 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1400 | +| iterations | 1494 | +| time_elapsed | 2184 | +| total_timesteps | 3059712 | +| train/ | | +| approx_kl | 0.011043636 | +| clip_fraction | 0.317 | +| clip_range | 0.0742 | +| entropy_loss | -7.29 | +| explained_variance | 0.308 | +| learning_rate | 4.93e-05 | +| loss | -0.0336 | +| n_updates | 21792 | +| policy_gradient_loss | -0.0222 | +| value_loss | 0.000134 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1400 | +| iterations | 1495 | +| time_elapsed | 2185 | +| total_timesteps | 3061760 | +| train/ | | +| approx_kl | 0.010930965 | +| clip_fraction | 0.311 | +| clip_range | 0.0742 | +| entropy_loss | -7.08 | +| explained_variance | 0.547 | +| learning_rate | 4.93e-05 | +| loss | -0.0274 | +| n_updates | 21796 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.00011 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1400 | +| iterations | 1496 | +| time_elapsed | 2187 | +| total_timesteps | 3063808 | +| train/ | | +| approx_kl | 0.011006381 | +| clip_fraction | 0.283 | +| clip_range | 0.0742 | +| entropy_loss | -7.25 | +| explained_variance | -0.185 | +| learning_rate | 4.93e-05 | +| loss | -0.0321 | +| n_updates | 21800 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000183 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1400 | +| iterations | 1497 | +| time_elapsed | 2188 | +| total_timesteps | 3065856 | +| train/ | | +| approx_kl | 0.009251899 | +| clip_fraction | 0.332 | +| clip_range | 0.0742 | +| entropy_loss | -6.82 | +| explained_variance | 0.129 | +| learning_rate | 4.93e-05 | +| loss | -0.0348 | +| n_updates | 21804 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000416 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1400 | +| iterations | 1498 | +| time_elapsed | 2190 | +| total_timesteps | 3067904 | +| train/ | | +| approx_kl | 0.012180117 | +| clip_fraction | 0.368 | +| clip_range | 0.0742 | +| entropy_loss | -7.21 | +| explained_variance | 0.17 | +| learning_rate | 4.93e-05 | +| loss | -0.0414 | +| n_updates | 21808 | +| policy_gradient_loss | -0.0249 | +| value_loss | 0.000116 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1400 | +| iterations | 1499 | +| time_elapsed | 2191 | +| total_timesteps | 3069952 | +| train/ | | +| approx_kl | 0.011476023 | +| clip_fraction | 0.328 | +| clip_range | 0.0742 | +| entropy_loss | -7.29 | +| explained_variance | 0.222 | +| learning_rate | 4.93e-05 | +| loss | -0.0296 | +| n_updates | 21812 | +| policy_gradient_loss | -0.0219 | +| value_loss | 0.000104 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1400 | +| iterations | 1500 | +| time_elapsed | 2193 | +| total_timesteps | 3072000 | +| train/ | | +| approx_kl | 0.010510404 | +| clip_fraction | 0.296 | +| clip_range | 0.0742 | +| entropy_loss | -7.14 | +| explained_variance | 0.368 | +| learning_rate | 4.93e-05 | +| loss | -0.031 | +| n_updates | 21816 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000286 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1400 | +| iterations | 1501 | +| time_elapsed | 2194 | +| total_timesteps | 3074048 | +| train/ | | +| approx_kl | 0.010641323 | +| clip_fraction | 0.327 | +| clip_range | 0.0742 | +| entropy_loss | -7.16 | +| explained_variance | 0.329 | +| learning_rate | 4.93e-05 | +| loss | -0.0377 | +| n_updates | 21820 | +| policy_gradient_loss | -0.0221 | +| value_loss | 0.000128 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1400 | +| iterations | 1502 | +| time_elapsed | 2196 | +| total_timesteps | 3076096 | +| train/ | | +| approx_kl | 0.011397472 | +| clip_fraction | 0.314 | +| clip_range | 0.0742 | +| entropy_loss | -7.46 | +| explained_variance | 0.0195 | +| learning_rate | 4.93e-05 | +| loss | -0.0325 | +| n_updates | 21824 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000207 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1400 | +| iterations | 1503 | +| time_elapsed | 2197 | +| total_timesteps | 3078144 | +| train/ | | +| approx_kl | 0.011426583 | +| clip_fraction | 0.33 | +| clip_range | 0.0742 | +| entropy_loss | -7.32 | +| explained_variance | 0.211 | +| learning_rate | 4.93e-05 | +| loss | -0.0335 | +| n_updates | 21828 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000154 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1400 | +| iterations | 1504 | +| time_elapsed | 2198 | +| total_timesteps | 3080192 | +| train/ | | +| approx_kl | 0.010121904 | +| clip_fraction | 0.314 | +| clip_range | 0.0742 | +| entropy_loss | -7.09 | +| explained_variance | 0.26 | +| learning_rate | 4.93e-05 | +| loss | -0.0378 | +| n_updates | 21832 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000205 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1400 | +| iterations | 1505 | +| time_elapsed | 2200 | +| total_timesteps | 3082240 | +| train/ | | +| approx_kl | 0.0105442945 | +| clip_fraction | 0.298 | +| clip_range | 0.0742 | +| entropy_loss | -7.04 | +| explained_variance | 0.306 | +| learning_rate | 4.93e-05 | +| loss | -0.0273 | +| n_updates | 21836 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000204 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1400 | +| iterations | 1506 | +| time_elapsed | 2201 | +| total_timesteps | 3084288 | +| train/ | | +| approx_kl | 0.011249172 | +| clip_fraction | 0.297 | +| clip_range | 0.0742 | +| entropy_loss | -6.99 | +| explained_variance | 0.378 | +| learning_rate | 4.93e-05 | +| loss | -0.0271 | +| n_updates | 21840 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000215 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1400 | +| iterations | 1507 | +| time_elapsed | 2203 | +| total_timesteps | 3086336 | +| train/ | | +| approx_kl | 0.011643023 | +| clip_fraction | 0.371 | +| clip_range | 0.0742 | +| entropy_loss | -7.15 | +| explained_variance | 0.462 | +| learning_rate | 4.93e-05 | +| loss | -0.0429 | +| n_updates | 21844 | +| policy_gradient_loss | -0.0271 | +| value_loss | 5.97e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1400 | +| iterations | 1508 | +| time_elapsed | 2204 | +| total_timesteps | 3088384 | +| train/ | | +| approx_kl | 0.0108684655 | +| clip_fraction | 0.328 | +| clip_range | 0.0742 | +| entropy_loss | -7.2 | +| explained_variance | 0.2 | +| learning_rate | 4.93e-05 | +| loss | -0.0299 | +| n_updates | 21848 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000284 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1400 | +| iterations | 1509 | +| time_elapsed | 2206 | +| total_timesteps | 3090432 | +| train/ | | +| approx_kl | 0.011726733 | +| clip_fraction | 0.344 | +| clip_range | 0.0742 | +| entropy_loss | -7.34 | +| explained_variance | -0.317 | +| learning_rate | 4.93e-05 | +| loss | -0.0433 | +| n_updates | 21852 | +| policy_gradient_loss | -0.0272 | +| value_loss | 5.86e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1400 | +| iterations | 1510 | +| time_elapsed | 2207 | +| total_timesteps | 3092480 | +| train/ | | +| approx_kl | 0.010720454 | +| clip_fraction | 0.329 | +| clip_range | 0.0742 | +| entropy_loss | -7.26 | +| explained_variance | 0.21 | +| learning_rate | 4.93e-05 | +| loss | -0.0379 | +| n_updates | 21856 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000156 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1400 | +| iterations | 1511 | +| time_elapsed | 2209 | +| total_timesteps | 3094528 | +| train/ | | +| approx_kl | 0.010889508 | +| clip_fraction | 0.32 | +| clip_range | 0.0742 | +| entropy_loss | -6.82 | +| explained_variance | 0.613 | +| learning_rate | 4.93e-05 | +| loss | -0.0324 | +| n_updates | 21860 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.00015 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1400 | +| iterations | 1512 | +| time_elapsed | 2210 | +| total_timesteps | 3096576 | +| train/ | | +| approx_kl | 0.0113864485 | +| clip_fraction | 0.315 | +| clip_range | 0.0742 | +| entropy_loss | -7 | +| explained_variance | 0.262 | +| learning_rate | 4.93e-05 | +| loss | -0.0334 | +| n_updates | 21864 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000129 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1400 | +| iterations | 1513 | +| time_elapsed | 2211 | +| total_timesteps | 3098624 | +| train/ | | +| approx_kl | 0.012312012 | +| clip_fraction | 0.306 | +| clip_range | 0.0742 | +| entropy_loss | -7.1 | +| explained_variance | 0.355 | +| learning_rate | 4.93e-05 | +| loss | -0.0321 | +| n_updates | 21868 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000236 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1400 | +| iterations | 1514 | +| time_elapsed | 2213 | +| total_timesteps | 3100672 | +| train/ | | +| approx_kl | 0.0111770425 | +| clip_fraction | 0.31 | +| clip_range | 0.0742 | +| entropy_loss | -7.44 | +| explained_variance | -0.0713 | +| learning_rate | 4.93e-05 | +| loss | -0.0313 | +| n_updates | 21872 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000184 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1400 | +| iterations | 1515 | +| time_elapsed | 2214 | +| total_timesteps | 3102720 | +| train/ | | +| approx_kl | 0.010700666 | +| clip_fraction | 0.307 | +| clip_range | 0.0742 | +| entropy_loss | -7.23 | +| explained_variance | -0.181 | +| learning_rate | 4.93e-05 | +| loss | -0.0313 | +| n_updates | 21876 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000155 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1401 | +| iterations | 1516 | +| time_elapsed | 2216 | +| total_timesteps | 3104768 | +| train/ | | +| approx_kl | 0.010965711 | +| clip_fraction | 0.307 | +| clip_range | 0.0742 | +| entropy_loss | -6.92 | +| explained_variance | 0.315 | +| learning_rate | 4.93e-05 | +| loss | -0.0325 | +| n_updates | 21880 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000303 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1401 | +| iterations | 1517 | +| time_elapsed | 2217 | +| total_timesteps | 3106816 | +| train/ | | +| approx_kl | 0.011137204 | +| clip_fraction | 0.307 | +| clip_range | 0.0742 | +| entropy_loss | -7.24 | +| explained_variance | -0.183 | +| learning_rate | 4.93e-05 | +| loss | -0.0364 | +| n_updates | 21884 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000205 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1401 | +| iterations | 1518 | +| time_elapsed | 2218 | +| total_timesteps | 3108864 | +| train/ | | +| approx_kl | 0.011710372 | +| clip_fraction | 0.304 | +| clip_range | 0.0742 | +| entropy_loss | -6.91 | +| explained_variance | 0.346 | +| learning_rate | 4.93e-05 | +| loss | -0.0308 | +| n_updates | 21888 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000294 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1401 | +| iterations | 1519 | +| time_elapsed | 2220 | +| total_timesteps | 3110912 | +| train/ | | +| approx_kl | 0.011523356 | +| clip_fraction | 0.322 | +| clip_range | 0.0742 | +| entropy_loss | -7.14 | +| explained_variance | 0.405 | +| learning_rate | 4.93e-05 | +| loss | -0.0312 | +| n_updates | 21892 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000164 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1401 | +| iterations | 1520 | +| time_elapsed | 2221 | +| total_timesteps | 3112960 | +| train/ | | +| approx_kl | 0.011517391 | +| clip_fraction | 0.297 | +| clip_range | 0.0742 | +| entropy_loss | -7.17 | +| explained_variance | 0.138 | +| learning_rate | 4.93e-05 | +| loss | -0.0277 | +| n_updates | 21896 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.00027 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1401 | +| iterations | 1521 | +| time_elapsed | 2223 | +| total_timesteps | 3115008 | +| train/ | | +| approx_kl | 0.010688499 | +| clip_fraction | 0.335 | +| clip_range | 0.0742 | +| entropy_loss | -7.45 | +| explained_variance | -0.139 | +| learning_rate | 4.93e-05 | +| loss | -0.0413 | +| n_updates | 21900 | +| policy_gradient_loss | -0.0228 | +| value_loss | 0.000129 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1401 | +| iterations | 1522 | +| time_elapsed | 2224 | +| total_timesteps | 3117056 | +| train/ | | +| approx_kl | 0.009548612 | +| clip_fraction | 0.309 | +| clip_range | 0.0742 | +| entropy_loss | -7.37 | +| explained_variance | 0.104 | +| learning_rate | 4.93e-05 | +| loss | -0.0339 | +| n_updates | 21904 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000217 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1401 | +| iterations | 1523 | +| time_elapsed | 2226 | +| total_timesteps | 3119104 | +| train/ | | +| approx_kl | 0.008865193 | +| clip_fraction | 0.304 | +| clip_range | 0.0742 | +| entropy_loss | -7.45 | +| explained_variance | 0.0981 | +| learning_rate | 4.93e-05 | +| loss | -0.0344 | +| n_updates | 21908 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000137 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1401 | +| iterations | 1524 | +| time_elapsed | 2227 | +| total_timesteps | 3121152 | +| train/ | | +| approx_kl | 0.008806438 | +| clip_fraction | 0.307 | +| clip_range | 0.0742 | +| entropy_loss | -6.89 | +| explained_variance | 0.301 | +| learning_rate | 4.93e-05 | +| loss | -0.0278 | +| n_updates | 21912 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000484 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1401 | +| iterations | 1525 | +| time_elapsed | 2229 | +| total_timesteps | 3123200 | +| train/ | | +| approx_kl | 0.010643147 | +| clip_fraction | 0.334 | +| clip_range | 0.0742 | +| entropy_loss | -7.19 | +| explained_variance | 0.415 | +| learning_rate | 4.93e-05 | +| loss | -0.0321 | +| n_updates | 21916 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000169 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1401 | +| iterations | 1526 | +| time_elapsed | 2230 | +| total_timesteps | 3125248 | +| train/ | | +| approx_kl | 0.009494821 | +| clip_fraction | 0.268 | +| clip_range | 0.0742 | +| entropy_loss | -7.08 | +| explained_variance | 0.0437 | +| learning_rate | 4.93e-05 | +| loss | -0.0307 | +| n_updates | 21920 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000199 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.386 | +| time/ | | +| fps | 1401 | +| iterations | 1527 | +| time_elapsed | 2232 | +| total_timesteps | 3127296 | +| train/ | | +| approx_kl | 0.011288235 | +| clip_fraction | 0.332 | +| clip_range | 0.0742 | +| entropy_loss | -7.18 | +| explained_variance | 0.278 | +| learning_rate | 4.93e-05 | +| loss | -0.0391 | +| n_updates | 21924 | +| policy_gradient_loss | -0.0222 | +| value_loss | 0.000125 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.386 | +| time/ | | +| fps | 1401 | +| iterations | 1528 | +| time_elapsed | 2233 | +| total_timesteps | 3129344 | +| train/ | | +| approx_kl | 0.009072831 | +| clip_fraction | 0.282 | +| clip_range | 0.0742 | +| entropy_loss | -6.87 | +| explained_variance | 0.256 | +| learning_rate | 4.93e-05 | +| loss | -0.0324 | +| n_updates | 21928 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000404 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1401 | +| iterations | 1529 | +| time_elapsed | 2234 | +| total_timesteps | 3131392 | +| train/ | | +| approx_kl | 0.0104162665 | +| clip_fraction | 0.309 | +| clip_range | 0.0742 | +| entropy_loss | -6.92 | +| explained_variance | 0.637 | +| learning_rate | 4.93e-05 | +| loss | -0.0303 | +| n_updates | 21932 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000109 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1401 | +| iterations | 1530 | +| time_elapsed | 2236 | +| total_timesteps | 3133440 | +| train/ | | +| approx_kl | 0.013022453 | +| clip_fraction | 0.348 | +| clip_range | 0.0742 | +| entropy_loss | -7.28 | +| explained_variance | 0.226 | +| learning_rate | 4.93e-05 | +| loss | -0.0331 | +| n_updates | 21936 | +| policy_gradient_loss | -0.0233 | +| value_loss | 0.000107 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1401 | +| iterations | 1531 | +| time_elapsed | 2237 | +| total_timesteps | 3135488 | +| train/ | | +| approx_kl | 0.011065015 | +| clip_fraction | 0.317 | +| clip_range | 0.0742 | +| entropy_loss | -7.37 | +| explained_variance | -0.0135 | +| learning_rate | 4.93e-05 | +| loss | -0.0349 | +| n_updates | 21940 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000157 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1401 | +| iterations | 1532 | +| time_elapsed | 2239 | +| total_timesteps | 3137536 | +| train/ | | +| approx_kl | 0.010521373 | +| clip_fraction | 0.306 | +| clip_range | 0.0742 | +| entropy_loss | -7.37 | +| explained_variance | -0.0827 | +| learning_rate | 4.93e-05 | +| loss | -0.0344 | +| n_updates | 21944 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000104 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.385 | +| time/ | | +| fps | 1401 | +| iterations | 1533 | +| time_elapsed | 2240 | +| total_timesteps | 3139584 | +| train/ | | +| approx_kl | 0.011676215 | +| clip_fraction | 0.311 | +| clip_range | 0.0742 | +| entropy_loss | -7.42 | +| explained_variance | -0.0223 | +| learning_rate | 4.93e-05 | +| loss | -0.0276 | +| n_updates | 21948 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000149 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1401 | +| iterations | 1534 | +| time_elapsed | 2242 | +| total_timesteps | 3141632 | +| train/ | | +| approx_kl | 0.010068428 | +| clip_fraction | 0.29 | +| clip_range | 0.0742 | +| entropy_loss | -7.16 | +| explained_variance | 0.304 | +| learning_rate | 4.93e-05 | +| loss | -0.0323 | +| n_updates | 21952 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000225 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1401 | +| iterations | 1535 | +| time_elapsed | 2243 | +| total_timesteps | 3143680 | +| train/ | | +| approx_kl | 0.008734321 | +| clip_fraction | 0.293 | +| clip_range | 0.0742 | +| entropy_loss | -6.98 | +| explained_variance | 0.44 | +| learning_rate | 4.93e-05 | +| loss | -0.0235 | +| n_updates | 21956 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000209 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1401 | +| iterations | 1536 | +| time_elapsed | 2245 | +| total_timesteps | 3145728 | +| train/ | | +| approx_kl | 0.009630781 | +| clip_fraction | 0.291 | +| clip_range | 0.0742 | +| entropy_loss | -6.56 | +| explained_variance | 0.724 | +| learning_rate | 4.93e-05 | +| loss | -0.0305 | +| n_updates | 21960 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000155 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1401 | +| iterations | 1537 | +| time_elapsed | 2246 | +| total_timesteps | 3147776 | +| train/ | | +| approx_kl | 0.010681844 | +| clip_fraction | 0.335 | +| clip_range | 0.0742 | +| entropy_loss | -7.31 | +| explained_variance | 0.017 | +| learning_rate | 4.93e-05 | +| loss | -0.0291 | +| n_updates | 21964 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000183 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1401 | +| iterations | 1538 | +| time_elapsed | 2248 | +| total_timesteps | 3149824 | +| train/ | | +| approx_kl | 0.011045692 | +| clip_fraction | 0.301 | +| clip_range | 0.0742 | +| entropy_loss | -7.23 | +| explained_variance | 0.207 | +| learning_rate | 4.93e-05 | +| loss | -0.0318 | +| n_updates | 21968 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000182 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1401 | +| iterations | 1539 | +| time_elapsed | 2249 | +| total_timesteps | 3151872 | +| train/ | | +| approx_kl | 0.012349828 | +| clip_fraction | 0.344 | +| clip_range | 0.0742 | +| entropy_loss | -7.15 | +| explained_variance | 0.238 | +| learning_rate | 4.93e-05 | +| loss | -0.0364 | +| n_updates | 21972 | +| policy_gradient_loss | -0.022 | +| value_loss | 0.000202 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1401 | +| iterations | 1540 | +| time_elapsed | 2250 | +| total_timesteps | 3153920 | +| train/ | | +| approx_kl | 0.009671009 | +| clip_fraction | 0.308 | +| clip_range | 0.0742 | +| entropy_loss | -7.32 | +| explained_variance | -0.0302 | +| learning_rate | 4.93e-05 | +| loss | -0.0282 | +| n_updates | 21976 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000339 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1401 | +| iterations | 1541 | +| time_elapsed | 2252 | +| total_timesteps | 3155968 | +| train/ | | +| approx_kl | 0.010826156 | +| clip_fraction | 0.335 | +| clip_range | 0.0742 | +| entropy_loss | -7.17 | +| explained_variance | 0.46 | +| learning_rate | 4.93e-05 | +| loss | -0.0346 | +| n_updates | 21980 | +| policy_gradient_loss | -0.023 | +| value_loss | 0.000119 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1401 | +| iterations | 1542 | +| time_elapsed | 2253 | +| total_timesteps | 3158016 | +| train/ | | +| approx_kl | 0.009469308 | +| clip_fraction | 0.301 | +| clip_range | 0.0742 | +| entropy_loss | -7.27 | +| explained_variance | 0.135 | +| learning_rate | 4.93e-05 | +| loss | -0.0344 | +| n_updates | 21984 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000185 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1401 | +| iterations | 1543 | +| time_elapsed | 2255 | +| total_timesteps | 3160064 | +| train/ | | +| approx_kl | 0.010829044 | +| clip_fraction | 0.326 | +| clip_range | 0.0742 | +| entropy_loss | -7.07 | +| explained_variance | 0.632 | +| learning_rate | 4.92e-05 | +| loss | -0.0326 | +| n_updates | 21988 | +| policy_gradient_loss | -0.0228 | +| value_loss | 9.93e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1401 | +| iterations | 1544 | +| time_elapsed | 2256 | +| total_timesteps | 3162112 | +| train/ | | +| approx_kl | 0.011682091 | +| clip_fraction | 0.317 | +| clip_range | 0.0742 | +| entropy_loss | -7.18 | +| explained_variance | 0.429 | +| learning_rate | 4.92e-05 | +| loss | -0.0324 | +| n_updates | 21992 | +| policy_gradient_loss | -0.021 | +| value_loss | 9.25e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1401 | +| iterations | 1545 | +| time_elapsed | 2257 | +| total_timesteps | 3164160 | +| train/ | | +| approx_kl | 0.010256048 | +| clip_fraction | 0.263 | +| clip_range | 0.0742 | +| entropy_loss | -7.12 | +| explained_variance | 0.339 | +| learning_rate | 4.92e-05 | +| loss | -0.0311 | +| n_updates | 21996 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000246 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1401 | +| iterations | 1546 | +| time_elapsed | 2259 | +| total_timesteps | 3166208 | +| train/ | | +| approx_kl | 0.011634747 | +| clip_fraction | 0.271 | +| clip_range | 0.0742 | +| entropy_loss | -7.01 | +| explained_variance | 0.373 | +| learning_rate | 4.92e-05 | +| loss | -0.0303 | +| n_updates | 22000 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000287 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1401 | +| iterations | 1547 | +| time_elapsed | 2260 | +| total_timesteps | 3168256 | +| train/ | | +| approx_kl | 0.011605811 | +| clip_fraction | 0.305 | +| clip_range | 0.0742 | +| entropy_loss | -7.18 | +| explained_variance | 0.399 | +| learning_rate | 4.92e-05 | +| loss | -0.0315 | +| n_updates | 22004 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000202 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1401 | +| iterations | 1548 | +| time_elapsed | 2262 | +| total_timesteps | 3170304 | +| train/ | | +| approx_kl | 0.011409918 | +| clip_fraction | 0.327 | +| clip_range | 0.0742 | +| entropy_loss | -7.15 | +| explained_variance | 0.621 | +| learning_rate | 4.92e-05 | +| loss | -0.0383 | +| n_updates | 22008 | +| policy_gradient_loss | -0.0228 | +| value_loss | 8.73e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1401 | +| iterations | 1549 | +| time_elapsed | 2263 | +| total_timesteps | 3172352 | +| train/ | | +| approx_kl | 0.010148803 | +| clip_fraction | 0.322 | +| clip_range | 0.0742 | +| entropy_loss | -7.33 | +| explained_variance | -0.227 | +| learning_rate | 4.92e-05 | +| loss | -0.0335 | +| n_updates | 22012 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000141 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1401 | +| iterations | 1550 | +| time_elapsed | 2265 | +| total_timesteps | 3174400 | +| train/ | | +| approx_kl | 0.01069903 | +| clip_fraction | 0.314 | +| clip_range | 0.0742 | +| entropy_loss | -7.32 | +| explained_variance | 0.319 | +| learning_rate | 4.92e-05 | +| loss | -0.0374 | +| n_updates | 22016 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000136 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1401 | +| iterations | 1551 | +| time_elapsed | 2266 | +| total_timesteps | 3176448 | +| train/ | | +| approx_kl | 0.010701075 | +| clip_fraction | 0.303 | +| clip_range | 0.0742 | +| entropy_loss | -7.23 | +| explained_variance | 0.255 | +| learning_rate | 4.92e-05 | +| loss | -0.0271 | +| n_updates | 22020 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000182 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1401 | +| iterations | 1552 | +| time_elapsed | 2267 | +| total_timesteps | 3178496 | +| train/ | | +| approx_kl | 0.0074370457 | +| clip_fraction | 0.261 | +| clip_range | 0.0742 | +| entropy_loss | -7.04 | +| explained_variance | 0.283 | +| learning_rate | 4.92e-05 | +| loss | -0.0255 | +| n_updates | 22024 | +| policy_gradient_loss | -0.0145 | +| value_loss | 0.000361 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1401 | +| iterations | 1553 | +| time_elapsed | 2269 | +| total_timesteps | 3180544 | +| train/ | | +| approx_kl | 0.009530608 | +| clip_fraction | 0.303 | +| clip_range | 0.0742 | +| entropy_loss | -6.88 | +| explained_variance | 0.484 | +| learning_rate | 4.92e-05 | +| loss | -0.0276 | +| n_updates | 22028 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000212 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1401 | +| iterations | 1554 | +| time_elapsed | 2270 | +| total_timesteps | 3182592 | +| train/ | | +| approx_kl | 0.010615967 | +| clip_fraction | 0.307 | +| clip_range | 0.0742 | +| entropy_loss | -7.11 | +| explained_variance | 0.348 | +| learning_rate | 4.92e-05 | +| loss | -0.0327 | +| n_updates | 22032 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000238 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1401 | +| iterations | 1555 | +| time_elapsed | 2272 | +| total_timesteps | 3184640 | +| train/ | | +| approx_kl | 0.011786877 | +| clip_fraction | 0.318 | +| clip_range | 0.0742 | +| entropy_loss | -7.48 | +| explained_variance | -0.317 | +| learning_rate | 4.92e-05 | +| loss | -0.0397 | +| n_updates | 22036 | +| policy_gradient_loss | -0.0234 | +| value_loss | 0.000102 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1401 | +| iterations | 1556 | +| time_elapsed | 2273 | +| total_timesteps | 3186688 | +| train/ | | +| approx_kl | 0.010452217 | +| clip_fraction | 0.32 | +| clip_range | 0.0742 | +| entropy_loss | -7.4 | +| explained_variance | -0.177 | +| learning_rate | 4.92e-05 | +| loss | -0.0369 | +| n_updates | 22040 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000175 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1401 | +| iterations | 1557 | +| time_elapsed | 2275 | +| total_timesteps | 3188736 | +| train/ | | +| approx_kl | 0.009541595 | +| clip_fraction | 0.286 | +| clip_range | 0.0742 | +| entropy_loss | -7.03 | +| explained_variance | 0.264 | +| learning_rate | 4.92e-05 | +| loss | -0.0276 | +| n_updates | 22044 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000314 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1401 | +| iterations | 1558 | +| time_elapsed | 2276 | +| total_timesteps | 3190784 | +| train/ | | +| approx_kl | 0.010449616 | +| clip_fraction | 0.338 | +| clip_range | 0.0742 | +| entropy_loss | -7.22 | +| explained_variance | 0.345 | +| learning_rate | 4.92e-05 | +| loss | -0.0379 | +| n_updates | 22048 | +| policy_gradient_loss | -0.0234 | +| value_loss | 0.000108 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1401 | +| iterations | 1559 | +| time_elapsed | 2278 | +| total_timesteps | 3192832 | +| train/ | | +| approx_kl | 0.010585807 | +| clip_fraction | 0.312 | +| clip_range | 0.0742 | +| entropy_loss | -7.26 | +| explained_variance | 0.219 | +| learning_rate | 4.92e-05 | +| loss | -0.0298 | +| n_updates | 22052 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000298 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1401 | +| iterations | 1560 | +| time_elapsed | 2279 | +| total_timesteps | 3194880 | +| train/ | | +| approx_kl | 0.010477842 | +| clip_fraction | 0.303 | +| clip_range | 0.0742 | +| entropy_loss | -7.17 | +| explained_variance | 0.297 | +| learning_rate | 4.92e-05 | +| loss | -0.0333 | +| n_updates | 22056 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000177 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1401 | +| iterations | 1561 | +| time_elapsed | 2280 | +| total_timesteps | 3196928 | +| train/ | | +| approx_kl | 0.00963155 | +| clip_fraction | 0.263 | +| clip_range | 0.0742 | +| entropy_loss | -6.99 | +| explained_variance | 0.49 | +| learning_rate | 4.92e-05 | +| loss | -0.0276 | +| n_updates | 22060 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.000206 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1401 | +| iterations | 1562 | +| time_elapsed | 2282 | +| total_timesteps | 3198976 | +| train/ | | +| approx_kl | 0.011192655 | +| clip_fraction | 0.327 | +| clip_range | 0.0742 | +| entropy_loss | -7.22 | +| explained_variance | 0.354 | +| learning_rate | 4.92e-05 | +| loss | -0.0352 | +| n_updates | 22064 | +| policy_gradient_loss | -0.0224 | +| value_loss | 0.000119 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1401 | +| iterations | 1563 | +| time_elapsed | 2283 | +| total_timesteps | 3201024 | +| train/ | | +| approx_kl | 0.011193228 | +| clip_fraction | 0.324 | +| clip_range | 0.0742 | +| entropy_loss | -6.79 | +| explained_variance | 0.609 | +| learning_rate | 4.92e-05 | +| loss | -0.0351 | +| n_updates | 22068 | +| policy_gradient_loss | -0.0228 | +| value_loss | 0.000128 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1401 | +| iterations | 1564 | +| time_elapsed | 2285 | +| total_timesteps | 3203072 | +| train/ | | +| approx_kl | 0.013886286 | +| clip_fraction | 0.303 | +| clip_range | 0.0742 | +| entropy_loss | -7.07 | +| explained_variance | 0.329 | +| learning_rate | 4.92e-05 | +| loss | -0.0355 | +| n_updates | 22072 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000257 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1401 | +| iterations | 1565 | +| time_elapsed | 2286 | +| total_timesteps | 3205120 | +| train/ | | +| approx_kl | 0.01213812 | +| clip_fraction | 0.318 | +| clip_range | 0.0742 | +| entropy_loss | -7.31 | +| explained_variance | 0.333 | +| learning_rate | 4.92e-05 | +| loss | -0.0384 | +| n_updates | 22076 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000132 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1401 | +| iterations | 1566 | +| time_elapsed | 2287 | +| total_timesteps | 3207168 | +| train/ | | +| approx_kl | 0.0121663585 | +| clip_fraction | 0.346 | +| clip_range | 0.0742 | +| entropy_loss | -7.52 | +| explained_variance | -0.172 | +| learning_rate | 4.92e-05 | +| loss | -0.0383 | +| n_updates | 22080 | +| policy_gradient_loss | -0.0254 | +| value_loss | 7.28e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1401 | +| iterations | 1567 | +| time_elapsed | 2289 | +| total_timesteps | 3209216 | +| train/ | | +| approx_kl | 0.008624232 | +| clip_fraction | 0.285 | +| clip_range | 0.0742 | +| entropy_loss | -7.38 | +| explained_variance | 0.0907 | +| learning_rate | 4.92e-05 | +| loss | -0.0302 | +| n_updates | 22084 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000296 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1401 | +| iterations | 1568 | +| time_elapsed | 2290 | +| total_timesteps | 3211264 | +| train/ | | +| approx_kl | 0.009759042 | +| clip_fraction | 0.282 | +| clip_range | 0.0742 | +| entropy_loss | -6.73 | +| explained_variance | 0.523 | +| learning_rate | 4.92e-05 | +| loss | -0.0285 | +| n_updates | 22088 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000197 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1401 | +| iterations | 1569 | +| time_elapsed | 2292 | +| total_timesteps | 3213312 | +| train/ | | +| approx_kl | 0.0115823215 | +| clip_fraction | 0.308 | +| clip_range | 0.0742 | +| entropy_loss | -7.29 | +| explained_variance | -0.209 | +| learning_rate | 4.92e-05 | +| loss | -0.0343 | +| n_updates | 22092 | +| policy_gradient_loss | -0.0204 | +| value_loss | 8.85e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1401 | +| iterations | 1570 | +| time_elapsed | 2293 | +| total_timesteps | 3215360 | +| train/ | | +| approx_kl | 0.009525963 | +| clip_fraction | 0.303 | +| clip_range | 0.0742 | +| entropy_loss | -7.11 | +| explained_variance | 0.271 | +| learning_rate | 4.92e-05 | +| loss | -0.0306 | +| n_updates | 22096 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000325 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.393 | +| time/ | | +| fps | 1401 | +| iterations | 1571 | +| time_elapsed | 2295 | +| total_timesteps | 3217408 | +| train/ | | +| approx_kl | 0.012299638 | +| clip_fraction | 0.332 | +| clip_range | 0.0742 | +| entropy_loss | -7.39 | +| explained_variance | -0.0326 | +| learning_rate | 4.92e-05 | +| loss | -0.0326 | +| n_updates | 22100 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000201 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.394 | +| time/ | | +| fps | 1401 | +| iterations | 1572 | +| time_elapsed | 2296 | +| total_timesteps | 3219456 | +| train/ | | +| approx_kl | 0.009857936 | +| clip_fraction | 0.292 | +| clip_range | 0.0742 | +| entropy_loss | -7.14 | +| explained_variance | 0.125 | +| learning_rate | 4.92e-05 | +| loss | -0.0272 | +| n_updates | 22104 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000288 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.387 | +| time/ | | +| fps | 1401 | +| iterations | 1573 | +| time_elapsed | 2297 | +| total_timesteps | 3221504 | +| train/ | | +| approx_kl | 0.010760061 | +| clip_fraction | 0.334 | +| clip_range | 0.0742 | +| entropy_loss | -6.84 | +| explained_variance | 0.588 | +| learning_rate | 4.92e-05 | +| loss | -0.0368 | +| n_updates | 22108 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000168 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.389 | +| time/ | | +| fps | 1401 | +| iterations | 1574 | +| time_elapsed | 2299 | +| total_timesteps | 3223552 | +| train/ | | +| approx_kl | 0.010074693 | +| clip_fraction | 0.311 | +| clip_range | 0.0742 | +| entropy_loss | -7.12 | +| explained_variance | 0.331 | +| learning_rate | 4.92e-05 | +| loss | -0.0303 | +| n_updates | 22112 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000278 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.389 | +| time/ | | +| fps | 1401 | +| iterations | 1575 | +| time_elapsed | 2300 | +| total_timesteps | 3225600 | +| train/ | | +| approx_kl | 0.011992922 | +| clip_fraction | 0.351 | +| clip_range | 0.0742 | +| entropy_loss | -7.23 | +| explained_variance | 0.333 | +| learning_rate | 4.92e-05 | +| loss | -0.0376 | +| n_updates | 22116 | +| policy_gradient_loss | -0.0262 | +| value_loss | 8.58e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.389 | +| time/ | | +| fps | 1401 | +| iterations | 1576 | +| time_elapsed | 2302 | +| total_timesteps | 3227648 | +| train/ | | +| approx_kl | 0.012056662 | +| clip_fraction | 0.335 | +| clip_range | 0.0742 | +| entropy_loss | -7.36 | +| explained_variance | -0.205 | +| learning_rate | 4.92e-05 | +| loss | -0.0341 | +| n_updates | 22120 | +| policy_gradient_loss | -0.022 | +| value_loss | 0.000135 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.393 | +| time/ | | +| fps | 1402 | +| iterations | 1577 | +| time_elapsed | 2303 | +| total_timesteps | 3229696 | +| train/ | | +| approx_kl | 0.010586885 | +| clip_fraction | 0.304 | +| clip_range | 0.0742 | +| entropy_loss | -7.18 | +| explained_variance | 0.2 | +| learning_rate | 4.92e-05 | +| loss | -0.0341 | +| n_updates | 22124 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000308 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.393 | +| time/ | | +| fps | 1401 | +| iterations | 1578 | +| time_elapsed | 2305 | +| total_timesteps | 3231744 | +| train/ | | +| approx_kl | 0.012108376 | +| clip_fraction | 0.306 | +| clip_range | 0.0742 | +| entropy_loss | -6.84 | +| explained_variance | 0.459 | +| learning_rate | 4.92e-05 | +| loss | -0.0334 | +| n_updates | 22128 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000235 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.386 | +| time/ | | +| fps | 1402 | +| iterations | 1579 | +| time_elapsed | 2306 | +| total_timesteps | 3233792 | +| train/ | | +| approx_kl | 0.012204675 | +| clip_fraction | 0.341 | +| clip_range | 0.0742 | +| entropy_loss | -7.3 | +| explained_variance | 0.225 | +| learning_rate | 4.92e-05 | +| loss | -0.0414 | +| n_updates | 22132 | +| policy_gradient_loss | -0.0247 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1402 | +| iterations | 1580 | +| time_elapsed | 2307 | +| total_timesteps | 3235840 | +| train/ | | +| approx_kl | 0.010148687 | +| clip_fraction | 0.317 | +| clip_range | 0.0742 | +| entropy_loss | -7.14 | +| explained_variance | 0.24 | +| learning_rate | 4.92e-05 | +| loss | -0.0302 | +| n_updates | 22136 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000193 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1402 | +| iterations | 1581 | +| time_elapsed | 2309 | +| total_timesteps | 3237888 | +| train/ | | +| approx_kl | 0.010404825 | +| clip_fraction | 0.305 | +| clip_range | 0.0742 | +| entropy_loss | -7.16 | +| explained_variance | 0.277 | +| learning_rate | 4.92e-05 | +| loss | -0.0333 | +| n_updates | 22140 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000143 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.387 | +| time/ | | +| fps | 1402 | +| iterations | 1582 | +| time_elapsed | 2310 | +| total_timesteps | 3239936 | +| train/ | | +| approx_kl | 0.010771649 | +| clip_fraction | 0.313 | +| clip_range | 0.0742 | +| entropy_loss | -7.11 | +| explained_variance | 0.37 | +| learning_rate | 4.92e-05 | +| loss | -0.032 | +| n_updates | 22144 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000259 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.388 | +| time/ | | +| fps | 1402 | +| iterations | 1583 | +| time_elapsed | 2312 | +| total_timesteps | 3241984 | +| train/ | | +| approx_kl | 0.010853936 | +| clip_fraction | 0.308 | +| clip_range | 0.0742 | +| entropy_loss | -7.21 | +| explained_variance | 0.305 | +| learning_rate | 4.92e-05 | +| loss | -0.0317 | +| n_updates | 22148 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000153 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1402 | +| iterations | 1584 | +| time_elapsed | 2313 | +| total_timesteps | 3244032 | +| train/ | | +| approx_kl | 0.009398161 | +| clip_fraction | 0.279 | +| clip_range | 0.0742 | +| entropy_loss | -7.29 | +| explained_variance | 0.119 | +| learning_rate | 4.92e-05 | +| loss | -0.0293 | +| n_updates | 22152 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000437 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1402 | +| iterations | 1585 | +| time_elapsed | 2315 | +| total_timesteps | 3246080 | +| train/ | | +| approx_kl | 0.008624097 | +| clip_fraction | 0.288 | +| clip_range | 0.0742 | +| entropy_loss | -7.06 | +| explained_variance | 0.206 | +| learning_rate | 4.92e-05 | +| loss | -0.0284 | +| n_updates | 22156 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000323 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1402 | +| iterations | 1586 | +| time_elapsed | 2316 | +| total_timesteps | 3248128 | +| train/ | | +| approx_kl | 0.009607403 | +| clip_fraction | 0.316 | +| clip_range | 0.0742 | +| entropy_loss | -7.36 | +| explained_variance | 0.33 | +| learning_rate | 4.92e-05 | +| loss | -0.0363 | +| n_updates | 22160 | +| policy_gradient_loss | -0.0229 | +| value_loss | 0.000162 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.386 | +| time/ | | +| fps | 1402 | +| iterations | 1587 | +| time_elapsed | 2317 | +| total_timesteps | 3250176 | +| train/ | | +| approx_kl | 0.011143365 | +| clip_fraction | 0.333 | +| clip_range | 0.0742 | +| entropy_loss | -7.48 | +| explained_variance | -0.329 | +| learning_rate | 4.92e-05 | +| loss | -0.0342 | +| n_updates | 22164 | +| policy_gradient_loss | -0.0242 | +| value_loss | 0.000119 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.39 | +| time/ | | +| fps | 1402 | +| iterations | 1588 | +| time_elapsed | 2319 | +| total_timesteps | 3252224 | +| train/ | | +| approx_kl | 0.012472184 | +| clip_fraction | 0.348 | +| clip_range | 0.0742 | +| entropy_loss | -7.26 | +| explained_variance | 0.346 | +| learning_rate | 4.92e-05 | +| loss | -0.0394 | +| n_updates | 22168 | +| policy_gradient_loss | -0.0238 | +| value_loss | 7.97e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.388 | +| time/ | | +| fps | 1402 | +| iterations | 1589 | +| time_elapsed | 2320 | +| total_timesteps | 3254272 | +| train/ | | +| approx_kl | 0.011186583 | +| clip_fraction | 0.318 | +| clip_range | 0.0742 | +| entropy_loss | -6.77 | +| explained_variance | 0.338 | +| learning_rate | 4.92e-05 | +| loss | -0.0291 | +| n_updates | 22172 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000245 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.384 | +| time/ | | +| fps | 1402 | +| iterations | 1590 | +| time_elapsed | 2322 | +| total_timesteps | 3256320 | +| train/ | | +| approx_kl | 0.010523122 | +| clip_fraction | 0.283 | +| clip_range | 0.0742 | +| entropy_loss | -6.98 | +| explained_variance | 0.54 | +| learning_rate | 4.92e-05 | +| loss | -0.033 | +| n_updates | 22176 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000187 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.384 | +| time/ | | +| fps | 1402 | +| iterations | 1591 | +| time_elapsed | 2323 | +| total_timesteps | 3258368 | +| train/ | | +| approx_kl | 0.011554865 | +| clip_fraction | 0.34 | +| clip_range | 0.0742 | +| entropy_loss | -7.29 | +| explained_variance | 0.371 | +| learning_rate | 4.92e-05 | +| loss | -0.038 | +| n_updates | 22180 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000128 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.384 | +| time/ | | +| fps | 1402 | +| iterations | 1592 | +| time_elapsed | 2324 | +| total_timesteps | 3260416 | +| train/ | | +| approx_kl | 0.009662251 | +| clip_fraction | 0.326 | +| clip_range | 0.0742 | +| entropy_loss | -7.42 | +| explained_variance | -0.0293 | +| learning_rate | 4.92e-05 | +| loss | -0.0336 | +| n_updates | 22184 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.00022 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.387 | +| time/ | | +| fps | 1402 | +| iterations | 1593 | +| time_elapsed | 2326 | +| total_timesteps | 3262464 | +| train/ | | +| approx_kl | 0.011750101 | +| clip_fraction | 0.336 | +| clip_range | 0.0742 | +| entropy_loss | -7.38 | +| explained_variance | -0.104 | +| learning_rate | 4.92e-05 | +| loss | -0.0336 | +| n_updates | 22188 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000194 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.393 | +| time/ | | +| fps | 1402 | +| iterations | 1594 | +| time_elapsed | 2327 | +| total_timesteps | 3264512 | +| train/ | | +| approx_kl | 0.011241993 | +| clip_fraction | 0.322 | +| clip_range | 0.0742 | +| entropy_loss | -7.07 | +| explained_variance | 0.425 | +| learning_rate | 4.92e-05 | +| loss | -0.0329 | +| n_updates | 22192 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000203 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.397 | +| time/ | | +| fps | 1402 | +| iterations | 1595 | +| time_elapsed | 2329 | +| total_timesteps | 3266560 | +| train/ | | +| approx_kl | 0.010426366 | +| clip_fraction | 0.32 | +| clip_range | 0.0742 | +| entropy_loss | -7.14 | +| explained_variance | 0.284 | +| learning_rate | 4.92e-05 | +| loss | -0.0227 | +| n_updates | 22196 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000379 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.397 | +| time/ | | +| fps | 1402 | +| iterations | 1596 | +| time_elapsed | 2330 | +| total_timesteps | 3268608 | +| train/ | | +| approx_kl | 0.010759473 | +| clip_fraction | 0.294 | +| clip_range | 0.0742 | +| entropy_loss | -6.93 | +| explained_variance | 0.496 | +| learning_rate | 4.92e-05 | +| loss | -0.0331 | +| n_updates | 22200 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000202 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.404 | +| time/ | | +| fps | 1402 | +| iterations | 1597 | +| time_elapsed | 2332 | +| total_timesteps | 3270656 | +| train/ | | +| approx_kl | 0.012146166 | +| clip_fraction | 0.335 | +| clip_range | 0.0742 | +| entropy_loss | -7.42 | +| explained_variance | -0.184 | +| learning_rate | 4.92e-05 | +| loss | -0.0328 | +| n_updates | 22204 | +| policy_gradient_loss | -0.022 | +| value_loss | 0.000107 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.402 | +| time/ | | +| fps | 1402 | +| iterations | 1598 | +| time_elapsed | 2333 | +| total_timesteps | 3272704 | +| train/ | | +| approx_kl | 0.010866982 | +| clip_fraction | 0.307 | +| clip_range | 0.0742 | +| entropy_loss | -7.04 | +| explained_variance | 0.378 | +| learning_rate | 4.92e-05 | +| loss | -0.0253 | +| n_updates | 22208 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000245 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.405 | +| time/ | | +| fps | 1402 | +| iterations | 1599 | +| time_elapsed | 2334 | +| total_timesteps | 3274752 | +| train/ | | +| approx_kl | 0.01217907 | +| clip_fraction | 0.336 | +| clip_range | 0.0742 | +| entropy_loss | -7.19 | +| explained_variance | 0.285 | +| learning_rate | 4.92e-05 | +| loss | -0.0349 | +| n_updates | 22212 | +| policy_gradient_loss | -0.0219 | +| value_loss | 0.000131 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.405 | +| time/ | | +| fps | 1402 | +| iterations | 1600 | +| time_elapsed | 2336 | +| total_timesteps | 3276800 | +| train/ | | +| approx_kl | 0.010019559 | +| clip_fraction | 0.303 | +| clip_range | 0.0742 | +| entropy_loss | -7.05 | +| explained_variance | 0.186 | +| learning_rate | 4.92e-05 | +| loss | -0.0294 | +| n_updates | 22216 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000232 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.405 | +| time/ | | +| fps | 1402 | +| iterations | 1601 | +| time_elapsed | 2337 | +| total_timesteps | 3278848 | +| train/ | | +| approx_kl | 0.012711309 | +| clip_fraction | 0.343 | +| clip_range | 0.0742 | +| entropy_loss | -7.35 | +| explained_variance | -0.117 | +| learning_rate | 4.92e-05 | +| loss | -0.0341 | +| n_updates | 22220 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000161 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.405 | +| time/ | | +| fps | 1402 | +| iterations | 1602 | +| time_elapsed | 2339 | +| total_timesteps | 3280896 | +| train/ | | +| approx_kl | 0.011339336 | +| clip_fraction | 0.309 | +| clip_range | 0.0742 | +| entropy_loss | -7.27 | +| explained_variance | -0.0884 | +| learning_rate | 4.92e-05 | +| loss | -0.033 | +| n_updates | 22224 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000196 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.414 | +| time/ | | +| fps | 1402 | +| iterations | 1603 | +| time_elapsed | 2340 | +| total_timesteps | 3282944 | +| train/ | | +| approx_kl | 0.010749018 | +| clip_fraction | 0.332 | +| clip_range | 0.0742 | +| entropy_loss | -7.47 | +| explained_variance | -0.183 | +| learning_rate | 4.92e-05 | +| loss | -0.0393 | +| n_updates | 22228 | +| policy_gradient_loss | -0.0223 | +| value_loss | 0.000105 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.419 | +| time/ | | +| fps | 1402 | +| iterations | 1604 | +| time_elapsed | 2342 | +| total_timesteps | 3284992 | +| train/ | | +| approx_kl | 0.009676772 | +| clip_fraction | 0.306 | +| clip_range | 0.0742 | +| entropy_loss | -6.96 | +| explained_variance | 0.344 | +| learning_rate | 4.92e-05 | +| loss | -0.0254 | +| n_updates | 22232 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000325 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.421 | +| time/ | | +| fps | 1402 | +| iterations | 1605 | +| time_elapsed | 2343 | +| total_timesteps | 3287040 | +| train/ | | +| approx_kl | 0.0117169805 | +| clip_fraction | 0.329 | +| clip_range | 0.0742 | +| entropy_loss | -7.08 | +| explained_variance | 0.476 | +| learning_rate | 4.92e-05 | +| loss | -0.031 | +| n_updates | 22236 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000142 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.42 | +| time/ | | +| fps | 1402 | +| iterations | 1606 | +| time_elapsed | 2344 | +| total_timesteps | 3289088 | +| train/ | | +| approx_kl | 0.010945578 | +| clip_fraction | 0.289 | +| clip_range | 0.0742 | +| entropy_loss | -7.08 | +| explained_variance | 0.328 | +| learning_rate | 4.92e-05 | +| loss | -0.0247 | +| n_updates | 22240 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000132 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.419 | +| time/ | | +| fps | 1402 | +| iterations | 1607 | +| time_elapsed | 2346 | +| total_timesteps | 3291136 | +| train/ | | +| approx_kl | 0.011649773 | +| clip_fraction | 0.329 | +| clip_range | 0.0742 | +| entropy_loss | -7.26 | +| explained_variance | 0.32 | +| learning_rate | 4.92e-05 | +| loss | -0.0316 | +| n_updates | 22244 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000119 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.419 | +| time/ | | +| fps | 1402 | +| iterations | 1608 | +| time_elapsed | 2347 | +| total_timesteps | 3293184 | +| train/ | | +| approx_kl | 0.010191046 | +| clip_fraction | 0.329 | +| clip_range | 0.0742 | +| entropy_loss | -7.11 | +| explained_variance | -0.202 | +| learning_rate | 4.92e-05 | +| loss | -0.0364 | +| n_updates | 22248 | +| policy_gradient_loss | -0.0224 | +| value_loss | 9.13e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.416 | +| time/ | | +| fps | 1402 | +| iterations | 1609 | +| time_elapsed | 2349 | +| total_timesteps | 3295232 | +| train/ | | +| approx_kl | 0.011324749 | +| clip_fraction | 0.327 | +| clip_range | 0.0742 | +| entropy_loss | -7.19 | +| explained_variance | 0.116 | +| learning_rate | 4.92e-05 | +| loss | -0.0364 | +| n_updates | 22252 | +| policy_gradient_loss | -0.022 | +| value_loss | 0.000122 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.416 | +| time/ | | +| fps | 1402 | +| iterations | 1610 | +| time_elapsed | 2350 | +| total_timesteps | 3297280 | +| train/ | | +| approx_kl | 0.011301648 | +| clip_fraction | 0.315 | +| clip_range | 0.0742 | +| entropy_loss | -7.27 | +| explained_variance | 0.34 | +| learning_rate | 4.92e-05 | +| loss | -0.0284 | +| n_updates | 22256 | +| policy_gradient_loss | -0.0195 | +| value_loss | 9.1e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.416 | +| time/ | | +| fps | 1402 | +| iterations | 1611 | +| time_elapsed | 2352 | +| total_timesteps | 3299328 | +| train/ | | +| approx_kl | 0.010589593 | +| clip_fraction | 0.305 | +| clip_range | 0.0742 | +| entropy_loss | -7.5 | +| explained_variance | -0.153 | +| learning_rate | 4.92e-05 | +| loss | -0.0279 | +| n_updates | 22260 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000154 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.421 | +| time/ | | +| fps | 1402 | +| iterations | 1612 | +| time_elapsed | 2353 | +| total_timesteps | 3301376 | +| train/ | | +| approx_kl | 0.010232723 | +| clip_fraction | 0.276 | +| clip_range | 0.0742 | +| entropy_loss | -7.03 | +| explained_variance | 0.373 | +| learning_rate | 4.92e-05 | +| loss | -0.0256 | +| n_updates | 22264 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.000212 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.421 | +| time/ | | +| fps | 1402 | +| iterations | 1613 | +| time_elapsed | 2354 | +| total_timesteps | 3303424 | +| train/ | | +| approx_kl | 0.01075604 | +| clip_fraction | 0.316 | +| clip_range | 0.0742 | +| entropy_loss | -7.16 | +| explained_variance | 0.315 | +| learning_rate | 4.92e-05 | +| loss | -0.03 | +| n_updates | 22268 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000282 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.423 | +| time/ | | +| fps | 1402 | +| iterations | 1614 | +| time_elapsed | 2356 | +| total_timesteps | 3305472 | +| train/ | | +| approx_kl | 0.008697908 | +| clip_fraction | 0.305 | +| clip_range | 0.0742 | +| entropy_loss | -7.41 | +| explained_variance | -0.079 | +| learning_rate | 4.92e-05 | +| loss | -0.0295 | +| n_updates | 22272 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.00015 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.431 | +| time/ | | +| fps | 1402 | +| iterations | 1615 | +| time_elapsed | 2357 | +| total_timesteps | 3307520 | +| train/ | | +| approx_kl | 0.008994044 | +| clip_fraction | 0.304 | +| clip_range | 0.0742 | +| entropy_loss | -7.25 | +| explained_variance | 0.355 | +| learning_rate | 4.92e-05 | +| loss | -0.0285 | +| n_updates | 22276 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000101 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.421 | +| time/ | | +| fps | 1402 | +| iterations | 1616 | +| time_elapsed | 2359 | +| total_timesteps | 3309568 | +| train/ | | +| approx_kl | 0.009408689 | +| clip_fraction | 0.312 | +| clip_range | 0.0742 | +| entropy_loss | -7.19 | +| explained_variance | -0.113 | +| learning_rate | 4.92e-05 | +| loss | -0.03 | +| n_updates | 22280 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000239 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.417 | +| time/ | | +| fps | 1402 | +| iterations | 1617 | +| time_elapsed | 2360 | +| total_timesteps | 3311616 | +| train/ | | +| approx_kl | 0.011605646 | +| clip_fraction | 0.353 | +| clip_range | 0.0742 | +| entropy_loss | -6.81 | +| explained_variance | 0.275 | +| learning_rate | 4.92e-05 | +| loss | -0.0339 | +| n_updates | 22284 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000207 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.418 | +| time/ | | +| fps | 1402 | +| iterations | 1618 | +| time_elapsed | 2362 | +| total_timesteps | 3313664 | +| train/ | | +| approx_kl | 0.011478811 | +| clip_fraction | 0.32 | +| clip_range | 0.0742 | +| entropy_loss | -7.39 | +| explained_variance | -0.204 | +| learning_rate | 4.92e-05 | +| loss | -0.0367 | +| n_updates | 22288 | +| policy_gradient_loss | -0.0221 | +| value_loss | 0.000104 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.417 | +| time/ | | +| fps | 1402 | +| iterations | 1619 | +| time_elapsed | 2363 | +| total_timesteps | 3315712 | +| train/ | | +| approx_kl | 0.011866362 | +| clip_fraction | 0.332 | +| clip_range | 0.0742 | +| entropy_loss | -7.14 | +| explained_variance | 0.223 | +| learning_rate | 4.92e-05 | +| loss | -0.0337 | +| n_updates | 22292 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000158 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.417 | +| time/ | | +| fps | 1402 | +| iterations | 1620 | +| time_elapsed | 2364 | +| total_timesteps | 3317760 | +| train/ | | +| approx_kl | 0.013730967 | +| clip_fraction | 0.312 | +| clip_range | 0.0742 | +| entropy_loss | -6.82 | +| explained_variance | 0.289 | +| learning_rate | 4.92e-05 | +| loss | -0.0279 | +| n_updates | 22296 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000458 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.416 | +| time/ | | +| fps | 1402 | +| iterations | 1621 | +| time_elapsed | 2366 | +| total_timesteps | 3319808 | +| train/ | | +| approx_kl | 0.011440307 | +| clip_fraction | 0.342 | +| clip_range | 0.0742 | +| entropy_loss | -7.37 | +| explained_variance | -0.192 | +| learning_rate | 4.92e-05 | +| loss | -0.0388 | +| n_updates | 22300 | +| policy_gradient_loss | -0.0238 | +| value_loss | 0.000146 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.411 | +| time/ | | +| fps | 1402 | +| iterations | 1622 | +| time_elapsed | 2367 | +| total_timesteps | 3321856 | +| train/ | | +| approx_kl | 0.0109921275 | +| clip_fraction | 0.314 | +| clip_range | 0.0742 | +| entropy_loss | -7.2 | +| explained_variance | 0.301 | +| learning_rate | 4.92e-05 | +| loss | -0.0342 | +| n_updates | 22304 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000202 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.411 | +| time/ | | +| fps | 1402 | +| iterations | 1623 | +| time_elapsed | 2369 | +| total_timesteps | 3323904 | +| train/ | | +| approx_kl | 0.010288073 | +| clip_fraction | 0.33 | +| clip_range | 0.0742 | +| entropy_loss | -7.23 | +| explained_variance | 0.428 | +| learning_rate | 4.92e-05 | +| loss | -0.0342 | +| n_updates | 22308 | +| policy_gradient_loss | -0.0218 | +| value_loss | 9.12e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.415 | +| time/ | | +| fps | 1403 | +| iterations | 1624 | +| time_elapsed | 2370 | +| total_timesteps | 3325952 | +| train/ | | +| approx_kl | 0.011662646 | +| clip_fraction | 0.34 | +| clip_range | 0.0742 | +| entropy_loss | -7.37 | +| explained_variance | -0.302 | +| learning_rate | 4.92e-05 | +| loss | -0.0398 | +| n_updates | 22312 | +| policy_gradient_loss | -0.0236 | +| value_loss | 7.02e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.415 | +| time/ | | +| fps | 1403 | +| iterations | 1625 | +| time_elapsed | 2372 | +| total_timesteps | 3328000 | +| train/ | | +| approx_kl | 0.009512422 | +| clip_fraction | 0.292 | +| clip_range | 0.0742 | +| entropy_loss | -7.22 | +| explained_variance | 0.22 | +| learning_rate | 4.92e-05 | +| loss | -0.025 | +| n_updates | 22316 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000227 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.413 | +| time/ | | +| fps | 1402 | +| iterations | 1626 | +| time_elapsed | 2373 | +| total_timesteps | 3330048 | +| train/ | | +| approx_kl | 0.010708686 | +| clip_fraction | 0.311 | +| clip_range | 0.0742 | +| entropy_loss | -7.46 | +| explained_variance | -0.163 | +| learning_rate | 4.92e-05 | +| loss | -0.0392 | +| n_updates | 22320 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000173 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.412 | +| time/ | | +| fps | 1403 | +| iterations | 1627 | +| time_elapsed | 2374 | +| total_timesteps | 3332096 | +| train/ | | +| approx_kl | 0.00931169 | +| clip_fraction | 0.28 | +| clip_range | 0.0742 | +| entropy_loss | -6.85 | +| explained_variance | 0.487 | +| learning_rate | 4.92e-05 | +| loss | -0.0299 | +| n_updates | 22324 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.00017 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.414 | +| time/ | | +| fps | 1403 | +| iterations | 1628 | +| time_elapsed | 2376 | +| total_timesteps | 3334144 | +| train/ | | +| approx_kl | 0.011213392 | +| clip_fraction | 0.321 | +| clip_range | 0.0742 | +| entropy_loss | -7.08 | +| explained_variance | 0.497 | +| learning_rate | 4.92e-05 | +| loss | -0.0337 | +| n_updates | 22328 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000131 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.414 | +| time/ | | +| fps | 1403 | +| iterations | 1629 | +| time_elapsed | 2377 | +| total_timesteps | 3336192 | +| train/ | | +| approx_kl | 0.010142267 | +| clip_fraction | 0.305 | +| clip_range | 0.0742 | +| entropy_loss | -7.16 | +| explained_variance | 0.015 | +| learning_rate | 4.92e-05 | +| loss | -0.032 | +| n_updates | 22332 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000196 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.416 | +| time/ | | +| fps | 1403 | +| iterations | 1630 | +| time_elapsed | 2379 | +| total_timesteps | 3338240 | +| train/ | | +| approx_kl | 0.008788135 | +| clip_fraction | 0.304 | +| clip_range | 0.0742 | +| entropy_loss | -6.81 | +| explained_variance | 0.336 | +| learning_rate | 4.92e-05 | +| loss | -0.0296 | +| n_updates | 22336 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000236 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.422 | +| time/ | | +| fps | 1403 | +| iterations | 1631 | +| time_elapsed | 2380 | +| total_timesteps | 3340288 | +| train/ | | +| approx_kl | 0.009672886 | +| clip_fraction | 0.331 | +| clip_range | 0.0742 | +| entropy_loss | -7.09 | +| explained_variance | 0.422 | +| learning_rate | 4.92e-05 | +| loss | -0.0334 | +| n_updates | 22340 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000258 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.422 | +| time/ | | +| fps | 1403 | +| iterations | 1632 | +| time_elapsed | 2382 | +| total_timesteps | 3342336 | +| train/ | | +| approx_kl | 0.009021898 | +| clip_fraction | 0.297 | +| clip_range | 0.0742 | +| entropy_loss | -7.21 | +| explained_variance | 0.344 | +| learning_rate | 4.92e-05 | +| loss | -0.0266 | +| n_updates | 22344 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000197 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.426 | +| time/ | | +| fps | 1403 | +| iterations | 1633 | +| time_elapsed | 2383 | +| total_timesteps | 3344384 | +| train/ | | +| approx_kl | 0.011901176 | +| clip_fraction | 0.297 | +| clip_range | 0.0742 | +| entropy_loss | -7.14 | +| explained_variance | 0.399 | +| learning_rate | 4.92e-05 | +| loss | -0.0335 | +| n_updates | 22348 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000189 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.426 | +| time/ | | +| fps | 1403 | +| iterations | 1634 | +| time_elapsed | 2385 | +| total_timesteps | 3346432 | +| train/ | | +| approx_kl | 0.011346284 | +| clip_fraction | 0.335 | +| clip_range | 0.0742 | +| entropy_loss | -7.3 | +| explained_variance | -0.176 | +| learning_rate | 4.92e-05 | +| loss | -0.0384 | +| n_updates | 22352 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.0001 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.421 | +| time/ | | +| fps | 1403 | +| iterations | 1635 | +| time_elapsed | 2386 | +| total_timesteps | 3348480 | +| train/ | | +| approx_kl | 0.009937951 | +| clip_fraction | 0.336 | +| clip_range | 0.0742 | +| entropy_loss | -7.44 | +| explained_variance | -0.147 | +| learning_rate | 4.92e-05 | +| loss | -0.029 | +| n_updates | 22356 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000109 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.416 | +| time/ | | +| fps | 1403 | +| iterations | 1636 | +| time_elapsed | 2387 | +| total_timesteps | 3350528 | +| train/ | | +| approx_kl | 0.011133896 | +| clip_fraction | 0.312 | +| clip_range | 0.0742 | +| entropy_loss | -7.27 | +| explained_variance | 0.24 | +| learning_rate | 4.92e-05 | +| loss | -0.0303 | +| n_updates | 22360 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000125 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.422 | +| time/ | | +| fps | 1403 | +| iterations | 1637 | +| time_elapsed | 2389 | +| total_timesteps | 3352576 | +| train/ | | +| approx_kl | 0.008276019 | +| clip_fraction | 0.299 | +| clip_range | 0.0742 | +| entropy_loss | -7.31 | +| explained_variance | 0.0729 | +| learning_rate | 4.92e-05 | +| loss | -0.0322 | +| n_updates | 22364 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000167 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.421 | +| time/ | | +| fps | 1403 | +| iterations | 1638 | +| time_elapsed | 2390 | +| total_timesteps | 3354624 | +| train/ | | +| approx_kl | 0.008709762 | +| clip_fraction | 0.281 | +| clip_range | 0.0742 | +| entropy_loss | -7.09 | +| explained_variance | 0.347 | +| learning_rate | 4.92e-05 | +| loss | -0.0296 | +| n_updates | 22368 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000342 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.421 | +| time/ | | +| fps | 1403 | +| iterations | 1639 | +| time_elapsed | 2392 | +| total_timesteps | 3356672 | +| train/ | | +| approx_kl | 0.012066977 | +| clip_fraction | 0.314 | +| clip_range | 0.0742 | +| entropy_loss | -7.29 | +| explained_variance | 0.182 | +| learning_rate | 4.92e-05 | +| loss | -0.0292 | +| n_updates | 22372 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000161 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.42 | +| time/ | | +| fps | 1403 | +| iterations | 1640 | +| time_elapsed | 2393 | +| total_timesteps | 3358720 | +| train/ | | +| approx_kl | 0.011824148 | +| clip_fraction | 0.318 | +| clip_range | 0.0742 | +| entropy_loss | -7.19 | +| explained_variance | 0.26 | +| learning_rate | 4.92e-05 | +| loss | -0.0285 | +| n_updates | 22376 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.00022 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.424 | +| time/ | | +| fps | 1403 | +| iterations | 1641 | +| time_elapsed | 2395 | +| total_timesteps | 3360768 | +| train/ | | +| approx_kl | 0.009752144 | +| clip_fraction | 0.316 | +| clip_range | 0.0742 | +| entropy_loss | -6.93 | +| explained_variance | 0.57 | +| learning_rate | 4.92e-05 | +| loss | -0.029 | +| n_updates | 22380 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000125 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.422 | +| time/ | | +| fps | 1403 | +| iterations | 1642 | +| time_elapsed | 2396 | +| total_timesteps | 3362816 | +| train/ | | +| approx_kl | 0.009714456 | +| clip_fraction | 0.292 | +| clip_range | 0.0742 | +| entropy_loss | -6.95 | +| explained_variance | 0.218 | +| learning_rate | 4.92e-05 | +| loss | -0.0247 | +| n_updates | 22384 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000242 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.422 | +| time/ | | +| fps | 1403 | +| iterations | 1643 | +| time_elapsed | 2397 | +| total_timesteps | 3364864 | +| train/ | | +| approx_kl | 0.010276089 | +| clip_fraction | 0.291 | +| clip_range | 0.0742 | +| entropy_loss | -7.04 | +| explained_variance | 0.154 | +| learning_rate | 4.92e-05 | +| loss | -0.0332 | +| n_updates | 22388 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000203 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.418 | +| time/ | | +| fps | 1403 | +| iterations | 1644 | +| time_elapsed | 2399 | +| total_timesteps | 3366912 | +| train/ | | +| approx_kl | 0.011219081 | +| clip_fraction | 0.308 | +| clip_range | 0.0742 | +| entropy_loss | -7.28 | +| explained_variance | 0.321 | +| learning_rate | 4.92e-05 | +| loss | -0.0329 | +| n_updates | 22392 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000183 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.419 | +| time/ | | +| fps | 1403 | +| iterations | 1645 | +| time_elapsed | 2400 | +| total_timesteps | 3368960 | +| train/ | | +| approx_kl | 0.011283195 | +| clip_fraction | 0.31 | +| clip_range | 0.0742 | +| entropy_loss | -7.35 | +| explained_variance | 0.35 | +| learning_rate | 4.92e-05 | +| loss | -0.0312 | +| n_updates | 22396 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000111 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.417 | +| time/ | | +| fps | 1403 | +| iterations | 1646 | +| time_elapsed | 2402 | +| total_timesteps | 3371008 | +| train/ | | +| approx_kl | 0.010176293 | +| clip_fraction | 0.312 | +| clip_range | 0.0742 | +| entropy_loss | -7.43 | +| explained_variance | -0.112 | +| learning_rate | 4.92e-05 | +| loss | -0.0371 | +| n_updates | 22400 | +| policy_gradient_loss | -0.0228 | +| value_loss | 0.000111 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.424 | +| time/ | | +| fps | 1403 | +| iterations | 1647 | +| time_elapsed | 2403 | +| total_timesteps | 3373056 | +| train/ | | +| approx_kl | 0.010695912 | +| clip_fraction | 0.317 | +| clip_range | 0.0742 | +| entropy_loss | -7.15 | +| explained_variance | 0.545 | +| learning_rate | 4.92e-05 | +| loss | -0.0384 | +| n_updates | 22404 | +| policy_gradient_loss | -0.0219 | +| value_loss | 0.000101 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.427 | +| time/ | | +| fps | 1403 | +| iterations | 1648 | +| time_elapsed | 2405 | +| total_timesteps | 3375104 | +| train/ | | +| approx_kl | 0.008274883 | +| clip_fraction | 0.292 | +| clip_range | 0.0742 | +| entropy_loss | -7.17 | +| explained_variance | 0.227 | +| learning_rate | 4.92e-05 | +| loss | -0.0249 | +| n_updates | 22408 | +| policy_gradient_loss | -0.0146 | +| value_loss | 0.000256 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.417 | +| time/ | | +| fps | 1403 | +| iterations | 1649 | +| time_elapsed | 2406 | +| total_timesteps | 3377152 | +| train/ | | +| approx_kl | 0.009336231 | +| clip_fraction | 0.288 | +| clip_range | 0.0742 | +| entropy_loss | -7.32 | +| explained_variance | -0.00458 | +| learning_rate | 4.92e-05 | +| loss | -0.0334 | +| n_updates | 22412 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000284 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.414 | +| time/ | | +| fps | 1403 | +| iterations | 1650 | +| time_elapsed | 2407 | +| total_timesteps | 3379200 | +| train/ | | +| approx_kl | 0.01172833 | +| clip_fraction | 0.317 | +| clip_range | 0.0742 | +| entropy_loss | -6.88 | +| explained_variance | 0.234 | +| learning_rate | 4.92e-05 | +| loss | -0.0395 | +| n_updates | 22416 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000165 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.414 | +| time/ | | +| fps | 1403 | +| iterations | 1651 | +| time_elapsed | 2409 | +| total_timesteps | 3381248 | +| train/ | | +| approx_kl | 0.010735556 | +| clip_fraction | 0.312 | +| clip_range | 0.0742 | +| entropy_loss | -7.31 | +| explained_variance | 0.429 | +| learning_rate | 4.92e-05 | +| loss | -0.0355 | +| n_updates | 22420 | +| policy_gradient_loss | -0.0231 | +| value_loss | 6.89e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.405 | +| time/ | | +| fps | 1403 | +| iterations | 1652 | +| time_elapsed | 2410 | +| total_timesteps | 3383296 | +| train/ | | +| approx_kl | 0.011781139 | +| clip_fraction | 0.292 | +| clip_range | 0.0742 | +| entropy_loss | -7.4 | +| explained_variance | -0.127 | +| learning_rate | 4.92e-05 | +| loss | -0.0313 | +| n_updates | 22424 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000166 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.404 | +| time/ | | +| fps | 1403 | +| iterations | 1653 | +| time_elapsed | 2412 | +| total_timesteps | 3385344 | +| train/ | | +| approx_kl | 0.009813525 | +| clip_fraction | 0.286 | +| clip_range | 0.0742 | +| entropy_loss | -6.94 | +| explained_variance | 0.548 | +| learning_rate | 4.92e-05 | +| loss | -0.0311 | +| n_updates | 22428 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000131 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.401 | +| time/ | | +| fps | 1403 | +| iterations | 1654 | +| time_elapsed | 2413 | +| total_timesteps | 3387392 | +| train/ | | +| approx_kl | 0.009065384 | +| clip_fraction | 0.29 | +| clip_range | 0.0742 | +| entropy_loss | -6.91 | +| explained_variance | 0.595 | +| learning_rate | 4.92e-05 | +| loss | -0.0264 | +| n_updates | 22432 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000146 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.401 | +| time/ | | +| fps | 1403 | +| iterations | 1655 | +| time_elapsed | 2415 | +| total_timesteps | 3389440 | +| train/ | | +| approx_kl | 0.010432331 | +| clip_fraction | 0.301 | +| clip_range | 0.0742 | +| entropy_loss | -6.96 | +| explained_variance | 0.567 | +| learning_rate | 4.92e-05 | +| loss | -0.0322 | +| n_updates | 22436 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000159 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.403 | +| time/ | | +| fps | 1403 | +| iterations | 1656 | +| time_elapsed | 2416 | +| total_timesteps | 3391488 | +| train/ | | +| approx_kl | 0.010060791 | +| clip_fraction | 0.327 | +| clip_range | 0.0742 | +| entropy_loss | -7.43 | +| explained_variance | 0.0322 | +| learning_rate | 4.92e-05 | +| loss | -0.0352 | +| n_updates | 22440 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000193 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.404 | +| time/ | | +| fps | 1403 | +| iterations | 1657 | +| time_elapsed | 2418 | +| total_timesteps | 3393536 | +| train/ | | +| approx_kl | 0.008167506 | +| clip_fraction | 0.278 | +| clip_range | 0.0742 | +| entropy_loss | -7.5 | +| explained_variance | 0.0811 | +| learning_rate | 4.92e-05 | +| loss | -0.029 | +| n_updates | 22444 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.00023 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.403 | +| time/ | | +| fps | 1403 | +| iterations | 1658 | +| time_elapsed | 2419 | +| total_timesteps | 3395584 | +| train/ | | +| approx_kl | 0.010911541 | +| clip_fraction | 0.314 | +| clip_range | 0.0742 | +| entropy_loss | -7.2 | +| explained_variance | 0.196 | +| learning_rate | 4.92e-05 | +| loss | -0.0343 | +| n_updates | 22448 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000142 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.397 | +| time/ | | +| fps | 1403 | +| iterations | 1659 | +| time_elapsed | 2421 | +| total_timesteps | 3397632 | +| train/ | | +| approx_kl | 0.008280824 | +| clip_fraction | 0.265 | +| clip_range | 0.0742 | +| entropy_loss | -7.06 | +| explained_variance | -0.0753 | +| learning_rate | 4.92e-05 | +| loss | -0.0323 | +| n_updates | 22452 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000336 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.398 | +| time/ | | +| fps | 1403 | +| iterations | 1660 | +| time_elapsed | 2422 | +| total_timesteps | 3399680 | +| train/ | | +| approx_kl | 0.009392599 | +| clip_fraction | 0.29 | +| clip_range | 0.0742 | +| entropy_loss | -7.34 | +| explained_variance | -0.0833 | +| learning_rate | 4.92e-05 | +| loss | -0.0349 | +| n_updates | 22456 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000208 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.398 | +| time/ | | +| fps | 1403 | +| iterations | 1661 | +| time_elapsed | 2423 | +| total_timesteps | 3401728 | +| train/ | | +| approx_kl | 0.008828975 | +| clip_fraction | 0.304 | +| clip_range | 0.0742 | +| entropy_loss | -7.28 | +| explained_variance | 0.199 | +| learning_rate | 4.92e-05 | +| loss | -0.0344 | +| n_updates | 22460 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000215 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.392 | +| time/ | | +| fps | 1403 | +| iterations | 1662 | +| time_elapsed | 2425 | +| total_timesteps | 3403776 | +| train/ | | +| approx_kl | 0.009069447 | +| clip_fraction | 0.322 | +| clip_range | 0.0741 | +| entropy_loss | -7.45 | +| explained_variance | -0.0691 | +| learning_rate | 4.92e-05 | +| loss | -0.0357 | +| n_updates | 22464 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000131 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.387 | +| time/ | | +| fps | 1403 | +| iterations | 1663 | +| time_elapsed | 2426 | +| total_timesteps | 3405824 | +| train/ | | +| approx_kl | 0.009768834 | +| clip_fraction | 0.269 | +| clip_range | 0.0741 | +| entropy_loss | -7.11 | +| explained_variance | 0.4 | +| learning_rate | 4.92e-05 | +| loss | -0.024 | +| n_updates | 22468 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000211 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.391 | +| time/ | | +| fps | 1403 | +| iterations | 1664 | +| time_elapsed | 2428 | +| total_timesteps | 3407872 | +| train/ | | +| approx_kl | 0.009965707 | +| clip_fraction | 0.297 | +| clip_range | 0.0741 | +| entropy_loss | -7.25 | +| explained_variance | 0.32 | +| learning_rate | 4.92e-05 | +| loss | -0.0341 | +| n_updates | 22472 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.00015 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.387 | +| time/ | | +| fps | 1403 | +| iterations | 1665 | +| time_elapsed | 2429 | +| total_timesteps | 3409920 | +| train/ | | +| approx_kl | 0.009049401 | +| clip_fraction | 0.259 | +| clip_range | 0.0741 | +| entropy_loss | -6.92 | +| explained_variance | 0.141 | +| learning_rate | 4.92e-05 | +| loss | -0.0239 | +| n_updates | 22476 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000283 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.386 | +| time/ | | +| fps | 1403 | +| iterations | 1666 | +| time_elapsed | 2431 | +| total_timesteps | 3411968 | +| train/ | | +| approx_kl | 0.009813899 | +| clip_fraction | 0.306 | +| clip_range | 0.0741 | +| entropy_loss | -7.08 | +| explained_variance | 0.275 | +| learning_rate | 4.92e-05 | +| loss | -0.0309 | +| n_updates | 22480 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000144 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1403 | +| iterations | 1667 | +| time_elapsed | 2432 | +| total_timesteps | 3414016 | +| train/ | | +| approx_kl | 0.011286339 | +| clip_fraction | 0.307 | +| clip_range | 0.0741 | +| entropy_loss | -7.28 | +| explained_variance | 0.244 | +| learning_rate | 4.92e-05 | +| loss | -0.0326 | +| n_updates | 22484 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000199 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1403 | +| iterations | 1668 | +| time_elapsed | 2433 | +| total_timesteps | 3416064 | +| train/ | | +| approx_kl | 0.008904435 | +| clip_fraction | 0.319 | +| clip_range | 0.0741 | +| entropy_loss | -7.24 | +| explained_variance | 0.34 | +| learning_rate | 4.92e-05 | +| loss | -0.04 | +| n_updates | 22488 | +| policy_gradient_loss | -0.0219 | +| value_loss | 9.94e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1403 | +| iterations | 1669 | +| time_elapsed | 2435 | +| total_timesteps | 3418112 | +| train/ | | +| approx_kl | 0.0104032215 | +| clip_fraction | 0.313 | +| clip_range | 0.0741 | +| entropy_loss | -7.06 | +| explained_variance | 0.314 | +| learning_rate | 4.92e-05 | +| loss | -0.0205 | +| n_updates | 22492 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000264 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1403 | +| iterations | 1670 | +| time_elapsed | 2436 | +| total_timesteps | 3420160 | +| train/ | | +| approx_kl | 0.009459206 | +| clip_fraction | 0.334 | +| clip_range | 0.0741 | +| entropy_loss | -7.2 | +| explained_variance | 0.51 | +| learning_rate | 4.92e-05 | +| loss | -0.0368 | +| n_updates | 22496 | +| policy_gradient_loss | -0.0229 | +| value_loss | 9.58e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1403 | +| iterations | 1671 | +| time_elapsed | 2438 | +| total_timesteps | 3422208 | +| train/ | | +| approx_kl | 0.008351186 | +| clip_fraction | 0.291 | +| clip_range | 0.0741 | +| entropy_loss | -7.42 | +| explained_variance | 0.0879 | +| learning_rate | 4.92e-05 | +| loss | -0.0359 | +| n_updates | 22500 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000128 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1403 | +| iterations | 1672 | +| time_elapsed | 2439 | +| total_timesteps | 3424256 | +| train/ | | +| approx_kl | 0.011114607 | +| clip_fraction | 0.327 | +| clip_range | 0.0741 | +| entropy_loss | -7.23 | +| explained_variance | -0.137 | +| learning_rate | 4.92e-05 | +| loss | -0.0365 | +| n_updates | 22504 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000121 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1403 | +| iterations | 1673 | +| time_elapsed | 2441 | +| total_timesteps | 3426304 | +| train/ | | +| approx_kl | 0.010816306 | +| clip_fraction | 0.32 | +| clip_range | 0.0741 | +| entropy_loss | -7.01 | +| explained_variance | 0.279 | +| learning_rate | 4.92e-05 | +| loss | -0.0295 | +| n_updates | 22508 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000244 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1403 | +| iterations | 1674 | +| time_elapsed | 2442 | +| total_timesteps | 3428352 | +| train/ | | +| approx_kl | 0.01053492 | +| clip_fraction | 0.305 | +| clip_range | 0.0741 | +| entropy_loss | -6.95 | +| explained_variance | 0.419 | +| learning_rate | 4.92e-05 | +| loss | -0.0308 | +| n_updates | 22512 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000168 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1403 | +| iterations | 1675 | +| time_elapsed | 2443 | +| total_timesteps | 3430400 | +| train/ | | +| approx_kl | 0.010775639 | +| clip_fraction | 0.306 | +| clip_range | 0.0741 | +| entropy_loss | -7.29 | +| explained_variance | 0.0903 | +| learning_rate | 4.92e-05 | +| loss | -0.0293 | +| n_updates | 22516 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000226 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1403 | +| iterations | 1676 | +| time_elapsed | 2445 | +| total_timesteps | 3432448 | +| train/ | | +| approx_kl | 0.011531316 | +| clip_fraction | 0.298 | +| clip_range | 0.0741 | +| entropy_loss | -7.09 | +| explained_variance | 0.485 | +| learning_rate | 4.92e-05 | +| loss | -0.0314 | +| n_updates | 22520 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000189 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1403 | +| iterations | 1677 | +| time_elapsed | 2446 | +| total_timesteps | 3434496 | +| train/ | | +| approx_kl | 0.009819163 | +| clip_fraction | 0.317 | +| clip_range | 0.0741 | +| entropy_loss | -7.2 | +| explained_variance | 0.339 | +| learning_rate | 4.92e-05 | +| loss | -0.0301 | +| n_updates | 22524 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000147 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1403 | +| iterations | 1678 | +| time_elapsed | 2448 | +| total_timesteps | 3436544 | +| train/ | | +| approx_kl | 0.011633467 | +| clip_fraction | 0.362 | +| clip_range | 0.0741 | +| entropy_loss | -7.2 | +| explained_variance | 0.433 | +| learning_rate | 4.92e-05 | +| loss | -0.0331 | +| n_updates | 22528 | +| policy_gradient_loss | -0.0223 | +| value_loss | 9.03e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1403 | +| iterations | 1679 | +| time_elapsed | 2449 | +| total_timesteps | 3438592 | +| train/ | | +| approx_kl | 0.010293963 | +| clip_fraction | 0.324 | +| clip_range | 0.0741 | +| entropy_loss | -7.23 | +| explained_variance | 0.664 | +| learning_rate | 4.92e-05 | +| loss | -0.0381 | +| n_updates | 22532 | +| policy_gradient_loss | -0.022 | +| value_loss | 6.06e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1403 | +| iterations | 1680 | +| time_elapsed | 2451 | +| total_timesteps | 3440640 | +| train/ | | +| approx_kl | 0.00870499 | +| clip_fraction | 0.282 | +| clip_range | 0.0741 | +| entropy_loss | -7.28 | +| explained_variance | 0.38 | +| learning_rate | 4.92e-05 | +| loss | -0.0305 | +| n_updates | 22536 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000132 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1403 | +| iterations | 1681 | +| time_elapsed | 2452 | +| total_timesteps | 3442688 | +| train/ | | +| approx_kl | 0.00985737 | +| clip_fraction | 0.301 | +| clip_range | 0.0741 | +| entropy_loss | -6.96 | +| explained_variance | 0.454 | +| learning_rate | 4.92e-05 | +| loss | -0.0278 | +| n_updates | 22540 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000252 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1403 | +| iterations | 1682 | +| time_elapsed | 2453 | +| total_timesteps | 3444736 | +| train/ | | +| approx_kl | 0.008987977 | +| clip_fraction | 0.269 | +| clip_range | 0.0741 | +| entropy_loss | -7.5 | +| explained_variance | -0.0608 | +| learning_rate | 4.92e-05 | +| loss | -0.0322 | +| n_updates | 22544 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000174 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1403 | +| iterations | 1683 | +| time_elapsed | 2455 | +| total_timesteps | 3446784 | +| train/ | | +| approx_kl | 0.010632809 | +| clip_fraction | 0.279 | +| clip_range | 0.0741 | +| entropy_loss | -7.26 | +| explained_variance | 0.0707 | +| learning_rate | 4.92e-05 | +| loss | -0.0302 | +| n_updates | 22548 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000136 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1403 | +| iterations | 1684 | +| time_elapsed | 2456 | +| total_timesteps | 3448832 | +| train/ | | +| approx_kl | 0.009666043 | +| clip_fraction | 0.277 | +| clip_range | 0.0741 | +| entropy_loss | -7.15 | +| explained_variance | 0.173 | +| learning_rate | 4.92e-05 | +| loss | -0.0357 | +| n_updates | 22552 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000256 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1403 | +| iterations | 1685 | +| time_elapsed | 2458 | +| total_timesteps | 3450880 | +| train/ | | +| approx_kl | 0.010957915 | +| clip_fraction | 0.3 | +| clip_range | 0.0741 | +| entropy_loss | -7.18 | +| explained_variance | 0.339 | +| learning_rate | 4.92e-05 | +| loss | -0.0251 | +| n_updates | 22556 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000218 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1403 | +| iterations | 1686 | +| time_elapsed | 2459 | +| total_timesteps | 3452928 | +| train/ | | +| approx_kl | 0.010558611 | +| clip_fraction | 0.316 | +| clip_range | 0.0741 | +| entropy_loss | -7.36 | +| explained_variance | 0.389 | +| learning_rate | 4.92e-05 | +| loss | -0.0337 | +| n_updates | 22560 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.00011 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1403 | +| iterations | 1687 | +| time_elapsed | 2461 | +| total_timesteps | 3454976 | +| train/ | | +| approx_kl | 0.010499931 | +| clip_fraction | 0.296 | +| clip_range | 0.0741 | +| entropy_loss | -6.92 | +| explained_variance | 0.448 | +| learning_rate | 4.92e-05 | +| loss | -0.034 | +| n_updates | 22564 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.00025 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1403 | +| iterations | 1688 | +| time_elapsed | 2462 | +| total_timesteps | 3457024 | +| train/ | | +| approx_kl | 0.011321452 | +| clip_fraction | 0.349 | +| clip_range | 0.0741 | +| entropy_loss | -7.41 | +| explained_variance | 0.335 | +| learning_rate | 4.92e-05 | +| loss | -0.0378 | +| n_updates | 22568 | +| policy_gradient_loss | -0.0257 | +| value_loss | 7.45e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1403 | +| iterations | 1689 | +| time_elapsed | 2463 | +| total_timesteps | 3459072 | +| train/ | | +| approx_kl | 0.010469512 | +| clip_fraction | 0.305 | +| clip_range | 0.0741 | +| entropy_loss | -7.23 | +| explained_variance | 0.213 | +| learning_rate | 4.92e-05 | +| loss | -0.0344 | +| n_updates | 22572 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000202 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1403 | +| iterations | 1690 | +| time_elapsed | 2465 | +| total_timesteps | 3461120 | +| train/ | | +| approx_kl | 0.010849438 | +| clip_fraction | 0.303 | +| clip_range | 0.0741 | +| entropy_loss | -7.12 | +| explained_variance | 0.421 | +| learning_rate | 4.92e-05 | +| loss | -0.0291 | +| n_updates | 22576 | +| policy_gradient_loss | -0.0211 | +| value_loss | 9.91e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1403 | +| iterations | 1691 | +| time_elapsed | 2466 | +| total_timesteps | 3463168 | +| train/ | | +| approx_kl | 0.010613149 | +| clip_fraction | 0.302 | +| clip_range | 0.0741 | +| entropy_loss | -7.17 | +| explained_variance | 0.238 | +| learning_rate | 4.92e-05 | +| loss | -0.0333 | +| n_updates | 22580 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000282 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1403 | +| iterations | 1692 | +| time_elapsed | 2468 | +| total_timesteps | 3465216 | +| train/ | | +| approx_kl | 0.010964377 | +| clip_fraction | 0.324 | +| clip_range | 0.0741 | +| entropy_loss | -7.23 | +| explained_variance | 0.221 | +| learning_rate | 4.92e-05 | +| loss | -0.0374 | +| n_updates | 22584 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.00024 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1404 | +| iterations | 1693 | +| time_elapsed | 2469 | +| total_timesteps | 3467264 | +| train/ | | +| approx_kl | 0.010862388 | +| clip_fraction | 0.323 | +| clip_range | 0.0741 | +| entropy_loss | -7.15 | +| explained_variance | 0.421 | +| learning_rate | 4.92e-05 | +| loss | -0.0388 | +| n_updates | 22588 | +| policy_gradient_loss | -0.0237 | +| value_loss | 0.000129 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1403 | +| iterations | 1694 | +| time_elapsed | 2471 | +| total_timesteps | 3469312 | +| train/ | | +| approx_kl | 0.0112155955 | +| clip_fraction | 0.322 | +| clip_range | 0.0741 | +| entropy_loss | -7.4 | +| explained_variance | -0.138 | +| learning_rate | 4.92e-05 | +| loss | -0.0388 | +| n_updates | 22592 | +| policy_gradient_loss | -0.0233 | +| value_loss | 8e-05 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1403 | +| iterations | 1695 | +| time_elapsed | 2472 | +| total_timesteps | 3471360 | +| train/ | | +| approx_kl | 0.00886405 | +| clip_fraction | 0.293 | +| clip_range | 0.0741 | +| entropy_loss | -7.39 | +| explained_variance | 0.189 | +| learning_rate | 4.92e-05 | +| loss | -0.0339 | +| n_updates | 22596 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000182 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1404 | +| iterations | 1696 | +| time_elapsed | 2473 | +| total_timesteps | 3473408 | +| train/ | | +| approx_kl | 0.009141834 | +| clip_fraction | 0.298 | +| clip_range | 0.0741 | +| entropy_loss | -7.22 | +| explained_variance | 0.114 | +| learning_rate | 4.92e-05 | +| loss | -0.027 | +| n_updates | 22600 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000197 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1404 | +| iterations | 1697 | +| time_elapsed | 2475 | +| total_timesteps | 3475456 | +| train/ | | +| approx_kl | 0.011643207 | +| clip_fraction | 0.305 | +| clip_range | 0.0741 | +| entropy_loss | -7.08 | +| explained_variance | 0.0834 | +| learning_rate | 4.92e-05 | +| loss | -0.0335 | +| n_updates | 22604 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000204 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1404 | +| iterations | 1698 | +| time_elapsed | 2476 | +| total_timesteps | 3477504 | +| train/ | | +| approx_kl | 0.010372335 | +| clip_fraction | 0.291 | +| clip_range | 0.0741 | +| entropy_loss | -7.2 | +| explained_variance | -0.0848 | +| learning_rate | 4.92e-05 | +| loss | -0.0301 | +| n_updates | 22608 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000333 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1404 | +| iterations | 1699 | +| time_elapsed | 2478 | +| total_timesteps | 3479552 | +| train/ | | +| approx_kl | 0.010670263 | +| clip_fraction | 0.314 | +| clip_range | 0.0741 | +| entropy_loss | -6.92 | +| explained_variance | 0.439 | +| learning_rate | 4.92e-05 | +| loss | -0.033 | +| n_updates | 22612 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000121 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1404 | +| iterations | 1700 | +| time_elapsed | 2479 | +| total_timesteps | 3481600 | +| train/ | | +| approx_kl | 0.01046748 | +| clip_fraction | 0.315 | +| clip_range | 0.0741 | +| entropy_loss | -7.13 | +| explained_variance | 0.383 | +| learning_rate | 4.92e-05 | +| loss | -0.0298 | +| n_updates | 22616 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000168 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1404 | +| iterations | 1701 | +| time_elapsed | 2481 | +| total_timesteps | 3483648 | +| train/ | | +| approx_kl | 0.009233838 | +| clip_fraction | 0.293 | +| clip_range | 0.0741 | +| entropy_loss | -7.17 | +| explained_variance | 0.253 | +| learning_rate | 4.92e-05 | +| loss | -0.0268 | +| n_updates | 22620 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000208 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1404 | +| iterations | 1702 | +| time_elapsed | 2482 | +| total_timesteps | 3485696 | +| train/ | | +| approx_kl | 0.010393532 | +| clip_fraction | 0.307 | +| clip_range | 0.0741 | +| entropy_loss | -7.3 | +| explained_variance | 0.223 | +| learning_rate | 4.92e-05 | +| loss | -0.031 | +| n_updates | 22624 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000184 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1404 | +| iterations | 1703 | +| time_elapsed | 2483 | +| total_timesteps | 3487744 | +| train/ | | +| approx_kl | 0.010251608 | +| clip_fraction | 0.319 | +| clip_range | 0.0741 | +| entropy_loss | -7.37 | +| explained_variance | -0.101 | +| learning_rate | 4.92e-05 | +| loss | -0.0344 | +| n_updates | 22628 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000147 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1404 | +| iterations | 1704 | +| time_elapsed | 2485 | +| total_timesteps | 3489792 | +| train/ | | +| approx_kl | 0.012388058 | +| clip_fraction | 0.323 | +| clip_range | 0.0741 | +| entropy_loss | -7.19 | +| explained_variance | 0.295 | +| learning_rate | 4.92e-05 | +| loss | -0.0347 | +| n_updates | 22632 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.00014 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1404 | +| iterations | 1705 | +| time_elapsed | 2486 | +| total_timesteps | 3491840 | +| train/ | | +| approx_kl | 0.010783199 | +| clip_fraction | 0.299 | +| clip_range | 0.0741 | +| entropy_loss | -7.38 | +| explained_variance | 0.28 | +| learning_rate | 4.92e-05 | +| loss | -0.0292 | +| n_updates | 22636 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000129 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1404 | +| iterations | 1706 | +| time_elapsed | 2488 | +| total_timesteps | 3493888 | +| train/ | | +| approx_kl | 0.011397848 | +| clip_fraction | 0.296 | +| clip_range | 0.0741 | +| entropy_loss | -7.41 | +| explained_variance | -0.0308 | +| learning_rate | 4.92e-05 | +| loss | -0.033 | +| n_updates | 22640 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000184 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1404 | +| iterations | 1707 | +| time_elapsed | 2489 | +| total_timesteps | 3495936 | +| train/ | | +| approx_kl | 0.011405664 | +| clip_fraction | 0.281 | +| clip_range | 0.0741 | +| entropy_loss | -7.26 | +| explained_variance | 0.051 | +| learning_rate | 4.92e-05 | +| loss | -0.0323 | +| n_updates | 22644 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000324 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1404 | +| iterations | 1708 | +| time_elapsed | 2491 | +| total_timesteps | 3497984 | +| train/ | | +| approx_kl | 0.010982372 | +| clip_fraction | 0.33 | +| clip_range | 0.0741 | +| entropy_loss | -7.45 | +| explained_variance | -0.356 | +| learning_rate | 4.92e-05 | +| loss | -0.0434 | +| n_updates | 22648 | +| policy_gradient_loss | -0.0244 | +| value_loss | 8.64e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1404 | +| iterations | 1709 | +| time_elapsed | 2492 | +| total_timesteps | 3500032 | +| train/ | | +| approx_kl | 0.01049247 | +| clip_fraction | 0.331 | +| clip_range | 0.0741 | +| entropy_loss | -7.19 | +| explained_variance | 0.171 | +| learning_rate | 4.92e-05 | +| loss | -0.031 | +| n_updates | 22652 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000107 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1404 | +| iterations | 1710 | +| time_elapsed | 2494 | +| total_timesteps | 3502080 | +| train/ | | +| approx_kl | 0.011210966 | +| clip_fraction | 0.331 | +| clip_range | 0.0741 | +| entropy_loss | -7.33 | +| explained_variance | 0.26 | +| learning_rate | 4.92e-05 | +| loss | -0.036 | +| n_updates | 22656 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000186 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1404 | +| iterations | 1711 | +| time_elapsed | 2495 | +| total_timesteps | 3504128 | +| train/ | | +| approx_kl | 0.008355465 | +| clip_fraction | 0.275 | +| clip_range | 0.0741 | +| entropy_loss | -6.95 | +| explained_variance | 0.297 | +| learning_rate | 4.92e-05 | +| loss | -0.0344 | +| n_updates | 22660 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000296 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1404 | +| iterations | 1712 | +| time_elapsed | 2496 | +| total_timesteps | 3506176 | +| train/ | | +| approx_kl | 0.009837361 | +| clip_fraction | 0.317 | +| clip_range | 0.0741 | +| entropy_loss | -7.07 | +| explained_variance | 0.359 | +| learning_rate | 4.92e-05 | +| loss | -0.0229 | +| n_updates | 22664 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000242 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1404 | +| iterations | 1713 | +| time_elapsed | 2498 | +| total_timesteps | 3508224 | +| train/ | | +| approx_kl | 0.011977814 | +| clip_fraction | 0.347 | +| clip_range | 0.0741 | +| entropy_loss | -6.89 | +| explained_variance | 0.73 | +| learning_rate | 4.92e-05 | +| loss | -0.0429 | +| n_updates | 22668 | +| policy_gradient_loss | -0.0266 | +| value_loss | 6.21e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1404 | +| iterations | 1714 | +| time_elapsed | 2499 | +| total_timesteps | 3510272 | +| train/ | | +| approx_kl | 0.01118791 | +| clip_fraction | 0.305 | +| clip_range | 0.0741 | +| entropy_loss | -7.25 | +| explained_variance | 0.502 | +| learning_rate | 4.92e-05 | +| loss | -0.0358 | +| n_updates | 22672 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000104 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1404 | +| iterations | 1715 | +| time_elapsed | 2501 | +| total_timesteps | 3512320 | +| train/ | | +| approx_kl | 0.010896878 | +| clip_fraction | 0.309 | +| clip_range | 0.0741 | +| entropy_loss | -7.27 | +| explained_variance | 0.278 | +| learning_rate | 4.92e-05 | +| loss | -0.0312 | +| n_updates | 22676 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000168 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1404 | +| iterations | 1716 | +| time_elapsed | 2502 | +| total_timesteps | 3514368 | +| train/ | | +| approx_kl | 0.010667699 | +| clip_fraction | 0.322 | +| clip_range | 0.0741 | +| entropy_loss | -7.4 | +| explained_variance | -0.0195 | +| learning_rate | 4.92e-05 | +| loss | -0.0336 | +| n_updates | 22680 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000179 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1404 | +| iterations | 1717 | +| time_elapsed | 2504 | +| total_timesteps | 3516416 | +| train/ | | +| approx_kl | 0.008262299 | +| clip_fraction | 0.275 | +| clip_range | 0.0741 | +| entropy_loss | -7.01 | +| explained_variance | 0.191 | +| learning_rate | 4.92e-05 | +| loss | -0.0243 | +| n_updates | 22684 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000343 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1404 | +| iterations | 1718 | +| time_elapsed | 2505 | +| total_timesteps | 3518464 | +| train/ | | +| approx_kl | 0.008349969 | +| clip_fraction | 0.314 | +| clip_range | 0.0741 | +| entropy_loss | -7.43 | +| explained_variance | -0.48 | +| learning_rate | 4.92e-05 | +| loss | -0.0343 | +| n_updates | 22688 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000135 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1404 | +| iterations | 1719 | +| time_elapsed | 2506 | +| total_timesteps | 3520512 | +| train/ | | +| approx_kl | 0.010505278 | +| clip_fraction | 0.309 | +| clip_range | 0.0741 | +| entropy_loss | -7.25 | +| explained_variance | 0.209 | +| learning_rate | 4.92e-05 | +| loss | -0.0292 | +| n_updates | 22692 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000182 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1404 | +| iterations | 1720 | +| time_elapsed | 2508 | +| total_timesteps | 3522560 | +| train/ | | +| approx_kl | 0.010158733 | +| clip_fraction | 0.29 | +| clip_range | 0.0741 | +| entropy_loss | -7.15 | +| explained_variance | 0.452 | +| learning_rate | 4.92e-05 | +| loss | -0.0356 | +| n_updates | 22696 | +| policy_gradient_loss | -0.022 | +| value_loss | 9.65e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1404 | +| iterations | 1721 | +| time_elapsed | 2509 | +| total_timesteps | 3524608 | +| train/ | | +| approx_kl | 0.009624846 | +| clip_fraction | 0.285 | +| clip_range | 0.0741 | +| entropy_loss | -7.09 | +| explained_variance | 0.444 | +| learning_rate | 4.92e-05 | +| loss | -0.0313 | +| n_updates | 22700 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000195 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1404 | +| iterations | 1722 | +| time_elapsed | 2511 | +| total_timesteps | 3526656 | +| train/ | | +| approx_kl | 0.009430002 | +| clip_fraction | 0.308 | +| clip_range | 0.0741 | +| entropy_loss | -7.11 | +| explained_variance | 0.458 | +| learning_rate | 4.92e-05 | +| loss | -0.0327 | +| n_updates | 22704 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000104 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1404 | +| iterations | 1723 | +| time_elapsed | 2512 | +| total_timesteps | 3528704 | +| train/ | | +| approx_kl | 0.0092773605 | +| clip_fraction | 0.274 | +| clip_range | 0.0741 | +| entropy_loss | -7.15 | +| explained_variance | 0.36 | +| learning_rate | 4.92e-05 | +| loss | -0.0259 | +| n_updates | 22708 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000238 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1404 | +| iterations | 1724 | +| time_elapsed | 2513 | +| total_timesteps | 3530752 | +| train/ | | +| approx_kl | 0.009585254 | +| clip_fraction | 0.318 | +| clip_range | 0.0741 | +| entropy_loss | -7.49 | +| explained_variance | 0.176 | +| learning_rate | 4.92e-05 | +| loss | -0.0349 | +| n_updates | 22712 | +| policy_gradient_loss | -0.023 | +| value_loss | 0.000135 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1404 | +| iterations | 1725 | +| time_elapsed | 2515 | +| total_timesteps | 3532800 | +| train/ | | +| approx_kl | 0.009072827 | +| clip_fraction | 0.295 | +| clip_range | 0.0741 | +| entropy_loss | -7.37 | +| explained_variance | 0.0141 | +| learning_rate | 4.92e-05 | +| loss | -0.033 | +| n_updates | 22716 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000169 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1404 | +| iterations | 1726 | +| time_elapsed | 2516 | +| total_timesteps | 3534848 | +| train/ | | +| approx_kl | 0.009055141 | +| clip_fraction | 0.341 | +| clip_range | 0.0741 | +| entropy_loss | -7.33 | +| explained_variance | 0.288 | +| learning_rate | 4.92e-05 | +| loss | -0.0363 | +| n_updates | 22720 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000117 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1404 | +| iterations | 1727 | +| time_elapsed | 2518 | +| total_timesteps | 3536896 | +| train/ | | +| approx_kl | 0.008884897 | +| clip_fraction | 0.265 | +| clip_range | 0.0741 | +| entropy_loss | -6.92 | +| explained_variance | 0.331 | +| learning_rate | 4.92e-05 | +| loss | -0.0238 | +| n_updates | 22724 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.000337 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1404 | +| iterations | 1728 | +| time_elapsed | 2519 | +| total_timesteps | 3538944 | +| train/ | | +| approx_kl | 0.01003546 | +| clip_fraction | 0.315 | +| clip_range | 0.0741 | +| entropy_loss | -6.89 | +| explained_variance | 0.714 | +| learning_rate | 4.92e-05 | +| loss | -0.0366 | +| n_updates | 22728 | +| policy_gradient_loss | -0.0202 | +| value_loss | 8.29e-05 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1404 | +| iterations | 1729 | +| time_elapsed | 2521 | +| total_timesteps | 3540992 | +| train/ | | +| approx_kl | 0.01191959 | +| clip_fraction | 0.339 | +| clip_range | 0.0741 | +| entropy_loss | -7.46 | +| explained_variance | -0.23 | +| learning_rate | 4.92e-05 | +| loss | -0.0381 | +| n_updates | 22732 | +| policy_gradient_loss | -0.0224 | +| value_loss | 9.67e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1404 | +| iterations | 1730 | +| time_elapsed | 2522 | +| total_timesteps | 3543040 | +| train/ | | +| approx_kl | 0.010269232 | +| clip_fraction | 0.293 | +| clip_range | 0.0741 | +| entropy_loss | -6.88 | +| explained_variance | 0.495 | +| learning_rate | 4.92e-05 | +| loss | -0.0274 | +| n_updates | 22736 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000218 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1404 | +| iterations | 1731 | +| time_elapsed | 2523 | +| total_timesteps | 3545088 | +| train/ | | +| approx_kl | 0.00986528 | +| clip_fraction | 0.298 | +| clip_range | 0.0741 | +| entropy_loss | -7.25 | +| explained_variance | 0.289 | +| learning_rate | 4.92e-05 | +| loss | -0.0317 | +| n_updates | 22740 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000167 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1404 | +| iterations | 1732 | +| time_elapsed | 2525 | +| total_timesteps | 3547136 | +| train/ | | +| approx_kl | 0.008359746 | +| clip_fraction | 0.269 | +| clip_range | 0.0741 | +| entropy_loss | -7.22 | +| explained_variance | 0.248 | +| learning_rate | 4.92e-05 | +| loss | -0.0251 | +| n_updates | 22744 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000269 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1404 | +| iterations | 1733 | +| time_elapsed | 2526 | +| total_timesteps | 3549184 | +| train/ | | +| approx_kl | 0.013187993 | +| clip_fraction | 0.326 | +| clip_range | 0.0741 | +| entropy_loss | -7.49 | +| explained_variance | -0.0642 | +| learning_rate | 4.92e-05 | +| loss | -0.0397 | +| n_updates | 22748 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.00017 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1404 | +| iterations | 1734 | +| time_elapsed | 2528 | +| total_timesteps | 3551232 | +| train/ | | +| approx_kl | 0.010229768 | +| clip_fraction | 0.326 | +| clip_range | 0.0741 | +| entropy_loss | -7.24 | +| explained_variance | 0.476 | +| learning_rate | 4.92e-05 | +| loss | -0.0401 | +| n_updates | 22752 | +| policy_gradient_loss | -0.0219 | +| value_loss | 0.00018 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1404 | +| iterations | 1735 | +| time_elapsed | 2529 | +| total_timesteps | 3553280 | +| train/ | | +| approx_kl | 0.0108963195 | +| clip_fraction | 0.32 | +| clip_range | 0.0741 | +| entropy_loss | -7.44 | +| explained_variance | -0.199 | +| learning_rate | 4.92e-05 | +| loss | -0.0309 | +| n_updates | 22756 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000168 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1404 | +| iterations | 1736 | +| time_elapsed | 2531 | +| total_timesteps | 3555328 | +| train/ | | +| approx_kl | 0.012410029 | +| clip_fraction | 0.317 | +| clip_range | 0.0741 | +| entropy_loss | -7.2 | +| explained_variance | 0.212 | +| learning_rate | 4.92e-05 | +| loss | -0.0327 | +| n_updates | 22760 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000167 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1404 | +| iterations | 1737 | +| time_elapsed | 2532 | +| total_timesteps | 3557376 | +| train/ | | +| approx_kl | 0.011634598 | +| clip_fraction | 0.345 | +| clip_range | 0.0741 | +| entropy_loss | -6.94 | +| explained_variance | 0.363 | +| learning_rate | 4.92e-05 | +| loss | -0.0397 | +| n_updates | 22764 | +| policy_gradient_loss | -0.0266 | +| value_loss | 7.49e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1404 | +| iterations | 1738 | +| time_elapsed | 2533 | +| total_timesteps | 3559424 | +| train/ | | +| approx_kl | 0.010442875 | +| clip_fraction | 0.322 | +| clip_range | 0.0741 | +| entropy_loss | -6.82 | +| explained_variance | 0.54 | +| learning_rate | 4.92e-05 | +| loss | -0.0296 | +| n_updates | 22768 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000103 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1404 | +| iterations | 1739 | +| time_elapsed | 2535 | +| total_timesteps | 3561472 | +| train/ | | +| approx_kl | 0.01020856 | +| clip_fraction | 0.302 | +| clip_range | 0.0741 | +| entropy_loss | -6.72 | +| explained_variance | 0.78 | +| learning_rate | 4.92e-05 | +| loss | -0.029 | +| n_updates | 22772 | +| policy_gradient_loss | -0.02 | +| value_loss | 9.05e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1404 | +| iterations | 1740 | +| time_elapsed | 2536 | +| total_timesteps | 3563520 | +| train/ | | +| approx_kl | 0.010512402 | +| clip_fraction | 0.311 | +| clip_range | 0.0741 | +| entropy_loss | -7.36 | +| explained_variance | -0.0138 | +| learning_rate | 4.92e-05 | +| loss | -0.0288 | +| n_updates | 22776 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000148 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1404 | +| iterations | 1741 | +| time_elapsed | 2538 | +| total_timesteps | 3565568 | +| train/ | | +| approx_kl | 0.00857679 | +| clip_fraction | 0.3 | +| clip_range | 0.0741 | +| entropy_loss | -7.29 | +| explained_variance | 0.157 | +| learning_rate | 4.92e-05 | +| loss | -0.0338 | +| n_updates | 22780 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.00014 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1404 | +| iterations | 1742 | +| time_elapsed | 2539 | +| total_timesteps | 3567616 | +| train/ | | +| approx_kl | 0.012366517 | +| clip_fraction | 0.301 | +| clip_range | 0.0741 | +| entropy_loss | -7.23 | +| explained_variance | 0.231 | +| learning_rate | 4.92e-05 | +| loss | -0.0306 | +| n_updates | 22784 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000219 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1404 | +| iterations | 1743 | +| time_elapsed | 2541 | +| total_timesteps | 3569664 | +| train/ | | +| approx_kl | 0.010400236 | +| clip_fraction | 0.291 | +| clip_range | 0.0741 | +| entropy_loss | -7.1 | +| explained_variance | 0.236 | +| learning_rate | 4.92e-05 | +| loss | -0.0354 | +| n_updates | 22788 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000226 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1404 | +| iterations | 1744 | +| time_elapsed | 2542 | +| total_timesteps | 3571712 | +| train/ | | +| approx_kl | 0.010446122 | +| clip_fraction | 0.288 | +| clip_range | 0.0741 | +| entropy_loss | -7.42 | +| explained_variance | -0.0286 | +| learning_rate | 4.92e-05 | +| loss | -0.0335 | +| n_updates | 22792 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000173 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1404 | +| iterations | 1745 | +| time_elapsed | 2544 | +| total_timesteps | 3573760 | +| train/ | | +| approx_kl | 0.009124558 | +| clip_fraction | 0.282 | +| clip_range | 0.0741 | +| entropy_loss | -7.3 | +| explained_variance | -0.0882 | +| learning_rate | 4.92e-05 | +| loss | -0.0353 | +| n_updates | 22796 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000177 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1404 | +| iterations | 1746 | +| time_elapsed | 2545 | +| total_timesteps | 3575808 | +| train/ | | +| approx_kl | 0.008686537 | +| clip_fraction | 0.284 | +| clip_range | 0.0741 | +| entropy_loss | -6.94 | +| explained_variance | 0.549 | +| learning_rate | 4.92e-05 | +| loss | -0.0354 | +| n_updates | 22800 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000188 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1404 | +| iterations | 1747 | +| time_elapsed | 2546 | +| total_timesteps | 3577856 | +| train/ | | +| approx_kl | 0.011660706 | +| clip_fraction | 0.349 | +| clip_range | 0.0741 | +| entropy_loss | -7.04 | +| explained_variance | 0.688 | +| learning_rate | 4.92e-05 | +| loss | -0.034 | +| n_updates | 22804 | +| policy_gradient_loss | -0.0243 | +| value_loss | 6.86e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1404 | +| iterations | 1748 | +| time_elapsed | 2548 | +| total_timesteps | 3579904 | +| train/ | | +| approx_kl | 0.011293622 | +| clip_fraction | 0.307 | +| clip_range | 0.0741 | +| entropy_loss | -6.81 | +| explained_variance | 0.471 | +| learning_rate | 4.92e-05 | +| loss | -0.0312 | +| n_updates | 22808 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000213 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1404 | +| iterations | 1749 | +| time_elapsed | 2549 | +| total_timesteps | 3581952 | +| train/ | | +| approx_kl | 0.010582042 | +| clip_fraction | 0.336 | +| clip_range | 0.0741 | +| entropy_loss | -7.24 | +| explained_variance | 0.508 | +| learning_rate | 4.91e-05 | +| loss | -0.0444 | +| n_updates | 22812 | +| policy_gradient_loss | -0.0242 | +| value_loss | 6.24e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1404 | +| iterations | 1750 | +| time_elapsed | 2551 | +| total_timesteps | 3584000 | +| train/ | | +| approx_kl | 0.010796095 | +| clip_fraction | 0.302 | +| clip_range | 0.0741 | +| entropy_loss | -7.3 | +| explained_variance | 0.204 | +| learning_rate | 4.91e-05 | +| loss | -0.0287 | +| n_updates | 22816 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000204 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1404 | +| iterations | 1751 | +| time_elapsed | 2552 | +| total_timesteps | 3586048 | +| train/ | | +| approx_kl | 0.009990752 | +| clip_fraction | 0.333 | +| clip_range | 0.0741 | +| entropy_loss | -7.31 | +| explained_variance | 0.332 | +| learning_rate | 4.91e-05 | +| loss | -0.036 | +| n_updates | 22820 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1404 | +| iterations | 1752 | +| time_elapsed | 2554 | +| total_timesteps | 3588096 | +| train/ | | +| approx_kl | 0.010046698 | +| clip_fraction | 0.29 | +| clip_range | 0.0741 | +| entropy_loss | -7.49 | +| explained_variance | -0.0889 | +| learning_rate | 4.91e-05 | +| loss | -0.033 | +| n_updates | 22824 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.00026 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1404 | +| iterations | 1753 | +| time_elapsed | 2555 | +| total_timesteps | 3590144 | +| train/ | | +| approx_kl | 0.009804772 | +| clip_fraction | 0.287 | +| clip_range | 0.0741 | +| entropy_loss | -7.11 | +| explained_variance | 0.352 | +| learning_rate | 4.91e-05 | +| loss | -0.0281 | +| n_updates | 22828 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000277 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1404 | +| iterations | 1754 | +| time_elapsed | 2557 | +| total_timesteps | 3592192 | +| train/ | | +| approx_kl | 0.0109787015 | +| clip_fraction | 0.302 | +| clip_range | 0.0741 | +| entropy_loss | -7.3 | +| explained_variance | -0.07 | +| learning_rate | 4.91e-05 | +| loss | -0.0356 | +| n_updates | 22832 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000152 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1404 | +| iterations | 1755 | +| time_elapsed | 2558 | +| total_timesteps | 3594240 | +| train/ | | +| approx_kl | 0.009030737 | +| clip_fraction | 0.287 | +| clip_range | 0.0741 | +| entropy_loss | -6.95 | +| explained_variance | 0.429 | +| learning_rate | 4.91e-05 | +| loss | -0.0285 | +| n_updates | 22836 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000332 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1404 | +| iterations | 1756 | +| time_elapsed | 2559 | +| total_timesteps | 3596288 | +| train/ | | +| approx_kl | 0.010010931 | +| clip_fraction | 0.301 | +| clip_range | 0.0741 | +| entropy_loss | -6.96 | +| explained_variance | 0.365 | +| learning_rate | 4.91e-05 | +| loss | -0.0333 | +| n_updates | 22840 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000174 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1404 | +| iterations | 1757 | +| time_elapsed | 2561 | +| total_timesteps | 3598336 | +| train/ | | +| approx_kl | 0.009324577 | +| clip_fraction | 0.319 | +| clip_range | 0.0741 | +| entropy_loss | -7.02 | +| explained_variance | 0.644 | +| learning_rate | 4.91e-05 | +| loss | -0.0384 | +| n_updates | 22844 | +| policy_gradient_loss | -0.0228 | +| value_loss | 7.92e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1404 | +| iterations | 1758 | +| time_elapsed | 2562 | +| total_timesteps | 3600384 | +| train/ | | +| approx_kl | 0.00947549 | +| clip_fraction | 0.312 | +| clip_range | 0.0741 | +| entropy_loss | -7.13 | +| explained_variance | 0.275 | +| learning_rate | 4.91e-05 | +| loss | -0.0315 | +| n_updates | 22848 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000117 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1404 | +| iterations | 1759 | +| time_elapsed | 2564 | +| total_timesteps | 3602432 | +| train/ | | +| approx_kl | 0.011236742 | +| clip_fraction | 0.305 | +| clip_range | 0.0741 | +| entropy_loss | -7.33 | +| explained_variance | 0.00606 | +| learning_rate | 4.91e-05 | +| loss | -0.0369 | +| n_updates | 22852 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000151 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1404 | +| iterations | 1760 | +| time_elapsed | 2565 | +| total_timesteps | 3604480 | +| train/ | | +| approx_kl | 0.011267061 | +| clip_fraction | 0.322 | +| clip_range | 0.0741 | +| entropy_loss | -7.37 | +| explained_variance | -0.183 | +| learning_rate | 4.91e-05 | +| loss | -0.036 | +| n_updates | 22856 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000141 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1404 | +| iterations | 1761 | +| time_elapsed | 2567 | +| total_timesteps | 3606528 | +| train/ | | +| approx_kl | 0.010569053 | +| clip_fraction | 0.312 | +| clip_range | 0.0741 | +| entropy_loss | -7.14 | +| explained_variance | 0.00639 | +| learning_rate | 4.91e-05 | +| loss | -0.0272 | +| n_updates | 22860 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.00034 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1404 | +| iterations | 1762 | +| time_elapsed | 2568 | +| total_timesteps | 3608576 | +| train/ | | +| approx_kl | 0.011606757 | +| clip_fraction | 0.338 | +| clip_range | 0.0741 | +| entropy_loss | -7.34 | +| explained_variance | 0.24 | +| learning_rate | 4.91e-05 | +| loss | -0.0413 | +| n_updates | 22864 | +| policy_gradient_loss | -0.0251 | +| value_loss | 8.67e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1404 | +| iterations | 1763 | +| time_elapsed | 2569 | +| total_timesteps | 3610624 | +| train/ | | +| approx_kl | 0.011091358 | +| clip_fraction | 0.306 | +| clip_range | 0.0741 | +| entropy_loss | -7.14 | +| explained_variance | 0.444 | +| learning_rate | 4.91e-05 | +| loss | -0.0312 | +| n_updates | 22868 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000172 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1404 | +| iterations | 1764 | +| time_elapsed | 2571 | +| total_timesteps | 3612672 | +| train/ | | +| approx_kl | 0.010505263 | +| clip_fraction | 0.291 | +| clip_range | 0.0741 | +| entropy_loss | -7.29 | +| explained_variance | 0.251 | +| learning_rate | 4.91e-05 | +| loss | -0.0241 | +| n_updates | 22872 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000172 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1405 | +| iterations | 1765 | +| time_elapsed | 2572 | +| total_timesteps | 3614720 | +| train/ | | +| approx_kl | 0.010978364 | +| clip_fraction | 0.336 | +| clip_range | 0.0741 | +| entropy_loss | -7.42 | +| explained_variance | -0.0317 | +| learning_rate | 4.91e-05 | +| loss | -0.036 | +| n_updates | 22876 | +| policy_gradient_loss | -0.022 | +| value_loss | 0.000161 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1405 | +| iterations | 1766 | +| time_elapsed | 2574 | +| total_timesteps | 3616768 | +| train/ | | +| approx_kl | 0.01158668 | +| clip_fraction | 0.286 | +| clip_range | 0.0741 | +| entropy_loss | -6.92 | +| explained_variance | 0.319 | +| learning_rate | 4.91e-05 | +| loss | -0.0279 | +| n_updates | 22880 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000265 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1405 | +| iterations | 1767 | +| time_elapsed | 2575 | +| total_timesteps | 3618816 | +| train/ | | +| approx_kl | 0.010855652 | +| clip_fraction | 0.302 | +| clip_range | 0.0741 | +| entropy_loss | -6.97 | +| explained_variance | 0.358 | +| learning_rate | 4.91e-05 | +| loss | -0.0335 | +| n_updates | 22884 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.00019 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1405 | +| iterations | 1768 | +| time_elapsed | 2577 | +| total_timesteps | 3620864 | +| train/ | | +| approx_kl | 0.009380176 | +| clip_fraction | 0.266 | +| clip_range | 0.0741 | +| entropy_loss | -7.11 | +| explained_variance | 0.312 | +| learning_rate | 4.91e-05 | +| loss | -0.0296 | +| n_updates | 22888 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000263 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1405 | +| iterations | 1769 | +| time_elapsed | 2578 | +| total_timesteps | 3622912 | +| train/ | | +| approx_kl | 0.008454721 | +| clip_fraction | 0.307 | +| clip_range | 0.0741 | +| entropy_loss | -7.4 | +| explained_variance | -0.0258 | +| learning_rate | 4.91e-05 | +| loss | -0.0363 | +| n_updates | 22892 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000111 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1405 | +| iterations | 1770 | +| time_elapsed | 2579 | +| total_timesteps | 3624960 | +| train/ | | +| approx_kl | 0.01006092 | +| clip_fraction | 0.304 | +| clip_range | 0.0741 | +| entropy_loss | -7.21 | +| explained_variance | 0.378 | +| learning_rate | 4.91e-05 | +| loss | -0.0312 | +| n_updates | 22896 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.00022 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1405 | +| iterations | 1771 | +| time_elapsed | 2581 | +| total_timesteps | 3627008 | +| train/ | | +| approx_kl | 0.009992994 | +| clip_fraction | 0.274 | +| clip_range | 0.0741 | +| entropy_loss | -6.98 | +| explained_variance | 0.513 | +| learning_rate | 4.91e-05 | +| loss | -0.027 | +| n_updates | 22900 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000208 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1405 | +| iterations | 1772 | +| time_elapsed | 2582 | +| total_timesteps | 3629056 | +| train/ | | +| approx_kl | 0.009521935 | +| clip_fraction | 0.311 | +| clip_range | 0.0741 | +| entropy_loss | -7.22 | +| explained_variance | 0.226 | +| learning_rate | 4.91e-05 | +| loss | -0.0319 | +| n_updates | 22904 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000278 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1405 | +| iterations | 1773 | +| time_elapsed | 2584 | +| total_timesteps | 3631104 | +| train/ | | +| approx_kl | 0.012944467 | +| clip_fraction | 0.357 | +| clip_range | 0.0741 | +| entropy_loss | -7.28 | +| explained_variance | 0.3 | +| learning_rate | 4.91e-05 | +| loss | -0.0347 | +| n_updates | 22908 | +| policy_gradient_loss | -0.026 | +| value_loss | 0.000108 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1405 | +| iterations | 1774 | +| time_elapsed | 2585 | +| total_timesteps | 3633152 | +| train/ | | +| approx_kl | 0.01325714 | +| clip_fraction | 0.309 | +| clip_range | 0.0741 | +| entropy_loss | -6.97 | +| explained_variance | 0.473 | +| learning_rate | 4.91e-05 | +| loss | -0.0257 | +| n_updates | 22912 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000242 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1405 | +| iterations | 1775 | +| time_elapsed | 2587 | +| total_timesteps | 3635200 | +| train/ | | +| approx_kl | 0.011754364 | +| clip_fraction | 0.325 | +| clip_range | 0.0741 | +| entropy_loss | -7.35 | +| explained_variance | -0.0731 | +| learning_rate | 4.91e-05 | +| loss | -0.0323 | +| n_updates | 22916 | +| policy_gradient_loss | -0.0223 | +| value_loss | 0.000141 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1405 | +| iterations | 1776 | +| time_elapsed | 2588 | +| total_timesteps | 3637248 | +| train/ | | +| approx_kl | 0.010660892 | +| clip_fraction | 0.307 | +| clip_range | 0.0741 | +| entropy_loss | -7.24 | +| explained_variance | 0.269 | +| learning_rate | 4.91e-05 | +| loss | -0.0304 | +| n_updates | 22920 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000206 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1405 | +| iterations | 1777 | +| time_elapsed | 2589 | +| total_timesteps | 3639296 | +| train/ | | +| approx_kl | 0.011504581 | +| clip_fraction | 0.304 | +| clip_range | 0.0741 | +| entropy_loss | -7.2 | +| explained_variance | 0.199 | +| learning_rate | 4.91e-05 | +| loss | -0.031 | +| n_updates | 22924 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000214 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1405 | +| iterations | 1778 | +| time_elapsed | 2591 | +| total_timesteps | 3641344 | +| train/ | | +| approx_kl | 0.01052327 | +| clip_fraction | 0.331 | +| clip_range | 0.0741 | +| entropy_loss | -7.09 | +| explained_variance | 0.129 | +| learning_rate | 4.91e-05 | +| loss | -0.0372 | +| n_updates | 22928 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000122 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1405 | +| iterations | 1779 | +| time_elapsed | 2592 | +| total_timesteps | 3643392 | +| train/ | | +| approx_kl | 0.0108541455 | +| clip_fraction | 0.328 | +| clip_range | 0.0741 | +| entropy_loss | -7.16 | +| explained_variance | 0.288 | +| learning_rate | 4.91e-05 | +| loss | -0.0338 | +| n_updates | 22932 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000141 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1405 | +| iterations | 1780 | +| time_elapsed | 2594 | +| total_timesteps | 3645440 | +| train/ | | +| approx_kl | 0.009485879 | +| clip_fraction | 0.32 | +| clip_range | 0.0741 | +| entropy_loss | -6.79 | +| explained_variance | 0.821 | +| learning_rate | 4.91e-05 | +| loss | -0.0322 | +| n_updates | 22936 | +| policy_gradient_loss | -0.0203 | +| value_loss | 6.15e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1405 | +| iterations | 1781 | +| time_elapsed | 2595 | +| total_timesteps | 3647488 | +| train/ | | +| approx_kl | 0.01203778 | +| clip_fraction | 0.301 | +| clip_range | 0.0741 | +| entropy_loss | -7.11 | +| explained_variance | 0.364 | +| learning_rate | 4.91e-05 | +| loss | -0.03 | +| n_updates | 22940 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000173 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1405 | +| iterations | 1782 | +| time_elapsed | 2597 | +| total_timesteps | 3649536 | +| train/ | | +| approx_kl | 0.010222544 | +| clip_fraction | 0.301 | +| clip_range | 0.0741 | +| entropy_loss | -7.1 | +| explained_variance | 0.45 | +| learning_rate | 4.91e-05 | +| loss | -0.03 | +| n_updates | 22944 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000205 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1405 | +| iterations | 1783 | +| time_elapsed | 2598 | +| total_timesteps | 3651584 | +| train/ | | +| approx_kl | 0.010350722 | +| clip_fraction | 0.322 | +| clip_range | 0.0741 | +| entropy_loss | -7.39 | +| explained_variance | -0.0854 | +| learning_rate | 4.91e-05 | +| loss | -0.0322 | +| n_updates | 22948 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000189 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1405 | +| iterations | 1784 | +| time_elapsed | 2600 | +| total_timesteps | 3653632 | +| train/ | | +| approx_kl | 0.010362551 | +| clip_fraction | 0.316 | +| clip_range | 0.0741 | +| entropy_loss | -7.23 | +| explained_variance | 0.519 | +| learning_rate | 4.91e-05 | +| loss | -0.0294 | +| n_updates | 22952 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.00011 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1405 | +| iterations | 1785 | +| time_elapsed | 2601 | +| total_timesteps | 3655680 | +| train/ | | +| approx_kl | 0.010967624 | +| clip_fraction | 0.293 | +| clip_range | 0.0741 | +| entropy_loss | -7.34 | +| explained_variance | -0.0164 | +| learning_rate | 4.91e-05 | +| loss | -0.0331 | +| n_updates | 22956 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000259 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1405 | +| iterations | 1786 | +| time_elapsed | 2603 | +| total_timesteps | 3657728 | +| train/ | | +| approx_kl | 0.009977633 | +| clip_fraction | 0.325 | +| clip_range | 0.0741 | +| entropy_loss | -7.19 | +| explained_variance | 0.527 | +| learning_rate | 4.91e-05 | +| loss | -0.0379 | +| n_updates | 22960 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000107 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1405 | +| iterations | 1787 | +| time_elapsed | 2604 | +| total_timesteps | 3659776 | +| train/ | | +| approx_kl | 0.011038391 | +| clip_fraction | 0.306 | +| clip_range | 0.0741 | +| entropy_loss | -7.36 | +| explained_variance | -0.136 | +| learning_rate | 4.91e-05 | +| loss | -0.0322 | +| n_updates | 22964 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000167 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1405 | +| iterations | 1788 | +| time_elapsed | 2606 | +| total_timesteps | 3661824 | +| train/ | | +| approx_kl | 0.011596413 | +| clip_fraction | 0.28 | +| clip_range | 0.0741 | +| entropy_loss | -7.13 | +| explained_variance | 0.31 | +| learning_rate | 4.91e-05 | +| loss | -0.0296 | +| n_updates | 22968 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.0003 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1405 | +| iterations | 1789 | +| time_elapsed | 2607 | +| total_timesteps | 3663872 | +| train/ | | +| approx_kl | 0.012613014 | +| clip_fraction | 0.316 | +| clip_range | 0.0741 | +| entropy_loss | -7.08 | +| explained_variance | 0.3 | +| learning_rate | 4.91e-05 | +| loss | -0.0337 | +| n_updates | 22972 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000187 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1405 | +| iterations | 1790 | +| time_elapsed | 2608 | +| total_timesteps | 3665920 | +| train/ | | +| approx_kl | 0.011388887 | +| clip_fraction | 0.342 | +| clip_range | 0.0741 | +| entropy_loss | -7.21 | +| explained_variance | 0.302 | +| learning_rate | 4.91e-05 | +| loss | -0.0396 | +| n_updates | 22976 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000182 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1405 | +| iterations | 1791 | +| time_elapsed | 2610 | +| total_timesteps | 3667968 | +| train/ | | +| approx_kl | 0.010537093 | +| clip_fraction | 0.298 | +| clip_range | 0.0741 | +| entropy_loss | -7.18 | +| explained_variance | 0.223 | +| learning_rate | 4.91e-05 | +| loss | -0.0311 | +| n_updates | 22980 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.00018 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1405 | +| iterations | 1792 | +| time_elapsed | 2611 | +| total_timesteps | 3670016 | +| train/ | | +| approx_kl | 0.011467851 | +| clip_fraction | 0.33 | +| clip_range | 0.0741 | +| entropy_loss | -7.26 | +| explained_variance | 0.503 | +| learning_rate | 4.91e-05 | +| loss | -0.0315 | +| n_updates | 22984 | +| policy_gradient_loss | -0.0226 | +| value_loss | 7.71e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1405 | +| iterations | 1793 | +| time_elapsed | 2613 | +| total_timesteps | 3672064 | +| train/ | | +| approx_kl | 0.01039754 | +| clip_fraction | 0.278 | +| clip_range | 0.0741 | +| entropy_loss | -6.67 | +| explained_variance | 0.401 | +| learning_rate | 4.91e-05 | +| loss | -0.0265 | +| n_updates | 22988 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000314 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1405 | +| iterations | 1794 | +| time_elapsed | 2614 | +| total_timesteps | 3674112 | +| train/ | | +| approx_kl | 0.0094129965 | +| clip_fraction | 0.298 | +| clip_range | 0.0741 | +| entropy_loss | -7.08 | +| explained_variance | 0.417 | +| learning_rate | 4.91e-05 | +| loss | -0.0322 | +| n_updates | 22992 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000122 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1405 | +| iterations | 1795 | +| time_elapsed | 2616 | +| total_timesteps | 3676160 | +| train/ | | +| approx_kl | 0.009846747 | +| clip_fraction | 0.314 | +| clip_range | 0.0741 | +| entropy_loss | -7.39 | +| explained_variance | -0.0461 | +| learning_rate | 4.91e-05 | +| loss | -0.0315 | +| n_updates | 22996 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000133 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1405 | +| iterations | 1796 | +| time_elapsed | 2617 | +| total_timesteps | 3678208 | +| train/ | | +| approx_kl | 0.010844948 | +| clip_fraction | 0.312 | +| clip_range | 0.0741 | +| entropy_loss | -7.29 | +| explained_variance | 0.218 | +| learning_rate | 4.91e-05 | +| loss | -0.0314 | +| n_updates | 23000 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000211 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1405 | +| iterations | 1797 | +| time_elapsed | 2619 | +| total_timesteps | 3680256 | +| train/ | | +| approx_kl | 0.010643404 | +| clip_fraction | 0.299 | +| clip_range | 0.0741 | +| entropy_loss | -7.32 | +| explained_variance | -0.0904 | +| learning_rate | 4.91e-05 | +| loss | -0.036 | +| n_updates | 23004 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000174 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1405 | +| iterations | 1798 | +| time_elapsed | 2620 | +| total_timesteps | 3682304 | +| train/ | | +| approx_kl | 0.01125808 | +| clip_fraction | 0.332 | +| clip_range | 0.0741 | +| entropy_loss | -7.3 | +| explained_variance | 0.207 | +| learning_rate | 4.91e-05 | +| loss | -0.0348 | +| n_updates | 23008 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000116 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1405 | +| iterations | 1799 | +| time_elapsed | 2622 | +| total_timesteps | 3684352 | +| train/ | | +| approx_kl | 0.011222834 | +| clip_fraction | 0.323 | +| clip_range | 0.0741 | +| entropy_loss | -7.22 | +| explained_variance | 0.42 | +| learning_rate | 4.91e-05 | +| loss | -0.0352 | +| n_updates | 23012 | +| policy_gradient_loss | -0.0213 | +| value_loss | 8.75e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1405 | +| iterations | 1800 | +| time_elapsed | 2623 | +| total_timesteps | 3686400 | +| train/ | | +| approx_kl | 0.010285749 | +| clip_fraction | 0.279 | +| clip_range | 0.0741 | +| entropy_loss | -7.24 | +| explained_variance | -0.0678 | +| learning_rate | 4.91e-05 | +| loss | -0.0317 | +| n_updates | 23016 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.00023 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1405 | +| iterations | 1801 | +| time_elapsed | 2624 | +| total_timesteps | 3688448 | +| train/ | | +| approx_kl | 0.010579174 | +| clip_fraction | 0.314 | +| clip_range | 0.0741 | +| entropy_loss | -6.8 | +| explained_variance | 0.389 | +| learning_rate | 4.91e-05 | +| loss | -0.0285 | +| n_updates | 23020 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000214 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1405 | +| iterations | 1802 | +| time_elapsed | 2626 | +| total_timesteps | 3690496 | +| train/ | | +| approx_kl | 0.0106091965 | +| clip_fraction | 0.322 | +| clip_range | 0.0741 | +| entropy_loss | -6.8 | +| explained_variance | 0.385 | +| learning_rate | 4.91e-05 | +| loss | -0.0264 | +| n_updates | 23024 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000219 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1405 | +| iterations | 1803 | +| time_elapsed | 2627 | +| total_timesteps | 3692544 | +| train/ | | +| approx_kl | 0.011504189 | +| clip_fraction | 0.303 | +| clip_range | 0.0741 | +| entropy_loss | -7.07 | +| explained_variance | 0.218 | +| learning_rate | 4.91e-05 | +| loss | -0.032 | +| n_updates | 23028 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000218 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1405 | +| iterations | 1804 | +| time_elapsed | 2629 | +| total_timesteps | 3694592 | +| train/ | | +| approx_kl | 0.011879644 | +| clip_fraction | 0.316 | +| clip_range | 0.0741 | +| entropy_loss | -7.27 | +| explained_variance | 0.059 | +| learning_rate | 4.91e-05 | +| loss | -0.0307 | +| n_updates | 23032 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000337 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1405 | +| iterations | 1805 | +| time_elapsed | 2630 | +| total_timesteps | 3696640 | +| train/ | | +| approx_kl | 0.011332209 | +| clip_fraction | 0.333 | +| clip_range | 0.0741 | +| entropy_loss | -7.19 | +| explained_variance | -0.568 | +| learning_rate | 4.91e-05 | +| loss | -0.0409 | +| n_updates | 23036 | +| policy_gradient_loss | -0.0247 | +| value_loss | 0.00011 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1405 | +| iterations | 1806 | +| time_elapsed | 2632 | +| total_timesteps | 3698688 | +| train/ | | +| approx_kl | 0.011238152 | +| clip_fraction | 0.34 | +| clip_range | 0.0741 | +| entropy_loss | -6.92 | +| explained_variance | 0.367 | +| learning_rate | 4.91e-05 | +| loss | -0.0379 | +| n_updates | 23040 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000327 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1405 | +| iterations | 1807 | +| time_elapsed | 2633 | +| total_timesteps | 3700736 | +| train/ | | +| approx_kl | 0.012482917 | +| clip_fraction | 0.344 | +| clip_range | 0.0741 | +| entropy_loss | -7.22 | +| explained_variance | 0.189 | +| learning_rate | 4.91e-05 | +| loss | -0.0362 | +| n_updates | 23044 | +| policy_gradient_loss | -0.0227 | +| value_loss | 0.000213 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1405 | +| iterations | 1808 | +| time_elapsed | 2635 | +| total_timesteps | 3702784 | +| train/ | | +| approx_kl | 0.011871475 | +| clip_fraction | 0.323 | +| clip_range | 0.0741 | +| entropy_loss | -7.13 | +| explained_variance | 0.0898 | +| learning_rate | 4.91e-05 | +| loss | -0.0295 | +| n_updates | 23048 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000228 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1405 | +| iterations | 1809 | +| time_elapsed | 2636 | +| total_timesteps | 3704832 | +| train/ | | +| approx_kl | 0.013029732 | +| clip_fraction | 0.354 | +| clip_range | 0.0741 | +| entropy_loss | -7.31 | +| explained_variance | -0.234 | +| learning_rate | 4.91e-05 | +| loss | -0.0332 | +| n_updates | 23052 | +| policy_gradient_loss | -0.0232 | +| value_loss | 9.82e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1405 | +| iterations | 1810 | +| time_elapsed | 2637 | +| total_timesteps | 3706880 | +| train/ | | +| approx_kl | 0.0122815855 | +| clip_fraction | 0.315 | +| clip_range | 0.0741 | +| entropy_loss | -7.25 | +| explained_variance | -0.0558 | +| learning_rate | 4.91e-05 | +| loss | -0.0276 | +| n_updates | 23056 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000309 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1405 | +| iterations | 1811 | +| time_elapsed | 2639 | +| total_timesteps | 3708928 | +| train/ | | +| approx_kl | 0.010113438 | +| clip_fraction | 0.309 | +| clip_range | 0.0741 | +| entropy_loss | -6.79 | +| explained_variance | 0.395 | +| learning_rate | 4.91e-05 | +| loss | -0.0329 | +| n_updates | 23060 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000281 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1405 | +| iterations | 1812 | +| time_elapsed | 2640 | +| total_timesteps | 3710976 | +| train/ | | +| approx_kl | 0.012580875 | +| clip_fraction | 0.339 | +| clip_range | 0.0741 | +| entropy_loss | -6.89 | +| explained_variance | 0.362 | +| learning_rate | 4.91e-05 | +| loss | -0.0382 | +| n_updates | 23064 | +| policy_gradient_loss | -0.0229 | +| value_loss | 8.17e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1405 | +| iterations | 1813 | +| time_elapsed | 2642 | +| total_timesteps | 3713024 | +| train/ | | +| approx_kl | 0.009490162 | +| clip_fraction | 0.305 | +| clip_range | 0.0741 | +| entropy_loss | -6.82 | +| explained_variance | 0.616 | +| learning_rate | 4.91e-05 | +| loss | -0.0254 | +| n_updates | 23068 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000154 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1405 | +| iterations | 1814 | +| time_elapsed | 2643 | +| total_timesteps | 3715072 | +| train/ | | +| approx_kl | 0.010112619 | +| clip_fraction | 0.285 | +| clip_range | 0.0741 | +| entropy_loss | -7.25 | +| explained_variance | 0.136 | +| learning_rate | 4.91e-05 | +| loss | -0.033 | +| n_updates | 23072 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000279 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1405 | +| iterations | 1815 | +| time_elapsed | 2644 | +| total_timesteps | 3717120 | +| train/ | | +| approx_kl | 0.012962316 | +| clip_fraction | 0.325 | +| clip_range | 0.0741 | +| entropy_loss | -7.42 | +| explained_variance | -0.166 | +| learning_rate | 4.91e-05 | +| loss | -0.0342 | +| n_updates | 23076 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000129 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1405 | +| iterations | 1816 | +| time_elapsed | 2646 | +| total_timesteps | 3719168 | +| train/ | | +| approx_kl | 0.011395723 | +| clip_fraction | 0.293 | +| clip_range | 0.0741 | +| entropy_loss | -7.2 | +| explained_variance | 0.102 | +| learning_rate | 4.91e-05 | +| loss | -0.0254 | +| n_updates | 23080 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000476 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1405 | +| iterations | 1817 | +| time_elapsed | 2647 | +| total_timesteps | 3721216 | +| train/ | | +| approx_kl | 0.010061729 | +| clip_fraction | 0.339 | +| clip_range | 0.0741 | +| entropy_loss | -7.26 | +| explained_variance | 0.273 | +| learning_rate | 4.91e-05 | +| loss | -0.0315 | +| n_updates | 23084 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000173 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1405 | +| iterations | 1818 | +| time_elapsed | 2649 | +| total_timesteps | 3723264 | +| train/ | | +| approx_kl | 0.010385227 | +| clip_fraction | 0.324 | +| clip_range | 0.0741 | +| entropy_loss | -7.09 | +| explained_variance | 0.281 | +| learning_rate | 4.91e-05 | +| loss | -0.0312 | +| n_updates | 23088 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.00023 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1405 | +| iterations | 1819 | +| time_elapsed | 2650 | +| total_timesteps | 3725312 | +| train/ | | +| approx_kl | 0.011628335 | +| clip_fraction | 0.318 | +| clip_range | 0.0741 | +| entropy_loss | -7.1 | +| explained_variance | 0.4 | +| learning_rate | 4.91e-05 | +| loss | -0.0399 | +| n_updates | 23092 | +| policy_gradient_loss | -0.0225 | +| value_loss | 0.000126 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1405 | +| iterations | 1820 | +| time_elapsed | 2652 | +| total_timesteps | 3727360 | +| train/ | | +| approx_kl | 0.010902515 | +| clip_fraction | 0.286 | +| clip_range | 0.0741 | +| entropy_loss | -6.5 | +| explained_variance | 0.408 | +| learning_rate | 4.91e-05 | +| loss | -0.0243 | +| n_updates | 23096 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000328 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1405 | +| iterations | 1821 | +| time_elapsed | 2653 | +| total_timesteps | 3729408 | +| train/ | | +| approx_kl | 0.012202112 | +| clip_fraction | 0.338 | +| clip_range | 0.0741 | +| entropy_loss | -7.08 | +| explained_variance | 0.0245 | +| learning_rate | 4.91e-05 | +| loss | -0.0345 | +| n_updates | 23100 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000184 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1405 | +| iterations | 1822 | +| time_elapsed | 2654 | +| total_timesteps | 3731456 | +| train/ | | +| approx_kl | 0.012904917 | +| clip_fraction | 0.336 | +| clip_range | 0.0741 | +| entropy_loss | -7.21 | +| explained_variance | 0.284 | +| learning_rate | 4.91e-05 | +| loss | -0.035 | +| n_updates | 23104 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000123 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1405 | +| iterations | 1823 | +| time_elapsed | 2656 | +| total_timesteps | 3733504 | +| train/ | | +| approx_kl | 0.012663512 | +| clip_fraction | 0.356 | +| clip_range | 0.0741 | +| entropy_loss | -7.16 | +| explained_variance | -0.132 | +| learning_rate | 4.91e-05 | +| loss | -0.037 | +| n_updates | 23108 | +| policy_gradient_loss | -0.0227 | +| value_loss | 0.000182 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1405 | +| iterations | 1824 | +| time_elapsed | 2657 | +| total_timesteps | 3735552 | +| train/ | | +| approx_kl | 0.012908433 | +| clip_fraction | 0.324 | +| clip_range | 0.0741 | +| entropy_loss | -7.31 | +| explained_variance | -0.189 | +| learning_rate | 4.91e-05 | +| loss | -0.0402 | +| n_updates | 23112 | +| policy_gradient_loss | -0.0225 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1405 | +| iterations | 1825 | +| time_elapsed | 2659 | +| total_timesteps | 3737600 | +| train/ | | +| approx_kl | 0.012532808 | +| clip_fraction | 0.342 | +| clip_range | 0.0741 | +| entropy_loss | -7.16 | +| explained_variance | 0.0762 | +| learning_rate | 4.91e-05 | +| loss | -0.0347 | +| n_updates | 23116 | +| policy_gradient_loss | -0.022 | +| value_loss | 0.000194 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1405 | +| iterations | 1826 | +| time_elapsed | 2660 | +| total_timesteps | 3739648 | +| train/ | | +| approx_kl | 0.012440036 | +| clip_fraction | 0.34 | +| clip_range | 0.0741 | +| entropy_loss | -7.32 | +| explained_variance | 0.28 | +| learning_rate | 4.91e-05 | +| loss | -0.0389 | +| n_updates | 23120 | +| policy_gradient_loss | -0.0221 | +| value_loss | 9.14e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1405 | +| iterations | 1827 | +| time_elapsed | 2662 | +| total_timesteps | 3741696 | +| train/ | | +| approx_kl | 0.009697893 | +| clip_fraction | 0.297 | +| clip_range | 0.0741 | +| entropy_loss | -7.31 | +| explained_variance | -0.113 | +| learning_rate | 4.91e-05 | +| loss | -0.0332 | +| n_updates | 23124 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000159 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1405 | +| iterations | 1828 | +| time_elapsed | 2663 | +| total_timesteps | 3743744 | +| train/ | | +| approx_kl | 0.010697088 | +| clip_fraction | 0.304 | +| clip_range | 0.0741 | +| entropy_loss | -7.08 | +| explained_variance | 0.473 | +| learning_rate | 4.91e-05 | +| loss | -0.0359 | +| n_updates | 23128 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000142 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1405 | +| iterations | 1829 | +| time_elapsed | 2664 | +| total_timesteps | 3745792 | +| train/ | | +| approx_kl | 0.012598904 | +| clip_fraction | 0.313 | +| clip_range | 0.0741 | +| entropy_loss | -6.95 | +| explained_variance | 0.445 | +| learning_rate | 4.91e-05 | +| loss | -0.037 | +| n_updates | 23132 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000149 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1405 | +| iterations | 1830 | +| time_elapsed | 2666 | +| total_timesteps | 3747840 | +| train/ | | +| approx_kl | 0.010925934 | +| clip_fraction | 0.323 | +| clip_range | 0.0741 | +| entropy_loss | -7.16 | +| explained_variance | 0.262 | +| learning_rate | 4.91e-05 | +| loss | -0.0345 | +| n_updates | 23136 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000119 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1405 | +| iterations | 1831 | +| time_elapsed | 2667 | +| total_timesteps | 3749888 | +| train/ | | +| approx_kl | 0.012268415 | +| clip_fraction | 0.335 | +| clip_range | 0.0741 | +| entropy_loss | -6.81 | +| explained_variance | 0.701 | +| learning_rate | 4.91e-05 | +| loss | -0.0416 | +| n_updates | 23140 | +| policy_gradient_loss | -0.0209 | +| value_loss | 8.71e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1405 | +| iterations | 1832 | +| time_elapsed | 2669 | +| total_timesteps | 3751936 | +| train/ | | +| approx_kl | 0.013361273 | +| clip_fraction | 0.333 | +| clip_range | 0.0741 | +| entropy_loss | -7.12 | +| explained_variance | 0.337 | +| learning_rate | 4.91e-05 | +| loss | -0.0319 | +| n_updates | 23144 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000135 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1405 | +| iterations | 1833 | +| time_elapsed | 2670 | +| total_timesteps | 3753984 | +| train/ | | +| approx_kl | 0.01068633 | +| clip_fraction | 0.319 | +| clip_range | 0.0741 | +| entropy_loss | -7.09 | +| explained_variance | 0.406 | +| learning_rate | 4.91e-05 | +| loss | -0.027 | +| n_updates | 23148 | +| policy_gradient_loss | -0.0198 | +| value_loss | 9.72e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1405 | +| iterations | 1834 | +| time_elapsed | 2672 | +| total_timesteps | 3756032 | +| train/ | | +| approx_kl | 0.012123844 | +| clip_fraction | 0.317 | +| clip_range | 0.0741 | +| entropy_loss | -6.96 | +| explained_variance | 0.491 | +| learning_rate | 4.91e-05 | +| loss | -0.0299 | +| n_updates | 23152 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000175 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1405 | +| iterations | 1835 | +| time_elapsed | 2673 | +| total_timesteps | 3758080 | +| train/ | | +| approx_kl | 0.012941071 | +| clip_fraction | 0.341 | +| clip_range | 0.0741 | +| entropy_loss | -7.28 | +| explained_variance | 0.208 | +| learning_rate | 4.91e-05 | +| loss | -0.0434 | +| n_updates | 23156 | +| policy_gradient_loss | -0.0245 | +| value_loss | 8.41e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1405 | +| iterations | 1836 | +| time_elapsed | 2675 | +| total_timesteps | 3760128 | +| train/ | | +| approx_kl | 0.008960932 | +| clip_fraction | 0.297 | +| clip_range | 0.0741 | +| entropy_loss | -7.17 | +| explained_variance | 0.204 | +| learning_rate | 4.91e-05 | +| loss | -0.0301 | +| n_updates | 23160 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000249 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1405 | +| iterations | 1837 | +| time_elapsed | 2676 | +| total_timesteps | 3762176 | +| train/ | | +| approx_kl | 0.011214186 | +| clip_fraction | 0.338 | +| clip_range | 0.0741 | +| entropy_loss | -7.01 | +| explained_variance | 0.0885 | +| learning_rate | 4.91e-05 | +| loss | -0.0349 | +| n_updates | 23164 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000175 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1405 | +| iterations | 1838 | +| time_elapsed | 2677 | +| total_timesteps | 3764224 | +| train/ | | +| approx_kl | 0.012683432 | +| clip_fraction | 0.344 | +| clip_range | 0.0741 | +| entropy_loss | -6.96 | +| explained_variance | 0.598 | +| learning_rate | 4.91e-05 | +| loss | -0.0349 | +| n_updates | 23168 | +| policy_gradient_loss | -0.0198 | +| value_loss | 9.73e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1405 | +| iterations | 1839 | +| time_elapsed | 2679 | +| total_timesteps | 3766272 | +| train/ | | +| approx_kl | 0.010950249 | +| clip_fraction | 0.308 | +| clip_range | 0.0741 | +| entropy_loss | -7.13 | +| explained_variance | 0.318 | +| learning_rate | 4.91e-05 | +| loss | -0.0357 | +| n_updates | 23172 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000139 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1405 | +| iterations | 1840 | +| time_elapsed | 2680 | +| total_timesteps | 3768320 | +| train/ | | +| approx_kl | 0.010932313 | +| clip_fraction | 0.31 | +| clip_range | 0.0741 | +| entropy_loss | -7.18 | +| explained_variance | -0.205 | +| learning_rate | 4.91e-05 | +| loss | -0.0352 | +| n_updates | 23176 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000186 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1405 | +| iterations | 1841 | +| time_elapsed | 2682 | +| total_timesteps | 3770368 | +| train/ | | +| approx_kl | 0.010692636 | +| clip_fraction | 0.32 | +| clip_range | 0.0741 | +| entropy_loss | -6.84 | +| explained_variance | 0.434 | +| learning_rate | 4.91e-05 | +| loss | -0.026 | +| n_updates | 23180 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000142 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1405 | +| iterations | 1842 | +| time_elapsed | 2683 | +| total_timesteps | 3772416 | +| train/ | | +| approx_kl | 0.013443348 | +| clip_fraction | 0.316 | +| clip_range | 0.0741 | +| entropy_loss | -7.07 | +| explained_variance | 0.0189 | +| learning_rate | 4.91e-05 | +| loss | -0.0323 | +| n_updates | 23184 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000148 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1405 | +| iterations | 1843 | +| time_elapsed | 2684 | +| total_timesteps | 3774464 | +| train/ | | +| approx_kl | 0.012927473 | +| clip_fraction | 0.336 | +| clip_range | 0.0741 | +| entropy_loss | -7.21 | +| explained_variance | 0.0711 | +| learning_rate | 4.91e-05 | +| loss | -0.0411 | +| n_updates | 23188 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000126 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1405 | +| iterations | 1844 | +| time_elapsed | 2686 | +| total_timesteps | 3776512 | +| train/ | | +| approx_kl | 0.010586131 | +| clip_fraction | 0.329 | +| clip_range | 0.0741 | +| entropy_loss | -7.37 | +| explained_variance | -0.11 | +| learning_rate | 4.91e-05 | +| loss | -0.0305 | +| n_updates | 23192 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000166 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1405 | +| iterations | 1845 | +| time_elapsed | 2687 | +| total_timesteps | 3778560 | +| train/ | | +| approx_kl | 0.008918525 | +| clip_fraction | 0.292 | +| clip_range | 0.0741 | +| entropy_loss | -7.2 | +| explained_variance | -0.0425 | +| learning_rate | 4.91e-05 | +| loss | -0.026 | +| n_updates | 23196 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000188 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1405 | +| iterations | 1846 | +| time_elapsed | 2689 | +| total_timesteps | 3780608 | +| train/ | | +| approx_kl | 0.010687895 | +| clip_fraction | 0.316 | +| clip_range | 0.0741 | +| entropy_loss | -6.86 | +| explained_variance | 0.31 | +| learning_rate | 4.91e-05 | +| loss | -0.0288 | +| n_updates | 23200 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000196 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1405 | +| iterations | 1847 | +| time_elapsed | 2690 | +| total_timesteps | 3782656 | +| train/ | | +| approx_kl | 0.0097060595 | +| clip_fraction | 0.317 | +| clip_range | 0.0741 | +| entropy_loss | -6.9 | +| explained_variance | 0.648 | +| learning_rate | 4.91e-05 | +| loss | -0.0275 | +| n_updates | 23204 | +| policy_gradient_loss | -0.0191 | +| value_loss | 9.05e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1405 | +| iterations | 1848 | +| time_elapsed | 2692 | +| total_timesteps | 3784704 | +| train/ | | +| approx_kl | 0.010458962 | +| clip_fraction | 0.292 | +| clip_range | 0.0741 | +| entropy_loss | -6.41 | +| explained_variance | 0.465 | +| learning_rate | 4.91e-05 | +| loss | -0.0191 | +| n_updates | 23208 | +| policy_gradient_loss | -0.0145 | +| value_loss | 0.000287 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1405 | +| iterations | 1849 | +| time_elapsed | 2693 | +| total_timesteps | 3786752 | +| train/ | | +| approx_kl | 0.0133366585 | +| clip_fraction | 0.362 | +| clip_range | 0.0741 | +| entropy_loss | -7.24 | +| explained_variance | 0.302 | +| learning_rate | 4.91e-05 | +| loss | -0.0475 | +| n_updates | 23212 | +| policy_gradient_loss | -0.0254 | +| value_loss | 6.28e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1405 | +| iterations | 1850 | +| time_elapsed | 2694 | +| total_timesteps | 3788800 | +| train/ | | +| approx_kl | 0.011979927 | +| clip_fraction | 0.327 | +| clip_range | 0.0741 | +| entropy_loss | -7.22 | +| explained_variance | -7.56e-05 | +| learning_rate | 4.91e-05 | +| loss | -0.0361 | +| n_updates | 23216 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.00017 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1405 | +| iterations | 1851 | +| time_elapsed | 2696 | +| total_timesteps | 3790848 | +| train/ | | +| approx_kl | 0.012622866 | +| clip_fraction | 0.321 | +| clip_range | 0.0741 | +| entropy_loss | -7.3 | +| explained_variance | 0.0141 | +| learning_rate | 4.91e-05 | +| loss | -0.0311 | +| n_updates | 23220 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000143 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1405 | +| iterations | 1852 | +| time_elapsed | 2697 | +| total_timesteps | 3792896 | +| train/ | | +| approx_kl | 0.013983996 | +| clip_fraction | 0.328 | +| clip_range | 0.0741 | +| entropy_loss | -7.35 | +| explained_variance | -0.082 | +| learning_rate | 4.91e-05 | +| loss | -0.0317 | +| n_updates | 23224 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000145 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1405 | +| iterations | 1853 | +| time_elapsed | 2699 | +| total_timesteps | 3794944 | +| train/ | | +| approx_kl | 0.010729346 | +| clip_fraction | 0.302 | +| clip_range | 0.0741 | +| entropy_loss | -7.03 | +| explained_variance | 0.409 | +| learning_rate | 4.91e-05 | +| loss | -0.0346 | +| n_updates | 23228 | +| policy_gradient_loss | -0.0206 | +| value_loss | 8.24e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1406 | +| iterations | 1854 | +| time_elapsed | 2700 | +| total_timesteps | 3796992 | +| train/ | | +| approx_kl | 0.010424327 | +| clip_fraction | 0.321 | +| clip_range | 0.0741 | +| entropy_loss | -6.95 | +| explained_variance | 0.299 | +| learning_rate | 4.91e-05 | +| loss | -0.025 | +| n_updates | 23232 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000214 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1406 | +| iterations | 1855 | +| time_elapsed | 2701 | +| total_timesteps | 3799040 | +| train/ | | +| approx_kl | 0.011191234 | +| clip_fraction | 0.334 | +| clip_range | 0.0741 | +| entropy_loss | -6.88 | +| explained_variance | 0.595 | +| learning_rate | 4.91e-05 | +| loss | -0.0369 | +| n_updates | 23236 | +| policy_gradient_loss | -0.021 | +| value_loss | 9.99e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1406 | +| iterations | 1856 | +| time_elapsed | 2703 | +| total_timesteps | 3801088 | +| train/ | | +| approx_kl | 0.012879241 | +| clip_fraction | 0.311 | +| clip_range | 0.0741 | +| entropy_loss | -6.97 | +| explained_variance | 0.312 | +| learning_rate | 4.91e-05 | +| loss | -0.0331 | +| n_updates | 23240 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000159 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1406 | +| iterations | 1857 | +| time_elapsed | 2704 | +| total_timesteps | 3803136 | +| train/ | | +| approx_kl | 0.010452131 | +| clip_fraction | 0.313 | +| clip_range | 0.074 | +| entropy_loss | -7 | +| explained_variance | 0.315 | +| learning_rate | 4.91e-05 | +| loss | -0.0272 | +| n_updates | 23244 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000278 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1406 | +| iterations | 1858 | +| time_elapsed | 2706 | +| total_timesteps | 3805184 | +| train/ | | +| approx_kl | 0.01335706 | +| clip_fraction | 0.347 | +| clip_range | 0.074 | +| entropy_loss | -7.36 | +| explained_variance | -0.25 | +| learning_rate | 4.91e-05 | +| loss | -0.0434 | +| n_updates | 23248 | +| policy_gradient_loss | -0.0226 | +| value_loss | 0.000146 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1406 | +| iterations | 1859 | +| time_elapsed | 2707 | +| total_timesteps | 3807232 | +| train/ | | +| approx_kl | 0.010263293 | +| clip_fraction | 0.338 | +| clip_range | 0.074 | +| entropy_loss | -7.39 | +| explained_variance | -0.136 | +| learning_rate | 4.91e-05 | +| loss | -0.0356 | +| n_updates | 23252 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000129 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1406 | +| iterations | 1860 | +| time_elapsed | 2709 | +| total_timesteps | 3809280 | +| train/ | | +| approx_kl | 0.0076140417 | +| clip_fraction | 0.276 | +| clip_range | 0.074 | +| entropy_loss | -7.04 | +| explained_variance | 0.156 | +| learning_rate | 4.91e-05 | +| loss | -0.0302 | +| n_updates | 23256 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000395 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1406 | +| iterations | 1861 | +| time_elapsed | 2710 | +| total_timesteps | 3811328 | +| train/ | | +| approx_kl | 0.010003064 | +| clip_fraction | 0.298 | +| clip_range | 0.074 | +| entropy_loss | -6.93 | +| explained_variance | 0.317 | +| learning_rate | 4.91e-05 | +| loss | -0.028 | +| n_updates | 23260 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000219 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1406 | +| iterations | 1862 | +| time_elapsed | 2711 | +| total_timesteps | 3813376 | +| train/ | | +| approx_kl | 0.01087685 | +| clip_fraction | 0.323 | +| clip_range | 0.074 | +| entropy_loss | -7.36 | +| explained_variance | -0.144 | +| learning_rate | 4.91e-05 | +| loss | -0.0339 | +| n_updates | 23264 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000119 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1406 | +| iterations | 1863 | +| time_elapsed | 2713 | +| total_timesteps | 3815424 | +| train/ | | +| approx_kl | 0.009177046 | +| clip_fraction | 0.276 | +| clip_range | 0.074 | +| entropy_loss | -7.07 | +| explained_variance | 0.148 | +| learning_rate | 4.91e-05 | +| loss | -0.0256 | +| n_updates | 23268 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.000418 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1406 | +| iterations | 1864 | +| time_elapsed | 2714 | +| total_timesteps | 3817472 | +| train/ | | +| approx_kl | 0.011394782 | +| clip_fraction | 0.344 | +| clip_range | 0.074 | +| entropy_loss | -7.06 | +| explained_variance | 0.514 | +| learning_rate | 4.91e-05 | +| loss | -0.0347 | +| n_updates | 23272 | +| policy_gradient_loss | -0.0239 | +| value_loss | 7.16e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1406 | +| iterations | 1865 | +| time_elapsed | 2716 | +| total_timesteps | 3819520 | +| train/ | | +| approx_kl | 0.009493962 | +| clip_fraction | 0.309 | +| clip_range | 0.074 | +| entropy_loss | -7.21 | +| explained_variance | 0.205 | +| learning_rate | 4.91e-05 | +| loss | -0.0283 | +| n_updates | 23276 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000228 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1406 | +| iterations | 1866 | +| time_elapsed | 2717 | +| total_timesteps | 3821568 | +| train/ | | +| approx_kl | 0.0108071575 | +| clip_fraction | 0.297 | +| clip_range | 0.074 | +| entropy_loss | -7.11 | +| explained_variance | 0.229 | +| learning_rate | 4.91e-05 | +| loss | -0.0317 | +| n_updates | 23280 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000188 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1406 | +| iterations | 1867 | +| time_elapsed | 2719 | +| total_timesteps | 3823616 | +| train/ | | +| approx_kl | 0.011554357 | +| clip_fraction | 0.326 | +| clip_range | 0.074 | +| entropy_loss | -7.18 | +| explained_variance | -0.0725 | +| learning_rate | 4.91e-05 | +| loss | -0.0387 | +| n_updates | 23284 | +| policy_gradient_loss | -0.0228 | +| value_loss | 9.46e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1406 | +| iterations | 1868 | +| time_elapsed | 2720 | +| total_timesteps | 3825664 | +| train/ | | +| approx_kl | 0.009252457 | +| clip_fraction | 0.287 | +| clip_range | 0.074 | +| entropy_loss | -6.89 | +| explained_variance | 0.464 | +| learning_rate | 4.91e-05 | +| loss | -0.0291 | +| n_updates | 23288 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000157 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1406 | +| iterations | 1869 | +| time_elapsed | 2721 | +| total_timesteps | 3827712 | +| train/ | | +| approx_kl | 0.011174783 | +| clip_fraction | 0.29 | +| clip_range | 0.074 | +| entropy_loss | -7.23 | +| explained_variance | 0.25 | +| learning_rate | 4.91e-05 | +| loss | -0.03 | +| n_updates | 23292 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000172 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1406 | +| iterations | 1870 | +| time_elapsed | 2723 | +| total_timesteps | 3829760 | +| train/ | | +| approx_kl | 0.011353802 | +| clip_fraction | 0.333 | +| clip_range | 0.074 | +| entropy_loss | -7.3 | +| explained_variance | 0.472 | +| learning_rate | 4.91e-05 | +| loss | -0.0394 | +| n_updates | 23296 | +| policy_gradient_loss | -0.023 | +| value_loss | 7.41e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1406 | +| iterations | 1871 | +| time_elapsed | 2724 | +| total_timesteps | 3831808 | +| train/ | | +| approx_kl | 0.010880565 | +| clip_fraction | 0.315 | +| clip_range | 0.074 | +| entropy_loss | -7.36 | +| explained_variance | -0.146 | +| learning_rate | 4.91e-05 | +| loss | -0.033 | +| n_updates | 23300 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000104 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1406 | +| iterations | 1872 | +| time_elapsed | 2726 | +| total_timesteps | 3833856 | +| train/ | | +| approx_kl | 0.013412517 | +| clip_fraction | 0.313 | +| clip_range | 0.074 | +| entropy_loss | -7.38 | +| explained_variance | -0.101 | +| learning_rate | 4.91e-05 | +| loss | -0.0364 | +| n_updates | 23304 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000102 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1406 | +| iterations | 1873 | +| time_elapsed | 2727 | +| total_timesteps | 3835904 | +| train/ | | +| approx_kl | 0.010315195 | +| clip_fraction | 0.282 | +| clip_range | 0.074 | +| entropy_loss | -6.79 | +| explained_variance | 0.66 | +| learning_rate | 4.91e-05 | +| loss | -0.032 | +| n_updates | 23308 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000103 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1406 | +| iterations | 1874 | +| time_elapsed | 2729 | +| total_timesteps | 3837952 | +| train/ | | +| approx_kl | 0.009309049 | +| clip_fraction | 0.302 | +| clip_range | 0.074 | +| entropy_loss | -7.03 | +| explained_variance | 0.324 | +| learning_rate | 4.91e-05 | +| loss | -0.0284 | +| n_updates | 23312 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000154 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1406 | +| iterations | 1875 | +| time_elapsed | 2730 | +| total_timesteps | 3840000 | +| train/ | | +| approx_kl | 0.010636101 | +| clip_fraction | 0.312 | +| clip_range | 0.074 | +| entropy_loss | -6.96 | +| explained_variance | 0.425 | +| learning_rate | 4.91e-05 | +| loss | -0.0269 | +| n_updates | 23316 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000173 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1406 | +| iterations | 1876 | +| time_elapsed | 2731 | +| total_timesteps | 3842048 | +| train/ | | +| approx_kl | 0.011430538 | +| clip_fraction | 0.321 | +| clip_range | 0.074 | +| entropy_loss | -7.27 | +| explained_variance | 0.382 | +| learning_rate | 4.91e-05 | +| loss | -0.0299 | +| n_updates | 23320 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000132 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1406 | +| iterations | 1877 | +| time_elapsed | 2733 | +| total_timesteps | 3844096 | +| train/ | | +| approx_kl | 0.012030394 | +| clip_fraction | 0.307 | +| clip_range | 0.074 | +| entropy_loss | -6.82 | +| explained_variance | 0.365 | +| learning_rate | 4.91e-05 | +| loss | -0.0289 | +| n_updates | 23324 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.00023 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1406 | +| iterations | 1878 | +| time_elapsed | 2734 | +| total_timesteps | 3846144 | +| train/ | | +| approx_kl | 0.01160587 | +| clip_fraction | 0.339 | +| clip_range | 0.074 | +| entropy_loss | -7.11 | +| explained_variance | 0.219 | +| learning_rate | 4.91e-05 | +| loss | -0.0263 | +| n_updates | 23328 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000174 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1406 | +| iterations | 1879 | +| time_elapsed | 2736 | +| total_timesteps | 3848192 | +| train/ | | +| approx_kl | 0.012245069 | +| clip_fraction | 0.337 | +| clip_range | 0.074 | +| entropy_loss | -7.2 | +| explained_variance | 0.303 | +| learning_rate | 4.91e-05 | +| loss | -0.0364 | +| n_updates | 23332 | +| policy_gradient_loss | -0.0238 | +| value_loss | 0.000121 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1406 | +| iterations | 1880 | +| time_elapsed | 2737 | +| total_timesteps | 3850240 | +| train/ | | +| approx_kl | 0.011398987 | +| clip_fraction | 0.325 | +| clip_range | 0.074 | +| entropy_loss | -7.38 | +| explained_variance | -0.104 | +| learning_rate | 4.91e-05 | +| loss | -0.0365 | +| n_updates | 23336 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000159 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1406 | +| iterations | 1881 | +| time_elapsed | 2739 | +| total_timesteps | 3852288 | +| train/ | | +| approx_kl | 0.0105736125 | +| clip_fraction | 0.287 | +| clip_range | 0.074 | +| entropy_loss | -7.21 | +| explained_variance | 0.24 | +| learning_rate | 4.91e-05 | +| loss | -0.0336 | +| n_updates | 23340 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.00017 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1406 | +| iterations | 1882 | +| time_elapsed | 2740 | +| total_timesteps | 3854336 | +| train/ | | +| approx_kl | 0.009245557 | +| clip_fraction | 0.283 | +| clip_range | 0.074 | +| entropy_loss | -7.31 | +| explained_variance | 0.319 | +| learning_rate | 4.91e-05 | +| loss | -0.0322 | +| n_updates | 23344 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000131 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1406 | +| iterations | 1883 | +| time_elapsed | 2741 | +| total_timesteps | 3856384 | +| train/ | | +| approx_kl | 0.011121105 | +| clip_fraction | 0.326 | +| clip_range | 0.074 | +| entropy_loss | -7.34 | +| explained_variance | -0.0931 | +| learning_rate | 4.91e-05 | +| loss | -0.0345 | +| n_updates | 23348 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000103 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1406 | +| iterations | 1884 | +| time_elapsed | 2743 | +| total_timesteps | 3858432 | +| train/ | | +| approx_kl | 0.011212919 | +| clip_fraction | 0.278 | +| clip_range | 0.074 | +| entropy_loss | -6.83 | +| explained_variance | 0.551 | +| learning_rate | 4.91e-05 | +| loss | -0.0245 | +| n_updates | 23352 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000159 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1406 | +| iterations | 1885 | +| time_elapsed | 2744 | +| total_timesteps | 3860480 | +| train/ | | +| approx_kl | 0.009716518 | +| clip_fraction | 0.302 | +| clip_range | 0.074 | +| entropy_loss | -6.67 | +| explained_variance | 0.447 | +| learning_rate | 4.91e-05 | +| loss | -0.0248 | +| n_updates | 23356 | +| policy_gradient_loss | -0.014 | +| value_loss | 0.000289 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1406 | +| iterations | 1886 | +| time_elapsed | 2746 | +| total_timesteps | 3862528 | +| train/ | | +| approx_kl | 0.010939049 | +| clip_fraction | 0.321 | +| clip_range | 0.074 | +| entropy_loss | -7.31 | +| explained_variance | 0.228 | +| learning_rate | 4.91e-05 | +| loss | -0.0352 | +| n_updates | 23360 | +| policy_gradient_loss | -0.0219 | +| value_loss | 0.000145 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1406 | +| iterations | 1887 | +| time_elapsed | 2747 | +| total_timesteps | 3864576 | +| train/ | | +| approx_kl | 0.011464564 | +| clip_fraction | 0.32 | +| clip_range | 0.074 | +| entropy_loss | -7.35 | +| explained_variance | 0.231 | +| learning_rate | 4.91e-05 | +| loss | -0.0318 | +| n_updates | 23364 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000217 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1406 | +| iterations | 1888 | +| time_elapsed | 2749 | +| total_timesteps | 3866624 | +| train/ | | +| approx_kl | 0.010737108 | +| clip_fraction | 0.297 | +| clip_range | 0.074 | +| entropy_loss | -6.98 | +| explained_variance | 0.324 | +| learning_rate | 4.91e-05 | +| loss | -0.0327 | +| n_updates | 23368 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000262 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1406 | +| iterations | 1889 | +| time_elapsed | 2750 | +| total_timesteps | 3868672 | +| train/ | | +| approx_kl | 0.011538091 | +| clip_fraction | 0.32 | +| clip_range | 0.074 | +| entropy_loss | -7.37 | +| explained_variance | -0.0847 | +| learning_rate | 4.91e-05 | +| loss | -0.0241 | +| n_updates | 23372 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000253 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1406 | +| iterations | 1890 | +| time_elapsed | 2752 | +| total_timesteps | 3870720 | +| train/ | | +| approx_kl | 0.010487303 | +| clip_fraction | 0.333 | +| clip_range | 0.074 | +| entropy_loss | -6.95 | +| explained_variance | 0.463 | +| learning_rate | 4.91e-05 | +| loss | -0.0296 | +| n_updates | 23376 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1406 | +| iterations | 1891 | +| time_elapsed | 2753 | +| total_timesteps | 3872768 | +| train/ | | +| approx_kl | 0.009460366 | +| clip_fraction | 0.338 | +| clip_range | 0.074 | +| entropy_loss | -7.43 | +| explained_variance | -0.106 | +| learning_rate | 4.91e-05 | +| loss | -0.035 | +| n_updates | 23380 | +| policy_gradient_loss | -0.0227 | +| value_loss | 0.000123 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1406 | +| iterations | 1892 | +| time_elapsed | 2754 | +| total_timesteps | 3874816 | +| train/ | | +| approx_kl | 0.009464811 | +| clip_fraction | 0.297 | +| clip_range | 0.074 | +| entropy_loss | -6.97 | +| explained_variance | 0.352 | +| learning_rate | 4.91e-05 | +| loss | -0.0344 | +| n_updates | 23384 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000274 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1406 | +| iterations | 1893 | +| time_elapsed | 2756 | +| total_timesteps | 3876864 | +| train/ | | +| approx_kl | 0.009581013 | +| clip_fraction | 0.317 | +| clip_range | 0.074 | +| entropy_loss | -7.11 | +| explained_variance | 0.475 | +| learning_rate | 4.91e-05 | +| loss | -0.0383 | +| n_updates | 23388 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000146 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1406 | +| iterations | 1894 | +| time_elapsed | 2757 | +| total_timesteps | 3878912 | +| train/ | | +| approx_kl | 0.008957455 | +| clip_fraction | 0.281 | +| clip_range | 0.074 | +| entropy_loss | -7.3 | +| explained_variance | 0.132 | +| learning_rate | 4.91e-05 | +| loss | -0.0327 | +| n_updates | 23392 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000241 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1406 | +| iterations | 1895 | +| time_elapsed | 2759 | +| total_timesteps | 3880960 | +| train/ | | +| approx_kl | 0.010829644 | +| clip_fraction | 0.293 | +| clip_range | 0.074 | +| entropy_loss | -7.05 | +| explained_variance | 0.536 | +| learning_rate | 4.91e-05 | +| loss | -0.0351 | +| n_updates | 23396 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.00015 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1406 | +| iterations | 1896 | +| time_elapsed | 2760 | +| total_timesteps | 3883008 | +| train/ | | +| approx_kl | 0.009172766 | +| clip_fraction | 0.302 | +| clip_range | 0.074 | +| entropy_loss | -7.32 | +| explained_variance | 0.0124 | +| learning_rate | 4.91e-05 | +| loss | -0.0351 | +| n_updates | 23400 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000121 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1406 | +| iterations | 1897 | +| time_elapsed | 2762 | +| total_timesteps | 3885056 | +| train/ | | +| approx_kl | 0.009506716 | +| clip_fraction | 0.294 | +| clip_range | 0.074 | +| entropy_loss | -6.92 | +| explained_variance | 0.347 | +| learning_rate | 4.91e-05 | +| loss | -0.0277 | +| n_updates | 23404 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000312 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1406 | +| iterations | 1898 | +| time_elapsed | 2763 | +| total_timesteps | 3887104 | +| train/ | | +| approx_kl | 0.010772275 | +| clip_fraction | 0.297 | +| clip_range | 0.074 | +| entropy_loss | -7.17 | +| explained_variance | 0.183 | +| learning_rate | 4.91e-05 | +| loss | -0.0353 | +| n_updates | 23408 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000191 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1406 | +| iterations | 1899 | +| time_elapsed | 2765 | +| total_timesteps | 3889152 | +| train/ | | +| approx_kl | 0.011446625 | +| clip_fraction | 0.347 | +| clip_range | 0.074 | +| entropy_loss | -7.08 | +| explained_variance | 0.398 | +| learning_rate | 4.91e-05 | +| loss | -0.0329 | +| n_updates | 23412 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000207 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1406 | +| iterations | 1900 | +| time_elapsed | 2766 | +| total_timesteps | 3891200 | +| train/ | | +| approx_kl | 0.012079865 | +| clip_fraction | 0.358 | +| clip_range | 0.074 | +| entropy_loss | -7.25 | +| explained_variance | 0.203 | +| learning_rate | 4.91e-05 | +| loss | -0.038 | +| n_updates | 23416 | +| policy_gradient_loss | -0.0244 | +| value_loss | 7.62e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1406 | +| iterations | 1901 | +| time_elapsed | 2767 | +| total_timesteps | 3893248 | +| train/ | | +| approx_kl | 0.010115809 | +| clip_fraction | 0.308 | +| clip_range | 0.074 | +| entropy_loss | -7.12 | +| explained_variance | 0.322 | +| learning_rate | 4.91e-05 | +| loss | -0.0279 | +| n_updates | 23420 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000246 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1406 | +| iterations | 1902 | +| time_elapsed | 2769 | +| total_timesteps | 3895296 | +| train/ | | +| approx_kl | 0.01021071 | +| clip_fraction | 0.297 | +| clip_range | 0.074 | +| entropy_loss | -7.27 | +| explained_variance | 0.325 | +| learning_rate | 4.91e-05 | +| loss | -0.0351 | +| n_updates | 23424 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000119 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1406 | +| iterations | 1903 | +| time_elapsed | 2770 | +| total_timesteps | 3897344 | +| train/ | | +| approx_kl | 0.011415801 | +| clip_fraction | 0.321 | +| clip_range | 0.074 | +| entropy_loss | -6.97 | +| explained_variance | 0.57 | +| learning_rate | 4.91e-05 | +| loss | -0.0342 | +| n_updates | 23428 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000101 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1406 | +| iterations | 1904 | +| time_elapsed | 2772 | +| total_timesteps | 3899392 | +| train/ | | +| approx_kl | 0.013380842 | +| clip_fraction | 0.344 | +| clip_range | 0.074 | +| entropy_loss | -7 | +| explained_variance | 0.483 | +| learning_rate | 4.91e-05 | +| loss | -0.036 | +| n_updates | 23432 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000159 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1406 | +| iterations | 1905 | +| time_elapsed | 2773 | +| total_timesteps | 3901440 | +| train/ | | +| approx_kl | 0.00968194 | +| clip_fraction | 0.268 | +| clip_range | 0.074 | +| entropy_loss | -7.09 | +| explained_variance | 0.107 | +| learning_rate | 4.91e-05 | +| loss | -0.0299 | +| n_updates | 23436 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000309 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1406 | +| iterations | 1906 | +| time_elapsed | 2775 | +| total_timesteps | 3903488 | +| train/ | | +| approx_kl | 0.012212396 | +| clip_fraction | 0.353 | +| clip_range | 0.074 | +| entropy_loss | -7.44 | +| explained_variance | -0.349 | +| learning_rate | 4.91e-05 | +| loss | -0.042 | +| n_updates | 23440 | +| policy_gradient_loss | -0.0241 | +| value_loss | 9.72e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1406 | +| iterations | 1907 | +| time_elapsed | 2776 | +| total_timesteps | 3905536 | +| train/ | | +| approx_kl | 0.011061184 | +| clip_fraction | 0.32 | +| clip_range | 0.074 | +| entropy_loss | -7.35 | +| explained_variance | -0.245 | +| learning_rate | 4.91e-05 | +| loss | -0.0372 | +| n_updates | 23444 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000129 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1406 | +| iterations | 1908 | +| time_elapsed | 2777 | +| total_timesteps | 3907584 | +| train/ | | +| approx_kl | 0.009857852 | +| clip_fraction | 0.313 | +| clip_range | 0.074 | +| entropy_loss | -7.06 | +| explained_variance | 0.13 | +| learning_rate | 4.91e-05 | +| loss | -0.0309 | +| n_updates | 23448 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000248 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1406 | +| iterations | 1909 | +| time_elapsed | 2779 | +| total_timesteps | 3909632 | +| train/ | | +| approx_kl | 0.011469681 | +| clip_fraction | 0.326 | +| clip_range | 0.074 | +| entropy_loss | -7.18 | +| explained_variance | -0.00262 | +| learning_rate | 4.91e-05 | +| loss | -0.0321 | +| n_updates | 23452 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000176 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1406 | +| iterations | 1910 | +| time_elapsed | 2780 | +| total_timesteps | 3911680 | +| train/ | | +| approx_kl | 0.0107329115 | +| clip_fraction | 0.316 | +| clip_range | 0.074 | +| entropy_loss | -7.25 | +| explained_variance | 0.205 | +| learning_rate | 4.91e-05 | +| loss | -0.0358 | +| n_updates | 23456 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000162 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1406 | +| iterations | 1911 | +| time_elapsed | 2782 | +| total_timesteps | 3913728 | +| train/ | | +| approx_kl | 0.011135304 | +| clip_fraction | 0.313 | +| clip_range | 0.074 | +| entropy_loss | -7.28 | +| explained_variance | 0.333 | +| learning_rate | 4.91e-05 | +| loss | -0.0339 | +| n_updates | 23460 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.00011 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1406 | +| iterations | 1912 | +| time_elapsed | 2783 | +| total_timesteps | 3915776 | +| train/ | | +| approx_kl | 0.010528729 | +| clip_fraction | 0.298 | +| clip_range | 0.074 | +| entropy_loss | -6.85 | +| explained_variance | 0.518 | +| learning_rate | 4.91e-05 | +| loss | -0.0382 | +| n_updates | 23464 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000204 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1406 | +| iterations | 1913 | +| time_elapsed | 2785 | +| total_timesteps | 3917824 | +| train/ | | +| approx_kl | 0.0077352994 | +| clip_fraction | 0.287 | +| clip_range | 0.074 | +| entropy_loss | -7.25 | +| explained_variance | 0.138 | +| learning_rate | 4.91e-05 | +| loss | -0.033 | +| n_updates | 23468 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000407 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1406 | +| iterations | 1914 | +| time_elapsed | 2786 | +| total_timesteps | 3919872 | +| train/ | | +| approx_kl | 0.012925228 | +| clip_fraction | 0.313 | +| clip_range | 0.074 | +| entropy_loss | -7.13 | +| explained_variance | 0.468 | +| learning_rate | 4.91e-05 | +| loss | -0.0395 | +| n_updates | 23472 | +| policy_gradient_loss | -0.0225 | +| value_loss | 0.000153 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1406 | +| iterations | 1915 | +| time_elapsed | 2787 | +| total_timesteps | 3921920 | +| train/ | | +| approx_kl | 0.011804879 | +| clip_fraction | 0.335 | +| clip_range | 0.074 | +| entropy_loss | -7.01 | +| explained_variance | 0.493 | +| learning_rate | 4.91e-05 | +| loss | -0.0338 | +| n_updates | 23476 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000164 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1406 | +| iterations | 1916 | +| time_elapsed | 2789 | +| total_timesteps | 3923968 | +| train/ | | +| approx_kl | 0.00981118 | +| clip_fraction | 0.285 | +| clip_range | 0.074 | +| entropy_loss | -6.75 | +| explained_variance | 0.464 | +| learning_rate | 4.91e-05 | +| loss | -0.0243 | +| n_updates | 23480 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000284 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1406 | +| iterations | 1917 | +| time_elapsed | 2790 | +| total_timesteps | 3926016 | +| train/ | | +| approx_kl | 0.0097525045 | +| clip_fraction | 0.319 | +| clip_range | 0.074 | +| entropy_loss | -7.31 | +| explained_variance | -0.186 | +| learning_rate | 4.91e-05 | +| loss | -0.0326 | +| n_updates | 23484 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.00013 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1406 | +| iterations | 1918 | +| time_elapsed | 2792 | +| total_timesteps | 3928064 | +| train/ | | +| approx_kl | 0.0098427255 | +| clip_fraction | 0.303 | +| clip_range | 0.074 | +| entropy_loss | -7.07 | +| explained_variance | 0.29 | +| learning_rate | 4.91e-05 | +| loss | -0.024 | +| n_updates | 23488 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000258 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1406 | +| iterations | 1919 | +| time_elapsed | 2793 | +| total_timesteps | 3930112 | +| train/ | | +| approx_kl | 0.010789846 | +| clip_fraction | 0.309 | +| clip_range | 0.074 | +| entropy_loss | -7.25 | +| explained_variance | 0.152 | +| learning_rate | 4.91e-05 | +| loss | -0.0378 | +| n_updates | 23492 | +| policy_gradient_loss | -0.0221 | +| value_loss | 0.000224 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1406 | +| iterations | 1920 | +| time_elapsed | 2795 | +| total_timesteps | 3932160 | +| train/ | | +| approx_kl | 0.012041917 | +| clip_fraction | 0.337 | +| clip_range | 0.074 | +| entropy_loss | -7.18 | +| explained_variance | -0.0895 | +| learning_rate | 4.91e-05 | +| loss | -0.0393 | +| n_updates | 23496 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.00019 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1406 | +| iterations | 1921 | +| time_elapsed | 2796 | +| total_timesteps | 3934208 | +| train/ | | +| approx_kl | 0.010114325 | +| clip_fraction | 0.318 | +| clip_range | 0.074 | +| entropy_loss | -7.06 | +| explained_variance | 0.517 | +| learning_rate | 4.91e-05 | +| loss | -0.0391 | +| n_updates | 23500 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000169 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1406 | +| iterations | 1922 | +| time_elapsed | 2798 | +| total_timesteps | 3936256 | +| train/ | | +| approx_kl | 0.0101001365 | +| clip_fraction | 0.301 | +| clip_range | 0.074 | +| entropy_loss | -7.27 | +| explained_variance | 0.277 | +| learning_rate | 4.91e-05 | +| loss | -0.0326 | +| n_updates | 23504 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000197 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1406 | +| iterations | 1923 | +| time_elapsed | 2799 | +| total_timesteps | 3938304 | +| train/ | | +| approx_kl | 0.012421084 | +| clip_fraction | 0.35 | +| clip_range | 0.074 | +| entropy_loss | -7.42 | +| explained_variance | -0.275 | +| learning_rate | 4.91e-05 | +| loss | -0.0375 | +| n_updates | 23508 | +| policy_gradient_loss | -0.0247 | +| value_loss | 9.86e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1406 | +| iterations | 1924 | +| time_elapsed | 2800 | +| total_timesteps | 3940352 | +| train/ | | +| approx_kl | 0.009813374 | +| clip_fraction | 0.304 | +| clip_range | 0.074 | +| entropy_loss | -7.55 | +| explained_variance | -0.0771 | +| learning_rate | 4.91e-05 | +| loss | -0.0365 | +| n_updates | 23512 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000157 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1406 | +| iterations | 1925 | +| time_elapsed | 2802 | +| total_timesteps | 3942400 | +| train/ | | +| approx_kl | 0.009902944 | +| clip_fraction | 0.282 | +| clip_range | 0.074 | +| entropy_loss | -7.1 | +| explained_variance | 0.467 | +| learning_rate | 4.91e-05 | +| loss | -0.0342 | +| n_updates | 23516 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000171 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1406 | +| iterations | 1926 | +| time_elapsed | 2803 | +| total_timesteps | 3944448 | +| train/ | | +| approx_kl | 0.01172624 | +| clip_fraction | 0.315 | +| clip_range | 0.074 | +| entropy_loss | -7.08 | +| explained_variance | 0.356 | +| learning_rate | 4.91e-05 | +| loss | -0.0356 | +| n_updates | 23520 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000114 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1406 | +| iterations | 1927 | +| time_elapsed | 2805 | +| total_timesteps | 3946496 | +| train/ | | +| approx_kl | 0.010381704 | +| clip_fraction | 0.293 | +| clip_range | 0.074 | +| entropy_loss | -6.66 | +| explained_variance | 0.248 | +| learning_rate | 4.91e-05 | +| loss | -0.0327 | +| n_updates | 23524 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000325 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1406 | +| iterations | 1928 | +| time_elapsed | 2806 | +| total_timesteps | 3948544 | +| train/ | | +| approx_kl | 0.011976229 | +| clip_fraction | 0.335 | +| clip_range | 0.074 | +| entropy_loss | -7.18 | +| explained_variance | 0.119 | +| learning_rate | 4.91e-05 | +| loss | -0.0356 | +| n_updates | 23528 | +| policy_gradient_loss | -0.0219 | +| value_loss | 0.000234 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1406 | +| iterations | 1929 | +| time_elapsed | 2807 | +| total_timesteps | 3950592 | +| train/ | | +| approx_kl | 0.011296289 | +| clip_fraction | 0.331 | +| clip_range | 0.074 | +| entropy_loss | -7.28 | +| explained_variance | -0.151 | +| learning_rate | 4.91e-05 | +| loss | -0.0284 | +| n_updates | 23532 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000247 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1406 | +| iterations | 1930 | +| time_elapsed | 2809 | +| total_timesteps | 3952640 | +| train/ | | +| approx_kl | 0.010840045 | +| clip_fraction | 0.332 | +| clip_range | 0.074 | +| entropy_loss | -7.29 | +| explained_variance | -0.0323 | +| learning_rate | 4.91e-05 | +| loss | -0.0364 | +| n_updates | 23536 | +| policy_gradient_loss | -0.022 | +| value_loss | 0.000147 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1406 | +| iterations | 1931 | +| time_elapsed | 2810 | +| total_timesteps | 3954688 | +| train/ | | +| approx_kl | 0.009323023 | +| clip_fraction | 0.281 | +| clip_range | 0.074 | +| entropy_loss | -7.06 | +| explained_variance | 0.182 | +| learning_rate | 4.91e-05 | +| loss | -0.0298 | +| n_updates | 23540 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000234 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1406 | +| iterations | 1932 | +| time_elapsed | 2812 | +| total_timesteps | 3956736 | +| train/ | | +| approx_kl | 0.012296159 | +| clip_fraction | 0.322 | +| clip_range | 0.074 | +| entropy_loss | -6.99 | +| explained_variance | 0.473 | +| learning_rate | 4.91e-05 | +| loss | -0.0282 | +| n_updates | 23544 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000128 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1407 | +| iterations | 1933 | +| time_elapsed | 2813 | +| total_timesteps | 3958784 | +| train/ | | +| approx_kl | 0.0090780705 | +| clip_fraction | 0.285 | +| clip_range | 0.074 | +| entropy_loss | -7.23 | +| explained_variance | 0.193 | +| learning_rate | 4.91e-05 | +| loss | -0.0257 | +| n_updates | 23548 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000336 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1407 | +| iterations | 1934 | +| time_elapsed | 2814 | +| total_timesteps | 3960832 | +| train/ | | +| approx_kl | 0.009846876 | +| clip_fraction | 0.295 | +| clip_range | 0.074 | +| entropy_loss | -7.13 | +| explained_variance | 0.227 | +| learning_rate | 4.91e-05 | +| loss | -0.0361 | +| n_updates | 23552 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.00034 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1407 | +| iterations | 1935 | +| time_elapsed | 2816 | +| total_timesteps | 3962880 | +| train/ | | +| approx_kl | 0.010799036 | +| clip_fraction | 0.324 | +| clip_range | 0.074 | +| entropy_loss | -7.31 | +| explained_variance | 0.0604 | +| learning_rate | 4.91e-05 | +| loss | -0.0364 | +| n_updates | 23556 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000177 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1407 | +| iterations | 1936 | +| time_elapsed | 2817 | +| total_timesteps | 3964928 | +| train/ | | +| approx_kl | 0.010920414 | +| clip_fraction | 0.32 | +| clip_range | 0.074 | +| entropy_loss | -7.04 | +| explained_variance | 0.462 | +| learning_rate | 4.91e-05 | +| loss | -0.0306 | +| n_updates | 23560 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000218 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1407 | +| iterations | 1937 | +| time_elapsed | 2819 | +| total_timesteps | 3966976 | +| train/ | | +| approx_kl | 0.010922403 | +| clip_fraction | 0.318 | +| clip_range | 0.074 | +| entropy_loss | -7.26 | +| explained_variance | -0.142 | +| learning_rate | 4.91e-05 | +| loss | -0.028 | +| n_updates | 23564 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000248 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.385 | +| time/ | | +| fps | 1407 | +| iterations | 1938 | +| time_elapsed | 2820 | +| total_timesteps | 3969024 | +| train/ | | +| approx_kl | 0.011182274 | +| clip_fraction | 0.333 | +| clip_range | 0.074 | +| entropy_loss | -7.42 | +| explained_variance | -0.157 | +| learning_rate | 4.91e-05 | +| loss | -0.0378 | +| n_updates | 23568 | +| policy_gradient_loss | -0.0222 | +| value_loss | 0.000185 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.385 | +| time/ | | +| fps | 1407 | +| iterations | 1939 | +| time_elapsed | 2822 | +| total_timesteps | 3971072 | +| train/ | | +| approx_kl | 0.009750364 | +| clip_fraction | 0.294 | +| clip_range | 0.074 | +| entropy_loss | -6.89 | +| explained_variance | 0.227 | +| learning_rate | 4.91e-05 | +| loss | -0.0273 | +| n_updates | 23572 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.00029 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1407 | +| iterations | 1940 | +| time_elapsed | 2823 | +| total_timesteps | 3973120 | +| train/ | | +| approx_kl | 0.011744687 | +| clip_fraction | 0.33 | +| clip_range | 0.074 | +| entropy_loss | -7.32 | +| explained_variance | 0.265 | +| learning_rate | 4.91e-05 | +| loss | -0.031 | +| n_updates | 23576 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000123 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1407 | +| iterations | 1941 | +| time_elapsed | 2824 | +| total_timesteps | 3975168 | +| train/ | | +| approx_kl | 0.010497942 | +| clip_fraction | 0.309 | +| clip_range | 0.074 | +| entropy_loss | -7.05 | +| explained_variance | 0.0856 | +| learning_rate | 4.91e-05 | +| loss | -0.0354 | +| n_updates | 23580 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.00019 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1407 | +| iterations | 1942 | +| time_elapsed | 2826 | +| total_timesteps | 3977216 | +| train/ | | +| approx_kl | 0.010872931 | +| clip_fraction | 0.329 | +| clip_range | 0.074 | +| entropy_loss | -7.3 | +| explained_variance | -0.146 | +| learning_rate | 4.91e-05 | +| loss | -0.0286 | +| n_updates | 23584 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000141 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1407 | +| iterations | 1943 | +| time_elapsed | 2827 | +| total_timesteps | 3979264 | +| train/ | | +| approx_kl | 0.011253649 | +| clip_fraction | 0.314 | +| clip_range | 0.074 | +| entropy_loss | -7.49 | +| explained_variance | -0.188 | +| learning_rate | 4.91e-05 | +| loss | -0.0361 | +| n_updates | 23588 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000121 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1407 | +| iterations | 1944 | +| time_elapsed | 2829 | +| total_timesteps | 3981312 | +| train/ | | +| approx_kl | 0.010632258 | +| clip_fraction | 0.333 | +| clip_range | 0.074 | +| entropy_loss | -7.36 | +| explained_variance | 0.151 | +| learning_rate | 4.91e-05 | +| loss | -0.0315 | +| n_updates | 23592 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000137 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1407 | +| iterations | 1945 | +| time_elapsed | 2830 | +| total_timesteps | 3983360 | +| train/ | | +| approx_kl | 0.009362962 | +| clip_fraction | 0.286 | +| clip_range | 0.074 | +| entropy_loss | -7 | +| explained_variance | 0.602 | +| learning_rate | 4.91e-05 | +| loss | -0.0295 | +| n_updates | 23596 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.00011 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1407 | +| iterations | 1946 | +| time_elapsed | 2832 | +| total_timesteps | 3985408 | +| train/ | | +| approx_kl | 0.010541445 | +| clip_fraction | 0.291 | +| clip_range | 0.074 | +| entropy_loss | -7.1 | +| explained_variance | 0.545 | +| learning_rate | 4.91e-05 | +| loss | -0.0299 | +| n_updates | 23600 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000119 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1407 | +| iterations | 1947 | +| time_elapsed | 2833 | +| total_timesteps | 3987456 | +| train/ | | +| approx_kl | 0.009510273 | +| clip_fraction | 0.31 | +| clip_range | 0.074 | +| entropy_loss | -7.47 | +| explained_variance | -0.0673 | +| learning_rate | 4.91e-05 | +| loss | -0.0342 | +| n_updates | 23604 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000175 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1407 | +| iterations | 1948 | +| time_elapsed | 2835 | +| total_timesteps | 3989504 | +| train/ | | +| approx_kl | 0.01055839 | +| clip_fraction | 0.314 | +| clip_range | 0.074 | +| entropy_loss | -7.19 | +| explained_variance | 0.478 | +| learning_rate | 4.91e-05 | +| loss | -0.0306 | +| n_updates | 23608 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.00014 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.387 | +| time/ | | +| fps | 1407 | +| iterations | 1949 | +| time_elapsed | 2836 | +| total_timesteps | 3991552 | +| train/ | | +| approx_kl | 0.009262735 | +| clip_fraction | 0.318 | +| clip_range | 0.074 | +| entropy_loss | -7.29 | +| explained_variance | 0.352 | +| learning_rate | 4.91e-05 | +| loss | -0.0221 | +| n_updates | 23612 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000126 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.387 | +| time/ | | +| fps | 1407 | +| iterations | 1950 | +| time_elapsed | 2837 | +| total_timesteps | 3993600 | +| train/ | | +| approx_kl | 0.011882474 | +| clip_fraction | 0.292 | +| clip_range | 0.074 | +| entropy_loss | -7.07 | +| explained_variance | 0.204 | +| learning_rate | 4.91e-05 | +| loss | -0.0259 | +| n_updates | 23616 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000253 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.384 | +| time/ | | +| fps | 1407 | +| iterations | 1951 | +| time_elapsed | 2839 | +| total_timesteps | 3995648 | +| train/ | | +| approx_kl | 0.0102318525 | +| clip_fraction | 0.305 | +| clip_range | 0.074 | +| entropy_loss | -7.01 | +| explained_variance | 0.191 | +| learning_rate | 4.91e-05 | +| loss | -0.0228 | +| n_updates | 23620 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000169 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1407 | +| iterations | 1952 | +| time_elapsed | 2840 | +| total_timesteps | 3997696 | +| train/ | | +| approx_kl | 0.011330266 | +| clip_fraction | 0.319 | +| clip_range | 0.074 | +| entropy_loss | -7.36 | +| explained_variance | -0.155 | +| learning_rate | 4.91e-05 | +| loss | -0.0291 | +| n_updates | 23624 | +| policy_gradient_loss | -0.0195 | +| value_loss | 9.46e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.384 | +| time/ | | +| fps | 1407 | +| iterations | 1953 | +| time_elapsed | 2842 | +| total_timesteps | 3999744 | +| train/ | | +| approx_kl | 0.010439731 | +| clip_fraction | 0.319 | +| clip_range | 0.074 | +| entropy_loss | -7.29 | +| explained_variance | -0.149 | +| learning_rate | 4.91e-05 | +| loss | -0.0247 | +| n_updates | 23628 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000124 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.385 | +| time/ | | +| fps | 1407 | +| iterations | 1954 | +| time_elapsed | 2843 | +| total_timesteps | 4001792 | +| train/ | | +| approx_kl | 0.010851759 | +| clip_fraction | 0.324 | +| clip_range | 0.074 | +| entropy_loss | -7.15 | +| explained_variance | 0.349 | +| learning_rate | 4.91e-05 | +| loss | -0.0332 | +| n_updates | 23632 | +| policy_gradient_loss | -0.0211 | +| value_loss | 9.34e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.385 | +| time/ | | +| fps | 1407 | +| iterations | 1955 | +| time_elapsed | 2845 | +| total_timesteps | 4003840 | +| train/ | | +| approx_kl | 0.0110983495 | +| clip_fraction | 0.347 | +| clip_range | 0.074 | +| entropy_loss | -7.11 | +| explained_variance | 0.415 | +| learning_rate | 4.9e-05 | +| loss | -0.0328 | +| n_updates | 23636 | +| policy_gradient_loss | -0.0209 | +| value_loss | 7.68e-05 | +------------------------------------------ +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1407 | +| iterations | 1956 | +| time_elapsed | 2846 | +| total_timesteps | 4005888 | +| train/ | | +| approx_kl | 0.0126107 | +| clip_fraction | 0.324 | +| clip_range | 0.074 | +| entropy_loss | -7.49 | +| explained_variance | -0.0583 | +| learning_rate | 4.9e-05 | +| loss | -0.0275 | +| n_updates | 23640 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000122 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1407 | +| iterations | 1957 | +| time_elapsed | 2847 | +| total_timesteps | 4007936 | +| train/ | | +| approx_kl | 0.010726795 | +| clip_fraction | 0.313 | +| clip_range | 0.074 | +| entropy_loss | -7.33 | +| explained_variance | -0.151 | +| learning_rate | 4.9e-05 | +| loss | -0.0389 | +| n_updates | 23644 | +| policy_gradient_loss | -0.021 | +| value_loss | 6.75e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1407 | +| iterations | 1958 | +| time_elapsed | 2849 | +| total_timesteps | 4009984 | +| train/ | | +| approx_kl | 0.012390658 | +| clip_fraction | 0.311 | +| clip_range | 0.074 | +| entropy_loss | -7.08 | +| explained_variance | 0.192 | +| learning_rate | 4.9e-05 | +| loss | -0.0261 | +| n_updates | 23648 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000117 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1407 | +| iterations | 1959 | +| time_elapsed | 2850 | +| total_timesteps | 4012032 | +| train/ | | +| approx_kl | 0.0098532885 | +| clip_fraction | 0.279 | +| clip_range | 0.074 | +| entropy_loss | -6.91 | +| explained_variance | 0.551 | +| learning_rate | 4.9e-05 | +| loss | -0.031 | +| n_updates | 23652 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000212 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1407 | +| iterations | 1960 | +| time_elapsed | 2852 | +| total_timesteps | 4014080 | +| train/ | | +| approx_kl | 0.011286761 | +| clip_fraction | 0.332 | +| clip_range | 0.074 | +| entropy_loss | -7.12 | +| explained_variance | 0.434 | +| learning_rate | 4.9e-05 | +| loss | -0.0345 | +| n_updates | 23656 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000185 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1407 | +| iterations | 1961 | +| time_elapsed | 2853 | +| total_timesteps | 4016128 | +| train/ | | +| approx_kl | 0.012980489 | +| clip_fraction | 0.32 | +| clip_range | 0.074 | +| entropy_loss | -7.29 | +| explained_variance | 0.316 | +| learning_rate | 4.9e-05 | +| loss | -0.0365 | +| n_updates | 23660 | +| policy_gradient_loss | -0.0227 | +| value_loss | 0.000129 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1407 | +| iterations | 1962 | +| time_elapsed | 2855 | +| total_timesteps | 4018176 | +| train/ | | +| approx_kl | 0.0118941665 | +| clip_fraction | 0.324 | +| clip_range | 0.074 | +| entropy_loss | -7.29 | +| explained_variance | 0.326 | +| learning_rate | 4.9e-05 | +| loss | -0.0355 | +| n_updates | 23664 | +| policy_gradient_loss | -0.0226 | +| value_loss | 0.000123 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1407 | +| iterations | 1963 | +| time_elapsed | 2856 | +| total_timesteps | 4020224 | +| train/ | | +| approx_kl | 0.012251817 | +| clip_fraction | 0.341 | +| clip_range | 0.074 | +| entropy_loss | -7.14 | +| explained_variance | 0.525 | +| learning_rate | 4.9e-05 | +| loss | -0.0429 | +| n_updates | 23668 | +| policy_gradient_loss | -0.0235 | +| value_loss | 0.000122 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1407 | +| iterations | 1964 | +| time_elapsed | 2858 | +| total_timesteps | 4022272 | +| train/ | | +| approx_kl | 0.009757443 | +| clip_fraction | 0.307 | +| clip_range | 0.074 | +| entropy_loss | -7.2 | +| explained_variance | -0.0759 | +| learning_rate | 4.9e-05 | +| loss | -0.0318 | +| n_updates | 23672 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000246 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1407 | +| iterations | 1965 | +| time_elapsed | 2859 | +| total_timesteps | 4024320 | +| train/ | | +| approx_kl | 0.011634974 | +| clip_fraction | 0.359 | +| clip_range | 0.074 | +| entropy_loss | -7.22 | +| explained_variance | 0.36 | +| learning_rate | 4.9e-05 | +| loss | -0.0436 | +| n_updates | 23676 | +| policy_gradient_loss | -0.0251 | +| value_loss | 6.62e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1407 | +| iterations | 1966 | +| time_elapsed | 2861 | +| total_timesteps | 4026368 | +| train/ | | +| approx_kl | 0.012579086 | +| clip_fraction | 0.3 | +| clip_range | 0.074 | +| entropy_loss | -7.14 | +| explained_variance | 0.268 | +| learning_rate | 4.9e-05 | +| loss | -0.0307 | +| n_updates | 23680 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000165 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1407 | +| iterations | 1967 | +| time_elapsed | 2862 | +| total_timesteps | 4028416 | +| train/ | | +| approx_kl | 0.012614845 | +| clip_fraction | 0.329 | +| clip_range | 0.074 | +| entropy_loss | -7.38 | +| explained_variance | -0.0217 | +| learning_rate | 4.9e-05 | +| loss | -0.0307 | +| n_updates | 23684 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000136 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1407 | +| iterations | 1968 | +| time_elapsed | 2863 | +| total_timesteps | 4030464 | +| train/ | | +| approx_kl | 0.01186303 | +| clip_fraction | 0.332 | +| clip_range | 0.074 | +| entropy_loss | -7.41 | +| explained_variance | -0.0957 | +| learning_rate | 4.9e-05 | +| loss | -0.0358 | +| n_updates | 23688 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000112 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1407 | +| iterations | 1969 | +| time_elapsed | 2865 | +| total_timesteps | 4032512 | +| train/ | | +| approx_kl | 0.011566651 | +| clip_fraction | 0.346 | +| clip_range | 0.074 | +| entropy_loss | -7.15 | +| explained_variance | -0.318 | +| learning_rate | 4.9e-05 | +| loss | -0.0378 | +| n_updates | 23692 | +| policy_gradient_loss | -0.0223 | +| value_loss | 6.4e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1407 | +| iterations | 1970 | +| time_elapsed | 2866 | +| total_timesteps | 4034560 | +| train/ | | +| approx_kl | 0.0115812905 | +| clip_fraction | 0.324 | +| clip_range | 0.074 | +| entropy_loss | -6.82 | +| explained_variance | 0.393 | +| learning_rate | 4.9e-05 | +| loss | -0.0289 | +| n_updates | 23696 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000162 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1407 | +| iterations | 1971 | +| time_elapsed | 2868 | +| total_timesteps | 4036608 | +| train/ | | +| approx_kl | 0.010915467 | +| clip_fraction | 0.304 | +| clip_range | 0.074 | +| entropy_loss | -7.09 | +| explained_variance | 0.199 | +| learning_rate | 4.9e-05 | +| loss | -0.0341 | +| n_updates | 23700 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000157 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1407 | +| iterations | 1972 | +| time_elapsed | 2869 | +| total_timesteps | 4038656 | +| train/ | | +| approx_kl | 0.010569896 | +| clip_fraction | 0.315 | +| clip_range | 0.074 | +| entropy_loss | -7.07 | +| explained_variance | 0.313 | +| learning_rate | 4.9e-05 | +| loss | -0.0369 | +| n_updates | 23704 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.00012 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1407 | +| iterations | 1973 | +| time_elapsed | 2870 | +| total_timesteps | 4040704 | +| train/ | | +| approx_kl | 0.013191029 | +| clip_fraction | 0.328 | +| clip_range | 0.074 | +| entropy_loss | -7.2 | +| explained_variance | 0.269 | +| learning_rate | 4.9e-05 | +| loss | -0.037 | +| n_updates | 23708 | +| policy_gradient_loss | -0.022 | +| value_loss | 0.000158 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1407 | +| iterations | 1974 | +| time_elapsed | 2872 | +| total_timesteps | 4042752 | +| train/ | | +| approx_kl | 0.0105690425 | +| clip_fraction | 0.333 | +| clip_range | 0.074 | +| entropy_loss | -7.18 | +| explained_variance | 0.389 | +| learning_rate | 4.9e-05 | +| loss | -0.0341 | +| n_updates | 23712 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000113 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1407 | +| iterations | 1975 | +| time_elapsed | 2873 | +| total_timesteps | 4044800 | +| train/ | | +| approx_kl | 0.012965942 | +| clip_fraction | 0.303 | +| clip_range | 0.074 | +| entropy_loss | -7.24 | +| explained_variance | 0.0132 | +| learning_rate | 4.9e-05 | +| loss | -0.0353 | +| n_updates | 23716 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000178 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1407 | +| iterations | 1976 | +| time_elapsed | 2875 | +| total_timesteps | 4046848 | +| train/ | | +| approx_kl | 0.012711903 | +| clip_fraction | 0.337 | +| clip_range | 0.074 | +| entropy_loss | -7.34 | +| explained_variance | 0.254 | +| learning_rate | 4.9e-05 | +| loss | -0.0328 | +| n_updates | 23720 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000129 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1407 | +| iterations | 1977 | +| time_elapsed | 2876 | +| total_timesteps | 4048896 | +| train/ | | +| approx_kl | 0.012030944 | +| clip_fraction | 0.33 | +| clip_range | 0.074 | +| entropy_loss | -7.41 | +| explained_variance | -0.0861 | +| learning_rate | 4.9e-05 | +| loss | -0.0321 | +| n_updates | 23724 | +| policy_gradient_loss | -0.022 | +| value_loss | 8.5e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1407 | +| iterations | 1978 | +| time_elapsed | 2878 | +| total_timesteps | 4050944 | +| train/ | | +| approx_kl | 0.010998621 | +| clip_fraction | 0.32 | +| clip_range | 0.074 | +| entropy_loss | -7.24 | +| explained_variance | 0.406 | +| learning_rate | 4.9e-05 | +| loss | -0.0309 | +| n_updates | 23728 | +| policy_gradient_loss | -0.0206 | +| value_loss | 9.57e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1407 | +| iterations | 1979 | +| time_elapsed | 2879 | +| total_timesteps | 4052992 | +| train/ | | +| approx_kl | 0.009289393 | +| clip_fraction | 0.293 | +| clip_range | 0.074 | +| entropy_loss | -7.02 | +| explained_variance | 0.118 | +| learning_rate | 4.9e-05 | +| loss | -0.034 | +| n_updates | 23732 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000199 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1407 | +| iterations | 1980 | +| time_elapsed | 2880 | +| total_timesteps | 4055040 | +| train/ | | +| approx_kl | 0.009793263 | +| clip_fraction | 0.298 | +| clip_range | 0.074 | +| entropy_loss | -6.79 | +| explained_variance | 0.283 | +| learning_rate | 4.9e-05 | +| loss | -0.0314 | +| n_updates | 23736 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000208 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1407 | +| iterations | 1981 | +| time_elapsed | 2882 | +| total_timesteps | 4057088 | +| train/ | | +| approx_kl | 0.0111379875 | +| clip_fraction | 0.313 | +| clip_range | 0.074 | +| entropy_loss | -7.26 | +| explained_variance | 0.365 | +| learning_rate | 4.9e-05 | +| loss | -0.0361 | +| n_updates | 23740 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000123 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1407 | +| iterations | 1982 | +| time_elapsed | 2883 | +| total_timesteps | 4059136 | +| train/ | | +| approx_kl | 0.011119461 | +| clip_fraction | 0.314 | +| clip_range | 0.074 | +| entropy_loss | -7.32 | +| explained_variance | 0.0514 | +| learning_rate | 4.9e-05 | +| loss | -0.0369 | +| n_updates | 23744 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000106 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1407 | +| iterations | 1983 | +| time_elapsed | 2885 | +| total_timesteps | 4061184 | +| train/ | | +| approx_kl | 0.011678254 | +| clip_fraction | 0.302 | +| clip_range | 0.074 | +| entropy_loss | -6.95 | +| explained_variance | 0.344 | +| learning_rate | 4.9e-05 | +| loss | -0.0317 | +| n_updates | 23748 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000236 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1407 | +| iterations | 1984 | +| time_elapsed | 2886 | +| total_timesteps | 4063232 | +| train/ | | +| approx_kl | 0.012038218 | +| clip_fraction | 0.328 | +| clip_range | 0.074 | +| entropy_loss | -7.32 | +| explained_variance | 0.397 | +| learning_rate | 4.9e-05 | +| loss | -0.0339 | +| n_updates | 23752 | +| policy_gradient_loss | -0.0211 | +| value_loss | 9.83e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1407 | +| iterations | 1985 | +| time_elapsed | 2888 | +| total_timesteps | 4065280 | +| train/ | | +| approx_kl | 0.01168726 | +| clip_fraction | 0.344 | +| clip_range | 0.074 | +| entropy_loss | -7.31 | +| explained_variance | -0.0866 | +| learning_rate | 4.9e-05 | +| loss | -0.0326 | +| n_updates | 23756 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000166 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1407 | +| iterations | 1986 | +| time_elapsed | 2889 | +| total_timesteps | 4067328 | +| train/ | | +| approx_kl | 0.010224899 | +| clip_fraction | 0.323 | +| clip_range | 0.074 | +| entropy_loss | -7.4 | +| explained_variance | 0.0192 | +| learning_rate | 4.9e-05 | +| loss | -0.0324 | +| n_updates | 23760 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000156 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1407 | +| iterations | 1987 | +| time_elapsed | 2891 | +| total_timesteps | 4069376 | +| train/ | | +| approx_kl | 0.010490988 | +| clip_fraction | 0.297 | +| clip_range | 0.074 | +| entropy_loss | -7.13 | +| explained_variance | 0.264 | +| learning_rate | 4.9e-05 | +| loss | -0.0288 | +| n_updates | 23764 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000291 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1407 | +| iterations | 1988 | +| time_elapsed | 2892 | +| total_timesteps | 4071424 | +| train/ | | +| approx_kl | 0.011299445 | +| clip_fraction | 0.329 | +| clip_range | 0.074 | +| entropy_loss | -7.03 | +| explained_variance | 0.538 | +| learning_rate | 4.9e-05 | +| loss | -0.0337 | +| n_updates | 23768 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000105 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1407 | +| iterations | 1989 | +| time_elapsed | 2893 | +| total_timesteps | 4073472 | +| train/ | | +| approx_kl | 0.0113218445 | +| clip_fraction | 0.31 | +| clip_range | 0.074 | +| entropy_loss | -7.12 | +| explained_variance | 0.627 | +| learning_rate | 4.9e-05 | +| loss | -0.0309 | +| n_updates | 23772 | +| policy_gradient_loss | -0.0222 | +| value_loss | 8.58e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1407 | +| iterations | 1990 | +| time_elapsed | 2895 | +| total_timesteps | 4075520 | +| train/ | | +| approx_kl | 0.011413563 | +| clip_fraction | 0.293 | +| clip_range | 0.074 | +| entropy_loss | -6.97 | +| explained_variance | 0.414 | +| learning_rate | 4.9e-05 | +| loss | -0.0318 | +| n_updates | 23776 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000181 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1407 | +| iterations | 1991 | +| time_elapsed | 2896 | +| total_timesteps | 4077568 | +| train/ | | +| approx_kl | 0.012581882 | +| clip_fraction | 0.306 | +| clip_range | 0.074 | +| entropy_loss | -7.19 | +| explained_variance | 0.0973 | +| learning_rate | 4.9e-05 | +| loss | -0.0287 | +| n_updates | 23780 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000172 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1407 | +| iterations | 1992 | +| time_elapsed | 2898 | +| total_timesteps | 4079616 | +| train/ | | +| approx_kl | 0.010609798 | +| clip_fraction | 0.303 | +| clip_range | 0.074 | +| entropy_loss | -7.12 | +| explained_variance | 0.299 | +| learning_rate | 4.9e-05 | +| loss | -0.0293 | +| n_updates | 23784 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000214 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1407 | +| iterations | 1993 | +| time_elapsed | 2899 | +| total_timesteps | 4081664 | +| train/ | | +| approx_kl | 0.013078177 | +| clip_fraction | 0.372 | +| clip_range | 0.074 | +| entropy_loss | -7.27 | +| explained_variance | 0.416 | +| learning_rate | 4.9e-05 | +| loss | -0.0432 | +| n_updates | 23788 | +| policy_gradient_loss | -0.0265 | +| value_loss | 6.83e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1407 | +| iterations | 1994 | +| time_elapsed | 2901 | +| total_timesteps | 4083712 | +| train/ | | +| approx_kl | 0.011426534 | +| clip_fraction | 0.337 | +| clip_range | 0.074 | +| entropy_loss | -7.02 | +| explained_variance | 0.54 | +| learning_rate | 4.9e-05 | +| loss | -0.0347 | +| n_updates | 23792 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000116 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1407 | +| iterations | 1995 | +| time_elapsed | 2902 | +| total_timesteps | 4085760 | +| train/ | | +| approx_kl | 0.0100770565 | +| clip_fraction | 0.296 | +| clip_range | 0.074 | +| entropy_loss | -7.32 | +| explained_variance | 0.0666 | +| learning_rate | 4.9e-05 | +| loss | -0.029 | +| n_updates | 23796 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000185 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 1407 | +| iterations | 1996 | +| time_elapsed | 2903 | +| total_timesteps | 4087808 | +| train/ | | +| approx_kl | 0.0109602045 | +| clip_fraction | 0.339 | +| clip_range | 0.074 | +| entropy_loss | -7.1 | +| explained_variance | 0.666 | +| learning_rate | 4.9e-05 | +| loss | -0.0478 | +| n_updates | 23800 | +| policy_gradient_loss | -0.0253 | +| value_loss | 6.35e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1407 | +| iterations | 1997 | +| time_elapsed | 2905 | +| total_timesteps | 4089856 | +| train/ | | +| approx_kl | 0.012741667 | +| clip_fraction | 0.316 | +| clip_range | 0.074 | +| entropy_loss | -6.92 | +| explained_variance | 0.498 | +| learning_rate | 4.9e-05 | +| loss | -0.03 | +| n_updates | 23804 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000149 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1407 | +| iterations | 1998 | +| time_elapsed | 2906 | +| total_timesteps | 4091904 | +| train/ | | +| approx_kl | 0.0101983575 | +| clip_fraction | 0.314 | +| clip_range | 0.074 | +| entropy_loss | -7.23 | +| explained_variance | 0.288 | +| learning_rate | 4.9e-05 | +| loss | -0.0312 | +| n_updates | 23808 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000181 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1407 | +| iterations | 1999 | +| time_elapsed | 2908 | +| total_timesteps | 4093952 | +| train/ | | +| approx_kl | 0.012725742 | +| clip_fraction | 0.361 | +| clip_range | 0.074 | +| entropy_loss | -7.19 | +| explained_variance | 0.51 | +| learning_rate | 4.9e-05 | +| loss | -0.0396 | +| n_updates | 23812 | +| policy_gradient_loss | -0.0249 | +| value_loss | 5.6e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1407 | +| iterations | 2000 | +| time_elapsed | 2909 | +| total_timesteps | 4096000 | +| train/ | | +| approx_kl | 0.011975567 | +| clip_fraction | 0.357 | +| clip_range | 0.074 | +| entropy_loss | -7.22 | +| explained_variance | 0.476 | +| learning_rate | 4.9e-05 | +| loss | -0.0361 | +| n_updates | 23816 | +| policy_gradient_loss | -0.0241 | +| value_loss | 7.31e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 1407 | +| iterations | 2001 | +| time_elapsed | 2911 | +| total_timesteps | 4098048 | +| train/ | | +| approx_kl | 0.010110221 | +| clip_fraction | 0.303 | +| clip_range | 0.074 | +| entropy_loss | -7.28 | +| explained_variance | -0.213 | +| learning_rate | 4.9e-05 | +| loss | -0.0242 | +| n_updates | 23820 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000134 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.298 | +| time/ | | +| fps | 1407 | +| iterations | 2002 | +| time_elapsed | 2912 | +| total_timesteps | 4100096 | +| train/ | | +| approx_kl | 0.010394292 | +| clip_fraction | 0.293 | +| clip_range | 0.074 | +| entropy_loss | -7.09 | +| explained_variance | 0.305 | +| learning_rate | 4.9e-05 | +| loss | -0.0287 | +| n_updates | 23824 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000231 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.297 | +| time/ | | +| fps | 1407 | +| iterations | 2003 | +| time_elapsed | 2913 | +| total_timesteps | 4102144 | +| train/ | | +| approx_kl | 0.011740934 | +| clip_fraction | 0.298 | +| clip_range | 0.074 | +| entropy_loss | -7.01 | +| explained_variance | 0.184 | +| learning_rate | 4.9e-05 | +| loss | -0.0327 | +| n_updates | 23828 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000313 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.298 | +| time/ | | +| fps | 1407 | +| iterations | 2004 | +| time_elapsed | 2915 | +| total_timesteps | 4104192 | +| train/ | | +| approx_kl | 0.013526117 | +| clip_fraction | 0.319 | +| clip_range | 0.074 | +| entropy_loss | -6.96 | +| explained_variance | 0.256 | +| learning_rate | 4.9e-05 | +| loss | -0.0254 | +| n_updates | 23832 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000212 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.297 | +| time/ | | +| fps | 1407 | +| iterations | 2005 | +| time_elapsed | 2916 | +| total_timesteps | 4106240 | +| train/ | | +| approx_kl | 0.01096319 | +| clip_fraction | 0.311 | +| clip_range | 0.074 | +| entropy_loss | -7.1 | +| explained_variance | 0.179 | +| learning_rate | 4.9e-05 | +| loss | -0.0275 | +| n_updates | 23836 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000255 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 1407 | +| iterations | 2006 | +| time_elapsed | 2918 | +| total_timesteps | 4108288 | +| train/ | | +| approx_kl | 0.013319064 | +| clip_fraction | 0.347 | +| clip_range | 0.074 | +| entropy_loss | -7.24 | +| explained_variance | 0.187 | +| learning_rate | 4.9e-05 | +| loss | -0.0381 | +| n_updates | 23840 | +| policy_gradient_loss | -0.0234 | +| value_loss | 0.000213 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.302 | +| time/ | | +| fps | 1407 | +| iterations | 2007 | +| time_elapsed | 2919 | +| total_timesteps | 4110336 | +| train/ | | +| approx_kl | 0.01072081 | +| clip_fraction | 0.353 | +| clip_range | 0.074 | +| entropy_loss | -7.14 | +| explained_variance | 0.221 | +| learning_rate | 4.9e-05 | +| loss | -0.0304 | +| n_updates | 23844 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000168 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.306 | +| time/ | | +| fps | 1407 | +| iterations | 2008 | +| time_elapsed | 2921 | +| total_timesteps | 4112384 | +| train/ | | +| approx_kl | 0.011168249 | +| clip_fraction | 0.335 | +| clip_range | 0.074 | +| entropy_loss | -7.27 | +| explained_variance | -0.0999 | +| learning_rate | 4.9e-05 | +| loss | -0.0393 | +| n_updates | 23848 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000142 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1407 | +| iterations | 2009 | +| time_elapsed | 2922 | +| total_timesteps | 4114432 | +| train/ | | +| approx_kl | 0.011080155 | +| clip_fraction | 0.298 | +| clip_range | 0.074 | +| entropy_loss | -7.08 | +| explained_variance | 0.242 | +| learning_rate | 4.9e-05 | +| loss | -0.0258 | +| n_updates | 23852 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000384 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.315 | +| time/ | | +| fps | 1407 | +| iterations | 2010 | +| time_elapsed | 2924 | +| total_timesteps | 4116480 | +| train/ | | +| approx_kl | 0.011189529 | +| clip_fraction | 0.339 | +| clip_range | 0.074 | +| entropy_loss | -6.95 | +| explained_variance | -0.00743 | +| learning_rate | 4.9e-05 | +| loss | -0.0349 | +| n_updates | 23856 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000287 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1407 | +| iterations | 2011 | +| time_elapsed | 2925 | +| total_timesteps | 4118528 | +| train/ | | +| approx_kl | 0.012641942 | +| clip_fraction | 0.345 | +| clip_range | 0.074 | +| entropy_loss | -7.12 | +| explained_variance | 0.346 | +| learning_rate | 4.9e-05 | +| loss | -0.0341 | +| n_updates | 23860 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000156 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 1407 | +| iterations | 2012 | +| time_elapsed | 2927 | +| total_timesteps | 4120576 | +| train/ | | +| approx_kl | 0.0113715 | +| clip_fraction | 0.344 | +| clip_range | 0.074 | +| entropy_loss | -7.15 | +| explained_variance | 0.122 | +| learning_rate | 4.9e-05 | +| loss | -0.0415 | +| n_updates | 23864 | +| policy_gradient_loss | -0.0246 | +| value_loss | 0.000115 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.302 | +| time/ | | +| fps | 1407 | +| iterations | 2013 | +| time_elapsed | 2928 | +| total_timesteps | 4122624 | +| train/ | | +| approx_kl | 0.011188759 | +| clip_fraction | 0.346 | +| clip_range | 0.074 | +| entropy_loss | -7.21 | +| explained_variance | -0.234 | +| learning_rate | 4.9e-05 | +| loss | -0.032 | +| n_updates | 23868 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000136 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 1407 | +| iterations | 2014 | +| time_elapsed | 2929 | +| total_timesteps | 4124672 | +| train/ | | +| approx_kl | 0.012154753 | +| clip_fraction | 0.355 | +| clip_range | 0.074 | +| entropy_loss | -7.1 | +| explained_variance | 0.37 | +| learning_rate | 4.9e-05 | +| loss | -0.0376 | +| n_updates | 23872 | +| policy_gradient_loss | -0.0226 | +| value_loss | 7.39e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 1407 | +| iterations | 2015 | +| time_elapsed | 2931 | +| total_timesteps | 4126720 | +| train/ | | +| approx_kl | 0.010987159 | +| clip_fraction | 0.305 | +| clip_range | 0.074 | +| entropy_loss | -7.29 | +| explained_variance | -0.106 | +| learning_rate | 4.9e-05 | +| loss | -0.0303 | +| n_updates | 23876 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000189 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 1407 | +| iterations | 2016 | +| time_elapsed | 2932 | +| total_timesteps | 4128768 | +| train/ | | +| approx_kl | 0.01145041 | +| clip_fraction | 0.318 | +| clip_range | 0.074 | +| entropy_loss | -7.22 | +| explained_variance | 0.327 | +| learning_rate | 4.9e-05 | +| loss | -0.0298 | +| n_updates | 23880 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000139 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.3 | +| time/ | | +| fps | 1407 | +| iterations | 2017 | +| time_elapsed | 2934 | +| total_timesteps | 4130816 | +| train/ | | +| approx_kl | 0.011716139 | +| clip_fraction | 0.317 | +| clip_range | 0.074 | +| entropy_loss | -6.83 | +| explained_variance | 0.498 | +| learning_rate | 4.9e-05 | +| loss | -0.0304 | +| n_updates | 23884 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.00015 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.3 | +| time/ | | +| fps | 1407 | +| iterations | 2018 | +| time_elapsed | 2935 | +| total_timesteps | 4132864 | +| train/ | | +| approx_kl | 0.00947514 | +| clip_fraction | 0.311 | +| clip_range | 0.074 | +| entropy_loss | -7.26 | +| explained_variance | -0.119 | +| learning_rate | 4.9e-05 | +| loss | -0.0352 | +| n_updates | 23888 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000148 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.3 | +| time/ | | +| fps | 1407 | +| iterations | 2019 | +| time_elapsed | 2936 | +| total_timesteps | 4134912 | +| train/ | | +| approx_kl | 0.010706667 | +| clip_fraction | 0.325 | +| clip_range | 0.074 | +| entropy_loss | -7 | +| explained_variance | 0.436 | +| learning_rate | 4.9e-05 | +| loss | -0.0258 | +| n_updates | 23892 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.00015 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1407 | +| iterations | 2020 | +| time_elapsed | 2938 | +| total_timesteps | 4136960 | +| train/ | | +| approx_kl | 0.011928609 | +| clip_fraction | 0.333 | +| clip_range | 0.074 | +| entropy_loss | -7.39 | +| explained_variance | -0.0854 | +| learning_rate | 4.9e-05 | +| loss | -0.0411 | +| n_updates | 23896 | +| policy_gradient_loss | -0.0243 | +| value_loss | 6.48e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.304 | +| time/ | | +| fps | 1407 | +| iterations | 2021 | +| time_elapsed | 2939 | +| total_timesteps | 4139008 | +| train/ | | +| approx_kl | 0.010377001 | +| clip_fraction | 0.297 | +| clip_range | 0.074 | +| entropy_loss | -7.31 | +| explained_variance | 0.0117 | +| learning_rate | 4.9e-05 | +| loss | -0.0291 | +| n_updates | 23900 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000284 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.306 | +| time/ | | +| fps | 1407 | +| iterations | 2022 | +| time_elapsed | 2941 | +| total_timesteps | 4141056 | +| train/ | | +| approx_kl | 0.011565229 | +| clip_fraction | 0.319 | +| clip_range | 0.074 | +| entropy_loss | -7.03 | +| explained_variance | 0.567 | +| learning_rate | 4.9e-05 | +| loss | -0.0331 | +| n_updates | 23904 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1407 | +| iterations | 2023 | +| time_elapsed | 2942 | +| total_timesteps | 4143104 | +| train/ | | +| approx_kl | 0.010854024 | +| clip_fraction | 0.336 | +| clip_range | 0.074 | +| entropy_loss | -6.98 | +| explained_variance | 0.55 | +| learning_rate | 4.9e-05 | +| loss | -0.0294 | +| n_updates | 23908 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000125 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1407 | +| iterations | 2024 | +| time_elapsed | 2944 | +| total_timesteps | 4145152 | +| train/ | | +| approx_kl | 0.012947123 | +| clip_fraction | 0.335 | +| clip_range | 0.074 | +| entropy_loss | -6.97 | +| explained_variance | 0.548 | +| learning_rate | 4.9e-05 | +| loss | -0.0302 | +| n_updates | 23912 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000104 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1407 | +| iterations | 2025 | +| time_elapsed | 2945 | +| total_timesteps | 4147200 | +| train/ | | +| approx_kl | 0.010721133 | +| clip_fraction | 0.309 | +| clip_range | 0.074 | +| entropy_loss | -7.36 | +| explained_variance | -0.0914 | +| learning_rate | 4.9e-05 | +| loss | -0.0356 | +| n_updates | 23916 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000109 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1407 | +| iterations | 2026 | +| time_elapsed | 2947 | +| total_timesteps | 4149248 | +| train/ | | +| approx_kl | 0.011139061 | +| clip_fraction | 0.306 | +| clip_range | 0.074 | +| entropy_loss | -7.05 | +| explained_variance | 0.21 | +| learning_rate | 4.9e-05 | +| loss | -0.0314 | +| n_updates | 23920 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000233 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1407 | +| iterations | 2027 | +| time_elapsed | 2948 | +| total_timesteps | 4151296 | +| train/ | | +| approx_kl | 0.011847864 | +| clip_fraction | 0.35 | +| clip_range | 0.074 | +| entropy_loss | -7.18 | +| explained_variance | -0.114 | +| learning_rate | 4.9e-05 | +| loss | -0.0315 | +| n_updates | 23924 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000147 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.315 | +| time/ | | +| fps | 1407 | +| iterations | 2028 | +| time_elapsed | 2950 | +| total_timesteps | 4153344 | +| train/ | | +| approx_kl | 0.009742114 | +| clip_fraction | 0.308 | +| clip_range | 0.074 | +| entropy_loss | -7.13 | +| explained_variance | 0.184 | +| learning_rate | 4.9e-05 | +| loss | -0.0319 | +| n_updates | 23928 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000326 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1407 | +| iterations | 2029 | +| time_elapsed | 2951 | +| total_timesteps | 4155392 | +| train/ | | +| approx_kl | 0.010257678 | +| clip_fraction | 0.3 | +| clip_range | 0.074 | +| entropy_loss | -7 | +| explained_variance | 0.413 | +| learning_rate | 4.9e-05 | +| loss | -0.0301 | +| n_updates | 23932 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000197 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1407 | +| iterations | 2030 | +| time_elapsed | 2952 | +| total_timesteps | 4157440 | +| train/ | | +| approx_kl | 0.012097499 | +| clip_fraction | 0.316 | +| clip_range | 0.074 | +| entropy_loss | -6.8 | +| explained_variance | 0.512 | +| learning_rate | 4.9e-05 | +| loss | -0.0331 | +| n_updates | 23936 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000161 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1407 | +| iterations | 2031 | +| time_elapsed | 2954 | +| total_timesteps | 4159488 | +| train/ | | +| approx_kl | 0.01127566 | +| clip_fraction | 0.296 | +| clip_range | 0.074 | +| entropy_loss | -7.02 | +| explained_variance | 0.249 | +| learning_rate | 4.9e-05 | +| loss | -0.026 | +| n_updates | 23940 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000276 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1407 | +| iterations | 2032 | +| time_elapsed | 2955 | +| total_timesteps | 4161536 | +| train/ | | +| approx_kl | 0.011074305 | +| clip_fraction | 0.339 | +| clip_range | 0.074 | +| entropy_loss | -7.23 | +| explained_variance | 0.198 | +| learning_rate | 4.9e-05 | +| loss | -0.0321 | +| n_updates | 23944 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000165 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1407 | +| iterations | 2033 | +| time_elapsed | 2957 | +| total_timesteps | 4163584 | +| train/ | | +| approx_kl | 0.010575313 | +| clip_fraction | 0.344 | +| clip_range | 0.074 | +| entropy_loss | -7.38 | +| explained_variance | 0.265 | +| learning_rate | 4.9e-05 | +| loss | -0.0388 | +| n_updates | 23948 | +| policy_gradient_loss | -0.024 | +| value_loss | 7.32e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1408 | +| iterations | 2034 | +| time_elapsed | 2958 | +| total_timesteps | 4165632 | +| train/ | | +| approx_kl | 0.012262108 | +| clip_fraction | 0.346 | +| clip_range | 0.074 | +| entropy_loss | -7.26 | +| explained_variance | 0.363 | +| learning_rate | 4.9e-05 | +| loss | -0.0352 | +| n_updates | 23952 | +| policy_gradient_loss | -0.0231 | +| value_loss | 0.000121 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1407 | +| iterations | 2035 | +| time_elapsed | 2960 | +| total_timesteps | 4167680 | +| train/ | | +| approx_kl | 0.01420859 | +| clip_fraction | 0.332 | +| clip_range | 0.074 | +| entropy_loss | -7.41 | +| explained_variance | -0.164 | +| learning_rate | 4.9e-05 | +| loss | -0.0358 | +| n_updates | 23956 | +| policy_gradient_loss | -0.023 | +| value_loss | 8.24e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1407 | +| iterations | 2036 | +| time_elapsed | 2961 | +| total_timesteps | 4169728 | +| train/ | | +| approx_kl | 0.011462562 | +| clip_fraction | 0.301 | +| clip_range | 0.074 | +| entropy_loss | -7.04 | +| explained_variance | 0.366 | +| learning_rate | 4.9e-05 | +| loss | -0.0305 | +| n_updates | 23960 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000236 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1408 | +| iterations | 2037 | +| time_elapsed | 2962 | +| total_timesteps | 4171776 | +| train/ | | +| approx_kl | 0.010266891 | +| clip_fraction | 0.279 | +| clip_range | 0.074 | +| entropy_loss | -7.13 | +| explained_variance | 0.268 | +| learning_rate | 4.9e-05 | +| loss | -0.0295 | +| n_updates | 23964 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000233 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1408 | +| iterations | 2038 | +| time_elapsed | 2964 | +| total_timesteps | 4173824 | +| train/ | | +| approx_kl | 0.01347857 | +| clip_fraction | 0.328 | +| clip_range | 0.074 | +| entropy_loss | -7.09 | +| explained_variance | 0.383 | +| learning_rate | 4.9e-05 | +| loss | -0.0309 | +| n_updates | 23968 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000122 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1408 | +| iterations | 2039 | +| time_elapsed | 2965 | +| total_timesteps | 4175872 | +| train/ | | +| approx_kl | 0.012754236 | +| clip_fraction | 0.358 | +| clip_range | 0.074 | +| entropy_loss | -7.01 | +| explained_variance | 0.434 | +| learning_rate | 4.9e-05 | +| loss | -0.0356 | +| n_updates | 23972 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000153 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1407 | +| iterations | 2040 | +| time_elapsed | 2967 | +| total_timesteps | 4177920 | +| train/ | | +| approx_kl | 0.012687288 | +| clip_fraction | 0.335 | +| clip_range | 0.074 | +| entropy_loss | -6.84 | +| explained_variance | 0.729 | +| learning_rate | 4.9e-05 | +| loss | -0.0381 | +| n_updates | 23976 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000104 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1407 | +| iterations | 2041 | +| time_elapsed | 2968 | +| total_timesteps | 4179968 | +| train/ | | +| approx_kl | 0.010856284 | +| clip_fraction | 0.303 | +| clip_range | 0.074 | +| entropy_loss | -7.37 | +| explained_variance | -0.0352 | +| learning_rate | 4.9e-05 | +| loss | -0.0344 | +| n_updates | 23980 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000153 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1407 | +| iterations | 2042 | +| time_elapsed | 2970 | +| total_timesteps | 4182016 | +| train/ | | +| approx_kl | 0.011385672 | +| clip_fraction | 0.286 | +| clip_range | 0.074 | +| entropy_loss | -7.03 | +| explained_variance | -0.0393 | +| learning_rate | 4.9e-05 | +| loss | -0.0219 | +| n_updates | 23984 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000406 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1407 | +| iterations | 2043 | +| time_elapsed | 2971 | +| total_timesteps | 4184064 | +| train/ | | +| approx_kl | 0.013401554 | +| clip_fraction | 0.339 | +| clip_range | 0.074 | +| entropy_loss | -7.07 | +| explained_variance | 0.436 | +| learning_rate | 4.9e-05 | +| loss | -0.0393 | +| n_updates | 23988 | +| policy_gradient_loss | -0.0242 | +| value_loss | 0.000104 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1408 | +| iterations | 2044 | +| time_elapsed | 2973 | +| total_timesteps | 4186112 | +| train/ | | +| approx_kl | 0.012366694 | +| clip_fraction | 0.349 | +| clip_range | 0.074 | +| entropy_loss | -7.38 | +| explained_variance | -0.362 | +| learning_rate | 4.9e-05 | +| loss | -0.0393 | +| n_updates | 23992 | +| policy_gradient_loss | -0.0245 | +| value_loss | 9.33e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1408 | +| iterations | 2045 | +| time_elapsed | 2974 | +| total_timesteps | 4188160 | +| train/ | | +| approx_kl | 0.010801632 | +| clip_fraction | 0.312 | +| clip_range | 0.074 | +| entropy_loss | -7.06 | +| explained_variance | 0.342 | +| learning_rate | 4.9e-05 | +| loss | -0.0389 | +| n_updates | 23996 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000206 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1408 | +| iterations | 2046 | +| time_elapsed | 2975 | +| total_timesteps | 4190208 | +| train/ | | +| approx_kl | 0.00993642 | +| clip_fraction | 0.316 | +| clip_range | 0.074 | +| entropy_loss | -7.36 | +| explained_variance | -0.0729 | +| learning_rate | 4.9e-05 | +| loss | -0.029 | +| n_updates | 24000 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000157 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1408 | +| iterations | 2047 | +| time_elapsed | 2977 | +| total_timesteps | 4192256 | +| train/ | | +| approx_kl | 0.01243685 | +| clip_fraction | 0.344 | +| clip_range | 0.074 | +| entropy_loss | -7.24 | +| explained_variance | 0.315 | +| learning_rate | 4.9e-05 | +| loss | -0.0377 | +| n_updates | 24004 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000129 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1408 | +| iterations | 2048 | +| time_elapsed | 2978 | +| total_timesteps | 4194304 | +| train/ | | +| approx_kl | 0.01214961 | +| clip_fraction | 0.344 | +| clip_range | 0.074 | +| entropy_loss | -7.16 | +| explained_variance | 0.554 | +| learning_rate | 4.9e-05 | +| loss | -0.0417 | +| n_updates | 24008 | +| policy_gradient_loss | -0.026 | +| value_loss | 5.54e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1408 | +| iterations | 2049 | +| time_elapsed | 2980 | +| total_timesteps | 4196352 | +| train/ | | +| approx_kl | 0.010496793 | +| clip_fraction | 0.323 | +| clip_range | 0.074 | +| entropy_loss | -6.79 | +| explained_variance | 0.54 | +| learning_rate | 4.9e-05 | +| loss | -0.0277 | +| n_updates | 24012 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000174 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1408 | +| iterations | 2050 | +| time_elapsed | 2981 | +| total_timesteps | 4198400 | +| train/ | | +| approx_kl | 0.010290055 | +| clip_fraction | 0.312 | +| clip_range | 0.074 | +| entropy_loss | -7.12 | +| explained_variance | 0.378 | +| learning_rate | 4.9e-05 | +| loss | -0.0324 | +| n_updates | 24016 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000126 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1408 | +| iterations | 2051 | +| time_elapsed | 2983 | +| total_timesteps | 4200448 | +| train/ | | +| approx_kl | 0.011923641 | +| clip_fraction | 0.312 | +| clip_range | 0.074 | +| entropy_loss | -6.94 | +| explained_variance | 0.467 | +| learning_rate | 4.9e-05 | +| loss | -0.0376 | +| n_updates | 24020 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.00018 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1408 | +| iterations | 2052 | +| time_elapsed | 2984 | +| total_timesteps | 4202496 | +| train/ | | +| approx_kl | 0.010831168 | +| clip_fraction | 0.31 | +| clip_range | 0.0739 | +| entropy_loss | -7.07 | +| explained_variance | 0.493 | +| learning_rate | 4.9e-05 | +| loss | -0.0314 | +| n_updates | 24024 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000129 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1408 | +| iterations | 2053 | +| time_elapsed | 2985 | +| total_timesteps | 4204544 | +| train/ | | +| approx_kl | 0.010402346 | +| clip_fraction | 0.296 | +| clip_range | 0.0739 | +| entropy_loss | -6.73 | +| explained_variance | 0.428 | +| learning_rate | 4.9e-05 | +| loss | -0.0313 | +| n_updates | 24028 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000259 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1408 | +| iterations | 2054 | +| time_elapsed | 2987 | +| total_timesteps | 4206592 | +| train/ | | +| approx_kl | 0.011341926 | +| clip_fraction | 0.317 | +| clip_range | 0.0739 | +| entropy_loss | -7.13 | +| explained_variance | 0.0996 | +| learning_rate | 4.9e-05 | +| loss | -0.0355 | +| n_updates | 24032 | +| policy_gradient_loss | -0.0219 | +| value_loss | 0.000106 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1408 | +| iterations | 2055 | +| time_elapsed | 2988 | +| total_timesteps | 4208640 | +| train/ | | +| approx_kl | 0.010820781 | +| clip_fraction | 0.341 | +| clip_range | 0.0739 | +| entropy_loss | -7.37 | +| explained_variance | -0.0455 | +| learning_rate | 4.9e-05 | +| loss | -0.0359 | +| n_updates | 24036 | +| policy_gradient_loss | -0.0219 | +| value_loss | 0.000174 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1408 | +| iterations | 2056 | +| time_elapsed | 2990 | +| total_timesteps | 4210688 | +| train/ | | +| approx_kl | 0.009838348 | +| clip_fraction | 0.323 | +| clip_range | 0.0739 | +| entropy_loss | -6.93 | +| explained_variance | 0.27 | +| learning_rate | 4.9e-05 | +| loss | -0.026 | +| n_updates | 24040 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.00044 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1408 | +| iterations | 2057 | +| time_elapsed | 2991 | +| total_timesteps | 4212736 | +| train/ | | +| approx_kl | 0.009089401 | +| clip_fraction | 0.297 | +| clip_range | 0.0739 | +| entropy_loss | -7.24 | +| explained_variance | 0.0257 | +| learning_rate | 4.9e-05 | +| loss | -0.0374 | +| n_updates | 24044 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000274 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1408 | +| iterations | 2058 | +| time_elapsed | 2993 | +| total_timesteps | 4214784 | +| train/ | | +| approx_kl | 0.010702699 | +| clip_fraction | 0.31 | +| clip_range | 0.0739 | +| entropy_loss | -7.29 | +| explained_variance | 0.146 | +| learning_rate | 4.9e-05 | +| loss | -0.0339 | +| n_updates | 24048 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000202 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1408 | +| iterations | 2059 | +| time_elapsed | 2994 | +| total_timesteps | 4216832 | +| train/ | | +| approx_kl | 0.010785843 | +| clip_fraction | 0.342 | +| clip_range | 0.0739 | +| entropy_loss | -6.94 | +| explained_variance | 0.253 | +| learning_rate | 4.9e-05 | +| loss | -0.033 | +| n_updates | 24052 | +| policy_gradient_loss | -0.0224 | +| value_loss | 0.000165 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1408 | +| iterations | 2060 | +| time_elapsed | 2996 | +| total_timesteps | 4218880 | +| train/ | | +| approx_kl | 0.009000901 | +| clip_fraction | 0.302 | +| clip_range | 0.0739 | +| entropy_loss | -6.98 | +| explained_variance | 0.553 | +| learning_rate | 4.9e-05 | +| loss | -0.0255 | +| n_updates | 24056 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.00012 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1408 | +| iterations | 2061 | +| time_elapsed | 2997 | +| total_timesteps | 4220928 | +| train/ | | +| approx_kl | 0.011036232 | +| clip_fraction | 0.326 | +| clip_range | 0.0739 | +| entropy_loss | -7.24 | +| explained_variance | 0.0918 | +| learning_rate | 4.9e-05 | +| loss | -0.0317 | +| n_updates | 24060 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.00023 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1408 | +| iterations | 2062 | +| time_elapsed | 2999 | +| total_timesteps | 4222976 | +| train/ | | +| approx_kl | 0.013121307 | +| clip_fraction | 0.325 | +| clip_range | 0.0739 | +| entropy_loss | -7 | +| explained_variance | 0.512 | +| learning_rate | 4.9e-05 | +| loss | -0.0315 | +| n_updates | 24064 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.00013 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1408 | +| iterations | 2063 | +| time_elapsed | 3000 | +| total_timesteps | 4225024 | +| train/ | | +| approx_kl | 0.01049595 | +| clip_fraction | 0.308 | +| clip_range | 0.0739 | +| entropy_loss | -6.92 | +| explained_variance | 0.406 | +| learning_rate | 4.9e-05 | +| loss | -0.0265 | +| n_updates | 24068 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000222 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1408 | +| iterations | 2064 | +| time_elapsed | 3001 | +| total_timesteps | 4227072 | +| train/ | | +| approx_kl | 0.012594737 | +| clip_fraction | 0.339 | +| clip_range | 0.0739 | +| entropy_loss | -7.01 | +| explained_variance | 0.44 | +| learning_rate | 4.9e-05 | +| loss | -0.0361 | +| n_updates | 24072 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000163 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1408 | +| iterations | 2065 | +| time_elapsed | 3003 | +| total_timesteps | 4229120 | +| train/ | | +| approx_kl | 0.011298947 | +| clip_fraction | 0.31 | +| clip_range | 0.0739 | +| entropy_loss | -7.02 | +| explained_variance | 0.188 | +| learning_rate | 4.9e-05 | +| loss | -0.0196 | +| n_updates | 24076 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000284 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1408 | +| iterations | 2066 | +| time_elapsed | 3004 | +| total_timesteps | 4231168 | +| train/ | | +| approx_kl | 0.0101627465 | +| clip_fraction | 0.317 | +| clip_range | 0.0739 | +| entropy_loss | -7.27 | +| explained_variance | 0.186 | +| learning_rate | 4.9e-05 | +| loss | -0.0351 | +| n_updates | 24080 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000173 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1408 | +| iterations | 2067 | +| time_elapsed | 3006 | +| total_timesteps | 4233216 | +| train/ | | +| approx_kl | 0.010988608 | +| clip_fraction | 0.349 | +| clip_range | 0.0739 | +| entropy_loss | -7.36 | +| explained_variance | -0.213 | +| learning_rate | 4.9e-05 | +| loss | -0.0345 | +| n_updates | 24084 | +| policy_gradient_loss | -0.0222 | +| value_loss | 0.000127 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1408 | +| iterations | 2068 | +| time_elapsed | 3007 | +| total_timesteps | 4235264 | +| train/ | | +| approx_kl | 0.0091379145 | +| clip_fraction | 0.309 | +| clip_range | 0.0739 | +| entropy_loss | -7.19 | +| explained_variance | 0.298 | +| learning_rate | 4.9e-05 | +| loss | -0.0322 | +| n_updates | 24088 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000192 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1408 | +| iterations | 2069 | +| time_elapsed | 3009 | +| total_timesteps | 4237312 | +| train/ | | +| approx_kl | 0.011313479 | +| clip_fraction | 0.313 | +| clip_range | 0.0739 | +| entropy_loss | -6.62 | +| explained_variance | 0.634 | +| learning_rate | 4.9e-05 | +| loss | -0.0343 | +| n_updates | 24092 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000117 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1408 | +| iterations | 2070 | +| time_elapsed | 3010 | +| total_timesteps | 4239360 | +| train/ | | +| approx_kl | 0.012087949 | +| clip_fraction | 0.325 | +| clip_range | 0.0739 | +| entropy_loss | -7.1 | +| explained_variance | -0.0578 | +| learning_rate | 4.9e-05 | +| loss | -0.0227 | +| n_updates | 24096 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.00023 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1408 | +| iterations | 2071 | +| time_elapsed | 3011 | +| total_timesteps | 4241408 | +| train/ | | +| approx_kl | 0.0121213775 | +| clip_fraction | 0.309 | +| clip_range | 0.0739 | +| entropy_loss | -7.22 | +| explained_variance | 0.228 | +| learning_rate | 4.9e-05 | +| loss | -0.0351 | +| n_updates | 24100 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000182 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1408 | +| iterations | 2072 | +| time_elapsed | 3013 | +| total_timesteps | 4243456 | +| train/ | | +| approx_kl | 0.010065306 | +| clip_fraction | 0.321 | +| clip_range | 0.0739 | +| entropy_loss | -7.33 | +| explained_variance | -0.049 | +| learning_rate | 4.9e-05 | +| loss | -0.0338 | +| n_updates | 24104 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000183 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1408 | +| iterations | 2073 | +| time_elapsed | 3014 | +| total_timesteps | 4245504 | +| train/ | | +| approx_kl | 0.011602721 | +| clip_fraction | 0.347 | +| clip_range | 0.0739 | +| entropy_loss | -6.86 | +| explained_variance | 0.646 | +| learning_rate | 4.9e-05 | +| loss | -0.0325 | +| n_updates | 24108 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000106 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1408 | +| iterations | 2074 | +| time_elapsed | 3016 | +| total_timesteps | 4247552 | +| train/ | | +| approx_kl | 0.011519503 | +| clip_fraction | 0.312 | +| clip_range | 0.0739 | +| entropy_loss | -6.8 | +| explained_variance | 0.48 | +| learning_rate | 4.9e-05 | +| loss | -0.0271 | +| n_updates | 24112 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000239 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1408 | +| iterations | 2075 | +| time_elapsed | 3017 | +| total_timesteps | 4249600 | +| train/ | | +| approx_kl | 0.010278691 | +| clip_fraction | 0.322 | +| clip_range | 0.0739 | +| entropy_loss | -7.25 | +| explained_variance | 0.00849 | +| learning_rate | 4.9e-05 | +| loss | -0.0326 | +| n_updates | 24116 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.00029 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1408 | +| iterations | 2076 | +| time_elapsed | 3019 | +| total_timesteps | 4251648 | +| train/ | | +| approx_kl | 0.011614385 | +| clip_fraction | 0.318 | +| clip_range | 0.0739 | +| entropy_loss | -7.08 | +| explained_variance | 0.125 | +| learning_rate | 4.9e-05 | +| loss | -0.0362 | +| n_updates | 24120 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000233 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1408 | +| iterations | 2077 | +| time_elapsed | 3020 | +| total_timesteps | 4253696 | +| train/ | | +| approx_kl | 0.01103736 | +| clip_fraction | 0.319 | +| clip_range | 0.0739 | +| entropy_loss | -7.34 | +| explained_variance | -0.11 | +| learning_rate | 4.9e-05 | +| loss | -0.032 | +| n_updates | 24124 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000101 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1408 | +| iterations | 2078 | +| time_elapsed | 3021 | +| total_timesteps | 4255744 | +| train/ | | +| approx_kl | 0.012539348 | +| clip_fraction | 0.345 | +| clip_range | 0.0739 | +| entropy_loss | -7.4 | +| explained_variance | -0.0735 | +| learning_rate | 4.9e-05 | +| loss | -0.0343 | +| n_updates | 24128 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000124 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1408 | +| iterations | 2079 | +| time_elapsed | 3023 | +| total_timesteps | 4257792 | +| train/ | | +| approx_kl | 0.010911496 | +| clip_fraction | 0.313 | +| clip_range | 0.0739 | +| entropy_loss | -7.38 | +| explained_variance | -0.166 | +| learning_rate | 4.9e-05 | +| loss | -0.0333 | +| n_updates | 24132 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000123 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1408 | +| iterations | 2080 | +| time_elapsed | 3024 | +| total_timesteps | 4259840 | +| train/ | | +| approx_kl | 0.00974232 | +| clip_fraction | 0.294 | +| clip_range | 0.0739 | +| entropy_loss | -6.89 | +| explained_variance | 0.366 | +| learning_rate | 4.9e-05 | +| loss | -0.0249 | +| n_updates | 24136 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000155 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1408 | +| iterations | 2081 | +| time_elapsed | 3026 | +| total_timesteps | 4261888 | +| train/ | | +| approx_kl | 0.012270698 | +| clip_fraction | 0.329 | +| clip_range | 0.0739 | +| entropy_loss | -7.17 | +| explained_variance | 0.0465 | +| learning_rate | 4.9e-05 | +| loss | -0.0294 | +| n_updates | 24140 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.00013 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1408 | +| iterations | 2082 | +| time_elapsed | 3027 | +| total_timesteps | 4263936 | +| train/ | | +| approx_kl | 0.0113575775 | +| clip_fraction | 0.311 | +| clip_range | 0.0739 | +| entropy_loss | -6.89 | +| explained_variance | 0.254 | +| learning_rate | 4.9e-05 | +| loss | -0.0287 | +| n_updates | 24144 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000213 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1408 | +| iterations | 2083 | +| time_elapsed | 3029 | +| total_timesteps | 4265984 | +| train/ | | +| approx_kl | 0.013003915 | +| clip_fraction | 0.348 | +| clip_range | 0.0739 | +| entropy_loss | -6.85 | +| explained_variance | 0.243 | +| learning_rate | 4.9e-05 | +| loss | -0.0361 | +| n_updates | 24148 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000174 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1408 | +| iterations | 2084 | +| time_elapsed | 3030 | +| total_timesteps | 4268032 | +| train/ | | +| approx_kl | 0.014060006 | +| clip_fraction | 0.342 | +| clip_range | 0.0739 | +| entropy_loss | -6.99 | +| explained_variance | 0.301 | +| learning_rate | 4.9e-05 | +| loss | -0.0265 | +| n_updates | 24152 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000184 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1408 | +| iterations | 2085 | +| time_elapsed | 3032 | +| total_timesteps | 4270080 | +| train/ | | +| approx_kl | 0.011900628 | +| clip_fraction | 0.321 | +| clip_range | 0.0739 | +| entropy_loss | -7.07 | +| explained_variance | 0.329 | +| learning_rate | 4.9e-05 | +| loss | -0.0324 | +| n_updates | 24156 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000153 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1408 | +| iterations | 2086 | +| time_elapsed | 3033 | +| total_timesteps | 4272128 | +| train/ | | +| approx_kl | 0.012061118 | +| clip_fraction | 0.34 | +| clip_range | 0.0739 | +| entropy_loss | -7.34 | +| explained_variance | -0.27 | +| learning_rate | 4.9e-05 | +| loss | -0.036 | +| n_updates | 24160 | +| policy_gradient_loss | -0.0221 | +| value_loss | 9.05e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1408 | +| iterations | 2087 | +| time_elapsed | 3034 | +| total_timesteps | 4274176 | +| train/ | | +| approx_kl | 0.011422217 | +| clip_fraction | 0.294 | +| clip_range | 0.0739 | +| entropy_loss | -7.39 | +| explained_variance | -0.0576 | +| learning_rate | 4.9e-05 | +| loss | -0.0357 | +| n_updates | 24164 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000234 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1408 | +| iterations | 2088 | +| time_elapsed | 3036 | +| total_timesteps | 4276224 | +| train/ | | +| approx_kl | 0.011645836 | +| clip_fraction | 0.298 | +| clip_range | 0.0739 | +| entropy_loss | -7.05 | +| explained_variance | 0.339 | +| learning_rate | 4.9e-05 | +| loss | -0.0283 | +| n_updates | 24168 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000115 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1408 | +| iterations | 2089 | +| time_elapsed | 3037 | +| total_timesteps | 4278272 | +| train/ | | +| approx_kl | 0.01011521 | +| clip_fraction | 0.276 | +| clip_range | 0.0739 | +| entropy_loss | -6.92 | +| explained_variance | 0.225 | +| learning_rate | 4.9e-05 | +| loss | -0.0234 | +| n_updates | 24172 | +| policy_gradient_loss | -0.0144 | +| value_loss | 0.000299 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1408 | +| iterations | 2090 | +| time_elapsed | 3039 | +| total_timesteps | 4280320 | +| train/ | | +| approx_kl | 0.011938125 | +| clip_fraction | 0.336 | +| clip_range | 0.0739 | +| entropy_loss | -7 | +| explained_variance | 0.386 | +| learning_rate | 4.9e-05 | +| loss | -0.0333 | +| n_updates | 24176 | +| policy_gradient_loss | -0.0223 | +| value_loss | 0.00018 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1408 | +| iterations | 2091 | +| time_elapsed | 3040 | +| total_timesteps | 4282368 | +| train/ | | +| approx_kl | 0.011770025 | +| clip_fraction | 0.345 | +| clip_range | 0.0739 | +| entropy_loss | -7.19 | +| explained_variance | 0.312 | +| learning_rate | 4.9e-05 | +| loss | -0.0389 | +| n_updates | 24180 | +| policy_gradient_loss | -0.0233 | +| value_loss | 0.000117 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1408 | +| iterations | 2092 | +| time_elapsed | 3041 | +| total_timesteps | 4284416 | +| train/ | | +| approx_kl | 0.01176158 | +| clip_fraction | 0.333 | +| clip_range | 0.0739 | +| entropy_loss | -6.92 | +| explained_variance | 0.614 | +| learning_rate | 4.9e-05 | +| loss | -0.0363 | +| n_updates | 24184 | +| policy_gradient_loss | -0.0209 | +| value_loss | 8.96e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1408 | +| iterations | 2093 | +| time_elapsed | 3043 | +| total_timesteps | 4286464 | +| train/ | | +| approx_kl | 0.013045218 | +| clip_fraction | 0.342 | +| clip_range | 0.0739 | +| entropy_loss | -7.23 | +| explained_variance | 0.0469 | +| learning_rate | 4.9e-05 | +| loss | -0.0355 | +| n_updates | 24188 | +| policy_gradient_loss | -0.0232 | +| value_loss | 0.000101 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1408 | +| iterations | 2094 | +| time_elapsed | 3044 | +| total_timesteps | 4288512 | +| train/ | | +| approx_kl | 0.012820529 | +| clip_fraction | 0.359 | +| clip_range | 0.0739 | +| entropy_loss | -7.13 | +| explained_variance | 0.337 | +| learning_rate | 4.9e-05 | +| loss | -0.0364 | +| n_updates | 24192 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.00011 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1408 | +| iterations | 2095 | +| time_elapsed | 3046 | +| total_timesteps | 4290560 | +| train/ | | +| approx_kl | 0.011482668 | +| clip_fraction | 0.323 | +| clip_range | 0.0739 | +| entropy_loss | -7.15 | +| explained_variance | -0.00902 | +| learning_rate | 4.9e-05 | +| loss | -0.031 | +| n_updates | 24196 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000157 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1408 | +| iterations | 2096 | +| time_elapsed | 3047 | +| total_timesteps | 4292608 | +| train/ | | +| approx_kl | 0.010075916 | +| clip_fraction | 0.32 | +| clip_range | 0.0739 | +| entropy_loss | -7.26 | +| explained_variance | 0.318 | +| learning_rate | 4.9e-05 | +| loss | -0.0379 | +| n_updates | 24200 | +| policy_gradient_loss | -0.0188 | +| value_loss | 8.77e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1408 | +| iterations | 2097 | +| time_elapsed | 3049 | +| total_timesteps | 4294656 | +| train/ | | +| approx_kl | 0.011548033 | +| clip_fraction | 0.314 | +| clip_range | 0.0739 | +| entropy_loss | -6.98 | +| explained_variance | -0.0709 | +| learning_rate | 4.9e-05 | +| loss | -0.0332 | +| n_updates | 24204 | +| policy_gradient_loss | -0.0202 | +| value_loss | 8.99e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1408 | +| iterations | 2098 | +| time_elapsed | 3050 | +| total_timesteps | 4296704 | +| train/ | | +| approx_kl | 0.01108915 | +| clip_fraction | 0.302 | +| clip_range | 0.0739 | +| entropy_loss | -7.11 | +| explained_variance | 0.153 | +| learning_rate | 4.9e-05 | +| loss | -0.0272 | +| n_updates | 24208 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000193 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1408 | +| iterations | 2099 | +| time_elapsed | 3051 | +| total_timesteps | 4298752 | +| train/ | | +| approx_kl | 0.0095847305 | +| clip_fraction | 0.282 | +| clip_range | 0.0739 | +| entropy_loss | -6.97 | +| explained_variance | 0.264 | +| learning_rate | 4.9e-05 | +| loss | -0.0311 | +| n_updates | 24212 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000246 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1408 | +| iterations | 2100 | +| time_elapsed | 3053 | +| total_timesteps | 4300800 | +| train/ | | +| approx_kl | 0.0104285665 | +| clip_fraction | 0.302 | +| clip_range | 0.0739 | +| entropy_loss | -7.14 | +| explained_variance | 0.211 | +| learning_rate | 4.9e-05 | +| loss | -0.0322 | +| n_updates | 24216 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000238 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1408 | +| iterations | 2101 | +| time_elapsed | 3054 | +| total_timesteps | 4302848 | +| train/ | | +| approx_kl | 0.011580004 | +| clip_fraction | 0.334 | +| clip_range | 0.0739 | +| entropy_loss | -7.05 | +| explained_variance | 0.524 | +| learning_rate | 4.9e-05 | +| loss | -0.0404 | +| n_updates | 24220 | +| policy_gradient_loss | -0.0224 | +| value_loss | 0.000122 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1408 | +| iterations | 2102 | +| time_elapsed | 3056 | +| total_timesteps | 4304896 | +| train/ | | +| approx_kl | 0.009908207 | +| clip_fraction | 0.298 | +| clip_range | 0.0739 | +| entropy_loss | -7.27 | +| explained_variance | -0.169 | +| learning_rate | 4.9e-05 | +| loss | -0.0265 | +| n_updates | 24224 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000285 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1408 | +| iterations | 2103 | +| time_elapsed | 3057 | +| total_timesteps | 4306944 | +| train/ | | +| approx_kl | 0.010964649 | +| clip_fraction | 0.307 | +| clip_range | 0.0739 | +| entropy_loss | -7.25 | +| explained_variance | 0.276 | +| learning_rate | 4.9e-05 | +| loss | -0.0388 | +| n_updates | 24228 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000154 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1408 | +| iterations | 2104 | +| time_elapsed | 3058 | +| total_timesteps | 4308992 | +| train/ | | +| approx_kl | 0.010672733 | +| clip_fraction | 0.327 | +| clip_range | 0.0739 | +| entropy_loss | -7.38 | +| explained_variance | -0.145 | +| learning_rate | 4.9e-05 | +| loss | -0.0401 | +| n_updates | 24232 | +| policy_gradient_loss | -0.022 | +| value_loss | 0.000177 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1408 | +| iterations | 2105 | +| time_elapsed | 3060 | +| total_timesteps | 4311040 | +| train/ | | +| approx_kl | 0.010294003 | +| clip_fraction | 0.323 | +| clip_range | 0.0739 | +| entropy_loss | -7.13 | +| explained_variance | 0.284 | +| learning_rate | 4.9e-05 | +| loss | -0.0321 | +| n_updates | 24236 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.00018 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1408 | +| iterations | 2106 | +| time_elapsed | 3061 | +| total_timesteps | 4313088 | +| train/ | | +| approx_kl | 0.010928536 | +| clip_fraction | 0.319 | +| clip_range | 0.0739 | +| entropy_loss | -7.3 | +| explained_variance | -0.114 | +| learning_rate | 4.9e-05 | +| loss | -0.0338 | +| n_updates | 24240 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000115 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1408 | +| iterations | 2107 | +| time_elapsed | 3063 | +| total_timesteps | 4315136 | +| train/ | | +| approx_kl | 0.008524554 | +| clip_fraction | 0.306 | +| clip_range | 0.0739 | +| entropy_loss | -6.81 | +| explained_variance | 0.33 | +| learning_rate | 4.9e-05 | +| loss | -0.0279 | +| n_updates | 24244 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000329 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1408 | +| iterations | 2108 | +| time_elapsed | 3064 | +| total_timesteps | 4317184 | +| train/ | | +| approx_kl | 0.010983754 | +| clip_fraction | 0.299 | +| clip_range | 0.0739 | +| entropy_loss | -6.68 | +| explained_variance | 0.462 | +| learning_rate | 4.9e-05 | +| loss | -0.0291 | +| n_updates | 24248 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000182 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1408 | +| iterations | 2109 | +| time_elapsed | 3066 | +| total_timesteps | 4319232 | +| train/ | | +| approx_kl | 0.010747625 | +| clip_fraction | 0.307 | +| clip_range | 0.0739 | +| entropy_loss | -7.22 | +| explained_variance | -0.0468 | +| learning_rate | 4.9e-05 | +| loss | -0.0373 | +| n_updates | 24252 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000277 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1408 | +| iterations | 2110 | +| time_elapsed | 3067 | +| total_timesteps | 4321280 | +| train/ | | +| approx_kl | 0.011786305 | +| clip_fraction | 0.337 | +| clip_range | 0.0739 | +| entropy_loss | -6.93 | +| explained_variance | 0.316 | +| learning_rate | 4.9e-05 | +| loss | -0.0377 | +| n_updates | 24256 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000224 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1408 | +| iterations | 2111 | +| time_elapsed | 3069 | +| total_timesteps | 4323328 | +| train/ | | +| approx_kl | 0.01294528 | +| clip_fraction | 0.329 | +| clip_range | 0.0739 | +| entropy_loss | -7.07 | +| explained_variance | 0.232 | +| learning_rate | 4.9e-05 | +| loss | -0.0333 | +| n_updates | 24260 | +| policy_gradient_loss | -0.0222 | +| value_loss | 0.000157 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1408 | +| iterations | 2112 | +| time_elapsed | 3070 | +| total_timesteps | 4325376 | +| train/ | | +| approx_kl | 0.011334967 | +| clip_fraction | 0.346 | +| clip_range | 0.0739 | +| entropy_loss | -7.29 | +| explained_variance | -0.153 | +| learning_rate | 4.9e-05 | +| loss | -0.0318 | +| n_updates | 24264 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000151 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1408 | +| iterations | 2113 | +| time_elapsed | 3071 | +| total_timesteps | 4327424 | +| train/ | | +| approx_kl | 0.012956183 | +| clip_fraction | 0.31 | +| clip_range | 0.0739 | +| entropy_loss | -7.24 | +| explained_variance | -0.134 | +| learning_rate | 4.9e-05 | +| loss | -0.0289 | +| n_updates | 24268 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000123 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1408 | +| iterations | 2114 | +| time_elapsed | 3073 | +| total_timesteps | 4329472 | +| train/ | | +| approx_kl | 0.009867329 | +| clip_fraction | 0.297 | +| clip_range | 0.0739 | +| entropy_loss | -7.14 | +| explained_variance | 0.372 | +| learning_rate | 4.9e-05 | +| loss | -0.0251 | +| n_updates | 24272 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000206 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1408 | +| iterations | 2115 | +| time_elapsed | 3074 | +| total_timesteps | 4331520 | +| train/ | | +| approx_kl | 0.012266224 | +| clip_fraction | 0.334 | +| clip_range | 0.0739 | +| entropy_loss | -7.34 | +| explained_variance | -0.186 | +| learning_rate | 4.9e-05 | +| loss | -0.0291 | +| n_updates | 24276 | +| policy_gradient_loss | -0.0221 | +| value_loss | 0.000112 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1408 | +| iterations | 2116 | +| time_elapsed | 3076 | +| total_timesteps | 4333568 | +| train/ | | +| approx_kl | 0.010734924 | +| clip_fraction | 0.281 | +| clip_range | 0.0739 | +| entropy_loss | -7.01 | +| explained_variance | 0.327 | +| learning_rate | 4.9e-05 | +| loss | -0.0298 | +| n_updates | 24280 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000241 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1408 | +| iterations | 2117 | +| time_elapsed | 3077 | +| total_timesteps | 4335616 | +| train/ | | +| approx_kl | 0.011025084 | +| clip_fraction | 0.32 | +| clip_range | 0.0739 | +| entropy_loss | -6.72 | +| explained_variance | 0.537 | +| learning_rate | 4.9e-05 | +| loss | -0.0285 | +| n_updates | 24284 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000168 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1408 | +| iterations | 2118 | +| time_elapsed | 3079 | +| total_timesteps | 4337664 | +| train/ | | +| approx_kl | 0.012771338 | +| clip_fraction | 0.307 | +| clip_range | 0.0739 | +| entropy_loss | -7.38 | +| explained_variance | 0.00219 | +| learning_rate | 4.9e-05 | +| loss | -0.0335 | +| n_updates | 24288 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.00016 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1408 | +| iterations | 2119 | +| time_elapsed | 3080 | +| total_timesteps | 4339712 | +| train/ | | +| approx_kl | 0.01116515 | +| clip_fraction | 0.331 | +| clip_range | 0.0739 | +| entropy_loss | -7.4 | +| explained_variance | -0.162 | +| learning_rate | 4.9e-05 | +| loss | -0.0334 | +| n_updates | 24292 | +| policy_gradient_loss | -0.0213 | +| value_loss | 9.04e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1408 | +| iterations | 2120 | +| time_elapsed | 3081 | +| total_timesteps | 4341760 | +| train/ | | +| approx_kl | 0.009973252 | +| clip_fraction | 0.288 | +| clip_range | 0.0739 | +| entropy_loss | -7.28 | +| explained_variance | 0.196 | +| learning_rate | 4.9e-05 | +| loss | -0.0369 | +| n_updates | 24296 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.00014 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1408 | +| iterations | 2121 | +| time_elapsed | 3083 | +| total_timesteps | 4343808 | +| train/ | | +| approx_kl | 0.009673089 | +| clip_fraction | 0.32 | +| clip_range | 0.0739 | +| entropy_loss | -6.55 | +| explained_variance | 0.764 | +| learning_rate | 4.9e-05 | +| loss | -0.0327 | +| n_updates | 24300 | +| policy_gradient_loss | -0.0188 | +| value_loss | 9.54e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1408 | +| iterations | 2122 | +| time_elapsed | 3084 | +| total_timesteps | 4345856 | +| train/ | | +| approx_kl | 0.012791162 | +| clip_fraction | 0.321 | +| clip_range | 0.0739 | +| entropy_loss | -6.9 | +| explained_variance | 0.391 | +| learning_rate | 4.9e-05 | +| loss | -0.0299 | +| n_updates | 24304 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000206 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1408 | +| iterations | 2123 | +| time_elapsed | 3086 | +| total_timesteps | 4347904 | +| train/ | | +| approx_kl | 0.011195652 | +| clip_fraction | 0.326 | +| clip_range | 0.0739 | +| entropy_loss | -7.32 | +| explained_variance | -0.0773 | +| learning_rate | 4.9e-05 | +| loss | -0.0336 | +| n_updates | 24308 | +| policy_gradient_loss | -0.0214 | +| value_loss | 8.62e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1408 | +| iterations | 2124 | +| time_elapsed | 3087 | +| total_timesteps | 4349952 | +| train/ | | +| approx_kl | 0.01096362 | +| clip_fraction | 0.332 | +| clip_range | 0.0739 | +| entropy_loss | -6.65 | +| explained_variance | 0.564 | +| learning_rate | 4.9e-05 | +| loss | -0.0323 | +| n_updates | 24312 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000161 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1408 | +| iterations | 2125 | +| time_elapsed | 3089 | +| total_timesteps | 4352000 | +| train/ | | +| approx_kl | 0.008252606 | +| clip_fraction | 0.318 | +| clip_range | 0.0739 | +| entropy_loss | -6.97 | +| explained_variance | 0.439 | +| learning_rate | 4.9e-05 | +| loss | -0.034 | +| n_updates | 24316 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000106 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1408 | +| iterations | 2126 | +| time_elapsed | 3090 | +| total_timesteps | 4354048 | +| train/ | | +| approx_kl | 0.010324956 | +| clip_fraction | 0.313 | +| clip_range | 0.0739 | +| entropy_loss | -7.19 | +| explained_variance | 0.32 | +| learning_rate | 4.9e-05 | +| loss | -0.0387 | +| n_updates | 24320 | +| policy_gradient_loss | -0.0198 | +| value_loss | 7.38e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1408 | +| iterations | 2127 | +| time_elapsed | 3091 | +| total_timesteps | 4356096 | +| train/ | | +| approx_kl | 0.010902347 | +| clip_fraction | 0.317 | +| clip_range | 0.0739 | +| entropy_loss | -7.1 | +| explained_variance | 0.193 | +| learning_rate | 4.9e-05 | +| loss | -0.0326 | +| n_updates | 24324 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000232 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1408 | +| iterations | 2128 | +| time_elapsed | 3093 | +| total_timesteps | 4358144 | +| train/ | | +| approx_kl | 0.011405245 | +| clip_fraction | 0.289 | +| clip_range | 0.0739 | +| entropy_loss | -7.43 | +| explained_variance | -0.0779 | +| learning_rate | 4.9e-05 | +| loss | -0.0362 | +| n_updates | 24328 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000169 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1408 | +| iterations | 2129 | +| time_elapsed | 3094 | +| total_timesteps | 4360192 | +| train/ | | +| approx_kl | 0.007956393 | +| clip_fraction | 0.287 | +| clip_range | 0.0739 | +| entropy_loss | -7.35 | +| explained_variance | -0.069 | +| learning_rate | 4.9e-05 | +| loss | -0.0302 | +| n_updates | 24332 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000394 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1408 | +| iterations | 2130 | +| time_elapsed | 3096 | +| total_timesteps | 4362240 | +| train/ | | +| approx_kl | 0.008949636 | +| clip_fraction | 0.286 | +| clip_range | 0.0739 | +| entropy_loss | -7.23 | +| explained_variance | 0.144 | +| learning_rate | 4.9e-05 | +| loss | -0.0262 | +| n_updates | 24336 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000274 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1408 | +| iterations | 2131 | +| time_elapsed | 3097 | +| total_timesteps | 4364288 | +| train/ | | +| approx_kl | 0.013651187 | +| clip_fraction | 0.343 | +| clip_range | 0.0739 | +| entropy_loss | -7.38 | +| explained_variance | -0.184 | +| learning_rate | 4.9e-05 | +| loss | -0.0376 | +| n_updates | 24340 | +| policy_gradient_loss | -0.0238 | +| value_loss | 0.000122 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1408 | +| iterations | 2132 | +| time_elapsed | 3099 | +| total_timesteps | 4366336 | +| train/ | | +| approx_kl | 0.010613036 | +| clip_fraction | 0.321 | +| clip_range | 0.0739 | +| entropy_loss | -7.22 | +| explained_variance | -0.0121 | +| learning_rate | 4.9e-05 | +| loss | -0.0367 | +| n_updates | 24344 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.00016 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1408 | +| iterations | 2133 | +| time_elapsed | 3100 | +| total_timesteps | 4368384 | +| train/ | | +| approx_kl | 0.011468161 | +| clip_fraction | 0.3 | +| clip_range | 0.0739 | +| entropy_loss | -6.93 | +| explained_variance | 0.236 | +| learning_rate | 4.9e-05 | +| loss | -0.0324 | +| n_updates | 24348 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000245 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1408 | +| iterations | 2134 | +| time_elapsed | 3101 | +| total_timesteps | 4370432 | +| train/ | | +| approx_kl | 0.012797561 | +| clip_fraction | 0.325 | +| clip_range | 0.0739 | +| entropy_loss | -6.8 | +| explained_variance | 0.423 | +| learning_rate | 4.9e-05 | +| loss | -0.037 | +| n_updates | 24352 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1408 | +| iterations | 2135 | +| time_elapsed | 3103 | +| total_timesteps | 4372480 | +| train/ | | +| approx_kl | 0.012102162 | +| clip_fraction | 0.32 | +| clip_range | 0.0739 | +| entropy_loss | -6.93 | +| explained_variance | 0.308 | +| learning_rate | 4.9e-05 | +| loss | -0.0251 | +| n_updates | 24356 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000152 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1408 | +| iterations | 2136 | +| time_elapsed | 3104 | +| total_timesteps | 4374528 | +| train/ | | +| approx_kl | 0.013539381 | +| clip_fraction | 0.343 | +| clip_range | 0.0739 | +| entropy_loss | -7.12 | +| explained_variance | 0.498 | +| learning_rate | 4.9e-05 | +| loss | -0.0345 | +| n_updates | 24360 | +| policy_gradient_loss | -0.0223 | +| value_loss | 0.000101 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1408 | +| iterations | 2137 | +| time_elapsed | 3106 | +| total_timesteps | 4376576 | +| train/ | | +| approx_kl | 0.010368623 | +| clip_fraction | 0.293 | +| clip_range | 0.0739 | +| entropy_loss | -6.83 | +| explained_variance | 0.531 | +| learning_rate | 4.9e-05 | +| loss | -0.0317 | +| n_updates | 24364 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000194 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1408 | +| iterations | 2138 | +| time_elapsed | 3107 | +| total_timesteps | 4378624 | +| train/ | | +| approx_kl | 0.012089616 | +| clip_fraction | 0.283 | +| clip_range | 0.0739 | +| entropy_loss | -7.19 | +| explained_variance | -0.117 | +| learning_rate | 4.9e-05 | +| loss | -0.0238 | +| n_updates | 24368 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000226 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1408 | +| iterations | 2139 | +| time_elapsed | 3109 | +| total_timesteps | 4380672 | +| train/ | | +| approx_kl | 0.011151483 | +| clip_fraction | 0.325 | +| clip_range | 0.0739 | +| entropy_loss | -7.31 | +| explained_variance | -0.21 | +| learning_rate | 4.9e-05 | +| loss | -0.0319 | +| n_updates | 24372 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000107 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1408 | +| iterations | 2140 | +| time_elapsed | 3110 | +| total_timesteps | 4382720 | +| train/ | | +| approx_kl | 0.011081226 | +| clip_fraction | 0.316 | +| clip_range | 0.0739 | +| entropy_loss | -7.34 | +| explained_variance | 0.234 | +| learning_rate | 4.9e-05 | +| loss | -0.0322 | +| n_updates | 24376 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000168 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1408 | +| iterations | 2141 | +| time_elapsed | 3112 | +| total_timesteps | 4384768 | +| train/ | | +| approx_kl | 0.011100868 | +| clip_fraction | 0.3 | +| clip_range | 0.0739 | +| entropy_loss | -7.2 | +| explained_variance | 0.277 | +| learning_rate | 4.9e-05 | +| loss | -0.028 | +| n_updates | 24380 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000159 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1408 | +| iterations | 2142 | +| time_elapsed | 3113 | +| total_timesteps | 4386816 | +| train/ | | +| approx_kl | 0.011287348 | +| clip_fraction | 0.314 | +| clip_range | 0.0739 | +| entropy_loss | -7.24 | +| explained_variance | 0.318 | +| learning_rate | 4.9e-05 | +| loss | -0.031 | +| n_updates | 24384 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000163 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1408 | +| iterations | 2143 | +| time_elapsed | 3114 | +| total_timesteps | 4388864 | +| train/ | | +| approx_kl | 0.01034218 | +| clip_fraction | 0.288 | +| clip_range | 0.0739 | +| entropy_loss | -7.16 | +| explained_variance | -0.00901 | +| learning_rate | 4.9e-05 | +| loss | -0.0279 | +| n_updates | 24388 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000406 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1409 | +| iterations | 2144 | +| time_elapsed | 3116 | +| total_timesteps | 4390912 | +| train/ | | +| approx_kl | 0.00927371 | +| clip_fraction | 0.315 | +| clip_range | 0.0739 | +| entropy_loss | -6.77 | +| explained_variance | 0.526 | +| learning_rate | 4.9e-05 | +| loss | -0.0244 | +| n_updates | 24392 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000169 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1409 | +| iterations | 2145 | +| time_elapsed | 3117 | +| total_timesteps | 4392960 | +| train/ | | +| approx_kl | 0.010951265 | +| clip_fraction | 0.32 | +| clip_range | 0.0739 | +| entropy_loss | -6.71 | +| explained_variance | 0.536 | +| learning_rate | 4.9e-05 | +| loss | -0.0274 | +| n_updates | 24396 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000135 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1408 | +| iterations | 2146 | +| time_elapsed | 3119 | +| total_timesteps | 4395008 | +| train/ | | +| approx_kl | 0.0105378395 | +| clip_fraction | 0.337 | +| clip_range | 0.0739 | +| entropy_loss | -7.28 | +| explained_variance | -0.226 | +| learning_rate | 4.9e-05 | +| loss | -0.0354 | +| n_updates | 24400 | +| policy_gradient_loss | -0.0215 | +| value_loss | 8.85e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1409 | +| iterations | 2147 | +| time_elapsed | 3120 | +| total_timesteps | 4397056 | +| train/ | | +| approx_kl | 0.011584031 | +| clip_fraction | 0.312 | +| clip_range | 0.0739 | +| entropy_loss | -7.14 | +| explained_variance | 0.149 | +| learning_rate | 4.9e-05 | +| loss | -0.0312 | +| n_updates | 24404 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000219 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1409 | +| iterations | 2148 | +| time_elapsed | 3122 | +| total_timesteps | 4399104 | +| train/ | | +| approx_kl | 0.01170625 | +| clip_fraction | 0.31 | +| clip_range | 0.0739 | +| entropy_loss | -7.16 | +| explained_variance | 0.28 | +| learning_rate | 4.9e-05 | +| loss | -0.0356 | +| n_updates | 24408 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000146 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1409 | +| iterations | 2149 | +| time_elapsed | 3123 | +| total_timesteps | 4401152 | +| train/ | | +| approx_kl | 0.009864305 | +| clip_fraction | 0.291 | +| clip_range | 0.0739 | +| entropy_loss | -7.1 | +| explained_variance | 0.312 | +| learning_rate | 4.9e-05 | +| loss | -0.0289 | +| n_updates | 24412 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000294 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1409 | +| iterations | 2150 | +| time_elapsed | 3124 | +| total_timesteps | 4403200 | +| train/ | | +| approx_kl | 0.011839544 | +| clip_fraction | 0.33 | +| clip_range | 0.0739 | +| entropy_loss | -7.31 | +| explained_variance | -0.176 | +| learning_rate | 4.9e-05 | +| loss | -0.0314 | +| n_updates | 24416 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000162 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1409 | +| iterations | 2151 | +| time_elapsed | 3126 | +| total_timesteps | 4405248 | +| train/ | | +| approx_kl | 0.012011144 | +| clip_fraction | 0.329 | +| clip_range | 0.0739 | +| entropy_loss | -7.39 | +| explained_variance | -0.0817 | +| learning_rate | 4.9e-05 | +| loss | -0.0313 | +| n_updates | 24420 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000166 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1409 | +| iterations | 2152 | +| time_elapsed | 3127 | +| total_timesteps | 4407296 | +| train/ | | +| approx_kl | 0.009705125 | +| clip_fraction | 0.287 | +| clip_range | 0.0739 | +| entropy_loss | -7.46 | +| explained_variance | -0.0638 | +| learning_rate | 4.9e-05 | +| loss | -0.0306 | +| n_updates | 24424 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000149 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1409 | +| iterations | 2153 | +| time_elapsed | 3129 | +| total_timesteps | 4409344 | +| train/ | | +| approx_kl | 0.0095808115 | +| clip_fraction | 0.278 | +| clip_range | 0.0739 | +| entropy_loss | -6.67 | +| explained_variance | 0.48 | +| learning_rate | 4.9e-05 | +| loss | -0.0261 | +| n_updates | 24428 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000214 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1409 | +| iterations | 2154 | +| time_elapsed | 3130 | +| total_timesteps | 4411392 | +| train/ | | +| approx_kl | 0.010856715 | +| clip_fraction | 0.31 | +| clip_range | 0.0739 | +| entropy_loss | -6.86 | +| explained_variance | 0.307 | +| learning_rate | 4.9e-05 | +| loss | -0.0299 | +| n_updates | 24432 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000272 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1409 | +| iterations | 2155 | +| time_elapsed | 3132 | +| total_timesteps | 4413440 | +| train/ | | +| approx_kl | 0.01044028 | +| clip_fraction | 0.305 | +| clip_range | 0.0739 | +| entropy_loss | -7.31 | +| explained_variance | -0.0717 | +| learning_rate | 4.9e-05 | +| loss | -0.0323 | +| n_updates | 24436 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000168 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1409 | +| iterations | 2156 | +| time_elapsed | 3133 | +| total_timesteps | 4415488 | +| train/ | | +| approx_kl | 0.0117283985 | +| clip_fraction | 0.309 | +| clip_range | 0.0739 | +| entropy_loss | -6.93 | +| explained_variance | 0.0692 | +| learning_rate | 4.9e-05 | +| loss | -0.0369 | +| n_updates | 24440 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000304 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1409 | +| iterations | 2157 | +| time_elapsed | 3135 | +| total_timesteps | 4417536 | +| train/ | | +| approx_kl | 0.009649579 | +| clip_fraction | 0.309 | +| clip_range | 0.0739 | +| entropy_loss | -7.15 | +| explained_variance | 0.0576 | +| learning_rate | 4.9e-05 | +| loss | -0.0338 | +| n_updates | 24444 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.00024 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1409 | +| iterations | 2158 | +| time_elapsed | 3136 | +| total_timesteps | 4419584 | +| train/ | | +| approx_kl | 0.010783385 | +| clip_fraction | 0.326 | +| clip_range | 0.0739 | +| entropy_loss | -7.1 | +| explained_variance | 0.419 | +| learning_rate | 4.9e-05 | +| loss | -0.0325 | +| n_updates | 24448 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.00018 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1409 | +| iterations | 2159 | +| time_elapsed | 3137 | +| total_timesteps | 4421632 | +| train/ | | +| approx_kl | 0.010799176 | +| clip_fraction | 0.328 | +| clip_range | 0.0739 | +| entropy_loss | -7.4 | +| explained_variance | -0.132 | +| learning_rate | 4.9e-05 | +| loss | -0.035 | +| n_updates | 24452 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000124 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1409 | +| iterations | 2160 | +| time_elapsed | 3139 | +| total_timesteps | 4423680 | +| train/ | | +| approx_kl | 0.011041002 | +| clip_fraction | 0.325 | +| clip_range | 0.0739 | +| entropy_loss | -7.09 | +| explained_variance | 0.466 | +| learning_rate | 4.89e-05 | +| loss | -0.0349 | +| n_updates | 24456 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1409 | +| iterations | 2161 | +| time_elapsed | 3140 | +| total_timesteps | 4425728 | +| train/ | | +| approx_kl | 0.012335768 | +| clip_fraction | 0.281 | +| clip_range | 0.0739 | +| entropy_loss | -7.08 | +| explained_variance | 0.305 | +| learning_rate | 4.89e-05 | +| loss | -0.026 | +| n_updates | 24460 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000296 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1409 | +| iterations | 2162 | +| time_elapsed | 3142 | +| total_timesteps | 4427776 | +| train/ | | +| approx_kl | 0.0108592305 | +| clip_fraction | 0.313 | +| clip_range | 0.0739 | +| entropy_loss | -7.09 | +| explained_variance | 0.273 | +| learning_rate | 4.89e-05 | +| loss | -0.0319 | +| n_updates | 24464 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000152 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1409 | +| iterations | 2163 | +| time_elapsed | 3143 | +| total_timesteps | 4429824 | +| train/ | | +| approx_kl | 0.009527586 | +| clip_fraction | 0.311 | +| clip_range | 0.0739 | +| entropy_loss | -7.19 | +| explained_variance | 0.437 | +| learning_rate | 4.89e-05 | +| loss | -0.0332 | +| n_updates | 24468 | +| policy_gradient_loss | -0.0214 | +| value_loss | 9.22e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1409 | +| iterations | 2164 | +| time_elapsed | 3145 | +| total_timesteps | 4431872 | +| train/ | | +| approx_kl | 0.009619087 | +| clip_fraction | 0.307 | +| clip_range | 0.0739 | +| entropy_loss | -7.24 | +| explained_variance | 0.284 | +| learning_rate | 4.89e-05 | +| loss | -0.0307 | +| n_updates | 24472 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000143 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1409 | +| iterations | 2165 | +| time_elapsed | 3146 | +| total_timesteps | 4433920 | +| train/ | | +| approx_kl | 0.011587208 | +| clip_fraction | 0.292 | +| clip_range | 0.0739 | +| entropy_loss | -7.38 | +| explained_variance | -0.103 | +| learning_rate | 4.89e-05 | +| loss | -0.0295 | +| n_updates | 24476 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.00013 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1409 | +| iterations | 2166 | +| time_elapsed | 3148 | +| total_timesteps | 4435968 | +| train/ | | +| approx_kl | 0.011453401 | +| clip_fraction | 0.318 | +| clip_range | 0.0739 | +| entropy_loss | -7.04 | +| explained_variance | 0.353 | +| learning_rate | 4.89e-05 | +| loss | -0.0318 | +| n_updates | 24480 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000204 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1409 | +| iterations | 2167 | +| time_elapsed | 3149 | +| total_timesteps | 4438016 | +| train/ | | +| approx_kl | 0.012147032 | +| clip_fraction | 0.293 | +| clip_range | 0.0739 | +| entropy_loss | -7.3 | +| explained_variance | 0.333 | +| learning_rate | 4.89e-05 | +| loss | -0.027 | +| n_updates | 24484 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000158 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1409 | +| iterations | 2168 | +| time_elapsed | 3150 | +| total_timesteps | 4440064 | +| train/ | | +| approx_kl | 0.012411825 | +| clip_fraction | 0.313 | +| clip_range | 0.0739 | +| entropy_loss | -7.32 | +| explained_variance | -0.182 | +| learning_rate | 4.89e-05 | +| loss | -0.032 | +| n_updates | 24488 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000145 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1409 | +| iterations | 2169 | +| time_elapsed | 3152 | +| total_timesteps | 4442112 | +| train/ | | +| approx_kl | 0.010151746 | +| clip_fraction | 0.297 | +| clip_range | 0.0739 | +| entropy_loss | -6.87 | +| explained_variance | 0.386 | +| learning_rate | 4.89e-05 | +| loss | -0.0251 | +| n_updates | 24492 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000212 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1409 | +| iterations | 2170 | +| time_elapsed | 3153 | +| total_timesteps | 4444160 | +| train/ | | +| approx_kl | 0.012281081 | +| clip_fraction | 0.307 | +| clip_range | 0.0739 | +| entropy_loss | -7.04 | +| explained_variance | 0.398 | +| learning_rate | 4.89e-05 | +| loss | -0.03 | +| n_updates | 24496 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000125 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1409 | +| iterations | 2171 | +| time_elapsed | 3155 | +| total_timesteps | 4446208 | +| train/ | | +| approx_kl | 0.0114259925 | +| clip_fraction | 0.29 | +| clip_range | 0.0739 | +| entropy_loss | -6.76 | +| explained_variance | 0.515 | +| learning_rate | 4.89e-05 | +| loss | -0.0281 | +| n_updates | 24500 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000147 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1409 | +| iterations | 2172 | +| time_elapsed | 3156 | +| total_timesteps | 4448256 | +| train/ | | +| approx_kl | 0.010521747 | +| clip_fraction | 0.296 | +| clip_range | 0.0739 | +| entropy_loss | -7.24 | +| explained_variance | 0.213 | +| learning_rate | 4.89e-05 | +| loss | -0.0343 | +| n_updates | 24504 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1409 | +| iterations | 2173 | +| time_elapsed | 3158 | +| total_timesteps | 4450304 | +| train/ | | +| approx_kl | 0.010963937 | +| clip_fraction | 0.314 | +| clip_range | 0.0739 | +| entropy_loss | -7.23 | +| explained_variance | 0.192 | +| learning_rate | 4.89e-05 | +| loss | -0.0275 | +| n_updates | 24508 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000269 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1409 | +| iterations | 2174 | +| time_elapsed | 3159 | +| total_timesteps | 4452352 | +| train/ | | +| approx_kl | 0.009967411 | +| clip_fraction | 0.307 | +| clip_range | 0.0739 | +| entropy_loss | -7.45 | +| explained_variance | -0.0923 | +| learning_rate | 4.89e-05 | +| loss | -0.0309 | +| n_updates | 24512 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000131 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1409 | +| iterations | 2175 | +| time_elapsed | 3160 | +| total_timesteps | 4454400 | +| train/ | | +| approx_kl | 0.010601295 | +| clip_fraction | 0.302 | +| clip_range | 0.0739 | +| entropy_loss | -7.35 | +| explained_variance | 0.324 | +| learning_rate | 4.89e-05 | +| loss | -0.0349 | +| n_updates | 24516 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000179 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1409 | +| iterations | 2176 | +| time_elapsed | 3162 | +| total_timesteps | 4456448 | +| train/ | | +| approx_kl | 0.011575991 | +| clip_fraction | 0.335 | +| clip_range | 0.0739 | +| entropy_loss | -6.81 | +| explained_variance | 0.558 | +| learning_rate | 4.89e-05 | +| loss | -0.0311 | +| n_updates | 24520 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.00017 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1409 | +| iterations | 2177 | +| time_elapsed | 3163 | +| total_timesteps | 4458496 | +| train/ | | +| approx_kl | 0.011607404 | +| clip_fraction | 0.32 | +| clip_range | 0.0739 | +| entropy_loss | -7.41 | +| explained_variance | -0.0277 | +| learning_rate | 4.89e-05 | +| loss | -0.0337 | +| n_updates | 24524 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000145 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1409 | +| iterations | 2178 | +| time_elapsed | 3165 | +| total_timesteps | 4460544 | +| train/ | | +| approx_kl | 0.00948393 | +| clip_fraction | 0.317 | +| clip_range | 0.0739 | +| entropy_loss | -7.44 | +| explained_variance | -0.000474 | +| learning_rate | 4.89e-05 | +| loss | -0.037 | +| n_updates | 24528 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.00018 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1409 | +| iterations | 2179 | +| time_elapsed | 3166 | +| total_timesteps | 4462592 | +| train/ | | +| approx_kl | 0.010473262 | +| clip_fraction | 0.306 | +| clip_range | 0.0739 | +| entropy_loss | -6.98 | +| explained_variance | 0.503 | +| learning_rate | 4.89e-05 | +| loss | -0.0322 | +| n_updates | 24532 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.00013 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1409 | +| iterations | 2180 | +| time_elapsed | 3168 | +| total_timesteps | 4464640 | +| train/ | | +| approx_kl | 0.009893906 | +| clip_fraction | 0.297 | +| clip_range | 0.0739 | +| entropy_loss | -7.34 | +| explained_variance | 0.00259 | +| learning_rate | 4.89e-05 | +| loss | -0.0349 | +| n_updates | 24536 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000159 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1409 | +| iterations | 2181 | +| time_elapsed | 3169 | +| total_timesteps | 4466688 | +| train/ | | +| approx_kl | 0.011290102 | +| clip_fraction | 0.305 | +| clip_range | 0.0739 | +| entropy_loss | -7.29 | +| explained_variance | 0.324 | +| learning_rate | 4.89e-05 | +| loss | -0.0326 | +| n_updates | 24540 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000109 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1409 | +| iterations | 2182 | +| time_elapsed | 3170 | +| total_timesteps | 4468736 | +| train/ | | +| approx_kl | 0.009941385 | +| clip_fraction | 0.275 | +| clip_range | 0.0739 | +| entropy_loss | -7.27 | +| explained_variance | 0.102 | +| learning_rate | 4.89e-05 | +| loss | -0.0224 | +| n_updates | 24544 | +| policy_gradient_loss | -0.0148 | +| value_loss | 0.000237 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1409 | +| iterations | 2183 | +| time_elapsed | 3172 | +| total_timesteps | 4470784 | +| train/ | | +| approx_kl | 0.00877909 | +| clip_fraction | 0.313 | +| clip_range | 0.0739 | +| entropy_loss | -6.69 | +| explained_variance | 0.533 | +| learning_rate | 4.89e-05 | +| loss | -0.0301 | +| n_updates | 24548 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000124 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1409 | +| iterations | 2184 | +| time_elapsed | 3173 | +| total_timesteps | 4472832 | +| train/ | | +| approx_kl | 0.010132739 | +| clip_fraction | 0.317 | +| clip_range | 0.0739 | +| entropy_loss | -7.31 | +| explained_variance | 0.0912 | +| learning_rate | 4.89e-05 | +| loss | -0.0313 | +| n_updates | 24552 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.00018 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1409 | +| iterations | 2185 | +| time_elapsed | 3175 | +| total_timesteps | 4474880 | +| train/ | | +| approx_kl | 0.008334915 | +| clip_fraction | 0.274 | +| clip_range | 0.0739 | +| entropy_loss | -6.99 | +| explained_variance | 0.0741 | +| learning_rate | 4.89e-05 | +| loss | -0.0386 | +| n_updates | 24556 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000249 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1409 | +| iterations | 2186 | +| time_elapsed | 3176 | +| total_timesteps | 4476928 | +| train/ | | +| approx_kl | 0.008552363 | +| clip_fraction | 0.309 | +| clip_range | 0.0739 | +| entropy_loss | -7.07 | +| explained_variance | 0.432 | +| learning_rate | 4.89e-05 | +| loss | -0.0316 | +| n_updates | 24560 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000206 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1409 | +| iterations | 2187 | +| time_elapsed | 3178 | +| total_timesteps | 4478976 | +| train/ | | +| approx_kl | 0.010931885 | +| clip_fraction | 0.311 | +| clip_range | 0.0739 | +| entropy_loss | -7.13 | +| explained_variance | 0.285 | +| learning_rate | 4.89e-05 | +| loss | -0.0294 | +| n_updates | 24564 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000181 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1409 | +| iterations | 2188 | +| time_elapsed | 3179 | +| total_timesteps | 4481024 | +| train/ | | +| approx_kl | 0.010855727 | +| clip_fraction | 0.304 | +| clip_range | 0.0739 | +| entropy_loss | -7.44 | +| explained_variance | 0.0918 | +| learning_rate | 4.89e-05 | +| loss | -0.0314 | +| n_updates | 24568 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.00016 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1409 | +| iterations | 2189 | +| time_elapsed | 3181 | +| total_timesteps | 4483072 | +| train/ | | +| approx_kl | 0.010845993 | +| clip_fraction | 0.307 | +| clip_range | 0.0739 | +| entropy_loss | -7.37 | +| explained_variance | 0.331 | +| learning_rate | 4.89e-05 | +| loss | -0.0359 | +| n_updates | 24572 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000195 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1409 | +| iterations | 2190 | +| time_elapsed | 3182 | +| total_timesteps | 4485120 | +| train/ | | +| approx_kl | 0.011238629 | +| clip_fraction | 0.333 | +| clip_range | 0.0739 | +| entropy_loss | -7.27 | +| explained_variance | 0.482 | +| learning_rate | 4.89e-05 | +| loss | -0.0368 | +| n_updates | 24576 | +| policy_gradient_loss | -0.0227 | +| value_loss | 0.000106 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1409 | +| iterations | 2191 | +| time_elapsed | 3183 | +| total_timesteps | 4487168 | +| train/ | | +| approx_kl | 0.008985836 | +| clip_fraction | 0.325 | +| clip_range | 0.0739 | +| entropy_loss | -7.2 | +| explained_variance | 0.437 | +| learning_rate | 4.89e-05 | +| loss | -0.0383 | +| n_updates | 24580 | +| policy_gradient_loss | -0.0244 | +| value_loss | 0.000102 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1409 | +| iterations | 2192 | +| time_elapsed | 3185 | +| total_timesteps | 4489216 | +| train/ | | +| approx_kl | 0.009580318 | +| clip_fraction | 0.29 | +| clip_range | 0.0739 | +| entropy_loss | -7.1 | +| explained_variance | 0.411 | +| learning_rate | 4.89e-05 | +| loss | -0.0278 | +| n_updates | 24584 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1409 | +| iterations | 2193 | +| time_elapsed | 3186 | +| total_timesteps | 4491264 | +| train/ | | +| approx_kl | 0.009683298 | +| clip_fraction | 0.298 | +| clip_range | 0.0739 | +| entropy_loss | -7.29 | +| explained_variance | 0.369 | +| learning_rate | 4.89e-05 | +| loss | -0.0355 | +| n_updates | 24588 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000115 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1409 | +| iterations | 2194 | +| time_elapsed | 3188 | +| total_timesteps | 4493312 | +| train/ | | +| approx_kl | 0.012462317 | +| clip_fraction | 0.314 | +| clip_range | 0.0739 | +| entropy_loss | -7.43 | +| explained_variance | -0.165 | +| learning_rate | 4.89e-05 | +| loss | -0.035 | +| n_updates | 24592 | +| policy_gradient_loss | -0.0199 | +| value_loss | 8.14e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1409 | +| iterations | 2195 | +| time_elapsed | 3189 | +| total_timesteps | 4495360 | +| train/ | | +| approx_kl | 0.010272592 | +| clip_fraction | 0.303 | +| clip_range | 0.0739 | +| entropy_loss | -7.15 | +| explained_variance | -0.0695 | +| learning_rate | 4.89e-05 | +| loss | -0.0303 | +| n_updates | 24596 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000217 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1409 | +| iterations | 2196 | +| time_elapsed | 3190 | +| total_timesteps | 4497408 | +| train/ | | +| approx_kl | 0.009620322 | +| clip_fraction | 0.32 | +| clip_range | 0.0739 | +| entropy_loss | -7.15 | +| explained_variance | 0.304 | +| learning_rate | 4.89e-05 | +| loss | -0.0292 | +| n_updates | 24600 | +| policy_gradient_loss | -0.0177 | +| value_loss | 9.52e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1409 | +| iterations | 2197 | +| time_elapsed | 3192 | +| total_timesteps | 4499456 | +| train/ | | +| approx_kl | 0.010246815 | +| clip_fraction | 0.31 | +| clip_range | 0.0739 | +| entropy_loss | -7.1 | +| explained_variance | 0.271 | +| learning_rate | 4.89e-05 | +| loss | -0.0233 | +| n_updates | 24604 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000165 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1409 | +| iterations | 2198 | +| time_elapsed | 3193 | +| total_timesteps | 4501504 | +| train/ | | +| approx_kl | 0.010137753 | +| clip_fraction | 0.322 | +| clip_range | 0.0739 | +| entropy_loss | -7.4 | +| explained_variance | -0.496 | +| learning_rate | 4.89e-05 | +| loss | -0.0351 | +| n_updates | 24608 | +| policy_gradient_loss | -0.0204 | +| value_loss | 9.45e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1409 | +| iterations | 2199 | +| time_elapsed | 3195 | +| total_timesteps | 4503552 | +| train/ | | +| approx_kl | 0.010131052 | +| clip_fraction | 0.297 | +| clip_range | 0.0739 | +| entropy_loss | -7.53 | +| explained_variance | -0.102 | +| learning_rate | 4.89e-05 | +| loss | -0.0309 | +| n_updates | 24612 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.0001 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1409 | +| iterations | 2200 | +| time_elapsed | 3196 | +| total_timesteps | 4505600 | +| train/ | | +| approx_kl | 0.011298899 | +| clip_fraction | 0.308 | +| clip_range | 0.0739 | +| entropy_loss | -7.41 | +| explained_variance | -0.0392 | +| learning_rate | 4.89e-05 | +| loss | -0.0325 | +| n_updates | 24616 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000187 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1409 | +| iterations | 2201 | +| time_elapsed | 3198 | +| total_timesteps | 4507648 | +| train/ | | +| approx_kl | 0.0103146145 | +| clip_fraction | 0.304 | +| clip_range | 0.0739 | +| entropy_loss | -6.79 | +| explained_variance | 0.434 | +| learning_rate | 4.89e-05 | +| loss | -0.0291 | +| n_updates | 24620 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000214 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1409 | +| iterations | 2202 | +| time_elapsed | 3199 | +| total_timesteps | 4509696 | +| train/ | | +| approx_kl | 0.010749558 | +| clip_fraction | 0.317 | +| clip_range | 0.0739 | +| entropy_loss | -7.1 | +| explained_variance | 0.307 | +| learning_rate | 4.89e-05 | +| loss | -0.0347 | +| n_updates | 24624 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000165 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1409 | +| iterations | 2203 | +| time_elapsed | 3201 | +| total_timesteps | 4511744 | +| train/ | | +| approx_kl | 0.012404828 | +| clip_fraction | 0.356 | +| clip_range | 0.0739 | +| entropy_loss | -7.06 | +| explained_variance | 0.797 | +| learning_rate | 4.89e-05 | +| loss | -0.0386 | +| n_updates | 24628 | +| policy_gradient_loss | -0.0247 | +| value_loss | 4.75e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1409 | +| iterations | 2204 | +| time_elapsed | 3202 | +| total_timesteps | 4513792 | +| train/ | | +| approx_kl | 0.00925388 | +| clip_fraction | 0.301 | +| clip_range | 0.0739 | +| entropy_loss | -7.45 | +| explained_variance | -0.0832 | +| learning_rate | 4.89e-05 | +| loss | -0.0363 | +| n_updates | 24632 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000159 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1409 | +| iterations | 2205 | +| time_elapsed | 3203 | +| total_timesteps | 4515840 | +| train/ | | +| approx_kl | 0.010864667 | +| clip_fraction | 0.317 | +| clip_range | 0.0739 | +| entropy_loss | -7.34 | +| explained_variance | 0.373 | +| learning_rate | 4.89e-05 | +| loss | -0.0319 | +| n_updates | 24636 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000135 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1409 | +| iterations | 2206 | +| time_elapsed | 3205 | +| total_timesteps | 4517888 | +| train/ | | +| approx_kl | 0.0092240665 | +| clip_fraction | 0.283 | +| clip_range | 0.0739 | +| entropy_loss | -7.31 | +| explained_variance | 0.245 | +| learning_rate | 4.89e-05 | +| loss | -0.0278 | +| n_updates | 24640 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000222 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1409 | +| iterations | 2207 | +| time_elapsed | 3206 | +| total_timesteps | 4519936 | +| train/ | | +| approx_kl | 0.010817752 | +| clip_fraction | 0.307 | +| clip_range | 0.0739 | +| entropy_loss | -7.48 | +| explained_variance | -0.0249 | +| learning_rate | 4.89e-05 | +| loss | -0.0318 | +| n_updates | 24644 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000111 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1409 | +| iterations | 2208 | +| time_elapsed | 3208 | +| total_timesteps | 4521984 | +| train/ | | +| approx_kl | 0.008825734 | +| clip_fraction | 0.297 | +| clip_range | 0.0739 | +| entropy_loss | -7.27 | +| explained_variance | 0.132 | +| learning_rate | 4.89e-05 | +| loss | -0.0266 | +| n_updates | 24648 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000279 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1409 | +| iterations | 2209 | +| time_elapsed | 3209 | +| total_timesteps | 4524032 | +| train/ | | +| approx_kl | 0.010085477 | +| clip_fraction | 0.286 | +| clip_range | 0.0739 | +| entropy_loss | -6.85 | +| explained_variance | 0.422 | +| learning_rate | 4.89e-05 | +| loss | -0.0197 | +| n_updates | 24652 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000227 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1409 | +| iterations | 2210 | +| time_elapsed | 3211 | +| total_timesteps | 4526080 | +| train/ | | +| approx_kl | 0.009539768 | +| clip_fraction | 0.272 | +| clip_range | 0.0739 | +| entropy_loss | -7.09 | +| explained_variance | 0.0734 | +| learning_rate | 4.89e-05 | +| loss | -0.0197 | +| n_updates | 24656 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000243 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1409 | +| iterations | 2211 | +| time_elapsed | 3212 | +| total_timesteps | 4528128 | +| train/ | | +| approx_kl | 0.010855343 | +| clip_fraction | 0.299 | +| clip_range | 0.0739 | +| entropy_loss | -7.27 | +| explained_variance | 0.247 | +| learning_rate | 4.89e-05 | +| loss | -0.0339 | +| n_updates | 24660 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000152 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1409 | +| iterations | 2212 | +| time_elapsed | 3214 | +| total_timesteps | 4530176 | +| train/ | | +| approx_kl | 0.009647116 | +| clip_fraction | 0.317 | +| clip_range | 0.0739 | +| entropy_loss | -6.89 | +| explained_variance | 0.622 | +| learning_rate | 4.89e-05 | +| loss | -0.0389 | +| n_updates | 24664 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1409 | +| iterations | 2213 | +| time_elapsed | 3215 | +| total_timesteps | 4532224 | +| train/ | | +| approx_kl | 0.010637961 | +| clip_fraction | 0.333 | +| clip_range | 0.0739 | +| entropy_loss | -7.45 | +| explained_variance | -0.072 | +| learning_rate | 4.89e-05 | +| loss | -0.0362 | +| n_updates | 24668 | +| policy_gradient_loss | -0.022 | +| value_loss | 9.49e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1409 | +| iterations | 2214 | +| time_elapsed | 3217 | +| total_timesteps | 4534272 | +| train/ | | +| approx_kl | 0.009319911 | +| clip_fraction | 0.278 | +| clip_range | 0.0739 | +| entropy_loss | -7.18 | +| explained_variance | 0.432 | +| learning_rate | 4.89e-05 | +| loss | -0.0319 | +| n_updates | 24672 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000194 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1409 | +| iterations | 2215 | +| time_elapsed | 3218 | +| total_timesteps | 4536320 | +| train/ | | +| approx_kl | 0.00892295 | +| clip_fraction | 0.299 | +| clip_range | 0.0739 | +| entropy_loss | -7.23 | +| explained_variance | 0.0979 | +| learning_rate | 4.89e-05 | +| loss | -0.0281 | +| n_updates | 24676 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000193 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1409 | +| iterations | 2216 | +| time_elapsed | 3219 | +| total_timesteps | 4538368 | +| train/ | | +| approx_kl | 0.008942381 | +| clip_fraction | 0.262 | +| clip_range | 0.0739 | +| entropy_loss | -7.14 | +| explained_variance | 0.368 | +| learning_rate | 4.89e-05 | +| loss | -0.0315 | +| n_updates | 24680 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000301 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1409 | +| iterations | 2217 | +| time_elapsed | 3221 | +| total_timesteps | 4540416 | +| train/ | | +| approx_kl | 0.008019885 | +| clip_fraction | 0.266 | +| clip_range | 0.0739 | +| entropy_loss | -7.28 | +| explained_variance | 0.0886 | +| learning_rate | 4.89e-05 | +| loss | -0.0313 | +| n_updates | 24684 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000215 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1409 | +| iterations | 2218 | +| time_elapsed | 3222 | +| total_timesteps | 4542464 | +| train/ | | +| approx_kl | 0.008154573 | +| clip_fraction | 0.292 | +| clip_range | 0.0739 | +| entropy_loss | -7.23 | +| explained_variance | 0.186 | +| learning_rate | 4.89e-05 | +| loss | -0.033 | +| n_updates | 24688 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000246 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1409 | +| iterations | 2219 | +| time_elapsed | 3224 | +| total_timesteps | 4544512 | +| train/ | | +| approx_kl | 0.009684229 | +| clip_fraction | 0.293 | +| clip_range | 0.0739 | +| entropy_loss | -7.27 | +| explained_variance | -0.0548 | +| learning_rate | 4.89e-05 | +| loss | -0.0296 | +| n_updates | 24692 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000154 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1409 | +| iterations | 2220 | +| time_elapsed | 3225 | +| total_timesteps | 4546560 | +| train/ | | +| approx_kl | 0.010011064 | +| clip_fraction | 0.306 | +| clip_range | 0.0739 | +| entropy_loss | -6.97 | +| explained_variance | 0.253 | +| learning_rate | 4.89e-05 | +| loss | -0.0281 | +| n_updates | 24696 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000247 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1409 | +| iterations | 2221 | +| time_elapsed | 3226 | +| total_timesteps | 4548608 | +| train/ | | +| approx_kl | 0.012029023 | +| clip_fraction | 0.314 | +| clip_range | 0.0739 | +| entropy_loss | -7.48 | +| explained_variance | -0.0826 | +| learning_rate | 4.89e-05 | +| loss | -0.0313 | +| n_updates | 24700 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000183 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1409 | +| iterations | 2222 | +| time_elapsed | 3228 | +| total_timesteps | 4550656 | +| train/ | | +| approx_kl | 0.009376192 | +| clip_fraction | 0.304 | +| clip_range | 0.0739 | +| entropy_loss | -7.21 | +| explained_variance | 0.364 | +| learning_rate | 4.89e-05 | +| loss | -0.0274 | +| n_updates | 24704 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000152 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1409 | +| iterations | 2223 | +| time_elapsed | 3229 | +| total_timesteps | 4552704 | +| train/ | | +| approx_kl | 0.010377345 | +| clip_fraction | 0.309 | +| clip_range | 0.0739 | +| entropy_loss | -7.51 | +| explained_variance | -0.468 | +| learning_rate | 4.89e-05 | +| loss | -0.0409 | +| n_updates | 24708 | +| policy_gradient_loss | -0.0223 | +| value_loss | 9.15e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1409 | +| iterations | 2224 | +| time_elapsed | 3231 | +| total_timesteps | 4554752 | +| train/ | | +| approx_kl | 0.009664409 | +| clip_fraction | 0.309 | +| clip_range | 0.0739 | +| entropy_loss | -7.49 | +| explained_variance | 0.0428 | +| learning_rate | 4.89e-05 | +| loss | -0.0313 | +| n_updates | 24712 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000126 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1409 | +| iterations | 2225 | +| time_elapsed | 3232 | +| total_timesteps | 4556800 | +| train/ | | +| approx_kl | 0.008780759 | +| clip_fraction | 0.296 | +| clip_range | 0.0739 | +| entropy_loss | -7.2 | +| explained_variance | 0.124 | +| learning_rate | 4.89e-05 | +| loss | -0.0281 | +| n_updates | 24716 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000387 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1409 | +| iterations | 2226 | +| time_elapsed | 3234 | +| total_timesteps | 4558848 | +| train/ | | +| approx_kl | 0.008772104 | +| clip_fraction | 0.298 | +| clip_range | 0.0739 | +| entropy_loss | -6.85 | +| explained_variance | 0.117 | +| learning_rate | 4.89e-05 | +| loss | -0.0258 | +| n_updates | 24720 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000177 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1409 | +| iterations | 2227 | +| time_elapsed | 3235 | +| total_timesteps | 4560896 | +| train/ | | +| approx_kl | 0.0123128835 | +| clip_fraction | 0.352 | +| clip_range | 0.0739 | +| entropy_loss | -7.21 | +| explained_variance | 0.0506 | +| learning_rate | 4.89e-05 | +| loss | -0.0425 | +| n_updates | 24724 | +| policy_gradient_loss | -0.0234 | +| value_loss | 0.000162 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1409 | +| iterations | 2228 | +| time_elapsed | 3236 | +| total_timesteps | 4562944 | +| train/ | | +| approx_kl | 0.0122323865 | +| clip_fraction | 0.331 | +| clip_range | 0.0739 | +| entropy_loss | -7.1 | +| explained_variance | 0.337 | +| learning_rate | 4.89e-05 | +| loss | -0.0378 | +| n_updates | 24728 | +| policy_gradient_loss | -0.0224 | +| value_loss | 0.000106 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1409 | +| iterations | 2229 | +| time_elapsed | 3238 | +| total_timesteps | 4564992 | +| train/ | | +| approx_kl | 0.00946462 | +| clip_fraction | 0.298 | +| clip_range | 0.0739 | +| entropy_loss | -7.05 | +| explained_variance | 0.233 | +| learning_rate | 4.89e-05 | +| loss | -0.0329 | +| n_updates | 24732 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000232 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1409 | +| iterations | 2230 | +| time_elapsed | 3239 | +| total_timesteps | 4567040 | +| train/ | | +| approx_kl | 0.011243134 | +| clip_fraction | 0.325 | +| clip_range | 0.0739 | +| entropy_loss | -7.11 | +| explained_variance | 0.35 | +| learning_rate | 4.89e-05 | +| loss | -0.0283 | +| n_updates | 24736 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000113 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1409 | +| iterations | 2231 | +| time_elapsed | 3241 | +| total_timesteps | 4569088 | +| train/ | | +| approx_kl | 0.011242805 | +| clip_fraction | 0.309 | +| clip_range | 0.0739 | +| entropy_loss | -7.03 | +| explained_variance | 0.513 | +| learning_rate | 4.89e-05 | +| loss | -0.0335 | +| n_updates | 24740 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000167 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1409 | +| iterations | 2232 | +| time_elapsed | 3242 | +| total_timesteps | 4571136 | +| train/ | | +| approx_kl | 0.010090908 | +| clip_fraction | 0.268 | +| clip_range | 0.0739 | +| entropy_loss | -6.99 | +| explained_variance | 0.448 | +| learning_rate | 4.89e-05 | +| loss | -0.0301 | +| n_updates | 24744 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000233 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1409 | +| iterations | 2233 | +| time_elapsed | 3244 | +| total_timesteps | 4573184 | +| train/ | | +| approx_kl | 0.010097016 | +| clip_fraction | 0.284 | +| clip_range | 0.0739 | +| entropy_loss | -7.23 | +| explained_variance | 0.15 | +| learning_rate | 4.89e-05 | +| loss | -0.0252 | +| n_updates | 24748 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000279 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1409 | +| iterations | 2234 | +| time_elapsed | 3245 | +| total_timesteps | 4575232 | +| train/ | | +| approx_kl | 0.009606687 | +| clip_fraction | 0.287 | +| clip_range | 0.0739 | +| entropy_loss | -7.39 | +| explained_variance | -0.0797 | +| learning_rate | 4.89e-05 | +| loss | -0.0328 | +| n_updates | 24752 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000286 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1409 | +| iterations | 2235 | +| time_elapsed | 3246 | +| total_timesteps | 4577280 | +| train/ | | +| approx_kl | 0.012047287 | +| clip_fraction | 0.331 | +| clip_range | 0.0739 | +| entropy_loss | -7.44 | +| explained_variance | -0.115 | +| learning_rate | 4.89e-05 | +| loss | -0.0357 | +| n_updates | 24756 | +| policy_gradient_loss | -0.0231 | +| value_loss | 0.000137 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1409 | +| iterations | 2236 | +| time_elapsed | 3248 | +| total_timesteps | 4579328 | +| train/ | | +| approx_kl | 0.012492123 | +| clip_fraction | 0.34 | +| clip_range | 0.0739 | +| entropy_loss | -7.38 | +| explained_variance | 0.18 | +| learning_rate | 4.89e-05 | +| loss | -0.038 | +| n_updates | 24760 | +| policy_gradient_loss | -0.0225 | +| value_loss | 0.000175 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1409 | +| iterations | 2237 | +| time_elapsed | 3249 | +| total_timesteps | 4581376 | +| train/ | | +| approx_kl | 0.010356747 | +| clip_fraction | 0.304 | +| clip_range | 0.0739 | +| entropy_loss | -7.13 | +| explained_variance | 0.176 | +| learning_rate | 4.89e-05 | +| loss | -0.0279 | +| n_updates | 24764 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000312 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1409 | +| iterations | 2238 | +| time_elapsed | 3251 | +| total_timesteps | 4583424 | +| train/ | | +| approx_kl | 0.011793885 | +| clip_fraction | 0.341 | +| clip_range | 0.0739 | +| entropy_loss | -7.3 | +| explained_variance | -0.128 | +| learning_rate | 4.89e-05 | +| loss | -0.0342 | +| n_updates | 24768 | +| policy_gradient_loss | -0.0228 | +| value_loss | 0.00017 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1409 | +| iterations | 2239 | +| time_elapsed | 3252 | +| total_timesteps | 4585472 | +| train/ | | +| approx_kl | 0.010840023 | +| clip_fraction | 0.294 | +| clip_range | 0.0739 | +| entropy_loss | -7.05 | +| explained_variance | 0.424 | +| learning_rate | 4.89e-05 | +| loss | -0.0328 | +| n_updates | 24772 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000214 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1409 | +| iterations | 2240 | +| time_elapsed | 3254 | +| total_timesteps | 4587520 | +| train/ | | +| approx_kl | 0.008835651 | +| clip_fraction | 0.282 | +| clip_range | 0.0739 | +| entropy_loss | -7.21 | +| explained_variance | 0.163 | +| learning_rate | 4.89e-05 | +| loss | -0.0312 | +| n_updates | 24776 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000213 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1409 | +| iterations | 2241 | +| time_elapsed | 3255 | +| total_timesteps | 4589568 | +| train/ | | +| approx_kl | 0.009694533 | +| clip_fraction | 0.304 | +| clip_range | 0.0739 | +| entropy_loss | -7.3 | +| explained_variance | -0.00219 | +| learning_rate | 4.89e-05 | +| loss | -0.0275 | +| n_updates | 24780 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000329 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1409 | +| iterations | 2242 | +| time_elapsed | 3256 | +| total_timesteps | 4591616 | +| train/ | | +| approx_kl | 0.010399206 | +| clip_fraction | 0.287 | +| clip_range | 0.0739 | +| entropy_loss | -6.66 | +| explained_variance | 0.186 | +| learning_rate | 4.89e-05 | +| loss | -0.0257 | +| n_updates | 24784 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000381 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1409 | +| iterations | 2243 | +| time_elapsed | 3258 | +| total_timesteps | 4593664 | +| train/ | | +| approx_kl | 0.010814879 | +| clip_fraction | 0.325 | +| clip_range | 0.0739 | +| entropy_loss | -7.21 | +| explained_variance | -0.0205 | +| learning_rate | 4.89e-05 | +| loss | -0.0332 | +| n_updates | 24788 | +| policy_gradient_loss | -0.0227 | +| value_loss | 0.000108 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1409 | +| iterations | 2244 | +| time_elapsed | 3259 | +| total_timesteps | 4595712 | +| train/ | | +| approx_kl | 0.012931726 | +| clip_fraction | 0.354 | +| clip_range | 0.0739 | +| entropy_loss | -7.26 | +| explained_variance | 0.322 | +| learning_rate | 4.89e-05 | +| loss | -0.0387 | +| n_updates | 24792 | +| policy_gradient_loss | -0.0241 | +| value_loss | 7.17e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1409 | +| iterations | 2245 | +| time_elapsed | 3261 | +| total_timesteps | 4597760 | +| train/ | | +| approx_kl | 0.012226231 | +| clip_fraction | 0.327 | +| clip_range | 0.0739 | +| entropy_loss | -7.43 | +| explained_variance | -0.0921 | +| learning_rate | 4.89e-05 | +| loss | -0.0359 | +| n_updates | 24796 | +| policy_gradient_loss | -0.0228 | +| value_loss | 0.00012 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1409 | +| iterations | 2246 | +| time_elapsed | 3262 | +| total_timesteps | 4599808 | +| train/ | | +| approx_kl | 0.010734518 | +| clip_fraction | 0.315 | +| clip_range | 0.0739 | +| entropy_loss | -7.52 | +| explained_variance | -0.138 | +| learning_rate | 4.89e-05 | +| loss | -0.0309 | +| n_updates | 24800 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000117 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1409 | +| iterations | 2247 | +| time_elapsed | 3264 | +| total_timesteps | 4601856 | +| train/ | | +| approx_kl | 0.011846488 | +| clip_fraction | 0.302 | +| clip_range | 0.0739 | +| entropy_loss | -7.11 | +| explained_variance | 0.563 | +| learning_rate | 4.89e-05 | +| loss | -0.0368 | +| n_updates | 24804 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000118 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1409 | +| iterations | 2248 | +| time_elapsed | 3265 | +| total_timesteps | 4603904 | +| train/ | | +| approx_kl | 0.011040026 | +| clip_fraction | 0.302 | +| clip_range | 0.0738 | +| entropy_loss | -7.24 | +| explained_variance | 0.434 | +| learning_rate | 4.89e-05 | +| loss | -0.0341 | +| n_updates | 24808 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.00011 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1409 | +| iterations | 2249 | +| time_elapsed | 3267 | +| total_timesteps | 4605952 | +| train/ | | +| approx_kl | 0.009801721 | +| clip_fraction | 0.299 | +| clip_range | 0.0738 | +| entropy_loss | -7.54 | +| explained_variance | -0.113 | +| learning_rate | 4.89e-05 | +| loss | -0.0313 | +| n_updates | 24812 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000109 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1409 | +| iterations | 2250 | +| time_elapsed | 3268 | +| total_timesteps | 4608000 | +| train/ | | +| approx_kl | 0.009856197 | +| clip_fraction | 0.291 | +| clip_range | 0.0738 | +| entropy_loss | -7.03 | +| explained_variance | 0.642 | +| learning_rate | 4.89e-05 | +| loss | -0.0315 | +| n_updates | 24816 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000115 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1409 | +| iterations | 2251 | +| time_elapsed | 3270 | +| total_timesteps | 4610048 | +| train/ | | +| approx_kl | 0.010382469 | +| clip_fraction | 0.29 | +| clip_range | 0.0738 | +| entropy_loss | -7.17 | +| explained_variance | 0.211 | +| learning_rate | 4.89e-05 | +| loss | -0.0276 | +| n_updates | 24820 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000136 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1409 | +| iterations | 2252 | +| time_elapsed | 3271 | +| total_timesteps | 4612096 | +| train/ | | +| approx_kl | 0.010316368 | +| clip_fraction | 0.317 | +| clip_range | 0.0738 | +| entropy_loss | -7.13 | +| explained_variance | 0.143 | +| learning_rate | 4.89e-05 | +| loss | -0.0315 | +| n_updates | 24824 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000169 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1409 | +| iterations | 2253 | +| time_elapsed | 3272 | +| total_timesteps | 4614144 | +| train/ | | +| approx_kl | 0.0109578725 | +| clip_fraction | 0.323 | +| clip_range | 0.0738 | +| entropy_loss | -6.9 | +| explained_variance | 0.279 | +| learning_rate | 4.89e-05 | +| loss | -0.0328 | +| n_updates | 24828 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000264 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1409 | +| iterations | 2254 | +| time_elapsed | 3274 | +| total_timesteps | 4616192 | +| train/ | | +| approx_kl | 0.010846732 | +| clip_fraction | 0.315 | +| clip_range | 0.0738 | +| entropy_loss | -7.36 | +| explained_variance | 0.142 | +| learning_rate | 4.89e-05 | +| loss | -0.0339 | +| n_updates | 24832 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000141 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1409 | +| iterations | 2255 | +| time_elapsed | 3275 | +| total_timesteps | 4618240 | +| train/ | | +| approx_kl | 0.008933449 | +| clip_fraction | 0.293 | +| clip_range | 0.0738 | +| entropy_loss | -6.96 | +| explained_variance | 0.319 | +| learning_rate | 4.89e-05 | +| loss | -0.0228 | +| n_updates | 24836 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000324 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1409 | +| iterations | 2256 | +| time_elapsed | 3277 | +| total_timesteps | 4620288 | +| train/ | | +| approx_kl | 0.011169294 | +| clip_fraction | 0.306 | +| clip_range | 0.0738 | +| entropy_loss | -7.45 | +| explained_variance | 0.0356 | +| learning_rate | 4.89e-05 | +| loss | -0.031 | +| n_updates | 24840 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000176 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1409 | +| iterations | 2257 | +| time_elapsed | 3278 | +| total_timesteps | 4622336 | +| train/ | | +| approx_kl | 0.0092602875 | +| clip_fraction | 0.296 | +| clip_range | 0.0738 | +| entropy_loss | -7.43 | +| explained_variance | -0.0461 | +| learning_rate | 4.89e-05 | +| loss | -0.0294 | +| n_updates | 24844 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000293 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1409 | +| iterations | 2258 | +| time_elapsed | 3280 | +| total_timesteps | 4624384 | +| train/ | | +| approx_kl | 0.010087743 | +| clip_fraction | 0.285 | +| clip_range | 0.0738 | +| entropy_loss | -7.15 | +| explained_variance | -0.0953 | +| learning_rate | 4.89e-05 | +| loss | -0.0281 | +| n_updates | 24848 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000228 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1409 | +| iterations | 2259 | +| time_elapsed | 3281 | +| total_timesteps | 4626432 | +| train/ | | +| approx_kl | 0.011594901 | +| clip_fraction | 0.305 | +| clip_range | 0.0738 | +| entropy_loss | -7.22 | +| explained_variance | -0.16 | +| learning_rate | 4.89e-05 | +| loss | -0.0333 | +| n_updates | 24852 | +| policy_gradient_loss | -0.0219 | +| value_loss | 0.000159 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1409 | +| iterations | 2260 | +| time_elapsed | 3283 | +| total_timesteps | 4628480 | +| train/ | | +| approx_kl | 0.009377778 | +| clip_fraction | 0.31 | +| clip_range | 0.0738 | +| entropy_loss | -7.07 | +| explained_variance | 0.207 | +| learning_rate | 4.89e-05 | +| loss | -0.0346 | +| n_updates | 24856 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000122 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1409 | +| iterations | 2261 | +| time_elapsed | 3284 | +| total_timesteps | 4630528 | +| train/ | | +| approx_kl | 0.011718788 | +| clip_fraction | 0.307 | +| clip_range | 0.0738 | +| entropy_loss | -7.44 | +| explained_variance | -0.0323 | +| learning_rate | 4.89e-05 | +| loss | -0.0318 | +| n_updates | 24860 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000177 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1409 | +| iterations | 2262 | +| time_elapsed | 3286 | +| total_timesteps | 4632576 | +| train/ | | +| approx_kl | 0.01047595 | +| clip_fraction | 0.316 | +| clip_range | 0.0738 | +| entropy_loss | -7.11 | +| explained_variance | -0.0153 | +| learning_rate | 4.89e-05 | +| loss | -0.0316 | +| n_updates | 24864 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000164 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1409 | +| iterations | 2263 | +| time_elapsed | 3287 | +| total_timesteps | 4634624 | +| train/ | | +| approx_kl | 0.010500476 | +| clip_fraction | 0.31 | +| clip_range | 0.0738 | +| entropy_loss | -7.21 | +| explained_variance | 0.274 | +| learning_rate | 4.89e-05 | +| loss | -0.0363 | +| n_updates | 24868 | +| policy_gradient_loss | -0.0225 | +| value_loss | 8.33e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1409 | +| iterations | 2264 | +| time_elapsed | 3288 | +| total_timesteps | 4636672 | +| train/ | | +| approx_kl | 0.0077990247 | +| clip_fraction | 0.26 | +| clip_range | 0.0738 | +| entropy_loss | -7.01 | +| explained_variance | 0.232 | +| learning_rate | 4.89e-05 | +| loss | -0.0286 | +| n_updates | 24872 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000237 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1409 | +| iterations | 2265 | +| time_elapsed | 3290 | +| total_timesteps | 4638720 | +| train/ | | +| approx_kl | 0.011668861 | +| clip_fraction | 0.313 | +| clip_range | 0.0738 | +| entropy_loss | -7.02 | +| explained_variance | 0.323 | +| learning_rate | 4.89e-05 | +| loss | -0.0339 | +| n_updates | 24876 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000224 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1409 | +| iterations | 2266 | +| time_elapsed | 3291 | +| total_timesteps | 4640768 | +| train/ | | +| approx_kl | 0.0104152 | +| clip_fraction | 0.313 | +| clip_range | 0.0738 | +| entropy_loss | -7.31 | +| explained_variance | 0.0969 | +| learning_rate | 4.89e-05 | +| loss | -0.0337 | +| n_updates | 24880 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000167 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1409 | +| iterations | 2267 | +| time_elapsed | 3293 | +| total_timesteps | 4642816 | +| train/ | | +| approx_kl | 0.011187846 | +| clip_fraction | 0.308 | +| clip_range | 0.0738 | +| entropy_loss | -6.98 | +| explained_variance | 0.394 | +| learning_rate | 4.89e-05 | +| loss | -0.0285 | +| n_updates | 24884 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000196 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1409 | +| iterations | 2268 | +| time_elapsed | 3294 | +| total_timesteps | 4644864 | +| train/ | | +| approx_kl | 0.009549024 | +| clip_fraction | 0.308 | +| clip_range | 0.0738 | +| entropy_loss | -7.24 | +| explained_variance | 0.299 | +| learning_rate | 4.89e-05 | +| loss | -0.036 | +| n_updates | 24888 | +| policy_gradient_loss | -0.0211 | +| value_loss | 9.34e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1409 | +| iterations | 2269 | +| time_elapsed | 3295 | +| total_timesteps | 4646912 | +| train/ | | +| approx_kl | 0.010270055 | +| clip_fraction | 0.322 | +| clip_range | 0.0738 | +| entropy_loss | -7.32 | +| explained_variance | 0.372 | +| learning_rate | 4.89e-05 | +| loss | -0.0322 | +| n_updates | 24892 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000101 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1409 | +| iterations | 2270 | +| time_elapsed | 3297 | +| total_timesteps | 4648960 | +| train/ | | +| approx_kl | 0.009694522 | +| clip_fraction | 0.312 | +| clip_range | 0.0738 | +| entropy_loss | -7.41 | +| explained_variance | -0.0478 | +| learning_rate | 4.89e-05 | +| loss | -0.031 | +| n_updates | 24896 | +| policy_gradient_loss | -0.0207 | +| value_loss | 8.84e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1409 | +| iterations | 2271 | +| time_elapsed | 3298 | +| total_timesteps | 4651008 | +| train/ | | +| approx_kl | 0.010328033 | +| clip_fraction | 0.307 | +| clip_range | 0.0738 | +| entropy_loss | -7.37 | +| explained_variance | 0.111 | +| learning_rate | 4.89e-05 | +| loss | -0.0321 | +| n_updates | 24900 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000152 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1409 | +| iterations | 2272 | +| time_elapsed | 3300 | +| total_timesteps | 4653056 | +| train/ | | +| approx_kl | 0.0073097013 | +| clip_fraction | 0.271 | +| clip_range | 0.0738 | +| entropy_loss | -7.31 | +| explained_variance | 0.106 | +| learning_rate | 4.89e-05 | +| loss | -0.0265 | +| n_updates | 24904 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000264 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1409 | +| iterations | 2273 | +| time_elapsed | 3301 | +| total_timesteps | 4655104 | +| train/ | | +| approx_kl | 0.008671939 | +| clip_fraction | 0.265 | +| clip_range | 0.0738 | +| entropy_loss | -6.99 | +| explained_variance | -0.052 | +| learning_rate | 4.89e-05 | +| loss | -0.0283 | +| n_updates | 24908 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000199 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1409 | +| iterations | 2274 | +| time_elapsed | 3303 | +| total_timesteps | 4657152 | +| train/ | | +| approx_kl | 0.01004697 | +| clip_fraction | 0.285 | +| clip_range | 0.0738 | +| entropy_loss | -7.03 | +| explained_variance | 0.154 | +| learning_rate | 4.89e-05 | +| loss | -0.0332 | +| n_updates | 24912 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000288 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1409 | +| iterations | 2275 | +| time_elapsed | 3304 | +| total_timesteps | 4659200 | +| train/ | | +| approx_kl | 0.011075724 | +| clip_fraction | 0.324 | +| clip_range | 0.0738 | +| entropy_loss | -7.18 | +| explained_variance | 0.0864 | +| learning_rate | 4.89e-05 | +| loss | -0.0318 | +| n_updates | 24916 | +| policy_gradient_loss | -0.0219 | +| value_loss | 0.00017 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1409 | +| iterations | 2276 | +| time_elapsed | 3306 | +| total_timesteps | 4661248 | +| train/ | | +| approx_kl | 0.009535312 | +| clip_fraction | 0.266 | +| clip_range | 0.0738 | +| entropy_loss | -6.72 | +| explained_variance | 0.415 | +| learning_rate | 4.89e-05 | +| loss | -0.0283 | +| n_updates | 24920 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000304 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1409 | +| iterations | 2277 | +| time_elapsed | 3307 | +| total_timesteps | 4663296 | +| train/ | | +| approx_kl | 0.010604605 | +| clip_fraction | 0.318 | +| clip_range | 0.0738 | +| entropy_loss | -7.37 | +| explained_variance | -0.258 | +| learning_rate | 4.89e-05 | +| loss | -0.0382 | +| n_updates | 24924 | +| policy_gradient_loss | -0.023 | +| value_loss | 9.44e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1409 | +| iterations | 2278 | +| time_elapsed | 3309 | +| total_timesteps | 4665344 | +| train/ | | +| approx_kl | 0.009716503 | +| clip_fraction | 0.304 | +| clip_range | 0.0738 | +| entropy_loss | -7.01 | +| explained_variance | 0.371 | +| learning_rate | 4.89e-05 | +| loss | -0.0281 | +| n_updates | 24928 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000233 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1409 | +| iterations | 2279 | +| time_elapsed | 3310 | +| total_timesteps | 4667392 | +| train/ | | +| approx_kl | 0.009129999 | +| clip_fraction | 0.299 | +| clip_range | 0.0738 | +| entropy_loss | -7.53 | +| explained_variance | -0.102 | +| learning_rate | 4.89e-05 | +| loss | -0.0332 | +| n_updates | 24932 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000149 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1409 | +| iterations | 2280 | +| time_elapsed | 3311 | +| total_timesteps | 4669440 | +| train/ | | +| approx_kl | 0.010019343 | +| clip_fraction | 0.304 | +| clip_range | 0.0738 | +| entropy_loss | -7.33 | +| explained_variance | 0.246 | +| learning_rate | 4.89e-05 | +| loss | -0.0324 | +| n_updates | 24936 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000218 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1409 | +| iterations | 2281 | +| time_elapsed | 3313 | +| total_timesteps | 4671488 | +| train/ | | +| approx_kl | 0.009450755 | +| clip_fraction | 0.31 | +| clip_range | 0.0738 | +| entropy_loss | -7.36 | +| explained_variance | 0.299 | +| learning_rate | 4.89e-05 | +| loss | -0.0335 | +| n_updates | 24940 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000149 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1409 | +| iterations | 2282 | +| time_elapsed | 3314 | +| total_timesteps | 4673536 | +| train/ | | +| approx_kl | 0.011347244 | +| clip_fraction | 0.342 | +| clip_range | 0.0738 | +| entropy_loss | -7.48 | +| explained_variance | -0.204 | +| learning_rate | 4.89e-05 | +| loss | -0.036 | +| n_updates | 24944 | +| policy_gradient_loss | -0.0229 | +| value_loss | 0.000164 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1409 | +| iterations | 2283 | +| time_elapsed | 3316 | +| total_timesteps | 4675584 | +| train/ | | +| approx_kl | 0.009137383 | +| clip_fraction | 0.298 | +| clip_range | 0.0738 | +| entropy_loss | -7.35 | +| explained_variance | -0.0489 | +| learning_rate | 4.89e-05 | +| loss | -0.0255 | +| n_updates | 24948 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000175 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1409 | +| iterations | 2284 | +| time_elapsed | 3317 | +| total_timesteps | 4677632 | +| train/ | | +| approx_kl | 0.009372059 | +| clip_fraction | 0.304 | +| clip_range | 0.0738 | +| entropy_loss | -7.26 | +| explained_variance | 0.367 | +| learning_rate | 4.89e-05 | +| loss | -0.0284 | +| n_updates | 24952 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000131 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1409 | +| iterations | 2285 | +| time_elapsed | 3319 | +| total_timesteps | 4679680 | +| train/ | | +| approx_kl | 0.011404416 | +| clip_fraction | 0.303 | +| clip_range | 0.0738 | +| entropy_loss | -6.94 | +| explained_variance | 0.635 | +| learning_rate | 4.89e-05 | +| loss | -0.0335 | +| n_updates | 24956 | +| policy_gradient_loss | -0.0193 | +| value_loss | 7.61e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1409 | +| iterations | 2286 | +| time_elapsed | 3320 | +| total_timesteps | 4681728 | +| train/ | | +| approx_kl | 0.009782796 | +| clip_fraction | 0.294 | +| clip_range | 0.0738 | +| entropy_loss | -7.26 | +| explained_variance | 0.37 | +| learning_rate | 4.89e-05 | +| loss | -0.0309 | +| n_updates | 24960 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000144 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1409 | +| iterations | 2287 | +| time_elapsed | 3321 | +| total_timesteps | 4683776 | +| train/ | | +| approx_kl | 0.011051875 | +| clip_fraction | 0.27 | +| clip_range | 0.0738 | +| entropy_loss | -7.09 | +| explained_variance | 0.184 | +| learning_rate | 4.89e-05 | +| loss | -0.0232 | +| n_updates | 24964 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000255 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1409 | +| iterations | 2288 | +| time_elapsed | 3323 | +| total_timesteps | 4685824 | +| train/ | | +| approx_kl | 0.0102656465 | +| clip_fraction | 0.294 | +| clip_range | 0.0738 | +| entropy_loss | -6.94 | +| explained_variance | 0.369 | +| learning_rate | 4.89e-05 | +| loss | -0.0306 | +| n_updates | 24968 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000148 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1409 | +| iterations | 2289 | +| time_elapsed | 3324 | +| total_timesteps | 4687872 | +| train/ | | +| approx_kl | 0.012939468 | +| clip_fraction | 0.349 | +| clip_range | 0.0738 | +| entropy_loss | -7.42 | +| explained_variance | -0.397 | +| learning_rate | 4.89e-05 | +| loss | -0.0379 | +| n_updates | 24972 | +| policy_gradient_loss | -0.0251 | +| value_loss | 6.96e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1409 | +| iterations | 2290 | +| time_elapsed | 3326 | +| total_timesteps | 4689920 | +| train/ | | +| approx_kl | 0.012744023 | +| clip_fraction | 0.305 | +| clip_range | 0.0738 | +| entropy_loss | -7.09 | +| explained_variance | 0.511 | +| learning_rate | 4.89e-05 | +| loss | -0.0305 | +| n_updates | 24976 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000147 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1409 | +| iterations | 2291 | +| time_elapsed | 3327 | +| total_timesteps | 4691968 | +| train/ | | +| approx_kl | 0.010652574 | +| clip_fraction | 0.298 | +| clip_range | 0.0738 | +| entropy_loss | -7.24 | +| explained_variance | 0.372 | +| learning_rate | 4.89e-05 | +| loss | -0.0345 | +| n_updates | 24980 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000141 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1409 | +| iterations | 2292 | +| time_elapsed | 3329 | +| total_timesteps | 4694016 | +| train/ | | +| approx_kl | 0.012869552 | +| clip_fraction | 0.32 | +| clip_range | 0.0738 | +| entropy_loss | -7.19 | +| explained_variance | 0.301 | +| learning_rate | 4.89e-05 | +| loss | -0.0342 | +| n_updates | 24984 | +| policy_gradient_loss | -0.0219 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1409 | +| iterations | 2293 | +| time_elapsed | 3330 | +| total_timesteps | 4696064 | +| train/ | | +| approx_kl | 0.011972085 | +| clip_fraction | 0.344 | +| clip_range | 0.0738 | +| entropy_loss | -7.27 | +| explained_variance | 0.0231 | +| learning_rate | 4.89e-05 | +| loss | -0.0424 | +| n_updates | 24988 | +| policy_gradient_loss | -0.0232 | +| value_loss | 0.000118 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1409 | +| iterations | 2294 | +| time_elapsed | 3332 | +| total_timesteps | 4698112 | +| train/ | | +| approx_kl | 0.011136752 | +| clip_fraction | 0.303 | +| clip_range | 0.0738 | +| entropy_loss | -7.27 | +| explained_variance | 0.295 | +| learning_rate | 4.89e-05 | +| loss | -0.0322 | +| n_updates | 24992 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000141 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1409 | +| iterations | 2295 | +| time_elapsed | 3333 | +| total_timesteps | 4700160 | +| train/ | | +| approx_kl | 0.01062093 | +| clip_fraction | 0.278 | +| clip_range | 0.0738 | +| entropy_loss | -7.23 | +| explained_variance | 0.0866 | +| learning_rate | 4.89e-05 | +| loss | -0.0261 | +| n_updates | 24996 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000272 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1409 | +| iterations | 2296 | +| time_elapsed | 3334 | +| total_timesteps | 4702208 | +| train/ | | +| approx_kl | 0.010819646 | +| clip_fraction | 0.304 | +| clip_range | 0.0738 | +| entropy_loss | -7.27 | +| explained_variance | 0.167 | +| learning_rate | 4.89e-05 | +| loss | -0.0324 | +| n_updates | 25000 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000217 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1410 | +| iterations | 2297 | +| time_elapsed | 3336 | +| total_timesteps | 4704256 | +| train/ | | +| approx_kl | 0.009294108 | +| clip_fraction | 0.318 | +| clip_range | 0.0738 | +| entropy_loss | -7.48 | +| explained_variance | -0.0835 | +| learning_rate | 4.89e-05 | +| loss | -0.0334 | +| n_updates | 25004 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000127 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1410 | +| iterations | 2298 | +| time_elapsed | 3337 | +| total_timesteps | 4706304 | +| train/ | | +| approx_kl | 0.0105775595 | +| clip_fraction | 0.298 | +| clip_range | 0.0738 | +| entropy_loss | -7.01 | +| explained_variance | 0.0781 | +| learning_rate | 4.89e-05 | +| loss | -0.0325 | +| n_updates | 25008 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000296 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1410 | +| iterations | 2299 | +| time_elapsed | 3339 | +| total_timesteps | 4708352 | +| train/ | | +| approx_kl | 0.008308159 | +| clip_fraction | 0.291 | +| clip_range | 0.0738 | +| entropy_loss | -6.97 | +| explained_variance | 0.279 | +| learning_rate | 4.89e-05 | +| loss | -0.0249 | +| n_updates | 25012 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000365 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1410 | +| iterations | 2300 | +| time_elapsed | 3340 | +| total_timesteps | 4710400 | +| train/ | | +| approx_kl | 0.010491861 | +| clip_fraction | 0.324 | +| clip_range | 0.0738 | +| entropy_loss | -6.94 | +| explained_variance | 0.561 | +| learning_rate | 4.89e-05 | +| loss | -0.0372 | +| n_updates | 25016 | +| policy_gradient_loss | -0.0222 | +| value_loss | 0.000122 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1409 | +| iterations | 2301 | +| time_elapsed | 3342 | +| total_timesteps | 4712448 | +| train/ | | +| approx_kl | 0.009915195 | +| clip_fraction | 0.314 | +| clip_range | 0.0738 | +| entropy_loss | -7.19 | +| explained_variance | 0.301 | +| learning_rate | 4.89e-05 | +| loss | -0.0352 | +| n_updates | 25020 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000173 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1410 | +| iterations | 2302 | +| time_elapsed | 3343 | +| total_timesteps | 4714496 | +| train/ | | +| approx_kl | 0.012684157 | +| clip_fraction | 0.314 | +| clip_range | 0.0738 | +| entropy_loss | -6.99 | +| explained_variance | 0.298 | +| learning_rate | 4.89e-05 | +| loss | -0.0284 | +| n_updates | 25024 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000149 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1410 | +| iterations | 2303 | +| time_elapsed | 3344 | +| total_timesteps | 4716544 | +| train/ | | +| approx_kl | 0.008567699 | +| clip_fraction | 0.29 | +| clip_range | 0.0738 | +| entropy_loss | -7.44 | +| explained_variance | -0.0387 | +| learning_rate | 4.89e-05 | +| loss | -0.0319 | +| n_updates | 25028 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000163 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1410 | +| iterations | 2304 | +| time_elapsed | 3346 | +| total_timesteps | 4718592 | +| train/ | | +| approx_kl | 0.010351041 | +| clip_fraction | 0.304 | +| clip_range | 0.0738 | +| entropy_loss | -7.24 | +| explained_variance | 0.131 | +| learning_rate | 4.89e-05 | +| loss | -0.0278 | +| n_updates | 25032 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000365 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1410 | +| iterations | 2305 | +| time_elapsed | 3347 | +| total_timesteps | 4720640 | +| train/ | | +| approx_kl | 0.010918442 | +| clip_fraction | 0.308 | +| clip_range | 0.0738 | +| entropy_loss | -7.2 | +| explained_variance | 0.3 | +| learning_rate | 4.89e-05 | +| loss | -0.0341 | +| n_updates | 25036 | +| policy_gradient_loss | -0.0221 | +| value_loss | 0.000189 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1410 | +| iterations | 2306 | +| time_elapsed | 3349 | +| total_timesteps | 4722688 | +| train/ | | +| approx_kl | 0.008824142 | +| clip_fraction | 0.282 | +| clip_range | 0.0738 | +| entropy_loss | -6.67 | +| explained_variance | 0.427 | +| learning_rate | 4.89e-05 | +| loss | -0.0312 | +| n_updates | 25040 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000432 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1410 | +| iterations | 2307 | +| time_elapsed | 3350 | +| total_timesteps | 4724736 | +| train/ | | +| approx_kl | 0.009880409 | +| clip_fraction | 0.32 | +| clip_range | 0.0738 | +| entropy_loss | -6.83 | +| explained_variance | 0.507 | +| learning_rate | 4.89e-05 | +| loss | -0.0274 | +| n_updates | 25044 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000189 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1410 | +| iterations | 2308 | +| time_elapsed | 3352 | +| total_timesteps | 4726784 | +| train/ | | +| approx_kl | 0.010988345 | +| clip_fraction | 0.322 | +| clip_range | 0.0738 | +| entropy_loss | -7.39 | +| explained_variance | -0.0792 | +| learning_rate | 4.89e-05 | +| loss | -0.037 | +| n_updates | 25048 | +| policy_gradient_loss | -0.0221 | +| value_loss | 0.000188 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1410 | +| iterations | 2309 | +| time_elapsed | 3353 | +| total_timesteps | 4728832 | +| train/ | | +| approx_kl | 0.009702855 | +| clip_fraction | 0.322 | +| clip_range | 0.0738 | +| entropy_loss | -7.49 | +| explained_variance | -0.12 | +| learning_rate | 4.89e-05 | +| loss | -0.0365 | +| n_updates | 25052 | +| policy_gradient_loss | -0.0228 | +| value_loss | 9.52e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1410 | +| iterations | 2310 | +| time_elapsed | 3355 | +| total_timesteps | 4730880 | +| train/ | | +| approx_kl | 0.010801688 | +| clip_fraction | 0.315 | +| clip_range | 0.0738 | +| entropy_loss | -7.31 | +| explained_variance | -0.116 | +| learning_rate | 4.89e-05 | +| loss | -0.0355 | +| n_updates | 25056 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000226 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1410 | +| iterations | 2311 | +| time_elapsed | 3356 | +| total_timesteps | 4732928 | +| train/ | | +| approx_kl | 0.011113973 | +| clip_fraction | 0.32 | +| clip_range | 0.0738 | +| entropy_loss | -7.2 | +| explained_variance | 0.227 | +| learning_rate | 4.89e-05 | +| loss | -0.0335 | +| n_updates | 25060 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000181 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1410 | +| iterations | 2312 | +| time_elapsed | 3357 | +| total_timesteps | 4734976 | +| train/ | | +| approx_kl | 0.00968837 | +| clip_fraction | 0.327 | +| clip_range | 0.0738 | +| entropy_loss | -7.22 | +| explained_variance | 0.248 | +| learning_rate | 4.89e-05 | +| loss | -0.0335 | +| n_updates | 25064 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000156 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1410 | +| iterations | 2313 | +| time_elapsed | 3359 | +| total_timesteps | 4737024 | +| train/ | | +| approx_kl | 0.010591831 | +| clip_fraction | 0.318 | +| clip_range | 0.0738 | +| entropy_loss | -7.42 | +| explained_variance | -0.119 | +| learning_rate | 4.89e-05 | +| loss | -0.0364 | +| n_updates | 25068 | +| policy_gradient_loss | -0.0227 | +| value_loss | 0.00016 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.388 | +| time/ | | +| fps | 1410 | +| iterations | 2314 | +| time_elapsed | 3360 | +| total_timesteps | 4739072 | +| train/ | | +| approx_kl | 0.008645894 | +| clip_fraction | 0.273 | +| clip_range | 0.0738 | +| entropy_loss | -7.16 | +| explained_variance | -0.044 | +| learning_rate | 4.89e-05 | +| loss | -0.0247 | +| n_updates | 25072 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000266 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1410 | +| iterations | 2315 | +| time_elapsed | 3362 | +| total_timesteps | 4741120 | +| train/ | | +| approx_kl | 0.012092038 | +| clip_fraction | 0.328 | +| clip_range | 0.0738 | +| entropy_loss | -7.21 | +| explained_variance | -0.0675 | +| learning_rate | 4.89e-05 | +| loss | -0.0266 | +| n_updates | 25076 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000286 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1410 | +| iterations | 2316 | +| time_elapsed | 3363 | +| total_timesteps | 4743168 | +| train/ | | +| approx_kl | 0.010572464 | +| clip_fraction | 0.297 | +| clip_range | 0.0738 | +| entropy_loss | -7.06 | +| explained_variance | 0.121 | +| learning_rate | 4.89e-05 | +| loss | -0.0329 | +| n_updates | 25080 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000273 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1410 | +| iterations | 2317 | +| time_elapsed | 3365 | +| total_timesteps | 4745216 | +| train/ | | +| approx_kl | 0.011071033 | +| clip_fraction | 0.312 | +| clip_range | 0.0738 | +| entropy_loss | -7.04 | +| explained_variance | 0.33 | +| learning_rate | 4.89e-05 | +| loss | -0.0314 | +| n_updates | 25084 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000233 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1410 | +| iterations | 2318 | +| time_elapsed | 3366 | +| total_timesteps | 4747264 | +| train/ | | +| approx_kl | 0.011110316 | +| clip_fraction | 0.32 | +| clip_range | 0.0738 | +| entropy_loss | -6.88 | +| explained_variance | 0.247 | +| learning_rate | 4.89e-05 | +| loss | -0.0349 | +| n_updates | 25088 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000189 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1410 | +| iterations | 2319 | +| time_elapsed | 3367 | +| total_timesteps | 4749312 | +| train/ | | +| approx_kl | 0.011073759 | +| clip_fraction | 0.308 | +| clip_range | 0.0738 | +| entropy_loss | -7.19 | +| explained_variance | 0.181 | +| learning_rate | 4.89e-05 | +| loss | -0.0275 | +| n_updates | 25092 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000157 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1410 | +| iterations | 2320 | +| time_elapsed | 3369 | +| total_timesteps | 4751360 | +| train/ | | +| approx_kl | 0.0117874835 | +| clip_fraction | 0.353 | +| clip_range | 0.0738 | +| entropy_loss | -7.45 | +| explained_variance | -0.0629 | +| learning_rate | 4.89e-05 | +| loss | -0.0402 | +| n_updates | 25096 | +| policy_gradient_loss | -0.0237 | +| value_loss | 0.000106 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1410 | +| iterations | 2321 | +| time_elapsed | 3370 | +| total_timesteps | 4753408 | +| train/ | | +| approx_kl | 0.010211017 | +| clip_fraction | 0.304 | +| clip_range | 0.0738 | +| entropy_loss | -7.1 | +| explained_variance | 0.141 | +| learning_rate | 4.89e-05 | +| loss | -0.0267 | +| n_updates | 25100 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000367 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1410 | +| iterations | 2322 | +| time_elapsed | 3372 | +| total_timesteps | 4755456 | +| train/ | | +| approx_kl | 0.010486027 | +| clip_fraction | 0.321 | +| clip_range | 0.0738 | +| entropy_loss | -7.02 | +| explained_variance | 0.604 | +| learning_rate | 4.89e-05 | +| loss | -0.0381 | +| n_updates | 25104 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000108 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1410 | +| iterations | 2323 | +| time_elapsed | 3373 | +| total_timesteps | 4757504 | +| train/ | | +| approx_kl | 0.010404483 | +| clip_fraction | 0.288 | +| clip_range | 0.0738 | +| entropy_loss | -7.31 | +| explained_variance | -0.0701 | +| learning_rate | 4.89e-05 | +| loss | -0.032 | +| n_updates | 25108 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000372 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1410 | +| iterations | 2324 | +| time_elapsed | 3375 | +| total_timesteps | 4759552 | +| train/ | | +| approx_kl | 0.010531958 | +| clip_fraction | 0.313 | +| clip_range | 0.0738 | +| entropy_loss | -6.89 | +| explained_variance | 0.49 | +| learning_rate | 4.89e-05 | +| loss | -0.0316 | +| n_updates | 25112 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.00016 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1410 | +| iterations | 2325 | +| time_elapsed | 3376 | +| total_timesteps | 4761600 | +| train/ | | +| approx_kl | 0.011130862 | +| clip_fraction | 0.319 | +| clip_range | 0.0738 | +| entropy_loss | -7.36 | +| explained_variance | -0.0877 | +| learning_rate | 4.89e-05 | +| loss | -0.0333 | +| n_updates | 25116 | +| policy_gradient_loss | -0.022 | +| value_loss | 0.000124 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1410 | +| iterations | 2326 | +| time_elapsed | 3377 | +| total_timesteps | 4763648 | +| train/ | | +| approx_kl | 0.011165911 | +| clip_fraction | 0.322 | +| clip_range | 0.0738 | +| entropy_loss | -7.5 | +| explained_variance | -0.265 | +| learning_rate | 4.89e-05 | +| loss | -0.0359 | +| n_updates | 25120 | +| policy_gradient_loss | -0.0223 | +| value_loss | 9.52e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1410 | +| iterations | 2327 | +| time_elapsed | 3379 | +| total_timesteps | 4765696 | +| train/ | | +| approx_kl | 0.011689582 | +| clip_fraction | 0.345 | +| clip_range | 0.0738 | +| entropy_loss | -7.38 | +| explained_variance | 0.487 | +| learning_rate | 4.89e-05 | +| loss | -0.042 | +| n_updates | 25124 | +| policy_gradient_loss | -0.0243 | +| value_loss | 7.11e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1410 | +| iterations | 2328 | +| time_elapsed | 3380 | +| total_timesteps | 4767744 | +| train/ | | +| approx_kl | 0.008971855 | +| clip_fraction | 0.276 | +| clip_range | 0.0738 | +| entropy_loss | -7.18 | +| explained_variance | 0.354 | +| learning_rate | 4.89e-05 | +| loss | -0.0308 | +| n_updates | 25128 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000183 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1410 | +| iterations | 2329 | +| time_elapsed | 3382 | +| total_timesteps | 4769792 | +| train/ | | +| approx_kl | 0.011358081 | +| clip_fraction | 0.319 | +| clip_range | 0.0738 | +| entropy_loss | -7.27 | +| explained_variance | 0.152 | +| learning_rate | 4.89e-05 | +| loss | -0.0358 | +| n_updates | 25132 | +| policy_gradient_loss | -0.022 | +| value_loss | 7.07e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1410 | +| iterations | 2330 | +| time_elapsed | 3383 | +| total_timesteps | 4771840 | +| train/ | | +| approx_kl | 0.009046208 | +| clip_fraction | 0.285 | +| clip_range | 0.0738 | +| entropy_loss | -7.08 | +| explained_variance | 0.293 | +| learning_rate | 4.89e-05 | +| loss | -0.0274 | +| n_updates | 25136 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000231 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1410 | +| iterations | 2331 | +| time_elapsed | 3384 | +| total_timesteps | 4773888 | +| train/ | | +| approx_kl | 0.008705927 | +| clip_fraction | 0.307 | +| clip_range | 0.0738 | +| entropy_loss | -7.09 | +| explained_variance | 0.483 | +| learning_rate | 4.89e-05 | +| loss | -0.0306 | +| n_updates | 25140 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000143 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1410 | +| iterations | 2332 | +| time_elapsed | 3386 | +| total_timesteps | 4775936 | +| train/ | | +| approx_kl | 0.009233596 | +| clip_fraction | 0.283 | +| clip_range | 0.0738 | +| entropy_loss | -7.08 | +| explained_variance | 0.431 | +| learning_rate | 4.89e-05 | +| loss | -0.0247 | +| n_updates | 25144 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000216 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1410 | +| iterations | 2333 | +| time_elapsed | 3387 | +| total_timesteps | 4777984 | +| train/ | | +| approx_kl | 0.009046581 | +| clip_fraction | 0.291 | +| clip_range | 0.0738 | +| entropy_loss | -7.16 | +| explained_variance | 0.517 | +| learning_rate | 4.89e-05 | +| loss | -0.0296 | +| n_updates | 25148 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000141 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1410 | +| iterations | 2334 | +| time_elapsed | 3389 | +| total_timesteps | 4780032 | +| train/ | | +| approx_kl | 0.008712312 | +| clip_fraction | 0.296 | +| clip_range | 0.0738 | +| entropy_loss | -6.97 | +| explained_variance | 0.539 | +| learning_rate | 4.89e-05 | +| loss | -0.0302 | +| n_updates | 25152 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000101 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1410 | +| iterations | 2335 | +| time_elapsed | 3390 | +| total_timesteps | 4782080 | +| train/ | | +| approx_kl | 0.010821624 | +| clip_fraction | 0.323 | +| clip_range | 0.0738 | +| entropy_loss | -7.26 | +| explained_variance | 0.228 | +| learning_rate | 4.89e-05 | +| loss | -0.0251 | +| n_updates | 25156 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000195 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1410 | +| iterations | 2336 | +| time_elapsed | 3392 | +| total_timesteps | 4784128 | +| train/ | | +| approx_kl | 0.0076683806 | +| clip_fraction | 0.262 | +| clip_range | 0.0738 | +| entropy_loss | -7.08 | +| explained_variance | 0.313 | +| learning_rate | 4.89e-05 | +| loss | -0.0221 | +| n_updates | 25160 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000216 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1410 | +| iterations | 2337 | +| time_elapsed | 3393 | +| total_timesteps | 4786176 | +| train/ | | +| approx_kl | 0.007955946 | +| clip_fraction | 0.302 | +| clip_range | 0.0738 | +| entropy_loss | -7.16 | +| explained_variance | 0.353 | +| learning_rate | 4.89e-05 | +| loss | -0.0316 | +| n_updates | 25164 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000233 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1410 | +| iterations | 2338 | +| time_elapsed | 3395 | +| total_timesteps | 4788224 | +| train/ | | +| approx_kl | 0.008837067 | +| clip_fraction | 0.301 | +| clip_range | 0.0738 | +| entropy_loss | -7.41 | +| explained_variance | -0.172 | +| learning_rate | 4.89e-05 | +| loss | -0.0315 | +| n_updates | 25168 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000169 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1410 | +| iterations | 2339 | +| time_elapsed | 3396 | +| total_timesteps | 4790272 | +| train/ | | +| approx_kl | 0.008763395 | +| clip_fraction | 0.266 | +| clip_range | 0.0738 | +| entropy_loss | -7.25 | +| explained_variance | 0.211 | +| learning_rate | 4.89e-05 | +| loss | -0.0315 | +| n_updates | 25172 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.00023 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1410 | +| iterations | 2340 | +| time_elapsed | 3397 | +| total_timesteps | 4792320 | +| train/ | | +| approx_kl | 0.011484682 | +| clip_fraction | 0.32 | +| clip_range | 0.0738 | +| entropy_loss | -7.13 | +| explained_variance | 0.415 | +| learning_rate | 4.89e-05 | +| loss | -0.0361 | +| n_updates | 25176 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000119 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1410 | +| iterations | 2341 | +| time_elapsed | 3399 | +| total_timesteps | 4794368 | +| train/ | | +| approx_kl | 0.009667607 | +| clip_fraction | 0.301 | +| clip_range | 0.0738 | +| entropy_loss | -7.13 | +| explained_variance | 0.0935 | +| learning_rate | 4.89e-05 | +| loss | -0.0406 | +| n_updates | 25180 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000147 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1410 | +| iterations | 2342 | +| time_elapsed | 3400 | +| total_timesteps | 4796416 | +| train/ | | +| approx_kl | 0.010777165 | +| clip_fraction | 0.303 | +| clip_range | 0.0738 | +| entropy_loss | -7.13 | +| explained_variance | 0.43 | +| learning_rate | 4.89e-05 | +| loss | -0.0333 | +| n_updates | 25184 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000113 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1410 | +| iterations | 2343 | +| time_elapsed | 3402 | +| total_timesteps | 4798464 | +| train/ | | +| approx_kl | 0.010991794 | +| clip_fraction | 0.339 | +| clip_range | 0.0738 | +| entropy_loss | -7.49 | +| explained_variance | -0.184 | +| learning_rate | 4.89e-05 | +| loss | -0.0317 | +| n_updates | 25188 | +| policy_gradient_loss | -0.0218 | +| value_loss | 7.9e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1410 | +| iterations | 2344 | +| time_elapsed | 3403 | +| total_timesteps | 4800512 | +| train/ | | +| approx_kl | 0.010831523 | +| clip_fraction | 0.323 | +| clip_range | 0.0738 | +| entropy_loss | -7.47 | +| explained_variance | -0.202 | +| learning_rate | 4.89e-05 | +| loss | -0.0412 | +| n_updates | 25192 | +| policy_gradient_loss | -0.0229 | +| value_loss | 6.93e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1410 | +| iterations | 2345 | +| time_elapsed | 3405 | +| total_timesteps | 4802560 | +| train/ | | +| approx_kl | 0.010598129 | +| clip_fraction | 0.304 | +| clip_range | 0.0738 | +| entropy_loss | -6.9 | +| explained_variance | 0.231 | +| learning_rate | 4.89e-05 | +| loss | -0.0308 | +| n_updates | 25196 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.00016 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1410 | +| iterations | 2346 | +| time_elapsed | 3406 | +| total_timesteps | 4804608 | +| train/ | | +| approx_kl | 0.010954035 | +| clip_fraction | 0.291 | +| clip_range | 0.0738 | +| entropy_loss | -6.89 | +| explained_variance | 0.284 | +| learning_rate | 4.89e-05 | +| loss | -0.0285 | +| n_updates | 25200 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000305 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1410 | +| iterations | 2347 | +| time_elapsed | 3407 | +| total_timesteps | 4806656 | +| train/ | | +| approx_kl | 0.011592452 | +| clip_fraction | 0.307 | +| clip_range | 0.0738 | +| entropy_loss | -6.77 | +| explained_variance | 0.42 | +| learning_rate | 4.89e-05 | +| loss | -0.0307 | +| n_updates | 25204 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.00018 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1410 | +| iterations | 2348 | +| time_elapsed | 3409 | +| total_timesteps | 4808704 | +| train/ | | +| approx_kl | 0.01380966 | +| clip_fraction | 0.356 | +| clip_range | 0.0738 | +| entropy_loss | -7.33 | +| explained_variance | 0.167 | +| learning_rate | 4.89e-05 | +| loss | -0.0327 | +| n_updates | 25208 | +| policy_gradient_loss | -0.0213 | +| value_loss | 9.61e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1410 | +| iterations | 2349 | +| time_elapsed | 3410 | +| total_timesteps | 4810752 | +| train/ | | +| approx_kl | 0.010256368 | +| clip_fraction | 0.318 | +| clip_range | 0.0738 | +| entropy_loss | -6.96 | +| explained_variance | 0.437 | +| learning_rate | 4.89e-05 | +| loss | -0.0269 | +| n_updates | 25212 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000145 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1410 | +| iterations | 2350 | +| time_elapsed | 3412 | +| total_timesteps | 4812800 | +| train/ | | +| approx_kl | 0.010911686 | +| clip_fraction | 0.316 | +| clip_range | 0.0738 | +| entropy_loss | -6.77 | +| explained_variance | 0.244 | +| learning_rate | 4.89e-05 | +| loss | -0.0329 | +| n_updates | 25216 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000473 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1410 | +| iterations | 2351 | +| time_elapsed | 3413 | +| total_timesteps | 4814848 | +| train/ | | +| approx_kl | 0.010161828 | +| clip_fraction | 0.294 | +| clip_range | 0.0738 | +| entropy_loss | -7.19 | +| explained_variance | 0.0657 | +| learning_rate | 4.89e-05 | +| loss | -0.0279 | +| n_updates | 25220 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000307 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1410 | +| iterations | 2352 | +| time_elapsed | 3414 | +| total_timesteps | 4816896 | +| train/ | | +| approx_kl | 0.009964806 | +| clip_fraction | 0.3 | +| clip_range | 0.0738 | +| entropy_loss | -7.35 | +| explained_variance | 0.199 | +| learning_rate | 4.89e-05 | +| loss | -0.04 | +| n_updates | 25224 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000116 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1410 | +| iterations | 2353 | +| time_elapsed | 3416 | +| total_timesteps | 4818944 | +| train/ | | +| approx_kl | 0.011108002 | +| clip_fraction | 0.315 | +| clip_range | 0.0738 | +| entropy_loss | -6.98 | +| explained_variance | 0.37 | +| learning_rate | 4.89e-05 | +| loss | -0.0367 | +| n_updates | 25228 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000282 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1410 | +| iterations | 2354 | +| time_elapsed | 3417 | +| total_timesteps | 4820992 | +| train/ | | +| approx_kl | 0.009614334 | +| clip_fraction | 0.291 | +| clip_range | 0.0738 | +| entropy_loss | -7.4 | +| explained_variance | 0.0406 | +| learning_rate | 4.89e-05 | +| loss | -0.0339 | +| n_updates | 25232 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.00032 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1410 | +| iterations | 2355 | +| time_elapsed | 3419 | +| total_timesteps | 4823040 | +| train/ | | +| approx_kl | 0.0107922945 | +| clip_fraction | 0.317 | +| clip_range | 0.0738 | +| entropy_loss | -7.06 | +| explained_variance | 0.379 | +| learning_rate | 4.89e-05 | +| loss | -0.0379 | +| n_updates | 25236 | +| policy_gradient_loss | -0.0222 | +| value_loss | 0.000193 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1410 | +| iterations | 2356 | +| time_elapsed | 3420 | +| total_timesteps | 4825088 | +| train/ | | +| approx_kl | 0.011302011 | +| clip_fraction | 0.323 | +| clip_range | 0.0738 | +| entropy_loss | -6.96 | +| explained_variance | 0.186 | +| learning_rate | 4.89e-05 | +| loss | -0.0327 | +| n_updates | 25240 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000196 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1410 | +| iterations | 2357 | +| time_elapsed | 3422 | +| total_timesteps | 4827136 | +| train/ | | +| approx_kl | 0.008919601 | +| clip_fraction | 0.282 | +| clip_range | 0.0738 | +| entropy_loss | -7.19 | +| explained_variance | 0.234 | +| learning_rate | 4.89e-05 | +| loss | -0.0283 | +| n_updates | 25244 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000182 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1410 | +| iterations | 2358 | +| time_elapsed | 3423 | +| total_timesteps | 4829184 | +| train/ | | +| approx_kl | 0.011731306 | +| clip_fraction | 0.337 | +| clip_range | 0.0738 | +| entropy_loss | -7.1 | +| explained_variance | 0.343 | +| learning_rate | 4.89e-05 | +| loss | -0.035 | +| n_updates | 25248 | +| policy_gradient_loss | -0.0223 | +| value_loss | 0.000149 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1410 | +| iterations | 2359 | +| time_elapsed | 3424 | +| total_timesteps | 4831232 | +| train/ | | +| approx_kl | 0.010736117 | +| clip_fraction | 0.314 | +| clip_range | 0.0738 | +| entropy_loss | -7.19 | +| explained_variance | 0.231 | +| learning_rate | 4.89e-05 | +| loss | -0.0376 | +| n_updates | 25252 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000173 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1410 | +| iterations | 2360 | +| time_elapsed | 3426 | +| total_timesteps | 4833280 | +| train/ | | +| approx_kl | 0.010387011 | +| clip_fraction | 0.299 | +| clip_range | 0.0738 | +| entropy_loss | -7.16 | +| explained_variance | 0.387 | +| learning_rate | 4.89e-05 | +| loss | -0.0279 | +| n_updates | 25256 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000136 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1410 | +| iterations | 2361 | +| time_elapsed | 3427 | +| total_timesteps | 4835328 | +| train/ | | +| approx_kl | 0.00956385 | +| clip_fraction | 0.307 | +| clip_range | 0.0738 | +| entropy_loss | -7.23 | +| explained_variance | 0.274 | +| learning_rate | 4.89e-05 | +| loss | -0.0319 | +| n_updates | 25260 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000192 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1410 | +| iterations | 2362 | +| time_elapsed | 3429 | +| total_timesteps | 4837376 | +| train/ | | +| approx_kl | 0.009380889 | +| clip_fraction | 0.287 | +| clip_range | 0.0738 | +| entropy_loss | -7.02 | +| explained_variance | 0.31 | +| learning_rate | 4.89e-05 | +| loss | -0.0226 | +| n_updates | 25264 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000171 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1410 | +| iterations | 2363 | +| time_elapsed | 3430 | +| total_timesteps | 4839424 | +| train/ | | +| approx_kl | 0.008469271 | +| clip_fraction | 0.3 | +| clip_range | 0.0738 | +| entropy_loss | -6.92 | +| explained_variance | 0.318 | +| learning_rate | 4.89e-05 | +| loss | -0.0272 | +| n_updates | 25268 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000179 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1410 | +| iterations | 2364 | +| time_elapsed | 3432 | +| total_timesteps | 4841472 | +| train/ | | +| approx_kl | 0.011063084 | +| clip_fraction | 0.329 | +| clip_range | 0.0738 | +| entropy_loss | -6.98 | +| explained_variance | 0.0435 | +| learning_rate | 4.89e-05 | +| loss | -0.0274 | +| n_updates | 25272 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000166 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1410 | +| iterations | 2365 | +| time_elapsed | 3433 | +| total_timesteps | 4843520 | +| train/ | | +| approx_kl | 0.009110063 | +| clip_fraction | 0.278 | +| clip_range | 0.0738 | +| entropy_loss | -7.24 | +| explained_variance | 0.0794 | +| learning_rate | 4.89e-05 | +| loss | -0.0297 | +| n_updates | 25276 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000266 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1410 | +| iterations | 2366 | +| time_elapsed | 3435 | +| total_timesteps | 4845568 | +| train/ | | +| approx_kl | 0.011087967 | +| clip_fraction | 0.325 | +| clip_range | 0.0738 | +| entropy_loss | -7.39 | +| explained_variance | -0.102 | +| learning_rate | 4.88e-05 | +| loss | -0.0337 | +| n_updates | 25280 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000166 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1410 | +| iterations | 2367 | +| time_elapsed | 3436 | +| total_timesteps | 4847616 | +| train/ | | +| approx_kl | 0.010512596 | +| clip_fraction | 0.293 | +| clip_range | 0.0738 | +| entropy_loss | -7.29 | +| explained_variance | 0.111 | +| learning_rate | 4.88e-05 | +| loss | -0.0318 | +| n_updates | 25284 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000251 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1410 | +| iterations | 2368 | +| time_elapsed | 3437 | +| total_timesteps | 4849664 | +| train/ | | +| approx_kl | 0.0119128 | +| clip_fraction | 0.331 | +| clip_range | 0.0738 | +| entropy_loss | -7.46 | +| explained_variance | -0.111 | +| learning_rate | 4.88e-05 | +| loss | -0.0339 | +| n_updates | 25288 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000164 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1410 | +| iterations | 2369 | +| time_elapsed | 3439 | +| total_timesteps | 4851712 | +| train/ | | +| approx_kl | 0.010060407 | +| clip_fraction | 0.3 | +| clip_range | 0.0738 | +| entropy_loss | -7.05 | +| explained_variance | -0.0229 | +| learning_rate | 4.88e-05 | +| loss | -0.0302 | +| n_updates | 25292 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000139 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1410 | +| iterations | 2370 | +| time_elapsed | 3440 | +| total_timesteps | 4853760 | +| train/ | | +| approx_kl | 0.009682765 | +| clip_fraction | 0.315 | +| clip_range | 0.0738 | +| entropy_loss | -6.78 | +| explained_variance | 0.259 | +| learning_rate | 4.88e-05 | +| loss | -0.0332 | +| n_updates | 25296 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000205 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1410 | +| iterations | 2371 | +| time_elapsed | 3442 | +| total_timesteps | 4855808 | +| train/ | | +| approx_kl | 0.012381984 | +| clip_fraction | 0.332 | +| clip_range | 0.0738 | +| entropy_loss | -6.96 | +| explained_variance | 0.292 | +| learning_rate | 4.88e-05 | +| loss | -0.0308 | +| n_updates | 25300 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000211 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1410 | +| iterations | 2372 | +| time_elapsed | 3443 | +| total_timesteps | 4857856 | +| train/ | | +| approx_kl | 0.012797577 | +| clip_fraction | 0.335 | +| clip_range | 0.0738 | +| entropy_loss | -7.24 | +| explained_variance | 0.289 | +| learning_rate | 4.88e-05 | +| loss | -0.0362 | +| n_updates | 25304 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000114 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1410 | +| iterations | 2373 | +| time_elapsed | 3445 | +| total_timesteps | 4859904 | +| train/ | | +| approx_kl | 0.010976298 | +| clip_fraction | 0.292 | +| clip_range | 0.0738 | +| entropy_loss | -6.79 | +| explained_variance | 0.218 | +| learning_rate | 4.88e-05 | +| loss | -0.0269 | +| n_updates | 25308 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000249 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1410 | +| iterations | 2374 | +| time_elapsed | 3446 | +| total_timesteps | 4861952 | +| train/ | | +| approx_kl | 0.010234013 | +| clip_fraction | 0.324 | +| clip_range | 0.0738 | +| entropy_loss | -7.31 | +| explained_variance | -0.0422 | +| learning_rate | 4.88e-05 | +| loss | -0.0394 | +| n_updates | 25312 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.00015 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1410 | +| iterations | 2375 | +| time_elapsed | 3447 | +| total_timesteps | 4864000 | +| train/ | | +| approx_kl | 0.009972942 | +| clip_fraction | 0.289 | +| clip_range | 0.0738 | +| entropy_loss | -7.25 | +| explained_variance | 0.137 | +| learning_rate | 4.88e-05 | +| loss | -0.0287 | +| n_updates | 25316 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.00021 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1410 | +| iterations | 2376 | +| time_elapsed | 3449 | +| total_timesteps | 4866048 | +| train/ | | +| approx_kl | 0.010446835 | +| clip_fraction | 0.303 | +| clip_range | 0.0738 | +| entropy_loss | -7.09 | +| explained_variance | 0.22 | +| learning_rate | 4.88e-05 | +| loss | -0.0346 | +| n_updates | 25320 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000133 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1410 | +| iterations | 2377 | +| time_elapsed | 3450 | +| total_timesteps | 4868096 | +| train/ | | +| approx_kl | 0.010213688 | +| clip_fraction | 0.321 | +| clip_range | 0.0738 | +| entropy_loss | -7.29 | +| explained_variance | -0.0302 | +| learning_rate | 4.88e-05 | +| loss | -0.035 | +| n_updates | 25324 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000125 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1410 | +| iterations | 2378 | +| time_elapsed | 3452 | +| total_timesteps | 4870144 | +| train/ | | +| approx_kl | 0.010627281 | +| clip_fraction | 0.31 | +| clip_range | 0.0738 | +| entropy_loss | -7.27 | +| explained_variance | -0.0828 | +| learning_rate | 4.88e-05 | +| loss | -0.0294 | +| n_updates | 25328 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000245 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1410 | +| iterations | 2379 | +| time_elapsed | 3453 | +| total_timesteps | 4872192 | +| train/ | | +| approx_kl | 0.011055058 | +| clip_fraction | 0.317 | +| clip_range | 0.0738 | +| entropy_loss | -7.29 | +| explained_variance | 0.0734 | +| learning_rate | 4.88e-05 | +| loss | -0.0294 | +| n_updates | 25332 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000167 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1410 | +| iterations | 2380 | +| time_elapsed | 3455 | +| total_timesteps | 4874240 | +| train/ | | +| approx_kl | 0.010955364 | +| clip_fraction | 0.29 | +| clip_range | 0.0738 | +| entropy_loss | -7.13 | +| explained_variance | 0.312 | +| learning_rate | 4.88e-05 | +| loss | -0.0306 | +| n_updates | 25336 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000197 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1410 | +| iterations | 2381 | +| time_elapsed | 3456 | +| total_timesteps | 4876288 | +| train/ | | +| approx_kl | 0.009946827 | +| clip_fraction | 0.289 | +| clip_range | 0.0738 | +| entropy_loss | -6.75 | +| explained_variance | 0.437 | +| learning_rate | 4.88e-05 | +| loss | -0.0289 | +| n_updates | 25340 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000179 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1410 | +| iterations | 2382 | +| time_elapsed | 3457 | +| total_timesteps | 4878336 | +| train/ | | +| approx_kl | 0.011282837 | +| clip_fraction | 0.328 | +| clip_range | 0.0738 | +| entropy_loss | -7.05 | +| explained_variance | 0.49 | +| learning_rate | 4.88e-05 | +| loss | -0.0323 | +| n_updates | 25344 | +| policy_gradient_loss | -0.0202 | +| value_loss | 6.78e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1410 | +| iterations | 2383 | +| time_elapsed | 3459 | +| total_timesteps | 4880384 | +| train/ | | +| approx_kl | 0.010501086 | +| clip_fraction | 0.298 | +| clip_range | 0.0738 | +| entropy_loss | -7.05 | +| explained_variance | 0.308 | +| learning_rate | 4.88e-05 | +| loss | -0.0304 | +| n_updates | 25348 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000204 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1410 | +| iterations | 2384 | +| time_elapsed | 3460 | +| total_timesteps | 4882432 | +| train/ | | +| approx_kl | 0.0120700095 | +| clip_fraction | 0.345 | +| clip_range | 0.0738 | +| entropy_loss | -6.88 | +| explained_variance | 0.682 | +| learning_rate | 4.88e-05 | +| loss | -0.0295 | +| n_updates | 25352 | +| policy_gradient_loss | -0.0206 | +| value_loss | 7.24e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1410 | +| iterations | 2385 | +| time_elapsed | 3462 | +| total_timesteps | 4884480 | +| train/ | | +| approx_kl | 0.010111978 | +| clip_fraction | 0.309 | +| clip_range | 0.0738 | +| entropy_loss | -7.23 | +| explained_variance | 0.427 | +| learning_rate | 4.88e-05 | +| loss | -0.0332 | +| n_updates | 25356 | +| policy_gradient_loss | -0.0201 | +| value_loss | 9.47e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1410 | +| iterations | 2386 | +| time_elapsed | 3463 | +| total_timesteps | 4886528 | +| train/ | | +| approx_kl | 0.008748362 | +| clip_fraction | 0.265 | +| clip_range | 0.0738 | +| entropy_loss | -7.45 | +| explained_variance | 0.0469 | +| learning_rate | 4.88e-05 | +| loss | -0.0274 | +| n_updates | 25360 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000242 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1410 | +| iterations | 2387 | +| time_elapsed | 3465 | +| total_timesteps | 4888576 | +| train/ | | +| approx_kl | 0.009939885 | +| clip_fraction | 0.295 | +| clip_range | 0.0738 | +| entropy_loss | -7.42 | +| explained_variance | -0.083 | +| learning_rate | 4.88e-05 | +| loss | -0.0238 | +| n_updates | 25364 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000171 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1410 | +| iterations | 2388 | +| time_elapsed | 3466 | +| total_timesteps | 4890624 | +| train/ | | +| approx_kl | 0.009487816 | +| clip_fraction | 0.306 | +| clip_range | 0.0738 | +| entropy_loss | -7.36 | +| explained_variance | 0.179 | +| learning_rate | 4.88e-05 | +| loss | -0.0272 | +| n_updates | 25368 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000269 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1410 | +| iterations | 2389 | +| time_elapsed | 3468 | +| total_timesteps | 4892672 | +| train/ | | +| approx_kl | 0.007924228 | +| clip_fraction | 0.261 | +| clip_range | 0.0738 | +| entropy_loss | -7.14 | +| explained_variance | 0.239 | +| learning_rate | 4.88e-05 | +| loss | -0.0283 | +| n_updates | 25372 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000316 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1410 | +| iterations | 2390 | +| time_elapsed | 3469 | +| total_timesteps | 4894720 | +| train/ | | +| approx_kl | 0.012063702 | +| clip_fraction | 0.337 | +| clip_range | 0.0738 | +| entropy_loss | -6.92 | +| explained_variance | 0.231 | +| learning_rate | 4.88e-05 | +| loss | -0.0398 | +| n_updates | 25376 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000173 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1410 | +| iterations | 2391 | +| time_elapsed | 3471 | +| total_timesteps | 4896768 | +| train/ | | +| approx_kl | 0.011422331 | +| clip_fraction | 0.334 | +| clip_range | 0.0738 | +| entropy_loss | -7.35 | +| explained_variance | 0.0459 | +| learning_rate | 4.88e-05 | +| loss | -0.0332 | +| n_updates | 25380 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1410 | +| iterations | 2392 | +| time_elapsed | 3472 | +| total_timesteps | 4898816 | +| train/ | | +| approx_kl | 0.010381527 | +| clip_fraction | 0.332 | +| clip_range | 0.0738 | +| entropy_loss | -7.54 | +| explained_variance | -0.000688 | +| learning_rate | 4.88e-05 | +| loss | -0.0321 | +| n_updates | 25384 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000125 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1410 | +| iterations | 2393 | +| time_elapsed | 3474 | +| total_timesteps | 4900864 | +| train/ | | +| approx_kl | 0.010867236 | +| clip_fraction | 0.308 | +| clip_range | 0.0738 | +| entropy_loss | -7.51 | +| explained_variance | -0.161 | +| learning_rate | 4.88e-05 | +| loss | -0.0313 | +| n_updates | 25388 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.00029 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1410 | +| iterations | 2394 | +| time_elapsed | 3475 | +| total_timesteps | 4902912 | +| train/ | | +| approx_kl | 0.0091368845 | +| clip_fraction | 0.298 | +| clip_range | 0.0738 | +| entropy_loss | -6.78 | +| explained_variance | 0.295 | +| learning_rate | 4.88e-05 | +| loss | -0.0272 | +| n_updates | 25392 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000144 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1410 | +| iterations | 2395 | +| time_elapsed | 3476 | +| total_timesteps | 4904960 | +| train/ | | +| approx_kl | 0.010980111 | +| clip_fraction | 0.32 | +| clip_range | 0.0738 | +| entropy_loss | -7.17 | +| explained_variance | 0.182 | +| learning_rate | 4.88e-05 | +| loss | -0.0323 | +| n_updates | 25396 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.00024 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1410 | +| iterations | 2396 | +| time_elapsed | 3478 | +| total_timesteps | 4907008 | +| train/ | | +| approx_kl | 0.010642236 | +| clip_fraction | 0.281 | +| clip_range | 0.0738 | +| entropy_loss | -6.73 | +| explained_variance | 0.277 | +| learning_rate | 4.88e-05 | +| loss | -0.0292 | +| n_updates | 25400 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000254 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1410 | +| iterations | 2397 | +| time_elapsed | 3479 | +| total_timesteps | 4909056 | +| train/ | | +| approx_kl | 0.014000384 | +| clip_fraction | 0.325 | +| clip_range | 0.0738 | +| entropy_loss | -6.94 | +| explained_variance | 0.494 | +| learning_rate | 4.88e-05 | +| loss | -0.036 | +| n_updates | 25404 | +| policy_gradient_loss | -0.0227 | +| value_loss | 0.000101 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1410 | +| iterations | 2398 | +| time_elapsed | 3481 | +| total_timesteps | 4911104 | +| train/ | | +| approx_kl | 0.011076478 | +| clip_fraction | 0.318 | +| clip_range | 0.0738 | +| entropy_loss | -7.12 | +| explained_variance | 0.303 | +| learning_rate | 4.88e-05 | +| loss | -0.0281 | +| n_updates | 25408 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000209 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1410 | +| iterations | 2399 | +| time_elapsed | 3482 | +| total_timesteps | 4913152 | +| train/ | | +| approx_kl | 0.008729024 | +| clip_fraction | 0.293 | +| clip_range | 0.0738 | +| entropy_loss | -7.24 | +| explained_variance | 0.205 | +| learning_rate | 4.88e-05 | +| loss | -0.0303 | +| n_updates | 25412 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000247 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1410 | +| iterations | 2400 | +| time_elapsed | 3483 | +| total_timesteps | 4915200 | +| train/ | | +| approx_kl | 0.0089027025 | +| clip_fraction | 0.307 | +| clip_range | 0.0738 | +| entropy_loss | -7.32 | +| explained_variance | 0.13 | +| learning_rate | 4.88e-05 | +| loss | -0.0319 | +| n_updates | 25416 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000371 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1410 | +| iterations | 2401 | +| time_elapsed | 3485 | +| total_timesteps | 4917248 | +| train/ | | +| approx_kl | 0.010337127 | +| clip_fraction | 0.323 | +| clip_range | 0.0738 | +| entropy_loss | -7.22 | +| explained_variance | 0.314 | +| learning_rate | 4.88e-05 | +| loss | -0.0346 | +| n_updates | 25420 | +| policy_gradient_loss | -0.0222 | +| value_loss | 0.000114 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1410 | +| iterations | 2402 | +| time_elapsed | 3486 | +| total_timesteps | 4919296 | +| train/ | | +| approx_kl | 0.009665649 | +| clip_fraction | 0.32 | +| clip_range | 0.0738 | +| entropy_loss | -7.11 | +| explained_variance | 0.507 | +| learning_rate | 4.88e-05 | +| loss | -0.0323 | +| n_updates | 25424 | +| policy_gradient_loss | -0.0216 | +| value_loss | 9.35e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1410 | +| iterations | 2403 | +| time_elapsed | 3488 | +| total_timesteps | 4921344 | +| train/ | | +| approx_kl | 0.011646155 | +| clip_fraction | 0.338 | +| clip_range | 0.0738 | +| entropy_loss | -7.5 | +| explained_variance | -0.395 | +| learning_rate | 4.88e-05 | +| loss | -0.0376 | +| n_updates | 25428 | +| policy_gradient_loss | -0.0255 | +| value_loss | 5.88e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1410 | +| iterations | 2404 | +| time_elapsed | 3489 | +| total_timesteps | 4923392 | +| train/ | | +| approx_kl | 0.013149515 | +| clip_fraction | 0.326 | +| clip_range | 0.0738 | +| entropy_loss | -7.15 | +| explained_variance | 0.0247 | +| learning_rate | 4.88e-05 | +| loss | -0.0296 | +| n_updates | 25432 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000225 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1410 | +| iterations | 2405 | +| time_elapsed | 3491 | +| total_timesteps | 4925440 | +| train/ | | +| approx_kl | 0.008768471 | +| clip_fraction | 0.314 | +| clip_range | 0.0738 | +| entropy_loss | -6.53 | +| explained_variance | 0.656 | +| learning_rate | 4.88e-05 | +| loss | -0.0338 | +| n_updates | 25436 | +| policy_gradient_loss | -0.0192 | +| value_loss | 9.32e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1410 | +| iterations | 2406 | +| time_elapsed | 3492 | +| total_timesteps | 4927488 | +| train/ | | +| approx_kl | 0.011348869 | +| clip_fraction | 0.308 | +| clip_range | 0.0738 | +| entropy_loss | -6.99 | +| explained_variance | 0.278 | +| learning_rate | 4.88e-05 | +| loss | -0.0345 | +| n_updates | 25440 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000189 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1410 | +| iterations | 2407 | +| time_elapsed | 3494 | +| total_timesteps | 4929536 | +| train/ | | +| approx_kl | 0.011755669 | +| clip_fraction | 0.334 | +| clip_range | 0.0738 | +| entropy_loss | -7.08 | +| explained_variance | 0.148 | +| learning_rate | 4.88e-05 | +| loss | -0.0406 | +| n_updates | 25444 | +| policy_gradient_loss | -0.0229 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1410 | +| iterations | 2408 | +| time_elapsed | 3495 | +| total_timesteps | 4931584 | +| train/ | | +| approx_kl | 0.011722317 | +| clip_fraction | 0.322 | +| clip_range | 0.0738 | +| entropy_loss | -7.29 | +| explained_variance | 0.0182 | +| learning_rate | 4.88e-05 | +| loss | -0.0301 | +| n_updates | 25448 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000139 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1410 | +| iterations | 2409 | +| time_elapsed | 3496 | +| total_timesteps | 4933632 | +| train/ | | +| approx_kl | 0.010939906 | +| clip_fraction | 0.304 | +| clip_range | 0.0738 | +| entropy_loss | -7.3 | +| explained_variance | 0.0928 | +| learning_rate | 4.88e-05 | +| loss | -0.0331 | +| n_updates | 25452 | +| policy_gradient_loss | -0.0212 | +| value_loss | 9.42e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1410 | +| iterations | 2410 | +| time_elapsed | 3498 | +| total_timesteps | 4935680 | +| train/ | | +| approx_kl | 0.010748789 | +| clip_fraction | 0.306 | +| clip_range | 0.0738 | +| entropy_loss | -7.17 | +| explained_variance | 0.0453 | +| learning_rate | 4.88e-05 | +| loss | -0.0302 | +| n_updates | 25456 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000239 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1410 | +| iterations | 2411 | +| time_elapsed | 3499 | +| total_timesteps | 4937728 | +| train/ | | +| approx_kl | 0.011904759 | +| clip_fraction | 0.291 | +| clip_range | 0.0738 | +| entropy_loss | -7.2 | +| explained_variance | 0.167 | +| learning_rate | 4.88e-05 | +| loss | -0.031 | +| n_updates | 25460 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000179 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1410 | +| iterations | 2412 | +| time_elapsed | 3501 | +| total_timesteps | 4939776 | +| train/ | | +| approx_kl | 0.009359887 | +| clip_fraction | 0.277 | +| clip_range | 0.0738 | +| entropy_loss | -7.09 | +| explained_variance | 0.0496 | +| learning_rate | 4.88e-05 | +| loss | -0.028 | +| n_updates | 25464 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000392 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1410 | +| iterations | 2413 | +| time_elapsed | 3502 | +| total_timesteps | 4941824 | +| train/ | | +| approx_kl | 0.010242045 | +| clip_fraction | 0.314 | +| clip_range | 0.0738 | +| entropy_loss | -7.01 | +| explained_variance | 0.197 | +| learning_rate | 4.88e-05 | +| loss | -0.0317 | +| n_updates | 25468 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000116 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1410 | +| iterations | 2414 | +| time_elapsed | 3504 | +| total_timesteps | 4943872 | +| train/ | | +| approx_kl | 0.01126976 | +| clip_fraction | 0.321 | +| clip_range | 0.0738 | +| entropy_loss | -7.17 | +| explained_variance | 0.213 | +| learning_rate | 4.88e-05 | +| loss | -0.0338 | +| n_updates | 25472 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.00017 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1410 | +| iterations | 2415 | +| time_elapsed | 3505 | +| total_timesteps | 4945920 | +| train/ | | +| approx_kl | 0.010844966 | +| clip_fraction | 0.301 | +| clip_range | 0.0738 | +| entropy_loss | -7.4 | +| explained_variance | -0.146 | +| learning_rate | 4.88e-05 | +| loss | -0.03 | +| n_updates | 25476 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000158 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1410 | +| iterations | 2416 | +| time_elapsed | 3507 | +| total_timesteps | 4947968 | +| train/ | | +| approx_kl | 0.01160324 | +| clip_fraction | 0.33 | +| clip_range | 0.0738 | +| entropy_loss | -7.34 | +| explained_variance | -0.149 | +| learning_rate | 4.88e-05 | +| loss | -0.0371 | +| n_updates | 25480 | +| policy_gradient_loss | -0.0221 | +| value_loss | 0.000147 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1410 | +| iterations | 2417 | +| time_elapsed | 3508 | +| total_timesteps | 4950016 | +| train/ | | +| approx_kl | 0.009570101 | +| clip_fraction | 0.296 | +| clip_range | 0.0738 | +| entropy_loss | -7.19 | +| explained_variance | 0.342 | +| learning_rate | 4.88e-05 | +| loss | -0.0345 | +| n_updates | 25484 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000149 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1410 | +| iterations | 2418 | +| time_elapsed | 3510 | +| total_timesteps | 4952064 | +| train/ | | +| approx_kl | 0.010398103 | +| clip_fraction | 0.289 | +| clip_range | 0.0738 | +| entropy_loss | -7.22 | +| explained_variance | -0.0281 | +| learning_rate | 4.88e-05 | +| loss | -0.0324 | +| n_updates | 25488 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000271 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1410 | +| iterations | 2419 | +| time_elapsed | 3511 | +| total_timesteps | 4954112 | +| train/ | | +| approx_kl | 0.008466249 | +| clip_fraction | 0.278 | +| clip_range | 0.0738 | +| entropy_loss | -7.07 | +| explained_variance | 0.303 | +| learning_rate | 4.88e-05 | +| loss | -0.0302 | +| n_updates | 25492 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000245 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1410 | +| iterations | 2420 | +| time_elapsed | 3512 | +| total_timesteps | 4956160 | +| train/ | | +| approx_kl | 0.008052442 | +| clip_fraction | 0.287 | +| clip_range | 0.0738 | +| entropy_loss | -6.79 | +| explained_variance | 0.293 | +| learning_rate | 4.88e-05 | +| loss | -0.0242 | +| n_updates | 25496 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000312 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1410 | +| iterations | 2421 | +| time_elapsed | 3514 | +| total_timesteps | 4958208 | +| train/ | | +| approx_kl | 0.010542527 | +| clip_fraction | 0.312 | +| clip_range | 0.0738 | +| entropy_loss | -7.04 | +| explained_variance | 0.399 | +| learning_rate | 4.88e-05 | +| loss | -0.0338 | +| n_updates | 25500 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000168 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1410 | +| iterations | 2422 | +| time_elapsed | 3515 | +| total_timesteps | 4960256 | +| train/ | | +| approx_kl | 0.011631027 | +| clip_fraction | 0.32 | +| clip_range | 0.0738 | +| entropy_loss | -7.38 | +| explained_variance | -0.131 | +| learning_rate | 4.88e-05 | +| loss | -0.0331 | +| n_updates | 25504 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000213 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1410 | +| iterations | 2423 | +| time_elapsed | 3517 | +| total_timesteps | 4962304 | +| train/ | | +| approx_kl | 0.010432174 | +| clip_fraction | 0.319 | +| clip_range | 0.0738 | +| entropy_loss | -7.01 | +| explained_variance | 0.38 | +| learning_rate | 4.88e-05 | +| loss | -0.0354 | +| n_updates | 25508 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000225 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1410 | +| iterations | 2424 | +| time_elapsed | 3518 | +| total_timesteps | 4964352 | +| train/ | | +| approx_kl | 0.0097469855 | +| clip_fraction | 0.333 | +| clip_range | 0.0738 | +| entropy_loss | -7.03 | +| explained_variance | 0.259 | +| learning_rate | 4.88e-05 | +| loss | -0.034 | +| n_updates | 25512 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000175 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1410 | +| iterations | 2425 | +| time_elapsed | 3520 | +| total_timesteps | 4966400 | +| train/ | | +| approx_kl | 0.011856817 | +| clip_fraction | 0.323 | +| clip_range | 0.0738 | +| entropy_loss | -7.42 | +| explained_variance | -0.138 | +| learning_rate | 4.88e-05 | +| loss | -0.0404 | +| n_updates | 25516 | +| policy_gradient_loss | -0.0227 | +| value_loss | 0.000128 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1410 | +| iterations | 2426 | +| time_elapsed | 3521 | +| total_timesteps | 4968448 | +| train/ | | +| approx_kl | 0.009707298 | +| clip_fraction | 0.29 | +| clip_range | 0.0738 | +| entropy_loss | -6.76 | +| explained_variance | 0.238 | +| learning_rate | 4.88e-05 | +| loss | -0.0277 | +| n_updates | 25520 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000554 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1410 | +| iterations | 2427 | +| time_elapsed | 3522 | +| total_timesteps | 4970496 | +| train/ | | +| approx_kl | 0.0102495095 | +| clip_fraction | 0.323 | +| clip_range | 0.0738 | +| entropy_loss | -7.25 | +| explained_variance | -0.217 | +| learning_rate | 4.88e-05 | +| loss | -0.0371 | +| n_updates | 25524 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000229 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1410 | +| iterations | 2428 | +| time_elapsed | 3524 | +| total_timesteps | 4972544 | +| train/ | | +| approx_kl | 0.01126613 | +| clip_fraction | 0.335 | +| clip_range | 0.0738 | +| entropy_loss | -7.3 | +| explained_variance | 0.15 | +| learning_rate | 4.88e-05 | +| loss | -0.0373 | +| n_updates | 25528 | +| policy_gradient_loss | -0.0226 | +| value_loss | 0.000156 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1410 | +| iterations | 2429 | +| time_elapsed | 3525 | +| total_timesteps | 4974592 | +| train/ | | +| approx_kl | 0.012113597 | +| clip_fraction | 0.362 | +| clip_range | 0.0738 | +| entropy_loss | -7.28 | +| explained_variance | 0.481 | +| learning_rate | 4.88e-05 | +| loss | -0.0375 | +| n_updates | 25532 | +| policy_gradient_loss | -0.0273 | +| value_loss | 7e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1410 | +| iterations | 2430 | +| time_elapsed | 3527 | +| total_timesteps | 4976640 | +| train/ | | +| approx_kl | 0.012007063 | +| clip_fraction | 0.296 | +| clip_range | 0.0738 | +| entropy_loss | -7.12 | +| explained_variance | 0.323 | +| learning_rate | 4.88e-05 | +| loss | -0.0335 | +| n_updates | 25536 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000126 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1410 | +| iterations | 2431 | +| time_elapsed | 3528 | +| total_timesteps | 4978688 | +| train/ | | +| approx_kl | 0.010165447 | +| clip_fraction | 0.312 | +| clip_range | 0.0738 | +| entropy_loss | -7.13 | +| explained_variance | 0.272 | +| learning_rate | 4.88e-05 | +| loss | -0.0283 | +| n_updates | 25540 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000177 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1410 | +| iterations | 2432 | +| time_elapsed | 3530 | +| total_timesteps | 4980736 | +| train/ | | +| approx_kl | 0.012083093 | +| clip_fraction | 0.319 | +| clip_range | 0.0738 | +| entropy_loss | -7.01 | +| explained_variance | 0.525 | +| learning_rate | 4.88e-05 | +| loss | -0.0282 | +| n_updates | 25544 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000129 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1410 | +| iterations | 2433 | +| time_elapsed | 3531 | +| total_timesteps | 4982784 | +| train/ | | +| approx_kl | 0.01213428 | +| clip_fraction | 0.303 | +| clip_range | 0.0738 | +| entropy_loss | -7.36 | +| explained_variance | -0.00969 | +| learning_rate | 4.88e-05 | +| loss | -0.0304 | +| n_updates | 25548 | +| policy_gradient_loss | -0.0199 | +| value_loss | 9.43e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1410 | +| iterations | 2434 | +| time_elapsed | 3532 | +| total_timesteps | 4984832 | +| train/ | | +| approx_kl | 0.011584269 | +| clip_fraction | 0.324 | +| clip_range | 0.0738 | +| entropy_loss | -7.06 | +| explained_variance | 0.339 | +| learning_rate | 4.88e-05 | +| loss | -0.0339 | +| n_updates | 25552 | +| policy_gradient_loss | -0.0207 | +| value_loss | 8.34e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1410 | +| iterations | 2435 | +| time_elapsed | 3534 | +| total_timesteps | 4986880 | +| train/ | | +| approx_kl | 0.009828491 | +| clip_fraction | 0.322 | +| clip_range | 0.0738 | +| entropy_loss | -7.11 | +| explained_variance | 0.291 | +| learning_rate | 4.88e-05 | +| loss | -0.0328 | +| n_updates | 25556 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000199 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1410 | +| iterations | 2436 | +| time_elapsed | 3535 | +| total_timesteps | 4988928 | +| train/ | | +| approx_kl | 0.011138295 | +| clip_fraction | 0.335 | +| clip_range | 0.0738 | +| entropy_loss | -7.38 | +| explained_variance | -0.0383 | +| learning_rate | 4.88e-05 | +| loss | -0.0352 | +| n_updates | 25560 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000151 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1410 | +| iterations | 2437 | +| time_elapsed | 3537 | +| total_timesteps | 4990976 | +| train/ | | +| approx_kl | 0.010193715 | +| clip_fraction | 0.296 | +| clip_range | 0.0738 | +| entropy_loss | -7.12 | +| explained_variance | 0.272 | +| learning_rate | 4.88e-05 | +| loss | -0.0298 | +| n_updates | 25564 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.00011 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1410 | +| iterations | 2438 | +| time_elapsed | 3538 | +| total_timesteps | 4993024 | +| train/ | | +| approx_kl | 0.010784576 | +| clip_fraction | 0.301 | +| clip_range | 0.0738 | +| entropy_loss | -7.21 | +| explained_variance | 0.466 | +| learning_rate | 4.88e-05 | +| loss | -0.0314 | +| n_updates | 25568 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.00014 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1410 | +| iterations | 2439 | +| time_elapsed | 3540 | +| total_timesteps | 4995072 | +| train/ | | +| approx_kl | 0.009360248 | +| clip_fraction | 0.302 | +| clip_range | 0.0738 | +| entropy_loss | -7.15 | +| explained_variance | 0.412 | +| learning_rate | 4.88e-05 | +| loss | -0.0317 | +| n_updates | 25572 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1411 | +| iterations | 2440 | +| time_elapsed | 3541 | +| total_timesteps | 4997120 | +| train/ | | +| approx_kl | 0.009014003 | +| clip_fraction | 0.299 | +| clip_range | 0.0738 | +| entropy_loss | -7.02 | +| explained_variance | 0.44 | +| learning_rate | 4.88e-05 | +| loss | -0.0333 | +| n_updates | 25576 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000134 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1411 | +| iterations | 2441 | +| time_elapsed | 3542 | +| total_timesteps | 4999168 | +| train/ | | +| approx_kl | 0.01039792 | +| clip_fraction | 0.301 | +| clip_range | 0.0738 | +| entropy_loss | -6.69 | +| explained_variance | 0.492 | +| learning_rate | 4.88e-05 | +| loss | -0.0273 | +| n_updates | 25580 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000143 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1411 | +| iterations | 2442 | +| time_elapsed | 3544 | +| total_timesteps | 5001216 | +| train/ | | +| approx_kl | 0.009741377 | +| clip_fraction | 0.288 | +| clip_range | 0.0738 | +| entropy_loss | -7.38 | +| explained_variance | 0.124 | +| learning_rate | 4.88e-05 | +| loss | -0.0376 | +| n_updates | 25584 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000234 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1410 | +| iterations | 2443 | +| time_elapsed | 3545 | +| total_timesteps | 5003264 | +| train/ | | +| approx_kl | 0.012993475 | +| clip_fraction | 0.351 | +| clip_range | 0.0737 | +| entropy_loss | -7.29 | +| explained_variance | 0.25 | +| learning_rate | 4.88e-05 | +| loss | -0.0364 | +| n_updates | 25588 | +| policy_gradient_loss | -0.0232 | +| value_loss | 0.000123 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1410 | +| iterations | 2444 | +| time_elapsed | 3547 | +| total_timesteps | 5005312 | +| train/ | | +| approx_kl | 0.011595301 | +| clip_fraction | 0.342 | +| clip_range | 0.0737 | +| entropy_loss | -7.46 | +| explained_variance | -0.286 | +| learning_rate | 4.88e-05 | +| loss | -0.0355 | +| n_updates | 25592 | +| policy_gradient_loss | -0.0245 | +| value_loss | 0.000124 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1410 | +| iterations | 2445 | +| time_elapsed | 3548 | +| total_timesteps | 5007360 | +| train/ | | +| approx_kl | 0.010411272 | +| clip_fraction | 0.328 | +| clip_range | 0.0737 | +| entropy_loss | -7.5 | +| explained_variance | -0.0229 | +| learning_rate | 4.88e-05 | +| loss | -0.0368 | +| n_updates | 25596 | +| policy_gradient_loss | -0.0229 | +| value_loss | 7.96e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1410 | +| iterations | 2446 | +| time_elapsed | 3550 | +| total_timesteps | 5009408 | +| train/ | | +| approx_kl | 0.011095822 | +| clip_fraction | 0.295 | +| clip_range | 0.0737 | +| entropy_loss | -7.14 | +| explained_variance | 0.182 | +| learning_rate | 4.88e-05 | +| loss | -0.0279 | +| n_updates | 25600 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000205 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1411 | +| iterations | 2447 | +| time_elapsed | 3551 | +| total_timesteps | 5011456 | +| train/ | | +| approx_kl | 0.013440883 | +| clip_fraction | 0.311 | +| clip_range | 0.0737 | +| entropy_loss | -6.85 | +| explained_variance | 0.347 | +| learning_rate | 4.88e-05 | +| loss | -0.0279 | +| n_updates | 25604 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000231 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1411 | +| iterations | 2448 | +| time_elapsed | 3553 | +| total_timesteps | 5013504 | +| train/ | | +| approx_kl | 0.010588102 | +| clip_fraction | 0.292 | +| clip_range | 0.0737 | +| entropy_loss | -7.04 | +| explained_variance | 0.122 | +| learning_rate | 4.88e-05 | +| loss | -0.0264 | +| n_updates | 25608 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000246 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1411 | +| iterations | 2449 | +| time_elapsed | 3554 | +| total_timesteps | 5015552 | +| train/ | | +| approx_kl | 0.0108797345 | +| clip_fraction | 0.332 | +| clip_range | 0.0737 | +| entropy_loss | -6.68 | +| explained_variance | 0.597 | +| learning_rate | 4.88e-05 | +| loss | -0.0336 | +| n_updates | 25612 | +| policy_gradient_loss | -0.0207 | +| value_loss | 8.79e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1411 | +| iterations | 2450 | +| time_elapsed | 3555 | +| total_timesteps | 5017600 | +| train/ | | +| approx_kl | 0.011676307 | +| clip_fraction | 0.342 | +| clip_range | 0.0737 | +| entropy_loss | -7.13 | +| explained_variance | -0.389 | +| learning_rate | 4.88e-05 | +| loss | -0.0302 | +| n_updates | 25616 | +| policy_gradient_loss | -0.0209 | +| value_loss | 9.21e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1411 | +| iterations | 2451 | +| time_elapsed | 3557 | +| total_timesteps | 5019648 | +| train/ | | +| approx_kl | 0.012050349 | +| clip_fraction | 0.328 | +| clip_range | 0.0737 | +| entropy_loss | -7.37 | +| explained_variance | -0.0683 | +| learning_rate | 4.88e-05 | +| loss | -0.0343 | +| n_updates | 25620 | +| policy_gradient_loss | -0.0221 | +| value_loss | 6.52e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1411 | +| iterations | 2452 | +| time_elapsed | 3558 | +| total_timesteps | 5021696 | +| train/ | | +| approx_kl | 0.010262249 | +| clip_fraction | 0.3 | +| clip_range | 0.0737 | +| entropy_loss | -6.83 | +| explained_variance | 0.215 | +| learning_rate | 4.88e-05 | +| loss | -0.0298 | +| n_updates | 25624 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.00016 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1411 | +| iterations | 2453 | +| time_elapsed | 3560 | +| total_timesteps | 5023744 | +| train/ | | +| approx_kl | 0.009148975 | +| clip_fraction | 0.312 | +| clip_range | 0.0737 | +| entropy_loss | -7.34 | +| explained_variance | 0.0511 | +| learning_rate | 4.88e-05 | +| loss | -0.0306 | +| n_updates | 25628 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000117 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1411 | +| iterations | 2454 | +| time_elapsed | 3561 | +| total_timesteps | 5025792 | +| train/ | | +| approx_kl | 0.012798975 | +| clip_fraction | 0.321 | +| clip_range | 0.0737 | +| entropy_loss | -7.44 | +| explained_variance | -0.183 | +| learning_rate | 4.88e-05 | +| loss | -0.028 | +| n_updates | 25632 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000114 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1411 | +| iterations | 2455 | +| time_elapsed | 3563 | +| total_timesteps | 5027840 | +| train/ | | +| approx_kl | 0.009770429 | +| clip_fraction | 0.297 | +| clip_range | 0.0737 | +| entropy_loss | -7.32 | +| explained_variance | 0.166 | +| learning_rate | 4.88e-05 | +| loss | -0.0312 | +| n_updates | 25636 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000181 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1411 | +| iterations | 2456 | +| time_elapsed | 3564 | +| total_timesteps | 5029888 | +| train/ | | +| approx_kl | 0.01162174 | +| clip_fraction | 0.288 | +| clip_range | 0.0737 | +| entropy_loss | -7.49 | +| explained_variance | -0.0593 | +| learning_rate | 4.88e-05 | +| loss | -0.0264 | +| n_updates | 25640 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000126 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1411 | +| iterations | 2457 | +| time_elapsed | 3565 | +| total_timesteps | 5031936 | +| train/ | | +| approx_kl | 0.009519128 | +| clip_fraction | 0.308 | +| clip_range | 0.0737 | +| entropy_loss | -7.09 | +| explained_variance | 0.512 | +| learning_rate | 4.88e-05 | +| loss | -0.0348 | +| n_updates | 25644 | +| policy_gradient_loss | -0.0203 | +| value_loss | 5.93e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1411 | +| iterations | 2458 | +| time_elapsed | 3567 | +| total_timesteps | 5033984 | +| train/ | | +| approx_kl | 0.009856163 | +| clip_fraction | 0.299 | +| clip_range | 0.0737 | +| entropy_loss | -7.14 | +| explained_variance | 0.386 | +| learning_rate | 4.88e-05 | +| loss | -0.0297 | +| n_updates | 25648 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000113 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1411 | +| iterations | 2459 | +| time_elapsed | 3568 | +| total_timesteps | 5036032 | +| train/ | | +| approx_kl | 0.013078462 | +| clip_fraction | 0.304 | +| clip_range | 0.0737 | +| entropy_loss | -7.03 | +| explained_variance | 0.363 | +| learning_rate | 4.88e-05 | +| loss | -0.0273 | +| n_updates | 25652 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000235 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1411 | +| iterations | 2460 | +| time_elapsed | 3570 | +| total_timesteps | 5038080 | +| train/ | | +| approx_kl | 0.011715941 | +| clip_fraction | 0.301 | +| clip_range | 0.0737 | +| entropy_loss | -7.12 | +| explained_variance | 0.414 | +| learning_rate | 4.88e-05 | +| loss | -0.0313 | +| n_updates | 25656 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000139 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1411 | +| iterations | 2461 | +| time_elapsed | 3571 | +| total_timesteps | 5040128 | +| train/ | | +| approx_kl | 0.009796385 | +| clip_fraction | 0.31 | +| clip_range | 0.0737 | +| entropy_loss | -7.23 | +| explained_variance | 0.116 | +| learning_rate | 4.88e-05 | +| loss | -0.0321 | +| n_updates | 25660 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.00016 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1411 | +| iterations | 2462 | +| time_elapsed | 3572 | +| total_timesteps | 5042176 | +| train/ | | +| approx_kl | 0.008808281 | +| clip_fraction | 0.299 | +| clip_range | 0.0737 | +| entropy_loss | -7.06 | +| explained_variance | 0.315 | +| learning_rate | 4.88e-05 | +| loss | -0.034 | +| n_updates | 25664 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000162 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1411 | +| iterations | 2463 | +| time_elapsed | 3574 | +| total_timesteps | 5044224 | +| train/ | | +| approx_kl | 0.010413549 | +| clip_fraction | 0.312 | +| clip_range | 0.0737 | +| entropy_loss | -7.01 | +| explained_variance | 0.367 | +| learning_rate | 4.88e-05 | +| loss | -0.0317 | +| n_updates | 25668 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000201 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1411 | +| iterations | 2464 | +| time_elapsed | 3575 | +| total_timesteps | 5046272 | +| train/ | | +| approx_kl | 0.010842226 | +| clip_fraction | 0.326 | +| clip_range | 0.0737 | +| entropy_loss | -7.38 | +| explained_variance | -0.132 | +| learning_rate | 4.88e-05 | +| loss | -0.0364 | +| n_updates | 25672 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000114 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1411 | +| iterations | 2465 | +| time_elapsed | 3577 | +| total_timesteps | 5048320 | +| train/ | | +| approx_kl | 0.010355175 | +| clip_fraction | 0.309 | +| clip_range | 0.0737 | +| entropy_loss | -7.29 | +| explained_variance | 0.213 | +| learning_rate | 4.88e-05 | +| loss | -0.0309 | +| n_updates | 25676 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000221 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1411 | +| iterations | 2466 | +| time_elapsed | 3578 | +| total_timesteps | 5050368 | +| train/ | | +| approx_kl | 0.007996281 | +| clip_fraction | 0.267 | +| clip_range | 0.0737 | +| entropy_loss | -6.7 | +| explained_variance | 0.139 | +| learning_rate | 4.88e-05 | +| loss | -0.0307 | +| n_updates | 25680 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000328 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1411 | +| iterations | 2467 | +| time_elapsed | 3580 | +| total_timesteps | 5052416 | +| train/ | | +| approx_kl | 0.010988824 | +| clip_fraction | 0.327 | +| clip_range | 0.0737 | +| entropy_loss | -7.07 | +| explained_variance | 0.296 | +| learning_rate | 4.88e-05 | +| loss | -0.0373 | +| n_updates | 25684 | +| policy_gradient_loss | -0.0222 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1411 | +| iterations | 2468 | +| time_elapsed | 3581 | +| total_timesteps | 5054464 | +| train/ | | +| approx_kl | 0.009798078 | +| clip_fraction | 0.322 | +| clip_range | 0.0737 | +| entropy_loss | -7.27 | +| explained_variance | 0.098 | +| learning_rate | 4.88e-05 | +| loss | -0.0281 | +| n_updates | 25688 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000202 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1411 | +| iterations | 2469 | +| time_elapsed | 3582 | +| total_timesteps | 5056512 | +| train/ | | +| approx_kl | 0.009825717 | +| clip_fraction | 0.29 | +| clip_range | 0.0737 | +| entropy_loss | -6.76 | +| explained_variance | 0.375 | +| learning_rate | 4.88e-05 | +| loss | -0.0335 | +| n_updates | 25692 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000241 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1411 | +| iterations | 2470 | +| time_elapsed | 3584 | +| total_timesteps | 5058560 | +| train/ | | +| approx_kl | 0.011221141 | +| clip_fraction | 0.331 | +| clip_range | 0.0737 | +| entropy_loss | -6.77 | +| explained_variance | 0.528 | +| learning_rate | 4.88e-05 | +| loss | -0.0348 | +| n_updates | 25696 | +| policy_gradient_loss | -0.0212 | +| value_loss | 9.81e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1411 | +| iterations | 2471 | +| time_elapsed | 3585 | +| total_timesteps | 5060608 | +| train/ | | +| approx_kl | 0.010972646 | +| clip_fraction | 0.335 | +| clip_range | 0.0737 | +| entropy_loss | -7.21 | +| explained_variance | -0.0323 | +| learning_rate | 4.88e-05 | +| loss | -0.0365 | +| n_updates | 25700 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000122 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1411 | +| iterations | 2472 | +| time_elapsed | 3587 | +| total_timesteps | 5062656 | +| train/ | | +| approx_kl | 0.011076303 | +| clip_fraction | 0.3 | +| clip_range | 0.0737 | +| entropy_loss | -7.18 | +| explained_variance | 0.095 | +| learning_rate | 4.88e-05 | +| loss | -0.0284 | +| n_updates | 25704 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000187 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1411 | +| iterations | 2473 | +| time_elapsed | 3588 | +| total_timesteps | 5064704 | +| train/ | | +| approx_kl | 0.011117512 | +| clip_fraction | 0.298 | +| clip_range | 0.0737 | +| entropy_loss | -7.49 | +| explained_variance | -0.178 | +| learning_rate | 4.88e-05 | +| loss | -0.0345 | +| n_updates | 25708 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000248 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1411 | +| iterations | 2474 | +| time_elapsed | 3590 | +| total_timesteps | 5066752 | +| train/ | | +| approx_kl | 0.011728363 | +| clip_fraction | 0.339 | +| clip_range | 0.0737 | +| entropy_loss | -7.36 | +| explained_variance | -0.0854 | +| learning_rate | 4.88e-05 | +| loss | -0.0359 | +| n_updates | 25712 | +| policy_gradient_loss | -0.0223 | +| value_loss | 0.000125 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1411 | +| iterations | 2475 | +| time_elapsed | 3591 | +| total_timesteps | 5068800 | +| train/ | | +| approx_kl | 0.009918903 | +| clip_fraction | 0.298 | +| clip_range | 0.0737 | +| entropy_loss | -6.99 | +| explained_variance | 0.116 | +| learning_rate | 4.88e-05 | +| loss | -0.0339 | +| n_updates | 25716 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000218 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1411 | +| iterations | 2476 | +| time_elapsed | 3592 | +| total_timesteps | 5070848 | +| train/ | | +| approx_kl | 0.011475708 | +| clip_fraction | 0.333 | +| clip_range | 0.0737 | +| entropy_loss | -7.18 | +| explained_variance | 0.169 | +| learning_rate | 4.88e-05 | +| loss | -0.0301 | +| n_updates | 25720 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000193 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1411 | +| iterations | 2477 | +| time_elapsed | 3594 | +| total_timesteps | 5072896 | +| train/ | | +| approx_kl | 0.012139374 | +| clip_fraction | 0.311 | +| clip_range | 0.0737 | +| entropy_loss | -7.37 | +| explained_variance | -0.0453 | +| learning_rate | 4.88e-05 | +| loss | -0.0265 | +| n_updates | 25724 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000128 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1411 | +| iterations | 2478 | +| time_elapsed | 3595 | +| total_timesteps | 5074944 | +| train/ | | +| approx_kl | 0.01169141 | +| clip_fraction | 0.33 | +| clip_range | 0.0737 | +| entropy_loss | -7.1 | +| explained_variance | 0.296 | +| learning_rate | 4.88e-05 | +| loss | -0.0318 | +| n_updates | 25728 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000179 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1411 | +| iterations | 2479 | +| time_elapsed | 3597 | +| total_timesteps | 5076992 | +| train/ | | +| approx_kl | 0.009550782 | +| clip_fraction | 0.308 | +| clip_range | 0.0737 | +| entropy_loss | -6.59 | +| explained_variance | 0.281 | +| learning_rate | 4.88e-05 | +| loss | -0.0267 | +| n_updates | 25732 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000267 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1411 | +| iterations | 2480 | +| time_elapsed | 3598 | +| total_timesteps | 5079040 | +| train/ | | +| approx_kl | 0.012383748 | +| clip_fraction | 0.31 | +| clip_range | 0.0737 | +| entropy_loss | -6.71 | +| explained_variance | 0.56 | +| learning_rate | 4.88e-05 | +| loss | -0.0301 | +| n_updates | 25736 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000146 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1411 | +| iterations | 2481 | +| time_elapsed | 3599 | +| total_timesteps | 5081088 | +| train/ | | +| approx_kl | 0.010812354 | +| clip_fraction | 0.332 | +| clip_range | 0.0737 | +| entropy_loss | -7.39 | +| explained_variance | -0.184 | +| learning_rate | 4.88e-05 | +| loss | -0.0326 | +| n_updates | 25740 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000123 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1411 | +| iterations | 2482 | +| time_elapsed | 3601 | +| total_timesteps | 5083136 | +| train/ | | +| approx_kl | 0.009758004 | +| clip_fraction | 0.313 | +| clip_range | 0.0737 | +| entropy_loss | -7.49 | +| explained_variance | -0.0612 | +| learning_rate | 4.88e-05 | +| loss | -0.03 | +| n_updates | 25744 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000181 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1411 | +| iterations | 2483 | +| time_elapsed | 3602 | +| total_timesteps | 5085184 | +| train/ | | +| approx_kl | 0.010999335 | +| clip_fraction | 0.306 | +| clip_range | 0.0737 | +| entropy_loss | -7.49 | +| explained_variance | 0.00101 | +| learning_rate | 4.88e-05 | +| loss | -0.0315 | +| n_updates | 25748 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000144 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1411 | +| iterations | 2484 | +| time_elapsed | 3604 | +| total_timesteps | 5087232 | +| train/ | | +| approx_kl | 0.011726165 | +| clip_fraction | 0.305 | +| clip_range | 0.0737 | +| entropy_loss | -7.09 | +| explained_variance | 0.303 | +| learning_rate | 4.88e-05 | +| loss | -0.0323 | +| n_updates | 25752 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000116 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1411 | +| iterations | 2485 | +| time_elapsed | 3605 | +| total_timesteps | 5089280 | +| train/ | | +| approx_kl | 0.01137932 | +| clip_fraction | 0.304 | +| clip_range | 0.0737 | +| entropy_loss | -6.92 | +| explained_variance | 0.0789 | +| learning_rate | 4.88e-05 | +| loss | -0.0332 | +| n_updates | 25756 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000418 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1411 | +| iterations | 2486 | +| time_elapsed | 3607 | +| total_timesteps | 5091328 | +| train/ | | +| approx_kl | 0.011180886 | +| clip_fraction | 0.315 | +| clip_range | 0.0737 | +| entropy_loss | -7.23 | +| explained_variance | 0.00601 | +| learning_rate | 4.88e-05 | +| loss | -0.0281 | +| n_updates | 25760 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000232 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1411 | +| iterations | 2487 | +| time_elapsed | 3608 | +| total_timesteps | 5093376 | +| train/ | | +| approx_kl | 0.007504238 | +| clip_fraction | 0.283 | +| clip_range | 0.0737 | +| entropy_loss | -7.46 | +| explained_variance | -0.0254 | +| learning_rate | 4.88e-05 | +| loss | -0.0278 | +| n_updates | 25764 | +| policy_gradient_loss | -0.0135 | +| value_loss | 0.000411 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1411 | +| iterations | 2488 | +| time_elapsed | 3609 | +| total_timesteps | 5095424 | +| train/ | | +| approx_kl | 0.0088409595 | +| clip_fraction | 0.312 | +| clip_range | 0.0737 | +| entropy_loss | -6.91 | +| explained_variance | 0.354 | +| learning_rate | 4.88e-05 | +| loss | -0.0305 | +| n_updates | 25768 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000174 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1411 | +| iterations | 2489 | +| time_elapsed | 3611 | +| total_timesteps | 5097472 | +| train/ | | +| approx_kl | 0.011550836 | +| clip_fraction | 0.344 | +| clip_range | 0.0737 | +| entropy_loss | -6.93 | +| explained_variance | 0.436 | +| learning_rate | 4.88e-05 | +| loss | -0.031 | +| n_updates | 25772 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000137 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1411 | +| iterations | 2490 | +| time_elapsed | 3612 | +| total_timesteps | 5099520 | +| train/ | | +| approx_kl | 0.01355564 | +| clip_fraction | 0.324 | +| clip_range | 0.0737 | +| entropy_loss | -7.05 | +| explained_variance | 0.16 | +| learning_rate | 4.88e-05 | +| loss | -0.0342 | +| n_updates | 25776 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000138 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1411 | +| iterations | 2491 | +| time_elapsed | 3614 | +| total_timesteps | 5101568 | +| train/ | | +| approx_kl | 0.0114498995 | +| clip_fraction | 0.32 | +| clip_range | 0.0737 | +| entropy_loss | -7.24 | +| explained_variance | 0.0587 | +| learning_rate | 4.88e-05 | +| loss | -0.0297 | +| n_updates | 25780 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.00017 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1411 | +| iterations | 2492 | +| time_elapsed | 3615 | +| total_timesteps | 5103616 | +| train/ | | +| approx_kl | 0.012216838 | +| clip_fraction | 0.311 | +| clip_range | 0.0737 | +| entropy_loss | -7.07 | +| explained_variance | 0.134 | +| learning_rate | 4.88e-05 | +| loss | -0.0321 | +| n_updates | 25784 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000214 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1411 | +| iterations | 2493 | +| time_elapsed | 3617 | +| total_timesteps | 5105664 | +| train/ | | +| approx_kl | 0.010886161 | +| clip_fraction | 0.312 | +| clip_range | 0.0737 | +| entropy_loss | -7.44 | +| explained_variance | -0.062 | +| learning_rate | 4.88e-05 | +| loss | -0.0309 | +| n_updates | 25788 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000223 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1411 | +| iterations | 2494 | +| time_elapsed | 3618 | +| total_timesteps | 5107712 | +| train/ | | +| approx_kl | 0.0103651695 | +| clip_fraction | 0.32 | +| clip_range | 0.0737 | +| entropy_loss | -7.47 | +| explained_variance | -0.0839 | +| learning_rate | 4.88e-05 | +| loss | -0.0292 | +| n_updates | 25792 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000226 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1411 | +| iterations | 2495 | +| time_elapsed | 3619 | +| total_timesteps | 5109760 | +| train/ | | +| approx_kl | 0.011405405 | +| clip_fraction | 0.308 | +| clip_range | 0.0737 | +| entropy_loss | -7.25 | +| explained_variance | 0.345 | +| learning_rate | 4.88e-05 | +| loss | -0.0327 | +| n_updates | 25796 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000168 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1411 | +| iterations | 2496 | +| time_elapsed | 3621 | +| total_timesteps | 5111808 | +| train/ | | +| approx_kl | 0.010145942 | +| clip_fraction | 0.317 | +| clip_range | 0.0737 | +| entropy_loss | -7 | +| explained_variance | 0.27 | +| learning_rate | 4.88e-05 | +| loss | -0.0303 | +| n_updates | 25800 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000216 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1411 | +| iterations | 2497 | +| time_elapsed | 3622 | +| total_timesteps | 5113856 | +| train/ | | +| approx_kl | 0.010290058 | +| clip_fraction | 0.315 | +| clip_range | 0.0737 | +| entropy_loss | -7.01 | +| explained_variance | 0.266 | +| learning_rate | 4.88e-05 | +| loss | -0.0256 | +| n_updates | 25804 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000198 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1411 | +| iterations | 2498 | +| time_elapsed | 3624 | +| total_timesteps | 5115904 | +| train/ | | +| approx_kl | 0.011055786 | +| clip_fraction | 0.333 | +| clip_range | 0.0737 | +| entropy_loss | -7.33 | +| explained_variance | -0.00994 | +| learning_rate | 4.88e-05 | +| loss | -0.0356 | +| n_updates | 25808 | +| policy_gradient_loss | -0.0239 | +| value_loss | 0.000119 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1411 | +| iterations | 2499 | +| time_elapsed | 3625 | +| total_timesteps | 5117952 | +| train/ | | +| approx_kl | 0.010288356 | +| clip_fraction | 0.294 | +| clip_range | 0.0737 | +| entropy_loss | -7.13 | +| explained_variance | 0.389 | +| learning_rate | 4.88e-05 | +| loss | -0.0303 | +| n_updates | 25812 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000172 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1411 | +| iterations | 2500 | +| time_elapsed | 3627 | +| total_timesteps | 5120000 | +| train/ | | +| approx_kl | 0.010209931 | +| clip_fraction | 0.326 | +| clip_range | 0.0737 | +| entropy_loss | -6.85 | +| explained_variance | 0.552 | +| learning_rate | 4.88e-05 | +| loss | -0.0333 | +| n_updates | 25816 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000148 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1411 | +| iterations | 2501 | +| time_elapsed | 3628 | +| total_timesteps | 5122048 | +| train/ | | +| approx_kl | 0.010566304 | +| clip_fraction | 0.289 | +| clip_range | 0.0737 | +| entropy_loss | -7.03 | +| explained_variance | 0.128 | +| learning_rate | 4.88e-05 | +| loss | -0.028 | +| n_updates | 25820 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000384 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1411 | +| iterations | 2502 | +| time_elapsed | 3629 | +| total_timesteps | 5124096 | +| train/ | | +| approx_kl | 0.010289796 | +| clip_fraction | 0.316 | +| clip_range | 0.0737 | +| entropy_loss | -7.05 | +| explained_variance | 0.318 | +| learning_rate | 4.88e-05 | +| loss | -0.0339 | +| n_updates | 25824 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.00024 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1411 | +| iterations | 2503 | +| time_elapsed | 3631 | +| total_timesteps | 5126144 | +| train/ | | +| approx_kl | 0.010404279 | +| clip_fraction | 0.322 | +| clip_range | 0.0737 | +| entropy_loss | -7.37 | +| explained_variance | -0.0791 | +| learning_rate | 4.88e-05 | +| loss | -0.0347 | +| n_updates | 25828 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.00021 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1411 | +| iterations | 2504 | +| time_elapsed | 3632 | +| total_timesteps | 5128192 | +| train/ | | +| approx_kl | 0.008560961 | +| clip_fraction | 0.306 | +| clip_range | 0.0737 | +| entropy_loss | -7.37 | +| explained_variance | 0.0766 | +| learning_rate | 4.88e-05 | +| loss | -0.0283 | +| n_updates | 25832 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000333 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1411 | +| iterations | 2505 | +| time_elapsed | 3634 | +| total_timesteps | 5130240 | +| train/ | | +| approx_kl | 0.010760149 | +| clip_fraction | 0.312 | +| clip_range | 0.0737 | +| entropy_loss | -7 | +| explained_variance | 0.429 | +| learning_rate | 4.88e-05 | +| loss | -0.0359 | +| n_updates | 25836 | +| policy_gradient_loss | -0.0221 | +| value_loss | 0.000141 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1411 | +| iterations | 2506 | +| time_elapsed | 3635 | +| total_timesteps | 5132288 | +| train/ | | +| approx_kl | 0.011383878 | +| clip_fraction | 0.283 | +| clip_range | 0.0737 | +| entropy_loss | -6.99 | +| explained_variance | 0.287 | +| learning_rate | 4.88e-05 | +| loss | -0.0191 | +| n_updates | 25840 | +| policy_gradient_loss | -0.0146 | +| value_loss | 0.000285 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1411 | +| iterations | 2507 | +| time_elapsed | 3637 | +| total_timesteps | 5134336 | +| train/ | | +| approx_kl | 0.013624304 | +| clip_fraction | 0.329 | +| clip_range | 0.0737 | +| entropy_loss | -7.06 | +| explained_variance | 0.00172 | +| learning_rate | 4.88e-05 | +| loss | -0.032 | +| n_updates | 25844 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.00016 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1411 | +| iterations | 2508 | +| time_elapsed | 3638 | +| total_timesteps | 5136384 | +| train/ | | +| approx_kl | 0.011993786 | +| clip_fraction | 0.329 | +| clip_range | 0.0737 | +| entropy_loss | -7.35 | +| explained_variance | 0.0157 | +| learning_rate | 4.88e-05 | +| loss | -0.032 | +| n_updates | 25848 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000163 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1411 | +| iterations | 2509 | +| time_elapsed | 3639 | +| total_timesteps | 5138432 | +| train/ | | +| approx_kl | 0.011604333 | +| clip_fraction | 0.321 | +| clip_range | 0.0737 | +| entropy_loss | -7.25 | +| explained_variance | 0.226 | +| learning_rate | 4.88e-05 | +| loss | -0.033 | +| n_updates | 25852 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000152 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1411 | +| iterations | 2510 | +| time_elapsed | 3641 | +| total_timesteps | 5140480 | +| train/ | | +| approx_kl | 0.012760627 | +| clip_fraction | 0.304 | +| clip_range | 0.0737 | +| entropy_loss | -7.22 | +| explained_variance | 0.333 | +| learning_rate | 4.88e-05 | +| loss | -0.0298 | +| n_updates | 25856 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000146 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1411 | +| iterations | 2511 | +| time_elapsed | 3642 | +| total_timesteps | 5142528 | +| train/ | | +| approx_kl | 0.010943847 | +| clip_fraction | 0.298 | +| clip_range | 0.0737 | +| entropy_loss | -7.27 | +| explained_variance | 0.181 | +| learning_rate | 4.88e-05 | +| loss | -0.0295 | +| n_updates | 25860 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000165 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1411 | +| iterations | 2512 | +| time_elapsed | 3644 | +| total_timesteps | 5144576 | +| train/ | | +| approx_kl | 0.013143702 | +| clip_fraction | 0.338 | +| clip_range | 0.0737 | +| entropy_loss | -7.18 | +| explained_variance | -0.0757 | +| learning_rate | 4.88e-05 | +| loss | -0.0331 | +| n_updates | 25864 | +| policy_gradient_loss | -0.022 | +| value_loss | 0.000125 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1411 | +| iterations | 2513 | +| time_elapsed | 3645 | +| total_timesteps | 5146624 | +| train/ | | +| approx_kl | 0.012915734 | +| clip_fraction | 0.341 | +| clip_range | 0.0737 | +| entropy_loss | -7.12 | +| explained_variance | 0.535 | +| learning_rate | 4.88e-05 | +| loss | -0.0333 | +| n_updates | 25868 | +| policy_gradient_loss | -0.0207 | +| value_loss | 8.18e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1411 | +| iterations | 2514 | +| time_elapsed | 3647 | +| total_timesteps | 5148672 | +| train/ | | +| approx_kl | 0.012354389 | +| clip_fraction | 0.304 | +| clip_range | 0.0737 | +| entropy_loss | -7.18 | +| explained_variance | 0.0381 | +| learning_rate | 4.88e-05 | +| loss | -0.0269 | +| n_updates | 25872 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.00018 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1411 | +| iterations | 2515 | +| time_elapsed | 3648 | +| total_timesteps | 5150720 | +| train/ | | +| approx_kl | 0.010068759 | +| clip_fraction | 0.309 | +| clip_range | 0.0737 | +| entropy_loss | -7.07 | +| explained_variance | 0.264 | +| learning_rate | 4.88e-05 | +| loss | -0.0286 | +| n_updates | 25876 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000185 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1411 | +| iterations | 2516 | +| time_elapsed | 3650 | +| total_timesteps | 5152768 | +| train/ | | +| approx_kl | 0.011366524 | +| clip_fraction | 0.341 | +| clip_range | 0.0737 | +| entropy_loss | -6.98 | +| explained_variance | 0.489 | +| learning_rate | 4.88e-05 | +| loss | -0.0295 | +| n_updates | 25880 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000115 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1411 | +| iterations | 2517 | +| time_elapsed | 3651 | +| total_timesteps | 5154816 | +| train/ | | +| approx_kl | 0.012060391 | +| clip_fraction | 0.302 | +| clip_range | 0.0737 | +| entropy_loss | -6.97 | +| explained_variance | 0.308 | +| learning_rate | 4.88e-05 | +| loss | -0.0306 | +| n_updates | 25884 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000204 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1411 | +| iterations | 2518 | +| time_elapsed | 3653 | +| total_timesteps | 5156864 | +| train/ | | +| approx_kl | 0.011605311 | +| clip_fraction | 0.316 | +| clip_range | 0.0737 | +| entropy_loss | -7.45 | +| explained_variance | -0.0127 | +| learning_rate | 4.88e-05 | +| loss | -0.03 | +| n_updates | 25888 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000176 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1411 | +| iterations | 2519 | +| time_elapsed | 3654 | +| total_timesteps | 5158912 | +| train/ | | +| approx_kl | 0.011820182 | +| clip_fraction | 0.324 | +| clip_range | 0.0737 | +| entropy_loss | -7.38 | +| explained_variance | 0.381 | +| learning_rate | 4.88e-05 | +| loss | -0.0312 | +| n_updates | 25892 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000139 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1411 | +| iterations | 2520 | +| time_elapsed | 3655 | +| total_timesteps | 5160960 | +| train/ | | +| approx_kl | 0.00976933 | +| clip_fraction | 0.278 | +| clip_range | 0.0737 | +| entropy_loss | -6.88 | +| explained_variance | 0.311 | +| learning_rate | 4.88e-05 | +| loss | -0.0271 | +| n_updates | 25896 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000394 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.385 | +| time/ | | +| fps | 1411 | +| iterations | 2521 | +| time_elapsed | 3657 | +| total_timesteps | 5163008 | +| train/ | | +| approx_kl | 0.01016598 | +| clip_fraction | 0.314 | +| clip_range | 0.0737 | +| entropy_loss | -7.19 | +| explained_variance | 0.358 | +| learning_rate | 4.88e-05 | +| loss | -0.0363 | +| n_updates | 25900 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000143 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.389 | +| time/ | | +| fps | 1411 | +| iterations | 2522 | +| time_elapsed | 3658 | +| total_timesteps | 5165056 | +| train/ | | +| approx_kl | 0.008763975 | +| clip_fraction | 0.281 | +| clip_range | 0.0737 | +| entropy_loss | -6.97 | +| explained_variance | 0.248 | +| learning_rate | 4.88e-05 | +| loss | -0.0241 | +| n_updates | 25904 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000392 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.387 | +| time/ | | +| fps | 1411 | +| iterations | 2523 | +| time_elapsed | 3660 | +| total_timesteps | 5167104 | +| train/ | | +| approx_kl | 0.010502126 | +| clip_fraction | 0.289 | +| clip_range | 0.0737 | +| entropy_loss | -7.01 | +| explained_variance | 0.0833 | +| learning_rate | 4.88e-05 | +| loss | -0.0354 | +| n_updates | 25908 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000276 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.389 | +| time/ | | +| fps | 1411 | +| iterations | 2524 | +| time_elapsed | 3661 | +| total_timesteps | 5169152 | +| train/ | | +| approx_kl | 0.011021999 | +| clip_fraction | 0.33 | +| clip_range | 0.0737 | +| entropy_loss | -7.19 | +| explained_variance | 0.115 | +| learning_rate | 4.88e-05 | +| loss | -0.0348 | +| n_updates | 25912 | +| policy_gradient_loss | -0.0225 | +| value_loss | 0.000223 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.388 | +| time/ | | +| fps | 1411 | +| iterations | 2525 | +| time_elapsed | 3663 | +| total_timesteps | 5171200 | +| train/ | | +| approx_kl | 0.009464483 | +| clip_fraction | 0.278 | +| clip_range | 0.0737 | +| entropy_loss | -7.15 | +| explained_variance | 0.202 | +| learning_rate | 4.88e-05 | +| loss | -0.0287 | +| n_updates | 25916 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000371 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.388 | +| time/ | | +| fps | 1411 | +| iterations | 2526 | +| time_elapsed | 3664 | +| total_timesteps | 5173248 | +| train/ | | +| approx_kl | 0.012139015 | +| clip_fraction | 0.314 | +| clip_range | 0.0737 | +| entropy_loss | -6.93 | +| explained_variance | 0.324 | +| learning_rate | 4.88e-05 | +| loss | -0.031 | +| n_updates | 25920 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000263 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1411 | +| iterations | 2527 | +| time_elapsed | 3666 | +| total_timesteps | 5175296 | +| train/ | | +| approx_kl | 0.011693418 | +| clip_fraction | 0.332 | +| clip_range | 0.0737 | +| entropy_loss | -7.01 | +| explained_variance | 0.387 | +| learning_rate | 4.88e-05 | +| loss | -0.0253 | +| n_updates | 25924 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000168 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1411 | +| iterations | 2528 | +| time_elapsed | 3667 | +| total_timesteps | 5177344 | +| train/ | | +| approx_kl | 0.009567197 | +| clip_fraction | 0.299 | +| clip_range | 0.0737 | +| entropy_loss | -7.36 | +| explained_variance | -0.164 | +| learning_rate | 4.88e-05 | +| loss | -0.0338 | +| n_updates | 25928 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000145 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.387 | +| time/ | | +| fps | 1411 | +| iterations | 2529 | +| time_elapsed | 3668 | +| total_timesteps | 5179392 | +| train/ | | +| approx_kl | 0.009868354 | +| clip_fraction | 0.313 | +| clip_range | 0.0737 | +| entropy_loss | -7.25 | +| explained_variance | 0.15 | +| learning_rate | 4.88e-05 | +| loss | -0.0362 | +| n_updates | 25932 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000212 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1411 | +| iterations | 2530 | +| time_elapsed | 3670 | +| total_timesteps | 5181440 | +| train/ | | +| approx_kl | 0.010410985 | +| clip_fraction | 0.322 | +| clip_range | 0.0737 | +| entropy_loss | -7.29 | +| explained_variance | 0.264 | +| learning_rate | 4.88e-05 | +| loss | -0.028 | +| n_updates | 25936 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000201 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.389 | +| time/ | | +| fps | 1411 | +| iterations | 2531 | +| time_elapsed | 3671 | +| total_timesteps | 5183488 | +| train/ | | +| approx_kl | 0.011694256 | +| clip_fraction | 0.315 | +| clip_range | 0.0737 | +| entropy_loss | -7.19 | +| explained_variance | 0.485 | +| learning_rate | 4.88e-05 | +| loss | -0.0368 | +| n_updates | 25940 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000137 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.389 | +| time/ | | +| fps | 1411 | +| iterations | 2532 | +| time_elapsed | 3673 | +| total_timesteps | 5185536 | +| train/ | | +| approx_kl | 0.011029923 | +| clip_fraction | 0.309 | +| clip_range | 0.0737 | +| entropy_loss | -7.13 | +| explained_variance | 0.21 | +| learning_rate | 4.88e-05 | +| loss | -0.037 | +| n_updates | 25944 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000248 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.387 | +| time/ | | +| fps | 1411 | +| iterations | 2533 | +| time_elapsed | 3674 | +| total_timesteps | 5187584 | +| train/ | | +| approx_kl | 0.0110531105 | +| clip_fraction | 0.32 | +| clip_range | 0.0737 | +| entropy_loss | -7.34 | +| explained_variance | 0.456 | +| learning_rate | 4.88e-05 | +| loss | -0.0364 | +| n_updates | 25948 | +| policy_gradient_loss | -0.0217 | +| value_loss | 9.02e-05 | +------------------------------------------ +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.388 | +| time/ | | +| fps | 1411 | +| iterations | 2534 | +| time_elapsed | 3676 | +| total_timesteps | 5189632 | +| train/ | | +| approx_kl | 0.0109197 | +| clip_fraction | 0.318 | +| clip_range | 0.0737 | +| entropy_loss | -7.13 | +| explained_variance | 0.368 | +| learning_rate | 4.88e-05 | +| loss | -0.0324 | +| n_updates | 25952 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000142 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.397 | +| time/ | | +| fps | 1411 | +| iterations | 2535 | +| time_elapsed | 3677 | +| total_timesteps | 5191680 | +| train/ | | +| approx_kl | 0.011351274 | +| clip_fraction | 0.297 | +| clip_range | 0.0737 | +| entropy_loss | -7.32 | +| explained_variance | -0.00886 | +| learning_rate | 4.88e-05 | +| loss | -0.0296 | +| n_updates | 25956 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000149 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.392 | +| time/ | | +| fps | 1411 | +| iterations | 2536 | +| time_elapsed | 3679 | +| total_timesteps | 5193728 | +| train/ | | +| approx_kl | 0.009994437 | +| clip_fraction | 0.295 | +| clip_range | 0.0737 | +| entropy_loss | -7.15 | +| explained_variance | 0.232 | +| learning_rate | 4.88e-05 | +| loss | -0.0319 | +| n_updates | 25960 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000187 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.397 | +| time/ | | +| fps | 1411 | +| iterations | 2537 | +| time_elapsed | 3680 | +| total_timesteps | 5195776 | +| train/ | | +| approx_kl | 0.011875622 | +| clip_fraction | 0.349 | +| clip_range | 0.0737 | +| entropy_loss | -7.21 | +| explained_variance | -0.119 | +| learning_rate | 4.88e-05 | +| loss | -0.0365 | +| n_updates | 25964 | +| policy_gradient_loss | -0.0219 | +| value_loss | 0.000126 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.394 | +| time/ | | +| fps | 1411 | +| iterations | 2538 | +| time_elapsed | 3681 | +| total_timesteps | 5197824 | +| train/ | | +| approx_kl | 0.010877389 | +| clip_fraction | 0.325 | +| clip_range | 0.0737 | +| entropy_loss | -7.2 | +| explained_variance | 0.324 | +| learning_rate | 4.88e-05 | +| loss | -0.0352 | +| n_updates | 25968 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000141 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.393 | +| time/ | | +| fps | 1411 | +| iterations | 2539 | +| time_elapsed | 3683 | +| total_timesteps | 5199872 | +| train/ | | +| approx_kl | 0.01062756 | +| clip_fraction | 0.312 | +| clip_range | 0.0737 | +| entropy_loss | -6.98 | +| explained_variance | 0.174 | +| learning_rate | 4.88e-05 | +| loss | -0.0342 | +| n_updates | 25972 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000273 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.393 | +| time/ | | +| fps | 1411 | +| iterations | 2540 | +| time_elapsed | 3684 | +| total_timesteps | 5201920 | +| train/ | | +| approx_kl | 0.010072025 | +| clip_fraction | 0.322 | +| clip_range | 0.0737 | +| entropy_loss | -6.54 | +| explained_variance | 0.406 | +| learning_rate | 4.88e-05 | +| loss | -0.0274 | +| n_updates | 25976 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000337 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.395 | +| time/ | | +| fps | 1411 | +| iterations | 2541 | +| time_elapsed | 3686 | +| total_timesteps | 5203968 | +| train/ | | +| approx_kl | 0.010904422 | +| clip_fraction | 0.336 | +| clip_range | 0.0737 | +| entropy_loss | -7.38 | +| explained_variance | -0.264 | +| learning_rate | 4.88e-05 | +| loss | -0.0393 | +| n_updates | 25980 | +| policy_gradient_loss | -0.0239 | +| value_loss | 0.000131 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.395 | +| time/ | | +| fps | 1411 | +| iterations | 2542 | +| time_elapsed | 3687 | +| total_timesteps | 5206016 | +| train/ | | +| approx_kl | 0.011202026 | +| clip_fraction | 0.321 | +| clip_range | 0.0737 | +| entropy_loss | -7.11 | +| explained_variance | 0.345 | +| learning_rate | 4.88e-05 | +| loss | -0.0362 | +| n_updates | 25984 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000115 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.393 | +| time/ | | +| fps | 1411 | +| iterations | 2543 | +| time_elapsed | 3689 | +| total_timesteps | 5208064 | +| train/ | | +| approx_kl | 0.011399442 | +| clip_fraction | 0.324 | +| clip_range | 0.0737 | +| entropy_loss | -7.33 | +| explained_variance | -0.131 | +| learning_rate | 4.88e-05 | +| loss | -0.0374 | +| n_updates | 25988 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000154 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.39 | +| time/ | | +| fps | 1411 | +| iterations | 2544 | +| time_elapsed | 3690 | +| total_timesteps | 5210112 | +| train/ | | +| approx_kl | 0.012818821 | +| clip_fraction | 0.313 | +| clip_range | 0.0737 | +| entropy_loss | -7.11 | +| explained_variance | 0.167 | +| learning_rate | 4.88e-05 | +| loss | -0.0373 | +| n_updates | 25992 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000128 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.394 | +| time/ | | +| fps | 1411 | +| iterations | 2545 | +| time_elapsed | 3692 | +| total_timesteps | 5212160 | +| train/ | | +| approx_kl | 0.013368463 | +| clip_fraction | 0.309 | +| clip_range | 0.0737 | +| entropy_loss | -7.43 | +| explained_variance | -0.0465 | +| learning_rate | 4.88e-05 | +| loss | -0.0333 | +| n_updates | 25996 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000176 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.394 | +| time/ | | +| fps | 1411 | +| iterations | 2546 | +| time_elapsed | 3693 | +| total_timesteps | 5214208 | +| train/ | | +| approx_kl | 0.011102712 | +| clip_fraction | 0.311 | +| clip_range | 0.0737 | +| entropy_loss | -6.98 | +| explained_variance | 0.304 | +| learning_rate | 4.88e-05 | +| loss | -0.029 | +| n_updates | 26000 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000166 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.386 | +| time/ | | +| fps | 1411 | +| iterations | 2547 | +| time_elapsed | 3694 | +| total_timesteps | 5216256 | +| train/ | | +| approx_kl | 0.011056447 | +| clip_fraction | 0.35 | +| clip_range | 0.0737 | +| entropy_loss | -7.35 | +| explained_variance | -0.0113 | +| learning_rate | 4.88e-05 | +| loss | -0.0372 | +| n_updates | 26004 | +| policy_gradient_loss | -0.0224 | +| value_loss | 7.61e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1411 | +| iterations | 2548 | +| time_elapsed | 3696 | +| total_timesteps | 5218304 | +| train/ | | +| approx_kl | 0.00957859 | +| clip_fraction | 0.28 | +| clip_range | 0.0737 | +| entropy_loss | -6.68 | +| explained_variance | 0.323 | +| learning_rate | 4.88e-05 | +| loss | -0.0113 | +| n_updates | 26008 | +| policy_gradient_loss | -0.0129 | +| value_loss | 0.00031 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.384 | +| time/ | | +| fps | 1411 | +| iterations | 2549 | +| time_elapsed | 3697 | +| total_timesteps | 5220352 | +| train/ | | +| approx_kl | 0.010210717 | +| clip_fraction | 0.324 | +| clip_range | 0.0737 | +| entropy_loss | -6.97 | +| explained_variance | 0.279 | +| learning_rate | 4.88e-05 | +| loss | -0.026 | +| n_updates | 26012 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000177 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.384 | +| time/ | | +| fps | 1411 | +| iterations | 2550 | +| time_elapsed | 3699 | +| total_timesteps | 5222400 | +| train/ | | +| approx_kl | 0.012370659 | +| clip_fraction | 0.344 | +| clip_range | 0.0737 | +| entropy_loss | -7.1 | +| explained_variance | 0.318 | +| learning_rate | 4.88e-05 | +| loss | -0.0327 | +| n_updates | 26016 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000166 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.385 | +| time/ | | +| fps | 1411 | +| iterations | 2551 | +| time_elapsed | 3700 | +| total_timesteps | 5224448 | +| train/ | | +| approx_kl | 0.012360643 | +| clip_fraction | 0.334 | +| clip_range | 0.0737 | +| entropy_loss | -7.17 | +| explained_variance | 0.0858 | +| learning_rate | 4.88e-05 | +| loss | -0.0325 | +| n_updates | 26020 | +| policy_gradient_loss | -0.0229 | +| value_loss | 0.000109 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1411 | +| iterations | 2552 | +| time_elapsed | 3702 | +| total_timesteps | 5226496 | +| train/ | | +| approx_kl | 0.012881529 | +| clip_fraction | 0.34 | +| clip_range | 0.0737 | +| entropy_loss | -7.05 | +| explained_variance | 0.301 | +| learning_rate | 4.88e-05 | +| loss | -0.0329 | +| n_updates | 26024 | +| policy_gradient_loss | -0.0225 | +| value_loss | 0.000249 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.385 | +| time/ | | +| fps | 1411 | +| iterations | 2553 | +| time_elapsed | 3703 | +| total_timesteps | 5228544 | +| train/ | | +| approx_kl | 0.009138374 | +| clip_fraction | 0.296 | +| clip_range | 0.0737 | +| entropy_loss | -7.06 | +| explained_variance | 0.362 | +| learning_rate | 4.88e-05 | +| loss | -0.0361 | +| n_updates | 26028 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000136 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.388 | +| time/ | | +| fps | 1411 | +| iterations | 2554 | +| time_elapsed | 3704 | +| total_timesteps | 5230592 | +| train/ | | +| approx_kl | 0.010414001 | +| clip_fraction | 0.322 | +| clip_range | 0.0737 | +| entropy_loss | -7.28 | +| explained_variance | 0.0228 | +| learning_rate | 4.88e-05 | +| loss | -0.0363 | +| n_updates | 26032 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000345 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.386 | +| time/ | | +| fps | 1411 | +| iterations | 2555 | +| time_elapsed | 3706 | +| total_timesteps | 5232640 | +| train/ | | +| approx_kl | 0.013363705 | +| clip_fraction | 0.326 | +| clip_range | 0.0737 | +| entropy_loss | -6.92 | +| explained_variance | 0.4 | +| learning_rate | 4.88e-05 | +| loss | -0.0359 | +| n_updates | 26036 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000129 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1411 | +| iterations | 2556 | +| time_elapsed | 3707 | +| total_timesteps | 5234688 | +| train/ | | +| approx_kl | 0.011515075 | +| clip_fraction | 0.334 | +| clip_range | 0.0737 | +| entropy_loss | -7.28 | +| explained_variance | 0.024 | +| learning_rate | 4.88e-05 | +| loss | -0.0287 | +| n_updates | 26040 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000135 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1411 | +| iterations | 2557 | +| time_elapsed | 3709 | +| total_timesteps | 5236736 | +| train/ | | +| approx_kl | 0.009717859 | +| clip_fraction | 0.281 | +| clip_range | 0.0737 | +| entropy_loss | -7.13 | +| explained_variance | 0.135 | +| learning_rate | 4.88e-05 | +| loss | -0.0335 | +| n_updates | 26044 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000286 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1411 | +| iterations | 2558 | +| time_elapsed | 3710 | +| total_timesteps | 5238784 | +| train/ | | +| approx_kl | 0.010016095 | +| clip_fraction | 0.335 | +| clip_range | 0.0737 | +| entropy_loss | -6.86 | +| explained_variance | 0.527 | +| learning_rate | 4.88e-05 | +| loss | -0.0308 | +| n_updates | 26048 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000155 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1411 | +| iterations | 2559 | +| time_elapsed | 3711 | +| total_timesteps | 5240832 | +| train/ | | +| approx_kl | 0.010941438 | +| clip_fraction | 0.294 | +| clip_range | 0.0737 | +| entropy_loss | -6.92 | +| explained_variance | 0.314 | +| learning_rate | 4.88e-05 | +| loss | -0.0315 | +| n_updates | 26052 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000246 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1411 | +| iterations | 2560 | +| time_elapsed | 3713 | +| total_timesteps | 5242880 | +| train/ | | +| approx_kl | 0.01045426 | +| clip_fraction | 0.314 | +| clip_range | 0.0737 | +| entropy_loss | -7.02 | +| explained_variance | 0.131 | +| learning_rate | 4.88e-05 | +| loss | -0.0318 | +| n_updates | 26056 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000243 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1411 | +| iterations | 2561 | +| time_elapsed | 3714 | +| total_timesteps | 5244928 | +| train/ | | +| approx_kl | 0.0126318075 | +| clip_fraction | 0.32 | +| clip_range | 0.0737 | +| entropy_loss | -7.41 | +| explained_variance | -0.115 | +| learning_rate | 4.88e-05 | +| loss | -0.0314 | +| n_updates | 26060 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000205 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1411 | +| iterations | 2562 | +| time_elapsed | 3716 | +| total_timesteps | 5246976 | +| train/ | | +| approx_kl | 0.012299089 | +| clip_fraction | 0.31 | +| clip_range | 0.0737 | +| entropy_loss | -7.24 | +| explained_variance | 0.0168 | +| learning_rate | 4.88e-05 | +| loss | -0.0309 | +| n_updates | 26064 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000271 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1411 | +| iterations | 2563 | +| time_elapsed | 3717 | +| total_timesteps | 5249024 | +| train/ | | +| approx_kl | 0.010781663 | +| clip_fraction | 0.32 | +| clip_range | 0.0737 | +| entropy_loss | -7.41 | +| explained_variance | -0.169 | +| learning_rate | 4.88e-05 | +| loss | -0.036 | +| n_updates | 26068 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.00015 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1411 | +| iterations | 2564 | +| time_elapsed | 3719 | +| total_timesteps | 5251072 | +| train/ | | +| approx_kl | 0.00986864 | +| clip_fraction | 0.298 | +| clip_range | 0.0737 | +| entropy_loss | -6.68 | +| explained_variance | 0.188 | +| learning_rate | 4.88e-05 | +| loss | -0.0264 | +| n_updates | 26072 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000355 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1411 | +| iterations | 2565 | +| time_elapsed | 3720 | +| total_timesteps | 5253120 | +| train/ | | +| approx_kl | 0.011578577 | +| clip_fraction | 0.339 | +| clip_range | 0.0737 | +| entropy_loss | -6.92 | +| explained_variance | 0.314 | +| learning_rate | 4.88e-05 | +| loss | -0.0344 | +| n_updates | 26076 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000212 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1411 | +| iterations | 2566 | +| time_elapsed | 3722 | +| total_timesteps | 5255168 | +| train/ | | +| approx_kl | 0.011296375 | +| clip_fraction | 0.313 | +| clip_range | 0.0737 | +| entropy_loss | -6.89 | +| explained_variance | 0.284 | +| learning_rate | 4.88e-05 | +| loss | -0.0262 | +| n_updates | 26080 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000449 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1411 | +| iterations | 2567 | +| time_elapsed | 3723 | +| total_timesteps | 5257216 | +| train/ | | +| approx_kl | 0.0118344175 | +| clip_fraction | 0.34 | +| clip_range | 0.0737 | +| entropy_loss | -7.2 | +| explained_variance | 0.341 | +| learning_rate | 4.88e-05 | +| loss | -0.0394 | +| n_updates | 26084 | +| policy_gradient_loss | -0.024 | +| value_loss | 8.96e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1411 | +| iterations | 2568 | +| time_elapsed | 3725 | +| total_timesteps | 5259264 | +| train/ | | +| approx_kl | 0.012916213 | +| clip_fraction | 0.347 | +| clip_range | 0.0737 | +| entropy_loss | -7.18 | +| explained_variance | -0.0503 | +| learning_rate | 4.88e-05 | +| loss | -0.0357 | +| n_updates | 26088 | +| policy_gradient_loss | -0.022 | +| value_loss | 0.000172 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1411 | +| iterations | 2569 | +| time_elapsed | 3726 | +| total_timesteps | 5261312 | +| train/ | | +| approx_kl | 0.012677284 | +| clip_fraction | 0.345 | +| clip_range | 0.0737 | +| entropy_loss | -7.43 | +| explained_variance | -0.0384 | +| learning_rate | 4.88e-05 | +| loss | -0.0353 | +| n_updates | 26092 | +| policy_gradient_loss | -0.0224 | +| value_loss | 0.000184 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.386 | +| time/ | | +| fps | 1411 | +| iterations | 2570 | +| time_elapsed | 3727 | +| total_timesteps | 5263360 | +| train/ | | +| approx_kl | 0.01093749 | +| clip_fraction | 0.318 | +| clip_range | 0.0737 | +| entropy_loss | -6.81 | +| explained_variance | 0.243 | +| learning_rate | 4.88e-05 | +| loss | -0.0295 | +| n_updates | 26096 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.00038 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.391 | +| time/ | | +| fps | 1411 | +| iterations | 2571 | +| time_elapsed | 3729 | +| total_timesteps | 5265408 | +| train/ | | +| approx_kl | 0.011734954 | +| clip_fraction | 0.332 | +| clip_range | 0.0737 | +| entropy_loss | -7.15 | +| explained_variance | 0.149 | +| learning_rate | 4.87e-05 | +| loss | -0.0397 | +| n_updates | 26100 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000319 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.389 | +| time/ | | +| fps | 1411 | +| iterations | 2572 | +| time_elapsed | 3730 | +| total_timesteps | 5267456 | +| train/ | | +| approx_kl | 0.011772634 | +| clip_fraction | 0.321 | +| clip_range | 0.0737 | +| entropy_loss | -7.09 | +| explained_variance | 0.131 | +| learning_rate | 4.87e-05 | +| loss | -0.033 | +| n_updates | 26104 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000334 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.389 | +| time/ | | +| fps | 1411 | +| iterations | 2573 | +| time_elapsed | 3732 | +| total_timesteps | 5269504 | +| train/ | | +| approx_kl | 0.012011273 | +| clip_fraction | 0.362 | +| clip_range | 0.0737 | +| entropy_loss | -7.23 | +| explained_variance | -0.0584 | +| learning_rate | 4.87e-05 | +| loss | -0.0414 | +| n_updates | 26108 | +| policy_gradient_loss | -0.025 | +| value_loss | 0.000113 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.391 | +| time/ | | +| fps | 1411 | +| iterations | 2574 | +| time_elapsed | 3733 | +| total_timesteps | 5271552 | +| train/ | | +| approx_kl | 0.0118605485 | +| clip_fraction | 0.342 | +| clip_range | 0.0737 | +| entropy_loss | -7.24 | +| explained_variance | 0.0987 | +| learning_rate | 4.87e-05 | +| loss | -0.0359 | +| n_updates | 26112 | +| policy_gradient_loss | -0.0227 | +| value_loss | 0.000195 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.393 | +| time/ | | +| fps | 1411 | +| iterations | 2575 | +| time_elapsed | 3735 | +| total_timesteps | 5273600 | +| train/ | | +| approx_kl | 0.009096196 | +| clip_fraction | 0.278 | +| clip_range | 0.0737 | +| entropy_loss | -7.04 | +| explained_variance | 0.108 | +| learning_rate | 4.87e-05 | +| loss | -0.0337 | +| n_updates | 26116 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000193 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.398 | +| time/ | | +| fps | 1411 | +| iterations | 2576 | +| time_elapsed | 3736 | +| total_timesteps | 5275648 | +| train/ | | +| approx_kl | 0.010612579 | +| clip_fraction | 0.348 | +| clip_range | 0.0737 | +| entropy_loss | -7.06 | +| explained_variance | 0.359 | +| learning_rate | 4.87e-05 | +| loss | -0.0359 | +| n_updates | 26120 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000155 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.401 | +| time/ | | +| fps | 1411 | +| iterations | 2577 | +| time_elapsed | 3737 | +| total_timesteps | 5277696 | +| train/ | | +| approx_kl | 0.012189671 | +| clip_fraction | 0.3 | +| clip_range | 0.0737 | +| entropy_loss | -7.2 | +| explained_variance | 0.216 | +| learning_rate | 4.87e-05 | +| loss | -0.0295 | +| n_updates | 26124 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000172 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.4 | +| time/ | | +| fps | 1411 | +| iterations | 2578 | +| time_elapsed | 3739 | +| total_timesteps | 5279744 | +| train/ | | +| approx_kl | 0.010541787 | +| clip_fraction | 0.286 | +| clip_range | 0.0737 | +| entropy_loss | -6.68 | +| explained_variance | 0.335 | +| learning_rate | 4.87e-05 | +| loss | -0.0302 | +| n_updates | 26128 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000314 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.404 | +| time/ | | +| fps | 1411 | +| iterations | 2579 | +| time_elapsed | 3740 | +| total_timesteps | 5281792 | +| train/ | | +| approx_kl | 0.010365845 | +| clip_fraction | 0.343 | +| clip_range | 0.0737 | +| entropy_loss | -7.1 | +| explained_variance | 0.216 | +| learning_rate | 4.87e-05 | +| loss | -0.0321 | +| n_updates | 26132 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000154 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.406 | +| time/ | | +| fps | 1411 | +| iterations | 2580 | +| time_elapsed | 3742 | +| total_timesteps | 5283840 | +| train/ | | +| approx_kl | 0.011499506 | +| clip_fraction | 0.328 | +| clip_range | 0.0737 | +| entropy_loss | -7.25 | +| explained_variance | 0.176 | +| learning_rate | 4.87e-05 | +| loss | -0.0329 | +| n_updates | 26136 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000304 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.396 | +| time/ | | +| fps | 1411 | +| iterations | 2581 | +| time_elapsed | 3743 | +| total_timesteps | 5285888 | +| train/ | | +| approx_kl | 0.009668254 | +| clip_fraction | 0.286 | +| clip_range | 0.0737 | +| entropy_loss | -6.69 | +| explained_variance | 0.18 | +| learning_rate | 4.87e-05 | +| loss | -0.0248 | +| n_updates | 26140 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000322 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.396 | +| time/ | | +| fps | 1411 | +| iterations | 2582 | +| time_elapsed | 3745 | +| total_timesteps | 5287936 | +| train/ | | +| approx_kl | 0.010029602 | +| clip_fraction | 0.324 | +| clip_range | 0.0737 | +| entropy_loss | -7.01 | +| explained_variance | 0.0147 | +| learning_rate | 4.87e-05 | +| loss | -0.0327 | +| n_updates | 26144 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.00025 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.397 | +| time/ | | +| fps | 1412 | +| iterations | 2583 | +| time_elapsed | 3746 | +| total_timesteps | 5289984 | +| train/ | | +| approx_kl | 0.010939541 | +| clip_fraction | 0.344 | +| clip_range | 0.0737 | +| entropy_loss | -7.3 | +| explained_variance | 0.381 | +| learning_rate | 4.87e-05 | +| loss | -0.0406 | +| n_updates | 26148 | +| policy_gradient_loss | -0.0259 | +| value_loss | 7.71e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.399 | +| time/ | | +| fps | 1412 | +| iterations | 2584 | +| time_elapsed | 3747 | +| total_timesteps | 5292032 | +| train/ | | +| approx_kl | 0.012507557 | +| clip_fraction | 0.342 | +| clip_range | 0.0737 | +| entropy_loss | -7.24 | +| explained_variance | 0.326 | +| learning_rate | 4.87e-05 | +| loss | -0.0291 | +| n_updates | 26152 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000129 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.395 | +| time/ | | +| fps | 1411 | +| iterations | 2585 | +| time_elapsed | 3749 | +| total_timesteps | 5294080 | +| train/ | | +| approx_kl | 0.010367934 | +| clip_fraction | 0.306 | +| clip_range | 0.0737 | +| entropy_loss | -7.29 | +| explained_variance | 0.235 | +| learning_rate | 4.87e-05 | +| loss | -0.0305 | +| n_updates | 26156 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000157 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.396 | +| time/ | | +| fps | 1412 | +| iterations | 2586 | +| time_elapsed | 3750 | +| total_timesteps | 5296128 | +| train/ | | +| approx_kl | 0.011148529 | +| clip_fraction | 0.309 | +| clip_range | 0.0737 | +| entropy_loss | -6.83 | +| explained_variance | 0.348 | +| learning_rate | 4.87e-05 | +| loss | -0.0281 | +| n_updates | 26160 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000195 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.4 | +| time/ | | +| fps | 1412 | +| iterations | 2587 | +| time_elapsed | 3752 | +| total_timesteps | 5298176 | +| train/ | | +| approx_kl | 0.0115668345 | +| clip_fraction | 0.307 | +| clip_range | 0.0737 | +| entropy_loss | -7.02 | +| explained_variance | 0.163 | +| learning_rate | 4.87e-05 | +| loss | -0.0276 | +| n_updates | 26164 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000323 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.398 | +| time/ | | +| fps | 1412 | +| iterations | 2588 | +| time_elapsed | 3753 | +| total_timesteps | 5300224 | +| train/ | | +| approx_kl | 0.009841676 | +| clip_fraction | 0.306 | +| clip_range | 0.0737 | +| entropy_loss | -7.35 | +| explained_variance | -0.0827 | +| learning_rate | 4.87e-05 | +| loss | -0.0296 | +| n_updates | 26168 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.00027 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.398 | +| time/ | | +| fps | 1412 | +| iterations | 2589 | +| time_elapsed | 3755 | +| total_timesteps | 5302272 | +| train/ | | +| approx_kl | 0.010333179 | +| clip_fraction | 0.299 | +| clip_range | 0.0737 | +| entropy_loss | -7.01 | +| explained_variance | 0.358 | +| learning_rate | 4.87e-05 | +| loss | -0.0332 | +| n_updates | 26172 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000202 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.396 | +| time/ | | +| fps | 1412 | +| iterations | 2590 | +| time_elapsed | 3756 | +| total_timesteps | 5304320 | +| train/ | | +| approx_kl | 0.011719036 | +| clip_fraction | 0.346 | +| clip_range | 0.0737 | +| entropy_loss | -7.27 | +| explained_variance | 0.416 | +| learning_rate | 4.87e-05 | +| loss | -0.0375 | +| n_updates | 26176 | +| policy_gradient_loss | -0.0229 | +| value_loss | 0.000105 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.396 | +| time/ | | +| fps | 1412 | +| iterations | 2591 | +| time_elapsed | 3757 | +| total_timesteps | 5306368 | +| train/ | | +| approx_kl | 0.011711718 | +| clip_fraction | 0.315 | +| clip_range | 0.0737 | +| entropy_loss | -6.82 | +| explained_variance | 0.483 | +| learning_rate | 4.87e-05 | +| loss | -0.0292 | +| n_updates | 26180 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000258 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.402 | +| time/ | | +| fps | 1412 | +| iterations | 2592 | +| time_elapsed | 3759 | +| total_timesteps | 5308416 | +| train/ | | +| approx_kl | 0.011088297 | +| clip_fraction | 0.33 | +| clip_range | 0.0737 | +| entropy_loss | -7.44 | +| explained_variance | -0.103 | +| learning_rate | 4.87e-05 | +| loss | -0.0348 | +| n_updates | 26184 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000111 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.402 | +| time/ | | +| fps | 1412 | +| iterations | 2593 | +| time_elapsed | 3760 | +| total_timesteps | 5310464 | +| train/ | | +| approx_kl | 0.010038997 | +| clip_fraction | 0.316 | +| clip_range | 0.0737 | +| entropy_loss | -7.31 | +| explained_variance | -0.0173 | +| learning_rate | 4.87e-05 | +| loss | -0.0326 | +| n_updates | 26188 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000203 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.404 | +| time/ | | +| fps | 1412 | +| iterations | 2594 | +| time_elapsed | 3762 | +| total_timesteps | 5312512 | +| train/ | | +| approx_kl | 0.008215085 | +| clip_fraction | 0.294 | +| clip_range | 0.0737 | +| entropy_loss | -7.28 | +| explained_variance | 0.101 | +| learning_rate | 4.87e-05 | +| loss | -0.0282 | +| n_updates | 26192 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000283 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.402 | +| time/ | | +| fps | 1412 | +| iterations | 2595 | +| time_elapsed | 3763 | +| total_timesteps | 5314560 | +| train/ | | +| approx_kl | 0.008096896 | +| clip_fraction | 0.283 | +| clip_range | 0.0737 | +| entropy_loss | -7.02 | +| explained_variance | 0.192 | +| learning_rate | 4.87e-05 | +| loss | -0.0271 | +| n_updates | 26196 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.000337 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.406 | +| time/ | | +| fps | 1412 | +| iterations | 2596 | +| time_elapsed | 3765 | +| total_timesteps | 5316608 | +| train/ | | +| approx_kl | 0.011029346 | +| clip_fraction | 0.293 | +| clip_range | 0.0737 | +| entropy_loss | -6.89 | +| explained_variance | 0.307 | +| learning_rate | 4.87e-05 | +| loss | -0.0312 | +| n_updates | 26200 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000275 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.403 | +| time/ | | +| fps | 1412 | +| iterations | 2597 | +| time_elapsed | 3766 | +| total_timesteps | 5318656 | +| train/ | | +| approx_kl | 0.012670476 | +| clip_fraction | 0.34 | +| clip_range | 0.0737 | +| entropy_loss | -7.12 | +| explained_variance | 0.245 | +| learning_rate | 4.87e-05 | +| loss | -0.0356 | +| n_updates | 26204 | +| policy_gradient_loss | -0.0226 | +| value_loss | 0.000187 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.403 | +| time/ | | +| fps | 1412 | +| iterations | 2598 | +| time_elapsed | 3767 | +| total_timesteps | 5320704 | +| train/ | | +| approx_kl | 0.011820782 | +| clip_fraction | 0.324 | +| clip_range | 0.0737 | +| entropy_loss | -7.2 | +| explained_variance | 0.227 | +| learning_rate | 4.87e-05 | +| loss | -0.0326 | +| n_updates | 26208 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000204 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.406 | +| time/ | | +| fps | 1412 | +| iterations | 2599 | +| time_elapsed | 3769 | +| total_timesteps | 5322752 | +| train/ | | +| approx_kl | 0.011564472 | +| clip_fraction | 0.321 | +| clip_range | 0.0737 | +| entropy_loss | -7.1 | +| explained_variance | 0.34 | +| learning_rate | 4.87e-05 | +| loss | -0.0397 | +| n_updates | 26212 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000146 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.4 | +| time/ | | +| fps | 1412 | +| iterations | 2600 | +| time_elapsed | 3770 | +| total_timesteps | 5324800 | +| train/ | | +| approx_kl | 0.011418421 | +| clip_fraction | 0.332 | +| clip_range | 0.0737 | +| entropy_loss | -6.95 | +| explained_variance | 0.203 | +| learning_rate | 4.87e-05 | +| loss | -0.0341 | +| n_updates | 26216 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000155 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.397 | +| time/ | | +| fps | 1412 | +| iterations | 2601 | +| time_elapsed | 3772 | +| total_timesteps | 5326848 | +| train/ | | +| approx_kl | 0.012580788 | +| clip_fraction | 0.344 | +| clip_range | 0.0737 | +| entropy_loss | -7.25 | +| explained_variance | 0.129 | +| learning_rate | 4.87e-05 | +| loss | -0.0327 | +| n_updates | 26220 | +| policy_gradient_loss | -0.0231 | +| value_loss | 0.000101 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.397 | +| time/ | | +| fps | 1412 | +| iterations | 2602 | +| time_elapsed | 3773 | +| total_timesteps | 5328896 | +| train/ | | +| approx_kl | 0.012751514 | +| clip_fraction | 0.336 | +| clip_range | 0.0737 | +| entropy_loss | -7.02 | +| explained_variance | 0.202 | +| learning_rate | 4.87e-05 | +| loss | -0.0316 | +| n_updates | 26224 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000264 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.395 | +| time/ | | +| fps | 1412 | +| iterations | 2603 | +| time_elapsed | 3775 | +| total_timesteps | 5330944 | +| train/ | | +| approx_kl | 0.012145627 | +| clip_fraction | 0.343 | +| clip_range | 0.0737 | +| entropy_loss | -7.3 | +| explained_variance | -0.215 | +| learning_rate | 4.87e-05 | +| loss | -0.0341 | +| n_updates | 26228 | +| policy_gradient_loss | -0.0225 | +| value_loss | 7.42e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.398 | +| time/ | | +| fps | 1412 | +| iterations | 2604 | +| time_elapsed | 3776 | +| total_timesteps | 5332992 | +| train/ | | +| approx_kl | 0.012055294 | +| clip_fraction | 0.328 | +| clip_range | 0.0737 | +| entropy_loss | -7.29 | +| explained_variance | 0.0613 | +| learning_rate | 4.87e-05 | +| loss | -0.036 | +| n_updates | 26232 | +| policy_gradient_loss | -0.0222 | +| value_loss | 8.76e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.4 | +| time/ | | +| fps | 1412 | +| iterations | 2605 | +| time_elapsed | 3778 | +| total_timesteps | 5335040 | +| train/ | | +| approx_kl | 0.01086277 | +| clip_fraction | 0.302 | +| clip_range | 0.0737 | +| entropy_loss | -7.11 | +| explained_variance | 0.121 | +| learning_rate | 4.87e-05 | +| loss | -0.0279 | +| n_updates | 26236 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000294 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.412 | +| time/ | | +| fps | 1412 | +| iterations | 2606 | +| time_elapsed | 3779 | +| total_timesteps | 5337088 | +| train/ | | +| approx_kl | 0.010388292 | +| clip_fraction | 0.279 | +| clip_range | 0.0737 | +| entropy_loss | -7.1 | +| explained_variance | 0.277 | +| learning_rate | 4.87e-05 | +| loss | -0.0297 | +| n_updates | 26240 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000195 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.408 | +| time/ | | +| fps | 1412 | +| iterations | 2607 | +| time_elapsed | 3780 | +| total_timesteps | 5339136 | +| train/ | | +| approx_kl | 0.008450743 | +| clip_fraction | 0.269 | +| clip_range | 0.0737 | +| entropy_loss | -6.86 | +| explained_variance | 0.239 | +| learning_rate | 4.87e-05 | +| loss | -0.0244 | +| n_updates | 26244 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000434 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.408 | +| time/ | | +| fps | 1412 | +| iterations | 2608 | +| time_elapsed | 3782 | +| total_timesteps | 5341184 | +| train/ | | +| approx_kl | 0.011081194 | +| clip_fraction | 0.314 | +| clip_range | 0.0737 | +| entropy_loss | -7.12 | +| explained_variance | 0.497 | +| learning_rate | 4.87e-05 | +| loss | -0.032 | +| n_updates | 26248 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000129 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.406 | +| time/ | | +| fps | 1412 | +| iterations | 2609 | +| time_elapsed | 3783 | +| total_timesteps | 5343232 | +| train/ | | +| approx_kl | 0.011389479 | +| clip_fraction | 0.341 | +| clip_range | 0.0737 | +| entropy_loss | -7.35 | +| explained_variance | -0.0597 | +| learning_rate | 4.87e-05 | +| loss | -0.0286 | +| n_updates | 26252 | +| policy_gradient_loss | -0.0222 | +| value_loss | 0.000143 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.404 | +| time/ | | +| fps | 1412 | +| iterations | 2610 | +| time_elapsed | 3785 | +| total_timesteps | 5345280 | +| train/ | | +| approx_kl | 0.010027198 | +| clip_fraction | 0.311 | +| clip_range | 0.0737 | +| entropy_loss | -7.15 | +| explained_variance | 0.149 | +| learning_rate | 4.87e-05 | +| loss | -0.0315 | +| n_updates | 26256 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000197 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.401 | +| time/ | | +| fps | 1412 | +| iterations | 2611 | +| time_elapsed | 3786 | +| total_timesteps | 5347328 | +| train/ | | +| approx_kl | 0.010687054 | +| clip_fraction | 0.303 | +| clip_range | 0.0737 | +| entropy_loss | -6.94 | +| explained_variance | 0.439 | +| learning_rate | 4.87e-05 | +| loss | -0.0322 | +| n_updates | 26260 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.00016 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.413 | +| time/ | | +| fps | 1412 | +| iterations | 2612 | +| time_elapsed | 3787 | +| total_timesteps | 5349376 | +| train/ | | +| approx_kl | 0.010610691 | +| clip_fraction | 0.323 | +| clip_range | 0.0737 | +| entropy_loss | -7.22 | +| explained_variance | -0.0255 | +| learning_rate | 4.87e-05 | +| loss | -0.035 | +| n_updates | 26264 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000231 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.413 | +| time/ | | +| fps | 1412 | +| iterations | 2613 | +| time_elapsed | 3789 | +| total_timesteps | 5351424 | +| train/ | | +| approx_kl | 0.009846795 | +| clip_fraction | 0.302 | +| clip_range | 0.0737 | +| entropy_loss | -6.94 | +| explained_variance | 0.0922 | +| learning_rate | 4.87e-05 | +| loss | -0.0246 | +| n_updates | 26268 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000534 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.413 | +| time/ | | +| fps | 1412 | +| iterations | 2614 | +| time_elapsed | 3790 | +| total_timesteps | 5353472 | +| train/ | | +| approx_kl | 0.011712322 | +| clip_fraction | 0.319 | +| clip_range | 0.0737 | +| entropy_loss | -6.91 | +| explained_variance | 0.18 | +| learning_rate | 4.87e-05 | +| loss | -0.0306 | +| n_updates | 26272 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000328 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.413 | +| time/ | | +| fps | 1412 | +| iterations | 2615 | +| time_elapsed | 3792 | +| total_timesteps | 5355520 | +| train/ | | +| approx_kl | 0.0122685945 | +| clip_fraction | 0.315 | +| clip_range | 0.0737 | +| entropy_loss | -7.51 | +| explained_variance | -0.277 | +| learning_rate | 4.87e-05 | +| loss | -0.0405 | +| n_updates | 26276 | +| policy_gradient_loss | -0.0233 | +| value_loss | 0.000181 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.414 | +| time/ | | +| fps | 1412 | +| iterations | 2616 | +| time_elapsed | 3793 | +| total_timesteps | 5357568 | +| train/ | | +| approx_kl | 0.012871811 | +| clip_fraction | 0.336 | +| clip_range | 0.0737 | +| entropy_loss | -7.45 | +| explained_variance | -0.259 | +| learning_rate | 4.87e-05 | +| loss | -0.0347 | +| n_updates | 26280 | +| policy_gradient_loss | -0.0229 | +| value_loss | 0.000121 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.416 | +| time/ | | +| fps | 1412 | +| iterations | 2617 | +| time_elapsed | 3795 | +| total_timesteps | 5359616 | +| train/ | | +| approx_kl | 0.011664523 | +| clip_fraction | 0.314 | +| clip_range | 0.0737 | +| entropy_loss | -7.08 | +| explained_variance | 0.43 | +| learning_rate | 4.87e-05 | +| loss | -0.0327 | +| n_updates | 26284 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000162 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.412 | +| time/ | | +| fps | 1412 | +| iterations | 2618 | +| time_elapsed | 3796 | +| total_timesteps | 5361664 | +| train/ | | +| approx_kl | 0.009563789 | +| clip_fraction | 0.29 | +| clip_range | 0.0737 | +| entropy_loss | -7.2 | +| explained_variance | 0.276 | +| learning_rate | 4.87e-05 | +| loss | -0.0369 | +| n_updates | 26288 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000221 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.413 | +| time/ | | +| fps | 1412 | +| iterations | 2619 | +| time_elapsed | 3798 | +| total_timesteps | 5363712 | +| train/ | | +| approx_kl | 0.010232235 | +| clip_fraction | 0.313 | +| clip_range | 0.0737 | +| entropy_loss | -7.25 | +| explained_variance | -0.0333 | +| learning_rate | 4.87e-05 | +| loss | -0.0353 | +| n_updates | 26292 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000136 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.413 | +| time/ | | +| fps | 1412 | +| iterations | 2620 | +| time_elapsed | 3799 | +| total_timesteps | 5365760 | +| train/ | | +| approx_kl | 0.00865864 | +| clip_fraction | 0.295 | +| clip_range | 0.0737 | +| entropy_loss | -7.11 | +| explained_variance | 0.299 | +| learning_rate | 4.87e-05 | +| loss | -0.0307 | +| n_updates | 26296 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000182 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.423 | +| time/ | | +| fps | 1412 | +| iterations | 2621 | +| time_elapsed | 3800 | +| total_timesteps | 5367808 | +| train/ | | +| approx_kl | 0.012050496 | +| clip_fraction | 0.307 | +| clip_range | 0.0737 | +| entropy_loss | -7.38 | +| explained_variance | -0.124 | +| learning_rate | 4.87e-05 | +| loss | -0.0356 | +| n_updates | 26300 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.421 | +| time/ | | +| fps | 1412 | +| iterations | 2622 | +| time_elapsed | 3802 | +| total_timesteps | 5369856 | +| train/ | | +| approx_kl | 0.009542706 | +| clip_fraction | 0.308 | +| clip_range | 0.0737 | +| entropy_loss | -7.17 | +| explained_variance | 0.305 | +| learning_rate | 4.87e-05 | +| loss | -0.0241 | +| n_updates | 26304 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000288 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.421 | +| time/ | | +| fps | 1412 | +| iterations | 2623 | +| time_elapsed | 3803 | +| total_timesteps | 5371904 | +| train/ | | +| approx_kl | 0.00907658 | +| clip_fraction | 0.275 | +| clip_range | 0.0737 | +| entropy_loss | -7.19 | +| explained_variance | -0.0597 | +| learning_rate | 4.87e-05 | +| loss | -0.0303 | +| n_updates | 26308 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000221 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.416 | +| time/ | | +| fps | 1412 | +| iterations | 2624 | +| time_elapsed | 3805 | +| total_timesteps | 5373952 | +| train/ | | +| approx_kl | 0.010623176 | +| clip_fraction | 0.311 | +| clip_range | 0.0737 | +| entropy_loss | -7 | +| explained_variance | -0.141 | +| learning_rate | 4.87e-05 | +| loss | -0.0331 | +| n_updates | 26312 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000155 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.416 | +| time/ | | +| fps | 1412 | +| iterations | 2625 | +| time_elapsed | 3806 | +| total_timesteps | 5376000 | +| train/ | | +| approx_kl | 0.010803679 | +| clip_fraction | 0.336 | +| clip_range | 0.0737 | +| entropy_loss | -6.71 | +| explained_variance | 0.522 | +| learning_rate | 4.87e-05 | +| loss | -0.032 | +| n_updates | 26316 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000109 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.404 | +| time/ | | +| fps | 1412 | +| iterations | 2626 | +| time_elapsed | 3808 | +| total_timesteps | 5378048 | +| train/ | | +| approx_kl | 0.011075955 | +| clip_fraction | 0.323 | +| clip_range | 0.0737 | +| entropy_loss | -7.43 | +| explained_variance | -0.0927 | +| learning_rate | 4.87e-05 | +| loss | -0.0299 | +| n_updates | 26320 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.00015 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.404 | +| time/ | | +| fps | 1412 | +| iterations | 2627 | +| time_elapsed | 3809 | +| total_timesteps | 5380096 | +| train/ | | +| approx_kl | 0.0108549185 | +| clip_fraction | 0.298 | +| clip_range | 0.0737 | +| entropy_loss | -6.9 | +| explained_variance | 0.33 | +| learning_rate | 4.87e-05 | +| loss | -0.0273 | +| n_updates | 26324 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000207 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.401 | +| time/ | | +| fps | 1412 | +| iterations | 2628 | +| time_elapsed | 3811 | +| total_timesteps | 5382144 | +| train/ | | +| approx_kl | 0.011004087 | +| clip_fraction | 0.325 | +| clip_range | 0.0737 | +| entropy_loss | -7.28 | +| explained_variance | -0.0155 | +| learning_rate | 4.87e-05 | +| loss | -0.0311 | +| n_updates | 26328 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000131 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.404 | +| time/ | | +| fps | 1412 | +| iterations | 2629 | +| time_elapsed | 3812 | +| total_timesteps | 5384192 | +| train/ | | +| approx_kl | 0.009237153 | +| clip_fraction | 0.307 | +| clip_range | 0.0737 | +| entropy_loss | -7.28 | +| explained_variance | 0.152 | +| learning_rate | 4.87e-05 | +| loss | -0.0318 | +| n_updates | 26332 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000344 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.409 | +| time/ | | +| fps | 1412 | +| iterations | 2630 | +| time_elapsed | 3813 | +| total_timesteps | 5386240 | +| train/ | | +| approx_kl | 0.009002341 | +| clip_fraction | 0.285 | +| clip_range | 0.0737 | +| entropy_loss | -7.15 | +| explained_variance | 0.215 | +| learning_rate | 4.87e-05 | +| loss | -0.0352 | +| n_updates | 26336 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000379 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.411 | +| time/ | | +| fps | 1412 | +| iterations | 2631 | +| time_elapsed | 3815 | +| total_timesteps | 5388288 | +| train/ | | +| approx_kl | 0.00851868 | +| clip_fraction | 0.305 | +| clip_range | 0.0737 | +| entropy_loss | -7.29 | +| explained_variance | 0.0484 | +| learning_rate | 4.87e-05 | +| loss | -0.0344 | +| n_updates | 26340 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000363 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.41 | +| time/ | | +| fps | 1412 | +| iterations | 2632 | +| time_elapsed | 3816 | +| total_timesteps | 5390336 | +| train/ | | +| approx_kl | 0.010711379 | +| clip_fraction | 0.307 | +| clip_range | 0.0737 | +| entropy_loss | -6.88 | +| explained_variance | 0.272 | +| learning_rate | 4.87e-05 | +| loss | -0.0287 | +| n_updates | 26344 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.00038 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.414 | +| time/ | | +| fps | 1412 | +| iterations | 2633 | +| time_elapsed | 3818 | +| total_timesteps | 5392384 | +| train/ | | +| approx_kl | 0.012251853 | +| clip_fraction | 0.334 | +| clip_range | 0.0737 | +| entropy_loss | -7.23 | +| explained_variance | 0.0704 | +| learning_rate | 4.87e-05 | +| loss | -0.0388 | +| n_updates | 26348 | +| policy_gradient_loss | -0.0233 | +| value_loss | 0.000235 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.411 | +| time/ | | +| fps | 1412 | +| iterations | 2634 | +| time_elapsed | 3819 | +| total_timesteps | 5394432 | +| train/ | | +| approx_kl | 0.010329281 | +| clip_fraction | 0.319 | +| clip_range | 0.0737 | +| entropy_loss | -7.04 | +| explained_variance | 0.34 | +| learning_rate | 4.87e-05 | +| loss | -0.0337 | +| n_updates | 26352 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000251 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.405 | +| time/ | | +| fps | 1412 | +| iterations | 2635 | +| time_elapsed | 3821 | +| total_timesteps | 5396480 | +| train/ | | +| approx_kl | 0.009757228 | +| clip_fraction | 0.325 | +| clip_range | 0.0737 | +| entropy_loss | -7 | +| explained_variance | 0.526 | +| learning_rate | 4.87e-05 | +| loss | -0.03 | +| n_updates | 26356 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000139 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.405 | +| time/ | | +| fps | 1412 | +| iterations | 2636 | +| time_elapsed | 3822 | +| total_timesteps | 5398528 | +| train/ | | +| approx_kl | 0.011600596 | +| clip_fraction | 0.32 | +| clip_range | 0.0737 | +| entropy_loss | -6.84 | +| explained_variance | 0.484 | +| learning_rate | 4.87e-05 | +| loss | -0.0325 | +| n_updates | 26360 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000161 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.405 | +| time/ | | +| fps | 1412 | +| iterations | 2637 | +| time_elapsed | 3823 | +| total_timesteps | 5400576 | +| train/ | | +| approx_kl | 0.00982419 | +| clip_fraction | 0.319 | +| clip_range | 0.0737 | +| entropy_loss | -7.36 | +| explained_variance | -0.205 | +| learning_rate | 4.87e-05 | +| loss | -0.0336 | +| n_updates | 26364 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.00013 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.401 | +| time/ | | +| fps | 1412 | +| iterations | 2638 | +| time_elapsed | 3825 | +| total_timesteps | 5402624 | +| train/ | | +| approx_kl | 0.011285691 | +| clip_fraction | 0.303 | +| clip_range | 0.0736 | +| entropy_loss | -7.48 | +| explained_variance | -0.0446 | +| learning_rate | 4.87e-05 | +| loss | -0.0336 | +| n_updates | 26368 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000208 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.401 | +| time/ | | +| fps | 1412 | +| iterations | 2639 | +| time_elapsed | 3826 | +| total_timesteps | 5404672 | +| train/ | | +| approx_kl | 0.0088243615 | +| clip_fraction | 0.291 | +| clip_range | 0.0736 | +| entropy_loss | -7.28 | +| explained_variance | 0.16 | +| learning_rate | 4.87e-05 | +| loss | -0.0285 | +| n_updates | 26372 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000167 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.397 | +| time/ | | +| fps | 1412 | +| iterations | 2640 | +| time_elapsed | 3828 | +| total_timesteps | 5406720 | +| train/ | | +| approx_kl | 0.0119768595 | +| clip_fraction | 0.312 | +| clip_range | 0.0736 | +| entropy_loss | -7.52 | +| explained_variance | -0.148 | +| learning_rate | 4.87e-05 | +| loss | -0.0323 | +| n_updates | 26376 | +| policy_gradient_loss | -0.0222 | +| value_loss | 0.000114 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.398 | +| time/ | | +| fps | 1412 | +| iterations | 2641 | +| time_elapsed | 3829 | +| total_timesteps | 5408768 | +| train/ | | +| approx_kl | 0.0104460735 | +| clip_fraction | 0.285 | +| clip_range | 0.0736 | +| entropy_loss | -7.22 | +| explained_variance | 0.217 | +| learning_rate | 4.87e-05 | +| loss | -0.0339 | +| n_updates | 26380 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.00012 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.392 | +| time/ | | +| fps | 1412 | +| iterations | 2642 | +| time_elapsed | 3831 | +| total_timesteps | 5410816 | +| train/ | | +| approx_kl | 0.009050503 | +| clip_fraction | 0.295 | +| clip_range | 0.0736 | +| entropy_loss | -7.18 | +| explained_variance | 0.307 | +| learning_rate | 4.87e-05 | +| loss | -0.026 | +| n_updates | 26384 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000181 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.39 | +| time/ | | +| fps | 1412 | +| iterations | 2643 | +| time_elapsed | 3832 | +| total_timesteps | 5412864 | +| train/ | | +| approx_kl | 0.012557064 | +| clip_fraction | 0.308 | +| clip_range | 0.0736 | +| entropy_loss | -7.02 | +| explained_variance | 0.353 | +| learning_rate | 4.87e-05 | +| loss | -0.0315 | +| n_updates | 26388 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000171 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.385 | +| time/ | | +| fps | 1412 | +| iterations | 2644 | +| time_elapsed | 3834 | +| total_timesteps | 5414912 | +| train/ | | +| approx_kl | 0.009974705 | +| clip_fraction | 0.351 | +| clip_range | 0.0736 | +| entropy_loss | -6.86 | +| explained_variance | 0.694 | +| learning_rate | 4.87e-05 | +| loss | -0.0328 | +| n_updates | 26392 | +| policy_gradient_loss | -0.0211 | +| value_loss | 7.15e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.384 | +| time/ | | +| fps | 1412 | +| iterations | 2645 | +| time_elapsed | 3835 | +| total_timesteps | 5416960 | +| train/ | | +| approx_kl | 0.011572488 | +| clip_fraction | 0.339 | +| clip_range | 0.0736 | +| entropy_loss | -7.29 | +| explained_variance | 0.512 | +| learning_rate | 4.87e-05 | +| loss | -0.0404 | +| n_updates | 26396 | +| policy_gradient_loss | -0.0237 | +| value_loss | 6.5e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.384 | +| time/ | | +| fps | 1412 | +| iterations | 2646 | +| time_elapsed | 3836 | +| total_timesteps | 5419008 | +| train/ | | +| approx_kl | 0.011805991 | +| clip_fraction | 0.32 | +| clip_range | 0.0736 | +| entropy_loss | -6.94 | +| explained_variance | 0.57 | +| learning_rate | 4.87e-05 | +| loss | -0.0331 | +| n_updates | 26400 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000168 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1412 | +| iterations | 2647 | +| time_elapsed | 3838 | +| total_timesteps | 5421056 | +| train/ | | +| approx_kl | 0.009624989 | +| clip_fraction | 0.311 | +| clip_range | 0.0736 | +| entropy_loss | -7.43 | +| explained_variance | 0.026 | +| learning_rate | 4.87e-05 | +| loss | -0.0378 | +| n_updates | 26404 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000102 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1412 | +| iterations | 2648 | +| time_elapsed | 3839 | +| total_timesteps | 5423104 | +| train/ | | +| approx_kl | 0.011725154 | +| clip_fraction | 0.317 | +| clip_range | 0.0736 | +| entropy_loss | -7.19 | +| explained_variance | 0.0799 | +| learning_rate | 4.87e-05 | +| loss | -0.0294 | +| n_updates | 26408 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000149 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1412 | +| iterations | 2649 | +| time_elapsed | 3841 | +| total_timesteps | 5425152 | +| train/ | | +| approx_kl | 0.012591768 | +| clip_fraction | 0.336 | +| clip_range | 0.0736 | +| entropy_loss | -7.21 | +| explained_variance | 0.546 | +| learning_rate | 4.87e-05 | +| loss | -0.0333 | +| n_updates | 26412 | +| policy_gradient_loss | -0.022 | +| value_loss | 8.14e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1412 | +| iterations | 2650 | +| time_elapsed | 3842 | +| total_timesteps | 5427200 | +| train/ | | +| approx_kl | 0.013827446 | +| clip_fraction | 0.301 | +| clip_range | 0.0736 | +| entropy_loss | -7.51 | +| explained_variance | -0.121 | +| learning_rate | 4.87e-05 | +| loss | -0.0305 | +| n_updates | 26416 | +| policy_gradient_loss | -0.0203 | +| value_loss | 9.72e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1412 | +| iterations | 2651 | +| time_elapsed | 3844 | +| total_timesteps | 5429248 | +| train/ | | +| approx_kl | 0.012200889 | +| clip_fraction | 0.328 | +| clip_range | 0.0736 | +| entropy_loss | -7.4 | +| explained_variance | -0.227 | +| learning_rate | 4.87e-05 | +| loss | -0.0341 | +| n_updates | 26420 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000115 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1412 | +| iterations | 2652 | +| time_elapsed | 3845 | +| total_timesteps | 5431296 | +| train/ | | +| approx_kl | 0.010474527 | +| clip_fraction | 0.286 | +| clip_range | 0.0736 | +| entropy_loss | -6.94 | +| explained_variance | 0.278 | +| learning_rate | 4.87e-05 | +| loss | -0.0199 | +| n_updates | 26424 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.00017 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1412 | +| iterations | 2653 | +| time_elapsed | 3847 | +| total_timesteps | 5433344 | +| train/ | | +| approx_kl | 0.012024186 | +| clip_fraction | 0.307 | +| clip_range | 0.0736 | +| entropy_loss | -7.11 | +| explained_variance | 0.309 | +| learning_rate | 4.87e-05 | +| loss | -0.0313 | +| n_updates | 26428 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000131 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1412 | +| iterations | 2654 | +| time_elapsed | 3848 | +| total_timesteps | 5435392 | +| train/ | | +| approx_kl | 0.011023506 | +| clip_fraction | 0.306 | +| clip_range | 0.0736 | +| entropy_loss | -7.06 | +| explained_variance | 0.128 | +| learning_rate | 4.87e-05 | +| loss | -0.033 | +| n_updates | 26432 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000341 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1412 | +| iterations | 2655 | +| time_elapsed | 3849 | +| total_timesteps | 5437440 | +| train/ | | +| approx_kl | 0.01097941 | +| clip_fraction | 0.346 | +| clip_range | 0.0736 | +| entropy_loss | -7.17 | +| explained_variance | 0.201 | +| learning_rate | 4.87e-05 | +| loss | -0.0309 | +| n_updates | 26436 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000111 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1412 | +| iterations | 2656 | +| time_elapsed | 3851 | +| total_timesteps | 5439488 | +| train/ | | +| approx_kl | 0.01199211 | +| clip_fraction | 0.309 | +| clip_range | 0.0736 | +| entropy_loss | -7.03 | +| explained_variance | 0.216 | +| learning_rate | 4.87e-05 | +| loss | -0.0361 | +| n_updates | 26440 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000283 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1412 | +| iterations | 2657 | +| time_elapsed | 3852 | +| total_timesteps | 5441536 | +| train/ | | +| approx_kl | 0.011830526 | +| clip_fraction | 0.327 | +| clip_range | 0.0736 | +| entropy_loss | -7.19 | +| explained_variance | 0.273 | +| learning_rate | 4.87e-05 | +| loss | -0.0351 | +| n_updates | 26444 | +| policy_gradient_loss | -0.0224 | +| value_loss | 0.000145 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1412 | +| iterations | 2658 | +| time_elapsed | 3854 | +| total_timesteps | 5443584 | +| train/ | | +| approx_kl | 0.012175422 | +| clip_fraction | 0.339 | +| clip_range | 0.0736 | +| entropy_loss | -7.19 | +| explained_variance | 0.398 | +| learning_rate | 4.87e-05 | +| loss | -0.0343 | +| n_updates | 26448 | +| policy_gradient_loss | -0.0238 | +| value_loss | 8.21e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1412 | +| iterations | 2659 | +| time_elapsed | 3855 | +| total_timesteps | 5445632 | +| train/ | | +| approx_kl | 0.012086059 | +| clip_fraction | 0.32 | +| clip_range | 0.0736 | +| entropy_loss | -6.96 | +| explained_variance | 0.547 | +| learning_rate | 4.87e-05 | +| loss | -0.0338 | +| n_updates | 26452 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000123 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1412 | +| iterations | 2660 | +| time_elapsed | 3857 | +| total_timesteps | 5447680 | +| train/ | | +| approx_kl | 0.012344922 | +| clip_fraction | 0.338 | +| clip_range | 0.0736 | +| entropy_loss | -7.36 | +| explained_variance | -0.297 | +| learning_rate | 4.87e-05 | +| loss | -0.0356 | +| n_updates | 26456 | +| policy_gradient_loss | -0.0236 | +| value_loss | 6.21e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1412 | +| iterations | 2661 | +| time_elapsed | 3858 | +| total_timesteps | 5449728 | +| train/ | | +| approx_kl | 0.0108805485 | +| clip_fraction | 0.317 | +| clip_range | 0.0736 | +| entropy_loss | -7.41 | +| explained_variance | -0.12 | +| learning_rate | 4.87e-05 | +| loss | -0.0318 | +| n_updates | 26460 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000114 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1412 | +| iterations | 2662 | +| time_elapsed | 3859 | +| total_timesteps | 5451776 | +| train/ | | +| approx_kl | 0.01066502 | +| clip_fraction | 0.314 | +| clip_range | 0.0736 | +| entropy_loss | -7.2 | +| explained_variance | 0.336 | +| learning_rate | 4.87e-05 | +| loss | -0.0287 | +| n_updates | 26464 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000136 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1412 | +| iterations | 2663 | +| time_elapsed | 3861 | +| total_timesteps | 5453824 | +| train/ | | +| approx_kl | 0.01150173 | +| clip_fraction | 0.32 | +| clip_range | 0.0736 | +| entropy_loss | -7.11 | +| explained_variance | 0.206 | +| learning_rate | 4.87e-05 | +| loss | -0.025 | +| n_updates | 26468 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000112 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1412 | +| iterations | 2664 | +| time_elapsed | 3862 | +| total_timesteps | 5455872 | +| train/ | | +| approx_kl | 0.010976154 | +| clip_fraction | 0.315 | +| clip_range | 0.0736 | +| entropy_loss | -6.74 | +| explained_variance | 0.703 | +| learning_rate | 4.87e-05 | +| loss | -0.0331 | +| n_updates | 26472 | +| policy_gradient_loss | -0.0183 | +| value_loss | 6.01e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1412 | +| iterations | 2665 | +| time_elapsed | 3864 | +| total_timesteps | 5457920 | +| train/ | | +| approx_kl | 0.009298848 | +| clip_fraction | 0.281 | +| clip_range | 0.0736 | +| entropy_loss | -7.23 | +| explained_variance | 0.000659 | +| learning_rate | 4.87e-05 | +| loss | -0.0276 | +| n_updates | 26476 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000213 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1412 | +| iterations | 2666 | +| time_elapsed | 3865 | +| total_timesteps | 5459968 | +| train/ | | +| approx_kl | 0.010001335 | +| clip_fraction | 0.289 | +| clip_range | 0.0736 | +| entropy_loss | -6.77 | +| explained_variance | 0.322 | +| learning_rate | 4.87e-05 | +| loss | -0.0322 | +| n_updates | 26480 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000184 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1412 | +| iterations | 2667 | +| time_elapsed | 3867 | +| total_timesteps | 5462016 | +| train/ | | +| approx_kl | 0.010084999 | +| clip_fraction | 0.325 | +| clip_range | 0.0736 | +| entropy_loss | -7 | +| explained_variance | 0.391 | +| learning_rate | 4.87e-05 | +| loss | -0.0296 | +| n_updates | 26484 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000266 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1412 | +| iterations | 2668 | +| time_elapsed | 3868 | +| total_timesteps | 5464064 | +| train/ | | +| approx_kl | 0.009900368 | +| clip_fraction | 0.324 | +| clip_range | 0.0736 | +| entropy_loss | -7.32 | +| explained_variance | 0.233 | +| learning_rate | 4.87e-05 | +| loss | -0.0424 | +| n_updates | 26488 | +| policy_gradient_loss | -0.0224 | +| value_loss | 0.000139 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1412 | +| iterations | 2669 | +| time_elapsed | 3870 | +| total_timesteps | 5466112 | +| train/ | | +| approx_kl | 0.013868118 | +| clip_fraction | 0.314 | +| clip_range | 0.0736 | +| entropy_loss | -7.03 | +| explained_variance | 0.392 | +| learning_rate | 4.87e-05 | +| loss | -0.0318 | +| n_updates | 26492 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000216 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1412 | +| iterations | 2670 | +| time_elapsed | 3871 | +| total_timesteps | 5468160 | +| train/ | | +| approx_kl | 0.011047074 | +| clip_fraction | 0.323 | +| clip_range | 0.0736 | +| entropy_loss | -7.36 | +| explained_variance | -0.0905 | +| learning_rate | 4.87e-05 | +| loss | -0.0373 | +| n_updates | 26496 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000186 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1412 | +| iterations | 2671 | +| time_elapsed | 3873 | +| total_timesteps | 5470208 | +| train/ | | +| approx_kl | 0.011465436 | +| clip_fraction | 0.296 | +| clip_range | 0.0736 | +| entropy_loss | -6.9 | +| explained_variance | 0.324 | +| learning_rate | 4.87e-05 | +| loss | -0.0284 | +| n_updates | 26500 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000235 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1412 | +| iterations | 2672 | +| time_elapsed | 3874 | +| total_timesteps | 5472256 | +| train/ | | +| approx_kl | 0.010512246 | +| clip_fraction | 0.33 | +| clip_range | 0.0736 | +| entropy_loss | -7.43 | +| explained_variance | -0.0582 | +| learning_rate | 4.87e-05 | +| loss | -0.031 | +| n_updates | 26504 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1412 | +| iterations | 2673 | +| time_elapsed | 3876 | +| total_timesteps | 5474304 | +| train/ | | +| approx_kl | 0.010037418 | +| clip_fraction | 0.307 | +| clip_range | 0.0736 | +| entropy_loss | -7.25 | +| explained_variance | 0.167 | +| learning_rate | 4.87e-05 | +| loss | -0.0283 | +| n_updates | 26508 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000409 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1412 | +| iterations | 2674 | +| time_elapsed | 3877 | +| total_timesteps | 5476352 | +| train/ | | +| approx_kl | 0.010715974 | +| clip_fraction | 0.302 | +| clip_range | 0.0736 | +| entropy_loss | -7.33 | +| explained_variance | 0.11 | +| learning_rate | 4.87e-05 | +| loss | -0.0349 | +| n_updates | 26512 | +| policy_gradient_loss | -0.0221 | +| value_loss | 0.000247 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1412 | +| iterations | 2675 | +| time_elapsed | 3878 | +| total_timesteps | 5478400 | +| train/ | | +| approx_kl | 0.010643104 | +| clip_fraction | 0.311 | +| clip_range | 0.0736 | +| entropy_loss | -7.2 | +| explained_variance | 0.478 | +| learning_rate | 4.87e-05 | +| loss | -0.0402 | +| n_updates | 26516 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000154 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1412 | +| iterations | 2676 | +| time_elapsed | 3880 | +| total_timesteps | 5480448 | +| train/ | | +| approx_kl | 0.012307961 | +| clip_fraction | 0.341 | +| clip_range | 0.0736 | +| entropy_loss | -7.31 | +| explained_variance | 0.154 | +| learning_rate | 4.87e-05 | +| loss | -0.0342 | +| n_updates | 26520 | +| policy_gradient_loss | -0.0228 | +| value_loss | 0.00011 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1412 | +| iterations | 2677 | +| time_elapsed | 3881 | +| total_timesteps | 5482496 | +| train/ | | +| approx_kl | 0.0097974185 | +| clip_fraction | 0.301 | +| clip_range | 0.0736 | +| entropy_loss | -7.23 | +| explained_variance | 0.41 | +| learning_rate | 4.87e-05 | +| loss | -0.0323 | +| n_updates | 26524 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.0002 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1412 | +| iterations | 2678 | +| time_elapsed | 3883 | +| total_timesteps | 5484544 | +| train/ | | +| approx_kl | 0.011212053 | +| clip_fraction | 0.312 | +| clip_range | 0.0736 | +| entropy_loss | -6.73 | +| explained_variance | 0.614 | +| learning_rate | 4.87e-05 | +| loss | -0.0295 | +| n_updates | 26528 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000124 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1412 | +| iterations | 2679 | +| time_elapsed | 3884 | +| total_timesteps | 5486592 | +| train/ | | +| approx_kl | 0.009523319 | +| clip_fraction | 0.303 | +| clip_range | 0.0736 | +| entropy_loss | -7.2 | +| explained_variance | 0.274 | +| learning_rate | 4.87e-05 | +| loss | -0.0333 | +| n_updates | 26532 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000154 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1412 | +| iterations | 2680 | +| time_elapsed | 3886 | +| total_timesteps | 5488640 | +| train/ | | +| approx_kl | 0.011727655 | +| clip_fraction | 0.35 | +| clip_range | 0.0736 | +| entropy_loss | -7.1 | +| explained_variance | 0.751 | +| learning_rate | 4.87e-05 | +| loss | -0.0381 | +| n_updates | 26536 | +| policy_gradient_loss | -0.0237 | +| value_loss | 4.59e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1412 | +| iterations | 2681 | +| time_elapsed | 3887 | +| total_timesteps | 5490688 | +| train/ | | +| approx_kl | 0.011414701 | +| clip_fraction | 0.296 | +| clip_range | 0.0736 | +| entropy_loss | -7.17 | +| explained_variance | 0.213 | +| learning_rate | 4.87e-05 | +| loss | -0.0254 | +| n_updates | 26540 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000276 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1412 | +| iterations | 2682 | +| time_elapsed | 3889 | +| total_timesteps | 5492736 | +| train/ | | +| approx_kl | 0.0101788975 | +| clip_fraction | 0.302 | +| clip_range | 0.0736 | +| entropy_loss | -7.16 | +| explained_variance | -0.0239 | +| learning_rate | 4.87e-05 | +| loss | -0.0305 | +| n_updates | 26544 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000206 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1412 | +| iterations | 2683 | +| time_elapsed | 3890 | +| total_timesteps | 5494784 | +| train/ | | +| approx_kl | 0.010242279 | +| clip_fraction | 0.298 | +| clip_range | 0.0736 | +| entropy_loss | -7.01 | +| explained_variance | 0.2 | +| learning_rate | 4.87e-05 | +| loss | -0.0308 | +| n_updates | 26548 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000292 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1412 | +| iterations | 2684 | +| time_elapsed | 3891 | +| total_timesteps | 5496832 | +| train/ | | +| approx_kl | 0.010149887 | +| clip_fraction | 0.297 | +| clip_range | 0.0736 | +| entropy_loss | -7.21 | +| explained_variance | 0.188 | +| learning_rate | 4.87e-05 | +| loss | -0.0239 | +| n_updates | 26552 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000464 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1412 | +| iterations | 2685 | +| time_elapsed | 3893 | +| total_timesteps | 5498880 | +| train/ | | +| approx_kl | 0.010161934 | +| clip_fraction | 0.313 | +| clip_range | 0.0736 | +| entropy_loss | -7.2 | +| explained_variance | 0.284 | +| learning_rate | 4.87e-05 | +| loss | -0.0412 | +| n_updates | 26556 | +| policy_gradient_loss | -0.022 | +| value_loss | 0.000183 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1412 | +| iterations | 2686 | +| time_elapsed | 3894 | +| total_timesteps | 5500928 | +| train/ | | +| approx_kl | 0.0108791515 | +| clip_fraction | 0.294 | +| clip_range | 0.0736 | +| entropy_loss | -7.12 | +| explained_variance | 0.0427 | +| learning_rate | 4.87e-05 | +| loss | -0.039 | +| n_updates | 26560 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.00011 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1412 | +| iterations | 2687 | +| time_elapsed | 3896 | +| total_timesteps | 5502976 | +| train/ | | +| approx_kl | 0.010677041 | +| clip_fraction | 0.313 | +| clip_range | 0.0736 | +| entropy_loss | -6.86 | +| explained_variance | 0.259 | +| learning_rate | 4.87e-05 | +| loss | -0.0301 | +| n_updates | 26564 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000383 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1412 | +| iterations | 2688 | +| time_elapsed | 3897 | +| total_timesteps | 5505024 | +| train/ | | +| approx_kl | 0.012588363 | +| clip_fraction | 0.345 | +| clip_range | 0.0736 | +| entropy_loss | -6.86 | +| explained_variance | 0.4 | +| learning_rate | 4.87e-05 | +| loss | -0.0335 | +| n_updates | 26568 | +| policy_gradient_loss | -0.0222 | +| value_loss | 0.000175 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1412 | +| iterations | 2689 | +| time_elapsed | 3899 | +| total_timesteps | 5507072 | +| train/ | | +| approx_kl | 0.011659507 | +| clip_fraction | 0.37 | +| clip_range | 0.0736 | +| entropy_loss | -7.25 | +| explained_variance | -0.124 | +| learning_rate | 4.87e-05 | +| loss | -0.0395 | +| n_updates | 26572 | +| policy_gradient_loss | -0.0245 | +| value_loss | 8.43e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1412 | +| iterations | 2690 | +| time_elapsed | 3900 | +| total_timesteps | 5509120 | +| train/ | | +| approx_kl | 0.011507237 | +| clip_fraction | 0.345 | +| clip_range | 0.0736 | +| entropy_loss | -7.12 | +| explained_variance | 0.312 | +| learning_rate | 4.87e-05 | +| loss | -0.038 | +| n_updates | 26576 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000105 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1412 | +| iterations | 2691 | +| time_elapsed | 3902 | +| total_timesteps | 5511168 | +| train/ | | +| approx_kl | 0.012675745 | +| clip_fraction | 0.302 | +| clip_range | 0.0736 | +| entropy_loss | -7.19 | +| explained_variance | 0.297 | +| learning_rate | 4.87e-05 | +| loss | -0.033 | +| n_updates | 26580 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000168 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1412 | +| iterations | 2692 | +| time_elapsed | 3903 | +| total_timesteps | 5513216 | +| train/ | | +| approx_kl | 0.012676401 | +| clip_fraction | 0.349 | +| clip_range | 0.0736 | +| entropy_loss | -6.92 | +| explained_variance | 0.692 | +| learning_rate | 4.87e-05 | +| loss | -0.0343 | +| n_updates | 26584 | +| policy_gradient_loss | -0.0239 | +| value_loss | 6.63e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1412 | +| iterations | 2693 | +| time_elapsed | 3905 | +| total_timesteps | 5515264 | +| train/ | | +| approx_kl | 0.013233209 | +| clip_fraction | 0.318 | +| clip_range | 0.0736 | +| entropy_loss | -7.29 | +| explained_variance | 0.3 | +| learning_rate | 4.87e-05 | +| loss | -0.0299 | +| n_updates | 26588 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000157 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1412 | +| iterations | 2694 | +| time_elapsed | 3906 | +| total_timesteps | 5517312 | +| train/ | | +| approx_kl | 0.012784697 | +| clip_fraction | 0.326 | +| clip_range | 0.0736 | +| entropy_loss | -6.96 | +| explained_variance | 0.231 | +| learning_rate | 4.87e-05 | +| loss | -0.033 | +| n_updates | 26592 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000217 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1412 | +| iterations | 2695 | +| time_elapsed | 3907 | +| total_timesteps | 5519360 | +| train/ | | +| approx_kl | 0.0115273 | +| clip_fraction | 0.33 | +| clip_range | 0.0736 | +| entropy_loss | -7.18 | +| explained_variance | 0.0995 | +| learning_rate | 4.87e-05 | +| loss | -0.031 | +| n_updates | 26596 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000223 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1412 | +| iterations | 2696 | +| time_elapsed | 3909 | +| total_timesteps | 5521408 | +| train/ | | +| approx_kl | 0.013524239 | +| clip_fraction | 0.331 | +| clip_range | 0.0736 | +| entropy_loss | -7.13 | +| explained_variance | 0.343 | +| learning_rate | 4.87e-05 | +| loss | -0.0322 | +| n_updates | 26600 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000149 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1412 | +| iterations | 2697 | +| time_elapsed | 3910 | +| total_timesteps | 5523456 | +| train/ | | +| approx_kl | 0.011378413 | +| clip_fraction | 0.305 | +| clip_range | 0.0736 | +| entropy_loss | -7.39 | +| explained_variance | -0.0198 | +| learning_rate | 4.87e-05 | +| loss | -0.029 | +| n_updates | 26604 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000227 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1412 | +| iterations | 2698 | +| time_elapsed | 3912 | +| total_timesteps | 5525504 | +| train/ | | +| approx_kl | 0.008353043 | +| clip_fraction | 0.281 | +| clip_range | 0.0736 | +| entropy_loss | -6.96 | +| explained_variance | 0.0696 | +| learning_rate | 4.87e-05 | +| loss | -0.0206 | +| n_updates | 26608 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000431 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1412 | +| iterations | 2699 | +| time_elapsed | 3913 | +| total_timesteps | 5527552 | +| train/ | | +| approx_kl | 0.010395008 | +| clip_fraction | 0.334 | +| clip_range | 0.0736 | +| entropy_loss | -7.13 | +| explained_variance | 0.364 | +| learning_rate | 4.87e-05 | +| loss | -0.0381 | +| n_updates | 26612 | +| policy_gradient_loss | -0.0242 | +| value_loss | 0.000115 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1412 | +| iterations | 2700 | +| time_elapsed | 3915 | +| total_timesteps | 5529600 | +| train/ | | +| approx_kl | 0.010915928 | +| clip_fraction | 0.326 | +| clip_range | 0.0736 | +| entropy_loss | -7.02 | +| explained_variance | 0.475 | +| learning_rate | 4.87e-05 | +| loss | -0.0307 | +| n_updates | 26616 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000134 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1412 | +| iterations | 2701 | +| time_elapsed | 3916 | +| total_timesteps | 5531648 | +| train/ | | +| approx_kl | 0.009352796 | +| clip_fraction | 0.334 | +| clip_range | 0.0736 | +| entropy_loss | -7.11 | +| explained_variance | 0.0917 | +| learning_rate | 4.87e-05 | +| loss | -0.0341 | +| n_updates | 26620 | +| policy_gradient_loss | -0.0203 | +| value_loss | 7.23e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1412 | +| iterations | 2702 | +| time_elapsed | 3917 | +| total_timesteps | 5533696 | +| train/ | | +| approx_kl | 0.008697545 | +| clip_fraction | 0.313 | +| clip_range | 0.0736 | +| entropy_loss | -7.21 | +| explained_variance | 0.223 | +| learning_rate | 4.87e-05 | +| loss | -0.0286 | +| n_updates | 26624 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000216 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1412 | +| iterations | 2703 | +| time_elapsed | 3919 | +| total_timesteps | 5535744 | +| train/ | | +| approx_kl | 0.008959348 | +| clip_fraction | 0.274 | +| clip_range | 0.0736 | +| entropy_loss | -6.66 | +| explained_variance | 0.282 | +| learning_rate | 4.87e-05 | +| loss | -0.0224 | +| n_updates | 26628 | +| policy_gradient_loss | -0.0135 | +| value_loss | 0.000338 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1412 | +| iterations | 2704 | +| time_elapsed | 3920 | +| total_timesteps | 5537792 | +| train/ | | +| approx_kl | 0.013244741 | +| clip_fraction | 0.345 | +| clip_range | 0.0736 | +| entropy_loss | -7.38 | +| explained_variance | -0.0822 | +| learning_rate | 4.87e-05 | +| loss | -0.0354 | +| n_updates | 26632 | +| policy_gradient_loss | -0.0219 | +| value_loss | 0.000184 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1412 | +| iterations | 2705 | +| time_elapsed | 3922 | +| total_timesteps | 5539840 | +| train/ | | +| approx_kl | 0.010859701 | +| clip_fraction | 0.317 | +| clip_range | 0.0736 | +| entropy_loss | -7.25 | +| explained_variance | -0.00688 | +| learning_rate | 4.87e-05 | +| loss | -0.0324 | +| n_updates | 26636 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000179 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1412 | +| iterations | 2706 | +| time_elapsed | 3923 | +| total_timesteps | 5541888 | +| train/ | | +| approx_kl | 0.00886683 | +| clip_fraction | 0.297 | +| clip_range | 0.0736 | +| entropy_loss | -7.05 | +| explained_variance | 0.237 | +| learning_rate | 4.87e-05 | +| loss | -0.0332 | +| n_updates | 26640 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000219 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1412 | +| iterations | 2707 | +| time_elapsed | 3924 | +| total_timesteps | 5543936 | +| train/ | | +| approx_kl | 0.011036577 | +| clip_fraction | 0.313 | +| clip_range | 0.0736 | +| entropy_loss | -7.28 | +| explained_variance | 0.264 | +| learning_rate | 4.87e-05 | +| loss | -0.0357 | +| n_updates | 26644 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000143 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1412 | +| iterations | 2708 | +| time_elapsed | 3926 | +| total_timesteps | 5545984 | +| train/ | | +| approx_kl | 0.010902787 | +| clip_fraction | 0.319 | +| clip_range | 0.0736 | +| entropy_loss | -7 | +| explained_variance | 0.209 | +| learning_rate | 4.87e-05 | +| loss | -0.0318 | +| n_updates | 26648 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000217 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1412 | +| iterations | 2709 | +| time_elapsed | 3927 | +| total_timesteps | 5548032 | +| train/ | | +| approx_kl | 0.0111266 | +| clip_fraction | 0.324 | +| clip_range | 0.0736 | +| entropy_loss | -7.05 | +| explained_variance | 0.337 | +| learning_rate | 4.87e-05 | +| loss | -0.0263 | +| n_updates | 26652 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000197 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1412 | +| iterations | 2710 | +| time_elapsed | 3929 | +| total_timesteps | 5550080 | +| train/ | | +| approx_kl | 0.012520481 | +| clip_fraction | 0.335 | +| clip_range | 0.0736 | +| entropy_loss | -7.11 | +| explained_variance | 0.273 | +| learning_rate | 4.87e-05 | +| loss | -0.0299 | +| n_updates | 26656 | +| policy_gradient_loss | -0.022 | +| value_loss | 0.00017 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1412 | +| iterations | 2711 | +| time_elapsed | 3930 | +| total_timesteps | 5552128 | +| train/ | | +| approx_kl | 0.010454735 | +| clip_fraction | 0.316 | +| clip_range | 0.0736 | +| entropy_loss | -7.05 | +| explained_variance | 0.422 | +| learning_rate | 4.87e-05 | +| loss | -0.0349 | +| n_updates | 26660 | +| policy_gradient_loss | -0.0209 | +| value_loss | 9.26e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1412 | +| iterations | 2712 | +| time_elapsed | 3931 | +| total_timesteps | 5554176 | +| train/ | | +| approx_kl | 0.011259793 | +| clip_fraction | 0.302 | +| clip_range | 0.0736 | +| entropy_loss | -6.99 | +| explained_variance | -0.0107 | +| learning_rate | 4.87e-05 | +| loss | -0.0308 | +| n_updates | 26664 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000201 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1412 | +| iterations | 2713 | +| time_elapsed | 3933 | +| total_timesteps | 5556224 | +| train/ | | +| approx_kl | 0.012662028 | +| clip_fraction | 0.314 | +| clip_range | 0.0736 | +| entropy_loss | -7.03 | +| explained_variance | 0.448 | +| learning_rate | 4.87e-05 | +| loss | -0.033 | +| n_updates | 26668 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000154 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1412 | +| iterations | 2714 | +| time_elapsed | 3934 | +| total_timesteps | 5558272 | +| train/ | | +| approx_kl | 0.013089049 | +| clip_fraction | 0.357 | +| clip_range | 0.0736 | +| entropy_loss | -7.15 | +| explained_variance | 0.692 | +| learning_rate | 4.87e-05 | +| loss | -0.0434 | +| n_updates | 26672 | +| policy_gradient_loss | -0.0256 | +| value_loss | 5.01e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1412 | +| iterations | 2715 | +| time_elapsed | 3936 | +| total_timesteps | 5560320 | +| train/ | | +| approx_kl | 0.01286323 | +| clip_fraction | 0.33 | +| clip_range | 0.0736 | +| entropy_loss | -7.28 | +| explained_variance | 0.0311 | +| learning_rate | 4.87e-05 | +| loss | -0.0336 | +| n_updates | 26676 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000183 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1412 | +| iterations | 2716 | +| time_elapsed | 3937 | +| total_timesteps | 5562368 | +| train/ | | +| approx_kl | 0.011454152 | +| clip_fraction | 0.322 | +| clip_range | 0.0736 | +| entropy_loss | -7.24 | +| explained_variance | 0.404 | +| learning_rate | 4.87e-05 | +| loss | -0.027 | +| n_updates | 26680 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000121 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1412 | +| iterations | 2717 | +| time_elapsed | 3939 | +| total_timesteps | 5564416 | +| train/ | | +| approx_kl | 0.012008213 | +| clip_fraction | 0.313 | +| clip_range | 0.0736 | +| entropy_loss | -7.09 | +| explained_variance | -0.0398 | +| learning_rate | 4.87e-05 | +| loss | -0.0288 | +| n_updates | 26684 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000121 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1412 | +| iterations | 2718 | +| time_elapsed | 3940 | +| total_timesteps | 5566464 | +| train/ | | +| approx_kl | 0.011484332 | +| clip_fraction | 0.328 | +| clip_range | 0.0736 | +| entropy_loss | -7.26 | +| explained_variance | -0.0249 | +| learning_rate | 4.87e-05 | +| loss | -0.0287 | +| n_updates | 26688 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000137 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1412 | +| iterations | 2719 | +| time_elapsed | 3942 | +| total_timesteps | 5568512 | +| train/ | | +| approx_kl | 0.011446189 | +| clip_fraction | 0.314 | +| clip_range | 0.0736 | +| entropy_loss | -6.97 | +| explained_variance | 0.221 | +| learning_rate | 4.87e-05 | +| loss | -0.0278 | +| n_updates | 26692 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000273 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1412 | +| iterations | 2720 | +| time_elapsed | 3943 | +| total_timesteps | 5570560 | +| train/ | | +| approx_kl | 0.012254988 | +| clip_fraction | 0.306 | +| clip_range | 0.0736 | +| entropy_loss | -6.89 | +| explained_variance | 0.23 | +| learning_rate | 4.87e-05 | +| loss | -0.0296 | +| n_updates | 26696 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000404 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1412 | +| iterations | 2721 | +| time_elapsed | 3944 | +| total_timesteps | 5572608 | +| train/ | | +| approx_kl | 0.01308641 | +| clip_fraction | 0.365 | +| clip_range | 0.0736 | +| entropy_loss | -7.11 | +| explained_variance | 0.189 | +| learning_rate | 4.87e-05 | +| loss | -0.0426 | +| n_updates | 26700 | +| policy_gradient_loss | -0.0282 | +| value_loss | 4.86e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1412 | +| iterations | 2722 | +| time_elapsed | 3946 | +| total_timesteps | 5574656 | +| train/ | | +| approx_kl | 0.012177308 | +| clip_fraction | 0.321 | +| clip_range | 0.0736 | +| entropy_loss | -7.01 | +| explained_variance | 0.35 | +| learning_rate | 4.87e-05 | +| loss | -0.0319 | +| n_updates | 26704 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000175 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1412 | +| iterations | 2723 | +| time_elapsed | 3947 | +| total_timesteps | 5576704 | +| train/ | | +| approx_kl | 0.010639877 | +| clip_fraction | 0.34 | +| clip_range | 0.0736 | +| entropy_loss | -7.01 | +| explained_variance | 0.524 | +| learning_rate | 4.87e-05 | +| loss | -0.0368 | +| n_updates | 26708 | +| policy_gradient_loss | -0.0224 | +| value_loss | 0.000112 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1412 | +| iterations | 2724 | +| time_elapsed | 3949 | +| total_timesteps | 5578752 | +| train/ | | +| approx_kl | 0.011249204 | +| clip_fraction | 0.331 | +| clip_range | 0.0736 | +| entropy_loss | -6.97 | +| explained_variance | 0.381 | +| learning_rate | 4.87e-05 | +| loss | -0.0344 | +| n_updates | 26712 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000235 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1412 | +| iterations | 2725 | +| time_elapsed | 3950 | +| total_timesteps | 5580800 | +| train/ | | +| approx_kl | 0.011820264 | +| clip_fraction | 0.328 | +| clip_range | 0.0736 | +| entropy_loss | -7.11 | +| explained_variance | 0.0642 | +| learning_rate | 4.87e-05 | +| loss | -0.0327 | +| n_updates | 26716 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.00013 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1412 | +| iterations | 2726 | +| time_elapsed | 3952 | +| total_timesteps | 5582848 | +| train/ | | +| approx_kl | 0.010312426 | +| clip_fraction | 0.314 | +| clip_range | 0.0736 | +| entropy_loss | -6.97 | +| explained_variance | 0.446 | +| learning_rate | 4.87e-05 | +| loss | -0.0314 | +| n_updates | 26720 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000137 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1412 | +| iterations | 2727 | +| time_elapsed | 3953 | +| total_timesteps | 5584896 | +| train/ | | +| approx_kl | 0.008561712 | +| clip_fraction | 0.286 | +| clip_range | 0.0736 | +| entropy_loss | -7.39 | +| explained_variance | -0.0468 | +| learning_rate | 4.87e-05 | +| loss | -0.0323 | +| n_updates | 26724 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.00012 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1412 | +| iterations | 2728 | +| time_elapsed | 3954 | +| total_timesteps | 5586944 | +| train/ | | +| approx_kl | 0.009757083 | +| clip_fraction | 0.312 | +| clip_range | 0.0736 | +| entropy_loss | -6.89 | +| explained_variance | 0.479 | +| learning_rate | 4.87e-05 | +| loss | -0.0341 | +| n_updates | 26728 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000259 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1412 | +| iterations | 2729 | +| time_elapsed | 3956 | +| total_timesteps | 5588992 | +| train/ | | +| approx_kl | 0.010871898 | +| clip_fraction | 0.286 | +| clip_range | 0.0736 | +| entropy_loss | -7.11 | +| explained_variance | 0.182 | +| learning_rate | 4.87e-05 | +| loss | -0.0288 | +| n_updates | 26732 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000264 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.385 | +| time/ | | +| fps | 1412 | +| iterations | 2730 | +| time_elapsed | 3957 | +| total_timesteps | 5591040 | +| train/ | | +| approx_kl | 0.0088659255 | +| clip_fraction | 0.288 | +| clip_range | 0.0736 | +| entropy_loss | -6.64 | +| explained_variance | 0.413 | +| learning_rate | 4.87e-05 | +| loss | -0.0317 | +| n_updates | 26736 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000327 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.389 | +| time/ | | +| fps | 1412 | +| iterations | 2731 | +| time_elapsed | 3959 | +| total_timesteps | 5593088 | +| train/ | | +| approx_kl | 0.009277576 | +| clip_fraction | 0.285 | +| clip_range | 0.0736 | +| entropy_loss | -7.3 | +| explained_variance | 0.173 | +| learning_rate | 4.87e-05 | +| loss | -0.033 | +| n_updates | 26740 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000286 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.386 | +| time/ | | +| fps | 1412 | +| iterations | 2732 | +| time_elapsed | 3960 | +| total_timesteps | 5595136 | +| train/ | | +| approx_kl | 0.009960863 | +| clip_fraction | 0.323 | +| clip_range | 0.0736 | +| entropy_loss | -6.9 | +| explained_variance | 0.203 | +| learning_rate | 4.87e-05 | +| loss | -0.0281 | +| n_updates | 26744 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000304 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.385 | +| time/ | | +| fps | 1412 | +| iterations | 2733 | +| time_elapsed | 3961 | +| total_timesteps | 5597184 | +| train/ | | +| approx_kl | 0.0140909925 | +| clip_fraction | 0.349 | +| clip_range | 0.0736 | +| entropy_loss | -7.02 | +| explained_variance | 0.198 | +| learning_rate | 4.87e-05 | +| loss | -0.0365 | +| n_updates | 26748 | +| policy_gradient_loss | -0.0238 | +| value_loss | 0.000251 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.385 | +| time/ | | +| fps | 1412 | +| iterations | 2734 | +| time_elapsed | 3963 | +| total_timesteps | 5599232 | +| train/ | | +| approx_kl | 0.011691911 | +| clip_fraction | 0.334 | +| clip_range | 0.0736 | +| entropy_loss | -7.25 | +| explained_variance | -0.0707 | +| learning_rate | 4.87e-05 | +| loss | -0.0288 | +| n_updates | 26752 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000235 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1412 | +| iterations | 2735 | +| time_elapsed | 3964 | +| total_timesteps | 5601280 | +| train/ | | +| approx_kl | 0.011144981 | +| clip_fraction | 0.332 | +| clip_range | 0.0736 | +| entropy_loss | -7.11 | +| explained_variance | 0.321 | +| learning_rate | 4.87e-05 | +| loss | -0.0328 | +| n_updates | 26756 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000184 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.384 | +| time/ | | +| fps | 1412 | +| iterations | 2736 | +| time_elapsed | 3966 | +| total_timesteps | 5603328 | +| train/ | | +| approx_kl | 0.011559345 | +| clip_fraction | 0.354 | +| clip_range | 0.0736 | +| entropy_loss | -7.28 | +| explained_variance | -0.18 | +| learning_rate | 4.87e-05 | +| loss | -0.0333 | +| n_updates | 26760 | +| policy_gradient_loss | -0.0229 | +| value_loss | 0.000172 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.384 | +| time/ | | +| fps | 1412 | +| iterations | 2737 | +| time_elapsed | 3967 | +| total_timesteps | 5605376 | +| train/ | | +| approx_kl | 0.009580215 | +| clip_fraction | 0.296 | +| clip_range | 0.0736 | +| entropy_loss | -7.04 | +| explained_variance | 0.0151 | +| learning_rate | 4.87e-05 | +| loss | -0.0314 | +| n_updates | 26764 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000359 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.384 | +| time/ | | +| fps | 1412 | +| iterations | 2738 | +| time_elapsed | 3969 | +| total_timesteps | 5607424 | +| train/ | | +| approx_kl | 0.010674806 | +| clip_fraction | 0.306 | +| clip_range | 0.0736 | +| entropy_loss | -7.04 | +| explained_variance | 0.0539 | +| learning_rate | 4.87e-05 | +| loss | -0.0323 | +| n_updates | 26768 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000254 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.394 | +| time/ | | +| fps | 1412 | +| iterations | 2739 | +| time_elapsed | 3970 | +| total_timesteps | 5609472 | +| train/ | | +| approx_kl | 0.00895493 | +| clip_fraction | 0.297 | +| clip_range | 0.0736 | +| entropy_loss | -6.87 | +| explained_variance | 0.251 | +| learning_rate | 4.87e-05 | +| loss | -0.029 | +| n_updates | 26772 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000255 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.397 | +| time/ | | +| fps | 1412 | +| iterations | 2740 | +| time_elapsed | 3971 | +| total_timesteps | 5611520 | +| train/ | | +| approx_kl | 0.00944512 | +| clip_fraction | 0.305 | +| clip_range | 0.0736 | +| entropy_loss | -7.01 | +| explained_variance | 0.121 | +| learning_rate | 4.87e-05 | +| loss | -0.0227 | +| n_updates | 26776 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.000322 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.392 | +| time/ | | +| fps | 1412 | +| iterations | 2741 | +| time_elapsed | 3973 | +| total_timesteps | 5613568 | +| train/ | | +| approx_kl | 0.010430022 | +| clip_fraction | 0.319 | +| clip_range | 0.0736 | +| entropy_loss | -7.11 | +| explained_variance | -0.0283 | +| learning_rate | 4.87e-05 | +| loss | -0.0333 | +| n_updates | 26780 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000115 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.388 | +| time/ | | +| fps | 1412 | +| iterations | 2742 | +| time_elapsed | 3974 | +| total_timesteps | 5615616 | +| train/ | | +| approx_kl | 0.01126431 | +| clip_fraction | 0.29 | +| clip_range | 0.0736 | +| entropy_loss | -6.9 | +| explained_variance | 0.352 | +| learning_rate | 4.87e-05 | +| loss | -0.0271 | +| n_updates | 26784 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000157 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.392 | +| time/ | | +| fps | 1412 | +| iterations | 2743 | +| time_elapsed | 3976 | +| total_timesteps | 5617664 | +| train/ | | +| approx_kl | 0.012010794 | +| clip_fraction | 0.323 | +| clip_range | 0.0736 | +| entropy_loss | -7.15 | +| explained_variance | -0.067 | +| learning_rate | 4.87e-05 | +| loss | -0.0351 | +| n_updates | 26788 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000131 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.397 | +| time/ | | +| fps | 1412 | +| iterations | 2744 | +| time_elapsed | 3977 | +| total_timesteps | 5619712 | +| train/ | | +| approx_kl | 0.012131671 | +| clip_fraction | 0.317 | +| clip_range | 0.0736 | +| entropy_loss | -7.19 | +| explained_variance | 0.166 | +| learning_rate | 4.87e-05 | +| loss | -0.0315 | +| n_updates | 26792 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000142 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.395 | +| time/ | | +| fps | 1412 | +| iterations | 2745 | +| time_elapsed | 3979 | +| total_timesteps | 5621760 | +| train/ | | +| approx_kl | 0.011509975 | +| clip_fraction | 0.334 | +| clip_range | 0.0736 | +| entropy_loss | -7.14 | +| explained_variance | 0.126 | +| learning_rate | 4.87e-05 | +| loss | -0.0362 | +| n_updates | 26796 | +| policy_gradient_loss | -0.0223 | +| value_loss | 0.000387 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.385 | +| time/ | | +| fps | 1412 | +| iterations | 2746 | +| time_elapsed | 3980 | +| total_timesteps | 5623808 | +| train/ | | +| approx_kl | 0.0106493905 | +| clip_fraction | 0.332 | +| clip_range | 0.0736 | +| entropy_loss | -7.1 | +| explained_variance | 0.293 | +| learning_rate | 4.87e-05 | +| loss | -0.0347 | +| n_updates | 26800 | +| policy_gradient_loss | -0.0221 | +| value_loss | 0.000164 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1412 | +| iterations | 2747 | +| time_elapsed | 3982 | +| total_timesteps | 5625856 | +| train/ | | +| approx_kl | 0.010807612 | +| clip_fraction | 0.324 | +| clip_range | 0.0736 | +| entropy_loss | -7.04 | +| explained_variance | 0.2 | +| learning_rate | 4.87e-05 | +| loss | -0.0384 | +| n_updates | 26804 | +| policy_gradient_loss | -0.0219 | +| value_loss | 0.000177 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.384 | +| time/ | | +| fps | 1412 | +| iterations | 2748 | +| time_elapsed | 3983 | +| total_timesteps | 5627904 | +| train/ | | +| approx_kl | 0.011696229 | +| clip_fraction | 0.334 | +| clip_range | 0.0736 | +| entropy_loss | -6.98 | +| explained_variance | 0.694 | +| learning_rate | 4.87e-05 | +| loss | -0.0358 | +| n_updates | 26808 | +| policy_gradient_loss | -0.0221 | +| value_loss | 6.33e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1412 | +| iterations | 2749 | +| time_elapsed | 3984 | +| total_timesteps | 5629952 | +| train/ | | +| approx_kl | 0.009719452 | +| clip_fraction | 0.302 | +| clip_range | 0.0736 | +| entropy_loss | -6.74 | +| explained_variance | 0.257 | +| learning_rate | 4.87e-05 | +| loss | -0.023 | +| n_updates | 26812 | +| policy_gradient_loss | -0.0147 | +| value_loss | 0.000444 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1412 | +| iterations | 2750 | +| time_elapsed | 3986 | +| total_timesteps | 5632000 | +| train/ | | +| approx_kl | 0.011868225 | +| clip_fraction | 0.325 | +| clip_range | 0.0736 | +| entropy_loss | -7.25 | +| explained_variance | -0.0253 | +| learning_rate | 4.87e-05 | +| loss | -0.0368 | +| n_updates | 26816 | +| policy_gradient_loss | -0.0228 | +| value_loss | 0.000207 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.387 | +| time/ | | +| fps | 1412 | +| iterations | 2751 | +| time_elapsed | 3987 | +| total_timesteps | 5634048 | +| train/ | | +| approx_kl | 0.009906527 | +| clip_fraction | 0.336 | +| clip_range | 0.0736 | +| entropy_loss | -7.17 | +| explained_variance | 0.153 | +| learning_rate | 4.87e-05 | +| loss | -0.037 | +| n_updates | 26820 | +| policy_gradient_loss | -0.0233 | +| value_loss | 0.00015 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.387 | +| time/ | | +| fps | 1412 | +| iterations | 2752 | +| time_elapsed | 3989 | +| total_timesteps | 5636096 | +| train/ | | +| approx_kl | 0.00852185 | +| clip_fraction | 0.287 | +| clip_range | 0.0736 | +| entropy_loss | -7.27 | +| explained_variance | 0.084 | +| learning_rate | 4.87e-05 | +| loss | -0.0302 | +| n_updates | 26824 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000281 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.394 | +| time/ | | +| fps | 1412 | +| iterations | 2753 | +| time_elapsed | 3990 | +| total_timesteps | 5638144 | +| train/ | | +| approx_kl | 0.012313262 | +| clip_fraction | 0.33 | +| clip_range | 0.0736 | +| entropy_loss | -7.38 | +| explained_variance | -0.218 | +| learning_rate | 4.87e-05 | +| loss | -0.0396 | +| n_updates | 26828 | +| policy_gradient_loss | -0.0227 | +| value_loss | 0.000128 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.394 | +| time/ | | +| fps | 1412 | +| iterations | 2754 | +| time_elapsed | 3991 | +| total_timesteps | 5640192 | +| train/ | | +| approx_kl | 0.010437382 | +| clip_fraction | 0.287 | +| clip_range | 0.0736 | +| entropy_loss | -7.18 | +| explained_variance | 0.405 | +| learning_rate | 4.87e-05 | +| loss | -0.0295 | +| n_updates | 26832 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000119 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.396 | +| time/ | | +| fps | 1412 | +| iterations | 2755 | +| time_elapsed | 3993 | +| total_timesteps | 5642240 | +| train/ | | +| approx_kl | 0.010731206 | +| clip_fraction | 0.331 | +| clip_range | 0.0736 | +| entropy_loss | -6.97 | +| explained_variance | 0.654 | +| learning_rate | 4.87e-05 | +| loss | -0.033 | +| n_updates | 26836 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000113 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.397 | +| time/ | | +| fps | 1412 | +| iterations | 2756 | +| time_elapsed | 3994 | +| total_timesteps | 5644288 | +| train/ | | +| approx_kl | 0.010815658 | +| clip_fraction | 0.33 | +| clip_range | 0.0736 | +| entropy_loss | -7.23 | +| explained_variance | 0.472 | +| learning_rate | 4.87e-05 | +| loss | -0.0403 | +| n_updates | 26840 | +| policy_gradient_loss | -0.0208 | +| value_loss | 7.52e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.397 | +| time/ | | +| fps | 1412 | +| iterations | 2757 | +| time_elapsed | 3996 | +| total_timesteps | 5646336 | +| train/ | | +| approx_kl | 0.010323865 | +| clip_fraction | 0.288 | +| clip_range | 0.0736 | +| entropy_loss | -6.85 | +| explained_variance | 0.466 | +| learning_rate | 4.87e-05 | +| loss | -0.0277 | +| n_updates | 26844 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.00017 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.392 | +| time/ | | +| fps | 1412 | +| iterations | 2758 | +| time_elapsed | 3997 | +| total_timesteps | 5648384 | +| train/ | | +| approx_kl | 0.010319719 | +| clip_fraction | 0.325 | +| clip_range | 0.0736 | +| entropy_loss | -7.4 | +| explained_variance | -0.174 | +| learning_rate | 4.87e-05 | +| loss | -0.0357 | +| n_updates | 26848 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000143 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.394 | +| time/ | | +| fps | 1412 | +| iterations | 2759 | +| time_elapsed | 3999 | +| total_timesteps | 5650432 | +| train/ | | +| approx_kl | 0.009574355 | +| clip_fraction | 0.275 | +| clip_range | 0.0736 | +| entropy_loss | -6.96 | +| explained_variance | 0.347 | +| learning_rate | 4.87e-05 | +| loss | -0.0192 | +| n_updates | 26852 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000281 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.395 | +| time/ | | +| fps | 1412 | +| iterations | 2760 | +| time_elapsed | 4000 | +| total_timesteps | 5652480 | +| train/ | | +| approx_kl | 0.009786239 | +| clip_fraction | 0.297 | +| clip_range | 0.0736 | +| entropy_loss | -6.81 | +| explained_variance | 0.226 | +| learning_rate | 4.87e-05 | +| loss | -0.028 | +| n_updates | 26856 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000317 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.402 | +| time/ | | +| fps | 1412 | +| iterations | 2761 | +| time_elapsed | 4001 | +| total_timesteps | 5654528 | +| train/ | | +| approx_kl | 0.009063103 | +| clip_fraction | 0.295 | +| clip_range | 0.0736 | +| entropy_loss | -6.81 | +| explained_variance | 0.282 | +| learning_rate | 4.87e-05 | +| loss | -0.026 | +| n_updates | 26860 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000282 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.402 | +| time/ | | +| fps | 1412 | +| iterations | 2762 | +| time_elapsed | 4003 | +| total_timesteps | 5656576 | +| train/ | | +| approx_kl | 0.010727042 | +| clip_fraction | 0.306 | +| clip_range | 0.0736 | +| entropy_loss | -7.16 | +| explained_variance | 0.000695 | +| learning_rate | 4.87e-05 | +| loss | -0.0276 | +| n_updates | 26864 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000373 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.397 | +| time/ | | +| fps | 1412 | +| iterations | 2763 | +| time_elapsed | 4004 | +| total_timesteps | 5658624 | +| train/ | | +| approx_kl | 0.009593157 | +| clip_fraction | 0.32 | +| clip_range | 0.0736 | +| entropy_loss | -7.11 | +| explained_variance | 0.284 | +| learning_rate | 4.87e-05 | +| loss | -0.0365 | +| n_updates | 26868 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000191 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.4 | +| time/ | | +| fps | 1412 | +| iterations | 2764 | +| time_elapsed | 4006 | +| total_timesteps | 5660672 | +| train/ | | +| approx_kl | 0.008779609 | +| clip_fraction | 0.302 | +| clip_range | 0.0736 | +| entropy_loss | -6.98 | +| explained_variance | 0.12 | +| learning_rate | 4.87e-05 | +| loss | -0.0317 | +| n_updates | 26872 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000343 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.402 | +| time/ | | +| fps | 1412 | +| iterations | 2765 | +| time_elapsed | 4007 | +| total_timesteps | 5662720 | +| train/ | | +| approx_kl | 0.008129157 | +| clip_fraction | 0.301 | +| clip_range | 0.0736 | +| entropy_loss | -7.03 | +| explained_variance | 0.0779 | +| learning_rate | 4.87e-05 | +| loss | -0.0328 | +| n_updates | 26876 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000486 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.405 | +| time/ | | +| fps | 1412 | +| iterations | 2766 | +| time_elapsed | 4009 | +| total_timesteps | 5664768 | +| train/ | | +| approx_kl | 0.006934993 | +| clip_fraction | 0.282 | +| clip_range | 0.0736 | +| entropy_loss | -7.04 | +| explained_variance | 0.177 | +| learning_rate | 4.87e-05 | +| loss | -0.0251 | +| n_updates | 26880 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000303 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.408 | +| time/ | | +| fps | 1412 | +| iterations | 2767 | +| time_elapsed | 4010 | +| total_timesteps | 5666816 | +| train/ | | +| approx_kl | 0.0085413065 | +| clip_fraction | 0.303 | +| clip_range | 0.0736 | +| entropy_loss | -7.15 | +| explained_variance | 0.256 | +| learning_rate | 4.87e-05 | +| loss | -0.034 | +| n_updates | 26884 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000246 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.405 | +| time/ | | +| fps | 1412 | +| iterations | 2768 | +| time_elapsed | 4012 | +| total_timesteps | 5668864 | +| train/ | | +| approx_kl | 0.010459876 | +| clip_fraction | 0.303 | +| clip_range | 0.0736 | +| entropy_loss | -7.09 | +| explained_variance | 0.119 | +| learning_rate | 4.87e-05 | +| loss | -0.0302 | +| n_updates | 26888 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000293 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.408 | +| time/ | | +| fps | 1412 | +| iterations | 2769 | +| time_elapsed | 4013 | +| total_timesteps | 5670912 | +| train/ | | +| approx_kl | 0.012801575 | +| clip_fraction | 0.355 | +| clip_range | 0.0736 | +| entropy_loss | -6.96 | +| explained_variance | 0.368 | +| learning_rate | 4.87e-05 | +| loss | -0.0323 | +| n_updates | 26892 | +| policy_gradient_loss | -0.0232 | +| value_loss | 0.000119 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.408 | +| time/ | | +| fps | 1412 | +| iterations | 2770 | +| time_elapsed | 4015 | +| total_timesteps | 5672960 | +| train/ | | +| approx_kl | 0.0091699585 | +| clip_fraction | 0.289 | +| clip_range | 0.0736 | +| entropy_loss | -7.23 | +| explained_variance | 0.0416 | +| learning_rate | 4.87e-05 | +| loss | -0.0294 | +| n_updates | 26896 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000223 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.408 | +| time/ | | +| fps | 1412 | +| iterations | 2771 | +| time_elapsed | 4016 | +| total_timesteps | 5675008 | +| train/ | | +| approx_kl | 0.010750513 | +| clip_fraction | 0.288 | +| clip_range | 0.0736 | +| entropy_loss | -6.89 | +| explained_variance | 0.389 | +| learning_rate | 4.87e-05 | +| loss | -0.0315 | +| n_updates | 26900 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000283 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.411 | +| time/ | | +| fps | 1412 | +| iterations | 2772 | +| time_elapsed | 4017 | +| total_timesteps | 5677056 | +| train/ | | +| approx_kl | 0.01098547 | +| clip_fraction | 0.322 | +| clip_range | 0.0736 | +| entropy_loss | -7.34 | +| explained_variance | -0.184 | +| learning_rate | 4.87e-05 | +| loss | -0.0393 | +| n_updates | 26904 | +| policy_gradient_loss | -0.0228 | +| value_loss | 0.000125 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.41 | +| time/ | | +| fps | 1412 | +| iterations | 2773 | +| time_elapsed | 4019 | +| total_timesteps | 5679104 | +| train/ | | +| approx_kl | 0.012817148 | +| clip_fraction | 0.327 | +| clip_range | 0.0736 | +| entropy_loss | -7.13 | +| explained_variance | 0.432 | +| learning_rate | 4.87e-05 | +| loss | -0.0331 | +| n_updates | 26908 | +| policy_gradient_loss | -0.0222 | +| value_loss | 9.04e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.41 | +| time/ | | +| fps | 1412 | +| iterations | 2774 | +| time_elapsed | 4020 | +| total_timesteps | 5681152 | +| train/ | | +| approx_kl | 0.012232699 | +| clip_fraction | 0.328 | +| clip_range | 0.0736 | +| entropy_loss | -6.65 | +| explained_variance | 0.497 | +| learning_rate | 4.87e-05 | +| loss | -0.0311 | +| n_updates | 26912 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000194 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.409 | +| time/ | | +| fps | 1412 | +| iterations | 2775 | +| time_elapsed | 4022 | +| total_timesteps | 5683200 | +| train/ | | +| approx_kl | 0.01186404 | +| clip_fraction | 0.286 | +| clip_range | 0.0736 | +| entropy_loss | -7.15 | +| explained_variance | -0.137 | +| learning_rate | 4.87e-05 | +| loss | -0.0335 | +| n_updates | 26916 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.00018 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.409 | +| time/ | | +| fps | 1412 | +| iterations | 2776 | +| time_elapsed | 4023 | +| total_timesteps | 5685248 | +| train/ | | +| approx_kl | 0.011282086 | +| clip_fraction | 0.285 | +| clip_range | 0.0736 | +| entropy_loss | -7.26 | +| explained_variance | 0.0616 | +| learning_rate | 4.87e-05 | +| loss | -0.0284 | +| n_updates | 26920 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000261 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.411 | +| time/ | | +| fps | 1412 | +| iterations | 2777 | +| time_elapsed | 4025 | +| total_timesteps | 5687296 | +| train/ | | +| approx_kl | 0.012304013 | +| clip_fraction | 0.354 | +| clip_range | 0.0736 | +| entropy_loss | -7.23 | +| explained_variance | 0.299 | +| learning_rate | 4.86e-05 | +| loss | -0.039 | +| n_updates | 26924 | +| policy_gradient_loss | -0.0242 | +| value_loss | 9.21e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.408 | +| time/ | | +| fps | 1413 | +| iterations | 2778 | +| time_elapsed | 4026 | +| total_timesteps | 5689344 | +| train/ | | +| approx_kl | 0.011401965 | +| clip_fraction | 0.34 | +| clip_range | 0.0736 | +| entropy_loss | -7.23 | +| explained_variance | -0.135 | +| learning_rate | 4.86e-05 | +| loss | -0.035 | +| n_updates | 26928 | +| policy_gradient_loss | -0.0227 | +| value_loss | 7.42e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.41 | +| time/ | | +| fps | 1413 | +| iterations | 2779 | +| time_elapsed | 4027 | +| total_timesteps | 5691392 | +| train/ | | +| approx_kl | 0.012102548 | +| clip_fraction | 0.318 | +| clip_range | 0.0736 | +| entropy_loss | -7.09 | +| explained_variance | 0.0249 | +| learning_rate | 4.86e-05 | +| loss | -0.0306 | +| n_updates | 26932 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000114 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.407 | +| time/ | | +| fps | 1413 | +| iterations | 2780 | +| time_elapsed | 4029 | +| total_timesteps | 5693440 | +| train/ | | +| approx_kl | 0.011969952 | +| clip_fraction | 0.312 | +| clip_range | 0.0736 | +| entropy_loss | -7.37 | +| explained_variance | -0.053 | +| learning_rate | 4.86e-05 | +| loss | -0.029 | +| n_updates | 26936 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.00024 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.405 | +| time/ | | +| fps | 1413 | +| iterations | 2781 | +| time_elapsed | 4030 | +| total_timesteps | 5695488 | +| train/ | | +| approx_kl | 0.011640906 | +| clip_fraction | 0.313 | +| clip_range | 0.0736 | +| entropy_loss | -7.05 | +| explained_variance | 0.266 | +| learning_rate | 4.86e-05 | +| loss | -0.0306 | +| n_updates | 26940 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000192 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.411 | +| time/ | | +| fps | 1413 | +| iterations | 2782 | +| time_elapsed | 4032 | +| total_timesteps | 5697536 | +| train/ | | +| approx_kl | 0.012036389 | +| clip_fraction | 0.316 | +| clip_range | 0.0736 | +| entropy_loss | -7.17 | +| explained_variance | -0.126 | +| learning_rate | 4.86e-05 | +| loss | -0.0318 | +| n_updates | 26944 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000177 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.412 | +| time/ | | +| fps | 1413 | +| iterations | 2783 | +| time_elapsed | 4033 | +| total_timesteps | 5699584 | +| train/ | | +| approx_kl | 0.01098203 | +| clip_fraction | 0.308 | +| clip_range | 0.0736 | +| entropy_loss | -6.8 | +| explained_variance | 0.28 | +| learning_rate | 4.86e-05 | +| loss | -0.0315 | +| n_updates | 26948 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000294 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.412 | +| time/ | | +| fps | 1413 | +| iterations | 2784 | +| time_elapsed | 4034 | +| total_timesteps | 5701632 | +| train/ | | +| approx_kl | 0.010019887 | +| clip_fraction | 0.309 | +| clip_range | 0.0736 | +| entropy_loss | -6.82 | +| explained_variance | 0.122 | +| learning_rate | 4.86e-05 | +| loss | -0.0329 | +| n_updates | 26952 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000226 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.415 | +| time/ | | +| fps | 1413 | +| iterations | 2785 | +| time_elapsed | 4036 | +| total_timesteps | 5703680 | +| train/ | | +| approx_kl | 0.012419301 | +| clip_fraction | 0.338 | +| clip_range | 0.0736 | +| entropy_loss | -7.06 | +| explained_variance | 0.087 | +| learning_rate | 4.86e-05 | +| loss | -0.0371 | +| n_updates | 26956 | +| policy_gradient_loss | -0.023 | +| value_loss | 0.000119 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.415 | +| time/ | | +| fps | 1413 | +| iterations | 2786 | +| time_elapsed | 4037 | +| total_timesteps | 5705728 | +| train/ | | +| approx_kl | 0.011243539 | +| clip_fraction | 0.317 | +| clip_range | 0.0736 | +| entropy_loss | -6.94 | +| explained_variance | 0.397 | +| learning_rate | 4.86e-05 | +| loss | -0.0327 | +| n_updates | 26960 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000221 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.412 | +| time/ | | +| fps | 1413 | +| iterations | 2787 | +| time_elapsed | 4039 | +| total_timesteps | 5707776 | +| train/ | | +| approx_kl | 0.011807431 | +| clip_fraction | 0.314 | +| clip_range | 0.0736 | +| entropy_loss | -7.38 | +| explained_variance | -0.0472 | +| learning_rate | 4.86e-05 | +| loss | -0.03 | +| n_updates | 26964 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000249 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.414 | +| time/ | | +| fps | 1413 | +| iterations | 2788 | +| time_elapsed | 4040 | +| total_timesteps | 5709824 | +| train/ | | +| approx_kl | 0.012993392 | +| clip_fraction | 0.334 | +| clip_range | 0.0736 | +| entropy_loss | -7.24 | +| explained_variance | -0.181 | +| learning_rate | 4.86e-05 | +| loss | -0.0348 | +| n_updates | 26968 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000115 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.409 | +| time/ | | +| fps | 1413 | +| iterations | 2789 | +| time_elapsed | 4042 | +| total_timesteps | 5711872 | +| train/ | | +| approx_kl | 0.010222356 | +| clip_fraction | 0.315 | +| clip_range | 0.0736 | +| entropy_loss | -7.32 | +| explained_variance | -0.0614 | +| learning_rate | 4.86e-05 | +| loss | -0.0327 | +| n_updates | 26972 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000139 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.406 | +| time/ | | +| fps | 1413 | +| iterations | 2790 | +| time_elapsed | 4043 | +| total_timesteps | 5713920 | +| train/ | | +| approx_kl | 0.011975623 | +| clip_fraction | 0.303 | +| clip_range | 0.0736 | +| entropy_loss | -7.01 | +| explained_variance | 0.21 | +| learning_rate | 4.86e-05 | +| loss | -0.0284 | +| n_updates | 26976 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000197 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.411 | +| time/ | | +| fps | 1413 | +| iterations | 2791 | +| time_elapsed | 4045 | +| total_timesteps | 5715968 | +| train/ | | +| approx_kl | 0.011474535 | +| clip_fraction | 0.328 | +| clip_range | 0.0736 | +| entropy_loss | -7.28 | +| explained_variance | 0.334 | +| learning_rate | 4.86e-05 | +| loss | -0.0373 | +| n_updates | 26980 | +| policy_gradient_loss | -0.0231 | +| value_loss | 9.74e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.41 | +| time/ | | +| fps | 1413 | +| iterations | 2792 | +| time_elapsed | 4046 | +| total_timesteps | 5718016 | +| train/ | | +| approx_kl | 0.010235365 | +| clip_fraction | 0.302 | +| clip_range | 0.0736 | +| entropy_loss | -6.96 | +| explained_variance | 0.0983 | +| learning_rate | 4.86e-05 | +| loss | -0.0245 | +| n_updates | 26984 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000215 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.404 | +| time/ | | +| fps | 1413 | +| iterations | 2793 | +| time_elapsed | 4047 | +| total_timesteps | 5720064 | +| train/ | | +| approx_kl | 0.011779964 | +| clip_fraction | 0.307 | +| clip_range | 0.0736 | +| entropy_loss | -7.1 | +| explained_variance | -0.11 | +| learning_rate | 4.86e-05 | +| loss | -0.0329 | +| n_updates | 26988 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000188 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.391 | +| time/ | | +| fps | 1413 | +| iterations | 2794 | +| time_elapsed | 4049 | +| total_timesteps | 5722112 | +| train/ | | +| approx_kl | 0.010555558 | +| clip_fraction | 0.329 | +| clip_range | 0.0736 | +| entropy_loss | -6.81 | +| explained_variance | 0.339 | +| learning_rate | 4.86e-05 | +| loss | -0.0341 | +| n_updates | 26992 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000144 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.393 | +| time/ | | +| fps | 1413 | +| iterations | 2795 | +| time_elapsed | 4050 | +| total_timesteps | 5724160 | +| train/ | | +| approx_kl | 0.011568354 | +| clip_fraction | 0.308 | +| clip_range | 0.0736 | +| entropy_loss | -6.69 | +| explained_variance | 0.542 | +| learning_rate | 4.86e-05 | +| loss | -0.0255 | +| n_updates | 26996 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000135 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.391 | +| time/ | | +| fps | 1413 | +| iterations | 2796 | +| time_elapsed | 4052 | +| total_timesteps | 5726208 | +| train/ | | +| approx_kl | 0.012759501 | +| clip_fraction | 0.305 | +| clip_range | 0.0736 | +| entropy_loss | -7.07 | +| explained_variance | 0.265 | +| learning_rate | 4.86e-05 | +| loss | -0.0309 | +| n_updates | 27000 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000176 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.397 | +| time/ | | +| fps | 1413 | +| iterations | 2797 | +| time_elapsed | 4053 | +| total_timesteps | 5728256 | +| train/ | | +| approx_kl | 0.012202142 | +| clip_fraction | 0.316 | +| clip_range | 0.0736 | +| entropy_loss | -7.22 | +| explained_variance | 0.172 | +| learning_rate | 4.86e-05 | +| loss | -0.036 | +| n_updates | 27004 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000216 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.395 | +| time/ | | +| fps | 1413 | +| iterations | 2798 | +| time_elapsed | 4055 | +| total_timesteps | 5730304 | +| train/ | | +| approx_kl | 0.00880729 | +| clip_fraction | 0.255 | +| clip_range | 0.0736 | +| entropy_loss | -7.23 | +| explained_variance | -0.0686 | +| learning_rate | 4.86e-05 | +| loss | -0.0282 | +| n_updates | 27008 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000348 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.395 | +| time/ | | +| fps | 1413 | +| iterations | 2799 | +| time_elapsed | 4056 | +| total_timesteps | 5732352 | +| train/ | | +| approx_kl | 0.009215785 | +| clip_fraction | 0.32 | +| clip_range | 0.0736 | +| entropy_loss | -7.16 | +| explained_variance | 0.323 | +| learning_rate | 4.86e-05 | +| loss | -0.0309 | +| n_updates | 27012 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000113 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.386 | +| time/ | | +| fps | 1413 | +| iterations | 2800 | +| time_elapsed | 4057 | +| total_timesteps | 5734400 | +| train/ | | +| approx_kl | 0.01264238 | +| clip_fraction | 0.317 | +| clip_range | 0.0736 | +| entropy_loss | -7.32 | +| explained_variance | 0.144 | +| learning_rate | 4.86e-05 | +| loss | -0.0336 | +| n_updates | 27016 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000219 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.388 | +| time/ | | +| fps | 1413 | +| iterations | 2801 | +| time_elapsed | 4059 | +| total_timesteps | 5736448 | +| train/ | | +| approx_kl | 0.009426799 | +| clip_fraction | 0.286 | +| clip_range | 0.0736 | +| entropy_loss | -6.85 | +| explained_variance | 0.24 | +| learning_rate | 4.86e-05 | +| loss | -0.0261 | +| n_updates | 27020 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000336 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.392 | +| time/ | | +| fps | 1413 | +| iterations | 2802 | +| time_elapsed | 4060 | +| total_timesteps | 5738496 | +| train/ | | +| approx_kl | 0.012168122 | +| clip_fraction | 0.328 | +| clip_range | 0.0736 | +| entropy_loss | -7.16 | +| explained_variance | -0.00814 | +| learning_rate | 4.86e-05 | +| loss | -0.0242 | +| n_updates | 27024 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000267 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.392 | +| time/ | | +| fps | 1413 | +| iterations | 2803 | +| time_elapsed | 4062 | +| total_timesteps | 5740544 | +| train/ | | +| approx_kl | 0.01148341 | +| clip_fraction | 0.321 | +| clip_range | 0.0736 | +| entropy_loss | -6.86 | +| explained_variance | 0.496 | +| learning_rate | 4.86e-05 | +| loss | -0.0258 | +| n_updates | 27028 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000181 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.389 | +| time/ | | +| fps | 1413 | +| iterations | 2804 | +| time_elapsed | 4063 | +| total_timesteps | 5742592 | +| train/ | | +| approx_kl | 0.011063337 | +| clip_fraction | 0.325 | +| clip_range | 0.0736 | +| entropy_loss | -7.08 | +| explained_variance | 0.086 | +| learning_rate | 4.86e-05 | +| loss | -0.0309 | +| n_updates | 27032 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000166 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.389 | +| time/ | | +| fps | 1413 | +| iterations | 2805 | +| time_elapsed | 4065 | +| total_timesteps | 5744640 | +| train/ | | +| approx_kl | 0.0136299925 | +| clip_fraction | 0.318 | +| clip_range | 0.0736 | +| entropy_loss | -7.13 | +| explained_variance | 0.342 | +| learning_rate | 4.86e-05 | +| loss | -0.0334 | +| n_updates | 27036 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000115 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.393 | +| time/ | | +| fps | 1413 | +| iterations | 2806 | +| time_elapsed | 4066 | +| total_timesteps | 5746688 | +| train/ | | +| approx_kl | 0.010571522 | +| clip_fraction | 0.316 | +| clip_range | 0.0736 | +| entropy_loss | -6.97 | +| explained_variance | 0.289 | +| learning_rate | 4.86e-05 | +| loss | -0.0317 | +| n_updates | 27040 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.00026 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.393 | +| time/ | | +| fps | 1413 | +| iterations | 2807 | +| time_elapsed | 4068 | +| total_timesteps | 5748736 | +| train/ | | +| approx_kl | 0.010922642 | +| clip_fraction | 0.326 | +| clip_range | 0.0736 | +| entropy_loss | -7.13 | +| explained_variance | 0.186 | +| learning_rate | 4.86e-05 | +| loss | -0.0324 | +| n_updates | 27044 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000204 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.404 | +| time/ | | +| fps | 1413 | +| iterations | 2808 | +| time_elapsed | 4069 | +| total_timesteps | 5750784 | +| train/ | | +| approx_kl | 0.011153776 | +| clip_fraction | 0.31 | +| clip_range | 0.0736 | +| entropy_loss | -7.41 | +| explained_variance | -0.11 | +| learning_rate | 4.86e-05 | +| loss | -0.0332 | +| n_updates | 27048 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000175 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.408 | +| time/ | | +| fps | 1413 | +| iterations | 2809 | +| time_elapsed | 4071 | +| total_timesteps | 5752832 | +| train/ | | +| approx_kl | 0.011226993 | +| clip_fraction | 0.289 | +| clip_range | 0.0736 | +| entropy_loss | -7.13 | +| explained_variance | 0.154 | +| learning_rate | 4.86e-05 | +| loss | -0.0268 | +| n_updates | 27052 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000342 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.406 | +| time/ | | +| fps | 1413 | +| iterations | 2810 | +| time_elapsed | 4072 | +| total_timesteps | 5754880 | +| train/ | | +| approx_kl | 0.014053449 | +| clip_fraction | 0.322 | +| clip_range | 0.0736 | +| entropy_loss | -7.18 | +| explained_variance | 0.262 | +| learning_rate | 4.86e-05 | +| loss | -0.0323 | +| n_updates | 27056 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000155 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.406 | +| time/ | | +| fps | 1413 | +| iterations | 2811 | +| time_elapsed | 4073 | +| total_timesteps | 5756928 | +| train/ | | +| approx_kl | 0.011505727 | +| clip_fraction | 0.32 | +| clip_range | 0.0736 | +| entropy_loss | -7.02 | +| explained_variance | 0.194 | +| learning_rate | 4.86e-05 | +| loss | -0.0344 | +| n_updates | 27060 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000314 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.404 | +| time/ | | +| fps | 1413 | +| iterations | 2812 | +| time_elapsed | 4075 | +| total_timesteps | 5758976 | +| train/ | | +| approx_kl | 0.014516594 | +| clip_fraction | 0.324 | +| clip_range | 0.0736 | +| entropy_loss | -7.25 | +| explained_variance | 0.254 | +| learning_rate | 4.86e-05 | +| loss | -0.0373 | +| n_updates | 27064 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000132 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.408 | +| time/ | | +| fps | 1413 | +| iterations | 2813 | +| time_elapsed | 4076 | +| total_timesteps | 5761024 | +| train/ | | +| approx_kl | 0.010979168 | +| clip_fraction | 0.328 | +| clip_range | 0.0736 | +| entropy_loss | -7.28 | +| explained_variance | 0.455 | +| learning_rate | 4.86e-05 | +| loss | -0.0364 | +| n_updates | 27068 | +| policy_gradient_loss | -0.0243 | +| value_loss | 7.93e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.406 | +| time/ | | +| fps | 1413 | +| iterations | 2814 | +| time_elapsed | 4078 | +| total_timesteps | 5763072 | +| train/ | | +| approx_kl | 0.010051149 | +| clip_fraction | 0.307 | +| clip_range | 0.0736 | +| entropy_loss | -7.03 | +| explained_variance | 0.0315 | +| learning_rate | 4.86e-05 | +| loss | -0.0286 | +| n_updates | 27072 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000178 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.406 | +| time/ | | +| fps | 1413 | +| iterations | 2815 | +| time_elapsed | 4079 | +| total_timesteps | 5765120 | +| train/ | | +| approx_kl | 0.011227312 | +| clip_fraction | 0.307 | +| clip_range | 0.0736 | +| entropy_loss | -7.04 | +| explained_variance | 0.399 | +| learning_rate | 4.86e-05 | +| loss | -0.0286 | +| n_updates | 27076 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000173 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.402 | +| time/ | | +| fps | 1413 | +| iterations | 2816 | +| time_elapsed | 4081 | +| total_timesteps | 5767168 | +| train/ | | +| approx_kl | 0.012411568 | +| clip_fraction | 0.303 | +| clip_range | 0.0736 | +| entropy_loss | -6.78 | +| explained_variance | 0.672 | +| learning_rate | 4.86e-05 | +| loss | -0.0334 | +| n_updates | 27080 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000133 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.403 | +| time/ | | +| fps | 1413 | +| iterations | 2817 | +| time_elapsed | 4082 | +| total_timesteps | 5769216 | +| train/ | | +| approx_kl | 0.011937803 | +| clip_fraction | 0.369 | +| clip_range | 0.0736 | +| entropy_loss | -6.77 | +| explained_variance | 0.53 | +| learning_rate | 4.86e-05 | +| loss | -0.0345 | +| n_updates | 27084 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000159 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.399 | +| time/ | | +| fps | 1413 | +| iterations | 2818 | +| time_elapsed | 4084 | +| total_timesteps | 5771264 | +| train/ | | +| approx_kl | 0.012069985 | +| clip_fraction | 0.336 | +| clip_range | 0.0736 | +| entropy_loss | -6.96 | +| explained_variance | 0.149 | +| learning_rate | 4.86e-05 | +| loss | -0.0323 | +| n_updates | 27088 | +| policy_gradient_loss | -0.0203 | +| value_loss | 8.65e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.399 | +| time/ | | +| fps | 1413 | +| iterations | 2819 | +| time_elapsed | 4085 | +| total_timesteps | 5773312 | +| train/ | | +| approx_kl | 0.012220876 | +| clip_fraction | 0.352 | +| clip_range | 0.0736 | +| entropy_loss | -7.25 | +| explained_variance | 0.26 | +| learning_rate | 4.86e-05 | +| loss | -0.0389 | +| n_updates | 27092 | +| policy_gradient_loss | -0.0221 | +| value_loss | 8.38e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.398 | +| time/ | | +| fps | 1413 | +| iterations | 2820 | +| time_elapsed | 4086 | +| total_timesteps | 5775360 | +| train/ | | +| approx_kl | 0.014881669 | +| clip_fraction | 0.329 | +| clip_range | 0.0736 | +| entropy_loss | -7.24 | +| explained_variance | 0.0373 | +| learning_rate | 4.86e-05 | +| loss | -0.0306 | +| n_updates | 27096 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000198 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.396 | +| time/ | | +| fps | 1413 | +| iterations | 2821 | +| time_elapsed | 4088 | +| total_timesteps | 5777408 | +| train/ | | +| approx_kl | 0.012637867 | +| clip_fraction | 0.33 | +| clip_range | 0.0736 | +| entropy_loss | -7.23 | +| explained_variance | 0.101 | +| learning_rate | 4.86e-05 | +| loss | -0.0311 | +| n_updates | 27100 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000276 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.396 | +| time/ | | +| fps | 1413 | +| iterations | 2822 | +| time_elapsed | 4089 | +| total_timesteps | 5779456 | +| train/ | | +| approx_kl | 0.010743406 | +| clip_fraction | 0.323 | +| clip_range | 0.0736 | +| entropy_loss | -7.05 | +| explained_variance | 0.133 | +| learning_rate | 4.86e-05 | +| loss | -0.0279 | +| n_updates | 27104 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000329 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.396 | +| time/ | | +| fps | 1413 | +| iterations | 2823 | +| time_elapsed | 4091 | +| total_timesteps | 5781504 | +| train/ | | +| approx_kl | 0.011086173 | +| clip_fraction | 0.317 | +| clip_range | 0.0736 | +| entropy_loss | -7.25 | +| explained_variance | 0.269 | +| learning_rate | 4.86e-05 | +| loss | -0.0328 | +| n_updates | 27108 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000147 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.395 | +| time/ | | +| fps | 1413 | +| iterations | 2824 | +| time_elapsed | 4092 | +| total_timesteps | 5783552 | +| train/ | | +| approx_kl | 0.011187216 | +| clip_fraction | 0.33 | +| clip_range | 0.0736 | +| entropy_loss | -7.16 | +| explained_variance | 0.301 | +| learning_rate | 4.86e-05 | +| loss | -0.0218 | +| n_updates | 27112 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000178 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.397 | +| time/ | | +| fps | 1413 | +| iterations | 2825 | +| time_elapsed | 4094 | +| total_timesteps | 5785600 | +| train/ | | +| approx_kl | 0.009609334 | +| clip_fraction | 0.321 | +| clip_range | 0.0736 | +| entropy_loss | -6.92 | +| explained_variance | 0.211 | +| learning_rate | 4.86e-05 | +| loss | -0.0259 | +| n_updates | 27116 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.00028 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.385 | +| time/ | | +| fps | 1413 | +| iterations | 2826 | +| time_elapsed | 4095 | +| total_timesteps | 5787648 | +| train/ | | +| approx_kl | 0.010748865 | +| clip_fraction | 0.307 | +| clip_range | 0.0736 | +| entropy_loss | -6.84 | +| explained_variance | 0.0606 | +| learning_rate | 4.86e-05 | +| loss | -0.0297 | +| n_updates | 27120 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000277 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.385 | +| time/ | | +| fps | 1413 | +| iterations | 2827 | +| time_elapsed | 4096 | +| total_timesteps | 5789696 | +| train/ | | +| approx_kl | 0.009269867 | +| clip_fraction | 0.333 | +| clip_range | 0.0736 | +| entropy_loss | -7.03 | +| explained_variance | 0.305 | +| learning_rate | 4.86e-05 | +| loss | -0.0374 | +| n_updates | 27124 | +| policy_gradient_loss | -0.0224 | +| value_loss | 9.55e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.388 | +| time/ | | +| fps | 1413 | +| iterations | 2828 | +| time_elapsed | 4098 | +| total_timesteps | 5791744 | +| train/ | | +| approx_kl | 0.009999285 | +| clip_fraction | 0.314 | +| clip_range | 0.0736 | +| entropy_loss | -7.2 | +| explained_variance | -0.303 | +| learning_rate | 4.86e-05 | +| loss | -0.0326 | +| n_updates | 27128 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000134 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.389 | +| time/ | | +| fps | 1413 | +| iterations | 2829 | +| time_elapsed | 4099 | +| total_timesteps | 5793792 | +| train/ | | +| approx_kl | 0.012055445 | +| clip_fraction | 0.317 | +| clip_range | 0.0736 | +| entropy_loss | -7.21 | +| explained_variance | -0.043 | +| learning_rate | 4.86e-05 | +| loss | -0.0321 | +| n_updates | 27132 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000239 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.386 | +| time/ | | +| fps | 1413 | +| iterations | 2830 | +| time_elapsed | 4101 | +| total_timesteps | 5795840 | +| train/ | | +| approx_kl | 0.013787792 | +| clip_fraction | 0.319 | +| clip_range | 0.0736 | +| entropy_loss | -6.98 | +| explained_variance | 0.11 | +| learning_rate | 4.86e-05 | +| loss | -0.0334 | +| n_updates | 27136 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000378 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1413 | +| iterations | 2831 | +| time_elapsed | 4102 | +| total_timesteps | 5797888 | +| train/ | | +| approx_kl | 0.013141513 | +| clip_fraction | 0.353 | +| clip_range | 0.0736 | +| entropy_loss | -7.1 | +| explained_variance | 0.227 | +| learning_rate | 4.86e-05 | +| loss | -0.0402 | +| n_updates | 27140 | +| policy_gradient_loss | -0.024 | +| value_loss | 0.00014 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1413 | +| iterations | 2832 | +| time_elapsed | 4104 | +| total_timesteps | 5799936 | +| train/ | | +| approx_kl | 0.012970064 | +| clip_fraction | 0.343 | +| clip_range | 0.0736 | +| entropy_loss | -7.29 | +| explained_variance | -0.264 | +| learning_rate | 4.86e-05 | +| loss | -0.0343 | +| n_updates | 27144 | +| policy_gradient_loss | -0.0221 | +| value_loss | 0.000183 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.391 | +| time/ | | +| fps | 1413 | +| iterations | 2833 | +| time_elapsed | 4105 | +| total_timesteps | 5801984 | +| train/ | | +| approx_kl | 0.01083289 | +| clip_fraction | 0.294 | +| clip_range | 0.0736 | +| entropy_loss | -7.13 | +| explained_variance | 0.362 | +| learning_rate | 4.86e-05 | +| loss | -0.027 | +| n_updates | 27148 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000276 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.391 | +| time/ | | +| fps | 1413 | +| iterations | 2834 | +| time_elapsed | 4106 | +| total_timesteps | 5804032 | +| train/ | | +| approx_kl | 0.010020759 | +| clip_fraction | 0.305 | +| clip_range | 0.0735 | +| entropy_loss | -6.83 | +| explained_variance | 0.331 | +| learning_rate | 4.86e-05 | +| loss | -0.0302 | +| n_updates | 27152 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000294 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.4 | +| time/ | | +| fps | 1413 | +| iterations | 2835 | +| time_elapsed | 4108 | +| total_timesteps | 5806080 | +| train/ | | +| approx_kl | 0.013004582 | +| clip_fraction | 0.36 | +| clip_range | 0.0735 | +| entropy_loss | -7.35 | +| explained_variance | -0.268 | +| learning_rate | 4.86e-05 | +| loss | -0.0372 | +| n_updates | 27156 | +| policy_gradient_loss | -0.0245 | +| value_loss | 0.000161 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.399 | +| time/ | | +| fps | 1413 | +| iterations | 2836 | +| time_elapsed | 4109 | +| total_timesteps | 5808128 | +| train/ | | +| approx_kl | 0.009417755 | +| clip_fraction | 0.287 | +| clip_range | 0.0735 | +| entropy_loss | -7.08 | +| explained_variance | 0.339 | +| learning_rate | 4.86e-05 | +| loss | -0.0271 | +| n_updates | 27160 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000314 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.398 | +| time/ | | +| fps | 1413 | +| iterations | 2837 | +| time_elapsed | 4111 | +| total_timesteps | 5810176 | +| train/ | | +| approx_kl | 0.011394469 | +| clip_fraction | 0.33 | +| clip_range | 0.0735 | +| entropy_loss | -7.24 | +| explained_variance | 0.375 | +| learning_rate | 4.86e-05 | +| loss | -0.0351 | +| n_updates | 27164 | +| policy_gradient_loss | -0.022 | +| value_loss | 0.000157 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.398 | +| time/ | | +| fps | 1413 | +| iterations | 2838 | +| time_elapsed | 4112 | +| total_timesteps | 5812224 | +| train/ | | +| approx_kl | 0.011425427 | +| clip_fraction | 0.325 | +| clip_range | 0.0735 | +| entropy_loss | -7.01 | +| explained_variance | 0.418 | +| learning_rate | 4.86e-05 | +| loss | -0.0329 | +| n_updates | 27168 | +| policy_gradient_loss | -0.0221 | +| value_loss | 0.000168 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.397 | +| time/ | | +| fps | 1413 | +| iterations | 2839 | +| time_elapsed | 4114 | +| total_timesteps | 5814272 | +| train/ | | +| approx_kl | 0.011522979 | +| clip_fraction | 0.353 | +| clip_range | 0.0735 | +| entropy_loss | -7.27 | +| explained_variance | 0.129 | +| learning_rate | 4.86e-05 | +| loss | -0.0381 | +| n_updates | 27172 | +| policy_gradient_loss | -0.0252 | +| value_loss | 0.000102 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.399 | +| time/ | | +| fps | 1413 | +| iterations | 2840 | +| time_elapsed | 4115 | +| total_timesteps | 5816320 | +| train/ | | +| approx_kl | 0.010351475 | +| clip_fraction | 0.291 | +| clip_range | 0.0735 | +| entropy_loss | -7.33 | +| explained_variance | -0.216 | +| learning_rate | 4.86e-05 | +| loss | -0.032 | +| n_updates | 27176 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000156 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.396 | +| time/ | | +| fps | 1413 | +| iterations | 2841 | +| time_elapsed | 4116 | +| total_timesteps | 5818368 | +| train/ | | +| approx_kl | 0.011448991 | +| clip_fraction | 0.317 | +| clip_range | 0.0735 | +| entropy_loss | -7.21 | +| explained_variance | -0.00317 | +| learning_rate | 4.86e-05 | +| loss | -0.0329 | +| n_updates | 27180 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000148 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.39 | +| time/ | | +| fps | 1413 | +| iterations | 2842 | +| time_elapsed | 4118 | +| total_timesteps | 5820416 | +| train/ | | +| approx_kl | 0.012081996 | +| clip_fraction | 0.318 | +| clip_range | 0.0735 | +| entropy_loss | -6.77 | +| explained_variance | 0.304 | +| learning_rate | 4.86e-05 | +| loss | -0.0287 | +| n_updates | 27184 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000227 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.395 | +| time/ | | +| fps | 1413 | +| iterations | 2843 | +| time_elapsed | 4119 | +| total_timesteps | 5822464 | +| train/ | | +| approx_kl | 0.012108898 | +| clip_fraction | 0.318 | +| clip_range | 0.0735 | +| entropy_loss | -7.15 | +| explained_variance | 0.121 | +| learning_rate | 4.86e-05 | +| loss | -0.036 | +| n_updates | 27188 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000202 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.39 | +| time/ | | +| fps | 1413 | +| iterations | 2844 | +| time_elapsed | 4121 | +| total_timesteps | 5824512 | +| train/ | | +| approx_kl | 0.010354541 | +| clip_fraction | 0.32 | +| clip_range | 0.0735 | +| entropy_loss | -7.4 | +| explained_variance | 0.0744 | +| learning_rate | 4.86e-05 | +| loss | -0.0349 | +| n_updates | 27192 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000246 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.385 | +| time/ | | +| fps | 1413 | +| iterations | 2845 | +| time_elapsed | 4122 | +| total_timesteps | 5826560 | +| train/ | | +| approx_kl | 0.010950776 | +| clip_fraction | 0.317 | +| clip_range | 0.0735 | +| entropy_loss | -6.94 | +| explained_variance | 0.475 | +| learning_rate | 4.86e-05 | +| loss | -0.034 | +| n_updates | 27196 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000123 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.385 | +| time/ | | +| fps | 1413 | +| iterations | 2846 | +| time_elapsed | 4124 | +| total_timesteps | 5828608 | +| train/ | | +| approx_kl | 0.010358619 | +| clip_fraction | 0.309 | +| clip_range | 0.0735 | +| entropy_loss | -7.44 | +| explained_variance | -0.0689 | +| learning_rate | 4.86e-05 | +| loss | -0.0352 | +| n_updates | 27200 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000118 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1413 | +| iterations | 2847 | +| time_elapsed | 4125 | +| total_timesteps | 5830656 | +| train/ | | +| approx_kl | 0.010641388 | +| clip_fraction | 0.292 | +| clip_range | 0.0735 | +| entropy_loss | -7.23 | +| explained_variance | 0.207 | +| learning_rate | 4.86e-05 | +| loss | -0.0304 | +| n_updates | 27204 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000245 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1413 | +| iterations | 2848 | +| time_elapsed | 4126 | +| total_timesteps | 5832704 | +| train/ | | +| approx_kl | 0.012619014 | +| clip_fraction | 0.361 | +| clip_range | 0.0735 | +| entropy_loss | -7.28 | +| explained_variance | 0.391 | +| learning_rate | 4.86e-05 | +| loss | -0.0454 | +| n_updates | 27208 | +| policy_gradient_loss | -0.0235 | +| value_loss | 8.71e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.386 | +| time/ | | +| fps | 1413 | +| iterations | 2849 | +| time_elapsed | 4128 | +| total_timesteps | 5834752 | +| train/ | | +| approx_kl | 0.013650995 | +| clip_fraction | 0.33 | +| clip_range | 0.0735 | +| entropy_loss | -7.37 | +| explained_variance | -0.147 | +| learning_rate | 4.86e-05 | +| loss | -0.0376 | +| n_updates | 27212 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000189 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1413 | +| iterations | 2850 | +| time_elapsed | 4129 | +| total_timesteps | 5836800 | +| train/ | | +| approx_kl | 0.0120638935 | +| clip_fraction | 0.363 | +| clip_range | 0.0735 | +| entropy_loss | -7.03 | +| explained_variance | 0.594 | +| learning_rate | 4.86e-05 | +| loss | -0.0345 | +| n_updates | 27216 | +| policy_gradient_loss | -0.0232 | +| value_loss | 9.36e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.387 | +| time/ | | +| fps | 1413 | +| iterations | 2851 | +| time_elapsed | 4131 | +| total_timesteps | 5838848 | +| train/ | | +| approx_kl | 0.010957314 | +| clip_fraction | 0.333 | +| clip_range | 0.0735 | +| entropy_loss | -7.16 | +| explained_variance | 0.373 | +| learning_rate | 4.86e-05 | +| loss | -0.0369 | +| n_updates | 27220 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000107 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.392 | +| time/ | | +| fps | 1413 | +| iterations | 2852 | +| time_elapsed | 4132 | +| total_timesteps | 5840896 | +| train/ | | +| approx_kl | 0.011215331 | +| clip_fraction | 0.303 | +| clip_range | 0.0735 | +| entropy_loss | -6.56 | +| explained_variance | 0.571 | +| learning_rate | 4.86e-05 | +| loss | -0.0283 | +| n_updates | 27224 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000219 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.392 | +| time/ | | +| fps | 1413 | +| iterations | 2853 | +| time_elapsed | 4133 | +| total_timesteps | 5842944 | +| train/ | | +| approx_kl | 0.011517684 | +| clip_fraction | 0.285 | +| clip_range | 0.0735 | +| entropy_loss | -6.9 | +| explained_variance | 0.24 | +| learning_rate | 4.86e-05 | +| loss | -0.0285 | +| n_updates | 27228 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000272 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.389 | +| time/ | | +| fps | 1413 | +| iterations | 2854 | +| time_elapsed | 4135 | +| total_timesteps | 5844992 | +| train/ | | +| approx_kl | 0.011940985 | +| clip_fraction | 0.333 | +| clip_range | 0.0735 | +| entropy_loss | -7.38 | +| explained_variance | 0.207 | +| learning_rate | 4.86e-05 | +| loss | -0.0334 | +| n_updates | 27232 | +| policy_gradient_loss | -0.0226 | +| value_loss | 0.000151 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.389 | +| time/ | | +| fps | 1413 | +| iterations | 2855 | +| time_elapsed | 4136 | +| total_timesteps | 5847040 | +| train/ | | +| approx_kl | 0.011471313 | +| clip_fraction | 0.327 | +| clip_range | 0.0735 | +| entropy_loss | -7.2 | +| explained_variance | 0.185 | +| learning_rate | 4.86e-05 | +| loss | -0.0336 | +| n_updates | 27236 | +| policy_gradient_loss | -0.0229 | +| value_loss | 0.000148 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1413 | +| iterations | 2856 | +| time_elapsed | 4138 | +| total_timesteps | 5849088 | +| train/ | | +| approx_kl | 0.009727718 | +| clip_fraction | 0.309 | +| clip_range | 0.0735 | +| entropy_loss | -7.3 | +| explained_variance | 0.284 | +| learning_rate | 4.86e-05 | +| loss | -0.03 | +| n_updates | 27240 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000181 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.391 | +| time/ | | +| fps | 1413 | +| iterations | 2857 | +| time_elapsed | 4139 | +| total_timesteps | 5851136 | +| train/ | | +| approx_kl | 0.010058563 | +| clip_fraction | 0.331 | +| clip_range | 0.0735 | +| entropy_loss | -7.2 | +| explained_variance | 0.0447 | +| learning_rate | 4.86e-05 | +| loss | -0.0396 | +| n_updates | 27244 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000119 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.395 | +| time/ | | +| fps | 1413 | +| iterations | 2858 | +| time_elapsed | 4140 | +| total_timesteps | 5853184 | +| train/ | | +| approx_kl | 0.009547228 | +| clip_fraction | 0.296 | +| clip_range | 0.0735 | +| entropy_loss | -6.76 | +| explained_variance | 0.411 | +| learning_rate | 4.86e-05 | +| loss | -0.0325 | +| n_updates | 27248 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000182 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.401 | +| time/ | | +| fps | 1413 | +| iterations | 2859 | +| time_elapsed | 4142 | +| total_timesteps | 5855232 | +| train/ | | +| approx_kl | 0.009386171 | +| clip_fraction | 0.312 | +| clip_range | 0.0735 | +| entropy_loss | -7.16 | +| explained_variance | 0.307 | +| learning_rate | 4.86e-05 | +| loss | -0.0314 | +| n_updates | 27252 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000223 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.399 | +| time/ | | +| fps | 1413 | +| iterations | 2860 | +| time_elapsed | 4143 | +| total_timesteps | 5857280 | +| train/ | | +| approx_kl | 0.009341692 | +| clip_fraction | 0.294 | +| clip_range | 0.0735 | +| entropy_loss | -7.09 | +| explained_variance | 0.121 | +| learning_rate | 4.86e-05 | +| loss | -0.0309 | +| n_updates | 27256 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000313 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.393 | +| time/ | | +| fps | 1413 | +| iterations | 2861 | +| time_elapsed | 4145 | +| total_timesteps | 5859328 | +| train/ | | +| approx_kl | 0.012102467 | +| clip_fraction | 0.341 | +| clip_range | 0.0735 | +| entropy_loss | -7.07 | +| explained_variance | 0.209 | +| learning_rate | 4.86e-05 | +| loss | -0.0292 | +| n_updates | 27260 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000149 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.39 | +| time/ | | +| fps | 1413 | +| iterations | 2862 | +| time_elapsed | 4146 | +| total_timesteps | 5861376 | +| train/ | | +| approx_kl | 0.0125942305 | +| clip_fraction | 0.335 | +| clip_range | 0.0735 | +| entropy_loss | -7.51 | +| explained_variance | -0.0742 | +| learning_rate | 4.86e-05 | +| loss | -0.0408 | +| n_updates | 27264 | +| policy_gradient_loss | -0.0222 | +| value_loss | 0.000162 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.388 | +| time/ | | +| fps | 1413 | +| iterations | 2863 | +| time_elapsed | 4148 | +| total_timesteps | 5863424 | +| train/ | | +| approx_kl | 0.009866366 | +| clip_fraction | 0.299 | +| clip_range | 0.0735 | +| entropy_loss | -7.18 | +| explained_variance | 0.276 | +| learning_rate | 4.86e-05 | +| loss | -0.0271 | +| n_updates | 27268 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000221 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.39 | +| time/ | | +| fps | 1413 | +| iterations | 2864 | +| time_elapsed | 4149 | +| total_timesteps | 5865472 | +| train/ | | +| approx_kl | 0.009694682 | +| clip_fraction | 0.303 | +| clip_range | 0.0735 | +| entropy_loss | -7.03 | +| explained_variance | 0.457 | +| learning_rate | 4.86e-05 | +| loss | -0.029 | +| n_updates | 27272 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000159 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.39 | +| time/ | | +| fps | 1413 | +| iterations | 2865 | +| time_elapsed | 4150 | +| total_timesteps | 5867520 | +| train/ | | +| approx_kl | 0.010832205 | +| clip_fraction | 0.328 | +| clip_range | 0.0735 | +| entropy_loss | -7.13 | +| explained_variance | 0.327 | +| learning_rate | 4.86e-05 | +| loss | -0.0363 | +| n_updates | 27276 | +| policy_gradient_loss | -0.0224 | +| value_loss | 0.000118 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.391 | +| time/ | | +| fps | 1413 | +| iterations | 2866 | +| time_elapsed | 4152 | +| total_timesteps | 5869568 | +| train/ | | +| approx_kl | 0.010059153 | +| clip_fraction | 0.296 | +| clip_range | 0.0735 | +| entropy_loss | -7.08 | +| explained_variance | 0.214 | +| learning_rate | 4.86e-05 | +| loss | -0.0273 | +| n_updates | 27280 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000313 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.387 | +| time/ | | +| fps | 1413 | +| iterations | 2867 | +| time_elapsed | 4153 | +| total_timesteps | 5871616 | +| train/ | | +| approx_kl | 0.009934351 | +| clip_fraction | 0.323 | +| clip_range | 0.0735 | +| entropy_loss | -6.96 | +| explained_variance | 0.399 | +| learning_rate | 4.86e-05 | +| loss | -0.0289 | +| n_updates | 27284 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000197 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.387 | +| time/ | | +| fps | 1413 | +| iterations | 2868 | +| time_elapsed | 4155 | +| total_timesteps | 5873664 | +| train/ | | +| approx_kl | 0.01044394 | +| clip_fraction | 0.34 | +| clip_range | 0.0735 | +| entropy_loss | -6.97 | +| explained_variance | 0.292 | +| learning_rate | 4.86e-05 | +| loss | -0.0327 | +| n_updates | 27288 | +| policy_gradient_loss | -0.0221 | +| value_loss | 0.000108 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.391 | +| time/ | | +| fps | 1413 | +| iterations | 2869 | +| time_elapsed | 4156 | +| total_timesteps | 5875712 | +| train/ | | +| approx_kl | 0.011372612 | +| clip_fraction | 0.341 | +| clip_range | 0.0735 | +| entropy_loss | -7.39 | +| explained_variance | -0.143 | +| learning_rate | 4.86e-05 | +| loss | -0.0392 | +| n_updates | 27292 | +| policy_gradient_loss | -0.0226 | +| value_loss | 0.0001 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.389 | +| time/ | | +| fps | 1413 | +| iterations | 2870 | +| time_elapsed | 4158 | +| total_timesteps | 5877760 | +| train/ | | +| approx_kl | 0.009722475 | +| clip_fraction | 0.308 | +| clip_range | 0.0735 | +| entropy_loss | -7.32 | +| explained_variance | 0.0498 | +| learning_rate | 4.86e-05 | +| loss | -0.0335 | +| n_updates | 27296 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000239 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.385 | +| time/ | | +| fps | 1413 | +| iterations | 2871 | +| time_elapsed | 4159 | +| total_timesteps | 5879808 | +| train/ | | +| approx_kl | 0.009610062 | +| clip_fraction | 0.307 | +| clip_range | 0.0735 | +| entropy_loss | -7.1 | +| explained_variance | 0.697 | +| learning_rate | 4.86e-05 | +| loss | -0.0309 | +| n_updates | 27300 | +| policy_gradient_loss | -0.0213 | +| value_loss | 6.69e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1413 | +| iterations | 2872 | +| time_elapsed | 4161 | +| total_timesteps | 5881856 | +| train/ | | +| approx_kl | 0.010765469 | +| clip_fraction | 0.305 | +| clip_range | 0.0735 | +| entropy_loss | -7.15 | +| explained_variance | 0.0156 | +| learning_rate | 4.86e-05 | +| loss | -0.026 | +| n_updates | 27304 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000373 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1413 | +| iterations | 2873 | +| time_elapsed | 4162 | +| total_timesteps | 5883904 | +| train/ | | +| approx_kl | 0.011582603 | +| clip_fraction | 0.297 | +| clip_range | 0.0735 | +| entropy_loss | -6.73 | +| explained_variance | 0.472 | +| learning_rate | 4.86e-05 | +| loss | -0.0266 | +| n_updates | 27308 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000168 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1413 | +| iterations | 2874 | +| time_elapsed | 4163 | +| total_timesteps | 5885952 | +| train/ | | +| approx_kl | 0.012660993 | +| clip_fraction | 0.315 | +| clip_range | 0.0735 | +| entropy_loss | -7.15 | +| explained_variance | 0.221 | +| learning_rate | 4.86e-05 | +| loss | -0.0322 | +| n_updates | 27312 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000134 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1413 | +| iterations | 2875 | +| time_elapsed | 4165 | +| total_timesteps | 5888000 | +| train/ | | +| approx_kl | 0.012897765 | +| clip_fraction | 0.344 | +| clip_range | 0.0735 | +| entropy_loss | -7.32 | +| explained_variance | 0.269 | +| learning_rate | 4.86e-05 | +| loss | -0.031 | +| n_updates | 27316 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.00016 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1413 | +| iterations | 2876 | +| time_elapsed | 4166 | +| total_timesteps | 5890048 | +| train/ | | +| approx_kl | 0.013188513 | +| clip_fraction | 0.311 | +| clip_range | 0.0735 | +| entropy_loss | -7.43 | +| explained_variance | -0.0754 | +| learning_rate | 4.86e-05 | +| loss | -0.0303 | +| n_updates | 27320 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000209 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1413 | +| iterations | 2877 | +| time_elapsed | 4168 | +| total_timesteps | 5892096 | +| train/ | | +| approx_kl | 0.013416972 | +| clip_fraction | 0.329 | +| clip_range | 0.0735 | +| entropy_loss | -7.36 | +| explained_variance | -0.116 | +| learning_rate | 4.86e-05 | +| loss | -0.0307 | +| n_updates | 27324 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000135 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1413 | +| iterations | 2878 | +| time_elapsed | 4169 | +| total_timesteps | 5894144 | +| train/ | | +| approx_kl | 0.0127377855 | +| clip_fraction | 0.316 | +| clip_range | 0.0735 | +| entropy_loss | -7.15 | +| explained_variance | -0.00618 | +| learning_rate | 4.86e-05 | +| loss | -0.0304 | +| n_updates | 27328 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000127 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1413 | +| iterations | 2879 | +| time_elapsed | 4170 | +| total_timesteps | 5896192 | +| train/ | | +| approx_kl | 0.011575837 | +| clip_fraction | 0.309 | +| clip_range | 0.0735 | +| entropy_loss | -6.97 | +| explained_variance | 0.407 | +| learning_rate | 4.86e-05 | +| loss | -0.0356 | +| n_updates | 27332 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000177 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1413 | +| iterations | 2880 | +| time_elapsed | 4172 | +| total_timesteps | 5898240 | +| train/ | | +| approx_kl | 0.009893648 | +| clip_fraction | 0.297 | +| clip_range | 0.0735 | +| entropy_loss | -6.65 | +| explained_variance | 0.433 | +| learning_rate | 4.86e-05 | +| loss | -0.0249 | +| n_updates | 27336 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.00033 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1413 | +| iterations | 2881 | +| time_elapsed | 4173 | +| total_timesteps | 5900288 | +| train/ | | +| approx_kl | 0.0131615875 | +| clip_fraction | 0.345 | +| clip_range | 0.0735 | +| entropy_loss | -7.28 | +| explained_variance | -0.363 | +| learning_rate | 4.86e-05 | +| loss | -0.0457 | +| n_updates | 27340 | +| policy_gradient_loss | -0.0237 | +| value_loss | 9.32e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1413 | +| iterations | 2882 | +| time_elapsed | 4175 | +| total_timesteps | 5902336 | +| train/ | | +| approx_kl | 0.010990905 | +| clip_fraction | 0.287 | +| clip_range | 0.0735 | +| entropy_loss | -7.16 | +| explained_variance | 0.378 | +| learning_rate | 4.86e-05 | +| loss | -0.0263 | +| n_updates | 27344 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000154 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1413 | +| iterations | 2883 | +| time_elapsed | 4176 | +| total_timesteps | 5904384 | +| train/ | | +| approx_kl | 0.013167616 | +| clip_fraction | 0.319 | +| clip_range | 0.0735 | +| entropy_loss | -7.42 | +| explained_variance | -0.0584 | +| learning_rate | 4.86e-05 | +| loss | -0.0328 | +| n_updates | 27348 | +| policy_gradient_loss | -0.0219 | +| value_loss | 0.000154 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1413 | +| iterations | 2884 | +| time_elapsed | 4178 | +| total_timesteps | 5906432 | +| train/ | | +| approx_kl | 0.011008684 | +| clip_fraction | 0.303 | +| clip_range | 0.0735 | +| entropy_loss | -7.43 | +| explained_variance | -0.0686 | +| learning_rate | 4.86e-05 | +| loss | -0.0314 | +| n_updates | 27352 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000206 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1413 | +| iterations | 2885 | +| time_elapsed | 4179 | +| total_timesteps | 5908480 | +| train/ | | +| approx_kl | 0.012093822 | +| clip_fraction | 0.334 | +| clip_range | 0.0735 | +| entropy_loss | -7.47 | +| explained_variance | -0.0815 | +| learning_rate | 4.86e-05 | +| loss | -0.0337 | +| n_updates | 27356 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1413 | +| iterations | 2886 | +| time_elapsed | 4180 | +| total_timesteps | 5910528 | +| train/ | | +| approx_kl | 0.010551656 | +| clip_fraction | 0.312 | +| clip_range | 0.0735 | +| entropy_loss | -7.05 | +| explained_variance | 0.324 | +| learning_rate | 4.86e-05 | +| loss | -0.0329 | +| n_updates | 27360 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000196 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1413 | +| iterations | 2887 | +| time_elapsed | 4182 | +| total_timesteps | 5912576 | +| train/ | | +| approx_kl | 0.010990627 | +| clip_fraction | 0.315 | +| clip_range | 0.0735 | +| entropy_loss | -7.03 | +| explained_variance | 0.251 | +| learning_rate | 4.86e-05 | +| loss | -0.0342 | +| n_updates | 27364 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.00014 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1413 | +| iterations | 2888 | +| time_elapsed | 4183 | +| total_timesteps | 5914624 | +| train/ | | +| approx_kl | 0.011252515 | +| clip_fraction | 0.297 | +| clip_range | 0.0735 | +| entropy_loss | -6.88 | +| explained_variance | 0.325 | +| learning_rate | 4.86e-05 | +| loss | -0.0272 | +| n_updates | 27368 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000388 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1413 | +| iterations | 2889 | +| time_elapsed | 4185 | +| total_timesteps | 5916672 | +| train/ | | +| approx_kl | 0.011253303 | +| clip_fraction | 0.331 | +| clip_range | 0.0735 | +| entropy_loss | -6.97 | +| explained_variance | 0.431 | +| learning_rate | 4.86e-05 | +| loss | -0.0343 | +| n_updates | 27372 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000129 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1413 | +| iterations | 2890 | +| time_elapsed | 4186 | +| total_timesteps | 5918720 | +| train/ | | +| approx_kl | 0.011758087 | +| clip_fraction | 0.333 | +| clip_range | 0.0735 | +| entropy_loss | -7.3 | +| explained_variance | -0.00736 | +| learning_rate | 4.86e-05 | +| loss | -0.0381 | +| n_updates | 27376 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000191 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1413 | +| iterations | 2891 | +| time_elapsed | 4188 | +| total_timesteps | 5920768 | +| train/ | | +| approx_kl | 0.012752132 | +| clip_fraction | 0.346 | +| clip_range | 0.0735 | +| entropy_loss | -7.22 | +| explained_variance | 0.22 | +| learning_rate | 4.86e-05 | +| loss | -0.0335 | +| n_updates | 27380 | +| policy_gradient_loss | -0.022 | +| value_loss | 0.000165 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1413 | +| iterations | 2892 | +| time_elapsed | 4189 | +| total_timesteps | 5922816 | +| train/ | | +| approx_kl | 0.011802265 | +| clip_fraction | 0.331 | +| clip_range | 0.0735 | +| entropy_loss | -7.4 | +| explained_variance | -0.205 | +| learning_rate | 4.86e-05 | +| loss | -0.0381 | +| n_updates | 27384 | +| policy_gradient_loss | -0.0233 | +| value_loss | 9.91e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1413 | +| iterations | 2893 | +| time_elapsed | 4190 | +| total_timesteps | 5924864 | +| train/ | | +| approx_kl | 0.0106734475 | +| clip_fraction | 0.323 | +| clip_range | 0.0735 | +| entropy_loss | -6.9 | +| explained_variance | 0.353 | +| learning_rate | 4.86e-05 | +| loss | -0.0311 | +| n_updates | 27388 | +| policy_gradient_loss | -0.0197 | +| value_loss | 9.15e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1413 | +| iterations | 2894 | +| time_elapsed | 4192 | +| total_timesteps | 5926912 | +| train/ | | +| approx_kl | 0.012170651 | +| clip_fraction | 0.32 | +| clip_range | 0.0735 | +| entropy_loss | -7.25 | +| explained_variance | -0.033 | +| learning_rate | 4.86e-05 | +| loss | -0.0293 | +| n_updates | 27392 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000126 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1413 | +| iterations | 2895 | +| time_elapsed | 4193 | +| total_timesteps | 5928960 | +| train/ | | +| approx_kl | 0.010587854 | +| clip_fraction | 0.289 | +| clip_range | 0.0735 | +| entropy_loss | -6.82 | +| explained_variance | 0.27 | +| learning_rate | 4.86e-05 | +| loss | -0.0296 | +| n_updates | 27396 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.00035 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1413 | +| iterations | 2896 | +| time_elapsed | 4195 | +| total_timesteps | 5931008 | +| train/ | | +| approx_kl | 0.012225649 | +| clip_fraction | 0.348 | +| clip_range | 0.0735 | +| entropy_loss | -7.02 | +| explained_variance | 0.536 | +| learning_rate | 4.86e-05 | +| loss | -0.0308 | +| n_updates | 27400 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000103 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1413 | +| iterations | 2897 | +| time_elapsed | 4196 | +| total_timesteps | 5933056 | +| train/ | | +| approx_kl | 0.012931749 | +| clip_fraction | 0.32 | +| clip_range | 0.0735 | +| entropy_loss | -7.25 | +| explained_variance | 0.108 | +| learning_rate | 4.86e-05 | +| loss | -0.0311 | +| n_updates | 27404 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000192 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1413 | +| iterations | 2898 | +| time_elapsed | 4198 | +| total_timesteps | 5935104 | +| train/ | | +| approx_kl | 0.013411637 | +| clip_fraction | 0.312 | +| clip_range | 0.0735 | +| entropy_loss | -7.28 | +| explained_variance | -0.123 | +| learning_rate | 4.86e-05 | +| loss | -0.036 | +| n_updates | 27408 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.00016 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1413 | +| iterations | 2899 | +| time_elapsed | 4199 | +| total_timesteps | 5937152 | +| train/ | | +| approx_kl | 0.010560405 | +| clip_fraction | 0.325 | +| clip_range | 0.0735 | +| entropy_loss | -7.24 | +| explained_variance | -0.145 | +| learning_rate | 4.86e-05 | +| loss | -0.0371 | +| n_updates | 27412 | +| policy_gradient_loss | -0.0225 | +| value_loss | 0.00013 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1413 | +| iterations | 2900 | +| time_elapsed | 4201 | +| total_timesteps | 5939200 | +| train/ | | +| approx_kl | 0.010705076 | +| clip_fraction | 0.289 | +| clip_range | 0.0735 | +| entropy_loss | -6.98 | +| explained_variance | 0.16 | +| learning_rate | 4.86e-05 | +| loss | -0.0242 | +| n_updates | 27416 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000377 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1413 | +| iterations | 2901 | +| time_elapsed | 4202 | +| total_timesteps | 5941248 | +| train/ | | +| approx_kl | 0.011451857 | +| clip_fraction | 0.319 | +| clip_range | 0.0735 | +| entropy_loss | -7.43 | +| explained_variance | -0.132 | +| learning_rate | 4.86e-05 | +| loss | -0.0346 | +| n_updates | 27420 | +| policy_gradient_loss | -0.0228 | +| value_loss | 0.000159 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1413 | +| iterations | 2902 | +| time_elapsed | 4204 | +| total_timesteps | 5943296 | +| train/ | | +| approx_kl | 0.011295259 | +| clip_fraction | 0.312 | +| clip_range | 0.0735 | +| entropy_loss | -6.53 | +| explained_variance | 0.447 | +| learning_rate | 4.86e-05 | +| loss | -0.0272 | +| n_updates | 27424 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000247 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1413 | +| iterations | 2903 | +| time_elapsed | 4205 | +| total_timesteps | 5945344 | +| train/ | | +| approx_kl | 0.011751554 | +| clip_fraction | 0.316 | +| clip_range | 0.0735 | +| entropy_loss | -7.09 | +| explained_variance | 0.162 | +| learning_rate | 4.86e-05 | +| loss | -0.0349 | +| n_updates | 27428 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000235 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1413 | +| iterations | 2904 | +| time_elapsed | 4206 | +| total_timesteps | 5947392 | +| train/ | | +| approx_kl | 0.010385497 | +| clip_fraction | 0.324 | +| clip_range | 0.0735 | +| entropy_loss | -7.12 | +| explained_variance | 0.243 | +| learning_rate | 4.86e-05 | +| loss | -0.038 | +| n_updates | 27432 | +| policy_gradient_loss | -0.0228 | +| value_loss | 0.000163 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1413 | +| iterations | 2905 | +| time_elapsed | 4208 | +| total_timesteps | 5949440 | +| train/ | | +| approx_kl | 0.010749772 | +| clip_fraction | 0.342 | +| clip_range | 0.0735 | +| entropy_loss | -7.31 | +| explained_variance | -0.273 | +| learning_rate | 4.86e-05 | +| loss | -0.0297 | +| n_updates | 27436 | +| policy_gradient_loss | -0.0208 | +| value_loss | 9.91e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1413 | +| iterations | 2906 | +| time_elapsed | 4209 | +| total_timesteps | 5951488 | +| train/ | | +| approx_kl | 0.010438515 | +| clip_fraction | 0.338 | +| clip_range | 0.0735 | +| entropy_loss | -7.17 | +| explained_variance | 0.474 | +| learning_rate | 4.86e-05 | +| loss | -0.0397 | +| n_updates | 27440 | +| policy_gradient_loss | -0.0224 | +| value_loss | 7.64e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1413 | +| iterations | 2907 | +| time_elapsed | 4211 | +| total_timesteps | 5953536 | +| train/ | | +| approx_kl | 0.01115466 | +| clip_fraction | 0.302 | +| clip_range | 0.0735 | +| entropy_loss | -7.03 | +| explained_variance | 0.303 | +| learning_rate | 4.86e-05 | +| loss | -0.033 | +| n_updates | 27444 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000187 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1413 | +| iterations | 2908 | +| time_elapsed | 4212 | +| total_timesteps | 5955584 | +| train/ | | +| approx_kl | 0.012630342 | +| clip_fraction | 0.36 | +| clip_range | 0.0735 | +| entropy_loss | -7.22 | +| explained_variance | -0.0113 | +| learning_rate | 4.86e-05 | +| loss | -0.0321 | +| n_updates | 27448 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000196 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1413 | +| iterations | 2909 | +| time_elapsed | 4214 | +| total_timesteps | 5957632 | +| train/ | | +| approx_kl | 0.011520812 | +| clip_fraction | 0.312 | +| clip_range | 0.0735 | +| entropy_loss | -6.98 | +| explained_variance | 0.251 | +| learning_rate | 4.86e-05 | +| loss | -0.0208 | +| n_updates | 27452 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000235 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1413 | +| iterations | 2910 | +| time_elapsed | 4215 | +| total_timesteps | 5959680 | +| train/ | | +| approx_kl | 0.011597267 | +| clip_fraction | 0.313 | +| clip_range | 0.0735 | +| entropy_loss | -7.08 | +| explained_variance | 0.349 | +| learning_rate | 4.86e-05 | +| loss | -0.031 | +| n_updates | 27456 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000242 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1413 | +| iterations | 2911 | +| time_elapsed | 4216 | +| total_timesteps | 5961728 | +| train/ | | +| approx_kl | 0.012339303 | +| clip_fraction | 0.318 | +| clip_range | 0.0735 | +| entropy_loss | -7.01 | +| explained_variance | 0.577 | +| learning_rate | 4.86e-05 | +| loss | -0.0353 | +| n_updates | 27460 | +| policy_gradient_loss | -0.0221 | +| value_loss | 8.63e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1413 | +| iterations | 2912 | +| time_elapsed | 4218 | +| total_timesteps | 5963776 | +| train/ | | +| approx_kl | 0.010985144 | +| clip_fraction | 0.317 | +| clip_range | 0.0735 | +| entropy_loss | -7.1 | +| explained_variance | 0.0399 | +| learning_rate | 4.86e-05 | +| loss | -0.033 | +| n_updates | 27464 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000246 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1413 | +| iterations | 2913 | +| time_elapsed | 4219 | +| total_timesteps | 5965824 | +| train/ | | +| approx_kl | 0.011548679 | +| clip_fraction | 0.329 | +| clip_range | 0.0735 | +| entropy_loss | -7.46 | +| explained_variance | -0.133 | +| learning_rate | 4.86e-05 | +| loss | -0.0302 | +| n_updates | 27468 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000134 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1413 | +| iterations | 2914 | +| time_elapsed | 4221 | +| total_timesteps | 5967872 | +| train/ | | +| approx_kl | 0.012761239 | +| clip_fraction | 0.325 | +| clip_range | 0.0735 | +| entropy_loss | -7.07 | +| explained_variance | 0.244 | +| learning_rate | 4.86e-05 | +| loss | -0.0363 | +| n_updates | 27472 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000165 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1413 | +| iterations | 2915 | +| time_elapsed | 4222 | +| total_timesteps | 5969920 | +| train/ | | +| approx_kl | 0.012215879 | +| clip_fraction | 0.322 | +| clip_range | 0.0735 | +| entropy_loss | -7.24 | +| explained_variance | 0.142 | +| learning_rate | 4.86e-05 | +| loss | -0.0238 | +| n_updates | 27476 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000286 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1413 | +| iterations | 2916 | +| time_elapsed | 4224 | +| total_timesteps | 5971968 | +| train/ | | +| approx_kl | 0.009015281 | +| clip_fraction | 0.299 | +| clip_range | 0.0735 | +| entropy_loss | -6.94 | +| explained_variance | 0.41 | +| learning_rate | 4.86e-05 | +| loss | -0.0183 | +| n_updates | 27480 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000234 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1413 | +| iterations | 2917 | +| time_elapsed | 4225 | +| total_timesteps | 5974016 | +| train/ | | +| approx_kl | 0.011213357 | +| clip_fraction | 0.315 | +| clip_range | 0.0735 | +| entropy_loss | -7.02 | +| explained_variance | 0.296 | +| learning_rate | 4.86e-05 | +| loss | -0.0353 | +| n_updates | 27484 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1413 | +| iterations | 2918 | +| time_elapsed | 4227 | +| total_timesteps | 5976064 | +| train/ | | +| approx_kl | 0.013682717 | +| clip_fraction | 0.315 | +| clip_range | 0.0735 | +| entropy_loss | -7.13 | +| explained_variance | 0.181 | +| learning_rate | 4.86e-05 | +| loss | -0.0305 | +| n_updates | 27488 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000272 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1413 | +| iterations | 2919 | +| time_elapsed | 4228 | +| total_timesteps | 5978112 | +| train/ | | +| approx_kl | 0.013329431 | +| clip_fraction | 0.341 | +| clip_range | 0.0735 | +| entropy_loss | -7.26 | +| explained_variance | 0.263 | +| learning_rate | 4.86e-05 | +| loss | -0.0353 | +| n_updates | 27492 | +| policy_gradient_loss | -0.024 | +| value_loss | 7.48e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1413 | +| iterations | 2920 | +| time_elapsed | 4230 | +| total_timesteps | 5980160 | +| train/ | | +| approx_kl | 0.014324516 | +| clip_fraction | 0.349 | +| clip_range | 0.0735 | +| entropy_loss | -7.31 | +| explained_variance | -0.487 | +| learning_rate | 4.86e-05 | +| loss | -0.0368 | +| n_updates | 27496 | +| policy_gradient_loss | -0.0251 | +| value_loss | 8.12e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1413 | +| iterations | 2921 | +| time_elapsed | 4231 | +| total_timesteps | 5982208 | +| train/ | | +| approx_kl | 0.010619372 | +| clip_fraction | 0.3 | +| clip_range | 0.0735 | +| entropy_loss | -6.9 | +| explained_variance | 0.337 | +| learning_rate | 4.86e-05 | +| loss | -0.0257 | +| n_updates | 27500 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000214 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1413 | +| iterations | 2922 | +| time_elapsed | 4232 | +| total_timesteps | 5984256 | +| train/ | | +| approx_kl | 0.011337576 | +| clip_fraction | 0.339 | +| clip_range | 0.0735 | +| entropy_loss | -7.23 | +| explained_variance | 0.454 | +| learning_rate | 4.86e-05 | +| loss | -0.0352 | +| n_updates | 27504 | +| policy_gradient_loss | -0.0222 | +| value_loss | 7.33e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1413 | +| iterations | 2923 | +| time_elapsed | 4234 | +| total_timesteps | 5986304 | +| train/ | | +| approx_kl | 0.011896191 | +| clip_fraction | 0.325 | +| clip_range | 0.0735 | +| entropy_loss | -7.32 | +| explained_variance | -0.228 | +| learning_rate | 4.86e-05 | +| loss | -0.0373 | +| n_updates | 27508 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000114 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1413 | +| iterations | 2924 | +| time_elapsed | 4235 | +| total_timesteps | 5988352 | +| train/ | | +| approx_kl | 0.011011966 | +| clip_fraction | 0.337 | +| clip_range | 0.0735 | +| entropy_loss | -7.37 | +| explained_variance | -0.0628 | +| learning_rate | 4.86e-05 | +| loss | -0.0345 | +| n_updates | 27512 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000153 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1413 | +| iterations | 2925 | +| time_elapsed | 4237 | +| total_timesteps | 5990400 | +| train/ | | +| approx_kl | 0.011952807 | +| clip_fraction | 0.295 | +| clip_range | 0.0735 | +| entropy_loss | -7.12 | +| explained_variance | 0.32 | +| learning_rate | 4.86e-05 | +| loss | -0.0306 | +| n_updates | 27516 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000185 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1413 | +| iterations | 2926 | +| time_elapsed | 4238 | +| total_timesteps | 5992448 | +| train/ | | +| approx_kl | 0.010269102 | +| clip_fraction | 0.31 | +| clip_range | 0.0735 | +| entropy_loss | -7 | +| explained_variance | 0.658 | +| learning_rate | 4.86e-05 | +| loss | -0.0309 | +| n_updates | 27520 | +| policy_gradient_loss | -0.0214 | +| value_loss | 6.36e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1413 | +| iterations | 2927 | +| time_elapsed | 4240 | +| total_timesteps | 5994496 | +| train/ | | +| approx_kl | 0.008529959 | +| clip_fraction | 0.292 | +| clip_range | 0.0735 | +| entropy_loss | -6.88 | +| explained_variance | 0.432 | +| learning_rate | 4.86e-05 | +| loss | -0.0302 | +| n_updates | 27524 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000207 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1413 | +| iterations | 2928 | +| time_elapsed | 4241 | +| total_timesteps | 5996544 | +| train/ | | +| approx_kl | 0.013553459 | +| clip_fraction | 0.346 | +| clip_range | 0.0735 | +| entropy_loss | -7.2 | +| explained_variance | -0.0276 | +| learning_rate | 4.86e-05 | +| loss | -0.0319 | +| n_updates | 27528 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.00012 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1413 | +| iterations | 2929 | +| time_elapsed | 4242 | +| total_timesteps | 5998592 | +| train/ | | +| approx_kl | 0.011612758 | +| clip_fraction | 0.344 | +| clip_range | 0.0735 | +| entropy_loss | -7 | +| explained_variance | 0.372 | +| learning_rate | 4.86e-05 | +| loss | -0.036 | +| n_updates | 27532 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000132 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1413 | +| iterations | 2930 | +| time_elapsed | 4244 | +| total_timesteps | 6000640 | +| train/ | | +| approx_kl | 0.012012139 | +| clip_fraction | 0.318 | +| clip_range | 0.0735 | +| entropy_loss | -7.16 | +| explained_variance | 0.212 | +| learning_rate | 4.86e-05 | +| loss | -0.0313 | +| n_updates | 27536 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000158 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1413 | +| iterations | 2931 | +| time_elapsed | 4245 | +| total_timesteps | 6002688 | +| train/ | | +| approx_kl | 0.011957862 | +| clip_fraction | 0.302 | +| clip_range | 0.0735 | +| entropy_loss | -7.07 | +| explained_variance | 0.293 | +| learning_rate | 4.86e-05 | +| loss | -0.0338 | +| n_updates | 27540 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000331 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1413 | +| iterations | 2932 | +| time_elapsed | 4247 | +| total_timesteps | 6004736 | +| train/ | | +| approx_kl | 0.010891838 | +| clip_fraction | 0.283 | +| clip_range | 0.0735 | +| entropy_loss | -6.88 | +| explained_variance | 0.0797 | +| learning_rate | 4.86e-05 | +| loss | -0.0254 | +| n_updates | 27544 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000291 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1413 | +| iterations | 2933 | +| time_elapsed | 4248 | +| total_timesteps | 6006784 | +| train/ | | +| approx_kl | 0.012679769 | +| clip_fraction | 0.325 | +| clip_range | 0.0735 | +| entropy_loss | -7.29 | +| explained_variance | -0.168 | +| learning_rate | 4.86e-05 | +| loss | -0.03 | +| n_updates | 27548 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000174 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1413 | +| iterations | 2934 | +| time_elapsed | 4250 | +| total_timesteps | 6008832 | +| train/ | | +| approx_kl | 0.012386628 | +| clip_fraction | 0.346 | +| clip_range | 0.0735 | +| entropy_loss | -7.17 | +| explained_variance | -0.226 | +| learning_rate | 4.86e-05 | +| loss | -0.0341 | +| n_updates | 27552 | +| policy_gradient_loss | -0.0223 | +| value_loss | 9.8e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1413 | +| iterations | 2935 | +| time_elapsed | 4251 | +| total_timesteps | 6010880 | +| train/ | | +| approx_kl | 0.009678485 | +| clip_fraction | 0.298 | +| clip_range | 0.0735 | +| entropy_loss | -7.18 | +| explained_variance | 0.0406 | +| learning_rate | 4.86e-05 | +| loss | -0.0341 | +| n_updates | 27556 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.00039 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1413 | +| iterations | 2936 | +| time_elapsed | 4253 | +| total_timesteps | 6012928 | +| train/ | | +| approx_kl | 0.010488622 | +| clip_fraction | 0.351 | +| clip_range | 0.0735 | +| entropy_loss | -7.29 | +| explained_variance | -0.328 | +| learning_rate | 4.86e-05 | +| loss | -0.0347 | +| n_updates | 27560 | +| policy_gradient_loss | -0.0227 | +| value_loss | 0.000103 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1413 | +| iterations | 2937 | +| time_elapsed | 4254 | +| total_timesteps | 6014976 | +| train/ | | +| approx_kl | 0.010778688 | +| clip_fraction | 0.334 | +| clip_range | 0.0735 | +| entropy_loss | -7.14 | +| explained_variance | 0.193 | +| learning_rate | 4.86e-05 | +| loss | -0.0325 | +| n_updates | 27564 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000135 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1413 | +| iterations | 2938 | +| time_elapsed | 4255 | +| total_timesteps | 6017024 | +| train/ | | +| approx_kl | 0.012015771 | +| clip_fraction | 0.341 | +| clip_range | 0.0735 | +| entropy_loss | -7.31 | +| explained_variance | -0.154 | +| learning_rate | 4.86e-05 | +| loss | -0.0361 | +| n_updates | 27568 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000124 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1413 | +| iterations | 2939 | +| time_elapsed | 4257 | +| total_timesteps | 6019072 | +| train/ | | +| approx_kl | 0.011558533 | +| clip_fraction | 0.315 | +| clip_range | 0.0735 | +| entropy_loss | -7.17 | +| explained_variance | 0.297 | +| learning_rate | 4.86e-05 | +| loss | -0.0367 | +| n_updates | 27572 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000123 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1413 | +| iterations | 2940 | +| time_elapsed | 4258 | +| total_timesteps | 6021120 | +| train/ | | +| approx_kl | 0.01017856 | +| clip_fraction | 0.31 | +| clip_range | 0.0735 | +| entropy_loss | -6.95 | +| explained_variance | 0.345 | +| learning_rate | 4.86e-05 | +| loss | -0.0293 | +| n_updates | 27576 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000253 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1413 | +| iterations | 2941 | +| time_elapsed | 4260 | +| total_timesteps | 6023168 | +| train/ | | +| approx_kl | 0.009134758 | +| clip_fraction | 0.294 | +| clip_range | 0.0735 | +| entropy_loss | -6.91 | +| explained_variance | 0.421 | +| learning_rate | 4.86e-05 | +| loss | -0.0297 | +| n_updates | 27580 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000167 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1413 | +| iterations | 2942 | +| time_elapsed | 4261 | +| total_timesteps | 6025216 | +| train/ | | +| approx_kl | 0.009535498 | +| clip_fraction | 0.295 | +| clip_range | 0.0735 | +| entropy_loss | -6.97 | +| explained_variance | 0.116 | +| learning_rate | 4.86e-05 | +| loss | -0.0323 | +| n_updates | 27584 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000186 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1413 | +| iterations | 2943 | +| time_elapsed | 4263 | +| total_timesteps | 6027264 | +| train/ | | +| approx_kl | 0.01069394 | +| clip_fraction | 0.293 | +| clip_range | 0.0735 | +| entropy_loss | -7.16 | +| explained_variance | 0.132 | +| learning_rate | 4.86e-05 | +| loss | -0.0348 | +| n_updates | 27588 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000193 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1413 | +| iterations | 2944 | +| time_elapsed | 4264 | +| total_timesteps | 6029312 | +| train/ | | +| approx_kl | 0.010195673 | +| clip_fraction | 0.302 | +| clip_range | 0.0735 | +| entropy_loss | -7.22 | +| explained_variance | -0.0226 | +| learning_rate | 4.86e-05 | +| loss | -0.0305 | +| n_updates | 27592 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000188 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1413 | +| iterations | 2945 | +| time_elapsed | 4266 | +| total_timesteps | 6031360 | +| train/ | | +| approx_kl | 0.010421497 | +| clip_fraction | 0.316 | +| clip_range | 0.0735 | +| entropy_loss | -7.31 | +| explained_variance | -0.0432 | +| learning_rate | 4.86e-05 | +| loss | -0.0346 | +| n_updates | 27596 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000129 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1413 | +| iterations | 2946 | +| time_elapsed | 4267 | +| total_timesteps | 6033408 | +| train/ | | +| approx_kl | 0.010155439 | +| clip_fraction | 0.324 | +| clip_range | 0.0735 | +| entropy_loss | -6.95 | +| explained_variance | 0.542 | +| learning_rate | 4.86e-05 | +| loss | -0.0307 | +| n_updates | 27600 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000113 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1413 | +| iterations | 2947 | +| time_elapsed | 4268 | +| total_timesteps | 6035456 | +| train/ | | +| approx_kl | 0.012234347 | +| clip_fraction | 0.319 | +| clip_range | 0.0735 | +| entropy_loss | -7.13 | +| explained_variance | 0.173 | +| learning_rate | 4.86e-05 | +| loss | -0.0318 | +| n_updates | 27604 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000185 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1413 | +| iterations | 2948 | +| time_elapsed | 4270 | +| total_timesteps | 6037504 | +| train/ | | +| approx_kl | 0.01347168 | +| clip_fraction | 0.34 | +| clip_range | 0.0735 | +| entropy_loss | -7.21 | +| explained_variance | 0.322 | +| learning_rate | 4.86e-05 | +| loss | -0.0379 | +| n_updates | 27608 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000106 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1413 | +| iterations | 2949 | +| time_elapsed | 4271 | +| total_timesteps | 6039552 | +| train/ | | +| approx_kl | 0.012068182 | +| clip_fraction | 0.353 | +| clip_range | 0.0735 | +| entropy_loss | -7.07 | +| explained_variance | 0.389 | +| learning_rate | 4.86e-05 | +| loss | -0.0286 | +| n_updates | 27612 | +| policy_gradient_loss | -0.022 | +| value_loss | 8.31e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1413 | +| iterations | 2950 | +| time_elapsed | 4273 | +| total_timesteps | 6041600 | +| train/ | | +| approx_kl | 0.013806458 | +| clip_fraction | 0.308 | +| clip_range | 0.0735 | +| entropy_loss | -7.11 | +| explained_variance | 0.194 | +| learning_rate | 4.86e-05 | +| loss | -0.0323 | +| n_updates | 27616 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000235 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1413 | +| iterations | 2951 | +| time_elapsed | 4274 | +| total_timesteps | 6043648 | +| train/ | | +| approx_kl | 0.012705757 | +| clip_fraction | 0.318 | +| clip_range | 0.0735 | +| entropy_loss | -6.76 | +| explained_variance | 0.13 | +| learning_rate | 4.86e-05 | +| loss | -0.0306 | +| n_updates | 27620 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000358 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1413 | +| iterations | 2952 | +| time_elapsed | 4276 | +| total_timesteps | 6045696 | +| train/ | | +| approx_kl | 0.013588097 | +| clip_fraction | 0.352 | +| clip_range | 0.0735 | +| entropy_loss | -6.97 | +| explained_variance | 0.6 | +| learning_rate | 4.86e-05 | +| loss | -0.0364 | +| n_updates | 27624 | +| policy_gradient_loss | -0.0244 | +| value_loss | 0.000101 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1413 | +| iterations | 2953 | +| time_elapsed | 4277 | +| total_timesteps | 6047744 | +| train/ | | +| approx_kl | 0.011811495 | +| clip_fraction | 0.342 | +| clip_range | 0.0735 | +| entropy_loss | -7.26 | +| explained_variance | 0.3 | +| learning_rate | 4.86e-05 | +| loss | -0.0385 | +| n_updates | 27628 | +| policy_gradient_loss | -0.0221 | +| value_loss | 0.00014 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1413 | +| iterations | 2954 | +| time_elapsed | 4278 | +| total_timesteps | 6049792 | +| train/ | | +| approx_kl | 0.012105338 | +| clip_fraction | 0.332 | +| clip_range | 0.0735 | +| entropy_loss | -7.34 | +| explained_variance | -0.129 | +| learning_rate | 4.86e-05 | +| loss | -0.0381 | +| n_updates | 27632 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000113 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1413 | +| iterations | 2955 | +| time_elapsed | 4280 | +| total_timesteps | 6051840 | +| train/ | | +| approx_kl | 0.010203336 | +| clip_fraction | 0.294 | +| clip_range | 0.0735 | +| entropy_loss | -6.94 | +| explained_variance | 0.507 | +| learning_rate | 4.86e-05 | +| loss | -0.0311 | +| n_updates | 27636 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000143 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1413 | +| iterations | 2956 | +| time_elapsed | 4281 | +| total_timesteps | 6053888 | +| train/ | | +| approx_kl | 0.011134655 | +| clip_fraction | 0.299 | +| clip_range | 0.0735 | +| entropy_loss | -7.08 | +| explained_variance | 0.249 | +| learning_rate | 4.86e-05 | +| loss | -0.0279 | +| n_updates | 27640 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000174 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1413 | +| iterations | 2957 | +| time_elapsed | 4283 | +| total_timesteps | 6055936 | +| train/ | | +| approx_kl | 0.011844735 | +| clip_fraction | 0.328 | +| clip_range | 0.0735 | +| entropy_loss | -7.16 | +| explained_variance | 0.208 | +| learning_rate | 4.86e-05 | +| loss | -0.0293 | +| n_updates | 27644 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.00024 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1413 | +| iterations | 2958 | +| time_elapsed | 4284 | +| total_timesteps | 6057984 | +| train/ | | +| approx_kl | 0.011503832 | +| clip_fraction | 0.289 | +| clip_range | 0.0735 | +| entropy_loss | -7.26 | +| explained_variance | -0.162 | +| learning_rate | 4.86e-05 | +| loss | -0.0327 | +| n_updates | 27648 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000279 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1413 | +| iterations | 2959 | +| time_elapsed | 4286 | +| total_timesteps | 6060032 | +| train/ | | +| approx_kl | 0.008918213 | +| clip_fraction | 0.333 | +| clip_range | 0.0735 | +| entropy_loss | -6.85 | +| explained_variance | 0.074 | +| learning_rate | 4.86e-05 | +| loss | -0.0326 | +| n_updates | 27652 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000292 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1413 | +| iterations | 2960 | +| time_elapsed | 4287 | +| total_timesteps | 6062080 | +| train/ | | +| approx_kl | 0.010259449 | +| clip_fraction | 0.33 | +| clip_range | 0.0735 | +| entropy_loss | -6.86 | +| explained_variance | 0.367 | +| learning_rate | 4.86e-05 | +| loss | -0.0234 | +| n_updates | 27656 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000365 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1413 | +| iterations | 2961 | +| time_elapsed | 4288 | +| total_timesteps | 6064128 | +| train/ | | +| approx_kl | 0.011990797 | +| clip_fraction | 0.338 | +| clip_range | 0.0735 | +| entropy_loss | -7.3 | +| explained_variance | -0.239 | +| learning_rate | 4.86e-05 | +| loss | -0.0314 | +| n_updates | 27660 | +| policy_gradient_loss | -0.0225 | +| value_loss | 0.000181 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1413 | +| iterations | 2962 | +| time_elapsed | 4290 | +| total_timesteps | 6066176 | +| train/ | | +| approx_kl | 0.01019961 | +| clip_fraction | 0.299 | +| clip_range | 0.0735 | +| entropy_loss | -6.79 | +| explained_variance | 0.334 | +| learning_rate | 4.86e-05 | +| loss | -0.0253 | +| n_updates | 27664 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000263 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1413 | +| iterations | 2963 | +| time_elapsed | 4291 | +| total_timesteps | 6068224 | +| train/ | | +| approx_kl | 0.009727754 | +| clip_fraction | 0.289 | +| clip_range | 0.0735 | +| entropy_loss | -6.94 | +| explained_variance | 0.263 | +| learning_rate | 4.86e-05 | +| loss | -0.0304 | +| n_updates | 27668 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000285 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1413 | +| iterations | 2964 | +| time_elapsed | 4293 | +| total_timesteps | 6070272 | +| train/ | | +| approx_kl | 0.009987939 | +| clip_fraction | 0.311 | +| clip_range | 0.0735 | +| entropy_loss | -7.1 | +| explained_variance | 0.349 | +| learning_rate | 4.86e-05 | +| loss | -0.0326 | +| n_updates | 27672 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000252 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1413 | +| iterations | 2965 | +| time_elapsed | 4294 | +| total_timesteps | 6072320 | +| train/ | | +| approx_kl | 0.010779129 | +| clip_fraction | 0.328 | +| clip_range | 0.0735 | +| entropy_loss | -7.27 | +| explained_variance | 0.197 | +| learning_rate | 4.86e-05 | +| loss | -0.0354 | +| n_updates | 27676 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000281 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1413 | +| iterations | 2966 | +| time_elapsed | 4295 | +| total_timesteps | 6074368 | +| train/ | | +| approx_kl | 0.013441282 | +| clip_fraction | 0.334 | +| clip_range | 0.0735 | +| entropy_loss | -7.37 | +| explained_variance | -0.228 | +| learning_rate | 4.86e-05 | +| loss | -0.0326 | +| n_updates | 27680 | +| policy_gradient_loss | -0.0221 | +| value_loss | 0.000166 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1413 | +| iterations | 2967 | +| time_elapsed | 4297 | +| total_timesteps | 6076416 | +| train/ | | +| approx_kl | 0.0112409685 | +| clip_fraction | 0.348 | +| clip_range | 0.0735 | +| entropy_loss | -7.3 | +| explained_variance | 0.425 | +| learning_rate | 4.86e-05 | +| loss | -0.0396 | +| n_updates | 27684 | +| policy_gradient_loss | -0.0249 | +| value_loss | 7.89e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1413 | +| iterations | 2968 | +| time_elapsed | 4298 | +| total_timesteps | 6078464 | +| train/ | | +| approx_kl | 0.011607963 | +| clip_fraction | 0.342 | +| clip_range | 0.0735 | +| entropy_loss | -7.37 | +| explained_variance | -0.189 | +| learning_rate | 4.86e-05 | +| loss | -0.0379 | +| n_updates | 27688 | +| policy_gradient_loss | -0.0233 | +| value_loss | 0.000108 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1413 | +| iterations | 2969 | +| time_elapsed | 4300 | +| total_timesteps | 6080512 | +| train/ | | +| approx_kl | 0.012003295 | +| clip_fraction | 0.299 | +| clip_range | 0.0735 | +| entropy_loss | -6.89 | +| explained_variance | 0.381 | +| learning_rate | 4.86e-05 | +| loss | -0.0302 | +| n_updates | 27692 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000211 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1413 | +| iterations | 2970 | +| time_elapsed | 4301 | +| total_timesteps | 6082560 | +| train/ | | +| approx_kl | 0.0115070855 | +| clip_fraction | 0.3 | +| clip_range | 0.0735 | +| entropy_loss | -7.1 | +| explained_variance | 0.34 | +| learning_rate | 4.86e-05 | +| loss | -0.0325 | +| n_updates | 27696 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000278 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1413 | +| iterations | 2971 | +| time_elapsed | 4303 | +| total_timesteps | 6084608 | +| train/ | | +| approx_kl | 0.010781549 | +| clip_fraction | 0.294 | +| clip_range | 0.0735 | +| entropy_loss | -7.14 | +| explained_variance | 0.221 | +| learning_rate | 4.86e-05 | +| loss | -0.0268 | +| n_updates | 27700 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000285 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1413 | +| iterations | 2972 | +| time_elapsed | 4304 | +| total_timesteps | 6086656 | +| train/ | | +| approx_kl | 0.012873431 | +| clip_fraction | 0.348 | +| clip_range | 0.0735 | +| entropy_loss | -7.05 | +| explained_variance | 0.285 | +| learning_rate | 4.86e-05 | +| loss | -0.0376 | +| n_updates | 27704 | +| policy_gradient_loss | -0.0225 | +| value_loss | 0.000105 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1413 | +| iterations | 2973 | +| time_elapsed | 4306 | +| total_timesteps | 6088704 | +| train/ | | +| approx_kl | 0.009779606 | +| clip_fraction | 0.292 | +| clip_range | 0.0735 | +| entropy_loss | -7.05 | +| explained_variance | 0.363 | +| learning_rate | 4.86e-05 | +| loss | -0.0331 | +| n_updates | 27708 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000131 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1414 | +| iterations | 2974 | +| time_elapsed | 4307 | +| total_timesteps | 6090752 | +| train/ | | +| approx_kl | 0.011834263 | +| clip_fraction | 0.316 | +| clip_range | 0.0735 | +| entropy_loss | -7.43 | +| explained_variance | -0.0166 | +| learning_rate | 4.86e-05 | +| loss | -0.0299 | +| n_updates | 27712 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000126 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1414 | +| iterations | 2975 | +| time_elapsed | 4308 | +| total_timesteps | 6092800 | +| train/ | | +| approx_kl | 0.010637482 | +| clip_fraction | 0.316 | +| clip_range | 0.0735 | +| entropy_loss | -7.26 | +| explained_variance | 0.133 | +| learning_rate | 4.86e-05 | +| loss | -0.0343 | +| n_updates | 27716 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000155 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1414 | +| iterations | 2976 | +| time_elapsed | 4310 | +| total_timesteps | 6094848 | +| train/ | | +| approx_kl | 0.009490771 | +| clip_fraction | 0.288 | +| clip_range | 0.0735 | +| entropy_loss | -6.89 | +| explained_variance | 0.296 | +| learning_rate | 4.86e-05 | +| loss | -0.0281 | +| n_updates | 27720 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.00032 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1414 | +| iterations | 2977 | +| time_elapsed | 4311 | +| total_timesteps | 6096896 | +| train/ | | +| approx_kl | 0.012515241 | +| clip_fraction | 0.334 | +| clip_range | 0.0735 | +| entropy_loss | -7.09 | +| explained_variance | 0.284 | +| learning_rate | 4.86e-05 | +| loss | -0.0395 | +| n_updates | 27724 | +| policy_gradient_loss | -0.0226 | +| value_loss | 0.00013 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1414 | +| iterations | 2978 | +| time_elapsed | 4313 | +| total_timesteps | 6098944 | +| train/ | | +| approx_kl | 0.01092224 | +| clip_fraction | 0.322 | +| clip_range | 0.0735 | +| entropy_loss | -7.45 | +| explained_variance | -0.0628 | +| learning_rate | 4.86e-05 | +| loss | -0.0352 | +| n_updates | 27728 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000207 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1414 | +| iterations | 2979 | +| time_elapsed | 4314 | +| total_timesteps | 6100992 | +| train/ | | +| approx_kl | 0.009278338 | +| clip_fraction | 0.278 | +| clip_range | 0.0735 | +| entropy_loss | -7.28 | +| explained_variance | 0.171 | +| learning_rate | 4.86e-05 | +| loss | -0.0295 | +| n_updates | 27732 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000337 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1414 | +| iterations | 2980 | +| time_elapsed | 4315 | +| total_timesteps | 6103040 | +| train/ | | +| approx_kl | 0.011813609 | +| clip_fraction | 0.326 | +| clip_range | 0.0735 | +| entropy_loss | -7.18 | +| explained_variance | 0.00781 | +| learning_rate | 4.86e-05 | +| loss | -0.0364 | +| n_updates | 27736 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000172 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1414 | +| iterations | 2981 | +| time_elapsed | 4317 | +| total_timesteps | 6105088 | +| train/ | | +| approx_kl | 0.013309732 | +| clip_fraction | 0.34 | +| clip_range | 0.0735 | +| entropy_loss | -7.41 | +| explained_variance | -0.136 | +| learning_rate | 4.86e-05 | +| loss | -0.0327 | +| n_updates | 27740 | +| policy_gradient_loss | -0.0236 | +| value_loss | 0.000126 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1414 | +| iterations | 2982 | +| time_elapsed | 4318 | +| total_timesteps | 6107136 | +| train/ | | +| approx_kl | 0.010462943 | +| clip_fraction | 0.297 | +| clip_range | 0.0735 | +| entropy_loss | -7.31 | +| explained_variance | -0.0427 | +| learning_rate | 4.86e-05 | +| loss | -0.0283 | +| n_updates | 27744 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000241 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1414 | +| iterations | 2983 | +| time_elapsed | 4320 | +| total_timesteps | 6109184 | +| train/ | | +| approx_kl | 0.013226453 | +| clip_fraction | 0.319 | +| clip_range | 0.0735 | +| entropy_loss | -6.56 | +| explained_variance | 0.378 | +| learning_rate | 4.85e-05 | +| loss | -0.0339 | +| n_updates | 27748 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000233 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1414 | +| iterations | 2984 | +| time_elapsed | 4321 | +| total_timesteps | 6111232 | +| train/ | | +| approx_kl | 0.013152409 | +| clip_fraction | 0.332 | +| clip_range | 0.0735 | +| entropy_loss | -7.25 | +| explained_variance | 0.372 | +| learning_rate | 4.85e-05 | +| loss | -0.0323 | +| n_updates | 27752 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000101 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1414 | +| iterations | 2985 | +| time_elapsed | 4322 | +| total_timesteps | 6113280 | +| train/ | | +| approx_kl | 0.0118240975 | +| clip_fraction | 0.335 | +| clip_range | 0.0735 | +| entropy_loss | -7.27 | +| explained_variance | 0.279 | +| learning_rate | 4.85e-05 | +| loss | -0.0291 | +| n_updates | 27756 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000145 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1414 | +| iterations | 2986 | +| time_elapsed | 4324 | +| total_timesteps | 6115328 | +| train/ | | +| approx_kl | 0.012306746 | +| clip_fraction | 0.336 | +| clip_range | 0.0735 | +| entropy_loss | -7.11 | +| explained_variance | 0.257 | +| learning_rate | 4.85e-05 | +| loss | -0.0359 | +| n_updates | 27760 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000107 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1414 | +| iterations | 2987 | +| time_elapsed | 4325 | +| total_timesteps | 6117376 | +| train/ | | +| approx_kl | 0.011902822 | +| clip_fraction | 0.315 | +| clip_range | 0.0735 | +| entropy_loss | -7.34 | +| explained_variance | 0.167 | +| learning_rate | 4.85e-05 | +| loss | -0.033 | +| n_updates | 27764 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000129 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1414 | +| iterations | 2988 | +| time_elapsed | 4327 | +| total_timesteps | 6119424 | +| train/ | | +| approx_kl | 0.014158817 | +| clip_fraction | 0.314 | +| clip_range | 0.0735 | +| entropy_loss | -6.98 | +| explained_variance | 0.321 | +| learning_rate | 4.85e-05 | +| loss | -0.0269 | +| n_updates | 27768 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000212 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1414 | +| iterations | 2989 | +| time_elapsed | 4328 | +| total_timesteps | 6121472 | +| train/ | | +| approx_kl | 0.013783243 | +| clip_fraction | 0.321 | +| clip_range | 0.0735 | +| entropy_loss | -7.05 | +| explained_variance | 0.0987 | +| learning_rate | 4.85e-05 | +| loss | -0.0285 | +| n_updates | 27772 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.00026 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1414 | +| iterations | 2990 | +| time_elapsed | 4330 | +| total_timesteps | 6123520 | +| train/ | | +| approx_kl | 0.01190844 | +| clip_fraction | 0.319 | +| clip_range | 0.0735 | +| entropy_loss | -7.15 | +| explained_variance | 0.233 | +| learning_rate | 4.85e-05 | +| loss | -0.0365 | +| n_updates | 27776 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000246 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1414 | +| iterations | 2991 | +| time_elapsed | 4331 | +| total_timesteps | 6125568 | +| train/ | | +| approx_kl | 0.012720136 | +| clip_fraction | 0.328 | +| clip_range | 0.0735 | +| entropy_loss | -7.24 | +| explained_variance | 0.141 | +| learning_rate | 4.85e-05 | +| loss | -0.0315 | +| n_updates | 27780 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.00021 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1414 | +| iterations | 2992 | +| time_elapsed | 4333 | +| total_timesteps | 6127616 | +| train/ | | +| approx_kl | 0.013002709 | +| clip_fraction | 0.328 | +| clip_range | 0.0735 | +| entropy_loss | -6.99 | +| explained_variance | 0.394 | +| learning_rate | 4.85e-05 | +| loss | -0.0334 | +| n_updates | 27784 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000183 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1414 | +| iterations | 2993 | +| time_elapsed | 4334 | +| total_timesteps | 6129664 | +| train/ | | +| approx_kl | 0.01250371 | +| clip_fraction | 0.362 | +| clip_range | 0.0735 | +| entropy_loss | -7.23 | +| explained_variance | -0.365 | +| learning_rate | 4.85e-05 | +| loss | -0.0416 | +| n_updates | 27788 | +| policy_gradient_loss | -0.0245 | +| value_loss | 0.000108 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1414 | +| iterations | 2994 | +| time_elapsed | 4335 | +| total_timesteps | 6131712 | +| train/ | | +| approx_kl | 0.011783622 | +| clip_fraction | 0.298 | +| clip_range | 0.0735 | +| entropy_loss | -7.09 | +| explained_variance | 0.239 | +| learning_rate | 4.85e-05 | +| loss | -0.0316 | +| n_updates | 27792 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000252 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1414 | +| iterations | 2995 | +| time_elapsed | 4337 | +| total_timesteps | 6133760 | +| train/ | | +| approx_kl | 0.01334296 | +| clip_fraction | 0.302 | +| clip_range | 0.0735 | +| entropy_loss | -7.12 | +| explained_variance | 0.0231 | +| learning_rate | 4.85e-05 | +| loss | -0.0351 | +| n_updates | 27796 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000198 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1414 | +| iterations | 2996 | +| time_elapsed | 4338 | +| total_timesteps | 6135808 | +| train/ | | +| approx_kl | 0.012157568 | +| clip_fraction | 0.311 | +| clip_range | 0.0735 | +| entropy_loss | -7.05 | +| explained_variance | 0.136 | +| learning_rate | 4.85e-05 | +| loss | -0.034 | +| n_updates | 27800 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000279 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1414 | +| iterations | 2997 | +| time_elapsed | 4340 | +| total_timesteps | 6137856 | +| train/ | | +| approx_kl | 0.011862538 | +| clip_fraction | 0.319 | +| clip_range | 0.0735 | +| entropy_loss | -6.93 | +| explained_variance | 0.417 | +| learning_rate | 4.85e-05 | +| loss | -0.0364 | +| n_updates | 27804 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000166 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1414 | +| iterations | 2998 | +| time_elapsed | 4341 | +| total_timesteps | 6139904 | +| train/ | | +| approx_kl | 0.012291379 | +| clip_fraction | 0.336 | +| clip_range | 0.0735 | +| entropy_loss | -7.12 | +| explained_variance | 0.0552 | +| learning_rate | 4.85e-05 | +| loss | -0.0313 | +| n_updates | 27808 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000211 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1414 | +| iterations | 2999 | +| time_elapsed | 4343 | +| total_timesteps | 6141952 | +| train/ | | +| approx_kl | 0.011102693 | +| clip_fraction | 0.344 | +| clip_range | 0.0735 | +| entropy_loss | -7.35 | +| explained_variance | 0.332 | +| learning_rate | 4.85e-05 | +| loss | -0.0296 | +| n_updates | 27812 | +| policy_gradient_loss | -0.0223 | +| value_loss | 9.19e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1414 | +| iterations | 3000 | +| time_elapsed | 4344 | +| total_timesteps | 6144000 | +| train/ | | +| approx_kl | 0.011692932 | +| clip_fraction | 0.322 | +| clip_range | 0.0735 | +| entropy_loss | -7.27 | +| explained_variance | -0.0414 | +| learning_rate | 4.85e-05 | +| loss | -0.0432 | +| n_updates | 27816 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.0001 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1414 | +| iterations | 3001 | +| time_elapsed | 4345 | +| total_timesteps | 6146048 | +| train/ | | +| approx_kl | 0.010099057 | +| clip_fraction | 0.312 | +| clip_range | 0.0735 | +| entropy_loss | -7.25 | +| explained_variance | 0.0396 | +| learning_rate | 4.85e-05 | +| loss | -0.0298 | +| n_updates | 27820 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000132 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1414 | +| iterations | 3002 | +| time_elapsed | 4347 | +| total_timesteps | 6148096 | +| train/ | | +| approx_kl | 0.010498701 | +| clip_fraction | 0.324 | +| clip_range | 0.0735 | +| entropy_loss | -7.32 | +| explained_variance | 0.23 | +| learning_rate | 4.85e-05 | +| loss | -0.0329 | +| n_updates | 27824 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000152 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1414 | +| iterations | 3003 | +| time_elapsed | 4348 | +| total_timesteps | 6150144 | +| train/ | | +| approx_kl | 0.011026289 | +| clip_fraction | 0.319 | +| clip_range | 0.0735 | +| entropy_loss | -6.94 | +| explained_variance | 0.604 | +| learning_rate | 4.85e-05 | +| loss | -0.0322 | +| n_updates | 27828 | +| policy_gradient_loss | -0.0195 | +| value_loss | 9.58e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1414 | +| iterations | 3004 | +| time_elapsed | 4350 | +| total_timesteps | 6152192 | +| train/ | | +| approx_kl | 0.011172039 | +| clip_fraction | 0.291 | +| clip_range | 0.0735 | +| entropy_loss | -6.85 | +| explained_variance | 0.278 | +| learning_rate | 4.85e-05 | +| loss | -0.0279 | +| n_updates | 27832 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000357 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1414 | +| iterations | 3005 | +| time_elapsed | 4351 | +| total_timesteps | 6154240 | +| train/ | | +| approx_kl | 0.012226615 | +| clip_fraction | 0.353 | +| clip_range | 0.0735 | +| entropy_loss | -7.35 | +| explained_variance | 0.23 | +| learning_rate | 4.85e-05 | +| loss | -0.0316 | +| n_updates | 27836 | +| policy_gradient_loss | -0.0223 | +| value_loss | 0.000155 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1414 | +| iterations | 3006 | +| time_elapsed | 4353 | +| total_timesteps | 6156288 | +| train/ | | +| approx_kl | 0.0110061765 | +| clip_fraction | 0.317 | +| clip_range | 0.0735 | +| entropy_loss | -7.01 | +| explained_variance | 0.422 | +| learning_rate | 4.85e-05 | +| loss | -0.0292 | +| n_updates | 27840 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000186 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1414 | +| iterations | 3007 | +| time_elapsed | 4354 | +| total_timesteps | 6158336 | +| train/ | | +| approx_kl | 0.013728543 | +| clip_fraction | 0.365 | +| clip_range | 0.0735 | +| entropy_loss | -7.18 | +| explained_variance | 0.485 | +| learning_rate | 4.85e-05 | +| loss | -0.0368 | +| n_updates | 27844 | +| policy_gradient_loss | -0.0254 | +| value_loss | 7.5e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1414 | +| iterations | 3008 | +| time_elapsed | 4355 | +| total_timesteps | 6160384 | +| train/ | | +| approx_kl | 0.012677126 | +| clip_fraction | 0.307 | +| clip_range | 0.0735 | +| entropy_loss | -6.66 | +| explained_variance | 0.765 | +| learning_rate | 4.85e-05 | +| loss | -0.0361 | +| n_updates | 27848 | +| policy_gradient_loss | -0.0193 | +| value_loss | 9.13e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1414 | +| iterations | 3009 | +| time_elapsed | 4357 | +| total_timesteps | 6162432 | +| train/ | | +| approx_kl | 0.011569985 | +| clip_fraction | 0.326 | +| clip_range | 0.0735 | +| entropy_loss | -7.28 | +| explained_variance | -0.0878 | +| learning_rate | 4.85e-05 | +| loss | -0.0313 | +| n_updates | 27852 | +| policy_gradient_loss | -0.022 | +| value_loss | 9.88e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1414 | +| iterations | 3010 | +| time_elapsed | 4358 | +| total_timesteps | 6164480 | +| train/ | | +| approx_kl | 0.011742914 | +| clip_fraction | 0.332 | +| clip_range | 0.0735 | +| entropy_loss | -7.41 | +| explained_variance | -0.0978 | +| learning_rate | 4.85e-05 | +| loss | -0.0336 | +| n_updates | 27856 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000144 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1414 | +| iterations | 3011 | +| time_elapsed | 4360 | +| total_timesteps | 6166528 | +| train/ | | +| approx_kl | 0.0128341075 | +| clip_fraction | 0.284 | +| clip_range | 0.0735 | +| entropy_loss | -7.24 | +| explained_variance | 0.315 | +| learning_rate | 4.85e-05 | +| loss | -0.0343 | +| n_updates | 27860 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000157 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1414 | +| iterations | 3012 | +| time_elapsed | 4361 | +| total_timesteps | 6168576 | +| train/ | | +| approx_kl | 0.008849492 | +| clip_fraction | 0.287 | +| clip_range | 0.0735 | +| entropy_loss | -7.2 | +| explained_variance | 0.284 | +| learning_rate | 4.85e-05 | +| loss | -0.0321 | +| n_updates | 27864 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000179 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1414 | +| iterations | 3013 | +| time_elapsed | 4363 | +| total_timesteps | 6170624 | +| train/ | | +| approx_kl | 0.009699047 | +| clip_fraction | 0.321 | +| clip_range | 0.0735 | +| entropy_loss | -7.31 | +| explained_variance | 0.0797 | +| learning_rate | 4.85e-05 | +| loss | -0.0263 | +| n_updates | 27868 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000152 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1414 | +| iterations | 3014 | +| time_elapsed | 4364 | +| total_timesteps | 6172672 | +| train/ | | +| approx_kl | 0.01146571 | +| clip_fraction | 0.311 | +| clip_range | 0.0735 | +| entropy_loss | -7.1 | +| explained_variance | 0.149 | +| learning_rate | 4.85e-05 | +| loss | -0.0348 | +| n_updates | 27872 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.00033 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1414 | +| iterations | 3015 | +| time_elapsed | 4365 | +| total_timesteps | 6174720 | +| train/ | | +| approx_kl | 0.01417662 | +| clip_fraction | 0.323 | +| clip_range | 0.0735 | +| entropy_loss | -6.74 | +| explained_variance | 0.479 | +| learning_rate | 4.85e-05 | +| loss | -0.0314 | +| n_updates | 27876 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000137 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1414 | +| iterations | 3016 | +| time_elapsed | 4367 | +| total_timesteps | 6176768 | +| train/ | | +| approx_kl | 0.011747735 | +| clip_fraction | 0.32 | +| clip_range | 0.0735 | +| entropy_loss | -7.16 | +| explained_variance | 0.27 | +| learning_rate | 4.85e-05 | +| loss | -0.0317 | +| n_updates | 27880 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000144 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1414 | +| iterations | 3017 | +| time_elapsed | 4368 | +| total_timesteps | 6178816 | +| train/ | | +| approx_kl | 0.011132203 | +| clip_fraction | 0.319 | +| clip_range | 0.0735 | +| entropy_loss | -7.21 | +| explained_variance | 0.341 | +| learning_rate | 4.85e-05 | +| loss | -0.0368 | +| n_updates | 27884 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.00015 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1414 | +| iterations | 3018 | +| time_elapsed | 4370 | +| total_timesteps | 6180864 | +| train/ | | +| approx_kl | 0.010553457 | +| clip_fraction | 0.31 | +| clip_range | 0.0735 | +| entropy_loss | -6.98 | +| explained_variance | 0.561 | +| learning_rate | 4.85e-05 | +| loss | -0.0391 | +| n_updates | 27888 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000145 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1414 | +| iterations | 3019 | +| time_elapsed | 4371 | +| total_timesteps | 6182912 | +| train/ | | +| approx_kl | 0.01052659 | +| clip_fraction | 0.318 | +| clip_range | 0.0735 | +| entropy_loss | -7.15 | +| explained_variance | 0.446 | +| learning_rate | 4.85e-05 | +| loss | -0.0359 | +| n_updates | 27892 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000132 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1414 | +| iterations | 3020 | +| time_elapsed | 4373 | +| total_timesteps | 6184960 | +| train/ | | +| approx_kl | 0.01129621 | +| clip_fraction | 0.29 | +| clip_range | 0.0735 | +| entropy_loss | -6.77 | +| explained_variance | 0.236 | +| learning_rate | 4.85e-05 | +| loss | -0.0271 | +| n_updates | 27896 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000323 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1414 | +| iterations | 3021 | +| time_elapsed | 4374 | +| total_timesteps | 6187008 | +| train/ | | +| approx_kl | 0.009126824 | +| clip_fraction | 0.295 | +| clip_range | 0.0735 | +| entropy_loss | -7.01 | +| explained_variance | 0.372 | +| learning_rate | 4.85e-05 | +| loss | -0.0341 | +| n_updates | 27900 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000243 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1414 | +| iterations | 3022 | +| time_elapsed | 4376 | +| total_timesteps | 6189056 | +| train/ | | +| approx_kl | 0.011192694 | +| clip_fraction | 0.333 | +| clip_range | 0.0735 | +| entropy_loss | -7.19 | +| explained_variance | 0.385 | +| learning_rate | 4.85e-05 | +| loss | -0.0366 | +| n_updates | 27904 | +| policy_gradient_loss | -0.022 | +| value_loss | 9.63e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1414 | +| iterations | 3023 | +| time_elapsed | 4377 | +| total_timesteps | 6191104 | +| train/ | | +| approx_kl | 0.01040904 | +| clip_fraction | 0.305 | +| clip_range | 0.0735 | +| entropy_loss | -6.9 | +| explained_variance | 0.0839 | +| learning_rate | 4.85e-05 | +| loss | -0.0276 | +| n_updates | 27908 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000168 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1414 | +| iterations | 3024 | +| time_elapsed | 4378 | +| total_timesteps | 6193152 | +| train/ | | +| approx_kl | 0.011320412 | +| clip_fraction | 0.332 | +| clip_range | 0.0735 | +| entropy_loss | -7.34 | +| explained_variance | -0.124 | +| learning_rate | 4.85e-05 | +| loss | -0.0294 | +| n_updates | 27912 | +| policy_gradient_loss | -0.0218 | +| value_loss | 9.15e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1414 | +| iterations | 3025 | +| time_elapsed | 4380 | +| total_timesteps | 6195200 | +| train/ | | +| approx_kl | 0.009219033 | +| clip_fraction | 0.314 | +| clip_range | 0.0735 | +| entropy_loss | -7.27 | +| explained_variance | -0.0594 | +| learning_rate | 4.85e-05 | +| loss | -0.0347 | +| n_updates | 27916 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000194 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1414 | +| iterations | 3026 | +| time_elapsed | 4381 | +| total_timesteps | 6197248 | +| train/ | | +| approx_kl | 0.009356088 | +| clip_fraction | 0.305 | +| clip_range | 0.0735 | +| entropy_loss | -7.11 | +| explained_variance | 0.522 | +| learning_rate | 4.85e-05 | +| loss | -0.0357 | +| n_updates | 27920 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.00011 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1414 | +| iterations | 3027 | +| time_elapsed | 4383 | +| total_timesteps | 6199296 | +| train/ | | +| approx_kl | 0.008421652 | +| clip_fraction | 0.293 | +| clip_range | 0.0735 | +| entropy_loss | -6.82 | +| explained_variance | 0.453 | +| learning_rate | 4.85e-05 | +| loss | -0.0267 | +| n_updates | 27924 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000297 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1414 | +| iterations | 3028 | +| time_elapsed | 4384 | +| total_timesteps | 6201344 | +| train/ | | +| approx_kl | 0.00876313 | +| clip_fraction | 0.294 | +| clip_range | 0.0735 | +| entropy_loss | -7.41 | +| explained_variance | -0.143 | +| learning_rate | 4.85e-05 | +| loss | -0.0352 | +| n_updates | 27928 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000251 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1414 | +| iterations | 3029 | +| time_elapsed | 4386 | +| total_timesteps | 6203392 | +| train/ | | +| approx_kl | 0.0111359395 | +| clip_fraction | 0.33 | +| clip_range | 0.0734 | +| entropy_loss | -7.41 | +| explained_variance | -0.0387 | +| learning_rate | 4.85e-05 | +| loss | -0.0293 | +| n_updates | 27932 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000179 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1414 | +| iterations | 3030 | +| time_elapsed | 4387 | +| total_timesteps | 6205440 | +| train/ | | +| approx_kl | 0.013604113 | +| clip_fraction | 0.333 | +| clip_range | 0.0734 | +| entropy_loss | -7.32 | +| explained_variance | -0.134 | +| learning_rate | 4.85e-05 | +| loss | -0.0335 | +| n_updates | 27936 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.00014 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1414 | +| iterations | 3031 | +| time_elapsed | 4388 | +| total_timesteps | 6207488 | +| train/ | | +| approx_kl | 0.010175398 | +| clip_fraction | 0.314 | +| clip_range | 0.0734 | +| entropy_loss | -6.93 | +| explained_variance | 0.122 | +| learning_rate | 4.85e-05 | +| loss | -0.0341 | +| n_updates | 27940 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000311 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1414 | +| iterations | 3032 | +| time_elapsed | 4390 | +| total_timesteps | 6209536 | +| train/ | | +| approx_kl | 0.011286775 | +| clip_fraction | 0.322 | +| clip_range | 0.0734 | +| entropy_loss | -6.98 | +| explained_variance | 0.162 | +| learning_rate | 4.85e-05 | +| loss | -0.0336 | +| n_updates | 27944 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000261 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1414 | +| iterations | 3033 | +| time_elapsed | 4391 | +| total_timesteps | 6211584 | +| train/ | | +| approx_kl | 0.011004419 | +| clip_fraction | 0.321 | +| clip_range | 0.0734 | +| entropy_loss | -7.15 | +| explained_variance | 0.149 | +| learning_rate | 4.85e-05 | +| loss | -0.0268 | +| n_updates | 27948 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000301 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1414 | +| iterations | 3034 | +| time_elapsed | 4393 | +| total_timesteps | 6213632 | +| train/ | | +| approx_kl | 0.012215243 | +| clip_fraction | 0.313 | +| clip_range | 0.0734 | +| entropy_loss | -7.26 | +| explained_variance | -0.041 | +| learning_rate | 4.85e-05 | +| loss | -0.0385 | +| n_updates | 27952 | +| policy_gradient_loss | -0.0231 | +| value_loss | 0.000159 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1414 | +| iterations | 3035 | +| time_elapsed | 4394 | +| total_timesteps | 6215680 | +| train/ | | +| approx_kl | 0.012804295 | +| clip_fraction | 0.344 | +| clip_range | 0.0734 | +| entropy_loss | -6.87 | +| explained_variance | 0.562 | +| learning_rate | 4.85e-05 | +| loss | -0.031 | +| n_updates | 27956 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000133 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1414 | +| iterations | 3036 | +| time_elapsed | 4396 | +| total_timesteps | 6217728 | +| train/ | | +| approx_kl | 0.009941572 | +| clip_fraction | 0.313 | +| clip_range | 0.0734 | +| entropy_loss | -7.38 | +| explained_variance | -0.055 | +| learning_rate | 4.85e-05 | +| loss | -0.0319 | +| n_updates | 27960 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000171 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1414 | +| iterations | 3037 | +| time_elapsed | 4397 | +| total_timesteps | 6219776 | +| train/ | | +| approx_kl | 0.011146368 | +| clip_fraction | 0.314 | +| clip_range | 0.0734 | +| entropy_loss | -7.47 | +| explained_variance | -0.0813 | +| learning_rate | 4.85e-05 | +| loss | -0.0317 | +| n_updates | 27964 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000138 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1414 | +| iterations | 3038 | +| time_elapsed | 4398 | +| total_timesteps | 6221824 | +| train/ | | +| approx_kl | 0.01048479 | +| clip_fraction | 0.304 | +| clip_range | 0.0734 | +| entropy_loss | -7.17 | +| explained_variance | 0.176 | +| learning_rate | 4.85e-05 | +| loss | -0.0249 | +| n_updates | 27968 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.00029 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1414 | +| iterations | 3039 | +| time_elapsed | 4400 | +| total_timesteps | 6223872 | +| train/ | | +| approx_kl | 0.010212779 | +| clip_fraction | 0.337 | +| clip_range | 0.0734 | +| entropy_loss | -6.8 | +| explained_variance | 0.708 | +| learning_rate | 4.85e-05 | +| loss | -0.0358 | +| n_updates | 27972 | +| policy_gradient_loss | -0.0219 | +| value_loss | 8.83e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1414 | +| iterations | 3040 | +| time_elapsed | 4401 | +| total_timesteps | 6225920 | +| train/ | | +| approx_kl | 0.010314605 | +| clip_fraction | 0.293 | +| clip_range | 0.0734 | +| entropy_loss | -6.7 | +| explained_variance | 0.322 | +| learning_rate | 4.85e-05 | +| loss | -0.0209 | +| n_updates | 27976 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000326 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1414 | +| iterations | 3041 | +| time_elapsed | 4403 | +| total_timesteps | 6227968 | +| train/ | | +| approx_kl | 0.013910937 | +| clip_fraction | 0.343 | +| clip_range | 0.0734 | +| entropy_loss | -6.98 | +| explained_variance | -0.0209 | +| learning_rate | 4.85e-05 | +| loss | -0.0316 | +| n_updates | 27980 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000172 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1414 | +| iterations | 3042 | +| time_elapsed | 4404 | +| total_timesteps | 6230016 | +| train/ | | +| approx_kl | 0.01176163 | +| clip_fraction | 0.313 | +| clip_range | 0.0734 | +| entropy_loss | -7.08 | +| explained_variance | 0.271 | +| learning_rate | 4.85e-05 | +| loss | -0.0337 | +| n_updates | 27984 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.0002 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1414 | +| iterations | 3043 | +| time_elapsed | 4406 | +| total_timesteps | 6232064 | +| train/ | | +| approx_kl | 0.0101403175 | +| clip_fraction | 0.307 | +| clip_range | 0.0734 | +| entropy_loss | -7.09 | +| explained_variance | 0.322 | +| learning_rate | 4.85e-05 | +| loss | -0.0367 | +| n_updates | 27988 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.000282 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1414 | +| iterations | 3044 | +| time_elapsed | 4407 | +| total_timesteps | 6234112 | +| train/ | | +| approx_kl | 0.010236361 | +| clip_fraction | 0.31 | +| clip_range | 0.0734 | +| entropy_loss | -6.99 | +| explained_variance | 0.515 | +| learning_rate | 4.85e-05 | +| loss | -0.0293 | +| n_updates | 27992 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000142 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1414 | +| iterations | 3045 | +| time_elapsed | 4408 | +| total_timesteps | 6236160 | +| train/ | | +| approx_kl | 0.01239033 | +| clip_fraction | 0.316 | +| clip_range | 0.0734 | +| entropy_loss | -7.1 | +| explained_variance | 0.162 | +| learning_rate | 4.85e-05 | +| loss | -0.033 | +| n_updates | 27996 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000299 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1414 | +| iterations | 3046 | +| time_elapsed | 4410 | +| total_timesteps | 6238208 | +| train/ | | +| approx_kl | 0.01194313 | +| clip_fraction | 0.322 | +| clip_range | 0.0734 | +| entropy_loss | -7.26 | +| explained_variance | 0.0038 | +| learning_rate | 4.85e-05 | +| loss | -0.0305 | +| n_updates | 28000 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000181 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1414 | +| iterations | 3047 | +| time_elapsed | 4411 | +| total_timesteps | 6240256 | +| train/ | | +| approx_kl | 0.010761162 | +| clip_fraction | 0.312 | +| clip_range | 0.0734 | +| entropy_loss | -7.29 | +| explained_variance | 0.183 | +| learning_rate | 4.85e-05 | +| loss | -0.0309 | +| n_updates | 28004 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000267 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1414 | +| iterations | 3048 | +| time_elapsed | 4413 | +| total_timesteps | 6242304 | +| train/ | | +| approx_kl | 0.0104156155 | +| clip_fraction | 0.323 | +| clip_range | 0.0734 | +| entropy_loss | -7.27 | +| explained_variance | 0.206 | +| learning_rate | 4.85e-05 | +| loss | -0.0291 | +| n_updates | 28008 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000217 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1414 | +| iterations | 3049 | +| time_elapsed | 4414 | +| total_timesteps | 6244352 | +| train/ | | +| approx_kl | 0.013414351 | +| clip_fraction | 0.356 | +| clip_range | 0.0734 | +| entropy_loss | -7.36 | +| explained_variance | -0.382 | +| learning_rate | 4.85e-05 | +| loss | -0.0435 | +| n_updates | 28012 | +| policy_gradient_loss | -0.0264 | +| value_loss | 7.05e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1414 | +| iterations | 3050 | +| time_elapsed | 4415 | +| total_timesteps | 6246400 | +| train/ | | +| approx_kl | 0.011104151 | +| clip_fraction | 0.308 | +| clip_range | 0.0734 | +| entropy_loss | -7.09 | +| explained_variance | 0.188 | +| learning_rate | 4.85e-05 | +| loss | -0.0282 | +| n_updates | 28016 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000201 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1414 | +| iterations | 3051 | +| time_elapsed | 4417 | +| total_timesteps | 6248448 | +| train/ | | +| approx_kl | 0.010985075 | +| clip_fraction | 0.319 | +| clip_range | 0.0734 | +| entropy_loss | -7.37 | +| explained_variance | -0.0746 | +| learning_rate | 4.85e-05 | +| loss | -0.0312 | +| n_updates | 28020 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000189 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1414 | +| iterations | 3052 | +| time_elapsed | 4418 | +| total_timesteps | 6250496 | +| train/ | | +| approx_kl | 0.010165406 | +| clip_fraction | 0.28 | +| clip_range | 0.0734 | +| entropy_loss | -6.85 | +| explained_variance | 0.422 | +| learning_rate | 4.85e-05 | +| loss | -0.0276 | +| n_updates | 28024 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000292 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1414 | +| iterations | 3053 | +| time_elapsed | 4420 | +| total_timesteps | 6252544 | +| train/ | | +| approx_kl | 0.0116250105 | +| clip_fraction | 0.338 | +| clip_range | 0.0734 | +| entropy_loss | -6.75 | +| explained_variance | 0.492 | +| learning_rate | 4.85e-05 | +| loss | -0.0246 | +| n_updates | 28028 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000152 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1414 | +| iterations | 3054 | +| time_elapsed | 4421 | +| total_timesteps | 6254592 | +| train/ | | +| approx_kl | 0.013739132 | +| clip_fraction | 0.349 | +| clip_range | 0.0734 | +| entropy_loss | -7.11 | +| explained_variance | 0.29 | +| learning_rate | 4.85e-05 | +| loss | -0.0348 | +| n_updates | 28032 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000139 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1414 | +| iterations | 3055 | +| time_elapsed | 4423 | +| total_timesteps | 6256640 | +| train/ | | +| approx_kl | 0.016447416 | +| clip_fraction | 0.342 | +| clip_range | 0.0734 | +| entropy_loss | -7.37 | +| explained_variance | -0.0423 | +| learning_rate | 4.85e-05 | +| loss | -0.0286 | +| n_updates | 28036 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000179 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1414 | +| iterations | 3056 | +| time_elapsed | 4424 | +| total_timesteps | 6258688 | +| train/ | | +| approx_kl | 0.011061837 | +| clip_fraction | 0.316 | +| clip_range | 0.0734 | +| entropy_loss | -7.26 | +| explained_variance | 0.388 | +| learning_rate | 4.85e-05 | +| loss | -0.0314 | +| n_updates | 28040 | +| policy_gradient_loss | -0.019 | +| value_loss | 9.28e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1414 | +| iterations | 3057 | +| time_elapsed | 4426 | +| total_timesteps | 6260736 | +| train/ | | +| approx_kl | 0.011615891 | +| clip_fraction | 0.314 | +| clip_range | 0.0734 | +| entropy_loss | -6.92 | +| explained_variance | 0.39 | +| learning_rate | 4.85e-05 | +| loss | -0.0209 | +| n_updates | 28044 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000247 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1414 | +| iterations | 3058 | +| time_elapsed | 4427 | +| total_timesteps | 6262784 | +| train/ | | +| approx_kl | 0.014852585 | +| clip_fraction | 0.317 | +| clip_range | 0.0734 | +| entropy_loss | -7.02 | +| explained_variance | 0.465 | +| learning_rate | 4.85e-05 | +| loss | -0.0371 | +| n_updates | 28048 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.00016 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1414 | +| iterations | 3059 | +| time_elapsed | 4428 | +| total_timesteps | 6264832 | +| train/ | | +| approx_kl | 0.013179947 | +| clip_fraction | 0.323 | +| clip_range | 0.0734 | +| entropy_loss | -7.14 | +| explained_variance | -0.363 | +| learning_rate | 4.85e-05 | +| loss | -0.0382 | +| n_updates | 28052 | +| policy_gradient_loss | -0.0225 | +| value_loss | 6.89e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1414 | +| iterations | 3060 | +| time_elapsed | 4430 | +| total_timesteps | 6266880 | +| train/ | | +| approx_kl | 0.012773803 | +| clip_fraction | 0.33 | +| clip_range | 0.0734 | +| entropy_loss | -7.4 | +| explained_variance | -0.113 | +| learning_rate | 4.85e-05 | +| loss | -0.0324 | +| n_updates | 28056 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000123 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1414 | +| iterations | 3061 | +| time_elapsed | 4431 | +| total_timesteps | 6268928 | +| train/ | | +| approx_kl | 0.009767318 | +| clip_fraction | 0.305 | +| clip_range | 0.0734 | +| entropy_loss | -7.27 | +| explained_variance | 0.235 | +| learning_rate | 4.85e-05 | +| loss | -0.0306 | +| n_updates | 28060 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000289 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1414 | +| iterations | 3062 | +| time_elapsed | 4433 | +| total_timesteps | 6270976 | +| train/ | | +| approx_kl | 0.0132093 | +| clip_fraction | 0.324 | +| clip_range | 0.0734 | +| entropy_loss | -7 | +| explained_variance | 0.291 | +| learning_rate | 4.85e-05 | +| loss | -0.0307 | +| n_updates | 28064 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000173 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1414 | +| iterations | 3063 | +| time_elapsed | 4434 | +| total_timesteps | 6273024 | +| train/ | | +| approx_kl | 0.010796428 | +| clip_fraction | 0.3 | +| clip_range | 0.0734 | +| entropy_loss | -7.2 | +| explained_variance | 0.209 | +| learning_rate | 4.85e-05 | +| loss | -0.0319 | +| n_updates | 28068 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000132 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1414 | +| iterations | 3064 | +| time_elapsed | 4436 | +| total_timesteps | 6275072 | +| train/ | | +| approx_kl | 0.011958184 | +| clip_fraction | 0.301 | +| clip_range | 0.0734 | +| entropy_loss | -7.07 | +| explained_variance | 0.236 | +| learning_rate | 4.85e-05 | +| loss | -0.0285 | +| n_updates | 28072 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000188 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1414 | +| iterations | 3065 | +| time_elapsed | 4437 | +| total_timesteps | 6277120 | +| train/ | | +| approx_kl | 0.013908535 | +| clip_fraction | 0.341 | +| clip_range | 0.0734 | +| entropy_loss | -7.21 | +| explained_variance | 0.285 | +| learning_rate | 4.85e-05 | +| loss | -0.0329 | +| n_updates | 28076 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000136 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1414 | +| iterations | 3066 | +| time_elapsed | 4438 | +| total_timesteps | 6279168 | +| train/ | | +| approx_kl | 0.011200482 | +| clip_fraction | 0.303 | +| clip_range | 0.0734 | +| entropy_loss | -7.04 | +| explained_variance | 0.203 | +| learning_rate | 4.85e-05 | +| loss | -0.0313 | +| n_updates | 28080 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000249 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1414 | +| iterations | 3067 | +| time_elapsed | 4440 | +| total_timesteps | 6281216 | +| train/ | | +| approx_kl | 0.011819776 | +| clip_fraction | 0.315 | +| clip_range | 0.0734 | +| entropy_loss | -7.11 | +| explained_variance | 0.271 | +| learning_rate | 4.85e-05 | +| loss | -0.0302 | +| n_updates | 28084 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000159 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1414 | +| iterations | 3068 | +| time_elapsed | 4441 | +| total_timesteps | 6283264 | +| train/ | | +| approx_kl | 0.012627406 | +| clip_fraction | 0.308 | +| clip_range | 0.0734 | +| entropy_loss | -7.21 | +| explained_variance | 0.211 | +| learning_rate | 4.85e-05 | +| loss | -0.0349 | +| n_updates | 28088 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000184 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1414 | +| iterations | 3069 | +| time_elapsed | 4443 | +| total_timesteps | 6285312 | +| train/ | | +| approx_kl | 0.01036144 | +| clip_fraction | 0.303 | +| clip_range | 0.0734 | +| entropy_loss | -7.17 | +| explained_variance | -0.0472 | +| learning_rate | 4.85e-05 | +| loss | -0.0192 | +| n_updates | 28092 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000285 | +---------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1414 | +| iterations | 3070 | +| time_elapsed | 4444 | +| total_timesteps | 6287360 | +| train/ | | +| approx_kl | 0.0117585 | +| clip_fraction | 0.306 | +| clip_range | 0.0734 | +| entropy_loss | -7.07 | +| explained_variance | 0.179 | +| learning_rate | 4.85e-05 | +| loss | -0.03 | +| n_updates | 28096 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000211 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1414 | +| iterations | 3071 | +| time_elapsed | 4446 | +| total_timesteps | 6289408 | +| train/ | | +| approx_kl | 0.011802057 | +| clip_fraction | 0.314 | +| clip_range | 0.0734 | +| entropy_loss | -7.29 | +| explained_variance | -0.0766 | +| learning_rate | 4.85e-05 | +| loss | -0.0354 | +| n_updates | 28100 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000184 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1414 | +| iterations | 3072 | +| time_elapsed | 4447 | +| total_timesteps | 6291456 | +| train/ | | +| approx_kl | 0.010163517 | +| clip_fraction | 0.301 | +| clip_range | 0.0734 | +| entropy_loss | -6.91 | +| explained_variance | 0.39 | +| learning_rate | 4.85e-05 | +| loss | -0.0224 | +| n_updates | 28104 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000258 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.388 | +| time/ | | +| fps | 1414 | +| iterations | 3073 | +| time_elapsed | 4448 | +| total_timesteps | 6293504 | +| train/ | | +| approx_kl | 0.0110731125 | +| clip_fraction | 0.273 | +| clip_range | 0.0734 | +| entropy_loss | -6.88 | +| explained_variance | 0.279 | +| learning_rate | 4.85e-05 | +| loss | -0.0269 | +| n_updates | 28108 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000305 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1414 | +| iterations | 3074 | +| time_elapsed | 4450 | +| total_timesteps | 6295552 | +| train/ | | +| approx_kl | 0.010244355 | +| clip_fraction | 0.291 | +| clip_range | 0.0734 | +| entropy_loss | -6.98 | +| explained_variance | 0.144 | +| learning_rate | 4.85e-05 | +| loss | -0.0243 | +| n_updates | 28112 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.00034 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1414 | +| iterations | 3075 | +| time_elapsed | 4451 | +| total_timesteps | 6297600 | +| train/ | | +| approx_kl | 0.011990479 | +| clip_fraction | 0.353 | +| clip_range | 0.0734 | +| entropy_loss | -6.96 | +| explained_variance | 0.602 | +| learning_rate | 4.85e-05 | +| loss | -0.0411 | +| n_updates | 28116 | +| policy_gradient_loss | -0.0263 | +| value_loss | 7.95e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1414 | +| iterations | 3076 | +| time_elapsed | 4453 | +| total_timesteps | 6299648 | +| train/ | | +| approx_kl | 0.011438653 | +| clip_fraction | 0.326 | +| clip_range | 0.0734 | +| entropy_loss | -7.28 | +| explained_variance | -0.142 | +| learning_rate | 4.85e-05 | +| loss | -0.0331 | +| n_updates | 28120 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000187 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1414 | +| iterations | 3077 | +| time_elapsed | 4454 | +| total_timesteps | 6301696 | +| train/ | | +| approx_kl | 0.010068159 | +| clip_fraction | 0.317 | +| clip_range | 0.0734 | +| entropy_loss | -7.38 | +| explained_variance | 0.0953 | +| learning_rate | 4.85e-05 | +| loss | -0.0339 | +| n_updates | 28124 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000195 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1414 | +| iterations | 3078 | +| time_elapsed | 4456 | +| total_timesteps | 6303744 | +| train/ | | +| approx_kl | 0.012894241 | +| clip_fraction | 0.342 | +| clip_range | 0.0734 | +| entropy_loss | -6.95 | +| explained_variance | 0.461 | +| learning_rate | 4.85e-05 | +| loss | -0.0329 | +| n_updates | 28128 | +| policy_gradient_loss | -0.0225 | +| value_loss | 0.000108 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1414 | +| iterations | 3079 | +| time_elapsed | 4457 | +| total_timesteps | 6305792 | +| train/ | | +| approx_kl | 0.009998952 | +| clip_fraction | 0.318 | +| clip_range | 0.0734 | +| entropy_loss | -6.83 | +| explained_variance | 0.587 | +| learning_rate | 4.85e-05 | +| loss | -0.0385 | +| n_updates | 28132 | +| policy_gradient_loss | -0.0205 | +| value_loss | 9.42e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1414 | +| iterations | 3080 | +| time_elapsed | 4458 | +| total_timesteps | 6307840 | +| train/ | | +| approx_kl | 0.011588263 | +| clip_fraction | 0.332 | +| clip_range | 0.0734 | +| entropy_loss | -7.39 | +| explained_variance | -0.0751 | +| learning_rate | 4.85e-05 | +| loss | -0.0356 | +| n_updates | 28136 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000104 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1414 | +| iterations | 3081 | +| time_elapsed | 4460 | +| total_timesteps | 6309888 | +| train/ | | +| approx_kl | 0.010772461 | +| clip_fraction | 0.316 | +| clip_range | 0.0734 | +| entropy_loss | -7.12 | +| explained_variance | 0.326 | +| learning_rate | 4.85e-05 | +| loss | -0.0325 | +| n_updates | 28140 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000154 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1414 | +| iterations | 3082 | +| time_elapsed | 4461 | +| total_timesteps | 6311936 | +| train/ | | +| approx_kl | 0.011848134 | +| clip_fraction | 0.29 | +| clip_range | 0.0734 | +| entropy_loss | -7.04 | +| explained_variance | 0.345 | +| learning_rate | 4.85e-05 | +| loss | -0.0315 | +| n_updates | 28144 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000253 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1414 | +| iterations | 3083 | +| time_elapsed | 4463 | +| total_timesteps | 6313984 | +| train/ | | +| approx_kl | 0.010859293 | +| clip_fraction | 0.322 | +| clip_range | 0.0734 | +| entropy_loss | -7.2 | +| explained_variance | 0.0619 | +| learning_rate | 4.85e-05 | +| loss | -0.028 | +| n_updates | 28148 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000217 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.385 | +| time/ | | +| fps | 1414 | +| iterations | 3084 | +| time_elapsed | 4464 | +| total_timesteps | 6316032 | +| train/ | | +| approx_kl | 0.010697894 | +| clip_fraction | 0.315 | +| clip_range | 0.0734 | +| entropy_loss | -7.05 | +| explained_variance | 0.425 | +| learning_rate | 4.85e-05 | +| loss | -0.0296 | +| n_updates | 28152 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000148 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.385 | +| time/ | | +| fps | 1414 | +| iterations | 3085 | +| time_elapsed | 4466 | +| total_timesteps | 6318080 | +| train/ | | +| approx_kl | 0.011229418 | +| clip_fraction | 0.323 | +| clip_range | 0.0734 | +| entropy_loss | -7.19 | +| explained_variance | 0.247 | +| learning_rate | 4.85e-05 | +| loss | -0.031 | +| n_updates | 28156 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000189 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.388 | +| time/ | | +| fps | 1414 | +| iterations | 3086 | +| time_elapsed | 4467 | +| total_timesteps | 6320128 | +| train/ | | +| approx_kl | 0.011254618 | +| clip_fraction | 0.295 | +| clip_range | 0.0734 | +| entropy_loss | -7.16 | +| explained_variance | 0.39 | +| learning_rate | 4.85e-05 | +| loss | -0.0233 | +| n_updates | 28160 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000213 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.387 | +| time/ | | +| fps | 1414 | +| iterations | 3087 | +| time_elapsed | 4468 | +| total_timesteps | 6322176 | +| train/ | | +| approx_kl | 0.011353533 | +| clip_fraction | 0.302 | +| clip_range | 0.0734 | +| entropy_loss | -7.35 | +| explained_variance | 0.253 | +| learning_rate | 4.85e-05 | +| loss | -0.029 | +| n_updates | 28164 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000167 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.385 | +| time/ | | +| fps | 1414 | +| iterations | 3088 | +| time_elapsed | 4470 | +| total_timesteps | 6324224 | +| train/ | | +| approx_kl | 0.012217339 | +| clip_fraction | 0.335 | +| clip_range | 0.0734 | +| entropy_loss | -6.83 | +| explained_variance | 0.54 | +| learning_rate | 4.85e-05 | +| loss | -0.0337 | +| n_updates | 28168 | +| policy_gradient_loss | -0.0223 | +| value_loss | 0.000167 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.385 | +| time/ | | +| fps | 1414 | +| iterations | 3089 | +| time_elapsed | 4471 | +| total_timesteps | 6326272 | +| train/ | | +| approx_kl | 0.009747596 | +| clip_fraction | 0.285 | +| clip_range | 0.0734 | +| entropy_loss | -7.34 | +| explained_variance | -0.0109 | +| learning_rate | 4.85e-05 | +| loss | -0.0362 | +| n_updates | 28172 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000163 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.384 | +| time/ | | +| fps | 1414 | +| iterations | 3090 | +| time_elapsed | 4473 | +| total_timesteps | 6328320 | +| train/ | | +| approx_kl | 0.011245163 | +| clip_fraction | 0.318 | +| clip_range | 0.0734 | +| entropy_loss | -7.29 | +| explained_variance | 0.274 | +| learning_rate | 4.85e-05 | +| loss | -0.0355 | +| n_updates | 28176 | +| policy_gradient_loss | -0.0228 | +| value_loss | 0.000133 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.386 | +| time/ | | +| fps | 1414 | +| iterations | 3091 | +| time_elapsed | 4474 | +| total_timesteps | 6330368 | +| train/ | | +| approx_kl | 0.010217057 | +| clip_fraction | 0.294 | +| clip_range | 0.0734 | +| entropy_loss | -7.32 | +| explained_variance | 0.295 | +| learning_rate | 4.85e-05 | +| loss | -0.0336 | +| n_updates | 28180 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000171 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1414 | +| iterations | 3092 | +| time_elapsed | 4476 | +| total_timesteps | 6332416 | +| train/ | | +| approx_kl | 0.013060671 | +| clip_fraction | 0.33 | +| clip_range | 0.0734 | +| entropy_loss | -7.25 | +| explained_variance | 0.403 | +| learning_rate | 4.85e-05 | +| loss | -0.0375 | +| n_updates | 28184 | +| policy_gradient_loss | -0.0237 | +| value_loss | 0.000112 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1414 | +| iterations | 3093 | +| time_elapsed | 4477 | +| total_timesteps | 6334464 | +| train/ | | +| approx_kl | 0.011426499 | +| clip_fraction | 0.291 | +| clip_range | 0.0734 | +| entropy_loss | -7.17 | +| explained_variance | 0.316 | +| learning_rate | 4.85e-05 | +| loss | -0.0278 | +| n_updates | 28188 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000152 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1414 | +| iterations | 3094 | +| time_elapsed | 4478 | +| total_timesteps | 6336512 | +| train/ | | +| approx_kl | 0.010864317 | +| clip_fraction | 0.333 | +| clip_range | 0.0734 | +| entropy_loss | -6.96 | +| explained_variance | 0.267 | +| learning_rate | 4.85e-05 | +| loss | -0.0341 | +| n_updates | 28192 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000186 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1414 | +| iterations | 3095 | +| time_elapsed | 4480 | +| total_timesteps | 6338560 | +| train/ | | +| approx_kl | 0.010951131 | +| clip_fraction | 0.344 | +| clip_range | 0.0734 | +| entropy_loss | -7.3 | +| explained_variance | 0.439 | +| learning_rate | 4.85e-05 | +| loss | -0.0411 | +| n_updates | 28196 | +| policy_gradient_loss | -0.024 | +| value_loss | 6.99e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1414 | +| iterations | 3096 | +| time_elapsed | 4481 | +| total_timesteps | 6340608 | +| train/ | | +| approx_kl | 0.010511076 | +| clip_fraction | 0.27 | +| clip_range | 0.0734 | +| entropy_loss | -7.2 | +| explained_variance | -0.119 | +| learning_rate | 4.85e-05 | +| loss | -0.0281 | +| n_updates | 28200 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000218 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1414 | +| iterations | 3097 | +| time_elapsed | 4483 | +| total_timesteps | 6342656 | +| train/ | | +| approx_kl | 0.010599339 | +| clip_fraction | 0.31 | +| clip_range | 0.0734 | +| entropy_loss | -6.92 | +| explained_variance | 0.288 | +| learning_rate | 4.85e-05 | +| loss | -0.0282 | +| n_updates | 28204 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000276 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1414 | +| iterations | 3098 | +| time_elapsed | 4484 | +| total_timesteps | 6344704 | +| train/ | | +| approx_kl | 0.011298242 | +| clip_fraction | 0.345 | +| clip_range | 0.0734 | +| entropy_loss | -7.24 | +| explained_variance | 0.146 | +| learning_rate | 4.85e-05 | +| loss | -0.035 | +| n_updates | 28208 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000111 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1414 | +| iterations | 3099 | +| time_elapsed | 4486 | +| total_timesteps | 6346752 | +| train/ | | +| approx_kl | 0.012186928 | +| clip_fraction | 0.34 | +| clip_range | 0.0734 | +| entropy_loss | -7.17 | +| explained_variance | 0.117 | +| learning_rate | 4.85e-05 | +| loss | -0.0347 | +| n_updates | 28212 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000166 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1414 | +| iterations | 3100 | +| time_elapsed | 4487 | +| total_timesteps | 6348800 | +| train/ | | +| approx_kl | 0.012609664 | +| clip_fraction | 0.32 | +| clip_range | 0.0734 | +| entropy_loss | -7.22 | +| explained_variance | 0.145 | +| learning_rate | 4.85e-05 | +| loss | -0.0343 | +| n_updates | 28216 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000208 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1414 | +| iterations | 3101 | +| time_elapsed | 4488 | +| total_timesteps | 6350848 | +| train/ | | +| approx_kl | 0.013832019 | +| clip_fraction | 0.339 | +| clip_range | 0.0734 | +| entropy_loss | -7.29 | +| explained_variance | -0.106 | +| learning_rate | 4.85e-05 | +| loss | -0.0338 | +| n_updates | 28220 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000232 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1414 | +| iterations | 3102 | +| time_elapsed | 4490 | +| total_timesteps | 6352896 | +| train/ | | +| approx_kl | 0.014045262 | +| clip_fraction | 0.341 | +| clip_range | 0.0734 | +| entropy_loss | -7.25 | +| explained_variance | 0.203 | +| learning_rate | 4.85e-05 | +| loss | -0.0306 | +| n_updates | 28224 | +| policy_gradient_loss | -0.0221 | +| value_loss | 0.000164 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1414 | +| iterations | 3103 | +| time_elapsed | 4491 | +| total_timesteps | 6354944 | +| train/ | | +| approx_kl | 0.013047911 | +| clip_fraction | 0.305 | +| clip_range | 0.0734 | +| entropy_loss | -7.2 | +| explained_variance | 0.162 | +| learning_rate | 4.85e-05 | +| loss | -0.0284 | +| n_updates | 28228 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000294 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1414 | +| iterations | 3104 | +| time_elapsed | 4493 | +| total_timesteps | 6356992 | +| train/ | | +| approx_kl | 0.012552852 | +| clip_fraction | 0.348 | +| clip_range | 0.0734 | +| entropy_loss | -7.27 | +| explained_variance | -0.165 | +| learning_rate | 4.85e-05 | +| loss | -0.0355 | +| n_updates | 28232 | +| policy_gradient_loss | -0.0237 | +| value_loss | 0.000196 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1414 | +| iterations | 3105 | +| time_elapsed | 4494 | +| total_timesteps | 6359040 | +| train/ | | +| approx_kl | 0.012795343 | +| clip_fraction | 0.324 | +| clip_range | 0.0734 | +| entropy_loss | -6.83 | +| explained_variance | 0.366 | +| learning_rate | 4.85e-05 | +| loss | -0.034 | +| n_updates | 28236 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000183 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.39 | +| time/ | | +| fps | 1414 | +| iterations | 3106 | +| time_elapsed | 4495 | +| total_timesteps | 6361088 | +| train/ | | +| approx_kl | 0.011703556 | +| clip_fraction | 0.326 | +| clip_range | 0.0734 | +| entropy_loss | -7.31 | +| explained_variance | -0.159 | +| learning_rate | 4.85e-05 | +| loss | -0.038 | +| n_updates | 28240 | +| policy_gradient_loss | -0.0222 | +| value_loss | 0.00017 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.391 | +| time/ | | +| fps | 1414 | +| iterations | 3107 | +| time_elapsed | 4497 | +| total_timesteps | 6363136 | +| train/ | | +| approx_kl | 0.012179576 | +| clip_fraction | 0.319 | +| clip_range | 0.0734 | +| entropy_loss | -6.66 | +| explained_variance | 0.597 | +| learning_rate | 4.85e-05 | +| loss | -0.0297 | +| n_updates | 28244 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000174 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.387 | +| time/ | | +| fps | 1414 | +| iterations | 3108 | +| time_elapsed | 4498 | +| total_timesteps | 6365184 | +| train/ | | +| approx_kl | 0.013216017 | +| clip_fraction | 0.318 | +| clip_range | 0.0734 | +| entropy_loss | -7.11 | +| explained_variance | 0.0265 | +| learning_rate | 4.85e-05 | +| loss | -0.0268 | +| n_updates | 28248 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.00029 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.389 | +| time/ | | +| fps | 1414 | +| iterations | 3109 | +| time_elapsed | 4500 | +| total_timesteps | 6367232 | +| train/ | | +| approx_kl | 0.013683308 | +| clip_fraction | 0.319 | +| clip_range | 0.0734 | +| entropy_loss | -7.08 | +| explained_variance | 0.265 | +| learning_rate | 4.85e-05 | +| loss | -0.0363 | +| n_updates | 28252 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.00017 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.394 | +| time/ | | +| fps | 1414 | +| iterations | 3110 | +| time_elapsed | 4501 | +| total_timesteps | 6369280 | +| train/ | | +| approx_kl | 0.0110047115 | +| clip_fraction | 0.321 | +| clip_range | 0.0734 | +| entropy_loss | -7.19 | +| explained_variance | 0.116 | +| learning_rate | 4.85e-05 | +| loss | -0.0272 | +| n_updates | 28256 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000222 | +------------------------------------------ +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.393 | +| time/ | | +| fps | 1414 | +| iterations | 3111 | +| time_elapsed | 4503 | +| total_timesteps | 6371328 | +| train/ | | +| approx_kl | 0.0102599 | +| clip_fraction | 0.326 | +| clip_range | 0.0734 | +| entropy_loss | -7.11 | +| explained_variance | 0.162 | +| learning_rate | 4.85e-05 | +| loss | -0.033 | +| n_updates | 28260 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000167 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.403 | +| time/ | | +| fps | 1414 | +| iterations | 3112 | +| time_elapsed | 4504 | +| total_timesteps | 6373376 | +| train/ | | +| approx_kl | 0.011236699 | +| clip_fraction | 0.329 | +| clip_range | 0.0734 | +| entropy_loss | -7.27 | +| explained_variance | 0.228 | +| learning_rate | 4.85e-05 | +| loss | -0.0358 | +| n_updates | 28264 | +| policy_gradient_loss | -0.0228 | +| value_loss | 0.000147 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.395 | +| time/ | | +| fps | 1414 | +| iterations | 3113 | +| time_elapsed | 4505 | +| total_timesteps | 6375424 | +| train/ | | +| approx_kl | 0.010510858 | +| clip_fraction | 0.319 | +| clip_range | 0.0734 | +| entropy_loss | -7.11 | +| explained_variance | 0.191 | +| learning_rate | 4.85e-05 | +| loss | -0.0315 | +| n_updates | 28268 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000205 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.393 | +| time/ | | +| fps | 1414 | +| iterations | 3114 | +| time_elapsed | 4507 | +| total_timesteps | 6377472 | +| train/ | | +| approx_kl | 0.013115314 | +| clip_fraction | 0.338 | +| clip_range | 0.0734 | +| entropy_loss | -7.2 | +| explained_variance | 0.113 | +| learning_rate | 4.85e-05 | +| loss | -0.0329 | +| n_updates | 28272 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000271 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.393 | +| time/ | | +| fps | 1414 | +| iterations | 3115 | +| time_elapsed | 4508 | +| total_timesteps | 6379520 | +| train/ | | +| approx_kl | 0.011399375 | +| clip_fraction | 0.324 | +| clip_range | 0.0734 | +| entropy_loss | -7.12 | +| explained_variance | 0.388 | +| learning_rate | 4.85e-05 | +| loss | -0.0307 | +| n_updates | 28276 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000134 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.39 | +| time/ | | +| fps | 1414 | +| iterations | 3116 | +| time_elapsed | 4510 | +| total_timesteps | 6381568 | +| train/ | | +| approx_kl | 0.011621945 | +| clip_fraction | 0.34 | +| clip_range | 0.0734 | +| entropy_loss | -7.3 | +| explained_variance | 0.0935 | +| learning_rate | 4.85e-05 | +| loss | -0.0374 | +| n_updates | 28280 | +| policy_gradient_loss | -0.0221 | +| value_loss | 0.000153 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.39 | +| time/ | | +| fps | 1414 | +| iterations | 3117 | +| time_elapsed | 4511 | +| total_timesteps | 6383616 | +| train/ | | +| approx_kl | 0.011173347 | +| clip_fraction | 0.341 | +| clip_range | 0.0734 | +| entropy_loss | -7.17 | +| explained_variance | 0.309 | +| learning_rate | 4.85e-05 | +| loss | -0.0335 | +| n_updates | 28284 | +| policy_gradient_loss | -0.0221 | +| value_loss | 0.000109 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.393 | +| time/ | | +| fps | 1414 | +| iterations | 3118 | +| time_elapsed | 4513 | +| total_timesteps | 6385664 | +| train/ | | +| approx_kl | 0.010259023 | +| clip_fraction | 0.324 | +| clip_range | 0.0734 | +| entropy_loss | -7.39 | +| explained_variance | -0.095 | +| learning_rate | 4.85e-05 | +| loss | -0.0344 | +| n_updates | 28288 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000128 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.397 | +| time/ | | +| fps | 1414 | +| iterations | 3119 | +| time_elapsed | 4514 | +| total_timesteps | 6387712 | +| train/ | | +| approx_kl | 0.00964981 | +| clip_fraction | 0.289 | +| clip_range | 0.0734 | +| entropy_loss | -6.86 | +| explained_variance | 0.302 | +| learning_rate | 4.85e-05 | +| loss | -0.0302 | +| n_updates | 28292 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000301 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.406 | +| time/ | | +| fps | 1414 | +| iterations | 3120 | +| time_elapsed | 4515 | +| total_timesteps | 6389760 | +| train/ | | +| approx_kl | 0.011778637 | +| clip_fraction | 0.313 | +| clip_range | 0.0734 | +| entropy_loss | -6.7 | +| explained_variance | 0.548 | +| learning_rate | 4.85e-05 | +| loss | -0.0286 | +| n_updates | 28296 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000173 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.402 | +| time/ | | +| fps | 1414 | +| iterations | 3121 | +| time_elapsed | 4517 | +| total_timesteps | 6391808 | +| train/ | | +| approx_kl | 0.012438959 | +| clip_fraction | 0.318 | +| clip_range | 0.0734 | +| entropy_loss | -7.03 | +| explained_variance | 0.0753 | +| learning_rate | 4.85e-05 | +| loss | -0.0329 | +| n_updates | 28300 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000226 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.402 | +| time/ | | +| fps | 1414 | +| iterations | 3122 | +| time_elapsed | 4518 | +| total_timesteps | 6393856 | +| train/ | | +| approx_kl | 0.013696758 | +| clip_fraction | 0.342 | +| clip_range | 0.0734 | +| entropy_loss | -6.83 | +| explained_variance | 0.465 | +| learning_rate | 4.85e-05 | +| loss | -0.0341 | +| n_updates | 28304 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000194 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.402 | +| time/ | | +| fps | 1414 | +| iterations | 3123 | +| time_elapsed | 4520 | +| total_timesteps | 6395904 | +| train/ | | +| approx_kl | 0.011799464 | +| clip_fraction | 0.331 | +| clip_range | 0.0734 | +| entropy_loss | -7.2 | +| explained_variance | 0.308 | +| learning_rate | 4.85e-05 | +| loss | -0.0334 | +| n_updates | 28308 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000157 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.406 | +| time/ | | +| fps | 1414 | +| iterations | 3124 | +| time_elapsed | 4521 | +| total_timesteps | 6397952 | +| train/ | | +| approx_kl | 0.013190057 | +| clip_fraction | 0.33 | +| clip_range | 0.0734 | +| entropy_loss | -7.48 | +| explained_variance | -0.057 | +| learning_rate | 4.85e-05 | +| loss | -0.0339 | +| n_updates | 28312 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000219 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.411 | +| time/ | | +| fps | 1414 | +| iterations | 3125 | +| time_elapsed | 4523 | +| total_timesteps | 6400000 | +| train/ | | +| approx_kl | 0.012791397 | +| clip_fraction | 0.321 | +| clip_range | 0.0734 | +| entropy_loss | -7.31 | +| explained_variance | 0.253 | +| learning_rate | 4.85e-05 | +| loss | -0.0305 | +| n_updates | 28316 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000155 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.406 | +| time/ | | +| fps | 1414 | +| iterations | 3126 | +| time_elapsed | 4524 | +| total_timesteps | 6402048 | +| train/ | | +| approx_kl | 0.012630208 | +| clip_fraction | 0.335 | +| clip_range | 0.0734 | +| entropy_loss | -7.15 | +| explained_variance | 0.188 | +| learning_rate | 4.85e-05 | +| loss | -0.0391 | +| n_updates | 28320 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000243 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.405 | +| time/ | | +| fps | 1414 | +| iterations | 3127 | +| time_elapsed | 4526 | +| total_timesteps | 6404096 | +| train/ | | +| approx_kl | 0.0114508625 | +| clip_fraction | 0.315 | +| clip_range | 0.0734 | +| entropy_loss | -6.75 | +| explained_variance | 0.466 | +| learning_rate | 4.85e-05 | +| loss | -0.0253 | +| n_updates | 28324 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000228 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.405 | +| time/ | | +| fps | 1414 | +| iterations | 3128 | +| time_elapsed | 4527 | +| total_timesteps | 6406144 | +| train/ | | +| approx_kl | 0.011469256 | +| clip_fraction | 0.348 | +| clip_range | 0.0734 | +| entropy_loss | -7.3 | +| explained_variance | -0.0415 | +| learning_rate | 4.85e-05 | +| loss | -0.0411 | +| n_updates | 28328 | +| policy_gradient_loss | -0.0219 | +| value_loss | 0.000133 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.403 | +| time/ | | +| fps | 1414 | +| iterations | 3129 | +| time_elapsed | 4528 | +| total_timesteps | 6408192 | +| train/ | | +| approx_kl | 0.011681483 | +| clip_fraction | 0.364 | +| clip_range | 0.0734 | +| entropy_loss | -7.23 | +| explained_variance | 0.445 | +| learning_rate | 4.85e-05 | +| loss | -0.0412 | +| n_updates | 28332 | +| policy_gradient_loss | -0.0246 | +| value_loss | 8.85e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.402 | +| time/ | | +| fps | 1414 | +| iterations | 3130 | +| time_elapsed | 4530 | +| total_timesteps | 6410240 | +| train/ | | +| approx_kl | 0.0107550975 | +| clip_fraction | 0.354 | +| clip_range | 0.0734 | +| entropy_loss | -7.08 | +| explained_variance | 0.491 | +| learning_rate | 4.85e-05 | +| loss | -0.0357 | +| n_updates | 28336 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000134 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.399 | +| time/ | | +| fps | 1414 | +| iterations | 3131 | +| time_elapsed | 4531 | +| total_timesteps | 6412288 | +| train/ | | +| approx_kl | 0.0109128095 | +| clip_fraction | 0.308 | +| clip_range | 0.0734 | +| entropy_loss | -7.17 | +| explained_variance | 0.0988 | +| learning_rate | 4.85e-05 | +| loss | -0.026 | +| n_updates | 28340 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000312 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.399 | +| time/ | | +| fps | 1414 | +| iterations | 3132 | +| time_elapsed | 4533 | +| total_timesteps | 6414336 | +| train/ | | +| approx_kl | 0.011212915 | +| clip_fraction | 0.313 | +| clip_range | 0.0734 | +| entropy_loss | -6.53 | +| explained_variance | 0.638 | +| learning_rate | 4.85e-05 | +| loss | -0.0327 | +| n_updates | 28344 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000162 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.394 | +| time/ | | +| fps | 1414 | +| iterations | 3133 | +| time_elapsed | 4534 | +| total_timesteps | 6416384 | +| train/ | | +| approx_kl | 0.01096542 | +| clip_fraction | 0.337 | +| clip_range | 0.0734 | +| entropy_loss | -7.2 | +| explained_variance | 0.503 | +| learning_rate | 4.85e-05 | +| loss | -0.0362 | +| n_updates | 28348 | +| policy_gradient_loss | -0.0229 | +| value_loss | 7.04e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.39 | +| time/ | | +| fps | 1414 | +| iterations | 3134 | +| time_elapsed | 4536 | +| total_timesteps | 6418432 | +| train/ | | +| approx_kl | 0.011410315 | +| clip_fraction | 0.308 | +| clip_range | 0.0734 | +| entropy_loss | -6.78 | +| explained_variance | 0.096 | +| learning_rate | 4.85e-05 | +| loss | -0.0262 | +| n_updates | 28352 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000259 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.39 | +| time/ | | +| fps | 1415 | +| iterations | 3135 | +| time_elapsed | 4537 | +| total_timesteps | 6420480 | +| train/ | | +| approx_kl | 0.012646984 | +| clip_fraction | 0.331 | +| clip_range | 0.0734 | +| entropy_loss | -7.26 | +| explained_variance | 0.248 | +| learning_rate | 4.85e-05 | +| loss | -0.0393 | +| n_updates | 28356 | +| policy_gradient_loss | -0.0226 | +| value_loss | 0.000152 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.391 | +| time/ | | +| fps | 1415 | +| iterations | 3136 | +| time_elapsed | 4538 | +| total_timesteps | 6422528 | +| train/ | | +| approx_kl | 0.0137608405 | +| clip_fraction | 0.358 | +| clip_range | 0.0734 | +| entropy_loss | -7.22 | +| explained_variance | -0.256 | +| learning_rate | 4.85e-05 | +| loss | -0.0408 | +| n_updates | 28360 | +| policy_gradient_loss | -0.0231 | +| value_loss | 8.39e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.391 | +| time/ | | +| fps | 1415 | +| iterations | 3137 | +| time_elapsed | 4540 | +| total_timesteps | 6424576 | +| train/ | | +| approx_kl | 0.011139249 | +| clip_fraction | 0.312 | +| clip_range | 0.0734 | +| entropy_loss | -7.33 | +| explained_variance | -0.109 | +| learning_rate | 4.85e-05 | +| loss | -0.0305 | +| n_updates | 28364 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000235 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.392 | +| time/ | | +| fps | 1415 | +| iterations | 3138 | +| time_elapsed | 4541 | +| total_timesteps | 6426624 | +| train/ | | +| approx_kl | 0.010695101 | +| clip_fraction | 0.314 | +| clip_range | 0.0734 | +| entropy_loss | -7.18 | +| explained_variance | 0.251 | +| learning_rate | 4.85e-05 | +| loss | -0.032 | +| n_updates | 28368 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000219 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.387 | +| time/ | | +| fps | 1415 | +| iterations | 3139 | +| time_elapsed | 4543 | +| total_timesteps | 6428672 | +| train/ | | +| approx_kl | 0.011036258 | +| clip_fraction | 0.32 | +| clip_range | 0.0734 | +| entropy_loss | -7.02 | +| explained_variance | 0.482 | +| learning_rate | 4.85e-05 | +| loss | -0.0362 | +| n_updates | 28372 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000142 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1415 | +| iterations | 3140 | +| time_elapsed | 4544 | +| total_timesteps | 6430720 | +| train/ | | +| approx_kl | 0.010760043 | +| clip_fraction | 0.338 | +| clip_range | 0.0734 | +| entropy_loss | -6.91 | +| explained_variance | 0.438 | +| learning_rate | 4.85e-05 | +| loss | -0.0298 | +| n_updates | 28376 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000179 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1415 | +| iterations | 3141 | +| time_elapsed | 4545 | +| total_timesteps | 6432768 | +| train/ | | +| approx_kl | 0.01391005 | +| clip_fraction | 0.351 | +| clip_range | 0.0734 | +| entropy_loss | -7.4 | +| explained_variance | -0.5 | +| learning_rate | 4.85e-05 | +| loss | -0.0382 | +| n_updates | 28380 | +| policy_gradient_loss | -0.0238 | +| value_loss | 6.51e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.388 | +| time/ | | +| fps | 1415 | +| iterations | 3142 | +| time_elapsed | 4547 | +| total_timesteps | 6434816 | +| train/ | | +| approx_kl | 0.009994923 | +| clip_fraction | 0.301 | +| clip_range | 0.0734 | +| entropy_loss | -6.6 | +| explained_variance | 0.49 | +| learning_rate | 4.85e-05 | +| loss | -0.0233 | +| n_updates | 28384 | +| policy_gradient_loss | -0.0137 | +| value_loss | 0.000216 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.387 | +| time/ | | +| fps | 1415 | +| iterations | 3143 | +| time_elapsed | 4548 | +| total_timesteps | 6436864 | +| train/ | | +| approx_kl | 0.012380874 | +| clip_fraction | 0.323 | +| clip_range | 0.0734 | +| entropy_loss | -6.58 | +| explained_variance | 0.386 | +| learning_rate | 4.85e-05 | +| loss | -0.0254 | +| n_updates | 28388 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000279 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.387 | +| time/ | | +| fps | 1415 | +| iterations | 3144 | +| time_elapsed | 4550 | +| total_timesteps | 6438912 | +| train/ | | +| approx_kl | 0.011867371 | +| clip_fraction | 0.302 | +| clip_range | 0.0734 | +| entropy_loss | -7 | +| explained_variance | 0.0354 | +| learning_rate | 4.85e-05 | +| loss | -0.031 | +| n_updates | 28392 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000266 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.387 | +| time/ | | +| fps | 1415 | +| iterations | 3145 | +| time_elapsed | 4551 | +| total_timesteps | 6440960 | +| train/ | | +| approx_kl | 0.010836275 | +| clip_fraction | 0.322 | +| clip_range | 0.0734 | +| entropy_loss | -7.45 | +| explained_variance | -0.17 | +| learning_rate | 4.85e-05 | +| loss | -0.032 | +| n_updates | 28396 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000172 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.388 | +| time/ | | +| fps | 1415 | +| iterations | 3146 | +| time_elapsed | 4553 | +| total_timesteps | 6443008 | +| train/ | | +| approx_kl | 0.009459617 | +| clip_fraction | 0.3 | +| clip_range | 0.0734 | +| entropy_loss | -7.43 | +| explained_variance | -0.0624 | +| learning_rate | 4.85e-05 | +| loss | -0.0286 | +| n_updates | 28400 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000177 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.393 | +| time/ | | +| fps | 1415 | +| iterations | 3147 | +| time_elapsed | 4554 | +| total_timesteps | 6445056 | +| train/ | | +| approx_kl | 0.009603832 | +| clip_fraction | 0.273 | +| clip_range | 0.0734 | +| entropy_loss | -7.21 | +| explained_variance | -0.0159 | +| learning_rate | 4.85e-05 | +| loss | -0.0253 | +| n_updates | 28404 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000379 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.388 | +| time/ | | +| fps | 1415 | +| iterations | 3148 | +| time_elapsed | 4555 | +| total_timesteps | 6447104 | +| train/ | | +| approx_kl | 0.010844933 | +| clip_fraction | 0.315 | +| clip_range | 0.0734 | +| entropy_loss | -6.95 | +| explained_variance | 0.268 | +| learning_rate | 4.85e-05 | +| loss | -0.0293 | +| n_updates | 28408 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000441 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.385 | +| time/ | | +| fps | 1415 | +| iterations | 3149 | +| time_elapsed | 4557 | +| total_timesteps | 6449152 | +| train/ | | +| approx_kl | 0.0109302495 | +| clip_fraction | 0.323 | +| clip_range | 0.0734 | +| entropy_loss | -6.8 | +| explained_variance | 0.237 | +| learning_rate | 4.85e-05 | +| loss | -0.0333 | +| n_updates | 28412 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000211 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.385 | +| time/ | | +| fps | 1415 | +| iterations | 3150 | +| time_elapsed | 4558 | +| total_timesteps | 6451200 | +| train/ | | +| approx_kl | 0.013762068 | +| clip_fraction | 0.35 | +| clip_range | 0.0734 | +| entropy_loss | -6.96 | +| explained_variance | 0.108 | +| learning_rate | 4.85e-05 | +| loss | -0.0375 | +| n_updates | 28416 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000218 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.385 | +| time/ | | +| fps | 1415 | +| iterations | 3151 | +| time_elapsed | 4560 | +| total_timesteps | 6453248 | +| train/ | | +| approx_kl | 0.012797646 | +| clip_fraction | 0.365 | +| clip_range | 0.0734 | +| entropy_loss | -7.34 | +| explained_variance | -0.241 | +| learning_rate | 4.85e-05 | +| loss | -0.0355 | +| n_updates | 28420 | +| policy_gradient_loss | -0.0245 | +| value_loss | 0.000113 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.386 | +| time/ | | +| fps | 1415 | +| iterations | 3152 | +| time_elapsed | 4561 | +| total_timesteps | 6455296 | +| train/ | | +| approx_kl | 0.0131916 | +| clip_fraction | 0.34 | +| clip_range | 0.0734 | +| entropy_loss | -7.37 | +| explained_variance | -0.176 | +| learning_rate | 4.85e-05 | +| loss | -0.0338 | +| n_updates | 28424 | +| policy_gradient_loss | -0.0222 | +| value_loss | 0.00015 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.39 | +| time/ | | +| fps | 1415 | +| iterations | 3153 | +| time_elapsed | 4563 | +| total_timesteps | 6457344 | +| train/ | | +| approx_kl | 0.010543866 | +| clip_fraction | 0.31 | +| clip_range | 0.0734 | +| entropy_loss | -7.16 | +| explained_variance | 0.174 | +| learning_rate | 4.85e-05 | +| loss | -0.0281 | +| n_updates | 28428 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000265 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.393 | +| time/ | | +| fps | 1415 | +| iterations | 3154 | +| time_elapsed | 4564 | +| total_timesteps | 6459392 | +| train/ | | +| approx_kl | 0.011213434 | +| clip_fraction | 0.328 | +| clip_range | 0.0734 | +| entropy_loss | -7.28 | +| explained_variance | -0.0896 | +| learning_rate | 4.85e-05 | +| loss | -0.0299 | +| n_updates | 28432 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000168 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.39 | +| time/ | | +| fps | 1415 | +| iterations | 3155 | +| time_elapsed | 4566 | +| total_timesteps | 6461440 | +| train/ | | +| approx_kl | 0.011720996 | +| clip_fraction | 0.311 | +| clip_range | 0.0734 | +| entropy_loss | -7.17 | +| explained_variance | 0.162 | +| learning_rate | 4.85e-05 | +| loss | -0.0276 | +| n_updates | 28436 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000254 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.393 | +| time/ | | +| fps | 1415 | +| iterations | 3156 | +| time_elapsed | 4567 | +| total_timesteps | 6463488 | +| train/ | | +| approx_kl | 0.011630388 | +| clip_fraction | 0.328 | +| clip_range | 0.0734 | +| entropy_loss | -6.88 | +| explained_variance | 0.516 | +| learning_rate | 4.85e-05 | +| loss | -0.0388 | +| n_updates | 28440 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.00011 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.387 | +| time/ | | +| fps | 1415 | +| iterations | 3157 | +| time_elapsed | 4569 | +| total_timesteps | 6465536 | +| train/ | | +| approx_kl | 0.01321453 | +| clip_fraction | 0.353 | +| clip_range | 0.0734 | +| entropy_loss | -6.96 | +| explained_variance | 0.263 | +| learning_rate | 4.85e-05 | +| loss | -0.0342 | +| n_updates | 28444 | +| policy_gradient_loss | -0.022 | +| value_loss | 0.000264 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.387 | +| time/ | | +| fps | 1415 | +| iterations | 3158 | +| time_elapsed | 4570 | +| total_timesteps | 6467584 | +| train/ | | +| approx_kl | 0.012271424 | +| clip_fraction | 0.334 | +| clip_range | 0.0734 | +| entropy_loss | -6.61 | +| explained_variance | 0.624 | +| learning_rate | 4.85e-05 | +| loss | -0.0307 | +| n_updates | 28448 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000123 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.385 | +| time/ | | +| fps | 1415 | +| iterations | 3159 | +| time_elapsed | 4571 | +| total_timesteps | 6469632 | +| train/ | | +| approx_kl | 0.012045896 | +| clip_fraction | 0.347 | +| clip_range | 0.0734 | +| entropy_loss | -7.13 | +| explained_variance | -0.332 | +| learning_rate | 4.85e-05 | +| loss | -0.043 | +| n_updates | 28452 | +| policy_gradient_loss | -0.0246 | +| value_loss | 8.19e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.389 | +| time/ | | +| fps | 1415 | +| iterations | 3160 | +| time_elapsed | 4573 | +| total_timesteps | 6471680 | +| train/ | | +| approx_kl | 0.012152227 | +| clip_fraction | 0.324 | +| clip_range | 0.0734 | +| entropy_loss | -7.15 | +| explained_variance | 0.373 | +| learning_rate | 4.85e-05 | +| loss | -0.0311 | +| n_updates | 28456 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000143 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.389 | +| time/ | | +| fps | 1415 | +| iterations | 3161 | +| time_elapsed | 4574 | +| total_timesteps | 6473728 | +| train/ | | +| approx_kl | 0.009650491 | +| clip_fraction | 0.299 | +| clip_range | 0.0734 | +| entropy_loss | -7.06 | +| explained_variance | 0.143 | +| learning_rate | 4.85e-05 | +| loss | -0.0298 | +| n_updates | 28460 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000448 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.388 | +| time/ | | +| fps | 1415 | +| iterations | 3162 | +| time_elapsed | 4576 | +| total_timesteps | 6475776 | +| train/ | | +| approx_kl | 0.010809445 | +| clip_fraction | 0.315 | +| clip_range | 0.0734 | +| entropy_loss | -7.22 | +| explained_variance | -0.0236 | +| learning_rate | 4.85e-05 | +| loss | -0.031 | +| n_updates | 28464 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000165 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.391 | +| time/ | | +| fps | 1415 | +| iterations | 3163 | +| time_elapsed | 4577 | +| total_timesteps | 6477824 | +| train/ | | +| approx_kl | 0.011919534 | +| clip_fraction | 0.301 | +| clip_range | 0.0734 | +| entropy_loss | -7.41 | +| explained_variance | -0.104 | +| learning_rate | 4.85e-05 | +| loss | -0.0329 | +| n_updates | 28468 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000144 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.388 | +| time/ | | +| fps | 1415 | +| iterations | 3164 | +| time_elapsed | 4578 | +| total_timesteps | 6479872 | +| train/ | | +| approx_kl | 0.011230372 | +| clip_fraction | 0.323 | +| clip_range | 0.0734 | +| entropy_loss | -7.12 | +| explained_variance | 0.144 | +| learning_rate | 4.85e-05 | +| loss | -0.0362 | +| n_updates | 28472 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.00018 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.385 | +| time/ | | +| fps | 1415 | +| iterations | 3165 | +| time_elapsed | 4580 | +| total_timesteps | 6481920 | +| train/ | | +| approx_kl | 0.010930835 | +| clip_fraction | 0.301 | +| clip_range | 0.0734 | +| entropy_loss | -7.16 | +| explained_variance | -0.0922 | +| learning_rate | 4.85e-05 | +| loss | -0.031 | +| n_updates | 28476 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000191 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1415 | +| iterations | 3166 | +| time_elapsed | 4581 | +| total_timesteps | 6483968 | +| train/ | | +| approx_kl | 0.0114677325 | +| clip_fraction | 0.302 | +| clip_range | 0.0734 | +| entropy_loss | -7.05 | +| explained_variance | 0.457 | +| learning_rate | 4.85e-05 | +| loss | -0.0349 | +| n_updates | 28480 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.00014 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.384 | +| time/ | | +| fps | 1415 | +| iterations | 3167 | +| time_elapsed | 4583 | +| total_timesteps | 6486016 | +| train/ | | +| approx_kl | 0.010200498 | +| clip_fraction | 0.311 | +| clip_range | 0.0734 | +| entropy_loss | -6.88 | +| explained_variance | 0.306 | +| learning_rate | 4.85e-05 | +| loss | -0.0258 | +| n_updates | 28484 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000174 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.384 | +| time/ | | +| fps | 1415 | +| iterations | 3168 | +| time_elapsed | 4584 | +| total_timesteps | 6488064 | +| train/ | | +| approx_kl | 0.011339419 | +| clip_fraction | 0.315 | +| clip_range | 0.0734 | +| entropy_loss | -6.84 | +| explained_variance | 0.214 | +| learning_rate | 4.85e-05 | +| loss | -0.0286 | +| n_updates | 28488 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000282 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.387 | +| time/ | | +| fps | 1415 | +| iterations | 3169 | +| time_elapsed | 4586 | +| total_timesteps | 6490112 | +| train/ | | +| approx_kl | 0.011140612 | +| clip_fraction | 0.312 | +| clip_range | 0.0734 | +| entropy_loss | -7.19 | +| explained_variance | 0.0919 | +| learning_rate | 4.85e-05 | +| loss | -0.0297 | +| n_updates | 28492 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000205 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.385 | +| time/ | | +| fps | 1415 | +| iterations | 3170 | +| time_elapsed | 4587 | +| total_timesteps | 6492160 | +| train/ | | +| approx_kl | 0.011779049 | +| clip_fraction | 0.323 | +| clip_range | 0.0734 | +| entropy_loss | -7.29 | +| explained_variance | 0.0777 | +| learning_rate | 4.85e-05 | +| loss | -0.0359 | +| n_updates | 28496 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000235 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.388 | +| time/ | | +| fps | 1415 | +| iterations | 3171 | +| time_elapsed | 4589 | +| total_timesteps | 6494208 | +| train/ | | +| approx_kl | 0.010887301 | +| clip_fraction | 0.32 | +| clip_range | 0.0734 | +| entropy_loss | -7.17 | +| explained_variance | 0.00438 | +| learning_rate | 4.85e-05 | +| loss | -0.0326 | +| n_updates | 28500 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000181 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.384 | +| time/ | | +| fps | 1415 | +| iterations | 3172 | +| time_elapsed | 4590 | +| total_timesteps | 6496256 | +| train/ | | +| approx_kl | 0.011633087 | +| clip_fraction | 0.311 | +| clip_range | 0.0734 | +| entropy_loss | -7.31 | +| explained_variance | 0.0221 | +| learning_rate | 4.85e-05 | +| loss | -0.033 | +| n_updates | 28504 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000218 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1415 | +| iterations | 3173 | +| time_elapsed | 4591 | +| total_timesteps | 6498304 | +| train/ | | +| approx_kl | 0.008545842 | +| clip_fraction | 0.269 | +| clip_range | 0.0734 | +| entropy_loss | -6.83 | +| explained_variance | 0.323 | +| learning_rate | 4.85e-05 | +| loss | -0.0236 | +| n_updates | 28508 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000325 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.387 | +| time/ | | +| fps | 1415 | +| iterations | 3174 | +| time_elapsed | 4593 | +| total_timesteps | 6500352 | +| train/ | | +| approx_kl | 0.009033752 | +| clip_fraction | 0.288 | +| clip_range | 0.0734 | +| entropy_loss | -7.28 | +| explained_variance | 0.0812 | +| learning_rate | 4.85e-05 | +| loss | -0.0286 | +| n_updates | 28512 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000358 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.392 | +| time/ | | +| fps | 1415 | +| iterations | 3175 | +| time_elapsed | 4594 | +| total_timesteps | 6502400 | +| train/ | | +| approx_kl | 0.013893485 | +| clip_fraction | 0.306 | +| clip_range | 0.0734 | +| entropy_loss | -6.66 | +| explained_variance | 0.256 | +| learning_rate | 4.85e-05 | +| loss | -0.0271 | +| n_updates | 28516 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.00027 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.392 | +| time/ | | +| fps | 1415 | +| iterations | 3176 | +| time_elapsed | 4596 | +| total_timesteps | 6504448 | +| train/ | | +| approx_kl | 0.01459151 | +| clip_fraction | 0.317 | +| clip_range | 0.0734 | +| entropy_loss | -6.92 | +| explained_variance | 0.159 | +| learning_rate | 4.85e-05 | +| loss | -0.034 | +| n_updates | 28520 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000309 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.387 | +| time/ | | +| fps | 1415 | +| iterations | 3177 | +| time_elapsed | 4597 | +| total_timesteps | 6506496 | +| train/ | | +| approx_kl | 0.0119786905 | +| clip_fraction | 0.313 | +| clip_range | 0.0734 | +| entropy_loss | -7.35 | +| explained_variance | 0.203 | +| learning_rate | 4.85e-05 | +| loss | -0.0356 | +| n_updates | 28524 | +| policy_gradient_loss | -0.0228 | +| value_loss | 0.000135 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1415 | +| iterations | 3178 | +| time_elapsed | 4599 | +| total_timesteps | 6508544 | +| train/ | | +| approx_kl | 0.011532731 | +| clip_fraction | 0.33 | +| clip_range | 0.0734 | +| entropy_loss | -7.18 | +| explained_variance | -0.0315 | +| learning_rate | 4.85e-05 | +| loss | -0.036 | +| n_updates | 28528 | +| policy_gradient_loss | -0.0221 | +| value_loss | 0.000131 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1415 | +| iterations | 3179 | +| time_elapsed | 4600 | +| total_timesteps | 6510592 | +| train/ | | +| approx_kl | 0.00953189 | +| clip_fraction | 0.32 | +| clip_range | 0.0734 | +| entropy_loss | -7.28 | +| explained_variance | -0.0761 | +| learning_rate | 4.85e-05 | +| loss | -0.0303 | +| n_updates | 28532 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000215 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.385 | +| time/ | | +| fps | 1415 | +| iterations | 3180 | +| time_elapsed | 4602 | +| total_timesteps | 6512640 | +| train/ | | +| approx_kl | 0.009609925 | +| clip_fraction | 0.305 | +| clip_range | 0.0734 | +| entropy_loss | -7.22 | +| explained_variance | 0.209 | +| learning_rate | 4.85e-05 | +| loss | -0.0307 | +| n_updates | 28536 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000174 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.388 | +| time/ | | +| fps | 1415 | +| iterations | 3181 | +| time_elapsed | 4603 | +| total_timesteps | 6514688 | +| train/ | | +| approx_kl | 0.011390269 | +| clip_fraction | 0.335 | +| clip_range | 0.0734 | +| entropy_loss | -7.35 | +| explained_variance | -0.592 | +| learning_rate | 4.85e-05 | +| loss | -0.0353 | +| n_updates | 28540 | +| policy_gradient_loss | -0.0213 | +| value_loss | 7.64e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1415 | +| iterations | 3182 | +| time_elapsed | 4604 | +| total_timesteps | 6516736 | +| train/ | | +| approx_kl | 0.0109203495 | +| clip_fraction | 0.286 | +| clip_range | 0.0734 | +| entropy_loss | -7 | +| explained_variance | 0.258 | +| learning_rate | 4.85e-05 | +| loss | -0.036 | +| n_updates | 28544 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000237 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1415 | +| iterations | 3183 | +| time_elapsed | 4606 | +| total_timesteps | 6518784 | +| train/ | | +| approx_kl | 0.010512494 | +| clip_fraction | 0.325 | +| clip_range | 0.0734 | +| entropy_loss | -6.78 | +| explained_variance | 0.393 | +| learning_rate | 4.85e-05 | +| loss | -0.0328 | +| n_updates | 28548 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000152 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1415 | +| iterations | 3184 | +| time_elapsed | 4607 | +| total_timesteps | 6520832 | +| train/ | | +| approx_kl | 0.0123049505 | +| clip_fraction | 0.339 | +| clip_range | 0.0734 | +| entropy_loss | -7.07 | +| explained_variance | 0.351 | +| learning_rate | 4.85e-05 | +| loss | -0.0346 | +| n_updates | 28552 | +| policy_gradient_loss | -0.022 | +| value_loss | 0.000136 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1415 | +| iterations | 3185 | +| time_elapsed | 4609 | +| total_timesteps | 6522880 | +| train/ | | +| approx_kl | 0.011520754 | +| clip_fraction | 0.318 | +| clip_range | 0.0734 | +| entropy_loss | -7.4 | +| explained_variance | -0.0969 | +| learning_rate | 4.85e-05 | +| loss | -0.0284 | +| n_updates | 28556 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000198 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1415 | +| iterations | 3186 | +| time_elapsed | 4610 | +| total_timesteps | 6524928 | +| train/ | | +| approx_kl | 0.0107006 | +| clip_fraction | 0.321 | +| clip_range | 0.0734 | +| entropy_loss | -7.21 | +| explained_variance | 0.379 | +| learning_rate | 4.85e-05 | +| loss | -0.0305 | +| n_updates | 28560 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000103 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1415 | +| iterations | 3187 | +| time_elapsed | 4611 | +| total_timesteps | 6526976 | +| train/ | | +| approx_kl | 0.009042026 | +| clip_fraction | 0.309 | +| clip_range | 0.0734 | +| entropy_loss | -6.84 | +| explained_variance | 0.526 | +| learning_rate | 4.85e-05 | +| loss | -0.0266 | +| n_updates | 28564 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000144 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1415 | +| iterations | 3188 | +| time_elapsed | 4613 | +| total_timesteps | 6529024 | +| train/ | | +| approx_kl | 0.0105887605 | +| clip_fraction | 0.342 | +| clip_range | 0.0734 | +| entropy_loss | -7.03 | +| explained_variance | 0.417 | +| learning_rate | 4.84e-05 | +| loss | -0.0339 | +| n_updates | 28568 | +| policy_gradient_loss | -0.0197 | +| value_loss | 9.53e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1415 | +| iterations | 3189 | +| time_elapsed | 4614 | +| total_timesteps | 6531072 | +| train/ | | +| approx_kl | 0.010698191 | +| clip_fraction | 0.311 | +| clip_range | 0.0734 | +| entropy_loss | -6.91 | +| explained_variance | 0.449 | +| learning_rate | 4.84e-05 | +| loss | -0.0273 | +| n_updates | 28572 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.00014 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1415 | +| iterations | 3190 | +| time_elapsed | 4616 | +| total_timesteps | 6533120 | +| train/ | | +| approx_kl | 0.014308479 | +| clip_fraction | 0.316 | +| clip_range | 0.0734 | +| entropy_loss | -7.12 | +| explained_variance | 0.178 | +| learning_rate | 4.84e-05 | +| loss | -0.0309 | +| n_updates | 28576 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.00028 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1415 | +| iterations | 3191 | +| time_elapsed | 4617 | +| total_timesteps | 6535168 | +| train/ | | +| approx_kl | 0.012427982 | +| clip_fraction | 0.366 | +| clip_range | 0.0734 | +| entropy_loss | -7.23 | +| explained_variance | 0.223 | +| learning_rate | 4.84e-05 | +| loss | -0.0391 | +| n_updates | 28580 | +| policy_gradient_loss | -0.0269 | +| value_loss | 7.21e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1415 | +| iterations | 3192 | +| time_elapsed | 4619 | +| total_timesteps | 6537216 | +| train/ | | +| approx_kl | 0.011115618 | +| clip_fraction | 0.32 | +| clip_range | 0.0734 | +| entropy_loss | -7.35 | +| explained_variance | 0.0303 | +| learning_rate | 4.84e-05 | +| loss | -0.031 | +| n_updates | 28584 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000224 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1415 | +| iterations | 3193 | +| time_elapsed | 4620 | +| total_timesteps | 6539264 | +| train/ | | +| approx_kl | 0.01036686 | +| clip_fraction | 0.334 | +| clip_range | 0.0734 | +| entropy_loss | -7.23 | +| explained_variance | -0.0663 | +| learning_rate | 4.84e-05 | +| loss | -0.0366 | +| n_updates | 28588 | +| policy_gradient_loss | -0.0214 | +| value_loss | 9.66e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1415 | +| iterations | 3194 | +| time_elapsed | 4621 | +| total_timesteps | 6541312 | +| train/ | | +| approx_kl | 0.012243327 | +| clip_fraction | 0.305 | +| clip_range | 0.0734 | +| entropy_loss | -7.31 | +| explained_variance | 0.0216 | +| learning_rate | 4.84e-05 | +| loss | -0.0307 | +| n_updates | 28592 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000156 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1415 | +| iterations | 3195 | +| time_elapsed | 4623 | +| total_timesteps | 6543360 | +| train/ | | +| approx_kl | 0.014609598 | +| clip_fraction | 0.317 | +| clip_range | 0.0734 | +| entropy_loss | -7.46 | +| explained_variance | -0.133 | +| learning_rate | 4.84e-05 | +| loss | -0.031 | +| n_updates | 28596 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.00011 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1415 | +| iterations | 3196 | +| time_elapsed | 4624 | +| total_timesteps | 6545408 | +| train/ | | +| approx_kl | 0.012356745 | +| clip_fraction | 0.316 | +| clip_range | 0.0734 | +| entropy_loss | -6.85 | +| explained_variance | 0.406 | +| learning_rate | 4.84e-05 | +| loss | -0.0288 | +| n_updates | 28600 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000222 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1415 | +| iterations | 3197 | +| time_elapsed | 4626 | +| total_timesteps | 6547456 | +| train/ | | +| approx_kl | 0.01318595 | +| clip_fraction | 0.327 | +| clip_range | 0.0734 | +| entropy_loss | -7.21 | +| explained_variance | 0.442 | +| learning_rate | 4.84e-05 | +| loss | -0.0326 | +| n_updates | 28604 | +| policy_gradient_loss | -0.0216 | +| value_loss | 8.01e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1415 | +| iterations | 3198 | +| time_elapsed | 4627 | +| total_timesteps | 6549504 | +| train/ | | +| approx_kl | 0.012252287 | +| clip_fraction | 0.323 | +| clip_range | 0.0734 | +| entropy_loss | -7.19 | +| explained_variance | 0.273 | +| learning_rate | 4.84e-05 | +| loss | -0.0327 | +| n_updates | 28608 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000126 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1415 | +| iterations | 3199 | +| time_elapsed | 4628 | +| total_timesteps | 6551552 | +| train/ | | +| approx_kl | 0.0105568 | +| clip_fraction | 0.321 | +| clip_range | 0.0734 | +| entropy_loss | -6.91 | +| explained_variance | 0.768 | +| learning_rate | 4.84e-05 | +| loss | -0.0298 | +| n_updates | 28612 | +| policy_gradient_loss | -0.0216 | +| value_loss | 5.93e-05 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1415 | +| iterations | 3200 | +| time_elapsed | 4630 | +| total_timesteps | 6553600 | +| train/ | | +| approx_kl | 0.013295184 | +| clip_fraction | 0.32 | +| clip_range | 0.0734 | +| entropy_loss | -6.87 | +| explained_variance | 0.595 | +| learning_rate | 4.84e-05 | +| loss | -0.0269 | +| n_updates | 28616 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1415 | +| iterations | 3201 | +| time_elapsed | 4631 | +| total_timesteps | 6555648 | +| train/ | | +| approx_kl | 0.009656086 | +| clip_fraction | 0.318 | +| clip_range | 0.0734 | +| entropy_loss | -7.02 | +| explained_variance | 0.326 | +| learning_rate | 4.84e-05 | +| loss | -0.0285 | +| n_updates | 28620 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000155 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1415 | +| iterations | 3202 | +| time_elapsed | 4633 | +| total_timesteps | 6557696 | +| train/ | | +| approx_kl | 0.010537108 | +| clip_fraction | 0.341 | +| clip_range | 0.0734 | +| entropy_loss | -6.96 | +| explained_variance | 0.471 | +| learning_rate | 4.84e-05 | +| loss | -0.0356 | +| n_updates | 28624 | +| policy_gradient_loss | -0.0213 | +| value_loss | 9.23e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1415 | +| iterations | 3203 | +| time_elapsed | 4634 | +| total_timesteps | 6559744 | +| train/ | | +| approx_kl | 0.011903697 | +| clip_fraction | 0.326 | +| clip_range | 0.0734 | +| entropy_loss | -7.35 | +| explained_variance | -0.00703 | +| learning_rate | 4.84e-05 | +| loss | -0.0296 | +| n_updates | 28628 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.00024 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1415 | +| iterations | 3204 | +| time_elapsed | 4636 | +| total_timesteps | 6561792 | +| train/ | | +| approx_kl | 0.013132088 | +| clip_fraction | 0.361 | +| clip_range | 0.0734 | +| entropy_loss | -7.34 | +| explained_variance | -0.263 | +| learning_rate | 4.84e-05 | +| loss | -0.0411 | +| n_updates | 28632 | +| policy_gradient_loss | -0.0261 | +| value_loss | 6.79e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1415 | +| iterations | 3205 | +| time_elapsed | 4637 | +| total_timesteps | 6563840 | +| train/ | | +| approx_kl | 0.009914489 | +| clip_fraction | 0.306 | +| clip_range | 0.0734 | +| entropy_loss | -7.18 | +| explained_variance | 0.188 | +| learning_rate | 4.84e-05 | +| loss | -0.0329 | +| n_updates | 28636 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000189 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1415 | +| iterations | 3206 | +| time_elapsed | 4639 | +| total_timesteps | 6565888 | +| train/ | | +| approx_kl | 0.0106542315 | +| clip_fraction | 0.333 | +| clip_range | 0.0734 | +| entropy_loss | -7 | +| explained_variance | 0.509 | +| learning_rate | 4.84e-05 | +| loss | -0.0394 | +| n_updates | 28640 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000103 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1415 | +| iterations | 3207 | +| time_elapsed | 4640 | +| total_timesteps | 6567936 | +| train/ | | +| approx_kl | 0.010394139 | +| clip_fraction | 0.303 | +| clip_range | 0.0734 | +| entropy_loss | -7.14 | +| explained_variance | 0.271 | +| learning_rate | 4.84e-05 | +| loss | -0.0306 | +| n_updates | 28644 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000184 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1415 | +| iterations | 3208 | +| time_elapsed | 4641 | +| total_timesteps | 6569984 | +| train/ | | +| approx_kl | 0.010298996 | +| clip_fraction | 0.311 | +| clip_range | 0.0734 | +| entropy_loss | -6.73 | +| explained_variance | 0.501 | +| learning_rate | 4.84e-05 | +| loss | -0.0303 | +| n_updates | 28648 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000155 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1415 | +| iterations | 3209 | +| time_elapsed | 4643 | +| total_timesteps | 6572032 | +| train/ | | +| approx_kl | 0.012783016 | +| clip_fraction | 0.318 | +| clip_range | 0.0734 | +| entropy_loss | -7.11 | +| explained_variance | 0.277 | +| learning_rate | 4.84e-05 | +| loss | -0.033 | +| n_updates | 28652 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000195 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1415 | +| iterations | 3210 | +| time_elapsed | 4644 | +| total_timesteps | 6574080 | +| train/ | | +| approx_kl | 0.012949742 | +| clip_fraction | 0.356 | +| clip_range | 0.0734 | +| entropy_loss | -6.87 | +| explained_variance | 0.769 | +| learning_rate | 4.84e-05 | +| loss | -0.0344 | +| n_updates | 28656 | +| policy_gradient_loss | -0.0245 | +| value_loss | 6.11e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1415 | +| iterations | 3211 | +| time_elapsed | 4646 | +| total_timesteps | 6576128 | +| train/ | | +| approx_kl | 0.010892831 | +| clip_fraction | 0.315 | +| clip_range | 0.0734 | +| entropy_loss | -7.4 | +| explained_variance | -0.0722 | +| learning_rate | 4.84e-05 | +| loss | -0.0309 | +| n_updates | 28660 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000112 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1415 | +| iterations | 3212 | +| time_elapsed | 4647 | +| total_timesteps | 6578176 | +| train/ | | +| approx_kl | 0.0124038365 | +| clip_fraction | 0.339 | +| clip_range | 0.0734 | +| entropy_loss | -7.01 | +| explained_variance | 0.401 | +| learning_rate | 4.84e-05 | +| loss | -0.0339 | +| n_updates | 28664 | +| policy_gradient_loss | -0.0215 | +| value_loss | 8.77e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1415 | +| iterations | 3213 | +| time_elapsed | 4649 | +| total_timesteps | 6580224 | +| train/ | | +| approx_kl | 0.010351914 | +| clip_fraction | 0.287 | +| clip_range | 0.0734 | +| entropy_loss | -6.65 | +| explained_variance | 0.435 | +| learning_rate | 4.84e-05 | +| loss | -0.0278 | +| n_updates | 28668 | +| policy_gradient_loss | -0.0146 | +| value_loss | 0.000257 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1415 | +| iterations | 3214 | +| time_elapsed | 4650 | +| total_timesteps | 6582272 | +| train/ | | +| approx_kl | 0.014016079 | +| clip_fraction | 0.327 | +| clip_range | 0.0734 | +| entropy_loss | -7.32 | +| explained_variance | -0.21 | +| learning_rate | 4.84e-05 | +| loss | -0.0329 | +| n_updates | 28672 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000103 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1415 | +| iterations | 3215 | +| time_elapsed | 4651 | +| total_timesteps | 6584320 | +| train/ | | +| approx_kl | 0.010616027 | +| clip_fraction | 0.32 | +| clip_range | 0.0734 | +| entropy_loss | -7.42 | +| explained_variance | -0.125 | +| learning_rate | 4.84e-05 | +| loss | -0.0413 | +| n_updates | 28676 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000165 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1415 | +| iterations | 3216 | +| time_elapsed | 4653 | +| total_timesteps | 6586368 | +| train/ | | +| approx_kl | 0.009525725 | +| clip_fraction | 0.303 | +| clip_range | 0.0734 | +| entropy_loss | -7.22 | +| explained_variance | 0.19 | +| learning_rate | 4.84e-05 | +| loss | -0.0304 | +| n_updates | 28680 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000145 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1415 | +| iterations | 3217 | +| time_elapsed | 4654 | +| total_timesteps | 6588416 | +| train/ | | +| approx_kl | 0.009072434 | +| clip_fraction | 0.3 | +| clip_range | 0.0734 | +| entropy_loss | -6.73 | +| explained_variance | 0.296 | +| learning_rate | 4.84e-05 | +| loss | -0.027 | +| n_updates | 28684 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.00039 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1415 | +| iterations | 3218 | +| time_elapsed | 4656 | +| total_timesteps | 6590464 | +| train/ | | +| approx_kl | 0.010059286 | +| clip_fraction | 0.319 | +| clip_range | 0.0734 | +| entropy_loss | -6.48 | +| explained_variance | 0.519 | +| learning_rate | 4.84e-05 | +| loss | -0.0301 | +| n_updates | 28688 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000292 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1415 | +| iterations | 3219 | +| time_elapsed | 4657 | +| total_timesteps | 6592512 | +| train/ | | +| approx_kl | 0.010717845 | +| clip_fraction | 0.334 | +| clip_range | 0.0734 | +| entropy_loss | -7.02 | +| explained_variance | 0.334 | +| learning_rate | 4.84e-05 | +| loss | -0.031 | +| n_updates | 28692 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000197 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1415 | +| iterations | 3220 | +| time_elapsed | 4659 | +| total_timesteps | 6594560 | +| train/ | | +| approx_kl | 0.013327047 | +| clip_fraction | 0.328 | +| clip_range | 0.0734 | +| entropy_loss | -7.45 | +| explained_variance | -0.159 | +| learning_rate | 4.84e-05 | +| loss | -0.0348 | +| n_updates | 28696 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000205 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1415 | +| iterations | 3221 | +| time_elapsed | 4660 | +| total_timesteps | 6596608 | +| train/ | | +| approx_kl | 0.012930384 | +| clip_fraction | 0.326 | +| clip_range | 0.0734 | +| entropy_loss | -7.26 | +| explained_variance | 0.174 | +| learning_rate | 4.84e-05 | +| loss | -0.0366 | +| n_updates | 28700 | +| policy_gradient_loss | -0.0223 | +| value_loss | 0.000163 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1415 | +| iterations | 3222 | +| time_elapsed | 4661 | +| total_timesteps | 6598656 | +| train/ | | +| approx_kl | 0.011984439 | +| clip_fraction | 0.355 | +| clip_range | 0.0734 | +| entropy_loss | -7 | +| explained_variance | 0.278 | +| learning_rate | 4.84e-05 | +| loss | -0.0368 | +| n_updates | 28704 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000156 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1415 | +| iterations | 3223 | +| time_elapsed | 4663 | +| total_timesteps | 6600704 | +| train/ | | +| approx_kl | 0.010500794 | +| clip_fraction | 0.31 | +| clip_range | 0.0734 | +| entropy_loss | -7.3 | +| explained_variance | 0.267 | +| learning_rate | 4.84e-05 | +| loss | -0.0351 | +| n_updates | 28708 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000132 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1415 | +| iterations | 3224 | +| time_elapsed | 4664 | +| total_timesteps | 6602752 | +| train/ | | +| approx_kl | 0.011170351 | +| clip_fraction | 0.325 | +| clip_range | 0.0733 | +| entropy_loss | -7.31 | +| explained_variance | 0.355 | +| learning_rate | 4.84e-05 | +| loss | -0.0355 | +| n_updates | 28712 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000113 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1415 | +| iterations | 3225 | +| time_elapsed | 4666 | +| total_timesteps | 6604800 | +| train/ | | +| approx_kl | 0.011371411 | +| clip_fraction | 0.313 | +| clip_range | 0.0733 | +| entropy_loss | -7.21 | +| explained_variance | -0.0131 | +| learning_rate | 4.84e-05 | +| loss | -0.0358 | +| n_updates | 28716 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000157 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1415 | +| iterations | 3226 | +| time_elapsed | 4667 | +| total_timesteps | 6606848 | +| train/ | | +| approx_kl | 0.011010577 | +| clip_fraction | 0.326 | +| clip_range | 0.0733 | +| entropy_loss | -7.25 | +| explained_variance | -0.0453 | +| learning_rate | 4.84e-05 | +| loss | -0.0315 | +| n_updates | 28720 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.00016 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1415 | +| iterations | 3227 | +| time_elapsed | 4669 | +| total_timesteps | 6608896 | +| train/ | | +| approx_kl | 0.011272267 | +| clip_fraction | 0.326 | +| clip_range | 0.0733 | +| entropy_loss | -6.92 | +| explained_variance | 0.297 | +| learning_rate | 4.84e-05 | +| loss | -0.0297 | +| n_updates | 28724 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000164 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1415 | +| iterations | 3228 | +| time_elapsed | 4670 | +| total_timesteps | 6610944 | +| train/ | | +| approx_kl | 0.009754203 | +| clip_fraction | 0.3 | +| clip_range | 0.0733 | +| entropy_loss | -6.84 | +| explained_variance | 0.363 | +| learning_rate | 4.84e-05 | +| loss | -0.0302 | +| n_updates | 28728 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000176 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1415 | +| iterations | 3229 | +| time_elapsed | 4671 | +| total_timesteps | 6612992 | +| train/ | | +| approx_kl | 0.012637761 | +| clip_fraction | 0.323 | +| clip_range | 0.0733 | +| entropy_loss | -7.1 | +| explained_variance | 0.0561 | +| learning_rate | 4.84e-05 | +| loss | -0.031 | +| n_updates | 28732 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000218 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1415 | +| iterations | 3230 | +| time_elapsed | 4673 | +| total_timesteps | 6615040 | +| train/ | | +| approx_kl | 0.012775468 | +| clip_fraction | 0.349 | +| clip_range | 0.0733 | +| entropy_loss | -6.99 | +| explained_variance | 0.321 | +| learning_rate | 4.84e-05 | +| loss | -0.0341 | +| n_updates | 28736 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000157 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1415 | +| iterations | 3231 | +| time_elapsed | 4674 | +| total_timesteps | 6617088 | +| train/ | | +| approx_kl | 0.0128131285 | +| clip_fraction | 0.343 | +| clip_range | 0.0733 | +| entropy_loss | -7.17 | +| explained_variance | -0.00584 | +| learning_rate | 4.84e-05 | +| loss | -0.0354 | +| n_updates | 28740 | +| policy_gradient_loss | -0.0222 | +| value_loss | 0.000124 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1415 | +| iterations | 3232 | +| time_elapsed | 4676 | +| total_timesteps | 6619136 | +| train/ | | +| approx_kl | 0.01100437 | +| clip_fraction | 0.307 | +| clip_range | 0.0733 | +| entropy_loss | -7.07 | +| explained_variance | 0.333 | +| learning_rate | 4.84e-05 | +| loss | -0.0316 | +| n_updates | 28744 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.00025 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1415 | +| iterations | 3233 | +| time_elapsed | 4677 | +| total_timesteps | 6621184 | +| train/ | | +| approx_kl | 0.013758085 | +| clip_fraction | 0.342 | +| clip_range | 0.0733 | +| entropy_loss | -7.1 | +| explained_variance | 0.547 | +| learning_rate | 4.84e-05 | +| loss | -0.0357 | +| n_updates | 28748 | +| policy_gradient_loss | -0.0229 | +| value_loss | 0.000105 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1415 | +| iterations | 3234 | +| time_elapsed | 4678 | +| total_timesteps | 6623232 | +| train/ | | +| approx_kl | 0.009652015 | +| clip_fraction | 0.312 | +| clip_range | 0.0733 | +| entropy_loss | -7.25 | +| explained_variance | 0.0555 | +| learning_rate | 4.84e-05 | +| loss | -0.0338 | +| n_updates | 28752 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.00021 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1415 | +| iterations | 3235 | +| time_elapsed | 4680 | +| total_timesteps | 6625280 | +| train/ | | +| approx_kl | 0.010669592 | +| clip_fraction | 0.344 | +| clip_range | 0.0733 | +| entropy_loss | -7.25 | +| explained_variance | 0.326 | +| learning_rate | 4.84e-05 | +| loss | -0.0403 | +| n_updates | 28756 | +| policy_gradient_loss | -0.0225 | +| value_loss | 0.000113 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1415 | +| iterations | 3236 | +| time_elapsed | 4681 | +| total_timesteps | 6627328 | +| train/ | | +| approx_kl | 0.009043334 | +| clip_fraction | 0.303 | +| clip_range | 0.0733 | +| entropy_loss | -7.19 | +| explained_variance | 0.166 | +| learning_rate | 4.84e-05 | +| loss | -0.0328 | +| n_updates | 28760 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000209 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1415 | +| iterations | 3237 | +| time_elapsed | 4683 | +| total_timesteps | 6629376 | +| train/ | | +| approx_kl | 0.00922583 | +| clip_fraction | 0.289 | +| clip_range | 0.0733 | +| entropy_loss | -7.17 | +| explained_variance | 0.11 | +| learning_rate | 4.84e-05 | +| loss | -0.0261 | +| n_updates | 28764 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000266 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1415 | +| iterations | 3238 | +| time_elapsed | 4684 | +| total_timesteps | 6631424 | +| train/ | | +| approx_kl | 0.011681532 | +| clip_fraction | 0.293 | +| clip_range | 0.0733 | +| entropy_loss | -7.01 | +| explained_variance | 0.387 | +| learning_rate | 4.84e-05 | +| loss | -0.0361 | +| n_updates | 28768 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000213 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1415 | +| iterations | 3239 | +| time_elapsed | 4686 | +| total_timesteps | 6633472 | +| train/ | | +| approx_kl | 0.013468622 | +| clip_fraction | 0.335 | +| clip_range | 0.0733 | +| entropy_loss | -6.46 | +| explained_variance | 0.622 | +| learning_rate | 4.84e-05 | +| loss | -0.0306 | +| n_updates | 28772 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000143 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1415 | +| iterations | 3240 | +| time_elapsed | 4687 | +| total_timesteps | 6635520 | +| train/ | | +| approx_kl | 0.011860838 | +| clip_fraction | 0.318 | +| clip_range | 0.0733 | +| entropy_loss | -7.21 | +| explained_variance | -0.0775 | +| learning_rate | 4.84e-05 | +| loss | -0.0315 | +| n_updates | 28776 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000131 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1415 | +| iterations | 3241 | +| time_elapsed | 4688 | +| total_timesteps | 6637568 | +| train/ | | +| approx_kl | 0.011824395 | +| clip_fraction | 0.335 | +| clip_range | 0.0733 | +| entropy_loss | -7.03 | +| explained_variance | 0.496 | +| learning_rate | 4.84e-05 | +| loss | -0.0314 | +| n_updates | 28780 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000115 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1415 | +| iterations | 3242 | +| time_elapsed | 4690 | +| total_timesteps | 6639616 | +| train/ | | +| approx_kl | 0.011993319 | +| clip_fraction | 0.327 | +| clip_range | 0.0733 | +| entropy_loss | -7.22 | +| explained_variance | -0.0621 | +| learning_rate | 4.84e-05 | +| loss | -0.0322 | +| n_updates | 28784 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000166 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1415 | +| iterations | 3243 | +| time_elapsed | 4691 | +| total_timesteps | 6641664 | +| train/ | | +| approx_kl | 0.010448192 | +| clip_fraction | 0.299 | +| clip_range | 0.0733 | +| entropy_loss | -6.71 | +| explained_variance | 0.596 | +| learning_rate | 4.84e-05 | +| loss | -0.0275 | +| n_updates | 28788 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000162 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1415 | +| iterations | 3244 | +| time_elapsed | 4693 | +| total_timesteps | 6643712 | +| train/ | | +| approx_kl | 0.0112717 | +| clip_fraction | 0.352 | +| clip_range | 0.0733 | +| entropy_loss | -7.24 | +| explained_variance | 0.292 | +| learning_rate | 4.84e-05 | +| loss | -0.0371 | +| n_updates | 28792 | +| policy_gradient_loss | -0.0239 | +| value_loss | 9.15e-05 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1415 | +| iterations | 3245 | +| time_elapsed | 4694 | +| total_timesteps | 6645760 | +| train/ | | +| approx_kl | 0.012321996 | +| clip_fraction | 0.342 | +| clip_range | 0.0733 | +| entropy_loss | -7.36 | +| explained_variance | -0.0707 | +| learning_rate | 4.84e-05 | +| loss | -0.0381 | +| n_updates | 28796 | +| policy_gradient_loss | -0.0227 | +| value_loss | 8.75e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1415 | +| iterations | 3246 | +| time_elapsed | 4696 | +| total_timesteps | 6647808 | +| train/ | | +| approx_kl | 0.012105372 | +| clip_fraction | 0.286 | +| clip_range | 0.0733 | +| entropy_loss | -6.88 | +| explained_variance | 0.386 | +| learning_rate | 4.84e-05 | +| loss | -0.0283 | +| n_updates | 28800 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000193 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1415 | +| iterations | 3247 | +| time_elapsed | 4697 | +| total_timesteps | 6649856 | +| train/ | | +| approx_kl | 0.01285521 | +| clip_fraction | 0.309 | +| clip_range | 0.0733 | +| entropy_loss | -7.18 | +| explained_variance | -0.0238 | +| learning_rate | 4.84e-05 | +| loss | -0.0292 | +| n_updates | 28804 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.00014 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1415 | +| iterations | 3248 | +| time_elapsed | 4698 | +| total_timesteps | 6651904 | +| train/ | | +| approx_kl | 0.008622931 | +| clip_fraction | 0.282 | +| clip_range | 0.0733 | +| entropy_loss | -6.73 | +| explained_variance | 0.612 | +| learning_rate | 4.84e-05 | +| loss | -0.0304 | +| n_updates | 28808 | +| policy_gradient_loss | -0.0174 | +| value_loss | 9.39e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1415 | +| iterations | 3249 | +| time_elapsed | 4700 | +| total_timesteps | 6653952 | +| train/ | | +| approx_kl | 0.011608395 | +| clip_fraction | 0.324 | +| clip_range | 0.0733 | +| entropy_loss | -7 | +| explained_variance | 0.395 | +| learning_rate | 4.84e-05 | +| loss | -0.0327 | +| n_updates | 28812 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000202 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1415 | +| iterations | 3250 | +| time_elapsed | 4701 | +| total_timesteps | 6656000 | +| train/ | | +| approx_kl | 0.008263916 | +| clip_fraction | 0.295 | +| clip_range | 0.0733 | +| entropy_loss | -6.9 | +| explained_variance | 0.373 | +| learning_rate | 4.84e-05 | +| loss | -0.0282 | +| n_updates | 28816 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000247 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1415 | +| iterations | 3251 | +| time_elapsed | 4703 | +| total_timesteps | 6658048 | +| train/ | | +| approx_kl | 0.01026421 | +| clip_fraction | 0.302 | +| clip_range | 0.0733 | +| entropy_loss | -7.02 | +| explained_variance | 0.424 | +| learning_rate | 4.84e-05 | +| loss | -0.0289 | +| n_updates | 28820 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000203 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1415 | +| iterations | 3252 | +| time_elapsed | 4704 | +| total_timesteps | 6660096 | +| train/ | | +| approx_kl | 0.009781929 | +| clip_fraction | 0.317 | +| clip_range | 0.0733 | +| entropy_loss | -7.22 | +| explained_variance | 0.0342 | +| learning_rate | 4.84e-05 | +| loss | -0.0256 | +| n_updates | 28824 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000286 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1415 | +| iterations | 3253 | +| time_elapsed | 4706 | +| total_timesteps | 6662144 | +| train/ | | +| approx_kl | 0.012424441 | +| clip_fraction | 0.336 | +| clip_range | 0.0733 | +| entropy_loss | -7.1 | +| explained_variance | 0.315 | +| learning_rate | 4.84e-05 | +| loss | -0.0329 | +| n_updates | 28828 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000155 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1415 | +| iterations | 3254 | +| time_elapsed | 4707 | +| total_timesteps | 6664192 | +| train/ | | +| approx_kl | 0.010003721 | +| clip_fraction | 0.321 | +| clip_range | 0.0733 | +| entropy_loss | -7.26 | +| explained_variance | -0.00241 | +| learning_rate | 4.84e-05 | +| loss | -0.0318 | +| n_updates | 28832 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000145 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1415 | +| iterations | 3255 | +| time_elapsed | 4708 | +| total_timesteps | 6666240 | +| train/ | | +| approx_kl | 0.010876028 | +| clip_fraction | 0.317 | +| clip_range | 0.0733 | +| entropy_loss | -6.6 | +| explained_variance | 0.265 | +| learning_rate | 4.84e-05 | +| loss | -0.0282 | +| n_updates | 28836 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.00037 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1415 | +| iterations | 3256 | +| time_elapsed | 4710 | +| total_timesteps | 6668288 | +| train/ | | +| approx_kl | 0.011771627 | +| clip_fraction | 0.344 | +| clip_range | 0.0733 | +| entropy_loss | -7.07 | +| explained_variance | 0.268 | +| learning_rate | 4.84e-05 | +| loss | -0.036 | +| n_updates | 28840 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000171 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1415 | +| iterations | 3257 | +| time_elapsed | 4711 | +| total_timesteps | 6670336 | +| train/ | | +| approx_kl | 0.007259689 | +| clip_fraction | 0.275 | +| clip_range | 0.0733 | +| entropy_loss | -7.01 | +| explained_variance | 0.334 | +| learning_rate | 4.84e-05 | +| loss | -0.0274 | +| n_updates | 28844 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000289 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1415 | +| iterations | 3258 | +| time_elapsed | 4713 | +| total_timesteps | 6672384 | +| train/ | | +| approx_kl | 0.008694619 | +| clip_fraction | 0.296 | +| clip_range | 0.0733 | +| entropy_loss | -6.87 | +| explained_variance | 0.417 | +| learning_rate | 4.84e-05 | +| loss | -0.0342 | +| n_updates | 28848 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000231 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1415 | +| iterations | 3259 | +| time_elapsed | 4714 | +| total_timesteps | 6674432 | +| train/ | | +| approx_kl | 0.01098954 | +| clip_fraction | 0.32 | +| clip_range | 0.0733 | +| entropy_loss | -6.79 | +| explained_variance | 0.172 | +| learning_rate | 4.84e-05 | +| loss | -0.027 | +| n_updates | 28852 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000493 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1415 | +| iterations | 3260 | +| time_elapsed | 4716 | +| total_timesteps | 6676480 | +| train/ | | +| approx_kl | 0.012861095 | +| clip_fraction | 0.342 | +| clip_range | 0.0733 | +| entropy_loss | -7.04 | +| explained_variance | 0.244 | +| learning_rate | 4.84e-05 | +| loss | -0.0335 | +| n_updates | 28856 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000239 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1415 | +| iterations | 3261 | +| time_elapsed | 4717 | +| total_timesteps | 6678528 | +| train/ | | +| approx_kl | 0.012885911 | +| clip_fraction | 0.342 | +| clip_range | 0.0733 | +| entropy_loss | -7.04 | +| explained_variance | 0.27 | +| learning_rate | 4.84e-05 | +| loss | -0.0295 | +| n_updates | 28860 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000284 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1415 | +| iterations | 3262 | +| time_elapsed | 4718 | +| total_timesteps | 6680576 | +| train/ | | +| approx_kl | 0.01169113 | +| clip_fraction | 0.361 | +| clip_range | 0.0733 | +| entropy_loss | -7.17 | +| explained_variance | 0.00963 | +| learning_rate | 4.84e-05 | +| loss | -0.0383 | +| n_updates | 28864 | +| policy_gradient_loss | -0.0224 | +| value_loss | 0.000187 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1415 | +| iterations | 3263 | +| time_elapsed | 4720 | +| total_timesteps | 6682624 | +| train/ | | +| approx_kl | 0.012066973 | +| clip_fraction | 0.324 | +| clip_range | 0.0733 | +| entropy_loss | -7.32 | +| explained_variance | -0.294 | +| learning_rate | 4.84e-05 | +| loss | -0.0366 | +| n_updates | 28868 | +| policy_gradient_loss | -0.0225 | +| value_loss | 0.000148 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1415 | +| iterations | 3264 | +| time_elapsed | 4721 | +| total_timesteps | 6684672 | +| train/ | | +| approx_kl | 0.011017021 | +| clip_fraction | 0.356 | +| clip_range | 0.0733 | +| entropy_loss | -7.2 | +| explained_variance | -0.805 | +| learning_rate | 4.84e-05 | +| loss | -0.0415 | +| n_updates | 28872 | +| policy_gradient_loss | -0.0232 | +| value_loss | 7.47e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1415 | +| iterations | 3265 | +| time_elapsed | 4723 | +| total_timesteps | 6686720 | +| train/ | | +| approx_kl | 0.012937601 | +| clip_fraction | 0.323 | +| clip_range | 0.0733 | +| entropy_loss | -7.16 | +| explained_variance | 0.076 | +| learning_rate | 4.84e-05 | +| loss | -0.0329 | +| n_updates | 28876 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000261 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1415 | +| iterations | 3266 | +| time_elapsed | 4724 | +| total_timesteps | 6688768 | +| train/ | | +| approx_kl | 0.012421006 | +| clip_fraction | 0.337 | +| clip_range | 0.0733 | +| entropy_loss | -7.19 | +| explained_variance | 0.24 | +| learning_rate | 4.84e-05 | +| loss | -0.0375 | +| n_updates | 28880 | +| policy_gradient_loss | -0.0234 | +| value_loss | 0.000124 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1415 | +| iterations | 3267 | +| time_elapsed | 4726 | +| total_timesteps | 6690816 | +| train/ | | +| approx_kl | 0.011628484 | +| clip_fraction | 0.328 | +| clip_range | 0.0733 | +| entropy_loss | -7.34 | +| explained_variance | -0.155 | +| learning_rate | 4.84e-05 | +| loss | -0.034 | +| n_updates | 28884 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000111 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1415 | +| iterations | 3268 | +| time_elapsed | 4727 | +| total_timesteps | 6692864 | +| train/ | | +| approx_kl | 0.011592863 | +| clip_fraction | 0.326 | +| clip_range | 0.0733 | +| entropy_loss | -7.06 | +| explained_variance | 0.592 | +| learning_rate | 4.84e-05 | +| loss | -0.0327 | +| n_updates | 28888 | +| policy_gradient_loss | -0.0215 | +| value_loss | 7.36e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1415 | +| iterations | 3269 | +| time_elapsed | 4728 | +| total_timesteps | 6694912 | +| train/ | | +| approx_kl | 0.009968698 | +| clip_fraction | 0.328 | +| clip_range | 0.0733 | +| entropy_loss | -6.85 | +| explained_variance | 0.353 | +| learning_rate | 4.84e-05 | +| loss | -0.03 | +| n_updates | 28892 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000241 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1415 | +| iterations | 3270 | +| time_elapsed | 4730 | +| total_timesteps | 6696960 | +| train/ | | +| approx_kl | 0.01238041 | +| clip_fraction | 0.356 | +| clip_range | 0.0733 | +| entropy_loss | -6.95 | +| explained_variance | 0.612 | +| learning_rate | 4.84e-05 | +| loss | -0.0354 | +| n_updates | 28896 | +| policy_gradient_loss | -0.0212 | +| value_loss | 8.38e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1415 | +| iterations | 3271 | +| time_elapsed | 4731 | +| total_timesteps | 6699008 | +| train/ | | +| approx_kl | 0.010183768 | +| clip_fraction | 0.332 | +| clip_range | 0.0733 | +| entropy_loss | -7.37 | +| explained_variance | -0.158 | +| learning_rate | 4.84e-05 | +| loss | -0.0325 | +| n_updates | 28900 | +| policy_gradient_loss | -0.0207 | +| value_loss | 8.8e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1415 | +| iterations | 3272 | +| time_elapsed | 4733 | +| total_timesteps | 6701056 | +| train/ | | +| approx_kl | 0.011578403 | +| clip_fraction | 0.312 | +| clip_range | 0.0733 | +| entropy_loss | -6.8 | +| explained_variance | 0.633 | +| learning_rate | 4.84e-05 | +| loss | -0.0297 | +| n_updates | 28904 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000117 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1415 | +| iterations | 3273 | +| time_elapsed | 4734 | +| total_timesteps | 6703104 | +| train/ | | +| approx_kl | 0.0104884375 | +| clip_fraction | 0.327 | +| clip_range | 0.0733 | +| entropy_loss | -7.1 | +| explained_variance | 0.296 | +| learning_rate | 4.84e-05 | +| loss | -0.0322 | +| n_updates | 28908 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000133 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1415 | +| iterations | 3274 | +| time_elapsed | 4736 | +| total_timesteps | 6705152 | +| train/ | | +| approx_kl | 0.012120578 | +| clip_fraction | 0.296 | +| clip_range | 0.0733 | +| entropy_loss | -7.16 | +| explained_variance | 0.352 | +| learning_rate | 4.84e-05 | +| loss | -0.0311 | +| n_updates | 28912 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000146 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1415 | +| iterations | 3275 | +| time_elapsed | 4737 | +| total_timesteps | 6707200 | +| train/ | | +| approx_kl | 0.012231171 | +| clip_fraction | 0.344 | +| clip_range | 0.0733 | +| entropy_loss | -7.4 | +| explained_variance | -0.0822 | +| learning_rate | 4.84e-05 | +| loss | -0.0345 | +| n_updates | 28916 | +| policy_gradient_loss | -0.0222 | +| value_loss | 9.32e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1415 | +| iterations | 3276 | +| time_elapsed | 4739 | +| total_timesteps | 6709248 | +| train/ | | +| approx_kl | 0.009289442 | +| clip_fraction | 0.289 | +| clip_range | 0.0733 | +| entropy_loss | -6.66 | +| explained_variance | 0.496 | +| learning_rate | 4.84e-05 | +| loss | -0.0229 | +| n_updates | 28920 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.000172 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.384 | +| time/ | | +| fps | 1415 | +| iterations | 3277 | +| time_elapsed | 4740 | +| total_timesteps | 6711296 | +| train/ | | +| approx_kl | 0.012659771 | +| clip_fraction | 0.32 | +| clip_range | 0.0733 | +| entropy_loss | -7.27 | +| explained_variance | 0.285 | +| learning_rate | 4.84e-05 | +| loss | -0.0305 | +| n_updates | 28924 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.00011 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.388 | +| time/ | | +| fps | 1415 | +| iterations | 3278 | +| time_elapsed | 4741 | +| total_timesteps | 6713344 | +| train/ | | +| approx_kl | 0.012312008 | +| clip_fraction | 0.318 | +| clip_range | 0.0733 | +| entropy_loss | -7.22 | +| explained_variance | -0.0468 | +| learning_rate | 4.84e-05 | +| loss | -0.0382 | +| n_updates | 28928 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000188 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.39 | +| time/ | | +| fps | 1415 | +| iterations | 3279 | +| time_elapsed | 4743 | +| total_timesteps | 6715392 | +| train/ | | +| approx_kl | 0.011586154 | +| clip_fraction | 0.31 | +| clip_range | 0.0733 | +| entropy_loss | -7.21 | +| explained_variance | -0.0389 | +| learning_rate | 4.84e-05 | +| loss | -0.0314 | +| n_updates | 28932 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000306 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.387 | +| time/ | | +| fps | 1415 | +| iterations | 3280 | +| time_elapsed | 4744 | +| total_timesteps | 6717440 | +| train/ | | +| approx_kl | 0.009721573 | +| clip_fraction | 0.307 | +| clip_range | 0.0733 | +| entropy_loss | -6.92 | +| explained_variance | 0.381 | +| learning_rate | 4.84e-05 | +| loss | -0.0271 | +| n_updates | 28936 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.00025 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1415 | +| iterations | 3281 | +| time_elapsed | 4746 | +| total_timesteps | 6719488 | +| train/ | | +| approx_kl | 0.009757092 | +| clip_fraction | 0.313 | +| clip_range | 0.0733 | +| entropy_loss | -6.72 | +| explained_variance | 0.585 | +| learning_rate | 4.84e-05 | +| loss | -0.0292 | +| n_updates | 28940 | +| policy_gradient_loss | -0.0202 | +| value_loss | 9.97e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1415 | +| iterations | 3282 | +| time_elapsed | 4747 | +| total_timesteps | 6721536 | +| train/ | | +| approx_kl | 0.011739804 | +| clip_fraction | 0.325 | +| clip_range | 0.0733 | +| entropy_loss | -7.15 | +| explained_variance | 0.21 | +| learning_rate | 4.84e-05 | +| loss | -0.031 | +| n_updates | 28944 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.00015 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1415 | +| iterations | 3283 | +| time_elapsed | 4749 | +| total_timesteps | 6723584 | +| train/ | | +| approx_kl | 0.012788595 | +| clip_fraction | 0.323 | +| clip_range | 0.0733 | +| entropy_loss | -6.87 | +| explained_variance | 0.607 | +| learning_rate | 4.84e-05 | +| loss | -0.0301 | +| n_updates | 28948 | +| policy_gradient_loss | -0.0192 | +| value_loss | 9.39e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1415 | +| iterations | 3284 | +| time_elapsed | 4750 | +| total_timesteps | 6725632 | +| train/ | | +| approx_kl | 0.0120258285 | +| clip_fraction | 0.337 | +| clip_range | 0.0733 | +| entropy_loss | -7.31 | +| explained_variance | 0.272 | +| learning_rate | 4.84e-05 | +| loss | -0.0442 | +| n_updates | 28952 | +| policy_gradient_loss | -0.0225 | +| value_loss | 5.8e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1415 | +| iterations | 3285 | +| time_elapsed | 4752 | +| total_timesteps | 6727680 | +| train/ | | +| approx_kl | 0.010950948 | +| clip_fraction | 0.319 | +| clip_range | 0.0733 | +| entropy_loss | -7.31 | +| explained_variance | 0.145 | +| learning_rate | 4.84e-05 | +| loss | -0.0285 | +| n_updates | 28956 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000111 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1415 | +| iterations | 3286 | +| time_elapsed | 4753 | +| total_timesteps | 6729728 | +| train/ | | +| approx_kl | 0.011480227 | +| clip_fraction | 0.313 | +| clip_range | 0.0733 | +| entropy_loss | -7.13 | +| explained_variance | 0.145 | +| learning_rate | 4.84e-05 | +| loss | -0.0306 | +| n_updates | 28960 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000203 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1415 | +| iterations | 3287 | +| time_elapsed | 4754 | +| total_timesteps | 6731776 | +| train/ | | +| approx_kl | 0.011013687 | +| clip_fraction | 0.305 | +| clip_range | 0.0733 | +| entropy_loss | -7.13 | +| explained_variance | 0.424 | +| learning_rate | 4.84e-05 | +| loss | -0.0353 | +| n_updates | 28964 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000123 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1415 | +| iterations | 3288 | +| time_elapsed | 4756 | +| total_timesteps | 6733824 | +| train/ | | +| approx_kl | 0.011301648 | +| clip_fraction | 0.305 | +| clip_range | 0.0733 | +| entropy_loss | -7.09 | +| explained_variance | 0.595 | +| learning_rate | 4.84e-05 | +| loss | -0.0324 | +| n_updates | 28968 | +| policy_gradient_loss | -0.0204 | +| value_loss | 9.68e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1415 | +| iterations | 3289 | +| time_elapsed | 4757 | +| total_timesteps | 6735872 | +| train/ | | +| approx_kl | 0.009746803 | +| clip_fraction | 0.331 | +| clip_range | 0.0733 | +| entropy_loss | -7.16 | +| explained_variance | -0.0575 | +| learning_rate | 4.84e-05 | +| loss | -0.0262 | +| n_updates | 28972 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000109 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1415 | +| iterations | 3290 | +| time_elapsed | 4759 | +| total_timesteps | 6737920 | +| train/ | | +| approx_kl | 0.010027878 | +| clip_fraction | 0.301 | +| clip_range | 0.0733 | +| entropy_loss | -6.59 | +| explained_variance | 0.631 | +| learning_rate | 4.84e-05 | +| loss | -0.0235 | +| n_updates | 28976 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000166 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1415 | +| iterations | 3291 | +| time_elapsed | 4760 | +| total_timesteps | 6739968 | +| train/ | | +| approx_kl | 0.011163278 | +| clip_fraction | 0.335 | +| clip_range | 0.0733 | +| entropy_loss | -7.22 | +| explained_variance | 0.0391 | +| learning_rate | 4.84e-05 | +| loss | -0.0248 | +| n_updates | 28980 | +| policy_gradient_loss | -0.0206 | +| value_loss | 9.38e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1415 | +| iterations | 3292 | +| time_elapsed | 4762 | +| total_timesteps | 6742016 | +| train/ | | +| approx_kl | 0.012005917 | +| clip_fraction | 0.313 | +| clip_range | 0.0733 | +| entropy_loss | -7.39 | +| explained_variance | -0.0984 | +| learning_rate | 4.84e-05 | +| loss | -0.037 | +| n_updates | 28984 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000106 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1415 | +| iterations | 3293 | +| time_elapsed | 4763 | +| total_timesteps | 6744064 | +| train/ | | +| approx_kl | 0.0128242895 | +| clip_fraction | 0.306 | +| clip_range | 0.0733 | +| entropy_loss | -7.43 | +| explained_variance | -0.162 | +| learning_rate | 4.84e-05 | +| loss | -0.0332 | +| n_updates | 28988 | +| policy_gradient_loss | -0.0194 | +| value_loss | 9.36e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1415 | +| iterations | 3294 | +| time_elapsed | 4764 | +| total_timesteps | 6746112 | +| train/ | | +| approx_kl | 0.012797957 | +| clip_fraction | 0.319 | +| clip_range | 0.0733 | +| entropy_loss | -7.08 | +| explained_variance | 0.293 | +| learning_rate | 4.84e-05 | +| loss | -0.0296 | +| n_updates | 28992 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000126 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1415 | +| iterations | 3295 | +| time_elapsed | 4766 | +| total_timesteps | 6748160 | +| train/ | | +| approx_kl | 0.011851757 | +| clip_fraction | 0.313 | +| clip_range | 0.0733 | +| entropy_loss | -7.18 | +| explained_variance | 0.395 | +| learning_rate | 4.84e-05 | +| loss | -0.0341 | +| n_updates | 28996 | +| policy_gradient_loss | -0.0199 | +| value_loss | 9.15e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1415 | +| iterations | 3296 | +| time_elapsed | 4767 | +| total_timesteps | 6750208 | +| train/ | | +| approx_kl | 0.012944087 | +| clip_fraction | 0.329 | +| clip_range | 0.0733 | +| entropy_loss | -6.63 | +| explained_variance | 0.454 | +| learning_rate | 4.84e-05 | +| loss | -0.03 | +| n_updates | 29000 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000241 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1415 | +| iterations | 3297 | +| time_elapsed | 4769 | +| total_timesteps | 6752256 | +| train/ | | +| approx_kl | 0.013180964 | +| clip_fraction | 0.334 | +| clip_range | 0.0733 | +| entropy_loss | -7.17 | +| explained_variance | 0.272 | +| learning_rate | 4.84e-05 | +| loss | -0.0382 | +| n_updates | 29004 | +| policy_gradient_loss | -0.0221 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1415 | +| iterations | 3298 | +| time_elapsed | 4770 | +| total_timesteps | 6754304 | +| train/ | | +| approx_kl | 0.010479473 | +| clip_fraction | 0.321 | +| clip_range | 0.0733 | +| entropy_loss | -6.81 | +| explained_variance | 0.402 | +| learning_rate | 4.84e-05 | +| loss | -0.0327 | +| n_updates | 29008 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000113 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1415 | +| iterations | 3299 | +| time_elapsed | 4772 | +| total_timesteps | 6756352 | +| train/ | | +| approx_kl | 0.0109839905 | +| clip_fraction | 0.311 | +| clip_range | 0.0733 | +| entropy_loss | -7.29 | +| explained_variance | 0.233 | +| learning_rate | 4.84e-05 | +| loss | -0.0332 | +| n_updates | 29012 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000177 | +------------------------------------------ +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1415 | +| iterations | 3300 | +| time_elapsed | 4773 | +| total_timesteps | 6758400 | +| train/ | | +| approx_kl | 0.0107015 | +| clip_fraction | 0.31 | +| clip_range | 0.0733 | +| entropy_loss | -6.99 | +| explained_variance | 0.197 | +| learning_rate | 4.84e-05 | +| loss | -0.0339 | +| n_updates | 29016 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000271 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1415 | +| iterations | 3301 | +| time_elapsed | 4775 | +| total_timesteps | 6760448 | +| train/ | | +| approx_kl | 0.011581669 | +| clip_fraction | 0.328 | +| clip_range | 0.0733 | +| entropy_loss | -7.23 | +| explained_variance | 0.212 | +| learning_rate | 4.84e-05 | +| loss | -0.0319 | +| n_updates | 29020 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000191 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1415 | +| iterations | 3302 | +| time_elapsed | 4776 | +| total_timesteps | 6762496 | +| train/ | | +| approx_kl | 0.011946134 | +| clip_fraction | 0.362 | +| clip_range | 0.0733 | +| entropy_loss | -7.44 | +| explained_variance | -0.182 | +| learning_rate | 4.84e-05 | +| loss | -0.0326 | +| n_updates | 29024 | +| policy_gradient_loss | -0.0233 | +| value_loss | 0.000139 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1415 | +| iterations | 3303 | +| time_elapsed | 4778 | +| total_timesteps | 6764544 | +| train/ | | +| approx_kl | 0.00818329 | +| clip_fraction | 0.3 | +| clip_range | 0.0733 | +| entropy_loss | -7.14 | +| explained_variance | 0.143 | +| learning_rate | 4.84e-05 | +| loss | -0.0223 | +| n_updates | 29028 | +| policy_gradient_loss | -0.0142 | +| value_loss | 0.000353 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1415 | +| iterations | 3304 | +| time_elapsed | 4779 | +| total_timesteps | 6766592 | +| train/ | | +| approx_kl | 0.010266369 | +| clip_fraction | 0.327 | +| clip_range | 0.0733 | +| entropy_loss | -6.93 | +| explained_variance | 0.335 | +| learning_rate | 4.84e-05 | +| loss | -0.0317 | +| n_updates | 29032 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.00014 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1415 | +| iterations | 3305 | +| time_elapsed | 4780 | +| total_timesteps | 6768640 | +| train/ | | +| approx_kl | 0.011146428 | +| clip_fraction | 0.331 | +| clip_range | 0.0733 | +| entropy_loss | -7.12 | +| explained_variance | -0.187 | +| learning_rate | 4.84e-05 | +| loss | -0.0301 | +| n_updates | 29036 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000132 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1415 | +| iterations | 3306 | +| time_elapsed | 4782 | +| total_timesteps | 6770688 | +| train/ | | +| approx_kl | 0.009950124 | +| clip_fraction | 0.293 | +| clip_range | 0.0733 | +| entropy_loss | -6.74 | +| explained_variance | 0.195 | +| learning_rate | 4.84e-05 | +| loss | -0.0274 | +| n_updates | 29040 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000277 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1415 | +| iterations | 3307 | +| time_elapsed | 4783 | +| total_timesteps | 6772736 | +| train/ | | +| approx_kl | 0.012794413 | +| clip_fraction | 0.348 | +| clip_range | 0.0733 | +| entropy_loss | -6.85 | +| explained_variance | 0.537 | +| learning_rate | 4.84e-05 | +| loss | -0.0294 | +| n_updates | 29044 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000187 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1415 | +| iterations | 3308 | +| time_elapsed | 4785 | +| total_timesteps | 6774784 | +| train/ | | +| approx_kl | 0.0150736105 | +| clip_fraction | 0.364 | +| clip_range | 0.0733 | +| entropy_loss | -7.13 | +| explained_variance | 0.215 | +| learning_rate | 4.84e-05 | +| loss | -0.0318 | +| n_updates | 29048 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000181 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1415 | +| iterations | 3309 | +| time_elapsed | 4786 | +| total_timesteps | 6776832 | +| train/ | | +| approx_kl | 0.013023002 | +| clip_fraction | 0.328 | +| clip_range | 0.0733 | +| entropy_loss | -6.99 | +| explained_variance | 0.467 | +| learning_rate | 4.84e-05 | +| loss | -0.0341 | +| n_updates | 29052 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000173 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1415 | +| iterations | 3310 | +| time_elapsed | 4787 | +| total_timesteps | 6778880 | +| train/ | | +| approx_kl | 0.012564097 | +| clip_fraction | 0.348 | +| clip_range | 0.0733 | +| entropy_loss | -7.38 | +| explained_variance | 0.103 | +| learning_rate | 4.84e-05 | +| loss | -0.0348 | +| n_updates | 29056 | +| policy_gradient_loss | -0.022 | +| value_loss | 0.000233 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1415 | +| iterations | 3311 | +| time_elapsed | 4789 | +| total_timesteps | 6780928 | +| train/ | | +| approx_kl | 0.013719968 | +| clip_fraction | 0.377 | +| clip_range | 0.0733 | +| entropy_loss | -7.15 | +| explained_variance | 0.372 | +| learning_rate | 4.84e-05 | +| loss | -0.0391 | +| n_updates | 29060 | +| policy_gradient_loss | -0.0251 | +| value_loss | 0.000105 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1415 | +| iterations | 3312 | +| time_elapsed | 4790 | +| total_timesteps | 6782976 | +| train/ | | +| approx_kl | 0.011821027 | +| clip_fraction | 0.298 | +| clip_range | 0.0733 | +| entropy_loss | -7.01 | +| explained_variance | 0.253 | +| learning_rate | 4.84e-05 | +| loss | -0.0224 | +| n_updates | 29064 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.00038 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1415 | +| iterations | 3313 | +| time_elapsed | 4792 | +| total_timesteps | 6785024 | +| train/ | | +| approx_kl | 0.012433111 | +| clip_fraction | 0.314 | +| clip_range | 0.0733 | +| entropy_loss | -6.91 | +| explained_variance | 0.334 | +| learning_rate | 4.84e-05 | +| loss | -0.026 | +| n_updates | 29068 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000305 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1415 | +| iterations | 3314 | +| time_elapsed | 4793 | +| total_timesteps | 6787072 | +| train/ | | +| approx_kl | 0.012904184 | +| clip_fraction | 0.361 | +| clip_range | 0.0733 | +| entropy_loss | -6.97 | +| explained_variance | 0.197 | +| learning_rate | 4.84e-05 | +| loss | -0.0336 | +| n_updates | 29072 | +| policy_gradient_loss | -0.023 | +| value_loss | 0.000166 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1415 | +| iterations | 3315 | +| time_elapsed | 4795 | +| total_timesteps | 6789120 | +| train/ | | +| approx_kl | 0.012528692 | +| clip_fraction | 0.353 | +| clip_range | 0.0733 | +| entropy_loss | -7.15 | +| explained_variance | 0.204 | +| learning_rate | 4.84e-05 | +| loss | -0.0388 | +| n_updates | 29076 | +| policy_gradient_loss | -0.0234 | +| value_loss | 0.000112 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1415 | +| iterations | 3316 | +| time_elapsed | 4796 | +| total_timesteps | 6791168 | +| train/ | | +| approx_kl | 0.011103217 | +| clip_fraction | 0.314 | +| clip_range | 0.0733 | +| entropy_loss | -6.58 | +| explained_variance | 0.491 | +| learning_rate | 4.84e-05 | +| loss | -0.0262 | +| n_updates | 29080 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000207 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1415 | +| iterations | 3317 | +| time_elapsed | 4798 | +| total_timesteps | 6793216 | +| train/ | | +| approx_kl | 0.010810859 | +| clip_fraction | 0.326 | +| clip_range | 0.0733 | +| entropy_loss | -7.22 | +| explained_variance | -0.127 | +| learning_rate | 4.84e-05 | +| loss | -0.0374 | +| n_updates | 29084 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000159 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1415 | +| iterations | 3318 | +| time_elapsed | 4799 | +| total_timesteps | 6795264 | +| train/ | | +| approx_kl | 0.011400828 | +| clip_fraction | 0.323 | +| clip_range | 0.0733 | +| entropy_loss | -7.01 | +| explained_variance | 0.0586 | +| learning_rate | 4.84e-05 | +| loss | -0.0217 | +| n_updates | 29088 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000196 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1415 | +| iterations | 3319 | +| time_elapsed | 4800 | +| total_timesteps | 6797312 | +| train/ | | +| approx_kl | 0.010740541 | +| clip_fraction | 0.339 | +| clip_range | 0.0733 | +| entropy_loss | -7.2 | +| explained_variance | 0.194 | +| learning_rate | 4.84e-05 | +| loss | -0.0339 | +| n_updates | 29092 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000115 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1415 | +| iterations | 3320 | +| time_elapsed | 4802 | +| total_timesteps | 6799360 | +| train/ | | +| approx_kl | 0.013976304 | +| clip_fraction | 0.328 | +| clip_range | 0.0733 | +| entropy_loss | -7.31 | +| explained_variance | -0.221 | +| learning_rate | 4.84e-05 | +| loss | -0.0347 | +| n_updates | 29096 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000105 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1415 | +| iterations | 3321 | +| time_elapsed | 4803 | +| total_timesteps | 6801408 | +| train/ | | +| approx_kl | 0.011300208 | +| clip_fraction | 0.315 | +| clip_range | 0.0733 | +| entropy_loss | -7.38 | +| explained_variance | -0.171 | +| learning_rate | 4.84e-05 | +| loss | -0.0361 | +| n_updates | 29100 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000122 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1415 | +| iterations | 3322 | +| time_elapsed | 4805 | +| total_timesteps | 6803456 | +| train/ | | +| approx_kl | 0.011762068 | +| clip_fraction | 0.295 | +| clip_range | 0.0733 | +| entropy_loss | -7.05 | +| explained_variance | 0.328 | +| learning_rate | 4.84e-05 | +| loss | -0.0318 | +| n_updates | 29104 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000144 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1415 | +| iterations | 3323 | +| time_elapsed | 4806 | +| total_timesteps | 6805504 | +| train/ | | +| approx_kl | 0.0134059675 | +| clip_fraction | 0.307 | +| clip_range | 0.0733 | +| entropy_loss | -6.81 | +| explained_variance | 0.376 | +| learning_rate | 4.84e-05 | +| loss | -0.0316 | +| n_updates | 29108 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000226 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1415 | +| iterations | 3324 | +| time_elapsed | 4808 | +| total_timesteps | 6807552 | +| train/ | | +| approx_kl | 0.014159875 | +| clip_fraction | 0.36 | +| clip_range | 0.0733 | +| entropy_loss | -7.15 | +| explained_variance | 0.406 | +| learning_rate | 4.84e-05 | +| loss | -0.0351 | +| n_updates | 29112 | +| policy_gradient_loss | -0.0234 | +| value_loss | 9.34e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1415 | +| iterations | 3325 | +| time_elapsed | 4809 | +| total_timesteps | 6809600 | +| train/ | | +| approx_kl | 0.010458162 | +| clip_fraction | 0.282 | +| clip_range | 0.0733 | +| entropy_loss | -6.86 | +| explained_variance | 0.329 | +| learning_rate | 4.84e-05 | +| loss | -0.0211 | +| n_updates | 29116 | +| policy_gradient_loss | -0.0146 | +| value_loss | 0.000342 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1415 | +| iterations | 3326 | +| time_elapsed | 4810 | +| total_timesteps | 6811648 | +| train/ | | +| approx_kl | 0.01309245 | +| clip_fraction | 0.333 | +| clip_range | 0.0733 | +| entropy_loss | -7.29 | +| explained_variance | 0.306 | +| learning_rate | 4.84e-05 | +| loss | -0.035 | +| n_updates | 29120 | +| policy_gradient_loss | -0.0229 | +| value_loss | 0.000128 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1415 | +| iterations | 3327 | +| time_elapsed | 4812 | +| total_timesteps | 6813696 | +| train/ | | +| approx_kl | 0.011814312 | +| clip_fraction | 0.311 | +| clip_range | 0.0733 | +| entropy_loss | -7.23 | +| explained_variance | 0.255 | +| learning_rate | 4.84e-05 | +| loss | -0.0304 | +| n_updates | 29124 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000173 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1415 | +| iterations | 3328 | +| time_elapsed | 4813 | +| total_timesteps | 6815744 | +| train/ | | +| approx_kl | 0.009474391 | +| clip_fraction | 0.29 | +| clip_range | 0.0733 | +| entropy_loss | -6.98 | +| explained_variance | 0.429 | +| learning_rate | 4.84e-05 | +| loss | -0.0344 | +| n_updates | 29128 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000228 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1415 | +| iterations | 3329 | +| time_elapsed | 4815 | +| total_timesteps | 6817792 | +| train/ | | +| approx_kl | 0.009724259 | +| clip_fraction | 0.302 | +| clip_range | 0.0733 | +| entropy_loss | -7.07 | +| explained_variance | 0.369 | +| learning_rate | 4.84e-05 | +| loss | -0.0273 | +| n_updates | 29132 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000144 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1415 | +| iterations | 3330 | +| time_elapsed | 4816 | +| total_timesteps | 6819840 | +| train/ | | +| approx_kl | 0.011036871 | +| clip_fraction | 0.313 | +| clip_range | 0.0733 | +| entropy_loss | -7.16 | +| explained_variance | 0.562 | +| learning_rate | 4.84e-05 | +| loss | -0.0359 | +| n_updates | 29136 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000112 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1415 | +| iterations | 3331 | +| time_elapsed | 4818 | +| total_timesteps | 6821888 | +| train/ | | +| approx_kl | 0.0116231255 | +| clip_fraction | 0.326 | +| clip_range | 0.0733 | +| entropy_loss | -7.12 | +| explained_variance | 0.258 | +| learning_rate | 4.84e-05 | +| loss | -0.0357 | +| n_updates | 29140 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000124 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1415 | +| iterations | 3332 | +| time_elapsed | 4819 | +| total_timesteps | 6823936 | +| train/ | | +| approx_kl | 0.012001311 | +| clip_fraction | 0.312 | +| clip_range | 0.0733 | +| entropy_loss | -7.03 | +| explained_variance | 0.449 | +| learning_rate | 4.84e-05 | +| loss | -0.0297 | +| n_updates | 29144 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000161 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1415 | +| iterations | 3333 | +| time_elapsed | 4820 | +| total_timesteps | 6825984 | +| train/ | | +| approx_kl | 0.010680364 | +| clip_fraction | 0.262 | +| clip_range | 0.0733 | +| entropy_loss | -6.42 | +| explained_variance | 0.451 | +| learning_rate | 4.84e-05 | +| loss | -0.0208 | +| n_updates | 29148 | +| policy_gradient_loss | -0.0133 | +| value_loss | 0.000331 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1415 | +| iterations | 3334 | +| time_elapsed | 4822 | +| total_timesteps | 6828032 | +| train/ | | +| approx_kl | 0.012518968 | +| clip_fraction | 0.353 | +| clip_range | 0.0733 | +| entropy_loss | -7.24 | +| explained_variance | -0.152 | +| learning_rate | 4.84e-05 | +| loss | -0.0229 | +| n_updates | 29152 | +| policy_gradient_loss | -0.0222 | +| value_loss | 9.86e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1415 | +| iterations | 3335 | +| time_elapsed | 4823 | +| total_timesteps | 6830080 | +| train/ | | +| approx_kl | 0.0115143545 | +| clip_fraction | 0.333 | +| clip_range | 0.0733 | +| entropy_loss | -7.31 | +| explained_variance | 0.00984 | +| learning_rate | 4.84e-05 | +| loss | -0.0343 | +| n_updates | 29156 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000165 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1415 | +| iterations | 3336 | +| time_elapsed | 4825 | +| total_timesteps | 6832128 | +| train/ | | +| approx_kl | 0.011517525 | +| clip_fraction | 0.322 | +| clip_range | 0.0733 | +| entropy_loss | -6.95 | +| explained_variance | 0.21 | +| learning_rate | 4.84e-05 | +| loss | -0.0253 | +| n_updates | 29160 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000249 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1415 | +| iterations | 3337 | +| time_elapsed | 4826 | +| total_timesteps | 6834176 | +| train/ | | +| approx_kl | 0.010916809 | +| clip_fraction | 0.331 | +| clip_range | 0.0733 | +| entropy_loss | -7.32 | +| explained_variance | -0.0843 | +| learning_rate | 4.84e-05 | +| loss | -0.0331 | +| n_updates | 29164 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000162 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1415 | +| iterations | 3338 | +| time_elapsed | 4828 | +| total_timesteps | 6836224 | +| train/ | | +| approx_kl | 0.013435899 | +| clip_fraction | 0.355 | +| clip_range | 0.0733 | +| entropy_loss | -7.17 | +| explained_variance | -0.0817 | +| learning_rate | 4.84e-05 | +| loss | -0.0397 | +| n_updates | 29168 | +| policy_gradient_loss | -0.0238 | +| value_loss | 9.66e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1415 | +| iterations | 3339 | +| time_elapsed | 4829 | +| total_timesteps | 6838272 | +| train/ | | +| approx_kl | 0.012234937 | +| clip_fraction | 0.346 | +| clip_range | 0.0733 | +| entropy_loss | -7.3 | +| explained_variance | -0.103 | +| learning_rate | 4.84e-05 | +| loss | -0.0298 | +| n_updates | 29172 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000117 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1415 | +| iterations | 3340 | +| time_elapsed | 4830 | +| total_timesteps | 6840320 | +| train/ | | +| approx_kl | 0.008600377 | +| clip_fraction | 0.305 | +| clip_range | 0.0733 | +| entropy_loss | -7.19 | +| explained_variance | 0.253 | +| learning_rate | 4.84e-05 | +| loss | -0.0285 | +| n_updates | 29176 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000167 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1415 | +| iterations | 3341 | +| time_elapsed | 4832 | +| total_timesteps | 6842368 | +| train/ | | +| approx_kl | 0.010829337 | +| clip_fraction | 0.35 | +| clip_range | 0.0733 | +| entropy_loss | -6.65 | +| explained_variance | 0.55 | +| learning_rate | 4.84e-05 | +| loss | -0.0274 | +| n_updates | 29180 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000205 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1415 | +| iterations | 3342 | +| time_elapsed | 4833 | +| total_timesteps | 6844416 | +| train/ | | +| approx_kl | 0.0125375055 | +| clip_fraction | 0.335 | +| clip_range | 0.0733 | +| entropy_loss | -7.16 | +| explained_variance | -0.0424 | +| learning_rate | 4.84e-05 | +| loss | -0.0345 | +| n_updates | 29184 | +| policy_gradient_loss | -0.0225 | +| value_loss | 0.00012 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1415 | +| iterations | 3343 | +| time_elapsed | 4835 | +| total_timesteps | 6846464 | +| train/ | | +| approx_kl | 0.011731341 | +| clip_fraction | 0.341 | +| clip_range | 0.0733 | +| entropy_loss | -7.05 | +| explained_variance | 0.248 | +| learning_rate | 4.84e-05 | +| loss | -0.0314 | +| n_updates | 29188 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000116 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1415 | +| iterations | 3344 | +| time_elapsed | 4836 | +| total_timesteps | 6848512 | +| train/ | | +| approx_kl | 0.015342584 | +| clip_fraction | 0.32 | +| clip_range | 0.0733 | +| entropy_loss | -7.04 | +| explained_variance | 0.464 | +| learning_rate | 4.84e-05 | +| loss | -0.0309 | +| n_updates | 29192 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000132 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1415 | +| iterations | 3345 | +| time_elapsed | 4838 | +| total_timesteps | 6850560 | +| train/ | | +| approx_kl | 0.012766322 | +| clip_fraction | 0.326 | +| clip_range | 0.0733 | +| entropy_loss | -7.02 | +| explained_variance | 0.446 | +| learning_rate | 4.84e-05 | +| loss | -0.0322 | +| n_updates | 29196 | +| policy_gradient_loss | -0.0205 | +| value_loss | 9.81e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1416 | +| iterations | 3346 | +| time_elapsed | 4839 | +| total_timesteps | 6852608 | +| train/ | | +| approx_kl | 0.013263135 | +| clip_fraction | 0.329 | +| clip_range | 0.0733 | +| entropy_loss | -6.77 | +| explained_variance | 0.567 | +| learning_rate | 4.84e-05 | +| loss | -0.0311 | +| n_updates | 29200 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000148 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1415 | +| iterations | 3347 | +| time_elapsed | 4840 | +| total_timesteps | 6854656 | +| train/ | | +| approx_kl | 0.0123989675 | +| clip_fraction | 0.316 | +| clip_range | 0.0733 | +| entropy_loss | -7.17 | +| explained_variance | 0.359 | +| learning_rate | 4.84e-05 | +| loss | -0.0325 | +| n_updates | 29204 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.00012 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1416 | +| iterations | 3348 | +| time_elapsed | 4842 | +| total_timesteps | 6856704 | +| train/ | | +| approx_kl | 0.012389551 | +| clip_fraction | 0.323 | +| clip_range | 0.0733 | +| entropy_loss | -7.45 | +| explained_variance | -0.144 | +| learning_rate | 4.84e-05 | +| loss | -0.0315 | +| n_updates | 29208 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.00016 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1416 | +| iterations | 3349 | +| time_elapsed | 4843 | +| total_timesteps | 6858752 | +| train/ | | +| approx_kl | 0.009460259 | +| clip_fraction | 0.285 | +| clip_range | 0.0733 | +| entropy_loss | -6.88 | +| explained_variance | 0.34 | +| learning_rate | 4.84e-05 | +| loss | -0.026 | +| n_updates | 29212 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000369 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1416 | +| iterations | 3350 | +| time_elapsed | 4845 | +| total_timesteps | 6860800 | +| train/ | | +| approx_kl | 0.009877941 | +| clip_fraction | 0.319 | +| clip_range | 0.0733 | +| entropy_loss | -7.35 | +| explained_variance | 0.185 | +| learning_rate | 4.84e-05 | +| loss | -0.037 | +| n_updates | 29216 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.00032 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1416 | +| iterations | 3351 | +| time_elapsed | 4846 | +| total_timesteps | 6862848 | +| train/ | | +| approx_kl | 0.011517908 | +| clip_fraction | 0.329 | +| clip_range | 0.0733 | +| entropy_loss | -6.77 | +| explained_variance | 0.599 | +| learning_rate | 4.84e-05 | +| loss | -0.0355 | +| n_updates | 29220 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000114 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1416 | +| iterations | 3352 | +| time_elapsed | 4847 | +| total_timesteps | 6864896 | +| train/ | | +| approx_kl | 0.009921743 | +| clip_fraction | 0.327 | +| clip_range | 0.0733 | +| entropy_loss | -7.23 | +| explained_variance | 0.0121 | +| learning_rate | 4.84e-05 | +| loss | -0.034 | +| n_updates | 29224 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000231 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1416 | +| iterations | 3353 | +| time_elapsed | 4849 | +| total_timesteps | 6866944 | +| train/ | | +| approx_kl | 0.011229655 | +| clip_fraction | 0.325 | +| clip_range | 0.0733 | +| entropy_loss | -7.04 | +| explained_variance | 0.319 | +| learning_rate | 4.84e-05 | +| loss | -0.032 | +| n_updates | 29228 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000132 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1416 | +| iterations | 3354 | +| time_elapsed | 4850 | +| total_timesteps | 6868992 | +| train/ | | +| approx_kl | 0.010378766 | +| clip_fraction | 0.318 | +| clip_range | 0.0733 | +| entropy_loss | -6.96 | +| explained_variance | 0.265 | +| learning_rate | 4.84e-05 | +| loss | -0.0306 | +| n_updates | 29232 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000225 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1416 | +| iterations | 3355 | +| time_elapsed | 4852 | +| total_timesteps | 6871040 | +| train/ | | +| approx_kl | 0.011612104 | +| clip_fraction | 0.339 | +| clip_range | 0.0733 | +| entropy_loss | -7.17 | +| explained_variance | 0.228 | +| learning_rate | 4.84e-05 | +| loss | -0.0317 | +| n_updates | 29236 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000183 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1416 | +| iterations | 3356 | +| time_elapsed | 4853 | +| total_timesteps | 6873088 | +| train/ | | +| approx_kl | 0.01199534 | +| clip_fraction | 0.338 | +| clip_range | 0.0733 | +| entropy_loss | -7.33 | +| explained_variance | 0.338 | +| learning_rate | 4.84e-05 | +| loss | -0.0361 | +| n_updates | 29240 | +| policy_gradient_loss | -0.0223 | +| value_loss | 0.000111 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1416 | +| iterations | 3357 | +| time_elapsed | 4855 | +| total_timesteps | 6875136 | +| train/ | | +| approx_kl | 0.008938497 | +| clip_fraction | 0.289 | +| clip_range | 0.0733 | +| entropy_loss | -7.01 | +| explained_variance | 0.307 | +| learning_rate | 4.84e-05 | +| loss | -0.0342 | +| n_updates | 29244 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000332 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1416 | +| iterations | 3358 | +| time_elapsed | 4856 | +| total_timesteps | 6877184 | +| train/ | | +| approx_kl | 0.0101004895 | +| clip_fraction | 0.335 | +| clip_range | 0.0733 | +| entropy_loss | -7.06 | +| explained_variance | 0.478 | +| learning_rate | 4.84e-05 | +| loss | -0.0364 | +| n_updates | 29248 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000112 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.384 | +| time/ | | +| fps | 1416 | +| iterations | 3359 | +| time_elapsed | 4858 | +| total_timesteps | 6879232 | +| train/ | | +| approx_kl | 0.011020921 | +| clip_fraction | 0.308 | +| clip_range | 0.0733 | +| entropy_loss | -6.79 | +| explained_variance | 0.447 | +| learning_rate | 4.84e-05 | +| loss | -0.0303 | +| n_updates | 29252 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000232 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.385 | +| time/ | | +| fps | 1416 | +| iterations | 3360 | +| time_elapsed | 4859 | +| total_timesteps | 6881280 | +| train/ | | +| approx_kl | 0.012480024 | +| clip_fraction | 0.308 | +| clip_range | 0.0733 | +| entropy_loss | -7.09 | +| explained_variance | 0.148 | +| learning_rate | 4.84e-05 | +| loss | -0.028 | +| n_updates | 29256 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000317 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.389 | +| time/ | | +| fps | 1416 | +| iterations | 3361 | +| time_elapsed | 4860 | +| total_timesteps | 6883328 | +| train/ | | +| approx_kl | 0.014177825 | +| clip_fraction | 0.326 | +| clip_range | 0.0733 | +| entropy_loss | -7.23 | +| explained_variance | 0.2 | +| learning_rate | 4.84e-05 | +| loss | -0.0352 | +| n_updates | 29260 | +| policy_gradient_loss | -0.0226 | +| value_loss | 0.000164 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.398 | +| time/ | | +| fps | 1416 | +| iterations | 3362 | +| time_elapsed | 4862 | +| total_timesteps | 6885376 | +| train/ | | +| approx_kl | 0.010441934 | +| clip_fraction | 0.324 | +| clip_range | 0.0733 | +| entropy_loss | -6.99 | +| explained_variance | 0.611 | +| learning_rate | 4.84e-05 | +| loss | -0.0441 | +| n_updates | 29264 | +| policy_gradient_loss | -0.0239 | +| value_loss | 8.73e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.393 | +| time/ | | +| fps | 1416 | +| iterations | 3363 | +| time_elapsed | 4863 | +| total_timesteps | 6887424 | +| train/ | | +| approx_kl | 0.0127972495 | +| clip_fraction | 0.336 | +| clip_range | 0.0733 | +| entropy_loss | -6.98 | +| explained_variance | 0.453 | +| learning_rate | 4.84e-05 | +| loss | -0.0384 | +| n_updates | 29268 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000163 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.39 | +| time/ | | +| fps | 1416 | +| iterations | 3364 | +| time_elapsed | 4865 | +| total_timesteps | 6889472 | +| train/ | | +| approx_kl | 0.014043815 | +| clip_fraction | 0.352 | +| clip_range | 0.0733 | +| entropy_loss | -7.27 | +| explained_variance | -0.307 | +| learning_rate | 4.84e-05 | +| loss | -0.0423 | +| n_updates | 29272 | +| policy_gradient_loss | -0.0229 | +| value_loss | 9.04e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.39 | +| time/ | | +| fps | 1416 | +| iterations | 3365 | +| time_elapsed | 4866 | +| total_timesteps | 6891520 | +| train/ | | +| approx_kl | 0.013236782 | +| clip_fraction | 0.365 | +| clip_range | 0.0733 | +| entropy_loss | -7.17 | +| explained_variance | -0.365 | +| learning_rate | 4.84e-05 | +| loss | -0.0386 | +| n_updates | 29276 | +| policy_gradient_loss | -0.0274 | +| value_loss | 6.17e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1416 | +| iterations | 3366 | +| time_elapsed | 4868 | +| total_timesteps | 6893568 | +| train/ | | +| approx_kl | 0.011196431 | +| clip_fraction | 0.326 | +| clip_range | 0.0733 | +| entropy_loss | -7.12 | +| explained_variance | 0.189 | +| learning_rate | 4.84e-05 | +| loss | -0.0283 | +| n_updates | 29280 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000253 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1416 | +| iterations | 3367 | +| time_elapsed | 4869 | +| total_timesteps | 6895616 | +| train/ | | +| approx_kl | 0.011988739 | +| clip_fraction | 0.324 | +| clip_range | 0.0733 | +| entropy_loss | -6.92 | +| explained_variance | 0.604 | +| learning_rate | 4.84e-05 | +| loss | -0.0356 | +| n_updates | 29284 | +| policy_gradient_loss | -0.0204 | +| value_loss | 8.9e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1416 | +| iterations | 3368 | +| time_elapsed | 4870 | +| total_timesteps | 6897664 | +| train/ | | +| approx_kl | 0.010951174 | +| clip_fraction | 0.309 | +| clip_range | 0.0733 | +| entropy_loss | -6.65 | +| explained_variance | 0.519 | +| learning_rate | 4.84e-05 | +| loss | -0.0294 | +| n_updates | 29288 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000242 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1416 | +| iterations | 3369 | +| time_elapsed | 4872 | +| total_timesteps | 6899712 | +| train/ | | +| approx_kl | 0.013592299 | +| clip_fraction | 0.323 | +| clip_range | 0.0733 | +| entropy_loss | -7.08 | +| explained_variance | 0.194 | +| learning_rate | 4.84e-05 | +| loss | -0.0287 | +| n_updates | 29292 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000209 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1416 | +| iterations | 3370 | +| time_elapsed | 4873 | +| total_timesteps | 6901760 | +| train/ | | +| approx_kl | 0.010999558 | +| clip_fraction | 0.338 | +| clip_range | 0.0733 | +| entropy_loss | -7.27 | +| explained_variance | -0.424 | +| learning_rate | 4.84e-05 | +| loss | -0.0339 | +| n_updates | 29296 | +| policy_gradient_loss | -0.0226 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1416 | +| iterations | 3371 | +| time_elapsed | 4875 | +| total_timesteps | 6903808 | +| train/ | | +| approx_kl | 0.009833651 | +| clip_fraction | 0.32 | +| clip_range | 0.0733 | +| entropy_loss | -7.27 | +| explained_variance | 0.187 | +| learning_rate | 4.84e-05 | +| loss | -0.0321 | +| n_updates | 29300 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.00018 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1416 | +| iterations | 3372 | +| time_elapsed | 4876 | +| total_timesteps | 6905856 | +| train/ | | +| approx_kl | 0.01240224 | +| clip_fraction | 0.341 | +| clip_range | 0.0733 | +| entropy_loss | -7.39 | +| explained_variance | -0.167 | +| learning_rate | 4.84e-05 | +| loss | -0.0345 | +| n_updates | 29304 | +| policy_gradient_loss | -0.0224 | +| value_loss | 0.000117 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1416 | +| iterations | 3373 | +| time_elapsed | 4877 | +| total_timesteps | 6907904 | +| train/ | | +| approx_kl | 0.0113566015 | +| clip_fraction | 0.354 | +| clip_range | 0.0733 | +| entropy_loss | -7.22 | +| explained_variance | 0.338 | +| learning_rate | 4.84e-05 | +| loss | -0.0386 | +| n_updates | 29308 | +| policy_gradient_loss | -0.0246 | +| value_loss | 8.61e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1416 | +| iterations | 3374 | +| time_elapsed | 4879 | +| total_timesteps | 6909952 | +| train/ | | +| approx_kl | 0.010569417 | +| clip_fraction | 0.331 | +| clip_range | 0.0733 | +| entropy_loss | -7.37 | +| explained_variance | -0.136 | +| learning_rate | 4.84e-05 | +| loss | -0.0337 | +| n_updates | 29312 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000131 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1416 | +| iterations | 3375 | +| time_elapsed | 4880 | +| total_timesteps | 6912000 | +| train/ | | +| approx_kl | 0.010289438 | +| clip_fraction | 0.296 | +| clip_range | 0.0733 | +| entropy_loss | -6.87 | +| explained_variance | 0.452 | +| learning_rate | 4.84e-05 | +| loss | -0.0237 | +| n_updates | 29316 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000154 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1416 | +| iterations | 3376 | +| time_elapsed | 4882 | +| total_timesteps | 6914048 | +| train/ | | +| approx_kl | 0.009808963 | +| clip_fraction | 0.297 | +| clip_range | 0.0733 | +| entropy_loss | -6.8 | +| explained_variance | 0.469 | +| learning_rate | 4.84e-05 | +| loss | -0.0343 | +| n_updates | 29320 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000219 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.384 | +| time/ | | +| fps | 1416 | +| iterations | 3377 | +| time_elapsed | 4883 | +| total_timesteps | 6916096 | +| train/ | | +| approx_kl | 0.012872534 | +| clip_fraction | 0.327 | +| clip_range | 0.0733 | +| entropy_loss | -6.92 | +| explained_variance | 0.185 | +| learning_rate | 4.84e-05 | +| loss | -0.0308 | +| n_updates | 29324 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000325 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.384 | +| time/ | | +| fps | 1416 | +| iterations | 3378 | +| time_elapsed | 4885 | +| total_timesteps | 6918144 | +| train/ | | +| approx_kl | 0.009744832 | +| clip_fraction | 0.297 | +| clip_range | 0.0733 | +| entropy_loss | -6.72 | +| explained_variance | 0.587 | +| learning_rate | 4.84e-05 | +| loss | -0.0271 | +| n_updates | 29328 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000214 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1416 | +| iterations | 3379 | +| time_elapsed | 4886 | +| total_timesteps | 6920192 | +| train/ | | +| approx_kl | 0.010806521 | +| clip_fraction | 0.345 | +| clip_range | 0.0733 | +| entropy_loss | -7.27 | +| explained_variance | -0.0867 | +| learning_rate | 4.84e-05 | +| loss | -0.039 | +| n_updates | 29332 | +| policy_gradient_loss | -0.0231 | +| value_loss | 0.000103 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1416 | +| iterations | 3380 | +| time_elapsed | 4888 | +| total_timesteps | 6922240 | +| train/ | | +| approx_kl | 0.010920834 | +| clip_fraction | 0.326 | +| clip_range | 0.0733 | +| entropy_loss | -6.97 | +| explained_variance | 0.174 | +| learning_rate | 4.84e-05 | +| loss | -0.0318 | +| n_updates | 29336 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000174 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.384 | +| time/ | | +| fps | 1416 | +| iterations | 3381 | +| time_elapsed | 4889 | +| total_timesteps | 6924288 | +| train/ | | +| approx_kl | 0.011129114 | +| clip_fraction | 0.345 | +| clip_range | 0.0733 | +| entropy_loss | -7.32 | +| explained_variance | -0.043 | +| learning_rate | 4.84e-05 | +| loss | -0.0341 | +| n_updates | 29340 | +| policy_gradient_loss | -0.0222 | +| value_loss | 8.51e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.386 | +| time/ | | +| fps | 1416 | +| iterations | 3382 | +| time_elapsed | 4890 | +| total_timesteps | 6926336 | +| train/ | | +| approx_kl | 0.01376783 | +| clip_fraction | 0.311 | +| clip_range | 0.0733 | +| entropy_loss | -7.39 | +| explained_variance | -0.174 | +| learning_rate | 4.84e-05 | +| loss | -0.0289 | +| n_updates | 29344 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000196 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.386 | +| time/ | | +| fps | 1416 | +| iterations | 3383 | +| time_elapsed | 4892 | +| total_timesteps | 6928384 | +| train/ | | +| approx_kl | 0.011588619 | +| clip_fraction | 0.312 | +| clip_range | 0.0733 | +| entropy_loss | -6.94 | +| explained_variance | 0.148 | +| learning_rate | 4.84e-05 | +| loss | -0.0284 | +| n_updates | 29348 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000371 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.388 | +| time/ | | +| fps | 1416 | +| iterations | 3384 | +| time_elapsed | 4893 | +| total_timesteps | 6930432 | +| train/ | | +| approx_kl | 0.012347335 | +| clip_fraction | 0.341 | +| clip_range | 0.0733 | +| entropy_loss | -7.27 | +| explained_variance | 0.0921 | +| learning_rate | 4.84e-05 | +| loss | -0.0371 | +| n_updates | 29352 | +| policy_gradient_loss | -0.0229 | +| value_loss | 0.000156 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.389 | +| time/ | | +| fps | 1416 | +| iterations | 3385 | +| time_elapsed | 4895 | +| total_timesteps | 6932480 | +| train/ | | +| approx_kl | 0.013827457 | +| clip_fraction | 0.359 | +| clip_range | 0.0733 | +| entropy_loss | -7.24 | +| explained_variance | 0.307 | +| learning_rate | 4.84e-05 | +| loss | -0.0363 | +| n_updates | 29356 | +| policy_gradient_loss | -0.024 | +| value_loss | 0.000125 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1416 | +| iterations | 3386 | +| time_elapsed | 4896 | +| total_timesteps | 6934528 | +| train/ | | +| approx_kl | 0.012656625 | +| clip_fraction | 0.32 | +| clip_range | 0.0733 | +| entropy_loss | -6.98 | +| explained_variance | 0.171 | +| learning_rate | 4.84e-05 | +| loss | -0.0313 | +| n_updates | 29360 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000261 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1416 | +| iterations | 3387 | +| time_elapsed | 4898 | +| total_timesteps | 6936576 | +| train/ | | +| approx_kl | 0.011391934 | +| clip_fraction | 0.337 | +| clip_range | 0.0733 | +| entropy_loss | -6.9 | +| explained_variance | 0.22 | +| learning_rate | 4.84e-05 | +| loss | -0.04 | +| n_updates | 29364 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000171 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1416 | +| iterations | 3388 | +| time_elapsed | 4899 | +| total_timesteps | 6938624 | +| train/ | | +| approx_kl | 0.012197473 | +| clip_fraction | 0.333 | +| clip_range | 0.0733 | +| entropy_loss | -7.04 | +| explained_variance | 0.0518 | +| learning_rate | 4.84e-05 | +| loss | -0.0279 | +| n_updates | 29368 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000165 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1416 | +| iterations | 3389 | +| time_elapsed | 4900 | +| total_timesteps | 6940672 | +| train/ | | +| approx_kl | 0.012501681 | +| clip_fraction | 0.338 | +| clip_range | 0.0733 | +| entropy_loss | -6.83 | +| explained_variance | 0.555 | +| learning_rate | 4.84e-05 | +| loss | -0.0321 | +| n_updates | 29372 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000147 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1416 | +| iterations | 3390 | +| time_elapsed | 4902 | +| total_timesteps | 6942720 | +| train/ | | +| approx_kl | 0.013944736 | +| clip_fraction | 0.324 | +| clip_range | 0.0733 | +| entropy_loss | -6.52 | +| explained_variance | 0.633 | +| learning_rate | 4.84e-05 | +| loss | -0.0318 | +| n_updates | 29376 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000117 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1416 | +| iterations | 3391 | +| time_elapsed | 4903 | +| total_timesteps | 6944768 | +| train/ | | +| approx_kl | 0.01416713 | +| clip_fraction | 0.358 | +| clip_range | 0.0733 | +| entropy_loss | -7.25 | +| explained_variance | -0.122 | +| learning_rate | 4.84e-05 | +| loss | -0.0344 | +| n_updates | 29380 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.00015 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1416 | +| iterations | 3392 | +| time_elapsed | 4905 | +| total_timesteps | 6946816 | +| train/ | | +| approx_kl | 0.014068171 | +| clip_fraction | 0.33 | +| clip_range | 0.0733 | +| entropy_loss | -7.35 | +| explained_variance | -0.0334 | +| learning_rate | 4.84e-05 | +| loss | -0.0342 | +| n_updates | 29384 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000212 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1416 | +| iterations | 3393 | +| time_elapsed | 4906 | +| total_timesteps | 6948864 | +| train/ | | +| approx_kl | 0.0099139605 | +| clip_fraction | 0.328 | +| clip_range | 0.0733 | +| entropy_loss | -7.23 | +| explained_variance | 0.342 | +| learning_rate | 4.84e-05 | +| loss | -0.0325 | +| n_updates | 29388 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000141 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1416 | +| iterations | 3394 | +| time_elapsed | 4908 | +| total_timesteps | 6950912 | +| train/ | | +| approx_kl | 0.012300782 | +| clip_fraction | 0.305 | +| clip_range | 0.0733 | +| entropy_loss | -6.84 | +| explained_variance | 0.123 | +| learning_rate | 4.83e-05 | +| loss | -0.0313 | +| n_updates | 29392 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000343 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1416 | +| iterations | 3395 | +| time_elapsed | 4909 | +| total_timesteps | 6952960 | +| train/ | | +| approx_kl | 0.012860907 | +| clip_fraction | 0.372 | +| clip_range | 0.0733 | +| entropy_loss | -7.26 | +| explained_variance | 0.0335 | +| learning_rate | 4.83e-05 | +| loss | -0.0392 | +| n_updates | 29396 | +| policy_gradient_loss | -0.0248 | +| value_loss | 0.000171 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1416 | +| iterations | 3396 | +| time_elapsed | 4911 | +| total_timesteps | 6955008 | +| train/ | | +| approx_kl | 0.011166286 | +| clip_fraction | 0.319 | +| clip_range | 0.0733 | +| entropy_loss | -7.21 | +| explained_variance | -0.119 | +| learning_rate | 4.83e-05 | +| loss | -0.0373 | +| n_updates | 29400 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000225 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1416 | +| iterations | 3397 | +| time_elapsed | 4912 | +| total_timesteps | 6957056 | +| train/ | | +| approx_kl | 0.011420448 | +| clip_fraction | 0.323 | +| clip_range | 0.0733 | +| entropy_loss | -7.14 | +| explained_variance | 0.11 | +| learning_rate | 4.83e-05 | +| loss | -0.0247 | +| n_updates | 29404 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000186 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1416 | +| iterations | 3398 | +| time_elapsed | 4914 | +| total_timesteps | 6959104 | +| train/ | | +| approx_kl | 0.011099992 | +| clip_fraction | 0.321 | +| clip_range | 0.0733 | +| entropy_loss | -6.42 | +| explained_variance | 0.566 | +| learning_rate | 4.83e-05 | +| loss | -0.028 | +| n_updates | 29408 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000212 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1416 | +| iterations | 3399 | +| time_elapsed | 4915 | +| total_timesteps | 6961152 | +| train/ | | +| approx_kl | 0.012850678 | +| clip_fraction | 0.346 | +| clip_range | 0.0733 | +| entropy_loss | -7.1 | +| explained_variance | 0.335 | +| learning_rate | 4.83e-05 | +| loss | -0.0326 | +| n_updates | 29412 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000134 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1416 | +| iterations | 3400 | +| time_elapsed | 4916 | +| total_timesteps | 6963200 | +| train/ | | +| approx_kl | 0.010915952 | +| clip_fraction | 0.313 | +| clip_range | 0.0733 | +| entropy_loss | -7.2 | +| explained_variance | 0.264 | +| learning_rate | 4.83e-05 | +| loss | -0.0335 | +| n_updates | 29416 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000217 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1416 | +| iterations | 3401 | +| time_elapsed | 4918 | +| total_timesteps | 6965248 | +| train/ | | +| approx_kl | 0.011393279 | +| clip_fraction | 0.309 | +| clip_range | 0.0733 | +| entropy_loss | -6.93 | +| explained_variance | 0.146 | +| learning_rate | 4.83e-05 | +| loss | -0.0345 | +| n_updates | 29420 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000212 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1416 | +| iterations | 3402 | +| time_elapsed | 4919 | +| total_timesteps | 6967296 | +| train/ | | +| approx_kl | 0.013242302 | +| clip_fraction | 0.367 | +| clip_range | 0.0733 | +| entropy_loss | -7.26 | +| explained_variance | -0.0681 | +| learning_rate | 4.83e-05 | +| loss | -0.0421 | +| n_updates | 29424 | +| policy_gradient_loss | -0.0245 | +| value_loss | 0.000126 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1416 | +| iterations | 3403 | +| time_elapsed | 4921 | +| total_timesteps | 6969344 | +| train/ | | +| approx_kl | 0.012828976 | +| clip_fraction | 0.323 | +| clip_range | 0.0733 | +| entropy_loss | -7.16 | +| explained_variance | 0.242 | +| learning_rate | 4.83e-05 | +| loss | -0.0322 | +| n_updates | 29428 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000175 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1416 | +| iterations | 3404 | +| time_elapsed | 4922 | +| total_timesteps | 6971392 | +| train/ | | +| approx_kl | 0.011523557 | +| clip_fraction | 0.286 | +| clip_range | 0.0733 | +| entropy_loss | -6.96 | +| explained_variance | 0.225 | +| learning_rate | 4.83e-05 | +| loss | -0.0288 | +| n_updates | 29432 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.00043 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1416 | +| iterations | 3405 | +| time_elapsed | 4924 | +| total_timesteps | 6973440 | +| train/ | | +| approx_kl | 0.010591043 | +| clip_fraction | 0.31 | +| clip_range | 0.0733 | +| entropy_loss | -6.94 | +| explained_variance | 0.33 | +| learning_rate | 4.83e-05 | +| loss | -0.0263 | +| n_updates | 29436 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000273 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1416 | +| iterations | 3406 | +| time_elapsed | 4925 | +| total_timesteps | 6975488 | +| train/ | | +| approx_kl | 0.013121914 | +| clip_fraction | 0.322 | +| clip_range | 0.0733 | +| entropy_loss | -7.2 | +| explained_variance | -0.341 | +| learning_rate | 4.83e-05 | +| loss | -0.035 | +| n_updates | 29440 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000164 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1416 | +| iterations | 3407 | +| time_elapsed | 4927 | +| total_timesteps | 6977536 | +| train/ | | +| approx_kl | 0.009654656 | +| clip_fraction | 0.308 | +| clip_range | 0.0733 | +| entropy_loss | -6.78 | +| explained_variance | 0.358 | +| learning_rate | 4.83e-05 | +| loss | -0.0325 | +| n_updates | 29444 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000262 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1416 | +| iterations | 3408 | +| time_elapsed | 4928 | +| total_timesteps | 6979584 | +| train/ | | +| approx_kl | 0.010790855 | +| clip_fraction | 0.331 | +| clip_range | 0.0733 | +| entropy_loss | -7.34 | +| explained_variance | -0.128 | +| learning_rate | 4.83e-05 | +| loss | -0.0357 | +| n_updates | 29448 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000152 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1416 | +| iterations | 3409 | +| time_elapsed | 4929 | +| total_timesteps | 6981632 | +| train/ | | +| approx_kl | 0.011555624 | +| clip_fraction | 0.314 | +| clip_range | 0.0733 | +| entropy_loss | -7.19 | +| explained_variance | 0.202 | +| learning_rate | 4.83e-05 | +| loss | -0.025 | +| n_updates | 29452 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000211 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1416 | +| iterations | 3410 | +| time_elapsed | 4931 | +| total_timesteps | 6983680 | +| train/ | | +| approx_kl | 0.012803999 | +| clip_fraction | 0.326 | +| clip_range | 0.0733 | +| entropy_loss | -6.93 | +| explained_variance | 0.585 | +| learning_rate | 4.83e-05 | +| loss | -0.0362 | +| n_updates | 29456 | +| policy_gradient_loss | -0.0219 | +| value_loss | 9.95e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1416 | +| iterations | 3411 | +| time_elapsed | 4932 | +| total_timesteps | 6985728 | +| train/ | | +| approx_kl | 0.014776194 | +| clip_fraction | 0.303 | +| clip_range | 0.0733 | +| entropy_loss | -7.05 | +| explained_variance | 0.289 | +| learning_rate | 4.83e-05 | +| loss | -0.0243 | +| n_updates | 29460 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000165 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1416 | +| iterations | 3412 | +| time_elapsed | 4934 | +| total_timesteps | 6987776 | +| train/ | | +| approx_kl | 0.012155077 | +| clip_fraction | 0.3 | +| clip_range | 0.0733 | +| entropy_loss | -6.99 | +| explained_variance | 0.251 | +| learning_rate | 4.83e-05 | +| loss | -0.023 | +| n_updates | 29464 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000255 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1416 | +| iterations | 3413 | +| time_elapsed | 4935 | +| total_timesteps | 6989824 | +| train/ | | +| approx_kl | 0.01272416 | +| clip_fraction | 0.346 | +| clip_range | 0.0733 | +| entropy_loss | -7.39 | +| explained_variance | -0.281 | +| learning_rate | 4.83e-05 | +| loss | -0.0443 | +| n_updates | 29468 | +| policy_gradient_loss | -0.0241 | +| value_loss | 0.000119 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1416 | +| iterations | 3414 | +| time_elapsed | 4936 | +| total_timesteps | 6991872 | +| train/ | | +| approx_kl | 0.010338489 | +| clip_fraction | 0.288 | +| clip_range | 0.0733 | +| entropy_loss | -6.64 | +| explained_variance | 0.422 | +| learning_rate | 4.83e-05 | +| loss | -0.0303 | +| n_updates | 29472 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000295 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1416 | +| iterations | 3415 | +| time_elapsed | 4938 | +| total_timesteps | 6993920 | +| train/ | | +| approx_kl | 0.011864178 | +| clip_fraction | 0.343 | +| clip_range | 0.0733 | +| entropy_loss | -7.1 | +| explained_variance | 0.564 | +| learning_rate | 4.83e-05 | +| loss | -0.0391 | +| n_updates | 29476 | +| policy_gradient_loss | -0.0218 | +| value_loss | 9.93e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1416 | +| iterations | 3416 | +| time_elapsed | 4939 | +| total_timesteps | 6995968 | +| train/ | | +| approx_kl | 0.013043103 | +| clip_fraction | 0.331 | +| clip_range | 0.0733 | +| entropy_loss | -7.02 | +| explained_variance | 0.471 | +| learning_rate | 4.83e-05 | +| loss | -0.0315 | +| n_updates | 29480 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000155 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1416 | +| iterations | 3417 | +| time_elapsed | 4941 | +| total_timesteps | 6998016 | +| train/ | | +| approx_kl | 0.012207402 | +| clip_fraction | 0.342 | +| clip_range | 0.0733 | +| entropy_loss | -7.39 | +| explained_variance | -0.097 | +| learning_rate | 4.83e-05 | +| loss | -0.0398 | +| n_updates | 29484 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000117 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1416 | +| iterations | 3418 | +| time_elapsed | 4942 | +| total_timesteps | 7000064 | +| train/ | | +| approx_kl | 0.012476357 | +| clip_fraction | 0.317 | +| clip_range | 0.0733 | +| entropy_loss | -7.44 | +| explained_variance | -0.148 | +| learning_rate | 4.83e-05 | +| loss | -0.042 | +| n_updates | 29488 | +| policy_gradient_loss | -0.0222 | +| value_loss | 9.54e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1416 | +| iterations | 3419 | +| time_elapsed | 4944 | +| total_timesteps | 7002112 | +| train/ | | +| approx_kl | 0.0118206665 | +| clip_fraction | 0.338 | +| clip_range | 0.0732 | +| entropy_loss | -6.92 | +| explained_variance | 0.56 | +| learning_rate | 4.83e-05 | +| loss | -0.0325 | +| n_updates | 29492 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000105 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1416 | +| iterations | 3420 | +| time_elapsed | 4945 | +| total_timesteps | 7004160 | +| train/ | | +| approx_kl | 0.012007093 | +| clip_fraction | 0.337 | +| clip_range | 0.0732 | +| entropy_loss | -7.15 | +| explained_variance | -0.108 | +| learning_rate | 4.83e-05 | +| loss | -0.0337 | +| n_updates | 29496 | +| policy_gradient_loss | -0.0202 | +| value_loss | 9.6e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1416 | +| iterations | 3421 | +| time_elapsed | 4946 | +| total_timesteps | 7006208 | +| train/ | | +| approx_kl | 0.013333276 | +| clip_fraction | 0.327 | +| clip_range | 0.0732 | +| entropy_loss | -6.7 | +| explained_variance | 0.518 | +| learning_rate | 4.83e-05 | +| loss | -0.0323 | +| n_updates | 29500 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000137 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1416 | +| iterations | 3422 | +| time_elapsed | 4948 | +| total_timesteps | 7008256 | +| train/ | | +| approx_kl | 0.012396093 | +| clip_fraction | 0.31 | +| clip_range | 0.0732 | +| entropy_loss | -6.85 | +| explained_variance | 0.535 | +| learning_rate | 4.83e-05 | +| loss | -0.0267 | +| n_updates | 29504 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.00015 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1416 | +| iterations | 3423 | +| time_elapsed | 4949 | +| total_timesteps | 7010304 | +| train/ | | +| approx_kl | 0.01024986 | +| clip_fraction | 0.301 | +| clip_range | 0.0732 | +| entropy_loss | -6.95 | +| explained_variance | 0.225 | +| learning_rate | 4.83e-05 | +| loss | -0.0257 | +| n_updates | 29508 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.00024 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1416 | +| iterations | 3424 | +| time_elapsed | 4951 | +| total_timesteps | 7012352 | +| train/ | | +| approx_kl | 0.011746811 | +| clip_fraction | 0.321 | +| clip_range | 0.0732 | +| entropy_loss | -7.26 | +| explained_variance | 0.0347 | +| learning_rate | 4.83e-05 | +| loss | -0.031 | +| n_updates | 29512 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000201 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1416 | +| iterations | 3425 | +| time_elapsed | 4952 | +| total_timesteps | 7014400 | +| train/ | | +| approx_kl | 0.010760698 | +| clip_fraction | 0.296 | +| clip_range | 0.0732 | +| entropy_loss | -6.99 | +| explained_variance | 0.347 | +| learning_rate | 4.83e-05 | +| loss | -0.031 | +| n_updates | 29516 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000231 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1416 | +| iterations | 3426 | +| time_elapsed | 4954 | +| total_timesteps | 7016448 | +| train/ | | +| approx_kl | 0.012482786 | +| clip_fraction | 0.353 | +| clip_range | 0.0732 | +| entropy_loss | -7.12 | +| explained_variance | -0.49 | +| learning_rate | 4.83e-05 | +| loss | -0.0406 | +| n_updates | 29520 | +| policy_gradient_loss | -0.0237 | +| value_loss | 9.55e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1416 | +| iterations | 3427 | +| time_elapsed | 4955 | +| total_timesteps | 7018496 | +| train/ | | +| approx_kl | 0.010293679 | +| clip_fraction | 0.316 | +| clip_range | 0.0732 | +| entropy_loss | -7.18 | +| explained_variance | 0.228 | +| learning_rate | 4.83e-05 | +| loss | -0.0351 | +| n_updates | 29524 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000145 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1416 | +| iterations | 3428 | +| time_elapsed | 4957 | +| total_timesteps | 7020544 | +| train/ | | +| approx_kl | 0.010884907 | +| clip_fraction | 0.301 | +| clip_range | 0.0732 | +| entropy_loss | -7.1 | +| explained_variance | 0.179 | +| learning_rate | 4.83e-05 | +| loss | -0.0323 | +| n_updates | 29528 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000262 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1416 | +| iterations | 3429 | +| time_elapsed | 4958 | +| total_timesteps | 7022592 | +| train/ | | +| approx_kl | 0.0109468885 | +| clip_fraction | 0.327 | +| clip_range | 0.0732 | +| entropy_loss | -7.13 | +| explained_variance | 0.0248 | +| learning_rate | 4.83e-05 | +| loss | -0.0266 | +| n_updates | 29532 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.00032 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1416 | +| iterations | 3430 | +| time_elapsed | 4959 | +| total_timesteps | 7024640 | +| train/ | | +| approx_kl | 0.012313586 | +| clip_fraction | 0.36 | +| clip_range | 0.0732 | +| entropy_loss | -6.87 | +| explained_variance | 0.345 | +| learning_rate | 4.83e-05 | +| loss | -0.0327 | +| n_updates | 29536 | +| policy_gradient_loss | -0.0227 | +| value_loss | 0.000121 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1416 | +| iterations | 3431 | +| time_elapsed | 4961 | +| total_timesteps | 7026688 | +| train/ | | +| approx_kl | 0.0121813575 | +| clip_fraction | 0.366 | +| clip_range | 0.0732 | +| entropy_loss | -7.15 | +| explained_variance | 0.0598 | +| learning_rate | 4.83e-05 | +| loss | -0.0318 | +| n_updates | 29540 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000162 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1416 | +| iterations | 3432 | +| time_elapsed | 4962 | +| total_timesteps | 7028736 | +| train/ | | +| approx_kl | 0.013199275 | +| clip_fraction | 0.324 | +| clip_range | 0.0732 | +| entropy_loss | -7.12 | +| explained_variance | -0.0633 | +| learning_rate | 4.83e-05 | +| loss | -0.0342 | +| n_updates | 29544 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000301 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1416 | +| iterations | 3433 | +| time_elapsed | 4964 | +| total_timesteps | 7030784 | +| train/ | | +| approx_kl | 0.011774806 | +| clip_fraction | 0.326 | +| clip_range | 0.0732 | +| entropy_loss | -6.84 | +| explained_variance | 0.246 | +| learning_rate | 4.83e-05 | +| loss | -0.0362 | +| n_updates | 29548 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000266 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1416 | +| iterations | 3434 | +| time_elapsed | 4965 | +| total_timesteps | 7032832 | +| train/ | | +| approx_kl | 0.013539482 | +| clip_fraction | 0.348 | +| clip_range | 0.0732 | +| entropy_loss | -7.14 | +| explained_variance | -0.128 | +| learning_rate | 4.83e-05 | +| loss | -0.031 | +| n_updates | 29552 | +| policy_gradient_loss | -0.0232 | +| value_loss | 0.000185 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1416 | +| iterations | 3435 | +| time_elapsed | 4967 | +| total_timesteps | 7034880 | +| train/ | | +| approx_kl | 0.011551056 | +| clip_fraction | 0.318 | +| clip_range | 0.0732 | +| entropy_loss | -7.15 | +| explained_variance | 0.095 | +| learning_rate | 4.83e-05 | +| loss | -0.03 | +| n_updates | 29556 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000272 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1416 | +| iterations | 3436 | +| time_elapsed | 4968 | +| total_timesteps | 7036928 | +| train/ | | +| approx_kl | 0.011201513 | +| clip_fraction | 0.307 | +| clip_range | 0.0732 | +| entropy_loss | -7.2 | +| explained_variance | 0.281 | +| learning_rate | 4.83e-05 | +| loss | -0.0283 | +| n_updates | 29560 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000186 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1416 | +| iterations | 3437 | +| time_elapsed | 4969 | +| total_timesteps | 7038976 | +| train/ | | +| approx_kl | 0.010470094 | +| clip_fraction | 0.314 | +| clip_range | 0.0732 | +| entropy_loss | -7.02 | +| explained_variance | 0.314 | +| learning_rate | 4.83e-05 | +| loss | -0.0304 | +| n_updates | 29564 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000253 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1416 | +| iterations | 3438 | +| time_elapsed | 4971 | +| total_timesteps | 7041024 | +| train/ | | +| approx_kl | 0.011046821 | +| clip_fraction | 0.311 | +| clip_range | 0.0732 | +| entropy_loss | -6.84 | +| explained_variance | 0.341 | +| learning_rate | 4.83e-05 | +| loss | -0.0336 | +| n_updates | 29568 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000302 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1416 | +| iterations | 3439 | +| time_elapsed | 4972 | +| total_timesteps | 7043072 | +| train/ | | +| approx_kl | 0.01279952 | +| clip_fraction | 0.36 | +| clip_range | 0.0732 | +| entropy_loss | -7.28 | +| explained_variance | 0.27 | +| learning_rate | 4.83e-05 | +| loss | -0.0402 | +| n_updates | 29572 | +| policy_gradient_loss | -0.0256 | +| value_loss | 8.79e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1416 | +| iterations | 3440 | +| time_elapsed | 4974 | +| total_timesteps | 7045120 | +| train/ | | +| approx_kl | 0.012790321 | +| clip_fraction | 0.301 | +| clip_range | 0.0732 | +| entropy_loss | -7.01 | +| explained_variance | 0.261 | +| learning_rate | 4.83e-05 | +| loss | -0.0315 | +| n_updates | 29576 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000334 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1416 | +| iterations | 3441 | +| time_elapsed | 4975 | +| total_timesteps | 7047168 | +| train/ | | +| approx_kl | 0.01070186 | +| clip_fraction | 0.305 | +| clip_range | 0.0732 | +| entropy_loss | -7.42 | +| explained_variance | -0.104 | +| learning_rate | 4.83e-05 | +| loss | -0.0332 | +| n_updates | 29580 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000357 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1416 | +| iterations | 3442 | +| time_elapsed | 4977 | +| total_timesteps | 7049216 | +| train/ | | +| approx_kl | 0.011631418 | +| clip_fraction | 0.344 | +| clip_range | 0.0732 | +| entropy_loss | -7.18 | +| explained_variance | 0.363 | +| learning_rate | 4.83e-05 | +| loss | -0.0383 | +| n_updates | 29584 | +| policy_gradient_loss | -0.0225 | +| value_loss | 0.000138 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1416 | +| iterations | 3443 | +| time_elapsed | 4978 | +| total_timesteps | 7051264 | +| train/ | | +| approx_kl | 0.00939825 | +| clip_fraction | 0.323 | +| clip_range | 0.0732 | +| entropy_loss | -6.53 | +| explained_variance | 0.607 | +| learning_rate | 4.83e-05 | +| loss | -0.0286 | +| n_updates | 29588 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000188 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1416 | +| iterations | 3444 | +| time_elapsed | 4979 | +| total_timesteps | 7053312 | +| train/ | | +| approx_kl | 0.012758093 | +| clip_fraction | 0.327 | +| clip_range | 0.0732 | +| entropy_loss | -6.72 | +| explained_variance | -0.068 | +| learning_rate | 4.83e-05 | +| loss | -0.0302 | +| n_updates | 29592 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000143 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1416 | +| iterations | 3445 | +| time_elapsed | 4981 | +| total_timesteps | 7055360 | +| train/ | | +| approx_kl | 0.013330236 | +| clip_fraction | 0.31 | +| clip_range | 0.0732 | +| entropy_loss | -6.85 | +| explained_variance | 0.264 | +| learning_rate | 4.83e-05 | +| loss | -0.0331 | +| n_updates | 29596 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000357 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1416 | +| iterations | 3446 | +| time_elapsed | 4982 | +| total_timesteps | 7057408 | +| train/ | | +| approx_kl | 0.0117857065 | +| clip_fraction | 0.347 | +| clip_range | 0.0732 | +| entropy_loss | -7.34 | +| explained_variance | -0.148 | +| learning_rate | 4.83e-05 | +| loss | -0.0323 | +| n_updates | 29600 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000182 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1416 | +| iterations | 3447 | +| time_elapsed | 4984 | +| total_timesteps | 7059456 | +| train/ | | +| approx_kl | 0.012541834 | +| clip_fraction | 0.328 | +| clip_range | 0.0732 | +| entropy_loss | -7.03 | +| explained_variance | 0.0556 | +| learning_rate | 4.83e-05 | +| loss | -0.031 | +| n_updates | 29604 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.00022 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1416 | +| iterations | 3448 | +| time_elapsed | 4985 | +| total_timesteps | 7061504 | +| train/ | | +| approx_kl | 0.008711601 | +| clip_fraction | 0.322 | +| clip_range | 0.0732 | +| entropy_loss | -7.33 | +| explained_variance | 0.0655 | +| learning_rate | 4.83e-05 | +| loss | -0.03 | +| n_updates | 29608 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000291 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1416 | +| iterations | 3449 | +| time_elapsed | 4987 | +| total_timesteps | 7063552 | +| train/ | | +| approx_kl | 0.010004224 | +| clip_fraction | 0.308 | +| clip_range | 0.0732 | +| entropy_loss | -7.38 | +| explained_variance | -0.0267 | +| learning_rate | 4.83e-05 | +| loss | -0.0318 | +| n_updates | 29612 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000376 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1416 | +| iterations | 3450 | +| time_elapsed | 4988 | +| total_timesteps | 7065600 | +| train/ | | +| approx_kl | 0.010491513 | +| clip_fraction | 0.332 | +| clip_range | 0.0732 | +| entropy_loss | -7.38 | +| explained_variance | -0.165 | +| learning_rate | 4.83e-05 | +| loss | -0.0365 | +| n_updates | 29616 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000193 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1416 | +| iterations | 3451 | +| time_elapsed | 4990 | +| total_timesteps | 7067648 | +| train/ | | +| approx_kl | 0.012788178 | +| clip_fraction | 0.346 | +| clip_range | 0.0732 | +| entropy_loss | -7.39 | +| explained_variance | -0.203 | +| learning_rate | 4.83e-05 | +| loss | -0.034 | +| n_updates | 29620 | +| policy_gradient_loss | -0.0225 | +| value_loss | 0.000112 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.385 | +| time/ | | +| fps | 1416 | +| iterations | 3452 | +| time_elapsed | 4991 | +| total_timesteps | 7069696 | +| train/ | | +| approx_kl | 0.008853171 | +| clip_fraction | 0.285 | +| clip_range | 0.0732 | +| entropy_loss | -6.99 | +| explained_variance | 0.49 | +| learning_rate | 4.83e-05 | +| loss | -0.0247 | +| n_updates | 29624 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000142 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.386 | +| time/ | | +| fps | 1416 | +| iterations | 3453 | +| time_elapsed | 4992 | +| total_timesteps | 7071744 | +| train/ | | +| approx_kl | 0.008855269 | +| clip_fraction | 0.301 | +| clip_range | 0.0732 | +| entropy_loss | -6.99 | +| explained_variance | 0.467 | +| learning_rate | 4.83e-05 | +| loss | -0.0241 | +| n_updates | 29628 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000166 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.39 | +| time/ | | +| fps | 1416 | +| iterations | 3454 | +| time_elapsed | 4994 | +| total_timesteps | 7073792 | +| train/ | | +| approx_kl | 0.010406523 | +| clip_fraction | 0.336 | +| clip_range | 0.0732 | +| entropy_loss | -7.12 | +| explained_variance | -0.121 | +| learning_rate | 4.83e-05 | +| loss | -0.0334 | +| n_updates | 29632 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000166 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.394 | +| time/ | | +| fps | 1416 | +| iterations | 3455 | +| time_elapsed | 4995 | +| total_timesteps | 7075840 | +| train/ | | +| approx_kl | 0.01352831 | +| clip_fraction | 0.308 | +| clip_range | 0.0732 | +| entropy_loss | -7.29 | +| explained_variance | -0.0998 | +| learning_rate | 4.83e-05 | +| loss | -0.0301 | +| n_updates | 29636 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000258 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.391 | +| time/ | | +| fps | 1416 | +| iterations | 3456 | +| time_elapsed | 4997 | +| total_timesteps | 7077888 | +| train/ | | +| approx_kl | 0.01248428 | +| clip_fraction | 0.328 | +| clip_range | 0.0732 | +| entropy_loss | -6.72 | +| explained_variance | 0.382 | +| learning_rate | 4.83e-05 | +| loss | -0.0336 | +| n_updates | 29640 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000171 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.391 | +| time/ | | +| fps | 1416 | +| iterations | 3457 | +| time_elapsed | 4998 | +| total_timesteps | 7079936 | +| train/ | | +| approx_kl | 0.014116039 | +| clip_fraction | 0.354 | +| clip_range | 0.0732 | +| entropy_loss | -7.12 | +| explained_variance | -0.0198 | +| learning_rate | 4.83e-05 | +| loss | -0.0374 | +| n_updates | 29644 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000206 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.397 | +| time/ | | +| fps | 1416 | +| iterations | 3458 | +| time_elapsed | 5000 | +| total_timesteps | 7081984 | +| train/ | | +| approx_kl | 0.013797852 | +| clip_fraction | 0.349 | +| clip_range | 0.0732 | +| entropy_loss | -7.02 | +| explained_variance | 0.381 | +| learning_rate | 4.83e-05 | +| loss | -0.0358 | +| n_updates | 29648 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000141 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.397 | +| time/ | | +| fps | 1416 | +| iterations | 3459 | +| time_elapsed | 5001 | +| total_timesteps | 7084032 | +| train/ | | +| approx_kl | 0.013306508 | +| clip_fraction | 0.343 | +| clip_range | 0.0732 | +| entropy_loss | -7.28 | +| explained_variance | -0.0399 | +| learning_rate | 4.83e-05 | +| loss | -0.0252 | +| n_updates | 29652 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000222 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.397 | +| time/ | | +| fps | 1416 | +| iterations | 3460 | +| time_elapsed | 5002 | +| total_timesteps | 7086080 | +| train/ | | +| approx_kl | 0.012013688 | +| clip_fraction | 0.333 | +| clip_range | 0.0732 | +| entropy_loss | -7.19 | +| explained_variance | 0.277 | +| learning_rate | 4.83e-05 | +| loss | -0.0363 | +| n_updates | 29656 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000128 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.396 | +| time/ | | +| fps | 1416 | +| iterations | 3461 | +| time_elapsed | 5004 | +| total_timesteps | 7088128 | +| train/ | | +| approx_kl | 0.01092387 | +| clip_fraction | 0.294 | +| clip_range | 0.0732 | +| entropy_loss | -7.31 | +| explained_variance | 0.235 | +| learning_rate | 4.83e-05 | +| loss | -0.0275 | +| n_updates | 29660 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000186 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.396 | +| time/ | | +| fps | 1416 | +| iterations | 3462 | +| time_elapsed | 5005 | +| total_timesteps | 7090176 | +| train/ | | +| approx_kl | 0.010645278 | +| clip_fraction | 0.31 | +| clip_range | 0.0732 | +| entropy_loss | -7.08 | +| explained_variance | 0.341 | +| learning_rate | 4.83e-05 | +| loss | -0.026 | +| n_updates | 29664 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000198 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.4 | +| time/ | | +| fps | 1416 | +| iterations | 3463 | +| time_elapsed | 5007 | +| total_timesteps | 7092224 | +| train/ | | +| approx_kl | 0.011805683 | +| clip_fraction | 0.33 | +| clip_range | 0.0732 | +| entropy_loss | -7.3 | +| explained_variance | 0.204 | +| learning_rate | 4.83e-05 | +| loss | -0.0359 | +| n_updates | 29668 | +| policy_gradient_loss | -0.0222 | +| value_loss | 0.000156 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.402 | +| time/ | | +| fps | 1416 | +| iterations | 3464 | +| time_elapsed | 5008 | +| total_timesteps | 7094272 | +| train/ | | +| approx_kl | 0.012357218 | +| clip_fraction | 0.311 | +| clip_range | 0.0732 | +| entropy_loss | -6.79 | +| explained_variance | 0.169 | +| learning_rate | 4.83e-05 | +| loss | -0.0309 | +| n_updates | 29672 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000234 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.394 | +| time/ | | +| fps | 1416 | +| iterations | 3465 | +| time_elapsed | 5010 | +| total_timesteps | 7096320 | +| train/ | | +| approx_kl | 0.013214953 | +| clip_fraction | 0.362 | +| clip_range | 0.0732 | +| entropy_loss | -6.95 | +| explained_variance | 0.042 | +| learning_rate | 4.83e-05 | +| loss | -0.0385 | +| n_updates | 29676 | +| policy_gradient_loss | -0.0225 | +| value_loss | 0.000113 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.393 | +| time/ | | +| fps | 1416 | +| iterations | 3466 | +| time_elapsed | 5011 | +| total_timesteps | 7098368 | +| train/ | | +| approx_kl | 0.010444047 | +| clip_fraction | 0.313 | +| clip_range | 0.0732 | +| entropy_loss | -6.48 | +| explained_variance | 0.525 | +| learning_rate | 4.83e-05 | +| loss | -0.0241 | +| n_updates | 29680 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000228 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.393 | +| time/ | | +| fps | 1416 | +| iterations | 3467 | +| time_elapsed | 5012 | +| total_timesteps | 7100416 | +| train/ | | +| approx_kl | 0.01373852 | +| clip_fraction | 0.31 | +| clip_range | 0.0732 | +| entropy_loss | -6.74 | +| explained_variance | 0.586 | +| learning_rate | 4.83e-05 | +| loss | -0.0291 | +| n_updates | 29684 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.00014 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.39 | +| time/ | | +| fps | 1416 | +| iterations | 3468 | +| time_elapsed | 5014 | +| total_timesteps | 7102464 | +| train/ | | +| approx_kl | 0.013467895 | +| clip_fraction | 0.358 | +| clip_range | 0.0732 | +| entropy_loss | -7.35 | +| explained_variance | -0.318 | +| learning_rate | 4.83e-05 | +| loss | -0.0414 | +| n_updates | 29688 | +| policy_gradient_loss | -0.0242 | +| value_loss | 0.000102 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.39 | +| time/ | | +| fps | 1416 | +| iterations | 3469 | +| time_elapsed | 5015 | +| total_timesteps | 7104512 | +| train/ | | +| approx_kl | 0.013072552 | +| clip_fraction | 0.344 | +| clip_range | 0.0732 | +| entropy_loss | -7.2 | +| explained_variance | 0.00344 | +| learning_rate | 4.83e-05 | +| loss | -0.0411 | +| n_updates | 29692 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000113 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.39 | +| time/ | | +| fps | 1416 | +| iterations | 3470 | +| time_elapsed | 5017 | +| total_timesteps | 7106560 | +| train/ | | +| approx_kl | 0.011067115 | +| clip_fraction | 0.325 | +| clip_range | 0.0732 | +| entropy_loss | -7.33 | +| explained_variance | 0.206 | +| learning_rate | 4.83e-05 | +| loss | -0.035 | +| n_updates | 29696 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000179 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.39 | +| time/ | | +| fps | 1416 | +| iterations | 3471 | +| time_elapsed | 5018 | +| total_timesteps | 7108608 | +| train/ | | +| approx_kl | 0.009955273 | +| clip_fraction | 0.306 | +| clip_range | 0.0732 | +| entropy_loss | -7.56 | +| explained_variance | 0.0325 | +| learning_rate | 4.83e-05 | +| loss | -0.0233 | +| n_updates | 29700 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.00011 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.39 | +| time/ | | +| fps | 1416 | +| iterations | 3472 | +| time_elapsed | 5019 | +| total_timesteps | 7110656 | +| train/ | | +| approx_kl | 0.011630623 | +| clip_fraction | 0.321 | +| clip_range | 0.0732 | +| entropy_loss | -7.45 | +| explained_variance | -0.0298 | +| learning_rate | 4.83e-05 | +| loss | -0.0318 | +| n_updates | 29704 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000216 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.39 | +| time/ | | +| fps | 1416 | +| iterations | 3473 | +| time_elapsed | 5021 | +| total_timesteps | 7112704 | +| train/ | | +| approx_kl | 0.011184715 | +| clip_fraction | 0.321 | +| clip_range | 0.0732 | +| entropy_loss | -7.02 | +| explained_variance | -0.0164 | +| learning_rate | 4.83e-05 | +| loss | -0.0303 | +| n_updates | 29708 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000202 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.39 | +| time/ | | +| fps | 1416 | +| iterations | 3474 | +| time_elapsed | 5022 | +| total_timesteps | 7114752 | +| train/ | | +| approx_kl | 0.0119622685 | +| clip_fraction | 0.331 | +| clip_range | 0.0732 | +| entropy_loss | -6.84 | +| explained_variance | 0.4 | +| learning_rate | 4.83e-05 | +| loss | -0.0361 | +| n_updates | 29712 | +| policy_gradient_loss | -0.0223 | +| value_loss | 0.000108 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.39 | +| time/ | | +| fps | 1416 | +| iterations | 3475 | +| time_elapsed | 5024 | +| total_timesteps | 7116800 | +| train/ | | +| approx_kl | 0.013123237 | +| clip_fraction | 0.328 | +| clip_range | 0.0732 | +| entropy_loss | -6.75 | +| explained_variance | 0.386 | +| learning_rate | 4.83e-05 | +| loss | -0.0299 | +| n_updates | 29716 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000209 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.389 | +| time/ | | +| fps | 1416 | +| iterations | 3476 | +| time_elapsed | 5025 | +| total_timesteps | 7118848 | +| train/ | | +| approx_kl | 0.010127623 | +| clip_fraction | 0.311 | +| clip_range | 0.0732 | +| entropy_loss | -6.89 | +| explained_variance | 0.485 | +| learning_rate | 4.83e-05 | +| loss | -0.0267 | +| n_updates | 29720 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000175 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.389 | +| time/ | | +| fps | 1416 | +| iterations | 3477 | +| time_elapsed | 5027 | +| total_timesteps | 7120896 | +| train/ | | +| approx_kl | 0.013673806 | +| clip_fraction | 0.331 | +| clip_range | 0.0732 | +| entropy_loss | -6.79 | +| explained_variance | 0.399 | +| learning_rate | 4.83e-05 | +| loss | -0.0309 | +| n_updates | 29724 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000184 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.396 | +| time/ | | +| fps | 1416 | +| iterations | 3478 | +| time_elapsed | 5028 | +| total_timesteps | 7122944 | +| train/ | | +| approx_kl | 0.0121395625 | +| clip_fraction | 0.355 | +| clip_range | 0.0732 | +| entropy_loss | -7.28 | +| explained_variance | 0.235 | +| learning_rate | 4.83e-05 | +| loss | -0.0352 | +| n_updates | 29728 | +| policy_gradient_loss | -0.023 | +| value_loss | 9.59e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.396 | +| time/ | | +| fps | 1416 | +| iterations | 3479 | +| time_elapsed | 5029 | +| total_timesteps | 7124992 | +| train/ | | +| approx_kl | 0.012165596 | +| clip_fraction | 0.33 | +| clip_range | 0.0732 | +| entropy_loss | -7.25 | +| explained_variance | 0.158 | +| learning_rate | 4.83e-05 | +| loss | -0.0296 | +| n_updates | 29732 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000303 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.402 | +| time/ | | +| fps | 1416 | +| iterations | 3480 | +| time_elapsed | 5031 | +| total_timesteps | 7127040 | +| train/ | | +| approx_kl | 0.011823429 | +| clip_fraction | 0.331 | +| clip_range | 0.0732 | +| entropy_loss | -7.21 | +| explained_variance | 0.235 | +| learning_rate | 4.83e-05 | +| loss | -0.0348 | +| n_updates | 29736 | +| policy_gradient_loss | -0.0223 | +| value_loss | 0.000141 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.402 | +| time/ | | +| fps | 1416 | +| iterations | 3481 | +| time_elapsed | 5032 | +| total_timesteps | 7129088 | +| train/ | | +| approx_kl | 0.012732577 | +| clip_fraction | 0.301 | +| clip_range | 0.0732 | +| entropy_loss | -7.1 | +| explained_variance | 0.302 | +| learning_rate | 4.83e-05 | +| loss | -0.028 | +| n_updates | 29740 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000267 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.412 | +| time/ | | +| fps | 1416 | +| iterations | 3482 | +| time_elapsed | 5034 | +| total_timesteps | 7131136 | +| train/ | | +| approx_kl | 0.012107013 | +| clip_fraction | 0.353 | +| clip_range | 0.0732 | +| entropy_loss | -7.34 | +| explained_variance | -0.2 | +| learning_rate | 4.83e-05 | +| loss | -0.0396 | +| n_updates | 29744 | +| policy_gradient_loss | -0.0226 | +| value_loss | 0.000111 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.416 | +| time/ | | +| fps | 1416 | +| iterations | 3483 | +| time_elapsed | 5035 | +| total_timesteps | 7133184 | +| train/ | | +| approx_kl | 0.010792711 | +| clip_fraction | 0.31 | +| clip_range | 0.0732 | +| entropy_loss | -7.26 | +| explained_variance | 0.0224 | +| learning_rate | 4.83e-05 | +| loss | -0.0268 | +| n_updates | 29748 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000391 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.414 | +| time/ | | +| fps | 1416 | +| iterations | 3484 | +| time_elapsed | 5037 | +| total_timesteps | 7135232 | +| train/ | | +| approx_kl | 0.011627823 | +| clip_fraction | 0.315 | +| clip_range | 0.0732 | +| entropy_loss | -6.54 | +| explained_variance | 0.519 | +| learning_rate | 4.83e-05 | +| loss | -0.0383 | +| n_updates | 29752 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000245 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.409 | +| time/ | | +| fps | 1416 | +| iterations | 3485 | +| time_elapsed | 5038 | +| total_timesteps | 7137280 | +| train/ | | +| approx_kl | 0.012300709 | +| clip_fraction | 0.362 | +| clip_range | 0.0732 | +| entropy_loss | -6.95 | +| explained_variance | 0.478 | +| learning_rate | 4.83e-05 | +| loss | -0.0406 | +| n_updates | 29756 | +| policy_gradient_loss | -0.023 | +| value_loss | 8.33e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.409 | +| time/ | | +| fps | 1416 | +| iterations | 3486 | +| time_elapsed | 5039 | +| total_timesteps | 7139328 | +| train/ | | +| approx_kl | 0.01346165 | +| clip_fraction | 0.348 | +| clip_range | 0.0732 | +| entropy_loss | -6.8 | +| explained_variance | 0.613 | +| learning_rate | 4.83e-05 | +| loss | -0.0346 | +| n_updates | 29760 | +| policy_gradient_loss | -0.022 | +| value_loss | 0.000113 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.409 | +| time/ | | +| fps | 1416 | +| iterations | 3487 | +| time_elapsed | 5041 | +| total_timesteps | 7141376 | +| train/ | | +| approx_kl | 0.012860808 | +| clip_fraction | 0.315 | +| clip_range | 0.0732 | +| entropy_loss | -7.04 | +| explained_variance | 0.569 | +| learning_rate | 4.83e-05 | +| loss | -0.0254 | +| n_updates | 29764 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000102 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.412 | +| time/ | | +| fps | 1416 | +| iterations | 3488 | +| time_elapsed | 5042 | +| total_timesteps | 7143424 | +| train/ | | +| approx_kl | 0.013908447 | +| clip_fraction | 0.345 | +| clip_range | 0.0732 | +| entropy_loss | -7.37 | +| explained_variance | -0.327 | +| learning_rate | 4.83e-05 | +| loss | -0.04 | +| n_updates | 29768 | +| policy_gradient_loss | -0.0225 | +| value_loss | 0.000108 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.409 | +| time/ | | +| fps | 1416 | +| iterations | 3489 | +| time_elapsed | 5044 | +| total_timesteps | 7145472 | +| train/ | | +| approx_kl | 0.0112919845 | +| clip_fraction | 0.284 | +| clip_range | 0.0732 | +| entropy_loss | -7.28 | +| explained_variance | -0.177 | +| learning_rate | 4.83e-05 | +| loss | -0.0266 | +| n_updates | 29772 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000234 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.408 | +| time/ | | +| fps | 1416 | +| iterations | 3490 | +| time_elapsed | 5045 | +| total_timesteps | 7147520 | +| train/ | | +| approx_kl | 0.012272799 | +| clip_fraction | 0.305 | +| clip_range | 0.0732 | +| entropy_loss | -7.3 | +| explained_variance | -0.0434 | +| learning_rate | 4.83e-05 | +| loss | -0.0335 | +| n_updates | 29776 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000121 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.408 | +| time/ | | +| fps | 1416 | +| iterations | 3491 | +| time_elapsed | 5046 | +| total_timesteps | 7149568 | +| train/ | | +| approx_kl | 0.012270872 | +| clip_fraction | 0.308 | +| clip_range | 0.0732 | +| entropy_loss | -7.12 | +| explained_variance | 0.145 | +| learning_rate | 4.83e-05 | +| loss | -0.0333 | +| n_updates | 29780 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000221 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.411 | +| time/ | | +| fps | 1416 | +| iterations | 3492 | +| time_elapsed | 5048 | +| total_timesteps | 7151616 | +| train/ | | +| approx_kl | 0.013429887 | +| clip_fraction | 0.343 | +| clip_range | 0.0732 | +| entropy_loss | -7.35 | +| explained_variance | -0.199 | +| learning_rate | 4.83e-05 | +| loss | -0.0353 | +| n_updates | 29784 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000113 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.411 | +| time/ | | +| fps | 1416 | +| iterations | 3493 | +| time_elapsed | 5049 | +| total_timesteps | 7153664 | +| train/ | | +| approx_kl | 0.012622088 | +| clip_fraction | 0.328 | +| clip_range | 0.0732 | +| entropy_loss | -7.25 | +| explained_variance | 0.145 | +| learning_rate | 4.83e-05 | +| loss | -0.0335 | +| n_updates | 29788 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000223 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.406 | +| time/ | | +| fps | 1416 | +| iterations | 3494 | +| time_elapsed | 5051 | +| total_timesteps | 7155712 | +| train/ | | +| approx_kl | 0.011207164 | +| clip_fraction | 0.332 | +| clip_range | 0.0732 | +| entropy_loss | -7.3 | +| explained_variance | -0.323 | +| learning_rate | 4.83e-05 | +| loss | -0.0349 | +| n_updates | 29792 | +| policy_gradient_loss | -0.0222 | +| value_loss | 8.6e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.399 | +| time/ | | +| fps | 1416 | +| iterations | 3495 | +| time_elapsed | 5052 | +| total_timesteps | 7157760 | +| train/ | | +| approx_kl | 0.011832604 | +| clip_fraction | 0.327 | +| clip_range | 0.0732 | +| entropy_loss | -6.25 | +| explained_variance | 0.474 | +| learning_rate | 4.83e-05 | +| loss | -0.0284 | +| n_updates | 29796 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000161 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.399 | +| time/ | | +| fps | 1416 | +| iterations | 3496 | +| time_elapsed | 5053 | +| total_timesteps | 7159808 | +| train/ | | +| approx_kl | 0.013981579 | +| clip_fraction | 0.335 | +| clip_range | 0.0732 | +| entropy_loss | -6.5 | +| explained_variance | 0.639 | +| learning_rate | 4.83e-05 | +| loss | -0.0326 | +| n_updates | 29800 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000131 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.399 | +| time/ | | +| fps | 1416 | +| iterations | 3497 | +| time_elapsed | 5055 | +| total_timesteps | 7161856 | +| train/ | | +| approx_kl | 0.015136988 | +| clip_fraction | 0.342 | +| clip_range | 0.0732 | +| entropy_loss | -7.23 | +| explained_variance | 0.152 | +| learning_rate | 4.83e-05 | +| loss | -0.0288 | +| n_updates | 29804 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000141 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.392 | +| time/ | | +| fps | 1416 | +| iterations | 3498 | +| time_elapsed | 5057 | +| total_timesteps | 7163904 | +| train/ | | +| approx_kl | 0.011527205 | +| clip_fraction | 0.346 | +| clip_range | 0.0732 | +| entropy_loss | -7.3 | +| explained_variance | -0.0376 | +| learning_rate | 4.83e-05 | +| loss | -0.0313 | +| n_updates | 29808 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.00014 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.392 | +| time/ | | +| fps | 1416 | +| iterations | 3499 | +| time_elapsed | 5058 | +| total_timesteps | 7165952 | +| train/ | | +| approx_kl | 0.008589257 | +| clip_fraction | 0.281 | +| clip_range | 0.0732 | +| entropy_loss | -7.06 | +| explained_variance | 0.162 | +| learning_rate | 4.83e-05 | +| loss | -0.0255 | +| n_updates | 29812 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000253 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.393 | +| time/ | | +| fps | 1416 | +| iterations | 3500 | +| time_elapsed | 5059 | +| total_timesteps | 7168000 | +| train/ | | +| approx_kl | 0.012286115 | +| clip_fraction | 0.361 | +| clip_range | 0.0732 | +| entropy_loss | -7.17 | +| explained_variance | 0.264 | +| learning_rate | 4.83e-05 | +| loss | -0.0393 | +| n_updates | 29816 | +| policy_gradient_loss | -0.023 | +| value_loss | 0.000111 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.392 | +| time/ | | +| fps | 1416 | +| iterations | 3501 | +| time_elapsed | 5061 | +| total_timesteps | 7170048 | +| train/ | | +| approx_kl | 0.011070153 | +| clip_fraction | 0.291 | +| clip_range | 0.0732 | +| entropy_loss | -7.27 | +| explained_variance | 0.15 | +| learning_rate | 4.83e-05 | +| loss | -0.0268 | +| n_updates | 29820 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000328 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.389 | +| time/ | | +| fps | 1416 | +| iterations | 3502 | +| time_elapsed | 5062 | +| total_timesteps | 7172096 | +| train/ | | +| approx_kl | 0.009689598 | +| clip_fraction | 0.305 | +| clip_range | 0.0732 | +| entropy_loss | -6.81 | +| explained_variance | 0.274 | +| learning_rate | 4.83e-05 | +| loss | -0.0271 | +| n_updates | 29824 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000321 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.39 | +| time/ | | +| fps | 1416 | +| iterations | 3503 | +| time_elapsed | 5064 | +| total_timesteps | 7174144 | +| train/ | | +| approx_kl | 0.01317392 | +| clip_fraction | 0.328 | +| clip_range | 0.0732 | +| entropy_loss | -6.34 | +| explained_variance | 0.352 | +| learning_rate | 4.83e-05 | +| loss | -0.0282 | +| n_updates | 29828 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000427 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.39 | +| time/ | | +| fps | 1416 | +| iterations | 3504 | +| time_elapsed | 5065 | +| total_timesteps | 7176192 | +| train/ | | +| approx_kl | 0.014574388 | +| clip_fraction | 0.37 | +| clip_range | 0.0732 | +| entropy_loss | -7 | +| explained_variance | 0.264 | +| learning_rate | 4.83e-05 | +| loss | -0.0413 | +| n_updates | 29832 | +| policy_gradient_loss | -0.0241 | +| value_loss | 0.000159 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.39 | +| time/ | | +| fps | 1416 | +| iterations | 3505 | +| time_elapsed | 5066 | +| total_timesteps | 7178240 | +| train/ | | +| approx_kl | 0.014412357 | +| clip_fraction | 0.356 | +| clip_range | 0.0732 | +| entropy_loss | -7.39 | +| explained_variance | -0.124 | +| learning_rate | 4.83e-05 | +| loss | -0.0366 | +| n_updates | 29836 | +| policy_gradient_loss | -0.0235 | +| value_loss | 0.000121 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.39 | +| time/ | | +| fps | 1416 | +| iterations | 3506 | +| time_elapsed | 5068 | +| total_timesteps | 7180288 | +| train/ | | +| approx_kl | 0.0131291365 | +| clip_fraction | 0.359 | +| clip_range | 0.0732 | +| entropy_loss | -7.32 | +| explained_variance | -0.198 | +| learning_rate | 4.83e-05 | +| loss | -0.0388 | +| n_updates | 29840 | +| policy_gradient_loss | -0.0232 | +| value_loss | 0.000123 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.391 | +| time/ | | +| fps | 1416 | +| iterations | 3507 | +| time_elapsed | 5069 | +| total_timesteps | 7182336 | +| train/ | | +| approx_kl | 0.014566092 | +| clip_fraction | 0.35 | +| clip_range | 0.0732 | +| entropy_loss | -7.37 | +| explained_variance | -0.0662 | +| learning_rate | 4.83e-05 | +| loss | -0.0353 | +| n_updates | 29844 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000129 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.396 | +| time/ | | +| fps | 1416 | +| iterations | 3508 | +| time_elapsed | 5071 | +| total_timesteps | 7184384 | +| train/ | | +| approx_kl | 0.012840338 | +| clip_fraction | 0.322 | +| clip_range | 0.0732 | +| entropy_loss | -7.08 | +| explained_variance | 0.226 | +| learning_rate | 4.83e-05 | +| loss | -0.0253 | +| n_updates | 29848 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000241 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.393 | +| time/ | | +| fps | 1416 | +| iterations | 3509 | +| time_elapsed | 5072 | +| total_timesteps | 7186432 | +| train/ | | +| approx_kl | 0.011304504 | +| clip_fraction | 0.336 | +| clip_range | 0.0732 | +| entropy_loss | -6.98 | +| explained_variance | 0.262 | +| learning_rate | 4.83e-05 | +| loss | -0.0322 | +| n_updates | 29852 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000155 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.396 | +| time/ | | +| fps | 1416 | +| iterations | 3510 | +| time_elapsed | 5074 | +| total_timesteps | 7188480 | +| train/ | | +| approx_kl | 0.013349766 | +| clip_fraction | 0.333 | +| clip_range | 0.0732 | +| entropy_loss | -7.18 | +| explained_variance | 0.421 | +| learning_rate | 4.83e-05 | +| loss | -0.0348 | +| n_updates | 29856 | +| policy_gradient_loss | -0.0215 | +| value_loss | 7.63e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.392 | +| time/ | | +| fps | 1416 | +| iterations | 3511 | +| time_elapsed | 5075 | +| total_timesteps | 7190528 | +| train/ | | +| approx_kl | 0.010060517 | +| clip_fraction | 0.33 | +| clip_range | 0.0732 | +| entropy_loss | -7.07 | +| explained_variance | 0.261 | +| learning_rate | 4.83e-05 | +| loss | -0.0287 | +| n_updates | 29860 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000206 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.392 | +| time/ | | +| fps | 1416 | +| iterations | 3512 | +| time_elapsed | 5076 | +| total_timesteps | 7192576 | +| train/ | | +| approx_kl | 0.012252974 | +| clip_fraction | 0.347 | +| clip_range | 0.0732 | +| entropy_loss | -6.56 | +| explained_variance | 0.652 | +| learning_rate | 4.83e-05 | +| loss | -0.0309 | +| n_updates | 29864 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000153 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.399 | +| time/ | | +| fps | 1416 | +| iterations | 3513 | +| time_elapsed | 5078 | +| total_timesteps | 7194624 | +| train/ | | +| approx_kl | 0.010512318 | +| clip_fraction | 0.346 | +| clip_range | 0.0732 | +| entropy_loss | -7.31 | +| explained_variance | -0.0416 | +| learning_rate | 4.83e-05 | +| loss | -0.0303 | +| n_updates | 29868 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000186 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.396 | +| time/ | | +| fps | 1416 | +| iterations | 3514 | +| time_elapsed | 5079 | +| total_timesteps | 7196672 | +| train/ | | +| approx_kl | 0.013457957 | +| clip_fraction | 0.31 | +| clip_range | 0.0732 | +| entropy_loss | -6.83 | +| explained_variance | 0.391 | +| learning_rate | 4.83e-05 | +| loss | -0.0335 | +| n_updates | 29872 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000211 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.396 | +| time/ | | +| fps | 1416 | +| iterations | 3515 | +| time_elapsed | 5081 | +| total_timesteps | 7198720 | +| train/ | | +| approx_kl | 0.012191198 | +| clip_fraction | 0.348 | +| clip_range | 0.0732 | +| entropy_loss | -6.96 | +| explained_variance | 0.368 | +| learning_rate | 4.83e-05 | +| loss | -0.0331 | +| n_updates | 29876 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000197 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.396 | +| time/ | | +| fps | 1416 | +| iterations | 3516 | +| time_elapsed | 5082 | +| total_timesteps | 7200768 | +| train/ | | +| approx_kl | 0.011252172 | +| clip_fraction | 0.329 | +| clip_range | 0.0732 | +| entropy_loss | -6.89 | +| explained_variance | 0.437 | +| learning_rate | 4.83e-05 | +| loss | -0.0316 | +| n_updates | 29880 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.00016 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.396 | +| time/ | | +| fps | 1416 | +| iterations | 3517 | +| time_elapsed | 5084 | +| total_timesteps | 7202816 | +| train/ | | +| approx_kl | 0.013496766 | +| clip_fraction | 0.354 | +| clip_range | 0.0732 | +| entropy_loss | -7.11 | +| explained_variance | -0.0764 | +| learning_rate | 4.83e-05 | +| loss | -0.0342 | +| n_updates | 29884 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000179 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.393 | +| time/ | | +| fps | 1416 | +| iterations | 3518 | +| time_elapsed | 5085 | +| total_timesteps | 7204864 | +| train/ | | +| approx_kl | 0.011079147 | +| clip_fraction | 0.321 | +| clip_range | 0.0732 | +| entropy_loss | -7.29 | +| explained_variance | -0.0638 | +| learning_rate | 4.83e-05 | +| loss | -0.0291 | +| n_updates | 29888 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000177 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.39 | +| time/ | | +| fps | 1416 | +| iterations | 3519 | +| time_elapsed | 5086 | +| total_timesteps | 7206912 | +| train/ | | +| approx_kl | 0.0090725515 | +| clip_fraction | 0.301 | +| clip_range | 0.0732 | +| entropy_loss | -7.07 | +| explained_variance | 0.027 | +| learning_rate | 4.83e-05 | +| loss | -0.0325 | +| n_updates | 29892 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.000294 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.39 | +| time/ | | +| fps | 1416 | +| iterations | 3520 | +| time_elapsed | 5088 | +| total_timesteps | 7208960 | +| train/ | | +| approx_kl | 0.010321891 | +| clip_fraction | 0.304 | +| clip_range | 0.0732 | +| entropy_loss | -7.08 | +| explained_variance | 0.246 | +| learning_rate | 4.83e-05 | +| loss | -0.0363 | +| n_updates | 29896 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.00022 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.388 | +| time/ | | +| fps | 1416 | +| iterations | 3521 | +| time_elapsed | 5089 | +| total_timesteps | 7211008 | +| train/ | | +| approx_kl | 0.012882255 | +| clip_fraction | 0.374 | +| clip_range | 0.0732 | +| entropy_loss | -7.4 | +| explained_variance | -0.305 | +| learning_rate | 4.83e-05 | +| loss | -0.0375 | +| n_updates | 29900 | +| policy_gradient_loss | -0.0239 | +| value_loss | 8.24e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.388 | +| time/ | | +| fps | 1416 | +| iterations | 3522 | +| time_elapsed | 5091 | +| total_timesteps | 7213056 | +| train/ | | +| approx_kl | 0.009890967 | +| clip_fraction | 0.296 | +| clip_range | 0.0732 | +| entropy_loss | -7.17 | +| explained_variance | 0.452 | +| learning_rate | 4.83e-05 | +| loss | -0.028 | +| n_updates | 29904 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000187 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.392 | +| time/ | | +| fps | 1416 | +| iterations | 3523 | +| time_elapsed | 5092 | +| total_timesteps | 7215104 | +| train/ | | +| approx_kl | 0.009829863 | +| clip_fraction | 0.328 | +| clip_range | 0.0732 | +| entropy_loss | -7.31 | +| explained_variance | -0.146 | +| learning_rate | 4.83e-05 | +| loss | -0.0279 | +| n_updates | 29908 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000132 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.39 | +| time/ | | +| fps | 1416 | +| iterations | 3524 | +| time_elapsed | 5094 | +| total_timesteps | 7217152 | +| train/ | | +| approx_kl | 0.01208926 | +| clip_fraction | 0.331 | +| clip_range | 0.0732 | +| entropy_loss | -6.4 | +| explained_variance | 0.312 | +| learning_rate | 4.83e-05 | +| loss | -0.0298 | +| n_updates | 29912 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.00044 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1416 | +| iterations | 3525 | +| time_elapsed | 5095 | +| total_timesteps | 7219200 | +| train/ | | +| approx_kl | 0.012486624 | +| clip_fraction | 0.348 | +| clip_range | 0.0732 | +| entropy_loss | -6.57 | +| explained_variance | 0.426 | +| learning_rate | 4.83e-05 | +| loss | -0.0329 | +| n_updates | 29916 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000184 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1416 | +| iterations | 3526 | +| time_elapsed | 5096 | +| total_timesteps | 7221248 | +| train/ | | +| approx_kl | 0.011438873 | +| clip_fraction | 0.361 | +| clip_range | 0.0732 | +| entropy_loss | -7.24 | +| explained_variance | 0.186 | +| learning_rate | 4.83e-05 | +| loss | -0.0388 | +| n_updates | 29920 | +| policy_gradient_loss | -0.022 | +| value_loss | 0.000159 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.388 | +| time/ | | +| fps | 1416 | +| iterations | 3527 | +| time_elapsed | 5098 | +| total_timesteps | 7223296 | +| train/ | | +| approx_kl | 0.014084508 | +| clip_fraction | 0.352 | +| clip_range | 0.0732 | +| entropy_loss | -7 | +| explained_variance | 0.348 | +| learning_rate | 4.83e-05 | +| loss | -0.0323 | +| n_updates | 29924 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000239 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.388 | +| time/ | | +| fps | 1416 | +| iterations | 3528 | +| time_elapsed | 5099 | +| total_timesteps | 7225344 | +| train/ | | +| approx_kl | 0.0142803015 | +| clip_fraction | 0.331 | +| clip_range | 0.0732 | +| entropy_loss | -7.24 | +| explained_variance | 0.215 | +| learning_rate | 4.83e-05 | +| loss | -0.0272 | +| n_updates | 29928 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000227 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.388 | +| time/ | | +| fps | 1416 | +| iterations | 3529 | +| time_elapsed | 5101 | +| total_timesteps | 7227392 | +| train/ | | +| approx_kl | 0.013015785 | +| clip_fraction | 0.35 | +| clip_range | 0.0732 | +| entropy_loss | -7.4 | +| explained_variance | -0.178 | +| learning_rate | 4.83e-05 | +| loss | -0.0321 | +| n_updates | 29932 | +| policy_gradient_loss | -0.0228 | +| value_loss | 0.000118 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.389 | +| time/ | | +| fps | 1416 | +| iterations | 3530 | +| time_elapsed | 5102 | +| total_timesteps | 7229440 | +| train/ | | +| approx_kl | 0.012501806 | +| clip_fraction | 0.336 | +| clip_range | 0.0732 | +| entropy_loss | -7.37 | +| explained_variance | -0.232 | +| learning_rate | 4.83e-05 | +| loss | -0.0419 | +| n_updates | 29936 | +| policy_gradient_loss | -0.022 | +| value_loss | 0.000113 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.39 | +| time/ | | +| fps | 1416 | +| iterations | 3531 | +| time_elapsed | 5104 | +| total_timesteps | 7231488 | +| train/ | | +| approx_kl | 0.010581236 | +| clip_fraction | 0.323 | +| clip_range | 0.0732 | +| entropy_loss | -7.47 | +| explained_variance | -0.0607 | +| learning_rate | 4.83e-05 | +| loss | -0.0324 | +| n_updates | 29940 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000216 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1416 | +| iterations | 3532 | +| time_elapsed | 5105 | +| total_timesteps | 7233536 | +| train/ | | +| approx_kl | 0.0106839 | +| clip_fraction | 0.317 | +| clip_range | 0.0732 | +| entropy_loss | -6.75 | +| explained_variance | 0.581 | +| learning_rate | 4.83e-05 | +| loss | -0.0314 | +| n_updates | 29944 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000144 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1416 | +| iterations | 3533 | +| time_elapsed | 5107 | +| total_timesteps | 7235584 | +| train/ | | +| approx_kl | 0.012419654 | +| clip_fraction | 0.381 | +| clip_range | 0.0732 | +| entropy_loss | -6.94 | +| explained_variance | 0.507 | +| learning_rate | 4.83e-05 | +| loss | -0.0414 | +| n_updates | 29948 | +| policy_gradient_loss | -0.0265 | +| value_loss | 5.11e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.385 | +| time/ | | +| fps | 1416 | +| iterations | 3534 | +| time_elapsed | 5108 | +| total_timesteps | 7237632 | +| train/ | | +| approx_kl | 0.011010434 | +| clip_fraction | 0.33 | +| clip_range | 0.0732 | +| entropy_loss | -6.86 | +| explained_variance | 0.383 | +| learning_rate | 4.83e-05 | +| loss | -0.0332 | +| n_updates | 29952 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000194 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.385 | +| time/ | | +| fps | 1416 | +| iterations | 3535 | +| time_elapsed | 5110 | +| total_timesteps | 7239680 | +| train/ | | +| approx_kl | 0.011216581 | +| clip_fraction | 0.301 | +| clip_range | 0.0732 | +| entropy_loss | -6.69 | +| explained_variance | 0.433 | +| learning_rate | 4.83e-05 | +| loss | -0.0283 | +| n_updates | 29956 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000222 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.391 | +| time/ | | +| fps | 1416 | +| iterations | 3536 | +| time_elapsed | 5111 | +| total_timesteps | 7241728 | +| train/ | | +| approx_kl | 0.0146606 | +| clip_fraction | 0.362 | +| clip_range | 0.0732 | +| entropy_loss | -7.07 | +| explained_variance | 0.594 | +| learning_rate | 4.83e-05 | +| loss | -0.0369 | +| n_updates | 29960 | +| policy_gradient_loss | -0.0231 | +| value_loss | 7.22e-05 | +--------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.39 | +| time/ | | +| fps | 1416 | +| iterations | 3537 | +| time_elapsed | 5112 | +| total_timesteps | 7243776 | +| train/ | | +| approx_kl | 0.01201486 | +| clip_fraction | 0.309 | +| clip_range | 0.0732 | +| entropy_loss | -7.2 | +| explained_variance | 0.277 | +| learning_rate | 4.83e-05 | +| loss | -0.0285 | +| n_updates | 29964 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000175 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.39 | +| time/ | | +| fps | 1416 | +| iterations | 3538 | +| time_elapsed | 5114 | +| total_timesteps | 7245824 | +| train/ | | +| approx_kl | 0.012066091 | +| clip_fraction | 0.314 | +| clip_range | 0.0732 | +| entropy_loss | -7.26 | +| explained_variance | 0.314 | +| learning_rate | 4.83e-05 | +| loss | -0.0258 | +| n_updates | 29968 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000152 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.386 | +| time/ | | +| fps | 1416 | +| iterations | 3539 | +| time_elapsed | 5115 | +| total_timesteps | 7247872 | +| train/ | | +| approx_kl | 0.012205407 | +| clip_fraction | 0.329 | +| clip_range | 0.0732 | +| entropy_loss | -7.24 | +| explained_variance | -0.0458 | +| learning_rate | 4.83e-05 | +| loss | -0.0337 | +| n_updates | 29972 | +| policy_gradient_loss | -0.0204 | +| value_loss | 9.22e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.391 | +| time/ | | +| fps | 1416 | +| iterations | 3540 | +| time_elapsed | 5117 | +| total_timesteps | 7249920 | +| train/ | | +| approx_kl | 0.010857629 | +| clip_fraction | 0.309 | +| clip_range | 0.0732 | +| entropy_loss | -7.05 | +| explained_variance | 0.211 | +| learning_rate | 4.83e-05 | +| loss | -0.0303 | +| n_updates | 29976 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000185 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.393 | +| time/ | | +| fps | 1416 | +| iterations | 3541 | +| time_elapsed | 5118 | +| total_timesteps | 7251968 | +| train/ | | +| approx_kl | 0.010780212 | +| clip_fraction | 0.321 | +| clip_range | 0.0732 | +| entropy_loss | -6.83 | +| explained_variance | 0.295 | +| learning_rate | 4.83e-05 | +| loss | -0.0285 | +| n_updates | 29980 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.00031 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.395 | +| time/ | | +| fps | 1416 | +| iterations | 3542 | +| time_elapsed | 5120 | +| total_timesteps | 7254016 | +| train/ | | +| approx_kl | 0.011336788 | +| clip_fraction | 0.351 | +| clip_range | 0.0732 | +| entropy_loss | -6.79 | +| explained_variance | 0.425 | +| learning_rate | 4.83e-05 | +| loss | -0.0253 | +| n_updates | 29984 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.00018 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.395 | +| time/ | | +| fps | 1416 | +| iterations | 3543 | +| time_elapsed | 5121 | +| total_timesteps | 7256064 | +| train/ | | +| approx_kl | 0.009921325 | +| clip_fraction | 0.313 | +| clip_range | 0.0732 | +| entropy_loss | -7.12 | +| explained_variance | -0.11 | +| learning_rate | 4.83e-05 | +| loss | -0.0251 | +| n_updates | 29988 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000227 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.389 | +| time/ | | +| fps | 1416 | +| iterations | 3544 | +| time_elapsed | 5122 | +| total_timesteps | 7258112 | +| train/ | | +| approx_kl | 0.010316352 | +| clip_fraction | 0.31 | +| clip_range | 0.0732 | +| entropy_loss | -7.26 | +| explained_variance | 0.197 | +| learning_rate | 4.83e-05 | +| loss | -0.0315 | +| n_updates | 29992 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000218 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.387 | +| time/ | | +| fps | 1416 | +| iterations | 3545 | +| time_elapsed | 5124 | +| total_timesteps | 7260160 | +| train/ | | +| approx_kl | 0.013800094 | +| clip_fraction | 0.374 | +| clip_range | 0.0732 | +| entropy_loss | -7.13 | +| explained_variance | 0.359 | +| learning_rate | 4.83e-05 | +| loss | -0.0379 | +| n_updates | 29996 | +| policy_gradient_loss | -0.0234 | +| value_loss | 8.83e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.387 | +| time/ | | +| fps | 1416 | +| iterations | 3546 | +| time_elapsed | 5125 | +| total_timesteps | 7262208 | +| train/ | | +| approx_kl | 0.0122302715 | +| clip_fraction | 0.319 | +| clip_range | 0.0732 | +| entropy_loss | -6.95 | +| explained_variance | 0.271 | +| learning_rate | 4.83e-05 | +| loss | -0.028 | +| n_updates | 30000 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000221 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.385 | +| time/ | | +| fps | 1416 | +| iterations | 3547 | +| time_elapsed | 5127 | +| total_timesteps | 7264256 | +| train/ | | +| approx_kl | 0.010950379 | +| clip_fraction | 0.339 | +| clip_range | 0.0732 | +| entropy_loss | -7.18 | +| explained_variance | 0.218 | +| learning_rate | 4.83e-05 | +| loss | -0.0357 | +| n_updates | 30004 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.00018 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1416 | +| iterations | 3548 | +| time_elapsed | 5128 | +| total_timesteps | 7266304 | +| train/ | | +| approx_kl | 0.010197403 | +| clip_fraction | 0.346 | +| clip_range | 0.0732 | +| entropy_loss | -7.33 | +| explained_variance | 0.0246 | +| learning_rate | 4.83e-05 | +| loss | -0.0355 | +| n_updates | 30008 | +| policy_gradient_loss | -0.0219 | +| value_loss | 0.000117 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1416 | +| iterations | 3549 | +| time_elapsed | 5130 | +| total_timesteps | 7268352 | +| train/ | | +| approx_kl | 0.011752127 | +| clip_fraction | 0.317 | +| clip_range | 0.0732 | +| entropy_loss | -6.57 | +| explained_variance | 0.654 | +| learning_rate | 4.83e-05 | +| loss | -0.0286 | +| n_updates | 30012 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000115 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1416 | +| iterations | 3550 | +| time_elapsed | 5131 | +| total_timesteps | 7270400 | +| train/ | | +| approx_kl | 0.012877813 | +| clip_fraction | 0.329 | +| clip_range | 0.0732 | +| entropy_loss | -6.74 | +| explained_variance | 0.311 | +| learning_rate | 4.83e-05 | +| loss | -0.0304 | +| n_updates | 30016 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000149 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1416 | +| iterations | 3551 | +| time_elapsed | 5133 | +| total_timesteps | 7272448 | +| train/ | | +| approx_kl | 0.010555165 | +| clip_fraction | 0.319 | +| clip_range | 0.0732 | +| entropy_loss | -6.97 | +| explained_variance | 0.184 | +| learning_rate | 4.83e-05 | +| loss | -0.026 | +| n_updates | 30020 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000233 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1416 | +| iterations | 3552 | +| time_elapsed | 5134 | +| total_timesteps | 7274496 | +| train/ | | +| approx_kl | 0.009518862 | +| clip_fraction | 0.316 | +| clip_range | 0.0732 | +| entropy_loss | -7.37 | +| explained_variance | -0.237 | +| learning_rate | 4.83e-05 | +| loss | -0.0315 | +| n_updates | 30024 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000148 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1416 | +| iterations | 3553 | +| time_elapsed | 5135 | +| total_timesteps | 7276544 | +| train/ | | +| approx_kl | 0.013292821 | +| clip_fraction | 0.346 | +| clip_range | 0.0732 | +| entropy_loss | -7.35 | +| explained_variance | -0.183 | +| learning_rate | 4.83e-05 | +| loss | -0.0354 | +| n_updates | 30028 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000122 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1416 | +| iterations | 3554 | +| time_elapsed | 5137 | +| total_timesteps | 7278592 | +| train/ | | +| approx_kl | 0.012585723 | +| clip_fraction | 0.339 | +| clip_range | 0.0732 | +| entropy_loss | -7.2 | +| explained_variance | 0.328 | +| learning_rate | 4.83e-05 | +| loss | -0.0359 | +| n_updates | 30032 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000153 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1416 | +| iterations | 3555 | +| time_elapsed | 5138 | +| total_timesteps | 7280640 | +| train/ | | +| approx_kl | 0.01351396 | +| clip_fraction | 0.33 | +| clip_range | 0.0732 | +| entropy_loss | -7.38 | +| explained_variance | -0.106 | +| learning_rate | 4.83e-05 | +| loss | -0.038 | +| n_updates | 30036 | +| policy_gradient_loss | -0.0215 | +| value_loss | 9.47e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1416 | +| iterations | 3556 | +| time_elapsed | 5140 | +| total_timesteps | 7282688 | +| train/ | | +| approx_kl | 0.011238733 | +| clip_fraction | 0.305 | +| clip_range | 0.0732 | +| entropy_loss | -6.51 | +| explained_variance | 0.544 | +| learning_rate | 4.83e-05 | +| loss | -0.0277 | +| n_updates | 30040 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000237 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1416 | +| iterations | 3557 | +| time_elapsed | 5141 | +| total_timesteps | 7284736 | +| train/ | | +| approx_kl | 0.011765426 | +| clip_fraction | 0.332 | +| clip_range | 0.0732 | +| entropy_loss | -6.88 | +| explained_variance | 0.33 | +| learning_rate | 4.83e-05 | +| loss | -0.0327 | +| n_updates | 30044 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000136 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1416 | +| iterations | 3558 | +| time_elapsed | 5143 | +| total_timesteps | 7286784 | +| train/ | | +| approx_kl | 0.013875852 | +| clip_fraction | 0.349 | +| clip_range | 0.0732 | +| entropy_loss | -7.3 | +| explained_variance | -0.0807 | +| learning_rate | 4.83e-05 | +| loss | -0.0358 | +| n_updates | 30048 | +| policy_gradient_loss | -0.0218 | +| value_loss | 9.41e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1416 | +| iterations | 3559 | +| time_elapsed | 5144 | +| total_timesteps | 7288832 | +| train/ | | +| approx_kl | 0.014343174 | +| clip_fraction | 0.365 | +| clip_range | 0.0732 | +| entropy_loss | -7.24 | +| explained_variance | 0.629 | +| learning_rate | 4.83e-05 | +| loss | -0.0462 | +| n_updates | 30052 | +| policy_gradient_loss | -0.026 | +| value_loss | 3.83e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1416 | +| iterations | 3560 | +| time_elapsed | 5146 | +| total_timesteps | 7290880 | +| train/ | | +| approx_kl | 0.012752492 | +| clip_fraction | 0.31 | +| clip_range | 0.0732 | +| entropy_loss | -7.05 | +| explained_variance | 0.269 | +| learning_rate | 4.83e-05 | +| loss | -0.0308 | +| n_updates | 30056 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000223 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1416 | +| iterations | 3561 | +| time_elapsed | 5147 | +| total_timesteps | 7292928 | +| train/ | | +| approx_kl | 0.012557255 | +| clip_fraction | 0.33 | +| clip_range | 0.0732 | +| entropy_loss | -6.56 | +| explained_variance | 0.51 | +| learning_rate | 4.83e-05 | +| loss | -0.029 | +| n_updates | 30060 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000154 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.385 | +| time/ | | +| fps | 1416 | +| iterations | 3562 | +| time_elapsed | 5148 | +| total_timesteps | 7294976 | +| train/ | | +| approx_kl | 0.013398549 | +| clip_fraction | 0.335 | +| clip_range | 0.0732 | +| entropy_loss | -6.74 | +| explained_variance | 0.568 | +| learning_rate | 4.83e-05 | +| loss | -0.0378 | +| n_updates | 30064 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000121 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1416 | +| iterations | 3563 | +| time_elapsed | 5150 | +| total_timesteps | 7297024 | +| train/ | | +| approx_kl | 0.01123826 | +| clip_fraction | 0.316 | +| clip_range | 0.0732 | +| entropy_loss | -7.3 | +| explained_variance | 0.0462 | +| learning_rate | 4.83e-05 | +| loss | -0.0344 | +| n_updates | 30068 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000188 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1416 | +| iterations | 3564 | +| time_elapsed | 5151 | +| total_timesteps | 7299072 | +| train/ | | +| approx_kl | 0.012531295 | +| clip_fraction | 0.327 | +| clip_range | 0.0732 | +| entropy_loss | -7.09 | +| explained_variance | 0.221 | +| learning_rate | 4.83e-05 | +| loss | -0.03 | +| n_updates | 30072 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.00024 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1416 | +| iterations | 3565 | +| time_elapsed | 5153 | +| total_timesteps | 7301120 | +| train/ | | +| approx_kl | 0.014132131 | +| clip_fraction | 0.354 | +| clip_range | 0.0732 | +| entropy_loss | -7.14 | +| explained_variance | 0.316 | +| learning_rate | 4.83e-05 | +| loss | -0.0341 | +| n_updates | 30076 | +| policy_gradient_loss | -0.023 | +| value_loss | 0.000175 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1416 | +| iterations | 3566 | +| time_elapsed | 5154 | +| total_timesteps | 7303168 | +| train/ | | +| approx_kl | 0.01126351 | +| clip_fraction | 0.307 | +| clip_range | 0.0732 | +| entropy_loss | -6.81 | +| explained_variance | 0.464 | +| learning_rate | 4.83e-05 | +| loss | -0.028 | +| n_updates | 30080 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000281 | +---------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1416 | +| iterations | 3567 | +| time_elapsed | 5155 | +| total_timesteps | 7305216 | +| train/ | | +| approx_kl | 0.0121483 | +| clip_fraction | 0.351 | +| clip_range | 0.0732 | +| entropy_loss | -7.11 | +| explained_variance | 0.231 | +| learning_rate | 4.83e-05 | +| loss | -0.0347 | +| n_updates | 30084 | +| policy_gradient_loss | -0.0224 | +| value_loss | 0.00014 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1416 | +| iterations | 3568 | +| time_elapsed | 5157 | +| total_timesteps | 7307264 | +| train/ | | +| approx_kl | 0.012262605 | +| clip_fraction | 0.345 | +| clip_range | 0.0732 | +| entropy_loss | -7.33 | +| explained_variance | -0.179 | +| learning_rate | 4.83e-05 | +| loss | -0.0365 | +| n_updates | 30088 | +| policy_gradient_loss | -0.0237 | +| value_loss | 0.000135 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1416 | +| iterations | 3569 | +| time_elapsed | 5158 | +| total_timesteps | 7309312 | +| train/ | | +| approx_kl | 0.011979427 | +| clip_fraction | 0.351 | +| clip_range | 0.0732 | +| entropy_loss | -6.95 | +| explained_variance | 0.608 | +| learning_rate | 4.83e-05 | +| loss | -0.0357 | +| n_updates | 30092 | +| policy_gradient_loss | -0.024 | +| value_loss | 7.05e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1416 | +| iterations | 3570 | +| time_elapsed | 5160 | +| total_timesteps | 7311360 | +| train/ | | +| approx_kl | 0.011500772 | +| clip_fraction | 0.318 | +| clip_range | 0.0732 | +| entropy_loss | -6.84 | +| explained_variance | 0.365 | +| learning_rate | 4.83e-05 | +| loss | -0.0284 | +| n_updates | 30096 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000259 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1416 | +| iterations | 3571 | +| time_elapsed | 5161 | +| total_timesteps | 7313408 | +| train/ | | +| approx_kl | 0.014271882 | +| clip_fraction | 0.339 | +| clip_range | 0.0732 | +| entropy_loss | -7 | +| explained_variance | 0.424 | +| learning_rate | 4.83e-05 | +| loss | -0.035 | +| n_updates | 30100 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000146 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1416 | +| iterations | 3572 | +| time_elapsed | 5163 | +| total_timesteps | 7315456 | +| train/ | | +| approx_kl | 0.013104716 | +| clip_fraction | 0.338 | +| clip_range | 0.0732 | +| entropy_loss | -7.02 | +| explained_variance | 0.143 | +| learning_rate | 4.83e-05 | +| loss | -0.037 | +| n_updates | 30104 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000207 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1416 | +| iterations | 3573 | +| time_elapsed | 5164 | +| total_timesteps | 7317504 | +| train/ | | +| approx_kl | 0.011845525 | +| clip_fraction | 0.348 | +| clip_range | 0.0732 | +| entropy_loss | -7.23 | +| explained_variance | 0.169 | +| learning_rate | 4.83e-05 | +| loss | -0.034 | +| n_updates | 30108 | +| policy_gradient_loss | -0.0221 | +| value_loss | 0.000187 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1416 | +| iterations | 3574 | +| time_elapsed | 5165 | +| total_timesteps | 7319552 | +| train/ | | +| approx_kl | 0.012753177 | +| clip_fraction | 0.329 | +| clip_range | 0.0732 | +| entropy_loss | -6.68 | +| explained_variance | 0.43 | +| learning_rate | 4.83e-05 | +| loss | -0.0299 | +| n_updates | 30112 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000209 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1416 | +| iterations | 3575 | +| time_elapsed | 5167 | +| total_timesteps | 7321600 | +| train/ | | +| approx_kl | 0.015455119 | +| clip_fraction | 0.351 | +| clip_range | 0.0732 | +| entropy_loss | -6.97 | +| explained_variance | 0.22 | +| learning_rate | 4.83e-05 | +| loss | -0.0433 | +| n_updates | 30116 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000199 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1416 | +| iterations | 3576 | +| time_elapsed | 5168 | +| total_timesteps | 7323648 | +| train/ | | +| approx_kl | 0.0129371025 | +| clip_fraction | 0.343 | +| clip_range | 0.0732 | +| entropy_loss | -7.07 | +| explained_variance | 0.298 | +| learning_rate | 4.83e-05 | +| loss | -0.0373 | +| n_updates | 30120 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000141 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1416 | +| iterations | 3577 | +| time_elapsed | 5170 | +| total_timesteps | 7325696 | +| train/ | | +| approx_kl | 0.011155007 | +| clip_fraction | 0.316 | +| clip_range | 0.0732 | +| entropy_loss | -7.25 | +| explained_variance | 0.244 | +| learning_rate | 4.83e-05 | +| loss | -0.0346 | +| n_updates | 30124 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000149 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1416 | +| iterations | 3578 | +| time_elapsed | 5171 | +| total_timesteps | 7327744 | +| train/ | | +| approx_kl | 0.013894469 | +| clip_fraction | 0.339 | +| clip_range | 0.0732 | +| entropy_loss | -7.12 | +| explained_variance | 0.361 | +| learning_rate | 4.83e-05 | +| loss | -0.0365 | +| n_updates | 30128 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000115 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1416 | +| iterations | 3579 | +| time_elapsed | 5173 | +| total_timesteps | 7329792 | +| train/ | | +| approx_kl | 0.011916724 | +| clip_fraction | 0.309 | +| clip_range | 0.0732 | +| entropy_loss | -7.25 | +| explained_variance | -0.177 | +| learning_rate | 4.83e-05 | +| loss | -0.0262 | +| n_updates | 30132 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000167 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1416 | +| iterations | 3580 | +| time_elapsed | 5174 | +| total_timesteps | 7331840 | +| train/ | | +| approx_kl | 0.013379273 | +| clip_fraction | 0.338 | +| clip_range | 0.0732 | +| entropy_loss | -7.17 | +| explained_variance | 0.295 | +| learning_rate | 4.83e-05 | +| loss | -0.0355 | +| n_updates | 30136 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000113 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1416 | +| iterations | 3581 | +| time_elapsed | 5175 | +| total_timesteps | 7333888 | +| train/ | | +| approx_kl | 0.011734156 | +| clip_fraction | 0.32 | +| clip_range | 0.0732 | +| entropy_loss | -6.84 | +| explained_variance | 0.231 | +| learning_rate | 4.83e-05 | +| loss | -0.0264 | +| n_updates | 30140 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000265 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1416 | +| iterations | 3582 | +| time_elapsed | 5177 | +| total_timesteps | 7335936 | +| train/ | | +| approx_kl | 0.013833871 | +| clip_fraction | 0.351 | +| clip_range | 0.0732 | +| entropy_loss | -7.14 | +| explained_variance | -0.139 | +| learning_rate | 4.83e-05 | +| loss | -0.0362 | +| n_updates | 30144 | +| policy_gradient_loss | -0.023 | +| value_loss | 9.98e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1416 | +| iterations | 3583 | +| time_elapsed | 5178 | +| total_timesteps | 7337984 | +| train/ | | +| approx_kl | 0.011034743 | +| clip_fraction | 0.324 | +| clip_range | 0.0732 | +| entropy_loss | -7.06 | +| explained_variance | 0.257 | +| learning_rate | 4.83e-05 | +| loss | -0.0281 | +| n_updates | 30148 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000125 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1416 | +| iterations | 3584 | +| time_elapsed | 5180 | +| total_timesteps | 7340032 | +| train/ | | +| approx_kl | 0.012953327 | +| clip_fraction | 0.323 | +| clip_range | 0.0732 | +| entropy_loss | -6.9 | +| explained_variance | 0.32 | +| learning_rate | 4.83e-05 | +| loss | -0.0385 | +| n_updates | 30152 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000184 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1416 | +| iterations | 3585 | +| time_elapsed | 5181 | +| total_timesteps | 7342080 | +| train/ | | +| approx_kl | 0.011817269 | +| clip_fraction | 0.336 | +| clip_range | 0.0732 | +| entropy_loss | -7.06 | +| explained_variance | 0.496 | +| learning_rate | 4.83e-05 | +| loss | -0.0397 | +| n_updates | 30156 | +| policy_gradient_loss | -0.0227 | +| value_loss | 0.00011 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1416 | +| iterations | 3586 | +| time_elapsed | 5183 | +| total_timesteps | 7344128 | +| train/ | | +| approx_kl | 0.014377657 | +| clip_fraction | 0.346 | +| clip_range | 0.0732 | +| entropy_loss | -7.32 | +| explained_variance | -0.0563 | +| learning_rate | 4.83e-05 | +| loss | -0.0318 | +| n_updates | 30160 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000134 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1416 | +| iterations | 3587 | +| time_elapsed | 5184 | +| total_timesteps | 7346176 | +| train/ | | +| approx_kl | 0.012408311 | +| clip_fraction | 0.315 | +| clip_range | 0.0732 | +| entropy_loss | -6.44 | +| explained_variance | 0.671 | +| learning_rate | 4.83e-05 | +| loss | -0.0299 | +| n_updates | 30164 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000132 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1416 | +| iterations | 3588 | +| time_elapsed | 5185 | +| total_timesteps | 7348224 | +| train/ | | +| approx_kl | 0.014616882 | +| clip_fraction | 0.337 | +| clip_range | 0.0732 | +| entropy_loss | -6.59 | +| explained_variance | 0.657 | +| learning_rate | 4.83e-05 | +| loss | -0.0279 | +| n_updates | 30168 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.00011 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1416 | +| iterations | 3589 | +| time_elapsed | 5187 | +| total_timesteps | 7350272 | +| train/ | | +| approx_kl | 0.012121564 | +| clip_fraction | 0.319 | +| clip_range | 0.0732 | +| entropy_loss | -7.14 | +| explained_variance | 0.298 | +| learning_rate | 4.83e-05 | +| loss | -0.0288 | +| n_updates | 30172 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000181 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1417 | +| iterations | 3590 | +| time_elapsed | 5188 | +| total_timesteps | 7352320 | +| train/ | | +| approx_kl | 0.013638034 | +| clip_fraction | 0.351 | +| clip_range | 0.0732 | +| entropy_loss | -7.44 | +| explained_variance | -0.211 | +| learning_rate | 4.83e-05 | +| loss | -0.036 | +| n_updates | 30176 | +| policy_gradient_loss | -0.0224 | +| value_loss | 0.00013 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1416 | +| iterations | 3591 | +| time_elapsed | 5190 | +| total_timesteps | 7354368 | +| train/ | | +| approx_kl | 0.013671547 | +| clip_fraction | 0.322 | +| clip_range | 0.0732 | +| entropy_loss | -7.15 | +| explained_variance | 0.361 | +| learning_rate | 4.83e-05 | +| loss | -0.0321 | +| n_updates | 30180 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000125 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1417 | +| iterations | 3592 | +| time_elapsed | 5191 | +| total_timesteps | 7356416 | +| train/ | | +| approx_kl | 0.012272531 | +| clip_fraction | 0.322 | +| clip_range | 0.0732 | +| entropy_loss | -7.27 | +| explained_variance | -0.0691 | +| learning_rate | 4.83e-05 | +| loss | -0.0316 | +| n_updates | 30184 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000201 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1417 | +| iterations | 3593 | +| time_elapsed | 5192 | +| total_timesteps | 7358464 | +| train/ | | +| approx_kl | 0.013421012 | +| clip_fraction | 0.315 | +| clip_range | 0.0732 | +| entropy_loss | -7.39 | +| explained_variance | -0.16 | +| learning_rate | 4.83e-05 | +| loss | -0.0342 | +| n_updates | 30188 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000125 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1417 | +| iterations | 3594 | +| time_elapsed | 5194 | +| total_timesteps | 7360512 | +| train/ | | +| approx_kl | 0.010971147 | +| clip_fraction | 0.298 | +| clip_range | 0.0732 | +| entropy_loss | -7.14 | +| explained_variance | 0.23 | +| learning_rate | 4.83e-05 | +| loss | -0.0236 | +| n_updates | 30192 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000189 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1417 | +| iterations | 3595 | +| time_elapsed | 5195 | +| total_timesteps | 7362560 | +| train/ | | +| approx_kl | 0.014538324 | +| clip_fraction | 0.344 | +| clip_range | 0.0732 | +| entropy_loss | -7.3 | +| explained_variance | -0.102 | +| learning_rate | 4.83e-05 | +| loss | -0.0338 | +| n_updates | 30196 | +| policy_gradient_loss | -0.0226 | +| value_loss | 0.000117 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1417 | +| iterations | 3596 | +| time_elapsed | 5197 | +| total_timesteps | 7364608 | +| train/ | | +| approx_kl | 0.012556974 | +| clip_fraction | 0.361 | +| clip_range | 0.0732 | +| entropy_loss | -7.41 | +| explained_variance | -0.603 | +| learning_rate | 4.83e-05 | +| loss | -0.0409 | +| n_updates | 30200 | +| policy_gradient_loss | -0.0267 | +| value_loss | 6.07e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1417 | +| iterations | 3597 | +| time_elapsed | 5198 | +| total_timesteps | 7366656 | +| train/ | | +| approx_kl | 0.010112586 | +| clip_fraction | 0.326 | +| clip_range | 0.0732 | +| entropy_loss | -6.9 | +| explained_variance | 0.439 | +| learning_rate | 4.83e-05 | +| loss | -0.029 | +| n_updates | 30204 | +| policy_gradient_loss | -0.0177 | +| value_loss | 8.82e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1417 | +| iterations | 3598 | +| time_elapsed | 5200 | +| total_timesteps | 7368704 | +| train/ | | +| approx_kl | 0.010727346 | +| clip_fraction | 0.309 | +| clip_range | 0.0732 | +| entropy_loss | -6.83 | +| explained_variance | 0.523 | +| learning_rate | 4.83e-05 | +| loss | -0.0278 | +| n_updates | 30208 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000128 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1417 | +| iterations | 3599 | +| time_elapsed | 5201 | +| total_timesteps | 7370752 | +| train/ | | +| approx_kl | 0.014507394 | +| clip_fraction | 0.349 | +| clip_range | 0.0732 | +| entropy_loss | -7.04 | +| explained_variance | 0.503 | +| learning_rate | 4.82e-05 | +| loss | -0.0367 | +| n_updates | 30212 | +| policy_gradient_loss | -0.0234 | +| value_loss | 8.01e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1417 | +| iterations | 3600 | +| time_elapsed | 5202 | +| total_timesteps | 7372800 | +| train/ | | +| approx_kl | 0.013595322 | +| clip_fraction | 0.294 | +| clip_range | 0.0732 | +| entropy_loss | -6.27 | +| explained_variance | 0.656 | +| learning_rate | 4.82e-05 | +| loss | -0.0273 | +| n_updates | 30216 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000199 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1417 | +| iterations | 3601 | +| time_elapsed | 5204 | +| total_timesteps | 7374848 | +| train/ | | +| approx_kl | 0.013323574 | +| clip_fraction | 0.363 | +| clip_range | 0.0732 | +| entropy_loss | -6.88 | +| explained_variance | 0.418 | +| learning_rate | 4.82e-05 | +| loss | -0.0312 | +| n_updates | 30220 | +| policy_gradient_loss | -0.0221 | +| value_loss | 7.4e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1417 | +| iterations | 3602 | +| time_elapsed | 5205 | +| total_timesteps | 7376896 | +| train/ | | +| approx_kl | 0.0138041545 | +| clip_fraction | 0.335 | +| clip_range | 0.0732 | +| entropy_loss | -7.15 | +| explained_variance | 0.189 | +| learning_rate | 4.82e-05 | +| loss | -0.0345 | +| n_updates | 30224 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000218 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1417 | +| iterations | 3603 | +| time_elapsed | 5207 | +| total_timesteps | 7378944 | +| train/ | | +| approx_kl | 0.013499298 | +| clip_fraction | 0.342 | +| clip_range | 0.0732 | +| entropy_loss | -7.41 | +| explained_variance | -0.243 | +| learning_rate | 4.82e-05 | +| loss | -0.0335 | +| n_updates | 30228 | +| policy_gradient_loss | -0.0227 | +| value_loss | 8.58e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1417 | +| iterations | 3604 | +| time_elapsed | 5208 | +| total_timesteps | 7380992 | +| train/ | | +| approx_kl | 0.010749511 | +| clip_fraction | 0.328 | +| clip_range | 0.0732 | +| entropy_loss | -7.38 | +| explained_variance | -0.188 | +| learning_rate | 4.82e-05 | +| loss | -0.034 | +| n_updates | 30232 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.00011 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1417 | +| iterations | 3605 | +| time_elapsed | 5209 | +| total_timesteps | 7383040 | +| train/ | | +| approx_kl | 0.011851255 | +| clip_fraction | 0.325 | +| clip_range | 0.0732 | +| entropy_loss | -7.07 | +| explained_variance | 0.366 | +| learning_rate | 4.82e-05 | +| loss | -0.0227 | +| n_updates | 30236 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000243 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1417 | +| iterations | 3606 | +| time_elapsed | 5211 | +| total_timesteps | 7385088 | +| train/ | | +| approx_kl | 0.010471478 | +| clip_fraction | 0.325 | +| clip_range | 0.0732 | +| entropy_loss | -7.01 | +| explained_variance | 0.271 | +| learning_rate | 4.82e-05 | +| loss | -0.0352 | +| n_updates | 30240 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000178 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1417 | +| iterations | 3607 | +| time_elapsed | 5212 | +| total_timesteps | 7387136 | +| train/ | | +| approx_kl | 0.012091849 | +| clip_fraction | 0.346 | +| clip_range | 0.0732 | +| entropy_loss | -7.37 | +| explained_variance | -0.0864 | +| learning_rate | 4.82e-05 | +| loss | -0.0429 | +| n_updates | 30244 | +| policy_gradient_loss | -0.0203 | +| value_loss | 9.21e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1417 | +| iterations | 3608 | +| time_elapsed | 5214 | +| total_timesteps | 7389184 | +| train/ | | +| approx_kl | 0.01366996 | +| clip_fraction | 0.336 | +| clip_range | 0.0732 | +| entropy_loss | -6.97 | +| explained_variance | 0.494 | +| learning_rate | 4.82e-05 | +| loss | -0.031 | +| n_updates | 30248 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000129 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1417 | +| iterations | 3609 | +| time_elapsed | 5215 | +| total_timesteps | 7391232 | +| train/ | | +| approx_kl | 0.010501256 | +| clip_fraction | 0.313 | +| clip_range | 0.0732 | +| entropy_loss | -7.09 | +| explained_variance | 0.178 | +| learning_rate | 4.82e-05 | +| loss | -0.0339 | +| n_updates | 30252 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000163 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1417 | +| iterations | 3610 | +| time_elapsed | 5217 | +| total_timesteps | 7393280 | +| train/ | | +| approx_kl | 0.01207722 | +| clip_fraction | 0.326 | +| clip_range | 0.0732 | +| entropy_loss | -6.99 | +| explained_variance | 0.208 | +| learning_rate | 4.82e-05 | +| loss | -0.0325 | +| n_updates | 30256 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000211 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1417 | +| iterations | 3611 | +| time_elapsed | 5218 | +| total_timesteps | 7395328 | +| train/ | | +| approx_kl | 0.010622877 | +| clip_fraction | 0.332 | +| clip_range | 0.0732 | +| entropy_loss | -6.86 | +| explained_variance | 0.413 | +| learning_rate | 4.82e-05 | +| loss | -0.0329 | +| n_updates | 30260 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000163 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1417 | +| iterations | 3612 | +| time_elapsed | 5220 | +| total_timesteps | 7397376 | +| train/ | | +| approx_kl | 0.011168534 | +| clip_fraction | 0.333 | +| clip_range | 0.0732 | +| entropy_loss | -7.15 | +| explained_variance | -0.0683 | +| learning_rate | 4.82e-05 | +| loss | -0.038 | +| n_updates | 30264 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.00014 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1417 | +| iterations | 3613 | +| time_elapsed | 5221 | +| total_timesteps | 7399424 | +| train/ | | +| approx_kl | 0.010142594 | +| clip_fraction | 0.312 | +| clip_range | 0.0732 | +| entropy_loss | -7.09 | +| explained_variance | 0.302 | +| learning_rate | 4.82e-05 | +| loss | -0.0308 | +| n_updates | 30268 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000185 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1417 | +| iterations | 3614 | +| time_elapsed | 5222 | +| total_timesteps | 7401472 | +| train/ | | +| approx_kl | 0.01294711 | +| clip_fraction | 0.34 | +| clip_range | 0.0732 | +| entropy_loss | -7.18 | +| explained_variance | 0.382 | +| learning_rate | 4.82e-05 | +| loss | -0.0299 | +| n_updates | 30272 | +| policy_gradient_loss | -0.0199 | +| value_loss | 8.06e-05 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1417 | +| iterations | 3615 | +| time_elapsed | 5224 | +| total_timesteps | 7403520 | +| train/ | | +| approx_kl | 0.0122222295 | +| clip_fraction | 0.326 | +| clip_range | 0.0731 | +| entropy_loss | -7.17 | +| explained_variance | 0.247 | +| learning_rate | 4.82e-05 | +| loss | -0.0336 | +| n_updates | 30276 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000204 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1417 | +| iterations | 3616 | +| time_elapsed | 5225 | +| total_timesteps | 7405568 | +| train/ | | +| approx_kl | 0.012763837 | +| clip_fraction | 0.354 | +| clip_range | 0.0731 | +| entropy_loss | -6.95 | +| explained_variance | 0.502 | +| learning_rate | 4.82e-05 | +| loss | -0.0381 | +| n_updates | 30280 | +| policy_gradient_loss | -0.0243 | +| value_loss | 6.72e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1417 | +| iterations | 3617 | +| time_elapsed | 5227 | +| total_timesteps | 7407616 | +| train/ | | +| approx_kl | 0.011211172 | +| clip_fraction | 0.308 | +| clip_range | 0.0731 | +| entropy_loss | -6.88 | +| explained_variance | 0.593 | +| learning_rate | 4.82e-05 | +| loss | -0.0265 | +| n_updates | 30284 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.00013 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1417 | +| iterations | 3618 | +| time_elapsed | 5228 | +| total_timesteps | 7409664 | +| train/ | | +| approx_kl | 0.012170918 | +| clip_fraction | 0.313 | +| clip_range | 0.0731 | +| entropy_loss | -7.1 | +| explained_variance | 0.265 | +| learning_rate | 4.82e-05 | +| loss | -0.0306 | +| n_updates | 30288 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000208 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1417 | +| iterations | 3619 | +| time_elapsed | 5229 | +| total_timesteps | 7411712 | +| train/ | | +| approx_kl | 0.012054269 | +| clip_fraction | 0.343 | +| clip_range | 0.0731 | +| entropy_loss | -7.17 | +| explained_variance | 0.386 | +| learning_rate | 4.82e-05 | +| loss | -0.0374 | +| n_updates | 30292 | +| policy_gradient_loss | -0.0235 | +| value_loss | 7.58e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1417 | +| iterations | 3620 | +| time_elapsed | 5231 | +| total_timesteps | 7413760 | +| train/ | | +| approx_kl | 0.012097317 | +| clip_fraction | 0.294 | +| clip_range | 0.0731 | +| entropy_loss | -6.94 | +| explained_variance | 0.301 | +| learning_rate | 4.82e-05 | +| loss | -0.0337 | +| n_updates | 30296 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000278 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1417 | +| iterations | 3621 | +| time_elapsed | 5232 | +| total_timesteps | 7415808 | +| train/ | | +| approx_kl | 0.012075004 | +| clip_fraction | 0.331 | +| clip_range | 0.0731 | +| entropy_loss | -6.65 | +| explained_variance | 0.573 | +| learning_rate | 4.82e-05 | +| loss | -0.0371 | +| n_updates | 30300 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000151 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1417 | +| iterations | 3622 | +| time_elapsed | 5234 | +| total_timesteps | 7417856 | +| train/ | | +| approx_kl | 0.011872528 | +| clip_fraction | 0.326 | +| clip_range | 0.0731 | +| entropy_loss | -6.98 | +| explained_variance | 0.506 | +| learning_rate | 4.82e-05 | +| loss | -0.0349 | +| n_updates | 30304 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000132 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1417 | +| iterations | 3623 | +| time_elapsed | 5235 | +| total_timesteps | 7419904 | +| train/ | | +| approx_kl | 0.0132869575 | +| clip_fraction | 0.323 | +| clip_range | 0.0731 | +| entropy_loss | -6.91 | +| explained_variance | 0.543 | +| learning_rate | 4.82e-05 | +| loss | -0.0343 | +| n_updates | 30308 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000113 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1417 | +| iterations | 3624 | +| time_elapsed | 5237 | +| total_timesteps | 7421952 | +| train/ | | +| approx_kl | 0.011823053 | +| clip_fraction | 0.305 | +| clip_range | 0.0731 | +| entropy_loss | -7.17 | +| explained_variance | 0.191 | +| learning_rate | 4.82e-05 | +| loss | -0.0339 | +| n_updates | 30312 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000178 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1417 | +| iterations | 3625 | +| time_elapsed | 5238 | +| total_timesteps | 7424000 | +| train/ | | +| approx_kl | 0.011037733 | +| clip_fraction | 0.293 | +| clip_range | 0.0731 | +| entropy_loss | -6.94 | +| explained_variance | 0.256 | +| learning_rate | 4.82e-05 | +| loss | -0.0237 | +| n_updates | 30316 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000343 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1417 | +| iterations | 3626 | +| time_elapsed | 5239 | +| total_timesteps | 7426048 | +| train/ | | +| approx_kl | 0.011130329 | +| clip_fraction | 0.3 | +| clip_range | 0.0731 | +| entropy_loss | -6.44 | +| explained_variance | 0.502 | +| learning_rate | 4.82e-05 | +| loss | -0.0242 | +| n_updates | 30320 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000292 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1417 | +| iterations | 3627 | +| time_elapsed | 5241 | +| total_timesteps | 7428096 | +| train/ | | +| approx_kl | 0.011935731 | +| clip_fraction | 0.358 | +| clip_range | 0.0731 | +| entropy_loss | -7.11 | +| explained_variance | -0.208 | +| learning_rate | 4.82e-05 | +| loss | -0.0457 | +| n_updates | 30324 | +| policy_gradient_loss | -0.0252 | +| value_loss | 9.49e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1417 | +| iterations | 3628 | +| time_elapsed | 5242 | +| total_timesteps | 7430144 | +| train/ | | +| approx_kl | 0.008554257 | +| clip_fraction | 0.31 | +| clip_range | 0.0731 | +| entropy_loss | -7.24 | +| explained_variance | 0.2 | +| learning_rate | 4.82e-05 | +| loss | -0.0309 | +| n_updates | 30328 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000146 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1417 | +| iterations | 3629 | +| time_elapsed | 5244 | +| total_timesteps | 7432192 | +| train/ | | +| approx_kl | 0.011399995 | +| clip_fraction | 0.345 | +| clip_range | 0.0731 | +| entropy_loss | -7.14 | +| explained_variance | 0.298 | +| learning_rate | 4.82e-05 | +| loss | -0.0327 | +| n_updates | 30332 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000122 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1417 | +| iterations | 3630 | +| time_elapsed | 5245 | +| total_timesteps | 7434240 | +| train/ | | +| approx_kl | 0.0104388185 | +| clip_fraction | 0.276 | +| clip_range | 0.0731 | +| entropy_loss | -7.12 | +| explained_variance | 0.242 | +| learning_rate | 4.82e-05 | +| loss | -0.0298 | +| n_updates | 30336 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000204 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1417 | +| iterations | 3631 | +| time_elapsed | 5247 | +| total_timesteps | 7436288 | +| train/ | | +| approx_kl | 0.012934508 | +| clip_fraction | 0.353 | +| clip_range | 0.0731 | +| entropy_loss | -7.33 | +| explained_variance | -0.118 | +| learning_rate | 4.82e-05 | +| loss | -0.0379 | +| n_updates | 30340 | +| policy_gradient_loss | -0.0229 | +| value_loss | 7.27e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1417 | +| iterations | 3632 | +| time_elapsed | 5248 | +| total_timesteps | 7438336 | +| train/ | | +| approx_kl | 0.009440342 | +| clip_fraction | 0.29 | +| clip_range | 0.0731 | +| entropy_loss | -6.75 | +| explained_variance | 0.341 | +| learning_rate | 4.82e-05 | +| loss | -0.0229 | +| n_updates | 30344 | +| policy_gradient_loss | -0.0146 | +| value_loss | 0.000288 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1417 | +| iterations | 3633 | +| time_elapsed | 5250 | +| total_timesteps | 7440384 | +| train/ | | +| approx_kl | 0.010333587 | +| clip_fraction | 0.324 | +| clip_range | 0.0731 | +| entropy_loss | -6.55 | +| explained_variance | 0.348 | +| learning_rate | 4.82e-05 | +| loss | -0.0322 | +| n_updates | 30348 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000275 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1417 | +| iterations | 3634 | +| time_elapsed | 5251 | +| total_timesteps | 7442432 | +| train/ | | +| approx_kl | 0.01435504 | +| clip_fraction | 0.356 | +| clip_range | 0.0731 | +| entropy_loss | -6.57 | +| explained_variance | 0.549 | +| learning_rate | 4.82e-05 | +| loss | -0.0357 | +| n_updates | 30352 | +| policy_gradient_loss | -0.0225 | +| value_loss | 0.000117 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1417 | +| iterations | 3635 | +| time_elapsed | 5252 | +| total_timesteps | 7444480 | +| train/ | | +| approx_kl | 0.014849936 | +| clip_fraction | 0.389 | +| clip_range | 0.0731 | +| entropy_loss | -7.18 | +| explained_variance | -0.48 | +| learning_rate | 4.82e-05 | +| loss | -0.0455 | +| n_updates | 30356 | +| policy_gradient_loss | -0.026 | +| value_loss | 7.01e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1417 | +| iterations | 3636 | +| time_elapsed | 5254 | +| total_timesteps | 7446528 | +| train/ | | +| approx_kl | 0.011764575 | +| clip_fraction | 0.357 | +| clip_range | 0.0731 | +| entropy_loss | -7.3 | +| explained_variance | -0.271 | +| learning_rate | 4.82e-05 | +| loss | -0.0387 | +| n_updates | 30360 | +| policy_gradient_loss | -0.0226 | +| value_loss | 0.00011 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1417 | +| iterations | 3637 | +| time_elapsed | 5255 | +| total_timesteps | 7448576 | +| train/ | | +| approx_kl | 0.012576556 | +| clip_fraction | 0.32 | +| clip_range | 0.0731 | +| entropy_loss | -7.09 | +| explained_variance | 0.257 | +| learning_rate | 4.82e-05 | +| loss | -0.0311 | +| n_updates | 30364 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000111 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1417 | +| iterations | 3638 | +| time_elapsed | 5257 | +| total_timesteps | 7450624 | +| train/ | | +| approx_kl | 0.013800163 | +| clip_fraction | 0.329 | +| clip_range | 0.0731 | +| entropy_loss | -7.21 | +| explained_variance | 0.374 | +| learning_rate | 4.82e-05 | +| loss | -0.0288 | +| n_updates | 30368 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000125 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1417 | +| iterations | 3639 | +| time_elapsed | 5258 | +| total_timesteps | 7452672 | +| train/ | | +| approx_kl | 0.011947213 | +| clip_fraction | 0.327 | +| clip_range | 0.0731 | +| entropy_loss | -7.08 | +| explained_variance | 0.286 | +| learning_rate | 4.82e-05 | +| loss | -0.033 | +| n_updates | 30372 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000143 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1417 | +| iterations | 3640 | +| time_elapsed | 5260 | +| total_timesteps | 7454720 | +| train/ | | +| approx_kl | 0.013373352 | +| clip_fraction | 0.35 | +| clip_range | 0.0731 | +| entropy_loss | -6.64 | +| explained_variance | 0.67 | +| learning_rate | 4.82e-05 | +| loss | -0.032 | +| n_updates | 30376 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000134 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1417 | +| iterations | 3641 | +| time_elapsed | 5261 | +| total_timesteps | 7456768 | +| train/ | | +| approx_kl | 0.01209985 | +| clip_fraction | 0.319 | +| clip_range | 0.0731 | +| entropy_loss | -6.93 | +| explained_variance | 0.275 | +| learning_rate | 4.82e-05 | +| loss | -0.0295 | +| n_updates | 30380 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000213 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1417 | +| iterations | 3642 | +| time_elapsed | 5262 | +| total_timesteps | 7458816 | +| train/ | | +| approx_kl | 0.012341263 | +| clip_fraction | 0.339 | +| clip_range | 0.0731 | +| entropy_loss | -7.15 | +| explained_variance | 0.219 | +| learning_rate | 4.82e-05 | +| loss | -0.0359 | +| n_updates | 30384 | +| policy_gradient_loss | -0.0223 | +| value_loss | 0.000102 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1417 | +| iterations | 3643 | +| time_elapsed | 5264 | +| total_timesteps | 7460864 | +| train/ | | +| approx_kl | 0.013367633 | +| clip_fraction | 0.358 | +| clip_range | 0.0731 | +| entropy_loss | -7.09 | +| explained_variance | 0.407 | +| learning_rate | 4.82e-05 | +| loss | -0.0356 | +| n_updates | 30388 | +| policy_gradient_loss | -0.0241 | +| value_loss | 8.29e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1417 | +| iterations | 3644 | +| time_elapsed | 5265 | +| total_timesteps | 7462912 | +| train/ | | +| approx_kl | 0.011261344 | +| clip_fraction | 0.305 | +| clip_range | 0.0731 | +| entropy_loss | -6.91 | +| explained_variance | 0.404 | +| learning_rate | 4.82e-05 | +| loss | -0.0256 | +| n_updates | 30392 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000197 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1417 | +| iterations | 3645 | +| time_elapsed | 5267 | +| total_timesteps | 7464960 | +| train/ | | +| approx_kl | 0.011448992 | +| clip_fraction | 0.309 | +| clip_range | 0.0731 | +| entropy_loss | -7.11 | +| explained_variance | 0.194 | +| learning_rate | 4.82e-05 | +| loss | -0.0315 | +| n_updates | 30396 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000217 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1417 | +| iterations | 3646 | +| time_elapsed | 5268 | +| total_timesteps | 7467008 | +| train/ | | +| approx_kl | 0.012155833 | +| clip_fraction | 0.356 | +| clip_range | 0.0731 | +| entropy_loss | -7.21 | +| explained_variance | 0.445 | +| learning_rate | 4.82e-05 | +| loss | -0.038 | +| n_updates | 30400 | +| policy_gradient_loss | -0.0248 | +| value_loss | 7.65e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1417 | +| iterations | 3647 | +| time_elapsed | 5270 | +| total_timesteps | 7469056 | +| train/ | | +| approx_kl | 0.011780743 | +| clip_fraction | 0.327 | +| clip_range | 0.0731 | +| entropy_loss | -7.06 | +| explained_variance | 0.362 | +| learning_rate | 4.82e-05 | +| loss | -0.0275 | +| n_updates | 30404 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000118 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1417 | +| iterations | 3648 | +| time_elapsed | 5271 | +| total_timesteps | 7471104 | +| train/ | | +| approx_kl | 0.010981144 | +| clip_fraction | 0.318 | +| clip_range | 0.0731 | +| entropy_loss | -6.73 | +| explained_variance | 0.577 | +| learning_rate | 4.82e-05 | +| loss | -0.0263 | +| n_updates | 30408 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000139 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1417 | +| iterations | 3649 | +| time_elapsed | 5272 | +| total_timesteps | 7473152 | +| train/ | | +| approx_kl | 0.010933452 | +| clip_fraction | 0.334 | +| clip_range | 0.0731 | +| entropy_loss | -7.2 | +| explained_variance | -0.124 | +| learning_rate | 4.82e-05 | +| loss | -0.0289 | +| n_updates | 30412 | +| policy_gradient_loss | -0.0199 | +| value_loss | 8.51e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1417 | +| iterations | 3650 | +| time_elapsed | 5274 | +| total_timesteps | 7475200 | +| train/ | | +| approx_kl | 0.0125457775 | +| clip_fraction | 0.326 | +| clip_range | 0.0731 | +| entropy_loss | -7.34 | +| explained_variance | -0.197 | +| learning_rate | 4.82e-05 | +| loss | -0.0355 | +| n_updates | 30416 | +| policy_gradient_loss | -0.0201 | +| value_loss | 9.03e-05 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1417 | +| iterations | 3651 | +| time_elapsed | 5275 | +| total_timesteps | 7477248 | +| train/ | | +| approx_kl | 0.01173904 | +| clip_fraction | 0.326 | +| clip_range | 0.0731 | +| entropy_loss | -6.86 | +| explained_variance | 0.53 | +| learning_rate | 4.82e-05 | +| loss | -0.031 | +| n_updates | 30420 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000101 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1417 | +| iterations | 3652 | +| time_elapsed | 5277 | +| total_timesteps | 7479296 | +| train/ | | +| approx_kl | 0.012432787 | +| clip_fraction | 0.356 | +| clip_range | 0.0731 | +| entropy_loss | -7.31 | +| explained_variance | -0.101 | +| learning_rate | 4.82e-05 | +| loss | -0.034 | +| n_updates | 30424 | +| policy_gradient_loss | -0.022 | +| value_loss | 8.12e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1417 | +| iterations | 3653 | +| time_elapsed | 5278 | +| total_timesteps | 7481344 | +| train/ | | +| approx_kl | 0.012805721 | +| clip_fraction | 0.343 | +| clip_range | 0.0731 | +| entropy_loss | -7.36 | +| explained_variance | -0.0273 | +| learning_rate | 4.82e-05 | +| loss | -0.0313 | +| n_updates | 30428 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.0002 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1417 | +| iterations | 3654 | +| time_elapsed | 5280 | +| total_timesteps | 7483392 | +| train/ | | +| approx_kl | 0.0128256455 | +| clip_fraction | 0.357 | +| clip_range | 0.0731 | +| entropy_loss | -6.99 | +| explained_variance | 0.49 | +| learning_rate | 4.82e-05 | +| loss | -0.0387 | +| n_updates | 30432 | +| policy_gradient_loss | -0.0231 | +| value_loss | 0.000104 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1417 | +| iterations | 3655 | +| time_elapsed | 5281 | +| total_timesteps | 7485440 | +| train/ | | +| approx_kl | 0.013056632 | +| clip_fraction | 0.328 | +| clip_range | 0.0731 | +| entropy_loss | -6.5 | +| explained_variance | 0.553 | +| learning_rate | 4.82e-05 | +| loss | -0.0318 | +| n_updates | 30436 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000198 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1417 | +| iterations | 3656 | +| time_elapsed | 5283 | +| total_timesteps | 7487488 | +| train/ | | +| approx_kl | 0.012392443 | +| clip_fraction | 0.35 | +| clip_range | 0.0731 | +| entropy_loss | -6.78 | +| explained_variance | 0.585 | +| learning_rate | 4.82e-05 | +| loss | -0.0367 | +| n_updates | 30440 | +| policy_gradient_loss | -0.0214 | +| value_loss | 9.09e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1417 | +| iterations | 3657 | +| time_elapsed | 5284 | +| total_timesteps | 7489536 | +| train/ | | +| approx_kl | 0.013644582 | +| clip_fraction | 0.363 | +| clip_range | 0.0731 | +| entropy_loss | -7.02 | +| explained_variance | 0.476 | +| learning_rate | 4.82e-05 | +| loss | -0.0379 | +| n_updates | 30444 | +| policy_gradient_loss | -0.0221 | +| value_loss | 7.29e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1417 | +| iterations | 3658 | +| time_elapsed | 5286 | +| total_timesteps | 7491584 | +| train/ | | +| approx_kl | 0.012622528 | +| clip_fraction | 0.339 | +| clip_range | 0.0731 | +| entropy_loss | -6.9 | +| explained_variance | 0.533 | +| learning_rate | 4.82e-05 | +| loss | -0.0265 | +| n_updates | 30448 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000123 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1417 | +| iterations | 3659 | +| time_elapsed | 5287 | +| total_timesteps | 7493632 | +| train/ | | +| approx_kl | 0.013822319 | +| clip_fraction | 0.335 | +| clip_range | 0.0731 | +| entropy_loss | -7.01 | +| explained_variance | 0.246 | +| learning_rate | 4.82e-05 | +| loss | -0.0292 | +| n_updates | 30452 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000202 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1417 | +| iterations | 3660 | +| time_elapsed | 5288 | +| total_timesteps | 7495680 | +| train/ | | +| approx_kl | 0.012626903 | +| clip_fraction | 0.328 | +| clip_range | 0.0731 | +| entropy_loss | -6.81 | +| explained_variance | 0.521 | +| learning_rate | 4.82e-05 | +| loss | -0.0286 | +| n_updates | 30456 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000143 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1417 | +| iterations | 3661 | +| time_elapsed | 5290 | +| total_timesteps | 7497728 | +| train/ | | +| approx_kl | 0.011487743 | +| clip_fraction | 0.345 | +| clip_range | 0.0731 | +| entropy_loss | -7.06 | +| explained_variance | 0.409 | +| learning_rate | 4.82e-05 | +| loss | -0.0328 | +| n_updates | 30460 | +| policy_gradient_loss | -0.0218 | +| value_loss | 8.22e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1417 | +| iterations | 3662 | +| time_elapsed | 5291 | +| total_timesteps | 7499776 | +| train/ | | +| approx_kl | 0.012831445 | +| clip_fraction | 0.342 | +| clip_range | 0.0731 | +| entropy_loss | -7.06 | +| explained_variance | 0.353 | +| learning_rate | 4.82e-05 | +| loss | -0.0301 | +| n_updates | 30464 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.00011 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1417 | +| iterations | 3663 | +| time_elapsed | 5293 | +| total_timesteps | 7501824 | +| train/ | | +| approx_kl | 0.009800743 | +| clip_fraction | 0.31 | +| clip_range | 0.0731 | +| entropy_loss | -7.03 | +| explained_variance | 0.422 | +| learning_rate | 4.82e-05 | +| loss | -0.0265 | +| n_updates | 30468 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000171 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1417 | +| iterations | 3664 | +| time_elapsed | 5294 | +| total_timesteps | 7503872 | +| train/ | | +| approx_kl | 0.010152742 | +| clip_fraction | 0.296 | +| clip_range | 0.0731 | +| entropy_loss | -6.76 | +| explained_variance | 0.504 | +| learning_rate | 4.82e-05 | +| loss | -0.0236 | +| n_updates | 30472 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.00016 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1417 | +| iterations | 3665 | +| time_elapsed | 5296 | +| total_timesteps | 7505920 | +| train/ | | +| approx_kl | 0.012328374 | +| clip_fraction | 0.341 | +| clip_range | 0.0731 | +| entropy_loss | -7.32 | +| explained_variance | -0.0931 | +| learning_rate | 4.82e-05 | +| loss | -0.0328 | +| n_updates | 30476 | +| policy_gradient_loss | -0.0226 | +| value_loss | 0.000237 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1417 | +| iterations | 3666 | +| time_elapsed | 5297 | +| total_timesteps | 7507968 | +| train/ | | +| approx_kl | 0.011421858 | +| clip_fraction | 0.371 | +| clip_range | 0.0731 | +| entropy_loss | -7.14 | +| explained_variance | 0.0601 | +| learning_rate | 4.82e-05 | +| loss | -0.0271 | +| n_updates | 30480 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000145 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1417 | +| iterations | 3667 | +| time_elapsed | 5298 | +| total_timesteps | 7510016 | +| train/ | | +| approx_kl | 0.010796114 | +| clip_fraction | 0.323 | +| clip_range | 0.0731 | +| entropy_loss | -6.53 | +| explained_variance | 0.337 | +| learning_rate | 4.82e-05 | +| loss | -0.0293 | +| n_updates | 30484 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000246 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1417 | +| iterations | 3668 | +| time_elapsed | 5300 | +| total_timesteps | 7512064 | +| train/ | | +| approx_kl | 0.012730304 | +| clip_fraction | 0.334 | +| clip_range | 0.0731 | +| entropy_loss | -6.66 | +| explained_variance | 0.496 | +| learning_rate | 4.82e-05 | +| loss | -0.0303 | +| n_updates | 30488 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000157 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1417 | +| iterations | 3669 | +| time_elapsed | 5301 | +| total_timesteps | 7514112 | +| train/ | | +| approx_kl | 0.013120515 | +| clip_fraction | 0.347 | +| clip_range | 0.0731 | +| entropy_loss | -7.19 | +| explained_variance | 0.0668 | +| learning_rate | 4.82e-05 | +| loss | -0.0335 | +| n_updates | 30492 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000183 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1417 | +| iterations | 3670 | +| time_elapsed | 5303 | +| total_timesteps | 7516160 | +| train/ | | +| approx_kl | 0.013066803 | +| clip_fraction | 0.373 | +| clip_range | 0.0731 | +| entropy_loss | -7.34 | +| explained_variance | -0.121 | +| learning_rate | 4.82e-05 | +| loss | -0.0404 | +| n_updates | 30496 | +| policy_gradient_loss | -0.0246 | +| value_loss | 0.000102 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1417 | +| iterations | 3671 | +| time_elapsed | 5304 | +| total_timesteps | 7518208 | +| train/ | | +| approx_kl | 0.011663272 | +| clip_fraction | 0.328 | +| clip_range | 0.0731 | +| entropy_loss | -7.24 | +| explained_variance | 0.298 | +| learning_rate | 4.82e-05 | +| loss | -0.0369 | +| n_updates | 30500 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000143 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1417 | +| iterations | 3672 | +| time_elapsed | 5306 | +| total_timesteps | 7520256 | +| train/ | | +| approx_kl | 0.012636875 | +| clip_fraction | 0.33 | +| clip_range | 0.0731 | +| entropy_loss | -6.58 | +| explained_variance | 0.56 | +| learning_rate | 4.82e-05 | +| loss | -0.0316 | +| n_updates | 30504 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000169 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1417 | +| iterations | 3673 | +| time_elapsed | 5307 | +| total_timesteps | 7522304 | +| train/ | | +| approx_kl | 0.01126921 | +| clip_fraction | 0.336 | +| clip_range | 0.0731 | +| entropy_loss | -7.25 | +| explained_variance | 0.113 | +| learning_rate | 4.82e-05 | +| loss | -0.0291 | +| n_updates | 30508 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000193 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1417 | +| iterations | 3674 | +| time_elapsed | 5309 | +| total_timesteps | 7524352 | +| train/ | | +| approx_kl | 0.011601452 | +| clip_fraction | 0.338 | +| clip_range | 0.0731 | +| entropy_loss | -7.03 | +| explained_variance | 0.288 | +| learning_rate | 4.82e-05 | +| loss | -0.0364 | +| n_updates | 30512 | +| policy_gradient_loss | -0.0221 | +| value_loss | 0.000145 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1417 | +| iterations | 3675 | +| time_elapsed | 5310 | +| total_timesteps | 7526400 | +| train/ | | +| approx_kl | 0.013566803 | +| clip_fraction | 0.351 | +| clip_range | 0.0731 | +| entropy_loss | -7.3 | +| explained_variance | -0.108 | +| learning_rate | 4.82e-05 | +| loss | -0.0374 | +| n_updates | 30516 | +| policy_gradient_loss | -0.0228 | +| value_loss | 7.02e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1417 | +| iterations | 3676 | +| time_elapsed | 5312 | +| total_timesteps | 7528448 | +| train/ | | +| approx_kl | 0.012552241 | +| clip_fraction | 0.328 | +| clip_range | 0.0731 | +| entropy_loss | -7.14 | +| explained_variance | 0.147 | +| learning_rate | 4.82e-05 | +| loss | -0.035 | +| n_updates | 30520 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000241 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1417 | +| iterations | 3677 | +| time_elapsed | 5313 | +| total_timesteps | 7530496 | +| train/ | | +| approx_kl | 0.0128859 | +| clip_fraction | 0.355 | +| clip_range | 0.0731 | +| entropy_loss | -6.98 | +| explained_variance | 0.413 | +| learning_rate | 4.82e-05 | +| loss | -0.0326 | +| n_updates | 30524 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000158 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1417 | +| iterations | 3678 | +| time_elapsed | 5314 | +| total_timesteps | 7532544 | +| train/ | | +| approx_kl | 0.015550233 | +| clip_fraction | 0.313 | +| clip_range | 0.0731 | +| entropy_loss | -6.94 | +| explained_variance | 0.266 | +| learning_rate | 4.82e-05 | +| loss | -0.0286 | +| n_updates | 30528 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000144 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1417 | +| iterations | 3679 | +| time_elapsed | 5316 | +| total_timesteps | 7534592 | +| train/ | | +| approx_kl | 0.011524316 | +| clip_fraction | 0.307 | +| clip_range | 0.0731 | +| entropy_loss | -7 | +| explained_variance | 0.412 | +| learning_rate | 4.82e-05 | +| loss | -0.0253 | +| n_updates | 30532 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000198 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1417 | +| iterations | 3680 | +| time_elapsed | 5317 | +| total_timesteps | 7536640 | +| train/ | | +| approx_kl | 0.012877606 | +| clip_fraction | 0.362 | +| clip_range | 0.0731 | +| entropy_loss | -7.04 | +| explained_variance | 0.305 | +| learning_rate | 4.82e-05 | +| loss | -0.0322 | +| n_updates | 30536 | +| policy_gradient_loss | -0.0233 | +| value_loss | 0.000105 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1417 | +| iterations | 3681 | +| time_elapsed | 5319 | +| total_timesteps | 7538688 | +| train/ | | +| approx_kl | 0.010852242 | +| clip_fraction | 0.34 | +| clip_range | 0.0731 | +| entropy_loss | -7.09 | +| explained_variance | 0.239 | +| learning_rate | 4.82e-05 | +| loss | -0.025 | +| n_updates | 30540 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000201 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1417 | +| iterations | 3682 | +| time_elapsed | 5320 | +| total_timesteps | 7540736 | +| train/ | | +| approx_kl | 0.011881936 | +| clip_fraction | 0.319 | +| clip_range | 0.0731 | +| entropy_loss | -6.84 | +| explained_variance | 0.497 | +| learning_rate | 4.82e-05 | +| loss | -0.0286 | +| n_updates | 30544 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000174 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1417 | +| iterations | 3683 | +| time_elapsed | 5322 | +| total_timesteps | 7542784 | +| train/ | | +| approx_kl | 0.0100201275 | +| clip_fraction | 0.326 | +| clip_range | 0.0731 | +| entropy_loss | -7.13 | +| explained_variance | 0.494 | +| learning_rate | 4.82e-05 | +| loss | -0.0321 | +| n_updates | 30548 | +| policy_gradient_loss | -0.0209 | +| value_loss | 9.72e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1417 | +| iterations | 3684 | +| time_elapsed | 5323 | +| total_timesteps | 7544832 | +| train/ | | +| approx_kl | 0.012951308 | +| clip_fraction | 0.326 | +| clip_range | 0.0731 | +| entropy_loss | -6.76 | +| explained_variance | 0.668 | +| learning_rate | 4.82e-05 | +| loss | -0.0257 | +| n_updates | 30552 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000115 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1417 | +| iterations | 3685 | +| time_elapsed | 5325 | +| total_timesteps | 7546880 | +| train/ | | +| approx_kl | 0.014509141 | +| clip_fraction | 0.355 | +| clip_range | 0.0731 | +| entropy_loss | -6.64 | +| explained_variance | 0.686 | +| learning_rate | 4.82e-05 | +| loss | -0.0372 | +| n_updates | 30556 | +| policy_gradient_loss | -0.0206 | +| value_loss | 7.34e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1417 | +| iterations | 3686 | +| time_elapsed | 5326 | +| total_timesteps | 7548928 | +| train/ | | +| approx_kl | 0.013214959 | +| clip_fraction | 0.348 | +| clip_range | 0.0731 | +| entropy_loss | -7.3 | +| explained_variance | -0.04 | +| learning_rate | 4.82e-05 | +| loss | -0.0364 | +| n_updates | 30560 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000197 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1417 | +| iterations | 3687 | +| time_elapsed | 5327 | +| total_timesteps | 7550976 | +| train/ | | +| approx_kl | 0.011706925 | +| clip_fraction | 0.325 | +| clip_range | 0.0731 | +| entropy_loss | -6.88 | +| explained_variance | 0.392 | +| learning_rate | 4.82e-05 | +| loss | -0.027 | +| n_updates | 30564 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000171 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1417 | +| iterations | 3688 | +| time_elapsed | 5329 | +| total_timesteps | 7553024 | +| train/ | | +| approx_kl | 0.011621547 | +| clip_fraction | 0.354 | +| clip_range | 0.0731 | +| entropy_loss | -7.39 | +| explained_variance | -0.0655 | +| learning_rate | 4.82e-05 | +| loss | -0.0358 | +| n_updates | 30568 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.00014 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1417 | +| iterations | 3689 | +| time_elapsed | 5330 | +| total_timesteps | 7555072 | +| train/ | | +| approx_kl | 0.012495508 | +| clip_fraction | 0.317 | +| clip_range | 0.0731 | +| entropy_loss | -6.94 | +| explained_variance | 0.477 | +| learning_rate | 4.82e-05 | +| loss | -0.0282 | +| n_updates | 30572 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1417 | +| iterations | 3690 | +| time_elapsed | 5332 | +| total_timesteps | 7557120 | +| train/ | | +| approx_kl | 0.012876234 | +| clip_fraction | 0.362 | +| clip_range | 0.0731 | +| entropy_loss | -7.18 | +| explained_variance | 0.0299 | +| learning_rate | 4.82e-05 | +| loss | -0.0326 | +| n_updates | 30576 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000125 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1417 | +| iterations | 3691 | +| time_elapsed | 5333 | +| total_timesteps | 7559168 | +| train/ | | +| approx_kl | 0.012768034 | +| clip_fraction | 0.35 | +| clip_range | 0.0731 | +| entropy_loss | -7.13 | +| explained_variance | 0.378 | +| learning_rate | 4.82e-05 | +| loss | -0.038 | +| n_updates | 30580 | +| policy_gradient_loss | -0.0219 | +| value_loss | 8.89e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1417 | +| iterations | 3692 | +| time_elapsed | 5334 | +| total_timesteps | 7561216 | +| train/ | | +| approx_kl | 0.011325905 | +| clip_fraction | 0.317 | +| clip_range | 0.0731 | +| entropy_loss | -6.96 | +| explained_variance | 0.365 | +| learning_rate | 4.82e-05 | +| loss | -0.0285 | +| n_updates | 30584 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000164 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1417 | +| iterations | 3693 | +| time_elapsed | 5336 | +| total_timesteps | 7563264 | +| train/ | | +| approx_kl | 0.011048697 | +| clip_fraction | 0.34 | +| clip_range | 0.0731 | +| entropy_loss | -6.88 | +| explained_variance | 0.351 | +| learning_rate | 4.82e-05 | +| loss | -0.0332 | +| n_updates | 30588 | +| policy_gradient_loss | -0.0199 | +| value_loss | 9.16e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1417 | +| iterations | 3694 | +| time_elapsed | 5337 | +| total_timesteps | 7565312 | +| train/ | | +| approx_kl | 0.012681859 | +| clip_fraction | 0.37 | +| clip_range | 0.0731 | +| entropy_loss | -6.83 | +| explained_variance | 0.663 | +| learning_rate | 4.82e-05 | +| loss | -0.0369 | +| n_updates | 30592 | +| policy_gradient_loss | -0.0222 | +| value_loss | 6.4e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1417 | +| iterations | 3695 | +| time_elapsed | 5339 | +| total_timesteps | 7567360 | +| train/ | | +| approx_kl | 0.012443995 | +| clip_fraction | 0.314 | +| clip_range | 0.0731 | +| entropy_loss | -7.21 | +| explained_variance | 0.16 | +| learning_rate | 4.82e-05 | +| loss | -0.03 | +| n_updates | 30596 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000244 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1417 | +| iterations | 3696 | +| time_elapsed | 5340 | +| total_timesteps | 7569408 | +| train/ | | +| approx_kl | 0.0120846 | +| clip_fraction | 0.31 | +| clip_range | 0.0731 | +| entropy_loss | -6.97 | +| explained_variance | 0.207 | +| learning_rate | 4.82e-05 | +| loss | -0.0296 | +| n_updates | 30600 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.0002 | +--------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1417 | +| iterations | 3697 | +| time_elapsed | 5342 | +| total_timesteps | 7571456 | +| train/ | | +| approx_kl | 0.01381658 | +| clip_fraction | 0.367 | +| clip_range | 0.0731 | +| entropy_loss | -6.63 | +| explained_variance | 0.516 | +| learning_rate | 4.82e-05 | +| loss | -0.0331 | +| n_updates | 30604 | +| policy_gradient_loss | -0.0226 | +| value_loss | 0.000106 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1417 | +| iterations | 3698 | +| time_elapsed | 5343 | +| total_timesteps | 7573504 | +| train/ | | +| approx_kl | 0.012648676 | +| clip_fraction | 0.345 | +| clip_range | 0.0731 | +| entropy_loss | -6.99 | +| explained_variance | 0.375 | +| learning_rate | 4.82e-05 | +| loss | -0.0381 | +| n_updates | 30608 | +| policy_gradient_loss | -0.0227 | +| value_loss | 9.68e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1417 | +| iterations | 3699 | +| time_elapsed | 5344 | +| total_timesteps | 7575552 | +| train/ | | +| approx_kl | 0.0125566125 | +| clip_fraction | 0.333 | +| clip_range | 0.0731 | +| entropy_loss | -7.15 | +| explained_variance | 0.00433 | +| learning_rate | 4.82e-05 | +| loss | -0.0321 | +| n_updates | 30612 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000183 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1417 | +| iterations | 3700 | +| time_elapsed | 5346 | +| total_timesteps | 7577600 | +| train/ | | +| approx_kl | 0.01130759 | +| clip_fraction | 0.317 | +| clip_range | 0.0731 | +| entropy_loss | -6.96 | +| explained_variance | 0.262 | +| learning_rate | 4.82e-05 | +| loss | -0.0281 | +| n_updates | 30616 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000247 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1417 | +| iterations | 3701 | +| time_elapsed | 5347 | +| total_timesteps | 7579648 | +| train/ | | +| approx_kl | 0.012553153 | +| clip_fraction | 0.348 | +| clip_range | 0.0731 | +| entropy_loss | -6.92 | +| explained_variance | 0.239 | +| learning_rate | 4.82e-05 | +| loss | -0.0415 | +| n_updates | 30620 | +| policy_gradient_loss | -0.0222 | +| value_loss | 0.000121 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1417 | +| iterations | 3702 | +| time_elapsed | 5349 | +| total_timesteps | 7581696 | +| train/ | | +| approx_kl | 0.013966585 | +| clip_fraction | 0.322 | +| clip_range | 0.0731 | +| entropy_loss | -7.28 | +| explained_variance | -0.105 | +| learning_rate | 4.82e-05 | +| loss | -0.0311 | +| n_updates | 30624 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000112 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1417 | +| iterations | 3703 | +| time_elapsed | 5350 | +| total_timesteps | 7583744 | +| train/ | | +| approx_kl | 0.01228722 | +| clip_fraction | 0.335 | +| clip_range | 0.0731 | +| entropy_loss | -7.18 | +| explained_variance | 0.358 | +| learning_rate | 4.82e-05 | +| loss | -0.0304 | +| n_updates | 30628 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000102 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1417 | +| iterations | 3704 | +| time_elapsed | 5351 | +| total_timesteps | 7585792 | +| train/ | | +| approx_kl | 0.011200054 | +| clip_fraction | 0.325 | +| clip_range | 0.0731 | +| entropy_loss | -7.27 | +| explained_variance | -0.0118 | +| learning_rate | 4.82e-05 | +| loss | -0.0276 | +| n_updates | 30632 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000289 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.43e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1417 | +| iterations | 3705 | +| time_elapsed | 5353 | +| total_timesteps | 7587840 | +| train/ | | +| approx_kl | 0.014200544 | +| clip_fraction | 0.345 | +| clip_range | 0.0731 | +| entropy_loss | -6.47 | +| explained_variance | 0.709 | +| learning_rate | 4.82e-05 | +| loss | -0.036 | +| n_updates | 30636 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.00011 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1417 | +| iterations | 3706 | +| time_elapsed | 5354 | +| total_timesteps | 7589888 | +| train/ | | +| approx_kl | 0.01471688 | +| clip_fraction | 0.342 | +| clip_range | 0.0731 | +| entropy_loss | -7.16 | +| explained_variance | 0.34 | +| learning_rate | 4.82e-05 | +| loss | -0.0358 | +| n_updates | 30640 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000141 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1417 | +| iterations | 3707 | +| time_elapsed | 5356 | +| total_timesteps | 7591936 | +| train/ | | +| approx_kl | 0.013000935 | +| clip_fraction | 0.337 | +| clip_range | 0.0731 | +| entropy_loss | -7.38 | +| explained_variance | -0.0336 | +| learning_rate | 4.82e-05 | +| loss | -0.0244 | +| n_updates | 30644 | +| policy_gradient_loss | -0.0199 | +| value_loss | 9.65e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.43e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1417 | +| iterations | 3708 | +| time_elapsed | 5357 | +| total_timesteps | 7593984 | +| train/ | | +| approx_kl | 0.014462173 | +| clip_fraction | 0.358 | +| clip_range | 0.0731 | +| entropy_loss | -6.87 | +| explained_variance | 0.553 | +| learning_rate | 4.82e-05 | +| loss | -0.0314 | +| n_updates | 30648 | +| policy_gradient_loss | -0.0229 | +| value_loss | 9.67e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.43e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1417 | +| iterations | 3709 | +| time_elapsed | 5359 | +| total_timesteps | 7596032 | +| train/ | | +| approx_kl | 0.010229396 | +| clip_fraction | 0.314 | +| clip_range | 0.0731 | +| entropy_loss | -6.82 | +| explained_variance | 0.415 | +| learning_rate | 4.82e-05 | +| loss | -0.0302 | +| n_updates | 30652 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000194 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1417 | +| iterations | 3710 | +| time_elapsed | 5360 | +| total_timesteps | 7598080 | +| train/ | | +| approx_kl | 0.011179965 | +| clip_fraction | 0.317 | +| clip_range | 0.0731 | +| entropy_loss | -7.05 | +| explained_variance | 0.342 | +| learning_rate | 4.82e-05 | +| loss | -0.0321 | +| n_updates | 30656 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000122 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1417 | +| iterations | 3711 | +| time_elapsed | 5362 | +| total_timesteps | 7600128 | +| train/ | | +| approx_kl | 0.011407953 | +| clip_fraction | 0.334 | +| clip_range | 0.0731 | +| entropy_loss | -6.92 | +| explained_variance | 0.52 | +| learning_rate | 4.82e-05 | +| loss | -0.0352 | +| n_updates | 30660 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.00011 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1417 | +| iterations | 3712 | +| time_elapsed | 5363 | +| total_timesteps | 7602176 | +| train/ | | +| approx_kl | 0.0111956885 | +| clip_fraction | 0.305 | +| clip_range | 0.0731 | +| entropy_loss | -6.78 | +| explained_variance | 0.325 | +| learning_rate | 4.82e-05 | +| loss | -0.0279 | +| n_updates | 30664 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000289 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1417 | +| iterations | 3713 | +| time_elapsed | 5364 | +| total_timesteps | 7604224 | +| train/ | | +| approx_kl | 0.014632949 | +| clip_fraction | 0.341 | +| clip_range | 0.0731 | +| entropy_loss | -7.21 | +| explained_variance | 0.102 | +| learning_rate | 4.82e-05 | +| loss | -0.0278 | +| n_updates | 30668 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000181 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1417 | +| iterations | 3714 | +| time_elapsed | 5366 | +| total_timesteps | 7606272 | +| train/ | | +| approx_kl | 0.011812906 | +| clip_fraction | 0.338 | +| clip_range | 0.0731 | +| entropy_loss | -6.8 | +| explained_variance | 0.0502 | +| learning_rate | 4.82e-05 | +| loss | -0.0297 | +| n_updates | 30672 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000259 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1417 | +| iterations | 3715 | +| time_elapsed | 5367 | +| total_timesteps | 7608320 | +| train/ | | +| approx_kl | 0.013377301 | +| clip_fraction | 0.349 | +| clip_range | 0.0731 | +| entropy_loss | -7.19 | +| explained_variance | 0.0786 | +| learning_rate | 4.82e-05 | +| loss | -0.0333 | +| n_updates | 30676 | +| policy_gradient_loss | -0.0223 | +| value_loss | 0.000148 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1417 | +| iterations | 3716 | +| time_elapsed | 5369 | +| total_timesteps | 7610368 | +| train/ | | +| approx_kl | 0.014499892 | +| clip_fraction | 0.357 | +| clip_range | 0.0731 | +| entropy_loss | -7.24 | +| explained_variance | -0.106 | +| learning_rate | 4.82e-05 | +| loss | -0.0337 | +| n_updates | 30680 | +| policy_gradient_loss | -0.0219 | +| value_loss | 0.000136 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1417 | +| iterations | 3717 | +| time_elapsed | 5370 | +| total_timesteps | 7612416 | +| train/ | | +| approx_kl | 0.011057214 | +| clip_fraction | 0.321 | +| clip_range | 0.0731 | +| entropy_loss | -6.95 | +| explained_variance | 0.069 | +| learning_rate | 4.82e-05 | +| loss | -0.0242 | +| n_updates | 30684 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000594 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1417 | +| iterations | 3718 | +| time_elapsed | 5372 | +| total_timesteps | 7614464 | +| train/ | | +| approx_kl | 0.009716397 | +| clip_fraction | 0.316 | +| clip_range | 0.0731 | +| entropy_loss | -6.59 | +| explained_variance | 0.217 | +| learning_rate | 4.82e-05 | +| loss | -0.0244 | +| n_updates | 30688 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000352 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1417 | +| iterations | 3719 | +| time_elapsed | 5373 | +| total_timesteps | 7616512 | +| train/ | | +| approx_kl | 0.012482594 | +| clip_fraction | 0.348 | +| clip_range | 0.0731 | +| entropy_loss | -7.18 | +| explained_variance | 0.103 | +| learning_rate | 4.82e-05 | +| loss | -0.0371 | +| n_updates | 30692 | +| policy_gradient_loss | -0.0225 | +| value_loss | 0.000171 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1417 | +| iterations | 3720 | +| time_elapsed | 5374 | +| total_timesteps | 7618560 | +| train/ | | +| approx_kl | 0.012372619 | +| clip_fraction | 0.348 | +| clip_range | 0.0731 | +| entropy_loss | -7.41 | +| explained_variance | -0.00953 | +| learning_rate | 4.82e-05 | +| loss | -0.0391 | +| n_updates | 30696 | +| policy_gradient_loss | -0.0224 | +| value_loss | 0.000145 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1417 | +| iterations | 3721 | +| time_elapsed | 5376 | +| total_timesteps | 7620608 | +| train/ | | +| approx_kl | 0.013782339 | +| clip_fraction | 0.326 | +| clip_range | 0.0731 | +| entropy_loss | -7.14 | +| explained_variance | 0.178 | +| learning_rate | 4.82e-05 | +| loss | -0.028 | +| n_updates | 30700 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000155 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1417 | +| iterations | 3722 | +| time_elapsed | 5377 | +| total_timesteps | 7622656 | +| train/ | | +| approx_kl | 0.0125963185 | +| clip_fraction | 0.331 | +| clip_range | 0.0731 | +| entropy_loss | -6.57 | +| explained_variance | 0.518 | +| learning_rate | 4.82e-05 | +| loss | -0.028 | +| n_updates | 30704 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000168 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1417 | +| iterations | 3723 | +| time_elapsed | 5379 | +| total_timesteps | 7624704 | +| train/ | | +| approx_kl | 0.013397539 | +| clip_fraction | 0.325 | +| clip_range | 0.0731 | +| entropy_loss | -6.89 | +| explained_variance | 0.331 | +| learning_rate | 4.82e-05 | +| loss | -0.032 | +| n_updates | 30708 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000258 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1417 | +| iterations | 3724 | +| time_elapsed | 5380 | +| total_timesteps | 7626752 | +| train/ | | +| approx_kl | 0.014679851 | +| clip_fraction | 0.364 | +| clip_range | 0.0731 | +| entropy_loss | -7.1 | +| explained_variance | -0.136 | +| learning_rate | 4.82e-05 | +| loss | -0.0396 | +| n_updates | 30712 | +| policy_gradient_loss | -0.0236 | +| value_loss | 0.000136 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1417 | +| iterations | 3725 | +| time_elapsed | 5381 | +| total_timesteps | 7628800 | +| train/ | | +| approx_kl | 0.012948111 | +| clip_fraction | 0.331 | +| clip_range | 0.0731 | +| entropy_loss | -7.22 | +| explained_variance | -0.212 | +| learning_rate | 4.82e-05 | +| loss | -0.034 | +| n_updates | 30716 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000171 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1417 | +| iterations | 3726 | +| time_elapsed | 5383 | +| total_timesteps | 7630848 | +| train/ | | +| approx_kl | 0.014995569 | +| clip_fraction | 0.359 | +| clip_range | 0.0731 | +| entropy_loss | -7.09 | +| explained_variance | 0.348 | +| learning_rate | 4.82e-05 | +| loss | -0.0371 | +| n_updates | 30720 | +| policy_gradient_loss | -0.0235 | +| value_loss | 9.93e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1417 | +| iterations | 3727 | +| time_elapsed | 5384 | +| total_timesteps | 7632896 | +| train/ | | +| approx_kl | 0.013969911 | +| clip_fraction | 0.319 | +| clip_range | 0.0731 | +| entropy_loss | -7.18 | +| explained_variance | 0.287 | +| learning_rate | 4.82e-05 | +| loss | -0.0341 | +| n_updates | 30724 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000143 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1417 | +| iterations | 3728 | +| time_elapsed | 5386 | +| total_timesteps | 7634944 | +| train/ | | +| approx_kl | 0.012147803 | +| clip_fraction | 0.324 | +| clip_range | 0.0731 | +| entropy_loss | -6.99 | +| explained_variance | 0.389 | +| learning_rate | 4.82e-05 | +| loss | -0.028 | +| n_updates | 30728 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000164 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1417 | +| iterations | 3729 | +| time_elapsed | 5387 | +| total_timesteps | 7636992 | +| train/ | | +| approx_kl | 0.011317285 | +| clip_fraction | 0.308 | +| clip_range | 0.0731 | +| entropy_loss | -7 | +| explained_variance | 0.249 | +| learning_rate | 4.82e-05 | +| loss | -0.0311 | +| n_updates | 30732 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000184 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1417 | +| iterations | 3730 | +| time_elapsed | 5388 | +| total_timesteps | 7639040 | +| train/ | | +| approx_kl | 0.011968087 | +| clip_fraction | 0.351 | +| clip_range | 0.0731 | +| entropy_loss | -7.18 | +| explained_variance | -0.215 | +| learning_rate | 4.82e-05 | +| loss | -0.0342 | +| n_updates | 30736 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000168 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1417 | +| iterations | 3731 | +| time_elapsed | 5390 | +| total_timesteps | 7641088 | +| train/ | | +| approx_kl | 0.012906076 | +| clip_fraction | 0.348 | +| clip_range | 0.0731 | +| entropy_loss | -6.94 | +| explained_variance | 0.321 | +| learning_rate | 4.82e-05 | +| loss | -0.0363 | +| n_updates | 30740 | +| policy_gradient_loss | -0.0219 | +| value_loss | 0.0001 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1417 | +| iterations | 3732 | +| time_elapsed | 5391 | +| total_timesteps | 7643136 | +| train/ | | +| approx_kl | 0.012307142 | +| clip_fraction | 0.308 | +| clip_range | 0.0731 | +| entropy_loss | -7.13 | +| explained_variance | 0.237 | +| learning_rate | 4.82e-05 | +| loss | -0.0291 | +| n_updates | 30744 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.0002 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1417 | +| iterations | 3733 | +| time_elapsed | 5393 | +| total_timesteps | 7645184 | +| train/ | | +| approx_kl | 0.011191488 | +| clip_fraction | 0.309 | +| clip_range | 0.0731 | +| entropy_loss | -7.05 | +| explained_variance | 0.303 | +| learning_rate | 4.82e-05 | +| loss | -0.0283 | +| n_updates | 30748 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.00028 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1417 | +| iterations | 3734 | +| time_elapsed | 5394 | +| total_timesteps | 7647232 | +| train/ | | +| approx_kl | 0.009617705 | +| clip_fraction | 0.312 | +| clip_range | 0.0731 | +| entropy_loss | -7.19 | +| explained_variance | -0.271 | +| learning_rate | 4.82e-05 | +| loss | -0.0295 | +| n_updates | 30752 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000155 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1417 | +| iterations | 3735 | +| time_elapsed | 5396 | +| total_timesteps | 7649280 | +| train/ | | +| approx_kl | 0.013693936 | +| clip_fraction | 0.361 | +| clip_range | 0.0731 | +| entropy_loss | -6.91 | +| explained_variance | 0.569 | +| learning_rate | 4.82e-05 | +| loss | -0.0368 | +| n_updates | 30756 | +| policy_gradient_loss | -0.023 | +| value_loss | 7.6e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1417 | +| iterations | 3736 | +| time_elapsed | 5397 | +| total_timesteps | 7651328 | +| train/ | | +| approx_kl | 0.012225328 | +| clip_fraction | 0.316 | +| clip_range | 0.0731 | +| entropy_loss | -7.15 | +| explained_variance | 0.152 | +| learning_rate | 4.82e-05 | +| loss | -0.024 | +| n_updates | 30760 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000284 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1417 | +| iterations | 3737 | +| time_elapsed | 5399 | +| total_timesteps | 7653376 | +| train/ | | +| approx_kl | 0.011983424 | +| clip_fraction | 0.318 | +| clip_range | 0.0731 | +| entropy_loss | -7.15 | +| explained_variance | 0.256 | +| learning_rate | 4.82e-05 | +| loss | -0.0319 | +| n_updates | 30764 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000137 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1417 | +| iterations | 3738 | +| time_elapsed | 5400 | +| total_timesteps | 7655424 | +| train/ | | +| approx_kl | 0.012482766 | +| clip_fraction | 0.323 | +| clip_range | 0.0731 | +| entropy_loss | -6.84 | +| explained_variance | 0.341 | +| learning_rate | 4.82e-05 | +| loss | -0.0307 | +| n_updates | 30768 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000213 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1417 | +| iterations | 3739 | +| time_elapsed | 5401 | +| total_timesteps | 7657472 | +| train/ | | +| approx_kl | 0.010529919 | +| clip_fraction | 0.345 | +| clip_range | 0.0731 | +| entropy_loss | -7.23 | +| explained_variance | -0.124 | +| learning_rate | 4.82e-05 | +| loss | -0.0323 | +| n_updates | 30772 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000155 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1417 | +| iterations | 3740 | +| time_elapsed | 5403 | +| total_timesteps | 7659520 | +| train/ | | +| approx_kl | 0.008013478 | +| clip_fraction | 0.307 | +| clip_range | 0.0731 | +| entropy_loss | -6.98 | +| explained_variance | 0.259 | +| learning_rate | 4.82e-05 | +| loss | -0.0227 | +| n_updates | 30776 | +| policy_gradient_loss | -0.0142 | +| value_loss | 0.000265 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1417 | +| iterations | 3741 | +| time_elapsed | 5404 | +| total_timesteps | 7661568 | +| train/ | | +| approx_kl | 0.013088105 | +| clip_fraction | 0.34 | +| clip_range | 0.0731 | +| entropy_loss | -6.77 | +| explained_variance | 0.539 | +| learning_rate | 4.82e-05 | +| loss | -0.0303 | +| n_updates | 30780 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000207 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1417 | +| iterations | 3742 | +| time_elapsed | 5406 | +| total_timesteps | 7663616 | +| train/ | | +| approx_kl | 0.0121278595 | +| clip_fraction | 0.333 | +| clip_range | 0.0731 | +| entropy_loss | -6.99 | +| explained_variance | 0.225 | +| learning_rate | 4.82e-05 | +| loss | -0.0327 | +| n_updates | 30784 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000155 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1417 | +| iterations | 3743 | +| time_elapsed | 5407 | +| total_timesteps | 7665664 | +| train/ | | +| approx_kl | 0.011400645 | +| clip_fraction | 0.357 | +| clip_range | 0.0731 | +| entropy_loss | -7.15 | +| explained_variance | 0.521 | +| learning_rate | 4.82e-05 | +| loss | -0.044 | +| n_updates | 30788 | +| policy_gradient_loss | -0.0245 | +| value_loss | 6.84e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1417 | +| iterations | 3744 | +| time_elapsed | 5408 | +| total_timesteps | 7667712 | +| train/ | | +| approx_kl | 0.013953129 | +| clip_fraction | 0.347 | +| clip_range | 0.0731 | +| entropy_loss | -6.76 | +| explained_variance | 0.546 | +| learning_rate | 4.82e-05 | +| loss | -0.0256 | +| n_updates | 30792 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000141 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1417 | +| iterations | 3745 | +| time_elapsed | 5410 | +| total_timesteps | 7669760 | +| train/ | | +| approx_kl | 0.013233214 | +| clip_fraction | 0.346 | +| clip_range | 0.0731 | +| entropy_loss | -7.05 | +| explained_variance | 0.279 | +| learning_rate | 4.82e-05 | +| loss | -0.0406 | +| n_updates | 30796 | +| policy_gradient_loss | -0.0224 | +| value_loss | 0.000101 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1417 | +| iterations | 3746 | +| time_elapsed | 5411 | +| total_timesteps | 7671808 | +| train/ | | +| approx_kl | 0.011194992 | +| clip_fraction | 0.337 | +| clip_range | 0.0731 | +| entropy_loss | -6.86 | +| explained_variance | 0.269 | +| learning_rate | 4.82e-05 | +| loss | -0.0288 | +| n_updates | 30800 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000171 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1417 | +| iterations | 3747 | +| time_elapsed | 5413 | +| total_timesteps | 7673856 | +| train/ | | +| approx_kl | 0.011983529 | +| clip_fraction | 0.32 | +| clip_range | 0.0731 | +| entropy_loss | -6.96 | +| explained_variance | 0.17 | +| learning_rate | 4.82e-05 | +| loss | -0.0334 | +| n_updates | 30804 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000155 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1417 | +| iterations | 3748 | +| time_elapsed | 5414 | +| total_timesteps | 7675904 | +| train/ | | +| approx_kl | 0.012952699 | +| clip_fraction | 0.328 | +| clip_range | 0.0731 | +| entropy_loss | -6.99 | +| explained_variance | 0.373 | +| learning_rate | 4.82e-05 | +| loss | -0.0313 | +| n_updates | 30808 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000178 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1417 | +| iterations | 3749 | +| time_elapsed | 5416 | +| total_timesteps | 7677952 | +| train/ | | +| approx_kl | 0.011944063 | +| clip_fraction | 0.328 | +| clip_range | 0.0731 | +| entropy_loss | -7.29 | +| explained_variance | 0.00731 | +| learning_rate | 4.82e-05 | +| loss | -0.036 | +| n_updates | 30812 | +| policy_gradient_loss | -0.022 | +| value_loss | 0.000119 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1417 | +| iterations | 3750 | +| time_elapsed | 5417 | +| total_timesteps | 7680000 | +| train/ | | +| approx_kl | 0.010933712 | +| clip_fraction | 0.345 | +| clip_range | 0.0731 | +| entropy_loss | -7.41 | +| explained_variance | -0.288 | +| learning_rate | 4.82e-05 | +| loss | -0.0385 | +| n_updates | 30816 | +| policy_gradient_loss | -0.0251 | +| value_loss | 7.31e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1417 | +| iterations | 3751 | +| time_elapsed | 5419 | +| total_timesteps | 7682048 | +| train/ | | +| approx_kl | 0.011706436 | +| clip_fraction | 0.315 | +| clip_range | 0.0731 | +| entropy_loss | -6.94 | +| explained_variance | 0.502 | +| learning_rate | 4.82e-05 | +| loss | -0.031 | +| n_updates | 30820 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000155 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1417 | +| iterations | 3752 | +| time_elapsed | 5420 | +| total_timesteps | 7684096 | +| train/ | | +| approx_kl | 0.010504023 | +| clip_fraction | 0.294 | +| clip_range | 0.0731 | +| entropy_loss | -7.42 | +| explained_variance | -0.109 | +| learning_rate | 4.82e-05 | +| loss | -0.0296 | +| n_updates | 30824 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000136 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1417 | +| iterations | 3753 | +| time_elapsed | 5421 | +| total_timesteps | 7686144 | +| train/ | | +| approx_kl | 0.00921296 | +| clip_fraction | 0.296 | +| clip_range | 0.0731 | +| entropy_loss | -6.96 | +| explained_variance | 0.653 | +| learning_rate | 4.82e-05 | +| loss | -0.0269 | +| n_updates | 30828 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000123 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1417 | +| iterations | 3754 | +| time_elapsed | 5423 | +| total_timesteps | 7688192 | +| train/ | | +| approx_kl | 0.012844135 | +| clip_fraction | 0.308 | +| clip_range | 0.0731 | +| entropy_loss | -6.42 | +| explained_variance | 0.727 | +| learning_rate | 4.82e-05 | +| loss | -0.0338 | +| n_updates | 30832 | +| policy_gradient_loss | -0.0179 | +| value_loss | 8.46e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1417 | +| iterations | 3755 | +| time_elapsed | 5424 | +| total_timesteps | 7690240 | +| train/ | | +| approx_kl | 0.0129746925 | +| clip_fraction | 0.332 | +| clip_range | 0.0731 | +| entropy_loss | -7.29 | +| explained_variance | -0.226 | +| learning_rate | 4.82e-05 | +| loss | -0.0313 | +| n_updates | 30836 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000124 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1417 | +| iterations | 3756 | +| time_elapsed | 5426 | +| total_timesteps | 7692288 | +| train/ | | +| approx_kl | 0.012921959 | +| clip_fraction | 0.328 | +| clip_range | 0.0731 | +| entropy_loss | -7.05 | +| explained_variance | 0.264 | +| learning_rate | 4.82e-05 | +| loss | -0.0261 | +| n_updates | 30840 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000142 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1417 | +| iterations | 3757 | +| time_elapsed | 5427 | +| total_timesteps | 7694336 | +| train/ | | +| approx_kl | 0.012564553 | +| clip_fraction | 0.34 | +| clip_range | 0.0731 | +| entropy_loss | -7.12 | +| explained_variance | 0.277 | +| learning_rate | 4.82e-05 | +| loss | -0.0348 | +| n_updates | 30844 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000111 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1417 | +| iterations | 3758 | +| time_elapsed | 5429 | +| total_timesteps | 7696384 | +| train/ | | +| approx_kl | 0.011224519 | +| clip_fraction | 0.312 | +| clip_range | 0.0731 | +| entropy_loss | -7.18 | +| explained_variance | 0.31 | +| learning_rate | 4.82e-05 | +| loss | -0.0326 | +| n_updates | 30848 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000165 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1417 | +| iterations | 3759 | +| time_elapsed | 5430 | +| total_timesteps | 7698432 | +| train/ | | +| approx_kl | 0.012753611 | +| clip_fraction | 0.337 | +| clip_range | 0.0731 | +| entropy_loss | -6.89 | +| explained_variance | 0.549 | +| learning_rate | 4.82e-05 | +| loss | -0.0334 | +| n_updates | 30852 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000122 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1417 | +| iterations | 3760 | +| time_elapsed | 5432 | +| total_timesteps | 7700480 | +| train/ | | +| approx_kl | 0.011396807 | +| clip_fraction | 0.329 | +| clip_range | 0.0731 | +| entropy_loss | -7.27 | +| explained_variance | -0.124 | +| learning_rate | 4.82e-05 | +| loss | -0.0351 | +| n_updates | 30856 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000106 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1417 | +| iterations | 3761 | +| time_elapsed | 5433 | +| total_timesteps | 7702528 | +| train/ | | +| approx_kl | 0.0118220225 | +| clip_fraction | 0.327 | +| clip_range | 0.0731 | +| entropy_loss | -7.25 | +| explained_variance | -0.053 | +| learning_rate | 4.82e-05 | +| loss | -0.032 | +| n_updates | 30860 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000118 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1417 | +| iterations | 3762 | +| time_elapsed | 5434 | +| total_timesteps | 7704576 | +| train/ | | +| approx_kl | 0.010976443 | +| clip_fraction | 0.303 | +| clip_range | 0.0731 | +| entropy_loss | -7.12 | +| explained_variance | 0.437 | +| learning_rate | 4.82e-05 | +| loss | -0.0305 | +| n_updates | 30864 | +| policy_gradient_loss | -0.019 | +| value_loss | 9.16e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1417 | +| iterations | 3763 | +| time_elapsed | 5436 | +| total_timesteps | 7706624 | +| train/ | | +| approx_kl | 0.010054078 | +| clip_fraction | 0.295 | +| clip_range | 0.0731 | +| entropy_loss | -6.63 | +| explained_variance | 0.409 | +| learning_rate | 4.82e-05 | +| loss | -0.0188 | +| n_updates | 30868 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.000324 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.384 | +| time/ | | +| fps | 1417 | +| iterations | 3764 | +| time_elapsed | 5437 | +| total_timesteps | 7708672 | +| train/ | | +| approx_kl | 0.013525331 | +| clip_fraction | 0.313 | +| clip_range | 0.0731 | +| entropy_loss | -7.16 | +| explained_variance | 0.194 | +| learning_rate | 4.82e-05 | +| loss | -0.0321 | +| n_updates | 30872 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000227 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1417 | +| iterations | 3765 | +| time_elapsed | 5439 | +| total_timesteps | 7710720 | +| train/ | | +| approx_kl | 0.009047773 | +| clip_fraction | 0.317 | +| clip_range | 0.0731 | +| entropy_loss | -7.15 | +| explained_variance | 0.386 | +| learning_rate | 4.82e-05 | +| loss | -0.0263 | +| n_updates | 30876 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000178 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1417 | +| iterations | 3766 | +| time_elapsed | 5440 | +| total_timesteps | 7712768 | +| train/ | | +| approx_kl | 0.01100206 | +| clip_fraction | 0.329 | +| clip_range | 0.0731 | +| entropy_loss | -7.04 | +| explained_variance | 0.277 | +| learning_rate | 4.82e-05 | +| loss | -0.0378 | +| n_updates | 30880 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000164 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.386 | +| time/ | | +| fps | 1417 | +| iterations | 3767 | +| time_elapsed | 5441 | +| total_timesteps | 7714816 | +| train/ | | +| approx_kl | 0.015728615 | +| clip_fraction | 0.308 | +| clip_range | 0.0731 | +| entropy_loss | -7.01 | +| explained_variance | 0.523 | +| learning_rate | 4.82e-05 | +| loss | -0.0326 | +| n_updates | 30884 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.00015 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.385 | +| time/ | | +| fps | 1417 | +| iterations | 3768 | +| time_elapsed | 5443 | +| total_timesteps | 7716864 | +| train/ | | +| approx_kl | 0.013917534 | +| clip_fraction | 0.331 | +| clip_range | 0.0731 | +| entropy_loss | -6.85 | +| explained_variance | 0.405 | +| learning_rate | 4.82e-05 | +| loss | -0.0349 | +| n_updates | 30888 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000224 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1417 | +| iterations | 3769 | +| time_elapsed | 5444 | +| total_timesteps | 7718912 | +| train/ | | +| approx_kl | 0.01264592 | +| clip_fraction | 0.292 | +| clip_range | 0.0731 | +| entropy_loss | -7.17 | +| explained_variance | 0.243 | +| learning_rate | 4.82e-05 | +| loss | -0.034 | +| n_updates | 30892 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000164 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.386 | +| time/ | | +| fps | 1417 | +| iterations | 3770 | +| time_elapsed | 5446 | +| total_timesteps | 7720960 | +| train/ | | +| approx_kl | 0.009507352 | +| clip_fraction | 0.302 | +| clip_range | 0.0731 | +| entropy_loss | -7.21 | +| explained_variance | 0.213 | +| learning_rate | 4.82e-05 | +| loss | -0.034 | +| n_updates | 30896 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000228 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.389 | +| time/ | | +| fps | 1417 | +| iterations | 3771 | +| time_elapsed | 5447 | +| total_timesteps | 7723008 | +| train/ | | +| approx_kl | 0.009578587 | +| clip_fraction | 0.31 | +| clip_range | 0.0731 | +| entropy_loss | -7.29 | +| explained_variance | -0.167 | +| learning_rate | 4.82e-05 | +| loss | -0.0307 | +| n_updates | 30900 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000217 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.389 | +| time/ | | +| fps | 1417 | +| iterations | 3772 | +| time_elapsed | 5449 | +| total_timesteps | 7725056 | +| train/ | | +| approx_kl | 0.011075844 | +| clip_fraction | 0.34 | +| clip_range | 0.0731 | +| entropy_loss | -6.77 | +| explained_variance | 0.258 | +| learning_rate | 4.82e-05 | +| loss | -0.0321 | +| n_updates | 30904 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000286 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.391 | +| time/ | | +| fps | 1417 | +| iterations | 3773 | +| time_elapsed | 5450 | +| total_timesteps | 7727104 | +| train/ | | +| approx_kl | 0.011525547 | +| clip_fraction | 0.316 | +| clip_range | 0.0731 | +| entropy_loss | -7.15 | +| explained_variance | 0.361 | +| learning_rate | 4.82e-05 | +| loss | -0.0223 | +| n_updates | 30908 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000112 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.391 | +| time/ | | +| fps | 1417 | +| iterations | 3774 | +| time_elapsed | 5452 | +| total_timesteps | 7729152 | +| train/ | | +| approx_kl | 0.011643085 | +| clip_fraction | 0.311 | +| clip_range | 0.0731 | +| entropy_loss | -7.22 | +| explained_variance | 0.194 | +| learning_rate | 4.82e-05 | +| loss | -0.0328 | +| n_updates | 30912 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000238 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.401 | +| time/ | | +| fps | 1417 | +| iterations | 3775 | +| time_elapsed | 5453 | +| total_timesteps | 7731200 | +| train/ | | +| approx_kl | 0.010278851 | +| clip_fraction | 0.332 | +| clip_range | 0.0731 | +| entropy_loss | -7.26 | +| explained_variance | -0.81 | +| learning_rate | 4.82e-05 | +| loss | -0.0431 | +| n_updates | 30916 | +| policy_gradient_loss | -0.023 | +| value_loss | 8.01e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.402 | +| time/ | | +| fps | 1417 | +| iterations | 3776 | +| time_elapsed | 5454 | +| total_timesteps | 7733248 | +| train/ | | +| approx_kl | 0.010199796 | +| clip_fraction | 0.315 | +| clip_range | 0.0731 | +| entropy_loss | -6.65 | +| explained_variance | 0.281 | +| learning_rate | 4.82e-05 | +| loss | -0.0304 | +| n_updates | 30920 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000405 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.399 | +| time/ | | +| fps | 1417 | +| iterations | 3777 | +| time_elapsed | 5456 | +| total_timesteps | 7735296 | +| train/ | | +| approx_kl | 0.012490277 | +| clip_fraction | 0.301 | +| clip_range | 0.0731 | +| entropy_loss | -6.58 | +| explained_variance | 0.324 | +| learning_rate | 4.82e-05 | +| loss | -0.0296 | +| n_updates | 30924 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000353 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.399 | +| time/ | | +| fps | 1417 | +| iterations | 3778 | +| time_elapsed | 5457 | +| total_timesteps | 7737344 | +| train/ | | +| approx_kl | 0.013684036 | +| clip_fraction | 0.358 | +| clip_range | 0.0731 | +| entropy_loss | -6.84 | +| explained_variance | 0.478 | +| learning_rate | 4.82e-05 | +| loss | -0.0384 | +| n_updates | 30928 | +| policy_gradient_loss | -0.0235 | +| value_loss | 0.000133 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.399 | +| time/ | | +| fps | 1417 | +| iterations | 3779 | +| time_elapsed | 5459 | +| total_timesteps | 7739392 | +| train/ | | +| approx_kl | 0.011455263 | +| clip_fraction | 0.371 | +| clip_range | 0.0731 | +| entropy_loss | -7.3 | +| explained_variance | -0.421 | +| learning_rate | 4.82e-05 | +| loss | -0.0387 | +| n_updates | 30932 | +| policy_gradient_loss | -0.0248 | +| value_loss | 0.000111 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.396 | +| time/ | | +| fps | 1417 | +| iterations | 3780 | +| time_elapsed | 5460 | +| total_timesteps | 7741440 | +| train/ | | +| approx_kl | 0.011690143 | +| clip_fraction | 0.348 | +| clip_range | 0.0731 | +| entropy_loss | -7.36 | +| explained_variance | -0.254 | +| learning_rate | 4.82e-05 | +| loss | -0.0401 | +| n_updates | 30936 | +| policy_gradient_loss | -0.0225 | +| value_loss | 7.46e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.396 | +| time/ | | +| fps | 1417 | +| iterations | 3781 | +| time_elapsed | 5462 | +| total_timesteps | 7743488 | +| train/ | | +| approx_kl | 0.011620687 | +| clip_fraction | 0.302 | +| clip_range | 0.0731 | +| entropy_loss | -6.74 | +| explained_variance | 0.397 | +| learning_rate | 4.82e-05 | +| loss | -0.0258 | +| n_updates | 30940 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.00026 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.396 | +| time/ | | +| fps | 1417 | +| iterations | 3782 | +| time_elapsed | 5463 | +| total_timesteps | 7745536 | +| train/ | | +| approx_kl | 0.012210625 | +| clip_fraction | 0.31 | +| clip_range | 0.0731 | +| entropy_loss | -7.03 | +| explained_variance | 0.231 | +| learning_rate | 4.82e-05 | +| loss | -0.0245 | +| n_updates | 30944 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000217 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.393 | +| time/ | | +| fps | 1417 | +| iterations | 3783 | +| time_elapsed | 5465 | +| total_timesteps | 7747584 | +| train/ | | +| approx_kl | 0.012550948 | +| clip_fraction | 0.339 | +| clip_range | 0.0731 | +| entropy_loss | -7.12 | +| explained_variance | 0.216 | +| learning_rate | 4.82e-05 | +| loss | -0.0363 | +| n_updates | 30948 | +| policy_gradient_loss | -0.0222 | +| value_loss | 0.000155 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.386 | +| time/ | | +| fps | 1417 | +| iterations | 3784 | +| time_elapsed | 5466 | +| total_timesteps | 7749632 | +| train/ | | +| approx_kl | 0.011855977 | +| clip_fraction | 0.36 | +| clip_range | 0.0731 | +| entropy_loss | -7.18 | +| explained_variance | -0.125 | +| learning_rate | 4.82e-05 | +| loss | -0.037 | +| n_updates | 30952 | +| policy_gradient_loss | -0.0234 | +| value_loss | 8.14e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.392 | +| time/ | | +| fps | 1417 | +| iterations | 3785 | +| time_elapsed | 5467 | +| total_timesteps | 7751680 | +| train/ | | +| approx_kl | 0.011431618 | +| clip_fraction | 0.305 | +| clip_range | 0.0731 | +| entropy_loss | -6.75 | +| explained_variance | 0.47 | +| learning_rate | 4.82e-05 | +| loss | -0.0277 | +| n_updates | 30956 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000202 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.392 | +| time/ | | +| fps | 1417 | +| iterations | 3786 | +| time_elapsed | 5469 | +| total_timesteps | 7753728 | +| train/ | | +| approx_kl | 0.013340216 | +| clip_fraction | 0.331 | +| clip_range | 0.0731 | +| entropy_loss | -7.02 | +| explained_variance | 0.359 | +| learning_rate | 4.82e-05 | +| loss | -0.0354 | +| n_updates | 30960 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000124 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.392 | +| time/ | | +| fps | 1417 | +| iterations | 3787 | +| time_elapsed | 5470 | +| total_timesteps | 7755776 | +| train/ | | +| approx_kl | 0.0126217995 | +| clip_fraction | 0.301 | +| clip_range | 0.0731 | +| entropy_loss | -7.08 | +| explained_variance | 0.339 | +| learning_rate | 4.82e-05 | +| loss | -0.0307 | +| n_updates | 30964 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000135 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.389 | +| time/ | | +| fps | 1417 | +| iterations | 3788 | +| time_elapsed | 5472 | +| total_timesteps | 7757824 | +| train/ | | +| approx_kl | 0.010212071 | +| clip_fraction | 0.353 | +| clip_range | 0.0731 | +| entropy_loss | -7.39 | +| explained_variance | -0.133 | +| learning_rate | 4.82e-05 | +| loss | -0.0351 | +| n_updates | 30968 | +| policy_gradient_loss | -0.0206 | +| value_loss | 9.33e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.388 | +| time/ | | +| fps | 1417 | +| iterations | 3789 | +| time_elapsed | 5473 | +| total_timesteps | 7759872 | +| train/ | | +| approx_kl | 0.012382704 | +| clip_fraction | 0.325 | +| clip_range | 0.0731 | +| entropy_loss | -6.63 | +| explained_variance | 0.628 | +| learning_rate | 4.82e-05 | +| loss | -0.0332 | +| n_updates | 30972 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000104 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.388 | +| time/ | | +| fps | 1417 | +| iterations | 3790 | +| time_elapsed | 5475 | +| total_timesteps | 7761920 | +| train/ | | +| approx_kl | 0.013536217 | +| clip_fraction | 0.346 | +| clip_range | 0.0731 | +| entropy_loss | -6.79 | +| explained_variance | 0.494 | +| learning_rate | 4.82e-05 | +| loss | -0.0332 | +| n_updates | 30976 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000118 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.388 | +| time/ | | +| fps | 1417 | +| iterations | 3791 | +| time_elapsed | 5476 | +| total_timesteps | 7763968 | +| train/ | | +| approx_kl | 0.01089834 | +| clip_fraction | 0.318 | +| clip_range | 0.0731 | +| entropy_loss | -7.29 | +| explained_variance | -0.153 | +| learning_rate | 4.82e-05 | +| loss | -0.0338 | +| n_updates | 30980 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000137 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.398 | +| time/ | | +| fps | 1417 | +| iterations | 3792 | +| time_elapsed | 5478 | +| total_timesteps | 7766016 | +| train/ | | +| approx_kl | 0.010621542 | +| clip_fraction | 0.333 | +| clip_range | 0.0731 | +| entropy_loss | -7.22 | +| explained_variance | 0.367 | +| learning_rate | 4.82e-05 | +| loss | -0.0316 | +| n_updates | 30984 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000137 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.399 | +| time/ | | +| fps | 1417 | +| iterations | 3793 | +| time_elapsed | 5479 | +| total_timesteps | 7768064 | +| train/ | | +| approx_kl | 0.009844486 | +| clip_fraction | 0.278 | +| clip_range | 0.0731 | +| entropy_loss | -7.02 | +| explained_variance | 0.257 | +| learning_rate | 4.82e-05 | +| loss | -0.028 | +| n_updates | 30988 | +| policy_gradient_loss | -0.0143 | +| value_loss | 0.000314 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.397 | +| time/ | | +| fps | 1417 | +| iterations | 3794 | +| time_elapsed | 5481 | +| total_timesteps | 7770112 | +| train/ | | +| approx_kl | 0.010627195 | +| clip_fraction | 0.309 | +| clip_range | 0.0731 | +| entropy_loss | -7.07 | +| explained_variance | 0.327 | +| learning_rate | 4.82e-05 | +| loss | -0.0295 | +| n_updates | 30992 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000166 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.396 | +| time/ | | +| fps | 1417 | +| iterations | 3795 | +| time_elapsed | 5482 | +| total_timesteps | 7772160 | +| train/ | | +| approx_kl | 0.013869127 | +| clip_fraction | 0.346 | +| clip_range | 0.0731 | +| entropy_loss | -7 | +| explained_variance | 0.228 | +| learning_rate | 4.82e-05 | +| loss | -0.0332 | +| n_updates | 30996 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000137 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.396 | +| time/ | | +| fps | 1417 | +| iterations | 3796 | +| time_elapsed | 5483 | +| total_timesteps | 7774208 | +| train/ | | +| approx_kl | 0.0131280795 | +| clip_fraction | 0.33 | +| clip_range | 0.0731 | +| entropy_loss | -7.27 | +| explained_variance | -0.175 | +| learning_rate | 4.82e-05 | +| loss | -0.0372 | +| n_updates | 31000 | +| policy_gradient_loss | -0.0225 | +| value_loss | 0.000141 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.395 | +| time/ | | +| fps | 1417 | +| iterations | 3797 | +| time_elapsed | 5485 | +| total_timesteps | 7776256 | +| train/ | | +| approx_kl | 0.012050587 | +| clip_fraction | 0.335 | +| clip_range | 0.0731 | +| entropy_loss | -7.12 | +| explained_variance | 0.253 | +| learning_rate | 4.82e-05 | +| loss | -0.0294 | +| n_updates | 31004 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.398 | +| time/ | | +| fps | 1417 | +| iterations | 3798 | +| time_elapsed | 5486 | +| total_timesteps | 7778304 | +| train/ | | +| approx_kl | 0.014746649 | +| clip_fraction | 0.336 | +| clip_range | 0.0731 | +| entropy_loss | -7.28 | +| explained_variance | -0.125 | +| learning_rate | 4.82e-05 | +| loss | -0.0291 | +| n_updates | 31008 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000119 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.391 | +| time/ | | +| fps | 1417 | +| iterations | 3799 | +| time_elapsed | 5488 | +| total_timesteps | 7780352 | +| train/ | | +| approx_kl | 0.010038847 | +| clip_fraction | 0.312 | +| clip_range | 0.0731 | +| entropy_loss | -7.11 | +| explained_variance | 0.253 | +| learning_rate | 4.82e-05 | +| loss | -0.027 | +| n_updates | 31012 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.0001 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.389 | +| time/ | | +| fps | 1417 | +| iterations | 3800 | +| time_elapsed | 5489 | +| total_timesteps | 7782400 | +| train/ | | +| approx_kl | 0.010031542 | +| clip_fraction | 0.304 | +| clip_range | 0.0731 | +| entropy_loss | -6.94 | +| explained_variance | 0.51 | +| learning_rate | 4.82e-05 | +| loss | -0.0295 | +| n_updates | 31016 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.388 | +| time/ | | +| fps | 1417 | +| iterations | 3801 | +| time_elapsed | 5491 | +| total_timesteps | 7784448 | +| train/ | | +| approx_kl | 0.010997312 | +| clip_fraction | 0.324 | +| clip_range | 0.0731 | +| entropy_loss | -7.18 | +| explained_variance | 0.347 | +| learning_rate | 4.82e-05 | +| loss | -0.0338 | +| n_updates | 31020 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000139 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.386 | +| time/ | | +| fps | 1417 | +| iterations | 3802 | +| time_elapsed | 5492 | +| total_timesteps | 7786496 | +| train/ | | +| approx_kl | 0.014520949 | +| clip_fraction | 0.322 | +| clip_range | 0.0731 | +| entropy_loss | -6.95 | +| explained_variance | 0.248 | +| learning_rate | 4.82e-05 | +| loss | -0.0313 | +| n_updates | 31024 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000172 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.388 | +| time/ | | +| fps | 1417 | +| iterations | 3803 | +| time_elapsed | 5493 | +| total_timesteps | 7788544 | +| train/ | | +| approx_kl | 0.012484385 | +| clip_fraction | 0.326 | +| clip_range | 0.0731 | +| entropy_loss | -6.56 | +| explained_variance | 0.449 | +| learning_rate | 4.82e-05 | +| loss | -0.0341 | +| n_updates | 31028 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.00028 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.387 | +| time/ | | +| fps | 1417 | +| iterations | 3804 | +| time_elapsed | 5495 | +| total_timesteps | 7790592 | +| train/ | | +| approx_kl | 0.012728666 | +| clip_fraction | 0.324 | +| clip_range | 0.0731 | +| entropy_loss | -6.88 | +| explained_variance | 0.449 | +| learning_rate | 4.82e-05 | +| loss | -0.0333 | +| n_updates | 31032 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000149 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.386 | +| time/ | | +| fps | 1417 | +| iterations | 3805 | +| time_elapsed | 5496 | +| total_timesteps | 7792640 | +| train/ | | +| approx_kl | 0.012548903 | +| clip_fraction | 0.339 | +| clip_range | 0.0731 | +| entropy_loss | -7.26 | +| explained_variance | -0.182 | +| learning_rate | 4.81e-05 | +| loss | -0.0319 | +| n_updates | 31036 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000183 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.386 | +| time/ | | +| fps | 1417 | +| iterations | 3806 | +| time_elapsed | 5498 | +| total_timesteps | 7794688 | +| train/ | | +| approx_kl | 0.011279633 | +| clip_fraction | 0.281 | +| clip_range | 0.0731 | +| entropy_loss | -6.71 | +| explained_variance | 0.411 | +| learning_rate | 4.81e-05 | +| loss | -0.0239 | +| n_updates | 31040 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000268 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.392 | +| time/ | | +| fps | 1417 | +| iterations | 3807 | +| time_elapsed | 5499 | +| total_timesteps | 7796736 | +| train/ | | +| approx_kl | 0.011905663 | +| clip_fraction | 0.342 | +| clip_range | 0.0731 | +| entropy_loss | -7.21 | +| explained_variance | 0.4 | +| learning_rate | 4.81e-05 | +| loss | -0.037 | +| n_updates | 31044 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000118 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.392 | +| time/ | | +| fps | 1417 | +| iterations | 3808 | +| time_elapsed | 5501 | +| total_timesteps | 7798784 | +| train/ | | +| approx_kl | 0.010242591 | +| clip_fraction | 0.336 | +| clip_range | 0.0731 | +| entropy_loss | -7.16 | +| explained_variance | 0.257 | +| learning_rate | 4.81e-05 | +| loss | -0.0216 | +| n_updates | 31048 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000175 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.388 | +| time/ | | +| fps | 1417 | +| iterations | 3809 | +| time_elapsed | 5502 | +| total_timesteps | 7800832 | +| train/ | | +| approx_kl | 0.012154965 | +| clip_fraction | 0.331 | +| clip_range | 0.0731 | +| entropy_loss | -7.45 | +| explained_variance | -0.226 | +| learning_rate | 4.81e-05 | +| loss | -0.0398 | +| n_updates | 31052 | +| policy_gradient_loss | -0.0224 | +| value_loss | 0.000111 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.396 | +| time/ | | +| fps | 1417 | +| iterations | 3810 | +| time_elapsed | 5504 | +| total_timesteps | 7802880 | +| train/ | | +| approx_kl | 0.011180641 | +| clip_fraction | 0.324 | +| clip_range | 0.073 | +| entropy_loss | -7.33 | +| explained_variance | 0.105 | +| learning_rate | 4.81e-05 | +| loss | -0.0328 | +| n_updates | 31056 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000233 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.4 | +| time/ | | +| fps | 1417 | +| iterations | 3811 | +| time_elapsed | 5505 | +| total_timesteps | 7804928 | +| train/ | | +| approx_kl | 0.011529217 | +| clip_fraction | 0.318 | +| clip_range | 0.073 | +| entropy_loss | -6.79 | +| explained_variance | 0.229 | +| learning_rate | 4.81e-05 | +| loss | -0.0299 | +| n_updates | 31060 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000448 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.39 | +| time/ | | +| fps | 1417 | +| iterations | 3812 | +| time_elapsed | 5506 | +| total_timesteps | 7806976 | +| train/ | | +| approx_kl | 0.011055449 | +| clip_fraction | 0.321 | +| clip_range | 0.073 | +| entropy_loss | -6.71 | +| explained_variance | 0.424 | +| learning_rate | 4.81e-05 | +| loss | -0.029 | +| n_updates | 31064 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000239 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.393 | +| time/ | | +| fps | 1417 | +| iterations | 3813 | +| time_elapsed | 5508 | +| total_timesteps | 7809024 | +| train/ | | +| approx_kl | 0.012606729 | +| clip_fraction | 0.343 | +| clip_range | 0.073 | +| entropy_loss | -6.55 | +| explained_variance | 0.733 | +| learning_rate | 4.81e-05 | +| loss | -0.0285 | +| n_updates | 31068 | +| policy_gradient_loss | -0.0222 | +| value_loss | 9.91e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.395 | +| time/ | | +| fps | 1417 | +| iterations | 3814 | +| time_elapsed | 5509 | +| total_timesteps | 7811072 | +| train/ | | +| approx_kl | 0.011773953 | +| clip_fraction | 0.323 | +| clip_range | 0.073 | +| entropy_loss | -7.32 | +| explained_variance | -0.0611 | +| learning_rate | 4.81e-05 | +| loss | -0.0348 | +| n_updates | 31072 | +| policy_gradient_loss | -0.0225 | +| value_loss | 0.000185 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.395 | +| time/ | | +| fps | 1417 | +| iterations | 3815 | +| time_elapsed | 5511 | +| total_timesteps | 7813120 | +| train/ | | +| approx_kl | 0.013629584 | +| clip_fraction | 0.323 | +| clip_range | 0.073 | +| entropy_loss | -6.9 | +| explained_variance | 0.492 | +| learning_rate | 4.81e-05 | +| loss | -0.0391 | +| n_updates | 31076 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000121 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.393 | +| time/ | | +| fps | 1417 | +| iterations | 3816 | +| time_elapsed | 5512 | +| total_timesteps | 7815168 | +| train/ | | +| approx_kl | 0.013254106 | +| clip_fraction | 0.353 | +| clip_range | 0.073 | +| entropy_loss | -7.13 | +| explained_variance | 0.326 | +| learning_rate | 4.81e-05 | +| loss | -0.035 | +| n_updates | 31080 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000146 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.397 | +| time/ | | +| fps | 1417 | +| iterations | 3817 | +| time_elapsed | 5513 | +| total_timesteps | 7817216 | +| train/ | | +| approx_kl | 0.009196281 | +| clip_fraction | 0.335 | +| clip_range | 0.073 | +| entropy_loss | -7.37 | +| explained_variance | -0.0104 | +| learning_rate | 4.81e-05 | +| loss | -0.0299 | +| n_updates | 31084 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000218 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.402 | +| time/ | | +| fps | 1417 | +| iterations | 3818 | +| time_elapsed | 5515 | +| total_timesteps | 7819264 | +| train/ | | +| approx_kl | 0.010237679 | +| clip_fraction | 0.305 | +| clip_range | 0.073 | +| entropy_loss | -6.87 | +| explained_variance | 0.3 | +| learning_rate | 4.81e-05 | +| loss | -0.0312 | +| n_updates | 31088 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000371 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.403 | +| time/ | | +| fps | 1417 | +| iterations | 3819 | +| time_elapsed | 5516 | +| total_timesteps | 7821312 | +| train/ | | +| approx_kl | 0.008125365 | +| clip_fraction | 0.288 | +| clip_range | 0.073 | +| entropy_loss | -6.82 | +| explained_variance | 0.406 | +| learning_rate | 4.81e-05 | +| loss | -0.0258 | +| n_updates | 31092 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000261 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.403 | +| time/ | | +| fps | 1417 | +| iterations | 3820 | +| time_elapsed | 5518 | +| total_timesteps | 7823360 | +| train/ | | +| approx_kl | 0.012173864 | +| clip_fraction | 0.349 | +| clip_range | 0.073 | +| entropy_loss | -7.27 | +| explained_variance | 0.315 | +| learning_rate | 4.81e-05 | +| loss | -0.0389 | +| n_updates | 31096 | +| policy_gradient_loss | -0.0244 | +| value_loss | 8.34e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.401 | +| time/ | | +| fps | 1417 | +| iterations | 3821 | +| time_elapsed | 5519 | +| total_timesteps | 7825408 | +| train/ | | +| approx_kl | 0.012026755 | +| clip_fraction | 0.312 | +| clip_range | 0.073 | +| entropy_loss | -7.14 | +| explained_variance | 0.336 | +| learning_rate | 4.81e-05 | +| loss | -0.0317 | +| n_updates | 31100 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000149 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.401 | +| time/ | | +| fps | 1417 | +| iterations | 3822 | +| time_elapsed | 5521 | +| total_timesteps | 7827456 | +| train/ | | +| approx_kl | 0.010092877 | +| clip_fraction | 0.339 | +| clip_range | 0.073 | +| entropy_loss | -7.23 | +| explained_variance | 0.459 | +| learning_rate | 4.81e-05 | +| loss | -0.036 | +| n_updates | 31104 | +| policy_gradient_loss | -0.0231 | +| value_loss | 5.79e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.401 | +| time/ | | +| fps | 1417 | +| iterations | 3823 | +| time_elapsed | 5522 | +| total_timesteps | 7829504 | +| train/ | | +| approx_kl | 0.011201762 | +| clip_fraction | 0.296 | +| clip_range | 0.073 | +| entropy_loss | -6.7 | +| explained_variance | 0.533 | +| learning_rate | 4.81e-05 | +| loss | -0.0238 | +| n_updates | 31108 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000211 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.399 | +| time/ | | +| fps | 1417 | +| iterations | 3824 | +| time_elapsed | 5523 | +| total_timesteps | 7831552 | +| train/ | | +| approx_kl | 0.01055789 | +| clip_fraction | 0.287 | +| clip_range | 0.073 | +| entropy_loss | -6.84 | +| explained_variance | 0.381 | +| learning_rate | 4.81e-05 | +| loss | -0.0269 | +| n_updates | 31112 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000293 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.4 | +| time/ | | +| fps | 1417 | +| iterations | 3825 | +| time_elapsed | 5525 | +| total_timesteps | 7833600 | +| train/ | | +| approx_kl | 0.010331006 | +| clip_fraction | 0.316 | +| clip_range | 0.073 | +| entropy_loss | -7.11 | +| explained_variance | 0.174 | +| learning_rate | 4.81e-05 | +| loss | -0.0329 | +| n_updates | 31116 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.00019 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.398 | +| time/ | | +| fps | 1417 | +| iterations | 3826 | +| time_elapsed | 5526 | +| total_timesteps | 7835648 | +| train/ | | +| approx_kl | 0.011584279 | +| clip_fraction | 0.338 | +| clip_range | 0.073 | +| entropy_loss | -7.28 | +| explained_variance | 0.31 | +| learning_rate | 4.81e-05 | +| loss | -0.0327 | +| n_updates | 31120 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000109 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.401 | +| time/ | | +| fps | 1417 | +| iterations | 3827 | +| time_elapsed | 5528 | +| total_timesteps | 7837696 | +| train/ | | +| approx_kl | 0.012740028 | +| clip_fraction | 0.322 | +| clip_range | 0.073 | +| entropy_loss | -7.15 | +| explained_variance | 0.363 | +| learning_rate | 4.81e-05 | +| loss | -0.0294 | +| n_updates | 31124 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000119 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.401 | +| time/ | | +| fps | 1417 | +| iterations | 3828 | +| time_elapsed | 5529 | +| total_timesteps | 7839744 | +| train/ | | +| approx_kl | 0.008724967 | +| clip_fraction | 0.272 | +| clip_range | 0.073 | +| entropy_loss | -7.35 | +| explained_variance | 0.212 | +| learning_rate | 4.81e-05 | +| loss | -0.0216 | +| n_updates | 31128 | +| policy_gradient_loss | -0.0143 | +| value_loss | 0.000286 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.396 | +| time/ | | +| fps | 1417 | +| iterations | 3829 | +| time_elapsed | 5531 | +| total_timesteps | 7841792 | +| train/ | | +| approx_kl | 0.013373964 | +| clip_fraction | 0.348 | +| clip_range | 0.073 | +| entropy_loss | -7.09 | +| explained_variance | 0.317 | +| learning_rate | 4.81e-05 | +| loss | -0.0323 | +| n_updates | 31132 | +| policy_gradient_loss | -0.0224 | +| value_loss | 0.000116 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.391 | +| time/ | | +| fps | 1417 | +| iterations | 3830 | +| time_elapsed | 5532 | +| total_timesteps | 7843840 | +| train/ | | +| approx_kl | 0.010323372 | +| clip_fraction | 0.323 | +| clip_range | 0.073 | +| entropy_loss | -7.15 | +| explained_variance | 0.387 | +| learning_rate | 4.81e-05 | +| loss | -0.0353 | +| n_updates | 31136 | +| policy_gradient_loss | -0.0209 | +| value_loss | 9.58e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.391 | +| time/ | | +| fps | 1417 | +| iterations | 3831 | +| time_elapsed | 5533 | +| total_timesteps | 7845888 | +| train/ | | +| approx_kl | 0.009833998 | +| clip_fraction | 0.316 | +| clip_range | 0.073 | +| entropy_loss | -7.03 | +| explained_variance | 0.64 | +| learning_rate | 4.81e-05 | +| loss | -0.0332 | +| n_updates | 31140 | +| policy_gradient_loss | -0.0214 | +| value_loss | 8.58e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.398 | +| time/ | | +| fps | 1417 | +| iterations | 3832 | +| time_elapsed | 5535 | +| total_timesteps | 7847936 | +| train/ | | +| approx_kl | 0.012689738 | +| clip_fraction | 0.323 | +| clip_range | 0.073 | +| entropy_loss | -6.99 | +| explained_variance | 0.608 | +| learning_rate | 4.81e-05 | +| loss | -0.0389 | +| n_updates | 31144 | +| policy_gradient_loss | -0.0184 | +| value_loss | 9.91e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.393 | +| time/ | | +| fps | 1417 | +| iterations | 3833 | +| time_elapsed | 5536 | +| total_timesteps | 7849984 | +| train/ | | +| approx_kl | 0.011280577 | +| clip_fraction | 0.285 | +| clip_range | 0.073 | +| entropy_loss | -7.03 | +| explained_variance | 0.372 | +| learning_rate | 4.81e-05 | +| loss | -0.0201 | +| n_updates | 31148 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.000255 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.387 | +| time/ | | +| fps | 1417 | +| iterations | 3834 | +| time_elapsed | 5538 | +| total_timesteps | 7852032 | +| train/ | | +| approx_kl | 0.011450549 | +| clip_fraction | 0.324 | +| clip_range | 0.073 | +| entropy_loss | -6.91 | +| explained_variance | 0.393 | +| learning_rate | 4.81e-05 | +| loss | -0.0333 | +| n_updates | 31152 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000144 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.387 | +| time/ | | +| fps | 1417 | +| iterations | 3835 | +| time_elapsed | 5539 | +| total_timesteps | 7854080 | +| train/ | | +| approx_kl | 0.012513597 | +| clip_fraction | 0.291 | +| clip_range | 0.073 | +| entropy_loss | -6.79 | +| explained_variance | 0.388 | +| learning_rate | 4.81e-05 | +| loss | -0.0312 | +| n_updates | 31156 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000152 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.387 | +| time/ | | +| fps | 1417 | +| iterations | 3836 | +| time_elapsed | 5541 | +| total_timesteps | 7856128 | +| train/ | | +| approx_kl | 0.011419139 | +| clip_fraction | 0.317 | +| clip_range | 0.073 | +| entropy_loss | -7.36 | +| explained_variance | -0.106 | +| learning_rate | 4.81e-05 | +| loss | -0.0342 | +| n_updates | 31160 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000176 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1417 | +| iterations | 3837 | +| time_elapsed | 5542 | +| total_timesteps | 7858176 | +| train/ | | +| approx_kl | 0.011043501 | +| clip_fraction | 0.341 | +| clip_range | 0.073 | +| entropy_loss | -7.44 | +| explained_variance | -0.127 | +| learning_rate | 4.81e-05 | +| loss | -0.0317 | +| n_updates | 31164 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000136 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.385 | +| time/ | | +| fps | 1417 | +| iterations | 3838 | +| time_elapsed | 5543 | +| total_timesteps | 7860224 | +| train/ | | +| approx_kl | 0.011431951 | +| clip_fraction | 0.315 | +| clip_range | 0.073 | +| entropy_loss | -6.96 | +| explained_variance | 0.322 | +| learning_rate | 4.81e-05 | +| loss | -0.0344 | +| n_updates | 31168 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000125 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.387 | +| time/ | | +| fps | 1417 | +| iterations | 3839 | +| time_elapsed | 5545 | +| total_timesteps | 7862272 | +| train/ | | +| approx_kl | 0.012546053 | +| clip_fraction | 0.331 | +| clip_range | 0.073 | +| entropy_loss | -7.23 | +| explained_variance | -0.072 | +| learning_rate | 4.81e-05 | +| loss | -0.03 | +| n_updates | 31172 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000165 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.387 | +| time/ | | +| fps | 1417 | +| iterations | 3840 | +| time_elapsed | 5546 | +| total_timesteps | 7864320 | +| train/ | | +| approx_kl | 0.012330999 | +| clip_fraction | 0.324 | +| clip_range | 0.073 | +| entropy_loss | -7.14 | +| explained_variance | 0.285 | +| learning_rate | 4.81e-05 | +| loss | -0.0241 | +| n_updates | 31176 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000194 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1417 | +| iterations | 3841 | +| time_elapsed | 5548 | +| total_timesteps | 7866368 | +| train/ | | +| approx_kl | 0.011668044 | +| clip_fraction | 0.314 | +| clip_range | 0.073 | +| entropy_loss | -7.09 | +| explained_variance | 0.348 | +| learning_rate | 4.81e-05 | +| loss | -0.0329 | +| n_updates | 31180 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000219 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1417 | +| iterations | 3842 | +| time_elapsed | 5549 | +| total_timesteps | 7868416 | +| train/ | | +| approx_kl | 0.01352403 | +| clip_fraction | 0.353 | +| clip_range | 0.073 | +| entropy_loss | -7.19 | +| explained_variance | 0.253 | +| learning_rate | 4.81e-05 | +| loss | -0.033 | +| n_updates | 31184 | +| policy_gradient_loss | -0.0219 | +| value_loss | 0.000149 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1417 | +| iterations | 3843 | +| time_elapsed | 5550 | +| total_timesteps | 7870464 | +| train/ | | +| approx_kl | 0.015393641 | +| clip_fraction | 0.349 | +| clip_range | 0.073 | +| entropy_loss | -6.66 | +| explained_variance | 0.48 | +| learning_rate | 4.81e-05 | +| loss | -0.0341 | +| n_updates | 31188 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000118 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1417 | +| iterations | 3844 | +| time_elapsed | 5552 | +| total_timesteps | 7872512 | +| train/ | | +| approx_kl | 0.0126071805 | +| clip_fraction | 0.333 | +| clip_range | 0.073 | +| entropy_loss | -7.15 | +| explained_variance | 0.37 | +| learning_rate | 4.81e-05 | +| loss | -0.0323 | +| n_updates | 31192 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000115 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1417 | +| iterations | 3845 | +| time_elapsed | 5553 | +| total_timesteps | 7874560 | +| train/ | | +| approx_kl | 0.01143891 | +| clip_fraction | 0.342 | +| clip_range | 0.073 | +| entropy_loss | -7.42 | +| explained_variance | -0.211 | +| learning_rate | 4.81e-05 | +| loss | -0.0422 | +| n_updates | 31196 | +| policy_gradient_loss | -0.0231 | +| value_loss | 8.93e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1417 | +| iterations | 3846 | +| time_elapsed | 5555 | +| total_timesteps | 7876608 | +| train/ | | +| approx_kl | 0.011231171 | +| clip_fraction | 0.316 | +| clip_range | 0.073 | +| entropy_loss | -6.73 | +| explained_variance | 0.542 | +| learning_rate | 4.81e-05 | +| loss | -0.0293 | +| n_updates | 31200 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000108 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1417 | +| iterations | 3847 | +| time_elapsed | 5556 | +| total_timesteps | 7878656 | +| train/ | | +| approx_kl | 0.014663005 | +| clip_fraction | 0.346 | +| clip_range | 0.073 | +| entropy_loss | -7.13 | +| explained_variance | 0.568 | +| learning_rate | 4.81e-05 | +| loss | -0.0324 | +| n_updates | 31204 | +| policy_gradient_loss | -0.0207 | +| value_loss | 6.35e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1417 | +| iterations | 3848 | +| time_elapsed | 5558 | +| total_timesteps | 7880704 | +| train/ | | +| approx_kl | 0.012020849 | +| clip_fraction | 0.327 | +| clip_range | 0.073 | +| entropy_loss | -7.31 | +| explained_variance | 0.181 | +| learning_rate | 4.81e-05 | +| loss | -0.0277 | +| n_updates | 31208 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000177 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1417 | +| iterations | 3849 | +| time_elapsed | 5559 | +| total_timesteps | 7882752 | +| train/ | | +| approx_kl | 0.011711597 | +| clip_fraction | 0.31 | +| clip_range | 0.073 | +| entropy_loss | -7.51 | +| explained_variance | -0.0907 | +| learning_rate | 4.81e-05 | +| loss | -0.034 | +| n_updates | 31212 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000165 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1417 | +| iterations | 3850 | +| time_elapsed | 5560 | +| total_timesteps | 7884800 | +| train/ | | +| approx_kl | 0.009928314 | +| clip_fraction | 0.332 | +| clip_range | 0.073 | +| entropy_loss | -7.38 | +| explained_variance | -0.059 | +| learning_rate | 4.81e-05 | +| loss | -0.0317 | +| n_updates | 31216 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000109 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1417 | +| iterations | 3851 | +| time_elapsed | 5562 | +| total_timesteps | 7886848 | +| train/ | | +| approx_kl | 0.009843368 | +| clip_fraction | 0.33 | +| clip_range | 0.073 | +| entropy_loss | -6.96 | +| explained_variance | 0.352 | +| learning_rate | 4.81e-05 | +| loss | -0.0297 | +| n_updates | 31220 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000219 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1417 | +| iterations | 3852 | +| time_elapsed | 5563 | +| total_timesteps | 7888896 | +| train/ | | +| approx_kl | 0.014567317 | +| clip_fraction | 0.353 | +| clip_range | 0.073 | +| entropy_loss | -6.92 | +| explained_variance | 0.372 | +| learning_rate | 4.81e-05 | +| loss | -0.0353 | +| n_updates | 31224 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000107 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1417 | +| iterations | 3853 | +| time_elapsed | 5565 | +| total_timesteps | 7890944 | +| train/ | | +| approx_kl | 0.010528401 | +| clip_fraction | 0.326 | +| clip_range | 0.073 | +| entropy_loss | -6.84 | +| explained_variance | 0.61 | +| learning_rate | 4.81e-05 | +| loss | -0.0308 | +| n_updates | 31228 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000116 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1417 | +| iterations | 3854 | +| time_elapsed | 5566 | +| total_timesteps | 7892992 | +| train/ | | +| approx_kl | 0.011737991 | +| clip_fraction | 0.325 | +| clip_range | 0.073 | +| entropy_loss | -6.61 | +| explained_variance | 0.691 | +| learning_rate | 4.81e-05 | +| loss | -0.0376 | +| n_updates | 31232 | +| policy_gradient_loss | -0.0207 | +| value_loss | 9.29e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1417 | +| iterations | 3855 | +| time_elapsed | 5568 | +| total_timesteps | 7895040 | +| train/ | | +| approx_kl | 0.010896239 | +| clip_fraction | 0.322 | +| clip_range | 0.073 | +| entropy_loss | -7.08 | +| explained_variance | 0.332 | +| learning_rate | 4.81e-05 | +| loss | -0.0322 | +| n_updates | 31236 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000135 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1417 | +| iterations | 3856 | +| time_elapsed | 5569 | +| total_timesteps | 7897088 | +| train/ | | +| approx_kl | 0.011848177 | +| clip_fraction | 0.319 | +| clip_range | 0.073 | +| entropy_loss | -6.45 | +| explained_variance | 0.601 | +| learning_rate | 4.81e-05 | +| loss | -0.0304 | +| n_updates | 31240 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000189 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1417 | +| iterations | 3857 | +| time_elapsed | 5570 | +| total_timesteps | 7899136 | +| train/ | | +| approx_kl | 0.010764527 | +| clip_fraction | 0.354 | +| clip_range | 0.073 | +| entropy_loss | -7.36 | +| explained_variance | -0.324 | +| learning_rate | 4.81e-05 | +| loss | -0.0379 | +| n_updates | 31244 | +| policy_gradient_loss | -0.0237 | +| value_loss | 7.33e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1417 | +| iterations | 3858 | +| time_elapsed | 5572 | +| total_timesteps | 7901184 | +| train/ | | +| approx_kl | 0.0111189615 | +| clip_fraction | 0.316 | +| clip_range | 0.073 | +| entropy_loss | -7.39 | +| explained_variance | -0.157 | +| learning_rate | 4.81e-05 | +| loss | -0.0334 | +| n_updates | 31248 | +| policy_gradient_loss | -0.0199 | +| value_loss | 9.96e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1417 | +| iterations | 3859 | +| time_elapsed | 5573 | +| total_timesteps | 7903232 | +| train/ | | +| approx_kl | 0.010473881 | +| clip_fraction | 0.323 | +| clip_range | 0.073 | +| entropy_loss | -7.02 | +| explained_variance | 0.578 | +| learning_rate | 4.81e-05 | +| loss | -0.031 | +| n_updates | 31252 | +| policy_gradient_loss | -0.0184 | +| value_loss | 8.49e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1417 | +| iterations | 3860 | +| time_elapsed | 5575 | +| total_timesteps | 7905280 | +| train/ | | +| approx_kl | 0.011043176 | +| clip_fraction | 0.319 | +| clip_range | 0.073 | +| entropy_loss | -7.18 | +| explained_variance | 0.171 | +| learning_rate | 4.81e-05 | +| loss | -0.0233 | +| n_updates | 31256 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000154 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1417 | +| iterations | 3861 | +| time_elapsed | 5576 | +| total_timesteps | 7907328 | +| train/ | | +| approx_kl | 0.011987334 | +| clip_fraction | 0.313 | +| clip_range | 0.073 | +| entropy_loss | -7.3 | +| explained_variance | 0.103 | +| learning_rate | 4.81e-05 | +| loss | -0.0322 | +| n_updates | 31260 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000197 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1417 | +| iterations | 3862 | +| time_elapsed | 5578 | +| total_timesteps | 7909376 | +| train/ | | +| approx_kl | 0.010116046 | +| clip_fraction | 0.305 | +| clip_range | 0.073 | +| entropy_loss | -7.03 | +| explained_variance | 0.42 | +| learning_rate | 4.81e-05 | +| loss | -0.0262 | +| n_updates | 31264 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000211 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1417 | +| iterations | 3863 | +| time_elapsed | 5579 | +| total_timesteps | 7911424 | +| train/ | | +| approx_kl | 0.012538226 | +| clip_fraction | 0.354 | +| clip_range | 0.073 | +| entropy_loss | -7.08 | +| explained_variance | 0.279 | +| learning_rate | 4.81e-05 | +| loss | -0.0347 | +| n_updates | 31268 | +| policy_gradient_loss | -0.0227 | +| value_loss | 0.000126 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1417 | +| iterations | 3864 | +| time_elapsed | 5580 | +| total_timesteps | 7913472 | +| train/ | | +| approx_kl | 0.013439573 | +| clip_fraction | 0.365 | +| clip_range | 0.073 | +| entropy_loss | -7.32 | +| explained_variance | -0.387 | +| learning_rate | 4.81e-05 | +| loss | -0.0387 | +| n_updates | 31272 | +| policy_gradient_loss | -0.0254 | +| value_loss | 5.15e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1417 | +| iterations | 3865 | +| time_elapsed | 5582 | +| total_timesteps | 7915520 | +| train/ | | +| approx_kl | 0.012794696 | +| clip_fraction | 0.32 | +| clip_range | 0.073 | +| entropy_loss | -6.65 | +| explained_variance | 0.709 | +| learning_rate | 4.81e-05 | +| loss | -0.033 | +| n_updates | 31276 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000103 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1417 | +| iterations | 3866 | +| time_elapsed | 5583 | +| total_timesteps | 7917568 | +| train/ | | +| approx_kl | 0.013678433 | +| clip_fraction | 0.324 | +| clip_range | 0.073 | +| entropy_loss | -6.87 | +| explained_variance | 0.343 | +| learning_rate | 4.81e-05 | +| loss | -0.0346 | +| n_updates | 31280 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000114 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1417 | +| iterations | 3867 | +| time_elapsed | 5585 | +| total_timesteps | 7919616 | +| train/ | | +| approx_kl | 0.012325985 | +| clip_fraction | 0.328 | +| clip_range | 0.073 | +| entropy_loss | -7.05 | +| explained_variance | 0.618 | +| learning_rate | 4.81e-05 | +| loss | -0.0342 | +| n_updates | 31284 | +| policy_gradient_loss | -0.0206 | +| value_loss | 8.33e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1417 | +| iterations | 3868 | +| time_elapsed | 5586 | +| total_timesteps | 7921664 | +| train/ | | +| approx_kl | 0.012390284 | +| clip_fraction | 0.36 | +| clip_range | 0.073 | +| entropy_loss | -7.32 | +| explained_variance | -0.00622 | +| learning_rate | 4.81e-05 | +| loss | -0.0371 | +| n_updates | 31288 | +| policy_gradient_loss | -0.0219 | +| value_loss | 0.000114 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1417 | +| iterations | 3869 | +| time_elapsed | 5588 | +| total_timesteps | 7923712 | +| train/ | | +| approx_kl | 0.010525308 | +| clip_fraction | 0.302 | +| clip_range | 0.073 | +| entropy_loss | -6.77 | +| explained_variance | 0.545 | +| learning_rate | 4.81e-05 | +| loss | -0.0273 | +| n_updates | 31292 | +| policy_gradient_loss | -0.0148 | +| value_loss | 0.000169 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1417 | +| iterations | 3870 | +| time_elapsed | 5589 | +| total_timesteps | 7925760 | +| train/ | | +| approx_kl | 0.013236608 | +| clip_fraction | 0.334 | +| clip_range | 0.073 | +| entropy_loss | -7.28 | +| explained_variance | -0.00663 | +| learning_rate | 4.81e-05 | +| loss | -0.0368 | +| n_updates | 31296 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000158 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1417 | +| iterations | 3871 | +| time_elapsed | 5590 | +| total_timesteps | 7927808 | +| train/ | | +| approx_kl | 0.011401884 | +| clip_fraction | 0.32 | +| clip_range | 0.073 | +| entropy_loss | -6.93 | +| explained_variance | 0.46 | +| learning_rate | 4.81e-05 | +| loss | -0.0234 | +| n_updates | 31300 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000107 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1417 | +| iterations | 3872 | +| time_elapsed | 5592 | +| total_timesteps | 7929856 | +| train/ | | +| approx_kl | 0.009411195 | +| clip_fraction | 0.321 | +| clip_range | 0.073 | +| entropy_loss | -7.13 | +| explained_variance | 0.308 | +| learning_rate | 4.81e-05 | +| loss | -0.031 | +| n_updates | 31304 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000161 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1417 | +| iterations | 3873 | +| time_elapsed | 5593 | +| total_timesteps | 7931904 | +| train/ | | +| approx_kl | 0.011590756 | +| clip_fraction | 0.326 | +| clip_range | 0.073 | +| entropy_loss | -6.97 | +| explained_variance | 0.386 | +| learning_rate | 4.81e-05 | +| loss | -0.0354 | +| n_updates | 31308 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000143 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1417 | +| iterations | 3874 | +| time_elapsed | 5595 | +| total_timesteps | 7933952 | +| train/ | | +| approx_kl | 0.012667686 | +| clip_fraction | 0.331 | +| clip_range | 0.073 | +| entropy_loss | -7.36 | +| explained_variance | -0.159 | +| learning_rate | 4.81e-05 | +| loss | -0.0314 | +| n_updates | 31312 | +| policy_gradient_loss | -0.0209 | +| value_loss | 9.64e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1417 | +| iterations | 3875 | +| time_elapsed | 5596 | +| total_timesteps | 7936000 | +| train/ | | +| approx_kl | 0.009576544 | +| clip_fraction | 0.283 | +| clip_range | 0.073 | +| entropy_loss | -6.76 | +| explained_variance | 0.295 | +| learning_rate | 4.81e-05 | +| loss | -0.0272 | +| n_updates | 31316 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.00026 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1417 | +| iterations | 3876 | +| time_elapsed | 5598 | +| total_timesteps | 7938048 | +| train/ | | +| approx_kl | 0.011547897 | +| clip_fraction | 0.313 | +| clip_range | 0.073 | +| entropy_loss | -6.89 | +| explained_variance | 0.202 | +| learning_rate | 4.81e-05 | +| loss | -0.0321 | +| n_updates | 31320 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000285 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1417 | +| iterations | 3877 | +| time_elapsed | 5599 | +| total_timesteps | 7940096 | +| train/ | | +| approx_kl | 0.01091883 | +| clip_fraction | 0.303 | +| clip_range | 0.073 | +| entropy_loss | -6.8 | +| explained_variance | 0.37 | +| learning_rate | 4.81e-05 | +| loss | -0.026 | +| n_updates | 31324 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000276 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1417 | +| iterations | 3878 | +| time_elapsed | 5600 | +| total_timesteps | 7942144 | +| train/ | | +| approx_kl | 0.010931838 | +| clip_fraction | 0.31 | +| clip_range | 0.073 | +| entropy_loss | -7.23 | +| explained_variance | 0.123 | +| learning_rate | 4.81e-05 | +| loss | -0.0349 | +| n_updates | 31328 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000185 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1418 | +| iterations | 3879 | +| time_elapsed | 5602 | +| total_timesteps | 7944192 | +| train/ | | +| approx_kl | 0.009954434 | +| clip_fraction | 0.312 | +| clip_range | 0.073 | +| entropy_loss | -6.95 | +| explained_variance | 0.467 | +| learning_rate | 4.81e-05 | +| loss | -0.0314 | +| n_updates | 31332 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000152 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1418 | +| iterations | 3880 | +| time_elapsed | 5603 | +| total_timesteps | 7946240 | +| train/ | | +| approx_kl | 0.012689309 | +| clip_fraction | 0.311 | +| clip_range | 0.073 | +| entropy_loss | -6.82 | +| explained_variance | 0.424 | +| learning_rate | 4.81e-05 | +| loss | -0.0315 | +| n_updates | 31336 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000198 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1418 | +| iterations | 3881 | +| time_elapsed | 5605 | +| total_timesteps | 7948288 | +| train/ | | +| approx_kl | 0.013329146 | +| clip_fraction | 0.351 | +| clip_range | 0.073 | +| entropy_loss | -7.32 | +| explained_variance | 0.207 | +| learning_rate | 4.81e-05 | +| loss | -0.0298 | +| n_updates | 31340 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000221 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1418 | +| iterations | 3882 | +| time_elapsed | 5606 | +| total_timesteps | 7950336 | +| train/ | | +| approx_kl | 0.01278191 | +| clip_fraction | 0.327 | +| clip_range | 0.073 | +| entropy_loss | -7.17 | +| explained_variance | 0.148 | +| learning_rate | 4.81e-05 | +| loss | -0.0285 | +| n_updates | 31344 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000316 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1418 | +| iterations | 3883 | +| time_elapsed | 5608 | +| total_timesteps | 7952384 | +| train/ | | +| approx_kl | 0.010145308 | +| clip_fraction | 0.326 | +| clip_range | 0.073 | +| entropy_loss | -6.97 | +| explained_variance | 0.261 | +| learning_rate | 4.81e-05 | +| loss | -0.0246 | +| n_updates | 31348 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000345 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1418 | +| iterations | 3884 | +| time_elapsed | 5609 | +| total_timesteps | 7954432 | +| train/ | | +| approx_kl | 0.010796704 | +| clip_fraction | 0.342 | +| clip_range | 0.073 | +| entropy_loss | -7.09 | +| explained_variance | 0.286 | +| learning_rate | 4.81e-05 | +| loss | -0.0354 | +| n_updates | 31352 | +| policy_gradient_loss | -0.0226 | +| value_loss | 0.000136 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1418 | +| iterations | 3885 | +| time_elapsed | 5610 | +| total_timesteps | 7956480 | +| train/ | | +| approx_kl | 0.009844322 | +| clip_fraction | 0.3 | +| clip_range | 0.073 | +| entropy_loss | -6.85 | +| explained_variance | 0.51 | +| learning_rate | 4.81e-05 | +| loss | -0.0398 | +| n_updates | 31356 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000137 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1418 | +| iterations | 3886 | +| time_elapsed | 5612 | +| total_timesteps | 7958528 | +| train/ | | +| approx_kl | 0.012299129 | +| clip_fraction | 0.317 | +| clip_range | 0.073 | +| entropy_loss | -6.57 | +| explained_variance | 0.467 | +| learning_rate | 4.81e-05 | +| loss | -0.0271 | +| n_updates | 31360 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000253 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1418 | +| iterations | 3887 | +| time_elapsed | 5613 | +| total_timesteps | 7960576 | +| train/ | | +| approx_kl | 0.013799109 | +| clip_fraction | 0.352 | +| clip_range | 0.073 | +| entropy_loss | -6.99 | +| explained_variance | 0.574 | +| learning_rate | 4.81e-05 | +| loss | -0.0354 | +| n_updates | 31364 | +| policy_gradient_loss | -0.0229 | +| value_loss | 9.6e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1418 | +| iterations | 3888 | +| time_elapsed | 5615 | +| total_timesteps | 7962624 | +| train/ | | +| approx_kl | 0.012110226 | +| clip_fraction | 0.363 | +| clip_range | 0.073 | +| entropy_loss | -7.31 | +| explained_variance | -0.267 | +| learning_rate | 4.81e-05 | +| loss | -0.0352 | +| n_updates | 31368 | +| policy_gradient_loss | -0.0214 | +| value_loss | 7.88e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1418 | +| iterations | 3889 | +| time_elapsed | 5616 | +| total_timesteps | 7964672 | +| train/ | | +| approx_kl | 0.013188401 | +| clip_fraction | 0.311 | +| clip_range | 0.073 | +| entropy_loss | -7.26 | +| explained_variance | 0.256 | +| learning_rate | 4.81e-05 | +| loss | -0.0296 | +| n_updates | 31372 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000196 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1418 | +| iterations | 3890 | +| time_elapsed | 5618 | +| total_timesteps | 7966720 | +| train/ | | +| approx_kl | 0.010095498 | +| clip_fraction | 0.304 | +| clip_range | 0.073 | +| entropy_loss | -6.91 | +| explained_variance | 0.478 | +| learning_rate | 4.81e-05 | +| loss | -0.0333 | +| n_updates | 31376 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000151 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1418 | +| iterations | 3891 | +| time_elapsed | 5619 | +| total_timesteps | 7968768 | +| train/ | | +| approx_kl | 0.012761264 | +| clip_fraction | 0.337 | +| clip_range | 0.073 | +| entropy_loss | -6.83 | +| explained_variance | 0.541 | +| learning_rate | 4.81e-05 | +| loss | -0.041 | +| n_updates | 31380 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000118 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1418 | +| iterations | 3892 | +| time_elapsed | 5621 | +| total_timesteps | 7970816 | +| train/ | | +| approx_kl | 0.01348122 | +| clip_fraction | 0.333 | +| clip_range | 0.073 | +| entropy_loss | -7.27 | +| explained_variance | 0.351 | +| learning_rate | 4.81e-05 | +| loss | -0.0333 | +| n_updates | 31384 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000142 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1418 | +| iterations | 3893 | +| time_elapsed | 5622 | +| total_timesteps | 7972864 | +| train/ | | +| approx_kl | 0.010127758 | +| clip_fraction | 0.297 | +| clip_range | 0.073 | +| entropy_loss | -7.31 | +| explained_variance | 0.015 | +| learning_rate | 4.81e-05 | +| loss | -0.0318 | +| n_updates | 31388 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000226 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1418 | +| iterations | 3894 | +| time_elapsed | 5623 | +| total_timesteps | 7974912 | +| train/ | | +| approx_kl | 0.010904286 | +| clip_fraction | 0.297 | +| clip_range | 0.073 | +| entropy_loss | -6.95 | +| explained_variance | 0.429 | +| learning_rate | 4.81e-05 | +| loss | -0.0288 | +| n_updates | 31392 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000199 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1418 | +| iterations | 3895 | +| time_elapsed | 5625 | +| total_timesteps | 7976960 | +| train/ | | +| approx_kl | 0.012706034 | +| clip_fraction | 0.34 | +| clip_range | 0.073 | +| entropy_loss | -7.1 | +| explained_variance | 0.364 | +| learning_rate | 4.81e-05 | +| loss | -0.0316 | +| n_updates | 31396 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000109 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1418 | +| iterations | 3896 | +| time_elapsed | 5626 | +| total_timesteps | 7979008 | +| train/ | | +| approx_kl | 0.011397161 | +| clip_fraction | 0.314 | +| clip_range | 0.073 | +| entropy_loss | -6.74 | +| explained_variance | 0.616 | +| learning_rate | 4.81e-05 | +| loss | -0.0273 | +| n_updates | 31400 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000129 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1418 | +| iterations | 3897 | +| time_elapsed | 5628 | +| total_timesteps | 7981056 | +| train/ | | +| approx_kl | 0.012389459 | +| clip_fraction | 0.357 | +| clip_range | 0.073 | +| entropy_loss | -7.35 | +| explained_variance | -0.228 | +| learning_rate | 4.81e-05 | +| loss | -0.0386 | +| n_updates | 31404 | +| policy_gradient_loss | -0.0249 | +| value_loss | 7.74e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1418 | +| iterations | 3898 | +| time_elapsed | 5629 | +| total_timesteps | 7983104 | +| train/ | | +| approx_kl | 0.0108245965 | +| clip_fraction | 0.32 | +| clip_range | 0.073 | +| entropy_loss | -6.73 | +| explained_variance | 0.413 | +| learning_rate | 4.81e-05 | +| loss | -0.0354 | +| n_updates | 31408 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000234 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1418 | +| iterations | 3899 | +| time_elapsed | 5631 | +| total_timesteps | 7985152 | +| train/ | | +| approx_kl | 0.013471462 | +| clip_fraction | 0.354 | +| clip_range | 0.073 | +| entropy_loss | -6.54 | +| explained_variance | 0.601 | +| learning_rate | 4.81e-05 | +| loss | -0.0345 | +| n_updates | 31412 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000118 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1418 | +| iterations | 3900 | +| time_elapsed | 5632 | +| total_timesteps | 7987200 | +| train/ | | +| approx_kl | 0.011639176 | +| clip_fraction | 0.337 | +| clip_range | 0.073 | +| entropy_loss | -7.3 | +| explained_variance | -0.153 | +| learning_rate | 4.81e-05 | +| loss | -0.0317 | +| n_updates | 31416 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000122 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1418 | +| iterations | 3901 | +| time_elapsed | 5633 | +| total_timesteps | 7989248 | +| train/ | | +| approx_kl | 0.013034834 | +| clip_fraction | 0.35 | +| clip_range | 0.073 | +| entropy_loss | -6.96 | +| explained_variance | 0.745 | +| learning_rate | 4.81e-05 | +| loss | -0.0366 | +| n_updates | 31420 | +| policy_gradient_loss | -0.0233 | +| value_loss | 5.27e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1418 | +| iterations | 3902 | +| time_elapsed | 5635 | +| total_timesteps | 7991296 | +| train/ | | +| approx_kl | 0.011700294 | +| clip_fraction | 0.337 | +| clip_range | 0.073 | +| entropy_loss | -7.44 | +| explained_variance | -0.00568 | +| learning_rate | 4.81e-05 | +| loss | -0.0339 | +| n_updates | 31424 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000116 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1418 | +| iterations | 3903 | +| time_elapsed | 5636 | +| total_timesteps | 7993344 | +| train/ | | +| approx_kl | 0.011235103 | +| clip_fraction | 0.302 | +| clip_range | 0.073 | +| entropy_loss | -6.92 | +| explained_variance | 0.32 | +| learning_rate | 4.81e-05 | +| loss | -0.0272 | +| n_updates | 31428 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000273 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1418 | +| iterations | 3904 | +| time_elapsed | 5638 | +| total_timesteps | 7995392 | +| train/ | | +| approx_kl | 0.011547545 | +| clip_fraction | 0.312 | +| clip_range | 0.073 | +| entropy_loss | -6.91 | +| explained_variance | 0.514 | +| learning_rate | 4.81e-05 | +| loss | -0.0319 | +| n_updates | 31432 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.00013 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1418 | +| iterations | 3905 | +| time_elapsed | 5639 | +| total_timesteps | 7997440 | +| train/ | | +| approx_kl | 0.010208647 | +| clip_fraction | 0.323 | +| clip_range | 0.073 | +| entropy_loss | -7.28 | +| explained_variance | -0.144 | +| learning_rate | 4.81e-05 | +| loss | -0.041 | +| n_updates | 31436 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000105 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1418 | +| iterations | 3906 | +| time_elapsed | 5641 | +| total_timesteps | 7999488 | +| train/ | | +| approx_kl | 0.008924786 | +| clip_fraction | 0.279 | +| clip_range | 0.073 | +| entropy_loss | -6.85 | +| explained_variance | 0.492 | +| learning_rate | 4.81e-05 | +| loss | -0.0213 | +| n_updates | 31440 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000193 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1418 | +| iterations | 3907 | +| time_elapsed | 5642 | +| total_timesteps | 8001536 | +| train/ | | +| approx_kl | 0.01090794 | +| clip_fraction | 0.324 | +| clip_range | 0.073 | +| entropy_loss | -7.06 | +| explained_variance | 0.478 | +| learning_rate | 4.81e-05 | +| loss | -0.0317 | +| n_updates | 31444 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000118 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1418 | +| iterations | 3908 | +| time_elapsed | 5644 | +| total_timesteps | 8003584 | +| train/ | | +| approx_kl | 0.011064117 | +| clip_fraction | 0.314 | +| clip_range | 0.073 | +| entropy_loss | -7.15 | +| explained_variance | 0.347 | +| learning_rate | 4.81e-05 | +| loss | -0.0413 | +| n_updates | 31448 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000114 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1418 | +| iterations | 3909 | +| time_elapsed | 5645 | +| total_timesteps | 8005632 | +| train/ | | +| approx_kl | 0.011425771 | +| clip_fraction | 0.31 | +| clip_range | 0.073 | +| entropy_loss | -7.42 | +| explained_variance | 0.0019 | +| learning_rate | 4.81e-05 | +| loss | -0.031 | +| n_updates | 31452 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000156 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1418 | +| iterations | 3910 | +| time_elapsed | 5647 | +| total_timesteps | 8007680 | +| train/ | | +| approx_kl | 0.010745955 | +| clip_fraction | 0.323 | +| clip_range | 0.073 | +| entropy_loss | -7.33 | +| explained_variance | 0.455 | +| learning_rate | 4.81e-05 | +| loss | -0.0363 | +| n_updates | 31456 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000114 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1418 | +| iterations | 3911 | +| time_elapsed | 5648 | +| total_timesteps | 8009728 | +| train/ | | +| approx_kl | 0.011035576 | +| clip_fraction | 0.297 | +| clip_range | 0.073 | +| entropy_loss | -6.7 | +| explained_variance | 0.359 | +| learning_rate | 4.81e-05 | +| loss | -0.0259 | +| n_updates | 31460 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000207 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1418 | +| iterations | 3912 | +| time_elapsed | 5649 | +| total_timesteps | 8011776 | +| train/ | | +| approx_kl | 0.011412316 | +| clip_fraction | 0.312 | +| clip_range | 0.073 | +| entropy_loss | -6.85 | +| explained_variance | 0.328 | +| learning_rate | 4.81e-05 | +| loss | -0.0217 | +| n_updates | 31464 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.00027 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1418 | +| iterations | 3913 | +| time_elapsed | 5651 | +| total_timesteps | 8013824 | +| train/ | | +| approx_kl | 0.010536682 | +| clip_fraction | 0.304 | +| clip_range | 0.073 | +| entropy_loss | -7.19 | +| explained_variance | 0.255 | +| learning_rate | 4.81e-05 | +| loss | -0.036 | +| n_updates | 31468 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000185 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1418 | +| iterations | 3914 | +| time_elapsed | 5652 | +| total_timesteps | 8015872 | +| train/ | | +| approx_kl | 0.012554899 | +| clip_fraction | 0.36 | +| clip_range | 0.073 | +| entropy_loss | -6.9 | +| explained_variance | 0.824 | +| learning_rate | 4.81e-05 | +| loss | -0.045 | +| n_updates | 31472 | +| policy_gradient_loss | -0.0266 | +| value_loss | 2.75e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1418 | +| iterations | 3915 | +| time_elapsed | 5654 | +| total_timesteps | 8017920 | +| train/ | | +| approx_kl | 0.013815962 | +| clip_fraction | 0.334 | +| clip_range | 0.073 | +| entropy_loss | -6.68 | +| explained_variance | 0.408 | +| learning_rate | 4.81e-05 | +| loss | -0.0295 | +| n_updates | 31476 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000184 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1418 | +| iterations | 3916 | +| time_elapsed | 5655 | +| total_timesteps | 8019968 | +| train/ | | +| approx_kl | 0.012369923 | +| clip_fraction | 0.364 | +| clip_range | 0.073 | +| entropy_loss | -7.41 | +| explained_variance | -0.34 | +| learning_rate | 4.81e-05 | +| loss | -0.0393 | +| n_updates | 31480 | +| policy_gradient_loss | -0.0254 | +| value_loss | 6.23e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1418 | +| iterations | 3917 | +| time_elapsed | 5657 | +| total_timesteps | 8022016 | +| train/ | | +| approx_kl | 0.011824184 | +| clip_fraction | 0.309 | +| clip_range | 0.073 | +| entropy_loss | -7.18 | +| explained_variance | 0.217 | +| learning_rate | 4.81e-05 | +| loss | -0.0264 | +| n_updates | 31484 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000236 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1418 | +| iterations | 3918 | +| time_elapsed | 5658 | +| total_timesteps | 8024064 | +| train/ | | +| approx_kl | 0.012036741 | +| clip_fraction | 0.346 | +| clip_range | 0.073 | +| entropy_loss | -6.74 | +| explained_variance | 0.584 | +| learning_rate | 4.81e-05 | +| loss | -0.0365 | +| n_updates | 31488 | +| policy_gradient_loss | -0.0221 | +| value_loss | 7.56e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1418 | +| iterations | 3919 | +| time_elapsed | 5659 | +| total_timesteps | 8026112 | +| train/ | | +| approx_kl | 0.0130523015 | +| clip_fraction | 0.321 | +| clip_range | 0.073 | +| entropy_loss | -7.36 | +| explained_variance | -0.286 | +| learning_rate | 4.81e-05 | +| loss | -0.0298 | +| n_updates | 31492 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000104 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1418 | +| iterations | 3920 | +| time_elapsed | 5661 | +| total_timesteps | 8028160 | +| train/ | | +| approx_kl | 0.013766367 | +| clip_fraction | 0.306 | +| clip_range | 0.073 | +| entropy_loss | -7.16 | +| explained_variance | 0.389 | +| learning_rate | 4.81e-05 | +| loss | -0.0274 | +| n_updates | 31496 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000105 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1418 | +| iterations | 3921 | +| time_elapsed | 5662 | +| total_timesteps | 8030208 | +| train/ | | +| approx_kl | 0.011878852 | +| clip_fraction | 0.316 | +| clip_range | 0.073 | +| entropy_loss | -6.78 | +| explained_variance | 0.602 | +| learning_rate | 4.81e-05 | +| loss | -0.0282 | +| n_updates | 31500 | +| policy_gradient_loss | -0.0194 | +| value_loss | 9.53e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1418 | +| iterations | 3922 | +| time_elapsed | 5664 | +| total_timesteps | 8032256 | +| train/ | | +| approx_kl | 0.012773238 | +| clip_fraction | 0.353 | +| clip_range | 0.073 | +| entropy_loss | -7.13 | +| explained_variance | 0.293 | +| learning_rate | 4.81e-05 | +| loss | -0.0357 | +| n_updates | 31504 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000171 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1418 | +| iterations | 3923 | +| time_elapsed | 5665 | +| total_timesteps | 8034304 | +| train/ | | +| approx_kl | 0.010438854 | +| clip_fraction | 0.307 | +| clip_range | 0.073 | +| entropy_loss | -7.09 | +| explained_variance | 0.178 | +| learning_rate | 4.81e-05 | +| loss | -0.0343 | +| n_updates | 31508 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000281 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1418 | +| iterations | 3924 | +| time_elapsed | 5667 | +| total_timesteps | 8036352 | +| train/ | | +| approx_kl | 0.011526918 | +| clip_fraction | 0.347 | +| clip_range | 0.073 | +| entropy_loss | -7.1 | +| explained_variance | 0.427 | +| learning_rate | 4.81e-05 | +| loss | -0.0397 | +| n_updates | 31512 | +| policy_gradient_loss | -0.0244 | +| value_loss | 7.43e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1418 | +| iterations | 3925 | +| time_elapsed | 5668 | +| total_timesteps | 8038400 | +| train/ | | +| approx_kl | 0.010008266 | +| clip_fraction | 0.305 | +| clip_range | 0.073 | +| entropy_loss | -6.89 | +| explained_variance | 0.553 | +| learning_rate | 4.81e-05 | +| loss | -0.0313 | +| n_updates | 31516 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000156 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1418 | +| iterations | 3926 | +| time_elapsed | 5669 | +| total_timesteps | 8040448 | +| train/ | | +| approx_kl | 0.012084545 | +| clip_fraction | 0.36 | +| clip_range | 0.073 | +| entropy_loss | -6.95 | +| explained_variance | 0.412 | +| learning_rate | 4.81e-05 | +| loss | -0.0418 | +| n_updates | 31520 | +| policy_gradient_loss | -0.0235 | +| value_loss | 7.42e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1418 | +| iterations | 3927 | +| time_elapsed | 5671 | +| total_timesteps | 8042496 | +| train/ | | +| approx_kl | 0.012187927 | +| clip_fraction | 0.308 | +| clip_range | 0.073 | +| entropy_loss | -7.01 | +| explained_variance | 0.227 | +| learning_rate | 4.81e-05 | +| loss | -0.0283 | +| n_updates | 31524 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.00016 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1418 | +| iterations | 3928 | +| time_elapsed | 5672 | +| total_timesteps | 8044544 | +| train/ | | +| approx_kl | 0.013942931 | +| clip_fraction | 0.342 | +| clip_range | 0.073 | +| entropy_loss | -6.89 | +| explained_variance | 0.513 | +| learning_rate | 4.81e-05 | +| loss | -0.0361 | +| n_updates | 31528 | +| policy_gradient_loss | -0.0225 | +| value_loss | 9.18e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1418 | +| iterations | 3929 | +| time_elapsed | 5674 | +| total_timesteps | 8046592 | +| train/ | | +| approx_kl | 0.011205684 | +| clip_fraction | 0.321 | +| clip_range | 0.073 | +| entropy_loss | -6.81 | +| explained_variance | 0.268 | +| learning_rate | 4.81e-05 | +| loss | -0.0325 | +| n_updates | 31532 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000368 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1418 | +| iterations | 3930 | +| time_elapsed | 5675 | +| total_timesteps | 8048640 | +| train/ | | +| approx_kl | 0.01114013 | +| clip_fraction | 0.334 | +| clip_range | 0.073 | +| entropy_loss | -6.61 | +| explained_variance | 0.614 | +| learning_rate | 4.81e-05 | +| loss | -0.0367 | +| n_updates | 31536 | +| policy_gradient_loss | -0.0224 | +| value_loss | 0.000121 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1418 | +| iterations | 3931 | +| time_elapsed | 5677 | +| total_timesteps | 8050688 | +| train/ | | +| approx_kl | 0.011731546 | +| clip_fraction | 0.317 | +| clip_range | 0.073 | +| entropy_loss | -7.45 | +| explained_variance | -0.111 | +| learning_rate | 4.81e-05 | +| loss | -0.0329 | +| n_updates | 31540 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000201 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1418 | +| iterations | 3932 | +| time_elapsed | 5678 | +| total_timesteps | 8052736 | +| train/ | | +| approx_kl | 0.009513323 | +| clip_fraction | 0.323 | +| clip_range | 0.073 | +| entropy_loss | -7.34 | +| explained_variance | -0.0741 | +| learning_rate | 4.81e-05 | +| loss | -0.0309 | +| n_updates | 31544 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000271 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1418 | +| iterations | 3933 | +| time_elapsed | 5680 | +| total_timesteps | 8054784 | +| train/ | | +| approx_kl | 0.011840135 | +| clip_fraction | 0.35 | +| clip_range | 0.073 | +| entropy_loss | -6.98 | +| explained_variance | 0.663 | +| learning_rate | 4.81e-05 | +| loss | -0.038 | +| n_updates | 31548 | +| policy_gradient_loss | -0.0226 | +| value_loss | 7.07e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1418 | +| iterations | 3934 | +| time_elapsed | 5681 | +| total_timesteps | 8056832 | +| train/ | | +| approx_kl | 0.010588107 | +| clip_fraction | 0.298 | +| clip_range | 0.073 | +| entropy_loss | -6.93 | +| explained_variance | 0.272 | +| learning_rate | 4.81e-05 | +| loss | -0.0219 | +| n_updates | 31552 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.000323 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1418 | +| iterations | 3935 | +| time_elapsed | 5682 | +| total_timesteps | 8058880 | +| train/ | | +| approx_kl | 0.012033699 | +| clip_fraction | 0.307 | +| clip_range | 0.073 | +| entropy_loss | -6.73 | +| explained_variance | 0.308 | +| learning_rate | 4.81e-05 | +| loss | -0.0284 | +| n_updates | 31556 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000298 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1418 | +| iterations | 3936 | +| time_elapsed | 5684 | +| total_timesteps | 8060928 | +| train/ | | +| approx_kl | 0.013541816 | +| clip_fraction | 0.348 | +| clip_range | 0.073 | +| entropy_loss | -6.69 | +| explained_variance | 0.555 | +| learning_rate | 4.81e-05 | +| loss | -0.0322 | +| n_updates | 31560 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000106 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1418 | +| iterations | 3937 | +| time_elapsed | 5685 | +| total_timesteps | 8062976 | +| train/ | | +| approx_kl | 0.0125927655 | +| clip_fraction | 0.335 | +| clip_range | 0.073 | +| entropy_loss | -6.89 | +| explained_variance | 0.336 | +| learning_rate | 4.81e-05 | +| loss | -0.0323 | +| n_updates | 31564 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000202 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1418 | +| iterations | 3938 | +| time_elapsed | 5687 | +| total_timesteps | 8065024 | +| train/ | | +| approx_kl | 0.011894733 | +| clip_fraction | 0.344 | +| clip_range | 0.073 | +| entropy_loss | -6.98 | +| explained_variance | 0.318 | +| learning_rate | 4.81e-05 | +| loss | -0.0295 | +| n_updates | 31568 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000133 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1418 | +| iterations | 3939 | +| time_elapsed | 5688 | +| total_timesteps | 8067072 | +| train/ | | +| approx_kl | 0.008663296 | +| clip_fraction | 0.302 | +| clip_range | 0.073 | +| entropy_loss | -6.69 | +| explained_variance | 0.619 | +| learning_rate | 4.81e-05 | +| loss | -0.0255 | +| n_updates | 31572 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000144 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1418 | +| iterations | 3940 | +| time_elapsed | 5690 | +| total_timesteps | 8069120 | +| train/ | | +| approx_kl | 0.010150846 | +| clip_fraction | 0.321 | +| clip_range | 0.073 | +| entropy_loss | -7.07 | +| explained_variance | 0.217 | +| learning_rate | 4.81e-05 | +| loss | -0.0295 | +| n_updates | 31576 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000171 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1418 | +| iterations | 3941 | +| time_elapsed | 5691 | +| total_timesteps | 8071168 | +| train/ | | +| approx_kl | 0.009677882 | +| clip_fraction | 0.322 | +| clip_range | 0.073 | +| entropy_loss | -6.96 | +| explained_variance | 0.264 | +| learning_rate | 4.81e-05 | +| loss | -0.032 | +| n_updates | 31580 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000155 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1418 | +| iterations | 3942 | +| time_elapsed | 5692 | +| total_timesteps | 8073216 | +| train/ | | +| approx_kl | 0.008320086 | +| clip_fraction | 0.302 | +| clip_range | 0.073 | +| entropy_loss | -6.88 | +| explained_variance | 0.23 | +| learning_rate | 4.81e-05 | +| loss | -0.0282 | +| n_updates | 31584 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000425 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1418 | +| iterations | 3943 | +| time_elapsed | 5694 | +| total_timesteps | 8075264 | +| train/ | | +| approx_kl | 0.0111022135 | +| clip_fraction | 0.332 | +| clip_range | 0.073 | +| entropy_loss | -6.85 | +| explained_variance | 0.303 | +| learning_rate | 4.81e-05 | +| loss | -0.0342 | +| n_updates | 31588 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000167 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1418 | +| iterations | 3944 | +| time_elapsed | 5695 | +| total_timesteps | 8077312 | +| train/ | | +| approx_kl | 0.012387622 | +| clip_fraction | 0.339 | +| clip_range | 0.073 | +| entropy_loss | -6.89 | +| explained_variance | 0.646 | +| learning_rate | 4.81e-05 | +| loss | -0.0372 | +| n_updates | 31592 | +| policy_gradient_loss | -0.023 | +| value_loss | 8e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1418 | +| iterations | 3945 | +| time_elapsed | 5697 | +| total_timesteps | 8079360 | +| train/ | | +| approx_kl | 0.011205211 | +| clip_fraction | 0.317 | +| clip_range | 0.073 | +| entropy_loss | -7.01 | +| explained_variance | 0.454 | +| learning_rate | 4.81e-05 | +| loss | -0.031 | +| n_updates | 31596 | +| policy_gradient_loss | -0.021 | +| value_loss | 9.69e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1418 | +| iterations | 3946 | +| time_elapsed | 5698 | +| total_timesteps | 8081408 | +| train/ | | +| approx_kl | 0.010850655 | +| clip_fraction | 0.35 | +| clip_range | 0.073 | +| entropy_loss | -7.38 | +| explained_variance | -0.134 | +| learning_rate | 4.81e-05 | +| loss | -0.0367 | +| n_updates | 31600 | +| policy_gradient_loss | -0.0227 | +| value_loss | 7.36e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1418 | +| iterations | 3947 | +| time_elapsed | 5700 | +| total_timesteps | 8083456 | +| train/ | | +| approx_kl | 0.010547227 | +| clip_fraction | 0.286 | +| clip_range | 0.073 | +| entropy_loss | -7.04 | +| explained_variance | 0.237 | +| learning_rate | 4.81e-05 | +| loss | -0.0283 | +| n_updates | 31604 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000279 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1418 | +| iterations | 3948 | +| time_elapsed | 5701 | +| total_timesteps | 8085504 | +| train/ | | +| approx_kl | 0.010634844 | +| clip_fraction | 0.294 | +| clip_range | 0.073 | +| entropy_loss | -6.77 | +| explained_variance | 0.613 | +| learning_rate | 4.81e-05 | +| loss | -0.0292 | +| n_updates | 31608 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000142 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1418 | +| iterations | 3949 | +| time_elapsed | 5702 | +| total_timesteps | 8087552 | +| train/ | | +| approx_kl | 0.013165757 | +| clip_fraction | 0.31 | +| clip_range | 0.073 | +| entropy_loss | -6.95 | +| explained_variance | 0.421 | +| learning_rate | 4.81e-05 | +| loss | -0.0313 | +| n_updates | 31612 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000173 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1418 | +| iterations | 3950 | +| time_elapsed | 5704 | +| total_timesteps | 8089600 | +| train/ | | +| approx_kl | 0.011080262 | +| clip_fraction | 0.302 | +| clip_range | 0.073 | +| entropy_loss | -6.86 | +| explained_variance | 0.384 | +| learning_rate | 4.81e-05 | +| loss | -0.0301 | +| n_updates | 31616 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000206 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1418 | +| iterations | 3951 | +| time_elapsed | 5705 | +| total_timesteps | 8091648 | +| train/ | | +| approx_kl | 0.011399564 | +| clip_fraction | 0.328 | +| clip_range | 0.073 | +| entropy_loss | -6.84 | +| explained_variance | 0.375 | +| learning_rate | 4.81e-05 | +| loss | -0.0363 | +| n_updates | 31620 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000195 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1418 | +| iterations | 3952 | +| time_elapsed | 5707 | +| total_timesteps | 8093696 | +| train/ | | +| approx_kl | 0.012759662 | +| clip_fraction | 0.349 | +| clip_range | 0.073 | +| entropy_loss | -6.84 | +| explained_variance | 0.604 | +| learning_rate | 4.81e-05 | +| loss | -0.0313 | +| n_updates | 31624 | +| policy_gradient_loss | -0.0233 | +| value_loss | 8.47e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1418 | +| iterations | 3953 | +| time_elapsed | 5708 | +| total_timesteps | 8095744 | +| train/ | | +| approx_kl | 0.012048016 | +| clip_fraction | 0.33 | +| clip_range | 0.073 | +| entropy_loss | -7.37 | +| explained_variance | -0.0627 | +| learning_rate | 4.81e-05 | +| loss | -0.0346 | +| n_updates | 31628 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000145 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1418 | +| iterations | 3954 | +| time_elapsed | 5710 | +| total_timesteps | 8097792 | +| train/ | | +| approx_kl | 0.010764205 | +| clip_fraction | 0.321 | +| clip_range | 0.073 | +| entropy_loss | -6.67 | +| explained_variance | 0.488 | +| learning_rate | 4.81e-05 | +| loss | -0.0379 | +| n_updates | 31632 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000174 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1418 | +| iterations | 3955 | +| time_elapsed | 5711 | +| total_timesteps | 8099840 | +| train/ | | +| approx_kl | 0.011276638 | +| clip_fraction | 0.313 | +| clip_range | 0.073 | +| entropy_loss | -7.11 | +| explained_variance | 0.281 | +| learning_rate | 4.81e-05 | +| loss | -0.0392 | +| n_updates | 31636 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.00016 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1418 | +| iterations | 3956 | +| time_elapsed | 5712 | +| total_timesteps | 8101888 | +| train/ | | +| approx_kl | 0.012950755 | +| clip_fraction | 0.311 | +| clip_range | 0.073 | +| entropy_loss | -7.25 | +| explained_variance | -0.0498 | +| learning_rate | 4.81e-05 | +| loss | -0.0335 | +| n_updates | 31640 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.00015 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1418 | +| iterations | 3957 | +| time_elapsed | 5714 | +| total_timesteps | 8103936 | +| train/ | | +| approx_kl | 0.0105114225 | +| clip_fraction | 0.323 | +| clip_range | 0.073 | +| entropy_loss | -7.31 | +| explained_variance | -0.465 | +| learning_rate | 4.81e-05 | +| loss | -0.0358 | +| n_updates | 31644 | +| policy_gradient_loss | -0.0222 | +| value_loss | 8.3e-05 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1418 | +| iterations | 3958 | +| time_elapsed | 5715 | +| total_timesteps | 8105984 | +| train/ | | +| approx_kl | 0.01354713 | +| clip_fraction | 0.33 | +| clip_range | 0.073 | +| entropy_loss | -7.4 | +| explained_variance | -0.101 | +| learning_rate | 4.81e-05 | +| loss | -0.0305 | +| n_updates | 31648 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000182 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1418 | +| iterations | 3959 | +| time_elapsed | 5717 | +| total_timesteps | 8108032 | +| train/ | | +| approx_kl | 0.010119043 | +| clip_fraction | 0.296 | +| clip_range | 0.073 | +| entropy_loss | -7.15 | +| explained_variance | 0.162 | +| learning_rate | 4.81e-05 | +| loss | -0.0301 | +| n_updates | 31652 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000232 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1418 | +| iterations | 3960 | +| time_elapsed | 5718 | +| total_timesteps | 8110080 | +| train/ | | +| approx_kl | 0.008874267 | +| clip_fraction | 0.304 | +| clip_range | 0.073 | +| entropy_loss | -6.77 | +| explained_variance | 0.635 | +| learning_rate | 4.81e-05 | +| loss | -0.0382 | +| n_updates | 31656 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000132 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1418 | +| iterations | 3961 | +| time_elapsed | 5720 | +| total_timesteps | 8112128 | +| train/ | | +| approx_kl | 0.013526996 | +| clip_fraction | 0.344 | +| clip_range | 0.073 | +| entropy_loss | -7.37 | +| explained_variance | -0.0102 | +| learning_rate | 4.81e-05 | +| loss | -0.0391 | +| n_updates | 31660 | +| policy_gradient_loss | -0.0221 | +| value_loss | 0.00011 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1418 | +| iterations | 3962 | +| time_elapsed | 5721 | +| total_timesteps | 8114176 | +| train/ | | +| approx_kl | 0.010998123 | +| clip_fraction | 0.324 | +| clip_range | 0.073 | +| entropy_loss | -6.93 | +| explained_variance | 0.498 | +| learning_rate | 4.81e-05 | +| loss | -0.0251 | +| n_updates | 31664 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000152 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1418 | +| iterations | 3963 | +| time_elapsed | 5723 | +| total_timesteps | 8116224 | +| train/ | | +| approx_kl | 0.009856472 | +| clip_fraction | 0.327 | +| clip_range | 0.073 | +| entropy_loss | -6.93 | +| explained_variance | 0.589 | +| learning_rate | 4.81e-05 | +| loss | -0.0345 | +| n_updates | 31668 | +| policy_gradient_loss | -0.0221 | +| value_loss | 6.77e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1418 | +| iterations | 3964 | +| time_elapsed | 5724 | +| total_timesteps | 8118272 | +| train/ | | +| approx_kl | 0.01228171 | +| clip_fraction | 0.348 | +| clip_range | 0.073 | +| entropy_loss | -6.84 | +| explained_variance | 0.68 | +| learning_rate | 4.81e-05 | +| loss | -0.0327 | +| n_updates | 31672 | +| policy_gradient_loss | -0.0214 | +| value_loss | 7.42e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1418 | +| iterations | 3965 | +| time_elapsed | 5725 | +| total_timesteps | 8120320 | +| train/ | | +| approx_kl | 0.013062661 | +| clip_fraction | 0.359 | +| clip_range | 0.073 | +| entropy_loss | -6.67 | +| explained_variance | 0.885 | +| learning_rate | 4.81e-05 | +| loss | -0.0417 | +| n_updates | 31676 | +| policy_gradient_loss | -0.0253 | +| value_loss | 2.42e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1418 | +| iterations | 3966 | +| time_elapsed | 5727 | +| total_timesteps | 8122368 | +| train/ | | +| approx_kl | 0.01255431 | +| clip_fraction | 0.313 | +| clip_range | 0.073 | +| entropy_loss | -6.76 | +| explained_variance | 0.644 | +| learning_rate | 4.81e-05 | +| loss | -0.0295 | +| n_updates | 31680 | +| policy_gradient_loss | -0.0188 | +| value_loss | 7.86e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1418 | +| iterations | 3967 | +| time_elapsed | 5728 | +| total_timesteps | 8124416 | +| train/ | | +| approx_kl | 0.011106924 | +| clip_fraction | 0.313 | +| clip_range | 0.073 | +| entropy_loss | -7.01 | +| explained_variance | 0.471 | +| learning_rate | 4.81e-05 | +| loss | -0.0279 | +| n_updates | 31684 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000101 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1418 | +| iterations | 3968 | +| time_elapsed | 5730 | +| total_timesteps | 8126464 | +| train/ | | +| approx_kl | 0.010798207 | +| clip_fraction | 0.306 | +| clip_range | 0.073 | +| entropy_loss | -7.25 | +| explained_variance | -0.0703 | +| learning_rate | 4.81e-05 | +| loss | -0.0344 | +| n_updates | 31688 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000179 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1418 | +| iterations | 3969 | +| time_elapsed | 5731 | +| total_timesteps | 8128512 | +| train/ | | +| approx_kl | 0.011024478 | +| clip_fraction | 0.329 | +| clip_range | 0.073 | +| entropy_loss | -7.42 | +| explained_variance | -0.0851 | +| learning_rate | 4.81e-05 | +| loss | -0.0299 | +| n_updates | 31692 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000152 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1418 | +| iterations | 3970 | +| time_elapsed | 5732 | +| total_timesteps | 8130560 | +| train/ | | +| approx_kl | 0.010446906 | +| clip_fraction | 0.316 | +| clip_range | 0.073 | +| entropy_loss | -6.72 | +| explained_variance | 0.593 | +| learning_rate | 4.81e-05 | +| loss | -0.0279 | +| n_updates | 31696 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000148 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1418 | +| iterations | 3971 | +| time_elapsed | 5734 | +| total_timesteps | 8132608 | +| train/ | | +| approx_kl | 0.0089282375 | +| clip_fraction | 0.304 | +| clip_range | 0.073 | +| entropy_loss | -7.24 | +| explained_variance | 0.389 | +| learning_rate | 4.81e-05 | +| loss | -0.0321 | +| n_updates | 31700 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000109 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1418 | +| iterations | 3972 | +| time_elapsed | 5735 | +| total_timesteps | 8134656 | +| train/ | | +| approx_kl | 0.0098962635 | +| clip_fraction | 0.284 | +| clip_range | 0.073 | +| entropy_loss | -7.23 | +| explained_variance | -0.00697 | +| learning_rate | 4.81e-05 | +| loss | -0.0285 | +| n_updates | 31704 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000205 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1418 | +| iterations | 3973 | +| time_elapsed | 5737 | +| total_timesteps | 8136704 | +| train/ | | +| approx_kl | 0.008762153 | +| clip_fraction | 0.279 | +| clip_range | 0.073 | +| entropy_loss | -7.09 | +| explained_variance | 0.326 | +| learning_rate | 4.81e-05 | +| loss | -0.0264 | +| n_updates | 31708 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000253 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1418 | +| iterations | 3974 | +| time_elapsed | 5738 | +| total_timesteps | 8138752 | +| train/ | | +| approx_kl | 0.0115929805 | +| clip_fraction | 0.324 | +| clip_range | 0.073 | +| entropy_loss | -6.85 | +| explained_variance | 0.618 | +| learning_rate | 4.81e-05 | +| loss | -0.0342 | +| n_updates | 31712 | +| policy_gradient_loss | -0.022 | +| value_loss | 8.29e-05 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1418 | +| iterations | 3975 | +| time_elapsed | 5740 | +| total_timesteps | 8140800 | +| train/ | | +| approx_kl | 0.01215427 | +| clip_fraction | 0.317 | +| clip_range | 0.073 | +| entropy_loss | -6.85 | +| explained_variance | 0.519 | +| learning_rate | 4.81e-05 | +| loss | -0.0321 | +| n_updates | 31716 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000205 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1418 | +| iterations | 3976 | +| time_elapsed | 5741 | +| total_timesteps | 8142848 | +| train/ | | +| approx_kl | 0.011895275 | +| clip_fraction | 0.333 | +| clip_range | 0.073 | +| entropy_loss | -6.95 | +| explained_variance | 0.32 | +| learning_rate | 4.81e-05 | +| loss | -0.031 | +| n_updates | 31720 | +| policy_gradient_loss | -0.0223 | +| value_loss | 0.000131 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1418 | +| iterations | 3977 | +| time_elapsed | 5742 | +| total_timesteps | 8144896 | +| train/ | | +| approx_kl | 0.011439769 | +| clip_fraction | 0.297 | +| clip_range | 0.073 | +| entropy_loss | -6.77 | +| explained_variance | 0.406 | +| learning_rate | 4.81e-05 | +| loss | -0.0289 | +| n_updates | 31724 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000291 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1418 | +| iterations | 3978 | +| time_elapsed | 5744 | +| total_timesteps | 8146944 | +| train/ | | +| approx_kl | 0.012118181 | +| clip_fraction | 0.323 | +| clip_range | 0.073 | +| entropy_loss | -6.65 | +| explained_variance | 0.549 | +| learning_rate | 4.81e-05 | +| loss | -0.0325 | +| n_updates | 31728 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000157 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1418 | +| iterations | 3979 | +| time_elapsed | 5745 | +| total_timesteps | 8148992 | +| train/ | | +| approx_kl | 0.009821825 | +| clip_fraction | 0.324 | +| clip_range | 0.073 | +| entropy_loss | -7.35 | +| explained_variance | -0.294 | +| learning_rate | 4.81e-05 | +| loss | -0.03 | +| n_updates | 31732 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.0002 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1418 | +| iterations | 3980 | +| time_elapsed | 5747 | +| total_timesteps | 8151040 | +| train/ | | +| approx_kl | 0.01076203 | +| clip_fraction | 0.343 | +| clip_range | 0.073 | +| entropy_loss | -7.43 | +| explained_variance | -0.223 | +| learning_rate | 4.81e-05 | +| loss | -0.0331 | +| n_updates | 31736 | +| policy_gradient_loss | -0.0222 | +| value_loss | 9.13e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1418 | +| iterations | 3981 | +| time_elapsed | 5748 | +| total_timesteps | 8153088 | +| train/ | | +| approx_kl | 0.009951138 | +| clip_fraction | 0.314 | +| clip_range | 0.073 | +| entropy_loss | -7.04 | +| explained_variance | 0.478 | +| learning_rate | 4.81e-05 | +| loss | -0.0292 | +| n_updates | 31740 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000176 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1418 | +| iterations | 3982 | +| time_elapsed | 5750 | +| total_timesteps | 8155136 | +| train/ | | +| approx_kl | 0.011111988 | +| clip_fraction | 0.319 | +| clip_range | 0.073 | +| entropy_loss | -6.94 | +| explained_variance | 0.298 | +| learning_rate | 4.81e-05 | +| loss | -0.0367 | +| n_updates | 31744 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000275 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1418 | +| iterations | 3983 | +| time_elapsed | 5751 | +| total_timesteps | 8157184 | +| train/ | | +| approx_kl | 0.00935686 | +| clip_fraction | 0.296 | +| clip_range | 0.073 | +| entropy_loss | -7.1 | +| explained_variance | 0.249 | +| learning_rate | 4.81e-05 | +| loss | -0.0247 | +| n_updates | 31748 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000229 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1418 | +| iterations | 3984 | +| time_elapsed | 5752 | +| total_timesteps | 8159232 | +| train/ | | +| approx_kl | 0.009568729 | +| clip_fraction | 0.296 | +| clip_range | 0.073 | +| entropy_loss | -7.01 | +| explained_variance | 0.37 | +| learning_rate | 4.81e-05 | +| loss | -0.0313 | +| n_updates | 31752 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000223 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1418 | +| iterations | 3985 | +| time_elapsed | 5754 | +| total_timesteps | 8161280 | +| train/ | | +| approx_kl | 0.011002993 | +| clip_fraction | 0.315 | +| clip_range | 0.073 | +| entropy_loss | -6.94 | +| explained_variance | 0.324 | +| learning_rate | 4.81e-05 | +| loss | -0.0338 | +| n_updates | 31756 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000107 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1418 | +| iterations | 3986 | +| time_elapsed | 5755 | +| total_timesteps | 8163328 | +| train/ | | +| approx_kl | 0.011572076 | +| clip_fraction | 0.348 | +| clip_range | 0.073 | +| entropy_loss | -6.77 | +| explained_variance | 0.574 | +| learning_rate | 4.81e-05 | +| loss | -0.0328 | +| n_updates | 31760 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000152 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1418 | +| iterations | 3987 | +| time_elapsed | 5757 | +| total_timesteps | 8165376 | +| train/ | | +| approx_kl | 0.012149107 | +| clip_fraction | 0.332 | +| clip_range | 0.073 | +| entropy_loss | -6.81 | +| explained_variance | 0.68 | +| learning_rate | 4.81e-05 | +| loss | -0.039 | +| n_updates | 31764 | +| policy_gradient_loss | -0.0224 | +| value_loss | 6.45e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1418 | +| iterations | 3988 | +| time_elapsed | 5758 | +| total_timesteps | 8167424 | +| train/ | | +| approx_kl | 0.012741251 | +| clip_fraction | 0.326 | +| clip_range | 0.073 | +| entropy_loss | -7.26 | +| explained_variance | 0.277 | +| learning_rate | 4.81e-05 | +| loss | -0.0306 | +| n_updates | 31768 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000157 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1418 | +| iterations | 3989 | +| time_elapsed | 5760 | +| total_timesteps | 8169472 | +| train/ | | +| approx_kl | 0.0120547805 | +| clip_fraction | 0.324 | +| clip_range | 0.073 | +| entropy_loss | -7.26 | +| explained_variance | 0.0246 | +| learning_rate | 4.81e-05 | +| loss | -0.0375 | +| n_updates | 31772 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000219 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1418 | +| iterations | 3990 | +| time_elapsed | 5761 | +| total_timesteps | 8171520 | +| train/ | | +| approx_kl | 0.010790085 | +| clip_fraction | 0.306 | +| clip_range | 0.073 | +| entropy_loss | -6.81 | +| explained_variance | 0.494 | +| learning_rate | 4.81e-05 | +| loss | -0.0274 | +| n_updates | 31776 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000183 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1418 | +| iterations | 3991 | +| time_elapsed | 5762 | +| total_timesteps | 8173568 | +| train/ | | +| approx_kl | 0.010212057 | +| clip_fraction | 0.313 | +| clip_range | 0.073 | +| entropy_loss | -7.26 | +| explained_variance | 0.163 | +| learning_rate | 4.81e-05 | +| loss | -0.028 | +| n_updates | 31780 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000272 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1418 | +| iterations | 3992 | +| time_elapsed | 5764 | +| total_timesteps | 8175616 | +| train/ | | +| approx_kl | 0.010012407 | +| clip_fraction | 0.325 | +| clip_range | 0.073 | +| entropy_loss | -7.22 | +| explained_variance | 0.21 | +| learning_rate | 4.81e-05 | +| loss | -0.0336 | +| n_updates | 31784 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.00028 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1418 | +| iterations | 3993 | +| time_elapsed | 5765 | +| total_timesteps | 8177664 | +| train/ | | +| approx_kl | 0.012666784 | +| clip_fraction | 0.321 | +| clip_range | 0.073 | +| entropy_loss | -6.85 | +| explained_variance | 0.477 | +| learning_rate | 4.81e-05 | +| loss | -0.0312 | +| n_updates | 31788 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000132 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1418 | +| iterations | 3994 | +| time_elapsed | 5767 | +| total_timesteps | 8179712 | +| train/ | | +| approx_kl | 0.011778586 | +| clip_fraction | 0.301 | +| clip_range | 0.073 | +| entropy_loss | -7 | +| explained_variance | 0.335 | +| learning_rate | 4.81e-05 | +| loss | -0.0245 | +| n_updates | 31792 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000273 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1418 | +| iterations | 3995 | +| time_elapsed | 5768 | +| total_timesteps | 8181760 | +| train/ | | +| approx_kl | 0.011478534 | +| clip_fraction | 0.333 | +| clip_range | 0.073 | +| entropy_loss | -7.26 | +| explained_variance | -0.0637 | +| learning_rate | 4.81e-05 | +| loss | -0.0313 | +| n_updates | 31796 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000245 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1418 | +| iterations | 3996 | +| time_elapsed | 5769 | +| total_timesteps | 8183808 | +| train/ | | +| approx_kl | 0.012731899 | +| clip_fraction | 0.316 | +| clip_range | 0.073 | +| entropy_loss | -7.17 | +| explained_variance | 0.227 | +| learning_rate | 4.81e-05 | +| loss | -0.0287 | +| n_updates | 31800 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000149 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1418 | +| iterations | 3997 | +| time_elapsed | 5771 | +| total_timesteps | 8185856 | +| train/ | | +| approx_kl | 0.01050364 | +| clip_fraction | 0.314 | +| clip_range | 0.073 | +| entropy_loss | -7.15 | +| explained_variance | 0.398 | +| learning_rate | 4.81e-05 | +| loss | -0.0354 | +| n_updates | 31804 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000146 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1418 | +| iterations | 3998 | +| time_elapsed | 5772 | +| total_timesteps | 8187904 | +| train/ | | +| approx_kl | 0.010816561 | +| clip_fraction | 0.343 | +| clip_range | 0.073 | +| entropy_loss | -7.26 | +| explained_variance | 0.332 | +| learning_rate | 4.81e-05 | +| loss | -0.0313 | +| n_updates | 31808 | +| policy_gradient_loss | -0.0223 | +| value_loss | 8.91e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1418 | +| iterations | 3999 | +| time_elapsed | 5774 | +| total_timesteps | 8189952 | +| train/ | | +| approx_kl | 0.011528674 | +| clip_fraction | 0.318 | +| clip_range | 0.073 | +| entropy_loss | -7.24 | +| explained_variance | 0.276 | +| learning_rate | 4.81e-05 | +| loss | -0.0308 | +| n_updates | 31812 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000178 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1418 | +| iterations | 4000 | +| time_elapsed | 5775 | +| total_timesteps | 8192000 | +| train/ | | +| approx_kl | 0.009566087 | +| clip_fraction | 0.307 | +| clip_range | 0.073 | +| entropy_loss | -6.86 | +| explained_variance | 0.619 | +| learning_rate | 4.81e-05 | +| loss | -0.0235 | +| n_updates | 31816 | +| policy_gradient_loss | -0.0189 | +| value_loss | 8.95e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1418 | +| iterations | 4001 | +| time_elapsed | 5777 | +| total_timesteps | 8194048 | +| train/ | | +| approx_kl | 0.0099573275 | +| clip_fraction | 0.316 | +| clip_range | 0.073 | +| entropy_loss | -7.04 | +| explained_variance | 0.501 | +| learning_rate | 4.81e-05 | +| loss | -0.034 | +| n_updates | 31820 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000132 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1418 | +| iterations | 4002 | +| time_elapsed | 5778 | +| total_timesteps | 8196096 | +| train/ | | +| approx_kl | 0.010495874 | +| clip_fraction | 0.313 | +| clip_range | 0.073 | +| entropy_loss | -6.73 | +| explained_variance | 0.596 | +| learning_rate | 4.81e-05 | +| loss | -0.0272 | +| n_updates | 31824 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000134 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1418 | +| iterations | 4003 | +| time_elapsed | 5779 | +| total_timesteps | 8198144 | +| train/ | | +| approx_kl | 0.011026021 | +| clip_fraction | 0.343 | +| clip_range | 0.073 | +| entropy_loss | -6.97 | +| explained_variance | 0.361 | +| learning_rate | 4.81e-05 | +| loss | -0.0293 | +| n_updates | 31828 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000106 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1418 | +| iterations | 4004 | +| time_elapsed | 5781 | +| total_timesteps | 8200192 | +| train/ | | +| approx_kl | 0.0115878545 | +| clip_fraction | 0.298 | +| clip_range | 0.073 | +| entropy_loss | -6.96 | +| explained_variance | 0.263 | +| learning_rate | 4.81e-05 | +| loss | -0.0277 | +| n_updates | 31832 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000276 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1418 | +| iterations | 4005 | +| time_elapsed | 5782 | +| total_timesteps | 8202240 | +| train/ | | +| approx_kl | 0.011408881 | +| clip_fraction | 0.314 | +| clip_range | 0.0729 | +| entropy_loss | -6.67 | +| explained_variance | 0.545 | +| learning_rate | 4.81e-05 | +| loss | -0.0301 | +| n_updates | 31836 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000134 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1418 | +| iterations | 4006 | +| time_elapsed | 5784 | +| total_timesteps | 8204288 | +| train/ | | +| approx_kl | 0.010737558 | +| clip_fraction | 0.282 | +| clip_range | 0.0729 | +| entropy_loss | -6.78 | +| explained_variance | 0.376 | +| learning_rate | 4.81e-05 | +| loss | -0.0278 | +| n_updates | 31840 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000267 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1418 | +| iterations | 4007 | +| time_elapsed | 5785 | +| total_timesteps | 8206336 | +| train/ | | +| approx_kl | 0.011857642 | +| clip_fraction | 0.306 | +| clip_range | 0.0729 | +| entropy_loss | -7.02 | +| explained_variance | 0.294 | +| learning_rate | 4.81e-05 | +| loss | -0.033 | +| n_updates | 31844 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000155 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1418 | +| iterations | 4008 | +| time_elapsed | 5787 | +| total_timesteps | 8208384 | +| train/ | | +| approx_kl | 0.014188042 | +| clip_fraction | 0.366 | +| clip_range | 0.0729 | +| entropy_loss | -7.31 | +| explained_variance | -0.182 | +| learning_rate | 4.81e-05 | +| loss | -0.0318 | +| n_updates | 31848 | +| policy_gradient_loss | -0.0222 | +| value_loss | 0.000102 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1418 | +| iterations | 4009 | +| time_elapsed | 5788 | +| total_timesteps | 8210432 | +| train/ | | +| approx_kl | 0.011207517 | +| clip_fraction | 0.316 | +| clip_range | 0.0729 | +| entropy_loss | -7.34 | +| explained_variance | -0.0292 | +| learning_rate | 4.81e-05 | +| loss | -0.0295 | +| n_updates | 31852 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000188 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1418 | +| iterations | 4010 | +| time_elapsed | 5790 | +| total_timesteps | 8212480 | +| train/ | | +| approx_kl | 0.0111552635 | +| clip_fraction | 0.304 | +| clip_range | 0.0729 | +| entropy_loss | -6.95 | +| explained_variance | 0.49 | +| learning_rate | 4.81e-05 | +| loss | -0.0286 | +| n_updates | 31856 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000141 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1418 | +| iterations | 4011 | +| time_elapsed | 5791 | +| total_timesteps | 8214528 | +| train/ | | +| approx_kl | 0.011758273 | +| clip_fraction | 0.321 | +| clip_range | 0.0729 | +| entropy_loss | -7.43 | +| explained_variance | -0.0894 | +| learning_rate | 4.8e-05 | +| loss | -0.0324 | +| n_updates | 31860 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000152 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1418 | +| iterations | 4012 | +| time_elapsed | 5792 | +| total_timesteps | 8216576 | +| train/ | | +| approx_kl | 0.010691188 | +| clip_fraction | 0.332 | +| clip_range | 0.0729 | +| entropy_loss | -7.25 | +| explained_variance | 0.255 | +| learning_rate | 4.8e-05 | +| loss | -0.0357 | +| n_updates | 31864 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000126 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1418 | +| iterations | 4013 | +| time_elapsed | 5794 | +| total_timesteps | 8218624 | +| train/ | | +| approx_kl | 0.010688083 | +| clip_fraction | 0.326 | +| clip_range | 0.0729 | +| entropy_loss | -7.38 | +| explained_variance | -0.0272 | +| learning_rate | 4.8e-05 | +| loss | -0.0359 | +| n_updates | 31868 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000117 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1418 | +| iterations | 4014 | +| time_elapsed | 5795 | +| total_timesteps | 8220672 | +| train/ | | +| approx_kl | 0.010755293 | +| clip_fraction | 0.322 | +| clip_range | 0.0729 | +| entropy_loss | -6.83 | +| explained_variance | 0.654 | +| learning_rate | 4.8e-05 | +| loss | -0.0306 | +| n_updates | 31872 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000115 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1418 | +| iterations | 4015 | +| time_elapsed | 5797 | +| total_timesteps | 8222720 | +| train/ | | +| approx_kl | 0.009820988 | +| clip_fraction | 0.318 | +| clip_range | 0.0729 | +| entropy_loss | -6.55 | +| explained_variance | 0.698 | +| learning_rate | 4.8e-05 | +| loss | -0.0317 | +| n_updates | 31876 | +| policy_gradient_loss | -0.0194 | +| value_loss | 9.54e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1418 | +| iterations | 4016 | +| time_elapsed | 5798 | +| total_timesteps | 8224768 | +| train/ | | +| approx_kl | 0.012651008 | +| clip_fraction | 0.346 | +| clip_range | 0.0729 | +| entropy_loss | -7.09 | +| explained_variance | 0.432 | +| learning_rate | 4.8e-05 | +| loss | -0.0302 | +| n_updates | 31880 | +| policy_gradient_loss | -0.0209 | +| value_loss | 8.97e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1418 | +| iterations | 4017 | +| time_elapsed | 5800 | +| total_timesteps | 8226816 | +| train/ | | +| approx_kl | 0.0107281115 | +| clip_fraction | 0.285 | +| clip_range | 0.0729 | +| entropy_loss | -6.63 | +| explained_variance | 0.469 | +| learning_rate | 4.8e-05 | +| loss | -0.0289 | +| n_updates | 31884 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000327 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1418 | +| iterations | 4018 | +| time_elapsed | 5801 | +| total_timesteps | 8228864 | +| train/ | | +| approx_kl | 0.011596957 | +| clip_fraction | 0.332 | +| clip_range | 0.0729 | +| entropy_loss | -6.71 | +| explained_variance | 0.458 | +| learning_rate | 4.8e-05 | +| loss | -0.0381 | +| n_updates | 31888 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000118 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1418 | +| iterations | 4019 | +| time_elapsed | 5802 | +| total_timesteps | 8230912 | +| train/ | | +| approx_kl | 0.012251006 | +| clip_fraction | 0.331 | +| clip_range | 0.0729 | +| entropy_loss | -7.11 | +| explained_variance | 0.246 | +| learning_rate | 4.8e-05 | +| loss | -0.0351 | +| n_updates | 31892 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000201 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1418 | +| iterations | 4020 | +| time_elapsed | 5804 | +| total_timesteps | 8232960 | +| train/ | | +| approx_kl | 0.011210943 | +| clip_fraction | 0.319 | +| clip_range | 0.0729 | +| entropy_loss | -7.29 | +| explained_variance | -0.162 | +| learning_rate | 4.8e-05 | +| loss | -0.0305 | +| n_updates | 31896 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000216 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1418 | +| iterations | 4021 | +| time_elapsed | 5805 | +| total_timesteps | 8235008 | +| train/ | | +| approx_kl | 0.0124033345 | +| clip_fraction | 0.343 | +| clip_range | 0.0729 | +| entropy_loss | -7.38 | +| explained_variance | -0.188 | +| learning_rate | 4.8e-05 | +| loss | -0.0349 | +| n_updates | 31900 | +| policy_gradient_loss | -0.0228 | +| value_loss | 0.000108 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1418 | +| iterations | 4022 | +| time_elapsed | 5807 | +| total_timesteps | 8237056 | +| train/ | | +| approx_kl | 0.011125745 | +| clip_fraction | 0.33 | +| clip_range | 0.0729 | +| entropy_loss | -7.11 | +| explained_variance | 0.571 | +| learning_rate | 4.8e-05 | +| loss | -0.0302 | +| n_updates | 31904 | +| policy_gradient_loss | -0.0197 | +| value_loss | 9.67e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1418 | +| iterations | 4023 | +| time_elapsed | 5808 | +| total_timesteps | 8239104 | +| train/ | | +| approx_kl | 0.012135187 | +| clip_fraction | 0.342 | +| clip_range | 0.0729 | +| entropy_loss | -7.39 | +| explained_variance | -0.14 | +| learning_rate | 4.8e-05 | +| loss | -0.033 | +| n_updates | 31908 | +| policy_gradient_loss | -0.022 | +| value_loss | 7.51e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1418 | +| iterations | 4024 | +| time_elapsed | 5810 | +| total_timesteps | 8241152 | +| train/ | | +| approx_kl | 0.011586316 | +| clip_fraction | 0.312 | +| clip_range | 0.0729 | +| entropy_loss | -7.41 | +| explained_variance | -0.101 | +| learning_rate | 4.8e-05 | +| loss | -0.034 | +| n_updates | 31912 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.00014 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1418 | +| iterations | 4025 | +| time_elapsed | 5811 | +| total_timesteps | 8243200 | +| train/ | | +| approx_kl | 0.008404244 | +| clip_fraction | 0.272 | +| clip_range | 0.0729 | +| entropy_loss | -7.12 | +| explained_variance | 0.328 | +| learning_rate | 4.8e-05 | +| loss | -0.0259 | +| n_updates | 31916 | +| policy_gradient_loss | -0.0146 | +| value_loss | 0.00023 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1418 | +| iterations | 4026 | +| time_elapsed | 5812 | +| total_timesteps | 8245248 | +| train/ | | +| approx_kl | 0.011433953 | +| clip_fraction | 0.32 | +| clip_range | 0.0729 | +| entropy_loss | -6.62 | +| explained_variance | 0.631 | +| learning_rate | 4.8e-05 | +| loss | -0.0288 | +| n_updates | 31920 | +| policy_gradient_loss | -0.0206 | +| value_loss | 9.11e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1418 | +| iterations | 4027 | +| time_elapsed | 5814 | +| total_timesteps | 8247296 | +| train/ | | +| approx_kl | 0.01284634 | +| clip_fraction | 0.33 | +| clip_range | 0.0729 | +| entropy_loss | -6.34 | +| explained_variance | 0.818 | +| learning_rate | 4.8e-05 | +| loss | -0.0349 | +| n_updates | 31924 | +| policy_gradient_loss | -0.0206 | +| value_loss | 6.68e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1418 | +| iterations | 4028 | +| time_elapsed | 5815 | +| total_timesteps | 8249344 | +| train/ | | +| approx_kl | 0.011051679 | +| clip_fraction | 0.336 | +| clip_range | 0.0729 | +| entropy_loss | -7.09 | +| explained_variance | 0.406 | +| learning_rate | 4.8e-05 | +| loss | -0.0394 | +| n_updates | 31928 | +| policy_gradient_loss | -0.0217 | +| value_loss | 9.31e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1418 | +| iterations | 4029 | +| time_elapsed | 5817 | +| total_timesteps | 8251392 | +| train/ | | +| approx_kl | 0.010072008 | +| clip_fraction | 0.325 | +| clip_range | 0.0729 | +| entropy_loss | -7.2 | +| explained_variance | 0.514 | +| learning_rate | 4.8e-05 | +| loss | -0.0296 | +| n_updates | 31932 | +| policy_gradient_loss | -0.0201 | +| value_loss | 7.62e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1418 | +| iterations | 4030 | +| time_elapsed | 5818 | +| total_timesteps | 8253440 | +| train/ | | +| approx_kl | 0.009037734 | +| clip_fraction | 0.286 | +| clip_range | 0.0729 | +| entropy_loss | -7.05 | +| explained_variance | 0.262 | +| learning_rate | 4.8e-05 | +| loss | -0.0282 | +| n_updates | 31936 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000164 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1418 | +| iterations | 4031 | +| time_elapsed | 5820 | +| total_timesteps | 8255488 | +| train/ | | +| approx_kl | 0.009973513 | +| clip_fraction | 0.319 | +| clip_range | 0.0729 | +| entropy_loss | -7.26 | +| explained_variance | 0.297 | +| learning_rate | 4.8e-05 | +| loss | -0.0337 | +| n_updates | 31940 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000158 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1418 | +| iterations | 4032 | +| time_elapsed | 5821 | +| total_timesteps | 8257536 | +| train/ | | +| approx_kl | 0.01032174 | +| clip_fraction | 0.316 | +| clip_range | 0.0729 | +| entropy_loss | -6.82 | +| explained_variance | 0.342 | +| learning_rate | 4.8e-05 | +| loss | -0.0255 | +| n_updates | 31944 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000265 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1418 | +| iterations | 4033 | +| time_elapsed | 5822 | +| total_timesteps | 8259584 | +| train/ | | +| approx_kl | 0.010406473 | +| clip_fraction | 0.331 | +| clip_range | 0.0729 | +| entropy_loss | -7.19 | +| explained_variance | 0.316 | +| learning_rate | 4.8e-05 | +| loss | -0.0349 | +| n_updates | 31948 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000177 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1418 | +| iterations | 4034 | +| time_elapsed | 5824 | +| total_timesteps | 8261632 | +| train/ | | +| approx_kl | 0.008806967 | +| clip_fraction | 0.314 | +| clip_range | 0.0729 | +| entropy_loss | -7.35 | +| explained_variance | -0.277 | +| learning_rate | 4.8e-05 | +| loss | -0.0359 | +| n_updates | 31952 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000181 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1418 | +| iterations | 4035 | +| time_elapsed | 5825 | +| total_timesteps | 8263680 | +| train/ | | +| approx_kl | 0.011019463 | +| clip_fraction | 0.307 | +| clip_range | 0.0729 | +| entropy_loss | -6.9 | +| explained_variance | 0.385 | +| learning_rate | 4.8e-05 | +| loss | -0.0254 | +| n_updates | 31956 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000228 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1418 | +| iterations | 4036 | +| time_elapsed | 5827 | +| total_timesteps | 8265728 | +| train/ | | +| approx_kl | 0.011111194 | +| clip_fraction | 0.304 | +| clip_range | 0.0729 | +| entropy_loss | -6.85 | +| explained_variance | 0.466 | +| learning_rate | 4.8e-05 | +| loss | -0.0275 | +| n_updates | 31960 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000203 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1418 | +| iterations | 4037 | +| time_elapsed | 5828 | +| total_timesteps | 8267776 | +| train/ | | +| approx_kl | 0.012094674 | +| clip_fraction | 0.36 | +| clip_range | 0.0729 | +| entropy_loss | -6.76 | +| explained_variance | 0.743 | +| learning_rate | 4.8e-05 | +| loss | -0.0413 | +| n_updates | 31964 | +| policy_gradient_loss | -0.0262 | +| value_loss | 5.16e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1418 | +| iterations | 4038 | +| time_elapsed | 5830 | +| total_timesteps | 8269824 | +| train/ | | +| approx_kl | 0.01055406 | +| clip_fraction | 0.307 | +| clip_range | 0.0729 | +| entropy_loss | -6.97 | +| explained_variance | 0.594 | +| learning_rate | 4.8e-05 | +| loss | -0.0307 | +| n_updates | 31968 | +| policy_gradient_loss | -0.0206 | +| value_loss | 8.79e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1418 | +| iterations | 4039 | +| time_elapsed | 5831 | +| total_timesteps | 8271872 | +| train/ | | +| approx_kl | 0.009632615 | +| clip_fraction | 0.309 | +| clip_range | 0.0729 | +| entropy_loss | -7.08 | +| explained_variance | 0.329 | +| learning_rate | 4.8e-05 | +| loss | -0.0286 | +| n_updates | 31972 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000172 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1418 | +| iterations | 4040 | +| time_elapsed | 5833 | +| total_timesteps | 8273920 | +| train/ | | +| approx_kl | 0.011834038 | +| clip_fraction | 0.31 | +| clip_range | 0.0729 | +| entropy_loss | -7.01 | +| explained_variance | 0.487 | +| learning_rate | 4.8e-05 | +| loss | -0.0331 | +| n_updates | 31976 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000149 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1418 | +| iterations | 4041 | +| time_elapsed | 5834 | +| total_timesteps | 8275968 | +| train/ | | +| approx_kl | 0.013708533 | +| clip_fraction | 0.326 | +| clip_range | 0.0729 | +| entropy_loss | -7.25 | +| explained_variance | -0.0983 | +| learning_rate | 4.8e-05 | +| loss | -0.0385 | +| n_updates | 31980 | +| policy_gradient_loss | -0.0202 | +| value_loss | 9.69e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1418 | +| iterations | 4042 | +| time_elapsed | 5835 | +| total_timesteps | 8278016 | +| train/ | | +| approx_kl | 0.0135035105 | +| clip_fraction | 0.34 | +| clip_range | 0.0729 | +| entropy_loss | -7.41 | +| explained_variance | -0.124 | +| learning_rate | 4.8e-05 | +| loss | -0.0359 | +| n_updates | 31984 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000156 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1418 | +| iterations | 4043 | +| time_elapsed | 5837 | +| total_timesteps | 8280064 | +| train/ | | +| approx_kl | 0.008993933 | +| clip_fraction | 0.28 | +| clip_range | 0.0729 | +| entropy_loss | -6.54 | +| explained_variance | 0.518 | +| learning_rate | 4.8e-05 | +| loss | -0.0288 | +| n_updates | 31988 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000248 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1418 | +| iterations | 4044 | +| time_elapsed | 5838 | +| total_timesteps | 8282112 | +| train/ | | +| approx_kl | 0.012711545 | +| clip_fraction | 0.364 | +| clip_range | 0.0729 | +| entropy_loss | -6.73 | +| explained_variance | 0.712 | +| learning_rate | 4.8e-05 | +| loss | -0.0406 | +| n_updates | 31992 | +| policy_gradient_loss | -0.0239 | +| value_loss | 6.46e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1418 | +| iterations | 4045 | +| time_elapsed | 5840 | +| total_timesteps | 8284160 | +| train/ | | +| approx_kl | 0.01356549 | +| clip_fraction | 0.354 | +| clip_range | 0.0729 | +| entropy_loss | -6.98 | +| explained_variance | 0.18 | +| learning_rate | 4.8e-05 | +| loss | -0.0328 | +| n_updates | 31996 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000266 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1418 | +| iterations | 4046 | +| time_elapsed | 5841 | +| total_timesteps | 8286208 | +| train/ | | +| approx_kl | 0.012492871 | +| clip_fraction | 0.343 | +| clip_range | 0.0729 | +| entropy_loss | -7.18 | +| explained_variance | 0.385 | +| learning_rate | 4.8e-05 | +| loss | -0.0384 | +| n_updates | 32000 | +| policy_gradient_loss | -0.0233 | +| value_loss | 7.94e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1418 | +| iterations | 4047 | +| time_elapsed | 5843 | +| total_timesteps | 8288256 | +| train/ | | +| approx_kl | 0.011195064 | +| clip_fraction | 0.341 | +| clip_range | 0.0729 | +| entropy_loss | -6.86 | +| explained_variance | 0.577 | +| learning_rate | 4.8e-05 | +| loss | -0.0406 | +| n_updates | 32004 | +| policy_gradient_loss | -0.022 | +| value_loss | 8.47e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1418 | +| iterations | 4048 | +| time_elapsed | 5844 | +| total_timesteps | 8290304 | +| train/ | | +| approx_kl | 0.012138203 | +| clip_fraction | 0.333 | +| clip_range | 0.0729 | +| entropy_loss | -7.13 | +| explained_variance | 0.449 | +| learning_rate | 4.8e-05 | +| loss | -0.0339 | +| n_updates | 32008 | +| policy_gradient_loss | -0.0213 | +| value_loss | 8.76e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1418 | +| iterations | 4049 | +| time_elapsed | 5846 | +| total_timesteps | 8292352 | +| train/ | | +| approx_kl | 0.011791993 | +| clip_fraction | 0.329 | +| clip_range | 0.0729 | +| entropy_loss | -7.42 | +| explained_variance | -0.0562 | +| learning_rate | 4.8e-05 | +| loss | -0.0275 | +| n_updates | 32012 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.00016 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1418 | +| iterations | 4050 | +| time_elapsed | 5847 | +| total_timesteps | 8294400 | +| train/ | | +| approx_kl | 0.012654237 | +| clip_fraction | 0.328 | +| clip_range | 0.0729 | +| entropy_loss | -7.41 | +| explained_variance | -0.0709 | +| learning_rate | 4.8e-05 | +| loss | -0.0337 | +| n_updates | 32016 | +| policy_gradient_loss | -0.0219 | +| value_loss | 0.00012 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1418 | +| iterations | 4051 | +| time_elapsed | 5848 | +| total_timesteps | 8296448 | +| train/ | | +| approx_kl | 0.00859125 | +| clip_fraction | 0.301 | +| clip_range | 0.0729 | +| entropy_loss | -7.11 | +| explained_variance | 0.371 | +| learning_rate | 4.8e-05 | +| loss | -0.0314 | +| n_updates | 32020 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000186 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1418 | +| iterations | 4052 | +| time_elapsed | 5850 | +| total_timesteps | 8298496 | +| train/ | | +| approx_kl | 0.010727268 | +| clip_fraction | 0.316 | +| clip_range | 0.0729 | +| entropy_loss | -7.09 | +| explained_variance | 0.252 | +| learning_rate | 4.8e-05 | +| loss | -0.0312 | +| n_updates | 32024 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000229 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1418 | +| iterations | 4053 | +| time_elapsed | 5851 | +| total_timesteps | 8300544 | +| train/ | | +| approx_kl | 0.012368925 | +| clip_fraction | 0.309 | +| clip_range | 0.0729 | +| entropy_loss | -6.72 | +| explained_variance | 0.709 | +| learning_rate | 4.8e-05 | +| loss | -0.0277 | +| n_updates | 32028 | +| policy_gradient_loss | -0.0209 | +| value_loss | 9.3e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1418 | +| iterations | 4054 | +| time_elapsed | 5853 | +| total_timesteps | 8302592 | +| train/ | | +| approx_kl | 0.009970649 | +| clip_fraction | 0.297 | +| clip_range | 0.0729 | +| entropy_loss | -6.58 | +| explained_variance | 0.632 | +| learning_rate | 4.8e-05 | +| loss | -0.0332 | +| n_updates | 32032 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000163 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1418 | +| iterations | 4055 | +| time_elapsed | 5854 | +| total_timesteps | 8304640 | +| train/ | | +| approx_kl | 0.010830405 | +| clip_fraction | 0.33 | +| clip_range | 0.0729 | +| entropy_loss | -7.04 | +| explained_variance | 0.634 | +| learning_rate | 4.8e-05 | +| loss | -0.0372 | +| n_updates | 32036 | +| policy_gradient_loss | -0.0197 | +| value_loss | 6.51e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1418 | +| iterations | 4056 | +| time_elapsed | 5856 | +| total_timesteps | 8306688 | +| train/ | | +| approx_kl | 0.011175657 | +| clip_fraction | 0.325 | +| clip_range | 0.0729 | +| entropy_loss | -7.34 | +| explained_variance | -0.0567 | +| learning_rate | 4.8e-05 | +| loss | -0.0371 | +| n_updates | 32040 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000115 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1418 | +| iterations | 4057 | +| time_elapsed | 5857 | +| total_timesteps | 8308736 | +| train/ | | +| approx_kl | 0.011500394 | +| clip_fraction | 0.322 | +| clip_range | 0.0729 | +| entropy_loss | -7.3 | +| explained_variance | -0.0996 | +| learning_rate | 4.8e-05 | +| loss | -0.0306 | +| n_updates | 32044 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000103 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1418 | +| iterations | 4058 | +| time_elapsed | 5858 | +| total_timesteps | 8310784 | +| train/ | | +| approx_kl | 0.012330749 | +| clip_fraction | 0.337 | +| clip_range | 0.0729 | +| entropy_loss | -6.78 | +| explained_variance | 0.354 | +| learning_rate | 4.8e-05 | +| loss | -0.0315 | +| n_updates | 32048 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000267 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1418 | +| iterations | 4059 | +| time_elapsed | 5860 | +| total_timesteps | 8312832 | +| train/ | | +| approx_kl | 0.011992717 | +| clip_fraction | 0.301 | +| clip_range | 0.0729 | +| entropy_loss | -6.89 | +| explained_variance | 0.133 | +| learning_rate | 4.8e-05 | +| loss | -0.03 | +| n_updates | 32052 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000366 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1418 | +| iterations | 4060 | +| time_elapsed | 5861 | +| total_timesteps | 8314880 | +| train/ | | +| approx_kl | 0.014397037 | +| clip_fraction | 0.363 | +| clip_range | 0.0729 | +| entropy_loss | -7.01 | +| explained_variance | 0.568 | +| learning_rate | 4.8e-05 | +| loss | -0.0429 | +| n_updates | 32056 | +| policy_gradient_loss | -0.0259 | +| value_loss | 7.81e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1418 | +| iterations | 4061 | +| time_elapsed | 5863 | +| total_timesteps | 8316928 | +| train/ | | +| approx_kl | 0.011111335 | +| clip_fraction | 0.319 | +| clip_range | 0.0729 | +| entropy_loss | -7.1 | +| explained_variance | 0.358 | +| learning_rate | 4.8e-05 | +| loss | -0.0333 | +| n_updates | 32060 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000199 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1418 | +| iterations | 4062 | +| time_elapsed | 5864 | +| total_timesteps | 8318976 | +| train/ | | +| approx_kl | 0.010705229 | +| clip_fraction | 0.332 | +| clip_range | 0.0729 | +| entropy_loss | -7.19 | +| explained_variance | -0.071 | +| learning_rate | 4.8e-05 | +| loss | -0.0336 | +| n_updates | 32064 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000126 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1418 | +| iterations | 4063 | +| time_elapsed | 5866 | +| total_timesteps | 8321024 | +| train/ | | +| approx_kl | 0.010932513 | +| clip_fraction | 0.309 | +| clip_range | 0.0729 | +| entropy_loss | -6.99 | +| explained_variance | 0.338 | +| learning_rate | 4.8e-05 | +| loss | -0.0331 | +| n_updates | 32068 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.00022 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1418 | +| iterations | 4064 | +| time_elapsed | 5867 | +| total_timesteps | 8323072 | +| train/ | | +| approx_kl | 0.009093117 | +| clip_fraction | 0.319 | +| clip_range | 0.0729 | +| entropy_loss | -6.7 | +| explained_variance | 0.432 | +| learning_rate | 4.8e-05 | +| loss | -0.0268 | +| n_updates | 32072 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000165 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1418 | +| iterations | 4065 | +| time_elapsed | 5869 | +| total_timesteps | 8325120 | +| train/ | | +| approx_kl | 0.0119910855 | +| clip_fraction | 0.323 | +| clip_range | 0.0729 | +| entropy_loss | -7.19 | +| explained_variance | 0.231 | +| learning_rate | 4.8e-05 | +| loss | -0.0328 | +| n_updates | 32076 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000157 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1418 | +| iterations | 4066 | +| time_elapsed | 5870 | +| total_timesteps | 8327168 | +| train/ | | +| approx_kl | 0.011140869 | +| clip_fraction | 0.332 | +| clip_range | 0.0729 | +| entropy_loss | -7.24 | +| explained_variance | 0.411 | +| learning_rate | 4.8e-05 | +| loss | -0.0308 | +| n_updates | 32080 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000104 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1418 | +| iterations | 4067 | +| time_elapsed | 5872 | +| total_timesteps | 8329216 | +| train/ | | +| approx_kl | 0.010945494 | +| clip_fraction | 0.341 | +| clip_range | 0.0729 | +| entropy_loss | -7.35 | +| explained_variance | -0.0182 | +| learning_rate | 4.8e-05 | +| loss | -0.0305 | +| n_updates | 32084 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000113 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1418 | +| iterations | 4068 | +| time_elapsed | 5873 | +| total_timesteps | 8331264 | +| train/ | | +| approx_kl | 0.011668086 | +| clip_fraction | 0.331 | +| clip_range | 0.0729 | +| entropy_loss | -7.43 | +| explained_variance | -0.112 | +| learning_rate | 4.8e-05 | +| loss | -0.0339 | +| n_updates | 32088 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000128 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1418 | +| iterations | 4069 | +| time_elapsed | 5874 | +| total_timesteps | 8333312 | +| train/ | | +| approx_kl | 0.009558383 | +| clip_fraction | 0.278 | +| clip_range | 0.0729 | +| entropy_loss | -6.4 | +| explained_variance | 0.636 | +| learning_rate | 4.8e-05 | +| loss | -0.0251 | +| n_updates | 32092 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000209 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1418 | +| iterations | 4070 | +| time_elapsed | 5876 | +| total_timesteps | 8335360 | +| train/ | | +| approx_kl | 0.011501728 | +| clip_fraction | 0.323 | +| clip_range | 0.0729 | +| entropy_loss | -7.01 | +| explained_variance | 0.318 | +| learning_rate | 4.8e-05 | +| loss | -0.0298 | +| n_updates | 32096 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000131 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1418 | +| iterations | 4071 | +| time_elapsed | 5877 | +| total_timesteps | 8337408 | +| train/ | | +| approx_kl | 0.010317629 | +| clip_fraction | 0.306 | +| clip_range | 0.0729 | +| entropy_loss | -6.65 | +| explained_variance | 0.51 | +| learning_rate | 4.8e-05 | +| loss | -0.021 | +| n_updates | 32100 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000213 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1418 | +| iterations | 4072 | +| time_elapsed | 5879 | +| total_timesteps | 8339456 | +| train/ | | +| approx_kl | 0.011204749 | +| clip_fraction | 0.339 | +| clip_range | 0.0729 | +| entropy_loss | -7.24 | +| explained_variance | -0.072 | +| learning_rate | 4.8e-05 | +| loss | -0.0328 | +| n_updates | 32104 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000177 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1418 | +| iterations | 4073 | +| time_elapsed | 5880 | +| total_timesteps | 8341504 | +| train/ | | +| approx_kl | 0.012060669 | +| clip_fraction | 0.342 | +| clip_range | 0.0729 | +| entropy_loss | -7.39 | +| explained_variance | -0.154 | +| learning_rate | 4.8e-05 | +| loss | -0.033 | +| n_updates | 32108 | +| policy_gradient_loss | -0.0228 | +| value_loss | 0.000145 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1418 | +| iterations | 4074 | +| time_elapsed | 5882 | +| total_timesteps | 8343552 | +| train/ | | +| approx_kl | 0.01066905 | +| clip_fraction | 0.305 | +| clip_range | 0.0729 | +| entropy_loss | -6.9 | +| explained_variance | 0.314 | +| learning_rate | 4.8e-05 | +| loss | -0.0315 | +| n_updates | 32112 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.00022 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1418 | +| iterations | 4075 | +| time_elapsed | 5883 | +| total_timesteps | 8345600 | +| train/ | | +| approx_kl | 0.010909643 | +| clip_fraction | 0.301 | +| clip_range | 0.0729 | +| entropy_loss | -6.81 | +| explained_variance | 0.375 | +| learning_rate | 4.8e-05 | +| loss | -0.0309 | +| n_updates | 32116 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000179 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1418 | +| iterations | 4076 | +| time_elapsed | 5884 | +| total_timesteps | 8347648 | +| train/ | | +| approx_kl | 0.010892775 | +| clip_fraction | 0.317 | +| clip_range | 0.0729 | +| entropy_loss | -7.22 | +| explained_variance | 0.077 | +| learning_rate | 4.8e-05 | +| loss | -0.0249 | +| n_updates | 32120 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.00016 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1418 | +| iterations | 4077 | +| time_elapsed | 5886 | +| total_timesteps | 8349696 | +| train/ | | +| approx_kl | 0.01274909 | +| clip_fraction | 0.276 | +| clip_range | 0.0729 | +| entropy_loss | -6.84 | +| explained_variance | 0.389 | +| learning_rate | 4.8e-05 | +| loss | -0.0257 | +| n_updates | 32124 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000302 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1418 | +| iterations | 4078 | +| time_elapsed | 5887 | +| total_timesteps | 8351744 | +| train/ | | +| approx_kl | 0.012772351 | +| clip_fraction | 0.341 | +| clip_range | 0.0729 | +| entropy_loss | -7.09 | +| explained_variance | 0.402 | +| learning_rate | 4.8e-05 | +| loss | -0.0356 | +| n_updates | 32128 | +| policy_gradient_loss | -0.0221 | +| value_loss | 8.9e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1418 | +| iterations | 4079 | +| time_elapsed | 5889 | +| total_timesteps | 8353792 | +| train/ | | +| approx_kl | 0.01301301 | +| clip_fraction | 0.332 | +| clip_range | 0.0729 | +| entropy_loss | -7.28 | +| explained_variance | -0.0625 | +| learning_rate | 4.8e-05 | +| loss | -0.0388 | +| n_updates | 32132 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000173 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1418 | +| iterations | 4080 | +| time_elapsed | 5890 | +| total_timesteps | 8355840 | +| train/ | | +| approx_kl | 0.01151423 | +| clip_fraction | 0.293 | +| clip_range | 0.0729 | +| entropy_loss | -7.19 | +| explained_variance | 0.149 | +| learning_rate | 4.8e-05 | +| loss | -0.0315 | +| n_updates | 32136 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000228 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1418 | +| iterations | 4081 | +| time_elapsed | 5892 | +| total_timesteps | 8357888 | +| train/ | | +| approx_kl | 0.011283558 | +| clip_fraction | 0.311 | +| clip_range | 0.0729 | +| entropy_loss | -6.84 | +| explained_variance | 0.452 | +| learning_rate | 4.8e-05 | +| loss | -0.0315 | +| n_updates | 32140 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000147 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1418 | +| iterations | 4082 | +| time_elapsed | 5893 | +| total_timesteps | 8359936 | +| train/ | | +| approx_kl | 0.0133722965 | +| clip_fraction | 0.333 | +| clip_range | 0.0729 | +| entropy_loss | -7.3 | +| explained_variance | 0.196 | +| learning_rate | 4.8e-05 | +| loss | -0.0348 | +| n_updates | 32144 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000169 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1418 | +| iterations | 4083 | +| time_elapsed | 5894 | +| total_timesteps | 8361984 | +| train/ | | +| approx_kl | 0.012745747 | +| clip_fraction | 0.316 | +| clip_range | 0.0729 | +| entropy_loss | -6.74 | +| explained_variance | 0.501 | +| learning_rate | 4.8e-05 | +| loss | -0.0312 | +| n_updates | 32148 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000147 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1418 | +| iterations | 4084 | +| time_elapsed | 5896 | +| total_timesteps | 8364032 | +| train/ | | +| approx_kl | 0.010211551 | +| clip_fraction | 0.306 | +| clip_range | 0.0729 | +| entropy_loss | -6.93 | +| explained_variance | 0.374 | +| learning_rate | 4.8e-05 | +| loss | -0.0298 | +| n_updates | 32152 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000111 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1418 | +| iterations | 4085 | +| time_elapsed | 5897 | +| total_timesteps | 8366080 | +| train/ | | +| approx_kl | 0.010958463 | +| clip_fraction | 0.295 | +| clip_range | 0.0729 | +| entropy_loss | -6.82 | +| explained_variance | 0.301 | +| learning_rate | 4.8e-05 | +| loss | -0.0295 | +| n_updates | 32156 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000368 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1418 | +| iterations | 4086 | +| time_elapsed | 5899 | +| total_timesteps | 8368128 | +| train/ | | +| approx_kl | 0.013309039 | +| clip_fraction | 0.335 | +| clip_range | 0.0729 | +| entropy_loss | -6.68 | +| explained_variance | 0.5 | +| learning_rate | 4.8e-05 | +| loss | -0.0294 | +| n_updates | 32160 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000212 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1418 | +| iterations | 4087 | +| time_elapsed | 5900 | +| total_timesteps | 8370176 | +| train/ | | +| approx_kl | 0.011494512 | +| clip_fraction | 0.336 | +| clip_range | 0.0729 | +| entropy_loss | -7.06 | +| explained_variance | 0.161 | +| learning_rate | 4.8e-05 | +| loss | -0.0334 | +| n_updates | 32164 | +| policy_gradient_loss | -0.0226 | +| value_loss | 0.00015 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1418 | +| iterations | 4088 | +| time_elapsed | 5902 | +| total_timesteps | 8372224 | +| train/ | | +| approx_kl | 0.0116468845 | +| clip_fraction | 0.324 | +| clip_range | 0.0729 | +| entropy_loss | -7.31 | +| explained_variance | -0.0822 | +| learning_rate | 4.8e-05 | +| loss | -0.0331 | +| n_updates | 32168 | +| policy_gradient_loss | -0.022 | +| value_loss | 0.00014 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1418 | +| iterations | 4089 | +| time_elapsed | 5903 | +| total_timesteps | 8374272 | +| train/ | | +| approx_kl | 0.01210146 | +| clip_fraction | 0.312 | +| clip_range | 0.0729 | +| entropy_loss | -7.13 | +| explained_variance | 0.315 | +| learning_rate | 4.8e-05 | +| loss | -0.0309 | +| n_updates | 32172 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000154 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1418 | +| iterations | 4090 | +| time_elapsed | 5905 | +| total_timesteps | 8376320 | +| train/ | | +| approx_kl | 0.011269366 | +| clip_fraction | 0.302 | +| clip_range | 0.0729 | +| entropy_loss | -6.9 | +| explained_variance | 0.555 | +| learning_rate | 4.8e-05 | +| loss | -0.0275 | +| n_updates | 32176 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000121 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1418 | +| iterations | 4091 | +| time_elapsed | 5906 | +| total_timesteps | 8378368 | +| train/ | | +| approx_kl | 0.009705294 | +| clip_fraction | 0.307 | +| clip_range | 0.0729 | +| entropy_loss | -7.02 | +| explained_variance | 0.378 | +| learning_rate | 4.8e-05 | +| loss | -0.0285 | +| n_updates | 32180 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000133 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1418 | +| iterations | 4092 | +| time_elapsed | 5907 | +| total_timesteps | 8380416 | +| train/ | | +| approx_kl | 0.011136216 | +| clip_fraction | 0.3 | +| clip_range | 0.0729 | +| entropy_loss | -7.17 | +| explained_variance | 0.226 | +| learning_rate | 4.8e-05 | +| loss | -0.0333 | +| n_updates | 32184 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000147 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1418 | +| iterations | 4093 | +| time_elapsed | 5909 | +| total_timesteps | 8382464 | +| train/ | | +| approx_kl | 0.010587537 | +| clip_fraction | 0.299 | +| clip_range | 0.0729 | +| entropy_loss | -7.15 | +| explained_variance | 0.227 | +| learning_rate | 4.8e-05 | +| loss | -0.0283 | +| n_updates | 32188 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000183 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1418 | +| iterations | 4094 | +| time_elapsed | 5910 | +| total_timesteps | 8384512 | +| train/ | | +| approx_kl | 0.0112283435 | +| clip_fraction | 0.294 | +| clip_range | 0.0729 | +| entropy_loss | -7.05 | +| explained_variance | -0.045 | +| learning_rate | 4.8e-05 | +| loss | -0.0269 | +| n_updates | 32192 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000174 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1418 | +| iterations | 4095 | +| time_elapsed | 5912 | +| total_timesteps | 8386560 | +| train/ | | +| approx_kl | 0.011017198 | +| clip_fraction | 0.33 | +| clip_range | 0.0729 | +| entropy_loss | -7.23 | +| explained_variance | 0.358 | +| learning_rate | 4.8e-05 | +| loss | -0.0306 | +| n_updates | 32196 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000111 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1418 | +| iterations | 4096 | +| time_elapsed | 5913 | +| total_timesteps | 8388608 | +| train/ | | +| approx_kl | 0.010636175 | +| clip_fraction | 0.331 | +| clip_range | 0.0729 | +| entropy_loss | -6.84 | +| explained_variance | 0.476 | +| learning_rate | 4.8e-05 | +| loss | -0.0349 | +| n_updates | 32200 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000126 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.385 | +| time/ | | +| fps | 1418 | +| iterations | 4097 | +| time_elapsed | 5914 | +| total_timesteps | 8390656 | +| train/ | | +| approx_kl | 0.011503972 | +| clip_fraction | 0.323 | +| clip_range | 0.0729 | +| entropy_loss | -6.68 | +| explained_variance | 0.356 | +| learning_rate | 4.8e-05 | +| loss | -0.0275 | +| n_updates | 32204 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000252 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1418 | +| iterations | 4098 | +| time_elapsed | 5916 | +| total_timesteps | 8392704 | +| train/ | | +| approx_kl | 0.01032001 | +| clip_fraction | 0.3 | +| clip_range | 0.0729 | +| entropy_loss | -6.72 | +| explained_variance | 0.471 | +| learning_rate | 4.8e-05 | +| loss | -0.0282 | +| n_updates | 32208 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000277 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1418 | +| iterations | 4099 | +| time_elapsed | 5917 | +| total_timesteps | 8394752 | +| train/ | | +| approx_kl | 0.009887144 | +| clip_fraction | 0.334 | +| clip_range | 0.0729 | +| entropy_loss | -7.23 | +| explained_variance | 0.202 | +| learning_rate | 4.8e-05 | +| loss | -0.0357 | +| n_updates | 32212 | +| policy_gradient_loss | -0.0241 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1418 | +| iterations | 4100 | +| time_elapsed | 5919 | +| total_timesteps | 8396800 | +| train/ | | +| approx_kl | 0.010639077 | +| clip_fraction | 0.295 | +| clip_range | 0.0729 | +| entropy_loss | -6.83 | +| explained_variance | 0.343 | +| learning_rate | 4.8e-05 | +| loss | -0.0304 | +| n_updates | 32216 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000238 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1418 | +| iterations | 4101 | +| time_elapsed | 5920 | +| total_timesteps | 8398848 | +| train/ | | +| approx_kl | 0.010236621 | +| clip_fraction | 0.318 | +| clip_range | 0.0729 | +| entropy_loss | -7.44 | +| explained_variance | -0.165 | +| learning_rate | 4.8e-05 | +| loss | -0.0338 | +| n_updates | 32220 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000105 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1418 | +| iterations | 4102 | +| time_elapsed | 5922 | +| total_timesteps | 8400896 | +| train/ | | +| approx_kl | 0.010796819 | +| clip_fraction | 0.286 | +| clip_range | 0.0729 | +| entropy_loss | -7.19 | +| explained_variance | 0.102 | +| learning_rate | 4.8e-05 | +| loss | -0.0275 | +| n_updates | 32224 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000302 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.387 | +| time/ | | +| fps | 1418 | +| iterations | 4103 | +| time_elapsed | 5923 | +| total_timesteps | 8402944 | +| train/ | | +| approx_kl | 0.012607422 | +| clip_fraction | 0.309 | +| clip_range | 0.0729 | +| entropy_loss | -7.43 | +| explained_variance | -0.0998 | +| learning_rate | 4.8e-05 | +| loss | -0.0287 | +| n_updates | 32228 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000215 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.387 | +| time/ | | +| fps | 1418 | +| iterations | 4104 | +| time_elapsed | 5924 | +| total_timesteps | 8404992 | +| train/ | | +| approx_kl | 0.011535939 | +| clip_fraction | 0.317 | +| clip_range | 0.0729 | +| entropy_loss | -6.62 | +| explained_variance | 0.319 | +| learning_rate | 4.8e-05 | +| loss | -0.0264 | +| n_updates | 32232 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000358 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1418 | +| iterations | 4105 | +| time_elapsed | 5926 | +| total_timesteps | 8407040 | +| train/ | | +| approx_kl | 0.013868157 | +| clip_fraction | 0.328 | +| clip_range | 0.0729 | +| entropy_loss | -7.39 | +| explained_variance | -0.228 | +| learning_rate | 4.8e-05 | +| loss | -0.0346 | +| n_updates | 32236 | +| policy_gradient_loss | -0.0229 | +| value_loss | 0.00016 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1418 | +| iterations | 4106 | +| time_elapsed | 5927 | +| total_timesteps | 8409088 | +| train/ | | +| approx_kl | 0.010123482 | +| clip_fraction | 0.293 | +| clip_range | 0.0729 | +| entropy_loss | -6.58 | +| explained_variance | 0.197 | +| learning_rate | 4.8e-05 | +| loss | -0.0299 | +| n_updates | 32240 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000272 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1418 | +| iterations | 4107 | +| time_elapsed | 5929 | +| total_timesteps | 8411136 | +| train/ | | +| approx_kl | 0.012346168 | +| clip_fraction | 0.32 | +| clip_range | 0.0729 | +| entropy_loss | -6.83 | +| explained_variance | 0.533 | +| learning_rate | 4.8e-05 | +| loss | -0.0422 | +| n_updates | 32244 | +| policy_gradient_loss | -0.0222 | +| value_loss | 7.9e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1418 | +| iterations | 4108 | +| time_elapsed | 5930 | +| total_timesteps | 8413184 | +| train/ | | +| approx_kl | 0.010356729 | +| clip_fraction | 0.342 | +| clip_range | 0.0729 | +| entropy_loss | -7.27 | +| explained_variance | -0.373 | +| learning_rate | 4.8e-05 | +| loss | -0.0291 | +| n_updates | 32248 | +| policy_gradient_loss | -0.0202 | +| value_loss | 8.78e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1418 | +| iterations | 4109 | +| time_elapsed | 5932 | +| total_timesteps | 8415232 | +| train/ | | +| approx_kl | 0.010153375 | +| clip_fraction | 0.295 | +| clip_range | 0.0729 | +| entropy_loss | -7.22 | +| explained_variance | -0.0321 | +| learning_rate | 4.8e-05 | +| loss | -0.0311 | +| n_updates | 32252 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000152 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1418 | +| iterations | 4110 | +| time_elapsed | 5933 | +| total_timesteps | 8417280 | +| train/ | | +| approx_kl | 0.010517015 | +| clip_fraction | 0.299 | +| clip_range | 0.0729 | +| entropy_loss | -7.15 | +| explained_variance | 0.0601 | +| learning_rate | 4.8e-05 | +| loss | -0.0292 | +| n_updates | 32256 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000213 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1418 | +| iterations | 4111 | +| time_elapsed | 5935 | +| total_timesteps | 8419328 | +| train/ | | +| approx_kl | 0.010113745 | +| clip_fraction | 0.3 | +| clip_range | 0.0729 | +| entropy_loss | -7 | +| explained_variance | 0.432 | +| learning_rate | 4.8e-05 | +| loss | -0.0299 | +| n_updates | 32260 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000169 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1418 | +| iterations | 4112 | +| time_elapsed | 5936 | +| total_timesteps | 8421376 | +| train/ | | +| approx_kl | 0.0111575 | +| clip_fraction | 0.32 | +| clip_range | 0.0729 | +| entropy_loss | -7.22 | +| explained_variance | 0.00345 | +| learning_rate | 4.8e-05 | +| loss | -0.0316 | +| n_updates | 32264 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000216 | +--------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1418 | +| iterations | 4113 | +| time_elapsed | 5937 | +| total_timesteps | 8423424 | +| train/ | | +| approx_kl | 0.0117949415 | +| clip_fraction | 0.315 | +| clip_range | 0.0729 | +| entropy_loss | -7 | +| explained_variance | 0.424 | +| learning_rate | 4.8e-05 | +| loss | -0.026 | +| n_updates | 32268 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000198 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1418 | +| iterations | 4114 | +| time_elapsed | 5939 | +| total_timesteps | 8425472 | +| train/ | | +| approx_kl | 0.01175325 | +| clip_fraction | 0.347 | +| clip_range | 0.0729 | +| entropy_loss | -6.93 | +| explained_variance | 0.516 | +| learning_rate | 4.8e-05 | +| loss | -0.0345 | +| n_updates | 32272 | +| policy_gradient_loss | -0.0204 | +| value_loss | 7.77e-05 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1418 | +| iterations | 4115 | +| time_elapsed | 5940 | +| total_timesteps | 8427520 | +| train/ | | +| approx_kl | 0.01250736 | +| clip_fraction | 0.323 | +| clip_range | 0.0729 | +| entropy_loss | -7.23 | +| explained_variance | -0.137 | +| learning_rate | 4.8e-05 | +| loss | -0.0332 | +| n_updates | 32276 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000224 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1418 | +| iterations | 4116 | +| time_elapsed | 5942 | +| total_timesteps | 8429568 | +| train/ | | +| approx_kl | 0.012171315 | +| clip_fraction | 0.339 | +| clip_range | 0.0729 | +| entropy_loss | -7.42 | +| explained_variance | -0.084 | +| learning_rate | 4.8e-05 | +| loss | -0.0305 | +| n_updates | 32280 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.00019 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.386 | +| time/ | | +| fps | 1418 | +| iterations | 4117 | +| time_elapsed | 5943 | +| total_timesteps | 8431616 | +| train/ | | +| approx_kl | 0.010315519 | +| clip_fraction | 0.303 | +| clip_range | 0.0729 | +| entropy_loss | -7.06 | +| explained_variance | -0.0218 | +| learning_rate | 4.8e-05 | +| loss | -0.0277 | +| n_updates | 32284 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000157 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.389 | +| time/ | | +| fps | 1418 | +| iterations | 4118 | +| time_elapsed | 5944 | +| total_timesteps | 8433664 | +| train/ | | +| approx_kl | 0.01327127 | +| clip_fraction | 0.316 | +| clip_range | 0.0729 | +| entropy_loss | -6.74 | +| explained_variance | 0.0421 | +| learning_rate | 4.8e-05 | +| loss | -0.0267 | +| n_updates | 32288 | +| policy_gradient_loss | -0.0148 | +| value_loss | 0.000303 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.389 | +| time/ | | +| fps | 1418 | +| iterations | 4119 | +| time_elapsed | 5946 | +| total_timesteps | 8435712 | +| train/ | | +| approx_kl | 0.010346375 | +| clip_fraction | 0.331 | +| clip_range | 0.0729 | +| entropy_loss | -6.52 | +| explained_variance | 0.349 | +| learning_rate | 4.8e-05 | +| loss | -0.0321 | +| n_updates | 32292 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000164 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.389 | +| time/ | | +| fps | 1418 | +| iterations | 4120 | +| time_elapsed | 5947 | +| total_timesteps | 8437760 | +| train/ | | +| approx_kl | 0.015642175 | +| clip_fraction | 0.331 | +| clip_range | 0.0729 | +| entropy_loss | -7.14 | +| explained_variance | -0.0218 | +| learning_rate | 4.8e-05 | +| loss | -0.0362 | +| n_updates | 32296 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000162 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.388 | +| time/ | | +| fps | 1418 | +| iterations | 4121 | +| time_elapsed | 5949 | +| total_timesteps | 8439808 | +| train/ | | +| approx_kl | 0.012157727 | +| clip_fraction | 0.333 | +| clip_range | 0.0729 | +| entropy_loss | -7.17 | +| explained_variance | 0.115 | +| learning_rate | 4.8e-05 | +| loss | -0.0287 | +| n_updates | 32300 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000187 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.385 | +| time/ | | +| fps | 1418 | +| iterations | 4122 | +| time_elapsed | 5950 | +| total_timesteps | 8441856 | +| train/ | | +| approx_kl | 0.01324626 | +| clip_fraction | 0.339 | +| clip_range | 0.0729 | +| entropy_loss | -6.47 | +| explained_variance | 0.454 | +| learning_rate | 4.8e-05 | +| loss | -0.0261 | +| n_updates | 32304 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000226 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.385 | +| time/ | | +| fps | 1418 | +| iterations | 4123 | +| time_elapsed | 5952 | +| total_timesteps | 8443904 | +| train/ | | +| approx_kl | 0.013141439 | +| clip_fraction | 0.356 | +| clip_range | 0.0729 | +| entropy_loss | -7.26 | +| explained_variance | -0.133 | +| learning_rate | 4.8e-05 | +| loss | -0.0362 | +| n_updates | 32308 | +| policy_gradient_loss | -0.0223 | +| value_loss | 0.000172 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1418 | +| iterations | 4124 | +| time_elapsed | 5953 | +| total_timesteps | 8445952 | +| train/ | | +| approx_kl | 0.012482042 | +| clip_fraction | 0.367 | +| clip_range | 0.0729 | +| entropy_loss | -7.18 | +| explained_variance | 0.503 | +| learning_rate | 4.8e-05 | +| loss | -0.0441 | +| n_updates | 32312 | +| policy_gradient_loss | -0.026 | +| value_loss | 6.31e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1418 | +| iterations | 4125 | +| time_elapsed | 5955 | +| total_timesteps | 8448000 | +| train/ | | +| approx_kl | 0.011188561 | +| clip_fraction | 0.336 | +| clip_range | 0.0729 | +| entropy_loss | -7.15 | +| explained_variance | 0.401 | +| learning_rate | 4.8e-05 | +| loss | -0.0285 | +| n_updates | 32316 | +| policy_gradient_loss | -0.0195 | +| value_loss | 9.34e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1418 | +| iterations | 4126 | +| time_elapsed | 5956 | +| total_timesteps | 8450048 | +| train/ | | +| approx_kl | 0.0105324825 | +| clip_fraction | 0.343 | +| clip_range | 0.0729 | +| entropy_loss | -7.3 | +| explained_variance | 0.499 | +| learning_rate | 4.8e-05 | +| loss | -0.0363 | +| n_updates | 32320 | +| policy_gradient_loss | -0.0219 | +| value_loss | 6.57e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1418 | +| iterations | 4127 | +| time_elapsed | 5957 | +| total_timesteps | 8452096 | +| train/ | | +| approx_kl | 0.009229643 | +| clip_fraction | 0.287 | +| clip_range | 0.0729 | +| entropy_loss | -7.4 | +| explained_variance | 0.0197 | +| learning_rate | 4.8e-05 | +| loss | -0.028 | +| n_updates | 32324 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000223 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1418 | +| iterations | 4128 | +| time_elapsed | 5959 | +| total_timesteps | 8454144 | +| train/ | | +| approx_kl | 0.010607145 | +| clip_fraction | 0.295 | +| clip_range | 0.0729 | +| entropy_loss | -6.6 | +| explained_variance | 0.472 | +| learning_rate | 4.8e-05 | +| loss | -0.0235 | +| n_updates | 32328 | +| policy_gradient_loss | -0.0148 | +| value_loss | 0.000268 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1418 | +| iterations | 4129 | +| time_elapsed | 5960 | +| total_timesteps | 8456192 | +| train/ | | +| approx_kl | 0.013313258 | +| clip_fraction | 0.344 | +| clip_range | 0.0729 | +| entropy_loss | -6.93 | +| explained_variance | 0.222 | +| learning_rate | 4.8e-05 | +| loss | -0.0365 | +| n_updates | 32332 | +| policy_gradient_loss | -0.0234 | +| value_loss | 0.000135 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1418 | +| iterations | 4130 | +| time_elapsed | 5962 | +| total_timesteps | 8458240 | +| train/ | | +| approx_kl | 0.013134344 | +| clip_fraction | 0.366 | +| clip_range | 0.0729 | +| entropy_loss | -7.24 | +| explained_variance | -0.204 | +| learning_rate | 4.8e-05 | +| loss | -0.0357 | +| n_updates | 32336 | +| policy_gradient_loss | -0.0239 | +| value_loss | 9.83e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1418 | +| iterations | 4131 | +| time_elapsed | 5963 | +| total_timesteps | 8460288 | +| train/ | | +| approx_kl | 0.010984285 | +| clip_fraction | 0.306 | +| clip_range | 0.0729 | +| entropy_loss | -6.68 | +| explained_variance | 0.429 | +| learning_rate | 4.8e-05 | +| loss | -0.0296 | +| n_updates | 32340 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000146 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1418 | +| iterations | 4132 | +| time_elapsed | 5964 | +| total_timesteps | 8462336 | +| train/ | | +| approx_kl | 0.012509233 | +| clip_fraction | 0.355 | +| clip_range | 0.0729 | +| entropy_loss | -7.11 | +| explained_variance | 0.456 | +| learning_rate | 4.8e-05 | +| loss | -0.0403 | +| n_updates | 32344 | +| policy_gradient_loss | -0.022 | +| value_loss | 5.71e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1418 | +| iterations | 4133 | +| time_elapsed | 5966 | +| total_timesteps | 8464384 | +| train/ | | +| approx_kl | 0.01221772 | +| clip_fraction | 0.312 | +| clip_range | 0.0729 | +| entropy_loss | -6.77 | +| explained_variance | 0.392 | +| learning_rate | 4.8e-05 | +| loss | -0.0298 | +| n_updates | 32348 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000193 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1418 | +| iterations | 4134 | +| time_elapsed | 5967 | +| total_timesteps | 8466432 | +| train/ | | +| approx_kl | 0.01380479 | +| clip_fraction | 0.335 | +| clip_range | 0.0729 | +| entropy_loss | -7.27 | +| explained_variance | -0.201 | +| learning_rate | 4.8e-05 | +| loss | -0.0371 | +| n_updates | 32352 | +| policy_gradient_loss | -0.0211 | +| value_loss | 8.64e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1418 | +| iterations | 4135 | +| time_elapsed | 5969 | +| total_timesteps | 8468480 | +| train/ | | +| approx_kl | 0.011933578 | +| clip_fraction | 0.321 | +| clip_range | 0.0729 | +| entropy_loss | -6.75 | +| explained_variance | 0.361 | +| learning_rate | 4.8e-05 | +| loss | -0.0275 | +| n_updates | 32356 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000179 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1418 | +| iterations | 4136 | +| time_elapsed | 5970 | +| total_timesteps | 8470528 | +| train/ | | +| approx_kl | 0.012291137 | +| clip_fraction | 0.343 | +| clip_range | 0.0729 | +| entropy_loss | -7.14 | +| explained_variance | 0.186 | +| learning_rate | 4.8e-05 | +| loss | -0.0295 | +| n_updates | 32360 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000115 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1418 | +| iterations | 4137 | +| time_elapsed | 5972 | +| total_timesteps | 8472576 | +| train/ | | +| approx_kl | 0.010629724 | +| clip_fraction | 0.294 | +| clip_range | 0.0729 | +| entropy_loss | -7.16 | +| explained_variance | 0.18 | +| learning_rate | 4.8e-05 | +| loss | -0.0264 | +| n_updates | 32364 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.00021 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1418 | +| iterations | 4138 | +| time_elapsed | 5973 | +| total_timesteps | 8474624 | +| train/ | | +| approx_kl | 0.012163637 | +| clip_fraction | 0.309 | +| clip_range | 0.0729 | +| entropy_loss | -7.2 | +| explained_variance | 0.165 | +| learning_rate | 4.8e-05 | +| loss | -0.0368 | +| n_updates | 32368 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000175 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1418 | +| iterations | 4139 | +| time_elapsed | 5974 | +| total_timesteps | 8476672 | +| train/ | | +| approx_kl | 0.011835401 | +| clip_fraction | 0.341 | +| clip_range | 0.0729 | +| entropy_loss | -7.02 | +| explained_variance | 0.304 | +| learning_rate | 4.8e-05 | +| loss | -0.0291 | +| n_updates | 32372 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000197 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1418 | +| iterations | 4140 | +| time_elapsed | 5976 | +| total_timesteps | 8478720 | +| train/ | | +| approx_kl | 0.011292672 | +| clip_fraction | 0.32 | +| clip_range | 0.0729 | +| entropy_loss | -6.9 | +| explained_variance | 0.456 | +| learning_rate | 4.8e-05 | +| loss | -0.0291 | +| n_updates | 32376 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000132 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1418 | +| iterations | 4141 | +| time_elapsed | 5977 | +| total_timesteps | 8480768 | +| train/ | | +| approx_kl | 0.010783311 | +| clip_fraction | 0.318 | +| clip_range | 0.0729 | +| entropy_loss | -7.15 | +| explained_variance | 0.278 | +| learning_rate | 4.8e-05 | +| loss | -0.0273 | +| n_updates | 32380 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000151 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1418 | +| iterations | 4142 | +| time_elapsed | 5979 | +| total_timesteps | 8482816 | +| train/ | | +| approx_kl | 0.010208779 | +| clip_fraction | 0.302 | +| clip_range | 0.0729 | +| entropy_loss | -7.08 | +| explained_variance | 0.211 | +| learning_rate | 4.8e-05 | +| loss | -0.0286 | +| n_updates | 32384 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000281 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1418 | +| iterations | 4143 | +| time_elapsed | 5980 | +| total_timesteps | 8484864 | +| train/ | | +| approx_kl | 0.010984303 | +| clip_fraction | 0.295 | +| clip_range | 0.0729 | +| entropy_loss | -6.49 | +| explained_variance | 0.66 | +| learning_rate | 4.8e-05 | +| loss | -0.0335 | +| n_updates | 32388 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.00014 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1418 | +| iterations | 4144 | +| time_elapsed | 5982 | +| total_timesteps | 8486912 | +| train/ | | +| approx_kl | 0.012314517 | +| clip_fraction | 0.345 | +| clip_range | 0.0729 | +| entropy_loss | -6.94 | +| explained_variance | 0.539 | +| learning_rate | 4.8e-05 | +| loss | -0.0332 | +| n_updates | 32392 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000101 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1418 | +| iterations | 4145 | +| time_elapsed | 5983 | +| total_timesteps | 8488960 | +| train/ | | +| approx_kl | 0.012435138 | +| clip_fraction | 0.35 | +| clip_range | 0.0729 | +| entropy_loss | -7.05 | +| explained_variance | 0.318 | +| learning_rate | 4.8e-05 | +| loss | -0.0366 | +| n_updates | 32396 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.00014 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1418 | +| iterations | 4146 | +| time_elapsed | 5985 | +| total_timesteps | 8491008 | +| train/ | | +| approx_kl | 0.012007624 | +| clip_fraction | 0.315 | +| clip_range | 0.0729 | +| entropy_loss | -7.03 | +| explained_variance | -0.122 | +| learning_rate | 4.8e-05 | +| loss | -0.0274 | +| n_updates | 32400 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000211 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1418 | +| iterations | 4147 | +| time_elapsed | 5986 | +| total_timesteps | 8493056 | +| train/ | | +| approx_kl | 0.011087798 | +| clip_fraction | 0.326 | +| clip_range | 0.0729 | +| entropy_loss | -7.24 | +| explained_variance | 0.274 | +| learning_rate | 4.8e-05 | +| loss | -0.0297 | +| n_updates | 32404 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000175 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1418 | +| iterations | 4148 | +| time_elapsed | 5987 | +| total_timesteps | 8495104 | +| train/ | | +| approx_kl | 0.010953676 | +| clip_fraction | 0.336 | +| clip_range | 0.0729 | +| entropy_loss | -7.26 | +| explained_variance | -0.107 | +| learning_rate | 4.8e-05 | +| loss | -0.0297 | +| n_updates | 32408 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000193 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1418 | +| iterations | 4149 | +| time_elapsed | 5989 | +| total_timesteps | 8497152 | +| train/ | | +| approx_kl | 0.01239207 | +| clip_fraction | 0.332 | +| clip_range | 0.0729 | +| entropy_loss | -7.35 | +| explained_variance | -0.0257 | +| learning_rate | 4.8e-05 | +| loss | -0.036 | +| n_updates | 32412 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000273 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1418 | +| iterations | 4150 | +| time_elapsed | 5990 | +| total_timesteps | 8499200 | +| train/ | | +| approx_kl | 0.010970683 | +| clip_fraction | 0.298 | +| clip_range | 0.0729 | +| entropy_loss | -6.79 | +| explained_variance | 0.334 | +| learning_rate | 4.8e-05 | +| loss | -0.0294 | +| n_updates | 32416 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000366 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1418 | +| iterations | 4151 | +| time_elapsed | 5992 | +| total_timesteps | 8501248 | +| train/ | | +| approx_kl | 0.010732515 | +| clip_fraction | 0.324 | +| clip_range | 0.0729 | +| entropy_loss | -6.33 | +| explained_variance | 0.684 | +| learning_rate | 4.8e-05 | +| loss | -0.0284 | +| n_updates | 32420 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000167 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1418 | +| iterations | 4152 | +| time_elapsed | 5993 | +| total_timesteps | 8503296 | +| train/ | | +| approx_kl | 0.011484129 | +| clip_fraction | 0.335 | +| clip_range | 0.0729 | +| entropy_loss | -7.13 | +| explained_variance | 0.33 | +| learning_rate | 4.8e-05 | +| loss | -0.0299 | +| n_updates | 32424 | +| policy_gradient_loss | -0.0219 | +| value_loss | 0.000134 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1418 | +| iterations | 4153 | +| time_elapsed | 5995 | +| total_timesteps | 8505344 | +| train/ | | +| approx_kl | 0.010923608 | +| clip_fraction | 0.331 | +| clip_range | 0.0729 | +| entropy_loss | -7.36 | +| explained_variance | -0.145 | +| learning_rate | 4.8e-05 | +| loss | -0.0358 | +| n_updates | 32428 | +| policy_gradient_loss | -0.0234 | +| value_loss | 0.000103 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1418 | +| iterations | 4154 | +| time_elapsed | 5996 | +| total_timesteps | 8507392 | +| train/ | | +| approx_kl | 0.010627339 | +| clip_fraction | 0.32 | +| clip_range | 0.0729 | +| entropy_loss | -7.37 | +| explained_variance | 0.227 | +| learning_rate | 4.8e-05 | +| loss | -0.03 | +| n_updates | 32432 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000147 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1418 | +| iterations | 4155 | +| time_elapsed | 5998 | +| total_timesteps | 8509440 | +| train/ | | +| approx_kl | 0.010174392 | +| clip_fraction | 0.282 | +| clip_range | 0.0729 | +| entropy_loss | -7.01 | +| explained_variance | 0.245 | +| learning_rate | 4.8e-05 | +| loss | -0.0336 | +| n_updates | 32436 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000251 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1418 | +| iterations | 4156 | +| time_elapsed | 5999 | +| total_timesteps | 8511488 | +| train/ | | +| approx_kl | 0.010744066 | +| clip_fraction | 0.333 | +| clip_range | 0.0729 | +| entropy_loss | -7.09 | +| explained_variance | 0.121 | +| learning_rate | 4.8e-05 | +| loss | -0.0328 | +| n_updates | 32440 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000365 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1418 | +| iterations | 4157 | +| time_elapsed | 6001 | +| total_timesteps | 8513536 | +| train/ | | +| approx_kl | 0.012418745 | +| clip_fraction | 0.35 | +| clip_range | 0.0729 | +| entropy_loss | -7.09 | +| explained_variance | 0.264 | +| learning_rate | 4.8e-05 | +| loss | -0.0355 | +| n_updates | 32444 | +| policy_gradient_loss | -0.0229 | +| value_loss | 0.00012 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1418 | +| iterations | 4158 | +| time_elapsed | 6002 | +| total_timesteps | 8515584 | +| train/ | | +| approx_kl | 0.011614372 | +| clip_fraction | 0.317 | +| clip_range | 0.0729 | +| entropy_loss | -7.14 | +| explained_variance | -0.103 | +| learning_rate | 4.8e-05 | +| loss | -0.0303 | +| n_updates | 32448 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000254 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1418 | +| iterations | 4159 | +| time_elapsed | 6003 | +| total_timesteps | 8517632 | +| train/ | | +| approx_kl | 0.011371584 | +| clip_fraction | 0.325 | +| clip_range | 0.0729 | +| entropy_loss | -7.34 | +| explained_variance | -0.117 | +| learning_rate | 4.8e-05 | +| loss | -0.0312 | +| n_updates | 32452 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000216 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1418 | +| iterations | 4160 | +| time_elapsed | 6005 | +| total_timesteps | 8519680 | +| train/ | | +| approx_kl | 0.011294913 | +| clip_fraction | 0.333 | +| clip_range | 0.0729 | +| entropy_loss | -7.03 | +| explained_variance | 0.26 | +| learning_rate | 4.8e-05 | +| loss | -0.0415 | +| n_updates | 32456 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000229 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1418 | +| iterations | 4161 | +| time_elapsed | 6006 | +| total_timesteps | 8521728 | +| train/ | | +| approx_kl | 0.012541065 | +| clip_fraction | 0.309 | +| clip_range | 0.0729 | +| entropy_loss | -6.89 | +| explained_variance | 0.499 | +| learning_rate | 4.8e-05 | +| loss | -0.0257 | +| n_updates | 32460 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000185 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1418 | +| iterations | 4162 | +| time_elapsed | 6008 | +| total_timesteps | 8523776 | +| train/ | | +| approx_kl | 0.0126717435 | +| clip_fraction | 0.341 | +| clip_range | 0.0729 | +| entropy_loss | -7.01 | +| explained_variance | 0.206 | +| learning_rate | 4.8e-05 | +| loss | -0.0339 | +| n_updates | 32464 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000258 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1418 | +| iterations | 4163 | +| time_elapsed | 6009 | +| total_timesteps | 8525824 | +| train/ | | +| approx_kl | 0.01047316 | +| clip_fraction | 0.308 | +| clip_range | 0.0729 | +| entropy_loss | -6.44 | +| explained_variance | 0.627 | +| learning_rate | 4.8e-05 | +| loss | -0.03 | +| n_updates | 32468 | +| policy_gradient_loss | -0.0148 | +| value_loss | 0.000171 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1418 | +| iterations | 4164 | +| time_elapsed | 6011 | +| total_timesteps | 8527872 | +| train/ | | +| approx_kl | 0.010769039 | +| clip_fraction | 0.305 | +| clip_range | 0.0729 | +| entropy_loss | -7.33 | +| explained_variance | -0.0963 | +| learning_rate | 4.8e-05 | +| loss | -0.0362 | +| n_updates | 32472 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1418 | +| iterations | 4165 | +| time_elapsed | 6012 | +| total_timesteps | 8529920 | +| train/ | | +| approx_kl | 0.012317312 | +| clip_fraction | 0.33 | +| clip_range | 0.0729 | +| entropy_loss | -7.27 | +| explained_variance | -0.212 | +| learning_rate | 4.8e-05 | +| loss | -0.0327 | +| n_updates | 32476 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.00022 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1418 | +| iterations | 4166 | +| time_elapsed | 6014 | +| total_timesteps | 8531968 | +| train/ | | +| approx_kl | 0.014177185 | +| clip_fraction | 0.332 | +| clip_range | 0.0729 | +| entropy_loss | -7.45 | +| explained_variance | -0.148 | +| learning_rate | 4.8e-05 | +| loss | -0.0331 | +| n_updates | 32480 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000162 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1418 | +| iterations | 4167 | +| time_elapsed | 6015 | +| total_timesteps | 8534016 | +| train/ | | +| approx_kl | 0.013383469 | +| clip_fraction | 0.306 | +| clip_range | 0.0729 | +| entropy_loss | -7.31 | +| explained_variance | 0.229 | +| learning_rate | 4.8e-05 | +| loss | -0.0323 | +| n_updates | 32484 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000235 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1418 | +| iterations | 4168 | +| time_elapsed | 6016 | +| total_timesteps | 8536064 | +| train/ | | +| approx_kl | 0.012235209 | +| clip_fraction | 0.335 | +| clip_range | 0.0729 | +| entropy_loss | -6.8 | +| explained_variance | 0.401 | +| learning_rate | 4.8e-05 | +| loss | -0.0411 | +| n_updates | 32488 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000158 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1418 | +| iterations | 4169 | +| time_elapsed | 6018 | +| total_timesteps | 8538112 | +| train/ | | +| approx_kl | 0.011588717 | +| clip_fraction | 0.312 | +| clip_range | 0.0729 | +| entropy_loss | -7.23 | +| explained_variance | -0.0307 | +| learning_rate | 4.8e-05 | +| loss | -0.0328 | +| n_updates | 32492 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.00012 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1418 | +| iterations | 4170 | +| time_elapsed | 6019 | +| total_timesteps | 8540160 | +| train/ | | +| approx_kl | 0.011807294 | +| clip_fraction | 0.328 | +| clip_range | 0.0729 | +| entropy_loss | -7.26 | +| explained_variance | 0.292 | +| learning_rate | 4.8e-05 | +| loss | -0.0343 | +| n_updates | 32496 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000159 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1418 | +| iterations | 4171 | +| time_elapsed | 6021 | +| total_timesteps | 8542208 | +| train/ | | +| approx_kl | 0.010329208 | +| clip_fraction | 0.328 | +| clip_range | 0.0729 | +| entropy_loss | -7.18 | +| explained_variance | 0.315 | +| learning_rate | 4.8e-05 | +| loss | -0.0354 | +| n_updates | 32500 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000131 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1418 | +| iterations | 4172 | +| time_elapsed | 6022 | +| total_timesteps | 8544256 | +| train/ | | +| approx_kl | 0.009876177 | +| clip_fraction | 0.307 | +| clip_range | 0.0729 | +| entropy_loss | -6.9 | +| explained_variance | 0.433 | +| learning_rate | 4.8e-05 | +| loss | -0.0286 | +| n_updates | 32504 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000171 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1418 | +| iterations | 4173 | +| time_elapsed | 6024 | +| total_timesteps | 8546304 | +| train/ | | +| approx_kl | 0.012166172 | +| clip_fraction | 0.348 | +| clip_range | 0.0729 | +| entropy_loss | -6.74 | +| explained_variance | 0.54 | +| learning_rate | 4.8e-05 | +| loss | -0.0322 | +| n_updates | 32508 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000147 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1418 | +| iterations | 4174 | +| time_elapsed | 6025 | +| total_timesteps | 8548352 | +| train/ | | +| approx_kl | 0.012690852 | +| clip_fraction | 0.341 | +| clip_range | 0.0729 | +| entropy_loss | -7.19 | +| explained_variance | 0.115 | +| learning_rate | 4.8e-05 | +| loss | -0.0311 | +| n_updates | 32512 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000112 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1418 | +| iterations | 4175 | +| time_elapsed | 6027 | +| total_timesteps | 8550400 | +| train/ | | +| approx_kl | 0.012337363 | +| clip_fraction | 0.321 | +| clip_range | 0.0729 | +| entropy_loss | -6.95 | +| explained_variance | 0.501 | +| learning_rate | 4.8e-05 | +| loss | -0.0381 | +| n_updates | 32516 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000103 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1418 | +| iterations | 4176 | +| time_elapsed | 6028 | +| total_timesteps | 8552448 | +| train/ | | +| approx_kl | 0.009797314 | +| clip_fraction | 0.302 | +| clip_range | 0.0729 | +| entropy_loss | -7.04 | +| explained_variance | 0.393 | +| learning_rate | 4.8e-05 | +| loss | -0.0254 | +| n_updates | 32520 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000126 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1418 | +| iterations | 4177 | +| time_elapsed | 6029 | +| total_timesteps | 8554496 | +| train/ | | +| approx_kl | 0.010391621 | +| clip_fraction | 0.285 | +| clip_range | 0.0729 | +| entropy_loss | -6.89 | +| explained_variance | 0.358 | +| learning_rate | 4.8e-05 | +| loss | -0.0232 | +| n_updates | 32524 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000273 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1418 | +| iterations | 4178 | +| time_elapsed | 6031 | +| total_timesteps | 8556544 | +| train/ | | +| approx_kl | 0.01202258 | +| clip_fraction | 0.326 | +| clip_range | 0.0729 | +| entropy_loss | -7.25 | +| explained_variance | 0.32 | +| learning_rate | 4.8e-05 | +| loss | -0.0354 | +| n_updates | 32528 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000157 | +---------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1418 | +| iterations | 4179 | +| time_elapsed | 6032 | +| total_timesteps | 8558592 | +| train/ | | +| approx_kl | 0.0106363 | +| clip_fraction | 0.328 | +| clip_range | 0.0729 | +| entropy_loss | -7.46 | +| explained_variance | -0.255 | +| learning_rate | 4.8e-05 | +| loss | -0.034 | +| n_updates | 32532 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000124 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1418 | +| iterations | 4180 | +| time_elapsed | 6034 | +| total_timesteps | 8560640 | +| train/ | | +| approx_kl | 0.011074098 | +| clip_fraction | 0.323 | +| clip_range | 0.0729 | +| entropy_loss | -7.04 | +| explained_variance | 0.48 | +| learning_rate | 4.8e-05 | +| loss | -0.0298 | +| n_updates | 32536 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000122 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1418 | +| iterations | 4181 | +| time_elapsed | 6035 | +| total_timesteps | 8562688 | +| train/ | | +| approx_kl | 0.010854139 | +| clip_fraction | 0.341 | +| clip_range | 0.0729 | +| entropy_loss | -7.47 | +| explained_variance | -0.0539 | +| learning_rate | 4.8e-05 | +| loss | -0.0347 | +| n_updates | 32540 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.00015 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1418 | +| iterations | 4182 | +| time_elapsed | 6036 | +| total_timesteps | 8564736 | +| train/ | | +| approx_kl | 0.012284426 | +| clip_fraction | 0.326 | +| clip_range | 0.0729 | +| entropy_loss | -6.98 | +| explained_variance | 0.332 | +| learning_rate | 4.8e-05 | +| loss | -0.0304 | +| n_updates | 32544 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000185 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1418 | +| iterations | 4183 | +| time_elapsed | 6038 | +| total_timesteps | 8566784 | +| train/ | | +| approx_kl | 0.012164172 | +| clip_fraction | 0.309 | +| clip_range | 0.0729 | +| entropy_loss | -6.99 | +| explained_variance | 0.706 | +| learning_rate | 4.8e-05 | +| loss | -0.0338 | +| n_updates | 32548 | +| policy_gradient_loss | -0.0194 | +| value_loss | 8.55e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1418 | +| iterations | 4184 | +| time_elapsed | 6039 | +| total_timesteps | 8568832 | +| train/ | | +| approx_kl | 0.012387686 | +| clip_fraction | 0.324 | +| clip_range | 0.0729 | +| entropy_loss | -6.81 | +| explained_variance | 0.535 | +| learning_rate | 4.8e-05 | +| loss | -0.033 | +| n_updates | 32552 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000112 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1418 | +| iterations | 4185 | +| time_elapsed | 6041 | +| total_timesteps | 8570880 | +| train/ | | +| approx_kl | 0.013100831 | +| clip_fraction | 0.321 | +| clip_range | 0.0729 | +| entropy_loss | -7.21 | +| explained_variance | 0.386 | +| learning_rate | 4.8e-05 | +| loss | -0.0259 | +| n_updates | 32556 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000132 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1418 | +| iterations | 4186 | +| time_elapsed | 6042 | +| total_timesteps | 8572928 | +| train/ | | +| approx_kl | 0.011392795 | +| clip_fraction | 0.303 | +| clip_range | 0.0729 | +| entropy_loss | -7.03 | +| explained_variance | 0.493 | +| learning_rate | 4.8e-05 | +| loss | -0.0323 | +| n_updates | 32560 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000147 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1418 | +| iterations | 4187 | +| time_elapsed | 6044 | +| total_timesteps | 8574976 | +| train/ | | +| approx_kl | 0.011791241 | +| clip_fraction | 0.35 | +| clip_range | 0.0729 | +| entropy_loss | -6.99 | +| explained_variance | 0.511 | +| learning_rate | 4.8e-05 | +| loss | -0.0416 | +| n_updates | 32564 | +| policy_gradient_loss | -0.0208 | +| value_loss | 8.6e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1418 | +| iterations | 4188 | +| time_elapsed | 6045 | +| total_timesteps | 8577024 | +| train/ | | +| approx_kl | 0.013888271 | +| clip_fraction | 0.321 | +| clip_range | 0.0729 | +| entropy_loss | -7.09 | +| explained_variance | 0.518 | +| learning_rate | 4.8e-05 | +| loss | -0.029 | +| n_updates | 32568 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.00012 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1418 | +| iterations | 4189 | +| time_elapsed | 6047 | +| total_timesteps | 8579072 | +| train/ | | +| approx_kl | 0.013167016 | +| clip_fraction | 0.321 | +| clip_range | 0.0729 | +| entropy_loss | -7.3 | +| explained_variance | -0.0291 | +| learning_rate | 4.8e-05 | +| loss | -0.0364 | +| n_updates | 32572 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000103 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1418 | +| iterations | 4190 | +| time_elapsed | 6048 | +| total_timesteps | 8581120 | +| train/ | | +| approx_kl | 0.010719752 | +| clip_fraction | 0.31 | +| clip_range | 0.0729 | +| entropy_loss | -6.96 | +| explained_variance | 0.338 | +| learning_rate | 4.8e-05 | +| loss | -0.0276 | +| n_updates | 32576 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000295 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1418 | +| iterations | 4191 | +| time_elapsed | 6050 | +| total_timesteps | 8583168 | +| train/ | | +| approx_kl | 0.011291534 | +| clip_fraction | 0.325 | +| clip_range | 0.0729 | +| entropy_loss | -6.88 | +| explained_variance | 0.429 | +| learning_rate | 4.8e-05 | +| loss | -0.0302 | +| n_updates | 32580 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000163 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1418 | +| iterations | 4192 | +| time_elapsed | 6051 | +| total_timesteps | 8585216 | +| train/ | | +| approx_kl | 0.009076946 | +| clip_fraction | 0.323 | +| clip_range | 0.0729 | +| entropy_loss | -7.18 | +| explained_variance | 0.375 | +| learning_rate | 4.8e-05 | +| loss | -0.0316 | +| n_updates | 32584 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000103 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1418 | +| iterations | 4193 | +| time_elapsed | 6052 | +| total_timesteps | 8587264 | +| train/ | | +| approx_kl | 0.011295751 | +| clip_fraction | 0.343 | +| clip_range | 0.0729 | +| entropy_loss | -7.17 | +| explained_variance | 0.277 | +| learning_rate | 4.8e-05 | +| loss | -0.0295 | +| n_updates | 32588 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000144 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1418 | +| iterations | 4194 | +| time_elapsed | 6054 | +| total_timesteps | 8589312 | +| train/ | | +| approx_kl | 0.011568334 | +| clip_fraction | 0.313 | +| clip_range | 0.0729 | +| entropy_loss | -6.98 | +| explained_variance | 0.266 | +| learning_rate | 4.8e-05 | +| loss | -0.0333 | +| n_updates | 32592 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000367 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1418 | +| iterations | 4195 | +| time_elapsed | 6055 | +| total_timesteps | 8591360 | +| train/ | | +| approx_kl | 0.0103569655 | +| clip_fraction | 0.339 | +| clip_range | 0.0729 | +| entropy_loss | -6.92 | +| explained_variance | 0.48 | +| learning_rate | 4.8e-05 | +| loss | -0.0346 | +| n_updates | 32596 | +| policy_gradient_loss | -0.0222 | +| value_loss | 0.000126 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1418 | +| iterations | 4196 | +| time_elapsed | 6057 | +| total_timesteps | 8593408 | +| train/ | | +| approx_kl | 0.010210904 | +| clip_fraction | 0.31 | +| clip_range | 0.0729 | +| entropy_loss | -6.68 | +| explained_variance | 0.425 | +| learning_rate | 4.8e-05 | +| loss | -0.0269 | +| n_updates | 32600 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000247 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1418 | +| iterations | 4197 | +| time_elapsed | 6058 | +| total_timesteps | 8595456 | +| train/ | | +| approx_kl | 0.011727075 | +| clip_fraction | 0.326 | +| clip_range | 0.0729 | +| entropy_loss | -7.14 | +| explained_variance | 0.226 | +| learning_rate | 4.8e-05 | +| loss | -0.0317 | +| n_updates | 32604 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000169 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1418 | +| iterations | 4198 | +| time_elapsed | 6060 | +| total_timesteps | 8597504 | +| train/ | | +| approx_kl | 0.013600597 | +| clip_fraction | 0.352 | +| clip_range | 0.0729 | +| entropy_loss | -6.93 | +| explained_variance | 0.0821 | +| learning_rate | 4.8e-05 | +| loss | -0.0274 | +| n_updates | 32608 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000171 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1418 | +| iterations | 4199 | +| time_elapsed | 6061 | +| total_timesteps | 8599552 | +| train/ | | +| approx_kl | 0.0132564455 | +| clip_fraction | 0.342 | +| clip_range | 0.0729 | +| entropy_loss | -7.1 | +| explained_variance | 0.145 | +| learning_rate | 4.8e-05 | +| loss | -0.0326 | +| n_updates | 32612 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000261 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1418 | +| iterations | 4200 | +| time_elapsed | 6062 | +| total_timesteps | 8601600 | +| train/ | | +| approx_kl | 0.010554064 | +| clip_fraction | 0.31 | +| clip_range | 0.0729 | +| entropy_loss | -7.06 | +| explained_variance | 0.127 | +| learning_rate | 4.8e-05 | +| loss | -0.031 | +| n_updates | 32616 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000334 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.386 | +| time/ | | +| fps | 1418 | +| iterations | 4201 | +| time_elapsed | 6064 | +| total_timesteps | 8603648 | +| train/ | | +| approx_kl | 0.010150898 | +| clip_fraction | 0.33 | +| clip_range | 0.0728 | +| entropy_loss | -7.27 | +| explained_variance | -0.04 | +| learning_rate | 4.8e-05 | +| loss | -0.0362 | +| n_updates | 32620 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000184 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.389 | +| time/ | | +| fps | 1418 | +| iterations | 4202 | +| time_elapsed | 6065 | +| total_timesteps | 8605696 | +| train/ | | +| approx_kl | 0.010305119 | +| clip_fraction | 0.31 | +| clip_range | 0.0728 | +| entropy_loss | -6.85 | +| explained_variance | 0.358 | +| learning_rate | 4.8e-05 | +| loss | -0.0327 | +| n_updates | 32624 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000333 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.392 | +| time/ | | +| fps | 1418 | +| iterations | 4203 | +| time_elapsed | 6067 | +| total_timesteps | 8607744 | +| train/ | | +| approx_kl | 0.009432289 | +| clip_fraction | 0.298 | +| clip_range | 0.0728 | +| entropy_loss | -6.75 | +| explained_variance | 0.528 | +| learning_rate | 4.8e-05 | +| loss | -0.0273 | +| n_updates | 32628 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000236 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.395 | +| time/ | | +| fps | 1418 | +| iterations | 4204 | +| time_elapsed | 6068 | +| total_timesteps | 8609792 | +| train/ | | +| approx_kl | 0.011891153 | +| clip_fraction | 0.339 | +| clip_range | 0.0728 | +| entropy_loss | -6.87 | +| explained_variance | 0.437 | +| learning_rate | 4.8e-05 | +| loss | -0.0314 | +| n_updates | 32632 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000235 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.394 | +| time/ | | +| fps | 1418 | +| iterations | 4205 | +| time_elapsed | 6070 | +| total_timesteps | 8611840 | +| train/ | | +| approx_kl | 0.011893173 | +| clip_fraction | 0.317 | +| clip_range | 0.0728 | +| entropy_loss | -6.96 | +| explained_variance | 0.347 | +| learning_rate | 4.8e-05 | +| loss | -0.0381 | +| n_updates | 32636 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000243 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.396 | +| time/ | | +| fps | 1418 | +| iterations | 4206 | +| time_elapsed | 6071 | +| total_timesteps | 8613888 | +| train/ | | +| approx_kl | 0.012327015 | +| clip_fraction | 0.35 | +| clip_range | 0.0728 | +| entropy_loss | -7.06 | +| explained_variance | 0.0512 | +| learning_rate | 4.8e-05 | +| loss | -0.0402 | +| n_updates | 32640 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000279 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.396 | +| time/ | | +| fps | 1418 | +| iterations | 4207 | +| time_elapsed | 6072 | +| total_timesteps | 8615936 | +| train/ | | +| approx_kl | 0.011127933 | +| clip_fraction | 0.322 | +| clip_range | 0.0728 | +| entropy_loss | -6.95 | +| explained_variance | 0.405 | +| learning_rate | 4.8e-05 | +| loss | -0.0344 | +| n_updates | 32644 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000213 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.404 | +| time/ | | +| fps | 1418 | +| iterations | 4208 | +| time_elapsed | 6074 | +| total_timesteps | 8617984 | +| train/ | | +| approx_kl | 0.011491643 | +| clip_fraction | 0.362 | +| clip_range | 0.0728 | +| entropy_loss | -7.37 | +| explained_variance | -0.538 | +| learning_rate | 4.8e-05 | +| loss | -0.0424 | +| n_updates | 32648 | +| policy_gradient_loss | -0.0255 | +| value_loss | 9.35e-05 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.404 | +| time/ | | +| fps | 1418 | +| iterations | 4209 | +| time_elapsed | 6075 | +| total_timesteps | 8620032 | +| train/ | | +| approx_kl | 0.0107795 | +| clip_fraction | 0.312 | +| clip_range | 0.0728 | +| entropy_loss | -7.03 | +| explained_variance | 0.227 | +| learning_rate | 4.8e-05 | +| loss | -0.0299 | +| n_updates | 32652 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000379 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.406 | +| time/ | | +| fps | 1418 | +| iterations | 4210 | +| time_elapsed | 6077 | +| total_timesteps | 8622080 | +| train/ | | +| approx_kl | 0.011777235 | +| clip_fraction | 0.345 | +| clip_range | 0.0728 | +| entropy_loss | -7.3 | +| explained_variance | -0.00967 | +| learning_rate | 4.8e-05 | +| loss | -0.0349 | +| n_updates | 32656 | +| policy_gradient_loss | -0.0225 | +| value_loss | 0.000227 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.407 | +| time/ | | +| fps | 1418 | +| iterations | 4211 | +| time_elapsed | 6078 | +| total_timesteps | 8624128 | +| train/ | | +| approx_kl | 0.010594826 | +| clip_fraction | 0.339 | +| clip_range | 0.0728 | +| entropy_loss | -7.31 | +| explained_variance | 0.138 | +| learning_rate | 4.8e-05 | +| loss | -0.0297 | +| n_updates | 32660 | +| policy_gradient_loss | -0.022 | +| value_loss | 0.000233 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.404 | +| time/ | | +| fps | 1418 | +| iterations | 4212 | +| time_elapsed | 6080 | +| total_timesteps | 8626176 | +| train/ | | +| approx_kl | 0.010119426 | +| clip_fraction | 0.339 | +| clip_range | 0.0728 | +| entropy_loss | -7.24 | +| explained_variance | 0.163 | +| learning_rate | 4.8e-05 | +| loss | -0.0376 | +| n_updates | 32664 | +| policy_gradient_loss | -0.0228 | +| value_loss | 0.000118 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.4 | +| time/ | | +| fps | 1418 | +| iterations | 4213 | +| time_elapsed | 6081 | +| total_timesteps | 8628224 | +| train/ | | +| approx_kl | 0.011069682 | +| clip_fraction | 0.327 | +| clip_range | 0.0728 | +| entropy_loss | -6.74 | +| explained_variance | 0.583 | +| learning_rate | 4.8e-05 | +| loss | -0.0276 | +| n_updates | 32668 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.00014 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.403 | +| time/ | | +| fps | 1418 | +| iterations | 4214 | +| time_elapsed | 6082 | +| total_timesteps | 8630272 | +| train/ | | +| approx_kl | 0.009341234 | +| clip_fraction | 0.307 | +| clip_range | 0.0728 | +| entropy_loss | -6.55 | +| explained_variance | 0.435 | +| learning_rate | 4.8e-05 | +| loss | -0.0281 | +| n_updates | 32672 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000297 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.404 | +| time/ | | +| fps | 1418 | +| iterations | 4215 | +| time_elapsed | 6084 | +| total_timesteps | 8632320 | +| train/ | | +| approx_kl | 0.012643777 | +| clip_fraction | 0.333 | +| clip_range | 0.0728 | +| entropy_loss | -6.69 | +| explained_variance | 0.594 | +| learning_rate | 4.8e-05 | +| loss | -0.0344 | +| n_updates | 32676 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000123 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.404 | +| time/ | | +| fps | 1418 | +| iterations | 4216 | +| time_elapsed | 6085 | +| total_timesteps | 8634368 | +| train/ | | +| approx_kl | 0.011639355 | +| clip_fraction | 0.322 | +| clip_range | 0.0728 | +| entropy_loss | -6.6 | +| explained_variance | 0.615 | +| learning_rate | 4.79e-05 | +| loss | -0.0327 | +| n_updates | 32680 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000143 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.399 | +| time/ | | +| fps | 1418 | +| iterations | 4217 | +| time_elapsed | 6087 | +| total_timesteps | 8636416 | +| train/ | | +| approx_kl | 0.013273098 | +| clip_fraction | 0.344 | +| clip_range | 0.0728 | +| entropy_loss | -7.29 | +| explained_variance | 0.0224 | +| learning_rate | 4.79e-05 | +| loss | -0.0368 | +| n_updates | 32684 | +| policy_gradient_loss | -0.022 | +| value_loss | 0.000124 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.399 | +| time/ | | +| fps | 1418 | +| iterations | 4218 | +| time_elapsed | 6088 | +| total_timesteps | 8638464 | +| train/ | | +| approx_kl | 0.010272518 | +| clip_fraction | 0.32 | +| clip_range | 0.0728 | +| entropy_loss | -6.92 | +| explained_variance | 0.667 | +| learning_rate | 4.79e-05 | +| loss | -0.0352 | +| n_updates | 32688 | +| policy_gradient_loss | -0.0215 | +| value_loss | 8.32e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.396 | +| time/ | | +| fps | 1418 | +| iterations | 4219 | +| time_elapsed | 6090 | +| total_timesteps | 8640512 | +| train/ | | +| approx_kl | 0.013600641 | +| clip_fraction | 0.351 | +| clip_range | 0.0728 | +| entropy_loss | -7.23 | +| explained_variance | 0.489 | +| learning_rate | 4.79e-05 | +| loss | -0.0388 | +| n_updates | 32692 | +| policy_gradient_loss | -0.0249 | +| value_loss | 5.11e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.397 | +| time/ | | +| fps | 1418 | +| iterations | 4220 | +| time_elapsed | 6091 | +| total_timesteps | 8642560 | +| train/ | | +| approx_kl | 0.012970398 | +| clip_fraction | 0.338 | +| clip_range | 0.0728 | +| entropy_loss | -7.27 | +| explained_variance | 0.334 | +| learning_rate | 4.79e-05 | +| loss | -0.036 | +| n_updates | 32696 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.00012 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.396 | +| time/ | | +| fps | 1418 | +| iterations | 4221 | +| time_elapsed | 6093 | +| total_timesteps | 8644608 | +| train/ | | +| approx_kl | 0.011609575 | +| clip_fraction | 0.303 | +| clip_range | 0.0728 | +| entropy_loss | -7.13 | +| explained_variance | 0.23 | +| learning_rate | 4.79e-05 | +| loss | -0.0258 | +| n_updates | 32700 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.00022 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.39 | +| time/ | | +| fps | 1418 | +| iterations | 4222 | +| time_elapsed | 6094 | +| total_timesteps | 8646656 | +| train/ | | +| approx_kl | 0.012943728 | +| clip_fraction | 0.297 | +| clip_range | 0.0728 | +| entropy_loss | -6.85 | +| explained_variance | 0.491 | +| learning_rate | 4.79e-05 | +| loss | -0.0255 | +| n_updates | 32704 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000215 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.392 | +| time/ | | +| fps | 1418 | +| iterations | 4223 | +| time_elapsed | 6095 | +| total_timesteps | 8648704 | +| train/ | | +| approx_kl | 0.012399578 | +| clip_fraction | 0.322 | +| clip_range | 0.0728 | +| entropy_loss | -7.2 | +| explained_variance | -0.19 | +| learning_rate | 4.79e-05 | +| loss | -0.034 | +| n_updates | 32708 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000158 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.389 | +| time/ | | +| fps | 1418 | +| iterations | 4224 | +| time_elapsed | 6097 | +| total_timesteps | 8650752 | +| train/ | | +| approx_kl | 0.011429009 | +| clip_fraction | 0.301 | +| clip_range | 0.0728 | +| entropy_loss | -7.12 | +| explained_variance | 0.0641 | +| learning_rate | 4.79e-05 | +| loss | -0.0336 | +| n_updates | 32712 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000409 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.389 | +| time/ | | +| fps | 1418 | +| iterations | 4225 | +| time_elapsed | 6098 | +| total_timesteps | 8652800 | +| train/ | | +| approx_kl | 0.012651302 | +| clip_fraction | 0.321 | +| clip_range | 0.0728 | +| entropy_loss | -7.15 | +| explained_variance | 0.195 | +| learning_rate | 4.79e-05 | +| loss | -0.0302 | +| n_updates | 32716 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.00021 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.389 | +| time/ | | +| fps | 1418 | +| iterations | 4226 | +| time_elapsed | 6100 | +| total_timesteps | 8654848 | +| train/ | | +| approx_kl | 0.013081648 | +| clip_fraction | 0.364 | +| clip_range | 0.0728 | +| entropy_loss | -7.28 | +| explained_variance | -0.285 | +| learning_rate | 4.79e-05 | +| loss | -0.0364 | +| n_updates | 32720 | +| policy_gradient_loss | -0.0222 | +| value_loss | 0.000169 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.392 | +| time/ | | +| fps | 1418 | +| iterations | 4227 | +| time_elapsed | 6101 | +| total_timesteps | 8656896 | +| train/ | | +| approx_kl | 0.013321239 | +| clip_fraction | 0.318 | +| clip_range | 0.0728 | +| entropy_loss | -7.47 | +| explained_variance | -0.192 | +| learning_rate | 4.79e-05 | +| loss | -0.0315 | +| n_updates | 32724 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000134 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.396 | +| time/ | | +| fps | 1418 | +| iterations | 4228 | +| time_elapsed | 6102 | +| total_timesteps | 8658944 | +| train/ | | +| approx_kl | 0.011709118 | +| clip_fraction | 0.324 | +| clip_range | 0.0728 | +| entropy_loss | -6.91 | +| explained_variance | 0.512 | +| learning_rate | 4.79e-05 | +| loss | -0.029 | +| n_updates | 32728 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000119 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.39 | +| time/ | | +| fps | 1418 | +| iterations | 4229 | +| time_elapsed | 6104 | +| total_timesteps | 8660992 | +| train/ | | +| approx_kl | 0.011836071 | +| clip_fraction | 0.304 | +| clip_range | 0.0728 | +| entropy_loss | -7.26 | +| explained_variance | 0.275 | +| learning_rate | 4.79e-05 | +| loss | -0.0276 | +| n_updates | 32732 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000188 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.393 | +| time/ | | +| fps | 1418 | +| iterations | 4230 | +| time_elapsed | 6105 | +| total_timesteps | 8663040 | +| train/ | | +| approx_kl | 0.010797625 | +| clip_fraction | 0.317 | +| clip_range | 0.0728 | +| entropy_loss | -7.17 | +| explained_variance | -0.0632 | +| learning_rate | 4.79e-05 | +| loss | -0.0285 | +| n_updates | 32736 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000153 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.39 | +| time/ | | +| fps | 1418 | +| iterations | 4231 | +| time_elapsed | 6107 | +| total_timesteps | 8665088 | +| train/ | | +| approx_kl | 0.00894807 | +| clip_fraction | 0.321 | +| clip_range | 0.0728 | +| entropy_loss | -7.22 | +| explained_variance | 0.242 | +| learning_rate | 4.79e-05 | +| loss | -0.031 | +| n_updates | 32740 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.00015 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.39 | +| time/ | | +| fps | 1418 | +| iterations | 4232 | +| time_elapsed | 6108 | +| total_timesteps | 8667136 | +| train/ | | +| approx_kl | 0.0117621925 | +| clip_fraction | 0.321 | +| clip_range | 0.0728 | +| entropy_loss | -6.68 | +| explained_variance | 0.576 | +| learning_rate | 4.79e-05 | +| loss | -0.0336 | +| n_updates | 32744 | +| policy_gradient_loss | -0.0202 | +| value_loss | 9.19e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.394 | +| time/ | | +| fps | 1418 | +| iterations | 4233 | +| time_elapsed | 6109 | +| total_timesteps | 8669184 | +| train/ | | +| approx_kl | 0.012986652 | +| clip_fraction | 0.352 | +| clip_range | 0.0728 | +| entropy_loss | -7.13 | +| explained_variance | 0.435 | +| learning_rate | 4.79e-05 | +| loss | -0.0353 | +| n_updates | 32748 | +| policy_gradient_loss | -0.0229 | +| value_loss | 6.44e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.392 | +| time/ | | +| fps | 1418 | +| iterations | 4234 | +| time_elapsed | 6111 | +| total_timesteps | 8671232 | +| train/ | | +| approx_kl | 0.01199723 | +| clip_fraction | 0.301 | +| clip_range | 0.0728 | +| entropy_loss | -7.05 | +| explained_variance | 0.468 | +| learning_rate | 4.79e-05 | +| loss | -0.0301 | +| n_updates | 32752 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000171 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.392 | +| time/ | | +| fps | 1418 | +| iterations | 4235 | +| time_elapsed | 6112 | +| total_timesteps | 8673280 | +| train/ | | +| approx_kl | 0.013682064 | +| clip_fraction | 0.329 | +| clip_range | 0.0728 | +| entropy_loss | -7.03 | +| explained_variance | 0.366 | +| learning_rate | 4.79e-05 | +| loss | -0.0391 | +| n_updates | 32756 | +| policy_gradient_loss | -0.0207 | +| value_loss | 9.9e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.386 | +| time/ | | +| fps | 1418 | +| iterations | 4236 | +| time_elapsed | 6114 | +| total_timesteps | 8675328 | +| train/ | | +| approx_kl | 0.010344705 | +| clip_fraction | 0.316 | +| clip_range | 0.0728 | +| entropy_loss | -7.4 | +| explained_variance | 0.0417 | +| learning_rate | 4.79e-05 | +| loss | -0.0337 | +| n_updates | 32760 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000129 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.385 | +| time/ | | +| fps | 1418 | +| iterations | 4237 | +| time_elapsed | 6115 | +| total_timesteps | 8677376 | +| train/ | | +| approx_kl | 0.011373691 | +| clip_fraction | 0.308 | +| clip_range | 0.0728 | +| entropy_loss | -7.21 | +| explained_variance | 0.278 | +| learning_rate | 4.79e-05 | +| loss | -0.0315 | +| n_updates | 32764 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000142 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.389 | +| time/ | | +| fps | 1418 | +| iterations | 4238 | +| time_elapsed | 6117 | +| total_timesteps | 8679424 | +| train/ | | +| approx_kl | 0.013909706 | +| clip_fraction | 0.294 | +| clip_range | 0.0728 | +| entropy_loss | -6.89 | +| explained_variance | 0.571 | +| learning_rate | 4.79e-05 | +| loss | -0.0296 | +| n_updates | 32768 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000139 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.389 | +| time/ | | +| fps | 1418 | +| iterations | 4239 | +| time_elapsed | 6118 | +| total_timesteps | 8681472 | +| train/ | | +| approx_kl | 0.011682496 | +| clip_fraction | 0.319 | +| clip_range | 0.0728 | +| entropy_loss | -6.84 | +| explained_variance | 0.628 | +| learning_rate | 4.79e-05 | +| loss | -0.0282 | +| n_updates | 32772 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000103 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.39 | +| time/ | | +| fps | 1418 | +| iterations | 4240 | +| time_elapsed | 6120 | +| total_timesteps | 8683520 | +| train/ | | +| approx_kl | 0.011047386 | +| clip_fraction | 0.297 | +| clip_range | 0.0728 | +| entropy_loss | -6.81 | +| explained_variance | 0.303 | +| learning_rate | 4.79e-05 | +| loss | -0.0224 | +| n_updates | 32776 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000275 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.389 | +| time/ | | +| fps | 1418 | +| iterations | 4241 | +| time_elapsed | 6121 | +| total_timesteps | 8685568 | +| train/ | | +| approx_kl | 0.013734719 | +| clip_fraction | 0.33 | +| clip_range | 0.0728 | +| entropy_loss | -7.08 | +| explained_variance | 0.307 | +| learning_rate | 4.79e-05 | +| loss | -0.0355 | +| n_updates | 32780 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000144 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.391 | +| time/ | | +| fps | 1418 | +| iterations | 4242 | +| time_elapsed | 6122 | +| total_timesteps | 8687616 | +| train/ | | +| approx_kl | 0.013801269 | +| clip_fraction | 0.331 | +| clip_range | 0.0728 | +| entropy_loss | -7.06 | +| explained_variance | 0.33 | +| learning_rate | 4.79e-05 | +| loss | -0.0339 | +| n_updates | 32784 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000308 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.398 | +| time/ | | +| fps | 1418 | +| iterations | 4243 | +| time_elapsed | 6124 | +| total_timesteps | 8689664 | +| train/ | | +| approx_kl | 0.012430014 | +| clip_fraction | 0.328 | +| clip_range | 0.0728 | +| entropy_loss | -7.12 | +| explained_variance | 0.262 | +| learning_rate | 4.79e-05 | +| loss | -0.0302 | +| n_updates | 32788 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000197 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.396 | +| time/ | | +| fps | 1418 | +| iterations | 4244 | +| time_elapsed | 6125 | +| total_timesteps | 8691712 | +| train/ | | +| approx_kl | 0.011314601 | +| clip_fraction | 0.357 | +| clip_range | 0.0728 | +| entropy_loss | -7.26 | +| explained_variance | 0.369 | +| learning_rate | 4.79e-05 | +| loss | -0.0343 | +| n_updates | 32792 | +| policy_gradient_loss | -0.0226 | +| value_loss | 8.31e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.397 | +| time/ | | +| fps | 1418 | +| iterations | 4245 | +| time_elapsed | 6127 | +| total_timesteps | 8693760 | +| train/ | | +| approx_kl | 0.01198988 | +| clip_fraction | 0.329 | +| clip_range | 0.0728 | +| entropy_loss | -7.19 | +| explained_variance | 0.303 | +| learning_rate | 4.79e-05 | +| loss | -0.0357 | +| n_updates | 32796 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.00014 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.398 | +| time/ | | +| fps | 1418 | +| iterations | 4246 | +| time_elapsed | 6128 | +| total_timesteps | 8695808 | +| train/ | | +| approx_kl | 0.011276483 | +| clip_fraction | 0.291 | +| clip_range | 0.0728 | +| entropy_loss | -6.77 | +| explained_variance | 0.38 | +| learning_rate | 4.79e-05 | +| loss | -0.0223 | +| n_updates | 32800 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000239 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.396 | +| time/ | | +| fps | 1418 | +| iterations | 4247 | +| time_elapsed | 6129 | +| total_timesteps | 8697856 | +| train/ | | +| approx_kl | 0.014335597 | +| clip_fraction | 0.346 | +| clip_range | 0.0728 | +| entropy_loss | -7.2 | +| explained_variance | 0.278 | +| learning_rate | 4.79e-05 | +| loss | -0.0304 | +| n_updates | 32804 | +| policy_gradient_loss | -0.0219 | +| value_loss | 0.000138 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.396 | +| time/ | | +| fps | 1418 | +| iterations | 4248 | +| time_elapsed | 6131 | +| total_timesteps | 8699904 | +| train/ | | +| approx_kl | 0.0122205615 | +| clip_fraction | 0.339 | +| clip_range | 0.0728 | +| entropy_loss | -7.04 | +| explained_variance | 0.27 | +| learning_rate | 4.79e-05 | +| loss | -0.033 | +| n_updates | 32808 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000138 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.395 | +| time/ | | +| fps | 1418 | +| iterations | 4249 | +| time_elapsed | 6132 | +| total_timesteps | 8701952 | +| train/ | | +| approx_kl | 0.012343119 | +| clip_fraction | 0.358 | +| clip_range | 0.0728 | +| entropy_loss | -7.38 | +| explained_variance | -0.0496 | +| learning_rate | 4.79e-05 | +| loss | -0.0394 | +| n_updates | 32812 | +| policy_gradient_loss | -0.0224 | +| value_loss | 0.000137 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.391 | +| time/ | | +| fps | 1418 | +| iterations | 4250 | +| time_elapsed | 6134 | +| total_timesteps | 8704000 | +| train/ | | +| approx_kl | 0.010719851 | +| clip_fraction | 0.299 | +| clip_range | 0.0728 | +| entropy_loss | -7.19 | +| explained_variance | 0.256 | +| learning_rate | 4.79e-05 | +| loss | -0.0344 | +| n_updates | 32816 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000231 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.389 | +| time/ | | +| fps | 1418 | +| iterations | 4251 | +| time_elapsed | 6135 | +| total_timesteps | 8706048 | +| train/ | | +| approx_kl | 0.01059012 | +| clip_fraction | 0.344 | +| clip_range | 0.0728 | +| entropy_loss | -6.77 | +| explained_variance | 0.585 | +| learning_rate | 4.79e-05 | +| loss | -0.0372 | +| n_updates | 32820 | +| policy_gradient_loss | -0.0233 | +| value_loss | 6.88e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.394 | +| time/ | | +| fps | 1418 | +| iterations | 4252 | +| time_elapsed | 6137 | +| total_timesteps | 8708096 | +| train/ | | +| approx_kl | 0.010825162 | +| clip_fraction | 0.302 | +| clip_range | 0.0728 | +| entropy_loss | -6.27 | +| explained_variance | 0.629 | +| learning_rate | 4.79e-05 | +| loss | -0.0259 | +| n_updates | 32824 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000198 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.394 | +| time/ | | +| fps | 1418 | +| iterations | 4253 | +| time_elapsed | 6138 | +| total_timesteps | 8710144 | +| train/ | | +| approx_kl | 0.011932941 | +| clip_fraction | 0.334 | +| clip_range | 0.0728 | +| entropy_loss | -6.93 | +| explained_variance | 0.266 | +| learning_rate | 4.79e-05 | +| loss | -0.0332 | +| n_updates | 32828 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000139 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.394 | +| time/ | | +| fps | 1418 | +| iterations | 4254 | +| time_elapsed | 6139 | +| total_timesteps | 8712192 | +| train/ | | +| approx_kl | 0.014947945 | +| clip_fraction | 0.359 | +| clip_range | 0.0728 | +| entropy_loss | -7.29 | +| explained_variance | -0.34 | +| learning_rate | 4.79e-05 | +| loss | -0.0345 | +| n_updates | 32832 | +| policy_gradient_loss | -0.0231 | +| value_loss | 7.89e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.396 | +| time/ | | +| fps | 1418 | +| iterations | 4255 | +| time_elapsed | 6141 | +| total_timesteps | 8714240 | +| train/ | | +| approx_kl | 0.014299171 | +| clip_fraction | 0.33 | +| clip_range | 0.0728 | +| entropy_loss | -7.34 | +| explained_variance | -0.222 | +| learning_rate | 4.79e-05 | +| loss | -0.03 | +| n_updates | 32836 | +| policy_gradient_loss | -0.0202 | +| value_loss | 7.98e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.394 | +| time/ | | +| fps | 1418 | +| iterations | 4256 | +| time_elapsed | 6142 | +| total_timesteps | 8716288 | +| train/ | | +| approx_kl | 0.0122879585 | +| clip_fraction | 0.305 | +| clip_range | 0.0728 | +| entropy_loss | -7.26 | +| explained_variance | 0.258 | +| learning_rate | 4.79e-05 | +| loss | -0.0235 | +| n_updates | 32840 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000167 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.394 | +| time/ | | +| fps | 1418 | +| iterations | 4257 | +| time_elapsed | 6144 | +| total_timesteps | 8718336 | +| train/ | | +| approx_kl | 0.010164863 | +| clip_fraction | 0.289 | +| clip_range | 0.0728 | +| entropy_loss | -6.6 | +| explained_variance | 0.259 | +| learning_rate | 4.79e-05 | +| loss | -0.0215 | +| n_updates | 32844 | +| policy_gradient_loss | -0.0136 | +| value_loss | 0.000346 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.389 | +| time/ | | +| fps | 1418 | +| iterations | 4258 | +| time_elapsed | 6145 | +| total_timesteps | 8720384 | +| train/ | | +| approx_kl | 0.012432683 | +| clip_fraction | 0.316 | +| clip_range | 0.0728 | +| entropy_loss | -7.35 | +| explained_variance | -0.148 | +| learning_rate | 4.79e-05 | +| loss | -0.032 | +| n_updates | 32848 | +| policy_gradient_loss | -0.0222 | +| value_loss | 0.000137 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.387 | +| time/ | | +| fps | 1418 | +| iterations | 4259 | +| time_elapsed | 6147 | +| total_timesteps | 8722432 | +| train/ | | +| approx_kl | 0.0129165305 | +| clip_fraction | 0.328 | +| clip_range | 0.0728 | +| entropy_loss | -7.31 | +| explained_variance | 0.101 | +| learning_rate | 4.79e-05 | +| loss | -0.0339 | +| n_updates | 32852 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000232 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.391 | +| time/ | | +| fps | 1418 | +| iterations | 4260 | +| time_elapsed | 6148 | +| total_timesteps | 8724480 | +| train/ | | +| approx_kl | 0.014176294 | +| clip_fraction | 0.376 | +| clip_range | 0.0728 | +| entropy_loss | -7.02 | +| explained_variance | 0.259 | +| learning_rate | 4.79e-05 | +| loss | -0.0385 | +| n_updates | 32856 | +| policy_gradient_loss | -0.0205 | +| value_loss | 8.82e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.394 | +| time/ | | +| fps | 1418 | +| iterations | 4261 | +| time_elapsed | 6149 | +| total_timesteps | 8726528 | +| train/ | | +| approx_kl | 0.012778761 | +| clip_fraction | 0.313 | +| clip_range | 0.0728 | +| entropy_loss | -6.78 | +| explained_variance | 0.507 | +| learning_rate | 4.79e-05 | +| loss | -0.0276 | +| n_updates | 32860 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000157 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.394 | +| time/ | | +| fps | 1418 | +| iterations | 4262 | +| time_elapsed | 6151 | +| total_timesteps | 8728576 | +| train/ | | +| approx_kl | 0.011012634 | +| clip_fraction | 0.288 | +| clip_range | 0.0728 | +| entropy_loss | -7.23 | +| explained_variance | 0.19 | +| learning_rate | 4.79e-05 | +| loss | -0.023 | +| n_updates | 32864 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000226 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.387 | +| time/ | | +| fps | 1418 | +| iterations | 4263 | +| time_elapsed | 6152 | +| total_timesteps | 8730624 | +| train/ | | +| approx_kl | 0.013911653 | +| clip_fraction | 0.329 | +| clip_range | 0.0728 | +| entropy_loss | -7.07 | +| explained_variance | 0.228 | +| learning_rate | 4.79e-05 | +| loss | -0.0321 | +| n_updates | 32868 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000192 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.389 | +| time/ | | +| fps | 1418 | +| iterations | 4264 | +| time_elapsed | 6154 | +| total_timesteps | 8732672 | +| train/ | | +| approx_kl | 0.012502514 | +| clip_fraction | 0.346 | +| clip_range | 0.0728 | +| entropy_loss | -6.94 | +| explained_variance | 0.549 | +| learning_rate | 4.79e-05 | +| loss | -0.0349 | +| n_updates | 32872 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000106 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.388 | +| time/ | | +| fps | 1418 | +| iterations | 4265 | +| time_elapsed | 6155 | +| total_timesteps | 8734720 | +| train/ | | +| approx_kl | 0.011959149 | +| clip_fraction | 0.291 | +| clip_range | 0.0728 | +| entropy_loss | -6.84 | +| explained_variance | 0.446 | +| learning_rate | 4.79e-05 | +| loss | -0.0251 | +| n_updates | 32876 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000144 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1418 | +| iterations | 4266 | +| time_elapsed | 6157 | +| total_timesteps | 8736768 | +| train/ | | +| approx_kl | 0.012993187 | +| clip_fraction | 0.338 | +| clip_range | 0.0728 | +| entropy_loss | -7.21 | +| explained_variance | 0.046 | +| learning_rate | 4.79e-05 | +| loss | -0.0364 | +| n_updates | 32880 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000159 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1418 | +| iterations | 4267 | +| time_elapsed | 6158 | +| total_timesteps | 8738816 | +| train/ | | +| approx_kl | 0.014028858 | +| clip_fraction | 0.321 | +| clip_range | 0.0728 | +| entropy_loss | -6.94 | +| explained_variance | 0.607 | +| learning_rate | 4.79e-05 | +| loss | -0.0338 | +| n_updates | 32884 | +| policy_gradient_loss | -0.0224 | +| value_loss | 6.7e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1418 | +| iterations | 4268 | +| time_elapsed | 6159 | +| total_timesteps | 8740864 | +| train/ | | +| approx_kl | 0.011167264 | +| clip_fraction | 0.324 | +| clip_range | 0.0728 | +| entropy_loss | -6.95 | +| explained_variance | 0.393 | +| learning_rate | 4.79e-05 | +| loss | -0.0282 | +| n_updates | 32888 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000208 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1418 | +| iterations | 4269 | +| time_elapsed | 6161 | +| total_timesteps | 8742912 | +| train/ | | +| approx_kl | 0.012329255 | +| clip_fraction | 0.346 | +| clip_range | 0.0728 | +| entropy_loss | -7.28 | +| explained_variance | -0.115 | +| learning_rate | 4.79e-05 | +| loss | -0.034 | +| n_updates | 32892 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000144 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1418 | +| iterations | 4270 | +| time_elapsed | 6162 | +| total_timesteps | 8744960 | +| train/ | | +| approx_kl | 0.012224357 | +| clip_fraction | 0.32 | +| clip_range | 0.0728 | +| entropy_loss | -7.32 | +| explained_variance | -0.0809 | +| learning_rate | 4.79e-05 | +| loss | -0.0315 | +| n_updates | 32896 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.00012 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1418 | +| iterations | 4271 | +| time_elapsed | 6164 | +| total_timesteps | 8747008 | +| train/ | | +| approx_kl | 0.010774067 | +| clip_fraction | 0.307 | +| clip_range | 0.0728 | +| entropy_loss | -7.06 | +| explained_variance | 0.455 | +| learning_rate | 4.79e-05 | +| loss | -0.0323 | +| n_updates | 32900 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000154 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1418 | +| iterations | 4272 | +| time_elapsed | 6165 | +| total_timesteps | 8749056 | +| train/ | | +| approx_kl | 0.011545666 | +| clip_fraction | 0.348 | +| clip_range | 0.0728 | +| entropy_loss | -7.13 | +| explained_variance | 0.537 | +| learning_rate | 4.79e-05 | +| loss | -0.0289 | +| n_updates | 32904 | +| policy_gradient_loss | -0.0218 | +| value_loss | 7.21e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1418 | +| iterations | 4273 | +| time_elapsed | 6167 | +| total_timesteps | 8751104 | +| train/ | | +| approx_kl | 0.011152096 | +| clip_fraction | 0.294 | +| clip_range | 0.0728 | +| entropy_loss | -7.01 | +| explained_variance | 0.41 | +| learning_rate | 4.79e-05 | +| loss | -0.0378 | +| n_updates | 32908 | +| policy_gradient_loss | -0.0193 | +| value_loss | 9.56e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1418 | +| iterations | 4274 | +| time_elapsed | 6168 | +| total_timesteps | 8753152 | +| train/ | | +| approx_kl | 0.012366818 | +| clip_fraction | 0.332 | +| clip_range | 0.0728 | +| entropy_loss | -7.12 | +| explained_variance | 0.184 | +| learning_rate | 4.79e-05 | +| loss | -0.0319 | +| n_updates | 32912 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.00024 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1418 | +| iterations | 4275 | +| time_elapsed | 6170 | +| total_timesteps | 8755200 | +| train/ | | +| approx_kl | 0.009132642 | +| clip_fraction | 0.275 | +| clip_range | 0.0728 | +| entropy_loss | -6.97 | +| explained_variance | 0.286 | +| learning_rate | 4.79e-05 | +| loss | -0.0321 | +| n_updates | 32916 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000348 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1418 | +| iterations | 4276 | +| time_elapsed | 6171 | +| total_timesteps | 8757248 | +| train/ | | +| approx_kl | 0.012087445 | +| clip_fraction | 0.347 | +| clip_range | 0.0728 | +| entropy_loss | -6.68 | +| explained_variance | 0.609 | +| learning_rate | 4.79e-05 | +| loss | -0.0423 | +| n_updates | 32920 | +| policy_gradient_loss | -0.0239 | +| value_loss | 8.01e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1418 | +| iterations | 4277 | +| time_elapsed | 6172 | +| total_timesteps | 8759296 | +| train/ | | +| approx_kl | 0.010801893 | +| clip_fraction | 0.318 | +| clip_range | 0.0728 | +| entropy_loss | -6.81 | +| explained_variance | 0.598 | +| learning_rate | 4.79e-05 | +| loss | -0.031 | +| n_updates | 32924 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000124 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1418 | +| iterations | 4278 | +| time_elapsed | 6174 | +| total_timesteps | 8761344 | +| train/ | | +| approx_kl | 0.009550959 | +| clip_fraction | 0.29 | +| clip_range | 0.0728 | +| entropy_loss | -7.19 | +| explained_variance | -0.00608 | +| learning_rate | 4.79e-05 | +| loss | -0.0255 | +| n_updates | 32928 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000131 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1418 | +| iterations | 4279 | +| time_elapsed | 6175 | +| total_timesteps | 8763392 | +| train/ | | +| approx_kl | 0.011827019 | +| clip_fraction | 0.298 | +| clip_range | 0.0728 | +| entropy_loss | -6.84 | +| explained_variance | 0.233 | +| learning_rate | 4.79e-05 | +| loss | -0.0299 | +| n_updates | 32932 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000227 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1418 | +| iterations | 4280 | +| time_elapsed | 6177 | +| total_timesteps | 8765440 | +| train/ | | +| approx_kl | 0.00955577 | +| clip_fraction | 0.302 | +| clip_range | 0.0728 | +| entropy_loss | -6.84 | +| explained_variance | 0.487 | +| learning_rate | 4.79e-05 | +| loss | -0.0326 | +| n_updates | 32936 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000159 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1418 | +| iterations | 4281 | +| time_elapsed | 6178 | +| total_timesteps | 8767488 | +| train/ | | +| approx_kl | 0.01075001 | +| clip_fraction | 0.321 | +| clip_range | 0.0728 | +| entropy_loss | -7.49 | +| explained_variance | 0.0318 | +| learning_rate | 4.79e-05 | +| loss | -0.0331 | +| n_updates | 32940 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000148 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1418 | +| iterations | 4282 | +| time_elapsed | 6180 | +| total_timesteps | 8769536 | +| train/ | | +| approx_kl | 0.009336701 | +| clip_fraction | 0.297 | +| clip_range | 0.0728 | +| entropy_loss | -7.27 | +| explained_variance | 0.276 | +| learning_rate | 4.79e-05 | +| loss | -0.0285 | +| n_updates | 32944 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1418 | +| iterations | 4283 | +| time_elapsed | 6181 | +| total_timesteps | 8771584 | +| train/ | | +| approx_kl | 0.009769023 | +| clip_fraction | 0.293 | +| clip_range | 0.0728 | +| entropy_loss | -7.32 | +| explained_variance | 0.0138 | +| learning_rate | 4.79e-05 | +| loss | -0.0268 | +| n_updates | 32948 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000347 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1419 | +| iterations | 4284 | +| time_elapsed | 6182 | +| total_timesteps | 8773632 | +| train/ | | +| approx_kl | 0.010753926 | +| clip_fraction | 0.344 | +| clip_range | 0.0728 | +| entropy_loss | -7.18 | +| explained_variance | 0.228 | +| learning_rate | 4.79e-05 | +| loss | -0.0398 | +| n_updates | 32952 | +| policy_gradient_loss | -0.023 | +| value_loss | 0.000144 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1418 | +| iterations | 4285 | +| time_elapsed | 6184 | +| total_timesteps | 8775680 | +| train/ | | +| approx_kl | 0.010602681 | +| clip_fraction | 0.321 | +| clip_range | 0.0728 | +| entropy_loss | -7.1 | +| explained_variance | 0.35 | +| learning_rate | 4.79e-05 | +| loss | -0.0336 | +| n_updates | 32956 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000182 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1418 | +| iterations | 4286 | +| time_elapsed | 6185 | +| total_timesteps | 8777728 | +| train/ | | +| approx_kl | 0.009098608 | +| clip_fraction | 0.272 | +| clip_range | 0.0728 | +| entropy_loss | -6.4 | +| explained_variance | 0.484 | +| learning_rate | 4.79e-05 | +| loss | -0.0316 | +| n_updates | 32960 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000361 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1418 | +| iterations | 4287 | +| time_elapsed | 6187 | +| total_timesteps | 8779776 | +| train/ | | +| approx_kl | 0.012006912 | +| clip_fraction | 0.363 | +| clip_range | 0.0728 | +| entropy_loss | -6.8 | +| explained_variance | 0.489 | +| learning_rate | 4.79e-05 | +| loss | -0.0362 | +| n_updates | 32964 | +| policy_gradient_loss | -0.0252 | +| value_loss | 8.1e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1419 | +| iterations | 4288 | +| time_elapsed | 6188 | +| total_timesteps | 8781824 | +| train/ | | +| approx_kl | 0.011656091 | +| clip_fraction | 0.329 | +| clip_range | 0.0728 | +| entropy_loss | -7.16 | +| explained_variance | 0.361 | +| learning_rate | 4.79e-05 | +| loss | -0.0323 | +| n_updates | 32968 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000101 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1419 | +| iterations | 4289 | +| time_elapsed | 6190 | +| total_timesteps | 8783872 | +| train/ | | +| approx_kl | 0.0114878295 | +| clip_fraction | 0.323 | +| clip_range | 0.0728 | +| entropy_loss | -7.45 | +| explained_variance | -0.167 | +| learning_rate | 4.79e-05 | +| loss | -0.0371 | +| n_updates | 32972 | +| policy_gradient_loss | -0.0216 | +| value_loss | 9.34e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1419 | +| iterations | 4290 | +| time_elapsed | 6191 | +| total_timesteps | 8785920 | +| train/ | | +| approx_kl | 0.009738054 | +| clip_fraction | 0.308 | +| clip_range | 0.0728 | +| entropy_loss | -6.6 | +| explained_variance | 0.588 | +| learning_rate | 4.79e-05 | +| loss | -0.0279 | +| n_updates | 32976 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000197 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1419 | +| iterations | 4291 | +| time_elapsed | 6192 | +| total_timesteps | 8787968 | +| train/ | | +| approx_kl | 0.012326523 | +| clip_fraction | 0.335 | +| clip_range | 0.0728 | +| entropy_loss | -7.06 | +| explained_variance | 0.248 | +| learning_rate | 4.79e-05 | +| loss | -0.0315 | +| n_updates | 32980 | +| policy_gradient_loss | -0.0207 | +| value_loss | 9.44e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1419 | +| iterations | 4292 | +| time_elapsed | 6194 | +| total_timesteps | 8790016 | +| train/ | | +| approx_kl | 0.011892755 | +| clip_fraction | 0.295 | +| clip_range | 0.0728 | +| entropy_loss | -7.16 | +| explained_variance | 0.187 | +| learning_rate | 4.79e-05 | +| loss | -0.0302 | +| n_updates | 32984 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000196 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1419 | +| iterations | 4293 | +| time_elapsed | 6195 | +| total_timesteps | 8792064 | +| train/ | | +| approx_kl | 0.008791129 | +| clip_fraction | 0.306 | +| clip_range | 0.0728 | +| entropy_loss | -7.14 | +| explained_variance | 0.357 | +| learning_rate | 4.79e-05 | +| loss | -0.0338 | +| n_updates | 32988 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000124 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1419 | +| iterations | 4294 | +| time_elapsed | 6197 | +| total_timesteps | 8794112 | +| train/ | | +| approx_kl | 0.010617941 | +| clip_fraction | 0.322 | +| clip_range | 0.0728 | +| entropy_loss | -7.13 | +| explained_variance | 0.401 | +| learning_rate | 4.79e-05 | +| loss | -0.0301 | +| n_updates | 32992 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000122 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1419 | +| iterations | 4295 | +| time_elapsed | 6198 | +| total_timesteps | 8796160 | +| train/ | | +| approx_kl | 0.010045519 | +| clip_fraction | 0.298 | +| clip_range | 0.0728 | +| entropy_loss | -7.14 | +| explained_variance | 0.428 | +| learning_rate | 4.79e-05 | +| loss | -0.0239 | +| n_updates | 32996 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000144 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1419 | +| iterations | 4296 | +| time_elapsed | 6200 | +| total_timesteps | 8798208 | +| train/ | | +| approx_kl | 0.011615722 | +| clip_fraction | 0.335 | +| clip_range | 0.0728 | +| entropy_loss | -7.25 | +| explained_variance | 0.157 | +| learning_rate | 4.79e-05 | +| loss | -0.0389 | +| n_updates | 33000 | +| policy_gradient_loss | -0.0229 | +| value_loss | 9.73e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1419 | +| iterations | 4297 | +| time_elapsed | 6201 | +| total_timesteps | 8800256 | +| train/ | | +| approx_kl | 0.012138286 | +| clip_fraction | 0.335 | +| clip_range | 0.0728 | +| entropy_loss | -7.17 | +| explained_variance | 0.397 | +| learning_rate | 4.79e-05 | +| loss | -0.0323 | +| n_updates | 33004 | +| policy_gradient_loss | -0.0212 | +| value_loss | 8.22e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1419 | +| iterations | 4298 | +| time_elapsed | 6203 | +| total_timesteps | 8802304 | +| train/ | | +| approx_kl | 0.011797547 | +| clip_fraction | 0.295 | +| clip_range | 0.0728 | +| entropy_loss | -7.43 | +| explained_variance | -0.0486 | +| learning_rate | 4.79e-05 | +| loss | -0.0326 | +| n_updates | 33008 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000117 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1419 | +| iterations | 4299 | +| time_elapsed | 6204 | +| total_timesteps | 8804352 | +| train/ | | +| approx_kl | 0.011181382 | +| clip_fraction | 0.297 | +| clip_range | 0.0728 | +| entropy_loss | -6.58 | +| explained_variance | 0.568 | +| learning_rate | 4.79e-05 | +| loss | -0.0232 | +| n_updates | 33012 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000187 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1419 | +| iterations | 4300 | +| time_elapsed | 6206 | +| total_timesteps | 8806400 | +| train/ | | +| approx_kl | 0.009903951 | +| clip_fraction | 0.31 | +| clip_range | 0.0728 | +| entropy_loss | -6.85 | +| explained_variance | 0.442 | +| learning_rate | 4.79e-05 | +| loss | -0.0262 | +| n_updates | 33016 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000136 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1419 | +| iterations | 4301 | +| time_elapsed | 6207 | +| total_timesteps | 8808448 | +| train/ | | +| approx_kl | 0.012680886 | +| clip_fraction | 0.32 | +| clip_range | 0.0728 | +| entropy_loss | -7.17 | +| explained_variance | 0.303 | +| learning_rate | 4.79e-05 | +| loss | -0.0311 | +| n_updates | 33020 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000128 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1419 | +| iterations | 4302 | +| time_elapsed | 6208 | +| total_timesteps | 8810496 | +| train/ | | +| approx_kl | 0.011521537 | +| clip_fraction | 0.344 | +| clip_range | 0.0728 | +| entropy_loss | -7.14 | +| explained_variance | 0.0524 | +| learning_rate | 4.79e-05 | +| loss | -0.0301 | +| n_updates | 33024 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000139 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1419 | +| iterations | 4303 | +| time_elapsed | 6210 | +| total_timesteps | 8812544 | +| train/ | | +| approx_kl | 0.009803582 | +| clip_fraction | 0.301 | +| clip_range | 0.0728 | +| entropy_loss | -6.83 | +| explained_variance | 0.387 | +| learning_rate | 4.79e-05 | +| loss | -0.0257 | +| n_updates | 33028 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000185 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1419 | +| iterations | 4304 | +| time_elapsed | 6211 | +| total_timesteps | 8814592 | +| train/ | | +| approx_kl | 0.0113971 | +| clip_fraction | 0.308 | +| clip_range | 0.0728 | +| entropy_loss | -7.17 | +| explained_variance | 0.143 | +| learning_rate | 4.79e-05 | +| loss | -0.0284 | +| n_updates | 33032 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000179 | +--------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1419 | +| iterations | 4305 | +| time_elapsed | 6213 | +| total_timesteps | 8816640 | +| train/ | | +| approx_kl | 0.0103055965 | +| clip_fraction | 0.326 | +| clip_range | 0.0728 | +| entropy_loss | -7.18 | +| explained_variance | 0.466 | +| learning_rate | 4.79e-05 | +| loss | -0.0387 | +| n_updates | 33036 | +| policy_gradient_loss | -0.0233 | +| value_loss | 7.17e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1419 | +| iterations | 4306 | +| time_elapsed | 6214 | +| total_timesteps | 8818688 | +| train/ | | +| approx_kl | 0.011486102 | +| clip_fraction | 0.299 | +| clip_range | 0.0728 | +| entropy_loss | -7.49 | +| explained_variance | -0.029 | +| learning_rate | 4.79e-05 | +| loss | -0.0325 | +| n_updates | 33040 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000235 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1419 | +| iterations | 4307 | +| time_elapsed | 6215 | +| total_timesteps | 8820736 | +| train/ | | +| approx_kl | 0.011417378 | +| clip_fraction | 0.325 | +| clip_range | 0.0728 | +| entropy_loss | -7.49 | +| explained_variance | -0.184 | +| learning_rate | 4.79e-05 | +| loss | -0.0348 | +| n_updates | 33044 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000125 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1419 | +| iterations | 4308 | +| time_elapsed | 6217 | +| total_timesteps | 8822784 | +| train/ | | +| approx_kl | 0.011244708 | +| clip_fraction | 0.311 | +| clip_range | 0.0728 | +| entropy_loss | -7.44 | +| explained_variance | -0.186 | +| learning_rate | 4.79e-05 | +| loss | -0.0359 | +| n_updates | 33048 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000101 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1419 | +| iterations | 4309 | +| time_elapsed | 6218 | +| total_timesteps | 8824832 | +| train/ | | +| approx_kl | 0.0098090535 | +| clip_fraction | 0.279 | +| clip_range | 0.0728 | +| entropy_loss | -6.89 | +| explained_variance | 0.452 | +| learning_rate | 4.79e-05 | +| loss | -0.0281 | +| n_updates | 33052 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000263 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1419 | +| iterations | 4310 | +| time_elapsed | 6220 | +| total_timesteps | 8826880 | +| train/ | | +| approx_kl | 0.009386588 | +| clip_fraction | 0.309 | +| clip_range | 0.0728 | +| entropy_loss | -6.67 | +| explained_variance | 0.576 | +| learning_rate | 4.79e-05 | +| loss | -0.0271 | +| n_updates | 33056 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000145 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1419 | +| iterations | 4311 | +| time_elapsed | 6221 | +| total_timesteps | 8828928 | +| train/ | | +| approx_kl | 0.012118716 | +| clip_fraction | 0.321 | +| clip_range | 0.0728 | +| entropy_loss | -6.98 | +| explained_variance | 0.337 | +| learning_rate | 4.79e-05 | +| loss | -0.0352 | +| n_updates | 33060 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000119 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1419 | +| iterations | 4312 | +| time_elapsed | 6223 | +| total_timesteps | 8830976 | +| train/ | | +| approx_kl | 0.0134750325 | +| clip_fraction | 0.333 | +| clip_range | 0.0728 | +| entropy_loss | -6.96 | +| explained_variance | 0.574 | +| learning_rate | 4.79e-05 | +| loss | -0.0328 | +| n_updates | 33064 | +| policy_gradient_loss | -0.0208 | +| value_loss | 9.34e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1419 | +| iterations | 4313 | +| time_elapsed | 6224 | +| total_timesteps | 8833024 | +| train/ | | +| approx_kl | 0.012205703 | +| clip_fraction | 0.307 | +| clip_range | 0.0728 | +| entropy_loss | -7.37 | +| explained_variance | -0.0954 | +| learning_rate | 4.79e-05 | +| loss | -0.0292 | +| n_updates | 33068 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000113 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1419 | +| iterations | 4314 | +| time_elapsed | 6225 | +| total_timesteps | 8835072 | +| train/ | | +| approx_kl | 0.010535995 | +| clip_fraction | 0.297 | +| clip_range | 0.0728 | +| entropy_loss | -7.31 | +| explained_variance | 0.297 | +| learning_rate | 4.79e-05 | +| loss | -0.0281 | +| n_updates | 33072 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000162 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1419 | +| iterations | 4315 | +| time_elapsed | 6227 | +| total_timesteps | 8837120 | +| train/ | | +| approx_kl | 0.012187369 | +| clip_fraction | 0.329 | +| clip_range | 0.0728 | +| entropy_loss | -7.07 | +| explained_variance | 0.301 | +| learning_rate | 4.79e-05 | +| loss | -0.0346 | +| n_updates | 33076 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000208 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1419 | +| iterations | 4316 | +| time_elapsed | 6228 | +| total_timesteps | 8839168 | +| train/ | | +| approx_kl | 0.012822181 | +| clip_fraction | 0.322 | +| clip_range | 0.0728 | +| entropy_loss | -7.12 | +| explained_variance | 0.392 | +| learning_rate | 4.79e-05 | +| loss | -0.0326 | +| n_updates | 33080 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.00018 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1419 | +| iterations | 4317 | +| time_elapsed | 6230 | +| total_timesteps | 8841216 | +| train/ | | +| approx_kl | 0.014826628 | +| clip_fraction | 0.336 | +| clip_range | 0.0728 | +| entropy_loss | -7.11 | +| explained_variance | -0.0185 | +| learning_rate | 4.79e-05 | +| loss | -0.032 | +| n_updates | 33084 | +| policy_gradient_loss | -0.0206 | +| value_loss | 8.12e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1419 | +| iterations | 4318 | +| time_elapsed | 6231 | +| total_timesteps | 8843264 | +| train/ | | +| approx_kl | 0.012108242 | +| clip_fraction | 0.316 | +| clip_range | 0.0728 | +| entropy_loss | -7.01 | +| explained_variance | 0.283 | +| learning_rate | 4.79e-05 | +| loss | -0.0339 | +| n_updates | 33088 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000167 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1419 | +| iterations | 4319 | +| time_elapsed | 6233 | +| total_timesteps | 8845312 | +| train/ | | +| approx_kl | 0.011821577 | +| clip_fraction | 0.325 | +| clip_range | 0.0728 | +| entropy_loss | -6.79 | +| explained_variance | 0.376 | +| learning_rate | 4.79e-05 | +| loss | -0.0277 | +| n_updates | 33092 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.00023 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1419 | +| iterations | 4320 | +| time_elapsed | 6234 | +| total_timesteps | 8847360 | +| train/ | | +| approx_kl | 0.0105125625 | +| clip_fraction | 0.317 | +| clip_range | 0.0728 | +| entropy_loss | -7.4 | +| explained_variance | -0.0987 | +| learning_rate | 4.79e-05 | +| loss | -0.0344 | +| n_updates | 33096 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000172 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1419 | +| iterations | 4321 | +| time_elapsed | 6236 | +| total_timesteps | 8849408 | +| train/ | | +| approx_kl | 0.012205648 | +| clip_fraction | 0.311 | +| clip_range | 0.0728 | +| entropy_loss | -7.38 | +| explained_variance | -0.069 | +| learning_rate | 4.79e-05 | +| loss | -0.0378 | +| n_updates | 33100 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000145 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1419 | +| iterations | 4322 | +| time_elapsed | 6237 | +| total_timesteps | 8851456 | +| train/ | | +| approx_kl | 0.011141114 | +| clip_fraction | 0.32 | +| clip_range | 0.0728 | +| entropy_loss | -7.03 | +| explained_variance | 0.59 | +| learning_rate | 4.79e-05 | +| loss | -0.0299 | +| n_updates | 33104 | +| policy_gradient_loss | -0.0203 | +| value_loss | 5.23e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1419 | +| iterations | 4323 | +| time_elapsed | 6238 | +| total_timesteps | 8853504 | +| train/ | | +| approx_kl | 0.01113068 | +| clip_fraction | 0.324 | +| clip_range | 0.0728 | +| entropy_loss | -7.07 | +| explained_variance | 0.368 | +| learning_rate | 4.79e-05 | +| loss | -0.0328 | +| n_updates | 33108 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000104 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1419 | +| iterations | 4324 | +| time_elapsed | 6240 | +| total_timesteps | 8855552 | +| train/ | | +| approx_kl | 0.010376964 | +| clip_fraction | 0.305 | +| clip_range | 0.0728 | +| entropy_loss | -7.22 | +| explained_variance | 0.264 | +| learning_rate | 4.79e-05 | +| loss | -0.0312 | +| n_updates | 33112 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000195 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1419 | +| iterations | 4325 | +| time_elapsed | 6241 | +| total_timesteps | 8857600 | +| train/ | | +| approx_kl | 0.013773968 | +| clip_fraction | 0.301 | +| clip_range | 0.0728 | +| entropy_loss | -6.85 | +| explained_variance | 0.446 | +| learning_rate | 4.79e-05 | +| loss | -0.0322 | +| n_updates | 33116 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.00016 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1419 | +| iterations | 4326 | +| time_elapsed | 6243 | +| total_timesteps | 8859648 | +| train/ | | +| approx_kl | 0.013649292 | +| clip_fraction | 0.319 | +| clip_range | 0.0728 | +| entropy_loss | -7.2 | +| explained_variance | -0.259 | +| learning_rate | 4.79e-05 | +| loss | -0.039 | +| n_updates | 33120 | +| policy_gradient_loss | -0.02 | +| value_loss | 9.81e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1419 | +| iterations | 4327 | +| time_elapsed | 6244 | +| total_timesteps | 8861696 | +| train/ | | +| approx_kl | 0.011447433 | +| clip_fraction | 0.293 | +| clip_range | 0.0728 | +| entropy_loss | -7.25 | +| explained_variance | 0.267 | +| learning_rate | 4.79e-05 | +| loss | -0.0268 | +| n_updates | 33124 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000148 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1419 | +| iterations | 4328 | +| time_elapsed | 6245 | +| total_timesteps | 8863744 | +| train/ | | +| approx_kl | 0.011733936 | +| clip_fraction | 0.3 | +| clip_range | 0.0728 | +| entropy_loss | -7.12 | +| explained_variance | 0.329 | +| learning_rate | 4.79e-05 | +| loss | -0.0337 | +| n_updates | 33128 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000119 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1419 | +| iterations | 4329 | +| time_elapsed | 6247 | +| total_timesteps | 8865792 | +| train/ | | +| approx_kl | 0.012484219 | +| clip_fraction | 0.285 | +| clip_range | 0.0728 | +| entropy_loss | -7.03 | +| explained_variance | 0.502 | +| learning_rate | 4.79e-05 | +| loss | -0.0286 | +| n_updates | 33132 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000146 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1419 | +| iterations | 4330 | +| time_elapsed | 6248 | +| total_timesteps | 8867840 | +| train/ | | +| approx_kl | 0.0138592245 | +| clip_fraction | 0.313 | +| clip_range | 0.0728 | +| entropy_loss | -7 | +| explained_variance | 0.443 | +| learning_rate | 4.79e-05 | +| loss | -0.0309 | +| n_updates | 33136 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000146 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1419 | +| iterations | 4331 | +| time_elapsed | 6250 | +| total_timesteps | 8869888 | +| train/ | | +| approx_kl | 0.012292286 | +| clip_fraction | 0.296 | +| clip_range | 0.0728 | +| entropy_loss | -6.65 | +| explained_variance | 0.563 | +| learning_rate | 4.79e-05 | +| loss | -0.0288 | +| n_updates | 33140 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000196 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1419 | +| iterations | 4332 | +| time_elapsed | 6251 | +| total_timesteps | 8871936 | +| train/ | | +| approx_kl | 0.011102625 | +| clip_fraction | 0.295 | +| clip_range | 0.0728 | +| entropy_loss | -6.85 | +| explained_variance | -0.0552 | +| learning_rate | 4.79e-05 | +| loss | -0.0285 | +| n_updates | 33144 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000283 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1419 | +| iterations | 4333 | +| time_elapsed | 6252 | +| total_timesteps | 8873984 | +| train/ | | +| approx_kl | 0.012589009 | +| clip_fraction | 0.329 | +| clip_range | 0.0728 | +| entropy_loss | -7.09 | +| explained_variance | 0.0737 | +| learning_rate | 4.79e-05 | +| loss | -0.0337 | +| n_updates | 33148 | +| policy_gradient_loss | -0.0226 | +| value_loss | 0.000147 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1419 | +| iterations | 4334 | +| time_elapsed | 6254 | +| total_timesteps | 8876032 | +| train/ | | +| approx_kl | 0.010033343 | +| clip_fraction | 0.321 | +| clip_range | 0.0728 | +| entropy_loss | -7.38 | +| explained_variance | -0.243 | +| learning_rate | 4.79e-05 | +| loss | -0.0287 | +| n_updates | 33152 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000115 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1419 | +| iterations | 4335 | +| time_elapsed | 6255 | +| total_timesteps | 8878080 | +| train/ | | +| approx_kl | 0.011511854 | +| clip_fraction | 0.334 | +| clip_range | 0.0728 | +| entropy_loss | -7.05 | +| explained_variance | 0.165 | +| learning_rate | 4.79e-05 | +| loss | -0.0327 | +| n_updates | 33156 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.0003 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1419 | +| iterations | 4336 | +| time_elapsed | 6257 | +| total_timesteps | 8880128 | +| train/ | | +| approx_kl | 0.010228856 | +| clip_fraction | 0.313 | +| clip_range | 0.0728 | +| entropy_loss | -7.39 | +| explained_variance | -0.0951 | +| learning_rate | 4.79e-05 | +| loss | -0.0301 | +| n_updates | 33160 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.00027 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1419 | +| iterations | 4337 | +| time_elapsed | 6258 | +| total_timesteps | 8882176 | +| train/ | | +| approx_kl | 0.010100778 | +| clip_fraction | 0.322 | +| clip_range | 0.0728 | +| entropy_loss | -7.19 | +| explained_variance | 0.023 | +| learning_rate | 4.79e-05 | +| loss | -0.0356 | +| n_updates | 33164 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000283 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1419 | +| iterations | 4338 | +| time_elapsed | 6260 | +| total_timesteps | 8884224 | +| train/ | | +| approx_kl | 0.012199022 | +| clip_fraction | 0.351 | +| clip_range | 0.0728 | +| entropy_loss | -7.3 | +| explained_variance | 0.2 | +| learning_rate | 4.79e-05 | +| loss | -0.0347 | +| n_updates | 33168 | +| policy_gradient_loss | -0.0238 | +| value_loss | 0.000131 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1419 | +| iterations | 4339 | +| time_elapsed | 6261 | +| total_timesteps | 8886272 | +| train/ | | +| approx_kl | 0.012082316 | +| clip_fraction | 0.32 | +| clip_range | 0.0728 | +| entropy_loss | -6.62 | +| explained_variance | 0.224 | +| learning_rate | 4.79e-05 | +| loss | -0.0355 | +| n_updates | 33172 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000347 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1419 | +| iterations | 4340 | +| time_elapsed | 6263 | +| total_timesteps | 8888320 | +| train/ | | +| approx_kl | 0.01133617 | +| clip_fraction | 0.338 | +| clip_range | 0.0728 | +| entropy_loss | -7.13 | +| explained_variance | -0.0639 | +| learning_rate | 4.79e-05 | +| loss | -0.0379 | +| n_updates | 33176 | +| policy_gradient_loss | -0.0239 | +| value_loss | 0.000106 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1419 | +| iterations | 4341 | +| time_elapsed | 6264 | +| total_timesteps | 8890368 | +| train/ | | +| approx_kl | 0.010725535 | +| clip_fraction | 0.312 | +| clip_range | 0.0728 | +| entropy_loss | -6.89 | +| explained_variance | 0.433 | +| learning_rate | 4.79e-05 | +| loss | -0.0317 | +| n_updates | 33180 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000102 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1419 | +| iterations | 4342 | +| time_elapsed | 6265 | +| total_timesteps | 8892416 | +| train/ | | +| approx_kl | 0.009394504 | +| clip_fraction | 0.307 | +| clip_range | 0.0728 | +| entropy_loss | -7.29 | +| explained_variance | 0.358 | +| learning_rate | 4.79e-05 | +| loss | -0.0286 | +| n_updates | 33184 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000113 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.384 | +| time/ | | +| fps | 1419 | +| iterations | 4343 | +| time_elapsed | 6267 | +| total_timesteps | 8894464 | +| train/ | | +| approx_kl | 0.009193551 | +| clip_fraction | 0.3 | +| clip_range | 0.0728 | +| entropy_loss | -6.82 | +| explained_variance | 0.354 | +| learning_rate | 4.79e-05 | +| loss | -0.0305 | +| n_updates | 33188 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000196 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.384 | +| time/ | | +| fps | 1419 | +| iterations | 4344 | +| time_elapsed | 6268 | +| total_timesteps | 8896512 | +| train/ | | +| approx_kl | 0.012266383 | +| clip_fraction | 0.332 | +| clip_range | 0.0728 | +| entropy_loss | -6.98 | +| explained_variance | 0.466 | +| learning_rate | 4.79e-05 | +| loss | -0.0385 | +| n_updates | 33192 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000124 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.384 | +| time/ | | +| fps | 1419 | +| iterations | 4345 | +| time_elapsed | 6270 | +| total_timesteps | 8898560 | +| train/ | | +| approx_kl | 0.011902885 | +| clip_fraction | 0.336 | +| clip_range | 0.0728 | +| entropy_loss | -6.95 | +| explained_variance | 0.504 | +| learning_rate | 4.79e-05 | +| loss | -0.0319 | +| n_updates | 33196 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000149 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1419 | +| iterations | 4346 | +| time_elapsed | 6271 | +| total_timesteps | 8900608 | +| train/ | | +| approx_kl | 0.012176249 | +| clip_fraction | 0.325 | +| clip_range | 0.0728 | +| entropy_loss | -7.31 | +| explained_variance | -0.239 | +| learning_rate | 4.79e-05 | +| loss | -0.0357 | +| n_updates | 33200 | +| policy_gradient_loss | -0.022 | +| value_loss | 0.000133 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1419 | +| iterations | 4347 | +| time_elapsed | 6273 | +| total_timesteps | 8902656 | +| train/ | | +| approx_kl | 0.009269198 | +| clip_fraction | 0.291 | +| clip_range | 0.0728 | +| entropy_loss | -7.19 | +| explained_variance | 0.16 | +| learning_rate | 4.79e-05 | +| loss | -0.0297 | +| n_updates | 33204 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000192 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1419 | +| iterations | 4348 | +| time_elapsed | 6274 | +| total_timesteps | 8904704 | +| train/ | | +| approx_kl | 0.01066244 | +| clip_fraction | 0.341 | +| clip_range | 0.0728 | +| entropy_loss | -7.33 | +| explained_variance | -0.183 | +| learning_rate | 4.79e-05 | +| loss | -0.0346 | +| n_updates | 33208 | +| policy_gradient_loss | -0.0198 | +| value_loss | 9.78e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1419 | +| iterations | 4349 | +| time_elapsed | 6275 | +| total_timesteps | 8906752 | +| train/ | | +| approx_kl | 0.010604269 | +| clip_fraction | 0.303 | +| clip_range | 0.0728 | +| entropy_loss | -7.28 | +| explained_variance | -0.0129 | +| learning_rate | 4.79e-05 | +| loss | -0.0277 | +| n_updates | 33212 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000142 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1419 | +| iterations | 4350 | +| time_elapsed | 6277 | +| total_timesteps | 8908800 | +| train/ | | +| approx_kl | 0.010838395 | +| clip_fraction | 0.32 | +| clip_range | 0.0728 | +| entropy_loss | -6.75 | +| explained_variance | 0.263 | +| learning_rate | 4.79e-05 | +| loss | -0.0223 | +| n_updates | 33216 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000257 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1419 | +| iterations | 4351 | +| time_elapsed | 6278 | +| total_timesteps | 8910848 | +| train/ | | +| approx_kl | 0.011513658 | +| clip_fraction | 0.326 | +| clip_range | 0.0728 | +| entropy_loss | -6.9 | +| explained_variance | 0.474 | +| learning_rate | 4.79e-05 | +| loss | -0.0355 | +| n_updates | 33220 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000128 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1419 | +| iterations | 4352 | +| time_elapsed | 6280 | +| total_timesteps | 8912896 | +| train/ | | +| approx_kl | 0.010478312 | +| clip_fraction | 0.297 | +| clip_range | 0.0728 | +| entropy_loss | -6.88 | +| explained_variance | 0.61 | +| learning_rate | 4.79e-05 | +| loss | -0.0365 | +| n_updates | 33224 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000125 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1419 | +| iterations | 4353 | +| time_elapsed | 6281 | +| total_timesteps | 8914944 | +| train/ | | +| approx_kl | 0.010059205 | +| clip_fraction | 0.294 | +| clip_range | 0.0728 | +| entropy_loss | -7.19 | +| explained_variance | 0.34 | +| learning_rate | 4.79e-05 | +| loss | -0.0279 | +| n_updates | 33228 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000134 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1419 | +| iterations | 4354 | +| time_elapsed | 6283 | +| total_timesteps | 8916992 | +| train/ | | +| approx_kl | 0.009997779 | +| clip_fraction | 0.3 | +| clip_range | 0.0728 | +| entropy_loss | -7.11 | +| explained_variance | 0.209 | +| learning_rate | 4.79e-05 | +| loss | -0.0305 | +| n_updates | 33232 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000231 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1419 | +| iterations | 4355 | +| time_elapsed | 6284 | +| total_timesteps | 8919040 | +| train/ | | +| approx_kl | 0.010352964 | +| clip_fraction | 0.291 | +| clip_range | 0.0728 | +| entropy_loss | -6.67 | +| explained_variance | 0.48 | +| learning_rate | 4.79e-05 | +| loss | -0.0252 | +| n_updates | 33236 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000255 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1419 | +| iterations | 4356 | +| time_elapsed | 6285 | +| total_timesteps | 8921088 | +| train/ | | +| approx_kl | 0.013595581 | +| clip_fraction | 0.333 | +| clip_range | 0.0728 | +| entropy_loss | -7.16 | +| explained_variance | -0.161 | +| learning_rate | 4.79e-05 | +| loss | -0.0337 | +| n_updates | 33240 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000151 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1419 | +| iterations | 4357 | +| time_elapsed | 6287 | +| total_timesteps | 8923136 | +| train/ | | +| approx_kl | 0.012315003 | +| clip_fraction | 0.32 | +| clip_range | 0.0728 | +| entropy_loss | -7.34 | +| explained_variance | 0.218 | +| learning_rate | 4.79e-05 | +| loss | -0.0339 | +| n_updates | 33244 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000166 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1419 | +| iterations | 4358 | +| time_elapsed | 6288 | +| total_timesteps | 8925184 | +| train/ | | +| approx_kl | 0.009054772 | +| clip_fraction | 0.297 | +| clip_range | 0.0728 | +| entropy_loss | -7.14 | +| explained_variance | 0.284 | +| learning_rate | 4.79e-05 | +| loss | -0.0271 | +| n_updates | 33248 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.00018 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1419 | +| iterations | 4359 | +| time_elapsed | 6290 | +| total_timesteps | 8927232 | +| train/ | | +| approx_kl | 0.009611683 | +| clip_fraction | 0.302 | +| clip_range | 0.0728 | +| entropy_loss | -6.92 | +| explained_variance | 0.441 | +| learning_rate | 4.79e-05 | +| loss | -0.0321 | +| n_updates | 33252 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000184 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1419 | +| iterations | 4360 | +| time_elapsed | 6291 | +| total_timesteps | 8929280 | +| train/ | | +| approx_kl | 0.011351643 | +| clip_fraction | 0.3 | +| clip_range | 0.0728 | +| entropy_loss | -7.21 | +| explained_variance | 0.187 | +| learning_rate | 4.79e-05 | +| loss | -0.0316 | +| n_updates | 33256 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000311 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1419 | +| iterations | 4361 | +| time_elapsed | 6292 | +| total_timesteps | 8931328 | +| train/ | | +| approx_kl | 0.010422006 | +| clip_fraction | 0.318 | +| clip_range | 0.0728 | +| entropy_loss | -6.93 | +| explained_variance | 0.555 | +| learning_rate | 4.79e-05 | +| loss | -0.0382 | +| n_updates | 33260 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000107 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1419 | +| iterations | 4362 | +| time_elapsed | 6294 | +| total_timesteps | 8933376 | +| train/ | | +| approx_kl | 0.012208602 | +| clip_fraction | 0.345 | +| clip_range | 0.0728 | +| entropy_loss | -7.04 | +| explained_variance | 0.503 | +| learning_rate | 4.79e-05 | +| loss | -0.0419 | +| n_updates | 33264 | +| policy_gradient_loss | -0.0232 | +| value_loss | 7.57e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1419 | +| iterations | 4363 | +| time_elapsed | 6295 | +| total_timesteps | 8935424 | +| train/ | | +| approx_kl | 0.011225723 | +| clip_fraction | 0.302 | +| clip_range | 0.0728 | +| entropy_loss | -7.22 | +| explained_variance | 0.359 | +| learning_rate | 4.79e-05 | +| loss | -0.0327 | +| n_updates | 33268 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000118 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1419 | +| iterations | 4364 | +| time_elapsed | 6297 | +| total_timesteps | 8937472 | +| train/ | | +| approx_kl | 0.012268489 | +| clip_fraction | 0.332 | +| clip_range | 0.0728 | +| entropy_loss | -6.92 | +| explained_variance | 0.53 | +| learning_rate | 4.79e-05 | +| loss | -0.0274 | +| n_updates | 33272 | +| policy_gradient_loss | -0.0201 | +| value_loss | 7.72e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1419 | +| iterations | 4365 | +| time_elapsed | 6298 | +| total_timesteps | 8939520 | +| train/ | | +| approx_kl | 0.0123382155 | +| clip_fraction | 0.33 | +| clip_range | 0.0728 | +| entropy_loss | -6.68 | +| explained_variance | 0.64 | +| learning_rate | 4.79e-05 | +| loss | -0.0331 | +| n_updates | 33276 | +| policy_gradient_loss | -0.0211 | +| value_loss | 7.39e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1419 | +| iterations | 4366 | +| time_elapsed | 6300 | +| total_timesteps | 8941568 | +| train/ | | +| approx_kl | 0.012524054 | +| clip_fraction | 0.335 | +| clip_range | 0.0728 | +| entropy_loss | -7.31 | +| explained_variance | -0.101 | +| learning_rate | 4.79e-05 | +| loss | -0.0325 | +| n_updates | 33280 | +| policy_gradient_loss | -0.021 | +| value_loss | 5.32e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1419 | +| iterations | 4367 | +| time_elapsed | 6301 | +| total_timesteps | 8943616 | +| train/ | | +| approx_kl | 0.011747824 | +| clip_fraction | 0.304 | +| clip_range | 0.0728 | +| entropy_loss | -6.94 | +| explained_variance | 0.373 | +| learning_rate | 4.79e-05 | +| loss | -0.0297 | +| n_updates | 33284 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000167 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1419 | +| iterations | 4368 | +| time_elapsed | 6302 | +| total_timesteps | 8945664 | +| train/ | | +| approx_kl | 0.011943032 | +| clip_fraction | 0.303 | +| clip_range | 0.0728 | +| entropy_loss | -7.1 | +| explained_variance | 0.361 | +| learning_rate | 4.79e-05 | +| loss | -0.0276 | +| n_updates | 33288 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000112 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1419 | +| iterations | 4369 | +| time_elapsed | 6304 | +| total_timesteps | 8947712 | +| train/ | | +| approx_kl | 0.010502039 | +| clip_fraction | 0.305 | +| clip_range | 0.0728 | +| entropy_loss | -7.47 | +| explained_variance | -0.0189 | +| learning_rate | 4.79e-05 | +| loss | -0.0293 | +| n_updates | 33292 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000172 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1419 | +| iterations | 4370 | +| time_elapsed | 6305 | +| total_timesteps | 8949760 | +| train/ | | +| approx_kl | 0.0117858965 | +| clip_fraction | 0.31 | +| clip_range | 0.0728 | +| entropy_loss | -7.1 | +| explained_variance | 0.326 | +| learning_rate | 4.79e-05 | +| loss | -0.0292 | +| n_updates | 33296 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000186 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1419 | +| iterations | 4371 | +| time_elapsed | 6307 | +| total_timesteps | 8951808 | +| train/ | | +| approx_kl | 0.011960918 | +| clip_fraction | 0.317 | +| clip_range | 0.0728 | +| entropy_loss | -7.24 | +| explained_variance | 0.261 | +| learning_rate | 4.79e-05 | +| loss | -0.0328 | +| n_updates | 33300 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000173 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1419 | +| iterations | 4372 | +| time_elapsed | 6308 | +| total_timesteps | 8953856 | +| train/ | | +| approx_kl | 0.011366764 | +| clip_fraction | 0.311 | +| clip_range | 0.0728 | +| entropy_loss | -7.21 | +| explained_variance | -0.0522 | +| learning_rate | 4.79e-05 | +| loss | -0.0315 | +| n_updates | 33304 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000175 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1419 | +| iterations | 4373 | +| time_elapsed | 6310 | +| total_timesteps | 8955904 | +| train/ | | +| approx_kl | 0.013302473 | +| clip_fraction | 0.304 | +| clip_range | 0.0728 | +| entropy_loss | -6.56 | +| explained_variance | 0.598 | +| learning_rate | 4.79e-05 | +| loss | -0.0342 | +| n_updates | 33308 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.00015 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1419 | +| iterations | 4374 | +| time_elapsed | 6311 | +| total_timesteps | 8957952 | +| train/ | | +| approx_kl | 0.011299733 | +| clip_fraction | 0.322 | +| clip_range | 0.0728 | +| entropy_loss | -7.18 | +| explained_variance | 0.0181 | +| learning_rate | 4.79e-05 | +| loss | -0.0374 | +| n_updates | 33312 | +| policy_gradient_loss | -0.0218 | +| value_loss | 9.39e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1419 | +| iterations | 4375 | +| time_elapsed | 6313 | +| total_timesteps | 8960000 | +| train/ | | +| approx_kl | 0.009960792 | +| clip_fraction | 0.323 | +| clip_range | 0.0728 | +| entropy_loss | -7.07 | +| explained_variance | 0.382 | +| learning_rate | 4.79e-05 | +| loss | -0.0356 | +| n_updates | 33316 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000184 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1419 | +| iterations | 4376 | +| time_elapsed | 6314 | +| total_timesteps | 8962048 | +| train/ | | +| approx_kl | 0.012208439 | +| clip_fraction | 0.317 | +| clip_range | 0.0728 | +| entropy_loss | -6.84 | +| explained_variance | 0.623 | +| learning_rate | 4.79e-05 | +| loss | -0.0345 | +| n_updates | 33320 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000118 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1419 | +| iterations | 4377 | +| time_elapsed | 6315 | +| total_timesteps | 8964096 | +| train/ | | +| approx_kl | 0.013843795 | +| clip_fraction | 0.311 | +| clip_range | 0.0728 | +| entropy_loss | -7.21 | +| explained_variance | 0.32 | +| learning_rate | 4.79e-05 | +| loss | -0.0337 | +| n_updates | 33324 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.00015 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1419 | +| iterations | 4378 | +| time_elapsed | 6317 | +| total_timesteps | 8966144 | +| train/ | | +| approx_kl | 0.009933415 | +| clip_fraction | 0.304 | +| clip_range | 0.0728 | +| entropy_loss | -7.46 | +| explained_variance | -0.0688 | +| learning_rate | 4.79e-05 | +| loss | -0.0253 | +| n_updates | 33328 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000396 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1419 | +| iterations | 4379 | +| time_elapsed | 6318 | +| total_timesteps | 8968192 | +| train/ | | +| approx_kl | 0.010170501 | +| clip_fraction | 0.309 | +| clip_range | 0.0728 | +| entropy_loss | -6.99 | +| explained_variance | 0.272 | +| learning_rate | 4.79e-05 | +| loss | -0.0309 | +| n_updates | 33332 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000196 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1419 | +| iterations | 4380 | +| time_elapsed | 6320 | +| total_timesteps | 8970240 | +| train/ | | +| approx_kl | 0.01133492 | +| clip_fraction | 0.313 | +| clip_range | 0.0728 | +| entropy_loss | -6.8 | +| explained_variance | 0.403 | +| learning_rate | 4.79e-05 | +| loss | -0.0299 | +| n_updates | 33336 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000144 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.385 | +| time/ | | +| fps | 1419 | +| iterations | 4381 | +| time_elapsed | 6321 | +| total_timesteps | 8972288 | +| train/ | | +| approx_kl | 0.010559341 | +| clip_fraction | 0.315 | +| clip_range | 0.0728 | +| entropy_loss | -7.13 | +| explained_variance | 0.237 | +| learning_rate | 4.79e-05 | +| loss | -0.0282 | +| n_updates | 33340 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000128 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.389 | +| time/ | | +| fps | 1419 | +| iterations | 4382 | +| time_elapsed | 6323 | +| total_timesteps | 8974336 | +| train/ | | +| approx_kl | 0.01258699 | +| clip_fraction | 0.323 | +| clip_range | 0.0728 | +| entropy_loss | -7.16 | +| explained_variance | 0.281 | +| learning_rate | 4.79e-05 | +| loss | -0.0361 | +| n_updates | 33344 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000209 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.391 | +| time/ | | +| fps | 1419 | +| iterations | 4383 | +| time_elapsed | 6324 | +| total_timesteps | 8976384 | +| train/ | | +| approx_kl | 0.010240205 | +| clip_fraction | 0.318 | +| clip_range | 0.0728 | +| entropy_loss | -7.23 | +| explained_variance | 0.209 | +| learning_rate | 4.79e-05 | +| loss | -0.0309 | +| n_updates | 33348 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000201 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.387 | +| time/ | | +| fps | 1419 | +| iterations | 4384 | +| time_elapsed | 6326 | +| total_timesteps | 8978432 | +| train/ | | +| approx_kl | 0.012709654 | +| clip_fraction | 0.323 | +| clip_range | 0.0728 | +| entropy_loss | -7.09 | +| explained_variance | -0.298 | +| learning_rate | 4.79e-05 | +| loss | -0.0322 | +| n_updates | 33352 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000186 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1419 | +| iterations | 4385 | +| time_elapsed | 6327 | +| total_timesteps | 8980480 | +| train/ | | +| approx_kl | 0.0118989255 | +| clip_fraction | 0.329 | +| clip_range | 0.0728 | +| entropy_loss | -6.61 | +| explained_variance | 0.321 | +| learning_rate | 4.79e-05 | +| loss | -0.0281 | +| n_updates | 33356 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000197 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1419 | +| iterations | 4386 | +| time_elapsed | 6328 | +| total_timesteps | 8982528 | +| train/ | | +| approx_kl | 0.0126286885 | +| clip_fraction | 0.344 | +| clip_range | 0.0728 | +| entropy_loss | -6.98 | +| explained_variance | 0.527 | +| learning_rate | 4.79e-05 | +| loss | -0.0388 | +| n_updates | 33360 | +| policy_gradient_loss | -0.0235 | +| value_loss | 0.000113 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1419 | +| iterations | 4387 | +| time_elapsed | 6330 | +| total_timesteps | 8984576 | +| train/ | | +| approx_kl | 0.010895081 | +| clip_fraction | 0.321 | +| clip_range | 0.0728 | +| entropy_loss | -7.19 | +| explained_variance | 0.34 | +| learning_rate | 4.79e-05 | +| loss | -0.0375 | +| n_updates | 33364 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000104 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1419 | +| iterations | 4388 | +| time_elapsed | 6331 | +| total_timesteps | 8986624 | +| train/ | | +| approx_kl | 0.010567914 | +| clip_fraction | 0.321 | +| clip_range | 0.0728 | +| entropy_loss | -7.07 | +| explained_variance | 0.271 | +| learning_rate | 4.79e-05 | +| loss | -0.0342 | +| n_updates | 33368 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000182 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1419 | +| iterations | 4389 | +| time_elapsed | 6333 | +| total_timesteps | 8988672 | +| train/ | | +| approx_kl | 0.008716984 | +| clip_fraction | 0.314 | +| clip_range | 0.0728 | +| entropy_loss | -7.23 | +| explained_variance | 0.163 | +| learning_rate | 4.79e-05 | +| loss | -0.0312 | +| n_updates | 33372 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000223 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1419 | +| iterations | 4390 | +| time_elapsed | 6334 | +| total_timesteps | 8990720 | +| train/ | | +| approx_kl | 0.010418884 | +| clip_fraction | 0.309 | +| clip_range | 0.0728 | +| entropy_loss | -7.13 | +| explained_variance | 0.481 | +| learning_rate | 4.79e-05 | +| loss | -0.0279 | +| n_updates | 33376 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000154 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1419 | +| iterations | 4391 | +| time_elapsed | 6336 | +| total_timesteps | 8992768 | +| train/ | | +| approx_kl | 0.010606436 | +| clip_fraction | 0.322 | +| clip_range | 0.0728 | +| entropy_loss | -7.42 | +| explained_variance | -0.0321 | +| learning_rate | 4.79e-05 | +| loss | -0.0384 | +| n_updates | 33380 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000126 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1419 | +| iterations | 4392 | +| time_elapsed | 6337 | +| total_timesteps | 8994816 | +| train/ | | +| approx_kl | 0.010652822 | +| clip_fraction | 0.326 | +| clip_range | 0.0728 | +| entropy_loss | -7.12 | +| explained_variance | 0.59 | +| learning_rate | 4.79e-05 | +| loss | -0.0388 | +| n_updates | 33384 | +| policy_gradient_loss | -0.022 | +| value_loss | 8.36e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1419 | +| iterations | 4393 | +| time_elapsed | 6338 | +| total_timesteps | 8996864 | +| train/ | | +| approx_kl | 0.009599175 | +| clip_fraction | 0.306 | +| clip_range | 0.0728 | +| entropy_loss | -7.17 | +| explained_variance | 0.233 | +| learning_rate | 4.79e-05 | +| loss | -0.026 | +| n_updates | 33388 | +| policy_gradient_loss | -0.0131 | +| value_loss | 0.000235 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1419 | +| iterations | 4394 | +| time_elapsed | 6340 | +| total_timesteps | 8998912 | +| train/ | | +| approx_kl | 0.012309944 | +| clip_fraction | 0.312 | +| clip_range | 0.0728 | +| entropy_loss | -7.17 | +| explained_variance | 0.32 | +| learning_rate | 4.79e-05 | +| loss | -0.0369 | +| n_updates | 33392 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000147 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1419 | +| iterations | 4395 | +| time_elapsed | 6341 | +| total_timesteps | 9000960 | +| train/ | | +| approx_kl | 0.012164995 | +| clip_fraction | 0.321 | +| clip_range | 0.0728 | +| entropy_loss | -6.61 | +| explained_variance | 0.739 | +| learning_rate | 4.79e-05 | +| loss | -0.0341 | +| n_updates | 33396 | +| policy_gradient_loss | -0.0207 | +| value_loss | 9.63e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1419 | +| iterations | 4396 | +| time_elapsed | 6343 | +| total_timesteps | 9003008 | +| train/ | | +| approx_kl | 0.012221811 | +| clip_fraction | 0.336 | +| clip_range | 0.0727 | +| entropy_loss | -7.15 | +| explained_variance | 0.534 | +| learning_rate | 4.79e-05 | +| loss | -0.0312 | +| n_updates | 33400 | +| policy_gradient_loss | -0.022 | +| value_loss | 6.77e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1419 | +| iterations | 4397 | +| time_elapsed | 6344 | +| total_timesteps | 9005056 | +| train/ | | +| approx_kl | 0.011397113 | +| clip_fraction | 0.309 | +| clip_range | 0.0727 | +| entropy_loss | -7.01 | +| explained_variance | 0.39 | +| learning_rate | 4.79e-05 | +| loss | -0.0253 | +| n_updates | 33404 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000118 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1419 | +| iterations | 4398 | +| time_elapsed | 6346 | +| total_timesteps | 9007104 | +| train/ | | +| approx_kl | 0.012599727 | +| clip_fraction | 0.339 | +| clip_range | 0.0727 | +| entropy_loss | -6.85 | +| explained_variance | 0.465 | +| learning_rate | 4.79e-05 | +| loss | -0.0313 | +| n_updates | 33408 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000125 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1419 | +| iterations | 4399 | +| time_elapsed | 6347 | +| total_timesteps | 9009152 | +| train/ | | +| approx_kl | 0.012638749 | +| clip_fraction | 0.301 | +| clip_range | 0.0727 | +| entropy_loss | -6.98 | +| explained_variance | 0.508 | +| learning_rate | 4.79e-05 | +| loss | -0.0328 | +| n_updates | 33412 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000126 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1419 | +| iterations | 4400 | +| time_elapsed | 6349 | +| total_timesteps | 9011200 | +| train/ | | +| approx_kl | 0.011928521 | +| clip_fraction | 0.328 | +| clip_range | 0.0727 | +| entropy_loss | -7.34 | +| explained_variance | 0.0144 | +| learning_rate | 4.79e-05 | +| loss | -0.035 | +| n_updates | 33416 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000172 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1419 | +| iterations | 4401 | +| time_elapsed | 6350 | +| total_timesteps | 9013248 | +| train/ | | +| approx_kl | 0.01143159 | +| clip_fraction | 0.321 | +| clip_range | 0.0727 | +| entropy_loss | -7.29 | +| explained_variance | 0.307 | +| learning_rate | 4.79e-05 | +| loss | -0.038 | +| n_updates | 33420 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000137 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1419 | +| iterations | 4402 | +| time_elapsed | 6352 | +| total_timesteps | 9015296 | +| train/ | | +| approx_kl | 0.011602819 | +| clip_fraction | 0.296 | +| clip_range | 0.0727 | +| entropy_loss | -7.11 | +| explained_variance | 0.253 | +| learning_rate | 4.79e-05 | +| loss | -0.0265 | +| n_updates | 33424 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000322 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1419 | +| iterations | 4403 | +| time_elapsed | 6353 | +| total_timesteps | 9017344 | +| train/ | | +| approx_kl | 0.010878408 | +| clip_fraction | 0.299 | +| clip_range | 0.0727 | +| entropy_loss | -6.94 | +| explained_variance | 0.295 | +| learning_rate | 4.79e-05 | +| loss | -0.033 | +| n_updates | 33428 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000159 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1419 | +| iterations | 4404 | +| time_elapsed | 6354 | +| total_timesteps | 9019392 | +| train/ | | +| approx_kl | 0.010180159 | +| clip_fraction | 0.339 | +| clip_range | 0.0727 | +| entropy_loss | -7.34 | +| explained_variance | -0.103 | +| learning_rate | 4.79e-05 | +| loss | -0.0356 | +| n_updates | 33432 | +| policy_gradient_loss | -0.0226 | +| value_loss | 7.45e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1419 | +| iterations | 4405 | +| time_elapsed | 6356 | +| total_timesteps | 9021440 | +| train/ | | +| approx_kl | 0.011683747 | +| clip_fraction | 0.33 | +| clip_range | 0.0727 | +| entropy_loss | -7.36 | +| explained_variance | 0.413 | +| learning_rate | 4.79e-05 | +| loss | -0.0389 | +| n_updates | 33436 | +| policy_gradient_loss | -0.0221 | +| value_loss | 7.35e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1419 | +| iterations | 4406 | +| time_elapsed | 6357 | +| total_timesteps | 9023488 | +| train/ | | +| approx_kl | 0.010236913 | +| clip_fraction | 0.321 | +| clip_range | 0.0727 | +| entropy_loss | -7.06 | +| explained_variance | 0.679 | +| learning_rate | 4.79e-05 | +| loss | -0.0367 | +| n_updates | 33440 | +| policy_gradient_loss | -0.0205 | +| value_loss | 7.53e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1419 | +| iterations | 4407 | +| time_elapsed | 6359 | +| total_timesteps | 9025536 | +| train/ | | +| approx_kl | 0.00837983 | +| clip_fraction | 0.298 | +| clip_range | 0.0727 | +| entropy_loss | -7.15 | +| explained_variance | 0.261 | +| learning_rate | 4.79e-05 | +| loss | -0.0256 | +| n_updates | 33444 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000204 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1419 | +| iterations | 4408 | +| time_elapsed | 6360 | +| total_timesteps | 9027584 | +| train/ | | +| approx_kl | 0.0128362235 | +| clip_fraction | 0.331 | +| clip_range | 0.0727 | +| entropy_loss | -6.93 | +| explained_variance | 0.471 | +| learning_rate | 4.79e-05 | +| loss | -0.034 | +| n_updates | 33448 | +| policy_gradient_loss | -0.0224 | +| value_loss | 0.000114 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1419 | +| iterations | 4409 | +| time_elapsed | 6362 | +| total_timesteps | 9029632 | +| train/ | | +| approx_kl | 0.012017002 | +| clip_fraction | 0.336 | +| clip_range | 0.0727 | +| entropy_loss | -7.24 | +| explained_variance | 0.0334 | +| learning_rate | 4.79e-05 | +| loss | -0.0329 | +| n_updates | 33452 | +| policy_gradient_loss | -0.023 | +| value_loss | 6.47e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1419 | +| iterations | 4410 | +| time_elapsed | 6363 | +| total_timesteps | 9031680 | +| train/ | | +| approx_kl | 0.010898529 | +| clip_fraction | 0.328 | +| clip_range | 0.0727 | +| entropy_loss | -7.18 | +| explained_variance | 0.393 | +| learning_rate | 4.79e-05 | +| loss | -0.0363 | +| n_updates | 33456 | +| policy_gradient_loss | -0.0203 | +| value_loss | 7.92e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1419 | +| iterations | 4411 | +| time_elapsed | 6364 | +| total_timesteps | 9033728 | +| train/ | | +| approx_kl | 0.012998122 | +| clip_fraction | 0.3 | +| clip_range | 0.0727 | +| entropy_loss | -6.99 | +| explained_variance | 0.287 | +| learning_rate | 4.79e-05 | +| loss | -0.0284 | +| n_updates | 33460 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000173 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1419 | +| iterations | 4412 | +| time_elapsed | 6366 | +| total_timesteps | 9035776 | +| train/ | | +| approx_kl | 0.013516989 | +| clip_fraction | 0.321 | +| clip_range | 0.0727 | +| entropy_loss | -7.17 | +| explained_variance | 0.194 | +| learning_rate | 4.79e-05 | +| loss | -0.0282 | +| n_updates | 33464 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000192 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1419 | +| iterations | 4413 | +| time_elapsed | 6367 | +| total_timesteps | 9037824 | +| train/ | | +| approx_kl | 0.012243396 | +| clip_fraction | 0.298 | +| clip_range | 0.0727 | +| entropy_loss | -7.38 | +| explained_variance | -0.274 | +| learning_rate | 4.79e-05 | +| loss | -0.0355 | +| n_updates | 33468 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.00011 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1419 | +| iterations | 4414 | +| time_elapsed | 6369 | +| total_timesteps | 9039872 | +| train/ | | +| approx_kl | 0.0110941995 | +| clip_fraction | 0.297 | +| clip_range | 0.0727 | +| entropy_loss | -7.47 | +| explained_variance | -0.0566 | +| learning_rate | 4.79e-05 | +| loss | -0.0317 | +| n_updates | 33472 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000257 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1419 | +| iterations | 4415 | +| time_elapsed | 6370 | +| total_timesteps | 9041920 | +| train/ | | +| approx_kl | 0.009983843 | +| clip_fraction | 0.301 | +| clip_range | 0.0727 | +| entropy_loss | -6.96 | +| explained_variance | 0.293 | +| learning_rate | 4.79e-05 | +| loss | -0.0299 | +| n_updates | 33476 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000237 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1419 | +| iterations | 4416 | +| time_elapsed | 6372 | +| total_timesteps | 9043968 | +| train/ | | +| approx_kl | 0.00951861 | +| clip_fraction | 0.299 | +| clip_range | 0.0727 | +| entropy_loss | -7.07 | +| explained_variance | 0.369 | +| learning_rate | 4.79e-05 | +| loss | -0.0338 | +| n_updates | 33480 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000238 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1419 | +| iterations | 4417 | +| time_elapsed | 6373 | +| total_timesteps | 9046016 | +| train/ | | +| approx_kl | 0.011198505 | +| clip_fraction | 0.301 | +| clip_range | 0.0727 | +| entropy_loss | -7.03 | +| explained_variance | 0.176 | +| learning_rate | 4.79e-05 | +| loss | -0.032 | +| n_updates | 33484 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000298 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1419 | +| iterations | 4418 | +| time_elapsed | 6375 | +| total_timesteps | 9048064 | +| train/ | | +| approx_kl | 0.0130275795 | +| clip_fraction | 0.321 | +| clip_range | 0.0727 | +| entropy_loss | -7.3 | +| explained_variance | -0.1 | +| learning_rate | 4.79e-05 | +| loss | -0.0381 | +| n_updates | 33488 | +| policy_gradient_loss | -0.0231 | +| value_loss | 0.000216 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1419 | +| iterations | 4419 | +| time_elapsed | 6376 | +| total_timesteps | 9050112 | +| train/ | | +| approx_kl | 0.010367521 | +| clip_fraction | 0.325 | +| clip_range | 0.0727 | +| entropy_loss | -6.96 | +| explained_variance | 0.46 | +| learning_rate | 4.79e-05 | +| loss | -0.0365 | +| n_updates | 33492 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000158 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1419 | +| iterations | 4420 | +| time_elapsed | 6378 | +| total_timesteps | 9052160 | +| train/ | | +| approx_kl | 0.010386109 | +| clip_fraction | 0.335 | +| clip_range | 0.0727 | +| entropy_loss | -6.82 | +| explained_variance | 0.611 | +| learning_rate | 4.79e-05 | +| loss | -0.0411 | +| n_updates | 33496 | +| policy_gradient_loss | -0.0237 | +| value_loss | 7.31e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1419 | +| iterations | 4421 | +| time_elapsed | 6379 | +| total_timesteps | 9054208 | +| train/ | | +| approx_kl | 0.012764957 | +| clip_fraction | 0.327 | +| clip_range | 0.0727 | +| entropy_loss | -7.25 | +| explained_variance | 0.311 | +| learning_rate | 4.79e-05 | +| loss | -0.0292 | +| n_updates | 33500 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000154 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1419 | +| iterations | 4422 | +| time_elapsed | 6380 | +| total_timesteps | 9056256 | +| train/ | | +| approx_kl | 0.013456641 | +| clip_fraction | 0.337 | +| clip_range | 0.0727 | +| entropy_loss | -7.04 | +| explained_variance | 0.272 | +| learning_rate | 4.78e-05 | +| loss | -0.0352 | +| n_updates | 33504 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000147 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1419 | +| iterations | 4423 | +| time_elapsed | 6382 | +| total_timesteps | 9058304 | +| train/ | | +| approx_kl | 0.011697834 | +| clip_fraction | 0.32 | +| clip_range | 0.0727 | +| entropy_loss | -7.28 | +| explained_variance | 0.331 | +| learning_rate | 4.78e-05 | +| loss | -0.0272 | +| n_updates | 33508 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000152 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1419 | +| iterations | 4424 | +| time_elapsed | 6383 | +| total_timesteps | 9060352 | +| train/ | | +| approx_kl | 0.011505684 | +| clip_fraction | 0.334 | +| clip_range | 0.0727 | +| entropy_loss | -7.19 | +| explained_variance | 0.338 | +| learning_rate | 4.78e-05 | +| loss | -0.0308 | +| n_updates | 33512 | +| policy_gradient_loss | -0.022 | +| value_loss | 0.000106 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1419 | +| iterations | 4425 | +| time_elapsed | 6385 | +| total_timesteps | 9062400 | +| train/ | | +| approx_kl | 0.011178953 | +| clip_fraction | 0.322 | +| clip_range | 0.0727 | +| entropy_loss | -7.21 | +| explained_variance | 0.255 | +| learning_rate | 4.78e-05 | +| loss | -0.0306 | +| n_updates | 33516 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000183 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1419 | +| iterations | 4426 | +| time_elapsed | 6386 | +| total_timesteps | 9064448 | +| train/ | | +| approx_kl | 0.012378236 | +| clip_fraction | 0.295 | +| clip_range | 0.0727 | +| entropy_loss | -7.21 | +| explained_variance | 0.167 | +| learning_rate | 4.78e-05 | +| loss | -0.0281 | +| n_updates | 33520 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.00029 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1419 | +| iterations | 4427 | +| time_elapsed | 6388 | +| total_timesteps | 9066496 | +| train/ | | +| approx_kl | 0.0092552025 | +| clip_fraction | 0.293 | +| clip_range | 0.0727 | +| entropy_loss | -6.85 | +| explained_variance | 0.403 | +| learning_rate | 4.78e-05 | +| loss | -0.0299 | +| n_updates | 33524 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000276 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1419 | +| iterations | 4428 | +| time_elapsed | 6389 | +| total_timesteps | 9068544 | +| train/ | | +| approx_kl | 0.009954758 | +| clip_fraction | 0.305 | +| clip_range | 0.0727 | +| entropy_loss | -6.8 | +| explained_variance | 0.178 | +| learning_rate | 4.78e-05 | +| loss | -0.0338 | +| n_updates | 33528 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000244 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1419 | +| iterations | 4429 | +| time_elapsed | 6391 | +| total_timesteps | 9070592 | +| train/ | | +| approx_kl | 0.011640135 | +| clip_fraction | 0.328 | +| clip_range | 0.0727 | +| entropy_loss | -7 | +| explained_variance | 0.538 | +| learning_rate | 4.78e-05 | +| loss | -0.0388 | +| n_updates | 33532 | +| policy_gradient_loss | -0.0227 | +| value_loss | 0.000116 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1419 | +| iterations | 4430 | +| time_elapsed | 6392 | +| total_timesteps | 9072640 | +| train/ | | +| approx_kl | 0.012853916 | +| clip_fraction | 0.313 | +| clip_range | 0.0727 | +| entropy_loss | -6.87 | +| explained_variance | 0.509 | +| learning_rate | 4.78e-05 | +| loss | -0.0329 | +| n_updates | 33536 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000115 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1419 | +| iterations | 4431 | +| time_elapsed | 6393 | +| total_timesteps | 9074688 | +| train/ | | +| approx_kl | 0.0108052185 | +| clip_fraction | 0.285 | +| clip_range | 0.0727 | +| entropy_loss | -7.38 | +| explained_variance | -0.0404 | +| learning_rate | 4.78e-05 | +| loss | -0.0215 | +| n_updates | 33540 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000206 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1419 | +| iterations | 4432 | +| time_elapsed | 6395 | +| total_timesteps | 9076736 | +| train/ | | +| approx_kl | 0.013643915 | +| clip_fraction | 0.337 | +| clip_range | 0.0727 | +| entropy_loss | -7.17 | +| explained_variance | 0.224 | +| learning_rate | 4.78e-05 | +| loss | -0.0345 | +| n_updates | 33544 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000131 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1419 | +| iterations | 4433 | +| time_elapsed | 6396 | +| total_timesteps | 9078784 | +| train/ | | +| approx_kl | 0.011286795 | +| clip_fraction | 0.341 | +| clip_range | 0.0727 | +| entropy_loss | -7.41 | +| explained_variance | -0.118 | +| learning_rate | 4.78e-05 | +| loss | -0.0384 | +| n_updates | 33548 | +| policy_gradient_loss | -0.0236 | +| value_loss | 6.76e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1419 | +| iterations | 4434 | +| time_elapsed | 6398 | +| total_timesteps | 9080832 | +| train/ | | +| approx_kl | 0.010906234 | +| clip_fraction | 0.322 | +| clip_range | 0.0727 | +| entropy_loss | -7.01 | +| explained_variance | 0.539 | +| learning_rate | 4.78e-05 | +| loss | -0.0338 | +| n_updates | 33552 | +| policy_gradient_loss | -0.0197 | +| value_loss | 9.41e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1419 | +| iterations | 4435 | +| time_elapsed | 6399 | +| total_timesteps | 9082880 | +| train/ | | +| approx_kl | 0.00939931 | +| clip_fraction | 0.311 | +| clip_range | 0.0727 | +| entropy_loss | -7.13 | +| explained_variance | 0.165 | +| learning_rate | 4.78e-05 | +| loss | -0.033 | +| n_updates | 33556 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000312 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1419 | +| iterations | 4436 | +| time_elapsed | 6401 | +| total_timesteps | 9084928 | +| train/ | | +| approx_kl | 0.010500591 | +| clip_fraction | 0.289 | +| clip_range | 0.0727 | +| entropy_loss | -7.03 | +| explained_variance | 0.326 | +| learning_rate | 4.78e-05 | +| loss | -0.0284 | +| n_updates | 33560 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000269 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1419 | +| iterations | 4437 | +| time_elapsed | 6402 | +| total_timesteps | 9086976 | +| train/ | | +| approx_kl | 0.011817997 | +| clip_fraction | 0.326 | +| clip_range | 0.0727 | +| entropy_loss | -7.34 | +| explained_variance | -0.194 | +| learning_rate | 4.78e-05 | +| loss | -0.0371 | +| n_updates | 33564 | +| policy_gradient_loss | -0.0221 | +| value_loss | 0.000136 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1419 | +| iterations | 4438 | +| time_elapsed | 6403 | +| total_timesteps | 9089024 | +| train/ | | +| approx_kl | 0.012413844 | +| clip_fraction | 0.329 | +| clip_range | 0.0727 | +| entropy_loss | -7.4 | +| explained_variance | -0.0244 | +| learning_rate | 4.78e-05 | +| loss | -0.0307 | +| n_updates | 33568 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000303 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1419 | +| iterations | 4439 | +| time_elapsed | 6405 | +| total_timesteps | 9091072 | +| train/ | | +| approx_kl | 0.012989465 | +| clip_fraction | 0.341 | +| clip_range | 0.0727 | +| entropy_loss | -6.69 | +| explained_variance | 0.36 | +| learning_rate | 4.78e-05 | +| loss | -0.0312 | +| n_updates | 33572 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000208 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1419 | +| iterations | 4440 | +| time_elapsed | 6406 | +| total_timesteps | 9093120 | +| train/ | | +| approx_kl | 0.011348594 | +| clip_fraction | 0.316 | +| clip_range | 0.0727 | +| entropy_loss | -6.43 | +| explained_variance | 0.646 | +| learning_rate | 4.78e-05 | +| loss | -0.0331 | +| n_updates | 33576 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000138 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1419 | +| iterations | 4441 | +| time_elapsed | 6408 | +| total_timesteps | 9095168 | +| train/ | | +| approx_kl | 0.0127152065 | +| clip_fraction | 0.345 | +| clip_range | 0.0727 | +| entropy_loss | -7.13 | +| explained_variance | 0.429 | +| learning_rate | 4.78e-05 | +| loss | -0.0375 | +| n_updates | 33580 | +| policy_gradient_loss | -0.0232 | +| value_loss | 7.78e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1419 | +| iterations | 4442 | +| time_elapsed | 6409 | +| total_timesteps | 9097216 | +| train/ | | +| approx_kl | 0.013793948 | +| clip_fraction | 0.305 | +| clip_range | 0.0727 | +| entropy_loss | -7.18 | +| explained_variance | 0.27 | +| learning_rate | 4.78e-05 | +| loss | -0.0276 | +| n_updates | 33584 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000131 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1419 | +| iterations | 4443 | +| time_elapsed | 6411 | +| total_timesteps | 9099264 | +| train/ | | +| approx_kl | 0.012343153 | +| clip_fraction | 0.298 | +| clip_range | 0.0727 | +| entropy_loss | -7.12 | +| explained_variance | 0.253 | +| learning_rate | 4.78e-05 | +| loss | -0.0321 | +| n_updates | 33588 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000161 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1419 | +| iterations | 4444 | +| time_elapsed | 6412 | +| total_timesteps | 9101312 | +| train/ | | +| approx_kl | 0.010892352 | +| clip_fraction | 0.313 | +| clip_range | 0.0727 | +| entropy_loss | -6.89 | +| explained_variance | 0.363 | +| learning_rate | 4.78e-05 | +| loss | -0.0234 | +| n_updates | 33592 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000176 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1419 | +| iterations | 4445 | +| time_elapsed | 6414 | +| total_timesteps | 9103360 | +| train/ | | +| approx_kl | 0.010623924 | +| clip_fraction | 0.317 | +| clip_range | 0.0727 | +| entropy_loss | -7.27 | +| explained_variance | 0.316 | +| learning_rate | 4.78e-05 | +| loss | -0.0316 | +| n_updates | 33596 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000154 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1419 | +| iterations | 4446 | +| time_elapsed | 6415 | +| total_timesteps | 9105408 | +| train/ | | +| approx_kl | 0.01340057 | +| clip_fraction | 0.33 | +| clip_range | 0.0727 | +| entropy_loss | -7.14 | +| explained_variance | 0.0987 | +| learning_rate | 4.78e-05 | +| loss | -0.0317 | +| n_updates | 33600 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000141 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1419 | +| iterations | 4447 | +| time_elapsed | 6416 | +| total_timesteps | 9107456 | +| train/ | | +| approx_kl | 0.0113106035 | +| clip_fraction | 0.336 | +| clip_range | 0.0727 | +| entropy_loss | -7.18 | +| explained_variance | 0.0723 | +| learning_rate | 4.78e-05 | +| loss | -0.0309 | +| n_updates | 33604 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000206 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1419 | +| iterations | 4448 | +| time_elapsed | 6418 | +| total_timesteps | 9109504 | +| train/ | | +| approx_kl | 0.010081536 | +| clip_fraction | 0.33 | +| clip_range | 0.0727 | +| entropy_loss | -7.15 | +| explained_variance | 0.4 | +| learning_rate | 4.78e-05 | +| loss | -0.0266 | +| n_updates | 33608 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000137 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1419 | +| iterations | 4449 | +| time_elapsed | 6419 | +| total_timesteps | 9111552 | +| train/ | | +| approx_kl | 0.011721011 | +| clip_fraction | 0.306 | +| clip_range | 0.0727 | +| entropy_loss | -7.2 | +| explained_variance | 0.3 | +| learning_rate | 4.78e-05 | +| loss | -0.0311 | +| n_updates | 33612 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000133 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1419 | +| iterations | 4450 | +| time_elapsed | 6421 | +| total_timesteps | 9113600 | +| train/ | | +| approx_kl | 0.011261263 | +| clip_fraction | 0.318 | +| clip_range | 0.0727 | +| entropy_loss | -7.36 | +| explained_variance | -0.11 | +| learning_rate | 4.78e-05 | +| loss | -0.0341 | +| n_updates | 33616 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.00022 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1419 | +| iterations | 4451 | +| time_elapsed | 6422 | +| total_timesteps | 9115648 | +| train/ | | +| approx_kl | 0.010522865 | +| clip_fraction | 0.304 | +| clip_range | 0.0727 | +| entropy_loss | -7.32 | +| explained_variance | -0.0301 | +| learning_rate | 4.78e-05 | +| loss | -0.0271 | +| n_updates | 33620 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000168 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1419 | +| iterations | 4452 | +| time_elapsed | 6424 | +| total_timesteps | 9117696 | +| train/ | | +| approx_kl | 0.0121755805 | +| clip_fraction | 0.352 | +| clip_range | 0.0727 | +| entropy_loss | -6.29 | +| explained_variance | 0.712 | +| learning_rate | 4.78e-05 | +| loss | -0.0378 | +| n_updates | 33624 | +| policy_gradient_loss | -0.0224 | +| value_loss | 8.33e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1419 | +| iterations | 4453 | +| time_elapsed | 6425 | +| total_timesteps | 9119744 | +| train/ | | +| approx_kl | 0.012382882 | +| clip_fraction | 0.331 | +| clip_range | 0.0727 | +| entropy_loss | -7.08 | +| explained_variance | 0.383 | +| learning_rate | 4.78e-05 | +| loss | -0.0351 | +| n_updates | 33628 | +| policy_gradient_loss | -0.0227 | +| value_loss | 0.000105 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1419 | +| iterations | 4454 | +| time_elapsed | 6426 | +| total_timesteps | 9121792 | +| train/ | | +| approx_kl | 0.010192093 | +| clip_fraction | 0.317 | +| clip_range | 0.0727 | +| entropy_loss | -6.84 | +| explained_variance | 0.739 | +| learning_rate | 4.78e-05 | +| loss | -0.0309 | +| n_updates | 33632 | +| policy_gradient_loss | -0.0193 | +| value_loss | 6.88e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1419 | +| iterations | 4455 | +| time_elapsed | 6428 | +| total_timesteps | 9123840 | +| train/ | | +| approx_kl | 0.010861637 | +| clip_fraction | 0.291 | +| clip_range | 0.0727 | +| entropy_loss | -6.94 | +| explained_variance | 0.291 | +| learning_rate | 4.78e-05 | +| loss | -0.0258 | +| n_updates | 33636 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000324 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1419 | +| iterations | 4456 | +| time_elapsed | 6429 | +| total_timesteps | 9125888 | +| train/ | | +| approx_kl | 0.013546795 | +| clip_fraction | 0.324 | +| clip_range | 0.0727 | +| entropy_loss | -7.19 | +| explained_variance | 0.382 | +| learning_rate | 4.78e-05 | +| loss | -0.0381 | +| n_updates | 33640 | +| policy_gradient_loss | -0.0238 | +| value_loss | 0.000103 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1419 | +| iterations | 4457 | +| time_elapsed | 6431 | +| total_timesteps | 9127936 | +| train/ | | +| approx_kl | 0.011885462 | +| clip_fraction | 0.327 | +| clip_range | 0.0727 | +| entropy_loss | -7.09 | +| explained_variance | 0.18 | +| learning_rate | 4.78e-05 | +| loss | -0.0328 | +| n_updates | 33644 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000203 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1419 | +| iterations | 4458 | +| time_elapsed | 6432 | +| total_timesteps | 9129984 | +| train/ | | +| approx_kl | 0.011566613 | +| clip_fraction | 0.307 | +| clip_range | 0.0727 | +| entropy_loss | -6.97 | +| explained_variance | 0.601 | +| learning_rate | 4.78e-05 | +| loss | -0.0313 | +| n_updates | 33648 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000105 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1419 | +| iterations | 4459 | +| time_elapsed | 6434 | +| total_timesteps | 9132032 | +| train/ | | +| approx_kl | 0.011529895 | +| clip_fraction | 0.289 | +| clip_range | 0.0727 | +| entropy_loss | -6.98 | +| explained_variance | 0.243 | +| learning_rate | 4.78e-05 | +| loss | -0.0326 | +| n_updates | 33652 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000266 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1419 | +| iterations | 4460 | +| time_elapsed | 6435 | +| total_timesteps | 9134080 | +| train/ | | +| approx_kl | 0.012477371 | +| clip_fraction | 0.333 | +| clip_range | 0.0727 | +| entropy_loss | -6.98 | +| explained_variance | 0.367 | +| learning_rate | 4.78e-05 | +| loss | -0.0274 | +| n_updates | 33656 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000173 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1419 | +| iterations | 4461 | +| time_elapsed | 6436 | +| total_timesteps | 9136128 | +| train/ | | +| approx_kl | 0.013713282 | +| clip_fraction | 0.371 | +| clip_range | 0.0727 | +| entropy_loss | -7.26 | +| explained_variance | -0.549 | +| learning_rate | 4.78e-05 | +| loss | -0.0437 | +| n_updates | 33660 | +| policy_gradient_loss | -0.0277 | +| value_loss | 6.15e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1419 | +| iterations | 4462 | +| time_elapsed | 6438 | +| total_timesteps | 9138176 | +| train/ | | +| approx_kl | 0.01025892 | +| clip_fraction | 0.306 | +| clip_range | 0.0727 | +| entropy_loss | -7.08 | +| explained_variance | 0.165 | +| learning_rate | 4.78e-05 | +| loss | -0.0348 | +| n_updates | 33664 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000173 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1419 | +| iterations | 4463 | +| time_elapsed | 6439 | +| total_timesteps | 9140224 | +| train/ | | +| approx_kl | 0.011444625 | +| clip_fraction | 0.326 | +| clip_range | 0.0727 | +| entropy_loss | -7.32 | +| explained_variance | -0.118 | +| learning_rate | 4.78e-05 | +| loss | -0.0312 | +| n_updates | 33668 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000134 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1419 | +| iterations | 4464 | +| time_elapsed | 6441 | +| total_timesteps | 9142272 | +| train/ | | +| approx_kl | 0.011340532 | +| clip_fraction | 0.311 | +| clip_range | 0.0727 | +| entropy_loss | -7.08 | +| explained_variance | 0.219 | +| learning_rate | 4.78e-05 | +| loss | -0.0253 | +| n_updates | 33672 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000192 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1419 | +| iterations | 4465 | +| time_elapsed | 6442 | +| total_timesteps | 9144320 | +| train/ | | +| approx_kl | 0.011073982 | +| clip_fraction | 0.311 | +| clip_range | 0.0727 | +| entropy_loss | -6.71 | +| explained_variance | 0.432 | +| learning_rate | 4.78e-05 | +| loss | -0.0307 | +| n_updates | 33676 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000213 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1419 | +| iterations | 4466 | +| time_elapsed | 6444 | +| total_timesteps | 9146368 | +| train/ | | +| approx_kl | 0.011183182 | +| clip_fraction | 0.314 | +| clip_range | 0.0727 | +| entropy_loss | -7.09 | +| explained_variance | 0.323 | +| learning_rate | 4.78e-05 | +| loss | -0.0332 | +| n_updates | 33680 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000142 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1419 | +| iterations | 4467 | +| time_elapsed | 6445 | +| total_timesteps | 9148416 | +| train/ | | +| approx_kl | 0.0097794365 | +| clip_fraction | 0.311 | +| clip_range | 0.0727 | +| entropy_loss | -6.91 | +| explained_variance | 0.447 | +| learning_rate | 4.78e-05 | +| loss | -0.0328 | +| n_updates | 33684 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.0002 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1419 | +| iterations | 4468 | +| time_elapsed | 6446 | +| total_timesteps | 9150464 | +| train/ | | +| approx_kl | 0.011793711 | +| clip_fraction | 0.349 | +| clip_range | 0.0727 | +| entropy_loss | -7.24 | +| explained_variance | 0.541 | +| learning_rate | 4.78e-05 | +| loss | -0.0425 | +| n_updates | 33688 | +| policy_gradient_loss | -0.0231 | +| value_loss | 8.28e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1419 | +| iterations | 4469 | +| time_elapsed | 6448 | +| total_timesteps | 9152512 | +| train/ | | +| approx_kl | 0.009877829 | +| clip_fraction | 0.313 | +| clip_range | 0.0727 | +| entropy_loss | -6.73 | +| explained_variance | 0.649 | +| learning_rate | 4.78e-05 | +| loss | -0.0334 | +| n_updates | 33692 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000133 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1419 | +| iterations | 4470 | +| time_elapsed | 6449 | +| total_timesteps | 9154560 | +| train/ | | +| approx_kl | 0.009834262 | +| clip_fraction | 0.303 | +| clip_range | 0.0727 | +| entropy_loss | -7.29 | +| explained_variance | -0.0649 | +| learning_rate | 4.78e-05 | +| loss | -0.0279 | +| n_updates | 33696 | +| policy_gradient_loss | -0.0195 | +| value_loss | 8.4e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1419 | +| iterations | 4471 | +| time_elapsed | 6451 | +| total_timesteps | 9156608 | +| train/ | | +| approx_kl | 0.011734222 | +| clip_fraction | 0.293 | +| clip_range | 0.0727 | +| entropy_loss | -7.21 | +| explained_variance | 0.381 | +| learning_rate | 4.78e-05 | +| loss | -0.0301 | +| n_updates | 33700 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000148 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1419 | +| iterations | 4472 | +| time_elapsed | 6452 | +| total_timesteps | 9158656 | +| train/ | | +| approx_kl | 0.009331073 | +| clip_fraction | 0.275 | +| clip_range | 0.0727 | +| entropy_loss | -6.86 | +| explained_variance | 0.232 | +| learning_rate | 4.78e-05 | +| loss | -0.0292 | +| n_updates | 33704 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000292 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1419 | +| iterations | 4473 | +| time_elapsed | 6454 | +| total_timesteps | 9160704 | +| train/ | | +| approx_kl | 0.013498608 | +| clip_fraction | 0.318 | +| clip_range | 0.0727 | +| entropy_loss | -7.26 | +| explained_variance | 0.16 | +| learning_rate | 4.78e-05 | +| loss | -0.0383 | +| n_updates | 33708 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000113 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1419 | +| iterations | 4474 | +| time_elapsed | 6455 | +| total_timesteps | 9162752 | +| train/ | | +| approx_kl | 0.012868665 | +| clip_fraction | 0.332 | +| clip_range | 0.0727 | +| entropy_loss | -7.28 | +| explained_variance | 0.196 | +| learning_rate | 4.78e-05 | +| loss | -0.0274 | +| n_updates | 33712 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000164 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1419 | +| iterations | 4475 | +| time_elapsed | 6457 | +| total_timesteps | 9164800 | +| train/ | | +| approx_kl | 0.0111209005 | +| clip_fraction | 0.309 | +| clip_range | 0.0727 | +| entropy_loss | -6.61 | +| explained_variance | 0.392 | +| learning_rate | 4.78e-05 | +| loss | -0.0296 | +| n_updates | 33716 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000257 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1419 | +| iterations | 4476 | +| time_elapsed | 6458 | +| total_timesteps | 9166848 | +| train/ | | +| approx_kl | 0.011750545 | +| clip_fraction | 0.33 | +| clip_range | 0.0727 | +| entropy_loss | -6.68 | +| explained_variance | 0.675 | +| learning_rate | 4.78e-05 | +| loss | -0.0348 | +| n_updates | 33720 | +| policy_gradient_loss | -0.0218 | +| value_loss | 9.04e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1419 | +| iterations | 4477 | +| time_elapsed | 6459 | +| total_timesteps | 9168896 | +| train/ | | +| approx_kl | 0.012686082 | +| clip_fraction | 0.318 | +| clip_range | 0.0727 | +| entropy_loss | -6.86 | +| explained_variance | 0.3 | +| learning_rate | 4.78e-05 | +| loss | -0.0283 | +| n_updates | 33724 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000292 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1419 | +| iterations | 4478 | +| time_elapsed | 6461 | +| total_timesteps | 9170944 | +| train/ | | +| approx_kl | 0.012850499 | +| clip_fraction | 0.341 | +| clip_range | 0.0727 | +| entropy_loss | -7.34 | +| explained_variance | -0.128 | +| learning_rate | 4.78e-05 | +| loss | -0.0345 | +| n_updates | 33728 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000154 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1419 | +| iterations | 4479 | +| time_elapsed | 6462 | +| total_timesteps | 9172992 | +| train/ | | +| approx_kl | 0.012370292 | +| clip_fraction | 0.318 | +| clip_range | 0.0727 | +| entropy_loss | -6.75 | +| explained_variance | 0.347 | +| learning_rate | 4.78e-05 | +| loss | -0.0238 | +| n_updates | 33732 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.00015 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1419 | +| iterations | 4480 | +| time_elapsed | 6463 | +| total_timesteps | 9175040 | +| train/ | | +| approx_kl | 0.012243139 | +| clip_fraction | 0.327 | +| clip_range | 0.0727 | +| entropy_loss | -7.16 | +| explained_variance | 0.0384 | +| learning_rate | 4.78e-05 | +| loss | -0.0337 | +| n_updates | 33736 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000204 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1419 | +| iterations | 4481 | +| time_elapsed | 6465 | +| total_timesteps | 9177088 | +| train/ | | +| approx_kl | 0.0132090915 | +| clip_fraction | 0.314 | +| clip_range | 0.0727 | +| entropy_loss | -6.88 | +| explained_variance | 0.262 | +| learning_rate | 4.78e-05 | +| loss | -0.038 | +| n_updates | 33740 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000164 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1419 | +| iterations | 4482 | +| time_elapsed | 6466 | +| total_timesteps | 9179136 | +| train/ | | +| approx_kl | 0.01111139 | +| clip_fraction | 0.318 | +| clip_range | 0.0727 | +| entropy_loss | -7.09 | +| explained_variance | 0.54 | +| learning_rate | 4.78e-05 | +| loss | -0.0294 | +| n_updates | 33744 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000116 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1419 | +| iterations | 4483 | +| time_elapsed | 6468 | +| total_timesteps | 9181184 | +| train/ | | +| approx_kl | 0.013741522 | +| clip_fraction | 0.34 | +| clip_range | 0.0727 | +| entropy_loss | -7.23 | +| explained_variance | -0.00443 | +| learning_rate | 4.78e-05 | +| loss | -0.0368 | +| n_updates | 33748 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.00014 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1419 | +| iterations | 4484 | +| time_elapsed | 6469 | +| total_timesteps | 9183232 | +| train/ | | +| approx_kl | 0.012787652 | +| clip_fraction | 0.322 | +| clip_range | 0.0727 | +| entropy_loss | -7.06 | +| explained_variance | 0.448 | +| learning_rate | 4.78e-05 | +| loss | -0.034 | +| n_updates | 33752 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000109 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1419 | +| iterations | 4485 | +| time_elapsed | 6471 | +| total_timesteps | 9185280 | +| train/ | | +| approx_kl | 0.012022581 | +| clip_fraction | 0.333 | +| clip_range | 0.0727 | +| entropy_loss | -6.94 | +| explained_variance | 0.496 | +| learning_rate | 4.78e-05 | +| loss | -0.0295 | +| n_updates | 33756 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000123 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1419 | +| iterations | 4486 | +| time_elapsed | 6472 | +| total_timesteps | 9187328 | +| train/ | | +| approx_kl | 0.010284387 | +| clip_fraction | 0.294 | +| clip_range | 0.0727 | +| entropy_loss | -7.25 | +| explained_variance | 0.312 | +| learning_rate | 4.78e-05 | +| loss | -0.035 | +| n_updates | 33760 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000155 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1419 | +| iterations | 4487 | +| time_elapsed | 6474 | +| total_timesteps | 9189376 | +| train/ | | +| approx_kl | 0.013632592 | +| clip_fraction | 0.323 | +| clip_range | 0.0727 | +| entropy_loss | -7.06 | +| explained_variance | 0.396 | +| learning_rate | 4.78e-05 | +| loss | -0.0341 | +| n_updates | 33764 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000103 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1419 | +| iterations | 4488 | +| time_elapsed | 6475 | +| total_timesteps | 9191424 | +| train/ | | +| approx_kl | 0.012506988 | +| clip_fraction | 0.327 | +| clip_range | 0.0727 | +| entropy_loss | -7.32 | +| explained_variance | -0.157 | +| learning_rate | 4.78e-05 | +| loss | -0.034 | +| n_updates | 33768 | +| policy_gradient_loss | -0.0203 | +| value_loss | 8.78e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1419 | +| iterations | 4489 | +| time_elapsed | 6476 | +| total_timesteps | 9193472 | +| train/ | | +| approx_kl | 0.010972992 | +| clip_fraction | 0.326 | +| clip_range | 0.0727 | +| entropy_loss | -6.75 | +| explained_variance | 0.536 | +| learning_rate | 4.78e-05 | +| loss | -0.0243 | +| n_updates | 33772 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000105 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1419 | +| iterations | 4490 | +| time_elapsed | 6478 | +| total_timesteps | 9195520 | +| train/ | | +| approx_kl | 0.013188893 | +| clip_fraction | 0.304 | +| clip_range | 0.0727 | +| entropy_loss | -7 | +| explained_variance | 0.347 | +| learning_rate | 4.78e-05 | +| loss | -0.0322 | +| n_updates | 33776 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000132 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1419 | +| iterations | 4491 | +| time_elapsed | 6479 | +| total_timesteps | 9197568 | +| train/ | | +| approx_kl | 0.010487979 | +| clip_fraction | 0.307 | +| clip_range | 0.0727 | +| entropy_loss | -6.93 | +| explained_variance | 0.387 | +| learning_rate | 4.78e-05 | +| loss | -0.0267 | +| n_updates | 33780 | +| policy_gradient_loss | -0.0172 | +| value_loss | 9.73e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1419 | +| iterations | 4492 | +| time_elapsed | 6481 | +| total_timesteps | 9199616 | +| train/ | | +| approx_kl | 0.01119308 | +| clip_fraction | 0.32 | +| clip_range | 0.0727 | +| entropy_loss | -7.32 | +| explained_variance | 0.0375 | +| learning_rate | 4.78e-05 | +| loss | -0.0329 | +| n_updates | 33784 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000139 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1419 | +| iterations | 4493 | +| time_elapsed | 6482 | +| total_timesteps | 9201664 | +| train/ | | +| approx_kl | 0.011801356 | +| clip_fraction | 0.376 | +| clip_range | 0.0727 | +| entropy_loss | -7.27 | +| explained_variance | 0.334 | +| learning_rate | 4.78e-05 | +| loss | -0.0416 | +| n_updates | 33788 | +| policy_gradient_loss | -0.0271 | +| value_loss | 5.08e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1419 | +| iterations | 4494 | +| time_elapsed | 6484 | +| total_timesteps | 9203712 | +| train/ | | +| approx_kl | 0.011498698 | +| clip_fraction | 0.3 | +| clip_range | 0.0727 | +| entropy_loss | -7.12 | +| explained_variance | 0.295 | +| learning_rate | 4.78e-05 | +| loss | -0.0323 | +| n_updates | 33792 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000302 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1419 | +| iterations | 4495 | +| time_elapsed | 6485 | +| total_timesteps | 9205760 | +| train/ | | +| approx_kl | 0.0110722445 | +| clip_fraction | 0.324 | +| clip_range | 0.0727 | +| entropy_loss | -7.05 | +| explained_variance | 0.087 | +| learning_rate | 4.78e-05 | +| loss | -0.0319 | +| n_updates | 33796 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000152 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1419 | +| iterations | 4496 | +| time_elapsed | 6486 | +| total_timesteps | 9207808 | +| train/ | | +| approx_kl | 0.010240319 | +| clip_fraction | 0.297 | +| clip_range | 0.0727 | +| entropy_loss | -7.08 | +| explained_variance | 0.33 | +| learning_rate | 4.78e-05 | +| loss | -0.0353 | +| n_updates | 33800 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000189 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1419 | +| iterations | 4497 | +| time_elapsed | 6488 | +| total_timesteps | 9209856 | +| train/ | | +| approx_kl | 0.011632595 | +| clip_fraction | 0.295 | +| clip_range | 0.0727 | +| entropy_loss | -7.03 | +| explained_variance | 0.359 | +| learning_rate | 4.78e-05 | +| loss | -0.0304 | +| n_updates | 33804 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000154 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1419 | +| iterations | 4498 | +| time_elapsed | 6489 | +| total_timesteps | 9211904 | +| train/ | | +| approx_kl | 0.010288039 | +| clip_fraction | 0.287 | +| clip_range | 0.0727 | +| entropy_loss | -7.07 | +| explained_variance | 0.277 | +| learning_rate | 4.78e-05 | +| loss | -0.027 | +| n_updates | 33808 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000284 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1419 | +| iterations | 4499 | +| time_elapsed | 6491 | +| total_timesteps | 9213952 | +| train/ | | +| approx_kl | 0.012306888 | +| clip_fraction | 0.331 | +| clip_range | 0.0727 | +| entropy_loss | -6.81 | +| explained_variance | 0.641 | +| learning_rate | 4.78e-05 | +| loss | -0.036 | +| n_updates | 33812 | +| policy_gradient_loss | -0.0234 | +| value_loss | 0.000102 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1419 | +| iterations | 4500 | +| time_elapsed | 6492 | +| total_timesteps | 9216000 | +| train/ | | +| approx_kl | 0.012656283 | +| clip_fraction | 0.328 | +| clip_range | 0.0727 | +| entropy_loss | -7.24 | +| explained_variance | 0.384 | +| learning_rate | 4.78e-05 | +| loss | -0.0362 | +| n_updates | 33816 | +| policy_gradient_loss | -0.023 | +| value_loss | 9.74e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1419 | +| iterations | 4501 | +| time_elapsed | 6494 | +| total_timesteps | 9218048 | +| train/ | | +| approx_kl | 0.012470644 | +| clip_fraction | 0.299 | +| clip_range | 0.0727 | +| entropy_loss | -6.66 | +| explained_variance | 0.649 | +| learning_rate | 4.78e-05 | +| loss | -0.0313 | +| n_updates | 33820 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000123 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1419 | +| iterations | 4502 | +| time_elapsed | 6495 | +| total_timesteps | 9220096 | +| train/ | | +| approx_kl | 0.010947986 | +| clip_fraction | 0.319 | +| clip_range | 0.0727 | +| entropy_loss | -6.78 | +| explained_variance | 0.631 | +| learning_rate | 4.78e-05 | +| loss | -0.034 | +| n_updates | 33824 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000144 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1419 | +| iterations | 4503 | +| time_elapsed | 6497 | +| total_timesteps | 9222144 | +| train/ | | +| approx_kl | 0.010055804 | +| clip_fraction | 0.297 | +| clip_range | 0.0727 | +| entropy_loss | -7.02 | +| explained_variance | 0.243 | +| learning_rate | 4.78e-05 | +| loss | -0.0289 | +| n_updates | 33828 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000228 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1419 | +| iterations | 4504 | +| time_elapsed | 6498 | +| total_timesteps | 9224192 | +| train/ | | +| approx_kl | 0.011662593 | +| clip_fraction | 0.324 | +| clip_range | 0.0727 | +| entropy_loss | -7.27 | +| explained_variance | -0.121 | +| learning_rate | 4.78e-05 | +| loss | -0.0292 | +| n_updates | 33832 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000156 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1419 | +| iterations | 4505 | +| time_elapsed | 6499 | +| total_timesteps | 9226240 | +| train/ | | +| approx_kl | 0.011231767 | +| clip_fraction | 0.338 | +| clip_range | 0.0727 | +| entropy_loss | -7.41 | +| explained_variance | -0.161 | +| learning_rate | 4.78e-05 | +| loss | -0.029 | +| n_updates | 33836 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000101 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1419 | +| iterations | 4506 | +| time_elapsed | 6501 | +| total_timesteps | 9228288 | +| train/ | | +| approx_kl | 0.011665862 | +| clip_fraction | 0.318 | +| clip_range | 0.0727 | +| entropy_loss | -6.97 | +| explained_variance | 0.489 | +| learning_rate | 4.78e-05 | +| loss | -0.0304 | +| n_updates | 33840 | +| policy_gradient_loss | -0.0199 | +| value_loss | 9.49e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1419 | +| iterations | 4507 | +| time_elapsed | 6502 | +| total_timesteps | 9230336 | +| train/ | | +| approx_kl | 0.011016101 | +| clip_fraction | 0.317 | +| clip_range | 0.0727 | +| entropy_loss | -7.14 | +| explained_variance | 0.415 | +| learning_rate | 4.78e-05 | +| loss | -0.03 | +| n_updates | 33844 | +| policy_gradient_loss | -0.0186 | +| value_loss | 8.76e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1419 | +| iterations | 4508 | +| time_elapsed | 6504 | +| total_timesteps | 9232384 | +| train/ | | +| approx_kl | 0.010943638 | +| clip_fraction | 0.307 | +| clip_range | 0.0727 | +| entropy_loss | -6.78 | +| explained_variance | 0.736 | +| learning_rate | 4.78e-05 | +| loss | -0.0277 | +| n_updates | 33848 | +| policy_gradient_loss | -0.0187 | +| value_loss | 7.9e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1419 | +| iterations | 4509 | +| time_elapsed | 6505 | +| total_timesteps | 9234432 | +| train/ | | +| approx_kl | 0.010957725 | +| clip_fraction | 0.298 | +| clip_range | 0.0727 | +| entropy_loss | -7.4 | +| explained_variance | -0.0647 | +| learning_rate | 4.78e-05 | +| loss | -0.0319 | +| n_updates | 33852 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000162 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1419 | +| iterations | 4510 | +| time_elapsed | 6507 | +| total_timesteps | 9236480 | +| train/ | | +| approx_kl | 0.012233179 | +| clip_fraction | 0.325 | +| clip_range | 0.0727 | +| entropy_loss | -7 | +| explained_variance | 0.618 | +| learning_rate | 4.78e-05 | +| loss | -0.0269 | +| n_updates | 33856 | +| policy_gradient_loss | -0.0199 | +| value_loss | 9.69e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1419 | +| iterations | 4511 | +| time_elapsed | 6508 | +| total_timesteps | 9238528 | +| train/ | | +| approx_kl | 0.011766309 | +| clip_fraction | 0.313 | +| clip_range | 0.0727 | +| entropy_loss | -7.06 | +| explained_variance | 0.473 | +| learning_rate | 4.78e-05 | +| loss | -0.0305 | +| n_updates | 33860 | +| policy_gradient_loss | -0.02 | +| value_loss | 8.1e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1419 | +| iterations | 4512 | +| time_elapsed | 6509 | +| total_timesteps | 9240576 | +| train/ | | +| approx_kl | 0.010174409 | +| clip_fraction | 0.303 | +| clip_range | 0.0727 | +| entropy_loss | -6.86 | +| explained_variance | 0.531 | +| learning_rate | 4.78e-05 | +| loss | -0.0291 | +| n_updates | 33864 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000126 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1419 | +| iterations | 4513 | +| time_elapsed | 6511 | +| total_timesteps | 9242624 | +| train/ | | +| approx_kl | 0.012716174 | +| clip_fraction | 0.325 | +| clip_range | 0.0727 | +| entropy_loss | -7.09 | +| explained_variance | 0.247 | +| learning_rate | 4.78e-05 | +| loss | -0.0336 | +| n_updates | 33868 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000129 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1419 | +| iterations | 4514 | +| time_elapsed | 6512 | +| total_timesteps | 9244672 | +| train/ | | +| approx_kl | 0.011245908 | +| clip_fraction | 0.33 | +| clip_range | 0.0727 | +| entropy_loss | -7 | +| explained_variance | 0.495 | +| learning_rate | 4.78e-05 | +| loss | -0.0328 | +| n_updates | 33872 | +| policy_gradient_loss | -0.0204 | +| value_loss | 8.4e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1419 | +| iterations | 4515 | +| time_elapsed | 6514 | +| total_timesteps | 9246720 | +| train/ | | +| approx_kl | 0.011753879 | +| clip_fraction | 0.307 | +| clip_range | 0.0727 | +| entropy_loss | -7.18 | +| explained_variance | 0.215 | +| learning_rate | 4.78e-05 | +| loss | -0.0271 | +| n_updates | 33876 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000158 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1419 | +| iterations | 4516 | +| time_elapsed | 6515 | +| total_timesteps | 9248768 | +| train/ | | +| approx_kl | 0.011145255 | +| clip_fraction | 0.313 | +| clip_range | 0.0727 | +| entropy_loss | -7.12 | +| explained_variance | 0.249 | +| learning_rate | 4.78e-05 | +| loss | -0.0338 | +| n_updates | 33880 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000177 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1419 | +| iterations | 4517 | +| time_elapsed | 6517 | +| total_timesteps | 9250816 | +| train/ | | +| approx_kl | 0.011232716 | +| clip_fraction | 0.319 | +| clip_range | 0.0727 | +| entropy_loss | -7.19 | +| explained_variance | 0.524 | +| learning_rate | 4.78e-05 | +| loss | -0.034 | +| n_updates | 33884 | +| policy_gradient_loss | -0.0213 | +| value_loss | 6.89e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1419 | +| iterations | 4518 | +| time_elapsed | 6518 | +| total_timesteps | 9252864 | +| train/ | | +| approx_kl | 0.010507848 | +| clip_fraction | 0.308 | +| clip_range | 0.0727 | +| entropy_loss | -7.16 | +| explained_variance | 0.455 | +| learning_rate | 4.78e-05 | +| loss | -0.0244 | +| n_updates | 33888 | +| policy_gradient_loss | -0.0183 | +| value_loss | 9.41e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1419 | +| iterations | 4519 | +| time_elapsed | 6520 | +| total_timesteps | 9254912 | +| train/ | | +| approx_kl | 0.009352515 | +| clip_fraction | 0.285 | +| clip_range | 0.0727 | +| entropy_loss | -7.17 | +| explained_variance | 0.279 | +| learning_rate | 4.78e-05 | +| loss | -0.0321 | +| n_updates | 33892 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000191 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1419 | +| iterations | 4520 | +| time_elapsed | 6521 | +| total_timesteps | 9256960 | +| train/ | | +| approx_kl | 0.011195343 | +| clip_fraction | 0.28 | +| clip_range | 0.0727 | +| entropy_loss | -6.88 | +| explained_variance | 0.385 | +| learning_rate | 4.78e-05 | +| loss | -0.0324 | +| n_updates | 33896 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000204 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1419 | +| iterations | 4521 | +| time_elapsed | 6522 | +| total_timesteps | 9259008 | +| train/ | | +| approx_kl | 0.008511635 | +| clip_fraction | 0.313 | +| clip_range | 0.0727 | +| entropy_loss | -7.49 | +| explained_variance | -0.171 | +| learning_rate | 4.78e-05 | +| loss | -0.0344 | +| n_updates | 33900 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000119 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1419 | +| iterations | 4522 | +| time_elapsed | 6524 | +| total_timesteps | 9261056 | +| train/ | | +| approx_kl | 0.010857612 | +| clip_fraction | 0.323 | +| clip_range | 0.0727 | +| entropy_loss | -7.08 | +| explained_variance | 0.519 | +| learning_rate | 4.78e-05 | +| loss | -0.0337 | +| n_updates | 33904 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000107 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1419 | +| iterations | 4523 | +| time_elapsed | 6525 | +| total_timesteps | 9263104 | +| train/ | | +| approx_kl | 0.010451452 | +| clip_fraction | 0.296 | +| clip_range | 0.0727 | +| entropy_loss | -6.67 | +| explained_variance | 0.466 | +| learning_rate | 4.78e-05 | +| loss | -0.0293 | +| n_updates | 33908 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000203 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1419 | +| iterations | 4524 | +| time_elapsed | 6527 | +| total_timesteps | 9265152 | +| train/ | | +| approx_kl | 0.011675117 | +| clip_fraction | 0.335 | +| clip_range | 0.0727 | +| entropy_loss | -7.24 | +| explained_variance | -0.0513 | +| learning_rate | 4.78e-05 | +| loss | -0.0311 | +| n_updates | 33912 | +| policy_gradient_loss | -0.0215 | +| value_loss | 8.99e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1419 | +| iterations | 4525 | +| time_elapsed | 6528 | +| total_timesteps | 9267200 | +| train/ | | +| approx_kl | 0.01023412 | +| clip_fraction | 0.307 | +| clip_range | 0.0727 | +| entropy_loss | -7.25 | +| explained_variance | 0.295 | +| learning_rate | 4.78e-05 | +| loss | -0.0242 | +| n_updates | 33916 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.00015 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1419 | +| iterations | 4526 | +| time_elapsed | 6530 | +| total_timesteps | 9269248 | +| train/ | | +| approx_kl | 0.012570337 | +| clip_fraction | 0.329 | +| clip_range | 0.0727 | +| entropy_loss | -6.98 | +| explained_variance | 0.577 | +| learning_rate | 4.78e-05 | +| loss | -0.036 | +| n_updates | 33920 | +| policy_gradient_loss | -0.0219 | +| value_loss | 0.00011 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1419 | +| iterations | 4527 | +| time_elapsed | 6531 | +| total_timesteps | 9271296 | +| train/ | | +| approx_kl | 0.011726728 | +| clip_fraction | 0.321 | +| clip_range | 0.0727 | +| entropy_loss | -7.25 | +| explained_variance | -0.087 | +| learning_rate | 4.78e-05 | +| loss | -0.0375 | +| n_updates | 33924 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000214 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1419 | +| iterations | 4528 | +| time_elapsed | 6533 | +| total_timesteps | 9273344 | +| train/ | | +| approx_kl | 0.009782566 | +| clip_fraction | 0.306 | +| clip_range | 0.0727 | +| entropy_loss | -6.88 | +| explained_variance | 0.482 | +| learning_rate | 4.78e-05 | +| loss | -0.0324 | +| n_updates | 33928 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1419 | +| iterations | 4529 | +| time_elapsed | 6534 | +| total_timesteps | 9275392 | +| train/ | | +| approx_kl | 0.011603746 | +| clip_fraction | 0.34 | +| clip_range | 0.0727 | +| entropy_loss | -7.2 | +| explained_variance | 0.53 | +| learning_rate | 4.78e-05 | +| loss | -0.0388 | +| n_updates | 33932 | +| policy_gradient_loss | -0.0235 | +| value_loss | 6.2e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1419 | +| iterations | 4530 | +| time_elapsed | 6535 | +| total_timesteps | 9277440 | +| train/ | | +| approx_kl | 0.011611648 | +| clip_fraction | 0.287 | +| clip_range | 0.0727 | +| entropy_loss | -7.2 | +| explained_variance | -0.289 | +| learning_rate | 4.78e-05 | +| loss | -0.0252 | +| n_updates | 33936 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1419 | +| iterations | 4531 | +| time_elapsed | 6537 | +| total_timesteps | 9279488 | +| train/ | | +| approx_kl | 0.010709699 | +| clip_fraction | 0.304 | +| clip_range | 0.0727 | +| entropy_loss | -6.4 | +| explained_variance | 0.349 | +| learning_rate | 4.78e-05 | +| loss | -0.0285 | +| n_updates | 33940 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000304 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1419 | +| iterations | 4532 | +| time_elapsed | 6538 | +| total_timesteps | 9281536 | +| train/ | | +| approx_kl | 0.010584025 | +| clip_fraction | 0.328 | +| clip_range | 0.0727 | +| entropy_loss | -6.96 | +| explained_variance | 0.473 | +| learning_rate | 4.78e-05 | +| loss | -0.0337 | +| n_updates | 33944 | +| policy_gradient_loss | -0.0213 | +| value_loss | 8.6e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1419 | +| iterations | 4533 | +| time_elapsed | 6540 | +| total_timesteps | 9283584 | +| train/ | | +| approx_kl | 0.0103079695 | +| clip_fraction | 0.321 | +| clip_range | 0.0727 | +| entropy_loss | -7.49 | +| explained_variance | -0.292 | +| learning_rate | 4.78e-05 | +| loss | -0.0313 | +| n_updates | 33948 | +| policy_gradient_loss | -0.0206 | +| value_loss | 8.39e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1419 | +| iterations | 4534 | +| time_elapsed | 6541 | +| total_timesteps | 9285632 | +| train/ | | +| approx_kl | 0.009877378 | +| clip_fraction | 0.267 | +| clip_range | 0.0727 | +| entropy_loss | -7.02 | +| explained_variance | 0.397 | +| learning_rate | 4.78e-05 | +| loss | -0.0256 | +| n_updates | 33952 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000189 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1419 | +| iterations | 4535 | +| time_elapsed | 6542 | +| total_timesteps | 9287680 | +| train/ | | +| approx_kl | 0.008811697 | +| clip_fraction | 0.296 | +| clip_range | 0.0727 | +| entropy_loss | -7.09 | +| explained_variance | 0.409 | +| learning_rate | 4.78e-05 | +| loss | -0.0332 | +| n_updates | 33956 | +| policy_gradient_loss | -0.0201 | +| value_loss | 9.09e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1419 | +| iterations | 4536 | +| time_elapsed | 6544 | +| total_timesteps | 9289728 | +| train/ | | +| approx_kl | 0.010019676 | +| clip_fraction | 0.31 | +| clip_range | 0.0727 | +| entropy_loss | -7.45 | +| explained_variance | -0.0254 | +| learning_rate | 4.78e-05 | +| loss | -0.029 | +| n_updates | 33960 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.0002 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1419 | +| iterations | 4537 | +| time_elapsed | 6545 | +| total_timesteps | 9291776 | +| train/ | | +| approx_kl | 0.010135384 | +| clip_fraction | 0.319 | +| clip_range | 0.0727 | +| entropy_loss | -7.49 | +| explained_variance | -0.142 | +| learning_rate | 4.78e-05 | +| loss | -0.0331 | +| n_updates | 33964 | +| policy_gradient_loss | -0.0206 | +| value_loss | 9.25e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1419 | +| iterations | 4538 | +| time_elapsed | 6547 | +| total_timesteps | 9293824 | +| train/ | | +| approx_kl | 0.010868599 | +| clip_fraction | 0.304 | +| clip_range | 0.0727 | +| entropy_loss | -6.99 | +| explained_variance | 0.246 | +| learning_rate | 4.78e-05 | +| loss | -0.0298 | +| n_updates | 33968 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000164 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1419 | +| iterations | 4539 | +| time_elapsed | 6548 | +| total_timesteps | 9295872 | +| train/ | | +| approx_kl | 0.010912371 | +| clip_fraction | 0.315 | +| clip_range | 0.0727 | +| entropy_loss | -6.7 | +| explained_variance | 0.591 | +| learning_rate | 4.78e-05 | +| loss | -0.027 | +| n_updates | 33972 | +| policy_gradient_loss | -0.0189 | +| value_loss | 9.15e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1419 | +| iterations | 4540 | +| time_elapsed | 6550 | +| total_timesteps | 9297920 | +| train/ | | +| approx_kl | 0.010565683 | +| clip_fraction | 0.287 | +| clip_range | 0.0727 | +| entropy_loss | -7.07 | +| explained_variance | 0.358 | +| learning_rate | 4.78e-05 | +| loss | -0.0313 | +| n_updates | 33976 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000267 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1419 | +| iterations | 4541 | +| time_elapsed | 6551 | +| total_timesteps | 9299968 | +| train/ | | +| approx_kl | 0.011240936 | +| clip_fraction | 0.289 | +| clip_range | 0.0727 | +| entropy_loss | -6.93 | +| explained_variance | 0.449 | +| learning_rate | 4.78e-05 | +| loss | -0.0305 | +| n_updates | 33980 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000155 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1419 | +| iterations | 4542 | +| time_elapsed | 6553 | +| total_timesteps | 9302016 | +| train/ | | +| approx_kl | 0.01147275 | +| clip_fraction | 0.296 | +| clip_range | 0.0727 | +| entropy_loss | -6.82 | +| explained_variance | 0.248 | +| learning_rate | 4.78e-05 | +| loss | -0.0335 | +| n_updates | 33984 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000206 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1419 | +| iterations | 4543 | +| time_elapsed | 6554 | +| total_timesteps | 9304064 | +| train/ | | +| approx_kl | 0.012289209 | +| clip_fraction | 0.336 | +| clip_range | 0.0727 | +| entropy_loss | -6.88 | +| explained_variance | 0.566 | +| learning_rate | 4.78e-05 | +| loss | -0.0344 | +| n_updates | 33988 | +| policy_gradient_loss | -0.0227 | +| value_loss | 9.51e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1419 | +| iterations | 4544 | +| time_elapsed | 6556 | +| total_timesteps | 9306112 | +| train/ | | +| approx_kl | 0.012553006 | +| clip_fraction | 0.323 | +| clip_range | 0.0727 | +| entropy_loss | -7.17 | +| explained_variance | 0.329 | +| learning_rate | 4.78e-05 | +| loss | -0.032 | +| n_updates | 33992 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1419 | +| iterations | 4545 | +| time_elapsed | 6557 | +| total_timesteps | 9308160 | +| train/ | | +| approx_kl | 0.010375338 | +| clip_fraction | 0.314 | +| clip_range | 0.0727 | +| entropy_loss | -7.25 | +| explained_variance | 0.164 | +| learning_rate | 4.78e-05 | +| loss | -0.0272 | +| n_updates | 33996 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000305 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1419 | +| iterations | 4546 | +| time_elapsed | 6558 | +| total_timesteps | 9310208 | +| train/ | | +| approx_kl | 0.0121290805 | +| clip_fraction | 0.337 | +| clip_range | 0.0727 | +| entropy_loss | -7.4 | +| explained_variance | -0.0141 | +| learning_rate | 4.78e-05 | +| loss | -0.0309 | +| n_updates | 34000 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000182 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1419 | +| iterations | 4547 | +| time_elapsed | 6560 | +| total_timesteps | 9312256 | +| train/ | | +| approx_kl | 0.011576246 | +| clip_fraction | 0.337 | +| clip_range | 0.0727 | +| entropy_loss | -7.27 | +| explained_variance | 0.488 | +| learning_rate | 4.78e-05 | +| loss | -0.0401 | +| n_updates | 34004 | +| policy_gradient_loss | -0.0237 | +| value_loss | 9.19e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1419 | +| iterations | 4548 | +| time_elapsed | 6561 | +| total_timesteps | 9314304 | +| train/ | | +| approx_kl | 0.0097996555 | +| clip_fraction | 0.297 | +| clip_range | 0.0727 | +| entropy_loss | -7.14 | +| explained_variance | 0.327 | +| learning_rate | 4.78e-05 | +| loss | -0.0311 | +| n_updates | 34008 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000135 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1419 | +| iterations | 4549 | +| time_elapsed | 6563 | +| total_timesteps | 9316352 | +| train/ | | +| approx_kl | 0.010632531 | +| clip_fraction | 0.298 | +| clip_range | 0.0727 | +| entropy_loss | -7.13 | +| explained_variance | 0.203 | +| learning_rate | 4.78e-05 | +| loss | -0.0347 | +| n_updates | 34012 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000239 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1419 | +| iterations | 4550 | +| time_elapsed | 6564 | +| total_timesteps | 9318400 | +| train/ | | +| approx_kl | 0.0101333335 | +| clip_fraction | 0.291 | +| clip_range | 0.0727 | +| entropy_loss | -6.56 | +| explained_variance | 0.614 | +| learning_rate | 4.78e-05 | +| loss | -0.0261 | +| n_updates | 34016 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000173 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1419 | +| iterations | 4551 | +| time_elapsed | 6566 | +| total_timesteps | 9320448 | +| train/ | | +| approx_kl | 0.010709748 | +| clip_fraction | 0.338 | +| clip_range | 0.0727 | +| entropy_loss | -7.33 | +| explained_variance | -0.084 | +| learning_rate | 4.78e-05 | +| loss | -0.0326 | +| n_updates | 34020 | +| policy_gradient_loss | -0.0224 | +| value_loss | 9.51e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1419 | +| iterations | 4552 | +| time_elapsed | 6567 | +| total_timesteps | 9322496 | +| train/ | | +| approx_kl | 0.011053514 | +| clip_fraction | 0.311 | +| clip_range | 0.0727 | +| entropy_loss | -7.06 | +| explained_variance | 0.237 | +| learning_rate | 4.78e-05 | +| loss | -0.035 | +| n_updates | 34024 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.0002 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1419 | +| iterations | 4553 | +| time_elapsed | 6569 | +| total_timesteps | 9324544 | +| train/ | | +| approx_kl | 0.009358708 | +| clip_fraction | 0.313 | +| clip_range | 0.0727 | +| entropy_loss | -6.81 | +| explained_variance | 0.308 | +| learning_rate | 4.78e-05 | +| loss | -0.0328 | +| n_updates | 34028 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000235 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1419 | +| iterations | 4554 | +| time_elapsed | 6570 | +| total_timesteps | 9326592 | +| train/ | | +| approx_kl | 0.009449487 | +| clip_fraction | 0.292 | +| clip_range | 0.0727 | +| entropy_loss | -6.66 | +| explained_variance | 0.675 | +| learning_rate | 4.78e-05 | +| loss | -0.0306 | +| n_updates | 34032 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000125 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1419 | +| iterations | 4555 | +| time_elapsed | 6572 | +| total_timesteps | 9328640 | +| train/ | | +| approx_kl | 0.010867845 | +| clip_fraction | 0.301 | +| clip_range | 0.0727 | +| entropy_loss | -7.15 | +| explained_variance | 0.198 | +| learning_rate | 4.78e-05 | +| loss | -0.0355 | +| n_updates | 34036 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.00031 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1419 | +| iterations | 4556 | +| time_elapsed | 6573 | +| total_timesteps | 9330688 | +| train/ | | +| approx_kl | 0.010508877 | +| clip_fraction | 0.327 | +| clip_range | 0.0727 | +| entropy_loss | -7.14 | +| explained_variance | 0.314 | +| learning_rate | 4.78e-05 | +| loss | -0.0401 | +| n_updates | 34040 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.00017 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1419 | +| iterations | 4557 | +| time_elapsed | 6574 | +| total_timesteps | 9332736 | +| train/ | | +| approx_kl | 0.012903237 | +| clip_fraction | 0.331 | +| clip_range | 0.0727 | +| entropy_loss | -7.39 | +| explained_variance | -0.0887 | +| learning_rate | 4.78e-05 | +| loss | -0.0371 | +| n_updates | 34044 | +| policy_gradient_loss | -0.0222 | +| value_loss | 0.000156 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1419 | +| iterations | 4558 | +| time_elapsed | 6576 | +| total_timesteps | 9334784 | +| train/ | | +| approx_kl | 0.009241828 | +| clip_fraction | 0.29 | +| clip_range | 0.0727 | +| entropy_loss | -7.29 | +| explained_variance | 0.279 | +| learning_rate | 4.78e-05 | +| loss | -0.0308 | +| n_updates | 34048 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000152 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1419 | +| iterations | 4559 | +| time_elapsed | 6577 | +| total_timesteps | 9336832 | +| train/ | | +| approx_kl | 0.010639703 | +| clip_fraction | 0.313 | +| clip_range | 0.0727 | +| entropy_loss | -7.41 | +| explained_variance | -0.00469 | +| learning_rate | 4.78e-05 | +| loss | -0.0368 | +| n_updates | 34052 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000164 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1419 | +| iterations | 4560 | +| time_elapsed | 6579 | +| total_timesteps | 9338880 | +| train/ | | +| approx_kl | 0.011655118 | +| clip_fraction | 0.286 | +| clip_range | 0.0727 | +| entropy_loss | -6.68 | +| explained_variance | 0.448 | +| learning_rate | 4.78e-05 | +| loss | -0.0251 | +| n_updates | 34056 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000281 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1419 | +| iterations | 4561 | +| time_elapsed | 6580 | +| total_timesteps | 9340928 | +| train/ | | +| approx_kl | 0.009836758 | +| clip_fraction | 0.33 | +| clip_range | 0.0727 | +| entropy_loss | -6.71 | +| explained_variance | 0.469 | +| learning_rate | 4.78e-05 | +| loss | -0.0348 | +| n_updates | 34060 | +| policy_gradient_loss | -0.022 | +| value_loss | 0.000146 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1419 | +| iterations | 4562 | +| time_elapsed | 6581 | +| total_timesteps | 9342976 | +| train/ | | +| approx_kl | 0.014111374 | +| clip_fraction | 0.333 | +| clip_range | 0.0727 | +| entropy_loss | -7.09 | +| explained_variance | 0.21 | +| learning_rate | 4.78e-05 | +| loss | -0.0369 | +| n_updates | 34064 | +| policy_gradient_loss | -0.0219 | +| value_loss | 0.000167 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1419 | +| iterations | 4563 | +| time_elapsed | 6583 | +| total_timesteps | 9345024 | +| train/ | | +| approx_kl | 0.012364155 | +| clip_fraction | 0.35 | +| clip_range | 0.0727 | +| entropy_loss | -7.07 | +| explained_variance | 0.348 | +| learning_rate | 4.78e-05 | +| loss | -0.0361 | +| n_updates | 34068 | +| policy_gradient_loss | -0.0224 | +| value_loss | 0.00011 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1419 | +| iterations | 4564 | +| time_elapsed | 6584 | +| total_timesteps | 9347072 | +| train/ | | +| approx_kl | 0.011011141 | +| clip_fraction | 0.297 | +| clip_range | 0.0727 | +| entropy_loss | -7 | +| explained_variance | 0.484 | +| learning_rate | 4.78e-05 | +| loss | -0.0331 | +| n_updates | 34072 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000145 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1419 | +| iterations | 4565 | +| time_elapsed | 6586 | +| total_timesteps | 9349120 | +| train/ | | +| approx_kl | 0.011781451 | +| clip_fraction | 0.32 | +| clip_range | 0.0727 | +| entropy_loss | -7.17 | +| explained_variance | 0.327 | +| learning_rate | 4.78e-05 | +| loss | -0.0336 | +| n_updates | 34076 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000146 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1419 | +| iterations | 4566 | +| time_elapsed | 6587 | +| total_timesteps | 9351168 | +| train/ | | +| approx_kl | 0.0132840015 | +| clip_fraction | 0.292 | +| clip_range | 0.0727 | +| entropy_loss | -6.95 | +| explained_variance | 0.333 | +| learning_rate | 4.78e-05 | +| loss | -0.0266 | +| n_updates | 34080 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000262 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1419 | +| iterations | 4567 | +| time_elapsed | 6589 | +| total_timesteps | 9353216 | +| train/ | | +| approx_kl | 0.010535485 | +| clip_fraction | 0.321 | +| clip_range | 0.0727 | +| entropy_loss | -7.13 | +| explained_variance | 0.338 | +| learning_rate | 4.78e-05 | +| loss | -0.0337 | +| n_updates | 34084 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000164 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1419 | +| iterations | 4568 | +| time_elapsed | 6590 | +| total_timesteps | 9355264 | +| train/ | | +| approx_kl | 0.011834412 | +| clip_fraction | 0.33 | +| clip_range | 0.0727 | +| entropy_loss | -7.35 | +| explained_variance | -0.0626 | +| learning_rate | 4.78e-05 | +| loss | -0.0362 | +| n_updates | 34088 | +| policy_gradient_loss | -0.022 | +| value_loss | 0.000117 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1419 | +| iterations | 4569 | +| time_elapsed | 6592 | +| total_timesteps | 9357312 | +| train/ | | +| approx_kl | 0.01103021 | +| clip_fraction | 0.295 | +| clip_range | 0.0727 | +| entropy_loss | -7.07 | +| explained_variance | 0.56 | +| learning_rate | 4.78e-05 | +| loss | -0.0318 | +| n_updates | 34092 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000121 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1419 | +| iterations | 4570 | +| time_elapsed | 6593 | +| total_timesteps | 9359360 | +| train/ | | +| approx_kl | 0.013561654 | +| clip_fraction | 0.316 | +| clip_range | 0.0727 | +| entropy_loss | -7.29 | +| explained_variance | 0.162 | +| learning_rate | 4.78e-05 | +| loss | -0.037 | +| n_updates | 34096 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000106 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1419 | +| iterations | 4571 | +| time_elapsed | 6595 | +| total_timesteps | 9361408 | +| train/ | | +| approx_kl | 0.010557085 | +| clip_fraction | 0.303 | +| clip_range | 0.0727 | +| entropy_loss | -7.07 | +| explained_variance | 0.316 | +| learning_rate | 4.78e-05 | +| loss | -0.0301 | +| n_updates | 34100 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000222 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1419 | +| iterations | 4572 | +| time_elapsed | 6596 | +| total_timesteps | 9363456 | +| train/ | | +| approx_kl | 0.012272434 | +| clip_fraction | 0.319 | +| clip_range | 0.0727 | +| entropy_loss | -6.25 | +| explained_variance | 0.755 | +| learning_rate | 4.78e-05 | +| loss | -0.0249 | +| n_updates | 34104 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000126 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.43e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1419 | +| iterations | 4573 | +| time_elapsed | 6597 | +| total_timesteps | 9365504 | +| train/ | | +| approx_kl | 0.010195099 | +| clip_fraction | 0.297 | +| clip_range | 0.0727 | +| entropy_loss | -7.09 | +| explained_variance | -0.0195 | +| learning_rate | 4.78e-05 | +| loss | -0.0265 | +| n_updates | 34108 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000202 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1419 | +| iterations | 4574 | +| time_elapsed | 6599 | +| total_timesteps | 9367552 | +| train/ | | +| approx_kl | 0.01285932 | +| clip_fraction | 0.319 | +| clip_range | 0.0727 | +| entropy_loss | -6.86 | +| explained_variance | 0.333 | +| learning_rate | 4.78e-05 | +| loss | -0.0305 | +| n_updates | 34112 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000131 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1419 | +| iterations | 4575 | +| time_elapsed | 6600 | +| total_timesteps | 9369600 | +| train/ | | +| approx_kl | 0.011395425 | +| clip_fraction | 0.303 | +| clip_range | 0.0727 | +| entropy_loss | -6.85 | +| explained_variance | 0.538 | +| learning_rate | 4.78e-05 | +| loss | -0.025 | +| n_updates | 34116 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.00016 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1419 | +| iterations | 4576 | +| time_elapsed | 6602 | +| total_timesteps | 9371648 | +| train/ | | +| approx_kl | 0.0129949935 | +| clip_fraction | 0.318 | +| clip_range | 0.0727 | +| entropy_loss | -7.11 | +| explained_variance | -0.205 | +| learning_rate | 4.78e-05 | +| loss | -0.0264 | +| n_updates | 34120 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000168 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1419 | +| iterations | 4577 | +| time_elapsed | 6603 | +| total_timesteps | 9373696 | +| train/ | | +| approx_kl | 0.010786369 | +| clip_fraction | 0.316 | +| clip_range | 0.0727 | +| entropy_loss | -7.34 | +| explained_variance | -0.00588 | +| learning_rate | 4.78e-05 | +| loss | -0.0332 | +| n_updates | 34124 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000188 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1419 | +| iterations | 4578 | +| time_elapsed | 6605 | +| total_timesteps | 9375744 | +| train/ | | +| approx_kl | 0.009564605 | +| clip_fraction | 0.3 | +| clip_range | 0.0727 | +| entropy_loss | -7.36 | +| explained_variance | -0.186 | +| learning_rate | 4.78e-05 | +| loss | -0.0319 | +| n_updates | 34128 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000172 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1419 | +| iterations | 4579 | +| time_elapsed | 6606 | +| total_timesteps | 9377792 | +| train/ | | +| approx_kl | 0.012352057 | +| clip_fraction | 0.326 | +| clip_range | 0.0727 | +| entropy_loss | -7.12 | +| explained_variance | 0.0917 | +| learning_rate | 4.78e-05 | +| loss | -0.0336 | +| n_updates | 34132 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000187 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1419 | +| iterations | 4580 | +| time_elapsed | 6607 | +| total_timesteps | 9379840 | +| train/ | | +| approx_kl | 0.010379024 | +| clip_fraction | 0.332 | +| clip_range | 0.0727 | +| entropy_loss | -7.32 | +| explained_variance | -0.082 | +| learning_rate | 4.78e-05 | +| loss | -0.0408 | +| n_updates | 34136 | +| policy_gradient_loss | -0.0221 | +| value_loss | 7.83e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1419 | +| iterations | 4581 | +| time_elapsed | 6609 | +| total_timesteps | 9381888 | +| train/ | | +| approx_kl | 0.0128954165 | +| clip_fraction | 0.297 | +| clip_range | 0.0727 | +| entropy_loss | -7.15 | +| explained_variance | 0.292 | +| learning_rate | 4.78e-05 | +| loss | -0.0325 | +| n_updates | 34140 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.0001 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1419 | +| iterations | 4582 | +| time_elapsed | 6610 | +| total_timesteps | 9383936 | +| train/ | | +| approx_kl | 0.01232187 | +| clip_fraction | 0.302 | +| clip_range | 0.0727 | +| entropy_loss | -7.23 | +| explained_variance | 0.224 | +| learning_rate | 4.78e-05 | +| loss | -0.0264 | +| n_updates | 34144 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000211 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1419 | +| iterations | 4583 | +| time_elapsed | 6612 | +| total_timesteps | 9385984 | +| train/ | | +| approx_kl | 0.011734845 | +| clip_fraction | 0.34 | +| clip_range | 0.0727 | +| entropy_loss | -7.22 | +| explained_variance | 0.423 | +| learning_rate | 4.78e-05 | +| loss | -0.0352 | +| n_updates | 34148 | +| policy_gradient_loss | -0.0219 | +| value_loss | 8.85e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1419 | +| iterations | 4584 | +| time_elapsed | 6613 | +| total_timesteps | 9388032 | +| train/ | | +| approx_kl | 0.009701852 | +| clip_fraction | 0.323 | +| clip_range | 0.0727 | +| entropy_loss | -7.04 | +| explained_variance | 0.654 | +| learning_rate | 4.78e-05 | +| loss | -0.039 | +| n_updates | 34152 | +| policy_gradient_loss | -0.0223 | +| value_loss | 5.94e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1419 | +| iterations | 4585 | +| time_elapsed | 6615 | +| total_timesteps | 9390080 | +| train/ | | +| approx_kl | 0.011304811 | +| clip_fraction | 0.308 | +| clip_range | 0.0727 | +| entropy_loss | -6.72 | +| explained_variance | 0.598 | +| learning_rate | 4.78e-05 | +| loss | -0.0298 | +| n_updates | 34156 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000122 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1419 | +| iterations | 4586 | +| time_elapsed | 6616 | +| total_timesteps | 9392128 | +| train/ | | +| approx_kl | 0.01193719 | +| clip_fraction | 0.296 | +| clip_range | 0.0727 | +| entropy_loss | -7.13 | +| explained_variance | 0.349 | +| learning_rate | 4.78e-05 | +| loss | -0.0303 | +| n_updates | 34160 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000145 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1419 | +| iterations | 4587 | +| time_elapsed | 6617 | +| total_timesteps | 9394176 | +| train/ | | +| approx_kl | 0.013049986 | +| clip_fraction | 0.324 | +| clip_range | 0.0727 | +| entropy_loss | -6.93 | +| explained_variance | 0.526 | +| learning_rate | 4.78e-05 | +| loss | -0.0285 | +| n_updates | 34164 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000124 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1419 | +| iterations | 4588 | +| time_elapsed | 6619 | +| total_timesteps | 9396224 | +| train/ | | +| approx_kl | 0.013003634 | +| clip_fraction | 0.317 | +| clip_range | 0.0727 | +| entropy_loss | -7.06 | +| explained_variance | 0.404 | +| learning_rate | 4.78e-05 | +| loss | -0.0294 | +| n_updates | 34168 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000114 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1419 | +| iterations | 4589 | +| time_elapsed | 6620 | +| total_timesteps | 9398272 | +| train/ | | +| approx_kl | 0.012952866 | +| clip_fraction | 0.318 | +| clip_range | 0.0727 | +| entropy_loss | -6.77 | +| explained_variance | 0.724 | +| learning_rate | 4.78e-05 | +| loss | -0.0385 | +| n_updates | 34172 | +| policy_gradient_loss | -0.0216 | +| value_loss | 8.29e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1419 | +| iterations | 4590 | +| time_elapsed | 6622 | +| total_timesteps | 9400320 | +| train/ | | +| approx_kl | 0.012016974 | +| clip_fraction | 0.296 | +| clip_range | 0.0727 | +| entropy_loss | -7.18 | +| explained_variance | -0.0333 | +| learning_rate | 4.78e-05 | +| loss | -0.0318 | +| n_updates | 34176 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000123 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1419 | +| iterations | 4591 | +| time_elapsed | 6623 | +| total_timesteps | 9402368 | +| train/ | | +| approx_kl | 0.010933106 | +| clip_fraction | 0.309 | +| clip_range | 0.0726 | +| entropy_loss | -6.89 | +| explained_variance | 0.545 | +| learning_rate | 4.78e-05 | +| loss | -0.0342 | +| n_updates | 34180 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000143 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1419 | +| iterations | 4592 | +| time_elapsed | 6625 | +| total_timesteps | 9404416 | +| train/ | | +| approx_kl | 0.010859268 | +| clip_fraction | 0.296 | +| clip_range | 0.0726 | +| entropy_loss | -7.24 | +| explained_variance | -0.0156 | +| learning_rate | 4.78e-05 | +| loss | -0.0301 | +| n_updates | 34184 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000253 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1419 | +| iterations | 4593 | +| time_elapsed | 6626 | +| total_timesteps | 9406464 | +| train/ | | +| approx_kl | 0.0119417105 | +| clip_fraction | 0.31 | +| clip_range | 0.0726 | +| entropy_loss | -7.4 | +| explained_variance | -0.134 | +| learning_rate | 4.78e-05 | +| loss | -0.0391 | +| n_updates | 34188 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000124 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1419 | +| iterations | 4594 | +| time_elapsed | 6627 | +| total_timesteps | 9408512 | +| train/ | | +| approx_kl | 0.009844387 | +| clip_fraction | 0.316 | +| clip_range | 0.0726 | +| entropy_loss | -6.93 | +| explained_variance | 0.364 | +| learning_rate | 4.78e-05 | +| loss | -0.0339 | +| n_updates | 34192 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000201 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1419 | +| iterations | 4595 | +| time_elapsed | 6629 | +| total_timesteps | 9410560 | +| train/ | | +| approx_kl | 0.010216763 | +| clip_fraction | 0.33 | +| clip_range | 0.0726 | +| entropy_loss | -7.24 | +| explained_variance | 0.214 | +| learning_rate | 4.78e-05 | +| loss | -0.0308 | +| n_updates | 34196 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000288 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1419 | +| iterations | 4596 | +| time_elapsed | 6630 | +| total_timesteps | 9412608 | +| train/ | | +| approx_kl | 0.009813603 | +| clip_fraction | 0.303 | +| clip_range | 0.0726 | +| entropy_loss | -6.87 | +| explained_variance | 0.162 | +| learning_rate | 4.78e-05 | +| loss | -0.0306 | +| n_updates | 34200 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000245 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.388 | +| time/ | | +| fps | 1419 | +| iterations | 4597 | +| time_elapsed | 6632 | +| total_timesteps | 9414656 | +| train/ | | +| approx_kl | 0.011711064 | +| clip_fraction | 0.331 | +| clip_range | 0.0726 | +| entropy_loss | -7.19 | +| explained_variance | 0.138 | +| learning_rate | 4.78e-05 | +| loss | -0.0333 | +| n_updates | 34204 | +| policy_gradient_loss | -0.0225 | +| value_loss | 0.000164 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.39 | +| time/ | | +| fps | 1419 | +| iterations | 4598 | +| time_elapsed | 6633 | +| total_timesteps | 9416704 | +| train/ | | +| approx_kl | 0.012194488 | +| clip_fraction | 0.321 | +| clip_range | 0.0726 | +| entropy_loss | -6.54 | +| explained_variance | 0.472 | +| learning_rate | 4.78e-05 | +| loss | -0.0333 | +| n_updates | 34208 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000215 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.388 | +| time/ | | +| fps | 1419 | +| iterations | 4599 | +| time_elapsed | 6635 | +| total_timesteps | 9418752 | +| train/ | | +| approx_kl | 0.012006554 | +| clip_fraction | 0.363 | +| clip_range | 0.0726 | +| entropy_loss | -6.92 | +| explained_variance | 0.387 | +| learning_rate | 4.78e-05 | +| loss | -0.042 | +| n_updates | 34212 | +| policy_gradient_loss | -0.024 | +| value_loss | 6.73e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.39 | +| time/ | | +| fps | 1419 | +| iterations | 4600 | +| time_elapsed | 6636 | +| total_timesteps | 9420800 | +| train/ | | +| approx_kl | 0.012063907 | +| clip_fraction | 0.337 | +| clip_range | 0.0726 | +| entropy_loss | -6.97 | +| explained_variance | 0.364 | +| learning_rate | 4.78e-05 | +| loss | -0.0346 | +| n_updates | 34216 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000156 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.39 | +| time/ | | +| fps | 1419 | +| iterations | 4601 | +| time_elapsed | 6638 | +| total_timesteps | 9422848 | +| train/ | | +| approx_kl | 0.011422866 | +| clip_fraction | 0.303 | +| clip_range | 0.0726 | +| entropy_loss | -7.09 | +| explained_variance | 0.0974 | +| learning_rate | 4.78e-05 | +| loss | -0.0306 | +| n_updates | 34220 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000149 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.39 | +| time/ | | +| fps | 1419 | +| iterations | 4602 | +| time_elapsed | 6639 | +| total_timesteps | 9424896 | +| train/ | | +| approx_kl | 0.012388708 | +| clip_fraction | 0.314 | +| clip_range | 0.0726 | +| entropy_loss | -7.23 | +| explained_variance | 0.303 | +| learning_rate | 4.78e-05 | +| loss | -0.0317 | +| n_updates | 34224 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000135 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.388 | +| time/ | | +| fps | 1419 | +| iterations | 4603 | +| time_elapsed | 6640 | +| total_timesteps | 9426944 | +| train/ | | +| approx_kl | 0.012413235 | +| clip_fraction | 0.331 | +| clip_range | 0.0726 | +| entropy_loss | -7.47 | +| explained_variance | -0.241 | +| learning_rate | 4.78e-05 | +| loss | -0.0319 | +| n_updates | 34228 | +| policy_gradient_loss | -0.0231 | +| value_loss | 0.000106 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.395 | +| time/ | | +| fps | 1419 | +| iterations | 4604 | +| time_elapsed | 6642 | +| total_timesteps | 9428992 | +| train/ | | +| approx_kl | 0.009937816 | +| clip_fraction | 0.289 | +| clip_range | 0.0726 | +| entropy_loss | -6.92 | +| explained_variance | 0.39 | +| learning_rate | 4.78e-05 | +| loss | -0.0186 | +| n_updates | 34232 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000207 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.394 | +| time/ | | +| fps | 1419 | +| iterations | 4605 | +| time_elapsed | 6643 | +| total_timesteps | 9431040 | +| train/ | | +| approx_kl | 0.011373222 | +| clip_fraction | 0.306 | +| clip_range | 0.0726 | +| entropy_loss | -6.52 | +| explained_variance | 0.298 | +| learning_rate | 4.78e-05 | +| loss | -0.0267 | +| n_updates | 34236 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000343 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.395 | +| time/ | | +| fps | 1419 | +| iterations | 4606 | +| time_elapsed | 6645 | +| total_timesteps | 9433088 | +| train/ | | +| approx_kl | 0.013623174 | +| clip_fraction | 0.339 | +| clip_range | 0.0726 | +| entropy_loss | -6.89 | +| explained_variance | 0.221 | +| learning_rate | 4.78e-05 | +| loss | -0.0393 | +| n_updates | 34240 | +| policy_gradient_loss | -0.0235 | +| value_loss | 0.000173 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.395 | +| time/ | | +| fps | 1419 | +| iterations | 4607 | +| time_elapsed | 6646 | +| total_timesteps | 9435136 | +| train/ | | +| approx_kl | 0.0127634555 | +| clip_fraction | 0.333 | +| clip_range | 0.0726 | +| entropy_loss | -7.05 | +| explained_variance | 0.14 | +| learning_rate | 4.78e-05 | +| loss | -0.0333 | +| n_updates | 34244 | +| policy_gradient_loss | -0.0219 | +| value_loss | 0.000166 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.394 | +| time/ | | +| fps | 1419 | +| iterations | 4608 | +| time_elapsed | 6647 | +| total_timesteps | 9437184 | +| train/ | | +| approx_kl | 0.01018334 | +| clip_fraction | 0.313 | +| clip_range | 0.0726 | +| entropy_loss | -7.25 | +| explained_variance | 0.333 | +| learning_rate | 4.78e-05 | +| loss | -0.0269 | +| n_updates | 34248 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000131 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.394 | +| time/ | | +| fps | 1419 | +| iterations | 4609 | +| time_elapsed | 6649 | +| total_timesteps | 9439232 | +| train/ | | +| approx_kl | 0.009797694 | +| clip_fraction | 0.297 | +| clip_range | 0.0726 | +| entropy_loss | -6.98 | +| explained_variance | 0.42 | +| learning_rate | 4.78e-05 | +| loss | -0.031 | +| n_updates | 34252 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000188 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.393 | +| time/ | | +| fps | 1419 | +| iterations | 4610 | +| time_elapsed | 6650 | +| total_timesteps | 9441280 | +| train/ | | +| approx_kl | 0.012794154 | +| clip_fraction | 0.3 | +| clip_range | 0.0726 | +| entropy_loss | -6.51 | +| explained_variance | 0.412 | +| learning_rate | 4.78e-05 | +| loss | -0.0289 | +| n_updates | 34256 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000289 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.395 | +| time/ | | +| fps | 1419 | +| iterations | 4611 | +| time_elapsed | 6652 | +| total_timesteps | 9443328 | +| train/ | | +| approx_kl | 0.012794813 | +| clip_fraction | 0.354 | +| clip_range | 0.0726 | +| entropy_loss | -7.2 | +| explained_variance | -0.235 | +| learning_rate | 4.78e-05 | +| loss | -0.0366 | +| n_updates | 34260 | +| policy_gradient_loss | -0.0254 | +| value_loss | 8.7e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.395 | +| time/ | | +| fps | 1419 | +| iterations | 4612 | +| time_elapsed | 6653 | +| total_timesteps | 9445376 | +| train/ | | +| approx_kl | 0.014911765 | +| clip_fraction | 0.324 | +| clip_range | 0.0726 | +| entropy_loss | -6.98 | +| explained_variance | 0.425 | +| learning_rate | 4.78e-05 | +| loss | -0.0329 | +| n_updates | 34264 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.00016 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.395 | +| time/ | | +| fps | 1419 | +| iterations | 4613 | +| time_elapsed | 6654 | +| total_timesteps | 9447424 | +| train/ | | +| approx_kl | 0.011920488 | +| clip_fraction | 0.359 | +| clip_range | 0.0726 | +| entropy_loss | -7.31 | +| explained_variance | -0.183 | +| learning_rate | 4.78e-05 | +| loss | -0.0359 | +| n_updates | 34268 | +| policy_gradient_loss | -0.0224 | +| value_loss | 0.00015 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.393 | +| time/ | | +| fps | 1419 | +| iterations | 4614 | +| time_elapsed | 6656 | +| total_timesteps | 9449472 | +| train/ | | +| approx_kl | 0.011347357 | +| clip_fraction | 0.309 | +| clip_range | 0.0726 | +| entropy_loss | -7.48 | +| explained_variance | -0.0784 | +| learning_rate | 4.78e-05 | +| loss | -0.0274 | +| n_updates | 34272 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000142 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.394 | +| time/ | | +| fps | 1419 | +| iterations | 4615 | +| time_elapsed | 6657 | +| total_timesteps | 9451520 | +| train/ | | +| approx_kl | 0.009779219 | +| clip_fraction | 0.316 | +| clip_range | 0.0726 | +| entropy_loss | -6.93 | +| explained_variance | 0.362 | +| learning_rate | 4.78e-05 | +| loss | -0.0343 | +| n_updates | 34276 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000137 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.395 | +| time/ | | +| fps | 1419 | +| iterations | 4616 | +| time_elapsed | 6659 | +| total_timesteps | 9453568 | +| train/ | | +| approx_kl | 0.01290036 | +| clip_fraction | 0.317 | +| clip_range | 0.0726 | +| entropy_loss | -7 | +| explained_variance | 0.564 | +| learning_rate | 4.78e-05 | +| loss | -0.0378 | +| n_updates | 34280 | +| policy_gradient_loss | -0.0205 | +| value_loss | 9.13e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.395 | +| time/ | | +| fps | 1419 | +| iterations | 4617 | +| time_elapsed | 6660 | +| total_timesteps | 9455616 | +| train/ | | +| approx_kl | 0.011332957 | +| clip_fraction | 0.295 | +| clip_range | 0.0726 | +| entropy_loss | -6.78 | +| explained_variance | 0.357 | +| learning_rate | 4.78e-05 | +| loss | -0.0303 | +| n_updates | 34284 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000251 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.395 | +| time/ | | +| fps | 1419 | +| iterations | 4618 | +| time_elapsed | 6662 | +| total_timesteps | 9457664 | +| train/ | | +| approx_kl | 0.014739946 | +| clip_fraction | 0.308 | +| clip_range | 0.0726 | +| entropy_loss | -6.85 | +| explained_variance | 0.509 | +| learning_rate | 4.78e-05 | +| loss | -0.0328 | +| n_updates | 34288 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000122 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.394 | +| time/ | | +| fps | 1419 | +| iterations | 4619 | +| time_elapsed | 6663 | +| total_timesteps | 9459712 | +| train/ | | +| approx_kl | 0.011937611 | +| clip_fraction | 0.32 | +| clip_range | 0.0726 | +| entropy_loss | -7.42 | +| explained_variance | -0.146 | +| learning_rate | 4.78e-05 | +| loss | -0.0352 | +| n_updates | 34292 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.392 | +| time/ | | +| fps | 1419 | +| iterations | 4620 | +| time_elapsed | 6664 | +| total_timesteps | 9461760 | +| train/ | | +| approx_kl | 0.012075323 | +| clip_fraction | 0.314 | +| clip_range | 0.0726 | +| entropy_loss | -6.96 | +| explained_variance | 0.437 | +| learning_rate | 4.78e-05 | +| loss | -0.0322 | +| n_updates | 34296 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000168 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.386 | +| time/ | | +| fps | 1419 | +| iterations | 4621 | +| time_elapsed | 6666 | +| total_timesteps | 9463808 | +| train/ | | +| approx_kl | 0.012940569 | +| clip_fraction | 0.343 | +| clip_range | 0.0726 | +| entropy_loss | -7.1 | +| explained_variance | 0.396 | +| learning_rate | 4.78e-05 | +| loss | -0.0399 | +| n_updates | 34300 | +| policy_gradient_loss | -0.0224 | +| value_loss | 7.98e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.385 | +| time/ | | +| fps | 1419 | +| iterations | 4622 | +| time_elapsed | 6667 | +| total_timesteps | 9465856 | +| train/ | | +| approx_kl | 0.011872979 | +| clip_fraction | 0.286 | +| clip_range | 0.0726 | +| entropy_loss | -6.71 | +| explained_variance | 0.462 | +| learning_rate | 4.78e-05 | +| loss | -0.0258 | +| n_updates | 34304 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000236 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1419 | +| iterations | 4623 | +| time_elapsed | 6669 | +| total_timesteps | 9467904 | +| train/ | | +| approx_kl | 0.011544386 | +| clip_fraction | 0.321 | +| clip_range | 0.0726 | +| entropy_loss | -6.69 | +| explained_variance | 0.489 | +| learning_rate | 4.78e-05 | +| loss | -0.0375 | +| n_updates | 34308 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000212 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1419 | +| iterations | 4624 | +| time_elapsed | 6670 | +| total_timesteps | 9469952 | +| train/ | | +| approx_kl | 0.012126618 | +| clip_fraction | 0.334 | +| clip_range | 0.0726 | +| entropy_loss | -6.94 | +| explained_variance | 0.395 | +| learning_rate | 4.78e-05 | +| loss | -0.0231 | +| n_updates | 34312 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000123 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1419 | +| iterations | 4625 | +| time_elapsed | 6672 | +| total_timesteps | 9472000 | +| train/ | | +| approx_kl | 0.010925622 | +| clip_fraction | 0.34 | +| clip_range | 0.0726 | +| entropy_loss | -7.09 | +| explained_variance | 0.457 | +| learning_rate | 4.78e-05 | +| loss | -0.033 | +| n_updates | 34316 | +| policy_gradient_loss | -0.0217 | +| value_loss | 8.24e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1419 | +| iterations | 4626 | +| time_elapsed | 6673 | +| total_timesteps | 9474048 | +| train/ | | +| approx_kl | 0.011059545 | +| clip_fraction | 0.316 | +| clip_range | 0.0726 | +| entropy_loss | -7.02 | +| explained_variance | 0.2 | +| learning_rate | 4.78e-05 | +| loss | -0.035 | +| n_updates | 34320 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000176 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1419 | +| iterations | 4627 | +| time_elapsed | 6674 | +| total_timesteps | 9476096 | +| train/ | | +| approx_kl | 0.009809267 | +| clip_fraction | 0.321 | +| clip_range | 0.0726 | +| entropy_loss | -7.19 | +| explained_variance | 0.356 | +| learning_rate | 4.77e-05 | +| loss | -0.0242 | +| n_updates | 34324 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.00012 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1419 | +| iterations | 4628 | +| time_elapsed | 6676 | +| total_timesteps | 9478144 | +| train/ | | +| approx_kl | 0.00775202 | +| clip_fraction | 0.294 | +| clip_range | 0.0726 | +| entropy_loss | -6.94 | +| explained_variance | 0.28 | +| learning_rate | 4.77e-05 | +| loss | -0.0291 | +| n_updates | 34328 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000272 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1419 | +| iterations | 4629 | +| time_elapsed | 6677 | +| total_timesteps | 9480192 | +| train/ | | +| approx_kl | 0.008278901 | +| clip_fraction | 0.29 | +| clip_range | 0.0726 | +| entropy_loss | -7.06 | +| explained_variance | 0.405 | +| learning_rate | 4.77e-05 | +| loss | -0.0297 | +| n_updates | 34332 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000186 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1419 | +| iterations | 4630 | +| time_elapsed | 6679 | +| total_timesteps | 9482240 | +| train/ | | +| approx_kl | 0.007556563 | +| clip_fraction | 0.268 | +| clip_range | 0.0726 | +| entropy_loss | -6.46 | +| explained_variance | 0.388 | +| learning_rate | 4.77e-05 | +| loss | -0.0231 | +| n_updates | 34336 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000447 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1419 | +| iterations | 4631 | +| time_elapsed | 6680 | +| total_timesteps | 9484288 | +| train/ | | +| approx_kl | 0.011776957 | +| clip_fraction | 0.33 | +| clip_range | 0.0726 | +| entropy_loss | -6.72 | +| explained_variance | 0.495 | +| learning_rate | 4.77e-05 | +| loss | -0.0333 | +| n_updates | 34340 | +| policy_gradient_loss | -0.0228 | +| value_loss | 0.000103 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1419 | +| iterations | 4632 | +| time_elapsed | 6682 | +| total_timesteps | 9486336 | +| train/ | | +| approx_kl | 0.011046629 | +| clip_fraction | 0.316 | +| clip_range | 0.0726 | +| entropy_loss | -7.05 | +| explained_variance | 0.4 | +| learning_rate | 4.77e-05 | +| loss | -0.0315 | +| n_updates | 34344 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000135 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1419 | +| iterations | 4633 | +| time_elapsed | 6683 | +| total_timesteps | 9488384 | +| train/ | | +| approx_kl | 0.010243505 | +| clip_fraction | 0.319 | +| clip_range | 0.0726 | +| entropy_loss | -7.19 | +| explained_variance | 0.225 | +| learning_rate | 4.77e-05 | +| loss | -0.0311 | +| n_updates | 34348 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.00015 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1419 | +| iterations | 4634 | +| time_elapsed | 6684 | +| total_timesteps | 9490432 | +| train/ | | +| approx_kl | 0.010311795 | +| clip_fraction | 0.305 | +| clip_range | 0.0726 | +| entropy_loss | -6.9 | +| explained_variance | 0.377 | +| learning_rate | 4.77e-05 | +| loss | -0.0349 | +| n_updates | 34352 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000215 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1419 | +| iterations | 4635 | +| time_elapsed | 6686 | +| total_timesteps | 9492480 | +| train/ | | +| approx_kl | 0.010037502 | +| clip_fraction | 0.289 | +| clip_range | 0.0726 | +| entropy_loss | -7.26 | +| explained_variance | -0.0784 | +| learning_rate | 4.77e-05 | +| loss | -0.0308 | +| n_updates | 34356 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000178 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1419 | +| iterations | 4636 | +| time_elapsed | 6687 | +| total_timesteps | 9494528 | +| train/ | | +| approx_kl | 0.009586178 | +| clip_fraction | 0.314 | +| clip_range | 0.0726 | +| entropy_loss | -7.02 | +| explained_variance | 0.369 | +| learning_rate | 4.77e-05 | +| loss | -0.0271 | +| n_updates | 34360 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000177 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1419 | +| iterations | 4637 | +| time_elapsed | 6689 | +| total_timesteps | 9496576 | +| train/ | | +| approx_kl | 0.01330517 | +| clip_fraction | 0.324 | +| clip_range | 0.0726 | +| entropy_loss | -6.99 | +| explained_variance | 0.0781 | +| learning_rate | 4.77e-05 | +| loss | -0.0317 | +| n_updates | 34364 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000107 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1419 | +| iterations | 4638 | +| time_elapsed | 6690 | +| total_timesteps | 9498624 | +| train/ | | +| approx_kl | 0.012944205 | +| clip_fraction | 0.325 | +| clip_range | 0.0726 | +| entropy_loss | -7.12 | +| explained_variance | 0.363 | +| learning_rate | 4.77e-05 | +| loss | -0.0351 | +| n_updates | 34368 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000103 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1419 | +| iterations | 4639 | +| time_elapsed | 6692 | +| total_timesteps | 9500672 | +| train/ | | +| approx_kl | 0.01158208 | +| clip_fraction | 0.344 | +| clip_range | 0.0726 | +| entropy_loss | -7.08 | +| explained_variance | 0.499 | +| learning_rate | 4.77e-05 | +| loss | -0.0343 | +| n_updates | 34372 | +| policy_gradient_loss | -0.0208 | +| value_loss | 6.59e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1419 | +| iterations | 4640 | +| time_elapsed | 6693 | +| total_timesteps | 9502720 | +| train/ | | +| approx_kl | 0.012327516 | +| clip_fraction | 0.288 | +| clip_range | 0.0726 | +| entropy_loss | -6.79 | +| explained_variance | 0.303 | +| learning_rate | 4.77e-05 | +| loss | -0.0241 | +| n_updates | 34376 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.0003 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1419 | +| iterations | 4641 | +| time_elapsed | 6695 | +| total_timesteps | 9504768 | +| train/ | | +| approx_kl | 0.011524117 | +| clip_fraction | 0.308 | +| clip_range | 0.0726 | +| entropy_loss | -6.63 | +| explained_variance | 0.619 | +| learning_rate | 4.77e-05 | +| loss | -0.0353 | +| n_updates | 34380 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000126 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1419 | +| iterations | 4642 | +| time_elapsed | 6696 | +| total_timesteps | 9506816 | +| train/ | | +| approx_kl | 0.010437666 | +| clip_fraction | 0.303 | +| clip_range | 0.0726 | +| entropy_loss | -7.13 | +| explained_variance | 0.301 | +| learning_rate | 4.77e-05 | +| loss | -0.031 | +| n_updates | 34384 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000135 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1419 | +| iterations | 4643 | +| time_elapsed | 6698 | +| total_timesteps | 9508864 | +| train/ | | +| approx_kl | 0.012267962 | +| clip_fraction | 0.312 | +| clip_range | 0.0726 | +| entropy_loss | -6.92 | +| explained_variance | 0.381 | +| learning_rate | 4.77e-05 | +| loss | -0.0333 | +| n_updates | 34388 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000203 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1419 | +| iterations | 4644 | +| time_elapsed | 6699 | +| total_timesteps | 9510912 | +| train/ | | +| approx_kl | 0.010038773 | +| clip_fraction | 0.314 | +| clip_range | 0.0726 | +| entropy_loss | -7.35 | +| explained_variance | -0.111 | +| learning_rate | 4.77e-05 | +| loss | -0.034 | +| n_updates | 34392 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000112 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1419 | +| iterations | 4645 | +| time_elapsed | 6701 | +| total_timesteps | 9512960 | +| train/ | | +| approx_kl | 0.011997312 | +| clip_fraction | 0.318 | +| clip_range | 0.0726 | +| entropy_loss | -7.01 | +| explained_variance | 0.524 | +| learning_rate | 4.77e-05 | +| loss | -0.0286 | +| n_updates | 34396 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000112 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.384 | +| time/ | | +| fps | 1419 | +| iterations | 4646 | +| time_elapsed | 6702 | +| total_timesteps | 9515008 | +| train/ | | +| approx_kl | 0.009509407 | +| clip_fraction | 0.298 | +| clip_range | 0.0726 | +| entropy_loss | -7.28 | +| explained_variance | 0.0255 | +| learning_rate | 4.77e-05 | +| loss | -0.0222 | +| n_updates | 34400 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000292 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1419 | +| iterations | 4647 | +| time_elapsed | 6703 | +| total_timesteps | 9517056 | +| train/ | | +| approx_kl | 0.010573726 | +| clip_fraction | 0.291 | +| clip_range | 0.0726 | +| entropy_loss | -6.69 | +| explained_variance | 0.464 | +| learning_rate | 4.77e-05 | +| loss | -0.0278 | +| n_updates | 34404 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000229 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1419 | +| iterations | 4648 | +| time_elapsed | 6705 | +| total_timesteps | 9519104 | +| train/ | | +| approx_kl | 0.01265578 | +| clip_fraction | 0.31 | +| clip_range | 0.0726 | +| entropy_loss | -6.73 | +| explained_variance | 0.529 | +| learning_rate | 4.77e-05 | +| loss | -0.0356 | +| n_updates | 34408 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000186 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.387 | +| time/ | | +| fps | 1419 | +| iterations | 4649 | +| time_elapsed | 6706 | +| total_timesteps | 9521152 | +| train/ | | +| approx_kl | 0.013835299 | +| clip_fraction | 0.365 | +| clip_range | 0.0726 | +| entropy_loss | -7.24 | +| explained_variance | -0.229 | +| learning_rate | 4.77e-05 | +| loss | -0.043 | +| n_updates | 34412 | +| policy_gradient_loss | -0.0244 | +| value_loss | 9.1e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1419 | +| iterations | 4650 | +| time_elapsed | 6708 | +| total_timesteps | 9523200 | +| train/ | | +| approx_kl | 0.008742491 | +| clip_fraction | 0.29 | +| clip_range | 0.0726 | +| entropy_loss | -7.32 | +| explained_variance | -0.0859 | +| learning_rate | 4.77e-05 | +| loss | -0.0316 | +| n_updates | 34416 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000301 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1419 | +| iterations | 4651 | +| time_elapsed | 6709 | +| total_timesteps | 9525248 | +| train/ | | +| approx_kl | 0.010703003 | +| clip_fraction | 0.295 | +| clip_range | 0.0726 | +| entropy_loss | -6.97 | +| explained_variance | 0.344 | +| learning_rate | 4.77e-05 | +| loss | -0.0326 | +| n_updates | 34420 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000202 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.387 | +| time/ | | +| fps | 1419 | +| iterations | 4652 | +| time_elapsed | 6711 | +| total_timesteps | 9527296 | +| train/ | | +| approx_kl | 0.011702757 | +| clip_fraction | 0.326 | +| clip_range | 0.0726 | +| entropy_loss | -7.1 | +| explained_variance | 0.301 | +| learning_rate | 4.77e-05 | +| loss | -0.0347 | +| n_updates | 34424 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000139 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.387 | +| time/ | | +| fps | 1419 | +| iterations | 4653 | +| time_elapsed | 6712 | +| total_timesteps | 9529344 | +| train/ | | +| approx_kl | 0.011136349 | +| clip_fraction | 0.323 | +| clip_range | 0.0726 | +| entropy_loss | -6.74 | +| explained_variance | 0.44 | +| learning_rate | 4.77e-05 | +| loss | -0.0309 | +| n_updates | 34428 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000245 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.392 | +| time/ | | +| fps | 1419 | +| iterations | 4654 | +| time_elapsed | 6713 | +| total_timesteps | 9531392 | +| train/ | | +| approx_kl | 0.014215857 | +| clip_fraction | 0.323 | +| clip_range | 0.0726 | +| entropy_loss | -6.7 | +| explained_variance | 0.407 | +| learning_rate | 4.77e-05 | +| loss | -0.028 | +| n_updates | 34432 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000182 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.39 | +| time/ | | +| fps | 1419 | +| iterations | 4655 | +| time_elapsed | 6715 | +| total_timesteps | 9533440 | +| train/ | | +| approx_kl | 0.012064116 | +| clip_fraction | 0.337 | +| clip_range | 0.0726 | +| entropy_loss | -6.82 | +| explained_variance | 0.416 | +| learning_rate | 4.77e-05 | +| loss | -0.0384 | +| n_updates | 34436 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000186 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.394 | +| time/ | | +| fps | 1419 | +| iterations | 4656 | +| time_elapsed | 6716 | +| total_timesteps | 9535488 | +| train/ | | +| approx_kl | 0.011881152 | +| clip_fraction | 0.322 | +| clip_range | 0.0726 | +| entropy_loss | -7.15 | +| explained_variance | 0.231 | +| learning_rate | 4.77e-05 | +| loss | -0.033 | +| n_updates | 34440 | +| policy_gradient_loss | -0.0216 | +| value_loss | 9.35e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.393 | +| time/ | | +| fps | 1419 | +| iterations | 4657 | +| time_elapsed | 6718 | +| total_timesteps | 9537536 | +| train/ | | +| approx_kl | 0.010658637 | +| clip_fraction | 0.295 | +| clip_range | 0.0726 | +| entropy_loss | -7.14 | +| explained_variance | 0.227 | +| learning_rate | 4.77e-05 | +| loss | -0.0248 | +| n_updates | 34444 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000344 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.391 | +| time/ | | +| fps | 1419 | +| iterations | 4658 | +| time_elapsed | 6719 | +| total_timesteps | 9539584 | +| train/ | | +| approx_kl | 0.010900879 | +| clip_fraction | 0.306 | +| clip_range | 0.0726 | +| entropy_loss | -7.17 | +| explained_variance | -0.0372 | +| learning_rate | 4.77e-05 | +| loss | -0.029 | +| n_updates | 34448 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000346 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.391 | +| time/ | | +| fps | 1419 | +| iterations | 4659 | +| time_elapsed | 6721 | +| total_timesteps | 9541632 | +| train/ | | +| approx_kl | 0.012240691 | +| clip_fraction | 0.337 | +| clip_range | 0.0726 | +| entropy_loss | -6.93 | +| explained_variance | 0.302 | +| learning_rate | 4.77e-05 | +| loss | -0.0407 | +| n_updates | 34452 | +| policy_gradient_loss | -0.0248 | +| value_loss | 0.000123 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.39 | +| time/ | | +| fps | 1419 | +| iterations | 4660 | +| time_elapsed | 6722 | +| total_timesteps | 9543680 | +| train/ | | +| approx_kl | 0.012077862 | +| clip_fraction | 0.316 | +| clip_range | 0.0726 | +| entropy_loss | -7.04 | +| explained_variance | 0.137 | +| learning_rate | 4.77e-05 | +| loss | -0.0307 | +| n_updates | 34456 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000238 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.391 | +| time/ | | +| fps | 1419 | +| iterations | 4661 | +| time_elapsed | 6724 | +| total_timesteps | 9545728 | +| train/ | | +| approx_kl | 0.010336233 | +| clip_fraction | 0.316 | +| clip_range | 0.0726 | +| entropy_loss | -7.3 | +| explained_variance | -0.13 | +| learning_rate | 4.77e-05 | +| loss | -0.0311 | +| n_updates | 34460 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000153 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.392 | +| time/ | | +| fps | 1419 | +| iterations | 4662 | +| time_elapsed | 6725 | +| total_timesteps | 9547776 | +| train/ | | +| approx_kl | 0.01141208 | +| clip_fraction | 0.305 | +| clip_range | 0.0726 | +| entropy_loss | -7.16 | +| explained_variance | 0.206 | +| learning_rate | 4.77e-05 | +| loss | -0.028 | +| n_updates | 34464 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000183 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.392 | +| time/ | | +| fps | 1419 | +| iterations | 4663 | +| time_elapsed | 6726 | +| total_timesteps | 9549824 | +| train/ | | +| approx_kl | 0.013228748 | +| clip_fraction | 0.332 | +| clip_range | 0.0726 | +| entropy_loss | -6.99 | +| explained_variance | 0.235 | +| learning_rate | 4.77e-05 | +| loss | -0.0285 | +| n_updates | 34468 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000204 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.388 | +| time/ | | +| fps | 1419 | +| iterations | 4664 | +| time_elapsed | 6728 | +| total_timesteps | 9551872 | +| train/ | | +| approx_kl | 0.012245726 | +| clip_fraction | 0.331 | +| clip_range | 0.0726 | +| entropy_loss | -6.99 | +| explained_variance | 0.543 | +| learning_rate | 4.77e-05 | +| loss | -0.043 | +| n_updates | 34472 | +| policy_gradient_loss | -0.0227 | +| value_loss | 0.000103 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.387 | +| time/ | | +| fps | 1419 | +| iterations | 4665 | +| time_elapsed | 6729 | +| total_timesteps | 9553920 | +| train/ | | +| approx_kl | 0.012024853 | +| clip_fraction | 0.311 | +| clip_range | 0.0726 | +| entropy_loss | -7.06 | +| explained_variance | 0.212 | +| learning_rate | 4.77e-05 | +| loss | -0.0283 | +| n_updates | 34476 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000225 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.39 | +| time/ | | +| fps | 1419 | +| iterations | 4666 | +| time_elapsed | 6731 | +| total_timesteps | 9555968 | +| train/ | | +| approx_kl | 0.012407368 | +| clip_fraction | 0.334 | +| clip_range | 0.0726 | +| entropy_loss | -6.66 | +| explained_variance | 0.68 | +| learning_rate | 4.77e-05 | +| loss | -0.0363 | +| n_updates | 34480 | +| policy_gradient_loss | -0.0225 | +| value_loss | 9.32e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1419 | +| iterations | 4667 | +| time_elapsed | 6732 | +| total_timesteps | 9558016 | +| train/ | | +| approx_kl | 0.0130988285 | +| clip_fraction | 0.296 | +| clip_range | 0.0726 | +| entropy_loss | -6.96 | +| explained_variance | 0.265 | +| learning_rate | 4.77e-05 | +| loss | -0.026 | +| n_updates | 34484 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000195 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1419 | +| iterations | 4668 | +| time_elapsed | 6734 | +| total_timesteps | 9560064 | +| train/ | | +| approx_kl | 0.011158844 | +| clip_fraction | 0.315 | +| clip_range | 0.0726 | +| entropy_loss | -6.91 | +| explained_variance | 0.36 | +| learning_rate | 4.77e-05 | +| loss | -0.0318 | +| n_updates | 34488 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000182 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1419 | +| iterations | 4669 | +| time_elapsed | 6735 | +| total_timesteps | 9562112 | +| train/ | | +| approx_kl | 0.011528609 | +| clip_fraction | 0.324 | +| clip_range | 0.0726 | +| entropy_loss | -6.68 | +| explained_variance | 0.357 | +| learning_rate | 4.77e-05 | +| loss | -0.0303 | +| n_updates | 34492 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000192 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1419 | +| iterations | 4670 | +| time_elapsed | 6737 | +| total_timesteps | 9564160 | +| train/ | | +| approx_kl | 0.009956628 | +| clip_fraction | 0.293 | +| clip_range | 0.0726 | +| entropy_loss | -6.99 | +| explained_variance | 0.187 | +| learning_rate | 4.77e-05 | +| loss | -0.0212 | +| n_updates | 34496 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000241 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.392 | +| time/ | | +| fps | 1419 | +| iterations | 4671 | +| time_elapsed | 6738 | +| total_timesteps | 9566208 | +| train/ | | +| approx_kl | 0.014531909 | +| clip_fraction | 0.381 | +| clip_range | 0.0726 | +| entropy_loss | -7.04 | +| explained_variance | 0.324 | +| learning_rate | 4.77e-05 | +| loss | -0.0368 | +| n_updates | 34500 | +| policy_gradient_loss | -0.0242 | +| value_loss | 0.000119 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.393 | +| time/ | | +| fps | 1419 | +| iterations | 4672 | +| time_elapsed | 6739 | +| total_timesteps | 9568256 | +| train/ | | +| approx_kl | 0.011243099 | +| clip_fraction | 0.309 | +| clip_range | 0.0726 | +| entropy_loss | -6.8 | +| explained_variance | 0.271 | +| learning_rate | 4.77e-05 | +| loss | -0.0274 | +| n_updates | 34504 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000388 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.393 | +| time/ | | +| fps | 1419 | +| iterations | 4673 | +| time_elapsed | 6741 | +| total_timesteps | 9570304 | +| train/ | | +| approx_kl | 0.011086513 | +| clip_fraction | 0.33 | +| clip_range | 0.0726 | +| entropy_loss | -6.85 | +| explained_variance | 0.456 | +| learning_rate | 4.77e-05 | +| loss | -0.0339 | +| n_updates | 34508 | +| policy_gradient_loss | -0.0223 | +| value_loss | 0.000134 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.395 | +| time/ | | +| fps | 1419 | +| iterations | 4674 | +| time_elapsed | 6742 | +| total_timesteps | 9572352 | +| train/ | | +| approx_kl | 0.012099231 | +| clip_fraction | 0.336 | +| clip_range | 0.0726 | +| entropy_loss | -7.37 | +| explained_variance | 0.0918 | +| learning_rate | 4.77e-05 | +| loss | -0.0317 | +| n_updates | 34512 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000182 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.392 | +| time/ | | +| fps | 1419 | +| iterations | 4675 | +| time_elapsed | 6744 | +| total_timesteps | 9574400 | +| train/ | | +| approx_kl | 0.010654263 | +| clip_fraction | 0.318 | +| clip_range | 0.0726 | +| entropy_loss | -6.97 | +| explained_variance | 0.41 | +| learning_rate | 4.77e-05 | +| loss | -0.0419 | +| n_updates | 34516 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000183 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.392 | +| time/ | | +| fps | 1419 | +| iterations | 4676 | +| time_elapsed | 6745 | +| total_timesteps | 9576448 | +| train/ | | +| approx_kl | 0.010494908 | +| clip_fraction | 0.283 | +| clip_range | 0.0726 | +| entropy_loss | -6.97 | +| explained_variance | 0.158 | +| learning_rate | 4.77e-05 | +| loss | -0.0287 | +| n_updates | 34520 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000289 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.393 | +| time/ | | +| fps | 1419 | +| iterations | 4677 | +| time_elapsed | 6747 | +| total_timesteps | 9578496 | +| train/ | | +| approx_kl | 0.014246559 | +| clip_fraction | 0.327 | +| clip_range | 0.0726 | +| entropy_loss | -7.01 | +| explained_variance | 0.476 | +| learning_rate | 4.77e-05 | +| loss | -0.0343 | +| n_updates | 34524 | +| policy_gradient_loss | -0.0223 | +| value_loss | 0.000128 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.393 | +| time/ | | +| fps | 1419 | +| iterations | 4678 | +| time_elapsed | 6748 | +| total_timesteps | 9580544 | +| train/ | | +| approx_kl | 0.010628429 | +| clip_fraction | 0.281 | +| clip_range | 0.0726 | +| entropy_loss | -6.76 | +| explained_variance | 0.404 | +| learning_rate | 4.77e-05 | +| loss | -0.0335 | +| n_updates | 34528 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000228 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.393 | +| time/ | | +| fps | 1419 | +| iterations | 4679 | +| time_elapsed | 6750 | +| total_timesteps | 9582592 | +| train/ | | +| approx_kl | 0.010985693 | +| clip_fraction | 0.311 | +| clip_range | 0.0726 | +| entropy_loss | -6.73 | +| explained_variance | 0.492 | +| learning_rate | 4.77e-05 | +| loss | -0.0338 | +| n_updates | 34532 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000197 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.395 | +| time/ | | +| fps | 1419 | +| iterations | 4680 | +| time_elapsed | 6751 | +| total_timesteps | 9584640 | +| train/ | | +| approx_kl | 0.0122120865 | +| clip_fraction | 0.346 | +| clip_range | 0.0726 | +| entropy_loss | -7.06 | +| explained_variance | 0.369 | +| learning_rate | 4.77e-05 | +| loss | -0.0372 | +| n_updates | 34536 | +| policy_gradient_loss | -0.0241 | +| value_loss | 9.71e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.405 | +| time/ | | +| fps | 1419 | +| iterations | 4681 | +| time_elapsed | 6752 | +| total_timesteps | 9586688 | +| train/ | | +| approx_kl | 0.012741158 | +| clip_fraction | 0.318 | +| clip_range | 0.0726 | +| entropy_loss | -7.35 | +| explained_variance | -0.0416 | +| learning_rate | 4.77e-05 | +| loss | -0.0322 | +| n_updates | 34540 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000387 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.408 | +| time/ | | +| fps | 1419 | +| iterations | 4682 | +| time_elapsed | 6754 | +| total_timesteps | 9588736 | +| train/ | | +| approx_kl | 0.009790948 | +| clip_fraction | 0.295 | +| clip_range | 0.0726 | +| entropy_loss | -6.52 | +| explained_variance | 0.225 | +| learning_rate | 4.77e-05 | +| loss | -0.0298 | +| n_updates | 34544 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000557 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.415 | +| time/ | | +| fps | 1419 | +| iterations | 4683 | +| time_elapsed | 6755 | +| total_timesteps | 9590784 | +| train/ | | +| approx_kl | 0.0101647265 | +| clip_fraction | 0.306 | +| clip_range | 0.0726 | +| entropy_loss | -6.66 | +| explained_variance | 0.502 | +| learning_rate | 4.77e-05 | +| loss | -0.0295 | +| n_updates | 34548 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000252 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.414 | +| time/ | | +| fps | 1419 | +| iterations | 4684 | +| time_elapsed | 6757 | +| total_timesteps | 9592832 | +| train/ | | +| approx_kl | 0.011625066 | +| clip_fraction | 0.318 | +| clip_range | 0.0726 | +| entropy_loss | -6.96 | +| explained_variance | 0.282 | +| learning_rate | 4.77e-05 | +| loss | -0.0327 | +| n_updates | 34552 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000361 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.414 | +| time/ | | +| fps | 1419 | +| iterations | 4685 | +| time_elapsed | 6758 | +| total_timesteps | 9594880 | +| train/ | | +| approx_kl | 0.013114882 | +| clip_fraction | 0.335 | +| clip_range | 0.0726 | +| entropy_loss | -6.72 | +| explained_variance | 0.373 | +| learning_rate | 4.77e-05 | +| loss | -0.0362 | +| n_updates | 34556 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000234 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.411 | +| time/ | | +| fps | 1419 | +| iterations | 4686 | +| time_elapsed | 6760 | +| total_timesteps | 9596928 | +| train/ | | +| approx_kl | 0.012898073 | +| clip_fraction | 0.376 | +| clip_range | 0.0726 | +| entropy_loss | -7.23 | +| explained_variance | -0.955 | +| learning_rate | 4.77e-05 | +| loss | -0.047 | +| n_updates | 34560 | +| policy_gradient_loss | -0.0288 | +| value_loss | 0.000109 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.417 | +| time/ | | +| fps | 1419 | +| iterations | 4687 | +| time_elapsed | 6761 | +| total_timesteps | 9598976 | +| train/ | | +| approx_kl | 0.010002656 | +| clip_fraction | 0.337 | +| clip_range | 0.0726 | +| entropy_loss | -7.38 | +| explained_variance | -0.127 | +| learning_rate | 4.77e-05 | +| loss | -0.0379 | +| n_updates | 34564 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000147 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.42 | +| time/ | | +| fps | 1419 | +| iterations | 4688 | +| time_elapsed | 6762 | +| total_timesteps | 9601024 | +| train/ | | +| approx_kl | 0.009651415 | +| clip_fraction | 0.302 | +| clip_range | 0.0726 | +| entropy_loss | -6.81 | +| explained_variance | 0.382 | +| learning_rate | 4.77e-05 | +| loss | -0.0296 | +| n_updates | 34568 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000234 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.415 | +| time/ | | +| fps | 1419 | +| iterations | 4689 | +| time_elapsed | 6764 | +| total_timesteps | 9603072 | +| train/ | | +| approx_kl | 0.01276699 | +| clip_fraction | 0.318 | +| clip_range | 0.0726 | +| entropy_loss | -6.95 | +| explained_variance | 0.472 | +| learning_rate | 4.77e-05 | +| loss | -0.0358 | +| n_updates | 34572 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.00015 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.412 | +| time/ | | +| fps | 1419 | +| iterations | 4690 | +| time_elapsed | 6765 | +| total_timesteps | 9605120 | +| train/ | | +| approx_kl | 0.011382053 | +| clip_fraction | 0.338 | +| clip_range | 0.0726 | +| entropy_loss | -6.95 | +| explained_variance | 0.632 | +| learning_rate | 4.77e-05 | +| loss | -0.0299 | +| n_updates | 34576 | +| policy_gradient_loss | -0.0212 | +| value_loss | 8.34e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.412 | +| time/ | | +| fps | 1419 | +| iterations | 4691 | +| time_elapsed | 6767 | +| total_timesteps | 9607168 | +| train/ | | +| approx_kl | 0.013403225 | +| clip_fraction | 0.333 | +| clip_range | 0.0726 | +| entropy_loss | -6.96 | +| explained_variance | 0.32 | +| learning_rate | 4.77e-05 | +| loss | -0.0351 | +| n_updates | 34580 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000193 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.415 | +| time/ | | +| fps | 1419 | +| iterations | 4692 | +| time_elapsed | 6768 | +| total_timesteps | 9609216 | +| train/ | | +| approx_kl | 0.012264699 | +| clip_fraction | 0.322 | +| clip_range | 0.0726 | +| entropy_loss | -7.34 | +| explained_variance | -0.00204 | +| learning_rate | 4.77e-05 | +| loss | -0.0312 | +| n_updates | 34584 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000159 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.413 | +| time/ | | +| fps | 1419 | +| iterations | 4693 | +| time_elapsed | 6770 | +| total_timesteps | 9611264 | +| train/ | | +| approx_kl | 0.009652776 | +| clip_fraction | 0.29 | +| clip_range | 0.0726 | +| entropy_loss | -6.55 | +| explained_variance | 0.362 | +| learning_rate | 4.77e-05 | +| loss | -0.0287 | +| n_updates | 34588 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000298 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.407 | +| time/ | | +| fps | 1419 | +| iterations | 4694 | +| time_elapsed | 6771 | +| total_timesteps | 9613312 | +| train/ | | +| approx_kl | 0.009774857 | +| clip_fraction | 0.306 | +| clip_range | 0.0726 | +| entropy_loss | -6.89 | +| explained_variance | 0.444 | +| learning_rate | 4.77e-05 | +| loss | -0.0316 | +| n_updates | 34592 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000203 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.407 | +| time/ | | +| fps | 1419 | +| iterations | 4695 | +| time_elapsed | 6773 | +| total_timesteps | 9615360 | +| train/ | | +| approx_kl | 0.010690493 | +| clip_fraction | 0.321 | +| clip_range | 0.0726 | +| entropy_loss | -6.83 | +| explained_variance | 0.421 | +| learning_rate | 4.77e-05 | +| loss | -0.0281 | +| n_updates | 34596 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000174 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.41 | +| time/ | | +| fps | 1419 | +| iterations | 4696 | +| time_elapsed | 6774 | +| total_timesteps | 9617408 | +| train/ | | +| approx_kl | 0.011278527 | +| clip_fraction | 0.336 | +| clip_range | 0.0726 | +| entropy_loss | -7.09 | +| explained_variance | 0.373 | +| learning_rate | 4.77e-05 | +| loss | -0.034 | +| n_updates | 34600 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000106 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.415 | +| time/ | | +| fps | 1419 | +| iterations | 4697 | +| time_elapsed | 6776 | +| total_timesteps | 9619456 | +| train/ | | +| approx_kl | 0.0109555265 | +| clip_fraction | 0.309 | +| clip_range | 0.0726 | +| entropy_loss | -7.14 | +| explained_variance | 0.073 | +| learning_rate | 4.77e-05 | +| loss | -0.0318 | +| n_updates | 34604 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000315 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.415 | +| time/ | | +| fps | 1419 | +| iterations | 4698 | +| time_elapsed | 6777 | +| total_timesteps | 9621504 | +| train/ | | +| approx_kl | 0.011599317 | +| clip_fraction | 0.317 | +| clip_range | 0.0726 | +| entropy_loss | -6.68 | +| explained_variance | 0.291 | +| learning_rate | 4.77e-05 | +| loss | -0.0246 | +| n_updates | 34608 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000458 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.417 | +| time/ | | +| fps | 1419 | +| iterations | 4699 | +| time_elapsed | 6778 | +| total_timesteps | 9623552 | +| train/ | | +| approx_kl | 0.011740645 | +| clip_fraction | 0.345 | +| clip_range | 0.0726 | +| entropy_loss | -7.39 | +| explained_variance | -0.163 | +| learning_rate | 4.77e-05 | +| loss | -0.0417 | +| n_updates | 34612 | +| policy_gradient_loss | -0.0239 | +| value_loss | 0.000148 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.419 | +| time/ | | +| fps | 1419 | +| iterations | 4700 | +| time_elapsed | 6780 | +| total_timesteps | 9625600 | +| train/ | | +| approx_kl | 0.011214048 | +| clip_fraction | 0.322 | +| clip_range | 0.0726 | +| entropy_loss | -7.14 | +| explained_variance | 0.32 | +| learning_rate | 4.77e-05 | +| loss | -0.0253 | +| n_updates | 34616 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000322 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.419 | +| time/ | | +| fps | 1419 | +| iterations | 4701 | +| time_elapsed | 6781 | +| total_timesteps | 9627648 | +| train/ | | +| approx_kl | 0.011729006 | +| clip_fraction | 0.35 | +| clip_range | 0.0726 | +| entropy_loss | -7.25 | +| explained_variance | -0.167 | +| learning_rate | 4.77e-05 | +| loss | -0.0392 | +| n_updates | 34620 | +| policy_gradient_loss | -0.0246 | +| value_loss | 0.000122 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.419 | +| time/ | | +| fps | 1419 | +| iterations | 4702 | +| time_elapsed | 6783 | +| total_timesteps | 9629696 | +| train/ | | +| approx_kl | 0.011584278 | +| clip_fraction | 0.335 | +| clip_range | 0.0726 | +| entropy_loss | -7.28 | +| explained_variance | 0.261 | +| learning_rate | 4.77e-05 | +| loss | -0.0337 | +| n_updates | 34624 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000159 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.428 | +| time/ | | +| fps | 1419 | +| iterations | 4703 | +| time_elapsed | 6784 | +| total_timesteps | 9631744 | +| train/ | | +| approx_kl | 0.011463152 | +| clip_fraction | 0.334 | +| clip_range | 0.0726 | +| entropy_loss | -7.5 | +| explained_variance | -0.075 | +| learning_rate | 4.77e-05 | +| loss | -0.0331 | +| n_updates | 34628 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.00018 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.425 | +| time/ | | +| fps | 1419 | +| iterations | 4704 | +| time_elapsed | 6786 | +| total_timesteps | 9633792 | +| train/ | | +| approx_kl | 0.010409519 | +| clip_fraction | 0.281 | +| clip_range | 0.0726 | +| entropy_loss | -6.25 | +| explained_variance | 0.376 | +| learning_rate | 4.77e-05 | +| loss | -0.0213 | +| n_updates | 34632 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000444 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.43 | +| time/ | | +| fps | 1419 | +| iterations | 4705 | +| time_elapsed | 6787 | +| total_timesteps | 9635840 | +| train/ | | +| approx_kl | 0.011317202 | +| clip_fraction | 0.31 | +| clip_range | 0.0726 | +| entropy_loss | -6.71 | +| explained_variance | 0.695 | +| learning_rate | 4.77e-05 | +| loss | -0.0342 | +| n_updates | 34636 | +| policy_gradient_loss | -0.0217 | +| value_loss | 9.8e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.429 | +| time/ | | +| fps | 1419 | +| iterations | 4706 | +| time_elapsed | 6788 | +| total_timesteps | 9637888 | +| train/ | | +| approx_kl | 0.011392342 | +| clip_fraction | 0.321 | +| clip_range | 0.0726 | +| entropy_loss | -7.01 | +| explained_variance | 0.284 | +| learning_rate | 4.77e-05 | +| loss | -0.0261 | +| n_updates | 34640 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000378 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.427 | +| time/ | | +| fps | 1419 | +| iterations | 4707 | +| time_elapsed | 6790 | +| total_timesteps | 9639936 | +| train/ | | +| approx_kl | 0.014481747 | +| clip_fraction | 0.336 | +| clip_range | 0.0726 | +| entropy_loss | -7.08 | +| explained_variance | -0.117 | +| learning_rate | 4.77e-05 | +| loss | -0.0339 | +| n_updates | 34644 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000198 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.429 | +| time/ | | +| fps | 1419 | +| iterations | 4708 | +| time_elapsed | 6791 | +| total_timesteps | 9641984 | +| train/ | | +| approx_kl | 0.0111511545 | +| clip_fraction | 0.326 | +| clip_range | 0.0726 | +| entropy_loss | -6.89 | +| explained_variance | 0.482 | +| learning_rate | 4.77e-05 | +| loss | -0.0344 | +| n_updates | 34648 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000132 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.433 | +| time/ | | +| fps | 1419 | +| iterations | 4709 | +| time_elapsed | 6793 | +| total_timesteps | 9644032 | +| train/ | | +| approx_kl | 0.012446135 | +| clip_fraction | 0.311 | +| clip_range | 0.0726 | +| entropy_loss | -7.09 | +| explained_variance | 0.229 | +| learning_rate | 4.77e-05 | +| loss | -0.033 | +| n_updates | 34652 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000171 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.433 | +| time/ | | +| fps | 1419 | +| iterations | 4710 | +| time_elapsed | 6794 | +| total_timesteps | 9646080 | +| train/ | | +| approx_kl | 0.010766333 | +| clip_fraction | 0.31 | +| clip_range | 0.0726 | +| entropy_loss | -7.38 | +| explained_variance | -0.145 | +| learning_rate | 4.77e-05 | +| loss | -0.0327 | +| n_updates | 34656 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000155 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.435 | +| time/ | | +| fps | 1419 | +| iterations | 4711 | +| time_elapsed | 6796 | +| total_timesteps | 9648128 | +| train/ | | +| approx_kl | 0.011726031 | +| clip_fraction | 0.307 | +| clip_range | 0.0726 | +| entropy_loss | -7.28 | +| explained_variance | 0.302 | +| learning_rate | 4.77e-05 | +| loss | -0.0274 | +| n_updates | 34660 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.00013 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.429 | +| time/ | | +| fps | 1419 | +| iterations | 4712 | +| time_elapsed | 6797 | +| total_timesteps | 9650176 | +| train/ | | +| approx_kl | 0.010826943 | +| clip_fraction | 0.299 | +| clip_range | 0.0726 | +| entropy_loss | -7.33 | +| explained_variance | 0.17 | +| learning_rate | 4.77e-05 | +| loss | -0.0245 | +| n_updates | 34664 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000235 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.433 | +| time/ | | +| fps | 1419 | +| iterations | 4713 | +| time_elapsed | 6799 | +| total_timesteps | 9652224 | +| train/ | | +| approx_kl | 0.011278376 | +| clip_fraction | 0.317 | +| clip_range | 0.0726 | +| entropy_loss | -7.34 | +| explained_variance | -0.0711 | +| learning_rate | 4.77e-05 | +| loss | -0.0304 | +| n_updates | 34668 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.00016 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.433 | +| time/ | | +| fps | 1419 | +| iterations | 4714 | +| time_elapsed | 6800 | +| total_timesteps | 9654272 | +| train/ | | +| approx_kl | 0.0098871235 | +| clip_fraction | 0.258 | +| clip_range | 0.0726 | +| entropy_loss | -6.87 | +| explained_variance | 0.386 | +| learning_rate | 4.77e-05 | +| loss | -0.0287 | +| n_updates | 34672 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000295 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.434 | +| time/ | | +| fps | 1419 | +| iterations | 4715 | +| time_elapsed | 6801 | +| total_timesteps | 9656320 | +| train/ | | +| approx_kl | 0.010816613 | +| clip_fraction | 0.274 | +| clip_range | 0.0726 | +| entropy_loss | -6.81 | +| explained_variance | 0.581 | +| learning_rate | 4.77e-05 | +| loss | -0.0288 | +| n_updates | 34676 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000156 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.433 | +| time/ | | +| fps | 1419 | +| iterations | 4716 | +| time_elapsed | 6803 | +| total_timesteps | 9658368 | +| train/ | | +| approx_kl | 0.010642863 | +| clip_fraction | 0.319 | +| clip_range | 0.0726 | +| entropy_loss | -6.9 | +| explained_variance | 0.325 | +| learning_rate | 4.77e-05 | +| loss | -0.0299 | +| n_updates | 34680 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000273 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.431 | +| time/ | | +| fps | 1419 | +| iterations | 4717 | +| time_elapsed | 6804 | +| total_timesteps | 9660416 | +| train/ | | +| approx_kl | 0.011752635 | +| clip_fraction | 0.309 | +| clip_range | 0.0726 | +| entropy_loss | -6.71 | +| explained_variance | 0.41 | +| learning_rate | 4.77e-05 | +| loss | -0.0339 | +| n_updates | 34684 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000189 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.429 | +| time/ | | +| fps | 1419 | +| iterations | 4718 | +| time_elapsed | 6806 | +| total_timesteps | 9662464 | +| train/ | | +| approx_kl | 0.013642412 | +| clip_fraction | 0.37 | +| clip_range | 0.0726 | +| entropy_loss | -6.97 | +| explained_variance | 0.664 | +| learning_rate | 4.77e-05 | +| loss | -0.0431 | +| n_updates | 34688 | +| policy_gradient_loss | -0.0253 | +| value_loss | 7.38e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.427 | +| time/ | | +| fps | 1419 | +| iterations | 4719 | +| time_elapsed | 6807 | +| total_timesteps | 9664512 | +| train/ | | +| approx_kl | 0.011090502 | +| clip_fraction | 0.308 | +| clip_range | 0.0726 | +| entropy_loss | -7.35 | +| explained_variance | 0.21 | +| learning_rate | 4.77e-05 | +| loss | -0.0284 | +| n_updates | 34692 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000195 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.426 | +| time/ | | +| fps | 1419 | +| iterations | 4720 | +| time_elapsed | 6809 | +| total_timesteps | 9666560 | +| train/ | | +| approx_kl | 0.010326274 | +| clip_fraction | 0.306 | +| clip_range | 0.0726 | +| entropy_loss | -7.16 | +| explained_variance | 0.423 | +| learning_rate | 4.77e-05 | +| loss | -0.0338 | +| n_updates | 34696 | +| policy_gradient_loss | -0.0214 | +| value_loss | 8.54e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.426 | +| time/ | | +| fps | 1419 | +| iterations | 4721 | +| time_elapsed | 6810 | +| total_timesteps | 9668608 | +| train/ | | +| approx_kl | 0.010570186 | +| clip_fraction | 0.29 | +| clip_range | 0.0726 | +| entropy_loss | -7.09 | +| explained_variance | 0.272 | +| learning_rate | 4.77e-05 | +| loss | -0.0289 | +| n_updates | 34700 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000137 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.426 | +| time/ | | +| fps | 1419 | +| iterations | 4722 | +| time_elapsed | 6811 | +| total_timesteps | 9670656 | +| train/ | | +| approx_kl | 0.008791374 | +| clip_fraction | 0.254 | +| clip_range | 0.0726 | +| entropy_loss | -7.12 | +| explained_variance | 0.163 | +| learning_rate | 4.77e-05 | +| loss | -0.0309 | +| n_updates | 34704 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.00029 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.429 | +| time/ | | +| fps | 1419 | +| iterations | 4723 | +| time_elapsed | 6813 | +| total_timesteps | 9672704 | +| train/ | | +| approx_kl | 0.011811862 | +| clip_fraction | 0.324 | +| clip_range | 0.0726 | +| entropy_loss | -7.18 | +| explained_variance | 0.359 | +| learning_rate | 4.77e-05 | +| loss | -0.0338 | +| n_updates | 34708 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000122 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.435 | +| time/ | | +| fps | 1419 | +| iterations | 4724 | +| time_elapsed | 6814 | +| total_timesteps | 9674752 | +| train/ | | +| approx_kl | 0.010440821 | +| clip_fraction | 0.309 | +| clip_range | 0.0726 | +| entropy_loss | -7.22 | +| explained_variance | 0.337 | +| learning_rate | 4.77e-05 | +| loss | -0.029 | +| n_updates | 34712 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000141 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.436 | +| time/ | | +| fps | 1419 | +| iterations | 4725 | +| time_elapsed | 6816 | +| total_timesteps | 9676800 | +| train/ | | +| approx_kl | 0.011232559 | +| clip_fraction | 0.264 | +| clip_range | 0.0726 | +| entropy_loss | -7.01 | +| explained_variance | 0.228 | +| learning_rate | 4.77e-05 | +| loss | -0.031 | +| n_updates | 34716 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000371 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.439 | +| time/ | | +| fps | 1419 | +| iterations | 4726 | +| time_elapsed | 6817 | +| total_timesteps | 9678848 | +| train/ | | +| approx_kl | 0.01112723 | +| clip_fraction | 0.321 | +| clip_range | 0.0726 | +| entropy_loss | -6.59 | +| explained_variance | 0.678 | +| learning_rate | 4.77e-05 | +| loss | -0.0361 | +| n_updates | 34720 | +| policy_gradient_loss | -0.0223 | +| value_loss | 9.14e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.439 | +| time/ | | +| fps | 1419 | +| iterations | 4727 | +| time_elapsed | 6819 | +| total_timesteps | 9680896 | +| train/ | | +| approx_kl | 0.010857504 | +| clip_fraction | 0.322 | +| clip_range | 0.0726 | +| entropy_loss | -7.04 | +| explained_variance | 0.409 | +| learning_rate | 4.77e-05 | +| loss | -0.0318 | +| n_updates | 34724 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000161 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.44 | +| time/ | | +| fps | 1419 | +| iterations | 4728 | +| time_elapsed | 6820 | +| total_timesteps | 9682944 | +| train/ | | +| approx_kl | 0.011592314 | +| clip_fraction | 0.313 | +| clip_range | 0.0726 | +| entropy_loss | -7.04 | +| explained_variance | 0.412 | +| learning_rate | 4.77e-05 | +| loss | -0.0314 | +| n_updates | 34728 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000119 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.44 | +| time/ | | +| fps | 1419 | +| iterations | 4729 | +| time_elapsed | 6822 | +| total_timesteps | 9684992 | +| train/ | | +| approx_kl | 0.009735172 | +| clip_fraction | 0.324 | +| clip_range | 0.0726 | +| entropy_loss | -7.05 | +| explained_variance | 0.454 | +| learning_rate | 4.77e-05 | +| loss | -0.0311 | +| n_updates | 34732 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.00018 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.438 | +| time/ | | +| fps | 1419 | +| iterations | 4730 | +| time_elapsed | 6823 | +| total_timesteps | 9687040 | +| train/ | | +| approx_kl | 0.010607033 | +| clip_fraction | 0.321 | +| clip_range | 0.0726 | +| entropy_loss | -7.43 | +| explained_variance | 0.00305 | +| learning_rate | 4.77e-05 | +| loss | -0.0314 | +| n_updates | 34736 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000183 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.444 | +| time/ | | +| fps | 1419 | +| iterations | 4731 | +| time_elapsed | 6824 | +| total_timesteps | 9689088 | +| train/ | | +| approx_kl | 0.010950347 | +| clip_fraction | 0.289 | +| clip_range | 0.0726 | +| entropy_loss | -7.27 | +| explained_variance | 0.395 | +| learning_rate | 4.77e-05 | +| loss | -0.0407 | +| n_updates | 34740 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.444 | +| time/ | | +| fps | 1419 | +| iterations | 4732 | +| time_elapsed | 6826 | +| total_timesteps | 9691136 | +| train/ | | +| approx_kl | 0.010006556 | +| clip_fraction | 0.282 | +| clip_range | 0.0726 | +| entropy_loss | -6.7 | +| explained_variance | 0.436 | +| learning_rate | 4.77e-05 | +| loss | -0.0267 | +| n_updates | 34744 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000328 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.444 | +| time/ | | +| fps | 1419 | +| iterations | 4733 | +| time_elapsed | 6827 | +| total_timesteps | 9693184 | +| train/ | | +| approx_kl | 0.01058571 | +| clip_fraction | 0.286 | +| clip_range | 0.0726 | +| entropy_loss | -6.58 | +| explained_variance | 0.331 | +| learning_rate | 4.77e-05 | +| loss | -0.025 | +| n_updates | 34748 | +| policy_gradient_loss | -0.0145 | +| value_loss | 0.00029 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.446 | +| time/ | | +| fps | 1419 | +| iterations | 4734 | +| time_elapsed | 6829 | +| total_timesteps | 9695232 | +| train/ | | +| approx_kl | 0.010754423 | +| clip_fraction | 0.311 | +| clip_range | 0.0726 | +| entropy_loss | -6.85 | +| explained_variance | 0.335 | +| learning_rate | 4.77e-05 | +| loss | -0.0253 | +| n_updates | 34752 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000283 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.441 | +| time/ | | +| fps | 1419 | +| iterations | 4735 | +| time_elapsed | 6830 | +| total_timesteps | 9697280 | +| train/ | | +| approx_kl | 0.009818023 | +| clip_fraction | 0.328 | +| clip_range | 0.0726 | +| entropy_loss | -7.21 | +| explained_variance | 0.0557 | +| learning_rate | 4.77e-05 | +| loss | -0.0405 | +| n_updates | 34756 | +| policy_gradient_loss | -0.0223 | +| value_loss | 0.000197 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.437 | +| time/ | | +| fps | 1419 | +| iterations | 4736 | +| time_elapsed | 6831 | +| total_timesteps | 9699328 | +| train/ | | +| approx_kl | 0.011023276 | +| clip_fraction | 0.299 | +| clip_range | 0.0726 | +| entropy_loss | -6.99 | +| explained_variance | 0.426 | +| learning_rate | 4.77e-05 | +| loss | -0.0273 | +| n_updates | 34760 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000155 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.44 | +| time/ | | +| fps | 1419 | +| iterations | 4737 | +| time_elapsed | 6833 | +| total_timesteps | 9701376 | +| train/ | | +| approx_kl | 0.010697313 | +| clip_fraction | 0.296 | +| clip_range | 0.0726 | +| entropy_loss | -7.09 | +| explained_variance | 0.433 | +| learning_rate | 4.77e-05 | +| loss | -0.0269 | +| n_updates | 34764 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.00016 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.446 | +| time/ | | +| fps | 1419 | +| iterations | 4738 | +| time_elapsed | 6834 | +| total_timesteps | 9703424 | +| train/ | | +| approx_kl | 0.01100125 | +| clip_fraction | 0.305 | +| clip_range | 0.0726 | +| entropy_loss | -6.88 | +| explained_variance | 0.433 | +| learning_rate | 4.77e-05 | +| loss | -0.035 | +| n_updates | 34768 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000188 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.446 | +| time/ | | +| fps | 1419 | +| iterations | 4739 | +| time_elapsed | 6836 | +| total_timesteps | 9705472 | +| train/ | | +| approx_kl | 0.011168173 | +| clip_fraction | 0.32 | +| clip_range | 0.0726 | +| entropy_loss | -7.16 | +| explained_variance | 0.193 | +| learning_rate | 4.77e-05 | +| loss | -0.0333 | +| n_updates | 34772 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.00026 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.447 | +| time/ | | +| fps | 1419 | +| iterations | 4740 | +| time_elapsed | 6837 | +| total_timesteps | 9707520 | +| train/ | | +| approx_kl | 0.011284246 | +| clip_fraction | 0.306 | +| clip_range | 0.0726 | +| entropy_loss | -7.41 | +| explained_variance | -0.209 | +| learning_rate | 4.77e-05 | +| loss | -0.0359 | +| n_updates | 34776 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000187 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.447 | +| time/ | | +| fps | 1419 | +| iterations | 4741 | +| time_elapsed | 6839 | +| total_timesteps | 9709568 | +| train/ | | +| approx_kl | 0.011001527 | +| clip_fraction | 0.304 | +| clip_range | 0.0726 | +| entropy_loss | -7.4 | +| explained_variance | -0.0891 | +| learning_rate | 4.77e-05 | +| loss | -0.0334 | +| n_updates | 34780 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000261 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.447 | +| time/ | | +| fps | 1419 | +| iterations | 4742 | +| time_elapsed | 6840 | +| total_timesteps | 9711616 | +| train/ | | +| approx_kl | 0.012896141 | +| clip_fraction | 0.327 | +| clip_range | 0.0726 | +| entropy_loss | -7.06 | +| explained_variance | 0.459 | +| learning_rate | 4.77e-05 | +| loss | -0.0406 | +| n_updates | 34784 | +| policy_gradient_loss | -0.0232 | +| value_loss | 0.000129 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.437 | +| time/ | | +| fps | 1419 | +| iterations | 4743 | +| time_elapsed | 6841 | +| total_timesteps | 9713664 | +| train/ | | +| approx_kl | 0.011924466 | +| clip_fraction | 0.331 | +| clip_range | 0.0726 | +| entropy_loss | -7.48 | +| explained_variance | -0.263 | +| learning_rate | 4.77e-05 | +| loss | -0.036 | +| n_updates | 34788 | +| policy_gradient_loss | -0.0227 | +| value_loss | 0.000112 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.43 | +| time/ | | +| fps | 1419 | +| iterations | 4744 | +| time_elapsed | 6843 | +| total_timesteps | 9715712 | +| train/ | | +| approx_kl | 0.009406521 | +| clip_fraction | 0.281 | +| clip_range | 0.0726 | +| entropy_loss | -6.79 | +| explained_variance | 0.475 | +| learning_rate | 4.77e-05 | +| loss | -0.0291 | +| n_updates | 34792 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000192 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.43 | +| time/ | | +| fps | 1419 | +| iterations | 4745 | +| time_elapsed | 6844 | +| total_timesteps | 9717760 | +| train/ | | +| approx_kl | 0.01131203 | +| clip_fraction | 0.321 | +| clip_range | 0.0726 | +| entropy_loss | -6.43 | +| explained_variance | 0.657 | +| learning_rate | 4.77e-05 | +| loss | -0.0386 | +| n_updates | 34796 | +| policy_gradient_loss | -0.0207 | +| value_loss | 9.75e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.426 | +| time/ | | +| fps | 1419 | +| iterations | 4746 | +| time_elapsed | 6846 | +| total_timesteps | 9719808 | +| train/ | | +| approx_kl | 0.010441361 | +| clip_fraction | 0.285 | +| clip_range | 0.0726 | +| entropy_loss | -6.91 | +| explained_variance | 0.453 | +| learning_rate | 4.77e-05 | +| loss | -0.0323 | +| n_updates | 34800 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000172 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.428 | +| time/ | | +| fps | 1419 | +| iterations | 4747 | +| time_elapsed | 6847 | +| total_timesteps | 9721856 | +| train/ | | +| approx_kl | 0.011425637 | +| clip_fraction | 0.333 | +| clip_range | 0.0726 | +| entropy_loss | -7.26 | +| explained_variance | 0.00937 | +| learning_rate | 4.77e-05 | +| loss | -0.031 | +| n_updates | 34804 | +| policy_gradient_loss | -0.0211 | +| value_loss | 9.55e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.429 | +| time/ | | +| fps | 1419 | +| iterations | 4748 | +| time_elapsed | 6849 | +| total_timesteps | 9723904 | +| train/ | | +| approx_kl | 0.008934166 | +| clip_fraction | 0.287 | +| clip_range | 0.0726 | +| entropy_loss | -7.05 | +| explained_variance | 0.143 | +| learning_rate | 4.77e-05 | +| loss | -0.0306 | +| n_updates | 34808 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000196 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.429 | +| time/ | | +| fps | 1419 | +| iterations | 4749 | +| time_elapsed | 6850 | +| total_timesteps | 9725952 | +| train/ | | +| approx_kl | 0.01003425 | +| clip_fraction | 0.281 | +| clip_range | 0.0726 | +| entropy_loss | -7.03 | +| explained_variance | 0.138 | +| learning_rate | 4.77e-05 | +| loss | -0.0249 | +| n_updates | 34812 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000213 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.429 | +| time/ | | +| fps | 1419 | +| iterations | 4750 | +| time_elapsed | 6852 | +| total_timesteps | 9728000 | +| train/ | | +| approx_kl | 0.012093134 | +| clip_fraction | 0.344 | +| clip_range | 0.0726 | +| entropy_loss | -7.39 | +| explained_variance | -0.161 | +| learning_rate | 4.77e-05 | +| loss | -0.0264 | +| n_updates | 34816 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000123 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.429 | +| time/ | | +| fps | 1419 | +| iterations | 4751 | +| time_elapsed | 6853 | +| total_timesteps | 9730048 | +| train/ | | +| approx_kl | 0.010747565 | +| clip_fraction | 0.318 | +| clip_range | 0.0726 | +| entropy_loss | -7.38 | +| explained_variance | -0.13 | +| learning_rate | 4.77e-05 | +| loss | -0.0313 | +| n_updates | 34820 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000115 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.426 | +| time/ | | +| fps | 1419 | +| iterations | 4752 | +| time_elapsed | 6854 | +| total_timesteps | 9732096 | +| train/ | | +| approx_kl | 0.011864012 | +| clip_fraction | 0.298 | +| clip_range | 0.0726 | +| entropy_loss | -7.51 | +| explained_variance | -0.163 | +| learning_rate | 4.77e-05 | +| loss | -0.0394 | +| n_updates | 34824 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.00013 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.423 | +| time/ | | +| fps | 1419 | +| iterations | 4753 | +| time_elapsed | 6856 | +| total_timesteps | 9734144 | +| train/ | | +| approx_kl | 0.0103977695 | +| clip_fraction | 0.304 | +| clip_range | 0.0726 | +| entropy_loss | -7.01 | +| explained_variance | 0.383 | +| learning_rate | 4.77e-05 | +| loss | -0.0307 | +| n_updates | 34828 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000184 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.424 | +| time/ | | +| fps | 1419 | +| iterations | 4754 | +| time_elapsed | 6857 | +| total_timesteps | 9736192 | +| train/ | | +| approx_kl | 0.009996856 | +| clip_fraction | 0.303 | +| clip_range | 0.0726 | +| entropy_loss | -7.19 | +| explained_variance | 0.127 | +| learning_rate | 4.77e-05 | +| loss | -0.0276 | +| n_updates | 34832 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000133 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.422 | +| time/ | | +| fps | 1419 | +| iterations | 4755 | +| time_elapsed | 6859 | +| total_timesteps | 9738240 | +| train/ | | +| approx_kl | 0.009270979 | +| clip_fraction | 0.278 | +| clip_range | 0.0726 | +| entropy_loss | -6.66 | +| explained_variance | 0.382 | +| learning_rate | 4.77e-05 | +| loss | -0.0287 | +| n_updates | 34836 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000288 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.422 | +| time/ | | +| fps | 1419 | +| iterations | 4756 | +| time_elapsed | 6860 | +| total_timesteps | 9740288 | +| train/ | | +| approx_kl | 0.011121003 | +| clip_fraction | 0.329 | +| clip_range | 0.0726 | +| entropy_loss | -6.66 | +| explained_variance | 0.398 | +| learning_rate | 4.77e-05 | +| loss | -0.0275 | +| n_updates | 34840 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000207 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.419 | +| time/ | | +| fps | 1419 | +| iterations | 4757 | +| time_elapsed | 6862 | +| total_timesteps | 9742336 | +| train/ | | +| approx_kl | 0.012440995 | +| clip_fraction | 0.321 | +| clip_range | 0.0726 | +| entropy_loss | -7.3 | +| explained_variance | -0.0668 | +| learning_rate | 4.77e-05 | +| loss | -0.0292 | +| n_updates | 34844 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.00014 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.425 | +| time/ | | +| fps | 1419 | +| iterations | 4758 | +| time_elapsed | 6863 | +| total_timesteps | 9744384 | +| train/ | | +| approx_kl | 0.010299071 | +| clip_fraction | 0.33 | +| clip_range | 0.0726 | +| entropy_loss | -7.04 | +| explained_variance | 0.282 | +| learning_rate | 4.77e-05 | +| loss | -0.0323 | +| n_updates | 34848 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000178 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.425 | +| time/ | | +| fps | 1419 | +| iterations | 4759 | +| time_elapsed | 6864 | +| total_timesteps | 9746432 | +| train/ | | +| approx_kl | 0.009929879 | +| clip_fraction | 0.315 | +| clip_range | 0.0726 | +| entropy_loss | -7.22 | +| explained_variance | 0.234 | +| learning_rate | 4.77e-05 | +| loss | -0.0319 | +| n_updates | 34852 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000268 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.422 | +| time/ | | +| fps | 1419 | +| iterations | 4760 | +| time_elapsed | 6866 | +| total_timesteps | 9748480 | +| train/ | | +| approx_kl | 0.011718239 | +| clip_fraction | 0.333 | +| clip_range | 0.0726 | +| entropy_loss | -7.32 | +| explained_variance | -0.141 | +| learning_rate | 4.77e-05 | +| loss | -0.0287 | +| n_updates | 34856 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000163 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.422 | +| time/ | | +| fps | 1419 | +| iterations | 4761 | +| time_elapsed | 6867 | +| total_timesteps | 9750528 | +| train/ | | +| approx_kl | 0.01183638 | +| clip_fraction | 0.349 | +| clip_range | 0.0726 | +| entropy_loss | -7.05 | +| explained_variance | 0.406 | +| learning_rate | 4.77e-05 | +| loss | -0.0314 | +| n_updates | 34860 | +| policy_gradient_loss | -0.0223 | +| value_loss | 0.000121 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.43 | +| time/ | | +| fps | 1419 | +| iterations | 4762 | +| time_elapsed | 6869 | +| total_timesteps | 9752576 | +| train/ | | +| approx_kl | 0.014118703 | +| clip_fraction | 0.333 | +| clip_range | 0.0726 | +| entropy_loss | -7.38 | +| explained_variance | -0.241 | +| learning_rate | 4.77e-05 | +| loss | -0.0356 | +| n_updates | 34864 | +| policy_gradient_loss | -0.0234 | +| value_loss | 7.41e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.424 | +| time/ | | +| fps | 1419 | +| iterations | 4763 | +| time_elapsed | 6870 | +| total_timesteps | 9754624 | +| train/ | | +| approx_kl | 0.011458861 | +| clip_fraction | 0.314 | +| clip_range | 0.0726 | +| entropy_loss | -7.06 | +| explained_variance | 0.349 | +| learning_rate | 4.77e-05 | +| loss | -0.0216 | +| n_updates | 34868 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000267 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.419 | +| time/ | | +| fps | 1419 | +| iterations | 4764 | +| time_elapsed | 6872 | +| total_timesteps | 9756672 | +| train/ | | +| approx_kl | 0.01092496 | +| clip_fraction | 0.335 | +| clip_range | 0.0726 | +| entropy_loss | -7.15 | +| explained_variance | 0.527 | +| learning_rate | 4.77e-05 | +| loss | -0.0368 | +| n_updates | 34872 | +| policy_gradient_loss | -0.0242 | +| value_loss | 7.03e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.412 | +| time/ | | +| fps | 1419 | +| iterations | 4765 | +| time_elapsed | 6873 | +| total_timesteps | 9758720 | +| train/ | | +| approx_kl | 0.011409963 | +| clip_fraction | 0.319 | +| clip_range | 0.0726 | +| entropy_loss | -6.94 | +| explained_variance | 0.368 | +| learning_rate | 4.77e-05 | +| loss | -0.0287 | +| n_updates | 34876 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000153 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.409 | +| time/ | | +| fps | 1419 | +| iterations | 4766 | +| time_elapsed | 6875 | +| total_timesteps | 9760768 | +| train/ | | +| approx_kl | 0.009177981 | +| clip_fraction | 0.318 | +| clip_range | 0.0726 | +| entropy_loss | -7.07 | +| explained_variance | 0.446 | +| learning_rate | 4.77e-05 | +| loss | -0.0326 | +| n_updates | 34880 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000108 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.402 | +| time/ | | +| fps | 1419 | +| iterations | 4767 | +| time_elapsed | 6876 | +| total_timesteps | 9762816 | +| train/ | | +| approx_kl | 0.012950474 | +| clip_fraction | 0.291 | +| clip_range | 0.0726 | +| entropy_loss | -7.06 | +| explained_variance | 0.311 | +| learning_rate | 4.77e-05 | +| loss | -0.0251 | +| n_updates | 34884 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000139 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.399 | +| time/ | | +| fps | 1419 | +| iterations | 4768 | +| time_elapsed | 6877 | +| total_timesteps | 9764864 | +| train/ | | +| approx_kl | 0.011337124 | +| clip_fraction | 0.32 | +| clip_range | 0.0726 | +| entropy_loss | -6.91 | +| explained_variance | 0.62 | +| learning_rate | 4.77e-05 | +| loss | -0.033 | +| n_updates | 34888 | +| policy_gradient_loss | -0.0201 | +| value_loss | 8.21e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.399 | +| time/ | | +| fps | 1419 | +| iterations | 4769 | +| time_elapsed | 6879 | +| total_timesteps | 9766912 | +| train/ | | +| approx_kl | 0.007580713 | +| clip_fraction | 0.262 | +| clip_range | 0.0726 | +| entropy_loss | -6.67 | +| explained_variance | 0.495 | +| learning_rate | 4.77e-05 | +| loss | -0.0143 | +| n_updates | 34892 | +| policy_gradient_loss | -0.0134 | +| value_loss | 0.000222 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.397 | +| time/ | | +| fps | 1419 | +| iterations | 4770 | +| time_elapsed | 6880 | +| total_timesteps | 9768960 | +| train/ | | +| approx_kl | 0.011244905 | +| clip_fraction | 0.319 | +| clip_range | 0.0726 | +| entropy_loss | -7.03 | +| explained_variance | 0.359 | +| learning_rate | 4.77e-05 | +| loss | -0.0307 | +| n_updates | 34896 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000166 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.398 | +| time/ | | +| fps | 1419 | +| iterations | 4771 | +| time_elapsed | 6882 | +| total_timesteps | 9771008 | +| train/ | | +| approx_kl | 0.011983659 | +| clip_fraction | 0.314 | +| clip_range | 0.0726 | +| entropy_loss | -7.18 | +| explained_variance | 0.345 | +| learning_rate | 4.77e-05 | +| loss | -0.037 | +| n_updates | 34900 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000128 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.393 | +| time/ | | +| fps | 1419 | +| iterations | 4772 | +| time_elapsed | 6883 | +| total_timesteps | 9773056 | +| train/ | | +| approx_kl | 0.0127648 | +| clip_fraction | 0.336 | +| clip_range | 0.0726 | +| entropy_loss | -7.37 | +| explained_variance | -0.0874 | +| learning_rate | 4.77e-05 | +| loss | -0.041 | +| n_updates | 34904 | +| policy_gradient_loss | -0.023 | +| value_loss | 7.63e-05 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.385 | +| time/ | | +| fps | 1419 | +| iterations | 4773 | +| time_elapsed | 6885 | +| total_timesteps | 9775104 | +| train/ | | +| approx_kl | 0.010876263 | +| clip_fraction | 0.298 | +| clip_range | 0.0726 | +| entropy_loss | -7.26 | +| explained_variance | -0.231 | +| learning_rate | 4.77e-05 | +| loss | -0.0303 | +| n_updates | 34908 | +| policy_gradient_loss | -0.0203 | +| value_loss | 9.19e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.387 | +| time/ | | +| fps | 1419 | +| iterations | 4774 | +| time_elapsed | 6886 | +| total_timesteps | 9777152 | +| train/ | | +| approx_kl | 0.011052591 | +| clip_fraction | 0.315 | +| clip_range | 0.0726 | +| entropy_loss | -6.79 | +| explained_variance | 0.458 | +| learning_rate | 4.77e-05 | +| loss | -0.033 | +| n_updates | 34912 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.00019 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.386 | +| time/ | | +| fps | 1419 | +| iterations | 4775 | +| time_elapsed | 6888 | +| total_timesteps | 9779200 | +| train/ | | +| approx_kl | 0.009586906 | +| clip_fraction | 0.316 | +| clip_range | 0.0726 | +| entropy_loss | -6.93 | +| explained_variance | 0.425 | +| learning_rate | 4.77e-05 | +| loss | -0.024 | +| n_updates | 34916 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000154 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1419 | +| iterations | 4776 | +| time_elapsed | 6889 | +| total_timesteps | 9781248 | +| train/ | | +| approx_kl | 0.011647768 | +| clip_fraction | 0.331 | +| clip_range | 0.0726 | +| entropy_loss | -7.34 | +| explained_variance | -0.0791 | +| learning_rate | 4.77e-05 | +| loss | -0.0293 | +| n_updates | 34920 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000137 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1419 | +| iterations | 4777 | +| time_elapsed | 6890 | +| total_timesteps | 9783296 | +| train/ | | +| approx_kl | 0.010821603 | +| clip_fraction | 0.304 | +| clip_range | 0.0726 | +| entropy_loss | -6.94 | +| explained_variance | 0.468 | +| learning_rate | 4.77e-05 | +| loss | -0.0213 | +| n_updates | 34924 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000187 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1419 | +| iterations | 4778 | +| time_elapsed | 6892 | +| total_timesteps | 9785344 | +| train/ | | +| approx_kl | 0.014211595 | +| clip_fraction | 0.347 | +| clip_range | 0.0726 | +| entropy_loss | -6.67 | +| explained_variance | 0.814 | +| learning_rate | 4.77e-05 | +| loss | -0.0426 | +| n_updates | 34928 | +| policy_gradient_loss | -0.0242 | +| value_loss | 5.54e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1419 | +| iterations | 4779 | +| time_elapsed | 6893 | +| total_timesteps | 9787392 | +| train/ | | +| approx_kl | 0.010999719 | +| clip_fraction | 0.299 | +| clip_range | 0.0726 | +| entropy_loss | -6.84 | +| explained_variance | 0.415 | +| learning_rate | 4.77e-05 | +| loss | -0.0231 | +| n_updates | 34932 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.00021 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1419 | +| iterations | 4780 | +| time_elapsed | 6895 | +| total_timesteps | 9789440 | +| train/ | | +| approx_kl | 0.012041744 | +| clip_fraction | 0.319 | +| clip_range | 0.0726 | +| entropy_loss | -7.43 | +| explained_variance | 0.00565 | +| learning_rate | 4.77e-05 | +| loss | -0.0315 | +| n_updates | 34936 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000108 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1419 | +| iterations | 4781 | +| time_elapsed | 6896 | +| total_timesteps | 9791488 | +| train/ | | +| approx_kl | 0.012733583 | +| clip_fraction | 0.313 | +| clip_range | 0.0726 | +| entropy_loss | -7.05 | +| explained_variance | 0.554 | +| learning_rate | 4.77e-05 | +| loss | -0.0334 | +| n_updates | 34940 | +| policy_gradient_loss | -0.0198 | +| value_loss | 9.93e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1419 | +| iterations | 4782 | +| time_elapsed | 6898 | +| total_timesteps | 9793536 | +| train/ | | +| approx_kl | 0.013914878 | +| clip_fraction | 0.331 | +| clip_range | 0.0726 | +| entropy_loss | -7.14 | +| explained_variance | 0.254 | +| learning_rate | 4.77e-05 | +| loss | -0.0331 | +| n_updates | 34944 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000198 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1419 | +| iterations | 4783 | +| time_elapsed | 6899 | +| total_timesteps | 9795584 | +| train/ | | +| approx_kl | 0.015545507 | +| clip_fraction | 0.319 | +| clip_range | 0.0726 | +| entropy_loss | -7.08 | +| explained_variance | 0.569 | +| learning_rate | 4.77e-05 | +| loss | -0.0332 | +| n_updates | 34948 | +| policy_gradient_loss | -0.0206 | +| value_loss | 8.03e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1419 | +| iterations | 4784 | +| time_elapsed | 6901 | +| total_timesteps | 9797632 | +| train/ | | +| approx_kl | 0.010153124 | +| clip_fraction | 0.318 | +| clip_range | 0.0726 | +| entropy_loss | -6.9 | +| explained_variance | 0.646 | +| learning_rate | 4.77e-05 | +| loss | -0.0296 | +| n_updates | 34952 | +| policy_gradient_loss | -0.0179 | +| value_loss | 8.61e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1419 | +| iterations | 4785 | +| time_elapsed | 6902 | +| total_timesteps | 9799680 | +| train/ | | +| approx_kl | 0.011663897 | +| clip_fraction | 0.329 | +| clip_range | 0.0726 | +| entropy_loss | -6.79 | +| explained_variance | 0.42 | +| learning_rate | 4.77e-05 | +| loss | -0.0325 | +| n_updates | 34956 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000113 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1419 | +| iterations | 4786 | +| time_elapsed | 6903 | +| total_timesteps | 9801728 | +| train/ | | +| approx_kl | 0.00956638 | +| clip_fraction | 0.28 | +| clip_range | 0.0726 | +| entropy_loss | -6.93 | +| explained_variance | 0.16 | +| learning_rate | 4.77e-05 | +| loss | -0.0207 | +| n_updates | 34960 | +| policy_gradient_loss | -0.0144 | +| value_loss | 0.000445 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1419 | +| iterations | 4787 | +| time_elapsed | 6905 | +| total_timesteps | 9803776 | +| train/ | | +| approx_kl | 0.0126277255 | +| clip_fraction | 0.35 | +| clip_range | 0.0725 | +| entropy_loss | -6.53 | +| explained_variance | 0.512 | +| learning_rate | 4.77e-05 | +| loss | -0.0316 | +| n_updates | 34964 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000167 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1419 | +| iterations | 4788 | +| time_elapsed | 6906 | +| total_timesteps | 9805824 | +| train/ | | +| approx_kl | 0.012252503 | +| clip_fraction | 0.349 | +| clip_range | 0.0725 | +| entropy_loss | -7.5 | +| explained_variance | -0.101 | +| learning_rate | 4.77e-05 | +| loss | -0.0381 | +| n_updates | 34968 | +| policy_gradient_loss | -0.0228 | +| value_loss | 0.000114 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1419 | +| iterations | 4789 | +| time_elapsed | 6908 | +| total_timesteps | 9807872 | +| train/ | | +| approx_kl | 0.010352043 | +| clip_fraction | 0.318 | +| clip_range | 0.0725 | +| entropy_loss | -7.08 | +| explained_variance | 0.298 | +| learning_rate | 4.77e-05 | +| loss | -0.0328 | +| n_updates | 34972 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000318 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1419 | +| iterations | 4790 | +| time_elapsed | 6909 | +| total_timesteps | 9809920 | +| train/ | | +| approx_kl | 0.011175232 | +| clip_fraction | 0.349 | +| clip_range | 0.0725 | +| entropy_loss | -7.19 | +| explained_variance | -0.0656 | +| learning_rate | 4.77e-05 | +| loss | -0.0352 | +| n_updates | 34976 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000157 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1419 | +| iterations | 4791 | +| time_elapsed | 6911 | +| total_timesteps | 9811968 | +| train/ | | +| approx_kl | 0.010523069 | +| clip_fraction | 0.288 | +| clip_range | 0.0725 | +| entropy_loss | -7.03 | +| explained_variance | 0.399 | +| learning_rate | 4.77e-05 | +| loss | -0.0297 | +| n_updates | 34980 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.0002 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1419 | +| iterations | 4792 | +| time_elapsed | 6912 | +| total_timesteps | 9814016 | +| train/ | | +| approx_kl | 0.010511819 | +| clip_fraction | 0.311 | +| clip_range | 0.0725 | +| entropy_loss | -7.17 | +| explained_variance | -0.0297 | +| learning_rate | 4.77e-05 | +| loss | -0.0255 | +| n_updates | 34984 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000137 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1419 | +| iterations | 4793 | +| time_elapsed | 6914 | +| total_timesteps | 9816064 | +| train/ | | +| approx_kl | 0.010243744 | +| clip_fraction | 0.285 | +| clip_range | 0.0725 | +| entropy_loss | -6.54 | +| explained_variance | 0.582 | +| learning_rate | 4.77e-05 | +| loss | -0.028 | +| n_updates | 34988 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000196 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1419 | +| iterations | 4794 | +| time_elapsed | 6915 | +| total_timesteps | 9818112 | +| train/ | | +| approx_kl | 0.012958018 | +| clip_fraction | 0.302 | +| clip_range | 0.0725 | +| entropy_loss | -6.8 | +| explained_variance | 0.457 | +| learning_rate | 4.77e-05 | +| loss | -0.0273 | +| n_updates | 34992 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000198 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1419 | +| iterations | 4795 | +| time_elapsed | 6916 | +| total_timesteps | 9820160 | +| train/ | | +| approx_kl | 0.010283865 | +| clip_fraction | 0.305 | +| clip_range | 0.0725 | +| entropy_loss | -7.19 | +| explained_variance | 0.241 | +| learning_rate | 4.77e-05 | +| loss | -0.0272 | +| n_updates | 34996 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000197 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1419 | +| iterations | 4796 | +| time_elapsed | 6918 | +| total_timesteps | 9822208 | +| train/ | | +| approx_kl | 0.011213849 | +| clip_fraction | 0.327 | +| clip_range | 0.0725 | +| entropy_loss | -6.91 | +| explained_variance | 0.434 | +| learning_rate | 4.77e-05 | +| loss | -0.0366 | +| n_updates | 35000 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000175 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1419 | +| iterations | 4797 | +| time_elapsed | 6919 | +| total_timesteps | 9824256 | +| train/ | | +| approx_kl | 0.011722848 | +| clip_fraction | 0.324 | +| clip_range | 0.0725 | +| entropy_loss | -7.18 | +| explained_variance | 0.228 | +| learning_rate | 4.77e-05 | +| loss | -0.0347 | +| n_updates | 35004 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.00017 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1419 | +| iterations | 4798 | +| time_elapsed | 6921 | +| total_timesteps | 9826304 | +| train/ | | +| approx_kl | 0.012364169 | +| clip_fraction | 0.335 | +| clip_range | 0.0725 | +| entropy_loss | -7.11 | +| explained_variance | 0.425 | +| learning_rate | 4.77e-05 | +| loss | -0.0381 | +| n_updates | 35008 | +| policy_gradient_loss | -0.023 | +| value_loss | 8.72e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1419 | +| iterations | 4799 | +| time_elapsed | 6922 | +| total_timesteps | 9828352 | +| train/ | | +| approx_kl | 0.0109458575 | +| clip_fraction | 0.316 | +| clip_range | 0.0725 | +| entropy_loss | -7.45 | +| explained_variance | -0.0957 | +| learning_rate | 4.77e-05 | +| loss | -0.0326 | +| n_updates | 35012 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.00015 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1419 | +| iterations | 4800 | +| time_elapsed | 6924 | +| total_timesteps | 9830400 | +| train/ | | +| approx_kl | 0.008548068 | +| clip_fraction | 0.281 | +| clip_range | 0.0725 | +| entropy_loss | -6.98 | +| explained_variance | 0.406 | +| learning_rate | 4.77e-05 | +| loss | -0.0218 | +| n_updates | 35016 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000185 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1419 | +| iterations | 4801 | +| time_elapsed | 6925 | +| total_timesteps | 9832448 | +| train/ | | +| approx_kl | 0.010287236 | +| clip_fraction | 0.295 | +| clip_range | 0.0725 | +| entropy_loss | -6.95 | +| explained_variance | 0.317 | +| learning_rate | 4.77e-05 | +| loss | -0.0301 | +| n_updates | 35020 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000228 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1419 | +| iterations | 4802 | +| time_elapsed | 6926 | +| total_timesteps | 9834496 | +| train/ | | +| approx_kl | 0.011106306 | +| clip_fraction | 0.317 | +| clip_range | 0.0725 | +| entropy_loss | -6.76 | +| explained_variance | 0.582 | +| learning_rate | 4.77e-05 | +| loss | -0.0307 | +| n_updates | 35024 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000121 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1419 | +| iterations | 4803 | +| time_elapsed | 6928 | +| total_timesteps | 9836544 | +| train/ | | +| approx_kl | 0.015378866 | +| clip_fraction | 0.353 | +| clip_range | 0.0725 | +| entropy_loss | -7.04 | +| explained_variance | 0.492 | +| learning_rate | 4.77e-05 | +| loss | -0.0354 | +| n_updates | 35028 | +| policy_gradient_loss | -0.022 | +| value_loss | 5.5e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1419 | +| iterations | 4804 | +| time_elapsed | 6929 | +| total_timesteps | 9838592 | +| train/ | | +| approx_kl | 0.01150424 | +| clip_fraction | 0.331 | +| clip_range | 0.0725 | +| entropy_loss | -7.18 | +| explained_variance | 0.317 | +| learning_rate | 4.77e-05 | +| loss | -0.0317 | +| n_updates | 35032 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000139 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1419 | +| iterations | 4805 | +| time_elapsed | 6931 | +| total_timesteps | 9840640 | +| train/ | | +| approx_kl | 0.012839304 | +| clip_fraction | 0.328 | +| clip_range | 0.0725 | +| entropy_loss | -7.18 | +| explained_variance | 0.274 | +| learning_rate | 4.77e-05 | +| loss | -0.0341 | +| n_updates | 35036 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000202 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1419 | +| iterations | 4806 | +| time_elapsed | 6932 | +| total_timesteps | 9842688 | +| train/ | | +| approx_kl | 0.010776766 | +| clip_fraction | 0.335 | +| clip_range | 0.0725 | +| entropy_loss | -6.77 | +| explained_variance | 0.499 | +| learning_rate | 4.77e-05 | +| loss | -0.0331 | +| n_updates | 35040 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000147 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1419 | +| iterations | 4807 | +| time_elapsed | 6934 | +| total_timesteps | 9844736 | +| train/ | | +| approx_kl | 0.010099396 | +| clip_fraction | 0.302 | +| clip_range | 0.0725 | +| entropy_loss | -6.83 | +| explained_variance | 0.403 | +| learning_rate | 4.77e-05 | +| loss | -0.0296 | +| n_updates | 35044 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000296 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1419 | +| iterations | 4808 | +| time_elapsed | 6935 | +| total_timesteps | 9846784 | +| train/ | | +| approx_kl | 0.011097815 | +| clip_fraction | 0.271 | +| clip_range | 0.0725 | +| entropy_loss | -7 | +| explained_variance | 0.395 | +| learning_rate | 4.77e-05 | +| loss | -0.0256 | +| n_updates | 35048 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000205 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1419 | +| iterations | 4809 | +| time_elapsed | 6937 | +| total_timesteps | 9848832 | +| train/ | | +| approx_kl | 0.012017748 | +| clip_fraction | 0.34 | +| clip_range | 0.0725 | +| entropy_loss | -7.18 | +| explained_variance | -0.0562 | +| learning_rate | 4.77e-05 | +| loss | -0.0326 | +| n_updates | 35052 | +| policy_gradient_loss | -0.0228 | +| value_loss | 0.000131 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1419 | +| iterations | 4810 | +| time_elapsed | 6938 | +| total_timesteps | 9850880 | +| train/ | | +| approx_kl | 0.011715417 | +| clip_fraction | 0.325 | +| clip_range | 0.0725 | +| entropy_loss | -7.3 | +| explained_variance | 0.352 | +| learning_rate | 4.77e-05 | +| loss | -0.0354 | +| n_updates | 35056 | +| policy_gradient_loss | -0.0225 | +| value_loss | 0.000118 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1419 | +| iterations | 4811 | +| time_elapsed | 6939 | +| total_timesteps | 9852928 | +| train/ | | +| approx_kl | 0.012017641 | +| clip_fraction | 0.331 | +| clip_range | 0.0725 | +| entropy_loss | -7.31 | +| explained_variance | -0.0687 | +| learning_rate | 4.77e-05 | +| loss | -0.0355 | +| n_updates | 35060 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000192 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1419 | +| iterations | 4812 | +| time_elapsed | 6941 | +| total_timesteps | 9854976 | +| train/ | | +| approx_kl | 0.009328682 | +| clip_fraction | 0.289 | +| clip_range | 0.0725 | +| entropy_loss | -7.29 | +| explained_variance | 0.118 | +| learning_rate | 4.77e-05 | +| loss | -0.0259 | +| n_updates | 35064 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000341 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1419 | +| iterations | 4813 | +| time_elapsed | 6942 | +| total_timesteps | 9857024 | +| train/ | | +| approx_kl | 0.011070989 | +| clip_fraction | 0.345 | +| clip_range | 0.0725 | +| entropy_loss | -6.45 | +| explained_variance | 0.76 | +| learning_rate | 4.77e-05 | +| loss | -0.0401 | +| n_updates | 35068 | +| policy_gradient_loss | -0.0237 | +| value_loss | 8.52e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1419 | +| iterations | 4814 | +| time_elapsed | 6944 | +| total_timesteps | 9859072 | +| train/ | | +| approx_kl | 0.011719465 | +| clip_fraction | 0.323 | +| clip_range | 0.0725 | +| entropy_loss | -6.79 | +| explained_variance | 0.441 | +| learning_rate | 4.77e-05 | +| loss | -0.0328 | +| n_updates | 35072 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000136 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1419 | +| iterations | 4815 | +| time_elapsed | 6945 | +| total_timesteps | 9861120 | +| train/ | | +| approx_kl | 0.01275561 | +| clip_fraction | 0.326 | +| clip_range | 0.0725 | +| entropy_loss | -6.86 | +| explained_variance | 0.387 | +| learning_rate | 4.77e-05 | +| loss | -0.0256 | +| n_updates | 35076 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.00021 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1419 | +| iterations | 4816 | +| time_elapsed | 6947 | +| total_timesteps | 9863168 | +| train/ | | +| approx_kl | 0.012840588 | +| clip_fraction | 0.314 | +| clip_range | 0.0725 | +| entropy_loss | -7 | +| explained_variance | 0.378 | +| learning_rate | 4.77e-05 | +| loss | -0.032 | +| n_updates | 35080 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000183 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1419 | +| iterations | 4817 | +| time_elapsed | 6948 | +| total_timesteps | 9865216 | +| train/ | | +| approx_kl | 0.01279822 | +| clip_fraction | 0.343 | +| clip_range | 0.0725 | +| entropy_loss | -7.31 | +| explained_variance | -0.0739 | +| learning_rate | 4.77e-05 | +| loss | -0.0307 | +| n_updates | 35084 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000105 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1419 | +| iterations | 4818 | +| time_elapsed | 6949 | +| total_timesteps | 9867264 | +| train/ | | +| approx_kl | 0.011180783 | +| clip_fraction | 0.333 | +| clip_range | 0.0725 | +| entropy_loss | -7.38 | +| explained_variance | 0.506 | +| learning_rate | 4.77e-05 | +| loss | -0.0338 | +| n_updates | 35088 | +| policy_gradient_loss | -0.0208 | +| value_loss | 7.99e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1419 | +| iterations | 4819 | +| time_elapsed | 6951 | +| total_timesteps | 9869312 | +| train/ | | +| approx_kl | 0.010138601 | +| clip_fraction | 0.289 | +| clip_range | 0.0725 | +| entropy_loss | -6.98 | +| explained_variance | 0.377 | +| learning_rate | 4.77e-05 | +| loss | -0.0298 | +| n_updates | 35092 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000152 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1419 | +| iterations | 4820 | +| time_elapsed | 6952 | +| total_timesteps | 9871360 | +| train/ | | +| approx_kl | 0.013552254 | +| clip_fraction | 0.333 | +| clip_range | 0.0725 | +| entropy_loss | -7.02 | +| explained_variance | 0.213 | +| learning_rate | 4.77e-05 | +| loss | -0.0337 | +| n_updates | 35096 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000103 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1419 | +| iterations | 4821 | +| time_elapsed | 6954 | +| total_timesteps | 9873408 | +| train/ | | +| approx_kl | 0.010960693 | +| clip_fraction | 0.32 | +| clip_range | 0.0725 | +| entropy_loss | -6.99 | +| explained_variance | 0.323 | +| learning_rate | 4.77e-05 | +| loss | -0.0263 | +| n_updates | 35100 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000141 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1419 | +| iterations | 4822 | +| time_elapsed | 6955 | +| total_timesteps | 9875456 | +| train/ | | +| approx_kl | 0.009911785 | +| clip_fraction | 0.312 | +| clip_range | 0.0725 | +| entropy_loss | -7.29 | +| explained_variance | -0.0902 | +| learning_rate | 4.77e-05 | +| loss | -0.0417 | +| n_updates | 35104 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000123 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1419 | +| iterations | 4823 | +| time_elapsed | 6957 | +| total_timesteps | 9877504 | +| train/ | | +| approx_kl | 0.010297325 | +| clip_fraction | 0.324 | +| clip_range | 0.0725 | +| entropy_loss | -6.9 | +| explained_variance | 0.559 | +| learning_rate | 4.77e-05 | +| loss | -0.0312 | +| n_updates | 35108 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000105 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1419 | +| iterations | 4824 | +| time_elapsed | 6958 | +| total_timesteps | 9879552 | +| train/ | | +| approx_kl | 0.010834636 | +| clip_fraction | 0.309 | +| clip_range | 0.0725 | +| entropy_loss | -6.33 | +| explained_variance | 0.501 | +| learning_rate | 4.77e-05 | +| loss | -0.0256 | +| n_updates | 35112 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000351 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1419 | +| iterations | 4825 | +| time_elapsed | 6959 | +| total_timesteps | 9881600 | +| train/ | | +| approx_kl | 0.01273197 | +| clip_fraction | 0.319 | +| clip_range | 0.0725 | +| entropy_loss | -6.66 | +| explained_variance | 0.35 | +| learning_rate | 4.77e-05 | +| loss | -0.0313 | +| n_updates | 35116 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.0002 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1419 | +| iterations | 4826 | +| time_elapsed | 6961 | +| total_timesteps | 9883648 | +| train/ | | +| approx_kl | 0.011844788 | +| clip_fraction | 0.343 | +| clip_range | 0.0725 | +| entropy_loss | -7.03 | +| explained_variance | 0.181 | +| learning_rate | 4.77e-05 | +| loss | -0.0432 | +| n_updates | 35120 | +| policy_gradient_loss | -0.0229 | +| value_loss | 9.32e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1419 | +| iterations | 4827 | +| time_elapsed | 6962 | +| total_timesteps | 9885696 | +| train/ | | +| approx_kl | 0.013798863 | +| clip_fraction | 0.332 | +| clip_range | 0.0725 | +| entropy_loss | -7.04 | +| explained_variance | 0.452 | +| learning_rate | 4.77e-05 | +| loss | -0.0316 | +| n_updates | 35124 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.00014 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1419 | +| iterations | 4828 | +| time_elapsed | 6964 | +| total_timesteps | 9887744 | +| train/ | | +| approx_kl | 0.009926526 | +| clip_fraction | 0.339 | +| clip_range | 0.0725 | +| entropy_loss | -7.43 | +| explained_variance | -0.289 | +| learning_rate | 4.77e-05 | +| loss | -0.03 | +| n_updates | 35128 | +| policy_gradient_loss | -0.0226 | +| value_loss | 7.5e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1419 | +| iterations | 4829 | +| time_elapsed | 6965 | +| total_timesteps | 9889792 | +| train/ | | +| approx_kl | 0.009729337 | +| clip_fraction | 0.293 | +| clip_range | 0.0725 | +| entropy_loss | -7.11 | +| explained_variance | 0.33 | +| learning_rate | 4.77e-05 | +| loss | -0.0318 | +| n_updates | 35132 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000251 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1419 | +| iterations | 4830 | +| time_elapsed | 6966 | +| total_timesteps | 9891840 | +| train/ | | +| approx_kl | 0.0106029725 | +| clip_fraction | 0.32 | +| clip_range | 0.0725 | +| entropy_loss | -7.29 | +| explained_variance | -0.0669 | +| learning_rate | 4.77e-05 | +| loss | -0.0299 | +| n_updates | 35136 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000178 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1419 | +| iterations | 4831 | +| time_elapsed | 6968 | +| total_timesteps | 9893888 | +| train/ | | +| approx_kl | 0.012653539 | +| clip_fraction | 0.311 | +| clip_range | 0.0725 | +| entropy_loss | -7.17 | +| explained_variance | -0.00414 | +| learning_rate | 4.77e-05 | +| loss | -0.0319 | +| n_updates | 35140 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.00016 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1419 | +| iterations | 4832 | +| time_elapsed | 6969 | +| total_timesteps | 9895936 | +| train/ | | +| approx_kl | 0.010724503 | +| clip_fraction | 0.314 | +| clip_range | 0.0725 | +| entropy_loss | -6.7 | +| explained_variance | 0.548 | +| learning_rate | 4.77e-05 | +| loss | -0.0279 | +| n_updates | 35144 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000187 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1419 | +| iterations | 4833 | +| time_elapsed | 6971 | +| total_timesteps | 9897984 | +| train/ | | +| approx_kl | 0.0116919875 | +| clip_fraction | 0.329 | +| clip_range | 0.0725 | +| entropy_loss | -7.02 | +| explained_variance | 0.482 | +| learning_rate | 4.76e-05 | +| loss | -0.0321 | +| n_updates | 35148 | +| policy_gradient_loss | -0.0203 | +| value_loss | 8.2e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1419 | +| iterations | 4834 | +| time_elapsed | 6972 | +| total_timesteps | 9900032 | +| train/ | | +| approx_kl | 0.010561681 | +| clip_fraction | 0.311 | +| clip_range | 0.0725 | +| entropy_loss | -7.38 | +| explained_variance | -0.191 | +| learning_rate | 4.76e-05 | +| loss | -0.0347 | +| n_updates | 35152 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000134 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1419 | +| iterations | 4835 | +| time_elapsed | 6974 | +| total_timesteps | 9902080 | +| train/ | | +| approx_kl | 0.009928393 | +| clip_fraction | 0.312 | +| clip_range | 0.0725 | +| entropy_loss | -7.02 | +| explained_variance | 0.432 | +| learning_rate | 4.76e-05 | +| loss | -0.0242 | +| n_updates | 35156 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000208 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1419 | +| iterations | 4836 | +| time_elapsed | 6975 | +| total_timesteps | 9904128 | +| train/ | | +| approx_kl | 0.010495748 | +| clip_fraction | 0.322 | +| clip_range | 0.0725 | +| entropy_loss | -6.86 | +| explained_variance | 0.478 | +| learning_rate | 4.76e-05 | +| loss | -0.041 | +| n_updates | 35160 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000161 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1419 | +| iterations | 4837 | +| time_elapsed | 6976 | +| total_timesteps | 9906176 | +| train/ | | +| approx_kl | 0.011268312 | +| clip_fraction | 0.298 | +| clip_range | 0.0725 | +| entropy_loss | -6.39 | +| explained_variance | 0.74 | +| learning_rate | 4.76e-05 | +| loss | -0.0319 | +| n_updates | 35164 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000102 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1419 | +| iterations | 4838 | +| time_elapsed | 6978 | +| total_timesteps | 9908224 | +| train/ | | +| approx_kl | 0.0125527205 | +| clip_fraction | 0.304 | +| clip_range | 0.0725 | +| entropy_loss | -6.81 | +| explained_variance | 0.256 | +| learning_rate | 4.76e-05 | +| loss | -0.0243 | +| n_updates | 35168 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000231 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1419 | +| iterations | 4839 | +| time_elapsed | 6979 | +| total_timesteps | 9910272 | +| train/ | | +| approx_kl | 0.010748503 | +| clip_fraction | 0.313 | +| clip_range | 0.0725 | +| entropy_loss | -7.05 | +| explained_variance | 0.342 | +| learning_rate | 4.76e-05 | +| loss | -0.0312 | +| n_updates | 35172 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000168 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1419 | +| iterations | 4840 | +| time_elapsed | 6981 | +| total_timesteps | 9912320 | +| train/ | | +| approx_kl | 0.010568723 | +| clip_fraction | 0.297 | +| clip_range | 0.0725 | +| entropy_loss | -7.53 | +| explained_variance | -0.213 | +| learning_rate | 4.76e-05 | +| loss | -0.0342 | +| n_updates | 35176 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000164 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1419 | +| iterations | 4841 | +| time_elapsed | 6982 | +| total_timesteps | 9914368 | +| train/ | | +| approx_kl | 0.010644363 | +| clip_fraction | 0.32 | +| clip_range | 0.0725 | +| entropy_loss | -7.36 | +| explained_variance | -0.0853 | +| learning_rate | 4.76e-05 | +| loss | -0.037 | +| n_updates | 35180 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000205 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1419 | +| iterations | 4842 | +| time_elapsed | 6984 | +| total_timesteps | 9916416 | +| train/ | | +| approx_kl | 0.009275421 | +| clip_fraction | 0.283 | +| clip_range | 0.0725 | +| entropy_loss | -7.09 | +| explained_variance | 0.285 | +| learning_rate | 4.76e-05 | +| loss | -0.0161 | +| n_updates | 35184 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000428 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1419 | +| iterations | 4843 | +| time_elapsed | 6985 | +| total_timesteps | 9918464 | +| train/ | | +| approx_kl | 0.010213104 | +| clip_fraction | 0.333 | +| clip_range | 0.0725 | +| entropy_loss | -7.22 | +| explained_variance | 0.0707 | +| learning_rate | 4.76e-05 | +| loss | -0.0377 | +| n_updates | 35188 | +| policy_gradient_loss | -0.0225 | +| value_loss | 0.000132 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1419 | +| iterations | 4844 | +| time_elapsed | 6986 | +| total_timesteps | 9920512 | +| train/ | | +| approx_kl | 0.012387218 | +| clip_fraction | 0.309 | +| clip_range | 0.0725 | +| entropy_loss | -7.06 | +| explained_variance | 0.235 | +| learning_rate | 4.76e-05 | +| loss | -0.0349 | +| n_updates | 35192 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000165 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1419 | +| iterations | 4845 | +| time_elapsed | 6988 | +| total_timesteps | 9922560 | +| train/ | | +| approx_kl | 0.0103465915 | +| clip_fraction | 0.296 | +| clip_range | 0.0725 | +| entropy_loss | -6.55 | +| explained_variance | 0.503 | +| learning_rate | 4.76e-05 | +| loss | -0.0302 | +| n_updates | 35196 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000201 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1419 | +| iterations | 4846 | +| time_elapsed | 6989 | +| total_timesteps | 9924608 | +| train/ | | +| approx_kl | 0.009213224 | +| clip_fraction | 0.311 | +| clip_range | 0.0725 | +| entropy_loss | -6.61 | +| explained_variance | 0.392 | +| learning_rate | 4.76e-05 | +| loss | -0.0265 | +| n_updates | 35200 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000311 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.39 | +| time/ | | +| fps | 1419 | +| iterations | 4847 | +| time_elapsed | 6991 | +| total_timesteps | 9926656 | +| train/ | | +| approx_kl | 0.012194848 | +| clip_fraction | 0.329 | +| clip_range | 0.0725 | +| entropy_loss | -7.11 | +| explained_variance | -0.187 | +| learning_rate | 4.76e-05 | +| loss | -0.0394 | +| n_updates | 35204 | +| policy_gradient_loss | -0.0244 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.39 | +| time/ | | +| fps | 1419 | +| iterations | 4848 | +| time_elapsed | 6992 | +| total_timesteps | 9928704 | +| train/ | | +| approx_kl | 0.010415716 | +| clip_fraction | 0.314 | +| clip_range | 0.0725 | +| entropy_loss | -7.18 | +| explained_variance | -0.118 | +| learning_rate | 4.76e-05 | +| loss | -0.0414 | +| n_updates | 35208 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.00022 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.387 | +| time/ | | +| fps | 1419 | +| iterations | 4849 | +| time_elapsed | 6994 | +| total_timesteps | 9930752 | +| train/ | | +| approx_kl | 0.012645597 | +| clip_fraction | 0.329 | +| clip_range | 0.0725 | +| entropy_loss | -7.38 | +| explained_variance | -0.0157 | +| learning_rate | 4.76e-05 | +| loss | -0.0376 | +| n_updates | 35212 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.00013 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.391 | +| time/ | | +| fps | 1419 | +| iterations | 4850 | +| time_elapsed | 6995 | +| total_timesteps | 9932800 | +| train/ | | +| approx_kl | 0.009261803 | +| clip_fraction | 0.286 | +| clip_range | 0.0725 | +| entropy_loss | -7.13 | +| explained_variance | 0.045 | +| learning_rate | 4.76e-05 | +| loss | -0.0211 | +| n_updates | 35216 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000378 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.392 | +| time/ | | +| fps | 1419 | +| iterations | 4851 | +| time_elapsed | 6997 | +| total_timesteps | 9934848 | +| train/ | | +| approx_kl | 0.009125518 | +| clip_fraction | 0.295 | +| clip_range | 0.0725 | +| entropy_loss | -6.93 | +| explained_variance | 0.269 | +| learning_rate | 4.76e-05 | +| loss | -0.0247 | +| n_updates | 35220 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000235 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.392 | +| time/ | | +| fps | 1419 | +| iterations | 4852 | +| time_elapsed | 6998 | +| total_timesteps | 9936896 | +| train/ | | +| approx_kl | 0.010774175 | +| clip_fraction | 0.317 | +| clip_range | 0.0725 | +| entropy_loss | -7.26 | +| explained_variance | 0.34 | +| learning_rate | 4.76e-05 | +| loss | -0.0295 | +| n_updates | 35224 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000145 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.389 | +| time/ | | +| fps | 1419 | +| iterations | 4853 | +| time_elapsed | 6999 | +| total_timesteps | 9938944 | +| train/ | | +| approx_kl | 0.012305578 | +| clip_fraction | 0.324 | +| clip_range | 0.0725 | +| entropy_loss | -7.49 | +| explained_variance | -0.133 | +| learning_rate | 4.76e-05 | +| loss | -0.032 | +| n_updates | 35228 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000153 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1419 | +| iterations | 4854 | +| time_elapsed | 7001 | +| total_timesteps | 9940992 | +| train/ | | +| approx_kl | 0.012066116 | +| clip_fraction | 0.31 | +| clip_range | 0.0725 | +| entropy_loss | -7.07 | +| explained_variance | 0.277 | +| learning_rate | 4.76e-05 | +| loss | -0.0288 | +| n_updates | 35232 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000223 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.386 | +| time/ | | +| fps | 1419 | +| iterations | 4855 | +| time_elapsed | 7002 | +| total_timesteps | 9943040 | +| train/ | | +| approx_kl | 0.012929966 | +| clip_fraction | 0.337 | +| clip_range | 0.0725 | +| entropy_loss | -6.74 | +| explained_variance | 0.677 | +| learning_rate | 4.76e-05 | +| loss | -0.0346 | +| n_updates | 35236 | +| policy_gradient_loss | -0.0228 | +| value_loss | 9.5e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.384 | +| time/ | | +| fps | 1419 | +| iterations | 4856 | +| time_elapsed | 7004 | +| total_timesteps | 9945088 | +| train/ | | +| approx_kl | 0.011508411 | +| clip_fraction | 0.283 | +| clip_range | 0.0725 | +| entropy_loss | -6.56 | +| explained_variance | 0.486 | +| learning_rate | 4.76e-05 | +| loss | -0.0269 | +| n_updates | 35240 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000169 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1419 | +| iterations | 4857 | +| time_elapsed | 7005 | +| total_timesteps | 9947136 | +| train/ | | +| approx_kl | 0.011937091 | +| clip_fraction | 0.312 | +| clip_range | 0.0725 | +| entropy_loss | -6.56 | +| explained_variance | 0.594 | +| learning_rate | 4.76e-05 | +| loss | -0.029 | +| n_updates | 35244 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000133 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1419 | +| iterations | 4858 | +| time_elapsed | 7007 | +| total_timesteps | 9949184 | +| train/ | | +| approx_kl | 0.01332819 | +| clip_fraction | 0.318 | +| clip_range | 0.0725 | +| entropy_loss | -7.21 | +| explained_variance | 0.184 | +| learning_rate | 4.76e-05 | +| loss | -0.0313 | +| n_updates | 35248 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000118 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1419 | +| iterations | 4859 | +| time_elapsed | 7008 | +| total_timesteps | 9951232 | +| train/ | | +| approx_kl | 0.0121625075 | +| clip_fraction | 0.334 | +| clip_range | 0.0725 | +| entropy_loss | -6.89 | +| explained_variance | 0.505 | +| learning_rate | 4.76e-05 | +| loss | -0.0309 | +| n_updates | 35252 | +| policy_gradient_loss | -0.0186 | +| value_loss | 8.87e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1419 | +| iterations | 4860 | +| time_elapsed | 7009 | +| total_timesteps | 9953280 | +| train/ | | +| approx_kl | 0.013843983 | +| clip_fraction | 0.328 | +| clip_range | 0.0725 | +| entropy_loss | -7.37 | +| explained_variance | -0.156 | +| learning_rate | 4.76e-05 | +| loss | -0.0268 | +| n_updates | 35256 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000109 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1419 | +| iterations | 4861 | +| time_elapsed | 7011 | +| total_timesteps | 9955328 | +| train/ | | +| approx_kl | 0.010384163 | +| clip_fraction | 0.303 | +| clip_range | 0.0725 | +| entropy_loss | -7.3 | +| explained_variance | 0.233 | +| learning_rate | 4.76e-05 | +| loss | -0.0252 | +| n_updates | 35260 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000151 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1419 | +| iterations | 4862 | +| time_elapsed | 7012 | +| total_timesteps | 9957376 | +| train/ | | +| approx_kl | 0.012540877 | +| clip_fraction | 0.295 | +| clip_range | 0.0725 | +| entropy_loss | -7.12 | +| explained_variance | 0.366 | +| learning_rate | 4.76e-05 | +| loss | -0.0323 | +| n_updates | 35264 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000216 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1419 | +| iterations | 4863 | +| time_elapsed | 7014 | +| total_timesteps | 9959424 | +| train/ | | +| approx_kl | 0.012464562 | +| clip_fraction | 0.312 | +| clip_range | 0.0725 | +| entropy_loss | -7.31 | +| explained_variance | -0.00958 | +| learning_rate | 4.76e-05 | +| loss | -0.0296 | +| n_updates | 35268 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000246 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1419 | +| iterations | 4864 | +| time_elapsed | 7015 | +| total_timesteps | 9961472 | +| train/ | | +| approx_kl | 0.012328342 | +| clip_fraction | 0.345 | +| clip_range | 0.0725 | +| entropy_loss | -7.43 | +| explained_variance | -0.0535 | +| learning_rate | 4.76e-05 | +| loss | -0.0323 | +| n_updates | 35272 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000141 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1419 | +| iterations | 4865 | +| time_elapsed | 7017 | +| total_timesteps | 9963520 | +| train/ | | +| approx_kl | 0.010541194 | +| clip_fraction | 0.314 | +| clip_range | 0.0725 | +| entropy_loss | -7.12 | +| explained_variance | 0.239 | +| learning_rate | 4.76e-05 | +| loss | -0.0221 | +| n_updates | 35276 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000195 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1419 | +| iterations | 4866 | +| time_elapsed | 7018 | +| total_timesteps | 9965568 | +| train/ | | +| approx_kl | 0.012049783 | +| clip_fraction | 0.306 | +| clip_range | 0.0725 | +| entropy_loss | -7.18 | +| explained_variance | 0.359 | +| learning_rate | 4.76e-05 | +| loss | -0.0358 | +| n_updates | 35280 | +| policy_gradient_loss | -0.0207 | +| value_loss | 9.19e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1419 | +| iterations | 4867 | +| time_elapsed | 7019 | +| total_timesteps | 9967616 | +| train/ | | +| approx_kl | 0.012730077 | +| clip_fraction | 0.298 | +| clip_range | 0.0725 | +| entropy_loss | -7.36 | +| explained_variance | 0.281 | +| learning_rate | 4.76e-05 | +| loss | -0.0304 | +| n_updates | 35284 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000172 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1419 | +| iterations | 4868 | +| time_elapsed | 7021 | +| total_timesteps | 9969664 | +| train/ | | +| approx_kl | 0.011872352 | +| clip_fraction | 0.324 | +| clip_range | 0.0725 | +| entropy_loss | -6.74 | +| explained_variance | 0.628 | +| learning_rate | 4.76e-05 | +| loss | -0.0314 | +| n_updates | 35288 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000107 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1419 | +| iterations | 4869 | +| time_elapsed | 7022 | +| total_timesteps | 9971712 | +| train/ | | +| approx_kl | 0.014079519 | +| clip_fraction | 0.315 | +| clip_range | 0.0725 | +| entropy_loss | -6.82 | +| explained_variance | 0.47 | +| learning_rate | 4.76e-05 | +| loss | -0.0301 | +| n_updates | 35292 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000152 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1419 | +| iterations | 4870 | +| time_elapsed | 7024 | +| total_timesteps | 9973760 | +| train/ | | +| approx_kl | 0.012658918 | +| clip_fraction | 0.305 | +| clip_range | 0.0725 | +| entropy_loss | -6.41 | +| explained_variance | 0.615 | +| learning_rate | 4.76e-05 | +| loss | -0.0273 | +| n_updates | 35296 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000168 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1419 | +| iterations | 4871 | +| time_elapsed | 7025 | +| total_timesteps | 9975808 | +| train/ | | +| approx_kl | 0.012234155 | +| clip_fraction | 0.311 | +| clip_range | 0.0725 | +| entropy_loss | -7.31 | +| explained_variance | -0.113 | +| learning_rate | 4.76e-05 | +| loss | -0.0324 | +| n_updates | 35300 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000142 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1419 | +| iterations | 4872 | +| time_elapsed | 7027 | +| total_timesteps | 9977856 | +| train/ | | +| approx_kl | 0.0118881725 | +| clip_fraction | 0.36 | +| clip_range | 0.0725 | +| entropy_loss | -7.18 | +| explained_variance | 0.0538 | +| learning_rate | 4.76e-05 | +| loss | -0.0465 | +| n_updates | 35304 | +| policy_gradient_loss | -0.026 | +| value_loss | 4.56e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1419 | +| iterations | 4873 | +| time_elapsed | 7028 | +| total_timesteps | 9979904 | +| train/ | | +| approx_kl | 0.010102084 | +| clip_fraction | 0.328 | +| clip_range | 0.0725 | +| entropy_loss | -7.36 | +| explained_variance | -0.0478 | +| learning_rate | 4.76e-05 | +| loss | -0.0335 | +| n_updates | 35308 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.0002 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1419 | +| iterations | 4874 | +| time_elapsed | 7030 | +| total_timesteps | 9981952 | +| train/ | | +| approx_kl | 0.009699715 | +| clip_fraction | 0.308 | +| clip_range | 0.0725 | +| entropy_loss | -7.43 | +| explained_variance | -0.0323 | +| learning_rate | 4.76e-05 | +| loss | -0.029 | +| n_updates | 35312 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000165 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1419 | +| iterations | 4875 | +| time_elapsed | 7031 | +| total_timesteps | 9984000 | +| train/ | | +| approx_kl | 0.0071863495 | +| clip_fraction | 0.264 | +| clip_range | 0.0725 | +| entropy_loss | -7.16 | +| explained_variance | 0.255 | +| learning_rate | 4.76e-05 | +| loss | -0.0229 | +| n_updates | 35316 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000242 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1419 | +| iterations | 4876 | +| time_elapsed | 7032 | +| total_timesteps | 9986048 | +| train/ | | +| approx_kl | 0.011128707 | +| clip_fraction | 0.311 | +| clip_range | 0.0725 | +| entropy_loss | -6.97 | +| explained_variance | 0.309 | +| learning_rate | 4.76e-05 | +| loss | -0.0308 | +| n_updates | 35320 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000182 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1419 | +| iterations | 4877 | +| time_elapsed | 7034 | +| total_timesteps | 9988096 | +| train/ | | +| approx_kl | 0.009655404 | +| clip_fraction | 0.289 | +| clip_range | 0.0725 | +| entropy_loss | -7.07 | +| explained_variance | 0.218 | +| learning_rate | 4.76e-05 | +| loss | -0.0307 | +| n_updates | 35324 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000286 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1419 | +| iterations | 4878 | +| time_elapsed | 7035 | +| total_timesteps | 9990144 | +| train/ | | +| approx_kl | 0.010176916 | +| clip_fraction | 0.304 | +| clip_range | 0.0725 | +| entropy_loss | -6.94 | +| explained_variance | 0.277 | +| learning_rate | 4.76e-05 | +| loss | -0.0328 | +| n_updates | 35328 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000197 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1419 | +| iterations | 4879 | +| time_elapsed | 7037 | +| total_timesteps | 9992192 | +| train/ | | +| approx_kl | 0.011557372 | +| clip_fraction | 0.317 | +| clip_range | 0.0725 | +| entropy_loss | -6.96 | +| explained_variance | 0.311 | +| learning_rate | 4.76e-05 | +| loss | -0.0296 | +| n_updates | 35332 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000188 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1419 | +| iterations | 4880 | +| time_elapsed | 7038 | +| total_timesteps | 9994240 | +| train/ | | +| approx_kl | 0.011806471 | +| clip_fraction | 0.339 | +| clip_range | 0.0725 | +| entropy_loss | -7.02 | +| explained_variance | 0.545 | +| learning_rate | 4.76e-05 | +| loss | -0.0351 | +| n_updates | 35336 | +| policy_gradient_loss | -0.022 | +| value_loss | 7.94e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1419 | +| iterations | 4881 | +| time_elapsed | 7039 | +| total_timesteps | 9996288 | +| train/ | | +| approx_kl | 0.012213087 | +| clip_fraction | 0.338 | +| clip_range | 0.0725 | +| entropy_loss | -6.66 | +| explained_variance | 0.783 | +| learning_rate | 4.76e-05 | +| loss | -0.0262 | +| n_updates | 35340 | +| policy_gradient_loss | -0.023 | +| value_loss | 5.41e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1419 | +| iterations | 4882 | +| time_elapsed | 7041 | +| total_timesteps | 9998336 | +| train/ | | +| approx_kl | 0.011893053 | +| clip_fraction | 0.306 | +| clip_range | 0.0725 | +| entropy_loss | -7.18 | +| explained_variance | 0.0478 | +| learning_rate | 4.76e-05 | +| loss | -0.0309 | +| n_updates | 35344 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000125 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1419 | +| iterations | 4883 | +| time_elapsed | 7042 | +| total_timesteps | 10000384 | +| train/ | | +| approx_kl | 0.011034579 | +| clip_fraction | 0.32 | +| clip_range | 0.0725 | +| entropy_loss | -7.4 | +| explained_variance | -0.0489 | +| learning_rate | 4.76e-05 | +| loss | -0.0324 | +| n_updates | 35348 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000193 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1419 | +| iterations | 4884 | +| time_elapsed | 7044 | +| total_timesteps | 10002432 | +| train/ | | +| approx_kl | 0.009509131 | +| clip_fraction | 0.295 | +| clip_range | 0.0725 | +| entropy_loss | -7.16 | +| explained_variance | 0.315 | +| learning_rate | 4.76e-05 | +| loss | -0.0335 | +| n_updates | 35352 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000251 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.388 | +| time/ | | +| fps | 1419 | +| iterations | 4885 | +| time_elapsed | 7045 | +| total_timesteps | 10004480 | +| train/ | | +| approx_kl | 0.0085793305 | +| clip_fraction | 0.289 | +| clip_range | 0.0725 | +| entropy_loss | -7.04 | +| explained_variance | 0.217 | +| learning_rate | 4.76e-05 | +| loss | -0.0323 | +| n_updates | 35356 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.00035 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.392 | +| time/ | | +| fps | 1419 | +| iterations | 4886 | +| time_elapsed | 7047 | +| total_timesteps | 10006528 | +| train/ | | +| approx_kl | 0.007999379 | +| clip_fraction | 0.284 | +| clip_range | 0.0725 | +| entropy_loss | -6.79 | +| explained_variance | 0.318 | +| learning_rate | 4.76e-05 | +| loss | -0.0309 | +| n_updates | 35360 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000352 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1419 | +| iterations | 4887 | +| time_elapsed | 7048 | +| total_timesteps | 10008576 | +| train/ | | +| approx_kl | 0.010699368 | +| clip_fraction | 0.302 | +| clip_range | 0.0725 | +| entropy_loss | -6.86 | +| explained_variance | 0.41 | +| learning_rate | 4.76e-05 | +| loss | -0.0248 | +| n_updates | 35364 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000225 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1419 | +| iterations | 4888 | +| time_elapsed | 7050 | +| total_timesteps | 10010624 | +| train/ | | +| approx_kl | 0.01032633 | +| clip_fraction | 0.305 | +| clip_range | 0.0725 | +| entropy_loss | -6.82 | +| explained_variance | 0.569 | +| learning_rate | 4.76e-05 | +| loss | -0.0342 | +| n_updates | 35368 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000136 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1419 | +| iterations | 4889 | +| time_elapsed | 7051 | +| total_timesteps | 10012672 | +| train/ | | +| approx_kl | 0.01085645 | +| clip_fraction | 0.313 | +| clip_range | 0.0725 | +| entropy_loss | -6.59 | +| explained_variance | 0.578 | +| learning_rate | 4.76e-05 | +| loss | -0.0309 | +| n_updates | 35372 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000206 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1419 | +| iterations | 4890 | +| time_elapsed | 7052 | +| total_timesteps | 10014720 | +| train/ | | +| approx_kl | 0.0121873915 | +| clip_fraction | 0.333 | +| clip_range | 0.0725 | +| entropy_loss | -7.26 | +| explained_variance | -0.00587 | +| learning_rate | 4.76e-05 | +| loss | -0.0272 | +| n_updates | 35376 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000149 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.388 | +| time/ | | +| fps | 1419 | +| iterations | 4891 | +| time_elapsed | 7054 | +| total_timesteps | 10016768 | +| train/ | | +| approx_kl | 0.011442254 | +| clip_fraction | 0.317 | +| clip_range | 0.0725 | +| entropy_loss | -7.18 | +| explained_variance | 0.274 | +| learning_rate | 4.76e-05 | +| loss | -0.0328 | +| n_updates | 35380 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000145 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.388 | +| time/ | | +| fps | 1419 | +| iterations | 4892 | +| time_elapsed | 7055 | +| total_timesteps | 10018816 | +| train/ | | +| approx_kl | 0.01051027 | +| clip_fraction | 0.304 | +| clip_range | 0.0725 | +| entropy_loss | -7.24 | +| explained_variance | 0.16 | +| learning_rate | 4.76e-05 | +| loss | -0.023 | +| n_updates | 35384 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000405 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.391 | +| time/ | | +| fps | 1419 | +| iterations | 4893 | +| time_elapsed | 7057 | +| total_timesteps | 10020864 | +| train/ | | +| approx_kl | 0.011287385 | +| clip_fraction | 0.358 | +| clip_range | 0.0725 | +| entropy_loss | -7.1 | +| explained_variance | 0.325 | +| learning_rate | 4.76e-05 | +| loss | -0.0405 | +| n_updates | 35388 | +| policy_gradient_loss | -0.0253 | +| value_loss | 9.55e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.394 | +| time/ | | +| fps | 1419 | +| iterations | 4894 | +| time_elapsed | 7058 | +| total_timesteps | 10022912 | +| train/ | | +| approx_kl | 0.011402227 | +| clip_fraction | 0.304 | +| clip_range | 0.0725 | +| entropy_loss | -7.16 | +| explained_variance | 0.0998 | +| learning_rate | 4.76e-05 | +| loss | -0.0354 | +| n_updates | 35392 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.00024 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.39 | +| time/ | | +| fps | 1419 | +| iterations | 4895 | +| time_elapsed | 7060 | +| total_timesteps | 10024960 | +| train/ | | +| approx_kl | 0.011409545 | +| clip_fraction | 0.295 | +| clip_range | 0.0725 | +| entropy_loss | -6.74 | +| explained_variance | 0.321 | +| learning_rate | 4.76e-05 | +| loss | -0.0298 | +| n_updates | 35396 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.00029 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.388 | +| time/ | | +| fps | 1419 | +| iterations | 4896 | +| time_elapsed | 7061 | +| total_timesteps | 10027008 | +| train/ | | +| approx_kl | 0.014103572 | +| clip_fraction | 0.324 | +| clip_range | 0.0725 | +| entropy_loss | -6.68 | +| explained_variance | 0.38 | +| learning_rate | 4.76e-05 | +| loss | -0.0288 | +| n_updates | 35400 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000223 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.389 | +| time/ | | +| fps | 1419 | +| iterations | 4897 | +| time_elapsed | 7063 | +| total_timesteps | 10029056 | +| train/ | | +| approx_kl | 0.012253438 | +| clip_fraction | 0.327 | +| clip_range | 0.0725 | +| entropy_loss | -7.16 | +| explained_variance | 0.214 | +| learning_rate | 4.76e-05 | +| loss | -0.0329 | +| n_updates | 35404 | +| policy_gradient_loss | -0.0224 | +| value_loss | 0.00017 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.389 | +| time/ | | +| fps | 1419 | +| iterations | 4898 | +| time_elapsed | 7064 | +| total_timesteps | 10031104 | +| train/ | | +| approx_kl | 0.013788253 | +| clip_fraction | 0.327 | +| clip_range | 0.0725 | +| entropy_loss | -7.17 | +| explained_variance | 0.177 | +| learning_rate | 4.76e-05 | +| loss | -0.0338 | +| n_updates | 35408 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000323 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.39 | +| time/ | | +| fps | 1419 | +| iterations | 4899 | +| time_elapsed | 7066 | +| total_timesteps | 10033152 | +| train/ | | +| approx_kl | 0.010601703 | +| clip_fraction | 0.353 | +| clip_range | 0.0725 | +| entropy_loss | -7.22 | +| explained_variance | 0.349 | +| learning_rate | 4.76e-05 | +| loss | -0.0356 | +| n_updates | 35412 | +| policy_gradient_loss | -0.0222 | +| value_loss | 0.000133 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.399 | +| time/ | | +| fps | 1419 | +| iterations | 4900 | +| time_elapsed | 7067 | +| total_timesteps | 10035200 | +| train/ | | +| approx_kl | 0.00860172 | +| clip_fraction | 0.308 | +| clip_range | 0.0725 | +| entropy_loss | -7.49 | +| explained_variance | -0.137 | +| learning_rate | 4.76e-05 | +| loss | -0.0259 | +| n_updates | 35416 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000197 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.396 | +| time/ | | +| fps | 1419 | +| iterations | 4901 | +| time_elapsed | 7068 | +| total_timesteps | 10037248 | +| train/ | | +| approx_kl | 0.009531058 | +| clip_fraction | 0.29 | +| clip_range | 0.0725 | +| entropy_loss | -6.64 | +| explained_variance | 0.539 | +| learning_rate | 4.76e-05 | +| loss | -0.021 | +| n_updates | 35420 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.00023 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.392 | +| time/ | | +| fps | 1419 | +| iterations | 4902 | +| time_elapsed | 7070 | +| total_timesteps | 10039296 | +| train/ | | +| approx_kl | 0.012558944 | +| clip_fraction | 0.339 | +| clip_range | 0.0725 | +| entropy_loss | -7.04 | +| explained_variance | -0.0078 | +| learning_rate | 4.76e-05 | +| loss | -0.0315 | +| n_updates | 35424 | +| policy_gradient_loss | -0.022 | +| value_loss | 0.000159 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.388 | +| time/ | | +| fps | 1419 | +| iterations | 4903 | +| time_elapsed | 7071 | +| total_timesteps | 10041344 | +| train/ | | +| approx_kl | 0.010924504 | +| clip_fraction | 0.317 | +| clip_range | 0.0725 | +| entropy_loss | -7.21 | +| explained_variance | 0.0633 | +| learning_rate | 4.76e-05 | +| loss | -0.0327 | +| n_updates | 35428 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000215 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.386 | +| time/ | | +| fps | 1419 | +| iterations | 4904 | +| time_elapsed | 7073 | +| total_timesteps | 10043392 | +| train/ | | +| approx_kl | 0.010643715 | +| clip_fraction | 0.329 | +| clip_range | 0.0725 | +| entropy_loss | -6.74 | +| explained_variance | 0.619 | +| learning_rate | 4.76e-05 | +| loss | -0.0377 | +| n_updates | 35432 | +| policy_gradient_loss | -0.0223 | +| value_loss | 6.69e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1419 | +| iterations | 4905 | +| time_elapsed | 7074 | +| total_timesteps | 10045440 | +| train/ | | +| approx_kl | 0.0126355905 | +| clip_fraction | 0.315 | +| clip_range | 0.0725 | +| entropy_loss | -6.94 | +| explained_variance | 0.58 | +| learning_rate | 4.76e-05 | +| loss | -0.0298 | +| n_updates | 35436 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000146 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1419 | +| iterations | 4906 | +| time_elapsed | 7076 | +| total_timesteps | 10047488 | +| train/ | | +| approx_kl | 0.011086225 | +| clip_fraction | 0.318 | +| clip_range | 0.0725 | +| entropy_loss | -7.05 | +| explained_variance | 0.081 | +| learning_rate | 4.76e-05 | +| loss | -0.0363 | +| n_updates | 35440 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000104 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1419 | +| iterations | 4907 | +| time_elapsed | 7077 | +| total_timesteps | 10049536 | +| train/ | | +| approx_kl | 0.010454008 | +| clip_fraction | 0.306 | +| clip_range | 0.0725 | +| entropy_loss | -7.29 | +| explained_variance | -0.109 | +| learning_rate | 4.76e-05 | +| loss | -0.0362 | +| n_updates | 35444 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000175 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1419 | +| iterations | 4908 | +| time_elapsed | 7079 | +| total_timesteps | 10051584 | +| train/ | | +| approx_kl | 0.010044046 | +| clip_fraction | 0.333 | +| clip_range | 0.0725 | +| entropy_loss | -6.92 | +| explained_variance | 0.636 | +| learning_rate | 4.76e-05 | +| loss | -0.0401 | +| n_updates | 35448 | +| policy_gradient_loss | -0.0214 | +| value_loss | 6.22e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1419 | +| iterations | 4909 | +| time_elapsed | 7080 | +| total_timesteps | 10053632 | +| train/ | | +| approx_kl | 0.012666423 | +| clip_fraction | 0.334 | +| clip_range | 0.0725 | +| entropy_loss | -7.24 | +| explained_variance | 0.278 | +| learning_rate | 4.76e-05 | +| loss | -0.0272 | +| n_updates | 35452 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000129 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1419 | +| iterations | 4910 | +| time_elapsed | 7081 | +| total_timesteps | 10055680 | +| train/ | | +| approx_kl | 0.008424973 | +| clip_fraction | 0.29 | +| clip_range | 0.0725 | +| entropy_loss | -7.45 | +| explained_variance | -0.074 | +| learning_rate | 4.76e-05 | +| loss | -0.029 | +| n_updates | 35456 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000174 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1419 | +| iterations | 4911 | +| time_elapsed | 7083 | +| total_timesteps | 10057728 | +| train/ | | +| approx_kl | 0.010217862 | +| clip_fraction | 0.301 | +| clip_range | 0.0725 | +| entropy_loss | -6.72 | +| explained_variance | 0.594 | +| learning_rate | 4.76e-05 | +| loss | -0.0318 | +| n_updates | 35460 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000142 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1419 | +| iterations | 4912 | +| time_elapsed | 7084 | +| total_timesteps | 10059776 | +| train/ | | +| approx_kl | 0.009835087 | +| clip_fraction | 0.29 | +| clip_range | 0.0725 | +| entropy_loss | -6.99 | +| explained_variance | -0.0263 | +| learning_rate | 4.76e-05 | +| loss | -0.0276 | +| n_updates | 35464 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.00016 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1419 | +| iterations | 4913 | +| time_elapsed | 7086 | +| total_timesteps | 10061824 | +| train/ | | +| approx_kl | 0.012346183 | +| clip_fraction | 0.325 | +| clip_range | 0.0725 | +| entropy_loss | -6.97 | +| explained_variance | 0.436 | +| learning_rate | 4.76e-05 | +| loss | -0.028 | +| n_updates | 35468 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000123 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1419 | +| iterations | 4914 | +| time_elapsed | 7087 | +| total_timesteps | 10063872 | +| train/ | | +| approx_kl | 0.011411132 | +| clip_fraction | 0.292 | +| clip_range | 0.0725 | +| entropy_loss | -6.48 | +| explained_variance | 0.483 | +| learning_rate | 4.76e-05 | +| loss | -0.0299 | +| n_updates | 35472 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000293 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1419 | +| iterations | 4915 | +| time_elapsed | 7089 | +| total_timesteps | 10065920 | +| train/ | | +| approx_kl | 0.0104509005 | +| clip_fraction | 0.345 | +| clip_range | 0.0725 | +| entropy_loss | -7.21 | +| explained_variance | -0.195 | +| learning_rate | 4.76e-05 | +| loss | -0.0388 | +| n_updates | 35476 | +| policy_gradient_loss | -0.0227 | +| value_loss | 0.000125 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1419 | +| iterations | 4916 | +| time_elapsed | 7090 | +| total_timesteps | 10067968 | +| train/ | | +| approx_kl | 0.01029801 | +| clip_fraction | 0.344 | +| clip_range | 0.0725 | +| entropy_loss | -7.11 | +| explained_variance | 0.207 | +| learning_rate | 4.76e-05 | +| loss | -0.0317 | +| n_updates | 35480 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.00031 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1419 | +| iterations | 4917 | +| time_elapsed | 7091 | +| total_timesteps | 10070016 | +| train/ | | +| approx_kl | 0.011824034 | +| clip_fraction | 0.347 | +| clip_range | 0.0725 | +| entropy_loss | -7.16 | +| explained_variance | 0.283 | +| learning_rate | 4.76e-05 | +| loss | -0.0367 | +| n_updates | 35484 | +| policy_gradient_loss | -0.0231 | +| value_loss | 7.8e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1419 | +| iterations | 4918 | +| time_elapsed | 7093 | +| total_timesteps | 10072064 | +| train/ | | +| approx_kl | 0.011372802 | +| clip_fraction | 0.341 | +| clip_range | 0.0725 | +| entropy_loss | -6.9 | +| explained_variance | 0.388 | +| learning_rate | 4.76e-05 | +| loss | -0.0333 | +| n_updates | 35488 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000122 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1419 | +| iterations | 4919 | +| time_elapsed | 7094 | +| total_timesteps | 10074112 | +| train/ | | +| approx_kl | 0.013262505 | +| clip_fraction | 0.326 | +| clip_range | 0.0725 | +| entropy_loss | -7.39 | +| explained_variance | -0.146 | +| learning_rate | 4.76e-05 | +| loss | -0.034 | +| n_updates | 35492 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000119 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1419 | +| iterations | 4920 | +| time_elapsed | 7096 | +| total_timesteps | 10076160 | +| train/ | | +| approx_kl | 0.009079546 | +| clip_fraction | 0.315 | +| clip_range | 0.0725 | +| entropy_loss | -7 | +| explained_variance | 0.274 | +| learning_rate | 4.76e-05 | +| loss | -0.0285 | +| n_updates | 35496 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000229 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1419 | +| iterations | 4921 | +| time_elapsed | 7097 | +| total_timesteps | 10078208 | +| train/ | | +| approx_kl | 0.0080368975 | +| clip_fraction | 0.272 | +| clip_range | 0.0725 | +| entropy_loss | -7.08 | +| explained_variance | 0.0967 | +| learning_rate | 4.76e-05 | +| loss | -0.0269 | +| n_updates | 35500 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000363 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.392 | +| time/ | | +| fps | 1419 | +| iterations | 4922 | +| time_elapsed | 7099 | +| total_timesteps | 10080256 | +| train/ | | +| approx_kl | 0.01126294 | +| clip_fraction | 0.325 | +| clip_range | 0.0725 | +| entropy_loss | -7.2 | +| explained_variance | 0.33 | +| learning_rate | 4.76e-05 | +| loss | -0.0304 | +| n_updates | 35504 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000126 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.393 | +| time/ | | +| fps | 1419 | +| iterations | 4923 | +| time_elapsed | 7100 | +| total_timesteps | 10082304 | +| train/ | | +| approx_kl | 0.009209285 | +| clip_fraction | 0.285 | +| clip_range | 0.0725 | +| entropy_loss | -6.69 | +| explained_variance | 0.464 | +| learning_rate | 4.76e-05 | +| loss | -0.0314 | +| n_updates | 35508 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000226 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.394 | +| time/ | | +| fps | 1419 | +| iterations | 4924 | +| time_elapsed | 7102 | +| total_timesteps | 10084352 | +| train/ | | +| approx_kl | 0.0103499945 | +| clip_fraction | 0.309 | +| clip_range | 0.0725 | +| entropy_loss | -6.93 | +| explained_variance | 0.378 | +| learning_rate | 4.76e-05 | +| loss | -0.0337 | +| n_updates | 35512 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000153 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.397 | +| time/ | | +| fps | 1419 | +| iterations | 4925 | +| time_elapsed | 7103 | +| total_timesteps | 10086400 | +| train/ | | +| approx_kl | 0.010156339 | +| clip_fraction | 0.316 | +| clip_range | 0.0725 | +| entropy_loss | -7.01 | +| explained_variance | 0.478 | +| learning_rate | 4.76e-05 | +| loss | -0.032 | +| n_updates | 35516 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000122 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.397 | +| time/ | | +| fps | 1419 | +| iterations | 4926 | +| time_elapsed | 7105 | +| total_timesteps | 10088448 | +| train/ | | +| approx_kl | 0.012964246 | +| clip_fraction | 0.309 | +| clip_range | 0.0725 | +| entropy_loss | -7.24 | +| explained_variance | -0.0745 | +| learning_rate | 4.76e-05 | +| loss | -0.0341 | +| n_updates | 35520 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000122 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.4 | +| time/ | | +| fps | 1419 | +| iterations | 4927 | +| time_elapsed | 7106 | +| total_timesteps | 10090496 | +| train/ | | +| approx_kl | 0.0095252 | +| clip_fraction | 0.293 | +| clip_range | 0.0725 | +| entropy_loss | -7.03 | +| explained_variance | 0.437 | +| learning_rate | 4.76e-05 | +| loss | -0.029 | +| n_updates | 35524 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000167 | +--------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.399 | +| time/ | | +| fps | 1419 | +| iterations | 4928 | +| time_elapsed | 7107 | +| total_timesteps | 10092544 | +| train/ | | +| approx_kl | 0.0106621925 | +| clip_fraction | 0.272 | +| clip_range | 0.0725 | +| entropy_loss | -7.02 | +| explained_variance | 0.295 | +| learning_rate | 4.76e-05 | +| loss | -0.0223 | +| n_updates | 35528 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000333 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.397 | +| time/ | | +| fps | 1419 | +| iterations | 4929 | +| time_elapsed | 7109 | +| total_timesteps | 10094592 | +| train/ | | +| approx_kl | 0.011817751 | +| clip_fraction | 0.325 | +| clip_range | 0.0725 | +| entropy_loss | -6.96 | +| explained_variance | 0.376 | +| learning_rate | 4.76e-05 | +| loss | -0.0348 | +| n_updates | 35532 | +| policy_gradient_loss | -0.0207 | +| value_loss | 9.88e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.401 | +| time/ | | +| fps | 1419 | +| iterations | 4930 | +| time_elapsed | 7110 | +| total_timesteps | 10096640 | +| train/ | | +| approx_kl | 0.01136897 | +| clip_fraction | 0.333 | +| clip_range | 0.0725 | +| entropy_loss | -7.21 | +| explained_variance | 0.313 | +| learning_rate | 4.76e-05 | +| loss | -0.032 | +| n_updates | 35536 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000135 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.402 | +| time/ | | +| fps | 1419 | +| iterations | 4931 | +| time_elapsed | 7112 | +| total_timesteps | 10098688 | +| train/ | | +| approx_kl | 0.0099234255 | +| clip_fraction | 0.293 | +| clip_range | 0.0725 | +| entropy_loss | -6.99 | +| explained_variance | 0.271 | +| learning_rate | 4.76e-05 | +| loss | -0.0298 | +| n_updates | 35540 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000251 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.402 | +| time/ | | +| fps | 1419 | +| iterations | 4932 | +| time_elapsed | 7113 | +| total_timesteps | 10100736 | +| train/ | | +| approx_kl | 0.009846413 | +| clip_fraction | 0.321 | +| clip_range | 0.0725 | +| entropy_loss | -7.08 | +| explained_variance | 0.275 | +| learning_rate | 4.76e-05 | +| loss | -0.0334 | +| n_updates | 35544 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000145 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.401 | +| time/ | | +| fps | 1419 | +| iterations | 4933 | +| time_elapsed | 7115 | +| total_timesteps | 10102784 | +| train/ | | +| approx_kl | 0.011083823 | +| clip_fraction | 0.328 | +| clip_range | 0.0725 | +| entropy_loss | -7.14 | +| explained_variance | 0.0489 | +| learning_rate | 4.76e-05 | +| loss | -0.031 | +| n_updates | 35548 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000123 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.406 | +| time/ | | +| fps | 1419 | +| iterations | 4934 | +| time_elapsed | 7116 | +| total_timesteps | 10104832 | +| train/ | | +| approx_kl | 0.011161945 | +| clip_fraction | 0.32 | +| clip_range | 0.0725 | +| entropy_loss | -7.08 | +| explained_variance | 0.172 | +| learning_rate | 4.76e-05 | +| loss | -0.0292 | +| n_updates | 35552 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000226 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.404 | +| time/ | | +| fps | 1419 | +| iterations | 4935 | +| time_elapsed | 7117 | +| total_timesteps | 10106880 | +| train/ | | +| approx_kl | 0.01043763 | +| clip_fraction | 0.3 | +| clip_range | 0.0725 | +| entropy_loss | -6.83 | +| explained_variance | 0.354 | +| learning_rate | 4.76e-05 | +| loss | -0.0284 | +| n_updates | 35556 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000268 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.407 | +| time/ | | +| fps | 1419 | +| iterations | 4936 | +| time_elapsed | 7119 | +| total_timesteps | 10108928 | +| train/ | | +| approx_kl | 0.01231054 | +| clip_fraction | 0.333 | +| clip_range | 0.0725 | +| entropy_loss | -7.05 | +| explained_variance | 0.214 | +| learning_rate | 4.76e-05 | +| loss | -0.0321 | +| n_updates | 35560 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000203 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.407 | +| time/ | | +| fps | 1419 | +| iterations | 4937 | +| time_elapsed | 7120 | +| total_timesteps | 10110976 | +| train/ | | +| approx_kl | 0.0121556055 | +| clip_fraction | 0.317 | +| clip_range | 0.0725 | +| entropy_loss | -7.08 | +| explained_variance | -0.019 | +| learning_rate | 4.76e-05 | +| loss | -0.0234 | +| n_updates | 35564 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000428 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.41 | +| time/ | | +| fps | 1419 | +| iterations | 4938 | +| time_elapsed | 7122 | +| total_timesteps | 10113024 | +| train/ | | +| approx_kl | 0.011571594 | +| clip_fraction | 0.34 | +| clip_range | 0.0725 | +| entropy_loss | -7.05 | +| explained_variance | -0.0826 | +| learning_rate | 4.76e-05 | +| loss | -0.0345 | +| n_updates | 35568 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000142 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.407 | +| time/ | | +| fps | 1419 | +| iterations | 4939 | +| time_elapsed | 7123 | +| total_timesteps | 10115072 | +| train/ | | +| approx_kl | 0.010467961 | +| clip_fraction | 0.306 | +| clip_range | 0.0725 | +| entropy_loss | -7.1 | +| explained_variance | 0.253 | +| learning_rate | 4.76e-05 | +| loss | -0.0278 | +| n_updates | 35572 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.00015 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.405 | +| time/ | | +| fps | 1419 | +| iterations | 4940 | +| time_elapsed | 7124 | +| total_timesteps | 10117120 | +| train/ | | +| approx_kl | 0.01006722 | +| clip_fraction | 0.301 | +| clip_range | 0.0725 | +| entropy_loss | -7.03 | +| explained_variance | 0.515 | +| learning_rate | 4.76e-05 | +| loss | -0.0268 | +| n_updates | 35576 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000128 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.406 | +| time/ | | +| fps | 1419 | +| iterations | 4941 | +| time_elapsed | 7126 | +| total_timesteps | 10119168 | +| train/ | | +| approx_kl | 0.011082955 | +| clip_fraction | 0.322 | +| clip_range | 0.0725 | +| entropy_loss | -7.24 | +| explained_variance | 0.101 | +| learning_rate | 4.76e-05 | +| loss | -0.0329 | +| n_updates | 35580 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000107 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.41 | +| time/ | | +| fps | 1419 | +| iterations | 4942 | +| time_elapsed | 7127 | +| total_timesteps | 10121216 | +| train/ | | +| approx_kl | 0.010191343 | +| clip_fraction | 0.29 | +| clip_range | 0.0725 | +| entropy_loss | -7.06 | +| explained_variance | 0.288 | +| learning_rate | 4.76e-05 | +| loss | -0.0252 | +| n_updates | 35584 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000179 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.409 | +| time/ | | +| fps | 1419 | +| iterations | 4943 | +| time_elapsed | 7129 | +| total_timesteps | 10123264 | +| train/ | | +| approx_kl | 0.0100777615 | +| clip_fraction | 0.298 | +| clip_range | 0.0725 | +| entropy_loss | -7.02 | +| explained_variance | 0.06 | +| learning_rate | 4.76e-05 | +| loss | -0.0263 | +| n_updates | 35588 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000223 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.411 | +| time/ | | +| fps | 1419 | +| iterations | 4944 | +| time_elapsed | 7130 | +| total_timesteps | 10125312 | +| train/ | | +| approx_kl | 0.010370083 | +| clip_fraction | 0.327 | +| clip_range | 0.0725 | +| entropy_loss | -6.76 | +| explained_variance | 0.269 | +| learning_rate | 4.76e-05 | +| loss | -0.0331 | +| n_updates | 35592 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000202 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.402 | +| time/ | | +| fps | 1419 | +| iterations | 4945 | +| time_elapsed | 7132 | +| total_timesteps | 10127360 | +| train/ | | +| approx_kl | 0.010083182 | +| clip_fraction | 0.318 | +| clip_range | 0.0725 | +| entropy_loss | -6.92 | +| explained_variance | 0.179 | +| learning_rate | 4.76e-05 | +| loss | -0.033 | +| n_updates | 35596 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000142 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.398 | +| time/ | | +| fps | 1419 | +| iterations | 4946 | +| time_elapsed | 7133 | +| total_timesteps | 10129408 | +| train/ | | +| approx_kl | 0.009571193 | +| clip_fraction | 0.326 | +| clip_range | 0.0725 | +| entropy_loss | -6.72 | +| explained_variance | 0.395 | +| learning_rate | 4.76e-05 | +| loss | -0.0306 | +| n_updates | 35600 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000131 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1419 | +| iterations | 4947 | +| time_elapsed | 7134 | +| total_timesteps | 10131456 | +| train/ | | +| approx_kl | 0.012231983 | +| clip_fraction | 0.342 | +| clip_range | 0.0725 | +| entropy_loss | -7.02 | +| explained_variance | 0.447 | +| learning_rate | 4.76e-05 | +| loss | -0.0314 | +| n_updates | 35604 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000121 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1419 | +| iterations | 4948 | +| time_elapsed | 7136 | +| total_timesteps | 10133504 | +| train/ | | +| approx_kl | 0.011321823 | +| clip_fraction | 0.316 | +| clip_range | 0.0725 | +| entropy_loss | -6.46 | +| explained_variance | 0.411 | +| learning_rate | 4.76e-05 | +| loss | -0.0309 | +| n_updates | 35608 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000171 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1419 | +| iterations | 4949 | +| time_elapsed | 7137 | +| total_timesteps | 10135552 | +| train/ | | +| approx_kl | 0.012352628 | +| clip_fraction | 0.328 | +| clip_range | 0.0725 | +| entropy_loss | -7.08 | +| explained_variance | -0.0895 | +| learning_rate | 4.76e-05 | +| loss | -0.0304 | +| n_updates | 35612 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000105 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1419 | +| iterations | 4950 | +| time_elapsed | 7139 | +| total_timesteps | 10137600 | +| train/ | | +| approx_kl | 0.011808078 | +| clip_fraction | 0.319 | +| clip_range | 0.0725 | +| entropy_loss | -7.4 | +| explained_variance | -0.0896 | +| learning_rate | 4.76e-05 | +| loss | -0.0346 | +| n_updates | 35616 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000129 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1419 | +| iterations | 4951 | +| time_elapsed | 7140 | +| total_timesteps | 10139648 | +| train/ | | +| approx_kl | 0.009823396 | +| clip_fraction | 0.33 | +| clip_range | 0.0725 | +| entropy_loss | -7.25 | +| explained_variance | 0.23 | +| learning_rate | 4.76e-05 | +| loss | -0.0324 | +| n_updates | 35620 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000135 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1419 | +| iterations | 4952 | +| time_elapsed | 7142 | +| total_timesteps | 10141696 | +| train/ | | +| approx_kl | 0.01010327 | +| clip_fraction | 0.3 | +| clip_range | 0.0725 | +| entropy_loss | -7.15 | +| explained_variance | 0.325 | +| learning_rate | 4.76e-05 | +| loss | -0.0294 | +| n_updates | 35624 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000125 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1419 | +| iterations | 4953 | +| time_elapsed | 7143 | +| total_timesteps | 10143744 | +| train/ | | +| approx_kl | 0.00935704 | +| clip_fraction | 0.325 | +| clip_range | 0.0725 | +| entropy_loss | -7.33 | +| explained_variance | -0.0746 | +| learning_rate | 4.76e-05 | +| loss | -0.028 | +| n_updates | 35628 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000128 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1419 | +| iterations | 4954 | +| time_elapsed | 7145 | +| total_timesteps | 10145792 | +| train/ | | +| approx_kl | 0.011406729 | +| clip_fraction | 0.306 | +| clip_range | 0.0725 | +| entropy_loss | -7.18 | +| explained_variance | 0.199 | +| learning_rate | 4.76e-05 | +| loss | -0.0274 | +| n_updates | 35632 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000149 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1419 | +| iterations | 4955 | +| time_elapsed | 7146 | +| total_timesteps | 10147840 | +| train/ | | +| approx_kl | 0.007714104 | +| clip_fraction | 0.276 | +| clip_range | 0.0725 | +| entropy_loss | -6.42 | +| explained_variance | 0.431 | +| learning_rate | 4.76e-05 | +| loss | -0.0199 | +| n_updates | 35636 | +| policy_gradient_loss | -0.0133 | +| value_loss | 0.000298 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1419 | +| iterations | 4956 | +| time_elapsed | 7147 | +| total_timesteps | 10149888 | +| train/ | | +| approx_kl | 0.011052318 | +| clip_fraction | 0.316 | +| clip_range | 0.0725 | +| entropy_loss | -6.81 | +| explained_variance | 0.34 | +| learning_rate | 4.76e-05 | +| loss | -0.0299 | +| n_updates | 35640 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000133 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1419 | +| iterations | 4957 | +| time_elapsed | 7149 | +| total_timesteps | 10151936 | +| train/ | | +| approx_kl | 0.012168746 | +| clip_fraction | 0.326 | +| clip_range | 0.0725 | +| entropy_loss | -7.13 | +| explained_variance | 0.369 | +| learning_rate | 4.76e-05 | +| loss | -0.0282 | +| n_updates | 35644 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000115 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1419 | +| iterations | 4958 | +| time_elapsed | 7150 | +| total_timesteps | 10153984 | +| train/ | | +| approx_kl | 0.0122046415 | +| clip_fraction | 0.338 | +| clip_range | 0.0725 | +| entropy_loss | -7.01 | +| explained_variance | 0.436 | +| learning_rate | 4.76e-05 | +| loss | -0.0386 | +| n_updates | 35648 | +| policy_gradient_loss | -0.0224 | +| value_loss | 5.76e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1420 | +| iterations | 4959 | +| time_elapsed | 7152 | +| total_timesteps | 10156032 | +| train/ | | +| approx_kl | 0.010426728 | +| clip_fraction | 0.317 | +| clip_range | 0.0725 | +| entropy_loss | -7.27 | +| explained_variance | 0.024 | +| learning_rate | 4.76e-05 | +| loss | -0.0276 | +| n_updates | 35652 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000177 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1420 | +| iterations | 4960 | +| time_elapsed | 7153 | +| total_timesteps | 10158080 | +| train/ | | +| approx_kl | 0.01021144 | +| clip_fraction | 0.323 | +| clip_range | 0.0725 | +| entropy_loss | -7.17 | +| explained_variance | 0.239 | +| learning_rate | 4.76e-05 | +| loss | -0.0327 | +| n_updates | 35656 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.00015 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1420 | +| iterations | 4961 | +| time_elapsed | 7154 | +| total_timesteps | 10160128 | +| train/ | | +| approx_kl | 0.011875447 | +| clip_fraction | 0.338 | +| clip_range | 0.0725 | +| entropy_loss | -7.04 | +| explained_variance | 0.466 | +| learning_rate | 4.76e-05 | +| loss | -0.0367 | +| n_updates | 35660 | +| policy_gradient_loss | -0.0203 | +| value_loss | 5.96e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1420 | +| iterations | 4962 | +| time_elapsed | 7156 | +| total_timesteps | 10162176 | +| train/ | | +| approx_kl | 0.00975036 | +| clip_fraction | 0.298 | +| clip_range | 0.0725 | +| entropy_loss | -7.13 | +| explained_variance | 0.309 | +| learning_rate | 4.76e-05 | +| loss | -0.0254 | +| n_updates | 35664 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000152 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1420 | +| iterations | 4963 | +| time_elapsed | 7157 | +| total_timesteps | 10164224 | +| train/ | | +| approx_kl | 0.011528152 | +| clip_fraction | 0.309 | +| clip_range | 0.0725 | +| entropy_loss | -7.24 | +| explained_variance | 0.0477 | +| learning_rate | 4.76e-05 | +| loss | -0.0301 | +| n_updates | 35668 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000173 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1420 | +| iterations | 4964 | +| time_elapsed | 7159 | +| total_timesteps | 10166272 | +| train/ | | +| approx_kl | 0.01070058 | +| clip_fraction | 0.304 | +| clip_range | 0.0725 | +| entropy_loss | -7.12 | +| explained_variance | 0.167 | +| learning_rate | 4.76e-05 | +| loss | -0.0263 | +| n_updates | 35672 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000223 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1420 | +| iterations | 4965 | +| time_elapsed | 7160 | +| total_timesteps | 10168320 | +| train/ | | +| approx_kl | 0.010773137 | +| clip_fraction | 0.313 | +| clip_range | 0.0725 | +| entropy_loss | -7.33 | +| explained_variance | 0.00679 | +| learning_rate | 4.76e-05 | +| loss | -0.0307 | +| n_updates | 35676 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000181 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1420 | +| iterations | 4966 | +| time_elapsed | 7162 | +| total_timesteps | 10170368 | +| train/ | | +| approx_kl | 0.009263847 | +| clip_fraction | 0.29 | +| clip_range | 0.0725 | +| entropy_loss | -6.32 | +| explained_variance | 0.538 | +| learning_rate | 4.76e-05 | +| loss | -0.0165 | +| n_updates | 35680 | +| policy_gradient_loss | -0.0136 | +| value_loss | 0.000304 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1420 | +| iterations | 4967 | +| time_elapsed | 7163 | +| total_timesteps | 10172416 | +| train/ | | +| approx_kl | 0.0118202 | +| clip_fraction | 0.328 | +| clip_range | 0.0725 | +| entropy_loss | -6.75 | +| explained_variance | 0.44 | +| learning_rate | 4.76e-05 | +| loss | -0.0333 | +| n_updates | 35684 | +| policy_gradient_loss | -0.0221 | +| value_loss | 0.000109 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1420 | +| iterations | 4968 | +| time_elapsed | 7164 | +| total_timesteps | 10174464 | +| train/ | | +| approx_kl | 0.010126276 | +| clip_fraction | 0.311 | +| clip_range | 0.0725 | +| entropy_loss | -6.98 | +| explained_variance | 0.553 | +| learning_rate | 4.76e-05 | +| loss | -0.0271 | +| n_updates | 35688 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000119 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1420 | +| iterations | 4969 | +| time_elapsed | 7166 | +| total_timesteps | 10176512 | +| train/ | | +| approx_kl | 0.013126116 | +| clip_fraction | 0.338 | +| clip_range | 0.0725 | +| entropy_loss | -7.08 | +| explained_variance | 0.0677 | +| learning_rate | 4.76e-05 | +| loss | -0.0295 | +| n_updates | 35692 | +| policy_gradient_loss | -0.0197 | +| value_loss | 8.84e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1420 | +| iterations | 4970 | +| time_elapsed | 7167 | +| total_timesteps | 10178560 | +| train/ | | +| approx_kl | 0.010549258 | +| clip_fraction | 0.311 | +| clip_range | 0.0725 | +| entropy_loss | -7.21 | +| explained_variance | 0.242 | +| learning_rate | 4.76e-05 | +| loss | -0.027 | +| n_updates | 35696 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000161 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1420 | +| iterations | 4971 | +| time_elapsed | 7169 | +| total_timesteps | 10180608 | +| train/ | | +| approx_kl | 0.010536885 | +| clip_fraction | 0.296 | +| clip_range | 0.0725 | +| entropy_loss | -7.08 | +| explained_variance | 0.308 | +| learning_rate | 4.76e-05 | +| loss | -0.0274 | +| n_updates | 35700 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000253 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1420 | +| iterations | 4972 | +| time_elapsed | 7170 | +| total_timesteps | 10182656 | +| train/ | | +| approx_kl | 0.011926591 | +| clip_fraction | 0.312 | +| clip_range | 0.0725 | +| entropy_loss | -7.16 | +| explained_variance | 0.00373 | +| learning_rate | 4.76e-05 | +| loss | -0.029 | +| n_updates | 35704 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000167 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1420 | +| iterations | 4973 | +| time_elapsed | 7171 | +| total_timesteps | 10184704 | +| train/ | | +| approx_kl | 0.010344781 | +| clip_fraction | 0.319 | +| clip_range | 0.0725 | +| entropy_loss | -7.46 | +| explained_variance | -0.22 | +| learning_rate | 4.76e-05 | +| loss | -0.0276 | +| n_updates | 35708 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000115 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1420 | +| iterations | 4974 | +| time_elapsed | 7173 | +| total_timesteps | 10186752 | +| train/ | | +| approx_kl | 0.012334372 | +| clip_fraction | 0.332 | +| clip_range | 0.0725 | +| entropy_loss | -7.17 | +| explained_variance | 0.317 | +| learning_rate | 4.76e-05 | +| loss | -0.0385 | +| n_updates | 35712 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000108 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1420 | +| iterations | 4975 | +| time_elapsed | 7174 | +| total_timesteps | 10188800 | +| train/ | | +| approx_kl | 0.012010697 | +| clip_fraction | 0.314 | +| clip_range | 0.0725 | +| entropy_loss | -7.41 | +| explained_variance | -0.0856 | +| learning_rate | 4.76e-05 | +| loss | -0.0292 | +| n_updates | 35716 | +| policy_gradient_loss | -0.0184 | +| value_loss | 8.88e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1420 | +| iterations | 4976 | +| time_elapsed | 7176 | +| total_timesteps | 10190848 | +| train/ | | +| approx_kl | 0.009097505 | +| clip_fraction | 0.296 | +| clip_range | 0.0725 | +| entropy_loss | -7.18 | +| explained_variance | 0.206 | +| learning_rate | 4.76e-05 | +| loss | -0.0232 | +| n_updates | 35720 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000205 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1420 | +| iterations | 4977 | +| time_elapsed | 7177 | +| total_timesteps | 10192896 | +| train/ | | +| approx_kl | 0.01031437 | +| clip_fraction | 0.316 | +| clip_range | 0.0725 | +| entropy_loss | -7.02 | +| explained_variance | 0.288 | +| learning_rate | 4.76e-05 | +| loss | -0.0286 | +| n_updates | 35724 | +| policy_gradient_loss | -0.0205 | +| value_loss | 8.62e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1420 | +| iterations | 4978 | +| time_elapsed | 7179 | +| total_timesteps | 10194944 | +| train/ | | +| approx_kl | 0.010184731 | +| clip_fraction | 0.307 | +| clip_range | 0.0725 | +| entropy_loss | -6.72 | +| explained_variance | 0.713 | +| learning_rate | 4.76e-05 | +| loss | -0.0296 | +| n_updates | 35728 | +| policy_gradient_loss | -0.019 | +| value_loss | 7.94e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1420 | +| iterations | 4979 | +| time_elapsed | 7180 | +| total_timesteps | 10196992 | +| train/ | | +| approx_kl | 0.008677049 | +| clip_fraction | 0.269 | +| clip_range | 0.0725 | +| entropy_loss | -7.57 | +| explained_variance | -0.11 | +| learning_rate | 4.76e-05 | +| loss | -0.0297 | +| n_updates | 35732 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000124 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1420 | +| iterations | 4980 | +| time_elapsed | 7182 | +| total_timesteps | 10199040 | +| train/ | | +| approx_kl | 0.009902697 | +| clip_fraction | 0.294 | +| clip_range | 0.0725 | +| entropy_loss | -6.83 | +| explained_variance | 0.622 | +| learning_rate | 4.76e-05 | +| loss | -0.0218 | +| n_updates | 35736 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000135 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1420 | +| iterations | 4981 | +| time_elapsed | 7183 | +| total_timesteps | 10201088 | +| train/ | | +| approx_kl | 0.0101145 | +| clip_fraction | 0.308 | +| clip_range | 0.0725 | +| entropy_loss | -6.62 | +| explained_variance | 0.451 | +| learning_rate | 4.76e-05 | +| loss | -0.0302 | +| n_updates | 35740 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000182 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1420 | +| iterations | 4982 | +| time_elapsed | 7184 | +| total_timesteps | 10203136 | +| train/ | | +| approx_kl | 0.011142015 | +| clip_fraction | 0.314 | +| clip_range | 0.0724 | +| entropy_loss | -7.31 | +| explained_variance | -0.106 | +| learning_rate | 4.76e-05 | +| loss | -0.0287 | +| n_updates | 35744 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000233 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1420 | +| iterations | 4983 | +| time_elapsed | 7186 | +| total_timesteps | 10205184 | +| train/ | | +| approx_kl | 0.011135193 | +| clip_fraction | 0.318 | +| clip_range | 0.0724 | +| entropy_loss | -7.04 | +| explained_variance | 0.116 | +| learning_rate | 4.76e-05 | +| loss | -0.0328 | +| n_updates | 35748 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000189 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1420 | +| iterations | 4984 | +| time_elapsed | 7187 | +| total_timesteps | 10207232 | +| train/ | | +| approx_kl | 0.013451744 | +| clip_fraction | 0.353 | +| clip_range | 0.0724 | +| entropy_loss | -6.97 | +| explained_variance | 0.56 | +| learning_rate | 4.76e-05 | +| loss | -0.0331 | +| n_updates | 35752 | +| policy_gradient_loss | -0.0211 | +| value_loss | 8.64e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1420 | +| iterations | 4985 | +| time_elapsed | 7189 | +| total_timesteps | 10209280 | +| train/ | | +| approx_kl | 0.012089092 | +| clip_fraction | 0.337 | +| clip_range | 0.0724 | +| entropy_loss | -7.39 | +| explained_variance | -0.172 | +| learning_rate | 4.76e-05 | +| loss | -0.0369 | +| n_updates | 35756 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.00011 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1420 | +| iterations | 4986 | +| time_elapsed | 7190 | +| total_timesteps | 10211328 | +| train/ | | +| approx_kl | 0.011367049 | +| clip_fraction | 0.303 | +| clip_range | 0.0724 | +| entropy_loss | -7.03 | +| explained_variance | 0.286 | +| learning_rate | 4.76e-05 | +| loss | -0.0257 | +| n_updates | 35760 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000203 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1420 | +| iterations | 4987 | +| time_elapsed | 7191 | +| total_timesteps | 10213376 | +| train/ | | +| approx_kl | 0.01097382 | +| clip_fraction | 0.316 | +| clip_range | 0.0724 | +| entropy_loss | -7.08 | +| explained_variance | 0.314 | +| learning_rate | 4.76e-05 | +| loss | -0.039 | +| n_updates | 35764 | +| policy_gradient_loss | -0.0202 | +| value_loss | 9.88e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1420 | +| iterations | 4988 | +| time_elapsed | 7193 | +| total_timesteps | 10215424 | +| train/ | | +| approx_kl | 0.010170365 | +| clip_fraction | 0.334 | +| clip_range | 0.0724 | +| entropy_loss | -6.94 | +| explained_variance | 0.392 | +| learning_rate | 4.76e-05 | +| loss | -0.0345 | +| n_updates | 35768 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000222 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1420 | +| iterations | 4989 | +| time_elapsed | 7194 | +| total_timesteps | 10217472 | +| train/ | | +| approx_kl | 0.011790181 | +| clip_fraction | 0.311 | +| clip_range | 0.0724 | +| entropy_loss | -6.93 | +| explained_variance | 0.222 | +| learning_rate | 4.76e-05 | +| loss | -0.0273 | +| n_updates | 35772 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000206 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1420 | +| iterations | 4990 | +| time_elapsed | 7196 | +| total_timesteps | 10219520 | +| train/ | | +| approx_kl | 0.0123318955 | +| clip_fraction | 0.318 | +| clip_range | 0.0724 | +| entropy_loss | -6.94 | +| explained_variance | 0.212 | +| learning_rate | 4.76e-05 | +| loss | -0.028 | +| n_updates | 35776 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000222 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1420 | +| iterations | 4991 | +| time_elapsed | 7197 | +| total_timesteps | 10221568 | +| train/ | | +| approx_kl | 0.014466054 | +| clip_fraction | 0.32 | +| clip_range | 0.0724 | +| entropy_loss | -6.96 | +| explained_variance | 0.331 | +| learning_rate | 4.76e-05 | +| loss | -0.0315 | +| n_updates | 35780 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1420 | +| iterations | 4992 | +| time_elapsed | 7199 | +| total_timesteps | 10223616 | +| train/ | | +| approx_kl | 0.010990204 | +| clip_fraction | 0.329 | +| clip_range | 0.0724 | +| entropy_loss | -7.1 | +| explained_variance | 0.196 | +| learning_rate | 4.76e-05 | +| loss | -0.0305 | +| n_updates | 35784 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000177 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1420 | +| iterations | 4993 | +| time_elapsed | 7200 | +| total_timesteps | 10225664 | +| train/ | | +| approx_kl | 0.009101979 | +| clip_fraction | 0.3 | +| clip_range | 0.0724 | +| entropy_loss | -7.36 | +| explained_variance | -0.205 | +| learning_rate | 4.76e-05 | +| loss | -0.027 | +| n_updates | 35788 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000212 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1420 | +| iterations | 4994 | +| time_elapsed | 7202 | +| total_timesteps | 10227712 | +| train/ | | +| approx_kl | 0.009410966 | +| clip_fraction | 0.317 | +| clip_range | 0.0724 | +| entropy_loss | -7.24 | +| explained_variance | 0.206 | +| learning_rate | 4.76e-05 | +| loss | -0.0248 | +| n_updates | 35792 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000168 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1420 | +| iterations | 4995 | +| time_elapsed | 7203 | +| total_timesteps | 10229760 | +| train/ | | +| approx_kl | 0.010691017 | +| clip_fraction | 0.319 | +| clip_range | 0.0724 | +| entropy_loss | -6.85 | +| explained_variance | 0.534 | +| learning_rate | 4.76e-05 | +| loss | -0.0364 | +| n_updates | 35796 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000114 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1420 | +| iterations | 4996 | +| time_elapsed | 7204 | +| total_timesteps | 10231808 | +| train/ | | +| approx_kl | 0.009859858 | +| clip_fraction | 0.298 | +| clip_range | 0.0724 | +| entropy_loss | -6.72 | +| explained_variance | 0.323 | +| learning_rate | 4.76e-05 | +| loss | -0.0273 | +| n_updates | 35800 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.00037 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1420 | +| iterations | 4997 | +| time_elapsed | 7206 | +| total_timesteps | 10233856 | +| train/ | | +| approx_kl | 0.011720013 | +| clip_fraction | 0.341 | +| clip_range | 0.0724 | +| entropy_loss | -6.77 | +| explained_variance | 0.503 | +| learning_rate | 4.76e-05 | +| loss | -0.034 | +| n_updates | 35804 | +| policy_gradient_loss | -0.0223 | +| value_loss | 0.000108 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1420 | +| iterations | 4998 | +| time_elapsed | 7207 | +| total_timesteps | 10235904 | +| train/ | | +| approx_kl | 0.010651324 | +| clip_fraction | 0.332 | +| clip_range | 0.0724 | +| entropy_loss | -7.08 | +| explained_variance | 0.27 | +| learning_rate | 4.76e-05 | +| loss | -0.0263 | +| n_updates | 35808 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1420 | +| iterations | 4999 | +| time_elapsed | 7209 | +| total_timesteps | 10237952 | +| train/ | | +| approx_kl | 0.012081008 | +| clip_fraction | 0.332 | +| clip_range | 0.0724 | +| entropy_loss | -6.69 | +| explained_variance | 0.491 | +| learning_rate | 4.76e-05 | +| loss | -0.026 | +| n_updates | 35812 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000142 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1420 | +| iterations | 5000 | +| time_elapsed | 7210 | +| total_timesteps | 10240000 | +| train/ | | +| approx_kl | 0.011258058 | +| clip_fraction | 0.303 | +| clip_range | 0.0724 | +| entropy_loss | -7.3 | +| explained_variance | -0.0466 | +| learning_rate | 4.76e-05 | +| loss | -0.0314 | +| n_updates | 35816 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000189 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1420 | +| iterations | 5001 | +| time_elapsed | 7212 | +| total_timesteps | 10242048 | +| train/ | | +| approx_kl | 0.010479682 | +| clip_fraction | 0.31 | +| clip_range | 0.0724 | +| entropy_loss | -7.18 | +| explained_variance | 0.0468 | +| learning_rate | 4.76e-05 | +| loss | -0.0335 | +| n_updates | 35820 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000248 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1420 | +| iterations | 5002 | +| time_elapsed | 7213 | +| total_timesteps | 10244096 | +| train/ | | +| approx_kl | 0.00961104 | +| clip_fraction | 0.301 | +| clip_range | 0.0724 | +| entropy_loss | -7.12 | +| explained_variance | 0.194 | +| learning_rate | 4.76e-05 | +| loss | -0.0268 | +| n_updates | 35824 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000181 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1420 | +| iterations | 5003 | +| time_elapsed | 7214 | +| total_timesteps | 10246144 | +| train/ | | +| approx_kl | 0.0117074195 | +| clip_fraction | 0.313 | +| clip_range | 0.0724 | +| entropy_loss | -6.92 | +| explained_variance | 0.201 | +| learning_rate | 4.76e-05 | +| loss | -0.0259 | +| n_updates | 35828 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000226 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1420 | +| iterations | 5004 | +| time_elapsed | 7216 | +| total_timesteps | 10248192 | +| train/ | | +| approx_kl | 0.012855273 | +| clip_fraction | 0.332 | +| clip_range | 0.0724 | +| entropy_loss | -7.25 | +| explained_variance | -0.0622 | +| learning_rate | 4.76e-05 | +| loss | -0.0375 | +| n_updates | 35832 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000188 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1420 | +| iterations | 5005 | +| time_elapsed | 7217 | +| total_timesteps | 10250240 | +| train/ | | +| approx_kl | 0.010323689 | +| clip_fraction | 0.298 | +| clip_range | 0.0724 | +| entropy_loss | -7.38 | +| explained_variance | -0.0798 | +| learning_rate | 4.76e-05 | +| loss | -0.0245 | +| n_updates | 35836 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000171 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1420 | +| iterations | 5006 | +| time_elapsed | 7219 | +| total_timesteps | 10252288 | +| train/ | | +| approx_kl | 0.01217078 | +| clip_fraction | 0.319 | +| clip_range | 0.0724 | +| entropy_loss | -7.04 | +| explained_variance | 0.485 | +| learning_rate | 4.76e-05 | +| loss | -0.0297 | +| n_updates | 35840 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000117 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1420 | +| iterations | 5007 | +| time_elapsed | 7220 | +| total_timesteps | 10254336 | +| train/ | | +| approx_kl | 0.011954727 | +| clip_fraction | 0.288 | +| clip_range | 0.0724 | +| entropy_loss | -6.67 | +| explained_variance | 0.404 | +| learning_rate | 4.76e-05 | +| loss | -0.0253 | +| n_updates | 35844 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000325 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1420 | +| iterations | 5008 | +| time_elapsed | 7222 | +| total_timesteps | 10256384 | +| train/ | | +| approx_kl | 0.014220617 | +| clip_fraction | 0.354 | +| clip_range | 0.0724 | +| entropy_loss | -6.95 | +| explained_variance | 0.377 | +| learning_rate | 4.76e-05 | +| loss | -0.045 | +| n_updates | 35848 | +| policy_gradient_loss | -0.0248 | +| value_loss | 0.000109 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1420 | +| iterations | 5009 | +| time_elapsed | 7223 | +| total_timesteps | 10258432 | +| train/ | | +| approx_kl | 0.011925937 | +| clip_fraction | 0.322 | +| clip_range | 0.0724 | +| entropy_loss | -6.47 | +| explained_variance | 0.5 | +| learning_rate | 4.76e-05 | +| loss | -0.0328 | +| n_updates | 35852 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000203 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1420 | +| iterations | 5010 | +| time_elapsed | 7225 | +| total_timesteps | 10260480 | +| train/ | | +| approx_kl | 0.013673531 | +| clip_fraction | 0.308 | +| clip_range | 0.0724 | +| entropy_loss | -6.82 | +| explained_variance | 0.51 | +| learning_rate | 4.76e-05 | +| loss | -0.0314 | +| n_updates | 35856 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000134 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1420 | +| iterations | 5011 | +| time_elapsed | 7226 | +| total_timesteps | 10262528 | +| train/ | | +| approx_kl | 0.010796471 | +| clip_fraction | 0.319 | +| clip_range | 0.0724 | +| entropy_loss | -7.23 | +| explained_variance | -0.0874 | +| learning_rate | 4.76e-05 | +| loss | -0.0298 | +| n_updates | 35860 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000178 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1420 | +| iterations | 5012 | +| time_elapsed | 7227 | +| total_timesteps | 10264576 | +| train/ | | +| approx_kl | 0.011671061 | +| clip_fraction | 0.333 | +| clip_range | 0.0724 | +| entropy_loss | -7.27 | +| explained_variance | -0.0296 | +| learning_rate | 4.76e-05 | +| loss | -0.0334 | +| n_updates | 35864 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000213 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1420 | +| iterations | 5013 | +| time_elapsed | 7229 | +| total_timesteps | 10266624 | +| train/ | | +| approx_kl | 0.011469921 | +| clip_fraction | 0.327 | +| clip_range | 0.0724 | +| entropy_loss | -7.31 | +| explained_variance | 0.257 | +| learning_rate | 4.76e-05 | +| loss | -0.0287 | +| n_updates | 35868 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000188 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1420 | +| iterations | 5014 | +| time_elapsed | 7230 | +| total_timesteps | 10268672 | +| train/ | | +| approx_kl | 0.010615056 | +| clip_fraction | 0.347 | +| clip_range | 0.0724 | +| entropy_loss | -6.89 | +| explained_variance | 0.276 | +| learning_rate | 4.76e-05 | +| loss | -0.0218 | +| n_updates | 35872 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.00025 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1420 | +| iterations | 5015 | +| time_elapsed | 7232 | +| total_timesteps | 10270720 | +| train/ | | +| approx_kl | 0.012573503 | +| clip_fraction | 0.338 | +| clip_range | 0.0724 | +| entropy_loss | -6.93 | +| explained_variance | 0.539 | +| learning_rate | 4.76e-05 | +| loss | -0.0363 | +| n_updates | 35876 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000109 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1420 | +| iterations | 5016 | +| time_elapsed | 7233 | +| total_timesteps | 10272768 | +| train/ | | +| approx_kl | 0.011160098 | +| clip_fraction | 0.34 | +| clip_range | 0.0724 | +| entropy_loss | -7.4 | +| explained_variance | -0.295 | +| learning_rate | 4.76e-05 | +| loss | -0.0373 | +| n_updates | 35880 | +| policy_gradient_loss | -0.0222 | +| value_loss | 0.000128 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1420 | +| iterations | 5017 | +| time_elapsed | 7235 | +| total_timesteps | 10274816 | +| train/ | | +| approx_kl | 0.00966533 | +| clip_fraction | 0.285 | +| clip_range | 0.0724 | +| entropy_loss | -7.03 | +| explained_variance | 0.148 | +| learning_rate | 4.76e-05 | +| loss | -0.0235 | +| n_updates | 35884 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000167 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1420 | +| iterations | 5018 | +| time_elapsed | 7236 | +| total_timesteps | 10276864 | +| train/ | | +| approx_kl | 0.013290302 | +| clip_fraction | 0.298 | +| clip_range | 0.0724 | +| entropy_loss | -7.03 | +| explained_variance | 0.237 | +| learning_rate | 4.76e-05 | +| loss | -0.0395 | +| n_updates | 35888 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000144 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1420 | +| iterations | 5019 | +| time_elapsed | 7238 | +| total_timesteps | 10278912 | +| train/ | | +| approx_kl | 0.011999993 | +| clip_fraction | 0.339 | +| clip_range | 0.0724 | +| entropy_loss | -7 | +| explained_variance | 0.399 | +| learning_rate | 4.76e-05 | +| loss | -0.0303 | +| n_updates | 35892 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000103 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1420 | +| iterations | 5020 | +| time_elapsed | 7239 | +| total_timesteps | 10280960 | +| train/ | | +| approx_kl | 0.009911148 | +| clip_fraction | 0.308 | +| clip_range | 0.0724 | +| entropy_loss | -6.98 | +| explained_variance | 0.397 | +| learning_rate | 4.76e-05 | +| loss | -0.0314 | +| n_updates | 35896 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000208 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1420 | +| iterations | 5021 | +| time_elapsed | 7240 | +| total_timesteps | 10283008 | +| train/ | | +| approx_kl | 0.011360228 | +| clip_fraction | 0.316 | +| clip_range | 0.0724 | +| entropy_loss | -7.34 | +| explained_variance | -0.127 | +| learning_rate | 4.76e-05 | +| loss | -0.0375 | +| n_updates | 35900 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000105 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1420 | +| iterations | 5022 | +| time_elapsed | 7242 | +| total_timesteps | 10285056 | +| train/ | | +| approx_kl | 0.010229845 | +| clip_fraction | 0.287 | +| clip_range | 0.0724 | +| entropy_loss | -7.04 | +| explained_variance | 0.31 | +| learning_rate | 4.76e-05 | +| loss | -0.026 | +| n_updates | 35904 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000108 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1420 | +| iterations | 5023 | +| time_elapsed | 7243 | +| total_timesteps | 10287104 | +| train/ | | +| approx_kl | 0.011276551 | +| clip_fraction | 0.33 | +| clip_range | 0.0724 | +| entropy_loss | -6.73 | +| explained_variance | 0.481 | +| learning_rate | 4.76e-05 | +| loss | -0.0352 | +| n_updates | 35908 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000135 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1420 | +| iterations | 5024 | +| time_elapsed | 7245 | +| total_timesteps | 10289152 | +| train/ | | +| approx_kl | 0.011910042 | +| clip_fraction | 0.332 | +| clip_range | 0.0724 | +| entropy_loss | -7.17 | +| explained_variance | -0.0577 | +| learning_rate | 4.76e-05 | +| loss | -0.0319 | +| n_updates | 35912 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000109 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1420 | +| iterations | 5025 | +| time_elapsed | 7246 | +| total_timesteps | 10291200 | +| train/ | | +| approx_kl | 0.010393969 | +| clip_fraction | 0.303 | +| clip_range | 0.0724 | +| entropy_loss | -7.37 | +| explained_variance | -0.0833 | +| learning_rate | 4.76e-05 | +| loss | -0.0316 | +| n_updates | 35916 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000147 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1420 | +| iterations | 5026 | +| time_elapsed | 7248 | +| total_timesteps | 10293248 | +| train/ | | +| approx_kl | 0.009536693 | +| clip_fraction | 0.304 | +| clip_range | 0.0724 | +| entropy_loss | -7 | +| explained_variance | 0.383 | +| learning_rate | 4.76e-05 | +| loss | -0.0273 | +| n_updates | 35920 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.00017 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1420 | +| iterations | 5027 | +| time_elapsed | 7249 | +| total_timesteps | 10295296 | +| train/ | | +| approx_kl | 0.008582106 | +| clip_fraction | 0.31 | +| clip_range | 0.0724 | +| entropy_loss | -6.95 | +| explained_variance | 0.558 | +| learning_rate | 4.76e-05 | +| loss | -0.025 | +| n_updates | 35924 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000126 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1420 | +| iterations | 5028 | +| time_elapsed | 7251 | +| total_timesteps | 10297344 | +| train/ | | +| approx_kl | 0.011843488 | +| clip_fraction | 0.314 | +| clip_range | 0.0724 | +| entropy_loss | -6.46 | +| explained_variance | 0.657 | +| learning_rate | 4.76e-05 | +| loss | -0.024 | +| n_updates | 35928 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000148 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1420 | +| iterations | 5029 | +| time_elapsed | 7252 | +| total_timesteps | 10299392 | +| train/ | | +| approx_kl | 0.011684285 | +| clip_fraction | 0.335 | +| clip_range | 0.0724 | +| entropy_loss | -7.06 | +| explained_variance | 0.544 | +| learning_rate | 4.76e-05 | +| loss | -0.0414 | +| n_updates | 35932 | +| policy_gradient_loss | -0.0226 | +| value_loss | 5.68e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1420 | +| iterations | 5030 | +| time_elapsed | 7254 | +| total_timesteps | 10301440 | +| train/ | | +| approx_kl | 0.012177175 | +| clip_fraction | 0.33 | +| clip_range | 0.0724 | +| entropy_loss | -7.21 | +| explained_variance | -0.15 | +| learning_rate | 4.76e-05 | +| loss | -0.0292 | +| n_updates | 35936 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.00013 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1420 | +| iterations | 5031 | +| time_elapsed | 7255 | +| total_timesteps | 10303488 | +| train/ | | +| approx_kl | 0.012645958 | +| clip_fraction | 0.27 | +| clip_range | 0.0724 | +| entropy_loss | -6.92 | +| explained_variance | 0.333 | +| learning_rate | 4.76e-05 | +| loss | -0.0328 | +| n_updates | 35940 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000232 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1420 | +| iterations | 5032 | +| time_elapsed | 7257 | +| total_timesteps | 10305536 | +| train/ | | +| approx_kl | 0.0111238025 | +| clip_fraction | 0.3 | +| clip_range | 0.0724 | +| entropy_loss | -6.86 | +| explained_variance | 0.429 | +| learning_rate | 4.76e-05 | +| loss | -0.0263 | +| n_updates | 35944 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000189 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1420 | +| iterations | 5033 | +| time_elapsed | 7258 | +| total_timesteps | 10307584 | +| train/ | | +| approx_kl | 0.010567648 | +| clip_fraction | 0.319 | +| clip_range | 0.0724 | +| entropy_loss | -7.46 | +| explained_variance | -0.13 | +| learning_rate | 4.76e-05 | +| loss | -0.0335 | +| n_updates | 35948 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000202 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1420 | +| iterations | 5034 | +| time_elapsed | 7259 | +| total_timesteps | 10309632 | +| train/ | | +| approx_kl | 0.01051179 | +| clip_fraction | 0.308 | +| clip_range | 0.0724 | +| entropy_loss | -7.29 | +| explained_variance | 0.292 | +| learning_rate | 4.76e-05 | +| loss | -0.0358 | +| n_updates | 35952 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000127 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1420 | +| iterations | 5035 | +| time_elapsed | 7261 | +| total_timesteps | 10311680 | +| train/ | | +| approx_kl | 0.012517256 | +| clip_fraction | 0.353 | +| clip_range | 0.0724 | +| entropy_loss | -7.03 | +| explained_variance | 0.443 | +| learning_rate | 4.76e-05 | +| loss | -0.0285 | +| n_updates | 35956 | +| policy_gradient_loss | -0.0221 | +| value_loss | 0.000132 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1420 | +| iterations | 5036 | +| time_elapsed | 7262 | +| total_timesteps | 10313728 | +| train/ | | +| approx_kl | 0.011417143 | +| clip_fraction | 0.315 | +| clip_range | 0.0724 | +| entropy_loss | -6.82 | +| explained_variance | 0.469 | +| learning_rate | 4.76e-05 | +| loss | -0.0254 | +| n_updates | 35960 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000178 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1420 | +| iterations | 5037 | +| time_elapsed | 7264 | +| total_timesteps | 10315776 | +| train/ | | +| approx_kl | 0.01243702 | +| clip_fraction | 0.34 | +| clip_range | 0.0724 | +| entropy_loss | -6.84 | +| explained_variance | 0.612 | +| learning_rate | 4.76e-05 | +| loss | -0.0428 | +| n_updates | 35964 | +| policy_gradient_loss | -0.0202 | +| value_loss | 9.17e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1420 | +| iterations | 5038 | +| time_elapsed | 7265 | +| total_timesteps | 10317824 | +| train/ | | +| approx_kl | 0.011474447 | +| clip_fraction | 0.321 | +| clip_range | 0.0724 | +| entropy_loss | -7.21 | +| explained_variance | 0.377 | +| learning_rate | 4.76e-05 | +| loss | -0.0309 | +| n_updates | 35968 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000112 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1420 | +| iterations | 5039 | +| time_elapsed | 7267 | +| total_timesteps | 10319872 | +| train/ | | +| approx_kl | 0.014170045 | +| clip_fraction | 0.303 | +| clip_range | 0.0724 | +| entropy_loss | -6.84 | +| explained_variance | 0.416 | +| learning_rate | 4.75e-05 | +| loss | -0.0294 | +| n_updates | 35972 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000119 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1420 | +| iterations | 5040 | +| time_elapsed | 7268 | +| total_timesteps | 10321920 | +| train/ | | +| approx_kl | 0.011219107 | +| clip_fraction | 0.336 | +| clip_range | 0.0724 | +| entropy_loss | -7.19 | +| explained_variance | 0.361 | +| learning_rate | 4.75e-05 | +| loss | -0.0363 | +| n_updates | 35976 | +| policy_gradient_loss | -0.0229 | +| value_loss | 8.12e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1420 | +| iterations | 5041 | +| time_elapsed | 7269 | +| total_timesteps | 10323968 | +| train/ | | +| approx_kl | 0.009260009 | +| clip_fraction | 0.303 | +| clip_range | 0.0724 | +| entropy_loss | -7.03 | +| explained_variance | 0.488 | +| learning_rate | 4.75e-05 | +| loss | -0.0287 | +| n_updates | 35980 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.00015 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1420 | +| iterations | 5042 | +| time_elapsed | 7271 | +| total_timesteps | 10326016 | +| train/ | | +| approx_kl | 0.011765284 | +| clip_fraction | 0.299 | +| clip_range | 0.0724 | +| entropy_loss | -7.02 | +| explained_variance | 0.21 | +| learning_rate | 4.75e-05 | +| loss | -0.031 | +| n_updates | 35984 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000208 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1420 | +| iterations | 5043 | +| time_elapsed | 7272 | +| total_timesteps | 10328064 | +| train/ | | +| approx_kl | 0.0123213865 | +| clip_fraction | 0.312 | +| clip_range | 0.0724 | +| entropy_loss | -7.29 | +| explained_variance | -0.0801 | +| learning_rate | 4.75e-05 | +| loss | -0.0294 | +| n_updates | 35988 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.00016 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1420 | +| iterations | 5044 | +| time_elapsed | 7274 | +| total_timesteps | 10330112 | +| train/ | | +| approx_kl | 0.011091653 | +| clip_fraction | 0.331 | +| clip_range | 0.0724 | +| entropy_loss | -7.41 | +| explained_variance | -0.143 | +| learning_rate | 4.75e-05 | +| loss | -0.0343 | +| n_updates | 35992 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000126 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1420 | +| iterations | 5045 | +| time_elapsed | 7275 | +| total_timesteps | 10332160 | +| train/ | | +| approx_kl | 0.01016396 | +| clip_fraction | 0.328 | +| clip_range | 0.0724 | +| entropy_loss | -6.77 | +| explained_variance | 0.247 | +| learning_rate | 4.75e-05 | +| loss | -0.0269 | +| n_updates | 35996 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000398 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1420 | +| iterations | 5046 | +| time_elapsed | 7277 | +| total_timesteps | 10334208 | +| train/ | | +| approx_kl | 0.011549831 | +| clip_fraction | 0.282 | +| clip_range | 0.0724 | +| entropy_loss | -6.64 | +| explained_variance | 0.289 | +| learning_rate | 4.75e-05 | +| loss | -0.0291 | +| n_updates | 36000 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000335 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1420 | +| iterations | 5047 | +| time_elapsed | 7278 | +| total_timesteps | 10336256 | +| train/ | | +| approx_kl | 0.011187151 | +| clip_fraction | 0.337 | +| clip_range | 0.0724 | +| entropy_loss | -7.03 | +| explained_variance | 0.266 | +| learning_rate | 4.75e-05 | +| loss | -0.0386 | +| n_updates | 36004 | +| policy_gradient_loss | -0.023 | +| value_loss | 0.000119 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1420 | +| iterations | 5048 | +| time_elapsed | 7280 | +| total_timesteps | 10338304 | +| train/ | | +| approx_kl | 0.012499617 | +| clip_fraction | 0.318 | +| clip_range | 0.0724 | +| entropy_loss | -7.24 | +| explained_variance | -0.038 | +| learning_rate | 4.75e-05 | +| loss | -0.028 | +| n_updates | 36008 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000191 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1420 | +| iterations | 5049 | +| time_elapsed | 7281 | +| total_timesteps | 10340352 | +| train/ | | +| approx_kl | 0.011350295 | +| clip_fraction | 0.33 | +| clip_range | 0.0724 | +| entropy_loss | -6.96 | +| explained_variance | 0.517 | +| learning_rate | 4.75e-05 | +| loss | -0.0329 | +| n_updates | 36012 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000105 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1420 | +| iterations | 5050 | +| time_elapsed | 7282 | +| total_timesteps | 10342400 | +| train/ | | +| approx_kl | 0.010694807 | +| clip_fraction | 0.352 | +| clip_range | 0.0724 | +| entropy_loss | -7.42 | +| explained_variance | -0.0808 | +| learning_rate | 4.75e-05 | +| loss | -0.0318 | +| n_updates | 36016 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000157 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1420 | +| iterations | 5051 | +| time_elapsed | 7284 | +| total_timesteps | 10344448 | +| train/ | | +| approx_kl | 0.009780823 | +| clip_fraction | 0.3 | +| clip_range | 0.0724 | +| entropy_loss | -6.82 | +| explained_variance | 0.474 | +| learning_rate | 4.75e-05 | +| loss | -0.031 | +| n_updates | 36020 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000196 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1420 | +| iterations | 5052 | +| time_elapsed | 7285 | +| total_timesteps | 10346496 | +| train/ | | +| approx_kl | 0.009655324 | +| clip_fraction | 0.318 | +| clip_range | 0.0724 | +| entropy_loss | -7 | +| explained_variance | 0.24 | +| learning_rate | 4.75e-05 | +| loss | -0.0347 | +| n_updates | 36024 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000193 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1420 | +| iterations | 5053 | +| time_elapsed | 7287 | +| total_timesteps | 10348544 | +| train/ | | +| approx_kl | 0.013094079 | +| clip_fraction | 0.334 | +| clip_range | 0.0724 | +| entropy_loss | -7.04 | +| explained_variance | 0.705 | +| learning_rate | 4.75e-05 | +| loss | -0.0405 | +| n_updates | 36028 | +| policy_gradient_loss | -0.0234 | +| value_loss | 5.5e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1420 | +| iterations | 5054 | +| time_elapsed | 7288 | +| total_timesteps | 10350592 | +| train/ | | +| approx_kl | 0.010784466 | +| clip_fraction | 0.303 | +| clip_range | 0.0724 | +| entropy_loss | -7.22 | +| explained_variance | 0.0282 | +| learning_rate | 4.75e-05 | +| loss | -0.0384 | +| n_updates | 36032 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000144 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1420 | +| iterations | 5055 | +| time_elapsed | 7290 | +| total_timesteps | 10352640 | +| train/ | | +| approx_kl | 0.011353793 | +| clip_fraction | 0.314 | +| clip_range | 0.0724 | +| entropy_loss | -6.72 | +| explained_variance | 0.632 | +| learning_rate | 4.75e-05 | +| loss | -0.0252 | +| n_updates | 36036 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000119 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1420 | +| iterations | 5056 | +| time_elapsed | 7291 | +| total_timesteps | 10354688 | +| train/ | | +| approx_kl | 0.010183836 | +| clip_fraction | 0.306 | +| clip_range | 0.0724 | +| entropy_loss | -6.97 | +| explained_variance | 0.219 | +| learning_rate | 4.75e-05 | +| loss | -0.0276 | +| n_updates | 36040 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.0002 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1420 | +| iterations | 5057 | +| time_elapsed | 7293 | +| total_timesteps | 10356736 | +| train/ | | +| approx_kl | 0.012717289 | +| clip_fraction | 0.338 | +| clip_range | 0.0724 | +| entropy_loss | -7.14 | +| explained_variance | 0.249 | +| learning_rate | 4.75e-05 | +| loss | -0.0345 | +| n_updates | 36044 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000164 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1420 | +| iterations | 5058 | +| time_elapsed | 7294 | +| total_timesteps | 10358784 | +| train/ | | +| approx_kl | 0.011832427 | +| clip_fraction | 0.33 | +| clip_range | 0.0724 | +| entropy_loss | -6.5 | +| explained_variance | 0.664 | +| learning_rate | 4.75e-05 | +| loss | -0.0347 | +| n_updates | 36048 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000132 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1420 | +| iterations | 5059 | +| time_elapsed | 7296 | +| total_timesteps | 10360832 | +| train/ | | +| approx_kl | 0.012737036 | +| clip_fraction | 0.343 | +| clip_range | 0.0724 | +| entropy_loss | -7.01 | +| explained_variance | -0.0228 | +| learning_rate | 4.75e-05 | +| loss | -0.0288 | +| n_updates | 36052 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000125 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1420 | +| iterations | 5060 | +| time_elapsed | 7297 | +| total_timesteps | 10362880 | +| train/ | | +| approx_kl | 0.012012539 | +| clip_fraction | 0.331 | +| clip_range | 0.0724 | +| entropy_loss | -6.91 | +| explained_variance | 0.298 | +| learning_rate | 4.75e-05 | +| loss | -0.0335 | +| n_updates | 36056 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000272 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1420 | +| iterations | 5061 | +| time_elapsed | 7298 | +| total_timesteps | 10364928 | +| train/ | | +| approx_kl | 0.011591956 | +| clip_fraction | 0.332 | +| clip_range | 0.0724 | +| entropy_loss | -6.83 | +| explained_variance | 0.333 | +| learning_rate | 4.75e-05 | +| loss | -0.0297 | +| n_updates | 36060 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000148 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1420 | +| iterations | 5062 | +| time_elapsed | 7300 | +| total_timesteps | 10366976 | +| train/ | | +| approx_kl | 0.012122342 | +| clip_fraction | 0.337 | +| clip_range | 0.0724 | +| entropy_loss | -7.21 | +| explained_variance | 0.0557 | +| learning_rate | 4.75e-05 | +| loss | -0.0325 | +| n_updates | 36064 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000171 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1420 | +| iterations | 5063 | +| time_elapsed | 7301 | +| total_timesteps | 10369024 | +| train/ | | +| approx_kl | 0.011098778 | +| clip_fraction | 0.32 | +| clip_range | 0.0724 | +| entropy_loss | -6.93 | +| explained_variance | 0.401 | +| learning_rate | 4.75e-05 | +| loss | -0.0225 | +| n_updates | 36068 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000145 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1420 | +| iterations | 5064 | +| time_elapsed | 7303 | +| total_timesteps | 10371072 | +| train/ | | +| approx_kl | 0.012088966 | +| clip_fraction | 0.318 | +| clip_range | 0.0724 | +| entropy_loss | -6.87 | +| explained_variance | 0.475 | +| learning_rate | 4.75e-05 | +| loss | -0.0273 | +| n_updates | 36072 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000135 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1420 | +| iterations | 5065 | +| time_elapsed | 7304 | +| total_timesteps | 10373120 | +| train/ | | +| approx_kl | 0.011755973 | +| clip_fraction | 0.331 | +| clip_range | 0.0724 | +| entropy_loss | -7.39 | +| explained_variance | -0.0701 | +| learning_rate | 4.75e-05 | +| loss | -0.0285 | +| n_updates | 36076 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000276 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1420 | +| iterations | 5066 | +| time_elapsed | 7305 | +| total_timesteps | 10375168 | +| train/ | | +| approx_kl | 0.009345465 | +| clip_fraction | 0.317 | +| clip_range | 0.0724 | +| entropy_loss | -7.36 | +| explained_variance | -0.0912 | +| learning_rate | 4.75e-05 | +| loss | -0.0328 | +| n_updates | 36080 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000147 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1420 | +| iterations | 5067 | +| time_elapsed | 7307 | +| total_timesteps | 10377216 | +| train/ | | +| approx_kl | 0.010857211 | +| clip_fraction | 0.312 | +| clip_range | 0.0724 | +| entropy_loss | -7.15 | +| explained_variance | 0.246 | +| learning_rate | 4.75e-05 | +| loss | -0.0299 | +| n_updates | 36084 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000166 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1420 | +| iterations | 5068 | +| time_elapsed | 7308 | +| total_timesteps | 10379264 | +| train/ | | +| approx_kl | 0.009387194 | +| clip_fraction | 0.319 | +| clip_range | 0.0724 | +| entropy_loss | -7.21 | +| explained_variance | 0.297 | +| learning_rate | 4.75e-05 | +| loss | -0.0343 | +| n_updates | 36088 | +| policy_gradient_loss | -0.0214 | +| value_loss | 9.24e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1420 | +| iterations | 5069 | +| time_elapsed | 7310 | +| total_timesteps | 10381312 | +| train/ | | +| approx_kl | 0.010287155 | +| clip_fraction | 0.298 | +| clip_range | 0.0724 | +| entropy_loss | -6.75 | +| explained_variance | 0.262 | +| learning_rate | 4.75e-05 | +| loss | -0.0264 | +| n_updates | 36092 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000328 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1420 | +| iterations | 5070 | +| time_elapsed | 7311 | +| total_timesteps | 10383360 | +| train/ | | +| approx_kl | 0.010848646 | +| clip_fraction | 0.313 | +| clip_range | 0.0724 | +| entropy_loss | -6.58 | +| explained_variance | 0.477 | +| learning_rate | 4.75e-05 | +| loss | -0.0273 | +| n_updates | 36096 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.00017 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1420 | +| iterations | 5071 | +| time_elapsed | 7313 | +| total_timesteps | 10385408 | +| train/ | | +| approx_kl | 0.012472054 | +| clip_fraction | 0.336 | +| clip_range | 0.0724 | +| entropy_loss | -6.64 | +| explained_variance | 0.625 | +| learning_rate | 4.75e-05 | +| loss | -0.0327 | +| n_updates | 36100 | +| policy_gradient_loss | -0.0217 | +| value_loss | 5.84e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1420 | +| iterations | 5072 | +| time_elapsed | 7314 | +| total_timesteps | 10387456 | +| train/ | | +| approx_kl | 0.014307833 | +| clip_fraction | 0.321 | +| clip_range | 0.0724 | +| entropy_loss | -7.37 | +| explained_variance | -0.114 | +| learning_rate | 4.75e-05 | +| loss | -0.031 | +| n_updates | 36104 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000115 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1420 | +| iterations | 5073 | +| time_elapsed | 7316 | +| total_timesteps | 10389504 | +| train/ | | +| approx_kl | 0.0117218215 | +| clip_fraction | 0.307 | +| clip_range | 0.0724 | +| entropy_loss | -6.71 | +| explained_variance | 0.478 | +| learning_rate | 4.75e-05 | +| loss | -0.0306 | +| n_updates | 36108 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000219 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1420 | +| iterations | 5074 | +| time_elapsed | 7317 | +| total_timesteps | 10391552 | +| train/ | | +| approx_kl | 0.012468936 | +| clip_fraction | 0.315 | +| clip_range | 0.0724 | +| entropy_loss | -6.5 | +| explained_variance | 0.562 | +| learning_rate | 4.75e-05 | +| loss | -0.0282 | +| n_updates | 36112 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000158 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1420 | +| iterations | 5075 | +| time_elapsed | 7318 | +| total_timesteps | 10393600 | +| train/ | | +| approx_kl | 0.01257977 | +| clip_fraction | 0.325 | +| clip_range | 0.0724 | +| entropy_loss | -7.11 | +| explained_variance | -0.348 | +| learning_rate | 4.75e-05 | +| loss | -0.0379 | +| n_updates | 36116 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000109 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1420 | +| iterations | 5076 | +| time_elapsed | 7320 | +| total_timesteps | 10395648 | +| train/ | | +| approx_kl | 0.014528301 | +| clip_fraction | 0.342 | +| clip_range | 0.0724 | +| entropy_loss | -7.38 | +| explained_variance | -0.076 | +| learning_rate | 4.75e-05 | +| loss | -0.0368 | +| n_updates | 36120 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000131 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1420 | +| iterations | 5077 | +| time_elapsed | 7321 | +| total_timesteps | 10397696 | +| train/ | | +| approx_kl | 0.01065727 | +| clip_fraction | 0.302 | +| clip_range | 0.0724 | +| entropy_loss | -7.38 | +| explained_variance | -0.025 | +| learning_rate | 4.75e-05 | +| loss | -0.0296 | +| n_updates | 36124 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000244 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1420 | +| iterations | 5078 | +| time_elapsed | 7323 | +| total_timesteps | 10399744 | +| train/ | | +| approx_kl | 0.012097351 | +| clip_fraction | 0.316 | +| clip_range | 0.0724 | +| entropy_loss | -7.01 | +| explained_variance | 0.263 | +| learning_rate | 4.75e-05 | +| loss | -0.0292 | +| n_updates | 36128 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000209 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1420 | +| iterations | 5079 | +| time_elapsed | 7324 | +| total_timesteps | 10401792 | +| train/ | | +| approx_kl | 0.0097229015 | +| clip_fraction | 0.305 | +| clip_range | 0.0724 | +| entropy_loss | -7.3 | +| explained_variance | -0.0588 | +| learning_rate | 4.75e-05 | +| loss | -0.0349 | +| n_updates | 36132 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000174 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1420 | +| iterations | 5080 | +| time_elapsed | 7326 | +| total_timesteps | 10403840 | +| train/ | | +| approx_kl | 0.009285068 | +| clip_fraction | 0.291 | +| clip_range | 0.0724 | +| entropy_loss | -6.42 | +| explained_variance | 0.624 | +| learning_rate | 4.75e-05 | +| loss | -0.0271 | +| n_updates | 36136 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000191 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1420 | +| iterations | 5081 | +| time_elapsed | 7327 | +| total_timesteps | 10405888 | +| train/ | | +| approx_kl | 0.012082949 | +| clip_fraction | 0.317 | +| clip_range | 0.0724 | +| entropy_loss | -6.75 | +| explained_variance | 0.563 | +| learning_rate | 4.75e-05 | +| loss | -0.0269 | +| n_updates | 36140 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000182 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1420 | +| iterations | 5082 | +| time_elapsed | 7328 | +| total_timesteps | 10407936 | +| train/ | | +| approx_kl | 0.010447154 | +| clip_fraction | 0.309 | +| clip_range | 0.0724 | +| entropy_loss | -6.33 | +| explained_variance | 0.567 | +| learning_rate | 4.75e-05 | +| loss | -0.0272 | +| n_updates | 36144 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.00016 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1420 | +| iterations | 5083 | +| time_elapsed | 7330 | +| total_timesteps | 10409984 | +| train/ | | +| approx_kl | 0.01164502 | +| clip_fraction | 0.306 | +| clip_range | 0.0724 | +| entropy_loss | -7.09 | +| explained_variance | 0.281 | +| learning_rate | 4.75e-05 | +| loss | -0.0355 | +| n_updates | 36148 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000164 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1420 | +| iterations | 5084 | +| time_elapsed | 7331 | +| total_timesteps | 10412032 | +| train/ | | +| approx_kl | 0.013877217 | +| clip_fraction | 0.364 | +| clip_range | 0.0724 | +| entropy_loss | -7.25 | +| explained_variance | -0.0289 | +| learning_rate | 4.75e-05 | +| loss | -0.036 | +| n_updates | 36152 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000178 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1420 | +| iterations | 5085 | +| time_elapsed | 7333 | +| total_timesteps | 10414080 | +| train/ | | +| approx_kl | 0.010263132 | +| clip_fraction | 0.327 | +| clip_range | 0.0724 | +| entropy_loss | -7.43 | +| explained_variance | -0.125 | +| learning_rate | 4.75e-05 | +| loss | -0.0313 | +| n_updates | 36156 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000181 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1420 | +| iterations | 5086 | +| time_elapsed | 7334 | +| total_timesteps | 10416128 | +| train/ | | +| approx_kl | 0.0117664775 | +| clip_fraction | 0.351 | +| clip_range | 0.0724 | +| entropy_loss | -7.41 | +| explained_variance | -0.398 | +| learning_rate | 4.75e-05 | +| loss | -0.0436 | +| n_updates | 36160 | +| policy_gradient_loss | -0.027 | +| value_loss | 5.15e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1420 | +| iterations | 5087 | +| time_elapsed | 7336 | +| total_timesteps | 10418176 | +| train/ | | +| approx_kl | 0.011461554 | +| clip_fraction | 0.32 | +| clip_range | 0.0724 | +| entropy_loss | -6.75 | +| explained_variance | 0.609 | +| learning_rate | 4.75e-05 | +| loss | -0.0307 | +| n_updates | 36164 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000141 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1420 | +| iterations | 5088 | +| time_elapsed | 7337 | +| total_timesteps | 10420224 | +| train/ | | +| approx_kl | 0.010969309 | +| clip_fraction | 0.284 | +| clip_range | 0.0724 | +| entropy_loss | -6.9 | +| explained_variance | 0.582 | +| learning_rate | 4.75e-05 | +| loss | -0.0277 | +| n_updates | 36168 | +| policy_gradient_loss | -0.0166 | +| value_loss | 9.83e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1420 | +| iterations | 5089 | +| time_elapsed | 7338 | +| total_timesteps | 10422272 | +| train/ | | +| approx_kl | 0.011455901 | +| clip_fraction | 0.33 | +| clip_range | 0.0724 | +| entropy_loss | -6.45 | +| explained_variance | 0.76 | +| learning_rate | 4.75e-05 | +| loss | -0.029 | +| n_updates | 36172 | +| policy_gradient_loss | -0.0187 | +| value_loss | 5.9e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1420 | +| iterations | 5090 | +| time_elapsed | 7340 | +| total_timesteps | 10424320 | +| train/ | | +| approx_kl | 0.013135915 | +| clip_fraction | 0.308 | +| clip_range | 0.0724 | +| entropy_loss | -6.99 | +| explained_variance | 0.339 | +| learning_rate | 4.75e-05 | +| loss | -0.032 | +| n_updates | 36176 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.00015 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1420 | +| iterations | 5091 | +| time_elapsed | 7341 | +| total_timesteps | 10426368 | +| train/ | | +| approx_kl | 0.01195889 | +| clip_fraction | 0.327 | +| clip_range | 0.0724 | +| entropy_loss | -7.42 | +| explained_variance | -0.145 | +| learning_rate | 4.75e-05 | +| loss | -0.0306 | +| n_updates | 36180 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000108 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1420 | +| iterations | 5092 | +| time_elapsed | 7343 | +| total_timesteps | 10428416 | +| train/ | | +| approx_kl | 0.009961309 | +| clip_fraction | 0.292 | +| clip_range | 0.0724 | +| entropy_loss | -6.82 | +| explained_variance | 0.55 | +| learning_rate | 4.75e-05 | +| loss | -0.0316 | +| n_updates | 36184 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000175 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1420 | +| iterations | 5093 | +| time_elapsed | 7344 | +| total_timesteps | 10430464 | +| train/ | | +| approx_kl | 0.013068481 | +| clip_fraction | 0.328 | +| clip_range | 0.0724 | +| entropy_loss | -6.75 | +| explained_variance | 0.334 | +| learning_rate | 4.75e-05 | +| loss | -0.0355 | +| n_updates | 36188 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.00011 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1420 | +| iterations | 5094 | +| time_elapsed | 7345 | +| total_timesteps | 10432512 | +| train/ | | +| approx_kl | 0.009772967 | +| clip_fraction | 0.3 | +| clip_range | 0.0724 | +| entropy_loss | -7.2 | +| explained_variance | -0.0652 | +| learning_rate | 4.75e-05 | +| loss | -0.0255 | +| n_updates | 36192 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000132 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1420 | +| iterations | 5095 | +| time_elapsed | 7347 | +| total_timesteps | 10434560 | +| train/ | | +| approx_kl | 0.012445309 | +| clip_fraction | 0.325 | +| clip_range | 0.0724 | +| entropy_loss | -7.37 | +| explained_variance | -0.108 | +| learning_rate | 4.75e-05 | +| loss | -0.0303 | +| n_updates | 36196 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000103 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1420 | +| iterations | 5096 | +| time_elapsed | 7348 | +| total_timesteps | 10436608 | +| train/ | | +| approx_kl | 0.010411973 | +| clip_fraction | 0.331 | +| clip_range | 0.0724 | +| entropy_loss | -7.36 | +| explained_variance | -0.14 | +| learning_rate | 4.75e-05 | +| loss | -0.0323 | +| n_updates | 36200 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000148 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1420 | +| iterations | 5097 | +| time_elapsed | 7350 | +| total_timesteps | 10438656 | +| train/ | | +| approx_kl | 0.010265056 | +| clip_fraction | 0.289 | +| clip_range | 0.0724 | +| entropy_loss | -7.5 | +| explained_variance | -0.0789 | +| learning_rate | 4.75e-05 | +| loss | -0.0275 | +| n_updates | 36204 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1420 | +| iterations | 5098 | +| time_elapsed | 7351 | +| total_timesteps | 10440704 | +| train/ | | +| approx_kl | 0.009109561 | +| clip_fraction | 0.288 | +| clip_range | 0.0724 | +| entropy_loss | -6.88 | +| explained_variance | 0.279 | +| learning_rate | 4.75e-05 | +| loss | -0.025 | +| n_updates | 36208 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000307 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1420 | +| iterations | 5099 | +| time_elapsed | 7353 | +| total_timesteps | 10442752 | +| train/ | | +| approx_kl | 0.008336071 | +| clip_fraction | 0.306 | +| clip_range | 0.0724 | +| entropy_loss | -6.65 | +| explained_variance | 0.44 | +| learning_rate | 4.75e-05 | +| loss | -0.0252 | +| n_updates | 36212 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000197 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1420 | +| iterations | 5100 | +| time_elapsed | 7354 | +| total_timesteps | 10444800 | +| train/ | | +| approx_kl | 0.010704137 | +| clip_fraction | 0.329 | +| clip_range | 0.0724 | +| entropy_loss | -6.78 | +| explained_variance | 0.449 | +| learning_rate | 4.75e-05 | +| loss | -0.0276 | +| n_updates | 36216 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.00016 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1420 | +| iterations | 5101 | +| time_elapsed | 7355 | +| total_timesteps | 10446848 | +| train/ | | +| approx_kl | 0.009765185 | +| clip_fraction | 0.317 | +| clip_range | 0.0724 | +| entropy_loss | -7.04 | +| explained_variance | 0.505 | +| learning_rate | 4.75e-05 | +| loss | -0.0254 | +| n_updates | 36220 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000146 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1420 | +| iterations | 5102 | +| time_elapsed | 7357 | +| total_timesteps | 10448896 | +| train/ | | +| approx_kl | 0.009898423 | +| clip_fraction | 0.305 | +| clip_range | 0.0724 | +| entropy_loss | -6.87 | +| explained_variance | 0.303 | +| learning_rate | 4.75e-05 | +| loss | -0.031 | +| n_updates | 36224 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000125 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1420 | +| iterations | 5103 | +| time_elapsed | 7358 | +| total_timesteps | 10450944 | +| train/ | | +| approx_kl | 0.011946766 | +| clip_fraction | 0.329 | +| clip_range | 0.0724 | +| entropy_loss | -7.1 | +| explained_variance | 0.402 | +| learning_rate | 4.75e-05 | +| loss | -0.035 | +| n_updates | 36228 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000116 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1420 | +| iterations | 5104 | +| time_elapsed | 7360 | +| total_timesteps | 10452992 | +| train/ | | +| approx_kl | 0.010187361 | +| clip_fraction | 0.295 | +| clip_range | 0.0724 | +| entropy_loss | -7.04 | +| explained_variance | 0.364 | +| learning_rate | 4.75e-05 | +| loss | -0.0236 | +| n_updates | 36232 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000212 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1420 | +| iterations | 5105 | +| time_elapsed | 7361 | +| total_timesteps | 10455040 | +| train/ | | +| approx_kl | 0.013414886 | +| clip_fraction | 0.326 | +| clip_range | 0.0724 | +| entropy_loss | -6.87 | +| explained_variance | 0.375 | +| learning_rate | 4.75e-05 | +| loss | -0.0323 | +| n_updates | 36236 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000116 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1420 | +| iterations | 5106 | +| time_elapsed | 7363 | +| total_timesteps | 10457088 | +| train/ | | +| approx_kl | 0.014185286 | +| clip_fraction | 0.352 | +| clip_range | 0.0724 | +| entropy_loss | -7.39 | +| explained_variance | -0.0473 | +| learning_rate | 4.75e-05 | +| loss | -0.0314 | +| n_updates | 36240 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.00012 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1420 | +| iterations | 5107 | +| time_elapsed | 7364 | +| total_timesteps | 10459136 | +| train/ | | +| approx_kl | 0.012631899 | +| clip_fraction | 0.299 | +| clip_range | 0.0724 | +| entropy_loss | -7.47 | +| explained_variance | -0.0824 | +| learning_rate | 4.75e-05 | +| loss | -0.0321 | +| n_updates | 36244 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000171 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1420 | +| iterations | 5108 | +| time_elapsed | 7365 | +| total_timesteps | 10461184 | +| train/ | | +| approx_kl | 0.009914398 | +| clip_fraction | 0.304 | +| clip_range | 0.0724 | +| entropy_loss | -7.36 | +| explained_variance | 0.418 | +| learning_rate | 4.75e-05 | +| loss | -0.035 | +| n_updates | 36248 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.0001 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1420 | +| iterations | 5109 | +| time_elapsed | 7367 | +| total_timesteps | 10463232 | +| train/ | | +| approx_kl | 0.010792807 | +| clip_fraction | 0.323 | +| clip_range | 0.0724 | +| entropy_loss | -6.9 | +| explained_variance | 0.256 | +| learning_rate | 4.75e-05 | +| loss | -0.0283 | +| n_updates | 36252 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000231 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1420 | +| iterations | 5110 | +| time_elapsed | 7368 | +| total_timesteps | 10465280 | +| train/ | | +| approx_kl | 0.0123362 | +| clip_fraction | 0.33 | +| clip_range | 0.0724 | +| entropy_loss | -6.92 | +| explained_variance | 0.615 | +| learning_rate | 4.75e-05 | +| loss | -0.0301 | +| n_updates | 36256 | +| policy_gradient_loss | -0.0187 | +| value_loss | 9.52e-05 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1420 | +| iterations | 5111 | +| time_elapsed | 7370 | +| total_timesteps | 10467328 | +| train/ | | +| approx_kl | 0.012102284 | +| clip_fraction | 0.308 | +| clip_range | 0.0724 | +| entropy_loss | -7.16 | +| explained_variance | 0.269 | +| learning_rate | 4.75e-05 | +| loss | -0.0315 | +| n_updates | 36260 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.00016 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1420 | +| iterations | 5112 | +| time_elapsed | 7371 | +| total_timesteps | 10469376 | +| train/ | | +| approx_kl | 0.0099622235 | +| clip_fraction | 0.288 | +| clip_range | 0.0724 | +| entropy_loss | -6.98 | +| explained_variance | 0.381 | +| learning_rate | 4.75e-05 | +| loss | -0.0203 | +| n_updates | 36264 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.00021 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1420 | +| iterations | 5113 | +| time_elapsed | 7373 | +| total_timesteps | 10471424 | +| train/ | | +| approx_kl | 0.011864534 | +| clip_fraction | 0.32 | +| clip_range | 0.0724 | +| entropy_loss | -6.8 | +| explained_variance | 0.508 | +| learning_rate | 4.75e-05 | +| loss | -0.0282 | +| n_updates | 36268 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000143 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1420 | +| iterations | 5114 | +| time_elapsed | 7374 | +| total_timesteps | 10473472 | +| train/ | | +| approx_kl | 0.013694676 | +| clip_fraction | 0.317 | +| clip_range | 0.0724 | +| entropy_loss | -6.89 | +| explained_variance | 0.449 | +| learning_rate | 4.75e-05 | +| loss | -0.0338 | +| n_updates | 36272 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000167 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1420 | +| iterations | 5115 | +| time_elapsed | 7375 | +| total_timesteps | 10475520 | +| train/ | | +| approx_kl | 0.012061937 | +| clip_fraction | 0.316 | +| clip_range | 0.0724 | +| entropy_loss | -7.04 | +| explained_variance | 0.162 | +| learning_rate | 4.75e-05 | +| loss | -0.0284 | +| n_updates | 36276 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000317 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1420 | +| iterations | 5116 | +| time_elapsed | 7377 | +| total_timesteps | 10477568 | +| train/ | | +| approx_kl | 0.010461582 | +| clip_fraction | 0.314 | +| clip_range | 0.0724 | +| entropy_loss | -7.2 | +| explained_variance | 0.135 | +| learning_rate | 4.75e-05 | +| loss | -0.0292 | +| n_updates | 36280 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000273 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1420 | +| iterations | 5117 | +| time_elapsed | 7378 | +| total_timesteps | 10479616 | +| train/ | | +| approx_kl | 0.011525839 | +| clip_fraction | 0.319 | +| clip_range | 0.0724 | +| entropy_loss | -7.12 | +| explained_variance | 0.29 | +| learning_rate | 4.75e-05 | +| loss | -0.0321 | +| n_updates | 36284 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000148 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1420 | +| iterations | 5118 | +| time_elapsed | 7380 | +| total_timesteps | 10481664 | +| train/ | | +| approx_kl | 0.010950281 | +| clip_fraction | 0.326 | +| clip_range | 0.0724 | +| entropy_loss | -7.49 | +| explained_variance | -0.143 | +| learning_rate | 4.75e-05 | +| loss | -0.0383 | +| n_updates | 36288 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000131 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1420 | +| iterations | 5119 | +| time_elapsed | 7381 | +| total_timesteps | 10483712 | +| train/ | | +| approx_kl | 0.011561998 | +| clip_fraction | 0.34 | +| clip_range | 0.0724 | +| entropy_loss | -7.42 | +| explained_variance | -0.124 | +| learning_rate | 4.75e-05 | +| loss | -0.0342 | +| n_updates | 36292 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000137 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1420 | +| iterations | 5120 | +| time_elapsed | 7383 | +| total_timesteps | 10485760 | +| train/ | | +| approx_kl | 0.012413725 | +| clip_fraction | 0.319 | +| clip_range | 0.0724 | +| entropy_loss | -6.4 | +| explained_variance | 0.643 | +| learning_rate | 4.75e-05 | +| loss | -0.0292 | +| n_updates | 36296 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.00011 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1420 | +| iterations | 5121 | +| time_elapsed | 7384 | +| total_timesteps | 10487808 | +| train/ | | +| approx_kl | 0.013700001 | +| clip_fraction | 0.341 | +| clip_range | 0.0724 | +| entropy_loss | -7.19 | +| explained_variance | -0.161 | +| learning_rate | 4.75e-05 | +| loss | -0.0368 | +| n_updates | 36300 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000146 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1420 | +| iterations | 5122 | +| time_elapsed | 7385 | +| total_timesteps | 10489856 | +| train/ | | +| approx_kl | 0.013997201 | +| clip_fraction | 0.31 | +| clip_range | 0.0724 | +| entropy_loss | -6.45 | +| explained_variance | 0.598 | +| learning_rate | 4.75e-05 | +| loss | -0.0256 | +| n_updates | 36304 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000185 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1420 | +| iterations | 5123 | +| time_elapsed | 7387 | +| total_timesteps | 10491904 | +| train/ | | +| approx_kl | 0.014627099 | +| clip_fraction | 0.308 | +| clip_range | 0.0724 | +| entropy_loss | -6.94 | +| explained_variance | 0.232 | +| learning_rate | 4.75e-05 | +| loss | -0.0353 | +| n_updates | 36308 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000185 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1420 | +| iterations | 5124 | +| time_elapsed | 7388 | +| total_timesteps | 10493952 | +| train/ | | +| approx_kl | 0.012399773 | +| clip_fraction | 0.314 | +| clip_range | 0.0724 | +| entropy_loss | -7.02 | +| explained_variance | 0.51 | +| learning_rate | 4.75e-05 | +| loss | -0.0319 | +| n_updates | 36312 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000132 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1420 | +| iterations | 5125 | +| time_elapsed | 7390 | +| total_timesteps | 10496000 | +| train/ | | +| approx_kl | 0.011433581 | +| clip_fraction | 0.315 | +| clip_range | 0.0724 | +| entropy_loss | -7.37 | +| explained_variance | -0.0539 | +| learning_rate | 4.75e-05 | +| loss | -0.0372 | +| n_updates | 36316 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000112 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1420 | +| iterations | 5126 | +| time_elapsed | 7391 | +| total_timesteps | 10498048 | +| train/ | | +| approx_kl | 0.010652542 | +| clip_fraction | 0.31 | +| clip_range | 0.0724 | +| entropy_loss | -6.95 | +| explained_variance | 0.508 | +| learning_rate | 4.75e-05 | +| loss | -0.0272 | +| n_updates | 36320 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000142 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1420 | +| iterations | 5127 | +| time_elapsed | 7393 | +| total_timesteps | 10500096 | +| train/ | | +| approx_kl | 0.01297264 | +| clip_fraction | 0.331 | +| clip_range | 0.0724 | +| entropy_loss | -7.13 | +| explained_variance | 0.517 | +| learning_rate | 4.75e-05 | +| loss | -0.0354 | +| n_updates | 36324 | +| policy_gradient_loss | -0.0207 | +| value_loss | 6.79e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1420 | +| iterations | 5128 | +| time_elapsed | 7394 | +| total_timesteps | 10502144 | +| train/ | | +| approx_kl | 0.012081976 | +| clip_fraction | 0.337 | +| clip_range | 0.0724 | +| entropy_loss | -7.32 | +| explained_variance | -0.169 | +| learning_rate | 4.75e-05 | +| loss | -0.0295 | +| n_updates | 36328 | +| policy_gradient_loss | -0.0202 | +| value_loss | 8.88e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1420 | +| iterations | 5129 | +| time_elapsed | 7396 | +| total_timesteps | 10504192 | +| train/ | | +| approx_kl | 0.011643158 | +| clip_fraction | 0.302 | +| clip_range | 0.0724 | +| entropy_loss | -6.41 | +| explained_variance | 0.71 | +| learning_rate | 4.75e-05 | +| loss | -0.0282 | +| n_updates | 36332 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000125 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1420 | +| iterations | 5130 | +| time_elapsed | 7397 | +| total_timesteps | 10506240 | +| train/ | | +| approx_kl | 0.012293433 | +| clip_fraction | 0.318 | +| clip_range | 0.0724 | +| entropy_loss | -7.32 | +| explained_variance | -0.0833 | +| learning_rate | 4.75e-05 | +| loss | -0.0346 | +| n_updates | 36336 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000103 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1420 | +| iterations | 5131 | +| time_elapsed | 7399 | +| total_timesteps | 10508288 | +| train/ | | +| approx_kl | 0.01309034 | +| clip_fraction | 0.349 | +| clip_range | 0.0724 | +| entropy_loss | -7.31 | +| explained_variance | -0.119 | +| learning_rate | 4.75e-05 | +| loss | -0.0334 | +| n_updates | 36340 | +| policy_gradient_loss | -0.0222 | +| value_loss | 0.000108 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1420 | +| iterations | 5132 | +| time_elapsed | 7400 | +| total_timesteps | 10510336 | +| train/ | | +| approx_kl | 0.013099806 | +| clip_fraction | 0.32 | +| clip_range | 0.0724 | +| entropy_loss | -7.34 | +| explained_variance | -0.146 | +| learning_rate | 4.75e-05 | +| loss | -0.0347 | +| n_updates | 36344 | +| policy_gradient_loss | -0.0197 | +| value_loss | 7.38e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1420 | +| iterations | 5133 | +| time_elapsed | 7401 | +| total_timesteps | 10512384 | +| train/ | | +| approx_kl | 0.010854166 | +| clip_fraction | 0.31 | +| clip_range | 0.0724 | +| entropy_loss | -7.25 | +| explained_variance | 0.248 | +| learning_rate | 4.75e-05 | +| loss | -0.0291 | +| n_updates | 36348 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000193 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1420 | +| iterations | 5134 | +| time_elapsed | 7403 | +| total_timesteps | 10514432 | +| train/ | | +| approx_kl | 0.009280264 | +| clip_fraction | 0.3 | +| clip_range | 0.0724 | +| entropy_loss | -7.12 | +| explained_variance | 0.2 | +| learning_rate | 4.75e-05 | +| loss | -0.0334 | +| n_updates | 36352 | +| policy_gradient_loss | -0.0184 | +| value_loss | 7.82e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1420 | +| iterations | 5135 | +| time_elapsed | 7404 | +| total_timesteps | 10516480 | +| train/ | | +| approx_kl | 0.009056144 | +| clip_fraction | 0.291 | +| clip_range | 0.0724 | +| entropy_loss | -6.93 | +| explained_variance | 0.477 | +| learning_rate | 4.75e-05 | +| loss | -0.0222 | +| n_updates | 36356 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000123 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1420 | +| iterations | 5136 | +| time_elapsed | 7406 | +| total_timesteps | 10518528 | +| train/ | | +| approx_kl | 0.010693101 | +| clip_fraction | 0.296 | +| clip_range | 0.0724 | +| entropy_loss | -6.71 | +| explained_variance | 0.308 | +| learning_rate | 4.75e-05 | +| loss | -0.0288 | +| n_updates | 36360 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.0003 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1420 | +| iterations | 5137 | +| time_elapsed | 7407 | +| total_timesteps | 10520576 | +| train/ | | +| approx_kl | 0.012005414 | +| clip_fraction | 0.33 | +| clip_range | 0.0724 | +| entropy_loss | -6.27 | +| explained_variance | 0.628 | +| learning_rate | 4.75e-05 | +| loss | -0.0334 | +| n_updates | 36364 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000151 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1420 | +| iterations | 5138 | +| time_elapsed | 7409 | +| total_timesteps | 10522624 | +| train/ | | +| approx_kl | 0.011582976 | +| clip_fraction | 0.325 | +| clip_range | 0.0724 | +| entropy_loss | -7.37 | +| explained_variance | -0.0992 | +| learning_rate | 4.75e-05 | +| loss | -0.0277 | +| n_updates | 36368 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000243 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1420 | +| iterations | 5139 | +| time_elapsed | 7410 | +| total_timesteps | 10524672 | +| train/ | | +| approx_kl | 0.012606393 | +| clip_fraction | 0.314 | +| clip_range | 0.0724 | +| entropy_loss | -7.03 | +| explained_variance | 0.32 | +| learning_rate | 4.75e-05 | +| loss | -0.0312 | +| n_updates | 36372 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000174 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1420 | +| iterations | 5140 | +| time_elapsed | 7411 | +| total_timesteps | 10526720 | +| train/ | | +| approx_kl | 0.011921117 | +| clip_fraction | 0.323 | +| clip_range | 0.0724 | +| entropy_loss | -7.11 | +| explained_variance | 0.00904 | +| learning_rate | 4.75e-05 | +| loss | -0.0324 | +| n_updates | 36376 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000168 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1420 | +| iterations | 5141 | +| time_elapsed | 7413 | +| total_timesteps | 10528768 | +| train/ | | +| approx_kl | 0.012436386 | +| clip_fraction | 0.356 | +| clip_range | 0.0724 | +| entropy_loss | -7.33 | +| explained_variance | -0.224 | +| learning_rate | 4.75e-05 | +| loss | -0.0326 | +| n_updates | 36380 | +| policy_gradient_loss | -0.022 | +| value_loss | 9.12e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1420 | +| iterations | 5142 | +| time_elapsed | 7414 | +| total_timesteps | 10530816 | +| train/ | | +| approx_kl | 0.012169618 | +| clip_fraction | 0.317 | +| clip_range | 0.0724 | +| entropy_loss | -7.09 | +| explained_variance | 0.323 | +| learning_rate | 4.75e-05 | +| loss | -0.0295 | +| n_updates | 36384 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000112 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1420 | +| iterations | 5143 | +| time_elapsed | 7416 | +| total_timesteps | 10532864 | +| train/ | | +| approx_kl | 0.012092102 | +| clip_fraction | 0.331 | +| clip_range | 0.0724 | +| entropy_loss | -7.03 | +| explained_variance | 0.303 | +| learning_rate | 4.75e-05 | +| loss | -0.0319 | +| n_updates | 36388 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1420 | +| iterations | 5144 | +| time_elapsed | 7417 | +| total_timesteps | 10534912 | +| train/ | | +| approx_kl | 0.010895314 | +| clip_fraction | 0.3 | +| clip_range | 0.0724 | +| entropy_loss | -7.15 | +| explained_variance | 0.106 | +| learning_rate | 4.75e-05 | +| loss | -0.0245 | +| n_updates | 36392 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000226 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1420 | +| iterations | 5145 | +| time_elapsed | 7418 | +| total_timesteps | 10536960 | +| train/ | | +| approx_kl | 0.012571588 | +| clip_fraction | 0.335 | +| clip_range | 0.0724 | +| entropy_loss | -7.03 | +| explained_variance | 0.348 | +| learning_rate | 4.75e-05 | +| loss | -0.0334 | +| n_updates | 36396 | +| policy_gradient_loss | -0.021 | +| value_loss | 8.3e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1420 | +| iterations | 5146 | +| time_elapsed | 7420 | +| total_timesteps | 10539008 | +| train/ | | +| approx_kl | 0.009996263 | +| clip_fraction | 0.324 | +| clip_range | 0.0724 | +| entropy_loss | -7.4 | +| explained_variance | -0.131 | +| learning_rate | 4.75e-05 | +| loss | -0.0326 | +| n_updates | 36400 | +| policy_gradient_loss | -0.02 | +| value_loss | 8.5e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1420 | +| iterations | 5147 | +| time_elapsed | 7421 | +| total_timesteps | 10541056 | +| train/ | | +| approx_kl | 0.009833044 | +| clip_fraction | 0.289 | +| clip_range | 0.0724 | +| entropy_loss | -6.5 | +| explained_variance | 0.67 | +| learning_rate | 4.75e-05 | +| loss | -0.026 | +| n_updates | 36404 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000135 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1420 | +| iterations | 5148 | +| time_elapsed | 7423 | +| total_timesteps | 10543104 | +| train/ | | +| approx_kl | 0.010377253 | +| clip_fraction | 0.3 | +| clip_range | 0.0724 | +| entropy_loss | -6.53 | +| explained_variance | 0.512 | +| learning_rate | 4.75e-05 | +| loss | -0.0229 | +| n_updates | 36408 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000268 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1420 | +| iterations | 5149 | +| time_elapsed | 7424 | +| total_timesteps | 10545152 | +| train/ | | +| approx_kl | 0.011565304 | +| clip_fraction | 0.333 | +| clip_range | 0.0724 | +| entropy_loss | -6.9 | +| explained_variance | 0.521 | +| learning_rate | 4.75e-05 | +| loss | -0.0322 | +| n_updates | 36412 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000102 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1420 | +| iterations | 5150 | +| time_elapsed | 7426 | +| total_timesteps | 10547200 | +| train/ | | +| approx_kl | 0.012336867 | +| clip_fraction | 0.34 | +| clip_range | 0.0724 | +| entropy_loss | -7.17 | +| explained_variance | 0.155 | +| learning_rate | 4.75e-05 | +| loss | -0.0305 | +| n_updates | 36416 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.0001 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1420 | +| iterations | 5151 | +| time_elapsed | 7427 | +| total_timesteps | 10549248 | +| train/ | | +| approx_kl | 0.011189241 | +| clip_fraction | 0.309 | +| clip_range | 0.0724 | +| entropy_loss | -7.44 | +| explained_variance | -0.0442 | +| learning_rate | 4.75e-05 | +| loss | -0.0348 | +| n_updates | 36420 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000199 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1420 | +| iterations | 5152 | +| time_elapsed | 7429 | +| total_timesteps | 10551296 | +| train/ | | +| approx_kl | 0.009927646 | +| clip_fraction | 0.31 | +| clip_range | 0.0724 | +| entropy_loss | -7.18 | +| explained_variance | 0.206 | +| learning_rate | 4.75e-05 | +| loss | -0.0338 | +| n_updates | 36424 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000173 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1420 | +| iterations | 5153 | +| time_elapsed | 7430 | +| total_timesteps | 10553344 | +| train/ | | +| approx_kl | 0.010963396 | +| clip_fraction | 0.318 | +| clip_range | 0.0724 | +| entropy_loss | -7.48 | +| explained_variance | -0.108 | +| learning_rate | 4.75e-05 | +| loss | -0.0358 | +| n_updates | 36428 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000106 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1420 | +| iterations | 5154 | +| time_elapsed | 7431 | +| total_timesteps | 10555392 | +| train/ | | +| approx_kl | 0.011042055 | +| clip_fraction | 0.321 | +| clip_range | 0.0724 | +| entropy_loss | -7.04 | +| explained_variance | 0.345 | +| learning_rate | 4.75e-05 | +| loss | -0.0289 | +| n_updates | 36432 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000199 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1420 | +| iterations | 5155 | +| time_elapsed | 7433 | +| total_timesteps | 10557440 | +| train/ | | +| approx_kl | 0.010786683 | +| clip_fraction | 0.312 | +| clip_range | 0.0724 | +| entropy_loss | -6.59 | +| explained_variance | 0.289 | +| learning_rate | 4.75e-05 | +| loss | -0.026 | +| n_updates | 36436 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000289 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1420 | +| iterations | 5156 | +| time_elapsed | 7434 | +| total_timesteps | 10559488 | +| train/ | | +| approx_kl | 0.0107451305 | +| clip_fraction | 0.354 | +| clip_range | 0.0724 | +| entropy_loss | -6.83 | +| explained_variance | 0.297 | +| learning_rate | 4.75e-05 | +| loss | -0.0293 | +| n_updates | 36440 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000181 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1420 | +| iterations | 5157 | +| time_elapsed | 7436 | +| total_timesteps | 10561536 | +| train/ | | +| approx_kl | 0.011287508 | +| clip_fraction | 0.352 | +| clip_range | 0.0724 | +| entropy_loss | -7.49 | +| explained_variance | -0.195 | +| learning_rate | 4.75e-05 | +| loss | -0.0386 | +| n_updates | 36444 | +| policy_gradient_loss | -0.0256 | +| value_loss | 0.00011 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1420 | +| iterations | 5158 | +| time_elapsed | 7437 | +| total_timesteps | 10563584 | +| train/ | | +| approx_kl | 0.009839841 | +| clip_fraction | 0.297 | +| clip_range | 0.0724 | +| entropy_loss | -7.08 | +| explained_variance | 0.358 | +| learning_rate | 4.75e-05 | +| loss | -0.0291 | +| n_updates | 36448 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000258 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.387 | +| time/ | | +| fps | 1420 | +| iterations | 5159 | +| time_elapsed | 7439 | +| total_timesteps | 10565632 | +| train/ | | +| approx_kl | 0.010087594 | +| clip_fraction | 0.314 | +| clip_range | 0.0724 | +| entropy_loss | -7.35 | +| explained_variance | 0.00397 | +| learning_rate | 4.75e-05 | +| loss | -0.0284 | +| n_updates | 36452 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000126 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.386 | +| time/ | | +| fps | 1420 | +| iterations | 5160 | +| time_elapsed | 7440 | +| total_timesteps | 10567680 | +| train/ | | +| approx_kl | 0.010822941 | +| clip_fraction | 0.31 | +| clip_range | 0.0724 | +| entropy_loss | -7.08 | +| explained_variance | 0.299 | +| learning_rate | 4.75e-05 | +| loss | -0.0356 | +| n_updates | 36456 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000107 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1420 | +| iterations | 5161 | +| time_elapsed | 7442 | +| total_timesteps | 10569728 | +| train/ | | +| approx_kl | 0.010277499 | +| clip_fraction | 0.313 | +| clip_range | 0.0724 | +| entropy_loss | -7.26 | +| explained_variance | 0.38 | +| learning_rate | 4.75e-05 | +| loss | -0.0359 | +| n_updates | 36460 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000104 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1420 | +| iterations | 5162 | +| time_elapsed | 7443 | +| total_timesteps | 10571776 | +| train/ | | +| approx_kl | 0.010202965 | +| clip_fraction | 0.31 | +| clip_range | 0.0724 | +| entropy_loss | -6.75 | +| explained_variance | 0.555 | +| learning_rate | 4.75e-05 | +| loss | -0.0305 | +| n_updates | 36464 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000119 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1420 | +| iterations | 5163 | +| time_elapsed | 7444 | +| total_timesteps | 10573824 | +| train/ | | +| approx_kl | 0.010635035 | +| clip_fraction | 0.29 | +| clip_range | 0.0724 | +| entropy_loss | -7.32 | +| explained_variance | 0.342 | +| learning_rate | 4.75e-05 | +| loss | -0.0336 | +| n_updates | 36468 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000129 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1420 | +| iterations | 5164 | +| time_elapsed | 7446 | +| total_timesteps | 10575872 | +| train/ | | +| approx_kl | 0.011547905 | +| clip_fraction | 0.296 | +| clip_range | 0.0724 | +| entropy_loss | -6.75 | +| explained_variance | 0.427 | +| learning_rate | 4.75e-05 | +| loss | -0.0278 | +| n_updates | 36472 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000189 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.388 | +| time/ | | +| fps | 1420 | +| iterations | 5165 | +| time_elapsed | 7447 | +| total_timesteps | 10577920 | +| train/ | | +| approx_kl | 0.013301279 | +| clip_fraction | 0.357 | +| clip_range | 0.0724 | +| entropy_loss | -7.21 | +| explained_variance | -0.128 | +| learning_rate | 4.75e-05 | +| loss | -0.0337 | +| n_updates | 36476 | +| policy_gradient_loss | -0.0231 | +| value_loss | 7.01e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1420 | +| iterations | 5166 | +| time_elapsed | 7449 | +| total_timesteps | 10579968 | +| train/ | | +| approx_kl | 0.009193392 | +| clip_fraction | 0.308 | +| clip_range | 0.0724 | +| entropy_loss | -7.02 | +| explained_variance | 0.335 | +| learning_rate | 4.75e-05 | +| loss | -0.0283 | +| n_updates | 36480 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000193 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.43e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1420 | +| iterations | 5167 | +| time_elapsed | 7450 | +| total_timesteps | 10582016 | +| train/ | | +| approx_kl | 0.011694507 | +| clip_fraction | 0.348 | +| clip_range | 0.0724 | +| entropy_loss | -6.88 | +| explained_variance | 0.635 | +| learning_rate | 4.75e-05 | +| loss | -0.0434 | +| n_updates | 36484 | +| policy_gradient_loss | -0.0237 | +| value_loss | 6.3e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.43e+03 | +| ep_rew_mean | 0.385 | +| time/ | | +| fps | 1420 | +| iterations | 5168 | +| time_elapsed | 7452 | +| total_timesteps | 10584064 | +| train/ | | +| approx_kl | 0.010229053 | +| clip_fraction | 0.283 | +| clip_range | 0.0724 | +| entropy_loss | -6.78 | +| explained_variance | 0.285 | +| learning_rate | 4.75e-05 | +| loss | -0.0297 | +| n_updates | 36488 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000259 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.43e+03 | +| ep_rew_mean | 0.398 | +| time/ | | +| fps | 1420 | +| iterations | 5169 | +| time_elapsed | 7453 | +| total_timesteps | 10586112 | +| train/ | | +| approx_kl | 0.011239174 | +| clip_fraction | 0.298 | +| clip_range | 0.0724 | +| entropy_loss | -7.05 | +| explained_variance | 0.283 | +| learning_rate | 4.75e-05 | +| loss | -0.0294 | +| n_updates | 36492 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000214 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.43e+03 | +| ep_rew_mean | 0.398 | +| time/ | | +| fps | 1420 | +| iterations | 5170 | +| time_elapsed | 7454 | +| total_timesteps | 10588160 | +| train/ | | +| approx_kl | 0.011467097 | +| clip_fraction | 0.31 | +| clip_range | 0.0724 | +| entropy_loss | -6.54 | +| explained_variance | 0.361 | +| learning_rate | 4.75e-05 | +| loss | -0.0258 | +| n_updates | 36496 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000397 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.43e+03 | +| ep_rew_mean | 0.398 | +| time/ | | +| fps | 1420 | +| iterations | 5171 | +| time_elapsed | 7456 | +| total_timesteps | 10590208 | +| train/ | | +| approx_kl | 0.012341624 | +| clip_fraction | 0.373 | +| clip_range | 0.0724 | +| entropy_loss | -7.11 | +| explained_variance | -0.129 | +| learning_rate | 4.75e-05 | +| loss | -0.0448 | +| n_updates | 36500 | +| policy_gradient_loss | -0.0274 | +| value_loss | 9.93e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.397 | +| time/ | | +| fps | 1420 | +| iterations | 5172 | +| time_elapsed | 7457 | +| total_timesteps | 10592256 | +| train/ | | +| approx_kl | 0.010139759 | +| clip_fraction | 0.322 | +| clip_range | 0.0724 | +| entropy_loss | -7.45 | +| explained_variance | -0.513 | +| learning_rate | 4.75e-05 | +| loss | -0.035 | +| n_updates | 36504 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.00016 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.397 | +| time/ | | +| fps | 1420 | +| iterations | 5173 | +| time_elapsed | 7459 | +| total_timesteps | 10594304 | +| train/ | | +| approx_kl | 0.011293982 | +| clip_fraction | 0.345 | +| clip_range | 0.0724 | +| entropy_loss | -7.35 | +| explained_variance | -0.245 | +| learning_rate | 4.75e-05 | +| loss | -0.0402 | +| n_updates | 36508 | +| policy_gradient_loss | -0.0233 | +| value_loss | 8.49e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.392 | +| time/ | | +| fps | 1420 | +| iterations | 5174 | +| time_elapsed | 7460 | +| total_timesteps | 10596352 | +| train/ | | +| approx_kl | 0.011197813 | +| clip_fraction | 0.308 | +| clip_range | 0.0724 | +| entropy_loss | -7.32 | +| explained_variance | 0.319 | +| learning_rate | 4.75e-05 | +| loss | -0.0343 | +| n_updates | 36512 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000101 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.39 | +| time/ | | +| fps | 1420 | +| iterations | 5175 | +| time_elapsed | 7462 | +| total_timesteps | 10598400 | +| train/ | | +| approx_kl | 0.011479012 | +| clip_fraction | 0.347 | +| clip_range | 0.0724 | +| entropy_loss | -6.95 | +| explained_variance | 0.295 | +| learning_rate | 4.75e-05 | +| loss | -0.0289 | +| n_updates | 36516 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000154 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.385 | +| time/ | | +| fps | 1420 | +| iterations | 5176 | +| time_elapsed | 7463 | +| total_timesteps | 10600448 | +| train/ | | +| approx_kl | 0.010787036 | +| clip_fraction | 0.326 | +| clip_range | 0.0724 | +| entropy_loss | -6.83 | +| explained_variance | 0.324 | +| learning_rate | 4.75e-05 | +| loss | -0.0327 | +| n_updates | 36520 | +| policy_gradient_loss | -0.0207 | +| value_loss | 8.65e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1420 | +| iterations | 5177 | +| time_elapsed | 7465 | +| total_timesteps | 10602496 | +| train/ | | +| approx_kl | 0.010207966 | +| clip_fraction | 0.308 | +| clip_range | 0.0723 | +| entropy_loss | -6.9 | +| explained_variance | 0.364 | +| learning_rate | 4.75e-05 | +| loss | -0.0269 | +| n_updates | 36524 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000205 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1420 | +| iterations | 5178 | +| time_elapsed | 7466 | +| total_timesteps | 10604544 | +| train/ | | +| approx_kl | 0.008522192 | +| clip_fraction | 0.294 | +| clip_range | 0.0723 | +| entropy_loss | -6.5 | +| explained_variance | 0.252 | +| learning_rate | 4.75e-05 | +| loss | -0.0232 | +| n_updates | 36528 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.000208 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1420 | +| iterations | 5179 | +| time_elapsed | 7467 | +| total_timesteps | 10606592 | +| train/ | | +| approx_kl | 0.013478184 | +| clip_fraction | 0.372 | +| clip_range | 0.0723 | +| entropy_loss | -6.74 | +| explained_variance | 0.625 | +| learning_rate | 4.75e-05 | +| loss | -0.0378 | +| n_updates | 36532 | +| policy_gradient_loss | -0.0211 | +| value_loss | 8.19e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1420 | +| iterations | 5180 | +| time_elapsed | 7469 | +| total_timesteps | 10608640 | +| train/ | | +| approx_kl | 0.012096288 | +| clip_fraction | 0.326 | +| clip_range | 0.0723 | +| entropy_loss | -7.42 | +| explained_variance | -0.0739 | +| learning_rate | 4.75e-05 | +| loss | -0.035 | +| n_updates | 36536 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000147 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1420 | +| iterations | 5181 | +| time_elapsed | 7470 | +| total_timesteps | 10610688 | +| train/ | | +| approx_kl | 0.0112005705 | +| clip_fraction | 0.332 | +| clip_range | 0.0723 | +| entropy_loss | -7.26 | +| explained_variance | 0.386 | +| learning_rate | 4.75e-05 | +| loss | -0.0286 | +| n_updates | 36540 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000103 | +------------------------------------------ +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1420 | +| iterations | 5182 | +| time_elapsed | 7472 | +| total_timesteps | 10612736 | +| train/ | | +| approx_kl | 0.0091777 | +| clip_fraction | 0.297 | +| clip_range | 0.0723 | +| entropy_loss | -7.23 | +| explained_variance | 0.313 | +| learning_rate | 4.75e-05 | +| loss | -0.0312 | +| n_updates | 36544 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000173 | +--------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1420 | +| iterations | 5183 | +| time_elapsed | 7473 | +| total_timesteps | 10614784 | +| train/ | | +| approx_kl | 0.01095169 | +| clip_fraction | 0.303 | +| clip_range | 0.0723 | +| entropy_loss | -6.97 | +| explained_variance | 0.397 | +| learning_rate | 4.75e-05 | +| loss | -0.0263 | +| n_updates | 36548 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000147 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1420 | +| iterations | 5184 | +| time_elapsed | 7475 | +| total_timesteps | 10616832 | +| train/ | | +| approx_kl | 0.012219128 | +| clip_fraction | 0.274 | +| clip_range | 0.0723 | +| entropy_loss | -7.2 | +| explained_variance | 0.0208 | +| learning_rate | 4.75e-05 | +| loss | -0.0279 | +| n_updates | 36552 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000224 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1420 | +| iterations | 5185 | +| time_elapsed | 7476 | +| total_timesteps | 10618880 | +| train/ | | +| approx_kl | 0.009650355 | +| clip_fraction | 0.289 | +| clip_range | 0.0723 | +| entropy_loss | -6.85 | +| explained_variance | 0.32 | +| learning_rate | 4.75e-05 | +| loss | -0.0262 | +| n_updates | 36556 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000272 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1420 | +| iterations | 5186 | +| time_elapsed | 7477 | +| total_timesteps | 10620928 | +| train/ | | +| approx_kl | 0.010852898 | +| clip_fraction | 0.322 | +| clip_range | 0.0723 | +| entropy_loss | -7.24 | +| explained_variance | -0.205 | +| learning_rate | 4.75e-05 | +| loss | -0.0381 | +| n_updates | 36560 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000135 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1420 | +| iterations | 5187 | +| time_elapsed | 7479 | +| total_timesteps | 10622976 | +| train/ | | +| approx_kl | 0.011813246 | +| clip_fraction | 0.324 | +| clip_range | 0.0723 | +| entropy_loss | -7.45 | +| explained_variance | -0.132 | +| learning_rate | 4.75e-05 | +| loss | -0.0314 | +| n_updates | 36564 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.00016 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1420 | +| iterations | 5188 | +| time_elapsed | 7480 | +| total_timesteps | 10625024 | +| train/ | | +| approx_kl | 0.012402251 | +| clip_fraction | 0.291 | +| clip_range | 0.0723 | +| entropy_loss | -6.81 | +| explained_variance | 0.397 | +| learning_rate | 4.75e-05 | +| loss | -0.0323 | +| n_updates | 36568 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000179 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1420 | +| iterations | 5189 | +| time_elapsed | 7482 | +| total_timesteps | 10627072 | +| train/ | | +| approx_kl | 0.012563681 | +| clip_fraction | 0.329 | +| clip_range | 0.0723 | +| entropy_loss | -7.04 | +| explained_variance | 0.288 | +| learning_rate | 4.75e-05 | +| loss | -0.0299 | +| n_updates | 36572 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000128 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1420 | +| iterations | 5190 | +| time_elapsed | 7483 | +| total_timesteps | 10629120 | +| train/ | | +| approx_kl | 0.011137001 | +| clip_fraction | 0.29 | +| clip_range | 0.0723 | +| entropy_loss | -7.28 | +| explained_variance | 0.223 | +| learning_rate | 4.75e-05 | +| loss | -0.0335 | +| n_updates | 36576 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000205 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1420 | +| iterations | 5191 | +| time_elapsed | 7484 | +| total_timesteps | 10631168 | +| train/ | | +| approx_kl | 0.0107850805 | +| clip_fraction | 0.308 | +| clip_range | 0.0723 | +| entropy_loss | -6.85 | +| explained_variance | 0.402 | +| learning_rate | 4.75e-05 | +| loss | -0.0269 | +| n_updates | 36580 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000199 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1420 | +| iterations | 5192 | +| time_elapsed | 7486 | +| total_timesteps | 10633216 | +| train/ | | +| approx_kl | 0.010895908 | +| clip_fraction | 0.318 | +| clip_range | 0.0723 | +| entropy_loss | -7.25 | +| explained_variance | 0.378 | +| learning_rate | 4.75e-05 | +| loss | -0.0316 | +| n_updates | 36584 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000129 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1420 | +| iterations | 5193 | +| time_elapsed | 7487 | +| total_timesteps | 10635264 | +| train/ | | +| approx_kl | 0.008900423 | +| clip_fraction | 0.313 | +| clip_range | 0.0723 | +| entropy_loss | -7.29 | +| explained_variance | -0.142 | +| learning_rate | 4.75e-05 | +| loss | -0.0314 | +| n_updates | 36588 | +| policy_gradient_loss | -0.0204 | +| value_loss | 8.41e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1420 | +| iterations | 5194 | +| time_elapsed | 7489 | +| total_timesteps | 10637312 | +| train/ | | +| approx_kl | 0.009259943 | +| clip_fraction | 0.285 | +| clip_range | 0.0723 | +| entropy_loss | -6.76 | +| explained_variance | 0.414 | +| learning_rate | 4.75e-05 | +| loss | -0.0223 | +| n_updates | 36592 | +| policy_gradient_loss | -0.0143 | +| value_loss | 0.000312 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1420 | +| iterations | 5195 | +| time_elapsed | 7490 | +| total_timesteps | 10639360 | +| train/ | | +| approx_kl | 0.012269268 | +| clip_fraction | 0.353 | +| clip_range | 0.0723 | +| entropy_loss | -6.3 | +| explained_variance | 0.851 | +| learning_rate | 4.75e-05 | +| loss | -0.0434 | +| n_updates | 36596 | +| policy_gradient_loss | -0.0256 | +| value_loss | 5.72e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1420 | +| iterations | 5196 | +| time_elapsed | 7491 | +| total_timesteps | 10641408 | +| train/ | | +| approx_kl | 0.009650952 | +| clip_fraction | 0.318 | +| clip_range | 0.0723 | +| entropy_loss | -7.22 | +| explained_variance | 0.329 | +| learning_rate | 4.75e-05 | +| loss | -0.0358 | +| n_updates | 36600 | +| policy_gradient_loss | -0.0212 | +| value_loss | 9.86e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1420 | +| iterations | 5197 | +| time_elapsed | 7493 | +| total_timesteps | 10643456 | +| train/ | | +| approx_kl | 0.012551877 | +| clip_fraction | 0.345 | +| clip_range | 0.0723 | +| entropy_loss | -7.19 | +| explained_variance | 0.0933 | +| learning_rate | 4.75e-05 | +| loss | -0.035 | +| n_updates | 36604 | +| policy_gradient_loss | -0.0208 | +| value_loss | 7.24e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1420 | +| iterations | 5198 | +| time_elapsed | 7494 | +| total_timesteps | 10645504 | +| train/ | | +| approx_kl | 0.011893516 | +| clip_fraction | 0.322 | +| clip_range | 0.0723 | +| entropy_loss | -6.58 | +| explained_variance | 0.542 | +| learning_rate | 4.75e-05 | +| loss | -0.0342 | +| n_updates | 36608 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000132 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1420 | +| iterations | 5199 | +| time_elapsed | 7496 | +| total_timesteps | 10647552 | +| train/ | | +| approx_kl | 0.0111676855 | +| clip_fraction | 0.338 | +| clip_range | 0.0723 | +| entropy_loss | -7.12 | +| explained_variance | 0.562 | +| learning_rate | 4.75e-05 | +| loss | -0.0368 | +| n_updates | 36612 | +| policy_gradient_loss | -0.0218 | +| value_loss | 5.54e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1420 | +| iterations | 5200 | +| time_elapsed | 7497 | +| total_timesteps | 10649600 | +| train/ | | +| approx_kl | 0.012229568 | +| clip_fraction | 0.308 | +| clip_range | 0.0723 | +| entropy_loss | -7.08 | +| explained_variance | 0.21 | +| learning_rate | 4.75e-05 | +| loss | -0.0251 | +| n_updates | 36616 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000315 | +----------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1420 | +| iterations | 5201 | +| time_elapsed | 7499 | +| total_timesteps | 10651648 | +| train/ | | +| approx_kl | 0.013678 | +| clip_fraction | 0.354 | +| clip_range | 0.0723 | +| entropy_loss | -6.71 | +| explained_variance | 0.524 | +| learning_rate | 4.75e-05 | +| loss | -0.0295 | +| n_updates | 36620 | +| policy_gradient_loss | -0.0206 | +| value_loss | 8.6e-05 | +-------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1420 | +| iterations | 5202 | +| time_elapsed | 7500 | +| total_timesteps | 10653696 | +| train/ | | +| approx_kl | 0.012001683 | +| clip_fraction | 0.353 | +| clip_range | 0.0723 | +| entropy_loss | -7.03 | +| explained_variance | 0.4 | +| learning_rate | 4.75e-05 | +| loss | -0.0297 | +| n_updates | 36624 | +| policy_gradient_loss | -0.0214 | +| value_loss | 7.88e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1420 | +| iterations | 5203 | +| time_elapsed | 7502 | +| total_timesteps | 10655744 | +| train/ | | +| approx_kl | 0.008976166 | +| clip_fraction | 0.304 | +| clip_range | 0.0723 | +| entropy_loss | -7.36 | +| explained_variance | -0.00961 | +| learning_rate | 4.75e-05 | +| loss | -0.0255 | +| n_updates | 36628 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000388 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1420 | +| iterations | 5204 | +| time_elapsed | 7503 | +| total_timesteps | 10657792 | +| train/ | | +| approx_kl | 0.010685675 | +| clip_fraction | 0.318 | +| clip_range | 0.0723 | +| entropy_loss | -6.99 | +| explained_variance | 0.296 | +| learning_rate | 4.75e-05 | +| loss | -0.0313 | +| n_updates | 36632 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000233 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1420 | +| iterations | 5205 | +| time_elapsed | 7505 | +| total_timesteps | 10659840 | +| train/ | | +| approx_kl | 0.010722782 | +| clip_fraction | 0.307 | +| clip_range | 0.0723 | +| entropy_loss | -6.63 | +| explained_variance | 0.445 | +| learning_rate | 4.75e-05 | +| loss | -0.023 | +| n_updates | 36636 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000253 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1420 | +| iterations | 5206 | +| time_elapsed | 7506 | +| total_timesteps | 10661888 | +| train/ | | +| approx_kl | 0.010646824 | +| clip_fraction | 0.324 | +| clip_range | 0.0723 | +| entropy_loss | -6.46 | +| explained_variance | 0.743 | +| learning_rate | 4.75e-05 | +| loss | -0.0295 | +| n_updates | 36640 | +| policy_gradient_loss | -0.0215 | +| value_loss | 9.4e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1420 | +| iterations | 5207 | +| time_elapsed | 7507 | +| total_timesteps | 10663936 | +| train/ | | +| approx_kl | 0.011000938 | +| clip_fraction | 0.309 | +| clip_range | 0.0723 | +| entropy_loss | -7.35 | +| explained_variance | -0.102 | +| learning_rate | 4.75e-05 | +| loss | -0.0303 | +| n_updates | 36644 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000181 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1420 | +| iterations | 5208 | +| time_elapsed | 7509 | +| total_timesteps | 10665984 | +| train/ | | +| approx_kl | 0.011164961 | +| clip_fraction | 0.328 | +| clip_range | 0.0723 | +| entropy_loss | -7.32 | +| explained_variance | -0.0221 | +| learning_rate | 4.75e-05 | +| loss | -0.0347 | +| n_updates | 36648 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000284 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1420 | +| iterations | 5209 | +| time_elapsed | 7510 | +| total_timesteps | 10668032 | +| train/ | | +| approx_kl | 0.011303057 | +| clip_fraction | 0.302 | +| clip_range | 0.0723 | +| entropy_loss | -6.85 | +| explained_variance | 0.294 | +| learning_rate | 4.75e-05 | +| loss | -0.0298 | +| n_updates | 36652 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000315 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1420 | +| iterations | 5210 | +| time_elapsed | 7512 | +| total_timesteps | 10670080 | +| train/ | | +| approx_kl | 0.011247728 | +| clip_fraction | 0.334 | +| clip_range | 0.0723 | +| entropy_loss | -7.36 | +| explained_variance | -0.142 | +| learning_rate | 4.75e-05 | +| loss | -0.0339 | +| n_updates | 36656 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000147 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1420 | +| iterations | 5211 | +| time_elapsed | 7513 | +| total_timesteps | 10672128 | +| train/ | | +| approx_kl | 0.01006374 | +| clip_fraction | 0.328 | +| clip_range | 0.0723 | +| entropy_loss | -7.04 | +| explained_variance | 0.458 | +| learning_rate | 4.75e-05 | +| loss | -0.032 | +| n_updates | 36660 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000156 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1420 | +| iterations | 5212 | +| time_elapsed | 7514 | +| total_timesteps | 10674176 | +| train/ | | +| approx_kl | 0.011424333 | +| clip_fraction | 0.296 | +| clip_range | 0.0723 | +| entropy_loss | -7.25 | +| explained_variance | -0.161 | +| learning_rate | 4.75e-05 | +| loss | -0.0296 | +| n_updates | 36664 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.00014 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1420 | +| iterations | 5213 | +| time_elapsed | 7516 | +| total_timesteps | 10676224 | +| train/ | | +| approx_kl | 0.012918903 | +| clip_fraction | 0.351 | +| clip_range | 0.0723 | +| entropy_loss | -7.21 | +| explained_variance | 0.238 | +| learning_rate | 4.75e-05 | +| loss | -0.0366 | +| n_updates | 36668 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000149 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1420 | +| iterations | 5214 | +| time_elapsed | 7517 | +| total_timesteps | 10678272 | +| train/ | | +| approx_kl | 0.011009265 | +| clip_fraction | 0.324 | +| clip_range | 0.0723 | +| entropy_loss | -6.92 | +| explained_variance | 0.387 | +| learning_rate | 4.75e-05 | +| loss | -0.0314 | +| n_updates | 36672 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000161 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1420 | +| iterations | 5215 | +| time_elapsed | 7519 | +| total_timesteps | 10680320 | +| train/ | | +| approx_kl | 0.010325157 | +| clip_fraction | 0.307 | +| clip_range | 0.0723 | +| entropy_loss | -7.23 | +| explained_variance | 0.293 | +| learning_rate | 4.75e-05 | +| loss | -0.028 | +| n_updates | 36676 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.00022 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1420 | +| iterations | 5216 | +| time_elapsed | 7520 | +| total_timesteps | 10682368 | +| train/ | | +| approx_kl | 0.011061391 | +| clip_fraction | 0.288 | +| clip_range | 0.0723 | +| entropy_loss | -6.7 | +| explained_variance | 0.344 | +| learning_rate | 4.75e-05 | +| loss | -0.0252 | +| n_updates | 36680 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000376 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.384 | +| time/ | | +| fps | 1420 | +| iterations | 5217 | +| time_elapsed | 7521 | +| total_timesteps | 10684416 | +| train/ | | +| approx_kl | 0.011467255 | +| clip_fraction | 0.369 | +| clip_range | 0.0723 | +| entropy_loss | -7.09 | +| explained_variance | 0.0155 | +| learning_rate | 4.75e-05 | +| loss | -0.0494 | +| n_updates | 36684 | +| policy_gradient_loss | -0.0251 | +| value_loss | 0.000116 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1420 | +| iterations | 5218 | +| time_elapsed | 7523 | +| total_timesteps | 10686464 | +| train/ | | +| approx_kl | 0.012167325 | +| clip_fraction | 0.338 | +| clip_range | 0.0723 | +| entropy_loss | -6.81 | +| explained_variance | 0.375 | +| learning_rate | 4.75e-05 | +| loss | -0.029 | +| n_updates | 36688 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000272 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1420 | +| iterations | 5219 | +| time_elapsed | 7524 | +| total_timesteps | 10688512 | +| train/ | | +| approx_kl | 0.011321641 | +| clip_fraction | 0.328 | +| clip_range | 0.0723 | +| entropy_loss | -6.6 | +| explained_variance | 0.458 | +| learning_rate | 4.75e-05 | +| loss | -0.028 | +| n_updates | 36692 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000148 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1420 | +| iterations | 5220 | +| time_elapsed | 7526 | +| total_timesteps | 10690560 | +| train/ | | +| approx_kl | 0.0115174595 | +| clip_fraction | 0.317 | +| clip_range | 0.0723 | +| entropy_loss | -7.05 | +| explained_variance | 0.27 | +| learning_rate | 4.75e-05 | +| loss | -0.0315 | +| n_updates | 36696 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000186 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1420 | +| iterations | 5221 | +| time_elapsed | 7527 | +| total_timesteps | 10692608 | +| train/ | | +| approx_kl | 0.012530918 | +| clip_fraction | 0.332 | +| clip_range | 0.0723 | +| entropy_loss | -7.42 | +| explained_variance | -0.213 | +| learning_rate | 4.75e-05 | +| loss | -0.0315 | +| n_updates | 36700 | +| policy_gradient_loss | -0.022 | +| value_loss | 8.91e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1420 | +| iterations | 5222 | +| time_elapsed | 7529 | +| total_timesteps | 10694656 | +| train/ | | +| approx_kl | 0.013417389 | +| clip_fraction | 0.354 | +| clip_range | 0.0723 | +| entropy_loss | -7.24 | +| explained_variance | 0.543 | +| learning_rate | 4.75e-05 | +| loss | -0.0402 | +| n_updates | 36704 | +| policy_gradient_loss | -0.0232 | +| value_loss | 7e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1420 | +| iterations | 5223 | +| time_elapsed | 7530 | +| total_timesteps | 10696704 | +| train/ | | +| approx_kl | 0.009774081 | +| clip_fraction | 0.291 | +| clip_range | 0.0723 | +| entropy_loss | -7.38 | +| explained_variance | -0.00168 | +| learning_rate | 4.75e-05 | +| loss | -0.0285 | +| n_updates | 36708 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000145 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1420 | +| iterations | 5224 | +| time_elapsed | 7531 | +| total_timesteps | 10698752 | +| train/ | | +| approx_kl | 0.012464333 | +| clip_fraction | 0.329 | +| clip_range | 0.0723 | +| entropy_loss | -7.36 | +| explained_variance | -0.175 | +| learning_rate | 4.75e-05 | +| loss | -0.0309 | +| n_updates | 36712 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000143 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1420 | +| iterations | 5225 | +| time_elapsed | 7533 | +| total_timesteps | 10700800 | +| train/ | | +| approx_kl | 0.0103411395 | +| clip_fraction | 0.293 | +| clip_range | 0.0723 | +| entropy_loss | -6.85 | +| explained_variance | 0.47 | +| learning_rate | 4.75e-05 | +| loss | -0.0277 | +| n_updates | 36716 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000185 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1420 | +| iterations | 5226 | +| time_elapsed | 7534 | +| total_timesteps | 10702848 | +| train/ | | +| approx_kl | 0.012501722 | +| clip_fraction | 0.336 | +| clip_range | 0.0723 | +| entropy_loss | -7.16 | +| explained_variance | 0.553 | +| learning_rate | 4.75e-05 | +| loss | -0.0329 | +| n_updates | 36720 | +| policy_gradient_loss | -0.0216 | +| value_loss | 5.29e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1420 | +| iterations | 5227 | +| time_elapsed | 7536 | +| total_timesteps | 10704896 | +| train/ | | +| approx_kl | 0.01275165 | +| clip_fraction | 0.304 | +| clip_range | 0.0723 | +| entropy_loss | -7.38 | +| explained_variance | -0.103 | +| learning_rate | 4.75e-05 | +| loss | -0.0305 | +| n_updates | 36724 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000108 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1420 | +| iterations | 5228 | +| time_elapsed | 7537 | +| total_timesteps | 10706944 | +| train/ | | +| approx_kl | 0.012409702 | +| clip_fraction | 0.33 | +| clip_range | 0.0723 | +| entropy_loss | -6.97 | +| explained_variance | 0.675 | +| learning_rate | 4.75e-05 | +| loss | -0.0341 | +| n_updates | 36728 | +| policy_gradient_loss | -0.0203 | +| value_loss | 6.76e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1420 | +| iterations | 5229 | +| time_elapsed | 7539 | +| total_timesteps | 10708992 | +| train/ | | +| approx_kl | 0.008766414 | +| clip_fraction | 0.312 | +| clip_range | 0.0723 | +| entropy_loss | -6.69 | +| explained_variance | 0.747 | +| learning_rate | 4.75e-05 | +| loss | -0.0357 | +| n_updates | 36732 | +| policy_gradient_loss | -0.018 | +| value_loss | 6.22e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1420 | +| iterations | 5230 | +| time_elapsed | 7540 | +| total_timesteps | 10711040 | +| train/ | | +| approx_kl | 0.009663318 | +| clip_fraction | 0.295 | +| clip_range | 0.0723 | +| entropy_loss | -6.29 | +| explained_variance | 0.437 | +| learning_rate | 4.75e-05 | +| loss | -0.0248 | +| n_updates | 36736 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000397 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1420 | +| iterations | 5231 | +| time_elapsed | 7542 | +| total_timesteps | 10713088 | +| train/ | | +| approx_kl | 0.0135142505 | +| clip_fraction | 0.337 | +| clip_range | 0.0723 | +| entropy_loss | -6.36 | +| explained_variance | 0.541 | +| learning_rate | 4.75e-05 | +| loss | -0.0401 | +| n_updates | 36740 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000152 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1420 | +| iterations | 5232 | +| time_elapsed | 7543 | +| total_timesteps | 10715136 | +| train/ | | +| approx_kl | 0.012140026 | +| clip_fraction | 0.356 | +| clip_range | 0.0723 | +| entropy_loss | -6.8 | +| explained_variance | 0.422 | +| learning_rate | 4.75e-05 | +| loss | -0.039 | +| n_updates | 36744 | +| policy_gradient_loss | -0.0238 | +| value_loss | 0.000126 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1420 | +| iterations | 5233 | +| time_elapsed | 7544 | +| total_timesteps | 10717184 | +| train/ | | +| approx_kl | 0.010358015 | +| clip_fraction | 0.307 | +| clip_range | 0.0723 | +| entropy_loss | -7.28 | +| explained_variance | -0.0443 | +| learning_rate | 4.75e-05 | +| loss | -0.0262 | +| n_updates | 36748 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000193 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1420 | +| iterations | 5234 | +| time_elapsed | 7546 | +| total_timesteps | 10719232 | +| train/ | | +| approx_kl | 0.009924402 | +| clip_fraction | 0.302 | +| clip_range | 0.0723 | +| entropy_loss | -7.49 | +| explained_variance | -0.0187 | +| learning_rate | 4.75e-05 | +| loss | -0.0325 | +| n_updates | 36752 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000173 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1420 | +| iterations | 5235 | +| time_elapsed | 7547 | +| total_timesteps | 10721280 | +| train/ | | +| approx_kl | 0.009987967 | +| clip_fraction | 0.31 | +| clip_range | 0.0723 | +| entropy_loss | -7.36 | +| explained_variance | 0.309 | +| learning_rate | 4.75e-05 | +| loss | -0.0384 | +| n_updates | 36756 | +| policy_gradient_loss | -0.0224 | +| value_loss | 0.000156 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1420 | +| iterations | 5236 | +| time_elapsed | 7549 | +| total_timesteps | 10723328 | +| train/ | | +| approx_kl | 0.0099741835 | +| clip_fraction | 0.348 | +| clip_range | 0.0723 | +| entropy_loss | -7.26 | +| explained_variance | 0.0229 | +| learning_rate | 4.75e-05 | +| loss | -0.0332 | +| n_updates | 36760 | +| policy_gradient_loss | -0.0215 | +| value_loss | 9.81e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1420 | +| iterations | 5237 | +| time_elapsed | 7550 | +| total_timesteps | 10725376 | +| train/ | | +| approx_kl | 0.009049574 | +| clip_fraction | 0.284 | +| clip_range | 0.0723 | +| entropy_loss | -6.71 | +| explained_variance | 0.37 | +| learning_rate | 4.75e-05 | +| loss | -0.0228 | +| n_updates | 36764 | +| policy_gradient_loss | -0.0136 | +| value_loss | 0.000294 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1420 | +| iterations | 5238 | +| time_elapsed | 7551 | +| total_timesteps | 10727424 | +| train/ | | +| approx_kl | 0.0096002845 | +| clip_fraction | 0.309 | +| clip_range | 0.0723 | +| entropy_loss | -7.26 | +| explained_variance | 0.359 | +| learning_rate | 4.75e-05 | +| loss | -0.036 | +| n_updates | 36768 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.00012 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1420 | +| iterations | 5239 | +| time_elapsed | 7553 | +| total_timesteps | 10729472 | +| train/ | | +| approx_kl | 0.010291318 | +| clip_fraction | 0.299 | +| clip_range | 0.0723 | +| entropy_loss | -6.95 | +| explained_variance | 0.213 | +| learning_rate | 4.75e-05 | +| loss | -0.0326 | +| n_updates | 36772 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000252 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1420 | +| iterations | 5240 | +| time_elapsed | 7554 | +| total_timesteps | 10731520 | +| train/ | | +| approx_kl | 0.011348708 | +| clip_fraction | 0.316 | +| clip_range | 0.0723 | +| entropy_loss | -7.1 | +| explained_variance | 0.487 | +| learning_rate | 4.75e-05 | +| loss | -0.0378 | +| n_updates | 36776 | +| policy_gradient_loss | -0.0217 | +| value_loss | 5.74e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1420 | +| iterations | 5241 | +| time_elapsed | 7556 | +| total_timesteps | 10733568 | +| train/ | | +| approx_kl | 0.011676702 | +| clip_fraction | 0.316 | +| clip_range | 0.0723 | +| entropy_loss | -7.06 | +| explained_variance | 0.35 | +| learning_rate | 4.75e-05 | +| loss | -0.0319 | +| n_updates | 36780 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000113 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1420 | +| iterations | 5242 | +| time_elapsed | 7557 | +| total_timesteps | 10735616 | +| train/ | | +| approx_kl | 0.012131862 | +| clip_fraction | 0.308 | +| clip_range | 0.0723 | +| entropy_loss | -6.64 | +| explained_variance | 0.393 | +| learning_rate | 4.75e-05 | +| loss | -0.0241 | +| n_updates | 36784 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000305 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.384 | +| time/ | | +| fps | 1420 | +| iterations | 5243 | +| time_elapsed | 7558 | +| total_timesteps | 10737664 | +| train/ | | +| approx_kl | 0.011699662 | +| clip_fraction | 0.343 | +| clip_range | 0.0723 | +| entropy_loss | -6.64 | +| explained_variance | 0.593 | +| learning_rate | 4.75e-05 | +| loss | -0.0391 | +| n_updates | 36788 | +| policy_gradient_loss | -0.022 | +| value_loss | 0.000103 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.388 | +| time/ | | +| fps | 1420 | +| iterations | 5244 | +| time_elapsed | 7560 | +| total_timesteps | 10739712 | +| train/ | | +| approx_kl | 0.009918769 | +| clip_fraction | 0.302 | +| clip_range | 0.0723 | +| entropy_loss | -7.15 | +| explained_variance | -0.00897 | +| learning_rate | 4.74e-05 | +| loss | -0.0292 | +| n_updates | 36792 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000259 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.388 | +| time/ | | +| fps | 1420 | +| iterations | 5245 | +| time_elapsed | 7561 | +| total_timesteps | 10741760 | +| train/ | | +| approx_kl | 0.008913059 | +| clip_fraction | 0.307 | +| clip_range | 0.0723 | +| entropy_loss | -7.14 | +| explained_variance | 0.121 | +| learning_rate | 4.74e-05 | +| loss | -0.027 | +| n_updates | 36796 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000262 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.389 | +| time/ | | +| fps | 1420 | +| iterations | 5246 | +| time_elapsed | 7563 | +| total_timesteps | 10743808 | +| train/ | | +| approx_kl | 0.01160709 | +| clip_fraction | 0.328 | +| clip_range | 0.0723 | +| entropy_loss | -7.36 | +| explained_variance | -0.208 | +| learning_rate | 4.74e-05 | +| loss | -0.0316 | +| n_updates | 36800 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000118 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.389 | +| time/ | | +| fps | 1420 | +| iterations | 5247 | +| time_elapsed | 7564 | +| total_timesteps | 10745856 | +| train/ | | +| approx_kl | 0.011585616 | +| clip_fraction | 0.318 | +| clip_range | 0.0723 | +| entropy_loss | -7.03 | +| explained_variance | 0.588 | +| learning_rate | 4.74e-05 | +| loss | -0.0373 | +| n_updates | 36804 | +| policy_gradient_loss | -0.0207 | +| value_loss | 7.98e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.387 | +| time/ | | +| fps | 1420 | +| iterations | 5248 | +| time_elapsed | 7565 | +| total_timesteps | 10747904 | +| train/ | | +| approx_kl | 0.0099068675 | +| clip_fraction | 0.313 | +| clip_range | 0.0723 | +| entropy_loss | -7.17 | +| explained_variance | 0.306 | +| learning_rate | 4.74e-05 | +| loss | -0.0309 | +| n_updates | 36808 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000139 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1420 | +| iterations | 5249 | +| time_elapsed | 7567 | +| total_timesteps | 10749952 | +| train/ | | +| approx_kl | 0.009583618 | +| clip_fraction | 0.294 | +| clip_range | 0.0723 | +| entropy_loss | -6.67 | +| explained_variance | 0.343 | +| learning_rate | 4.74e-05 | +| loss | -0.0198 | +| n_updates | 36812 | +| policy_gradient_loss | -0.0141 | +| value_loss | 0.000244 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.384 | +| time/ | | +| fps | 1420 | +| iterations | 5250 | +| time_elapsed | 7568 | +| total_timesteps | 10752000 | +| train/ | | +| approx_kl | 0.011070745 | +| clip_fraction | 0.316 | +| clip_range | 0.0723 | +| entropy_loss | -7.07 | +| explained_variance | 0.309 | +| learning_rate | 4.74e-05 | +| loss | -0.0284 | +| n_updates | 36816 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000161 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.388 | +| time/ | | +| fps | 1420 | +| iterations | 5251 | +| time_elapsed | 7570 | +| total_timesteps | 10754048 | +| train/ | | +| approx_kl | 0.011430007 | +| clip_fraction | 0.305 | +| clip_range | 0.0723 | +| entropy_loss | -7.15 | +| explained_variance | 0.196 | +| learning_rate | 4.74e-05 | +| loss | -0.0261 | +| n_updates | 36820 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000231 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.391 | +| time/ | | +| fps | 1420 | +| iterations | 5252 | +| time_elapsed | 7571 | +| total_timesteps | 10756096 | +| train/ | | +| approx_kl | 0.011085574 | +| clip_fraction | 0.329 | +| clip_range | 0.0723 | +| entropy_loss | -7.24 | +| explained_variance | -0.18 | +| learning_rate | 4.74e-05 | +| loss | -0.028 | +| n_updates | 36824 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000182 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.395 | +| time/ | | +| fps | 1420 | +| iterations | 5253 | +| time_elapsed | 7573 | +| total_timesteps | 10758144 | +| train/ | | +| approx_kl | 0.0116168205 | +| clip_fraction | 0.314 | +| clip_range | 0.0723 | +| entropy_loss | -7.18 | +| explained_variance | -0.0941 | +| learning_rate | 4.74e-05 | +| loss | -0.0298 | +| n_updates | 36828 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000211 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.395 | +| time/ | | +| fps | 1420 | +| iterations | 5254 | +| time_elapsed | 7574 | +| total_timesteps | 10760192 | +| train/ | | +| approx_kl | 0.009963186 | +| clip_fraction | 0.314 | +| clip_range | 0.0723 | +| entropy_loss | -6.87 | +| explained_variance | 0.475 | +| learning_rate | 4.74e-05 | +| loss | -0.0217 | +| n_updates | 36832 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000113 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.393 | +| time/ | | +| fps | 1420 | +| iterations | 5255 | +| time_elapsed | 7575 | +| total_timesteps | 10762240 | +| train/ | | +| approx_kl | 0.014112941 | +| clip_fraction | 0.337 | +| clip_range | 0.0723 | +| entropy_loss | -7.08 | +| explained_variance | -0.173 | +| learning_rate | 4.74e-05 | +| loss | -0.0414 | +| n_updates | 36836 | +| policy_gradient_loss | -0.0217 | +| value_loss | 8.89e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.391 | +| time/ | | +| fps | 1420 | +| iterations | 5256 | +| time_elapsed | 7577 | +| total_timesteps | 10764288 | +| train/ | | +| approx_kl | 0.012438442 | +| clip_fraction | 0.327 | +| clip_range | 0.0723 | +| entropy_loss | -7 | +| explained_variance | 0.297 | +| learning_rate | 4.74e-05 | +| loss | -0.0297 | +| n_updates | 36840 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000107 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.385 | +| time/ | | +| fps | 1420 | +| iterations | 5257 | +| time_elapsed | 7578 | +| total_timesteps | 10766336 | +| train/ | | +| approx_kl | 0.012361753 | +| clip_fraction | 0.305 | +| clip_range | 0.0723 | +| entropy_loss | -7.1 | +| explained_variance | 0.326 | +| learning_rate | 4.74e-05 | +| loss | -0.031 | +| n_updates | 36844 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000136 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1420 | +| iterations | 5258 | +| time_elapsed | 7580 | +| total_timesteps | 10768384 | +| train/ | | +| approx_kl | 0.012896119 | +| clip_fraction | 0.305 | +| clip_range | 0.0723 | +| entropy_loss | -6.84 | +| explained_variance | 0.505 | +| learning_rate | 4.74e-05 | +| loss | -0.0306 | +| n_updates | 36848 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000133 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.385 | +| time/ | | +| fps | 1420 | +| iterations | 5259 | +| time_elapsed | 7581 | +| total_timesteps | 10770432 | +| train/ | | +| approx_kl | 0.008980646 | +| clip_fraction | 0.266 | +| clip_range | 0.0723 | +| entropy_loss | -6.92 | +| explained_variance | 0.394 | +| learning_rate | 4.74e-05 | +| loss | -0.0293 | +| n_updates | 36852 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000243 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.388 | +| time/ | | +| fps | 1420 | +| iterations | 5260 | +| time_elapsed | 7583 | +| total_timesteps | 10772480 | +| train/ | | +| approx_kl | 0.009061355 | +| clip_fraction | 0.304 | +| clip_range | 0.0723 | +| entropy_loss | -6.75 | +| explained_variance | 0.293 | +| learning_rate | 4.74e-05 | +| loss | -0.0311 | +| n_updates | 36856 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000308 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.388 | +| time/ | | +| fps | 1420 | +| iterations | 5261 | +| time_elapsed | 7584 | +| total_timesteps | 10774528 | +| train/ | | +| approx_kl | 0.010405682 | +| clip_fraction | 0.323 | +| clip_range | 0.0723 | +| entropy_loss | -6.75 | +| explained_variance | 0.515 | +| learning_rate | 4.74e-05 | +| loss | -0.0392 | +| n_updates | 36860 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000204 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.39 | +| time/ | | +| fps | 1420 | +| iterations | 5262 | +| time_elapsed | 7586 | +| total_timesteps | 10776576 | +| train/ | | +| approx_kl | 0.011929816 | +| clip_fraction | 0.338 | +| clip_range | 0.0723 | +| entropy_loss | -7.27 | +| explained_variance | -0.172 | +| learning_rate | 4.74e-05 | +| loss | -0.0329 | +| n_updates | 36864 | +| policy_gradient_loss | -0.022 | +| value_loss | 0.000136 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.39 | +| time/ | | +| fps | 1420 | +| iterations | 5263 | +| time_elapsed | 7587 | +| total_timesteps | 10778624 | +| train/ | | +| approx_kl | 0.012032067 | +| clip_fraction | 0.309 | +| clip_range | 0.0723 | +| entropy_loss | -6.91 | +| explained_variance | 0.128 | +| learning_rate | 4.74e-05 | +| loss | -0.0313 | +| n_updates | 36868 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000181 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.396 | +| time/ | | +| fps | 1420 | +| iterations | 5264 | +| time_elapsed | 7588 | +| total_timesteps | 10780672 | +| train/ | | +| approx_kl | 0.012775425 | +| clip_fraction | 0.331 | +| clip_range | 0.0723 | +| entropy_loss | -7.39 | +| explained_variance | -0.0332 | +| learning_rate | 4.74e-05 | +| loss | -0.0345 | +| n_updates | 36872 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.396 | +| time/ | | +| fps | 1420 | +| iterations | 5265 | +| time_elapsed | 7590 | +| total_timesteps | 10782720 | +| train/ | | +| approx_kl | 0.010954017 | +| clip_fraction | 0.312 | +| clip_range | 0.0723 | +| entropy_loss | -6.94 | +| explained_variance | 0.32 | +| learning_rate | 4.74e-05 | +| loss | -0.0357 | +| n_updates | 36876 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000268 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.396 | +| time/ | | +| fps | 1420 | +| iterations | 5266 | +| time_elapsed | 7591 | +| total_timesteps | 10784768 | +| train/ | | +| approx_kl | 0.00966139 | +| clip_fraction | 0.302 | +| clip_range | 0.0723 | +| entropy_loss | -7.14 | +| explained_variance | 0.0465 | +| learning_rate | 4.74e-05 | +| loss | -0.0315 | +| n_updates | 36880 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000114 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.396 | +| time/ | | +| fps | 1420 | +| iterations | 5267 | +| time_elapsed | 7593 | +| total_timesteps | 10786816 | +| train/ | | +| approx_kl | 0.010709936 | +| clip_fraction | 0.326 | +| clip_range | 0.0723 | +| entropy_loss | -7.12 | +| explained_variance | 0.221 | +| learning_rate | 4.74e-05 | +| loss | -0.03 | +| n_updates | 36884 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000159 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.397 | +| time/ | | +| fps | 1420 | +| iterations | 5268 | +| time_elapsed | 7594 | +| total_timesteps | 10788864 | +| train/ | | +| approx_kl | 0.013656681 | +| clip_fraction | 0.334 | +| clip_range | 0.0723 | +| entropy_loss | -7.49 | +| explained_variance | -0.0558 | +| learning_rate | 4.74e-05 | +| loss | -0.0325 | +| n_updates | 36888 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000146 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.401 | +| time/ | | +| fps | 1420 | +| iterations | 5269 | +| time_elapsed | 7596 | +| total_timesteps | 10790912 | +| train/ | | +| approx_kl | 0.011208209 | +| clip_fraction | 0.347 | +| clip_range | 0.0723 | +| entropy_loss | -7.15 | +| explained_variance | 0.435 | +| learning_rate | 4.74e-05 | +| loss | -0.0379 | +| n_updates | 36892 | +| policy_gradient_loss | -0.0226 | +| value_loss | 7.85e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.406 | +| time/ | | +| fps | 1420 | +| iterations | 5270 | +| time_elapsed | 7597 | +| total_timesteps | 10792960 | +| train/ | | +| approx_kl | 0.010637184 | +| clip_fraction | 0.318 | +| clip_range | 0.0723 | +| entropy_loss | -7.03 | +| explained_variance | 0.353 | +| learning_rate | 4.74e-05 | +| loss | -0.0347 | +| n_updates | 36896 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.403 | +| time/ | | +| fps | 1420 | +| iterations | 5271 | +| time_elapsed | 7598 | +| total_timesteps | 10795008 | +| train/ | | +| approx_kl | 0.009331962 | +| clip_fraction | 0.273 | +| clip_range | 0.0723 | +| entropy_loss | -6.55 | +| explained_variance | 0.584 | +| learning_rate | 4.74e-05 | +| loss | -0.0246 | +| n_updates | 36900 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000217 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.406 | +| time/ | | +| fps | 1420 | +| iterations | 5272 | +| time_elapsed | 7600 | +| total_timesteps | 10797056 | +| train/ | | +| approx_kl | 0.01140313 | +| clip_fraction | 0.337 | +| clip_range | 0.0723 | +| entropy_loss | -6.49 | +| explained_variance | 0.799 | +| learning_rate | 4.74e-05 | +| loss | -0.0411 | +| n_updates | 36904 | +| policy_gradient_loss | -0.024 | +| value_loss | 4.24e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.402 | +| time/ | | +| fps | 1420 | +| iterations | 5273 | +| time_elapsed | 7601 | +| total_timesteps | 10799104 | +| train/ | | +| approx_kl | 0.010297044 | +| clip_fraction | 0.303 | +| clip_range | 0.0723 | +| entropy_loss | -7.06 | +| explained_variance | 0.372 | +| learning_rate | 4.74e-05 | +| loss | -0.0257 | +| n_updates | 36908 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000133 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.404 | +| time/ | | +| fps | 1420 | +| iterations | 5274 | +| time_elapsed | 7603 | +| total_timesteps | 10801152 | +| train/ | | +| approx_kl | 0.01028144 | +| clip_fraction | 0.315 | +| clip_range | 0.0723 | +| entropy_loss | -7.15 | +| explained_variance | 0.249 | +| learning_rate | 4.74e-05 | +| loss | -0.0327 | +| n_updates | 36912 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000241 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.405 | +| time/ | | +| fps | 1420 | +| iterations | 5275 | +| time_elapsed | 7604 | +| total_timesteps | 10803200 | +| train/ | | +| approx_kl | 0.01097821 | +| clip_fraction | 0.288 | +| clip_range | 0.0723 | +| entropy_loss | -7.12 | +| explained_variance | 0.209 | +| learning_rate | 4.74e-05 | +| loss | -0.0324 | +| n_updates | 36916 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000179 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.406 | +| time/ | | +| fps | 1420 | +| iterations | 5276 | +| time_elapsed | 7606 | +| total_timesteps | 10805248 | +| train/ | | +| approx_kl | 0.011273207 | +| clip_fraction | 0.301 | +| clip_range | 0.0723 | +| entropy_loss | -7.22 | +| explained_variance | 0.221 | +| learning_rate | 4.74e-05 | +| loss | -0.027 | +| n_updates | 36920 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.00025 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.402 | +| time/ | | +| fps | 1420 | +| iterations | 5277 | +| time_elapsed | 7607 | +| total_timesteps | 10807296 | +| train/ | | +| approx_kl | 0.009342673 | +| clip_fraction | 0.309 | +| clip_range | 0.0723 | +| entropy_loss | -6.81 | +| explained_variance | 0.317 | +| learning_rate | 4.74e-05 | +| loss | -0.0307 | +| n_updates | 36924 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000275 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.4 | +| time/ | | +| fps | 1420 | +| iterations | 5278 | +| time_elapsed | 7609 | +| total_timesteps | 10809344 | +| train/ | | +| approx_kl | 0.010698455 | +| clip_fraction | 0.339 | +| clip_range | 0.0723 | +| entropy_loss | -7.09 | +| explained_variance | 0.417 | +| learning_rate | 4.74e-05 | +| loss | -0.039 | +| n_updates | 36928 | +| policy_gradient_loss | -0.0237 | +| value_loss | 8.1e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.398 | +| time/ | | +| fps | 1420 | +| iterations | 5279 | +| time_elapsed | 7610 | +| total_timesteps | 10811392 | +| train/ | | +| approx_kl | 0.0130094625 | +| clip_fraction | 0.342 | +| clip_range | 0.0723 | +| entropy_loss | -7.28 | +| explained_variance | -0.0379 | +| learning_rate | 4.74e-05 | +| loss | -0.0327 | +| n_updates | 36932 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.00014 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.399 | +| time/ | | +| fps | 1420 | +| iterations | 5280 | +| time_elapsed | 7612 | +| total_timesteps | 10813440 | +| train/ | | +| approx_kl | 0.011108683 | +| clip_fraction | 0.295 | +| clip_range | 0.0723 | +| entropy_loss | -7.13 | +| explained_variance | 0.241 | +| learning_rate | 4.74e-05 | +| loss | -0.0286 | +| n_updates | 36936 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000199 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.395 | +| time/ | | +| fps | 1420 | +| iterations | 5281 | +| time_elapsed | 7613 | +| total_timesteps | 10815488 | +| train/ | | +| approx_kl | 0.011022549 | +| clip_fraction | 0.303 | +| clip_range | 0.0723 | +| entropy_loss | -7.26 | +| explained_variance | 0.257 | +| learning_rate | 4.74e-05 | +| loss | -0.0256 | +| n_updates | 36940 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000211 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.396 | +| time/ | | +| fps | 1420 | +| iterations | 5282 | +| time_elapsed | 7614 | +| total_timesteps | 10817536 | +| train/ | | +| approx_kl | 0.012157771 | +| clip_fraction | 0.357 | +| clip_range | 0.0723 | +| entropy_loss | -7.14 | +| explained_variance | 0.153 | +| learning_rate | 4.74e-05 | +| loss | -0.0437 | +| n_updates | 36944 | +| policy_gradient_loss | -0.0238 | +| value_loss | 6.62e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.389 | +| time/ | | +| fps | 1420 | +| iterations | 5283 | +| time_elapsed | 7616 | +| total_timesteps | 10819584 | +| train/ | | +| approx_kl | 0.011130089 | +| clip_fraction | 0.308 | +| clip_range | 0.0723 | +| entropy_loss | -7.01 | +| explained_variance | 0.445 | +| learning_rate | 4.74e-05 | +| loss | -0.0328 | +| n_updates | 36948 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000134 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.388 | +| time/ | | +| fps | 1420 | +| iterations | 5284 | +| time_elapsed | 7617 | +| total_timesteps | 10821632 | +| train/ | | +| approx_kl | 0.011767101 | +| clip_fraction | 0.312 | +| clip_range | 0.0723 | +| entropy_loss | -6.46 | +| explained_variance | 0.43 | +| learning_rate | 4.74e-05 | +| loss | -0.0306 | +| n_updates | 36952 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.00023 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.391 | +| time/ | | +| fps | 1420 | +| iterations | 5285 | +| time_elapsed | 7619 | +| total_timesteps | 10823680 | +| train/ | | +| approx_kl | 0.012211415 | +| clip_fraction | 0.337 | +| clip_range | 0.0723 | +| entropy_loss | -6.79 | +| explained_variance | 0.28 | +| learning_rate | 4.74e-05 | +| loss | -0.0306 | +| n_updates | 36956 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.00013 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.391 | +| time/ | | +| fps | 1420 | +| iterations | 5286 | +| time_elapsed | 7620 | +| total_timesteps | 10825728 | +| train/ | | +| approx_kl | 0.0108326245 | +| clip_fraction | 0.294 | +| clip_range | 0.0723 | +| entropy_loss | -6.21 | +| explained_variance | 0.427 | +| learning_rate | 4.74e-05 | +| loss | -0.0255 | +| n_updates | 36960 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.000335 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.391 | +| time/ | | +| fps | 1420 | +| iterations | 5287 | +| time_elapsed | 7622 | +| total_timesteps | 10827776 | +| train/ | | +| approx_kl | 0.010348575 | +| clip_fraction | 0.32 | +| clip_range | 0.0723 | +| entropy_loss | -7.11 | +| explained_variance | 0.0439 | +| learning_rate | 4.74e-05 | +| loss | -0.0388 | +| n_updates | 36964 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000143 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.392 | +| time/ | | +| fps | 1420 | +| iterations | 5288 | +| time_elapsed | 7623 | +| total_timesteps | 10829824 | +| train/ | | +| approx_kl | 0.010667253 | +| clip_fraction | 0.339 | +| clip_range | 0.0723 | +| entropy_loss | -7.36 | +| explained_variance | -0.181 | +| learning_rate | 4.74e-05 | +| loss | -0.0391 | +| n_updates | 36968 | +| policy_gradient_loss | -0.0229 | +| value_loss | 0.000104 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.39 | +| time/ | | +| fps | 1420 | +| iterations | 5289 | +| time_elapsed | 7624 | +| total_timesteps | 10831872 | +| train/ | | +| approx_kl | 0.0087062605 | +| clip_fraction | 0.273 | +| clip_range | 0.0723 | +| entropy_loss | -7.37 | +| explained_variance | -0.0345 | +| learning_rate | 4.74e-05 | +| loss | -0.024 | +| n_updates | 36972 | +| policy_gradient_loss | -0.0142 | +| value_loss | 0.000224 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.395 | +| time/ | | +| fps | 1420 | +| iterations | 5290 | +| time_elapsed | 7626 | +| total_timesteps | 10833920 | +| train/ | | +| approx_kl | 0.008814901 | +| clip_fraction | 0.331 | +| clip_range | 0.0723 | +| entropy_loss | -7.14 | +| explained_variance | 0.296 | +| learning_rate | 4.74e-05 | +| loss | -0.0422 | +| n_updates | 36976 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000104 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.394 | +| time/ | | +| fps | 1420 | +| iterations | 5291 | +| time_elapsed | 7627 | +| total_timesteps | 10835968 | +| train/ | | +| approx_kl | 0.009732747 | +| clip_fraction | 0.29 | +| clip_range | 0.0723 | +| entropy_loss | -7.07 | +| explained_variance | 0.178 | +| learning_rate | 4.74e-05 | +| loss | -0.0288 | +| n_updates | 36980 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000258 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.394 | +| time/ | | +| fps | 1420 | +| iterations | 5292 | +| time_elapsed | 7629 | +| total_timesteps | 10838016 | +| train/ | | +| approx_kl | 0.010421682 | +| clip_fraction | 0.276 | +| clip_range | 0.0723 | +| entropy_loss | -6.61 | +| explained_variance | 0.261 | +| learning_rate | 4.74e-05 | +| loss | -0.03 | +| n_updates | 36984 | +| policy_gradient_loss | -0.0143 | +| value_loss | 0.000231 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.391 | +| time/ | | +| fps | 1420 | +| iterations | 5293 | +| time_elapsed | 7630 | +| total_timesteps | 10840064 | +| train/ | | +| approx_kl | 0.011534372 | +| clip_fraction | 0.362 | +| clip_range | 0.0723 | +| entropy_loss | -7.44 | +| explained_variance | -0.452 | +| learning_rate | 4.74e-05 | +| loss | -0.0378 | +| n_updates | 36988 | +| policy_gradient_loss | -0.023 | +| value_loss | 0.000111 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.392 | +| time/ | | +| fps | 1420 | +| iterations | 5294 | +| time_elapsed | 7632 | +| total_timesteps | 10842112 | +| train/ | | +| approx_kl | 0.009704175 | +| clip_fraction | 0.302 | +| clip_range | 0.0723 | +| entropy_loss | -7.14 | +| explained_variance | 0.271 | +| learning_rate | 4.74e-05 | +| loss | -0.03 | +| n_updates | 36992 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000168 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.386 | +| time/ | | +| fps | 1420 | +| iterations | 5295 | +| time_elapsed | 7633 | +| total_timesteps | 10844160 | +| train/ | | +| approx_kl | 0.009540642 | +| clip_fraction | 0.299 | +| clip_range | 0.0723 | +| entropy_loss | -7.21 | +| explained_variance | -0.0503 | +| learning_rate | 4.74e-05 | +| loss | -0.0309 | +| n_updates | 36996 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000202 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1420 | +| iterations | 5296 | +| time_elapsed | 7635 | +| total_timesteps | 10846208 | +| train/ | | +| approx_kl | 0.009962498 | +| clip_fraction | 0.295 | +| clip_range | 0.0723 | +| entropy_loss | -7.13 | +| explained_variance | 0.53 | +| learning_rate | 4.74e-05 | +| loss | -0.0283 | +| n_updates | 37000 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000112 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1420 | +| iterations | 5297 | +| time_elapsed | 7636 | +| total_timesteps | 10848256 | +| train/ | | +| approx_kl | 0.010821366 | +| clip_fraction | 0.301 | +| clip_range | 0.0723 | +| entropy_loss | -6.24 | +| explained_variance | 0.318 | +| learning_rate | 4.74e-05 | +| loss | -0.0278 | +| n_updates | 37004 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000481 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1420 | +| iterations | 5298 | +| time_elapsed | 7637 | +| total_timesteps | 10850304 | +| train/ | | +| approx_kl | 0.012030679 | +| clip_fraction | 0.34 | +| clip_range | 0.0723 | +| entropy_loss | -6.93 | +| explained_variance | 0.403 | +| learning_rate | 4.74e-05 | +| loss | -0.0439 | +| n_updates | 37008 | +| policy_gradient_loss | -0.0222 | +| value_loss | 8.74e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1420 | +| iterations | 5299 | +| time_elapsed | 7639 | +| total_timesteps | 10852352 | +| train/ | | +| approx_kl | 0.010204464 | +| clip_fraction | 0.298 | +| clip_range | 0.0723 | +| entropy_loss | -7.03 | +| explained_variance | 0.186 | +| learning_rate | 4.74e-05 | +| loss | -0.031 | +| n_updates | 37012 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000163 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1420 | +| iterations | 5300 | +| time_elapsed | 7640 | +| total_timesteps | 10854400 | +| train/ | | +| approx_kl | 0.010516617 | +| clip_fraction | 0.325 | +| clip_range | 0.0723 | +| entropy_loss | -7.2 | +| explained_variance | 0.0615 | +| learning_rate | 4.74e-05 | +| loss | -0.0347 | +| n_updates | 37016 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000128 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1420 | +| iterations | 5301 | +| time_elapsed | 7642 | +| total_timesteps | 10856448 | +| train/ | | +| approx_kl | 0.011578565 | +| clip_fraction | 0.319 | +| clip_range | 0.0723 | +| entropy_loss | -6.86 | +| explained_variance | 0.538 | +| learning_rate | 4.74e-05 | +| loss | -0.0303 | +| n_updates | 37020 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000115 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1420 | +| iterations | 5302 | +| time_elapsed | 7643 | +| total_timesteps | 10858496 | +| train/ | | +| approx_kl | 0.01097127 | +| clip_fraction | 0.324 | +| clip_range | 0.0723 | +| entropy_loss | -7.14 | +| explained_variance | 0.384 | +| learning_rate | 4.74e-05 | +| loss | -0.0393 | +| n_updates | 37024 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000115 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.385 | +| time/ | | +| fps | 1420 | +| iterations | 5303 | +| time_elapsed | 7645 | +| total_timesteps | 10860544 | +| train/ | | +| approx_kl | 0.009100111 | +| clip_fraction | 0.285 | +| clip_range | 0.0723 | +| entropy_loss | -7.29 | +| explained_variance | 0.104 | +| learning_rate | 4.74e-05 | +| loss | -0.0281 | +| n_updates | 37028 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000334 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.385 | +| time/ | | +| fps | 1420 | +| iterations | 5304 | +| time_elapsed | 7646 | +| total_timesteps | 10862592 | +| train/ | | +| approx_kl | 0.01271496 | +| clip_fraction | 0.336 | +| clip_range | 0.0723 | +| entropy_loss | -6.91 | +| explained_variance | 0.621 | +| learning_rate | 4.74e-05 | +| loss | -0.028 | +| n_updates | 37032 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000116 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.385 | +| time/ | | +| fps | 1420 | +| iterations | 5305 | +| time_elapsed | 7648 | +| total_timesteps | 10864640 | +| train/ | | +| approx_kl | 0.009764446 | +| clip_fraction | 0.291 | +| clip_range | 0.0723 | +| entropy_loss | -7.14 | +| explained_variance | 0.175 | +| learning_rate | 4.74e-05 | +| loss | -0.0296 | +| n_updates | 37036 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000265 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.384 | +| time/ | | +| fps | 1420 | +| iterations | 5306 | +| time_elapsed | 7649 | +| total_timesteps | 10866688 | +| train/ | | +| approx_kl | 0.008999767 | +| clip_fraction | 0.319 | +| clip_range | 0.0723 | +| entropy_loss | -7.48 | +| explained_variance | -0.364 | +| learning_rate | 4.74e-05 | +| loss | -0.0287 | +| n_updates | 37040 | +| policy_gradient_loss | -0.0221 | +| value_loss | 8.06e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1420 | +| iterations | 5307 | +| time_elapsed | 7651 | +| total_timesteps | 10868736 | +| train/ | | +| approx_kl | 0.011131265 | +| clip_fraction | 0.336 | +| clip_range | 0.0723 | +| entropy_loss | -6.98 | +| explained_variance | 0.602 | +| learning_rate | 4.74e-05 | +| loss | -0.0353 | +| n_updates | 37044 | +| policy_gradient_loss | -0.0195 | +| value_loss | 8.6e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1420 | +| iterations | 5308 | +| time_elapsed | 7652 | +| total_timesteps | 10870784 | +| train/ | | +| approx_kl | 0.010584159 | +| clip_fraction | 0.324 | +| clip_range | 0.0723 | +| entropy_loss | -6.85 | +| explained_variance | 0.552 | +| learning_rate | 4.74e-05 | +| loss | -0.0333 | +| n_updates | 37048 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000125 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1420 | +| iterations | 5309 | +| time_elapsed | 7653 | +| total_timesteps | 10872832 | +| train/ | | +| approx_kl | 0.010970123 | +| clip_fraction | 0.348 | +| clip_range | 0.0723 | +| entropy_loss | -6.79 | +| explained_variance | 0.766 | +| learning_rate | 4.74e-05 | +| loss | -0.0346 | +| n_updates | 37052 | +| policy_gradient_loss | -0.0231 | +| value_loss | 4.57e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1420 | +| iterations | 5310 | +| time_elapsed | 7655 | +| total_timesteps | 10874880 | +| train/ | | +| approx_kl | 0.012363839 | +| clip_fraction | 0.335 | +| clip_range | 0.0723 | +| entropy_loss | -6.79 | +| explained_variance | 0.29 | +| learning_rate | 4.74e-05 | +| loss | -0.0274 | +| n_updates | 37056 | +| policy_gradient_loss | -0.0191 | +| value_loss | 6.08e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1420 | +| iterations | 5311 | +| time_elapsed | 7656 | +| total_timesteps | 10876928 | +| train/ | | +| approx_kl | 0.012050381 | +| clip_fraction | 0.316 | +| clip_range | 0.0723 | +| entropy_loss | -7.31 | +| explained_variance | 0.0516 | +| learning_rate | 4.74e-05 | +| loss | -0.0296 | +| n_updates | 37060 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000135 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1420 | +| iterations | 5312 | +| time_elapsed | 7658 | +| total_timesteps | 10878976 | +| train/ | | +| approx_kl | 0.011386706 | +| clip_fraction | 0.291 | +| clip_range | 0.0723 | +| entropy_loss | -6.87 | +| explained_variance | 0.195 | +| learning_rate | 4.74e-05 | +| loss | -0.032 | +| n_updates | 37064 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000255 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1420 | +| iterations | 5313 | +| time_elapsed | 7659 | +| total_timesteps | 10881024 | +| train/ | | +| approx_kl | 0.011191754 | +| clip_fraction | 0.314 | +| clip_range | 0.0723 | +| entropy_loss | -7.11 | +| explained_variance | 0.348 | +| learning_rate | 4.74e-05 | +| loss | -0.0352 | +| n_updates | 37068 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000125 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1420 | +| iterations | 5314 | +| time_elapsed | 7661 | +| total_timesteps | 10883072 | +| train/ | | +| approx_kl | 0.011264064 | +| clip_fraction | 0.307 | +| clip_range | 0.0723 | +| entropy_loss | -6.67 | +| explained_variance | 0.535 | +| learning_rate | 4.74e-05 | +| loss | -0.025 | +| n_updates | 37072 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000151 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1420 | +| iterations | 5315 | +| time_elapsed | 7662 | +| total_timesteps | 10885120 | +| train/ | | +| approx_kl | 0.010764845 | +| clip_fraction | 0.315 | +| clip_range | 0.0723 | +| entropy_loss | -6.71 | +| explained_variance | 0.371 | +| learning_rate | 4.74e-05 | +| loss | -0.0231 | +| n_updates | 37076 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.00027 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1420 | +| iterations | 5316 | +| time_elapsed | 7664 | +| total_timesteps | 10887168 | +| train/ | | +| approx_kl | 0.012440134 | +| clip_fraction | 0.34 | +| clip_range | 0.0723 | +| entropy_loss | -6.81 | +| explained_variance | 0.578 | +| learning_rate | 4.74e-05 | +| loss | -0.0294 | +| n_updates | 37080 | +| policy_gradient_loss | -0.0214 | +| value_loss | 9.3e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1420 | +| iterations | 5317 | +| time_elapsed | 7665 | +| total_timesteps | 10889216 | +| train/ | | +| approx_kl | 0.01076716 | +| clip_fraction | 0.338 | +| clip_range | 0.0723 | +| entropy_loss | -7.4 | +| explained_variance | -0.0989 | +| learning_rate | 4.74e-05 | +| loss | -0.0346 | +| n_updates | 37084 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000127 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1420 | +| iterations | 5318 | +| time_elapsed | 7666 | +| total_timesteps | 10891264 | +| train/ | | +| approx_kl | 0.009587048 | +| clip_fraction | 0.311 | +| clip_range | 0.0723 | +| entropy_loss | -7.46 | +| explained_variance | -0.127 | +| learning_rate | 4.74e-05 | +| loss | -0.0304 | +| n_updates | 37088 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000148 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1420 | +| iterations | 5319 | +| time_elapsed | 7668 | +| total_timesteps | 10893312 | +| train/ | | +| approx_kl | 0.013598439 | +| clip_fraction | 0.297 | +| clip_range | 0.0723 | +| entropy_loss | -7.13 | +| explained_variance | -0.127 | +| learning_rate | 4.74e-05 | +| loss | -0.0299 | +| n_updates | 37092 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000152 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1420 | +| iterations | 5320 | +| time_elapsed | 7669 | +| total_timesteps | 10895360 | +| train/ | | +| approx_kl | 0.009571296 | +| clip_fraction | 0.304 | +| clip_range | 0.0723 | +| entropy_loss | -7.23 | +| explained_variance | 0.159 | +| learning_rate | 4.74e-05 | +| loss | -0.0298 | +| n_updates | 37096 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000172 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1420 | +| iterations | 5321 | +| time_elapsed | 7671 | +| total_timesteps | 10897408 | +| train/ | | +| approx_kl | 0.010260106 | +| clip_fraction | 0.292 | +| clip_range | 0.0723 | +| entropy_loss | -6.56 | +| explained_variance | 0.644 | +| learning_rate | 4.74e-05 | +| loss | -0.0318 | +| n_updates | 37100 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000105 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1420 | +| iterations | 5322 | +| time_elapsed | 7672 | +| total_timesteps | 10899456 | +| train/ | | +| approx_kl | 0.011718744 | +| clip_fraction | 0.332 | +| clip_range | 0.0723 | +| entropy_loss | -6.72 | +| explained_variance | 0.481 | +| learning_rate | 4.74e-05 | +| loss | -0.033 | +| n_updates | 37104 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000149 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1420 | +| iterations | 5323 | +| time_elapsed | 7674 | +| total_timesteps | 10901504 | +| train/ | | +| approx_kl | 0.0119991135 | +| clip_fraction | 0.308 | +| clip_range | 0.0723 | +| entropy_loss | -6.6 | +| explained_variance | 0.349 | +| learning_rate | 4.74e-05 | +| loss | -0.0275 | +| n_updates | 37108 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000272 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1420 | +| iterations | 5324 | +| time_elapsed | 7675 | +| total_timesteps | 10903552 | +| train/ | | +| approx_kl | 0.009501452 | +| clip_fraction | 0.311 | +| clip_range | 0.0723 | +| entropy_loss | -6.9 | +| explained_variance | 0.126 | +| learning_rate | 4.74e-05 | +| loss | -0.0313 | +| n_updates | 37112 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000426 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1420 | +| iterations | 5325 | +| time_elapsed | 7677 | +| total_timesteps | 10905600 | +| train/ | | +| approx_kl | 0.010930696 | +| clip_fraction | 0.313 | +| clip_range | 0.0723 | +| entropy_loss | -7.06 | +| explained_variance | 0.152 | +| learning_rate | 4.74e-05 | +| loss | -0.0312 | +| n_updates | 37116 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000164 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1420 | +| iterations | 5326 | +| time_elapsed | 7678 | +| total_timesteps | 10907648 | +| train/ | | +| approx_kl | 0.012328922 | +| clip_fraction | 0.336 | +| clip_range | 0.0723 | +| entropy_loss | -6.75 | +| explained_variance | 0.596 | +| learning_rate | 4.74e-05 | +| loss | -0.0318 | +| n_updates | 37120 | +| policy_gradient_loss | -0.0225 | +| value_loss | 0.000137 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1420 | +| iterations | 5327 | +| time_elapsed | 7679 | +| total_timesteps | 10909696 | +| train/ | | +| approx_kl | 0.010142615 | +| clip_fraction | 0.328 | +| clip_range | 0.0723 | +| entropy_loss | -7.06 | +| explained_variance | 0.39 | +| learning_rate | 4.74e-05 | +| loss | -0.0393 | +| n_updates | 37124 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000105 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1420 | +| iterations | 5328 | +| time_elapsed | 7681 | +| total_timesteps | 10911744 | +| train/ | | +| approx_kl | 0.012867448 | +| clip_fraction | 0.309 | +| clip_range | 0.0723 | +| entropy_loss | -7.25 | +| explained_variance | -0.149 | +| learning_rate | 4.74e-05 | +| loss | -0.0333 | +| n_updates | 37128 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000125 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1420 | +| iterations | 5329 | +| time_elapsed | 7682 | +| total_timesteps | 10913792 | +| train/ | | +| approx_kl | 0.0104843285 | +| clip_fraction | 0.319 | +| clip_range | 0.0723 | +| entropy_loss | -7.34 | +| explained_variance | -0.123 | +| learning_rate | 4.74e-05 | +| loss | -0.0326 | +| n_updates | 37132 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000117 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1420 | +| iterations | 5330 | +| time_elapsed | 7684 | +| total_timesteps | 10915840 | +| train/ | | +| approx_kl | 0.01017342 | +| clip_fraction | 0.333 | +| clip_range | 0.0723 | +| entropy_loss | -7.45 | +| explained_variance | -0.48 | +| learning_rate | 4.74e-05 | +| loss | -0.0392 | +| n_updates | 37136 | +| policy_gradient_loss | -0.0244 | +| value_loss | 6.36e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1420 | +| iterations | 5331 | +| time_elapsed | 7685 | +| total_timesteps | 10917888 | +| train/ | | +| approx_kl | 0.011464333 | +| clip_fraction | 0.29 | +| clip_range | 0.0723 | +| entropy_loss | -6.83 | +| explained_variance | 0.254 | +| learning_rate | 4.74e-05 | +| loss | -0.0286 | +| n_updates | 37140 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000356 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1420 | +| iterations | 5332 | +| time_elapsed | 7687 | +| total_timesteps | 10919936 | +| train/ | | +| approx_kl | 0.010061022 | +| clip_fraction | 0.31 | +| clip_range | 0.0723 | +| entropy_loss | -6.27 | +| explained_variance | 0.497 | +| learning_rate | 4.74e-05 | +| loss | -0.0225 | +| n_updates | 37144 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000218 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1420 | +| iterations | 5333 | +| time_elapsed | 7688 | +| total_timesteps | 10921984 | +| train/ | | +| approx_kl | 0.010788644 | +| clip_fraction | 0.356 | +| clip_range | 0.0723 | +| entropy_loss | -7.04 | +| explained_variance | 0.181 | +| learning_rate | 4.74e-05 | +| loss | -0.0362 | +| n_updates | 37148 | +| policy_gradient_loss | -0.0229 | +| value_loss | 0.000121 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1420 | +| iterations | 5334 | +| time_elapsed | 7690 | +| total_timesteps | 10924032 | +| train/ | | +| approx_kl | 0.011668313 | +| clip_fraction | 0.347 | +| clip_range | 0.0723 | +| entropy_loss | -7.32 | +| explained_variance | -0.185 | +| learning_rate | 4.74e-05 | +| loss | -0.0368 | +| n_updates | 37152 | +| policy_gradient_loss | -0.0218 | +| value_loss | 7e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1420 | +| iterations | 5335 | +| time_elapsed | 7691 | +| total_timesteps | 10926080 | +| train/ | | +| approx_kl | 0.013334568 | +| clip_fraction | 0.312 | +| clip_range | 0.0723 | +| entropy_loss | -6.92 | +| explained_variance | 0.31 | +| learning_rate | 4.74e-05 | +| loss | -0.0304 | +| n_updates | 37156 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.0002 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1420 | +| iterations | 5336 | +| time_elapsed | 7692 | +| total_timesteps | 10928128 | +| train/ | | +| approx_kl | 0.010537915 | +| clip_fraction | 0.312 | +| clip_range | 0.0723 | +| entropy_loss | -6.82 | +| explained_variance | 0.257 | +| learning_rate | 4.74e-05 | +| loss | -0.0268 | +| n_updates | 37160 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000169 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1420 | +| iterations | 5337 | +| time_elapsed | 7694 | +| total_timesteps | 10930176 | +| train/ | | +| approx_kl | 0.011684189 | +| clip_fraction | 0.347 | +| clip_range | 0.0723 | +| entropy_loss | -7.25 | +| explained_variance | -0.167 | +| learning_rate | 4.74e-05 | +| loss | -0.0355 | +| n_updates | 37164 | +| policy_gradient_loss | -0.02 | +| value_loss | 8.69e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1420 | +| iterations | 5338 | +| time_elapsed | 7695 | +| total_timesteps | 10932224 | +| train/ | | +| approx_kl | 0.010874497 | +| clip_fraction | 0.327 | +| clip_range | 0.0723 | +| entropy_loss | -7.21 | +| explained_variance | 0.379 | +| learning_rate | 4.74e-05 | +| loss | -0.035 | +| n_updates | 37168 | +| policy_gradient_loss | -0.0204 | +| value_loss | 9.1e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1420 | +| iterations | 5339 | +| time_elapsed | 7697 | +| total_timesteps | 10934272 | +| train/ | | +| approx_kl | 0.010533869 | +| clip_fraction | 0.303 | +| clip_range | 0.0723 | +| entropy_loss | -7.12 | +| explained_variance | 0.408 | +| learning_rate | 4.74e-05 | +| loss | -0.0362 | +| n_updates | 37172 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000112 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1420 | +| iterations | 5340 | +| time_elapsed | 7698 | +| total_timesteps | 10936320 | +| train/ | | +| approx_kl | 0.010970208 | +| clip_fraction | 0.328 | +| clip_range | 0.0723 | +| entropy_loss | -6.99 | +| explained_variance | 0.403 | +| learning_rate | 4.74e-05 | +| loss | -0.0331 | +| n_updates | 37176 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000118 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1420 | +| iterations | 5341 | +| time_elapsed | 7700 | +| total_timesteps | 10938368 | +| train/ | | +| approx_kl | 0.011838807 | +| clip_fraction | 0.345 | +| clip_range | 0.0723 | +| entropy_loss | -7.1 | +| explained_variance | 0.511 | +| learning_rate | 4.74e-05 | +| loss | -0.0378 | +| n_updates | 37180 | +| policy_gradient_loss | -0.0217 | +| value_loss | 7.95e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1420 | +| iterations | 5342 | +| time_elapsed | 7701 | +| total_timesteps | 10940416 | +| train/ | | +| approx_kl | 0.0085278535 | +| clip_fraction | 0.297 | +| clip_range | 0.0723 | +| entropy_loss | -7.31 | +| explained_variance | 0.439 | +| learning_rate | 4.74e-05 | +| loss | -0.036 | +| n_updates | 37184 | +| policy_gradient_loss | -0.019 | +| value_loss | 8.42e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1420 | +| iterations | 5343 | +| time_elapsed | 7702 | +| total_timesteps | 10942464 | +| train/ | | +| approx_kl | 0.010446951 | +| clip_fraction | 0.272 | +| clip_range | 0.0723 | +| entropy_loss | -7.13 | +| explained_variance | 0.257 | +| learning_rate | 4.74e-05 | +| loss | -0.0225 | +| n_updates | 37188 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000206 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1420 | +| iterations | 5344 | +| time_elapsed | 7704 | +| total_timesteps | 10944512 | +| train/ | | +| approx_kl | 0.00977426 | +| clip_fraction | 0.3 | +| clip_range | 0.0723 | +| entropy_loss | -7 | +| explained_variance | 0.505 | +| learning_rate | 4.74e-05 | +| loss | -0.0368 | +| n_updates | 37192 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000129 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1420 | +| iterations | 5345 | +| time_elapsed | 7705 | +| total_timesteps | 10946560 | +| train/ | | +| approx_kl | 0.009651898 | +| clip_fraction | 0.292 | +| clip_range | 0.0723 | +| entropy_loss | -6.73 | +| explained_variance | 0.312 | +| learning_rate | 4.74e-05 | +| loss | -0.0266 | +| n_updates | 37196 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.00046 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1420 | +| iterations | 5346 | +| time_elapsed | 7707 | +| total_timesteps | 10948608 | +| train/ | | +| approx_kl | 0.0106081795 | +| clip_fraction | 0.31 | +| clip_range | 0.0723 | +| entropy_loss | -6.76 | +| explained_variance | 0.228 | +| learning_rate | 4.74e-05 | +| loss | -0.0358 | +| n_updates | 37200 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000165 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1420 | +| iterations | 5347 | +| time_elapsed | 7708 | +| total_timesteps | 10950656 | +| train/ | | +| approx_kl | 0.012461324 | +| clip_fraction | 0.33 | +| clip_range | 0.0723 | +| entropy_loss | -6.78 | +| explained_variance | 0.18 | +| learning_rate | 4.74e-05 | +| loss | -0.0345 | +| n_updates | 37204 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000196 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1420 | +| iterations | 5348 | +| time_elapsed | 7709 | +| total_timesteps | 10952704 | +| train/ | | +| approx_kl | 0.011319328 | +| clip_fraction | 0.348 | +| clip_range | 0.0723 | +| entropy_loss | -7.03 | +| explained_variance | 0.207 | +| learning_rate | 4.74e-05 | +| loss | -0.0353 | +| n_updates | 37208 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000112 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1420 | +| iterations | 5349 | +| time_elapsed | 7711 | +| total_timesteps | 10954752 | +| train/ | | +| approx_kl | 0.0127652995 | +| clip_fraction | 0.345 | +| clip_range | 0.0723 | +| entropy_loss | -7.11 | +| explained_variance | 0.357 | +| learning_rate | 4.74e-05 | +| loss | -0.0359 | +| n_updates | 37212 | +| policy_gradient_loss | -0.0219 | +| value_loss | 0.000102 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1420 | +| iterations | 5350 | +| time_elapsed | 7712 | +| total_timesteps | 10956800 | +| train/ | | +| approx_kl | 0.0098588355 | +| clip_fraction | 0.297 | +| clip_range | 0.0723 | +| entropy_loss | -7.52 | +| explained_variance | -0.062 | +| learning_rate | 4.74e-05 | +| loss | -0.0313 | +| n_updates | 37216 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000111 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1420 | +| iterations | 5351 | +| time_elapsed | 7714 | +| total_timesteps | 10958848 | +| train/ | | +| approx_kl | 0.011211123 | +| clip_fraction | 0.296 | +| clip_range | 0.0723 | +| entropy_loss | -7.45 | +| explained_variance | -0.114 | +| learning_rate | 4.74e-05 | +| loss | -0.0317 | +| n_updates | 37220 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000115 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1420 | +| iterations | 5352 | +| time_elapsed | 7715 | +| total_timesteps | 10960896 | +| train/ | | +| approx_kl | 0.010505304 | +| clip_fraction | 0.299 | +| clip_range | 0.0723 | +| entropy_loss | -7.45 | +| explained_variance | -0.0645 | +| learning_rate | 4.74e-05 | +| loss | -0.0284 | +| n_updates | 37224 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000163 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1420 | +| iterations | 5353 | +| time_elapsed | 7717 | +| total_timesteps | 10962944 | +| train/ | | +| approx_kl | 0.010008341 | +| clip_fraction | 0.261 | +| clip_range | 0.0723 | +| entropy_loss | -6.98 | +| explained_variance | 0.329 | +| learning_rate | 4.74e-05 | +| loss | -0.0282 | +| n_updates | 37228 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000133 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1420 | +| iterations | 5354 | +| time_elapsed | 7718 | +| total_timesteps | 10964992 | +| train/ | | +| approx_kl | 0.010643119 | +| clip_fraction | 0.302 | +| clip_range | 0.0723 | +| entropy_loss | -6.32 | +| explained_variance | 0.425 | +| learning_rate | 4.74e-05 | +| loss | -0.028 | +| n_updates | 37232 | +| policy_gradient_loss | -0.0147 | +| value_loss | 0.000283 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1420 | +| iterations | 5355 | +| time_elapsed | 7720 | +| total_timesteps | 10967040 | +| train/ | | +| approx_kl | 0.009153504 | +| clip_fraction | 0.295 | +| clip_range | 0.0723 | +| entropy_loss | -6.69 | +| explained_variance | 0.384 | +| learning_rate | 4.74e-05 | +| loss | -0.0316 | +| n_updates | 37236 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000188 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1420 | +| iterations | 5356 | +| time_elapsed | 7721 | +| total_timesteps | 10969088 | +| train/ | | +| approx_kl | 0.010641275 | +| clip_fraction | 0.316 | +| clip_range | 0.0723 | +| entropy_loss | -6.89 | +| explained_variance | 0.16 | +| learning_rate | 4.74e-05 | +| loss | -0.0283 | +| n_updates | 37240 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000137 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1420 | +| iterations | 5357 | +| time_elapsed | 7722 | +| total_timesteps | 10971136 | +| train/ | | +| approx_kl | 0.0100826565 | +| clip_fraction | 0.319 | +| clip_range | 0.0723 | +| entropy_loss | -7.09 | +| explained_variance | 0.226 | +| learning_rate | 4.74e-05 | +| loss | -0.0302 | +| n_updates | 37244 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000182 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1420 | +| iterations | 5358 | +| time_elapsed | 7724 | +| total_timesteps | 10973184 | +| train/ | | +| approx_kl | 0.011500727 | +| clip_fraction | 0.324 | +| clip_range | 0.0723 | +| entropy_loss | -7.07 | +| explained_variance | 0.0897 | +| learning_rate | 4.74e-05 | +| loss | -0.0347 | +| n_updates | 37248 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000121 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1420 | +| iterations | 5359 | +| time_elapsed | 7725 | +| total_timesteps | 10975232 | +| train/ | | +| approx_kl | 0.009258477 | +| clip_fraction | 0.273 | +| clip_range | 0.0723 | +| entropy_loss | -6.75 | +| explained_variance | 0.214 | +| learning_rate | 4.74e-05 | +| loss | -0.0264 | +| n_updates | 37252 | +| policy_gradient_loss | -0.0148 | +| value_loss | 0.000244 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1420 | +| iterations | 5360 | +| time_elapsed | 7727 | +| total_timesteps | 10977280 | +| train/ | | +| approx_kl | 0.01161633 | +| clip_fraction | 0.307 | +| clip_range | 0.0723 | +| entropy_loss | -6.72 | +| explained_variance | 0.0651 | +| learning_rate | 4.74e-05 | +| loss | -0.0266 | +| n_updates | 37256 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000509 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1420 | +| iterations | 5361 | +| time_elapsed | 7728 | +| total_timesteps | 10979328 | +| train/ | | +| approx_kl | 0.010832875 | +| clip_fraction | 0.335 | +| clip_range | 0.0723 | +| entropy_loss | -6.96 | +| explained_variance | 0.261 | +| learning_rate | 4.74e-05 | +| loss | -0.0291 | +| n_updates | 37260 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000133 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1420 | +| iterations | 5362 | +| time_elapsed | 7729 | +| total_timesteps | 10981376 | +| train/ | | +| approx_kl | 0.009686539 | +| clip_fraction | 0.318 | +| clip_range | 0.0723 | +| entropy_loss | -7.37 | +| explained_variance | -0.0761 | +| learning_rate | 4.74e-05 | +| loss | -0.0335 | +| n_updates | 37264 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000237 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1420 | +| iterations | 5363 | +| time_elapsed | 7731 | +| total_timesteps | 10983424 | +| train/ | | +| approx_kl | 0.011515418 | +| clip_fraction | 0.334 | +| clip_range | 0.0723 | +| entropy_loss | -7.17 | +| explained_variance | 0.42 | +| learning_rate | 4.74e-05 | +| loss | -0.0377 | +| n_updates | 37268 | +| policy_gradient_loss | -0.0217 | +| value_loss | 9.13e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1420 | +| iterations | 5364 | +| time_elapsed | 7732 | +| total_timesteps | 10985472 | +| train/ | | +| approx_kl | 0.00852251 | +| clip_fraction | 0.284 | +| clip_range | 0.0723 | +| entropy_loss | -7.33 | +| explained_variance | -0.0212 | +| learning_rate | 4.74e-05 | +| loss | -0.0275 | +| n_updates | 37272 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.00031 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1420 | +| iterations | 5365 | +| time_elapsed | 7734 | +| total_timesteps | 10987520 | +| train/ | | +| approx_kl | 0.011657564 | +| clip_fraction | 0.294 | +| clip_range | 0.0723 | +| entropy_loss | -7.08 | +| explained_variance | 0.213 | +| learning_rate | 4.74e-05 | +| loss | -0.0344 | +| n_updates | 37276 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000231 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.385 | +| time/ | | +| fps | 1420 | +| iterations | 5366 | +| time_elapsed | 7735 | +| total_timesteps | 10989568 | +| train/ | | +| approx_kl | 0.01047801 | +| clip_fraction | 0.338 | +| clip_range | 0.0723 | +| entropy_loss | -7.44 | +| explained_variance | -0.191 | +| learning_rate | 4.74e-05 | +| loss | -0.039 | +| n_updates | 37280 | +| policy_gradient_loss | -0.0224 | +| value_loss | 0.00013 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.385 | +| time/ | | +| fps | 1420 | +| iterations | 5367 | +| time_elapsed | 7736 | +| total_timesteps | 10991616 | +| train/ | | +| approx_kl | 0.010551173 | +| clip_fraction | 0.297 | +| clip_range | 0.0723 | +| entropy_loss | -6.92 | +| explained_variance | 0.382 | +| learning_rate | 4.74e-05 | +| loss | -0.0219 | +| n_updates | 37284 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000233 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.385 | +| time/ | | +| fps | 1420 | +| iterations | 5368 | +| time_elapsed | 7738 | +| total_timesteps | 10993664 | +| train/ | | +| approx_kl | 0.009838573 | +| clip_fraction | 0.309 | +| clip_range | 0.0723 | +| entropy_loss | -6.77 | +| explained_variance | 0.461 | +| learning_rate | 4.74e-05 | +| loss | -0.0368 | +| n_updates | 37288 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.00016 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1420 | +| iterations | 5369 | +| time_elapsed | 7739 | +| total_timesteps | 10995712 | +| train/ | | +| approx_kl | 0.011901822 | +| clip_fraction | 0.334 | +| clip_range | 0.0723 | +| entropy_loss | -7.27 | +| explained_variance | -0.257 | +| learning_rate | 4.74e-05 | +| loss | -0.0375 | +| n_updates | 37292 | +| policy_gradient_loss | -0.0223 | +| value_loss | 7.62e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1420 | +| iterations | 5370 | +| time_elapsed | 7741 | +| total_timesteps | 10997760 | +| train/ | | +| approx_kl | 0.012253919 | +| clip_fraction | 0.304 | +| clip_range | 0.0723 | +| entropy_loss | -7.16 | +| explained_variance | -0.0124 | +| learning_rate | 4.74e-05 | +| loss | -0.0252 | +| n_updates | 37296 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000215 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1420 | +| iterations | 5371 | +| time_elapsed | 7742 | +| total_timesteps | 10999808 | +| train/ | | +| approx_kl | 0.012134652 | +| clip_fraction | 0.318 | +| clip_range | 0.0723 | +| entropy_loss | -6.93 | +| explained_variance | 0.236 | +| learning_rate | 4.74e-05 | +| loss | -0.0304 | +| n_updates | 37300 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000185 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1420 | +| iterations | 5372 | +| time_elapsed | 7744 | +| total_timesteps | 11001856 | +| train/ | | +| approx_kl | 0.010001367 | +| clip_fraction | 0.301 | +| clip_range | 0.0723 | +| entropy_loss | -6.86 | +| explained_variance | 0.357 | +| learning_rate | 4.74e-05 | +| loss | -0.0261 | +| n_updates | 37304 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.00024 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1420 | +| iterations | 5373 | +| time_elapsed | 7745 | +| total_timesteps | 11003904 | +| train/ | | +| approx_kl | 0.010081628 | +| clip_fraction | 0.305 | +| clip_range | 0.0722 | +| entropy_loss | -6.95 | +| explained_variance | 0.431 | +| learning_rate | 4.74e-05 | +| loss | -0.031 | +| n_updates | 37308 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000165 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1420 | +| iterations | 5374 | +| time_elapsed | 7746 | +| total_timesteps | 11005952 | +| train/ | | +| approx_kl | 0.011453196 | +| clip_fraction | 0.331 | +| clip_range | 0.0722 | +| entropy_loss | -7.09 | +| explained_variance | 0.446 | +| learning_rate | 4.74e-05 | +| loss | -0.0328 | +| n_updates | 37312 | +| policy_gradient_loss | -0.0214 | +| value_loss | 9.32e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1420 | +| iterations | 5375 | +| time_elapsed | 7748 | +| total_timesteps | 11008000 | +| train/ | | +| approx_kl | 0.011470065 | +| clip_fraction | 0.316 | +| clip_range | 0.0722 | +| entropy_loss | -7.26 | +| explained_variance | 0.021 | +| learning_rate | 4.74e-05 | +| loss | -0.03 | +| n_updates | 37316 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000107 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1420 | +| iterations | 5376 | +| time_elapsed | 7749 | +| total_timesteps | 11010048 | +| train/ | | +| approx_kl | 0.009599694 | +| clip_fraction | 0.312 | +| clip_range | 0.0722 | +| entropy_loss | -6.96 | +| explained_variance | 0.26 | +| learning_rate | 4.74e-05 | +| loss | -0.0295 | +| n_updates | 37320 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.00028 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1420 | +| iterations | 5377 | +| time_elapsed | 7751 | +| total_timesteps | 11012096 | +| train/ | | +| approx_kl | 0.012179924 | +| clip_fraction | 0.317 | +| clip_range | 0.0722 | +| entropy_loss | -6.59 | +| explained_variance | 0.578 | +| learning_rate | 4.74e-05 | +| loss | -0.0285 | +| n_updates | 37324 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000145 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1420 | +| iterations | 5378 | +| time_elapsed | 7752 | +| total_timesteps | 11014144 | +| train/ | | +| approx_kl | 0.009870222 | +| clip_fraction | 0.298 | +| clip_range | 0.0722 | +| entropy_loss | -7.26 | +| explained_variance | -0.0485 | +| learning_rate | 4.74e-05 | +| loss | -0.0305 | +| n_updates | 37328 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000207 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1420 | +| iterations | 5379 | +| time_elapsed | 7754 | +| total_timesteps | 11016192 | +| train/ | | +| approx_kl | 0.010214483 | +| clip_fraction | 0.281 | +| clip_range | 0.0722 | +| entropy_loss | -7.28 | +| explained_variance | -0.103 | +| learning_rate | 4.74e-05 | +| loss | -0.0289 | +| n_updates | 37332 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000203 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1420 | +| iterations | 5380 | +| time_elapsed | 7755 | +| total_timesteps | 11018240 | +| train/ | | +| approx_kl | 0.009452211 | +| clip_fraction | 0.277 | +| clip_range | 0.0722 | +| entropy_loss | -6.83 | +| explained_variance | 0.473 | +| learning_rate | 4.74e-05 | +| loss | -0.0293 | +| n_updates | 37336 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.00014 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1420 | +| iterations | 5381 | +| time_elapsed | 7757 | +| total_timesteps | 11020288 | +| train/ | | +| approx_kl | 0.00810929 | +| clip_fraction | 0.29 | +| clip_range | 0.0722 | +| entropy_loss | -6.86 | +| explained_variance | 0.377 | +| learning_rate | 4.74e-05 | +| loss | -0.0246 | +| n_updates | 37340 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000302 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1420 | +| iterations | 5382 | +| time_elapsed | 7758 | +| total_timesteps | 11022336 | +| train/ | | +| approx_kl | 0.013502218 | +| clip_fraction | 0.333 | +| clip_range | 0.0722 | +| entropy_loss | -7.24 | +| explained_variance | -0.356 | +| learning_rate | 4.74e-05 | +| loss | -0.0368 | +| n_updates | 37344 | +| policy_gradient_loss | -0.0237 | +| value_loss | 6.82e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1420 | +| iterations | 5383 | +| time_elapsed | 7759 | +| total_timesteps | 11024384 | +| train/ | | +| approx_kl | 0.010674781 | +| clip_fraction | 0.341 | +| clip_range | 0.0722 | +| entropy_loss | -7.16 | +| explained_variance | 0.288 | +| learning_rate | 4.74e-05 | +| loss | -0.0313 | +| n_updates | 37348 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000156 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1420 | +| iterations | 5384 | +| time_elapsed | 7761 | +| total_timesteps | 11026432 | +| train/ | | +| approx_kl | 0.010983458 | +| clip_fraction | 0.33 | +| clip_range | 0.0722 | +| entropy_loss | -7.1 | +| explained_variance | -0.0633 | +| learning_rate | 4.74e-05 | +| loss | -0.0267 | +| n_updates | 37352 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000276 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1420 | +| iterations | 5385 | +| time_elapsed | 7762 | +| total_timesteps | 11028480 | +| train/ | | +| approx_kl | 0.012459781 | +| clip_fraction | 0.311 | +| clip_range | 0.0722 | +| entropy_loss | -7.18 | +| explained_variance | -0.167 | +| learning_rate | 4.74e-05 | +| loss | -0.0305 | +| n_updates | 37356 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000186 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1420 | +| iterations | 5386 | +| time_elapsed | 7764 | +| total_timesteps | 11030528 | +| train/ | | +| approx_kl | 0.011354722 | +| clip_fraction | 0.342 | +| clip_range | 0.0722 | +| entropy_loss | -6.86 | +| explained_variance | 0.365 | +| learning_rate | 4.74e-05 | +| loss | -0.0293 | +| n_updates | 37360 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000106 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1420 | +| iterations | 5387 | +| time_elapsed | 7765 | +| total_timesteps | 11032576 | +| train/ | | +| approx_kl | 0.011360161 | +| clip_fraction | 0.312 | +| clip_range | 0.0722 | +| entropy_loss | -7.07 | +| explained_variance | 0.142 | +| learning_rate | 4.74e-05 | +| loss | -0.028 | +| n_updates | 37364 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000363 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1420 | +| iterations | 5388 | +| time_elapsed | 7767 | +| total_timesteps | 11034624 | +| train/ | | +| approx_kl | 0.012348486 | +| clip_fraction | 0.352 | +| clip_range | 0.0722 | +| entropy_loss | -7.31 | +| explained_variance | -0.238 | +| learning_rate | 4.74e-05 | +| loss | -0.0384 | +| n_updates | 37368 | +| policy_gradient_loss | -0.0246 | +| value_loss | 0.000117 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1420 | +| iterations | 5389 | +| time_elapsed | 7768 | +| total_timesteps | 11036672 | +| train/ | | +| approx_kl | 0.010014239 | +| clip_fraction | 0.286 | +| clip_range | 0.0722 | +| entropy_loss | -6.86 | +| explained_variance | 0.295 | +| learning_rate | 4.74e-05 | +| loss | -0.0295 | +| n_updates | 37372 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000251 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1420 | +| iterations | 5390 | +| time_elapsed | 7769 | +| total_timesteps | 11038720 | +| train/ | | +| approx_kl | 0.012032535 | +| clip_fraction | 0.341 | +| clip_range | 0.0722 | +| entropy_loss | -6.72 | +| explained_variance | 0.374 | +| learning_rate | 4.74e-05 | +| loss | -0.0404 | +| n_updates | 37376 | +| policy_gradient_loss | -0.0207 | +| value_loss | 9.42e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1420 | +| iterations | 5391 | +| time_elapsed | 7771 | +| total_timesteps | 11040768 | +| train/ | | +| approx_kl | 0.0118553955 | +| clip_fraction | 0.314 | +| clip_range | 0.0722 | +| entropy_loss | -6.95 | +| explained_variance | 0.322 | +| learning_rate | 4.74e-05 | +| loss | -0.0302 | +| n_updates | 37380 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000143 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1420 | +| iterations | 5392 | +| time_elapsed | 7772 | +| total_timesteps | 11042816 | +| train/ | | +| approx_kl | 0.010700133 | +| clip_fraction | 0.289 | +| clip_range | 0.0722 | +| entropy_loss | -7.27 | +| explained_variance | 0.31 | +| learning_rate | 4.74e-05 | +| loss | -0.0323 | +| n_updates | 37384 | +| policy_gradient_loss | -0.0181 | +| value_loss | 9.01e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1420 | +| iterations | 5393 | +| time_elapsed | 7774 | +| total_timesteps | 11044864 | +| train/ | | +| approx_kl | 0.011299035 | +| clip_fraction | 0.315 | +| clip_range | 0.0722 | +| entropy_loss | -7.07 | +| explained_variance | 0.504 | +| learning_rate | 4.74e-05 | +| loss | -0.0357 | +| n_updates | 37388 | +| policy_gradient_loss | -0.0197 | +| value_loss | 9.61e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1420 | +| iterations | 5394 | +| time_elapsed | 7775 | +| total_timesteps | 11046912 | +| train/ | | +| approx_kl | 0.010931784 | +| clip_fraction | 0.306 | +| clip_range | 0.0722 | +| entropy_loss | -7.17 | +| explained_variance | -0.131 | +| learning_rate | 4.74e-05 | +| loss | -0.03 | +| n_updates | 37392 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000125 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1420 | +| iterations | 5395 | +| time_elapsed | 7777 | +| total_timesteps | 11048960 | +| train/ | | +| approx_kl | 0.010975396 | +| clip_fraction | 0.317 | +| clip_range | 0.0722 | +| entropy_loss | -7.13 | +| explained_variance | 0.299 | +| learning_rate | 4.74e-05 | +| loss | -0.0309 | +| n_updates | 37396 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000162 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1420 | +| iterations | 5396 | +| time_elapsed | 7778 | +| total_timesteps | 11051008 | +| train/ | | +| approx_kl | 0.012221183 | +| clip_fraction | 0.317 | +| clip_range | 0.0722 | +| entropy_loss | -6.9 | +| explained_variance | 0.293 | +| learning_rate | 4.74e-05 | +| loss | -0.0292 | +| n_updates | 37400 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000131 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1420 | +| iterations | 5397 | +| time_elapsed | 7779 | +| total_timesteps | 11053056 | +| train/ | | +| approx_kl | 0.0108517725 | +| clip_fraction | 0.323 | +| clip_range | 0.0722 | +| entropy_loss | -6.69 | +| explained_variance | 0.537 | +| learning_rate | 4.74e-05 | +| loss | -0.0309 | +| n_updates | 37404 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000176 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1420 | +| iterations | 5398 | +| time_elapsed | 7781 | +| total_timesteps | 11055104 | +| train/ | | +| approx_kl | 0.009829758 | +| clip_fraction | 0.324 | +| clip_range | 0.0722 | +| entropy_loss | -7.48 | +| explained_variance | -0.224 | +| learning_rate | 4.74e-05 | +| loss | -0.0269 | +| n_updates | 37408 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000105 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1420 | +| iterations | 5399 | +| time_elapsed | 7782 | +| total_timesteps | 11057152 | +| train/ | | +| approx_kl | 0.01112955 | +| clip_fraction | 0.308 | +| clip_range | 0.0722 | +| entropy_loss | -7.27 | +| explained_variance | -0.022 | +| learning_rate | 4.74e-05 | +| loss | -0.0278 | +| n_updates | 37412 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000241 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1420 | +| iterations | 5400 | +| time_elapsed | 7784 | +| total_timesteps | 11059200 | +| train/ | | +| approx_kl | 0.010917025 | +| clip_fraction | 0.329 | +| clip_range | 0.0722 | +| entropy_loss | -6.71 | +| explained_variance | 0.655 | +| learning_rate | 4.74e-05 | +| loss | -0.0339 | +| n_updates | 37416 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000115 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1420 | +| iterations | 5401 | +| time_elapsed | 7785 | +| total_timesteps | 11061248 | +| train/ | | +| approx_kl | 0.010403427 | +| clip_fraction | 0.348 | +| clip_range | 0.0722 | +| entropy_loss | -7.29 | +| explained_variance | 0.554 | +| learning_rate | 4.74e-05 | +| loss | -0.0357 | +| n_updates | 37420 | +| policy_gradient_loss | -0.0224 | +| value_loss | 6.79e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1420 | +| iterations | 5402 | +| time_elapsed | 7787 | +| total_timesteps | 11063296 | +| train/ | | +| approx_kl | 0.01080428 | +| clip_fraction | 0.308 | +| clip_range | 0.0722 | +| entropy_loss | -6.81 | +| explained_variance | 0.104 | +| learning_rate | 4.74e-05 | +| loss | -0.0202 | +| n_updates | 37424 | +| policy_gradient_loss | -0.0148 | +| value_loss | 0.000298 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1420 | +| iterations | 5403 | +| time_elapsed | 7788 | +| total_timesteps | 11065344 | +| train/ | | +| approx_kl | 0.010552308 | +| clip_fraction | 0.316 | +| clip_range | 0.0722 | +| entropy_loss | -6.99 | +| explained_variance | 0.386 | +| learning_rate | 4.74e-05 | +| loss | -0.0316 | +| n_updates | 37428 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.00015 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1420 | +| iterations | 5404 | +| time_elapsed | 7789 | +| total_timesteps | 11067392 | +| train/ | | +| approx_kl | 0.009595001 | +| clip_fraction | 0.307 | +| clip_range | 0.0722 | +| entropy_loss | -6.89 | +| explained_variance | 0.432 | +| learning_rate | 4.74e-05 | +| loss | -0.0292 | +| n_updates | 37432 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.00024 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1420 | +| iterations | 5405 | +| time_elapsed | 7791 | +| total_timesteps | 11069440 | +| train/ | | +| approx_kl | 0.011246743 | +| clip_fraction | 0.303 | +| clip_range | 0.0722 | +| entropy_loss | -7.22 | +| explained_variance | -0.247 | +| learning_rate | 4.74e-05 | +| loss | -0.0275 | +| n_updates | 37436 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000127 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1420 | +| iterations | 5406 | +| time_elapsed | 7792 | +| total_timesteps | 11071488 | +| train/ | | +| approx_kl | 0.0112145655 | +| clip_fraction | 0.313 | +| clip_range | 0.0722 | +| entropy_loss | -6.85 | +| explained_variance | 0.44 | +| learning_rate | 4.74e-05 | +| loss | -0.0297 | +| n_updates | 37440 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000136 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1420 | +| iterations | 5407 | +| time_elapsed | 7794 | +| total_timesteps | 11073536 | +| train/ | | +| approx_kl | 0.010080754 | +| clip_fraction | 0.302 | +| clip_range | 0.0722 | +| entropy_loss | -6.57 | +| explained_variance | 0.376 | +| learning_rate | 4.74e-05 | +| loss | -0.0318 | +| n_updates | 37444 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000341 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1420 | +| iterations | 5408 | +| time_elapsed | 7795 | +| total_timesteps | 11075584 | +| train/ | | +| approx_kl | 0.012252215 | +| clip_fraction | 0.351 | +| clip_range | 0.0722 | +| entropy_loss | -6.96 | +| explained_variance | 0.387 | +| learning_rate | 4.74e-05 | +| loss | -0.0341 | +| n_updates | 37448 | +| policy_gradient_loss | -0.0228 | +| value_loss | 9.13e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1420 | +| iterations | 5409 | +| time_elapsed | 7796 | +| total_timesteps | 11077632 | +| train/ | | +| approx_kl | 0.011441683 | +| clip_fraction | 0.324 | +| clip_range | 0.0722 | +| entropy_loss | -6.99 | +| explained_variance | 0.277 | +| learning_rate | 4.74e-05 | +| loss | -0.0338 | +| n_updates | 37452 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000172 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1420 | +| iterations | 5410 | +| time_elapsed | 7798 | +| total_timesteps | 11079680 | +| train/ | | +| approx_kl | 0.010202655 | +| clip_fraction | 0.31 | +| clip_range | 0.0722 | +| entropy_loss | -6.85 | +| explained_variance | 0.3 | +| learning_rate | 4.74e-05 | +| loss | -0.0305 | +| n_updates | 37456 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000246 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1420 | +| iterations | 5411 | +| time_elapsed | 7799 | +| total_timesteps | 11081728 | +| train/ | | +| approx_kl | 0.0114127295 | +| clip_fraction | 0.333 | +| clip_range | 0.0722 | +| entropy_loss | -7.25 | +| explained_variance | -0.123 | +| learning_rate | 4.74e-05 | +| loss | -0.0372 | +| n_updates | 37460 | +| policy_gradient_loss | -0.0222 | +| value_loss | 0.000171 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1420 | +| iterations | 5412 | +| time_elapsed | 7801 | +| total_timesteps | 11083776 | +| train/ | | +| approx_kl | 0.010384778 | +| clip_fraction | 0.337 | +| clip_range | 0.0722 | +| entropy_loss | -7.51 | +| explained_variance | -0.225 | +| learning_rate | 4.74e-05 | +| loss | -0.0334 | +| n_updates | 37464 | +| policy_gradient_loss | -0.0219 | +| value_loss | 0.000163 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1420 | +| iterations | 5413 | +| time_elapsed | 7802 | +| total_timesteps | 11085824 | +| train/ | | +| approx_kl | 0.011125134 | +| clip_fraction | 0.32 | +| clip_range | 0.0722 | +| entropy_loss | -7.16 | +| explained_variance | 0.246 | +| learning_rate | 4.74e-05 | +| loss | -0.0256 | +| n_updates | 37468 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000214 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1420 | +| iterations | 5414 | +| time_elapsed | 7804 | +| total_timesteps | 11087872 | +| train/ | | +| approx_kl | 0.009305289 | +| clip_fraction | 0.302 | +| clip_range | 0.0722 | +| entropy_loss | -7.04 | +| explained_variance | 0.476 | +| learning_rate | 4.74e-05 | +| loss | -0.0318 | +| n_updates | 37472 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000171 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1420 | +| iterations | 5415 | +| time_elapsed | 7805 | +| total_timesteps | 11089920 | +| train/ | | +| approx_kl | 0.009637299 | +| clip_fraction | 0.311 | +| clip_range | 0.0722 | +| entropy_loss | -7.17 | +| explained_variance | 0.175 | +| learning_rate | 4.74e-05 | +| loss | -0.0283 | +| n_updates | 37476 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000199 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1420 | +| iterations | 5416 | +| time_elapsed | 7807 | +| total_timesteps | 11091968 | +| train/ | | +| approx_kl | 0.011740918 | +| clip_fraction | 0.328 | +| clip_range | 0.0722 | +| entropy_loss | -7.08 | +| explained_variance | 0.144 | +| learning_rate | 4.74e-05 | +| loss | -0.0318 | +| n_updates | 37480 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000248 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1420 | +| iterations | 5417 | +| time_elapsed | 7808 | +| total_timesteps | 11094016 | +| train/ | | +| approx_kl | 0.011060502 | +| clip_fraction | 0.338 | +| clip_range | 0.0722 | +| entropy_loss | -6.49 | +| explained_variance | 0.651 | +| learning_rate | 4.74e-05 | +| loss | -0.0242 | +| n_updates | 37484 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000111 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1420 | +| iterations | 5418 | +| time_elapsed | 7809 | +| total_timesteps | 11096064 | +| train/ | | +| approx_kl | 0.01159603 | +| clip_fraction | 0.352 | +| clip_range | 0.0722 | +| entropy_loss | -6.93 | +| explained_variance | 0.465 | +| learning_rate | 4.74e-05 | +| loss | -0.032 | +| n_updates | 37488 | +| policy_gradient_loss | -0.0219 | +| value_loss | 7.86e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1420 | +| iterations | 5419 | +| time_elapsed | 7811 | +| total_timesteps | 11098112 | +| train/ | | +| approx_kl | 0.013450976 | +| clip_fraction | 0.305 | +| clip_range | 0.0722 | +| entropy_loss | -6.83 | +| explained_variance | 0.323 | +| learning_rate | 4.74e-05 | +| loss | -0.0329 | +| n_updates | 37492 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000186 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1420 | +| iterations | 5420 | +| time_elapsed | 7812 | +| total_timesteps | 11100160 | +| train/ | | +| approx_kl | 0.012219757 | +| clip_fraction | 0.335 | +| clip_range | 0.0722 | +| entropy_loss | -6.93 | +| explained_variance | 0.266 | +| learning_rate | 4.74e-05 | +| loss | -0.0301 | +| n_updates | 37496 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000251 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1420 | +| iterations | 5421 | +| time_elapsed | 7814 | +| total_timesteps | 11102208 | +| train/ | | +| approx_kl | 0.011672395 | +| clip_fraction | 0.317 | +| clip_range | 0.0722 | +| entropy_loss | -6.85 | +| explained_variance | 0.299 | +| learning_rate | 4.74e-05 | +| loss | -0.0189 | +| n_updates | 37500 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000311 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1420 | +| iterations | 5422 | +| time_elapsed | 7815 | +| total_timesteps | 11104256 | +| train/ | | +| approx_kl | 0.01221216 | +| clip_fraction | 0.326 | +| clip_range | 0.0722 | +| entropy_loss | -6.83 | +| explained_variance | 0.342 | +| learning_rate | 4.74e-05 | +| loss | -0.0357 | +| n_updates | 37504 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000143 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1420 | +| iterations | 5423 | +| time_elapsed | 7817 | +| total_timesteps | 11106304 | +| train/ | | +| approx_kl | 0.011444195 | +| clip_fraction | 0.329 | +| clip_range | 0.0722 | +| entropy_loss | -7.09 | +| explained_variance | 0.129 | +| learning_rate | 4.74e-05 | +| loss | -0.0307 | +| n_updates | 37508 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000226 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1420 | +| iterations | 5424 | +| time_elapsed | 7818 | +| total_timesteps | 11108352 | +| train/ | | +| approx_kl | 0.011274864 | +| clip_fraction | 0.307 | +| clip_range | 0.0722 | +| entropy_loss | -6.99 | +| explained_variance | 0.244 | +| learning_rate | 4.74e-05 | +| loss | -0.0331 | +| n_updates | 37512 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000161 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1420 | +| iterations | 5425 | +| time_elapsed | 7820 | +| total_timesteps | 11110400 | +| train/ | | +| approx_kl | 0.0106765935 | +| clip_fraction | 0.339 | +| clip_range | 0.0722 | +| entropy_loss | -7.27 | +| explained_variance | 0.0991 | +| learning_rate | 4.74e-05 | +| loss | -0.0332 | +| n_updates | 37516 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000101 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1420 | +| iterations | 5426 | +| time_elapsed | 7821 | +| total_timesteps | 11112448 | +| train/ | | +| approx_kl | 0.010301455 | +| clip_fraction | 0.307 | +| clip_range | 0.0722 | +| entropy_loss | -7.17 | +| explained_variance | 0.267 | +| learning_rate | 4.74e-05 | +| loss | -0.0315 | +| n_updates | 37520 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000173 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1420 | +| iterations | 5427 | +| time_elapsed | 7822 | +| total_timesteps | 11114496 | +| train/ | | +| approx_kl | 0.011732468 | +| clip_fraction | 0.333 | +| clip_range | 0.0722 | +| entropy_loss | -7.31 | +| explained_variance | -0.245 | +| learning_rate | 4.74e-05 | +| loss | -0.0297 | +| n_updates | 37524 | +| policy_gradient_loss | -0.0226 | +| value_loss | 8.45e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1420 | +| iterations | 5428 | +| time_elapsed | 7824 | +| total_timesteps | 11116544 | +| train/ | | +| approx_kl | 0.012652072 | +| clip_fraction | 0.331 | +| clip_range | 0.0722 | +| entropy_loss | -6.99 | +| explained_variance | 0.592 | +| learning_rate | 4.74e-05 | +| loss | -0.0264 | +| n_updates | 37528 | +| policy_gradient_loss | -0.0201 | +| value_loss | 8.25e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1420 | +| iterations | 5429 | +| time_elapsed | 7825 | +| total_timesteps | 11118592 | +| train/ | | +| approx_kl | 0.013148317 | +| clip_fraction | 0.333 | +| clip_range | 0.0722 | +| entropy_loss | -6.81 | +| explained_variance | 0.53 | +| learning_rate | 4.74e-05 | +| loss | -0.0295 | +| n_updates | 37532 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000117 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1420 | +| iterations | 5430 | +| time_elapsed | 7827 | +| total_timesteps | 11120640 | +| train/ | | +| approx_kl | 0.01321782 | +| clip_fraction | 0.31 | +| clip_range | 0.0722 | +| entropy_loss | -6.77 | +| explained_variance | -0.108 | +| learning_rate | 4.74e-05 | +| loss | -0.0183 | +| n_updates | 37536 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000128 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1420 | +| iterations | 5431 | +| time_elapsed | 7828 | +| total_timesteps | 11122688 | +| train/ | | +| approx_kl | 0.011983987 | +| clip_fraction | 0.347 | +| clip_range | 0.0722 | +| entropy_loss | -6.7 | +| explained_variance | 0.708 | +| learning_rate | 4.74e-05 | +| loss | -0.0299 | +| n_updates | 37540 | +| policy_gradient_loss | -0.0208 | +| value_loss | 4.48e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1420 | +| iterations | 5432 | +| time_elapsed | 7830 | +| total_timesteps | 11124736 | +| train/ | | +| approx_kl | 0.012439938 | +| clip_fraction | 0.329 | +| clip_range | 0.0722 | +| entropy_loss | -6.56 | +| explained_variance | 0.526 | +| learning_rate | 4.74e-05 | +| loss | -0.027 | +| n_updates | 37544 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000149 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1420 | +| iterations | 5433 | +| time_elapsed | 7831 | +| total_timesteps | 11126784 | +| train/ | | +| approx_kl | 0.014256413 | +| clip_fraction | 0.316 | +| clip_range | 0.0722 | +| entropy_loss | -7.03 | +| explained_variance | 0.245 | +| learning_rate | 4.74e-05 | +| loss | -0.0297 | +| n_updates | 37548 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000221 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1420 | +| iterations | 5434 | +| time_elapsed | 7832 | +| total_timesteps | 11128832 | +| train/ | | +| approx_kl | 0.012587058 | +| clip_fraction | 0.344 | +| clip_range | 0.0722 | +| entropy_loss | -7.41 | +| explained_variance | -0.277 | +| learning_rate | 4.74e-05 | +| loss | -0.0337 | +| n_updates | 37552 | +| policy_gradient_loss | -0.0218 | +| value_loss | 7.44e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1420 | +| iterations | 5435 | +| time_elapsed | 7834 | +| total_timesteps | 11130880 | +| train/ | | +| approx_kl | 0.010930415 | +| clip_fraction | 0.313 | +| clip_range | 0.0722 | +| entropy_loss | -7.16 | +| explained_variance | 0.264 | +| learning_rate | 4.74e-05 | +| loss | -0.0294 | +| n_updates | 37556 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000212 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1420 | +| iterations | 5436 | +| time_elapsed | 7835 | +| total_timesteps | 11132928 | +| train/ | | +| approx_kl | 0.009956944 | +| clip_fraction | 0.319 | +| clip_range | 0.0722 | +| entropy_loss | -7.35 | +| explained_variance | 0.106 | +| learning_rate | 4.74e-05 | +| loss | -0.0295 | +| n_updates | 37560 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000182 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1420 | +| iterations | 5437 | +| time_elapsed | 7837 | +| total_timesteps | 11134976 | +| train/ | | +| approx_kl | 0.011463366 | +| clip_fraction | 0.339 | +| clip_range | 0.0722 | +| entropy_loss | -6.82 | +| explained_variance | 0.2 | +| learning_rate | 4.74e-05 | +| loss | -0.0324 | +| n_updates | 37564 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000171 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1420 | +| iterations | 5438 | +| time_elapsed | 7838 | +| total_timesteps | 11137024 | +| train/ | | +| approx_kl | 0.0120635405 | +| clip_fraction | 0.315 | +| clip_range | 0.0722 | +| entropy_loss | -6.81 | +| explained_variance | 0.342 | +| learning_rate | 4.74e-05 | +| loss | -0.0272 | +| n_updates | 37568 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000231 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1420 | +| iterations | 5439 | +| time_elapsed | 7840 | +| total_timesteps | 11139072 | +| train/ | | +| approx_kl | 0.009809753 | +| clip_fraction | 0.319 | +| clip_range | 0.0722 | +| entropy_loss | -6.82 | +| explained_variance | 0.519 | +| learning_rate | 4.74e-05 | +| loss | -0.0306 | +| n_updates | 37572 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000146 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1420 | +| iterations | 5440 | +| time_elapsed | 7841 | +| total_timesteps | 11141120 | +| train/ | | +| approx_kl | 0.010331409 | +| clip_fraction | 0.311 | +| clip_range | 0.0722 | +| entropy_loss | -6.4 | +| explained_variance | 0.59 | +| learning_rate | 4.74e-05 | +| loss | -0.0202 | +| n_updates | 37576 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000199 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1420 | +| iterations | 5441 | +| time_elapsed | 7842 | +| total_timesteps | 11143168 | +| train/ | | +| approx_kl | 0.0118762385 | +| clip_fraction | 0.332 | +| clip_range | 0.0722 | +| entropy_loss | -7.11 | +| explained_variance | 0.411 | +| learning_rate | 4.74e-05 | +| loss | -0.0388 | +| n_updates | 37580 | +| policy_gradient_loss | -0.0207 | +| value_loss | 9.26e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1420 | +| iterations | 5442 | +| time_elapsed | 7844 | +| total_timesteps | 11145216 | +| train/ | | +| approx_kl | 0.012039065 | +| clip_fraction | 0.329 | +| clip_range | 0.0722 | +| entropy_loss | -7.22 | +| explained_variance | -0.23 | +| learning_rate | 4.74e-05 | +| loss | -0.0315 | +| n_updates | 37584 | +| policy_gradient_loss | -0.0218 | +| value_loss | 8.17e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1420 | +| iterations | 5443 | +| time_elapsed | 7845 | +| total_timesteps | 11147264 | +| train/ | | +| approx_kl | 0.010895072 | +| clip_fraction | 0.31 | +| clip_range | 0.0722 | +| entropy_loss | -7.14 | +| explained_variance | 0.202 | +| learning_rate | 4.74e-05 | +| loss | -0.027 | +| n_updates | 37588 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000254 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1420 | +| iterations | 5444 | +| time_elapsed | 7847 | +| total_timesteps | 11149312 | +| train/ | | +| approx_kl | 0.011296023 | +| clip_fraction | 0.304 | +| clip_range | 0.0722 | +| entropy_loss | -6.78 | +| explained_variance | 0.414 | +| learning_rate | 4.74e-05 | +| loss | -0.029 | +| n_updates | 37592 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000224 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1420 | +| iterations | 5445 | +| time_elapsed | 7848 | +| total_timesteps | 11151360 | +| train/ | | +| approx_kl | 0.011584856 | +| clip_fraction | 0.353 | +| clip_range | 0.0722 | +| entropy_loss | -7.09 | +| explained_variance | 0.13 | +| learning_rate | 4.74e-05 | +| loss | -0.0307 | +| n_updates | 37596 | +| policy_gradient_loss | -0.0214 | +| value_loss | 7.58e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1420 | +| iterations | 5446 | +| time_elapsed | 7850 | +| total_timesteps | 11153408 | +| train/ | | +| approx_kl | 0.013163331 | +| clip_fraction | 0.313 | +| clip_range | 0.0722 | +| entropy_loss | -7.06 | +| explained_variance | 0.19 | +| learning_rate | 4.74e-05 | +| loss | -0.029 | +| n_updates | 37600 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000191 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1420 | +| iterations | 5447 | +| time_elapsed | 7851 | +| total_timesteps | 11155456 | +| train/ | | +| approx_kl | 0.01132809 | +| clip_fraction | 0.33 | +| clip_range | 0.0722 | +| entropy_loss | -7.1 | +| explained_variance | 0.266 | +| learning_rate | 4.74e-05 | +| loss | -0.0246 | +| n_updates | 37604 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000177 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1420 | +| iterations | 5448 | +| time_elapsed | 7852 | +| total_timesteps | 11157504 | +| train/ | | +| approx_kl | 0.011553573 | +| clip_fraction | 0.305 | +| clip_range | 0.0722 | +| entropy_loss | -6.71 | +| explained_variance | 0.321 | +| learning_rate | 4.74e-05 | +| loss | -0.0262 | +| n_updates | 37608 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000284 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1420 | +| iterations | 5449 | +| time_elapsed | 7854 | +| total_timesteps | 11159552 | +| train/ | | +| approx_kl | 0.013040861 | +| clip_fraction | 0.342 | +| clip_range | 0.0722 | +| entropy_loss | -7.06 | +| explained_variance | 0.468 | +| learning_rate | 4.74e-05 | +| loss | -0.0382 | +| n_updates | 37612 | +| policy_gradient_loss | -0.0238 | +| value_loss | 9.18e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1420 | +| iterations | 5450 | +| time_elapsed | 7855 | +| total_timesteps | 11161600 | +| train/ | | +| approx_kl | 0.012560242 | +| clip_fraction | 0.336 | +| clip_range | 0.0722 | +| entropy_loss | -6.99 | +| explained_variance | 0.0978 | +| learning_rate | 4.73e-05 | +| loss | -0.0335 | +| n_updates | 37616 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000253 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1420 | +| iterations | 5451 | +| time_elapsed | 7857 | +| total_timesteps | 11163648 | +| train/ | | +| approx_kl | 0.0127811115 | +| clip_fraction | 0.324 | +| clip_range | 0.0722 | +| entropy_loss | -6.93 | +| explained_variance | 0.37 | +| learning_rate | 4.73e-05 | +| loss | -0.031 | +| n_updates | 37620 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000109 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1420 | +| iterations | 5452 | +| time_elapsed | 7858 | +| total_timesteps | 11165696 | +| train/ | | +| approx_kl | 0.011418629 | +| clip_fraction | 0.325 | +| clip_range | 0.0722 | +| entropy_loss | -6.84 | +| explained_variance | 0.309 | +| learning_rate | 4.73e-05 | +| loss | -0.0308 | +| n_updates | 37624 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000226 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1420 | +| iterations | 5453 | +| time_elapsed | 7860 | +| total_timesteps | 11167744 | +| train/ | | +| approx_kl | 0.011696011 | +| clip_fraction | 0.34 | +| clip_range | 0.0722 | +| entropy_loss | -7.01 | +| explained_variance | 0.31 | +| learning_rate | 4.73e-05 | +| loss | -0.0349 | +| n_updates | 37628 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000108 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1420 | +| iterations | 5454 | +| time_elapsed | 7861 | +| total_timesteps | 11169792 | +| train/ | | +| approx_kl | 0.010343777 | +| clip_fraction | 0.323 | +| clip_range | 0.0722 | +| entropy_loss | -7.09 | +| explained_variance | 0.505 | +| learning_rate | 4.73e-05 | +| loss | -0.0346 | +| n_updates | 37632 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000132 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1420 | +| iterations | 5455 | +| time_elapsed | 7863 | +| total_timesteps | 11171840 | +| train/ | | +| approx_kl | 0.010172633 | +| clip_fraction | 0.304 | +| clip_range | 0.0722 | +| entropy_loss | -7.09 | +| explained_variance | 0.37 | +| learning_rate | 4.73e-05 | +| loss | -0.0259 | +| n_updates | 37636 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000117 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1420 | +| iterations | 5456 | +| time_elapsed | 7864 | +| total_timesteps | 11173888 | +| train/ | | +| approx_kl | 0.009974796 | +| clip_fraction | 0.333 | +| clip_range | 0.0722 | +| entropy_loss | -7.31 | +| explained_variance | -0.214 | +| learning_rate | 4.73e-05 | +| loss | -0.0326 | +| n_updates | 37640 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000134 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1420 | +| iterations | 5457 | +| time_elapsed | 7866 | +| total_timesteps | 11175936 | +| train/ | | +| approx_kl | 0.011333107 | +| clip_fraction | 0.337 | +| clip_range | 0.0722 | +| entropy_loss | -7.35 | +| explained_variance | -0.0603 | +| learning_rate | 4.73e-05 | +| loss | -0.028 | +| n_updates | 37644 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.00015 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1420 | +| iterations | 5458 | +| time_elapsed | 7867 | +| total_timesteps | 11177984 | +| train/ | | +| approx_kl | 0.011082318 | +| clip_fraction | 0.315 | +| clip_range | 0.0722 | +| entropy_loss | -7.02 | +| explained_variance | 0.618 | +| learning_rate | 4.73e-05 | +| loss | -0.0309 | +| n_updates | 37648 | +| policy_gradient_loss | -0.0179 | +| value_loss | 6.9e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1420 | +| iterations | 5459 | +| time_elapsed | 7868 | +| total_timesteps | 11180032 | +| train/ | | +| approx_kl | 0.012301199 | +| clip_fraction | 0.309 | +| clip_range | 0.0722 | +| entropy_loss | -6.18 | +| explained_variance | 0.513 | +| learning_rate | 4.73e-05 | +| loss | -0.0149 | +| n_updates | 37652 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000208 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1420 | +| iterations | 5460 | +| time_elapsed | 7870 | +| total_timesteps | 11182080 | +| train/ | | +| approx_kl | 0.009093934 | +| clip_fraction | 0.285 | +| clip_range | 0.0722 | +| entropy_loss | -7.04 | +| explained_variance | -0.0533 | +| learning_rate | 4.73e-05 | +| loss | -0.0275 | +| n_updates | 37656 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000396 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1420 | +| iterations | 5461 | +| time_elapsed | 7871 | +| total_timesteps | 11184128 | +| train/ | | +| approx_kl | 0.011114201 | +| clip_fraction | 0.321 | +| clip_range | 0.0722 | +| entropy_loss | -6.58 | +| explained_variance | 0.419 | +| learning_rate | 4.73e-05 | +| loss | -0.0345 | +| n_updates | 37660 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000223 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1420 | +| iterations | 5462 | +| time_elapsed | 7873 | +| total_timesteps | 11186176 | +| train/ | | +| approx_kl | 0.01219645 | +| clip_fraction | 0.348 | +| clip_range | 0.0722 | +| entropy_loss | -6.99 | +| explained_variance | 0.262 | +| learning_rate | 4.73e-05 | +| loss | -0.0353 | +| n_updates | 37664 | +| policy_gradient_loss | -0.0221 | +| value_loss | 0.000157 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1420 | +| iterations | 5463 | +| time_elapsed | 7874 | +| total_timesteps | 11188224 | +| train/ | | +| approx_kl | 0.0127474405 | +| clip_fraction | 0.34 | +| clip_range | 0.0722 | +| entropy_loss | -6.87 | +| explained_variance | 0.539 | +| learning_rate | 4.73e-05 | +| loss | -0.0343 | +| n_updates | 37668 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000103 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1420 | +| iterations | 5464 | +| time_elapsed | 7876 | +| total_timesteps | 11190272 | +| train/ | | +| approx_kl | 0.011111837 | +| clip_fraction | 0.317 | +| clip_range | 0.0722 | +| entropy_loss | -7.14 | +| explained_variance | -0.147 | +| learning_rate | 4.73e-05 | +| loss | -0.0301 | +| n_updates | 37672 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.00012 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1420 | +| iterations | 5465 | +| time_elapsed | 7877 | +| total_timesteps | 11192320 | +| train/ | | +| approx_kl | 0.011224832 | +| clip_fraction | 0.316 | +| clip_range | 0.0722 | +| entropy_loss | -7.07 | +| explained_variance | 0.139 | +| learning_rate | 4.73e-05 | +| loss | -0.0316 | +| n_updates | 37676 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.00027 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1420 | +| iterations | 5466 | +| time_elapsed | 7878 | +| total_timesteps | 11194368 | +| train/ | | +| approx_kl | 0.009210173 | +| clip_fraction | 0.323 | +| clip_range | 0.0722 | +| entropy_loss | -7.03 | +| explained_variance | 0.349 | +| learning_rate | 4.73e-05 | +| loss | -0.0299 | +| n_updates | 37680 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000229 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1420 | +| iterations | 5467 | +| time_elapsed | 7880 | +| total_timesteps | 11196416 | +| train/ | | +| approx_kl | 0.009983847 | +| clip_fraction | 0.319 | +| clip_range | 0.0722 | +| entropy_loss | -7.1 | +| explained_variance | 0.313 | +| learning_rate | 4.73e-05 | +| loss | -0.0334 | +| n_updates | 37684 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000109 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1420 | +| iterations | 5468 | +| time_elapsed | 7881 | +| total_timesteps | 11198464 | +| train/ | | +| approx_kl | 0.00936982 | +| clip_fraction | 0.319 | +| clip_range | 0.0722 | +| entropy_loss | -7.27 | +| explained_variance | -0.00623 | +| learning_rate | 4.73e-05 | +| loss | -0.0332 | +| n_updates | 37688 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000205 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1420 | +| iterations | 5469 | +| time_elapsed | 7883 | +| total_timesteps | 11200512 | +| train/ | | +| approx_kl | 0.013818838 | +| clip_fraction | 0.33 | +| clip_range | 0.0722 | +| entropy_loss | -7.34 | +| explained_variance | -0.128 | +| learning_rate | 4.73e-05 | +| loss | -0.0344 | +| n_updates | 37692 | +| policy_gradient_loss | -0.0215 | +| value_loss | 6.88e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1420 | +| iterations | 5470 | +| time_elapsed | 7884 | +| total_timesteps | 11202560 | +| train/ | | +| approx_kl | 0.010398171 | +| clip_fraction | 0.323 | +| clip_range | 0.0722 | +| entropy_loss | -6.55 | +| explained_variance | 0.589 | +| learning_rate | 4.73e-05 | +| loss | -0.0213 | +| n_updates | 37696 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000148 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1420 | +| iterations | 5471 | +| time_elapsed | 7886 | +| total_timesteps | 11204608 | +| train/ | | +| approx_kl | 0.010621145 | +| clip_fraction | 0.296 | +| clip_range | 0.0722 | +| entropy_loss | -6.26 | +| explained_variance | 0.222 | +| learning_rate | 4.73e-05 | +| loss | -0.0192 | +| n_updates | 37700 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000385 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1420 | +| iterations | 5472 | +| time_elapsed | 7887 | +| total_timesteps | 11206656 | +| train/ | | +| approx_kl | 0.009908558 | +| clip_fraction | 0.326 | +| clip_range | 0.0722 | +| entropy_loss | -6.91 | +| explained_variance | 0.235 | +| learning_rate | 4.73e-05 | +| loss | -0.0307 | +| n_updates | 37704 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.00025 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1420 | +| iterations | 5473 | +| time_elapsed | 7888 | +| total_timesteps | 11208704 | +| train/ | | +| approx_kl | 0.010130103 | +| clip_fraction | 0.363 | +| clip_range | 0.0722 | +| entropy_loss | -6.88 | +| explained_variance | 0.378 | +| learning_rate | 4.73e-05 | +| loss | -0.033 | +| n_updates | 37708 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000108 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1420 | +| iterations | 5474 | +| time_elapsed | 7890 | +| total_timesteps | 11210752 | +| train/ | | +| approx_kl | 0.010932332 | +| clip_fraction | 0.334 | +| clip_range | 0.0722 | +| entropy_loss | -7.21 | +| explained_variance | -0.172 | +| learning_rate | 4.73e-05 | +| loss | -0.0382 | +| n_updates | 37712 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.00018 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1420 | +| iterations | 5475 | +| time_elapsed | 7891 | +| total_timesteps | 11212800 | +| train/ | | +| approx_kl | 0.011122592 | +| clip_fraction | 0.307 | +| clip_range | 0.0722 | +| entropy_loss | -7.43 | +| explained_variance | -0.0507 | +| learning_rate | 4.73e-05 | +| loss | -0.0317 | +| n_updates | 37716 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000153 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1420 | +| iterations | 5476 | +| time_elapsed | 7893 | +| total_timesteps | 11214848 | +| train/ | | +| approx_kl | 0.010565108 | +| clip_fraction | 0.318 | +| clip_range | 0.0722 | +| entropy_loss | -6.91 | +| explained_variance | 0.309 | +| learning_rate | 4.73e-05 | +| loss | -0.0264 | +| n_updates | 37720 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000253 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1420 | +| iterations | 5477 | +| time_elapsed | 7894 | +| total_timesteps | 11216896 | +| train/ | | +| approx_kl | 0.008942958 | +| clip_fraction | 0.318 | +| clip_range | 0.0722 | +| entropy_loss | -7.1 | +| explained_variance | 0.0543 | +| learning_rate | 4.73e-05 | +| loss | -0.033 | +| n_updates | 37724 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000167 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1420 | +| iterations | 5478 | +| time_elapsed | 7896 | +| total_timesteps | 11218944 | +| train/ | | +| approx_kl | 0.010354234 | +| clip_fraction | 0.312 | +| clip_range | 0.0722 | +| entropy_loss | -6.66 | +| explained_variance | 0.333 | +| learning_rate | 4.73e-05 | +| loss | -0.0327 | +| n_updates | 37728 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000318 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1420 | +| iterations | 5479 | +| time_elapsed | 7897 | +| total_timesteps | 11220992 | +| train/ | | +| approx_kl | 0.01364273 | +| clip_fraction | 0.349 | +| clip_range | 0.0722 | +| entropy_loss | -6.99 | +| explained_variance | -0.267 | +| learning_rate | 4.73e-05 | +| loss | -0.0322 | +| n_updates | 37732 | +| policy_gradient_loss | -0.0222 | +| value_loss | 9.57e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1420 | +| iterations | 5480 | +| time_elapsed | 7898 | +| total_timesteps | 11223040 | +| train/ | | +| approx_kl | 0.010683173 | +| clip_fraction | 0.342 | +| clip_range | 0.0722 | +| entropy_loss | -7.27 | +| explained_variance | -0.405 | +| learning_rate | 4.73e-05 | +| loss | -0.0369 | +| n_updates | 37736 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000122 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1420 | +| iterations | 5481 | +| time_elapsed | 7900 | +| total_timesteps | 11225088 | +| train/ | | +| approx_kl | 0.010625097 | +| clip_fraction | 0.3 | +| clip_range | 0.0722 | +| entropy_loss | -6.42 | +| explained_variance | 0.284 | +| learning_rate | 4.73e-05 | +| loss | -0.0233 | +| n_updates | 37740 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000337 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1420 | +| iterations | 5482 | +| time_elapsed | 7901 | +| total_timesteps | 11227136 | +| train/ | | +| approx_kl | 0.011957737 | +| clip_fraction | 0.335 | +| clip_range | 0.0722 | +| entropy_loss | -6.92 | +| explained_variance | 0.209 | +| learning_rate | 4.73e-05 | +| loss | -0.0319 | +| n_updates | 37744 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000188 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1420 | +| iterations | 5483 | +| time_elapsed | 7903 | +| total_timesteps | 11229184 | +| train/ | | +| approx_kl | 0.015540525 | +| clip_fraction | 0.336 | +| clip_range | 0.0722 | +| entropy_loss | -7.11 | +| explained_variance | -0.17 | +| learning_rate | 4.73e-05 | +| loss | -0.0355 | +| n_updates | 37748 | +| policy_gradient_loss | -0.0212 | +| value_loss | 8.91e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1420 | +| iterations | 5484 | +| time_elapsed | 7904 | +| total_timesteps | 11231232 | +| train/ | | +| approx_kl | 0.012192537 | +| clip_fraction | 0.334 | +| clip_range | 0.0722 | +| entropy_loss | -7.36 | +| explained_variance | -0.399 | +| learning_rate | 4.73e-05 | +| loss | -0.0429 | +| n_updates | 37752 | +| policy_gradient_loss | -0.0232 | +| value_loss | 5.36e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1420 | +| iterations | 5485 | +| time_elapsed | 7905 | +| total_timesteps | 11233280 | +| train/ | | +| approx_kl | 0.011276837 | +| clip_fraction | 0.324 | +| clip_range | 0.0722 | +| entropy_loss | -7.04 | +| explained_variance | 0.441 | +| learning_rate | 4.73e-05 | +| loss | -0.0325 | +| n_updates | 37756 | +| policy_gradient_loss | -0.0189 | +| value_loss | 9.24e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1420 | +| iterations | 5486 | +| time_elapsed | 7907 | +| total_timesteps | 11235328 | +| train/ | | +| approx_kl | 0.010376455 | +| clip_fraction | 0.305 | +| clip_range | 0.0722 | +| entropy_loss | -6.55 | +| explained_variance | 0.344 | +| learning_rate | 4.73e-05 | +| loss | -0.0265 | +| n_updates | 37760 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000193 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1420 | +| iterations | 5487 | +| time_elapsed | 7908 | +| total_timesteps | 11237376 | +| train/ | | +| approx_kl | 0.0113323 | +| clip_fraction | 0.311 | +| clip_range | 0.0722 | +| entropy_loss | -7.07 | +| explained_variance | 0.127 | +| learning_rate | 4.73e-05 | +| loss | -0.0301 | +| n_updates | 37764 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000223 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1420 | +| iterations | 5488 | +| time_elapsed | 7910 | +| total_timesteps | 11239424 | +| train/ | | +| approx_kl | 0.013575632 | +| clip_fraction | 0.352 | +| clip_range | 0.0722 | +| entropy_loss | -6.76 | +| explained_variance | 0.366 | +| learning_rate | 4.73e-05 | +| loss | -0.032 | +| n_updates | 37768 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.00016 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1420 | +| iterations | 5489 | +| time_elapsed | 7911 | +| total_timesteps | 11241472 | +| train/ | | +| approx_kl | 0.012848955 | +| clip_fraction | 0.348 | +| clip_range | 0.0722 | +| entropy_loss | -6.99 | +| explained_variance | 0.317 | +| learning_rate | 4.73e-05 | +| loss | -0.0299 | +| n_updates | 37772 | +| policy_gradient_loss | -0.0219 | +| value_loss | 9.75e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1420 | +| iterations | 5490 | +| time_elapsed | 7913 | +| total_timesteps | 11243520 | +| train/ | | +| approx_kl | 0.010982049 | +| clip_fraction | 0.296 | +| clip_range | 0.0722 | +| entropy_loss | -6.99 | +| explained_variance | 0.104 | +| learning_rate | 4.73e-05 | +| loss | -0.0278 | +| n_updates | 37776 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000229 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1420 | +| iterations | 5491 | +| time_elapsed | 7914 | +| total_timesteps | 11245568 | +| train/ | | +| approx_kl | 0.011940788 | +| clip_fraction | 0.365 | +| clip_range | 0.0722 | +| entropy_loss | -7.11 | +| explained_variance | -0.22 | +| learning_rate | 4.73e-05 | +| loss | -0.0342 | +| n_updates | 37780 | +| policy_gradient_loss | -0.0227 | +| value_loss | 0.000105 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1420 | +| iterations | 5492 | +| time_elapsed | 7915 | +| total_timesteps | 11247616 | +| train/ | | +| approx_kl | 0.011163021 | +| clip_fraction | 0.33 | +| clip_range | 0.0722 | +| entropy_loss | -7.17 | +| explained_variance | 0.035 | +| learning_rate | 4.73e-05 | +| loss | -0.0322 | +| n_updates | 37784 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000198 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1420 | +| iterations | 5493 | +| time_elapsed | 7917 | +| total_timesteps | 11249664 | +| train/ | | +| approx_kl | 0.011104055 | +| clip_fraction | 0.324 | +| clip_range | 0.0722 | +| entropy_loss | -6.99 | +| explained_variance | 0.178 | +| learning_rate | 4.73e-05 | +| loss | -0.0296 | +| n_updates | 37788 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000239 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1420 | +| iterations | 5494 | +| time_elapsed | 7918 | +| total_timesteps | 11251712 | +| train/ | | +| approx_kl | 0.010577643 | +| clip_fraction | 0.313 | +| clip_range | 0.0722 | +| entropy_loss | -6.98 | +| explained_variance | 0.243 | +| learning_rate | 4.73e-05 | +| loss | -0.03 | +| n_updates | 37792 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000186 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1420 | +| iterations | 5495 | +| time_elapsed | 7919 | +| total_timesteps | 11253760 | +| train/ | | +| approx_kl | 0.010536724 | +| clip_fraction | 0.318 | +| clip_range | 0.0722 | +| entropy_loss | -6.62 | +| explained_variance | 0.291 | +| learning_rate | 4.73e-05 | +| loss | -0.0285 | +| n_updates | 37796 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000257 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1420 | +| iterations | 5496 | +| time_elapsed | 7921 | +| total_timesteps | 11255808 | +| train/ | | +| approx_kl | 0.012405697 | +| clip_fraction | 0.349 | +| clip_range | 0.0722 | +| entropy_loss | -7.1 | +| explained_variance | 0.334 | +| learning_rate | 4.73e-05 | +| loss | -0.0339 | +| n_updates | 37800 | +| policy_gradient_loss | -0.0221 | +| value_loss | 0.000107 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1420 | +| iterations | 5497 | +| time_elapsed | 7922 | +| total_timesteps | 11257856 | +| train/ | | +| approx_kl | 0.0117922425 | +| clip_fraction | 0.324 | +| clip_range | 0.0722 | +| entropy_loss | -7.22 | +| explained_variance | -0.185 | +| learning_rate | 4.73e-05 | +| loss | -0.0305 | +| n_updates | 37804 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000186 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1420 | +| iterations | 5498 | +| time_elapsed | 7924 | +| total_timesteps | 11259904 | +| train/ | | +| approx_kl | 0.011568712 | +| clip_fraction | 0.301 | +| clip_range | 0.0722 | +| entropy_loss | -7.22 | +| explained_variance | 0.183 | +| learning_rate | 4.73e-05 | +| loss | -0.0316 | +| n_updates | 37808 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000214 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1420 | +| iterations | 5499 | +| time_elapsed | 7925 | +| total_timesteps | 11261952 | +| train/ | | +| approx_kl | 0.011713104 | +| clip_fraction | 0.335 | +| clip_range | 0.0722 | +| entropy_loss | -6.47 | +| explained_variance | 0.522 | +| learning_rate | 4.73e-05 | +| loss | -0.0265 | +| n_updates | 37812 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000157 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1420 | +| iterations | 5500 | +| time_elapsed | 7927 | +| total_timesteps | 11264000 | +| train/ | | +| approx_kl | 0.010761333 | +| clip_fraction | 0.33 | +| clip_range | 0.0722 | +| entropy_loss | -6.89 | +| explained_variance | 0.248 | +| learning_rate | 4.73e-05 | +| loss | -0.0313 | +| n_updates | 37816 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000185 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.385 | +| time/ | | +| fps | 1420 | +| iterations | 5501 | +| time_elapsed | 7928 | +| total_timesteps | 11266048 | +| train/ | | +| approx_kl | 0.011498455 | +| clip_fraction | 0.311 | +| clip_range | 0.0722 | +| entropy_loss | -6.66 | +| explained_variance | 0.429 | +| learning_rate | 4.73e-05 | +| loss | -0.0311 | +| n_updates | 37820 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000178 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.385 | +| time/ | | +| fps | 1420 | +| iterations | 5502 | +| time_elapsed | 7930 | +| total_timesteps | 11268096 | +| train/ | | +| approx_kl | 0.010191308 | +| clip_fraction | 0.298 | +| clip_range | 0.0722 | +| entropy_loss | -6.9 | +| explained_variance | 0.107 | +| learning_rate | 4.73e-05 | +| loss | -0.0177 | +| n_updates | 37824 | +| policy_gradient_loss | -0.0146 | +| value_loss | 0.000442 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.387 | +| time/ | | +| fps | 1420 | +| iterations | 5503 | +| time_elapsed | 7931 | +| total_timesteps | 11270144 | +| train/ | | +| approx_kl | 0.011266366 | +| clip_fraction | 0.346 | +| clip_range | 0.0722 | +| entropy_loss | -7.01 | +| explained_variance | 0.346 | +| learning_rate | 4.73e-05 | +| loss | -0.0395 | +| n_updates | 37828 | +| policy_gradient_loss | -0.0225 | +| value_loss | 0.000109 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.387 | +| time/ | | +| fps | 1420 | +| iterations | 5504 | +| time_elapsed | 7933 | +| total_timesteps | 11272192 | +| train/ | | +| approx_kl | 0.011340443 | +| clip_fraction | 0.337 | +| clip_range | 0.0722 | +| entropy_loss | -7.16 | +| explained_variance | -0.0808 | +| learning_rate | 4.73e-05 | +| loss | -0.0332 | +| n_updates | 37832 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000109 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.39 | +| time/ | | +| fps | 1420 | +| iterations | 5505 | +| time_elapsed | 7934 | +| total_timesteps | 11274240 | +| train/ | | +| approx_kl | 0.012578393 | +| clip_fraction | 0.321 | +| clip_range | 0.0722 | +| entropy_loss | -7.21 | +| explained_variance | -0.0683 | +| learning_rate | 4.73e-05 | +| loss | -0.0349 | +| n_updates | 37836 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000164 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.386 | +| time/ | | +| fps | 1420 | +| iterations | 5506 | +| time_elapsed | 7935 | +| total_timesteps | 11276288 | +| train/ | | +| approx_kl | 0.011842358 | +| clip_fraction | 0.321 | +| clip_range | 0.0722 | +| entropy_loss | -7.11 | +| explained_variance | 0.0784 | +| learning_rate | 4.73e-05 | +| loss | -0.0279 | +| n_updates | 37840 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000227 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1420 | +| iterations | 5507 | +| time_elapsed | 7937 | +| total_timesteps | 11278336 | +| train/ | | +| approx_kl | 0.012212626 | +| clip_fraction | 0.312 | +| clip_range | 0.0722 | +| entropy_loss | -6.99 | +| explained_variance | 0.247 | +| learning_rate | 4.73e-05 | +| loss | -0.0296 | +| n_updates | 37844 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000136 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1420 | +| iterations | 5508 | +| time_elapsed | 7938 | +| total_timesteps | 11280384 | +| train/ | | +| approx_kl | 0.011308548 | +| clip_fraction | 0.341 | +| clip_range | 0.0722 | +| entropy_loss | -6.96 | +| explained_variance | -0.0728 | +| learning_rate | 4.73e-05 | +| loss | -0.0296 | +| n_updates | 37848 | +| policy_gradient_loss | -0.0204 | +| value_loss | 9e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1420 | +| iterations | 5509 | +| time_elapsed | 7940 | +| total_timesteps | 11282432 | +| train/ | | +| approx_kl | 0.0118122045 | +| clip_fraction | 0.324 | +| clip_range | 0.0722 | +| entropy_loss | -6.73 | +| explained_variance | 0.305 | +| learning_rate | 4.73e-05 | +| loss | -0.0326 | +| n_updates | 37852 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000166 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1420 | +| iterations | 5510 | +| time_elapsed | 7941 | +| total_timesteps | 11284480 | +| train/ | | +| approx_kl | 0.011504754 | +| clip_fraction | 0.333 | +| clip_range | 0.0722 | +| entropy_loss | -6.98 | +| explained_variance | 0.264 | +| learning_rate | 4.73e-05 | +| loss | -0.0323 | +| n_updates | 37856 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1420 | +| iterations | 5511 | +| time_elapsed | 7942 | +| total_timesteps | 11286528 | +| train/ | | +| approx_kl | 0.010198533 | +| clip_fraction | 0.298 | +| clip_range | 0.0722 | +| entropy_loss | -6.88 | +| explained_variance | 0.26 | +| learning_rate | 4.73e-05 | +| loss | -0.0237 | +| n_updates | 37860 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000295 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1420 | +| iterations | 5512 | +| time_elapsed | 7944 | +| total_timesteps | 11288576 | +| train/ | | +| approx_kl | 0.011885444 | +| clip_fraction | 0.323 | +| clip_range | 0.0722 | +| entropy_loss | -6.71 | +| explained_variance | 0.579 | +| learning_rate | 4.73e-05 | +| loss | -0.0365 | +| n_updates | 37864 | +| policy_gradient_loss | -0.0229 | +| value_loss | 7.45e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1420 | +| iterations | 5513 | +| time_elapsed | 7945 | +| total_timesteps | 11290624 | +| train/ | | +| approx_kl | 0.011716364 | +| clip_fraction | 0.339 | +| clip_range | 0.0722 | +| entropy_loss | -7.31 | +| explained_variance | -0.144 | +| learning_rate | 4.73e-05 | +| loss | -0.0311 | +| n_updates | 37868 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000187 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1420 | +| iterations | 5514 | +| time_elapsed | 7947 | +| total_timesteps | 11292672 | +| train/ | | +| approx_kl | 0.011347119 | +| clip_fraction | 0.325 | +| clip_range | 0.0722 | +| entropy_loss | -7.36 | +| explained_variance | -0.0481 | +| learning_rate | 4.73e-05 | +| loss | -0.0349 | +| n_updates | 37872 | +| policy_gradient_loss | -0.0204 | +| value_loss | 8.75e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1420 | +| iterations | 5515 | +| time_elapsed | 7948 | +| total_timesteps | 11294720 | +| train/ | | +| approx_kl | 0.0111279655 | +| clip_fraction | 0.318 | +| clip_range | 0.0722 | +| entropy_loss | -7.02 | +| explained_variance | 0.212 | +| learning_rate | 4.73e-05 | +| loss | -0.0343 | +| n_updates | 37876 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000187 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1420 | +| iterations | 5516 | +| time_elapsed | 7950 | +| total_timesteps | 11296768 | +| train/ | | +| approx_kl | 0.013970055 | +| clip_fraction | 0.351 | +| clip_range | 0.0722 | +| entropy_loss | -6.94 | +| explained_variance | 0.41 | +| learning_rate | 4.73e-05 | +| loss | -0.0315 | +| n_updates | 37880 | +| policy_gradient_loss | -0.0207 | +| value_loss | 9.42e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1420 | +| iterations | 5517 | +| time_elapsed | 7951 | +| total_timesteps | 11298816 | +| train/ | | +| approx_kl | 0.011322942 | +| clip_fraction | 0.344 | +| clip_range | 0.0722 | +| entropy_loss | -7.03 | +| explained_variance | 0.111 | +| learning_rate | 4.73e-05 | +| loss | -0.0297 | +| n_updates | 37884 | +| policy_gradient_loss | -0.0186 | +| value_loss | 7.13e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1420 | +| iterations | 5518 | +| time_elapsed | 7952 | +| total_timesteps | 11300864 | +| train/ | | +| approx_kl | 0.010670487 | +| clip_fraction | 0.301 | +| clip_range | 0.0722 | +| entropy_loss | -6.93 | +| explained_variance | 0.0597 | +| learning_rate | 4.73e-05 | +| loss | -0.0238 | +| n_updates | 37888 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000142 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1420 | +| iterations | 5519 | +| time_elapsed | 7954 | +| total_timesteps | 11302912 | +| train/ | | +| approx_kl | 0.01060975 | +| clip_fraction | 0.325 | +| clip_range | 0.0722 | +| entropy_loss | -7.22 | +| explained_variance | 0.0394 | +| learning_rate | 4.73e-05 | +| loss | -0.0288 | +| n_updates | 37892 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.0002 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1420 | +| iterations | 5520 | +| time_elapsed | 7955 | +| total_timesteps | 11304960 | +| train/ | | +| approx_kl | 0.009698557 | +| clip_fraction | 0.303 | +| clip_range | 0.0722 | +| entropy_loss | -7.07 | +| explained_variance | 0.304 | +| learning_rate | 4.73e-05 | +| loss | -0.0318 | +| n_updates | 37896 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000147 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1420 | +| iterations | 5521 | +| time_elapsed | 7957 | +| total_timesteps | 11307008 | +| train/ | | +| approx_kl | 0.009235266 | +| clip_fraction | 0.314 | +| clip_range | 0.0722 | +| entropy_loss | -6.55 | +| explained_variance | 0.607 | +| learning_rate | 4.73e-05 | +| loss | -0.021 | +| n_updates | 37900 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000151 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1420 | +| iterations | 5522 | +| time_elapsed | 7958 | +| total_timesteps | 11309056 | +| train/ | | +| approx_kl | 0.011077859 | +| clip_fraction | 0.328 | +| clip_range | 0.0722 | +| entropy_loss | -7.11 | +| explained_variance | -0.068 | +| learning_rate | 4.73e-05 | +| loss | -0.0302 | +| n_updates | 37904 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000201 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1420 | +| iterations | 5523 | +| time_elapsed | 7960 | +| total_timesteps | 11311104 | +| train/ | | +| approx_kl | 0.011480838 | +| clip_fraction | 0.33 | +| clip_range | 0.0722 | +| entropy_loss | -7 | +| explained_variance | 0.00886 | +| learning_rate | 4.73e-05 | +| loss | -0.0301 | +| n_updates | 37908 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.00026 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1420 | +| iterations | 5524 | +| time_elapsed | 7961 | +| total_timesteps | 11313152 | +| train/ | | +| approx_kl | 0.011905495 | +| clip_fraction | 0.347 | +| clip_range | 0.0722 | +| entropy_loss | -6.91 | +| explained_variance | 0.371 | +| learning_rate | 4.73e-05 | +| loss | -0.032 | +| n_updates | 37912 | +| policy_gradient_loss | -0.0197 | +| value_loss | 7.1e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1420 | +| iterations | 5525 | +| time_elapsed | 7963 | +| total_timesteps | 11315200 | +| train/ | | +| approx_kl | 0.01118105 | +| clip_fraction | 0.317 | +| clip_range | 0.0722 | +| entropy_loss | -7.32 | +| explained_variance | -0.114 | +| learning_rate | 4.73e-05 | +| loss | -0.0379 | +| n_updates | 37916 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000196 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1420 | +| iterations | 5526 | +| time_elapsed | 7964 | +| total_timesteps | 11317248 | +| train/ | | +| approx_kl | 0.012597265 | +| clip_fraction | 0.349 | +| clip_range | 0.0722 | +| entropy_loss | -7.28 | +| explained_variance | -0.0307 | +| learning_rate | 4.73e-05 | +| loss | -0.0357 | +| n_updates | 37920 | +| policy_gradient_loss | -0.0218 | +| value_loss | 8.58e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1420 | +| iterations | 5527 | +| time_elapsed | 7965 | +| total_timesteps | 11319296 | +| train/ | | +| approx_kl | 0.010638004 | +| clip_fraction | 0.319 | +| clip_range | 0.0722 | +| entropy_loss | -6.86 | +| explained_variance | 0.324 | +| learning_rate | 4.73e-05 | +| loss | -0.0311 | +| n_updates | 37924 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000255 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1420 | +| iterations | 5528 | +| time_elapsed | 7967 | +| total_timesteps | 11321344 | +| train/ | | +| approx_kl | 0.011788014 | +| clip_fraction | 0.31 | +| clip_range | 0.0722 | +| entropy_loss | -6.63 | +| explained_variance | 0.238 | +| learning_rate | 4.73e-05 | +| loss | -0.0289 | +| n_updates | 37928 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000253 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1420 | +| iterations | 5529 | +| time_elapsed | 7968 | +| total_timesteps | 11323392 | +| train/ | | +| approx_kl | 0.010680923 | +| clip_fraction | 0.307 | +| clip_range | 0.0722 | +| entropy_loss | -6.9 | +| explained_variance | 0.444 | +| learning_rate | 4.73e-05 | +| loss | -0.0299 | +| n_updates | 37932 | +| policy_gradient_loss | -0.0204 | +| value_loss | 9.84e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1420 | +| iterations | 5530 | +| time_elapsed | 7970 | +| total_timesteps | 11325440 | +| train/ | | +| approx_kl | 0.010044126 | +| clip_fraction | 0.302 | +| clip_range | 0.0722 | +| entropy_loss | -6.8 | +| explained_variance | 0.216 | +| learning_rate | 4.73e-05 | +| loss | -0.0257 | +| n_updates | 37936 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000248 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1420 | +| iterations | 5531 | +| time_elapsed | 7971 | +| total_timesteps | 11327488 | +| train/ | | +| approx_kl | 0.0111421365 | +| clip_fraction | 0.317 | +| clip_range | 0.0722 | +| entropy_loss | -6.77 | +| explained_variance | 0.338 | +| learning_rate | 4.73e-05 | +| loss | -0.0253 | +| n_updates | 37940 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000251 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1420 | +| iterations | 5532 | +| time_elapsed | 7973 | +| total_timesteps | 11329536 | +| train/ | | +| approx_kl | 0.010102004 | +| clip_fraction | 0.338 | +| clip_range | 0.0722 | +| entropy_loss | -6.94 | +| explained_variance | 0.297 | +| learning_rate | 4.73e-05 | +| loss | -0.0405 | +| n_updates | 37944 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000108 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1420 | +| iterations | 5533 | +| time_elapsed | 7974 | +| total_timesteps | 11331584 | +| train/ | | +| approx_kl | 0.012827106 | +| clip_fraction | 0.331 | +| clip_range | 0.0722 | +| entropy_loss | -6.97 | +| explained_variance | -0.518 | +| learning_rate | 4.73e-05 | +| loss | -0.0408 | +| n_updates | 37948 | +| policy_gradient_loss | -0.0196 | +| value_loss | 9.47e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1420 | +| iterations | 5534 | +| time_elapsed | 7976 | +| total_timesteps | 11333632 | +| train/ | | +| approx_kl | 0.010420732 | +| clip_fraction | 0.319 | +| clip_range | 0.0722 | +| entropy_loss | -7.2 | +| explained_variance | 0.0785 | +| learning_rate | 4.73e-05 | +| loss | -0.0316 | +| n_updates | 37952 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000303 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1420 | +| iterations | 5535 | +| time_elapsed | 7977 | +| total_timesteps | 11335680 | +| train/ | | +| approx_kl | 0.010712154 | +| clip_fraction | 0.328 | +| clip_range | 0.0722 | +| entropy_loss | -7.36 | +| explained_variance | 0.0435 | +| learning_rate | 4.73e-05 | +| loss | -0.0415 | +| n_updates | 37956 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000111 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1420 | +| iterations | 5536 | +| time_elapsed | 7979 | +| total_timesteps | 11337728 | +| train/ | | +| approx_kl | 0.010437258 | +| clip_fraction | 0.317 | +| clip_range | 0.0722 | +| entropy_loss | -7.22 | +| explained_variance | -0.0613 | +| learning_rate | 4.73e-05 | +| loss | -0.0284 | +| n_updates | 37960 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.00023 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1420 | +| iterations | 5537 | +| time_elapsed | 7980 | +| total_timesteps | 11339776 | +| train/ | | +| approx_kl | 0.009711986 | +| clip_fraction | 0.339 | +| clip_range | 0.0722 | +| entropy_loss | -6.61 | +| explained_variance | 0.297 | +| learning_rate | 4.73e-05 | +| loss | -0.0256 | +| n_updates | 37964 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000204 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1420 | +| iterations | 5538 | +| time_elapsed | 7981 | +| total_timesteps | 11341824 | +| train/ | | +| approx_kl | 0.008373412 | +| clip_fraction | 0.289 | +| clip_range | 0.0722 | +| entropy_loss | -6.88 | +| explained_variance | 0.142 | +| learning_rate | 4.73e-05 | +| loss | -0.0307 | +| n_updates | 37968 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000184 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1420 | +| iterations | 5539 | +| time_elapsed | 7983 | +| total_timesteps | 11343872 | +| train/ | | +| approx_kl | 0.010323377 | +| clip_fraction | 0.325 | +| clip_range | 0.0722 | +| entropy_loss | -7.36 | +| explained_variance | -0.239 | +| learning_rate | 4.73e-05 | +| loss | -0.0356 | +| n_updates | 37972 | +| policy_gradient_loss | -0.0228 | +| value_loss | 8.64e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1420 | +| iterations | 5540 | +| time_elapsed | 7984 | +| total_timesteps | 11345920 | +| train/ | | +| approx_kl | 0.011448149 | +| clip_fraction | 0.313 | +| clip_range | 0.0722 | +| entropy_loss | -7.21 | +| explained_variance | -0.0931 | +| learning_rate | 4.73e-05 | +| loss | -0.0283 | +| n_updates | 37976 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000188 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1420 | +| iterations | 5541 | +| time_elapsed | 7986 | +| total_timesteps | 11347968 | +| train/ | | +| approx_kl | 0.011653032 | +| clip_fraction | 0.322 | +| clip_range | 0.0722 | +| entropy_loss | -7.19 | +| explained_variance | 0.126 | +| learning_rate | 4.73e-05 | +| loss | -0.0334 | +| n_updates | 37980 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000196 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1420 | +| iterations | 5542 | +| time_elapsed | 7987 | +| total_timesteps | 11350016 | +| train/ | | +| approx_kl | 0.009270896 | +| clip_fraction | 0.317 | +| clip_range | 0.0722 | +| entropy_loss | -6.31 | +| explained_variance | 0.431 | +| learning_rate | 4.73e-05 | +| loss | -0.0308 | +| n_updates | 37984 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000342 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1420 | +| iterations | 5543 | +| time_elapsed | 7989 | +| total_timesteps | 11352064 | +| train/ | | +| approx_kl | 0.010056719 | +| clip_fraction | 0.331 | +| clip_range | 0.0722 | +| entropy_loss | -6.71 | +| explained_variance | 0.518 | +| learning_rate | 4.73e-05 | +| loss | -0.0338 | +| n_updates | 37988 | +| policy_gradient_loss | -0.0213 | +| value_loss | 9.05e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1420 | +| iterations | 5544 | +| time_elapsed | 7990 | +| total_timesteps | 11354112 | +| train/ | | +| approx_kl | 0.012404637 | +| clip_fraction | 0.349 | +| clip_range | 0.0722 | +| entropy_loss | -7.19 | +| explained_variance | 0.421 | +| learning_rate | 4.73e-05 | +| loss | -0.0429 | +| n_updates | 37992 | +| policy_gradient_loss | -0.0235 | +| value_loss | 9.27e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1420 | +| iterations | 5545 | +| time_elapsed | 7992 | +| total_timesteps | 11356160 | +| train/ | | +| approx_kl | 0.01086623 | +| clip_fraction | 0.311 | +| clip_range | 0.0722 | +| entropy_loss | -7.44 | +| explained_variance | -0.148 | +| learning_rate | 4.73e-05 | +| loss | -0.0319 | +| n_updates | 37996 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000142 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1420 | +| iterations | 5546 | +| time_elapsed | 7993 | +| total_timesteps | 11358208 | +| train/ | | +| approx_kl | 0.0101977885 | +| clip_fraction | 0.312 | +| clip_range | 0.0722 | +| entropy_loss | -7.39 | +| explained_variance | -0.138 | +| learning_rate | 4.73e-05 | +| loss | -0.033 | +| n_updates | 38000 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000108 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1420 | +| iterations | 5547 | +| time_elapsed | 7994 | +| total_timesteps | 11360256 | +| train/ | | +| approx_kl | 0.010063006 | +| clip_fraction | 0.31 | +| clip_range | 0.0722 | +| entropy_loss | -7.01 | +| explained_variance | 0.419 | +| learning_rate | 4.73e-05 | +| loss | -0.0256 | +| n_updates | 38004 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.00014 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1420 | +| iterations | 5548 | +| time_elapsed | 7996 | +| total_timesteps | 11362304 | +| train/ | | +| approx_kl | 0.011598475 | +| clip_fraction | 0.328 | +| clip_range | 0.0722 | +| entropy_loss | -7.09 | +| explained_variance | 0.335 | +| learning_rate | 4.73e-05 | +| loss | -0.0338 | +| n_updates | 38008 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000149 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1420 | +| iterations | 5549 | +| time_elapsed | 7997 | +| total_timesteps | 11364352 | +| train/ | | +| approx_kl | 0.010215307 | +| clip_fraction | 0.302 | +| clip_range | 0.0722 | +| entropy_loss | -7.08 | +| explained_variance | 0.0786 | +| learning_rate | 4.73e-05 | +| loss | -0.0325 | +| n_updates | 38012 | +| policy_gradient_loss | -0.0193 | +| value_loss | 9.93e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1420 | +| iterations | 5550 | +| time_elapsed | 7999 | +| total_timesteps | 11366400 | +| train/ | | +| approx_kl | 0.011408027 | +| clip_fraction | 0.336 | +| clip_range | 0.0722 | +| entropy_loss | -7.1 | +| explained_variance | 0.365 | +| learning_rate | 4.73e-05 | +| loss | -0.0331 | +| n_updates | 38016 | +| policy_gradient_loss | -0.0212 | +| value_loss | 6.81e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1420 | +| iterations | 5551 | +| time_elapsed | 8000 | +| total_timesteps | 11368448 | +| train/ | | +| approx_kl | 0.011782589 | +| clip_fraction | 0.314 | +| clip_range | 0.0722 | +| entropy_loss | -6.59 | +| explained_variance | 0.53 | +| learning_rate | 4.73e-05 | +| loss | -0.0306 | +| n_updates | 38020 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000133 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1420 | +| iterations | 5552 | +| time_elapsed | 8002 | +| total_timesteps | 11370496 | +| train/ | | +| approx_kl | 0.010915702 | +| clip_fraction | 0.294 | +| clip_range | 0.0722 | +| entropy_loss | -6.7 | +| explained_variance | 0.41 | +| learning_rate | 4.73e-05 | +| loss | -0.0303 | +| n_updates | 38024 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000213 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1420 | +| iterations | 5553 | +| time_elapsed | 8003 | +| total_timesteps | 11372544 | +| train/ | | +| approx_kl | 0.009786122 | +| clip_fraction | 0.309 | +| clip_range | 0.0722 | +| entropy_loss | -6.99 | +| explained_variance | 0.436 | +| learning_rate | 4.73e-05 | +| loss | -0.034 | +| n_updates | 38028 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000108 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1420 | +| iterations | 5554 | +| time_elapsed | 8005 | +| total_timesteps | 11374592 | +| train/ | | +| approx_kl | 0.011077365 | +| clip_fraction | 0.343 | +| clip_range | 0.0722 | +| entropy_loss | -6.97 | +| explained_variance | 0.369 | +| learning_rate | 4.73e-05 | +| loss | -0.0326 | +| n_updates | 38032 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000207 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1420 | +| iterations | 5555 | +| time_elapsed | 8006 | +| total_timesteps | 11376640 | +| train/ | | +| approx_kl | 0.0117699355 | +| clip_fraction | 0.322 | +| clip_range | 0.0722 | +| entropy_loss | -7.06 | +| explained_variance | 0.35 | +| learning_rate | 4.73e-05 | +| loss | -0.0298 | +| n_updates | 38036 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000113 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1420 | +| iterations | 5556 | +| time_elapsed | 8007 | +| total_timesteps | 11378688 | +| train/ | | +| approx_kl | 0.011384837 | +| clip_fraction | 0.319 | +| clip_range | 0.0722 | +| entropy_loss | -7.3 | +| explained_variance | -0.223 | +| learning_rate | 4.73e-05 | +| loss | -0.0222 | +| n_updates | 38040 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000114 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1420 | +| iterations | 5557 | +| time_elapsed | 8009 | +| total_timesteps | 11380736 | +| train/ | | +| approx_kl | 0.00991858 | +| clip_fraction | 0.304 | +| clip_range | 0.0722 | +| entropy_loss | -7.37 | +| explained_variance | -0.0231 | +| learning_rate | 4.73e-05 | +| loss | -0.0224 | +| n_updates | 38044 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000311 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1420 | +| iterations | 5558 | +| time_elapsed | 8010 | +| total_timesteps | 11382784 | +| train/ | | +| approx_kl | 0.013034058 | +| clip_fraction | 0.295 | +| clip_range | 0.0722 | +| entropy_loss | -6.91 | +| explained_variance | 0.184 | +| learning_rate | 4.73e-05 | +| loss | -0.0306 | +| n_updates | 38048 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000249 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1420 | +| iterations | 5559 | +| time_elapsed | 8012 | +| total_timesteps | 11384832 | +| train/ | | +| approx_kl | 0.011642054 | +| clip_fraction | 0.342 | +| clip_range | 0.0722 | +| entropy_loss | -7.09 | +| explained_variance | 0.203 | +| learning_rate | 4.73e-05 | +| loss | -0.0333 | +| n_updates | 38052 | +| policy_gradient_loss | -0.0221 | +| value_loss | 0.000179 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1420 | +| iterations | 5560 | +| time_elapsed | 8013 | +| total_timesteps | 11386880 | +| train/ | | +| approx_kl | 0.01249658 | +| clip_fraction | 0.324 | +| clip_range | 0.0722 | +| entropy_loss | -7.24 | +| explained_variance | 0.306 | +| learning_rate | 4.73e-05 | +| loss | -0.0357 | +| n_updates | 38056 | +| policy_gradient_loss | -0.0221 | +| value_loss | 0.000117 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1420 | +| iterations | 5561 | +| time_elapsed | 8015 | +| total_timesteps | 11388928 | +| train/ | | +| approx_kl | 0.010294582 | +| clip_fraction | 0.311 | +| clip_range | 0.0722 | +| entropy_loss | -7.21 | +| explained_variance | 0.153 | +| learning_rate | 4.73e-05 | +| loss | -0.0282 | +| n_updates | 38060 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000177 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1420 | +| iterations | 5562 | +| time_elapsed | 8016 | +| total_timesteps | 11390976 | +| train/ | | +| approx_kl | 0.010675844 | +| clip_fraction | 0.296 | +| clip_range | 0.0722 | +| entropy_loss | -6.72 | +| explained_variance | 0.4 | +| learning_rate | 4.73e-05 | +| loss | -0.0209 | +| n_updates | 38064 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000189 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1420 | +| iterations | 5563 | +| time_elapsed | 8017 | +| total_timesteps | 11393024 | +| train/ | | +| approx_kl | 0.011406994 | +| clip_fraction | 0.337 | +| clip_range | 0.0722 | +| entropy_loss | -6.98 | +| explained_variance | 0.208 | +| learning_rate | 4.73e-05 | +| loss | -0.0308 | +| n_updates | 38068 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.00016 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1420 | +| iterations | 5564 | +| time_elapsed | 8019 | +| total_timesteps | 11395072 | +| train/ | | +| approx_kl | 0.011935769 | +| clip_fraction | 0.334 | +| clip_range | 0.0722 | +| entropy_loss | -6.4 | +| explained_variance | 0.602 | +| learning_rate | 4.73e-05 | +| loss | -0.0335 | +| n_updates | 38072 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.00019 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1420 | +| iterations | 5565 | +| time_elapsed | 8020 | +| total_timesteps | 11397120 | +| train/ | | +| approx_kl | 0.010945519 | +| clip_fraction | 0.313 | +| clip_range | 0.0722 | +| entropy_loss | -6.77 | +| explained_variance | 0.239 | +| learning_rate | 4.73e-05 | +| loss | -0.0278 | +| n_updates | 38076 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000323 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1420 | +| iterations | 5566 | +| time_elapsed | 8022 | +| total_timesteps | 11399168 | +| train/ | | +| approx_kl | 0.012565972 | +| clip_fraction | 0.331 | +| clip_range | 0.0722 | +| entropy_loss | -6.64 | +| explained_variance | 0.519 | +| learning_rate | 4.73e-05 | +| loss | -0.0276 | +| n_updates | 38080 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000175 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1420 | +| iterations | 5567 | +| time_elapsed | 8023 | +| total_timesteps | 11401216 | +| train/ | | +| approx_kl | 0.012625873 | +| clip_fraction | 0.353 | +| clip_range | 0.0722 | +| entropy_loss | -7.22 | +| explained_variance | -0.375 | +| learning_rate | 4.73e-05 | +| loss | -0.0435 | +| n_updates | 38084 | +| policy_gradient_loss | -0.0237 | +| value_loss | 7.57e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1420 | +| iterations | 5568 | +| time_elapsed | 8025 | +| total_timesteps | 11403264 | +| train/ | | +| approx_kl | 0.009961242 | +| clip_fraction | 0.319 | +| clip_range | 0.0721 | +| entropy_loss | -7.19 | +| explained_variance | 0.161 | +| learning_rate | 4.73e-05 | +| loss | -0.0264 | +| n_updates | 38088 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000301 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1420 | +| iterations | 5569 | +| time_elapsed | 8026 | +| total_timesteps | 11405312 | +| train/ | | +| approx_kl | 0.011244894 | +| clip_fraction | 0.308 | +| clip_range | 0.0721 | +| entropy_loss | -7.07 | +| explained_variance | 0.303 | +| learning_rate | 4.73e-05 | +| loss | -0.0307 | +| n_updates | 38092 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000165 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1420 | +| iterations | 5570 | +| time_elapsed | 8027 | +| total_timesteps | 11407360 | +| train/ | | +| approx_kl | 0.011199351 | +| clip_fraction | 0.368 | +| clip_range | 0.0721 | +| entropy_loss | -7.03 | +| explained_variance | 0.505 | +| learning_rate | 4.73e-05 | +| loss | -0.0436 | +| n_updates | 38096 | +| policy_gradient_loss | -0.0262 | +| value_loss | 5.96e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1420 | +| iterations | 5571 | +| time_elapsed | 8029 | +| total_timesteps | 11409408 | +| train/ | | +| approx_kl | 0.010122864 | +| clip_fraction | 0.308 | +| clip_range | 0.0721 | +| entropy_loss | -6.83 | +| explained_variance | 0.272 | +| learning_rate | 4.73e-05 | +| loss | -0.0264 | +| n_updates | 38100 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000365 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1420 | +| iterations | 5572 | +| time_elapsed | 8030 | +| total_timesteps | 11411456 | +| train/ | | +| approx_kl | 0.011307647 | +| clip_fraction | 0.324 | +| clip_range | 0.0721 | +| entropy_loss | -6.95 | +| explained_variance | -0.0334 | +| learning_rate | 4.73e-05 | +| loss | -0.0325 | +| n_updates | 38104 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000237 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1420 | +| iterations | 5573 | +| time_elapsed | 8032 | +| total_timesteps | 11413504 | +| train/ | | +| approx_kl | 0.010908011 | +| clip_fraction | 0.327 | +| clip_range | 0.0721 | +| entropy_loss | -7.21 | +| explained_variance | -0.0801 | +| learning_rate | 4.73e-05 | +| loss | -0.0284 | +| n_updates | 38108 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000152 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1420 | +| iterations | 5574 | +| time_elapsed | 8033 | +| total_timesteps | 11415552 | +| train/ | | +| approx_kl | 0.011866174 | +| clip_fraction | 0.342 | +| clip_range | 0.0721 | +| entropy_loss | -6.55 | +| explained_variance | 0.21 | +| learning_rate | 4.73e-05 | +| loss | -0.0251 | +| n_updates | 38112 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.00036 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1420 | +| iterations | 5575 | +| time_elapsed | 8035 | +| total_timesteps | 11417600 | +| train/ | | +| approx_kl | 0.013406016 | +| clip_fraction | 0.332 | +| clip_range | 0.0721 | +| entropy_loss | -7.36 | +| explained_variance | -0.0109 | +| learning_rate | 4.73e-05 | +| loss | -0.0352 | +| n_updates | 38116 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000192 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1420 | +| iterations | 5576 | +| time_elapsed | 8036 | +| total_timesteps | 11419648 | +| train/ | | +| approx_kl | 0.011246201 | +| clip_fraction | 0.335 | +| clip_range | 0.0721 | +| entropy_loss | -7.4 | +| explained_variance | 0.00509 | +| learning_rate | 4.73e-05 | +| loss | -0.034 | +| n_updates | 38120 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000204 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1421 | +| iterations | 5577 | +| time_elapsed | 8037 | +| total_timesteps | 11421696 | +| train/ | | +| approx_kl | 0.01090795 | +| clip_fraction | 0.333 | +| clip_range | 0.0721 | +| entropy_loss | -7.53 | +| explained_variance | -0.227 | +| learning_rate | 4.73e-05 | +| loss | -0.0352 | +| n_updates | 38124 | +| policy_gradient_loss | -0.0225 | +| value_loss | 0.000105 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1420 | +| iterations | 5578 | +| time_elapsed | 8039 | +| total_timesteps | 11423744 | +| train/ | | +| approx_kl | 0.009566458 | +| clip_fraction | 0.31 | +| clip_range | 0.0721 | +| entropy_loss | -7.3 | +| explained_variance | 0.151 | +| learning_rate | 4.73e-05 | +| loss | -0.0281 | +| n_updates | 38128 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000251 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1420 | +| iterations | 5579 | +| time_elapsed | 8040 | +| total_timesteps | 11425792 | +| train/ | | +| approx_kl | 0.009364327 | +| clip_fraction | 0.308 | +| clip_range | 0.0721 | +| entropy_loss | -7.08 | +| explained_variance | 0.311 | +| learning_rate | 4.73e-05 | +| loss | -0.0267 | +| n_updates | 38132 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000191 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1420 | +| iterations | 5580 | +| time_elapsed | 8042 | +| total_timesteps | 11427840 | +| train/ | | +| approx_kl | 0.009770282 | +| clip_fraction | 0.32 | +| clip_range | 0.0721 | +| entropy_loss | -6.83 | +| explained_variance | 0.411 | +| learning_rate | 4.73e-05 | +| loss | -0.0307 | +| n_updates | 38136 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000171 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1421 | +| iterations | 5581 | +| time_elapsed | 8043 | +| total_timesteps | 11429888 | +| train/ | | +| approx_kl | 0.009876449 | +| clip_fraction | 0.307 | +| clip_range | 0.0721 | +| entropy_loss | -6.85 | +| explained_variance | 0.45 | +| learning_rate | 4.73e-05 | +| loss | -0.033 | +| n_updates | 38140 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000145 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1420 | +| iterations | 5582 | +| time_elapsed | 8044 | +| total_timesteps | 11431936 | +| train/ | | +| approx_kl | 0.009589474 | +| clip_fraction | 0.316 | +| clip_range | 0.0721 | +| entropy_loss | -7.23 | +| explained_variance | 0.221 | +| learning_rate | 4.73e-05 | +| loss | -0.0327 | +| n_updates | 38144 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000221 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1421 | +| iterations | 5583 | +| time_elapsed | 8046 | +| total_timesteps | 11433984 | +| train/ | | +| approx_kl | 0.01028724 | +| clip_fraction | 0.341 | +| clip_range | 0.0721 | +| entropy_loss | -7.27 | +| explained_variance | 0.31 | +| learning_rate | 4.73e-05 | +| loss | -0.0316 | +| n_updates | 38148 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000118 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1421 | +| iterations | 5584 | +| time_elapsed | 8047 | +| total_timesteps | 11436032 | +| train/ | | +| approx_kl | 0.010227405 | +| clip_fraction | 0.302 | +| clip_range | 0.0721 | +| entropy_loss | -7.09 | +| explained_variance | -0.121 | +| learning_rate | 4.73e-05 | +| loss | -0.0327 | +| n_updates | 38152 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.00014 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1421 | +| iterations | 5585 | +| time_elapsed | 8049 | +| total_timesteps | 11438080 | +| train/ | | +| approx_kl | 0.010890881 | +| clip_fraction | 0.325 | +| clip_range | 0.0721 | +| entropy_loss | -6.99 | +| explained_variance | 0.375 | +| learning_rate | 4.73e-05 | +| loss | -0.0363 | +| n_updates | 38156 | +| policy_gradient_loss | -0.0214 | +| value_loss | 7.54e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1421 | +| iterations | 5586 | +| time_elapsed | 8050 | +| total_timesteps | 11440128 | +| train/ | | +| approx_kl | 0.010539049 | +| clip_fraction | 0.311 | +| clip_range | 0.0721 | +| entropy_loss | -6.98 | +| explained_variance | 0.139 | +| learning_rate | 4.73e-05 | +| loss | -0.0258 | +| n_updates | 38160 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000172 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1421 | +| iterations | 5587 | +| time_elapsed | 8051 | +| total_timesteps | 11442176 | +| train/ | | +| approx_kl | 0.011946285 | +| clip_fraction | 0.329 | +| clip_range | 0.0721 | +| entropy_loss | -7.32 | +| explained_variance | -0.156 | +| learning_rate | 4.73e-05 | +| loss | -0.0389 | +| n_updates | 38164 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000111 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1421 | +| iterations | 5588 | +| time_elapsed | 8053 | +| total_timesteps | 11444224 | +| train/ | | +| approx_kl | 0.011345664 | +| clip_fraction | 0.318 | +| clip_range | 0.0721 | +| entropy_loss | -7.35 | +| explained_variance | -0.0333 | +| learning_rate | 4.73e-05 | +| loss | -0.0255 | +| n_updates | 38168 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000166 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1421 | +| iterations | 5589 | +| time_elapsed | 8054 | +| total_timesteps | 11446272 | +| train/ | | +| approx_kl | 0.009007429 | +| clip_fraction | 0.299 | +| clip_range | 0.0721 | +| entropy_loss | -6.65 | +| explained_variance | 0.388 | +| learning_rate | 4.73e-05 | +| loss | -0.0302 | +| n_updates | 38172 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000141 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1421 | +| iterations | 5590 | +| time_elapsed | 8056 | +| total_timesteps | 11448320 | +| train/ | | +| approx_kl | 0.011632244 | +| clip_fraction | 0.316 | +| clip_range | 0.0721 | +| entropy_loss | -6.91 | +| explained_variance | 0.245 | +| learning_rate | 4.73e-05 | +| loss | -0.0281 | +| n_updates | 38176 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000156 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1421 | +| iterations | 5591 | +| time_elapsed | 8057 | +| total_timesteps | 11450368 | +| train/ | | +| approx_kl | 0.01154906 | +| clip_fraction | 0.319 | +| clip_range | 0.0721 | +| entropy_loss | -6.97 | +| explained_variance | 0.516 | +| learning_rate | 4.73e-05 | +| loss | -0.0239 | +| n_updates | 38180 | +| policy_gradient_loss | -0.0195 | +| value_loss | 9.6e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1421 | +| iterations | 5592 | +| time_elapsed | 8059 | +| total_timesteps | 11452416 | +| train/ | | +| approx_kl | 0.011030288 | +| clip_fraction | 0.315 | +| clip_range | 0.0721 | +| entropy_loss | -7.15 | +| explained_variance | 0.255 | +| learning_rate | 4.73e-05 | +| loss | -0.0297 | +| n_updates | 38184 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000222 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1421 | +| iterations | 5593 | +| time_elapsed | 8060 | +| total_timesteps | 11454464 | +| train/ | | +| approx_kl | 0.009376012 | +| clip_fraction | 0.317 | +| clip_range | 0.0721 | +| entropy_loss | -7.07 | +| explained_variance | 0.362 | +| learning_rate | 4.73e-05 | +| loss | -0.0319 | +| n_updates | 38188 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000116 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1421 | +| iterations | 5594 | +| time_elapsed | 8061 | +| total_timesteps | 11456512 | +| train/ | | +| approx_kl | 0.011646368 | +| clip_fraction | 0.304 | +| clip_range | 0.0721 | +| entropy_loss | -7.04 | +| explained_variance | 0.384 | +| learning_rate | 4.73e-05 | +| loss | -0.0286 | +| n_updates | 38192 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000192 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1421 | +| iterations | 5595 | +| time_elapsed | 8063 | +| total_timesteps | 11458560 | +| train/ | | +| approx_kl | 0.012082273 | +| clip_fraction | 0.327 | +| clip_range | 0.0721 | +| entropy_loss | -7.24 | +| explained_variance | 0.394 | +| learning_rate | 4.73e-05 | +| loss | -0.0358 | +| n_updates | 38196 | +| policy_gradient_loss | -0.0225 | +| value_loss | 7.27e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1421 | +| iterations | 5596 | +| time_elapsed | 8064 | +| total_timesteps | 11460608 | +| train/ | | +| approx_kl | 0.010179471 | +| clip_fraction | 0.319 | +| clip_range | 0.0721 | +| entropy_loss | -7.32 | +| explained_variance | -0.137 | +| learning_rate | 4.73e-05 | +| loss | -0.0278 | +| n_updates | 38200 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000153 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1421 | +| iterations | 5597 | +| time_elapsed | 8066 | +| total_timesteps | 11462656 | +| train/ | | +| approx_kl | 0.00977583 | +| clip_fraction | 0.333 | +| clip_range | 0.0721 | +| entropy_loss | -7.25 | +| explained_variance | 0.488 | +| learning_rate | 4.73e-05 | +| loss | -0.041 | +| n_updates | 38204 | +| policy_gradient_loss | -0.022 | +| value_loss | 6.24e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1421 | +| iterations | 5598 | +| time_elapsed | 8067 | +| total_timesteps | 11464704 | +| train/ | | +| approx_kl | 0.011320868 | +| clip_fraction | 0.302 | +| clip_range | 0.0721 | +| entropy_loss | -7.28 | +| explained_variance | 0.0592 | +| learning_rate | 4.73e-05 | +| loss | -0.0281 | +| n_updates | 38208 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000186 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1421 | +| iterations | 5599 | +| time_elapsed | 8069 | +| total_timesteps | 11466752 | +| train/ | | +| approx_kl | 0.009678577 | +| clip_fraction | 0.288 | +| clip_range | 0.0721 | +| entropy_loss | -6.7 | +| explained_variance | 0.393 | +| learning_rate | 4.73e-05 | +| loss | -0.0265 | +| n_updates | 38212 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.00021 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1421 | +| iterations | 5600 | +| time_elapsed | 8070 | +| total_timesteps | 11468800 | +| train/ | | +| approx_kl | 0.009403446 | +| clip_fraction | 0.322 | +| clip_range | 0.0721 | +| entropy_loss | -6.78 | +| explained_variance | 0.637 | +| learning_rate | 4.73e-05 | +| loss | -0.0371 | +| n_updates | 38216 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000105 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1421 | +| iterations | 5601 | +| time_elapsed | 8071 | +| total_timesteps | 11470848 | +| train/ | | +| approx_kl | 0.009282555 | +| clip_fraction | 0.309 | +| clip_range | 0.0721 | +| entropy_loss | -6.46 | +| explained_variance | 0.419 | +| learning_rate | 4.73e-05 | +| loss | -0.0223 | +| n_updates | 38220 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000298 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1421 | +| iterations | 5602 | +| time_elapsed | 8073 | +| total_timesteps | 11472896 | +| train/ | | +| approx_kl | 0.011790864 | +| clip_fraction | 0.314 | +| clip_range | 0.0721 | +| entropy_loss | -7.14 | +| explained_variance | 0.283 | +| learning_rate | 4.73e-05 | +| loss | -0.0298 | +| n_updates | 38224 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000133 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1421 | +| iterations | 5603 | +| time_elapsed | 8074 | +| total_timesteps | 11474944 | +| train/ | | +| approx_kl | 0.009664241 | +| clip_fraction | 0.338 | +| clip_range | 0.0721 | +| entropy_loss | -7.06 | +| explained_variance | 0.35 | +| learning_rate | 4.73e-05 | +| loss | -0.0286 | +| n_updates | 38228 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000114 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1421 | +| iterations | 5604 | +| time_elapsed | 8076 | +| total_timesteps | 11476992 | +| train/ | | +| approx_kl | 0.010371617 | +| clip_fraction | 0.302 | +| clip_range | 0.0721 | +| entropy_loss | -7.23 | +| explained_variance | 0.00423 | +| learning_rate | 4.73e-05 | +| loss | -0.0243 | +| n_updates | 38232 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.00023 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1421 | +| iterations | 5605 | +| time_elapsed | 8077 | +| total_timesteps | 11479040 | +| train/ | | +| approx_kl | 0.011337636 | +| clip_fraction | 0.309 | +| clip_range | 0.0721 | +| entropy_loss | -7.13 | +| explained_variance | 0.0147 | +| learning_rate | 4.73e-05 | +| loss | -0.0302 | +| n_updates | 38236 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000255 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1421 | +| iterations | 5606 | +| time_elapsed | 8078 | +| total_timesteps | 11481088 | +| train/ | | +| approx_kl | 0.010437623 | +| clip_fraction | 0.33 | +| clip_range | 0.0721 | +| entropy_loss | -7.45 | +| explained_variance | -0.0735 | +| learning_rate | 4.73e-05 | +| loss | -0.0308 | +| n_updates | 38240 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000146 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1421 | +| iterations | 5607 | +| time_elapsed | 8080 | +| total_timesteps | 11483136 | +| train/ | | +| approx_kl | 0.010701863 | +| clip_fraction | 0.321 | +| clip_range | 0.0721 | +| entropy_loss | -7.37 | +| explained_variance | -0.0768 | +| learning_rate | 4.73e-05 | +| loss | -0.0365 | +| n_updates | 38244 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000128 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1421 | +| iterations | 5608 | +| time_elapsed | 8081 | +| total_timesteps | 11485184 | +| train/ | | +| approx_kl | 0.012429005 | +| clip_fraction | 0.323 | +| clip_range | 0.0721 | +| entropy_loss | -7.39 | +| explained_variance | -0.0969 | +| learning_rate | 4.73e-05 | +| loss | -0.0283 | +| n_updates | 38248 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000175 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1421 | +| iterations | 5609 | +| time_elapsed | 8083 | +| total_timesteps | 11487232 | +| train/ | | +| approx_kl | 0.009813923 | +| clip_fraction | 0.34 | +| clip_range | 0.0721 | +| entropy_loss | -7.36 | +| explained_variance | -0.00874 | +| learning_rate | 4.73e-05 | +| loss | -0.0333 | +| n_updates | 38252 | +| policy_gradient_loss | -0.0213 | +| value_loss | 7.14e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1421 | +| iterations | 5610 | +| time_elapsed | 8084 | +| total_timesteps | 11489280 | +| train/ | | +| approx_kl | 0.010350857 | +| clip_fraction | 0.32 | +| clip_range | 0.0721 | +| entropy_loss | -6.85 | +| explained_variance | 0.463 | +| learning_rate | 4.73e-05 | +| loss | -0.0309 | +| n_updates | 38256 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000142 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1421 | +| iterations | 5611 | +| time_elapsed | 8086 | +| total_timesteps | 11491328 | +| train/ | | +| approx_kl | 0.011101242 | +| clip_fraction | 0.284 | +| clip_range | 0.0721 | +| entropy_loss | -7.12 | +| explained_variance | 0.0715 | +| learning_rate | 4.73e-05 | +| loss | -0.0269 | +| n_updates | 38260 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000176 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1421 | +| iterations | 5612 | +| time_elapsed | 8087 | +| total_timesteps | 11493376 | +| train/ | | +| approx_kl | 0.011163576 | +| clip_fraction | 0.289 | +| clip_range | 0.0721 | +| entropy_loss | -6.57 | +| explained_variance | 0.527 | +| learning_rate | 4.73e-05 | +| loss | -0.0266 | +| n_updates | 38264 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000155 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1421 | +| iterations | 5613 | +| time_elapsed | 8088 | +| total_timesteps | 11495424 | +| train/ | | +| approx_kl | 0.010902311 | +| clip_fraction | 0.326 | +| clip_range | 0.0721 | +| entropy_loss | -7.06 | +| explained_variance | 0.259 | +| learning_rate | 4.73e-05 | +| loss | -0.0323 | +| n_updates | 38268 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000152 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1421 | +| iterations | 5614 | +| time_elapsed | 8090 | +| total_timesteps | 11497472 | +| train/ | | +| approx_kl | 0.011394071 | +| clip_fraction | 0.331 | +| clip_range | 0.0721 | +| entropy_loss | -6.77 | +| explained_variance | 0.545 | +| learning_rate | 4.73e-05 | +| loss | -0.0303 | +| n_updates | 38272 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000133 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1421 | +| iterations | 5615 | +| time_elapsed | 8091 | +| total_timesteps | 11499520 | +| train/ | | +| approx_kl | 0.0110307485 | +| clip_fraction | 0.308 | +| clip_range | 0.0721 | +| entropy_loss | -6.97 | +| explained_variance | 0.0231 | +| learning_rate | 4.73e-05 | +| loss | -0.0281 | +| n_updates | 38276 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000405 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1421 | +| iterations | 5616 | +| time_elapsed | 8093 | +| total_timesteps | 11501568 | +| train/ | | +| approx_kl | 0.010996981 | +| clip_fraction | 0.315 | +| clip_range | 0.0721 | +| entropy_loss | -6.89 | +| explained_variance | 0.291 | +| learning_rate | 4.73e-05 | +| loss | -0.0334 | +| n_updates | 38280 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.00027 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1421 | +| iterations | 5617 | +| time_elapsed | 8094 | +| total_timesteps | 11503616 | +| train/ | | +| approx_kl | 0.01255697 | +| clip_fraction | 0.345 | +| clip_range | 0.0721 | +| entropy_loss | -7.12 | +| explained_variance | -0.216 | +| learning_rate | 4.73e-05 | +| loss | -0.0329 | +| n_updates | 38284 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000178 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1421 | +| iterations | 5618 | +| time_elapsed | 8096 | +| total_timesteps | 11505664 | +| train/ | | +| approx_kl | 0.010145245 | +| clip_fraction | 0.289 | +| clip_range | 0.0721 | +| entropy_loss | -6.92 | +| explained_variance | 0.187 | +| learning_rate | 4.73e-05 | +| loss | -0.021 | +| n_updates | 38288 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000299 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1421 | +| iterations | 5619 | +| time_elapsed | 8097 | +| total_timesteps | 11507712 | +| train/ | | +| approx_kl | 0.010772405 | +| clip_fraction | 0.328 | +| clip_range | 0.0721 | +| entropy_loss | -7.12 | +| explained_variance | 0.254 | +| learning_rate | 4.73e-05 | +| loss | -0.0372 | +| n_updates | 38292 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.00021 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1421 | +| iterations | 5620 | +| time_elapsed | 8098 | +| total_timesteps | 11509760 | +| train/ | | +| approx_kl | 0.009567713 | +| clip_fraction | 0.311 | +| clip_range | 0.0721 | +| entropy_loss | -7.08 | +| explained_variance | 0.218 | +| learning_rate | 4.73e-05 | +| loss | -0.0322 | +| n_updates | 38296 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000248 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1421 | +| iterations | 5621 | +| time_elapsed | 8100 | +| total_timesteps | 11511808 | +| train/ | | +| approx_kl | 0.011542484 | +| clip_fraction | 0.339 | +| clip_range | 0.0721 | +| entropy_loss | -7.14 | +| explained_variance | 0.166 | +| learning_rate | 4.73e-05 | +| loss | -0.0307 | +| n_updates | 38300 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000185 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1421 | +| iterations | 5622 | +| time_elapsed | 8101 | +| total_timesteps | 11513856 | +| train/ | | +| approx_kl | 0.013078151 | +| clip_fraction | 0.334 | +| clip_range | 0.0721 | +| entropy_loss | -7.1 | +| explained_variance | 0.426 | +| learning_rate | 4.73e-05 | +| loss | -0.0292 | +| n_updates | 38304 | +| policy_gradient_loss | -0.021 | +| value_loss | 9.05e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1421 | +| iterations | 5623 | +| time_elapsed | 8103 | +| total_timesteps | 11515904 | +| train/ | | +| approx_kl | 0.011420278 | +| clip_fraction | 0.312 | +| clip_range | 0.0721 | +| entropy_loss | -6.98 | +| explained_variance | 0.488 | +| learning_rate | 4.73e-05 | +| loss | -0.0266 | +| n_updates | 38308 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000173 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1421 | +| iterations | 5624 | +| time_elapsed | 8104 | +| total_timesteps | 11517952 | +| train/ | | +| approx_kl | 0.0105232 | +| clip_fraction | 0.307 | +| clip_range | 0.0721 | +| entropy_loss | -6.77 | +| explained_variance | 0.416 | +| learning_rate | 4.73e-05 | +| loss | -0.0276 | +| n_updates | 38312 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000229 | +--------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1421 | +| iterations | 5625 | +| time_elapsed | 8106 | +| total_timesteps | 11520000 | +| train/ | | +| approx_kl | 0.01180619 | +| clip_fraction | 0.342 | +| clip_range | 0.0721 | +| entropy_loss | -7.36 | +| explained_variance | -0.0956 | +| learning_rate | 4.73e-05 | +| loss | -0.0295 | +| n_updates | 38316 | +| policy_gradient_loss | -0.0215 | +| value_loss | 8.04e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1421 | +| iterations | 5626 | +| time_elapsed | 8107 | +| total_timesteps | 11522048 | +| train/ | | +| approx_kl | 0.009801282 | +| clip_fraction | 0.311 | +| clip_range | 0.0721 | +| entropy_loss | -6.71 | +| explained_variance | 0.512 | +| learning_rate | 4.73e-05 | +| loss | -0.0252 | +| n_updates | 38320 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000221 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1421 | +| iterations | 5627 | +| time_elapsed | 8108 | +| total_timesteps | 11524096 | +| train/ | | +| approx_kl | 0.010257771 | +| clip_fraction | 0.293 | +| clip_range | 0.0721 | +| entropy_loss | -6.58 | +| explained_variance | 0.399 | +| learning_rate | 4.73e-05 | +| loss | -0.0223 | +| n_updates | 38324 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000329 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1421 | +| iterations | 5628 | +| time_elapsed | 8110 | +| total_timesteps | 11526144 | +| train/ | | +| approx_kl | 0.010030545 | +| clip_fraction | 0.333 | +| clip_range | 0.0721 | +| entropy_loss | -7.33 | +| explained_variance | -0.0164 | +| learning_rate | 4.73e-05 | +| loss | -0.0258 | +| n_updates | 38328 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000352 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1421 | +| iterations | 5629 | +| time_elapsed | 8111 | +| total_timesteps | 11528192 | +| train/ | | +| approx_kl | 0.010679649 | +| clip_fraction | 0.322 | +| clip_range | 0.0721 | +| entropy_loss | -7.23 | +| explained_variance | 0.28 | +| learning_rate | 4.73e-05 | +| loss | -0.0366 | +| n_updates | 38332 | +| policy_gradient_loss | -0.022 | +| value_loss | 0.00018 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1421 | +| iterations | 5630 | +| time_elapsed | 8113 | +| total_timesteps | 11530240 | +| train/ | | +| approx_kl | 0.009050826 | +| clip_fraction | 0.297 | +| clip_range | 0.0721 | +| entropy_loss | -7.15 | +| explained_variance | 0.163 | +| learning_rate | 4.73e-05 | +| loss | -0.0335 | +| n_updates | 38336 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000263 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1421 | +| iterations | 5631 | +| time_elapsed | 8114 | +| total_timesteps | 11532288 | +| train/ | | +| approx_kl | 0.010172127 | +| clip_fraction | 0.317 | +| clip_range | 0.0721 | +| entropy_loss | -7.23 | +| explained_variance | 0.148 | +| learning_rate | 4.73e-05 | +| loss | -0.0271 | +| n_updates | 38340 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000195 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1421 | +| iterations | 5632 | +| time_elapsed | 8116 | +| total_timesteps | 11534336 | +| train/ | | +| approx_kl | 0.008932704 | +| clip_fraction | 0.31 | +| clip_range | 0.0721 | +| entropy_loss | -7.06 | +| explained_variance | 0.429 | +| learning_rate | 4.73e-05 | +| loss | -0.0312 | +| n_updates | 38344 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000208 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1421 | +| iterations | 5633 | +| time_elapsed | 8117 | +| total_timesteps | 11536384 | +| train/ | | +| approx_kl | 0.009857131 | +| clip_fraction | 0.325 | +| clip_range | 0.0721 | +| entropy_loss | -7.1 | +| explained_variance | 0.254 | +| learning_rate | 4.73e-05 | +| loss | -0.029 | +| n_updates | 38348 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000216 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.389 | +| time/ | | +| fps | 1421 | +| iterations | 5634 | +| time_elapsed | 8119 | +| total_timesteps | 11538432 | +| train/ | | +| approx_kl | 0.01089027 | +| clip_fraction | 0.331 | +| clip_range | 0.0721 | +| entropy_loss | -7.41 | +| explained_variance | -0.0808 | +| learning_rate | 4.73e-05 | +| loss | -0.0357 | +| n_updates | 38352 | +| policy_gradient_loss | -0.021 | +| value_loss | 9.02e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.392 | +| time/ | | +| fps | 1421 | +| iterations | 5635 | +| time_elapsed | 8120 | +| total_timesteps | 11540480 | +| train/ | | +| approx_kl | 0.008019215 | +| clip_fraction | 0.283 | +| clip_range | 0.0721 | +| entropy_loss | -7.16 | +| explained_variance | 0.137 | +| learning_rate | 4.73e-05 | +| loss | -0.0235 | +| n_updates | 38356 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000342 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.395 | +| time/ | | +| fps | 1421 | +| iterations | 5636 | +| time_elapsed | 8121 | +| total_timesteps | 11542528 | +| train/ | | +| approx_kl | 0.009355177 | +| clip_fraction | 0.3 | +| clip_range | 0.0721 | +| entropy_loss | -6.61 | +| explained_variance | 0.317 | +| learning_rate | 4.73e-05 | +| loss | -0.027 | +| n_updates | 38360 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000411 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.394 | +| time/ | | +| fps | 1421 | +| iterations | 5637 | +| time_elapsed | 8123 | +| total_timesteps | 11544576 | +| train/ | | +| approx_kl | 0.012617955 | +| clip_fraction | 0.354 | +| clip_range | 0.0721 | +| entropy_loss | -6.88 | +| explained_variance | 0.46 | +| learning_rate | 4.73e-05 | +| loss | -0.034 | +| n_updates | 38364 | +| policy_gradient_loss | -0.0231 | +| value_loss | 0.000107 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.393 | +| time/ | | +| fps | 1421 | +| iterations | 5638 | +| time_elapsed | 8124 | +| total_timesteps | 11546624 | +| train/ | | +| approx_kl | 0.012533052 | +| clip_fraction | 0.325 | +| clip_range | 0.0721 | +| entropy_loss | -7.28 | +| explained_variance | 0.00119 | +| learning_rate | 4.73e-05 | +| loss | -0.0365 | +| n_updates | 38368 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000163 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.393 | +| time/ | | +| fps | 1421 | +| iterations | 5639 | +| time_elapsed | 8126 | +| total_timesteps | 11548672 | +| train/ | | +| approx_kl | 0.009346338 | +| clip_fraction | 0.274 | +| clip_range | 0.0721 | +| entropy_loss | -6.89 | +| explained_variance | 0.446 | +| learning_rate | 4.73e-05 | +| loss | -0.0244 | +| n_updates | 38372 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000258 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.385 | +| time/ | | +| fps | 1421 | +| iterations | 5640 | +| time_elapsed | 8127 | +| total_timesteps | 11550720 | +| train/ | | +| approx_kl | 0.009594938 | +| clip_fraction | 0.313 | +| clip_range | 0.0721 | +| entropy_loss | -7.3 | +| explained_variance | -0.015 | +| learning_rate | 4.73e-05 | +| loss | -0.0312 | +| n_updates | 38376 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000178 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1421 | +| iterations | 5641 | +| time_elapsed | 8128 | +| total_timesteps | 11552768 | +| train/ | | +| approx_kl | 0.01061997 | +| clip_fraction | 0.349 | +| clip_range | 0.0721 | +| entropy_loss | -7.18 | +| explained_variance | 0.313 | +| learning_rate | 4.73e-05 | +| loss | -0.0319 | +| n_updates | 38380 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000122 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.384 | +| time/ | | +| fps | 1421 | +| iterations | 5642 | +| time_elapsed | 8130 | +| total_timesteps | 11554816 | +| train/ | | +| approx_kl | 0.011727216 | +| clip_fraction | 0.321 | +| clip_range | 0.0721 | +| entropy_loss | -6.73 | +| explained_variance | 0.264 | +| learning_rate | 4.73e-05 | +| loss | -0.0365 | +| n_updates | 38384 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000124 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1421 | +| iterations | 5643 | +| time_elapsed | 8131 | +| total_timesteps | 11556864 | +| train/ | | +| approx_kl | 0.008577872 | +| clip_fraction | 0.292 | +| clip_range | 0.0721 | +| entropy_loss | -6.75 | +| explained_variance | 0.417 | +| learning_rate | 4.73e-05 | +| loss | -0.0286 | +| n_updates | 38388 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000243 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.385 | +| time/ | | +| fps | 1421 | +| iterations | 5644 | +| time_elapsed | 8133 | +| total_timesteps | 11558912 | +| train/ | | +| approx_kl | 0.010914659 | +| clip_fraction | 0.339 | +| clip_range | 0.0721 | +| entropy_loss | -7.19 | +| explained_variance | 0.353 | +| learning_rate | 4.73e-05 | +| loss | -0.0282 | +| n_updates | 38392 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000104 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1421 | +| iterations | 5645 | +| time_elapsed | 8134 | +| total_timesteps | 11560960 | +| train/ | | +| approx_kl | 0.01086629 | +| clip_fraction | 0.305 | +| clip_range | 0.0721 | +| entropy_loss | -7.12 | +| explained_variance | 0.211 | +| learning_rate | 4.73e-05 | +| loss | -0.0254 | +| n_updates | 38396 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000247 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1421 | +| iterations | 5646 | +| time_elapsed | 8136 | +| total_timesteps | 11563008 | +| train/ | | +| approx_kl | 0.009896589 | +| clip_fraction | 0.307 | +| clip_range | 0.0721 | +| entropy_loss | -7.06 | +| explained_variance | 0.279 | +| learning_rate | 4.73e-05 | +| loss | -0.0291 | +| n_updates | 38400 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000142 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1421 | +| iterations | 5647 | +| time_elapsed | 8137 | +| total_timesteps | 11565056 | +| train/ | | +| approx_kl | 0.0106265545 | +| clip_fraction | 0.293 | +| clip_range | 0.0721 | +| entropy_loss | -6.97 | +| explained_variance | 0.225 | +| learning_rate | 4.73e-05 | +| loss | -0.0312 | +| n_updates | 38404 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000218 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1421 | +| iterations | 5648 | +| time_elapsed | 8138 | +| total_timesteps | 11567104 | +| train/ | | +| approx_kl | 0.011828836 | +| clip_fraction | 0.32 | +| clip_range | 0.0721 | +| entropy_loss | -7.21 | +| explained_variance | -0.0326 | +| learning_rate | 4.73e-05 | +| loss | -0.0294 | +| n_updates | 38408 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1421 | +| iterations | 5649 | +| time_elapsed | 8140 | +| total_timesteps | 11569152 | +| train/ | | +| approx_kl | 0.012327512 | +| clip_fraction | 0.327 | +| clip_range | 0.0721 | +| entropy_loss | -6.58 | +| explained_variance | 0.487 | +| learning_rate | 4.73e-05 | +| loss | -0.0309 | +| n_updates | 38412 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000158 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1421 | +| iterations | 5650 | +| time_elapsed | 8141 | +| total_timesteps | 11571200 | +| train/ | | +| approx_kl | 0.013661711 | +| clip_fraction | 0.364 | +| clip_range | 0.0721 | +| entropy_loss | -7.05 | +| explained_variance | 0.0285 | +| learning_rate | 4.73e-05 | +| loss | -0.0371 | +| n_updates | 38416 | +| policy_gradient_loss | -0.0222 | +| value_loss | 8.8e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1421 | +| iterations | 5651 | +| time_elapsed | 8143 | +| total_timesteps | 11573248 | +| train/ | | +| approx_kl | 0.012295519 | +| clip_fraction | 0.334 | +| clip_range | 0.0721 | +| entropy_loss | -7.08 | +| explained_variance | 0.34 | +| learning_rate | 4.73e-05 | +| loss | -0.0264 | +| n_updates | 38420 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000158 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1421 | +| iterations | 5652 | +| time_elapsed | 8144 | +| total_timesteps | 11575296 | +| train/ | | +| approx_kl | 0.010208391 | +| clip_fraction | 0.289 | +| clip_range | 0.0721 | +| entropy_loss | -7.31 | +| explained_variance | 0.0382 | +| learning_rate | 4.73e-05 | +| loss | -0.0236 | +| n_updates | 38424 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000205 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1421 | +| iterations | 5653 | +| time_elapsed | 8146 | +| total_timesteps | 11577344 | +| train/ | | +| approx_kl | 0.013413126 | +| clip_fraction | 0.305 | +| clip_range | 0.0721 | +| entropy_loss | -7.22 | +| explained_variance | 0.234 | +| learning_rate | 4.73e-05 | +| loss | -0.0355 | +| n_updates | 38428 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000164 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1421 | +| iterations | 5654 | +| time_elapsed | 8147 | +| total_timesteps | 11579392 | +| train/ | | +| approx_kl | 0.010045981 | +| clip_fraction | 0.299 | +| clip_range | 0.0721 | +| entropy_loss | -6.49 | +| explained_variance | 0.439 | +| learning_rate | 4.73e-05 | +| loss | -0.0301 | +| n_updates | 38432 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000224 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1421 | +| iterations | 5655 | +| time_elapsed | 8148 | +| total_timesteps | 11581440 | +| train/ | | +| approx_kl | 0.014537893 | +| clip_fraction | 0.316 | +| clip_range | 0.0721 | +| entropy_loss | -7.32 | +| explained_variance | -0.472 | +| learning_rate | 4.72e-05 | +| loss | -0.0333 | +| n_updates | 38436 | +| policy_gradient_loss | -0.0216 | +| value_loss | 7.14e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1421 | +| iterations | 5656 | +| time_elapsed | 8150 | +| total_timesteps | 11583488 | +| train/ | | +| approx_kl | 0.012379254 | +| clip_fraction | 0.329 | +| clip_range | 0.0721 | +| entropy_loss | -6.89 | +| explained_variance | 0.467 | +| learning_rate | 4.72e-05 | +| loss | -0.0326 | +| n_updates | 38440 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000123 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1421 | +| iterations | 5657 | +| time_elapsed | 8151 | +| total_timesteps | 11585536 | +| train/ | | +| approx_kl | 0.011777315 | +| clip_fraction | 0.321 | +| clip_range | 0.0721 | +| entropy_loss | -7.19 | +| explained_variance | 0.338 | +| learning_rate | 4.72e-05 | +| loss | -0.0333 | +| n_updates | 38444 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000124 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1421 | +| iterations | 5658 | +| time_elapsed | 8153 | +| total_timesteps | 11587584 | +| train/ | | +| approx_kl | 0.0098646255 | +| clip_fraction | 0.315 | +| clip_range | 0.0721 | +| entropy_loss | -7.28 | +| explained_variance | -0.142 | +| learning_rate | 4.72e-05 | +| loss | -0.022 | +| n_updates | 38448 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000108 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1421 | +| iterations | 5659 | +| time_elapsed | 8154 | +| total_timesteps | 11589632 | +| train/ | | +| approx_kl | 0.008558422 | +| clip_fraction | 0.31 | +| clip_range | 0.0721 | +| entropy_loss | -7.16 | +| explained_variance | 0.268 | +| learning_rate | 4.72e-05 | +| loss | -0.0264 | +| n_updates | 38452 | +| policy_gradient_loss | -0.0133 | +| value_loss | 0.0002 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1421 | +| iterations | 5660 | +| time_elapsed | 8156 | +| total_timesteps | 11591680 | +| train/ | | +| approx_kl | 0.011981152 | +| clip_fraction | 0.32 | +| clip_range | 0.0721 | +| entropy_loss | -6.81 | +| explained_variance | 0.622 | +| learning_rate | 4.72e-05 | +| loss | -0.0328 | +| n_updates | 38456 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000106 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1421 | +| iterations | 5661 | +| time_elapsed | 8157 | +| total_timesteps | 11593728 | +| train/ | | +| approx_kl | 0.010201045 | +| clip_fraction | 0.341 | +| clip_range | 0.0721 | +| entropy_loss | -6.96 | +| explained_variance | 0.499 | +| learning_rate | 4.72e-05 | +| loss | -0.0296 | +| n_updates | 38460 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000126 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1421 | +| iterations | 5662 | +| time_elapsed | 8159 | +| total_timesteps | 11595776 | +| train/ | | +| approx_kl | 0.0096351635 | +| clip_fraction | 0.308 | +| clip_range | 0.0721 | +| entropy_loss | -7.13 | +| explained_variance | -0.0698 | +| learning_rate | 4.72e-05 | +| loss | -0.0283 | +| n_updates | 38464 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000166 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.385 | +| time/ | | +| fps | 1421 | +| iterations | 5663 | +| time_elapsed | 8160 | +| total_timesteps | 11597824 | +| train/ | | +| approx_kl | 0.010958012 | +| clip_fraction | 0.329 | +| clip_range | 0.0721 | +| entropy_loss | -6.97 | +| explained_variance | 0.236 | +| learning_rate | 4.72e-05 | +| loss | -0.0312 | +| n_updates | 38468 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000198 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.385 | +| time/ | | +| fps | 1421 | +| iterations | 5664 | +| time_elapsed | 8162 | +| total_timesteps | 11599872 | +| train/ | | +| approx_kl | 0.012644467 | +| clip_fraction | 0.318 | +| clip_range | 0.0721 | +| entropy_loss | -6.96 | +| explained_variance | 0.3 | +| learning_rate | 4.72e-05 | +| loss | -0.0292 | +| n_updates | 38472 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000149 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1421 | +| iterations | 5665 | +| time_elapsed | 8163 | +| total_timesteps | 11601920 | +| train/ | | +| approx_kl | 0.012706116 | +| clip_fraction | 0.351 | +| clip_range | 0.0721 | +| entropy_loss | -7.32 | +| explained_variance | -0.223 | +| learning_rate | 4.72e-05 | +| loss | -0.0368 | +| n_updates | 38476 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000105 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1421 | +| iterations | 5666 | +| time_elapsed | 8164 | +| total_timesteps | 11603968 | +| train/ | | +| approx_kl | 0.011194032 | +| clip_fraction | 0.341 | +| clip_range | 0.0721 | +| entropy_loss | -7.1 | +| explained_variance | 0.52 | +| learning_rate | 4.72e-05 | +| loss | -0.0369 | +| n_updates | 38480 | +| policy_gradient_loss | -0.021 | +| value_loss | 6.52e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1421 | +| iterations | 5667 | +| time_elapsed | 8166 | +| total_timesteps | 11606016 | +| train/ | | +| approx_kl | 0.010975304 | +| clip_fraction | 0.313 | +| clip_range | 0.0721 | +| entropy_loss | -7.13 | +| explained_variance | 0.358 | +| learning_rate | 4.72e-05 | +| loss | -0.0308 | +| n_updates | 38484 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000134 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1421 | +| iterations | 5668 | +| time_elapsed | 8167 | +| total_timesteps | 11608064 | +| train/ | | +| approx_kl | 0.011110943 | +| clip_fraction | 0.307 | +| clip_range | 0.0721 | +| entropy_loss | -7.35 | +| explained_variance | -0.0605 | +| learning_rate | 4.72e-05 | +| loss | -0.0303 | +| n_updates | 38488 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.00017 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1421 | +| iterations | 5669 | +| time_elapsed | 8169 | +| total_timesteps | 11610112 | +| train/ | | +| approx_kl | 0.01243804 | +| clip_fraction | 0.316 | +| clip_range | 0.0721 | +| entropy_loss | -6.75 | +| explained_variance | 0.624 | +| learning_rate | 4.72e-05 | +| loss | -0.0244 | +| n_updates | 38492 | +| policy_gradient_loss | -0.0171 | +| value_loss | 9.96e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1421 | +| iterations | 5670 | +| time_elapsed | 8170 | +| total_timesteps | 11612160 | +| train/ | | +| approx_kl | 0.009963922 | +| clip_fraction | 0.322 | +| clip_range | 0.0721 | +| entropy_loss | -7.11 | +| explained_variance | 0.296 | +| learning_rate | 4.72e-05 | +| loss | -0.027 | +| n_updates | 38496 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000161 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1421 | +| iterations | 5671 | +| time_elapsed | 8172 | +| total_timesteps | 11614208 | +| train/ | | +| approx_kl | 0.009440436 | +| clip_fraction | 0.296 | +| clip_range | 0.0721 | +| entropy_loss | -6.47 | +| explained_variance | 0.594 | +| learning_rate | 4.72e-05 | +| loss | -0.0199 | +| n_updates | 38500 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000174 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1421 | +| iterations | 5672 | +| time_elapsed | 8173 | +| total_timesteps | 11616256 | +| train/ | | +| approx_kl | 0.009532212 | +| clip_fraction | 0.323 | +| clip_range | 0.0721 | +| entropy_loss | -7.08 | +| explained_variance | 0.339 | +| learning_rate | 4.72e-05 | +| loss | -0.0287 | +| n_updates | 38504 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000141 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1421 | +| iterations | 5673 | +| time_elapsed | 8174 | +| total_timesteps | 11618304 | +| train/ | | +| approx_kl | 0.012341263 | +| clip_fraction | 0.317 | +| clip_range | 0.0721 | +| entropy_loss | -6.79 | +| explained_variance | 0.561 | +| learning_rate | 4.72e-05 | +| loss | -0.0325 | +| n_updates | 38508 | +| policy_gradient_loss | -0.02 | +| value_loss | 9.36e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1421 | +| iterations | 5674 | +| time_elapsed | 8176 | +| total_timesteps | 11620352 | +| train/ | | +| approx_kl | 0.011214729 | +| clip_fraction | 0.323 | +| clip_range | 0.0721 | +| entropy_loss | -7.29 | +| explained_variance | -0.0998 | +| learning_rate | 4.72e-05 | +| loss | -0.0309 | +| n_updates | 38512 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.00012 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1421 | +| iterations | 5675 | +| time_elapsed | 8177 | +| total_timesteps | 11622400 | +| train/ | | +| approx_kl | 0.012011987 | +| clip_fraction | 0.32 | +| clip_range | 0.0721 | +| entropy_loss | -6.98 | +| explained_variance | 0.297 | +| learning_rate | 4.72e-05 | +| loss | -0.0292 | +| n_updates | 38516 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000102 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1421 | +| iterations | 5676 | +| time_elapsed | 8179 | +| total_timesteps | 11624448 | +| train/ | | +| approx_kl | 0.011575576 | +| clip_fraction | 0.322 | +| clip_range | 0.0721 | +| entropy_loss | -7.1 | +| explained_variance | 0.267 | +| learning_rate | 4.72e-05 | +| loss | -0.0295 | +| n_updates | 38520 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000191 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1421 | +| iterations | 5677 | +| time_elapsed | 8180 | +| total_timesteps | 11626496 | +| train/ | | +| approx_kl | 0.009602649 | +| clip_fraction | 0.319 | +| clip_range | 0.0721 | +| entropy_loss | -6.9 | +| explained_variance | 0.713 | +| learning_rate | 4.72e-05 | +| loss | -0.0293 | +| n_updates | 38524 | +| policy_gradient_loss | -0.0194 | +| value_loss | 5.31e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1421 | +| iterations | 5678 | +| time_elapsed | 8182 | +| total_timesteps | 11628544 | +| train/ | | +| approx_kl | 0.0077931527 | +| clip_fraction | 0.269 | +| clip_range | 0.0721 | +| entropy_loss | -7.04 | +| explained_variance | 0.322 | +| learning_rate | 4.72e-05 | +| loss | -0.0262 | +| n_updates | 38528 | +| policy_gradient_loss | -0.0137 | +| value_loss | 0.000302 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1421 | +| iterations | 5679 | +| time_elapsed | 8183 | +| total_timesteps | 11630592 | +| train/ | | +| approx_kl | 0.01251898 | +| clip_fraction | 0.316 | +| clip_range | 0.0721 | +| entropy_loss | -7.42 | +| explained_variance | -0.154 | +| learning_rate | 4.72e-05 | +| loss | -0.0358 | +| n_updates | 38532 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000131 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1421 | +| iterations | 5680 | +| time_elapsed | 8185 | +| total_timesteps | 11632640 | +| train/ | | +| approx_kl | 0.0114044165 | +| clip_fraction | 0.323 | +| clip_range | 0.0721 | +| entropy_loss | -7.26 | +| explained_variance | 0.258 | +| learning_rate | 4.72e-05 | +| loss | -0.0326 | +| n_updates | 38536 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000242 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1421 | +| iterations | 5681 | +| time_elapsed | 8186 | +| total_timesteps | 11634688 | +| train/ | | +| approx_kl | 0.010670032 | +| clip_fraction | 0.359 | +| clip_range | 0.0721 | +| entropy_loss | -7.25 | +| explained_variance | -0.669 | +| learning_rate | 4.72e-05 | +| loss | -0.0323 | +| n_updates | 38540 | +| policy_gradient_loss | -0.022 | +| value_loss | 8.59e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1421 | +| iterations | 5682 | +| time_elapsed | 8187 | +| total_timesteps | 11636736 | +| train/ | | +| approx_kl | 0.010574713 | +| clip_fraction | 0.304 | +| clip_range | 0.0721 | +| entropy_loss | -7.11 | +| explained_variance | 0.47 | +| learning_rate | 4.72e-05 | +| loss | -0.0262 | +| n_updates | 38544 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000151 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1421 | +| iterations | 5683 | +| time_elapsed | 8189 | +| total_timesteps | 11638784 | +| train/ | | +| approx_kl | 0.011059661 | +| clip_fraction | 0.299 | +| clip_range | 0.0721 | +| entropy_loss | -7.26 | +| explained_variance | -0.00694 | +| learning_rate | 4.72e-05 | +| loss | -0.0274 | +| n_updates | 38548 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000315 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1421 | +| iterations | 5684 | +| time_elapsed | 8190 | +| total_timesteps | 11640832 | +| train/ | | +| approx_kl | 0.009202491 | +| clip_fraction | 0.313 | +| clip_range | 0.0721 | +| entropy_loss | -6.75 | +| explained_variance | 0.619 | +| learning_rate | 4.72e-05 | +| loss | -0.0329 | +| n_updates | 38552 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000126 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1421 | +| iterations | 5685 | +| time_elapsed | 8192 | +| total_timesteps | 11642880 | +| train/ | | +| approx_kl | 0.011431048 | +| clip_fraction | 0.329 | +| clip_range | 0.0721 | +| entropy_loss | -6.61 | +| explained_variance | 0.504 | +| learning_rate | 4.72e-05 | +| loss | -0.0346 | +| n_updates | 38556 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.00013 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1421 | +| iterations | 5686 | +| time_elapsed | 8193 | +| total_timesteps | 11644928 | +| train/ | | +| approx_kl | 0.013586814 | +| clip_fraction | 0.339 | +| clip_range | 0.0721 | +| entropy_loss | -6.6 | +| explained_variance | 0.781 | +| learning_rate | 4.72e-05 | +| loss | -0.0352 | +| n_updates | 38560 | +| policy_gradient_loss | -0.0207 | +| value_loss | 6.41e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1421 | +| iterations | 5687 | +| time_elapsed | 8195 | +| total_timesteps | 11646976 | +| train/ | | +| approx_kl | 0.0093570305 | +| clip_fraction | 0.284 | +| clip_range | 0.0721 | +| entropy_loss | -7.15 | +| explained_variance | 0.35 | +| learning_rate | 4.72e-05 | +| loss | -0.0309 | +| n_updates | 38564 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000134 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1421 | +| iterations | 5688 | +| time_elapsed | 8196 | +| total_timesteps | 11649024 | +| train/ | | +| approx_kl | 0.011220128 | +| clip_fraction | 0.306 | +| clip_range | 0.0721 | +| entropy_loss | -6.9 | +| explained_variance | 0.239 | +| learning_rate | 4.72e-05 | +| loss | -0.0269 | +| n_updates | 38568 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.00038 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1421 | +| iterations | 5689 | +| time_elapsed | 8197 | +| total_timesteps | 11651072 | +| train/ | | +| approx_kl | 0.0109097455 | +| clip_fraction | 0.313 | +| clip_range | 0.0721 | +| entropy_loss | -7.01 | +| explained_variance | 0.12 | +| learning_rate | 4.72e-05 | +| loss | -0.0304 | +| n_updates | 38572 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.00017 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1421 | +| iterations | 5690 | +| time_elapsed | 8199 | +| total_timesteps | 11653120 | +| train/ | | +| approx_kl | 0.011076192 | +| clip_fraction | 0.314 | +| clip_range | 0.0721 | +| entropy_loss | -7.21 | +| explained_variance | 0.279 | +| learning_rate | 4.72e-05 | +| loss | -0.0315 | +| n_updates | 38576 | +| policy_gradient_loss | -0.0219 | +| value_loss | 0.000111 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1421 | +| iterations | 5691 | +| time_elapsed | 8200 | +| total_timesteps | 11655168 | +| train/ | | +| approx_kl | 0.010691565 | +| clip_fraction | 0.319 | +| clip_range | 0.0721 | +| entropy_loss | -7.25 | +| explained_variance | 0.308 | +| learning_rate | 4.72e-05 | +| loss | -0.0313 | +| n_updates | 38580 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000123 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1421 | +| iterations | 5692 | +| time_elapsed | 8202 | +| total_timesteps | 11657216 | +| train/ | | +| approx_kl | 0.012078903 | +| clip_fraction | 0.317 | +| clip_range | 0.0721 | +| entropy_loss | -6.95 | +| explained_variance | 0.403 | +| learning_rate | 4.72e-05 | +| loss | -0.0304 | +| n_updates | 38584 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000126 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1421 | +| iterations | 5693 | +| time_elapsed | 8203 | +| total_timesteps | 11659264 | +| train/ | | +| approx_kl | 0.010042616 | +| clip_fraction | 0.297 | +| clip_range | 0.0721 | +| entropy_loss | -7.01 | +| explained_variance | 0.404 | +| learning_rate | 4.72e-05 | +| loss | -0.0238 | +| n_updates | 38588 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000195 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1421 | +| iterations | 5694 | +| time_elapsed | 8204 | +| total_timesteps | 11661312 | +| train/ | | +| approx_kl | 0.010075665 | +| clip_fraction | 0.286 | +| clip_range | 0.0721 | +| entropy_loss | -6.98 | +| explained_variance | 0.218 | +| learning_rate | 4.72e-05 | +| loss | -0.0275 | +| n_updates | 38592 | +| policy_gradient_loss | -0.0148 | +| value_loss | 0.000306 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1421 | +| iterations | 5695 | +| time_elapsed | 8206 | +| total_timesteps | 11663360 | +| train/ | | +| approx_kl | 0.009348506 | +| clip_fraction | 0.317 | +| clip_range | 0.0721 | +| entropy_loss | -6.8 | +| explained_variance | 0.378 | +| learning_rate | 4.72e-05 | +| loss | -0.0326 | +| n_updates | 38596 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000187 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1421 | +| iterations | 5696 | +| time_elapsed | 8207 | +| total_timesteps | 11665408 | +| train/ | | +| approx_kl | 0.010292796 | +| clip_fraction | 0.321 | +| clip_range | 0.0721 | +| entropy_loss | -7.01 | +| explained_variance | 0.392 | +| learning_rate | 4.72e-05 | +| loss | -0.0317 | +| n_updates | 38600 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.00017 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1421 | +| iterations | 5697 | +| time_elapsed | 8209 | +| total_timesteps | 11667456 | +| train/ | | +| approx_kl | 0.010515796 | +| clip_fraction | 0.297 | +| clip_range | 0.0721 | +| entropy_loss | -6.88 | +| explained_variance | 0.353 | +| learning_rate | 4.72e-05 | +| loss | -0.0259 | +| n_updates | 38604 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000242 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1421 | +| iterations | 5698 | +| time_elapsed | 8210 | +| total_timesteps | 11669504 | +| train/ | | +| approx_kl | 0.0109122675 | +| clip_fraction | 0.315 | +| clip_range | 0.0721 | +| entropy_loss | -6.73 | +| explained_variance | 0.323 | +| learning_rate | 4.72e-05 | +| loss | -0.0226 | +| n_updates | 38608 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000303 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1421 | +| iterations | 5699 | +| time_elapsed | 8212 | +| total_timesteps | 11671552 | +| train/ | | +| approx_kl | 0.011127239 | +| clip_fraction | 0.324 | +| clip_range | 0.0721 | +| entropy_loss | -7.36 | +| explained_variance | -0.0436 | +| learning_rate | 4.72e-05 | +| loss | -0.0414 | +| n_updates | 38612 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000183 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1421 | +| iterations | 5700 | +| time_elapsed | 8213 | +| total_timesteps | 11673600 | +| train/ | | +| approx_kl | 0.009086263 | +| clip_fraction | 0.333 | +| clip_range | 0.0721 | +| entropy_loss | -7.43 | +| explained_variance | -0.14 | +| learning_rate | 4.72e-05 | +| loss | -0.0307 | +| n_updates | 38616 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000204 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1421 | +| iterations | 5701 | +| time_elapsed | 8214 | +| total_timesteps | 11675648 | +| train/ | | +| approx_kl | 0.0075100507 | +| clip_fraction | 0.312 | +| clip_range | 0.0721 | +| entropy_loss | -7.26 | +| explained_variance | 0.306 | +| learning_rate | 4.72e-05 | +| loss | -0.0367 | +| n_updates | 38620 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000124 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1421 | +| iterations | 5702 | +| time_elapsed | 8216 | +| total_timesteps | 11677696 | +| train/ | | +| approx_kl | 0.00973971 | +| clip_fraction | 0.268 | +| clip_range | 0.0721 | +| entropy_loss | -6.81 | +| explained_variance | 0.372 | +| learning_rate | 4.72e-05 | +| loss | -0.0249 | +| n_updates | 38624 | +| policy_gradient_loss | -0.0141 | +| value_loss | 0.0004 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1421 | +| iterations | 5703 | +| time_elapsed | 8217 | +| total_timesteps | 11679744 | +| train/ | | +| approx_kl | 0.011910512 | +| clip_fraction | 0.326 | +| clip_range | 0.0721 | +| entropy_loss | -6.85 | +| explained_variance | 0.55 | +| learning_rate | 4.72e-05 | +| loss | -0.0364 | +| n_updates | 38628 | +| policy_gradient_loss | -0.0236 | +| value_loss | 0.000108 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1421 | +| iterations | 5704 | +| time_elapsed | 8219 | +| total_timesteps | 11681792 | +| train/ | | +| approx_kl | 0.012194492 | +| clip_fraction | 0.353 | +| clip_range | 0.0721 | +| entropy_loss | -7.1 | +| explained_variance | 0.441 | +| learning_rate | 4.72e-05 | +| loss | -0.0375 | +| n_updates | 38632 | +| policy_gradient_loss | -0.0242 | +| value_loss | 6.28e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1421 | +| iterations | 5705 | +| time_elapsed | 8220 | +| total_timesteps | 11683840 | +| train/ | | +| approx_kl | 0.009044274 | +| clip_fraction | 0.272 | +| clip_range | 0.0721 | +| entropy_loss | -6.83 | +| explained_variance | 0.491 | +| learning_rate | 4.72e-05 | +| loss | -0.0277 | +| n_updates | 38636 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000231 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1421 | +| iterations | 5706 | +| time_elapsed | 8222 | +| total_timesteps | 11685888 | +| train/ | | +| approx_kl | 0.010831372 | +| clip_fraction | 0.328 | +| clip_range | 0.0721 | +| entropy_loss | -7.13 | +| explained_variance | 0.365 | +| learning_rate | 4.72e-05 | +| loss | -0.0297 | +| n_updates | 38640 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000126 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1421 | +| iterations | 5707 | +| time_elapsed | 8223 | +| total_timesteps | 11687936 | +| train/ | | +| approx_kl | 0.012960946 | +| clip_fraction | 0.337 | +| clip_range | 0.0721 | +| entropy_loss | -7.04 | +| explained_variance | -0.000645 | +| learning_rate | 4.72e-05 | +| loss | -0.0309 | +| n_updates | 38644 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000189 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1421 | +| iterations | 5708 | +| time_elapsed | 8225 | +| total_timesteps | 11689984 | +| train/ | | +| approx_kl | 0.011649238 | +| clip_fraction | 0.32 | +| clip_range | 0.0721 | +| entropy_loss | -7.09 | +| explained_variance | 0.00126 | +| learning_rate | 4.72e-05 | +| loss | -0.032 | +| n_updates | 38648 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000244 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1421 | +| iterations | 5709 | +| time_elapsed | 8226 | +| total_timesteps | 11692032 | +| train/ | | +| approx_kl | 0.009763807 | +| clip_fraction | 0.313 | +| clip_range | 0.0721 | +| entropy_loss | -7.15 | +| explained_variance | 0.271 | +| learning_rate | 4.72e-05 | +| loss | -0.0314 | +| n_updates | 38652 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000246 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1421 | +| iterations | 5710 | +| time_elapsed | 8227 | +| total_timesteps | 11694080 | +| train/ | | +| approx_kl | 0.009521533 | +| clip_fraction | 0.31 | +| clip_range | 0.0721 | +| entropy_loss | -6.93 | +| explained_variance | 0.344 | +| learning_rate | 4.72e-05 | +| loss | -0.0271 | +| n_updates | 38656 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000247 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1421 | +| iterations | 5711 | +| time_elapsed | 8229 | +| total_timesteps | 11696128 | +| train/ | | +| approx_kl | 0.0113137355 | +| clip_fraction | 0.345 | +| clip_range | 0.0721 | +| entropy_loss | -7.38 | +| explained_variance | -0.664 | +| learning_rate | 4.72e-05 | +| loss | -0.0373 | +| n_updates | 38660 | +| policy_gradient_loss | -0.0255 | +| value_loss | 8.57e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1421 | +| iterations | 5712 | +| time_elapsed | 8230 | +| total_timesteps | 11698176 | +| train/ | | +| approx_kl | 0.010003572 | +| clip_fraction | 0.302 | +| clip_range | 0.0721 | +| entropy_loss | -6.99 | +| explained_variance | 0.394 | +| learning_rate | 4.72e-05 | +| loss | -0.0226 | +| n_updates | 38664 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000182 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1421 | +| iterations | 5713 | +| time_elapsed | 8232 | +| total_timesteps | 11700224 | +| train/ | | +| approx_kl | 0.010826644 | +| clip_fraction | 0.28 | +| clip_range | 0.0721 | +| entropy_loss | -7.12 | +| explained_variance | 0.12 | +| learning_rate | 4.72e-05 | +| loss | -0.0269 | +| n_updates | 38668 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000159 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1421 | +| iterations | 5714 | +| time_elapsed | 8233 | +| total_timesteps | 11702272 | +| train/ | | +| approx_kl | 0.012241966 | +| clip_fraction | 0.336 | +| clip_range | 0.0721 | +| entropy_loss | -7.25 | +| explained_variance | 0.198 | +| learning_rate | 4.72e-05 | +| loss | -0.0378 | +| n_updates | 38672 | +| policy_gradient_loss | -0.0215 | +| value_loss | 9.65e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1421 | +| iterations | 5715 | +| time_elapsed | 8235 | +| total_timesteps | 11704320 | +| train/ | | +| approx_kl | 0.011495411 | +| clip_fraction | 0.319 | +| clip_range | 0.0721 | +| entropy_loss | -7.16 | +| explained_variance | 0.234 | +| learning_rate | 4.72e-05 | +| loss | -0.0308 | +| n_updates | 38676 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.00013 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1421 | +| iterations | 5716 | +| time_elapsed | 8236 | +| total_timesteps | 11706368 | +| train/ | | +| approx_kl | 0.00963175 | +| clip_fraction | 0.293 | +| clip_range | 0.0721 | +| entropy_loss | -6.99 | +| explained_variance | 0.359 | +| learning_rate | 4.72e-05 | +| loss | -0.0307 | +| n_updates | 38680 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000191 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1421 | +| iterations | 5717 | +| time_elapsed | 8237 | +| total_timesteps | 11708416 | +| train/ | | +| approx_kl | 0.010943513 | +| clip_fraction | 0.317 | +| clip_range | 0.0721 | +| entropy_loss | -7.12 | +| explained_variance | 0.00654 | +| learning_rate | 4.72e-05 | +| loss | -0.026 | +| n_updates | 38684 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000118 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1421 | +| iterations | 5718 | +| time_elapsed | 8239 | +| total_timesteps | 11710464 | +| train/ | | +| approx_kl | 0.010140536 | +| clip_fraction | 0.31 | +| clip_range | 0.0721 | +| entropy_loss | -7.5 | +| explained_variance | -0.0346 | +| learning_rate | 4.72e-05 | +| loss | -0.0302 | +| n_updates | 38688 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000138 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1421 | +| iterations | 5719 | +| time_elapsed | 8240 | +| total_timesteps | 11712512 | +| train/ | | +| approx_kl | 0.00966452 | +| clip_fraction | 0.282 | +| clip_range | 0.0721 | +| entropy_loss | -6.67 | +| explained_variance | 0.556 | +| learning_rate | 4.72e-05 | +| loss | -0.0219 | +| n_updates | 38692 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000226 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1421 | +| iterations | 5720 | +| time_elapsed | 8242 | +| total_timesteps | 11714560 | +| train/ | | +| approx_kl | 0.012264587 | +| clip_fraction | 0.309 | +| clip_range | 0.0721 | +| entropy_loss | -6.93 | +| explained_variance | 0.153 | +| learning_rate | 4.72e-05 | +| loss | -0.0304 | +| n_updates | 38696 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000133 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1421 | +| iterations | 5721 | +| time_elapsed | 8243 | +| total_timesteps | 11716608 | +| train/ | | +| approx_kl | 0.011242308 | +| clip_fraction | 0.318 | +| clip_range | 0.0721 | +| entropy_loss | -7.28 | +| explained_variance | -0.179 | +| learning_rate | 4.72e-05 | +| loss | -0.0312 | +| n_updates | 38700 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000155 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1421 | +| iterations | 5722 | +| time_elapsed | 8245 | +| total_timesteps | 11718656 | +| train/ | | +| approx_kl | 0.011112999 | +| clip_fraction | 0.302 | +| clip_range | 0.0721 | +| entropy_loss | -7 | +| explained_variance | 0.132 | +| learning_rate | 4.72e-05 | +| loss | -0.0317 | +| n_updates | 38704 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000231 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1421 | +| iterations | 5723 | +| time_elapsed | 8246 | +| total_timesteps | 11720704 | +| train/ | | +| approx_kl | 0.009702256 | +| clip_fraction | 0.312 | +| clip_range | 0.0721 | +| entropy_loss | -6.99 | +| explained_variance | 0.325 | +| learning_rate | 4.72e-05 | +| loss | -0.0312 | +| n_updates | 38708 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.00023 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1421 | +| iterations | 5724 | +| time_elapsed | 8247 | +| total_timesteps | 11722752 | +| train/ | | +| approx_kl | 0.010077803 | +| clip_fraction | 0.323 | +| clip_range | 0.0721 | +| entropy_loss | -7.15 | +| explained_variance | 0.294 | +| learning_rate | 4.72e-05 | +| loss | -0.0278 | +| n_updates | 38712 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000159 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1421 | +| iterations | 5725 | +| time_elapsed | 8249 | +| total_timesteps | 11724800 | +| train/ | | +| approx_kl | 0.010762349 | +| clip_fraction | 0.322 | +| clip_range | 0.0721 | +| entropy_loss | -7.5 | +| explained_variance | -0.0402 | +| learning_rate | 4.72e-05 | +| loss | -0.0298 | +| n_updates | 38716 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.00021 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1421 | +| iterations | 5726 | +| time_elapsed | 8250 | +| total_timesteps | 11726848 | +| train/ | | +| approx_kl | 0.010592388 | +| clip_fraction | 0.292 | +| clip_range | 0.0721 | +| entropy_loss | -7.02 | +| explained_variance | 0.436 | +| learning_rate | 4.72e-05 | +| loss | -0.0262 | +| n_updates | 38720 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000177 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1421 | +| iterations | 5727 | +| time_elapsed | 8252 | +| total_timesteps | 11728896 | +| train/ | | +| approx_kl | 0.011983156 | +| clip_fraction | 0.323 | +| clip_range | 0.0721 | +| entropy_loss | -7.34 | +| explained_variance | -0.0827 | +| learning_rate | 4.72e-05 | +| loss | -0.0313 | +| n_updates | 38724 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000158 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1421 | +| iterations | 5728 | +| time_elapsed | 8253 | +| total_timesteps | 11730944 | +| train/ | | +| approx_kl | 0.011341114 | +| clip_fraction | 0.337 | +| clip_range | 0.0721 | +| entropy_loss | -7.3 | +| explained_variance | -0.328 | +| learning_rate | 4.72e-05 | +| loss | -0.0322 | +| n_updates | 38728 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000107 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1421 | +| iterations | 5729 | +| time_elapsed | 8255 | +| total_timesteps | 11732992 | +| train/ | | +| approx_kl | 0.009765498 | +| clip_fraction | 0.292 | +| clip_range | 0.0721 | +| entropy_loss | -6.82 | +| explained_variance | 0.288 | +| learning_rate | 4.72e-05 | +| loss | -0.0272 | +| n_updates | 38732 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000375 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1421 | +| iterations | 5730 | +| time_elapsed | 8256 | +| total_timesteps | 11735040 | +| train/ | | +| approx_kl | 0.008579547 | +| clip_fraction | 0.311 | +| clip_range | 0.0721 | +| entropy_loss | -6.6 | +| explained_variance | 0.475 | +| learning_rate | 4.72e-05 | +| loss | -0.0277 | +| n_updates | 38736 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000298 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1421 | +| iterations | 5731 | +| time_elapsed | 8257 | +| total_timesteps | 11737088 | +| train/ | | +| approx_kl | 0.0086376835 | +| clip_fraction | 0.314 | +| clip_range | 0.0721 | +| entropy_loss | -6.51 | +| explained_variance | 0.425 | +| learning_rate | 4.72e-05 | +| loss | -0.0345 | +| n_updates | 38740 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000193 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1421 | +| iterations | 5732 | +| time_elapsed | 8259 | +| total_timesteps | 11739136 | +| train/ | | +| approx_kl | 0.010115106 | +| clip_fraction | 0.341 | +| clip_range | 0.0721 | +| entropy_loss | -7.16 | +| explained_variance | 0.385 | +| learning_rate | 4.72e-05 | +| loss | -0.0308 | +| n_updates | 38744 | +| policy_gradient_loss | -0.0217 | +| value_loss | 9.99e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1421 | +| iterations | 5733 | +| time_elapsed | 8260 | +| total_timesteps | 11741184 | +| train/ | | +| approx_kl | 0.009357877 | +| clip_fraction | 0.309 | +| clip_range | 0.0721 | +| entropy_loss | -7.19 | +| explained_variance | 0.00183 | +| learning_rate | 4.72e-05 | +| loss | -0.0326 | +| n_updates | 38748 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000231 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1421 | +| iterations | 5734 | +| time_elapsed | 8262 | +| total_timesteps | 11743232 | +| train/ | | +| approx_kl | 0.010443427 | +| clip_fraction | 0.301 | +| clip_range | 0.0721 | +| entropy_loss | -7.36 | +| explained_variance | 0.0509 | +| learning_rate | 4.72e-05 | +| loss | -0.0309 | +| n_updates | 38752 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000209 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1421 | +| iterations | 5735 | +| time_elapsed | 8263 | +| total_timesteps | 11745280 | +| train/ | | +| approx_kl | 0.00923462 | +| clip_fraction | 0.299 | +| clip_range | 0.0721 | +| entropy_loss | -7.25 | +| explained_variance | 0.142 | +| learning_rate | 4.72e-05 | +| loss | -0.0292 | +| n_updates | 38756 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000197 | +---------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1421 | +| iterations | 5736 | +| time_elapsed | 8265 | +| total_timesteps | 11747328 | +| train/ | | +| approx_kl | 0.0120689 | +| clip_fraction | 0.328 | +| clip_range | 0.0721 | +| entropy_loss | -7.46 | +| explained_variance | -0.141 | +| learning_rate | 4.72e-05 | +| loss | -0.036 | +| n_updates | 38760 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000177 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.391 | +| time/ | | +| fps | 1421 | +| iterations | 5737 | +| time_elapsed | 8266 | +| total_timesteps | 11749376 | +| train/ | | +| approx_kl | 0.009648867 | +| clip_fraction | 0.302 | +| clip_range | 0.0721 | +| entropy_loss | -7.24 | +| explained_variance | 0.0197 | +| learning_rate | 4.72e-05 | +| loss | -0.0285 | +| n_updates | 38764 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.00024 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.391 | +| time/ | | +| fps | 1421 | +| iterations | 5738 | +| time_elapsed | 8267 | +| total_timesteps | 11751424 | +| train/ | | +| approx_kl | 0.008479271 | +| clip_fraction | 0.298 | +| clip_range | 0.0721 | +| entropy_loss | -6.64 | +| explained_variance | 0.344 | +| learning_rate | 4.72e-05 | +| loss | -0.0265 | +| n_updates | 38768 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000365 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.393 | +| time/ | | +| fps | 1421 | +| iterations | 5739 | +| time_elapsed | 8269 | +| total_timesteps | 11753472 | +| train/ | | +| approx_kl | 0.012104402 | +| clip_fraction | 0.335 | +| clip_range | 0.0721 | +| entropy_loss | -6.44 | +| explained_variance | 0.556 | +| learning_rate | 4.72e-05 | +| loss | -0.0337 | +| n_updates | 38772 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000199 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.395 | +| time/ | | +| fps | 1421 | +| iterations | 5740 | +| time_elapsed | 8270 | +| total_timesteps | 11755520 | +| train/ | | +| approx_kl | 0.010759411 | +| clip_fraction | 0.334 | +| clip_range | 0.0721 | +| entropy_loss | -7.33 | +| explained_variance | 0.274 | +| learning_rate | 4.72e-05 | +| loss | -0.0299 | +| n_updates | 38776 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000177 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.391 | +| time/ | | +| fps | 1421 | +| iterations | 5741 | +| time_elapsed | 8272 | +| total_timesteps | 11757568 | +| train/ | | +| approx_kl | 0.010914224 | +| clip_fraction | 0.333 | +| clip_range | 0.0721 | +| entropy_loss | -7.11 | +| explained_variance | 0.33 | +| learning_rate | 4.72e-05 | +| loss | -0.0354 | +| n_updates | 38780 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000122 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.395 | +| time/ | | +| fps | 1421 | +| iterations | 5742 | +| time_elapsed | 8273 | +| total_timesteps | 11759616 | +| train/ | | +| approx_kl | 0.008590598 | +| clip_fraction | 0.304 | +| clip_range | 0.0721 | +| entropy_loss | -7.13 | +| explained_variance | 0.219 | +| learning_rate | 4.72e-05 | +| loss | -0.0289 | +| n_updates | 38784 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000339 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.405 | +| time/ | | +| fps | 1421 | +| iterations | 5743 | +| time_elapsed | 8274 | +| total_timesteps | 11761664 | +| train/ | | +| approx_kl | 0.009542513 | +| clip_fraction | 0.306 | +| clip_range | 0.0721 | +| entropy_loss | -6.92 | +| explained_variance | 0.466 | +| learning_rate | 4.72e-05 | +| loss | -0.0375 | +| n_updates | 38788 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000157 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.405 | +| time/ | | +| fps | 1421 | +| iterations | 5744 | +| time_elapsed | 8276 | +| total_timesteps | 11763712 | +| train/ | | +| approx_kl | 0.009657718 | +| clip_fraction | 0.278 | +| clip_range | 0.0721 | +| entropy_loss | -6.81 | +| explained_variance | 0.274 | +| learning_rate | 4.72e-05 | +| loss | -0.0223 | +| n_updates | 38792 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.00046 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.407 | +| time/ | | +| fps | 1421 | +| iterations | 5745 | +| time_elapsed | 8277 | +| total_timesteps | 11765760 | +| train/ | | +| approx_kl | 0.0116128 | +| clip_fraction | 0.359 | +| clip_range | 0.0721 | +| entropy_loss | -7.3 | +| explained_variance | -0.497 | +| learning_rate | 4.72e-05 | +| loss | -0.0387 | +| n_updates | 38796 | +| policy_gradient_loss | -0.0255 | +| value_loss | 8.94e-05 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.408 | +| time/ | | +| fps | 1421 | +| iterations | 5746 | +| time_elapsed | 8279 | +| total_timesteps | 11767808 | +| train/ | | +| approx_kl | 0.010816492 | +| clip_fraction | 0.3 | +| clip_range | 0.0721 | +| entropy_loss | -6.82 | +| explained_variance | 0.181 | +| learning_rate | 4.72e-05 | +| loss | -0.0234 | +| n_updates | 38800 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000375 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.413 | +| time/ | | +| fps | 1421 | +| iterations | 5747 | +| time_elapsed | 8280 | +| total_timesteps | 11769856 | +| train/ | | +| approx_kl | 0.011659741 | +| clip_fraction | 0.314 | +| clip_range | 0.0721 | +| entropy_loss | -6.91 | +| explained_variance | 0.215 | +| learning_rate | 4.72e-05 | +| loss | -0.0357 | +| n_updates | 38804 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.00031 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.413 | +| time/ | | +| fps | 1421 | +| iterations | 5748 | +| time_elapsed | 8282 | +| total_timesteps | 11771904 | +| train/ | | +| approx_kl | 0.009692285 | +| clip_fraction | 0.317 | +| clip_range | 0.0721 | +| entropy_loss | -6.86 | +| explained_variance | 0.382 | +| learning_rate | 4.72e-05 | +| loss | -0.0308 | +| n_updates | 38808 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000202 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.413 | +| time/ | | +| fps | 1421 | +| iterations | 5749 | +| time_elapsed | 8283 | +| total_timesteps | 11773952 | +| train/ | | +| approx_kl | 0.010936996 | +| clip_fraction | 0.342 | +| clip_range | 0.0721 | +| entropy_loss | -7.4 | +| explained_variance | -0.335 | +| learning_rate | 4.72e-05 | +| loss | -0.0366 | +| n_updates | 38812 | +| policy_gradient_loss | -0.0224 | +| value_loss | 0.000131 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.411 | +| time/ | | +| fps | 1421 | +| iterations | 5750 | +| time_elapsed | 8284 | +| total_timesteps | 11776000 | +| train/ | | +| approx_kl | 0.011417959 | +| clip_fraction | 0.324 | +| clip_range | 0.0721 | +| entropy_loss | -7.44 | +| explained_variance | -0.0975 | +| learning_rate | 4.72e-05 | +| loss | -0.0336 | +| n_updates | 38816 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000126 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.404 | +| time/ | | +| fps | 1421 | +| iterations | 5751 | +| time_elapsed | 8286 | +| total_timesteps | 11778048 | +| train/ | | +| approx_kl | 0.009489367 | +| clip_fraction | 0.298 | +| clip_range | 0.0721 | +| entropy_loss | -7.31 | +| explained_variance | 0.247 | +| learning_rate | 4.72e-05 | +| loss | -0.0303 | +| n_updates | 38820 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000194 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.408 | +| time/ | | +| fps | 1421 | +| iterations | 5752 | +| time_elapsed | 8287 | +| total_timesteps | 11780096 | +| train/ | | +| approx_kl | 0.008479596 | +| clip_fraction | 0.308 | +| clip_range | 0.0721 | +| entropy_loss | -7.11 | +| explained_variance | 0.575 | +| learning_rate | 4.72e-05 | +| loss | -0.0288 | +| n_updates | 38824 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000114 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.41 | +| time/ | | +| fps | 1421 | +| iterations | 5753 | +| time_elapsed | 8289 | +| total_timesteps | 11782144 | +| train/ | | +| approx_kl | 0.01131693 | +| clip_fraction | 0.326 | +| clip_range | 0.0721 | +| entropy_loss | -7.14 | +| explained_variance | 0.338 | +| learning_rate | 4.72e-05 | +| loss | -0.0294 | +| n_updates | 38828 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000115 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.408 | +| time/ | | +| fps | 1421 | +| iterations | 5754 | +| time_elapsed | 8290 | +| total_timesteps | 11784192 | +| train/ | | +| approx_kl | 0.012378256 | +| clip_fraction | 0.297 | +| clip_range | 0.0721 | +| entropy_loss | -7.16 | +| explained_variance | 0.344 | +| learning_rate | 4.72e-05 | +| loss | -0.0287 | +| n_updates | 38832 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000133 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.411 | +| time/ | | +| fps | 1421 | +| iterations | 5755 | +| time_elapsed | 8292 | +| total_timesteps | 11786240 | +| train/ | | +| approx_kl | 0.011439068 | +| clip_fraction | 0.287 | +| clip_range | 0.0721 | +| entropy_loss | -6.98 | +| explained_variance | 0.443 | +| learning_rate | 4.72e-05 | +| loss | -0.026 | +| n_updates | 38836 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000181 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.412 | +| time/ | | +| fps | 1421 | +| iterations | 5756 | +| time_elapsed | 8293 | +| total_timesteps | 11788288 | +| train/ | | +| approx_kl | 0.009652693 | +| clip_fraction | 0.311 | +| clip_range | 0.0721 | +| entropy_loss | -7.18 | +| explained_variance | 0.257 | +| learning_rate | 4.72e-05 | +| loss | -0.0247 | +| n_updates | 38840 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000176 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.412 | +| time/ | | +| fps | 1421 | +| iterations | 5757 | +| time_elapsed | 8295 | +| total_timesteps | 11790336 | +| train/ | | +| approx_kl | 0.009795856 | +| clip_fraction | 0.298 | +| clip_range | 0.0721 | +| entropy_loss | -7.17 | +| explained_variance | 0.388 | +| learning_rate | 4.72e-05 | +| loss | -0.0225 | +| n_updates | 38844 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000251 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.414 | +| time/ | | +| fps | 1421 | +| iterations | 5758 | +| time_elapsed | 8296 | +| total_timesteps | 11792384 | +| train/ | | +| approx_kl | 0.009600632 | +| clip_fraction | 0.312 | +| clip_range | 0.0721 | +| entropy_loss | -6.87 | +| explained_variance | 0.256 | +| learning_rate | 4.72e-05 | +| loss | -0.0283 | +| n_updates | 38848 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000132 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.416 | +| time/ | | +| fps | 1421 | +| iterations | 5759 | +| time_elapsed | 8297 | +| total_timesteps | 11794432 | +| train/ | | +| approx_kl | 0.010689117 | +| clip_fraction | 0.318 | +| clip_range | 0.0721 | +| entropy_loss | -6.77 | +| explained_variance | 0.66 | +| learning_rate | 4.72e-05 | +| loss | -0.0271 | +| n_updates | 38852 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000114 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.416 | +| time/ | | +| fps | 1421 | +| iterations | 5760 | +| time_elapsed | 8299 | +| total_timesteps | 11796480 | +| train/ | | +| approx_kl | 0.0098864315 | +| clip_fraction | 0.315 | +| clip_range | 0.0721 | +| entropy_loss | -7.23 | +| explained_variance | 0.426 | +| learning_rate | 4.72e-05 | +| loss | -0.0303 | +| n_updates | 38856 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000106 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.416 | +| time/ | | +| fps | 1421 | +| iterations | 5761 | +| time_elapsed | 8300 | +| total_timesteps | 11798528 | +| train/ | | +| approx_kl | 0.013155544 | +| clip_fraction | 0.338 | +| clip_range | 0.0721 | +| entropy_loss | -7.35 | +| explained_variance | -0.0491 | +| learning_rate | 4.72e-05 | +| loss | -0.0273 | +| n_updates | 38860 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000138 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.416 | +| time/ | | +| fps | 1421 | +| iterations | 5762 | +| time_elapsed | 8302 | +| total_timesteps | 11800576 | +| train/ | | +| approx_kl | 0.0106057 | +| clip_fraction | 0.309 | +| clip_range | 0.0721 | +| entropy_loss | -7.47 | +| explained_variance | -0.059 | +| learning_rate | 4.72e-05 | +| loss | -0.0287 | +| n_updates | 38864 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.00017 | +--------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.416 | +| time/ | | +| fps | 1421 | +| iterations | 5763 | +| time_elapsed | 8303 | +| total_timesteps | 11802624 | +| train/ | | +| approx_kl | 0.0111456625 | +| clip_fraction | 0.324 | +| clip_range | 0.072 | +| entropy_loss | -7.21 | +| explained_variance | 0.561 | +| learning_rate | 4.72e-05 | +| loss | -0.0317 | +| n_updates | 38868 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000117 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.414 | +| time/ | | +| fps | 1421 | +| iterations | 5764 | +| time_elapsed | 8305 | +| total_timesteps | 11804672 | +| train/ | | +| approx_kl | 0.011007316 | +| clip_fraction | 0.336 | +| clip_range | 0.072 | +| entropy_loss | -7.19 | +| explained_variance | 0.11 | +| learning_rate | 4.72e-05 | +| loss | -0.0342 | +| n_updates | 38872 | +| policy_gradient_loss | -0.0224 | +| value_loss | 0.000114 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.42 | +| time/ | | +| fps | 1421 | +| iterations | 5765 | +| time_elapsed | 8306 | +| total_timesteps | 11806720 | +| train/ | | +| approx_kl | 0.011272915 | +| clip_fraction | 0.308 | +| clip_range | 0.072 | +| entropy_loss | -7.15 | +| explained_variance | 0.281 | +| learning_rate | 4.72e-05 | +| loss | -0.024 | +| n_updates | 38876 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000236 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.42 | +| time/ | | +| fps | 1421 | +| iterations | 5766 | +| time_elapsed | 8307 | +| total_timesteps | 11808768 | +| train/ | | +| approx_kl | 0.010282592 | +| clip_fraction | 0.288 | +| clip_range | 0.072 | +| entropy_loss | -6.67 | +| explained_variance | 0.517 | +| learning_rate | 4.72e-05 | +| loss | -0.0255 | +| n_updates | 38880 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000257 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.42 | +| time/ | | +| fps | 1421 | +| iterations | 5767 | +| time_elapsed | 8309 | +| total_timesteps | 11810816 | +| train/ | | +| approx_kl | 0.012192621 | +| clip_fraction | 0.339 | +| clip_range | 0.072 | +| entropy_loss | -7.13 | +| explained_variance | 0.126 | +| learning_rate | 4.72e-05 | +| loss | -0.0384 | +| n_updates | 38884 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000126 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.419 | +| time/ | | +| fps | 1421 | +| iterations | 5768 | +| time_elapsed | 8310 | +| total_timesteps | 11812864 | +| train/ | | +| approx_kl | 0.011334936 | +| clip_fraction | 0.328 | +| clip_range | 0.072 | +| entropy_loss | -7.44 | +| explained_variance | -0.195 | +| learning_rate | 4.72e-05 | +| loss | -0.0333 | +| n_updates | 38888 | +| policy_gradient_loss | -0.0223 | +| value_loss | 0.000137 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.414 | +| time/ | | +| fps | 1421 | +| iterations | 5769 | +| time_elapsed | 8312 | +| total_timesteps | 11814912 | +| train/ | | +| approx_kl | 0.0097173005 | +| clip_fraction | 0.294 | +| clip_range | 0.072 | +| entropy_loss | -7 | +| explained_variance | 0.428 | +| learning_rate | 4.72e-05 | +| loss | -0.0328 | +| n_updates | 38892 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000161 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.416 | +| time/ | | +| fps | 1421 | +| iterations | 5770 | +| time_elapsed | 8313 | +| total_timesteps | 11816960 | +| train/ | | +| approx_kl | 0.011744108 | +| clip_fraction | 0.304 | +| clip_range | 0.072 | +| entropy_loss | -6.73 | +| explained_variance | 0.492 | +| learning_rate | 4.72e-05 | +| loss | -0.0333 | +| n_updates | 38896 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000166 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.412 | +| time/ | | +| fps | 1421 | +| iterations | 5771 | +| time_elapsed | 8315 | +| total_timesteps | 11819008 | +| train/ | | +| approx_kl | 0.011832774 | +| clip_fraction | 0.328 | +| clip_range | 0.072 | +| entropy_loss | -7.13 | +| explained_variance | 0.298 | +| learning_rate | 4.72e-05 | +| loss | -0.0317 | +| n_updates | 38900 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000109 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.412 | +| time/ | | +| fps | 1421 | +| iterations | 5772 | +| time_elapsed | 8316 | +| total_timesteps | 11821056 | +| train/ | | +| approx_kl | 0.010096865 | +| clip_fraction | 0.297 | +| clip_range | 0.072 | +| entropy_loss | -6.76 | +| explained_variance | 0.444 | +| learning_rate | 4.72e-05 | +| loss | -0.0262 | +| n_updates | 38904 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000133 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.411 | +| time/ | | +| fps | 1421 | +| iterations | 5773 | +| time_elapsed | 8318 | +| total_timesteps | 11823104 | +| train/ | | +| approx_kl | 0.009128589 | +| clip_fraction | 0.308 | +| clip_range | 0.072 | +| entropy_loss | -7.32 | +| explained_variance | -0.00531 | +| learning_rate | 4.72e-05 | +| loss | -0.0274 | +| n_updates | 38908 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000172 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.413 | +| time/ | | +| fps | 1421 | +| iterations | 5774 | +| time_elapsed | 8319 | +| total_timesteps | 11825152 | +| train/ | | +| approx_kl | 0.009101632 | +| clip_fraction | 0.312 | +| clip_range | 0.072 | +| entropy_loss | -7.28 | +| explained_variance | 0.221 | +| learning_rate | 4.72e-05 | +| loss | -0.0284 | +| n_updates | 38912 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000202 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.413 | +| time/ | | +| fps | 1421 | +| iterations | 5775 | +| time_elapsed | 8320 | +| total_timesteps | 11827200 | +| train/ | | +| approx_kl | 0.0096431635 | +| clip_fraction | 0.301 | +| clip_range | 0.072 | +| entropy_loss | -6.91 | +| explained_variance | 0.385 | +| learning_rate | 4.72e-05 | +| loss | -0.0275 | +| n_updates | 38916 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000199 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.413 | +| time/ | | +| fps | 1421 | +| iterations | 5776 | +| time_elapsed | 8322 | +| total_timesteps | 11829248 | +| train/ | | +| approx_kl | 0.009277545 | +| clip_fraction | 0.338 | +| clip_range | 0.072 | +| entropy_loss | -7.38 | +| explained_variance | -0.261 | +| learning_rate | 4.72e-05 | +| loss | -0.0366 | +| n_updates | 38920 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000102 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.413 | +| time/ | | +| fps | 1421 | +| iterations | 5777 | +| time_elapsed | 8323 | +| total_timesteps | 11831296 | +| train/ | | +| approx_kl | 0.010260007 | +| clip_fraction | 0.336 | +| clip_range | 0.072 | +| entropy_loss | -7.5 | +| explained_variance | -0.188 | +| learning_rate | 4.72e-05 | +| loss | -0.0371 | +| n_updates | 38924 | +| policy_gradient_loss | -0.021 | +| value_loss | 8.44e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.402 | +| time/ | | +| fps | 1421 | +| iterations | 5778 | +| time_elapsed | 8325 | +| total_timesteps | 11833344 | +| train/ | | +| approx_kl | 0.0110254865 | +| clip_fraction | 0.323 | +| clip_range | 0.072 | +| entropy_loss | -7.35 | +| explained_variance | 0.357 | +| learning_rate | 4.72e-05 | +| loss | -0.0298 | +| n_updates | 38928 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000118 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.409 | +| time/ | | +| fps | 1421 | +| iterations | 5779 | +| time_elapsed | 8326 | +| total_timesteps | 11835392 | +| train/ | | +| approx_kl | 0.0081435405 | +| clip_fraction | 0.294 | +| clip_range | 0.072 | +| entropy_loss | -7.14 | +| explained_variance | 0.283 | +| learning_rate | 4.72e-05 | +| loss | -0.0267 | +| n_updates | 38932 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000222 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.409 | +| time/ | | +| fps | 1421 | +| iterations | 5780 | +| time_elapsed | 8328 | +| total_timesteps | 11837440 | +| train/ | | +| approx_kl | 0.008578696 | +| clip_fraction | 0.282 | +| clip_range | 0.072 | +| entropy_loss | -6.7 | +| explained_variance | 0.269 | +| learning_rate | 4.72e-05 | +| loss | -0.0228 | +| n_updates | 38936 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.00031 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.408 | +| time/ | | +| fps | 1421 | +| iterations | 5781 | +| time_elapsed | 8329 | +| total_timesteps | 11839488 | +| train/ | | +| approx_kl | 0.009262206 | +| clip_fraction | 0.322 | +| clip_range | 0.072 | +| entropy_loss | -7.11 | +| explained_variance | 0.0695 | +| learning_rate | 4.72e-05 | +| loss | -0.0295 | +| n_updates | 38940 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000138 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.408 | +| time/ | | +| fps | 1421 | +| iterations | 5782 | +| time_elapsed | 8331 | +| total_timesteps | 11841536 | +| train/ | | +| approx_kl | 0.01120645 | +| clip_fraction | 0.309 | +| clip_range | 0.072 | +| entropy_loss | -6.81 | +| explained_variance | 0.282 | +| learning_rate | 4.72e-05 | +| loss | -0.0226 | +| n_updates | 38944 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000201 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.411 | +| time/ | | +| fps | 1421 | +| iterations | 5783 | +| time_elapsed | 8332 | +| total_timesteps | 11843584 | +| train/ | | +| approx_kl | 0.009849593 | +| clip_fraction | 0.278 | +| clip_range | 0.072 | +| entropy_loss | -6.76 | +| explained_variance | 0.33 | +| learning_rate | 4.72e-05 | +| loss | -0.0251 | +| n_updates | 38948 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.000358 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.404 | +| time/ | | +| fps | 1421 | +| iterations | 5784 | +| time_elapsed | 8334 | +| total_timesteps | 11845632 | +| train/ | | +| approx_kl | 0.00984952 | +| clip_fraction | 0.301 | +| clip_range | 0.072 | +| entropy_loss | -6.72 | +| explained_variance | 0.423 | +| learning_rate | 4.72e-05 | +| loss | -0.0282 | +| n_updates | 38952 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000177 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.409 | +| time/ | | +| fps | 1421 | +| iterations | 5785 | +| time_elapsed | 8335 | +| total_timesteps | 11847680 | +| train/ | | +| approx_kl | 0.009576014 | +| clip_fraction | 0.32 | +| clip_range | 0.072 | +| entropy_loss | -7.21 | +| explained_variance | -0.0141 | +| learning_rate | 4.72e-05 | +| loss | -0.0366 | +| n_updates | 38956 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000131 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.409 | +| time/ | | +| fps | 1421 | +| iterations | 5786 | +| time_elapsed | 8336 | +| total_timesteps | 11849728 | +| train/ | | +| approx_kl | 0.009073783 | +| clip_fraction | 0.302 | +| clip_range | 0.072 | +| entropy_loss | -7.2 | +| explained_variance | 0.161 | +| learning_rate | 4.72e-05 | +| loss | -0.0276 | +| n_updates | 38960 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000316 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.409 | +| time/ | | +| fps | 1421 | +| iterations | 5787 | +| time_elapsed | 8338 | +| total_timesteps | 11851776 | +| train/ | | +| approx_kl | 0.010433215 | +| clip_fraction | 0.305 | +| clip_range | 0.072 | +| entropy_loss | -7.38 | +| explained_variance | -0.0333 | +| learning_rate | 4.72e-05 | +| loss | -0.0295 | +| n_updates | 38964 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000225 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.41 | +| time/ | | +| fps | 1421 | +| iterations | 5788 | +| time_elapsed | 8339 | +| total_timesteps | 11853824 | +| train/ | | +| approx_kl | 0.011425458 | +| clip_fraction | 0.328 | +| clip_range | 0.072 | +| entropy_loss | -7.4 | +| explained_variance | -0.0382 | +| learning_rate | 4.72e-05 | +| loss | -0.0382 | +| n_updates | 38968 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000141 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.407 | +| time/ | | +| fps | 1421 | +| iterations | 5789 | +| time_elapsed | 8341 | +| total_timesteps | 11855872 | +| train/ | | +| approx_kl | 0.011252855 | +| clip_fraction | 0.296 | +| clip_range | 0.072 | +| entropy_loss | -7.3 | +| explained_variance | 0.29 | +| learning_rate | 4.72e-05 | +| loss | -0.0251 | +| n_updates | 38972 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000187 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.402 | +| time/ | | +| fps | 1421 | +| iterations | 5790 | +| time_elapsed | 8342 | +| total_timesteps | 11857920 | +| train/ | | +| approx_kl | 0.008695162 | +| clip_fraction | 0.304 | +| clip_range | 0.072 | +| entropy_loss | -7.33 | +| explained_variance | 0.126 | +| learning_rate | 4.72e-05 | +| loss | -0.0292 | +| n_updates | 38976 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000241 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.398 | +| time/ | | +| fps | 1421 | +| iterations | 5791 | +| time_elapsed | 8344 | +| total_timesteps | 11859968 | +| train/ | | +| approx_kl | 0.010841403 | +| clip_fraction | 0.343 | +| clip_range | 0.072 | +| entropy_loss | -6.89 | +| explained_variance | 0.761 | +| learning_rate | 4.72e-05 | +| loss | -0.0361 | +| n_updates | 38980 | +| policy_gradient_loss | -0.022 | +| value_loss | 6.19e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.389 | +| time/ | | +| fps | 1421 | +| iterations | 5792 | +| time_elapsed | 8345 | +| total_timesteps | 11862016 | +| train/ | | +| approx_kl | 0.010897937 | +| clip_fraction | 0.333 | +| clip_range | 0.072 | +| entropy_loss | -7.14 | +| explained_variance | 0.638 | +| learning_rate | 4.72e-05 | +| loss | -0.0342 | +| n_updates | 38984 | +| policy_gradient_loss | -0.0221 | +| value_loss | 6.02e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.385 | +| time/ | | +| fps | 1421 | +| iterations | 5793 | +| time_elapsed | 8346 | +| total_timesteps | 11864064 | +| train/ | | +| approx_kl | 0.010175855 | +| clip_fraction | 0.304 | +| clip_range | 0.072 | +| entropy_loss | -6.67 | +| explained_variance | 0.712 | +| learning_rate | 4.72e-05 | +| loss | -0.0209 | +| n_updates | 38988 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000122 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.385 | +| time/ | | +| fps | 1421 | +| iterations | 5794 | +| time_elapsed | 8348 | +| total_timesteps | 11866112 | +| train/ | | +| approx_kl | 0.010655442 | +| clip_fraction | 0.29 | +| clip_range | 0.072 | +| entropy_loss | -6.61 | +| explained_variance | 0.695 | +| learning_rate | 4.72e-05 | +| loss | -0.0286 | +| n_updates | 38992 | +| policy_gradient_loss | -0.0179 | +| value_loss | 7.51e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.385 | +| time/ | | +| fps | 1421 | +| iterations | 5795 | +| time_elapsed | 8349 | +| total_timesteps | 11868160 | +| train/ | | +| approx_kl | 0.0108653335 | +| clip_fraction | 0.327 | +| clip_range | 0.072 | +| entropy_loss | -7.19 | +| explained_variance | 0.457 | +| learning_rate | 4.72e-05 | +| loss | -0.0282 | +| n_updates | 38996 | +| policy_gradient_loss | -0.0183 | +| value_loss | 9.03e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1421 | +| iterations | 5796 | +| time_elapsed | 8351 | +| total_timesteps | 11870208 | +| train/ | | +| approx_kl | 0.008844716 | +| clip_fraction | 0.278 | +| clip_range | 0.072 | +| entropy_loss | -7.3 | +| explained_variance | 0.0106 | +| learning_rate | 4.72e-05 | +| loss | -0.0283 | +| n_updates | 39000 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000212 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.384 | +| time/ | | +| fps | 1421 | +| iterations | 5797 | +| time_elapsed | 8352 | +| total_timesteps | 11872256 | +| train/ | | +| approx_kl | 0.0103160925 | +| clip_fraction | 0.308 | +| clip_range | 0.072 | +| entropy_loss | -7.21 | +| explained_variance | -0.0086 | +| learning_rate | 4.72e-05 | +| loss | -0.0296 | +| n_updates | 39004 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000147 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.384 | +| time/ | | +| fps | 1421 | +| iterations | 5798 | +| time_elapsed | 8354 | +| total_timesteps | 11874304 | +| train/ | | +| approx_kl | 0.009260535 | +| clip_fraction | 0.323 | +| clip_range | 0.072 | +| entropy_loss | -6.91 | +| explained_variance | 0.242 | +| learning_rate | 4.72e-05 | +| loss | -0.0258 | +| n_updates | 39008 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000236 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.384 | +| time/ | | +| fps | 1421 | +| iterations | 5799 | +| time_elapsed | 8355 | +| total_timesteps | 11876352 | +| train/ | | +| approx_kl | 0.011110209 | +| clip_fraction | 0.332 | +| clip_range | 0.072 | +| entropy_loss | -7.29 | +| explained_variance | -0.0432 | +| learning_rate | 4.72e-05 | +| loss | -0.0315 | +| n_updates | 39012 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000156 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.384 | +| time/ | | +| fps | 1421 | +| iterations | 5800 | +| time_elapsed | 8357 | +| total_timesteps | 11878400 | +| train/ | | +| approx_kl | 0.009906639 | +| clip_fraction | 0.305 | +| clip_range | 0.072 | +| entropy_loss | -7.41 | +| explained_variance | 0.168 | +| learning_rate | 4.72e-05 | +| loss | -0.0293 | +| n_updates | 39016 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000157 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.384 | +| time/ | | +| fps | 1421 | +| iterations | 5801 | +| time_elapsed | 8358 | +| total_timesteps | 11880448 | +| train/ | | +| approx_kl | 0.011455245 | +| clip_fraction | 0.363 | +| clip_range | 0.072 | +| entropy_loss | -7.38 | +| explained_variance | -0.693 | +| learning_rate | 4.72e-05 | +| loss | -0.0447 | +| n_updates | 39020 | +| policy_gradient_loss | -0.028 | +| value_loss | 3.66e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1421 | +| iterations | 5802 | +| time_elapsed | 8359 | +| total_timesteps | 11882496 | +| train/ | | +| approx_kl | 0.0092346845 | +| clip_fraction | 0.315 | +| clip_range | 0.072 | +| entropy_loss | -7.45 | +| explained_variance | 0.466 | +| learning_rate | 4.72e-05 | +| loss | -0.0317 | +| n_updates | 39024 | +| policy_gradient_loss | -0.0168 | +| value_loss | 7.84e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1421 | +| iterations | 5803 | +| time_elapsed | 8361 | +| total_timesteps | 11884544 | +| train/ | | +| approx_kl | 0.010306247 | +| clip_fraction | 0.295 | +| clip_range | 0.072 | +| entropy_loss | -7.1 | +| explained_variance | 0.665 | +| learning_rate | 4.72e-05 | +| loss | -0.0306 | +| n_updates | 39028 | +| policy_gradient_loss | -0.019 | +| value_loss | 7.43e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1421 | +| iterations | 5804 | +| time_elapsed | 8362 | +| total_timesteps | 11886592 | +| train/ | | +| approx_kl | 0.010194833 | +| clip_fraction | 0.269 | +| clip_range | 0.072 | +| entropy_loss | -7.33 | +| explained_variance | 0.0838 | +| learning_rate | 4.72e-05 | +| loss | -0.032 | +| n_updates | 39032 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000125 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1421 | +| iterations | 5805 | +| time_elapsed | 8364 | +| total_timesteps | 11888640 | +| train/ | | +| approx_kl | 0.010137066 | +| clip_fraction | 0.28 | +| clip_range | 0.072 | +| entropy_loss | -6.83 | +| explained_variance | 0.313 | +| learning_rate | 4.72e-05 | +| loss | -0.0212 | +| n_updates | 39036 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000225 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1421 | +| iterations | 5806 | +| time_elapsed | 8365 | +| total_timesteps | 11890688 | +| train/ | | +| approx_kl | 0.0125504015 | +| clip_fraction | 0.343 | +| clip_range | 0.072 | +| entropy_loss | -7.07 | +| explained_variance | 0.229 | +| learning_rate | 4.72e-05 | +| loss | -0.0294 | +| n_updates | 39040 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000134 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1421 | +| iterations | 5807 | +| time_elapsed | 8367 | +| total_timesteps | 11892736 | +| train/ | | +| approx_kl | 0.0118882535 | +| clip_fraction | 0.337 | +| clip_range | 0.072 | +| entropy_loss | -6.95 | +| explained_variance | 0.686 | +| learning_rate | 4.72e-05 | +| loss | -0.0309 | +| n_updates | 39044 | +| policy_gradient_loss | -0.0207 | +| value_loss | 7.14e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1421 | +| iterations | 5808 | +| time_elapsed | 8368 | +| total_timesteps | 11894784 | +| train/ | | +| approx_kl | 0.010433627 | +| clip_fraction | 0.304 | +| clip_range | 0.072 | +| entropy_loss | -7.18 | +| explained_variance | 0.282 | +| learning_rate | 4.72e-05 | +| loss | -0.0317 | +| n_updates | 39048 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000124 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1421 | +| iterations | 5809 | +| time_elapsed | 8370 | +| total_timesteps | 11896832 | +| train/ | | +| approx_kl | 0.010302924 | +| clip_fraction | 0.288 | +| clip_range | 0.072 | +| entropy_loss | -7.1 | +| explained_variance | 0.352 | +| learning_rate | 4.72e-05 | +| loss | -0.0254 | +| n_updates | 39052 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000222 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1421 | +| iterations | 5810 | +| time_elapsed | 8371 | +| total_timesteps | 11898880 | +| train/ | | +| approx_kl | 0.008499101 | +| clip_fraction | 0.331 | +| clip_range | 0.072 | +| entropy_loss | -7.28 | +| explained_variance | 0.0125 | +| learning_rate | 4.72e-05 | +| loss | -0.0342 | +| n_updates | 39056 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000154 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1421 | +| iterations | 5811 | +| time_elapsed | 8372 | +| total_timesteps | 11900928 | +| train/ | | +| approx_kl | 0.00866287 | +| clip_fraction | 0.304 | +| clip_range | 0.072 | +| entropy_loss | -6.59 | +| explained_variance | 0.556 | +| learning_rate | 4.72e-05 | +| loss | -0.0285 | +| n_updates | 39060 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000204 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1421 | +| iterations | 5812 | +| time_elapsed | 8374 | +| total_timesteps | 11902976 | +| train/ | | +| approx_kl | 0.010974181 | +| clip_fraction | 0.327 | +| clip_range | 0.072 | +| entropy_loss | -6.98 | +| explained_variance | 0.286 | +| learning_rate | 4.72e-05 | +| loss | -0.0292 | +| n_updates | 39064 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000194 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1421 | +| iterations | 5813 | +| time_elapsed | 8375 | +| total_timesteps | 11905024 | +| train/ | | +| approx_kl | 0.010863459 | +| clip_fraction | 0.318 | +| clip_range | 0.072 | +| entropy_loss | -7.29 | +| explained_variance | 0.146 | +| learning_rate | 4.72e-05 | +| loss | -0.0288 | +| n_updates | 39068 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000221 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1421 | +| iterations | 5814 | +| time_elapsed | 8377 | +| total_timesteps | 11907072 | +| train/ | | +| approx_kl | 0.009415148 | +| clip_fraction | 0.311 | +| clip_range | 0.072 | +| entropy_loss | -7.28 | +| explained_variance | -0.185 | +| learning_rate | 4.72e-05 | +| loss | -0.0382 | +| n_updates | 39072 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000201 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1421 | +| iterations | 5815 | +| time_elapsed | 8378 | +| total_timesteps | 11909120 | +| train/ | | +| approx_kl | 0.009474304 | +| clip_fraction | 0.309 | +| clip_range | 0.072 | +| entropy_loss | -7.1 | +| explained_variance | 0.182 | +| learning_rate | 4.72e-05 | +| loss | -0.0202 | +| n_updates | 39076 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000206 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1421 | +| iterations | 5816 | +| time_elapsed | 8380 | +| total_timesteps | 11911168 | +| train/ | | +| approx_kl | 0.009830945 | +| clip_fraction | 0.301 | +| clip_range | 0.072 | +| entropy_loss | -7.46 | +| explained_variance | -0.127 | +| learning_rate | 4.72e-05 | +| loss | -0.0325 | +| n_updates | 39080 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000169 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1421 | +| iterations | 5817 | +| time_elapsed | 8381 | +| total_timesteps | 11913216 | +| train/ | | +| approx_kl | 0.010351561 | +| clip_fraction | 0.325 | +| clip_range | 0.072 | +| entropy_loss | -7.28 | +| explained_variance | 0.393 | +| learning_rate | 4.72e-05 | +| loss | -0.0388 | +| n_updates | 39084 | +| policy_gradient_loss | -0.0223 | +| value_loss | 7.54e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1421 | +| iterations | 5818 | +| time_elapsed | 8382 | +| total_timesteps | 11915264 | +| train/ | | +| approx_kl | 0.01224865 | +| clip_fraction | 0.342 | +| clip_range | 0.072 | +| entropy_loss | -7.46 | +| explained_variance | -0.281 | +| learning_rate | 4.72e-05 | +| loss | -0.0318 | +| n_updates | 39088 | +| policy_gradient_loss | -0.0214 | +| value_loss | 5.84e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1421 | +| iterations | 5819 | +| time_elapsed | 8384 | +| total_timesteps | 11917312 | +| train/ | | +| approx_kl | 0.011869526 | +| clip_fraction | 0.307 | +| clip_range | 0.072 | +| entropy_loss | -7.19 | +| explained_variance | 0.0549 | +| learning_rate | 4.72e-05 | +| loss | -0.0259 | +| n_updates | 39092 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000198 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1421 | +| iterations | 5820 | +| time_elapsed | 8385 | +| total_timesteps | 11919360 | +| train/ | | +| approx_kl | 0.011184143 | +| clip_fraction | 0.306 | +| clip_range | 0.072 | +| entropy_loss | -7.18 | +| explained_variance | 0.289 | +| learning_rate | 4.72e-05 | +| loss | -0.0285 | +| n_updates | 39096 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000106 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1421 | +| iterations | 5821 | +| time_elapsed | 8387 | +| total_timesteps | 11921408 | +| train/ | | +| approx_kl | 0.011044031 | +| clip_fraction | 0.31 | +| clip_range | 0.072 | +| entropy_loss | -7.18 | +| explained_variance | 0.348 | +| learning_rate | 4.72e-05 | +| loss | -0.0314 | +| n_updates | 39100 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000257 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1421 | +| iterations | 5822 | +| time_elapsed | 8388 | +| total_timesteps | 11923456 | +| train/ | | +| approx_kl | 0.009792913 | +| clip_fraction | 0.32 | +| clip_range | 0.072 | +| entropy_loss | -6.61 | +| explained_variance | 0.595 | +| learning_rate | 4.72e-05 | +| loss | -0.0306 | +| n_updates | 39104 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000206 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1421 | +| iterations | 5823 | +| time_elapsed | 8390 | +| total_timesteps | 11925504 | +| train/ | | +| approx_kl | 0.010655368 | +| clip_fraction | 0.324 | +| clip_range | 0.072 | +| entropy_loss | -7.24 | +| explained_variance | 0.574 | +| learning_rate | 4.72e-05 | +| loss | -0.0286 | +| n_updates | 39108 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000113 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1421 | +| iterations | 5824 | +| time_elapsed | 8391 | +| total_timesteps | 11927552 | +| train/ | | +| approx_kl | 0.010168505 | +| clip_fraction | 0.306 | +| clip_range | 0.072 | +| entropy_loss | -7.2 | +| explained_variance | 0.618 | +| learning_rate | 4.72e-05 | +| loss | -0.029 | +| n_updates | 39112 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000111 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1421 | +| iterations | 5825 | +| time_elapsed | 8392 | +| total_timesteps | 11929600 | +| train/ | | +| approx_kl | 0.010273362 | +| clip_fraction | 0.314 | +| clip_range | 0.072 | +| entropy_loss | -7.15 | +| explained_variance | 0.412 | +| learning_rate | 4.72e-05 | +| loss | -0.0282 | +| n_updates | 39116 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000116 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1421 | +| iterations | 5826 | +| time_elapsed | 8394 | +| total_timesteps | 11931648 | +| train/ | | +| approx_kl | 0.01119652 | +| clip_fraction | 0.306 | +| clip_range | 0.072 | +| entropy_loss | -7.39 | +| explained_variance | -0.0913 | +| learning_rate | 4.72e-05 | +| loss | -0.0302 | +| n_updates | 39120 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000166 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1421 | +| iterations | 5827 | +| time_elapsed | 8395 | +| total_timesteps | 11933696 | +| train/ | | +| approx_kl | 0.0132479295 | +| clip_fraction | 0.341 | +| clip_range | 0.072 | +| entropy_loss | -7.25 | +| explained_variance | 0.214 | +| learning_rate | 4.72e-05 | +| loss | -0.033 | +| n_updates | 39124 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000128 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1421 | +| iterations | 5828 | +| time_elapsed | 8397 | +| total_timesteps | 11935744 | +| train/ | | +| approx_kl | 0.01061276 | +| clip_fraction | 0.314 | +| clip_range | 0.072 | +| entropy_loss | -7.15 | +| explained_variance | 0.217 | +| learning_rate | 4.72e-05 | +| loss | -0.0307 | +| n_updates | 39128 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000229 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1421 | +| iterations | 5829 | +| time_elapsed | 8398 | +| total_timesteps | 11937792 | +| train/ | | +| approx_kl | 0.0115878675 | +| clip_fraction | 0.318 | +| clip_range | 0.072 | +| entropy_loss | -7.39 | +| explained_variance | -0.0445 | +| learning_rate | 4.72e-05 | +| loss | -0.0365 | +| n_updates | 39132 | +| policy_gradient_loss | -0.0213 | +| value_loss | 5.12e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1421 | +| iterations | 5830 | +| time_elapsed | 8400 | +| total_timesteps | 11939840 | +| train/ | | +| approx_kl | 0.012400394 | +| clip_fraction | 0.315 | +| clip_range | 0.072 | +| entropy_loss | -7.13 | +| explained_variance | 0.483 | +| learning_rate | 4.72e-05 | +| loss | -0.0287 | +| n_updates | 39136 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.00016 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1421 | +| iterations | 5831 | +| time_elapsed | 8401 | +| total_timesteps | 11941888 | +| train/ | | +| approx_kl | 0.009786957 | +| clip_fraction | 0.28 | +| clip_range | 0.072 | +| entropy_loss | -7.15 | +| explained_variance | 0.454 | +| learning_rate | 4.72e-05 | +| loss | -0.0284 | +| n_updates | 39140 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000207 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1421 | +| iterations | 5832 | +| time_elapsed | 8402 | +| total_timesteps | 11943936 | +| train/ | | +| approx_kl | 0.010036056 | +| clip_fraction | 0.319 | +| clip_range | 0.072 | +| entropy_loss | -7.29 | +| explained_variance | 0.0714 | +| learning_rate | 4.72e-05 | +| loss | -0.0303 | +| n_updates | 39144 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.315 | +| time/ | | +| fps | 1421 | +| iterations | 5833 | +| time_elapsed | 8404 | +| total_timesteps | 11945984 | +| train/ | | +| approx_kl | 0.010862891 | +| clip_fraction | 0.3 | +| clip_range | 0.072 | +| entropy_loss | -7.15 | +| explained_variance | 0.43 | +| learning_rate | 4.72e-05 | +| loss | -0.0324 | +| n_updates | 39148 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000197 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1421 | +| iterations | 5834 | +| time_elapsed | 8405 | +| total_timesteps | 11948032 | +| train/ | | +| approx_kl | 0.009495895 | +| clip_fraction | 0.311 | +| clip_range | 0.072 | +| entropy_loss | -7.02 | +| explained_variance | 0.274 | +| learning_rate | 4.72e-05 | +| loss | -0.028 | +| n_updates | 39152 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000186 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1421 | +| iterations | 5835 | +| time_elapsed | 8407 | +| total_timesteps | 11950080 | +| train/ | | +| approx_kl | 0.010410346 | +| clip_fraction | 0.314 | +| clip_range | 0.072 | +| entropy_loss | -7.06 | +| explained_variance | 0.51 | +| learning_rate | 4.72e-05 | +| loss | -0.0327 | +| n_updates | 39156 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000135 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1421 | +| iterations | 5836 | +| time_elapsed | 8408 | +| total_timesteps | 11952128 | +| train/ | | +| approx_kl | 0.010372668 | +| clip_fraction | 0.308 | +| clip_range | 0.072 | +| entropy_loss | -7.07 | +| explained_variance | 0.309 | +| learning_rate | 4.72e-05 | +| loss | -0.0324 | +| n_updates | 39160 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000146 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.315 | +| time/ | | +| fps | 1421 | +| iterations | 5837 | +| time_elapsed | 8410 | +| total_timesteps | 11954176 | +| train/ | | +| approx_kl | 0.012462769 | +| clip_fraction | 0.354 | +| clip_range | 0.072 | +| entropy_loss | -7.24 | +| explained_variance | -0.212 | +| learning_rate | 4.72e-05 | +| loss | -0.0374 | +| n_updates | 39164 | +| policy_gradient_loss | -0.0235 | +| value_loss | 7.27e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.306 | +| time/ | | +| fps | 1421 | +| iterations | 5838 | +| time_elapsed | 8411 | +| total_timesteps | 11956224 | +| train/ | | +| approx_kl | 0.012355253 | +| clip_fraction | 0.345 | +| clip_range | 0.072 | +| entropy_loss | -6.77 | +| explained_variance | 0.694 | +| learning_rate | 4.72e-05 | +| loss | -0.0246 | +| n_updates | 39168 | +| policy_gradient_loss | -0.0185 | +| value_loss | 9.53e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1421 | +| iterations | 5839 | +| time_elapsed | 8413 | +| total_timesteps | 11958272 | +| train/ | | +| approx_kl | 0.009754009 | +| clip_fraction | 0.319 | +| clip_range | 0.072 | +| entropy_loss | -7.15 | +| explained_variance | 0.48 | +| learning_rate | 4.72e-05 | +| loss | -0.0284 | +| n_updates | 39172 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000101 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1421 | +| iterations | 5840 | +| time_elapsed | 8414 | +| total_timesteps | 11960320 | +| train/ | | +| approx_kl | 0.009869877 | +| clip_fraction | 0.299 | +| clip_range | 0.072 | +| entropy_loss | -7.45 | +| explained_variance | -0.0346 | +| learning_rate | 4.72e-05 | +| loss | -0.0315 | +| n_updates | 39176 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000243 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1421 | +| iterations | 5841 | +| time_elapsed | 8415 | +| total_timesteps | 11962368 | +| train/ | | +| approx_kl | 0.008500266 | +| clip_fraction | 0.305 | +| clip_range | 0.072 | +| entropy_loss | -7.11 | +| explained_variance | 0.263 | +| learning_rate | 4.72e-05 | +| loss | -0.0227 | +| n_updates | 39180 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000314 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1421 | +| iterations | 5842 | +| time_elapsed | 8417 | +| total_timesteps | 11964416 | +| train/ | | +| approx_kl | 0.010204781 | +| clip_fraction | 0.317 | +| clip_range | 0.072 | +| entropy_loss | -6.75 | +| explained_variance | 0.436 | +| learning_rate | 4.72e-05 | +| loss | -0.0291 | +| n_updates | 39184 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000279 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1421 | +| iterations | 5843 | +| time_elapsed | 8418 | +| total_timesteps | 11966464 | +| train/ | | +| approx_kl | 0.0102351215 | +| clip_fraction | 0.338 | +| clip_range | 0.072 | +| entropy_loss | -7.4 | +| explained_variance | -0.11 | +| learning_rate | 4.72e-05 | +| loss | -0.0332 | +| n_updates | 39188 | +| policy_gradient_loss | -0.0219 | +| value_loss | 0.000163 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1421 | +| iterations | 5844 | +| time_elapsed | 8420 | +| total_timesteps | 11968512 | +| train/ | | +| approx_kl | 0.010417938 | +| clip_fraction | 0.315 | +| clip_range | 0.072 | +| entropy_loss | -7.35 | +| explained_variance | -0.0273 | +| learning_rate | 4.72e-05 | +| loss | -0.0269 | +| n_updates | 39192 | +| policy_gradient_loss | -0.0196 | +| value_loss | 9.82e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1421 | +| iterations | 5845 | +| time_elapsed | 8421 | +| total_timesteps | 11970560 | +| train/ | | +| approx_kl | 0.010332077 | +| clip_fraction | 0.284 | +| clip_range | 0.072 | +| entropy_loss | -6.89 | +| explained_variance | 0.477 | +| learning_rate | 4.72e-05 | +| loss | -0.0286 | +| n_updates | 39196 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000263 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1421 | +| iterations | 5846 | +| time_elapsed | 8423 | +| total_timesteps | 11972608 | +| train/ | | +| approx_kl | 0.011687148 | +| clip_fraction | 0.324 | +| clip_range | 0.072 | +| entropy_loss | -7.26 | +| explained_variance | -0.116 | +| learning_rate | 4.72e-05 | +| loss | -0.0318 | +| n_updates | 39200 | +| policy_gradient_loss | -0.0223 | +| value_loss | 0.000135 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1421 | +| iterations | 5847 | +| time_elapsed | 8424 | +| total_timesteps | 11974656 | +| train/ | | +| approx_kl | 0.010680065 | +| clip_fraction | 0.271 | +| clip_range | 0.072 | +| entropy_loss | -7.06 | +| explained_variance | 0.162 | +| learning_rate | 4.72e-05 | +| loss | -0.0294 | +| n_updates | 39204 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000182 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1421 | +| iterations | 5848 | +| time_elapsed | 8426 | +| total_timesteps | 11976704 | +| train/ | | +| approx_kl | 0.011722716 | +| clip_fraction | 0.312 | +| clip_range | 0.072 | +| entropy_loss | -6.89 | +| explained_variance | 0.414 | +| learning_rate | 4.72e-05 | +| loss | -0.0303 | +| n_updates | 39208 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000135 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1421 | +| iterations | 5849 | +| time_elapsed | 8427 | +| total_timesteps | 11978752 | +| train/ | | +| approx_kl | 0.01160321 | +| clip_fraction | 0.326 | +| clip_range | 0.072 | +| entropy_loss | -7.38 | +| explained_variance | -0.0588 | +| learning_rate | 4.72e-05 | +| loss | -0.0285 | +| n_updates | 39212 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000121 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1421 | +| iterations | 5850 | +| time_elapsed | 8429 | +| total_timesteps | 11980800 | +| train/ | | +| approx_kl | 0.0092087155 | +| clip_fraction | 0.307 | +| clip_range | 0.072 | +| entropy_loss | -7.24 | +| explained_variance | 0.388 | +| learning_rate | 4.72e-05 | +| loss | -0.0268 | +| n_updates | 39216 | +| policy_gradient_loss | -0.0182 | +| value_loss | 9.19e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1421 | +| iterations | 5851 | +| time_elapsed | 8430 | +| total_timesteps | 11982848 | +| train/ | | +| approx_kl | 0.010893574 | +| clip_fraction | 0.299 | +| clip_range | 0.072 | +| entropy_loss | -7.15 | +| explained_variance | -0.0747 | +| learning_rate | 4.72e-05 | +| loss | -0.0296 | +| n_updates | 39220 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000189 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1421 | +| iterations | 5852 | +| time_elapsed | 8431 | +| total_timesteps | 11984896 | +| train/ | | +| approx_kl | 0.01166599 | +| clip_fraction | 0.322 | +| clip_range | 0.072 | +| entropy_loss | -7.06 | +| explained_variance | 0.241 | +| learning_rate | 4.72e-05 | +| loss | -0.0286 | +| n_updates | 39224 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000188 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1421 | +| iterations | 5853 | +| time_elapsed | 8433 | +| total_timesteps | 11986944 | +| train/ | | +| approx_kl | 0.009852121 | +| clip_fraction | 0.299 | +| clip_range | 0.072 | +| entropy_loss | -6.72 | +| explained_variance | 0.387 | +| learning_rate | 4.72e-05 | +| loss | -0.0278 | +| n_updates | 39228 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000319 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1421 | +| iterations | 5854 | +| time_elapsed | 8434 | +| total_timesteps | 11988992 | +| train/ | | +| approx_kl | 0.011056386 | +| clip_fraction | 0.317 | +| clip_range | 0.072 | +| entropy_loss | -7.04 | +| explained_variance | -0.0058 | +| learning_rate | 4.72e-05 | +| loss | -0.0281 | +| n_updates | 39232 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000219 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1421 | +| iterations | 5855 | +| time_elapsed | 8436 | +| total_timesteps | 11991040 | +| train/ | | +| approx_kl | 0.011882353 | +| clip_fraction | 0.275 | +| clip_range | 0.072 | +| entropy_loss | -7.27 | +| explained_variance | 0.108 | +| learning_rate | 4.72e-05 | +| loss | -0.0264 | +| n_updates | 39236 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000274 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1421 | +| iterations | 5856 | +| time_elapsed | 8437 | +| total_timesteps | 11993088 | +| train/ | | +| approx_kl | 0.010144317 | +| clip_fraction | 0.317 | +| clip_range | 0.072 | +| entropy_loss | -7.41 | +| explained_variance | -0.257 | +| learning_rate | 4.72e-05 | +| loss | -0.0363 | +| n_updates | 39240 | +| policy_gradient_loss | -0.0229 | +| value_loss | 0.000147 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1421 | +| iterations | 5857 | +| time_elapsed | 8438 | +| total_timesteps | 11995136 | +| train/ | | +| approx_kl | 0.0092141535 | +| clip_fraction | 0.285 | +| clip_range | 0.072 | +| entropy_loss | -7.5 | +| explained_variance | -0.0899 | +| learning_rate | 4.72e-05 | +| loss | -0.0258 | +| n_updates | 39244 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000289 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1421 | +| iterations | 5858 | +| time_elapsed | 8440 | +| total_timesteps | 11997184 | +| train/ | | +| approx_kl | 0.009786379 | +| clip_fraction | 0.326 | +| clip_range | 0.072 | +| entropy_loss | -7.16 | +| explained_variance | 0.369 | +| learning_rate | 4.72e-05 | +| loss | -0.0328 | +| n_updates | 39248 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000194 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1421 | +| iterations | 5859 | +| time_elapsed | 8441 | +| total_timesteps | 11999232 | +| train/ | | +| approx_kl | 0.011057419 | +| clip_fraction | 0.326 | +| clip_range | 0.072 | +| entropy_loss | -7.43 | +| explained_variance | -0.143 | +| learning_rate | 4.72e-05 | +| loss | -0.0282 | +| n_updates | 39252 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.00014 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1421 | +| iterations | 5860 | +| time_elapsed | 8443 | +| total_timesteps | 12001280 | +| train/ | | +| approx_kl | 0.011185775 | +| clip_fraction | 0.33 | +| clip_range | 0.072 | +| entropy_loss | -7.41 | +| explained_variance | -0.145 | +| learning_rate | 4.72e-05 | +| loss | -0.0336 | +| n_updates | 39256 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000105 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1421 | +| iterations | 5861 | +| time_elapsed | 8444 | +| total_timesteps | 12003328 | +| train/ | | +| approx_kl | 0.011301011 | +| clip_fraction | 0.31 | +| clip_range | 0.072 | +| entropy_loss | -7.07 | +| explained_variance | 0.468 | +| learning_rate | 4.71e-05 | +| loss | -0.0267 | +| n_updates | 39260 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000164 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1421 | +| iterations | 5862 | +| time_elapsed | 8446 | +| total_timesteps | 12005376 | +| train/ | | +| approx_kl | 0.010823872 | +| clip_fraction | 0.333 | +| clip_range | 0.072 | +| entropy_loss | -6.79 | +| explained_variance | 0.341 | +| learning_rate | 4.71e-05 | +| loss | -0.0335 | +| n_updates | 39264 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000118 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1421 | +| iterations | 5863 | +| time_elapsed | 8447 | +| total_timesteps | 12007424 | +| train/ | | +| approx_kl | 0.013294479 | +| clip_fraction | 0.323 | +| clip_range | 0.072 | +| entropy_loss | -7.04 | +| explained_variance | 0.187 | +| learning_rate | 4.71e-05 | +| loss | -0.033 | +| n_updates | 39268 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000285 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1421 | +| iterations | 5864 | +| time_elapsed | 8449 | +| total_timesteps | 12009472 | +| train/ | | +| approx_kl | 0.010171694 | +| clip_fraction | 0.301 | +| clip_range | 0.072 | +| entropy_loss | -7.09 | +| explained_variance | 0.376 | +| learning_rate | 4.71e-05 | +| loss | -0.0298 | +| n_updates | 39272 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000232 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1421 | +| iterations | 5865 | +| time_elapsed | 8450 | +| total_timesteps | 12011520 | +| train/ | | +| approx_kl | 0.010143021 | +| clip_fraction | 0.348 | +| clip_range | 0.072 | +| entropy_loss | -7.14 | +| explained_variance | 0.408 | +| learning_rate | 4.71e-05 | +| loss | -0.0354 | +| n_updates | 39276 | +| policy_gradient_loss | -0.021 | +| value_loss | 9.36e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1421 | +| iterations | 5866 | +| time_elapsed | 8451 | +| total_timesteps | 12013568 | +| train/ | | +| approx_kl | 0.011619555 | +| clip_fraction | 0.317 | +| clip_range | 0.072 | +| entropy_loss | -7.03 | +| explained_variance | 0.413 | +| learning_rate | 4.71e-05 | +| loss | -0.0362 | +| n_updates | 39280 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000245 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1421 | +| iterations | 5867 | +| time_elapsed | 8453 | +| total_timesteps | 12015616 | +| train/ | | +| approx_kl | 0.010182383 | +| clip_fraction | 0.342 | +| clip_range | 0.072 | +| entropy_loss | -7.42 | +| explained_variance | -0.401 | +| learning_rate | 4.71e-05 | +| loss | -0.0441 | +| n_updates | 39284 | +| policy_gradient_loss | -0.025 | +| value_loss | 6.08e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1421 | +| iterations | 5868 | +| time_elapsed | 8454 | +| total_timesteps | 12017664 | +| train/ | | +| approx_kl | 0.010997751 | +| clip_fraction | 0.31 | +| clip_range | 0.072 | +| entropy_loss | -7.14 | +| explained_variance | 0.24 | +| learning_rate | 4.71e-05 | +| loss | -0.0351 | +| n_updates | 39288 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000125 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1421 | +| iterations | 5869 | +| time_elapsed | 8456 | +| total_timesteps | 12019712 | +| train/ | | +| approx_kl | 0.012060165 | +| clip_fraction | 0.32 | +| clip_range | 0.072 | +| entropy_loss | -6.86 | +| explained_variance | 0.374 | +| learning_rate | 4.71e-05 | +| loss | -0.025 | +| n_updates | 39292 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000231 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1421 | +| iterations | 5870 | +| time_elapsed | 8457 | +| total_timesteps | 12021760 | +| train/ | | +| approx_kl | 0.009659752 | +| clip_fraction | 0.308 | +| clip_range | 0.072 | +| entropy_loss | -7.28 | +| explained_variance | 0.367 | +| learning_rate | 4.71e-05 | +| loss | -0.0335 | +| n_updates | 39296 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000113 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1421 | +| iterations | 5871 | +| time_elapsed | 8459 | +| total_timesteps | 12023808 | +| train/ | | +| approx_kl | 0.011798627 | +| clip_fraction | 0.349 | +| clip_range | 0.072 | +| entropy_loss | -7.22 | +| explained_variance | -0.189 | +| learning_rate | 4.71e-05 | +| loss | -0.0331 | +| n_updates | 39300 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000106 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1421 | +| iterations | 5872 | +| time_elapsed | 8460 | +| total_timesteps | 12025856 | +| train/ | | +| approx_kl | 0.010594141 | +| clip_fraction | 0.304 | +| clip_range | 0.072 | +| entropy_loss | -7.18 | +| explained_variance | -0.0534 | +| learning_rate | 4.71e-05 | +| loss | -0.0257 | +| n_updates | 39304 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000174 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1421 | +| iterations | 5873 | +| time_elapsed | 8462 | +| total_timesteps | 12027904 | +| train/ | | +| approx_kl | 0.012428975 | +| clip_fraction | 0.317 | +| clip_range | 0.072 | +| entropy_loss | -7.17 | +| explained_variance | -0.0215 | +| learning_rate | 4.71e-05 | +| loss | -0.0351 | +| n_updates | 39308 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000157 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1421 | +| iterations | 5874 | +| time_elapsed | 8463 | +| total_timesteps | 12029952 | +| train/ | | +| approx_kl | 0.010605086 | +| clip_fraction | 0.322 | +| clip_range | 0.072 | +| entropy_loss | -7.09 | +| explained_variance | 0.447 | +| learning_rate | 4.71e-05 | +| loss | -0.0308 | +| n_updates | 39312 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000189 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1421 | +| iterations | 5875 | +| time_elapsed | 8464 | +| total_timesteps | 12032000 | +| train/ | | +| approx_kl | 0.00926665 | +| clip_fraction | 0.317 | +| clip_range | 0.072 | +| entropy_loss | -7.11 | +| explained_variance | 0.308 | +| learning_rate | 4.71e-05 | +| loss | -0.0331 | +| n_updates | 39316 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.00014 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1421 | +| iterations | 5876 | +| time_elapsed | 8466 | +| total_timesteps | 12034048 | +| train/ | | +| approx_kl | 0.008731214 | +| clip_fraction | 0.311 | +| clip_range | 0.072 | +| entropy_loss | -7.44 | +| explained_variance | -0.0674 | +| learning_rate | 4.71e-05 | +| loss | -0.0319 | +| n_updates | 39320 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000108 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1421 | +| iterations | 5877 | +| time_elapsed | 8467 | +| total_timesteps | 12036096 | +| train/ | | +| approx_kl | 0.012045898 | +| clip_fraction | 0.322 | +| clip_range | 0.072 | +| entropy_loss | -6.76 | +| explained_variance | 0.414 | +| learning_rate | 4.71e-05 | +| loss | -0.0298 | +| n_updates | 39324 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.00017 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1421 | +| iterations | 5878 | +| time_elapsed | 8468 | +| total_timesteps | 12038144 | +| train/ | | +| approx_kl | 0.012836473 | +| clip_fraction | 0.333 | +| clip_range | 0.072 | +| entropy_loss | -7.28 | +| explained_variance | -0.23 | +| learning_rate | 4.71e-05 | +| loss | -0.0322 | +| n_updates | 39328 | +| policy_gradient_loss | -0.0203 | +| value_loss | 9.17e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1421 | +| iterations | 5879 | +| time_elapsed | 8470 | +| total_timesteps | 12040192 | +| train/ | | +| approx_kl | 0.012299725 | +| clip_fraction | 0.281 | +| clip_range | 0.072 | +| entropy_loss | -7.5 | +| explained_variance | -0.146 | +| learning_rate | 4.71e-05 | +| loss | -0.0308 | +| n_updates | 39332 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000115 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1421 | +| iterations | 5880 | +| time_elapsed | 8471 | +| total_timesteps | 12042240 | +| train/ | | +| approx_kl | 0.011435989 | +| clip_fraction | 0.339 | +| clip_range | 0.072 | +| entropy_loss | -6.91 | +| explained_variance | 0.662 | +| learning_rate | 4.71e-05 | +| loss | -0.0322 | +| n_updates | 39336 | +| policy_gradient_loss | -0.0211 | +| value_loss | 8.67e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1421 | +| iterations | 5881 | +| time_elapsed | 8473 | +| total_timesteps | 12044288 | +| train/ | | +| approx_kl | 0.012678649 | +| clip_fraction | 0.326 | +| clip_range | 0.072 | +| entropy_loss | -7.2 | +| explained_variance | 0.19 | +| learning_rate | 4.71e-05 | +| loss | -0.0341 | +| n_updates | 39340 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000281 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1421 | +| iterations | 5882 | +| time_elapsed | 8474 | +| total_timesteps | 12046336 | +| train/ | | +| approx_kl | 0.013500507 | +| clip_fraction | 0.319 | +| clip_range | 0.072 | +| entropy_loss | -7.16 | +| explained_variance | 0.328 | +| learning_rate | 4.71e-05 | +| loss | -0.0315 | +| n_updates | 39344 | +| policy_gradient_loss | -0.0212 | +| value_loss | 7.73e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1421 | +| iterations | 5883 | +| time_elapsed | 8476 | +| total_timesteps | 12048384 | +| train/ | | +| approx_kl | 0.010830417 | +| clip_fraction | 0.305 | +| clip_range | 0.072 | +| entropy_loss | -6.86 | +| explained_variance | 0.512 | +| learning_rate | 4.71e-05 | +| loss | -0.0316 | +| n_updates | 39348 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000152 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1421 | +| iterations | 5884 | +| time_elapsed | 8477 | +| total_timesteps | 12050432 | +| train/ | | +| approx_kl | 0.010385749 | +| clip_fraction | 0.324 | +| clip_range | 0.072 | +| entropy_loss | -7.19 | +| explained_variance | 0.303 | +| learning_rate | 4.71e-05 | +| loss | -0.0298 | +| n_updates | 39352 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.00019 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1421 | +| iterations | 5885 | +| time_elapsed | 8479 | +| total_timesteps | 12052480 | +| train/ | | +| approx_kl | 0.009992247 | +| clip_fraction | 0.321 | +| clip_range | 0.072 | +| entropy_loss | -7.32 | +| explained_variance | 0.333 | +| learning_rate | 4.71e-05 | +| loss | -0.0315 | +| n_updates | 39356 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000127 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1421 | +| iterations | 5886 | +| time_elapsed | 8480 | +| total_timesteps | 12054528 | +| train/ | | +| approx_kl | 0.00931592 | +| clip_fraction | 0.296 | +| clip_range | 0.072 | +| entropy_loss | -7.21 | +| explained_variance | 0.177 | +| learning_rate | 4.71e-05 | +| loss | -0.032 | +| n_updates | 39360 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000274 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1421 | +| iterations | 5887 | +| time_elapsed | 8482 | +| total_timesteps | 12056576 | +| train/ | | +| approx_kl | 0.01037993 | +| clip_fraction | 0.324 | +| clip_range | 0.072 | +| entropy_loss | -7.19 | +| explained_variance | 0.402 | +| learning_rate | 4.71e-05 | +| loss | -0.0365 | +| n_updates | 39364 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000117 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1421 | +| iterations | 5888 | +| time_elapsed | 8483 | +| total_timesteps | 12058624 | +| train/ | | +| approx_kl | 0.010288825 | +| clip_fraction | 0.294 | +| clip_range | 0.072 | +| entropy_loss | -6.98 | +| explained_variance | 0.232 | +| learning_rate | 4.71e-05 | +| loss | -0.0231 | +| n_updates | 39368 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000233 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1421 | +| iterations | 5889 | +| time_elapsed | 8484 | +| total_timesteps | 12060672 | +| train/ | | +| approx_kl | 0.010515195 | +| clip_fraction | 0.317 | +| clip_range | 0.072 | +| entropy_loss | -7.05 | +| explained_variance | 0.493 | +| learning_rate | 4.71e-05 | +| loss | -0.0295 | +| n_updates | 39372 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000119 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1421 | +| iterations | 5890 | +| time_elapsed | 8486 | +| total_timesteps | 12062720 | +| train/ | | +| approx_kl | 0.010353986 | +| clip_fraction | 0.296 | +| clip_range | 0.072 | +| entropy_loss | -7.36 | +| explained_variance | 0.266 | +| learning_rate | 4.71e-05 | +| loss | -0.0323 | +| n_updates | 39376 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000187 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1421 | +| iterations | 5891 | +| time_elapsed | 8487 | +| total_timesteps | 12064768 | +| train/ | | +| approx_kl | 0.010995497 | +| clip_fraction | 0.335 | +| clip_range | 0.072 | +| entropy_loss | -7.11 | +| explained_variance | 0.32 | +| learning_rate | 4.71e-05 | +| loss | -0.0257 | +| n_updates | 39380 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.00024 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1421 | +| iterations | 5892 | +| time_elapsed | 8489 | +| total_timesteps | 12066816 | +| train/ | | +| approx_kl | 0.009022532 | +| clip_fraction | 0.284 | +| clip_range | 0.072 | +| entropy_loss | -6.64 | +| explained_variance | 0.512 | +| learning_rate | 4.71e-05 | +| loss | -0.0265 | +| n_updates | 39384 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000242 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1421 | +| iterations | 5893 | +| time_elapsed | 8490 | +| total_timesteps | 12068864 | +| train/ | | +| approx_kl | 0.010537214 | +| clip_fraction | 0.34 | +| clip_range | 0.072 | +| entropy_loss | -7.26 | +| explained_variance | 0.464 | +| learning_rate | 4.71e-05 | +| loss | -0.0345 | +| n_updates | 39388 | +| policy_gradient_loss | -0.023 | +| value_loss | 8.24e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1421 | +| iterations | 5894 | +| time_elapsed | 8491 | +| total_timesteps | 12070912 | +| train/ | | +| approx_kl | 0.009781292 | +| clip_fraction | 0.311 | +| clip_range | 0.072 | +| entropy_loss | -7.58 | +| explained_variance | -0.0331 | +| learning_rate | 4.71e-05 | +| loss | -0.0303 | +| n_updates | 39392 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000211 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1421 | +| iterations | 5895 | +| time_elapsed | 8493 | +| total_timesteps | 12072960 | +| train/ | | +| approx_kl | 0.009683484 | +| clip_fraction | 0.298 | +| clip_range | 0.072 | +| entropy_loss | -7.02 | +| explained_variance | 0.603 | +| learning_rate | 4.71e-05 | +| loss | -0.0352 | +| n_updates | 39396 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000182 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1421 | +| iterations | 5896 | +| time_elapsed | 8494 | +| total_timesteps | 12075008 | +| train/ | | +| approx_kl | 0.00927763 | +| clip_fraction | 0.292 | +| clip_range | 0.072 | +| entropy_loss | -7.06 | +| explained_variance | 0.369 | +| learning_rate | 4.71e-05 | +| loss | -0.0284 | +| n_updates | 39400 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000307 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1421 | +| iterations | 5897 | +| time_elapsed | 8496 | +| total_timesteps | 12077056 | +| train/ | | +| approx_kl | 0.009429693 | +| clip_fraction | 0.299 | +| clip_range | 0.072 | +| entropy_loss | -7.2 | +| explained_variance | 0.116 | +| learning_rate | 4.71e-05 | +| loss | -0.0311 | +| n_updates | 39404 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000268 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1421 | +| iterations | 5898 | +| time_elapsed | 8497 | +| total_timesteps | 12079104 | +| train/ | | +| approx_kl | 0.009001525 | +| clip_fraction | 0.28 | +| clip_range | 0.072 | +| entropy_loss | -6.92 | +| explained_variance | 0.176 | +| learning_rate | 4.71e-05 | +| loss | -0.0263 | +| n_updates | 39408 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000396 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1421 | +| iterations | 5899 | +| time_elapsed | 8498 | +| total_timesteps | 12081152 | +| train/ | | +| approx_kl | 0.009616729 | +| clip_fraction | 0.305 | +| clip_range | 0.072 | +| entropy_loss | -6.66 | +| explained_variance | 0.503 | +| learning_rate | 4.71e-05 | +| loss | -0.0309 | +| n_updates | 39412 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000259 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1421 | +| iterations | 5900 | +| time_elapsed | 8500 | +| total_timesteps | 12083200 | +| train/ | | +| approx_kl | 0.012839796 | +| clip_fraction | 0.341 | +| clip_range | 0.072 | +| entropy_loss | -7.17 | +| explained_variance | -0.348 | +| learning_rate | 4.71e-05 | +| loss | -0.0379 | +| n_updates | 39416 | +| policy_gradient_loss | -0.0238 | +| value_loss | 9.41e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1421 | +| iterations | 5901 | +| time_elapsed | 8501 | +| total_timesteps | 12085248 | +| train/ | | +| approx_kl | 0.009903177 | +| clip_fraction | 0.314 | +| clip_range | 0.072 | +| entropy_loss | -7.18 | +| explained_variance | 0.175 | +| learning_rate | 4.71e-05 | +| loss | -0.0309 | +| n_updates | 39420 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000226 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1421 | +| iterations | 5902 | +| time_elapsed | 8503 | +| total_timesteps | 12087296 | +| train/ | | +| approx_kl | 0.0115021225 | +| clip_fraction | 0.324 | +| clip_range | 0.072 | +| entropy_loss | -7.49 | +| explained_variance | -0.145 | +| learning_rate | 4.71e-05 | +| loss | -0.0333 | +| n_updates | 39424 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000137 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1421 | +| iterations | 5903 | +| time_elapsed | 8504 | +| total_timesteps | 12089344 | +| train/ | | +| approx_kl | 0.010691168 | +| clip_fraction | 0.324 | +| clip_range | 0.072 | +| entropy_loss | -7.33 | +| explained_variance | 0.25 | +| learning_rate | 4.71e-05 | +| loss | -0.0365 | +| n_updates | 39428 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000178 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1421 | +| iterations | 5904 | +| time_elapsed | 8506 | +| total_timesteps | 12091392 | +| train/ | | +| approx_kl | 0.010286514 | +| clip_fraction | 0.302 | +| clip_range | 0.072 | +| entropy_loss | -7.34 | +| explained_variance | 0.321 | +| learning_rate | 4.71e-05 | +| loss | -0.0298 | +| n_updates | 39432 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000137 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1421 | +| iterations | 5905 | +| time_elapsed | 8507 | +| total_timesteps | 12093440 | +| train/ | | +| approx_kl | 0.010806318 | +| clip_fraction | 0.296 | +| clip_range | 0.072 | +| entropy_loss | -7.25 | +| explained_variance | 0.329 | +| learning_rate | 4.71e-05 | +| loss | -0.0334 | +| n_updates | 39436 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000145 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1421 | +| iterations | 5906 | +| time_elapsed | 8509 | +| total_timesteps | 12095488 | +| train/ | | +| approx_kl | 0.010596097 | +| clip_fraction | 0.306 | +| clip_range | 0.072 | +| entropy_loss | -7.23 | +| explained_variance | 0.728 | +| learning_rate | 4.71e-05 | +| loss | -0.0331 | +| n_updates | 39440 | +| policy_gradient_loss | -0.0214 | +| value_loss | 6.08e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1421 | +| iterations | 5907 | +| time_elapsed | 8510 | +| total_timesteps | 12097536 | +| train/ | | +| approx_kl | 0.0102370735 | +| clip_fraction | 0.273 | +| clip_range | 0.072 | +| entropy_loss | -6.81 | +| explained_variance | 0.587 | +| learning_rate | 4.71e-05 | +| loss | -0.0239 | +| n_updates | 39444 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000181 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1421 | +| iterations | 5908 | +| time_elapsed | 8511 | +| total_timesteps | 12099584 | +| train/ | | +| approx_kl | 0.009523474 | +| clip_fraction | 0.317 | +| clip_range | 0.072 | +| entropy_loss | -7.26 | +| explained_variance | 0.544 | +| learning_rate | 4.71e-05 | +| loss | -0.0315 | +| n_updates | 39448 | +| policy_gradient_loss | -0.021 | +| value_loss | 7.06e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1421 | +| iterations | 5909 | +| time_elapsed | 8513 | +| total_timesteps | 12101632 | +| train/ | | +| approx_kl | 0.011149874 | +| clip_fraction | 0.323 | +| clip_range | 0.072 | +| entropy_loss | -6.92 | +| explained_variance | 0.655 | +| learning_rate | 4.71e-05 | +| loss | -0.0297 | +| n_updates | 39452 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000118 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1421 | +| iterations | 5910 | +| time_elapsed | 8514 | +| total_timesteps | 12103680 | +| train/ | | +| approx_kl | 0.010070933 | +| clip_fraction | 0.305 | +| clip_range | 0.072 | +| entropy_loss | -7.35 | +| explained_variance | 0.0549 | +| learning_rate | 4.71e-05 | +| loss | -0.0292 | +| n_updates | 39456 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000137 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1421 | +| iterations | 5911 | +| time_elapsed | 8516 | +| total_timesteps | 12105728 | +| train/ | | +| approx_kl | 0.011030222 | +| clip_fraction | 0.303 | +| clip_range | 0.072 | +| entropy_loss | -7.55 | +| explained_variance | -0.0542 | +| learning_rate | 4.71e-05 | +| loss | -0.0338 | +| n_updates | 39460 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000214 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1421 | +| iterations | 5912 | +| time_elapsed | 8517 | +| total_timesteps | 12107776 | +| train/ | | +| approx_kl | 0.009214632 | +| clip_fraction | 0.293 | +| clip_range | 0.072 | +| entropy_loss | -7.31 | +| explained_variance | 0.149 | +| learning_rate | 4.71e-05 | +| loss | -0.0365 | +| n_updates | 39464 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000197 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1421 | +| iterations | 5913 | +| time_elapsed | 8519 | +| total_timesteps | 12109824 | +| train/ | | +| approx_kl | 0.009122512 | +| clip_fraction | 0.332 | +| clip_range | 0.072 | +| entropy_loss | -7.09 | +| explained_variance | 0.492 | +| learning_rate | 4.71e-05 | +| loss | -0.0362 | +| n_updates | 39468 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000153 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1421 | +| iterations | 5914 | +| time_elapsed | 8520 | +| total_timesteps | 12111872 | +| train/ | | +| approx_kl | 0.009817449 | +| clip_fraction | 0.278 | +| clip_range | 0.072 | +| entropy_loss | -7.01 | +| explained_variance | 0.329 | +| learning_rate | 4.71e-05 | +| loss | -0.0231 | +| n_updates | 39472 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.000306 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1421 | +| iterations | 5915 | +| time_elapsed | 8522 | +| total_timesteps | 12113920 | +| train/ | | +| approx_kl | 0.007961176 | +| clip_fraction | 0.289 | +| clip_range | 0.072 | +| entropy_loss | -6.82 | +| explained_variance | 0.459 | +| learning_rate | 4.71e-05 | +| loss | -0.0305 | +| n_updates | 39476 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000284 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1421 | +| iterations | 5916 | +| time_elapsed | 8523 | +| total_timesteps | 12115968 | +| train/ | | +| approx_kl | 0.009417983 | +| clip_fraction | 0.321 | +| clip_range | 0.072 | +| entropy_loss | -7.16 | +| explained_variance | 0.535 | +| learning_rate | 4.71e-05 | +| loss | -0.037 | +| n_updates | 39480 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000123 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1421 | +| iterations | 5917 | +| time_elapsed | 8524 | +| total_timesteps | 12118016 | +| train/ | | +| approx_kl | 0.010084877 | +| clip_fraction | 0.344 | +| clip_range | 0.072 | +| entropy_loss | -7.48 | +| explained_variance | -0.0713 | +| learning_rate | 4.71e-05 | +| loss | -0.0297 | +| n_updates | 39484 | +| policy_gradient_loss | -0.0223 | +| value_loss | 0.00013 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1421 | +| iterations | 5918 | +| time_elapsed | 8526 | +| total_timesteps | 12120064 | +| train/ | | +| approx_kl | 0.009809244 | +| clip_fraction | 0.307 | +| clip_range | 0.072 | +| entropy_loss | -7.48 | +| explained_variance | -0.0614 | +| learning_rate | 4.71e-05 | +| loss | -0.0358 | +| n_updates | 39488 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.00016 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1421 | +| iterations | 5919 | +| time_elapsed | 8527 | +| total_timesteps | 12122112 | +| train/ | | +| approx_kl | 0.011558383 | +| clip_fraction | 0.305 | +| clip_range | 0.072 | +| entropy_loss | -6.83 | +| explained_variance | 0.498 | +| learning_rate | 4.71e-05 | +| loss | -0.0285 | +| n_updates | 39492 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000253 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1421 | +| iterations | 5920 | +| time_elapsed | 8529 | +| total_timesteps | 12124160 | +| train/ | | +| approx_kl | 0.009741165 | +| clip_fraction | 0.3 | +| clip_range | 0.072 | +| entropy_loss | -7.3 | +| explained_variance | 0.282 | +| learning_rate | 4.71e-05 | +| loss | -0.0327 | +| n_updates | 39496 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000173 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1421 | +| iterations | 5921 | +| time_elapsed | 8530 | +| total_timesteps | 12126208 | +| train/ | | +| approx_kl | 0.008600146 | +| clip_fraction | 0.293 | +| clip_range | 0.072 | +| entropy_loss | -6.93 | +| explained_variance | 0.522 | +| learning_rate | 4.71e-05 | +| loss | -0.0336 | +| n_updates | 39500 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000173 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1421 | +| iterations | 5922 | +| time_elapsed | 8532 | +| total_timesteps | 12128256 | +| train/ | | +| approx_kl | 0.009808458 | +| clip_fraction | 0.308 | +| clip_range | 0.072 | +| entropy_loss | -7.07 | +| explained_variance | 0.33 | +| learning_rate | 4.71e-05 | +| loss | -0.0207 | +| n_updates | 39504 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.00023 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1421 | +| iterations | 5923 | +| time_elapsed | 8533 | +| total_timesteps | 12130304 | +| train/ | | +| approx_kl | 0.011827648 | +| clip_fraction | 0.286 | +| clip_range | 0.072 | +| entropy_loss | -7.17 | +| explained_variance | -0.173 | +| learning_rate | 4.71e-05 | +| loss | -0.0357 | +| n_updates | 39508 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000226 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1421 | +| iterations | 5924 | +| time_elapsed | 8535 | +| total_timesteps | 12132352 | +| train/ | | +| approx_kl | 0.0097801685 | +| clip_fraction | 0.312 | +| clip_range | 0.072 | +| entropy_loss | -6.75 | +| explained_variance | 0.317 | +| learning_rate | 4.71e-05 | +| loss | -0.0268 | +| n_updates | 39512 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.00036 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1421 | +| iterations | 5925 | +| time_elapsed | 8536 | +| total_timesteps | 12134400 | +| train/ | | +| approx_kl | 0.00942091 | +| clip_fraction | 0.331 | +| clip_range | 0.072 | +| entropy_loss | -7.28 | +| explained_variance | 0.229 | +| learning_rate | 4.71e-05 | +| loss | -0.0313 | +| n_updates | 39516 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.00019 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1421 | +| iterations | 5926 | +| time_elapsed | 8538 | +| total_timesteps | 12136448 | +| train/ | | +| approx_kl | 0.010330656 | +| clip_fraction | 0.302 | +| clip_range | 0.072 | +| entropy_loss | -7.57 | +| explained_variance | -0.121 | +| learning_rate | 4.71e-05 | +| loss | -0.0323 | +| n_updates | 39520 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000176 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1421 | +| iterations | 5927 | +| time_elapsed | 8539 | +| total_timesteps | 12138496 | +| train/ | | +| approx_kl | 0.010078688 | +| clip_fraction | 0.305 | +| clip_range | 0.072 | +| entropy_loss | -7.49 | +| explained_variance | -0.123 | +| learning_rate | 4.71e-05 | +| loss | -0.0339 | +| n_updates | 39524 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000214 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1421 | +| iterations | 5928 | +| time_elapsed | 8540 | +| total_timesteps | 12140544 | +| train/ | | +| approx_kl | 0.010589036 | +| clip_fraction | 0.327 | +| clip_range | 0.072 | +| entropy_loss | -7.27 | +| explained_variance | 0.276 | +| learning_rate | 4.71e-05 | +| loss | -0.0354 | +| n_updates | 39528 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000197 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1421 | +| iterations | 5929 | +| time_elapsed | 8542 | +| total_timesteps | 12142592 | +| train/ | | +| approx_kl | 0.010482619 | +| clip_fraction | 0.315 | +| clip_range | 0.072 | +| entropy_loss | -7.55 | +| explained_variance | -0.157 | +| learning_rate | 4.71e-05 | +| loss | -0.0302 | +| n_updates | 39532 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000156 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1421 | +| iterations | 5930 | +| time_elapsed | 8543 | +| total_timesteps | 12144640 | +| train/ | | +| approx_kl | 0.010476813 | +| clip_fraction | 0.289 | +| clip_range | 0.072 | +| entropy_loss | -7.25 | +| explained_variance | 0.419 | +| learning_rate | 4.71e-05 | +| loss | -0.0307 | +| n_updates | 39536 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000172 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1421 | +| iterations | 5931 | +| time_elapsed | 8545 | +| total_timesteps | 12146688 | +| train/ | | +| approx_kl | 0.009997108 | +| clip_fraction | 0.281 | +| clip_range | 0.072 | +| entropy_loss | -6.62 | +| explained_variance | 0.568 | +| learning_rate | 4.71e-05 | +| loss | -0.0281 | +| n_updates | 39540 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000215 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1421 | +| iterations | 5932 | +| time_elapsed | 8546 | +| total_timesteps | 12148736 | +| train/ | | +| approx_kl | 0.012201167 | +| clip_fraction | 0.274 | +| clip_range | 0.072 | +| entropy_loss | -7.06 | +| explained_variance | 0.475 | +| learning_rate | 4.71e-05 | +| loss | -0.032 | +| n_updates | 39544 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000136 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1421 | +| iterations | 5933 | +| time_elapsed | 8548 | +| total_timesteps | 12150784 | +| train/ | | +| approx_kl | 0.009221941 | +| clip_fraction | 0.288 | +| clip_range | 0.072 | +| entropy_loss | -7.12 | +| explained_variance | 0.191 | +| learning_rate | 4.71e-05 | +| loss | -0.0315 | +| n_updates | 39548 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000244 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1421 | +| iterations | 5934 | +| time_elapsed | 8549 | +| total_timesteps | 12152832 | +| train/ | | +| approx_kl | 0.010569366 | +| clip_fraction | 0.302 | +| clip_range | 0.072 | +| entropy_loss | -7.25 | +| explained_variance | 0.194 | +| learning_rate | 4.71e-05 | +| loss | -0.0345 | +| n_updates | 39552 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000281 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1421 | +| iterations | 5935 | +| time_elapsed | 8551 | +| total_timesteps | 12154880 | +| train/ | | +| approx_kl | 0.009155095 | +| clip_fraction | 0.325 | +| clip_range | 0.072 | +| entropy_loss | -7.36 | +| explained_variance | 0.325 | +| learning_rate | 4.71e-05 | +| loss | -0.037 | +| n_updates | 39556 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.00012 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.392 | +| time/ | | +| fps | 1421 | +| iterations | 5936 | +| time_elapsed | 8552 | +| total_timesteps | 12156928 | +| train/ | | +| approx_kl | 0.0087218825 | +| clip_fraction | 0.325 | +| clip_range | 0.072 | +| entropy_loss | -7.5 | +| explained_variance | -0.0959 | +| learning_rate | 4.71e-05 | +| loss | -0.032 | +| n_updates | 39560 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000109 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.389 | +| time/ | | +| fps | 1421 | +| iterations | 5937 | +| time_elapsed | 8553 | +| total_timesteps | 12158976 | +| train/ | | +| approx_kl | 0.009719236 | +| clip_fraction | 0.281 | +| clip_range | 0.072 | +| entropy_loss | -7.06 | +| explained_variance | 0.314 | +| learning_rate | 4.71e-05 | +| loss | -0.0329 | +| n_updates | 39564 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000319 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.389 | +| time/ | | +| fps | 1421 | +| iterations | 5938 | +| time_elapsed | 8555 | +| total_timesteps | 12161024 | +| train/ | | +| approx_kl | 0.009091489 | +| clip_fraction | 0.308 | +| clip_range | 0.072 | +| entropy_loss | -6.89 | +| explained_variance | 0.635 | +| learning_rate | 4.71e-05 | +| loss | -0.0267 | +| n_updates | 39568 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000124 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.393 | +| time/ | | +| fps | 1421 | +| iterations | 5939 | +| time_elapsed | 8556 | +| total_timesteps | 12163072 | +| train/ | | +| approx_kl | 0.011442019 | +| clip_fraction | 0.326 | +| clip_range | 0.072 | +| entropy_loss | -7.41 | +| explained_variance | -0.184 | +| learning_rate | 4.71e-05 | +| loss | -0.0268 | +| n_updates | 39572 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000111 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.392 | +| time/ | | +| fps | 1421 | +| iterations | 5940 | +| time_elapsed | 8558 | +| total_timesteps | 12165120 | +| train/ | | +| approx_kl | 0.009308506 | +| clip_fraction | 0.308 | +| clip_range | 0.072 | +| entropy_loss | -7.38 | +| explained_variance | 0.172 | +| learning_rate | 4.71e-05 | +| loss | -0.0257 | +| n_updates | 39576 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000236 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.393 | +| time/ | | +| fps | 1421 | +| iterations | 5941 | +| time_elapsed | 8559 | +| total_timesteps | 12167168 | +| train/ | | +| approx_kl | 0.010490865 | +| clip_fraction | 0.334 | +| clip_range | 0.072 | +| entropy_loss | -7.12 | +| explained_variance | 0.253 | +| learning_rate | 4.71e-05 | +| loss | -0.032 | +| n_updates | 39580 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000162 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.392 | +| time/ | | +| fps | 1421 | +| iterations | 5942 | +| time_elapsed | 8561 | +| total_timesteps | 12169216 | +| train/ | | +| approx_kl | 0.01103726 | +| clip_fraction | 0.312 | +| clip_range | 0.072 | +| entropy_loss | -7.36 | +| explained_variance | -0.103 | +| learning_rate | 4.71e-05 | +| loss | -0.0324 | +| n_updates | 39584 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000167 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.392 | +| time/ | | +| fps | 1421 | +| iterations | 5943 | +| time_elapsed | 8562 | +| total_timesteps | 12171264 | +| train/ | | +| approx_kl | 0.009982739 | +| clip_fraction | 0.294 | +| clip_range | 0.072 | +| entropy_loss | -6.98 | +| explained_variance | 0.481 | +| learning_rate | 4.71e-05 | +| loss | -0.0306 | +| n_updates | 39588 | +| policy_gradient_loss | -0.017 | +| value_loss | 8.8e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.387 | +| time/ | | +| fps | 1421 | +| iterations | 5944 | +| time_elapsed | 8564 | +| total_timesteps | 12173312 | +| train/ | | +| approx_kl | 0.010441408 | +| clip_fraction | 0.318 | +| clip_range | 0.072 | +| entropy_loss | -6.94 | +| explained_variance | 0.457 | +| learning_rate | 4.71e-05 | +| loss | -0.0277 | +| n_updates | 39592 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000158 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.387 | +| time/ | | +| fps | 1421 | +| iterations | 5945 | +| time_elapsed | 8565 | +| total_timesteps | 12175360 | +| train/ | | +| approx_kl | 0.009061921 | +| clip_fraction | 0.311 | +| clip_range | 0.072 | +| entropy_loss | -7.23 | +| explained_variance | 0.478 | +| learning_rate | 4.71e-05 | +| loss | -0.0309 | +| n_updates | 39596 | +| policy_gradient_loss | -0.0192 | +| value_loss | 7.44e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.384 | +| time/ | | +| fps | 1421 | +| iterations | 5946 | +| time_elapsed | 8566 | +| total_timesteps | 12177408 | +| train/ | | +| approx_kl | 0.00793758 | +| clip_fraction | 0.288 | +| clip_range | 0.072 | +| entropy_loss | -7.48 | +| explained_variance | -0.0681 | +| learning_rate | 4.71e-05 | +| loss | -0.0293 | +| n_updates | 39600 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000129 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.386 | +| time/ | | +| fps | 1421 | +| iterations | 5947 | +| time_elapsed | 8568 | +| total_timesteps | 12179456 | +| train/ | | +| approx_kl | 0.007682667 | +| clip_fraction | 0.269 | +| clip_range | 0.072 | +| entropy_loss | -6.99 | +| explained_variance | 0.44 | +| learning_rate | 4.71e-05 | +| loss | -0.0202 | +| n_updates | 39604 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000326 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.392 | +| time/ | | +| fps | 1421 | +| iterations | 5948 | +| time_elapsed | 8569 | +| total_timesteps | 12181504 | +| train/ | | +| approx_kl | 0.009092784 | +| clip_fraction | 0.284 | +| clip_range | 0.072 | +| entropy_loss | -6.74 | +| explained_variance | 0.266 | +| learning_rate | 4.71e-05 | +| loss | -0.0225 | +| n_updates | 39608 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000243 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.389 | +| time/ | | +| fps | 1421 | +| iterations | 5949 | +| time_elapsed | 8571 | +| total_timesteps | 12183552 | +| train/ | | +| approx_kl | 0.013059441 | +| clip_fraction | 0.341 | +| clip_range | 0.072 | +| entropy_loss | -6.93 | +| explained_variance | 0.472 | +| learning_rate | 4.71e-05 | +| loss | -0.0393 | +| n_updates | 39612 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000146 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.391 | +| time/ | | +| fps | 1421 | +| iterations | 5950 | +| time_elapsed | 8572 | +| total_timesteps | 12185600 | +| train/ | | +| approx_kl | 0.010241419 | +| clip_fraction | 0.306 | +| clip_range | 0.072 | +| entropy_loss | -7.12 | +| explained_variance | 0.244 | +| learning_rate | 4.71e-05 | +| loss | -0.032 | +| n_updates | 39616 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000237 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.391 | +| time/ | | +| fps | 1421 | +| iterations | 5951 | +| time_elapsed | 8573 | +| total_timesteps | 12187648 | +| train/ | | +| approx_kl | 0.0088957315 | +| clip_fraction | 0.299 | +| clip_range | 0.072 | +| entropy_loss | -7.14 | +| explained_variance | 0.463 | +| learning_rate | 4.71e-05 | +| loss | -0.0312 | +| n_updates | 39620 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000158 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.389 | +| time/ | | +| fps | 1421 | +| iterations | 5952 | +| time_elapsed | 8575 | +| total_timesteps | 12189696 | +| train/ | | +| approx_kl | 0.011007132 | +| clip_fraction | 0.315 | +| clip_range | 0.072 | +| entropy_loss | -7.47 | +| explained_variance | -0.19 | +| learning_rate | 4.71e-05 | +| loss | -0.036 | +| n_updates | 39624 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000155 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.389 | +| time/ | | +| fps | 1421 | +| iterations | 5953 | +| time_elapsed | 8576 | +| total_timesteps | 12191744 | +| train/ | | +| approx_kl | 0.011196515 | +| clip_fraction | 0.325 | +| clip_range | 0.072 | +| entropy_loss | -6.81 | +| explained_variance | 0.74 | +| learning_rate | 4.71e-05 | +| loss | -0.0361 | +| n_updates | 39628 | +| policy_gradient_loss | -0.0213 | +| value_loss | 6.84e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.389 | +| time/ | | +| fps | 1421 | +| iterations | 5954 | +| time_elapsed | 8578 | +| total_timesteps | 12193792 | +| train/ | | +| approx_kl | 0.009747912 | +| clip_fraction | 0.302 | +| clip_range | 0.072 | +| entropy_loss | -7.46 | +| explained_variance | -0.146 | +| learning_rate | 4.71e-05 | +| loss | -0.0359 | +| n_updates | 39632 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000119 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.391 | +| time/ | | +| fps | 1421 | +| iterations | 5955 | +| time_elapsed | 8579 | +| total_timesteps | 12195840 | +| train/ | | +| approx_kl | 0.009722291 | +| clip_fraction | 0.284 | +| clip_range | 0.072 | +| entropy_loss | -7.59 | +| explained_variance | -0.0506 | +| learning_rate | 4.71e-05 | +| loss | -0.0319 | +| n_updates | 39636 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000126 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.397 | +| time/ | | +| fps | 1421 | +| iterations | 5956 | +| time_elapsed | 8581 | +| total_timesteps | 12197888 | +| train/ | | +| approx_kl | 0.0087629 | +| clip_fraction | 0.284 | +| clip_range | 0.072 | +| entropy_loss | -7.37 | +| explained_variance | 0.253 | +| learning_rate | 4.71e-05 | +| loss | -0.0277 | +| n_updates | 39640 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000269 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.396 | +| time/ | | +| fps | 1421 | +| iterations | 5957 | +| time_elapsed | 8582 | +| total_timesteps | 12199936 | +| train/ | | +| approx_kl | 0.009312855 | +| clip_fraction | 0.274 | +| clip_range | 0.072 | +| entropy_loss | -6.77 | +| explained_variance | 0.431 | +| learning_rate | 4.71e-05 | +| loss | -0.0272 | +| n_updates | 39644 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.00027 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.396 | +| time/ | | +| fps | 1421 | +| iterations | 5958 | +| time_elapsed | 8583 | +| total_timesteps | 12201984 | +| train/ | | +| approx_kl | 0.009671909 | +| clip_fraction | 0.299 | +| clip_range | 0.072 | +| entropy_loss | -7.16 | +| explained_variance | 0.308 | +| learning_rate | 4.71e-05 | +| loss | -0.0323 | +| n_updates | 39648 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000117 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.395 | +| time/ | | +| fps | 1421 | +| iterations | 5959 | +| time_elapsed | 8585 | +| total_timesteps | 12204032 | +| train/ | | +| approx_kl | 0.009957574 | +| clip_fraction | 0.298 | +| clip_range | 0.0719 | +| entropy_loss | -6.79 | +| explained_variance | 0.509 | +| learning_rate | 4.71e-05 | +| loss | -0.0286 | +| n_updates | 39652 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.00021 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.395 | +| time/ | | +| fps | 1421 | +| iterations | 5960 | +| time_elapsed | 8586 | +| total_timesteps | 12206080 | +| train/ | | +| approx_kl | 0.010121122 | +| clip_fraction | 0.289 | +| clip_range | 0.0719 | +| entropy_loss | -7.26 | +| explained_variance | 0.434 | +| learning_rate | 4.71e-05 | +| loss | -0.0303 | +| n_updates | 39656 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.00011 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.395 | +| time/ | | +| fps | 1421 | +| iterations | 5961 | +| time_elapsed | 8588 | +| total_timesteps | 12208128 | +| train/ | | +| approx_kl | 0.010002249 | +| clip_fraction | 0.28 | +| clip_range | 0.0719 | +| entropy_loss | -7.29 | +| explained_variance | 0.243 | +| learning_rate | 4.71e-05 | +| loss | -0.0287 | +| n_updates | 39660 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000281 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.395 | +| time/ | | +| fps | 1421 | +| iterations | 5962 | +| time_elapsed | 8589 | +| total_timesteps | 12210176 | +| train/ | | +| approx_kl | 0.009650644 | +| clip_fraction | 0.302 | +| clip_range | 0.0719 | +| entropy_loss | -7.14 | +| explained_variance | 0.396 | +| learning_rate | 4.71e-05 | +| loss | -0.0361 | +| n_updates | 39664 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000119 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.399 | +| time/ | | +| fps | 1421 | +| iterations | 5963 | +| time_elapsed | 8591 | +| total_timesteps | 12212224 | +| train/ | | +| approx_kl | 0.01041056 | +| clip_fraction | 0.301 | +| clip_range | 0.0719 | +| entropy_loss | -7.11 | +| explained_variance | 0.347 | +| learning_rate | 4.71e-05 | +| loss | -0.0304 | +| n_updates | 39668 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.00024 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.399 | +| time/ | | +| fps | 1421 | +| iterations | 5964 | +| time_elapsed | 8592 | +| total_timesteps | 12214272 | +| train/ | | +| approx_kl | 0.009155284 | +| clip_fraction | 0.298 | +| clip_range | 0.0719 | +| entropy_loss | -7.43 | +| explained_variance | 0.00516 | +| learning_rate | 4.71e-05 | +| loss | -0.0323 | +| n_updates | 39672 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000259 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.399 | +| time/ | | +| fps | 1421 | +| iterations | 5965 | +| time_elapsed | 8594 | +| total_timesteps | 12216320 | +| train/ | | +| approx_kl | 0.009923243 | +| clip_fraction | 0.321 | +| clip_range | 0.0719 | +| entropy_loss | -7.37 | +| explained_variance | 0.285 | +| learning_rate | 4.71e-05 | +| loss | -0.0354 | +| n_updates | 39676 | +| policy_gradient_loss | -0.0226 | +| value_loss | 9.76e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.393 | +| time/ | | +| fps | 1421 | +| iterations | 5966 | +| time_elapsed | 8595 | +| total_timesteps | 12218368 | +| train/ | | +| approx_kl | 0.0093506975 | +| clip_fraction | 0.299 | +| clip_range | 0.0719 | +| entropy_loss | -7.59 | +| explained_variance | -0.137 | +| learning_rate | 4.71e-05 | +| loss | -0.035 | +| n_updates | 39680 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000192 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.392 | +| time/ | | +| fps | 1421 | +| iterations | 5967 | +| time_elapsed | 8597 | +| total_timesteps | 12220416 | +| train/ | | +| approx_kl | 0.009671031 | +| clip_fraction | 0.31 | +| clip_range | 0.0719 | +| entropy_loss | -7.11 | +| explained_variance | 0.475 | +| learning_rate | 4.71e-05 | +| loss | -0.0282 | +| n_updates | 39684 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000166 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.4 | +| time/ | | +| fps | 1421 | +| iterations | 5968 | +| time_elapsed | 8598 | +| total_timesteps | 12222464 | +| train/ | | +| approx_kl | 0.009550896 | +| clip_fraction | 0.308 | +| clip_range | 0.0719 | +| entropy_loss | -7.26 | +| explained_variance | 0.276 | +| learning_rate | 4.71e-05 | +| loss | -0.0339 | +| n_updates | 39688 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000136 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.401 | +| time/ | | +| fps | 1421 | +| iterations | 5969 | +| time_elapsed | 8599 | +| total_timesteps | 12224512 | +| train/ | | +| approx_kl | 0.008581847 | +| clip_fraction | 0.269 | +| clip_range | 0.0719 | +| entropy_loss | -6.91 | +| explained_variance | 0.218 | +| learning_rate | 4.71e-05 | +| loss | -0.0298 | +| n_updates | 39692 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000213 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.401 | +| time/ | | +| fps | 1421 | +| iterations | 5970 | +| time_elapsed | 8601 | +| total_timesteps | 12226560 | +| train/ | | +| approx_kl | 0.009996962 | +| clip_fraction | 0.302 | +| clip_range | 0.0719 | +| entropy_loss | -7.16 | +| explained_variance | 0.183 | +| learning_rate | 4.71e-05 | +| loss | -0.0276 | +| n_updates | 39696 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000228 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.404 | +| time/ | | +| fps | 1421 | +| iterations | 5971 | +| time_elapsed | 8602 | +| total_timesteps | 12228608 | +| train/ | | +| approx_kl | 0.010535374 | +| clip_fraction | 0.321 | +| clip_range | 0.0719 | +| entropy_loss | -7.28 | +| explained_variance | -0.189 | +| learning_rate | 4.71e-05 | +| loss | -0.0367 | +| n_updates | 39700 | +| policy_gradient_loss | -0.0218 | +| value_loss | 9.8e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.406 | +| time/ | | +| fps | 1421 | +| iterations | 5972 | +| time_elapsed | 8604 | +| total_timesteps | 12230656 | +| train/ | | +| approx_kl | 0.010102782 | +| clip_fraction | 0.291 | +| clip_range | 0.0719 | +| entropy_loss | -7.44 | +| explained_variance | -0.111 | +| learning_rate | 4.71e-05 | +| loss | -0.0272 | +| n_updates | 39704 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000115 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.403 | +| time/ | | +| fps | 1421 | +| iterations | 5973 | +| time_elapsed | 8605 | +| total_timesteps | 12232704 | +| train/ | | +| approx_kl | 0.010941809 | +| clip_fraction | 0.292 | +| clip_range | 0.0719 | +| entropy_loss | -6.96 | +| explained_variance | 0.322 | +| learning_rate | 4.71e-05 | +| loss | -0.0286 | +| n_updates | 39708 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000283 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.403 | +| time/ | | +| fps | 1421 | +| iterations | 5974 | +| time_elapsed | 8607 | +| total_timesteps | 12234752 | +| train/ | | +| approx_kl | 0.010843487 | +| clip_fraction | 0.294 | +| clip_range | 0.0719 | +| entropy_loss | -7.46 | +| explained_variance | -0.0228 | +| learning_rate | 4.71e-05 | +| loss | -0.0299 | +| n_updates | 39712 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000102 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.404 | +| time/ | | +| fps | 1421 | +| iterations | 5975 | +| time_elapsed | 8608 | +| total_timesteps | 12236800 | +| train/ | | +| approx_kl | 0.009617582 | +| clip_fraction | 0.283 | +| clip_range | 0.0719 | +| entropy_loss | -7.48 | +| explained_variance | -0.0132 | +| learning_rate | 4.71e-05 | +| loss | -0.0354 | +| n_updates | 39716 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000185 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.405 | +| time/ | | +| fps | 1421 | +| iterations | 5976 | +| time_elapsed | 8609 | +| total_timesteps | 12238848 | +| train/ | | +| approx_kl | 0.011205662 | +| clip_fraction | 0.292 | +| clip_range | 0.0719 | +| entropy_loss | -7.28 | +| explained_variance | 0.0932 | +| learning_rate | 4.71e-05 | +| loss | -0.0293 | +| n_updates | 39720 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000199 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.405 | +| time/ | | +| fps | 1421 | +| iterations | 5977 | +| time_elapsed | 8611 | +| total_timesteps | 12240896 | +| train/ | | +| approx_kl | 0.009878099 | +| clip_fraction | 0.308 | +| clip_range | 0.0719 | +| entropy_loss | -7.25 | +| explained_variance | 0.262 | +| learning_rate | 4.71e-05 | +| loss | -0.0291 | +| n_updates | 39724 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000144 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.405 | +| time/ | | +| fps | 1421 | +| iterations | 5978 | +| time_elapsed | 8612 | +| total_timesteps | 12242944 | +| train/ | | +| approx_kl | 0.011597238 | +| clip_fraction | 0.344 | +| clip_range | 0.0719 | +| entropy_loss | -7.33 | +| explained_variance | 0.478 | +| learning_rate | 4.71e-05 | +| loss | -0.0409 | +| n_updates | 39728 | +| policy_gradient_loss | -0.0248 | +| value_loss | 7.2e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.394 | +| time/ | | +| fps | 1421 | +| iterations | 5979 | +| time_elapsed | 8614 | +| total_timesteps | 12244992 | +| train/ | | +| approx_kl | 0.008739076 | +| clip_fraction | 0.294 | +| clip_range | 0.0719 | +| entropy_loss | -7.54 | +| explained_variance | -0.571 | +| learning_rate | 4.71e-05 | +| loss | -0.0345 | +| n_updates | 39732 | +| policy_gradient_loss | -0.0183 | +| value_loss | 5.83e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.394 | +| time/ | | +| fps | 1421 | +| iterations | 5980 | +| time_elapsed | 8615 | +| total_timesteps | 12247040 | +| train/ | | +| approx_kl | 0.007878506 | +| clip_fraction | 0.288 | +| clip_range | 0.0719 | +| entropy_loss | -6.39 | +| explained_variance | 0.335 | +| learning_rate | 4.71e-05 | +| loss | -0.0281 | +| n_updates | 39736 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000296 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.394 | +| time/ | | +| fps | 1421 | +| iterations | 5981 | +| time_elapsed | 8617 | +| total_timesteps | 12249088 | +| train/ | | +| approx_kl | 0.010871444 | +| clip_fraction | 0.315 | +| clip_range | 0.0719 | +| entropy_loss | -6.72 | +| explained_variance | 0.571 | +| learning_rate | 4.71e-05 | +| loss | -0.0378 | +| n_updates | 39740 | +| policy_gradient_loss | -0.0201 | +| value_loss | 8.63e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.393 | +| time/ | | +| fps | 1421 | +| iterations | 5982 | +| time_elapsed | 8618 | +| total_timesteps | 12251136 | +| train/ | | +| approx_kl | 0.009216207 | +| clip_fraction | 0.323 | +| clip_range | 0.0719 | +| entropy_loss | -7.47 | +| explained_variance | 0.071 | +| learning_rate | 4.71e-05 | +| loss | -0.0302 | +| n_updates | 39744 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000188 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.391 | +| time/ | | +| fps | 1421 | +| iterations | 5983 | +| time_elapsed | 8619 | +| total_timesteps | 12253184 | +| train/ | | +| approx_kl | 0.009608645 | +| clip_fraction | 0.282 | +| clip_range | 0.0719 | +| entropy_loss | -7.16 | +| explained_variance | 0.22 | +| learning_rate | 4.71e-05 | +| loss | -0.0301 | +| n_updates | 39748 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000124 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1421 | +| iterations | 5984 | +| time_elapsed | 8621 | +| total_timesteps | 12255232 | +| train/ | | +| approx_kl | 0.009308788 | +| clip_fraction | 0.284 | +| clip_range | 0.0719 | +| entropy_loss | -7.1 | +| explained_variance | 0.6 | +| learning_rate | 4.71e-05 | +| loss | -0.0307 | +| n_updates | 39752 | +| policy_gradient_loss | -0.0189 | +| value_loss | 9.07e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1421 | +| iterations | 5985 | +| time_elapsed | 8622 | +| total_timesteps | 12257280 | +| train/ | | +| approx_kl | 0.010151867 | +| clip_fraction | 0.311 | +| clip_range | 0.0719 | +| entropy_loss | -7.3 | +| explained_variance | 0.291 | +| learning_rate | 4.71e-05 | +| loss | -0.0309 | +| n_updates | 39756 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000177 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1421 | +| iterations | 5986 | +| time_elapsed | 8624 | +| total_timesteps | 12259328 | +| train/ | | +| approx_kl | 0.0086138975 | +| clip_fraction | 0.297 | +| clip_range | 0.0719 | +| entropy_loss | -6.84 | +| explained_variance | 0.642 | +| learning_rate | 4.71e-05 | +| loss | -0.0314 | +| n_updates | 39760 | +| policy_gradient_loss | -0.0197 | +| value_loss | 8.7e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1421 | +| iterations | 5987 | +| time_elapsed | 8625 | +| total_timesteps | 12261376 | +| train/ | | +| approx_kl | 0.009695408 | +| clip_fraction | 0.285 | +| clip_range | 0.0719 | +| entropy_loss | -7.42 | +| explained_variance | -0.0894 | +| learning_rate | 4.71e-05 | +| loss | -0.0286 | +| n_updates | 39764 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000169 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1421 | +| iterations | 5988 | +| time_elapsed | 8627 | +| total_timesteps | 12263424 | +| train/ | | +| approx_kl | 0.010137611 | +| clip_fraction | 0.299 | +| clip_range | 0.0719 | +| entropy_loss | -7.37 | +| explained_variance | 0.0209 | +| learning_rate | 4.71e-05 | +| loss | -0.034 | +| n_updates | 39768 | +| policy_gradient_loss | -0.0212 | +| value_loss | 9.82e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1421 | +| iterations | 5989 | +| time_elapsed | 8628 | +| total_timesteps | 12265472 | +| train/ | | +| approx_kl | 0.00971774 | +| clip_fraction | 0.28 | +| clip_range | 0.0719 | +| entropy_loss | -6.83 | +| explained_variance | 0.333 | +| learning_rate | 4.71e-05 | +| loss | -0.0226 | +| n_updates | 39772 | +| policy_gradient_loss | -0.0146 | +| value_loss | 0.000219 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1421 | +| iterations | 5990 | +| time_elapsed | 8630 | +| total_timesteps | 12267520 | +| train/ | | +| approx_kl | 0.010458933 | +| clip_fraction | 0.309 | +| clip_range | 0.0719 | +| entropy_loss | -7.04 | +| explained_variance | 0.216 | +| learning_rate | 4.71e-05 | +| loss | -0.0261 | +| n_updates | 39776 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000182 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1421 | +| iterations | 5991 | +| time_elapsed | 8631 | +| total_timesteps | 12269568 | +| train/ | | +| approx_kl | 0.0106561575 | +| clip_fraction | 0.292 | +| clip_range | 0.0719 | +| entropy_loss | -7.21 | +| explained_variance | 0.264 | +| learning_rate | 4.71e-05 | +| loss | -0.0274 | +| n_updates | 39780 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000248 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1421 | +| iterations | 5992 | +| time_elapsed | 8632 | +| total_timesteps | 12271616 | +| train/ | | +| approx_kl | 0.009932054 | +| clip_fraction | 0.291 | +| clip_range | 0.0719 | +| entropy_loss | -7.2 | +| explained_variance | 0.241 | +| learning_rate | 4.71e-05 | +| loss | -0.0266 | +| n_updates | 39784 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000171 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1421 | +| iterations | 5993 | +| time_elapsed | 8634 | +| total_timesteps | 12273664 | +| train/ | | +| approx_kl | 0.0117052905 | +| clip_fraction | 0.323 | +| clip_range | 0.0719 | +| entropy_loss | -7.36 | +| explained_variance | 0.367 | +| learning_rate | 4.71e-05 | +| loss | -0.0358 | +| n_updates | 39788 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000108 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1421 | +| iterations | 5994 | +| time_elapsed | 8635 | +| total_timesteps | 12275712 | +| train/ | | +| approx_kl | 0.0104987025 | +| clip_fraction | 0.305 | +| clip_range | 0.0719 | +| entropy_loss | -7.46 | +| explained_variance | -0.0848 | +| learning_rate | 4.71e-05 | +| loss | -0.0376 | +| n_updates | 39792 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000147 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1421 | +| iterations | 5995 | +| time_elapsed | 8637 | +| total_timesteps | 12277760 | +| train/ | | +| approx_kl | 0.011182131 | +| clip_fraction | 0.311 | +| clip_range | 0.0719 | +| entropy_loss | -7.15 | +| explained_variance | 0.452 | +| learning_rate | 4.71e-05 | +| loss | -0.0257 | +| n_updates | 39796 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.00018 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1421 | +| iterations | 5996 | +| time_elapsed | 8638 | +| total_timesteps | 12279808 | +| train/ | | +| approx_kl | 0.010736588 | +| clip_fraction | 0.281 | +| clip_range | 0.0719 | +| entropy_loss | -6.88 | +| explained_variance | 0.513 | +| learning_rate | 4.71e-05 | +| loss | -0.0263 | +| n_updates | 39800 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.00018 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1421 | +| iterations | 5997 | +| time_elapsed | 8640 | +| total_timesteps | 12281856 | +| train/ | | +| approx_kl | 0.0108119715 | +| clip_fraction | 0.317 | +| clip_range | 0.0719 | +| entropy_loss | -7.06 | +| explained_variance | 0.532 | +| learning_rate | 4.71e-05 | +| loss | -0.0335 | +| n_updates | 39804 | +| policy_gradient_loss | -0.0217 | +| value_loss | 9.53e-05 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1421 | +| iterations | 5998 | +| time_elapsed | 8641 | +| total_timesteps | 12283904 | +| train/ | | +| approx_kl | 0.00959738 | +| clip_fraction | 0.323 | +| clip_range | 0.0719 | +| entropy_loss | -7.4 | +| explained_variance | -0.091 | +| learning_rate | 4.71e-05 | +| loss | -0.0377 | +| n_updates | 39808 | +| policy_gradient_loss | -0.0209 | +| value_loss | 9.73e-05 | +---------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1421 | +| iterations | 5999 | +| time_elapsed | 8642 | +| total_timesteps | 12285952 | +| train/ | | +| approx_kl | 0.0090618 | +| clip_fraction | 0.279 | +| clip_range | 0.0719 | +| entropy_loss | -7.03 | +| explained_variance | 0.526 | +| learning_rate | 4.71e-05 | +| loss | -0.0315 | +| n_updates | 39812 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000124 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1421 | +| iterations | 6000 | +| time_elapsed | 8644 | +| total_timesteps | 12288000 | +| train/ | | +| approx_kl | 0.008020125 | +| clip_fraction | 0.251 | +| clip_range | 0.0719 | +| entropy_loss | -6.51 | +| explained_variance | 0.439 | +| learning_rate | 4.71e-05 | +| loss | -0.0255 | +| n_updates | 39816 | +| policy_gradient_loss | -0.0145 | +| value_loss | 0.000286 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1421 | +| iterations | 6001 | +| time_elapsed | 8645 | +| total_timesteps | 12290048 | +| train/ | | +| approx_kl | 0.010631819 | +| clip_fraction | 0.305 | +| clip_range | 0.0719 | +| entropy_loss | -7.1 | +| explained_variance | 0.197 | +| learning_rate | 4.71e-05 | +| loss | -0.0301 | +| n_updates | 39820 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000294 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1421 | +| iterations | 6002 | +| time_elapsed | 8647 | +| total_timesteps | 12292096 | +| train/ | | +| approx_kl | 0.010468841 | +| clip_fraction | 0.307 | +| clip_range | 0.0719 | +| entropy_loss | -7.32 | +| explained_variance | 0.263 | +| learning_rate | 4.71e-05 | +| loss | -0.0343 | +| n_updates | 39824 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000166 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1421 | +| iterations | 6003 | +| time_elapsed | 8648 | +| total_timesteps | 12294144 | +| train/ | | +| approx_kl | 0.009418357 | +| clip_fraction | 0.299 | +| clip_range | 0.0719 | +| entropy_loss | -7.47 | +| explained_variance | 0.234 | +| learning_rate | 4.71e-05 | +| loss | -0.0291 | +| n_updates | 39828 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000172 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1421 | +| iterations | 6004 | +| time_elapsed | 8649 | +| total_timesteps | 12296192 | +| train/ | | +| approx_kl | 0.008926481 | +| clip_fraction | 0.305 | +| clip_range | 0.0719 | +| entropy_loss | -7.4 | +| explained_variance | 0.0381 | +| learning_rate | 4.71e-05 | +| loss | -0.039 | +| n_updates | 39832 | +| policy_gradient_loss | -0.0228 | +| value_loss | 9.52e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1421 | +| iterations | 6005 | +| time_elapsed | 8651 | +| total_timesteps | 12298240 | +| train/ | | +| approx_kl | 0.00888671 | +| clip_fraction | 0.294 | +| clip_range | 0.0719 | +| entropy_loss | -6.8 | +| explained_variance | 0.39 | +| learning_rate | 4.71e-05 | +| loss | -0.0228 | +| n_updates | 39836 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000304 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1421 | +| iterations | 6006 | +| time_elapsed | 8652 | +| total_timesteps | 12300288 | +| train/ | | +| approx_kl | 0.01100219 | +| clip_fraction | 0.287 | +| clip_range | 0.0719 | +| entropy_loss | -7.25 | +| explained_variance | 0.144 | +| learning_rate | 4.71e-05 | +| loss | -0.0301 | +| n_updates | 39840 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000149 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1421 | +| iterations | 6007 | +| time_elapsed | 8654 | +| total_timesteps | 12302336 | +| train/ | | +| approx_kl | 0.009655177 | +| clip_fraction | 0.301 | +| clip_range | 0.0719 | +| entropy_loss | -7.04 | +| explained_variance | 0.528 | +| learning_rate | 4.71e-05 | +| loss | -0.0292 | +| n_updates | 39844 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000158 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1421 | +| iterations | 6008 | +| time_elapsed | 8655 | +| total_timesteps | 12304384 | +| train/ | | +| approx_kl | 0.010229504 | +| clip_fraction | 0.342 | +| clip_range | 0.0719 | +| entropy_loss | -7.53 | +| explained_variance | -0.551 | +| learning_rate | 4.71e-05 | +| loss | -0.0455 | +| n_updates | 39848 | +| policy_gradient_loss | -0.0248 | +| value_loss | 5.43e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1421 | +| iterations | 6009 | +| time_elapsed | 8657 | +| total_timesteps | 12306432 | +| train/ | | +| approx_kl | 0.009760277 | +| clip_fraction | 0.291 | +| clip_range | 0.0719 | +| entropy_loss | -7.41 | +| explained_variance | 0.0894 | +| learning_rate | 4.71e-05 | +| loss | -0.0306 | +| n_updates | 39852 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000105 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1421 | +| iterations | 6010 | +| time_elapsed | 8658 | +| total_timesteps | 12308480 | +| train/ | | +| approx_kl | 0.0101456065 | +| clip_fraction | 0.274 | +| clip_range | 0.0719 | +| entropy_loss | -7.44 | +| explained_variance | -0.134 | +| learning_rate | 4.71e-05 | +| loss | -0.0276 | +| n_updates | 39856 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000183 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1421 | +| iterations | 6011 | +| time_elapsed | 8660 | +| total_timesteps | 12310528 | +| train/ | | +| approx_kl | 0.0073783705 | +| clip_fraction | 0.261 | +| clip_range | 0.0719 | +| entropy_loss | -6.64 | +| explained_variance | 0.242 | +| learning_rate | 4.71e-05 | +| loss | -0.0227 | +| n_updates | 39860 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.00037 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1421 | +| iterations | 6012 | +| time_elapsed | 8661 | +| total_timesteps | 12312576 | +| train/ | | +| approx_kl | 0.010228187 | +| clip_fraction | 0.331 | +| clip_range | 0.0719 | +| entropy_loss | -7.11 | +| explained_variance | 0.2 | +| learning_rate | 4.71e-05 | +| loss | -0.034 | +| n_updates | 39864 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000178 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1421 | +| iterations | 6013 | +| time_elapsed | 8663 | +| total_timesteps | 12314624 | +| train/ | | +| approx_kl | 0.010582101 | +| clip_fraction | 0.283 | +| clip_range | 0.0719 | +| entropy_loss | -6.87 | +| explained_variance | 0.428 | +| learning_rate | 4.71e-05 | +| loss | -0.03 | +| n_updates | 39868 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000199 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1421 | +| iterations | 6014 | +| time_elapsed | 8664 | +| total_timesteps | 12316672 | +| train/ | | +| approx_kl | 0.011229965 | +| clip_fraction | 0.31 | +| clip_range | 0.0719 | +| entropy_loss | -7.13 | +| explained_variance | 0.381 | +| learning_rate | 4.71e-05 | +| loss | -0.0272 | +| n_updates | 39872 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000121 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1421 | +| iterations | 6015 | +| time_elapsed | 8665 | +| total_timesteps | 12318720 | +| train/ | | +| approx_kl | 0.009962484 | +| clip_fraction | 0.307 | +| clip_range | 0.0719 | +| entropy_loss | -7.35 | +| explained_variance | -0.122 | +| learning_rate | 4.71e-05 | +| loss | -0.0296 | +| n_updates | 39876 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000126 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1421 | +| iterations | 6016 | +| time_elapsed | 8667 | +| total_timesteps | 12320768 | +| train/ | | +| approx_kl | 0.009364452 | +| clip_fraction | 0.273 | +| clip_range | 0.0719 | +| entropy_loss | -7.24 | +| explained_variance | 0.279 | +| learning_rate | 4.71e-05 | +| loss | -0.0223 | +| n_updates | 39880 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000295 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1421 | +| iterations | 6017 | +| time_elapsed | 8668 | +| total_timesteps | 12322816 | +| train/ | | +| approx_kl | 0.010029761 | +| clip_fraction | 0.323 | +| clip_range | 0.0719 | +| entropy_loss | -7.4 | +| explained_variance | -0.199 | +| learning_rate | 4.71e-05 | +| loss | -0.031 | +| n_updates | 39884 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000129 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1421 | +| iterations | 6018 | +| time_elapsed | 8670 | +| total_timesteps | 12324864 | +| train/ | | +| approx_kl | 0.010474677 | +| clip_fraction | 0.302 | +| clip_range | 0.0719 | +| entropy_loss | -7.07 | +| explained_variance | 0.285 | +| learning_rate | 4.71e-05 | +| loss | -0.0336 | +| n_updates | 39888 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000215 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1421 | +| iterations | 6019 | +| time_elapsed | 8671 | +| total_timesteps | 12326912 | +| train/ | | +| approx_kl | 0.009953225 | +| clip_fraction | 0.292 | +| clip_range | 0.0719 | +| entropy_loss | -7.11 | +| explained_variance | 0.455 | +| learning_rate | 4.71e-05 | +| loss | -0.0316 | +| n_updates | 39892 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000191 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1421 | +| iterations | 6020 | +| time_elapsed | 8673 | +| total_timesteps | 12328960 | +| train/ | | +| approx_kl | 0.009171228 | +| clip_fraction | 0.284 | +| clip_range | 0.0719 | +| entropy_loss | -6.98 | +| explained_variance | 0.358 | +| learning_rate | 4.71e-05 | +| loss | -0.0331 | +| n_updates | 39896 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000143 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1421 | +| iterations | 6021 | +| time_elapsed | 8674 | +| total_timesteps | 12331008 | +| train/ | | +| approx_kl | 0.009521158 | +| clip_fraction | 0.31 | +| clip_range | 0.0719 | +| entropy_loss | -7.34 | +| explained_variance | 0.323 | +| learning_rate | 4.71e-05 | +| loss | -0.0292 | +| n_updates | 39900 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000129 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1421 | +| iterations | 6022 | +| time_elapsed | 8676 | +| total_timesteps | 12333056 | +| train/ | | +| approx_kl | 0.008930854 | +| clip_fraction | 0.274 | +| clip_range | 0.0719 | +| entropy_loss | -7.1 | +| explained_variance | 0.161 | +| learning_rate | 4.71e-05 | +| loss | -0.0214 | +| n_updates | 39904 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.000333 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1421 | +| iterations | 6023 | +| time_elapsed | 8677 | +| total_timesteps | 12335104 | +| train/ | | +| approx_kl | 0.008579133 | +| clip_fraction | 0.279 | +| clip_range | 0.0719 | +| entropy_loss | -6.86 | +| explained_variance | 0.496 | +| learning_rate | 4.71e-05 | +| loss | -0.0254 | +| n_updates | 39908 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000212 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1421 | +| iterations | 6024 | +| time_elapsed | 8678 | +| total_timesteps | 12337152 | +| train/ | | +| approx_kl | 0.0128711285 | +| clip_fraction | 0.316 | +| clip_range | 0.0719 | +| entropy_loss | -7.31 | +| explained_variance | 0.248 | +| learning_rate | 4.71e-05 | +| loss | -0.0288 | +| n_updates | 39912 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000163 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1421 | +| iterations | 6025 | +| time_elapsed | 8680 | +| total_timesteps | 12339200 | +| train/ | | +| approx_kl | 0.010179512 | +| clip_fraction | 0.278 | +| clip_range | 0.0719 | +| entropy_loss | -7.16 | +| explained_variance | 0.23 | +| learning_rate | 4.71e-05 | +| loss | -0.0215 | +| n_updates | 39916 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000302 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1421 | +| iterations | 6026 | +| time_elapsed | 8681 | +| total_timesteps | 12341248 | +| train/ | | +| approx_kl | 0.010781614 | +| clip_fraction | 0.328 | +| clip_range | 0.0719 | +| entropy_loss | -7.48 | +| explained_variance | 0.0987 | +| learning_rate | 4.71e-05 | +| loss | -0.0322 | +| n_updates | 39920 | +| policy_gradient_loss | -0.0231 | +| value_loss | 0.000115 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1421 | +| iterations | 6027 | +| time_elapsed | 8683 | +| total_timesteps | 12343296 | +| train/ | | +| approx_kl | 0.010444298 | +| clip_fraction | 0.321 | +| clip_range | 0.0719 | +| entropy_loss | -7.25 | +| explained_variance | 0.22 | +| learning_rate | 4.71e-05 | +| loss | -0.0336 | +| n_updates | 39924 | +| policy_gradient_loss | -0.0226 | +| value_loss | 0.000141 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1421 | +| iterations | 6028 | +| time_elapsed | 8684 | +| total_timesteps | 12345344 | +| train/ | | +| approx_kl | 0.012769068 | +| clip_fraction | 0.334 | +| clip_range | 0.0719 | +| entropy_loss | -7.16 | +| explained_variance | 0.471 | +| learning_rate | 4.71e-05 | +| loss | -0.0318 | +| n_updates | 39928 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.00013 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1421 | +| iterations | 6029 | +| time_elapsed | 8686 | +| total_timesteps | 12347392 | +| train/ | | +| approx_kl | 0.009651901 | +| clip_fraction | 0.28 | +| clip_range | 0.0719 | +| entropy_loss | -7.34 | +| explained_variance | 0.317 | +| learning_rate | 4.71e-05 | +| loss | -0.0248 | +| n_updates | 39932 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000203 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1421 | +| iterations | 6030 | +| time_elapsed | 8687 | +| total_timesteps | 12349440 | +| train/ | | +| approx_kl | 0.00983477 | +| clip_fraction | 0.273 | +| clip_range | 0.0719 | +| entropy_loss | -6.82 | +| explained_variance | 0.496 | +| learning_rate | 4.71e-05 | +| loss | -0.0256 | +| n_updates | 39936 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000281 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1421 | +| iterations | 6031 | +| time_elapsed | 8688 | +| total_timesteps | 12351488 | +| train/ | | +| approx_kl | 0.009335637 | +| clip_fraction | 0.309 | +| clip_range | 0.0719 | +| entropy_loss | -7.36 | +| explained_variance | -0.182 | +| learning_rate | 4.71e-05 | +| loss | -0.0302 | +| n_updates | 39940 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000234 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1421 | +| iterations | 6032 | +| time_elapsed | 8690 | +| total_timesteps | 12353536 | +| train/ | | +| approx_kl | 0.011709744 | +| clip_fraction | 0.32 | +| clip_range | 0.0719 | +| entropy_loss | -7.1 | +| explained_variance | 0.453 | +| learning_rate | 4.71e-05 | +| loss | -0.0307 | +| n_updates | 39944 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000135 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1421 | +| iterations | 6033 | +| time_elapsed | 8691 | +| total_timesteps | 12355584 | +| train/ | | +| approx_kl | 0.010918024 | +| clip_fraction | 0.297 | +| clip_range | 0.0719 | +| entropy_loss | -7.24 | +| explained_variance | 0.247 | +| learning_rate | 4.71e-05 | +| loss | -0.0296 | +| n_updates | 39948 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000181 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1421 | +| iterations | 6034 | +| time_elapsed | 8693 | +| total_timesteps | 12357632 | +| train/ | | +| approx_kl | 0.012458449 | +| clip_fraction | 0.293 | +| clip_range | 0.0719 | +| entropy_loss | -7.28 | +| explained_variance | 0.0639 | +| learning_rate | 4.71e-05 | +| loss | -0.0279 | +| n_updates | 39952 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000446 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1421 | +| iterations | 6035 | +| time_elapsed | 8694 | +| total_timesteps | 12359680 | +| train/ | | +| approx_kl | 0.011162672 | +| clip_fraction | 0.34 | +| clip_range | 0.0719 | +| entropy_loss | -7.24 | +| explained_variance | -0.0184 | +| learning_rate | 4.71e-05 | +| loss | -0.0327 | +| n_updates | 39956 | +| policy_gradient_loss | -0.0223 | +| value_loss | 0.000179 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1421 | +| iterations | 6036 | +| time_elapsed | 8696 | +| total_timesteps | 12361728 | +| train/ | | +| approx_kl | 0.01043798 | +| clip_fraction | 0.296 | +| clip_range | 0.0719 | +| entropy_loss | -7.6 | +| explained_variance | -0.12 | +| learning_rate | 4.71e-05 | +| loss | -0.0344 | +| n_updates | 39960 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000242 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1421 | +| iterations | 6037 | +| time_elapsed | 8697 | +| total_timesteps | 12363776 | +| train/ | | +| approx_kl | 0.008998748 | +| clip_fraction | 0.291 | +| clip_range | 0.0719 | +| entropy_loss | -7.48 | +| explained_variance | -0.0601 | +| learning_rate | 4.71e-05 | +| loss | -0.0272 | +| n_updates | 39964 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000318 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1421 | +| iterations | 6038 | +| time_elapsed | 8699 | +| total_timesteps | 12365824 | +| train/ | | +| approx_kl | 0.007318358 | +| clip_fraction | 0.277 | +| clip_range | 0.0719 | +| entropy_loss | -6.54 | +| explained_variance | 0.433 | +| learning_rate | 4.71e-05 | +| loss | -0.0238 | +| n_updates | 39968 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000373 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1421 | +| iterations | 6039 | +| time_elapsed | 8700 | +| total_timesteps | 12367872 | +| train/ | | +| approx_kl | 0.010286437 | +| clip_fraction | 0.331 | +| clip_range | 0.0719 | +| entropy_loss | -7.06 | +| explained_variance | 0.574 | +| learning_rate | 4.71e-05 | +| loss | -0.0306 | +| n_updates | 39972 | +| policy_gradient_loss | -0.0226 | +| value_loss | 0.000108 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1421 | +| iterations | 6040 | +| time_elapsed | 8702 | +| total_timesteps | 12369920 | +| train/ | | +| approx_kl | 0.0091020055 | +| clip_fraction | 0.294 | +| clip_range | 0.0719 | +| entropy_loss | -7.17 | +| explained_variance | 0.391 | +| learning_rate | 4.71e-05 | +| loss | -0.0298 | +| n_updates | 39976 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000135 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1421 | +| iterations | 6041 | +| time_elapsed | 8703 | +| total_timesteps | 12371968 | +| train/ | | +| approx_kl | 0.0115649095 | +| clip_fraction | 0.319 | +| clip_range | 0.0719 | +| entropy_loss | -7.25 | +| explained_variance | 0.294 | +| learning_rate | 4.71e-05 | +| loss | -0.0317 | +| n_updates | 39980 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000135 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1421 | +| iterations | 6042 | +| time_elapsed | 8704 | +| total_timesteps | 12374016 | +| train/ | | +| approx_kl | 0.011392635 | +| clip_fraction | 0.308 | +| clip_range | 0.0719 | +| entropy_loss | -7.22 | +| explained_variance | 0.478 | +| learning_rate | 4.71e-05 | +| loss | -0.0328 | +| n_updates | 39984 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000162 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1421 | +| iterations | 6043 | +| time_elapsed | 8706 | +| total_timesteps | 12376064 | +| train/ | | +| approx_kl | 0.012359817 | +| clip_fraction | 0.313 | +| clip_range | 0.0719 | +| entropy_loss | -7.47 | +| explained_variance | -0.0156 | +| learning_rate | 4.71e-05 | +| loss | -0.0317 | +| n_updates | 39988 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000152 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1421 | +| iterations | 6044 | +| time_elapsed | 8707 | +| total_timesteps | 12378112 | +| train/ | | +| approx_kl | 0.008742361 | +| clip_fraction | 0.287 | +| clip_range | 0.0719 | +| entropy_loss | -7.28 | +| explained_variance | 0.111 | +| learning_rate | 4.71e-05 | +| loss | -0.0365 | +| n_updates | 39992 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000201 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1421 | +| iterations | 6045 | +| time_elapsed | 8709 | +| total_timesteps | 12380160 | +| train/ | | +| approx_kl | 0.010088338 | +| clip_fraction | 0.278 | +| clip_range | 0.0719 | +| entropy_loss | -7.22 | +| explained_variance | 0.401 | +| learning_rate | 4.71e-05 | +| loss | -0.0243 | +| n_updates | 39996 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000215 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1421 | +| iterations | 6046 | +| time_elapsed | 8710 | +| total_timesteps | 12382208 | +| train/ | | +| approx_kl | 0.010470904 | +| clip_fraction | 0.315 | +| clip_range | 0.0719 | +| entropy_loss | -6.95 | +| explained_variance | 0.586 | +| learning_rate | 4.71e-05 | +| loss | -0.036 | +| n_updates | 40000 | +| policy_gradient_loss | -0.0197 | +| value_loss | 8.16e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1421 | +| iterations | 6047 | +| time_elapsed | 8712 | +| total_timesteps | 12384256 | +| train/ | | +| approx_kl | 0.011014519 | +| clip_fraction | 0.3 | +| clip_range | 0.0719 | +| entropy_loss | -7.33 | +| explained_variance | 0.249 | +| learning_rate | 4.71e-05 | +| loss | -0.0306 | +| n_updates | 40004 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000114 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1421 | +| iterations | 6048 | +| time_elapsed | 8713 | +| total_timesteps | 12386304 | +| train/ | | +| approx_kl | 0.010926574 | +| clip_fraction | 0.292 | +| clip_range | 0.0719 | +| entropy_loss | -7.06 | +| explained_variance | 0.329 | +| learning_rate | 4.71e-05 | +| loss | -0.0339 | +| n_updates | 40008 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.00035 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1421 | +| iterations | 6049 | +| time_elapsed | 8715 | +| total_timesteps | 12388352 | +| train/ | | +| approx_kl | 0.010600241 | +| clip_fraction | 0.321 | +| clip_range | 0.0719 | +| entropy_loss | -7.26 | +| explained_variance | -0.157 | +| learning_rate | 4.71e-05 | +| loss | -0.0261 | +| n_updates | 40012 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000128 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1421 | +| iterations | 6050 | +| time_elapsed | 8716 | +| total_timesteps | 12390400 | +| train/ | | +| approx_kl | 0.009721623 | +| clip_fraction | 0.301 | +| clip_range | 0.0719 | +| entropy_loss | -7.37 | +| explained_variance | 0.246 | +| learning_rate | 4.71e-05 | +| loss | -0.0313 | +| n_updates | 40016 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000153 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1421 | +| iterations | 6051 | +| time_elapsed | 8717 | +| total_timesteps | 12392448 | +| train/ | | +| approx_kl | 0.011097183 | +| clip_fraction | 0.311 | +| clip_range | 0.0719 | +| entropy_loss | -7.06 | +| explained_variance | 0.581 | +| learning_rate | 4.71e-05 | +| loss | -0.0356 | +| n_updates | 40020 | +| policy_gradient_loss | -0.022 | +| value_loss | 9.23e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1421 | +| iterations | 6052 | +| time_elapsed | 8719 | +| total_timesteps | 12394496 | +| train/ | | +| approx_kl | 0.010225074 | +| clip_fraction | 0.311 | +| clip_range | 0.0719 | +| entropy_loss | -7.51 | +| explained_variance | 0.175 | +| learning_rate | 4.71e-05 | +| loss | -0.0372 | +| n_updates | 40024 | +| policy_gradient_loss | -0.0206 | +| value_loss | 8.4e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1421 | +| iterations | 6053 | +| time_elapsed | 8720 | +| total_timesteps | 12396544 | +| train/ | | +| approx_kl | 0.00900553 | +| clip_fraction | 0.294 | +| clip_range | 0.0719 | +| entropy_loss | -7.33 | +| explained_variance | 0.213 | +| learning_rate | 4.71e-05 | +| loss | -0.0296 | +| n_updates | 40028 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000161 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1421 | +| iterations | 6054 | +| time_elapsed | 8722 | +| total_timesteps | 12398592 | +| train/ | | +| approx_kl | 0.010795942 | +| clip_fraction | 0.284 | +| clip_range | 0.0719 | +| entropy_loss | -7.24 | +| explained_variance | 0.529 | +| learning_rate | 4.71e-05 | +| loss | -0.031 | +| n_updates | 40032 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000122 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1421 | +| iterations | 6055 | +| time_elapsed | 8723 | +| total_timesteps | 12400640 | +| train/ | | +| approx_kl | 0.009547551 | +| clip_fraction | 0.311 | +| clip_range | 0.0719 | +| entropy_loss | -6.82 | +| explained_variance | 0.747 | +| learning_rate | 4.71e-05 | +| loss | -0.0284 | +| n_updates | 40036 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000105 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1421 | +| iterations | 6056 | +| time_elapsed | 8725 | +| total_timesteps | 12402688 | +| train/ | | +| approx_kl | 0.009478878 | +| clip_fraction | 0.296 | +| clip_range | 0.0719 | +| entropy_loss | -7.15 | +| explained_variance | 0.276 | +| learning_rate | 4.71e-05 | +| loss | -0.0257 | +| n_updates | 40040 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000187 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1421 | +| iterations | 6057 | +| time_elapsed | 8726 | +| total_timesteps | 12404736 | +| train/ | | +| approx_kl | 0.010957414 | +| clip_fraction | 0.322 | +| clip_range | 0.0719 | +| entropy_loss | -7.34 | +| explained_variance | 0.385 | +| learning_rate | 4.71e-05 | +| loss | -0.0301 | +| n_updates | 40044 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000127 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1421 | +| iterations | 6058 | +| time_elapsed | 8727 | +| total_timesteps | 12406784 | +| train/ | | +| approx_kl | 0.00801085 | +| clip_fraction | 0.272 | +| clip_range | 0.0719 | +| entropy_loss | -7.47 | +| explained_variance | -0.0539 | +| learning_rate | 4.71e-05 | +| loss | -0.0307 | +| n_updates | 40048 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000297 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1421 | +| iterations | 6059 | +| time_elapsed | 8729 | +| total_timesteps | 12408832 | +| train/ | | +| approx_kl | 0.00974338 | +| clip_fraction | 0.323 | +| clip_range | 0.0719 | +| entropy_loss | -7.34 | +| explained_variance | 0.279 | +| learning_rate | 4.71e-05 | +| loss | -0.035 | +| n_updates | 40052 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000171 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1421 | +| iterations | 6060 | +| time_elapsed | 8730 | +| total_timesteps | 12410880 | +| train/ | | +| approx_kl | 0.011223275 | +| clip_fraction | 0.29 | +| clip_range | 0.0719 | +| entropy_loss | -7.34 | +| explained_variance | 0.273 | +| learning_rate | 4.71e-05 | +| loss | -0.0273 | +| n_updates | 40056 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000136 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1421 | +| iterations | 6061 | +| time_elapsed | 8732 | +| total_timesteps | 12412928 | +| train/ | | +| approx_kl | 0.008419425 | +| clip_fraction | 0.283 | +| clip_range | 0.0719 | +| entropy_loss | -7.03 | +| explained_variance | 0.373 | +| learning_rate | 4.71e-05 | +| loss | -0.0303 | +| n_updates | 40060 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000257 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1421 | +| iterations | 6062 | +| time_elapsed | 8733 | +| total_timesteps | 12414976 | +| train/ | | +| approx_kl | 0.0069281394 | +| clip_fraction | 0.251 | +| clip_range | 0.0719 | +| entropy_loss | -6.65 | +| explained_variance | 0.401 | +| learning_rate | 4.71e-05 | +| loss | -0.0227 | +| n_updates | 40064 | +| policy_gradient_loss | -0.0137 | +| value_loss | 0.000418 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1421 | +| iterations | 6063 | +| time_elapsed | 8735 | +| total_timesteps | 12417024 | +| train/ | | +| approx_kl | 0.009677617 | +| clip_fraction | 0.328 | +| clip_range | 0.0719 | +| entropy_loss | -7.21 | +| explained_variance | 0.312 | +| learning_rate | 4.71e-05 | +| loss | -0.0365 | +| n_updates | 40068 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000145 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1421 | +| iterations | 6064 | +| time_elapsed | 8736 | +| total_timesteps | 12419072 | +| train/ | | +| approx_kl | 0.009095686 | +| clip_fraction | 0.313 | +| clip_range | 0.0719 | +| entropy_loss | -7.12 | +| explained_variance | 0.501 | +| learning_rate | 4.71e-05 | +| loss | -0.0345 | +| n_updates | 40072 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000177 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1421 | +| iterations | 6065 | +| time_elapsed | 8738 | +| total_timesteps | 12421120 | +| train/ | | +| approx_kl | 0.009154325 | +| clip_fraction | 0.293 | +| clip_range | 0.0719 | +| entropy_loss | -7.08 | +| explained_variance | 0.38 | +| learning_rate | 4.71e-05 | +| loss | -0.0281 | +| n_updates | 40076 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000306 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1421 | +| iterations | 6066 | +| time_elapsed | 8739 | +| total_timesteps | 12423168 | +| train/ | | +| approx_kl | 0.009448168 | +| clip_fraction | 0.303 | +| clip_range | 0.0719 | +| entropy_loss | -7.56 | +| explained_variance | -0.0839 | +| learning_rate | 4.7e-05 | +| loss | -0.0337 | +| n_updates | 40080 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000227 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1421 | +| iterations | 6067 | +| time_elapsed | 8741 | +| total_timesteps | 12425216 | +| train/ | | +| approx_kl | 0.00909101 | +| clip_fraction | 0.302 | +| clip_range | 0.0719 | +| entropy_loss | -7.55 | +| explained_variance | -0.11 | +| learning_rate | 4.7e-05 | +| loss | -0.0313 | +| n_updates | 40084 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000143 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1421 | +| iterations | 6068 | +| time_elapsed | 8742 | +| total_timesteps | 12427264 | +| train/ | | +| approx_kl | 0.008464587 | +| clip_fraction | 0.297 | +| clip_range | 0.0719 | +| entropy_loss | -7.4 | +| explained_variance | 0.153 | +| learning_rate | 4.7e-05 | +| loss | -0.0262 | +| n_updates | 40088 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.00032 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1421 | +| iterations | 6069 | +| time_elapsed | 8743 | +| total_timesteps | 12429312 | +| train/ | | +| approx_kl | 0.010334728 | +| clip_fraction | 0.309 | +| clip_range | 0.0719 | +| entropy_loss | -6.97 | +| explained_variance | 0.61 | +| learning_rate | 4.7e-05 | +| loss | -0.027 | +| n_updates | 40092 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000146 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1421 | +| iterations | 6070 | +| time_elapsed | 8745 | +| total_timesteps | 12431360 | +| train/ | | +| approx_kl | 0.010016982 | +| clip_fraction | 0.311 | +| clip_range | 0.0719 | +| entropy_loss | -7.57 | +| explained_variance | -0.228 | +| learning_rate | 4.7e-05 | +| loss | -0.0411 | +| n_updates | 40096 | +| policy_gradient_loss | -0.0228 | +| value_loss | 9.3e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1421 | +| iterations | 6071 | +| time_elapsed | 8746 | +| total_timesteps | 12433408 | +| train/ | | +| approx_kl | 0.009503528 | +| clip_fraction | 0.295 | +| clip_range | 0.0719 | +| entropy_loss | -7.45 | +| explained_variance | -0.0788 | +| learning_rate | 4.7e-05 | +| loss | -0.0272 | +| n_updates | 40100 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000149 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1421 | +| iterations | 6072 | +| time_elapsed | 8748 | +| total_timesteps | 12435456 | +| train/ | | +| approx_kl | 0.010051066 | +| clip_fraction | 0.315 | +| clip_range | 0.0719 | +| entropy_loss | -7.07 | +| explained_variance | 0.566 | +| learning_rate | 4.7e-05 | +| loss | -0.0315 | +| n_updates | 40104 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000174 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1421 | +| iterations | 6073 | +| time_elapsed | 8749 | +| total_timesteps | 12437504 | +| train/ | | +| approx_kl | 0.011798056 | +| clip_fraction | 0.347 | +| clip_range | 0.0719 | +| entropy_loss | -7.22 | +| explained_variance | 0.564 | +| learning_rate | 4.7e-05 | +| loss | -0.0297 | +| n_updates | 40108 | +| policy_gradient_loss | -0.0224 | +| value_loss | 5.56e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1421 | +| iterations | 6074 | +| time_elapsed | 8751 | +| total_timesteps | 12439552 | +| train/ | | +| approx_kl | 0.012675926 | +| clip_fraction | 0.317 | +| clip_range | 0.0719 | +| entropy_loss | -7.18 | +| explained_variance | 0.587 | +| learning_rate | 4.7e-05 | +| loss | -0.0292 | +| n_updates | 40112 | +| policy_gradient_loss | -0.0187 | +| value_loss | 9.85e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1421 | +| iterations | 6075 | +| time_elapsed | 8752 | +| total_timesteps | 12441600 | +| train/ | | +| approx_kl | 0.009869093 | +| clip_fraction | 0.303 | +| clip_range | 0.0719 | +| entropy_loss | -7.49 | +| explained_variance | -0.121 | +| learning_rate | 4.7e-05 | +| loss | -0.0301 | +| n_updates | 40116 | +| policy_gradient_loss | -0.0194 | +| value_loss | 9.97e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1421 | +| iterations | 6076 | +| time_elapsed | 8753 | +| total_timesteps | 12443648 | +| train/ | | +| approx_kl | 0.00972339 | +| clip_fraction | 0.302 | +| clip_range | 0.0719 | +| entropy_loss | -7.38 | +| explained_variance | 0.226 | +| learning_rate | 4.7e-05 | +| loss | -0.0318 | +| n_updates | 40120 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.00016 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1421 | +| iterations | 6077 | +| time_elapsed | 8755 | +| total_timesteps | 12445696 | +| train/ | | +| approx_kl | 0.010250925 | +| clip_fraction | 0.304 | +| clip_range | 0.0719 | +| entropy_loss | -7.08 | +| explained_variance | 0.606 | +| learning_rate | 4.7e-05 | +| loss | -0.0286 | +| n_updates | 40124 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.00013 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1421 | +| iterations | 6078 | +| time_elapsed | 8756 | +| total_timesteps | 12447744 | +| train/ | | +| approx_kl | 0.012029728 | +| clip_fraction | 0.312 | +| clip_range | 0.0719 | +| entropy_loss | -7.03 | +| explained_variance | 0.148 | +| learning_rate | 4.7e-05 | +| loss | -0.0277 | +| n_updates | 40128 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000356 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1421 | +| iterations | 6079 | +| time_elapsed | 8758 | +| total_timesteps | 12449792 | +| train/ | | +| approx_kl | 0.0116091855 | +| clip_fraction | 0.332 | +| clip_range | 0.0719 | +| entropy_loss | -7.23 | +| explained_variance | 0.46 | +| learning_rate | 4.7e-05 | +| loss | -0.0304 | +| n_updates | 40132 | +| policy_gradient_loss | -0.0222 | +| value_loss | 8.5e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1421 | +| iterations | 6080 | +| time_elapsed | 8759 | +| total_timesteps | 12451840 | +| train/ | | +| approx_kl | 0.010997249 | +| clip_fraction | 0.313 | +| clip_range | 0.0719 | +| entropy_loss | -7.26 | +| explained_variance | -0.0403 | +| learning_rate | 4.7e-05 | +| loss | -0.0311 | +| n_updates | 40136 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000171 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1421 | +| iterations | 6081 | +| time_elapsed | 8761 | +| total_timesteps | 12453888 | +| train/ | | +| approx_kl | 0.012012716 | +| clip_fraction | 0.323 | +| clip_range | 0.0719 | +| entropy_loss | -7.15 | +| explained_variance | 0.416 | +| learning_rate | 4.7e-05 | +| loss | -0.0358 | +| n_updates | 40140 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.00014 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1421 | +| iterations | 6082 | +| time_elapsed | 8762 | +| total_timesteps | 12455936 | +| train/ | | +| approx_kl | 0.009565765 | +| clip_fraction | 0.304 | +| clip_range | 0.0719 | +| entropy_loss | -7.08 | +| explained_variance | 0.35 | +| learning_rate | 4.7e-05 | +| loss | -0.0298 | +| n_updates | 40144 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000268 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1421 | +| iterations | 6083 | +| time_elapsed | 8763 | +| total_timesteps | 12457984 | +| train/ | | +| approx_kl | 0.009426065 | +| clip_fraction | 0.325 | +| clip_range | 0.0719 | +| entropy_loss | -7.47 | +| explained_variance | -0.193 | +| learning_rate | 4.7e-05 | +| loss | -0.0359 | +| n_updates | 40148 | +| policy_gradient_loss | -0.0226 | +| value_loss | 9.68e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1421 | +| iterations | 6084 | +| time_elapsed | 8765 | +| total_timesteps | 12460032 | +| train/ | | +| approx_kl | 0.009423108 | +| clip_fraction | 0.298 | +| clip_range | 0.0719 | +| entropy_loss | -7.23 | +| explained_variance | 0.0906 | +| learning_rate | 4.7e-05 | +| loss | -0.0326 | +| n_updates | 40152 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000335 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1421 | +| iterations | 6085 | +| time_elapsed | 8766 | +| total_timesteps | 12462080 | +| train/ | | +| approx_kl | 0.00914981 | +| clip_fraction | 0.297 | +| clip_range | 0.0719 | +| entropy_loss | -7.37 | +| explained_variance | 0.103 | +| learning_rate | 4.7e-05 | +| loss | -0.0312 | +| n_updates | 40156 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000156 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1421 | +| iterations | 6086 | +| time_elapsed | 8768 | +| total_timesteps | 12464128 | +| train/ | | +| approx_kl | 0.009819884 | +| clip_fraction | 0.303 | +| clip_range | 0.0719 | +| entropy_loss | -7.08 | +| explained_variance | 0.345 | +| learning_rate | 4.7e-05 | +| loss | -0.0339 | +| n_updates | 40160 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000232 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1421 | +| iterations | 6087 | +| time_elapsed | 8769 | +| total_timesteps | 12466176 | +| train/ | | +| approx_kl | 0.010101093 | +| clip_fraction | 0.316 | +| clip_range | 0.0719 | +| entropy_loss | -7.27 | +| explained_variance | 0.38 | +| learning_rate | 4.7e-05 | +| loss | -0.0311 | +| n_updates | 40164 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000109 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1421 | +| iterations | 6088 | +| time_elapsed | 8771 | +| total_timesteps | 12468224 | +| train/ | | +| approx_kl | 0.010606522 | +| clip_fraction | 0.325 | +| clip_range | 0.0719 | +| entropy_loss | -7.18 | +| explained_variance | 0.694 | +| learning_rate | 4.7e-05 | +| loss | -0.0316 | +| n_updates | 40168 | +| policy_gradient_loss | -0.0218 | +| value_loss | 6.65e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1421 | +| iterations | 6089 | +| time_elapsed | 8772 | +| total_timesteps | 12470272 | +| train/ | | +| approx_kl | 0.012351425 | +| clip_fraction | 0.319 | +| clip_range | 0.0719 | +| entropy_loss | -7.12 | +| explained_variance | 0.747 | +| learning_rate | 4.7e-05 | +| loss | -0.0359 | +| n_updates | 40172 | +| policy_gradient_loss | -0.0212 | +| value_loss | 5.64e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1421 | +| iterations | 6090 | +| time_elapsed | 8774 | +| total_timesteps | 12472320 | +| train/ | | +| approx_kl | 0.011160245 | +| clip_fraction | 0.297 | +| clip_range | 0.0719 | +| entropy_loss | -6.95 | +| explained_variance | 0.719 | +| learning_rate | 4.7e-05 | +| loss | -0.0318 | +| n_updates | 40176 | +| policy_gradient_loss | -0.018 | +| value_loss | 8.92e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1421 | +| iterations | 6091 | +| time_elapsed | 8775 | +| total_timesteps | 12474368 | +| train/ | | +| approx_kl | 0.008989827 | +| clip_fraction | 0.273 | +| clip_range | 0.0719 | +| entropy_loss | -7.09 | +| explained_variance | 0.446 | +| learning_rate | 4.7e-05 | +| loss | -0.0237 | +| n_updates | 40180 | +| policy_gradient_loss | -0.0138 | +| value_loss | 0.000177 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1421 | +| iterations | 6092 | +| time_elapsed | 8777 | +| total_timesteps | 12476416 | +| train/ | | +| approx_kl | 0.010100221 | +| clip_fraction | 0.296 | +| clip_range | 0.0719 | +| entropy_loss | -7.48 | +| explained_variance | -0.0695 | +| learning_rate | 4.7e-05 | +| loss | -0.0277 | +| n_updates | 40184 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.00014 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1421 | +| iterations | 6093 | +| time_elapsed | 8778 | +| total_timesteps | 12478464 | +| train/ | | +| approx_kl | 0.009172602 | +| clip_fraction | 0.291 | +| clip_range | 0.0719 | +| entropy_loss | -7.5 | +| explained_variance | -0.00512 | +| learning_rate | 4.7e-05 | +| loss | -0.0314 | +| n_updates | 40188 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000174 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1421 | +| iterations | 6094 | +| time_elapsed | 8779 | +| total_timesteps | 12480512 | +| train/ | | +| approx_kl | 0.00970378 | +| clip_fraction | 0.288 | +| clip_range | 0.0719 | +| entropy_loss | -6.96 | +| explained_variance | 0.553 | +| learning_rate | 4.7e-05 | +| loss | -0.0291 | +| n_updates | 40192 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000177 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1421 | +| iterations | 6095 | +| time_elapsed | 8781 | +| total_timesteps | 12482560 | +| train/ | | +| approx_kl | 0.012219474 | +| clip_fraction | 0.323 | +| clip_range | 0.0719 | +| entropy_loss | -7.17 | +| explained_variance | 0.467 | +| learning_rate | 4.7e-05 | +| loss | -0.0371 | +| n_updates | 40196 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000133 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1421 | +| iterations | 6096 | +| time_elapsed | 8782 | +| total_timesteps | 12484608 | +| train/ | | +| approx_kl | 0.012046884 | +| clip_fraction | 0.297 | +| clip_range | 0.0719 | +| entropy_loss | -7.4 | +| explained_variance | -0.0129 | +| learning_rate | 4.7e-05 | +| loss | -0.0342 | +| n_updates | 40200 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.00013 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1421 | +| iterations | 6097 | +| time_elapsed | 8784 | +| total_timesteps | 12486656 | +| train/ | | +| approx_kl | 0.010850774 | +| clip_fraction | 0.289 | +| clip_range | 0.0719 | +| entropy_loss | -7.03 | +| explained_variance | 0.396 | +| learning_rate | 4.7e-05 | +| loss | -0.0324 | +| n_updates | 40204 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.00022 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1421 | +| iterations | 6098 | +| time_elapsed | 8785 | +| total_timesteps | 12488704 | +| train/ | | +| approx_kl | 0.009907069 | +| clip_fraction | 0.295 | +| clip_range | 0.0719 | +| entropy_loss | -7.03 | +| explained_variance | 0.465 | +| learning_rate | 4.7e-05 | +| loss | -0.0312 | +| n_updates | 40208 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000213 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1421 | +| iterations | 6099 | +| time_elapsed | 8787 | +| total_timesteps | 12490752 | +| train/ | | +| approx_kl | 0.0101697715 | +| clip_fraction | 0.3 | +| clip_range | 0.0719 | +| entropy_loss | -6.74 | +| explained_variance | 0.534 | +| learning_rate | 4.7e-05 | +| loss | -0.0285 | +| n_updates | 40212 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000259 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1421 | +| iterations | 6100 | +| time_elapsed | 8788 | +| total_timesteps | 12492800 | +| train/ | | +| approx_kl | 0.008360475 | +| clip_fraction | 0.276 | +| clip_range | 0.0719 | +| entropy_loss | -7.51 | +| explained_variance | -0.0292 | +| learning_rate | 4.7e-05 | +| loss | -0.0377 | +| n_updates | 40216 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000132 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1421 | +| iterations | 6101 | +| time_elapsed | 8789 | +| total_timesteps | 12494848 | +| train/ | | +| approx_kl | 0.010785404 | +| clip_fraction | 0.31 | +| clip_range | 0.0719 | +| entropy_loss | -7.23 | +| explained_variance | -0.172 | +| learning_rate | 4.7e-05 | +| loss | -0.0304 | +| n_updates | 40220 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.00015 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1421 | +| iterations | 6102 | +| time_elapsed | 8791 | +| total_timesteps | 12496896 | +| train/ | | +| approx_kl | 0.011370298 | +| clip_fraction | 0.297 | +| clip_range | 0.0719 | +| entropy_loss | -7.07 | +| explained_variance | 0.336 | +| learning_rate | 4.7e-05 | +| loss | -0.0204 | +| n_updates | 40224 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000225 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1421 | +| iterations | 6103 | +| time_elapsed | 8792 | +| total_timesteps | 12498944 | +| train/ | | +| approx_kl | 0.012441709 | +| clip_fraction | 0.327 | +| clip_range | 0.0719 | +| entropy_loss | -7.15 | +| explained_variance | 0.433 | +| learning_rate | 4.7e-05 | +| loss | -0.0336 | +| n_updates | 40228 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000162 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1421 | +| iterations | 6104 | +| time_elapsed | 8794 | +| total_timesteps | 12500992 | +| train/ | | +| approx_kl | 0.011724416 | +| clip_fraction | 0.34 | +| clip_range | 0.0719 | +| entropy_loss | -7.43 | +| explained_variance | -0.0922 | +| learning_rate | 4.7e-05 | +| loss | -0.0334 | +| n_updates | 40232 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000174 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1421 | +| iterations | 6105 | +| time_elapsed | 8795 | +| total_timesteps | 12503040 | +| train/ | | +| approx_kl | 0.011890888 | +| clip_fraction | 0.304 | +| clip_range | 0.0719 | +| entropy_loss | -7.34 | +| explained_variance | 0.284 | +| learning_rate | 4.7e-05 | +| loss | -0.0292 | +| n_updates | 40236 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000172 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1421 | +| iterations | 6106 | +| time_elapsed | 8797 | +| total_timesteps | 12505088 | +| train/ | | +| approx_kl | 0.010700434 | +| clip_fraction | 0.344 | +| clip_range | 0.0719 | +| entropy_loss | -6.93 | +| explained_variance | 0.778 | +| learning_rate | 4.7e-05 | +| loss | -0.0438 | +| n_updates | 40240 | +| policy_gradient_loss | -0.0239 | +| value_loss | 5.25e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1421 | +| iterations | 6107 | +| time_elapsed | 8798 | +| total_timesteps | 12507136 | +| train/ | | +| approx_kl | 0.01147775 | +| clip_fraction | 0.288 | +| clip_range | 0.0719 | +| entropy_loss | -7.31 | +| explained_variance | 0.342 | +| learning_rate | 4.7e-05 | +| loss | -0.0289 | +| n_updates | 40244 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000149 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1421 | +| iterations | 6108 | +| time_elapsed | 8799 | +| total_timesteps | 12509184 | +| train/ | | +| approx_kl | 0.01264153 | +| clip_fraction | 0.322 | +| clip_range | 0.0719 | +| entropy_loss | -7.19 | +| explained_variance | 0.417 | +| learning_rate | 4.7e-05 | +| loss | -0.0302 | +| n_updates | 40248 | +| policy_gradient_loss | -0.0206 | +| value_loss | 8.54e-05 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1421 | +| iterations | 6109 | +| time_elapsed | 8801 | +| total_timesteps | 12511232 | +| train/ | | +| approx_kl | 0.01059268 | +| clip_fraction | 0.306 | +| clip_range | 0.0719 | +| entropy_loss | -7.35 | +| explained_variance | 0.375 | +| learning_rate | 4.7e-05 | +| loss | -0.0314 | +| n_updates | 40252 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000113 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1421 | +| iterations | 6110 | +| time_elapsed | 8802 | +| total_timesteps | 12513280 | +| train/ | | +| approx_kl | 0.011866359 | +| clip_fraction | 0.306 | +| clip_range | 0.0719 | +| entropy_loss | -7.26 | +| explained_variance | 0.0563 | +| learning_rate | 4.7e-05 | +| loss | -0.0325 | +| n_updates | 40256 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000302 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1421 | +| iterations | 6111 | +| time_elapsed | 8804 | +| total_timesteps | 12515328 | +| train/ | | +| approx_kl | 0.0115302 | +| clip_fraction | 0.315 | +| clip_range | 0.0719 | +| entropy_loss | -6.71 | +| explained_variance | 0.738 | +| learning_rate | 4.7e-05 | +| loss | -0.0325 | +| n_updates | 40260 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000113 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1421 | +| iterations | 6112 | +| time_elapsed | 8805 | +| total_timesteps | 12517376 | +| train/ | | +| approx_kl | 0.011219369 | +| clip_fraction | 0.315 | +| clip_range | 0.0719 | +| entropy_loss | -7.33 | +| explained_variance | 0.365 | +| learning_rate | 4.7e-05 | +| loss | -0.0316 | +| n_updates | 40264 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000103 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1421 | +| iterations | 6113 | +| time_elapsed | 8807 | +| total_timesteps | 12519424 | +| train/ | | +| approx_kl | 0.010889027 | +| clip_fraction | 0.312 | +| clip_range | 0.0719 | +| entropy_loss | -7.1 | +| explained_variance | 0.277 | +| learning_rate | 4.7e-05 | +| loss | -0.0243 | +| n_updates | 40268 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000375 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1421 | +| iterations | 6114 | +| time_elapsed | 8808 | +| total_timesteps | 12521472 | +| train/ | | +| approx_kl | 0.013291322 | +| clip_fraction | 0.303 | +| clip_range | 0.0719 | +| entropy_loss | -6.91 | +| explained_variance | 0.683 | +| learning_rate | 4.7e-05 | +| loss | -0.0284 | +| n_updates | 40272 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1421 | +| iterations | 6115 | +| time_elapsed | 8810 | +| total_timesteps | 12523520 | +| train/ | | +| approx_kl | 0.010423515 | +| clip_fraction | 0.285 | +| clip_range | 0.0719 | +| entropy_loss | -7.36 | +| explained_variance | -0.0632 | +| learning_rate | 4.7e-05 | +| loss | -0.0288 | +| n_updates | 40276 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000156 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1421 | +| iterations | 6116 | +| time_elapsed | 8811 | +| total_timesteps | 12525568 | +| train/ | | +| approx_kl | 0.009880429 | +| clip_fraction | 0.292 | +| clip_range | 0.0719 | +| entropy_loss | -7.2 | +| explained_variance | 0.3 | +| learning_rate | 4.7e-05 | +| loss | -0.0271 | +| n_updates | 40280 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000206 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1421 | +| iterations | 6117 | +| time_elapsed | 8812 | +| total_timesteps | 12527616 | +| train/ | | +| approx_kl | 0.010262494 | +| clip_fraction | 0.306 | +| clip_range | 0.0719 | +| entropy_loss | -7.42 | +| explained_variance | -0.12 | +| learning_rate | 4.7e-05 | +| loss | -0.0323 | +| n_updates | 40284 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000132 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1421 | +| iterations | 6118 | +| time_elapsed | 8814 | +| total_timesteps | 12529664 | +| train/ | | +| approx_kl | 0.011727578 | +| clip_fraction | 0.309 | +| clip_range | 0.0719 | +| entropy_loss | -7.3 | +| explained_variance | 0.303 | +| learning_rate | 4.7e-05 | +| loss | -0.0325 | +| n_updates | 40288 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000145 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1421 | +| iterations | 6119 | +| time_elapsed | 8815 | +| total_timesteps | 12531712 | +| train/ | | +| approx_kl | 0.010862659 | +| clip_fraction | 0.324 | +| clip_range | 0.0719 | +| entropy_loss | -6.94 | +| explained_variance | 0.668 | +| learning_rate | 4.7e-05 | +| loss | -0.0311 | +| n_updates | 40292 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000115 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1421 | +| iterations | 6120 | +| time_elapsed | 8817 | +| total_timesteps | 12533760 | +| train/ | | +| approx_kl | 0.010758166 | +| clip_fraction | 0.311 | +| clip_range | 0.0719 | +| entropy_loss | -7.45 | +| explained_variance | -0.0517 | +| learning_rate | 4.7e-05 | +| loss | -0.031 | +| n_updates | 40296 | +| policy_gradient_loss | -0.0192 | +| value_loss | 8.52e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1421 | +| iterations | 6121 | +| time_elapsed | 8818 | +| total_timesteps | 12535808 | +| train/ | | +| approx_kl | 0.008206025 | +| clip_fraction | 0.288 | +| clip_range | 0.0719 | +| entropy_loss | -7.19 | +| explained_variance | 0.301 | +| learning_rate | 4.7e-05 | +| loss | -0.0277 | +| n_updates | 40300 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000306 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1421 | +| iterations | 6122 | +| time_elapsed | 8820 | +| total_timesteps | 12537856 | +| train/ | | +| approx_kl | 0.009661054 | +| clip_fraction | 0.295 | +| clip_range | 0.0719 | +| entropy_loss | -6.72 | +| explained_variance | 0.663 | +| learning_rate | 4.7e-05 | +| loss | -0.0337 | +| n_updates | 40304 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000157 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1421 | +| iterations | 6123 | +| time_elapsed | 8821 | +| total_timesteps | 12539904 | +| train/ | | +| approx_kl | 0.012042834 | +| clip_fraction | 0.31 | +| clip_range | 0.0719 | +| entropy_loss | -7.25 | +| explained_variance | 0.321 | +| learning_rate | 4.7e-05 | +| loss | -0.0277 | +| n_updates | 40308 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.00011 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1421 | +| iterations | 6124 | +| time_elapsed | 8822 | +| total_timesteps | 12541952 | +| train/ | | +| approx_kl | 0.010348883 | +| clip_fraction | 0.316 | +| clip_range | 0.0719 | +| entropy_loss | -7.49 | +| explained_variance | -0.142 | +| learning_rate | 4.7e-05 | +| loss | -0.0296 | +| n_updates | 40312 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000145 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1421 | +| iterations | 6125 | +| time_elapsed | 8824 | +| total_timesteps | 12544000 | +| train/ | | +| approx_kl | 0.01040439 | +| clip_fraction | 0.29 | +| clip_range | 0.0719 | +| entropy_loss | -7.14 | +| explained_variance | 0.241 | +| learning_rate | 4.7e-05 | +| loss | -0.0247 | +| n_updates | 40316 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.00024 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1421 | +| iterations | 6126 | +| time_elapsed | 8825 | +| total_timesteps | 12546048 | +| train/ | | +| approx_kl | 0.010447944 | +| clip_fraction | 0.308 | +| clip_range | 0.0719 | +| entropy_loss | -7.44 | +| explained_variance | 0.254 | +| learning_rate | 4.7e-05 | +| loss | -0.0328 | +| n_updates | 40320 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000114 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1421 | +| iterations | 6127 | +| time_elapsed | 8827 | +| total_timesteps | 12548096 | +| train/ | | +| approx_kl | 0.009322286 | +| clip_fraction | 0.295 | +| clip_range | 0.0719 | +| entropy_loss | -7.1 | +| explained_variance | 0.398 | +| learning_rate | 4.7e-05 | +| loss | -0.0324 | +| n_updates | 40324 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000207 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1421 | +| iterations | 6128 | +| time_elapsed | 8828 | +| total_timesteps | 12550144 | +| train/ | | +| approx_kl | 0.0078074317 | +| clip_fraction | 0.301 | +| clip_range | 0.0719 | +| entropy_loss | -7.42 | +| explained_variance | -0.0545 | +| learning_rate | 4.7e-05 | +| loss | -0.0249 | +| n_updates | 40328 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000235 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1421 | +| iterations | 6129 | +| time_elapsed | 8830 | +| total_timesteps | 12552192 | +| train/ | | +| approx_kl | 0.00857494 | +| clip_fraction | 0.305 | +| clip_range | 0.0719 | +| entropy_loss | -6.77 | +| explained_variance | 0.623 | +| learning_rate | 4.7e-05 | +| loss | -0.0365 | +| n_updates | 40332 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000156 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1421 | +| iterations | 6130 | +| time_elapsed | 8831 | +| total_timesteps | 12554240 | +| train/ | | +| approx_kl | 0.008569583 | +| clip_fraction | 0.297 | +| clip_range | 0.0719 | +| entropy_loss | -7.11 | +| explained_variance | 0.278 | +| learning_rate | 4.7e-05 | +| loss | -0.0254 | +| n_updates | 40336 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000217 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1421 | +| iterations | 6131 | +| time_elapsed | 8832 | +| total_timesteps | 12556288 | +| train/ | | +| approx_kl | 0.008055235 | +| clip_fraction | 0.274 | +| clip_range | 0.0719 | +| entropy_loss | -7.27 | +| explained_variance | 0.423 | +| learning_rate | 4.7e-05 | +| loss | -0.0277 | +| n_updates | 40340 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000198 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1421 | +| iterations | 6132 | +| time_elapsed | 8834 | +| total_timesteps | 12558336 | +| train/ | | +| approx_kl | 0.010809318 | +| clip_fraction | 0.343 | +| clip_range | 0.0719 | +| entropy_loss | -6.74 | +| explained_variance | 0.703 | +| learning_rate | 4.7e-05 | +| loss | -0.0295 | +| n_updates | 40344 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000112 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1421 | +| iterations | 6133 | +| time_elapsed | 8835 | +| total_timesteps | 12560384 | +| train/ | | +| approx_kl | 0.012287276 | +| clip_fraction | 0.34 | +| clip_range | 0.0719 | +| entropy_loss | -7.39 | +| explained_variance | -0.0566 | +| learning_rate | 4.7e-05 | +| loss | -0.0355 | +| n_updates | 40348 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000148 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1421 | +| iterations | 6134 | +| time_elapsed | 8837 | +| total_timesteps | 12562432 | +| train/ | | +| approx_kl | 0.011587506 | +| clip_fraction | 0.354 | +| clip_range | 0.0719 | +| entropy_loss | -7.19 | +| explained_variance | 0.474 | +| learning_rate | 4.7e-05 | +| loss | -0.0385 | +| n_updates | 40352 | +| policy_gradient_loss | -0.023 | +| value_loss | 8.42e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1421 | +| iterations | 6135 | +| time_elapsed | 8838 | +| total_timesteps | 12564480 | +| train/ | | +| approx_kl | 0.00985164 | +| clip_fraction | 0.319 | +| clip_range | 0.0719 | +| entropy_loss | -7.35 | +| explained_variance | 0.166 | +| learning_rate | 4.7e-05 | +| loss | -0.0316 | +| n_updates | 40356 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000264 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1421 | +| iterations | 6136 | +| time_elapsed | 8840 | +| total_timesteps | 12566528 | +| train/ | | +| approx_kl | 0.009248674 | +| clip_fraction | 0.297 | +| clip_range | 0.0719 | +| entropy_loss | -7.07 | +| explained_variance | 0.258 | +| learning_rate | 4.7e-05 | +| loss | -0.0229 | +| n_updates | 40360 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000327 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1421 | +| iterations | 6137 | +| time_elapsed | 8841 | +| total_timesteps | 12568576 | +| train/ | | +| approx_kl | 0.011327066 | +| clip_fraction | 0.348 | +| clip_range | 0.0719 | +| entropy_loss | -6.98 | +| explained_variance | 0.297 | +| learning_rate | 4.7e-05 | +| loss | -0.0408 | +| n_updates | 40364 | +| policy_gradient_loss | -0.0246 | +| value_loss | 0.000105 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1421 | +| iterations | 6138 | +| time_elapsed | 8843 | +| total_timesteps | 12570624 | +| train/ | | +| approx_kl | 0.012846294 | +| clip_fraction | 0.335 | +| clip_range | 0.0719 | +| entropy_loss | -6.99 | +| explained_variance | 0.472 | +| learning_rate | 4.7e-05 | +| loss | -0.0295 | +| n_updates | 40368 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000157 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1421 | +| iterations | 6139 | +| time_elapsed | 8844 | +| total_timesteps | 12572672 | +| train/ | | +| approx_kl | 0.011665512 | +| clip_fraction | 0.361 | +| clip_range | 0.0719 | +| entropy_loss | -7.36 | +| explained_variance | -0.225 | +| learning_rate | 4.7e-05 | +| loss | -0.0334 | +| n_updates | 40372 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.00016 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1421 | +| iterations | 6140 | +| time_elapsed | 8845 | +| total_timesteps | 12574720 | +| train/ | | +| approx_kl | 0.011030368 | +| clip_fraction | 0.337 | +| clip_range | 0.0719 | +| entropy_loss | -7.31 | +| explained_variance | 0.0189 | +| learning_rate | 4.7e-05 | +| loss | -0.0346 | +| n_updates | 40376 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000122 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1421 | +| iterations | 6141 | +| time_elapsed | 8847 | +| total_timesteps | 12576768 | +| train/ | | +| approx_kl | 0.010288873 | +| clip_fraction | 0.282 | +| clip_range | 0.0719 | +| entropy_loss | -6.95 | +| explained_variance | 0.382 | +| learning_rate | 4.7e-05 | +| loss | -0.0316 | +| n_updates | 40380 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000228 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1421 | +| iterations | 6142 | +| time_elapsed | 8848 | +| total_timesteps | 12578816 | +| train/ | | +| approx_kl | 0.011032717 | +| clip_fraction | 0.344 | +| clip_range | 0.0719 | +| entropy_loss | -7.11 | +| explained_variance | 0.504 | +| learning_rate | 4.7e-05 | +| loss | -0.0381 | +| n_updates | 40384 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000137 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1421 | +| iterations | 6143 | +| time_elapsed | 8850 | +| total_timesteps | 12580864 | +| train/ | | +| approx_kl | 0.010118706 | +| clip_fraction | 0.293 | +| clip_range | 0.0719 | +| entropy_loss | -7.07 | +| explained_variance | 0.35 | +| learning_rate | 4.7e-05 | +| loss | -0.029 | +| n_updates | 40388 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000184 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1421 | +| iterations | 6144 | +| time_elapsed | 8851 | +| total_timesteps | 12582912 | +| train/ | | +| approx_kl | 0.012226551 | +| clip_fraction | 0.341 | +| clip_range | 0.0719 | +| entropy_loss | -7.15 | +| explained_variance | 0.553 | +| learning_rate | 4.7e-05 | +| loss | -0.0375 | +| n_updates | 40392 | +| policy_gradient_loss | -0.0223 | +| value_loss | 9.78e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1421 | +| iterations | 6145 | +| time_elapsed | 8852 | +| total_timesteps | 12584960 | +| train/ | | +| approx_kl | 0.009850516 | +| clip_fraction | 0.307 | +| clip_range | 0.0719 | +| entropy_loss | -7.4 | +| explained_variance | 0.173 | +| learning_rate | 4.7e-05 | +| loss | -0.0342 | +| n_updates | 40396 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000118 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1421 | +| iterations | 6146 | +| time_elapsed | 8854 | +| total_timesteps | 12587008 | +| train/ | | +| approx_kl | 0.011008066 | +| clip_fraction | 0.31 | +| clip_range | 0.0719 | +| entropy_loss | -7.29 | +| explained_variance | 0.22 | +| learning_rate | 4.7e-05 | +| loss | -0.0329 | +| n_updates | 40400 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000198 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1421 | +| iterations | 6147 | +| time_elapsed | 8855 | +| total_timesteps | 12589056 | +| train/ | | +| approx_kl | 0.011670366 | +| clip_fraction | 0.339 | +| clip_range | 0.0719 | +| entropy_loss | -7.02 | +| explained_variance | 0.529 | +| learning_rate | 4.7e-05 | +| loss | -0.0388 | +| n_updates | 40404 | +| policy_gradient_loss | -0.0227 | +| value_loss | 0.000103 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1421 | +| iterations | 6148 | +| time_elapsed | 8857 | +| total_timesteps | 12591104 | +| train/ | | +| approx_kl | 0.009019509 | +| clip_fraction | 0.302 | +| clip_range | 0.0719 | +| entropy_loss | -6.76 | +| explained_variance | 0.459 | +| learning_rate | 4.7e-05 | +| loss | -0.029 | +| n_updates | 40408 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000284 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1421 | +| iterations | 6149 | +| time_elapsed | 8858 | +| total_timesteps | 12593152 | +| train/ | | +| approx_kl | 0.010565206 | +| clip_fraction | 0.329 | +| clip_range | 0.0719 | +| entropy_loss | -7.15 | +| explained_variance | 0.588 | +| learning_rate | 4.7e-05 | +| loss | -0.0308 | +| n_updates | 40412 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000134 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1421 | +| iterations | 6150 | +| time_elapsed | 8860 | +| total_timesteps | 12595200 | +| train/ | | +| approx_kl | 0.0098928455 | +| clip_fraction | 0.288 | +| clip_range | 0.0719 | +| entropy_loss | -7.29 | +| explained_variance | 0.0202 | +| learning_rate | 4.7e-05 | +| loss | -0.0269 | +| n_updates | 40416 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000283 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1421 | +| iterations | 6151 | +| time_elapsed | 8861 | +| total_timesteps | 12597248 | +| train/ | | +| approx_kl | 0.010071129 | +| clip_fraction | 0.287 | +| clip_range | 0.0719 | +| entropy_loss | -7.23 | +| explained_variance | 0.332 | +| learning_rate | 4.7e-05 | +| loss | -0.0302 | +| n_updates | 40420 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000216 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1421 | +| iterations | 6152 | +| time_elapsed | 8863 | +| total_timesteps | 12599296 | +| train/ | | +| approx_kl | 0.0109043345 | +| clip_fraction | 0.333 | +| clip_range | 0.0719 | +| entropy_loss | -7.49 | +| explained_variance | -0.347 | +| learning_rate | 4.7e-05 | +| loss | -0.0395 | +| n_updates | 40424 | +| policy_gradient_loss | -0.0223 | +| value_loss | 9.27e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1421 | +| iterations | 6153 | +| time_elapsed | 8864 | +| total_timesteps | 12601344 | +| train/ | | +| approx_kl | 0.012059629 | +| clip_fraction | 0.345 | +| clip_range | 0.0719 | +| entropy_loss | -7.26 | +| explained_variance | 0.235 | +| learning_rate | 4.7e-05 | +| loss | -0.0335 | +| n_updates | 40428 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000155 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1421 | +| iterations | 6154 | +| time_elapsed | 8865 | +| total_timesteps | 12603392 | +| train/ | | +| approx_kl | 0.010148739 | +| clip_fraction | 0.28 | +| clip_range | 0.0718 | +| entropy_loss | -7.12 | +| explained_variance | 0.263 | +| learning_rate | 4.7e-05 | +| loss | -0.0283 | +| n_updates | 40432 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000187 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1421 | +| iterations | 6155 | +| time_elapsed | 8867 | +| total_timesteps | 12605440 | +| train/ | | +| approx_kl | 0.010557484 | +| clip_fraction | 0.299 | +| clip_range | 0.0718 | +| entropy_loss | -7.25 | +| explained_variance | 0.14 | +| learning_rate | 4.7e-05 | +| loss | -0.0232 | +| n_updates | 40436 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.00022 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1421 | +| iterations | 6156 | +| time_elapsed | 8868 | +| total_timesteps | 12607488 | +| train/ | | +| approx_kl | 0.012291307 | +| clip_fraction | 0.342 | +| clip_range | 0.0718 | +| entropy_loss | -7.38 | +| explained_variance | -0.387 | +| learning_rate | 4.7e-05 | +| loss | -0.0361 | +| n_updates | 40440 | +| policy_gradient_loss | -0.0239 | +| value_loss | 8.16e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1421 | +| iterations | 6157 | +| time_elapsed | 8870 | +| total_timesteps | 12609536 | +| train/ | | +| approx_kl | 0.009394575 | +| clip_fraction | 0.305 | +| clip_range | 0.0718 | +| entropy_loss | -6.82 | +| explained_variance | 0.513 | +| learning_rate | 4.7e-05 | +| loss | -0.0327 | +| n_updates | 40444 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000162 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1421 | +| iterations | 6158 | +| time_elapsed | 8871 | +| total_timesteps | 12611584 | +| train/ | | +| approx_kl | 0.009111013 | +| clip_fraction | 0.321 | +| clip_range | 0.0718 | +| entropy_loss | -7.25 | +| explained_variance | 0.372 | +| learning_rate | 4.7e-05 | +| loss | -0.0332 | +| n_updates | 40448 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000116 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1421 | +| iterations | 6159 | +| time_elapsed | 8873 | +| total_timesteps | 12613632 | +| train/ | | +| approx_kl | 0.0104962485 | +| clip_fraction | 0.319 | +| clip_range | 0.0718 | +| entropy_loss | -7.51 | +| explained_variance | -0.0516 | +| learning_rate | 4.7e-05 | +| loss | -0.0336 | +| n_updates | 40452 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000153 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1421 | +| iterations | 6160 | +| time_elapsed | 8874 | +| total_timesteps | 12615680 | +| train/ | | +| approx_kl | 0.009329252 | +| clip_fraction | 0.299 | +| clip_range | 0.0718 | +| entropy_loss | -7.21 | +| explained_variance | 0.587 | +| learning_rate | 4.7e-05 | +| loss | -0.0336 | +| n_updates | 40456 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000108 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1421 | +| iterations | 6161 | +| time_elapsed | 8876 | +| total_timesteps | 12617728 | +| train/ | | +| approx_kl | 0.0076933606 | +| clip_fraction | 0.267 | +| clip_range | 0.0718 | +| entropy_loss | -7.1 | +| explained_variance | 0.289 | +| learning_rate | 4.7e-05 | +| loss | -0.0244 | +| n_updates | 40460 | +| policy_gradient_loss | -0.0133 | +| value_loss | 0.000405 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1421 | +| iterations | 6162 | +| time_elapsed | 8877 | +| total_timesteps | 12619776 | +| train/ | | +| approx_kl | 0.009642372 | +| clip_fraction | 0.318 | +| clip_range | 0.0718 | +| entropy_loss | -7.19 | +| explained_variance | 0.485 | +| learning_rate | 4.7e-05 | +| loss | -0.0373 | +| n_updates | 40464 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000158 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1421 | +| iterations | 6163 | +| time_elapsed | 8879 | +| total_timesteps | 12621824 | +| train/ | | +| approx_kl | 0.0108534815 | +| clip_fraction | 0.288 | +| clip_range | 0.0718 | +| entropy_loss | -7.37 | +| explained_variance | 0.24 | +| learning_rate | 4.7e-05 | +| loss | -0.0285 | +| n_updates | 40468 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.00022 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1421 | +| iterations | 6164 | +| time_elapsed | 8880 | +| total_timesteps | 12623872 | +| train/ | | +| approx_kl | 0.009668723 | +| clip_fraction | 0.317 | +| clip_range | 0.0718 | +| entropy_loss | -6.97 | +| explained_variance | 0.665 | +| learning_rate | 4.7e-05 | +| loss | -0.0325 | +| n_updates | 40472 | +| policy_gradient_loss | -0.0196 | +| value_loss | 9.97e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1421 | +| iterations | 6165 | +| time_elapsed | 8882 | +| total_timesteps | 12625920 | +| train/ | | +| approx_kl | 0.008225793 | +| clip_fraction | 0.288 | +| clip_range | 0.0718 | +| entropy_loss | -7.08 | +| explained_variance | 0.43 | +| learning_rate | 4.7e-05 | +| loss | -0.0315 | +| n_updates | 40476 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000187 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1421 | +| iterations | 6166 | +| time_elapsed | 8883 | +| total_timesteps | 12627968 | +| train/ | | +| approx_kl | 0.008506746 | +| clip_fraction | 0.287 | +| clip_range | 0.0718 | +| entropy_loss | -7.2 | +| explained_variance | 0.36 | +| learning_rate | 4.7e-05 | +| loss | -0.0291 | +| n_updates | 40480 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.00021 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1421 | +| iterations | 6167 | +| time_elapsed | 8884 | +| total_timesteps | 12630016 | +| train/ | | +| approx_kl | 0.0088931015 | +| clip_fraction | 0.327 | +| clip_range | 0.0718 | +| entropy_loss | -7.59 | +| explained_variance | -0.423 | +| learning_rate | 4.7e-05 | +| loss | -0.0364 | +| n_updates | 40484 | +| policy_gradient_loss | -0.023 | +| value_loss | 9.56e-05 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1421 | +| iterations | 6168 | +| time_elapsed | 8886 | +| total_timesteps | 12632064 | +| train/ | | +| approx_kl | 0.01144197 | +| clip_fraction | 0.326 | +| clip_range | 0.0718 | +| entropy_loss | -7.12 | +| explained_variance | 0.296 | +| learning_rate | 4.7e-05 | +| loss | -0.0334 | +| n_updates | 40488 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000271 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1421 | +| iterations | 6169 | +| time_elapsed | 8887 | +| total_timesteps | 12634112 | +| train/ | | +| approx_kl | 0.011346221 | +| clip_fraction | 0.352 | +| clip_range | 0.0718 | +| entropy_loss | -7.48 | +| explained_variance | -0.23 | +| learning_rate | 4.7e-05 | +| loss | -0.0444 | +| n_updates | 40492 | +| policy_gradient_loss | -0.0252 | +| value_loss | 4.97e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1421 | +| iterations | 6170 | +| time_elapsed | 8889 | +| total_timesteps | 12636160 | +| train/ | | +| approx_kl | 0.011749199 | +| clip_fraction | 0.303 | +| clip_range | 0.0718 | +| entropy_loss | -7.06 | +| explained_variance | 0.369 | +| learning_rate | 4.7e-05 | +| loss | -0.0337 | +| n_updates | 40496 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000148 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1421 | +| iterations | 6171 | +| time_elapsed | 8890 | +| total_timesteps | 12638208 | +| train/ | | +| approx_kl | 0.010628646 | +| clip_fraction | 0.33 | +| clip_range | 0.0718 | +| entropy_loss | -6.92 | +| explained_variance | 0.386 | +| learning_rate | 4.7e-05 | +| loss | -0.0343 | +| n_updates | 40500 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000211 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1421 | +| iterations | 6172 | +| time_elapsed | 8892 | +| total_timesteps | 12640256 | +| train/ | | +| approx_kl | 0.0118555175 | +| clip_fraction | 0.295 | +| clip_range | 0.0718 | +| entropy_loss | -6.93 | +| explained_variance | 0.461 | +| learning_rate | 4.7e-05 | +| loss | -0.027 | +| n_updates | 40504 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000237 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1421 | +| iterations | 6173 | +| time_elapsed | 8893 | +| total_timesteps | 12642304 | +| train/ | | +| approx_kl | 0.00978258 | +| clip_fraction | 0.294 | +| clip_range | 0.0718 | +| entropy_loss | -7.32 | +| explained_variance | 0.286 | +| learning_rate | 4.7e-05 | +| loss | -0.0308 | +| n_updates | 40508 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000156 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1421 | +| iterations | 6174 | +| time_elapsed | 8894 | +| total_timesteps | 12644352 | +| train/ | | +| approx_kl | 0.0082310345 | +| clip_fraction | 0.294 | +| clip_range | 0.0718 | +| entropy_loss | -7.37 | +| explained_variance | -0.0156 | +| learning_rate | 4.7e-05 | +| loss | -0.0268 | +| n_updates | 40512 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000265 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1421 | +| iterations | 6175 | +| time_elapsed | 8896 | +| total_timesteps | 12646400 | +| train/ | | +| approx_kl | 0.008637496 | +| clip_fraction | 0.312 | +| clip_range | 0.0718 | +| entropy_loss | -6.85 | +| explained_variance | 0.599 | +| learning_rate | 4.7e-05 | +| loss | -0.0299 | +| n_updates | 40516 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000165 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1421 | +| iterations | 6176 | +| time_elapsed | 8897 | +| total_timesteps | 12648448 | +| train/ | | +| approx_kl | 0.011083244 | +| clip_fraction | 0.326 | +| clip_range | 0.0718 | +| entropy_loss | -7.11 | +| explained_variance | 0.586 | +| learning_rate | 4.7e-05 | +| loss | -0.031 | +| n_updates | 40520 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000129 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1421 | +| iterations | 6177 | +| time_elapsed | 8899 | +| total_timesteps | 12650496 | +| train/ | | +| approx_kl | 0.011007645 | +| clip_fraction | 0.297 | +| clip_range | 0.0718 | +| entropy_loss | -7.34 | +| explained_variance | -0.131 | +| learning_rate | 4.7e-05 | +| loss | -0.0343 | +| n_updates | 40524 | +| policy_gradient_loss | -0.0194 | +| value_loss | 8.44e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1421 | +| iterations | 6178 | +| time_elapsed | 8900 | +| total_timesteps | 12652544 | +| train/ | | +| approx_kl | 0.012088794 | +| clip_fraction | 0.297 | +| clip_range | 0.0718 | +| entropy_loss | -7.31 | +| explained_variance | -0.0333 | +| learning_rate | 4.7e-05 | +| loss | -0.0284 | +| n_updates | 40528 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000265 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1421 | +| iterations | 6179 | +| time_elapsed | 8902 | +| total_timesteps | 12654592 | +| train/ | | +| approx_kl | 0.010959747 | +| clip_fraction | 0.32 | +| clip_range | 0.0718 | +| entropy_loss | -7.39 | +| explained_variance | 0.254 | +| learning_rate | 4.7e-05 | +| loss | -0.0347 | +| n_updates | 40532 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000134 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1421 | +| iterations | 6180 | +| time_elapsed | 8903 | +| total_timesteps | 12656640 | +| train/ | | +| approx_kl | 0.008932991 | +| clip_fraction | 0.299 | +| clip_range | 0.0718 | +| entropy_loss | -6.85 | +| explained_variance | 0.365 | +| learning_rate | 4.7e-05 | +| loss | -0.0305 | +| n_updates | 40536 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000254 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1421 | +| iterations | 6181 | +| time_elapsed | 8905 | +| total_timesteps | 12658688 | +| train/ | | +| approx_kl | 0.012961804 | +| clip_fraction | 0.353 | +| clip_range | 0.0718 | +| entropy_loss | -7.17 | +| explained_variance | 0.173 | +| learning_rate | 4.7e-05 | +| loss | -0.0302 | +| n_updates | 40540 | +| policy_gradient_loss | -0.0219 | +| value_loss | 0.000133 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1421 | +| iterations | 6182 | +| time_elapsed | 8906 | +| total_timesteps | 12660736 | +| train/ | | +| approx_kl | 0.012330331 | +| clip_fraction | 0.312 | +| clip_range | 0.0718 | +| entropy_loss | -7.15 | +| explained_variance | 0.535 | +| learning_rate | 4.7e-05 | +| loss | -0.031 | +| n_updates | 40544 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000121 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1421 | +| iterations | 6183 | +| time_elapsed | 8907 | +| total_timesteps | 12662784 | +| train/ | | +| approx_kl | 0.011134841 | +| clip_fraction | 0.316 | +| clip_range | 0.0718 | +| entropy_loss | -7.31 | +| explained_variance | 0.157 | +| learning_rate | 4.7e-05 | +| loss | -0.0341 | +| n_updates | 40548 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000144 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1421 | +| iterations | 6184 | +| time_elapsed | 8909 | +| total_timesteps | 12664832 | +| train/ | | +| approx_kl | 0.010914374 | +| clip_fraction | 0.352 | +| clip_range | 0.0718 | +| entropy_loss | -7.1 | +| explained_variance | 0.591 | +| learning_rate | 4.7e-05 | +| loss | -0.0428 | +| n_updates | 40552 | +| policy_gradient_loss | -0.0244 | +| value_loss | 6.82e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1421 | +| iterations | 6185 | +| time_elapsed | 8910 | +| total_timesteps | 12666880 | +| train/ | | +| approx_kl | 0.009636847 | +| clip_fraction | 0.311 | +| clip_range | 0.0718 | +| entropy_loss | -7.35 | +| explained_variance | -0.0959 | +| learning_rate | 4.7e-05 | +| loss | -0.02 | +| n_updates | 40556 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000162 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1421 | +| iterations | 6186 | +| time_elapsed | 8912 | +| total_timesteps | 12668928 | +| train/ | | +| approx_kl | 0.009236091 | +| clip_fraction | 0.285 | +| clip_range | 0.0718 | +| entropy_loss | -7.06 | +| explained_variance | 0.526 | +| learning_rate | 4.7e-05 | +| loss | -0.0279 | +| n_updates | 40560 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000174 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1421 | +| iterations | 6187 | +| time_elapsed | 8913 | +| total_timesteps | 12670976 | +| train/ | | +| approx_kl | 0.010686902 | +| clip_fraction | 0.331 | +| clip_range | 0.0718 | +| entropy_loss | -7.46 | +| explained_variance | -0.0416 | +| learning_rate | 4.7e-05 | +| loss | -0.0358 | +| n_updates | 40564 | +| policy_gradient_loss | -0.0218 | +| value_loss | 8.63e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1421 | +| iterations | 6188 | +| time_elapsed | 8915 | +| total_timesteps | 12673024 | +| train/ | | +| approx_kl | 0.010410186 | +| clip_fraction | 0.295 | +| clip_range | 0.0718 | +| entropy_loss | -7.15 | +| explained_variance | 0.179 | +| learning_rate | 4.7e-05 | +| loss | -0.0291 | +| n_updates | 40568 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000284 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1421 | +| iterations | 6189 | +| time_elapsed | 8916 | +| total_timesteps | 12675072 | +| train/ | | +| approx_kl | 0.014726807 | +| clip_fraction | 0.321 | +| clip_range | 0.0718 | +| entropy_loss | -6.87 | +| explained_variance | 0.607 | +| learning_rate | 4.7e-05 | +| loss | -0.0328 | +| n_updates | 40572 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000136 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1421 | +| iterations | 6190 | +| time_elapsed | 8917 | +| total_timesteps | 12677120 | +| train/ | | +| approx_kl | 0.012906789 | +| clip_fraction | 0.303 | +| clip_range | 0.0718 | +| entropy_loss | -7.08 | +| explained_variance | 0.429 | +| learning_rate | 4.7e-05 | +| loss | -0.0317 | +| n_updates | 40576 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.00018 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1421 | +| iterations | 6191 | +| time_elapsed | 8919 | +| total_timesteps | 12679168 | +| train/ | | +| approx_kl | 0.010384451 | +| clip_fraction | 0.326 | +| clip_range | 0.0718 | +| entropy_loss | -7.31 | +| explained_variance | 0.244 | +| learning_rate | 4.7e-05 | +| loss | -0.0305 | +| n_updates | 40580 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000208 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1421 | +| iterations | 6192 | +| time_elapsed | 8920 | +| total_timesteps | 12681216 | +| train/ | | +| approx_kl | 0.008294405 | +| clip_fraction | 0.266 | +| clip_range | 0.0718 | +| entropy_loss | -7.08 | +| explained_variance | 0.358 | +| learning_rate | 4.7e-05 | +| loss | -0.0273 | +| n_updates | 40584 | +| policy_gradient_loss | -0.0138 | +| value_loss | 0.00036 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1421 | +| iterations | 6193 | +| time_elapsed | 8922 | +| total_timesteps | 12683264 | +| train/ | | +| approx_kl | 0.010569858 | +| clip_fraction | 0.318 | +| clip_range | 0.0718 | +| entropy_loss | -7.22 | +| explained_variance | 0.325 | +| learning_rate | 4.7e-05 | +| loss | -0.0354 | +| n_updates | 40588 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000179 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1421 | +| iterations | 6194 | +| time_elapsed | 8923 | +| total_timesteps | 12685312 | +| train/ | | +| approx_kl | 0.008726584 | +| clip_fraction | 0.299 | +| clip_range | 0.0718 | +| entropy_loss | -7.2 | +| explained_variance | 0.363 | +| learning_rate | 4.7e-05 | +| loss | -0.0282 | +| n_updates | 40592 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000157 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1421 | +| iterations | 6195 | +| time_elapsed | 8925 | +| total_timesteps | 12687360 | +| train/ | | +| approx_kl | 0.009704854 | +| clip_fraction | 0.29 | +| clip_range | 0.0718 | +| entropy_loss | -7.48 | +| explained_variance | 0.0122 | +| learning_rate | 4.7e-05 | +| loss | -0.0321 | +| n_updates | 40596 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000328 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1421 | +| iterations | 6196 | +| time_elapsed | 8926 | +| total_timesteps | 12689408 | +| train/ | | +| approx_kl | 0.012892287 | +| clip_fraction | 0.329 | +| clip_range | 0.0718 | +| entropy_loss | -6.79 | +| explained_variance | 0.694 | +| learning_rate | 4.7e-05 | +| loss | -0.033 | +| n_updates | 40600 | +| policy_gradient_loss | -0.0225 | +| value_loss | 9.22e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1421 | +| iterations | 6197 | +| time_elapsed | 8928 | +| total_timesteps | 12691456 | +| train/ | | +| approx_kl | 0.011439951 | +| clip_fraction | 0.3 | +| clip_range | 0.0718 | +| entropy_loss | -7.52 | +| explained_variance | -0.252 | +| learning_rate | 4.7e-05 | +| loss | -0.0317 | +| n_updates | 40604 | +| policy_gradient_loss | -0.022 | +| value_loss | 8.93e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1421 | +| iterations | 6198 | +| time_elapsed | 8929 | +| total_timesteps | 12693504 | +| train/ | | +| approx_kl | 0.010802054 | +| clip_fraction | 0.317 | +| clip_range | 0.0718 | +| entropy_loss | -7.13 | +| explained_variance | 0.464 | +| learning_rate | 4.7e-05 | +| loss | -0.033 | +| n_updates | 40608 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000157 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1421 | +| iterations | 6199 | +| time_elapsed | 8930 | +| total_timesteps | 12695552 | +| train/ | | +| approx_kl | 0.01071589 | +| clip_fraction | 0.316 | +| clip_range | 0.0718 | +| entropy_loss | -7.2 | +| explained_variance | 0.567 | +| learning_rate | 4.7e-05 | +| loss | -0.0378 | +| n_updates | 40612 | +| policy_gradient_loss | -0.0212 | +| value_loss | 9.69e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1421 | +| iterations | 6200 | +| time_elapsed | 8932 | +| total_timesteps | 12697600 | +| train/ | | +| approx_kl | 0.011146238 | +| clip_fraction | 0.328 | +| clip_range | 0.0718 | +| entropy_loss | -7.35 | +| explained_variance | 0.41 | +| learning_rate | 4.7e-05 | +| loss | -0.0394 | +| n_updates | 40616 | +| policy_gradient_loss | -0.0218 | +| value_loss | 7.34e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1421 | +| iterations | 6201 | +| time_elapsed | 8933 | +| total_timesteps | 12699648 | +| train/ | | +| approx_kl | 0.011560375 | +| clip_fraction | 0.321 | +| clip_range | 0.0718 | +| entropy_loss | -7.44 | +| explained_variance | -0.0711 | +| learning_rate | 4.7e-05 | +| loss | -0.0271 | +| n_updates | 40620 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000159 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1421 | +| iterations | 6202 | +| time_elapsed | 8935 | +| total_timesteps | 12701696 | +| train/ | | +| approx_kl | 0.010268814 | +| clip_fraction | 0.317 | +| clip_range | 0.0718 | +| entropy_loss | -7.02 | +| explained_variance | 0.552 | +| learning_rate | 4.7e-05 | +| loss | -0.0342 | +| n_updates | 40624 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000142 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1421 | +| iterations | 6203 | +| time_elapsed | 8936 | +| total_timesteps | 12703744 | +| train/ | | +| approx_kl | 0.008913286 | +| clip_fraction | 0.273 | +| clip_range | 0.0718 | +| entropy_loss | -7.21 | +| explained_variance | 0.244 | +| learning_rate | 4.7e-05 | +| loss | -0.0238 | +| n_updates | 40628 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000222 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1421 | +| iterations | 6204 | +| time_elapsed | 8937 | +| total_timesteps | 12705792 | +| train/ | | +| approx_kl | 0.011049114 | +| clip_fraction | 0.293 | +| clip_range | 0.0718 | +| entropy_loss | -7 | +| explained_variance | 0.344 | +| learning_rate | 4.7e-05 | +| loss | -0.0235 | +| n_updates | 40632 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000239 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1421 | +| iterations | 6205 | +| time_elapsed | 8939 | +| total_timesteps | 12707840 | +| train/ | | +| approx_kl | 0.011359878 | +| clip_fraction | 0.322 | +| clip_range | 0.0718 | +| entropy_loss | -7.45 | +| explained_variance | -0.124 | +| learning_rate | 4.7e-05 | +| loss | -0.0368 | +| n_updates | 40636 | +| policy_gradient_loss | -0.0235 | +| value_loss | 9.14e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1421 | +| iterations | 6206 | +| time_elapsed | 8940 | +| total_timesteps | 12709888 | +| train/ | | +| approx_kl | 0.009532552 | +| clip_fraction | 0.324 | +| clip_range | 0.0718 | +| entropy_loss | -6.9 | +| explained_variance | 0.491 | +| learning_rate | 4.7e-05 | +| loss | -0.0263 | +| n_updates | 40640 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000188 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1421 | +| iterations | 6207 | +| time_elapsed | 8942 | +| total_timesteps | 12711936 | +| train/ | | +| approx_kl | 0.01144515 | +| clip_fraction | 0.322 | +| clip_range | 0.0718 | +| entropy_loss | -7.2 | +| explained_variance | 0.232 | +| learning_rate | 4.7e-05 | +| loss | -0.0347 | +| n_updates | 40644 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000169 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1421 | +| iterations | 6208 | +| time_elapsed | 8943 | +| total_timesteps | 12713984 | +| train/ | | +| approx_kl | 0.008914296 | +| clip_fraction | 0.285 | +| clip_range | 0.0718 | +| entropy_loss | -7.24 | +| explained_variance | 0.227 | +| learning_rate | 4.7e-05 | +| loss | -0.0288 | +| n_updates | 40648 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000227 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1421 | +| iterations | 6209 | +| time_elapsed | 8945 | +| total_timesteps | 12716032 | +| train/ | | +| approx_kl | 0.011866764 | +| clip_fraction | 0.292 | +| clip_range | 0.0718 | +| entropy_loss | -6.95 | +| explained_variance | 0.423 | +| learning_rate | 4.7e-05 | +| loss | -0.0314 | +| n_updates | 40652 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000288 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1421 | +| iterations | 6210 | +| time_elapsed | 8946 | +| total_timesteps | 12718080 | +| train/ | | +| approx_kl | 0.010620305 | +| clip_fraction | 0.311 | +| clip_range | 0.0718 | +| entropy_loss | -7.12 | +| explained_variance | 0.318 | +| learning_rate | 4.7e-05 | +| loss | -0.0326 | +| n_updates | 40656 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000187 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1421 | +| iterations | 6211 | +| time_elapsed | 8947 | +| total_timesteps | 12720128 | +| train/ | | +| approx_kl | 0.011850119 | +| clip_fraction | 0.323 | +| clip_range | 0.0718 | +| entropy_loss | -7.11 | +| explained_variance | 0.552 | +| learning_rate | 4.7e-05 | +| loss | -0.0318 | +| n_updates | 40660 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000152 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1421 | +| iterations | 6212 | +| time_elapsed | 8949 | +| total_timesteps | 12722176 | +| train/ | | +| approx_kl | 0.013112774 | +| clip_fraction | 0.343 | +| clip_range | 0.0718 | +| entropy_loss | -7.23 | +| explained_variance | 0.408 | +| learning_rate | 4.7e-05 | +| loss | -0.0328 | +| n_updates | 40664 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000178 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1421 | +| iterations | 6213 | +| time_elapsed | 8950 | +| total_timesteps | 12724224 | +| train/ | | +| approx_kl | 0.01040331 | +| clip_fraction | 0.306 | +| clip_range | 0.0718 | +| entropy_loss | -7.26 | +| explained_variance | 0.268 | +| learning_rate | 4.7e-05 | +| loss | -0.0234 | +| n_updates | 40668 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000238 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1421 | +| iterations | 6214 | +| time_elapsed | 8952 | +| total_timesteps | 12726272 | +| train/ | | +| approx_kl | 0.0116744265 | +| clip_fraction | 0.34 | +| clip_range | 0.0718 | +| entropy_loss | -7.33 | +| explained_variance | 0.319 | +| learning_rate | 4.7e-05 | +| loss | -0.0333 | +| n_updates | 40672 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000167 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1421 | +| iterations | 6215 | +| time_elapsed | 8953 | +| total_timesteps | 12728320 | +| train/ | | +| approx_kl | 0.010876649 | +| clip_fraction | 0.308 | +| clip_range | 0.0718 | +| entropy_loss | -7.32 | +| explained_variance | 0.227 | +| learning_rate | 4.7e-05 | +| loss | -0.0345 | +| n_updates | 40676 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000267 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1421 | +| iterations | 6216 | +| time_elapsed | 8955 | +| total_timesteps | 12730368 | +| train/ | | +| approx_kl | 0.010031516 | +| clip_fraction | 0.317 | +| clip_range | 0.0718 | +| entropy_loss | -7.05 | +| explained_variance | 0.448 | +| learning_rate | 4.7e-05 | +| loss | -0.0253 | +| n_updates | 40680 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000184 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1421 | +| iterations | 6217 | +| time_elapsed | 8956 | +| total_timesteps | 12732416 | +| train/ | | +| approx_kl | 0.012837088 | +| clip_fraction | 0.344 | +| clip_range | 0.0718 | +| entropy_loss | -6.98 | +| explained_variance | 0.438 | +| learning_rate | 4.7e-05 | +| loss | -0.0375 | +| n_updates | 40684 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000196 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1421 | +| iterations | 6218 | +| time_elapsed | 8957 | +| total_timesteps | 12734464 | +| train/ | | +| approx_kl | 0.010576777 | +| clip_fraction | 0.304 | +| clip_range | 0.0718 | +| entropy_loss | -7.45 | +| explained_variance | -0.0714 | +| learning_rate | 4.7e-05 | +| loss | -0.0281 | +| n_updates | 40688 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000249 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1421 | +| iterations | 6219 | +| time_elapsed | 8959 | +| total_timesteps | 12736512 | +| train/ | | +| approx_kl | 0.012394039 | +| clip_fraction | 0.323 | +| clip_range | 0.0718 | +| entropy_loss | -7.12 | +| explained_variance | 0.456 | +| learning_rate | 4.7e-05 | +| loss | -0.0363 | +| n_updates | 40692 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000151 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1421 | +| iterations | 6220 | +| time_elapsed | 8960 | +| total_timesteps | 12738560 | +| train/ | | +| approx_kl | 0.011348982 | +| clip_fraction | 0.318 | +| clip_range | 0.0718 | +| entropy_loss | -6.8 | +| explained_variance | 0.466 | +| learning_rate | 4.7e-05 | +| loss | -0.0314 | +| n_updates | 40696 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000277 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1421 | +| iterations | 6221 | +| time_elapsed | 8962 | +| total_timesteps | 12740608 | +| train/ | | +| approx_kl | 0.013068889 | +| clip_fraction | 0.338 | +| clip_range | 0.0718 | +| entropy_loss | -7.02 | +| explained_variance | 0.564 | +| learning_rate | 4.7e-05 | +| loss | -0.0347 | +| n_updates | 40700 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000135 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1421 | +| iterations | 6222 | +| time_elapsed | 8963 | +| total_timesteps | 12742656 | +| train/ | | +| approx_kl | 0.012763839 | +| clip_fraction | 0.352 | +| clip_range | 0.0718 | +| entropy_loss | -7.4 | +| explained_variance | -0.249 | +| learning_rate | 4.7e-05 | +| loss | -0.0413 | +| n_updates | 40704 | +| policy_gradient_loss | -0.0236 | +| value_loss | 0.000138 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1421 | +| iterations | 6223 | +| time_elapsed | 8964 | +| total_timesteps | 12744704 | +| train/ | | +| approx_kl | 0.0110982545 | +| clip_fraction | 0.318 | +| clip_range | 0.0718 | +| entropy_loss | -7.12 | +| explained_variance | 0.533 | +| learning_rate | 4.7e-05 | +| loss | -0.0339 | +| n_updates | 40708 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000106 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1421 | +| iterations | 6224 | +| time_elapsed | 8966 | +| total_timesteps | 12746752 | +| train/ | | +| approx_kl | 0.012627203 | +| clip_fraction | 0.323 | +| clip_range | 0.0718 | +| entropy_loss | -7.28 | +| explained_variance | 0.433 | +| learning_rate | 4.7e-05 | +| loss | -0.0288 | +| n_updates | 40712 | +| policy_gradient_loss | -0.0202 | +| value_loss | 8.94e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1421 | +| iterations | 6225 | +| time_elapsed | 8967 | +| total_timesteps | 12748800 | +| train/ | | +| approx_kl | 0.009709427 | +| clip_fraction | 0.311 | +| clip_range | 0.0718 | +| entropy_loss | -7.32 | +| explained_variance | 0.297 | +| learning_rate | 4.7e-05 | +| loss | -0.0321 | +| n_updates | 40716 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000167 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1421 | +| iterations | 6226 | +| time_elapsed | 8969 | +| total_timesteps | 12750848 | +| train/ | | +| approx_kl | 0.010659961 | +| clip_fraction | 0.298 | +| clip_range | 0.0718 | +| entropy_loss | -7.18 | +| explained_variance | 0.272 | +| learning_rate | 4.7e-05 | +| loss | -0.033 | +| n_updates | 40720 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000256 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1421 | +| iterations | 6227 | +| time_elapsed | 8970 | +| total_timesteps | 12752896 | +| train/ | | +| approx_kl | 0.010483103 | +| clip_fraction | 0.324 | +| clip_range | 0.0718 | +| entropy_loss | -6.95 | +| explained_variance | 0.653 | +| learning_rate | 4.7e-05 | +| loss | -0.0339 | +| n_updates | 40724 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000134 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1421 | +| iterations | 6228 | +| time_elapsed | 8971 | +| total_timesteps | 12754944 | +| train/ | | +| approx_kl | 0.010473387 | +| clip_fraction | 0.344 | +| clip_range | 0.0718 | +| entropy_loss | -7 | +| explained_variance | 0.723 | +| learning_rate | 4.7e-05 | +| loss | -0.0263 | +| n_updates | 40728 | +| policy_gradient_loss | -0.0204 | +| value_loss | 7.67e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1421 | +| iterations | 6229 | +| time_elapsed | 8973 | +| total_timesteps | 12756992 | +| train/ | | +| approx_kl | 0.008287854 | +| clip_fraction | 0.299 | +| clip_range | 0.0718 | +| entropy_loss | -7.13 | +| explained_variance | 0.465 | +| learning_rate | 4.7e-05 | +| loss | -0.0231 | +| n_updates | 40732 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000158 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1421 | +| iterations | 6230 | +| time_elapsed | 8974 | +| total_timesteps | 12759040 | +| train/ | | +| approx_kl | 0.012604456 | +| clip_fraction | 0.343 | +| clip_range | 0.0718 | +| entropy_loss | -7.19 | +| explained_variance | 0.52 | +| learning_rate | 4.7e-05 | +| loss | -0.0388 | +| n_updates | 40736 | +| policy_gradient_loss | -0.0224 | +| value_loss | 8.81e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1421 | +| iterations | 6231 | +| time_elapsed | 8976 | +| total_timesteps | 12761088 | +| train/ | | +| approx_kl | 0.011014223 | +| clip_fraction | 0.335 | +| clip_range | 0.0718 | +| entropy_loss | -7.15 | +| explained_variance | 0.405 | +| learning_rate | 4.7e-05 | +| loss | -0.0288 | +| n_updates | 40740 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000115 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1421 | +| iterations | 6232 | +| time_elapsed | 8977 | +| total_timesteps | 12763136 | +| train/ | | +| approx_kl | 0.008930388 | +| clip_fraction | 0.314 | +| clip_range | 0.0718 | +| entropy_loss | -7.37 | +| explained_variance | 0.0847 | +| learning_rate | 4.7e-05 | +| loss | -0.0297 | +| n_updates | 40744 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000179 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1421 | +| iterations | 6233 | +| time_elapsed | 8979 | +| total_timesteps | 12765184 | +| train/ | | +| approx_kl | 0.009435918 | +| clip_fraction | 0.311 | +| clip_range | 0.0718 | +| entropy_loss | -7.43 | +| explained_variance | 0.287 | +| learning_rate | 4.7e-05 | +| loss | -0.0305 | +| n_updates | 40748 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.00013 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1421 | +| iterations | 6234 | +| time_elapsed | 8980 | +| total_timesteps | 12767232 | +| train/ | | +| approx_kl | 0.009820981 | +| clip_fraction | 0.296 | +| clip_range | 0.0718 | +| entropy_loss | -7.26 | +| explained_variance | 0.353 | +| learning_rate | 4.7e-05 | +| loss | -0.0312 | +| n_updates | 40752 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000141 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1421 | +| iterations | 6235 | +| time_elapsed | 8981 | +| total_timesteps | 12769280 | +| train/ | | +| approx_kl | 0.0074170725 | +| clip_fraction | 0.291 | +| clip_range | 0.0718 | +| entropy_loss | -6.99 | +| explained_variance | 0.477 | +| learning_rate | 4.7e-05 | +| loss | -0.023 | +| n_updates | 40756 | +| policy_gradient_loss | -0.0143 | +| value_loss | 0.000246 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1421 | +| iterations | 6236 | +| time_elapsed | 8983 | +| total_timesteps | 12771328 | +| train/ | | +| approx_kl | 0.01164633 | +| clip_fraction | 0.294 | +| clip_range | 0.0718 | +| entropy_loss | -6.93 | +| explained_variance | 0.278 | +| learning_rate | 4.7e-05 | +| loss | -0.0284 | +| n_updates | 40760 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000232 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1421 | +| iterations | 6237 | +| time_elapsed | 8984 | +| total_timesteps | 12773376 | +| train/ | | +| approx_kl | 0.010324172 | +| clip_fraction | 0.32 | +| clip_range | 0.0718 | +| entropy_loss | -7.07 | +| explained_variance | 0.513 | +| learning_rate | 4.7e-05 | +| loss | -0.0307 | +| n_updates | 40764 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000136 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1421 | +| iterations | 6238 | +| time_elapsed | 8986 | +| total_timesteps | 12775424 | +| train/ | | +| approx_kl | 0.010039112 | +| clip_fraction | 0.325 | +| clip_range | 0.0718 | +| entropy_loss | -7.2 | +| explained_variance | 0.364 | +| learning_rate | 4.7e-05 | +| loss | -0.0375 | +| n_updates | 40768 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000119 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1421 | +| iterations | 6239 | +| time_elapsed | 8987 | +| total_timesteps | 12777472 | +| train/ | | +| approx_kl | 0.011631908 | +| clip_fraction | 0.326 | +| clip_range | 0.0718 | +| entropy_loss | -7.07 | +| explained_variance | 0.503 | +| learning_rate | 4.7e-05 | +| loss | -0.0285 | +| n_updates | 40772 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000147 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1421 | +| iterations | 6240 | +| time_elapsed | 8989 | +| total_timesteps | 12779520 | +| train/ | | +| approx_kl | 0.011985829 | +| clip_fraction | 0.348 | +| clip_range | 0.0718 | +| entropy_loss | -7.29 | +| explained_variance | 0.373 | +| learning_rate | 4.7e-05 | +| loss | -0.0325 | +| n_updates | 40776 | +| policy_gradient_loss | -0.0209 | +| value_loss | 9.91e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1421 | +| iterations | 6241 | +| time_elapsed | 8990 | +| total_timesteps | 12781568 | +| train/ | | +| approx_kl | 0.010534013 | +| clip_fraction | 0.309 | +| clip_range | 0.0718 | +| entropy_loss | -7.18 | +| explained_variance | 0.339 | +| learning_rate | 4.7e-05 | +| loss | -0.0299 | +| n_updates | 40780 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000261 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1421 | +| iterations | 6242 | +| time_elapsed | 8992 | +| total_timesteps | 12783616 | +| train/ | | +| approx_kl | 0.012945092 | +| clip_fraction | 0.347 | +| clip_range | 0.0718 | +| entropy_loss | -7.32 | +| explained_variance | 0.149 | +| learning_rate | 4.7e-05 | +| loss | -0.041 | +| n_updates | 40784 | +| policy_gradient_loss | -0.0248 | +| value_loss | 7.02e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1421 | +| iterations | 6243 | +| time_elapsed | 8993 | +| total_timesteps | 12785664 | +| train/ | | +| approx_kl | 0.010911607 | +| clip_fraction | 0.32 | +| clip_range | 0.0718 | +| entropy_loss | -6.96 | +| explained_variance | 0.57 | +| learning_rate | 4.7e-05 | +| loss | -0.0318 | +| n_updates | 40788 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000175 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1421 | +| iterations | 6244 | +| time_elapsed | 8994 | +| total_timesteps | 12787712 | +| train/ | | +| approx_kl | 0.00930966 | +| clip_fraction | 0.296 | +| clip_range | 0.0718 | +| entropy_loss | -7.32 | +| explained_variance | 0.239 | +| learning_rate | 4.7e-05 | +| loss | -0.029 | +| n_updates | 40792 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000313 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1421 | +| iterations | 6245 | +| time_elapsed | 8996 | +| total_timesteps | 12789760 | +| train/ | | +| approx_kl | 0.010392006 | +| clip_fraction | 0.317 | +| clip_range | 0.0718 | +| entropy_loss | -6.97 | +| explained_variance | 0.338 | +| learning_rate | 4.7e-05 | +| loss | -0.0332 | +| n_updates | 40796 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000206 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1421 | +| iterations | 6246 | +| time_elapsed | 8997 | +| total_timesteps | 12791808 | +| train/ | | +| approx_kl | 0.0110522 | +| clip_fraction | 0.32 | +| clip_range | 0.0718 | +| entropy_loss | -6.97 | +| explained_variance | 0.419 | +| learning_rate | 4.7e-05 | +| loss | -0.0311 | +| n_updates | 40800 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000209 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1421 | +| iterations | 6247 | +| time_elapsed | 8999 | +| total_timesteps | 12793856 | +| train/ | | +| approx_kl | 0.010857137 | +| clip_fraction | 0.318 | +| clip_range | 0.0718 | +| entropy_loss | -7.25 | +| explained_variance | 0.348 | +| learning_rate | 4.7e-05 | +| loss | -0.0396 | +| n_updates | 40804 | +| policy_gradient_loss | -0.0218 | +| value_loss | 9.9e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1421 | +| iterations | 6248 | +| time_elapsed | 9000 | +| total_timesteps | 12795904 | +| train/ | | +| approx_kl | 0.009623704 | +| clip_fraction | 0.327 | +| clip_range | 0.0718 | +| entropy_loss | -7.51 | +| explained_variance | -0.108 | +| learning_rate | 4.7e-05 | +| loss | -0.0403 | +| n_updates | 40808 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000114 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1421 | +| iterations | 6249 | +| time_elapsed | 9002 | +| total_timesteps | 12797952 | +| train/ | | +| approx_kl | 0.010945298 | +| clip_fraction | 0.308 | +| clip_range | 0.0718 | +| entropy_loss | -7.08 | +| explained_variance | 0.429 | +| learning_rate | 4.7e-05 | +| loss | -0.0324 | +| n_updates | 40812 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000119 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1421 | +| iterations | 6250 | +| time_elapsed | 9003 | +| total_timesteps | 12800000 | +| train/ | | +| approx_kl | 0.0113417255 | +| clip_fraction | 0.328 | +| clip_range | 0.0718 | +| entropy_loss | -7.26 | +| explained_variance | 0.232 | +| learning_rate | 4.7e-05 | +| loss | -0.0336 | +| n_updates | 40816 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000113 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1421 | +| iterations | 6251 | +| time_elapsed | 9004 | +| total_timesteps | 12802048 | +| train/ | | +| approx_kl | 0.012313452 | +| clip_fraction | 0.287 | +| clip_range | 0.0718 | +| entropy_loss | -6.56 | +| explained_variance | 0.616 | +| learning_rate | 4.7e-05 | +| loss | -0.0286 | +| n_updates | 40820 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000223 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1421 | +| iterations | 6252 | +| time_elapsed | 9006 | +| total_timesteps | 12804096 | +| train/ | | +| approx_kl | 0.01035941 | +| clip_fraction | 0.315 | +| clip_range | 0.0718 | +| entropy_loss | -6.82 | +| explained_variance | 0.591 | +| learning_rate | 4.7e-05 | +| loss | -0.0263 | +| n_updates | 40824 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000164 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1421 | +| iterations | 6253 | +| time_elapsed | 9007 | +| total_timesteps | 12806144 | +| train/ | | +| approx_kl | 0.0088862935 | +| clip_fraction | 0.301 | +| clip_range | 0.0718 | +| entropy_loss | -7.29 | +| explained_variance | -0.196 | +| learning_rate | 4.7e-05 | +| loss | -0.0276 | +| n_updates | 40828 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000196 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1421 | +| iterations | 6254 | +| time_elapsed | 9009 | +| total_timesteps | 12808192 | +| train/ | | +| approx_kl | 0.010108033 | +| clip_fraction | 0.349 | +| clip_range | 0.0718 | +| entropy_loss | -7.43 | +| explained_variance | -0.0401 | +| learning_rate | 4.7e-05 | +| loss | -0.0318 | +| n_updates | 40832 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000164 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1421 | +| iterations | 6255 | +| time_elapsed | 9010 | +| total_timesteps | 12810240 | +| train/ | | +| approx_kl | 0.010708021 | +| clip_fraction | 0.315 | +| clip_range | 0.0718 | +| entropy_loss | -7.31 | +| explained_variance | 0.384 | +| learning_rate | 4.7e-05 | +| loss | -0.0323 | +| n_updates | 40836 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000114 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1421 | +| iterations | 6256 | +| time_elapsed | 9012 | +| total_timesteps | 12812288 | +| train/ | | +| approx_kl | 0.010235334 | +| clip_fraction | 0.325 | +| clip_range | 0.0718 | +| entropy_loss | -7.03 | +| explained_variance | 0.539 | +| learning_rate | 4.7e-05 | +| loss | -0.0276 | +| n_updates | 40840 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000133 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1421 | +| iterations | 6257 | +| time_elapsed | 9013 | +| total_timesteps | 12814336 | +| train/ | | +| approx_kl | 0.009711606 | +| clip_fraction | 0.309 | +| clip_range | 0.0718 | +| entropy_loss | -6.81 | +| explained_variance | 0.411 | +| learning_rate | 4.7e-05 | +| loss | -0.0275 | +| n_updates | 40844 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000292 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1421 | +| iterations | 6258 | +| time_elapsed | 9014 | +| total_timesteps | 12816384 | +| train/ | | +| approx_kl | 0.010330504 | +| clip_fraction | 0.334 | +| clip_range | 0.0718 | +| entropy_loss | -6.78 | +| explained_variance | 0.736 | +| learning_rate | 4.7e-05 | +| loss | -0.0359 | +| n_updates | 40848 | +| policy_gradient_loss | -0.0226 | +| value_loss | 0.000115 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1421 | +| iterations | 6259 | +| time_elapsed | 9016 | +| total_timesteps | 12818432 | +| train/ | | +| approx_kl | 0.009608893 | +| clip_fraction | 0.283 | +| clip_range | 0.0718 | +| entropy_loss | -7.51 | +| explained_variance | -0.212 | +| learning_rate | 4.7e-05 | +| loss | -0.0342 | +| n_updates | 40852 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000132 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1421 | +| iterations | 6260 | +| time_elapsed | 9017 | +| total_timesteps | 12820480 | +| train/ | | +| approx_kl | 0.0103516765 | +| clip_fraction | 0.325 | +| clip_range | 0.0718 | +| entropy_loss | -7.09 | +| explained_variance | 0.413 | +| learning_rate | 4.7e-05 | +| loss | -0.0278 | +| n_updates | 40856 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000193 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1421 | +| iterations | 6261 | +| time_elapsed | 9019 | +| total_timesteps | 12822528 | +| train/ | | +| approx_kl | 0.00846227 | +| clip_fraction | 0.273 | +| clip_range | 0.0718 | +| entropy_loss | -7 | +| explained_variance | 0.393 | +| learning_rate | 4.7e-05 | +| loss | -0.023 | +| n_updates | 40860 | +| policy_gradient_loss | -0.0145 | +| value_loss | 0.000266 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1421 | +| iterations | 6262 | +| time_elapsed | 9020 | +| total_timesteps | 12824576 | +| train/ | | +| approx_kl | 0.009769625 | +| clip_fraction | 0.292 | +| clip_range | 0.0718 | +| entropy_loss | -7.36 | +| explained_variance | 0.0827 | +| learning_rate | 4.7e-05 | +| loss | -0.0314 | +| n_updates | 40864 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.00023 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 1421 | +| iterations | 6263 | +| time_elapsed | 9022 | +| total_timesteps | 12826624 | +| train/ | | +| approx_kl | 0.009804749 | +| clip_fraction | 0.306 | +| clip_range | 0.0718 | +| entropy_loss | -7.09 | +| explained_variance | 0.545 | +| learning_rate | 4.7e-05 | +| loss | -0.0339 | +| n_updates | 40868 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.00011 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1421 | +| iterations | 6264 | +| time_elapsed | 9023 | +| total_timesteps | 12828672 | +| train/ | | +| approx_kl | 0.011050467 | +| clip_fraction | 0.32 | +| clip_range | 0.0718 | +| entropy_loss | -7.3 | +| explained_variance | 0.43 | +| learning_rate | 4.7e-05 | +| loss | -0.031 | +| n_updates | 40872 | +| policy_gradient_loss | -0.0211 | +| value_loss | 9.79e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.306 | +| time/ | | +| fps | 1421 | +| iterations | 6265 | +| time_elapsed | 9024 | +| total_timesteps | 12830720 | +| train/ | | +| approx_kl | 0.00900568 | +| clip_fraction | 0.293 | +| clip_range | 0.0718 | +| entropy_loss | -7.05 | +| explained_variance | 0.42 | +| learning_rate | 4.7e-05 | +| loss | -0.0276 | +| n_updates | 40876 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000313 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.3 | +| time/ | | +| fps | 1421 | +| iterations | 6266 | +| time_elapsed | 9026 | +| total_timesteps | 12832768 | +| train/ | | +| approx_kl | 0.01172838 | +| clip_fraction | 0.338 | +| clip_range | 0.0718 | +| entropy_loss | -7.11 | +| explained_variance | 0.339 | +| learning_rate | 4.7e-05 | +| loss | -0.0342 | +| n_updates | 40880 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000139 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.302 | +| time/ | | +| fps | 1421 | +| iterations | 6267 | +| time_elapsed | 9027 | +| total_timesteps | 12834816 | +| train/ | | +| approx_kl | 0.009911995 | +| clip_fraction | 0.317 | +| clip_range | 0.0718 | +| entropy_loss | -7.04 | +| explained_variance | 0.56 | +| learning_rate | 4.7e-05 | +| loss | -0.0352 | +| n_updates | 40884 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000121 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 1421 | +| iterations | 6268 | +| time_elapsed | 9029 | +| total_timesteps | 12836864 | +| train/ | | +| approx_kl | 0.011618298 | +| clip_fraction | 0.302 | +| clip_range | 0.0718 | +| entropy_loss | -7.17 | +| explained_variance | 0.315 | +| learning_rate | 4.7e-05 | +| loss | -0.0252 | +| n_updates | 40888 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.00024 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 1421 | +| iterations | 6269 | +| time_elapsed | 9030 | +| total_timesteps | 12838912 | +| train/ | | +| approx_kl | 0.008724145 | +| clip_fraction | 0.28 | +| clip_range | 0.0718 | +| entropy_loss | -7.24 | +| explained_variance | 0.137 | +| learning_rate | 4.7e-05 | +| loss | -0.0217 | +| n_updates | 40892 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000411 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 1421 | +| iterations | 6270 | +| time_elapsed | 9032 | +| total_timesteps | 12840960 | +| train/ | | +| approx_kl | 0.010329536 | +| clip_fraction | 0.3 | +| clip_range | 0.0718 | +| entropy_loss | -6.86 | +| explained_variance | 0.539 | +| learning_rate | 4.7e-05 | +| loss | -0.0354 | +| n_updates | 40896 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000158 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 1421 | +| iterations | 6271 | +| time_elapsed | 9033 | +| total_timesteps | 12843008 | +| train/ | | +| approx_kl | 0.011633826 | +| clip_fraction | 0.286 | +| clip_range | 0.0718 | +| entropy_loss | -6.9 | +| explained_variance | 0.443 | +| learning_rate | 4.7e-05 | +| loss | -0.0312 | +| n_updates | 40900 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000247 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1421 | +| iterations | 6272 | +| time_elapsed | 9034 | +| total_timesteps | 12845056 | +| train/ | | +| approx_kl | 0.010739958 | +| clip_fraction | 0.335 | +| clip_range | 0.0718 | +| entropy_loss | -7.43 | +| explained_variance | -0.0397 | +| learning_rate | 4.69e-05 | +| loss | -0.0317 | +| n_updates | 40904 | +| policy_gradient_loss | -0.023 | +| value_loss | 0.000117 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1421 | +| iterations | 6273 | +| time_elapsed | 9036 | +| total_timesteps | 12847104 | +| train/ | | +| approx_kl | 0.009073472 | +| clip_fraction | 0.297 | +| clip_range | 0.0718 | +| entropy_loss | -7.03 | +| explained_variance | 0.294 | +| learning_rate | 4.69e-05 | +| loss | -0.0296 | +| n_updates | 40908 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000394 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.306 | +| time/ | | +| fps | 1421 | +| iterations | 6274 | +| time_elapsed | 9037 | +| total_timesteps | 12849152 | +| train/ | | +| approx_kl | 0.011250001 | +| clip_fraction | 0.302 | +| clip_range | 0.0718 | +| entropy_loss | -7.5 | +| explained_variance | -0.176 | +| learning_rate | 4.69e-05 | +| loss | -0.0315 | +| n_updates | 40912 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000219 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.304 | +| time/ | | +| fps | 1421 | +| iterations | 6275 | +| time_elapsed | 9039 | +| total_timesteps | 12851200 | +| train/ | | +| approx_kl | 0.009322015 | +| clip_fraction | 0.307 | +| clip_range | 0.0718 | +| entropy_loss | -7.09 | +| explained_variance | 0.283 | +| learning_rate | 4.69e-05 | +| loss | -0.0301 | +| n_updates | 40916 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000254 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.304 | +| time/ | | +| fps | 1421 | +| iterations | 6276 | +| time_elapsed | 9040 | +| total_timesteps | 12853248 | +| train/ | | +| approx_kl | 0.01150739 | +| clip_fraction | 0.327 | +| clip_range | 0.0718 | +| entropy_loss | -7.12 | +| explained_variance | 0.499 | +| learning_rate | 4.69e-05 | +| loss | -0.0409 | +| n_updates | 40920 | +| policy_gradient_loss | -0.0224 | +| value_loss | 0.000103 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1421 | +| iterations | 6277 | +| time_elapsed | 9042 | +| total_timesteps | 12855296 | +| train/ | | +| approx_kl | 0.0089928005 | +| clip_fraction | 0.294 | +| clip_range | 0.0718 | +| entropy_loss | -6.94 | +| explained_variance | 0.333 | +| learning_rate | 4.69e-05 | +| loss | -0.028 | +| n_updates | 40924 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000274 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1421 | +| iterations | 6278 | +| time_elapsed | 9043 | +| total_timesteps | 12857344 | +| train/ | | +| approx_kl | 0.01241646 | +| clip_fraction | 0.288 | +| clip_range | 0.0718 | +| entropy_loss | -7.16 | +| explained_variance | 0.303 | +| learning_rate | 4.69e-05 | +| loss | -0.0388 | +| n_updates | 40928 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000274 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1421 | +| iterations | 6279 | +| time_elapsed | 9045 | +| total_timesteps | 12859392 | +| train/ | | +| approx_kl | 0.010508852 | +| clip_fraction | 0.323 | +| clip_range | 0.0718 | +| entropy_loss | -7.35 | +| explained_variance | 0.227 | +| learning_rate | 4.69e-05 | +| loss | -0.0306 | +| n_updates | 40932 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000185 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1421 | +| iterations | 6280 | +| time_elapsed | 9046 | +| total_timesteps | 12861440 | +| train/ | | +| approx_kl | 0.012773623 | +| clip_fraction | 0.339 | +| clip_range | 0.0718 | +| entropy_loss | -7.23 | +| explained_variance | 0.192 | +| learning_rate | 4.69e-05 | +| loss | -0.0373 | +| n_updates | 40936 | +| policy_gradient_loss | -0.0235 | +| value_loss | 0.000128 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1421 | +| iterations | 6281 | +| time_elapsed | 9047 | +| total_timesteps | 12863488 | +| train/ | | +| approx_kl | 0.010985487 | +| clip_fraction | 0.298 | +| clip_range | 0.0718 | +| entropy_loss | -7.11 | +| explained_variance | 0.137 | +| learning_rate | 4.69e-05 | +| loss | -0.0316 | +| n_updates | 40940 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000166 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1421 | +| iterations | 6282 | +| time_elapsed | 9049 | +| total_timesteps | 12865536 | +| train/ | | +| approx_kl | 0.013054334 | +| clip_fraction | 0.334 | +| clip_range | 0.0718 | +| entropy_loss | -6.95 | +| explained_variance | 0.646 | +| learning_rate | 4.69e-05 | +| loss | -0.0221 | +| n_updates | 40944 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.00011 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 1421 | +| iterations | 6283 | +| time_elapsed | 9050 | +| total_timesteps | 12867584 | +| train/ | | +| approx_kl | 0.011267607 | +| clip_fraction | 0.315 | +| clip_range | 0.0718 | +| entropy_loss | -7.09 | +| explained_variance | 0.429 | +| learning_rate | 4.69e-05 | +| loss | -0.0323 | +| n_updates | 40948 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000164 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.306 | +| time/ | | +| fps | 1421 | +| iterations | 6284 | +| time_elapsed | 9052 | +| total_timesteps | 12869632 | +| train/ | | +| approx_kl | 0.01053367 | +| clip_fraction | 0.323 | +| clip_range | 0.0718 | +| entropy_loss | -7.22 | +| explained_variance | 0.317 | +| learning_rate | 4.69e-05 | +| loss | -0.0287 | +| n_updates | 40952 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000131 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1421 | +| iterations | 6285 | +| time_elapsed | 9053 | +| total_timesteps | 12871680 | +| train/ | | +| approx_kl | 0.00983728 | +| clip_fraction | 0.326 | +| clip_range | 0.0718 | +| entropy_loss | -7.12 | +| explained_variance | 0.619 | +| learning_rate | 4.69e-05 | +| loss | -0.0348 | +| n_updates | 40956 | +| policy_gradient_loss | -0.0217 | +| value_loss | 8.43e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1421 | +| iterations | 6286 | +| time_elapsed | 9055 | +| total_timesteps | 12873728 | +| train/ | | +| approx_kl | 0.008781054 | +| clip_fraction | 0.264 | +| clip_range | 0.0718 | +| entropy_loss | -7.36 | +| explained_variance | 0.133 | +| learning_rate | 4.69e-05 | +| loss | -0.033 | +| n_updates | 40960 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000215 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1421 | +| iterations | 6287 | +| time_elapsed | 9056 | +| total_timesteps | 12875776 | +| train/ | | +| approx_kl | 0.008860706 | +| clip_fraction | 0.292 | +| clip_range | 0.0718 | +| entropy_loss | -7.28 | +| explained_variance | 0.448 | +| learning_rate | 4.69e-05 | +| loss | -0.0343 | +| n_updates | 40964 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000146 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.315 | +| time/ | | +| fps | 1421 | +| iterations | 6288 | +| time_elapsed | 9057 | +| total_timesteps | 12877824 | +| train/ | | +| approx_kl | 0.0101830205 | +| clip_fraction | 0.291 | +| clip_range | 0.0718 | +| entropy_loss | -7.35 | +| explained_variance | 0.103 | +| learning_rate | 4.69e-05 | +| loss | -0.0311 | +| n_updates | 40968 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000163 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1421 | +| iterations | 6289 | +| time_elapsed | 9059 | +| total_timesteps | 12879872 | +| train/ | | +| approx_kl | 0.009585733 | +| clip_fraction | 0.318 | +| clip_range | 0.0718 | +| entropy_loss | -7.02 | +| explained_variance | 0.375 | +| learning_rate | 4.69e-05 | +| loss | -0.0274 | +| n_updates | 40972 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000306 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1421 | +| iterations | 6290 | +| time_elapsed | 9060 | +| total_timesteps | 12881920 | +| train/ | | +| approx_kl | 0.008496704 | +| clip_fraction | 0.278 | +| clip_range | 0.0718 | +| entropy_loss | -6.92 | +| explained_variance | 0.37 | +| learning_rate | 4.69e-05 | +| loss | -0.0299 | +| n_updates | 40976 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000341 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1421 | +| iterations | 6291 | +| time_elapsed | 9062 | +| total_timesteps | 12883968 | +| train/ | | +| approx_kl | 0.01162515 | +| clip_fraction | 0.332 | +| clip_range | 0.0718 | +| entropy_loss | -7.05 | +| explained_variance | 0.293 | +| learning_rate | 4.69e-05 | +| loss | -0.0344 | +| n_updates | 40980 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000169 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1421 | +| iterations | 6292 | +| time_elapsed | 9063 | +| total_timesteps | 12886016 | +| train/ | | +| approx_kl | 0.011453159 | +| clip_fraction | 0.321 | +| clip_range | 0.0718 | +| entropy_loss | -7.08 | +| explained_variance | 0.351 | +| learning_rate | 4.69e-05 | +| loss | -0.029 | +| n_updates | 40984 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000217 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1421 | +| iterations | 6293 | +| time_elapsed | 9065 | +| total_timesteps | 12888064 | +| train/ | | +| approx_kl | 0.011062976 | +| clip_fraction | 0.298 | +| clip_range | 0.0718 | +| entropy_loss | -7.13 | +| explained_variance | 0.29 | +| learning_rate | 4.69e-05 | +| loss | -0.0291 | +| n_updates | 40988 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000215 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1421 | +| iterations | 6294 | +| time_elapsed | 9066 | +| total_timesteps | 12890112 | +| train/ | | +| approx_kl | 0.010819997 | +| clip_fraction | 0.294 | +| clip_range | 0.0718 | +| entropy_loss | -7.19 | +| explained_variance | 0.0695 | +| learning_rate | 4.69e-05 | +| loss | -0.0324 | +| n_updates | 40992 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000267 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1421 | +| iterations | 6295 | +| time_elapsed | 9068 | +| total_timesteps | 12892160 | +| train/ | | +| approx_kl | 0.013370568 | +| clip_fraction | 0.34 | +| clip_range | 0.0718 | +| entropy_loss | -7.27 | +| explained_variance | 0.188 | +| learning_rate | 4.69e-05 | +| loss | -0.0307 | +| n_updates | 40996 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000191 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1421 | +| iterations | 6296 | +| time_elapsed | 9069 | +| total_timesteps | 12894208 | +| train/ | | +| approx_kl | 0.00850868 | +| clip_fraction | 0.304 | +| clip_range | 0.0718 | +| entropy_loss | -7.29 | +| explained_variance | 0.2 | +| learning_rate | 4.69e-05 | +| loss | -0.0166 | +| n_updates | 41000 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000312 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1421 | +| iterations | 6297 | +| time_elapsed | 9071 | +| total_timesteps | 12896256 | +| train/ | | +| approx_kl | 0.010173511 | +| clip_fraction | 0.305 | +| clip_range | 0.0718 | +| entropy_loss | -7.18 | +| explained_variance | 0.303 | +| learning_rate | 4.69e-05 | +| loss | -0.0377 | +| n_updates | 41004 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000131 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1421 | +| iterations | 6298 | +| time_elapsed | 9072 | +| total_timesteps | 12898304 | +| train/ | | +| approx_kl | 0.012017524 | +| clip_fraction | 0.314 | +| clip_range | 0.0718 | +| entropy_loss | -7.14 | +| explained_variance | 0.24 | +| learning_rate | 4.69e-05 | +| loss | -0.0298 | +| n_updates | 41008 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000382 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1421 | +| iterations | 6299 | +| time_elapsed | 9074 | +| total_timesteps | 12900352 | +| train/ | | +| approx_kl | 0.012927831 | +| clip_fraction | 0.337 | +| clip_range | 0.0718 | +| entropy_loss | -7.05 | +| explained_variance | 0.41 | +| learning_rate | 4.69e-05 | +| loss | -0.0334 | +| n_updates | 41012 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000151 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1421 | +| iterations | 6300 | +| time_elapsed | 9075 | +| total_timesteps | 12902400 | +| train/ | | +| approx_kl | 0.011350732 | +| clip_fraction | 0.328 | +| clip_range | 0.0718 | +| entropy_loss | -6.98 | +| explained_variance | 0.566 | +| learning_rate | 4.69e-05 | +| loss | -0.0351 | +| n_updates | 41016 | +| policy_gradient_loss | -0.0213 | +| value_loss | 9.13e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1421 | +| iterations | 6301 | +| time_elapsed | 9076 | +| total_timesteps | 12904448 | +| train/ | | +| approx_kl | 0.011924763 | +| clip_fraction | 0.332 | +| clip_range | 0.0718 | +| entropy_loss | -7.29 | +| explained_variance | 0.399 | +| learning_rate | 4.69e-05 | +| loss | -0.0337 | +| n_updates | 41020 | +| policy_gradient_loss | -0.0216 | +| value_loss | 9.24e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1421 | +| iterations | 6302 | +| time_elapsed | 9078 | +| total_timesteps | 12906496 | +| train/ | | +| approx_kl | 0.008441325 | +| clip_fraction | 0.282 | +| clip_range | 0.0718 | +| entropy_loss | -7.08 | +| explained_variance | 0.357 | +| learning_rate | 4.69e-05 | +| loss | -0.0273 | +| n_updates | 41024 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000233 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1421 | +| iterations | 6303 | +| time_elapsed | 9079 | +| total_timesteps | 12908544 | +| train/ | | +| approx_kl | 0.013177734 | +| clip_fraction | 0.327 | +| clip_range | 0.0718 | +| entropy_loss | -7.42 | +| explained_variance | -0.0196 | +| learning_rate | 4.69e-05 | +| loss | -0.033 | +| n_updates | 41028 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000137 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1421 | +| iterations | 6304 | +| time_elapsed | 9081 | +| total_timesteps | 12910592 | +| train/ | | +| approx_kl | 0.012985328 | +| clip_fraction | 0.341 | +| clip_range | 0.0718 | +| entropy_loss | -7.4 | +| explained_variance | -0.168 | +| learning_rate | 4.69e-05 | +| loss | -0.0322 | +| n_updates | 41032 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000124 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1421 | +| iterations | 6305 | +| time_elapsed | 9082 | +| total_timesteps | 12912640 | +| train/ | | +| approx_kl | 0.009197847 | +| clip_fraction | 0.286 | +| clip_range | 0.0718 | +| entropy_loss | -7.19 | +| explained_variance | 0.391 | +| learning_rate | 4.69e-05 | +| loss | -0.0323 | +| n_updates | 41036 | +| policy_gradient_loss | -0.0148 | +| value_loss | 0.000266 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1421 | +| iterations | 6306 | +| time_elapsed | 9084 | +| total_timesteps | 12914688 | +| train/ | | +| approx_kl | 0.011153419 | +| clip_fraction | 0.312 | +| clip_range | 0.0718 | +| entropy_loss | -7.16 | +| explained_variance | 0.462 | +| learning_rate | 4.69e-05 | +| loss | -0.0374 | +| n_updates | 41040 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000143 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1421 | +| iterations | 6307 | +| time_elapsed | 9085 | +| total_timesteps | 12916736 | +| train/ | | +| approx_kl | 0.011695346 | +| clip_fraction | 0.334 | +| clip_range | 0.0718 | +| entropy_loss | -7.3 | +| explained_variance | 0.349 | +| learning_rate | 4.69e-05 | +| loss | -0.0324 | +| n_updates | 41044 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000132 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1421 | +| iterations | 6308 | +| time_elapsed | 9087 | +| total_timesteps | 12918784 | +| train/ | | +| approx_kl | 0.009306321 | +| clip_fraction | 0.305 | +| clip_range | 0.0718 | +| entropy_loss | -7.15 | +| explained_variance | 0.243 | +| learning_rate | 4.69e-05 | +| loss | -0.025 | +| n_updates | 41048 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.00022 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1421 | +| iterations | 6309 | +| time_elapsed | 9088 | +| total_timesteps | 12920832 | +| train/ | | +| approx_kl | 0.009699394 | +| clip_fraction | 0.289 | +| clip_range | 0.0718 | +| entropy_loss | -6.76 | +| explained_variance | 0.634 | +| learning_rate | 4.69e-05 | +| loss | -0.0282 | +| n_updates | 41052 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000201 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1421 | +| iterations | 6310 | +| time_elapsed | 9090 | +| total_timesteps | 12922880 | +| train/ | | +| approx_kl | 0.01010902 | +| clip_fraction | 0.343 | +| clip_range | 0.0718 | +| entropy_loss | -7.51 | +| explained_variance | 0.00249 | +| learning_rate | 4.69e-05 | +| loss | -0.0348 | +| n_updates | 41056 | +| policy_gradient_loss | -0.0217 | +| value_loss | 9.96e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1421 | +| iterations | 6311 | +| time_elapsed | 9091 | +| total_timesteps | 12924928 | +| train/ | | +| approx_kl | 0.009669272 | +| clip_fraction | 0.323 | +| clip_range | 0.0718 | +| entropy_loss | -7.03 | +| explained_variance | 0.455 | +| learning_rate | 4.69e-05 | +| loss | -0.0361 | +| n_updates | 41060 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000156 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1421 | +| iterations | 6312 | +| time_elapsed | 9093 | +| total_timesteps | 12926976 | +| train/ | | +| approx_kl | 0.01099649 | +| clip_fraction | 0.311 | +| clip_range | 0.0718 | +| entropy_loss | -7.35 | +| explained_variance | 0.49 | +| learning_rate | 4.69e-05 | +| loss | -0.0338 | +| n_updates | 41064 | +| policy_gradient_loss | -0.022 | +| value_loss | 7.2e-05 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1421 | +| iterations | 6313 | +| time_elapsed | 9094 | +| total_timesteps | 12929024 | +| train/ | | +| approx_kl | 0.00818712 | +| clip_fraction | 0.281 | +| clip_range | 0.0718 | +| entropy_loss | -7.36 | +| explained_variance | 0.245 | +| learning_rate | 4.69e-05 | +| loss | -0.026 | +| n_updates | 41068 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000231 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1421 | +| iterations | 6314 | +| time_elapsed | 9095 | +| total_timesteps | 12931072 | +| train/ | | +| approx_kl | 0.008362467 | +| clip_fraction | 0.271 | +| clip_range | 0.0718 | +| entropy_loss | -6.97 | +| explained_variance | 0.441 | +| learning_rate | 4.69e-05 | +| loss | -0.0247 | +| n_updates | 41072 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000301 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1421 | +| iterations | 6315 | +| time_elapsed | 9097 | +| total_timesteps | 12933120 | +| train/ | | +| approx_kl | 0.011198099 | +| clip_fraction | 0.341 | +| clip_range | 0.0718 | +| entropy_loss | -6.79 | +| explained_variance | 0.609 | +| learning_rate | 4.69e-05 | +| loss | -0.0323 | +| n_updates | 41076 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000135 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1421 | +| iterations | 6316 | +| time_elapsed | 9098 | +| total_timesteps | 12935168 | +| train/ | | +| approx_kl | 0.012071678 | +| clip_fraction | 0.313 | +| clip_range | 0.0718 | +| entropy_loss | -7.01 | +| explained_variance | 0.528 | +| learning_rate | 4.69e-05 | +| loss | -0.029 | +| n_updates | 41080 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000122 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1421 | +| iterations | 6317 | +| time_elapsed | 9100 | +| total_timesteps | 12937216 | +| train/ | | +| approx_kl | 0.011615289 | +| clip_fraction | 0.319 | +| clip_range | 0.0718 | +| entropy_loss | -7.1 | +| explained_variance | 0.532 | +| learning_rate | 4.69e-05 | +| loss | -0.0329 | +| n_updates | 41084 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000125 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1421 | +| iterations | 6318 | +| time_elapsed | 9101 | +| total_timesteps | 12939264 | +| train/ | | +| approx_kl | 0.01253284 | +| clip_fraction | 0.296 | +| clip_range | 0.0718 | +| entropy_loss | -7.43 | +| explained_variance | -0.0322 | +| learning_rate | 4.69e-05 | +| loss | -0.0292 | +| n_updates | 41088 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000283 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1421 | +| iterations | 6319 | +| time_elapsed | 9103 | +| total_timesteps | 12941312 | +| train/ | | +| approx_kl | 0.009383913 | +| clip_fraction | 0.308 | +| clip_range | 0.0718 | +| entropy_loss | -7.3 | +| explained_variance | 0.178 | +| learning_rate | 4.69e-05 | +| loss | -0.0325 | +| n_updates | 41092 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000175 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1421 | +| iterations | 6320 | +| time_elapsed | 9104 | +| total_timesteps | 12943360 | +| train/ | | +| approx_kl | 0.011346123 | +| clip_fraction | 0.301 | +| clip_range | 0.0718 | +| entropy_loss | -7.61 | +| explained_variance | -0.174 | +| learning_rate | 4.69e-05 | +| loss | -0.0314 | +| n_updates | 41096 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000139 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1421 | +| iterations | 6321 | +| time_elapsed | 9105 | +| total_timesteps | 12945408 | +| train/ | | +| approx_kl | 0.012151938 | +| clip_fraction | 0.333 | +| clip_range | 0.0718 | +| entropy_loss | -7.51 | +| explained_variance | -0.0482 | +| learning_rate | 4.69e-05 | +| loss | -0.0341 | +| n_updates | 41100 | +| policy_gradient_loss | -0.0223 | +| value_loss | 8.55e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1421 | +| iterations | 6322 | +| time_elapsed | 9107 | +| total_timesteps | 12947456 | +| train/ | | +| approx_kl | 0.010368359 | +| clip_fraction | 0.291 | +| clip_range | 0.0718 | +| entropy_loss | -7.13 | +| explained_variance | 0.428 | +| learning_rate | 4.69e-05 | +| loss | -0.0294 | +| n_updates | 41104 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000147 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1421 | +| iterations | 6323 | +| time_elapsed | 9108 | +| total_timesteps | 12949504 | +| train/ | | +| approx_kl | 0.010580136 | +| clip_fraction | 0.322 | +| clip_range | 0.0718 | +| entropy_loss | -7.05 | +| explained_variance | 0.683 | +| learning_rate | 4.69e-05 | +| loss | -0.0302 | +| n_updates | 41108 | +| policy_gradient_loss | -0.0184 | +| value_loss | 9.48e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1421 | +| iterations | 6324 | +| time_elapsed | 9110 | +| total_timesteps | 12951552 | +| train/ | | +| approx_kl | 0.010516336 | +| clip_fraction | 0.311 | +| clip_range | 0.0718 | +| entropy_loss | -7.2 | +| explained_variance | 0.575 | +| learning_rate | 4.69e-05 | +| loss | -0.0286 | +| n_updates | 41112 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000111 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1421 | +| iterations | 6325 | +| time_elapsed | 9111 | +| total_timesteps | 12953600 | +| train/ | | +| approx_kl | 0.012239793 | +| clip_fraction | 0.339 | +| clip_range | 0.0718 | +| entropy_loss | -7.13 | +| explained_variance | 0.593 | +| learning_rate | 4.69e-05 | +| loss | -0.0338 | +| n_updates | 41116 | +| policy_gradient_loss | -0.0223 | +| value_loss | 6.36e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1421 | +| iterations | 6326 | +| time_elapsed | 9113 | +| total_timesteps | 12955648 | +| train/ | | +| approx_kl | 0.009284789 | +| clip_fraction | 0.282 | +| clip_range | 0.0718 | +| entropy_loss | -7.05 | +| explained_variance | 0.435 | +| learning_rate | 4.69e-05 | +| loss | -0.0228 | +| n_updates | 41120 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000168 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1421 | +| iterations | 6327 | +| time_elapsed | 9114 | +| total_timesteps | 12957696 | +| train/ | | +| approx_kl | 0.010018912 | +| clip_fraction | 0.307 | +| clip_range | 0.0718 | +| entropy_loss | -7.24 | +| explained_variance | 0.219 | +| learning_rate | 4.69e-05 | +| loss | -0.0309 | +| n_updates | 41124 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000246 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1421 | +| iterations | 6328 | +| time_elapsed | 9116 | +| total_timesteps | 12959744 | +| train/ | | +| approx_kl | 0.012084238 | +| clip_fraction | 0.329 | +| clip_range | 0.0718 | +| entropy_loss | -7.32 | +| explained_variance | 0.3 | +| learning_rate | 4.69e-05 | +| loss | -0.0365 | +| n_updates | 41128 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000118 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1421 | +| iterations | 6329 | +| time_elapsed | 9117 | +| total_timesteps | 12961792 | +| train/ | | +| approx_kl | 0.010377556 | +| clip_fraction | 0.299 | +| clip_range | 0.0718 | +| entropy_loss | -7.17 | +| explained_variance | 0.169 | +| learning_rate | 4.69e-05 | +| loss | -0.0258 | +| n_updates | 41132 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000336 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1421 | +| iterations | 6330 | +| time_elapsed | 9118 | +| total_timesteps | 12963840 | +| train/ | | +| approx_kl | 0.009665748 | +| clip_fraction | 0.312 | +| clip_range | 0.0718 | +| entropy_loss | -7.48 | +| explained_variance | -0.195 | +| learning_rate | 4.69e-05 | +| loss | -0.0345 | +| n_updates | 41136 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000157 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1421 | +| iterations | 6331 | +| time_elapsed | 9120 | +| total_timesteps | 12965888 | +| train/ | | +| approx_kl | 0.010946898 | +| clip_fraction | 0.328 | +| clip_range | 0.0718 | +| entropy_loss | -6.97 | +| explained_variance | 0.495 | +| learning_rate | 4.69e-05 | +| loss | -0.0328 | +| n_updates | 41140 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000188 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1421 | +| iterations | 6332 | +| time_elapsed | 9121 | +| total_timesteps | 12967936 | +| train/ | | +| approx_kl | 0.011141505 | +| clip_fraction | 0.329 | +| clip_range | 0.0718 | +| entropy_loss | -7.27 | +| explained_variance | 0.284 | +| learning_rate | 4.69e-05 | +| loss | -0.0288 | +| n_updates | 41144 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000157 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1421 | +| iterations | 6333 | +| time_elapsed | 9123 | +| total_timesteps | 12969984 | +| train/ | | +| approx_kl | 0.011264745 | +| clip_fraction | 0.322 | +| clip_range | 0.0718 | +| entropy_loss | -7.38 | +| explained_variance | 0.264 | +| learning_rate | 4.69e-05 | +| loss | -0.0342 | +| n_updates | 41148 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000158 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1421 | +| iterations | 6334 | +| time_elapsed | 9124 | +| total_timesteps | 12972032 | +| train/ | | +| approx_kl | 0.013187974 | +| clip_fraction | 0.293 | +| clip_range | 0.0718 | +| entropy_loss | -6.97 | +| explained_variance | 0.378 | +| learning_rate | 4.69e-05 | +| loss | -0.0236 | +| n_updates | 41152 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000213 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1421 | +| iterations | 6335 | +| time_elapsed | 9125 | +| total_timesteps | 12974080 | +| train/ | | +| approx_kl | 0.010059943 | +| clip_fraction | 0.31 | +| clip_range | 0.0718 | +| entropy_loss | -6.89 | +| explained_variance | 0.358 | +| learning_rate | 4.69e-05 | +| loss | -0.0227 | +| n_updates | 41156 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000367 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1421 | +| iterations | 6336 | +| time_elapsed | 9127 | +| total_timesteps | 12976128 | +| train/ | | +| approx_kl | 0.009744595 | +| clip_fraction | 0.296 | +| clip_range | 0.0718 | +| entropy_loss | -7.28 | +| explained_variance | 0.392 | +| learning_rate | 4.69e-05 | +| loss | -0.031 | +| n_updates | 41160 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000163 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1421 | +| iterations | 6337 | +| time_elapsed | 9128 | +| total_timesteps | 12978176 | +| train/ | | +| approx_kl | 0.009908766 | +| clip_fraction | 0.301 | +| clip_range | 0.0718 | +| entropy_loss | -6.96 | +| explained_variance | 0.501 | +| learning_rate | 4.69e-05 | +| loss | -0.032 | +| n_updates | 41164 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000198 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1421 | +| iterations | 6338 | +| time_elapsed | 9130 | +| total_timesteps | 12980224 | +| train/ | | +| approx_kl | 0.008263322 | +| clip_fraction | 0.299 | +| clip_range | 0.0718 | +| entropy_loss | -7.18 | +| explained_variance | 0.558 | +| learning_rate | 4.69e-05 | +| loss | -0.0317 | +| n_updates | 41168 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000156 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1421 | +| iterations | 6339 | +| time_elapsed | 9131 | +| total_timesteps | 12982272 | +| train/ | | +| approx_kl | 0.008668913 | +| clip_fraction | 0.261 | +| clip_range | 0.0718 | +| entropy_loss | -7.24 | +| explained_variance | 0.226 | +| learning_rate | 4.69e-05 | +| loss | -0.0231 | +| n_updates | 41172 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000196 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1421 | +| iterations | 6340 | +| time_elapsed | 9133 | +| total_timesteps | 12984320 | +| train/ | | +| approx_kl | 0.009418776 | +| clip_fraction | 0.314 | +| clip_range | 0.0718 | +| entropy_loss | -7.23 | +| explained_variance | 0.444 | +| learning_rate | 4.69e-05 | +| loss | -0.0363 | +| n_updates | 41176 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000172 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1421 | +| iterations | 6341 | +| time_elapsed | 9134 | +| total_timesteps | 12986368 | +| train/ | | +| approx_kl | 0.009518316 | +| clip_fraction | 0.308 | +| clip_range | 0.0718 | +| entropy_loss | -7.25 | +| explained_variance | 0.144 | +| learning_rate | 4.69e-05 | +| loss | -0.0234 | +| n_updates | 41180 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000332 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1421 | +| iterations | 6342 | +| time_elapsed | 9135 | +| total_timesteps | 12988416 | +| train/ | | +| approx_kl | 0.011335378 | +| clip_fraction | 0.324 | +| clip_range | 0.0718 | +| entropy_loss | -7.24 | +| explained_variance | 0.425 | +| learning_rate | 4.69e-05 | +| loss | -0.0321 | +| n_updates | 41184 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000184 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1421 | +| iterations | 6343 | +| time_elapsed | 9137 | +| total_timesteps | 12990464 | +| train/ | | +| approx_kl | 0.009990411 | +| clip_fraction | 0.344 | +| clip_range | 0.0718 | +| entropy_loss | -7.32 | +| explained_variance | 0.356 | +| learning_rate | 4.69e-05 | +| loss | -0.0418 | +| n_updates | 41188 | +| policy_gradient_loss | -0.0251 | +| value_loss | 8.1e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1421 | +| iterations | 6344 | +| time_elapsed | 9138 | +| total_timesteps | 12992512 | +| train/ | | +| approx_kl | 0.009340091 | +| clip_fraction | 0.32 | +| clip_range | 0.0718 | +| entropy_loss | -7.21 | +| explained_variance | 0.426 | +| learning_rate | 4.69e-05 | +| loss | -0.0327 | +| n_updates | 41192 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000198 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1421 | +| iterations | 6345 | +| time_elapsed | 9140 | +| total_timesteps | 12994560 | +| train/ | | +| approx_kl | 0.009919314 | +| clip_fraction | 0.311 | +| clip_range | 0.0718 | +| entropy_loss | -6.94 | +| explained_variance | 0.517 | +| learning_rate | 4.69e-05 | +| loss | -0.0363 | +| n_updates | 41196 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000144 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1421 | +| iterations | 6346 | +| time_elapsed | 9141 | +| total_timesteps | 12996608 | +| train/ | | +| approx_kl | 0.009811259 | +| clip_fraction | 0.312 | +| clip_range | 0.0718 | +| entropy_loss | -6.76 | +| explained_variance | 0.392 | +| learning_rate | 4.69e-05 | +| loss | -0.0235 | +| n_updates | 41200 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000311 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1421 | +| iterations | 6347 | +| time_elapsed | 9143 | +| total_timesteps | 12998656 | +| train/ | | +| approx_kl | 0.010873307 | +| clip_fraction | 0.32 | +| clip_range | 0.0718 | +| entropy_loss | -7.13 | +| explained_variance | 0.394 | +| learning_rate | 4.69e-05 | +| loss | -0.0337 | +| n_updates | 41204 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000182 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1421 | +| iterations | 6348 | +| time_elapsed | 9144 | +| total_timesteps | 13000704 | +| train/ | | +| approx_kl | 0.013520057 | +| clip_fraction | 0.318 | +| clip_range | 0.0718 | +| entropy_loss | -7.39 | +| explained_variance | -0.0727 | +| learning_rate | 4.69e-05 | +| loss | -0.033 | +| n_updates | 41208 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000194 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1421 | +| iterations | 6349 | +| time_elapsed | 9146 | +| total_timesteps | 13002752 | +| train/ | | +| approx_kl | 0.011229801 | +| clip_fraction | 0.332 | +| clip_range | 0.0717 | +| entropy_loss | -7.11 | +| explained_variance | 0.709 | +| learning_rate | 4.69e-05 | +| loss | -0.0345 | +| n_updates | 41212 | +| policy_gradient_loss | -0.0225 | +| value_loss | 5.81e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1421 | +| iterations | 6350 | +| time_elapsed | 9147 | +| total_timesteps | 13004800 | +| train/ | | +| approx_kl | 0.010962531 | +| clip_fraction | 0.322 | +| clip_range | 0.0717 | +| entropy_loss | -7.18 | +| explained_variance | 0.366 | +| learning_rate | 4.69e-05 | +| loss | -0.0221 | +| n_updates | 41216 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000126 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1421 | +| iterations | 6351 | +| time_elapsed | 9148 | +| total_timesteps | 13006848 | +| train/ | | +| approx_kl | 0.011359534 | +| clip_fraction | 0.316 | +| clip_range | 0.0717 | +| entropy_loss | -7.49 | +| explained_variance | -0.0556 | +| learning_rate | 4.69e-05 | +| loss | -0.0295 | +| n_updates | 41220 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000143 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1421 | +| iterations | 6352 | +| time_elapsed | 9150 | +| total_timesteps | 13008896 | +| train/ | | +| approx_kl | 0.009987212 | +| clip_fraction | 0.299 | +| clip_range | 0.0717 | +| entropy_loss | -7.17 | +| explained_variance | 0.533 | +| learning_rate | 4.69e-05 | +| loss | -0.032 | +| n_updates | 41224 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000138 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1421 | +| iterations | 6353 | +| time_elapsed | 9151 | +| total_timesteps | 13010944 | +| train/ | | +| approx_kl | 0.0112151485 | +| clip_fraction | 0.326 | +| clip_range | 0.0717 | +| entropy_loss | -7.23 | +| explained_variance | 0.298 | +| learning_rate | 4.69e-05 | +| loss | -0.036 | +| n_updates | 41228 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000143 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1421 | +| iterations | 6354 | +| time_elapsed | 9153 | +| total_timesteps | 13012992 | +| train/ | | +| approx_kl | 0.010631115 | +| clip_fraction | 0.3 | +| clip_range | 0.0717 | +| entropy_loss | -7.36 | +| explained_variance | 0.274 | +| learning_rate | 4.69e-05 | +| loss | -0.0338 | +| n_updates | 41232 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000173 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1421 | +| iterations | 6355 | +| time_elapsed | 9154 | +| total_timesteps | 13015040 | +| train/ | | +| approx_kl | 0.010488094 | +| clip_fraction | 0.309 | +| clip_range | 0.0717 | +| entropy_loss | -7.32 | +| explained_variance | 0.468 | +| learning_rate | 4.69e-05 | +| loss | -0.032 | +| n_updates | 41236 | +| policy_gradient_loss | -0.0206 | +| value_loss | 9.53e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1421 | +| iterations | 6356 | +| time_elapsed | 9156 | +| total_timesteps | 13017088 | +| train/ | | +| approx_kl | 0.010291174 | +| clip_fraction | 0.327 | +| clip_range | 0.0717 | +| entropy_loss | -7.28 | +| explained_variance | 0.331 | +| learning_rate | 4.69e-05 | +| loss | -0.0346 | +| n_updates | 41240 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000162 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1421 | +| iterations | 6357 | +| time_elapsed | 9157 | +| total_timesteps | 13019136 | +| train/ | | +| approx_kl | 0.009042898 | +| clip_fraction | 0.262 | +| clip_range | 0.0717 | +| entropy_loss | -7.22 | +| explained_variance | 0.258 | +| learning_rate | 4.69e-05 | +| loss | -0.0239 | +| n_updates | 41244 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.000399 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1421 | +| iterations | 6358 | +| time_elapsed | 9158 | +| total_timesteps | 13021184 | +| train/ | | +| approx_kl | 0.011482777 | +| clip_fraction | 0.331 | +| clip_range | 0.0717 | +| entropy_loss | -6.5 | +| explained_variance | 0.768 | +| learning_rate | 4.69e-05 | +| loss | -0.0388 | +| n_updates | 41248 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000106 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1421 | +| iterations | 6359 | +| time_elapsed | 9160 | +| total_timesteps | 13023232 | +| train/ | | +| approx_kl | 0.0129816905 | +| clip_fraction | 0.346 | +| clip_range | 0.0717 | +| entropy_loss | -7.09 | +| explained_variance | 0.548 | +| learning_rate | 4.69e-05 | +| loss | -0.034 | +| n_updates | 41252 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000122 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1421 | +| iterations | 6360 | +| time_elapsed | 9161 | +| total_timesteps | 13025280 | +| train/ | | +| approx_kl | 0.011540322 | +| clip_fraction | 0.338 | +| clip_range | 0.0717 | +| entropy_loss | -7.26 | +| explained_variance | 0.401 | +| learning_rate | 4.69e-05 | +| loss | -0.0334 | +| n_updates | 41256 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000117 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1421 | +| iterations | 6361 | +| time_elapsed | 9163 | +| total_timesteps | 13027328 | +| train/ | | +| approx_kl | 0.011390802 | +| clip_fraction | 0.305 | +| clip_range | 0.0717 | +| entropy_loss | -7.25 | +| explained_variance | 0.2 | +| learning_rate | 4.69e-05 | +| loss | -0.0284 | +| n_updates | 41260 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000229 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1421 | +| iterations | 6362 | +| time_elapsed | 9164 | +| total_timesteps | 13029376 | +| train/ | | +| approx_kl | 0.008935681 | +| clip_fraction | 0.287 | +| clip_range | 0.0717 | +| entropy_loss | -7.09 | +| explained_variance | 0.487 | +| learning_rate | 4.69e-05 | +| loss | -0.0303 | +| n_updates | 41264 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000196 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1421 | +| iterations | 6363 | +| time_elapsed | 9165 | +| total_timesteps | 13031424 | +| train/ | | +| approx_kl | 0.008590305 | +| clip_fraction | 0.278 | +| clip_range | 0.0717 | +| entropy_loss | -7.33 | +| explained_variance | 0.187 | +| learning_rate | 4.69e-05 | +| loss | -0.0294 | +| n_updates | 41268 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000306 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1421 | +| iterations | 6364 | +| time_elapsed | 9167 | +| total_timesteps | 13033472 | +| train/ | | +| approx_kl | 0.011736694 | +| clip_fraction | 0.31 | +| clip_range | 0.0717 | +| entropy_loss | -7.03 | +| explained_variance | 0.335 | +| learning_rate | 4.69e-05 | +| loss | -0.0249 | +| n_updates | 41272 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000272 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1421 | +| iterations | 6365 | +| time_elapsed | 9168 | +| total_timesteps | 13035520 | +| train/ | | +| approx_kl | 0.00983058 | +| clip_fraction | 0.311 | +| clip_range | 0.0717 | +| entropy_loss | -7.47 | +| explained_variance | -0.21 | +| learning_rate | 4.69e-05 | +| loss | -0.0349 | +| n_updates | 41276 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000247 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1421 | +| iterations | 6366 | +| time_elapsed | 9170 | +| total_timesteps | 13037568 | +| train/ | | +| approx_kl | 0.010186223 | +| clip_fraction | 0.32 | +| clip_range | 0.0717 | +| entropy_loss | -7.14 | +| explained_variance | 0.212 | +| learning_rate | 4.69e-05 | +| loss | -0.0322 | +| n_updates | 41280 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000146 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1421 | +| iterations | 6367 | +| time_elapsed | 9171 | +| total_timesteps | 13039616 | +| train/ | | +| approx_kl | 0.010481889 | +| clip_fraction | 0.339 | +| clip_range | 0.0717 | +| entropy_loss | -6.78 | +| explained_variance | 0.7 | +| learning_rate | 4.69e-05 | +| loss | -0.0329 | +| n_updates | 41284 | +| policy_gradient_loss | -0.0182 | +| value_loss | 7.95e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1421 | +| iterations | 6368 | +| time_elapsed | 9173 | +| total_timesteps | 13041664 | +| train/ | | +| approx_kl | 0.009401597 | +| clip_fraction | 0.32 | +| clip_range | 0.0717 | +| entropy_loss | -7.4 | +| explained_variance | 0.139 | +| learning_rate | 4.69e-05 | +| loss | -0.0301 | +| n_updates | 41288 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000143 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1421 | +| iterations | 6369 | +| time_elapsed | 9174 | +| total_timesteps | 13043712 | +| train/ | | +| approx_kl | 0.010097148 | +| clip_fraction | 0.323 | +| clip_range | 0.0717 | +| entropy_loss | -7.15 | +| explained_variance | 0.528 | +| learning_rate | 4.69e-05 | +| loss | -0.0358 | +| n_updates | 41292 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000117 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1421 | +| iterations | 6370 | +| time_elapsed | 9176 | +| total_timesteps | 13045760 | +| train/ | | +| approx_kl | 0.007978561 | +| clip_fraction | 0.291 | +| clip_range | 0.0717 | +| entropy_loss | -7.52 | +| explained_variance | 0.000231 | +| learning_rate | 4.69e-05 | +| loss | -0.0289 | +| n_updates | 41296 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000159 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1421 | +| iterations | 6371 | +| time_elapsed | 9177 | +| total_timesteps | 13047808 | +| train/ | | +| approx_kl | 0.008359598 | +| clip_fraction | 0.275 | +| clip_range | 0.0717 | +| entropy_loss | -7.43 | +| explained_variance | -0.128 | +| learning_rate | 4.69e-05 | +| loss | -0.029 | +| n_updates | 41300 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000177 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1421 | +| iterations | 6372 | +| time_elapsed | 9178 | +| total_timesteps | 13049856 | +| train/ | | +| approx_kl | 0.010031802 | +| clip_fraction | 0.3 | +| clip_range | 0.0717 | +| entropy_loss | -7.1 | +| explained_variance | 0.463 | +| learning_rate | 4.69e-05 | +| loss | -0.0301 | +| n_updates | 41304 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000154 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1421 | +| iterations | 6373 | +| time_elapsed | 9180 | +| total_timesteps | 13051904 | +| train/ | | +| approx_kl | 0.012430957 | +| clip_fraction | 0.321 | +| clip_range | 0.0717 | +| entropy_loss | -7.02 | +| explained_variance | 0.535 | +| learning_rate | 4.69e-05 | +| loss | -0.0311 | +| n_updates | 41308 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000121 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1421 | +| iterations | 6374 | +| time_elapsed | 9181 | +| total_timesteps | 13053952 | +| train/ | | +| approx_kl | 0.010243044 | +| clip_fraction | 0.288 | +| clip_range | 0.0717 | +| entropy_loss | -7.28 | +| explained_variance | 0.22 | +| learning_rate | 4.69e-05 | +| loss | -0.0286 | +| n_updates | 41312 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000249 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1421 | +| iterations | 6375 | +| time_elapsed | 9183 | +| total_timesteps | 13056000 | +| train/ | | +| approx_kl | 0.009249664 | +| clip_fraction | 0.314 | +| clip_range | 0.0717 | +| entropy_loss | -7.5 | +| explained_variance | 0.0607 | +| learning_rate | 4.69e-05 | +| loss | -0.0333 | +| n_updates | 41316 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000172 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1421 | +| iterations | 6376 | +| time_elapsed | 9184 | +| total_timesteps | 13058048 | +| train/ | | +| approx_kl | 0.008305393 | +| clip_fraction | 0.292 | +| clip_range | 0.0717 | +| entropy_loss | -6.71 | +| explained_variance | 0.61 | +| learning_rate | 4.69e-05 | +| loss | -0.0267 | +| n_updates | 41320 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000152 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1421 | +| iterations | 6377 | +| time_elapsed | 9185 | +| total_timesteps | 13060096 | +| train/ | | +| approx_kl | 0.0114405565 | +| clip_fraction | 0.329 | +| clip_range | 0.0717 | +| entropy_loss | -7.03 | +| explained_variance | 0.502 | +| learning_rate | 4.69e-05 | +| loss | -0.0281 | +| n_updates | 41324 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000151 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1421 | +| iterations | 6378 | +| time_elapsed | 9187 | +| total_timesteps | 13062144 | +| train/ | | +| approx_kl | 0.009586493 | +| clip_fraction | 0.308 | +| clip_range | 0.0717 | +| entropy_loss | -6.89 | +| explained_variance | 0.714 | +| learning_rate | 4.69e-05 | +| loss | -0.0442 | +| n_updates | 41328 | +| policy_gradient_loss | -0.0183 | +| value_loss | 9.31e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1421 | +| iterations | 6379 | +| time_elapsed | 9188 | +| total_timesteps | 13064192 | +| train/ | | +| approx_kl | 0.012206261 | +| clip_fraction | 0.324 | +| clip_range | 0.0717 | +| entropy_loss | -7.27 | +| explained_variance | 0.355 | +| learning_rate | 4.69e-05 | +| loss | -0.0308 | +| n_updates | 41332 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000137 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1421 | +| iterations | 6380 | +| time_elapsed | 9190 | +| total_timesteps | 13066240 | +| train/ | | +| approx_kl | 0.008882121 | +| clip_fraction | 0.305 | +| clip_range | 0.0717 | +| entropy_loss | -7.28 | +| explained_variance | 0.166 | +| learning_rate | 4.69e-05 | +| loss | -0.0329 | +| n_updates | 41336 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000283 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1421 | +| iterations | 6381 | +| time_elapsed | 9191 | +| total_timesteps | 13068288 | +| train/ | | +| approx_kl | 0.011198519 | +| clip_fraction | 0.331 | +| clip_range | 0.0717 | +| entropy_loss | -7.51 | +| explained_variance | -0.0781 | +| learning_rate | 4.69e-05 | +| loss | -0.0343 | +| n_updates | 41340 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000157 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1421 | +| iterations | 6382 | +| time_elapsed | 9193 | +| total_timesteps | 13070336 | +| train/ | | +| approx_kl | 0.007872852 | +| clip_fraction | 0.3 | +| clip_range | 0.0717 | +| entropy_loss | -7.29 | +| explained_variance | 0.167 | +| learning_rate | 4.69e-05 | +| loss | -0.0313 | +| n_updates | 41344 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000262 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1421 | +| iterations | 6383 | +| time_elapsed | 9194 | +| total_timesteps | 13072384 | +| train/ | | +| approx_kl | 0.007280137 | +| clip_fraction | 0.285 | +| clip_range | 0.0717 | +| entropy_loss | -7.19 | +| explained_variance | 0.385 | +| learning_rate | 4.69e-05 | +| loss | -0.0321 | +| n_updates | 41348 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000221 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1421 | +| iterations | 6384 | +| time_elapsed | 9195 | +| total_timesteps | 13074432 | +| train/ | | +| approx_kl | 0.010744534 | +| clip_fraction | 0.331 | +| clip_range | 0.0717 | +| entropy_loss | -7.3 | +| explained_variance | 0.365 | +| learning_rate | 4.69e-05 | +| loss | -0.038 | +| n_updates | 41352 | +| policy_gradient_loss | -0.0229 | +| value_loss | 8.15e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1421 | +| iterations | 6385 | +| time_elapsed | 9197 | +| total_timesteps | 13076480 | +| train/ | | +| approx_kl | 0.010832507 | +| clip_fraction | 0.304 | +| clip_range | 0.0717 | +| entropy_loss | -7.15 | +| explained_variance | 0.155 | +| learning_rate | 4.69e-05 | +| loss | -0.0332 | +| n_updates | 41356 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000188 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1421 | +| iterations | 6386 | +| time_elapsed | 9198 | +| total_timesteps | 13078528 | +| train/ | | +| approx_kl | 0.011894925 | +| clip_fraction | 0.335 | +| clip_range | 0.0717 | +| entropy_loss | -7.04 | +| explained_variance | 0.617 | +| learning_rate | 4.69e-05 | +| loss | -0.0346 | +| n_updates | 41360 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000106 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1421 | +| iterations | 6387 | +| time_elapsed | 9200 | +| total_timesteps | 13080576 | +| train/ | | +| approx_kl | 0.011762027 | +| clip_fraction | 0.302 | +| clip_range | 0.0717 | +| entropy_loss | -7.1 | +| explained_variance | 0.409 | +| learning_rate | 4.69e-05 | +| loss | -0.0291 | +| n_updates | 41364 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000195 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1421 | +| iterations | 6388 | +| time_elapsed | 9201 | +| total_timesteps | 13082624 | +| train/ | | +| approx_kl | 0.009405625 | +| clip_fraction | 0.29 | +| clip_range | 0.0717 | +| entropy_loss | -7.25 | +| explained_variance | 0.324 | +| learning_rate | 4.69e-05 | +| loss | -0.0265 | +| n_updates | 41368 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000134 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1421 | +| iterations | 6389 | +| time_elapsed | 9202 | +| total_timesteps | 13084672 | +| train/ | | +| approx_kl | 0.012974228 | +| clip_fraction | 0.328 | +| clip_range | 0.0717 | +| entropy_loss | -7.11 | +| explained_variance | 0.687 | +| learning_rate | 4.69e-05 | +| loss | -0.0382 | +| n_updates | 41372 | +| policy_gradient_loss | -0.0241 | +| value_loss | 5.8e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1421 | +| iterations | 6390 | +| time_elapsed | 9204 | +| total_timesteps | 13086720 | +| train/ | | +| approx_kl | 0.009559248 | +| clip_fraction | 0.304 | +| clip_range | 0.0717 | +| entropy_loss | -7.04 | +| explained_variance | 0.454 | +| learning_rate | 4.69e-05 | +| loss | -0.0289 | +| n_updates | 41376 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000161 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1421 | +| iterations | 6391 | +| time_elapsed | 9205 | +| total_timesteps | 13088768 | +| train/ | | +| approx_kl | 0.010701982 | +| clip_fraction | 0.364 | +| clip_range | 0.0717 | +| entropy_loss | -7.41 | +| explained_variance | -0.56 | +| learning_rate | 4.69e-05 | +| loss | -0.0407 | +| n_updates | 41380 | +| policy_gradient_loss | -0.0267 | +| value_loss | 5.55e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1421 | +| iterations | 6392 | +| time_elapsed | 9207 | +| total_timesteps | 13090816 | +| train/ | | +| approx_kl | 0.014309745 | +| clip_fraction | 0.322 | +| clip_range | 0.0717 | +| entropy_loss | -6.88 | +| explained_variance | 0.448 | +| learning_rate | 4.69e-05 | +| loss | -0.0315 | +| n_updates | 41384 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000234 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1421 | +| iterations | 6393 | +| time_elapsed | 9208 | +| total_timesteps | 13092864 | +| train/ | | +| approx_kl | 0.013394708 | +| clip_fraction | 0.332 | +| clip_range | 0.0717 | +| entropy_loss | -7.23 | +| explained_variance | 0.477 | +| learning_rate | 4.69e-05 | +| loss | -0.0316 | +| n_updates | 41388 | +| policy_gradient_loss | -0.0214 | +| value_loss | 8.51e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1421 | +| iterations | 6394 | +| time_elapsed | 9210 | +| total_timesteps | 13094912 | +| train/ | | +| approx_kl | 0.011843642 | +| clip_fraction | 0.322 | +| clip_range | 0.0717 | +| entropy_loss | -6.94 | +| explained_variance | 0.326 | +| learning_rate | 4.69e-05 | +| loss | -0.0288 | +| n_updates | 41392 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.00023 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1421 | +| iterations | 6395 | +| time_elapsed | 9211 | +| total_timesteps | 13096960 | +| train/ | | +| approx_kl | 0.009559105 | +| clip_fraction | 0.307 | +| clip_range | 0.0717 | +| entropy_loss | -7.03 | +| explained_variance | 0.359 | +| learning_rate | 4.69e-05 | +| loss | -0.0325 | +| n_updates | 41396 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000194 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1421 | +| iterations | 6396 | +| time_elapsed | 9213 | +| total_timesteps | 13099008 | +| train/ | | +| approx_kl | 0.011176232 | +| clip_fraction | 0.305 | +| clip_range | 0.0717 | +| entropy_loss | -7.28 | +| explained_variance | 0.233 | +| learning_rate | 4.69e-05 | +| loss | -0.0299 | +| n_updates | 41400 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000193 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1421 | +| iterations | 6397 | +| time_elapsed | 9214 | +| total_timesteps | 13101056 | +| train/ | | +| approx_kl | 0.010209782 | +| clip_fraction | 0.284 | +| clip_range | 0.0717 | +| entropy_loss | -7.03 | +| explained_variance | 0.39 | +| learning_rate | 4.69e-05 | +| loss | -0.0297 | +| n_updates | 41404 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000184 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1421 | +| iterations | 6398 | +| time_elapsed | 9215 | +| total_timesteps | 13103104 | +| train/ | | +| approx_kl | 0.011095349 | +| clip_fraction | 0.31 | +| clip_range | 0.0717 | +| entropy_loss | -7.26 | +| explained_variance | 0.229 | +| learning_rate | 4.69e-05 | +| loss | -0.0287 | +| n_updates | 41408 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000151 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1421 | +| iterations | 6399 | +| time_elapsed | 9217 | +| total_timesteps | 13105152 | +| train/ | | +| approx_kl | 0.010037109 | +| clip_fraction | 0.268 | +| clip_range | 0.0717 | +| entropy_loss | -7.03 | +| explained_variance | 0.292 | +| learning_rate | 4.69e-05 | +| loss | -0.0323 | +| n_updates | 41412 | +| policy_gradient_loss | -0.0147 | +| value_loss | 0.000357 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1421 | +| iterations | 6400 | +| time_elapsed | 9218 | +| total_timesteps | 13107200 | +| train/ | | +| approx_kl | 0.011385258 | +| clip_fraction | 0.313 | +| clip_range | 0.0717 | +| entropy_loss | -6.84 | +| explained_variance | 0.52 | +| learning_rate | 4.69e-05 | +| loss | -0.0323 | +| n_updates | 41416 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.0002 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1421 | +| iterations | 6401 | +| time_elapsed | 9220 | +| total_timesteps | 13109248 | +| train/ | | +| approx_kl | 0.012957341 | +| clip_fraction | 0.344 | +| clip_range | 0.0717 | +| entropy_loss | -7.06 | +| explained_variance | 0.469 | +| learning_rate | 4.69e-05 | +| loss | -0.0399 | +| n_updates | 41420 | +| policy_gradient_loss | -0.0228 | +| value_loss | 9.07e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1421 | +| iterations | 6402 | +| time_elapsed | 9221 | +| total_timesteps | 13111296 | +| train/ | | +| approx_kl | 0.0104357265 | +| clip_fraction | 0.333 | +| clip_range | 0.0717 | +| entropy_loss | -7.01 | +| explained_variance | 0.344 | +| learning_rate | 4.69e-05 | +| loss | -0.0269 | +| n_updates | 41424 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000238 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1421 | +| iterations | 6403 | +| time_elapsed | 9223 | +| total_timesteps | 13113344 | +| train/ | | +| approx_kl | 0.010850741 | +| clip_fraction | 0.315 | +| clip_range | 0.0717 | +| entropy_loss | -6.89 | +| explained_variance | 0.383 | +| learning_rate | 4.69e-05 | +| loss | -0.0343 | +| n_updates | 41428 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000258 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1421 | +| iterations | 6404 | +| time_elapsed | 9224 | +| total_timesteps | 13115392 | +| train/ | | +| approx_kl | 0.011651928 | +| clip_fraction | 0.334 | +| clip_range | 0.0717 | +| entropy_loss | -7.32 | +| explained_variance | 0.268 | +| learning_rate | 4.69e-05 | +| loss | -0.0384 | +| n_updates | 41432 | +| policy_gradient_loss | -0.0224 | +| value_loss | 0.000126 | +----------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1421 | +| iterations | 6405 | +| time_elapsed | 9225 | +| total_timesteps | 13117440 | +| train/ | | +| approx_kl | 0.010847 | +| clip_fraction | 0.328 | +| clip_range | 0.0717 | +| entropy_loss | -7.27 | +| explained_variance | 0.268 | +| learning_rate | 4.69e-05 | +| loss | -0.0344 | +| n_updates | 41436 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000185 | +-------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1421 | +| iterations | 6406 | +| time_elapsed | 9227 | +| total_timesteps | 13119488 | +| train/ | | +| approx_kl | 0.010303944 | +| clip_fraction | 0.298 | +| clip_range | 0.0717 | +| entropy_loss | -7.44 | +| explained_variance | -0.141 | +| learning_rate | 4.69e-05 | +| loss | -0.0296 | +| n_updates | 41440 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000186 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1421 | +| iterations | 6407 | +| time_elapsed | 9228 | +| total_timesteps | 13121536 | +| train/ | | +| approx_kl | 0.009716406 | +| clip_fraction | 0.329 | +| clip_range | 0.0717 | +| entropy_loss | -7.35 | +| explained_variance | 0.387 | +| learning_rate | 4.69e-05 | +| loss | -0.0342 | +| n_updates | 41444 | +| policy_gradient_loss | -0.0206 | +| value_loss | 8.34e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1421 | +| iterations | 6408 | +| time_elapsed | 9230 | +| total_timesteps | 13123584 | +| train/ | | +| approx_kl | 0.010417249 | +| clip_fraction | 0.313 | +| clip_range | 0.0717 | +| entropy_loss | -6.66 | +| explained_variance | 0.487 | +| learning_rate | 4.69e-05 | +| loss | -0.0239 | +| n_updates | 41448 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000299 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1421 | +| iterations | 6409 | +| time_elapsed | 9231 | +| total_timesteps | 13125632 | +| train/ | | +| approx_kl | 0.011754133 | +| clip_fraction | 0.328 | +| clip_range | 0.0717 | +| entropy_loss | -7.27 | +| explained_variance | 0.346 | +| learning_rate | 4.69e-05 | +| loss | -0.0386 | +| n_updates | 41452 | +| policy_gradient_loss | -0.0219 | +| value_loss | 0.000108 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1421 | +| iterations | 6410 | +| time_elapsed | 9233 | +| total_timesteps | 13127680 | +| train/ | | +| approx_kl | 0.009561358 | +| clip_fraction | 0.287 | +| clip_range | 0.0717 | +| entropy_loss | -7.2 | +| explained_variance | 0.193 | +| learning_rate | 4.69e-05 | +| loss | -0.0277 | +| n_updates | 41456 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000229 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1421 | +| iterations | 6411 | +| time_elapsed | 9234 | +| total_timesteps | 13129728 | +| train/ | | +| approx_kl | 0.009915738 | +| clip_fraction | 0.305 | +| clip_range | 0.0717 | +| entropy_loss | -7.04 | +| explained_variance | 0.559 | +| learning_rate | 4.69e-05 | +| loss | -0.032 | +| n_updates | 41460 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000122 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1421 | +| iterations | 6412 | +| time_elapsed | 9235 | +| total_timesteps | 13131776 | +| train/ | | +| approx_kl | 0.011225185 | +| clip_fraction | 0.32 | +| clip_range | 0.0717 | +| entropy_loss | -7.19 | +| explained_variance | 0.43 | +| learning_rate | 4.69e-05 | +| loss | -0.0292 | +| n_updates | 41464 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000182 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1421 | +| iterations | 6413 | +| time_elapsed | 9237 | +| total_timesteps | 13133824 | +| train/ | | +| approx_kl | 0.009496022 | +| clip_fraction | 0.289 | +| clip_range | 0.0717 | +| entropy_loss | -7.27 | +| explained_variance | 0.225 | +| learning_rate | 4.69e-05 | +| loss | -0.03 | +| n_updates | 41468 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.00024 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1421 | +| iterations | 6414 | +| time_elapsed | 9238 | +| total_timesteps | 13135872 | +| train/ | | +| approx_kl | 0.010188398 | +| clip_fraction | 0.317 | +| clip_range | 0.0717 | +| entropy_loss | -7.11 | +| explained_variance | 0.476 | +| learning_rate | 4.69e-05 | +| loss | -0.0368 | +| n_updates | 41472 | +| policy_gradient_loss | -0.022 | +| value_loss | 0.000122 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1421 | +| iterations | 6415 | +| time_elapsed | 9240 | +| total_timesteps | 13137920 | +| train/ | | +| approx_kl | 0.008640517 | +| clip_fraction | 0.294 | +| clip_range | 0.0717 | +| entropy_loss | -7.19 | +| explained_variance | 0.31 | +| learning_rate | 4.69e-05 | +| loss | -0.0266 | +| n_updates | 41476 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000183 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1421 | +| iterations | 6416 | +| time_elapsed | 9241 | +| total_timesteps | 13139968 | +| train/ | | +| approx_kl | 0.0106035285 | +| clip_fraction | 0.31 | +| clip_range | 0.0717 | +| entropy_loss | -7.04 | +| explained_variance | 0.357 | +| learning_rate | 4.69e-05 | +| loss | -0.0297 | +| n_updates | 41480 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000232 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1421 | +| iterations | 6417 | +| time_elapsed | 9243 | +| total_timesteps | 13142016 | +| train/ | | +| approx_kl | 0.010219267 | +| clip_fraction | 0.322 | +| clip_range | 0.0717 | +| entropy_loss | -7.47 | +| explained_variance | -0.278 | +| learning_rate | 4.69e-05 | +| loss | -0.0381 | +| n_updates | 41484 | +| policy_gradient_loss | -0.0224 | +| value_loss | 8.53e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1421 | +| iterations | 6418 | +| time_elapsed | 9244 | +| total_timesteps | 13144064 | +| train/ | | +| approx_kl | 0.009987571 | +| clip_fraction | 0.321 | +| clip_range | 0.0717 | +| entropy_loss | -7.2 | +| explained_variance | 0.304 | +| learning_rate | 4.69e-05 | +| loss | -0.0287 | +| n_updates | 41488 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000251 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1421 | +| iterations | 6419 | +| time_elapsed | 9246 | +| total_timesteps | 13146112 | +| train/ | | +| approx_kl | 0.010341613 | +| clip_fraction | 0.329 | +| clip_range | 0.0717 | +| entropy_loss | -7.06 | +| explained_variance | 0.563 | +| learning_rate | 4.69e-05 | +| loss | -0.0355 | +| n_updates | 41492 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000117 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1421 | +| iterations | 6420 | +| time_elapsed | 9247 | +| total_timesteps | 13148160 | +| train/ | | +| approx_kl | 0.011146388 | +| clip_fraction | 0.322 | +| clip_range | 0.0717 | +| entropy_loss | -7.25 | +| explained_variance | 0.329 | +| learning_rate | 4.69e-05 | +| loss | -0.0345 | +| n_updates | 41496 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000118 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1421 | +| iterations | 6421 | +| time_elapsed | 9249 | +| total_timesteps | 13150208 | +| train/ | | +| approx_kl | 0.010481768 | +| clip_fraction | 0.301 | +| clip_range | 0.0717 | +| entropy_loss | -7.32 | +| explained_variance | 0.48 | +| learning_rate | 4.69e-05 | +| loss | -0.0331 | +| n_updates | 41500 | +| policy_gradient_loss | -0.02 | +| value_loss | 8.22e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1421 | +| iterations | 6422 | +| time_elapsed | 9250 | +| total_timesteps | 13152256 | +| train/ | | +| approx_kl | 0.011116832 | +| clip_fraction | 0.292 | +| clip_range | 0.0717 | +| entropy_loss | -7.38 | +| explained_variance | 0.291 | +| learning_rate | 4.69e-05 | +| loss | -0.0358 | +| n_updates | 41504 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.00017 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1421 | +| iterations | 6423 | +| time_elapsed | 9251 | +| total_timesteps | 13154304 | +| train/ | | +| approx_kl | 0.009589927 | +| clip_fraction | 0.284 | +| clip_range | 0.0717 | +| entropy_loss | -6.98 | +| explained_variance | 0.511 | +| learning_rate | 4.69e-05 | +| loss | -0.0233 | +| n_updates | 41508 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000148 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1421 | +| iterations | 6424 | +| time_elapsed | 9253 | +| total_timesteps | 13156352 | +| train/ | | +| approx_kl | 0.009758318 | +| clip_fraction | 0.299 | +| clip_range | 0.0717 | +| entropy_loss | -6.8 | +| explained_variance | 0.584 | +| learning_rate | 4.69e-05 | +| loss | -0.0285 | +| n_updates | 41512 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000183 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1421 | +| iterations | 6425 | +| time_elapsed | 9254 | +| total_timesteps | 13158400 | +| train/ | | +| approx_kl | 0.008948537 | +| clip_fraction | 0.304 | +| clip_range | 0.0717 | +| entropy_loss | -7.49 | +| explained_variance | -0.00634 | +| learning_rate | 4.69e-05 | +| loss | -0.0309 | +| n_updates | 41516 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000124 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1421 | +| iterations | 6426 | +| time_elapsed | 9256 | +| total_timesteps | 13160448 | +| train/ | | +| approx_kl | 0.011997607 | +| clip_fraction | 0.314 | +| clip_range | 0.0717 | +| entropy_loss | -6.87 | +| explained_variance | 0.75 | +| learning_rate | 4.69e-05 | +| loss | -0.0344 | +| n_updates | 41520 | +| policy_gradient_loss | -0.0205 | +| value_loss | 6.62e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1421 | +| iterations | 6427 | +| time_elapsed | 9257 | +| total_timesteps | 13162496 | +| train/ | | +| approx_kl | 0.010436306 | +| clip_fraction | 0.32 | +| clip_range | 0.0717 | +| entropy_loss | -7.01 | +| explained_variance | 0.422 | +| learning_rate | 4.69e-05 | +| loss | -0.0245 | +| n_updates | 41524 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000156 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1421 | +| iterations | 6428 | +| time_elapsed | 9259 | +| total_timesteps | 13164544 | +| train/ | | +| approx_kl | 0.00977461 | +| clip_fraction | 0.318 | +| clip_range | 0.0717 | +| entropy_loss | -7.41 | +| explained_variance | -0.00251 | +| learning_rate | 4.69e-05 | +| loss | -0.0255 | +| n_updates | 41528 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000168 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1421 | +| iterations | 6429 | +| time_elapsed | 9260 | +| total_timesteps | 13166592 | +| train/ | | +| approx_kl | 0.010088601 | +| clip_fraction | 0.298 | +| clip_range | 0.0717 | +| entropy_loss | -6.78 | +| explained_variance | 0.677 | +| learning_rate | 4.69e-05 | +| loss | -0.0274 | +| n_updates | 41532 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000137 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1421 | +| iterations | 6430 | +| time_elapsed | 9262 | +| total_timesteps | 13168640 | +| train/ | | +| approx_kl | 0.010596955 | +| clip_fraction | 0.31 | +| clip_range | 0.0717 | +| entropy_loss | -7.11 | +| explained_variance | 0.236 | +| learning_rate | 4.69e-05 | +| loss | -0.0254 | +| n_updates | 41536 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000265 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1421 | +| iterations | 6431 | +| time_elapsed | 9263 | +| total_timesteps | 13170688 | +| train/ | | +| approx_kl | 0.010068161 | +| clip_fraction | 0.311 | +| clip_range | 0.0717 | +| entropy_loss | -7.37 | +| explained_variance | 0.0725 | +| learning_rate | 4.69e-05 | +| loss | -0.0291 | +| n_updates | 41540 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000188 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1421 | +| iterations | 6432 | +| time_elapsed | 9264 | +| total_timesteps | 13172736 | +| train/ | | +| approx_kl | 0.011323466 | +| clip_fraction | 0.313 | +| clip_range | 0.0717 | +| entropy_loss | -7.39 | +| explained_variance | 0.067 | +| learning_rate | 4.69e-05 | +| loss | -0.0337 | +| n_updates | 41544 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000192 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1421 | +| iterations | 6433 | +| time_elapsed | 9266 | +| total_timesteps | 13174784 | +| train/ | | +| approx_kl | 0.008987479 | +| clip_fraction | 0.307 | +| clip_range | 0.0717 | +| entropy_loss | -6.87 | +| explained_variance | 0.337 | +| learning_rate | 4.69e-05 | +| loss | -0.0291 | +| n_updates | 41548 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000261 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1421 | +| iterations | 6434 | +| time_elapsed | 9267 | +| total_timesteps | 13176832 | +| train/ | | +| approx_kl | 0.011170989 | +| clip_fraction | 0.308 | +| clip_range | 0.0717 | +| entropy_loss | -7.01 | +| explained_variance | 0.339 | +| learning_rate | 4.69e-05 | +| loss | -0.0361 | +| n_updates | 41552 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000216 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1421 | +| iterations | 6435 | +| time_elapsed | 9269 | +| total_timesteps | 13178880 | +| train/ | | +| approx_kl | 0.009227523 | +| clip_fraction | 0.3 | +| clip_range | 0.0717 | +| entropy_loss | -7.14 | +| explained_variance | 0.423 | +| learning_rate | 4.69e-05 | +| loss | -0.0303 | +| n_updates | 41556 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000183 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1421 | +| iterations | 6436 | +| time_elapsed | 9270 | +| total_timesteps | 13180928 | +| train/ | | +| approx_kl | 0.012969036 | +| clip_fraction | 0.297 | +| clip_range | 0.0717 | +| entropy_loss | -7.23 | +| explained_variance | -0.288 | +| learning_rate | 4.69e-05 | +| loss | -0.0288 | +| n_updates | 41560 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000142 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1421 | +| iterations | 6437 | +| time_elapsed | 9272 | +| total_timesteps | 13182976 | +| train/ | | +| approx_kl | 0.0123867225 | +| clip_fraction | 0.342 | +| clip_range | 0.0717 | +| entropy_loss | -7.03 | +| explained_variance | 0.473 | +| learning_rate | 4.69e-05 | +| loss | -0.0381 | +| n_updates | 41564 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000126 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1421 | +| iterations | 6438 | +| time_elapsed | 9273 | +| total_timesteps | 13185024 | +| train/ | | +| approx_kl | 0.013397817 | +| clip_fraction | 0.339 | +| clip_range | 0.0717 | +| entropy_loss | -7.35 | +| explained_variance | -0.216 | +| learning_rate | 4.69e-05 | +| loss | -0.0285 | +| n_updates | 41568 | +| policy_gradient_loss | -0.0219 | +| value_loss | 8.48e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1421 | +| iterations | 6439 | +| time_elapsed | 9274 | +| total_timesteps | 13187072 | +| train/ | | +| approx_kl | 0.012038812 | +| clip_fraction | 0.316 | +| clip_range | 0.0717 | +| entropy_loss | -7.41 | +| explained_variance | -0.152 | +| learning_rate | 4.69e-05 | +| loss | -0.0332 | +| n_updates | 41572 | +| policy_gradient_loss | -0.0196 | +| value_loss | 9.17e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1421 | +| iterations | 6440 | +| time_elapsed | 9276 | +| total_timesteps | 13189120 | +| train/ | | +| approx_kl | 0.0098322835 | +| clip_fraction | 0.28 | +| clip_range | 0.0717 | +| entropy_loss | -6.69 | +| explained_variance | 0.641 | +| learning_rate | 4.69e-05 | +| loss | -0.0317 | +| n_updates | 41576 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000157 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1421 | +| iterations | 6441 | +| time_elapsed | 9277 | +| total_timesteps | 13191168 | +| train/ | | +| approx_kl | 0.011327069 | +| clip_fraction | 0.309 | +| clip_range | 0.0717 | +| entropy_loss | -7.05 | +| explained_variance | 0.531 | +| learning_rate | 4.69e-05 | +| loss | -0.0235 | +| n_updates | 41580 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.00014 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1421 | +| iterations | 6442 | +| time_elapsed | 9279 | +| total_timesteps | 13193216 | +| train/ | | +| approx_kl | 0.009181446 | +| clip_fraction | 0.29 | +| clip_range | 0.0717 | +| entropy_loss | -7.25 | +| explained_variance | 0.296 | +| learning_rate | 4.69e-05 | +| loss | -0.0289 | +| n_updates | 41584 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000188 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1421 | +| iterations | 6443 | +| time_elapsed | 9280 | +| total_timesteps | 13195264 | +| train/ | | +| approx_kl | 0.009275662 | +| clip_fraction | 0.333 | +| clip_range | 0.0717 | +| entropy_loss | -7.14 | +| explained_variance | 0.62 | +| learning_rate | 4.69e-05 | +| loss | -0.0343 | +| n_updates | 41588 | +| policy_gradient_loss | -0.0209 | +| value_loss | 9.06e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1421 | +| iterations | 6444 | +| time_elapsed | 9282 | +| total_timesteps | 13197312 | +| train/ | | +| approx_kl | 0.01044069 | +| clip_fraction | 0.319 | +| clip_range | 0.0717 | +| entropy_loss | -7.12 | +| explained_variance | 0.458 | +| learning_rate | 4.69e-05 | +| loss | -0.0287 | +| n_updates | 41592 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000134 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1421 | +| iterations | 6445 | +| time_elapsed | 9283 | +| total_timesteps | 13199360 | +| train/ | | +| approx_kl | 0.009855043 | +| clip_fraction | 0.3 | +| clip_range | 0.0717 | +| entropy_loss | -7.31 | +| explained_variance | 0.0739 | +| learning_rate | 4.69e-05 | +| loss | -0.0264 | +| n_updates | 41596 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000182 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1421 | +| iterations | 6446 | +| time_elapsed | 9285 | +| total_timesteps | 13201408 | +| train/ | | +| approx_kl | 0.012609527 | +| clip_fraction | 0.314 | +| clip_range | 0.0717 | +| entropy_loss | -6.93 | +| explained_variance | 0.502 | +| learning_rate | 4.69e-05 | +| loss | -0.0266 | +| n_updates | 41600 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000176 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1421 | +| iterations | 6447 | +| time_elapsed | 9286 | +| total_timesteps | 13203456 | +| train/ | | +| approx_kl | 0.010871144 | +| clip_fraction | 0.297 | +| clip_range | 0.0717 | +| entropy_loss | -7.3 | +| explained_variance | 0.353 | +| learning_rate | 4.69e-05 | +| loss | -0.031 | +| n_updates | 41604 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000162 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1421 | +| iterations | 6448 | +| time_elapsed | 9287 | +| total_timesteps | 13205504 | +| train/ | | +| approx_kl | 0.011823257 | +| clip_fraction | 0.298 | +| clip_range | 0.0717 | +| entropy_loss | -7.34 | +| explained_variance | 0.3 | +| learning_rate | 4.69e-05 | +| loss | -0.0326 | +| n_updates | 41608 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000135 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1421 | +| iterations | 6449 | +| time_elapsed | 9289 | +| total_timesteps | 13207552 | +| train/ | | +| approx_kl | 0.010955503 | +| clip_fraction | 0.311 | +| clip_range | 0.0717 | +| entropy_loss | -7.13 | +| explained_variance | 0.519 | +| learning_rate | 4.69e-05 | +| loss | -0.0264 | +| n_updates | 41612 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.00014 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1421 | +| iterations | 6450 | +| time_elapsed | 9290 | +| total_timesteps | 13209600 | +| train/ | | +| approx_kl | 0.010493719 | +| clip_fraction | 0.287 | +| clip_range | 0.0717 | +| entropy_loss | -7.22 | +| explained_variance | 0.417 | +| learning_rate | 4.69e-05 | +| loss | -0.0285 | +| n_updates | 41616 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000214 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1421 | +| iterations | 6451 | +| time_elapsed | 9292 | +| total_timesteps | 13211648 | +| train/ | | +| approx_kl | 0.009766875 | +| clip_fraction | 0.285 | +| clip_range | 0.0717 | +| entropy_loss | -7.36 | +| explained_variance | 0.311 | +| learning_rate | 4.69e-05 | +| loss | -0.0319 | +| n_updates | 41620 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.00016 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1421 | +| iterations | 6452 | +| time_elapsed | 9293 | +| total_timesteps | 13213696 | +| train/ | | +| approx_kl | 0.010961432 | +| clip_fraction | 0.313 | +| clip_range | 0.0717 | +| entropy_loss | -7.29 | +| explained_variance | 0.306 | +| learning_rate | 4.69e-05 | +| loss | -0.0304 | +| n_updates | 41624 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000158 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1421 | +| iterations | 6453 | +| time_elapsed | 9295 | +| total_timesteps | 13215744 | +| train/ | | +| approx_kl | 0.013603335 | +| clip_fraction | 0.301 | +| clip_range | 0.0717 | +| entropy_loss | -6.96 | +| explained_variance | 0.436 | +| learning_rate | 4.69e-05 | +| loss | -0.0292 | +| n_updates | 41628 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000276 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1421 | +| iterations | 6454 | +| time_elapsed | 9296 | +| total_timesteps | 13217792 | +| train/ | | +| approx_kl | 0.010143761 | +| clip_fraction | 0.322 | +| clip_range | 0.0717 | +| entropy_loss | -7.23 | +| explained_variance | 0.505 | +| learning_rate | 4.69e-05 | +| loss | -0.0315 | +| n_updates | 41632 | +| policy_gradient_loss | -0.0204 | +| value_loss | 9.98e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1421 | +| iterations | 6455 | +| time_elapsed | 9297 | +| total_timesteps | 13219840 | +| train/ | | +| approx_kl | 0.008441511 | +| clip_fraction | 0.283 | +| clip_range | 0.0717 | +| entropy_loss | -7.19 | +| explained_variance | 0.489 | +| learning_rate | 4.69e-05 | +| loss | -0.0297 | +| n_updates | 41636 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000171 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1421 | +| iterations | 6456 | +| time_elapsed | 9299 | +| total_timesteps | 13221888 | +| train/ | | +| approx_kl | 0.0101430025 | +| clip_fraction | 0.298 | +| clip_range | 0.0717 | +| entropy_loss | -7.27 | +| explained_variance | 0.298 | +| learning_rate | 4.69e-05 | +| loss | -0.0336 | +| n_updates | 41640 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000245 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1421 | +| iterations | 6457 | +| time_elapsed | 9300 | +| total_timesteps | 13223936 | +| train/ | | +| approx_kl | 0.0077405227 | +| clip_fraction | 0.273 | +| clip_range | 0.0717 | +| entropy_loss | -7.18 | +| explained_variance | 0.219 | +| learning_rate | 4.69e-05 | +| loss | -0.0313 | +| n_updates | 41644 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000294 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1421 | +| iterations | 6458 | +| time_elapsed | 9302 | +| total_timesteps | 13225984 | +| train/ | | +| approx_kl | 0.00929207 | +| clip_fraction | 0.286 | +| clip_range | 0.0717 | +| entropy_loss | -7.06 | +| explained_variance | 0.411 | +| learning_rate | 4.69e-05 | +| loss | -0.0289 | +| n_updates | 41648 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000329 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1421 | +| iterations | 6459 | +| time_elapsed | 9303 | +| total_timesteps | 13228032 | +| train/ | | +| approx_kl | 0.010176284 | +| clip_fraction | 0.329 | +| clip_range | 0.0717 | +| entropy_loss | -7.47 | +| explained_variance | -0.0572 | +| learning_rate | 4.69e-05 | +| loss | -0.0337 | +| n_updates | 41652 | +| policy_gradient_loss | -0.0241 | +| value_loss | 0.000102 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1421 | +| iterations | 6460 | +| time_elapsed | 9305 | +| total_timesteps | 13230080 | +| train/ | | +| approx_kl | 0.008677719 | +| clip_fraction | 0.297 | +| clip_range | 0.0717 | +| entropy_loss | -7.2 | +| explained_variance | 0.387 | +| learning_rate | 4.69e-05 | +| loss | -0.0314 | +| n_updates | 41656 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000197 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1421 | +| iterations | 6461 | +| time_elapsed | 9306 | +| total_timesteps | 13232128 | +| train/ | | +| approx_kl | 0.010215759 | +| clip_fraction | 0.31 | +| clip_range | 0.0717 | +| entropy_loss | -7.17 | +| explained_variance | 0.528 | +| learning_rate | 4.69e-05 | +| loss | -0.0326 | +| n_updates | 41660 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000127 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1421 | +| iterations | 6462 | +| time_elapsed | 9307 | +| total_timesteps | 13234176 | +| train/ | | +| approx_kl | 0.0104128355 | +| clip_fraction | 0.321 | +| clip_range | 0.0717 | +| entropy_loss | -7.29 | +| explained_variance | 0.385 | +| learning_rate | 4.69e-05 | +| loss | -0.0308 | +| n_updates | 41664 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000112 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1421 | +| iterations | 6463 | +| time_elapsed | 9309 | +| total_timesteps | 13236224 | +| train/ | | +| approx_kl | 0.0105306115 | +| clip_fraction | 0.298 | +| clip_range | 0.0717 | +| entropy_loss | -7.36 | +| explained_variance | 0.343 | +| learning_rate | 4.69e-05 | +| loss | -0.0282 | +| n_updates | 41668 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000165 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1421 | +| iterations | 6464 | +| time_elapsed | 9310 | +| total_timesteps | 13238272 | +| train/ | | +| approx_kl | 0.011400424 | +| clip_fraction | 0.309 | +| clip_range | 0.0717 | +| entropy_loss | -6.93 | +| explained_variance | 0.439 | +| learning_rate | 4.69e-05 | +| loss | -0.0313 | +| n_updates | 41672 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.00017 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1421 | +| iterations | 6465 | +| time_elapsed | 9312 | +| total_timesteps | 13240320 | +| train/ | | +| approx_kl | 0.0114878435 | +| clip_fraction | 0.345 | +| clip_range | 0.0717 | +| entropy_loss | -7.15 | +| explained_variance | 0.615 | +| learning_rate | 4.69e-05 | +| loss | -0.0348 | +| n_updates | 41676 | +| policy_gradient_loss | -0.0231 | +| value_loss | 7.95e-05 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1421 | +| iterations | 6466 | +| time_elapsed | 9313 | +| total_timesteps | 13242368 | +| train/ | | +| approx_kl | 0.0117426235 | +| clip_fraction | 0.327 | +| clip_range | 0.0717 | +| entropy_loss | -6.84 | +| explained_variance | 0.499 | +| learning_rate | 4.69e-05 | +| loss | -0.0248 | +| n_updates | 41680 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000201 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1421 | +| iterations | 6467 | +| time_elapsed | 9315 | +| total_timesteps | 13244416 | +| train/ | | +| approx_kl | 0.011656357 | +| clip_fraction | 0.328 | +| clip_range | 0.0717 | +| entropy_loss | -7.34 | +| explained_variance | -0.31 | +| learning_rate | 4.69e-05 | +| loss | -0.0332 | +| n_updates | 41684 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1421 | +| iterations | 6468 | +| time_elapsed | 9316 | +| total_timesteps | 13246464 | +| train/ | | +| approx_kl | 0.013392009 | +| clip_fraction | 0.312 | +| clip_range | 0.0717 | +| entropy_loss | -7.22 | +| explained_variance | 0.35 | +| learning_rate | 4.69e-05 | +| loss | -0.031 | +| n_updates | 41688 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000147 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1421 | +| iterations | 6469 | +| time_elapsed | 9317 | +| total_timesteps | 13248512 | +| train/ | | +| approx_kl | 0.013734212 | +| clip_fraction | 0.31 | +| clip_range | 0.0717 | +| entropy_loss | -7.27 | +| explained_variance | 0.335 | +| learning_rate | 4.69e-05 | +| loss | -0.0321 | +| n_updates | 41692 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000169 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1421 | +| iterations | 6470 | +| time_elapsed | 9319 | +| total_timesteps | 13250560 | +| train/ | | +| approx_kl | 0.010164265 | +| clip_fraction | 0.297 | +| clip_range | 0.0717 | +| entropy_loss | -7.28 | +| explained_variance | 0.281 | +| learning_rate | 4.69e-05 | +| loss | -0.0264 | +| n_updates | 41696 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000192 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1421 | +| iterations | 6471 | +| time_elapsed | 9320 | +| total_timesteps | 13252608 | +| train/ | | +| approx_kl | 0.009846453 | +| clip_fraction | 0.301 | +| clip_range | 0.0717 | +| entropy_loss | -7.35 | +| explained_variance | 0.394 | +| learning_rate | 4.69e-05 | +| loss | -0.0364 | +| n_updates | 41700 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000123 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1421 | +| iterations | 6472 | +| time_elapsed | 9322 | +| total_timesteps | 13254656 | +| train/ | | +| approx_kl | 0.009877989 | +| clip_fraction | 0.321 | +| clip_range | 0.0717 | +| entropy_loss | -6.91 | +| explained_variance | 0.549 | +| learning_rate | 4.69e-05 | +| loss | -0.0289 | +| n_updates | 41704 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000175 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1421 | +| iterations | 6473 | +| time_elapsed | 9323 | +| total_timesteps | 13256704 | +| train/ | | +| approx_kl | 0.010527384 | +| clip_fraction | 0.322 | +| clip_range | 0.0717 | +| entropy_loss | -7.11 | +| explained_variance | 0.439 | +| learning_rate | 4.69e-05 | +| loss | -0.0348 | +| n_updates | 41708 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000144 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1421 | +| iterations | 6474 | +| time_elapsed | 9325 | +| total_timesteps | 13258752 | +| train/ | | +| approx_kl | 0.0094739115 | +| clip_fraction | 0.28 | +| clip_range | 0.0717 | +| entropy_loss | -7.42 | +| explained_variance | 0.244 | +| learning_rate | 4.69e-05 | +| loss | -0.0346 | +| n_updates | 41712 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000168 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1421 | +| iterations | 6475 | +| time_elapsed | 9326 | +| total_timesteps | 13260800 | +| train/ | | +| approx_kl | 0.009920787 | +| clip_fraction | 0.294 | +| clip_range | 0.0717 | +| entropy_loss | -7.31 | +| explained_variance | 0.401 | +| learning_rate | 4.69e-05 | +| loss | -0.0303 | +| n_updates | 41716 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000122 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1421 | +| iterations | 6476 | +| time_elapsed | 9327 | +| total_timesteps | 13262848 | +| train/ | | +| approx_kl | 0.010370403 | +| clip_fraction | 0.324 | +| clip_range | 0.0717 | +| entropy_loss | -7.48 | +| explained_variance | -0.0168 | +| learning_rate | 4.69e-05 | +| loss | -0.0275 | +| n_updates | 41720 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000192 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1421 | +| iterations | 6477 | +| time_elapsed | 9329 | +| total_timesteps | 13264896 | +| train/ | | +| approx_kl | 0.010590391 | +| clip_fraction | 0.314 | +| clip_range | 0.0717 | +| entropy_loss | -6.97 | +| explained_variance | 0.581 | +| learning_rate | 4.69e-05 | +| loss | -0.0364 | +| n_updates | 41724 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000123 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1421 | +| iterations | 6478 | +| time_elapsed | 9330 | +| total_timesteps | 13266944 | +| train/ | | +| approx_kl | 0.0120301 | +| clip_fraction | 0.304 | +| clip_range | 0.0717 | +| entropy_loss | -7.08 | +| explained_variance | 0.437 | +| learning_rate | 4.68e-05 | +| loss | -0.0303 | +| n_updates | 41728 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000176 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1421 | +| iterations | 6479 | +| time_elapsed | 9332 | +| total_timesteps | 13268992 | +| train/ | | +| approx_kl | 0.010498477 | +| clip_fraction | 0.297 | +| clip_range | 0.0717 | +| entropy_loss | -7.02 | +| explained_variance | 0.711 | +| learning_rate | 4.68e-05 | +| loss | -0.0304 | +| n_updates | 41732 | +| policy_gradient_loss | -0.0185 | +| value_loss | 8.43e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1421 | +| iterations | 6480 | +| time_elapsed | 9333 | +| total_timesteps | 13271040 | +| train/ | | +| approx_kl | 0.010511519 | +| clip_fraction | 0.316 | +| clip_range | 0.0717 | +| entropy_loss | -7.4 | +| explained_variance | 0.193 | +| learning_rate | 4.68e-05 | +| loss | -0.0342 | +| n_updates | 41736 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000183 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1421 | +| iterations | 6481 | +| time_elapsed | 9335 | +| total_timesteps | 13273088 | +| train/ | | +| approx_kl | 0.01028883 | +| clip_fraction | 0.312 | +| clip_range | 0.0717 | +| entropy_loss | -7.31 | +| explained_variance | 0.298 | +| learning_rate | 4.68e-05 | +| loss | -0.0318 | +| n_updates | 41740 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000191 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1421 | +| iterations | 6482 | +| time_elapsed | 9336 | +| total_timesteps | 13275136 | +| train/ | | +| approx_kl | 0.012807423 | +| clip_fraction | 0.288 | +| clip_range | 0.0717 | +| entropy_loss | -7.21 | +| explained_variance | 0.488 | +| learning_rate | 4.68e-05 | +| loss | -0.0346 | +| n_updates | 41744 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000141 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1421 | +| iterations | 6483 | +| time_elapsed | 9337 | +| total_timesteps | 13277184 | +| train/ | | +| approx_kl | 0.009773476 | +| clip_fraction | 0.319 | +| clip_range | 0.0717 | +| entropy_loss | -7.11 | +| explained_variance | 0.346 | +| learning_rate | 4.68e-05 | +| loss | -0.0283 | +| n_updates | 41748 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000243 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1421 | +| iterations | 6484 | +| time_elapsed | 9339 | +| total_timesteps | 13279232 | +| train/ | | +| approx_kl | 0.010434667 | +| clip_fraction | 0.339 | +| clip_range | 0.0717 | +| entropy_loss | -7.07 | +| explained_variance | 0.61 | +| learning_rate | 4.68e-05 | +| loss | -0.0351 | +| n_updates | 41752 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000103 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1421 | +| iterations | 6485 | +| time_elapsed | 9340 | +| total_timesteps | 13281280 | +| train/ | | +| approx_kl | 0.009719866 | +| clip_fraction | 0.3 | +| clip_range | 0.0717 | +| entropy_loss | -7.42 | +| explained_variance | 0.265 | +| learning_rate | 4.68e-05 | +| loss | -0.0311 | +| n_updates | 41756 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000128 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1421 | +| iterations | 6486 | +| time_elapsed | 9342 | +| total_timesteps | 13283328 | +| train/ | | +| approx_kl | 0.01201348 | +| clip_fraction | 0.319 | +| clip_range | 0.0717 | +| entropy_loss | -7.33 | +| explained_variance | -0.167 | +| learning_rate | 4.68e-05 | +| loss | -0.0247 | +| n_updates | 41760 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000204 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1421 | +| iterations | 6487 | +| time_elapsed | 9343 | +| total_timesteps | 13285376 | +| train/ | | +| approx_kl | 0.012570888 | +| clip_fraction | 0.328 | +| clip_range | 0.0717 | +| entropy_loss | -6.95 | +| explained_variance | 0.382 | +| learning_rate | 4.68e-05 | +| loss | -0.0298 | +| n_updates | 41764 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000176 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1421 | +| iterations | 6488 | +| time_elapsed | 9344 | +| total_timesteps | 13287424 | +| train/ | | +| approx_kl | 0.011740327 | +| clip_fraction | 0.337 | +| clip_range | 0.0717 | +| entropy_loss | -7.16 | +| explained_variance | 0.169 | +| learning_rate | 4.68e-05 | +| loss | -0.0281 | +| n_updates | 41768 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000125 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1421 | +| iterations | 6489 | +| time_elapsed | 9346 | +| total_timesteps | 13289472 | +| train/ | | +| approx_kl | 0.011237106 | +| clip_fraction | 0.319 | +| clip_range | 0.0717 | +| entropy_loss | -6.65 | +| explained_variance | 0.77 | +| learning_rate | 4.68e-05 | +| loss | -0.0363 | +| n_updates | 41772 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000103 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1421 | +| iterations | 6490 | +| time_elapsed | 9347 | +| total_timesteps | 13291520 | +| train/ | | +| approx_kl | 0.010664925 | +| clip_fraction | 0.321 | +| clip_range | 0.0717 | +| entropy_loss | -7.35 | +| explained_variance | -0.122 | +| learning_rate | 4.68e-05 | +| loss | -0.0321 | +| n_updates | 41776 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000145 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1421 | +| iterations | 6491 | +| time_elapsed | 9349 | +| total_timesteps | 13293568 | +| train/ | | +| approx_kl | 0.010171002 | +| clip_fraction | 0.313 | +| clip_range | 0.0717 | +| entropy_loss | -6.74 | +| explained_variance | 0.442 | +| learning_rate | 4.68e-05 | +| loss | -0.0264 | +| n_updates | 41780 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000329 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1421 | +| iterations | 6492 | +| time_elapsed | 9350 | +| total_timesteps | 13295616 | +| train/ | | +| approx_kl | 0.012018817 | +| clip_fraction | 0.317 | +| clip_range | 0.0717 | +| entropy_loss | -7.21 | +| explained_variance | 0.15 | +| learning_rate | 4.68e-05 | +| loss | -0.0342 | +| n_updates | 41784 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000253 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1421 | +| iterations | 6493 | +| time_elapsed | 9352 | +| total_timesteps | 13297664 | +| train/ | | +| approx_kl | 0.011127426 | +| clip_fraction | 0.342 | +| clip_range | 0.0717 | +| entropy_loss | -7.31 | +| explained_variance | 0.408 | +| learning_rate | 4.68e-05 | +| loss | -0.039 | +| n_updates | 41788 | +| policy_gradient_loss | -0.0231 | +| value_loss | 9.16e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1421 | +| iterations | 6494 | +| time_elapsed | 9353 | +| total_timesteps | 13299712 | +| train/ | | +| approx_kl | 0.010443201 | +| clip_fraction | 0.286 | +| clip_range | 0.0717 | +| entropy_loss | -7.39 | +| explained_variance | 0.221 | +| learning_rate | 4.68e-05 | +| loss | -0.0305 | +| n_updates | 41792 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000202 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1421 | +| iterations | 6495 | +| time_elapsed | 9355 | +| total_timesteps | 13301760 | +| train/ | | +| approx_kl | 0.008250135 | +| clip_fraction | 0.285 | +| clip_range | 0.0717 | +| entropy_loss | -7.14 | +| explained_variance | 0.402 | +| learning_rate | 4.68e-05 | +| loss | -0.026 | +| n_updates | 41796 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.00019 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1421 | +| iterations | 6496 | +| time_elapsed | 9356 | +| total_timesteps | 13303808 | +| train/ | | +| approx_kl | 0.011742614 | +| clip_fraction | 0.337 | +| clip_range | 0.0717 | +| entropy_loss | -7.28 | +| explained_variance | 0.406 | +| learning_rate | 4.68e-05 | +| loss | -0.0376 | +| n_updates | 41800 | +| policy_gradient_loss | -0.0229 | +| value_loss | 0.000101 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1421 | +| iterations | 6497 | +| time_elapsed | 9357 | +| total_timesteps | 13305856 | +| train/ | | +| approx_kl | 0.011521407 | +| clip_fraction | 0.333 | +| clip_range | 0.0717 | +| entropy_loss | -7.36 | +| explained_variance | 0.544 | +| learning_rate | 4.68e-05 | +| loss | -0.0345 | +| n_updates | 41804 | +| policy_gradient_loss | -0.0238 | +| value_loss | 5.76e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1421 | +| iterations | 6498 | +| time_elapsed | 9359 | +| total_timesteps | 13307904 | +| train/ | | +| approx_kl | 0.0107290335 | +| clip_fraction | 0.327 | +| clip_range | 0.0717 | +| entropy_loss | -7.52 | +| explained_variance | -0.218 | +| learning_rate | 4.68e-05 | +| loss | -0.0404 | +| n_updates | 41808 | +| policy_gradient_loss | -0.0205 | +| value_loss | 8.67e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1421 | +| iterations | 6499 | +| time_elapsed | 9360 | +| total_timesteps | 13309952 | +| train/ | | +| approx_kl | 0.008960819 | +| clip_fraction | 0.29 | +| clip_range | 0.0717 | +| entropy_loss | -7.03 | +| explained_variance | 0.628 | +| learning_rate | 4.68e-05 | +| loss | -0.0328 | +| n_updates | 41812 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000122 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1421 | +| iterations | 6500 | +| time_elapsed | 9362 | +| total_timesteps | 13312000 | +| train/ | | +| approx_kl | 0.009122929 | +| clip_fraction | 0.3 | +| clip_range | 0.0717 | +| entropy_loss | -6.91 | +| explained_variance | 0.811 | +| learning_rate | 4.68e-05 | +| loss | -0.0348 | +| n_updates | 41816 | +| policy_gradient_loss | -0.0203 | +| value_loss | 5.33e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1421 | +| iterations | 6501 | +| time_elapsed | 9363 | +| total_timesteps | 13314048 | +| train/ | | +| approx_kl | 0.010679513 | +| clip_fraction | 0.26 | +| clip_range | 0.0717 | +| entropy_loss | -7 | +| explained_variance | 0.469 | +| learning_rate | 4.68e-05 | +| loss | -0.0257 | +| n_updates | 41820 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.000171 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1421 | +| iterations | 6502 | +| time_elapsed | 9365 | +| total_timesteps | 13316096 | +| train/ | | +| approx_kl | 0.011939064 | +| clip_fraction | 0.304 | +| clip_range | 0.0717 | +| entropy_loss | -7.05 | +| explained_variance | 0.37 | +| learning_rate | 4.68e-05 | +| loss | -0.0217 | +| n_updates | 41824 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000251 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1421 | +| iterations | 6503 | +| time_elapsed | 9366 | +| total_timesteps | 13318144 | +| train/ | | +| approx_kl | 0.010098424 | +| clip_fraction | 0.328 | +| clip_range | 0.0717 | +| entropy_loss | -7.27 | +| explained_variance | 0.253 | +| learning_rate | 4.68e-05 | +| loss | -0.024 | +| n_updates | 41828 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000156 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1421 | +| iterations | 6504 | +| time_elapsed | 9367 | +| total_timesteps | 13320192 | +| train/ | | +| approx_kl | 0.0123103615 | +| clip_fraction | 0.327 | +| clip_range | 0.0717 | +| entropy_loss | -7.36 | +| explained_variance | -0.373 | +| learning_rate | 4.68e-05 | +| loss | -0.0317 | +| n_updates | 41832 | +| policy_gradient_loss | -0.0214 | +| value_loss | 7.13e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1421 | +| iterations | 6505 | +| time_elapsed | 9369 | +| total_timesteps | 13322240 | +| train/ | | +| approx_kl | 0.012325237 | +| clip_fraction | 0.31 | +| clip_range | 0.0717 | +| entropy_loss | -7.31 | +| explained_variance | 0.243 | +| learning_rate | 4.68e-05 | +| loss | -0.029 | +| n_updates | 41836 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000167 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1421 | +| iterations | 6506 | +| time_elapsed | 9370 | +| total_timesteps | 13324288 | +| train/ | | +| approx_kl | 0.011017766 | +| clip_fraction | 0.325 | +| clip_range | 0.0717 | +| entropy_loss | -7.3 | +| explained_variance | 0.509 | +| learning_rate | 4.68e-05 | +| loss | -0.0286 | +| n_updates | 41840 | +| policy_gradient_loss | -0.0202 | +| value_loss | 7.07e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1421 | +| iterations | 6507 | +| time_elapsed | 9372 | +| total_timesteps | 13326336 | +| train/ | | +| approx_kl | 0.010945877 | +| clip_fraction | 0.339 | +| clip_range | 0.0717 | +| entropy_loss | -7.26 | +| explained_variance | 0.289 | +| learning_rate | 4.68e-05 | +| loss | -0.0326 | +| n_updates | 41844 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000155 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1421 | +| iterations | 6508 | +| time_elapsed | 9373 | +| total_timesteps | 13328384 | +| train/ | | +| approx_kl | 0.011350986 | +| clip_fraction | 0.321 | +| clip_range | 0.0717 | +| entropy_loss | -6.75 | +| explained_variance | 0.75 | +| learning_rate | 4.68e-05 | +| loss | -0.0343 | +| n_updates | 41848 | +| policy_gradient_loss | -0.0193 | +| value_loss | 7.33e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1421 | +| iterations | 6509 | +| time_elapsed | 9374 | +| total_timesteps | 13330432 | +| train/ | | +| approx_kl | 0.009147162 | +| clip_fraction | 0.298 | +| clip_range | 0.0717 | +| entropy_loss | -6.8 | +| explained_variance | 0.55 | +| learning_rate | 4.68e-05 | +| loss | -0.0243 | +| n_updates | 41852 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.00022 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1421 | +| iterations | 6510 | +| time_elapsed | 9376 | +| total_timesteps | 13332480 | +| train/ | | +| approx_kl | 0.011789572 | +| clip_fraction | 0.299 | +| clip_range | 0.0717 | +| entropy_loss | -7.28 | +| explained_variance | -0.167 | +| learning_rate | 4.68e-05 | +| loss | -0.0259 | +| n_updates | 41856 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000142 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1421 | +| iterations | 6511 | +| time_elapsed | 9377 | +| total_timesteps | 13334528 | +| train/ | | +| approx_kl | 0.012507258 | +| clip_fraction | 0.332 | +| clip_range | 0.0717 | +| entropy_loss | -7 | +| explained_variance | 0.583 | +| learning_rate | 4.68e-05 | +| loss | -0.0301 | +| n_updates | 41860 | +| policy_gradient_loss | -0.0218 | +| value_loss | 6.97e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1421 | +| iterations | 6512 | +| time_elapsed | 9379 | +| total_timesteps | 13336576 | +| train/ | | +| approx_kl | 0.011610994 | +| clip_fraction | 0.328 | +| clip_range | 0.0717 | +| entropy_loss | -7.24 | +| explained_variance | 0.383 | +| learning_rate | 4.68e-05 | +| loss | -0.036 | +| n_updates | 41864 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000117 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1421 | +| iterations | 6513 | +| time_elapsed | 9380 | +| total_timesteps | 13338624 | +| train/ | | +| approx_kl | 0.0101668285 | +| clip_fraction | 0.324 | +| clip_range | 0.0717 | +| entropy_loss | -7.38 | +| explained_variance | -0.139 | +| learning_rate | 4.68e-05 | +| loss | -0.0351 | +| n_updates | 41868 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000116 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1421 | +| iterations | 6514 | +| time_elapsed | 9382 | +| total_timesteps | 13340672 | +| train/ | | +| approx_kl | 0.009492373 | +| clip_fraction | 0.297 | +| clip_range | 0.0717 | +| entropy_loss | -7.06 | +| explained_variance | 0.556 | +| learning_rate | 4.68e-05 | +| loss | -0.0329 | +| n_updates | 41872 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000146 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 1421 | +| iterations | 6515 | +| time_elapsed | 9383 | +| total_timesteps | 13342720 | +| train/ | | +| approx_kl | 0.011768571 | +| clip_fraction | 0.323 | +| clip_range | 0.0717 | +| entropy_loss | -7.25 | +| explained_variance | 0.193 | +| learning_rate | 4.68e-05 | +| loss | -0.0308 | +| n_updates | 41876 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000252 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 1421 | +| iterations | 6516 | +| time_elapsed | 9385 | +| total_timesteps | 13344768 | +| train/ | | +| approx_kl | 0.010008832 | +| clip_fraction | 0.335 | +| clip_range | 0.0717 | +| entropy_loss | -6.98 | +| explained_variance | 0.698 | +| learning_rate | 4.68e-05 | +| loss | -0.0352 | +| n_updates | 41880 | +| policy_gradient_loss | -0.0222 | +| value_loss | 6.02e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.288 | +| time/ | | +| fps | 1421 | +| iterations | 6517 | +| time_elapsed | 9386 | +| total_timesteps | 13346816 | +| train/ | | +| approx_kl | 0.011343378 | +| clip_fraction | 0.34 | +| clip_range | 0.0717 | +| entropy_loss | -6.83 | +| explained_variance | 0.755 | +| learning_rate | 4.68e-05 | +| loss | -0.033 | +| n_updates | 41884 | +| policy_gradient_loss | -0.02 | +| value_loss | 6.64e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.284 | +| time/ | | +| fps | 1421 | +| iterations | 6518 | +| time_elapsed | 9388 | +| total_timesteps | 13348864 | +| train/ | | +| approx_kl | 0.010795616 | +| clip_fraction | 0.302 | +| clip_range | 0.0717 | +| entropy_loss | -6.9 | +| explained_variance | 0.529 | +| learning_rate | 4.68e-05 | +| loss | -0.0329 | +| n_updates | 41888 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000153 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.284 | +| time/ | | +| fps | 1421 | +| iterations | 6519 | +| time_elapsed | 9389 | +| total_timesteps | 13350912 | +| train/ | | +| approx_kl | 0.0115127005 | +| clip_fraction | 0.317 | +| clip_range | 0.0717 | +| entropy_loss | -6.93 | +| explained_variance | 0.495 | +| learning_rate | 4.68e-05 | +| loss | -0.029 | +| n_updates | 41892 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000171 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.291 | +| time/ | | +| fps | 1421 | +| iterations | 6520 | +| time_elapsed | 9390 | +| total_timesteps | 13352960 | +| train/ | | +| approx_kl | 0.010014325 | +| clip_fraction | 0.343 | +| clip_range | 0.0717 | +| entropy_loss | -7.29 | +| explained_variance | 0.741 | +| learning_rate | 4.68e-05 | +| loss | -0.045 | +| n_updates | 41896 | +| policy_gradient_loss | -0.0257 | +| value_loss | 4.52e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.288 | +| time/ | | +| fps | 1421 | +| iterations | 6521 | +| time_elapsed | 9392 | +| total_timesteps | 13355008 | +| train/ | | +| approx_kl | 0.008630041 | +| clip_fraction | 0.268 | +| clip_range | 0.0717 | +| entropy_loss | -7.29 | +| explained_variance | 0.171 | +| learning_rate | 4.68e-05 | +| loss | -0.0244 | +| n_updates | 41900 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000333 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.288 | +| time/ | | +| fps | 1421 | +| iterations | 6522 | +| time_elapsed | 9393 | +| total_timesteps | 13357056 | +| train/ | | +| approx_kl | 0.010914784 | +| clip_fraction | 0.326 | +| clip_range | 0.0717 | +| entropy_loss | -7.19 | +| explained_variance | 0.253 | +| learning_rate | 4.68e-05 | +| loss | -0.0302 | +| n_updates | 41904 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000195 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.29 | +| time/ | | +| fps | 1421 | +| iterations | 6523 | +| time_elapsed | 9395 | +| total_timesteps | 13359104 | +| train/ | | +| approx_kl | 0.010589173 | +| clip_fraction | 0.312 | +| clip_range | 0.0717 | +| entropy_loss | -7.37 | +| explained_variance | 0.331 | +| learning_rate | 4.68e-05 | +| loss | -0.0357 | +| n_updates | 41908 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000105 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.292 | +| time/ | | +| fps | 1421 | +| iterations | 6524 | +| time_elapsed | 9396 | +| total_timesteps | 13361152 | +| train/ | | +| approx_kl | 0.009883696 | +| clip_fraction | 0.305 | +| clip_range | 0.0717 | +| entropy_loss | -7.32 | +| explained_variance | 0.268 | +| learning_rate | 4.68e-05 | +| loss | -0.0347 | +| n_updates | 41912 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000129 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.295 | +| time/ | | +| fps | 1421 | +| iterations | 6525 | +| time_elapsed | 9398 | +| total_timesteps | 13363200 | +| train/ | | +| approx_kl | 0.010620726 | +| clip_fraction | 0.301 | +| clip_range | 0.0717 | +| entropy_loss | -7.25 | +| explained_variance | 0.0701 | +| learning_rate | 4.68e-05 | +| loss | -0.0337 | +| n_updates | 41916 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000377 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.295 | +| time/ | | +| fps | 1421 | +| iterations | 6526 | +| time_elapsed | 9399 | +| total_timesteps | 13365248 | +| train/ | | +| approx_kl | 0.010506403 | +| clip_fraction | 0.301 | +| clip_range | 0.0717 | +| entropy_loss | -6.92 | +| explained_variance | 0.568 | +| learning_rate | 4.68e-05 | +| loss | -0.0384 | +| n_updates | 41920 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000192 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.297 | +| time/ | | +| fps | 1421 | +| iterations | 6527 | +| time_elapsed | 9400 | +| total_timesteps | 13367296 | +| train/ | | +| approx_kl | 0.010499496 | +| clip_fraction | 0.31 | +| clip_range | 0.0717 | +| entropy_loss | -7.56 | +| explained_variance | -0.233 | +| learning_rate | 4.68e-05 | +| loss | -0.0343 | +| n_updates | 41924 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000105 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.294 | +| time/ | | +| fps | 1421 | +| iterations | 6528 | +| time_elapsed | 9402 | +| total_timesteps | 13369344 | +| train/ | | +| approx_kl | 0.008497814 | +| clip_fraction | 0.313 | +| clip_range | 0.0717 | +| entropy_loss | -7.07 | +| explained_variance | 0.467 | +| learning_rate | 4.68e-05 | +| loss | -0.0292 | +| n_updates | 41928 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000186 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.298 | +| time/ | | +| fps | 1421 | +| iterations | 6529 | +| time_elapsed | 9403 | +| total_timesteps | 13371392 | +| train/ | | +| approx_kl | 0.011566918 | +| clip_fraction | 0.324 | +| clip_range | 0.0717 | +| entropy_loss | -7.19 | +| explained_variance | 0.316 | +| learning_rate | 4.68e-05 | +| loss | -0.0336 | +| n_updates | 41932 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000122 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.295 | +| time/ | | +| fps | 1421 | +| iterations | 6530 | +| time_elapsed | 9405 | +| total_timesteps | 13373440 | +| train/ | | +| approx_kl | 0.009186828 | +| clip_fraction | 0.267 | +| clip_range | 0.0717 | +| entropy_loss | -7.07 | +| explained_variance | 0.425 | +| learning_rate | 4.68e-05 | +| loss | -0.0312 | +| n_updates | 41936 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000247 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 1421 | +| iterations | 6531 | +| time_elapsed | 9406 | +| total_timesteps | 13375488 | +| train/ | | +| approx_kl | 0.012119428 | +| clip_fraction | 0.302 | +| clip_range | 0.0717 | +| entropy_loss | -6.91 | +| explained_variance | 0.518 | +| learning_rate | 4.68e-05 | +| loss | -0.0286 | +| n_updates | 41940 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000161 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 1421 | +| iterations | 6532 | +| time_elapsed | 9407 | +| total_timesteps | 13377536 | +| train/ | | +| approx_kl | 0.009416031 | +| clip_fraction | 0.296 | +| clip_range | 0.0717 | +| entropy_loss | -6.75 | +| explained_variance | 0.485 | +| learning_rate | 4.68e-05 | +| loss | -0.0195 | +| n_updates | 41944 | +| policy_gradient_loss | -0.0146 | +| value_loss | 0.000285 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 1421 | +| iterations | 6533 | +| time_elapsed | 9409 | +| total_timesteps | 13379584 | +| train/ | | +| approx_kl | 0.011066255 | +| clip_fraction | 0.316 | +| clip_range | 0.0717 | +| entropy_loss | -7.2 | +| explained_variance | 0.479 | +| learning_rate | 4.68e-05 | +| loss | -0.0323 | +| n_updates | 41948 | +| policy_gradient_loss | -0.0226 | +| value_loss | 0.000133 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.297 | +| time/ | | +| fps | 1421 | +| iterations | 6534 | +| time_elapsed | 9410 | +| total_timesteps | 13381632 | +| train/ | | +| approx_kl | 0.010711286 | +| clip_fraction | 0.313 | +| clip_range | 0.0717 | +| entropy_loss | -7.61 | +| explained_variance | -0.0707 | +| learning_rate | 4.68e-05 | +| loss | -0.0294 | +| n_updates | 41952 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000212 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 1421 | +| iterations | 6535 | +| time_elapsed | 9412 | +| total_timesteps | 13383680 | +| train/ | | +| approx_kl | 0.011072903 | +| clip_fraction | 0.323 | +| clip_range | 0.0717 | +| entropy_loss | -7.34 | +| explained_variance | 0.33 | +| learning_rate | 4.68e-05 | +| loss | -0.0355 | +| n_updates | 41956 | +| policy_gradient_loss | -0.0225 | +| value_loss | 0.000164 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 1421 | +| iterations | 6536 | +| time_elapsed | 9413 | +| total_timesteps | 13385728 | +| train/ | | +| approx_kl | 0.010836415 | +| clip_fraction | 0.332 | +| clip_range | 0.0717 | +| entropy_loss | -7.11 | +| explained_variance | 0.524 | +| learning_rate | 4.68e-05 | +| loss | -0.0384 | +| n_updates | 41960 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000131 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.298 | +| time/ | | +| fps | 1421 | +| iterations | 6537 | +| time_elapsed | 9415 | +| total_timesteps | 13387776 | +| train/ | | +| approx_kl | 0.013724036 | +| clip_fraction | 0.33 | +| clip_range | 0.0717 | +| entropy_loss | -7.52 | +| explained_variance | -0.287 | +| learning_rate | 4.68e-05 | +| loss | -0.0397 | +| n_updates | 41964 | +| policy_gradient_loss | -0.0231 | +| value_loss | 7.02e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.298 | +| time/ | | +| fps | 1421 | +| iterations | 6538 | +| time_elapsed | 9416 | +| total_timesteps | 13389824 | +| train/ | | +| approx_kl | 0.010591164 | +| clip_fraction | 0.26 | +| clip_range | 0.0717 | +| entropy_loss | -7.19 | +| explained_variance | 0.314 | +| learning_rate | 4.68e-05 | +| loss | -0.0271 | +| n_updates | 41968 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.000232 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.306 | +| time/ | | +| fps | 1421 | +| iterations | 6539 | +| time_elapsed | 9417 | +| total_timesteps | 13391872 | +| train/ | | +| approx_kl | 0.011487051 | +| clip_fraction | 0.317 | +| clip_range | 0.0717 | +| entropy_loss | -7.28 | +| explained_variance | 0.474 | +| learning_rate | 4.68e-05 | +| loss | -0.035 | +| n_updates | 41972 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000116 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1421 | +| iterations | 6540 | +| time_elapsed | 9419 | +| total_timesteps | 13393920 | +| train/ | | +| approx_kl | 0.0069896653 | +| clip_fraction | 0.24 | +| clip_range | 0.0717 | +| entropy_loss | -6.97 | +| explained_variance | 0.387 | +| learning_rate | 4.68e-05 | +| loss | -0.0246 | +| n_updates | 41976 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.00034 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1421 | +| iterations | 6541 | +| time_elapsed | 9420 | +| total_timesteps | 13395968 | +| train/ | | +| approx_kl | 0.012130205 | +| clip_fraction | 0.331 | +| clip_range | 0.0717 | +| entropy_loss | -7.11 | +| explained_variance | 0.248 | +| learning_rate | 4.68e-05 | +| loss | -0.0364 | +| n_updates | 41980 | +| policy_gradient_loss | -0.0223 | +| value_loss | 0.000133 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.3 | +| time/ | | +| fps | 1421 | +| iterations | 6542 | +| time_elapsed | 9422 | +| total_timesteps | 13398016 | +| train/ | | +| approx_kl | 0.011540519 | +| clip_fraction | 0.312 | +| clip_range | 0.0717 | +| entropy_loss | -7.53 | +| explained_variance | -0.233 | +| learning_rate | 4.68e-05 | +| loss | -0.0307 | +| n_updates | 41984 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000154 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.302 | +| time/ | | +| fps | 1421 | +| iterations | 6543 | +| time_elapsed | 9423 | +| total_timesteps | 13400064 | +| train/ | | +| approx_kl | 0.010354219 | +| clip_fraction | 0.306 | +| clip_range | 0.0717 | +| entropy_loss | -7.03 | +| explained_variance | 0.324 | +| learning_rate | 4.68e-05 | +| loss | -0.0259 | +| n_updates | 41988 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000218 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 1421 | +| iterations | 6544 | +| time_elapsed | 9425 | +| total_timesteps | 13402112 | +| train/ | | +| approx_kl | 0.010964755 | +| clip_fraction | 0.317 | +| clip_range | 0.0716 | +| entropy_loss | -7.28 | +| explained_variance | -0.0487 | +| learning_rate | 4.68e-05 | +| loss | -0.0343 | +| n_updates | 41992 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.00015 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 1421 | +| iterations | 6545 | +| time_elapsed | 9426 | +| total_timesteps | 13404160 | +| train/ | | +| approx_kl | 0.009321284 | +| clip_fraction | 0.3 | +| clip_range | 0.0716 | +| entropy_loss | -7.04 | +| explained_variance | 0.514 | +| learning_rate | 4.68e-05 | +| loss | -0.0239 | +| n_updates | 41996 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000158 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 1421 | +| iterations | 6546 | +| time_elapsed | 9428 | +| total_timesteps | 13406208 | +| train/ | | +| approx_kl | 0.009118598 | +| clip_fraction | 0.296 | +| clip_range | 0.0716 | +| entropy_loss | -7.47 | +| explained_variance | 0.0172 | +| learning_rate | 4.68e-05 | +| loss | -0.0294 | +| n_updates | 42000 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.00012 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.302 | +| time/ | | +| fps | 1421 | +| iterations | 6547 | +| time_elapsed | 9429 | +| total_timesteps | 13408256 | +| train/ | | +| approx_kl | 0.011328885 | +| clip_fraction | 0.309 | +| clip_range | 0.0716 | +| entropy_loss | -7.41 | +| explained_variance | -0.106 | +| learning_rate | 4.68e-05 | +| loss | -0.0337 | +| n_updates | 42004 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000155 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1421 | +| iterations | 6548 | +| time_elapsed | 9430 | +| total_timesteps | 13410304 | +| train/ | | +| approx_kl | 0.010595283 | +| clip_fraction | 0.297 | +| clip_range | 0.0716 | +| entropy_loss | -7.15 | +| explained_variance | 0.439 | +| learning_rate | 4.68e-05 | +| loss | -0.029 | +| n_updates | 42008 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000169 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1421 | +| iterations | 6549 | +| time_elapsed | 9432 | +| total_timesteps | 13412352 | +| train/ | | +| approx_kl | 0.011097723 | +| clip_fraction | 0.325 | +| clip_range | 0.0716 | +| entropy_loss | -6.9 | +| explained_variance | 0.572 | +| learning_rate | 4.68e-05 | +| loss | -0.026 | +| n_updates | 42012 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000191 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1421 | +| iterations | 6550 | +| time_elapsed | 9433 | +| total_timesteps | 13414400 | +| train/ | | +| approx_kl | 0.009467846 | +| clip_fraction | 0.279 | +| clip_range | 0.0716 | +| entropy_loss | -7.32 | +| explained_variance | 0.385 | +| learning_rate | 4.68e-05 | +| loss | -0.0308 | +| n_updates | 42016 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.00019 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.306 | +| time/ | | +| fps | 1421 | +| iterations | 6551 | +| time_elapsed | 9435 | +| total_timesteps | 13416448 | +| train/ | | +| approx_kl | 0.009691967 | +| clip_fraction | 0.286 | +| clip_range | 0.0716 | +| entropy_loss | -7.49 | +| explained_variance | 0.306 | +| learning_rate | 4.68e-05 | +| loss | -0.0289 | +| n_updates | 42020 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000157 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 1421 | +| iterations | 6552 | +| time_elapsed | 9436 | +| total_timesteps | 13418496 | +| train/ | | +| approx_kl | 0.009370223 | +| clip_fraction | 0.289 | +| clip_range | 0.0716 | +| entropy_loss | -7.43 | +| explained_variance | 0.252 | +| learning_rate | 4.68e-05 | +| loss | -0.0318 | +| n_updates | 42024 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000176 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.302 | +| time/ | | +| fps | 1421 | +| iterations | 6553 | +| time_elapsed | 9438 | +| total_timesteps | 13420544 | +| train/ | | +| approx_kl | 0.0107147535 | +| clip_fraction | 0.302 | +| clip_range | 0.0716 | +| entropy_loss | -6.9 | +| explained_variance | 0.626 | +| learning_rate | 4.68e-05 | +| loss | -0.0314 | +| n_updates | 42028 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000136 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.302 | +| time/ | | +| fps | 1421 | +| iterations | 6554 | +| time_elapsed | 9439 | +| total_timesteps | 13422592 | +| train/ | | +| approx_kl | 0.010086723 | +| clip_fraction | 0.312 | +| clip_range | 0.0716 | +| entropy_loss | -7.26 | +| explained_variance | 0.289 | +| learning_rate | 4.68e-05 | +| loss | -0.0301 | +| n_updates | 42032 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000169 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 1421 | +| iterations | 6555 | +| time_elapsed | 9441 | +| total_timesteps | 13424640 | +| train/ | | +| approx_kl | 0.00979713 | +| clip_fraction | 0.299 | +| clip_range | 0.0716 | +| entropy_loss | -7.6 | +| explained_variance | -0.0432 | +| learning_rate | 4.68e-05 | +| loss | -0.0306 | +| n_updates | 42036 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000141 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 1421 | +| iterations | 6556 | +| time_elapsed | 9442 | +| total_timesteps | 13426688 | +| train/ | | +| approx_kl | 0.009228386 | +| clip_fraction | 0.274 | +| clip_range | 0.0716 | +| entropy_loss | -7.5 | +| explained_variance | 0.274 | +| learning_rate | 4.68e-05 | +| loss | -0.0285 | +| n_updates | 42040 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000107 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 1421 | +| iterations | 6557 | +| time_elapsed | 9444 | +| total_timesteps | 13428736 | +| train/ | | +| approx_kl | 0.01168943 | +| clip_fraction | 0.326 | +| clip_range | 0.0716 | +| entropy_loss | -7.52 | +| explained_variance | 0.105 | +| learning_rate | 4.68e-05 | +| loss | -0.0343 | +| n_updates | 42044 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000124 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 1421 | +| iterations | 6558 | +| time_elapsed | 9445 | +| total_timesteps | 13430784 | +| train/ | | +| approx_kl | 0.009593036 | +| clip_fraction | 0.275 | +| clip_range | 0.0716 | +| entropy_loss | -7.03 | +| explained_variance | 0.708 | +| learning_rate | 4.68e-05 | +| loss | -0.0323 | +| n_updates | 42048 | +| policy_gradient_loss | -0.018 | +| value_loss | 9.18e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1421 | +| iterations | 6559 | +| time_elapsed | 9447 | +| total_timesteps | 13432832 | +| train/ | | +| approx_kl | 0.008791097 | +| clip_fraction | 0.295 | +| clip_range | 0.0716 | +| entropy_loss | -7.06 | +| explained_variance | 0.677 | +| learning_rate | 4.68e-05 | +| loss | -0.0278 | +| n_updates | 42052 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000108 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1421 | +| iterations | 6560 | +| time_elapsed | 9448 | +| total_timesteps | 13434880 | +| train/ | | +| approx_kl | 0.011177015 | +| clip_fraction | 0.269 | +| clip_range | 0.0716 | +| entropy_loss | -6.9 | +| explained_variance | 0.352 | +| learning_rate | 4.68e-05 | +| loss | -0.0267 | +| n_updates | 42056 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000205 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1421 | +| iterations | 6561 | +| time_elapsed | 9449 | +| total_timesteps | 13436928 | +| train/ | | +| approx_kl | 0.011140607 | +| clip_fraction | 0.295 | +| clip_range | 0.0716 | +| entropy_loss | -7.37 | +| explained_variance | -0.061 | +| learning_rate | 4.68e-05 | +| loss | -0.033 | +| n_updates | 42060 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000159 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1421 | +| iterations | 6562 | +| time_elapsed | 9451 | +| total_timesteps | 13438976 | +| train/ | | +| approx_kl | 0.011413842 | +| clip_fraction | 0.3 | +| clip_range | 0.0716 | +| entropy_loss | -6.98 | +| explained_variance | 0.376 | +| learning_rate | 4.68e-05 | +| loss | -0.028 | +| n_updates | 42064 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.00024 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1421 | +| iterations | 6563 | +| time_elapsed | 9452 | +| total_timesteps | 13441024 | +| train/ | | +| approx_kl | 0.010310652 | +| clip_fraction | 0.294 | +| clip_range | 0.0716 | +| entropy_loss | -7.49 | +| explained_variance | -0.0677 | +| learning_rate | 4.68e-05 | +| loss | -0.024 | +| n_updates | 42068 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000196 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1421 | +| iterations | 6564 | +| time_elapsed | 9454 | +| total_timesteps | 13443072 | +| train/ | | +| approx_kl | 0.009872902 | +| clip_fraction | 0.288 | +| clip_range | 0.0716 | +| entropy_loss | -7.31 | +| explained_variance | 0.168 | +| learning_rate | 4.68e-05 | +| loss | -0.0264 | +| n_updates | 42072 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000289 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1421 | +| iterations | 6565 | +| time_elapsed | 9455 | +| total_timesteps | 13445120 | +| train/ | | +| approx_kl | 0.010900677 | +| clip_fraction | 0.308 | +| clip_range | 0.0716 | +| entropy_loss | -7.42 | +| explained_variance | -0.13 | +| learning_rate | 4.68e-05 | +| loss | -0.0287 | +| n_updates | 42076 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000184 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1421 | +| iterations | 6566 | +| time_elapsed | 9457 | +| total_timesteps | 13447168 | +| train/ | | +| approx_kl | 0.010931598 | +| clip_fraction | 0.311 | +| clip_range | 0.0716 | +| entropy_loss | -7.32 | +| explained_variance | 0.192 | +| learning_rate | 4.68e-05 | +| loss | -0.0306 | +| n_updates | 42080 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000211 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1421 | +| iterations | 6567 | +| time_elapsed | 9458 | +| total_timesteps | 13449216 | +| train/ | | +| approx_kl | 0.009694032 | +| clip_fraction | 0.312 | +| clip_range | 0.0716 | +| entropy_loss | -7.34 | +| explained_variance | -0.0453 | +| learning_rate | 4.68e-05 | +| loss | -0.0321 | +| n_updates | 42084 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000151 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1421 | +| iterations | 6568 | +| time_elapsed | 9459 | +| total_timesteps | 13451264 | +| train/ | | +| approx_kl | 0.012217932 | +| clip_fraction | 0.308 | +| clip_range | 0.0716 | +| entropy_loss | -6.91 | +| explained_variance | 0.413 | +| learning_rate | 4.68e-05 | +| loss | -0.0276 | +| n_updates | 42088 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000145 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1421 | +| iterations | 6569 | +| time_elapsed | 9461 | +| total_timesteps | 13453312 | +| train/ | | +| approx_kl | 0.011591706 | +| clip_fraction | 0.342 | +| clip_range | 0.0716 | +| entropy_loss | -6.93 | +| explained_variance | 0.658 | +| learning_rate | 4.68e-05 | +| loss | -0.0355 | +| n_updates | 42092 | +| policy_gradient_loss | -0.0219 | +| value_loss | 0.000111 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1421 | +| iterations | 6570 | +| time_elapsed | 9462 | +| total_timesteps | 13455360 | +| train/ | | +| approx_kl | 0.010763612 | +| clip_fraction | 0.321 | +| clip_range | 0.0716 | +| entropy_loss | -7.43 | +| explained_variance | 0.0158 | +| learning_rate | 4.68e-05 | +| loss | -0.0305 | +| n_updates | 42096 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.00017 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1421 | +| iterations | 6571 | +| time_elapsed | 9464 | +| total_timesteps | 13457408 | +| train/ | | +| approx_kl | 0.010426741 | +| clip_fraction | 0.3 | +| clip_range | 0.0716 | +| entropy_loss | -7.31 | +| explained_variance | 0.133 | +| learning_rate | 4.68e-05 | +| loss | -0.0278 | +| n_updates | 42100 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000193 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1421 | +| iterations | 6572 | +| time_elapsed | 9465 | +| total_timesteps | 13459456 | +| train/ | | +| approx_kl | 0.010457095 | +| clip_fraction | 0.294 | +| clip_range | 0.0716 | +| entropy_loss | -6.93 | +| explained_variance | 0.359 | +| learning_rate | 4.68e-05 | +| loss | -0.0337 | +| n_updates | 42104 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000318 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1421 | +| iterations | 6573 | +| time_elapsed | 9467 | +| total_timesteps | 13461504 | +| train/ | | +| approx_kl | 0.0075643654 | +| clip_fraction | 0.276 | +| clip_range | 0.0716 | +| entropy_loss | -6.94 | +| explained_variance | 0.26 | +| learning_rate | 4.68e-05 | +| loss | -0.0272 | +| n_updates | 42108 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000514 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1421 | +| iterations | 6574 | +| time_elapsed | 9468 | +| total_timesteps | 13463552 | +| train/ | | +| approx_kl | 0.0104023125 | +| clip_fraction | 0.321 | +| clip_range | 0.0716 | +| entropy_loss | -6.58 | +| explained_variance | 0.594 | +| learning_rate | 4.68e-05 | +| loss | -0.0382 | +| n_updates | 42112 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000205 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1421 | +| iterations | 6575 | +| time_elapsed | 9469 | +| total_timesteps | 13465600 | +| train/ | | +| approx_kl | 0.013834046 | +| clip_fraction | 0.325 | +| clip_range | 0.0716 | +| entropy_loss | -7.34 | +| explained_variance | 0.226 | +| learning_rate | 4.68e-05 | +| loss | -0.0403 | +| n_updates | 42116 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000177 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1421 | +| iterations | 6576 | +| time_elapsed | 9471 | +| total_timesteps | 13467648 | +| train/ | | +| approx_kl | 0.011034101 | +| clip_fraction | 0.323 | +| clip_range | 0.0716 | +| entropy_loss | -7.34 | +| explained_variance | 0.312 | +| learning_rate | 4.68e-05 | +| loss | -0.0356 | +| n_updates | 42120 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000131 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1421 | +| iterations | 6577 | +| time_elapsed | 9472 | +| total_timesteps | 13469696 | +| train/ | | +| approx_kl | 0.010800818 | +| clip_fraction | 0.322 | +| clip_range | 0.0716 | +| entropy_loss | -7.32 | +| explained_variance | 0.412 | +| learning_rate | 4.68e-05 | +| loss | -0.0416 | +| n_updates | 42124 | +| policy_gradient_loss | -0.0242 | +| value_loss | 7.06e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1421 | +| iterations | 6578 | +| time_elapsed | 9474 | +| total_timesteps | 13471744 | +| train/ | | +| approx_kl | 0.011819597 | +| clip_fraction | 0.32 | +| clip_range | 0.0716 | +| entropy_loss | -7.24 | +| explained_variance | 0.287 | +| learning_rate | 4.68e-05 | +| loss | -0.0254 | +| n_updates | 42128 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000165 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1421 | +| iterations | 6579 | +| time_elapsed | 9475 | +| total_timesteps | 13473792 | +| train/ | | +| approx_kl | 0.009443071 | +| clip_fraction | 0.299 | +| clip_range | 0.0716 | +| entropy_loss | -7.43 | +| explained_variance | 0.286 | +| learning_rate | 4.68e-05 | +| loss | -0.0329 | +| n_updates | 42132 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.00017 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1421 | +| iterations | 6580 | +| time_elapsed | 9477 | +| total_timesteps | 13475840 | +| train/ | | +| approx_kl | 0.010787841 | +| clip_fraction | 0.282 | +| clip_range | 0.0716 | +| entropy_loss | -7.45 | +| explained_variance | 0.0303 | +| learning_rate | 4.68e-05 | +| loss | -0.0283 | +| n_updates | 42136 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000157 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1421 | +| iterations | 6581 | +| time_elapsed | 9478 | +| total_timesteps | 13477888 | +| train/ | | +| approx_kl | 0.007616905 | +| clip_fraction | 0.262 | +| clip_range | 0.0716 | +| entropy_loss | -7.05 | +| explained_variance | 0.221 | +| learning_rate | 4.68e-05 | +| loss | -0.0247 | +| n_updates | 42140 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000364 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1421 | +| iterations | 6582 | +| time_elapsed | 9479 | +| total_timesteps | 13479936 | +| train/ | | +| approx_kl | 0.008567523 | +| clip_fraction | 0.286 | +| clip_range | 0.0716 | +| entropy_loss | -7.07 | +| explained_variance | 0.333 | +| learning_rate | 4.68e-05 | +| loss | -0.0298 | +| n_updates | 42144 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000298 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1421 | +| iterations | 6583 | +| time_elapsed | 9481 | +| total_timesteps | 13481984 | +| train/ | | +| approx_kl | 0.011407599 | +| clip_fraction | 0.315 | +| clip_range | 0.0716 | +| entropy_loss | -7.21 | +| explained_variance | 0.183 | +| learning_rate | 4.68e-05 | +| loss | -0.0347 | +| n_updates | 42148 | +| policy_gradient_loss | -0.0223 | +| value_loss | 0.000145 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1421 | +| iterations | 6584 | +| time_elapsed | 9482 | +| total_timesteps | 13484032 | +| train/ | | +| approx_kl | 0.01062323 | +| clip_fraction | 0.325 | +| clip_range | 0.0716 | +| entropy_loss | -7.37 | +| explained_variance | -0.255 | +| learning_rate | 4.68e-05 | +| loss | -0.0351 | +| n_updates | 42152 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000132 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1421 | +| iterations | 6585 | +| time_elapsed | 9484 | +| total_timesteps | 13486080 | +| train/ | | +| approx_kl | 0.0090268655 | +| clip_fraction | 0.28 | +| clip_range | 0.0716 | +| entropy_loss | -7.21 | +| explained_variance | 0.115 | +| learning_rate | 4.68e-05 | +| loss | -0.0175 | +| n_updates | 42156 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000352 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1421 | +| iterations | 6586 | +| time_elapsed | 9485 | +| total_timesteps | 13488128 | +| train/ | | +| approx_kl | 0.01039875 | +| clip_fraction | 0.316 | +| clip_range | 0.0716 | +| entropy_loss | -7.1 | +| explained_variance | 0.343 | +| learning_rate | 4.68e-05 | +| loss | -0.0358 | +| n_updates | 42160 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000235 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1421 | +| iterations | 6587 | +| time_elapsed | 9487 | +| total_timesteps | 13490176 | +| train/ | | +| approx_kl | 0.011213346 | +| clip_fraction | 0.318 | +| clip_range | 0.0716 | +| entropy_loss | -7.13 | +| explained_variance | 0.219 | +| learning_rate | 4.68e-05 | +| loss | -0.0363 | +| n_updates | 42164 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000107 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1421 | +| iterations | 6588 | +| time_elapsed | 9488 | +| total_timesteps | 13492224 | +| train/ | | +| approx_kl | 0.007663759 | +| clip_fraction | 0.283 | +| clip_range | 0.0716 | +| entropy_loss | -7.19 | +| explained_variance | 0.395 | +| learning_rate | 4.68e-05 | +| loss | -0.0237 | +| n_updates | 42168 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000203 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1421 | +| iterations | 6589 | +| time_elapsed | 9489 | +| total_timesteps | 13494272 | +| train/ | | +| approx_kl | 0.009868415 | +| clip_fraction | 0.306 | +| clip_range | 0.0716 | +| entropy_loss | -7.4 | +| explained_variance | 0.317 | +| learning_rate | 4.68e-05 | +| loss | -0.0305 | +| n_updates | 42172 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000104 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1421 | +| iterations | 6590 | +| time_elapsed | 9491 | +| total_timesteps | 13496320 | +| train/ | | +| approx_kl | 0.010778572 | +| clip_fraction | 0.267 | +| clip_range | 0.0716 | +| entropy_loss | -6.92 | +| explained_variance | 0.44 | +| learning_rate | 4.68e-05 | +| loss | -0.0259 | +| n_updates | 42176 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000245 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1421 | +| iterations | 6591 | +| time_elapsed | 9492 | +| total_timesteps | 13498368 | +| train/ | | +| approx_kl | 0.009926844 | +| clip_fraction | 0.296 | +| clip_range | 0.0716 | +| entropy_loss | -7.25 | +| explained_variance | 0.246 | +| learning_rate | 4.68e-05 | +| loss | -0.0325 | +| n_updates | 42180 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000237 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1421 | +| iterations | 6592 | +| time_elapsed | 9494 | +| total_timesteps | 13500416 | +| train/ | | +| approx_kl | 0.01116352 | +| clip_fraction | 0.32 | +| clip_range | 0.0716 | +| entropy_loss | -7.09 | +| explained_variance | 0.382 | +| learning_rate | 4.68e-05 | +| loss | -0.0282 | +| n_updates | 42184 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000237 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1421 | +| iterations | 6593 | +| time_elapsed | 9495 | +| total_timesteps | 13502464 | +| train/ | | +| approx_kl | 0.012296601 | +| clip_fraction | 0.283 | +| clip_range | 0.0716 | +| entropy_loss | -6.43 | +| explained_variance | 0.432 | +| learning_rate | 4.68e-05 | +| loss | -0.0244 | +| n_updates | 42188 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.00052 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1421 | +| iterations | 6594 | +| time_elapsed | 9497 | +| total_timesteps | 13504512 | +| train/ | | +| approx_kl | 0.010333399 | +| clip_fraction | 0.323 | +| clip_range | 0.0716 | +| entropy_loss | -7.35 | +| explained_variance | -0.11 | +| learning_rate | 4.68e-05 | +| loss | -0.0372 | +| n_updates | 42192 | +| policy_gradient_loss | -0.0219 | +| value_loss | 0.000162 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1421 | +| iterations | 6595 | +| time_elapsed | 9498 | +| total_timesteps | 13506560 | +| train/ | | +| approx_kl | 0.009172526 | +| clip_fraction | 0.311 | +| clip_range | 0.0716 | +| entropy_loss | -7.55 | +| explained_variance | -0.209 | +| learning_rate | 4.68e-05 | +| loss | -0.0331 | +| n_updates | 42196 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000178 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1421 | +| iterations | 6596 | +| time_elapsed | 9500 | +| total_timesteps | 13508608 | +| train/ | | +| approx_kl | 0.009587169 | +| clip_fraction | 0.292 | +| clip_range | 0.0716 | +| entropy_loss | -7.37 | +| explained_variance | 0.104 | +| learning_rate | 4.68e-05 | +| loss | -0.0291 | +| n_updates | 42200 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000334 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1421 | +| iterations | 6597 | +| time_elapsed | 9501 | +| total_timesteps | 13510656 | +| train/ | | +| approx_kl | 0.01077856 | +| clip_fraction | 0.311 | +| clip_range | 0.0716 | +| entropy_loss | -7.09 | +| explained_variance | 0.427 | +| learning_rate | 4.68e-05 | +| loss | -0.0337 | +| n_updates | 42204 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000147 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1421 | +| iterations | 6598 | +| time_elapsed | 9502 | +| total_timesteps | 13512704 | +| train/ | | +| approx_kl | 0.00900204 | +| clip_fraction | 0.319 | +| clip_range | 0.0716 | +| entropy_loss | -7.39 | +| explained_variance | -0.0502 | +| learning_rate | 4.68e-05 | +| loss | -0.0331 | +| n_updates | 42208 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.00014 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1421 | +| iterations | 6599 | +| time_elapsed | 9504 | +| total_timesteps | 13514752 | +| train/ | | +| approx_kl | 0.010875999 | +| clip_fraction | 0.311 | +| clip_range | 0.0716 | +| entropy_loss | -7.36 | +| explained_variance | -0.099 | +| learning_rate | 4.68e-05 | +| loss | -0.032 | +| n_updates | 42212 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.00015 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1421 | +| iterations | 6600 | +| time_elapsed | 9505 | +| total_timesteps | 13516800 | +| train/ | | +| approx_kl | 0.010064997 | +| clip_fraction | 0.291 | +| clip_range | 0.0716 | +| entropy_loss | -6.68 | +| explained_variance | 0.469 | +| learning_rate | 4.68e-05 | +| loss | -0.0247 | +| n_updates | 42216 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000269 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1421 | +| iterations | 6601 | +| time_elapsed | 9507 | +| total_timesteps | 13518848 | +| train/ | | +| approx_kl | 0.008949345 | +| clip_fraction | 0.309 | +| clip_range | 0.0716 | +| entropy_loss | -7.45 | +| explained_variance | 0.261 | +| learning_rate | 4.68e-05 | +| loss | -0.0317 | +| n_updates | 42220 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000153 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1421 | +| iterations | 6602 | +| time_elapsed | 9508 | +| total_timesteps | 13520896 | +| train/ | | +| approx_kl | 0.00853309 | +| clip_fraction | 0.288 | +| clip_range | 0.0716 | +| entropy_loss | -7.32 | +| explained_variance | 0.372 | +| learning_rate | 4.68e-05 | +| loss | -0.0274 | +| n_updates | 42224 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000106 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1421 | +| iterations | 6603 | +| time_elapsed | 9510 | +| total_timesteps | 13522944 | +| train/ | | +| approx_kl | 0.008906656 | +| clip_fraction | 0.303 | +| clip_range | 0.0716 | +| entropy_loss | -6.99 | +| explained_variance | 0.631 | +| learning_rate | 4.68e-05 | +| loss | -0.028 | +| n_updates | 42228 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.00012 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1421 | +| iterations | 6604 | +| time_elapsed | 9511 | +| total_timesteps | 13524992 | +| train/ | | +| approx_kl | 0.009335894 | +| clip_fraction | 0.287 | +| clip_range | 0.0716 | +| entropy_loss | -7.34 | +| explained_variance | 0.0152 | +| learning_rate | 4.68e-05 | +| loss | -0.0266 | +| n_updates | 42232 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000167 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1421 | +| iterations | 6605 | +| time_elapsed | 9512 | +| total_timesteps | 13527040 | +| train/ | | +| approx_kl | 0.011118023 | +| clip_fraction | 0.335 | +| clip_range | 0.0716 | +| entropy_loss | -7.31 | +| explained_variance | 0.307 | +| learning_rate | 4.68e-05 | +| loss | -0.0296 | +| n_updates | 42236 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.00013 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1421 | +| iterations | 6606 | +| time_elapsed | 9514 | +| total_timesteps | 13529088 | +| train/ | | +| approx_kl | 0.010147718 | +| clip_fraction | 0.292 | +| clip_range | 0.0716 | +| entropy_loss | -6.92 | +| explained_variance | 0.477 | +| learning_rate | 4.68e-05 | +| loss | -0.0292 | +| n_updates | 42240 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000238 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1421 | +| iterations | 6607 | +| time_elapsed | 9515 | +| total_timesteps | 13531136 | +| train/ | | +| approx_kl | 0.009732975 | +| clip_fraction | 0.302 | +| clip_range | 0.0716 | +| entropy_loss | -6.84 | +| explained_variance | 0.541 | +| learning_rate | 4.68e-05 | +| loss | -0.0341 | +| n_updates | 42244 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000189 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1421 | +| iterations | 6608 | +| time_elapsed | 9517 | +| total_timesteps | 13533184 | +| train/ | | +| approx_kl | 0.009539435 | +| clip_fraction | 0.312 | +| clip_range | 0.0716 | +| entropy_loss | -7.17 | +| explained_variance | 0.441 | +| learning_rate | 4.68e-05 | +| loss | -0.0337 | +| n_updates | 42248 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000158 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1421 | +| iterations | 6609 | +| time_elapsed | 9518 | +| total_timesteps | 13535232 | +| train/ | | +| approx_kl | 0.010542354 | +| clip_fraction | 0.313 | +| clip_range | 0.0716 | +| entropy_loss | -7.37 | +| explained_variance | 0.112 | +| learning_rate | 4.68e-05 | +| loss | -0.0341 | +| n_updates | 42252 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000244 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1421 | +| iterations | 6610 | +| time_elapsed | 9520 | +| total_timesteps | 13537280 | +| train/ | | +| approx_kl | 0.0098072775 | +| clip_fraction | 0.292 | +| clip_range | 0.0716 | +| entropy_loss | -7.1 | +| explained_variance | 0.43 | +| learning_rate | 4.68e-05 | +| loss | -0.027 | +| n_updates | 42256 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000211 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1421 | +| iterations | 6611 | +| time_elapsed | 9521 | +| total_timesteps | 13539328 | +| train/ | | +| approx_kl | 0.012431655 | +| clip_fraction | 0.297 | +| clip_range | 0.0716 | +| entropy_loss | -7.09 | +| explained_variance | 0.35 | +| learning_rate | 4.68e-05 | +| loss | -0.0314 | +| n_updates | 42260 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000254 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1421 | +| iterations | 6612 | +| time_elapsed | 9522 | +| total_timesteps | 13541376 | +| train/ | | +| approx_kl | 0.010951129 | +| clip_fraction | 0.351 | +| clip_range | 0.0716 | +| entropy_loss | -7.37 | +| explained_variance | -0.334 | +| learning_rate | 4.68e-05 | +| loss | -0.047 | +| n_updates | 42264 | +| policy_gradient_loss | -0.0248 | +| value_loss | 8.71e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1421 | +| iterations | 6613 | +| time_elapsed | 9524 | +| total_timesteps | 13543424 | +| train/ | | +| approx_kl | 0.010890035 | +| clip_fraction | 0.315 | +| clip_range | 0.0716 | +| entropy_loss | -6.93 | +| explained_variance | 0.51 | +| learning_rate | 4.68e-05 | +| loss | -0.0313 | +| n_updates | 42268 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000185 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1421 | +| iterations | 6614 | +| time_elapsed | 9525 | +| total_timesteps | 13545472 | +| train/ | | +| approx_kl | 0.011065434 | +| clip_fraction | 0.306 | +| clip_range | 0.0716 | +| entropy_loss | -7.05 | +| explained_variance | 0.551 | +| learning_rate | 4.68e-05 | +| loss | -0.0314 | +| n_updates | 42272 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000116 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1422 | +| iterations | 6615 | +| time_elapsed | 9527 | +| total_timesteps | 13547520 | +| train/ | | +| approx_kl | 0.010052772 | +| clip_fraction | 0.297 | +| clip_range | 0.0716 | +| entropy_loss | -7.44 | +| explained_variance | -0.0456 | +| learning_rate | 4.68e-05 | +| loss | -0.031 | +| n_updates | 42276 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.00013 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1421 | +| iterations | 6616 | +| time_elapsed | 9528 | +| total_timesteps | 13549568 | +| train/ | | +| approx_kl | 0.011785334 | +| clip_fraction | 0.305 | +| clip_range | 0.0716 | +| entropy_loss | -7.36 | +| explained_variance | 0.318 | +| learning_rate | 4.68e-05 | +| loss | -0.0292 | +| n_updates | 42280 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000147 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1422 | +| iterations | 6617 | +| time_elapsed | 9529 | +| total_timesteps | 13551616 | +| train/ | | +| approx_kl | 0.010891711 | +| clip_fraction | 0.333 | +| clip_range | 0.0716 | +| entropy_loss | -6.92 | +| explained_variance | 0.31 | +| learning_rate | 4.68e-05 | +| loss | -0.0299 | +| n_updates | 42284 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000292 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1422 | +| iterations | 6618 | +| time_elapsed | 9531 | +| total_timesteps | 13553664 | +| train/ | | +| approx_kl | 0.01106434 | +| clip_fraction | 0.294 | +| clip_range | 0.0716 | +| entropy_loss | -6.99 | +| explained_variance | 0.351 | +| learning_rate | 4.68e-05 | +| loss | -0.0224 | +| n_updates | 42288 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000297 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1421 | +| iterations | 6619 | +| time_elapsed | 9532 | +| total_timesteps | 13555712 | +| train/ | | +| approx_kl | 0.010881409 | +| clip_fraction | 0.313 | +| clip_range | 0.0716 | +| entropy_loss | -7.16 | +| explained_variance | 0.103 | +| learning_rate | 4.68e-05 | +| loss | -0.0369 | +| n_updates | 42292 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000147 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1421 | +| iterations | 6620 | +| time_elapsed | 9534 | +| total_timesteps | 13557760 | +| train/ | | +| approx_kl | 0.010171992 | +| clip_fraction | 0.318 | +| clip_range | 0.0716 | +| entropy_loss | -7.13 | +| explained_variance | 0.459 | +| learning_rate | 4.68e-05 | +| loss | -0.0311 | +| n_updates | 42296 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000117 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1421 | +| iterations | 6621 | +| time_elapsed | 9535 | +| total_timesteps | 13559808 | +| train/ | | +| approx_kl | 0.0073930854 | +| clip_fraction | 0.277 | +| clip_range | 0.0716 | +| entropy_loss | -6.96 | +| explained_variance | 0.264 | +| learning_rate | 4.68e-05 | +| loss | -0.0212 | +| n_updates | 42300 | +| policy_gradient_loss | -0.0137 | +| value_loss | 0.000435 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1421 | +| iterations | 6622 | +| time_elapsed | 9537 | +| total_timesteps | 13561856 | +| train/ | | +| approx_kl | 0.0102091115 | +| clip_fraction | 0.325 | +| clip_range | 0.0716 | +| entropy_loss | -6.99 | +| explained_variance | 0.4 | +| learning_rate | 4.68e-05 | +| loss | -0.0403 | +| n_updates | 42304 | +| policy_gradient_loss | -0.0219 | +| value_loss | 0.000149 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1422 | +| iterations | 6623 | +| time_elapsed | 9538 | +| total_timesteps | 13563904 | +| train/ | | +| approx_kl | 0.010898948 | +| clip_fraction | 0.323 | +| clip_range | 0.0716 | +| entropy_loss | -6.93 | +| explained_variance | 0.62 | +| learning_rate | 4.68e-05 | +| loss | -0.0352 | +| n_updates | 42308 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000118 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1422 | +| iterations | 6624 | +| time_elapsed | 9539 | +| total_timesteps | 13565952 | +| train/ | | +| approx_kl | 0.008914466 | +| clip_fraction | 0.316 | +| clip_range | 0.0716 | +| entropy_loss | -7.1 | +| explained_variance | 0.47 | +| learning_rate | 4.68e-05 | +| loss | -0.0306 | +| n_updates | 42312 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000158 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1422 | +| iterations | 6625 | +| time_elapsed | 9541 | +| total_timesteps | 13568000 | +| train/ | | +| approx_kl | 0.011606796 | +| clip_fraction | 0.332 | +| clip_range | 0.0716 | +| entropy_loss | -7.44 | +| explained_variance | -0.0738 | +| learning_rate | 4.68e-05 | +| loss | -0.0336 | +| n_updates | 42316 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000128 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1422 | +| iterations | 6626 | +| time_elapsed | 9542 | +| total_timesteps | 13570048 | +| train/ | | +| approx_kl | 0.011000967 | +| clip_fraction | 0.297 | +| clip_range | 0.0716 | +| entropy_loss | -7.07 | +| explained_variance | 0.42 | +| learning_rate | 4.68e-05 | +| loss | -0.0291 | +| n_updates | 42320 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000178 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1422 | +| iterations | 6627 | +| time_elapsed | 9544 | +| total_timesteps | 13572096 | +| train/ | | +| approx_kl | 0.009808569 | +| clip_fraction | 0.294 | +| clip_range | 0.0716 | +| entropy_loss | -7.44 | +| explained_variance | -0.00608 | +| learning_rate | 4.68e-05 | +| loss | -0.0315 | +| n_updates | 42324 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000246 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1422 | +| iterations | 6628 | +| time_elapsed | 9545 | +| total_timesteps | 13574144 | +| train/ | | +| approx_kl | 0.007582747 | +| clip_fraction | 0.277 | +| clip_range | 0.0716 | +| entropy_loss | -6.79 | +| explained_variance | 0.397 | +| learning_rate | 4.68e-05 | +| loss | -0.0304 | +| n_updates | 42328 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.0004 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1422 | +| iterations | 6629 | +| time_elapsed | 9547 | +| total_timesteps | 13576192 | +| train/ | | +| approx_kl | 0.010472573 | +| clip_fraction | 0.335 | +| clip_range | 0.0716 | +| entropy_loss | -7.36 | +| explained_variance | 0.318 | +| learning_rate | 4.68e-05 | +| loss | -0.0408 | +| n_updates | 42332 | +| policy_gradient_loss | -0.0227 | +| value_loss | 0.000132 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1422 | +| iterations | 6630 | +| time_elapsed | 9548 | +| total_timesteps | 13578240 | +| train/ | | +| approx_kl | 0.01224509 | +| clip_fraction | 0.323 | +| clip_range | 0.0716 | +| entropy_loss | -7.13 | +| explained_variance | 0.441 | +| learning_rate | 4.68e-05 | +| loss | -0.0323 | +| n_updates | 42336 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000158 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1422 | +| iterations | 6631 | +| time_elapsed | 9549 | +| total_timesteps | 13580288 | +| train/ | | +| approx_kl | 0.011774179 | +| clip_fraction | 0.318 | +| clip_range | 0.0716 | +| entropy_loss | -7.47 | +| explained_variance | -0.0875 | +| learning_rate | 4.68e-05 | +| loss | -0.0387 | +| n_updates | 42340 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000146 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1422 | +| iterations | 6632 | +| time_elapsed | 9551 | +| total_timesteps | 13582336 | +| train/ | | +| approx_kl | 0.011694428 | +| clip_fraction | 0.321 | +| clip_range | 0.0716 | +| entropy_loss | -7.18 | +| explained_variance | 0.196 | +| learning_rate | 4.68e-05 | +| loss | -0.0321 | +| n_updates | 42344 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000162 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1422 | +| iterations | 6633 | +| time_elapsed | 9552 | +| total_timesteps | 13584384 | +| train/ | | +| approx_kl | 0.012278207 | +| clip_fraction | 0.333 | +| clip_range | 0.0716 | +| entropy_loss | -6.93 | +| explained_variance | 0.504 | +| learning_rate | 4.68e-05 | +| loss | -0.0338 | +| n_updates | 42348 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000108 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1422 | +| iterations | 6634 | +| time_elapsed | 9554 | +| total_timesteps | 13586432 | +| train/ | | +| approx_kl | 0.009866463 | +| clip_fraction | 0.297 | +| clip_range | 0.0716 | +| entropy_loss | -7.37 | +| explained_variance | 0.196 | +| learning_rate | 4.68e-05 | +| loss | -0.0317 | +| n_updates | 42352 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000217 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1422 | +| iterations | 6635 | +| time_elapsed | 9555 | +| total_timesteps | 13588480 | +| train/ | | +| approx_kl | 0.009882987 | +| clip_fraction | 0.285 | +| clip_range | 0.0716 | +| entropy_loss | -6.93 | +| explained_variance | 0.363 | +| learning_rate | 4.68e-05 | +| loss | -0.0266 | +| n_updates | 42356 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000365 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1422 | +| iterations | 6636 | +| time_elapsed | 9556 | +| total_timesteps | 13590528 | +| train/ | | +| approx_kl | 0.010372589 | +| clip_fraction | 0.292 | +| clip_range | 0.0716 | +| entropy_loss | -7.23 | +| explained_variance | 0.261 | +| learning_rate | 4.68e-05 | +| loss | -0.0323 | +| n_updates | 42360 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000237 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1422 | +| iterations | 6637 | +| time_elapsed | 9558 | +| total_timesteps | 13592576 | +| train/ | | +| approx_kl | 0.0104075335 | +| clip_fraction | 0.332 | +| clip_range | 0.0716 | +| entropy_loss | -7.38 | +| explained_variance | 0.387 | +| learning_rate | 4.68e-05 | +| loss | -0.026 | +| n_updates | 42364 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.00011 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1422 | +| iterations | 6638 | +| time_elapsed | 9559 | +| total_timesteps | 13594624 | +| train/ | | +| approx_kl | 0.010604473 | +| clip_fraction | 0.32 | +| clip_range | 0.0716 | +| entropy_loss | -7.01 | +| explained_variance | 0.439 | +| learning_rate | 4.68e-05 | +| loss | -0.0311 | +| n_updates | 42368 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000191 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1422 | +| iterations | 6639 | +| time_elapsed | 9561 | +| total_timesteps | 13596672 | +| train/ | | +| approx_kl | 0.010253632 | +| clip_fraction | 0.302 | +| clip_range | 0.0716 | +| entropy_loss | -7.01 | +| explained_variance | 0.574 | +| learning_rate | 4.68e-05 | +| loss | -0.0347 | +| n_updates | 42372 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.00013 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1422 | +| iterations | 6640 | +| time_elapsed | 9562 | +| total_timesteps | 13598720 | +| train/ | | +| approx_kl | 0.009775555 | +| clip_fraction | 0.316 | +| clip_range | 0.0716 | +| entropy_loss | -7.4 | +| explained_variance | 0.103 | +| learning_rate | 4.68e-05 | +| loss | -0.0284 | +| n_updates | 42376 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000175 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1422 | +| iterations | 6641 | +| time_elapsed | 9564 | +| total_timesteps | 13600768 | +| train/ | | +| approx_kl | 0.010824112 | +| clip_fraction | 0.307 | +| clip_range | 0.0716 | +| entropy_loss | -7.46 | +| explained_variance | -0.0962 | +| learning_rate | 4.68e-05 | +| loss | -0.0348 | +| n_updates | 42380 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000169 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1422 | +| iterations | 6642 | +| time_elapsed | 9565 | +| total_timesteps | 13602816 | +| train/ | | +| approx_kl | 0.009459074 | +| clip_fraction | 0.293 | +| clip_range | 0.0716 | +| entropy_loss | -7.21 | +| explained_variance | 0.304 | +| learning_rate | 4.68e-05 | +| loss | -0.0301 | +| n_updates | 42384 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000227 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1422 | +| iterations | 6643 | +| time_elapsed | 9566 | +| total_timesteps | 13604864 | +| train/ | | +| approx_kl | 0.00993097 | +| clip_fraction | 0.319 | +| clip_range | 0.0716 | +| entropy_loss | -7.04 | +| explained_variance | 0.777 | +| learning_rate | 4.68e-05 | +| loss | -0.0389 | +| n_updates | 42388 | +| policy_gradient_loss | -0.022 | +| value_loss | 6.21e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1422 | +| iterations | 6644 | +| time_elapsed | 9568 | +| total_timesteps | 13606912 | +| train/ | | +| approx_kl | 0.008657153 | +| clip_fraction | 0.276 | +| clip_range | 0.0716 | +| entropy_loss | -7.15 | +| explained_variance | 0.46 | +| learning_rate | 4.68e-05 | +| loss | -0.03 | +| n_updates | 42392 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000185 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1422 | +| iterations | 6645 | +| time_elapsed | 9569 | +| total_timesteps | 13608960 | +| train/ | | +| approx_kl | 0.009950703 | +| clip_fraction | 0.316 | +| clip_range | 0.0716 | +| entropy_loss | -7.01 | +| explained_variance | 0.664 | +| learning_rate | 4.68e-05 | +| loss | -0.0368 | +| n_updates | 42396 | +| policy_gradient_loss | -0.0203 | +| value_loss | 7.25e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1422 | +| iterations | 6646 | +| time_elapsed | 9571 | +| total_timesteps | 13611008 | +| train/ | | +| approx_kl | 0.012598991 | +| clip_fraction | 0.305 | +| clip_range | 0.0716 | +| entropy_loss | -7.27 | +| explained_variance | 0.309 | +| learning_rate | 4.68e-05 | +| loss | -0.0327 | +| n_updates | 42400 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000143 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1422 | +| iterations | 6647 | +| time_elapsed | 9572 | +| total_timesteps | 13613056 | +| train/ | | +| approx_kl | 0.010282748 | +| clip_fraction | 0.326 | +| clip_range | 0.0716 | +| entropy_loss | -6.96 | +| explained_variance | 0.648 | +| learning_rate | 4.68e-05 | +| loss | -0.0308 | +| n_updates | 42404 | +| policy_gradient_loss | -0.0208 | +| value_loss | 9.75e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1422 | +| iterations | 6648 | +| time_elapsed | 9574 | +| total_timesteps | 13615104 | +| train/ | | +| approx_kl | 0.01074503 | +| clip_fraction | 0.321 | +| clip_range | 0.0716 | +| entropy_loss | -7.18 | +| explained_variance | 0.351 | +| learning_rate | 4.68e-05 | +| loss | -0.0334 | +| n_updates | 42408 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000147 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1422 | +| iterations | 6649 | +| time_elapsed | 9575 | +| total_timesteps | 13617152 | +| train/ | | +| approx_kl | 0.011831319 | +| clip_fraction | 0.302 | +| clip_range | 0.0716 | +| entropy_loss | -6.97 | +| explained_variance | 0.357 | +| learning_rate | 4.68e-05 | +| loss | -0.0313 | +| n_updates | 42412 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000159 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1422 | +| iterations | 6650 | +| time_elapsed | 9577 | +| total_timesteps | 13619200 | +| train/ | | +| approx_kl | 0.01181915 | +| clip_fraction | 0.361 | +| clip_range | 0.0716 | +| entropy_loss | -7.2 | +| explained_variance | 0.771 | +| learning_rate | 4.68e-05 | +| loss | -0.044 | +| n_updates | 42416 | +| policy_gradient_loss | -0.0276 | +| value_loss | 3.79e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1422 | +| iterations | 6651 | +| time_elapsed | 9578 | +| total_timesteps | 13621248 | +| train/ | | +| approx_kl | 0.009641126 | +| clip_fraction | 0.302 | +| clip_range | 0.0716 | +| entropy_loss | -7.14 | +| explained_variance | 0.582 | +| learning_rate | 4.68e-05 | +| loss | -0.0323 | +| n_updates | 42420 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000115 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1422 | +| iterations | 6652 | +| time_elapsed | 9579 | +| total_timesteps | 13623296 | +| train/ | | +| approx_kl | 0.011486826 | +| clip_fraction | 0.307 | +| clip_range | 0.0716 | +| entropy_loss | -7.28 | +| explained_variance | 0.391 | +| learning_rate | 4.68e-05 | +| loss | -0.0278 | +| n_updates | 42424 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000101 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1422 | +| iterations | 6653 | +| time_elapsed | 9581 | +| total_timesteps | 13625344 | +| train/ | | +| approx_kl | 0.009590925 | +| clip_fraction | 0.289 | +| clip_range | 0.0716 | +| entropy_loss | -7.31 | +| explained_variance | 0.26 | +| learning_rate | 4.68e-05 | +| loss | -0.0334 | +| n_updates | 42428 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000235 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1422 | +| iterations | 6654 | +| time_elapsed | 9582 | +| total_timesteps | 13627392 | +| train/ | | +| approx_kl | 0.012411446 | +| clip_fraction | 0.305 | +| clip_range | 0.0716 | +| entropy_loss | -7.29 | +| explained_variance | 0.212 | +| learning_rate | 4.68e-05 | +| loss | -0.0263 | +| n_updates | 42432 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000171 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1422 | +| iterations | 6655 | +| time_elapsed | 9584 | +| total_timesteps | 13629440 | +| train/ | | +| approx_kl | 0.011287373 | +| clip_fraction | 0.32 | +| clip_range | 0.0716 | +| entropy_loss | -7.17 | +| explained_variance | 0.463 | +| learning_rate | 4.68e-05 | +| loss | -0.0329 | +| n_updates | 42436 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000156 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1422 | +| iterations | 6656 | +| time_elapsed | 9585 | +| total_timesteps | 13631488 | +| train/ | | +| approx_kl | 0.011208845 | +| clip_fraction | 0.344 | +| clip_range | 0.0716 | +| entropy_loss | -6.86 | +| explained_variance | 0.375 | +| learning_rate | 4.68e-05 | +| loss | -0.0278 | +| n_updates | 42440 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000112 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1422 | +| iterations | 6657 | +| time_elapsed | 9587 | +| total_timesteps | 13633536 | +| train/ | | +| approx_kl | 0.009325523 | +| clip_fraction | 0.287 | +| clip_range | 0.0716 | +| entropy_loss | -6.7 | +| explained_variance | 0.342 | +| learning_rate | 4.68e-05 | +| loss | -0.0227 | +| n_updates | 42444 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000402 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1422 | +| iterations | 6658 | +| time_elapsed | 9588 | +| total_timesteps | 13635584 | +| train/ | | +| approx_kl | 0.011456925 | +| clip_fraction | 0.345 | +| clip_range | 0.0716 | +| entropy_loss | -7.31 | +| explained_variance | 0.497 | +| learning_rate | 4.68e-05 | +| loss | -0.0396 | +| n_updates | 42448 | +| policy_gradient_loss | -0.0243 | +| value_loss | 6.82e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1422 | +| iterations | 6659 | +| time_elapsed | 9589 | +| total_timesteps | 13637632 | +| train/ | | +| approx_kl | 0.0099000875 | +| clip_fraction | 0.309 | +| clip_range | 0.0716 | +| entropy_loss | -7.13 | +| explained_variance | 0.315 | +| learning_rate | 4.68e-05 | +| loss | -0.0307 | +| n_updates | 42452 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000157 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1422 | +| iterations | 6660 | +| time_elapsed | 9591 | +| total_timesteps | 13639680 | +| train/ | | +| approx_kl | 0.011022215 | +| clip_fraction | 0.324 | +| clip_range | 0.0716 | +| entropy_loss | -7.48 | +| explained_variance | -0.119 | +| learning_rate | 4.68e-05 | +| loss | -0.0327 | +| n_updates | 42456 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000131 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1422 | +| iterations | 6661 | +| time_elapsed | 9592 | +| total_timesteps | 13641728 | +| train/ | | +| approx_kl | 0.01001619 | +| clip_fraction | 0.295 | +| clip_range | 0.0716 | +| entropy_loss | -7.4 | +| explained_variance | 0.00817 | +| learning_rate | 4.68e-05 | +| loss | -0.0298 | +| n_updates | 42460 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000161 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1422 | +| iterations | 6662 | +| time_elapsed | 9594 | +| total_timesteps | 13643776 | +| train/ | | +| approx_kl | 0.009620897 | +| clip_fraction | 0.286 | +| clip_range | 0.0716 | +| entropy_loss | -6.85 | +| explained_variance | 0.494 | +| learning_rate | 4.68e-05 | +| loss | -0.0308 | +| n_updates | 42464 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000298 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1422 | +| iterations | 6663 | +| time_elapsed | 9595 | +| total_timesteps | 13645824 | +| train/ | | +| approx_kl | 0.00969833 | +| clip_fraction | 0.291 | +| clip_range | 0.0716 | +| entropy_loss | -7.22 | +| explained_variance | 0.205 | +| learning_rate | 4.68e-05 | +| loss | -0.0209 | +| n_updates | 42468 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000287 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1422 | +| iterations | 6664 | +| time_elapsed | 9597 | +| total_timesteps | 13647872 | +| train/ | | +| approx_kl | 0.011843706 | +| clip_fraction | 0.35 | +| clip_range | 0.0716 | +| entropy_loss | -6.91 | +| explained_variance | 0.554 | +| learning_rate | 4.68e-05 | +| loss | -0.0344 | +| n_updates | 42472 | +| policy_gradient_loss | -0.0245 | +| value_loss | 9.37e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1422 | +| iterations | 6665 | +| time_elapsed | 9598 | +| total_timesteps | 13649920 | +| train/ | | +| approx_kl | 0.012254793 | +| clip_fraction | 0.349 | +| clip_range | 0.0716 | +| entropy_loss | -7.34 | +| explained_variance | 0.413 | +| learning_rate | 4.68e-05 | +| loss | -0.0419 | +| n_updates | 42476 | +| policy_gradient_loss | -0.0242 | +| value_loss | 8.87e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1422 | +| iterations | 6666 | +| time_elapsed | 9600 | +| total_timesteps | 13651968 | +| train/ | | +| approx_kl | 0.009530684 | +| clip_fraction | 0.311 | +| clip_range | 0.0716 | +| entropy_loss | -7.47 | +| explained_variance | -0.0452 | +| learning_rate | 4.68e-05 | +| loss | -0.0325 | +| n_updates | 42480 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000168 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1422 | +| iterations | 6667 | +| time_elapsed | 9601 | +| total_timesteps | 13654016 | +| train/ | | +| approx_kl | 0.0095721185 | +| clip_fraction | 0.298 | +| clip_range | 0.0716 | +| entropy_loss | -6.81 | +| explained_variance | 0.56 | +| learning_rate | 4.68e-05 | +| loss | -0.0268 | +| n_updates | 42484 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000202 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1422 | +| iterations | 6668 | +| time_elapsed | 9602 | +| total_timesteps | 13656064 | +| train/ | | +| approx_kl | 0.0098189805 | +| clip_fraction | 0.328 | +| clip_range | 0.0716 | +| entropy_loss | -7.37 | +| explained_variance | 0.00616 | +| learning_rate | 4.68e-05 | +| loss | -0.0339 | +| n_updates | 42488 | +| policy_gradient_loss | -0.0218 | +| value_loss | 8.63e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1422 | +| iterations | 6669 | +| time_elapsed | 9604 | +| total_timesteps | 13658112 | +| train/ | | +| approx_kl | 0.010890364 | +| clip_fraction | 0.327 | +| clip_range | 0.0716 | +| entropy_loss | -6.74 | +| explained_variance | 0.722 | +| learning_rate | 4.68e-05 | +| loss | -0.0264 | +| n_updates | 42492 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000142 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1422 | +| iterations | 6670 | +| time_elapsed | 9605 | +| total_timesteps | 13660160 | +| train/ | | +| approx_kl | 0.01105413 | +| clip_fraction | 0.312 | +| clip_range | 0.0716 | +| entropy_loss | -7.18 | +| explained_variance | 0.239 | +| learning_rate | 4.68e-05 | +| loss | -0.0312 | +| n_updates | 42496 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000234 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1422 | +| iterations | 6671 | +| time_elapsed | 9607 | +| total_timesteps | 13662208 | +| train/ | | +| approx_kl | 0.011373911 | +| clip_fraction | 0.3 | +| clip_range | 0.0716 | +| entropy_loss | -6.73 | +| explained_variance | 0.571 | +| learning_rate | 4.68e-05 | +| loss | -0.0327 | +| n_updates | 42500 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000181 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1422 | +| iterations | 6672 | +| time_elapsed | 9608 | +| total_timesteps | 13664256 | +| train/ | | +| approx_kl | 0.012912284 | +| clip_fraction | 0.335 | +| clip_range | 0.0716 | +| entropy_loss | -7.17 | +| explained_variance | 0.396 | +| learning_rate | 4.68e-05 | +| loss | -0.0366 | +| n_updates | 42504 | +| policy_gradient_loss | -0.0219 | +| value_loss | 0.00013 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1422 | +| iterations | 6673 | +| time_elapsed | 9610 | +| total_timesteps | 13666304 | +| train/ | | +| approx_kl | 0.012121232 | +| clip_fraction | 0.314 | +| clip_range | 0.0716 | +| entropy_loss | -7.3 | +| explained_variance | 0.192 | +| learning_rate | 4.68e-05 | +| loss | -0.0342 | +| n_updates | 42508 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000247 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1422 | +| iterations | 6674 | +| time_elapsed | 9611 | +| total_timesteps | 13668352 | +| train/ | | +| approx_kl | 0.011306841 | +| clip_fraction | 0.313 | +| clip_range | 0.0716 | +| entropy_loss | -7.36 | +| explained_variance | -0.0882 | +| learning_rate | 4.68e-05 | +| loss | -0.0309 | +| n_updates | 42512 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000132 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1422 | +| iterations | 6675 | +| time_elapsed | 9613 | +| total_timesteps | 13670400 | +| train/ | | +| approx_kl | 0.010503916 | +| clip_fraction | 0.293 | +| clip_range | 0.0716 | +| entropy_loss | -7.06 | +| explained_variance | 0.267 | +| learning_rate | 4.68e-05 | +| loss | -0.0329 | +| n_updates | 42516 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000227 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1422 | +| iterations | 6676 | +| time_elapsed | 9614 | +| total_timesteps | 13672448 | +| train/ | | +| approx_kl | 0.010129366 | +| clip_fraction | 0.294 | +| clip_range | 0.0716 | +| entropy_loss | -7.15 | +| explained_variance | 0.111 | +| learning_rate | 4.68e-05 | +| loss | -0.0317 | +| n_updates | 42520 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000376 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1422 | +| iterations | 6677 | +| time_elapsed | 9616 | +| total_timesteps | 13674496 | +| train/ | | +| approx_kl | 0.00985616 | +| clip_fraction | 0.28 | +| clip_range | 0.0716 | +| entropy_loss | -6.77 | +| explained_variance | 0.415 | +| learning_rate | 4.68e-05 | +| loss | -0.0241 | +| n_updates | 42524 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000318 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1422 | +| iterations | 6678 | +| time_elapsed | 9617 | +| total_timesteps | 13676544 | +| train/ | | +| approx_kl | 0.010670155 | +| clip_fraction | 0.348 | +| clip_range | 0.0716 | +| entropy_loss | -7.23 | +| explained_variance | 0.352 | +| learning_rate | 4.68e-05 | +| loss | -0.0366 | +| n_updates | 42528 | +| policy_gradient_loss | -0.0225 | +| value_loss | 0.000123 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1422 | +| iterations | 6679 | +| time_elapsed | 9618 | +| total_timesteps | 13678592 | +| train/ | | +| approx_kl | 0.01043129 | +| clip_fraction | 0.315 | +| clip_range | 0.0716 | +| entropy_loss | -7.2 | +| explained_variance | 0.4 | +| learning_rate | 4.68e-05 | +| loss | -0.0334 | +| n_updates | 42532 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000132 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1422 | +| iterations | 6680 | +| time_elapsed | 9620 | +| total_timesteps | 13680640 | +| train/ | | +| approx_kl | 0.013494648 | +| clip_fraction | 0.34 | +| clip_range | 0.0716 | +| entropy_loss | -7.2 | +| explained_variance | 0.214 | +| learning_rate | 4.68e-05 | +| loss | -0.0402 | +| n_updates | 42536 | +| policy_gradient_loss | -0.0229 | +| value_loss | 7.49e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1422 | +| iterations | 6681 | +| time_elapsed | 9621 | +| total_timesteps | 13682688 | +| train/ | | +| approx_kl | 0.010375157 | +| clip_fraction | 0.285 | +| clip_range | 0.0716 | +| entropy_loss | -7.15 | +| explained_variance | 0.522 | +| learning_rate | 4.68e-05 | +| loss | -0.0316 | +| n_updates | 42540 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000122 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1422 | +| iterations | 6682 | +| time_elapsed | 9623 | +| total_timesteps | 13684736 | +| train/ | | +| approx_kl | 0.0101909125 | +| clip_fraction | 0.308 | +| clip_range | 0.0716 | +| entropy_loss | -7.28 | +| explained_variance | 0.203 | +| learning_rate | 4.68e-05 | +| loss | -0.0329 | +| n_updates | 42544 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000111 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1422 | +| iterations | 6683 | +| time_elapsed | 9624 | +| total_timesteps | 13686784 | +| train/ | | +| approx_kl | 0.011221887 | +| clip_fraction | 0.316 | +| clip_range | 0.0716 | +| entropy_loss | -7.14 | +| explained_variance | 0.695 | +| learning_rate | 4.67e-05 | +| loss | -0.0304 | +| n_updates | 42548 | +| policy_gradient_loss | -0.0215 | +| value_loss | 7.62e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1422 | +| iterations | 6684 | +| time_elapsed | 9626 | +| total_timesteps | 13688832 | +| train/ | | +| approx_kl | 0.009634578 | +| clip_fraction | 0.308 | +| clip_range | 0.0716 | +| entropy_loss | -7.28 | +| explained_variance | 0.538 | +| learning_rate | 4.67e-05 | +| loss | -0.0358 | +| n_updates | 42552 | +| policy_gradient_loss | -0.0209 | +| value_loss | 8.1e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1422 | +| iterations | 6685 | +| time_elapsed | 9627 | +| total_timesteps | 13690880 | +| train/ | | +| approx_kl | 0.010630982 | +| clip_fraction | 0.305 | +| clip_range | 0.0716 | +| entropy_loss | -7.49 | +| explained_variance | -0.0185 | +| learning_rate | 4.67e-05 | +| loss | -0.0337 | +| n_updates | 42556 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000142 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1422 | +| iterations | 6686 | +| time_elapsed | 9628 | +| total_timesteps | 13692928 | +| train/ | | +| approx_kl | 0.009796007 | +| clip_fraction | 0.3 | +| clip_range | 0.0716 | +| entropy_loss | -6.81 | +| explained_variance | 0.353 | +| learning_rate | 4.67e-05 | +| loss | -0.0287 | +| n_updates | 42560 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000288 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1422 | +| iterations | 6687 | +| time_elapsed | 9630 | +| total_timesteps | 13694976 | +| train/ | | +| approx_kl | 0.012372277 | +| clip_fraction | 0.315 | +| clip_range | 0.0716 | +| entropy_loss | -7.21 | +| explained_variance | 0.299 | +| learning_rate | 4.67e-05 | +| loss | -0.03 | +| n_updates | 42564 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000177 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1422 | +| iterations | 6688 | +| time_elapsed | 9631 | +| total_timesteps | 13697024 | +| train/ | | +| approx_kl | 0.0104311 | +| clip_fraction | 0.302 | +| clip_range | 0.0716 | +| entropy_loss | -6.87 | +| explained_variance | 0.462 | +| learning_rate | 4.67e-05 | +| loss | -0.0263 | +| n_updates | 42568 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000242 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1422 | +| iterations | 6689 | +| time_elapsed | 9633 | +| total_timesteps | 13699072 | +| train/ | | +| approx_kl | 0.011510329 | +| clip_fraction | 0.31 | +| clip_range | 0.0716 | +| entropy_loss | -7.26 | +| explained_variance | 0.291 | +| learning_rate | 4.67e-05 | +| loss | -0.0354 | +| n_updates | 42572 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000151 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1422 | +| iterations | 6690 | +| time_elapsed | 9634 | +| total_timesteps | 13701120 | +| train/ | | +| approx_kl | 0.010051829 | +| clip_fraction | 0.307 | +| clip_range | 0.0716 | +| entropy_loss | -7.17 | +| explained_variance | 0.257 | +| learning_rate | 4.67e-05 | +| loss | -0.0339 | +| n_updates | 42576 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000233 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1422 | +| iterations | 6691 | +| time_elapsed | 9636 | +| total_timesteps | 13703168 | +| train/ | | +| approx_kl | 0.008596979 | +| clip_fraction | 0.294 | +| clip_range | 0.0716 | +| entropy_loss | -7.28 | +| explained_variance | 0.147 | +| learning_rate | 4.67e-05 | +| loss | -0.033 | +| n_updates | 42580 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000464 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1422 | +| iterations | 6692 | +| time_elapsed | 9637 | +| total_timesteps | 13705216 | +| train/ | | +| approx_kl | 0.010959007 | +| clip_fraction | 0.29 | +| clip_range | 0.0716 | +| entropy_loss | -7.05 | +| explained_variance | 0.239 | +| learning_rate | 4.67e-05 | +| loss | -0.0315 | +| n_updates | 42584 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000371 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1422 | +| iterations | 6693 | +| time_elapsed | 9638 | +| total_timesteps | 13707264 | +| train/ | | +| approx_kl | 0.012486372 | +| clip_fraction | 0.32 | +| clip_range | 0.0716 | +| entropy_loss | -6.7 | +| explained_variance | 0.589 | +| learning_rate | 4.67e-05 | +| loss | -0.031 | +| n_updates | 42588 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000176 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1422 | +| iterations | 6694 | +| time_elapsed | 9640 | +| total_timesteps | 13709312 | +| train/ | | +| approx_kl | 0.012355919 | +| clip_fraction | 0.362 | +| clip_range | 0.0716 | +| entropy_loss | -7.49 | +| explained_variance | -0.372 | +| learning_rate | 4.67e-05 | +| loss | -0.0452 | +| n_updates | 42592 | +| policy_gradient_loss | -0.0262 | +| value_loss | 6.77e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1422 | +| iterations | 6695 | +| time_elapsed | 9641 | +| total_timesteps | 13711360 | +| train/ | | +| approx_kl | 0.010072942 | +| clip_fraction | 0.314 | +| clip_range | 0.0716 | +| entropy_loss | -7.32 | +| explained_variance | 0.363 | +| learning_rate | 4.67e-05 | +| loss | -0.0336 | +| n_updates | 42596 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1422 | +| iterations | 6696 | +| time_elapsed | 9643 | +| total_timesteps | 13713408 | +| train/ | | +| approx_kl | 0.009030137 | +| clip_fraction | 0.28 | +| clip_range | 0.0716 | +| entropy_loss | -7.21 | +| explained_variance | 0.274 | +| learning_rate | 4.67e-05 | +| loss | -0.0312 | +| n_updates | 42600 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000197 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1422 | +| iterations | 6697 | +| time_elapsed | 9644 | +| total_timesteps | 13715456 | +| train/ | | +| approx_kl | 0.008451821 | +| clip_fraction | 0.302 | +| clip_range | 0.0716 | +| entropy_loss | -6.88 | +| explained_variance | 0.74 | +| learning_rate | 4.67e-05 | +| loss | -0.0363 | +| n_updates | 42604 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000116 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1422 | +| iterations | 6698 | +| time_elapsed | 9646 | +| total_timesteps | 13717504 | +| train/ | | +| approx_kl | 0.008717153 | +| clip_fraction | 0.312 | +| clip_range | 0.0716 | +| entropy_loss | -7.39 | +| explained_variance | 0.0548 | +| learning_rate | 4.67e-05 | +| loss | -0.0337 | +| n_updates | 42608 | +| policy_gradient_loss | -0.022 | +| value_loss | 0.000105 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1422 | +| iterations | 6699 | +| time_elapsed | 9647 | +| total_timesteps | 13719552 | +| train/ | | +| approx_kl | 0.0094761085 | +| clip_fraction | 0.304 | +| clip_range | 0.0716 | +| entropy_loss | -6.92 | +| explained_variance | 0.458 | +| learning_rate | 4.67e-05 | +| loss | -0.0231 | +| n_updates | 42612 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000286 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1422 | +| iterations | 6700 | +| time_elapsed | 9649 | +| total_timesteps | 13721600 | +| train/ | | +| approx_kl | 0.009189184 | +| clip_fraction | 0.331 | +| clip_range | 0.0716 | +| entropy_loss | -7.25 | +| explained_variance | 0.532 | +| learning_rate | 4.67e-05 | +| loss | -0.0365 | +| n_updates | 42616 | +| policy_gradient_loss | -0.0241 | +| value_loss | 6.64e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1422 | +| iterations | 6701 | +| time_elapsed | 9650 | +| total_timesteps | 13723648 | +| train/ | | +| approx_kl | 0.008903833 | +| clip_fraction | 0.283 | +| clip_range | 0.0716 | +| entropy_loss | -7.05 | +| explained_variance | 0.299 | +| learning_rate | 4.67e-05 | +| loss | -0.0301 | +| n_updates | 42620 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000295 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1422 | +| iterations | 6702 | +| time_elapsed | 9651 | +| total_timesteps | 13725696 | +| train/ | | +| approx_kl | 0.010601218 | +| clip_fraction | 0.285 | +| clip_range | 0.0716 | +| entropy_loss | -7.32 | +| explained_variance | 0.261 | +| learning_rate | 4.67e-05 | +| loss | -0.03 | +| n_updates | 42624 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000182 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1422 | +| iterations | 6703 | +| time_elapsed | 9653 | +| total_timesteps | 13727744 | +| train/ | | +| approx_kl | 0.008114506 | +| clip_fraction | 0.255 | +| clip_range | 0.0716 | +| entropy_loss | -7.15 | +| explained_variance | 0.236 | +| learning_rate | 4.67e-05 | +| loss | -0.0277 | +| n_updates | 42628 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000426 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1422 | +| iterations | 6704 | +| time_elapsed | 9654 | +| total_timesteps | 13729792 | +| train/ | | +| approx_kl | 0.0093356455 | +| clip_fraction | 0.314 | +| clip_range | 0.0716 | +| entropy_loss | -6.96 | +| explained_variance | 0.354 | +| learning_rate | 4.67e-05 | +| loss | -0.0275 | +| n_updates | 42632 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000225 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1422 | +| iterations | 6705 | +| time_elapsed | 9656 | +| total_timesteps | 13731840 | +| train/ | | +| approx_kl | 0.008538971 | +| clip_fraction | 0.3 | +| clip_range | 0.0716 | +| entropy_loss | -7.26 | +| explained_variance | 0.273 | +| learning_rate | 4.67e-05 | +| loss | -0.0305 | +| n_updates | 42636 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000142 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1422 | +| iterations | 6706 | +| time_elapsed | 9657 | +| total_timesteps | 13733888 | +| train/ | | +| approx_kl | 0.008485303 | +| clip_fraction | 0.31 | +| clip_range | 0.0716 | +| entropy_loss | -7.08 | +| explained_variance | 0.384 | +| learning_rate | 4.67e-05 | +| loss | -0.0235 | +| n_updates | 42640 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.00027 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1422 | +| iterations | 6707 | +| time_elapsed | 9659 | +| total_timesteps | 13735936 | +| train/ | | +| approx_kl | 0.010341679 | +| clip_fraction | 0.326 | +| clip_range | 0.0716 | +| entropy_loss | -7.22 | +| explained_variance | 0.329 | +| learning_rate | 4.67e-05 | +| loss | -0.0444 | +| n_updates | 42644 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000117 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1422 | +| iterations | 6708 | +| time_elapsed | 9660 | +| total_timesteps | 13737984 | +| train/ | | +| approx_kl | 0.011072021 | +| clip_fraction | 0.29 | +| clip_range | 0.0716 | +| entropy_loss | -7.46 | +| explained_variance | -0.0566 | +| learning_rate | 4.67e-05 | +| loss | -0.0261 | +| n_updates | 42648 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000151 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1422 | +| iterations | 6709 | +| time_elapsed | 9661 | +| total_timesteps | 13740032 | +| train/ | | +| approx_kl | 0.011413482 | +| clip_fraction | 0.293 | +| clip_range | 0.0716 | +| entropy_loss | -7.01 | +| explained_variance | 0.375 | +| learning_rate | 4.67e-05 | +| loss | -0.0304 | +| n_updates | 42652 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000209 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1422 | +| iterations | 6710 | +| time_elapsed | 9663 | +| total_timesteps | 13742080 | +| train/ | | +| approx_kl | 0.0113417795 | +| clip_fraction | 0.32 | +| clip_range | 0.0716 | +| entropy_loss | -7.11 | +| explained_variance | 0.28 | +| learning_rate | 4.67e-05 | +| loss | -0.03 | +| n_updates | 42656 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000113 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1422 | +| iterations | 6711 | +| time_elapsed | 9664 | +| total_timesteps | 13744128 | +| train/ | | +| approx_kl | 0.010103945 | +| clip_fraction | 0.303 | +| clip_range | 0.0716 | +| entropy_loss | -7.44 | +| explained_variance | -0.0438 | +| learning_rate | 4.67e-05 | +| loss | -0.0311 | +| n_updates | 42660 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000213 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1422 | +| iterations | 6712 | +| time_elapsed | 9666 | +| total_timesteps | 13746176 | +| train/ | | +| approx_kl | 0.010588307 | +| clip_fraction | 0.329 | +| clip_range | 0.0716 | +| entropy_loss | -7.33 | +| explained_variance | -0.138 | +| learning_rate | 4.67e-05 | +| loss | -0.0334 | +| n_updates | 42664 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000149 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1422 | +| iterations | 6713 | +| time_elapsed | 9667 | +| total_timesteps | 13748224 | +| train/ | | +| approx_kl | 0.0095115835 | +| clip_fraction | 0.298 | +| clip_range | 0.0716 | +| entropy_loss | -7.01 | +| explained_variance | 0.207 | +| learning_rate | 4.67e-05 | +| loss | -0.0229 | +| n_updates | 42668 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000224 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1422 | +| iterations | 6714 | +| time_elapsed | 9669 | +| total_timesteps | 13750272 | +| train/ | | +| approx_kl | 0.011611225 | +| clip_fraction | 0.304 | +| clip_range | 0.0716 | +| entropy_loss | -6.88 | +| explained_variance | 0.676 | +| learning_rate | 4.67e-05 | +| loss | -0.0323 | +| n_updates | 42672 | +| policy_gradient_loss | -0.0194 | +| value_loss | 9.92e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1422 | +| iterations | 6715 | +| time_elapsed | 9670 | +| total_timesteps | 13752320 | +| train/ | | +| approx_kl | 0.010945534 | +| clip_fraction | 0.321 | +| clip_range | 0.0716 | +| entropy_loss | -7.21 | +| explained_variance | 0.56 | +| learning_rate | 4.67e-05 | +| loss | -0.0344 | +| n_updates | 42676 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000111 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1422 | +| iterations | 6716 | +| time_elapsed | 9671 | +| total_timesteps | 13754368 | +| train/ | | +| approx_kl | 0.010268543 | +| clip_fraction | 0.33 | +| clip_range | 0.0716 | +| entropy_loss | -7.24 | +| explained_variance | -0.0218 | +| learning_rate | 4.67e-05 | +| loss | -0.0314 | +| n_updates | 42680 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000152 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1422 | +| iterations | 6717 | +| time_elapsed | 9673 | +| total_timesteps | 13756416 | +| train/ | | +| approx_kl | 0.009343475 | +| clip_fraction | 0.3 | +| clip_range | 0.0716 | +| entropy_loss | -7.11 | +| explained_variance | 0.491 | +| learning_rate | 4.67e-05 | +| loss | -0.0382 | +| n_updates | 42684 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000147 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1422 | +| iterations | 6718 | +| time_elapsed | 9674 | +| total_timesteps | 13758464 | +| train/ | | +| approx_kl | 0.009589821 | +| clip_fraction | 0.285 | +| clip_range | 0.0716 | +| entropy_loss | -7.43 | +| explained_variance | 0.26 | +| learning_rate | 4.67e-05 | +| loss | -0.0241 | +| n_updates | 42688 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000195 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1422 | +| iterations | 6719 | +| time_elapsed | 9676 | +| total_timesteps | 13760512 | +| train/ | | +| approx_kl | 0.009155667 | +| clip_fraction | 0.276 | +| clip_range | 0.0716 | +| entropy_loss | -7.03 | +| explained_variance | 0.25 | +| learning_rate | 4.67e-05 | +| loss | -0.0258 | +| n_updates | 42692 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000375 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1422 | +| iterations | 6720 | +| time_elapsed | 9677 | +| total_timesteps | 13762560 | +| train/ | | +| approx_kl | 0.011916723 | +| clip_fraction | 0.354 | +| clip_range | 0.0716 | +| entropy_loss | -7.01 | +| explained_variance | 0.698 | +| learning_rate | 4.67e-05 | +| loss | -0.0391 | +| n_updates | 42696 | +| policy_gradient_loss | -0.0246 | +| value_loss | 6.14e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1422 | +| iterations | 6721 | +| time_elapsed | 9678 | +| total_timesteps | 13764608 | +| train/ | | +| approx_kl | 0.009051425 | +| clip_fraction | 0.296 | +| clip_range | 0.0716 | +| entropy_loss | -6.88 | +| explained_variance | 0.453 | +| learning_rate | 4.67e-05 | +| loss | -0.0212 | +| n_updates | 42700 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000203 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1422 | +| iterations | 6722 | +| time_elapsed | 9680 | +| total_timesteps | 13766656 | +| train/ | | +| approx_kl | 0.012256819 | +| clip_fraction | 0.339 | +| clip_range | 0.0716 | +| entropy_loss | -6.77 | +| explained_variance | 0.849 | +| learning_rate | 4.67e-05 | +| loss | -0.0386 | +| n_updates | 42704 | +| policy_gradient_loss | -0.023 | +| value_loss | 5.17e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1422 | +| iterations | 6723 | +| time_elapsed | 9681 | +| total_timesteps | 13768704 | +| train/ | | +| approx_kl | 0.011071235 | +| clip_fraction | 0.316 | +| clip_range | 0.0716 | +| entropy_loss | -6.92 | +| explained_variance | 0.572 | +| learning_rate | 4.67e-05 | +| loss | -0.0315 | +| n_updates | 42708 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000129 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1422 | +| iterations | 6724 | +| time_elapsed | 9683 | +| total_timesteps | 13770752 | +| train/ | | +| approx_kl | 0.010046687 | +| clip_fraction | 0.308 | +| clip_range | 0.0716 | +| entropy_loss | -7.03 | +| explained_variance | 0.674 | +| learning_rate | 4.67e-05 | +| loss | -0.029 | +| n_updates | 42712 | +| policy_gradient_loss | -0.019 | +| value_loss | 7.68e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1422 | +| iterations | 6725 | +| time_elapsed | 9684 | +| total_timesteps | 13772800 | +| train/ | | +| approx_kl | 0.01072143 | +| clip_fraction | 0.321 | +| clip_range | 0.0716 | +| entropy_loss | -7.16 | +| explained_variance | 0.231 | +| learning_rate | 4.67e-05 | +| loss | -0.0323 | +| n_updates | 42716 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000192 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1422 | +| iterations | 6726 | +| time_elapsed | 9686 | +| total_timesteps | 13774848 | +| train/ | | +| approx_kl | 0.009377081 | +| clip_fraction | 0.291 | +| clip_range | 0.0716 | +| entropy_loss | -7.25 | +| explained_variance | 0.346 | +| learning_rate | 4.67e-05 | +| loss | -0.0319 | +| n_updates | 42720 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000151 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1422 | +| iterations | 6727 | +| time_elapsed | 9687 | +| total_timesteps | 13776896 | +| train/ | | +| approx_kl | 0.008723356 | +| clip_fraction | 0.305 | +| clip_range | 0.0716 | +| entropy_loss | -7.19 | +| explained_variance | 0.0545 | +| learning_rate | 4.67e-05 | +| loss | -0.0246 | +| n_updates | 42724 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000559 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1422 | +| iterations | 6728 | +| time_elapsed | 9689 | +| total_timesteps | 13778944 | +| train/ | | +| approx_kl | 0.009711891 | +| clip_fraction | 0.301 | +| clip_range | 0.0716 | +| entropy_loss | -7.15 | +| explained_variance | 0.409 | +| learning_rate | 4.67e-05 | +| loss | -0.0296 | +| n_updates | 42728 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.0002 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1422 | +| iterations | 6729 | +| time_elapsed | 9690 | +| total_timesteps | 13780992 | +| train/ | | +| approx_kl | 0.009104233 | +| clip_fraction | 0.292 | +| clip_range | 0.0716 | +| entropy_loss | -6.85 | +| explained_variance | 0.472 | +| learning_rate | 4.67e-05 | +| loss | -0.0269 | +| n_updates | 42732 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000293 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1422 | +| iterations | 6730 | +| time_elapsed | 9691 | +| total_timesteps | 13783040 | +| train/ | | +| approx_kl | 0.008883661 | +| clip_fraction | 0.288 | +| clip_range | 0.0716 | +| entropy_loss | -7.14 | +| explained_variance | 0.217 | +| learning_rate | 4.67e-05 | +| loss | -0.0316 | +| n_updates | 42736 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000271 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1422 | +| iterations | 6731 | +| time_elapsed | 9693 | +| total_timesteps | 13785088 | +| train/ | | +| approx_kl | 0.009981009 | +| clip_fraction | 0.337 | +| clip_range | 0.0716 | +| entropy_loss | -7.05 | +| explained_variance | 0.545 | +| learning_rate | 4.67e-05 | +| loss | -0.0386 | +| n_updates | 42740 | +| policy_gradient_loss | -0.0232 | +| value_loss | 9.27e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1422 | +| iterations | 6732 | +| time_elapsed | 9694 | +| total_timesteps | 13787136 | +| train/ | | +| approx_kl | 0.009530324 | +| clip_fraction | 0.28 | +| clip_range | 0.0716 | +| entropy_loss | -7.27 | +| explained_variance | 0.207 | +| learning_rate | 4.67e-05 | +| loss | -0.0261 | +| n_updates | 42744 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000298 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1422 | +| iterations | 6733 | +| time_elapsed | 9696 | +| total_timesteps | 13789184 | +| train/ | | +| approx_kl | 0.009774482 | +| clip_fraction | 0.294 | +| clip_range | 0.0716 | +| entropy_loss | -7.05 | +| explained_variance | 0.413 | +| learning_rate | 4.67e-05 | +| loss | -0.0276 | +| n_updates | 42748 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000206 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1422 | +| iterations | 6734 | +| time_elapsed | 9697 | +| total_timesteps | 13791232 | +| train/ | | +| approx_kl | 0.010285895 | +| clip_fraction | 0.325 | +| clip_range | 0.0716 | +| entropy_loss | -7.32 | +| explained_variance | 0.0893 | +| learning_rate | 4.67e-05 | +| loss | -0.0322 | +| n_updates | 42752 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000136 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1422 | +| iterations | 6735 | +| time_elapsed | 9698 | +| total_timesteps | 13793280 | +| train/ | | +| approx_kl | 0.008362589 | +| clip_fraction | 0.28 | +| clip_range | 0.0716 | +| entropy_loss | -6.76 | +| explained_variance | 0.39 | +| learning_rate | 4.67e-05 | +| loss | -0.0259 | +| n_updates | 42756 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.000326 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1422 | +| iterations | 6736 | +| time_elapsed | 9700 | +| total_timesteps | 13795328 | +| train/ | | +| approx_kl | 0.011670661 | +| clip_fraction | 0.337 | +| clip_range | 0.0716 | +| entropy_loss | -7.24 | +| explained_variance | 0.252 | +| learning_rate | 4.67e-05 | +| loss | -0.0409 | +| n_updates | 42760 | +| policy_gradient_loss | -0.0219 | +| value_loss | 0.000158 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1422 | +| iterations | 6737 | +| time_elapsed | 9701 | +| total_timesteps | 13797376 | +| train/ | | +| approx_kl | 0.011586143 | +| clip_fraction | 0.333 | +| clip_range | 0.0716 | +| entropy_loss | -7.06 | +| explained_variance | 0.297 | +| learning_rate | 4.67e-05 | +| loss | -0.0353 | +| n_updates | 42764 | +| policy_gradient_loss | -0.023 | +| value_loss | 0.000107 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1422 | +| iterations | 6738 | +| time_elapsed | 9703 | +| total_timesteps | 13799424 | +| train/ | | +| approx_kl | 0.010186039 | +| clip_fraction | 0.311 | +| clip_range | 0.0716 | +| entropy_loss | -6.79 | +| explained_variance | 0.481 | +| learning_rate | 4.67e-05 | +| loss | -0.0269 | +| n_updates | 42768 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.00018 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1422 | +| iterations | 6739 | +| time_elapsed | 9704 | +| total_timesteps | 13801472 | +| train/ | | +| approx_kl | 0.011650109 | +| clip_fraction | 0.335 | +| clip_range | 0.0716 | +| entropy_loss | -6.78 | +| explained_variance | 0.589 | +| learning_rate | 4.67e-05 | +| loss | -0.0306 | +| n_updates | 42772 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000141 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1422 | +| iterations | 6740 | +| time_elapsed | 9705 | +| total_timesteps | 13803520 | +| train/ | | +| approx_kl | 0.011482159 | +| clip_fraction | 0.351 | +| clip_range | 0.0715 | +| entropy_loss | -7.15 | +| explained_variance | 0.394 | +| learning_rate | 4.67e-05 | +| loss | -0.0386 | +| n_updates | 42776 | +| policy_gradient_loss | -0.0235 | +| value_loss | 9.03e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1422 | +| iterations | 6741 | +| time_elapsed | 9707 | +| total_timesteps | 13805568 | +| train/ | | +| approx_kl | 0.010132132 | +| clip_fraction | 0.294 | +| clip_range | 0.0715 | +| entropy_loss | -6.75 | +| explained_variance | 0.47 | +| learning_rate | 4.67e-05 | +| loss | -0.0223 | +| n_updates | 42780 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000245 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1422 | +| iterations | 6742 | +| time_elapsed | 9708 | +| total_timesteps | 13807616 | +| train/ | | +| approx_kl | 0.010343345 | +| clip_fraction | 0.337 | +| clip_range | 0.0715 | +| entropy_loss | -7.18 | +| explained_variance | 0.564 | +| learning_rate | 4.67e-05 | +| loss | -0.0376 | +| n_updates | 42784 | +| policy_gradient_loss | -0.0235 | +| value_loss | 6.06e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1422 | +| iterations | 6743 | +| time_elapsed | 9710 | +| total_timesteps | 13809664 | +| train/ | | +| approx_kl | 0.01373277 | +| clip_fraction | 0.335 | +| clip_range | 0.0715 | +| entropy_loss | -7.19 | +| explained_variance | 0.194 | +| learning_rate | 4.67e-05 | +| loss | -0.0327 | +| n_updates | 42788 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000279 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1422 | +| iterations | 6744 | +| time_elapsed | 9711 | +| total_timesteps | 13811712 | +| train/ | | +| approx_kl | 0.009960441 | +| clip_fraction | 0.319 | +| clip_range | 0.0715 | +| entropy_loss | -7.02 | +| explained_variance | 0.335 | +| learning_rate | 4.67e-05 | +| loss | -0.0311 | +| n_updates | 42792 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.00021 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1422 | +| iterations | 6745 | +| time_elapsed | 9713 | +| total_timesteps | 13813760 | +| train/ | | +| approx_kl | 0.010179687 | +| clip_fraction | 0.313 | +| clip_range | 0.0715 | +| entropy_loss | -7.49 | +| explained_variance | 0.0207 | +| learning_rate | 4.67e-05 | +| loss | -0.0345 | +| n_updates | 42796 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000156 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1422 | +| iterations | 6746 | +| time_elapsed | 9714 | +| total_timesteps | 13815808 | +| train/ | | +| approx_kl | 0.010979507 | +| clip_fraction | 0.338 | +| clip_range | 0.0715 | +| entropy_loss | -7.28 | +| explained_variance | 0.301 | +| learning_rate | 4.67e-05 | +| loss | -0.0371 | +| n_updates | 42800 | +| policy_gradient_loss | -0.0233 | +| value_loss | 5.01e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1422 | +| iterations | 6747 | +| time_elapsed | 9715 | +| total_timesteps | 13817856 | +| train/ | | +| approx_kl | 0.010707237 | +| clip_fraction | 0.302 | +| clip_range | 0.0715 | +| entropy_loss | -6.49 | +| explained_variance | 0.618 | +| learning_rate | 4.67e-05 | +| loss | -0.029 | +| n_updates | 42804 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000233 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1422 | +| iterations | 6748 | +| time_elapsed | 9717 | +| total_timesteps | 13819904 | +| train/ | | +| approx_kl | 0.011377308 | +| clip_fraction | 0.336 | +| clip_range | 0.0715 | +| entropy_loss | -7.08 | +| explained_variance | 0.371 | +| learning_rate | 4.67e-05 | +| loss | -0.0378 | +| n_updates | 42808 | +| policy_gradient_loss | -0.0231 | +| value_loss | 6.77e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1422 | +| iterations | 6749 | +| time_elapsed | 9718 | +| total_timesteps | 13821952 | +| train/ | | +| approx_kl | 0.010209977 | +| clip_fraction | 0.305 | +| clip_range | 0.0715 | +| entropy_loss | -7.3 | +| explained_variance | 0.292 | +| learning_rate | 4.67e-05 | +| loss | -0.0281 | +| n_updates | 42812 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000178 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1422 | +| iterations | 6750 | +| time_elapsed | 9720 | +| total_timesteps | 13824000 | +| train/ | | +| approx_kl | 0.009785373 | +| clip_fraction | 0.297 | +| clip_range | 0.0715 | +| entropy_loss | -6.99 | +| explained_variance | 0.532 | +| learning_rate | 4.67e-05 | +| loss | -0.0292 | +| n_updates | 42816 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000202 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1422 | +| iterations | 6751 | +| time_elapsed | 9721 | +| total_timesteps | 13826048 | +| train/ | | +| approx_kl | 0.011202188 | +| clip_fraction | 0.354 | +| clip_range | 0.0715 | +| entropy_loss | -7.52 | +| explained_variance | -0.47 | +| learning_rate | 4.67e-05 | +| loss | -0.0401 | +| n_updates | 42820 | +| policy_gradient_loss | -0.0262 | +| value_loss | 5.78e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1422 | +| iterations | 6752 | +| time_elapsed | 9722 | +| total_timesteps | 13828096 | +| train/ | | +| approx_kl | 0.012248618 | +| clip_fraction | 0.311 | +| clip_range | 0.0715 | +| entropy_loss | -7.44 | +| explained_variance | -0.152 | +| learning_rate | 4.67e-05 | +| loss | -0.0324 | +| n_updates | 42824 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000197 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1422 | +| iterations | 6753 | +| time_elapsed | 9724 | +| total_timesteps | 13830144 | +| train/ | | +| approx_kl | 0.008603409 | +| clip_fraction | 0.282 | +| clip_range | 0.0715 | +| entropy_loss | -6.63 | +| explained_variance | 0.363 | +| learning_rate | 4.67e-05 | +| loss | -0.0207 | +| n_updates | 42828 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000381 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1422 | +| iterations | 6754 | +| time_elapsed | 9725 | +| total_timesteps | 13832192 | +| train/ | | +| approx_kl | 0.0125625245 | +| clip_fraction | 0.334 | +| clip_range | 0.0715 | +| entropy_loss | -6.59 | +| explained_variance | 0.663 | +| learning_rate | 4.67e-05 | +| loss | -0.0421 | +| n_updates | 42832 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000141 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1422 | +| iterations | 6755 | +| time_elapsed | 9727 | +| total_timesteps | 13834240 | +| train/ | | +| approx_kl | 0.010507671 | +| clip_fraction | 0.318 | +| clip_range | 0.0715 | +| entropy_loss | -7.35 | +| explained_variance | 0.167 | +| learning_rate | 4.67e-05 | +| loss | -0.0334 | +| n_updates | 42836 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.00018 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1422 | +| iterations | 6756 | +| time_elapsed | 9728 | +| total_timesteps | 13836288 | +| train/ | | +| approx_kl | 0.010188876 | +| clip_fraction | 0.305 | +| clip_range | 0.0715 | +| entropy_loss | -7.31 | +| explained_variance | 0.0605 | +| learning_rate | 4.67e-05 | +| loss | -0.0301 | +| n_updates | 42840 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000214 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1422 | +| iterations | 6757 | +| time_elapsed | 9730 | +| total_timesteps | 13838336 | +| train/ | | +| approx_kl | 0.0099524 | +| clip_fraction | 0.306 | +| clip_range | 0.0715 | +| entropy_loss | -6.87 | +| explained_variance | 0.266 | +| learning_rate | 4.67e-05 | +| loss | -0.0303 | +| n_updates | 42844 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.00033 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1422 | +| iterations | 6758 | +| time_elapsed | 9731 | +| total_timesteps | 13840384 | +| train/ | | +| approx_kl | 0.011604368 | +| clip_fraction | 0.329 | +| clip_range | 0.0715 | +| entropy_loss | -6.76 | +| explained_variance | 0.692 | +| learning_rate | 4.67e-05 | +| loss | -0.0286 | +| n_updates | 42848 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000118 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1422 | +| iterations | 6759 | +| time_elapsed | 9733 | +| total_timesteps | 13842432 | +| train/ | | +| approx_kl | 0.010423806 | +| clip_fraction | 0.331 | +| clip_range | 0.0715 | +| entropy_loss | -7.42 | +| explained_variance | -0.307 | +| learning_rate | 4.67e-05 | +| loss | -0.0324 | +| n_updates | 42852 | +| policy_gradient_loss | -0.0217 | +| value_loss | 9.72e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1422 | +| iterations | 6760 | +| time_elapsed | 9734 | +| total_timesteps | 13844480 | +| train/ | | +| approx_kl | 0.012399944 | +| clip_fraction | 0.314 | +| clip_range | 0.0715 | +| entropy_loss | -7.07 | +| explained_variance | 0.465 | +| learning_rate | 4.67e-05 | +| loss | -0.03 | +| n_updates | 42856 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000132 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1422 | +| iterations | 6761 | +| time_elapsed | 9735 | +| total_timesteps | 13846528 | +| train/ | | +| approx_kl | 0.01317721 | +| clip_fraction | 0.364 | +| clip_range | 0.0715 | +| entropy_loss | -7.07 | +| explained_variance | 0.573 | +| learning_rate | 4.67e-05 | +| loss | -0.036 | +| n_updates | 42860 | +| policy_gradient_loss | -0.0244 | +| value_loss | 5.22e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1422 | +| iterations | 6762 | +| time_elapsed | 9737 | +| total_timesteps | 13848576 | +| train/ | | +| approx_kl | 0.011212708 | +| clip_fraction | 0.295 | +| clip_range | 0.0715 | +| entropy_loss | -6.92 | +| explained_variance | 0.333 | +| learning_rate | 4.67e-05 | +| loss | -0.0292 | +| n_updates | 42864 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000265 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1422 | +| iterations | 6763 | +| time_elapsed | 9738 | +| total_timesteps | 13850624 | +| train/ | | +| approx_kl | 0.012178479 | +| clip_fraction | 0.307 | +| clip_range | 0.0715 | +| entropy_loss | -6.99 | +| explained_variance | 0.233 | +| learning_rate | 4.67e-05 | +| loss | -0.023 | +| n_updates | 42868 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000394 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1422 | +| iterations | 6764 | +| time_elapsed | 9740 | +| total_timesteps | 13852672 | +| train/ | | +| approx_kl | 0.011565468 | +| clip_fraction | 0.332 | +| clip_range | 0.0715 | +| entropy_loss | -7.31 | +| explained_variance | 0.37 | +| learning_rate | 4.67e-05 | +| loss | -0.0379 | +| n_updates | 42872 | +| policy_gradient_loss | -0.0222 | +| value_loss | 0.000134 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1422 | +| iterations | 6765 | +| time_elapsed | 9741 | +| total_timesteps | 13854720 | +| train/ | | +| approx_kl | 0.009793276 | +| clip_fraction | 0.321 | +| clip_range | 0.0715 | +| entropy_loss | -7.18 | +| explained_variance | 0.384 | +| learning_rate | 4.67e-05 | +| loss | -0.0361 | +| n_updates | 42876 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000177 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1422 | +| iterations | 6766 | +| time_elapsed | 9743 | +| total_timesteps | 13856768 | +| train/ | | +| approx_kl | 0.012174491 | +| clip_fraction | 0.317 | +| clip_range | 0.0715 | +| entropy_loss | -7.05 | +| explained_variance | 0.417 | +| learning_rate | 4.67e-05 | +| loss | -0.034 | +| n_updates | 42880 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000167 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1422 | +| iterations | 6767 | +| time_elapsed | 9744 | +| total_timesteps | 13858816 | +| train/ | | +| approx_kl | 0.009009426 | +| clip_fraction | 0.291 | +| clip_range | 0.0715 | +| entropy_loss | -6.95 | +| explained_variance | 0.281 | +| learning_rate | 4.67e-05 | +| loss | -0.0299 | +| n_updates | 42884 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000352 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1422 | +| iterations | 6768 | +| time_elapsed | 9746 | +| total_timesteps | 13860864 | +| train/ | | +| approx_kl | 0.009447252 | +| clip_fraction | 0.33 | +| clip_range | 0.0715 | +| entropy_loss | -6.65 | +| explained_variance | 0.69 | +| learning_rate | 4.67e-05 | +| loss | -0.0335 | +| n_updates | 42888 | +| policy_gradient_loss | -0.0221 | +| value_loss | 0.000115 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1422 | +| iterations | 6769 | +| time_elapsed | 9747 | +| total_timesteps | 13862912 | +| train/ | | +| approx_kl | 0.009186609 | +| clip_fraction | 0.287 | +| clip_range | 0.0715 | +| entropy_loss | -7.22 | +| explained_variance | 0.354 | +| learning_rate | 4.67e-05 | +| loss | -0.0349 | +| n_updates | 42892 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000149 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1422 | +| iterations | 6770 | +| time_elapsed | 9749 | +| total_timesteps | 13864960 | +| train/ | | +| approx_kl | 0.010225084 | +| clip_fraction | 0.297 | +| clip_range | 0.0715 | +| entropy_loss | -7.22 | +| explained_variance | 0.27 | +| learning_rate | 4.67e-05 | +| loss | -0.0358 | +| n_updates | 42896 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000256 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.14e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1422 | +| iterations | 6771 | +| time_elapsed | 9750 | +| total_timesteps | 13867008 | +| train/ | | +| approx_kl | 0.013172125 | +| clip_fraction | 0.315 | +| clip_range | 0.0715 | +| entropy_loss | -7.07 | +| explained_variance | 0.518 | +| learning_rate | 4.67e-05 | +| loss | -0.0355 | +| n_updates | 42900 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000138 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1422 | +| iterations | 6772 | +| time_elapsed | 9751 | +| total_timesteps | 13869056 | +| train/ | | +| approx_kl | 0.01217831 | +| clip_fraction | 0.316 | +| clip_range | 0.0715 | +| entropy_loss | -6.66 | +| explained_variance | 0.39 | +| learning_rate | 4.67e-05 | +| loss | -0.0262 | +| n_updates | 42904 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000485 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1422 | +| iterations | 6773 | +| time_elapsed | 9753 | +| total_timesteps | 13871104 | +| train/ | | +| approx_kl | 0.010417042 | +| clip_fraction | 0.325 | +| clip_range | 0.0715 | +| entropy_loss | -7.13 | +| explained_variance | 0.268 | +| learning_rate | 4.67e-05 | +| loss | -0.0375 | +| n_updates | 42908 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000179 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.14e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1422 | +| iterations | 6774 | +| time_elapsed | 9754 | +| total_timesteps | 13873152 | +| train/ | | +| approx_kl | 0.011435725 | +| clip_fraction | 0.342 | +| clip_range | 0.0715 | +| entropy_loss | -7.21 | +| explained_variance | 0.227 | +| learning_rate | 4.67e-05 | +| loss | -0.035 | +| n_updates | 42912 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000177 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.13e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1422 | +| iterations | 6775 | +| time_elapsed | 9756 | +| total_timesteps | 13875200 | +| train/ | | +| approx_kl | 0.010205882 | +| clip_fraction | 0.307 | +| clip_range | 0.0715 | +| entropy_loss | -7.26 | +| explained_variance | 0.359 | +| learning_rate | 4.67e-05 | +| loss | -0.0309 | +| n_updates | 42916 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000228 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.13e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1422 | +| iterations | 6776 | +| time_elapsed | 9757 | +| total_timesteps | 13877248 | +| train/ | | +| approx_kl | 0.009002103 | +| clip_fraction | 0.307 | +| clip_range | 0.0715 | +| entropy_loss | -7.22 | +| explained_variance | 0.196 | +| learning_rate | 4.67e-05 | +| loss | -0.0307 | +| n_updates | 42920 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000403 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1422 | +| iterations | 6777 | +| time_elapsed | 9759 | +| total_timesteps | 13879296 | +| train/ | | +| approx_kl | 0.011058779 | +| clip_fraction | 0.354 | +| clip_range | 0.0715 | +| entropy_loss | -7.02 | +| explained_variance | 0.496 | +| learning_rate | 4.67e-05 | +| loss | -0.0391 | +| n_updates | 42924 | +| policy_gradient_loss | -0.0244 | +| value_loss | 0.000123 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1422 | +| iterations | 6778 | +| time_elapsed | 9760 | +| total_timesteps | 13881344 | +| train/ | | +| approx_kl | 0.010477271 | +| clip_fraction | 0.296 | +| clip_range | 0.0715 | +| entropy_loss | -7.05 | +| explained_variance | 0.368 | +| learning_rate | 4.67e-05 | +| loss | -0.0298 | +| n_updates | 42928 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.00019 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1422 | +| iterations | 6779 | +| time_elapsed | 9762 | +| total_timesteps | 13883392 | +| train/ | | +| approx_kl | 0.008768849 | +| clip_fraction | 0.32 | +| clip_range | 0.0715 | +| entropy_loss | -6.85 | +| explained_variance | 0.604 | +| learning_rate | 4.67e-05 | +| loss | -0.0298 | +| n_updates | 42932 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000153 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1422 | +| iterations | 6780 | +| time_elapsed | 9763 | +| total_timesteps | 13885440 | +| train/ | | +| approx_kl | 0.010146984 | +| clip_fraction | 0.319 | +| clip_range | 0.0715 | +| entropy_loss | -7.15 | +| explained_variance | 0.301 | +| learning_rate | 4.67e-05 | +| loss | -0.0307 | +| n_updates | 42936 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000205 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.14e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1422 | +| iterations | 6781 | +| time_elapsed | 9764 | +| total_timesteps | 13887488 | +| train/ | | +| approx_kl | 0.010024552 | +| clip_fraction | 0.297 | +| clip_range | 0.0715 | +| entropy_loss | -6.61 | +| explained_variance | 0.404 | +| learning_rate | 4.67e-05 | +| loss | -0.0309 | +| n_updates | 42940 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000421 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.14e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1422 | +| iterations | 6782 | +| time_elapsed | 9766 | +| total_timesteps | 13889536 | +| train/ | | +| approx_kl | 0.012807321 | +| clip_fraction | 0.349 | +| clip_range | 0.0715 | +| entropy_loss | -6.92 | +| explained_variance | 0.595 | +| learning_rate | 4.67e-05 | +| loss | -0.0385 | +| n_updates | 42944 | +| policy_gradient_loss | -0.0253 | +| value_loss | 8.54e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.14e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1422 | +| iterations | 6783 | +| time_elapsed | 9767 | +| total_timesteps | 13891584 | +| train/ | | +| approx_kl | 0.013066752 | +| clip_fraction | 0.307 | +| clip_range | 0.0715 | +| entropy_loss | -7.22 | +| explained_variance | 0.231 | +| learning_rate | 4.67e-05 | +| loss | -0.032 | +| n_updates | 42948 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000178 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.14e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1422 | +| iterations | 6784 | +| time_elapsed | 9769 | +| total_timesteps | 13893632 | +| train/ | | +| approx_kl | 0.011316775 | +| clip_fraction | 0.341 | +| clip_range | 0.0715 | +| entropy_loss | -7.12 | +| explained_variance | 0.511 | +| learning_rate | 4.67e-05 | +| loss | -0.0306 | +| n_updates | 42952 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000133 | +----------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.13e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1422 | +| iterations | 6785 | +| time_elapsed | 9770 | +| total_timesteps | 13895680 | +| train/ | | +| approx_kl | 0.010302 | +| clip_fraction | 0.305 | +| clip_range | 0.0715 | +| entropy_loss | -7.1 | +| explained_variance | 0.294 | +| learning_rate | 4.67e-05 | +| loss | -0.0322 | +| n_updates | 42956 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000154 | +-------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.13e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1422 | +| iterations | 6786 | +| time_elapsed | 9772 | +| total_timesteps | 13897728 | +| train/ | | +| approx_kl | 0.00960283 | +| clip_fraction | 0.307 | +| clip_range | 0.0715 | +| entropy_loss | -7.11 | +| explained_variance | 0.373 | +| learning_rate | 4.67e-05 | +| loss | -0.0299 | +| n_updates | 42960 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000205 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.14e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1422 | +| iterations | 6787 | +| time_elapsed | 9773 | +| total_timesteps | 13899776 | +| train/ | | +| approx_kl | 0.011488414 | +| clip_fraction | 0.296 | +| clip_range | 0.0715 | +| entropy_loss | -6.93 | +| explained_variance | 0.484 | +| learning_rate | 4.67e-05 | +| loss | -0.024 | +| n_updates | 42964 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000169 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1422 | +| iterations | 6788 | +| time_elapsed | 9774 | +| total_timesteps | 13901824 | +| train/ | | +| approx_kl | 0.011534291 | +| clip_fraction | 0.331 | +| clip_range | 0.0715 | +| entropy_loss | -7.22 | +| explained_variance | 0.278 | +| learning_rate | 4.67e-05 | +| loss | -0.0331 | +| n_updates | 42968 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000137 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.14e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1422 | +| iterations | 6789 | +| time_elapsed | 9776 | +| total_timesteps | 13903872 | +| train/ | | +| approx_kl | 0.010026999 | +| clip_fraction | 0.34 | +| clip_range | 0.0715 | +| entropy_loss | -7.09 | +| explained_variance | 0.462 | +| learning_rate | 4.67e-05 | +| loss | -0.0294 | +| n_updates | 42972 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.00015 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.14e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1422 | +| iterations | 6790 | +| time_elapsed | 9777 | +| total_timesteps | 13905920 | +| train/ | | +| approx_kl | 0.009499598 | +| clip_fraction | 0.272 | +| clip_range | 0.0715 | +| entropy_loss | -6.67 | +| explained_variance | 0.4 | +| learning_rate | 4.67e-05 | +| loss | -0.0287 | +| n_updates | 42976 | +| policy_gradient_loss | -0.0147 | +| value_loss | 0.000366 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.14e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1422 | +| iterations | 6791 | +| time_elapsed | 9779 | +| total_timesteps | 13907968 | +| train/ | | +| approx_kl | 0.012400569 | +| clip_fraction | 0.345 | +| clip_range | 0.0715 | +| entropy_loss | -7.34 | +| explained_variance | -0.274 | +| learning_rate | 4.67e-05 | +| loss | -0.0385 | +| n_updates | 42980 | +| policy_gradient_loss | -0.0244 | +| value_loss | 8.88e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.14e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1422 | +| iterations | 6792 | +| time_elapsed | 9780 | +| total_timesteps | 13910016 | +| train/ | | +| approx_kl | 0.011846509 | +| clip_fraction | 0.329 | +| clip_range | 0.0715 | +| entropy_loss | -6.56 | +| explained_variance | 0.482 | +| learning_rate | 4.67e-05 | +| loss | -0.0289 | +| n_updates | 42984 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000317 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.14e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1422 | +| iterations | 6793 | +| time_elapsed | 9782 | +| total_timesteps | 13912064 | +| train/ | | +| approx_kl | 0.010813234 | +| clip_fraction | 0.318 | +| clip_range | 0.0715 | +| entropy_loss | -7.32 | +| explained_variance | -0.0326 | +| learning_rate | 4.67e-05 | +| loss | -0.0319 | +| n_updates | 42988 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.00015 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.13e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1422 | +| iterations | 6794 | +| time_elapsed | 9783 | +| total_timesteps | 13914112 | +| train/ | | +| approx_kl | 0.011910919 | +| clip_fraction | 0.324 | +| clip_range | 0.0715 | +| entropy_loss | -7.11 | +| explained_variance | 0.137 | +| learning_rate | 4.67e-05 | +| loss | -0.0302 | +| n_updates | 42992 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000213 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.12e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1422 | +| iterations | 6795 | +| time_elapsed | 9784 | +| total_timesteps | 13916160 | +| train/ | | +| approx_kl | 0.009338869 | +| clip_fraction | 0.303 | +| clip_range | 0.0715 | +| entropy_loss | -7.25 | +| explained_variance | 0.208 | +| learning_rate | 4.67e-05 | +| loss | -0.032 | +| n_updates | 42996 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000222 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.12e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1422 | +| iterations | 6796 | +| time_elapsed | 9786 | +| total_timesteps | 13918208 | +| train/ | | +| approx_kl | 0.011228213 | +| clip_fraction | 0.349 | +| clip_range | 0.0715 | +| entropy_loss | -7 | +| explained_variance | 0.671 | +| learning_rate | 4.67e-05 | +| loss | -0.0375 | +| n_updates | 43000 | +| policy_gradient_loss | -0.0242 | +| value_loss | 6.55e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.13e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1422 | +| iterations | 6797 | +| time_elapsed | 9787 | +| total_timesteps | 13920256 | +| train/ | | +| approx_kl | 0.010400661 | +| clip_fraction | 0.32 | +| clip_range | 0.0715 | +| entropy_loss | -7.22 | +| explained_variance | 0.377 | +| learning_rate | 4.67e-05 | +| loss | -0.0332 | +| n_updates | 43004 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000117 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.13e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1422 | +| iterations | 6798 | +| time_elapsed | 9789 | +| total_timesteps | 13922304 | +| train/ | | +| approx_kl | 0.010759015 | +| clip_fraction | 0.315 | +| clip_range | 0.0715 | +| entropy_loss | -7.09 | +| explained_variance | 0.194 | +| learning_rate | 4.67e-05 | +| loss | -0.0279 | +| n_updates | 43008 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000168 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.14e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1422 | +| iterations | 6799 | +| time_elapsed | 9790 | +| total_timesteps | 13924352 | +| train/ | | +| approx_kl | 0.010679454 | +| clip_fraction | 0.317 | +| clip_range | 0.0715 | +| entropy_loss | -6.99 | +| explained_variance | 0.611 | +| learning_rate | 4.67e-05 | +| loss | -0.0332 | +| n_updates | 43012 | +| policy_gradient_loss | -0.0196 | +| value_loss | 8.54e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.14e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1422 | +| iterations | 6800 | +| time_elapsed | 9792 | +| total_timesteps | 13926400 | +| train/ | | +| approx_kl | 0.009301035 | +| clip_fraction | 0.312 | +| clip_range | 0.0715 | +| entropy_loss | -7.19 | +| explained_variance | 0.0224 | +| learning_rate | 4.67e-05 | +| loss | -0.033 | +| n_updates | 43016 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000126 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.13e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1422 | +| iterations | 6801 | +| time_elapsed | 9793 | +| total_timesteps | 13928448 | +| train/ | | +| approx_kl | 0.0094396835 | +| clip_fraction | 0.29 | +| clip_range | 0.0715 | +| entropy_loss | -7.11 | +| explained_variance | 0.355 | +| learning_rate | 4.67e-05 | +| loss | -0.0308 | +| n_updates | 43020 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000242 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.14e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1422 | +| iterations | 6802 | +| time_elapsed | 9795 | +| total_timesteps | 13930496 | +| train/ | | +| approx_kl | 0.00881129 | +| clip_fraction | 0.3 | +| clip_range | 0.0715 | +| entropy_loss | -7.11 | +| explained_variance | 0.471 | +| learning_rate | 4.67e-05 | +| loss | -0.0278 | +| n_updates | 43024 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000134 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.14e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1422 | +| iterations | 6803 | +| time_elapsed | 9796 | +| total_timesteps | 13932544 | +| train/ | | +| approx_kl | 0.01127219 | +| clip_fraction | 0.339 | +| clip_range | 0.0715 | +| entropy_loss | -6.7 | +| explained_variance | 0.623 | +| learning_rate | 4.67e-05 | +| loss | -0.0325 | +| n_updates | 43028 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.00016 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.14e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1422 | +| iterations | 6804 | +| time_elapsed | 9798 | +| total_timesteps | 13934592 | +| train/ | | +| approx_kl | 0.0100071505 | +| clip_fraction | 0.297 | +| clip_range | 0.0715 | +| entropy_loss | -6.79 | +| explained_variance | 0.667 | +| learning_rate | 4.67e-05 | +| loss | -0.0247 | +| n_updates | 43032 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000121 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.14e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1422 | +| iterations | 6805 | +| time_elapsed | 9799 | +| total_timesteps | 13936640 | +| train/ | | +| approx_kl | 0.010725241 | +| clip_fraction | 0.312 | +| clip_range | 0.0715 | +| entropy_loss | -6.99 | +| explained_variance | 0.337 | +| learning_rate | 4.67e-05 | +| loss | -0.0222 | +| n_updates | 43036 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000173 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.13e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1422 | +| iterations | 6806 | +| time_elapsed | 9800 | +| total_timesteps | 13938688 | +| train/ | | +| approx_kl | 0.01372486 | +| clip_fraction | 0.36 | +| clip_range | 0.0715 | +| entropy_loss | -7.23 | +| explained_variance | 0.366 | +| learning_rate | 4.67e-05 | +| loss | -0.0291 | +| n_updates | 43040 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000109 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.13e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1422 | +| iterations | 6807 | +| time_elapsed | 9802 | +| total_timesteps | 13940736 | +| train/ | | +| approx_kl | 0.011189475 | +| clip_fraction | 0.312 | +| clip_range | 0.0715 | +| entropy_loss | -7.19 | +| explained_variance | 0.23 | +| learning_rate | 4.67e-05 | +| loss | -0.0303 | +| n_updates | 43044 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.00023 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.13e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1422 | +| iterations | 6808 | +| time_elapsed | 9803 | +| total_timesteps | 13942784 | +| train/ | | +| approx_kl | 0.01275503 | +| clip_fraction | 0.338 | +| clip_range | 0.0715 | +| entropy_loss | -7.03 | +| explained_variance | 0.335 | +| learning_rate | 4.67e-05 | +| loss | -0.0299 | +| n_updates | 43048 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000176 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.13e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1422 | +| iterations | 6809 | +| time_elapsed | 9805 | +| total_timesteps | 13944832 | +| train/ | | +| approx_kl | 0.01309125 | +| clip_fraction | 0.34 | +| clip_range | 0.0715 | +| entropy_loss | -7.25 | +| explained_variance | -0.265 | +| learning_rate | 4.67e-05 | +| loss | -0.0386 | +| n_updates | 43052 | +| policy_gradient_loss | -0.023 | +| value_loss | 0.000137 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.13e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1422 | +| iterations | 6810 | +| time_elapsed | 9806 | +| total_timesteps | 13946880 | +| train/ | | +| approx_kl | 0.013484446 | +| clip_fraction | 0.333 | +| clip_range | 0.0715 | +| entropy_loss | -7.17 | +| explained_variance | 0.315 | +| learning_rate | 4.67e-05 | +| loss | -0.034 | +| n_updates | 43056 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000135 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.14e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1422 | +| iterations | 6811 | +| time_elapsed | 9808 | +| total_timesteps | 13948928 | +| train/ | | +| approx_kl | 0.011718477 | +| clip_fraction | 0.277 | +| clip_range | 0.0715 | +| entropy_loss | -6.82 | +| explained_variance | 0.274 | +| learning_rate | 4.67e-05 | +| loss | -0.0272 | +| n_updates | 43060 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000426 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.14e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1422 | +| iterations | 6812 | +| time_elapsed | 9809 | +| total_timesteps | 13950976 | +| train/ | | +| approx_kl | 0.011012072 | +| clip_fraction | 0.33 | +| clip_range | 0.0715 | +| entropy_loss | -6.78 | +| explained_variance | 0.511 | +| learning_rate | 4.67e-05 | +| loss | -0.0361 | +| n_updates | 43064 | +| policy_gradient_loss | -0.0219 | +| value_loss | 0.000143 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1422 | +| iterations | 6813 | +| time_elapsed | 9811 | +| total_timesteps | 13953024 | +| train/ | | +| approx_kl | 0.010722779 | +| clip_fraction | 0.339 | +| clip_range | 0.0715 | +| entropy_loss | -6.84 | +| explained_variance | 0.418 | +| learning_rate | 4.67e-05 | +| loss | -0.032 | +| n_updates | 43068 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000142 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1422 | +| iterations | 6814 | +| time_elapsed | 9812 | +| total_timesteps | 13955072 | +| train/ | | +| approx_kl | 0.012224885 | +| clip_fraction | 0.322 | +| clip_range | 0.0715 | +| entropy_loss | -7.08 | +| explained_variance | 0.247 | +| learning_rate | 4.67e-05 | +| loss | -0.0246 | +| n_updates | 43072 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000182 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1422 | +| iterations | 6815 | +| time_elapsed | 9813 | +| total_timesteps | 13957120 | +| train/ | | +| approx_kl | 0.013064453 | +| clip_fraction | 0.328 | +| clip_range | 0.0715 | +| entropy_loss | -6.75 | +| explained_variance | 0.618 | +| learning_rate | 4.67e-05 | +| loss | -0.0381 | +| n_updates | 43076 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000129 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1422 | +| iterations | 6816 | +| time_elapsed | 9815 | +| total_timesteps | 13959168 | +| train/ | | +| approx_kl | 0.008943187 | +| clip_fraction | 0.319 | +| clip_range | 0.0715 | +| entropy_loss | -7.34 | +| explained_variance | -0.0846 | +| learning_rate | 4.67e-05 | +| loss | -0.0294 | +| n_updates | 43080 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000194 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1422 | +| iterations | 6817 | +| time_elapsed | 9816 | +| total_timesteps | 13961216 | +| train/ | | +| approx_kl | 0.0124147 | +| clip_fraction | 0.324 | +| clip_range | 0.0715 | +| entropy_loss | -7.22 | +| explained_variance | 0.435 | +| learning_rate | 4.67e-05 | +| loss | -0.0327 | +| n_updates | 43084 | +| policy_gradient_loss | -0.0234 | +| value_loss | 7.91e-05 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1422 | +| iterations | 6818 | +| time_elapsed | 9818 | +| total_timesteps | 13963264 | +| train/ | | +| approx_kl | 0.011545991 | +| clip_fraction | 0.313 | +| clip_range | 0.0715 | +| entropy_loss | -7.24 | +| explained_variance | -0.035 | +| learning_rate | 4.67e-05 | +| loss | -0.0324 | +| n_updates | 43088 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000256 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1422 | +| iterations | 6819 | +| time_elapsed | 9819 | +| total_timesteps | 13965312 | +| train/ | | +| approx_kl | 0.012707448 | +| clip_fraction | 0.313 | +| clip_range | 0.0715 | +| entropy_loss | -7.17 | +| explained_variance | 0.253 | +| learning_rate | 4.67e-05 | +| loss | -0.0315 | +| n_updates | 43092 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.00017 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1422 | +| iterations | 6820 | +| time_elapsed | 9821 | +| total_timesteps | 13967360 | +| train/ | | +| approx_kl | 0.010831147 | +| clip_fraction | 0.312 | +| clip_range | 0.0715 | +| entropy_loss | -7.37 | +| explained_variance | -0.0839 | +| learning_rate | 4.67e-05 | +| loss | -0.0326 | +| n_updates | 43096 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000205 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1422 | +| iterations | 6821 | +| time_elapsed | 9822 | +| total_timesteps | 13969408 | +| train/ | | +| approx_kl | 0.010577912 | +| clip_fraction | 0.294 | +| clip_range | 0.0715 | +| entropy_loss | -7.1 | +| explained_variance | 0.334 | +| learning_rate | 4.67e-05 | +| loss | -0.0246 | +| n_updates | 43100 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000257 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1422 | +| iterations | 6822 | +| time_elapsed | 9823 | +| total_timesteps | 13971456 | +| train/ | | +| approx_kl | 0.012994179 | +| clip_fraction | 0.344 | +| clip_range | 0.0715 | +| entropy_loss | -6.59 | +| explained_variance | 0.631 | +| learning_rate | 4.67e-05 | +| loss | -0.0246 | +| n_updates | 43104 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000167 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1422 | +| iterations | 6823 | +| time_elapsed | 9825 | +| total_timesteps | 13973504 | +| train/ | | +| approx_kl | 0.014196005 | +| clip_fraction | 0.336 | +| clip_range | 0.0715 | +| entropy_loss | -6.72 | +| explained_variance | 0.719 | +| learning_rate | 4.67e-05 | +| loss | -0.032 | +| n_updates | 43108 | +| policy_gradient_loss | -0.0216 | +| value_loss | 8.51e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1422 | +| iterations | 6824 | +| time_elapsed | 9826 | +| total_timesteps | 13975552 | +| train/ | | +| approx_kl | 0.011841332 | +| clip_fraction | 0.334 | +| clip_range | 0.0715 | +| entropy_loss | -6.7 | +| explained_variance | 0.731 | +| learning_rate | 4.67e-05 | +| loss | -0.0333 | +| n_updates | 43112 | +| policy_gradient_loss | -0.0205 | +| value_loss | 8.48e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1422 | +| iterations | 6825 | +| time_elapsed | 9828 | +| total_timesteps | 13977600 | +| train/ | | +| approx_kl | 0.010953644 | +| clip_fraction | 0.308 | +| clip_range | 0.0715 | +| entropy_loss | -7.37 | +| explained_variance | -0.0611 | +| learning_rate | 4.67e-05 | +| loss | -0.0323 | +| n_updates | 43116 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000257 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1422 | +| iterations | 6826 | +| time_elapsed | 9829 | +| total_timesteps | 13979648 | +| train/ | | +| approx_kl | 0.00924775 | +| clip_fraction | 0.299 | +| clip_range | 0.0715 | +| entropy_loss | -7.27 | +| explained_variance | 0.282 | +| learning_rate | 4.67e-05 | +| loss | -0.0332 | +| n_updates | 43120 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000135 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1422 | +| iterations | 6827 | +| time_elapsed | 9831 | +| total_timesteps | 13981696 | +| train/ | | +| approx_kl | 0.00992541 | +| clip_fraction | 0.326 | +| clip_range | 0.0715 | +| entropy_loss | -7.34 | +| explained_variance | 0.0518 | +| learning_rate | 4.67e-05 | +| loss | -0.0333 | +| n_updates | 43124 | +| policy_gradient_loss | -0.0219 | +| value_loss | 8.7e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1422 | +| iterations | 6828 | +| time_elapsed | 9832 | +| total_timesteps | 13983744 | +| train/ | | +| approx_kl | 0.009222545 | +| clip_fraction | 0.314 | +| clip_range | 0.0715 | +| entropy_loss | -6.7 | +| explained_variance | 0.564 | +| learning_rate | 4.67e-05 | +| loss | -0.024 | +| n_updates | 43128 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000228 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1422 | +| iterations | 6829 | +| time_elapsed | 9834 | +| total_timesteps | 13985792 | +| train/ | | +| approx_kl | 0.010492054 | +| clip_fraction | 0.31 | +| clip_range | 0.0715 | +| entropy_loss | -7.48 | +| explained_variance | -0.0161 | +| learning_rate | 4.67e-05 | +| loss | -0.0295 | +| n_updates | 43132 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000182 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1422 | +| iterations | 6830 | +| time_elapsed | 9835 | +| total_timesteps | 13987840 | +| train/ | | +| approx_kl | 0.009415323 | +| clip_fraction | 0.302 | +| clip_range | 0.0715 | +| entropy_loss | -7.52 | +| explained_variance | -0.00615 | +| learning_rate | 4.67e-05 | +| loss | -0.031 | +| n_updates | 43136 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000168 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1422 | +| iterations | 6831 | +| time_elapsed | 9837 | +| total_timesteps | 13989888 | +| train/ | | +| approx_kl | 0.010070127 | +| clip_fraction | 0.31 | +| clip_range | 0.0715 | +| entropy_loss | -7.27 | +| explained_variance | 0.085 | +| learning_rate | 4.67e-05 | +| loss | -0.0247 | +| n_updates | 43140 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000259 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.315 | +| time/ | | +| fps | 1422 | +| iterations | 6832 | +| time_elapsed | 9838 | +| total_timesteps | 13991936 | +| train/ | | +| approx_kl | 0.011825254 | +| clip_fraction | 0.311 | +| clip_range | 0.0715 | +| entropy_loss | -6.48 | +| explained_variance | 0.691 | +| learning_rate | 4.67e-05 | +| loss | -0.023 | +| n_updates | 43144 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000139 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1422 | +| iterations | 6833 | +| time_elapsed | 9839 | +| total_timesteps | 13993984 | +| train/ | | +| approx_kl | 0.01122415 | +| clip_fraction | 0.31 | +| clip_range | 0.0715 | +| entropy_loss | -7.03 | +| explained_variance | 0.488 | +| learning_rate | 4.67e-05 | +| loss | -0.0267 | +| n_updates | 43148 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000153 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1422 | +| iterations | 6834 | +| time_elapsed | 9841 | +| total_timesteps | 13996032 | +| train/ | | +| approx_kl | 0.012475202 | +| clip_fraction | 0.329 | +| clip_range | 0.0715 | +| entropy_loss | -7.23 | +| explained_variance | 0.349 | +| learning_rate | 4.67e-05 | +| loss | -0.032 | +| n_updates | 43152 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000141 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1422 | +| iterations | 6835 | +| time_elapsed | 9842 | +| total_timesteps | 13998080 | +| train/ | | +| approx_kl | 0.010919584 | +| clip_fraction | 0.309 | +| clip_range | 0.0715 | +| entropy_loss | -7.45 | +| explained_variance | -0.0793 | +| learning_rate | 4.67e-05 | +| loss | -0.0334 | +| n_updates | 43156 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.00014 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1422 | +| iterations | 6836 | +| time_elapsed | 9844 | +| total_timesteps | 14000128 | +| train/ | | +| approx_kl | 0.009886576 | +| clip_fraction | 0.304 | +| clip_range | 0.0715 | +| entropy_loss | -7.08 | +| explained_variance | 0.4 | +| learning_rate | 4.67e-05 | +| loss | -0.0326 | +| n_updates | 43160 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000223 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1422 | +| iterations | 6837 | +| time_elapsed | 9845 | +| total_timesteps | 14002176 | +| train/ | | +| approx_kl | 0.0085420525 | +| clip_fraction | 0.314 | +| clip_range | 0.0715 | +| entropy_loss | -7.15 | +| explained_variance | 0.35 | +| learning_rate | 4.67e-05 | +| loss | -0.0207 | +| n_updates | 43164 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000241 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1422 | +| iterations | 6838 | +| time_elapsed | 9847 | +| total_timesteps | 14004224 | +| train/ | | +| approx_kl | 0.010286342 | +| clip_fraction | 0.305 | +| clip_range | 0.0715 | +| entropy_loss | -6.96 | +| explained_variance | 0.266 | +| learning_rate | 4.67e-05 | +| loss | -0.026 | +| n_updates | 43168 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000278 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1422 | +| iterations | 6839 | +| time_elapsed | 9848 | +| total_timesteps | 14006272 | +| train/ | | +| approx_kl | 0.011431344 | +| clip_fraction | 0.308 | +| clip_range | 0.0715 | +| entropy_loss | -7.23 | +| explained_variance | 0.539 | +| learning_rate | 4.67e-05 | +| loss | -0.0318 | +| n_updates | 43172 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000111 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1422 | +| iterations | 6840 | +| time_elapsed | 9849 | +| total_timesteps | 14008320 | +| train/ | | +| approx_kl | 0.008603147 | +| clip_fraction | 0.264 | +| clip_range | 0.0715 | +| entropy_loss | -6.74 | +| explained_variance | 0.363 | +| learning_rate | 4.67e-05 | +| loss | -0.0233 | +| n_updates | 43176 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000439 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1422 | +| iterations | 6841 | +| time_elapsed | 9851 | +| total_timesteps | 14010368 | +| train/ | | +| approx_kl | 0.011295866 | +| clip_fraction | 0.292 | +| clip_range | 0.0715 | +| entropy_loss | -6.84 | +| explained_variance | 0.387 | +| learning_rate | 4.67e-05 | +| loss | -0.03 | +| n_updates | 43180 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000223 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1422 | +| iterations | 6842 | +| time_elapsed | 9852 | +| total_timesteps | 14012416 | +| train/ | | +| approx_kl | 0.010830473 | +| clip_fraction | 0.358 | +| clip_range | 0.0715 | +| entropy_loss | -7.14 | +| explained_variance | 0.537 | +| learning_rate | 4.67e-05 | +| loss | -0.0414 | +| n_updates | 43184 | +| policy_gradient_loss | -0.0252 | +| value_loss | 0.000105 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1422 | +| iterations | 6843 | +| time_elapsed | 9854 | +| total_timesteps | 14014464 | +| train/ | | +| approx_kl | 0.010966413 | +| clip_fraction | 0.306 | +| clip_range | 0.0715 | +| entropy_loss | -7.32 | +| explained_variance | 0.15 | +| learning_rate | 4.67e-05 | +| loss | -0.0337 | +| n_updates | 43188 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000257 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1422 | +| iterations | 6844 | +| time_elapsed | 9855 | +| total_timesteps | 14016512 | +| train/ | | +| approx_kl | 0.011310777 | +| clip_fraction | 0.298 | +| clip_range | 0.0715 | +| entropy_loss | -7.25 | +| explained_variance | 0.259 | +| learning_rate | 4.67e-05 | +| loss | -0.0301 | +| n_updates | 43192 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000195 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1422 | +| iterations | 6845 | +| time_elapsed | 9857 | +| total_timesteps | 14018560 | +| train/ | | +| approx_kl | 0.011292418 | +| clip_fraction | 0.349 | +| clip_range | 0.0715 | +| entropy_loss | -7.46 | +| explained_variance | -0.298 | +| learning_rate | 4.67e-05 | +| loss | -0.0369 | +| n_updates | 43196 | +| policy_gradient_loss | -0.0254 | +| value_loss | 7.06e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1422 | +| iterations | 6846 | +| time_elapsed | 9858 | +| total_timesteps | 14020608 | +| train/ | | +| approx_kl | 0.011634029 | +| clip_fraction | 0.333 | +| clip_range | 0.0715 | +| entropy_loss | -7.28 | +| explained_variance | 0.251 | +| learning_rate | 4.67e-05 | +| loss | -0.0294 | +| n_updates | 43200 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.00023 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1422 | +| iterations | 6847 | +| time_elapsed | 9859 | +| total_timesteps | 14022656 | +| train/ | | +| approx_kl | 0.010840271 | +| clip_fraction | 0.338 | +| clip_range | 0.0715 | +| entropy_loss | -7.23 | +| explained_variance | 0.569 | +| learning_rate | 4.67e-05 | +| loss | -0.0425 | +| n_updates | 43204 | +| policy_gradient_loss | -0.0243 | +| value_loss | 5.5e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1422 | +| iterations | 6848 | +| time_elapsed | 9861 | +| total_timesteps | 14024704 | +| train/ | | +| approx_kl | 0.009718142 | +| clip_fraction | 0.316 | +| clip_range | 0.0715 | +| entropy_loss | -7.05 | +| explained_variance | 0.495 | +| learning_rate | 4.67e-05 | +| loss | -0.0333 | +| n_updates | 43208 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000128 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1422 | +| iterations | 6849 | +| time_elapsed | 9862 | +| total_timesteps | 14026752 | +| train/ | | +| approx_kl | 0.009742084 | +| clip_fraction | 0.286 | +| clip_range | 0.0715 | +| entropy_loss | -7.1 | +| explained_variance | 0.467 | +| learning_rate | 4.67e-05 | +| loss | -0.0232 | +| n_updates | 43212 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.00018 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1422 | +| iterations | 6850 | +| time_elapsed | 9864 | +| total_timesteps | 14028800 | +| train/ | | +| approx_kl | 0.010393264 | +| clip_fraction | 0.273 | +| clip_range | 0.0715 | +| entropy_loss | -6.94 | +| explained_variance | 0.502 | +| learning_rate | 4.67e-05 | +| loss | -0.0279 | +| n_updates | 43216 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000225 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1422 | +| iterations | 6851 | +| time_elapsed | 9865 | +| total_timesteps | 14030848 | +| train/ | | +| approx_kl | 0.008666018 | +| clip_fraction | 0.299 | +| clip_range | 0.0715 | +| entropy_loss | -7.15 | +| explained_variance | 0.5 | +| learning_rate | 4.67e-05 | +| loss | -0.0276 | +| n_updates | 43220 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000126 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1422 | +| iterations | 6852 | +| time_elapsed | 9867 | +| total_timesteps | 14032896 | +| train/ | | +| approx_kl | 0.009667808 | +| clip_fraction | 0.335 | +| clip_range | 0.0715 | +| entropy_loss | -7.43 | +| explained_variance | -0.327 | +| learning_rate | 4.67e-05 | +| loss | -0.0443 | +| n_updates | 43224 | +| policy_gradient_loss | -0.0234 | +| value_loss | 0.000129 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1422 | +| iterations | 6853 | +| time_elapsed | 9868 | +| total_timesteps | 14034944 | +| train/ | | +| approx_kl | 0.012075316 | +| clip_fraction | 0.327 | +| clip_range | 0.0715 | +| entropy_loss | -7.11 | +| explained_variance | 0.229 | +| learning_rate | 4.67e-05 | +| loss | -0.0337 | +| n_updates | 43228 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000197 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1422 | +| iterations | 6854 | +| time_elapsed | 9869 | +| total_timesteps | 14036992 | +| train/ | | +| approx_kl | 0.011390241 | +| clip_fraction | 0.335 | +| clip_range | 0.0715 | +| entropy_loss | -7.12 | +| explained_variance | 0.468 | +| learning_rate | 4.67e-05 | +| loss | -0.0355 | +| n_updates | 43232 | +| policy_gradient_loss | -0.0223 | +| value_loss | 0.000108 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1422 | +| iterations | 6855 | +| time_elapsed | 9871 | +| total_timesteps | 14039040 | +| train/ | | +| approx_kl | 0.011346538 | +| clip_fraction | 0.325 | +| clip_range | 0.0715 | +| entropy_loss | -6.8 | +| explained_variance | 0.668 | +| learning_rate | 4.67e-05 | +| loss | -0.0399 | +| n_updates | 43236 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000105 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1422 | +| iterations | 6856 | +| time_elapsed | 9872 | +| total_timesteps | 14041088 | +| train/ | | +| approx_kl | 0.01037148 | +| clip_fraction | 0.326 | +| clip_range | 0.0715 | +| entropy_loss | -6.89 | +| explained_variance | 0.658 | +| learning_rate | 4.67e-05 | +| loss | -0.039 | +| n_updates | 43240 | +| policy_gradient_loss | -0.0214 | +| value_loss | 7.98e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1422 | +| iterations | 6857 | +| time_elapsed | 9874 | +| total_timesteps | 14043136 | +| train/ | | +| approx_kl | 0.012413449 | +| clip_fraction | 0.294 | +| clip_range | 0.0715 | +| entropy_loss | -6.93 | +| explained_variance | 0.485 | +| learning_rate | 4.67e-05 | +| loss | -0.0294 | +| n_updates | 43244 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000189 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1422 | +| iterations | 6858 | +| time_elapsed | 9875 | +| total_timesteps | 14045184 | +| train/ | | +| approx_kl | 0.011424786 | +| clip_fraction | 0.343 | +| clip_range | 0.0715 | +| entropy_loss | -7.43 | +| explained_variance | -0.117 | +| learning_rate | 4.67e-05 | +| loss | -0.0362 | +| n_updates | 43248 | +| policy_gradient_loss | -0.0223 | +| value_loss | 0.000132 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1422 | +| iterations | 6859 | +| time_elapsed | 9877 | +| total_timesteps | 14047232 | +| train/ | | +| approx_kl | 0.011294428 | +| clip_fraction | 0.307 | +| clip_range | 0.0715 | +| entropy_loss | -7.1 | +| explained_variance | 0.272 | +| learning_rate | 4.67e-05 | +| loss | -0.0353 | +| n_updates | 43252 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000311 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1422 | +| iterations | 6860 | +| time_elapsed | 9878 | +| total_timesteps | 14049280 | +| train/ | | +| approx_kl | 0.011591265 | +| clip_fraction | 0.317 | +| clip_range | 0.0715 | +| entropy_loss | -6.91 | +| explained_variance | 0.487 | +| learning_rate | 4.67e-05 | +| loss | -0.0312 | +| n_updates | 43256 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000152 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1422 | +| iterations | 6861 | +| time_elapsed | 9879 | +| total_timesteps | 14051328 | +| train/ | | +| approx_kl | 0.010403769 | +| clip_fraction | 0.305 | +| clip_range | 0.0715 | +| entropy_loss | -6.55 | +| explained_variance | 0.566 | +| learning_rate | 4.67e-05 | +| loss | -0.0311 | +| n_updates | 43260 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000173 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1422 | +| iterations | 6862 | +| time_elapsed | 9881 | +| total_timesteps | 14053376 | +| train/ | | +| approx_kl | 0.012684356 | +| clip_fraction | 0.304 | +| clip_range | 0.0715 | +| entropy_loss | -6.91 | +| explained_variance | 0.312 | +| learning_rate | 4.67e-05 | +| loss | -0.029 | +| n_updates | 43264 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000238 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1422 | +| iterations | 6863 | +| time_elapsed | 9882 | +| total_timesteps | 14055424 | +| train/ | | +| approx_kl | 0.009408003 | +| clip_fraction | 0.279 | +| clip_range | 0.0715 | +| entropy_loss | -7.31 | +| explained_variance | 0.26 | +| learning_rate | 4.67e-05 | +| loss | -0.0324 | +| n_updates | 43268 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000175 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1422 | +| iterations | 6864 | +| time_elapsed | 9884 | +| total_timesteps | 14057472 | +| train/ | | +| approx_kl | 0.012704351 | +| clip_fraction | 0.361 | +| clip_range | 0.0715 | +| entropy_loss | -7.44 | +| explained_variance | -0.283 | +| learning_rate | 4.67e-05 | +| loss | -0.0358 | +| n_updates | 43272 | +| policy_gradient_loss | -0.025 | +| value_loss | 8.12e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1422 | +| iterations | 6865 | +| time_elapsed | 9885 | +| total_timesteps | 14059520 | +| train/ | | +| approx_kl | 0.009660933 | +| clip_fraction | 0.287 | +| clip_range | 0.0715 | +| entropy_loss | -7.17 | +| explained_variance | 0.277 | +| learning_rate | 4.67e-05 | +| loss | -0.0265 | +| n_updates | 43276 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000196 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1422 | +| iterations | 6866 | +| time_elapsed | 9886 | +| total_timesteps | 14061568 | +| train/ | | +| approx_kl | 0.008607134 | +| clip_fraction | 0.277 | +| clip_range | 0.0715 | +| entropy_loss | -7.29 | +| explained_variance | 0.0324 | +| learning_rate | 4.67e-05 | +| loss | -0.0277 | +| n_updates | 43280 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000291 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1422 | +| iterations | 6867 | +| time_elapsed | 9888 | +| total_timesteps | 14063616 | +| train/ | | +| approx_kl | 0.009665156 | +| clip_fraction | 0.275 | +| clip_range | 0.0715 | +| entropy_loss | -6.95 | +| explained_variance | 0.34 | +| learning_rate | 4.67e-05 | +| loss | -0.0313 | +| n_updates | 43284 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000342 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1422 | +| iterations | 6868 | +| time_elapsed | 9889 | +| total_timesteps | 14065664 | +| train/ | | +| approx_kl | 0.011050291 | +| clip_fraction | 0.306 | +| clip_range | 0.0715 | +| entropy_loss | -6.79 | +| explained_variance | 0.469 | +| learning_rate | 4.67e-05 | +| loss | -0.0281 | +| n_updates | 43288 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000241 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1422 | +| iterations | 6869 | +| time_elapsed | 9891 | +| total_timesteps | 14067712 | +| train/ | | +| approx_kl | 0.011309436 | +| clip_fraction | 0.328 | +| clip_range | 0.0715 | +| entropy_loss | -7.13 | +| explained_variance | 0.325 | +| learning_rate | 4.67e-05 | +| loss | -0.0365 | +| n_updates | 43292 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000145 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1422 | +| iterations | 6870 | +| time_elapsed | 9892 | +| total_timesteps | 14069760 | +| train/ | | +| approx_kl | 0.012321122 | +| clip_fraction | 0.355 | +| clip_range | 0.0715 | +| entropy_loss | -7.27 | +| explained_variance | 0.347 | +| learning_rate | 4.67e-05 | +| loss | -0.0417 | +| n_updates | 43296 | +| policy_gradient_loss | -0.0244 | +| value_loss | 7.27e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1422 | +| iterations | 6871 | +| time_elapsed | 9894 | +| total_timesteps | 14071808 | +| train/ | | +| approx_kl | 0.010402607 | +| clip_fraction | 0.303 | +| clip_range | 0.0715 | +| entropy_loss | -7.04 | +| explained_variance | 0.449 | +| learning_rate | 4.67e-05 | +| loss | -0.027 | +| n_updates | 43300 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000176 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1422 | +| iterations | 6872 | +| time_elapsed | 9895 | +| total_timesteps | 14073856 | +| train/ | | +| approx_kl | 0.009261959 | +| clip_fraction | 0.313 | +| clip_range | 0.0715 | +| entropy_loss | -7.24 | +| explained_variance | 0.358 | +| learning_rate | 4.67e-05 | +| loss | -0.0271 | +| n_updates | 43304 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000163 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1422 | +| iterations | 6873 | +| time_elapsed | 9897 | +| total_timesteps | 14075904 | +| train/ | | +| approx_kl | 0.0091567375 | +| clip_fraction | 0.318 | +| clip_range | 0.0715 | +| entropy_loss | -7.17 | +| explained_variance | 0.52 | +| learning_rate | 4.67e-05 | +| loss | -0.0331 | +| n_updates | 43308 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000113 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1422 | +| iterations | 6874 | +| time_elapsed | 9898 | +| total_timesteps | 14077952 | +| train/ | | +| approx_kl | 0.009925818 | +| clip_fraction | 0.319 | +| clip_range | 0.0715 | +| entropy_loss | -7.06 | +| explained_variance | 0.571 | +| learning_rate | 4.67e-05 | +| loss | -0.0314 | +| n_updates | 43312 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000109 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1422 | +| iterations | 6875 | +| time_elapsed | 9899 | +| total_timesteps | 14080000 | +| train/ | | +| approx_kl | 0.010194795 | +| clip_fraction | 0.303 | +| clip_range | 0.0715 | +| entropy_loss | -6.82 | +| explained_variance | 0.392 | +| learning_rate | 4.67e-05 | +| loss | -0.0232 | +| n_updates | 43316 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000433 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1422 | +| iterations | 6876 | +| time_elapsed | 9901 | +| total_timesteps | 14082048 | +| train/ | | +| approx_kl | 0.009921424 | +| clip_fraction | 0.302 | +| clip_range | 0.0715 | +| entropy_loss | -7.05 | +| explained_variance | 0.357 | +| learning_rate | 4.67e-05 | +| loss | -0.0297 | +| n_updates | 43320 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000169 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1422 | +| iterations | 6877 | +| time_elapsed | 9902 | +| total_timesteps | 14084096 | +| train/ | | +| approx_kl | 0.010076395 | +| clip_fraction | 0.298 | +| clip_range | 0.0715 | +| entropy_loss | -7.2 | +| explained_variance | 0.232 | +| learning_rate | 4.67e-05 | +| loss | -0.0356 | +| n_updates | 43324 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000141 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1422 | +| iterations | 6878 | +| time_elapsed | 9904 | +| total_timesteps | 14086144 | +| train/ | | +| approx_kl | 0.010075714 | +| clip_fraction | 0.316 | +| clip_range | 0.0715 | +| entropy_loss | -7.07 | +| explained_variance | 0.305 | +| learning_rate | 4.67e-05 | +| loss | -0.0309 | +| n_updates | 43328 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000225 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1422 | +| iterations | 6879 | +| time_elapsed | 9905 | +| total_timesteps | 14088192 | +| train/ | | +| approx_kl | 0.011570396 | +| clip_fraction | 0.342 | +| clip_range | 0.0715 | +| entropy_loss | -6.85 | +| explained_variance | 0.695 | +| learning_rate | 4.67e-05 | +| loss | -0.0374 | +| n_updates | 43332 | +| policy_gradient_loss | -0.023 | +| value_loss | 6.24e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1422 | +| iterations | 6880 | +| time_elapsed | 9907 | +| total_timesteps | 14090240 | +| train/ | | +| approx_kl | 0.010374496 | +| clip_fraction | 0.313 | +| clip_range | 0.0715 | +| entropy_loss | -7.13 | +| explained_variance | 0.293 | +| learning_rate | 4.67e-05 | +| loss | -0.0318 | +| n_updates | 43336 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000218 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1422 | +| iterations | 6881 | +| time_elapsed | 9908 | +| total_timesteps | 14092288 | +| train/ | | +| approx_kl | 0.009032378 | +| clip_fraction | 0.298 | +| clip_range | 0.0715 | +| entropy_loss | -7.12 | +| explained_variance | 0.434 | +| learning_rate | 4.67e-05 | +| loss | -0.0307 | +| n_updates | 43340 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000114 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1422 | +| iterations | 6882 | +| time_elapsed | 9909 | +| total_timesteps | 14094336 | +| train/ | | +| approx_kl | 0.010749869 | +| clip_fraction | 0.329 | +| clip_range | 0.0715 | +| entropy_loss | -7.05 | +| explained_variance | 0.597 | +| learning_rate | 4.67e-05 | +| loss | -0.0383 | +| n_updates | 43344 | +| policy_gradient_loss | -0.0212 | +| value_loss | 8.26e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1422 | +| iterations | 6883 | +| time_elapsed | 9911 | +| total_timesteps | 14096384 | +| train/ | | +| approx_kl | 0.010293844 | +| clip_fraction | 0.3 | +| clip_range | 0.0715 | +| entropy_loss | -7 | +| explained_variance | 0.529 | +| learning_rate | 4.67e-05 | +| loss | -0.0226 | +| n_updates | 43348 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000148 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1422 | +| iterations | 6884 | +| time_elapsed | 9912 | +| total_timesteps | 14098432 | +| train/ | | +| approx_kl | 0.009758287 | +| clip_fraction | 0.297 | +| clip_range | 0.0715 | +| entropy_loss | -7.01 | +| explained_variance | 0.461 | +| learning_rate | 4.67e-05 | +| loss | -0.0313 | +| n_updates | 43352 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.00015 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1422 | +| iterations | 6885 | +| time_elapsed | 9914 | +| total_timesteps | 14100480 | +| train/ | | +| approx_kl | 0.00800673 | +| clip_fraction | 0.279 | +| clip_range | 0.0715 | +| entropy_loss | -7.22 | +| explained_variance | 0.274 | +| learning_rate | 4.67e-05 | +| loss | -0.0309 | +| n_updates | 43356 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000206 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1422 | +| iterations | 6886 | +| time_elapsed | 9915 | +| total_timesteps | 14102528 | +| train/ | | +| approx_kl | 0.009573093 | +| clip_fraction | 0.296 | +| clip_range | 0.0715 | +| entropy_loss | -7.11 | +| explained_variance | 0.213 | +| learning_rate | 4.67e-05 | +| loss | -0.0285 | +| n_updates | 43360 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.00018 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1422 | +| iterations | 6887 | +| time_elapsed | 9916 | +| total_timesteps | 14104576 | +| train/ | | +| approx_kl | 0.010734207 | +| clip_fraction | 0.302 | +| clip_range | 0.0715 | +| entropy_loss | -7.26 | +| explained_variance | -0.174 | +| learning_rate | 4.67e-05 | +| loss | -0.0331 | +| n_updates | 43364 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000125 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1422 | +| iterations | 6888 | +| time_elapsed | 9918 | +| total_timesteps | 14106624 | +| train/ | | +| approx_kl | 0.010100538 | +| clip_fraction | 0.311 | +| clip_range | 0.0715 | +| entropy_loss | -7.28 | +| explained_variance | 0.391 | +| learning_rate | 4.67e-05 | +| loss | -0.0256 | +| n_updates | 43368 | +| policy_gradient_loss | -0.0188 | +| value_loss | 8.25e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1422 | +| iterations | 6889 | +| time_elapsed | 9919 | +| total_timesteps | 14108672 | +| train/ | | +| approx_kl | 0.010011885 | +| clip_fraction | 0.336 | +| clip_range | 0.0715 | +| entropy_loss | -7.2 | +| explained_variance | 0.479 | +| learning_rate | 4.66e-05 | +| loss | -0.0339 | +| n_updates | 43372 | +| policy_gradient_loss | -0.0209 | +| value_loss | 7e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1422 | +| iterations | 6890 | +| time_elapsed | 9921 | +| total_timesteps | 14110720 | +| train/ | | +| approx_kl | 0.01066204 | +| clip_fraction | 0.297 | +| clip_range | 0.0715 | +| entropy_loss | -6.98 | +| explained_variance | 0.346 | +| learning_rate | 4.66e-05 | +| loss | -0.0294 | +| n_updates | 43376 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000131 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1422 | +| iterations | 6891 | +| time_elapsed | 9922 | +| total_timesteps | 14112768 | +| train/ | | +| approx_kl | 0.009888072 | +| clip_fraction | 0.3 | +| clip_range | 0.0715 | +| entropy_loss | -6.48 | +| explained_variance | 0.696 | +| learning_rate | 4.66e-05 | +| loss | -0.0326 | +| n_updates | 43380 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000145 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1422 | +| iterations | 6892 | +| time_elapsed | 9924 | +| total_timesteps | 14114816 | +| train/ | | +| approx_kl | 0.0109031685 | +| clip_fraction | 0.327 | +| clip_range | 0.0715 | +| entropy_loss | -7.19 | +| explained_variance | 0.464 | +| learning_rate | 4.66e-05 | +| loss | -0.03 | +| n_updates | 43384 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000103 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1422 | +| iterations | 6893 | +| time_elapsed | 9925 | +| total_timesteps | 14116864 | +| train/ | | +| approx_kl | 0.009348646 | +| clip_fraction | 0.3 | +| clip_range | 0.0715 | +| entropy_loss | -7.29 | +| explained_variance | 0.435 | +| learning_rate | 4.66e-05 | +| loss | -0.0249 | +| n_updates | 43388 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000107 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1422 | +| iterations | 6894 | +| time_elapsed | 9926 | +| total_timesteps | 14118912 | +| train/ | | +| approx_kl | 0.009724143 | +| clip_fraction | 0.306 | +| clip_range | 0.0715 | +| entropy_loss | -7.36 | +| explained_variance | -0.127 | +| learning_rate | 4.66e-05 | +| loss | -0.031 | +| n_updates | 43392 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000123 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 1422 | +| iterations | 6895 | +| time_elapsed | 9928 | +| total_timesteps | 14120960 | +| train/ | | +| approx_kl | 0.009069333 | +| clip_fraction | 0.285 | +| clip_range | 0.0715 | +| entropy_loss | -7.03 | +| explained_variance | 0.517 | +| learning_rate | 4.66e-05 | +| loss | -0.0328 | +| n_updates | 43396 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000162 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 1422 | +| iterations | 6896 | +| time_elapsed | 9929 | +| total_timesteps | 14123008 | +| train/ | | +| approx_kl | 0.010044969 | +| clip_fraction | 0.31 | +| clip_range | 0.0715 | +| entropy_loss | -6.57 | +| explained_variance | 0.792 | +| learning_rate | 4.66e-05 | +| loss | -0.0323 | +| n_updates | 43400 | +| policy_gradient_loss | -0.0195 | +| value_loss | 8.05e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 1422 | +| iterations | 6897 | +| time_elapsed | 9931 | +| total_timesteps | 14125056 | +| train/ | | +| approx_kl | 0.011147192 | +| clip_fraction | 0.307 | +| clip_range | 0.0715 | +| entropy_loss | -7.03 | +| explained_variance | 0.313 | +| learning_rate | 4.66e-05 | +| loss | -0.0314 | +| n_updates | 43404 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000212 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.297 | +| time/ | | +| fps | 1422 | +| iterations | 6898 | +| time_elapsed | 9932 | +| total_timesteps | 14127104 | +| train/ | | +| approx_kl | 0.010065994 | +| clip_fraction | 0.288 | +| clip_range | 0.0715 | +| entropy_loss | -7.28 | +| explained_variance | 0.338 | +| learning_rate | 4.66e-05 | +| loss | -0.0265 | +| n_updates | 43408 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000165 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.294 | +| time/ | | +| fps | 1422 | +| iterations | 6899 | +| time_elapsed | 9934 | +| total_timesteps | 14129152 | +| train/ | | +| approx_kl | 0.010711262 | +| clip_fraction | 0.292 | +| clip_range | 0.0715 | +| entropy_loss | -6.99 | +| explained_variance | 0.445 | +| learning_rate | 4.66e-05 | +| loss | -0.0321 | +| n_updates | 43412 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.00015 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 1422 | +| iterations | 6900 | +| time_elapsed | 9935 | +| total_timesteps | 14131200 | +| train/ | | +| approx_kl | 0.01045696 | +| clip_fraction | 0.309 | +| clip_range | 0.0715 | +| entropy_loss | -7.2 | +| explained_variance | 0.353 | +| learning_rate | 4.66e-05 | +| loss | -0.0299 | +| n_updates | 43416 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.00013 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.298 | +| time/ | | +| fps | 1422 | +| iterations | 6901 | +| time_elapsed | 9937 | +| total_timesteps | 14133248 | +| train/ | | +| approx_kl | 0.008916877 | +| clip_fraction | 0.295 | +| clip_range | 0.0715 | +| entropy_loss | -7.16 | +| explained_variance | 0.294 | +| learning_rate | 4.66e-05 | +| loss | -0.0338 | +| n_updates | 43420 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000134 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.298 | +| time/ | | +| fps | 1422 | +| iterations | 6902 | +| time_elapsed | 9938 | +| total_timesteps | 14135296 | +| train/ | | +| approx_kl | 0.012095053 | +| clip_fraction | 0.336 | +| clip_range | 0.0715 | +| entropy_loss | -6.96 | +| explained_variance | 0.583 | +| learning_rate | 4.66e-05 | +| loss | -0.0288 | +| n_updates | 43424 | +| policy_gradient_loss | -0.0201 | +| value_loss | 9.37e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.306 | +| time/ | | +| fps | 1422 | +| iterations | 6903 | +| time_elapsed | 9940 | +| total_timesteps | 14137344 | +| train/ | | +| approx_kl | 0.012337364 | +| clip_fraction | 0.307 | +| clip_range | 0.0715 | +| entropy_loss | -7.25 | +| explained_variance | 0.395 | +| learning_rate | 4.66e-05 | +| loss | -0.0292 | +| n_updates | 43428 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000105 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 1422 | +| iterations | 6904 | +| time_elapsed | 9941 | +| total_timesteps | 14139392 | +| train/ | | +| approx_kl | 0.009167035 | +| clip_fraction | 0.271 | +| clip_range | 0.0715 | +| entropy_loss | -6.47 | +| explained_variance | 0.423 | +| learning_rate | 4.66e-05 | +| loss | -0.0254 | +| n_updates | 43432 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000443 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.298 | +| time/ | | +| fps | 1422 | +| iterations | 6905 | +| time_elapsed | 9942 | +| total_timesteps | 14141440 | +| train/ | | +| approx_kl | 0.012245465 | +| clip_fraction | 0.353 | +| clip_range | 0.0715 | +| entropy_loss | -7 | +| explained_variance | 0.274 | +| learning_rate | 4.66e-05 | +| loss | -0.0344 | +| n_updates | 43436 | +| policy_gradient_loss | -0.0236 | +| value_loss | 0.000141 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 1422 | +| iterations | 6906 | +| time_elapsed | 9944 | +| total_timesteps | 14143488 | +| train/ | | +| approx_kl | 0.009919507 | +| clip_fraction | 0.338 | +| clip_range | 0.0715 | +| entropy_loss | -6.77 | +| explained_variance | 0.628 | +| learning_rate | 4.66e-05 | +| loss | -0.0363 | +| n_updates | 43440 | +| policy_gradient_loss | -0.0221 | +| value_loss | 9.36e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 1422 | +| iterations | 6907 | +| time_elapsed | 9945 | +| total_timesteps | 14145536 | +| train/ | | +| approx_kl | 0.011031518 | +| clip_fraction | 0.328 | +| clip_range | 0.0715 | +| entropy_loss | -7.18 | +| explained_variance | 0.324 | +| learning_rate | 4.66e-05 | +| loss | -0.0337 | +| n_updates | 43444 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000112 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 1422 | +| iterations | 6908 | +| time_elapsed | 9947 | +| total_timesteps | 14147584 | +| train/ | | +| approx_kl | 0.011994103 | +| clip_fraction | 0.301 | +| clip_range | 0.0715 | +| entropy_loss | -7.37 | +| explained_variance | -0.0512 | +| learning_rate | 4.66e-05 | +| loss | -0.0303 | +| n_updates | 43448 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000149 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.292 | +| time/ | | +| fps | 1422 | +| iterations | 6909 | +| time_elapsed | 9948 | +| total_timesteps | 14149632 | +| train/ | | +| approx_kl | 0.008803333 | +| clip_fraction | 0.308 | +| clip_range | 0.0715 | +| entropy_loss | -7.51 | +| explained_variance | 0.0341 | +| learning_rate | 4.66e-05 | +| loss | -0.0318 | +| n_updates | 43452 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000182 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.294 | +| time/ | | +| fps | 1422 | +| iterations | 6910 | +| time_elapsed | 9950 | +| total_timesteps | 14151680 | +| train/ | | +| approx_kl | 0.009018824 | +| clip_fraction | 0.29 | +| clip_range | 0.0715 | +| entropy_loss | -7.23 | +| explained_variance | 0.331 | +| learning_rate | 4.66e-05 | +| loss | -0.0321 | +| n_updates | 43456 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000148 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.294 | +| time/ | | +| fps | 1422 | +| iterations | 6911 | +| time_elapsed | 9951 | +| total_timesteps | 14153728 | +| train/ | | +| approx_kl | 0.011276923 | +| clip_fraction | 0.302 | +| clip_range | 0.0715 | +| entropy_loss | -6.39 | +| explained_variance | 0.592 | +| learning_rate | 4.66e-05 | +| loss | -0.0272 | +| n_updates | 43460 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000245 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.3 | +| time/ | | +| fps | 1422 | +| iterations | 6912 | +| time_elapsed | 9952 | +| total_timesteps | 14155776 | +| train/ | | +| approx_kl | 0.011238665 | +| clip_fraction | 0.357 | +| clip_range | 0.0715 | +| entropy_loss | -7.05 | +| explained_variance | 0.362 | +| learning_rate | 4.66e-05 | +| loss | -0.0354 | +| n_updates | 43464 | +| policy_gradient_loss | -0.023 | +| value_loss | 7.84e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1422 | +| iterations | 6913 | +| time_elapsed | 9954 | +| total_timesteps | 14157824 | +| train/ | | +| approx_kl | 0.0100078415 | +| clip_fraction | 0.293 | +| clip_range | 0.0715 | +| entropy_loss | -7.32 | +| explained_variance | 0.227 | +| learning_rate | 4.66e-05 | +| loss | -0.0333 | +| n_updates | 43468 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000222 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1422 | +| iterations | 6914 | +| time_elapsed | 9955 | +| total_timesteps | 14159872 | +| train/ | | +| approx_kl | 0.010528265 | +| clip_fraction | 0.293 | +| clip_range | 0.0715 | +| entropy_loss | -6.89 | +| explained_variance | 0.425 | +| learning_rate | 4.66e-05 | +| loss | -0.0363 | +| n_updates | 43472 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000154 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1422 | +| iterations | 6915 | +| time_elapsed | 9957 | +| total_timesteps | 14161920 | +| train/ | | +| approx_kl | 0.011071056 | +| clip_fraction | 0.28 | +| clip_range | 0.0715 | +| entropy_loss | -6.42 | +| explained_variance | 0.549 | +| learning_rate | 4.66e-05 | +| loss | -0.0257 | +| n_updates | 43476 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000242 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1422 | +| iterations | 6916 | +| time_elapsed | 9958 | +| total_timesteps | 14163968 | +| train/ | | +| approx_kl | 0.007545311 | +| clip_fraction | 0.307 | +| clip_range | 0.0715 | +| entropy_loss | -7.29 | +| explained_variance | 0.265 | +| learning_rate | 4.66e-05 | +| loss | -0.0363 | +| n_updates | 43480 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000106 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1422 | +| iterations | 6917 | +| time_elapsed | 9960 | +| total_timesteps | 14166016 | +| train/ | | +| approx_kl | 0.00810831 | +| clip_fraction | 0.285 | +| clip_range | 0.0715 | +| entropy_loss | -7.34 | +| explained_variance | 0.205 | +| learning_rate | 4.66e-05 | +| loss | -0.0315 | +| n_updates | 43484 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000254 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1422 | +| iterations | 6918 | +| time_elapsed | 9961 | +| total_timesteps | 14168064 | +| train/ | | +| approx_kl | 0.008262886 | +| clip_fraction | 0.292 | +| clip_range | 0.0715 | +| entropy_loss | -7.19 | +| explained_variance | 0.296 | +| learning_rate | 4.66e-05 | +| loss | -0.0259 | +| n_updates | 43488 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000272 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1422 | +| iterations | 6919 | +| time_elapsed | 9963 | +| total_timesteps | 14170112 | +| train/ | | +| approx_kl | 0.008657262 | +| clip_fraction | 0.328 | +| clip_range | 0.0715 | +| entropy_loss | -7.24 | +| explained_variance | 0.322 | +| learning_rate | 4.66e-05 | +| loss | -0.041 | +| n_updates | 43492 | +| policy_gradient_loss | -0.0239 | +| value_loss | 9.77e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1422 | +| iterations | 6920 | +| time_elapsed | 9964 | +| total_timesteps | 14172160 | +| train/ | | +| approx_kl | 0.010107826 | +| clip_fraction | 0.321 | +| clip_range | 0.0715 | +| entropy_loss | -6.53 | +| explained_variance | 0.491 | +| learning_rate | 4.66e-05 | +| loss | -0.0302 | +| n_updates | 43496 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000283 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1422 | +| iterations | 6921 | +| time_elapsed | 9965 | +| total_timesteps | 14174208 | +| train/ | | +| approx_kl | 0.011903003 | +| clip_fraction | 0.316 | +| clip_range | 0.0715 | +| entropy_loss | -6.99 | +| explained_variance | 0.349 | +| learning_rate | 4.66e-05 | +| loss | -0.0272 | +| n_updates | 43500 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000145 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1422 | +| iterations | 6922 | +| time_elapsed | 9967 | +| total_timesteps | 14176256 | +| train/ | | +| approx_kl | 0.011557222 | +| clip_fraction | 0.333 | +| clip_range | 0.0715 | +| entropy_loss | -7.39 | +| explained_variance | -0.127 | +| learning_rate | 4.66e-05 | +| loss | -0.0398 | +| n_updates | 43504 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000119 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1422 | +| iterations | 6923 | +| time_elapsed | 9968 | +| total_timesteps | 14178304 | +| train/ | | +| approx_kl | 0.012911047 | +| clip_fraction | 0.319 | +| clip_range | 0.0715 | +| entropy_loss | -7.46 | +| explained_variance | -0.121 | +| learning_rate | 4.66e-05 | +| loss | -0.0347 | +| n_updates | 43508 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000196 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.315 | +| time/ | | +| fps | 1422 | +| iterations | 6924 | +| time_elapsed | 9970 | +| total_timesteps | 14180352 | +| train/ | | +| approx_kl | 0.011559596 | +| clip_fraction | 0.333 | +| clip_range | 0.0715 | +| entropy_loss | -7.3 | +| explained_variance | -0.105 | +| learning_rate | 4.66e-05 | +| loss | -0.0301 | +| n_updates | 43512 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000101 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1422 | +| iterations | 6925 | +| time_elapsed | 9971 | +| total_timesteps | 14182400 | +| train/ | | +| approx_kl | 0.011836955 | +| clip_fraction | 0.312 | +| clip_range | 0.0715 | +| entropy_loss | -6.86 | +| explained_variance | 0.469 | +| learning_rate | 4.66e-05 | +| loss | -0.0273 | +| n_updates | 43516 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000126 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1422 | +| iterations | 6926 | +| time_elapsed | 9973 | +| total_timesteps | 14184448 | +| train/ | | +| approx_kl | 0.010173009 | +| clip_fraction | 0.312 | +| clip_range | 0.0715 | +| entropy_loss | -7.04 | +| explained_variance | 0.502 | +| learning_rate | 4.66e-05 | +| loss | -0.0316 | +| n_updates | 43520 | +| policy_gradient_loss | -0.0202 | +| value_loss | 8.88e-05 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1422 | +| iterations | 6927 | +| time_elapsed | 9974 | +| total_timesteps | 14186496 | +| train/ | | +| approx_kl | 0.0117367 | +| clip_fraction | 0.323 | +| clip_range | 0.0715 | +| entropy_loss | -7.39 | +| explained_variance | -0.198 | +| learning_rate | 4.66e-05 | +| loss | -0.0346 | +| n_updates | 43524 | +| policy_gradient_loss | -0.0211 | +| value_loss | 5.81e-05 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 1422 | +| iterations | 6928 | +| time_elapsed | 9976 | +| total_timesteps | 14188544 | +| train/ | | +| approx_kl | 0.011265854 | +| clip_fraction | 0.279 | +| clip_range | 0.0715 | +| entropy_loss | -6.93 | +| explained_variance | 0.521 | +| learning_rate | 4.66e-05 | +| loss | -0.0277 | +| n_updates | 43528 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000152 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1422 | +| iterations | 6929 | +| time_elapsed | 9977 | +| total_timesteps | 14190592 | +| train/ | | +| approx_kl | 0.013103241 | +| clip_fraction | 0.326 | +| clip_range | 0.0715 | +| entropy_loss | -6.77 | +| explained_variance | 0.754 | +| learning_rate | 4.66e-05 | +| loss | -0.0344 | +| n_updates | 43532 | +| policy_gradient_loss | -0.0212 | +| value_loss | 6.77e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1422 | +| iterations | 6930 | +| time_elapsed | 9978 | +| total_timesteps | 14192640 | +| train/ | | +| approx_kl | 0.009882429 | +| clip_fraction | 0.286 | +| clip_range | 0.0715 | +| entropy_loss | -7.07 | +| explained_variance | 0.505 | +| learning_rate | 4.66e-05 | +| loss | -0.0272 | +| n_updates | 43536 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000131 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1422 | +| iterations | 6931 | +| time_elapsed | 9980 | +| total_timesteps | 14194688 | +| train/ | | +| approx_kl | 0.009555649 | +| clip_fraction | 0.325 | +| clip_range | 0.0715 | +| entropy_loss | -6.8 | +| explained_variance | 0.583 | +| learning_rate | 4.66e-05 | +| loss | -0.0336 | +| n_updates | 43540 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000113 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1422 | +| iterations | 6932 | +| time_elapsed | 9981 | +| total_timesteps | 14196736 | +| train/ | | +| approx_kl | 0.011885917 | +| clip_fraction | 0.324 | +| clip_range | 0.0715 | +| entropy_loss | -6.98 | +| explained_variance | 0.366 | +| learning_rate | 4.66e-05 | +| loss | -0.0331 | +| n_updates | 43544 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000217 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1422 | +| iterations | 6933 | +| time_elapsed | 9983 | +| total_timesteps | 14198784 | +| train/ | | +| approx_kl | 0.010939218 | +| clip_fraction | 0.329 | +| clip_range | 0.0715 | +| entropy_loss | -7.26 | +| explained_variance | 0.176 | +| learning_rate | 4.66e-05 | +| loss | -0.0347 | +| n_updates | 43548 | +| policy_gradient_loss | -0.0232 | +| value_loss | 5.37e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 1422 | +| iterations | 6934 | +| time_elapsed | 9984 | +| total_timesteps | 14200832 | +| train/ | | +| approx_kl | 0.009381385 | +| clip_fraction | 0.308 | +| clip_range | 0.0715 | +| entropy_loss | -7.12 | +| explained_variance | 0.423 | +| learning_rate | 4.66e-05 | +| loss | -0.0309 | +| n_updates | 43552 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.00015 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.306 | +| time/ | | +| fps | 1422 | +| iterations | 6935 | +| time_elapsed | 9986 | +| total_timesteps | 14202880 | +| train/ | | +| approx_kl | 0.01150999 | +| clip_fraction | 0.32 | +| clip_range | 0.0714 | +| entropy_loss | -7.35 | +| explained_variance | -0.0293 | +| learning_rate | 4.66e-05 | +| loss | -0.036 | +| n_updates | 43556 | +| policy_gradient_loss | -0.0205 | +| value_loss | 8.08e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 1422 | +| iterations | 6936 | +| time_elapsed | 9987 | +| total_timesteps | 14204928 | +| train/ | | +| approx_kl | 0.008633034 | +| clip_fraction | 0.263 | +| clip_range | 0.0714 | +| entropy_loss | -7.02 | +| explained_variance | 0.373 | +| learning_rate | 4.66e-05 | +| loss | -0.0221 | +| n_updates | 43560 | +| policy_gradient_loss | -0.0139 | +| value_loss | 0.000261 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 1422 | +| iterations | 6937 | +| time_elapsed | 9989 | +| total_timesteps | 14206976 | +| train/ | | +| approx_kl | 0.014965652 | +| clip_fraction | 0.29 | +| clip_range | 0.0714 | +| entropy_loss | -6.58 | +| explained_variance | 0.556 | +| learning_rate | 4.66e-05 | +| loss | -0.0286 | +| n_updates | 43564 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000215 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 1422 | +| iterations | 6938 | +| time_elapsed | 9990 | +| total_timesteps | 14209024 | +| train/ | | +| approx_kl | 0.010931769 | +| clip_fraction | 0.321 | +| clip_range | 0.0714 | +| entropy_loss | -6.89 | +| explained_variance | 0.546 | +| learning_rate | 4.66e-05 | +| loss | -0.032 | +| n_updates | 43568 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000114 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 1422 | +| iterations | 6939 | +| time_elapsed | 9991 | +| total_timesteps | 14211072 | +| train/ | | +| approx_kl | 0.009145791 | +| clip_fraction | 0.32 | +| clip_range | 0.0714 | +| entropy_loss | -6.83 | +| explained_variance | 0.569 | +| learning_rate | 4.66e-05 | +| loss | -0.035 | +| n_updates | 43572 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000117 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 1422 | +| iterations | 6940 | +| time_elapsed | 9993 | +| total_timesteps | 14213120 | +| train/ | | +| approx_kl | 0.008508862 | +| clip_fraction | 0.281 | +| clip_range | 0.0714 | +| entropy_loss | -7.15 | +| explained_variance | 0.246 | +| learning_rate | 4.66e-05 | +| loss | -0.0269 | +| n_updates | 43576 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000259 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1422 | +| iterations | 6941 | +| time_elapsed | 9994 | +| total_timesteps | 14215168 | +| train/ | | +| approx_kl | 0.010641144 | +| clip_fraction | 0.314 | +| clip_range | 0.0714 | +| entropy_loss | -7.07 | +| explained_variance | 0.437 | +| learning_rate | 4.66e-05 | +| loss | -0.0283 | +| n_updates | 43580 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000133 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 1422 | +| iterations | 6942 | +| time_elapsed | 9996 | +| total_timesteps | 14217216 | +| train/ | | +| approx_kl | 0.009019228 | +| clip_fraction | 0.3 | +| clip_range | 0.0714 | +| entropy_loss | -7.04 | +| explained_variance | 0.222 | +| learning_rate | 4.66e-05 | +| loss | -0.0324 | +| n_updates | 43584 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000344 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 1422 | +| iterations | 6943 | +| time_elapsed | 9997 | +| total_timesteps | 14219264 | +| train/ | | +| approx_kl | 0.008850945 | +| clip_fraction | 0.297 | +| clip_range | 0.0714 | +| entropy_loss | -7.2 | +| explained_variance | 0.118 | +| learning_rate | 4.66e-05 | +| loss | -0.0317 | +| n_updates | 43588 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000181 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1422 | +| iterations | 6944 | +| time_elapsed | 9999 | +| total_timesteps | 14221312 | +| train/ | | +| approx_kl | 0.011278903 | +| clip_fraction | 0.354 | +| clip_range | 0.0714 | +| entropy_loss | -7.26 | +| explained_variance | 0.306 | +| learning_rate | 4.66e-05 | +| loss | -0.0374 | +| n_updates | 43592 | +| policy_gradient_loss | -0.0219 | +| value_loss | 0.000137 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1422 | +| iterations | 6945 | +| time_elapsed | 10000 | +| total_timesteps | 14223360 | +| train/ | | +| approx_kl | 0.010290256 | +| clip_fraction | 0.324 | +| clip_range | 0.0714 | +| entropy_loss | -7.2 | +| explained_variance | 0.251 | +| learning_rate | 4.66e-05 | +| loss | -0.0285 | +| n_updates | 43596 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000212 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1422 | +| iterations | 6946 | +| time_elapsed | 10001 | +| total_timesteps | 14225408 | +| train/ | | +| approx_kl | 0.008233188 | +| clip_fraction | 0.31 | +| clip_range | 0.0714 | +| entropy_loss | -7.13 | +| explained_variance | 0.329 | +| learning_rate | 4.66e-05 | +| loss | -0.0317 | +| n_updates | 43600 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000202 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1422 | +| iterations | 6947 | +| time_elapsed | 10003 | +| total_timesteps | 14227456 | +| train/ | | +| approx_kl | 0.009728145 | +| clip_fraction | 0.344 | +| clip_range | 0.0714 | +| entropy_loss | -6.8 | +| explained_variance | 0.64 | +| learning_rate | 4.66e-05 | +| loss | -0.0281 | +| n_updates | 43604 | +| policy_gradient_loss | -0.0208 | +| value_loss | 9.9e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1422 | +| iterations | 6948 | +| time_elapsed | 10004 | +| total_timesteps | 14229504 | +| train/ | | +| approx_kl | 0.008620778 | +| clip_fraction | 0.311 | +| clip_range | 0.0714 | +| entropy_loss | -6.75 | +| explained_variance | 0.472 | +| learning_rate | 4.66e-05 | +| loss | -0.0313 | +| n_updates | 43608 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000215 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1422 | +| iterations | 6949 | +| time_elapsed | 10006 | +| total_timesteps | 14231552 | +| train/ | | +| approx_kl | 0.01064788 | +| clip_fraction | 0.316 | +| clip_range | 0.0714 | +| entropy_loss | -6.75 | +| explained_variance | 0.516 | +| learning_rate | 4.66e-05 | +| loss | -0.0368 | +| n_updates | 43612 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000171 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1422 | +| iterations | 6950 | +| time_elapsed | 10007 | +| total_timesteps | 14233600 | +| train/ | | +| approx_kl | 0.010781099 | +| clip_fraction | 0.302 | +| clip_range | 0.0714 | +| entropy_loss | -7.07 | +| explained_variance | 0.147 | +| learning_rate | 4.66e-05 | +| loss | -0.0309 | +| n_updates | 43616 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000289 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1422 | +| iterations | 6951 | +| time_elapsed | 10009 | +| total_timesteps | 14235648 | +| train/ | | +| approx_kl | 0.011370551 | +| clip_fraction | 0.329 | +| clip_range | 0.0714 | +| entropy_loss | -6.97 | +| explained_variance | 0.427 | +| learning_rate | 4.66e-05 | +| loss | -0.0375 | +| n_updates | 43620 | +| policy_gradient_loss | -0.022 | +| value_loss | 0.000158 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1422 | +| iterations | 6952 | +| time_elapsed | 10010 | +| total_timesteps | 14237696 | +| train/ | | +| approx_kl | 0.012109765 | +| clip_fraction | 0.372 | +| clip_range | 0.0714 | +| entropy_loss | -7.15 | +| explained_variance | -0.179 | +| learning_rate | 4.66e-05 | +| loss | -0.0378 | +| n_updates | 43624 | +| policy_gradient_loss | -0.0222 | +| value_loss | 0.000133 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1422 | +| iterations | 6953 | +| time_elapsed | 10012 | +| total_timesteps | 14239744 | +| train/ | | +| approx_kl | 0.011515474 | +| clip_fraction | 0.328 | +| clip_range | 0.0714 | +| entropy_loss | -7.08 | +| explained_variance | 0.436 | +| learning_rate | 4.66e-05 | +| loss | -0.0381 | +| n_updates | 43628 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000149 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1422 | +| iterations | 6954 | +| time_elapsed | 10013 | +| total_timesteps | 14241792 | +| train/ | | +| approx_kl | 0.010725439 | +| clip_fraction | 0.299 | +| clip_range | 0.0714 | +| entropy_loss | -7.05 | +| explained_variance | 0.467 | +| learning_rate | 4.66e-05 | +| loss | -0.0318 | +| n_updates | 43632 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000169 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1422 | +| iterations | 6955 | +| time_elapsed | 10015 | +| total_timesteps | 14243840 | +| train/ | | +| approx_kl | 0.009586066 | +| clip_fraction | 0.31 | +| clip_range | 0.0714 | +| entropy_loss | -7.16 | +| explained_variance | 0.213 | +| learning_rate | 4.66e-05 | +| loss | -0.0332 | +| n_updates | 43636 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000229 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1422 | +| iterations | 6956 | +| time_elapsed | 10016 | +| total_timesteps | 14245888 | +| train/ | | +| approx_kl | 0.0086061945 | +| clip_fraction | 0.312 | +| clip_range | 0.0714 | +| entropy_loss | -7.2 | +| explained_variance | 0.239 | +| learning_rate | 4.66e-05 | +| loss | -0.0283 | +| n_updates | 43640 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000179 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1422 | +| iterations | 6957 | +| time_elapsed | 10017 | +| total_timesteps | 14247936 | +| train/ | | +| approx_kl | 0.010443347 | +| clip_fraction | 0.332 | +| clip_range | 0.0714 | +| entropy_loss | -7.29 | +| explained_variance | -0.115 | +| learning_rate | 4.66e-05 | +| loss | -0.0337 | +| n_updates | 43644 | +| policy_gradient_loss | -0.0225 | +| value_loss | 7.51e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1422 | +| iterations | 6958 | +| time_elapsed | 10019 | +| total_timesteps | 14249984 | +| train/ | | +| approx_kl | 0.011209572 | +| clip_fraction | 0.339 | +| clip_range | 0.0714 | +| entropy_loss | -6.83 | +| explained_variance | 0.787 | +| learning_rate | 4.66e-05 | +| loss | -0.0347 | +| n_updates | 43648 | +| policy_gradient_loss | -0.023 | +| value_loss | 5.43e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1422 | +| iterations | 6959 | +| time_elapsed | 10020 | +| total_timesteps | 14252032 | +| train/ | | +| approx_kl | 0.009435994 | +| clip_fraction | 0.312 | +| clip_range | 0.0714 | +| entropy_loss | -6.75 | +| explained_variance | 0.671 | +| learning_rate | 4.66e-05 | +| loss | -0.0298 | +| n_updates | 43652 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000111 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1422 | +| iterations | 6960 | +| time_elapsed | 10022 | +| total_timesteps | 14254080 | +| train/ | | +| approx_kl | 0.010800926 | +| clip_fraction | 0.3 | +| clip_range | 0.0714 | +| entropy_loss | -6.76 | +| explained_variance | 0.361 | +| learning_rate | 4.66e-05 | +| loss | -0.0267 | +| n_updates | 43656 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000305 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1422 | +| iterations | 6961 | +| time_elapsed | 10023 | +| total_timesteps | 14256128 | +| train/ | | +| approx_kl | 0.010241004 | +| clip_fraction | 0.322 | +| clip_range | 0.0714 | +| entropy_loss | -6.79 | +| explained_variance | 0.494 | +| learning_rate | 4.66e-05 | +| loss | -0.0297 | +| n_updates | 43660 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000164 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1422 | +| iterations | 6962 | +| time_elapsed | 10024 | +| total_timesteps | 14258176 | +| train/ | | +| approx_kl | 0.010915272 | +| clip_fraction | 0.319 | +| clip_range | 0.0714 | +| entropy_loss | -6.93 | +| explained_variance | 0.468 | +| learning_rate | 4.66e-05 | +| loss | -0.0281 | +| n_updates | 43664 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000152 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1422 | +| iterations | 6963 | +| time_elapsed | 10026 | +| total_timesteps | 14260224 | +| train/ | | +| approx_kl | 0.009591142 | +| clip_fraction | 0.305 | +| clip_range | 0.0714 | +| entropy_loss | -7.41 | +| explained_variance | -0.175 | +| learning_rate | 4.66e-05 | +| loss | -0.0307 | +| n_updates | 43668 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000115 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.315 | +| time/ | | +| fps | 1422 | +| iterations | 6964 | +| time_elapsed | 10027 | +| total_timesteps | 14262272 | +| train/ | | +| approx_kl | 0.012900032 | +| clip_fraction | 0.331 | +| clip_range | 0.0714 | +| entropy_loss | -7.2 | +| explained_variance | 0.411 | +| learning_rate | 4.66e-05 | +| loss | -0.0338 | +| n_updates | 43672 | +| policy_gradient_loss | -0.0218 | +| value_loss | 7.67e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.315 | +| time/ | | +| fps | 1422 | +| iterations | 6965 | +| time_elapsed | 10029 | +| total_timesteps | 14264320 | +| train/ | | +| approx_kl | 0.011513969 | +| clip_fraction | 0.338 | +| clip_range | 0.0714 | +| entropy_loss | -6.85 | +| explained_variance | 0.641 | +| learning_rate | 4.66e-05 | +| loss | -0.0327 | +| n_updates | 43676 | +| policy_gradient_loss | -0.0217 | +| value_loss | 8.12e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1422 | +| iterations | 6966 | +| time_elapsed | 10030 | +| total_timesteps | 14266368 | +| train/ | | +| approx_kl | 0.009929767 | +| clip_fraction | 0.311 | +| clip_range | 0.0714 | +| entropy_loss | -7.35 | +| explained_variance | 0.034 | +| learning_rate | 4.66e-05 | +| loss | -0.0291 | +| n_updates | 43680 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000141 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1422 | +| iterations | 6967 | +| time_elapsed | 10032 | +| total_timesteps | 14268416 | +| train/ | | +| approx_kl | 0.0090442225 | +| clip_fraction | 0.278 | +| clip_range | 0.0714 | +| entropy_loss | -7.01 | +| explained_variance | 0.472 | +| learning_rate | 4.66e-05 | +| loss | -0.0292 | +| n_updates | 43684 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.00017 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1422 | +| iterations | 6968 | +| time_elapsed | 10033 | +| total_timesteps | 14270464 | +| train/ | | +| approx_kl | 0.0132363755 | +| clip_fraction | 0.336 | +| clip_range | 0.0714 | +| entropy_loss | -7.16 | +| explained_variance | 0.0617 | +| learning_rate | 4.66e-05 | +| loss | -0.0335 | +| n_updates | 43688 | +| policy_gradient_loss | -0.0208 | +| value_loss | 8.27e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1422 | +| iterations | 6969 | +| time_elapsed | 10034 | +| total_timesteps | 14272512 | +| train/ | | +| approx_kl | 0.010785679 | +| clip_fraction | 0.304 | +| clip_range | 0.0714 | +| entropy_loss | -6.95 | +| explained_variance | 0.406 | +| learning_rate | 4.66e-05 | +| loss | -0.03 | +| n_updates | 43692 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000172 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1422 | +| iterations | 6970 | +| time_elapsed | 10036 | +| total_timesteps | 14274560 | +| train/ | | +| approx_kl | 0.011746405 | +| clip_fraction | 0.325 | +| clip_range | 0.0714 | +| entropy_loss | -6.77 | +| explained_variance | 0.476 | +| learning_rate | 4.66e-05 | +| loss | -0.0219 | +| n_updates | 43696 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000178 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1422 | +| iterations | 6971 | +| time_elapsed | 10037 | +| total_timesteps | 14276608 | +| train/ | | +| approx_kl | 0.013226505 | +| clip_fraction | 0.31 | +| clip_range | 0.0714 | +| entropy_loss | -6.87 | +| explained_variance | 0.371 | +| learning_rate | 4.66e-05 | +| loss | -0.0281 | +| n_updates | 43700 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000224 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1422 | +| iterations | 6972 | +| time_elapsed | 10039 | +| total_timesteps | 14278656 | +| train/ | | +| approx_kl | 0.011227047 | +| clip_fraction | 0.339 | +| clip_range | 0.0714 | +| entropy_loss | -6.83 | +| explained_variance | 0.644 | +| learning_rate | 4.66e-05 | +| loss | -0.0342 | +| n_updates | 43704 | +| policy_gradient_loss | -0.0212 | +| value_loss | 9.44e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1422 | +| iterations | 6973 | +| time_elapsed | 10040 | +| total_timesteps | 14280704 | +| train/ | | +| approx_kl | 0.013017697 | +| clip_fraction | 0.33 | +| clip_range | 0.0714 | +| entropy_loss | -6.89 | +| explained_variance | 0.514 | +| learning_rate | 4.66e-05 | +| loss | -0.0315 | +| n_updates | 43708 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.00011 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1422 | +| iterations | 6974 | +| time_elapsed | 10042 | +| total_timesteps | 14282752 | +| train/ | | +| approx_kl | 0.008897714 | +| clip_fraction | 0.284 | +| clip_range | 0.0714 | +| entropy_loss | -6.95 | +| explained_variance | 0.419 | +| learning_rate | 4.66e-05 | +| loss | -0.0284 | +| n_updates | 43712 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000194 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1422 | +| iterations | 6975 | +| time_elapsed | 10043 | +| total_timesteps | 14284800 | +| train/ | | +| approx_kl | 0.009484652 | +| clip_fraction | 0.33 | +| clip_range | 0.0714 | +| entropy_loss | -7.28 | +| explained_variance | 0.269 | +| learning_rate | 4.66e-05 | +| loss | -0.0272 | +| n_updates | 43716 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000202 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1422 | +| iterations | 6976 | +| time_elapsed | 10045 | +| total_timesteps | 14286848 | +| train/ | | +| approx_kl | 0.009645378 | +| clip_fraction | 0.313 | +| clip_range | 0.0714 | +| entropy_loss | -6.66 | +| explained_variance | 0.35 | +| learning_rate | 4.66e-05 | +| loss | -0.0318 | +| n_updates | 43720 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000405 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1422 | +| iterations | 6977 | +| time_elapsed | 10046 | +| total_timesteps | 14288896 | +| train/ | | +| approx_kl | 0.011484754 | +| clip_fraction | 0.355 | +| clip_range | 0.0714 | +| entropy_loss | -6.81 | +| explained_variance | 0.299 | +| learning_rate | 4.66e-05 | +| loss | -0.0251 | +| n_updates | 43724 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000298 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1422 | +| iterations | 6978 | +| time_elapsed | 10047 | +| total_timesteps | 14290944 | +| train/ | | +| approx_kl | 0.010389796 | +| clip_fraction | 0.332 | +| clip_range | 0.0714 | +| entropy_loss | -7.2 | +| explained_variance | 0.204 | +| learning_rate | 4.66e-05 | +| loss | -0.0365 | +| n_updates | 43728 | +| policy_gradient_loss | -0.0229 | +| value_loss | 0.000145 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1422 | +| iterations | 6979 | +| time_elapsed | 10049 | +| total_timesteps | 14292992 | +| train/ | | +| approx_kl | 0.009448042 | +| clip_fraction | 0.338 | +| clip_range | 0.0714 | +| entropy_loss | -6.99 | +| explained_variance | 0.199 | +| learning_rate | 4.66e-05 | +| loss | -0.0264 | +| n_updates | 43732 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000271 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1422 | +| iterations | 6980 | +| time_elapsed | 10050 | +| total_timesteps | 14295040 | +| train/ | | +| approx_kl | 0.011532249 | +| clip_fraction | 0.334 | +| clip_range | 0.0714 | +| entropy_loss | -6.62 | +| explained_variance | 0.504 | +| learning_rate | 4.66e-05 | +| loss | -0.0319 | +| n_updates | 43736 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000181 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1422 | +| iterations | 6981 | +| time_elapsed | 10052 | +| total_timesteps | 14297088 | +| train/ | | +| approx_kl | 0.010870899 | +| clip_fraction | 0.331 | +| clip_range | 0.0714 | +| entropy_loss | -7.17 | +| explained_variance | 0.251 | +| learning_rate | 4.66e-05 | +| loss | -0.0308 | +| n_updates | 43740 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.00018 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1422 | +| iterations | 6982 | +| time_elapsed | 10053 | +| total_timesteps | 14299136 | +| train/ | | +| approx_kl | 0.012764784 | +| clip_fraction | 0.319 | +| clip_range | 0.0714 | +| entropy_loss | -7.06 | +| explained_variance | -0.114 | +| learning_rate | 4.66e-05 | +| loss | -0.0335 | +| n_updates | 43744 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000239 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1422 | +| iterations | 6983 | +| time_elapsed | 10055 | +| total_timesteps | 14301184 | +| train/ | | +| approx_kl | 0.014894069 | +| clip_fraction | 0.337 | +| clip_range | 0.0714 | +| entropy_loss | -7.09 | +| explained_variance | 0.243 | +| learning_rate | 4.66e-05 | +| loss | -0.0328 | +| n_updates | 43748 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1422 | +| iterations | 6984 | +| time_elapsed | 10056 | +| total_timesteps | 14303232 | +| train/ | | +| approx_kl | 0.015496986 | +| clip_fraction | 0.291 | +| clip_range | 0.0714 | +| entropy_loss | -6.98 | +| explained_variance | 0.269 | +| learning_rate | 4.66e-05 | +| loss | -0.0258 | +| n_updates | 43752 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000373 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1422 | +| iterations | 6985 | +| time_elapsed | 10057 | +| total_timesteps | 14305280 | +| train/ | | +| approx_kl | 0.011726944 | +| clip_fraction | 0.321 | +| clip_range | 0.0714 | +| entropy_loss | -6.55 | +| explained_variance | 0.705 | +| learning_rate | 4.66e-05 | +| loss | -0.0324 | +| n_updates | 43756 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000111 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1422 | +| iterations | 6986 | +| time_elapsed | 10059 | +| total_timesteps | 14307328 | +| train/ | | +| approx_kl | 0.010406053 | +| clip_fraction | 0.35 | +| clip_range | 0.0714 | +| entropy_loss | -6.66 | +| explained_variance | 0.572 | +| learning_rate | 4.66e-05 | +| loss | -0.0316 | +| n_updates | 43760 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000156 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1422 | +| iterations | 6987 | +| time_elapsed | 10060 | +| total_timesteps | 14309376 | +| train/ | | +| approx_kl | 0.0110353585 | +| clip_fraction | 0.348 | +| clip_range | 0.0714 | +| entropy_loss | -7.32 | +| explained_variance | 0.0186 | +| learning_rate | 4.66e-05 | +| loss | -0.037 | +| n_updates | 43764 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000116 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1422 | +| iterations | 6988 | +| time_elapsed | 10062 | +| total_timesteps | 14311424 | +| train/ | | +| approx_kl | 0.008674305 | +| clip_fraction | 0.312 | +| clip_range | 0.0714 | +| entropy_loss | -7.06 | +| explained_variance | 0.274 | +| learning_rate | 4.66e-05 | +| loss | -0.0356 | +| n_updates | 43768 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.00021 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1422 | +| iterations | 6989 | +| time_elapsed | 10063 | +| total_timesteps | 14313472 | +| train/ | | +| approx_kl | 0.009884616 | +| clip_fraction | 0.352 | +| clip_range | 0.0714 | +| entropy_loss | -7.22 | +| explained_variance | 0.372 | +| learning_rate | 4.66e-05 | +| loss | -0.0361 | +| n_updates | 43772 | +| policy_gradient_loss | -0.0236 | +| value_loss | 9.85e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1422 | +| iterations | 6990 | +| time_elapsed | 10064 | +| total_timesteps | 14315520 | +| train/ | | +| approx_kl | 0.010554612 | +| clip_fraction | 0.309 | +| clip_range | 0.0714 | +| entropy_loss | -6.41 | +| explained_variance | 0.423 | +| learning_rate | 4.66e-05 | +| loss | -0.0273 | +| n_updates | 43776 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000349 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1422 | +| iterations | 6991 | +| time_elapsed | 10066 | +| total_timesteps | 14317568 | +| train/ | | +| approx_kl | 0.013246231 | +| clip_fraction | 0.354 | +| clip_range | 0.0714 | +| entropy_loss | -7.09 | +| explained_variance | 0.223 | +| learning_rate | 4.66e-05 | +| loss | -0.0432 | +| n_updates | 43780 | +| policy_gradient_loss | -0.0239 | +| value_loss | 0.000168 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1422 | +| iterations | 6992 | +| time_elapsed | 10067 | +| total_timesteps | 14319616 | +| train/ | | +| approx_kl | 0.009972776 | +| clip_fraction | 0.323 | +| clip_range | 0.0714 | +| entropy_loss | -7.06 | +| explained_variance | 0.339 | +| learning_rate | 4.66e-05 | +| loss | -0.0361 | +| n_updates | 43784 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000211 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1422 | +| iterations | 6993 | +| time_elapsed | 10069 | +| total_timesteps | 14321664 | +| train/ | | +| approx_kl | 0.012351608 | +| clip_fraction | 0.348 | +| clip_range | 0.0714 | +| entropy_loss | -6.67 | +| explained_variance | 0.609 | +| learning_rate | 4.66e-05 | +| loss | -0.0371 | +| n_updates | 43788 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000135 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1422 | +| iterations | 6994 | +| time_elapsed | 10070 | +| total_timesteps | 14323712 | +| train/ | | +| approx_kl | 0.010153728 | +| clip_fraction | 0.364 | +| clip_range | 0.0714 | +| entropy_loss | -7 | +| explained_variance | 0.278 | +| learning_rate | 4.66e-05 | +| loss | -0.0414 | +| n_updates | 43792 | +| policy_gradient_loss | -0.0252 | +| value_loss | 8.45e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1422 | +| iterations | 6995 | +| time_elapsed | 10072 | +| total_timesteps | 14325760 | +| train/ | | +| approx_kl | 0.011498656 | +| clip_fraction | 0.31 | +| clip_range | 0.0714 | +| entropy_loss | -6.92 | +| explained_variance | 0.253 | +| learning_rate | 4.66e-05 | +| loss | -0.0308 | +| n_updates | 43796 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.00025 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1422 | +| iterations | 6996 | +| time_elapsed | 10073 | +| total_timesteps | 14327808 | +| train/ | | +| approx_kl | 0.01025082 | +| clip_fraction | 0.336 | +| clip_range | 0.0714 | +| entropy_loss | -7.01 | +| explained_variance | 0.566 | +| learning_rate | 4.66e-05 | +| loss | -0.0283 | +| n_updates | 43800 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000102 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1422 | +| iterations | 6997 | +| time_elapsed | 10075 | +| total_timesteps | 14329856 | +| train/ | | +| approx_kl | 0.010486592 | +| clip_fraction | 0.318 | +| clip_range | 0.0714 | +| entropy_loss | -7.1 | +| explained_variance | 0.241 | +| learning_rate | 4.66e-05 | +| loss | -0.0309 | +| n_updates | 43804 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.00018 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1422 | +| iterations | 6998 | +| time_elapsed | 10076 | +| total_timesteps | 14331904 | +| train/ | | +| approx_kl | 0.009763623 | +| clip_fraction | 0.298 | +| clip_range | 0.0714 | +| entropy_loss | -7.14 | +| explained_variance | 0.238 | +| learning_rate | 4.66e-05 | +| loss | -0.0214 | +| n_updates | 43808 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000271 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1422 | +| iterations | 6999 | +| time_elapsed | 10077 | +| total_timesteps | 14333952 | +| train/ | | +| approx_kl | 0.008679402 | +| clip_fraction | 0.277 | +| clip_range | 0.0714 | +| entropy_loss | -7.1 | +| explained_variance | 0.164 | +| learning_rate | 4.66e-05 | +| loss | -0.0225 | +| n_updates | 43812 | +| policy_gradient_loss | -0.013 | +| value_loss | 0.000224 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1422 | +| iterations | 7000 | +| time_elapsed | 10079 | +| total_timesteps | 14336000 | +| train/ | | +| approx_kl | 0.013322571 | +| clip_fraction | 0.324 | +| clip_range | 0.0714 | +| entropy_loss | -6.68 | +| explained_variance | 0.594 | +| learning_rate | 4.66e-05 | +| loss | -0.0355 | +| n_updates | 43816 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000137 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1422 | +| iterations | 7001 | +| time_elapsed | 10080 | +| total_timesteps | 14338048 | +| train/ | | +| approx_kl | 0.008874072 | +| clip_fraction | 0.305 | +| clip_range | 0.0714 | +| entropy_loss | -6.76 | +| explained_variance | 0.516 | +| learning_rate | 4.66e-05 | +| loss | -0.0289 | +| n_updates | 43820 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.00021 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1422 | +| iterations | 7002 | +| time_elapsed | 10082 | +| total_timesteps | 14340096 | +| train/ | | +| approx_kl | 0.008898247 | +| clip_fraction | 0.287 | +| clip_range | 0.0714 | +| entropy_loss | -7.12 | +| explained_variance | 0.259 | +| learning_rate | 4.66e-05 | +| loss | -0.031 | +| n_updates | 43824 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000156 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1422 | +| iterations | 7003 | +| time_elapsed | 10083 | +| total_timesteps | 14342144 | +| train/ | | +| approx_kl | 0.010832146 | +| clip_fraction | 0.34 | +| clip_range | 0.0714 | +| entropy_loss | -7.24 | +| explained_variance | -0.185 | +| learning_rate | 4.66e-05 | +| loss | -0.0358 | +| n_updates | 43828 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000148 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1422 | +| iterations | 7004 | +| time_elapsed | 10085 | +| total_timesteps | 14344192 | +| train/ | | +| approx_kl | 0.009200478 | +| clip_fraction | 0.265 | +| clip_range | 0.0714 | +| entropy_loss | -6.64 | +| explained_variance | 0.392 | +| learning_rate | 4.66e-05 | +| loss | -0.0218 | +| n_updates | 43832 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000288 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1422 | +| iterations | 7005 | +| time_elapsed | 10086 | +| total_timesteps | 14346240 | +| train/ | | +| approx_kl | 0.01215103 | +| clip_fraction | 0.327 | +| clip_range | 0.0714 | +| entropy_loss | -6.88 | +| explained_variance | 0.687 | +| learning_rate | 4.66e-05 | +| loss | -0.0348 | +| n_updates | 43836 | +| policy_gradient_loss | -0.0217 | +| value_loss | 7.2e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1422 | +| iterations | 7006 | +| time_elapsed | 10087 | +| total_timesteps | 14348288 | +| train/ | | +| approx_kl | 0.010799867 | +| clip_fraction | 0.313 | +| clip_range | 0.0714 | +| entropy_loss | -7.04 | +| explained_variance | 0.254 | +| learning_rate | 4.66e-05 | +| loss | -0.0223 | +| n_updates | 43840 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000195 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1422 | +| iterations | 7007 | +| time_elapsed | 10089 | +| total_timesteps | 14350336 | +| train/ | | +| approx_kl | 0.010929956 | +| clip_fraction | 0.316 | +| clip_range | 0.0714 | +| entropy_loss | -6.95 | +| explained_variance | 0.474 | +| learning_rate | 4.66e-05 | +| loss | -0.0321 | +| n_updates | 43844 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000146 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1422 | +| iterations | 7008 | +| time_elapsed | 10090 | +| total_timesteps | 14352384 | +| train/ | | +| approx_kl | 0.009750191 | +| clip_fraction | 0.323 | +| clip_range | 0.0714 | +| entropy_loss | -6.65 | +| explained_variance | 0.597 | +| learning_rate | 4.66e-05 | +| loss | -0.0323 | +| n_updates | 43848 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000144 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1422 | +| iterations | 7009 | +| time_elapsed | 10092 | +| total_timesteps | 14354432 | +| train/ | | +| approx_kl | 0.010452036 | +| clip_fraction | 0.349 | +| clip_range | 0.0714 | +| entropy_loss | -7.23 | +| explained_variance | -0.0618 | +| learning_rate | 4.66e-05 | +| loss | -0.0334 | +| n_updates | 43852 | +| policy_gradient_loss | -0.0225 | +| value_loss | 5.21e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1422 | +| iterations | 7010 | +| time_elapsed | 10093 | +| total_timesteps | 14356480 | +| train/ | | +| approx_kl | 0.009304923 | +| clip_fraction | 0.299 | +| clip_range | 0.0714 | +| entropy_loss | -7.13 | +| explained_variance | 0.414 | +| learning_rate | 4.66e-05 | +| loss | -0.0286 | +| n_updates | 43856 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000134 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1422 | +| iterations | 7011 | +| time_elapsed | 10095 | +| total_timesteps | 14358528 | +| train/ | | +| approx_kl | 0.013802106 | +| clip_fraction | 0.3 | +| clip_range | 0.0714 | +| entropy_loss | -6.93 | +| explained_variance | 0.416 | +| learning_rate | 4.66e-05 | +| loss | -0.0285 | +| n_updates | 43860 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000195 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1422 | +| iterations | 7012 | +| time_elapsed | 10096 | +| total_timesteps | 14360576 | +| train/ | | +| approx_kl | 0.010169445 | +| clip_fraction | 0.292 | +| clip_range | 0.0714 | +| entropy_loss | -6.75 | +| explained_variance | 0.409 | +| learning_rate | 4.66e-05 | +| loss | -0.0287 | +| n_updates | 43864 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.00031 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1422 | +| iterations | 7013 | +| time_elapsed | 10098 | +| total_timesteps | 14362624 | +| train/ | | +| approx_kl | 0.012327807 | +| clip_fraction | 0.36 | +| clip_range | 0.0714 | +| entropy_loss | -6.99 | +| explained_variance | 0.444 | +| learning_rate | 4.66e-05 | +| loss | -0.0352 | +| n_updates | 43868 | +| policy_gradient_loss | -0.0234 | +| value_loss | 8.15e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1422 | +| iterations | 7014 | +| time_elapsed | 10099 | +| total_timesteps | 14364672 | +| train/ | | +| approx_kl | 0.010830257 | +| clip_fraction | 0.325 | +| clip_range | 0.0714 | +| entropy_loss | -6.99 | +| explained_variance | 0.338 | +| learning_rate | 4.66e-05 | +| loss | -0.035 | +| n_updates | 43872 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000231 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1422 | +| iterations | 7015 | +| time_elapsed | 10100 | +| total_timesteps | 14366720 | +| train/ | | +| approx_kl | 0.010558699 | +| clip_fraction | 0.288 | +| clip_range | 0.0714 | +| entropy_loss | -7.17 | +| explained_variance | 0.0962 | +| learning_rate | 4.66e-05 | +| loss | -0.0317 | +| n_updates | 43876 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000189 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1422 | +| iterations | 7016 | +| time_elapsed | 10102 | +| total_timesteps | 14368768 | +| train/ | | +| approx_kl | 0.010335182 | +| clip_fraction | 0.305 | +| clip_range | 0.0714 | +| entropy_loss | -6.6 | +| explained_variance | 0.535 | +| learning_rate | 4.66e-05 | +| loss | -0.0304 | +| n_updates | 43880 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000212 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1422 | +| iterations | 7017 | +| time_elapsed | 10103 | +| total_timesteps | 14370816 | +| train/ | | +| approx_kl | 0.00917688 | +| clip_fraction | 0.313 | +| clip_range | 0.0714 | +| entropy_loss | -7.26 | +| explained_variance | -0.0101 | +| learning_rate | 4.66e-05 | +| loss | -0.0214 | +| n_updates | 43884 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000168 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1422 | +| iterations | 7018 | +| time_elapsed | 10105 | +| total_timesteps | 14372864 | +| train/ | | +| approx_kl | 0.010382526 | +| clip_fraction | 0.314 | +| clip_range | 0.0714 | +| entropy_loss | -6.92 | +| explained_variance | 0.476 | +| learning_rate | 4.66e-05 | +| loss | -0.0313 | +| n_updates | 43888 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000134 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1422 | +| iterations | 7019 | +| time_elapsed | 10106 | +| total_timesteps | 14374912 | +| train/ | | +| approx_kl | 0.009466822 | +| clip_fraction | 0.331 | +| clip_range | 0.0714 | +| entropy_loss | -6.9 | +| explained_variance | 0.564 | +| learning_rate | 4.66e-05 | +| loss | -0.0339 | +| n_updates | 43892 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000113 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1422 | +| iterations | 7020 | +| time_elapsed | 10108 | +| total_timesteps | 14376960 | +| train/ | | +| approx_kl | 0.013118086 | +| clip_fraction | 0.36 | +| clip_range | 0.0714 | +| entropy_loss | -7.07 | +| explained_variance | 0.303 | +| learning_rate | 4.66e-05 | +| loss | -0.0389 | +| n_updates | 43896 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000161 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1422 | +| iterations | 7021 | +| time_elapsed | 10109 | +| total_timesteps | 14379008 | +| train/ | | +| approx_kl | 0.009380396 | +| clip_fraction | 0.285 | +| clip_range | 0.0714 | +| entropy_loss | -6.99 | +| explained_variance | 0.335 | +| learning_rate | 4.66e-05 | +| loss | -0.0261 | +| n_updates | 43900 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000214 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1422 | +| iterations | 7022 | +| time_elapsed | 10111 | +| total_timesteps | 14381056 | +| train/ | | +| approx_kl | 0.016034305 | +| clip_fraction | 0.32 | +| clip_range | 0.0714 | +| entropy_loss | -6.93 | +| explained_variance | 0.449 | +| learning_rate | 4.66e-05 | +| loss | -0.0332 | +| n_updates | 43904 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1422 | +| iterations | 7023 | +| time_elapsed | 10112 | +| total_timesteps | 14383104 | +| train/ | | +| approx_kl | 0.008422116 | +| clip_fraction | 0.293 | +| clip_range | 0.0714 | +| entropy_loss | -7.05 | +| explained_variance | 0.292 | +| learning_rate | 4.66e-05 | +| loss | -0.026 | +| n_updates | 43908 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000363 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1422 | +| iterations | 7024 | +| time_elapsed | 10114 | +| total_timesteps | 14385152 | +| train/ | | +| approx_kl | 0.011290273 | +| clip_fraction | 0.346 | +| clip_range | 0.0714 | +| entropy_loss | -7.22 | +| explained_variance | -0.2 | +| learning_rate | 4.66e-05 | +| loss | -0.0406 | +| n_updates | 43912 | +| policy_gradient_loss | -0.0229 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1422 | +| iterations | 7025 | +| time_elapsed | 10115 | +| total_timesteps | 14387200 | +| train/ | | +| approx_kl | 0.011436973 | +| clip_fraction | 0.323 | +| clip_range | 0.0714 | +| entropy_loss | -7.03 | +| explained_variance | 0.553 | +| learning_rate | 4.66e-05 | +| loss | -0.0331 | +| n_updates | 43916 | +| policy_gradient_loss | -0.0214 | +| value_loss | 8.3e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1422 | +| iterations | 7026 | +| time_elapsed | 10116 | +| total_timesteps | 14389248 | +| train/ | | +| approx_kl | 0.011488833 | +| clip_fraction | 0.333 | +| clip_range | 0.0714 | +| entropy_loss | -6.69 | +| explained_variance | 0.52 | +| learning_rate | 4.66e-05 | +| loss | -0.0319 | +| n_updates | 43920 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000188 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1422 | +| iterations | 7027 | +| time_elapsed | 10118 | +| total_timesteps | 14391296 | +| train/ | | +| approx_kl | 0.010975953 | +| clip_fraction | 0.343 | +| clip_range | 0.0714 | +| entropy_loss | -7.17 | +| explained_variance | -0.0266 | +| learning_rate | 4.66e-05 | +| loss | -0.0298 | +| n_updates | 43924 | +| policy_gradient_loss | -0.0217 | +| value_loss | 9.3e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1422 | +| iterations | 7028 | +| time_elapsed | 10119 | +| total_timesteps | 14393344 | +| train/ | | +| approx_kl | 0.010224433 | +| clip_fraction | 0.338 | +| clip_range | 0.0714 | +| entropy_loss | -6.93 | +| explained_variance | 0.516 | +| learning_rate | 4.66e-05 | +| loss | -0.0322 | +| n_updates | 43928 | +| policy_gradient_loss | -0.0208 | +| value_loss | 9.59e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1422 | +| iterations | 7029 | +| time_elapsed | 10121 | +| total_timesteps | 14395392 | +| train/ | | +| approx_kl | 0.011478579 | +| clip_fraction | 0.315 | +| clip_range | 0.0714 | +| entropy_loss | -6.69 | +| explained_variance | 0.586 | +| learning_rate | 4.66e-05 | +| loss | -0.024 | +| n_updates | 43932 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000135 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1422 | +| iterations | 7030 | +| time_elapsed | 10122 | +| total_timesteps | 14397440 | +| train/ | | +| approx_kl | 0.010700803 | +| clip_fraction | 0.34 | +| clip_range | 0.0714 | +| entropy_loss | -7.27 | +| explained_variance | -0.0724 | +| learning_rate | 4.66e-05 | +| loss | -0.0294 | +| n_updates | 43936 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.00011 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1422 | +| iterations | 7031 | +| time_elapsed | 10124 | +| total_timesteps | 14399488 | +| train/ | | +| approx_kl | 0.0068310774 | +| clip_fraction | 0.259 | +| clip_range | 0.0714 | +| entropy_loss | -7.15 | +| explained_variance | 0.374 | +| learning_rate | 4.66e-05 | +| loss | -0.0245 | +| n_updates | 43940 | +| policy_gradient_loss | -0.014 | +| value_loss | 0.000235 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1422 | +| iterations | 7032 | +| time_elapsed | 10125 | +| total_timesteps | 14401536 | +| train/ | | +| approx_kl | 0.008266887 | +| clip_fraction | 0.311 | +| clip_range | 0.0714 | +| entropy_loss | -7.04 | +| explained_variance | 0.389 | +| learning_rate | 4.66e-05 | +| loss | -0.0265 | +| n_updates | 43944 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1422 | +| iterations | 7033 | +| time_elapsed | 10127 | +| total_timesteps | 14403584 | +| train/ | | +| approx_kl | 0.007932698 | +| clip_fraction | 0.303 | +| clip_range | 0.0714 | +| entropy_loss | -7.23 | +| explained_variance | 0.287 | +| learning_rate | 4.66e-05 | +| loss | -0.0371 | +| n_updates | 43948 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000179 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1422 | +| iterations | 7034 | +| time_elapsed | 10128 | +| total_timesteps | 14405632 | +| train/ | | +| approx_kl | 0.0110799465 | +| clip_fraction | 0.31 | +| clip_range | 0.0714 | +| entropy_loss | -7.05 | +| explained_variance | 0.264 | +| learning_rate | 4.66e-05 | +| loss | -0.0308 | +| n_updates | 43952 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000197 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1422 | +| iterations | 7035 | +| time_elapsed | 10129 | +| total_timesteps | 14407680 | +| train/ | | +| approx_kl | 0.012893332 | +| clip_fraction | 0.343 | +| clip_range | 0.0714 | +| entropy_loss | -6.53 | +| explained_variance | 0.827 | +| learning_rate | 4.66e-05 | +| loss | -0.0401 | +| n_updates | 43956 | +| policy_gradient_loss | -0.0212 | +| value_loss | 6.2e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1422 | +| iterations | 7036 | +| time_elapsed | 10131 | +| total_timesteps | 14409728 | +| train/ | | +| approx_kl | 0.011771566 | +| clip_fraction | 0.333 | +| clip_range | 0.0714 | +| entropy_loss | -6.6 | +| explained_variance | 0.7 | +| learning_rate | 4.66e-05 | +| loss | -0.034 | +| n_updates | 43960 | +| policy_gradient_loss | -0.0186 | +| value_loss | 9.46e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1422 | +| iterations | 7037 | +| time_elapsed | 10132 | +| total_timesteps | 14411776 | +| train/ | | +| approx_kl | 0.011311328 | +| clip_fraction | 0.33 | +| clip_range | 0.0714 | +| entropy_loss | -7.29 | +| explained_variance | -0.155 | +| learning_rate | 4.66e-05 | +| loss | -0.0328 | +| n_updates | 43964 | +| policy_gradient_loss | -0.0202 | +| value_loss | 9.42e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1422 | +| iterations | 7038 | +| time_elapsed | 10134 | +| total_timesteps | 14413824 | +| train/ | | +| approx_kl | 0.013443571 | +| clip_fraction | 0.335 | +| clip_range | 0.0714 | +| entropy_loss | -7.35 | +| explained_variance | -0.2 | +| learning_rate | 4.66e-05 | +| loss | -0.0322 | +| n_updates | 43968 | +| policy_gradient_loss | -0.0199 | +| value_loss | 7.08e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1422 | +| iterations | 7039 | +| time_elapsed | 10135 | +| total_timesteps | 14415872 | +| train/ | | +| approx_kl | 0.009348981 | +| clip_fraction | 0.291 | +| clip_range | 0.0714 | +| entropy_loss | -7.33 | +| explained_variance | -0.0894 | +| learning_rate | 4.66e-05 | +| loss | -0.0302 | +| n_updates | 43972 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000132 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1422 | +| iterations | 7040 | +| time_elapsed | 10137 | +| total_timesteps | 14417920 | +| train/ | | +| approx_kl | 0.011339218 | +| clip_fraction | 0.305 | +| clip_range | 0.0714 | +| entropy_loss | -6.94 | +| explained_variance | 0.428 | +| learning_rate | 4.66e-05 | +| loss | -0.0259 | +| n_updates | 43976 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000156 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1422 | +| iterations | 7041 | +| time_elapsed | 10138 | +| total_timesteps | 14419968 | +| train/ | | +| approx_kl | 0.01276532 | +| clip_fraction | 0.307 | +| clip_range | 0.0714 | +| entropy_loss | -6.81 | +| explained_variance | 0.51 | +| learning_rate | 4.66e-05 | +| loss | -0.0268 | +| n_updates | 43980 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000148 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1422 | +| iterations | 7042 | +| time_elapsed | 10140 | +| total_timesteps | 14422016 | +| train/ | | +| approx_kl | 0.011266741 | +| clip_fraction | 0.322 | +| clip_range | 0.0714 | +| entropy_loss | -7.03 | +| explained_variance | 0.343 | +| learning_rate | 4.66e-05 | +| loss | -0.029 | +| n_updates | 43984 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000134 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1422 | +| iterations | 7043 | +| time_elapsed | 10141 | +| total_timesteps | 14424064 | +| train/ | | +| approx_kl | 0.010496064 | +| clip_fraction | 0.298 | +| clip_range | 0.0714 | +| entropy_loss | -6.67 | +| explained_variance | 0.454 | +| learning_rate | 4.66e-05 | +| loss | -0.0292 | +| n_updates | 43988 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000268 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1422 | +| iterations | 7044 | +| time_elapsed | 10142 | +| total_timesteps | 14426112 | +| train/ | | +| approx_kl | 0.012701886 | +| clip_fraction | 0.357 | +| clip_range | 0.0714 | +| entropy_loss | -7.01 | +| explained_variance | 0.43 | +| learning_rate | 4.66e-05 | +| loss | -0.0307 | +| n_updates | 43992 | +| policy_gradient_loss | -0.0236 | +| value_loss | 9.89e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1422 | +| iterations | 7045 | +| time_elapsed | 10144 | +| total_timesteps | 14428160 | +| train/ | | +| approx_kl | 0.011850305 | +| clip_fraction | 0.324 | +| clip_range | 0.0714 | +| entropy_loss | -7.3 | +| explained_variance | 0.0216 | +| learning_rate | 4.66e-05 | +| loss | -0.0359 | +| n_updates | 43996 | +| policy_gradient_loss | -0.0209 | +| value_loss | 9.09e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1422 | +| iterations | 7046 | +| time_elapsed | 10145 | +| total_timesteps | 14430208 | +| train/ | | +| approx_kl | 0.010290185 | +| clip_fraction | 0.297 | +| clip_range | 0.0714 | +| entropy_loss | -6.97 | +| explained_variance | 0.426 | +| learning_rate | 4.66e-05 | +| loss | -0.0312 | +| n_updates | 44000 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000185 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1422 | +| iterations | 7047 | +| time_elapsed | 10147 | +| total_timesteps | 14432256 | +| train/ | | +| approx_kl | 0.012971052 | +| clip_fraction | 0.318 | +| clip_range | 0.0714 | +| entropy_loss | -6.68 | +| explained_variance | 0.621 | +| learning_rate | 4.66e-05 | +| loss | -0.028 | +| n_updates | 44004 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000151 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1422 | +| iterations | 7048 | +| time_elapsed | 10148 | +| total_timesteps | 14434304 | +| train/ | | +| approx_kl | 0.010467699 | +| clip_fraction | 0.299 | +| clip_range | 0.0714 | +| entropy_loss | -6.86 | +| explained_variance | 0.433 | +| learning_rate | 4.66e-05 | +| loss | -0.0278 | +| n_updates | 44008 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000203 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1422 | +| iterations | 7049 | +| time_elapsed | 10150 | +| total_timesteps | 14436352 | +| train/ | | +| approx_kl | 0.010567421 | +| clip_fraction | 0.316 | +| clip_range | 0.0714 | +| entropy_loss | -6.93 | +| explained_variance | 0.3 | +| learning_rate | 4.66e-05 | +| loss | -0.0342 | +| n_updates | 44012 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000313 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1422 | +| iterations | 7050 | +| time_elapsed | 10151 | +| total_timesteps | 14438400 | +| train/ | | +| approx_kl | 0.011077499 | +| clip_fraction | 0.34 | +| clip_range | 0.0714 | +| entropy_loss | -6.68 | +| explained_variance | 0.558 | +| learning_rate | 4.66e-05 | +| loss | -0.0366 | +| n_updates | 44016 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000109 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1422 | +| iterations | 7051 | +| time_elapsed | 10153 | +| total_timesteps | 14440448 | +| train/ | | +| approx_kl | 0.010114878 | +| clip_fraction | 0.327 | +| clip_range | 0.0714 | +| entropy_loss | -6.86 | +| explained_variance | 0.239 | +| learning_rate | 4.66e-05 | +| loss | -0.0333 | +| n_updates | 44020 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000279 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1422 | +| iterations | 7052 | +| time_elapsed | 10154 | +| total_timesteps | 14442496 | +| train/ | | +| approx_kl | 0.014669442 | +| clip_fraction | 0.356 | +| clip_range | 0.0714 | +| entropy_loss | -7.13 | +| explained_variance | -0.142 | +| learning_rate | 4.66e-05 | +| loss | -0.0315 | +| n_updates | 44024 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.00018 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1422 | +| iterations | 7053 | +| time_elapsed | 10155 | +| total_timesteps | 14444544 | +| train/ | | +| approx_kl | 0.010923094 | +| clip_fraction | 0.351 | +| clip_range | 0.0714 | +| entropy_loss | -7.27 | +| explained_variance | -0.183 | +| learning_rate | 4.66e-05 | +| loss | -0.0329 | +| n_updates | 44028 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.00011 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1422 | +| iterations | 7054 | +| time_elapsed | 10157 | +| total_timesteps | 14446592 | +| train/ | | +| approx_kl | 0.011377738 | +| clip_fraction | 0.332 | +| clip_range | 0.0714 | +| entropy_loss | -6.88 | +| explained_variance | 0.439 | +| learning_rate | 4.66e-05 | +| loss | -0.033 | +| n_updates | 44032 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000182 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1422 | +| iterations | 7055 | +| time_elapsed | 10158 | +| total_timesteps | 14448640 | +| train/ | | +| approx_kl | 0.01196043 | +| clip_fraction | 0.307 | +| clip_range | 0.0714 | +| entropy_loss | -7.08 | +| explained_variance | 0.19 | +| learning_rate | 4.66e-05 | +| loss | -0.0263 | +| n_updates | 44036 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.00021 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1422 | +| iterations | 7056 | +| time_elapsed | 10160 | +| total_timesteps | 14450688 | +| train/ | | +| approx_kl | 0.011546446 | +| clip_fraction | 0.335 | +| clip_range | 0.0714 | +| entropy_loss | -7.06 | +| explained_variance | 0.177 | +| learning_rate | 4.66e-05 | +| loss | -0.0315 | +| n_updates | 44040 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000238 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1422 | +| iterations | 7057 | +| time_elapsed | 10161 | +| total_timesteps | 14452736 | +| train/ | | +| approx_kl | 0.010477106 | +| clip_fraction | 0.317 | +| clip_range | 0.0714 | +| entropy_loss | -7.17 | +| explained_variance | 0.0174 | +| learning_rate | 4.66e-05 | +| loss | -0.0275 | +| n_updates | 44044 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000214 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1422 | +| iterations | 7058 | +| time_elapsed | 10163 | +| total_timesteps | 14454784 | +| train/ | | +| approx_kl | 0.010585589 | +| clip_fraction | 0.315 | +| clip_range | 0.0714 | +| entropy_loss | -6.56 | +| explained_variance | 0.543 | +| learning_rate | 4.66e-05 | +| loss | -0.0285 | +| n_updates | 44048 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000172 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1422 | +| iterations | 7059 | +| time_elapsed | 10164 | +| total_timesteps | 14456832 | +| train/ | | +| approx_kl | 0.011235488 | +| clip_fraction | 0.351 | +| clip_range | 0.0714 | +| entropy_loss | -6.88 | +| explained_variance | 0.692 | +| learning_rate | 4.66e-05 | +| loss | -0.0374 | +| n_updates | 44052 | +| policy_gradient_loss | -0.0236 | +| value_loss | 6.29e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1422 | +| iterations | 7060 | +| time_elapsed | 10166 | +| total_timesteps | 14458880 | +| train/ | | +| approx_kl | 0.011024579 | +| clip_fraction | 0.297 | +| clip_range | 0.0714 | +| entropy_loss | -7.04 | +| explained_variance | 0.36 | +| learning_rate | 4.66e-05 | +| loss | -0.0254 | +| n_updates | 44056 | +| policy_gradient_loss | -0.0142 | +| value_loss | 0.000211 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1422 | +| iterations | 7061 | +| time_elapsed | 10167 | +| total_timesteps | 14460928 | +| train/ | | +| approx_kl | 0.010749593 | +| clip_fraction | 0.311 | +| clip_range | 0.0714 | +| entropy_loss | -6.59 | +| explained_variance | 0.446 | +| learning_rate | 4.66e-05 | +| loss | -0.03 | +| n_updates | 44060 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000284 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1422 | +| iterations | 7062 | +| time_elapsed | 10169 | +| total_timesteps | 14462976 | +| train/ | | +| approx_kl | 0.011831868 | +| clip_fraction | 0.362 | +| clip_range | 0.0714 | +| entropy_loss | -6.93 | +| explained_variance | 0.322 | +| learning_rate | 4.66e-05 | +| loss | -0.0338 | +| n_updates | 44064 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000144 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1422 | +| iterations | 7063 | +| time_elapsed | 10170 | +| total_timesteps | 14465024 | +| train/ | | +| approx_kl | 0.010341499 | +| clip_fraction | 0.321 | +| clip_range | 0.0714 | +| entropy_loss | -6.9 | +| explained_variance | 0.465 | +| learning_rate | 4.66e-05 | +| loss | -0.0372 | +| n_updates | 44068 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000152 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1422 | +| iterations | 7064 | +| time_elapsed | 10172 | +| total_timesteps | 14467072 | +| train/ | | +| approx_kl | 0.010666432 | +| clip_fraction | 0.316 | +| clip_range | 0.0714 | +| entropy_loss | -7.02 | +| explained_variance | 0.49 | +| learning_rate | 4.66e-05 | +| loss | -0.0262 | +| n_updates | 44072 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000111 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1422 | +| iterations | 7065 | +| time_elapsed | 10173 | +| total_timesteps | 14469120 | +| train/ | | +| approx_kl | 0.010121673 | +| clip_fraction | 0.34 | +| clip_range | 0.0714 | +| entropy_loss | -7.14 | +| explained_variance | 0.266 | +| learning_rate | 4.66e-05 | +| loss | -0.0325 | +| n_updates | 44076 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000196 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1422 | +| iterations | 7066 | +| time_elapsed | 10174 | +| total_timesteps | 14471168 | +| train/ | | +| approx_kl | 0.009785372 | +| clip_fraction | 0.283 | +| clip_range | 0.0714 | +| entropy_loss | -7 | +| explained_variance | 0.256 | +| learning_rate | 4.66e-05 | +| loss | -0.0281 | +| n_updates | 44080 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000345 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1422 | +| iterations | 7067 | +| time_elapsed | 10176 | +| total_timesteps | 14473216 | +| train/ | | +| approx_kl | 0.010215823 | +| clip_fraction | 0.322 | +| clip_range | 0.0714 | +| entropy_loss | -7.09 | +| explained_variance | 0.307 | +| learning_rate | 4.66e-05 | +| loss | -0.0284 | +| n_updates | 44084 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000167 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1422 | +| iterations | 7068 | +| time_elapsed | 10177 | +| total_timesteps | 14475264 | +| train/ | | +| approx_kl | 0.011821144 | +| clip_fraction | 0.315 | +| clip_range | 0.0714 | +| entropy_loss | -6.8 | +| explained_variance | 0.488 | +| learning_rate | 4.66e-05 | +| loss | -0.0312 | +| n_updates | 44088 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000228 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1422 | +| iterations | 7069 | +| time_elapsed | 10179 | +| total_timesteps | 14477312 | +| train/ | | +| approx_kl | 0.009554279 | +| clip_fraction | 0.301 | +| clip_range | 0.0714 | +| entropy_loss | -7.06 | +| explained_variance | 0.222 | +| learning_rate | 4.66e-05 | +| loss | -0.0244 | +| n_updates | 44092 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.00026 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1422 | +| iterations | 7070 | +| time_elapsed | 10180 | +| total_timesteps | 14479360 | +| train/ | | +| approx_kl | 0.010222534 | +| clip_fraction | 0.323 | +| clip_range | 0.0714 | +| entropy_loss | -7.13 | +| explained_variance | 0.296 | +| learning_rate | 4.66e-05 | +| loss | -0.0389 | +| n_updates | 44096 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000142 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1422 | +| iterations | 7071 | +| time_elapsed | 10182 | +| total_timesteps | 14481408 | +| train/ | | +| approx_kl | 0.0099968705 | +| clip_fraction | 0.298 | +| clip_range | 0.0714 | +| entropy_loss | -7.01 | +| explained_variance | 0.413 | +| learning_rate | 4.66e-05 | +| loss | -0.0262 | +| n_updates | 44100 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000154 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1422 | +| iterations | 7072 | +| time_elapsed | 10183 | +| total_timesteps | 14483456 | +| train/ | | +| approx_kl | 0.008789151 | +| clip_fraction | 0.304 | +| clip_range | 0.0714 | +| entropy_loss | -6.58 | +| explained_variance | 0.615 | +| learning_rate | 4.66e-05 | +| loss | -0.0337 | +| n_updates | 44104 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1422 | +| iterations | 7073 | +| time_elapsed | 10184 | +| total_timesteps | 14485504 | +| train/ | | +| approx_kl | 0.009467665 | +| clip_fraction | 0.321 | +| clip_range | 0.0714 | +| entropy_loss | -7.01 | +| explained_variance | 0.456 | +| learning_rate | 4.66e-05 | +| loss | -0.0312 | +| n_updates | 44108 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000198 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1422 | +| iterations | 7074 | +| time_elapsed | 10186 | +| total_timesteps | 14487552 | +| train/ | | +| approx_kl | 0.00954243 | +| clip_fraction | 0.327 | +| clip_range | 0.0714 | +| entropy_loss | -6.94 | +| explained_variance | 0.378 | +| learning_rate | 4.66e-05 | +| loss | -0.0321 | +| n_updates | 44112 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.00027 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1422 | +| iterations | 7075 | +| time_elapsed | 10187 | +| total_timesteps | 14489600 | +| train/ | | +| approx_kl | 0.009804991 | +| clip_fraction | 0.32 | +| clip_range | 0.0714 | +| entropy_loss | -7.07 | +| explained_variance | 0.297 | +| learning_rate | 4.66e-05 | +| loss | -0.0334 | +| n_updates | 44116 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000207 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1422 | +| iterations | 7076 | +| time_elapsed | 10189 | +| total_timesteps | 14491648 | +| train/ | | +| approx_kl | 0.011240467 | +| clip_fraction | 0.317 | +| clip_range | 0.0714 | +| entropy_loss | -6.8 | +| explained_variance | 0.384 | +| learning_rate | 4.66e-05 | +| loss | -0.0414 | +| n_updates | 44120 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000159 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1422 | +| iterations | 7077 | +| time_elapsed | 10190 | +| total_timesteps | 14493696 | +| train/ | | +| approx_kl | 0.01122877 | +| clip_fraction | 0.313 | +| clip_range | 0.0714 | +| entropy_loss | -6.97 | +| explained_variance | 0.322 | +| learning_rate | 4.66e-05 | +| loss | -0.039 | +| n_updates | 44124 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000148 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1422 | +| iterations | 7078 | +| time_elapsed | 10192 | +| total_timesteps | 14495744 | +| train/ | | +| approx_kl | 0.010780184 | +| clip_fraction | 0.317 | +| clip_range | 0.0714 | +| entropy_loss | -6.7 | +| explained_variance | 0.807 | +| learning_rate | 4.66e-05 | +| loss | -0.0367 | +| n_updates | 44128 | +| policy_gradient_loss | -0.0217 | +| value_loss | 6.05e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1422 | +| iterations | 7079 | +| time_elapsed | 10193 | +| total_timesteps | 14497792 | +| train/ | | +| approx_kl | 0.011711661 | +| clip_fraction | 0.297 | +| clip_range | 0.0714 | +| entropy_loss | -7.15 | +| explained_variance | 0.185 | +| learning_rate | 4.66e-05 | +| loss | -0.0312 | +| n_updates | 44132 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000229 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1422 | +| iterations | 7080 | +| time_elapsed | 10194 | +| total_timesteps | 14499840 | +| train/ | | +| approx_kl | 0.009590039 | +| clip_fraction | 0.303 | +| clip_range | 0.0714 | +| entropy_loss | -7.07 | +| explained_variance | 0.44 | +| learning_rate | 4.66e-05 | +| loss | -0.0286 | +| n_updates | 44136 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000207 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1422 | +| iterations | 7081 | +| time_elapsed | 10196 | +| total_timesteps | 14501888 | +| train/ | | +| approx_kl | 0.011288535 | +| clip_fraction | 0.339 | +| clip_range | 0.0714 | +| entropy_loss | -7.33 | +| explained_variance | -0.332 | +| learning_rate | 4.66e-05 | +| loss | -0.0379 | +| n_updates | 44140 | +| policy_gradient_loss | -0.0222 | +| value_loss | 0.000157 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1422 | +| iterations | 7082 | +| time_elapsed | 10197 | +| total_timesteps | 14503936 | +| train/ | | +| approx_kl | 0.013420072 | +| clip_fraction | 0.337 | +| clip_range | 0.0714 | +| entropy_loss | -6.97 | +| explained_variance | 0.531 | +| learning_rate | 4.66e-05 | +| loss | -0.0458 | +| n_updates | 44144 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000123 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1422 | +| iterations | 7083 | +| time_elapsed | 10199 | +| total_timesteps | 14505984 | +| train/ | | +| approx_kl | 0.011375289 | +| clip_fraction | 0.351 | +| clip_range | 0.0714 | +| entropy_loss | -7.13 | +| explained_variance | 0.309 | +| learning_rate | 4.66e-05 | +| loss | -0.0308 | +| n_updates | 44148 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1422 | +| iterations | 7084 | +| time_elapsed | 10200 | +| total_timesteps | 14508032 | +| train/ | | +| approx_kl | 0.011614955 | +| clip_fraction | 0.326 | +| clip_range | 0.0714 | +| entropy_loss | -7.2 | +| explained_variance | 0.27 | +| learning_rate | 4.66e-05 | +| loss | -0.0309 | +| n_updates | 44152 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000154 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1422 | +| iterations | 7085 | +| time_elapsed | 10202 | +| total_timesteps | 14510080 | +| train/ | | +| approx_kl | 0.010920164 | +| clip_fraction | 0.293 | +| clip_range | 0.0714 | +| entropy_loss | -7 | +| explained_variance | 0.21 | +| learning_rate | 4.66e-05 | +| loss | -0.0283 | +| n_updates | 44156 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000261 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1422 | +| iterations | 7086 | +| time_elapsed | 10203 | +| total_timesteps | 14512128 | +| train/ | | +| approx_kl | 0.009459374 | +| clip_fraction | 0.298 | +| clip_range | 0.0714 | +| entropy_loss | -6.77 | +| explained_variance | 0.366 | +| learning_rate | 4.66e-05 | +| loss | -0.028 | +| n_updates | 44160 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000322 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1422 | +| iterations | 7087 | +| time_elapsed | 10205 | +| total_timesteps | 14514176 | +| train/ | | +| approx_kl | 0.010647014 | +| clip_fraction | 0.332 | +| clip_range | 0.0714 | +| entropy_loss | -6.6 | +| explained_variance | 0.487 | +| learning_rate | 4.66e-05 | +| loss | -0.031 | +| n_updates | 44164 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000207 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1422 | +| iterations | 7088 | +| time_elapsed | 10206 | +| total_timesteps | 14516224 | +| train/ | | +| approx_kl | 0.009786939 | +| clip_fraction | 0.309 | +| clip_range | 0.0714 | +| entropy_loss | -6.4 | +| explained_variance | 0.473 | +| learning_rate | 4.66e-05 | +| loss | -0.036 | +| n_updates | 44168 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.00034 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1422 | +| iterations | 7089 | +| time_elapsed | 10207 | +| total_timesteps | 14518272 | +| train/ | | +| approx_kl | 0.009701945 | +| clip_fraction | 0.338 | +| clip_range | 0.0714 | +| entropy_loss | -6.92 | +| explained_variance | 0.424 | +| learning_rate | 4.66e-05 | +| loss | -0.0287 | +| n_updates | 44172 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000141 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1422 | +| iterations | 7090 | +| time_elapsed | 10209 | +| total_timesteps | 14520320 | +| train/ | | +| approx_kl | 0.010183884 | +| clip_fraction | 0.343 | +| clip_range | 0.0714 | +| entropy_loss | -7.16 | +| explained_variance | 0.141 | +| learning_rate | 4.66e-05 | +| loss | -0.036 | +| n_updates | 44176 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000194 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1422 | +| iterations | 7091 | +| time_elapsed | 10210 | +| total_timesteps | 14522368 | +| train/ | | +| approx_kl | 0.013900427 | +| clip_fraction | 0.36 | +| clip_range | 0.0714 | +| entropy_loss | -7.17 | +| explained_variance | 0.0827 | +| learning_rate | 4.66e-05 | +| loss | -0.0367 | +| n_updates | 44180 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000115 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1422 | +| iterations | 7092 | +| time_elapsed | 10212 | +| total_timesteps | 14524416 | +| train/ | | +| approx_kl | 0.015559641 | +| clip_fraction | 0.388 | +| clip_range | 0.0714 | +| entropy_loss | -6.9 | +| explained_variance | 0.628 | +| learning_rate | 4.66e-05 | +| loss | -0.0404 | +| n_updates | 44184 | +| policy_gradient_loss | -0.0249 | +| value_loss | 7.51e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1422 | +| iterations | 7093 | +| time_elapsed | 10213 | +| total_timesteps | 14526464 | +| train/ | | +| approx_kl | 0.0122240465 | +| clip_fraction | 0.336 | +| clip_range | 0.0714 | +| entropy_loss | -7.14 | +| explained_variance | 0.0759 | +| learning_rate | 4.66e-05 | +| loss | -0.0294 | +| n_updates | 44188 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000139 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1422 | +| iterations | 7094 | +| time_elapsed | 10215 | +| total_timesteps | 14528512 | +| train/ | | +| approx_kl | 0.010662384 | +| clip_fraction | 0.349 | +| clip_range | 0.0714 | +| entropy_loss | -7.08 | +| explained_variance | 0.195 | +| learning_rate | 4.65e-05 | +| loss | -0.0297 | +| n_updates | 44192 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000192 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1422 | +| iterations | 7095 | +| time_elapsed | 10216 | +| total_timesteps | 14530560 | +| train/ | | +| approx_kl | 0.011400146 | +| clip_fraction | 0.318 | +| clip_range | 0.0714 | +| entropy_loss | -6.84 | +| explained_variance | 0.359 | +| learning_rate | 4.65e-05 | +| loss | -0.0249 | +| n_updates | 44196 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000216 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1422 | +| iterations | 7096 | +| time_elapsed | 10217 | +| total_timesteps | 14532608 | +| train/ | | +| approx_kl | 0.012290922 | +| clip_fraction | 0.351 | +| clip_range | 0.0714 | +| entropy_loss | -7.02 | +| explained_variance | 0.373 | +| learning_rate | 4.65e-05 | +| loss | -0.0364 | +| n_updates | 44200 | +| policy_gradient_loss | -0.0226 | +| value_loss | 0.000133 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1422 | +| iterations | 7097 | +| time_elapsed | 10219 | +| total_timesteps | 14534656 | +| train/ | | +| approx_kl | 0.012834295 | +| clip_fraction | 0.339 | +| clip_range | 0.0714 | +| entropy_loss | -7.13 | +| explained_variance | 0.00419 | +| learning_rate | 4.65e-05 | +| loss | -0.0363 | +| n_updates | 44204 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000142 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1422 | +| iterations | 7098 | +| time_elapsed | 10220 | +| total_timesteps | 14536704 | +| train/ | | +| approx_kl | 0.010082016 | +| clip_fraction | 0.32 | +| clip_range | 0.0714 | +| entropy_loss | -7.07 | +| explained_variance | 0.529 | +| learning_rate | 4.65e-05 | +| loss | -0.0341 | +| n_updates | 44208 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000106 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1422 | +| iterations | 7099 | +| time_elapsed | 10222 | +| total_timesteps | 14538752 | +| train/ | | +| approx_kl | 0.008747065 | +| clip_fraction | 0.296 | +| clip_range | 0.0714 | +| entropy_loss | -6.53 | +| explained_variance | 0.519 | +| learning_rate | 4.65e-05 | +| loss | -0.0229 | +| n_updates | 44212 | +| policy_gradient_loss | -0.0141 | +| value_loss | 0.000272 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1422 | +| iterations | 7100 | +| time_elapsed | 10223 | +| total_timesteps | 14540800 | +| train/ | | +| approx_kl | 0.008518943 | +| clip_fraction | 0.298 | +| clip_range | 0.0714 | +| entropy_loss | -6.28 | +| explained_variance | 0.585 | +| learning_rate | 4.65e-05 | +| loss | -0.0255 | +| n_updates | 44216 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000215 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1422 | +| iterations | 7101 | +| time_elapsed | 10225 | +| total_timesteps | 14542848 | +| train/ | | +| approx_kl | 0.011261929 | +| clip_fraction | 0.338 | +| clip_range | 0.0714 | +| entropy_loss | -7.06 | +| explained_variance | 0.243 | +| learning_rate | 4.65e-05 | +| loss | -0.0289 | +| n_updates | 44220 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000179 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1422 | +| iterations | 7102 | +| time_elapsed | 10226 | +| total_timesteps | 14544896 | +| train/ | | +| approx_kl | 0.010003751 | +| clip_fraction | 0.313 | +| clip_range | 0.0714 | +| entropy_loss | -7.2 | +| explained_variance | -0.0163 | +| learning_rate | 4.65e-05 | +| loss | -0.0331 | +| n_updates | 44224 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000207 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1422 | +| iterations | 7103 | +| time_elapsed | 10228 | +| total_timesteps | 14546944 | +| train/ | | +| approx_kl | 0.008521631 | +| clip_fraction | 0.29 | +| clip_range | 0.0714 | +| entropy_loss | -7.25 | +| explained_variance | 0.188 | +| learning_rate | 4.65e-05 | +| loss | -0.0319 | +| n_updates | 44228 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000167 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1422 | +| iterations | 7104 | +| time_elapsed | 10229 | +| total_timesteps | 14548992 | +| train/ | | +| approx_kl | 0.011243224 | +| clip_fraction | 0.311 | +| clip_range | 0.0714 | +| entropy_loss | -6.92 | +| explained_variance | 0.455 | +| learning_rate | 4.65e-05 | +| loss | -0.0299 | +| n_updates | 44232 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1422 | +| iterations | 7105 | +| time_elapsed | 10230 | +| total_timesteps | 14551040 | +| train/ | | +| approx_kl | 0.011691954 | +| clip_fraction | 0.331 | +| clip_range | 0.0714 | +| entropy_loss | -7.31 | +| explained_variance | -0.128 | +| learning_rate | 4.65e-05 | +| loss | -0.0259 | +| n_updates | 44236 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000121 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1422 | +| iterations | 7106 | +| time_elapsed | 10232 | +| total_timesteps | 14553088 | +| train/ | | +| approx_kl | 0.010041254 | +| clip_fraction | 0.308 | +| clip_range | 0.0714 | +| entropy_loss | -7.21 | +| explained_variance | 0.328 | +| learning_rate | 4.65e-05 | +| loss | -0.0265 | +| n_updates | 44240 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000187 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1422 | +| iterations | 7107 | +| time_elapsed | 10233 | +| total_timesteps | 14555136 | +| train/ | | +| approx_kl | 0.011994339 | +| clip_fraction | 0.295 | +| clip_range | 0.0714 | +| entropy_loss | -6.91 | +| explained_variance | 0.216 | +| learning_rate | 4.65e-05 | +| loss | -0.0261 | +| n_updates | 44244 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000271 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1422 | +| iterations | 7108 | +| time_elapsed | 10235 | +| total_timesteps | 14557184 | +| train/ | | +| approx_kl | 0.010492916 | +| clip_fraction | 0.321 | +| clip_range | 0.0714 | +| entropy_loss | -6.67 | +| explained_variance | 0.56 | +| learning_rate | 4.65e-05 | +| loss | -0.0233 | +| n_updates | 44248 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.00018 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1422 | +| iterations | 7109 | +| time_elapsed | 10236 | +| total_timesteps | 14559232 | +| train/ | | +| approx_kl | 0.009959705 | +| clip_fraction | 0.315 | +| clip_range | 0.0714 | +| entropy_loss | -6.87 | +| explained_variance | 0.255 | +| learning_rate | 4.65e-05 | +| loss | -0.0294 | +| n_updates | 44252 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000245 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1422 | +| iterations | 7110 | +| time_elapsed | 10238 | +| total_timesteps | 14561280 | +| train/ | | +| approx_kl | 0.010998683 | +| clip_fraction | 0.337 | +| clip_range | 0.0714 | +| entropy_loss | -7 | +| explained_variance | 0.452 | +| learning_rate | 4.65e-05 | +| loss | -0.0345 | +| n_updates | 44256 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.00014 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1422 | +| iterations | 7111 | +| time_elapsed | 10239 | +| total_timesteps | 14563328 | +| train/ | | +| approx_kl | 0.008958206 | +| clip_fraction | 0.325 | +| clip_range | 0.0714 | +| entropy_loss | -6.94 | +| explained_variance | 0.468 | +| learning_rate | 4.65e-05 | +| loss | -0.0323 | +| n_updates | 44260 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000154 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1422 | +| iterations | 7112 | +| time_elapsed | 10240 | +| total_timesteps | 14565376 | +| train/ | | +| approx_kl | 0.010654092 | +| clip_fraction | 0.336 | +| clip_range | 0.0714 | +| entropy_loss | -7.31 | +| explained_variance | -0.334 | +| learning_rate | 4.65e-05 | +| loss | -0.0371 | +| n_updates | 44264 | +| policy_gradient_loss | -0.0221 | +| value_loss | 6.38e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1422 | +| iterations | 7113 | +| time_elapsed | 10242 | +| total_timesteps | 14567424 | +| train/ | | +| approx_kl | 0.01100512 | +| clip_fraction | 0.317 | +| clip_range | 0.0714 | +| entropy_loss | -6.73 | +| explained_variance | 0.6 | +| learning_rate | 4.65e-05 | +| loss | -0.0319 | +| n_updates | 44268 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000125 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1422 | +| iterations | 7114 | +| time_elapsed | 10243 | +| total_timesteps | 14569472 | +| train/ | | +| approx_kl | 0.008395633 | +| clip_fraction | 0.295 | +| clip_range | 0.0714 | +| entropy_loss | -7.21 | +| explained_variance | 0.15 | +| learning_rate | 4.65e-05 | +| loss | -0.0273 | +| n_updates | 44272 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.00032 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1422 | +| iterations | 7115 | +| time_elapsed | 10245 | +| total_timesteps | 14571520 | +| train/ | | +| approx_kl | 0.009977537 | +| clip_fraction | 0.324 | +| clip_range | 0.0714 | +| entropy_loss | -7.28 | +| explained_variance | -0.0198 | +| learning_rate | 4.65e-05 | +| loss | -0.0335 | +| n_updates | 44276 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000147 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1422 | +| iterations | 7116 | +| time_elapsed | 10246 | +| total_timesteps | 14573568 | +| train/ | | +| approx_kl | 0.009849767 | +| clip_fraction | 0.31 | +| clip_range | 0.0714 | +| entropy_loss | -6.81 | +| explained_variance | 0.445 | +| learning_rate | 4.65e-05 | +| loss | -0.0319 | +| n_updates | 44280 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000184 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1422 | +| iterations | 7117 | +| time_elapsed | 10248 | +| total_timesteps | 14575616 | +| train/ | | +| approx_kl | 0.010420057 | +| clip_fraction | 0.325 | +| clip_range | 0.0714 | +| entropy_loss | -6.3 | +| explained_variance | 0.643 | +| learning_rate | 4.65e-05 | +| loss | -0.0311 | +| n_updates | 44284 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000156 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1422 | +| iterations | 7118 | +| time_elapsed | 10249 | +| total_timesteps | 14577664 | +| train/ | | +| approx_kl | 0.010427149 | +| clip_fraction | 0.328 | +| clip_range | 0.0714 | +| entropy_loss | -6.87 | +| explained_variance | 0.537 | +| learning_rate | 4.65e-05 | +| loss | -0.0264 | +| n_updates | 44288 | +| policy_gradient_loss | -0.0199 | +| value_loss | 9.63e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1422 | +| iterations | 7119 | +| time_elapsed | 10250 | +| total_timesteps | 14579712 | +| train/ | | +| approx_kl | 0.010513304 | +| clip_fraction | 0.321 | +| clip_range | 0.0714 | +| entropy_loss | -7.16 | +| explained_variance | 0.376 | +| learning_rate | 4.65e-05 | +| loss | -0.0281 | +| n_updates | 44292 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000131 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1422 | +| iterations | 7120 | +| time_elapsed | 10252 | +| total_timesteps | 14581760 | +| train/ | | +| approx_kl | 0.010142721 | +| clip_fraction | 0.308 | +| clip_range | 0.0714 | +| entropy_loss | -7.23 | +| explained_variance | 0.0795 | +| learning_rate | 4.65e-05 | +| loss | -0.0308 | +| n_updates | 44296 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000163 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1422 | +| iterations | 7121 | +| time_elapsed | 10253 | +| total_timesteps | 14583808 | +| train/ | | +| approx_kl | 0.011038817 | +| clip_fraction | 0.301 | +| clip_range | 0.0714 | +| entropy_loss | -6.84 | +| explained_variance | 0.284 | +| learning_rate | 4.65e-05 | +| loss | -0.0296 | +| n_updates | 44300 | +| policy_gradient_loss | -0.0144 | +| value_loss | 0.000295 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1422 | +| iterations | 7122 | +| time_elapsed | 10255 | +| total_timesteps | 14585856 | +| train/ | | +| approx_kl | 0.01081964 | +| clip_fraction | 0.316 | +| clip_range | 0.0714 | +| entropy_loss | -6.66 | +| explained_variance | 0.517 | +| learning_rate | 4.65e-05 | +| loss | -0.0273 | +| n_updates | 44304 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000183 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1422 | +| iterations | 7123 | +| time_elapsed | 10256 | +| total_timesteps | 14587904 | +| train/ | | +| approx_kl | 0.012248628 | +| clip_fraction | 0.353 | +| clip_range | 0.0714 | +| entropy_loss | -6.95 | +| explained_variance | 0.291 | +| learning_rate | 4.65e-05 | +| loss | -0.0324 | +| n_updates | 44308 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000142 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1422 | +| iterations | 7124 | +| time_elapsed | 10257 | +| total_timesteps | 14589952 | +| train/ | | +| approx_kl | 0.011321805 | +| clip_fraction | 0.312 | +| clip_range | 0.0714 | +| entropy_loss | -7.29 | +| explained_variance | 0.0902 | +| learning_rate | 4.65e-05 | +| loss | -0.0288 | +| n_updates | 44312 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000155 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1422 | +| iterations | 7125 | +| time_elapsed | 10259 | +| total_timesteps | 14592000 | +| train/ | | +| approx_kl | 0.008640797 | +| clip_fraction | 0.283 | +| clip_range | 0.0714 | +| entropy_loss | -6.62 | +| explained_variance | 0.322 | +| learning_rate | 4.65e-05 | +| loss | -0.0262 | +| n_updates | 44316 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000445 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1422 | +| iterations | 7126 | +| time_elapsed | 10260 | +| total_timesteps | 14594048 | +| train/ | | +| approx_kl | 0.009764526 | +| clip_fraction | 0.319 | +| clip_range | 0.0714 | +| entropy_loss | -6.66 | +| explained_variance | 0.361 | +| learning_rate | 4.65e-05 | +| loss | -0.0259 | +| n_updates | 44320 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000206 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1422 | +| iterations | 7127 | +| time_elapsed | 10262 | +| total_timesteps | 14596096 | +| train/ | | +| approx_kl | 0.010629693 | +| clip_fraction | 0.341 | +| clip_range | 0.0714 | +| entropy_loss | -6.91 | +| explained_variance | 0.407 | +| learning_rate | 4.65e-05 | +| loss | -0.0343 | +| n_updates | 44324 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.00018 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1422 | +| iterations | 7128 | +| time_elapsed | 10263 | +| total_timesteps | 14598144 | +| train/ | | +| approx_kl | 0.010072619 | +| clip_fraction | 0.348 | +| clip_range | 0.0714 | +| entropy_loss | -7.03 | +| explained_variance | 0.297 | +| learning_rate | 4.65e-05 | +| loss | -0.0368 | +| n_updates | 44328 | +| policy_gradient_loss | -0.0236 | +| value_loss | 0.000115 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1422 | +| iterations | 7129 | +| time_elapsed | 10265 | +| total_timesteps | 14600192 | +| train/ | | +| approx_kl | 0.01057573 | +| clip_fraction | 0.319 | +| clip_range | 0.0714 | +| entropy_loss | -7.36 | +| explained_variance | -0.284 | +| learning_rate | 4.65e-05 | +| loss | -0.0314 | +| n_updates | 44332 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000104 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1422 | +| iterations | 7130 | +| time_elapsed | 10266 | +| total_timesteps | 14602240 | +| train/ | | +| approx_kl | 0.012167454 | +| clip_fraction | 0.355 | +| clip_range | 0.0713 | +| entropy_loss | -7.31 | +| explained_variance | -0.277 | +| learning_rate | 4.65e-05 | +| loss | -0.0314 | +| n_updates | 44336 | +| policy_gradient_loss | -0.0231 | +| value_loss | 7.22e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1422 | +| iterations | 7131 | +| time_elapsed | 10267 | +| total_timesteps | 14604288 | +| train/ | | +| approx_kl | 0.010865718 | +| clip_fraction | 0.32 | +| clip_range | 0.0713 | +| entropy_loss | -6.93 | +| explained_variance | 0.519 | +| learning_rate | 4.65e-05 | +| loss | -0.0346 | +| n_updates | 44340 | +| policy_gradient_loss | -0.02 | +| value_loss | 9.87e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1422 | +| iterations | 7132 | +| time_elapsed | 10269 | +| total_timesteps | 14606336 | +| train/ | | +| approx_kl | 0.010803799 | +| clip_fraction | 0.304 | +| clip_range | 0.0713 | +| entropy_loss | -6.72 | +| explained_variance | 0.597 | +| learning_rate | 4.65e-05 | +| loss | -0.0294 | +| n_updates | 44344 | +| policy_gradient_loss | -0.0172 | +| value_loss | 8.99e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1422 | +| iterations | 7133 | +| time_elapsed | 10270 | +| total_timesteps | 14608384 | +| train/ | | +| approx_kl | 0.011063126 | +| clip_fraction | 0.292 | +| clip_range | 0.0713 | +| entropy_loss | -6.42 | +| explained_variance | 0.524 | +| learning_rate | 4.65e-05 | +| loss | -0.0234 | +| n_updates | 44348 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000206 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1422 | +| iterations | 7134 | +| time_elapsed | 10272 | +| total_timesteps | 14610432 | +| train/ | | +| approx_kl | 0.0099158175 | +| clip_fraction | 0.307 | +| clip_range | 0.0713 | +| entropy_loss | -6.92 | +| explained_variance | 0.388 | +| learning_rate | 4.65e-05 | +| loss | -0.0314 | +| n_updates | 44352 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000242 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1422 | +| iterations | 7135 | +| time_elapsed | 10273 | +| total_timesteps | 14612480 | +| train/ | | +| approx_kl | 0.011035825 | +| clip_fraction | 0.287 | +| clip_range | 0.0713 | +| entropy_loss | -6.58 | +| explained_variance | 0.317 | +| learning_rate | 4.65e-05 | +| loss | -0.0238 | +| n_updates | 44356 | +| policy_gradient_loss | -0.0145 | +| value_loss | 0.000384 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1422 | +| iterations | 7136 | +| time_elapsed | 10274 | +| total_timesteps | 14614528 | +| train/ | | +| approx_kl | 0.011653731 | +| clip_fraction | 0.34 | +| clip_range | 0.0713 | +| entropy_loss | -6.8 | +| explained_variance | 0.592 | +| learning_rate | 4.65e-05 | +| loss | -0.034 | +| n_updates | 44360 | +| policy_gradient_loss | -0.0228 | +| value_loss | 9.72e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1422 | +| iterations | 7137 | +| time_elapsed | 10276 | +| total_timesteps | 14616576 | +| train/ | | +| approx_kl | 0.013243463 | +| clip_fraction | 0.359 | +| clip_range | 0.0713 | +| entropy_loss | -6.87 | +| explained_variance | 0.252 | +| learning_rate | 4.65e-05 | +| loss | -0.0292 | +| n_updates | 44364 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000146 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1422 | +| iterations | 7138 | +| time_elapsed | 10277 | +| total_timesteps | 14618624 | +| train/ | | +| approx_kl | 0.011129312 | +| clip_fraction | 0.324 | +| clip_range | 0.0713 | +| entropy_loss | -6.85 | +| explained_variance | 0.461 | +| learning_rate | 4.65e-05 | +| loss | -0.0346 | +| n_updates | 44368 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000179 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1422 | +| iterations | 7139 | +| time_elapsed | 10279 | +| total_timesteps | 14620672 | +| train/ | | +| approx_kl | 0.011551052 | +| clip_fraction | 0.324 | +| clip_range | 0.0713 | +| entropy_loss | -6.42 | +| explained_variance | 0.548 | +| learning_rate | 4.65e-05 | +| loss | -0.0296 | +| n_updates | 44372 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.00019 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1422 | +| iterations | 7140 | +| time_elapsed | 10280 | +| total_timesteps | 14622720 | +| train/ | | +| approx_kl | 0.0114312 | +| clip_fraction | 0.352 | +| clip_range | 0.0713 | +| entropy_loss | -6.86 | +| explained_variance | 0.574 | +| learning_rate | 4.65e-05 | +| loss | -0.0407 | +| n_updates | 44376 | +| policy_gradient_loss | -0.0238 | +| value_loss | 0.000108 | +--------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1422 | +| iterations | 7141 | +| time_elapsed | 10282 | +| total_timesteps | 14624768 | +| train/ | | +| approx_kl | 0.0073018833 | +| clip_fraction | 0.283 | +| clip_range | 0.0713 | +| entropy_loss | -6.78 | +| explained_variance | 0.369 | +| learning_rate | 4.65e-05 | +| loss | -0.0261 | +| n_updates | 44380 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000283 | +------------------------------------------ +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1422 | +| iterations | 7142 | +| time_elapsed | 10283 | +| total_timesteps | 14626816 | +| train/ | | +| approx_kl | 0.0126694 | +| clip_fraction | 0.327 | +| clip_range | 0.0713 | +| entropy_loss | -7 | +| explained_variance | 0.277 | +| learning_rate | 4.65e-05 | +| loss | -0.0363 | +| n_updates | 44384 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.00016 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1422 | +| iterations | 7143 | +| time_elapsed | 10284 | +| total_timesteps | 14628864 | +| train/ | | +| approx_kl | 0.011451181 | +| clip_fraction | 0.361 | +| clip_range | 0.0713 | +| entropy_loss | -7.3 | +| explained_variance | -0.24 | +| learning_rate | 4.65e-05 | +| loss | -0.0371 | +| n_updates | 44388 | +| policy_gradient_loss | -0.0216 | +| value_loss | 8.83e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1422 | +| iterations | 7144 | +| time_elapsed | 10286 | +| total_timesteps | 14630912 | +| train/ | | +| approx_kl | 0.012897302 | +| clip_fraction | 0.322 | +| clip_range | 0.0713 | +| entropy_loss | -7.08 | +| explained_variance | 0.171 | +| learning_rate | 4.65e-05 | +| loss | -0.0299 | +| n_updates | 44392 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000252 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1422 | +| iterations | 7145 | +| time_elapsed | 10287 | +| total_timesteps | 14632960 | +| train/ | | +| approx_kl | 0.010114154 | +| clip_fraction | 0.307 | +| clip_range | 0.0713 | +| entropy_loss | -7.08 | +| explained_variance | 0.221 | +| learning_rate | 4.65e-05 | +| loss | -0.0339 | +| n_updates | 44396 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000143 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1422 | +| iterations | 7146 | +| time_elapsed | 10289 | +| total_timesteps | 14635008 | +| train/ | | +| approx_kl | 0.00971931 | +| clip_fraction | 0.335 | +| clip_range | 0.0713 | +| entropy_loss | -6.92 | +| explained_variance | 0.464 | +| learning_rate | 4.65e-05 | +| loss | -0.0364 | +| n_updates | 44400 | +| policy_gradient_loss | -0.0215 | +| value_loss | 9.44e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1422 | +| iterations | 7147 | +| time_elapsed | 10290 | +| total_timesteps | 14637056 | +| train/ | | +| approx_kl | 0.008547561 | +| clip_fraction | 0.319 | +| clip_range | 0.0713 | +| entropy_loss | -7.14 | +| explained_variance | 0.18 | +| learning_rate | 4.65e-05 | +| loss | -0.0224 | +| n_updates | 44404 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000278 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1422 | +| iterations | 7148 | +| time_elapsed | 10292 | +| total_timesteps | 14639104 | +| train/ | | +| approx_kl | 0.011069607 | +| clip_fraction | 0.294 | +| clip_range | 0.0713 | +| entropy_loss | -6.81 | +| explained_variance | 0.223 | +| learning_rate | 4.65e-05 | +| loss | -0.0293 | +| n_updates | 44408 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000209 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1422 | +| iterations | 7149 | +| time_elapsed | 10293 | +| total_timesteps | 14641152 | +| train/ | | +| approx_kl | 0.011537926 | +| clip_fraction | 0.341 | +| clip_range | 0.0713 | +| entropy_loss | -6.35 | +| explained_variance | 0.708 | +| learning_rate | 4.65e-05 | +| loss | -0.0369 | +| n_updates | 44412 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000107 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1422 | +| iterations | 7150 | +| time_elapsed | 10294 | +| total_timesteps | 14643200 | +| train/ | | +| approx_kl | 0.011445902 | +| clip_fraction | 0.333 | +| clip_range | 0.0713 | +| entropy_loss | -6.87 | +| explained_variance | 0.477 | +| learning_rate | 4.65e-05 | +| loss | -0.0332 | +| n_updates | 44416 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000152 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1422 | +| iterations | 7151 | +| time_elapsed | 10296 | +| total_timesteps | 14645248 | +| train/ | | +| approx_kl | 0.008815779 | +| clip_fraction | 0.304 | +| clip_range | 0.0713 | +| entropy_loss | -6.98 | +| explained_variance | 0.461 | +| learning_rate | 4.65e-05 | +| loss | -0.0275 | +| n_updates | 44420 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000187 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1422 | +| iterations | 7152 | +| time_elapsed | 10297 | +| total_timesteps | 14647296 | +| train/ | | +| approx_kl | 0.010617297 | +| clip_fraction | 0.323 | +| clip_range | 0.0713 | +| entropy_loss | -6.86 | +| explained_variance | 0.186 | +| learning_rate | 4.65e-05 | +| loss | -0.0337 | +| n_updates | 44424 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000234 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1422 | +| iterations | 7153 | +| time_elapsed | 10299 | +| total_timesteps | 14649344 | +| train/ | | +| approx_kl | 0.012542464 | +| clip_fraction | 0.317 | +| clip_range | 0.0713 | +| entropy_loss | -6.89 | +| explained_variance | 0.369 | +| learning_rate | 4.65e-05 | +| loss | -0.0329 | +| n_updates | 44428 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000208 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1422 | +| iterations | 7154 | +| time_elapsed | 10300 | +| total_timesteps | 14651392 | +| train/ | | +| approx_kl | 0.011272849 | +| clip_fraction | 0.361 | +| clip_range | 0.0713 | +| entropy_loss | -7.23 | +| explained_variance | 0.0335 | +| learning_rate | 4.65e-05 | +| loss | -0.0375 | +| n_updates | 44432 | +| policy_gradient_loss | -0.0233 | +| value_loss | 9.91e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1422 | +| iterations | 7155 | +| time_elapsed | 10302 | +| total_timesteps | 14653440 | +| train/ | | +| approx_kl | 0.012164379 | +| clip_fraction | 0.321 | +| clip_range | 0.0713 | +| entropy_loss | -7.03 | +| explained_variance | 0.289 | +| learning_rate | 4.65e-05 | +| loss | -0.039 | +| n_updates | 44436 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000133 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1422 | +| iterations | 7156 | +| time_elapsed | 10303 | +| total_timesteps | 14655488 | +| train/ | | +| approx_kl | 0.010602082 | +| clip_fraction | 0.309 | +| clip_range | 0.0713 | +| entropy_loss | -6.85 | +| explained_variance | 0.299 | +| learning_rate | 4.65e-05 | +| loss | -0.0281 | +| n_updates | 44440 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000364 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1422 | +| iterations | 7157 | +| time_elapsed | 10305 | +| total_timesteps | 14657536 | +| train/ | | +| approx_kl | 0.011968352 | +| clip_fraction | 0.373 | +| clip_range | 0.0713 | +| entropy_loss | -7.1 | +| explained_variance | 0.372 | +| learning_rate | 4.65e-05 | +| loss | -0.0425 | +| n_updates | 44444 | +| policy_gradient_loss | -0.0261 | +| value_loss | 0.000106 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1422 | +| iterations | 7158 | +| time_elapsed | 10306 | +| total_timesteps | 14659584 | +| train/ | | +| approx_kl | 0.010959061 | +| clip_fraction | 0.32 | +| clip_range | 0.0713 | +| entropy_loss | -7.28 | +| explained_variance | -0.17 | +| learning_rate | 4.65e-05 | +| loss | -0.0397 | +| n_updates | 44448 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000145 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1422 | +| iterations | 7159 | +| time_elapsed | 10308 | +| total_timesteps | 14661632 | +| train/ | | +| approx_kl | 0.010411552 | +| clip_fraction | 0.323 | +| clip_range | 0.0713 | +| entropy_loss | -6.32 | +| explained_variance | 0.774 | +| learning_rate | 4.65e-05 | +| loss | -0.0259 | +| n_updates | 44452 | +| policy_gradient_loss | -0.0187 | +| value_loss | 8.8e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1422 | +| iterations | 7160 | +| time_elapsed | 10309 | +| total_timesteps | 14663680 | +| train/ | | +| approx_kl | 0.010020005 | +| clip_fraction | 0.321 | +| clip_range | 0.0713 | +| entropy_loss | -6.94 | +| explained_variance | 0.295 | +| learning_rate | 4.65e-05 | +| loss | -0.0268 | +| n_updates | 44456 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000206 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1422 | +| iterations | 7161 | +| time_elapsed | 10310 | +| total_timesteps | 14665728 | +| train/ | | +| approx_kl | 0.009289066 | +| clip_fraction | 0.332 | +| clip_range | 0.0713 | +| entropy_loss | -6.84 | +| explained_variance | 0.314 | +| learning_rate | 4.65e-05 | +| loss | -0.0336 | +| n_updates | 44460 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000226 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1422 | +| iterations | 7162 | +| time_elapsed | 10312 | +| total_timesteps | 14667776 | +| train/ | | +| approx_kl | 0.010687038 | +| clip_fraction | 0.318 | +| clip_range | 0.0713 | +| entropy_loss | -6.68 | +| explained_variance | 0.611 | +| learning_rate | 4.65e-05 | +| loss | -0.0343 | +| n_updates | 44464 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000126 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1422 | +| iterations | 7163 | +| time_elapsed | 10313 | +| total_timesteps | 14669824 | +| train/ | | +| approx_kl | 0.0102347955 | +| clip_fraction | 0.321 | +| clip_range | 0.0713 | +| entropy_loss | -6.85 | +| explained_variance | 0.263 | +| learning_rate | 4.65e-05 | +| loss | -0.0244 | +| n_updates | 44468 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000221 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1422 | +| iterations | 7164 | +| time_elapsed | 10315 | +| total_timesteps | 14671872 | +| train/ | | +| approx_kl | 0.013102863 | +| clip_fraction | 0.335 | +| clip_range | 0.0713 | +| entropy_loss | -7.18 | +| explained_variance | 0.266 | +| learning_rate | 4.65e-05 | +| loss | -0.0305 | +| n_updates | 44472 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000188 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1422 | +| iterations | 7165 | +| time_elapsed | 10316 | +| total_timesteps | 14673920 | +| train/ | | +| approx_kl | 0.010341849 | +| clip_fraction | 0.313 | +| clip_range | 0.0713 | +| entropy_loss | -6.83 | +| explained_variance | 0.32 | +| learning_rate | 4.65e-05 | +| loss | -0.0233 | +| n_updates | 44476 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000261 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1422 | +| iterations | 7166 | +| time_elapsed | 10317 | +| total_timesteps | 14675968 | +| train/ | | +| approx_kl | 0.01080792 | +| clip_fraction | 0.292 | +| clip_range | 0.0713 | +| entropy_loss | -6.95 | +| explained_variance | 0.369 | +| learning_rate | 4.65e-05 | +| loss | -0.0258 | +| n_updates | 44480 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000231 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1422 | +| iterations | 7167 | +| time_elapsed | 10319 | +| total_timesteps | 14678016 | +| train/ | | +| approx_kl | 0.011989053 | +| clip_fraction | 0.367 | +| clip_range | 0.0713 | +| entropy_loss | -6.68 | +| explained_variance | 0.493 | +| learning_rate | 4.65e-05 | +| loss | -0.0355 | +| n_updates | 44484 | +| policy_gradient_loss | -0.0241 | +| value_loss | 0.000106 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1422 | +| iterations | 7168 | +| time_elapsed | 10320 | +| total_timesteps | 14680064 | +| train/ | | +| approx_kl | 0.012452115 | +| clip_fraction | 0.332 | +| clip_range | 0.0713 | +| entropy_loss | -6.75 | +| explained_variance | 0.451 | +| learning_rate | 4.65e-05 | +| loss | -0.0322 | +| n_updates | 44488 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000169 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1422 | +| iterations | 7169 | +| time_elapsed | 10322 | +| total_timesteps | 14682112 | +| train/ | | +| approx_kl | 0.012958318 | +| clip_fraction | 0.309 | +| clip_range | 0.0713 | +| entropy_loss | -6.88 | +| explained_variance | 0.226 | +| learning_rate | 4.65e-05 | +| loss | -0.0228 | +| n_updates | 44492 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000272 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1422 | +| iterations | 7170 | +| time_elapsed | 10323 | +| total_timesteps | 14684160 | +| train/ | | +| approx_kl | 0.011636065 | +| clip_fraction | 0.312 | +| clip_range | 0.0713 | +| entropy_loss | -6.7 | +| explained_variance | 0.326 | +| learning_rate | 4.65e-05 | +| loss | -0.0234 | +| n_updates | 44496 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000355 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1422 | +| iterations | 7171 | +| time_elapsed | 10325 | +| total_timesteps | 14686208 | +| train/ | | +| approx_kl | 0.013401169 | +| clip_fraction | 0.345 | +| clip_range | 0.0713 | +| entropy_loss | -6.84 | +| explained_variance | 0.188 | +| learning_rate | 4.65e-05 | +| loss | -0.0329 | +| n_updates | 44500 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000161 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1422 | +| iterations | 7172 | +| time_elapsed | 10326 | +| total_timesteps | 14688256 | +| train/ | | +| approx_kl | 0.010892115 | +| clip_fraction | 0.336 | +| clip_range | 0.0713 | +| entropy_loss | -6.84 | +| explained_variance | 0.495 | +| learning_rate | 4.65e-05 | +| loss | -0.0351 | +| n_updates | 44504 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000136 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1422 | +| iterations | 7173 | +| time_elapsed | 10328 | +| total_timesteps | 14690304 | +| train/ | | +| approx_kl | 0.010806525 | +| clip_fraction | 0.312 | +| clip_range | 0.0713 | +| entropy_loss | -6.99 | +| explained_variance | 0.132 | +| learning_rate | 4.65e-05 | +| loss | -0.0318 | +| n_updates | 44508 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000285 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1422 | +| iterations | 7174 | +| time_elapsed | 10329 | +| total_timesteps | 14692352 | +| train/ | | +| approx_kl | 0.011343373 | +| clip_fraction | 0.338 | +| clip_range | 0.0713 | +| entropy_loss | -7.09 | +| explained_variance | 0.247 | +| learning_rate | 4.65e-05 | +| loss | -0.0359 | +| n_updates | 44512 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000153 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1422 | +| iterations | 7175 | +| time_elapsed | 10330 | +| total_timesteps | 14694400 | +| train/ | | +| approx_kl | 0.01171032 | +| clip_fraction | 0.325 | +| clip_range | 0.0713 | +| entropy_loss | -6.84 | +| explained_variance | 0.223 | +| learning_rate | 4.65e-05 | +| loss | -0.0247 | +| n_updates | 44516 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000252 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1422 | +| iterations | 7176 | +| time_elapsed | 10332 | +| total_timesteps | 14696448 | +| train/ | | +| approx_kl | 0.012465926 | +| clip_fraction | 0.336 | +| clip_range | 0.0713 | +| entropy_loss | -6.79 | +| explained_variance | 0.389 | +| learning_rate | 4.65e-05 | +| loss | -0.0329 | +| n_updates | 44520 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000154 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1422 | +| iterations | 7177 | +| time_elapsed | 10333 | +| total_timesteps | 14698496 | +| train/ | | +| approx_kl | 0.009464458 | +| clip_fraction | 0.327 | +| clip_range | 0.0713 | +| entropy_loss | -6.9 | +| explained_variance | 0.523 | +| learning_rate | 4.65e-05 | +| loss | -0.0249 | +| n_updates | 44524 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.00013 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1422 | +| iterations | 7178 | +| time_elapsed | 10335 | +| total_timesteps | 14700544 | +| train/ | | +| approx_kl | 0.010568956 | +| clip_fraction | 0.304 | +| clip_range | 0.0713 | +| entropy_loss | -6.98 | +| explained_variance | 0.404 | +| learning_rate | 4.65e-05 | +| loss | -0.0322 | +| n_updates | 44528 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000213 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1422 | +| iterations | 7179 | +| time_elapsed | 10336 | +| total_timesteps | 14702592 | +| train/ | | +| approx_kl | 0.012399333 | +| clip_fraction | 0.333 | +| clip_range | 0.0713 | +| entropy_loss | -6.98 | +| explained_variance | 0.347 | +| learning_rate | 4.65e-05 | +| loss | -0.0306 | +| n_updates | 44532 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000152 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1422 | +| iterations | 7180 | +| time_elapsed | 10338 | +| total_timesteps | 14704640 | +| train/ | | +| approx_kl | 0.008711612 | +| clip_fraction | 0.3 | +| clip_range | 0.0713 | +| entropy_loss | -6.32 | +| explained_variance | 0.507 | +| learning_rate | 4.65e-05 | +| loss | -0.0292 | +| n_updates | 44536 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000261 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1422 | +| iterations | 7181 | +| time_elapsed | 10339 | +| total_timesteps | 14706688 | +| train/ | | +| approx_kl | 0.012163363 | +| clip_fraction | 0.349 | +| clip_range | 0.0713 | +| entropy_loss | -6.84 | +| explained_variance | 0.299 | +| learning_rate | 4.65e-05 | +| loss | -0.0373 | +| n_updates | 44540 | +| policy_gradient_loss | -0.0223 | +| value_loss | 0.000116 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1422 | +| iterations | 7182 | +| time_elapsed | 10341 | +| total_timesteps | 14708736 | +| train/ | | +| approx_kl | 0.01148889 | +| clip_fraction | 0.344 | +| clip_range | 0.0713 | +| entropy_loss | -7.05 | +| explained_variance | 0.394 | +| learning_rate | 4.65e-05 | +| loss | -0.0341 | +| n_updates | 44544 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000143 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1422 | +| iterations | 7183 | +| time_elapsed | 10342 | +| total_timesteps | 14710784 | +| train/ | | +| approx_kl | 0.011435583 | +| clip_fraction | 0.302 | +| clip_range | 0.0713 | +| entropy_loss | -6.79 | +| explained_variance | 0.262 | +| learning_rate | 4.65e-05 | +| loss | -0.0252 | +| n_updates | 44548 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000328 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1422 | +| iterations | 7184 | +| time_elapsed | 10344 | +| total_timesteps | 14712832 | +| train/ | | +| approx_kl | 0.009162408 | +| clip_fraction | 0.334 | +| clip_range | 0.0713 | +| entropy_loss | -7.12 | +| explained_variance | 0.331 | +| learning_rate | 4.65e-05 | +| loss | -0.0332 | +| n_updates | 44552 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000163 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1422 | +| iterations | 7185 | +| time_elapsed | 10345 | +| total_timesteps | 14714880 | +| train/ | | +| approx_kl | 0.01030959 | +| clip_fraction | 0.306 | +| clip_range | 0.0713 | +| entropy_loss | -7.16 | +| explained_variance | -0.103 | +| learning_rate | 4.65e-05 | +| loss | -0.0294 | +| n_updates | 44556 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000299 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1422 | +| iterations | 7186 | +| time_elapsed | 10346 | +| total_timesteps | 14716928 | +| train/ | | +| approx_kl | 0.010211181 | +| clip_fraction | 0.31 | +| clip_range | 0.0713 | +| entropy_loss | -6.99 | +| explained_variance | 0.409 | +| learning_rate | 4.65e-05 | +| loss | -0.0319 | +| n_updates | 44560 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000193 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1422 | +| iterations | 7187 | +| time_elapsed | 10348 | +| total_timesteps | 14718976 | +| train/ | | +| approx_kl | 0.01272364 | +| clip_fraction | 0.322 | +| clip_range | 0.0713 | +| entropy_loss | -7.09 | +| explained_variance | 0.302 | +| learning_rate | 4.65e-05 | +| loss | -0.0241 | +| n_updates | 44564 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000168 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1422 | +| iterations | 7188 | +| time_elapsed | 10349 | +| total_timesteps | 14721024 | +| train/ | | +| approx_kl | 0.012469714 | +| clip_fraction | 0.332 | +| clip_range | 0.0713 | +| entropy_loss | -6.67 | +| explained_variance | 0.609 | +| learning_rate | 4.65e-05 | +| loss | -0.0354 | +| n_updates | 44568 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000132 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1422 | +| iterations | 7189 | +| time_elapsed | 10351 | +| total_timesteps | 14723072 | +| train/ | | +| approx_kl | 0.011781182 | +| clip_fraction | 0.306 | +| clip_range | 0.0713 | +| entropy_loss | -7.06 | +| explained_variance | 0.0674 | +| learning_rate | 4.65e-05 | +| loss | -0.0336 | +| n_updates | 44572 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000183 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1422 | +| iterations | 7190 | +| time_elapsed | 10352 | +| total_timesteps | 14725120 | +| train/ | | +| approx_kl | 0.013591833 | +| clip_fraction | 0.347 | +| clip_range | 0.0713 | +| entropy_loss | -6.9 | +| explained_variance | 0.437 | +| learning_rate | 4.65e-05 | +| loss | -0.0323 | +| n_updates | 44576 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000138 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1422 | +| iterations | 7191 | +| time_elapsed | 10354 | +| total_timesteps | 14727168 | +| train/ | | +| approx_kl | 0.00960811 | +| clip_fraction | 0.289 | +| clip_range | 0.0713 | +| entropy_loss | -7.04 | +| explained_variance | 0.196 | +| learning_rate | 4.65e-05 | +| loss | -0.0244 | +| n_updates | 44580 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000279 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1422 | +| iterations | 7192 | +| time_elapsed | 10355 | +| total_timesteps | 14729216 | +| train/ | | +| approx_kl | 0.013997576 | +| clip_fraction | 0.342 | +| clip_range | 0.0713 | +| entropy_loss | -6.6 | +| explained_variance | 0.538 | +| learning_rate | 4.65e-05 | +| loss | -0.0324 | +| n_updates | 44584 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000165 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1422 | +| iterations | 7193 | +| time_elapsed | 10357 | +| total_timesteps | 14731264 | +| train/ | | +| approx_kl | 0.010797158 | +| clip_fraction | 0.312 | +| clip_range | 0.0713 | +| entropy_loss | -7.02 | +| explained_variance | 0.26 | +| learning_rate | 4.65e-05 | +| loss | -0.0343 | +| n_updates | 44588 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.00019 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1422 | +| iterations | 7194 | +| time_elapsed | 10358 | +| total_timesteps | 14733312 | +| train/ | | +| approx_kl | 0.0107156355 | +| clip_fraction | 0.306 | +| clip_range | 0.0713 | +| entropy_loss | -6.18 | +| explained_variance | 0.61 | +| learning_rate | 4.65e-05 | +| loss | -0.0238 | +| n_updates | 44592 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000202 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1422 | +| iterations | 7195 | +| time_elapsed | 10359 | +| total_timesteps | 14735360 | +| train/ | | +| approx_kl | 0.011173919 | +| clip_fraction | 0.321 | +| clip_range | 0.0713 | +| entropy_loss | -6.89 | +| explained_variance | 0.0214 | +| learning_rate | 4.65e-05 | +| loss | -0.0359 | +| n_updates | 44596 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.00026 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1422 | +| iterations | 7196 | +| time_elapsed | 10361 | +| total_timesteps | 14737408 | +| train/ | | +| approx_kl | 0.00841485 | +| clip_fraction | 0.306 | +| clip_range | 0.0713 | +| entropy_loss | -7.11 | +| explained_variance | 0.215 | +| learning_rate | 4.65e-05 | +| loss | -0.0311 | +| n_updates | 44600 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000179 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.385 | +| time/ | | +| fps | 1422 | +| iterations | 7197 | +| time_elapsed | 10362 | +| total_timesteps | 14739456 | +| train/ | | +| approx_kl | 0.010219423 | +| clip_fraction | 0.295 | +| clip_range | 0.0713 | +| entropy_loss | -6.75 | +| explained_variance | 0.323 | +| learning_rate | 4.65e-05 | +| loss | -0.0249 | +| n_updates | 44604 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000401 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.385 | +| time/ | | +| fps | 1422 | +| iterations | 7198 | +| time_elapsed | 10364 | +| total_timesteps | 14741504 | +| train/ | | +| approx_kl | 0.011438128 | +| clip_fraction | 0.344 | +| clip_range | 0.0713 | +| entropy_loss | -6.57 | +| explained_variance | 0.42 | +| learning_rate | 4.65e-05 | +| loss | -0.0306 | +| n_updates | 44608 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.00022 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.386 | +| time/ | | +| fps | 1422 | +| iterations | 7199 | +| time_elapsed | 10365 | +| total_timesteps | 14743552 | +| train/ | | +| approx_kl | 0.012055719 | +| clip_fraction | 0.348 | +| clip_range | 0.0713 | +| entropy_loss | -6.89 | +| explained_variance | 0.3 | +| learning_rate | 4.65e-05 | +| loss | -0.0308 | +| n_updates | 44612 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000122 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1422 | +| iterations | 7200 | +| time_elapsed | 10366 | +| total_timesteps | 14745600 | +| train/ | | +| approx_kl | 0.0109288925 | +| clip_fraction | 0.344 | +| clip_range | 0.0713 | +| entropy_loss | -7.14 | +| explained_variance | 0.18 | +| learning_rate | 4.65e-05 | +| loss | -0.0328 | +| n_updates | 44616 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000116 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.387 | +| time/ | | +| fps | 1422 | +| iterations | 7201 | +| time_elapsed | 10368 | +| total_timesteps | 14747648 | +| train/ | | +| approx_kl | 0.009975852 | +| clip_fraction | 0.304 | +| clip_range | 0.0713 | +| entropy_loss | -6.62 | +| explained_variance | 0.616 | +| learning_rate | 4.65e-05 | +| loss | -0.0312 | +| n_updates | 44620 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000141 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1422 | +| iterations | 7202 | +| time_elapsed | 10369 | +| total_timesteps | 14749696 | +| train/ | | +| approx_kl | 0.009513093 | +| clip_fraction | 0.326 | +| clip_range | 0.0713 | +| entropy_loss | -6.69 | +| explained_variance | 0.414 | +| learning_rate | 4.65e-05 | +| loss | -0.0224 | +| n_updates | 44624 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.000287 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1422 | +| iterations | 7203 | +| time_elapsed | 10371 | +| total_timesteps | 14751744 | +| train/ | | +| approx_kl | 0.013710421 | +| clip_fraction | 0.332 | +| clip_range | 0.0713 | +| entropy_loss | -6.94 | +| explained_variance | 0.226 | +| learning_rate | 4.65e-05 | +| loss | -0.0329 | +| n_updates | 44628 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000141 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1422 | +| iterations | 7204 | +| time_elapsed | 10372 | +| total_timesteps | 14753792 | +| train/ | | +| approx_kl | 0.012140812 | +| clip_fraction | 0.306 | +| clip_range | 0.0713 | +| entropy_loss | -6.79 | +| explained_variance | 0.379 | +| learning_rate | 4.65e-05 | +| loss | -0.0353 | +| n_updates | 44632 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000227 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1422 | +| iterations | 7205 | +| time_elapsed | 10374 | +| total_timesteps | 14755840 | +| train/ | | +| approx_kl | 0.010163552 | +| clip_fraction | 0.33 | +| clip_range | 0.0713 | +| entropy_loss | -6.95 | +| explained_variance | 0.277 | +| learning_rate | 4.65e-05 | +| loss | -0.0314 | +| n_updates | 44636 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000181 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1422 | +| iterations | 7206 | +| time_elapsed | 10375 | +| total_timesteps | 14757888 | +| train/ | | +| approx_kl | 0.012493414 | +| clip_fraction | 0.326 | +| clip_range | 0.0713 | +| entropy_loss | -6.59 | +| explained_variance | 0.376 | +| learning_rate | 4.65e-05 | +| loss | -0.0287 | +| n_updates | 44640 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000216 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1422 | +| iterations | 7207 | +| time_elapsed | 10377 | +| total_timesteps | 14759936 | +| train/ | | +| approx_kl | 0.010911764 | +| clip_fraction | 0.341 | +| clip_range | 0.0713 | +| entropy_loss | -6.68 | +| explained_variance | 0.513 | +| learning_rate | 4.65e-05 | +| loss | -0.0327 | +| n_updates | 44644 | +| policy_gradient_loss | -0.0216 | +| value_loss | 9.43e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1422 | +| iterations | 7208 | +| time_elapsed | 10378 | +| total_timesteps | 14761984 | +| train/ | | +| approx_kl | 0.00937755 | +| clip_fraction | 0.334 | +| clip_range | 0.0713 | +| entropy_loss | -7.16 | +| explained_variance | -0.0916 | +| learning_rate | 4.65e-05 | +| loss | -0.0259 | +| n_updates | 44648 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000118 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1422 | +| iterations | 7209 | +| time_elapsed | 10379 | +| total_timesteps | 14764032 | +| train/ | | +| approx_kl | 0.011693547 | +| clip_fraction | 0.315 | +| clip_range | 0.0713 | +| entropy_loss | -6.78 | +| explained_variance | 0.463 | +| learning_rate | 4.65e-05 | +| loss | -0.027 | +| n_updates | 44652 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000165 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1422 | +| iterations | 7210 | +| time_elapsed | 10381 | +| total_timesteps | 14766080 | +| train/ | | +| approx_kl | 0.0114132315 | +| clip_fraction | 0.321 | +| clip_range | 0.0713 | +| entropy_loss | -6.53 | +| explained_variance | 0.558 | +| learning_rate | 4.65e-05 | +| loss | -0.0327 | +| n_updates | 44656 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000167 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1422 | +| iterations | 7211 | +| time_elapsed | 10382 | +| total_timesteps | 14768128 | +| train/ | | +| approx_kl | 0.009613281 | +| clip_fraction | 0.319 | +| clip_range | 0.0713 | +| entropy_loss | -7.26 | +| explained_variance | -0.12 | +| learning_rate | 4.65e-05 | +| loss | -0.0333 | +| n_updates | 44660 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000102 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1422 | +| iterations | 7212 | +| time_elapsed | 10384 | +| total_timesteps | 14770176 | +| train/ | | +| approx_kl | 0.009547314 | +| clip_fraction | 0.312 | +| clip_range | 0.0713 | +| entropy_loss | -7.19 | +| explained_variance | 0.163 | +| learning_rate | 4.65e-05 | +| loss | -0.0281 | +| n_updates | 44664 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000173 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1422 | +| iterations | 7213 | +| time_elapsed | 10385 | +| total_timesteps | 14772224 | +| train/ | | +| approx_kl | 0.012052718 | +| clip_fraction | 0.332 | +| clip_range | 0.0713 | +| entropy_loss | -6.67 | +| explained_variance | 0.368 | +| learning_rate | 4.65e-05 | +| loss | -0.0235 | +| n_updates | 44668 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000183 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1422 | +| iterations | 7214 | +| time_elapsed | 10387 | +| total_timesteps | 14774272 | +| train/ | | +| approx_kl | 0.011205303 | +| clip_fraction | 0.313 | +| clip_range | 0.0713 | +| entropy_loss | -6.8 | +| explained_variance | 0.43 | +| learning_rate | 4.65e-05 | +| loss | -0.0332 | +| n_updates | 44672 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.00023 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.386 | +| time/ | | +| fps | 1422 | +| iterations | 7215 | +| time_elapsed | 10388 | +| total_timesteps | 14776320 | +| train/ | | +| approx_kl | 0.010556803 | +| clip_fraction | 0.305 | +| clip_range | 0.0713 | +| entropy_loss | -7 | +| explained_variance | 0.0493 | +| learning_rate | 4.65e-05 | +| loss | -0.0295 | +| n_updates | 44676 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000262 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1422 | +| iterations | 7216 | +| time_elapsed | 10389 | +| total_timesteps | 14778368 | +| train/ | | +| approx_kl | 0.01037754 | +| clip_fraction | 0.29 | +| clip_range | 0.0713 | +| entropy_loss | -6.62 | +| explained_variance | 0.349 | +| learning_rate | 4.65e-05 | +| loss | -0.0328 | +| n_updates | 44680 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000351 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1422 | +| iterations | 7217 | +| time_elapsed | 10391 | +| total_timesteps | 14780416 | +| train/ | | +| approx_kl | 0.0152375875 | +| clip_fraction | 0.35 | +| clip_range | 0.0713 | +| entropy_loss | -7.01 | +| explained_variance | 0.343 | +| learning_rate | 4.65e-05 | +| loss | -0.0408 | +| n_updates | 44684 | +| policy_gradient_loss | -0.0225 | +| value_loss | 0.000115 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1422 | +| iterations | 7218 | +| time_elapsed | 10392 | +| total_timesteps | 14782464 | +| train/ | | +| approx_kl | 0.010931805 | +| clip_fraction | 0.328 | +| clip_range | 0.0713 | +| entropy_loss | -6.49 | +| explained_variance | 0.408 | +| learning_rate | 4.65e-05 | +| loss | -0.0313 | +| n_updates | 44688 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.00035 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.388 | +| time/ | | +| fps | 1422 | +| iterations | 7219 | +| time_elapsed | 10394 | +| total_timesteps | 14784512 | +| train/ | | +| approx_kl | 0.011507478 | +| clip_fraction | 0.326 | +| clip_range | 0.0713 | +| entropy_loss | -6.86 | +| explained_variance | 0.366 | +| learning_rate | 4.65e-05 | +| loss | -0.0366 | +| n_updates | 44692 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000196 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.388 | +| time/ | | +| fps | 1422 | +| iterations | 7220 | +| time_elapsed | 10395 | +| total_timesteps | 14786560 | +| train/ | | +| approx_kl | 0.010575648 | +| clip_fraction | 0.314 | +| clip_range | 0.0713 | +| entropy_loss | -7.28 | +| explained_variance | 0.0101 | +| learning_rate | 4.65e-05 | +| loss | -0.0221 | +| n_updates | 44696 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000211 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.388 | +| time/ | | +| fps | 1422 | +| iterations | 7221 | +| time_elapsed | 10396 | +| total_timesteps | 14788608 | +| train/ | | +| approx_kl | 0.010240741 | +| clip_fraction | 0.342 | +| clip_range | 0.0713 | +| entropy_loss | -7.16 | +| explained_variance | 0.283 | +| learning_rate | 4.65e-05 | +| loss | -0.033 | +| n_updates | 44700 | +| policy_gradient_loss | -0.0223 | +| value_loss | 0.000148 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.388 | +| time/ | | +| fps | 1422 | +| iterations | 7222 | +| time_elapsed | 10398 | +| total_timesteps | 14790656 | +| train/ | | +| approx_kl | 0.009213928 | +| clip_fraction | 0.325 | +| clip_range | 0.0713 | +| entropy_loss | -7.31 | +| explained_variance | -0.143 | +| learning_rate | 4.65e-05 | +| loss | -0.0298 | +| n_updates | 44704 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000171 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1422 | +| iterations | 7223 | +| time_elapsed | 10399 | +| total_timesteps | 14792704 | +| train/ | | +| approx_kl | 0.010266734 | +| clip_fraction | 0.277 | +| clip_range | 0.0713 | +| entropy_loss | -6.48 | +| explained_variance | 0.492 | +| learning_rate | 4.65e-05 | +| loss | -0.0242 | +| n_updates | 44708 | +| policy_gradient_loss | -0.0134 | +| value_loss | 0.000268 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1422 | +| iterations | 7224 | +| time_elapsed | 10401 | +| total_timesteps | 14794752 | +| train/ | | +| approx_kl | 0.010941113 | +| clip_fraction | 0.345 | +| clip_range | 0.0713 | +| entropy_loss | -6.99 | +| explained_variance | 0.474 | +| learning_rate | 4.65e-05 | +| loss | -0.0288 | +| n_updates | 44712 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000129 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.385 | +| time/ | | +| fps | 1422 | +| iterations | 7225 | +| time_elapsed | 10402 | +| total_timesteps | 14796800 | +| train/ | | +| approx_kl | 0.010035897 | +| clip_fraction | 0.323 | +| clip_range | 0.0713 | +| entropy_loss | -6.36 | +| explained_variance | 0.681 | +| learning_rate | 4.65e-05 | +| loss | -0.0302 | +| n_updates | 44716 | +| policy_gradient_loss | -0.0182 | +| value_loss | 9.99e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.386 | +| time/ | | +| fps | 1422 | +| iterations | 7226 | +| time_elapsed | 10404 | +| total_timesteps | 14798848 | +| train/ | | +| approx_kl | 0.00947674 | +| clip_fraction | 0.313 | +| clip_range | 0.0713 | +| entropy_loss | -6.75 | +| explained_variance | 0.346 | +| learning_rate | 4.65e-05 | +| loss | -0.0209 | +| n_updates | 44720 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000256 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.388 | +| time/ | | +| fps | 1422 | +| iterations | 7227 | +| time_elapsed | 10405 | +| total_timesteps | 14800896 | +| train/ | | +| approx_kl | 0.012507245 | +| clip_fraction | 0.335 | +| clip_range | 0.0713 | +| entropy_loss | -6.75 | +| explained_variance | 0.365 | +| learning_rate | 4.65e-05 | +| loss | -0.0356 | +| n_updates | 44724 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000131 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.388 | +| time/ | | +| fps | 1422 | +| iterations | 7228 | +| time_elapsed | 10407 | +| total_timesteps | 14802944 | +| train/ | | +| approx_kl | 0.012112558 | +| clip_fraction | 0.34 | +| clip_range | 0.0713 | +| entropy_loss | -6.77 | +| explained_variance | 0.474 | +| learning_rate | 4.65e-05 | +| loss | -0.0348 | +| n_updates | 44728 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000177 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.388 | +| time/ | | +| fps | 1422 | +| iterations | 7229 | +| time_elapsed | 10408 | +| total_timesteps | 14804992 | +| train/ | | +| approx_kl | 0.01180708 | +| clip_fraction | 0.332 | +| clip_range | 0.0713 | +| entropy_loss | -7.23 | +| explained_variance | -0.0616 | +| learning_rate | 4.65e-05 | +| loss | -0.0339 | +| n_updates | 44732 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000129 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.385 | +| time/ | | +| fps | 1422 | +| iterations | 7230 | +| time_elapsed | 10409 | +| total_timesteps | 14807040 | +| train/ | | +| approx_kl | 0.0107572945 | +| clip_fraction | 0.312 | +| clip_range | 0.0713 | +| entropy_loss | -7.2 | +| explained_variance | 0.118 | +| learning_rate | 4.65e-05 | +| loss | -0.0347 | +| n_updates | 44736 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000322 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.385 | +| time/ | | +| fps | 1422 | +| iterations | 7231 | +| time_elapsed | 10411 | +| total_timesteps | 14809088 | +| train/ | | +| approx_kl | 0.012494197 | +| clip_fraction | 0.339 | +| clip_range | 0.0713 | +| entropy_loss | -6.25 | +| explained_variance | 0.704 | +| learning_rate | 4.65e-05 | +| loss | -0.0291 | +| n_updates | 44740 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000139 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1422 | +| iterations | 7232 | +| time_elapsed | 10412 | +| total_timesteps | 14811136 | +| train/ | | +| approx_kl | 0.011587162 | +| clip_fraction | 0.336 | +| clip_range | 0.0713 | +| entropy_loss | -6.7 | +| explained_variance | 0.377 | +| learning_rate | 4.65e-05 | +| loss | -0.0306 | +| n_updates | 44744 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000232 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1422 | +| iterations | 7233 | +| time_elapsed | 10414 | +| total_timesteps | 14813184 | +| train/ | | +| approx_kl | 0.0115651395 | +| clip_fraction | 0.323 | +| clip_range | 0.0713 | +| entropy_loss | -6.85 | +| explained_variance | 0.413 | +| learning_rate | 4.65e-05 | +| loss | -0.0292 | +| n_updates | 44748 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000212 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1422 | +| iterations | 7234 | +| time_elapsed | 10415 | +| total_timesteps | 14815232 | +| train/ | | +| approx_kl | 0.010029972 | +| clip_fraction | 0.306 | +| clip_range | 0.0713 | +| entropy_loss | -7.14 | +| explained_variance | -0.0271 | +| learning_rate | 4.65e-05 | +| loss | -0.0384 | +| n_updates | 44752 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000231 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1422 | +| iterations | 7235 | +| time_elapsed | 10417 | +| total_timesteps | 14817280 | +| train/ | | +| approx_kl | 0.010206737 | +| clip_fraction | 0.325 | +| clip_range | 0.0713 | +| entropy_loss | -6.88 | +| explained_variance | 0.515 | +| learning_rate | 4.65e-05 | +| loss | -0.0277 | +| n_updates | 44756 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000123 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1422 | +| iterations | 7236 | +| time_elapsed | 10418 | +| total_timesteps | 14819328 | +| train/ | | +| approx_kl | 0.0082201995 | +| clip_fraction | 0.303 | +| clip_range | 0.0713 | +| entropy_loss | -6.65 | +| explained_variance | 0.523 | +| learning_rate | 4.65e-05 | +| loss | -0.0318 | +| n_updates | 44760 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000158 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1422 | +| iterations | 7237 | +| time_elapsed | 10419 | +| total_timesteps | 14821376 | +| train/ | | +| approx_kl | 0.0113558825 | +| clip_fraction | 0.329 | +| clip_range | 0.0713 | +| entropy_loss | -7.05 | +| explained_variance | 0.281 | +| learning_rate | 4.65e-05 | +| loss | -0.0345 | +| n_updates | 44764 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000162 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1422 | +| iterations | 7238 | +| time_elapsed | 10421 | +| total_timesteps | 14823424 | +| train/ | | +| approx_kl | 0.00917117 | +| clip_fraction | 0.3 | +| clip_range | 0.0713 | +| entropy_loss | -6.62 | +| explained_variance | 0.459 | +| learning_rate | 4.65e-05 | +| loss | -0.0233 | +| n_updates | 44768 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.00025 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1422 | +| iterations | 7239 | +| time_elapsed | 10422 | +| total_timesteps | 14825472 | +| train/ | | +| approx_kl | 0.010938159 | +| clip_fraction | 0.355 | +| clip_range | 0.0713 | +| entropy_loss | -6.95 | +| explained_variance | 0.271 | +| learning_rate | 4.65e-05 | +| loss | -0.0314 | +| n_updates | 44772 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000147 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1422 | +| iterations | 7240 | +| time_elapsed | 10424 | +| total_timesteps | 14827520 | +| train/ | | +| approx_kl | 0.013071565 | +| clip_fraction | 0.332 | +| clip_range | 0.0713 | +| entropy_loss | -7.25 | +| explained_variance | -0.227 | +| learning_rate | 4.65e-05 | +| loss | -0.0351 | +| n_updates | 44776 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000155 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1422 | +| iterations | 7241 | +| time_elapsed | 10425 | +| total_timesteps | 14829568 | +| train/ | | +| approx_kl | 0.010642936 | +| clip_fraction | 0.289 | +| clip_range | 0.0713 | +| entropy_loss | -6.93 | +| explained_variance | 0.246 | +| learning_rate | 4.65e-05 | +| loss | -0.028 | +| n_updates | 44780 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000213 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1422 | +| iterations | 7242 | +| time_elapsed | 10426 | +| total_timesteps | 14831616 | +| train/ | | +| approx_kl | 0.012371542 | +| clip_fraction | 0.33 | +| clip_range | 0.0713 | +| entropy_loss | -7.09 | +| explained_variance | 0.397 | +| learning_rate | 4.65e-05 | +| loss | -0.0327 | +| n_updates | 44784 | +| policy_gradient_loss | -0.0209 | +| value_loss | 8.23e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1422 | +| iterations | 7243 | +| time_elapsed | 10428 | +| total_timesteps | 14833664 | +| train/ | | +| approx_kl | 0.009885483 | +| clip_fraction | 0.309 | +| clip_range | 0.0713 | +| entropy_loss | -5.89 | +| explained_variance | 0.771 | +| learning_rate | 4.65e-05 | +| loss | -0.0284 | +| n_updates | 44788 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000117 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1422 | +| iterations | 7244 | +| time_elapsed | 10429 | +| total_timesteps | 14835712 | +| train/ | | +| approx_kl | 0.01192403 | +| clip_fraction | 0.338 | +| clip_range | 0.0713 | +| entropy_loss | -6.87 | +| explained_variance | 0.338 | +| learning_rate | 4.65e-05 | +| loss | -0.0349 | +| n_updates | 44792 | +| policy_gradient_loss | -0.0197 | +| value_loss | 9.37e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1422 | +| iterations | 7245 | +| time_elapsed | 10431 | +| total_timesteps | 14837760 | +| train/ | | +| approx_kl | 0.012935501 | +| clip_fraction | 0.358 | +| clip_range | 0.0713 | +| entropy_loss | -7.13 | +| explained_variance | -0.0322 | +| learning_rate | 4.65e-05 | +| loss | -0.034 | +| n_updates | 44796 | +| policy_gradient_loss | -0.0197 | +| value_loss | 9.19e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1422 | +| iterations | 7246 | +| time_elapsed | 10432 | +| total_timesteps | 14839808 | +| train/ | | +| approx_kl | 0.018507402 | +| clip_fraction | 0.358 | +| clip_range | 0.0713 | +| entropy_loss | -6.83 | +| explained_variance | 0.526 | +| learning_rate | 4.65e-05 | +| loss | -0.0323 | +| n_updates | 44800 | +| policy_gradient_loss | -0.0208 | +| value_loss | 6.63e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1422 | +| iterations | 7247 | +| time_elapsed | 10434 | +| total_timesteps | 14841856 | +| train/ | | +| approx_kl | 0.013511741 | +| clip_fraction | 0.343 | +| clip_range | 0.0713 | +| entropy_loss | -6.62 | +| explained_variance | 0.788 | +| learning_rate | 4.65e-05 | +| loss | -0.0351 | +| n_updates | 44804 | +| policy_gradient_loss | -0.0211 | +| value_loss | 5.96e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1422 | +| iterations | 7248 | +| time_elapsed | 10435 | +| total_timesteps | 14843904 | +| train/ | | +| approx_kl | 0.008872361 | +| clip_fraction | 0.331 | +| clip_range | 0.0713 | +| entropy_loss | -6.8 | +| explained_variance | 0.212 | +| learning_rate | 4.65e-05 | +| loss | -0.0317 | +| n_updates | 44808 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000323 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1422 | +| iterations | 7249 | +| time_elapsed | 10436 | +| total_timesteps | 14845952 | +| train/ | | +| approx_kl | 0.0116160475 | +| clip_fraction | 0.328 | +| clip_range | 0.0713 | +| entropy_loss | -7.1 | +| explained_variance | 0.314 | +| learning_rate | 4.65e-05 | +| loss | -0.0305 | +| n_updates | 44812 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000136 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1422 | +| iterations | 7250 | +| time_elapsed | 10438 | +| total_timesteps | 14848000 | +| train/ | | +| approx_kl | 0.010341103 | +| clip_fraction | 0.303 | +| clip_range | 0.0713 | +| entropy_loss | -6.94 | +| explained_variance | 0.315 | +| learning_rate | 4.65e-05 | +| loss | -0.0253 | +| n_updates | 44816 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.00026 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1422 | +| iterations | 7251 | +| time_elapsed | 10439 | +| total_timesteps | 14850048 | +| train/ | | +| approx_kl | 0.011800045 | +| clip_fraction | 0.312 | +| clip_range | 0.0713 | +| entropy_loss | -6.73 | +| explained_variance | 0.513 | +| learning_rate | 4.65e-05 | +| loss | -0.0231 | +| n_updates | 44820 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000147 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1422 | +| iterations | 7252 | +| time_elapsed | 10441 | +| total_timesteps | 14852096 | +| train/ | | +| approx_kl | 0.014001435 | +| clip_fraction | 0.326 | +| clip_range | 0.0713 | +| entropy_loss | -6.49 | +| explained_variance | 0.414 | +| learning_rate | 4.65e-05 | +| loss | -0.0244 | +| n_updates | 44824 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000247 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1422 | +| iterations | 7253 | +| time_elapsed | 10442 | +| total_timesteps | 14854144 | +| train/ | | +| approx_kl | 0.013313645 | +| clip_fraction | 0.341 | +| clip_range | 0.0713 | +| entropy_loss | -6.58 | +| explained_variance | 0.718 | +| learning_rate | 4.65e-05 | +| loss | -0.0411 | +| n_updates | 44828 | +| policy_gradient_loss | -0.0228 | +| value_loss | 8.64e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1422 | +| iterations | 7254 | +| time_elapsed | 10443 | +| total_timesteps | 14856192 | +| train/ | | +| approx_kl | 0.010802474 | +| clip_fraction | 0.3 | +| clip_range | 0.0713 | +| entropy_loss | -7.26 | +| explained_variance | -0.0198 | +| learning_rate | 4.65e-05 | +| loss | -0.0276 | +| n_updates | 44832 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000403 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1422 | +| iterations | 7255 | +| time_elapsed | 10445 | +| total_timesteps | 14858240 | +| train/ | | +| approx_kl | 0.0104830535 | +| clip_fraction | 0.35 | +| clip_range | 0.0713 | +| entropy_loss | -7.05 | +| explained_variance | 0.307 | +| learning_rate | 4.65e-05 | +| loss | -0.0404 | +| n_updates | 44836 | +| policy_gradient_loss | -0.0225 | +| value_loss | 0.000144 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1422 | +| iterations | 7256 | +| time_elapsed | 10446 | +| total_timesteps | 14860288 | +| train/ | | +| approx_kl | 0.011198931 | +| clip_fraction | 0.307 | +| clip_range | 0.0713 | +| entropy_loss | -7.15 | +| explained_variance | 0.223 | +| learning_rate | 4.65e-05 | +| loss | -0.0335 | +| n_updates | 44840 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000195 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1422 | +| iterations | 7257 | +| time_elapsed | 10448 | +| total_timesteps | 14862336 | +| train/ | | +| approx_kl | 0.009389204 | +| clip_fraction | 0.327 | +| clip_range | 0.0713 | +| entropy_loss | -6.91 | +| explained_variance | 0.403 | +| learning_rate | 4.65e-05 | +| loss | -0.0317 | +| n_updates | 44844 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000165 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1422 | +| iterations | 7258 | +| time_elapsed | 10449 | +| total_timesteps | 14864384 | +| train/ | | +| approx_kl | 0.011353932 | +| clip_fraction | 0.312 | +| clip_range | 0.0713 | +| entropy_loss | -6.83 | +| explained_variance | 0.363 | +| learning_rate | 4.65e-05 | +| loss | -0.0355 | +| n_updates | 44848 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000187 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1422 | +| iterations | 7259 | +| time_elapsed | 10451 | +| total_timesteps | 14866432 | +| train/ | | +| approx_kl | 0.013788761 | +| clip_fraction | 0.336 | +| clip_range | 0.0713 | +| entropy_loss | -6.66 | +| explained_variance | 0.389 | +| learning_rate | 4.65e-05 | +| loss | -0.0311 | +| n_updates | 44852 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000158 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1422 | +| iterations | 7260 | +| time_elapsed | 10452 | +| total_timesteps | 14868480 | +| train/ | | +| approx_kl | 0.012524517 | +| clip_fraction | 0.351 | +| clip_range | 0.0713 | +| entropy_loss | -6.88 | +| explained_variance | 0.539 | +| learning_rate | 4.65e-05 | +| loss | -0.0346 | +| n_updates | 44856 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000106 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1422 | +| iterations | 7261 | +| time_elapsed | 10453 | +| total_timesteps | 14870528 | +| train/ | | +| approx_kl | 0.010544657 | +| clip_fraction | 0.322 | +| clip_range | 0.0713 | +| entropy_loss | -7.08 | +| explained_variance | 0.15 | +| learning_rate | 4.65e-05 | +| loss | -0.031 | +| n_updates | 44860 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000201 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1422 | +| iterations | 7262 | +| time_elapsed | 10455 | +| total_timesteps | 14872576 | +| train/ | | +| approx_kl | 0.009966769 | +| clip_fraction | 0.301 | +| clip_range | 0.0713 | +| entropy_loss | -6.36 | +| explained_variance | 0.502 | +| learning_rate | 4.65e-05 | +| loss | -0.0232 | +| n_updates | 44864 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.00029 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1422 | +| iterations | 7263 | +| time_elapsed | 10456 | +| total_timesteps | 14874624 | +| train/ | | +| approx_kl | 0.013298796 | +| clip_fraction | 0.353 | +| clip_range | 0.0713 | +| entropy_loss | -6.76 | +| explained_variance | 0.611 | +| learning_rate | 4.65e-05 | +| loss | -0.0353 | +| n_updates | 44868 | +| policy_gradient_loss | -0.0228 | +| value_loss | 0.000105 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1422 | +| iterations | 7264 | +| time_elapsed | 10458 | +| total_timesteps | 14876672 | +| train/ | | +| approx_kl | 0.011784029 | +| clip_fraction | 0.358 | +| clip_range | 0.0713 | +| entropy_loss | -6.84 | +| explained_variance | 0.32 | +| learning_rate | 4.65e-05 | +| loss | -0.0364 | +| n_updates | 44872 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000159 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1422 | +| iterations | 7265 | +| time_elapsed | 10459 | +| total_timesteps | 14878720 | +| train/ | | +| approx_kl | 0.008992406 | +| clip_fraction | 0.304 | +| clip_range | 0.0713 | +| entropy_loss | -6.63 | +| explained_variance | 0.481 | +| learning_rate | 4.65e-05 | +| loss | -0.0274 | +| n_updates | 44876 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000215 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1422 | +| iterations | 7266 | +| time_elapsed | 10461 | +| total_timesteps | 14880768 | +| train/ | | +| approx_kl | 0.010115178 | +| clip_fraction | 0.323 | +| clip_range | 0.0713 | +| entropy_loss | -7.14 | +| explained_variance | 0.0238 | +| learning_rate | 4.65e-05 | +| loss | -0.0287 | +| n_updates | 44880 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000365 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1422 | +| iterations | 7267 | +| time_elapsed | 10462 | +| total_timesteps | 14882816 | +| train/ | | +| approx_kl | 0.012305949 | +| clip_fraction | 0.383 | +| clip_range | 0.0713 | +| entropy_loss | -6.93 | +| explained_variance | 0.296 | +| learning_rate | 4.65e-05 | +| loss | -0.0424 | +| n_updates | 44884 | +| policy_gradient_loss | -0.0253 | +| value_loss | 9.41e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1422 | +| iterations | 7268 | +| time_elapsed | 10464 | +| total_timesteps | 14884864 | +| train/ | | +| approx_kl | 0.011326539 | +| clip_fraction | 0.322 | +| clip_range | 0.0713 | +| entropy_loss | -6.67 | +| explained_variance | 0.314 | +| learning_rate | 4.65e-05 | +| loss | -0.0298 | +| n_updates | 44888 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000359 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1422 | +| iterations | 7269 | +| time_elapsed | 10465 | +| total_timesteps | 14886912 | +| train/ | | +| approx_kl | 0.014618506 | +| clip_fraction | 0.37 | +| clip_range | 0.0713 | +| entropy_loss | -6.68 | +| explained_variance | 0.537 | +| learning_rate | 4.65e-05 | +| loss | -0.037 | +| n_updates | 44892 | +| policy_gradient_loss | -0.0239 | +| value_loss | 0.00014 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1422 | +| iterations | 7270 | +| time_elapsed | 10466 | +| total_timesteps | 14888960 | +| train/ | | +| approx_kl | 0.014271904 | +| clip_fraction | 0.401 | +| clip_range | 0.0713 | +| entropy_loss | -7.06 | +| explained_variance | -0.752 | +| learning_rate | 4.65e-05 | +| loss | -0.038 | +| n_updates | 44896 | +| policy_gradient_loss | -0.0267 | +| value_loss | 6.81e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1422 | +| iterations | 7271 | +| time_elapsed | 10468 | +| total_timesteps | 14891008 | +| train/ | | +| approx_kl | 0.011359669 | +| clip_fraction | 0.356 | +| clip_range | 0.0713 | +| entropy_loss | -7.25 | +| explained_variance | -0.127 | +| learning_rate | 4.65e-05 | +| loss | -0.0428 | +| n_updates | 44900 | +| policy_gradient_loss | -0.022 | +| value_loss | 0.000105 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1422 | +| iterations | 7272 | +| time_elapsed | 10469 | +| total_timesteps | 14893056 | +| train/ | | +| approx_kl | 0.012893409 | +| clip_fraction | 0.315 | +| clip_range | 0.0713 | +| entropy_loss | -6.87 | +| explained_variance | 0.545 | +| learning_rate | 4.65e-05 | +| loss | -0.0307 | +| n_updates | 44904 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000113 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1422 | +| iterations | 7273 | +| time_elapsed | 10471 | +| total_timesteps | 14895104 | +| train/ | | +| approx_kl | 0.013832349 | +| clip_fraction | 0.324 | +| clip_range | 0.0713 | +| entropy_loss | -6.79 | +| explained_variance | 0.42 | +| learning_rate | 4.65e-05 | +| loss | -0.0265 | +| n_updates | 44908 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1422 | +| iterations | 7274 | +| time_elapsed | 10472 | +| total_timesteps | 14897152 | +| train/ | | +| approx_kl | 0.012645827 | +| clip_fraction | 0.347 | +| clip_range | 0.0713 | +| entropy_loss | -6.43 | +| explained_variance | 0.583 | +| learning_rate | 4.65e-05 | +| loss | -0.026 | +| n_updates | 44912 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000179 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1422 | +| iterations | 7275 | +| time_elapsed | 10474 | +| total_timesteps | 14899200 | +| train/ | | +| approx_kl | 0.010992417 | +| clip_fraction | 0.335 | +| clip_range | 0.0713 | +| entropy_loss | -6.79 | +| explained_variance | 0.475 | +| learning_rate | 4.65e-05 | +| loss | -0.0302 | +| n_updates | 44916 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000158 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1422 | +| iterations | 7276 | +| time_elapsed | 10475 | +| total_timesteps | 14901248 | +| train/ | | +| approx_kl | 0.011711107 | +| clip_fraction | 0.349 | +| clip_range | 0.0713 | +| entropy_loss | -6.53 | +| explained_variance | 0.838 | +| learning_rate | 4.65e-05 | +| loss | -0.0365 | +| n_updates | 44920 | +| policy_gradient_loss | -0.0258 | +| value_loss | 4.84e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1422 | +| iterations | 7277 | +| time_elapsed | 10477 | +| total_timesteps | 14903296 | +| train/ | | +| approx_kl | 0.011611189 | +| clip_fraction | 0.306 | +| clip_range | 0.0713 | +| entropy_loss | -6.94 | +| explained_variance | -0.0474 | +| learning_rate | 4.65e-05 | +| loss | -0.0294 | +| n_updates | 44924 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.00012 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1422 | +| iterations | 7278 | +| time_elapsed | 10478 | +| total_timesteps | 14905344 | +| train/ | | +| approx_kl | 0.012099175 | +| clip_fraction | 0.333 | +| clip_range | 0.0713 | +| entropy_loss | -7.12 | +| explained_variance | 0.00937 | +| learning_rate | 4.65e-05 | +| loss | -0.0308 | +| n_updates | 44928 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000209 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1422 | +| iterations | 7279 | +| time_elapsed | 10479 | +| total_timesteps | 14907392 | +| train/ | | +| approx_kl | 0.009809887 | +| clip_fraction | 0.316 | +| clip_range | 0.0713 | +| entropy_loss | -7.22 | +| explained_variance | -0.0629 | +| learning_rate | 4.65e-05 | +| loss | -0.0321 | +| n_updates | 44932 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000237 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1422 | +| iterations | 7280 | +| time_elapsed | 10481 | +| total_timesteps | 14909440 | +| train/ | | +| approx_kl | 0.011792976 | +| clip_fraction | 0.331 | +| clip_range | 0.0713 | +| entropy_loss | -6.46 | +| explained_variance | 0.681 | +| learning_rate | 4.65e-05 | +| loss | -0.0316 | +| n_updates | 44936 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000126 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1422 | +| iterations | 7281 | +| time_elapsed | 10482 | +| total_timesteps | 14911488 | +| train/ | | +| approx_kl | 0.009618217 | +| clip_fraction | 0.332 | +| clip_range | 0.0713 | +| entropy_loss | -7.25 | +| explained_variance | 0.179 | +| learning_rate | 4.65e-05 | +| loss | -0.0318 | +| n_updates | 44940 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000105 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1422 | +| iterations | 7282 | +| time_elapsed | 10484 | +| total_timesteps | 14913536 | +| train/ | | +| approx_kl | 0.010933245 | +| clip_fraction | 0.284 | +| clip_range | 0.0713 | +| entropy_loss | -6.71 | +| explained_variance | 0.408 | +| learning_rate | 4.65e-05 | +| loss | -0.028 | +| n_updates | 44944 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000242 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1422 | +| iterations | 7283 | +| time_elapsed | 10485 | +| total_timesteps | 14915584 | +| train/ | | +| approx_kl | 0.0098208785 | +| clip_fraction | 0.305 | +| clip_range | 0.0713 | +| entropy_loss | -6.25 | +| explained_variance | 0.591 | +| learning_rate | 4.65e-05 | +| loss | -0.0238 | +| n_updates | 44948 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000207 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1422 | +| iterations | 7284 | +| time_elapsed | 10487 | +| total_timesteps | 14917632 | +| train/ | | +| approx_kl | 0.009521278 | +| clip_fraction | 0.326 | +| clip_range | 0.0713 | +| entropy_loss | -6.74 | +| explained_variance | 0.54 | +| learning_rate | 4.65e-05 | +| loss | -0.0336 | +| n_updates | 44952 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000129 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1422 | +| iterations | 7285 | +| time_elapsed | 10488 | +| total_timesteps | 14919680 | +| train/ | | +| approx_kl | 0.010423064 | +| clip_fraction | 0.316 | +| clip_range | 0.0713 | +| entropy_loss | -7.23 | +| explained_variance | -0.115 | +| learning_rate | 4.65e-05 | +| loss | -0.0319 | +| n_updates | 44956 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000258 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1422 | +| iterations | 7286 | +| time_elapsed | 10490 | +| total_timesteps | 14921728 | +| train/ | | +| approx_kl | 0.009889408 | +| clip_fraction | 0.307 | +| clip_range | 0.0713 | +| entropy_loss | -6.79 | +| explained_variance | 0.376 | +| learning_rate | 4.65e-05 | +| loss | -0.023 | +| n_updates | 44960 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000253 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1422 | +| iterations | 7287 | +| time_elapsed | 10491 | +| total_timesteps | 14923776 | +| train/ | | +| approx_kl | 0.011525705 | +| clip_fraction | 0.331 | +| clip_range | 0.0713 | +| entropy_loss | -6.85 | +| explained_variance | 0.35 | +| learning_rate | 4.65e-05 | +| loss | -0.0322 | +| n_updates | 44964 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000262 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1422 | +| iterations | 7288 | +| time_elapsed | 10493 | +| total_timesteps | 14925824 | +| train/ | | +| approx_kl | 0.010582839 | +| clip_fraction | 0.328 | +| clip_range | 0.0713 | +| entropy_loss | -7.32 | +| explained_variance | 0.0164 | +| learning_rate | 4.65e-05 | +| loss | -0.0324 | +| n_updates | 44968 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.00022 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1422 | +| iterations | 7289 | +| time_elapsed | 10494 | +| total_timesteps | 14927872 | +| train/ | | +| approx_kl | 0.009941196 | +| clip_fraction | 0.324 | +| clip_range | 0.0713 | +| entropy_loss | -6.81 | +| explained_variance | 0.337 | +| learning_rate | 4.65e-05 | +| loss | -0.0233 | +| n_updates | 44972 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.00037 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1422 | +| iterations | 7290 | +| time_elapsed | 10496 | +| total_timesteps | 14929920 | +| train/ | | +| approx_kl | 0.012622229 | +| clip_fraction | 0.321 | +| clip_range | 0.0713 | +| entropy_loss | -6.73 | +| explained_variance | 0.478 | +| learning_rate | 4.65e-05 | +| loss | -0.0282 | +| n_updates | 44976 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000181 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1422 | +| iterations | 7291 | +| time_elapsed | 10497 | +| total_timesteps | 14931968 | +| train/ | | +| approx_kl | 0.010887707 | +| clip_fraction | 0.319 | +| clip_range | 0.0713 | +| entropy_loss | -6.89 | +| explained_variance | 0.376 | +| learning_rate | 4.65e-05 | +| loss | -0.0264 | +| n_updates | 44980 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.00022 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1422 | +| iterations | 7292 | +| time_elapsed | 10498 | +| total_timesteps | 14934016 | +| train/ | | +| approx_kl | 0.009582424 | +| clip_fraction | 0.314 | +| clip_range | 0.0713 | +| entropy_loss | -7.02 | +| explained_variance | 0.171 | +| learning_rate | 4.65e-05 | +| loss | -0.0281 | +| n_updates | 44984 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.00033 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1422 | +| iterations | 7293 | +| time_elapsed | 10500 | +| total_timesteps | 14936064 | +| train/ | | +| approx_kl | 0.0112763345 | +| clip_fraction | 0.338 | +| clip_range | 0.0713 | +| entropy_loss | -6.78 | +| explained_variance | 0.462 | +| learning_rate | 4.65e-05 | +| loss | -0.0356 | +| n_updates | 44988 | +| policy_gradient_loss | -0.0222 | +| value_loss | 0.000154 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1422 | +| iterations | 7294 | +| time_elapsed | 10501 | +| total_timesteps | 14938112 | +| train/ | | +| approx_kl | 0.012153684 | +| clip_fraction | 0.325 | +| clip_range | 0.0713 | +| entropy_loss | -6.78 | +| explained_variance | 0.437 | +| learning_rate | 4.65e-05 | +| loss | -0.0407 | +| n_updates | 44992 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000209 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1422 | +| iterations | 7295 | +| time_elapsed | 10503 | +| total_timesteps | 14940160 | +| train/ | | +| approx_kl | 0.011978298 | +| clip_fraction | 0.31 | +| clip_range | 0.0713 | +| entropy_loss | -6.61 | +| explained_variance | 0.386 | +| learning_rate | 4.65e-05 | +| loss | -0.0262 | +| n_updates | 44996 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000304 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1422 | +| iterations | 7296 | +| time_elapsed | 10504 | +| total_timesteps | 14942208 | +| train/ | | +| approx_kl | 0.011642098 | +| clip_fraction | 0.317 | +| clip_range | 0.0713 | +| entropy_loss | -6.64 | +| explained_variance | 0.239 | +| learning_rate | 4.65e-05 | +| loss | -0.0249 | +| n_updates | 45000 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000296 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1422 | +| iterations | 7297 | +| time_elapsed | 10506 | +| total_timesteps | 14944256 | +| train/ | | +| approx_kl | 0.014335948 | +| clip_fraction | 0.335 | +| clip_range | 0.0713 | +| entropy_loss | -6.86 | +| explained_variance | 0.11 | +| learning_rate | 4.65e-05 | +| loss | -0.0339 | +| n_updates | 45004 | +| policy_gradient_loss | -0.0219 | +| value_loss | 0.000169 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1422 | +| iterations | 7298 | +| time_elapsed | 10507 | +| total_timesteps | 14946304 | +| train/ | | +| approx_kl | 0.011220501 | +| clip_fraction | 0.303 | +| clip_range | 0.0713 | +| entropy_loss | -7.1 | +| explained_variance | 0.104 | +| learning_rate | 4.65e-05 | +| loss | -0.0239 | +| n_updates | 45008 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000305 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1422 | +| iterations | 7299 | +| time_elapsed | 10508 | +| total_timesteps | 14948352 | +| train/ | | +| approx_kl | 0.012008438 | +| clip_fraction | 0.368 | +| clip_range | 0.0713 | +| entropy_loss | -7.08 | +| explained_variance | 0.172 | +| learning_rate | 4.65e-05 | +| loss | -0.0398 | +| n_updates | 45012 | +| policy_gradient_loss | -0.0237 | +| value_loss | 0.00014 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1422 | +| iterations | 7300 | +| time_elapsed | 10510 | +| total_timesteps | 14950400 | +| train/ | | +| approx_kl | 0.012982123 | +| clip_fraction | 0.336 | +| clip_range | 0.0713 | +| entropy_loss | -6.77 | +| explained_variance | 0.11 | +| learning_rate | 4.64e-05 | +| loss | -0.0345 | +| n_updates | 45016 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000278 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1422 | +| iterations | 7301 | +| time_elapsed | 10511 | +| total_timesteps | 14952448 | +| train/ | | +| approx_kl | 0.013385173 | +| clip_fraction | 0.351 | +| clip_range | 0.0713 | +| entropy_loss | -6.47 | +| explained_variance | 0.474 | +| learning_rate | 4.64e-05 | +| loss | -0.0316 | +| n_updates | 45020 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000208 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1422 | +| iterations | 7302 | +| time_elapsed | 10513 | +| total_timesteps | 14954496 | +| train/ | | +| approx_kl | 0.013770796 | +| clip_fraction | 0.349 | +| clip_range | 0.0713 | +| entropy_loss | -6.45 | +| explained_variance | 0.524 | +| learning_rate | 4.64e-05 | +| loss | -0.0297 | +| n_updates | 45024 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.00015 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1422 | +| iterations | 7303 | +| time_elapsed | 10514 | +| total_timesteps | 14956544 | +| train/ | | +| approx_kl | 0.013391606 | +| clip_fraction | 0.364 | +| clip_range | 0.0713 | +| entropy_loss | -6.5 | +| explained_variance | 0.417 | +| learning_rate | 4.64e-05 | +| loss | -0.0306 | +| n_updates | 45028 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000126 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1422 | +| iterations | 7304 | +| time_elapsed | 10516 | +| total_timesteps | 14958592 | +| train/ | | +| approx_kl | 0.013869512 | +| clip_fraction | 0.324 | +| clip_range | 0.0713 | +| entropy_loss | -6.93 | +| explained_variance | 0.223 | +| learning_rate | 4.64e-05 | +| loss | -0.0282 | +| n_updates | 45032 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.00018 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1422 | +| iterations | 7305 | +| time_elapsed | 10517 | +| total_timesteps | 14960640 | +| train/ | | +| approx_kl | 0.009427136 | +| clip_fraction | 0.302 | +| clip_range | 0.0713 | +| entropy_loss | -7.3 | +| explained_variance | -0.0495 | +| learning_rate | 4.64e-05 | +| loss | -0.0331 | +| n_updates | 45036 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.00017 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1422 | +| iterations | 7306 | +| time_elapsed | 10519 | +| total_timesteps | 14962688 | +| train/ | | +| approx_kl | 0.009383779 | +| clip_fraction | 0.302 | +| clip_range | 0.0713 | +| entropy_loss | -7.07 | +| explained_variance | 0.275 | +| learning_rate | 4.64e-05 | +| loss | -0.0283 | +| n_updates | 45040 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000118 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1422 | +| iterations | 7307 | +| time_elapsed | 10520 | +| total_timesteps | 14964736 | +| train/ | | +| approx_kl | 0.013459523 | +| clip_fraction | 0.335 | +| clip_range | 0.0713 | +| entropy_loss | -7.03 | +| explained_variance | 0.259 | +| learning_rate | 4.64e-05 | +| loss | -0.033 | +| n_updates | 45044 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000133 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1422 | +| iterations | 7308 | +| time_elapsed | 10522 | +| total_timesteps | 14966784 | +| train/ | | +| approx_kl | 0.010684298 | +| clip_fraction | 0.327 | +| clip_range | 0.0713 | +| entropy_loss | -6.89 | +| explained_variance | 0.427 | +| learning_rate | 4.64e-05 | +| loss | -0.0274 | +| n_updates | 45048 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.00017 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1422 | +| iterations | 7309 | +| time_elapsed | 10523 | +| total_timesteps | 14968832 | +| train/ | | +| approx_kl | 0.00861928 | +| clip_fraction | 0.313 | +| clip_range | 0.0713 | +| entropy_loss | -6.96 | +| explained_variance | 0.6 | +| learning_rate | 4.64e-05 | +| loss | -0.0358 | +| n_updates | 45052 | +| policy_gradient_loss | -0.0209 | +| value_loss | 6.28e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1422 | +| iterations | 7310 | +| time_elapsed | 10525 | +| total_timesteps | 14970880 | +| train/ | | +| approx_kl | 0.010019111 | +| clip_fraction | 0.31 | +| clip_range | 0.0713 | +| entropy_loss | -7.1 | +| explained_variance | 0.221 | +| learning_rate | 4.64e-05 | +| loss | -0.0244 | +| n_updates | 45056 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000166 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1422 | +| iterations | 7311 | +| time_elapsed | 10526 | +| total_timesteps | 14972928 | +| train/ | | +| approx_kl | 0.013828022 | +| clip_fraction | 0.322 | +| clip_range | 0.0713 | +| entropy_loss | -6.49 | +| explained_variance | 0.534 | +| learning_rate | 4.64e-05 | +| loss | -0.0216 | +| n_updates | 45060 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000219 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1422 | +| iterations | 7312 | +| time_elapsed | 10528 | +| total_timesteps | 14974976 | +| train/ | | +| approx_kl | 0.00975091 | +| clip_fraction | 0.295 | +| clip_range | 0.0713 | +| entropy_loss | -6.6 | +| explained_variance | 0.477 | +| learning_rate | 4.64e-05 | +| loss | -0.0312 | +| n_updates | 45064 | +| policy_gradient_loss | -0.0144 | +| value_loss | 0.000243 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1422 | +| iterations | 7313 | +| time_elapsed | 10529 | +| total_timesteps | 14977024 | +| train/ | | +| approx_kl | 0.012176512 | +| clip_fraction | 0.34 | +| clip_range | 0.0713 | +| entropy_loss | -6.95 | +| explained_variance | 0.0405 | +| learning_rate | 4.64e-05 | +| loss | -0.0264 | +| n_updates | 45068 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000166 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1422 | +| iterations | 7314 | +| time_elapsed | 10531 | +| total_timesteps | 14979072 | +| train/ | | +| approx_kl | 0.0141070895 | +| clip_fraction | 0.341 | +| clip_range | 0.0713 | +| entropy_loss | -7.04 | +| explained_variance | 0.254 | +| learning_rate | 4.64e-05 | +| loss | -0.0339 | +| n_updates | 45072 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.00017 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1422 | +| iterations | 7315 | +| time_elapsed | 10532 | +| total_timesteps | 14981120 | +| train/ | | +| approx_kl | 0.013100866 | +| clip_fraction | 0.324 | +| clip_range | 0.0713 | +| entropy_loss | -6.69 | +| explained_variance | 0.405 | +| learning_rate | 4.64e-05 | +| loss | -0.0314 | +| n_updates | 45076 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000185 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1422 | +| iterations | 7316 | +| time_elapsed | 10533 | +| total_timesteps | 14983168 | +| train/ | | +| approx_kl | 0.011682929 | +| clip_fraction | 0.327 | +| clip_range | 0.0713 | +| entropy_loss | -7.02 | +| explained_variance | 0.264 | +| learning_rate | 4.64e-05 | +| loss | -0.0344 | +| n_updates | 45080 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000184 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1422 | +| iterations | 7317 | +| time_elapsed | 10535 | +| total_timesteps | 14985216 | +| train/ | | +| approx_kl | 0.010887151 | +| clip_fraction | 0.311 | +| clip_range | 0.0713 | +| entropy_loss | -7.2 | +| explained_variance | -0.0844 | +| learning_rate | 4.64e-05 | +| loss | -0.0319 | +| n_updates | 45084 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000269 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1422 | +| iterations | 7318 | +| time_elapsed | 10536 | +| total_timesteps | 14987264 | +| train/ | | +| approx_kl | 0.011390364 | +| clip_fraction | 0.327 | +| clip_range | 0.0713 | +| entropy_loss | -6.76 | +| explained_variance | 0.537 | +| learning_rate | 4.64e-05 | +| loss | -0.0366 | +| n_updates | 45088 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000121 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1422 | +| iterations | 7319 | +| time_elapsed | 10538 | +| total_timesteps | 14989312 | +| train/ | | +| approx_kl | 0.010531778 | +| clip_fraction | 0.324 | +| clip_range | 0.0713 | +| entropy_loss | -7.02 | +| explained_variance | 0.295 | +| learning_rate | 4.64e-05 | +| loss | -0.0231 | +| n_updates | 45092 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000179 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1422 | +| iterations | 7320 | +| time_elapsed | 10539 | +| total_timesteps | 14991360 | +| train/ | | +| approx_kl | 0.012190245 | +| clip_fraction | 0.336 | +| clip_range | 0.0713 | +| entropy_loss | -6.83 | +| explained_variance | 0.498 | +| learning_rate | 4.64e-05 | +| loss | -0.0296 | +| n_updates | 45096 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000121 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1422 | +| iterations | 7321 | +| time_elapsed | 10540 | +| total_timesteps | 14993408 | +| train/ | | +| approx_kl | 0.011110194 | +| clip_fraction | 0.316 | +| clip_range | 0.0713 | +| entropy_loss | -6.77 | +| explained_variance | 0.587 | +| learning_rate | 4.64e-05 | +| loss | -0.0316 | +| n_updates | 45100 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000132 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1422 | +| iterations | 7322 | +| time_elapsed | 10542 | +| total_timesteps | 14995456 | +| train/ | | +| approx_kl | 0.010460457 | +| clip_fraction | 0.323 | +| clip_range | 0.0713 | +| entropy_loss | -6.75 | +| explained_variance | 0.485 | +| learning_rate | 4.64e-05 | +| loss | -0.0337 | +| n_updates | 45104 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000132 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1422 | +| iterations | 7323 | +| time_elapsed | 10543 | +| total_timesteps | 14997504 | +| train/ | | +| approx_kl | 0.010769549 | +| clip_fraction | 0.337 | +| clip_range | 0.0713 | +| entropy_loss | -7.08 | +| explained_variance | 0.454 | +| learning_rate | 4.64e-05 | +| loss | -0.0309 | +| n_updates | 45108 | +| policy_gradient_loss | -0.021 | +| value_loss | 9.06e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1422 | +| iterations | 7324 | +| time_elapsed | 10545 | +| total_timesteps | 14999552 | +| train/ | | +| approx_kl | 0.009188927 | +| clip_fraction | 0.3 | +| clip_range | 0.0713 | +| entropy_loss | -7.04 | +| explained_variance | 0.248 | +| learning_rate | 4.64e-05 | +| loss | -0.0311 | +| n_updates | 45112 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000233 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1422 | +| iterations | 7325 | +| time_elapsed | 10546 | +| total_timesteps | 15001600 | +| train/ | | +| approx_kl | 0.011627346 | +| clip_fraction | 0.334 | +| clip_range | 0.0713 | +| entropy_loss | -6.88 | +| explained_variance | 0.481 | +| learning_rate | 4.64e-05 | +| loss | -0.0353 | +| n_updates | 45116 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000146 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1422 | +| iterations | 7326 | +| time_elapsed | 10548 | +| total_timesteps | 15003648 | +| train/ | | +| approx_kl | 0.01236493 | +| clip_fraction | 0.319 | +| clip_range | 0.0712 | +| entropy_loss | -6.58 | +| explained_variance | 0.324 | +| learning_rate | 4.64e-05 | +| loss | -0.0274 | +| n_updates | 45120 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000386 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1422 | +| iterations | 7327 | +| time_elapsed | 10549 | +| total_timesteps | 15005696 | +| train/ | | +| approx_kl | 0.010724642 | +| clip_fraction | 0.315 | +| clip_range | 0.0712 | +| entropy_loss | -6.59 | +| explained_variance | 0.27 | +| learning_rate | 4.64e-05 | +| loss | -0.0297 | +| n_updates | 45124 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000209 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1422 | +| iterations | 7328 | +| time_elapsed | 10551 | +| total_timesteps | 15007744 | +| train/ | | +| approx_kl | 0.01035404 | +| clip_fraction | 0.321 | +| clip_range | 0.0712 | +| entropy_loss | -6.82 | +| explained_variance | 0.13 | +| learning_rate | 4.64e-05 | +| loss | -0.0331 | +| n_updates | 45128 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000427 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1422 | +| iterations | 7329 | +| time_elapsed | 10552 | +| total_timesteps | 15009792 | +| train/ | | +| approx_kl | 0.012875797 | +| clip_fraction | 0.335 | +| clip_range | 0.0712 | +| entropy_loss | -7.01 | +| explained_variance | 0.191 | +| learning_rate | 4.64e-05 | +| loss | -0.0363 | +| n_updates | 45132 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000156 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.384 | +| time/ | | +| fps | 1422 | +| iterations | 7330 | +| time_elapsed | 10554 | +| total_timesteps | 15011840 | +| train/ | | +| approx_kl | 0.009973584 | +| clip_fraction | 0.333 | +| clip_range | 0.0712 | +| entropy_loss | -7.3 | +| explained_variance | -0.12 | +| learning_rate | 4.64e-05 | +| loss | -0.0373 | +| n_updates | 45136 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.00013 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1422 | +| iterations | 7331 | +| time_elapsed | 10555 | +| total_timesteps | 15013888 | +| train/ | | +| approx_kl | 0.009418527 | +| clip_fraction | 0.291 | +| clip_range | 0.0712 | +| entropy_loss | -7 | +| explained_variance | 0.143 | +| learning_rate | 4.64e-05 | +| loss | -0.0241 | +| n_updates | 45140 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000467 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.385 | +| time/ | | +| fps | 1422 | +| iterations | 7332 | +| time_elapsed | 10557 | +| total_timesteps | 15015936 | +| train/ | | +| approx_kl | 0.01245014 | +| clip_fraction | 0.363 | +| clip_range | 0.0712 | +| entropy_loss | -6.55 | +| explained_variance | 0.536 | +| learning_rate | 4.64e-05 | +| loss | -0.0323 | +| n_updates | 45144 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000146 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.389 | +| time/ | | +| fps | 1422 | +| iterations | 7333 | +| time_elapsed | 10558 | +| total_timesteps | 15017984 | +| train/ | | +| approx_kl | 0.010245241 | +| clip_fraction | 0.343 | +| clip_range | 0.0712 | +| entropy_loss | -7.07 | +| explained_variance | 0.14 | +| learning_rate | 4.64e-05 | +| loss | -0.0374 | +| n_updates | 45148 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000355 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.391 | +| time/ | | +| fps | 1422 | +| iterations | 7334 | +| time_elapsed | 10559 | +| total_timesteps | 15020032 | +| train/ | | +| approx_kl | 0.010917433 | +| clip_fraction | 0.316 | +| clip_range | 0.0712 | +| entropy_loss | -7.17 | +| explained_variance | 0.116 | +| learning_rate | 4.64e-05 | +| loss | -0.0293 | +| n_updates | 45152 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.00027 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.389 | +| time/ | | +| fps | 1422 | +| iterations | 7335 | +| time_elapsed | 10561 | +| total_timesteps | 15022080 | +| train/ | | +| approx_kl | 0.011926908 | +| clip_fraction | 0.348 | +| clip_range | 0.0712 | +| entropy_loss | -6.78 | +| explained_variance | 0.308 | +| learning_rate | 4.64e-05 | +| loss | -0.0344 | +| n_updates | 45156 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000291 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.395 | +| time/ | | +| fps | 1422 | +| iterations | 7336 | +| time_elapsed | 10562 | +| total_timesteps | 15024128 | +| train/ | | +| approx_kl | 0.01090695 | +| clip_fraction | 0.333 | +| clip_range | 0.0712 | +| entropy_loss | -6.93 | +| explained_variance | 0.481 | +| learning_rate | 4.64e-05 | +| loss | -0.0355 | +| n_updates | 45160 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000141 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.395 | +| time/ | | +| fps | 1422 | +| iterations | 7337 | +| time_elapsed | 10564 | +| total_timesteps | 15026176 | +| train/ | | +| approx_kl | 0.010798321 | +| clip_fraction | 0.305 | +| clip_range | 0.0712 | +| entropy_loss | -6.44 | +| explained_variance | 0.529 | +| learning_rate | 4.64e-05 | +| loss | -0.0305 | +| n_updates | 45164 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000241 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.395 | +| time/ | | +| fps | 1422 | +| iterations | 7338 | +| time_elapsed | 10565 | +| total_timesteps | 15028224 | +| train/ | | +| approx_kl | 0.010517826 | +| clip_fraction | 0.315 | +| clip_range | 0.0712 | +| entropy_loss | -7.07 | +| explained_variance | -0.0749 | +| learning_rate | 4.64e-05 | +| loss | -0.0316 | +| n_updates | 45168 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.00011 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.395 | +| time/ | | +| fps | 1422 | +| iterations | 7339 | +| time_elapsed | 10567 | +| total_timesteps | 15030272 | +| train/ | | +| approx_kl | 0.009309918 | +| clip_fraction | 0.302 | +| clip_range | 0.0712 | +| entropy_loss | -6.84 | +| explained_variance | 0.358 | +| learning_rate | 4.64e-05 | +| loss | -0.0318 | +| n_updates | 45172 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000295 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.395 | +| time/ | | +| fps | 1422 | +| iterations | 7340 | +| time_elapsed | 10568 | +| total_timesteps | 15032320 | +| train/ | | +| approx_kl | 0.013797902 | +| clip_fraction | 0.338 | +| clip_range | 0.0712 | +| entropy_loss | -7.12 | +| explained_variance | -0.0878 | +| learning_rate | 4.64e-05 | +| loss | -0.0302 | +| n_updates | 45176 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000146 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.389 | +| time/ | | +| fps | 1422 | +| iterations | 7341 | +| time_elapsed | 10569 | +| total_timesteps | 15034368 | +| train/ | | +| approx_kl | 0.011543691 | +| clip_fraction | 0.338 | +| clip_range | 0.0712 | +| entropy_loss | -7.22 | +| explained_variance | -0.233 | +| learning_rate | 4.64e-05 | +| loss | -0.0372 | +| n_updates | 45180 | +| policy_gradient_loss | -0.0223 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.395 | +| time/ | | +| fps | 1422 | +| iterations | 7342 | +| time_elapsed | 10571 | +| total_timesteps | 15036416 | +| train/ | | +| approx_kl | 0.012304183 | +| clip_fraction | 0.338 | +| clip_range | 0.0712 | +| entropy_loss | -7.03 | +| explained_variance | 0.203 | +| learning_rate | 4.64e-05 | +| loss | -0.0268 | +| n_updates | 45184 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000261 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.397 | +| time/ | | +| fps | 1422 | +| iterations | 7343 | +| time_elapsed | 10572 | +| total_timesteps | 15038464 | +| train/ | | +| approx_kl | 0.010469828 | +| clip_fraction | 0.314 | +| clip_range | 0.0712 | +| entropy_loss | -6.41 | +| explained_variance | 0.718 | +| learning_rate | 4.64e-05 | +| loss | -0.0326 | +| n_updates | 45188 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000112 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.399 | +| time/ | | +| fps | 1422 | +| iterations | 7344 | +| time_elapsed | 10574 | +| total_timesteps | 15040512 | +| train/ | | +| approx_kl | 0.011008578 | +| clip_fraction | 0.325 | +| clip_range | 0.0712 | +| entropy_loss | -6.34 | +| explained_variance | 0.566 | +| learning_rate | 4.64e-05 | +| loss | -0.0294 | +| n_updates | 45192 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000216 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.396 | +| time/ | | +| fps | 1422 | +| iterations | 7345 | +| time_elapsed | 10575 | +| total_timesteps | 15042560 | +| train/ | | +| approx_kl | 0.010601211 | +| clip_fraction | 0.321 | +| clip_range | 0.0712 | +| entropy_loss | -6.95 | +| explained_variance | 0.332 | +| learning_rate | 4.64e-05 | +| loss | -0.0311 | +| n_updates | 45196 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000157 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.398 | +| time/ | | +| fps | 1422 | +| iterations | 7346 | +| time_elapsed | 10577 | +| total_timesteps | 15044608 | +| train/ | | +| approx_kl | 0.008509019 | +| clip_fraction | 0.328 | +| clip_range | 0.0712 | +| entropy_loss | -7.1 | +| explained_variance | 0.328 | +| learning_rate | 4.64e-05 | +| loss | -0.0286 | +| n_updates | 45200 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000137 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.395 | +| time/ | | +| fps | 1422 | +| iterations | 7347 | +| time_elapsed | 10578 | +| total_timesteps | 15046656 | +| train/ | | +| approx_kl | 0.008593049 | +| clip_fraction | 0.284 | +| clip_range | 0.0712 | +| entropy_loss | -6.72 | +| explained_variance | 0.271 | +| learning_rate | 4.64e-05 | +| loss | -0.0262 | +| n_updates | 45204 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000516 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.388 | +| time/ | | +| fps | 1422 | +| iterations | 7348 | +| time_elapsed | 10579 | +| total_timesteps | 15048704 | +| train/ | | +| approx_kl | 0.010806691 | +| clip_fraction | 0.34 | +| clip_range | 0.0712 | +| entropy_loss | -6.62 | +| explained_variance | 0.538 | +| learning_rate | 4.64e-05 | +| loss | -0.0318 | +| n_updates | 45208 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000172 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.386 | +| time/ | | +| fps | 1422 | +| iterations | 7349 | +| time_elapsed | 10581 | +| total_timesteps | 15050752 | +| train/ | | +| approx_kl | 0.009816615 | +| clip_fraction | 0.303 | +| clip_range | 0.0712 | +| entropy_loss | -6.75 | +| explained_variance | 0.438 | +| learning_rate | 4.64e-05 | +| loss | -0.0264 | +| n_updates | 45212 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000236 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1422 | +| iterations | 7350 | +| time_elapsed | 10582 | +| total_timesteps | 15052800 | +| train/ | | +| approx_kl | 0.011238282 | +| clip_fraction | 0.331 | +| clip_range | 0.0712 | +| entropy_loss | -7.05 | +| explained_variance | 0.0984 | +| learning_rate | 4.64e-05 | +| loss | -0.0348 | +| n_updates | 45216 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000189 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.386 | +| time/ | | +| fps | 1422 | +| iterations | 7351 | +| time_elapsed | 10584 | +| total_timesteps | 15054848 | +| train/ | | +| approx_kl | 0.009544024 | +| clip_fraction | 0.318 | +| clip_range | 0.0712 | +| entropy_loss | -6.84 | +| explained_variance | 0.45 | +| learning_rate | 4.64e-05 | +| loss | -0.0347 | +| n_updates | 45220 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000204 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.389 | +| time/ | | +| fps | 1422 | +| iterations | 7352 | +| time_elapsed | 10585 | +| total_timesteps | 15056896 | +| train/ | | +| approx_kl | 0.009813909 | +| clip_fraction | 0.306 | +| clip_range | 0.0712 | +| entropy_loss | -7.21 | +| explained_variance | -0.0316 | +| learning_rate | 4.64e-05 | +| loss | -0.0304 | +| n_updates | 45224 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000216 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.386 | +| time/ | | +| fps | 1422 | +| iterations | 7353 | +| time_elapsed | 10587 | +| total_timesteps | 15058944 | +| train/ | | +| approx_kl | 0.011150304 | +| clip_fraction | 0.296 | +| clip_range | 0.0712 | +| entropy_loss | -6.87 | +| explained_variance | 0.325 | +| learning_rate | 4.64e-05 | +| loss | -0.0279 | +| n_updates | 45228 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000322 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.391 | +| time/ | | +| fps | 1422 | +| iterations | 7354 | +| time_elapsed | 10588 | +| total_timesteps | 15060992 | +| train/ | | +| approx_kl | 0.011306126 | +| clip_fraction | 0.353 | +| clip_range | 0.0712 | +| entropy_loss | -7.06 | +| explained_variance | 0.442 | +| learning_rate | 4.64e-05 | +| loss | -0.0333 | +| n_updates | 45232 | +| policy_gradient_loss | -0.023 | +| value_loss | 9.42e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1422 | +| iterations | 7355 | +| time_elapsed | 10589 | +| total_timesteps | 15063040 | +| train/ | | +| approx_kl | 0.011648368 | +| clip_fraction | 0.297 | +| clip_range | 0.0712 | +| entropy_loss | -6.72 | +| explained_variance | 0.367 | +| learning_rate | 4.64e-05 | +| loss | -0.0268 | +| n_updates | 45236 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000358 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.391 | +| time/ | | +| fps | 1422 | +| iterations | 7356 | +| time_elapsed | 10591 | +| total_timesteps | 15065088 | +| train/ | | +| approx_kl | 0.011148602 | +| clip_fraction | 0.323 | +| clip_range | 0.0712 | +| entropy_loss | -6.8 | +| explained_variance | 0.405 | +| learning_rate | 4.64e-05 | +| loss | -0.0388 | +| n_updates | 45240 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000194 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.389 | +| time/ | | +| fps | 1422 | +| iterations | 7357 | +| time_elapsed | 10592 | +| total_timesteps | 15067136 | +| train/ | | +| approx_kl | 0.009722771 | +| clip_fraction | 0.304 | +| clip_range | 0.0712 | +| entropy_loss | -6.86 | +| explained_variance | 0.183 | +| learning_rate | 4.64e-05 | +| loss | -0.0358 | +| n_updates | 45244 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000214 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.389 | +| time/ | | +| fps | 1422 | +| iterations | 7358 | +| time_elapsed | 10594 | +| total_timesteps | 15069184 | +| train/ | | +| approx_kl | 0.010451212 | +| clip_fraction | 0.318 | +| clip_range | 0.0712 | +| entropy_loss | -6.61 | +| explained_variance | 0.45 | +| learning_rate | 4.64e-05 | +| loss | -0.0326 | +| n_updates | 45248 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000248 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.391 | +| time/ | | +| fps | 1422 | +| iterations | 7359 | +| time_elapsed | 10595 | +| total_timesteps | 15071232 | +| train/ | | +| approx_kl | 0.011712486 | +| clip_fraction | 0.341 | +| clip_range | 0.0712 | +| entropy_loss | -6.75 | +| explained_variance | 0.537 | +| learning_rate | 4.64e-05 | +| loss | -0.0301 | +| n_updates | 45252 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000118 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.393 | +| time/ | | +| fps | 1422 | +| iterations | 7360 | +| time_elapsed | 10597 | +| total_timesteps | 15073280 | +| train/ | | +| approx_kl | 0.009922667 | +| clip_fraction | 0.319 | +| clip_range | 0.0712 | +| entropy_loss | -7.26 | +| explained_variance | -0.228 | +| learning_rate | 4.64e-05 | +| loss | -0.0333 | +| n_updates | 45256 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000123 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.392 | +| time/ | | +| fps | 1422 | +| iterations | 7361 | +| time_elapsed | 10598 | +| total_timesteps | 15075328 | +| train/ | | +| approx_kl | 0.008194025 | +| clip_fraction | 0.301 | +| clip_range | 0.0712 | +| entropy_loss | -7.03 | +| explained_variance | 0.0447 | +| learning_rate | 4.64e-05 | +| loss | -0.0337 | +| n_updates | 45260 | +| policy_gradient_loss | -0.0145 | +| value_loss | 0.000265 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.396 | +| time/ | | +| fps | 1422 | +| iterations | 7362 | +| time_elapsed | 10599 | +| total_timesteps | 15077376 | +| train/ | | +| approx_kl | 0.01197045 | +| clip_fraction | 0.33 | +| clip_range | 0.0712 | +| entropy_loss | -6.67 | +| explained_variance | 0.407 | +| learning_rate | 4.64e-05 | +| loss | -0.0305 | +| n_updates | 45264 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000199 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.396 | +| time/ | | +| fps | 1422 | +| iterations | 7363 | +| time_elapsed | 10601 | +| total_timesteps | 15079424 | +| train/ | | +| approx_kl | 0.013248849 | +| clip_fraction | 0.329 | +| clip_range | 0.0712 | +| entropy_loss | -6.99 | +| explained_variance | 0.181 | +| learning_rate | 4.64e-05 | +| loss | -0.0306 | +| n_updates | 45268 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000181 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.396 | +| time/ | | +| fps | 1422 | +| iterations | 7364 | +| time_elapsed | 10602 | +| total_timesteps | 15081472 | +| train/ | | +| approx_kl | 0.011433173 | +| clip_fraction | 0.356 | +| clip_range | 0.0712 | +| entropy_loss | -6.86 | +| explained_variance | 0.627 | +| learning_rate | 4.64e-05 | +| loss | -0.0318 | +| n_updates | 45272 | +| policy_gradient_loss | -0.0219 | +| value_loss | 8.62e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.395 | +| time/ | | +| fps | 1422 | +| iterations | 7365 | +| time_elapsed | 10604 | +| total_timesteps | 15083520 | +| train/ | | +| approx_kl | 0.01230686 | +| clip_fraction | 0.329 | +| clip_range | 0.0712 | +| entropy_loss | -7.3 | +| explained_variance | -0.215 | +| learning_rate | 4.64e-05 | +| loss | -0.0329 | +| n_updates | 45276 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000158 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.392 | +| time/ | | +| fps | 1422 | +| iterations | 7366 | +| time_elapsed | 10605 | +| total_timesteps | 15085568 | +| train/ | | +| approx_kl | 0.0109222885 | +| clip_fraction | 0.327 | +| clip_range | 0.0712 | +| entropy_loss | -6.66 | +| explained_variance | 0.49 | +| learning_rate | 4.64e-05 | +| loss | -0.0323 | +| n_updates | 45280 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000186 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.392 | +| time/ | | +| fps | 1422 | +| iterations | 7367 | +| time_elapsed | 10607 | +| total_timesteps | 15087616 | +| train/ | | +| approx_kl | 0.012710774 | +| clip_fraction | 0.353 | +| clip_range | 0.0712 | +| entropy_loss | -6.61 | +| explained_variance | 0.712 | +| learning_rate | 4.64e-05 | +| loss | -0.0411 | +| n_updates | 45284 | +| policy_gradient_loss | -0.0233 | +| value_loss | 7.52e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.391 | +| time/ | | +| fps | 1422 | +| iterations | 7368 | +| time_elapsed | 10608 | +| total_timesteps | 15089664 | +| train/ | | +| approx_kl | 0.012418033 | +| clip_fraction | 0.324 | +| clip_range | 0.0712 | +| entropy_loss | -7.12 | +| explained_variance | 0.058 | +| learning_rate | 4.64e-05 | +| loss | -0.0304 | +| n_updates | 45288 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000202 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.391 | +| time/ | | +| fps | 1422 | +| iterations | 7369 | +| time_elapsed | 10609 | +| total_timesteps | 15091712 | +| train/ | | +| approx_kl | 0.010916288 | +| clip_fraction | 0.284 | +| clip_range | 0.0712 | +| entropy_loss | -7.18 | +| explained_variance | 0.148 | +| learning_rate | 4.64e-05 | +| loss | -0.0272 | +| n_updates | 45292 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000308 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.392 | +| time/ | | +| fps | 1422 | +| iterations | 7370 | +| time_elapsed | 10611 | +| total_timesteps | 15093760 | +| train/ | | +| approx_kl | 0.01079323 | +| clip_fraction | 0.314 | +| clip_range | 0.0712 | +| entropy_loss | -7.13 | +| explained_variance | 0.325 | +| learning_rate | 4.64e-05 | +| loss | -0.0344 | +| n_updates | 45296 | +| policy_gradient_loss | -0.023 | +| value_loss | 0.000119 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.386 | +| time/ | | +| fps | 1422 | +| iterations | 7371 | +| time_elapsed | 10612 | +| total_timesteps | 15095808 | +| train/ | | +| approx_kl | 0.011282988 | +| clip_fraction | 0.316 | +| clip_range | 0.0712 | +| entropy_loss | -6.83 | +| explained_variance | 0.204 | +| learning_rate | 4.64e-05 | +| loss | -0.0273 | +| n_updates | 45300 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000211 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.384 | +| time/ | | +| fps | 1422 | +| iterations | 7372 | +| time_elapsed | 10614 | +| total_timesteps | 15097856 | +| train/ | | +| approx_kl | 0.013511623 | +| clip_fraction | 0.346 | +| clip_range | 0.0712 | +| entropy_loss | -6.32 | +| explained_variance | 0.773 | +| learning_rate | 4.64e-05 | +| loss | -0.0343 | +| n_updates | 45304 | +| policy_gradient_loss | -0.0207 | +| value_loss | 9.54e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.386 | +| time/ | | +| fps | 1422 | +| iterations | 7373 | +| time_elapsed | 10615 | +| total_timesteps | 15099904 | +| train/ | | +| approx_kl | 0.012637859 | +| clip_fraction | 0.327 | +| clip_range | 0.0712 | +| entropy_loss | -6.85 | +| explained_variance | 0.478 | +| learning_rate | 4.64e-05 | +| loss | -0.0354 | +| n_updates | 45308 | +| policy_gradient_loss | -0.0208 | +| value_loss | 9.84e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1422 | +| iterations | 7374 | +| time_elapsed | 10616 | +| total_timesteps | 15101952 | +| train/ | | +| approx_kl | 0.010315187 | +| clip_fraction | 0.323 | +| clip_range | 0.0712 | +| entropy_loss | -6.87 | +| explained_variance | 0.356 | +| learning_rate | 4.64e-05 | +| loss | -0.0316 | +| n_updates | 45312 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000213 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1422 | +| iterations | 7375 | +| time_elapsed | 10618 | +| total_timesteps | 15104000 | +| train/ | | +| approx_kl | 0.012359167 | +| clip_fraction | 0.304 | +| clip_range | 0.0712 | +| entropy_loss | -6.84 | +| explained_variance | 0.243 | +| learning_rate | 4.64e-05 | +| loss | -0.0296 | +| n_updates | 45316 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000246 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1422 | +| iterations | 7376 | +| time_elapsed | 10619 | +| total_timesteps | 15106048 | +| train/ | | +| approx_kl | 0.01253393 | +| clip_fraction | 0.34 | +| clip_range | 0.0712 | +| entropy_loss | -6.85 | +| explained_variance | 0.377 | +| learning_rate | 4.64e-05 | +| loss | -0.0288 | +| n_updates | 45320 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000212 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1422 | +| iterations | 7377 | +| time_elapsed | 10621 | +| total_timesteps | 15108096 | +| train/ | | +| approx_kl | 0.012845181 | +| clip_fraction | 0.353 | +| clip_range | 0.0712 | +| entropy_loss | -7.08 | +| explained_variance | 0.278 | +| learning_rate | 4.64e-05 | +| loss | -0.0353 | +| n_updates | 45324 | +| policy_gradient_loss | -0.0225 | +| value_loss | 0.000133 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1422 | +| iterations | 7378 | +| time_elapsed | 10622 | +| total_timesteps | 15110144 | +| train/ | | +| approx_kl | 0.012263812 | +| clip_fraction | 0.325 | +| clip_range | 0.0712 | +| entropy_loss | -7.23 | +| explained_variance | -0.0969 | +| learning_rate | 4.64e-05 | +| loss | -0.0297 | +| n_updates | 45328 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000156 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1422 | +| iterations | 7379 | +| time_elapsed | 10624 | +| total_timesteps | 15112192 | +| train/ | | +| approx_kl | 0.013664724 | +| clip_fraction | 0.309 | +| clip_range | 0.0712 | +| entropy_loss | -6.46 | +| explained_variance | 0.563 | +| learning_rate | 4.64e-05 | +| loss | -0.0247 | +| n_updates | 45332 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000203 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1422 | +| iterations | 7380 | +| time_elapsed | 10625 | +| total_timesteps | 15114240 | +| train/ | | +| approx_kl | 0.011748545 | +| clip_fraction | 0.319 | +| clip_range | 0.0712 | +| entropy_loss | -6.43 | +| explained_variance | 0.53 | +| learning_rate | 4.64e-05 | +| loss | -0.0302 | +| n_updates | 45336 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000193 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1422 | +| iterations | 7381 | +| time_elapsed | 10627 | +| total_timesteps | 15116288 | +| train/ | | +| approx_kl | 0.009259285 | +| clip_fraction | 0.299 | +| clip_range | 0.0712 | +| entropy_loss | -6.66 | +| explained_variance | 0.382 | +| learning_rate | 4.64e-05 | +| loss | -0.0219 | +| n_updates | 45340 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000221 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1422 | +| iterations | 7382 | +| time_elapsed | 10628 | +| total_timesteps | 15118336 | +| train/ | | +| approx_kl | 0.011874289 | +| clip_fraction | 0.351 | +| clip_range | 0.0712 | +| entropy_loss | -6.95 | +| explained_variance | 0.533 | +| learning_rate | 4.64e-05 | +| loss | -0.0413 | +| n_updates | 45344 | +| policy_gradient_loss | -0.0237 | +| value_loss | 8.99e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1422 | +| iterations | 7383 | +| time_elapsed | 10630 | +| total_timesteps | 15120384 | +| train/ | | +| approx_kl | 0.010918238 | +| clip_fraction | 0.336 | +| clip_range | 0.0712 | +| entropy_loss | -7.26 | +| explained_variance | -0.0481 | +| learning_rate | 4.64e-05 | +| loss | -0.0329 | +| n_updates | 45348 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000185 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1422 | +| iterations | 7384 | +| time_elapsed | 10631 | +| total_timesteps | 15122432 | +| train/ | | +| approx_kl | 0.009608867 | +| clip_fraction | 0.337 | +| clip_range | 0.0712 | +| entropy_loss | -7.34 | +| explained_variance | -0.0775 | +| learning_rate | 4.64e-05 | +| loss | -0.0348 | +| n_updates | 45352 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.00011 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1422 | +| iterations | 7385 | +| time_elapsed | 10632 | +| total_timesteps | 15124480 | +| train/ | | +| approx_kl | 0.010670898 | +| clip_fraction | 0.304 | +| clip_range | 0.0712 | +| entropy_loss | -6.85 | +| explained_variance | 0.29 | +| learning_rate | 4.64e-05 | +| loss | -0.0271 | +| n_updates | 45356 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000453 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1422 | +| iterations | 7386 | +| time_elapsed | 10634 | +| total_timesteps | 15126528 | +| train/ | | +| approx_kl | 0.012037823 | +| clip_fraction | 0.331 | +| clip_range | 0.0712 | +| entropy_loss | -6.64 | +| explained_variance | 0.403 | +| learning_rate | 4.64e-05 | +| loss | -0.0336 | +| n_updates | 45360 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000238 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1422 | +| iterations | 7387 | +| time_elapsed | 10635 | +| total_timesteps | 15128576 | +| train/ | | +| approx_kl | 0.010337131 | +| clip_fraction | 0.326 | +| clip_range | 0.0712 | +| entropy_loss | -6.49 | +| explained_variance | 0.594 | +| learning_rate | 4.64e-05 | +| loss | -0.0326 | +| n_updates | 45364 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000182 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1422 | +| iterations | 7388 | +| time_elapsed | 10637 | +| total_timesteps | 15130624 | +| train/ | | +| approx_kl | 0.010079042 | +| clip_fraction | 0.344 | +| clip_range | 0.0712 | +| entropy_loss | -7.23 | +| explained_variance | -0.0103 | +| learning_rate | 4.64e-05 | +| loss | -0.0276 | +| n_updates | 45368 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000144 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1422 | +| iterations | 7389 | +| time_elapsed | 10638 | +| total_timesteps | 15132672 | +| train/ | | +| approx_kl | 0.008830598 | +| clip_fraction | 0.3 | +| clip_range | 0.0712 | +| entropy_loss | -6.95 | +| explained_variance | 0.374 | +| learning_rate | 4.64e-05 | +| loss | -0.0337 | +| n_updates | 45372 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.00023 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1422 | +| iterations | 7390 | +| time_elapsed | 10640 | +| total_timesteps | 15134720 | +| train/ | | +| approx_kl | 0.00996598 | +| clip_fraction | 0.306 | +| clip_range | 0.0712 | +| entropy_loss | -7.23 | +| explained_variance | 0.324 | +| learning_rate | 4.64e-05 | +| loss | -0.0307 | +| n_updates | 45376 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000148 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1422 | +| iterations | 7391 | +| time_elapsed | 10641 | +| total_timesteps | 15136768 | +| train/ | | +| approx_kl | 0.012665163 | +| clip_fraction | 0.349 | +| clip_range | 0.0712 | +| entropy_loss | -7.24 | +| explained_variance | 0.000117 | +| learning_rate | 4.64e-05 | +| loss | -0.0339 | +| n_updates | 45380 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.00016 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1422 | +| iterations | 7392 | +| time_elapsed | 10642 | +| total_timesteps | 15138816 | +| train/ | | +| approx_kl | 0.009592509 | +| clip_fraction | 0.277 | +| clip_range | 0.0712 | +| entropy_loss | -6.68 | +| explained_variance | 0.29 | +| learning_rate | 4.64e-05 | +| loss | -0.0282 | +| n_updates | 45384 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000334 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1422 | +| iterations | 7393 | +| time_elapsed | 10644 | +| total_timesteps | 15140864 | +| train/ | | +| approx_kl | 0.010637446 | +| clip_fraction | 0.304 | +| clip_range | 0.0712 | +| entropy_loss | -6.2 | +| explained_variance | 0.524 | +| learning_rate | 4.64e-05 | +| loss | -0.0308 | +| n_updates | 45388 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000285 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1422 | +| iterations | 7394 | +| time_elapsed | 10645 | +| total_timesteps | 15142912 | +| train/ | | +| approx_kl | 0.011781761 | +| clip_fraction | 0.32 | +| clip_range | 0.0712 | +| entropy_loss | -7.01 | +| explained_variance | 0.247 | +| learning_rate | 4.64e-05 | +| loss | -0.0337 | +| n_updates | 45392 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000225 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1422 | +| iterations | 7395 | +| time_elapsed | 10647 | +| total_timesteps | 15144960 | +| train/ | | +| approx_kl | 0.010465199 | +| clip_fraction | 0.34 | +| clip_range | 0.0712 | +| entropy_loss | -7.26 | +| explained_variance | -0.232 | +| learning_rate | 4.64e-05 | +| loss | -0.0365 | +| n_updates | 45396 | +| policy_gradient_loss | -0.0228 | +| value_loss | 0.000121 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1422 | +| iterations | 7396 | +| time_elapsed | 10648 | +| total_timesteps | 15147008 | +| train/ | | +| approx_kl | 0.008530557 | +| clip_fraction | 0.282 | +| clip_range | 0.0712 | +| entropy_loss | -6.81 | +| explained_variance | 0.413 | +| learning_rate | 4.64e-05 | +| loss | -0.0306 | +| n_updates | 45400 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000168 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1422 | +| iterations | 7397 | +| time_elapsed | 10650 | +| total_timesteps | 15149056 | +| train/ | | +| approx_kl | 0.010667262 | +| clip_fraction | 0.315 | +| clip_range | 0.0712 | +| entropy_loss | -6.42 | +| explained_variance | 0.588 | +| learning_rate | 4.64e-05 | +| loss | -0.0263 | +| n_updates | 45404 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000175 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.386 | +| time/ | | +| fps | 1422 | +| iterations | 7398 | +| time_elapsed | 10651 | +| total_timesteps | 15151104 | +| train/ | | +| approx_kl | 0.0102468915 | +| clip_fraction | 0.317 | +| clip_range | 0.0712 | +| entropy_loss | -7.02 | +| explained_variance | 0.194 | +| learning_rate | 4.64e-05 | +| loss | -0.0328 | +| n_updates | 45408 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000234 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.385 | +| time/ | | +| fps | 1422 | +| iterations | 7399 | +| time_elapsed | 10652 | +| total_timesteps | 15153152 | +| train/ | | +| approx_kl | 0.009440152 | +| clip_fraction | 0.292 | +| clip_range | 0.0712 | +| entropy_loss | -7.36 | +| explained_variance | -0.0866 | +| learning_rate | 4.64e-05 | +| loss | -0.027 | +| n_updates | 45412 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000225 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.385 | +| time/ | | +| fps | 1422 | +| iterations | 7400 | +| time_elapsed | 10654 | +| total_timesteps | 15155200 | +| train/ | | +| approx_kl | 0.0140144145 | +| clip_fraction | 0.329 | +| clip_range | 0.0712 | +| entropy_loss | -6.8 | +| explained_variance | 0.398 | +| learning_rate | 4.64e-05 | +| loss | -0.0367 | +| n_updates | 45416 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000125 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1422 | +| iterations | 7401 | +| time_elapsed | 10655 | +| total_timesteps | 15157248 | +| train/ | | +| approx_kl | 0.011436615 | +| clip_fraction | 0.344 | +| clip_range | 0.0712 | +| entropy_loss | -7.29 | +| explained_variance | -0.0772 | +| learning_rate | 4.64e-05 | +| loss | -0.0365 | +| n_updates | 45420 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.0001 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1422 | +| iterations | 7402 | +| time_elapsed | 10657 | +| total_timesteps | 15159296 | +| train/ | | +| approx_kl | 0.011652319 | +| clip_fraction | 0.312 | +| clip_range | 0.0712 | +| entropy_loss | -6.47 | +| explained_variance | 0.43 | +| learning_rate | 4.64e-05 | +| loss | -0.0285 | +| n_updates | 45424 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000361 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.384 | +| time/ | | +| fps | 1422 | +| iterations | 7403 | +| time_elapsed | 10658 | +| total_timesteps | 15161344 | +| train/ | | +| approx_kl | 0.012153847 | +| clip_fraction | 0.353 | +| clip_range | 0.0712 | +| entropy_loss | -6.64 | +| explained_variance | 0.591 | +| learning_rate | 4.64e-05 | +| loss | -0.0354 | +| n_updates | 45428 | +| policy_gradient_loss | -0.0222 | +| value_loss | 0.000106 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.385 | +| time/ | | +| fps | 1422 | +| iterations | 7404 | +| time_elapsed | 10660 | +| total_timesteps | 15163392 | +| train/ | | +| approx_kl | 0.011248612 | +| clip_fraction | 0.322 | +| clip_range | 0.0712 | +| entropy_loss | -7.04 | +| explained_variance | 0.263 | +| learning_rate | 4.64e-05 | +| loss | -0.0331 | +| n_updates | 45432 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000181 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.385 | +| time/ | | +| fps | 1422 | +| iterations | 7405 | +| time_elapsed | 10661 | +| total_timesteps | 15165440 | +| train/ | | +| approx_kl | 0.009807524 | +| clip_fraction | 0.322 | +| clip_range | 0.0712 | +| entropy_loss | -7.1 | +| explained_variance | 0.285 | +| learning_rate | 4.64e-05 | +| loss | -0.0304 | +| n_updates | 45436 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000184 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.389 | +| time/ | | +| fps | 1422 | +| iterations | 7406 | +| time_elapsed | 10663 | +| total_timesteps | 15167488 | +| train/ | | +| approx_kl | 0.0113656605 | +| clip_fraction | 0.344 | +| clip_range | 0.0712 | +| entropy_loss | -7.17 | +| explained_variance | 0.295 | +| learning_rate | 4.64e-05 | +| loss | -0.0316 | +| n_updates | 45440 | +| policy_gradient_loss | -0.0224 | +| value_loss | 0.000123 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.388 | +| time/ | | +| fps | 1422 | +| iterations | 7407 | +| time_elapsed | 10664 | +| total_timesteps | 15169536 | +| train/ | | +| approx_kl | 0.011325136 | +| clip_fraction | 0.317 | +| clip_range | 0.0712 | +| entropy_loss | -7.16 | +| explained_variance | 0.0917 | +| learning_rate | 4.64e-05 | +| loss | -0.0337 | +| n_updates | 45444 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000129 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1422 | +| iterations | 7408 | +| time_elapsed | 10665 | +| total_timesteps | 15171584 | +| train/ | | +| approx_kl | 0.011102908 | +| clip_fraction | 0.292 | +| clip_range | 0.0712 | +| entropy_loss | -7.06 | +| explained_variance | 0.344 | +| learning_rate | 4.64e-05 | +| loss | -0.0334 | +| n_updates | 45448 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000235 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.384 | +| time/ | | +| fps | 1422 | +| iterations | 7409 | +| time_elapsed | 10667 | +| total_timesteps | 15173632 | +| train/ | | +| approx_kl | 0.009174541 | +| clip_fraction | 0.321 | +| clip_range | 0.0712 | +| entropy_loss | -6.2 | +| explained_variance | 0.606 | +| learning_rate | 4.64e-05 | +| loss | -0.0217 | +| n_updates | 45452 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000243 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1422 | +| iterations | 7410 | +| time_elapsed | 10668 | +| total_timesteps | 15175680 | +| train/ | | +| approx_kl | 0.010760619 | +| clip_fraction | 0.346 | +| clip_range | 0.0712 | +| entropy_loss | -6.75 | +| explained_variance | 0.55 | +| learning_rate | 4.64e-05 | +| loss | -0.0364 | +| n_updates | 45456 | +| policy_gradient_loss | -0.0224 | +| value_loss | 0.000113 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1422 | +| iterations | 7411 | +| time_elapsed | 10670 | +| total_timesteps | 15177728 | +| train/ | | +| approx_kl | 0.008573886 | +| clip_fraction | 0.309 | +| clip_range | 0.0712 | +| entropy_loss | -6.72 | +| explained_variance | -0.0709 | +| learning_rate | 4.64e-05 | +| loss | -0.0286 | +| n_updates | 45460 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000223 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1422 | +| iterations | 7412 | +| time_elapsed | 10671 | +| total_timesteps | 15179776 | +| train/ | | +| approx_kl | 0.010997068 | +| clip_fraction | 0.321 | +| clip_range | 0.0712 | +| entropy_loss | -7.24 | +| explained_variance | 0.256 | +| learning_rate | 4.64e-05 | +| loss | -0.0323 | +| n_updates | 45464 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000124 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1422 | +| iterations | 7413 | +| time_elapsed | 10673 | +| total_timesteps | 15181824 | +| train/ | | +| approx_kl | 0.009859902 | +| clip_fraction | 0.304 | +| clip_range | 0.0712 | +| entropy_loss | -7.03 | +| explained_variance | 0.376 | +| learning_rate | 4.64e-05 | +| loss | -0.0301 | +| n_updates | 45468 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.0001 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1422 | +| iterations | 7414 | +| time_elapsed | 10674 | +| total_timesteps | 15183872 | +| train/ | | +| approx_kl | 0.01108784 | +| clip_fraction | 0.308 | +| clip_range | 0.0712 | +| entropy_loss | -7.18 | +| explained_variance | 0.3 | +| learning_rate | 4.64e-05 | +| loss | -0.034 | +| n_updates | 45472 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000148 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1422 | +| iterations | 7415 | +| time_elapsed | 10676 | +| total_timesteps | 15185920 | +| train/ | | +| approx_kl | 0.011708605 | +| clip_fraction | 0.333 | +| clip_range | 0.0712 | +| entropy_loss | -7.04 | +| explained_variance | 0.298 | +| learning_rate | 4.64e-05 | +| loss | -0.0353 | +| n_updates | 45476 | +| policy_gradient_loss | -0.0225 | +| value_loss | 0.000144 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1422 | +| iterations | 7416 | +| time_elapsed | 10677 | +| total_timesteps | 15187968 | +| train/ | | +| approx_kl | 0.011003492 | +| clip_fraction | 0.34 | +| clip_range | 0.0712 | +| entropy_loss | -6.99 | +| explained_variance | 0.64 | +| learning_rate | 4.64e-05 | +| loss | -0.0407 | +| n_updates | 45480 | +| policy_gradient_loss | -0.0229 | +| value_loss | 8.53e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1422 | +| iterations | 7417 | +| time_elapsed | 10678 | +| total_timesteps | 15190016 | +| train/ | | +| approx_kl | 0.010597656 | +| clip_fraction | 0.31 | +| clip_range | 0.0712 | +| entropy_loss | -6.71 | +| explained_variance | 0.478 | +| learning_rate | 4.64e-05 | +| loss | -0.0269 | +| n_updates | 45484 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000177 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1422 | +| iterations | 7418 | +| time_elapsed | 10680 | +| total_timesteps | 15192064 | +| train/ | | +| approx_kl | 0.010812096 | +| clip_fraction | 0.307 | +| clip_range | 0.0712 | +| entropy_loss | -7.12 | +| explained_variance | 0.229 | +| learning_rate | 4.64e-05 | +| loss | -0.0299 | +| n_updates | 45488 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000147 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1422 | +| iterations | 7419 | +| time_elapsed | 10681 | +| total_timesteps | 15194112 | +| train/ | | +| approx_kl | 0.008310286 | +| clip_fraction | 0.29 | +| clip_range | 0.0712 | +| entropy_loss | -7.04 | +| explained_variance | 0.227 | +| learning_rate | 4.64e-05 | +| loss | -0.0272 | +| n_updates | 45492 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000161 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1422 | +| iterations | 7420 | +| time_elapsed | 10683 | +| total_timesteps | 15196160 | +| train/ | | +| approx_kl | 0.011825861 | +| clip_fraction | 0.332 | +| clip_range | 0.0712 | +| entropy_loss | -7.06 | +| explained_variance | 0.00743 | +| learning_rate | 4.64e-05 | +| loss | -0.0357 | +| n_updates | 45496 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000108 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1422 | +| iterations | 7421 | +| time_elapsed | 10684 | +| total_timesteps | 15198208 | +| train/ | | +| approx_kl | 0.011609854 | +| clip_fraction | 0.287 | +| clip_range | 0.0712 | +| entropy_loss | -6.39 | +| explained_variance | 0.571 | +| learning_rate | 4.64e-05 | +| loss | -0.0255 | +| n_updates | 45500 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000187 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1422 | +| iterations | 7422 | +| time_elapsed | 10686 | +| total_timesteps | 15200256 | +| train/ | | +| approx_kl | 0.012337891 | +| clip_fraction | 0.352 | +| clip_range | 0.0712 | +| entropy_loss | -6.75 | +| explained_variance | 0.494 | +| learning_rate | 4.64e-05 | +| loss | -0.0358 | +| n_updates | 45504 | +| policy_gradient_loss | -0.0222 | +| value_loss | 0.000167 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1422 | +| iterations | 7423 | +| time_elapsed | 10687 | +| total_timesteps | 15202304 | +| train/ | | +| approx_kl | 0.010346774 | +| clip_fraction | 0.312 | +| clip_range | 0.0712 | +| entropy_loss | -7.18 | +| explained_variance | 0.0107 | +| learning_rate | 4.64e-05 | +| loss | -0.0232 | +| n_updates | 45508 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000206 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1422 | +| iterations | 7424 | +| time_elapsed | 10689 | +| total_timesteps | 15204352 | +| train/ | | +| approx_kl | 0.011756416 | +| clip_fraction | 0.325 | +| clip_range | 0.0712 | +| entropy_loss | -7.16 | +| explained_variance | 0.301 | +| learning_rate | 4.64e-05 | +| loss | -0.0353 | +| n_updates | 45512 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000148 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1422 | +| iterations | 7425 | +| time_elapsed | 10690 | +| total_timesteps | 15206400 | +| train/ | | +| approx_kl | 0.009363736 | +| clip_fraction | 0.296 | +| clip_range | 0.0712 | +| entropy_loss | -6.76 | +| explained_variance | 0.408 | +| learning_rate | 4.64e-05 | +| loss | -0.0311 | +| n_updates | 45516 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000331 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1422 | +| iterations | 7426 | +| time_elapsed | 10691 | +| total_timesteps | 15208448 | +| train/ | | +| approx_kl | 0.009693896 | +| clip_fraction | 0.305 | +| clip_range | 0.0712 | +| entropy_loss | -6.67 | +| explained_variance | 0.449 | +| learning_rate | 4.64e-05 | +| loss | -0.0308 | +| n_updates | 45520 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000197 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1422 | +| iterations | 7427 | +| time_elapsed | 10693 | +| total_timesteps | 15210496 | +| train/ | | +| approx_kl | 0.00761715 | +| clip_fraction | 0.287 | +| clip_range | 0.0712 | +| entropy_loss | -7.04 | +| explained_variance | 0.313 | +| learning_rate | 4.64e-05 | +| loss | -0.0242 | +| n_updates | 45524 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000274 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1422 | +| iterations | 7428 | +| time_elapsed | 10694 | +| total_timesteps | 15212544 | +| train/ | | +| approx_kl | 0.012141135 | +| clip_fraction | 0.365 | +| clip_range | 0.0712 | +| entropy_loss | -6.75 | +| explained_variance | 0.644 | +| learning_rate | 4.64e-05 | +| loss | -0.0339 | +| n_updates | 45528 | +| policy_gradient_loss | -0.024 | +| value_loss | 7.09e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1422 | +| iterations | 7429 | +| time_elapsed | 10696 | +| total_timesteps | 15214592 | +| train/ | | +| approx_kl | 0.00989732 | +| clip_fraction | 0.328 | +| clip_range | 0.0712 | +| entropy_loss | -6.89 | +| explained_variance | 0.451 | +| learning_rate | 4.64e-05 | +| loss | -0.03 | +| n_updates | 45532 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.00017 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1422 | +| iterations | 7430 | +| time_elapsed | 10697 | +| total_timesteps | 15216640 | +| train/ | | +| approx_kl | 0.011279476 | +| clip_fraction | 0.327 | +| clip_range | 0.0712 | +| entropy_loss | -7.28 | +| explained_variance | -0.127 | +| learning_rate | 4.64e-05 | +| loss | -0.0316 | +| n_updates | 45536 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000145 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1422 | +| iterations | 7431 | +| time_elapsed | 10699 | +| total_timesteps | 15218688 | +| train/ | | +| approx_kl | 0.011414006 | +| clip_fraction | 0.33 | +| clip_range | 0.0712 | +| entropy_loss | -7.18 | +| explained_variance | 0.32 | +| learning_rate | 4.64e-05 | +| loss | -0.0311 | +| n_updates | 45540 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000173 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1422 | +| iterations | 7432 | +| time_elapsed | 10700 | +| total_timesteps | 15220736 | +| train/ | | +| approx_kl | 0.011136962 | +| clip_fraction | 0.301 | +| clip_range | 0.0712 | +| entropy_loss | -6.88 | +| explained_variance | 0.431 | +| learning_rate | 4.64e-05 | +| loss | -0.0268 | +| n_updates | 45544 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000186 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1422 | +| iterations | 7433 | +| time_elapsed | 10702 | +| total_timesteps | 15222784 | +| train/ | | +| approx_kl | 0.007318098 | +| clip_fraction | 0.274 | +| clip_range | 0.0712 | +| entropy_loss | -6.84 | +| explained_variance | 0.413 | +| learning_rate | 4.64e-05 | +| loss | -0.0292 | +| n_updates | 45548 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.000195 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1422 | +| iterations | 7434 | +| time_elapsed | 10703 | +| total_timesteps | 15224832 | +| train/ | | +| approx_kl | 0.0116652455 | +| clip_fraction | 0.297 | +| clip_range | 0.0712 | +| entropy_loss | -6.94 | +| explained_variance | 0.245 | +| learning_rate | 4.64e-05 | +| loss | -0.036 | +| n_updates | 45552 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000216 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1422 | +| iterations | 7435 | +| time_elapsed | 10704 | +| total_timesteps | 15226880 | +| train/ | | +| approx_kl | 0.008786206 | +| clip_fraction | 0.296 | +| clip_range | 0.0712 | +| entropy_loss | -7.16 | +| explained_variance | 0.218 | +| learning_rate | 4.64e-05 | +| loss | -0.0252 | +| n_updates | 45556 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000178 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1422 | +| iterations | 7436 | +| time_elapsed | 10706 | +| total_timesteps | 15228928 | +| train/ | | +| approx_kl | 0.010290073 | +| clip_fraction | 0.316 | +| clip_range | 0.0712 | +| entropy_loss | -7.08 | +| explained_variance | 0.61 | +| learning_rate | 4.64e-05 | +| loss | -0.0262 | +| n_updates | 45560 | +| policy_gradient_loss | -0.0191 | +| value_loss | 8.62e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1422 | +| iterations | 7437 | +| time_elapsed | 10707 | +| total_timesteps | 15230976 | +| train/ | | +| approx_kl | 0.012299177 | +| clip_fraction | 0.327 | +| clip_range | 0.0712 | +| entropy_loss | -6.83 | +| explained_variance | 0.583 | +| learning_rate | 4.64e-05 | +| loss | -0.0286 | +| n_updates | 45564 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000155 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1422 | +| iterations | 7438 | +| time_elapsed | 10709 | +| total_timesteps | 15233024 | +| train/ | | +| approx_kl | 0.010000592 | +| clip_fraction | 0.285 | +| clip_range | 0.0712 | +| entropy_loss | -6.86 | +| explained_variance | 0.282 | +| learning_rate | 4.64e-05 | +| loss | -0.0256 | +| n_updates | 45568 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.00014 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1422 | +| iterations | 7439 | +| time_elapsed | 10710 | +| total_timesteps | 15235072 | +| train/ | | +| approx_kl | 0.013835439 | +| clip_fraction | 0.357 | +| clip_range | 0.0712 | +| entropy_loss | -6.98 | +| explained_variance | 0.352 | +| learning_rate | 4.64e-05 | +| loss | -0.0351 | +| n_updates | 45572 | +| policy_gradient_loss | -0.0222 | +| value_loss | 0.000121 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1422 | +| iterations | 7440 | +| time_elapsed | 10712 | +| total_timesteps | 15237120 | +| train/ | | +| approx_kl | 0.010809232 | +| clip_fraction | 0.332 | +| clip_range | 0.0712 | +| entropy_loss | -7.23 | +| explained_variance | -0.168 | +| learning_rate | 4.64e-05 | +| loss | -0.0326 | +| n_updates | 45576 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000126 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1422 | +| iterations | 7441 | +| time_elapsed | 10713 | +| total_timesteps | 15239168 | +| train/ | | +| approx_kl | 0.0120898215 | +| clip_fraction | 0.291 | +| clip_range | 0.0712 | +| entropy_loss | -7.04 | +| explained_variance | 0.469 | +| learning_rate | 4.64e-05 | +| loss | -0.0252 | +| n_updates | 45580 | +| policy_gradient_loss | -0.0183 | +| value_loss | 9e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1422 | +| iterations | 7442 | +| time_elapsed | 10714 | +| total_timesteps | 15241216 | +| train/ | | +| approx_kl | 0.009379761 | +| clip_fraction | 0.318 | +| clip_range | 0.0712 | +| entropy_loss | -6.67 | +| explained_variance | 0.769 | +| learning_rate | 4.64e-05 | +| loss | -0.0253 | +| n_updates | 45584 | +| policy_gradient_loss | -0.0195 | +| value_loss | 7.03e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1422 | +| iterations | 7443 | +| time_elapsed | 10716 | +| total_timesteps | 15243264 | +| train/ | | +| approx_kl | 0.010765025 | +| clip_fraction | 0.301 | +| clip_range | 0.0712 | +| entropy_loss | -7.23 | +| explained_variance | 0.0162 | +| learning_rate | 4.64e-05 | +| loss | -0.0313 | +| n_updates | 45588 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000166 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1422 | +| iterations | 7444 | +| time_elapsed | 10717 | +| total_timesteps | 15245312 | +| train/ | | +| approx_kl | 0.011869507 | +| clip_fraction | 0.294 | +| clip_range | 0.0712 | +| entropy_loss | -7.02 | +| explained_variance | 0.348 | +| learning_rate | 4.64e-05 | +| loss | -0.0308 | +| n_updates | 45592 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000192 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1422 | +| iterations | 7445 | +| time_elapsed | 10719 | +| total_timesteps | 15247360 | +| train/ | | +| approx_kl | 0.009826796 | +| clip_fraction | 0.292 | +| clip_range | 0.0712 | +| entropy_loss | -6.24 | +| explained_variance | 0.58 | +| learning_rate | 4.64e-05 | +| loss | -0.0211 | +| n_updates | 45596 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000267 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1422 | +| iterations | 7446 | +| time_elapsed | 10720 | +| total_timesteps | 15249408 | +| train/ | | +| approx_kl | 0.009959368 | +| clip_fraction | 0.3 | +| clip_range | 0.0712 | +| entropy_loss | -6.87 | +| explained_variance | 0.239 | +| learning_rate | 4.64e-05 | +| loss | -0.023 | +| n_updates | 45600 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000394 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1422 | +| iterations | 7447 | +| time_elapsed | 10722 | +| total_timesteps | 15251456 | +| train/ | | +| approx_kl | 0.010315436 | +| clip_fraction | 0.314 | +| clip_range | 0.0712 | +| entropy_loss | -7.06 | +| explained_variance | -0.126 | +| learning_rate | 4.64e-05 | +| loss | -0.0351 | +| n_updates | 45604 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000295 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1422 | +| iterations | 7448 | +| time_elapsed | 10723 | +| total_timesteps | 15253504 | +| train/ | | +| approx_kl | 0.010773468 | +| clip_fraction | 0.339 | +| clip_range | 0.0712 | +| entropy_loss | -7.38 | +| explained_variance | -0.34 | +| learning_rate | 4.64e-05 | +| loss | -0.0358 | +| n_updates | 45608 | +| policy_gradient_loss | -0.0242 | +| value_loss | 8.99e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1422 | +| iterations | 7449 | +| time_elapsed | 10725 | +| total_timesteps | 15255552 | +| train/ | | +| approx_kl | 0.009114787 | +| clip_fraction | 0.301 | +| clip_range | 0.0712 | +| entropy_loss | -7.02 | +| explained_variance | 0.438 | +| learning_rate | 4.64e-05 | +| loss | -0.0298 | +| n_updates | 45612 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.00013 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1422 | +| iterations | 7450 | +| time_elapsed | 10726 | +| total_timesteps | 15257600 | +| train/ | | +| approx_kl | 0.013129896 | +| clip_fraction | 0.329 | +| clip_range | 0.0712 | +| entropy_loss | -7.26 | +| explained_variance | -0.15 | +| learning_rate | 4.64e-05 | +| loss | -0.0366 | +| n_updates | 45616 | +| policy_gradient_loss | -0.0227 | +| value_loss | 7.8e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1422 | +| iterations | 7451 | +| time_elapsed | 10727 | +| total_timesteps | 15259648 | +| train/ | | +| approx_kl | 0.010046524 | +| clip_fraction | 0.295 | +| clip_range | 0.0712 | +| entropy_loss | -7.31 | +| explained_variance | -0.0955 | +| learning_rate | 4.64e-05 | +| loss | -0.0303 | +| n_updates | 45620 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000232 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1422 | +| iterations | 7452 | +| time_elapsed | 10729 | +| total_timesteps | 15261696 | +| train/ | | +| approx_kl | 0.009362197 | +| clip_fraction | 0.295 | +| clip_range | 0.0712 | +| entropy_loss | -7 | +| explained_variance | 0.39 | +| learning_rate | 4.64e-05 | +| loss | -0.0283 | +| n_updates | 45624 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000169 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1422 | +| iterations | 7453 | +| time_elapsed | 10730 | +| total_timesteps | 15263744 | +| train/ | | +| approx_kl | 0.009278075 | +| clip_fraction | 0.291 | +| clip_range | 0.0712 | +| entropy_loss | -6.84 | +| explained_variance | 0.463 | +| learning_rate | 4.64e-05 | +| loss | -0.0246 | +| n_updates | 45628 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.0002 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1422 | +| iterations | 7454 | +| time_elapsed | 10732 | +| total_timesteps | 15265792 | +| train/ | | +| approx_kl | 0.011950519 | +| clip_fraction | 0.295 | +| clip_range | 0.0712 | +| entropy_loss | -6.58 | +| explained_variance | 0.45 | +| learning_rate | 4.64e-05 | +| loss | -0.0308 | +| n_updates | 45632 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000171 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1422 | +| iterations | 7455 | +| time_elapsed | 10733 | +| total_timesteps | 15267840 | +| train/ | | +| approx_kl | 0.010506041 | +| clip_fraction | 0.325 | +| clip_range | 0.0712 | +| entropy_loss | -7.02 | +| explained_variance | 0.422 | +| learning_rate | 4.64e-05 | +| loss | -0.0293 | +| n_updates | 45636 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1422 | +| iterations | 7456 | +| time_elapsed | 10735 | +| total_timesteps | 15269888 | +| train/ | | +| approx_kl | 0.009836445 | +| clip_fraction | 0.275 | +| clip_range | 0.0712 | +| entropy_loss | -7.11 | +| explained_variance | 0.313 | +| learning_rate | 4.64e-05 | +| loss | -0.0258 | +| n_updates | 45640 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000198 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1422 | +| iterations | 7457 | +| time_elapsed | 10736 | +| total_timesteps | 15271936 | +| train/ | | +| approx_kl | 0.010124724 | +| clip_fraction | 0.308 | +| clip_range | 0.0712 | +| entropy_loss | -6.62 | +| explained_variance | 0.622 | +| learning_rate | 4.64e-05 | +| loss | -0.0308 | +| n_updates | 45644 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000146 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1422 | +| iterations | 7458 | +| time_elapsed | 10737 | +| total_timesteps | 15273984 | +| train/ | | +| approx_kl | 0.009530573 | +| clip_fraction | 0.305 | +| clip_range | 0.0712 | +| entropy_loss | -7.07 | +| explained_variance | 0.0599 | +| learning_rate | 4.64e-05 | +| loss | -0.028 | +| n_updates | 45648 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.00026 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1422 | +| iterations | 7459 | +| time_elapsed | 10739 | +| total_timesteps | 15276032 | +| train/ | | +| approx_kl | 0.012164964 | +| clip_fraction | 0.312 | +| clip_range | 0.0712 | +| entropy_loss | -6.89 | +| explained_variance | 0.468 | +| learning_rate | 4.64e-05 | +| loss | -0.0335 | +| n_updates | 45652 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000154 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1422 | +| iterations | 7460 | +| time_elapsed | 10740 | +| total_timesteps | 15278080 | +| train/ | | +| approx_kl | 0.012869071 | +| clip_fraction | 0.322 | +| clip_range | 0.0712 | +| entropy_loss | -7.18 | +| explained_variance | 0.0395 | +| learning_rate | 4.64e-05 | +| loss | -0.0307 | +| n_updates | 45656 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000439 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1422 | +| iterations | 7461 | +| time_elapsed | 10742 | +| total_timesteps | 15280128 | +| train/ | | +| approx_kl | 0.010511365 | +| clip_fraction | 0.301 | +| clip_range | 0.0712 | +| entropy_loss | -6.77 | +| explained_variance | 0.552 | +| learning_rate | 4.64e-05 | +| loss | -0.0261 | +| n_updates | 45660 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000246 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1422 | +| iterations | 7462 | +| time_elapsed | 10743 | +| total_timesteps | 15282176 | +| train/ | | +| approx_kl | 0.014018938 | +| clip_fraction | 0.326 | +| clip_range | 0.0712 | +| entropy_loss | -6.65 | +| explained_variance | 0.351 | +| learning_rate | 4.64e-05 | +| loss | -0.0292 | +| n_updates | 45664 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000253 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1422 | +| iterations | 7463 | +| time_elapsed | 10745 | +| total_timesteps | 15284224 | +| train/ | | +| approx_kl | 0.012932701 | +| clip_fraction | 0.326 | +| clip_range | 0.0712 | +| entropy_loss | -7.34 | +| explained_variance | -0.0905 | +| learning_rate | 4.64e-05 | +| loss | -0.0332 | +| n_updates | 45668 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000202 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1422 | +| iterations | 7464 | +| time_elapsed | 10746 | +| total_timesteps | 15286272 | +| train/ | | +| approx_kl | 0.011764097 | +| clip_fraction | 0.358 | +| clip_range | 0.0712 | +| entropy_loss | -6.81 | +| explained_variance | 0.612 | +| learning_rate | 4.64e-05 | +| loss | -0.0366 | +| n_updates | 45672 | +| policy_gradient_loss | -0.0223 | +| value_loss | 0.00011 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1422 | +| iterations | 7465 | +| time_elapsed | 10747 | +| total_timesteps | 15288320 | +| train/ | | +| approx_kl | 0.011312846 | +| clip_fraction | 0.329 | +| clip_range | 0.0712 | +| entropy_loss | -6.75 | +| explained_variance | 0.344 | +| learning_rate | 4.64e-05 | +| loss | -0.0307 | +| n_updates | 45676 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000248 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1422 | +| iterations | 7466 | +| time_elapsed | 10749 | +| total_timesteps | 15290368 | +| train/ | | +| approx_kl | 0.011175411 | +| clip_fraction | 0.324 | +| clip_range | 0.0712 | +| entropy_loss | -7.14 | +| explained_variance | 0.227 | +| learning_rate | 4.64e-05 | +| loss | -0.0308 | +| n_updates | 45680 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000258 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1422 | +| iterations | 7467 | +| time_elapsed | 10750 | +| total_timesteps | 15292416 | +| train/ | | +| approx_kl | 0.008892301 | +| clip_fraction | 0.31 | +| clip_range | 0.0712 | +| entropy_loss | -7.24 | +| explained_variance | 0.261 | +| learning_rate | 4.64e-05 | +| loss | -0.0309 | +| n_updates | 45684 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000125 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1422 | +| iterations | 7468 | +| time_elapsed | 10752 | +| total_timesteps | 15294464 | +| train/ | | +| approx_kl | 0.009088671 | +| clip_fraction | 0.296 | +| clip_range | 0.0712 | +| entropy_loss | -7.11 | +| explained_variance | 0.382 | +| learning_rate | 4.64e-05 | +| loss | -0.0319 | +| n_updates | 45688 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000146 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1422 | +| iterations | 7469 | +| time_elapsed | 10753 | +| total_timesteps | 15296512 | +| train/ | | +| approx_kl | 0.010124626 | +| clip_fraction | 0.324 | +| clip_range | 0.0712 | +| entropy_loss | -7.12 | +| explained_variance | 0.524 | +| learning_rate | 4.64e-05 | +| loss | -0.0295 | +| n_updates | 45692 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000109 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1422 | +| iterations | 7470 | +| time_elapsed | 10755 | +| total_timesteps | 15298560 | +| train/ | | +| approx_kl | 0.012032777 | +| clip_fraction | 0.297 | +| clip_range | 0.0712 | +| entropy_loss | -6.77 | +| explained_variance | 0.546 | +| learning_rate | 4.64e-05 | +| loss | -0.0298 | +| n_updates | 45696 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000134 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1422 | +| iterations | 7471 | +| time_elapsed | 10756 | +| total_timesteps | 15300608 | +| train/ | | +| approx_kl | 0.010189047 | +| clip_fraction | 0.306 | +| clip_range | 0.0712 | +| entropy_loss | -7.01 | +| explained_variance | 0.679 | +| learning_rate | 4.64e-05 | +| loss | -0.0319 | +| n_updates | 45700 | +| policy_gradient_loss | -0.0198 | +| value_loss | 6.59e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1422 | +| iterations | 7472 | +| time_elapsed | 10757 | +| total_timesteps | 15302656 | +| train/ | | +| approx_kl | 0.008819285 | +| clip_fraction | 0.288 | +| clip_range | 0.0712 | +| entropy_loss | -6.62 | +| explained_variance | 0.291 | +| learning_rate | 4.64e-05 | +| loss | -0.0274 | +| n_updates | 45704 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000291 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1422 | +| iterations | 7473 | +| time_elapsed | 10759 | +| total_timesteps | 15304704 | +| train/ | | +| approx_kl | 0.009285523 | +| clip_fraction | 0.304 | +| clip_range | 0.0712 | +| entropy_loss | -6.87 | +| explained_variance | 0.492 | +| learning_rate | 4.64e-05 | +| loss | -0.0301 | +| n_updates | 45708 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.00019 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1422 | +| iterations | 7474 | +| time_elapsed | 10760 | +| total_timesteps | 15306752 | +| train/ | | +| approx_kl | 0.00998875 | +| clip_fraction | 0.33 | +| clip_range | 0.0712 | +| entropy_loss | -6.68 | +| explained_variance | 0.423 | +| learning_rate | 4.64e-05 | +| loss | -0.023 | +| n_updates | 45712 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000264 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1422 | +| iterations | 7475 | +| time_elapsed | 10762 | +| total_timesteps | 15308800 | +| train/ | | +| approx_kl | 0.0107442625 | +| clip_fraction | 0.333 | +| clip_range | 0.0712 | +| entropy_loss | -7.09 | +| explained_variance | 0.096 | +| learning_rate | 4.64e-05 | +| loss | -0.0375 | +| n_updates | 45716 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000265 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1422 | +| iterations | 7476 | +| time_elapsed | 10763 | +| total_timesteps | 15310848 | +| train/ | | +| approx_kl | 0.009633828 | +| clip_fraction | 0.298 | +| clip_range | 0.0712 | +| entropy_loss | -7.31 | +| explained_variance | 0.283 | +| learning_rate | 4.64e-05 | +| loss | -0.0311 | +| n_updates | 45720 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000222 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1422 | +| iterations | 7477 | +| time_elapsed | 10765 | +| total_timesteps | 15312896 | +| train/ | | +| approx_kl | 0.011312515 | +| clip_fraction | 0.323 | +| clip_range | 0.0712 | +| entropy_loss | -7.28 | +| explained_variance | 0.26 | +| learning_rate | 4.64e-05 | +| loss | -0.0393 | +| n_updates | 45724 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000146 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1422 | +| iterations | 7478 | +| time_elapsed | 10766 | +| total_timesteps | 15314944 | +| train/ | | +| approx_kl | 0.009170712 | +| clip_fraction | 0.303 | +| clip_range | 0.0712 | +| entropy_loss | -7.25 | +| explained_variance | 0.0465 | +| learning_rate | 4.64e-05 | +| loss | -0.0342 | +| n_updates | 45728 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000307 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1422 | +| iterations | 7479 | +| time_elapsed | 10767 | +| total_timesteps | 15316992 | +| train/ | | +| approx_kl | 0.009348661 | +| clip_fraction | 0.319 | +| clip_range | 0.0712 | +| entropy_loss | -6.76 | +| explained_variance | 0.602 | +| learning_rate | 4.64e-05 | +| loss | -0.035 | +| n_updates | 45732 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000129 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1422 | +| iterations | 7480 | +| time_elapsed | 10769 | +| total_timesteps | 15319040 | +| train/ | | +| approx_kl | 0.007468634 | +| clip_fraction | 0.303 | +| clip_range | 0.0712 | +| entropy_loss | -6.92 | +| explained_variance | 0.191 | +| learning_rate | 4.64e-05 | +| loss | -0.0299 | +| n_updates | 45736 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000315 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1422 | +| iterations | 7481 | +| time_elapsed | 10770 | +| total_timesteps | 15321088 | +| train/ | | +| approx_kl | 0.009071503 | +| clip_fraction | 0.297 | +| clip_range | 0.0712 | +| entropy_loss | -6.97 | +| explained_variance | 0.326 | +| learning_rate | 4.64e-05 | +| loss | -0.0297 | +| n_updates | 45740 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000298 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1422 | +| iterations | 7482 | +| time_elapsed | 10772 | +| total_timesteps | 15323136 | +| train/ | | +| approx_kl | 0.010766182 | +| clip_fraction | 0.356 | +| clip_range | 0.0712 | +| entropy_loss | -7.21 | +| explained_variance | 0.0485 | +| learning_rate | 4.64e-05 | +| loss | -0.0395 | +| n_updates | 45744 | +| policy_gradient_loss | -0.0227 | +| value_loss | 0.00014 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1422 | +| iterations | 7483 | +| time_elapsed | 10773 | +| total_timesteps | 15325184 | +| train/ | | +| approx_kl | 0.007984141 | +| clip_fraction | 0.295 | +| clip_range | 0.0712 | +| entropy_loss | -6.95 | +| explained_variance | 0.59 | +| learning_rate | 4.64e-05 | +| loss | -0.0285 | +| n_updates | 45748 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000125 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1422 | +| iterations | 7484 | +| time_elapsed | 10775 | +| total_timesteps | 15327232 | +| train/ | | +| approx_kl | 0.010682175 | +| clip_fraction | 0.311 | +| clip_range | 0.0712 | +| entropy_loss | -7.11 | +| explained_variance | 0.271 | +| learning_rate | 4.64e-05 | +| loss | -0.0287 | +| n_updates | 45752 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000123 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1422 | +| iterations | 7485 | +| time_elapsed | 10776 | +| total_timesteps | 15329280 | +| train/ | | +| approx_kl | 0.010482663 | +| clip_fraction | 0.323 | +| clip_range | 0.0712 | +| entropy_loss | -7.14 | +| explained_variance | 0.47 | +| learning_rate | 4.64e-05 | +| loss | -0.0331 | +| n_updates | 45756 | +| policy_gradient_loss | -0.0218 | +| value_loss | 7.77e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1422 | +| iterations | 7486 | +| time_elapsed | 10778 | +| total_timesteps | 15331328 | +| train/ | | +| approx_kl | 0.009504823 | +| clip_fraction | 0.317 | +| clip_range | 0.0712 | +| entropy_loss | -7.13 | +| explained_variance | 0.224 | +| learning_rate | 4.64e-05 | +| loss | -0.0302 | +| n_updates | 45760 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000319 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1422 | +| iterations | 7487 | +| time_elapsed | 10779 | +| total_timesteps | 15333376 | +| train/ | | +| approx_kl | 0.012297342 | +| clip_fraction | 0.313 | +| clip_range | 0.0712 | +| entropy_loss | -6.82 | +| explained_variance | 0.392 | +| learning_rate | 4.64e-05 | +| loss | -0.0242 | +| n_updates | 45764 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000216 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1422 | +| iterations | 7488 | +| time_elapsed | 10781 | +| total_timesteps | 15335424 | +| train/ | | +| approx_kl | 0.011451488 | +| clip_fraction | 0.315 | +| clip_range | 0.0712 | +| entropy_loss | -6.9 | +| explained_variance | 0.468 | +| learning_rate | 4.64e-05 | +| loss | -0.0251 | +| n_updates | 45768 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000167 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1422 | +| iterations | 7489 | +| time_elapsed | 10782 | +| total_timesteps | 15337472 | +| train/ | | +| approx_kl | 0.009432295 | +| clip_fraction | 0.291 | +| clip_range | 0.0712 | +| entropy_loss | -7.03 | +| explained_variance | 0.469 | +| learning_rate | 4.64e-05 | +| loss | -0.0286 | +| n_updates | 45772 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000173 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1422 | +| iterations | 7490 | +| time_elapsed | 10783 | +| total_timesteps | 15339520 | +| train/ | | +| approx_kl | 0.00994923 | +| clip_fraction | 0.296 | +| clip_range | 0.0712 | +| entropy_loss | -7.09 | +| explained_variance | 0.484 | +| learning_rate | 4.64e-05 | +| loss | -0.032 | +| n_updates | 45776 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000131 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1422 | +| iterations | 7491 | +| time_elapsed | 10785 | +| total_timesteps | 15341568 | +| train/ | | +| approx_kl | 0.009430657 | +| clip_fraction | 0.294 | +| clip_range | 0.0712 | +| entropy_loss | -7.3 | +| explained_variance | 0.184 | +| learning_rate | 4.64e-05 | +| loss | -0.0269 | +| n_updates | 45780 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000356 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1422 | +| iterations | 7492 | +| time_elapsed | 10786 | +| total_timesteps | 15343616 | +| train/ | | +| approx_kl | 0.008780615 | +| clip_fraction | 0.277 | +| clip_range | 0.0712 | +| entropy_loss | -7.19 | +| explained_variance | 0.318 | +| learning_rate | 4.64e-05 | +| loss | -0.0257 | +| n_updates | 45784 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000294 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1422 | +| iterations | 7493 | +| time_elapsed | 10787 | +| total_timesteps | 15345664 | +| train/ | | +| approx_kl | 0.0079156365 | +| clip_fraction | 0.274 | +| clip_range | 0.0712 | +| entropy_loss | -6.58 | +| explained_variance | 0.631 | +| learning_rate | 4.64e-05 | +| loss | -0.0294 | +| n_updates | 45788 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000181 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1422 | +| iterations | 7494 | +| time_elapsed | 10789 | +| total_timesteps | 15347712 | +| train/ | | +| approx_kl | 0.009078607 | +| clip_fraction | 0.322 | +| clip_range | 0.0712 | +| entropy_loss | -7.07 | +| explained_variance | -0.00492 | +| learning_rate | 4.64e-05 | +| loss | -0.036 | +| n_updates | 45792 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000162 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1422 | +| iterations | 7495 | +| time_elapsed | 10790 | +| total_timesteps | 15349760 | +| train/ | | +| approx_kl | 0.009517846 | +| clip_fraction | 0.31 | +| clip_range | 0.0712 | +| entropy_loss | -7.53 | +| explained_variance | 0.0824 | +| learning_rate | 4.64e-05 | +| loss | -0.0334 | +| n_updates | 45796 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000173 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1422 | +| iterations | 7496 | +| time_elapsed | 10792 | +| total_timesteps | 15351808 | +| train/ | | +| approx_kl | 0.009144782 | +| clip_fraction | 0.299 | +| clip_range | 0.0712 | +| entropy_loss | -7.51 | +| explained_variance | -0.236 | +| learning_rate | 4.64e-05 | +| loss | -0.0309 | +| n_updates | 45800 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000126 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1422 | +| iterations | 7497 | +| time_elapsed | 10793 | +| total_timesteps | 15353856 | +| train/ | | +| approx_kl | 0.010564202 | +| clip_fraction | 0.294 | +| clip_range | 0.0712 | +| entropy_loss | -7.2 | +| explained_variance | 0.443 | +| learning_rate | 4.64e-05 | +| loss | -0.0353 | +| n_updates | 45804 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000178 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1422 | +| iterations | 7498 | +| time_elapsed | 10795 | +| total_timesteps | 15355904 | +| train/ | | +| approx_kl | 0.01000288 | +| clip_fraction | 0.319 | +| clip_range | 0.0712 | +| entropy_loss | -7.04 | +| explained_variance | 0.421 | +| learning_rate | 4.64e-05 | +| loss | -0.0292 | +| n_updates | 45808 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000113 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1422 | +| iterations | 7499 | +| time_elapsed | 10796 | +| total_timesteps | 15357952 | +| train/ | | +| approx_kl | 0.009228999 | +| clip_fraction | 0.309 | +| clip_range | 0.0712 | +| entropy_loss | -6.73 | +| explained_variance | 0.669 | +| learning_rate | 4.64e-05 | +| loss | -0.0256 | +| n_updates | 45812 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000129 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1422 | +| iterations | 7500 | +| time_elapsed | 10797 | +| total_timesteps | 15360000 | +| train/ | | +| approx_kl | 0.011582199 | +| clip_fraction | 0.32 | +| clip_range | 0.0712 | +| entropy_loss | -6.81 | +| explained_variance | 0.65 | +| learning_rate | 4.64e-05 | +| loss | -0.0307 | +| n_updates | 45816 | +| policy_gradient_loss | -0.0196 | +| value_loss | 7.14e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1422 | +| iterations | 7501 | +| time_elapsed | 10799 | +| total_timesteps | 15362048 | +| train/ | | +| approx_kl | 0.010559794 | +| clip_fraction | 0.291 | +| clip_range | 0.0712 | +| entropy_loss | -7.02 | +| explained_variance | 0.211 | +| learning_rate | 4.64e-05 | +| loss | -0.0334 | +| n_updates | 45820 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000175 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1422 | +| iterations | 7502 | +| time_elapsed | 10800 | +| total_timesteps | 15364096 | +| train/ | | +| approx_kl | 0.01175008 | +| clip_fraction | 0.314 | +| clip_range | 0.0712 | +| entropy_loss | -7.41 | +| explained_variance | 0.155 | +| learning_rate | 4.64e-05 | +| loss | -0.0357 | +| n_updates | 45824 | +| policy_gradient_loss | -0.0206 | +| value_loss | 9.23e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1422 | +| iterations | 7503 | +| time_elapsed | 10802 | +| total_timesteps | 15366144 | +| train/ | | +| approx_kl | 0.011057068 | +| clip_fraction | 0.336 | +| clip_range | 0.0712 | +| entropy_loss | -7.39 | +| explained_variance | -0.0199 | +| learning_rate | 4.64e-05 | +| loss | -0.0286 | +| n_updates | 45828 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000299 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1422 | +| iterations | 7504 | +| time_elapsed | 10803 | +| total_timesteps | 15368192 | +| train/ | | +| approx_kl | 0.0088331755 | +| clip_fraction | 0.297 | +| clip_range | 0.0712 | +| entropy_loss | -6.89 | +| explained_variance | 0.161 | +| learning_rate | 4.64e-05 | +| loss | -0.0235 | +| n_updates | 45832 | +| policy_gradient_loss | -0.0135 | +| value_loss | 0.000406 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1422 | +| iterations | 7505 | +| time_elapsed | 10804 | +| total_timesteps | 15370240 | +| train/ | | +| approx_kl | 0.010190386 | +| clip_fraction | 0.327 | +| clip_range | 0.0712 | +| entropy_loss | -7.33 | +| explained_variance | -0.272 | +| learning_rate | 4.64e-05 | +| loss | -0.0311 | +| n_updates | 45836 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000128 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1422 | +| iterations | 7506 | +| time_elapsed | 10806 | +| total_timesteps | 15372288 | +| train/ | | +| approx_kl | 0.011694061 | +| clip_fraction | 0.331 | +| clip_range | 0.0712 | +| entropy_loss | -7.49 | +| explained_variance | -0.0629 | +| learning_rate | 4.63e-05 | +| loss | -0.0305 | +| n_updates | 45840 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000106 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1422 | +| iterations | 7507 | +| time_elapsed | 10807 | +| total_timesteps | 15374336 | +| train/ | | +| approx_kl | 0.010450659 | +| clip_fraction | 0.293 | +| clip_range | 0.0712 | +| entropy_loss | -6.74 | +| explained_variance | 0.583 | +| learning_rate | 4.63e-05 | +| loss | -0.0228 | +| n_updates | 45844 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000193 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1422 | +| iterations | 7508 | +| time_elapsed | 10809 | +| total_timesteps | 15376384 | +| train/ | | +| approx_kl | 0.010961823 | +| clip_fraction | 0.288 | +| clip_range | 0.0712 | +| entropy_loss | -7.12 | +| explained_variance | -0.11 | +| learning_rate | 4.63e-05 | +| loss | -0.0347 | +| n_updates | 45848 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000157 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1422 | +| iterations | 7509 | +| time_elapsed | 10810 | +| total_timesteps | 15378432 | +| train/ | | +| approx_kl | 0.011445742 | +| clip_fraction | 0.306 | +| clip_range | 0.0712 | +| entropy_loss | -7.02 | +| explained_variance | 0.336 | +| learning_rate | 4.63e-05 | +| loss | -0.0251 | +| n_updates | 45852 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000153 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1422 | +| iterations | 7510 | +| time_elapsed | 10812 | +| total_timesteps | 15380480 | +| train/ | | +| approx_kl | 0.009374855 | +| clip_fraction | 0.277 | +| clip_range | 0.0712 | +| entropy_loss | -7.33 | +| explained_variance | 0.188 | +| learning_rate | 4.63e-05 | +| loss | -0.0254 | +| n_updates | 45856 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000242 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1422 | +| iterations | 7511 | +| time_elapsed | 10813 | +| total_timesteps | 15382528 | +| train/ | | +| approx_kl | 0.009291472 | +| clip_fraction | 0.313 | +| clip_range | 0.0712 | +| entropy_loss | -7.25 | +| explained_variance | -0.107 | +| learning_rate | 4.63e-05 | +| loss | -0.0254 | +| n_updates | 45860 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000219 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1422 | +| iterations | 7512 | +| time_elapsed | 10815 | +| total_timesteps | 15384576 | +| train/ | | +| approx_kl | 0.011978179 | +| clip_fraction | 0.337 | +| clip_range | 0.0712 | +| entropy_loss | -7.23 | +| explained_variance | -0.246 | +| learning_rate | 4.63e-05 | +| loss | -0.03 | +| n_updates | 45864 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000185 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1422 | +| iterations | 7513 | +| time_elapsed | 10816 | +| total_timesteps | 15386624 | +| train/ | | +| approx_kl | 0.011469204 | +| clip_fraction | 0.276 | +| clip_range | 0.0712 | +| entropy_loss | -7.13 | +| explained_variance | 0.155 | +| learning_rate | 4.63e-05 | +| loss | -0.0286 | +| n_updates | 45868 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000271 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1422 | +| iterations | 7514 | +| time_elapsed | 10817 | +| total_timesteps | 15388672 | +| train/ | | +| approx_kl | 0.010201471 | +| clip_fraction | 0.295 | +| clip_range | 0.0712 | +| entropy_loss | -6.95 | +| explained_variance | 0.271 | +| learning_rate | 4.63e-05 | +| loss | -0.0306 | +| n_updates | 45872 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000237 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1422 | +| iterations | 7515 | +| time_elapsed | 10819 | +| total_timesteps | 15390720 | +| train/ | | +| approx_kl | 0.012350833 | +| clip_fraction | 0.334 | +| clip_range | 0.0712 | +| entropy_loss | -7.36 | +| explained_variance | -0.11 | +| learning_rate | 4.63e-05 | +| loss | -0.0374 | +| n_updates | 45876 | +| policy_gradient_loss | -0.0228 | +| value_loss | 0.000123 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1422 | +| iterations | 7516 | +| time_elapsed | 10820 | +| total_timesteps | 15392768 | +| train/ | | +| approx_kl | 0.010989035 | +| clip_fraction | 0.302 | +| clip_range | 0.0712 | +| entropy_loss | -7.24 | +| explained_variance | 0.387 | +| learning_rate | 4.63e-05 | +| loss | -0.0313 | +| n_updates | 45880 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000121 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1422 | +| iterations | 7517 | +| time_elapsed | 10822 | +| total_timesteps | 15394816 | +| train/ | | +| approx_kl | 0.0110816425 | +| clip_fraction | 0.312 | +| clip_range | 0.0712 | +| entropy_loss | -6.87 | +| explained_variance | 0.536 | +| learning_rate | 4.63e-05 | +| loss | -0.0249 | +| n_updates | 45884 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.00017 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1422 | +| iterations | 7518 | +| time_elapsed | 10823 | +| total_timesteps | 15396864 | +| train/ | | +| approx_kl | 0.011005145 | +| clip_fraction | 0.299 | +| clip_range | 0.0712 | +| entropy_loss | -7.12 | +| explained_variance | 0.305 | +| learning_rate | 4.63e-05 | +| loss | -0.0315 | +| n_updates | 45888 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000132 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1422 | +| iterations | 7519 | +| time_elapsed | 10825 | +| total_timesteps | 15398912 | +| train/ | | +| approx_kl | 0.010506254 | +| clip_fraction | 0.33 | +| clip_range | 0.0712 | +| entropy_loss | -7.12 | +| explained_variance | 0.538 | +| learning_rate | 4.63e-05 | +| loss | -0.0396 | +| n_updates | 45892 | +| policy_gradient_loss | -0.0206 | +| value_loss | 8.92e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1422 | +| iterations | 7520 | +| time_elapsed | 10826 | +| total_timesteps | 15400960 | +| train/ | | +| approx_kl | 0.009518854 | +| clip_fraction | 0.309 | +| clip_range | 0.0712 | +| entropy_loss | -7.06 | +| explained_variance | 0.374 | +| learning_rate | 4.63e-05 | +| loss | -0.0286 | +| n_updates | 45896 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000194 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1422 | +| iterations | 7521 | +| time_elapsed | 10827 | +| total_timesteps | 15403008 | +| train/ | | +| approx_kl | 0.010844268 | +| clip_fraction | 0.315 | +| clip_range | 0.0711 | +| entropy_loss | -6.91 | +| explained_variance | 0.673 | +| learning_rate | 4.63e-05 | +| loss | -0.035 | +| n_updates | 45900 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000102 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1422 | +| iterations | 7522 | +| time_elapsed | 10829 | +| total_timesteps | 15405056 | +| train/ | | +| approx_kl | 0.010334462 | +| clip_fraction | 0.318 | +| clip_range | 0.0711 | +| entropy_loss | -7.29 | +| explained_variance | -0.0491 | +| learning_rate | 4.63e-05 | +| loss | -0.036 | +| n_updates | 45904 | +| policy_gradient_loss | -0.0217 | +| value_loss | 9.43e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1422 | +| iterations | 7523 | +| time_elapsed | 10830 | +| total_timesteps | 15407104 | +| train/ | | +| approx_kl | 0.007592944 | +| clip_fraction | 0.273 | +| clip_range | 0.0711 | +| entropy_loss | -7.33 | +| explained_variance | 0.246 | +| learning_rate | 4.63e-05 | +| loss | -0.031 | +| n_updates | 45908 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000173 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1422 | +| iterations | 7524 | +| time_elapsed | 10832 | +| total_timesteps | 15409152 | +| train/ | | +| approx_kl | 0.008312268 | +| clip_fraction | 0.283 | +| clip_range | 0.0711 | +| entropy_loss | -7.02 | +| explained_variance | 0.421 | +| learning_rate | 4.63e-05 | +| loss | -0.0233 | +| n_updates | 45912 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000191 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1422 | +| iterations | 7525 | +| time_elapsed | 10833 | +| total_timesteps | 15411200 | +| train/ | | +| approx_kl | 0.009105636 | +| clip_fraction | 0.313 | +| clip_range | 0.0711 | +| entropy_loss | -6.91 | +| explained_variance | 0.319 | +| learning_rate | 4.63e-05 | +| loss | -0.0272 | +| n_updates | 45916 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000298 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1422 | +| iterations | 7526 | +| time_elapsed | 10835 | +| total_timesteps | 15413248 | +| train/ | | +| approx_kl | 0.008173549 | +| clip_fraction | 0.282 | +| clip_range | 0.0711 | +| entropy_loss | -6.88 | +| explained_variance | 0.535 | +| learning_rate | 4.63e-05 | +| loss | -0.0173 | +| n_updates | 45920 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000159 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1422 | +| iterations | 7527 | +| time_elapsed | 10836 | +| total_timesteps | 15415296 | +| train/ | | +| approx_kl | 0.008508986 | +| clip_fraction | 0.285 | +| clip_range | 0.0711 | +| entropy_loss | -6.79 | +| explained_variance | 0.492 | +| learning_rate | 4.63e-05 | +| loss | -0.0292 | +| n_updates | 45924 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.0003 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1422 | +| iterations | 7528 | +| time_elapsed | 10837 | +| total_timesteps | 15417344 | +| train/ | | +| approx_kl | 0.010081882 | +| clip_fraction | 0.325 | +| clip_range | 0.0711 | +| entropy_loss | -7.23 | +| explained_variance | 0.358 | +| learning_rate | 4.63e-05 | +| loss | -0.0364 | +| n_updates | 45928 | +| policy_gradient_loss | -0.0236 | +| value_loss | 8.91e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1422 | +| iterations | 7529 | +| time_elapsed | 10839 | +| total_timesteps | 15419392 | +| train/ | | +| approx_kl | 0.009140911 | +| clip_fraction | 0.295 | +| clip_range | 0.0711 | +| entropy_loss | -7.57 | +| explained_variance | -0.0346 | +| learning_rate | 4.63e-05 | +| loss | -0.0345 | +| n_updates | 45932 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000168 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1422 | +| iterations | 7530 | +| time_elapsed | 10840 | +| total_timesteps | 15421440 | +| train/ | | +| approx_kl | 0.007671629 | +| clip_fraction | 0.279 | +| clip_range | 0.0711 | +| entropy_loss | -7.55 | +| explained_variance | -0.125 | +| learning_rate | 4.63e-05 | +| loss | -0.0265 | +| n_updates | 45936 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1422 | +| iterations | 7531 | +| time_elapsed | 10842 | +| total_timesteps | 15423488 | +| train/ | | +| approx_kl | 0.008883795 | +| clip_fraction | 0.291 | +| clip_range | 0.0711 | +| entropy_loss | -7.06 | +| explained_variance | 0.276 | +| learning_rate | 4.63e-05 | +| loss | -0.0302 | +| n_updates | 45940 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000327 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1422 | +| iterations | 7532 | +| time_elapsed | 10843 | +| total_timesteps | 15425536 | +| train/ | | +| approx_kl | 0.008656151 | +| clip_fraction | 0.29 | +| clip_range | 0.0711 | +| entropy_loss | -7.11 | +| explained_variance | 0.194 | +| learning_rate | 4.63e-05 | +| loss | -0.0287 | +| n_updates | 45944 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000309 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1422 | +| iterations | 7533 | +| time_elapsed | 10845 | +| total_timesteps | 15427584 | +| train/ | | +| approx_kl | 0.008984482 | +| clip_fraction | 0.319 | +| clip_range | 0.0711 | +| entropy_loss | -7.36 | +| explained_variance | 0.241 | +| learning_rate | 4.63e-05 | +| loss | -0.0381 | +| n_updates | 45948 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000126 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1422 | +| iterations | 7534 | +| time_elapsed | 10846 | +| total_timesteps | 15429632 | +| train/ | | +| approx_kl | 0.0100921355 | +| clip_fraction | 0.319 | +| clip_range | 0.0711 | +| entropy_loss | -6.74 | +| explained_variance | 0.277 | +| learning_rate | 4.63e-05 | +| loss | -0.0236 | +| n_updates | 45952 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000156 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1422 | +| iterations | 7535 | +| time_elapsed | 10848 | +| total_timesteps | 15431680 | +| train/ | | +| approx_kl | 0.011050063 | +| clip_fraction | 0.308 | +| clip_range | 0.0711 | +| entropy_loss | -7.25 | +| explained_variance | 0.319 | +| learning_rate | 4.63e-05 | +| loss | -0.0305 | +| n_updates | 45956 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000114 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1422 | +| iterations | 7536 | +| time_elapsed | 10849 | +| total_timesteps | 15433728 | +| train/ | | +| approx_kl | 0.008353235 | +| clip_fraction | 0.304 | +| clip_range | 0.0711 | +| entropy_loss | -6.78 | +| explained_variance | 0.362 | +| learning_rate | 4.63e-05 | +| loss | -0.0272 | +| n_updates | 45960 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000306 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1422 | +| iterations | 7537 | +| time_elapsed | 10851 | +| total_timesteps | 15435776 | +| train/ | | +| approx_kl | 0.010431522 | +| clip_fraction | 0.325 | +| clip_range | 0.0711 | +| entropy_loss | -7.19 | +| explained_variance | -0.51 | +| learning_rate | 4.63e-05 | +| loss | -0.0404 | +| n_updates | 45964 | +| policy_gradient_loss | -0.0225 | +| value_loss | 6.15e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1422 | +| iterations | 7538 | +| time_elapsed | 10852 | +| total_timesteps | 15437824 | +| train/ | | +| approx_kl | 0.008863183 | +| clip_fraction | 0.316 | +| clip_range | 0.0711 | +| entropy_loss | -7.09 | +| explained_variance | 0.515 | +| learning_rate | 4.63e-05 | +| loss | -0.0262 | +| n_updates | 45968 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000136 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1422 | +| iterations | 7539 | +| time_elapsed | 10853 | +| total_timesteps | 15439872 | +| train/ | | +| approx_kl | 0.0075376723 | +| clip_fraction | 0.271 | +| clip_range | 0.0711 | +| entropy_loss | -6.99 | +| explained_variance | 0.399 | +| learning_rate | 4.63e-05 | +| loss | -0.02 | +| n_updates | 45972 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000325 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1422 | +| iterations | 7540 | +| time_elapsed | 10855 | +| total_timesteps | 15441920 | +| train/ | | +| approx_kl | 0.00871466 | +| clip_fraction | 0.307 | +| clip_range | 0.0711 | +| entropy_loss | -7.1 | +| explained_variance | 0.383 | +| learning_rate | 4.63e-05 | +| loss | -0.032 | +| n_updates | 45976 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000202 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1422 | +| iterations | 7541 | +| time_elapsed | 10856 | +| total_timesteps | 15443968 | +| train/ | | +| approx_kl | 0.008338911 | +| clip_fraction | 0.286 | +| clip_range | 0.0711 | +| entropy_loss | -7.24 | +| explained_variance | 0.151 | +| learning_rate | 4.63e-05 | +| loss | -0.0242 | +| n_updates | 45980 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000329 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1422 | +| iterations | 7542 | +| time_elapsed | 10858 | +| total_timesteps | 15446016 | +| train/ | | +| approx_kl | 0.012190483 | +| clip_fraction | 0.33 | +| clip_range | 0.0711 | +| entropy_loss | -7.07 | +| explained_variance | 0.555 | +| learning_rate | 4.63e-05 | +| loss | -0.0333 | +| n_updates | 45984 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000107 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1422 | +| iterations | 7543 | +| time_elapsed | 10859 | +| total_timesteps | 15448064 | +| train/ | | +| approx_kl | 0.010306838 | +| clip_fraction | 0.31 | +| clip_range | 0.0711 | +| entropy_loss | -7.05 | +| explained_variance | 0.311 | +| learning_rate | 4.63e-05 | +| loss | -0.0349 | +| n_updates | 45988 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000317 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1422 | +| iterations | 7544 | +| time_elapsed | 10861 | +| total_timesteps | 15450112 | +| train/ | | +| approx_kl | 0.008630514 | +| clip_fraction | 0.298 | +| clip_range | 0.0711 | +| entropy_loss | -7.03 | +| explained_variance | 0.537 | +| learning_rate | 4.63e-05 | +| loss | -0.0331 | +| n_updates | 45992 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000196 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1422 | +| iterations | 7545 | +| time_elapsed | 10862 | +| total_timesteps | 15452160 | +| train/ | | +| approx_kl | 0.0094922 | +| clip_fraction | 0.304 | +| clip_range | 0.0711 | +| entropy_loss | -7.01 | +| explained_variance | -0.278 | +| learning_rate | 4.63e-05 | +| loss | -0.0344 | +| n_updates | 45996 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.00011 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1422 | +| iterations | 7546 | +| time_elapsed | 10863 | +| total_timesteps | 15454208 | +| train/ | | +| approx_kl | 0.008600101 | +| clip_fraction | 0.321 | +| clip_range | 0.0711 | +| entropy_loss | -7.48 | +| explained_variance | 0.00762 | +| learning_rate | 4.63e-05 | +| loss | -0.0361 | +| n_updates | 46000 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000164 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1422 | +| iterations | 7547 | +| time_elapsed | 10865 | +| total_timesteps | 15456256 | +| train/ | | +| approx_kl | 0.009774911 | +| clip_fraction | 0.314 | +| clip_range | 0.0711 | +| entropy_loss | -7.15 | +| explained_variance | 0.0291 | +| learning_rate | 4.63e-05 | +| loss | -0.0326 | +| n_updates | 46004 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000175 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1422 | +| iterations | 7548 | +| time_elapsed | 10866 | +| total_timesteps | 15458304 | +| train/ | | +| approx_kl | 0.010946803 | +| clip_fraction | 0.345 | +| clip_range | 0.0711 | +| entropy_loss | -7.35 | +| explained_variance | -0.326 | +| learning_rate | 4.63e-05 | +| loss | -0.0353 | +| n_updates | 46008 | +| policy_gradient_loss | -0.0233 | +| value_loss | 5.77e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1422 | +| iterations | 7549 | +| time_elapsed | 10868 | +| total_timesteps | 15460352 | +| train/ | | +| approx_kl | 0.008800636 | +| clip_fraction | 0.301 | +| clip_range | 0.0711 | +| entropy_loss | -7.17 | +| explained_variance | 0.203 | +| learning_rate | 4.63e-05 | +| loss | -0.034 | +| n_updates | 46012 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000253 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1422 | +| iterations | 7550 | +| time_elapsed | 10869 | +| total_timesteps | 15462400 | +| train/ | | +| approx_kl | 0.008409286 | +| clip_fraction | 0.28 | +| clip_range | 0.0711 | +| entropy_loss | -6.9 | +| explained_variance | 0.385 | +| learning_rate | 4.63e-05 | +| loss | -0.0292 | +| n_updates | 46016 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000253 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1422 | +| iterations | 7551 | +| time_elapsed | 10871 | +| total_timesteps | 15464448 | +| train/ | | +| approx_kl | 0.008826211 | +| clip_fraction | 0.295 | +| clip_range | 0.0711 | +| entropy_loss | -7.05 | +| explained_variance | 0.357 | +| learning_rate | 4.63e-05 | +| loss | -0.0292 | +| n_updates | 46020 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000235 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1422 | +| iterations | 7552 | +| time_elapsed | 10872 | +| total_timesteps | 15466496 | +| train/ | | +| approx_kl | 0.008589791 | +| clip_fraction | 0.303 | +| clip_range | 0.0711 | +| entropy_loss | -7.04 | +| explained_variance | 0.553 | +| learning_rate | 4.63e-05 | +| loss | -0.0352 | +| n_updates | 46024 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000133 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1422 | +| iterations | 7553 | +| time_elapsed | 10873 | +| total_timesteps | 15468544 | +| train/ | | +| approx_kl | 0.0079976795 | +| clip_fraction | 0.281 | +| clip_range | 0.0711 | +| entropy_loss | -7.06 | +| explained_variance | 0.391 | +| learning_rate | 4.63e-05 | +| loss | -0.0234 | +| n_updates | 46028 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000198 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1422 | +| iterations | 7554 | +| time_elapsed | 10875 | +| total_timesteps | 15470592 | +| train/ | | +| approx_kl | 0.010160198 | +| clip_fraction | 0.311 | +| clip_range | 0.0711 | +| entropy_loss | -7.1 | +| explained_variance | 0.309 | +| learning_rate | 4.63e-05 | +| loss | -0.0296 | +| n_updates | 46032 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000129 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1422 | +| iterations | 7555 | +| time_elapsed | 10876 | +| total_timesteps | 15472640 | +| train/ | | +| approx_kl | 0.008965016 | +| clip_fraction | 0.297 | +| clip_range | 0.0711 | +| entropy_loss | -6.66 | +| explained_variance | 0.541 | +| learning_rate | 4.63e-05 | +| loss | -0.0314 | +| n_updates | 46036 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.00018 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1422 | +| iterations | 7556 | +| time_elapsed | 10878 | +| total_timesteps | 15474688 | +| train/ | | +| approx_kl | 0.0090497695 | +| clip_fraction | 0.297 | +| clip_range | 0.0711 | +| entropy_loss | -7.36 | +| explained_variance | -0.00833 | +| learning_rate | 4.63e-05 | +| loss | -0.032 | +| n_updates | 46040 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000141 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1422 | +| iterations | 7557 | +| time_elapsed | 10879 | +| total_timesteps | 15476736 | +| train/ | | +| approx_kl | 0.008035929 | +| clip_fraction | 0.287 | +| clip_range | 0.0711 | +| entropy_loss | -7.25 | +| explained_variance | 0.187 | +| learning_rate | 4.63e-05 | +| loss | -0.0249 | +| n_updates | 46044 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.00025 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1422 | +| iterations | 7558 | +| time_elapsed | 10881 | +| total_timesteps | 15478784 | +| train/ | | +| approx_kl | 0.009377038 | +| clip_fraction | 0.317 | +| clip_range | 0.0711 | +| entropy_loss | -7.1 | +| explained_variance | 0.575 | +| learning_rate | 4.63e-05 | +| loss | -0.0352 | +| n_updates | 46048 | +| policy_gradient_loss | -0.0214 | +| value_loss | 9.28e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1422 | +| iterations | 7559 | +| time_elapsed | 10882 | +| total_timesteps | 15480832 | +| train/ | | +| approx_kl | 0.00908909 | +| clip_fraction | 0.297 | +| clip_range | 0.0711 | +| entropy_loss | -6.58 | +| explained_variance | 0.514 | +| learning_rate | 4.63e-05 | +| loss | -0.0259 | +| n_updates | 46052 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000236 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1422 | +| iterations | 7560 | +| time_elapsed | 10884 | +| total_timesteps | 15482880 | +| train/ | | +| approx_kl | 0.011400042 | +| clip_fraction | 0.322 | +| clip_range | 0.0711 | +| entropy_loss | -7.2 | +| explained_variance | 0.431 | +| learning_rate | 4.63e-05 | +| loss | -0.0317 | +| n_updates | 46056 | +| policy_gradient_loss | -0.0197 | +| value_loss | 9.36e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1422 | +| iterations | 7561 | +| time_elapsed | 10885 | +| total_timesteps | 15484928 | +| train/ | | +| approx_kl | 0.009100631 | +| clip_fraction | 0.299 | +| clip_range | 0.0711 | +| entropy_loss | -6.98 | +| explained_variance | 0.586 | +| learning_rate | 4.63e-05 | +| loss | -0.025 | +| n_updates | 46060 | +| policy_gradient_loss | -0.0169 | +| value_loss | 9.71e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1422 | +| iterations | 7562 | +| time_elapsed | 10886 | +| total_timesteps | 15486976 | +| train/ | | +| approx_kl | 0.009022454 | +| clip_fraction | 0.286 | +| clip_range | 0.0711 | +| entropy_loss | -6.89 | +| explained_variance | 0.462 | +| learning_rate | 4.63e-05 | +| loss | -0.0246 | +| n_updates | 46064 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000175 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1422 | +| iterations | 7563 | +| time_elapsed | 10888 | +| total_timesteps | 15489024 | +| train/ | | +| approx_kl | 0.00985165 | +| clip_fraction | 0.306 | +| clip_range | 0.0711 | +| entropy_loss | -6.94 | +| explained_variance | 0.351 | +| learning_rate | 4.63e-05 | +| loss | -0.0286 | +| n_updates | 46068 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000232 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1422 | +| iterations | 7564 | +| time_elapsed | 10889 | +| total_timesteps | 15491072 | +| train/ | | +| approx_kl | 0.0075441734 | +| clip_fraction | 0.284 | +| clip_range | 0.0711 | +| entropy_loss | -7.33 | +| explained_variance | 0.217 | +| learning_rate | 4.63e-05 | +| loss | -0.0299 | +| n_updates | 46072 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000253 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1422 | +| iterations | 7565 | +| time_elapsed | 10891 | +| total_timesteps | 15493120 | +| train/ | | +| approx_kl | 0.009650816 | +| clip_fraction | 0.323 | +| clip_range | 0.0711 | +| entropy_loss | -7.35 | +| explained_variance | 0.00779 | +| learning_rate | 4.63e-05 | +| loss | -0.0299 | +| n_updates | 46076 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000123 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1422 | +| iterations | 7566 | +| time_elapsed | 10892 | +| total_timesteps | 15495168 | +| train/ | | +| approx_kl | 0.009009133 | +| clip_fraction | 0.29 | +| clip_range | 0.0711 | +| entropy_loss | -6.47 | +| explained_variance | 0.418 | +| learning_rate | 4.63e-05 | +| loss | -0.0295 | +| n_updates | 46080 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000381 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1422 | +| iterations | 7567 | +| time_elapsed | 10894 | +| total_timesteps | 15497216 | +| train/ | | +| approx_kl | 0.009960894 | +| clip_fraction | 0.312 | +| clip_range | 0.0711 | +| entropy_loss | -7.05 | +| explained_variance | 0.086 | +| learning_rate | 4.63e-05 | +| loss | -0.0289 | +| n_updates | 46084 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000194 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1422 | +| iterations | 7568 | +| time_elapsed | 10895 | +| total_timesteps | 15499264 | +| train/ | | +| approx_kl | 0.010092957 | +| clip_fraction | 0.288 | +| clip_range | 0.0711 | +| entropy_loss | -7.37 | +| explained_variance | -0.0634 | +| learning_rate | 4.63e-05 | +| loss | -0.0327 | +| n_updates | 46088 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000226 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1422 | +| iterations | 7569 | +| time_elapsed | 10897 | +| total_timesteps | 15501312 | +| train/ | | +| approx_kl | 0.008183739 | +| clip_fraction | 0.291 | +| clip_range | 0.0711 | +| entropy_loss | -7.05 | +| explained_variance | 0.478 | +| learning_rate | 4.63e-05 | +| loss | -0.0271 | +| n_updates | 46092 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000125 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1422 | +| iterations | 7570 | +| time_elapsed | 10898 | +| total_timesteps | 15503360 | +| train/ | | +| approx_kl | 0.009492022 | +| clip_fraction | 0.295 | +| clip_range | 0.0711 | +| entropy_loss | -6.9 | +| explained_variance | 0.395 | +| learning_rate | 4.63e-05 | +| loss | -0.0311 | +| n_updates | 46096 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000231 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1422 | +| iterations | 7571 | +| time_elapsed | 10900 | +| total_timesteps | 15505408 | +| train/ | | +| approx_kl | 0.009172845 | +| clip_fraction | 0.314 | +| clip_range | 0.0711 | +| entropy_loss | -6.64 | +| explained_variance | 0.611 | +| learning_rate | 4.63e-05 | +| loss | -0.0305 | +| n_updates | 46100 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000187 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1422 | +| iterations | 7572 | +| time_elapsed | 10901 | +| total_timesteps | 15507456 | +| train/ | | +| approx_kl | 0.009644712 | +| clip_fraction | 0.301 | +| clip_range | 0.0711 | +| entropy_loss | -6.91 | +| explained_variance | 0.472 | +| learning_rate | 4.63e-05 | +| loss | -0.0303 | +| n_updates | 46104 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000162 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1422 | +| iterations | 7573 | +| time_elapsed | 10902 | +| total_timesteps | 15509504 | +| train/ | | +| approx_kl | 0.008754552 | +| clip_fraction | 0.295 | +| clip_range | 0.0711 | +| entropy_loss | -6.83 | +| explained_variance | 0.375 | +| learning_rate | 4.63e-05 | +| loss | -0.0299 | +| n_updates | 46108 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000259 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1422 | +| iterations | 7574 | +| time_elapsed | 10904 | +| total_timesteps | 15511552 | +| train/ | | +| approx_kl | 0.009305792 | +| clip_fraction | 0.321 | +| clip_range | 0.0711 | +| entropy_loss | -7.32 | +| explained_variance | -0.00706 | +| learning_rate | 4.63e-05 | +| loss | -0.0355 | +| n_updates | 46112 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000142 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.14e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1422 | +| iterations | 7575 | +| time_elapsed | 10905 | +| total_timesteps | 15513600 | +| train/ | | +| approx_kl | 0.009315848 | +| clip_fraction | 0.305 | +| clip_range | 0.0711 | +| entropy_loss | -7.22 | +| explained_variance | 0.304 | +| learning_rate | 4.63e-05 | +| loss | -0.03 | +| n_updates | 46116 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000249 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1422 | +| iterations | 7576 | +| time_elapsed | 10907 | +| total_timesteps | 15515648 | +| train/ | | +| approx_kl | 0.0074206986 | +| clip_fraction | 0.262 | +| clip_range | 0.0711 | +| entropy_loss | -6.98 | +| explained_variance | 0.155 | +| learning_rate | 4.63e-05 | +| loss | -0.0247 | +| n_updates | 46120 | +| policy_gradient_loss | -0.0143 | +| value_loss | 0.000431 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1422 | +| iterations | 7577 | +| time_elapsed | 10908 | +| total_timesteps | 15517696 | +| train/ | | +| approx_kl | 0.00935397 | +| clip_fraction | 0.3 | +| clip_range | 0.0711 | +| entropy_loss | -7.18 | +| explained_variance | 0.106 | +| learning_rate | 4.63e-05 | +| loss | -0.0361 | +| n_updates | 46124 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000249 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.14e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1422 | +| iterations | 7578 | +| time_elapsed | 10910 | +| total_timesteps | 15519744 | +| train/ | | +| approx_kl | 0.008535366 | +| clip_fraction | 0.286 | +| clip_range | 0.0711 | +| entropy_loss | -7.07 | +| explained_variance | 0.464 | +| learning_rate | 4.63e-05 | +| loss | -0.0299 | +| n_updates | 46128 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000177 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1422 | +| iterations | 7579 | +| time_elapsed | 10911 | +| total_timesteps | 15521792 | +| train/ | | +| approx_kl | 0.0077737626 | +| clip_fraction | 0.261 | +| clip_range | 0.0711 | +| entropy_loss | -7.02 | +| explained_variance | 0.232 | +| learning_rate | 4.63e-05 | +| loss | -0.0235 | +| n_updates | 46132 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.00024 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1422 | +| iterations | 7580 | +| time_elapsed | 10912 | +| total_timesteps | 15523840 | +| train/ | | +| approx_kl | 0.011042213 | +| clip_fraction | 0.293 | +| clip_range | 0.0711 | +| entropy_loss | -7.07 | +| explained_variance | 0.151 | +| learning_rate | 4.63e-05 | +| loss | -0.0265 | +| n_updates | 46136 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000401 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1422 | +| iterations | 7581 | +| time_elapsed | 10914 | +| total_timesteps | 15525888 | +| train/ | | +| approx_kl | 0.012605123 | +| clip_fraction | 0.341 | +| clip_range | 0.0711 | +| entropy_loss | -6.98 | +| explained_variance | 0.281 | +| learning_rate | 4.63e-05 | +| loss | -0.035 | +| n_updates | 46140 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000151 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1422 | +| iterations | 7582 | +| time_elapsed | 10915 | +| total_timesteps | 15527936 | +| train/ | | +| approx_kl | 0.011442428 | +| clip_fraction | 0.362 | +| clip_range | 0.0711 | +| entropy_loss | -7.47 | +| explained_variance | -0.351 | +| learning_rate | 4.63e-05 | +| loss | -0.0397 | +| n_updates | 46144 | +| policy_gradient_loss | -0.0237 | +| value_loss | 0.000102 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1422 | +| iterations | 7583 | +| time_elapsed | 10917 | +| total_timesteps | 15529984 | +| train/ | | +| approx_kl | 0.010548187 | +| clip_fraction | 0.308 | +| clip_range | 0.0711 | +| entropy_loss | -7.08 | +| explained_variance | 0.315 | +| learning_rate | 4.63e-05 | +| loss | -0.0307 | +| n_updates | 46148 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000153 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1422 | +| iterations | 7584 | +| time_elapsed | 10918 | +| total_timesteps | 15532032 | +| train/ | | +| approx_kl | 0.009792082 | +| clip_fraction | 0.303 | +| clip_range | 0.0711 | +| entropy_loss | -7.18 | +| explained_variance | 0.378 | +| learning_rate | 4.63e-05 | +| loss | -0.0327 | +| n_updates | 46152 | +| policy_gradient_loss | -0.0198 | +| value_loss | 9.47e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1422 | +| iterations | 7585 | +| time_elapsed | 10920 | +| total_timesteps | 15534080 | +| train/ | | +| approx_kl | 0.007005915 | +| clip_fraction | 0.263 | +| clip_range | 0.0711 | +| entropy_loss | -7.34 | +| explained_variance | 0.172 | +| learning_rate | 4.63e-05 | +| loss | -0.0202 | +| n_updates | 46156 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000359 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1422 | +| iterations | 7586 | +| time_elapsed | 10921 | +| total_timesteps | 15536128 | +| train/ | | +| approx_kl | 0.009660393 | +| clip_fraction | 0.291 | +| clip_range | 0.0711 | +| entropy_loss | -6.36 | +| explained_variance | 0.563 | +| learning_rate | 4.63e-05 | +| loss | -0.0297 | +| n_updates | 46160 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000252 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1422 | +| iterations | 7587 | +| time_elapsed | 10922 | +| total_timesteps | 15538176 | +| train/ | | +| approx_kl | 0.012730792 | +| clip_fraction | 0.383 | +| clip_range | 0.0711 | +| entropy_loss | -6.7 | +| explained_variance | 0.775 | +| learning_rate | 4.63e-05 | +| loss | -0.0477 | +| n_updates | 46164 | +| policy_gradient_loss | -0.028 | +| value_loss | 5.47e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1422 | +| iterations | 7588 | +| time_elapsed | 10924 | +| total_timesteps | 15540224 | +| train/ | | +| approx_kl | 0.009045337 | +| clip_fraction | 0.314 | +| clip_range | 0.0711 | +| entropy_loss | -7.35 | +| explained_variance | -0.103 | +| learning_rate | 4.63e-05 | +| loss | -0.0342 | +| n_updates | 46168 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000137 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1422 | +| iterations | 7589 | +| time_elapsed | 10925 | +| total_timesteps | 15542272 | +| train/ | | +| approx_kl | 0.010301502 | +| clip_fraction | 0.3 | +| clip_range | 0.0711 | +| entropy_loss | -7.22 | +| explained_variance | 0.239 | +| learning_rate | 4.63e-05 | +| loss | -0.0345 | +| n_updates | 46172 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000248 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1422 | +| iterations | 7590 | +| time_elapsed | 10927 | +| total_timesteps | 15544320 | +| train/ | | +| approx_kl | 0.010087008 | +| clip_fraction | 0.298 | +| clip_range | 0.0711 | +| entropy_loss | -7.08 | +| explained_variance | 0.409 | +| learning_rate | 4.63e-05 | +| loss | -0.0287 | +| n_updates | 46176 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.00014 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1422 | +| iterations | 7591 | +| time_elapsed | 10928 | +| total_timesteps | 15546368 | +| train/ | | +| approx_kl | 0.010769611 | +| clip_fraction | 0.325 | +| clip_range | 0.0711 | +| entropy_loss | -6.91 | +| explained_variance | 0.476 | +| learning_rate | 4.63e-05 | +| loss | -0.0347 | +| n_updates | 46180 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000193 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1422 | +| iterations | 7592 | +| time_elapsed | 10930 | +| total_timesteps | 15548416 | +| train/ | | +| approx_kl | 0.011575415 | +| clip_fraction | 0.32 | +| clip_range | 0.0711 | +| entropy_loss | -7.22 | +| explained_variance | 0.39 | +| learning_rate | 4.63e-05 | +| loss | -0.0348 | +| n_updates | 46184 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000102 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1422 | +| iterations | 7593 | +| time_elapsed | 10931 | +| total_timesteps | 15550464 | +| train/ | | +| approx_kl | 0.010469416 | +| clip_fraction | 0.331 | +| clip_range | 0.0711 | +| entropy_loss | -7.25 | +| explained_variance | 0.469 | +| learning_rate | 4.63e-05 | +| loss | -0.0291 | +| n_updates | 46188 | +| policy_gradient_loss | -0.0198 | +| value_loss | 7.73e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1422 | +| iterations | 7594 | +| time_elapsed | 10932 | +| total_timesteps | 15552512 | +| train/ | | +| approx_kl | 0.009695163 | +| clip_fraction | 0.305 | +| clip_range | 0.0711 | +| entropy_loss | -7.22 | +| explained_variance | 0.319 | +| learning_rate | 4.63e-05 | +| loss | -0.0318 | +| n_updates | 46192 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000122 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1422 | +| iterations | 7595 | +| time_elapsed | 10934 | +| total_timesteps | 15554560 | +| train/ | | +| approx_kl | 0.010149986 | +| clip_fraction | 0.308 | +| clip_range | 0.0711 | +| entropy_loss | -7.17 | +| explained_variance | 0.453 | +| learning_rate | 4.63e-05 | +| loss | -0.0272 | +| n_updates | 46196 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000109 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1422 | +| iterations | 7596 | +| time_elapsed | 10935 | +| total_timesteps | 15556608 | +| train/ | | +| approx_kl | 0.009401119 | +| clip_fraction | 0.292 | +| clip_range | 0.0711 | +| entropy_loss | -6.27 | +| explained_variance | 0.73 | +| learning_rate | 4.63e-05 | +| loss | -0.0249 | +| n_updates | 46200 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.00014 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1422 | +| iterations | 7597 | +| time_elapsed | 10937 | +| total_timesteps | 15558656 | +| train/ | | +| approx_kl | 0.009914899 | +| clip_fraction | 0.31 | +| clip_range | 0.0711 | +| entropy_loss | -6.9 | +| explained_variance | 0.309 | +| learning_rate | 4.63e-05 | +| loss | -0.0292 | +| n_updates | 46204 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000189 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1422 | +| iterations | 7598 | +| time_elapsed | 10938 | +| total_timesteps | 15560704 | +| train/ | | +| approx_kl | 0.0120048355 | +| clip_fraction | 0.32 | +| clip_range | 0.0711 | +| entropy_loss | -7.04 | +| explained_variance | 0.224 | +| learning_rate | 4.63e-05 | +| loss | -0.031 | +| n_updates | 46208 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000141 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1422 | +| iterations | 7599 | +| time_elapsed | 10940 | +| total_timesteps | 15562752 | +| train/ | | +| approx_kl | 0.010889614 | +| clip_fraction | 0.304 | +| clip_range | 0.0711 | +| entropy_loss | -7.09 | +| explained_variance | 0.292 | +| learning_rate | 4.63e-05 | +| loss | -0.0308 | +| n_updates | 46212 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000151 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1422 | +| iterations | 7600 | +| time_elapsed | 10941 | +| total_timesteps | 15564800 | +| train/ | | +| approx_kl | 0.01060212 | +| clip_fraction | 0.309 | +| clip_range | 0.0711 | +| entropy_loss | -7.28 | +| explained_variance | 0.0749 | +| learning_rate | 4.63e-05 | +| loss | -0.0346 | +| n_updates | 46216 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000271 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1422 | +| iterations | 7601 | +| time_elapsed | 10942 | +| total_timesteps | 15566848 | +| train/ | | +| approx_kl | 0.010683471 | +| clip_fraction | 0.285 | +| clip_range | 0.0711 | +| entropy_loss | -6.86 | +| explained_variance | 0.302 | +| learning_rate | 4.63e-05 | +| loss | -0.0239 | +| n_updates | 46220 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.00033 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1422 | +| iterations | 7602 | +| time_elapsed | 10944 | +| total_timesteps | 15568896 | +| train/ | | +| approx_kl | 0.010255808 | +| clip_fraction | 0.309 | +| clip_range | 0.0711 | +| entropy_loss | -6.82 | +| explained_variance | 0.372 | +| learning_rate | 4.63e-05 | +| loss | -0.0265 | +| n_updates | 46224 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000284 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1422 | +| iterations | 7603 | +| time_elapsed | 10945 | +| total_timesteps | 15570944 | +| train/ | | +| approx_kl | 0.011653615 | +| clip_fraction | 0.319 | +| clip_range | 0.0711 | +| entropy_loss | -7.25 | +| explained_variance | 0.256 | +| learning_rate | 4.63e-05 | +| loss | -0.035 | +| n_updates | 46228 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000172 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1422 | +| iterations | 7604 | +| time_elapsed | 10947 | +| total_timesteps | 15572992 | +| train/ | | +| approx_kl | 0.009581508 | +| clip_fraction | 0.291 | +| clip_range | 0.0711 | +| entropy_loss | -6.87 | +| explained_variance | 0.368 | +| learning_rate | 4.63e-05 | +| loss | -0.0267 | +| n_updates | 46232 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000273 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1422 | +| iterations | 7605 | +| time_elapsed | 10948 | +| total_timesteps | 15575040 | +| train/ | | +| approx_kl | 0.009758748 | +| clip_fraction | 0.302 | +| clip_range | 0.0711 | +| entropy_loss | -6.88 | +| explained_variance | 0.452 | +| learning_rate | 4.63e-05 | +| loss | -0.0324 | +| n_updates | 46236 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000174 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1422 | +| iterations | 7606 | +| time_elapsed | 10950 | +| total_timesteps | 15577088 | +| train/ | | +| approx_kl | 0.008420867 | +| clip_fraction | 0.273 | +| clip_range | 0.0711 | +| entropy_loss | -6.91 | +| explained_variance | 0.461 | +| learning_rate | 4.63e-05 | +| loss | -0.0289 | +| n_updates | 46240 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.00022 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1422 | +| iterations | 7607 | +| time_elapsed | 10951 | +| total_timesteps | 15579136 | +| train/ | | +| approx_kl | 0.008939132 | +| clip_fraction | 0.275 | +| clip_range | 0.0711 | +| entropy_loss | -6.93 | +| explained_variance | 0.254 | +| learning_rate | 4.63e-05 | +| loss | -0.0301 | +| n_updates | 46244 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000308 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1422 | +| iterations | 7608 | +| time_elapsed | 10953 | +| total_timesteps | 15581184 | +| train/ | | +| approx_kl | 0.011494786 | +| clip_fraction | 0.331 | +| clip_range | 0.0711 | +| entropy_loss | -7.17 | +| explained_variance | 0.545 | +| learning_rate | 4.63e-05 | +| loss | -0.0425 | +| n_updates | 46248 | +| policy_gradient_loss | -0.024 | +| value_loss | 7.72e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1422 | +| iterations | 7609 | +| time_elapsed | 10954 | +| total_timesteps | 15583232 | +| train/ | | +| approx_kl | 0.009547913 | +| clip_fraction | 0.293 | +| clip_range | 0.0711 | +| entropy_loss | -7.15 | +| explained_variance | 0.21 | +| learning_rate | 4.63e-05 | +| loss | -0.0307 | +| n_updates | 46252 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000374 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1422 | +| iterations | 7610 | +| time_elapsed | 10955 | +| total_timesteps | 15585280 | +| train/ | | +| approx_kl | 0.011066891 | +| clip_fraction | 0.301 | +| clip_range | 0.0711 | +| entropy_loss | -7.24 | +| explained_variance | 0.134 | +| learning_rate | 4.63e-05 | +| loss | -0.0332 | +| n_updates | 46256 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000278 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1422 | +| iterations | 7611 | +| time_elapsed | 10957 | +| total_timesteps | 15587328 | +| train/ | | +| approx_kl | 0.010898465 | +| clip_fraction | 0.326 | +| clip_range | 0.0711 | +| entropy_loss | -7.21 | +| explained_variance | 0.251 | +| learning_rate | 4.63e-05 | +| loss | -0.0388 | +| n_updates | 46260 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000163 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1422 | +| iterations | 7612 | +| time_elapsed | 10958 | +| total_timesteps | 15589376 | +| train/ | | +| approx_kl | 0.010025774 | +| clip_fraction | 0.303 | +| clip_range | 0.0711 | +| entropy_loss | -7.27 | +| explained_variance | 0.172 | +| learning_rate | 4.63e-05 | +| loss | -0.0304 | +| n_updates | 46264 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000186 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1422 | +| iterations | 7613 | +| time_elapsed | 10960 | +| total_timesteps | 15591424 | +| train/ | | +| approx_kl | 0.009796476 | +| clip_fraction | 0.304 | +| clip_range | 0.0711 | +| entropy_loss | -7.14 | +| explained_variance | 0.246 | +| learning_rate | 4.63e-05 | +| loss | -0.0297 | +| n_updates | 46268 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000323 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1422 | +| iterations | 7614 | +| time_elapsed | 10961 | +| total_timesteps | 15593472 | +| train/ | | +| approx_kl | 0.010051557 | +| clip_fraction | 0.309 | +| clip_range | 0.0711 | +| entropy_loss | -6.97 | +| explained_variance | 0.381 | +| learning_rate | 4.63e-05 | +| loss | -0.033 | +| n_updates | 46272 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000253 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1422 | +| iterations | 7615 | +| time_elapsed | 10963 | +| total_timesteps | 15595520 | +| train/ | | +| approx_kl | 0.011665653 | +| clip_fraction | 0.347 | +| clip_range | 0.0711 | +| entropy_loss | -7.27 | +| explained_variance | -0.101 | +| learning_rate | 4.63e-05 | +| loss | -0.0373 | +| n_updates | 46276 | +| policy_gradient_loss | -0.022 | +| value_loss | 0.000124 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1422 | +| iterations | 7616 | +| time_elapsed | 10964 | +| total_timesteps | 15597568 | +| train/ | | +| approx_kl | 0.010599898 | +| clip_fraction | 0.325 | +| clip_range | 0.0711 | +| entropy_loss | -7.03 | +| explained_variance | 0.557 | +| learning_rate | 4.63e-05 | +| loss | -0.0318 | +| n_updates | 46280 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000129 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1422 | +| iterations | 7617 | +| time_elapsed | 10965 | +| total_timesteps | 15599616 | +| train/ | | +| approx_kl | 0.013561488 | +| clip_fraction | 0.308 | +| clip_range | 0.0711 | +| entropy_loss | -6.56 | +| explained_variance | 0.261 | +| learning_rate | 4.63e-05 | +| loss | -0.026 | +| n_updates | 46284 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000259 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1422 | +| iterations | 7618 | +| time_elapsed | 10967 | +| total_timesteps | 15601664 | +| train/ | | +| approx_kl | 0.009976681 | +| clip_fraction | 0.305 | +| clip_range | 0.0711 | +| entropy_loss | -6.84 | +| explained_variance | 0.393 | +| learning_rate | 4.63e-05 | +| loss | -0.0285 | +| n_updates | 46288 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000216 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1422 | +| iterations | 7619 | +| time_elapsed | 10968 | +| total_timesteps | 15603712 | +| train/ | | +| approx_kl | 0.010335162 | +| clip_fraction | 0.321 | +| clip_range | 0.0711 | +| entropy_loss | -7.39 | +| explained_variance | -0.126 | +| learning_rate | 4.63e-05 | +| loss | -0.0319 | +| n_updates | 46292 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000123 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1422 | +| iterations | 7620 | +| time_elapsed | 10970 | +| total_timesteps | 15605760 | +| train/ | | +| approx_kl | 0.00965224 | +| clip_fraction | 0.318 | +| clip_range | 0.0711 | +| entropy_loss | -7.32 | +| explained_variance | 0.364 | +| learning_rate | 4.63e-05 | +| loss | -0.031 | +| n_updates | 46296 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000115 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1422 | +| iterations | 7621 | +| time_elapsed | 10971 | +| total_timesteps | 15607808 | +| train/ | | +| approx_kl | 0.00907892 | +| clip_fraction | 0.307 | +| clip_range | 0.0711 | +| entropy_loss | -7.29 | +| explained_variance | 0.0513 | +| learning_rate | 4.63e-05 | +| loss | -0.0256 | +| n_updates | 46300 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.00019 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1422 | +| iterations | 7622 | +| time_elapsed | 10972 | +| total_timesteps | 15609856 | +| train/ | | +| approx_kl | 0.008063498 | +| clip_fraction | 0.262 | +| clip_range | 0.0711 | +| entropy_loss | -6.98 | +| explained_variance | 0.309 | +| learning_rate | 4.63e-05 | +| loss | -0.0296 | +| n_updates | 46304 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000341 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1422 | +| iterations | 7623 | +| time_elapsed | 10974 | +| total_timesteps | 15611904 | +| train/ | | +| approx_kl | 0.009267423 | +| clip_fraction | 0.307 | +| clip_range | 0.0711 | +| entropy_loss | -6.66 | +| explained_variance | 0.706 | +| learning_rate | 4.63e-05 | +| loss | -0.0346 | +| n_updates | 46308 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000121 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1422 | +| iterations | 7624 | +| time_elapsed | 10975 | +| total_timesteps | 15613952 | +| train/ | | +| approx_kl | 0.008670613 | +| clip_fraction | 0.287 | +| clip_range | 0.0711 | +| entropy_loss | -6.79 | +| explained_variance | 0.557 | +| learning_rate | 4.63e-05 | +| loss | -0.0311 | +| n_updates | 46312 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.00017 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1422 | +| iterations | 7625 | +| time_elapsed | 10977 | +| total_timesteps | 15616000 | +| train/ | | +| approx_kl | 0.00937273 | +| clip_fraction | 0.276 | +| clip_range | 0.0711 | +| entropy_loss | -6.85 | +| explained_variance | 0.421 | +| learning_rate | 4.63e-05 | +| loss | -0.0321 | +| n_updates | 46316 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000305 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1422 | +| iterations | 7626 | +| time_elapsed | 10978 | +| total_timesteps | 15618048 | +| train/ | | +| approx_kl | 0.0083509255 | +| clip_fraction | 0.307 | +| clip_range | 0.0711 | +| entropy_loss | -7.13 | +| explained_variance | 0.488 | +| learning_rate | 4.63e-05 | +| loss | -0.0321 | +| n_updates | 46320 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000111 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1422 | +| iterations | 7627 | +| time_elapsed | 10979 | +| total_timesteps | 15620096 | +| train/ | | +| approx_kl | 0.009406777 | +| clip_fraction | 0.295 | +| clip_range | 0.0711 | +| entropy_loss | -7.51 | +| explained_variance | -0.059 | +| learning_rate | 4.63e-05 | +| loss | -0.0319 | +| n_updates | 46324 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000201 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1422 | +| iterations | 7628 | +| time_elapsed | 10981 | +| total_timesteps | 15622144 | +| train/ | | +| approx_kl | 0.008253071 | +| clip_fraction | 0.281 | +| clip_range | 0.0711 | +| entropy_loss | -7.33 | +| explained_variance | -0.0463 | +| learning_rate | 4.63e-05 | +| loss | -0.0218 | +| n_updates | 46328 | +| policy_gradient_loss | -0.0145 | +| value_loss | 0.000279 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1422 | +| iterations | 7629 | +| time_elapsed | 10982 | +| total_timesteps | 15624192 | +| train/ | | +| approx_kl | 0.008921938 | +| clip_fraction | 0.297 | +| clip_range | 0.0711 | +| entropy_loss | -6.99 | +| explained_variance | 0.248 | +| learning_rate | 4.63e-05 | +| loss | -0.0238 | +| n_updates | 46332 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000391 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1422 | +| iterations | 7630 | +| time_elapsed | 10984 | +| total_timesteps | 15626240 | +| train/ | | +| approx_kl | 0.010971228 | +| clip_fraction | 0.309 | +| clip_range | 0.0711 | +| entropy_loss | -7.11 | +| explained_variance | 0.156 | +| learning_rate | 4.63e-05 | +| loss | -0.0337 | +| n_updates | 46336 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000212 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1422 | +| iterations | 7631 | +| time_elapsed | 10985 | +| total_timesteps | 15628288 | +| train/ | | +| approx_kl | 0.009805837 | +| clip_fraction | 0.32 | +| clip_range | 0.0711 | +| entropy_loss | -7.39 | +| explained_variance | 0.38 | +| learning_rate | 4.63e-05 | +| loss | -0.0388 | +| n_updates | 46340 | +| policy_gradient_loss | -0.0238 | +| value_loss | 9.4e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1422 | +| iterations | 7632 | +| time_elapsed | 10987 | +| total_timesteps | 15630336 | +| train/ | | +| approx_kl | 0.012340343 | +| clip_fraction | 0.303 | +| clip_range | 0.0711 | +| entropy_loss | -6.92 | +| explained_variance | 0.409 | +| learning_rate | 4.63e-05 | +| loss | -0.0237 | +| n_updates | 46344 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000203 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1422 | +| iterations | 7633 | +| time_elapsed | 10988 | +| total_timesteps | 15632384 | +| train/ | | +| approx_kl | 0.01096737 | +| clip_fraction | 0.312 | +| clip_range | 0.0711 | +| entropy_loss | -7.27 | +| explained_variance | 0.41 | +| learning_rate | 4.63e-05 | +| loss | -0.0361 | +| n_updates | 46348 | +| policy_gradient_loss | -0.022 | +| value_loss | 8.08e-05 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1422 | +| iterations | 7634 | +| time_elapsed | 10989 | +| total_timesteps | 15634432 | +| train/ | | +| approx_kl | 0.01095297 | +| clip_fraction | 0.33 | +| clip_range | 0.0711 | +| entropy_loss | -7.03 | +| explained_variance | 0.308 | +| learning_rate | 4.63e-05 | +| loss | -0.0316 | +| n_updates | 46352 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000205 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1422 | +| iterations | 7635 | +| time_elapsed | 10991 | +| total_timesteps | 15636480 | +| train/ | | +| approx_kl | 0.009495107 | +| clip_fraction | 0.304 | +| clip_range | 0.0711 | +| entropy_loss | -7 | +| explained_variance | 0.427 | +| learning_rate | 4.63e-05 | +| loss | -0.028 | +| n_updates | 46356 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000164 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1422 | +| iterations | 7636 | +| time_elapsed | 10992 | +| total_timesteps | 15638528 | +| train/ | | +| approx_kl | 0.007872346 | +| clip_fraction | 0.266 | +| clip_range | 0.0711 | +| entropy_loss | -6.83 | +| explained_variance | 0.429 | +| learning_rate | 4.63e-05 | +| loss | -0.0213 | +| n_updates | 46360 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000254 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1422 | +| iterations | 7637 | +| time_elapsed | 10994 | +| total_timesteps | 15640576 | +| train/ | | +| approx_kl | 0.010604847 | +| clip_fraction | 0.32 | +| clip_range | 0.0711 | +| entropy_loss | -6.89 | +| explained_variance | 0.597 | +| learning_rate | 4.63e-05 | +| loss | -0.0366 | +| n_updates | 46364 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000101 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1422 | +| iterations | 7638 | +| time_elapsed | 10995 | +| total_timesteps | 15642624 | +| train/ | | +| approx_kl | 0.008581906 | +| clip_fraction | 0.291 | +| clip_range | 0.0711 | +| entropy_loss | -6.92 | +| explained_variance | 0.386 | +| learning_rate | 4.63e-05 | +| loss | -0.0247 | +| n_updates | 46368 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000199 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1422 | +| iterations | 7639 | +| time_elapsed | 10996 | +| total_timesteps | 15644672 | +| train/ | | +| approx_kl | 0.010176245 | +| clip_fraction | 0.3 | +| clip_range | 0.0711 | +| entropy_loss | -6.66 | +| explained_variance | 0.514 | +| learning_rate | 4.63e-05 | +| loss | -0.0264 | +| n_updates | 46372 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000202 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1422 | +| iterations | 7640 | +| time_elapsed | 10998 | +| total_timesteps | 15646720 | +| train/ | | +| approx_kl | 0.010429205 | +| clip_fraction | 0.293 | +| clip_range | 0.0711 | +| entropy_loss | -7.19 | +| explained_variance | 0.158 | +| learning_rate | 4.63e-05 | +| loss | -0.0337 | +| n_updates | 46376 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000178 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1422 | +| iterations | 7641 | +| time_elapsed | 10999 | +| total_timesteps | 15648768 | +| train/ | | +| approx_kl | 0.01063077 | +| clip_fraction | 0.308 | +| clip_range | 0.0711 | +| entropy_loss | -7.24 | +| explained_variance | 0.0118 | +| learning_rate | 4.63e-05 | +| loss | -0.0272 | +| n_updates | 46380 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000343 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1422 | +| iterations | 7642 | +| time_elapsed | 11001 | +| total_timesteps | 15650816 | +| train/ | | +| approx_kl | 0.011845064 | +| clip_fraction | 0.298 | +| clip_range | 0.0711 | +| entropy_loss | -7.12 | +| explained_variance | 0.174 | +| learning_rate | 4.63e-05 | +| loss | -0.0303 | +| n_updates | 46384 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000189 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1422 | +| iterations | 7643 | +| time_elapsed | 11002 | +| total_timesteps | 15652864 | +| train/ | | +| approx_kl | 0.012674377 | +| clip_fraction | 0.36 | +| clip_range | 0.0711 | +| entropy_loss | -7.06 | +| explained_variance | 0.327 | +| learning_rate | 4.63e-05 | +| loss | -0.0413 | +| n_updates | 46388 | +| policy_gradient_loss | -0.0254 | +| value_loss | 9.16e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1422 | +| iterations | 7644 | +| time_elapsed | 11004 | +| total_timesteps | 15654912 | +| train/ | | +| approx_kl | 0.012960814 | +| clip_fraction | 0.329 | +| clip_range | 0.0711 | +| entropy_loss | -7.18 | +| explained_variance | 0.27 | +| learning_rate | 4.63e-05 | +| loss | -0.0301 | +| n_updates | 46392 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000172 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1422 | +| iterations | 7645 | +| time_elapsed | 11005 | +| total_timesteps | 15656960 | +| train/ | | +| approx_kl | 0.012267435 | +| clip_fraction | 0.298 | +| clip_range | 0.0711 | +| entropy_loss | -7.25 | +| explained_variance | -0.0187 | +| learning_rate | 4.63e-05 | +| loss | -0.0298 | +| n_updates | 46396 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000175 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1422 | +| iterations | 7646 | +| time_elapsed | 11006 | +| total_timesteps | 15659008 | +| train/ | | +| approx_kl | 0.009146781 | +| clip_fraction | 0.295 | +| clip_range | 0.0711 | +| entropy_loss | -6.87 | +| explained_variance | 0.594 | +| learning_rate | 4.63e-05 | +| loss | -0.031 | +| n_updates | 46400 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000143 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1422 | +| iterations | 7647 | +| time_elapsed | 11008 | +| total_timesteps | 15661056 | +| train/ | | +| approx_kl | 0.008375087 | +| clip_fraction | 0.298 | +| clip_range | 0.0711 | +| entropy_loss | -6.78 | +| explained_variance | 0.595 | +| learning_rate | 4.63e-05 | +| loss | -0.0232 | +| n_updates | 46404 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.00015 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1422 | +| iterations | 7648 | +| time_elapsed | 11009 | +| total_timesteps | 15663104 | +| train/ | | +| approx_kl | 0.010618902 | +| clip_fraction | 0.318 | +| clip_range | 0.0711 | +| entropy_loss | -6.93 | +| explained_variance | 0.703 | +| learning_rate | 4.63e-05 | +| loss | -0.0345 | +| n_updates | 46408 | +| policy_gradient_loss | -0.0212 | +| value_loss | 6.75e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1422 | +| iterations | 7649 | +| time_elapsed | 11011 | +| total_timesteps | 15665152 | +| train/ | | +| approx_kl | 0.009989761 | +| clip_fraction | 0.306 | +| clip_range | 0.0711 | +| entropy_loss | -7.19 | +| explained_variance | -0.0208 | +| learning_rate | 4.63e-05 | +| loss | -0.0336 | +| n_updates | 46412 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000108 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1422 | +| iterations | 7650 | +| time_elapsed | 11012 | +| total_timesteps | 15667200 | +| train/ | | +| approx_kl | 0.009955399 | +| clip_fraction | 0.322 | +| clip_range | 0.0711 | +| entropy_loss | -7.41 | +| explained_variance | -0.0372 | +| learning_rate | 4.63e-05 | +| loss | -0.031 | +| n_updates | 46416 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000131 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1422 | +| iterations | 7651 | +| time_elapsed | 11014 | +| total_timesteps | 15669248 | +| train/ | | +| approx_kl | 0.010187568 | +| clip_fraction | 0.308 | +| clip_range | 0.0711 | +| entropy_loss | -7.12 | +| explained_variance | 0.187 | +| learning_rate | 4.63e-05 | +| loss | -0.0297 | +| n_updates | 46420 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000215 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1422 | +| iterations | 7652 | +| time_elapsed | 11015 | +| total_timesteps | 15671296 | +| train/ | | +| approx_kl | 0.012272077 | +| clip_fraction | 0.317 | +| clip_range | 0.0711 | +| entropy_loss | -6.97 | +| explained_variance | 0.451 | +| learning_rate | 4.63e-05 | +| loss | -0.0278 | +| n_updates | 46424 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000166 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1422 | +| iterations | 7653 | +| time_elapsed | 11017 | +| total_timesteps | 15673344 | +| train/ | | +| approx_kl | 0.011037406 | +| clip_fraction | 0.313 | +| clip_range | 0.0711 | +| entropy_loss | -7.13 | +| explained_variance | -0.0527 | +| learning_rate | 4.63e-05 | +| loss | -0.031 | +| n_updates | 46428 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000151 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1422 | +| iterations | 7654 | +| time_elapsed | 11018 | +| total_timesteps | 15675392 | +| train/ | | +| approx_kl | 0.011161262 | +| clip_fraction | 0.316 | +| clip_range | 0.0711 | +| entropy_loss | -6.89 | +| explained_variance | 0.272 | +| learning_rate | 4.63e-05 | +| loss | -0.0329 | +| n_updates | 46432 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.00018 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1422 | +| iterations | 7655 | +| time_elapsed | 11019 | +| total_timesteps | 15677440 | +| train/ | | +| approx_kl | 0.013319577 | +| clip_fraction | 0.29 | +| clip_range | 0.0711 | +| entropy_loss | -7.12 | +| explained_variance | -0.286 | +| learning_rate | 4.63e-05 | +| loss | -0.0285 | +| n_updates | 46436 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000123 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1422 | +| iterations | 7656 | +| time_elapsed | 11021 | +| total_timesteps | 15679488 | +| train/ | | +| approx_kl | 0.011299499 | +| clip_fraction | 0.321 | +| clip_range | 0.0711 | +| entropy_loss | -6.6 | +| explained_variance | 0.275 | +| learning_rate | 4.63e-05 | +| loss | -0.0311 | +| n_updates | 46440 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000186 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1422 | +| iterations | 7657 | +| time_elapsed | 11022 | +| total_timesteps | 15681536 | +| train/ | | +| approx_kl | 0.010520201 | +| clip_fraction | 0.308 | +| clip_range | 0.0711 | +| entropy_loss | -6.87 | +| explained_variance | 0.0199 | +| learning_rate | 4.63e-05 | +| loss | -0.0308 | +| n_updates | 46444 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.00037 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1422 | +| iterations | 7658 | +| time_elapsed | 11024 | +| total_timesteps | 15683584 | +| train/ | | +| approx_kl | 0.012253265 | +| clip_fraction | 0.308 | +| clip_range | 0.0711 | +| entropy_loss | -7.13 | +| explained_variance | 0.274 | +| learning_rate | 4.63e-05 | +| loss | -0.0313 | +| n_updates | 46448 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000201 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1422 | +| iterations | 7659 | +| time_elapsed | 11025 | +| total_timesteps | 15685632 | +| train/ | | +| approx_kl | 0.011833886 | +| clip_fraction | 0.335 | +| clip_range | 0.0711 | +| entropy_loss | -7.39 | +| explained_variance | -0.191 | +| learning_rate | 4.63e-05 | +| loss | -0.03 | +| n_updates | 46452 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000124 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1422 | +| iterations | 7660 | +| time_elapsed | 11027 | +| total_timesteps | 15687680 | +| train/ | | +| approx_kl | 0.012388676 | +| clip_fraction | 0.315 | +| clip_range | 0.0711 | +| entropy_loss | -7.19 | +| explained_variance | -0.186 | +| learning_rate | 4.63e-05 | +| loss | -0.0344 | +| n_updates | 46456 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000171 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1422 | +| iterations | 7661 | +| time_elapsed | 11028 | +| total_timesteps | 15689728 | +| train/ | | +| approx_kl | 0.012920471 | +| clip_fraction | 0.307 | +| clip_range | 0.0711 | +| entropy_loss | -7.25 | +| explained_variance | 0.236 | +| learning_rate | 4.63e-05 | +| loss | -0.0346 | +| n_updates | 46460 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000165 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1422 | +| iterations | 7662 | +| time_elapsed | 11030 | +| total_timesteps | 15691776 | +| train/ | | +| approx_kl | 0.009979258 | +| clip_fraction | 0.282 | +| clip_range | 0.0711 | +| entropy_loss | -7.34 | +| explained_variance | -0.0254 | +| learning_rate | 4.63e-05 | +| loss | -0.02 | +| n_updates | 46464 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000312 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1422 | +| iterations | 7663 | +| time_elapsed | 11031 | +| total_timesteps | 15693824 | +| train/ | | +| approx_kl | 0.009036773 | +| clip_fraction | 0.305 | +| clip_range | 0.0711 | +| entropy_loss | -6.49 | +| explained_variance | 0.518 | +| learning_rate | 4.63e-05 | +| loss | -0.0224 | +| n_updates | 46468 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000226 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1422 | +| iterations | 7664 | +| time_elapsed | 11032 | +| total_timesteps | 15695872 | +| train/ | | +| approx_kl | 0.012273304 | +| clip_fraction | 0.33 | +| clip_range | 0.0711 | +| entropy_loss | -6.94 | +| explained_variance | -0.4 | +| learning_rate | 4.63e-05 | +| loss | -0.039 | +| n_updates | 46472 | +| policy_gradient_loss | -0.0227 | +| value_loss | 9.66e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1422 | +| iterations | 7665 | +| time_elapsed | 11034 | +| total_timesteps | 15697920 | +| train/ | | +| approx_kl | 0.0086988155 | +| clip_fraction | 0.289 | +| clip_range | 0.0711 | +| entropy_loss | -7 | +| explained_variance | 0.362 | +| learning_rate | 4.63e-05 | +| loss | -0.0216 | +| n_updates | 46476 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000251 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1422 | +| iterations | 7666 | +| time_elapsed | 11035 | +| total_timesteps | 15699968 | +| train/ | | +| approx_kl | 0.013793174 | +| clip_fraction | 0.309 | +| clip_range | 0.0711 | +| entropy_loss | -6.99 | +| explained_variance | -0.0732 | +| learning_rate | 4.63e-05 | +| loss | -0.0264 | +| n_updates | 46480 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000238 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1422 | +| iterations | 7667 | +| time_elapsed | 11037 | +| total_timesteps | 15702016 | +| train/ | | +| approx_kl | 0.011004953 | +| clip_fraction | 0.325 | +| clip_range | 0.0711 | +| entropy_loss | -6.8 | +| explained_variance | 0.511 | +| learning_rate | 4.63e-05 | +| loss | -0.0267 | +| n_updates | 46484 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000108 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1422 | +| iterations | 7668 | +| time_elapsed | 11038 | +| total_timesteps | 15704064 | +| train/ | | +| approx_kl | 0.011794686 | +| clip_fraction | 0.326 | +| clip_range | 0.0711 | +| entropy_loss | -7.28 | +| explained_variance | -0.253 | +| learning_rate | 4.63e-05 | +| loss | -0.0338 | +| n_updates | 46488 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000125 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1422 | +| iterations | 7669 | +| time_elapsed | 11039 | +| total_timesteps | 15706112 | +| train/ | | +| approx_kl | 0.010690255 | +| clip_fraction | 0.316 | +| clip_range | 0.0711 | +| entropy_loss | -7.37 | +| explained_variance | 0.0146 | +| learning_rate | 4.63e-05 | +| loss | -0.029 | +| n_updates | 46492 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000201 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1422 | +| iterations | 7670 | +| time_elapsed | 11041 | +| total_timesteps | 15708160 | +| train/ | | +| approx_kl | 0.0110335415 | +| clip_fraction | 0.315 | +| clip_range | 0.0711 | +| entropy_loss | -7.26 | +| explained_variance | 0.241 | +| learning_rate | 4.63e-05 | +| loss | -0.0344 | +| n_updates | 46496 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000152 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1422 | +| iterations | 7671 | +| time_elapsed | 11042 | +| total_timesteps | 15710208 | +| train/ | | +| approx_kl | 0.009657346 | +| clip_fraction | 0.285 | +| clip_range | 0.0711 | +| entropy_loss | -6.91 | +| explained_variance | 0.239 | +| learning_rate | 4.63e-05 | +| loss | -0.0241 | +| n_updates | 46500 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000296 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1422 | +| iterations | 7672 | +| time_elapsed | 11044 | +| total_timesteps | 15712256 | +| train/ | | +| approx_kl | 0.012079218 | +| clip_fraction | 0.337 | +| clip_range | 0.0711 | +| entropy_loss | -7.28 | +| explained_variance | 0.0957 | +| learning_rate | 4.63e-05 | +| loss | -0.0359 | +| n_updates | 46504 | +| policy_gradient_loss | -0.0243 | +| value_loss | 9.58e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1422 | +| iterations | 7673 | +| time_elapsed | 11045 | +| total_timesteps | 15714304 | +| train/ | | +| approx_kl | 0.011218411 | +| clip_fraction | 0.321 | +| clip_range | 0.0711 | +| entropy_loss | -7.33 | +| explained_variance | -0.186 | +| learning_rate | 4.63e-05 | +| loss | -0.0386 | +| n_updates | 46508 | +| policy_gradient_loss | -0.0217 | +| value_loss | 5.52e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1422 | +| iterations | 7674 | +| time_elapsed | 11047 | +| total_timesteps | 15716352 | +| train/ | | +| approx_kl | 0.01008597 | +| clip_fraction | 0.305 | +| clip_range | 0.0711 | +| entropy_loss | -6.66 | +| explained_variance | 0.514 | +| learning_rate | 4.63e-05 | +| loss | -0.0314 | +| n_updates | 46512 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000168 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1422 | +| iterations | 7675 | +| time_elapsed | 11048 | +| total_timesteps | 15718400 | +| train/ | | +| approx_kl | 0.009316751 | +| clip_fraction | 0.299 | +| clip_range | 0.0711 | +| entropy_loss | -6.91 | +| explained_variance | 0.279 | +| learning_rate | 4.63e-05 | +| loss | -0.0333 | +| n_updates | 46516 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000322 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1422 | +| iterations | 7676 | +| time_elapsed | 11050 | +| total_timesteps | 15720448 | +| train/ | | +| approx_kl | 0.00930187 | +| clip_fraction | 0.292 | +| clip_range | 0.0711 | +| entropy_loss | -7.18 | +| explained_variance | -0.076 | +| learning_rate | 4.63e-05 | +| loss | -0.0337 | +| n_updates | 46520 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000176 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1422 | +| iterations | 7677 | +| time_elapsed | 11051 | +| total_timesteps | 15722496 | +| train/ | | +| approx_kl | 0.009414227 | +| clip_fraction | 0.299 | +| clip_range | 0.0711 | +| entropy_loss | -6.69 | +| explained_variance | 0.451 | +| learning_rate | 4.63e-05 | +| loss | -0.0306 | +| n_updates | 46524 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000204 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1422 | +| iterations | 7678 | +| time_elapsed | 11053 | +| total_timesteps | 15724544 | +| train/ | | +| approx_kl | 0.010092749 | +| clip_fraction | 0.31 | +| clip_range | 0.0711 | +| entropy_loss | -6.73 | +| explained_variance | 0.373 | +| learning_rate | 4.63e-05 | +| loss | -0.0271 | +| n_updates | 46528 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000293 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1422 | +| iterations | 7679 | +| time_elapsed | 11054 | +| total_timesteps | 15726592 | +| train/ | | +| approx_kl | 0.008441297 | +| clip_fraction | 0.292 | +| clip_range | 0.0711 | +| entropy_loss | -6.78 | +| explained_variance | 0.304 | +| learning_rate | 4.63e-05 | +| loss | -0.0266 | +| n_updates | 46532 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000276 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1422 | +| iterations | 7680 | +| time_elapsed | 11055 | +| total_timesteps | 15728640 | +| train/ | | +| approx_kl | 0.010880206 | +| clip_fraction | 0.321 | +| clip_range | 0.0711 | +| entropy_loss | -6.96 | +| explained_variance | 0.23 | +| learning_rate | 4.63e-05 | +| loss | -0.0335 | +| n_updates | 46536 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000197 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1422 | +| iterations | 7681 | +| time_elapsed | 11057 | +| total_timesteps | 15730688 | +| train/ | | +| approx_kl | 0.008699917 | +| clip_fraction | 0.298 | +| clip_range | 0.0711 | +| entropy_loss | -7.19 | +| explained_variance | 0.144 | +| learning_rate | 4.63e-05 | +| loss | -0.0245 | +| n_updates | 46540 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000286 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1422 | +| iterations | 7682 | +| time_elapsed | 11058 | +| total_timesteps | 15732736 | +| train/ | | +| approx_kl | 0.0109472 | +| clip_fraction | 0.293 | +| clip_range | 0.0711 | +| entropy_loss | -7.16 | +| explained_variance | 0.212 | +| learning_rate | 4.63e-05 | +| loss | -0.0329 | +| n_updates | 46544 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000189 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1422 | +| iterations | 7683 | +| time_elapsed | 11060 | +| total_timesteps | 15734784 | +| train/ | | +| approx_kl | 0.010137978 | +| clip_fraction | 0.302 | +| clip_range | 0.0711 | +| entropy_loss | -7.06 | +| explained_variance | 0.306 | +| learning_rate | 4.63e-05 | +| loss | -0.0359 | +| n_updates | 46548 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000191 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1422 | +| iterations | 7684 | +| time_elapsed | 11061 | +| total_timesteps | 15736832 | +| train/ | | +| approx_kl | 0.008810102 | +| clip_fraction | 0.294 | +| clip_range | 0.0711 | +| entropy_loss | -6.83 | +| explained_variance | 0.471 | +| learning_rate | 4.63e-05 | +| loss | -0.0285 | +| n_updates | 46552 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000157 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1422 | +| iterations | 7685 | +| time_elapsed | 11063 | +| total_timesteps | 15738880 | +| train/ | | +| approx_kl | 0.008549439 | +| clip_fraction | 0.291 | +| clip_range | 0.0711 | +| entropy_loss | -7.38 | +| explained_variance | -0.138 | +| learning_rate | 4.63e-05 | +| loss | -0.0226 | +| n_updates | 46556 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000161 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1422 | +| iterations | 7686 | +| time_elapsed | 11064 | +| total_timesteps | 15740928 | +| train/ | | +| approx_kl | 0.0077039246 | +| clip_fraction | 0.272 | +| clip_range | 0.0711 | +| entropy_loss | -7.43 | +| explained_variance | 0.235 | +| learning_rate | 4.63e-05 | +| loss | -0.0335 | +| n_updates | 46560 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000113 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1422 | +| iterations | 7687 | +| time_elapsed | 11066 | +| total_timesteps | 15742976 | +| train/ | | +| approx_kl | 0.009023147 | +| clip_fraction | 0.297 | +| clip_range | 0.0711 | +| entropy_loss | -7.04 | +| explained_variance | 0.243 | +| learning_rate | 4.63e-05 | +| loss | -0.0322 | +| n_updates | 46564 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000273 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1422 | +| iterations | 7688 | +| time_elapsed | 11067 | +| total_timesteps | 15745024 | +| train/ | | +| approx_kl | 0.01202041 | +| clip_fraction | 0.282 | +| clip_range | 0.0711 | +| entropy_loss | -6.85 | +| explained_variance | 0.358 | +| learning_rate | 4.63e-05 | +| loss | -0.0226 | +| n_updates | 46568 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000246 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1422 | +| iterations | 7689 | +| time_elapsed | 11068 | +| total_timesteps | 15747072 | +| train/ | | +| approx_kl | 0.012068017 | +| clip_fraction | 0.305 | +| clip_range | 0.0711 | +| entropy_loss | -6.69 | +| explained_variance | 0.32 | +| learning_rate | 4.63e-05 | +| loss | -0.0231 | +| n_updates | 46572 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.00031 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1422 | +| iterations | 7690 | +| time_elapsed | 11070 | +| total_timesteps | 15749120 | +| train/ | | +| approx_kl | 0.009679051 | +| clip_fraction | 0.307 | +| clip_range | 0.0711 | +| entropy_loss | -6.39 | +| explained_variance | 0.67 | +| learning_rate | 4.63e-05 | +| loss | -0.0263 | +| n_updates | 46576 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000139 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1422 | +| iterations | 7691 | +| time_elapsed | 11071 | +| total_timesteps | 15751168 | +| train/ | | +| approx_kl | 0.012154669 | +| clip_fraction | 0.347 | +| clip_range | 0.0711 | +| entropy_loss | -7.06 | +| explained_variance | 0.324 | +| learning_rate | 4.63e-05 | +| loss | -0.0389 | +| n_updates | 46580 | +| policy_gradient_loss | -0.0252 | +| value_loss | 5.95e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1422 | +| iterations | 7692 | +| time_elapsed | 11073 | +| total_timesteps | 15753216 | +| train/ | | +| approx_kl | 0.008758832 | +| clip_fraction | 0.293 | +| clip_range | 0.0711 | +| entropy_loss | -6.86 | +| explained_variance | 0.466 | +| learning_rate | 4.63e-05 | +| loss | -0.032 | +| n_updates | 46584 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000161 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1422 | +| iterations | 7693 | +| time_elapsed | 11074 | +| total_timesteps | 15755264 | +| train/ | | +| approx_kl | 0.011512654 | +| clip_fraction | 0.315 | +| clip_range | 0.0711 | +| entropy_loss | -7.06 | +| explained_variance | 0.199 | +| learning_rate | 4.63e-05 | +| loss | -0.0307 | +| n_updates | 46588 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000183 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1422 | +| iterations | 7694 | +| time_elapsed | 11076 | +| total_timesteps | 15757312 | +| train/ | | +| approx_kl | 0.009150725 | +| clip_fraction | 0.289 | +| clip_range | 0.0711 | +| entropy_loss | -6.84 | +| explained_variance | 0.323 | +| learning_rate | 4.63e-05 | +| loss | -0.0328 | +| n_updates | 46592 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.00028 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1422 | +| iterations | 7695 | +| time_elapsed | 11077 | +| total_timesteps | 15759360 | +| train/ | | +| approx_kl | 0.007078833 | +| clip_fraction | 0.276 | +| clip_range | 0.0711 | +| entropy_loss | -7.25 | +| explained_variance | 0.13 | +| learning_rate | 4.63e-05 | +| loss | -0.0288 | +| n_updates | 46596 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000372 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1422 | +| iterations | 7696 | +| time_elapsed | 11078 | +| total_timesteps | 15761408 | +| train/ | | +| approx_kl | 0.008906955 | +| clip_fraction | 0.321 | +| clip_range | 0.0711 | +| entropy_loss | -7.2 | +| explained_variance | 0.294 | +| learning_rate | 4.63e-05 | +| loss | -0.0303 | +| n_updates | 46600 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000159 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1422 | +| iterations | 7697 | +| time_elapsed | 11080 | +| total_timesteps | 15763456 | +| train/ | | +| approx_kl | 0.009189487 | +| clip_fraction | 0.313 | +| clip_range | 0.0711 | +| entropy_loss | -7.04 | +| explained_variance | 0.39 | +| learning_rate | 4.63e-05 | +| loss | -0.0349 | +| n_updates | 46604 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000166 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1422 | +| iterations | 7698 | +| time_elapsed | 11081 | +| total_timesteps | 15765504 | +| train/ | | +| approx_kl | 0.010921926 | +| clip_fraction | 0.303 | +| clip_range | 0.0711 | +| entropy_loss | -6.58 | +| explained_variance | 0.51 | +| learning_rate | 4.63e-05 | +| loss | -0.0218 | +| n_updates | 46608 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.00023 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1422 | +| iterations | 7699 | +| time_elapsed | 11083 | +| total_timesteps | 15767552 | +| train/ | | +| approx_kl | 0.009568352 | +| clip_fraction | 0.322 | +| clip_range | 0.0711 | +| entropy_loss | -6.88 | +| explained_variance | 0.545 | +| learning_rate | 4.63e-05 | +| loss | -0.0321 | +| n_updates | 46612 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000136 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1422 | +| iterations | 7700 | +| time_elapsed | 11084 | +| total_timesteps | 15769600 | +| train/ | | +| approx_kl | 0.007988796 | +| clip_fraction | 0.276 | +| clip_range | 0.0711 | +| entropy_loss | -6.76 | +| explained_variance | 0.303 | +| learning_rate | 4.63e-05 | +| loss | -0.0276 | +| n_updates | 46616 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.00026 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1422 | +| iterations | 7701 | +| time_elapsed | 11086 | +| total_timesteps | 15771648 | +| train/ | | +| approx_kl | 0.008932805 | +| clip_fraction | 0.293 | +| clip_range | 0.0711 | +| entropy_loss | -7.01 | +| explained_variance | 0.204 | +| learning_rate | 4.63e-05 | +| loss | -0.0294 | +| n_updates | 46620 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000262 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1422 | +| iterations | 7702 | +| time_elapsed | 11087 | +| total_timesteps | 15773696 | +| train/ | | +| approx_kl | 0.011533963 | +| clip_fraction | 0.308 | +| clip_range | 0.0711 | +| entropy_loss | -6.93 | +| explained_variance | 0.384 | +| learning_rate | 4.63e-05 | +| loss | -0.0284 | +| n_updates | 46624 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000216 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1422 | +| iterations | 7703 | +| time_elapsed | 11089 | +| total_timesteps | 15775744 | +| train/ | | +| approx_kl | 0.011362158 | +| clip_fraction | 0.311 | +| clip_range | 0.0711 | +| entropy_loss | -7.36 | +| explained_variance | -0.101 | +| learning_rate | 4.63e-05 | +| loss | -0.031 | +| n_updates | 46628 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000214 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1422 | +| iterations | 7704 | +| time_elapsed | 11090 | +| total_timesteps | 15777792 | +| train/ | | +| approx_kl | 0.012240558 | +| clip_fraction | 0.354 | +| clip_range | 0.0711 | +| entropy_loss | -7.12 | +| explained_variance | 0.474 | +| learning_rate | 4.63e-05 | +| loss | -0.0316 | +| n_updates | 46632 | +| policy_gradient_loss | -0.024 | +| value_loss | 6.7e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1422 | +| iterations | 7705 | +| time_elapsed | 11091 | +| total_timesteps | 15779840 | +| train/ | | +| approx_kl | 0.009103891 | +| clip_fraction | 0.276 | +| clip_range | 0.0711 | +| entropy_loss | -6.52 | +| explained_variance | 0.54 | +| learning_rate | 4.63e-05 | +| loss | -0.0333 | +| n_updates | 46636 | +| policy_gradient_loss | -0.0146 | +| value_loss | 0.000258 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1422 | +| iterations | 7706 | +| time_elapsed | 11093 | +| total_timesteps | 15781888 | +| train/ | | +| approx_kl | 0.010502135 | +| clip_fraction | 0.32 | +| clip_range | 0.0711 | +| entropy_loss | -6.85 | +| explained_variance | 0.503 | +| learning_rate | 4.63e-05 | +| loss | -0.0327 | +| n_updates | 46640 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000128 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1422 | +| iterations | 7707 | +| time_elapsed | 11094 | +| total_timesteps | 15783936 | +| train/ | | +| approx_kl | 0.011690712 | +| clip_fraction | 0.339 | +| clip_range | 0.0711 | +| entropy_loss | -6.5 | +| explained_variance | 0.752 | +| learning_rate | 4.63e-05 | +| loss | -0.0317 | +| n_updates | 46644 | +| policy_gradient_loss | -0.0221 | +| value_loss | 7.54e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1422 | +| iterations | 7708 | +| time_elapsed | 11096 | +| total_timesteps | 15785984 | +| train/ | | +| approx_kl | 0.009450985 | +| clip_fraction | 0.307 | +| clip_range | 0.0711 | +| entropy_loss | -7.12 | +| explained_variance | 0.148 | +| learning_rate | 4.63e-05 | +| loss | -0.0282 | +| n_updates | 46648 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000138 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1422 | +| iterations | 7709 | +| time_elapsed | 11097 | +| total_timesteps | 15788032 | +| train/ | | +| approx_kl | 0.01117396 | +| clip_fraction | 0.306 | +| clip_range | 0.0711 | +| entropy_loss | -7.1 | +| explained_variance | 0.364 | +| learning_rate | 4.63e-05 | +| loss | -0.0328 | +| n_updates | 46652 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000126 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1422 | +| iterations | 7710 | +| time_elapsed | 11099 | +| total_timesteps | 15790080 | +| train/ | | +| approx_kl | 0.012712527 | +| clip_fraction | 0.362 | +| clip_range | 0.0711 | +| entropy_loss | -6.51 | +| explained_variance | 0.81 | +| learning_rate | 4.63e-05 | +| loss | -0.0367 | +| n_updates | 46656 | +| policy_gradient_loss | -0.0236 | +| value_loss | 5.73e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1422 | +| iterations | 7711 | +| time_elapsed | 11100 | +| total_timesteps | 15792128 | +| train/ | | +| approx_kl | 0.011904734 | +| clip_fraction | 0.311 | +| clip_range | 0.0711 | +| entropy_loss | -6.88 | +| explained_variance | 0.359 | +| learning_rate | 4.62e-05 | +| loss | -0.03 | +| n_updates | 46660 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000168 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1422 | +| iterations | 7712 | +| time_elapsed | 11102 | +| total_timesteps | 15794176 | +| train/ | | +| approx_kl | 0.008766299 | +| clip_fraction | 0.327 | +| clip_range | 0.0711 | +| entropy_loss | -6.89 | +| explained_variance | 0.177 | +| learning_rate | 4.62e-05 | +| loss | -0.035 | +| n_updates | 46664 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000115 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1422 | +| iterations | 7713 | +| time_elapsed | 11103 | +| total_timesteps | 15796224 | +| train/ | | +| approx_kl | 0.008607935 | +| clip_fraction | 0.287 | +| clip_range | 0.0711 | +| entropy_loss | -6.82 | +| explained_variance | 0.528 | +| learning_rate | 4.62e-05 | +| loss | -0.0315 | +| n_updates | 46668 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000205 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1422 | +| iterations | 7714 | +| time_elapsed | 11104 | +| total_timesteps | 15798272 | +| train/ | | +| approx_kl | 0.008227416 | +| clip_fraction | 0.284 | +| clip_range | 0.0711 | +| entropy_loss | -6.94 | +| explained_variance | 0.485 | +| learning_rate | 4.62e-05 | +| loss | -0.0289 | +| n_updates | 46672 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000158 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1422 | +| iterations | 7715 | +| time_elapsed | 11106 | +| total_timesteps | 15800320 | +| train/ | | +| approx_kl | 0.011931453 | +| clip_fraction | 0.348 | +| clip_range | 0.0711 | +| entropy_loss | -6.77 | +| explained_variance | 0.659 | +| learning_rate | 4.62e-05 | +| loss | -0.0381 | +| n_updates | 46676 | +| policy_gradient_loss | -0.0223 | +| value_loss | 8e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1422 | +| iterations | 7716 | +| time_elapsed | 11107 | +| total_timesteps | 15802368 | +| train/ | | +| approx_kl | 0.010829529 | +| clip_fraction | 0.324 | +| clip_range | 0.071 | +| entropy_loss | -6.96 | +| explained_variance | 0.405 | +| learning_rate | 4.62e-05 | +| loss | -0.0308 | +| n_updates | 46680 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000121 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1422 | +| iterations | 7717 | +| time_elapsed | 11109 | +| total_timesteps | 15804416 | +| train/ | | +| approx_kl | 0.010293996 | +| clip_fraction | 0.3 | +| clip_range | 0.071 | +| entropy_loss | -7.17 | +| explained_variance | 0.286 | +| learning_rate | 4.62e-05 | +| loss | -0.0321 | +| n_updates | 46684 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000156 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1422 | +| iterations | 7718 | +| time_elapsed | 11110 | +| total_timesteps | 15806464 | +| train/ | | +| approx_kl | 0.0146118775 | +| clip_fraction | 0.306 | +| clip_range | 0.071 | +| entropy_loss | -6.86 | +| explained_variance | 0.505 | +| learning_rate | 4.62e-05 | +| loss | -0.0274 | +| n_updates | 46688 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000123 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1422 | +| iterations | 7719 | +| time_elapsed | 11111 | +| total_timesteps | 15808512 | +| train/ | | +| approx_kl | 0.009765059 | +| clip_fraction | 0.313 | +| clip_range | 0.071 | +| entropy_loss | -6.43 | +| explained_variance | 0.751 | +| learning_rate | 4.62e-05 | +| loss | -0.0278 | +| n_updates | 46692 | +| policy_gradient_loss | -0.0192 | +| value_loss | 9.41e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1422 | +| iterations | 7720 | +| time_elapsed | 11113 | +| total_timesteps | 15810560 | +| train/ | | +| approx_kl | 0.0095149735 | +| clip_fraction | 0.307 | +| clip_range | 0.071 | +| entropy_loss | -6.7 | +| explained_variance | 0.654 | +| learning_rate | 4.62e-05 | +| loss | -0.0319 | +| n_updates | 46696 | +| policy_gradient_loss | -0.0194 | +| value_loss | 8.01e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1422 | +| iterations | 7721 | +| time_elapsed | 11114 | +| total_timesteps | 15812608 | +| train/ | | +| approx_kl | 0.008099424 | +| clip_fraction | 0.285 | +| clip_range | 0.071 | +| entropy_loss | -7.01 | +| explained_variance | 0.376 | +| learning_rate | 4.62e-05 | +| loss | -0.0295 | +| n_updates | 46700 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.00014 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1422 | +| iterations | 7722 | +| time_elapsed | 11116 | +| total_timesteps | 15814656 | +| train/ | | +| approx_kl | 0.008210235 | +| clip_fraction | 0.305 | +| clip_range | 0.071 | +| entropy_loss | -7.08 | +| explained_variance | 0.293 | +| learning_rate | 4.62e-05 | +| loss | -0.0279 | +| n_updates | 46704 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000142 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1422 | +| iterations | 7723 | +| time_elapsed | 11117 | +| total_timesteps | 15816704 | +| train/ | | +| approx_kl | 0.011420274 | +| clip_fraction | 0.326 | +| clip_range | 0.071 | +| entropy_loss | -7.26 | +| explained_variance | -0.0769 | +| learning_rate | 4.62e-05 | +| loss | -0.0331 | +| n_updates | 46708 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000158 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1422 | +| iterations | 7724 | +| time_elapsed | 11119 | +| total_timesteps | 15818752 | +| train/ | | +| approx_kl | 0.011090729 | +| clip_fraction | 0.327 | +| clip_range | 0.071 | +| entropy_loss | -7.42 | +| explained_variance | -0.149 | +| learning_rate | 4.62e-05 | +| loss | -0.0324 | +| n_updates | 46712 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000152 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1422 | +| iterations | 7725 | +| time_elapsed | 11120 | +| total_timesteps | 15820800 | +| train/ | | +| approx_kl | 0.0113280695 | +| clip_fraction | 0.308 | +| clip_range | 0.071 | +| entropy_loss | -7.07 | +| explained_variance | 0.164 | +| learning_rate | 4.62e-05 | +| loss | -0.0294 | +| n_updates | 46716 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000293 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1422 | +| iterations | 7726 | +| time_elapsed | 11121 | +| total_timesteps | 15822848 | +| train/ | | +| approx_kl | 0.011685426 | +| clip_fraction | 0.313 | +| clip_range | 0.071 | +| entropy_loss | -5.72 | +| explained_variance | 0.695 | +| learning_rate | 4.62e-05 | +| loss | -0.0283 | +| n_updates | 46720 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.00023 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1422 | +| iterations | 7727 | +| time_elapsed | 11123 | +| total_timesteps | 15824896 | +| train/ | | +| approx_kl | 0.011554552 | +| clip_fraction | 0.361 | +| clip_range | 0.071 | +| entropy_loss | -6.57 | +| explained_variance | 0.718 | +| learning_rate | 4.62e-05 | +| loss | -0.0416 | +| n_updates | 46724 | +| policy_gradient_loss | -0.0248 | +| value_loss | 5.31e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1422 | +| iterations | 7728 | +| time_elapsed | 11124 | +| total_timesteps | 15826944 | +| train/ | | +| approx_kl | 0.0100532025 | +| clip_fraction | 0.298 | +| clip_range | 0.071 | +| entropy_loss | -7.01 | +| explained_variance | 0.548 | +| learning_rate | 4.62e-05 | +| loss | -0.0297 | +| n_updates | 46728 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000113 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1422 | +| iterations | 7729 | +| time_elapsed | 11126 | +| total_timesteps | 15828992 | +| train/ | | +| approx_kl | 0.010946095 | +| clip_fraction | 0.316 | +| clip_range | 0.071 | +| entropy_loss | -6.78 | +| explained_variance | 0.227 | +| learning_rate | 4.62e-05 | +| loss | -0.0313 | +| n_updates | 46732 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000158 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1422 | +| iterations | 7730 | +| time_elapsed | 11127 | +| total_timesteps | 15831040 | +| train/ | | +| approx_kl | 0.011188087 | +| clip_fraction | 0.328 | +| clip_range | 0.071 | +| entropy_loss | -7.24 | +| explained_variance | -0.126 | +| learning_rate | 4.62e-05 | +| loss | -0.0299 | +| n_updates | 46736 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000108 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1422 | +| iterations | 7731 | +| time_elapsed | 11129 | +| total_timesteps | 15833088 | +| train/ | | +| approx_kl | 0.011973598 | +| clip_fraction | 0.338 | +| clip_range | 0.071 | +| entropy_loss | -7 | +| explained_variance | 0.589 | +| learning_rate | 4.62e-05 | +| loss | -0.0348 | +| n_updates | 46740 | +| policy_gradient_loss | -0.0215 | +| value_loss | 8.92e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1422 | +| iterations | 7732 | +| time_elapsed | 11130 | +| total_timesteps | 15835136 | +| train/ | | +| approx_kl | 0.010211984 | +| clip_fraction | 0.314 | +| clip_range | 0.071 | +| entropy_loss | -7.29 | +| explained_variance | -0.0286 | +| learning_rate | 4.62e-05 | +| loss | -0.0307 | +| n_updates | 46744 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000121 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1422 | +| iterations | 7733 | +| time_elapsed | 11131 | +| total_timesteps | 15837184 | +| train/ | | +| approx_kl | 0.010851126 | +| clip_fraction | 0.313 | +| clip_range | 0.071 | +| entropy_loss | -6.89 | +| explained_variance | 0.378 | +| learning_rate | 4.62e-05 | +| loss | -0.0323 | +| n_updates | 46748 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000226 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1422 | +| iterations | 7734 | +| time_elapsed | 11133 | +| total_timesteps | 15839232 | +| train/ | | +| approx_kl | 0.010496367 | +| clip_fraction | 0.29 | +| clip_range | 0.071 | +| entropy_loss | -6.63 | +| explained_variance | 0.366 | +| learning_rate | 4.62e-05 | +| loss | -0.0312 | +| n_updates | 46752 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000364 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1422 | +| iterations | 7735 | +| time_elapsed | 11134 | +| total_timesteps | 15841280 | +| train/ | | +| approx_kl | 0.011331124 | +| clip_fraction | 0.328 | +| clip_range | 0.071 | +| entropy_loss | -6.4 | +| explained_variance | 0.529 | +| learning_rate | 4.62e-05 | +| loss | -0.0268 | +| n_updates | 46756 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000177 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1422 | +| iterations | 7736 | +| time_elapsed | 11136 | +| total_timesteps | 15843328 | +| train/ | | +| approx_kl | 0.012077296 | +| clip_fraction | 0.309 | +| clip_range | 0.071 | +| entropy_loss | -6.78 | +| explained_variance | 0.494 | +| learning_rate | 4.62e-05 | +| loss | -0.0314 | +| n_updates | 46760 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000126 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.315 | +| time/ | | +| fps | 1422 | +| iterations | 7737 | +| time_elapsed | 11137 | +| total_timesteps | 15845376 | +| train/ | | +| approx_kl | 0.011131322 | +| clip_fraction | 0.317 | +| clip_range | 0.071 | +| entropy_loss | -7.32 | +| explained_variance | -0.0411 | +| learning_rate | 4.62e-05 | +| loss | -0.0299 | +| n_updates | 46764 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000191 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1422 | +| iterations | 7738 | +| time_elapsed | 11139 | +| total_timesteps | 15847424 | +| train/ | | +| approx_kl | 0.009935592 | +| clip_fraction | 0.304 | +| clip_range | 0.071 | +| entropy_loss | -7.07 | +| explained_variance | 0.348 | +| learning_rate | 4.62e-05 | +| loss | -0.0308 | +| n_updates | 46768 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000239 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1422 | +| iterations | 7739 | +| time_elapsed | 11140 | +| total_timesteps | 15849472 | +| train/ | | +| approx_kl | 0.010351704 | +| clip_fraction | 0.295 | +| clip_range | 0.071 | +| entropy_loss | -6.96 | +| explained_variance | 0.026 | +| learning_rate | 4.62e-05 | +| loss | -0.0212 | +| n_updates | 46772 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000331 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1422 | +| iterations | 7740 | +| time_elapsed | 11142 | +| total_timesteps | 15851520 | +| train/ | | +| approx_kl | 0.010621373 | +| clip_fraction | 0.322 | +| clip_range | 0.071 | +| entropy_loss | -7.21 | +| explained_variance | 0.186 | +| learning_rate | 4.62e-05 | +| loss | -0.0298 | +| n_updates | 46776 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000175 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1422 | +| iterations | 7741 | +| time_elapsed | 11143 | +| total_timesteps | 15853568 | +| train/ | | +| approx_kl | 0.0081680175 | +| clip_fraction | 0.298 | +| clip_range | 0.071 | +| entropy_loss | -7.09 | +| explained_variance | 0.389 | +| learning_rate | 4.62e-05 | +| loss | -0.0297 | +| n_updates | 46780 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.00019 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1422 | +| iterations | 7742 | +| time_elapsed | 11144 | +| total_timesteps | 15855616 | +| train/ | | +| approx_kl | 0.0102071185 | +| clip_fraction | 0.332 | +| clip_range | 0.071 | +| entropy_loss | -7.25 | +| explained_variance | 0.137 | +| learning_rate | 4.62e-05 | +| loss | -0.0326 | +| n_updates | 46784 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000177 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1422 | +| iterations | 7743 | +| time_elapsed | 11146 | +| total_timesteps | 15857664 | +| train/ | | +| approx_kl | 0.011086314 | +| clip_fraction | 0.307 | +| clip_range | 0.071 | +| entropy_loss | -6.87 | +| explained_variance | 0.321 | +| learning_rate | 4.62e-05 | +| loss | -0.0323 | +| n_updates | 46788 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.0002 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1422 | +| iterations | 7744 | +| time_elapsed | 11147 | +| total_timesteps | 15859712 | +| train/ | | +| approx_kl | 0.0107646985 | +| clip_fraction | 0.331 | +| clip_range | 0.071 | +| entropy_loss | -6.66 | +| explained_variance | 0.183 | +| learning_rate | 4.62e-05 | +| loss | -0.0335 | +| n_updates | 46792 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000202 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1422 | +| iterations | 7745 | +| time_elapsed | 11149 | +| total_timesteps | 15861760 | +| train/ | | +| approx_kl | 0.011073839 | +| clip_fraction | 0.331 | +| clip_range | 0.071 | +| entropy_loss | -6.41 | +| explained_variance | 0.538 | +| learning_rate | 4.62e-05 | +| loss | -0.0317 | +| n_updates | 46796 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000165 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1422 | +| iterations | 7746 | +| time_elapsed | 11150 | +| total_timesteps | 15863808 | +| train/ | | +| approx_kl | 0.010736797 | +| clip_fraction | 0.328 | +| clip_range | 0.071 | +| entropy_loss | -6.93 | +| explained_variance | 0.471 | +| learning_rate | 4.62e-05 | +| loss | -0.0405 | +| n_updates | 46800 | +| policy_gradient_loss | -0.0219 | +| value_loss | 9.07e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1422 | +| iterations | 7747 | +| time_elapsed | 11151 | +| total_timesteps | 15865856 | +| train/ | | +| approx_kl | 0.012109805 | +| clip_fraction | 0.317 | +| clip_range | 0.071 | +| entropy_loss | -6.88 | +| explained_variance | 0.513 | +| learning_rate | 4.62e-05 | +| loss | -0.0311 | +| n_updates | 46804 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000116 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1422 | +| iterations | 7748 | +| time_elapsed | 11153 | +| total_timesteps | 15867904 | +| train/ | | +| approx_kl | 0.010278862 | +| clip_fraction | 0.315 | +| clip_range | 0.071 | +| entropy_loss | -7.22 | +| explained_variance | -0.0342 | +| learning_rate | 4.62e-05 | +| loss | -0.0329 | +| n_updates | 46808 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000163 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1422 | +| iterations | 7749 | +| time_elapsed | 11154 | +| total_timesteps | 15869952 | +| train/ | | +| approx_kl | 0.009068634 | +| clip_fraction | 0.295 | +| clip_range | 0.071 | +| entropy_loss | -7.26 | +| explained_variance | 0.374 | +| learning_rate | 4.62e-05 | +| loss | -0.0311 | +| n_updates | 46812 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000146 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1422 | +| iterations | 7750 | +| time_elapsed | 11156 | +| total_timesteps | 15872000 | +| train/ | | +| approx_kl | 0.01017501 | +| clip_fraction | 0.292 | +| clip_range | 0.071 | +| entropy_loss | -6.89 | +| explained_variance | 0.46 | +| learning_rate | 4.62e-05 | +| loss | -0.0303 | +| n_updates | 46816 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000168 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1422 | +| iterations | 7751 | +| time_elapsed | 11157 | +| total_timesteps | 15874048 | +| train/ | | +| approx_kl | 0.008934675 | +| clip_fraction | 0.3 | +| clip_range | 0.071 | +| entropy_loss | -7.1 | +| explained_variance | 0.258 | +| learning_rate | 4.62e-05 | +| loss | -0.0309 | +| n_updates | 46820 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000113 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1422 | +| iterations | 7752 | +| time_elapsed | 11158 | +| total_timesteps | 15876096 | +| train/ | | +| approx_kl | 0.009753464 | +| clip_fraction | 0.306 | +| clip_range | 0.071 | +| entropy_loss | -6.57 | +| explained_variance | 0.472 | +| learning_rate | 4.62e-05 | +| loss | -0.0262 | +| n_updates | 46824 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000283 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1422 | +| iterations | 7753 | +| time_elapsed | 11160 | +| total_timesteps | 15878144 | +| train/ | | +| approx_kl | 0.011992517 | +| clip_fraction | 0.271 | +| clip_range | 0.071 | +| entropy_loss | -6.7 | +| explained_variance | 0.528 | +| learning_rate | 4.62e-05 | +| loss | -0.0305 | +| n_updates | 46828 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000195 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1422 | +| iterations | 7754 | +| time_elapsed | 11161 | +| total_timesteps | 15880192 | +| train/ | | +| approx_kl | 0.01096282 | +| clip_fraction | 0.305 | +| clip_range | 0.071 | +| entropy_loss | -7.06 | +| explained_variance | 0.278 | +| learning_rate | 4.62e-05 | +| loss | -0.0307 | +| n_updates | 46832 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000167 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.306 | +| time/ | | +| fps | 1422 | +| iterations | 7755 | +| time_elapsed | 11163 | +| total_timesteps | 15882240 | +| train/ | | +| approx_kl | 0.009165433 | +| clip_fraction | 0.287 | +| clip_range | 0.071 | +| entropy_loss | -7.16 | +| explained_variance | 0.242 | +| learning_rate | 4.62e-05 | +| loss | -0.0258 | +| n_updates | 46836 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000202 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.298 | +| time/ | | +| fps | 1422 | +| iterations | 7756 | +| time_elapsed | 11164 | +| total_timesteps | 15884288 | +| train/ | | +| approx_kl | 0.010441833 | +| clip_fraction | 0.279 | +| clip_range | 0.071 | +| entropy_loss | -6.42 | +| explained_variance | 0.453 | +| learning_rate | 4.62e-05 | +| loss | -0.0292 | +| n_updates | 46840 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000293 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.298 | +| time/ | | +| fps | 1422 | +| iterations | 7757 | +| time_elapsed | 11166 | +| total_timesteps | 15886336 | +| train/ | | +| approx_kl | 0.009291114 | +| clip_fraction | 0.295 | +| clip_range | 0.071 | +| entropy_loss | -6.7 | +| explained_variance | 0.439 | +| learning_rate | 4.62e-05 | +| loss | -0.0335 | +| n_updates | 46844 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000196 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.298 | +| time/ | | +| fps | 1422 | +| iterations | 7758 | +| time_elapsed | 11167 | +| total_timesteps | 15888384 | +| train/ | | +| approx_kl | 0.008400571 | +| clip_fraction | 0.294 | +| clip_range | 0.071 | +| entropy_loss | -7.03 | +| explained_variance | 0.285 | +| learning_rate | 4.62e-05 | +| loss | -0.0274 | +| n_updates | 46848 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000152 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.297 | +| time/ | | +| fps | 1422 | +| iterations | 7759 | +| time_elapsed | 11168 | +| total_timesteps | 15890432 | +| train/ | | +| approx_kl | 0.011011372 | +| clip_fraction | 0.295 | +| clip_range | 0.071 | +| entropy_loss | -7.42 | +| explained_variance | -0.037 | +| learning_rate | 4.62e-05 | +| loss | -0.0352 | +| n_updates | 46852 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000142 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 1422 | +| iterations | 7760 | +| time_elapsed | 11170 | +| total_timesteps | 15892480 | +| train/ | | +| approx_kl | 0.010385654 | +| clip_fraction | 0.297 | +| clip_range | 0.071 | +| entropy_loss | -7.24 | +| explained_variance | 0.315 | +| learning_rate | 4.62e-05 | +| loss | -0.0244 | +| n_updates | 46856 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000199 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 1422 | +| iterations | 7761 | +| time_elapsed | 11171 | +| total_timesteps | 15894528 | +| train/ | | +| approx_kl | 0.011895176 | +| clip_fraction | 0.296 | +| clip_range | 0.071 | +| entropy_loss | -7.13 | +| explained_variance | 0.401 | +| learning_rate | 4.62e-05 | +| loss | -0.0284 | +| n_updates | 46860 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000158 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.297 | +| time/ | | +| fps | 1422 | +| iterations | 7762 | +| time_elapsed | 11173 | +| total_timesteps | 15896576 | +| train/ | | +| approx_kl | 0.011684629 | +| clip_fraction | 0.332 | +| clip_range | 0.071 | +| entropy_loss | -7.12 | +| explained_variance | 0.297 | +| learning_rate | 4.62e-05 | +| loss | -0.0391 | +| n_updates | 46864 | +| policy_gradient_loss | -0.0223 | +| value_loss | 0.000106 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.298 | +| time/ | | +| fps | 1422 | +| iterations | 7763 | +| time_elapsed | 11174 | +| total_timesteps | 15898624 | +| train/ | | +| approx_kl | 0.008639277 | +| clip_fraction | 0.302 | +| clip_range | 0.071 | +| entropy_loss | -7.29 | +| explained_variance | 0.37 | +| learning_rate | 4.62e-05 | +| loss | -0.0342 | +| n_updates | 46868 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000143 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.298 | +| time/ | | +| fps | 1422 | +| iterations | 7764 | +| time_elapsed | 11175 | +| total_timesteps | 15900672 | +| train/ | | +| approx_kl | 0.010355467 | +| clip_fraction | 0.307 | +| clip_range | 0.071 | +| entropy_loss | -6.98 | +| explained_variance | 0.39 | +| learning_rate | 4.62e-05 | +| loss | -0.0244 | +| n_updates | 46872 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000105 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.298 | +| time/ | | +| fps | 1422 | +| iterations | 7765 | +| time_elapsed | 11177 | +| total_timesteps | 15902720 | +| train/ | | +| approx_kl | 0.009266572 | +| clip_fraction | 0.299 | +| clip_range | 0.071 | +| entropy_loss | -6.87 | +| explained_variance | 0.62 | +| learning_rate | 4.62e-05 | +| loss | -0.0377 | +| n_updates | 46876 | +| policy_gradient_loss | -0.0191 | +| value_loss | 9.36e-05 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.297 | +| time/ | | +| fps | 1422 | +| iterations | 7766 | +| time_elapsed | 11178 | +| total_timesteps | 15904768 | +| train/ | | +| approx_kl | 0.0110496 | +| clip_fraction | 0.292 | +| clip_range | 0.071 | +| entropy_loss | -7.2 | +| explained_variance | 0.0743 | +| learning_rate | 4.62e-05 | +| loss | -0.0285 | +| n_updates | 46880 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000168 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.297 | +| time/ | | +| fps | 1422 | +| iterations | 7767 | +| time_elapsed | 11180 | +| total_timesteps | 15906816 | +| train/ | | +| approx_kl | 0.010965234 | +| clip_fraction | 0.326 | +| clip_range | 0.071 | +| entropy_loss | -6.89 | +| explained_variance | 0.494 | +| learning_rate | 4.62e-05 | +| loss | -0.0292 | +| n_updates | 46884 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000107 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.295 | +| time/ | | +| fps | 1422 | +| iterations | 7768 | +| time_elapsed | 11181 | +| total_timesteps | 15908864 | +| train/ | | +| approx_kl | 0.011328163 | +| clip_fraction | 0.302 | +| clip_range | 0.071 | +| entropy_loss | -7.19 | +| explained_variance | -0.0197 | +| learning_rate | 4.62e-05 | +| loss | -0.0297 | +| n_updates | 46888 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000148 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.304 | +| time/ | | +| fps | 1422 | +| iterations | 7769 | +| time_elapsed | 11183 | +| total_timesteps | 15910912 | +| train/ | | +| approx_kl | 0.010529103 | +| clip_fraction | 0.331 | +| clip_range | 0.071 | +| entropy_loss | -7.08 | +| explained_variance | 0.519 | +| learning_rate | 4.62e-05 | +| loss | -0.0329 | +| n_updates | 46892 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000101 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1422 | +| iterations | 7770 | +| time_elapsed | 11184 | +| total_timesteps | 15912960 | +| train/ | | +| approx_kl | 0.010779223 | +| clip_fraction | 0.307 | +| clip_range | 0.071 | +| entropy_loss | -6.46 | +| explained_variance | 0.539 | +| learning_rate | 4.62e-05 | +| loss | -0.0219 | +| n_updates | 46896 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000171 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1422 | +| iterations | 7771 | +| time_elapsed | 11185 | +| total_timesteps | 15915008 | +| train/ | | +| approx_kl | 0.012893798 | +| clip_fraction | 0.332 | +| clip_range | 0.071 | +| entropy_loss | -6.57 | +| explained_variance | 0.698 | +| learning_rate | 4.62e-05 | +| loss | -0.0365 | +| n_updates | 46900 | +| policy_gradient_loss | -0.0199 | +| value_loss | 7.32e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1422 | +| iterations | 7772 | +| time_elapsed | 11187 | +| total_timesteps | 15917056 | +| train/ | | +| approx_kl | 0.010472458 | +| clip_fraction | 0.328 | +| clip_range | 0.071 | +| entropy_loss | -6.74 | +| explained_variance | 0.626 | +| learning_rate | 4.62e-05 | +| loss | -0.0345 | +| n_updates | 46904 | +| policy_gradient_loss | -0.021 | +| value_loss | 9.52e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1422 | +| iterations | 7773 | +| time_elapsed | 11188 | +| total_timesteps | 15919104 | +| train/ | | +| approx_kl | 0.010284504 | +| clip_fraction | 0.275 | +| clip_range | 0.071 | +| entropy_loss | -7.04 | +| explained_variance | 0.258 | +| learning_rate | 4.62e-05 | +| loss | -0.028 | +| n_updates | 46908 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000291 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1422 | +| iterations | 7774 | +| time_elapsed | 11190 | +| total_timesteps | 15921152 | +| train/ | | +| approx_kl | 0.011407845 | +| clip_fraction | 0.313 | +| clip_range | 0.071 | +| entropy_loss | -6.46 | +| explained_variance | 0.519 | +| learning_rate | 4.62e-05 | +| loss | -0.0206 | +| n_updates | 46912 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000213 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1422 | +| iterations | 7775 | +| time_elapsed | 11191 | +| total_timesteps | 15923200 | +| train/ | | +| approx_kl | 0.010626191 | +| clip_fraction | 0.316 | +| clip_range | 0.071 | +| entropy_loss | -6.95 | +| explained_variance | 0.233 | +| learning_rate | 4.62e-05 | +| loss | -0.0283 | +| n_updates | 46916 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000157 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1422 | +| iterations | 7776 | +| time_elapsed | 11193 | +| total_timesteps | 15925248 | +| train/ | | +| approx_kl | 0.012418404 | +| clip_fraction | 0.332 | +| clip_range | 0.071 | +| entropy_loss | -7.17 | +| explained_variance | -0.25 | +| learning_rate | 4.62e-05 | +| loss | -0.0325 | +| n_updates | 46920 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000124 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1422 | +| iterations | 7777 | +| time_elapsed | 11194 | +| total_timesteps | 15927296 | +| train/ | | +| approx_kl | 0.011973968 | +| clip_fraction | 0.329 | +| clip_range | 0.071 | +| entropy_loss | -7.36 | +| explained_variance | 0.0367 | +| learning_rate | 4.62e-05 | +| loss | -0.0339 | +| n_updates | 46924 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000166 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1422 | +| iterations | 7778 | +| time_elapsed | 11195 | +| total_timesteps | 15929344 | +| train/ | | +| approx_kl | 0.012678401 | +| clip_fraction | 0.351 | +| clip_range | 0.071 | +| entropy_loss | -7.34 | +| explained_variance | -0.257 | +| learning_rate | 4.62e-05 | +| loss | -0.0351 | +| n_updates | 46928 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000109 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1422 | +| iterations | 7779 | +| time_elapsed | 11197 | +| total_timesteps | 15931392 | +| train/ | | +| approx_kl | 0.010133477 | +| clip_fraction | 0.3 | +| clip_range | 0.071 | +| entropy_loss | -6.73 | +| explained_variance | 0.471 | +| learning_rate | 4.62e-05 | +| loss | -0.0295 | +| n_updates | 46932 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000135 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1422 | +| iterations | 7780 | +| time_elapsed | 11198 | +| total_timesteps | 15933440 | +| train/ | | +| approx_kl | 0.011701047 | +| clip_fraction | 0.343 | +| clip_range | 0.071 | +| entropy_loss | -6.66 | +| explained_variance | 0.662 | +| learning_rate | 4.62e-05 | +| loss | -0.0324 | +| n_updates | 46936 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000104 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1422 | +| iterations | 7781 | +| time_elapsed | 11200 | +| total_timesteps | 15935488 | +| train/ | | +| approx_kl | 0.011311434 | +| clip_fraction | 0.295 | +| clip_range | 0.071 | +| entropy_loss | -6.82 | +| explained_variance | 0.434 | +| learning_rate | 4.62e-05 | +| loss | -0.0296 | +| n_updates | 46940 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000188 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1422 | +| iterations | 7782 | +| time_elapsed | 11201 | +| total_timesteps | 15937536 | +| train/ | | +| approx_kl | 0.010550659 | +| clip_fraction | 0.294 | +| clip_range | 0.071 | +| entropy_loss | -7.16 | +| explained_variance | 0.244 | +| learning_rate | 4.62e-05 | +| loss | -0.0287 | +| n_updates | 46944 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000254 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1422 | +| iterations | 7783 | +| time_elapsed | 11203 | +| total_timesteps | 15939584 | +| train/ | | +| approx_kl | 0.011614836 | +| clip_fraction | 0.322 | +| clip_range | 0.071 | +| entropy_loss | -6.71 | +| explained_variance | 0.642 | +| learning_rate | 4.62e-05 | +| loss | -0.0351 | +| n_updates | 46948 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000124 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1422 | +| iterations | 7784 | +| time_elapsed | 11204 | +| total_timesteps | 15941632 | +| train/ | | +| approx_kl | 0.011476858 | +| clip_fraction | 0.322 | +| clip_range | 0.071 | +| entropy_loss | -6.87 | +| explained_variance | 0.261 | +| learning_rate | 4.62e-05 | +| loss | -0.0397 | +| n_updates | 46952 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000149 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1422 | +| iterations | 7785 | +| time_elapsed | 11206 | +| total_timesteps | 15943680 | +| train/ | | +| approx_kl | 0.009636562 | +| clip_fraction | 0.275 | +| clip_range | 0.071 | +| entropy_loss | -6.85 | +| explained_variance | 0.531 | +| learning_rate | 4.62e-05 | +| loss | -0.035 | +| n_updates | 46956 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000137 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1422 | +| iterations | 7786 | +| time_elapsed | 11207 | +| total_timesteps | 15945728 | +| train/ | | +| approx_kl | 0.009963851 | +| clip_fraction | 0.305 | +| clip_range | 0.071 | +| entropy_loss | -6.81 | +| explained_variance | 0.604 | +| learning_rate | 4.62e-05 | +| loss | -0.0352 | +| n_updates | 46960 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000112 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1422 | +| iterations | 7787 | +| time_elapsed | 11209 | +| total_timesteps | 15947776 | +| train/ | | +| approx_kl | 0.009886166 | +| clip_fraction | 0.301 | +| clip_range | 0.071 | +| entropy_loss | -7.19 | +| explained_variance | 0.0447 | +| learning_rate | 4.62e-05 | +| loss | -0.0308 | +| n_updates | 46964 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000118 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1422 | +| iterations | 7788 | +| time_elapsed | 11210 | +| total_timesteps | 15949824 | +| train/ | | +| approx_kl | 0.009365173 | +| clip_fraction | 0.299 | +| clip_range | 0.071 | +| entropy_loss | -7.01 | +| explained_variance | 0.481 | +| learning_rate | 4.62e-05 | +| loss | -0.027 | +| n_updates | 46968 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000174 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1422 | +| iterations | 7789 | +| time_elapsed | 11211 | +| total_timesteps | 15951872 | +| train/ | | +| approx_kl | 0.011912353 | +| clip_fraction | 0.351 | +| clip_range | 0.071 | +| entropy_loss | -6.88 | +| explained_variance | 0.507 | +| learning_rate | 4.62e-05 | +| loss | -0.0386 | +| n_updates | 46972 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000108 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1422 | +| iterations | 7790 | +| time_elapsed | 11213 | +| total_timesteps | 15953920 | +| train/ | | +| approx_kl | 0.009084819 | +| clip_fraction | 0.292 | +| clip_range | 0.071 | +| entropy_loss | -6.91 | +| explained_variance | 0.109 | +| learning_rate | 4.62e-05 | +| loss | -0.0316 | +| n_updates | 46976 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000505 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1422 | +| iterations | 7791 | +| time_elapsed | 11214 | +| total_timesteps | 15955968 | +| train/ | | +| approx_kl | 0.012242915 | +| clip_fraction | 0.326 | +| clip_range | 0.071 | +| entropy_loss | -6.96 | +| explained_variance | 0.567 | +| learning_rate | 4.62e-05 | +| loss | -0.0325 | +| n_updates | 46980 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000114 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1422 | +| iterations | 7792 | +| time_elapsed | 11216 | +| total_timesteps | 15958016 | +| train/ | | +| approx_kl | 0.011515603 | +| clip_fraction | 0.325 | +| clip_range | 0.071 | +| entropy_loss | -7.01 | +| explained_variance | 0.321 | +| learning_rate | 4.62e-05 | +| loss | -0.0343 | +| n_updates | 46984 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000155 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1422 | +| iterations | 7793 | +| time_elapsed | 11217 | +| total_timesteps | 15960064 | +| train/ | | +| approx_kl | 0.012340004 | +| clip_fraction | 0.366 | +| clip_range | 0.071 | +| entropy_loss | -6.79 | +| explained_variance | 0.557 | +| learning_rate | 4.62e-05 | +| loss | -0.0363 | +| n_updates | 46988 | +| policy_gradient_loss | -0.025 | +| value_loss | 5.83e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1422 | +| iterations | 7794 | +| time_elapsed | 11219 | +| total_timesteps | 15962112 | +| train/ | | +| approx_kl | 0.01106777 | +| clip_fraction | 0.316 | +| clip_range | 0.071 | +| entropy_loss | -6.81 | +| explained_variance | 0.276 | +| learning_rate | 4.62e-05 | +| loss | -0.0283 | +| n_updates | 46992 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000311 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1422 | +| iterations | 7795 | +| time_elapsed | 11220 | +| total_timesteps | 15964160 | +| train/ | | +| approx_kl | 0.0108295195 | +| clip_fraction | 0.316 | +| clip_range | 0.071 | +| entropy_loss | -7.32 | +| explained_variance | -0.104 | +| learning_rate | 4.62e-05 | +| loss | -0.0309 | +| n_updates | 46996 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000119 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1422 | +| iterations | 7796 | +| time_elapsed | 11222 | +| total_timesteps | 15966208 | +| train/ | | +| approx_kl | 0.010829778 | +| clip_fraction | 0.31 | +| clip_range | 0.071 | +| entropy_loss | -7.07 | +| explained_variance | 0.274 | +| learning_rate | 4.62e-05 | +| loss | -0.0335 | +| n_updates | 47000 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000215 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1422 | +| iterations | 7797 | +| time_elapsed | 11223 | +| total_timesteps | 15968256 | +| train/ | | +| approx_kl | 0.010894905 | +| clip_fraction | 0.323 | +| clip_range | 0.071 | +| entropy_loss | -6.48 | +| explained_variance | 0.425 | +| learning_rate | 4.62e-05 | +| loss | -0.0264 | +| n_updates | 47004 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000243 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1422 | +| iterations | 7798 | +| time_elapsed | 11225 | +| total_timesteps | 15970304 | +| train/ | | +| approx_kl | 0.011453852 | +| clip_fraction | 0.332 | +| clip_range | 0.071 | +| entropy_loss | -6.78 | +| explained_variance | 0.559 | +| learning_rate | 4.62e-05 | +| loss | -0.0304 | +| n_updates | 47008 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000158 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1422 | +| iterations | 7799 | +| time_elapsed | 11226 | +| total_timesteps | 15972352 | +| train/ | | +| approx_kl | 0.012554393 | +| clip_fraction | 0.34 | +| clip_range | 0.071 | +| entropy_loss | -7.11 | +| explained_variance | -0.466 | +| learning_rate | 4.62e-05 | +| loss | -0.0389 | +| n_updates | 47012 | +| policy_gradient_loss | -0.0236 | +| value_loss | 0.000104 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1422 | +| iterations | 7800 | +| time_elapsed | 11227 | +| total_timesteps | 15974400 | +| train/ | | +| approx_kl | 0.010364998 | +| clip_fraction | 0.323 | +| clip_range | 0.071 | +| entropy_loss | -7.17 | +| explained_variance | 0.505 | +| learning_rate | 4.62e-05 | +| loss | -0.0346 | +| n_updates | 47016 | +| policy_gradient_loss | -0.0227 | +| value_loss | 7.72e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1422 | +| iterations | 7801 | +| time_elapsed | 11229 | +| total_timesteps | 15976448 | +| train/ | | +| approx_kl | 0.010386387 | +| clip_fraction | 0.328 | +| clip_range | 0.071 | +| entropy_loss | -7.02 | +| explained_variance | 0.328 | +| learning_rate | 4.62e-05 | +| loss | -0.0339 | +| n_updates | 47020 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000122 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1422 | +| iterations | 7802 | +| time_elapsed | 11230 | +| total_timesteps | 15978496 | +| train/ | | +| approx_kl | 0.00943115 | +| clip_fraction | 0.296 | +| clip_range | 0.071 | +| entropy_loss | -7.2 | +| explained_variance | 0.316 | +| learning_rate | 4.62e-05 | +| loss | -0.0268 | +| n_updates | 47024 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000165 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1422 | +| iterations | 7803 | +| time_elapsed | 11232 | +| total_timesteps | 15980544 | +| train/ | | +| approx_kl | 0.009481824 | +| clip_fraction | 0.298 | +| clip_range | 0.071 | +| entropy_loss | -6.43 | +| explained_variance | 0.729 | +| learning_rate | 4.62e-05 | +| loss | -0.0332 | +| n_updates | 47028 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1422 | +| iterations | 7804 | +| time_elapsed | 11233 | +| total_timesteps | 15982592 | +| train/ | | +| approx_kl | 0.008718106 | +| clip_fraction | 0.286 | +| clip_range | 0.071 | +| entropy_loss | -6.36 | +| explained_variance | 0.425 | +| learning_rate | 4.62e-05 | +| loss | -0.024 | +| n_updates | 47032 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000252 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1422 | +| iterations | 7805 | +| time_elapsed | 11235 | +| total_timesteps | 15984640 | +| train/ | | +| approx_kl | 0.008008158 | +| clip_fraction | 0.283 | +| clip_range | 0.071 | +| entropy_loss | -6.83 | +| explained_variance | 0.456 | +| learning_rate | 4.62e-05 | +| loss | -0.0292 | +| n_updates | 47036 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000169 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1422 | +| iterations | 7806 | +| time_elapsed | 11236 | +| total_timesteps | 15986688 | +| train/ | | +| approx_kl | 0.010949496 | +| clip_fraction | 0.331 | +| clip_range | 0.071 | +| entropy_loss | -7.3 | +| explained_variance | -0.0618 | +| learning_rate | 4.62e-05 | +| loss | -0.033 | +| n_updates | 47040 | +| policy_gradient_loss | -0.0213 | +| value_loss | 7.9e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1422 | +| iterations | 7807 | +| time_elapsed | 11237 | +| total_timesteps | 15988736 | +| train/ | | +| approx_kl | 0.009816341 | +| clip_fraction | 0.259 | +| clip_range | 0.071 | +| entropy_loss | -6.89 | +| explained_variance | 0.377 | +| learning_rate | 4.62e-05 | +| loss | -0.027 | +| n_updates | 47044 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000208 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1422 | +| iterations | 7808 | +| time_elapsed | 11239 | +| total_timesteps | 15990784 | +| train/ | | +| approx_kl | 0.010310939 | +| clip_fraction | 0.324 | +| clip_range | 0.071 | +| entropy_loss | -6.88 | +| explained_variance | 0.37 | +| learning_rate | 4.62e-05 | +| loss | -0.0329 | +| n_updates | 47048 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1422 | +| iterations | 7809 | +| time_elapsed | 11240 | +| total_timesteps | 15992832 | +| train/ | | +| approx_kl | 0.009961036 | +| clip_fraction | 0.304 | +| clip_range | 0.071 | +| entropy_loss | -7.26 | +| explained_variance | 0.17 | +| learning_rate | 4.62e-05 | +| loss | -0.0315 | +| n_updates | 47052 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000299 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1422 | +| iterations | 7810 | +| time_elapsed | 11242 | +| total_timesteps | 15994880 | +| train/ | | +| approx_kl | 0.011234447 | +| clip_fraction | 0.334 | +| clip_range | 0.071 | +| entropy_loss | -7.03 | +| explained_variance | 0.177 | +| learning_rate | 4.62e-05 | +| loss | -0.0362 | +| n_updates | 47056 | +| policy_gradient_loss | -0.0227 | +| value_loss | 8.67e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1422 | +| iterations | 7811 | +| time_elapsed | 11243 | +| total_timesteps | 15996928 | +| train/ | | +| approx_kl | 0.009408935 | +| clip_fraction | 0.321 | +| clip_range | 0.071 | +| entropy_loss | -6.74 | +| explained_variance | 0.563 | +| learning_rate | 4.62e-05 | +| loss | -0.0258 | +| n_updates | 47060 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000159 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1422 | +| iterations | 7812 | +| time_elapsed | 11245 | +| total_timesteps | 15998976 | +| train/ | | +| approx_kl | 0.007595334 | +| clip_fraction | 0.269 | +| clip_range | 0.071 | +| entropy_loss | -7.17 | +| explained_variance | 0.109 | +| learning_rate | 4.62e-05 | +| loss | -0.0279 | +| n_updates | 47064 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000413 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1422 | +| iterations | 7813 | +| time_elapsed | 11246 | +| total_timesteps | 16001024 | +| train/ | | +| approx_kl | 0.01105546 | +| clip_fraction | 0.298 | +| clip_range | 0.071 | +| entropy_loss | -6.84 | +| explained_variance | 0.12 | +| learning_rate | 4.62e-05 | +| loss | -0.0308 | +| n_updates | 47068 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000173 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1422 | +| iterations | 7814 | +| time_elapsed | 11248 | +| total_timesteps | 16003072 | +| train/ | | +| approx_kl | 0.012461701 | +| clip_fraction | 0.329 | +| clip_range | 0.071 | +| entropy_loss | -6.99 | +| explained_variance | -0.0836 | +| learning_rate | 4.62e-05 | +| loss | -0.0359 | +| n_updates | 47072 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000225 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1422 | +| iterations | 7815 | +| time_elapsed | 11249 | +| total_timesteps | 16005120 | +| train/ | | +| approx_kl | 0.010908452 | +| clip_fraction | 0.298 | +| clip_range | 0.071 | +| entropy_loss | -6.65 | +| explained_variance | 0.379 | +| learning_rate | 4.62e-05 | +| loss | -0.0303 | +| n_updates | 47076 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000319 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1422 | +| iterations | 7816 | +| time_elapsed | 11251 | +| total_timesteps | 16007168 | +| train/ | | +| approx_kl | 0.011000304 | +| clip_fraction | 0.318 | +| clip_range | 0.071 | +| entropy_loss | -6.9 | +| explained_variance | -0.0645 | +| learning_rate | 4.62e-05 | +| loss | -0.0386 | +| n_updates | 47080 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000206 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1422 | +| iterations | 7817 | +| time_elapsed | 11252 | +| total_timesteps | 16009216 | +| train/ | | +| approx_kl | 0.010017473 | +| clip_fraction | 0.329 | +| clip_range | 0.071 | +| entropy_loss | -6.37 | +| explained_variance | 0.588 | +| learning_rate | 4.62e-05 | +| loss | -0.0294 | +| n_updates | 47084 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000177 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1422 | +| iterations | 7818 | +| time_elapsed | 11253 | +| total_timesteps | 16011264 | +| train/ | | +| approx_kl | 0.012392202 | +| clip_fraction | 0.298 | +| clip_range | 0.071 | +| entropy_loss | -7.02 | +| explained_variance | 0.243 | +| learning_rate | 4.62e-05 | +| loss | -0.0265 | +| n_updates | 47088 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000232 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1422 | +| iterations | 7819 | +| time_elapsed | 11255 | +| total_timesteps | 16013312 | +| train/ | | +| approx_kl | 0.010286498 | +| clip_fraction | 0.323 | +| clip_range | 0.071 | +| entropy_loss | -7.33 | +| explained_variance | -0.231 | +| learning_rate | 4.62e-05 | +| loss | -0.0343 | +| n_updates | 47092 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000126 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1422 | +| iterations | 7820 | +| time_elapsed | 11257 | +| total_timesteps | 16015360 | +| train/ | | +| approx_kl | 0.0102921985 | +| clip_fraction | 0.323 | +| clip_range | 0.071 | +| entropy_loss | -6.96 | +| explained_variance | 0.297 | +| learning_rate | 4.62e-05 | +| loss | -0.0304 | +| n_updates | 47096 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000258 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1422 | +| iterations | 7821 | +| time_elapsed | 11258 | +| total_timesteps | 16017408 | +| train/ | | +| approx_kl | 0.010323415 | +| clip_fraction | 0.318 | +| clip_range | 0.071 | +| entropy_loss | -6.8 | +| explained_variance | 0.46 | +| learning_rate | 4.62e-05 | +| loss | -0.0323 | +| n_updates | 47100 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000172 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1422 | +| iterations | 7822 | +| time_elapsed | 11259 | +| total_timesteps | 16019456 | +| train/ | | +| approx_kl | 0.009839442 | +| clip_fraction | 0.333 | +| clip_range | 0.071 | +| entropy_loss | -6.95 | +| explained_variance | 0.369 | +| learning_rate | 4.62e-05 | +| loss | -0.0379 | +| n_updates | 47104 | +| policy_gradient_loss | -0.0223 | +| value_loss | 0.000119 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1422 | +| iterations | 7823 | +| time_elapsed | 11261 | +| total_timesteps | 16021504 | +| train/ | | +| approx_kl | 0.009855177 | +| clip_fraction | 0.31 | +| clip_range | 0.071 | +| entropy_loss | -7.12 | +| explained_variance | 0.293 | +| learning_rate | 4.62e-05 | +| loss | -0.0304 | +| n_updates | 47108 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000192 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1422 | +| iterations | 7824 | +| time_elapsed | 11262 | +| total_timesteps | 16023552 | +| train/ | | +| approx_kl | 0.009471713 | +| clip_fraction | 0.299 | +| clip_range | 0.071 | +| entropy_loss | -6.82 | +| explained_variance | 0.397 | +| learning_rate | 4.62e-05 | +| loss | -0.0227 | +| n_updates | 47112 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000296 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1422 | +| iterations | 7825 | +| time_elapsed | 11264 | +| total_timesteps | 16025600 | +| train/ | | +| approx_kl | 0.011281641 | +| clip_fraction | 0.37 | +| clip_range | 0.071 | +| entropy_loss | -6.94 | +| explained_variance | 0.576 | +| learning_rate | 4.62e-05 | +| loss | -0.0376 | +| n_updates | 47116 | +| policy_gradient_loss | -0.0249 | +| value_loss | 6.22e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1422 | +| iterations | 7826 | +| time_elapsed | 11265 | +| total_timesteps | 16027648 | +| train/ | | +| approx_kl | 0.009476298 | +| clip_fraction | 0.312 | +| clip_range | 0.071 | +| entropy_loss | -7.12 | +| explained_variance | 0.352 | +| learning_rate | 4.62e-05 | +| loss | -0.0317 | +| n_updates | 47120 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000164 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1422 | +| iterations | 7827 | +| time_elapsed | 11267 | +| total_timesteps | 16029696 | +| train/ | | +| approx_kl | 0.011222844 | +| clip_fraction | 0.326 | +| clip_range | 0.071 | +| entropy_loss | -6.52 | +| explained_variance | 0.573 | +| learning_rate | 4.62e-05 | +| loss | -0.0315 | +| n_updates | 47124 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000175 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1422 | +| iterations | 7828 | +| time_elapsed | 11268 | +| total_timesteps | 16031744 | +| train/ | | +| approx_kl | 0.010625862 | +| clip_fraction | 0.3 | +| clip_range | 0.071 | +| entropy_loss | -6.7 | +| explained_variance | 0.206 | +| learning_rate | 4.62e-05 | +| loss | -0.0223 | +| n_updates | 47128 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.00038 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1422 | +| iterations | 7829 | +| time_elapsed | 11269 | +| total_timesteps | 16033792 | +| train/ | | +| approx_kl | 0.008473847 | +| clip_fraction | 0.283 | +| clip_range | 0.071 | +| entropy_loss | -6.64 | +| explained_variance | 0.523 | +| learning_rate | 4.62e-05 | +| loss | -0.0217 | +| n_updates | 47132 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000232 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1422 | +| iterations | 7830 | +| time_elapsed | 11271 | +| total_timesteps | 16035840 | +| train/ | | +| approx_kl | 0.010661919 | +| clip_fraction | 0.363 | +| clip_range | 0.071 | +| entropy_loss | -6.61 | +| explained_variance | 0.596 | +| learning_rate | 4.62e-05 | +| loss | -0.0349 | +| n_updates | 47136 | +| policy_gradient_loss | -0.0235 | +| value_loss | 0.000101 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1422 | +| iterations | 7831 | +| time_elapsed | 11272 | +| total_timesteps | 16037888 | +| train/ | | +| approx_kl | 0.011264207 | +| clip_fraction | 0.318 | +| clip_range | 0.071 | +| entropy_loss | -7.07 | +| explained_variance | 0.263 | +| learning_rate | 4.62e-05 | +| loss | -0.0329 | +| n_updates | 47140 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000227 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1422 | +| iterations | 7832 | +| time_elapsed | 11274 | +| total_timesteps | 16039936 | +| train/ | | +| approx_kl | 0.010654515 | +| clip_fraction | 0.315 | +| clip_range | 0.071 | +| entropy_loss | -7.03 | +| explained_variance | 0.195 | +| learning_rate | 4.62e-05 | +| loss | -0.0316 | +| n_updates | 47144 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000281 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1422 | +| iterations | 7833 | +| time_elapsed | 11275 | +| total_timesteps | 16041984 | +| train/ | | +| approx_kl | 0.009276105 | +| clip_fraction | 0.293 | +| clip_range | 0.071 | +| entropy_loss | -6.75 | +| explained_variance | 0.367 | +| learning_rate | 4.62e-05 | +| loss | -0.0289 | +| n_updates | 47148 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000289 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1422 | +| iterations | 7834 | +| time_elapsed | 11277 | +| total_timesteps | 16044032 | +| train/ | | +| approx_kl | 0.010836949 | +| clip_fraction | 0.324 | +| clip_range | 0.071 | +| entropy_loss | -6.99 | +| explained_variance | 0.158 | +| learning_rate | 4.62e-05 | +| loss | -0.0238 | +| n_updates | 47152 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000401 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1422 | +| iterations | 7835 | +| time_elapsed | 11278 | +| total_timesteps | 16046080 | +| train/ | | +| approx_kl | 0.0120521 | +| clip_fraction | 0.366 | +| clip_range | 0.071 | +| entropy_loss | -6.83 | +| explained_variance | 0.647 | +| learning_rate | 4.62e-05 | +| loss | -0.0419 | +| n_updates | 47156 | +| policy_gradient_loss | -0.027 | +| value_loss | 8.56e-05 | +--------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1422 | +| iterations | 7836 | +| time_elapsed | 11279 | +| total_timesteps | 16048128 | +| train/ | | +| approx_kl | 0.01091718 | +| clip_fraction | 0.328 | +| clip_range | 0.071 | +| entropy_loss | -7.34 | +| explained_variance | -0.0488 | +| learning_rate | 4.62e-05 | +| loss | -0.0383 | +| n_updates | 47160 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000176 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1422 | +| iterations | 7837 | +| time_elapsed | 11281 | +| total_timesteps | 16050176 | +| train/ | | +| approx_kl | 0.010443214 | +| clip_fraction | 0.316 | +| clip_range | 0.071 | +| entropy_loss | -6.24 | +| explained_variance | 0.628 | +| learning_rate | 4.62e-05 | +| loss | -0.0302 | +| n_updates | 47164 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000219 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1422 | +| iterations | 7838 | +| time_elapsed | 11282 | +| total_timesteps | 16052224 | +| train/ | | +| approx_kl | 0.013136308 | +| clip_fraction | 0.355 | +| clip_range | 0.071 | +| entropy_loss | -6.38 | +| explained_variance | 0.762 | +| learning_rate | 4.62e-05 | +| loss | -0.0405 | +| n_updates | 47168 | +| policy_gradient_loss | -0.0238 | +| value_loss | 7.81e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1422 | +| iterations | 7839 | +| time_elapsed | 11284 | +| total_timesteps | 16054272 | +| train/ | | +| approx_kl | 0.010423204 | +| clip_fraction | 0.317 | +| clip_range | 0.071 | +| entropy_loss | -7.07 | +| explained_variance | -0.28 | +| learning_rate | 4.62e-05 | +| loss | -0.0351 | +| n_updates | 47172 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000141 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1422 | +| iterations | 7840 | +| time_elapsed | 11285 | +| total_timesteps | 16056320 | +| train/ | | +| approx_kl | 0.011723382 | +| clip_fraction | 0.323 | +| clip_range | 0.071 | +| entropy_loss | -7.23 | +| explained_variance | -0.103 | +| learning_rate | 4.62e-05 | +| loss | -0.0283 | +| n_updates | 47176 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000103 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1422 | +| iterations | 7841 | +| time_elapsed | 11287 | +| total_timesteps | 16058368 | +| train/ | | +| approx_kl | 0.011181229 | +| clip_fraction | 0.319 | +| clip_range | 0.071 | +| entropy_loss | -7.14 | +| explained_variance | 0.0868 | +| learning_rate | 4.62e-05 | +| loss | -0.0287 | +| n_updates | 47180 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000153 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1422 | +| iterations | 7842 | +| time_elapsed | 11288 | +| total_timesteps | 16060416 | +| train/ | | +| approx_kl | 0.010730982 | +| clip_fraction | 0.327 | +| clip_range | 0.071 | +| entropy_loss | -6.72 | +| explained_variance | 0.386 | +| learning_rate | 4.62e-05 | +| loss | -0.0308 | +| n_updates | 47184 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000274 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1422 | +| iterations | 7843 | +| time_elapsed | 11290 | +| total_timesteps | 16062464 | +| train/ | | +| approx_kl | 0.011912687 | +| clip_fraction | 0.345 | +| clip_range | 0.071 | +| entropy_loss | -7.32 | +| explained_variance | -0.104 | +| learning_rate | 4.62e-05 | +| loss | -0.0311 | +| n_updates | 47188 | +| policy_gradient_loss | -0.022 | +| value_loss | 0.000131 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1422 | +| iterations | 7844 | +| time_elapsed | 11291 | +| total_timesteps | 16064512 | +| train/ | | +| approx_kl | 0.008952615 | +| clip_fraction | 0.31 | +| clip_range | 0.071 | +| entropy_loss | -7.17 | +| explained_variance | 0.173 | +| learning_rate | 4.62e-05 | +| loss | -0.0289 | +| n_updates | 47192 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000171 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1422 | +| iterations | 7845 | +| time_elapsed | 11292 | +| total_timesteps | 16066560 | +| train/ | | +| approx_kl | 0.010228077 | +| clip_fraction | 0.325 | +| clip_range | 0.071 | +| entropy_loss | -6.6 | +| explained_variance | 0.622 | +| learning_rate | 4.62e-05 | +| loss | -0.0272 | +| n_updates | 47196 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000153 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1422 | +| iterations | 7846 | +| time_elapsed | 11294 | +| total_timesteps | 16068608 | +| train/ | | +| approx_kl | 0.010712071 | +| clip_fraction | 0.336 | +| clip_range | 0.071 | +| entropy_loss | -6.84 | +| explained_variance | 0.526 | +| learning_rate | 4.62e-05 | +| loss | -0.0344 | +| n_updates | 47200 | +| policy_gradient_loss | -0.0223 | +| value_loss | 8.58e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1422 | +| iterations | 7847 | +| time_elapsed | 11295 | +| total_timesteps | 16070656 | +| train/ | | +| approx_kl | 0.011858206 | +| clip_fraction | 0.319 | +| clip_range | 0.071 | +| entropy_loss | -6.1 | +| explained_variance | 0.768 | +| learning_rate | 4.62e-05 | +| loss | -0.0306 | +| n_updates | 47204 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000117 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1422 | +| iterations | 7848 | +| time_elapsed | 11297 | +| total_timesteps | 16072704 | +| train/ | | +| approx_kl | 0.009133186 | +| clip_fraction | 0.308 | +| clip_range | 0.071 | +| entropy_loss | -6.91 | +| explained_variance | 0.291 | +| learning_rate | 4.62e-05 | +| loss | -0.0341 | +| n_updates | 47208 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000258 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1422 | +| iterations | 7849 | +| time_elapsed | 11298 | +| total_timesteps | 16074752 | +| train/ | | +| approx_kl | 0.010668986 | +| clip_fraction | 0.302 | +| clip_range | 0.071 | +| entropy_loss | -6.76 | +| explained_variance | 0.35 | +| learning_rate | 4.62e-05 | +| loss | -0.0226 | +| n_updates | 47212 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000217 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1422 | +| iterations | 7850 | +| time_elapsed | 11299 | +| total_timesteps | 16076800 | +| train/ | | +| approx_kl | 0.011967634 | +| clip_fraction | 0.334 | +| clip_range | 0.071 | +| entropy_loss | -7.01 | +| explained_variance | 0.151 | +| learning_rate | 4.62e-05 | +| loss | -0.0317 | +| n_updates | 47216 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000163 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1422 | +| iterations | 7851 | +| time_elapsed | 11301 | +| total_timesteps | 16078848 | +| train/ | | +| approx_kl | 0.010634208 | +| clip_fraction | 0.286 | +| clip_range | 0.071 | +| entropy_loss | -6.93 | +| explained_variance | 0.246 | +| learning_rate | 4.62e-05 | +| loss | -0.0286 | +| n_updates | 47220 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000294 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1422 | +| iterations | 7852 | +| time_elapsed | 11302 | +| total_timesteps | 16080896 | +| train/ | | +| approx_kl | 0.009585601 | +| clip_fraction | 0.32 | +| clip_range | 0.071 | +| entropy_loss | -7.06 | +| explained_variance | 0.379 | +| learning_rate | 4.62e-05 | +| loss | -0.0327 | +| n_updates | 47224 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000111 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1422 | +| iterations | 7853 | +| time_elapsed | 11304 | +| total_timesteps | 16082944 | +| train/ | | +| approx_kl | 0.009292202 | +| clip_fraction | 0.306 | +| clip_range | 0.071 | +| entropy_loss | -7.14 | +| explained_variance | 0.252 | +| learning_rate | 4.62e-05 | +| loss | -0.0347 | +| n_updates | 47228 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.00015 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1422 | +| iterations | 7854 | +| time_elapsed | 11305 | +| total_timesteps | 16084992 | +| train/ | | +| approx_kl | 0.009594516 | +| clip_fraction | 0.315 | +| clip_range | 0.071 | +| entropy_loss | -6.89 | +| explained_variance | 0.356 | +| learning_rate | 4.62e-05 | +| loss | -0.0286 | +| n_updates | 47232 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000207 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1422 | +| iterations | 7855 | +| time_elapsed | 11306 | +| total_timesteps | 16087040 | +| train/ | | +| approx_kl | 0.008504903 | +| clip_fraction | 0.282 | +| clip_range | 0.071 | +| entropy_loss | -7 | +| explained_variance | 0.398 | +| learning_rate | 4.62e-05 | +| loss | -0.0294 | +| n_updates | 47236 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000169 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1422 | +| iterations | 7856 | +| time_elapsed | 11308 | +| total_timesteps | 16089088 | +| train/ | | +| approx_kl | 0.008851493 | +| clip_fraction | 0.295 | +| clip_range | 0.071 | +| entropy_loss | -6.7 | +| explained_variance | 0.422 | +| learning_rate | 4.62e-05 | +| loss | -0.0284 | +| n_updates | 47240 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000209 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1422 | +| iterations | 7857 | +| time_elapsed | 11309 | +| total_timesteps | 16091136 | +| train/ | | +| approx_kl | 0.010105196 | +| clip_fraction | 0.328 | +| clip_range | 0.071 | +| entropy_loss | -7.08 | +| explained_variance | 0.287 | +| learning_rate | 4.62e-05 | +| loss | -0.0296 | +| n_updates | 47244 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000148 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1422 | +| iterations | 7858 | +| time_elapsed | 11311 | +| total_timesteps | 16093184 | +| train/ | | +| approx_kl | 0.0071867052 | +| clip_fraction | 0.299 | +| clip_range | 0.071 | +| entropy_loss | -7.18 | +| explained_variance | 0.239 | +| learning_rate | 4.62e-05 | +| loss | -0.0279 | +| n_updates | 47248 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000349 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1422 | +| iterations | 7859 | +| time_elapsed | 11312 | +| total_timesteps | 16095232 | +| train/ | | +| approx_kl | 0.009771174 | +| clip_fraction | 0.322 | +| clip_range | 0.071 | +| entropy_loss | -6.9 | +| explained_variance | 0.151 | +| learning_rate | 4.62e-05 | +| loss | -0.0271 | +| n_updates | 47252 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000339 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1422 | +| iterations | 7860 | +| time_elapsed | 11314 | +| total_timesteps | 16097280 | +| train/ | | +| approx_kl | 0.010306827 | +| clip_fraction | 0.324 | +| clip_range | 0.071 | +| entropy_loss | -6.78 | +| explained_variance | 0.615 | +| learning_rate | 4.62e-05 | +| loss | -0.038 | +| n_updates | 47256 | +| policy_gradient_loss | -0.0231 | +| value_loss | 8.18e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1422 | +| iterations | 7861 | +| time_elapsed | 11315 | +| total_timesteps | 16099328 | +| train/ | | +| approx_kl | 0.010658677 | +| clip_fraction | 0.296 | +| clip_range | 0.071 | +| entropy_loss | -6.76 | +| explained_variance | 0.218 | +| learning_rate | 4.62e-05 | +| loss | -0.0232 | +| n_updates | 47260 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000403 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1422 | +| iterations | 7862 | +| time_elapsed | 11317 | +| total_timesteps | 16101376 | +| train/ | | +| approx_kl | 0.010769534 | +| clip_fraction | 0.301 | +| clip_range | 0.071 | +| entropy_loss | -7.14 | +| explained_variance | -0.161 | +| learning_rate | 4.62e-05 | +| loss | -0.0343 | +| n_updates | 47264 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000205 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1422 | +| iterations | 7863 | +| time_elapsed | 11318 | +| total_timesteps | 16103424 | +| train/ | | +| approx_kl | 0.011545448 | +| clip_fraction | 0.343 | +| clip_range | 0.071 | +| entropy_loss | -7.06 | +| explained_variance | 0.307 | +| learning_rate | 4.62e-05 | +| loss | -0.0398 | +| n_updates | 47268 | +| policy_gradient_loss | -0.0244 | +| value_loss | 6.38e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1422 | +| iterations | 7864 | +| time_elapsed | 11319 | +| total_timesteps | 16105472 | +| train/ | | +| approx_kl | 0.011510803 | +| clip_fraction | 0.319 | +| clip_range | 0.071 | +| entropy_loss | -6.92 | +| explained_variance | 0.329 | +| learning_rate | 4.62e-05 | +| loss | -0.0238 | +| n_updates | 47272 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000274 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1422 | +| iterations | 7865 | +| time_elapsed | 11321 | +| total_timesteps | 16107520 | +| train/ | | +| approx_kl | 0.013157181 | +| clip_fraction | 0.302 | +| clip_range | 0.071 | +| entropy_loss | -6.91 | +| explained_variance | 0.184 | +| learning_rate | 4.62e-05 | +| loss | -0.0343 | +| n_updates | 47276 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000183 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1422 | +| iterations | 7866 | +| time_elapsed | 11322 | +| total_timesteps | 16109568 | +| train/ | | +| approx_kl | 0.011552511 | +| clip_fraction | 0.307 | +| clip_range | 0.071 | +| entropy_loss | -6.9 | +| explained_variance | 0.169 | +| learning_rate | 4.62e-05 | +| loss | -0.0333 | +| n_updates | 47280 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.00028 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1422 | +| iterations | 7867 | +| time_elapsed | 11324 | +| total_timesteps | 16111616 | +| train/ | | +| approx_kl | 0.01018249 | +| clip_fraction | 0.301 | +| clip_range | 0.071 | +| entropy_loss | -7.03 | +| explained_variance | 0.167 | +| learning_rate | 4.62e-05 | +| loss | -0.0334 | +| n_updates | 47284 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000271 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1422 | +| iterations | 7868 | +| time_elapsed | 11325 | +| total_timesteps | 16113664 | +| train/ | | +| approx_kl | 0.010206531 | +| clip_fraction | 0.335 | +| clip_range | 0.071 | +| entropy_loss | -6.68 | +| explained_variance | 0.446 | +| learning_rate | 4.62e-05 | +| loss | -0.0252 | +| n_updates | 47288 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000193 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1422 | +| iterations | 7869 | +| time_elapsed | 11327 | +| total_timesteps | 16115712 | +| train/ | | +| approx_kl | 0.012771504 | +| clip_fraction | 0.353 | +| clip_range | 0.071 | +| entropy_loss | -6.58 | +| explained_variance | 0.592 | +| learning_rate | 4.62e-05 | +| loss | -0.0339 | +| n_updates | 47292 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000122 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1422 | +| iterations | 7870 | +| time_elapsed | 11328 | +| total_timesteps | 16117760 | +| train/ | | +| approx_kl | 0.0130998455 | +| clip_fraction | 0.332 | +| clip_range | 0.071 | +| entropy_loss | -7.05 | +| explained_variance | 0.363 | +| learning_rate | 4.62e-05 | +| loss | -0.037 | +| n_updates | 47296 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.0001 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1422 | +| iterations | 7871 | +| time_elapsed | 11329 | +| total_timesteps | 16119808 | +| train/ | | +| approx_kl | 0.012026666 | +| clip_fraction | 0.308 | +| clip_range | 0.071 | +| entropy_loss | -6.77 | +| explained_variance | 0.272 | +| learning_rate | 4.62e-05 | +| loss | -0.0313 | +| n_updates | 47300 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000392 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1422 | +| iterations | 7872 | +| time_elapsed | 11331 | +| total_timesteps | 16121856 | +| train/ | | +| approx_kl | 0.01051564 | +| clip_fraction | 0.316 | +| clip_range | 0.071 | +| entropy_loss | -6.58 | +| explained_variance | 0.396 | +| learning_rate | 4.62e-05 | +| loss | -0.0366 | +| n_updates | 47304 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000247 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1422 | +| iterations | 7873 | +| time_elapsed | 11332 | +| total_timesteps | 16123904 | +| train/ | | +| approx_kl | 0.01124314 | +| clip_fraction | 0.296 | +| clip_range | 0.071 | +| entropy_loss | -6.78 | +| explained_variance | 0.285 | +| learning_rate | 4.62e-05 | +| loss | -0.0301 | +| n_updates | 47308 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000279 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1422 | +| iterations | 7874 | +| time_elapsed | 11334 | +| total_timesteps | 16125952 | +| train/ | | +| approx_kl | 0.012684865 | +| clip_fraction | 0.318 | +| clip_range | 0.071 | +| entropy_loss | -6.95 | +| explained_variance | 0.368 | +| learning_rate | 4.62e-05 | +| loss | -0.0292 | +| n_updates | 47312 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000173 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1422 | +| iterations | 7875 | +| time_elapsed | 11335 | +| total_timesteps | 16128000 | +| train/ | | +| approx_kl | 0.010717139 | +| clip_fraction | 0.329 | +| clip_range | 0.071 | +| entropy_loss | -6.99 | +| explained_variance | 0.339 | +| learning_rate | 4.62e-05 | +| loss | -0.0287 | +| n_updates | 47316 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000118 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1422 | +| iterations | 7876 | +| time_elapsed | 11337 | +| total_timesteps | 16130048 | +| train/ | | +| approx_kl | 0.009901401 | +| clip_fraction | 0.313 | +| clip_range | 0.071 | +| entropy_loss | -7.37 | +| explained_variance | -0.078 | +| learning_rate | 4.62e-05 | +| loss | -0.0322 | +| n_updates | 47320 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000133 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1422 | +| iterations | 7877 | +| time_elapsed | 11338 | +| total_timesteps | 16132096 | +| train/ | | +| approx_kl | 0.009880155 | +| clip_fraction | 0.296 | +| clip_range | 0.071 | +| entropy_loss | -7.37 | +| explained_variance | -0.195 | +| learning_rate | 4.62e-05 | +| loss | -0.0296 | +| n_updates | 47324 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000137 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1422 | +| iterations | 7878 | +| time_elapsed | 11339 | +| total_timesteps | 16134144 | +| train/ | | +| approx_kl | 0.009340774 | +| clip_fraction | 0.269 | +| clip_range | 0.071 | +| entropy_loss | -6.18 | +| explained_variance | 0.574 | +| learning_rate | 4.62e-05 | +| loss | -0.0259 | +| n_updates | 47328 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000275 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1422 | +| iterations | 7879 | +| time_elapsed | 11341 | +| total_timesteps | 16136192 | +| train/ | | +| approx_kl | 0.0103891315 | +| clip_fraction | 0.292 | +| clip_range | 0.071 | +| entropy_loss | -6.11 | +| explained_variance | 0.443 | +| learning_rate | 4.62e-05 | +| loss | -0.025 | +| n_updates | 47332 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000365 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1422 | +| iterations | 7880 | +| time_elapsed | 11342 | +| total_timesteps | 16138240 | +| train/ | | +| approx_kl | 0.012252424 | +| clip_fraction | 0.342 | +| clip_range | 0.071 | +| entropy_loss | -6.83 | +| explained_variance | 0.259 | +| learning_rate | 4.62e-05 | +| loss | -0.0356 | +| n_updates | 47336 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000148 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1422 | +| iterations | 7881 | +| time_elapsed | 11344 | +| total_timesteps | 16140288 | +| train/ | | +| approx_kl | 0.01049543 | +| clip_fraction | 0.318 | +| clip_range | 0.071 | +| entropy_loss | -7.09 | +| explained_variance | 0.106 | +| learning_rate | 4.62e-05 | +| loss | -0.0292 | +| n_updates | 47340 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000279 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1422 | +| iterations | 7882 | +| time_elapsed | 11345 | +| total_timesteps | 16142336 | +| train/ | | +| approx_kl | 0.011322844 | +| clip_fraction | 0.349 | +| clip_range | 0.071 | +| entropy_loss | -7.13 | +| explained_variance | 0.386 | +| learning_rate | 4.62e-05 | +| loss | -0.0324 | +| n_updates | 47344 | +| policy_gradient_loss | -0.0224 | +| value_loss | 7.82e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1422 | +| iterations | 7883 | +| time_elapsed | 11346 | +| total_timesteps | 16144384 | +| train/ | | +| approx_kl | 0.011009467 | +| clip_fraction | 0.308 | +| clip_range | 0.071 | +| entropy_loss | -7.08 | +| explained_variance | 0.228 | +| learning_rate | 4.62e-05 | +| loss | -0.0257 | +| n_updates | 47348 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000222 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1422 | +| iterations | 7884 | +| time_elapsed | 11348 | +| total_timesteps | 16146432 | +| train/ | | +| approx_kl | 0.011777429 | +| clip_fraction | 0.348 | +| clip_range | 0.071 | +| entropy_loss | -7.03 | +| explained_variance | 0.413 | +| learning_rate | 4.62e-05 | +| loss | -0.0331 | +| n_updates | 47352 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000117 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1422 | +| iterations | 7885 | +| time_elapsed | 11349 | +| total_timesteps | 16148480 | +| train/ | | +| approx_kl | 0.012050206 | +| clip_fraction | 0.32 | +| clip_range | 0.071 | +| entropy_loss | -6.75 | +| explained_variance | 0.309 | +| learning_rate | 4.62e-05 | +| loss | -0.0265 | +| n_updates | 47356 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000311 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1422 | +| iterations | 7886 | +| time_elapsed | 11351 | +| total_timesteps | 16150528 | +| train/ | | +| approx_kl | 0.011593309 | +| clip_fraction | 0.332 | +| clip_range | 0.071 | +| entropy_loss | -6.63 | +| explained_variance | 0.373 | +| learning_rate | 4.62e-05 | +| loss | -0.0204 | +| n_updates | 47360 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000302 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1422 | +| iterations | 7887 | +| time_elapsed | 11352 | +| total_timesteps | 16152576 | +| train/ | | +| approx_kl | 0.011993203 | +| clip_fraction | 0.339 | +| clip_range | 0.071 | +| entropy_loss | -6.57 | +| explained_variance | 0.553 | +| learning_rate | 4.62e-05 | +| loss | -0.037 | +| n_updates | 47364 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000166 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1422 | +| iterations | 7888 | +| time_elapsed | 11354 | +| total_timesteps | 16154624 | +| train/ | | +| approx_kl | 0.011541001 | +| clip_fraction | 0.339 | +| clip_range | 0.071 | +| entropy_loss | -6.9 | +| explained_variance | 0.412 | +| learning_rate | 4.62e-05 | +| loss | -0.0387 | +| n_updates | 47368 | +| policy_gradient_loss | -0.0224 | +| value_loss | 0.000125 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1422 | +| iterations | 7889 | +| time_elapsed | 11355 | +| total_timesteps | 16156672 | +| train/ | | +| approx_kl | 0.010817598 | +| clip_fraction | 0.315 | +| clip_range | 0.071 | +| entropy_loss | -6.57 | +| explained_variance | 0.243 | +| learning_rate | 4.62e-05 | +| loss | -0.0327 | +| n_updates | 47372 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000375 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1422 | +| iterations | 7890 | +| time_elapsed | 11357 | +| total_timesteps | 16158720 | +| train/ | | +| approx_kl | 0.01107214 | +| clip_fraction | 0.305 | +| clip_range | 0.071 | +| entropy_loss | -6.84 | +| explained_variance | 0.346 | +| learning_rate | 4.62e-05 | +| loss | -0.0293 | +| n_updates | 47376 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000181 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1422 | +| iterations | 7891 | +| time_elapsed | 11358 | +| total_timesteps | 16160768 | +| train/ | | +| approx_kl | 0.012374271 | +| clip_fraction | 0.329 | +| clip_range | 0.071 | +| entropy_loss | -7.09 | +| explained_variance | 0.251 | +| learning_rate | 4.62e-05 | +| loss | -0.0346 | +| n_updates | 47380 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000193 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1422 | +| iterations | 7892 | +| time_elapsed | 11360 | +| total_timesteps | 16162816 | +| train/ | | +| approx_kl | 0.010162964 | +| clip_fraction | 0.326 | +| clip_range | 0.071 | +| entropy_loss | -7.41 | +| explained_variance | -0.0491 | +| learning_rate | 4.62e-05 | +| loss | -0.0321 | +| n_updates | 47384 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000183 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1422 | +| iterations | 7893 | +| time_elapsed | 11361 | +| total_timesteps | 16164864 | +| train/ | | +| approx_kl | 0.009881955 | +| clip_fraction | 0.341 | +| clip_range | 0.071 | +| entropy_loss | -6.75 | +| explained_variance | 0.513 | +| learning_rate | 4.62e-05 | +| loss | -0.0272 | +| n_updates | 47388 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000207 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1422 | +| iterations | 7894 | +| time_elapsed | 11362 | +| total_timesteps | 16166912 | +| train/ | | +| approx_kl | 0.017340817 | +| clip_fraction | 0.356 | +| clip_range | 0.071 | +| entropy_loss | -6.93 | +| explained_variance | 0.319 | +| learning_rate | 4.62e-05 | +| loss | -0.0335 | +| n_updates | 47392 | +| policy_gradient_loss | -0.0224 | +| value_loss | 0.000109 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1422 | +| iterations | 7895 | +| time_elapsed | 11364 | +| total_timesteps | 16168960 | +| train/ | | +| approx_kl | 0.014250474 | +| clip_fraction | 0.313 | +| clip_range | 0.071 | +| entropy_loss | -6.71 | +| explained_variance | 0.36 | +| learning_rate | 4.62e-05 | +| loss | -0.0296 | +| n_updates | 47396 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.00033 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1422 | +| iterations | 7896 | +| time_elapsed | 11365 | +| total_timesteps | 16171008 | +| train/ | | +| approx_kl | 0.013292877 | +| clip_fraction | 0.36 | +| clip_range | 0.071 | +| entropy_loss | -6.75 | +| explained_variance | 0.35 | +| learning_rate | 4.62e-05 | +| loss | -0.0325 | +| n_updates | 47400 | +| policy_gradient_loss | -0.0228 | +| value_loss | 0.00013 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1422 | +| iterations | 7897 | +| time_elapsed | 11367 | +| total_timesteps | 16173056 | +| train/ | | +| approx_kl | 0.009340797 | +| clip_fraction | 0.312 | +| clip_range | 0.071 | +| entropy_loss | -7.01 | +| explained_variance | 0.167 | +| learning_rate | 4.62e-05 | +| loss | -0.0235 | +| n_updates | 47404 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000346 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1422 | +| iterations | 7898 | +| time_elapsed | 11368 | +| total_timesteps | 16175104 | +| train/ | | +| approx_kl | 0.011744766 | +| clip_fraction | 0.345 | +| clip_range | 0.071 | +| entropy_loss | -6.28 | +| explained_variance | 0.599 | +| learning_rate | 4.62e-05 | +| loss | -0.0309 | +| n_updates | 47408 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000158 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1422 | +| iterations | 7899 | +| time_elapsed | 11370 | +| total_timesteps | 16177152 | +| train/ | | +| approx_kl | 0.010738285 | +| clip_fraction | 0.317 | +| clip_range | 0.071 | +| entropy_loss | -6.9 | +| explained_variance | 0.239 | +| learning_rate | 4.62e-05 | +| loss | -0.0313 | +| n_updates | 47412 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000201 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1422 | +| iterations | 7900 | +| time_elapsed | 11371 | +| total_timesteps | 16179200 | +| train/ | | +| approx_kl | 0.010060281 | +| clip_fraction | 0.299 | +| clip_range | 0.071 | +| entropy_loss | -6.78 | +| explained_variance | 0.434 | +| learning_rate | 4.62e-05 | +| loss | -0.0246 | +| n_updates | 47416 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000228 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1422 | +| iterations | 7901 | +| time_elapsed | 11372 | +| total_timesteps | 16181248 | +| train/ | | +| approx_kl | 0.011096058 | +| clip_fraction | 0.314 | +| clip_range | 0.071 | +| entropy_loss | -7.21 | +| explained_variance | -0.224 | +| learning_rate | 4.62e-05 | +| loss | -0.0358 | +| n_updates | 47420 | +| policy_gradient_loss | -0.0222 | +| value_loss | 0.000155 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1422 | +| iterations | 7902 | +| time_elapsed | 11374 | +| total_timesteps | 16183296 | +| train/ | | +| approx_kl | 0.011845689 | +| clip_fraction | 0.33 | +| clip_range | 0.071 | +| entropy_loss | -6.96 | +| explained_variance | 0.276 | +| learning_rate | 4.62e-05 | +| loss | -0.034 | +| n_updates | 47424 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000154 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1422 | +| iterations | 7903 | +| time_elapsed | 11375 | +| total_timesteps | 16185344 | +| train/ | | +| approx_kl | 0.010634735 | +| clip_fraction | 0.321 | +| clip_range | 0.071 | +| entropy_loss | -7.04 | +| explained_variance | 0.287 | +| learning_rate | 4.62e-05 | +| loss | -0.0299 | +| n_updates | 47428 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000199 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.14e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1422 | +| iterations | 7904 | +| time_elapsed | 11377 | +| total_timesteps | 16187392 | +| train/ | | +| approx_kl | 0.009675337 | +| clip_fraction | 0.311 | +| clip_range | 0.071 | +| entropy_loss | -6.65 | +| explained_variance | 0.281 | +| learning_rate | 4.62e-05 | +| loss | -0.0231 | +| n_updates | 47432 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000253 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1422 | +| iterations | 7905 | +| time_elapsed | 11378 | +| total_timesteps | 16189440 | +| train/ | | +| approx_kl | 0.011951156 | +| clip_fraction | 0.314 | +| clip_range | 0.071 | +| entropy_loss | -6.33 | +| explained_variance | 0.597 | +| learning_rate | 4.62e-05 | +| loss | -0.0316 | +| n_updates | 47436 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000183 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1422 | +| iterations | 7906 | +| time_elapsed | 11380 | +| total_timesteps | 16191488 | +| train/ | | +| approx_kl | 0.011658227 | +| clip_fraction | 0.331 | +| clip_range | 0.071 | +| entropy_loss | -6.36 | +| explained_variance | 0.575 | +| learning_rate | 4.62e-05 | +| loss | -0.0365 | +| n_updates | 47440 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000149 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1422 | +| iterations | 7907 | +| time_elapsed | 11381 | +| total_timesteps | 16193536 | +| train/ | | +| approx_kl | 0.011528952 | +| clip_fraction | 0.345 | +| clip_range | 0.071 | +| entropy_loss | -6.9 | +| explained_variance | 0.47 | +| learning_rate | 4.62e-05 | +| loss | -0.0398 | +| n_updates | 47444 | +| policy_gradient_loss | -0.0231 | +| value_loss | 7.49e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1422 | +| iterations | 7908 | +| time_elapsed | 11383 | +| total_timesteps | 16195584 | +| train/ | | +| approx_kl | 0.012424424 | +| clip_fraction | 0.339 | +| clip_range | 0.071 | +| entropy_loss | -6.96 | +| explained_variance | 0.513 | +| learning_rate | 4.62e-05 | +| loss | -0.0285 | +| n_updates | 47448 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000157 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1422 | +| iterations | 7909 | +| time_elapsed | 11384 | +| total_timesteps | 16197632 | +| train/ | | +| approx_kl | 0.012420334 | +| clip_fraction | 0.343 | +| clip_range | 0.071 | +| entropy_loss | -7.21 | +| explained_variance | -0.231 | +| learning_rate | 4.62e-05 | +| loss | -0.0328 | +| n_updates | 47452 | +| policy_gradient_loss | -0.0222 | +| value_loss | 9.28e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1422 | +| iterations | 7910 | +| time_elapsed | 11386 | +| total_timesteps | 16199680 | +| train/ | | +| approx_kl | 0.011272528 | +| clip_fraction | 0.315 | +| clip_range | 0.071 | +| entropy_loss | -7.24 | +| explained_variance | -0.0707 | +| learning_rate | 4.62e-05 | +| loss | -0.031 | +| n_updates | 47456 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000222 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1422 | +| iterations | 7911 | +| time_elapsed | 11387 | +| total_timesteps | 16201728 | +| train/ | | +| approx_kl | 0.011059365 | +| clip_fraction | 0.295 | +| clip_range | 0.071 | +| entropy_loss | -7.22 | +| explained_variance | 0.223 | +| learning_rate | 4.62e-05 | +| loss | -0.0325 | +| n_updates | 47460 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000233 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1422 | +| iterations | 7912 | +| time_elapsed | 11388 | +| total_timesteps | 16203776 | +| train/ | | +| approx_kl | 0.011908505 | +| clip_fraction | 0.331 | +| clip_range | 0.0709 | +| entropy_loss | -7.25 | +| explained_variance | -0.108 | +| learning_rate | 4.62e-05 | +| loss | -0.0324 | +| n_updates | 47464 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000131 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1422 | +| iterations | 7913 | +| time_elapsed | 11390 | +| total_timesteps | 16205824 | +| train/ | | +| approx_kl | 0.013505168 | +| clip_fraction | 0.327 | +| clip_range | 0.0709 | +| entropy_loss | -7.02 | +| explained_variance | 0.321 | +| learning_rate | 4.62e-05 | +| loss | -0.0325 | +| n_updates | 47468 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000139 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1422 | +| iterations | 7914 | +| time_elapsed | 11391 | +| total_timesteps | 16207872 | +| train/ | | +| approx_kl | 0.010873675 | +| clip_fraction | 0.309 | +| clip_range | 0.0709 | +| entropy_loss | -7.33 | +| explained_variance | -0.156 | +| learning_rate | 4.62e-05 | +| loss | -0.0284 | +| n_updates | 47472 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000131 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1422 | +| iterations | 7915 | +| time_elapsed | 11393 | +| total_timesteps | 16209920 | +| train/ | | +| approx_kl | 0.008677809 | +| clip_fraction | 0.286 | +| clip_range | 0.0709 | +| entropy_loss | -7.08 | +| explained_variance | 0.209 | +| learning_rate | 4.62e-05 | +| loss | -0.0225 | +| n_updates | 47476 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000258 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1422 | +| iterations | 7916 | +| time_elapsed | 11394 | +| total_timesteps | 16211968 | +| train/ | | +| approx_kl | 0.009549114 | +| clip_fraction | 0.306 | +| clip_range | 0.0709 | +| entropy_loss | -6.11 | +| explained_variance | 0.809 | +| learning_rate | 4.62e-05 | +| loss | -0.0309 | +| n_updates | 47480 | +| policy_gradient_loss | -0.0184 | +| value_loss | 9.67e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1422 | +| iterations | 7917 | +| time_elapsed | 11396 | +| total_timesteps | 16214016 | +| train/ | | +| approx_kl | 0.011378152 | +| clip_fraction | 0.311 | +| clip_range | 0.0709 | +| entropy_loss | -6.14 | +| explained_variance | 0.649 | +| learning_rate | 4.61e-05 | +| loss | -0.0261 | +| n_updates | 47484 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000146 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1422 | +| iterations | 7918 | +| time_elapsed | 11397 | +| total_timesteps | 16216064 | +| train/ | | +| approx_kl | 0.011214276 | +| clip_fraction | 0.306 | +| clip_range | 0.0709 | +| entropy_loss | -6.85 | +| explained_variance | 0.226 | +| learning_rate | 4.61e-05 | +| loss | -0.0278 | +| n_updates | 47488 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.00016 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1422 | +| iterations | 7919 | +| time_elapsed | 11399 | +| total_timesteps | 16218112 | +| train/ | | +| approx_kl | 0.011216934 | +| clip_fraction | 0.331 | +| clip_range | 0.0709 | +| entropy_loss | -6.95 | +| explained_variance | 0.186 | +| learning_rate | 4.61e-05 | +| loss | -0.0286 | +| n_updates | 47492 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000226 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1422 | +| iterations | 7920 | +| time_elapsed | 11400 | +| total_timesteps | 16220160 | +| train/ | | +| approx_kl | 0.009273429 | +| clip_fraction | 0.309 | +| clip_range | 0.0709 | +| entropy_loss | -7.04 | +| explained_variance | 0.205 | +| learning_rate | 4.61e-05 | +| loss | -0.0296 | +| n_updates | 47496 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.00016 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1422 | +| iterations | 7921 | +| time_elapsed | 11402 | +| total_timesteps | 16222208 | +| train/ | | +| approx_kl | 0.010876544 | +| clip_fraction | 0.328 | +| clip_range | 0.0709 | +| entropy_loss | -7.31 | +| explained_variance | -0.0483 | +| learning_rate | 4.61e-05 | +| loss | -0.0319 | +| n_updates | 47500 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000131 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1422 | +| iterations | 7922 | +| time_elapsed | 11403 | +| total_timesteps | 16224256 | +| train/ | | +| approx_kl | 0.008542959 | +| clip_fraction | 0.27 | +| clip_range | 0.0709 | +| entropy_loss | -7.26 | +| explained_variance | 0.208 | +| learning_rate | 4.61e-05 | +| loss | -0.0213 | +| n_updates | 47504 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000316 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1422 | +| iterations | 7923 | +| time_elapsed | 11404 | +| total_timesteps | 16226304 | +| train/ | | +| approx_kl | 0.010549423 | +| clip_fraction | 0.322 | +| clip_range | 0.0709 | +| entropy_loss | -7.08 | +| explained_variance | 0.404 | +| learning_rate | 4.61e-05 | +| loss | -0.0388 | +| n_updates | 47508 | +| policy_gradient_loss | -0.0225 | +| value_loss | 9.4e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1422 | +| iterations | 7924 | +| time_elapsed | 11406 | +| total_timesteps | 16228352 | +| train/ | | +| approx_kl | 0.008434957 | +| clip_fraction | 0.265 | +| clip_range | 0.0709 | +| entropy_loss | -6.99 | +| explained_variance | 0.304 | +| learning_rate | 4.61e-05 | +| loss | -0.0255 | +| n_updates | 47512 | +| policy_gradient_loss | -0.0147 | +| value_loss | 0.000316 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1422 | +| iterations | 7925 | +| time_elapsed | 11407 | +| total_timesteps | 16230400 | +| train/ | | +| approx_kl | 0.007946433 | +| clip_fraction | 0.285 | +| clip_range | 0.0709 | +| entropy_loss | -6.63 | +| explained_variance | 0.487 | +| learning_rate | 4.61e-05 | +| loss | -0.0267 | +| n_updates | 47516 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000187 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1422 | +| iterations | 7926 | +| time_elapsed | 11409 | +| total_timesteps | 16232448 | +| train/ | | +| approx_kl | 0.010770023 | +| clip_fraction | 0.317 | +| clip_range | 0.0709 | +| entropy_loss | -6.59 | +| explained_variance | 0.458 | +| learning_rate | 4.61e-05 | +| loss | -0.0321 | +| n_updates | 47520 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000122 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1422 | +| iterations | 7927 | +| time_elapsed | 11410 | +| total_timesteps | 16234496 | +| train/ | | +| approx_kl | 0.010998312 | +| clip_fraction | 0.309 | +| clip_range | 0.0709 | +| entropy_loss | -6.68 | +| explained_variance | 0.583 | +| learning_rate | 4.61e-05 | +| loss | -0.0338 | +| n_updates | 47524 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000141 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1422 | +| iterations | 7928 | +| time_elapsed | 11412 | +| total_timesteps | 16236544 | +| train/ | | +| approx_kl | 0.011255357 | +| clip_fraction | 0.312 | +| clip_range | 0.0709 | +| entropy_loss | -7.08 | +| explained_variance | 0.234 | +| learning_rate | 4.61e-05 | +| loss | -0.0323 | +| n_updates | 47528 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000251 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1422 | +| iterations | 7929 | +| time_elapsed | 11413 | +| total_timesteps | 16238592 | +| train/ | | +| approx_kl | 0.0098012425 | +| clip_fraction | 0.319 | +| clip_range | 0.0709 | +| entropy_loss | -6.61 | +| explained_variance | 0.528 | +| learning_rate | 4.61e-05 | +| loss | -0.0305 | +| n_updates | 47532 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000178 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1422 | +| iterations | 7930 | +| time_elapsed | 11414 | +| total_timesteps | 16240640 | +| train/ | | +| approx_kl | 0.010837134 | +| clip_fraction | 0.305 | +| clip_range | 0.0709 | +| entropy_loss | -7.17 | +| explained_variance | 0.0913 | +| learning_rate | 4.61e-05 | +| loss | -0.0318 | +| n_updates | 47536 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000199 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1422 | +| iterations | 7931 | +| time_elapsed | 11416 | +| total_timesteps | 16242688 | +| train/ | | +| approx_kl | 0.0089793205 | +| clip_fraction | 0.288 | +| clip_range | 0.0709 | +| entropy_loss | -6.96 | +| explained_variance | 0.269 | +| learning_rate | 4.61e-05 | +| loss | -0.0267 | +| n_updates | 47540 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000288 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1422 | +| iterations | 7932 | +| time_elapsed | 11417 | +| total_timesteps | 16244736 | +| train/ | | +| approx_kl | 0.007435421 | +| clip_fraction | 0.263 | +| clip_range | 0.0709 | +| entropy_loss | -6.81 | +| explained_variance | 0.367 | +| learning_rate | 4.61e-05 | +| loss | -0.0275 | +| n_updates | 47544 | +| policy_gradient_loss | -0.0147 | +| value_loss | 0.000341 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1422 | +| iterations | 7933 | +| time_elapsed | 11419 | +| total_timesteps | 16246784 | +| train/ | | +| approx_kl | 0.010455387 | +| clip_fraction | 0.337 | +| clip_range | 0.0709 | +| entropy_loss | -6.61 | +| explained_variance | 0.633 | +| learning_rate | 4.61e-05 | +| loss | -0.0306 | +| n_updates | 47548 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000133 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1422 | +| iterations | 7934 | +| time_elapsed | 11420 | +| total_timesteps | 16248832 | +| train/ | | +| approx_kl | 0.013536119 | +| clip_fraction | 0.324 | +| clip_range | 0.0709 | +| entropy_loss | -6.86 | +| explained_variance | 0.315 | +| learning_rate | 4.61e-05 | +| loss | -0.0302 | +| n_updates | 47552 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000139 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1422 | +| iterations | 7935 | +| time_elapsed | 11422 | +| total_timesteps | 16250880 | +| train/ | | +| approx_kl | 0.012410744 | +| clip_fraction | 0.333 | +| clip_range | 0.0709 | +| entropy_loss | -6.94 | +| explained_variance | 0.318 | +| learning_rate | 4.61e-05 | +| loss | -0.0348 | +| n_updates | 47556 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000143 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1422 | +| iterations | 7936 | +| time_elapsed | 11423 | +| total_timesteps | 16252928 | +| train/ | | +| approx_kl | 0.012064649 | +| clip_fraction | 0.323 | +| clip_range | 0.0709 | +| entropy_loss | -6.6 | +| explained_variance | 0.429 | +| learning_rate | 4.61e-05 | +| loss | -0.0285 | +| n_updates | 47560 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000216 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1422 | +| iterations | 7937 | +| time_elapsed | 11424 | +| total_timesteps | 16254976 | +| train/ | | +| approx_kl | 0.010556607 | +| clip_fraction | 0.301 | +| clip_range | 0.0709 | +| entropy_loss | -6.95 | +| explained_variance | 0.296 | +| learning_rate | 4.61e-05 | +| loss | -0.0333 | +| n_updates | 47564 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000201 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1422 | +| iterations | 7938 | +| time_elapsed | 11426 | +| total_timesteps | 16257024 | +| train/ | | +| approx_kl | 0.0110989325 | +| clip_fraction | 0.353 | +| clip_range | 0.0709 | +| entropy_loss | -6.99 | +| explained_variance | 0.31 | +| learning_rate | 4.61e-05 | +| loss | -0.0279 | +| n_updates | 47568 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000143 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1422 | +| iterations | 7939 | +| time_elapsed | 11427 | +| total_timesteps | 16259072 | +| train/ | | +| approx_kl | 0.012516926 | +| clip_fraction | 0.329 | +| clip_range | 0.0709 | +| entropy_loss | -6.92 | +| explained_variance | 0.286 | +| learning_rate | 4.61e-05 | +| loss | -0.0314 | +| n_updates | 47572 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000145 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1422 | +| iterations | 7940 | +| time_elapsed | 11429 | +| total_timesteps | 16261120 | +| train/ | | +| approx_kl | 0.01279686 | +| clip_fraction | 0.339 | +| clip_range | 0.0709 | +| entropy_loss | -7.21 | +| explained_variance | -0.506 | +| learning_rate | 4.61e-05 | +| loss | -0.0345 | +| n_updates | 47576 | +| policy_gradient_loss | -0.0225 | +| value_loss | 7.65e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1422 | +| iterations | 7941 | +| time_elapsed | 11430 | +| total_timesteps | 16263168 | +| train/ | | +| approx_kl | 0.010991107 | +| clip_fraction | 0.307 | +| clip_range | 0.0709 | +| entropy_loss | -6.93 | +| explained_variance | 0.454 | +| learning_rate | 4.61e-05 | +| loss | -0.0281 | +| n_updates | 47580 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000155 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1422 | +| iterations | 7942 | +| time_elapsed | 11432 | +| total_timesteps | 16265216 | +| train/ | | +| approx_kl | 0.01122335 | +| clip_fraction | 0.301 | +| clip_range | 0.0709 | +| entropy_loss | -6.81 | +| explained_variance | 0.17 | +| learning_rate | 4.61e-05 | +| loss | -0.0219 | +| n_updates | 47584 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000291 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1422 | +| iterations | 7943 | +| time_elapsed | 11433 | +| total_timesteps | 16267264 | +| train/ | | +| approx_kl | 0.012176906 | +| clip_fraction | 0.299 | +| clip_range | 0.0709 | +| entropy_loss | -6.89 | +| explained_variance | 0.431 | +| learning_rate | 4.61e-05 | +| loss | -0.0296 | +| n_updates | 47588 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000134 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1422 | +| iterations | 7944 | +| time_elapsed | 11434 | +| total_timesteps | 16269312 | +| train/ | | +| approx_kl | 0.010921035 | +| clip_fraction | 0.315 | +| clip_range | 0.0709 | +| entropy_loss | -6.66 | +| explained_variance | 0.482 | +| learning_rate | 4.61e-05 | +| loss | -0.0254 | +| n_updates | 47592 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000191 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1422 | +| iterations | 7945 | +| time_elapsed | 11436 | +| total_timesteps | 16271360 | +| train/ | | +| approx_kl | 0.012071819 | +| clip_fraction | 0.302 | +| clip_range | 0.0709 | +| entropy_loss | -6.82 | +| explained_variance | 0.353 | +| learning_rate | 4.61e-05 | +| loss | -0.0319 | +| n_updates | 47596 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000178 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1422 | +| iterations | 7946 | +| time_elapsed | 11437 | +| total_timesteps | 16273408 | +| train/ | | +| approx_kl | 0.012340881 | +| clip_fraction | 0.316 | +| clip_range | 0.0709 | +| entropy_loss | -7.03 | +| explained_variance | 0.237 | +| learning_rate | 4.61e-05 | +| loss | -0.0281 | +| n_updates | 47600 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000136 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1422 | +| iterations | 7947 | +| time_elapsed | 11439 | +| total_timesteps | 16275456 | +| train/ | | +| approx_kl | 0.011134314 | +| clip_fraction | 0.335 | +| clip_range | 0.0709 | +| entropy_loss | -6.81 | +| explained_variance | 0.489 | +| learning_rate | 4.61e-05 | +| loss | -0.0302 | +| n_updates | 47604 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000143 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1422 | +| iterations | 7948 | +| time_elapsed | 11440 | +| total_timesteps | 16277504 | +| train/ | | +| approx_kl | 0.012037428 | +| clip_fraction | 0.33 | +| clip_range | 0.0709 | +| entropy_loss | -7.11 | +| explained_variance | -0.0172 | +| learning_rate | 4.61e-05 | +| loss | -0.0334 | +| n_updates | 47608 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000199 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1422 | +| iterations | 7949 | +| time_elapsed | 11442 | +| total_timesteps | 16279552 | +| train/ | | +| approx_kl | 0.010816243 | +| clip_fraction | 0.326 | +| clip_range | 0.0709 | +| entropy_loss | -7 | +| explained_variance | 0.228 | +| learning_rate | 4.61e-05 | +| loss | -0.0299 | +| n_updates | 47612 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000168 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1422 | +| iterations | 7950 | +| time_elapsed | 11443 | +| total_timesteps | 16281600 | +| train/ | | +| approx_kl | 0.011915117 | +| clip_fraction | 0.305 | +| clip_range | 0.0709 | +| entropy_loss | -7.01 | +| explained_variance | 0.197 | +| learning_rate | 4.61e-05 | +| loss | -0.0283 | +| n_updates | 47616 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000331 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1422 | +| iterations | 7951 | +| time_elapsed | 11445 | +| total_timesteps | 16283648 | +| train/ | | +| approx_kl | 0.012329706 | +| clip_fraction | 0.36 | +| clip_range | 0.0709 | +| entropy_loss | -6.48 | +| explained_variance | 0.617 | +| learning_rate | 4.61e-05 | +| loss | -0.0339 | +| n_updates | 47620 | +| policy_gradient_loss | -0.0232 | +| value_loss | 0.000108 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1422 | +| iterations | 7952 | +| time_elapsed | 11446 | +| total_timesteps | 16285696 | +| train/ | | +| approx_kl | 0.011705073 | +| clip_fraction | 0.332 | +| clip_range | 0.0709 | +| entropy_loss | -7.12 | +| explained_variance | -0.22 | +| learning_rate | 4.61e-05 | +| loss | -0.0412 | +| n_updates | 47624 | +| policy_gradient_loss | -0.0219 | +| value_loss | 0.0001 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1422 | +| iterations | 7953 | +| time_elapsed | 11447 | +| total_timesteps | 16287744 | +| train/ | | +| approx_kl | 0.010523131 | +| clip_fraction | 0.327 | +| clip_range | 0.0709 | +| entropy_loss | -6.94 | +| explained_variance | 0.309 | +| learning_rate | 4.61e-05 | +| loss | -0.0232 | +| n_updates | 47628 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000302 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1422 | +| iterations | 7954 | +| time_elapsed | 11449 | +| total_timesteps | 16289792 | +| train/ | | +| approx_kl | 0.009843181 | +| clip_fraction | 0.317 | +| clip_range | 0.0709 | +| entropy_loss | -6.48 | +| explained_variance | 0.675 | +| learning_rate | 4.61e-05 | +| loss | -0.0343 | +| n_updates | 47632 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000125 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1422 | +| iterations | 7955 | +| time_elapsed | 11450 | +| total_timesteps | 16291840 | +| train/ | | +| approx_kl | 0.014731314 | +| clip_fraction | 0.345 | +| clip_range | 0.0709 | +| entropy_loss | -7.06 | +| explained_variance | 0.0934 | +| learning_rate | 4.61e-05 | +| loss | -0.0315 | +| n_updates | 47636 | +| policy_gradient_loss | -0.022 | +| value_loss | 0.00013 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1422 | +| iterations | 7956 | +| time_elapsed | 11452 | +| total_timesteps | 16293888 | +| train/ | | +| approx_kl | 0.01136145 | +| clip_fraction | 0.319 | +| clip_range | 0.0709 | +| entropy_loss | -7.33 | +| explained_variance | -0.0423 | +| learning_rate | 4.61e-05 | +| loss | -0.0283 | +| n_updates | 47640 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000132 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1422 | +| iterations | 7957 | +| time_elapsed | 11453 | +| total_timesteps | 16295936 | +| train/ | | +| approx_kl | 0.012523619 | +| clip_fraction | 0.326 | +| clip_range | 0.0709 | +| entropy_loss | -7.19 | +| explained_variance | -0.0935 | +| learning_rate | 4.61e-05 | +| loss | -0.0304 | +| n_updates | 47644 | +| policy_gradient_loss | -0.0195 | +| value_loss | 9.71e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1422 | +| iterations | 7958 | +| time_elapsed | 11455 | +| total_timesteps | 16297984 | +| train/ | | +| approx_kl | 0.011491414 | +| clip_fraction | 0.296 | +| clip_range | 0.0709 | +| entropy_loss | -6.43 | +| explained_variance | 0.671 | +| learning_rate | 4.61e-05 | +| loss | -0.0291 | +| n_updates | 47648 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.00015 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1422 | +| iterations | 7959 | +| time_elapsed | 11456 | +| total_timesteps | 16300032 | +| train/ | | +| approx_kl | 0.008765671 | +| clip_fraction | 0.292 | +| clip_range | 0.0709 | +| entropy_loss | -6.74 | +| explained_variance | 0.459 | +| learning_rate | 4.61e-05 | +| loss | -0.0162 | +| n_updates | 47652 | +| policy_gradient_loss | -0.013 | +| value_loss | 0.00026 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1422 | +| iterations | 7960 | +| time_elapsed | 11457 | +| total_timesteps | 16302080 | +| train/ | | +| approx_kl | 0.012878585 | +| clip_fraction | 0.356 | +| clip_range | 0.0709 | +| entropy_loss | -7.12 | +| explained_variance | -0.118 | +| learning_rate | 4.61e-05 | +| loss | -0.0346 | +| n_updates | 47656 | +| policy_gradient_loss | -0.023 | +| value_loss | 7.81e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1422 | +| iterations | 7961 | +| time_elapsed | 11459 | +| total_timesteps | 16304128 | +| train/ | | +| approx_kl | 0.0103448015 | +| clip_fraction | 0.279 | +| clip_range | 0.0709 | +| entropy_loss | -7.11 | +| explained_variance | -0.2 | +| learning_rate | 4.61e-05 | +| loss | -0.028 | +| n_updates | 47660 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000197 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1422 | +| iterations | 7962 | +| time_elapsed | 11460 | +| total_timesteps | 16306176 | +| train/ | | +| approx_kl | 0.0101602245 | +| clip_fraction | 0.281 | +| clip_range | 0.0709 | +| entropy_loss | -6.96 | +| explained_variance | 0.421 | +| learning_rate | 4.61e-05 | +| loss | -0.0322 | +| n_updates | 47664 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000189 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1422 | +| iterations | 7963 | +| time_elapsed | 11462 | +| total_timesteps | 16308224 | +| train/ | | +| approx_kl | 0.011132684 | +| clip_fraction | 0.334 | +| clip_range | 0.0709 | +| entropy_loss | -6.83 | +| explained_variance | 0.622 | +| learning_rate | 4.61e-05 | +| loss | -0.0328 | +| n_updates | 47668 | +| policy_gradient_loss | -0.0213 | +| value_loss | 9.3e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1422 | +| iterations | 7964 | +| time_elapsed | 11463 | +| total_timesteps | 16310272 | +| train/ | | +| approx_kl | 0.011776419 | +| clip_fraction | 0.305 | +| clip_range | 0.0709 | +| entropy_loss | -6.54 | +| explained_variance | 0.385 | +| learning_rate | 4.61e-05 | +| loss | -0.0262 | +| n_updates | 47672 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000225 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1422 | +| iterations | 7965 | +| time_elapsed | 11465 | +| total_timesteps | 16312320 | +| train/ | | +| approx_kl | 0.013708966 | +| clip_fraction | 0.328 | +| clip_range | 0.0709 | +| entropy_loss | -6.25 | +| explained_variance | 0.667 | +| learning_rate | 4.61e-05 | +| loss | -0.0298 | +| n_updates | 47676 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000148 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1422 | +| iterations | 7966 | +| time_elapsed | 11466 | +| total_timesteps | 16314368 | +| train/ | | +| approx_kl | 0.012002526 | +| clip_fraction | 0.335 | +| clip_range | 0.0709 | +| entropy_loss | -7.06 | +| explained_variance | -0.0378 | +| learning_rate | 4.61e-05 | +| loss | -0.0287 | +| n_updates | 47680 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000147 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1422 | +| iterations | 7967 | +| time_elapsed | 11468 | +| total_timesteps | 16316416 | +| train/ | | +| approx_kl | 0.011455799 | +| clip_fraction | 0.322 | +| clip_range | 0.0709 | +| entropy_loss | -7.14 | +| explained_variance | 0.306 | +| learning_rate | 4.61e-05 | +| loss | -0.0377 | +| n_updates | 47684 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000117 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1422 | +| iterations | 7968 | +| time_elapsed | 11469 | +| total_timesteps | 16318464 | +| train/ | | +| approx_kl | 0.011452224 | +| clip_fraction | 0.323 | +| clip_range | 0.0709 | +| entropy_loss | -6.82 | +| explained_variance | 0.622 | +| learning_rate | 4.61e-05 | +| loss | -0.0294 | +| n_updates | 47688 | +| policy_gradient_loss | -0.0182 | +| value_loss | 8.7e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1422 | +| iterations | 7969 | +| time_elapsed | 11470 | +| total_timesteps | 16320512 | +| train/ | | +| approx_kl | 0.009943282 | +| clip_fraction | 0.296 | +| clip_range | 0.0709 | +| entropy_loss | -6.81 | +| explained_variance | 0.464 | +| learning_rate | 4.61e-05 | +| loss | -0.0308 | +| n_updates | 47692 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000153 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1422 | +| iterations | 7970 | +| time_elapsed | 11472 | +| total_timesteps | 16322560 | +| train/ | | +| approx_kl | 0.011777587 | +| clip_fraction | 0.309 | +| clip_range | 0.0709 | +| entropy_loss | -6.92 | +| explained_variance | 0.405 | +| learning_rate | 4.61e-05 | +| loss | -0.0274 | +| n_updates | 47696 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000151 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1422 | +| iterations | 7971 | +| time_elapsed | 11473 | +| total_timesteps | 16324608 | +| train/ | | +| approx_kl | 0.013152381 | +| clip_fraction | 0.334 | +| clip_range | 0.0709 | +| entropy_loss | -6.54 | +| explained_variance | 0.539 | +| learning_rate | 4.61e-05 | +| loss | -0.0293 | +| n_updates | 47700 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000175 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1422 | +| iterations | 7972 | +| time_elapsed | 11475 | +| total_timesteps | 16326656 | +| train/ | | +| approx_kl | 0.013736172 | +| clip_fraction | 0.298 | +| clip_range | 0.0709 | +| entropy_loss | -7.34 | +| explained_variance | -0.117 | +| learning_rate | 4.61e-05 | +| loss | -0.0297 | +| n_updates | 47704 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000109 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1422 | +| iterations | 7973 | +| time_elapsed | 11476 | +| total_timesteps | 16328704 | +| train/ | | +| approx_kl | 0.010058479 | +| clip_fraction | 0.281 | +| clip_range | 0.0709 | +| entropy_loss | -7.25 | +| explained_variance | 0.235 | +| learning_rate | 4.61e-05 | +| loss | -0.0259 | +| n_updates | 47708 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000283 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1422 | +| iterations | 7974 | +| time_elapsed | 11478 | +| total_timesteps | 16330752 | +| train/ | | +| approx_kl | 0.010599911 | +| clip_fraction | 0.337 | +| clip_range | 0.0709 | +| entropy_loss | -6.91 | +| explained_variance | 0.371 | +| learning_rate | 4.61e-05 | +| loss | -0.0302 | +| n_updates | 47712 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000161 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1422 | +| iterations | 7975 | +| time_elapsed | 11479 | +| total_timesteps | 16332800 | +| train/ | | +| approx_kl | 0.011553036 | +| clip_fraction | 0.305 | +| clip_range | 0.0709 | +| entropy_loss | -6.57 | +| explained_variance | 0.587 | +| learning_rate | 4.61e-05 | +| loss | -0.0273 | +| n_updates | 47716 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000146 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1422 | +| iterations | 7976 | +| time_elapsed | 11480 | +| total_timesteps | 16334848 | +| train/ | | +| approx_kl | 0.010412389 | +| clip_fraction | 0.306 | +| clip_range | 0.0709 | +| entropy_loss | -6.95 | +| explained_variance | 0.32 | +| learning_rate | 4.61e-05 | +| loss | -0.0273 | +| n_updates | 47720 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000258 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1422 | +| iterations | 7977 | +| time_elapsed | 11482 | +| total_timesteps | 16336896 | +| train/ | | +| approx_kl | 0.0135242855 | +| clip_fraction | 0.292 | +| clip_range | 0.0709 | +| entropy_loss | -6.85 | +| explained_variance | -0.0588 | +| learning_rate | 4.61e-05 | +| loss | -0.0214 | +| n_updates | 47724 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000306 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1422 | +| iterations | 7978 | +| time_elapsed | 11483 | +| total_timesteps | 16338944 | +| train/ | | +| approx_kl | 0.011702046 | +| clip_fraction | 0.325 | +| clip_range | 0.0709 | +| entropy_loss | -6.85 | +| explained_variance | 0.177 | +| learning_rate | 4.61e-05 | +| loss | -0.0292 | +| n_updates | 47728 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000232 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1422 | +| iterations | 7979 | +| time_elapsed | 11485 | +| total_timesteps | 16340992 | +| train/ | | +| approx_kl | 0.014757229 | +| clip_fraction | 0.356 | +| clip_range | 0.0709 | +| entropy_loss | -6.83 | +| explained_variance | 0.467 | +| learning_rate | 4.61e-05 | +| loss | -0.0405 | +| n_updates | 47732 | +| policy_gradient_loss | -0.0241 | +| value_loss | 0.000116 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1422 | +| iterations | 7980 | +| time_elapsed | 11486 | +| total_timesteps | 16343040 | +| train/ | | +| approx_kl | 0.01211381 | +| clip_fraction | 0.352 | +| clip_range | 0.0709 | +| entropy_loss | -7.25 | +| explained_variance | -0.258 | +| learning_rate | 4.61e-05 | +| loss | -0.041 | +| n_updates | 47736 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000124 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1422 | +| iterations | 7981 | +| time_elapsed | 11488 | +| total_timesteps | 16345088 | +| train/ | | +| approx_kl | 0.010476688 | +| clip_fraction | 0.308 | +| clip_range | 0.0709 | +| entropy_loss | -6.88 | +| explained_variance | 0.436 | +| learning_rate | 4.61e-05 | +| loss | -0.0257 | +| n_updates | 47740 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.00019 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1422 | +| iterations | 7982 | +| time_elapsed | 11489 | +| total_timesteps | 16347136 | +| train/ | | +| approx_kl | 0.011799838 | +| clip_fraction | 0.285 | +| clip_range | 0.0709 | +| entropy_loss | -6.72 | +| explained_variance | 0.27 | +| learning_rate | 4.61e-05 | +| loss | -0.0287 | +| n_updates | 47744 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000315 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1422 | +| iterations | 7983 | +| time_elapsed | 11490 | +| total_timesteps | 16349184 | +| train/ | | +| approx_kl | 0.012495307 | +| clip_fraction | 0.338 | +| clip_range | 0.0709 | +| entropy_loss | -6.5 | +| explained_variance | 0.402 | +| learning_rate | 4.61e-05 | +| loss | -0.031 | +| n_updates | 47748 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000185 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1422 | +| iterations | 7984 | +| time_elapsed | 11492 | +| total_timesteps | 16351232 | +| train/ | | +| approx_kl | 0.0120215155 | +| clip_fraction | 0.336 | +| clip_range | 0.0709 | +| entropy_loss | -6.8 | +| explained_variance | 0.573 | +| learning_rate | 4.61e-05 | +| loss | -0.0333 | +| n_updates | 47752 | +| policy_gradient_loss | -0.0223 | +| value_loss | 9.24e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1422 | +| iterations | 7985 | +| time_elapsed | 11493 | +| total_timesteps | 16353280 | +| train/ | | +| approx_kl | 0.010603251 | +| clip_fraction | 0.31 | +| clip_range | 0.0709 | +| entropy_loss | -7.03 | +| explained_variance | 0.55 | +| learning_rate | 4.61e-05 | +| loss | -0.0308 | +| n_updates | 47756 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000107 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1422 | +| iterations | 7986 | +| time_elapsed | 11495 | +| total_timesteps | 16355328 | +| train/ | | +| approx_kl | 0.012056014 | +| clip_fraction | 0.308 | +| clip_range | 0.0709 | +| entropy_loss | -7.1 | +| explained_variance | -0.0681 | +| learning_rate | 4.61e-05 | +| loss | -0.0319 | +| n_updates | 47760 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000195 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1422 | +| iterations | 7987 | +| time_elapsed | 11496 | +| total_timesteps | 16357376 | +| train/ | | +| approx_kl | 0.01083514 | +| clip_fraction | 0.325 | +| clip_range | 0.0709 | +| entropy_loss | -6.9 | +| explained_variance | 0.627 | +| learning_rate | 4.61e-05 | +| loss | -0.037 | +| n_updates | 47764 | +| policy_gradient_loss | -0.0213 | +| value_loss | 9.61e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1422 | +| iterations | 7988 | +| time_elapsed | 11498 | +| total_timesteps | 16359424 | +| train/ | | +| approx_kl | 0.010625696 | +| clip_fraction | 0.326 | +| clip_range | 0.0709 | +| entropy_loss | -7.27 | +| explained_variance | -0.184 | +| learning_rate | 4.61e-05 | +| loss | -0.0344 | +| n_updates | 47768 | +| policy_gradient_loss | -0.0209 | +| value_loss | 9.84e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1422 | +| iterations | 7989 | +| time_elapsed | 11499 | +| total_timesteps | 16361472 | +| train/ | | +| approx_kl | 0.011783766 | +| clip_fraction | 0.328 | +| clip_range | 0.0709 | +| entropy_loss | -6.72 | +| explained_variance | 0.267 | +| learning_rate | 4.61e-05 | +| loss | -0.0289 | +| n_updates | 47772 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000311 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1422 | +| iterations | 7990 | +| time_elapsed | 11501 | +| total_timesteps | 16363520 | +| train/ | | +| approx_kl | 0.011126826 | +| clip_fraction | 0.32 | +| clip_range | 0.0709 | +| entropy_loss | -6.92 | +| explained_variance | 0.146 | +| learning_rate | 4.61e-05 | +| loss | -0.0303 | +| n_updates | 47776 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000164 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1422 | +| iterations | 7991 | +| time_elapsed | 11502 | +| total_timesteps | 16365568 | +| train/ | | +| approx_kl | 0.010653752 | +| clip_fraction | 0.313 | +| clip_range | 0.0709 | +| entropy_loss | -7.11 | +| explained_variance | 0.293 | +| learning_rate | 4.61e-05 | +| loss | -0.0281 | +| n_updates | 47780 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000162 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1422 | +| iterations | 7992 | +| time_elapsed | 11503 | +| total_timesteps | 16367616 | +| train/ | | +| approx_kl | 0.01100672 | +| clip_fraction | 0.303 | +| clip_range | 0.0709 | +| entropy_loss | -7.08 | +| explained_variance | 0.0163 | +| learning_rate | 4.61e-05 | +| loss | -0.0345 | +| n_updates | 47784 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000185 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1422 | +| iterations | 7993 | +| time_elapsed | 11505 | +| total_timesteps | 16369664 | +| train/ | | +| approx_kl | 0.007840444 | +| clip_fraction | 0.296 | +| clip_range | 0.0709 | +| entropy_loss | -6.7 | +| explained_variance | 0.534 | +| learning_rate | 4.61e-05 | +| loss | -0.0259 | +| n_updates | 47788 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000181 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1422 | +| iterations | 7994 | +| time_elapsed | 11506 | +| total_timesteps | 16371712 | +| train/ | | +| approx_kl | 0.008444086 | +| clip_fraction | 0.297 | +| clip_range | 0.0709 | +| entropy_loss | -7.03 | +| explained_variance | 0.266 | +| learning_rate | 4.61e-05 | +| loss | -0.0281 | +| n_updates | 47792 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000205 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1422 | +| iterations | 7995 | +| time_elapsed | 11508 | +| total_timesteps | 16373760 | +| train/ | | +| approx_kl | 0.010261605 | +| clip_fraction | 0.319 | +| clip_range | 0.0709 | +| entropy_loss | -7.04 | +| explained_variance | -0.0743 | +| learning_rate | 4.61e-05 | +| loss | -0.033 | +| n_updates | 47796 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000188 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1422 | +| iterations | 7996 | +| time_elapsed | 11509 | +| total_timesteps | 16375808 | +| train/ | | +| approx_kl | 0.0105850855 | +| clip_fraction | 0.31 | +| clip_range | 0.0709 | +| entropy_loss | -6.95 | +| explained_variance | 0.229 | +| learning_rate | 4.61e-05 | +| loss | -0.0352 | +| n_updates | 47800 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000243 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1422 | +| iterations | 7997 | +| time_elapsed | 11510 | +| total_timesteps | 16377856 | +| train/ | | +| approx_kl | 0.0117100235 | +| clip_fraction | 0.335 | +| clip_range | 0.0709 | +| entropy_loss | -6.6 | +| explained_variance | 0.655 | +| learning_rate | 4.61e-05 | +| loss | -0.0365 | +| n_updates | 47804 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000121 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1422 | +| iterations | 7998 | +| time_elapsed | 11512 | +| total_timesteps | 16379904 | +| train/ | | +| approx_kl | 0.011457664 | +| clip_fraction | 0.339 | +| clip_range | 0.0709 | +| entropy_loss | -7.12 | +| explained_variance | 0.447 | +| learning_rate | 4.61e-05 | +| loss | -0.0315 | +| n_updates | 47808 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000106 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1422 | +| iterations | 7999 | +| time_elapsed | 11513 | +| total_timesteps | 16381952 | +| train/ | | +| approx_kl | 0.0093441075 | +| clip_fraction | 0.287 | +| clip_range | 0.0709 | +| entropy_loss | -7.27 | +| explained_variance | 0.269 | +| learning_rate | 4.61e-05 | +| loss | -0.0282 | +| n_updates | 47812 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000213 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1422 | +| iterations | 8000 | +| time_elapsed | 11515 | +| total_timesteps | 16384000 | +| train/ | | +| approx_kl | 0.0069442587 | +| clip_fraction | 0.257 | +| clip_range | 0.0709 | +| entropy_loss | -6.92 | +| explained_variance | 0.303 | +| learning_rate | 4.61e-05 | +| loss | -0.0239 | +| n_updates | 47816 | +| policy_gradient_loss | -0.0148 | +| value_loss | 0.000315 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1422 | +| iterations | 8001 | +| time_elapsed | 11516 | +| total_timesteps | 16386048 | +| train/ | | +| approx_kl | 0.008420584 | +| clip_fraction | 0.3 | +| clip_range | 0.0709 | +| entropy_loss | -6.49 | +| explained_variance | 0.449 | +| learning_rate | 4.61e-05 | +| loss | -0.0279 | +| n_updates | 47820 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000335 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1422 | +| iterations | 8002 | +| time_elapsed | 11517 | +| total_timesteps | 16388096 | +| train/ | | +| approx_kl | 0.011378531 | +| clip_fraction | 0.345 | +| clip_range | 0.0709 | +| entropy_loss | -7.14 | +| explained_variance | -0.0591 | +| learning_rate | 4.61e-05 | +| loss | -0.0349 | +| n_updates | 47824 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000128 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1422 | +| iterations | 8003 | +| time_elapsed | 11519 | +| total_timesteps | 16390144 | +| train/ | | +| approx_kl | 0.011809511 | +| clip_fraction | 0.35 | +| clip_range | 0.0709 | +| entropy_loss | -6.61 | +| explained_variance | 0.641 | +| learning_rate | 4.61e-05 | +| loss | -0.0315 | +| n_updates | 47828 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000103 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1422 | +| iterations | 8004 | +| time_elapsed | 11520 | +| total_timesteps | 16392192 | +| train/ | | +| approx_kl | 0.012587809 | +| clip_fraction | 0.319 | +| clip_range | 0.0709 | +| entropy_loss | -7.03 | +| explained_variance | -0.106 | +| learning_rate | 4.61e-05 | +| loss | -0.0292 | +| n_updates | 47832 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000154 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1422 | +| iterations | 8005 | +| time_elapsed | 11522 | +| total_timesteps | 16394240 | +| train/ | | +| approx_kl | 0.009921875 | +| clip_fraction | 0.289 | +| clip_range | 0.0709 | +| entropy_loss | -6.78 | +| explained_variance | 0.62 | +| learning_rate | 4.61e-05 | +| loss | -0.0295 | +| n_updates | 47836 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000136 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1422 | +| iterations | 8006 | +| time_elapsed | 11523 | +| total_timesteps | 16396288 | +| train/ | | +| approx_kl | 0.0127974 | +| clip_fraction | 0.3 | +| clip_range | 0.0709 | +| entropy_loss | -6.87 | +| explained_variance | 0.35 | +| learning_rate | 4.61e-05 | +| loss | -0.0261 | +| n_updates | 47840 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.00013 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1422 | +| iterations | 8007 | +| time_elapsed | 11525 | +| total_timesteps | 16398336 | +| train/ | | +| approx_kl | 0.011256146 | +| clip_fraction | 0.319 | +| clip_range | 0.0709 | +| entropy_loss | -7.28 | +| explained_variance | -0.014 | +| learning_rate | 4.61e-05 | +| loss | -0.0324 | +| n_updates | 47844 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000142 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1422 | +| iterations | 8008 | +| time_elapsed | 11526 | +| total_timesteps | 16400384 | +| train/ | | +| approx_kl | 0.011516338 | +| clip_fraction | 0.331 | +| clip_range | 0.0709 | +| entropy_loss | -7.25 | +| explained_variance | -0.169 | +| learning_rate | 4.61e-05 | +| loss | -0.0321 | +| n_updates | 47848 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000115 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1422 | +| iterations | 8009 | +| time_elapsed | 11527 | +| total_timesteps | 16402432 | +| train/ | | +| approx_kl | 0.014593171 | +| clip_fraction | 0.321 | +| clip_range | 0.0709 | +| entropy_loss | -7.03 | +| explained_variance | 0.286 | +| learning_rate | 4.61e-05 | +| loss | -0.0334 | +| n_updates | 47852 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000132 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1422 | +| iterations | 8010 | +| time_elapsed | 11529 | +| total_timesteps | 16404480 | +| train/ | | +| approx_kl | 0.0113195125 | +| clip_fraction | 0.315 | +| clip_range | 0.0709 | +| entropy_loss | -6.59 | +| explained_variance | 0.505 | +| learning_rate | 4.61e-05 | +| loss | -0.0325 | +| n_updates | 47856 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000197 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1422 | +| iterations | 8011 | +| time_elapsed | 11530 | +| total_timesteps | 16406528 | +| train/ | | +| approx_kl | 0.012364343 | +| clip_fraction | 0.316 | +| clip_range | 0.0709 | +| entropy_loss | -6.88 | +| explained_variance | 0.255 | +| learning_rate | 4.61e-05 | +| loss | -0.0333 | +| n_updates | 47860 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000196 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1422 | +| iterations | 8012 | +| time_elapsed | 11532 | +| total_timesteps | 16408576 | +| train/ | | +| approx_kl | 0.011643352 | +| clip_fraction | 0.329 | +| clip_range | 0.0709 | +| entropy_loss | -7.07 | +| explained_variance | 0.0647 | +| learning_rate | 4.61e-05 | +| loss | -0.0333 | +| n_updates | 47864 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.00017 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1422 | +| iterations | 8013 | +| time_elapsed | 11533 | +| total_timesteps | 16410624 | +| train/ | | +| approx_kl | 0.012398779 | +| clip_fraction | 0.351 | +| clip_range | 0.0709 | +| entropy_loss | -6.64 | +| explained_variance | 0.493 | +| learning_rate | 4.61e-05 | +| loss | -0.0311 | +| n_updates | 47868 | +| policy_gradient_loss | -0.0209 | +| value_loss | 9.03e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1422 | +| iterations | 8014 | +| time_elapsed | 11535 | +| total_timesteps | 16412672 | +| train/ | | +| approx_kl | 0.009940614 | +| clip_fraction | 0.334 | +| clip_range | 0.0709 | +| entropy_loss | -6.89 | +| explained_variance | 0.292 | +| learning_rate | 4.61e-05 | +| loss | -0.0298 | +| n_updates | 47872 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000147 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1422 | +| iterations | 8015 | +| time_elapsed | 11536 | +| total_timesteps | 16414720 | +| train/ | | +| approx_kl | 0.010845356 | +| clip_fraction | 0.288 | +| clip_range | 0.0709 | +| entropy_loss | -7.04 | +| explained_variance | 0.271 | +| learning_rate | 4.61e-05 | +| loss | -0.0326 | +| n_updates | 47876 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000153 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1422 | +| iterations | 8016 | +| time_elapsed | 11538 | +| total_timesteps | 16416768 | +| train/ | | +| approx_kl | 0.010475362 | +| clip_fraction | 0.292 | +| clip_range | 0.0709 | +| entropy_loss | -7.34 | +| explained_variance | -0.0543 | +| learning_rate | 4.61e-05 | +| loss | -0.0289 | +| n_updates | 47880 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000202 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1422 | +| iterations | 8017 | +| time_elapsed | 11539 | +| total_timesteps | 16418816 | +| train/ | | +| approx_kl | 0.011137739 | +| clip_fraction | 0.301 | +| clip_range | 0.0709 | +| entropy_loss | -6.9 | +| explained_variance | 0.531 | +| learning_rate | 4.61e-05 | +| loss | -0.0326 | +| n_updates | 47884 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000133 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1422 | +| iterations | 8018 | +| time_elapsed | 11541 | +| total_timesteps | 16420864 | +| train/ | | +| approx_kl | 0.011011012 | +| clip_fraction | 0.312 | +| clip_range | 0.0709 | +| entropy_loss | -7.06 | +| explained_variance | 0.329 | +| learning_rate | 4.61e-05 | +| loss | -0.0318 | +| n_updates | 47888 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1422 | +| iterations | 8019 | +| time_elapsed | 11542 | +| total_timesteps | 16422912 | +| train/ | | +| approx_kl | 0.009562032 | +| clip_fraction | 0.275 | +| clip_range | 0.0709 | +| entropy_loss | -6.34 | +| explained_variance | 0.531 | +| learning_rate | 4.61e-05 | +| loss | -0.0299 | +| n_updates | 47892 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000181 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1422 | +| iterations | 8020 | +| time_elapsed | 11543 | +| total_timesteps | 16424960 | +| train/ | | +| approx_kl | 0.011258259 | +| clip_fraction | 0.303 | +| clip_range | 0.0709 | +| entropy_loss | -6.5 | +| explained_variance | 0.711 | +| learning_rate | 4.61e-05 | +| loss | -0.0332 | +| n_updates | 47896 | +| policy_gradient_loss | -0.0189 | +| value_loss | 9.86e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1422 | +| iterations | 8021 | +| time_elapsed | 11545 | +| total_timesteps | 16427008 | +| train/ | | +| approx_kl | 0.009343041 | +| clip_fraction | 0.302 | +| clip_range | 0.0709 | +| entropy_loss | -7.02 | +| explained_variance | 0.549 | +| learning_rate | 4.61e-05 | +| loss | -0.0223 | +| n_updates | 47900 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000111 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1422 | +| iterations | 8022 | +| time_elapsed | 11546 | +| total_timesteps | 16429056 | +| train/ | | +| approx_kl | 0.010545138 | +| clip_fraction | 0.329 | +| clip_range | 0.0709 | +| entropy_loss | -7.08 | +| explained_variance | 0.367 | +| learning_rate | 4.61e-05 | +| loss | -0.03 | +| n_updates | 47904 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000165 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1422 | +| iterations | 8023 | +| time_elapsed | 11548 | +| total_timesteps | 16431104 | +| train/ | | +| approx_kl | 0.011522284 | +| clip_fraction | 0.316 | +| clip_range | 0.0709 | +| entropy_loss | -7.14 | +| explained_variance | -0.0221 | +| learning_rate | 4.61e-05 | +| loss | -0.0297 | +| n_updates | 47908 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.00014 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1422 | +| iterations | 8024 | +| time_elapsed | 11549 | +| total_timesteps | 16433152 | +| train/ | | +| approx_kl | 0.008856655 | +| clip_fraction | 0.288 | +| clip_range | 0.0709 | +| entropy_loss | -6.68 | +| explained_variance | 0.507 | +| learning_rate | 4.61e-05 | +| loss | -0.027 | +| n_updates | 47912 | +| policy_gradient_loss | -0.0141 | +| value_loss | 0.00024 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1422 | +| iterations | 8025 | +| time_elapsed | 11550 | +| total_timesteps | 16435200 | +| train/ | | +| approx_kl | 0.0097748395 | +| clip_fraction | 0.323 | +| clip_range | 0.0709 | +| entropy_loss | -6.75 | +| explained_variance | 0.538 | +| learning_rate | 4.61e-05 | +| loss | -0.0338 | +| n_updates | 47916 | +| policy_gradient_loss | -0.021 | +| value_loss | 9.84e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1422 | +| iterations | 8026 | +| time_elapsed | 11552 | +| total_timesteps | 16437248 | +| train/ | | +| approx_kl | 0.008383068 | +| clip_fraction | 0.29 | +| clip_range | 0.0709 | +| entropy_loss | -6.7 | +| explained_variance | 0.571 | +| learning_rate | 4.61e-05 | +| loss | -0.0338 | +| n_updates | 47920 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000175 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1422 | +| iterations | 8027 | +| time_elapsed | 11553 | +| total_timesteps | 16439296 | +| train/ | | +| approx_kl | 0.009004072 | +| clip_fraction | 0.308 | +| clip_range | 0.0709 | +| entropy_loss | -7.27 | +| explained_variance | 0.189 | +| learning_rate | 4.61e-05 | +| loss | -0.0357 | +| n_updates | 47924 | +| policy_gradient_loss | -0.022 | +| value_loss | 6.14e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1422 | +| iterations | 8028 | +| time_elapsed | 11555 | +| total_timesteps | 16441344 | +| train/ | | +| approx_kl | 0.010369863 | +| clip_fraction | 0.311 | +| clip_range | 0.0709 | +| entropy_loss | -6.67 | +| explained_variance | 0.675 | +| learning_rate | 4.61e-05 | +| loss | -0.0282 | +| n_updates | 47928 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000124 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1422 | +| iterations | 8029 | +| time_elapsed | 11556 | +| total_timesteps | 16443392 | +| train/ | | +| approx_kl | 0.011344301 | +| clip_fraction | 0.319 | +| clip_range | 0.0709 | +| entropy_loss | -7.01 | +| explained_variance | 0.403 | +| learning_rate | 4.61e-05 | +| loss | -0.0309 | +| n_updates | 47932 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000124 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1422 | +| iterations | 8030 | +| time_elapsed | 11558 | +| total_timesteps | 16445440 | +| train/ | | +| approx_kl | 0.009508689 | +| clip_fraction | 0.311 | +| clip_range | 0.0709 | +| entropy_loss | -7.26 | +| explained_variance | 0.00792 | +| learning_rate | 4.61e-05 | +| loss | -0.0287 | +| n_updates | 47936 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000133 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1422 | +| iterations | 8031 | +| time_elapsed | 11559 | +| total_timesteps | 16447488 | +| train/ | | +| approx_kl | 0.009137778 | +| clip_fraction | 0.265 | +| clip_range | 0.0709 | +| entropy_loss | -7.13 | +| explained_variance | 0.313 | +| learning_rate | 4.61e-05 | +| loss | -0.0282 | +| n_updates | 47940 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000159 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1422 | +| iterations | 8032 | +| time_elapsed | 11561 | +| total_timesteps | 16449536 | +| train/ | | +| approx_kl | 0.009058559 | +| clip_fraction | 0.271 | +| clip_range | 0.0709 | +| entropy_loss | -7.08 | +| explained_variance | 0.215 | +| learning_rate | 4.61e-05 | +| loss | -0.0324 | +| n_updates | 47944 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000184 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1422 | +| iterations | 8033 | +| time_elapsed | 11562 | +| total_timesteps | 16451584 | +| train/ | | +| approx_kl | 0.010577225 | +| clip_fraction | 0.311 | +| clip_range | 0.0709 | +| entropy_loss | -7.11 | +| explained_variance | -0.0306 | +| learning_rate | 4.61e-05 | +| loss | -0.0301 | +| n_updates | 47948 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.00021 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1422 | +| iterations | 8034 | +| time_elapsed | 11563 | +| total_timesteps | 16453632 | +| train/ | | +| approx_kl | 0.009707652 | +| clip_fraction | 0.316 | +| clip_range | 0.0709 | +| entropy_loss | -6.99 | +| explained_variance | 0.311 | +| learning_rate | 4.61e-05 | +| loss | -0.0259 | +| n_updates | 47952 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000317 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1422 | +| iterations | 8035 | +| time_elapsed | 11565 | +| total_timesteps | 16455680 | +| train/ | | +| approx_kl | 0.010391323 | +| clip_fraction | 0.31 | +| clip_range | 0.0709 | +| entropy_loss | -6.91 | +| explained_variance | -0.223 | +| learning_rate | 4.61e-05 | +| loss | -0.0335 | +| n_updates | 47956 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000188 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1422 | +| iterations | 8036 | +| time_elapsed | 11566 | +| total_timesteps | 16457728 | +| train/ | | +| approx_kl | 0.010634271 | +| clip_fraction | 0.326 | +| clip_range | 0.0709 | +| entropy_loss | -7.09 | +| explained_variance | 0.137 | +| learning_rate | 4.61e-05 | +| loss | -0.0326 | +| n_updates | 47960 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000201 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1422 | +| iterations | 8037 | +| time_elapsed | 11568 | +| total_timesteps | 16459776 | +| train/ | | +| approx_kl | 0.011187205 | +| clip_fraction | 0.344 | +| clip_range | 0.0709 | +| entropy_loss | -6.45 | +| explained_variance | 0.639 | +| learning_rate | 4.61e-05 | +| loss | -0.0327 | +| n_updates | 47964 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000131 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1422 | +| iterations | 8038 | +| time_elapsed | 11569 | +| total_timesteps | 16461824 | +| train/ | | +| approx_kl | 0.010733598 | +| clip_fraction | 0.327 | +| clip_range | 0.0709 | +| entropy_loss | -7.03 | +| explained_variance | -0.136 | +| learning_rate | 4.61e-05 | +| loss | -0.033 | +| n_updates | 47968 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000105 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1422 | +| iterations | 8039 | +| time_elapsed | 11571 | +| total_timesteps | 16463872 | +| train/ | | +| approx_kl | 0.010704984 | +| clip_fraction | 0.323 | +| clip_range | 0.0709 | +| entropy_loss | -6.98 | +| explained_variance | 0.246 | +| learning_rate | 4.61e-05 | +| loss | -0.0236 | +| n_updates | 47972 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000205 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1422 | +| iterations | 8040 | +| time_elapsed | 11572 | +| total_timesteps | 16465920 | +| train/ | | +| approx_kl | 0.011067372 | +| clip_fraction | 0.318 | +| clip_range | 0.0709 | +| entropy_loss | -7.38 | +| explained_variance | -0.191 | +| learning_rate | 4.61e-05 | +| loss | -0.0296 | +| n_updates | 47976 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000126 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1422 | +| iterations | 8041 | +| time_elapsed | 11574 | +| total_timesteps | 16467968 | +| train/ | | +| approx_kl | 0.011525996 | +| clip_fraction | 0.324 | +| clip_range | 0.0709 | +| entropy_loss | -7.03 | +| explained_variance | 0.342 | +| learning_rate | 4.61e-05 | +| loss | -0.0295 | +| n_updates | 47980 | +| policy_gradient_loss | -0.0198 | +| value_loss | 8.43e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1422 | +| iterations | 8042 | +| time_elapsed | 11575 | +| total_timesteps | 16470016 | +| train/ | | +| approx_kl | 0.011244003 | +| clip_fraction | 0.305 | +| clip_range | 0.0709 | +| entropy_loss | -7.11 | +| explained_variance | 0.293 | +| learning_rate | 4.61e-05 | +| loss | -0.0306 | +| n_updates | 47984 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000133 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.315 | +| time/ | | +| fps | 1422 | +| iterations | 8043 | +| time_elapsed | 11577 | +| total_timesteps | 16472064 | +| train/ | | +| approx_kl | 0.00993813 | +| clip_fraction | 0.302 | +| clip_range | 0.0709 | +| entropy_loss | -7.07 | +| explained_variance | 0.29 | +| learning_rate | 4.61e-05 | +| loss | -0.0283 | +| n_updates | 47988 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000156 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.315 | +| time/ | | +| fps | 1422 | +| iterations | 8044 | +| time_elapsed | 11578 | +| total_timesteps | 16474112 | +| train/ | | +| approx_kl | 0.010507278 | +| clip_fraction | 0.286 | +| clip_range | 0.0709 | +| entropy_loss | -6.58 | +| explained_variance | 0.592 | +| learning_rate | 4.61e-05 | +| loss | -0.0251 | +| n_updates | 47992 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000157 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1422 | +| iterations | 8045 | +| time_elapsed | 11579 | +| total_timesteps | 16476160 | +| train/ | | +| approx_kl | 0.011361007 | +| clip_fraction | 0.359 | +| clip_range | 0.0709 | +| entropy_loss | -7.22 | +| explained_variance | -0.329 | +| learning_rate | 4.61e-05 | +| loss | -0.0422 | +| n_updates | 47996 | +| policy_gradient_loss | -0.0248 | +| value_loss | 5.14e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1422 | +| iterations | 8046 | +| time_elapsed | 11581 | +| total_timesteps | 16478208 | +| train/ | | +| approx_kl | 0.008858212 | +| clip_fraction | 0.291 | +| clip_range | 0.0709 | +| entropy_loss | -7.29 | +| explained_variance | 0.00763 | +| learning_rate | 4.61e-05 | +| loss | -0.0289 | +| n_updates | 48000 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000246 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1422 | +| iterations | 8047 | +| time_elapsed | 11582 | +| total_timesteps | 16480256 | +| train/ | | +| approx_kl | 0.01017608 | +| clip_fraction | 0.293 | +| clip_range | 0.0709 | +| entropy_loss | -6.84 | +| explained_variance | 0.323 | +| learning_rate | 4.61e-05 | +| loss | -0.0305 | +| n_updates | 48004 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000172 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1422 | +| iterations | 8048 | +| time_elapsed | 11584 | +| total_timesteps | 16482304 | +| train/ | | +| approx_kl | 0.012264886 | +| clip_fraction | 0.289 | +| clip_range | 0.0709 | +| entropy_loss | -6.73 | +| explained_variance | 0.473 | +| learning_rate | 4.61e-05 | +| loss | -0.0273 | +| n_updates | 48008 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000225 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1422 | +| iterations | 8049 | +| time_elapsed | 11585 | +| total_timesteps | 16484352 | +| train/ | | +| approx_kl | 0.008845735 | +| clip_fraction | 0.308 | +| clip_range | 0.0709 | +| entropy_loss | -6.99 | +| explained_variance | 0.197 | +| learning_rate | 4.61e-05 | +| loss | -0.034 | +| n_updates | 48012 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000187 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1422 | +| iterations | 8050 | +| time_elapsed | 11587 | +| total_timesteps | 16486400 | +| train/ | | +| approx_kl | 0.010297261 | +| clip_fraction | 0.308 | +| clip_range | 0.0709 | +| entropy_loss | -6.84 | +| explained_variance | 0.489 | +| learning_rate | 4.61e-05 | +| loss | -0.0314 | +| n_updates | 48016 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.00016 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1422 | +| iterations | 8051 | +| time_elapsed | 11588 | +| total_timesteps | 16488448 | +| train/ | | +| approx_kl | 0.009525536 | +| clip_fraction | 0.295 | +| clip_range | 0.0709 | +| entropy_loss | -7.07 | +| explained_variance | 0.229 | +| learning_rate | 4.61e-05 | +| loss | -0.0311 | +| n_updates | 48020 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000193 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1422 | +| iterations | 8052 | +| time_elapsed | 11589 | +| total_timesteps | 16490496 | +| train/ | | +| approx_kl | 0.010220177 | +| clip_fraction | 0.302 | +| clip_range | 0.0709 | +| entropy_loss | -7.19 | +| explained_variance | -0.178 | +| learning_rate | 4.61e-05 | +| loss | -0.0316 | +| n_updates | 48024 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000183 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1422 | +| iterations | 8053 | +| time_elapsed | 11591 | +| total_timesteps | 16492544 | +| train/ | | +| approx_kl | 0.010029523 | +| clip_fraction | 0.286 | +| clip_range | 0.0709 | +| entropy_loss | -7.04 | +| explained_variance | -0.0126 | +| learning_rate | 4.61e-05 | +| loss | -0.0315 | +| n_updates | 48028 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000221 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1422 | +| iterations | 8054 | +| time_elapsed | 11592 | +| total_timesteps | 16494592 | +| train/ | | +| approx_kl | 0.011425513 | +| clip_fraction | 0.308 | +| clip_range | 0.0709 | +| entropy_loss | -6.99 | +| explained_variance | 0.402 | +| learning_rate | 4.61e-05 | +| loss | -0.0291 | +| n_updates | 48032 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000136 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1422 | +| iterations | 8055 | +| time_elapsed | 11594 | +| total_timesteps | 16496640 | +| train/ | | +| approx_kl | 0.010844571 | +| clip_fraction | 0.301 | +| clip_range | 0.0709 | +| entropy_loss | -6.63 | +| explained_variance | 0.295 | +| learning_rate | 4.61e-05 | +| loss | -0.0257 | +| n_updates | 48036 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000315 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1422 | +| iterations | 8056 | +| time_elapsed | 11595 | +| total_timesteps | 16498688 | +| train/ | | +| approx_kl | 0.012804272 | +| clip_fraction | 0.333 | +| clip_range | 0.0709 | +| entropy_loss | -6.66 | +| explained_variance | 0.444 | +| learning_rate | 4.61e-05 | +| loss | -0.0322 | +| n_updates | 48040 | +| policy_gradient_loss | -0.0224 | +| value_loss | 0.000137 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1422 | +| iterations | 8057 | +| time_elapsed | 11597 | +| total_timesteps | 16500736 | +| train/ | | +| approx_kl | 0.011048665 | +| clip_fraction | 0.338 | +| clip_range | 0.0709 | +| entropy_loss | -7.18 | +| explained_variance | -0.432 | +| learning_rate | 4.61e-05 | +| loss | -0.0397 | +| n_updates | 48044 | +| policy_gradient_loss | -0.0239 | +| value_loss | 8.29e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1422 | +| iterations | 8058 | +| time_elapsed | 11598 | +| total_timesteps | 16502784 | +| train/ | | +| approx_kl | 0.009821508 | +| clip_fraction | 0.326 | +| clip_range | 0.0709 | +| entropy_loss | -6.98 | +| explained_variance | 0.167 | +| learning_rate | 4.61e-05 | +| loss | -0.0321 | +| n_updates | 48048 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000206 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1422 | +| iterations | 8059 | +| time_elapsed | 11600 | +| total_timesteps | 16504832 | +| train/ | | +| approx_kl | 0.01136407 | +| clip_fraction | 0.309 | +| clip_range | 0.0709 | +| entropy_loss | -6.84 | +| explained_variance | 0.455 | +| learning_rate | 4.61e-05 | +| loss | -0.0314 | +| n_updates | 48052 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000157 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1422 | +| iterations | 8060 | +| time_elapsed | 11601 | +| total_timesteps | 16506880 | +| train/ | | +| approx_kl | 0.009146031 | +| clip_fraction | 0.29 | +| clip_range | 0.0709 | +| entropy_loss | -6.58 | +| explained_variance | 0.384 | +| learning_rate | 4.61e-05 | +| loss | -0.0283 | +| n_updates | 48056 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000366 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1422 | +| iterations | 8061 | +| time_elapsed | 11603 | +| total_timesteps | 16508928 | +| train/ | | +| approx_kl | 0.012180309 | +| clip_fraction | 0.333 | +| clip_range | 0.0709 | +| entropy_loss | -7.02 | +| explained_variance | 0.216 | +| learning_rate | 4.61e-05 | +| loss | -0.0302 | +| n_updates | 48060 | +| policy_gradient_loss | -0.0227 | +| value_loss | 0.000118 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1422 | +| iterations | 8062 | +| time_elapsed | 11604 | +| total_timesteps | 16510976 | +| train/ | | +| approx_kl | 0.011295476 | +| clip_fraction | 0.302 | +| clip_range | 0.0709 | +| entropy_loss | -7.16 | +| explained_variance | 0.217 | +| learning_rate | 4.61e-05 | +| loss | -0.0256 | +| n_updates | 48064 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000258 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1422 | +| iterations | 8063 | +| time_elapsed | 11606 | +| total_timesteps | 16513024 | +| train/ | | +| approx_kl | 0.010453735 | +| clip_fraction | 0.32 | +| clip_range | 0.0709 | +| entropy_loss | -6.74 | +| explained_variance | 0.465 | +| learning_rate | 4.61e-05 | +| loss | -0.0326 | +| n_updates | 48068 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000219 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1422 | +| iterations | 8064 | +| time_elapsed | 11607 | +| total_timesteps | 16515072 | +| train/ | | +| approx_kl | 0.011096381 | +| clip_fraction | 0.325 | +| clip_range | 0.0709 | +| entropy_loss | -7.17 | +| explained_variance | -0.0655 | +| learning_rate | 4.61e-05 | +| loss | -0.0385 | +| n_updates | 48072 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000142 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1422 | +| iterations | 8065 | +| time_elapsed | 11608 | +| total_timesteps | 16517120 | +| train/ | | +| approx_kl | 0.0109722605 | +| clip_fraction | 0.318 | +| clip_range | 0.0709 | +| entropy_loss | -6.97 | +| explained_variance | 0.509 | +| learning_rate | 4.61e-05 | +| loss | -0.0284 | +| n_updates | 48076 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.00012 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1422 | +| iterations | 8066 | +| time_elapsed | 11610 | +| total_timesteps | 16519168 | +| train/ | | +| approx_kl | 0.011318365 | +| clip_fraction | 0.365 | +| clip_range | 0.0709 | +| entropy_loss | -6.48 | +| explained_variance | 0.854 | +| learning_rate | 4.61e-05 | +| loss | -0.0395 | +| n_updates | 48080 | +| policy_gradient_loss | -0.0239 | +| value_loss | 3.73e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 1422 | +| iterations | 8067 | +| time_elapsed | 11611 | +| total_timesteps | 16521216 | +| train/ | | +| approx_kl | 0.012253182 | +| clip_fraction | 0.285 | +| clip_range | 0.0709 | +| entropy_loss | -6.64 | +| explained_variance | 0.402 | +| learning_rate | 4.61e-05 | +| loss | -0.0288 | +| n_updates | 48084 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.00022 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.306 | +| time/ | | +| fps | 1422 | +| iterations | 8068 | +| time_elapsed | 11613 | +| total_timesteps | 16523264 | +| train/ | | +| approx_kl | 0.011451367 | +| clip_fraction | 0.331 | +| clip_range | 0.0709 | +| entropy_loss | -7.29 | +| explained_variance | -0.0982 | +| learning_rate | 4.61e-05 | +| loss | -0.0316 | +| n_updates | 48088 | +| policy_gradient_loss | -0.0212 | +| value_loss | 6.85e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.306 | +| time/ | | +| fps | 1422 | +| iterations | 8069 | +| time_elapsed | 11614 | +| total_timesteps | 16525312 | +| train/ | | +| approx_kl | 0.009749908 | +| clip_fraction | 0.316 | +| clip_range | 0.0709 | +| entropy_loss | -7.03 | +| explained_variance | 0.292 | +| learning_rate | 4.61e-05 | +| loss | -0.0304 | +| n_updates | 48092 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000192 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 1422 | +| iterations | 8070 | +| time_elapsed | 11616 | +| total_timesteps | 16527360 | +| train/ | | +| approx_kl | 0.010995904 | +| clip_fraction | 0.319 | +| clip_range | 0.0709 | +| entropy_loss | -7.24 | +| explained_variance | 0.363 | +| learning_rate | 4.61e-05 | +| loss | -0.0283 | +| n_updates | 48096 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000117 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1422 | +| iterations | 8071 | +| time_elapsed | 11617 | +| total_timesteps | 16529408 | +| train/ | | +| approx_kl | 0.011368671 | +| clip_fraction | 0.31 | +| clip_range | 0.0709 | +| entropy_loss | -7.16 | +| explained_variance | 0.298 | +| learning_rate | 4.61e-05 | +| loss | -0.0325 | +| n_updates | 48100 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000185 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1422 | +| iterations | 8072 | +| time_elapsed | 11619 | +| total_timesteps | 16531456 | +| train/ | | +| approx_kl | 0.011035731 | +| clip_fraction | 0.317 | +| clip_range | 0.0709 | +| entropy_loss | -7.03 | +| explained_variance | 0.401 | +| learning_rate | 4.61e-05 | +| loss | -0.024 | +| n_updates | 48104 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000215 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1422 | +| iterations | 8073 | +| time_elapsed | 11620 | +| total_timesteps | 16533504 | +| train/ | | +| approx_kl | 0.010221833 | +| clip_fraction | 0.329 | +| clip_range | 0.0709 | +| entropy_loss | -6.11 | +| explained_variance | 0.708 | +| learning_rate | 4.61e-05 | +| loss | -0.0322 | +| n_updates | 48108 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.00013 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.315 | +| time/ | | +| fps | 1422 | +| iterations | 8074 | +| time_elapsed | 11622 | +| total_timesteps | 16535552 | +| train/ | | +| approx_kl | 0.011012977 | +| clip_fraction | 0.316 | +| clip_range | 0.0709 | +| entropy_loss | -6.92 | +| explained_variance | 0.216 | +| learning_rate | 4.61e-05 | +| loss | -0.0279 | +| n_updates | 48112 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000257 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1422 | +| iterations | 8075 | +| time_elapsed | 11623 | +| total_timesteps | 16537600 | +| train/ | | +| approx_kl | 0.009387894 | +| clip_fraction | 0.281 | +| clip_range | 0.0709 | +| entropy_loss | -7.16 | +| explained_variance | 0.148 | +| learning_rate | 4.61e-05 | +| loss | -0.0213 | +| n_updates | 48116 | +| policy_gradient_loss | -0.0146 | +| value_loss | 0.000298 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1422 | +| iterations | 8076 | +| time_elapsed | 11624 | +| total_timesteps | 16539648 | +| train/ | | +| approx_kl | 0.009772854 | +| clip_fraction | 0.287 | +| clip_range | 0.0709 | +| entropy_loss | -7.05 | +| explained_variance | 0.0849 | +| learning_rate | 4.61e-05 | +| loss | -0.0341 | +| n_updates | 48120 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000157 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1422 | +| iterations | 8077 | +| time_elapsed | 11626 | +| total_timesteps | 16541696 | +| train/ | | +| approx_kl | 0.010719571 | +| clip_fraction | 0.293 | +| clip_range | 0.0709 | +| entropy_loss | -6.44 | +| explained_variance | 0.557 | +| learning_rate | 4.61e-05 | +| loss | -0.0242 | +| n_updates | 48124 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000174 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1422 | +| iterations | 8078 | +| time_elapsed | 11627 | +| total_timesteps | 16543744 | +| train/ | | +| approx_kl | 0.009834238 | +| clip_fraction | 0.326 | +| clip_range | 0.0709 | +| entropy_loss | -6.45 | +| explained_variance | 0.678 | +| learning_rate | 4.61e-05 | +| loss | -0.0319 | +| n_updates | 48128 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000121 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1422 | +| iterations | 8079 | +| time_elapsed | 11629 | +| total_timesteps | 16545792 | +| train/ | | +| approx_kl | 0.01155383 | +| clip_fraction | 0.298 | +| clip_range | 0.0709 | +| entropy_loss | -6.8 | +| explained_variance | 0.36 | +| learning_rate | 4.61e-05 | +| loss | -0.0281 | +| n_updates | 48132 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000204 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1422 | +| iterations | 8080 | +| time_elapsed | 11630 | +| total_timesteps | 16547840 | +| train/ | | +| approx_kl | 0.010568716 | +| clip_fraction | 0.302 | +| clip_range | 0.0709 | +| entropy_loss | -7.29 | +| explained_variance | 0.0909 | +| learning_rate | 4.61e-05 | +| loss | -0.0331 | +| n_updates | 48136 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000139 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1422 | +| iterations | 8081 | +| time_elapsed | 11632 | +| total_timesteps | 16549888 | +| train/ | | +| approx_kl | 0.009163894 | +| clip_fraction | 0.291 | +| clip_range | 0.0709 | +| entropy_loss | -6.97 | +| explained_variance | 0.381 | +| learning_rate | 4.61e-05 | +| loss | -0.0274 | +| n_updates | 48140 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000167 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1422 | +| iterations | 8082 | +| time_elapsed | 11633 | +| total_timesteps | 16551936 | +| train/ | | +| approx_kl | 0.009803902 | +| clip_fraction | 0.317 | +| clip_range | 0.0709 | +| entropy_loss | -6.91 | +| explained_variance | 0.506 | +| learning_rate | 4.61e-05 | +| loss | -0.0323 | +| n_updates | 48144 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000113 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1422 | +| iterations | 8083 | +| time_elapsed | 11634 | +| total_timesteps | 16553984 | +| train/ | | +| approx_kl | 0.00851822 | +| clip_fraction | 0.285 | +| clip_range | 0.0709 | +| entropy_loss | -6.94 | +| explained_variance | 0.347 | +| learning_rate | 4.61e-05 | +| loss | -0.02 | +| n_updates | 48148 | +| policy_gradient_loss | -0.0147 | +| value_loss | 0.00026 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1422 | +| iterations | 8084 | +| time_elapsed | 11636 | +| total_timesteps | 16556032 | +| train/ | | +| approx_kl | 0.011216474 | +| clip_fraction | 0.297 | +| clip_range | 0.0709 | +| entropy_loss | -6.83 | +| explained_variance | 0.198 | +| learning_rate | 4.61e-05 | +| loss | -0.0258 | +| n_updates | 48152 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000216 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1422 | +| iterations | 8085 | +| time_elapsed | 11637 | +| total_timesteps | 16558080 | +| train/ | | +| approx_kl | 0.011740877 | +| clip_fraction | 0.314 | +| clip_range | 0.0709 | +| entropy_loss | -6.47 | +| explained_variance | 0.554 | +| learning_rate | 4.61e-05 | +| loss | -0.0311 | +| n_updates | 48156 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000164 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1422 | +| iterations | 8086 | +| time_elapsed | 11639 | +| total_timesteps | 16560128 | +| train/ | | +| approx_kl | 0.013101186 | +| clip_fraction | 0.324 | +| clip_range | 0.0709 | +| entropy_loss | -6.71 | +| explained_variance | 0.398 | +| learning_rate | 4.61e-05 | +| loss | -0.0299 | +| n_updates | 48160 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000255 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1422 | +| iterations | 8087 | +| time_elapsed | 11640 | +| total_timesteps | 16562176 | +| train/ | | +| approx_kl | 0.012259121 | +| clip_fraction | 0.32 | +| clip_range | 0.0709 | +| entropy_loss | -6.86 | +| explained_variance | 0.045 | +| learning_rate | 4.61e-05 | +| loss | -0.03 | +| n_updates | 48164 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000257 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1422 | +| iterations | 8088 | +| time_elapsed | 11642 | +| total_timesteps | 16564224 | +| train/ | | +| approx_kl | 0.013418564 | +| clip_fraction | 0.328 | +| clip_range | 0.0709 | +| entropy_loss | -6.95 | +| explained_variance | 0.177 | +| learning_rate | 4.61e-05 | +| loss | -0.0319 | +| n_updates | 48168 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000181 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1422 | +| iterations | 8089 | +| time_elapsed | 11643 | +| total_timesteps | 16566272 | +| train/ | | +| approx_kl | 0.011833985 | +| clip_fraction | 0.34 | +| clip_range | 0.0709 | +| entropy_loss | -7.08 | +| explained_variance | -0.17 | +| learning_rate | 4.61e-05 | +| loss | -0.0344 | +| n_updates | 48172 | +| policy_gradient_loss | -0.0223 | +| value_loss | 0.000123 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1422 | +| iterations | 8090 | +| time_elapsed | 11645 | +| total_timesteps | 16568320 | +| train/ | | +| approx_kl | 0.01208891 | +| clip_fraction | 0.353 | +| clip_range | 0.0709 | +| entropy_loss | -7.07 | +| explained_variance | 0.393 | +| learning_rate | 4.61e-05 | +| loss | -0.0372 | +| n_updates | 48176 | +| policy_gradient_loss | -0.0224 | +| value_loss | 8.37e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1422 | +| iterations | 8091 | +| time_elapsed | 11646 | +| total_timesteps | 16570368 | +| train/ | | +| approx_kl | 0.013726821 | +| clip_fraction | 0.328 | +| clip_range | 0.0709 | +| entropy_loss | -7.05 | +| explained_variance | 0.349 | +| learning_rate | 4.61e-05 | +| loss | -0.0368 | +| n_updates | 48180 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000124 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1422 | +| iterations | 8092 | +| time_elapsed | 11647 | +| total_timesteps | 16572416 | +| train/ | | +| approx_kl | 0.012367671 | +| clip_fraction | 0.354 | +| clip_range | 0.0709 | +| entropy_loss | -7.29 | +| explained_variance | -0.392 | +| learning_rate | 4.61e-05 | +| loss | -0.0308 | +| n_updates | 48184 | +| policy_gradient_loss | -0.0215 | +| value_loss | 6.09e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1422 | +| iterations | 8093 | +| time_elapsed | 11649 | +| total_timesteps | 16574464 | +| train/ | | +| approx_kl | 0.011733867 | +| clip_fraction | 0.286 | +| clip_range | 0.0709 | +| entropy_loss | -7.04 | +| explained_variance | 0.00229 | +| learning_rate | 4.61e-05 | +| loss | -0.0284 | +| n_updates | 48188 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000169 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1422 | +| iterations | 8094 | +| time_elapsed | 11650 | +| total_timesteps | 16576512 | +| train/ | | +| approx_kl | 0.013875521 | +| clip_fraction | 0.32 | +| clip_range | 0.0709 | +| entropy_loss | -7.24 | +| explained_variance | -0.125 | +| learning_rate | 4.61e-05 | +| loss | -0.0305 | +| n_updates | 48192 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000103 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1422 | +| iterations | 8095 | +| time_elapsed | 11652 | +| total_timesteps | 16578560 | +| train/ | | +| approx_kl | 0.010639371 | +| clip_fraction | 0.296 | +| clip_range | 0.0709 | +| entropy_loss | -6.74 | +| explained_variance | 0.548 | +| learning_rate | 4.61e-05 | +| loss | -0.0281 | +| n_updates | 48196 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000164 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1422 | +| iterations | 8096 | +| time_elapsed | 11653 | +| total_timesteps | 16580608 | +| train/ | | +| approx_kl | 0.012926856 | +| clip_fraction | 0.354 | +| clip_range | 0.0709 | +| entropy_loss | -6.87 | +| explained_variance | 0.564 | +| learning_rate | 4.61e-05 | +| loss | -0.0391 | +| n_updates | 48200 | +| policy_gradient_loss | -0.0245 | +| value_loss | 5.3e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1422 | +| iterations | 8097 | +| time_elapsed | 11654 | +| total_timesteps | 16582656 | +| train/ | | +| approx_kl | 0.010822869 | +| clip_fraction | 0.325 | +| clip_range | 0.0709 | +| entropy_loss | -6.78 | +| explained_variance | 0.145 | +| learning_rate | 4.61e-05 | +| loss | -0.0283 | +| n_updates | 48204 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000131 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1422 | +| iterations | 8098 | +| time_elapsed | 11656 | +| total_timesteps | 16584704 | +| train/ | | +| approx_kl | 0.010907373 | +| clip_fraction | 0.318 | +| clip_range | 0.0709 | +| entropy_loss | -6.47 | +| explained_variance | 0.631 | +| learning_rate | 4.61e-05 | +| loss | -0.0305 | +| n_updates | 48208 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000129 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1422 | +| iterations | 8099 | +| time_elapsed | 11657 | +| total_timesteps | 16586752 | +| train/ | | +| approx_kl | 0.01043147 | +| clip_fraction | 0.317 | +| clip_range | 0.0709 | +| entropy_loss | -6.93 | +| explained_variance | 0.573 | +| learning_rate | 4.61e-05 | +| loss | -0.0332 | +| n_updates | 48212 | +| policy_gradient_loss | -0.0201 | +| value_loss | 5.53e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1422 | +| iterations | 8100 | +| time_elapsed | 11659 | +| total_timesteps | 16588800 | +| train/ | | +| approx_kl | 0.011376318 | +| clip_fraction | 0.298 | +| clip_range | 0.0709 | +| entropy_loss | -6.63 | +| explained_variance | 0.589 | +| learning_rate | 4.61e-05 | +| loss | -0.0268 | +| n_updates | 48216 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000146 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1422 | +| iterations | 8101 | +| time_elapsed | 11660 | +| total_timesteps | 16590848 | +| train/ | | +| approx_kl | 0.012764559 | +| clip_fraction | 0.331 | +| clip_range | 0.0709 | +| entropy_loss | -6.58 | +| explained_variance | 0.457 | +| learning_rate | 4.61e-05 | +| loss | -0.0294 | +| n_updates | 48220 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.00018 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1422 | +| iterations | 8102 | +| time_elapsed | 11662 | +| total_timesteps | 16592896 | +| train/ | | +| approx_kl | 0.011442589 | +| clip_fraction | 0.326 | +| clip_range | 0.0709 | +| entropy_loss | -7.1 | +| explained_variance | -0.144 | +| learning_rate | 4.61e-05 | +| loss | -0.0334 | +| n_updates | 48224 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.00013 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1422 | +| iterations | 8103 | +| time_elapsed | 11663 | +| total_timesteps | 16594944 | +| train/ | | +| approx_kl | 0.010885578 | +| clip_fraction | 0.338 | +| clip_range | 0.0709 | +| entropy_loss | -7.19 | +| explained_variance | 0.402 | +| learning_rate | 4.61e-05 | +| loss | -0.0319 | +| n_updates | 48228 | +| policy_gradient_loss | -0.02 | +| value_loss | 9.17e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1422 | +| iterations | 8104 | +| time_elapsed | 11664 | +| total_timesteps | 16596992 | +| train/ | | +| approx_kl | 0.010535914 | +| clip_fraction | 0.274 | +| clip_range | 0.0709 | +| entropy_loss | -6.83 | +| explained_variance | 0.295 | +| learning_rate | 4.61e-05 | +| loss | -0.0293 | +| n_updates | 48232 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000378 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1422 | +| iterations | 8105 | +| time_elapsed | 11666 | +| total_timesteps | 16599040 | +| train/ | | +| approx_kl | 0.009403434 | +| clip_fraction | 0.34 | +| clip_range | 0.0709 | +| entropy_loss | -7.14 | +| explained_variance | 0.27 | +| learning_rate | 4.61e-05 | +| loss | -0.0298 | +| n_updates | 48236 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000175 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1422 | +| iterations | 8106 | +| time_elapsed | 11667 | +| total_timesteps | 16601088 | +| train/ | | +| approx_kl | 0.010946261 | +| clip_fraction | 0.343 | +| clip_range | 0.0709 | +| entropy_loss | -7.1 | +| explained_variance | 0.0149 | +| learning_rate | 4.61e-05 | +| loss | -0.0312 | +| n_updates | 48240 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000199 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1422 | +| iterations | 8107 | +| time_elapsed | 11669 | +| total_timesteps | 16603136 | +| train/ | | +| approx_kl | 0.011720428 | +| clip_fraction | 0.338 | +| clip_range | 0.0708 | +| entropy_loss | -6.63 | +| explained_variance | 0.52 | +| learning_rate | 4.61e-05 | +| loss | -0.0255 | +| n_updates | 48244 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000187 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1422 | +| iterations | 8108 | +| time_elapsed | 11670 | +| total_timesteps | 16605184 | +| train/ | | +| approx_kl | 0.012623818 | +| clip_fraction | 0.329 | +| clip_range | 0.0708 | +| entropy_loss | -6.77 | +| explained_variance | 0.479 | +| learning_rate | 4.61e-05 | +| loss | -0.0323 | +| n_updates | 48248 | +| policy_gradient_loss | -0.0221 | +| value_loss | 0.000119 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1422 | +| iterations | 8109 | +| time_elapsed | 11672 | +| total_timesteps | 16607232 | +| train/ | | +| approx_kl | 0.0119772935 | +| clip_fraction | 0.335 | +| clip_range | 0.0708 | +| entropy_loss | -7.07 | +| explained_variance | -0.164 | +| learning_rate | 4.61e-05 | +| loss | -0.0409 | +| n_updates | 48252 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000103 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1422 | +| iterations | 8110 | +| time_elapsed | 11673 | +| total_timesteps | 16609280 | +| train/ | | +| approx_kl | 0.013577972 | +| clip_fraction | 0.324 | +| clip_range | 0.0708 | +| entropy_loss | -7.08 | +| explained_variance | 0.318 | +| learning_rate | 4.61e-05 | +| loss | -0.0255 | +| n_updates | 48256 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000132 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1422 | +| iterations | 8111 | +| time_elapsed | 11674 | +| total_timesteps | 16611328 | +| train/ | | +| approx_kl | 0.014103848 | +| clip_fraction | 0.342 | +| clip_range | 0.0708 | +| entropy_loss | -6.91 | +| explained_variance | 0.412 | +| learning_rate | 4.61e-05 | +| loss | -0.0389 | +| n_updates | 48260 | +| policy_gradient_loss | -0.0214 | +| value_loss | 9.16e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1422 | +| iterations | 8112 | +| time_elapsed | 11676 | +| total_timesteps | 16613376 | +| train/ | | +| approx_kl | 0.009871083 | +| clip_fraction | 0.304 | +| clip_range | 0.0708 | +| entropy_loss | -6.64 | +| explained_variance | 0.398 | +| learning_rate | 4.61e-05 | +| loss | -0.0272 | +| n_updates | 48264 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000254 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1422 | +| iterations | 8113 | +| time_elapsed | 11677 | +| total_timesteps | 16615424 | +| train/ | | +| approx_kl | 0.011840006 | +| clip_fraction | 0.318 | +| clip_range | 0.0708 | +| entropy_loss | -6.68 | +| explained_variance | 0.511 | +| learning_rate | 4.61e-05 | +| loss | -0.0319 | +| n_updates | 48268 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000151 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1422 | +| iterations | 8114 | +| time_elapsed | 11679 | +| total_timesteps | 16617472 | +| train/ | | +| approx_kl | 0.012132812 | +| clip_fraction | 0.318 | +| clip_range | 0.0708 | +| entropy_loss | -6.69 | +| explained_variance | 0.512 | +| learning_rate | 4.61e-05 | +| loss | -0.0342 | +| n_updates | 48272 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000158 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1422 | +| iterations | 8115 | +| time_elapsed | 11680 | +| total_timesteps | 16619520 | +| train/ | | +| approx_kl | 0.011324186 | +| clip_fraction | 0.328 | +| clip_range | 0.0708 | +| entropy_loss | -6.99 | +| explained_variance | 0.0277 | +| learning_rate | 4.61e-05 | +| loss | -0.0344 | +| n_updates | 48276 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.00021 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1422 | +| iterations | 8116 | +| time_elapsed | 11682 | +| total_timesteps | 16621568 | +| train/ | | +| approx_kl | 0.009306404 | +| clip_fraction | 0.333 | +| clip_range | 0.0708 | +| entropy_loss | -6.68 | +| explained_variance | 0.421 | +| learning_rate | 4.61e-05 | +| loss | -0.0266 | +| n_updates | 48280 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000141 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1422 | +| iterations | 8117 | +| time_elapsed | 11683 | +| total_timesteps | 16623616 | +| train/ | | +| approx_kl | 0.013002367 | +| clip_fraction | 0.324 | +| clip_range | 0.0708 | +| entropy_loss | -6.68 | +| explained_variance | 0.489 | +| learning_rate | 4.61e-05 | +| loss | -0.0284 | +| n_updates | 48284 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000158 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1422 | +| iterations | 8118 | +| time_elapsed | 11684 | +| total_timesteps | 16625664 | +| train/ | | +| approx_kl | 0.012506403 | +| clip_fraction | 0.335 | +| clip_range | 0.0708 | +| entropy_loss | -6.81 | +| explained_variance | 0.508 | +| learning_rate | 4.61e-05 | +| loss | -0.0352 | +| n_updates | 48288 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000131 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1422 | +| iterations | 8119 | +| time_elapsed | 11686 | +| total_timesteps | 16627712 | +| train/ | | +| approx_kl | 0.012178911 | +| clip_fraction | 0.326 | +| clip_range | 0.0708 | +| entropy_loss | -7.09 | +| explained_variance | 0.319 | +| learning_rate | 4.61e-05 | +| loss | -0.0322 | +| n_updates | 48292 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000145 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1422 | +| iterations | 8120 | +| time_elapsed | 11687 | +| total_timesteps | 16629760 | +| train/ | | +| approx_kl | 0.010239922 | +| clip_fraction | 0.302 | +| clip_range | 0.0708 | +| entropy_loss | -6.81 | +| explained_variance | 0.256 | +| learning_rate | 4.61e-05 | +| loss | -0.0229 | +| n_updates | 48296 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000366 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1422 | +| iterations | 8121 | +| time_elapsed | 11689 | +| total_timesteps | 16631808 | +| train/ | | +| approx_kl | 0.012043544 | +| clip_fraction | 0.343 | +| clip_range | 0.0708 | +| entropy_loss | -6.88 | +| explained_variance | 0.29 | +| learning_rate | 4.61e-05 | +| loss | -0.0341 | +| n_updates | 48300 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000158 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1422 | +| iterations | 8122 | +| time_elapsed | 11690 | +| total_timesteps | 16633856 | +| train/ | | +| approx_kl | 0.0118379155 | +| clip_fraction | 0.336 | +| clip_range | 0.0708 | +| entropy_loss | -6.67 | +| explained_variance | 0.466 | +| learning_rate | 4.6e-05 | +| loss | -0.0303 | +| n_updates | 48304 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000181 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1422 | +| iterations | 8123 | +| time_elapsed | 11692 | +| total_timesteps | 16635904 | +| train/ | | +| approx_kl | 0.0144378105 | +| clip_fraction | 0.339 | +| clip_range | 0.0708 | +| entropy_loss | -6.6 | +| explained_variance | 0.518 | +| learning_rate | 4.6e-05 | +| loss | -0.0343 | +| n_updates | 48308 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000107 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1422 | +| iterations | 8124 | +| time_elapsed | 11693 | +| total_timesteps | 16637952 | +| train/ | | +| approx_kl | 0.013207948 | +| clip_fraction | 0.329 | +| clip_range | 0.0708 | +| entropy_loss | -7.37 | +| explained_variance | -0.232 | +| learning_rate | 4.6e-05 | +| loss | -0.0351 | +| n_updates | 48312 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000135 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1422 | +| iterations | 8125 | +| time_elapsed | 11694 | +| total_timesteps | 16640000 | +| train/ | | +| approx_kl | 0.012366533 | +| clip_fraction | 0.318 | +| clip_range | 0.0708 | +| entropy_loss | -7.11 | +| explained_variance | 0.304 | +| learning_rate | 4.6e-05 | +| loss | -0.0276 | +| n_updates | 48316 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000167 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1422 | +| iterations | 8126 | +| time_elapsed | 11696 | +| total_timesteps | 16642048 | +| train/ | | +| approx_kl | 0.011030884 | +| clip_fraction | 0.296 | +| clip_range | 0.0708 | +| entropy_loss | -6.37 | +| explained_variance | 0.657 | +| learning_rate | 4.6e-05 | +| loss | -0.0184 | +| n_updates | 48320 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000163 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1422 | +| iterations | 8127 | +| time_elapsed | 11697 | +| total_timesteps | 16644096 | +| train/ | | +| approx_kl | 0.011853363 | +| clip_fraction | 0.327 | +| clip_range | 0.0708 | +| entropy_loss | -6.81 | +| explained_variance | 0.234 | +| learning_rate | 4.6e-05 | +| loss | -0.0321 | +| n_updates | 48324 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.00018 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1422 | +| iterations | 8128 | +| time_elapsed | 11699 | +| total_timesteps | 16646144 | +| train/ | | +| approx_kl | 0.010692585 | +| clip_fraction | 0.324 | +| clip_range | 0.0708 | +| entropy_loss | -6.59 | +| explained_variance | 0.554 | +| learning_rate | 4.6e-05 | +| loss | -0.0282 | +| n_updates | 48328 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1422 | +| iterations | 8129 | +| time_elapsed | 11700 | +| total_timesteps | 16648192 | +| train/ | | +| approx_kl | 0.012541404 | +| clip_fraction | 0.338 | +| clip_range | 0.0708 | +| entropy_loss | -6.71 | +| explained_variance | 0.399 | +| learning_rate | 4.6e-05 | +| loss | -0.0356 | +| n_updates | 48332 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000136 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1422 | +| iterations | 8130 | +| time_elapsed | 11701 | +| total_timesteps | 16650240 | +| train/ | | +| approx_kl | 0.012859935 | +| clip_fraction | 0.357 | +| clip_range | 0.0708 | +| entropy_loss | -6.65 | +| explained_variance | 0.614 | +| learning_rate | 4.6e-05 | +| loss | -0.034 | +| n_updates | 48336 | +| policy_gradient_loss | -0.0221 | +| value_loss | 8.48e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1422 | +| iterations | 8131 | +| time_elapsed | 11703 | +| total_timesteps | 16652288 | +| train/ | | +| approx_kl | 0.013121781 | +| clip_fraction | 0.35 | +| clip_range | 0.0708 | +| entropy_loss | -7.14 | +| explained_variance | -0.162 | +| learning_rate | 4.6e-05 | +| loss | -0.0437 | +| n_updates | 48340 | +| policy_gradient_loss | -0.0213 | +| value_loss | 6.12e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1422 | +| iterations | 8132 | +| time_elapsed | 11704 | +| total_timesteps | 16654336 | +| train/ | | +| approx_kl | 0.009045465 | +| clip_fraction | 0.275 | +| clip_range | 0.0708 | +| entropy_loss | -6.73 | +| explained_variance | 0.482 | +| learning_rate | 4.6e-05 | +| loss | -0.0303 | +| n_updates | 48344 | +| policy_gradient_loss | -0.0147 | +| value_loss | 0.000254 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1422 | +| iterations | 8133 | +| time_elapsed | 11706 | +| total_timesteps | 16656384 | +| train/ | | +| approx_kl | 0.009235659 | +| clip_fraction | 0.299 | +| clip_range | 0.0708 | +| entropy_loss | -6.7 | +| explained_variance | 0.411 | +| learning_rate | 4.6e-05 | +| loss | -0.0311 | +| n_updates | 48348 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000242 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1422 | +| iterations | 8134 | +| time_elapsed | 11707 | +| total_timesteps | 16658432 | +| train/ | | +| approx_kl | 0.010228554 | +| clip_fraction | 0.32 | +| clip_range | 0.0708 | +| entropy_loss | -6.56 | +| explained_variance | 0.592 | +| learning_rate | 4.6e-05 | +| loss | -0.0328 | +| n_updates | 48352 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1422 | +| iterations | 8135 | +| time_elapsed | 11708 | +| total_timesteps | 16660480 | +| train/ | | +| approx_kl | 0.015192512 | +| clip_fraction | 0.347 | +| clip_range | 0.0708 | +| entropy_loss | -6.86 | +| explained_variance | 0.511 | +| learning_rate | 4.6e-05 | +| loss | -0.0315 | +| n_updates | 48356 | +| policy_gradient_loss | -0.0215 | +| value_loss | 8.73e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1422 | +| iterations | 8136 | +| time_elapsed | 11710 | +| total_timesteps | 16662528 | +| train/ | | +| approx_kl | 0.014423484 | +| clip_fraction | 0.344 | +| clip_range | 0.0708 | +| entropy_loss | -7.07 | +| explained_variance | 0.348 | +| learning_rate | 4.6e-05 | +| loss | -0.033 | +| n_updates | 48360 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.00014 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1422 | +| iterations | 8137 | +| time_elapsed | 11711 | +| total_timesteps | 16664576 | +| train/ | | +| approx_kl | 0.010123187 | +| clip_fraction | 0.313 | +| clip_range | 0.0708 | +| entropy_loss | -6.95 | +| explained_variance | 0.277 | +| learning_rate | 4.6e-05 | +| loss | -0.031 | +| n_updates | 48364 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000187 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1422 | +| iterations | 8138 | +| time_elapsed | 11713 | +| total_timesteps | 16666624 | +| train/ | | +| approx_kl | 0.010318408 | +| clip_fraction | 0.297 | +| clip_range | 0.0708 | +| entropy_loss | -7.05 | +| explained_variance | 0.104 | +| learning_rate | 4.6e-05 | +| loss | -0.0313 | +| n_updates | 48368 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000275 | +----------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1422 | +| iterations | 8139 | +| time_elapsed | 11714 | +| total_timesteps | 16668672 | +| train/ | | +| approx_kl | 0.00943 | +| clip_fraction | 0.302 | +| clip_range | 0.0708 | +| entropy_loss | -6.78 | +| explained_variance | 0.508 | +| learning_rate | 4.6e-05 | +| loss | -0.0295 | +| n_updates | 48372 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000142 | +-------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1422 | +| iterations | 8140 | +| time_elapsed | 11716 | +| total_timesteps | 16670720 | +| train/ | | +| approx_kl | 0.011541713 | +| clip_fraction | 0.319 | +| clip_range | 0.0708 | +| entropy_loss | -6.84 | +| explained_variance | 0.451 | +| learning_rate | 4.6e-05 | +| loss | -0.0283 | +| n_updates | 48376 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000145 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1422 | +| iterations | 8141 | +| time_elapsed | 11717 | +| total_timesteps | 16672768 | +| train/ | | +| approx_kl | 0.012059877 | +| clip_fraction | 0.323 | +| clip_range | 0.0708 | +| entropy_loss | -6.75 | +| explained_variance | 0.378 | +| learning_rate | 4.6e-05 | +| loss | -0.0359 | +| n_updates | 48380 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000134 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1422 | +| iterations | 8142 | +| time_elapsed | 11718 | +| total_timesteps | 16674816 | +| train/ | | +| approx_kl | 0.010700605 | +| clip_fraction | 0.314 | +| clip_range | 0.0708 | +| entropy_loss | -6.69 | +| explained_variance | 0.53 | +| learning_rate | 4.6e-05 | +| loss | -0.0331 | +| n_updates | 48384 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1422 | +| iterations | 8143 | +| time_elapsed | 11720 | +| total_timesteps | 16676864 | +| train/ | | +| approx_kl | 0.012478406 | +| clip_fraction | 0.306 | +| clip_range | 0.0708 | +| entropy_loss | -7.19 | +| explained_variance | -0.155 | +| learning_rate | 4.6e-05 | +| loss | -0.0287 | +| n_updates | 48388 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000145 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1422 | +| iterations | 8144 | +| time_elapsed | 11721 | +| total_timesteps | 16678912 | +| train/ | | +| approx_kl | 0.012304001 | +| clip_fraction | 0.331 | +| clip_range | 0.0708 | +| entropy_loss | -6.39 | +| explained_variance | 0.622 | +| learning_rate | 4.6e-05 | +| loss | -0.0284 | +| n_updates | 48392 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000119 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1422 | +| iterations | 8145 | +| time_elapsed | 11723 | +| total_timesteps | 16680960 | +| train/ | | +| approx_kl | 0.0140580665 | +| clip_fraction | 0.305 | +| clip_range | 0.0708 | +| entropy_loss | -6.63 | +| explained_variance | -0.0603 | +| learning_rate | 4.6e-05 | +| loss | -0.0316 | +| n_updates | 48396 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000137 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1422 | +| iterations | 8146 | +| time_elapsed | 11724 | +| total_timesteps | 16683008 | +| train/ | | +| approx_kl | 0.010574946 | +| clip_fraction | 0.327 | +| clip_range | 0.0708 | +| entropy_loss | -6.58 | +| explained_variance | 0.283 | +| learning_rate | 4.6e-05 | +| loss | -0.0305 | +| n_updates | 48400 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000295 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1422 | +| iterations | 8147 | +| time_elapsed | 11726 | +| total_timesteps | 16685056 | +| train/ | | +| approx_kl | 0.012211015 | +| clip_fraction | 0.356 | +| clip_range | 0.0708 | +| entropy_loss | -6.79 | +| explained_variance | 0.4 | +| learning_rate | 4.6e-05 | +| loss | -0.0423 | +| n_updates | 48404 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000112 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1422 | +| iterations | 8148 | +| time_elapsed | 11727 | +| total_timesteps | 16687104 | +| train/ | | +| approx_kl | 0.011586491 | +| clip_fraction | 0.317 | +| clip_range | 0.0708 | +| entropy_loss | -6.41 | +| explained_variance | 0.658 | +| learning_rate | 4.6e-05 | +| loss | -0.0289 | +| n_updates | 48408 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000134 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1422 | +| iterations | 8149 | +| time_elapsed | 11728 | +| total_timesteps | 16689152 | +| train/ | | +| approx_kl | 0.012790719 | +| clip_fraction | 0.38 | +| clip_range | 0.0708 | +| entropy_loss | -6.7 | +| explained_variance | 0.152 | +| learning_rate | 4.6e-05 | +| loss | -0.0386 | +| n_updates | 48412 | +| policy_gradient_loss | -0.0248 | +| value_loss | 5.65e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1422 | +| iterations | 8150 | +| time_elapsed | 11730 | +| total_timesteps | 16691200 | +| train/ | | +| approx_kl | 0.011925247 | +| clip_fraction | 0.314 | +| clip_range | 0.0708 | +| entropy_loss | -6.91 | +| explained_variance | 0.284 | +| learning_rate | 4.6e-05 | +| loss | -0.0305 | +| n_updates | 48416 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000268 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1422 | +| iterations | 8151 | +| time_elapsed | 11731 | +| total_timesteps | 16693248 | +| train/ | | +| approx_kl | 0.010464623 | +| clip_fraction | 0.323 | +| clip_range | 0.0708 | +| entropy_loss | -6.89 | +| explained_variance | 0.342 | +| learning_rate | 4.6e-05 | +| loss | -0.0324 | +| n_updates | 48420 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000123 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1422 | +| iterations | 8152 | +| time_elapsed | 11733 | +| total_timesteps | 16695296 | +| train/ | | +| approx_kl | 0.012204203 | +| clip_fraction | 0.324 | +| clip_range | 0.0708 | +| entropy_loss | -7.05 | +| explained_variance | 0.0981 | +| learning_rate | 4.6e-05 | +| loss | -0.0316 | +| n_updates | 48424 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000155 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1422 | +| iterations | 8153 | +| time_elapsed | 11734 | +| total_timesteps | 16697344 | +| train/ | | +| approx_kl | 0.010561085 | +| clip_fraction | 0.327 | +| clip_range | 0.0708 | +| entropy_loss | -7.25 | +| explained_variance | 0.325 | +| learning_rate | 4.6e-05 | +| loss | -0.0337 | +| n_updates | 48428 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000107 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1422 | +| iterations | 8154 | +| time_elapsed | 11736 | +| total_timesteps | 16699392 | +| train/ | | +| approx_kl | 0.011838699 | +| clip_fraction | 0.33 | +| clip_range | 0.0708 | +| entropy_loss | -7.05 | +| explained_variance | 0.42 | +| learning_rate | 4.6e-05 | +| loss | -0.0416 | +| n_updates | 48432 | +| policy_gradient_loss | -0.0221 | +| value_loss | 0.000109 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1422 | +| iterations | 8155 | +| time_elapsed | 11737 | +| total_timesteps | 16701440 | +| train/ | | +| approx_kl | 0.013844544 | +| clip_fraction | 0.336 | +| clip_range | 0.0708 | +| entropy_loss | -6.42 | +| explained_variance | 0.697 | +| learning_rate | 4.6e-05 | +| loss | -0.0302 | +| n_updates | 48436 | +| policy_gradient_loss | -0.0188 | +| value_loss | 8.59e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1422 | +| iterations | 8156 | +| time_elapsed | 11738 | +| total_timesteps | 16703488 | +| train/ | | +| approx_kl | 0.010109516 | +| clip_fraction | 0.31 | +| clip_range | 0.0708 | +| entropy_loss | -6.25 | +| explained_variance | 0.642 | +| learning_rate | 4.6e-05 | +| loss | -0.0293 | +| n_updates | 48440 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000167 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1422 | +| iterations | 8157 | +| time_elapsed | 11740 | +| total_timesteps | 16705536 | +| train/ | | +| approx_kl | 0.0121406 | +| clip_fraction | 0.311 | +| clip_range | 0.0708 | +| entropy_loss | -6.2 | +| explained_variance | 0.566 | +| learning_rate | 4.6e-05 | +| loss | -0.0273 | +| n_updates | 48444 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000169 | +--------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1422 | +| iterations | 8158 | +| time_elapsed | 11741 | +| total_timesteps | 16707584 | +| train/ | | +| approx_kl | 0.01165891 | +| clip_fraction | 0.33 | +| clip_range | 0.0708 | +| entropy_loss | -6.69 | +| explained_variance | 0.554 | +| learning_rate | 4.6e-05 | +| loss | -0.0335 | +| n_updates | 48448 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000102 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1422 | +| iterations | 8159 | +| time_elapsed | 11743 | +| total_timesteps | 16709632 | +| train/ | | +| approx_kl | 0.008152457 | +| clip_fraction | 0.278 | +| clip_range | 0.0708 | +| entropy_loss | -7.36 | +| explained_variance | 0.122 | +| learning_rate | 4.6e-05 | +| loss | -0.0264 | +| n_updates | 48452 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000328 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1422 | +| iterations | 8160 | +| time_elapsed | 11744 | +| total_timesteps | 16711680 | +| train/ | | +| approx_kl | 0.011305183 | +| clip_fraction | 0.356 | +| clip_range | 0.0708 | +| entropy_loss | -7.13 | +| explained_variance | 0.289 | +| learning_rate | 4.6e-05 | +| loss | -0.0371 | +| n_updates | 48456 | +| policy_gradient_loss | -0.0222 | +| value_loss | 0.000151 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1422 | +| iterations | 8161 | +| time_elapsed | 11746 | +| total_timesteps | 16713728 | +| train/ | | +| approx_kl | 0.010957163 | +| clip_fraction | 0.312 | +| clip_range | 0.0708 | +| entropy_loss | -6.93 | +| explained_variance | 0.369 | +| learning_rate | 4.6e-05 | +| loss | -0.0274 | +| n_updates | 48460 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000223 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1422 | +| iterations | 8162 | +| time_elapsed | 11747 | +| total_timesteps | 16715776 | +| train/ | | +| approx_kl | 0.012750479 | +| clip_fraction | 0.349 | +| clip_range | 0.0708 | +| entropy_loss | -6.78 | +| explained_variance | -0.837 | +| learning_rate | 4.6e-05 | +| loss | -0.0358 | +| n_updates | 48464 | +| policy_gradient_loss | -0.0233 | +| value_loss | 0.000109 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1422 | +| iterations | 8163 | +| time_elapsed | 11749 | +| total_timesteps | 16717824 | +| train/ | | +| approx_kl | 0.013300607 | +| clip_fraction | 0.336 | +| clip_range | 0.0708 | +| entropy_loss | -6.57 | +| explained_variance | 0.22 | +| learning_rate | 4.6e-05 | +| loss | -0.028 | +| n_updates | 48468 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000156 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1422 | +| iterations | 8164 | +| time_elapsed | 11750 | +| total_timesteps | 16719872 | +| train/ | | +| approx_kl | 0.012069725 | +| clip_fraction | 0.323 | +| clip_range | 0.0708 | +| entropy_loss | -6.74 | +| explained_variance | 0.357 | +| learning_rate | 4.6e-05 | +| loss | -0.0328 | +| n_updates | 48472 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000207 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1422 | +| iterations | 8165 | +| time_elapsed | 11752 | +| total_timesteps | 16721920 | +| train/ | | +| approx_kl | 0.0134876 | +| clip_fraction | 0.339 | +| clip_range | 0.0708 | +| entropy_loss | -6.55 | +| explained_variance | 0.509 | +| learning_rate | 4.6e-05 | +| loss | -0.0325 | +| n_updates | 48476 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000211 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1422 | +| iterations | 8166 | +| time_elapsed | 11753 | +| total_timesteps | 16723968 | +| train/ | | +| approx_kl | 0.011203577 | +| clip_fraction | 0.33 | +| clip_range | 0.0708 | +| entropy_loss | -6.91 | +| explained_variance | 0.255 | +| learning_rate | 4.6e-05 | +| loss | -0.0349 | +| n_updates | 48480 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.00022 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1422 | +| iterations | 8167 | +| time_elapsed | 11754 | +| total_timesteps | 16726016 | +| train/ | | +| approx_kl | 0.013260467 | +| clip_fraction | 0.324 | +| clip_range | 0.0708 | +| entropy_loss | -7.26 | +| explained_variance | 0.011 | +| learning_rate | 4.6e-05 | +| loss | -0.0334 | +| n_updates | 48484 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1422 | +| iterations | 8168 | +| time_elapsed | 11756 | +| total_timesteps | 16728064 | +| train/ | | +| approx_kl | 0.010412548 | +| clip_fraction | 0.33 | +| clip_range | 0.0708 | +| entropy_loss | -7.19 | +| explained_variance | 0.0286 | +| learning_rate | 4.6e-05 | +| loss | -0.0274 | +| n_updates | 48488 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000195 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1422 | +| iterations | 8169 | +| time_elapsed | 11757 | +| total_timesteps | 16730112 | +| train/ | | +| approx_kl | 0.010773292 | +| clip_fraction | 0.288 | +| clip_range | 0.0708 | +| entropy_loss | -6.14 | +| explained_variance | 0.472 | +| learning_rate | 4.6e-05 | +| loss | -0.0244 | +| n_updates | 48492 | +| policy_gradient_loss | -0.0138 | +| value_loss | 0.000306 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1422 | +| iterations | 8170 | +| time_elapsed | 11759 | +| total_timesteps | 16732160 | +| train/ | | +| approx_kl | 0.011217533 | +| clip_fraction | 0.316 | +| clip_range | 0.0708 | +| entropy_loss | -6.33 | +| explained_variance | 0.384 | +| learning_rate | 4.6e-05 | +| loss | -0.0292 | +| n_updates | 48496 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000296 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1422 | +| iterations | 8171 | +| time_elapsed | 11760 | +| total_timesteps | 16734208 | +| train/ | | +| approx_kl | 0.012958782 | +| clip_fraction | 0.365 | +| clip_range | 0.0708 | +| entropy_loss | -7.05 | +| explained_variance | -0.293 | +| learning_rate | 4.6e-05 | +| loss | -0.0382 | +| n_updates | 48500 | +| policy_gradient_loss | -0.0253 | +| value_loss | 9.26e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1422 | +| iterations | 8172 | +| time_elapsed | 11762 | +| total_timesteps | 16736256 | +| train/ | | +| approx_kl | 0.011258379 | +| clip_fraction | 0.342 | +| clip_range | 0.0708 | +| entropy_loss | -6.98 | +| explained_variance | 0.348 | +| learning_rate | 4.6e-05 | +| loss | -0.032 | +| n_updates | 48504 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.00021 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.306 | +| time/ | | +| fps | 1422 | +| iterations | 8173 | +| time_elapsed | 11763 | +| total_timesteps | 16738304 | +| train/ | | +| approx_kl | 0.0113101695 | +| clip_fraction | 0.322 | +| clip_range | 0.0708 | +| entropy_loss | -6.95 | +| explained_variance | 0.388 | +| learning_rate | 4.6e-05 | +| loss | -0.0308 | +| n_updates | 48508 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000208 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1422 | +| iterations | 8174 | +| time_elapsed | 11764 | +| total_timesteps | 16740352 | +| train/ | | +| approx_kl | 0.009619501 | +| clip_fraction | 0.307 | +| clip_range | 0.0708 | +| entropy_loss | -6.2 | +| explained_variance | 0.576 | +| learning_rate | 4.6e-05 | +| loss | -0.0319 | +| n_updates | 48512 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000251 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1422 | +| iterations | 8175 | +| time_elapsed | 11766 | +| total_timesteps | 16742400 | +| train/ | | +| approx_kl | 0.010338862 | +| clip_fraction | 0.333 | +| clip_range | 0.0708 | +| entropy_loss | -6.73 | +| explained_variance | 0.643 | +| learning_rate | 4.6e-05 | +| loss | -0.0293 | +| n_updates | 48516 | +| policy_gradient_loss | -0.0212 | +| value_loss | 8.07e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1422 | +| iterations | 8176 | +| time_elapsed | 11767 | +| total_timesteps | 16744448 | +| train/ | | +| approx_kl | 0.013053808 | +| clip_fraction | 0.342 | +| clip_range | 0.0708 | +| entropy_loss | -6.61 | +| explained_variance | 0.582 | +| learning_rate | 4.6e-05 | +| loss | -0.0306 | +| n_updates | 48520 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000101 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.315 | +| time/ | | +| fps | 1422 | +| iterations | 8177 | +| time_elapsed | 11769 | +| total_timesteps | 16746496 | +| train/ | | +| approx_kl | 0.010410156 | +| clip_fraction | 0.33 | +| clip_range | 0.0708 | +| entropy_loss | -6.78 | +| explained_variance | 0.222 | +| learning_rate | 4.6e-05 | +| loss | -0.0223 | +| n_updates | 48524 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000319 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1422 | +| iterations | 8178 | +| time_elapsed | 11770 | +| total_timesteps | 16748544 | +| train/ | | +| approx_kl | 0.010918487 | +| clip_fraction | 0.338 | +| clip_range | 0.0708 | +| entropy_loss | -6.86 | +| explained_variance | 0.546 | +| learning_rate | 4.6e-05 | +| loss | -0.0234 | +| n_updates | 48528 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000154 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1422 | +| iterations | 8179 | +| time_elapsed | 11772 | +| total_timesteps | 16750592 | +| train/ | | +| approx_kl | 0.009732277 | +| clip_fraction | 0.307 | +| clip_range | 0.0708 | +| entropy_loss | -7.09 | +| explained_variance | 0.0267 | +| learning_rate | 4.6e-05 | +| loss | -0.0313 | +| n_updates | 48532 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000241 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1422 | +| iterations | 8180 | +| time_elapsed | 11773 | +| total_timesteps | 16752640 | +| train/ | | +| approx_kl | 0.009852802 | +| clip_fraction | 0.309 | +| clip_range | 0.0708 | +| entropy_loss | -6.73 | +| explained_variance | 0.375 | +| learning_rate | 4.6e-05 | +| loss | -0.0321 | +| n_updates | 48536 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000233 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1422 | +| iterations | 8181 | +| time_elapsed | 11775 | +| total_timesteps | 16754688 | +| train/ | | +| approx_kl | 0.011472145 | +| clip_fraction | 0.33 | +| clip_range | 0.0708 | +| entropy_loss | -6.89 | +| explained_variance | 0.31 | +| learning_rate | 4.6e-05 | +| loss | -0.0271 | +| n_updates | 48540 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000181 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1422 | +| iterations | 8182 | +| time_elapsed | 11776 | +| total_timesteps | 16756736 | +| train/ | | +| approx_kl | 0.013215004 | +| clip_fraction | 0.358 | +| clip_range | 0.0708 | +| entropy_loss | -6.59 | +| explained_variance | 0.646 | +| learning_rate | 4.6e-05 | +| loss | -0.0334 | +| n_updates | 48544 | +| policy_gradient_loss | -0.0233 | +| value_loss | 9.98e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1422 | +| iterations | 8183 | +| time_elapsed | 11777 | +| total_timesteps | 16758784 | +| train/ | | +| approx_kl | 0.011129946 | +| clip_fraction | 0.328 | +| clip_range | 0.0708 | +| entropy_loss | -7.05 | +| explained_variance | 0.0901 | +| learning_rate | 4.6e-05 | +| loss | -0.0316 | +| n_updates | 48548 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000196 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1422 | +| iterations | 8184 | +| time_elapsed | 11779 | +| total_timesteps | 16760832 | +| train/ | | +| approx_kl | 0.009422574 | +| clip_fraction | 0.293 | +| clip_range | 0.0708 | +| entropy_loss | -7.18 | +| explained_variance | 0.191 | +| learning_rate | 4.6e-05 | +| loss | -0.0312 | +| n_updates | 48552 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000201 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1422 | +| iterations | 8185 | +| time_elapsed | 11780 | +| total_timesteps | 16762880 | +| train/ | | +| approx_kl | 0.011182875 | +| clip_fraction | 0.324 | +| clip_range | 0.0708 | +| entropy_loss | -6.67 | +| explained_variance | 0.712 | +| learning_rate | 4.6e-05 | +| loss | -0.034 | +| n_updates | 48556 | +| policy_gradient_loss | -0.0195 | +| value_loss | 8.95e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1422 | +| iterations | 8186 | +| time_elapsed | 11782 | +| total_timesteps | 16764928 | +| train/ | | +| approx_kl | 0.0081837885 | +| clip_fraction | 0.289 | +| clip_range | 0.0708 | +| entropy_loss | -6.78 | +| explained_variance | 0.282 | +| learning_rate | 4.6e-05 | +| loss | -0.0279 | +| n_updates | 48560 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000215 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1422 | +| iterations | 8187 | +| time_elapsed | 11783 | +| total_timesteps | 16766976 | +| train/ | | +| approx_kl | 0.0105337445 | +| clip_fraction | 0.304 | +| clip_range | 0.0708 | +| entropy_loss | -6.63 | +| explained_variance | 0.598 | +| learning_rate | 4.6e-05 | +| loss | -0.0302 | +| n_updates | 48564 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000143 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1422 | +| iterations | 8188 | +| time_elapsed | 11785 | +| total_timesteps | 16769024 | +| train/ | | +| approx_kl | 0.012233881 | +| clip_fraction | 0.338 | +| clip_range | 0.0708 | +| entropy_loss | -7.05 | +| explained_variance | -0.101 | +| learning_rate | 4.6e-05 | +| loss | -0.035 | +| n_updates | 48568 | +| policy_gradient_loss | -0.0213 | +| value_loss | 9.58e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1422 | +| iterations | 8189 | +| time_elapsed | 11786 | +| total_timesteps | 16771072 | +| train/ | | +| approx_kl | 0.010182057 | +| clip_fraction | 0.291 | +| clip_range | 0.0708 | +| entropy_loss | -6.7 | +| explained_variance | 0.569 | +| learning_rate | 4.6e-05 | +| loss | -0.0252 | +| n_updates | 48572 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000109 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1422 | +| iterations | 8190 | +| time_elapsed | 11788 | +| total_timesteps | 16773120 | +| train/ | | +| approx_kl | 0.00934183 | +| clip_fraction | 0.328 | +| clip_range | 0.0708 | +| entropy_loss | -6.7 | +| explained_variance | 0.533 | +| learning_rate | 4.6e-05 | +| loss | -0.0283 | +| n_updates | 48576 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000208 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1422 | +| iterations | 8191 | +| time_elapsed | 11789 | +| total_timesteps | 16775168 | +| train/ | | +| approx_kl | 0.009935855 | +| clip_fraction | 0.299 | +| clip_range | 0.0708 | +| entropy_loss | -6.49 | +| explained_variance | 0.524 | +| learning_rate | 4.6e-05 | +| loss | -0.0243 | +| n_updates | 48580 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000258 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1422 | +| iterations | 8192 | +| time_elapsed | 11790 | +| total_timesteps | 16777216 | +| train/ | | +| approx_kl | 0.010760639 | +| clip_fraction | 0.322 | +| clip_range | 0.0708 | +| entropy_loss | -6.71 | +| explained_variance | 0.541 | +| learning_rate | 4.6e-05 | +| loss | -0.0324 | +| n_updates | 48584 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.0001 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1422 | +| iterations | 8193 | +| time_elapsed | 11792 | +| total_timesteps | 16779264 | +| train/ | | +| approx_kl | 0.014106159 | +| clip_fraction | 0.373 | +| clip_range | 0.0708 | +| entropy_loss | -6.88 | +| explained_variance | -0.281 | +| learning_rate | 4.6e-05 | +| loss | -0.0395 | +| n_updates | 48588 | +| policy_gradient_loss | -0.0236 | +| value_loss | 7.04e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1422 | +| iterations | 8194 | +| time_elapsed | 11793 | +| total_timesteps | 16781312 | +| train/ | | +| approx_kl | 0.012214169 | +| clip_fraction | 0.331 | +| clip_range | 0.0708 | +| entropy_loss | -6.78 | +| explained_variance | 0.563 | +| learning_rate | 4.6e-05 | +| loss | -0.0387 | +| n_updates | 48592 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000102 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.306 | +| time/ | | +| fps | 1422 | +| iterations | 8195 | +| time_elapsed | 11795 | +| total_timesteps | 16783360 | +| train/ | | +| approx_kl | 0.01292849 | +| clip_fraction | 0.295 | +| clip_range | 0.0708 | +| entropy_loss | -7.32 | +| explained_variance | -0.0321 | +| learning_rate | 4.6e-05 | +| loss | -0.0296 | +| n_updates | 48596 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000111 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.306 | +| time/ | | +| fps | 1422 | +| iterations | 8196 | +| time_elapsed | 11796 | +| total_timesteps | 16785408 | +| train/ | | +| approx_kl | 0.009258321 | +| clip_fraction | 0.303 | +| clip_range | 0.0708 | +| entropy_loss | -6.63 | +| explained_variance | 0.512 | +| learning_rate | 4.6e-05 | +| loss | -0.0292 | +| n_updates | 48600 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000139 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.304 | +| time/ | | +| fps | 1422 | +| iterations | 8197 | +| time_elapsed | 11798 | +| total_timesteps | 16787456 | +| train/ | | +| approx_kl | 0.012595363 | +| clip_fraction | 0.314 | +| clip_range | 0.0708 | +| entropy_loss | -6.4 | +| explained_variance | 0.637 | +| learning_rate | 4.6e-05 | +| loss | -0.0338 | +| n_updates | 48604 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000114 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.306 | +| time/ | | +| fps | 1422 | +| iterations | 8198 | +| time_elapsed | 11799 | +| total_timesteps | 16789504 | +| train/ | | +| approx_kl | 0.011648381 | +| clip_fraction | 0.326 | +| clip_range | 0.0708 | +| entropy_loss | -7 | +| explained_variance | 0.4 | +| learning_rate | 4.6e-05 | +| loss | -0.0329 | +| n_updates | 48608 | +| policy_gradient_loss | -0.0185 | +| value_loss | 9.18e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 1422 | +| iterations | 8199 | +| time_elapsed | 11800 | +| total_timesteps | 16791552 | +| train/ | | +| approx_kl | 0.009459103 | +| clip_fraction | 0.287 | +| clip_range | 0.0708 | +| entropy_loss | -6.83 | +| explained_variance | 0.531 | +| learning_rate | 4.6e-05 | +| loss | -0.0302 | +| n_updates | 48612 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.00019 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 1422 | +| iterations | 8200 | +| time_elapsed | 11802 | +| total_timesteps | 16793600 | +| train/ | | +| approx_kl | 0.010828736 | +| clip_fraction | 0.329 | +| clip_range | 0.0708 | +| entropy_loss | -6.77 | +| explained_variance | 0.663 | +| learning_rate | 4.6e-05 | +| loss | -0.0349 | +| n_updates | 48616 | +| policy_gradient_loss | -0.0217 | +| value_loss | 8.31e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1422 | +| iterations | 8201 | +| time_elapsed | 11803 | +| total_timesteps | 16795648 | +| train/ | | +| approx_kl | 0.0093692625 | +| clip_fraction | 0.312 | +| clip_range | 0.0708 | +| entropy_loss | -6.82 | +| explained_variance | 0.554 | +| learning_rate | 4.6e-05 | +| loss | -0.0285 | +| n_updates | 48620 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000115 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1422 | +| iterations | 8202 | +| time_elapsed | 11805 | +| total_timesteps | 16797696 | +| train/ | | +| approx_kl | 0.011084512 | +| clip_fraction | 0.314 | +| clip_range | 0.0708 | +| entropy_loss | -7.14 | +| explained_variance | 0.0353 | +| learning_rate | 4.6e-05 | +| loss | -0.024 | +| n_updates | 48624 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000263 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1422 | +| iterations | 8203 | +| time_elapsed | 11806 | +| total_timesteps | 16799744 | +| train/ | | +| approx_kl | 0.009538177 | +| clip_fraction | 0.302 | +| clip_range | 0.0708 | +| entropy_loss | -6.87 | +| explained_variance | 0.15 | +| learning_rate | 4.6e-05 | +| loss | -0.0285 | +| n_updates | 48628 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000268 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1422 | +| iterations | 8204 | +| time_elapsed | 11808 | +| total_timesteps | 16801792 | +| train/ | | +| approx_kl | 0.0145613 | +| clip_fraction | 0.37 | +| clip_range | 0.0708 | +| entropy_loss | -6.98 | +| explained_variance | 0.217 | +| learning_rate | 4.6e-05 | +| loss | -0.0354 | +| n_updates | 48632 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000196 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1422 | +| iterations | 8205 | +| time_elapsed | 11809 | +| total_timesteps | 16803840 | +| train/ | | +| approx_kl | 0.011231091 | +| clip_fraction | 0.33 | +| clip_range | 0.0708 | +| entropy_loss | -7.03 | +| explained_variance | 0.254 | +| learning_rate | 4.6e-05 | +| loss | -0.03 | +| n_updates | 48636 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000169 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1422 | +| iterations | 8206 | +| time_elapsed | 11811 | +| total_timesteps | 16805888 | +| train/ | | +| approx_kl | 0.010907028 | +| clip_fraction | 0.292 | +| clip_range | 0.0708 | +| entropy_loss | -6.91 | +| explained_variance | 0.317 | +| learning_rate | 4.6e-05 | +| loss | -0.0265 | +| n_updates | 48640 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000276 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1422 | +| iterations | 8207 | +| time_elapsed | 11812 | +| total_timesteps | 16807936 | +| train/ | | +| approx_kl | 0.0115018925 | +| clip_fraction | 0.319 | +| clip_range | 0.0708 | +| entropy_loss | -6.73 | +| explained_variance | 0.461 | +| learning_rate | 4.6e-05 | +| loss | -0.0377 | +| n_updates | 48644 | +| policy_gradient_loss | -0.022 | +| value_loss | 0.000127 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1422 | +| iterations | 8208 | +| time_elapsed | 11813 | +| total_timesteps | 16809984 | +| train/ | | +| approx_kl | 0.011952003 | +| clip_fraction | 0.338 | +| clip_range | 0.0708 | +| entropy_loss | -6.77 | +| explained_variance | 0.265 | +| learning_rate | 4.6e-05 | +| loss | -0.0323 | +| n_updates | 48648 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000157 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1422 | +| iterations | 8209 | +| time_elapsed | 11815 | +| total_timesteps | 16812032 | +| train/ | | +| approx_kl | 0.012280719 | +| clip_fraction | 0.338 | +| clip_range | 0.0708 | +| entropy_loss | -6.9 | +| explained_variance | 0.361 | +| learning_rate | 4.6e-05 | +| loss | -0.0351 | +| n_updates | 48652 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000111 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1422 | +| iterations | 8210 | +| time_elapsed | 11816 | +| total_timesteps | 16814080 | +| train/ | | +| approx_kl | 0.012470742 | +| clip_fraction | 0.296 | +| clip_range | 0.0708 | +| entropy_loss | -6.85 | +| explained_variance | 0.0756 | +| learning_rate | 4.6e-05 | +| loss | -0.023 | +| n_updates | 48656 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000282 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1422 | +| iterations | 8211 | +| time_elapsed | 11818 | +| total_timesteps | 16816128 | +| train/ | | +| approx_kl | 0.013377007 | +| clip_fraction | 0.345 | +| clip_range | 0.0708 | +| entropy_loss | -6.44 | +| explained_variance | 0.418 | +| learning_rate | 4.6e-05 | +| loss | -0.0338 | +| n_updates | 48660 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000143 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1422 | +| iterations | 8212 | +| time_elapsed | 11819 | +| total_timesteps | 16818176 | +| train/ | | +| approx_kl | 0.012085864 | +| clip_fraction | 0.324 | +| clip_range | 0.0708 | +| entropy_loss | -6.85 | +| explained_variance | 0.447 | +| learning_rate | 4.6e-05 | +| loss | -0.0307 | +| n_updates | 48664 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000135 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1422 | +| iterations | 8213 | +| time_elapsed | 11821 | +| total_timesteps | 16820224 | +| train/ | | +| approx_kl | 0.012278188 | +| clip_fraction | 0.343 | +| clip_range | 0.0708 | +| entropy_loss | -7.17 | +| explained_variance | 0.0199 | +| learning_rate | 4.6e-05 | +| loss | -0.0302 | +| n_updates | 48668 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000142 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1422 | +| iterations | 8214 | +| time_elapsed | 11822 | +| total_timesteps | 16822272 | +| train/ | | +| approx_kl | 0.010529395 | +| clip_fraction | 0.316 | +| clip_range | 0.0708 | +| entropy_loss | -7.06 | +| explained_variance | 0.276 | +| learning_rate | 4.6e-05 | +| loss | -0.0306 | +| n_updates | 48672 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000186 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1422 | +| iterations | 8215 | +| time_elapsed | 11824 | +| total_timesteps | 16824320 | +| train/ | | +| approx_kl | 0.00914294 | +| clip_fraction | 0.314 | +| clip_range | 0.0708 | +| entropy_loss | -6.86 | +| explained_variance | 0.311 | +| learning_rate | 4.6e-05 | +| loss | -0.024 | +| n_updates | 48676 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.00029 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1422 | +| iterations | 8216 | +| time_elapsed | 11825 | +| total_timesteps | 16826368 | +| train/ | | +| approx_kl | 0.011908809 | +| clip_fraction | 0.344 | +| clip_range | 0.0708 | +| entropy_loss | -6.77 | +| explained_variance | -0.516 | +| learning_rate | 4.6e-05 | +| loss | -0.0272 | +| n_updates | 48680 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000133 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1422 | +| iterations | 8217 | +| time_elapsed | 11826 | +| total_timesteps | 16828416 | +| train/ | | +| approx_kl | 0.012411292 | +| clip_fraction | 0.325 | +| clip_range | 0.0708 | +| entropy_loss | -7.32 | +| explained_variance | -0.0832 | +| learning_rate | 4.6e-05 | +| loss | -0.0352 | +| n_updates | 48684 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000126 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1422 | +| iterations | 8218 | +| time_elapsed | 11828 | +| total_timesteps | 16830464 | +| train/ | | +| approx_kl | 0.013114808 | +| clip_fraction | 0.318 | +| clip_range | 0.0708 | +| entropy_loss | -6.83 | +| explained_variance | 0.157 | +| learning_rate | 4.6e-05 | +| loss | -0.0336 | +| n_updates | 48688 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000353 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1422 | +| iterations | 8219 | +| time_elapsed | 11829 | +| total_timesteps | 16832512 | +| train/ | | +| approx_kl | 0.011548072 | +| clip_fraction | 0.344 | +| clip_range | 0.0708 | +| entropy_loss | -6.14 | +| explained_variance | 0.541 | +| learning_rate | 4.6e-05 | +| loss | -0.0303 | +| n_updates | 48692 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000153 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1422 | +| iterations | 8220 | +| time_elapsed | 11831 | +| total_timesteps | 16834560 | +| train/ | | +| approx_kl | 0.014847668 | +| clip_fraction | 0.377 | +| clip_range | 0.0708 | +| entropy_loss | -6.96 | +| explained_variance | -0.0395 | +| learning_rate | 4.6e-05 | +| loss | -0.0379 | +| n_updates | 48696 | +| policy_gradient_loss | -0.0227 | +| value_loss | 0.000121 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1422 | +| iterations | 8221 | +| time_elapsed | 11832 | +| total_timesteps | 16836608 | +| train/ | | +| approx_kl | 0.012455106 | +| clip_fraction | 0.359 | +| clip_range | 0.0708 | +| entropy_loss | -7.29 | +| explained_variance | -0.131 | +| learning_rate | 4.6e-05 | +| loss | -0.035 | +| n_updates | 48700 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000173 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1422 | +| iterations | 8222 | +| time_elapsed | 11834 | +| total_timesteps | 16838656 | +| train/ | | +| approx_kl | 0.0110252 | +| clip_fraction | 0.327 | +| clip_range | 0.0708 | +| entropy_loss | -6.57 | +| explained_variance | 0.349 | +| learning_rate | 4.6e-05 | +| loss | -0.0331 | +| n_updates | 48704 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000192 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1422 | +| iterations | 8223 | +| time_elapsed | 11835 | +| total_timesteps | 16840704 | +| train/ | | +| approx_kl | 0.012268145 | +| clip_fraction | 0.337 | +| clip_range | 0.0708 | +| entropy_loss | -6.92 | +| explained_variance | 0.149 | +| learning_rate | 4.6e-05 | +| loss | -0.0285 | +| n_updates | 48708 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000207 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1422 | +| iterations | 8224 | +| time_elapsed | 11837 | +| total_timesteps | 16842752 | +| train/ | | +| approx_kl | 0.011125352 | +| clip_fraction | 0.323 | +| clip_range | 0.0708 | +| entropy_loss | -6.68 | +| explained_variance | 0.332 | +| learning_rate | 4.6e-05 | +| loss | -0.0265 | +| n_updates | 48712 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000291 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1422 | +| iterations | 8225 | +| time_elapsed | 11838 | +| total_timesteps | 16844800 | +| train/ | | +| approx_kl | 0.012307752 | +| clip_fraction | 0.352 | +| clip_range | 0.0708 | +| entropy_loss | -6.62 | +| explained_variance | 0.601 | +| learning_rate | 4.6e-05 | +| loss | -0.0383 | +| n_updates | 48716 | +| policy_gradient_loss | -0.0249 | +| value_loss | 7.95e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1422 | +| iterations | 8226 | +| time_elapsed | 11839 | +| total_timesteps | 16846848 | +| train/ | | +| approx_kl | 0.0120291915 | +| clip_fraction | 0.356 | +| clip_range | 0.0708 | +| entropy_loss | -6.58 | +| explained_variance | 0.725 | +| learning_rate | 4.6e-05 | +| loss | -0.0388 | +| n_updates | 48720 | +| policy_gradient_loss | -0.0239 | +| value_loss | 6.65e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1422 | +| iterations | 8227 | +| time_elapsed | 11841 | +| total_timesteps | 16848896 | +| train/ | | +| approx_kl | 0.015513202 | +| clip_fraction | 0.339 | +| clip_range | 0.0708 | +| entropy_loss | -6.81 | +| explained_variance | 0.218 | +| learning_rate | 4.6e-05 | +| loss | -0.0359 | +| n_updates | 48724 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.00011 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1422 | +| iterations | 8228 | +| time_elapsed | 11842 | +| total_timesteps | 16850944 | +| train/ | | +| approx_kl | 0.012513932 | +| clip_fraction | 0.332 | +| clip_range | 0.0708 | +| entropy_loss | -6.85 | +| explained_variance | 0.461 | +| learning_rate | 4.6e-05 | +| loss | -0.0305 | +| n_updates | 48728 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000178 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1422 | +| iterations | 8229 | +| time_elapsed | 11844 | +| total_timesteps | 16852992 | +| train/ | | +| approx_kl | 0.013597608 | +| clip_fraction | 0.333 | +| clip_range | 0.0708 | +| entropy_loss | -6.48 | +| explained_variance | 0.607 | +| learning_rate | 4.6e-05 | +| loss | -0.0368 | +| n_updates | 48732 | +| policy_gradient_loss | -0.0203 | +| value_loss | 8.87e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1422 | +| iterations | 8230 | +| time_elapsed | 11845 | +| total_timesteps | 16855040 | +| train/ | | +| approx_kl | 0.01120808 | +| clip_fraction | 0.319 | +| clip_range | 0.0708 | +| entropy_loss | -6.83 | +| explained_variance | 0.417 | +| learning_rate | 4.6e-05 | +| loss | -0.0314 | +| n_updates | 48736 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000207 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1422 | +| iterations | 8231 | +| time_elapsed | 11847 | +| total_timesteps | 16857088 | +| train/ | | +| approx_kl | 0.013059717 | +| clip_fraction | 0.352 | +| clip_range | 0.0708 | +| entropy_loss | -6.76 | +| explained_variance | 0.603 | +| learning_rate | 4.6e-05 | +| loss | -0.0369 | +| n_updates | 48740 | +| policy_gradient_loss | -0.0231 | +| value_loss | 8.06e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1422 | +| iterations | 8232 | +| time_elapsed | 11848 | +| total_timesteps | 16859136 | +| train/ | | +| approx_kl | 0.010945238 | +| clip_fraction | 0.33 | +| clip_range | 0.0708 | +| entropy_loss | -6.91 | +| explained_variance | 0.0388 | +| learning_rate | 4.6e-05 | +| loss | -0.0325 | +| n_updates | 48744 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000121 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1422 | +| iterations | 8233 | +| time_elapsed | 11849 | +| total_timesteps | 16861184 | +| train/ | | +| approx_kl | 0.014080066 | +| clip_fraction | 0.358 | +| clip_range | 0.0708 | +| entropy_loss | -7.2 | +| explained_variance | -0.129 | +| learning_rate | 4.6e-05 | +| loss | -0.0273 | +| n_updates | 48748 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000156 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1422 | +| iterations | 8234 | +| time_elapsed | 11851 | +| total_timesteps | 16863232 | +| train/ | | +| approx_kl | 0.011966107 | +| clip_fraction | 0.306 | +| clip_range | 0.0708 | +| entropy_loss | -6.54 | +| explained_variance | 0.506 | +| learning_rate | 4.6e-05 | +| loss | -0.0251 | +| n_updates | 48752 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000215 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1422 | +| iterations | 8235 | +| time_elapsed | 11852 | +| total_timesteps | 16865280 | +| train/ | | +| approx_kl | 0.0107024815 | +| clip_fraction | 0.309 | +| clip_range | 0.0708 | +| entropy_loss | -6.3 | +| explained_variance | 0.399 | +| learning_rate | 4.6e-05 | +| loss | -0.0264 | +| n_updates | 48756 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000367 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1422 | +| iterations | 8236 | +| time_elapsed | 11854 | +| total_timesteps | 16867328 | +| train/ | | +| approx_kl | 0.010803189 | +| clip_fraction | 0.328 | +| clip_range | 0.0708 | +| entropy_loss | -6.77 | +| explained_variance | 0.248 | +| learning_rate | 4.6e-05 | +| loss | -0.0267 | +| n_updates | 48760 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000196 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1422 | +| iterations | 8237 | +| time_elapsed | 11855 | +| total_timesteps | 16869376 | +| train/ | | +| approx_kl | 0.012303798 | +| clip_fraction | 0.343 | +| clip_range | 0.0708 | +| entropy_loss | -6.88 | +| explained_variance | 0.335 | +| learning_rate | 4.6e-05 | +| loss | -0.0291 | +| n_updates | 48764 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000187 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1422 | +| iterations | 8238 | +| time_elapsed | 11856 | +| total_timesteps | 16871424 | +| train/ | | +| approx_kl | 0.013366264 | +| clip_fraction | 0.372 | +| clip_range | 0.0708 | +| entropy_loss | -6.5 | +| explained_variance | 0.432 | +| learning_rate | 4.6e-05 | +| loss | -0.0325 | +| n_updates | 48768 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.00016 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1422 | +| iterations | 8239 | +| time_elapsed | 11858 | +| total_timesteps | 16873472 | +| train/ | | +| approx_kl | 0.013993034 | +| clip_fraction | 0.342 | +| clip_range | 0.0708 | +| entropy_loss | -6.85 | +| explained_variance | 0.325 | +| learning_rate | 4.6e-05 | +| loss | -0.0297 | +| n_updates | 48772 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000198 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1422 | +| iterations | 8240 | +| time_elapsed | 11859 | +| total_timesteps | 16875520 | +| train/ | | +| approx_kl | 0.011512484 | +| clip_fraction | 0.307 | +| clip_range | 0.0708 | +| entropy_loss | -6.47 | +| explained_variance | 0.478 | +| learning_rate | 4.6e-05 | +| loss | -0.0307 | +| n_updates | 48776 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000283 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1422 | +| iterations | 8241 | +| time_elapsed | 11861 | +| total_timesteps | 16877568 | +| train/ | | +| approx_kl | 0.0110188015 | +| clip_fraction | 0.323 | +| clip_range | 0.0708 | +| entropy_loss | -6.99 | +| explained_variance | -0.00487 | +| learning_rate | 4.6e-05 | +| loss | -0.0309 | +| n_updates | 48780 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000221 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1422 | +| iterations | 8242 | +| time_elapsed | 11862 | +| total_timesteps | 16879616 | +| train/ | | +| approx_kl | 0.00977879 | +| clip_fraction | 0.305 | +| clip_range | 0.0708 | +| entropy_loss | -6.71 | +| explained_variance | 0.249 | +| learning_rate | 4.6e-05 | +| loss | -0.0258 | +| n_updates | 48784 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000453 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1422 | +| iterations | 8243 | +| time_elapsed | 11864 | +| total_timesteps | 16881664 | +| train/ | | +| approx_kl | 0.012591633 | +| clip_fraction | 0.368 | +| clip_range | 0.0708 | +| entropy_loss | -6.75 | +| explained_variance | 0.324 | +| learning_rate | 4.6e-05 | +| loss | -0.0461 | +| n_updates | 48788 | +| policy_gradient_loss | -0.0258 | +| value_loss | 8.49e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1422 | +| iterations | 8244 | +| time_elapsed | 11865 | +| total_timesteps | 16883712 | +| train/ | | +| approx_kl | 0.012637433 | +| clip_fraction | 0.316 | +| clip_range | 0.0708 | +| entropy_loss | -7.09 | +| explained_variance | -0.249 | +| learning_rate | 4.6e-05 | +| loss | -0.0333 | +| n_updates | 48792 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000219 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1422 | +| iterations | 8245 | +| time_elapsed | 11867 | +| total_timesteps | 16885760 | +| train/ | | +| approx_kl | 0.012745993 | +| clip_fraction | 0.343 | +| clip_range | 0.0708 | +| entropy_loss | -6.84 | +| explained_variance | 0.201 | +| learning_rate | 4.6e-05 | +| loss | -0.0328 | +| n_updates | 48796 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000142 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1422 | +| iterations | 8246 | +| time_elapsed | 11868 | +| total_timesteps | 16887808 | +| train/ | | +| approx_kl | 0.010870311 | +| clip_fraction | 0.328 | +| clip_range | 0.0708 | +| entropy_loss | -6.93 | +| explained_variance | 0.46 | +| learning_rate | 4.6e-05 | +| loss | -0.0318 | +| n_updates | 48800 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000145 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1422 | +| iterations | 8247 | +| time_elapsed | 11869 | +| total_timesteps | 16889856 | +| train/ | | +| approx_kl | 0.010728549 | +| clip_fraction | 0.319 | +| clip_range | 0.0708 | +| entropy_loss | -7.1 | +| explained_variance | 0.0797 | +| learning_rate | 4.6e-05 | +| loss | -0.0278 | +| n_updates | 48804 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000143 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1422 | +| iterations | 8248 | +| time_elapsed | 11871 | +| total_timesteps | 16891904 | +| train/ | | +| approx_kl | 0.011462309 | +| clip_fraction | 0.332 | +| clip_range | 0.0708 | +| entropy_loss | -7.04 | +| explained_variance | 0.391 | +| learning_rate | 4.6e-05 | +| loss | -0.0342 | +| n_updates | 48808 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000128 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1422 | +| iterations | 8249 | +| time_elapsed | 11872 | +| total_timesteps | 16893952 | +| train/ | | +| approx_kl | 0.011820843 | +| clip_fraction | 0.329 | +| clip_range | 0.0708 | +| entropy_loss | -7 | +| explained_variance | 0.333 | +| learning_rate | 4.6e-05 | +| loss | -0.033 | +| n_updates | 48812 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000204 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1422 | +| iterations | 8250 | +| time_elapsed | 11874 | +| total_timesteps | 16896000 | +| train/ | | +| approx_kl | 0.0115892785 | +| clip_fraction | 0.333 | +| clip_range | 0.0708 | +| entropy_loss | -6.97 | +| explained_variance | 0.424 | +| learning_rate | 4.6e-05 | +| loss | -0.0262 | +| n_updates | 48816 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000125 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1422 | +| iterations | 8251 | +| time_elapsed | 11875 | +| total_timesteps | 16898048 | +| train/ | | +| approx_kl | 0.010782941 | +| clip_fraction | 0.31 | +| clip_range | 0.0708 | +| entropy_loss | -5.99 | +| explained_variance | 0.38 | +| learning_rate | 4.6e-05 | +| loss | -0.0245 | +| n_updates | 48820 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000484 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1422 | +| iterations | 8252 | +| time_elapsed | 11876 | +| total_timesteps | 16900096 | +| train/ | | +| approx_kl | 0.013452832 | +| clip_fraction | 0.354 | +| clip_range | 0.0708 | +| entropy_loss | -6.67 | +| explained_variance | 0.469 | +| learning_rate | 4.6e-05 | +| loss | -0.0409 | +| n_updates | 48824 | +| policy_gradient_loss | -0.0232 | +| value_loss | 0.000126 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1422 | +| iterations | 8253 | +| time_elapsed | 11878 | +| total_timesteps | 16902144 | +| train/ | | +| approx_kl | 0.011436434 | +| clip_fraction | 0.32 | +| clip_range | 0.0708 | +| entropy_loss | -6.25 | +| explained_variance | 0.397 | +| learning_rate | 4.6e-05 | +| loss | -0.0294 | +| n_updates | 48828 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000413 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1422 | +| iterations | 8254 | +| time_elapsed | 11879 | +| total_timesteps | 16904192 | +| train/ | | +| approx_kl | 0.00971408 | +| clip_fraction | 0.346 | +| clip_range | 0.0708 | +| entropy_loss | -6.68 | +| explained_variance | 0.249 | +| learning_rate | 4.6e-05 | +| loss | -0.0342 | +| n_updates | 48832 | +| policy_gradient_loss | -0.0222 | +| value_loss | 0.000134 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1422 | +| iterations | 8255 | +| time_elapsed | 11881 | +| total_timesteps | 16906240 | +| train/ | | +| approx_kl | 0.011636435 | +| clip_fraction | 0.349 | +| clip_range | 0.0708 | +| entropy_loss | -7.22 | +| explained_variance | -0.267 | +| learning_rate | 4.6e-05 | +| loss | -0.0446 | +| n_updates | 48836 | +| policy_gradient_loss | -0.023 | +| value_loss | 8.73e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1422 | +| iterations | 8256 | +| time_elapsed | 11882 | +| total_timesteps | 16908288 | +| train/ | | +| approx_kl | 0.010685287 | +| clip_fraction | 0.318 | +| clip_range | 0.0708 | +| entropy_loss | -7.25 | +| explained_variance | -0.0513 | +| learning_rate | 4.6e-05 | +| loss | -0.0324 | +| n_updates | 48840 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.00022 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1422 | +| iterations | 8257 | +| time_elapsed | 11884 | +| total_timesteps | 16910336 | +| train/ | | +| approx_kl | 0.011003038 | +| clip_fraction | 0.341 | +| clip_range | 0.0708 | +| entropy_loss | -7.03 | +| explained_variance | 0.213 | +| learning_rate | 4.6e-05 | +| loss | -0.0347 | +| n_updates | 48844 | +| policy_gradient_loss | -0.0221 | +| value_loss | 0.000122 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1422 | +| iterations | 8258 | +| time_elapsed | 11885 | +| total_timesteps | 16912384 | +| train/ | | +| approx_kl | 0.011842537 | +| clip_fraction | 0.333 | +| clip_range | 0.0708 | +| entropy_loss | -6.46 | +| explained_variance | 0.189 | +| learning_rate | 4.6e-05 | +| loss | -0.0294 | +| n_updates | 48848 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000508 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1422 | +| iterations | 8259 | +| time_elapsed | 11886 | +| total_timesteps | 16914432 | +| train/ | | +| approx_kl | 0.013745189 | +| clip_fraction | 0.377 | +| clip_range | 0.0708 | +| entropy_loss | -6.67 | +| explained_variance | 0.144 | +| learning_rate | 4.6e-05 | +| loss | -0.0421 | +| n_updates | 48852 | +| policy_gradient_loss | -0.0244 | +| value_loss | 0.00014 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1422 | +| iterations | 8260 | +| time_elapsed | 11888 | +| total_timesteps | 16916480 | +| train/ | | +| approx_kl | 0.01202547 | +| clip_fraction | 0.34 | +| clip_range | 0.0708 | +| entropy_loss | -7.18 | +| explained_variance | -0.218 | +| learning_rate | 4.6e-05 | +| loss | -0.037 | +| n_updates | 48856 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000137 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1422 | +| iterations | 8261 | +| time_elapsed | 11889 | +| total_timesteps | 16918528 | +| train/ | | +| approx_kl | 0.010684048 | +| clip_fraction | 0.343 | +| clip_range | 0.0708 | +| entropy_loss | -6.44 | +| explained_variance | 0.491 | +| learning_rate | 4.6e-05 | +| loss | -0.0245 | +| n_updates | 48860 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000171 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1422 | +| iterations | 8262 | +| time_elapsed | 11891 | +| total_timesteps | 16920576 | +| train/ | | +| approx_kl | 0.009424217 | +| clip_fraction | 0.293 | +| clip_range | 0.0708 | +| entropy_loss | -6.54 | +| explained_variance | 0.351 | +| learning_rate | 4.6e-05 | +| loss | -0.0232 | +| n_updates | 48864 | +| policy_gradient_loss | -0.0146 | +| value_loss | 0.000248 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1422 | +| iterations | 8263 | +| time_elapsed | 11892 | +| total_timesteps | 16922624 | +| train/ | | +| approx_kl | 0.013015868 | +| clip_fraction | 0.316 | +| clip_range | 0.0708 | +| entropy_loss | -6.35 | +| explained_variance | 0.497 | +| learning_rate | 4.6e-05 | +| loss | -0.0301 | +| n_updates | 48868 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000186 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1422 | +| iterations | 8264 | +| time_elapsed | 11894 | +| total_timesteps | 16924672 | +| train/ | | +| approx_kl | 0.01453193 | +| clip_fraction | 0.348 | +| clip_range | 0.0708 | +| entropy_loss | -6.29 | +| explained_variance | 0.502 | +| learning_rate | 4.6e-05 | +| loss | -0.0305 | +| n_updates | 48872 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000149 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1422 | +| iterations | 8265 | +| time_elapsed | 11895 | +| total_timesteps | 16926720 | +| train/ | | +| approx_kl | 0.011666589 | +| clip_fraction | 0.346 | +| clip_range | 0.0708 | +| entropy_loss | -6.92 | +| explained_variance | -0.217 | +| learning_rate | 4.6e-05 | +| loss | -0.0354 | +| n_updates | 48876 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000128 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1422 | +| iterations | 8266 | +| time_elapsed | 11896 | +| total_timesteps | 16928768 | +| train/ | | +| approx_kl | 0.011025075 | +| clip_fraction | 0.349 | +| clip_range | 0.0708 | +| entropy_loss | -6.81 | +| explained_variance | 0.293 | +| learning_rate | 4.6e-05 | +| loss | -0.0285 | +| n_updates | 48880 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000164 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1422 | +| iterations | 8267 | +| time_elapsed | 11898 | +| total_timesteps | 16930816 | +| train/ | | +| approx_kl | 0.014933057 | +| clip_fraction | 0.359 | +| clip_range | 0.0708 | +| entropy_loss | -6.89 | +| explained_variance | 0.313 | +| learning_rate | 4.6e-05 | +| loss | -0.0336 | +| n_updates | 48884 | +| policy_gradient_loss | -0.0221 | +| value_loss | 0.000111 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1422 | +| iterations | 8268 | +| time_elapsed | 11899 | +| total_timesteps | 16932864 | +| train/ | | +| approx_kl | 0.012693558 | +| clip_fraction | 0.34 | +| clip_range | 0.0708 | +| entropy_loss | -6.88 | +| explained_variance | 0.251 | +| learning_rate | 4.6e-05 | +| loss | -0.0266 | +| n_updates | 48888 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.0002 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1422 | +| iterations | 8269 | +| time_elapsed | 11901 | +| total_timesteps | 16934912 | +| train/ | | +| approx_kl | 0.011596853 | +| clip_fraction | 0.325 | +| clip_range | 0.0708 | +| entropy_loss | -6.65 | +| explained_variance | 0.442 | +| learning_rate | 4.6e-05 | +| loss | -0.0328 | +| n_updates | 48892 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000159 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1422 | +| iterations | 8270 | +| time_elapsed | 11902 | +| total_timesteps | 16936960 | +| train/ | | +| approx_kl | 0.013163751 | +| clip_fraction | 0.346 | +| clip_range | 0.0708 | +| entropy_loss | -6.98 | +| explained_variance | -0.254 | +| learning_rate | 4.6e-05 | +| loss | -0.0351 | +| n_updates | 48896 | +| policy_gradient_loss | -0.022 | +| value_loss | 8.82e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1422 | +| iterations | 8271 | +| time_elapsed | 11904 | +| total_timesteps | 16939008 | +| train/ | | +| approx_kl | 0.013553621 | +| clip_fraction | 0.309 | +| clip_range | 0.0708 | +| entropy_loss | -6.59 | +| explained_variance | 0.544 | +| learning_rate | 4.6e-05 | +| loss | -0.0287 | +| n_updates | 48900 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000126 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1422 | +| iterations | 8272 | +| time_elapsed | 11905 | +| total_timesteps | 16941056 | +| train/ | | +| approx_kl | 0.0103393905 | +| clip_fraction | 0.317 | +| clip_range | 0.0708 | +| entropy_loss | -6.59 | +| explained_variance | 0.56 | +| learning_rate | 4.6e-05 | +| loss | -0.0336 | +| n_updates | 48904 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000141 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1422 | +| iterations | 8273 | +| time_elapsed | 11907 | +| total_timesteps | 16943104 | +| train/ | | +| approx_kl | 0.01380789 | +| clip_fraction | 0.318 | +| clip_range | 0.0708 | +| entropy_loss | -6.09 | +| explained_variance | 0.664 | +| learning_rate | 4.6e-05 | +| loss | -0.0296 | +| n_updates | 48908 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000145 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1422 | +| iterations | 8274 | +| time_elapsed | 11908 | +| total_timesteps | 16945152 | +| train/ | | +| approx_kl | 0.009290996 | +| clip_fraction | 0.314 | +| clip_range | 0.0708 | +| entropy_loss | -6.71 | +| explained_variance | 0.497 | +| learning_rate | 4.6e-05 | +| loss | -0.0283 | +| n_updates | 48912 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000174 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1422 | +| iterations | 8275 | +| time_elapsed | 11909 | +| total_timesteps | 16947200 | +| train/ | | +| approx_kl | 0.009355677 | +| clip_fraction | 0.336 | +| clip_range | 0.0708 | +| entropy_loss | -7.13 | +| explained_variance | 0.189 | +| learning_rate | 4.6e-05 | +| loss | -0.0332 | +| n_updates | 48916 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000103 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1422 | +| iterations | 8276 | +| time_elapsed | 11911 | +| total_timesteps | 16949248 | +| train/ | | +| approx_kl | 0.010686434 | +| clip_fraction | 0.364 | +| clip_range | 0.0708 | +| entropy_loss | -7.17 | +| explained_variance | -0.143 | +| learning_rate | 4.6e-05 | +| loss | -0.0395 | +| n_updates | 48920 | +| policy_gradient_loss | -0.0248 | +| value_loss | 5.46e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1422 | +| iterations | 8277 | +| time_elapsed | 11912 | +| total_timesteps | 16951296 | +| train/ | | +| approx_kl | 0.009723669 | +| clip_fraction | 0.281 | +| clip_range | 0.0708 | +| entropy_loss | -6.68 | +| explained_variance | 0.37 | +| learning_rate | 4.6e-05 | +| loss | -0.0208 | +| n_updates | 48924 | +| policy_gradient_loss | -0.0139 | +| value_loss | 0.00032 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1422 | +| iterations | 8278 | +| time_elapsed | 11914 | +| total_timesteps | 16953344 | +| train/ | | +| approx_kl | 0.012978994 | +| clip_fraction | 0.348 | +| clip_range | 0.0708 | +| entropy_loss | -6.95 | +| explained_variance | -0.0614 | +| learning_rate | 4.6e-05 | +| loss | -0.0363 | +| n_updates | 48928 | +| policy_gradient_loss | -0.0225 | +| value_loss | 0.000178 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1422 | +| iterations | 8279 | +| time_elapsed | 11915 | +| total_timesteps | 16955392 | +| train/ | | +| approx_kl | 0.010500423 | +| clip_fraction | 0.332 | +| clip_range | 0.0708 | +| entropy_loss | -6.52 | +| explained_variance | 0.566 | +| learning_rate | 4.6e-05 | +| loss | -0.03 | +| n_updates | 48932 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.00021 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1422 | +| iterations | 8280 | +| time_elapsed | 11917 | +| total_timesteps | 16957440 | +| train/ | | +| approx_kl | 0.010671973 | +| clip_fraction | 0.3 | +| clip_range | 0.0708 | +| entropy_loss | -6.85 | +| explained_variance | 0.452 | +| learning_rate | 4.6e-05 | +| loss | -0.0312 | +| n_updates | 48936 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000181 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1422 | +| iterations | 8281 | +| time_elapsed | 11918 | +| total_timesteps | 16959488 | +| train/ | | +| approx_kl | 0.010745134 | +| clip_fraction | 0.316 | +| clip_range | 0.0708 | +| entropy_loss | -6.79 | +| explained_variance | 0.282 | +| learning_rate | 4.6e-05 | +| loss | -0.0291 | +| n_updates | 48940 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000239 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1422 | +| iterations | 8282 | +| time_elapsed | 11919 | +| total_timesteps | 16961536 | +| train/ | | +| approx_kl | 0.009761132 | +| clip_fraction | 0.329 | +| clip_range | 0.0708 | +| entropy_loss | -6.84 | +| explained_variance | 0.242 | +| learning_rate | 4.6e-05 | +| loss | -0.0317 | +| n_updates | 48944 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.00023 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1422 | +| iterations | 8283 | +| time_elapsed | 11921 | +| total_timesteps | 16963584 | +| train/ | | +| approx_kl | 0.01177202 | +| clip_fraction | 0.341 | +| clip_range | 0.0708 | +| entropy_loss | -6.58 | +| explained_variance | 0.408 | +| learning_rate | 4.6e-05 | +| loss | -0.025 | +| n_updates | 48948 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000216 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1422 | +| iterations | 8284 | +| time_elapsed | 11922 | +| total_timesteps | 16965632 | +| train/ | | +| approx_kl | 0.012029781 | +| clip_fraction | 0.348 | +| clip_range | 0.0708 | +| entropy_loss | -6.97 | +| explained_variance | -0.0438 | +| learning_rate | 4.6e-05 | +| loss | -0.0325 | +| n_updates | 48952 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000153 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1422 | +| iterations | 8285 | +| time_elapsed | 11924 | +| total_timesteps | 16967680 | +| train/ | | +| approx_kl | 0.010425765 | +| clip_fraction | 0.31 | +| clip_range | 0.0708 | +| entropy_loss | -6.95 | +| explained_variance | 0.257 | +| learning_rate | 4.6e-05 | +| loss | -0.0329 | +| n_updates | 48956 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000164 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1422 | +| iterations | 8286 | +| time_elapsed | 11925 | +| total_timesteps | 16969728 | +| train/ | | +| approx_kl | 0.01187557 | +| clip_fraction | 0.314 | +| clip_range | 0.0708 | +| entropy_loss | -6.61 | +| explained_variance | 0.326 | +| learning_rate | 4.6e-05 | +| loss | -0.0232 | +| n_updates | 48960 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000297 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1422 | +| iterations | 8287 | +| time_elapsed | 11927 | +| total_timesteps | 16971776 | +| train/ | | +| approx_kl | 0.010201236 | +| clip_fraction | 0.307 | +| clip_range | 0.0708 | +| entropy_loss | -6.91 | +| explained_variance | 0.43 | +| learning_rate | 4.6e-05 | +| loss | -0.0298 | +| n_updates | 48964 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000176 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1422 | +| iterations | 8288 | +| time_elapsed | 11928 | +| total_timesteps | 16973824 | +| train/ | | +| approx_kl | 0.011530237 | +| clip_fraction | 0.3 | +| clip_range | 0.0708 | +| entropy_loss | -6.58 | +| explained_variance | 0.503 | +| learning_rate | 4.6e-05 | +| loss | -0.0346 | +| n_updates | 48968 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000196 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1422 | +| iterations | 8289 | +| time_elapsed | 11930 | +| total_timesteps | 16975872 | +| train/ | | +| approx_kl | 0.013440454 | +| clip_fraction | 0.353 | +| clip_range | 0.0708 | +| entropy_loss | -6.92 | +| explained_variance | -0.0571 | +| learning_rate | 4.6e-05 | +| loss | -0.0312 | +| n_updates | 48972 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000103 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1422 | +| iterations | 8290 | +| time_elapsed | 11931 | +| total_timesteps | 16977920 | +| train/ | | +| approx_kl | 0.012227079 | +| clip_fraction | 0.329 | +| clip_range | 0.0708 | +| entropy_loss | -6.85 | +| explained_variance | 0.293 | +| learning_rate | 4.6e-05 | +| loss | -0.0245 | +| n_updates | 48976 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.00018 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1422 | +| iterations | 8291 | +| time_elapsed | 11933 | +| total_timesteps | 16979968 | +| train/ | | +| approx_kl | 0.011320777 | +| clip_fraction | 0.33 | +| clip_range | 0.0708 | +| entropy_loss | -6.37 | +| explained_variance | 0.565 | +| learning_rate | 4.6e-05 | +| loss | -0.0337 | +| n_updates | 48980 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000193 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1422 | +| iterations | 8292 | +| time_elapsed | 11934 | +| total_timesteps | 16982016 | +| train/ | | +| approx_kl | 0.0085277 | +| clip_fraction | 0.292 | +| clip_range | 0.0708 | +| entropy_loss | -6.76 | +| explained_variance | 0.303 | +| learning_rate | 4.6e-05 | +| loss | -0.0296 | +| n_updates | 48984 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.000327 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1422 | +| iterations | 8293 | +| time_elapsed | 11936 | +| total_timesteps | 16984064 | +| train/ | | +| approx_kl | 0.012218883 | +| clip_fraction | 0.368 | +| clip_range | 0.0708 | +| entropy_loss | -6.29 | +| explained_variance | 0.699 | +| learning_rate | 4.6e-05 | +| loss | -0.0349 | +| n_updates | 48988 | +| policy_gradient_loss | -0.024 | +| value_loss | 5.82e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1422 | +| iterations | 8294 | +| time_elapsed | 11937 | +| total_timesteps | 16986112 | +| train/ | | +| approx_kl | 0.012655038 | +| clip_fraction | 0.31 | +| clip_range | 0.0708 | +| entropy_loss | -6.6 | +| explained_variance | 0.41 | +| learning_rate | 4.6e-05 | +| loss | -0.026 | +| n_updates | 48992 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000251 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1422 | +| iterations | 8295 | +| time_elapsed | 11938 | +| total_timesteps | 16988160 | +| train/ | | +| approx_kl | 0.0125318235 | +| clip_fraction | 0.346 | +| clip_range | 0.0708 | +| entropy_loss | -6.99 | +| explained_variance | 0.0169 | +| learning_rate | 4.6e-05 | +| loss | -0.0365 | +| n_updates | 48996 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000154 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1422 | +| iterations | 8296 | +| time_elapsed | 11940 | +| total_timesteps | 16990208 | +| train/ | | +| approx_kl | 0.0125397835 | +| clip_fraction | 0.318 | +| clip_range | 0.0708 | +| entropy_loss | -6.7 | +| explained_variance | 0.379 | +| learning_rate | 4.6e-05 | +| loss | -0.0306 | +| n_updates | 49000 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000236 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1422 | +| iterations | 8297 | +| time_elapsed | 11941 | +| total_timesteps | 16992256 | +| train/ | | +| approx_kl | 0.011174306 | +| clip_fraction | 0.337 | +| clip_range | 0.0708 | +| entropy_loss | -6.5 | +| explained_variance | 0.402 | +| learning_rate | 4.6e-05 | +| loss | -0.0283 | +| n_updates | 49004 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000221 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1422 | +| iterations | 8298 | +| time_elapsed | 11943 | +| total_timesteps | 16994304 | +| train/ | | +| approx_kl | 0.0129900165 | +| clip_fraction | 0.362 | +| clip_range | 0.0708 | +| entropy_loss | -6.67 | +| explained_variance | 0.402 | +| learning_rate | 4.6e-05 | +| loss | -0.0367 | +| n_updates | 49008 | +| policy_gradient_loss | -0.0221 | +| value_loss | 0.000104 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1422 | +| iterations | 8299 | +| time_elapsed | 11944 | +| total_timesteps | 16996352 | +| train/ | | +| approx_kl | 0.011079564 | +| clip_fraction | 0.354 | +| clip_range | 0.0708 | +| entropy_loss | -7.06 | +| explained_variance | -0.0408 | +| learning_rate | 4.6e-05 | +| loss | -0.0339 | +| n_updates | 49012 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.00016 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1422 | +| iterations | 8300 | +| time_elapsed | 11945 | +| total_timesteps | 16998400 | +| train/ | | +| approx_kl | 0.012799729 | +| clip_fraction | 0.32 | +| clip_range | 0.0708 | +| entropy_loss | -7.09 | +| explained_variance | 0.308 | +| learning_rate | 4.6e-05 | +| loss | -0.0316 | +| n_updates | 49016 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000122 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1422 | +| iterations | 8301 | +| time_elapsed | 11947 | +| total_timesteps | 17000448 | +| train/ | | +| approx_kl | 0.012680646 | +| clip_fraction | 0.358 | +| clip_range | 0.0708 | +| entropy_loss | -6.54 | +| explained_variance | 0.185 | +| learning_rate | 4.6e-05 | +| loss | -0.0295 | +| n_updates | 49020 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000187 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1422 | +| iterations | 8302 | +| time_elapsed | 11949 | +| total_timesteps | 17002496 | +| train/ | | +| approx_kl | 0.011757294 | +| clip_fraction | 0.309 | +| clip_range | 0.0707 | +| entropy_loss | -6.62 | +| explained_variance | 0.205 | +| learning_rate | 4.6e-05 | +| loss | -0.0264 | +| n_updates | 49024 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000331 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1422 | +| iterations | 8303 | +| time_elapsed | 11950 | +| total_timesteps | 17004544 | +| train/ | | +| approx_kl | 0.013492199 | +| clip_fraction | 0.341 | +| clip_range | 0.0707 | +| entropy_loss | -6.2 | +| explained_variance | 0.615 | +| learning_rate | 4.6e-05 | +| loss | -0.0326 | +| n_updates | 49028 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000125 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1422 | +| iterations | 8304 | +| time_elapsed | 11951 | +| total_timesteps | 17006592 | +| train/ | | +| approx_kl | 0.011549508 | +| clip_fraction | 0.3 | +| clip_range | 0.0707 | +| entropy_loss | -6.4 | +| explained_variance | 0.488 | +| learning_rate | 4.6e-05 | +| loss | -0.0269 | +| n_updates | 49032 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000197 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1422 | +| iterations | 8305 | +| time_elapsed | 11953 | +| total_timesteps | 17008640 | +| train/ | | +| approx_kl | 0.015111886 | +| clip_fraction | 0.348 | +| clip_range | 0.0707 | +| entropy_loss | -6.82 | +| explained_variance | -0.0694 | +| learning_rate | 4.6e-05 | +| loss | -0.0357 | +| n_updates | 49036 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000139 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1422 | +| iterations | 8306 | +| time_elapsed | 11954 | +| total_timesteps | 17010688 | +| train/ | | +| approx_kl | 0.010526121 | +| clip_fraction | 0.33 | +| clip_range | 0.0707 | +| entropy_loss | -7.04 | +| explained_variance | 0.25 | +| learning_rate | 4.6e-05 | +| loss | -0.0362 | +| n_updates | 49040 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.00023 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1422 | +| iterations | 8307 | +| time_elapsed | 11956 | +| total_timesteps | 17012736 | +| train/ | | +| approx_kl | 0.014189031 | +| clip_fraction | 0.349 | +| clip_range | 0.0707 | +| entropy_loss | -6.89 | +| explained_variance | 0.283 | +| learning_rate | 4.6e-05 | +| loss | -0.0315 | +| n_updates | 49044 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000172 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1422 | +| iterations | 8308 | +| time_elapsed | 11957 | +| total_timesteps | 17014784 | +| train/ | | +| approx_kl | 0.014295398 | +| clip_fraction | 0.369 | +| clip_range | 0.0707 | +| entropy_loss | -6.96 | +| explained_variance | -0.139 | +| learning_rate | 4.6e-05 | +| loss | -0.0292 | +| n_updates | 49048 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000137 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1422 | +| iterations | 8309 | +| time_elapsed | 11959 | +| total_timesteps | 17016832 | +| train/ | | +| approx_kl | 0.014756894 | +| clip_fraction | 0.326 | +| clip_range | 0.0707 | +| entropy_loss | -6.85 | +| explained_variance | -0.104 | +| learning_rate | 4.6e-05 | +| loss | -0.0303 | +| n_updates | 49052 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000176 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1422 | +| iterations | 8310 | +| time_elapsed | 11960 | +| total_timesteps | 17018880 | +| train/ | | +| approx_kl | 0.011294642 | +| clip_fraction | 0.316 | +| clip_range | 0.0707 | +| entropy_loss | -7.09 | +| explained_variance | -0.0689 | +| learning_rate | 4.6e-05 | +| loss | -0.03 | +| n_updates | 49056 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.00029 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1422 | +| iterations | 8311 | +| time_elapsed | 11962 | +| total_timesteps | 17020928 | +| train/ | | +| approx_kl | 0.013155996 | +| clip_fraction | 0.33 | +| clip_range | 0.0707 | +| entropy_loss | -6.63 | +| explained_variance | 0.372 | +| learning_rate | 4.6e-05 | +| loss | -0.0325 | +| n_updates | 49060 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000199 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1422 | +| iterations | 8312 | +| time_elapsed | 11963 | +| total_timesteps | 17022976 | +| train/ | | +| approx_kl | 0.013343038 | +| clip_fraction | 0.317 | +| clip_range | 0.0707 | +| entropy_loss | -6.34 | +| explained_variance | 0.407 | +| learning_rate | 4.6e-05 | +| loss | -0.0232 | +| n_updates | 49064 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000329 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1422 | +| iterations | 8313 | +| time_elapsed | 11965 | +| total_timesteps | 17025024 | +| train/ | | +| approx_kl | 0.011732092 | +| clip_fraction | 0.315 | +| clip_range | 0.0707 | +| entropy_loss | -6.37 | +| explained_variance | 0.343 | +| learning_rate | 4.6e-05 | +| loss | -0.0277 | +| n_updates | 49068 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000241 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1422 | +| iterations | 8314 | +| time_elapsed | 11966 | +| total_timesteps | 17027072 | +| train/ | | +| approx_kl | 0.013704734 | +| clip_fraction | 0.337 | +| clip_range | 0.0707 | +| entropy_loss | -6.72 | +| explained_variance | 0.281 | +| learning_rate | 4.6e-05 | +| loss | -0.0331 | +| n_updates | 49072 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000192 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1422 | +| iterations | 8315 | +| time_elapsed | 11967 | +| total_timesteps | 17029120 | +| train/ | | +| approx_kl | 0.012145307 | +| clip_fraction | 0.338 | +| clip_range | 0.0707 | +| entropy_loss | -6.74 | +| explained_variance | 0.268 | +| learning_rate | 4.6e-05 | +| loss | -0.0323 | +| n_updates | 49076 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000179 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1422 | +| iterations | 8316 | +| time_elapsed | 11969 | +| total_timesteps | 17031168 | +| train/ | | +| approx_kl | 0.013885774 | +| clip_fraction | 0.357 | +| clip_range | 0.0707 | +| entropy_loss | -6.56 | +| explained_variance | 0.446 | +| learning_rate | 4.6e-05 | +| loss | -0.0356 | +| n_updates | 49080 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000199 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1422 | +| iterations | 8317 | +| time_elapsed | 11970 | +| total_timesteps | 17033216 | +| train/ | | +| approx_kl | 0.009810797 | +| clip_fraction | 0.292 | +| clip_range | 0.0707 | +| entropy_loss | -6.53 | +| explained_variance | 0.349 | +| learning_rate | 4.6e-05 | +| loss | -0.0308 | +| n_updates | 49084 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000225 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1422 | +| iterations | 8318 | +| time_elapsed | 11972 | +| total_timesteps | 17035264 | +| train/ | | +| approx_kl | 0.010347476 | +| clip_fraction | 0.307 | +| clip_range | 0.0707 | +| entropy_loss | -6.99 | +| explained_variance | 0.0492 | +| learning_rate | 4.6e-05 | +| loss | -0.0248 | +| n_updates | 49088 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000358 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1422 | +| iterations | 8319 | +| time_elapsed | 11973 | +| total_timesteps | 17037312 | +| train/ | | +| approx_kl | 0.009182059 | +| clip_fraction | 0.321 | +| clip_range | 0.0707 | +| entropy_loss | -6.96 | +| explained_variance | 0.226 | +| learning_rate | 4.6e-05 | +| loss | -0.0268 | +| n_updates | 49092 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000402 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1422 | +| iterations | 8320 | +| time_elapsed | 11975 | +| total_timesteps | 17039360 | +| train/ | | +| approx_kl | 0.0113733895 | +| clip_fraction | 0.332 | +| clip_range | 0.0707 | +| entropy_loss | -6.79 | +| explained_variance | 0.492 | +| learning_rate | 4.6e-05 | +| loss | -0.0423 | +| n_updates | 49096 | +| policy_gradient_loss | -0.0221 | +| value_loss | 0.000149 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1422 | +| iterations | 8321 | +| time_elapsed | 11976 | +| total_timesteps | 17041408 | +| train/ | | +| approx_kl | 0.010081055 | +| clip_fraction | 0.33 | +| clip_range | 0.0707 | +| entropy_loss | -5.98 | +| explained_variance | 0.558 | +| learning_rate | 4.6e-05 | +| loss | -0.0267 | +| n_updates | 49100 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000294 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1422 | +| iterations | 8322 | +| time_elapsed | 11978 | +| total_timesteps | 17043456 | +| train/ | | +| approx_kl | 0.010996221 | +| clip_fraction | 0.367 | +| clip_range | 0.0707 | +| entropy_loss | -6.7 | +| explained_variance | 0.0829 | +| learning_rate | 4.6e-05 | +| loss | -0.0371 | +| n_updates | 49104 | +| policy_gradient_loss | -0.022 | +| value_loss | 0.000254 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1422 | +| iterations | 8323 | +| time_elapsed | 11979 | +| total_timesteps | 17045504 | +| train/ | | +| approx_kl | 0.01358009 | +| clip_fraction | 0.383 | +| clip_range | 0.0707 | +| entropy_loss | -7.13 | +| explained_variance | -0.0946 | +| learning_rate | 4.6e-05 | +| loss | -0.0405 | +| n_updates | 49108 | +| policy_gradient_loss | -0.0241 | +| value_loss | 0.0001 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1422 | +| iterations | 8324 | +| time_elapsed | 11980 | +| total_timesteps | 17047552 | +| train/ | | +| approx_kl | 0.012610523 | +| clip_fraction | 0.318 | +| clip_range | 0.0707 | +| entropy_loss | -6.46 | +| explained_variance | 0.423 | +| learning_rate | 4.6e-05 | +| loss | -0.0266 | +| n_updates | 49112 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000261 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1422 | +| iterations | 8325 | +| time_elapsed | 11982 | +| total_timesteps | 17049600 | +| train/ | | +| approx_kl | 0.0144865895 | +| clip_fraction | 0.406 | +| clip_range | 0.0707 | +| entropy_loss | -6.74 | +| explained_variance | 0.547 | +| learning_rate | 4.6e-05 | +| loss | -0.0396 | +| n_updates | 49116 | +| policy_gradient_loss | -0.0276 | +| value_loss | 5.18e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1422 | +| iterations | 8326 | +| time_elapsed | 11983 | +| total_timesteps | 17051648 | +| train/ | | +| approx_kl | 0.012344075 | +| clip_fraction | 0.322 | +| clip_range | 0.0707 | +| entropy_loss | -6.94 | +| explained_variance | 0.296 | +| learning_rate | 4.6e-05 | +| loss | -0.0313 | +| n_updates | 49120 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000165 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1422 | +| iterations | 8327 | +| time_elapsed | 11985 | +| total_timesteps | 17053696 | +| train/ | | +| approx_kl | 0.009137986 | +| clip_fraction | 0.312 | +| clip_range | 0.0707 | +| entropy_loss | -6.91 | +| explained_variance | 0.173 | +| learning_rate | 4.6e-05 | +| loss | -0.0321 | +| n_updates | 49124 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000187 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1422 | +| iterations | 8328 | +| time_elapsed | 11986 | +| total_timesteps | 17055744 | +| train/ | | +| approx_kl | 0.012745635 | +| clip_fraction | 0.339 | +| clip_range | 0.0707 | +| entropy_loss | -6.85 | +| explained_variance | 0.24 | +| learning_rate | 4.59e-05 | +| loss | -0.0314 | +| n_updates | 49128 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000179 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1422 | +| iterations | 8329 | +| time_elapsed | 11988 | +| total_timesteps | 17057792 | +| train/ | | +| approx_kl | 0.01265893 | +| clip_fraction | 0.326 | +| clip_range | 0.0707 | +| entropy_loss | -6.93 | +| explained_variance | -0.385 | +| learning_rate | 4.59e-05 | +| loss | -0.0271 | +| n_updates | 49132 | +| policy_gradient_loss | -0.0174 | +| value_loss | 9.46e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1422 | +| iterations | 8330 | +| time_elapsed | 11989 | +| total_timesteps | 17059840 | +| train/ | | +| approx_kl | 0.012629523 | +| clip_fraction | 0.336 | +| clip_range | 0.0707 | +| entropy_loss | -7.03 | +| explained_variance | -0.0444 | +| learning_rate | 4.59e-05 | +| loss | -0.0284 | +| n_updates | 49136 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000156 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1422 | +| iterations | 8331 | +| time_elapsed | 11990 | +| total_timesteps | 17061888 | +| train/ | | +| approx_kl | 0.012974041 | +| clip_fraction | 0.336 | +| clip_range | 0.0707 | +| entropy_loss | -6.73 | +| explained_variance | 0.407 | +| learning_rate | 4.59e-05 | +| loss | -0.0341 | +| n_updates | 49140 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000148 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1422 | +| iterations | 8332 | +| time_elapsed | 11992 | +| total_timesteps | 17063936 | +| train/ | | +| approx_kl | 0.011908223 | +| clip_fraction | 0.342 | +| clip_range | 0.0707 | +| entropy_loss | -6.54 | +| explained_variance | 0.628 | +| learning_rate | 4.59e-05 | +| loss | -0.032 | +| n_updates | 49144 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.00011 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1422 | +| iterations | 8333 | +| time_elapsed | 11993 | +| total_timesteps | 17065984 | +| train/ | | +| approx_kl | 0.013934959 | +| clip_fraction | 0.345 | +| clip_range | 0.0707 | +| entropy_loss | -6.32 | +| explained_variance | 0.641 | +| learning_rate | 4.59e-05 | +| loss | -0.0304 | +| n_updates | 49148 | +| policy_gradient_loss | -0.0203 | +| value_loss | 9.56e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1422 | +| iterations | 8334 | +| time_elapsed | 11995 | +| total_timesteps | 17068032 | +| train/ | | +| approx_kl | 0.012281219 | +| clip_fraction | 0.333 | +| clip_range | 0.0707 | +| entropy_loss | -6.46 | +| explained_variance | 0.521 | +| learning_rate | 4.59e-05 | +| loss | -0.0254 | +| n_updates | 49152 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000115 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1422 | +| iterations | 8335 | +| time_elapsed | 11996 | +| total_timesteps | 17070080 | +| train/ | | +| approx_kl | 0.01043216 | +| clip_fraction | 0.324 | +| clip_range | 0.0707 | +| entropy_loss | -6.55 | +| explained_variance | 0.517 | +| learning_rate | 4.59e-05 | +| loss | -0.0285 | +| n_updates | 49156 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000177 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1422 | +| iterations | 8336 | +| time_elapsed | 11997 | +| total_timesteps | 17072128 | +| train/ | | +| approx_kl | 0.01253069 | +| clip_fraction | 0.363 | +| clip_range | 0.0707 | +| entropy_loss | -6.67 | +| explained_variance | 0.462 | +| learning_rate | 4.59e-05 | +| loss | -0.0364 | +| n_updates | 49160 | +| policy_gradient_loss | -0.0223 | +| value_loss | 8.55e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1422 | +| iterations | 8337 | +| time_elapsed | 11999 | +| total_timesteps | 17074176 | +| train/ | | +| approx_kl | 0.011225248 | +| clip_fraction | 0.333 | +| clip_range | 0.0707 | +| entropy_loss | -6.89 | +| explained_variance | 0.22 | +| learning_rate | 4.59e-05 | +| loss | -0.029 | +| n_updates | 49164 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000238 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1422 | +| iterations | 8338 | +| time_elapsed | 12000 | +| total_timesteps | 17076224 | +| train/ | | +| approx_kl | 0.0107046645 | +| clip_fraction | 0.316 | +| clip_range | 0.0707 | +| entropy_loss | -6.34 | +| explained_variance | 0.575 | +| learning_rate | 4.59e-05 | +| loss | -0.031 | +| n_updates | 49168 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000157 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1422 | +| iterations | 8339 | +| time_elapsed | 12002 | +| total_timesteps | 17078272 | +| train/ | | +| approx_kl | 0.014246456 | +| clip_fraction | 0.345 | +| clip_range | 0.0707 | +| entropy_loss | -6.45 | +| explained_variance | 0.347 | +| learning_rate | 4.59e-05 | +| loss | -0.0277 | +| n_updates | 49172 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000235 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1422 | +| iterations | 8340 | +| time_elapsed | 12003 | +| total_timesteps | 17080320 | +| train/ | | +| approx_kl | 0.014829945 | +| clip_fraction | 0.38 | +| clip_range | 0.0707 | +| entropy_loss | -6.68 | +| explained_variance | 0.236 | +| learning_rate | 4.59e-05 | +| loss | -0.0275 | +| n_updates | 49176 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000143 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1422 | +| iterations | 8341 | +| time_elapsed | 12005 | +| total_timesteps | 17082368 | +| train/ | | +| approx_kl | 0.012163784 | +| clip_fraction | 0.337 | +| clip_range | 0.0707 | +| entropy_loss | -6.3 | +| explained_variance | 0.641 | +| learning_rate | 4.59e-05 | +| loss | -0.0314 | +| n_updates | 49180 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000142 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1422 | +| iterations | 8342 | +| time_elapsed | 12006 | +| total_timesteps | 17084416 | +| train/ | | +| approx_kl | 0.013204487 | +| clip_fraction | 0.351 | +| clip_range | 0.0707 | +| entropy_loss | -6.62 | +| explained_variance | 0.422 | +| learning_rate | 4.59e-05 | +| loss | -0.032 | +| n_updates | 49184 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000147 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1422 | +| iterations | 8343 | +| time_elapsed | 12008 | +| total_timesteps | 17086464 | +| train/ | | +| approx_kl | 0.013716431 | +| clip_fraction | 0.348 | +| clip_range | 0.0707 | +| entropy_loss | -7.06 | +| explained_variance | 0.0795 | +| learning_rate | 4.59e-05 | +| loss | -0.0359 | +| n_updates | 49188 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000116 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1422 | +| iterations | 8344 | +| time_elapsed | 12009 | +| total_timesteps | 17088512 | +| train/ | | +| approx_kl | 0.01087464 | +| clip_fraction | 0.332 | +| clip_range | 0.0707 | +| entropy_loss | -6.52 | +| explained_variance | 0.354 | +| learning_rate | 4.59e-05 | +| loss | -0.029 | +| n_updates | 49192 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000262 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1422 | +| iterations | 8345 | +| time_elapsed | 12011 | +| total_timesteps | 17090560 | +| train/ | | +| approx_kl | 0.011318676 | +| clip_fraction | 0.347 | +| clip_range | 0.0707 | +| entropy_loss | -6.72 | +| explained_variance | 0.508 | +| learning_rate | 4.59e-05 | +| loss | -0.0336 | +| n_updates | 49196 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.00013 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1422 | +| iterations | 8346 | +| time_elapsed | 12012 | +| total_timesteps | 17092608 | +| train/ | | +| approx_kl | 0.013185687 | +| clip_fraction | 0.342 | +| clip_range | 0.0707 | +| entropy_loss | -6.79 | +| explained_variance | 0.425 | +| learning_rate | 4.59e-05 | +| loss | -0.0325 | +| n_updates | 49200 | +| policy_gradient_loss | -0.0215 | +| value_loss | 8.68e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1422 | +| iterations | 8347 | +| time_elapsed | 12013 | +| total_timesteps | 17094656 | +| train/ | | +| approx_kl | 0.010441093 | +| clip_fraction | 0.352 | +| clip_range | 0.0707 | +| entropy_loss | -6.55 | +| explained_variance | 0.581 | +| learning_rate | 4.59e-05 | +| loss | -0.0352 | +| n_updates | 49204 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.00012 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1422 | +| iterations | 8348 | +| time_elapsed | 12015 | +| total_timesteps | 17096704 | +| train/ | | +| approx_kl | 0.010171659 | +| clip_fraction | 0.297 | +| clip_range | 0.0707 | +| entropy_loss | -6.4 | +| explained_variance | 0.456 | +| learning_rate | 4.59e-05 | +| loss | -0.0235 | +| n_updates | 49208 | +| policy_gradient_loss | -0.0144 | +| value_loss | 0.000149 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1422 | +| iterations | 8349 | +| time_elapsed | 12016 | +| total_timesteps | 17098752 | +| train/ | | +| approx_kl | 0.013307561 | +| clip_fraction | 0.331 | +| clip_range | 0.0707 | +| entropy_loss | -6.08 | +| explained_variance | 0.609 | +| learning_rate | 4.59e-05 | +| loss | -0.0297 | +| n_updates | 49212 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000163 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1422 | +| iterations | 8350 | +| time_elapsed | 12018 | +| total_timesteps | 17100800 | +| train/ | | +| approx_kl | 0.01372685 | +| clip_fraction | 0.352 | +| clip_range | 0.0707 | +| entropy_loss | -6.7 | +| explained_variance | 0.454 | +| learning_rate | 4.59e-05 | +| loss | -0.0319 | +| n_updates | 49216 | +| policy_gradient_loss | -0.0221 | +| value_loss | 0.000101 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1422 | +| iterations | 8351 | +| time_elapsed | 12019 | +| total_timesteps | 17102848 | +| train/ | | +| approx_kl | 0.013707286 | +| clip_fraction | 0.371 | +| clip_range | 0.0707 | +| entropy_loss | -6.81 | +| explained_variance | 0.326 | +| learning_rate | 4.59e-05 | +| loss | -0.0338 | +| n_updates | 49220 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000101 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1422 | +| iterations | 8352 | +| time_elapsed | 12021 | +| total_timesteps | 17104896 | +| train/ | | +| approx_kl | 0.013583901 | +| clip_fraction | 0.33 | +| clip_range | 0.0707 | +| entropy_loss | -6.85 | +| explained_variance | 0.21 | +| learning_rate | 4.59e-05 | +| loss | -0.0344 | +| n_updates | 49224 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000256 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1422 | +| iterations | 8353 | +| time_elapsed | 12022 | +| total_timesteps | 17106944 | +| train/ | | +| approx_kl | 0.010523615 | +| clip_fraction | 0.304 | +| clip_range | 0.0707 | +| entropy_loss | -6.17 | +| explained_variance | 0.364 | +| learning_rate | 4.59e-05 | +| loss | -0.024 | +| n_updates | 49228 | +| policy_gradient_loss | -0.0134 | +| value_loss | 0.00037 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1422 | +| iterations | 8354 | +| time_elapsed | 12023 | +| total_timesteps | 17108992 | +| train/ | | +| approx_kl | 0.010424923 | +| clip_fraction | 0.339 | +| clip_range | 0.0707 | +| entropy_loss | -6.37 | +| explained_variance | 0.491 | +| learning_rate | 4.59e-05 | +| loss | -0.0381 | +| n_updates | 49232 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000228 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1422 | +| iterations | 8355 | +| time_elapsed | 12025 | +| total_timesteps | 17111040 | +| train/ | | +| approx_kl | 0.011318101 | +| clip_fraction | 0.33 | +| clip_range | 0.0707 | +| entropy_loss | -6.59 | +| explained_variance | 0.339 | +| learning_rate | 4.59e-05 | +| loss | -0.0337 | +| n_updates | 49236 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000258 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1422 | +| iterations | 8356 | +| time_elapsed | 12026 | +| total_timesteps | 17113088 | +| train/ | | +| approx_kl | 0.010885688 | +| clip_fraction | 0.351 | +| clip_range | 0.0707 | +| entropy_loss | -6.95 | +| explained_variance | 0.473 | +| learning_rate | 4.59e-05 | +| loss | -0.0437 | +| n_updates | 49240 | +| policy_gradient_loss | -0.0224 | +| value_loss | 9.84e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1422 | +| iterations | 8357 | +| time_elapsed | 12028 | +| total_timesteps | 17115136 | +| train/ | | +| approx_kl | 0.010218424 | +| clip_fraction | 0.344 | +| clip_range | 0.0707 | +| entropy_loss | -6.94 | +| explained_variance | 0.163 | +| learning_rate | 4.59e-05 | +| loss | -0.0306 | +| n_updates | 49244 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000354 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1422 | +| iterations | 8358 | +| time_elapsed | 12029 | +| total_timesteps | 17117184 | +| train/ | | +| approx_kl | 0.009845814 | +| clip_fraction | 0.333 | +| clip_range | 0.0707 | +| entropy_loss | -6.74 | +| explained_variance | 0.275 | +| learning_rate | 4.59e-05 | +| loss | -0.0326 | +| n_updates | 49248 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000189 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1422 | +| iterations | 8359 | +| time_elapsed | 12031 | +| total_timesteps | 17119232 | +| train/ | | +| approx_kl | 0.011503545 | +| clip_fraction | 0.339 | +| clip_range | 0.0707 | +| entropy_loss | -6.51 | +| explained_variance | 0.502 | +| learning_rate | 4.59e-05 | +| loss | -0.0332 | +| n_updates | 49252 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000137 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1422 | +| iterations | 8360 | +| time_elapsed | 12032 | +| total_timesteps | 17121280 | +| train/ | | +| approx_kl | 0.012327157 | +| clip_fraction | 0.341 | +| clip_range | 0.0707 | +| entropy_loss | -6.34 | +| explained_variance | 0.65 | +| learning_rate | 4.59e-05 | +| loss | -0.0341 | +| n_updates | 49256 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.00014 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1422 | +| iterations | 8361 | +| time_elapsed | 12034 | +| total_timesteps | 17123328 | +| train/ | | +| approx_kl | 0.0106517915 | +| clip_fraction | 0.367 | +| clip_range | 0.0707 | +| entropy_loss | -6.68 | +| explained_variance | 0.509 | +| learning_rate | 4.59e-05 | +| loss | -0.0424 | +| n_updates | 49260 | +| policy_gradient_loss | -0.023 | +| value_loss | 6.5e-05 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1422 | +| iterations | 8362 | +| time_elapsed | 12035 | +| total_timesteps | 17125376 | +| train/ | | +| approx_kl | 0.0113223195 | +| clip_fraction | 0.348 | +| clip_range | 0.0707 | +| entropy_loss | -6.85 | +| explained_variance | 0.388 | +| learning_rate | 4.59e-05 | +| loss | -0.0328 | +| n_updates | 49264 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000137 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1422 | +| iterations | 8363 | +| time_elapsed | 12036 | +| total_timesteps | 17127424 | +| train/ | | +| approx_kl | 0.012575179 | +| clip_fraction | 0.339 | +| clip_range | 0.0707 | +| entropy_loss | -6.65 | +| explained_variance | 0.455 | +| learning_rate | 4.59e-05 | +| loss | -0.029 | +| n_updates | 49268 | +| policy_gradient_loss | -0.0188 | +| value_loss | 9.63e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1422 | +| iterations | 8364 | +| time_elapsed | 12038 | +| total_timesteps | 17129472 | +| train/ | | +| approx_kl | 0.0129528325 | +| clip_fraction | 0.326 | +| clip_range | 0.0707 | +| entropy_loss | -6.76 | +| explained_variance | 0.311 | +| learning_rate | 4.59e-05 | +| loss | -0.0292 | +| n_updates | 49272 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000151 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1422 | +| iterations | 8365 | +| time_elapsed | 12039 | +| total_timesteps | 17131520 | +| train/ | | +| approx_kl | 0.0135865435 | +| clip_fraction | 0.342 | +| clip_range | 0.0707 | +| entropy_loss | -6.73 | +| explained_variance | -0.0267 | +| learning_rate | 4.59e-05 | +| loss | -0.0257 | +| n_updates | 49276 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000185 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1422 | +| iterations | 8366 | +| time_elapsed | 12041 | +| total_timesteps | 17133568 | +| train/ | | +| approx_kl | 0.014277165 | +| clip_fraction | 0.343 | +| clip_range | 0.0707 | +| entropy_loss | -6.75 | +| explained_variance | 0.351 | +| learning_rate | 4.59e-05 | +| loss | -0.0287 | +| n_updates | 49280 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.00015 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1422 | +| iterations | 8367 | +| time_elapsed | 12042 | +| total_timesteps | 17135616 | +| train/ | | +| approx_kl | 0.012868598 | +| clip_fraction | 0.348 | +| clip_range | 0.0707 | +| entropy_loss | -6.18 | +| explained_variance | 0.537 | +| learning_rate | 4.59e-05 | +| loss | -0.0311 | +| n_updates | 49284 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000204 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1422 | +| iterations | 8368 | +| time_elapsed | 12044 | +| total_timesteps | 17137664 | +| train/ | | +| approx_kl | 0.014384495 | +| clip_fraction | 0.371 | +| clip_range | 0.0707 | +| entropy_loss | -6.61 | +| explained_variance | 0.487 | +| learning_rate | 4.59e-05 | +| loss | -0.0412 | +| n_updates | 49288 | +| policy_gradient_loss | -0.023 | +| value_loss | 0.00011 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1422 | +| iterations | 8369 | +| time_elapsed | 12045 | +| total_timesteps | 17139712 | +| train/ | | +| approx_kl | 0.011118364 | +| clip_fraction | 0.344 | +| clip_range | 0.0707 | +| entropy_loss | -6.8 | +| explained_variance | 0.145 | +| learning_rate | 4.59e-05 | +| loss | -0.0298 | +| n_updates | 49292 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000329 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1422 | +| iterations | 8370 | +| time_elapsed | 12047 | +| total_timesteps | 17141760 | +| train/ | | +| approx_kl | 0.015382668 | +| clip_fraction | 0.351 | +| clip_range | 0.0707 | +| entropy_loss | -6.51 | +| explained_variance | 0.339 | +| learning_rate | 4.59e-05 | +| loss | -0.0301 | +| n_updates | 49296 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000159 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1422 | +| iterations | 8371 | +| time_elapsed | 12048 | +| total_timesteps | 17143808 | +| train/ | | +| approx_kl | 0.014320077 | +| clip_fraction | 0.387 | +| clip_range | 0.0707 | +| entropy_loss | -6.65 | +| explained_variance | 0.196 | +| learning_rate | 4.59e-05 | +| loss | -0.0354 | +| n_updates | 49300 | +| policy_gradient_loss | -0.0229 | +| value_loss | 0.000124 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1422 | +| iterations | 8372 | +| time_elapsed | 12049 | +| total_timesteps | 17145856 | +| train/ | | +| approx_kl | 0.013773898 | +| clip_fraction | 0.34 | +| clip_range | 0.0707 | +| entropy_loss | -6.78 | +| explained_variance | 0.394 | +| learning_rate | 4.59e-05 | +| loss | -0.0422 | +| n_updates | 49304 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000115 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1422 | +| iterations | 8373 | +| time_elapsed | 12051 | +| total_timesteps | 17147904 | +| train/ | | +| approx_kl | 0.012731982 | +| clip_fraction | 0.368 | +| clip_range | 0.0707 | +| entropy_loss | -6.34 | +| explained_variance | 0.73 | +| learning_rate | 4.59e-05 | +| loss | -0.0323 | +| n_updates | 49308 | +| policy_gradient_loss | -0.0212 | +| value_loss | 8.68e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1422 | +| iterations | 8374 | +| time_elapsed | 12052 | +| total_timesteps | 17149952 | +| train/ | | +| approx_kl | 0.014426483 | +| clip_fraction | 0.374 | +| clip_range | 0.0707 | +| entropy_loss | -6.59 | +| explained_variance | 0.49 | +| learning_rate | 4.59e-05 | +| loss | -0.0281 | +| n_updates | 49312 | +| policy_gradient_loss | -0.022 | +| value_loss | 7.12e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1422 | +| iterations | 8375 | +| time_elapsed | 12054 | +| total_timesteps | 17152000 | +| train/ | | +| approx_kl | 0.014623621 | +| clip_fraction | 0.336 | +| clip_range | 0.0707 | +| entropy_loss | -5.86 | +| explained_variance | 0.502 | +| learning_rate | 4.59e-05 | +| loss | -0.0272 | +| n_updates | 49316 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000338 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1422 | +| iterations | 8376 | +| time_elapsed | 12055 | +| total_timesteps | 17154048 | +| train/ | | +| approx_kl | 0.014661217 | +| clip_fraction | 0.378 | +| clip_range | 0.0707 | +| entropy_loss | -6.53 | +| explained_variance | -0.438 | +| learning_rate | 4.59e-05 | +| loss | -0.0323 | +| n_updates | 49320 | +| policy_gradient_loss | -0.0231 | +| value_loss | 0.000124 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.306 | +| time/ | | +| fps | 1422 | +| iterations | 8377 | +| time_elapsed | 12057 | +| total_timesteps | 17156096 | +| train/ | | +| approx_kl | 0.014585433 | +| clip_fraction | 0.365 | +| clip_range | 0.0707 | +| entropy_loss | -6.43 | +| explained_variance | 0.588 | +| learning_rate | 4.59e-05 | +| loss | -0.0353 | +| n_updates | 49324 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000111 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.306 | +| time/ | | +| fps | 1422 | +| iterations | 8378 | +| time_elapsed | 12058 | +| total_timesteps | 17158144 | +| train/ | | +| approx_kl | 0.0151073355 | +| clip_fraction | 0.361 | +| clip_range | 0.0707 | +| entropy_loss | -6.62 | +| explained_variance | -0.0259 | +| learning_rate | 4.59e-05 | +| loss | -0.0327 | +| n_updates | 49328 | +| policy_gradient_loss | -0.0213 | +| value_loss | 8.75e-05 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.302 | +| time/ | | +| fps | 1422 | +| iterations | 8379 | +| time_elapsed | 12059 | +| total_timesteps | 17160192 | +| train/ | | +| approx_kl | 0.0149101345 | +| clip_fraction | 0.341 | +| clip_range | 0.0707 | +| entropy_loss | -6.71 | +| explained_variance | 0.423 | +| learning_rate | 4.59e-05 | +| loss | -0.0311 | +| n_updates | 49332 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.00017 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 1422 | +| iterations | 8380 | +| time_elapsed | 12061 | +| total_timesteps | 17162240 | +| train/ | | +| approx_kl | 0.016207863 | +| clip_fraction | 0.355 | +| clip_range | 0.0707 | +| entropy_loss | -6.83 | +| explained_variance | 0.175 | +| learning_rate | 4.59e-05 | +| loss | -0.0333 | +| n_updates | 49336 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000191 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 1422 | +| iterations | 8381 | +| time_elapsed | 12062 | +| total_timesteps | 17164288 | +| train/ | | +| approx_kl | 0.013153261 | +| clip_fraction | 0.387 | +| clip_range | 0.0707 | +| entropy_loss | -6.4 | +| explained_variance | 0.643 | +| learning_rate | 4.59e-05 | +| loss | -0.0298 | +| n_updates | 49340 | +| policy_gradient_loss | -0.0222 | +| value_loss | 9.97e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 1422 | +| iterations | 8382 | +| time_elapsed | 12064 | +| total_timesteps | 17166336 | +| train/ | | +| approx_kl | 0.015892949 | +| clip_fraction | 0.381 | +| clip_range | 0.0707 | +| entropy_loss | -7.01 | +| explained_variance | -0.228 | +| learning_rate | 4.59e-05 | +| loss | -0.0383 | +| n_updates | 49344 | +| policy_gradient_loss | -0.0252 | +| value_loss | 7.38e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 1422 | +| iterations | 8383 | +| time_elapsed | 12065 | +| total_timesteps | 17168384 | +| train/ | | +| approx_kl | 0.013411965 | +| clip_fraction | 0.339 | +| clip_range | 0.0707 | +| entropy_loss | -6.78 | +| explained_variance | 0.212 | +| learning_rate | 4.59e-05 | +| loss | -0.0339 | +| n_updates | 49348 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000268 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.294 | +| time/ | | +| fps | 1422 | +| iterations | 8384 | +| time_elapsed | 12067 | +| total_timesteps | 17170432 | +| train/ | | +| approx_kl | 0.014647745 | +| clip_fraction | 0.37 | +| clip_range | 0.0707 | +| entropy_loss | -6.33 | +| explained_variance | 0.396 | +| learning_rate | 4.59e-05 | +| loss | -0.0336 | +| n_updates | 49352 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000195 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 1422 | +| iterations | 8385 | +| time_elapsed | 12068 | +| total_timesteps | 17172480 | +| train/ | | +| approx_kl | 0.01566936 | +| clip_fraction | 0.39 | +| clip_range | 0.0707 | +| entropy_loss | -6.1 | +| explained_variance | 0.74 | +| learning_rate | 4.59e-05 | +| loss | -0.0401 | +| n_updates | 49356 | +| policy_gradient_loss | -0.0238 | +| value_loss | 7.95e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 1422 | +| iterations | 8386 | +| time_elapsed | 12069 | +| total_timesteps | 17174528 | +| train/ | | +| approx_kl | 0.015167231 | +| clip_fraction | 0.357 | +| clip_range | 0.0707 | +| entropy_loss | -6.43 | +| explained_variance | 0.467 | +| learning_rate | 4.59e-05 | +| loss | -0.0303 | +| n_updates | 49360 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000149 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.298 | +| time/ | | +| fps | 1422 | +| iterations | 8387 | +| time_elapsed | 12071 | +| total_timesteps | 17176576 | +| train/ | | +| approx_kl | 0.011280512 | +| clip_fraction | 0.353 | +| clip_range | 0.0707 | +| entropy_loss | -6.69 | +| explained_variance | -0.0287 | +| learning_rate | 4.59e-05 | +| loss | -0.0317 | +| n_updates | 49364 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000195 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 1422 | +| iterations | 8388 | +| time_elapsed | 12072 | +| total_timesteps | 17178624 | +| train/ | | +| approx_kl | 0.013612673 | +| clip_fraction | 0.365 | +| clip_range | 0.0707 | +| entropy_loss | -6.56 | +| explained_variance | 0.666 | +| learning_rate | 4.59e-05 | +| loss | -0.0311 | +| n_updates | 49368 | +| policy_gradient_loss | -0.022 | +| value_loss | 7.4e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1422 | +| iterations | 8389 | +| time_elapsed | 12074 | +| total_timesteps | 17180672 | +| train/ | | +| approx_kl | 0.01212251 | +| clip_fraction | 0.31 | +| clip_range | 0.0707 | +| entropy_loss | -6.1 | +| explained_variance | 0.388 | +| learning_rate | 4.59e-05 | +| loss | -0.02 | +| n_updates | 49372 | +| policy_gradient_loss | -0.0145 | +| value_loss | 0.00031 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1422 | +| iterations | 8390 | +| time_elapsed | 12075 | +| total_timesteps | 17182720 | +| train/ | | +| approx_kl | 0.014402636 | +| clip_fraction | 0.37 | +| clip_range | 0.0707 | +| entropy_loss | -6.34 | +| explained_variance | 0.439 | +| learning_rate | 4.59e-05 | +| loss | -0.0303 | +| n_updates | 49376 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000139 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1422 | +| iterations | 8391 | +| time_elapsed | 12077 | +| total_timesteps | 17184768 | +| train/ | | +| approx_kl | 0.011858754 | +| clip_fraction | 0.354 | +| clip_range | 0.0707 | +| entropy_loss | -6.48 | +| explained_variance | 0.311 | +| learning_rate | 4.59e-05 | +| loss | -0.025 | +| n_updates | 49380 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000316 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1422 | +| iterations | 8392 | +| time_elapsed | 12078 | +| total_timesteps | 17186816 | +| train/ | | +| approx_kl | 0.010756842 | +| clip_fraction | 0.338 | +| clip_range | 0.0707 | +| entropy_loss | -6.91 | +| explained_variance | 0.217 | +| learning_rate | 4.59e-05 | +| loss | -0.0236 | +| n_updates | 49384 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000193 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1422 | +| iterations | 8393 | +| time_elapsed | 12079 | +| total_timesteps | 17188864 | +| train/ | | +| approx_kl | 0.012161482 | +| clip_fraction | 0.323 | +| clip_range | 0.0707 | +| entropy_loss | -7.14 | +| explained_variance | -0.124 | +| learning_rate | 4.59e-05 | +| loss | -0.0338 | +| n_updates | 49388 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000227 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1422 | +| iterations | 8394 | +| time_elapsed | 12081 | +| total_timesteps | 17190912 | +| train/ | | +| approx_kl | 0.014425017 | +| clip_fraction | 0.368 | +| clip_range | 0.0707 | +| entropy_loss | -6.54 | +| explained_variance | 0.687 | +| learning_rate | 4.59e-05 | +| loss | -0.0322 | +| n_updates | 49392 | +| policy_gradient_loss | -0.0216 | +| value_loss | 9.13e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1422 | +| iterations | 8395 | +| time_elapsed | 12082 | +| total_timesteps | 17192960 | +| train/ | | +| approx_kl | 0.01286301 | +| clip_fraction | 0.343 | +| clip_range | 0.0707 | +| entropy_loss | -6.86 | +| explained_variance | 0.222 | +| learning_rate | 4.59e-05 | +| loss | -0.0347 | +| n_updates | 49396 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000148 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1422 | +| iterations | 8396 | +| time_elapsed | 12084 | +| total_timesteps | 17195008 | +| train/ | | +| approx_kl | 0.0115150735 | +| clip_fraction | 0.319 | +| clip_range | 0.0707 | +| entropy_loss | -6.98 | +| explained_variance | 0.331 | +| learning_rate | 4.59e-05 | +| loss | -0.0283 | +| n_updates | 49400 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000143 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1422 | +| iterations | 8397 | +| time_elapsed | 12085 | +| total_timesteps | 17197056 | +| train/ | | +| approx_kl | 0.011755831 | +| clip_fraction | 0.344 | +| clip_range | 0.0707 | +| entropy_loss | -6.37 | +| explained_variance | 0.723 | +| learning_rate | 4.59e-05 | +| loss | -0.0298 | +| n_updates | 49404 | +| policy_gradient_loss | -0.0196 | +| value_loss | 9.59e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 1422 | +| iterations | 8398 | +| time_elapsed | 12087 | +| total_timesteps | 17199104 | +| train/ | | +| approx_kl | 0.013043926 | +| clip_fraction | 0.366 | +| clip_range | 0.0707 | +| entropy_loss | -6.77 | +| explained_variance | 0.474 | +| learning_rate | 4.59e-05 | +| loss | -0.031 | +| n_updates | 49408 | +| policy_gradient_loss | -0.0199 | +| value_loss | 7.53e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.306 | +| time/ | | +| fps | 1422 | +| iterations | 8399 | +| time_elapsed | 12088 | +| total_timesteps | 17201152 | +| train/ | | +| approx_kl | 0.013008436 | +| clip_fraction | 0.324 | +| clip_range | 0.0707 | +| entropy_loss | -6.57 | +| explained_variance | 0.575 | +| learning_rate | 4.59e-05 | +| loss | -0.0294 | +| n_updates | 49412 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.00012 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.306 | +| time/ | | +| fps | 1422 | +| iterations | 8400 | +| time_elapsed | 12089 | +| total_timesteps | 17203200 | +| train/ | | +| approx_kl | 0.014695821 | +| clip_fraction | 0.373 | +| clip_range | 0.0707 | +| entropy_loss | -6.34 | +| explained_variance | 0.687 | +| learning_rate | 4.59e-05 | +| loss | -0.0303 | +| n_updates | 49416 | +| policy_gradient_loss | -0.0196 | +| value_loss | 9.75e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.306 | +| time/ | | +| fps | 1422 | +| iterations | 8401 | +| time_elapsed | 12091 | +| total_timesteps | 17205248 | +| train/ | | +| approx_kl | 0.013200812 | +| clip_fraction | 0.363 | +| clip_range | 0.0707 | +| entropy_loss | -6.77 | +| explained_variance | -0.00576 | +| learning_rate | 4.59e-05 | +| loss | -0.0326 | +| n_updates | 49420 | +| policy_gradient_loss | -0.0209 | +| value_loss | 7.97e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.306 | +| time/ | | +| fps | 1422 | +| iterations | 8402 | +| time_elapsed | 12092 | +| total_timesteps | 17207296 | +| train/ | | +| approx_kl | 0.012850026 | +| clip_fraction | 0.348 | +| clip_range | 0.0707 | +| entropy_loss | -6.68 | +| explained_variance | 0.462 | +| learning_rate | 4.59e-05 | +| loss | -0.0289 | +| n_updates | 49424 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000182 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1422 | +| iterations | 8403 | +| time_elapsed | 12094 | +| total_timesteps | 17209344 | +| train/ | | +| approx_kl | 0.014266901 | +| clip_fraction | 0.349 | +| clip_range | 0.0707 | +| entropy_loss | -6.76 | +| explained_variance | 0.414 | +| learning_rate | 4.59e-05 | +| loss | -0.0309 | +| n_updates | 49428 | +| policy_gradient_loss | -0.0199 | +| value_loss | 9.66e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1422 | +| iterations | 8404 | +| time_elapsed | 12095 | +| total_timesteps | 17211392 | +| train/ | | +| approx_kl | 0.012161801 | +| clip_fraction | 0.343 | +| clip_range | 0.0707 | +| entropy_loss | -6.8 | +| explained_variance | 0.262 | +| learning_rate | 4.59e-05 | +| loss | -0.031 | +| n_updates | 49432 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000196 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1422 | +| iterations | 8405 | +| time_elapsed | 12097 | +| total_timesteps | 17213440 | +| train/ | | +| approx_kl | 0.0122338105 | +| clip_fraction | 0.342 | +| clip_range | 0.0707 | +| entropy_loss | -6.36 | +| explained_variance | 0.483 | +| learning_rate | 4.59e-05 | +| loss | -0.0283 | +| n_updates | 49436 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000129 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1422 | +| iterations | 8406 | +| time_elapsed | 12098 | +| total_timesteps | 17215488 | +| train/ | | +| approx_kl | 0.0138440635 | +| clip_fraction | 0.389 | +| clip_range | 0.0707 | +| entropy_loss | -6.54 | +| explained_variance | 0.0359 | +| learning_rate | 4.59e-05 | +| loss | -0.0279 | +| n_updates | 49440 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000194 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 1422 | +| iterations | 8407 | +| time_elapsed | 12099 | +| total_timesteps | 17217536 | +| train/ | | +| approx_kl | 0.015879977 | +| clip_fraction | 0.4 | +| clip_range | 0.0707 | +| entropy_loss | -6.22 | +| explained_variance | 0.787 | +| learning_rate | 4.59e-05 | +| loss | -0.0403 | +| n_updates | 49444 | +| policy_gradient_loss | -0.0251 | +| value_loss | 6.08e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1422 | +| iterations | 8408 | +| time_elapsed | 12101 | +| total_timesteps | 17219584 | +| train/ | | +| approx_kl | 0.013978913 | +| clip_fraction | 0.356 | +| clip_range | 0.0707 | +| entropy_loss | -6.64 | +| explained_variance | 0.393 | +| learning_rate | 4.59e-05 | +| loss | -0.0319 | +| n_updates | 49448 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000132 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1422 | +| iterations | 8409 | +| time_elapsed | 12102 | +| total_timesteps | 17221632 | +| train/ | | +| approx_kl | 0.012070115 | +| clip_fraction | 0.332 | +| clip_range | 0.0707 | +| entropy_loss | -6.41 | +| explained_variance | 0.383 | +| learning_rate | 4.59e-05 | +| loss | -0.0211 | +| n_updates | 49452 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000221 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1422 | +| iterations | 8410 | +| time_elapsed | 12104 | +| total_timesteps | 17223680 | +| train/ | | +| approx_kl | 0.014588783 | +| clip_fraction | 0.342 | +| clip_range | 0.0707 | +| entropy_loss | -6.41 | +| explained_variance | 0.675 | +| learning_rate | 4.59e-05 | +| loss | -0.0279 | +| n_updates | 49456 | +| policy_gradient_loss | -0.0198 | +| value_loss | 9.98e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 1422 | +| iterations | 8411 | +| time_elapsed | 12105 | +| total_timesteps | 17225728 | +| train/ | | +| approx_kl | 0.016673088 | +| clip_fraction | 0.382 | +| clip_range | 0.0707 | +| entropy_loss | -6.65 | +| explained_variance | 0.521 | +| learning_rate | 4.59e-05 | +| loss | -0.0345 | +| n_updates | 49460 | +| policy_gradient_loss | -0.0239 | +| value_loss | 5.82e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.304 | +| time/ | | +| fps | 1422 | +| iterations | 8412 | +| time_elapsed | 12107 | +| total_timesteps | 17227776 | +| train/ | | +| approx_kl | 0.015876098 | +| clip_fraction | 0.345 | +| clip_range | 0.0707 | +| entropy_loss | -6.73 | +| explained_variance | 0.332 | +| learning_rate | 4.59e-05 | +| loss | -0.033 | +| n_updates | 49464 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000145 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.304 | +| time/ | | +| fps | 1422 | +| iterations | 8413 | +| time_elapsed | 12108 | +| total_timesteps | 17229824 | +| train/ | | +| approx_kl | 0.016338948 | +| clip_fraction | 0.369 | +| clip_range | 0.0707 | +| entropy_loss | -6.71 | +| explained_variance | 0.351 | +| learning_rate | 4.59e-05 | +| loss | -0.0287 | +| n_updates | 49468 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000141 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.3 | +| time/ | | +| fps | 1422 | +| iterations | 8414 | +| time_elapsed | 12109 | +| total_timesteps | 17231872 | +| train/ | | +| approx_kl | 0.0164301 | +| clip_fraction | 0.36 | +| clip_range | 0.0707 | +| entropy_loss | -6.91 | +| explained_variance | 0.25 | +| learning_rate | 4.59e-05 | +| loss | -0.0277 | +| n_updates | 49472 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000177 | +--------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.298 | +| time/ | | +| fps | 1422 | +| iterations | 8415 | +| time_elapsed | 12111 | +| total_timesteps | 17233920 | +| train/ | | +| approx_kl | 0.01219256 | +| clip_fraction | 0.356 | +| clip_range | 0.0707 | +| entropy_loss | -6.92 | +| explained_variance | 0.212 | +| learning_rate | 4.59e-05 | +| loss | -0.0333 | +| n_updates | 49476 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.00023 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.3 | +| time/ | | +| fps | 1422 | +| iterations | 8416 | +| time_elapsed | 12112 | +| total_timesteps | 17235968 | +| train/ | | +| approx_kl | 0.012726274 | +| clip_fraction | 0.33 | +| clip_range | 0.0707 | +| entropy_loss | -6.41 | +| explained_variance | 0.37 | +| learning_rate | 4.59e-05 | +| loss | -0.0321 | +| n_updates | 49480 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000288 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.293 | +| time/ | | +| fps | 1422 | +| iterations | 8417 | +| time_elapsed | 12114 | +| total_timesteps | 17238016 | +| train/ | | +| approx_kl | 0.01429323 | +| clip_fraction | 0.383 | +| clip_range | 0.0707 | +| entropy_loss | -6.57 | +| explained_variance | 0.497 | +| learning_rate | 4.59e-05 | +| loss | -0.0353 | +| n_updates | 49484 | +| policy_gradient_loss | -0.0222 | +| value_loss | 0.000145 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 1422 | +| iterations | 8418 | +| time_elapsed | 12115 | +| total_timesteps | 17240064 | +| train/ | | +| approx_kl | 0.013286237 | +| clip_fraction | 0.385 | +| clip_range | 0.0707 | +| entropy_loss | -6.61 | +| explained_variance | 0.367 | +| learning_rate | 4.59e-05 | +| loss | -0.0423 | +| n_updates | 49488 | +| policy_gradient_loss | -0.0238 | +| value_loss | 8.55e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 1422 | +| iterations | 8419 | +| time_elapsed | 12117 | +| total_timesteps | 17242112 | +| train/ | | +| approx_kl | 0.013489162 | +| clip_fraction | 0.346 | +| clip_range | 0.0707 | +| entropy_loss | -6.46 | +| explained_variance | 0.346 | +| learning_rate | 4.59e-05 | +| loss | -0.0267 | +| n_updates | 49492 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000268 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 1422 | +| iterations | 8420 | +| time_elapsed | 12118 | +| total_timesteps | 17244160 | +| train/ | | +| approx_kl | 0.015689174 | +| clip_fraction | 0.346 | +| clip_range | 0.0707 | +| entropy_loss | -6.44 | +| explained_variance | 0.319 | +| learning_rate | 4.59e-05 | +| loss | -0.0352 | +| n_updates | 49496 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000134 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1422 | +| iterations | 8421 | +| time_elapsed | 12120 | +| total_timesteps | 17246208 | +| train/ | | +| approx_kl | 0.013899818 | +| clip_fraction | 0.36 | +| clip_range | 0.0707 | +| entropy_loss | -6.66 | +| explained_variance | 0.316 | +| learning_rate | 4.59e-05 | +| loss | -0.0253 | +| n_updates | 49500 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000148 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.306 | +| time/ | | +| fps | 1422 | +| iterations | 8422 | +| time_elapsed | 12121 | +| total_timesteps | 17248256 | +| train/ | | +| approx_kl | 0.013862426 | +| clip_fraction | 0.36 | +| clip_range | 0.0707 | +| entropy_loss | -6.35 | +| explained_variance | 0.558 | +| learning_rate | 4.59e-05 | +| loss | -0.0406 | +| n_updates | 49504 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.00011 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.302 | +| time/ | | +| fps | 1422 | +| iterations | 8423 | +| time_elapsed | 12122 | +| total_timesteps | 17250304 | +| train/ | | +| approx_kl | 0.013896532 | +| clip_fraction | 0.331 | +| clip_range | 0.0707 | +| entropy_loss | -6.23 | +| explained_variance | 0.679 | +| learning_rate | 4.59e-05 | +| loss | -0.0358 | +| n_updates | 49508 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000107 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.302 | +| time/ | | +| fps | 1422 | +| iterations | 8424 | +| time_elapsed | 12124 | +| total_timesteps | 17252352 | +| train/ | | +| approx_kl | 0.013057142 | +| clip_fraction | 0.343 | +| clip_range | 0.0707 | +| entropy_loss | -6.35 | +| explained_variance | 0.519 | +| learning_rate | 4.59e-05 | +| loss | -0.0238 | +| n_updates | 49512 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000128 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.302 | +| time/ | | +| fps | 1422 | +| iterations | 8425 | +| time_elapsed | 12125 | +| total_timesteps | 17254400 | +| train/ | | +| approx_kl | 0.0132268155 | +| clip_fraction | 0.353 | +| clip_range | 0.0707 | +| entropy_loss | -6.58 | +| explained_variance | 0.417 | +| learning_rate | 4.59e-05 | +| loss | -0.0311 | +| n_updates | 49516 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000144 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 1422 | +| iterations | 8426 | +| time_elapsed | 12127 | +| total_timesteps | 17256448 | +| train/ | | +| approx_kl | 0.014970325 | +| clip_fraction | 0.366 | +| clip_range | 0.0707 | +| entropy_loss | -6.76 | +| explained_variance | -0.0599 | +| learning_rate | 4.59e-05 | +| loss | -0.0425 | +| n_updates | 49520 | +| policy_gradient_loss | -0.0216 | +| value_loss | 7.62e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 1422 | +| iterations | 8427 | +| time_elapsed | 12128 | +| total_timesteps | 17258496 | +| train/ | | +| approx_kl | 0.015242797 | +| clip_fraction | 0.369 | +| clip_range | 0.0707 | +| entropy_loss | -6.56 | +| explained_variance | 0.414 | +| learning_rate | 4.59e-05 | +| loss | -0.0357 | +| n_updates | 49524 | +| policy_gradient_loss | -0.0207 | +| value_loss | 8.82e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 1422 | +| iterations | 8428 | +| time_elapsed | 12130 | +| total_timesteps | 17260544 | +| train/ | | +| approx_kl | 0.011693223 | +| clip_fraction | 0.328 | +| clip_range | 0.0707 | +| entropy_loss | -6.19 | +| explained_variance | 0.509 | +| learning_rate | 4.59e-05 | +| loss | -0.021 | +| n_updates | 49528 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000229 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 1422 | +| iterations | 8429 | +| time_elapsed | 12131 | +| total_timesteps | 17262592 | +| train/ | | +| approx_kl | 0.013041225 | +| clip_fraction | 0.349 | +| clip_range | 0.0707 | +| entropy_loss | -6.43 | +| explained_variance | 0.61 | +| learning_rate | 4.59e-05 | +| loss | -0.0319 | +| n_updates | 49532 | +| policy_gradient_loss | -0.021 | +| value_loss | 8.74e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.289 | +| time/ | | +| fps | 1422 | +| iterations | 8430 | +| time_elapsed | 12133 | +| total_timesteps | 17264640 | +| train/ | | +| approx_kl | 0.013165669 | +| clip_fraction | 0.361 | +| clip_range | 0.0707 | +| entropy_loss | -6.78 | +| explained_variance | 0.205 | +| learning_rate | 4.59e-05 | +| loss | -0.0362 | +| n_updates | 49536 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000171 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.287 | +| time/ | | +| fps | 1422 | +| iterations | 8431 | +| time_elapsed | 12134 | +| total_timesteps | 17266688 | +| train/ | | +| approx_kl | 0.013571082 | +| clip_fraction | 0.358 | +| clip_range | 0.0707 | +| entropy_loss | -6.85 | +| explained_variance | 0.206 | +| learning_rate | 4.59e-05 | +| loss | -0.0375 | +| n_updates | 49540 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.00017 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.287 | +| time/ | | +| fps | 1422 | +| iterations | 8432 | +| time_elapsed | 12135 | +| total_timesteps | 17268736 | +| train/ | | +| approx_kl | 0.012092313 | +| clip_fraction | 0.346 | +| clip_range | 0.0707 | +| entropy_loss | -6.66 | +| explained_variance | 0.353 | +| learning_rate | 4.59e-05 | +| loss | -0.0269 | +| n_updates | 49544 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000114 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.302 | +| time/ | | +| fps | 1422 | +| iterations | 8433 | +| time_elapsed | 12137 | +| total_timesteps | 17270784 | +| train/ | | +| approx_kl | 0.014886072 | +| clip_fraction | 0.362 | +| clip_range | 0.0707 | +| entropy_loss | -6.42 | +| explained_variance | 0.514 | +| learning_rate | 4.59e-05 | +| loss | -0.0355 | +| n_updates | 49548 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000136 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1422 | +| iterations | 8434 | +| time_elapsed | 12138 | +| total_timesteps | 17272832 | +| train/ | | +| approx_kl | 0.01640025 | +| clip_fraction | 0.298 | +| clip_range | 0.0707 | +| entropy_loss | -6.58 | +| explained_variance | 0.0578 | +| learning_rate | 4.59e-05 | +| loss | -0.0228 | +| n_updates | 49552 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.000347 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1422 | +| iterations | 8435 | +| time_elapsed | 12140 | +| total_timesteps | 17274880 | +| train/ | | +| approx_kl | 0.014273612 | +| clip_fraction | 0.364 | +| clip_range | 0.0707 | +| entropy_loss | -6.15 | +| explained_variance | 0.283 | +| learning_rate | 4.59e-05 | +| loss | -0.0291 | +| n_updates | 49556 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000261 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1422 | +| iterations | 8436 | +| time_elapsed | 12141 | +| total_timesteps | 17276928 | +| train/ | | +| approx_kl | 0.012524842 | +| clip_fraction | 0.365 | +| clip_range | 0.0707 | +| entropy_loss | -6.66 | +| explained_variance | 0.329 | +| learning_rate | 4.59e-05 | +| loss | -0.0357 | +| n_updates | 49560 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000198 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1422 | +| iterations | 8437 | +| time_elapsed | 12143 | +| total_timesteps | 17278976 | +| train/ | | +| approx_kl | 0.012205388 | +| clip_fraction | 0.364 | +| clip_range | 0.0707 | +| entropy_loss | -6.92 | +| explained_variance | -0.224 | +| learning_rate | 4.59e-05 | +| loss | -0.0326 | +| n_updates | 49564 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000145 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1422 | +| iterations | 8438 | +| time_elapsed | 12144 | +| total_timesteps | 17281024 | +| train/ | | +| approx_kl | 0.0117226895 | +| clip_fraction | 0.349 | +| clip_range | 0.0707 | +| entropy_loss | -6.8 | +| explained_variance | 0.418 | +| learning_rate | 4.59e-05 | +| loss | -0.0278 | +| n_updates | 49568 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000205 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1422 | +| iterations | 8439 | +| time_elapsed | 12145 | +| total_timesteps | 17283072 | +| train/ | | +| approx_kl | 0.013905233 | +| clip_fraction | 0.337 | +| clip_range | 0.0707 | +| entropy_loss | -6.44 | +| explained_variance | 0.388 | +| learning_rate | 4.59e-05 | +| loss | -0.0314 | +| n_updates | 49572 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000191 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1422 | +| iterations | 8440 | +| time_elapsed | 12147 | +| total_timesteps | 17285120 | +| train/ | | +| approx_kl | 0.01623207 | +| clip_fraction | 0.333 | +| clip_range | 0.0707 | +| entropy_loss | -6.44 | +| explained_variance | 0.28 | +| learning_rate | 4.59e-05 | +| loss | -0.0255 | +| n_updates | 49576 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000314 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1422 | +| iterations | 8441 | +| time_elapsed | 12148 | +| total_timesteps | 17287168 | +| train/ | | +| approx_kl | 0.011607267 | +| clip_fraction | 0.366 | +| clip_range | 0.0707 | +| entropy_loss | -6.61 | +| explained_variance | -0.239 | +| learning_rate | 4.59e-05 | +| loss | -0.0306 | +| n_updates | 49580 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000206 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1422 | +| iterations | 8442 | +| time_elapsed | 12150 | +| total_timesteps | 17289216 | +| train/ | | +| approx_kl | 0.012555281 | +| clip_fraction | 0.354 | +| clip_range | 0.0707 | +| entropy_loss | -6.82 | +| explained_variance | 0.234 | +| learning_rate | 4.59e-05 | +| loss | -0.0373 | +| n_updates | 49584 | +| policy_gradient_loss | -0.0223 | +| value_loss | 0.000163 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1422 | +| iterations | 8443 | +| time_elapsed | 12151 | +| total_timesteps | 17291264 | +| train/ | | +| approx_kl | 0.011184106 | +| clip_fraction | 0.333 | +| clip_range | 0.0707 | +| entropy_loss | -6.8 | +| explained_variance | 0.149 | +| learning_rate | 4.59e-05 | +| loss | -0.0348 | +| n_updates | 49588 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000359 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1422 | +| iterations | 8444 | +| time_elapsed | 12153 | +| total_timesteps | 17293312 | +| train/ | | +| approx_kl | 0.01495729 | +| clip_fraction | 0.354 | +| clip_range | 0.0707 | +| entropy_loss | -6.76 | +| explained_variance | 0.263 | +| learning_rate | 4.59e-05 | +| loss | -0.0335 | +| n_updates | 49592 | +| policy_gradient_loss | -0.0221 | +| value_loss | 0.000146 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1422 | +| iterations | 8445 | +| time_elapsed | 12154 | +| total_timesteps | 17295360 | +| train/ | | +| approx_kl | 0.0126576945 | +| clip_fraction | 0.339 | +| clip_range | 0.0707 | +| entropy_loss | -6.65 | +| explained_variance | 0.496 | +| learning_rate | 4.59e-05 | +| loss | -0.0288 | +| n_updates | 49596 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000144 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1422 | +| iterations | 8446 | +| time_elapsed | 12156 | +| total_timesteps | 17297408 | +| train/ | | +| approx_kl | 0.011728551 | +| clip_fraction | 0.343 | +| clip_range | 0.0707 | +| entropy_loss | -6.12 | +| explained_variance | 0.73 | +| learning_rate | 4.59e-05 | +| loss | -0.0303 | +| n_updates | 49600 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000105 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1422 | +| iterations | 8447 | +| time_elapsed | 12157 | +| total_timesteps | 17299456 | +| train/ | | +| approx_kl | 0.012659447 | +| clip_fraction | 0.316 | +| clip_range | 0.0707 | +| entropy_loss | -6.37 | +| explained_variance | 0.519 | +| learning_rate | 4.59e-05 | +| loss | -0.0239 | +| n_updates | 49604 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.0002 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1422 | +| iterations | 8448 | +| time_elapsed | 12159 | +| total_timesteps | 17301504 | +| train/ | | +| approx_kl | 0.013613399 | +| clip_fraction | 0.352 | +| clip_range | 0.0707 | +| entropy_loss | -6.42 | +| explained_variance | 0.494 | +| learning_rate | 4.59e-05 | +| loss | -0.0343 | +| n_updates | 49608 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000173 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1422 | +| iterations | 8449 | +| time_elapsed | 12160 | +| total_timesteps | 17303552 | +| train/ | | +| approx_kl | 0.01242205 | +| clip_fraction | 0.334 | +| clip_range | 0.0707 | +| entropy_loss | -6.99 | +| explained_variance | 0.344 | +| learning_rate | 4.59e-05 | +| loss | -0.0323 | +| n_updates | 49612 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000161 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1422 | +| iterations | 8450 | +| time_elapsed | 12162 | +| total_timesteps | 17305600 | +| train/ | | +| approx_kl | 0.013823891 | +| clip_fraction | 0.373 | +| clip_range | 0.0707 | +| entropy_loss | -7.01 | +| explained_variance | -0.174 | +| learning_rate | 4.59e-05 | +| loss | -0.0335 | +| n_updates | 49616 | +| policy_gradient_loss | -0.0226 | +| value_loss | 9.66e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1422 | +| iterations | 8451 | +| time_elapsed | 12163 | +| total_timesteps | 17307648 | +| train/ | | +| approx_kl | 0.013381902 | +| clip_fraction | 0.362 | +| clip_range | 0.0707 | +| entropy_loss | -7.03 | +| explained_variance | 0.466 | +| learning_rate | 4.59e-05 | +| loss | -0.0358 | +| n_updates | 49620 | +| policy_gradient_loss | -0.0219 | +| value_loss | 7.02e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1422 | +| iterations | 8452 | +| time_elapsed | 12164 | +| total_timesteps | 17309696 | +| train/ | | +| approx_kl | 0.013714943 | +| clip_fraction | 0.32 | +| clip_range | 0.0707 | +| entropy_loss | -6.74 | +| explained_variance | -0.00331 | +| learning_rate | 4.59e-05 | +| loss | -0.0289 | +| n_updates | 49624 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000186 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1422 | +| iterations | 8453 | +| time_elapsed | 12166 | +| total_timesteps | 17311744 | +| train/ | | +| approx_kl | 0.012991739 | +| clip_fraction | 0.348 | +| clip_range | 0.0707 | +| entropy_loss | -6.2 | +| explained_variance | 0.476 | +| learning_rate | 4.59e-05 | +| loss | -0.0262 | +| n_updates | 49628 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000178 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1422 | +| iterations | 8454 | +| time_elapsed | 12167 | +| total_timesteps | 17313792 | +| train/ | | +| approx_kl | 0.014672967 | +| clip_fraction | 0.372 | +| clip_range | 0.0707 | +| entropy_loss | -6.86 | +| explained_variance | 0.361 | +| learning_rate | 4.59e-05 | +| loss | -0.0395 | +| n_updates | 49632 | +| policy_gradient_loss | -0.0235 | +| value_loss | 5.21e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1422 | +| iterations | 8455 | +| time_elapsed | 12169 | +| total_timesteps | 17315840 | +| train/ | | +| approx_kl | 0.0146407345 | +| clip_fraction | 0.333 | +| clip_range | 0.0707 | +| entropy_loss | -6.38 | +| explained_variance | 0.471 | +| learning_rate | 4.59e-05 | +| loss | -0.0314 | +| n_updates | 49636 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.00019 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1422 | +| iterations | 8456 | +| time_elapsed | 12170 | +| total_timesteps | 17317888 | +| train/ | | +| approx_kl | 0.015273639 | +| clip_fraction | 0.368 | +| clip_range | 0.0707 | +| entropy_loss | -6.38 | +| explained_variance | 0.735 | +| learning_rate | 4.59e-05 | +| loss | -0.0315 | +| n_updates | 49640 | +| policy_gradient_loss | -0.0209 | +| value_loss | 6.6e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.315 | +| time/ | | +| fps | 1422 | +| iterations | 8457 | +| time_elapsed | 12172 | +| total_timesteps | 17319936 | +| train/ | | +| approx_kl | 0.012499581 | +| clip_fraction | 0.334 | +| clip_range | 0.0707 | +| entropy_loss | -6.36 | +| explained_variance | 0.382 | +| learning_rate | 4.59e-05 | +| loss | -0.0325 | +| n_updates | 49644 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000223 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.315 | +| time/ | | +| fps | 1422 | +| iterations | 8458 | +| time_elapsed | 12173 | +| total_timesteps | 17321984 | +| train/ | | +| approx_kl | 0.011114486 | +| clip_fraction | 0.319 | +| clip_range | 0.0707 | +| entropy_loss | -6.61 | +| explained_variance | 0.371 | +| learning_rate | 4.59e-05 | +| loss | -0.0264 | +| n_updates | 49648 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000244 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1422 | +| iterations | 8459 | +| time_elapsed | 12175 | +| total_timesteps | 17324032 | +| train/ | | +| approx_kl | 0.0122356415 | +| clip_fraction | 0.338 | +| clip_range | 0.0707 | +| entropy_loss | -6.65 | +| explained_variance | 0.365 | +| learning_rate | 4.59e-05 | +| loss | -0.0366 | +| n_updates | 49652 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000131 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1422 | +| iterations | 8460 | +| time_elapsed | 12176 | +| total_timesteps | 17326080 | +| train/ | | +| approx_kl | 0.009770245 | +| clip_fraction | 0.319 | +| clip_range | 0.0707 | +| entropy_loss | -6.57 | +| explained_variance | 0.317 | +| learning_rate | 4.59e-05 | +| loss | -0.0266 | +| n_updates | 49656 | +| policy_gradient_loss | -0.0138 | +| value_loss | 0.000424 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1422 | +| iterations | 8461 | +| time_elapsed | 12177 | +| total_timesteps | 17328128 | +| train/ | | +| approx_kl | 0.015096668 | +| clip_fraction | 0.359 | +| clip_range | 0.0707 | +| entropy_loss | -6.78 | +| explained_variance | 0.177 | +| learning_rate | 4.59e-05 | +| loss | -0.0361 | +| n_updates | 49660 | +| policy_gradient_loss | -0.023 | +| value_loss | 0.000188 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1422 | +| iterations | 8462 | +| time_elapsed | 12179 | +| total_timesteps | 17330176 | +| train/ | | +| approx_kl | 0.014553997 | +| clip_fraction | 0.357 | +| clip_range | 0.0707 | +| entropy_loss | -7 | +| explained_variance | -0.119 | +| learning_rate | 4.59e-05 | +| loss | -0.0345 | +| n_updates | 49664 | +| policy_gradient_loss | -0.0222 | +| value_loss | 0.000183 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1422 | +| iterations | 8463 | +| time_elapsed | 12180 | +| total_timesteps | 17332224 | +| train/ | | +| approx_kl | 0.01412937 | +| clip_fraction | 0.352 | +| clip_range | 0.0707 | +| entropy_loss | -6.87 | +| explained_variance | 0.273 | +| learning_rate | 4.59e-05 | +| loss | -0.0348 | +| n_updates | 49668 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000243 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1422 | +| iterations | 8464 | +| time_elapsed | 12182 | +| total_timesteps | 17334272 | +| train/ | | +| approx_kl | 0.012806127 | +| clip_fraction | 0.335 | +| clip_range | 0.0707 | +| entropy_loss | -6.23 | +| explained_variance | 0.496 | +| learning_rate | 4.59e-05 | +| loss | -0.0315 | +| n_updates | 49672 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000213 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1422 | +| iterations | 8465 | +| time_elapsed | 12183 | +| total_timesteps | 17336320 | +| train/ | | +| approx_kl | 0.012892366 | +| clip_fraction | 0.333 | +| clip_range | 0.0707 | +| entropy_loss | -6.18 | +| explained_variance | 0.313 | +| learning_rate | 4.59e-05 | +| loss | -0.0332 | +| n_updates | 49676 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000269 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1422 | +| iterations | 8466 | +| time_elapsed | 12185 | +| total_timesteps | 17338368 | +| train/ | | +| approx_kl | 0.015468121 | +| clip_fraction | 0.362 | +| clip_range | 0.0707 | +| entropy_loss | -6.19 | +| explained_variance | 0.638 | +| learning_rate | 4.59e-05 | +| loss | -0.0376 | +| n_updates | 49680 | +| policy_gradient_loss | -0.0232 | +| value_loss | 9.64e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1422 | +| iterations | 8467 | +| time_elapsed | 12186 | +| total_timesteps | 17340416 | +| train/ | | +| approx_kl | 0.013645443 | +| clip_fraction | 0.335 | +| clip_range | 0.0707 | +| entropy_loss | -6.66 | +| explained_variance | 0.256 | +| learning_rate | 4.59e-05 | +| loss | -0.032 | +| n_updates | 49684 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000141 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1422 | +| iterations | 8468 | +| time_elapsed | 12187 | +| total_timesteps | 17342464 | +| train/ | | +| approx_kl | 0.013303831 | +| clip_fraction | 0.347 | +| clip_range | 0.0707 | +| entropy_loss | -6.2 | +| explained_variance | 0.494 | +| learning_rate | 4.59e-05 | +| loss | -0.0286 | +| n_updates | 49688 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.00026 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1422 | +| iterations | 8469 | +| time_elapsed | 12189 | +| total_timesteps | 17344512 | +| train/ | | +| approx_kl | 0.012578266 | +| clip_fraction | 0.333 | +| clip_range | 0.0707 | +| entropy_loss | -6.51 | +| explained_variance | 0.166 | +| learning_rate | 4.59e-05 | +| loss | -0.0298 | +| n_updates | 49692 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000321 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1422 | +| iterations | 8470 | +| time_elapsed | 12190 | +| total_timesteps | 17346560 | +| train/ | | +| approx_kl | 0.009989811 | +| clip_fraction | 0.326 | +| clip_range | 0.0707 | +| entropy_loss | -6.66 | +| explained_variance | 0.252 | +| learning_rate | 4.59e-05 | +| loss | -0.0217 | +| n_updates | 49696 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000461 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1422 | +| iterations | 8471 | +| time_elapsed | 12192 | +| total_timesteps | 17348608 | +| train/ | | +| approx_kl | 0.013815493 | +| clip_fraction | 0.37 | +| clip_range | 0.0707 | +| entropy_loss | -6.82 | +| explained_variance | 0.38 | +| learning_rate | 4.59e-05 | +| loss | -0.0385 | +| n_updates | 49700 | +| policy_gradient_loss | -0.0225 | +| value_loss | 0.00013 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1422 | +| iterations | 8472 | +| time_elapsed | 12193 | +| total_timesteps | 17350656 | +| train/ | | +| approx_kl | 0.010446623 | +| clip_fraction | 0.366 | +| clip_range | 0.0707 | +| entropy_loss | -7.02 | +| explained_variance | 0.0746 | +| learning_rate | 4.59e-05 | +| loss | -0.0331 | +| n_updates | 49704 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000128 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1422 | +| iterations | 8473 | +| time_elapsed | 12195 | +| total_timesteps | 17352704 | +| train/ | | +| approx_kl | 0.011343388 | +| clip_fraction | 0.327 | +| clip_range | 0.0707 | +| entropy_loss | -6.74 | +| explained_variance | 0.284 | +| learning_rate | 4.59e-05 | +| loss | -0.023 | +| n_updates | 49708 | +| policy_gradient_loss | -0.0146 | +| value_loss | 0.000377 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1422 | +| iterations | 8474 | +| time_elapsed | 12196 | +| total_timesteps | 17354752 | +| train/ | | +| approx_kl | 0.011012248 | +| clip_fraction | 0.344 | +| clip_range | 0.0707 | +| entropy_loss | -6.36 | +| explained_variance | 0.471 | +| learning_rate | 4.59e-05 | +| loss | -0.0246 | +| n_updates | 49712 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000253 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1422 | +| iterations | 8475 | +| time_elapsed | 12197 | +| total_timesteps | 17356800 | +| train/ | | +| approx_kl | 0.011664363 | +| clip_fraction | 0.359 | +| clip_range | 0.0707 | +| entropy_loss | -6.08 | +| explained_variance | 0.646 | +| learning_rate | 4.59e-05 | +| loss | -0.032 | +| n_updates | 49716 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000121 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1422 | +| iterations | 8476 | +| time_elapsed | 12199 | +| total_timesteps | 17358848 | +| train/ | | +| approx_kl | 0.014044357 | +| clip_fraction | 0.375 | +| clip_range | 0.0707 | +| entropy_loss | -6.64 | +| explained_variance | 0.257 | +| learning_rate | 4.59e-05 | +| loss | -0.0396 | +| n_updates | 49720 | +| policy_gradient_loss | -0.0221 | +| value_loss | 0.000118 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1422 | +| iterations | 8477 | +| time_elapsed | 12200 | +| total_timesteps | 17360896 | +| train/ | | +| approx_kl | 0.013937186 | +| clip_fraction | 0.34 | +| clip_range | 0.0707 | +| entropy_loss | -6.48 | +| explained_variance | 0.601 | +| learning_rate | 4.59e-05 | +| loss | -0.0317 | +| n_updates | 49724 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000133 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1422 | +| iterations | 8478 | +| time_elapsed | 12202 | +| total_timesteps | 17362944 | +| train/ | | +| approx_kl | 0.012376128 | +| clip_fraction | 0.345 | +| clip_range | 0.0707 | +| entropy_loss | -6.48 | +| explained_variance | 0.049 | +| learning_rate | 4.59e-05 | +| loss | -0.026 | +| n_updates | 49728 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000223 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1422 | +| iterations | 8479 | +| time_elapsed | 12203 | +| total_timesteps | 17364992 | +| train/ | | +| approx_kl | 0.014481671 | +| clip_fraction | 0.379 | +| clip_range | 0.0707 | +| entropy_loss | -6.74 | +| explained_variance | -0.00863 | +| learning_rate | 4.59e-05 | +| loss | -0.0392 | +| n_updates | 49732 | +| policy_gradient_loss | -0.0222 | +| value_loss | 0.000119 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1422 | +| iterations | 8480 | +| time_elapsed | 12205 | +| total_timesteps | 17367040 | +| train/ | | +| approx_kl | 0.014821577 | +| clip_fraction | 0.344 | +| clip_range | 0.0707 | +| entropy_loss | -6.39 | +| explained_variance | 0.296 | +| learning_rate | 4.59e-05 | +| loss | -0.0227 | +| n_updates | 49736 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000258 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1422 | +| iterations | 8481 | +| time_elapsed | 12206 | +| total_timesteps | 17369088 | +| train/ | | +| approx_kl | 0.016048947 | +| clip_fraction | 0.377 | +| clip_range | 0.0707 | +| entropy_loss | -6.65 | +| explained_variance | -0.0702 | +| learning_rate | 4.59e-05 | +| loss | -0.0373 | +| n_updates | 49740 | +| policy_gradient_loss | -0.0234 | +| value_loss | 0.00011 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1422 | +| iterations | 8482 | +| time_elapsed | 12207 | +| total_timesteps | 17371136 | +| train/ | | +| approx_kl | 0.013415944 | +| clip_fraction | 0.346 | +| clip_range | 0.0707 | +| entropy_loss | -6.44 | +| explained_variance | 0.305 | +| learning_rate | 4.59e-05 | +| loss | -0.0265 | +| n_updates | 49744 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000228 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1422 | +| iterations | 8483 | +| time_elapsed | 12209 | +| total_timesteps | 17373184 | +| train/ | | +| approx_kl | 0.013840171 | +| clip_fraction | 0.356 | +| clip_range | 0.0707 | +| entropy_loss | -6.52 | +| explained_variance | 0.284 | +| learning_rate | 4.59e-05 | +| loss | -0.036 | +| n_updates | 49748 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000132 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1422 | +| iterations | 8484 | +| time_elapsed | 12210 | +| total_timesteps | 17375232 | +| train/ | | +| approx_kl | 0.016208088 | +| clip_fraction | 0.378 | +| clip_range | 0.0707 | +| entropy_loss | -6.83 | +| explained_variance | -0.182 | +| learning_rate | 4.59e-05 | +| loss | -0.0374 | +| n_updates | 49752 | +| policy_gradient_loss | -0.0232 | +| value_loss | 8.39e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1422 | +| iterations | 8485 | +| time_elapsed | 12212 | +| total_timesteps | 17377280 | +| train/ | | +| approx_kl | 0.014205188 | +| clip_fraction | 0.345 | +| clip_range | 0.0707 | +| entropy_loss | -6.36 | +| explained_variance | 0.394 | +| learning_rate | 4.59e-05 | +| loss | -0.034 | +| n_updates | 49756 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000169 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1422 | +| iterations | 8486 | +| time_elapsed | 12213 | +| total_timesteps | 17379328 | +| train/ | | +| approx_kl | 0.011075245 | +| clip_fraction | 0.342 | +| clip_range | 0.0707 | +| entropy_loss | -6.46 | +| explained_variance | 0.499 | +| learning_rate | 4.59e-05 | +| loss | -0.0279 | +| n_updates | 49760 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000135 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1422 | +| iterations | 8487 | +| time_elapsed | 12215 | +| total_timesteps | 17381376 | +| train/ | | +| approx_kl | 0.015803691 | +| clip_fraction | 0.347 | +| clip_range | 0.0707 | +| entropy_loss | -6.08 | +| explained_variance | 0.596 | +| learning_rate | 4.59e-05 | +| loss | -0.0358 | +| n_updates | 49764 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000113 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1422 | +| iterations | 8488 | +| time_elapsed | 12216 | +| total_timesteps | 17383424 | +| train/ | | +| approx_kl | 0.015928306 | +| clip_fraction | 0.399 | +| clip_range | 0.0707 | +| entropy_loss | -6.24 | +| explained_variance | 0.599 | +| learning_rate | 4.59e-05 | +| loss | -0.0302 | +| n_updates | 49768 | +| policy_gradient_loss | -0.0236 | +| value_loss | 8.54e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1422 | +| iterations | 8489 | +| time_elapsed | 12217 | +| total_timesteps | 17385472 | +| train/ | | +| approx_kl | 0.016034378 | +| clip_fraction | 0.342 | +| clip_range | 0.0707 | +| entropy_loss | -6.44 | +| explained_variance | -0.08 | +| learning_rate | 4.59e-05 | +| loss | -0.0231 | +| n_updates | 49772 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000168 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1422 | +| iterations | 8490 | +| time_elapsed | 12219 | +| total_timesteps | 17387520 | +| train/ | | +| approx_kl | 0.017071217 | +| clip_fraction | 0.368 | +| clip_range | 0.0707 | +| entropy_loss | -6.64 | +| explained_variance | -0.357 | +| learning_rate | 4.59e-05 | +| loss | -0.0337 | +| n_updates | 49776 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000134 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1422 | +| iterations | 8491 | +| time_elapsed | 12220 | +| total_timesteps | 17389568 | +| train/ | | +| approx_kl | 0.013156305 | +| clip_fraction | 0.356 | +| clip_range | 0.0707 | +| entropy_loss | -6.89 | +| explained_variance | 0.139 | +| learning_rate | 4.59e-05 | +| loss | -0.0225 | +| n_updates | 49780 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000324 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1422 | +| iterations | 8492 | +| time_elapsed | 12222 | +| total_timesteps | 17391616 | +| train/ | | +| approx_kl | 0.014250242 | +| clip_fraction | 0.377 | +| clip_range | 0.0707 | +| entropy_loss | -6.69 | +| explained_variance | 0.189 | +| learning_rate | 4.59e-05 | +| loss | -0.0316 | +| n_updates | 49784 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000201 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1422 | +| iterations | 8493 | +| time_elapsed | 12223 | +| total_timesteps | 17393664 | +| train/ | | +| approx_kl | 0.014219444 | +| clip_fraction | 0.352 | +| clip_range | 0.0707 | +| entropy_loss | -6.51 | +| explained_variance | 0.321 | +| learning_rate | 4.59e-05 | +| loss | -0.0325 | +| n_updates | 49788 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000269 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1422 | +| iterations | 8494 | +| time_elapsed | 12225 | +| total_timesteps | 17395712 | +| train/ | | +| approx_kl | 0.013464515 | +| clip_fraction | 0.353 | +| clip_range | 0.0707 | +| entropy_loss | -6.51 | +| explained_variance | 0.282 | +| learning_rate | 4.59e-05 | +| loss | -0.0292 | +| n_updates | 49792 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000145 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1422 | +| iterations | 8495 | +| time_elapsed | 12226 | +| total_timesteps | 17397760 | +| train/ | | +| approx_kl | 0.0127300415 | +| clip_fraction | 0.353 | +| clip_range | 0.0707 | +| entropy_loss | -6.69 | +| explained_variance | 0.465 | +| learning_rate | 4.59e-05 | +| loss | -0.0376 | +| n_updates | 49796 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000172 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1422 | +| iterations | 8496 | +| time_elapsed | 12228 | +| total_timesteps | 17399808 | +| train/ | | +| approx_kl | 0.013578594 | +| clip_fraction | 0.334 | +| clip_range | 0.0707 | +| entropy_loss | -6.87 | +| explained_variance | -0.0634 | +| learning_rate | 4.59e-05 | +| loss | -0.034 | +| n_updates | 49800 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000195 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1422 | +| iterations | 8497 | +| time_elapsed | 12229 | +| total_timesteps | 17401856 | +| train/ | | +| approx_kl | 0.012079307 | +| clip_fraction | 0.344 | +| clip_range | 0.0707 | +| entropy_loss | -6.22 | +| explained_variance | 0.579 | +| learning_rate | 4.59e-05 | +| loss | -0.0336 | +| n_updates | 49804 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000181 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1422 | +| iterations | 8498 | +| time_elapsed | 12230 | +| total_timesteps | 17403904 | +| train/ | | +| approx_kl | 0.0135072 | +| clip_fraction | 0.369 | +| clip_range | 0.0706 | +| entropy_loss | -6.49 | +| explained_variance | 0.582 | +| learning_rate | 4.59e-05 | +| loss | -0.0332 | +| n_updates | 49808 | +| policy_gradient_loss | -0.0222 | +| value_loss | 9.51e-05 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1422 | +| iterations | 8499 | +| time_elapsed | 12232 | +| total_timesteps | 17405952 | +| train/ | | +| approx_kl | 0.013067229 | +| clip_fraction | 0.374 | +| clip_range | 0.0706 | +| entropy_loss | -6.94 | +| explained_variance | -0.173 | +| learning_rate | 4.59e-05 | +| loss | -0.0412 | +| n_updates | 49812 | +| policy_gradient_loss | -0.0231 | +| value_loss | 6.87e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1422 | +| iterations | 8500 | +| time_elapsed | 12233 | +| total_timesteps | 17408000 | +| train/ | | +| approx_kl | 0.010556728 | +| clip_fraction | 0.312 | +| clip_range | 0.0706 | +| entropy_loss | -6.19 | +| explained_variance | 0.439 | +| learning_rate | 4.59e-05 | +| loss | -0.0258 | +| n_updates | 49816 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000231 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1422 | +| iterations | 8501 | +| time_elapsed | 12235 | +| total_timesteps | 17410048 | +| train/ | | +| approx_kl | 0.015190618 | +| clip_fraction | 0.35 | +| clip_range | 0.0706 | +| entropy_loss | -6.87 | +| explained_variance | -0.0722 | +| learning_rate | 4.59e-05 | +| loss | -0.0391 | +| n_updates | 49820 | +| policy_gradient_loss | -0.0214 | +| value_loss | 7.59e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1422 | +| iterations | 8502 | +| time_elapsed | 12236 | +| total_timesteps | 17412096 | +| train/ | | +| approx_kl | 0.013485879 | +| clip_fraction | 0.357 | +| clip_range | 0.0706 | +| entropy_loss | -7.1 | +| explained_variance | -0.112 | +| learning_rate | 4.59e-05 | +| loss | -0.0331 | +| n_updates | 49824 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000202 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1422 | +| iterations | 8503 | +| time_elapsed | 12238 | +| total_timesteps | 17414144 | +| train/ | | +| approx_kl | 0.014018558 | +| clip_fraction | 0.337 | +| clip_range | 0.0706 | +| entropy_loss | -6.38 | +| explained_variance | 0.213 | +| learning_rate | 4.59e-05 | +| loss | -0.0225 | +| n_updates | 49828 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000284 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1422 | +| iterations | 8504 | +| time_elapsed | 12239 | +| total_timesteps | 17416192 | +| train/ | | +| approx_kl | 0.013805121 | +| clip_fraction | 0.353 | +| clip_range | 0.0706 | +| entropy_loss | -6.42 | +| explained_variance | 0.547 | +| learning_rate | 4.59e-05 | +| loss | -0.0284 | +| n_updates | 49832 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000114 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1422 | +| iterations | 8505 | +| time_elapsed | 12240 | +| total_timesteps | 17418240 | +| train/ | | +| approx_kl | 0.01352481 | +| clip_fraction | 0.333 | +| clip_range | 0.0706 | +| entropy_loss | -6.1 | +| explained_variance | 0.677 | +| learning_rate | 4.59e-05 | +| loss | -0.0247 | +| n_updates | 49836 | +| policy_gradient_loss | -0.019 | +| value_loss | 8.59e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1422 | +| iterations | 8506 | +| time_elapsed | 12242 | +| total_timesteps | 17420288 | +| train/ | | +| approx_kl | 0.014818979 | +| clip_fraction | 0.356 | +| clip_range | 0.0706 | +| entropy_loss | -5.95 | +| explained_variance | 0.687 | +| learning_rate | 4.59e-05 | +| loss | -0.0329 | +| n_updates | 49840 | +| policy_gradient_loss | -0.0204 | +| value_loss | 8.81e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1422 | +| iterations | 8507 | +| time_elapsed | 12243 | +| total_timesteps | 17422336 | +| train/ | | +| approx_kl | 0.014686904 | +| clip_fraction | 0.364 | +| clip_range | 0.0706 | +| entropy_loss | -6.7 | +| explained_variance | 0.292 | +| learning_rate | 4.59e-05 | +| loss | -0.0352 | +| n_updates | 49844 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.00012 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1422 | +| iterations | 8508 | +| time_elapsed | 12245 | +| total_timesteps | 17424384 | +| train/ | | +| approx_kl | 0.017430233 | +| clip_fraction | 0.335 | +| clip_range | 0.0706 | +| entropy_loss | -6.73 | +| explained_variance | 0.192 | +| learning_rate | 4.59e-05 | +| loss | -0.0278 | +| n_updates | 49848 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000142 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1422 | +| iterations | 8509 | +| time_elapsed | 12246 | +| total_timesteps | 17426432 | +| train/ | | +| approx_kl | 0.014475857 | +| clip_fraction | 0.334 | +| clip_range | 0.0706 | +| entropy_loss | -6.29 | +| explained_variance | 0.421 | +| learning_rate | 4.59e-05 | +| loss | -0.0252 | +| n_updates | 49852 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000204 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1422 | +| iterations | 8510 | +| time_elapsed | 12248 | +| total_timesteps | 17428480 | +| train/ | | +| approx_kl | 0.015667705 | +| clip_fraction | 0.339 | +| clip_range | 0.0706 | +| entropy_loss | -6.46 | +| explained_variance | 0.28 | +| learning_rate | 4.59e-05 | +| loss | -0.0307 | +| n_updates | 49856 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000234 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1422 | +| iterations | 8511 | +| time_elapsed | 12249 | +| total_timesteps | 17430528 | +| train/ | | +| approx_kl | 0.0141218025 | +| clip_fraction | 0.337 | +| clip_range | 0.0706 | +| entropy_loss | -6.73 | +| explained_variance | 0.176 | +| learning_rate | 4.59e-05 | +| loss | -0.0323 | +| n_updates | 49860 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000159 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1422 | +| iterations | 8512 | +| time_elapsed | 12250 | +| total_timesteps | 17432576 | +| train/ | | +| approx_kl | 0.0134517085 | +| clip_fraction | 0.332 | +| clip_range | 0.0706 | +| entropy_loss | -6.24 | +| explained_variance | 0.221 | +| learning_rate | 4.59e-05 | +| loss | -0.0257 | +| n_updates | 49864 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000307 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1422 | +| iterations | 8513 | +| time_elapsed | 12252 | +| total_timesteps | 17434624 | +| train/ | | +| approx_kl | 0.014662862 | +| clip_fraction | 0.382 | +| clip_range | 0.0706 | +| entropy_loss | -6.48 | +| explained_variance | 0.249 | +| learning_rate | 4.59e-05 | +| loss | -0.0399 | +| n_updates | 49868 | +| policy_gradient_loss | -0.0227 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1422 | +| iterations | 8514 | +| time_elapsed | 12253 | +| total_timesteps | 17436672 | +| train/ | | +| approx_kl | 0.013844808 | +| clip_fraction | 0.367 | +| clip_range | 0.0706 | +| entropy_loss | -6.69 | +| explained_variance | 0.652 | +| learning_rate | 4.59e-05 | +| loss | -0.0344 | +| n_updates | 49872 | +| policy_gradient_loss | -0.022 | +| value_loss | 8.62e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1422 | +| iterations | 8515 | +| time_elapsed | 12255 | +| total_timesteps | 17438720 | +| train/ | | +| approx_kl | 0.013987798 | +| clip_fraction | 0.377 | +| clip_range | 0.0706 | +| entropy_loss | -6.6 | +| explained_variance | -0.329 | +| learning_rate | 4.59e-05 | +| loss | -0.0351 | +| n_updates | 49876 | +| policy_gradient_loss | -0.0224 | +| value_loss | 7.99e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1422 | +| iterations | 8516 | +| time_elapsed | 12256 | +| total_timesteps | 17440768 | +| train/ | | +| approx_kl | 0.013614911 | +| clip_fraction | 0.325 | +| clip_range | 0.0706 | +| entropy_loss | -6.22 | +| explained_variance | 0.319 | +| learning_rate | 4.59e-05 | +| loss | -0.0232 | +| n_updates | 49880 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000257 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1422 | +| iterations | 8517 | +| time_elapsed | 12258 | +| total_timesteps | 17442816 | +| train/ | | +| approx_kl | 0.01577903 | +| clip_fraction | 0.364 | +| clip_range | 0.0706 | +| entropy_loss | -6.02 | +| explained_variance | 0.595 | +| learning_rate | 4.59e-05 | +| loss | -0.0317 | +| n_updates | 49884 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000108 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1422 | +| iterations | 8518 | +| time_elapsed | 12259 | +| total_timesteps | 17444864 | +| train/ | | +| approx_kl | 0.01348624 | +| clip_fraction | 0.361 | +| clip_range | 0.0706 | +| entropy_loss | -6.49 | +| explained_variance | 0.207 | +| learning_rate | 4.59e-05 | +| loss | -0.0326 | +| n_updates | 49888 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000143 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1422 | +| iterations | 8519 | +| time_elapsed | 12260 | +| total_timesteps | 17446912 | +| train/ | | +| approx_kl | 0.013437677 | +| clip_fraction | 0.368 | +| clip_range | 0.0706 | +| entropy_loss | -6.49 | +| explained_variance | 0.528 | +| learning_rate | 4.59e-05 | +| loss | -0.0277 | +| n_updates | 49892 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1422 | +| iterations | 8520 | +| time_elapsed | 12262 | +| total_timesteps | 17448960 | +| train/ | | +| approx_kl | 0.012753582 | +| clip_fraction | 0.373 | +| clip_range | 0.0706 | +| entropy_loss | -6.66 | +| explained_variance | 0.592 | +| learning_rate | 4.59e-05 | +| loss | -0.0422 | +| n_updates | 49896 | +| policy_gradient_loss | -0.0247 | +| value_loss | 6.45e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1422 | +| iterations | 8521 | +| time_elapsed | 12263 | +| total_timesteps | 17451008 | +| train/ | | +| approx_kl | 0.014830123 | +| clip_fraction | 0.358 | +| clip_range | 0.0706 | +| entropy_loss | -6.68 | +| explained_variance | 0.192 | +| learning_rate | 4.59e-05 | +| loss | -0.0327 | +| n_updates | 49900 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.00018 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1422 | +| iterations | 8522 | +| time_elapsed | 12265 | +| total_timesteps | 17453056 | +| train/ | | +| approx_kl | 0.01208991 | +| clip_fraction | 0.357 | +| clip_range | 0.0706 | +| entropy_loss | -6.73 | +| explained_variance | 0.341 | +| learning_rate | 4.59e-05 | +| loss | -0.0288 | +| n_updates | 49904 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000139 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1422 | +| iterations | 8523 | +| time_elapsed | 12266 | +| total_timesteps | 17455104 | +| train/ | | +| approx_kl | 0.011361308 | +| clip_fraction | 0.336 | +| clip_range | 0.0706 | +| entropy_loss | -6.25 | +| explained_variance | 0.421 | +| learning_rate | 4.59e-05 | +| loss | -0.0284 | +| n_updates | 49908 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000286 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1422 | +| iterations | 8524 | +| time_elapsed | 12268 | +| total_timesteps | 17457152 | +| train/ | | +| approx_kl | 0.013014858 | +| clip_fraction | 0.353 | +| clip_range | 0.0706 | +| entropy_loss | -6.27 | +| explained_variance | 0.168 | +| learning_rate | 4.59e-05 | +| loss | -0.0331 | +| n_updates | 49912 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000165 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1422 | +| iterations | 8525 | +| time_elapsed | 12269 | +| total_timesteps | 17459200 | +| train/ | | +| approx_kl | 0.013593491 | +| clip_fraction | 0.329 | +| clip_range | 0.0706 | +| entropy_loss | -6.25 | +| explained_variance | 0.44 | +| learning_rate | 4.59e-05 | +| loss | -0.0285 | +| n_updates | 49916 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000235 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1422 | +| iterations | 8526 | +| time_elapsed | 12271 | +| total_timesteps | 17461248 | +| train/ | | +| approx_kl | 0.01476857 | +| clip_fraction | 0.377 | +| clip_range | 0.0706 | +| entropy_loss | -6.95 | +| explained_variance | 0.0307 | +| learning_rate | 4.59e-05 | +| loss | -0.0405 | +| n_updates | 49920 | +| policy_gradient_loss | -0.0232 | +| value_loss | 8.39e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1422 | +| iterations | 8527 | +| time_elapsed | 12272 | +| total_timesteps | 17463296 | +| train/ | | +| approx_kl | 0.013820172 | +| clip_fraction | 0.33 | +| clip_range | 0.0706 | +| entropy_loss | -6.71 | +| explained_variance | 0.495 | +| learning_rate | 4.59e-05 | +| loss | -0.0299 | +| n_updates | 49924 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000131 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1422 | +| iterations | 8528 | +| time_elapsed | 12274 | +| total_timesteps | 17465344 | +| train/ | | +| approx_kl | 0.016403075 | +| clip_fraction | 0.339 | +| clip_range | 0.0706 | +| entropy_loss | -6.11 | +| explained_variance | 0.622 | +| learning_rate | 4.59e-05 | +| loss | -0.0331 | +| n_updates | 49928 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000136 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1422 | +| iterations | 8529 | +| time_elapsed | 12275 | +| total_timesteps | 17467392 | +| train/ | | +| approx_kl | 0.012511782 | +| clip_fraction | 0.365 | +| clip_range | 0.0706 | +| entropy_loss | -6.46 | +| explained_variance | 0.447 | +| learning_rate | 4.59e-05 | +| loss | -0.0317 | +| n_updates | 49932 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000144 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1422 | +| iterations | 8530 | +| time_elapsed | 12276 | +| total_timesteps | 17469440 | +| train/ | | +| approx_kl | 0.0148423705 | +| clip_fraction | 0.375 | +| clip_range | 0.0706 | +| entropy_loss | -6.58 | +| explained_variance | 0.614 | +| learning_rate | 4.59e-05 | +| loss | -0.0359 | +| n_updates | 49936 | +| policy_gradient_loss | -0.0242 | +| value_loss | 5.38e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1422 | +| iterations | 8531 | +| time_elapsed | 12278 | +| total_timesteps | 17471488 | +| train/ | | +| approx_kl | 0.013399797 | +| clip_fraction | 0.354 | +| clip_range | 0.0706 | +| entropy_loss | -7.16 | +| explained_variance | -0.202 | +| learning_rate | 4.59e-05 | +| loss | -0.0357 | +| n_updates | 49940 | +| policy_gradient_loss | -0.0215 | +| value_loss | 9.69e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1422 | +| iterations | 8532 | +| time_elapsed | 12279 | +| total_timesteps | 17473536 | +| train/ | | +| approx_kl | 0.013650898 | +| clip_fraction | 0.312 | +| clip_range | 0.0706 | +| entropy_loss | -6.92 | +| explained_variance | 0.232 | +| learning_rate | 4.59e-05 | +| loss | -0.0336 | +| n_updates | 49944 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000209 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1422 | +| iterations | 8533 | +| time_elapsed | 12281 | +| total_timesteps | 17475584 | +| train/ | | +| approx_kl | 0.01388211 | +| clip_fraction | 0.327 | +| clip_range | 0.0706 | +| entropy_loss | -6.29 | +| explained_variance | 0.627 | +| learning_rate | 4.59e-05 | +| loss | -0.0301 | +| n_updates | 49948 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000117 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1422 | +| iterations | 8534 | +| time_elapsed | 12282 | +| total_timesteps | 17477632 | +| train/ | | +| approx_kl | 0.015239988 | +| clip_fraction | 0.343 | +| clip_range | 0.0706 | +| entropy_loss | -6.52 | +| explained_variance | 0.338 | +| learning_rate | 4.58e-05 | +| loss | -0.0296 | +| n_updates | 49952 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000103 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.306 | +| time/ | | +| fps | 1422 | +| iterations | 8535 | +| time_elapsed | 12284 | +| total_timesteps | 17479680 | +| train/ | | +| approx_kl | 0.013821725 | +| clip_fraction | 0.348 | +| clip_range | 0.0706 | +| entropy_loss | -6.89 | +| explained_variance | -0.102 | +| learning_rate | 4.58e-05 | +| loss | -0.0311 | +| n_updates | 49956 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000116 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.306 | +| time/ | | +| fps | 1422 | +| iterations | 8536 | +| time_elapsed | 12285 | +| total_timesteps | 17481728 | +| train/ | | +| approx_kl | 0.011254126 | +| clip_fraction | 0.34 | +| clip_range | 0.0706 | +| entropy_loss | -6.8 | +| explained_variance | 0.304 | +| learning_rate | 4.58e-05 | +| loss | -0.0262 | +| n_updates | 49960 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.0002 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1422 | +| iterations | 8537 | +| time_elapsed | 12287 | +| total_timesteps | 17483776 | +| train/ | | +| approx_kl | 0.013769072 | +| clip_fraction | 0.324 | +| clip_range | 0.0706 | +| entropy_loss | -6.18 | +| explained_variance | 0.455 | +| learning_rate | 4.58e-05 | +| loss | -0.0349 | +| n_updates | 49964 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000135 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1422 | +| iterations | 8538 | +| time_elapsed | 12288 | +| total_timesteps | 17485824 | +| train/ | | +| approx_kl | 0.015317679 | +| clip_fraction | 0.345 | +| clip_range | 0.0706 | +| entropy_loss | -6.32 | +| explained_variance | 0.459 | +| learning_rate | 4.58e-05 | +| loss | -0.0269 | +| n_updates | 49968 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000183 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 1422 | +| iterations | 8539 | +| time_elapsed | 12289 | +| total_timesteps | 17487872 | +| train/ | | +| approx_kl | 0.014219509 | +| clip_fraction | 0.366 | +| clip_range | 0.0706 | +| entropy_loss | -6.59 | +| explained_variance | 0.302 | +| learning_rate | 4.58e-05 | +| loss | -0.0374 | +| n_updates | 49972 | +| policy_gradient_loss | -0.0205 | +| value_loss | 8.54e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.298 | +| time/ | | +| fps | 1422 | +| iterations | 8540 | +| time_elapsed | 12291 | +| total_timesteps | 17489920 | +| train/ | | +| approx_kl | 0.015396148 | +| clip_fraction | 0.358 | +| clip_range | 0.0706 | +| entropy_loss | -6.32 | +| explained_variance | 0.503 | +| learning_rate | 4.58e-05 | +| loss | -0.036 | +| n_updates | 49976 | +| policy_gradient_loss | -0.0208 | +| value_loss | 9.31e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.3 | +| time/ | | +| fps | 1422 | +| iterations | 8541 | +| time_elapsed | 12292 | +| total_timesteps | 17491968 | +| train/ | | +| approx_kl | 0.016124798 | +| clip_fraction | 0.334 | +| clip_range | 0.0706 | +| entropy_loss | -6.09 | +| explained_variance | 0.624 | +| learning_rate | 4.58e-05 | +| loss | -0.0256 | +| n_updates | 49980 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000124 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.295 | +| time/ | | +| fps | 1422 | +| iterations | 8542 | +| time_elapsed | 12294 | +| total_timesteps | 17494016 | +| train/ | | +| approx_kl | 0.014793689 | +| clip_fraction | 0.331 | +| clip_range | 0.0706 | +| entropy_loss | -6.35 | +| explained_variance | 0.49 | +| learning_rate | 4.58e-05 | +| loss | -0.0267 | +| n_updates | 49984 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000128 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 1422 | +| iterations | 8543 | +| time_elapsed | 12295 | +| total_timesteps | 17496064 | +| train/ | | +| approx_kl | 0.013465104 | +| clip_fraction | 0.339 | +| clip_range | 0.0706 | +| entropy_loss | -6.55 | +| explained_variance | 0.29 | +| learning_rate | 4.58e-05 | +| loss | -0.029 | +| n_updates | 49988 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000147 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.293 | +| time/ | | +| fps | 1422 | +| iterations | 8544 | +| time_elapsed | 12297 | +| total_timesteps | 17498112 | +| train/ | | +| approx_kl | 0.015250308 | +| clip_fraction | 0.364 | +| clip_range | 0.0706 | +| entropy_loss | -6.79 | +| explained_variance | -0.6 | +| learning_rate | 4.58e-05 | +| loss | -0.033 | +| n_updates | 49992 | +| policy_gradient_loss | -0.0204 | +| value_loss | 7.91e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.293 | +| time/ | | +| fps | 1422 | +| iterations | 8545 | +| time_elapsed | 12298 | +| total_timesteps | 17500160 | +| train/ | | +| approx_kl | 0.014455827 | +| clip_fraction | 0.337 | +| clip_range | 0.0706 | +| entropy_loss | -6.68 | +| explained_variance | 0.284 | +| learning_rate | 4.58e-05 | +| loss | -0.0273 | +| n_updates | 49996 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000196 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.289 | +| time/ | | +| fps | 1422 | +| iterations | 8546 | +| time_elapsed | 12300 | +| total_timesteps | 17502208 | +| train/ | | +| approx_kl | 0.014249856 | +| clip_fraction | 0.351 | +| clip_range | 0.0706 | +| entropy_loss | -6.61 | +| explained_variance | 0.387 | +| learning_rate | 4.58e-05 | +| loss | -0.0332 | +| n_updates | 50000 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.00011 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.286 | +| time/ | | +| fps | 1422 | +| iterations | 8547 | +| time_elapsed | 12301 | +| total_timesteps | 17504256 | +| train/ | | +| approx_kl | 0.014614157 | +| clip_fraction | 0.354 | +| clip_range | 0.0706 | +| entropy_loss | -6.73 | +| explained_variance | 0.463 | +| learning_rate | 4.58e-05 | +| loss | -0.0335 | +| n_updates | 50004 | +| policy_gradient_loss | -0.0205 | +| value_loss | 9.45e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.291 | +| time/ | | +| fps | 1422 | +| iterations | 8548 | +| time_elapsed | 12303 | +| total_timesteps | 17506304 | +| train/ | | +| approx_kl | 0.010944419 | +| clip_fraction | 0.336 | +| clip_range | 0.0706 | +| entropy_loss | -6.6 | +| explained_variance | 0.469 | +| learning_rate | 4.58e-05 | +| loss | -0.0308 | +| n_updates | 50008 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000178 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.298 | +| time/ | | +| fps | 1422 | +| iterations | 8549 | +| time_elapsed | 12304 | +| total_timesteps | 17508352 | +| train/ | | +| approx_kl | 0.010756339 | +| clip_fraction | 0.315 | +| clip_range | 0.0706 | +| entropy_loss | -6.33 | +| explained_variance | 0.627 | +| learning_rate | 4.58e-05 | +| loss | -0.0266 | +| n_updates | 50012 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000131 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 1422 | +| iterations | 8550 | +| time_elapsed | 12306 | +| total_timesteps | 17510400 | +| train/ | | +| approx_kl | 0.012017915 | +| clip_fraction | 0.328 | +| clip_range | 0.0706 | +| entropy_loss | -6.27 | +| explained_variance | 0.376 | +| learning_rate | 4.58e-05 | +| loss | -0.0292 | +| n_updates | 50016 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000285 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 1422 | +| iterations | 8551 | +| time_elapsed | 12307 | +| total_timesteps | 17512448 | +| train/ | | +| approx_kl | 0.012071615 | +| clip_fraction | 0.358 | +| clip_range | 0.0706 | +| entropy_loss | -6.2 | +| explained_variance | 0.587 | +| learning_rate | 4.58e-05 | +| loss | -0.0357 | +| n_updates | 50020 | +| policy_gradient_loss | -0.0225 | +| value_loss | 0.000123 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.293 | +| time/ | | +| fps | 1422 | +| iterations | 8552 | +| time_elapsed | 12308 | +| total_timesteps | 17514496 | +| train/ | | +| approx_kl | 0.011927022 | +| clip_fraction | 0.347 | +| clip_range | 0.0706 | +| entropy_loss | -7.05 | +| explained_variance | -0.114 | +| learning_rate | 4.58e-05 | +| loss | -0.031 | +| n_updates | 50024 | +| policy_gradient_loss | -0.0203 | +| value_loss | 9.72e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.297 | +| time/ | | +| fps | 1422 | +| iterations | 8553 | +| time_elapsed | 12310 | +| total_timesteps | 17516544 | +| train/ | | +| approx_kl | 0.010074608 | +| clip_fraction | 0.315 | +| clip_range | 0.0706 | +| entropy_loss | -6.59 | +| explained_variance | 0.477 | +| learning_rate | 4.58e-05 | +| loss | -0.0252 | +| n_updates | 50028 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000253 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.297 | +| time/ | | +| fps | 1422 | +| iterations | 8554 | +| time_elapsed | 12311 | +| total_timesteps | 17518592 | +| train/ | | +| approx_kl | 0.010784478 | +| clip_fraction | 0.327 | +| clip_range | 0.0706 | +| entropy_loss | -6.93 | +| explained_variance | 0.0698 | +| learning_rate | 4.58e-05 | +| loss | -0.0318 | +| n_updates | 50032 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000291 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.29 | +| time/ | | +| fps | 1422 | +| iterations | 8555 | +| time_elapsed | 12313 | +| total_timesteps | 17520640 | +| train/ | | +| approx_kl | 0.014987138 | +| clip_fraction | 0.387 | +| clip_range | 0.0706 | +| entropy_loss | -6.91 | +| explained_variance | 0.231 | +| learning_rate | 4.58e-05 | +| loss | -0.0377 | +| n_updates | 50036 | +| policy_gradient_loss | -0.0224 | +| value_loss | 0.000108 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.298 | +| time/ | | +| fps | 1422 | +| iterations | 8556 | +| time_elapsed | 12314 | +| total_timesteps | 17522688 | +| train/ | | +| approx_kl | 0.011495309 | +| clip_fraction | 0.37 | +| clip_range | 0.0706 | +| entropy_loss | -6.54 | +| explained_variance | 0.612 | +| learning_rate | 4.58e-05 | +| loss | -0.0359 | +| n_updates | 50040 | +| policy_gradient_loss | -0.0218 | +| value_loss | 8.18e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.294 | +| time/ | | +| fps | 1422 | +| iterations | 8557 | +| time_elapsed | 12316 | +| total_timesteps | 17524736 | +| train/ | | +| approx_kl | 0.012223419 | +| clip_fraction | 0.338 | +| clip_range | 0.0706 | +| entropy_loss | -6.11 | +| explained_variance | 0.497 | +| learning_rate | 4.58e-05 | +| loss | -0.0279 | +| n_updates | 50044 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.0002 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.297 | +| time/ | | +| fps | 1422 | +| iterations | 8558 | +| time_elapsed | 12317 | +| total_timesteps | 17526784 | +| train/ | | +| approx_kl | 0.012011064 | +| clip_fraction | 0.353 | +| clip_range | 0.0706 | +| entropy_loss | -6.59 | +| explained_variance | -0.0255 | +| learning_rate | 4.58e-05 | +| loss | -0.0341 | +| n_updates | 50048 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000133 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 1422 | +| iterations | 8559 | +| time_elapsed | 12318 | +| total_timesteps | 17528832 | +| train/ | | +| approx_kl | 0.014711577 | +| clip_fraction | 0.327 | +| clip_range | 0.0706 | +| entropy_loss | -6.78 | +| explained_variance | 0.294 | +| learning_rate | 4.58e-05 | +| loss | -0.0301 | +| n_updates | 50052 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000142 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 1422 | +| iterations | 8560 | +| time_elapsed | 12320 | +| total_timesteps | 17530880 | +| train/ | | +| approx_kl | 0.015449715 | +| clip_fraction | 0.384 | +| clip_range | 0.0706 | +| entropy_loss | -6.61 | +| explained_variance | 0.747 | +| learning_rate | 4.58e-05 | +| loss | -0.0398 | +| n_updates | 50056 | +| policy_gradient_loss | -0.0262 | +| value_loss | 5.42e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.291 | +| time/ | | +| fps | 1422 | +| iterations | 8561 | +| time_elapsed | 12321 | +| total_timesteps | 17532928 | +| train/ | | +| approx_kl | 0.014227681 | +| clip_fraction | 0.348 | +| clip_range | 0.0706 | +| entropy_loss | -6.64 | +| explained_variance | 0.302 | +| learning_rate | 4.58e-05 | +| loss | -0.026 | +| n_updates | 50060 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000128 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.291 | +| time/ | | +| fps | 1422 | +| iterations | 8562 | +| time_elapsed | 12323 | +| total_timesteps | 17534976 | +| train/ | | +| approx_kl | 0.013638642 | +| clip_fraction | 0.359 | +| clip_range | 0.0706 | +| entropy_loss | -6.4 | +| explained_variance | 0.62 | +| learning_rate | 4.58e-05 | +| loss | -0.0296 | +| n_updates | 50064 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.00013 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.291 | +| time/ | | +| fps | 1422 | +| iterations | 8563 | +| time_elapsed | 12324 | +| total_timesteps | 17537024 | +| train/ | | +| approx_kl | 0.01305937 | +| clip_fraction | 0.341 | +| clip_range | 0.0706 | +| entropy_loss | -6.52 | +| explained_variance | 0.327 | +| learning_rate | 4.58e-05 | +| loss | -0.0319 | +| n_updates | 50068 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000145 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.292 | +| time/ | | +| fps | 1422 | +| iterations | 8564 | +| time_elapsed | 12326 | +| total_timesteps | 17539072 | +| train/ | | +| approx_kl | 0.012109214 | +| clip_fraction | 0.35 | +| clip_range | 0.0706 | +| entropy_loss | -6.38 | +| explained_variance | 0.63 | +| learning_rate | 4.58e-05 | +| loss | -0.0347 | +| n_updates | 50072 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.00012 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.291 | +| time/ | | +| fps | 1422 | +| iterations | 8565 | +| time_elapsed | 12327 | +| total_timesteps | 17541120 | +| train/ | | +| approx_kl | 0.015227321 | +| clip_fraction | 0.347 | +| clip_range | 0.0706 | +| entropy_loss | -6.46 | +| explained_variance | 0.492 | +| learning_rate | 4.58e-05 | +| loss | -0.0286 | +| n_updates | 50076 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000179 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.289 | +| time/ | | +| fps | 1422 | +| iterations | 8566 | +| time_elapsed | 12329 | +| total_timesteps | 17543168 | +| train/ | | +| approx_kl | 0.014851072 | +| clip_fraction | 0.376 | +| clip_range | 0.0706 | +| entropy_loss | -6.62 | +| explained_variance | -0.146 | +| learning_rate | 4.58e-05 | +| loss | -0.035 | +| n_updates | 50080 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000118 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.285 | +| time/ | | +| fps | 1422 | +| iterations | 8567 | +| time_elapsed | 12330 | +| total_timesteps | 17545216 | +| train/ | | +| approx_kl | 0.016817238 | +| clip_fraction | 0.39 | +| clip_range | 0.0706 | +| entropy_loss | -6.41 | +| explained_variance | 0.778 | +| learning_rate | 4.58e-05 | +| loss | -0.0355 | +| n_updates | 50084 | +| policy_gradient_loss | -0.0237 | +| value_loss | 4.1e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.287 | +| time/ | | +| fps | 1422 | +| iterations | 8568 | +| time_elapsed | 12331 | +| total_timesteps | 17547264 | +| train/ | | +| approx_kl | 0.01116712 | +| clip_fraction | 0.323 | +| clip_range | 0.0706 | +| entropy_loss | -5.9 | +| explained_variance | 0.776 | +| learning_rate | 4.58e-05 | +| loss | -0.03 | +| n_updates | 50088 | +| policy_gradient_loss | -0.0183 | +| value_loss | 9.44e-05 | +---------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.285 | +| time/ | | +| fps | 1422 | +| iterations | 8569 | +| time_elapsed | 12333 | +| total_timesteps | 17549312 | +| train/ | | +| approx_kl | 0.0097144 | +| clip_fraction | 0.317 | +| clip_range | 0.0706 | +| entropy_loss | -6.52 | +| explained_variance | 0.391 | +| learning_rate | 4.58e-05 | +| loss | -0.0299 | +| n_updates | 50092 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000232 | +--------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.285 | +| time/ | | +| fps | 1422 | +| iterations | 8570 | +| time_elapsed | 12334 | +| total_timesteps | 17551360 | +| train/ | | +| approx_kl | 0.01046654 | +| clip_fraction | 0.301 | +| clip_range | 0.0706 | +| entropy_loss | -6.98 | +| explained_variance | -0.136 | +| learning_rate | 4.58e-05 | +| loss | -0.027 | +| n_updates | 50096 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000245 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.292 | +| time/ | | +| fps | 1422 | +| iterations | 8571 | +| time_elapsed | 12336 | +| total_timesteps | 17553408 | +| train/ | | +| approx_kl | 0.018976554 | +| clip_fraction | 0.374 | +| clip_range | 0.0706 | +| entropy_loss | -6.58 | +| explained_variance | 0.478 | +| learning_rate | 4.58e-05 | +| loss | -0.0399 | +| n_updates | 50100 | +| policy_gradient_loss | -0.0221 | +| value_loss | 7.11e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.281 | +| time/ | | +| fps | 1422 | +| iterations | 8572 | +| time_elapsed | 12337 | +| total_timesteps | 17555456 | +| train/ | | +| approx_kl | 0.010909315 | +| clip_fraction | 0.337 | +| clip_range | 0.0706 | +| entropy_loss | -7.11 | +| explained_variance | -0.0503 | +| learning_rate | 4.58e-05 | +| loss | -0.0268 | +| n_updates | 50104 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.00035 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.294 | +| time/ | | +| fps | 1422 | +| iterations | 8573 | +| time_elapsed | 12339 | +| total_timesteps | 17557504 | +| train/ | | +| approx_kl | 0.011093289 | +| clip_fraction | 0.347 | +| clip_range | 0.0706 | +| entropy_loss | -6.14 | +| explained_variance | 0.615 | +| learning_rate | 4.58e-05 | +| loss | -0.0335 | +| n_updates | 50108 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000166 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.288 | +| time/ | | +| fps | 1422 | +| iterations | 8574 | +| time_elapsed | 12340 | +| total_timesteps | 17559552 | +| train/ | | +| approx_kl | 0.011865443 | +| clip_fraction | 0.362 | +| clip_range | 0.0706 | +| entropy_loss | -6.56 | +| explained_variance | 0.209 | +| learning_rate | 4.58e-05 | +| loss | -0.0307 | +| n_updates | 50112 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000339 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.289 | +| time/ | | +| fps | 1422 | +| iterations | 8575 | +| time_elapsed | 12342 | +| total_timesteps | 17561600 | +| train/ | | +| approx_kl | 0.01131944 | +| clip_fraction | 0.331 | +| clip_range | 0.0706 | +| entropy_loss | -6.18 | +| explained_variance | 0.63 | +| learning_rate | 4.58e-05 | +| loss | -0.0339 | +| n_updates | 50116 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000112 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.292 | +| time/ | | +| fps | 1422 | +| iterations | 8576 | +| time_elapsed | 12343 | +| total_timesteps | 17563648 | +| train/ | | +| approx_kl | 0.010331018 | +| clip_fraction | 0.353 | +| clip_range | 0.0706 | +| entropy_loss | -6.48 | +| explained_variance | 0.313 | +| learning_rate | 4.58e-05 | +| loss | -0.033 | +| n_updates | 50120 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000179 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.295 | +| time/ | | +| fps | 1422 | +| iterations | 8577 | +| time_elapsed | 12344 | +| total_timesteps | 17565696 | +| train/ | | +| approx_kl | 0.013299262 | +| clip_fraction | 0.336 | +| clip_range | 0.0706 | +| entropy_loss | -6.31 | +| explained_variance | 0.39 | +| learning_rate | 4.58e-05 | +| loss | -0.027 | +| n_updates | 50124 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.00021 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.298 | +| time/ | | +| fps | 1422 | +| iterations | 8578 | +| time_elapsed | 12346 | +| total_timesteps | 17567744 | +| train/ | | +| approx_kl | 0.01070049 | +| clip_fraction | 0.325 | +| clip_range | 0.0706 | +| entropy_loss | -6.62 | +| explained_variance | 0.278 | +| learning_rate | 4.58e-05 | +| loss | -0.0297 | +| n_updates | 50128 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000219 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.298 | +| time/ | | +| fps | 1422 | +| iterations | 8579 | +| time_elapsed | 12347 | +| total_timesteps | 17569792 | +| train/ | | +| approx_kl | 0.015598169 | +| clip_fraction | 0.354 | +| clip_range | 0.0706 | +| entropy_loss | -6.78 | +| explained_variance | 0.219 | +| learning_rate | 4.58e-05 | +| loss | -0.0348 | +| n_updates | 50132 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.00018 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.298 | +| time/ | | +| fps | 1422 | +| iterations | 8580 | +| time_elapsed | 12349 | +| total_timesteps | 17571840 | +| train/ | | +| approx_kl | 0.013372319 | +| clip_fraction | 0.332 | +| clip_range | 0.0706 | +| entropy_loss | -6.15 | +| explained_variance | 0.493 | +| learning_rate | 4.58e-05 | +| loss | -0.0227 | +| n_updates | 50136 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000261 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.298 | +| time/ | | +| fps | 1422 | +| iterations | 8581 | +| time_elapsed | 12350 | +| total_timesteps | 17573888 | +| train/ | | +| approx_kl | 0.012592058 | +| clip_fraction | 0.356 | +| clip_range | 0.0706 | +| entropy_loss | -6.35 | +| explained_variance | 0.574 | +| learning_rate | 4.58e-05 | +| loss | -0.0368 | +| n_updates | 50140 | +| policy_gradient_loss | -0.0228 | +| value_loss | 9.4e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.298 | +| time/ | | +| fps | 1422 | +| iterations | 8582 | +| time_elapsed | 12352 | +| total_timesteps | 17575936 | +| train/ | | +| approx_kl | 0.011964945 | +| clip_fraction | 0.335 | +| clip_range | 0.0706 | +| entropy_loss | -7.08 | +| explained_variance | 0.0555 | +| learning_rate | 4.58e-05 | +| loss | -0.0325 | +| n_updates | 50144 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000203 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.3 | +| time/ | | +| fps | 1422 | +| iterations | 8583 | +| time_elapsed | 12353 | +| total_timesteps | 17577984 | +| train/ | | +| approx_kl | 0.011081447 | +| clip_fraction | 0.337 | +| clip_range | 0.0706 | +| entropy_loss | -6.9 | +| explained_variance | 0.398 | +| learning_rate | 4.58e-05 | +| loss | -0.0285 | +| n_updates | 50148 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000229 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1422 | +| iterations | 8584 | +| time_elapsed | 12355 | +| total_timesteps | 17580032 | +| train/ | | +| approx_kl | 0.0128971655 | +| clip_fraction | 0.358 | +| clip_range | 0.0706 | +| entropy_loss | -6.47 | +| explained_variance | 0.207 | +| learning_rate | 4.58e-05 | +| loss | -0.0306 | +| n_updates | 50152 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000337 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1422 | +| iterations | 8585 | +| time_elapsed | 12356 | +| total_timesteps | 17582080 | +| train/ | | +| approx_kl | 0.011774161 | +| clip_fraction | 0.358 | +| clip_range | 0.0706 | +| entropy_loss | -6.07 | +| explained_variance | 0.488 | +| learning_rate | 4.58e-05 | +| loss | -0.0288 | +| n_updates | 50156 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000238 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1422 | +| iterations | 8586 | +| time_elapsed | 12357 | +| total_timesteps | 17584128 | +| train/ | | +| approx_kl | 0.012702526 | +| clip_fraction | 0.385 | +| clip_range | 0.0706 | +| entropy_loss | -6.29 | +| explained_variance | 0.5 | +| learning_rate | 4.58e-05 | +| loss | -0.0387 | +| n_updates | 50160 | +| policy_gradient_loss | -0.0233 | +| value_loss | 0.000108 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1422 | +| iterations | 8587 | +| time_elapsed | 12359 | +| total_timesteps | 17586176 | +| train/ | | +| approx_kl | 0.012249298 | +| clip_fraction | 0.339 | +| clip_range | 0.0706 | +| entropy_loss | -6.9 | +| explained_variance | 0.113 | +| learning_rate | 4.58e-05 | +| loss | -0.0264 | +| n_updates | 50164 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000306 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1422 | +| iterations | 8588 | +| time_elapsed | 12360 | +| total_timesteps | 17588224 | +| train/ | | +| approx_kl | 0.010479726 | +| clip_fraction | 0.345 | +| clip_range | 0.0706 | +| entropy_loss | -6.52 | +| explained_variance | 0.627 | +| learning_rate | 4.58e-05 | +| loss | -0.0352 | +| n_updates | 50168 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000117 | +----------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1422 | +| iterations | 8589 | +| time_elapsed | 12362 | +| total_timesteps | 17590272 | +| train/ | | +| approx_kl | 0.011118 | +| clip_fraction | 0.362 | +| clip_range | 0.0706 | +| entropy_loss | -6.63 | +| explained_variance | 0.544 | +| learning_rate | 4.58e-05 | +| loss | -0.033 | +| n_updates | 50172 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000111 | +-------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1422 | +| iterations | 8590 | +| time_elapsed | 12363 | +| total_timesteps | 17592320 | +| train/ | | +| approx_kl | 0.011265209 | +| clip_fraction | 0.326 | +| clip_range | 0.0706 | +| entropy_loss | -6.37 | +| explained_variance | 0.201 | +| learning_rate | 4.58e-05 | +| loss | -0.0231 | +| n_updates | 50176 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000267 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1422 | +| iterations | 8591 | +| time_elapsed | 12365 | +| total_timesteps | 17594368 | +| train/ | | +| approx_kl | 0.0121483775 | +| clip_fraction | 0.327 | +| clip_range | 0.0706 | +| entropy_loss | -6.48 | +| explained_variance | 0.323 | +| learning_rate | 4.58e-05 | +| loss | -0.0285 | +| n_updates | 50180 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000326 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1422 | +| iterations | 8592 | +| time_elapsed | 12366 | +| total_timesteps | 17596416 | +| train/ | | +| approx_kl | 0.013222848 | +| clip_fraction | 0.377 | +| clip_range | 0.0706 | +| entropy_loss | -6.57 | +| explained_variance | 0.534 | +| learning_rate | 4.58e-05 | +| loss | -0.0432 | +| n_updates | 50184 | +| policy_gradient_loss | -0.0248 | +| value_loss | 0.000106 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1422 | +| iterations | 8593 | +| time_elapsed | 12368 | +| total_timesteps | 17598464 | +| train/ | | +| approx_kl | 0.015653811 | +| clip_fraction | 0.385 | +| clip_range | 0.0706 | +| entropy_loss | -6.31 | +| explained_variance | 0.164 | +| learning_rate | 4.58e-05 | +| loss | -0.0367 | +| n_updates | 50188 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000259 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1422 | +| iterations | 8594 | +| time_elapsed | 12369 | +| total_timesteps | 17600512 | +| train/ | | +| approx_kl | 0.015431769 | +| clip_fraction | 0.365 | +| clip_range | 0.0706 | +| entropy_loss | -6.76 | +| explained_variance | 0.261 | +| learning_rate | 4.58e-05 | +| loss | -0.03 | +| n_updates | 50192 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000186 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1422 | +| iterations | 8595 | +| time_elapsed | 12371 | +| total_timesteps | 17602560 | +| train/ | | +| approx_kl | 0.015664294 | +| clip_fraction | 0.387 | +| clip_range | 0.0706 | +| entropy_loss | -6.58 | +| explained_variance | 0.307 | +| learning_rate | 4.58e-05 | +| loss | -0.0322 | +| n_updates | 50196 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1422 | +| iterations | 8596 | +| time_elapsed | 12372 | +| total_timesteps | 17604608 | +| train/ | | +| approx_kl | 0.014362922 | +| clip_fraction | 0.357 | +| clip_range | 0.0706 | +| entropy_loss | -6.17 | +| explained_variance | 0.46 | +| learning_rate | 4.58e-05 | +| loss | -0.034 | +| n_updates | 50200 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000247 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1422 | +| iterations | 8597 | +| time_elapsed | 12373 | +| total_timesteps | 17606656 | +| train/ | | +| approx_kl | 0.010996187 | +| clip_fraction | 0.327 | +| clip_range | 0.0706 | +| entropy_loss | -6.6 | +| explained_variance | 0.312 | +| learning_rate | 4.58e-05 | +| loss | -0.0312 | +| n_updates | 50204 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000354 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1422 | +| iterations | 8598 | +| time_elapsed | 12375 | +| total_timesteps | 17608704 | +| train/ | | +| approx_kl | 0.014340361 | +| clip_fraction | 0.374 | +| clip_range | 0.0706 | +| entropy_loss | -6.31 | +| explained_variance | 0.444 | +| learning_rate | 4.58e-05 | +| loss | -0.0364 | +| n_updates | 50208 | +| policy_gradient_loss | -0.023 | +| value_loss | 0.000137 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1422 | +| iterations | 8599 | +| time_elapsed | 12376 | +| total_timesteps | 17610752 | +| train/ | | +| approx_kl | 0.015575878 | +| clip_fraction | 0.363 | +| clip_range | 0.0706 | +| entropy_loss | -6.61 | +| explained_variance | 0.365 | +| learning_rate | 4.58e-05 | +| loss | -0.0345 | +| n_updates | 50212 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000114 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1422 | +| iterations | 8600 | +| time_elapsed | 12378 | +| total_timesteps | 17612800 | +| train/ | | +| approx_kl | 0.016811952 | +| clip_fraction | 0.39 | +| clip_range | 0.0706 | +| entropy_loss | -6.62 | +| explained_variance | -0.432 | +| learning_rate | 4.58e-05 | +| loss | -0.0397 | +| n_updates | 50216 | +| policy_gradient_loss | -0.0225 | +| value_loss | 9.95e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1422 | +| iterations | 8601 | +| time_elapsed | 12379 | +| total_timesteps | 17614848 | +| train/ | | +| approx_kl | 0.013931805 | +| clip_fraction | 0.357 | +| clip_range | 0.0706 | +| entropy_loss | -6.5 | +| explained_variance | 0.339 | +| learning_rate | 4.58e-05 | +| loss | -0.0313 | +| n_updates | 50220 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000144 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1422 | +| iterations | 8602 | +| time_elapsed | 12381 | +| total_timesteps | 17616896 | +| train/ | | +| approx_kl | 0.014988089 | +| clip_fraction | 0.354 | +| clip_range | 0.0706 | +| entropy_loss | -6.35 | +| explained_variance | 0.49 | +| learning_rate | 4.58e-05 | +| loss | -0.0233 | +| n_updates | 50224 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000137 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1422 | +| iterations | 8603 | +| time_elapsed | 12382 | +| total_timesteps | 17618944 | +| train/ | | +| approx_kl | 0.016139321 | +| clip_fraction | 0.356 | +| clip_range | 0.0706 | +| entropy_loss | -6.57 | +| explained_variance | 0.314 | +| learning_rate | 4.58e-05 | +| loss | -0.0321 | +| n_updates | 50228 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000142 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1422 | +| iterations | 8604 | +| time_elapsed | 12384 | +| total_timesteps | 17620992 | +| train/ | | +| approx_kl | 0.0156090725 | +| clip_fraction | 0.355 | +| clip_range | 0.0706 | +| entropy_loss | -6.3 | +| explained_variance | 0.449 | +| learning_rate | 4.58e-05 | +| loss | -0.0327 | +| n_updates | 50232 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000143 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1422 | +| iterations | 8605 | +| time_elapsed | 12385 | +| total_timesteps | 17623040 | +| train/ | | +| approx_kl | 0.01657638 | +| clip_fraction | 0.388 | +| clip_range | 0.0706 | +| entropy_loss | -6.66 | +| explained_variance | -0.0559 | +| learning_rate | 4.58e-05 | +| loss | -0.0353 | +| n_updates | 50236 | +| policy_gradient_loss | -0.024 | +| value_loss | 9.01e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1422 | +| iterations | 8606 | +| time_elapsed | 12386 | +| total_timesteps | 17625088 | +| train/ | | +| approx_kl | 0.015418868 | +| clip_fraction | 0.376 | +| clip_range | 0.0706 | +| entropy_loss | -6.72 | +| explained_variance | -0.0791 | +| learning_rate | 4.58e-05 | +| loss | -0.0323 | +| n_updates | 50240 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000206 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1422 | +| iterations | 8607 | +| time_elapsed | 12388 | +| total_timesteps | 17627136 | +| train/ | | +| approx_kl | 0.014968638 | +| clip_fraction | 0.337 | +| clip_range | 0.0706 | +| entropy_loss | -6.31 | +| explained_variance | 0.418 | +| learning_rate | 4.58e-05 | +| loss | -0.0282 | +| n_updates | 50244 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000175 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1422 | +| iterations | 8608 | +| time_elapsed | 12389 | +| total_timesteps | 17629184 | +| train/ | | +| approx_kl | 0.016761335 | +| clip_fraction | 0.342 | +| clip_range | 0.0706 | +| entropy_loss | -5.96 | +| explained_variance | 0.744 | +| learning_rate | 4.58e-05 | +| loss | -0.0284 | +| n_updates | 50248 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000124 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1422 | +| iterations | 8609 | +| time_elapsed | 12391 | +| total_timesteps | 17631232 | +| train/ | | +| approx_kl | 0.015545549 | +| clip_fraction | 0.353 | +| clip_range | 0.0706 | +| entropy_loss | -6.56 | +| explained_variance | 0.145 | +| learning_rate | 4.58e-05 | +| loss | -0.0296 | +| n_updates | 50252 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000179 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1422 | +| iterations | 8610 | +| time_elapsed | 12392 | +| total_timesteps | 17633280 | +| train/ | | +| approx_kl | 0.011817271 | +| clip_fraction | 0.333 | +| clip_range | 0.0706 | +| entropy_loss | -6.89 | +| explained_variance | 0.295 | +| learning_rate | 4.58e-05 | +| loss | -0.0286 | +| n_updates | 50256 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000263 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1422 | +| iterations | 8611 | +| time_elapsed | 12394 | +| total_timesteps | 17635328 | +| train/ | | +| approx_kl | 0.013645263 | +| clip_fraction | 0.344 | +| clip_range | 0.0706 | +| entropy_loss | -5.96 | +| explained_variance | 0.594 | +| learning_rate | 4.58e-05 | +| loss | -0.0287 | +| n_updates | 50260 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.00017 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1422 | +| iterations | 8612 | +| time_elapsed | 12395 | +| total_timesteps | 17637376 | +| train/ | | +| approx_kl | 0.014222512 | +| clip_fraction | 0.365 | +| clip_range | 0.0706 | +| entropy_loss | -6.5 | +| explained_variance | 0.36 | +| learning_rate | 4.58e-05 | +| loss | -0.041 | +| n_updates | 50264 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000108 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1422 | +| iterations | 8613 | +| time_elapsed | 12396 | +| total_timesteps | 17639424 | +| train/ | | +| approx_kl | 0.014064527 | +| clip_fraction | 0.333 | +| clip_range | 0.0706 | +| entropy_loss | -6.8 | +| explained_variance | 0.254 | +| learning_rate | 4.58e-05 | +| loss | -0.0292 | +| n_updates | 50268 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000203 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1422 | +| iterations | 8614 | +| time_elapsed | 12398 | +| total_timesteps | 17641472 | +| train/ | | +| approx_kl | 0.013344055 | +| clip_fraction | 0.338 | +| clip_range | 0.0706 | +| entropy_loss | -6.61 | +| explained_variance | 0.405 | +| learning_rate | 4.58e-05 | +| loss | -0.0279 | +| n_updates | 50272 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000134 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1422 | +| iterations | 8615 | +| time_elapsed | 12399 | +| total_timesteps | 17643520 | +| train/ | | +| approx_kl | 0.0120140165 | +| clip_fraction | 0.341 | +| clip_range | 0.0706 | +| entropy_loss | -6.88 | +| explained_variance | 0.113 | +| learning_rate | 4.58e-05 | +| loss | -0.0312 | +| n_updates | 50276 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000162 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1422 | +| iterations | 8616 | +| time_elapsed | 12401 | +| total_timesteps | 17645568 | +| train/ | | +| approx_kl | 0.012109651 | +| clip_fraction | 0.352 | +| clip_range | 0.0706 | +| entropy_loss | -6.87 | +| explained_variance | 0.402 | +| learning_rate | 4.58e-05 | +| loss | -0.0319 | +| n_updates | 50280 | +| policy_gradient_loss | -0.0187 | +| value_loss | 9.74e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1422 | +| iterations | 8617 | +| time_elapsed | 12402 | +| total_timesteps | 17647616 | +| train/ | | +| approx_kl | 0.011486902 | +| clip_fraction | 0.338 | +| clip_range | 0.0706 | +| entropy_loss | -6.86 | +| explained_variance | 0.248 | +| learning_rate | 4.58e-05 | +| loss | -0.0304 | +| n_updates | 50284 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000212 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1422 | +| iterations | 8618 | +| time_elapsed | 12404 | +| total_timesteps | 17649664 | +| train/ | | +| approx_kl | 0.013188664 | +| clip_fraction | 0.33 | +| clip_range | 0.0706 | +| entropy_loss | -6.72 | +| explained_variance | -0.128 | +| learning_rate | 4.58e-05 | +| loss | -0.0278 | +| n_updates | 50288 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000144 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1422 | +| iterations | 8619 | +| time_elapsed | 12405 | +| total_timesteps | 17651712 | +| train/ | | +| approx_kl | 0.011848243 | +| clip_fraction | 0.318 | +| clip_range | 0.0706 | +| entropy_loss | -5.92 | +| explained_variance | 0.523 | +| learning_rate | 4.58e-05 | +| loss | -0.021 | +| n_updates | 50292 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000267 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1422 | +| iterations | 8620 | +| time_elapsed | 12406 | +| total_timesteps | 17653760 | +| train/ | | +| approx_kl | 0.01300977 | +| clip_fraction | 0.336 | +| clip_range | 0.0706 | +| entropy_loss | -6.15 | +| explained_variance | 0.539 | +| learning_rate | 4.58e-05 | +| loss | -0.0316 | +| n_updates | 50296 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000177 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1422 | +| iterations | 8621 | +| time_elapsed | 12408 | +| total_timesteps | 17655808 | +| train/ | | +| approx_kl | 0.0135037955 | +| clip_fraction | 0.384 | +| clip_range | 0.0706 | +| entropy_loss | -6.51 | +| explained_variance | -0.0758 | +| learning_rate | 4.58e-05 | +| loss | -0.0351 | +| n_updates | 50300 | +| policy_gradient_loss | -0.0225 | +| value_loss | 0.000115 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1422 | +| iterations | 8622 | +| time_elapsed | 12409 | +| total_timesteps | 17657856 | +| train/ | | +| approx_kl | 0.012999639 | +| clip_fraction | 0.332 | +| clip_range | 0.0706 | +| entropy_loss | -6.42 | +| explained_variance | 0.493 | +| learning_rate | 4.58e-05 | +| loss | -0.0268 | +| n_updates | 50304 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000202 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1422 | +| iterations | 8623 | +| time_elapsed | 12411 | +| total_timesteps | 17659904 | +| train/ | | +| approx_kl | 0.012546152 | +| clip_fraction | 0.368 | +| clip_range | 0.0706 | +| entropy_loss | -6.54 | +| explained_variance | -0.0423 | +| learning_rate | 4.58e-05 | +| loss | -0.0339 | +| n_updates | 50308 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000243 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1422 | +| iterations | 8624 | +| time_elapsed | 12412 | +| total_timesteps | 17661952 | +| train/ | | +| approx_kl | 0.015915578 | +| clip_fraction | 0.348 | +| clip_range | 0.0706 | +| entropy_loss | -6.9 | +| explained_variance | -0.224 | +| learning_rate | 4.58e-05 | +| loss | -0.034 | +| n_updates | 50312 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000208 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1422 | +| iterations | 8625 | +| time_elapsed | 12414 | +| total_timesteps | 17664000 | +| train/ | | +| approx_kl | 0.016394654 | +| clip_fraction | 0.391 | +| clip_range | 0.0706 | +| entropy_loss | -6.79 | +| explained_variance | -0.198 | +| learning_rate | 4.58e-05 | +| loss | -0.0334 | +| n_updates | 50316 | +| policy_gradient_loss | -0.0221 | +| value_loss | 0.000121 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1422 | +| iterations | 8626 | +| time_elapsed | 12415 | +| total_timesteps | 17666048 | +| train/ | | +| approx_kl | 0.014025843 | +| clip_fraction | 0.352 | +| clip_range | 0.0706 | +| entropy_loss | -6.13 | +| explained_variance | 0.596 | +| learning_rate | 4.58e-05 | +| loss | -0.0275 | +| n_updates | 50320 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000206 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1422 | +| iterations | 8627 | +| time_elapsed | 12416 | +| total_timesteps | 17668096 | +| train/ | | +| approx_kl | 0.0153058525 | +| clip_fraction | 0.335 | +| clip_range | 0.0706 | +| entropy_loss | -5.92 | +| explained_variance | 0.374 | +| learning_rate | 4.58e-05 | +| loss | -0.023 | +| n_updates | 50324 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000171 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1422 | +| iterations | 8628 | +| time_elapsed | 12418 | +| total_timesteps | 17670144 | +| train/ | | +| approx_kl | 0.0140424445 | +| clip_fraction | 0.368 | +| clip_range | 0.0706 | +| entropy_loss | -6.52 | +| explained_variance | 0.535 | +| learning_rate | 4.58e-05 | +| loss | -0.0352 | +| n_updates | 50328 | +| policy_gradient_loss | -0.0224 | +| value_loss | 9.45e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1422 | +| iterations | 8629 | +| time_elapsed | 12419 | +| total_timesteps | 17672192 | +| train/ | | +| approx_kl | 0.014050301 | +| clip_fraction | 0.379 | +| clip_range | 0.0706 | +| entropy_loss | -6.27 | +| explained_variance | 0.439 | +| learning_rate | 4.58e-05 | +| loss | -0.034 | +| n_updates | 50332 | +| policy_gradient_loss | -0.0213 | +| value_loss | 9.84e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1422 | +| iterations | 8630 | +| time_elapsed | 12421 | +| total_timesteps | 17674240 | +| train/ | | +| approx_kl | 0.013078805 | +| clip_fraction | 0.33 | +| clip_range | 0.0706 | +| entropy_loss | -6.67 | +| explained_variance | 0.307 | +| learning_rate | 4.58e-05 | +| loss | -0.0286 | +| n_updates | 50336 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000156 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1422 | +| iterations | 8631 | +| time_elapsed | 12422 | +| total_timesteps | 17676288 | +| train/ | | +| approx_kl | 0.012788368 | +| clip_fraction | 0.335 | +| clip_range | 0.0706 | +| entropy_loss | -6.89 | +| explained_variance | 0.235 | +| learning_rate | 4.58e-05 | +| loss | -0.0276 | +| n_updates | 50340 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000184 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1422 | +| iterations | 8632 | +| time_elapsed | 12424 | +| total_timesteps | 17678336 | +| train/ | | +| approx_kl | 0.01211255 | +| clip_fraction | 0.349 | +| clip_range | 0.0706 | +| entropy_loss | -6.75 | +| explained_variance | 0.129 | +| learning_rate | 4.58e-05 | +| loss | -0.0328 | +| n_updates | 50344 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000236 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1422 | +| iterations | 8633 | +| time_elapsed | 12425 | +| total_timesteps | 17680384 | +| train/ | | +| approx_kl | 0.012131839 | +| clip_fraction | 0.337 | +| clip_range | 0.0706 | +| entropy_loss | -6.59 | +| explained_variance | 0.168 | +| learning_rate | 4.58e-05 | +| loss | -0.0279 | +| n_updates | 50348 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000358 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1422 | +| iterations | 8634 | +| time_elapsed | 12426 | +| total_timesteps | 17682432 | +| train/ | | +| approx_kl | 0.012490522 | +| clip_fraction | 0.32 | +| clip_range | 0.0706 | +| entropy_loss | -6.24 | +| explained_variance | 0.449 | +| learning_rate | 4.58e-05 | +| loss | -0.0311 | +| n_updates | 50352 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000244 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1422 | +| iterations | 8635 | +| time_elapsed | 12428 | +| total_timesteps | 17684480 | +| train/ | | +| approx_kl | 0.011762627 | +| clip_fraction | 0.319 | +| clip_range | 0.0706 | +| entropy_loss | -6.41 | +| explained_variance | 0.266 | +| learning_rate | 4.58e-05 | +| loss | -0.0262 | +| n_updates | 50356 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000307 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1422 | +| iterations | 8636 | +| time_elapsed | 12429 | +| total_timesteps | 17686528 | +| train/ | | +| approx_kl | 0.01282335 | +| clip_fraction | 0.37 | +| clip_range | 0.0706 | +| entropy_loss | -6.09 | +| explained_variance | 0.362 | +| learning_rate | 4.58e-05 | +| loss | -0.0356 | +| n_updates | 50360 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000132 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1422 | +| iterations | 8637 | +| time_elapsed | 12431 | +| total_timesteps | 17688576 | +| train/ | | +| approx_kl | 0.0132528385 | +| clip_fraction | 0.356 | +| clip_range | 0.0706 | +| entropy_loss | -6.62 | +| explained_variance | 0.218 | +| learning_rate | 4.58e-05 | +| loss | -0.0306 | +| n_updates | 50364 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000209 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1422 | +| iterations | 8638 | +| time_elapsed | 12432 | +| total_timesteps | 17690624 | +| train/ | | +| approx_kl | 0.012120125 | +| clip_fraction | 0.369 | +| clip_range | 0.0706 | +| entropy_loss | -6.25 | +| explained_variance | 0.758 | +| learning_rate | 4.58e-05 | +| loss | -0.034 | +| n_updates | 50368 | +| policy_gradient_loss | -0.0208 | +| value_loss | 6.28e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1422 | +| iterations | 8639 | +| time_elapsed | 12434 | +| total_timesteps | 17692672 | +| train/ | | +| approx_kl | 0.012549838 | +| clip_fraction | 0.372 | +| clip_range | 0.0706 | +| entropy_loss | -6.47 | +| explained_variance | 0.317 | +| learning_rate | 4.58e-05 | +| loss | -0.0253 | +| n_updates | 50372 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000317 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1422 | +| iterations | 8640 | +| time_elapsed | 12435 | +| total_timesteps | 17694720 | +| train/ | | +| approx_kl | 0.011367962 | +| clip_fraction | 0.343 | +| clip_range | 0.0706 | +| entropy_loss | -6.86 | +| explained_variance | -0.0461 | +| learning_rate | 4.58e-05 | +| loss | -0.0314 | +| n_updates | 50376 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000136 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1422 | +| iterations | 8641 | +| time_elapsed | 12436 | +| total_timesteps | 17696768 | +| train/ | | +| approx_kl | 0.012121283 | +| clip_fraction | 0.347 | +| clip_range | 0.0706 | +| entropy_loss | -6.61 | +| explained_variance | 0.302 | +| learning_rate | 4.58e-05 | +| loss | -0.0338 | +| n_updates | 50380 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000254 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1422 | +| iterations | 8642 | +| time_elapsed | 12438 | +| total_timesteps | 17698816 | +| train/ | | +| approx_kl | 0.014661806 | +| clip_fraction | 0.363 | +| clip_range | 0.0706 | +| entropy_loss | -6.52 | +| explained_variance | 0.507 | +| learning_rate | 4.58e-05 | +| loss | -0.0326 | +| n_updates | 50384 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000112 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1422 | +| iterations | 8643 | +| time_elapsed | 12439 | +| total_timesteps | 17700864 | +| train/ | | +| approx_kl | 0.011325169 | +| clip_fraction | 0.342 | +| clip_range | 0.0706 | +| entropy_loss | -6.84 | +| explained_variance | 0.315 | +| learning_rate | 4.58e-05 | +| loss | -0.0292 | +| n_updates | 50388 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000156 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1422 | +| iterations | 8644 | +| time_elapsed | 12441 | +| total_timesteps | 17702912 | +| train/ | | +| approx_kl | 0.014274868 | +| clip_fraction | 0.353 | +| clip_range | 0.0706 | +| entropy_loss | -6.5 | +| explained_variance | 0.432 | +| learning_rate | 4.58e-05 | +| loss | -0.0294 | +| n_updates | 50392 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000203 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1422 | +| iterations | 8645 | +| time_elapsed | 12442 | +| total_timesteps | 17704960 | +| train/ | | +| approx_kl | 0.01252839 | +| clip_fraction | 0.346 | +| clip_range | 0.0706 | +| entropy_loss | -6.06 | +| explained_variance | 0.286 | +| learning_rate | 4.58e-05 | +| loss | -0.0319 | +| n_updates | 50396 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000335 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1422 | +| iterations | 8646 | +| time_elapsed | 12444 | +| total_timesteps | 17707008 | +| train/ | | +| approx_kl | 0.013629142 | +| clip_fraction | 0.371 | +| clip_range | 0.0706 | +| entropy_loss | -6.77 | +| explained_variance | 0.397 | +| learning_rate | 4.58e-05 | +| loss | -0.0329 | +| n_updates | 50400 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000135 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1422 | +| iterations | 8647 | +| time_elapsed | 12445 | +| total_timesteps | 17709056 | +| train/ | | +| approx_kl | 0.012840407 | +| clip_fraction | 0.323 | +| clip_range | 0.0706 | +| entropy_loss | -5.98 | +| explained_variance | 0.526 | +| learning_rate | 4.58e-05 | +| loss | -0.02 | +| n_updates | 50404 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000253 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1422 | +| iterations | 8648 | +| time_elapsed | 12446 | +| total_timesteps | 17711104 | +| train/ | | +| approx_kl | 0.013008704 | +| clip_fraction | 0.36 | +| clip_range | 0.0706 | +| entropy_loss | -6.52 | +| explained_variance | 0.226 | +| learning_rate | 4.58e-05 | +| loss | -0.0387 | +| n_updates | 50408 | +| policy_gradient_loss | -0.0224 | +| value_loss | 0.000136 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1422 | +| iterations | 8649 | +| time_elapsed | 12448 | +| total_timesteps | 17713152 | +| train/ | | +| approx_kl | 0.011517348 | +| clip_fraction | 0.337 | +| clip_range | 0.0706 | +| entropy_loss | -6.81 | +| explained_variance | 0.114 | +| learning_rate | 4.58e-05 | +| loss | -0.0313 | +| n_updates | 50412 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000186 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1422 | +| iterations | 8650 | +| time_elapsed | 12449 | +| total_timesteps | 17715200 | +| train/ | | +| approx_kl | 0.016063359 | +| clip_fraction | 0.363 | +| clip_range | 0.0706 | +| entropy_loss | -6.92 | +| explained_variance | -0.143 | +| learning_rate | 4.58e-05 | +| loss | -0.032 | +| n_updates | 50416 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000165 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1422 | +| iterations | 8651 | +| time_elapsed | 12451 | +| total_timesteps | 17717248 | +| train/ | | +| approx_kl | 0.013345705 | +| clip_fraction | 0.331 | +| clip_range | 0.0706 | +| entropy_loss | -6.62 | +| explained_variance | 0.132 | +| learning_rate | 4.58e-05 | +| loss | -0.0291 | +| n_updates | 50420 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000246 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1422 | +| iterations | 8652 | +| time_elapsed | 12452 | +| total_timesteps | 17719296 | +| train/ | | +| approx_kl | 0.0139232185 | +| clip_fraction | 0.359 | +| clip_range | 0.0706 | +| entropy_loss | -5.76 | +| explained_variance | 0.637 | +| learning_rate | 4.58e-05 | +| loss | -0.0318 | +| n_updates | 50424 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000131 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1422 | +| iterations | 8653 | +| time_elapsed | 12454 | +| total_timesteps | 17721344 | +| train/ | | +| approx_kl | 0.013786618 | +| clip_fraction | 0.339 | +| clip_range | 0.0706 | +| entropy_loss | -6.6 | +| explained_variance | 0.304 | +| learning_rate | 4.58e-05 | +| loss | -0.0268 | +| n_updates | 50428 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000165 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1422 | +| iterations | 8654 | +| time_elapsed | 12455 | +| total_timesteps | 17723392 | +| train/ | | +| approx_kl | 0.012736381 | +| clip_fraction | 0.344 | +| clip_range | 0.0706 | +| entropy_loss | -6.68 | +| explained_variance | 0.283 | +| learning_rate | 4.58e-05 | +| loss | -0.0319 | +| n_updates | 50432 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000148 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1422 | +| iterations | 8655 | +| time_elapsed | 12456 | +| total_timesteps | 17725440 | +| train/ | | +| approx_kl | 0.009612915 | +| clip_fraction | 0.325 | +| clip_range | 0.0706 | +| entropy_loss | -6.3 | +| explained_variance | 0.402 | +| learning_rate | 4.58e-05 | +| loss | -0.0253 | +| n_updates | 50436 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000367 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1422 | +| iterations | 8656 | +| time_elapsed | 12458 | +| total_timesteps | 17727488 | +| train/ | | +| approx_kl | 0.012475154 | +| clip_fraction | 0.305 | +| clip_range | 0.0706 | +| entropy_loss | -6.54 | +| explained_variance | 0.151 | +| learning_rate | 4.58e-05 | +| loss | -0.0291 | +| n_updates | 50440 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000258 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1422 | +| iterations | 8657 | +| time_elapsed | 12459 | +| total_timesteps | 17729536 | +| train/ | | +| approx_kl | 0.012582473 | +| clip_fraction | 0.334 | +| clip_range | 0.0706 | +| entropy_loss | -6.33 | +| explained_variance | 0.42 | +| learning_rate | 4.58e-05 | +| loss | -0.0296 | +| n_updates | 50444 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000244 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1422 | +| iterations | 8658 | +| time_elapsed | 12461 | +| total_timesteps | 17731584 | +| train/ | | +| approx_kl | 0.012064485 | +| clip_fraction | 0.372 | +| clip_range | 0.0706 | +| entropy_loss | -6.71 | +| explained_variance | 0.374 | +| learning_rate | 4.58e-05 | +| loss | -0.034 | +| n_updates | 50448 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000156 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1422 | +| iterations | 8659 | +| time_elapsed | 12462 | +| total_timesteps | 17733632 | +| train/ | | +| approx_kl | 0.01604947 | +| clip_fraction | 0.366 | +| clip_range | 0.0706 | +| entropy_loss | -6.79 | +| explained_variance | -0.214 | +| learning_rate | 4.58e-05 | +| loss | -0.0386 | +| n_updates | 50452 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000136 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1422 | +| iterations | 8660 | +| time_elapsed | 12464 | +| total_timesteps | 17735680 | +| train/ | | +| approx_kl | 0.013034688 | +| clip_fraction | 0.377 | +| clip_range | 0.0706 | +| entropy_loss | -6.76 | +| explained_variance | -0.186 | +| learning_rate | 4.58e-05 | +| loss | -0.0321 | +| n_updates | 50456 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000144 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1422 | +| iterations | 8661 | +| time_elapsed | 12465 | +| total_timesteps | 17737728 | +| train/ | | +| approx_kl | 0.015968053 | +| clip_fraction | 0.33 | +| clip_range | 0.0706 | +| entropy_loss | -6.16 | +| explained_variance | 0.0453 | +| learning_rate | 4.58e-05 | +| loss | -0.0286 | +| n_updates | 50460 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000187 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1422 | +| iterations | 8662 | +| time_elapsed | 12467 | +| total_timesteps | 17739776 | +| train/ | | +| approx_kl | 0.016503112 | +| clip_fraction | 0.371 | +| clip_range | 0.0706 | +| entropy_loss | -6.51 | +| explained_variance | 0.142 | +| learning_rate | 4.58e-05 | +| loss | -0.0322 | +| n_updates | 50464 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000253 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1422 | +| iterations | 8663 | +| time_elapsed | 12468 | +| total_timesteps | 17741824 | +| train/ | | +| approx_kl | 0.014937075 | +| clip_fraction | 0.357 | +| clip_range | 0.0706 | +| entropy_loss | -6.59 | +| explained_variance | 0.404 | +| learning_rate | 4.58e-05 | +| loss | -0.0341 | +| n_updates | 50468 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000119 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1422 | +| iterations | 8664 | +| time_elapsed | 12469 | +| total_timesteps | 17743872 | +| train/ | | +| approx_kl | 0.01556694 | +| clip_fraction | 0.33 | +| clip_range | 0.0706 | +| entropy_loss | -6.36 | +| explained_variance | 0.254 | +| learning_rate | 4.58e-05 | +| loss | -0.0268 | +| n_updates | 50472 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.00017 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1422 | +| iterations | 8665 | +| time_elapsed | 12471 | +| total_timesteps | 17745920 | +| train/ | | +| approx_kl | 0.013355843 | +| clip_fraction | 0.343 | +| clip_range | 0.0706 | +| entropy_loss | -6.53 | +| explained_variance | 0.421 | +| learning_rate | 4.58e-05 | +| loss | -0.0233 | +| n_updates | 50476 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000218 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1422 | +| iterations | 8666 | +| time_elapsed | 12472 | +| total_timesteps | 17747968 | +| train/ | | +| approx_kl | 0.01171877 | +| clip_fraction | 0.34 | +| clip_range | 0.0706 | +| entropy_loss | -6.51 | +| explained_variance | 0.0845 | +| learning_rate | 4.58e-05 | +| loss | -0.0274 | +| n_updates | 50480 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000113 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1422 | +| iterations | 8667 | +| time_elapsed | 12474 | +| total_timesteps | 17750016 | +| train/ | | +| approx_kl | 0.011483807 | +| clip_fraction | 0.314 | +| clip_range | 0.0706 | +| entropy_loss | -6.86 | +| explained_variance | 0.225 | +| learning_rate | 4.58e-05 | +| loss | -0.0285 | +| n_updates | 50484 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000176 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1422 | +| iterations | 8668 | +| time_elapsed | 12475 | +| total_timesteps | 17752064 | +| train/ | | +| approx_kl | 0.013059891 | +| clip_fraction | 0.321 | +| clip_range | 0.0706 | +| entropy_loss | -6.52 | +| explained_variance | 0.31 | +| learning_rate | 4.58e-05 | +| loss | -0.0311 | +| n_updates | 50488 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000168 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1422 | +| iterations | 8669 | +| time_elapsed | 12477 | +| total_timesteps | 17754112 | +| train/ | | +| approx_kl | 0.01146383 | +| clip_fraction | 0.326 | +| clip_range | 0.0706 | +| entropy_loss | -6.47 | +| explained_variance | 0.52 | +| learning_rate | 4.58e-05 | +| loss | -0.0268 | +| n_updates | 50492 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000154 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1422 | +| iterations | 8670 | +| time_elapsed | 12478 | +| total_timesteps | 17756160 | +| train/ | | +| approx_kl | 0.011073025 | +| clip_fraction | 0.345 | +| clip_range | 0.0706 | +| entropy_loss | -6.96 | +| explained_variance | 0.431 | +| learning_rate | 4.58e-05 | +| loss | -0.0286 | +| n_updates | 50496 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000123 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1422 | +| iterations | 8671 | +| time_elapsed | 12480 | +| total_timesteps | 17758208 | +| train/ | | +| approx_kl | 0.011505065 | +| clip_fraction | 0.312 | +| clip_range | 0.0706 | +| entropy_loss | -6.5 | +| explained_variance | 0.438 | +| learning_rate | 4.58e-05 | +| loss | -0.0292 | +| n_updates | 50500 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000192 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1422 | +| iterations | 8672 | +| time_elapsed | 12481 | +| total_timesteps | 17760256 | +| train/ | | +| approx_kl | 0.0117709525 | +| clip_fraction | 0.343 | +| clip_range | 0.0706 | +| entropy_loss | -6.68 | +| explained_variance | 0.263 | +| learning_rate | 4.58e-05 | +| loss | -0.0332 | +| n_updates | 50504 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000158 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1422 | +| iterations | 8673 | +| time_elapsed | 12483 | +| total_timesteps | 17762304 | +| train/ | | +| approx_kl | 0.011624056 | +| clip_fraction | 0.344 | +| clip_range | 0.0706 | +| entropy_loss | -6.8 | +| explained_variance | 0.349 | +| learning_rate | 4.58e-05 | +| loss | -0.0307 | +| n_updates | 50508 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000123 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1422 | +| iterations | 8674 | +| time_elapsed | 12484 | +| total_timesteps | 17764352 | +| train/ | | +| approx_kl | 0.013760397 | +| clip_fraction | 0.325 | +| clip_range | 0.0706 | +| entropy_loss | -6.73 | +| explained_variance | 0.568 | +| learning_rate | 4.58e-05 | +| loss | -0.0337 | +| n_updates | 50512 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000119 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1422 | +| iterations | 8675 | +| time_elapsed | 12486 | +| total_timesteps | 17766400 | +| train/ | | +| approx_kl | 0.013322204 | +| clip_fraction | 0.328 | +| clip_range | 0.0706 | +| entropy_loss | -6.74 | +| explained_variance | 0.312 | +| learning_rate | 4.58e-05 | +| loss | -0.0301 | +| n_updates | 50516 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000138 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1422 | +| iterations | 8676 | +| time_elapsed | 12487 | +| total_timesteps | 17768448 | +| train/ | | +| approx_kl | 0.01207272 | +| clip_fraction | 0.328 | +| clip_range | 0.0706 | +| entropy_loss | -6.64 | +| explained_variance | 0.00602 | +| learning_rate | 4.58e-05 | +| loss | -0.0241 | +| n_updates | 50520 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000267 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1422 | +| iterations | 8677 | +| time_elapsed | 12489 | +| total_timesteps | 17770496 | +| train/ | | +| approx_kl | 0.011669662 | +| clip_fraction | 0.335 | +| clip_range | 0.0706 | +| entropy_loss | -6.47 | +| explained_variance | 0.495 | +| learning_rate | 4.58e-05 | +| loss | -0.0288 | +| n_updates | 50524 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000161 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1422 | +| iterations | 8678 | +| time_elapsed | 12490 | +| total_timesteps | 17772544 | +| train/ | | +| approx_kl | 0.0112884715 | +| clip_fraction | 0.349 | +| clip_range | 0.0706 | +| entropy_loss | -6.48 | +| explained_variance | 0.538 | +| learning_rate | 4.58e-05 | +| loss | -0.031 | +| n_updates | 50528 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000141 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1422 | +| iterations | 8679 | +| time_elapsed | 12491 | +| total_timesteps | 17774592 | +| train/ | | +| approx_kl | 0.013009567 | +| clip_fraction | 0.314 | +| clip_range | 0.0706 | +| entropy_loss | -6.17 | +| explained_variance | 0.307 | +| learning_rate | 4.58e-05 | +| loss | -0.0292 | +| n_updates | 50532 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000475 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1422 | +| iterations | 8680 | +| time_elapsed | 12493 | +| total_timesteps | 17776640 | +| train/ | | +| approx_kl | 0.011538599 | +| clip_fraction | 0.338 | +| clip_range | 0.0706 | +| entropy_loss | -6.05 | +| explained_variance | 0.627 | +| learning_rate | 4.58e-05 | +| loss | -0.035 | +| n_updates | 50536 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.00012 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1422 | +| iterations | 8681 | +| time_elapsed | 12494 | +| total_timesteps | 17778688 | +| train/ | | +| approx_kl | 0.017255694 | +| clip_fraction | 0.365 | +| clip_range | 0.0706 | +| entropy_loss | -6.71 | +| explained_variance | -0.204 | +| learning_rate | 4.58e-05 | +| loss | -0.0333 | +| n_updates | 50540 | +| policy_gradient_loss | -0.0222 | +| value_loss | 0.000165 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1422 | +| iterations | 8682 | +| time_elapsed | 12496 | +| total_timesteps | 17780736 | +| train/ | | +| approx_kl | 0.016020795 | +| clip_fraction | 0.382 | +| clip_range | 0.0706 | +| entropy_loss | -6.82 | +| explained_variance | -0.0458 | +| learning_rate | 4.58e-05 | +| loss | -0.0305 | +| n_updates | 50544 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000174 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1422 | +| iterations | 8683 | +| time_elapsed | 12497 | +| total_timesteps | 17782784 | +| train/ | | +| approx_kl | 0.013017518 | +| clip_fraction | 0.362 | +| clip_range | 0.0706 | +| entropy_loss | -6.86 | +| explained_variance | 0.143 | +| learning_rate | 4.58e-05 | +| loss | -0.0265 | +| n_updates | 50548 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000191 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1422 | +| iterations | 8684 | +| time_elapsed | 12499 | +| total_timesteps | 17784832 | +| train/ | | +| approx_kl | 0.011841615 | +| clip_fraction | 0.326 | +| clip_range | 0.0706 | +| entropy_loss | -5.97 | +| explained_variance | 0.526 | +| learning_rate | 4.58e-05 | +| loss | -0.0255 | +| n_updates | 50552 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000261 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1422 | +| iterations | 8685 | +| time_elapsed | 12500 | +| total_timesteps | 17786880 | +| train/ | | +| approx_kl | 0.01167364 | +| clip_fraction | 0.358 | +| clip_range | 0.0706 | +| entropy_loss | -6.62 | +| explained_variance | 0.229 | +| learning_rate | 4.58e-05 | +| loss | -0.0308 | +| n_updates | 50556 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000283 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1422 | +| iterations | 8686 | +| time_elapsed | 12501 | +| total_timesteps | 17788928 | +| train/ | | +| approx_kl | 0.012798264 | +| clip_fraction | 0.357 | +| clip_range | 0.0706 | +| entropy_loss | -6.69 | +| explained_variance | 0.369 | +| learning_rate | 4.58e-05 | +| loss | -0.0303 | +| n_updates | 50560 | +| policy_gradient_loss | -0.0221 | +| value_loss | 0.000112 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1422 | +| iterations | 8687 | +| time_elapsed | 12503 | +| total_timesteps | 17790976 | +| train/ | | +| approx_kl | 0.015413778 | +| clip_fraction | 0.364 | +| clip_range | 0.0706 | +| entropy_loss | -6.41 | +| explained_variance | 0.306 | +| learning_rate | 4.58e-05 | +| loss | -0.0322 | +| n_updates | 50564 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.00024 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1422 | +| iterations | 8688 | +| time_elapsed | 12504 | +| total_timesteps | 17793024 | +| train/ | | +| approx_kl | 0.015954347 | +| clip_fraction | 0.343 | +| clip_range | 0.0706 | +| entropy_loss | -6.23 | +| explained_variance | 0.504 | +| learning_rate | 4.58e-05 | +| loss | -0.0294 | +| n_updates | 50568 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000188 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1422 | +| iterations | 8689 | +| time_elapsed | 12506 | +| total_timesteps | 17795072 | +| train/ | | +| approx_kl | 0.013688838 | +| clip_fraction | 0.37 | +| clip_range | 0.0706 | +| entropy_loss | -6.62 | +| explained_variance | -0.0817 | +| learning_rate | 4.58e-05 | +| loss | -0.0351 | +| n_updates | 50572 | +| policy_gradient_loss | -0.0222 | +| value_loss | 0.000189 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1422 | +| iterations | 8690 | +| time_elapsed | 12507 | +| total_timesteps | 17797120 | +| train/ | | +| approx_kl | 0.012444068 | +| clip_fraction | 0.373 | +| clip_range | 0.0706 | +| entropy_loss | -6.95 | +| explained_variance | -0.339 | +| learning_rate | 4.58e-05 | +| loss | -0.0352 | +| n_updates | 50576 | +| policy_gradient_loss | -0.0225 | +| value_loss | 0.000108 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1422 | +| iterations | 8691 | +| time_elapsed | 12509 | +| total_timesteps | 17799168 | +| train/ | | +| approx_kl | 0.012315411 | +| clip_fraction | 0.331 | +| clip_range | 0.0706 | +| entropy_loss | -6.48 | +| explained_variance | 0.224 | +| learning_rate | 4.58e-05 | +| loss | -0.0294 | +| n_updates | 50580 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.0003 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1422 | +| iterations | 8692 | +| time_elapsed | 12510 | +| total_timesteps | 17801216 | +| train/ | | +| approx_kl | 0.014955372 | +| clip_fraction | 0.365 | +| clip_range | 0.0706 | +| entropy_loss | -6.65 | +| explained_variance | 0.206 | +| learning_rate | 4.58e-05 | +| loss | -0.0329 | +| n_updates | 50584 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000143 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1422 | +| iterations | 8693 | +| time_elapsed | 12512 | +| total_timesteps | 17803264 | +| train/ | | +| approx_kl | 0.012312286 | +| clip_fraction | 0.334 | +| clip_range | 0.0705 | +| entropy_loss | -6.79 | +| explained_variance | 0.412 | +| learning_rate | 4.58e-05 | +| loss | -0.0292 | +| n_updates | 50588 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000212 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1422 | +| iterations | 8694 | +| time_elapsed | 12513 | +| total_timesteps | 17805312 | +| train/ | | +| approx_kl | 0.013003424 | +| clip_fraction | 0.307 | +| clip_range | 0.0705 | +| entropy_loss | -6.61 | +| explained_variance | 0.303 | +| learning_rate | 4.58e-05 | +| loss | -0.0289 | +| n_updates | 50592 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000156 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1422 | +| iterations | 8695 | +| time_elapsed | 12514 | +| total_timesteps | 17807360 | +| train/ | | +| approx_kl | 0.012307959 | +| clip_fraction | 0.312 | +| clip_range | 0.0705 | +| entropy_loss | -6.32 | +| explained_variance | 0.329 | +| learning_rate | 4.58e-05 | +| loss | -0.0193 | +| n_updates | 50596 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000302 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1422 | +| iterations | 8696 | +| time_elapsed | 12516 | +| total_timesteps | 17809408 | +| train/ | | +| approx_kl | 0.014532359 | +| clip_fraction | 0.354 | +| clip_range | 0.0705 | +| entropy_loss | -5.86 | +| explained_variance | 0.742 | +| learning_rate | 4.58e-05 | +| loss | -0.0274 | +| n_updates | 50600 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000107 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1422 | +| iterations | 8697 | +| time_elapsed | 12517 | +| total_timesteps | 17811456 | +| train/ | | +| approx_kl | 0.012639001 | +| clip_fraction | 0.352 | +| clip_range | 0.0705 | +| entropy_loss | -6.47 | +| explained_variance | 0.281 | +| learning_rate | 4.58e-05 | +| loss | -0.0333 | +| n_updates | 50604 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000107 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1422 | +| iterations | 8698 | +| time_elapsed | 12519 | +| total_timesteps | 17813504 | +| train/ | | +| approx_kl | 0.011474039 | +| clip_fraction | 0.339 | +| clip_range | 0.0705 | +| entropy_loss | -6.9 | +| explained_variance | 0.421 | +| learning_rate | 4.58e-05 | +| loss | -0.0315 | +| n_updates | 50608 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000118 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1422 | +| iterations | 8699 | +| time_elapsed | 12520 | +| total_timesteps | 17815552 | +| train/ | | +| approx_kl | 0.015460366 | +| clip_fraction | 0.341 | +| clip_range | 0.0705 | +| entropy_loss | -6.78 | +| explained_variance | 0.277 | +| learning_rate | 4.58e-05 | +| loss | -0.0282 | +| n_updates | 50612 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000214 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1422 | +| iterations | 8700 | +| time_elapsed | 12522 | +| total_timesteps | 17817600 | +| train/ | | +| approx_kl | 0.01281422 | +| clip_fraction | 0.348 | +| clip_range | 0.0705 | +| entropy_loss | -6.65 | +| explained_variance | 0.382 | +| learning_rate | 4.58e-05 | +| loss | -0.0246 | +| n_updates | 50616 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000128 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1422 | +| iterations | 8701 | +| time_elapsed | 12523 | +| total_timesteps | 17819648 | +| train/ | | +| approx_kl | 0.010842973 | +| clip_fraction | 0.327 | +| clip_range | 0.0705 | +| entropy_loss | -6.48 | +| explained_variance | 0.361 | +| learning_rate | 4.58e-05 | +| loss | -0.0253 | +| n_updates | 50620 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000385 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1422 | +| iterations | 8702 | +| time_elapsed | 12524 | +| total_timesteps | 17821696 | +| train/ | | +| approx_kl | 0.014258568 | +| clip_fraction | 0.364 | +| clip_range | 0.0705 | +| entropy_loss | -6.72 | +| explained_variance | -0.164 | +| learning_rate | 4.58e-05 | +| loss | -0.0367 | +| n_updates | 50624 | +| policy_gradient_loss | -0.0247 | +| value_loss | 8.84e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1422 | +| iterations | 8703 | +| time_elapsed | 12526 | +| total_timesteps | 17823744 | +| train/ | | +| approx_kl | 0.013935057 | +| clip_fraction | 0.331 | +| clip_range | 0.0705 | +| entropy_loss | -7.01 | +| explained_variance | 0.342 | +| learning_rate | 4.58e-05 | +| loss | -0.0292 | +| n_updates | 50628 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000144 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1422 | +| iterations | 8704 | +| time_elapsed | 12527 | +| total_timesteps | 17825792 | +| train/ | | +| approx_kl | 0.015595377 | +| clip_fraction | 0.382 | +| clip_range | 0.0705 | +| entropy_loss | -5.87 | +| explained_variance | 0.806 | +| learning_rate | 4.58e-05 | +| loss | -0.0284 | +| n_updates | 50632 | +| policy_gradient_loss | -0.0198 | +| value_loss | 8.04e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1422 | +| iterations | 8705 | +| time_elapsed | 12529 | +| total_timesteps | 17827840 | +| train/ | | +| approx_kl | 0.016106486 | +| clip_fraction | 0.377 | +| clip_range | 0.0705 | +| entropy_loss | -6.2 | +| explained_variance | -0.978 | +| learning_rate | 4.58e-05 | +| loss | -0.0366 | +| n_updates | 50636 | +| policy_gradient_loss | -0.0178 | +| value_loss | 9.6e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1422 | +| iterations | 8706 | +| time_elapsed | 12530 | +| total_timesteps | 17829888 | +| train/ | | +| approx_kl | 0.010214042 | +| clip_fraction | 0.344 | +| clip_range | 0.0705 | +| entropy_loss | -6.53 | +| explained_variance | -0.0496 | +| learning_rate | 4.58e-05 | +| loss | -0.0261 | +| n_updates | 50640 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000257 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1422 | +| iterations | 8707 | +| time_elapsed | 12532 | +| total_timesteps | 17831936 | +| train/ | | +| approx_kl | 0.012211597 | +| clip_fraction | 0.324 | +| clip_range | 0.0705 | +| entropy_loss | -6.33 | +| explained_variance | 0.11 | +| learning_rate | 4.58e-05 | +| loss | -0.0249 | +| n_updates | 50644 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000256 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1422 | +| iterations | 8708 | +| time_elapsed | 12533 | +| total_timesteps | 17833984 | +| train/ | | +| approx_kl | 0.014289087 | +| clip_fraction | 0.376 | +| clip_range | 0.0705 | +| entropy_loss | -6.61 | +| explained_variance | 0.192 | +| learning_rate | 4.58e-05 | +| loss | -0.0314 | +| n_updates | 50648 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000181 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1422 | +| iterations | 8709 | +| time_elapsed | 12535 | +| total_timesteps | 17836032 | +| train/ | | +| approx_kl | 0.011598813 | +| clip_fraction | 0.335 | +| clip_range | 0.0705 | +| entropy_loss | -6.95 | +| explained_variance | 0.325 | +| learning_rate | 4.58e-05 | +| loss | -0.0318 | +| n_updates | 50652 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000133 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1422 | +| iterations | 8710 | +| time_elapsed | 12536 | +| total_timesteps | 17838080 | +| train/ | | +| approx_kl | 0.012993416 | +| clip_fraction | 0.335 | +| clip_range | 0.0705 | +| entropy_loss | -6.61 | +| explained_variance | 0.479 | +| learning_rate | 4.58e-05 | +| loss | -0.033 | +| n_updates | 50656 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000243 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1422 | +| iterations | 8711 | +| time_elapsed | 12537 | +| total_timesteps | 17840128 | +| train/ | | +| approx_kl | 0.014673345 | +| clip_fraction | 0.338 | +| clip_range | 0.0705 | +| entropy_loss | -6.02 | +| explained_variance | 0.36 | +| learning_rate | 4.58e-05 | +| loss | -0.0272 | +| n_updates | 50660 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000249 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1422 | +| iterations | 8712 | +| time_elapsed | 12539 | +| total_timesteps | 17842176 | +| train/ | | +| approx_kl | 0.01314846 | +| clip_fraction | 0.336 | +| clip_range | 0.0705 | +| entropy_loss | -6.64 | +| explained_variance | 0.00758 | +| learning_rate | 4.58e-05 | +| loss | -0.0322 | +| n_updates | 50664 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000237 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1422 | +| iterations | 8713 | +| time_elapsed | 12540 | +| total_timesteps | 17844224 | +| train/ | | +| approx_kl | 0.0125393635 | +| clip_fraction | 0.351 | +| clip_range | 0.0705 | +| entropy_loss | -6.25 | +| explained_variance | 0.599 | +| learning_rate | 4.58e-05 | +| loss | -0.0327 | +| n_updates | 50668 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000135 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1422 | +| iterations | 8714 | +| time_elapsed | 12542 | +| total_timesteps | 17846272 | +| train/ | | +| approx_kl | 0.015095854 | +| clip_fraction | 0.362 | +| clip_range | 0.0705 | +| entropy_loss | -7.07 | +| explained_variance | -0.128 | +| learning_rate | 4.58e-05 | +| loss | -0.0323 | +| n_updates | 50672 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000116 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1422 | +| iterations | 8715 | +| time_elapsed | 12543 | +| total_timesteps | 17848320 | +| train/ | | +| approx_kl | 0.012877399 | +| clip_fraction | 0.344 | +| clip_range | 0.0705 | +| entropy_loss | -6.97 | +| explained_variance | -0.0891 | +| learning_rate | 4.58e-05 | +| loss | -0.0297 | +| n_updates | 50676 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000182 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1422 | +| iterations | 8716 | +| time_elapsed | 12545 | +| total_timesteps | 17850368 | +| train/ | | +| approx_kl | 0.011966532 | +| clip_fraction | 0.33 | +| clip_range | 0.0705 | +| entropy_loss | -6.13 | +| explained_variance | 0.537 | +| learning_rate | 4.58e-05 | +| loss | -0.0249 | +| n_updates | 50680 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000257 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1422 | +| iterations | 8717 | +| time_elapsed | 12546 | +| total_timesteps | 17852416 | +| train/ | | +| approx_kl | 0.014538182 | +| clip_fraction | 0.367 | +| clip_range | 0.0705 | +| entropy_loss | -6.27 | +| explained_variance | 0.625 | +| learning_rate | 4.58e-05 | +| loss | -0.0354 | +| n_updates | 50684 | +| policy_gradient_loss | -0.0236 | +| value_loss | 7.64e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1422 | +| iterations | 8718 | +| time_elapsed | 12548 | +| total_timesteps | 17854464 | +| train/ | | +| approx_kl | 0.011649115 | +| clip_fraction | 0.327 | +| clip_range | 0.0705 | +| entropy_loss | -6.62 | +| explained_variance | 0.34 | +| learning_rate | 4.58e-05 | +| loss | -0.0318 | +| n_updates | 50688 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000132 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1422 | +| iterations | 8719 | +| time_elapsed | 12549 | +| total_timesteps | 17856512 | +| train/ | | +| approx_kl | 0.011266654 | +| clip_fraction | 0.329 | +| clip_range | 0.0705 | +| entropy_loss | -6.11 | +| explained_variance | 0.42 | +| learning_rate | 4.58e-05 | +| loss | -0.0345 | +| n_updates | 50692 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000442 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1422 | +| iterations | 8720 | +| time_elapsed | 12550 | +| total_timesteps | 17858560 | +| train/ | | +| approx_kl | 0.014107551 | +| clip_fraction | 0.385 | +| clip_range | 0.0705 | +| entropy_loss | -6.56 | +| explained_variance | 0.244 | +| learning_rate | 4.58e-05 | +| loss | -0.0456 | +| n_updates | 50696 | +| policy_gradient_loss | -0.0263 | +| value_loss | 9.26e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1422 | +| iterations | 8721 | +| time_elapsed | 12552 | +| total_timesteps | 17860608 | +| train/ | | +| approx_kl | 0.012379654 | +| clip_fraction | 0.342 | +| clip_range | 0.0705 | +| entropy_loss | -6.83 | +| explained_variance | 0.0752 | +| learning_rate | 4.58e-05 | +| loss | -0.031 | +| n_updates | 50700 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000213 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1422 | +| iterations | 8722 | +| time_elapsed | 12553 | +| total_timesteps | 17862656 | +| train/ | | +| approx_kl | 0.01631607 | +| clip_fraction | 0.393 | +| clip_range | 0.0705 | +| entropy_loss | -6.59 | +| explained_variance | 0.125 | +| learning_rate | 4.58e-05 | +| loss | -0.0343 | +| n_updates | 50704 | +| policy_gradient_loss | -0.0228 | +| value_loss | 0.000111 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1422 | +| iterations | 8723 | +| time_elapsed | 12555 | +| total_timesteps | 17864704 | +| train/ | | +| approx_kl | 0.014051642 | +| clip_fraction | 0.37 | +| clip_range | 0.0705 | +| entropy_loss | -6.65 | +| explained_variance | 0.302 | +| learning_rate | 4.58e-05 | +| loss | -0.0276 | +| n_updates | 50708 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000154 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1422 | +| iterations | 8724 | +| time_elapsed | 12556 | +| total_timesteps | 17866752 | +| train/ | | +| approx_kl | 0.015373535 | +| clip_fraction | 0.349 | +| clip_range | 0.0705 | +| entropy_loss | -6.19 | +| explained_variance | 0.296 | +| learning_rate | 4.58e-05 | +| loss | -0.02 | +| n_updates | 50712 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.0003 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1422 | +| iterations | 8725 | +| time_elapsed | 12558 | +| total_timesteps | 17868800 | +| train/ | | +| approx_kl | 0.015739365 | +| clip_fraction | 0.341 | +| clip_range | 0.0705 | +| entropy_loss | -6.03 | +| explained_variance | 0.561 | +| learning_rate | 4.58e-05 | +| loss | -0.0298 | +| n_updates | 50716 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000209 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1422 | +| iterations | 8726 | +| time_elapsed | 12559 | +| total_timesteps | 17870848 | +| train/ | | +| approx_kl | 0.014173189 | +| clip_fraction | 0.391 | +| clip_range | 0.0705 | +| entropy_loss | -6.15 | +| explained_variance | 0.37 | +| learning_rate | 4.58e-05 | +| loss | -0.0308 | +| n_updates | 50720 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000135 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1422 | +| iterations | 8727 | +| time_elapsed | 12560 | +| total_timesteps | 17872896 | +| train/ | | +| approx_kl | 0.015511299 | +| clip_fraction | 0.349 | +| clip_range | 0.0705 | +| entropy_loss | -6.55 | +| explained_variance | 0.232 | +| learning_rate | 4.58e-05 | +| loss | -0.0247 | +| n_updates | 50724 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.00024 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1422 | +| iterations | 8728 | +| time_elapsed | 12562 | +| total_timesteps | 17874944 | +| train/ | | +| approx_kl | 0.013927424 | +| clip_fraction | 0.346 | +| clip_range | 0.0705 | +| entropy_loss | -6.64 | +| explained_variance | 0.151 | +| learning_rate | 4.58e-05 | +| loss | -0.0253 | +| n_updates | 50728 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000266 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1422 | +| iterations | 8729 | +| time_elapsed | 12563 | +| total_timesteps | 17876992 | +| train/ | | +| approx_kl | 0.014335356 | +| clip_fraction | 0.366 | +| clip_range | 0.0705 | +| entropy_loss | -6.28 | +| explained_variance | 0.607 | +| learning_rate | 4.58e-05 | +| loss | -0.0379 | +| n_updates | 50732 | +| policy_gradient_loss | -0.0239 | +| value_loss | 9.32e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1422 | +| iterations | 8730 | +| time_elapsed | 12565 | +| total_timesteps | 17879040 | +| train/ | | +| approx_kl | 0.013628807 | +| clip_fraction | 0.353 | +| clip_range | 0.0705 | +| entropy_loss | -6.51 | +| explained_variance | 0.491 | +| learning_rate | 4.58e-05 | +| loss | -0.0313 | +| n_updates | 50736 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000145 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1422 | +| iterations | 8731 | +| time_elapsed | 12566 | +| total_timesteps | 17881088 | +| train/ | | +| approx_kl | 0.014132129 | +| clip_fraction | 0.354 | +| clip_range | 0.0705 | +| entropy_loss | -6.37 | +| explained_variance | 0.653 | +| learning_rate | 4.58e-05 | +| loss | -0.0389 | +| n_updates | 50740 | +| policy_gradient_loss | -0.0221 | +| value_loss | 7.76e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1422 | +| iterations | 8732 | +| time_elapsed | 12568 | +| total_timesteps | 17883136 | +| train/ | | +| approx_kl | 0.014526759 | +| clip_fraction | 0.34 | +| clip_range | 0.0705 | +| entropy_loss | -6.61 | +| explained_variance | 0.577 | +| learning_rate | 4.58e-05 | +| loss | -0.0247 | +| n_updates | 50744 | +| policy_gradient_loss | -0.0187 | +| value_loss | 9.51e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1422 | +| iterations | 8733 | +| time_elapsed | 12569 | +| total_timesteps | 17885184 | +| train/ | | +| approx_kl | 0.011335174 | +| clip_fraction | 0.323 | +| clip_range | 0.0705 | +| entropy_loss | -6.23 | +| explained_variance | 0.538 | +| learning_rate | 4.58e-05 | +| loss | -0.0244 | +| n_updates | 50748 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000166 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1422 | +| iterations | 8734 | +| time_elapsed | 12570 | +| total_timesteps | 17887232 | +| train/ | | +| approx_kl | 0.011611601 | +| clip_fraction | 0.352 | +| clip_range | 0.0705 | +| entropy_loss | -6.82 | +| explained_variance | 0.368 | +| learning_rate | 4.58e-05 | +| loss | -0.0302 | +| n_updates | 50752 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.00015 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1422 | +| iterations | 8735 | +| time_elapsed | 12572 | +| total_timesteps | 17889280 | +| train/ | | +| approx_kl | 0.015776739 | +| clip_fraction | 0.336 | +| clip_range | 0.0705 | +| entropy_loss | -6.71 | +| explained_variance | 0.265 | +| learning_rate | 4.58e-05 | +| loss | -0.0313 | +| n_updates | 50756 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000163 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1422 | +| iterations | 8736 | +| time_elapsed | 12573 | +| total_timesteps | 17891328 | +| train/ | | +| approx_kl | 0.011510905 | +| clip_fraction | 0.348 | +| clip_range | 0.0705 | +| entropy_loss | -6.65 | +| explained_variance | 0.305 | +| learning_rate | 4.58e-05 | +| loss | -0.0282 | +| n_updates | 50760 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000172 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1422 | +| iterations | 8737 | +| time_elapsed | 12575 | +| total_timesteps | 17893376 | +| train/ | | +| approx_kl | 0.011606621 | +| clip_fraction | 0.32 | +| clip_range | 0.0705 | +| entropy_loss | -5.62 | +| explained_variance | 0.429 | +| learning_rate | 4.58e-05 | +| loss | -0.0273 | +| n_updates | 50764 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000467 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1422 | +| iterations | 8738 | +| time_elapsed | 12576 | +| total_timesteps | 17895424 | +| train/ | | +| approx_kl | 0.015259002 | +| clip_fraction | 0.357 | +| clip_range | 0.0705 | +| entropy_loss | -6.16 | +| explained_variance | 0.376 | +| learning_rate | 4.58e-05 | +| loss | -0.0362 | +| n_updates | 50768 | +| policy_gradient_loss | -0.0226 | +| value_loss | 0.000169 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1422 | +| iterations | 8739 | +| time_elapsed | 12578 | +| total_timesteps | 17897472 | +| train/ | | +| approx_kl | 0.011564679 | +| clip_fraction | 0.361 | +| clip_range | 0.0705 | +| entropy_loss | -7.1 | +| explained_variance | -0.0578 | +| learning_rate | 4.57e-05 | +| loss | -0.0324 | +| n_updates | 50772 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000222 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1422 | +| iterations | 8740 | +| time_elapsed | 12579 | +| total_timesteps | 17899520 | +| train/ | | +| approx_kl | 0.015120556 | +| clip_fraction | 0.396 | +| clip_range | 0.0705 | +| entropy_loss | -6.71 | +| explained_variance | 0.238 | +| learning_rate | 4.57e-05 | +| loss | -0.0425 | +| n_updates | 50776 | +| policy_gradient_loss | -0.0233 | +| value_loss | 0.00013 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1422 | +| iterations | 8741 | +| time_elapsed | 12580 | +| total_timesteps | 17901568 | +| train/ | | +| approx_kl | 0.015708225 | +| clip_fraction | 0.355 | +| clip_range | 0.0705 | +| entropy_loss | -6.6 | +| explained_variance | 0.0328 | +| learning_rate | 4.57e-05 | +| loss | -0.0339 | +| n_updates | 50780 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000309 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1422 | +| iterations | 8742 | +| time_elapsed | 12582 | +| total_timesteps | 17903616 | +| train/ | | +| approx_kl | 0.013571551 | +| clip_fraction | 0.375 | +| clip_range | 0.0705 | +| entropy_loss | -5.8 | +| explained_variance | 0.57 | +| learning_rate | 4.57e-05 | +| loss | -0.0319 | +| n_updates | 50784 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000191 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1422 | +| iterations | 8743 | +| time_elapsed | 12583 | +| total_timesteps | 17905664 | +| train/ | | +| approx_kl | 0.014913157 | +| clip_fraction | 0.311 | +| clip_range | 0.0705 | +| entropy_loss | -6.54 | +| explained_variance | 0.154 | +| learning_rate | 4.57e-05 | +| loss | -0.0303 | +| n_updates | 50788 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000238 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1422 | +| iterations | 8744 | +| time_elapsed | 12585 | +| total_timesteps | 17907712 | +| train/ | | +| approx_kl | 0.01440679 | +| clip_fraction | 0.357 | +| clip_range | 0.0705 | +| entropy_loss | -6.96 | +| explained_variance | -0.0603 | +| learning_rate | 4.57e-05 | +| loss | -0.0366 | +| n_updates | 50792 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000201 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1422 | +| iterations | 8745 | +| time_elapsed | 12586 | +| total_timesteps | 17909760 | +| train/ | | +| approx_kl | 0.016089408 | +| clip_fraction | 0.365 | +| clip_range | 0.0705 | +| entropy_loss | -6.27 | +| explained_variance | 0.624 | +| learning_rate | 4.57e-05 | +| loss | -0.0362 | +| n_updates | 50796 | +| policy_gradient_loss | -0.0237 | +| value_loss | 0.000104 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1422 | +| iterations | 8746 | +| time_elapsed | 12588 | +| total_timesteps | 17911808 | +| train/ | | +| approx_kl | 0.019296102 | +| clip_fraction | 0.365 | +| clip_range | 0.0705 | +| entropy_loss | -6.73 | +| explained_variance | -0.335 | +| learning_rate | 4.57e-05 | +| loss | -0.0346 | +| n_updates | 50800 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000111 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1422 | +| iterations | 8747 | +| time_elapsed | 12589 | +| total_timesteps | 17913856 | +| train/ | | +| approx_kl | 0.0149631165 | +| clip_fraction | 0.348 | +| clip_range | 0.0705 | +| entropy_loss | -6.4 | +| explained_variance | 0.517 | +| learning_rate | 4.57e-05 | +| loss | -0.0315 | +| n_updates | 50804 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000122 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1422 | +| iterations | 8748 | +| time_elapsed | 12591 | +| total_timesteps | 17915904 | +| train/ | | +| approx_kl | 0.016021673 | +| clip_fraction | 0.36 | +| clip_range | 0.0705 | +| entropy_loss | -6.32 | +| explained_variance | 0.513 | +| learning_rate | 4.57e-05 | +| loss | -0.0267 | +| n_updates | 50808 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000137 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1422 | +| iterations | 8749 | +| time_elapsed | 12592 | +| total_timesteps | 17917952 | +| train/ | | +| approx_kl | 0.015000944 | +| clip_fraction | 0.346 | +| clip_range | 0.0705 | +| entropy_loss | -6.53 | +| explained_variance | 0.252 | +| learning_rate | 4.57e-05 | +| loss | -0.0276 | +| n_updates | 50812 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000194 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1422 | +| iterations | 8750 | +| time_elapsed | 12593 | +| total_timesteps | 17920000 | +| train/ | | +| approx_kl | 0.013131031 | +| clip_fraction | 0.328 | +| clip_range | 0.0705 | +| entropy_loss | -6.27 | +| explained_variance | 0.637 | +| learning_rate | 4.57e-05 | +| loss | -0.0307 | +| n_updates | 50816 | +| policy_gradient_loss | -0.0192 | +| value_loss | 9.46e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1422 | +| iterations | 8751 | +| time_elapsed | 12595 | +| total_timesteps | 17922048 | +| train/ | | +| approx_kl | 0.013070039 | +| clip_fraction | 0.341 | +| clip_range | 0.0705 | +| entropy_loss | -6.45 | +| explained_variance | 0.513 | +| learning_rate | 4.57e-05 | +| loss | -0.0284 | +| n_updates | 50820 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.00015 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1422 | +| iterations | 8752 | +| time_elapsed | 12596 | +| total_timesteps | 17924096 | +| train/ | | +| approx_kl | 0.0132108815 | +| clip_fraction | 0.31 | +| clip_range | 0.0705 | +| entropy_loss | -6.47 | +| explained_variance | 0.297 | +| learning_rate | 4.57e-05 | +| loss | -0.03 | +| n_updates | 50824 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000201 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1422 | +| iterations | 8753 | +| time_elapsed | 12598 | +| total_timesteps | 17926144 | +| train/ | | +| approx_kl | 0.012944254 | +| clip_fraction | 0.351 | +| clip_range | 0.0705 | +| entropy_loss | -6.6 | +| explained_variance | 0.21 | +| learning_rate | 4.57e-05 | +| loss | -0.0339 | +| n_updates | 50828 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000152 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1422 | +| iterations | 8754 | +| time_elapsed | 12599 | +| total_timesteps | 17928192 | +| train/ | | +| approx_kl | 0.014749199 | +| clip_fraction | 0.323 | +| clip_range | 0.0705 | +| entropy_loss | -7.11 | +| explained_variance | -0.126 | +| learning_rate | 4.57e-05 | +| loss | -0.0308 | +| n_updates | 50832 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000185 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1422 | +| iterations | 8755 | +| time_elapsed | 12601 | +| total_timesteps | 17930240 | +| train/ | | +| approx_kl | 0.010544671 | +| clip_fraction | 0.323 | +| clip_range | 0.0705 | +| entropy_loss | -6.81 | +| explained_variance | 0.0631 | +| learning_rate | 4.57e-05 | +| loss | -0.0253 | +| n_updates | 50836 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000226 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1422 | +| iterations | 8756 | +| time_elapsed | 12602 | +| total_timesteps | 17932288 | +| train/ | | +| approx_kl | 0.0105115995 | +| clip_fraction | 0.331 | +| clip_range | 0.0705 | +| entropy_loss | -6.87 | +| explained_variance | 0.208 | +| learning_rate | 4.57e-05 | +| loss | -0.0293 | +| n_updates | 50840 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000158 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1422 | +| iterations | 8757 | +| time_elapsed | 12603 | +| total_timesteps | 17934336 | +| train/ | | +| approx_kl | 0.010329455 | +| clip_fraction | 0.317 | +| clip_range | 0.0705 | +| entropy_loss | -6.07 | +| explained_variance | 0.292 | +| learning_rate | 4.57e-05 | +| loss | -0.0265 | +| n_updates | 50844 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000519 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1422 | +| iterations | 8758 | +| time_elapsed | 12605 | +| total_timesteps | 17936384 | +| train/ | | +| approx_kl | 0.016229719 | +| clip_fraction | 0.386 | +| clip_range | 0.0705 | +| entropy_loss | -5.87 | +| explained_variance | 0.495 | +| learning_rate | 4.57e-05 | +| loss | -0.0359 | +| n_updates | 50848 | +| policy_gradient_loss | -0.0219 | +| value_loss | 0.000117 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1422 | +| iterations | 8759 | +| time_elapsed | 12606 | +| total_timesteps | 17938432 | +| train/ | | +| approx_kl | 0.0103807105 | +| clip_fraction | 0.332 | +| clip_range | 0.0705 | +| entropy_loss | -6.14 | +| explained_variance | 0.385 | +| learning_rate | 4.57e-05 | +| loss | -0.0284 | +| n_updates | 50852 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000296 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1422 | +| iterations | 8760 | +| time_elapsed | 12608 | +| total_timesteps | 17940480 | +| train/ | | +| approx_kl | 0.011598755 | +| clip_fraction | 0.362 | +| clip_range | 0.0705 | +| entropy_loss | -7.09 | +| explained_variance | -0.221 | +| learning_rate | 4.57e-05 | +| loss | -0.0387 | +| n_updates | 50856 | +| policy_gradient_loss | -0.0227 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1422 | +| iterations | 8761 | +| time_elapsed | 12609 | +| total_timesteps | 17942528 | +| train/ | | +| approx_kl | 0.015437946 | +| clip_fraction | 0.384 | +| clip_range | 0.0705 | +| entropy_loss | -6.8 | +| explained_variance | -0.146 | +| learning_rate | 4.57e-05 | +| loss | -0.0329 | +| n_updates | 50860 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000169 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1422 | +| iterations | 8762 | +| time_elapsed | 12611 | +| total_timesteps | 17944576 | +| train/ | | +| approx_kl | 0.014698117 | +| clip_fraction | 0.36 | +| clip_range | 0.0705 | +| entropy_loss | -6.57 | +| explained_variance | 0.334 | +| learning_rate | 4.57e-05 | +| loss | -0.029 | +| n_updates | 50864 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000133 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1422 | +| iterations | 8763 | +| time_elapsed | 12612 | +| total_timesteps | 17946624 | +| train/ | | +| approx_kl | 0.0126041975 | +| clip_fraction | 0.348 | +| clip_range | 0.0705 | +| entropy_loss | -6.43 | +| explained_variance | 0.462 | +| learning_rate | 4.57e-05 | +| loss | -0.0267 | +| n_updates | 50868 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000131 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1422 | +| iterations | 8764 | +| time_elapsed | 12614 | +| total_timesteps | 17948672 | +| train/ | | +| approx_kl | 0.013924507 | +| clip_fraction | 0.342 | +| clip_range | 0.0705 | +| entropy_loss | -6.3 | +| explained_variance | 0.317 | +| learning_rate | 4.57e-05 | +| loss | -0.0175 | +| n_updates | 50872 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000291 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1422 | +| iterations | 8765 | +| time_elapsed | 12615 | +| total_timesteps | 17950720 | +| train/ | | +| approx_kl | 0.016437292 | +| clip_fraction | 0.363 | +| clip_range | 0.0705 | +| entropy_loss | -5.99 | +| explained_variance | 0.504 | +| learning_rate | 4.57e-05 | +| loss | -0.0357 | +| n_updates | 50876 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000151 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1422 | +| iterations | 8766 | +| time_elapsed | 12617 | +| total_timesteps | 17952768 | +| train/ | | +| approx_kl | 0.015158277 | +| clip_fraction | 0.337 | +| clip_range | 0.0705 | +| entropy_loss | -6.37 | +| explained_variance | 0.0955 | +| learning_rate | 4.57e-05 | +| loss | -0.0272 | +| n_updates | 50880 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000208 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1422 | +| iterations | 8767 | +| time_elapsed | 12618 | +| total_timesteps | 17954816 | +| train/ | | +| approx_kl | 0.014154305 | +| clip_fraction | 0.367 | +| clip_range | 0.0705 | +| entropy_loss | -6.01 | +| explained_variance | 0.627 | +| learning_rate | 4.57e-05 | +| loss | -0.0311 | +| n_updates | 50884 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000108 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1422 | +| iterations | 8768 | +| time_elapsed | 12620 | +| total_timesteps | 17956864 | +| train/ | | +| approx_kl | 0.013444193 | +| clip_fraction | 0.359 | +| clip_range | 0.0705 | +| entropy_loss | -6.19 | +| explained_variance | 0.59 | +| learning_rate | 4.57e-05 | +| loss | -0.0302 | +| n_updates | 50888 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.00014 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1422 | +| iterations | 8769 | +| time_elapsed | 12621 | +| total_timesteps | 17958912 | +| train/ | | +| approx_kl | 0.014069438 | +| clip_fraction | 0.378 | +| clip_range | 0.0705 | +| entropy_loss | -6.5 | +| explained_variance | 0.232 | +| learning_rate | 4.57e-05 | +| loss | -0.0326 | +| n_updates | 50892 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000183 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1422 | +| iterations | 8770 | +| time_elapsed | 12622 | +| total_timesteps | 17960960 | +| train/ | | +| approx_kl | 0.015474806 | +| clip_fraction | 0.317 | +| clip_range | 0.0705 | +| entropy_loss | -6.47 | +| explained_variance | 0.405 | +| learning_rate | 4.57e-05 | +| loss | -0.0324 | +| n_updates | 50896 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000188 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1422 | +| iterations | 8771 | +| time_elapsed | 12624 | +| total_timesteps | 17963008 | +| train/ | | +| approx_kl | 0.015296759 | +| clip_fraction | 0.394 | +| clip_range | 0.0705 | +| entropy_loss | -6.05 | +| explained_variance | 0.471 | +| learning_rate | 4.57e-05 | +| loss | -0.0332 | +| n_updates | 50900 | +| policy_gradient_loss | -0.0245 | +| value_loss | 7.42e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1422 | +| iterations | 8772 | +| time_elapsed | 12625 | +| total_timesteps | 17965056 | +| train/ | | +| approx_kl | 0.014070215 | +| clip_fraction | 0.374 | +| clip_range | 0.0705 | +| entropy_loss | -6.34 | +| explained_variance | 0.546 | +| learning_rate | 4.57e-05 | +| loss | -0.033 | +| n_updates | 50904 | +| policy_gradient_loss | -0.0218 | +| value_loss | 6.33e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1422 | +| iterations | 8773 | +| time_elapsed | 12627 | +| total_timesteps | 17967104 | +| train/ | | +| approx_kl | 0.013036504 | +| clip_fraction | 0.327 | +| clip_range | 0.0705 | +| entropy_loss | -6.8 | +| explained_variance | 0.217 | +| learning_rate | 4.57e-05 | +| loss | -0.0312 | +| n_updates | 50908 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.00025 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1422 | +| iterations | 8774 | +| time_elapsed | 12628 | +| total_timesteps | 17969152 | +| train/ | | +| approx_kl | 0.01064459 | +| clip_fraction | 0.322 | +| clip_range | 0.0705 | +| entropy_loss | -6.28 | +| explained_variance | 0.316 | +| learning_rate | 4.57e-05 | +| loss | -0.0291 | +| n_updates | 50912 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000442 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1422 | +| iterations | 8775 | +| time_elapsed | 12630 | +| total_timesteps | 17971200 | +| train/ | | +| approx_kl | 0.013871176 | +| clip_fraction | 0.328 | +| clip_range | 0.0705 | +| entropy_loss | -6.66 | +| explained_variance | -0.203 | +| learning_rate | 4.57e-05 | +| loss | -0.0285 | +| n_updates | 50916 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000146 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1422 | +| iterations | 8776 | +| time_elapsed | 12631 | +| total_timesteps | 17973248 | +| train/ | | +| approx_kl | 0.014916347 | +| clip_fraction | 0.319 | +| clip_range | 0.0705 | +| entropy_loss | -6.33 | +| explained_variance | 0.136 | +| learning_rate | 4.57e-05 | +| loss | -0.0299 | +| n_updates | 50920 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000287 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1422 | +| iterations | 8777 | +| time_elapsed | 12633 | +| total_timesteps | 17975296 | +| train/ | | +| approx_kl | 0.012981299 | +| clip_fraction | 0.334 | +| clip_range | 0.0705 | +| entropy_loss | -5.25 | +| explained_variance | 0.529 | +| learning_rate | 4.57e-05 | +| loss | -0.0272 | +| n_updates | 50924 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000391 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1422 | +| iterations | 8778 | +| time_elapsed | 12634 | +| total_timesteps | 17977344 | +| train/ | | +| approx_kl | 0.015395846 | +| clip_fraction | 0.374 | +| clip_range | 0.0705 | +| entropy_loss | -6.05 | +| explained_variance | 0.444 | +| learning_rate | 4.57e-05 | +| loss | -0.0371 | +| n_updates | 50928 | +| policy_gradient_loss | -0.023 | +| value_loss | 0.000141 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1422 | +| iterations | 8779 | +| time_elapsed | 12635 | +| total_timesteps | 17979392 | +| train/ | | +| approx_kl | 0.0120643955 | +| clip_fraction | 0.37 | +| clip_range | 0.0705 | +| entropy_loss | -6.45 | +| explained_variance | 0.52 | +| learning_rate | 4.57e-05 | +| loss | -0.0369 | +| n_updates | 50932 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000143 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1422 | +| iterations | 8780 | +| time_elapsed | 12637 | +| total_timesteps | 17981440 | +| train/ | | +| approx_kl | 0.013414921 | +| clip_fraction | 0.373 | +| clip_range | 0.0705 | +| entropy_loss | -6.48 | +| explained_variance | 0.0711 | +| learning_rate | 4.57e-05 | +| loss | -0.0365 | +| n_updates | 50936 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000149 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1422 | +| iterations | 8781 | +| time_elapsed | 12638 | +| total_timesteps | 17983488 | +| train/ | | +| approx_kl | 0.015211545 | +| clip_fraction | 0.362 | +| clip_range | 0.0705 | +| entropy_loss | -7 | +| explained_variance | -0.206 | +| learning_rate | 4.57e-05 | +| loss | -0.0358 | +| n_updates | 50940 | +| policy_gradient_loss | -0.0212 | +| value_loss | 7.34e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1422 | +| iterations | 8782 | +| time_elapsed | 12640 | +| total_timesteps | 17985536 | +| train/ | | +| approx_kl | 0.014459603 | +| clip_fraction | 0.381 | +| clip_range | 0.0705 | +| entropy_loss | -6.62 | +| explained_variance | 0.412 | +| learning_rate | 4.57e-05 | +| loss | -0.0308 | +| n_updates | 50944 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.0001 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1422 | +| iterations | 8783 | +| time_elapsed | 12641 | +| total_timesteps | 17987584 | +| train/ | | +| approx_kl | 0.01527138 | +| clip_fraction | 0.348 | +| clip_range | 0.0705 | +| entropy_loss | -6.37 | +| explained_variance | 0.302 | +| learning_rate | 4.57e-05 | +| loss | -0.029 | +| n_updates | 50948 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000125 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1422 | +| iterations | 8784 | +| time_elapsed | 12643 | +| total_timesteps | 17989632 | +| train/ | | +| approx_kl | 0.016135085 | +| clip_fraction | 0.349 | +| clip_range | 0.0705 | +| entropy_loss | -6.05 | +| explained_variance | 0.408 | +| learning_rate | 4.57e-05 | +| loss | -0.0311 | +| n_updates | 50952 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000195 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1422 | +| iterations | 8785 | +| time_elapsed | 12644 | +| total_timesteps | 17991680 | +| train/ | | +| approx_kl | 0.014082431 | +| clip_fraction | 0.367 | +| clip_range | 0.0705 | +| entropy_loss | -6.27 | +| explained_variance | 0.636 | +| learning_rate | 4.57e-05 | +| loss | -0.0338 | +| n_updates | 50956 | +| policy_gradient_loss | -0.0215 | +| value_loss | 7.4e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1422 | +| iterations | 8786 | +| time_elapsed | 12646 | +| total_timesteps | 17993728 | +| train/ | | +| approx_kl | 0.0148568135 | +| clip_fraction | 0.332 | +| clip_range | 0.0705 | +| entropy_loss | -6.58 | +| explained_variance | -0.0383 | +| learning_rate | 4.57e-05 | +| loss | -0.0289 | +| n_updates | 50960 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000145 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1422 | +| iterations | 8787 | +| time_elapsed | 12647 | +| total_timesteps | 17995776 | +| train/ | | +| approx_kl | 0.013464094 | +| clip_fraction | 0.345 | +| clip_range | 0.0705 | +| entropy_loss | -6.17 | +| explained_variance | 0.464 | +| learning_rate | 4.57e-05 | +| loss | -0.0325 | +| n_updates | 50964 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000154 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1422 | +| iterations | 8788 | +| time_elapsed | 12648 | +| total_timesteps | 17997824 | +| train/ | | +| approx_kl | 0.016942631 | +| clip_fraction | 0.363 | +| clip_range | 0.0705 | +| entropy_loss | -6.32 | +| explained_variance | 0.536 | +| learning_rate | 4.57e-05 | +| loss | -0.035 | +| n_updates | 50968 | +| policy_gradient_loss | -0.0204 | +| value_loss | 8.3e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1422 | +| iterations | 8789 | +| time_elapsed | 12650 | +| total_timesteps | 17999872 | +| train/ | | +| approx_kl | 0.015943974 | +| clip_fraction | 0.37 | +| clip_range | 0.0705 | +| entropy_loss | -6.03 | +| explained_variance | 0.669 | +| learning_rate | 4.57e-05 | +| loss | -0.0276 | +| n_updates | 50972 | +| policy_gradient_loss | -0.0199 | +| value_loss | 8.23e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1422 | +| iterations | 8790 | +| time_elapsed | 12651 | +| total_timesteps | 18001920 | +| train/ | | +| approx_kl | 0.013138425 | +| clip_fraction | 0.348 | +| clip_range | 0.0705 | +| entropy_loss | -6.36 | +| explained_variance | 0.595 | +| learning_rate | 4.57e-05 | +| loss | -0.0271 | +| n_updates | 50976 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000105 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1422 | +| iterations | 8791 | +| time_elapsed | 12653 | +| total_timesteps | 18003968 | +| train/ | | +| approx_kl | 0.016817322 | +| clip_fraction | 0.361 | +| clip_range | 0.0705 | +| entropy_loss | -6.71 | +| explained_variance | 0.379 | +| learning_rate | 4.57e-05 | +| loss | -0.0267 | +| n_updates | 50980 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000119 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1422 | +| iterations | 8792 | +| time_elapsed | 12654 | +| total_timesteps | 18006016 | +| train/ | | +| approx_kl | 0.014350311 | +| clip_fraction | 0.362 | +| clip_range | 0.0705 | +| entropy_loss | -6.7 | +| explained_variance | 0.44 | +| learning_rate | 4.57e-05 | +| loss | -0.0373 | +| n_updates | 50984 | +| policy_gradient_loss | -0.0191 | +| value_loss | 9.97e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1422 | +| iterations | 8793 | +| time_elapsed | 12656 | +| total_timesteps | 18008064 | +| train/ | | +| approx_kl | 0.013456443 | +| clip_fraction | 0.347 | +| clip_range | 0.0705 | +| entropy_loss | -6.4 | +| explained_variance | 0.325 | +| learning_rate | 4.57e-05 | +| loss | -0.029 | +| n_updates | 50988 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000163 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1422 | +| iterations | 8794 | +| time_elapsed | 12657 | +| total_timesteps | 18010112 | +| train/ | | +| approx_kl | 0.01364283 | +| clip_fraction | 0.303 | +| clip_range | 0.0705 | +| entropy_loss | -6.32 | +| explained_variance | 0.541 | +| learning_rate | 4.57e-05 | +| loss | -0.0305 | +| n_updates | 50992 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000161 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1422 | +| iterations | 8795 | +| time_elapsed | 12659 | +| total_timesteps | 18012160 | +| train/ | | +| approx_kl | 0.0117894625 | +| clip_fraction | 0.333 | +| clip_range | 0.0705 | +| entropy_loss | -6.67 | +| explained_variance | -0.02 | +| learning_rate | 4.57e-05 | +| loss | -0.0276 | +| n_updates | 50996 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000145 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1422 | +| iterations | 8796 | +| time_elapsed | 12660 | +| total_timesteps | 18014208 | +| train/ | | +| approx_kl | 0.012824211 | +| clip_fraction | 0.341 | +| clip_range | 0.0705 | +| entropy_loss | -6.96 | +| explained_variance | -0.239 | +| learning_rate | 4.57e-05 | +| loss | -0.0354 | +| n_updates | 51000 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.00011 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1422 | +| iterations | 8797 | +| time_elapsed | 12662 | +| total_timesteps | 18016256 | +| train/ | | +| approx_kl | 0.014536019 | +| clip_fraction | 0.331 | +| clip_range | 0.0705 | +| entropy_loss | -6.13 | +| explained_variance | 0.43 | +| learning_rate | 4.57e-05 | +| loss | -0.0304 | +| n_updates | 51004 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000256 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1422 | +| iterations | 8798 | +| time_elapsed | 12663 | +| total_timesteps | 18018304 | +| train/ | | +| approx_kl | 0.012683341 | +| clip_fraction | 0.319 | +| clip_range | 0.0705 | +| entropy_loss | -5.9 | +| explained_variance | 0.679 | +| learning_rate | 4.57e-05 | +| loss | -0.0243 | +| n_updates | 51008 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.00011 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1422 | +| iterations | 8799 | +| time_elapsed | 12665 | +| total_timesteps | 18020352 | +| train/ | | +| approx_kl | 0.011718843 | +| clip_fraction | 0.34 | +| clip_range | 0.0705 | +| entropy_loss | -6.45 | +| explained_variance | 0.43 | +| learning_rate | 4.57e-05 | +| loss | -0.0295 | +| n_updates | 51012 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000189 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1422 | +| iterations | 8800 | +| time_elapsed | 12666 | +| total_timesteps | 18022400 | +| train/ | | +| approx_kl | 0.015044219 | +| clip_fraction | 0.335 | +| clip_range | 0.0705 | +| entropy_loss | -6.63 | +| explained_variance | 0.249 | +| learning_rate | 4.57e-05 | +| loss | -0.0358 | +| n_updates | 51016 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000186 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1422 | +| iterations | 8801 | +| time_elapsed | 12667 | +| total_timesteps | 18024448 | +| train/ | | +| approx_kl | 0.012777772 | +| clip_fraction | 0.329 | +| clip_range | 0.0705 | +| entropy_loss | -6.02 | +| explained_variance | 0.344 | +| learning_rate | 4.57e-05 | +| loss | -0.0261 | +| n_updates | 51020 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000302 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1422 | +| iterations | 8802 | +| time_elapsed | 12669 | +| total_timesteps | 18026496 | +| train/ | | +| approx_kl | 0.011660241 | +| clip_fraction | 0.355 | +| clip_range | 0.0705 | +| entropy_loss | -6.45 | +| explained_variance | 0.397 | +| learning_rate | 4.57e-05 | +| loss | -0.0349 | +| n_updates | 51024 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000153 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1422 | +| iterations | 8803 | +| time_elapsed | 12670 | +| total_timesteps | 18028544 | +| train/ | | +| approx_kl | 0.012226213 | +| clip_fraction | 0.364 | +| clip_range | 0.0705 | +| entropy_loss | -6.54 | +| explained_variance | 0.563 | +| learning_rate | 4.57e-05 | +| loss | -0.0302 | +| n_updates | 51028 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000109 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1422 | +| iterations | 8804 | +| time_elapsed | 12672 | +| total_timesteps | 18030592 | +| train/ | | +| approx_kl | 0.012902164 | +| clip_fraction | 0.363 | +| clip_range | 0.0705 | +| entropy_loss | -6.68 | +| explained_variance | 0.0876 | +| learning_rate | 4.57e-05 | +| loss | -0.0306 | +| n_updates | 51032 | +| policy_gradient_loss | -0.0204 | +| value_loss | 9.92e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.304 | +| time/ | | +| fps | 1422 | +| iterations | 8805 | +| time_elapsed | 12673 | +| total_timesteps | 18032640 | +| train/ | | +| approx_kl | 0.015208395 | +| clip_fraction | 0.383 | +| clip_range | 0.0705 | +| entropy_loss | -6.46 | +| explained_variance | 0.38 | +| learning_rate | 4.57e-05 | +| loss | -0.0325 | +| n_updates | 51036 | +| policy_gradient_loss | -0.0222 | +| value_loss | 8.15e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1422 | +| iterations | 8806 | +| time_elapsed | 12675 | +| total_timesteps | 18034688 | +| train/ | | +| approx_kl | 0.013719738 | +| clip_fraction | 0.374 | +| clip_range | 0.0705 | +| entropy_loss | -6.35 | +| explained_variance | 0.612 | +| learning_rate | 4.57e-05 | +| loss | -0.0311 | +| n_updates | 51040 | +| policy_gradient_loss | -0.0205 | +| value_loss | 9.63e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 1422 | +| iterations | 8807 | +| time_elapsed | 12676 | +| total_timesteps | 18036736 | +| train/ | | +| approx_kl | 0.012458026 | +| clip_fraction | 0.345 | +| clip_range | 0.0705 | +| entropy_loss | -6.28 | +| explained_variance | 0.774 | +| learning_rate | 4.57e-05 | +| loss | -0.0283 | +| n_updates | 51044 | +| policy_gradient_loss | -0.021 | +| value_loss | 4.8e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 1422 | +| iterations | 8808 | +| time_elapsed | 12678 | +| total_timesteps | 18038784 | +| train/ | | +| approx_kl | 0.012029557 | +| clip_fraction | 0.31 | +| clip_range | 0.0705 | +| entropy_loss | -5.72 | +| explained_variance | 0.812 | +| learning_rate | 4.57e-05 | +| loss | -0.0235 | +| n_updates | 51048 | +| policy_gradient_loss | -0.015 | +| value_loss | 8.88e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 1422 | +| iterations | 8809 | +| time_elapsed | 12679 | +| total_timesteps | 18040832 | +| train/ | | +| approx_kl | 0.015054053 | +| clip_fraction | 0.353 | +| clip_range | 0.0705 | +| entropy_loss | -6.3 | +| explained_variance | 0.386 | +| learning_rate | 4.57e-05 | +| loss | -0.0297 | +| n_updates | 51052 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000144 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 1422 | +| iterations | 8810 | +| time_elapsed | 12681 | +| total_timesteps | 18042880 | +| train/ | | +| approx_kl | 0.018665293 | +| clip_fraction | 0.351 | +| clip_range | 0.0705 | +| entropy_loss | -6.62 | +| explained_variance | -0.000204 | +| learning_rate | 4.57e-05 | +| loss | -0.0232 | +| n_updates | 51056 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000177 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.302 | +| time/ | | +| fps | 1422 | +| iterations | 8811 | +| time_elapsed | 12682 | +| total_timesteps | 18044928 | +| train/ | | +| approx_kl | 0.014076494 | +| clip_fraction | 0.337 | +| clip_range | 0.0705 | +| entropy_loss | -7.14 | +| explained_variance | -0.0177 | +| learning_rate | 4.57e-05 | +| loss | -0.0324 | +| n_updates | 51060 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000158 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.304 | +| time/ | | +| fps | 1422 | +| iterations | 8812 | +| time_elapsed | 12683 | +| total_timesteps | 18046976 | +| train/ | | +| approx_kl | 0.0123749245 | +| clip_fraction | 0.364 | +| clip_range | 0.0705 | +| entropy_loss | -6.37 | +| explained_variance | 0.499 | +| learning_rate | 4.57e-05 | +| loss | -0.0361 | +| n_updates | 51064 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000115 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 1422 | +| iterations | 8813 | +| time_elapsed | 12685 | +| total_timesteps | 18049024 | +| train/ | | +| approx_kl | 0.012051353 | +| clip_fraction | 0.334 | +| clip_range | 0.0705 | +| entropy_loss | -5.94 | +| explained_variance | 0.464 | +| learning_rate | 4.57e-05 | +| loss | -0.0273 | +| n_updates | 51068 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000257 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 1422 | +| iterations | 8814 | +| time_elapsed | 12686 | +| total_timesteps | 18051072 | +| train/ | | +| approx_kl | 0.012257396 | +| clip_fraction | 0.347 | +| clip_range | 0.0705 | +| entropy_loss | -6.59 | +| explained_variance | 0.259 | +| learning_rate | 4.57e-05 | +| loss | -0.032 | +| n_updates | 51072 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000194 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1422 | +| iterations | 8815 | +| time_elapsed | 12688 | +| total_timesteps | 18053120 | +| train/ | | +| approx_kl | 0.013481689 | +| clip_fraction | 0.355 | +| clip_range | 0.0705 | +| entropy_loss | -6.67 | +| explained_variance | -0.0639 | +| learning_rate | 4.57e-05 | +| loss | -0.0283 | +| n_updates | 51076 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000173 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1422 | +| iterations | 8816 | +| time_elapsed | 12689 | +| total_timesteps | 18055168 | +| train/ | | +| approx_kl | 0.015568321 | +| clip_fraction | 0.36 | +| clip_range | 0.0705 | +| entropy_loss | -6.33 | +| explained_variance | 0.214 | +| learning_rate | 4.57e-05 | +| loss | -0.0308 | +| n_updates | 51080 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.00034 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.306 | +| time/ | | +| fps | 1422 | +| iterations | 8817 | +| time_elapsed | 12691 | +| total_timesteps | 18057216 | +| train/ | | +| approx_kl | 0.014270952 | +| clip_fraction | 0.362 | +| clip_range | 0.0705 | +| entropy_loss | -6.5 | +| explained_variance | 0.395 | +| learning_rate | 4.57e-05 | +| loss | -0.0321 | +| n_updates | 51084 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.00014 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 1422 | +| iterations | 8818 | +| time_elapsed | 12692 | +| total_timesteps | 18059264 | +| train/ | | +| approx_kl | 0.014706486 | +| clip_fraction | 0.342 | +| clip_range | 0.0705 | +| entropy_loss | -6.29 | +| explained_variance | 0.572 | +| learning_rate | 4.57e-05 | +| loss | -0.0318 | +| n_updates | 51088 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000136 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1422 | +| iterations | 8819 | +| time_elapsed | 12694 | +| total_timesteps | 18061312 | +| train/ | | +| approx_kl | 0.01424091 | +| clip_fraction | 0.357 | +| clip_range | 0.0705 | +| entropy_loss | -6.32 | +| explained_variance | 0.392 | +| learning_rate | 4.57e-05 | +| loss | -0.0299 | +| n_updates | 51092 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000126 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1422 | +| iterations | 8820 | +| time_elapsed | 12695 | +| total_timesteps | 18063360 | +| train/ | | +| approx_kl | 0.01291725 | +| clip_fraction | 0.355 | +| clip_range | 0.0705 | +| entropy_loss | -6.39 | +| explained_variance | 0.481 | +| learning_rate | 4.57e-05 | +| loss | -0.026 | +| n_updates | 51096 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000159 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1422 | +| iterations | 8821 | +| time_elapsed | 12696 | +| total_timesteps | 18065408 | +| train/ | | +| approx_kl | 0.015419509 | +| clip_fraction | 0.355 | +| clip_range | 0.0705 | +| entropy_loss | -6.57 | +| explained_variance | -0.0585 | +| learning_rate | 4.57e-05 | +| loss | -0.0264 | +| n_updates | 51100 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.00017 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1422 | +| iterations | 8822 | +| time_elapsed | 12698 | +| total_timesteps | 18067456 | +| train/ | | +| approx_kl | 0.013139611 | +| clip_fraction | 0.354 | +| clip_range | 0.0705 | +| entropy_loss | -6.71 | +| explained_variance | 0.0415 | +| learning_rate | 4.57e-05 | +| loss | -0.0206 | +| n_updates | 51104 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000216 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1422 | +| iterations | 8823 | +| time_elapsed | 12699 | +| total_timesteps | 18069504 | +| train/ | | +| approx_kl | 0.013728979 | +| clip_fraction | 0.341 | +| clip_range | 0.0705 | +| entropy_loss | -6.33 | +| explained_variance | 0.389 | +| learning_rate | 4.57e-05 | +| loss | -0.0305 | +| n_updates | 51108 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000147 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1422 | +| iterations | 8824 | +| time_elapsed | 12701 | +| total_timesteps | 18071552 | +| train/ | | +| approx_kl | 0.012467533 | +| clip_fraction | 0.326 | +| clip_range | 0.0705 | +| entropy_loss | -5.92 | +| explained_variance | 0.408 | +| learning_rate | 4.57e-05 | +| loss | -0.025 | +| n_updates | 51112 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000304 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1422 | +| iterations | 8825 | +| time_elapsed | 12702 | +| total_timesteps | 18073600 | +| train/ | | +| approx_kl | 0.011119636 | +| clip_fraction | 0.36 | +| clip_range | 0.0705 | +| entropy_loss | -6.03 | +| explained_variance | 0.557 | +| learning_rate | 4.57e-05 | +| loss | -0.0308 | +| n_updates | 51116 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000151 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1422 | +| iterations | 8826 | +| time_elapsed | 12704 | +| total_timesteps | 18075648 | +| train/ | | +| approx_kl | 0.012968134 | +| clip_fraction | 0.349 | +| clip_range | 0.0705 | +| entropy_loss | -6.82 | +| explained_variance | 0.11 | +| learning_rate | 4.57e-05 | +| loss | -0.0328 | +| n_updates | 51120 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000212 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1422 | +| iterations | 8827 | +| time_elapsed | 12705 | +| total_timesteps | 18077696 | +| train/ | | +| approx_kl | 0.013340911 | +| clip_fraction | 0.33 | +| clip_range | 0.0705 | +| entropy_loss | -6.62 | +| explained_variance | 0.316 | +| learning_rate | 4.57e-05 | +| loss | -0.0306 | +| n_updates | 51124 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000292 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1422 | +| iterations | 8828 | +| time_elapsed | 12707 | +| total_timesteps | 18079744 | +| train/ | | +| approx_kl | 0.01110651 | +| clip_fraction | 0.327 | +| clip_range | 0.0705 | +| entropy_loss | -6.33 | +| explained_variance | 0.333 | +| learning_rate | 4.57e-05 | +| loss | -0.0302 | +| n_updates | 51128 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000237 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1422 | +| iterations | 8829 | +| time_elapsed | 12708 | +| total_timesteps | 18081792 | +| train/ | | +| approx_kl | 0.0122184325 | +| clip_fraction | 0.346 | +| clip_range | 0.0705 | +| entropy_loss | -6.8 | +| explained_variance | -0.083 | +| learning_rate | 4.57e-05 | +| loss | -0.0328 | +| n_updates | 51132 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000219 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1422 | +| iterations | 8830 | +| time_elapsed | 12709 | +| total_timesteps | 18083840 | +| train/ | | +| approx_kl | 0.013625767 | +| clip_fraction | 0.365 | +| clip_range | 0.0705 | +| entropy_loss | -6.41 | +| explained_variance | 0.489 | +| learning_rate | 4.57e-05 | +| loss | -0.0317 | +| n_updates | 51136 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000115 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1422 | +| iterations | 8831 | +| time_elapsed | 12711 | +| total_timesteps | 18085888 | +| train/ | | +| approx_kl | 0.014552934 | +| clip_fraction | 0.353 | +| clip_range | 0.0705 | +| entropy_loss | -6.3 | +| explained_variance | 0.45 | +| learning_rate | 4.57e-05 | +| loss | -0.0335 | +| n_updates | 51140 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000169 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1422 | +| iterations | 8832 | +| time_elapsed | 12712 | +| total_timesteps | 18087936 | +| train/ | | +| approx_kl | 0.015319925 | +| clip_fraction | 0.353 | +| clip_range | 0.0705 | +| entropy_loss | -6.46 | +| explained_variance | 0.186 | +| learning_rate | 4.57e-05 | +| loss | -0.0278 | +| n_updates | 51144 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000237 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1422 | +| iterations | 8833 | +| time_elapsed | 12714 | +| total_timesteps | 18089984 | +| train/ | | +| approx_kl | 0.014087553 | +| clip_fraction | 0.318 | +| clip_range | 0.0705 | +| entropy_loss | -6.01 | +| explained_variance | 0.439 | +| learning_rate | 4.57e-05 | +| loss | -0.0261 | +| n_updates | 51148 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000331 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1422 | +| iterations | 8834 | +| time_elapsed | 12715 | +| total_timesteps | 18092032 | +| train/ | | +| approx_kl | 0.013724714 | +| clip_fraction | 0.352 | +| clip_range | 0.0705 | +| entropy_loss | -5.62 | +| explained_variance | 0.53 | +| learning_rate | 4.57e-05 | +| loss | -0.0284 | +| n_updates | 51152 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000207 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1422 | +| iterations | 8835 | +| time_elapsed | 12716 | +| total_timesteps | 18094080 | +| train/ | | +| approx_kl | 0.01499663 | +| clip_fraction | 0.368 | +| clip_range | 0.0705 | +| entropy_loss | -6.19 | +| explained_variance | 0.232 | +| learning_rate | 4.57e-05 | +| loss | -0.0355 | +| n_updates | 51156 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.00018 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1422 | +| iterations | 8836 | +| time_elapsed | 12718 | +| total_timesteps | 18096128 | +| train/ | | +| approx_kl | 0.013172464 | +| clip_fraction | 0.32 | +| clip_range | 0.0705 | +| entropy_loss | -6.11 | +| explained_variance | 0.365 | +| learning_rate | 4.57e-05 | +| loss | -0.0283 | +| n_updates | 51160 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000309 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1422 | +| iterations | 8837 | +| time_elapsed | 12719 | +| total_timesteps | 18098176 | +| train/ | | +| approx_kl | 0.013703427 | +| clip_fraction | 0.342 | +| clip_range | 0.0705 | +| entropy_loss | -6.34 | +| explained_variance | 0.237 | +| learning_rate | 4.57e-05 | +| loss | -0.0356 | +| n_updates | 51164 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000171 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1422 | +| iterations | 8838 | +| time_elapsed | 12721 | +| total_timesteps | 18100224 | +| train/ | | +| approx_kl | 0.013966637 | +| clip_fraction | 0.355 | +| clip_range | 0.0705 | +| entropy_loss | -6.53 | +| explained_variance | 0.297 | +| learning_rate | 4.57e-05 | +| loss | -0.0355 | +| n_updates | 51168 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000165 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1422 | +| iterations | 8839 | +| time_elapsed | 12722 | +| total_timesteps | 18102272 | +| train/ | | +| approx_kl | 0.013717119 | +| clip_fraction | 0.359 | +| clip_range | 0.0705 | +| entropy_loss | -6.75 | +| explained_variance | -0.312 | +| learning_rate | 4.57e-05 | +| loss | -0.035 | +| n_updates | 51172 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000158 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1422 | +| iterations | 8840 | +| time_elapsed | 12724 | +| total_timesteps | 18104320 | +| train/ | | +| approx_kl | 0.013945244 | +| clip_fraction | 0.335 | +| clip_range | 0.0705 | +| entropy_loss | -6.71 | +| explained_variance | 0.191 | +| learning_rate | 4.57e-05 | +| loss | -0.0255 | +| n_updates | 51176 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000272 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1422 | +| iterations | 8841 | +| time_elapsed | 12725 | +| total_timesteps | 18106368 | +| train/ | | +| approx_kl | 0.013165515 | +| clip_fraction | 0.3 | +| clip_range | 0.0705 | +| entropy_loss | -6.01 | +| explained_variance | 0.447 | +| learning_rate | 4.57e-05 | +| loss | -0.0292 | +| n_updates | 51180 | +| policy_gradient_loss | -0.0142 | +| value_loss | 0.00034 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1422 | +| iterations | 8842 | +| time_elapsed | 12727 | +| total_timesteps | 18108416 | +| train/ | | +| approx_kl | 0.011579098 | +| clip_fraction | 0.337 | +| clip_range | 0.0705 | +| entropy_loss | -6.15 | +| explained_variance | 0.448 | +| learning_rate | 4.57e-05 | +| loss | -0.0362 | +| n_updates | 51184 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000249 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1422 | +| iterations | 8843 | +| time_elapsed | 12728 | +| total_timesteps | 18110464 | +| train/ | | +| approx_kl | 0.01275589 | +| clip_fraction | 0.358 | +| clip_range | 0.0705 | +| entropy_loss | -6.39 | +| explained_variance | -0.0191 | +| learning_rate | 4.57e-05 | +| loss | -0.0288 | +| n_updates | 51188 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.00028 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1422 | +| iterations | 8844 | +| time_elapsed | 12730 | +| total_timesteps | 18112512 | +| train/ | | +| approx_kl | 0.015397422 | +| clip_fraction | 0.341 | +| clip_range | 0.0705 | +| entropy_loss | -5.72 | +| explained_variance | 0.601 | +| learning_rate | 4.57e-05 | +| loss | -0.0224 | +| n_updates | 51192 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000238 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1422 | +| iterations | 8845 | +| time_elapsed | 12731 | +| total_timesteps | 18114560 | +| train/ | | +| approx_kl | 0.0123826135 | +| clip_fraction | 0.344 | +| clip_range | 0.0705 | +| entropy_loss | -6.7 | +| explained_variance | 0.217 | +| learning_rate | 4.57e-05 | +| loss | -0.0304 | +| n_updates | 51196 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000224 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1422 | +| iterations | 8846 | +| time_elapsed | 12732 | +| total_timesteps | 18116608 | +| train/ | | +| approx_kl | 0.012815408 | +| clip_fraction | 0.348 | +| clip_range | 0.0705 | +| entropy_loss | -6.79 | +| explained_variance | -0.307 | +| learning_rate | 4.57e-05 | +| loss | -0.0309 | +| n_updates | 51200 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000157 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1422 | +| iterations | 8847 | +| time_elapsed | 12734 | +| total_timesteps | 18118656 | +| train/ | | +| approx_kl | 0.015173564 | +| clip_fraction | 0.368 | +| clip_range | 0.0705 | +| entropy_loss | -6.49 | +| explained_variance | 0.324 | +| learning_rate | 4.57e-05 | +| loss | -0.0348 | +| n_updates | 51204 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000171 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1422 | +| iterations | 8848 | +| time_elapsed | 12735 | +| total_timesteps | 18120704 | +| train/ | | +| approx_kl | 0.011818005 | +| clip_fraction | 0.361 | +| clip_range | 0.0705 | +| entropy_loss | -6.07 | +| explained_variance | 0.517 | +| learning_rate | 4.57e-05 | +| loss | -0.0316 | +| n_updates | 51208 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000228 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1422 | +| iterations | 8849 | +| time_elapsed | 12737 | +| total_timesteps | 18122752 | +| train/ | | +| approx_kl | 0.014351044 | +| clip_fraction | 0.378 | +| clip_range | 0.0705 | +| entropy_loss | -6.09 | +| explained_variance | 0.4 | +| learning_rate | 4.57e-05 | +| loss | -0.0352 | +| n_updates | 51212 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000101 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1422 | +| iterations | 8850 | +| time_elapsed | 12738 | +| total_timesteps | 18124800 | +| train/ | | +| approx_kl | 0.012996882 | +| clip_fraction | 0.353 | +| clip_range | 0.0705 | +| entropy_loss | -6.41 | +| explained_variance | 0.435 | +| learning_rate | 4.57e-05 | +| loss | -0.0285 | +| n_updates | 51216 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000112 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1422 | +| iterations | 8851 | +| time_elapsed | 12740 | +| total_timesteps | 18126848 | +| train/ | | +| approx_kl | 0.014517808 | +| clip_fraction | 0.337 | +| clip_range | 0.0705 | +| entropy_loss | -6.1 | +| explained_variance | 0.38 | +| learning_rate | 4.57e-05 | +| loss | -0.0248 | +| n_updates | 51220 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000284 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1422 | +| iterations | 8852 | +| time_elapsed | 12741 | +| total_timesteps | 18128896 | +| train/ | | +| approx_kl | 0.014070826 | +| clip_fraction | 0.367 | +| clip_range | 0.0705 | +| entropy_loss | -6.09 | +| explained_variance | 0.59 | +| learning_rate | 4.57e-05 | +| loss | -0.031 | +| n_updates | 51224 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000136 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1422 | +| iterations | 8853 | +| time_elapsed | 12743 | +| total_timesteps | 18130944 | +| train/ | | +| approx_kl | 0.015894843 | +| clip_fraction | 0.358 | +| clip_range | 0.0705 | +| entropy_loss | -6.01 | +| explained_variance | 0.431 | +| learning_rate | 4.57e-05 | +| loss | -0.0292 | +| n_updates | 51228 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000165 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1422 | +| iterations | 8854 | +| time_elapsed | 12744 | +| total_timesteps | 18132992 | +| train/ | | +| approx_kl | 0.013105183 | +| clip_fraction | 0.332 | +| clip_range | 0.0705 | +| entropy_loss | -6.45 | +| explained_variance | 0.269 | +| learning_rate | 4.57e-05 | +| loss | -0.0294 | +| n_updates | 51232 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000174 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1422 | +| iterations | 8855 | +| time_elapsed | 12745 | +| total_timesteps | 18135040 | +| train/ | | +| approx_kl | 0.01331467 | +| clip_fraction | 0.371 | +| clip_range | 0.0705 | +| entropy_loss | -6.38 | +| explained_variance | 0.427 | +| learning_rate | 4.57e-05 | +| loss | -0.0326 | +| n_updates | 51236 | +| policy_gradient_loss | -0.0195 | +| value_loss | 9.7e-05 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1422 | +| iterations | 8856 | +| time_elapsed | 12747 | +| total_timesteps | 18137088 | +| train/ | | +| approx_kl | 0.01436773 | +| clip_fraction | 0.354 | +| clip_range | 0.0705 | +| entropy_loss | -6.28 | +| explained_variance | 0.3 | +| learning_rate | 4.57e-05 | +| loss | -0.0323 | +| n_updates | 51240 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000145 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1422 | +| iterations | 8857 | +| time_elapsed | 12748 | +| total_timesteps | 18139136 | +| train/ | | +| approx_kl | 0.015778078 | +| clip_fraction | 0.361 | +| clip_range | 0.0705 | +| entropy_loss | -6.29 | +| explained_variance | 0.359 | +| learning_rate | 4.57e-05 | +| loss | -0.0264 | +| n_updates | 51244 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000139 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1422 | +| iterations | 8858 | +| time_elapsed | 12750 | +| total_timesteps | 18141184 | +| train/ | | +| approx_kl | 0.013149062 | +| clip_fraction | 0.332 | +| clip_range | 0.0705 | +| entropy_loss | -6.1 | +| explained_variance | 0.674 | +| learning_rate | 4.57e-05 | +| loss | -0.0273 | +| n_updates | 51248 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000101 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1422 | +| iterations | 8859 | +| time_elapsed | 12751 | +| total_timesteps | 18143232 | +| train/ | | +| approx_kl | 0.011861341 | +| clip_fraction | 0.351 | +| clip_range | 0.0705 | +| entropy_loss | -6.33 | +| explained_variance | 0.305 | +| learning_rate | 4.57e-05 | +| loss | -0.0308 | +| n_updates | 51252 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000186 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1422 | +| iterations | 8860 | +| time_elapsed | 12752 | +| total_timesteps | 18145280 | +| train/ | | +| approx_kl | 0.013310855 | +| clip_fraction | 0.344 | +| clip_range | 0.0705 | +| entropy_loss | -6.32 | +| explained_variance | 0.543 | +| learning_rate | 4.57e-05 | +| loss | -0.0327 | +| n_updates | 51256 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000113 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1422 | +| iterations | 8861 | +| time_elapsed | 12754 | +| total_timesteps | 18147328 | +| train/ | | +| approx_kl | 0.01417985 | +| clip_fraction | 0.326 | +| clip_range | 0.0705 | +| entropy_loss | -6.34 | +| explained_variance | 0.478 | +| learning_rate | 4.57e-05 | +| loss | -0.0285 | +| n_updates | 51260 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000153 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1422 | +| iterations | 8862 | +| time_elapsed | 12755 | +| total_timesteps | 18149376 | +| train/ | | +| approx_kl | 0.01430672 | +| clip_fraction | 0.371 | +| clip_range | 0.0705 | +| entropy_loss | -6.24 | +| explained_variance | 0.654 | +| learning_rate | 4.57e-05 | +| loss | -0.0358 | +| n_updates | 51264 | +| policy_gradient_loss | -0.0237 | +| value_loss | 8.67e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1422 | +| iterations | 8863 | +| time_elapsed | 12757 | +| total_timesteps | 18151424 | +| train/ | | +| approx_kl | 0.012911434 | +| clip_fraction | 0.346 | +| clip_range | 0.0705 | +| entropy_loss | -6.53 | +| explained_variance | 0.323 | +| learning_rate | 4.57e-05 | +| loss | -0.0351 | +| n_updates | 51268 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000125 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1422 | +| iterations | 8864 | +| time_elapsed | 12758 | +| total_timesteps | 18153472 | +| train/ | | +| approx_kl | 0.012836207 | +| clip_fraction | 0.33 | +| clip_range | 0.0705 | +| entropy_loss | -6.53 | +| explained_variance | 0.293 | +| learning_rate | 4.57e-05 | +| loss | -0.0294 | +| n_updates | 51272 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000166 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1422 | +| iterations | 8865 | +| time_elapsed | 12760 | +| total_timesteps | 18155520 | +| train/ | | +| approx_kl | 0.012972452 | +| clip_fraction | 0.346 | +| clip_range | 0.0705 | +| entropy_loss | -6.09 | +| explained_variance | 0.633 | +| learning_rate | 4.57e-05 | +| loss | -0.0257 | +| n_updates | 51276 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000143 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1422 | +| iterations | 8866 | +| time_elapsed | 12761 | +| total_timesteps | 18157568 | +| train/ | | +| approx_kl | 0.015106711 | +| clip_fraction | 0.35 | +| clip_range | 0.0705 | +| entropy_loss | -5.67 | +| explained_variance | 0.654 | +| learning_rate | 4.57e-05 | +| loss | -0.0243 | +| n_updates | 51280 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000134 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1422 | +| iterations | 8867 | +| time_elapsed | 12762 | +| total_timesteps | 18159616 | +| train/ | | +| approx_kl | 0.013532933 | +| clip_fraction | 0.335 | +| clip_range | 0.0705 | +| entropy_loss | -6.52 | +| explained_variance | 0.337 | +| learning_rate | 4.57e-05 | +| loss | -0.0312 | +| n_updates | 51284 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000154 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1422 | +| iterations | 8868 | +| time_elapsed | 12764 | +| total_timesteps | 18161664 | +| train/ | | +| approx_kl | 0.01191617 | +| clip_fraction | 0.335 | +| clip_range | 0.0705 | +| entropy_loss | -6.4 | +| explained_variance | 0.433 | +| learning_rate | 4.57e-05 | +| loss | -0.0289 | +| n_updates | 51288 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.00019 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1422 | +| iterations | 8869 | +| time_elapsed | 12765 | +| total_timesteps | 18163712 | +| train/ | | +| approx_kl | 0.012544861 | +| clip_fraction | 0.307 | +| clip_range | 0.0705 | +| entropy_loss | -6.31 | +| explained_variance | 0.277 | +| learning_rate | 4.57e-05 | +| loss | -0.0242 | +| n_updates | 51292 | +| policy_gradient_loss | -0.0143 | +| value_loss | 0.000254 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1422 | +| iterations | 8870 | +| time_elapsed | 12767 | +| total_timesteps | 18165760 | +| train/ | | +| approx_kl | 0.010696409 | +| clip_fraction | 0.363 | +| clip_range | 0.0705 | +| entropy_loss | -6.76 | +| explained_variance | 0.165 | +| learning_rate | 4.57e-05 | +| loss | -0.0303 | +| n_updates | 51296 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000191 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1422 | +| iterations | 8871 | +| time_elapsed | 12768 | +| total_timesteps | 18167808 | +| train/ | | +| approx_kl | 0.015979724 | +| clip_fraction | 0.365 | +| clip_range | 0.0705 | +| entropy_loss | -6.75 | +| explained_variance | 0.333 | +| learning_rate | 4.57e-05 | +| loss | -0.028 | +| n_updates | 51300 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000134 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1422 | +| iterations | 8872 | +| time_elapsed | 12770 | +| total_timesteps | 18169856 | +| train/ | | +| approx_kl | 0.012434434 | +| clip_fraction | 0.337 | +| clip_range | 0.0705 | +| entropy_loss | -6.49 | +| explained_variance | 0.125 | +| learning_rate | 4.57e-05 | +| loss | -0.0339 | +| n_updates | 51304 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000324 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1422 | +| iterations | 8873 | +| time_elapsed | 12771 | +| total_timesteps | 18171904 | +| train/ | | +| approx_kl | 0.01317736 | +| clip_fraction | 0.292 | +| clip_range | 0.0705 | +| entropy_loss | -5.92 | +| explained_variance | 0.291 | +| learning_rate | 4.57e-05 | +| loss | -0.0243 | +| n_updates | 51308 | +| policy_gradient_loss | -0.0137 | +| value_loss | 0.000351 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1422 | +| iterations | 8874 | +| time_elapsed | 12773 | +| total_timesteps | 18173952 | +| train/ | | +| approx_kl | 0.014209443 | +| clip_fraction | 0.373 | +| clip_range | 0.0705 | +| entropy_loss | -6.29 | +| explained_variance | 0.559 | +| learning_rate | 4.57e-05 | +| loss | -0.0365 | +| n_updates | 51312 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000119 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1422 | +| iterations | 8875 | +| time_elapsed | 12774 | +| total_timesteps | 18176000 | +| train/ | | +| approx_kl | 0.012696698 | +| clip_fraction | 0.327 | +| clip_range | 0.0705 | +| entropy_loss | -5.78 | +| explained_variance | 0.576 | +| learning_rate | 4.57e-05 | +| loss | -0.0259 | +| n_updates | 51316 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000234 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1422 | +| iterations | 8876 | +| time_elapsed | 12775 | +| total_timesteps | 18178048 | +| train/ | | +| approx_kl | 0.016250547 | +| clip_fraction | 0.333 | +| clip_range | 0.0705 | +| entropy_loss | -6.18 | +| explained_variance | 0.383 | +| learning_rate | 4.57e-05 | +| loss | -0.0237 | +| n_updates | 51320 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000145 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1422 | +| iterations | 8877 | +| time_elapsed | 12777 | +| total_timesteps | 18180096 | +| train/ | | +| approx_kl | 0.011910513 | +| clip_fraction | 0.345 | +| clip_range | 0.0705 | +| entropy_loss | -6.93 | +| explained_variance | -0.00117 | +| learning_rate | 4.57e-05 | +| loss | -0.0316 | +| n_updates | 51324 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000158 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1422 | +| iterations | 8878 | +| time_elapsed | 12778 | +| total_timesteps | 18182144 | +| train/ | | +| approx_kl | 0.014937176 | +| clip_fraction | 0.355 | +| clip_range | 0.0705 | +| entropy_loss | -6.47 | +| explained_variance | 0.201 | +| learning_rate | 4.57e-05 | +| loss | -0.0337 | +| n_updates | 51328 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000265 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1422 | +| iterations | 8879 | +| time_elapsed | 12780 | +| total_timesteps | 18184192 | +| train/ | | +| approx_kl | 0.015850028 | +| clip_fraction | 0.368 | +| clip_range | 0.0705 | +| entropy_loss | -6.51 | +| explained_variance | 0.379 | +| learning_rate | 4.57e-05 | +| loss | -0.0404 | +| n_updates | 51332 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000133 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1422 | +| iterations | 8880 | +| time_elapsed | 12781 | +| total_timesteps | 18186240 | +| train/ | | +| approx_kl | 0.014023148 | +| clip_fraction | 0.356 | +| clip_range | 0.0705 | +| entropy_loss | -6.62 | +| explained_variance | 0.208 | +| learning_rate | 4.57e-05 | +| loss | -0.0322 | +| n_updates | 51336 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000144 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1422 | +| iterations | 8881 | +| time_elapsed | 12783 | +| total_timesteps | 18188288 | +| train/ | | +| approx_kl | 0.01329571 | +| clip_fraction | 0.328 | +| clip_range | 0.0705 | +| entropy_loss | -5.85 | +| explained_variance | 0.468 | +| learning_rate | 4.57e-05 | +| loss | -0.0264 | +| n_updates | 51340 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000319 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1422 | +| iterations | 8882 | +| time_elapsed | 12784 | +| total_timesteps | 18190336 | +| train/ | | +| approx_kl | 0.01127038 | +| clip_fraction | 0.356 | +| clip_range | 0.0705 | +| entropy_loss | -5.91 | +| explained_variance | 0.414 | +| learning_rate | 4.57e-05 | +| loss | -0.0358 | +| n_updates | 51344 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000186 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1422 | +| iterations | 8883 | +| time_elapsed | 12786 | +| total_timesteps | 18192384 | +| train/ | | +| approx_kl | 0.014874583 | +| clip_fraction | 0.362 | +| clip_range | 0.0705 | +| entropy_loss | -6.82 | +| explained_variance | -0.0573 | +| learning_rate | 4.57e-05 | +| loss | -0.0321 | +| n_updates | 51348 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000246 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1422 | +| iterations | 8884 | +| time_elapsed | 12787 | +| total_timesteps | 18194432 | +| train/ | | +| approx_kl | 0.011803978 | +| clip_fraction | 0.344 | +| clip_range | 0.0705 | +| entropy_loss | -6.66 | +| explained_variance | 0.315 | +| learning_rate | 4.57e-05 | +| loss | -0.0284 | +| n_updates | 51352 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000306 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1422 | +| iterations | 8885 | +| time_elapsed | 12788 | +| total_timesteps | 18196480 | +| train/ | | +| approx_kl | 0.01046774 | +| clip_fraction | 0.327 | +| clip_range | 0.0705 | +| entropy_loss | -6.48 | +| explained_variance | 0.274 | +| learning_rate | 4.57e-05 | +| loss | -0.0341 | +| n_updates | 51356 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000224 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1422 | +| iterations | 8886 | +| time_elapsed | 12790 | +| total_timesteps | 18198528 | +| train/ | | +| approx_kl | 0.012073221 | +| clip_fraction | 0.36 | +| clip_range | 0.0705 | +| entropy_loss | -6.57 | +| explained_variance | 0.447 | +| learning_rate | 4.57e-05 | +| loss | -0.0336 | +| n_updates | 51360 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000142 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1422 | +| iterations | 8887 | +| time_elapsed | 12791 | +| total_timesteps | 18200576 | +| train/ | | +| approx_kl | 0.012010137 | +| clip_fraction | 0.358 | +| clip_range | 0.0705 | +| entropy_loss | -6.49 | +| explained_variance | 0.596 | +| learning_rate | 4.57e-05 | +| loss | -0.0327 | +| n_updates | 51364 | +| policy_gradient_loss | -0.0188 | +| value_loss | 8.88e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1422 | +| iterations | 8888 | +| time_elapsed | 12793 | +| total_timesteps | 18202624 | +| train/ | | +| approx_kl | 0.012674194 | +| clip_fraction | 0.338 | +| clip_range | 0.0704 | +| entropy_loss | -6.66 | +| explained_variance | 0.0421 | +| learning_rate | 4.57e-05 | +| loss | -0.0261 | +| n_updates | 51368 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000145 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1422 | +| iterations | 8889 | +| time_elapsed | 12794 | +| total_timesteps | 18204672 | +| train/ | | +| approx_kl | 0.012543328 | +| clip_fraction | 0.33 | +| clip_range | 0.0704 | +| entropy_loss | -6.13 | +| explained_variance | 0.553 | +| learning_rate | 4.57e-05 | +| loss | -0.0225 | +| n_updates | 51372 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.00023 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1422 | +| iterations | 8890 | +| time_elapsed | 12796 | +| total_timesteps | 18206720 | +| train/ | | +| approx_kl | 0.010997506 | +| clip_fraction | 0.332 | +| clip_range | 0.0704 | +| entropy_loss | -6.03 | +| explained_variance | 0.384 | +| learning_rate | 4.57e-05 | +| loss | -0.0286 | +| n_updates | 51376 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000315 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1422 | +| iterations | 8891 | +| time_elapsed | 12797 | +| total_timesteps | 18208768 | +| train/ | | +| approx_kl | 0.013056705 | +| clip_fraction | 0.38 | +| clip_range | 0.0704 | +| entropy_loss | -6.02 | +| explained_variance | 0.482 | +| learning_rate | 4.57e-05 | +| loss | -0.0352 | +| n_updates | 51380 | +| policy_gradient_loss | -0.0233 | +| value_loss | 0.000114 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1422 | +| iterations | 8892 | +| time_elapsed | 12798 | +| total_timesteps | 18210816 | +| train/ | | +| approx_kl | 0.011013038 | +| clip_fraction | 0.351 | +| clip_range | 0.0704 | +| entropy_loss | -6.79 | +| explained_variance | -0.0338 | +| learning_rate | 4.57e-05 | +| loss | -0.0265 | +| n_updates | 51384 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000202 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1422 | +| iterations | 8893 | +| time_elapsed | 12800 | +| total_timesteps | 18212864 | +| train/ | | +| approx_kl | 0.012407064 | +| clip_fraction | 0.31 | +| clip_range | 0.0704 | +| entropy_loss | -6.32 | +| explained_variance | 0.418 | +| learning_rate | 4.57e-05 | +| loss | -0.0264 | +| n_updates | 51388 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000215 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1422 | +| iterations | 8894 | +| time_elapsed | 12801 | +| total_timesteps | 18214912 | +| train/ | | +| approx_kl | 0.012844095 | +| clip_fraction | 0.363 | +| clip_range | 0.0704 | +| entropy_loss | -6.41 | +| explained_variance | 0.256 | +| learning_rate | 4.57e-05 | +| loss | -0.0281 | +| n_updates | 51392 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000186 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1422 | +| iterations | 8895 | +| time_elapsed | 12803 | +| total_timesteps | 18216960 | +| train/ | | +| approx_kl | 0.013497282 | +| clip_fraction | 0.369 | +| clip_range | 0.0704 | +| entropy_loss | -6.52 | +| explained_variance | 0.256 | +| learning_rate | 4.57e-05 | +| loss | -0.0333 | +| n_updates | 51396 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000162 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1422 | +| iterations | 8896 | +| time_elapsed | 12804 | +| total_timesteps | 18219008 | +| train/ | | +| approx_kl | 0.014112067 | +| clip_fraction | 0.351 | +| clip_range | 0.0704 | +| entropy_loss | -6.3 | +| explained_variance | 0.594 | +| learning_rate | 4.57e-05 | +| loss | -0.0228 | +| n_updates | 51400 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000164 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1422 | +| iterations | 8897 | +| time_elapsed | 12806 | +| total_timesteps | 18221056 | +| train/ | | +| approx_kl | 0.01534706 | +| clip_fraction | 0.352 | +| clip_range | 0.0704 | +| entropy_loss | -6.03 | +| explained_variance | 0.552 | +| learning_rate | 4.57e-05 | +| loss | -0.0352 | +| n_updates | 51404 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000124 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1422 | +| iterations | 8898 | +| time_elapsed | 12807 | +| total_timesteps | 18223104 | +| train/ | | +| approx_kl | 0.012991948 | +| clip_fraction | 0.344 | +| clip_range | 0.0704 | +| entropy_loss | -6.32 | +| explained_variance | 0.362 | +| learning_rate | 4.57e-05 | +| loss | -0.0276 | +| n_updates | 51408 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000224 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1422 | +| iterations | 8899 | +| time_elapsed | 12809 | +| total_timesteps | 18225152 | +| train/ | | +| approx_kl | 0.011990857 | +| clip_fraction | 0.318 | +| clip_range | 0.0704 | +| entropy_loss | -6.51 | +| explained_variance | 0.329 | +| learning_rate | 4.57e-05 | +| loss | -0.0218 | +| n_updates | 51412 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000144 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1422 | +| iterations | 8900 | +| time_elapsed | 12810 | +| total_timesteps | 18227200 | +| train/ | | +| approx_kl | 0.014827774 | +| clip_fraction | 0.348 | +| clip_range | 0.0704 | +| entropy_loss | -6.03 | +| explained_variance | 0.669 | +| learning_rate | 4.57e-05 | +| loss | -0.0271 | +| n_updates | 51416 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000145 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1422 | +| iterations | 8901 | +| time_elapsed | 12811 | +| total_timesteps | 18229248 | +| train/ | | +| approx_kl | 0.015810607 | +| clip_fraction | 0.375 | +| clip_range | 0.0704 | +| entropy_loss | -6.33 | +| explained_variance | -0.114 | +| learning_rate | 4.57e-05 | +| loss | -0.035 | +| n_updates | 51420 | +| policy_gradient_loss | -0.0218 | +| value_loss | 7.43e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1422 | +| iterations | 8902 | +| time_elapsed | 12813 | +| total_timesteps | 18231296 | +| train/ | | +| approx_kl | 0.012884799 | +| clip_fraction | 0.344 | +| clip_range | 0.0704 | +| entropy_loss | -6.38 | +| explained_variance | 0.51 | +| learning_rate | 4.57e-05 | +| loss | -0.0303 | +| n_updates | 51424 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000137 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1422 | +| iterations | 8903 | +| time_elapsed | 12814 | +| total_timesteps | 18233344 | +| train/ | | +| approx_kl | 0.014311335 | +| clip_fraction | 0.365 | +| clip_range | 0.0704 | +| entropy_loss | -6.48 | +| explained_variance | 0.496 | +| learning_rate | 4.57e-05 | +| loss | -0.0356 | +| n_updates | 51428 | +| policy_gradient_loss | -0.0204 | +| value_loss | 7.53e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1422 | +| iterations | 8904 | +| time_elapsed | 12816 | +| total_timesteps | 18235392 | +| train/ | | +| approx_kl | 0.0134580275 | +| clip_fraction | 0.348 | +| clip_range | 0.0704 | +| entropy_loss | -6.19 | +| explained_variance | 0.708 | +| learning_rate | 4.57e-05 | +| loss | -0.0309 | +| n_updates | 51432 | +| policy_gradient_loss | -0.0184 | +| value_loss | 6.24e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1422 | +| iterations | 8905 | +| time_elapsed | 12817 | +| total_timesteps | 18237440 | +| train/ | | +| approx_kl | 0.016159404 | +| clip_fraction | 0.315 | +| clip_range | 0.0704 | +| entropy_loss | -5.95 | +| explained_variance | 0.47 | +| learning_rate | 4.57e-05 | +| loss | -0.0276 | +| n_updates | 51436 | +| policy_gradient_loss | -0.0148 | +| value_loss | 0.000268 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1422 | +| iterations | 8906 | +| time_elapsed | 12819 | +| total_timesteps | 18239488 | +| train/ | | +| approx_kl | 0.01716551 | +| clip_fraction | 0.346 | +| clip_range | 0.0704 | +| entropy_loss | -6.24 | +| explained_variance | 0.351 | +| learning_rate | 4.57e-05 | +| loss | -0.0336 | +| n_updates | 51440 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000109 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1422 | +| iterations | 8907 | +| time_elapsed | 12820 | +| total_timesteps | 18241536 | +| train/ | | +| approx_kl | 0.013949193 | +| clip_fraction | 0.375 | +| clip_range | 0.0704 | +| entropy_loss | -6.62 | +| explained_variance | 0.264 | +| learning_rate | 4.57e-05 | +| loss | -0.0321 | +| n_updates | 51444 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000188 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1422 | +| iterations | 8908 | +| time_elapsed | 12821 | +| total_timesteps | 18243584 | +| train/ | | +| approx_kl | 0.0166622 | +| clip_fraction | 0.358 | +| clip_range | 0.0704 | +| entropy_loss | -6.39 | +| explained_variance | 0.5 | +| learning_rate | 4.57e-05 | +| loss | -0.0332 | +| n_updates | 51448 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000126 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1422 | +| iterations | 8909 | +| time_elapsed | 12823 | +| total_timesteps | 18245632 | +| train/ | | +| approx_kl | 0.014758138 | +| clip_fraction | 0.346 | +| clip_range | 0.0704 | +| entropy_loss | -6.53 | +| explained_variance | 0.351 | +| learning_rate | 4.57e-05 | +| loss | -0.0293 | +| n_updates | 51452 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000161 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1422 | +| iterations | 8910 | +| time_elapsed | 12824 | +| total_timesteps | 18247680 | +| train/ | | +| approx_kl | 0.016178414 | +| clip_fraction | 0.366 | +| clip_range | 0.0704 | +| entropy_loss | -6.48 | +| explained_variance | 0.388 | +| learning_rate | 4.57e-05 | +| loss | -0.0339 | +| n_updates | 51456 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000189 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1422 | +| iterations | 8911 | +| time_elapsed | 12826 | +| total_timesteps | 18249728 | +| train/ | | +| approx_kl | 0.014960075 | +| clip_fraction | 0.344 | +| clip_range | 0.0704 | +| entropy_loss | -6.71 | +| explained_variance | -0.145 | +| learning_rate | 4.57e-05 | +| loss | -0.0352 | +| n_updates | 51460 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000112 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1422 | +| iterations | 8912 | +| time_elapsed | 12827 | +| total_timesteps | 18251776 | +| train/ | | +| approx_kl | 0.0153627945 | +| clip_fraction | 0.349 | +| clip_range | 0.0704 | +| entropy_loss | -6.27 | +| explained_variance | 0.417 | +| learning_rate | 4.57e-05 | +| loss | -0.0257 | +| n_updates | 51464 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.00025 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1422 | +| iterations | 8913 | +| time_elapsed | 12829 | +| total_timesteps | 18253824 | +| train/ | | +| approx_kl | 0.017088387 | +| clip_fraction | 0.381 | +| clip_range | 0.0704 | +| entropy_loss | -6.38 | +| explained_variance | 0.39 | +| learning_rate | 4.57e-05 | +| loss | -0.0361 | +| n_updates | 51468 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000121 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1422 | +| iterations | 8914 | +| time_elapsed | 12830 | +| total_timesteps | 18255872 | +| train/ | | +| approx_kl | 0.015722085 | +| clip_fraction | 0.339 | +| clip_range | 0.0704 | +| entropy_loss | -5.75 | +| explained_variance | 0.626 | +| learning_rate | 4.57e-05 | +| loss | -0.0262 | +| n_updates | 51472 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000202 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1422 | +| iterations | 8915 | +| time_elapsed | 12832 | +| total_timesteps | 18257920 | +| train/ | | +| approx_kl | 0.017214194 | +| clip_fraction | 0.377 | +| clip_range | 0.0704 | +| entropy_loss | -6.27 | +| explained_variance | 0.255 | +| learning_rate | 4.57e-05 | +| loss | -0.0314 | +| n_updates | 51476 | +| policy_gradient_loss | -0.0216 | +| value_loss | 7.26e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1422 | +| iterations | 8916 | +| time_elapsed | 12833 | +| total_timesteps | 18259968 | +| train/ | | +| approx_kl | 0.013073157 | +| clip_fraction | 0.328 | +| clip_range | 0.0704 | +| entropy_loss | -6.73 | +| explained_variance | 0.00704 | +| learning_rate | 4.57e-05 | +| loss | -0.0254 | +| n_updates | 51480 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000226 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1422 | +| iterations | 8917 | +| time_elapsed | 12834 | +| total_timesteps | 18262016 | +| train/ | | +| approx_kl | 0.012214116 | +| clip_fraction | 0.338 | +| clip_range | 0.0704 | +| entropy_loss | -6.53 | +| explained_variance | 0.387 | +| learning_rate | 4.57e-05 | +| loss | -0.0283 | +| n_updates | 51484 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000222 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1422 | +| iterations | 8918 | +| time_elapsed | 12836 | +| total_timesteps | 18264064 | +| train/ | | +| approx_kl | 0.014883662 | +| clip_fraction | 0.373 | +| clip_range | 0.0704 | +| entropy_loss | -6.06 | +| explained_variance | 0.587 | +| learning_rate | 4.57e-05 | +| loss | -0.0341 | +| n_updates | 51488 | +| policy_gradient_loss | -0.0219 | +| value_loss | 9.97e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1422 | +| iterations | 8919 | +| time_elapsed | 12837 | +| total_timesteps | 18266112 | +| train/ | | +| approx_kl | 0.014552342 | +| clip_fraction | 0.341 | +| clip_range | 0.0704 | +| entropy_loss | -6.34 | +| explained_variance | 0.118 | +| learning_rate | 4.57e-05 | +| loss | -0.0285 | +| n_updates | 51492 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1422 | +| iterations | 8920 | +| time_elapsed | 12839 | +| total_timesteps | 18268160 | +| train/ | | +| approx_kl | 0.015928373 | +| clip_fraction | 0.386 | +| clip_range | 0.0704 | +| entropy_loss | -5.72 | +| explained_variance | 0.643 | +| learning_rate | 4.57e-05 | +| loss | -0.0282 | +| n_updates | 51496 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.00011 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1422 | +| iterations | 8921 | +| time_elapsed | 12840 | +| total_timesteps | 18270208 | +| train/ | | +| approx_kl | 0.017496713 | +| clip_fraction | 0.382 | +| clip_range | 0.0704 | +| entropy_loss | -6.24 | +| explained_variance | 0.558 | +| learning_rate | 4.57e-05 | +| loss | -0.0263 | +| n_updates | 51500 | +| policy_gradient_loss | -0.0197 | +| value_loss | 9.52e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1422 | +| iterations | 8922 | +| time_elapsed | 12842 | +| total_timesteps | 18272256 | +| train/ | | +| approx_kl | 0.014475915 | +| clip_fraction | 0.347 | +| clip_range | 0.0704 | +| entropy_loss | -6.91 | +| explained_variance | -0.00384 | +| learning_rate | 4.57e-05 | +| loss | -0.0252 | +| n_updates | 51504 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000154 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1422 | +| iterations | 8923 | +| time_elapsed | 12843 | +| total_timesteps | 18274304 | +| train/ | | +| approx_kl | 0.011113317 | +| clip_fraction | 0.368 | +| clip_range | 0.0704 | +| entropy_loss | -6.69 | +| explained_variance | 0.32 | +| learning_rate | 4.57e-05 | +| loss | -0.0326 | +| n_updates | 51508 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000191 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1422 | +| iterations | 8924 | +| time_elapsed | 12845 | +| total_timesteps | 18276352 | +| train/ | | +| approx_kl | 0.01457352 | +| clip_fraction | 0.365 | +| clip_range | 0.0704 | +| entropy_loss | -6.42 | +| explained_variance | 0.401 | +| learning_rate | 4.57e-05 | +| loss | -0.0375 | +| n_updates | 51512 | +| policy_gradient_loss | -0.0211 | +| value_loss | 9.39e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1422 | +| iterations | 8925 | +| time_elapsed | 12846 | +| total_timesteps | 18278400 | +| train/ | | +| approx_kl | 0.013913823 | +| clip_fraction | 0.361 | +| clip_range | 0.0704 | +| entropy_loss | -5.84 | +| explained_variance | 0.423 | +| learning_rate | 4.57e-05 | +| loss | -0.0304 | +| n_updates | 51516 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000297 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1422 | +| iterations | 8926 | +| time_elapsed | 12848 | +| total_timesteps | 18280448 | +| train/ | | +| approx_kl | 0.013627993 | +| clip_fraction | 0.376 | +| clip_range | 0.0704 | +| entropy_loss | -5.73 | +| explained_variance | 0.733 | +| learning_rate | 4.57e-05 | +| loss | -0.0378 | +| n_updates | 51520 | +| policy_gradient_loss | -0.023 | +| value_loss | 8.22e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1422 | +| iterations | 8927 | +| time_elapsed | 12849 | +| total_timesteps | 18282496 | +| train/ | | +| approx_kl | 0.017222561 | +| clip_fraction | 0.384 | +| clip_range | 0.0704 | +| entropy_loss | -6.07 | +| explained_variance | 0.562 | +| learning_rate | 4.57e-05 | +| loss | -0.0379 | +| n_updates | 51524 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000102 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1422 | +| iterations | 8928 | +| time_elapsed | 12850 | +| total_timesteps | 18284544 | +| train/ | | +| approx_kl | 0.01745422 | +| clip_fraction | 0.357 | +| clip_range | 0.0704 | +| entropy_loss | -6.71 | +| explained_variance | -0.188 | +| learning_rate | 4.57e-05 | +| loss | -0.0316 | +| n_updates | 51528 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000175 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1422 | +| iterations | 8929 | +| time_elapsed | 12852 | +| total_timesteps | 18286592 | +| train/ | | +| approx_kl | 0.014601626 | +| clip_fraction | 0.367 | +| clip_range | 0.0704 | +| entropy_loss | -6.7 | +| explained_variance | 0.36 | +| learning_rate | 4.57e-05 | +| loss | -0.0299 | +| n_updates | 51532 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000128 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1422 | +| iterations | 8930 | +| time_elapsed | 12853 | +| total_timesteps | 18288640 | +| train/ | | +| approx_kl | 0.013018826 | +| clip_fraction | 0.345 | +| clip_range | 0.0704 | +| entropy_loss | -6.61 | +| explained_variance | 0.265 | +| learning_rate | 4.57e-05 | +| loss | -0.0252 | +| n_updates | 51536 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000198 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1422 | +| iterations | 8931 | +| time_elapsed | 12855 | +| total_timesteps | 18290688 | +| train/ | | +| approx_kl | 0.014697142 | +| clip_fraction | 0.358 | +| clip_range | 0.0704 | +| entropy_loss | -6.58 | +| explained_variance | 0.481 | +| learning_rate | 4.57e-05 | +| loss | -0.0369 | +| n_updates | 51540 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.00014 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1422 | +| iterations | 8932 | +| time_elapsed | 12856 | +| total_timesteps | 18292736 | +| train/ | | +| approx_kl | 0.0110438615 | +| clip_fraction | 0.329 | +| clip_range | 0.0704 | +| entropy_loss | -6.28 | +| explained_variance | 0.323 | +| learning_rate | 4.57e-05 | +| loss | -0.0279 | +| n_updates | 51544 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000428 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1422 | +| iterations | 8933 | +| time_elapsed | 12858 | +| total_timesteps | 18294784 | +| train/ | | +| approx_kl | 0.012861712 | +| clip_fraction | 0.364 | +| clip_range | 0.0704 | +| entropy_loss | -6.54 | +| explained_variance | 0.147 | +| learning_rate | 4.57e-05 | +| loss | -0.0329 | +| n_updates | 51548 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000291 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1422 | +| iterations | 8934 | +| time_elapsed | 12859 | +| total_timesteps | 18296832 | +| train/ | | +| approx_kl | 0.011549127 | +| clip_fraction | 0.359 | +| clip_range | 0.0704 | +| entropy_loss | -6.31 | +| explained_variance | 0.25 | +| learning_rate | 4.57e-05 | +| loss | -0.0266 | +| n_updates | 51552 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000239 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1422 | +| iterations | 8935 | +| time_elapsed | 12860 | +| total_timesteps | 18298880 | +| train/ | | +| approx_kl | 0.0144665865 | +| clip_fraction | 0.351 | +| clip_range | 0.0704 | +| entropy_loss | -6.27 | +| explained_variance | 0.444 | +| learning_rate | 4.57e-05 | +| loss | -0.0324 | +| n_updates | 51556 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.00017 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1422 | +| iterations | 8936 | +| time_elapsed | 12862 | +| total_timesteps | 18300928 | +| train/ | | +| approx_kl | 0.017199371 | +| clip_fraction | 0.358 | +| clip_range | 0.0704 | +| entropy_loss | -6.34 | +| explained_variance | 0.327 | +| learning_rate | 4.57e-05 | +| loss | -0.0328 | +| n_updates | 51560 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000149 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1422 | +| iterations | 8937 | +| time_elapsed | 12863 | +| total_timesteps | 18302976 | +| train/ | | +| approx_kl | 0.013843309 | +| clip_fraction | 0.358 | +| clip_range | 0.0704 | +| entropy_loss | -6.37 | +| explained_variance | 0.563 | +| learning_rate | 4.57e-05 | +| loss | -0.0339 | +| n_updates | 51564 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000103 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1422 | +| iterations | 8938 | +| time_elapsed | 12865 | +| total_timesteps | 18305024 | +| train/ | | +| approx_kl | 0.0125075765 | +| clip_fraction | 0.363 | +| clip_range | 0.0704 | +| entropy_loss | -6.75 | +| explained_variance | 0.0241 | +| learning_rate | 4.57e-05 | +| loss | -0.033 | +| n_updates | 51568 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000145 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1422 | +| iterations | 8939 | +| time_elapsed | 12866 | +| total_timesteps | 18307072 | +| train/ | | +| approx_kl | 0.011984707 | +| clip_fraction | 0.333 | +| clip_range | 0.0704 | +| entropy_loss | -6.03 | +| explained_variance | 0.645 | +| learning_rate | 4.57e-05 | +| loss | -0.0338 | +| n_updates | 51572 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000121 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1422 | +| iterations | 8940 | +| time_elapsed | 12868 | +| total_timesteps | 18309120 | +| train/ | | +| approx_kl | 0.012319654 | +| clip_fraction | 0.344 | +| clip_range | 0.0704 | +| entropy_loss | -6.1 | +| explained_variance | 0.455 | +| learning_rate | 4.57e-05 | +| loss | -0.0239 | +| n_updates | 51576 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000262 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1422 | +| iterations | 8941 | +| time_elapsed | 12869 | +| total_timesteps | 18311168 | +| train/ | | +| approx_kl | 0.01524609 | +| clip_fraction | 0.343 | +| clip_range | 0.0704 | +| entropy_loss | -6.22 | +| explained_variance | 0.477 | +| learning_rate | 4.57e-05 | +| loss | -0.0275 | +| n_updates | 51580 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000241 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1422 | +| iterations | 8942 | +| time_elapsed | 12871 | +| total_timesteps | 18313216 | +| train/ | | +| approx_kl | 0.015648402 | +| clip_fraction | 0.375 | +| clip_range | 0.0704 | +| entropy_loss | -6.47 | +| explained_variance | 0.0149 | +| learning_rate | 4.57e-05 | +| loss | -0.0295 | +| n_updates | 51584 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.00013 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1422 | +| iterations | 8943 | +| time_elapsed | 12872 | +| total_timesteps | 18315264 | +| train/ | | +| approx_kl | 0.018762965 | +| clip_fraction | 0.388 | +| clip_range | 0.0704 | +| entropy_loss | -6.73 | +| explained_variance | -0.177 | +| learning_rate | 4.57e-05 | +| loss | -0.0375 | +| n_updates | 51588 | +| policy_gradient_loss | -0.0229 | +| value_loss | 9.46e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1422 | +| iterations | 8944 | +| time_elapsed | 12873 | +| total_timesteps | 18317312 | +| train/ | | +| approx_kl | 0.014327881 | +| clip_fraction | 0.347 | +| clip_range | 0.0704 | +| entropy_loss | -6.46 | +| explained_variance | 0.149 | +| learning_rate | 4.57e-05 | +| loss | -0.0231 | +| n_updates | 51592 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000292 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1422 | +| iterations | 8945 | +| time_elapsed | 12875 | +| total_timesteps | 18319360 | +| train/ | | +| approx_kl | 0.014353218 | +| clip_fraction | 0.34 | +| clip_range | 0.0704 | +| entropy_loss | -5.9 | +| explained_variance | 0.281 | +| learning_rate | 4.56e-05 | +| loss | -0.0293 | +| n_updates | 51596 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000248 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1422 | +| iterations | 8946 | +| time_elapsed | 12877 | +| total_timesteps | 18321408 | +| train/ | | +| approx_kl | 0.015228205 | +| clip_fraction | 0.379 | +| clip_range | 0.0704 | +| entropy_loss | -6.2 | +| explained_variance | 0.616 | +| learning_rate | 4.56e-05 | +| loss | -0.0337 | +| n_updates | 51600 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000102 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1422 | +| iterations | 8947 | +| time_elapsed | 12878 | +| total_timesteps | 18323456 | +| train/ | | +| approx_kl | 0.012040189 | +| clip_fraction | 0.332 | +| clip_range | 0.0704 | +| entropy_loss | -5.71 | +| explained_variance | 0.442 | +| learning_rate | 4.56e-05 | +| loss | -0.0219 | +| n_updates | 51604 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.000253 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1422 | +| iterations | 8948 | +| time_elapsed | 12880 | +| total_timesteps | 18325504 | +| train/ | | +| approx_kl | 0.0140926745 | +| clip_fraction | 0.382 | +| clip_range | 0.0704 | +| entropy_loss | -6.19 | +| explained_variance | 0.186 | +| learning_rate | 4.56e-05 | +| loss | -0.0355 | +| n_updates | 51608 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000176 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1422 | +| iterations | 8949 | +| time_elapsed | 12881 | +| total_timesteps | 18327552 | +| train/ | | +| approx_kl | 0.013598208 | +| clip_fraction | 0.383 | +| clip_range | 0.0704 | +| entropy_loss | -6.45 | +| explained_variance | 0.027 | +| learning_rate | 4.56e-05 | +| loss | -0.04 | +| n_updates | 51612 | +| policy_gradient_loss | -0.0235 | +| value_loss | 8.17e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1422 | +| iterations | 8950 | +| time_elapsed | 12882 | +| total_timesteps | 18329600 | +| train/ | | +| approx_kl | 0.014412768 | +| clip_fraction | 0.326 | +| clip_range | 0.0704 | +| entropy_loss | -5.75 | +| explained_variance | 0.461 | +| learning_rate | 4.56e-05 | +| loss | -0.0305 | +| n_updates | 51616 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000172 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1422 | +| iterations | 8951 | +| time_elapsed | 12884 | +| total_timesteps | 18331648 | +| train/ | | +| approx_kl | 0.01345304 | +| clip_fraction | 0.341 | +| clip_range | 0.0704 | +| entropy_loss | -6.07 | +| explained_variance | 0.373 | +| learning_rate | 4.56e-05 | +| loss | -0.0274 | +| n_updates | 51620 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000204 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1422 | +| iterations | 8952 | +| time_elapsed | 12885 | +| total_timesteps | 18333696 | +| train/ | | +| approx_kl | 0.01347109 | +| clip_fraction | 0.375 | +| clip_range | 0.0704 | +| entropy_loss | -6.63 | +| explained_variance | -0.102 | +| learning_rate | 4.56e-05 | +| loss | -0.0319 | +| n_updates | 51624 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000135 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1422 | +| iterations | 8953 | +| time_elapsed | 12887 | +| total_timesteps | 18335744 | +| train/ | | +| approx_kl | 0.01358329 | +| clip_fraction | 0.342 | +| clip_range | 0.0704 | +| entropy_loss | -6.42 | +| explained_variance | 0.475 | +| learning_rate | 4.56e-05 | +| loss | -0.0301 | +| n_updates | 51628 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000212 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1422 | +| iterations | 8954 | +| time_elapsed | 12888 | +| total_timesteps | 18337792 | +| train/ | | +| approx_kl | 0.013384218 | +| clip_fraction | 0.329 | +| clip_range | 0.0704 | +| entropy_loss | -6.55 | +| explained_variance | 0.175 | +| learning_rate | 4.56e-05 | +| loss | -0.0257 | +| n_updates | 51632 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000338 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1422 | +| iterations | 8955 | +| time_elapsed | 12890 | +| total_timesteps | 18339840 | +| train/ | | +| approx_kl | 0.0155090485 | +| clip_fraction | 0.37 | +| clip_range | 0.0704 | +| entropy_loss | -6.62 | +| explained_variance | 0.328 | +| learning_rate | 4.56e-05 | +| loss | -0.0302 | +| n_updates | 51636 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000147 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1422 | +| iterations | 8956 | +| time_elapsed | 12891 | +| total_timesteps | 18341888 | +| train/ | | +| approx_kl | 0.015495155 | +| clip_fraction | 0.331 | +| clip_range | 0.0704 | +| entropy_loss | -6.09 | +| explained_variance | 0.577 | +| learning_rate | 4.56e-05 | +| loss | -0.0335 | +| n_updates | 51640 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000128 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1422 | +| iterations | 8957 | +| time_elapsed | 12893 | +| total_timesteps | 18343936 | +| train/ | | +| approx_kl | 0.014915135 | +| clip_fraction | 0.343 | +| clip_range | 0.0704 | +| entropy_loss | -6.42 | +| explained_variance | -0.107 | +| learning_rate | 4.56e-05 | +| loss | -0.0296 | +| n_updates | 51644 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000233 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1422 | +| iterations | 8958 | +| time_elapsed | 12894 | +| total_timesteps | 18345984 | +| train/ | | +| approx_kl | 0.015253282 | +| clip_fraction | 0.37 | +| clip_range | 0.0704 | +| entropy_loss | -6.21 | +| explained_variance | 0.584 | +| learning_rate | 4.56e-05 | +| loss | -0.0306 | +| n_updates | 51648 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000122 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1422 | +| iterations | 8959 | +| time_elapsed | 12895 | +| total_timesteps | 18348032 | +| train/ | | +| approx_kl | 0.01780368 | +| clip_fraction | 0.383 | +| clip_range | 0.0704 | +| entropy_loss | -6.45 | +| explained_variance | 0.436 | +| learning_rate | 4.56e-05 | +| loss | -0.0426 | +| n_updates | 51652 | +| policy_gradient_loss | -0.0238 | +| value_loss | 9.22e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1422 | +| iterations | 8960 | +| time_elapsed | 12897 | +| total_timesteps | 18350080 | +| train/ | | +| approx_kl | 0.014068566 | +| clip_fraction | 0.356 | +| clip_range | 0.0704 | +| entropy_loss | -6.59 | +| explained_variance | 0.369 | +| learning_rate | 4.56e-05 | +| loss | -0.0322 | +| n_updates | 51656 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000123 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1422 | +| iterations | 8961 | +| time_elapsed | 12898 | +| total_timesteps | 18352128 | +| train/ | | +| approx_kl | 0.015570089 | +| clip_fraction | 0.348 | +| clip_range | 0.0704 | +| entropy_loss | -6.51 | +| explained_variance | 0.43 | +| learning_rate | 4.56e-05 | +| loss | -0.0296 | +| n_updates | 51660 | +| policy_gradient_loss | -0.0194 | +| value_loss | 9.54e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1422 | +| iterations | 8962 | +| time_elapsed | 12900 | +| total_timesteps | 18354176 | +| train/ | | +| approx_kl | 0.01314079 | +| clip_fraction | 0.364 | +| clip_range | 0.0704 | +| entropy_loss | -6.27 | +| explained_variance | 0.434 | +| learning_rate | 4.56e-05 | +| loss | -0.0339 | +| n_updates | 51664 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000181 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1422 | +| iterations | 8963 | +| time_elapsed | 12901 | +| total_timesteps | 18356224 | +| train/ | | +| approx_kl | 0.014828984 | +| clip_fraction | 0.36 | +| clip_range | 0.0704 | +| entropy_loss | -6.58 | +| explained_variance | 0.0276 | +| learning_rate | 4.56e-05 | +| loss | -0.0298 | +| n_updates | 51668 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000244 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1422 | +| iterations | 8964 | +| time_elapsed | 12903 | +| total_timesteps | 18358272 | +| train/ | | +| approx_kl | 0.015541211 | +| clip_fraction | 0.349 | +| clip_range | 0.0704 | +| entropy_loss | -6.2 | +| explained_variance | 0.347 | +| learning_rate | 4.56e-05 | +| loss | -0.0311 | +| n_updates | 51672 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000225 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1422 | +| iterations | 8965 | +| time_elapsed | 12904 | +| total_timesteps | 18360320 | +| train/ | | +| approx_kl | 0.012835132 | +| clip_fraction | 0.361 | +| clip_range | 0.0704 | +| entropy_loss | -6.62 | +| explained_variance | 0.204 | +| learning_rate | 4.56e-05 | +| loss | -0.0239 | +| n_updates | 51676 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000322 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1422 | +| iterations | 8966 | +| time_elapsed | 12905 | +| total_timesteps | 18362368 | +| train/ | | +| approx_kl | 0.015927993 | +| clip_fraction | 0.346 | +| clip_range | 0.0704 | +| entropy_loss | -6.52 | +| explained_variance | 0.542 | +| learning_rate | 4.56e-05 | +| loss | -0.0305 | +| n_updates | 51680 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000139 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1422 | +| iterations | 8967 | +| time_elapsed | 12907 | +| total_timesteps | 18364416 | +| train/ | | +| approx_kl | 0.012206092 | +| clip_fraction | 0.359 | +| clip_range | 0.0704 | +| entropy_loss | -6.31 | +| explained_variance | 0.472 | +| learning_rate | 4.56e-05 | +| loss | -0.0287 | +| n_updates | 51684 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000187 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1422 | +| iterations | 8968 | +| time_elapsed | 12908 | +| total_timesteps | 18366464 | +| train/ | | +| approx_kl | 0.016275728 | +| clip_fraction | 0.393 | +| clip_range | 0.0704 | +| entropy_loss | -6.52 | +| explained_variance | -0.12 | +| learning_rate | 4.56e-05 | +| loss | -0.0326 | +| n_updates | 51688 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000119 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1422 | +| iterations | 8969 | +| time_elapsed | 12910 | +| total_timesteps | 18368512 | +| train/ | | +| approx_kl | 0.011059174 | +| clip_fraction | 0.339 | +| clip_range | 0.0704 | +| entropy_loss | -6.37 | +| explained_variance | 0.237 | +| learning_rate | 4.56e-05 | +| loss | -0.0317 | +| n_updates | 51692 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000345 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1422 | +| iterations | 8970 | +| time_elapsed | 12911 | +| total_timesteps | 18370560 | +| train/ | | +| approx_kl | 0.014778924 | +| clip_fraction | 0.379 | +| clip_range | 0.0704 | +| entropy_loss | -6.33 | +| explained_variance | 0.346 | +| learning_rate | 4.56e-05 | +| loss | -0.0369 | +| n_updates | 51696 | +| policy_gradient_loss | -0.022 | +| value_loss | 0.000107 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1422 | +| iterations | 8971 | +| time_elapsed | 12913 | +| total_timesteps | 18372608 | +| train/ | | +| approx_kl | 0.013132834 | +| clip_fraction | 0.324 | +| clip_range | 0.0704 | +| entropy_loss | -6.46 | +| explained_variance | 0.574 | +| learning_rate | 4.56e-05 | +| loss | -0.0342 | +| n_updates | 51700 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000109 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1422 | +| iterations | 8972 | +| time_elapsed | 12914 | +| total_timesteps | 18374656 | +| train/ | | +| approx_kl | 0.01404279 | +| clip_fraction | 0.303 | +| clip_range | 0.0704 | +| entropy_loss | -6.43 | +| explained_variance | 0.412 | +| learning_rate | 4.56e-05 | +| loss | -0.0241 | +| n_updates | 51704 | +| policy_gradient_loss | -0.0147 | +| value_loss | 0.000203 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1422 | +| iterations | 8973 | +| time_elapsed | 12916 | +| total_timesteps | 18376704 | +| train/ | | +| approx_kl | 0.012508801 | +| clip_fraction | 0.347 | +| clip_range | 0.0704 | +| entropy_loss | -6.28 | +| explained_variance | 0.61 | +| learning_rate | 4.56e-05 | +| loss | -0.0328 | +| n_updates | 51708 | +| policy_gradient_loss | -0.0191 | +| value_loss | 9.23e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1422 | +| iterations | 8974 | +| time_elapsed | 12917 | +| total_timesteps | 18378752 | +| train/ | | +| approx_kl | 0.012677625 | +| clip_fraction | 0.353 | +| clip_range | 0.0704 | +| entropy_loss | -6.5 | +| explained_variance | 0.234 | +| learning_rate | 4.56e-05 | +| loss | -0.0303 | +| n_updates | 51712 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000183 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1422 | +| iterations | 8975 | +| time_elapsed | 12918 | +| total_timesteps | 18380800 | +| train/ | | +| approx_kl | 0.009784281 | +| clip_fraction | 0.312 | +| clip_range | 0.0704 | +| entropy_loss | -6.9 | +| explained_variance | 0.0164 | +| learning_rate | 4.56e-05 | +| loss | -0.0291 | +| n_updates | 51716 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000139 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1422 | +| iterations | 8976 | +| time_elapsed | 12920 | +| total_timesteps | 18382848 | +| train/ | | +| approx_kl | 0.011301819 | +| clip_fraction | 0.364 | +| clip_range | 0.0704 | +| entropy_loss | -6.88 | +| explained_variance | 0.36 | +| learning_rate | 4.56e-05 | +| loss | -0.0312 | +| n_updates | 51720 | +| policy_gradient_loss | -0.0209 | +| value_loss | 8.32e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1422 | +| iterations | 8977 | +| time_elapsed | 12921 | +| total_timesteps | 18384896 | +| train/ | | +| approx_kl | 0.012869704 | +| clip_fraction | 0.339 | +| clip_range | 0.0704 | +| entropy_loss | -6.04 | +| explained_variance | 0.568 | +| learning_rate | 4.56e-05 | +| loss | -0.026 | +| n_updates | 51724 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000135 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1422 | +| iterations | 8978 | +| time_elapsed | 12923 | +| total_timesteps | 18386944 | +| train/ | | +| approx_kl | 0.013294207 | +| clip_fraction | 0.349 | +| clip_range | 0.0704 | +| entropy_loss | -5.63 | +| explained_variance | 0.626 | +| learning_rate | 4.56e-05 | +| loss | -0.0234 | +| n_updates | 51728 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000161 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1422 | +| iterations | 8979 | +| time_elapsed | 12924 | +| total_timesteps | 18388992 | +| train/ | | +| approx_kl | 0.015511259 | +| clip_fraction | 0.363 | +| clip_range | 0.0704 | +| entropy_loss | -6.21 | +| explained_variance | 0.554 | +| learning_rate | 4.56e-05 | +| loss | -0.0317 | +| n_updates | 51732 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000118 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1422 | +| iterations | 8980 | +| time_elapsed | 12926 | +| total_timesteps | 18391040 | +| train/ | | +| approx_kl | 0.013362907 | +| clip_fraction | 0.359 | +| clip_range | 0.0704 | +| entropy_loss | -6.69 | +| explained_variance | 0.0157 | +| learning_rate | 4.56e-05 | +| loss | -0.0267 | +| n_updates | 51736 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000218 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1422 | +| iterations | 8981 | +| time_elapsed | 12927 | +| total_timesteps | 18393088 | +| train/ | | +| approx_kl | 0.015493574 | +| clip_fraction | 0.378 | +| clip_range | 0.0704 | +| entropy_loss | -6.48 | +| explained_variance | 0.326 | +| learning_rate | 4.56e-05 | +| loss | -0.0297 | +| n_updates | 51740 | +| policy_gradient_loss | -0.0203 | +| value_loss | 9.34e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1422 | +| iterations | 8982 | +| time_elapsed | 12928 | +| total_timesteps | 18395136 | +| train/ | | +| approx_kl | 0.013723987 | +| clip_fraction | 0.333 | +| clip_range | 0.0704 | +| entropy_loss | -6.37 | +| explained_variance | 0.327 | +| learning_rate | 4.56e-05 | +| loss | -0.0323 | +| n_updates | 51744 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000278 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1422 | +| iterations | 8983 | +| time_elapsed | 12930 | +| total_timesteps | 18397184 | +| train/ | | +| approx_kl | 0.016946485 | +| clip_fraction | 0.39 | +| clip_range | 0.0704 | +| entropy_loss | -6.55 | +| explained_variance | 0.314 | +| learning_rate | 4.56e-05 | +| loss | -0.0348 | +| n_updates | 51748 | +| policy_gradient_loss | -0.0221 | +| value_loss | 0.000167 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1422 | +| iterations | 8984 | +| time_elapsed | 12931 | +| total_timesteps | 18399232 | +| train/ | | +| approx_kl | 0.014505257 | +| clip_fraction | 0.366 | +| clip_range | 0.0704 | +| entropy_loss | -6.15 | +| explained_variance | 0.548 | +| learning_rate | 4.56e-05 | +| loss | -0.0256 | +| n_updates | 51752 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000193 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1422 | +| iterations | 8985 | +| time_elapsed | 12933 | +| total_timesteps | 18401280 | +| train/ | | +| approx_kl | 0.014822302 | +| clip_fraction | 0.385 | +| clip_range | 0.0704 | +| entropy_loss | -6.53 | +| explained_variance | 0.294 | +| learning_rate | 4.56e-05 | +| loss | -0.0397 | +| n_updates | 51756 | +| policy_gradient_loss | -0.0247 | +| value_loss | 6.74e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1422 | +| iterations | 8986 | +| time_elapsed | 12934 | +| total_timesteps | 18403328 | +| train/ | | +| approx_kl | 0.010576391 | +| clip_fraction | 0.349 | +| clip_range | 0.0704 | +| entropy_loss | -6.73 | +| explained_variance | 0.217 | +| learning_rate | 4.56e-05 | +| loss | -0.0307 | +| n_updates | 51760 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000292 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1422 | +| iterations | 8987 | +| time_elapsed | 12936 | +| total_timesteps | 18405376 | +| train/ | | +| approx_kl | 0.015929282 | +| clip_fraction | 0.349 | +| clip_range | 0.0704 | +| entropy_loss | -6.02 | +| explained_variance | 0.637 | +| learning_rate | 4.56e-05 | +| loss | -0.0366 | +| n_updates | 51764 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000104 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1422 | +| iterations | 8988 | +| time_elapsed | 12937 | +| total_timesteps | 18407424 | +| train/ | | +| approx_kl | 0.011236599 | +| clip_fraction | 0.327 | +| clip_range | 0.0704 | +| entropy_loss | -6.45 | +| explained_variance | 0.338 | +| learning_rate | 4.56e-05 | +| loss | -0.0288 | +| n_updates | 51768 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000132 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1422 | +| iterations | 8989 | +| time_elapsed | 12939 | +| total_timesteps | 18409472 | +| train/ | | +| approx_kl | 0.012415397 | +| clip_fraction | 0.338 | +| clip_range | 0.0704 | +| entropy_loss | -6.42 | +| explained_variance | 0.581 | +| learning_rate | 4.56e-05 | +| loss | -0.0316 | +| n_updates | 51772 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000134 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1422 | +| iterations | 8990 | +| time_elapsed | 12940 | +| total_timesteps | 18411520 | +| train/ | | +| approx_kl | 0.018583352 | +| clip_fraction | 0.367 | +| clip_range | 0.0704 | +| entropy_loss | -6.59 | +| explained_variance | 0.247 | +| learning_rate | 4.56e-05 | +| loss | -0.0292 | +| n_updates | 51776 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000153 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1422 | +| iterations | 8991 | +| time_elapsed | 12941 | +| total_timesteps | 18413568 | +| train/ | | +| approx_kl | 0.013519771 | +| clip_fraction | 0.356 | +| clip_range | 0.0704 | +| entropy_loss | -6.75 | +| explained_variance | 0.00789 | +| learning_rate | 4.56e-05 | +| loss | -0.0282 | +| n_updates | 51780 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000353 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1422 | +| iterations | 8992 | +| time_elapsed | 12943 | +| total_timesteps | 18415616 | +| train/ | | +| approx_kl | 0.012429555 | +| clip_fraction | 0.331 | +| clip_range | 0.0704 | +| entropy_loss | -6.54 | +| explained_variance | 0.568 | +| learning_rate | 4.56e-05 | +| loss | -0.0345 | +| n_updates | 51784 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000123 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1422 | +| iterations | 8993 | +| time_elapsed | 12944 | +| total_timesteps | 18417664 | +| train/ | | +| approx_kl | 0.011002663 | +| clip_fraction | 0.304 | +| clip_range | 0.0704 | +| entropy_loss | -5.79 | +| explained_variance | 0.364 | +| learning_rate | 4.56e-05 | +| loss | -0.0196 | +| n_updates | 51788 | +| policy_gradient_loss | -0.0146 | +| value_loss | 0.000383 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1422 | +| iterations | 8994 | +| time_elapsed | 12946 | +| total_timesteps | 18419712 | +| train/ | | +| approx_kl | 0.013495176 | +| clip_fraction | 0.381 | +| clip_range | 0.0704 | +| entropy_loss | -5.98 | +| explained_variance | 0.428 | +| learning_rate | 4.56e-05 | +| loss | -0.0303 | +| n_updates | 51792 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000231 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1422 | +| iterations | 8995 | +| time_elapsed | 12947 | +| total_timesteps | 18421760 | +| train/ | | +| approx_kl | 0.0142956 | +| clip_fraction | 0.364 | +| clip_range | 0.0704 | +| entropy_loss | -6.56 | +| explained_variance | 0.0722 | +| learning_rate | 4.56e-05 | +| loss | -0.0313 | +| n_updates | 51796 | +| policy_gradient_loss | -0.0219 | +| value_loss | 0.000217 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1422 | +| iterations | 8996 | +| time_elapsed | 12949 | +| total_timesteps | 18423808 | +| train/ | | +| approx_kl | 0.0162936 | +| clip_fraction | 0.393 | +| clip_range | 0.0704 | +| entropy_loss | -6.6 | +| explained_variance | 0.237 | +| learning_rate | 4.56e-05 | +| loss | -0.0366 | +| n_updates | 51800 | +| policy_gradient_loss | -0.0243 | +| value_loss | 0.000145 | +--------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1422 | +| iterations | 8997 | +| time_elapsed | 12950 | +| total_timesteps | 18425856 | +| train/ | | +| approx_kl | 0.01403543 | +| clip_fraction | 0.347 | +| clip_range | 0.0704 | +| entropy_loss | -6.58 | +| explained_variance | 0.175 | +| learning_rate | 4.56e-05 | +| loss | -0.0362 | +| n_updates | 51804 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000193 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1422 | +| iterations | 8998 | +| time_elapsed | 12951 | +| total_timesteps | 18427904 | +| train/ | | +| approx_kl | 0.0120531125 | +| clip_fraction | 0.336 | +| clip_range | 0.0704 | +| entropy_loss | -6.69 | +| explained_variance | 0.408 | +| learning_rate | 4.56e-05 | +| loss | -0.0308 | +| n_updates | 51808 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000136 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1422 | +| iterations | 8999 | +| time_elapsed | 12953 | +| total_timesteps | 18429952 | +| train/ | | +| approx_kl | 0.013801843 | +| clip_fraction | 0.349 | +| clip_range | 0.0704 | +| entropy_loss | -6.73 | +| explained_variance | 0.246 | +| learning_rate | 4.56e-05 | +| loss | -0.0301 | +| n_updates | 51812 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000112 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1422 | +| iterations | 9000 | +| time_elapsed | 12954 | +| total_timesteps | 18432000 | +| train/ | | +| approx_kl | 0.012218554 | +| clip_fraction | 0.342 | +| clip_range | 0.0704 | +| entropy_loss | -6.67 | +| explained_variance | 0.177 | +| learning_rate | 4.56e-05 | +| loss | -0.0298 | +| n_updates | 51816 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000392 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1422 | +| iterations | 9001 | +| time_elapsed | 12956 | +| total_timesteps | 18434048 | +| train/ | | +| approx_kl | 0.011029478 | +| clip_fraction | 0.351 | +| clip_range | 0.0704 | +| entropy_loss | -5.86 | +| explained_variance | 0.607 | +| learning_rate | 4.56e-05 | +| loss | -0.0281 | +| n_updates | 51820 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000165 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1422 | +| iterations | 9002 | +| time_elapsed | 12957 | +| total_timesteps | 18436096 | +| train/ | | +| approx_kl | 0.011228036 | +| clip_fraction | 0.356 | +| clip_range | 0.0704 | +| entropy_loss | -6.62 | +| explained_variance | 0.0593 | +| learning_rate | 4.56e-05 | +| loss | -0.0388 | +| n_updates | 51824 | +| policy_gradient_loss | -0.022 | +| value_loss | 9.82e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1422 | +| iterations | 9003 | +| time_elapsed | 12959 | +| total_timesteps | 18438144 | +| train/ | | +| approx_kl | 0.014268336 | +| clip_fraction | 0.322 | +| clip_range | 0.0704 | +| entropy_loss | -5.92 | +| explained_variance | 0.54 | +| learning_rate | 4.56e-05 | +| loss | -0.031 | +| n_updates | 51828 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000268 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1422 | +| iterations | 9004 | +| time_elapsed | 12960 | +| total_timesteps | 18440192 | +| train/ | | +| approx_kl | 0.012986711 | +| clip_fraction | 0.341 | +| clip_range | 0.0704 | +| entropy_loss | -6.15 | +| explained_variance | 0.613 | +| learning_rate | 4.56e-05 | +| loss | -0.0281 | +| n_updates | 51832 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000123 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1422 | +| iterations | 9005 | +| time_elapsed | 12961 | +| total_timesteps | 18442240 | +| train/ | | +| approx_kl | 0.011546972 | +| clip_fraction | 0.338 | +| clip_range | 0.0704 | +| entropy_loss | -6.69 | +| explained_variance | 0.0798 | +| learning_rate | 4.56e-05 | +| loss | -0.0314 | +| n_updates | 51836 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000205 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1422 | +| iterations | 9006 | +| time_elapsed | 12963 | +| total_timesteps | 18444288 | +| train/ | | +| approx_kl | 0.0099643655 | +| clip_fraction | 0.331 | +| clip_range | 0.0704 | +| entropy_loss | -6.78 | +| explained_variance | 0.286 | +| learning_rate | 4.56e-05 | +| loss | -0.0263 | +| n_updates | 51840 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000278 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1422 | +| iterations | 9007 | +| time_elapsed | 12964 | +| total_timesteps | 18446336 | +| train/ | | +| approx_kl | 0.012959277 | +| clip_fraction | 0.384 | +| clip_range | 0.0704 | +| entropy_loss | -5.86 | +| explained_variance | 0.786 | +| learning_rate | 4.56e-05 | +| loss | -0.0375 | +| n_updates | 51844 | +| policy_gradient_loss | -0.0239 | +| value_loss | 6.08e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1422 | +| iterations | 9008 | +| time_elapsed | 12966 | +| total_timesteps | 18448384 | +| train/ | | +| approx_kl | 0.014028743 | +| clip_fraction | 0.339 | +| clip_range | 0.0704 | +| entropy_loss | -6.28 | +| explained_variance | -0.145 | +| learning_rate | 4.56e-05 | +| loss | -0.0272 | +| n_updates | 51848 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000186 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1422 | +| iterations | 9009 | +| time_elapsed | 12967 | +| total_timesteps | 18450432 | +| train/ | | +| approx_kl | 0.010191125 | +| clip_fraction | 0.308 | +| clip_range | 0.0704 | +| entropy_loss | -6.65 | +| explained_variance | 0.0527 | +| learning_rate | 4.56e-05 | +| loss | -0.0277 | +| n_updates | 51852 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000389 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1422 | +| iterations | 9010 | +| time_elapsed | 12968 | +| total_timesteps | 18452480 | +| train/ | | +| approx_kl | 0.01233802 | +| clip_fraction | 0.35 | +| clip_range | 0.0704 | +| entropy_loss | -5.91 | +| explained_variance | 0.647 | +| learning_rate | 4.56e-05 | +| loss | -0.029 | +| n_updates | 51856 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.00015 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1422 | +| iterations | 9011 | +| time_elapsed | 12970 | +| total_timesteps | 18454528 | +| train/ | | +| approx_kl | 0.015231409 | +| clip_fraction | 0.345 | +| clip_range | 0.0704 | +| entropy_loss | -6.27 | +| explained_variance | 0.423 | +| learning_rate | 4.56e-05 | +| loss | -0.0345 | +| n_updates | 51860 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000174 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1422 | +| iterations | 9012 | +| time_elapsed | 12971 | +| total_timesteps | 18456576 | +| train/ | | +| approx_kl | 0.01425295 | +| clip_fraction | 0.368 | +| clip_range | 0.0704 | +| entropy_loss | -6.49 | +| explained_variance | -0.044 | +| learning_rate | 4.56e-05 | +| loss | -0.0321 | +| n_updates | 51864 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000151 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1422 | +| iterations | 9013 | +| time_elapsed | 12973 | +| total_timesteps | 18458624 | +| train/ | | +| approx_kl | 0.013817846 | +| clip_fraction | 0.342 | +| clip_range | 0.0704 | +| entropy_loss | -5.87 | +| explained_variance | 0.691 | +| learning_rate | 4.56e-05 | +| loss | -0.0353 | +| n_updates | 51868 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000123 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1422 | +| iterations | 9014 | +| time_elapsed | 12974 | +| total_timesteps | 18460672 | +| train/ | | +| approx_kl | 0.013011022 | +| clip_fraction | 0.347 | +| clip_range | 0.0704 | +| entropy_loss | -5.91 | +| explained_variance | 0.535 | +| learning_rate | 4.56e-05 | +| loss | -0.0238 | +| n_updates | 51872 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000184 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1422 | +| iterations | 9015 | +| time_elapsed | 12976 | +| total_timesteps | 18462720 | +| train/ | | +| approx_kl | 0.016864413 | +| clip_fraction | 0.369 | +| clip_range | 0.0704 | +| entropy_loss | -6.43 | +| explained_variance | -0.116 | +| learning_rate | 4.56e-05 | +| loss | -0.0284 | +| n_updates | 51876 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000131 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1422 | +| iterations | 9016 | +| time_elapsed | 12977 | +| total_timesteps | 18464768 | +| train/ | | +| approx_kl | 0.013162254 | +| clip_fraction | 0.357 | +| clip_range | 0.0704 | +| entropy_loss | -6.08 | +| explained_variance | 0.453 | +| learning_rate | 4.56e-05 | +| loss | -0.0238 | +| n_updates | 51880 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000233 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1422 | +| iterations | 9017 | +| time_elapsed | 12979 | +| total_timesteps | 18466816 | +| train/ | | +| approx_kl | 0.013749467 | +| clip_fraction | 0.349 | +| clip_range | 0.0704 | +| entropy_loss | -6.52 | +| explained_variance | 0.19 | +| learning_rate | 4.56e-05 | +| loss | -0.0224 | +| n_updates | 51884 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000342 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1422 | +| iterations | 9018 | +| time_elapsed | 12980 | +| total_timesteps | 18468864 | +| train/ | | +| approx_kl | 0.014350805 | +| clip_fraction | 0.344 | +| clip_range | 0.0704 | +| entropy_loss | -5.98 | +| explained_variance | 0.597 | +| learning_rate | 4.56e-05 | +| loss | -0.0297 | +| n_updates | 51888 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000162 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1422 | +| iterations | 9019 | +| time_elapsed | 12982 | +| total_timesteps | 18470912 | +| train/ | | +| approx_kl | 0.01327195 | +| clip_fraction | 0.362 | +| clip_range | 0.0704 | +| entropy_loss | -6.33 | +| explained_variance | 0.386 | +| learning_rate | 4.56e-05 | +| loss | -0.0399 | +| n_updates | 51892 | +| policy_gradient_loss | -0.0234 | +| value_loss | 0.000114 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1422 | +| iterations | 9020 | +| time_elapsed | 12983 | +| total_timesteps | 18472960 | +| train/ | | +| approx_kl | 0.011885485 | +| clip_fraction | 0.329 | +| clip_range | 0.0704 | +| entropy_loss | -7.03 | +| explained_variance | -0.116 | +| learning_rate | 4.56e-05 | +| loss | -0.0312 | +| n_updates | 51896 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000229 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1422 | +| iterations | 9021 | +| time_elapsed | 12984 | +| total_timesteps | 18475008 | +| train/ | | +| approx_kl | 0.012784361 | +| clip_fraction | 0.376 | +| clip_range | 0.0704 | +| entropy_loss | -7.04 | +| explained_variance | -0.138 | +| learning_rate | 4.56e-05 | +| loss | -0.0331 | +| n_updates | 51900 | +| policy_gradient_loss | -0.0224 | +| value_loss | 9.29e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1422 | +| iterations | 9022 | +| time_elapsed | 12986 | +| total_timesteps | 18477056 | +| train/ | | +| approx_kl | 0.013098579 | +| clip_fraction | 0.363 | +| clip_range | 0.0704 | +| entropy_loss | -6.62 | +| explained_variance | 0.24 | +| learning_rate | 4.56e-05 | +| loss | -0.0342 | +| n_updates | 51904 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.00028 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1422 | +| iterations | 9023 | +| time_elapsed | 12987 | +| total_timesteps | 18479104 | +| train/ | | +| approx_kl | 0.015506762 | +| clip_fraction | 0.36 | +| clip_range | 0.0704 | +| entropy_loss | -5.98 | +| explained_variance | 0.616 | +| learning_rate | 4.56e-05 | +| loss | -0.0285 | +| n_updates | 51908 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000125 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1422 | +| iterations | 9024 | +| time_elapsed | 12989 | +| total_timesteps | 18481152 | +| train/ | | +| approx_kl | 0.014812205 | +| clip_fraction | 0.35 | +| clip_range | 0.0704 | +| entropy_loss | -6.05 | +| explained_variance | 0.512 | +| learning_rate | 4.56e-05 | +| loss | -0.0317 | +| n_updates | 51912 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000142 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1422 | +| iterations | 9025 | +| time_elapsed | 12990 | +| total_timesteps | 18483200 | +| train/ | | +| approx_kl | 0.013486082 | +| clip_fraction | 0.364 | +| clip_range | 0.0704 | +| entropy_loss | -6.68 | +| explained_variance | 0.0281 | +| learning_rate | 4.56e-05 | +| loss | -0.0365 | +| n_updates | 51916 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000107 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1422 | +| iterations | 9026 | +| time_elapsed | 12992 | +| total_timesteps | 18485248 | +| train/ | | +| approx_kl | 0.015399492 | +| clip_fraction | 0.388 | +| clip_range | 0.0704 | +| entropy_loss | -6.67 | +| explained_variance | -0.0579 | +| learning_rate | 4.56e-05 | +| loss | -0.0446 | +| n_updates | 51920 | +| policy_gradient_loss | -0.0241 | +| value_loss | 3.88e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1422 | +| iterations | 9027 | +| time_elapsed | 12993 | +| total_timesteps | 18487296 | +| train/ | | +| approx_kl | 0.015291788 | +| clip_fraction | 0.339 | +| clip_range | 0.0704 | +| entropy_loss | -5.57 | +| explained_variance | 0.764 | +| learning_rate | 4.56e-05 | +| loss | -0.0242 | +| n_updates | 51924 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.0001 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1422 | +| iterations | 9028 | +| time_elapsed | 12995 | +| total_timesteps | 18489344 | +| train/ | | +| approx_kl | 0.014606945 | +| clip_fraction | 0.357 | +| clip_range | 0.0704 | +| entropy_loss | -6.17 | +| explained_variance | 0.364 | +| learning_rate | 4.56e-05 | +| loss | -0.0285 | +| n_updates | 51928 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.00017 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1422 | +| iterations | 9029 | +| time_elapsed | 12996 | +| total_timesteps | 18491392 | +| train/ | | +| approx_kl | 0.0153265055 | +| clip_fraction | 0.33 | +| clip_range | 0.0704 | +| entropy_loss | -6.36 | +| explained_variance | 0.144 | +| learning_rate | 4.56e-05 | +| loss | -0.0266 | +| n_updates | 51932 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000258 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1422 | +| iterations | 9030 | +| time_elapsed | 12998 | +| total_timesteps | 18493440 | +| train/ | | +| approx_kl | 0.01683588 | +| clip_fraction | 0.325 | +| clip_range | 0.0704 | +| entropy_loss | -6.3 | +| explained_variance | 0.229 | +| learning_rate | 4.56e-05 | +| loss | -0.0341 | +| n_updates | 51936 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000164 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1422 | +| iterations | 9031 | +| time_elapsed | 12999 | +| total_timesteps | 18495488 | +| train/ | | +| approx_kl | 0.01614452 | +| clip_fraction | 0.374 | +| clip_range | 0.0704 | +| entropy_loss | -6.64 | +| explained_variance | 0.462 | +| learning_rate | 4.56e-05 | +| loss | -0.0331 | +| n_updates | 51940 | +| policy_gradient_loss | -0.0212 | +| value_loss | 8.84e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1422 | +| iterations | 9032 | +| time_elapsed | 13000 | +| total_timesteps | 18497536 | +| train/ | | +| approx_kl | 0.013347236 | +| clip_fraction | 0.345 | +| clip_range | 0.0704 | +| entropy_loss | -6.71 | +| explained_variance | 0.294 | +| learning_rate | 4.56e-05 | +| loss | -0.0338 | +| n_updates | 51944 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000142 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1422 | +| iterations | 9033 | +| time_elapsed | 13002 | +| total_timesteps | 18499584 | +| train/ | | +| approx_kl | 0.01248837 | +| clip_fraction | 0.329 | +| clip_range | 0.0704 | +| entropy_loss | -6.84 | +| explained_variance | 0.211 | +| learning_rate | 4.56e-05 | +| loss | -0.0307 | +| n_updates | 51948 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000232 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1422 | +| iterations | 9034 | +| time_elapsed | 13003 | +| total_timesteps | 18501632 | +| train/ | | +| approx_kl | 0.01424963 | +| clip_fraction | 0.353 | +| clip_range | 0.0704 | +| entropy_loss | -6.77 | +| explained_variance | -0.0696 | +| learning_rate | 4.56e-05 | +| loss | -0.0345 | +| n_updates | 51952 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000109 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1422 | +| iterations | 9035 | +| time_elapsed | 13005 | +| total_timesteps | 18503680 | +| train/ | | +| approx_kl | 0.012919513 | +| clip_fraction | 0.333 | +| clip_range | 0.0704 | +| entropy_loss | -6 | +| explained_variance | 0.858 | +| learning_rate | 4.56e-05 | +| loss | -0.0273 | +| n_updates | 51956 | +| policy_gradient_loss | -0.0202 | +| value_loss | 5.06e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1422 | +| iterations | 9036 | +| time_elapsed | 13006 | +| total_timesteps | 18505728 | +| train/ | | +| approx_kl | 0.012528532 | +| clip_fraction | 0.315 | +| clip_range | 0.0704 | +| entropy_loss | -5.96 | +| explained_variance | 0.684 | +| learning_rate | 4.56e-05 | +| loss | -0.0219 | +| n_updates | 51960 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.00013 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1422 | +| iterations | 9037 | +| time_elapsed | 13008 | +| total_timesteps | 18507776 | +| train/ | | +| approx_kl | 0.015592698 | +| clip_fraction | 0.4 | +| clip_range | 0.0704 | +| entropy_loss | -6.06 | +| explained_variance | 0.79 | +| learning_rate | 4.56e-05 | +| loss | -0.0364 | +| n_updates | 51964 | +| policy_gradient_loss | -0.0217 | +| value_loss | 3.88e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1422 | +| iterations | 9038 | +| time_elapsed | 13009 | +| total_timesteps | 18509824 | +| train/ | | +| approx_kl | 0.013563599 | +| clip_fraction | 0.349 | +| clip_range | 0.0704 | +| entropy_loss | -6.48 | +| explained_variance | 0.437 | +| learning_rate | 4.56e-05 | +| loss | -0.0298 | +| n_updates | 51968 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000158 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1422 | +| iterations | 9039 | +| time_elapsed | 13011 | +| total_timesteps | 18511872 | +| train/ | | +| approx_kl | 0.012603599 | +| clip_fraction | 0.365 | +| clip_range | 0.0704 | +| entropy_loss | -6.66 | +| explained_variance | 0.376 | +| learning_rate | 4.56e-05 | +| loss | -0.0295 | +| n_updates | 51972 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000128 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1422 | +| iterations | 9040 | +| time_elapsed | 13012 | +| total_timesteps | 18513920 | +| train/ | | +| approx_kl | 0.012647189 | +| clip_fraction | 0.344 | +| clip_range | 0.0704 | +| entropy_loss | -6.87 | +| explained_variance | -0.0461 | +| learning_rate | 4.56e-05 | +| loss | -0.0298 | +| n_updates | 51976 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000223 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1422 | +| iterations | 9041 | +| time_elapsed | 13014 | +| total_timesteps | 18515968 | +| train/ | | +| approx_kl | 0.013706015 | +| clip_fraction | 0.349 | +| clip_range | 0.0704 | +| entropy_loss | -6.59 | +| explained_variance | 0.324 | +| learning_rate | 4.56e-05 | +| loss | -0.0278 | +| n_updates | 51980 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000143 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1422 | +| iterations | 9042 | +| time_elapsed | 13015 | +| total_timesteps | 18518016 | +| train/ | | +| approx_kl | 0.013701286 | +| clip_fraction | 0.349 | +| clip_range | 0.0704 | +| entropy_loss | -6.58 | +| explained_variance | 0.51 | +| learning_rate | 4.56e-05 | +| loss | -0.0287 | +| n_updates | 51984 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000117 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1422 | +| iterations | 9043 | +| time_elapsed | 13016 | +| total_timesteps | 18520064 | +| train/ | | +| approx_kl | 0.014195264 | +| clip_fraction | 0.36 | +| clip_range | 0.0704 | +| entropy_loss | -6.72 | +| explained_variance | 0.471 | +| learning_rate | 4.56e-05 | +| loss | -0.0319 | +| n_updates | 51988 | +| policy_gradient_loss | -0.0204 | +| value_loss | 6.34e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1422 | +| iterations | 9044 | +| time_elapsed | 13018 | +| total_timesteps | 18522112 | +| train/ | | +| approx_kl | 0.011779658 | +| clip_fraction | 0.331 | +| clip_range | 0.0704 | +| entropy_loss | -6.41 | +| explained_variance | 0.294 | +| learning_rate | 4.56e-05 | +| loss | -0.0332 | +| n_updates | 51992 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000225 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1422 | +| iterations | 9045 | +| time_elapsed | 13019 | +| total_timesteps | 18524160 | +| train/ | | +| approx_kl | 0.0127509 | +| clip_fraction | 0.342 | +| clip_range | 0.0704 | +| entropy_loss | -6.47 | +| explained_variance | 0.537 | +| learning_rate | 4.56e-05 | +| loss | -0.0304 | +| n_updates | 51996 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000108 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1422 | +| iterations | 9046 | +| time_elapsed | 13021 | +| total_timesteps | 18526208 | +| train/ | | +| approx_kl | 0.013705812 | +| clip_fraction | 0.322 | +| clip_range | 0.0704 | +| entropy_loss | -6.1 | +| explained_variance | 0.445 | +| learning_rate | 4.56e-05 | +| loss | -0.026 | +| n_updates | 52000 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000316 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1422 | +| iterations | 9047 | +| time_elapsed | 13022 | +| total_timesteps | 18528256 | +| train/ | | +| approx_kl | 0.016537543 | +| clip_fraction | 0.376 | +| clip_range | 0.0704 | +| entropy_loss | -5.92 | +| explained_variance | 0.562 | +| learning_rate | 4.56e-05 | +| loss | -0.039 | +| n_updates | 52004 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000109 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1422 | +| iterations | 9048 | +| time_elapsed | 13024 | +| total_timesteps | 18530304 | +| train/ | | +| approx_kl | 0.01384416 | +| clip_fraction | 0.369 | +| clip_range | 0.0704 | +| entropy_loss | -5.93 | +| explained_variance | 0.78 | +| learning_rate | 4.56e-05 | +| loss | -0.0378 | +| n_updates | 52008 | +| policy_gradient_loss | -0.0226 | +| value_loss | 7.26e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1422 | +| iterations | 9049 | +| time_elapsed | 13025 | +| total_timesteps | 18532352 | +| train/ | | +| approx_kl | 0.015426178 | +| clip_fraction | 0.374 | +| clip_range | 0.0704 | +| entropy_loss | -6.13 | +| explained_variance | 0.267 | +| learning_rate | 4.56e-05 | +| loss | -0.0438 | +| n_updates | 52012 | +| policy_gradient_loss | -0.024 | +| value_loss | 5.32e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1422 | +| iterations | 9050 | +| time_elapsed | 13027 | +| total_timesteps | 18534400 | +| train/ | | +| approx_kl | 0.014559705 | +| clip_fraction | 0.351 | +| clip_range | 0.0704 | +| entropy_loss | -6.7 | +| explained_variance | 0.00399 | +| learning_rate | 4.56e-05 | +| loss | -0.0284 | +| n_updates | 52016 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000125 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1422 | +| iterations | 9051 | +| time_elapsed | 13028 | +| total_timesteps | 18536448 | +| train/ | | +| approx_kl | 0.012201484 | +| clip_fraction | 0.329 | +| clip_range | 0.0704 | +| entropy_loss | -6.58 | +| explained_variance | 0.27 | +| learning_rate | 4.56e-05 | +| loss | -0.0275 | +| n_updates | 52020 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000253 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1422 | +| iterations | 9052 | +| time_elapsed | 13030 | +| total_timesteps | 18538496 | +| train/ | | +| approx_kl | 0.012553338 | +| clip_fraction | 0.375 | +| clip_range | 0.0704 | +| entropy_loss | -6 | +| explained_variance | 0.477 | +| learning_rate | 4.56e-05 | +| loss | -0.0335 | +| n_updates | 52024 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000185 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1422 | +| iterations | 9053 | +| time_elapsed | 13031 | +| total_timesteps | 18540544 | +| train/ | | +| approx_kl | 0.011696875 | +| clip_fraction | 0.372 | +| clip_range | 0.0704 | +| entropy_loss | -6.19 | +| explained_variance | 0.273 | +| learning_rate | 4.56e-05 | +| loss | -0.025 | +| n_updates | 52028 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000375 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1422 | +| iterations | 9054 | +| time_elapsed | 13033 | +| total_timesteps | 18542592 | +| train/ | | +| approx_kl | 0.013870737 | +| clip_fraction | 0.362 | +| clip_range | 0.0704 | +| entropy_loss | -6.26 | +| explained_variance | 0.412 | +| learning_rate | 4.56e-05 | +| loss | -0.032 | +| n_updates | 52032 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000203 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1422 | +| iterations | 9055 | +| time_elapsed | 13034 | +| total_timesteps | 18544640 | +| train/ | | +| approx_kl | 0.013129826 | +| clip_fraction | 0.395 | +| clip_range | 0.0704 | +| entropy_loss | -6.46 | +| explained_variance | 0.442 | +| learning_rate | 4.56e-05 | +| loss | -0.0404 | +| n_updates | 52036 | +| policy_gradient_loss | -0.026 | +| value_loss | 0.000105 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 1422 | +| iterations | 9056 | +| time_elapsed | 13035 | +| total_timesteps | 18546688 | +| train/ | | +| approx_kl | 0.010217971 | +| clip_fraction | 0.335 | +| clip_range | 0.0704 | +| entropy_loss | -6.63 | +| explained_variance | 0.318 | +| learning_rate | 4.56e-05 | +| loss | -0.0286 | +| n_updates | 52040 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.00023 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.304 | +| time/ | | +| fps | 1422 | +| iterations | 9057 | +| time_elapsed | 13037 | +| total_timesteps | 18548736 | +| train/ | | +| approx_kl | 0.014571525 | +| clip_fraction | 0.361 | +| clip_range | 0.0704 | +| entropy_loss | -6.16 | +| explained_variance | 0.557 | +| learning_rate | 4.56e-05 | +| loss | -0.0354 | +| n_updates | 52044 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000147 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1422 | +| iterations | 9058 | +| time_elapsed | 13038 | +| total_timesteps | 18550784 | +| train/ | | +| approx_kl | 0.014183257 | +| clip_fraction | 0.376 | +| clip_range | 0.0704 | +| entropy_loss | -6.21 | +| explained_variance | 0.281 | +| learning_rate | 4.56e-05 | +| loss | -0.031 | +| n_updates | 52048 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000101 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1422 | +| iterations | 9059 | +| time_elapsed | 13040 | +| total_timesteps | 18552832 | +| train/ | | +| approx_kl | 0.013687633 | +| clip_fraction | 0.34 | +| clip_range | 0.0704 | +| entropy_loss | -6.43 | +| explained_variance | 0.362 | +| learning_rate | 4.56e-05 | +| loss | -0.0197 | +| n_updates | 52052 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000251 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1422 | +| iterations | 9060 | +| time_elapsed | 13041 | +| total_timesteps | 18554880 | +| train/ | | +| approx_kl | 0.012023607 | +| clip_fraction | 0.319 | +| clip_range | 0.0704 | +| entropy_loss | -6.49 | +| explained_variance | 0.196 | +| learning_rate | 4.56e-05 | +| loss | -0.0288 | +| n_updates | 52056 | +| policy_gradient_loss | -0.0139 | +| value_loss | 0.000244 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1422 | +| iterations | 9061 | +| time_elapsed | 13042 | +| total_timesteps | 18556928 | +| train/ | | +| approx_kl | 0.014291575 | +| clip_fraction | 0.358 | +| clip_range | 0.0704 | +| entropy_loss | -6.51 | +| explained_variance | 0.256 | +| learning_rate | 4.56e-05 | +| loss | -0.0337 | +| n_updates | 52060 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000124 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1422 | +| iterations | 9062 | +| time_elapsed | 13044 | +| total_timesteps | 18558976 | +| train/ | | +| approx_kl | 0.0122802 | +| clip_fraction | 0.352 | +| clip_range | 0.0704 | +| entropy_loss | -6.25 | +| explained_variance | 0.275 | +| learning_rate | 4.56e-05 | +| loss | -0.0326 | +| n_updates | 52064 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000292 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.304 | +| time/ | | +| fps | 1422 | +| iterations | 9063 | +| time_elapsed | 13045 | +| total_timesteps | 18561024 | +| train/ | | +| approx_kl | 0.013773575 | +| clip_fraction | 0.35 | +| clip_range | 0.0704 | +| entropy_loss | -6.46 | +| explained_variance | 0.257 | +| learning_rate | 4.56e-05 | +| loss | -0.0364 | +| n_updates | 52068 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000151 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1422 | +| iterations | 9064 | +| time_elapsed | 13047 | +| total_timesteps | 18563072 | +| train/ | | +| approx_kl | 0.014706029 | +| clip_fraction | 0.375 | +| clip_range | 0.0704 | +| entropy_loss | -6.54 | +| explained_variance | 0.554 | +| learning_rate | 4.56e-05 | +| loss | -0.042 | +| n_updates | 52072 | +| policy_gradient_loss | -0.0252 | +| value_loss | 5.77e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1422 | +| iterations | 9065 | +| time_elapsed | 13048 | +| total_timesteps | 18565120 | +| train/ | | +| approx_kl | 0.017577803 | +| clip_fraction | 0.334 | +| clip_range | 0.0704 | +| entropy_loss | -5.67 | +| explained_variance | 0.602 | +| learning_rate | 4.56e-05 | +| loss | -0.0309 | +| n_updates | 52076 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000192 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1422 | +| iterations | 9066 | +| time_elapsed | 13050 | +| total_timesteps | 18567168 | +| train/ | | +| approx_kl | 0.013487844 | +| clip_fraction | 0.334 | +| clip_range | 0.0704 | +| entropy_loss | -6.5 | +| explained_variance | -0.0973 | +| learning_rate | 4.56e-05 | +| loss | -0.0308 | +| n_updates | 52080 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.302 | +| time/ | | +| fps | 1422 | +| iterations | 9067 | +| time_elapsed | 13051 | +| total_timesteps | 18569216 | +| train/ | | +| approx_kl | 0.015348408 | +| clip_fraction | 0.344 | +| clip_range | 0.0704 | +| entropy_loss | -6.49 | +| explained_variance | 0.197 | +| learning_rate | 4.56e-05 | +| loss | -0.0347 | +| n_updates | 52084 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000135 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.304 | +| time/ | | +| fps | 1422 | +| iterations | 9068 | +| time_elapsed | 13053 | +| total_timesteps | 18571264 | +| train/ | | +| approx_kl | 0.0151901785 | +| clip_fraction | 0.339 | +| clip_range | 0.0704 | +| entropy_loss | -6.35 | +| explained_variance | 0.318 | +| learning_rate | 4.56e-05 | +| loss | -0.0331 | +| n_updates | 52088 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.00017 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1422 | +| iterations | 9069 | +| time_elapsed | 13054 | +| total_timesteps | 18573312 | +| train/ | | +| approx_kl | 0.012271478 | +| clip_fraction | 0.333 | +| clip_range | 0.0704 | +| entropy_loss | -6.47 | +| explained_variance | 0.372 | +| learning_rate | 4.56e-05 | +| loss | -0.0276 | +| n_updates | 52092 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000201 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1422 | +| iterations | 9070 | +| time_elapsed | 13056 | +| total_timesteps | 18575360 | +| train/ | | +| approx_kl | 0.013389577 | +| clip_fraction | 0.335 | +| clip_range | 0.0704 | +| entropy_loss | -6.23 | +| explained_variance | 0.389 | +| learning_rate | 4.56e-05 | +| loss | -0.0255 | +| n_updates | 52096 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000317 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1422 | +| iterations | 9071 | +| time_elapsed | 13057 | +| total_timesteps | 18577408 | +| train/ | | +| approx_kl | 0.013609735 | +| clip_fraction | 0.358 | +| clip_range | 0.0704 | +| entropy_loss | -5.98 | +| explained_variance | 0.656 | +| learning_rate | 4.56e-05 | +| loss | -0.0298 | +| n_updates | 52100 | +| policy_gradient_loss | -0.0203 | +| value_loss | 8.22e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1422 | +| iterations | 9072 | +| time_elapsed | 13059 | +| total_timesteps | 18579456 | +| train/ | | +| approx_kl | 0.015257228 | +| clip_fraction | 0.38 | +| clip_range | 0.0704 | +| entropy_loss | -6.69 | +| explained_variance | -0.109 | +| learning_rate | 4.56e-05 | +| loss | -0.0394 | +| n_updates | 52104 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000107 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1422 | +| iterations | 9073 | +| time_elapsed | 13060 | +| total_timesteps | 18581504 | +| train/ | | +| approx_kl | 0.012866629 | +| clip_fraction | 0.335 | +| clip_range | 0.0704 | +| entropy_loss | -6.49 | +| explained_variance | 0.62 | +| learning_rate | 4.56e-05 | +| loss | -0.0269 | +| n_updates | 52108 | +| policy_gradient_loss | -0.0185 | +| value_loss | 9.08e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1422 | +| iterations | 9074 | +| time_elapsed | 13061 | +| total_timesteps | 18583552 | +| train/ | | +| approx_kl | 0.012730677 | +| clip_fraction | 0.359 | +| clip_range | 0.0704 | +| entropy_loss | -6.74 | +| explained_variance | -0.0755 | +| learning_rate | 4.56e-05 | +| loss | -0.0288 | +| n_updates | 52112 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000122 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1422 | +| iterations | 9075 | +| time_elapsed | 13063 | +| total_timesteps | 18585600 | +| train/ | | +| approx_kl | 0.010429322 | +| clip_fraction | 0.329 | +| clip_range | 0.0704 | +| entropy_loss | -6.48 | +| explained_variance | 0.196 | +| learning_rate | 4.56e-05 | +| loss | -0.0243 | +| n_updates | 52116 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000253 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1422 | +| iterations | 9076 | +| time_elapsed | 13064 | +| total_timesteps | 18587648 | +| train/ | | +| approx_kl | 0.020996395 | +| clip_fraction | 0.37 | +| clip_range | 0.0704 | +| entropy_loss | -6.06 | +| explained_variance | 0.387 | +| learning_rate | 4.56e-05 | +| loss | -0.0219 | +| n_updates | 52120 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000213 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1422 | +| iterations | 9077 | +| time_elapsed | 13066 | +| total_timesteps | 18589696 | +| train/ | | +| approx_kl | 0.01184375 | +| clip_fraction | 0.338 | +| clip_range | 0.0704 | +| entropy_loss | -5.96 | +| explained_variance | 0.553 | +| learning_rate | 4.56e-05 | +| loss | -0.0318 | +| n_updates | 52124 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000222 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.315 | +| time/ | | +| fps | 1422 | +| iterations | 9078 | +| time_elapsed | 13067 | +| total_timesteps | 18591744 | +| train/ | | +| approx_kl | 0.012770483 | +| clip_fraction | 0.347 | +| clip_range | 0.0704 | +| entropy_loss | -6.11 | +| explained_variance | 0.489 | +| learning_rate | 4.56e-05 | +| loss | -0.0259 | +| n_updates | 52128 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.00011 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1422 | +| iterations | 9079 | +| time_elapsed | 13069 | +| total_timesteps | 18593792 | +| train/ | | +| approx_kl | 0.010734446 | +| clip_fraction | 0.327 | +| clip_range | 0.0704 | +| entropy_loss | -6.67 | +| explained_variance | 0.366 | +| learning_rate | 4.56e-05 | +| loss | -0.0334 | +| n_updates | 52132 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000132 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1422 | +| iterations | 9080 | +| time_elapsed | 13070 | +| total_timesteps | 18595840 | +| train/ | | +| approx_kl | 0.014545185 | +| clip_fraction | 0.338 | +| clip_range | 0.0704 | +| entropy_loss | -6.35 | +| explained_variance | 0.294 | +| learning_rate | 4.56e-05 | +| loss | -0.0279 | +| n_updates | 52136 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.00024 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1422 | +| iterations | 9081 | +| time_elapsed | 13072 | +| total_timesteps | 18597888 | +| train/ | | +| approx_kl | 0.011979769 | +| clip_fraction | 0.332 | +| clip_range | 0.0704 | +| entropy_loss | -5.76 | +| explained_variance | 0.657 | +| learning_rate | 4.56e-05 | +| loss | -0.0303 | +| n_updates | 52140 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000137 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1422 | +| iterations | 9082 | +| time_elapsed | 13073 | +| total_timesteps | 18599936 | +| train/ | | +| approx_kl | 0.011705907 | +| clip_fraction | 0.354 | +| clip_range | 0.0704 | +| entropy_loss | -6.68 | +| explained_variance | 0.145 | +| learning_rate | 4.56e-05 | +| loss | -0.029 | +| n_updates | 52144 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000209 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1422 | +| iterations | 9083 | +| time_elapsed | 13074 | +| total_timesteps | 18601984 | +| train/ | | +| approx_kl | 0.014926612 | +| clip_fraction | 0.339 | +| clip_range | 0.0704 | +| entropy_loss | -6.52 | +| explained_variance | 0.063 | +| learning_rate | 4.56e-05 | +| loss | -0.0274 | +| n_updates | 52148 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000425 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1422 | +| iterations | 9084 | +| time_elapsed | 13076 | +| total_timesteps | 18604032 | +| train/ | | +| approx_kl | 0.0148263415 | +| clip_fraction | 0.37 | +| clip_range | 0.0703 | +| entropy_loss | -5.83 | +| explained_variance | 0.622 | +| learning_rate | 4.56e-05 | +| loss | -0.032 | +| n_updates | 52152 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000166 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1422 | +| iterations | 9085 | +| time_elapsed | 13077 | +| total_timesteps | 18606080 | +| train/ | | +| approx_kl | 0.015501515 | +| clip_fraction | 0.357 | +| clip_range | 0.0703 | +| entropy_loss | -6.09 | +| explained_variance | 0.204 | +| learning_rate | 4.56e-05 | +| loss | -0.0275 | +| n_updates | 52156 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000336 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1422 | +| iterations | 9086 | +| time_elapsed | 13079 | +| total_timesteps | 18608128 | +| train/ | | +| approx_kl | 0.011708433 | +| clip_fraction | 0.354 | +| clip_range | 0.0703 | +| entropy_loss | -6.3 | +| explained_variance | 0.331 | +| learning_rate | 4.56e-05 | +| loss | -0.0285 | +| n_updates | 52160 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000226 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1422 | +| iterations | 9087 | +| time_elapsed | 13080 | +| total_timesteps | 18610176 | +| train/ | | +| approx_kl | 0.015128233 | +| clip_fraction | 0.39 | +| clip_range | 0.0703 | +| entropy_loss | -6.66 | +| explained_variance | 0.343 | +| learning_rate | 4.56e-05 | +| loss | -0.0312 | +| n_updates | 52164 | +| policy_gradient_loss | -0.0223 | +| value_loss | 0.000112 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1422 | +| iterations | 9088 | +| time_elapsed | 13081 | +| total_timesteps | 18612224 | +| train/ | | +| approx_kl | 0.016668497 | +| clip_fraction | 0.369 | +| clip_range | 0.0703 | +| entropy_loss | -6.34 | +| explained_variance | 0.34 | +| learning_rate | 4.56e-05 | +| loss | -0.0353 | +| n_updates | 52168 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1422 | +| iterations | 9089 | +| time_elapsed | 13083 | +| total_timesteps | 18614272 | +| train/ | | +| approx_kl | 0.014766177 | +| clip_fraction | 0.342 | +| clip_range | 0.0703 | +| entropy_loss | -6.59 | +| explained_variance | 0.297 | +| learning_rate | 4.56e-05 | +| loss | -0.0305 | +| n_updates | 52172 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000134 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1422 | +| iterations | 9090 | +| time_elapsed | 13084 | +| total_timesteps | 18616320 | +| train/ | | +| approx_kl | 0.013642721 | +| clip_fraction | 0.363 | +| clip_range | 0.0703 | +| entropy_loss | -6.7 | +| explained_variance | 0.435 | +| learning_rate | 4.56e-05 | +| loss | -0.0264 | +| n_updates | 52176 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000102 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1422 | +| iterations | 9091 | +| time_elapsed | 13086 | +| total_timesteps | 18618368 | +| train/ | | +| approx_kl | 0.011206202 | +| clip_fraction | 0.314 | +| clip_range | 0.0703 | +| entropy_loss | -6.59 | +| explained_variance | 0.138 | +| learning_rate | 4.56e-05 | +| loss | -0.0265 | +| n_updates | 52180 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000324 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1422 | +| iterations | 9092 | +| time_elapsed | 13087 | +| total_timesteps | 18620416 | +| train/ | | +| approx_kl | 0.014775831 | +| clip_fraction | 0.354 | +| clip_range | 0.0703 | +| entropy_loss | -6.26 | +| explained_variance | 0.465 | +| learning_rate | 4.56e-05 | +| loss | -0.0292 | +| n_updates | 52184 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000141 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1422 | +| iterations | 9093 | +| time_elapsed | 13089 | +| total_timesteps | 18622464 | +| train/ | | +| approx_kl | 0.0120940935 | +| clip_fraction | 0.375 | +| clip_range | 0.0703 | +| entropy_loss | -6.19 | +| explained_variance | 0.451 | +| learning_rate | 4.56e-05 | +| loss | -0.0324 | +| n_updates | 52188 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000126 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1422 | +| iterations | 9094 | +| time_elapsed | 13090 | +| total_timesteps | 18624512 | +| train/ | | +| approx_kl | 0.014305845 | +| clip_fraction | 0.355 | +| clip_range | 0.0703 | +| entropy_loss | -6.06 | +| explained_variance | 0.493 | +| learning_rate | 4.56e-05 | +| loss | -0.0268 | +| n_updates | 52192 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000197 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1422 | +| iterations | 9095 | +| time_elapsed | 13091 | +| total_timesteps | 18626560 | +| train/ | | +| approx_kl | 0.013828318 | +| clip_fraction | 0.352 | +| clip_range | 0.0703 | +| entropy_loss | -6.31 | +| explained_variance | 0.51 | +| learning_rate | 4.56e-05 | +| loss | -0.0311 | +| n_updates | 52196 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1422 | +| iterations | 9096 | +| time_elapsed | 13093 | +| total_timesteps | 18628608 | +| train/ | | +| approx_kl | 0.012874281 | +| clip_fraction | 0.358 | +| clip_range | 0.0703 | +| entropy_loss | -6.53 | +| explained_variance | 0.0787 | +| learning_rate | 4.56e-05 | +| loss | -0.0354 | +| n_updates | 52200 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000119 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1422 | +| iterations | 9097 | +| time_elapsed | 13094 | +| total_timesteps | 18630656 | +| train/ | | +| approx_kl | 0.012048854 | +| clip_fraction | 0.347 | +| clip_range | 0.0703 | +| entropy_loss | -6.19 | +| explained_variance | 0.359 | +| learning_rate | 4.56e-05 | +| loss | -0.0224 | +| n_updates | 52204 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000366 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1422 | +| iterations | 9098 | +| time_elapsed | 13096 | +| total_timesteps | 18632704 | +| train/ | | +| approx_kl | 0.016914247 | +| clip_fraction | 0.333 | +| clip_range | 0.0703 | +| entropy_loss | -6.08 | +| explained_variance | 0.519 | +| learning_rate | 4.56e-05 | +| loss | -0.0286 | +| n_updates | 52208 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000188 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1422 | +| iterations | 9099 | +| time_elapsed | 13097 | +| total_timesteps | 18634752 | +| train/ | | +| approx_kl | 0.011196503 | +| clip_fraction | 0.338 | +| clip_range | 0.0703 | +| entropy_loss | -6.45 | +| explained_variance | 0.177 | +| learning_rate | 4.56e-05 | +| loss | -0.0301 | +| n_updates | 52212 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000132 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1422 | +| iterations | 9100 | +| time_elapsed | 13099 | +| total_timesteps | 18636800 | +| train/ | | +| approx_kl | 0.012614412 | +| clip_fraction | 0.335 | +| clip_range | 0.0703 | +| entropy_loss | -6.42 | +| explained_variance | 0.233 | +| learning_rate | 4.56e-05 | +| loss | -0.0276 | +| n_updates | 52216 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000349 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1422 | +| iterations | 9101 | +| time_elapsed | 13100 | +| total_timesteps | 18638848 | +| train/ | | +| approx_kl | 0.015579872 | +| clip_fraction | 0.361 | +| clip_range | 0.0703 | +| entropy_loss | -6.37 | +| explained_variance | -0.224 | +| learning_rate | 4.56e-05 | +| loss | -0.0336 | +| n_updates | 52220 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000229 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1422 | +| iterations | 9102 | +| time_elapsed | 13101 | +| total_timesteps | 18640896 | +| train/ | | +| approx_kl | 0.013808617 | +| clip_fraction | 0.344 | +| clip_range | 0.0703 | +| entropy_loss | -6.32 | +| explained_variance | 0.254 | +| learning_rate | 4.56e-05 | +| loss | -0.0244 | +| n_updates | 52224 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000507 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1422 | +| iterations | 9103 | +| time_elapsed | 13103 | +| total_timesteps | 18642944 | +| train/ | | +| approx_kl | 0.016163621 | +| clip_fraction | 0.384 | +| clip_range | 0.0703 | +| entropy_loss | -5.88 | +| explained_variance | 0.286 | +| learning_rate | 4.56e-05 | +| loss | -0.0343 | +| n_updates | 52228 | +| policy_gradient_loss | -0.0245 | +| value_loss | 0.000151 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1422 | +| iterations | 9104 | +| time_elapsed | 13104 | +| total_timesteps | 18644992 | +| train/ | | +| approx_kl | 0.01763348 | +| clip_fraction | 0.375 | +| clip_range | 0.0703 | +| entropy_loss | -6.4 | +| explained_variance | -0.0561 | +| learning_rate | 4.56e-05 | +| loss | -0.0368 | +| n_updates | 52232 | +| policy_gradient_loss | -0.0225 | +| value_loss | 0.000117 | +---------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1422 | +| iterations | 9105 | +| time_elapsed | 13106 | +| total_timesteps | 18647040 | +| train/ | | +| approx_kl | 0.0145764 | +| clip_fraction | 0.366 | +| clip_range | 0.0703 | +| entropy_loss | -6.12 | +| explained_variance | 0.523 | +| learning_rate | 4.56e-05 | +| loss | -0.0392 | +| n_updates | 52236 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000183 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1422 | +| iterations | 9106 | +| time_elapsed | 13107 | +| total_timesteps | 18649088 | +| train/ | | +| approx_kl | 0.014730709 | +| clip_fraction | 0.357 | +| clip_range | 0.0703 | +| entropy_loss | -6.22 | +| explained_variance | 0.252 | +| learning_rate | 4.56e-05 | +| loss | -0.0316 | +| n_updates | 52240 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000218 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1422 | +| iterations | 9107 | +| time_elapsed | 13109 | +| total_timesteps | 18651136 | +| train/ | | +| approx_kl | 0.014705231 | +| clip_fraction | 0.369 | +| clip_range | 0.0703 | +| entropy_loss | -6.43 | +| explained_variance | 0.147 | +| learning_rate | 4.56e-05 | +| loss | -0.0263 | +| n_updates | 52244 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000177 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1422 | +| iterations | 9108 | +| time_elapsed | 13110 | +| total_timesteps | 18653184 | +| train/ | | +| approx_kl | 0.01220453 | +| clip_fraction | 0.348 | +| clip_range | 0.0703 | +| entropy_loss | -6.76 | +| explained_variance | 0.0743 | +| learning_rate | 4.56e-05 | +| loss | -0.0304 | +| n_updates | 52248 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000241 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1422 | +| iterations | 9109 | +| time_elapsed | 13111 | +| total_timesteps | 18655232 | +| train/ | | +| approx_kl | 0.013137108 | +| clip_fraction | 0.374 | +| clip_range | 0.0703 | +| entropy_loss | -6.77 | +| explained_variance | 0.149 | +| learning_rate | 4.56e-05 | +| loss | -0.0361 | +| n_updates | 52252 | +| policy_gradient_loss | -0.0235 | +| value_loss | 0.000117 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1422 | +| iterations | 9110 | +| time_elapsed | 13113 | +| total_timesteps | 18657280 | +| train/ | | +| approx_kl | 0.013587028 | +| clip_fraction | 0.381 | +| clip_range | 0.0703 | +| entropy_loss | -6.89 | +| explained_variance | 0.477 | +| learning_rate | 4.56e-05 | +| loss | -0.0332 | +| n_updates | 52256 | +| policy_gradient_loss | -0.0221 | +| value_loss | 9.63e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1422 | +| iterations | 9111 | +| time_elapsed | 13114 | +| total_timesteps | 18659328 | +| train/ | | +| approx_kl | 0.012407865 | +| clip_fraction | 0.329 | +| clip_range | 0.0703 | +| entropy_loss | -6.18 | +| explained_variance | 0.483 | +| learning_rate | 4.56e-05 | +| loss | -0.026 | +| n_updates | 52260 | +| policy_gradient_loss | -0.0147 | +| value_loss | 0.00025 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1422 | +| iterations | 9112 | +| time_elapsed | 13116 | +| total_timesteps | 18661376 | +| train/ | | +| approx_kl | 0.014011054 | +| clip_fraction | 0.347 | +| clip_range | 0.0703 | +| entropy_loss | -6 | +| explained_variance | 0.579 | +| learning_rate | 4.56e-05 | +| loss | -0.0337 | +| n_updates | 52264 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000103 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1422 | +| iterations | 9113 | +| time_elapsed | 13117 | +| total_timesteps | 18663424 | +| train/ | | +| approx_kl | 0.015102018 | +| clip_fraction | 0.351 | +| clip_range | 0.0703 | +| entropy_loss | -6.45 | +| explained_variance | 0.349 | +| learning_rate | 4.56e-05 | +| loss | -0.0336 | +| n_updates | 52268 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000123 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1422 | +| iterations | 9114 | +| time_elapsed | 13118 | +| total_timesteps | 18665472 | +| train/ | | +| approx_kl | 0.0147915585 | +| clip_fraction | 0.317 | +| clip_range | 0.0703 | +| entropy_loss | -6.3 | +| explained_variance | 0.565 | +| learning_rate | 4.56e-05 | +| loss | -0.0275 | +| n_updates | 52272 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000176 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1422 | +| iterations | 9115 | +| time_elapsed | 13120 | +| total_timesteps | 18667520 | +| train/ | | +| approx_kl | 0.015979508 | +| clip_fraction | 0.349 | +| clip_range | 0.0703 | +| entropy_loss | -6.15 | +| explained_variance | 0.501 | +| learning_rate | 4.56e-05 | +| loss | -0.0374 | +| n_updates | 52276 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000139 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1422 | +| iterations | 9116 | +| time_elapsed | 13121 | +| total_timesteps | 18669568 | +| train/ | | +| approx_kl | 0.0136934 | +| clip_fraction | 0.359 | +| clip_range | 0.0703 | +| entropy_loss | -6.68 | +| explained_variance | 0.335 | +| learning_rate | 4.56e-05 | +| loss | -0.0314 | +| n_updates | 52280 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000147 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1422 | +| iterations | 9117 | +| time_elapsed | 13123 | +| total_timesteps | 18671616 | +| train/ | | +| approx_kl | 0.011860972 | +| clip_fraction | 0.341 | +| clip_range | 0.0703 | +| entropy_loss | -6.45 | +| explained_variance | 0.606 | +| learning_rate | 4.56e-05 | +| loss | -0.0347 | +| n_updates | 52284 | +| policy_gradient_loss | -0.0196 | +| value_loss | 9e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1422 | +| iterations | 9118 | +| time_elapsed | 13124 | +| total_timesteps | 18673664 | +| train/ | | +| approx_kl | 0.013126072 | +| clip_fraction | 0.344 | +| clip_range | 0.0703 | +| entropy_loss | -6.22 | +| explained_variance | 0.593 | +| learning_rate | 4.56e-05 | +| loss | -0.03 | +| n_updates | 52288 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000149 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1422 | +| iterations | 9119 | +| time_elapsed | 13126 | +| total_timesteps | 18675712 | +| train/ | | +| approx_kl | 0.013786932 | +| clip_fraction | 0.335 | +| clip_range | 0.0703 | +| entropy_loss | -6.38 | +| explained_variance | 0.306 | +| learning_rate | 4.56e-05 | +| loss | -0.0267 | +| n_updates | 52292 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.00017 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1422 | +| iterations | 9120 | +| time_elapsed | 13127 | +| total_timesteps | 18677760 | +| train/ | | +| approx_kl | 0.013658334 | +| clip_fraction | 0.349 | +| clip_range | 0.0703 | +| entropy_loss | -6.62 | +| explained_variance | -0.149 | +| learning_rate | 4.56e-05 | +| loss | -0.0269 | +| n_updates | 52296 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000121 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1422 | +| iterations | 9121 | +| time_elapsed | 13129 | +| total_timesteps | 18679808 | +| train/ | | +| approx_kl | 0.013923818 | +| clip_fraction | 0.345 | +| clip_range | 0.0703 | +| entropy_loss | -6.5 | +| explained_variance | 0.404 | +| learning_rate | 4.56e-05 | +| loss | -0.0338 | +| n_updates | 52300 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000131 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1422 | +| iterations | 9122 | +| time_elapsed | 13130 | +| total_timesteps | 18681856 | +| train/ | | +| approx_kl | 0.014673693 | +| clip_fraction | 0.375 | +| clip_range | 0.0703 | +| entropy_loss | -6.48 | +| explained_variance | -0.0105 | +| learning_rate | 4.56e-05 | +| loss | -0.031 | +| n_updates | 52304 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000169 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1422 | +| iterations | 9123 | +| time_elapsed | 13132 | +| total_timesteps | 18683904 | +| train/ | | +| approx_kl | 0.015359647 | +| clip_fraction | 0.348 | +| clip_range | 0.0703 | +| entropy_loss | -6.72 | +| explained_variance | 0.252 | +| learning_rate | 4.56e-05 | +| loss | -0.0309 | +| n_updates | 52308 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000136 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1422 | +| iterations | 9124 | +| time_elapsed | 13133 | +| total_timesteps | 18685952 | +| train/ | | +| approx_kl | 0.01398127 | +| clip_fraction | 0.328 | +| clip_range | 0.0703 | +| entropy_loss | -6.75 | +| explained_variance | -0.171 | +| learning_rate | 4.56e-05 | +| loss | -0.029 | +| n_updates | 52312 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000157 | +---------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1422 | +| iterations | 9125 | +| time_elapsed | 13134 | +| total_timesteps | 18688000 | +| train/ | | +| approx_kl | 0.0160075 | +| clip_fraction | 0.357 | +| clip_range | 0.0703 | +| entropy_loss | -5.91 | +| explained_variance | 0.588 | +| learning_rate | 4.56e-05 | +| loss | -0.0286 | +| n_updates | 52316 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000124 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1422 | +| iterations | 9126 | +| time_elapsed | 13136 | +| total_timesteps | 18690048 | +| train/ | | +| approx_kl | 0.015621328 | +| clip_fraction | 0.356 | +| clip_range | 0.0703 | +| entropy_loss | -6.12 | +| explained_variance | 0.371 | +| learning_rate | 4.56e-05 | +| loss | -0.0354 | +| n_updates | 52320 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000242 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1422 | +| iterations | 9127 | +| time_elapsed | 13137 | +| total_timesteps | 18692096 | +| train/ | | +| approx_kl | 0.012747384 | +| clip_fraction | 0.355 | +| clip_range | 0.0703 | +| entropy_loss | -6.31 | +| explained_variance | 0.255 | +| learning_rate | 4.56e-05 | +| loss | -0.0305 | +| n_updates | 52324 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000156 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1422 | +| iterations | 9128 | +| time_elapsed | 13139 | +| total_timesteps | 18694144 | +| train/ | | +| approx_kl | 0.0145957675 | +| clip_fraction | 0.345 | +| clip_range | 0.0703 | +| entropy_loss | -6.58 | +| explained_variance | -0.0309 | +| learning_rate | 4.56e-05 | +| loss | -0.0286 | +| n_updates | 52328 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.0002 | +------------------------------------------ +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1422 | +| iterations | 9129 | +| time_elapsed | 13140 | +| total_timesteps | 18696192 | +| train/ | | +| approx_kl | 0.0148034 | +| clip_fraction | 0.361 | +| clip_range | 0.0703 | +| entropy_loss | -6.59 | +| explained_variance | 0.25 | +| learning_rate | 4.56e-05 | +| loss | -0.0331 | +| n_updates | 52332 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000152 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1422 | +| iterations | 9130 | +| time_elapsed | 13141 | +| total_timesteps | 18698240 | +| train/ | | +| approx_kl | 0.015402047 | +| clip_fraction | 0.353 | +| clip_range | 0.0703 | +| entropy_loss | -6.29 | +| explained_variance | 0.553 | +| learning_rate | 4.56e-05 | +| loss | -0.0343 | +| n_updates | 52336 | +| policy_gradient_loss | -0.0194 | +| value_loss | 9.27e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1422 | +| iterations | 9131 | +| time_elapsed | 13143 | +| total_timesteps | 18700288 | +| train/ | | +| approx_kl | 0.012614773 | +| clip_fraction | 0.295 | +| clip_range | 0.0703 | +| entropy_loss | -6.12 | +| explained_variance | 0.362 | +| learning_rate | 4.56e-05 | +| loss | -0.0217 | +| n_updates | 52340 | +| policy_gradient_loss | -0.0136 | +| value_loss | 0.00038 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1422 | +| iterations | 9132 | +| time_elapsed | 13144 | +| total_timesteps | 18702336 | +| train/ | | +| approx_kl | 0.012640549 | +| clip_fraction | 0.358 | +| clip_range | 0.0703 | +| entropy_loss | -6.56 | +| explained_variance | 0.246 | +| learning_rate | 4.56e-05 | +| loss | -0.0321 | +| n_updates | 52344 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000181 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1422 | +| iterations | 9133 | +| time_elapsed | 13146 | +| total_timesteps | 18704384 | +| train/ | | +| approx_kl | 0.014433967 | +| clip_fraction | 0.352 | +| clip_range | 0.0703 | +| entropy_loss | -6.4 | +| explained_variance | 0.412 | +| learning_rate | 4.56e-05 | +| loss | -0.0299 | +| n_updates | 52348 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000192 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1422 | +| iterations | 9134 | +| time_elapsed | 13147 | +| total_timesteps | 18706432 | +| train/ | | +| approx_kl | 0.015041349 | +| clip_fraction | 0.385 | +| clip_range | 0.0703 | +| entropy_loss | -6.6 | +| explained_variance | 0.512 | +| learning_rate | 4.56e-05 | +| loss | -0.0392 | +| n_updates | 52352 | +| policy_gradient_loss | -0.0244 | +| value_loss | 5.46e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1422 | +| iterations | 9135 | +| time_elapsed | 13149 | +| total_timesteps | 18708480 | +| train/ | | +| approx_kl | 0.013940064 | +| clip_fraction | 0.326 | +| clip_range | 0.0703 | +| entropy_loss | -6.56 | +| explained_variance | 0.198 | +| learning_rate | 4.56e-05 | +| loss | -0.0317 | +| n_updates | 52356 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000303 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1422 | +| iterations | 9136 | +| time_elapsed | 13150 | +| total_timesteps | 18710528 | +| train/ | | +| approx_kl | 0.015959376 | +| clip_fraction | 0.365 | +| clip_range | 0.0703 | +| entropy_loss | -6.74 | +| explained_variance | -0.154 | +| learning_rate | 4.56e-05 | +| loss | -0.0321 | +| n_updates | 52360 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000149 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1422 | +| iterations | 9137 | +| time_elapsed | 13151 | +| total_timesteps | 18712576 | +| train/ | | +| approx_kl | 0.015191875 | +| clip_fraction | 0.363 | +| clip_range | 0.0703 | +| entropy_loss | -6.25 | +| explained_variance | 0.608 | +| learning_rate | 4.56e-05 | +| loss | -0.0349 | +| n_updates | 52364 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000126 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1422 | +| iterations | 9138 | +| time_elapsed | 13153 | +| total_timesteps | 18714624 | +| train/ | | +| approx_kl | 0.015401205 | +| clip_fraction | 0.362 | +| clip_range | 0.0703 | +| entropy_loss | -6.15 | +| explained_variance | 0.571 | +| learning_rate | 4.56e-05 | +| loss | -0.0314 | +| n_updates | 52368 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000152 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1422 | +| iterations | 9139 | +| time_elapsed | 13154 | +| total_timesteps | 18716672 | +| train/ | | +| approx_kl | 0.013636334 | +| clip_fraction | 0.357 | +| clip_range | 0.0703 | +| entropy_loss | -6.56 | +| explained_variance | 0.527 | +| learning_rate | 4.56e-05 | +| loss | -0.0326 | +| n_updates | 52372 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000118 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1422 | +| iterations | 9140 | +| time_elapsed | 13156 | +| total_timesteps | 18718720 | +| train/ | | +| approx_kl | 0.009902893 | +| clip_fraction | 0.328 | +| clip_range | 0.0703 | +| entropy_loss | -7 | +| explained_variance | 0.101 | +| learning_rate | 4.56e-05 | +| loss | -0.031 | +| n_updates | 52376 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000164 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1422 | +| iterations | 9141 | +| time_elapsed | 13157 | +| total_timesteps | 18720768 | +| train/ | | +| approx_kl | 0.0108552 | +| clip_fraction | 0.344 | +| clip_range | 0.0703 | +| entropy_loss | -6.86 | +| explained_variance | 0.363 | +| learning_rate | 4.56e-05 | +| loss | -0.0326 | +| n_updates | 52380 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000147 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1422 | +| iterations | 9142 | +| time_elapsed | 13159 | +| total_timesteps | 18722816 | +| train/ | | +| approx_kl | 0.012566634 | +| clip_fraction | 0.351 | +| clip_range | 0.0703 | +| entropy_loss | -6.46 | +| explained_variance | 0.278 | +| learning_rate | 4.56e-05 | +| loss | -0.0204 | +| n_updates | 52384 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000328 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1422 | +| iterations | 9143 | +| time_elapsed | 13160 | +| total_timesteps | 18724864 | +| train/ | | +| approx_kl | 0.014956377 | +| clip_fraction | 0.347 | +| clip_range | 0.0703 | +| entropy_loss | -6.22 | +| explained_variance | 0.433 | +| learning_rate | 4.56e-05 | +| loss | -0.0292 | +| n_updates | 52388 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000208 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1422 | +| iterations | 9144 | +| time_elapsed | 13162 | +| total_timesteps | 18726912 | +| train/ | | +| approx_kl | 0.014509285 | +| clip_fraction | 0.377 | +| clip_range | 0.0703 | +| entropy_loss | -6.43 | +| explained_variance | 0.534 | +| learning_rate | 4.56e-05 | +| loss | -0.0359 | +| n_updates | 52392 | +| policy_gradient_loss | -0.0227 | +| value_loss | 0.000108 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1422 | +| iterations | 9145 | +| time_elapsed | 13163 | +| total_timesteps | 18728960 | +| train/ | | +| approx_kl | 0.012944946 | +| clip_fraction | 0.353 | +| clip_range | 0.0703 | +| entropy_loss | -6.45 | +| explained_variance | 0.454 | +| learning_rate | 4.56e-05 | +| loss | -0.0331 | +| n_updates | 52396 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000125 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1422 | +| iterations | 9146 | +| time_elapsed | 13164 | +| total_timesteps | 18731008 | +| train/ | | +| approx_kl | 0.014009133 | +| clip_fraction | 0.362 | +| clip_range | 0.0703 | +| entropy_loss | -6.39 | +| explained_variance | 0.319 | +| learning_rate | 4.56e-05 | +| loss | -0.0326 | +| n_updates | 52400 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000132 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1422 | +| iterations | 9147 | +| time_elapsed | 13166 | +| total_timesteps | 18733056 | +| train/ | | +| approx_kl | 0.013418061 | +| clip_fraction | 0.308 | +| clip_range | 0.0703 | +| entropy_loss | -5.95 | +| explained_variance | 0.43 | +| learning_rate | 4.56e-05 | +| loss | -0.0279 | +| n_updates | 52404 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000183 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1422 | +| iterations | 9148 | +| time_elapsed | 13167 | +| total_timesteps | 18735104 | +| train/ | | +| approx_kl | 0.010487132 | +| clip_fraction | 0.326 | +| clip_range | 0.0703 | +| entropy_loss | -5.93 | +| explained_variance | 0.359 | +| learning_rate | 4.56e-05 | +| loss | -0.0259 | +| n_updates | 52408 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000421 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1422 | +| iterations | 9149 | +| time_elapsed | 13169 | +| total_timesteps | 18737152 | +| train/ | | +| approx_kl | 0.011775633 | +| clip_fraction | 0.346 | +| clip_range | 0.0703 | +| entropy_loss | -6.36 | +| explained_variance | 0.308 | +| learning_rate | 4.56e-05 | +| loss | -0.0316 | +| n_updates | 52412 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000173 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1422 | +| iterations | 9150 | +| time_elapsed | 13170 | +| total_timesteps | 18739200 | +| train/ | | +| approx_kl | 0.012868192 | +| clip_fraction | 0.346 | +| clip_range | 0.0703 | +| entropy_loss | -6.31 | +| explained_variance | 0.455 | +| learning_rate | 4.55e-05 | +| loss | -0.033 | +| n_updates | 52416 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000194 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1422 | +| iterations | 9151 | +| time_elapsed | 13172 | +| total_timesteps | 18741248 | +| train/ | | +| approx_kl | 0.013546303 | +| clip_fraction | 0.365 | +| clip_range | 0.0703 | +| entropy_loss | -6.59 | +| explained_variance | 0.408 | +| learning_rate | 4.55e-05 | +| loss | -0.0367 | +| n_updates | 52420 | +| policy_gradient_loss | -0.0224 | +| value_loss | 0.000105 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1422 | +| iterations | 9152 | +| time_elapsed | 13173 | +| total_timesteps | 18743296 | +| train/ | | +| approx_kl | 0.015123913 | +| clip_fraction | 0.364 | +| clip_range | 0.0703 | +| entropy_loss | -6.63 | +| explained_variance | 0.195 | +| learning_rate | 4.55e-05 | +| loss | -0.0342 | +| n_updates | 52424 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000173 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1422 | +| iterations | 9153 | +| time_elapsed | 13175 | +| total_timesteps | 18745344 | +| train/ | | +| approx_kl | 0.011646525 | +| clip_fraction | 0.348 | +| clip_range | 0.0703 | +| entropy_loss | -6.82 | +| explained_variance | -0.135 | +| learning_rate | 4.55e-05 | +| loss | -0.0347 | +| n_updates | 52428 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000178 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1422 | +| iterations | 9154 | +| time_elapsed | 13176 | +| total_timesteps | 18747392 | +| train/ | | +| approx_kl | 0.010420829 | +| clip_fraction | 0.313 | +| clip_range | 0.0703 | +| entropy_loss | -6.57 | +| explained_variance | 0.358 | +| learning_rate | 4.55e-05 | +| loss | -0.0284 | +| n_updates | 52432 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000306 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1422 | +| iterations | 9155 | +| time_elapsed | 13178 | +| total_timesteps | 18749440 | +| train/ | | +| approx_kl | 0.013297886 | +| clip_fraction | 0.376 | +| clip_range | 0.0703 | +| entropy_loss | -6.78 | +| explained_variance | 0.338 | +| learning_rate | 4.55e-05 | +| loss | -0.0399 | +| n_updates | 52436 | +| policy_gradient_loss | -0.0223 | +| value_loss | 0.000116 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1422 | +| iterations | 9156 | +| time_elapsed | 13179 | +| total_timesteps | 18751488 | +| train/ | | +| approx_kl | 0.011786862 | +| clip_fraction | 0.35 | +| clip_range | 0.0703 | +| entropy_loss | -6.34 | +| explained_variance | 0.391 | +| learning_rate | 4.55e-05 | +| loss | -0.0313 | +| n_updates | 52440 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000162 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1422 | +| iterations | 9157 | +| time_elapsed | 13180 | +| total_timesteps | 18753536 | +| train/ | | +| approx_kl | 0.013747419 | +| clip_fraction | 0.363 | +| clip_range | 0.0703 | +| entropy_loss | -6.38 | +| explained_variance | 0.378 | +| learning_rate | 4.55e-05 | +| loss | -0.0289 | +| n_updates | 52444 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.00022 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1422 | +| iterations | 9158 | +| time_elapsed | 13182 | +| total_timesteps | 18755584 | +| train/ | | +| approx_kl | 0.009920356 | +| clip_fraction | 0.336 | +| clip_range | 0.0703 | +| entropy_loss | -6.89 | +| explained_variance | -0.0225 | +| learning_rate | 4.55e-05 | +| loss | -0.0277 | +| n_updates | 52448 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000117 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1422 | +| iterations | 9159 | +| time_elapsed | 13183 | +| total_timesteps | 18757632 | +| train/ | | +| approx_kl | 0.010530824 | +| clip_fraction | 0.315 | +| clip_range | 0.0703 | +| entropy_loss | -6.23 | +| explained_variance | 0.575 | +| learning_rate | 4.55e-05 | +| loss | -0.0278 | +| n_updates | 52452 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000227 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1422 | +| iterations | 9160 | +| time_elapsed | 13185 | +| total_timesteps | 18759680 | +| train/ | | +| approx_kl | 0.015202307 | +| clip_fraction | 0.328 | +| clip_range | 0.0703 | +| entropy_loss | -5.94 | +| explained_variance | 0.36 | +| learning_rate | 4.55e-05 | +| loss | -0.0301 | +| n_updates | 52456 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000179 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1422 | +| iterations | 9161 | +| time_elapsed | 13186 | +| total_timesteps | 18761728 | +| train/ | | +| approx_kl | 0.013242098 | +| clip_fraction | 0.337 | +| clip_range | 0.0703 | +| entropy_loss | -5.92 | +| explained_variance | 0.589 | +| learning_rate | 4.55e-05 | +| loss | -0.0275 | +| n_updates | 52460 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000166 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1422 | +| iterations | 9162 | +| time_elapsed | 13188 | +| total_timesteps | 18763776 | +| train/ | | +| approx_kl | 0.016013265 | +| clip_fraction | 0.375 | +| clip_range | 0.0703 | +| entropy_loss | -6.47 | +| explained_variance | 0.415 | +| learning_rate | 4.55e-05 | +| loss | -0.0367 | +| n_updates | 52464 | +| policy_gradient_loss | -0.0217 | +| value_loss | 8.96e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1422 | +| iterations | 9163 | +| time_elapsed | 13189 | +| total_timesteps | 18765824 | +| train/ | | +| approx_kl | 0.012669483 | +| clip_fraction | 0.333 | +| clip_range | 0.0703 | +| entropy_loss | -6.72 | +| explained_variance | 0.25 | +| learning_rate | 4.55e-05 | +| loss | -0.0274 | +| n_updates | 52468 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000162 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1422 | +| iterations | 9164 | +| time_elapsed | 13191 | +| total_timesteps | 18767872 | +| train/ | | +| approx_kl | 0.016150657 | +| clip_fraction | 0.348 | +| clip_range | 0.0703 | +| entropy_loss | -6.74 | +| explained_variance | 0.0691 | +| learning_rate | 4.55e-05 | +| loss | -0.0385 | +| n_updates | 52472 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000152 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1422 | +| iterations | 9165 | +| time_elapsed | 13192 | +| total_timesteps | 18769920 | +| train/ | | +| approx_kl | 0.011781157 | +| clip_fraction | 0.33 | +| clip_range | 0.0703 | +| entropy_loss | -6.54 | +| explained_variance | 0.178 | +| learning_rate | 4.55e-05 | +| loss | -0.0312 | +| n_updates | 52476 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000175 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1422 | +| iterations | 9166 | +| time_elapsed | 13193 | +| total_timesteps | 18771968 | +| train/ | | +| approx_kl | 0.013339272 | +| clip_fraction | 0.328 | +| clip_range | 0.0703 | +| entropy_loss | -6.43 | +| explained_variance | 0.212 | +| learning_rate | 4.55e-05 | +| loss | -0.0271 | +| n_updates | 52480 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000145 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1422 | +| iterations | 9167 | +| time_elapsed | 13195 | +| total_timesteps | 18774016 | +| train/ | | +| approx_kl | 0.013372131 | +| clip_fraction | 0.347 | +| clip_range | 0.0703 | +| entropy_loss | -6.26 | +| explained_variance | 0.37 | +| learning_rate | 4.55e-05 | +| loss | -0.0318 | +| n_updates | 52484 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000282 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.315 | +| time/ | | +| fps | 1422 | +| iterations | 9168 | +| time_elapsed | 13196 | +| total_timesteps | 18776064 | +| train/ | | +| approx_kl | 0.016284255 | +| clip_fraction | 0.396 | +| clip_range | 0.0703 | +| entropy_loss | -6.21 | +| explained_variance | 0.562 | +| learning_rate | 4.55e-05 | +| loss | -0.0386 | +| n_updates | 52488 | +| policy_gradient_loss | -0.0228 | +| value_loss | 0.000108 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1422 | +| iterations | 9169 | +| time_elapsed | 13198 | +| total_timesteps | 18778112 | +| train/ | | +| approx_kl | 0.01539884 | +| clip_fraction | 0.352 | +| clip_range | 0.0703 | +| entropy_loss | -6.31 | +| explained_variance | 0.55 | +| learning_rate | 4.55e-05 | +| loss | -0.0304 | +| n_updates | 52492 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000114 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1422 | +| iterations | 9170 | +| time_elapsed | 13199 | +| total_timesteps | 18780160 | +| train/ | | +| approx_kl | 0.012480493 | +| clip_fraction | 0.331 | +| clip_range | 0.0703 | +| entropy_loss | -6.06 | +| explained_variance | 0.558 | +| learning_rate | 4.55e-05 | +| loss | -0.0257 | +| n_updates | 52496 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000172 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 1422 | +| iterations | 9171 | +| time_elapsed | 13201 | +| total_timesteps | 18782208 | +| train/ | | +| approx_kl | 0.014427697 | +| clip_fraction | 0.345 | +| clip_range | 0.0703 | +| entropy_loss | -6.83 | +| explained_variance | -0.00322 | +| learning_rate | 4.55e-05 | +| loss | -0.0325 | +| n_updates | 52500 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000173 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1422 | +| iterations | 9172 | +| time_elapsed | 13202 | +| total_timesteps | 18784256 | +| train/ | | +| approx_kl | 0.012884055 | +| clip_fraction | 0.332 | +| clip_range | 0.0703 | +| entropy_loss | -6.45 | +| explained_variance | 0.554 | +| learning_rate | 4.55e-05 | +| loss | -0.0277 | +| n_updates | 52504 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000185 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1422 | +| iterations | 9173 | +| time_elapsed | 13204 | +| total_timesteps | 18786304 | +| train/ | | +| approx_kl | 0.010633141 | +| clip_fraction | 0.323 | +| clip_range | 0.0703 | +| entropy_loss | -6.28 | +| explained_variance | 0.289 | +| learning_rate | 4.55e-05 | +| loss | -0.0287 | +| n_updates | 52508 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000185 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1422 | +| iterations | 9174 | +| time_elapsed | 13205 | +| total_timesteps | 18788352 | +| train/ | | +| approx_kl | 0.013429202 | +| clip_fraction | 0.332 | +| clip_range | 0.0703 | +| entropy_loss | -6.28 | +| explained_variance | 0.343 | +| learning_rate | 4.55e-05 | +| loss | -0.0274 | +| n_updates | 52512 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000279 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1422 | +| iterations | 9175 | +| time_elapsed | 13207 | +| total_timesteps | 18790400 | +| train/ | | +| approx_kl | 0.011932077 | +| clip_fraction | 0.359 | +| clip_range | 0.0703 | +| entropy_loss | -6.95 | +| explained_variance | -0.0235 | +| learning_rate | 4.55e-05 | +| loss | -0.0351 | +| n_updates | 52516 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000164 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1422 | +| iterations | 9176 | +| time_elapsed | 13208 | +| total_timesteps | 18792448 | +| train/ | | +| approx_kl | 0.013621181 | +| clip_fraction | 0.38 | +| clip_range | 0.0703 | +| entropy_loss | -6.67 | +| explained_variance | 0.339 | +| learning_rate | 4.55e-05 | +| loss | -0.0318 | +| n_updates | 52520 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000155 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1422 | +| iterations | 9177 | +| time_elapsed | 13209 | +| total_timesteps | 18794496 | +| train/ | | +| approx_kl | 0.012187578 | +| clip_fraction | 0.348 | +| clip_range | 0.0703 | +| entropy_loss | -6.13 | +| explained_variance | 0.419 | +| learning_rate | 4.55e-05 | +| loss | -0.0281 | +| n_updates | 52524 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.00033 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1422 | +| iterations | 9178 | +| time_elapsed | 13211 | +| total_timesteps | 18796544 | +| train/ | | +| approx_kl | 0.015741363 | +| clip_fraction | 0.344 | +| clip_range | 0.0703 | +| entropy_loss | -6.33 | +| explained_variance | 0.146 | +| learning_rate | 4.55e-05 | +| loss | -0.0363 | +| n_updates | 52528 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000196 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1422 | +| iterations | 9179 | +| time_elapsed | 13212 | +| total_timesteps | 18798592 | +| train/ | | +| approx_kl | 0.013265938 | +| clip_fraction | 0.357 | +| clip_range | 0.0703 | +| entropy_loss | -6.26 | +| explained_variance | 0.459 | +| learning_rate | 4.55e-05 | +| loss | -0.0349 | +| n_updates | 52532 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000159 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1422 | +| iterations | 9180 | +| time_elapsed | 13214 | +| total_timesteps | 18800640 | +| train/ | | +| approx_kl | 0.013752557 | +| clip_fraction | 0.342 | +| clip_range | 0.0703 | +| entropy_loss | -6.4 | +| explained_variance | 0.401 | +| learning_rate | 4.55e-05 | +| loss | -0.0297 | +| n_updates | 52536 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000166 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1422 | +| iterations | 9181 | +| time_elapsed | 13215 | +| total_timesteps | 18802688 | +| train/ | | +| approx_kl | 0.014047163 | +| clip_fraction | 0.336 | +| clip_range | 0.0703 | +| entropy_loss | -6.59 | +| explained_variance | -0.279 | +| learning_rate | 4.55e-05 | +| loss | -0.0321 | +| n_updates | 52540 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000176 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1422 | +| iterations | 9182 | +| time_elapsed | 13217 | +| total_timesteps | 18804736 | +| train/ | | +| approx_kl | 0.014677865 | +| clip_fraction | 0.347 | +| clip_range | 0.0703 | +| entropy_loss | -6.64 | +| explained_variance | 0.464 | +| learning_rate | 4.55e-05 | +| loss | -0.0381 | +| n_updates | 52544 | +| policy_gradient_loss | -0.0204 | +| value_loss | 8.73e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1422 | +| iterations | 9183 | +| time_elapsed | 13218 | +| total_timesteps | 18806784 | +| train/ | | +| approx_kl | 0.012378028 | +| clip_fraction | 0.328 | +| clip_range | 0.0703 | +| entropy_loss | -6.11 | +| explained_variance | 0.582 | +| learning_rate | 4.55e-05 | +| loss | -0.0283 | +| n_updates | 52548 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000137 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1422 | +| iterations | 9184 | +| time_elapsed | 13219 | +| total_timesteps | 18808832 | +| train/ | | +| approx_kl | 0.010044611 | +| clip_fraction | 0.326 | +| clip_range | 0.0703 | +| entropy_loss | -6.5 | +| explained_variance | 0.247 | +| learning_rate | 4.55e-05 | +| loss | -0.0239 | +| n_updates | 52552 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000219 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1422 | +| iterations | 9185 | +| time_elapsed | 13221 | +| total_timesteps | 18810880 | +| train/ | | +| approx_kl | 0.011737209 | +| clip_fraction | 0.321 | +| clip_range | 0.0703 | +| entropy_loss | -6.22 | +| explained_variance | 0.302 | +| learning_rate | 4.55e-05 | +| loss | -0.0188 | +| n_updates | 52556 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000429 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1422 | +| iterations | 9186 | +| time_elapsed | 13222 | +| total_timesteps | 18812928 | +| train/ | | +| approx_kl | 0.012378982 | +| clip_fraction | 0.344 | +| clip_range | 0.0703 | +| entropy_loss | -6.07 | +| explained_variance | 0.661 | +| learning_rate | 4.55e-05 | +| loss | -0.0303 | +| n_updates | 52560 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000166 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1422 | +| iterations | 9187 | +| time_elapsed | 13224 | +| total_timesteps | 18814976 | +| train/ | | +| approx_kl | 0.011747678 | +| clip_fraction | 0.389 | +| clip_range | 0.0703 | +| entropy_loss | -6.31 | +| explained_variance | 0.471 | +| learning_rate | 4.55e-05 | +| loss | -0.0298 | +| n_updates | 52564 | +| policy_gradient_loss | -0.022 | +| value_loss | 8.6e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1422 | +| iterations | 9188 | +| time_elapsed | 13225 | +| total_timesteps | 18817024 | +| train/ | | +| approx_kl | 0.013472627 | +| clip_fraction | 0.377 | +| clip_range | 0.0703 | +| entropy_loss | -6.69 | +| explained_variance | -0.136 | +| learning_rate | 4.55e-05 | +| loss | -0.0317 | +| n_updates | 52568 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000143 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1422 | +| iterations | 9189 | +| time_elapsed | 13227 | +| total_timesteps | 18819072 | +| train/ | | +| approx_kl | 0.012828786 | +| clip_fraction | 0.368 | +| clip_range | 0.0703 | +| entropy_loss | -6.76 | +| explained_variance | 0.362 | +| learning_rate | 4.55e-05 | +| loss | -0.0333 | +| n_updates | 52572 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000147 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1422 | +| iterations | 9190 | +| time_elapsed | 13228 | +| total_timesteps | 18821120 | +| train/ | | +| approx_kl | 0.012769737 | +| clip_fraction | 0.314 | +| clip_range | 0.0703 | +| entropy_loss | -6.31 | +| explained_variance | 0.365 | +| learning_rate | 4.55e-05 | +| loss | -0.0252 | +| n_updates | 52576 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000294 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1422 | +| iterations | 9191 | +| time_elapsed | 13230 | +| total_timesteps | 18823168 | +| train/ | | +| approx_kl | 0.013110653 | +| clip_fraction | 0.302 | +| clip_range | 0.0703 | +| entropy_loss | -6.2 | +| explained_variance | 0.241 | +| learning_rate | 4.55e-05 | +| loss | -0.0197 | +| n_updates | 52580 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000449 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1422 | +| iterations | 9192 | +| time_elapsed | 13231 | +| total_timesteps | 18825216 | +| train/ | | +| approx_kl | 0.015215407 | +| clip_fraction | 0.372 | +| clip_range | 0.0703 | +| entropy_loss | -6.55 | +| explained_variance | -0.218 | +| learning_rate | 4.55e-05 | +| loss | -0.0315 | +| n_updates | 52584 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000218 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1422 | +| iterations | 9193 | +| time_elapsed | 13233 | +| total_timesteps | 18827264 | +| train/ | | +| approx_kl | 0.015988026 | +| clip_fraction | 0.366 | +| clip_range | 0.0703 | +| entropy_loss | -6.32 | +| explained_variance | 0.591 | +| learning_rate | 4.55e-05 | +| loss | -0.0366 | +| n_updates | 52588 | +| policy_gradient_loss | -0.0233 | +| value_loss | 9.9e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1422 | +| iterations | 9194 | +| time_elapsed | 13234 | +| total_timesteps | 18829312 | +| train/ | | +| approx_kl | 0.015008143 | +| clip_fraction | 0.36 | +| clip_range | 0.0703 | +| entropy_loss | -6.53 | +| explained_variance | 0.315 | +| learning_rate | 4.55e-05 | +| loss | -0.0303 | +| n_updates | 52592 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000137 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1422 | +| iterations | 9195 | +| time_elapsed | 13235 | +| total_timesteps | 18831360 | +| train/ | | +| approx_kl | 0.018626895 | +| clip_fraction | 0.362 | +| clip_range | 0.0703 | +| entropy_loss | -6.52 | +| explained_variance | 0.448 | +| learning_rate | 4.55e-05 | +| loss | -0.0263 | +| n_updates | 52596 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000155 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1422 | +| iterations | 9196 | +| time_elapsed | 13237 | +| total_timesteps | 18833408 | +| train/ | | +| approx_kl | 0.017972793 | +| clip_fraction | 0.329 | +| clip_range | 0.0703 | +| entropy_loss | -6.15 | +| explained_variance | 0.205 | +| learning_rate | 4.55e-05 | +| loss | -0.0259 | +| n_updates | 52600 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000152 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1422 | +| iterations | 9197 | +| time_elapsed | 13238 | +| total_timesteps | 18835456 | +| train/ | | +| approx_kl | 0.011883145 | +| clip_fraction | 0.328 | +| clip_range | 0.0703 | +| entropy_loss | -6.16 | +| explained_variance | 0.384 | +| learning_rate | 4.55e-05 | +| loss | -0.0219 | +| n_updates | 52604 | +| policy_gradient_loss | -0.0144 | +| value_loss | 0.000225 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1422 | +| iterations | 9198 | +| time_elapsed | 13240 | +| total_timesteps | 18837504 | +| train/ | | +| approx_kl | 0.015613741 | +| clip_fraction | 0.346 | +| clip_range | 0.0703 | +| entropy_loss | -6.19 | +| explained_variance | 0.421 | +| learning_rate | 4.55e-05 | +| loss | -0.0282 | +| n_updates | 52608 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000229 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1422 | +| iterations | 9199 | +| time_elapsed | 13241 | +| total_timesteps | 18839552 | +| train/ | | +| approx_kl | 0.017096683 | +| clip_fraction | 0.344 | +| clip_range | 0.0703 | +| entropy_loss | -5.93 | +| explained_variance | 0.445 | +| learning_rate | 4.55e-05 | +| loss | -0.0269 | +| n_updates | 52612 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000186 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1422 | +| iterations | 9200 | +| time_elapsed | 13243 | +| total_timesteps | 18841600 | +| train/ | | +| approx_kl | 0.015263644 | +| clip_fraction | 0.403 | +| clip_range | 0.0703 | +| entropy_loss | -6.03 | +| explained_variance | 0.535 | +| learning_rate | 4.55e-05 | +| loss | -0.0371 | +| n_updates | 52616 | +| policy_gradient_loss | -0.0239 | +| value_loss | 0.000102 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1422 | +| iterations | 9201 | +| time_elapsed | 13244 | +| total_timesteps | 18843648 | +| train/ | | +| approx_kl | 0.017122589 | +| clip_fraction | 0.368 | +| clip_range | 0.0703 | +| entropy_loss | -6.47 | +| explained_variance | 0.487 | +| learning_rate | 4.55e-05 | +| loss | -0.0388 | +| n_updates | 52620 | +| policy_gradient_loss | -0.0221 | +| value_loss | 7.36e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1422 | +| iterations | 9202 | +| time_elapsed | 13246 | +| total_timesteps | 18845696 | +| train/ | | +| approx_kl | 0.01428073 | +| clip_fraction | 0.352 | +| clip_range | 0.0703 | +| entropy_loss | -6.6 | +| explained_variance | 0.668 | +| learning_rate | 4.55e-05 | +| loss | -0.0262 | +| n_updates | 52624 | +| policy_gradient_loss | -0.0192 | +| value_loss | 7.82e-05 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1422 | +| iterations | 9203 | +| time_elapsed | 13247 | +| total_timesteps | 18847744 | +| train/ | | +| approx_kl | 0.0115412455 | +| clip_fraction | 0.323 | +| clip_range | 0.0703 | +| entropy_loss | -6.53 | +| explained_variance | 0.275 | +| learning_rate | 4.55e-05 | +| loss | -0.0294 | +| n_updates | 52628 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000157 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1422 | +| iterations | 9204 | +| time_elapsed | 13249 | +| total_timesteps | 18849792 | +| train/ | | +| approx_kl | 0.010544213 | +| clip_fraction | 0.327 | +| clip_range | 0.0703 | +| entropy_loss | -6.57 | +| explained_variance | 0.307 | +| learning_rate | 4.55e-05 | +| loss | -0.0273 | +| n_updates | 52632 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000191 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1422 | +| iterations | 9205 | +| time_elapsed | 13250 | +| total_timesteps | 18851840 | +| train/ | | +| approx_kl | 0.010575684 | +| clip_fraction | 0.327 | +| clip_range | 0.0703 | +| entropy_loss | -5.74 | +| explained_variance | 0.492 | +| learning_rate | 4.55e-05 | +| loss | -0.0274 | +| n_updates | 52636 | +| policy_gradient_loss | -0.0148 | +| value_loss | 0.000289 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1422 | +| iterations | 9206 | +| time_elapsed | 13252 | +| total_timesteps | 18853888 | +| train/ | | +| approx_kl | 0.0138053 | +| clip_fraction | 0.346 | +| clip_range | 0.0703 | +| entropy_loss | -6.38 | +| explained_variance | 0.467 | +| learning_rate | 4.55e-05 | +| loss | -0.0311 | +| n_updates | 52640 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000129 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1422 | +| iterations | 9207 | +| time_elapsed | 13253 | +| total_timesteps | 18855936 | +| train/ | | +| approx_kl | 0.013688198 | +| clip_fraction | 0.369 | +| clip_range | 0.0703 | +| entropy_loss | -6.63 | +| explained_variance | 0.263 | +| learning_rate | 4.55e-05 | +| loss | -0.0332 | +| n_updates | 52644 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000183 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1422 | +| iterations | 9208 | +| time_elapsed | 13254 | +| total_timesteps | 18857984 | +| train/ | | +| approx_kl | 0.014582334 | +| clip_fraction | 0.345 | +| clip_range | 0.0703 | +| entropy_loss | -6.6 | +| explained_variance | 0.286 | +| learning_rate | 4.55e-05 | +| loss | -0.0297 | +| n_updates | 52648 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000166 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1422 | +| iterations | 9209 | +| time_elapsed | 13256 | +| total_timesteps | 18860032 | +| train/ | | +| approx_kl | 0.01054276 | +| clip_fraction | 0.316 | +| clip_range | 0.0703 | +| entropy_loss | -6.41 | +| explained_variance | 0.309 | +| learning_rate | 4.55e-05 | +| loss | -0.0253 | +| n_updates | 52652 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000362 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1422 | +| iterations | 9210 | +| time_elapsed | 13257 | +| total_timesteps | 18862080 | +| train/ | | +| approx_kl | 0.0131094195 | +| clip_fraction | 0.327 | +| clip_range | 0.0703 | +| entropy_loss | -6.19 | +| explained_variance | 0.619 | +| learning_rate | 4.55e-05 | +| loss | -0.0289 | +| n_updates | 52656 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000117 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1422 | +| iterations | 9211 | +| time_elapsed | 13259 | +| total_timesteps | 18864128 | +| train/ | | +| approx_kl | 0.013353759 | +| clip_fraction | 0.353 | +| clip_range | 0.0703 | +| entropy_loss | -5.95 | +| explained_variance | 0.737 | +| learning_rate | 4.55e-05 | +| loss | -0.0291 | +| n_updates | 52660 | +| policy_gradient_loss | -0.0195 | +| value_loss | 8.4e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1422 | +| iterations | 9212 | +| time_elapsed | 13260 | +| total_timesteps | 18866176 | +| train/ | | +| approx_kl | 0.012972536 | +| clip_fraction | 0.337 | +| clip_range | 0.0703 | +| entropy_loss | -6.65 | +| explained_variance | 0.00767 | +| learning_rate | 4.55e-05 | +| loss | -0.0298 | +| n_updates | 52664 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000115 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1422 | +| iterations | 9213 | +| time_elapsed | 13262 | +| total_timesteps | 18868224 | +| train/ | | +| approx_kl | 0.015124699 | +| clip_fraction | 0.342 | +| clip_range | 0.0703 | +| entropy_loss | -6.56 | +| explained_variance | -0.0948 | +| learning_rate | 4.55e-05 | +| loss | -0.0251 | +| n_updates | 52668 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000192 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1422 | +| iterations | 9214 | +| time_elapsed | 13263 | +| total_timesteps | 18870272 | +| train/ | | +| approx_kl | 0.015272511 | +| clip_fraction | 0.345 | +| clip_range | 0.0703 | +| entropy_loss | -6.1 | +| explained_variance | 0.55 | +| learning_rate | 4.55e-05 | +| loss | -0.0301 | +| n_updates | 52672 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.00014 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1422 | +| iterations | 9215 | +| time_elapsed | 13264 | +| total_timesteps | 18872320 | +| train/ | | +| approx_kl | 0.013957147 | +| clip_fraction | 0.363 | +| clip_range | 0.0703 | +| entropy_loss | -6.36 | +| explained_variance | 0.345 | +| learning_rate | 4.55e-05 | +| loss | -0.0303 | +| n_updates | 52676 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000185 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1422 | +| iterations | 9216 | +| time_elapsed | 13266 | +| total_timesteps | 18874368 | +| train/ | | +| approx_kl | 0.013897733 | +| clip_fraction | 0.36 | +| clip_range | 0.0703 | +| entropy_loss | -6.7 | +| explained_variance | 0.264 | +| learning_rate | 4.55e-05 | +| loss | -0.0367 | +| n_updates | 52680 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000173 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1422 | +| iterations | 9217 | +| time_elapsed | 13267 | +| total_timesteps | 18876416 | +| train/ | | +| approx_kl | 0.0129149165 | +| clip_fraction | 0.318 | +| clip_range | 0.0703 | +| entropy_loss | -6.19 | +| explained_variance | 0.43 | +| learning_rate | 4.55e-05 | +| loss | -0.0255 | +| n_updates | 52684 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000272 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1422 | +| iterations | 9218 | +| time_elapsed | 13269 | +| total_timesteps | 18878464 | +| train/ | | +| approx_kl | 0.012668632 | +| clip_fraction | 0.34 | +| clip_range | 0.0703 | +| entropy_loss | -6.3 | +| explained_variance | 0.433 | +| learning_rate | 4.55e-05 | +| loss | -0.0293 | +| n_updates | 52688 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000205 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1422 | +| iterations | 9219 | +| time_elapsed | 13270 | +| total_timesteps | 18880512 | +| train/ | | +| approx_kl | 0.014520835 | +| clip_fraction | 0.375 | +| clip_range | 0.0703 | +| entropy_loss | -6.54 | +| explained_variance | 0.397 | +| learning_rate | 4.55e-05 | +| loss | -0.0414 | +| n_updates | 52692 | +| policy_gradient_loss | -0.0248 | +| value_loss | 8.29e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1422 | +| iterations | 9220 | +| time_elapsed | 13272 | +| total_timesteps | 18882560 | +| train/ | | +| approx_kl | 0.012804608 | +| clip_fraction | 0.358 | +| clip_range | 0.0703 | +| entropy_loss | -6.67 | +| explained_variance | 0.224 | +| learning_rate | 4.55e-05 | +| loss | -0.0214 | +| n_updates | 52696 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000229 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1422 | +| iterations | 9221 | +| time_elapsed | 13273 | +| total_timesteps | 18884608 | +| train/ | | +| approx_kl | 0.016227862 | +| clip_fraction | 0.372 | +| clip_range | 0.0703 | +| entropy_loss | -6.65 | +| explained_variance | 0.462 | +| learning_rate | 4.55e-05 | +| loss | -0.0394 | +| n_updates | 52700 | +| policy_gradient_loss | -0.0203 | +| value_loss | 8.24e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1422 | +| iterations | 9222 | +| time_elapsed | 13274 | +| total_timesteps | 18886656 | +| train/ | | +| approx_kl | 0.012067938 | +| clip_fraction | 0.342 | +| clip_range | 0.0703 | +| entropy_loss | -6.32 | +| explained_variance | 0.363 | +| learning_rate | 4.55e-05 | +| loss | -0.0237 | +| n_updates | 52704 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000278 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1422 | +| iterations | 9223 | +| time_elapsed | 13276 | +| total_timesteps | 18888704 | +| train/ | | +| approx_kl | 0.017244708 | +| clip_fraction | 0.37 | +| clip_range | 0.0703 | +| entropy_loss | -5.56 | +| explained_variance | 0.614 | +| learning_rate | 4.55e-05 | +| loss | -0.035 | +| n_updates | 52708 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000142 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1422 | +| iterations | 9224 | +| time_elapsed | 13277 | +| total_timesteps | 18890752 | +| train/ | | +| approx_kl | 0.012520645 | +| clip_fraction | 0.38 | +| clip_range | 0.0703 | +| entropy_loss | -6.28 | +| explained_variance | 0.645 | +| learning_rate | 4.55e-05 | +| loss | -0.031 | +| n_updates | 52712 | +| policy_gradient_loss | -0.0204 | +| value_loss | 9.74e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1422 | +| iterations | 9225 | +| time_elapsed | 13279 | +| total_timesteps | 18892800 | +| train/ | | +| approx_kl | 0.01640522 | +| clip_fraction | 0.369 | +| clip_range | 0.0703 | +| entropy_loss | -6.8 | +| explained_variance | -0.0778 | +| learning_rate | 4.55e-05 | +| loss | -0.0336 | +| n_updates | 52716 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000129 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1422 | +| iterations | 9226 | +| time_elapsed | 13280 | +| total_timesteps | 18894848 | +| train/ | | +| approx_kl | 0.0136963455 | +| clip_fraction | 0.324 | +| clip_range | 0.0703 | +| entropy_loss | -6.64 | +| explained_variance | -0.0821 | +| learning_rate | 4.55e-05 | +| loss | -0.0216 | +| n_updates | 52720 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000219 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1422 | +| iterations | 9227 | +| time_elapsed | 13282 | +| total_timesteps | 18896896 | +| train/ | | +| approx_kl | 0.013553457 | +| clip_fraction | 0.334 | +| clip_range | 0.0703 | +| entropy_loss | -6.09 | +| explained_variance | 0.388 | +| learning_rate | 4.55e-05 | +| loss | -0.0328 | +| n_updates | 52724 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000212 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1422 | +| iterations | 9228 | +| time_elapsed | 13283 | +| total_timesteps | 18898944 | +| train/ | | +| approx_kl | 0.014427371 | +| clip_fraction | 0.366 | +| clip_range | 0.0703 | +| entropy_loss | -6.75 | +| explained_variance | 0.0646 | +| learning_rate | 4.55e-05 | +| loss | -0.0341 | +| n_updates | 52728 | +| policy_gradient_loss | -0.0224 | +| value_loss | 0.000105 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1422 | +| iterations | 9229 | +| time_elapsed | 13285 | +| total_timesteps | 18900992 | +| train/ | | +| approx_kl | 0.015251317 | +| clip_fraction | 0.364 | +| clip_range | 0.0703 | +| entropy_loss | -6.27 | +| explained_variance | 0.256 | +| learning_rate | 4.55e-05 | +| loss | -0.032 | +| n_updates | 52732 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000248 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1422 | +| iterations | 9230 | +| time_elapsed | 13286 | +| total_timesteps | 18903040 | +| train/ | | +| approx_kl | 0.01588549 | +| clip_fraction | 0.339 | +| clip_range | 0.0703 | +| entropy_loss | -6.21 | +| explained_variance | 0.46 | +| learning_rate | 4.55e-05 | +| loss | -0.0311 | +| n_updates | 52736 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000174 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1422 | +| iterations | 9231 | +| time_elapsed | 13288 | +| total_timesteps | 18905088 | +| train/ | | +| approx_kl | 0.012541877 | +| clip_fraction | 0.344 | +| clip_range | 0.0703 | +| entropy_loss | -6.89 | +| explained_variance | 0.0375 | +| learning_rate | 4.55e-05 | +| loss | -0.0342 | +| n_updates | 52740 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000148 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1422 | +| iterations | 9232 | +| time_elapsed | 13289 | +| total_timesteps | 18907136 | +| train/ | | +| approx_kl | 0.014411758 | +| clip_fraction | 0.348 | +| clip_range | 0.0703 | +| entropy_loss | -6.76 | +| explained_variance | 0.296 | +| learning_rate | 4.55e-05 | +| loss | -0.027 | +| n_updates | 52744 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000102 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1422 | +| iterations | 9233 | +| time_elapsed | 13290 | +| total_timesteps | 18909184 | +| train/ | | +| approx_kl | 0.015967935 | +| clip_fraction | 0.35 | +| clip_range | 0.0703 | +| entropy_loss | -6 | +| explained_variance | 0.51 | +| learning_rate | 4.55e-05 | +| loss | -0.0304 | +| n_updates | 52748 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.00019 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1422 | +| iterations | 9234 | +| time_elapsed | 13292 | +| total_timesteps | 18911232 | +| train/ | | +| approx_kl | 0.012143452 | +| clip_fraction | 0.34 | +| clip_range | 0.0703 | +| entropy_loss | -6.49 | +| explained_variance | 0.528 | +| learning_rate | 4.55e-05 | +| loss | -0.0315 | +| n_updates | 52752 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000131 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1422 | +| iterations | 9235 | +| time_elapsed | 13293 | +| total_timesteps | 18913280 | +| train/ | | +| approx_kl | 0.016048858 | +| clip_fraction | 0.385 | +| clip_range | 0.0703 | +| entropy_loss | -6.81 | +| explained_variance | -0.477 | +| learning_rate | 4.55e-05 | +| loss | -0.0385 | +| n_updates | 52756 | +| policy_gradient_loss | -0.0226 | +| value_loss | 6.82e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1422 | +| iterations | 9236 | +| time_elapsed | 13295 | +| total_timesteps | 18915328 | +| train/ | | +| approx_kl | 0.014213643 | +| clip_fraction | 0.365 | +| clip_range | 0.0703 | +| entropy_loss | -6.79 | +| explained_variance | 0.265 | +| learning_rate | 4.55e-05 | +| loss | -0.0264 | +| n_updates | 52760 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000221 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1422 | +| iterations | 9237 | +| time_elapsed | 13296 | +| total_timesteps | 18917376 | +| train/ | | +| approx_kl | 0.012185149 | +| clip_fraction | 0.349 | +| clip_range | 0.0703 | +| entropy_loss | -6.28 | +| explained_variance | 0.334 | +| learning_rate | 4.55e-05 | +| loss | -0.0312 | +| n_updates | 52764 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000157 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1422 | +| iterations | 9238 | +| time_elapsed | 13298 | +| total_timesteps | 18919424 | +| train/ | | +| approx_kl | 0.012391706 | +| clip_fraction | 0.351 | +| clip_range | 0.0703 | +| entropy_loss | -6.11 | +| explained_variance | 0.511 | +| learning_rate | 4.55e-05 | +| loss | -0.0326 | +| n_updates | 52768 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000156 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1422 | +| iterations | 9239 | +| time_elapsed | 13299 | +| total_timesteps | 18921472 | +| train/ | | +| approx_kl | 0.012540772 | +| clip_fraction | 0.326 | +| clip_range | 0.0703 | +| entropy_loss | -5.78 | +| explained_variance | 0.606 | +| learning_rate | 4.55e-05 | +| loss | -0.0267 | +| n_updates | 52772 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000174 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1422 | +| iterations | 9240 | +| time_elapsed | 13300 | +| total_timesteps | 18923520 | +| train/ | | +| approx_kl | 0.016225485 | +| clip_fraction | 0.322 | +| clip_range | 0.0703 | +| entropy_loss | -6.41 | +| explained_variance | -0.113 | +| learning_rate | 4.55e-05 | +| loss | -0.0259 | +| n_updates | 52776 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000297 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1422 | +| iterations | 9241 | +| time_elapsed | 13302 | +| total_timesteps | 18925568 | +| train/ | | +| approx_kl | 0.014126949 | +| clip_fraction | 0.336 | +| clip_range | 0.0703 | +| entropy_loss | -6.62 | +| explained_variance | 0.132 | +| learning_rate | 4.55e-05 | +| loss | -0.0292 | +| n_updates | 52780 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000274 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1422 | +| iterations | 9242 | +| time_elapsed | 13303 | +| total_timesteps | 18927616 | +| train/ | | +| approx_kl | 0.0133580975 | +| clip_fraction | 0.326 | +| clip_range | 0.0703 | +| entropy_loss | -6.75 | +| explained_variance | 0.128 | +| learning_rate | 4.55e-05 | +| loss | -0.0337 | +| n_updates | 52784 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000212 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1422 | +| iterations | 9243 | +| time_elapsed | 13305 | +| total_timesteps | 18929664 | +| train/ | | +| approx_kl | 0.014845194 | +| clip_fraction | 0.349 | +| clip_range | 0.0703 | +| entropy_loss | -6.95 | +| explained_variance | -0.0489 | +| learning_rate | 4.55e-05 | +| loss | -0.034 | +| n_updates | 52788 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000197 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1422 | +| iterations | 9244 | +| time_elapsed | 13306 | +| total_timesteps | 18931712 | +| train/ | | +| approx_kl | 0.015034462 | +| clip_fraction | 0.353 | +| clip_range | 0.0703 | +| entropy_loss | -7.06 | +| explained_variance | 0.0478 | +| learning_rate | 4.55e-05 | +| loss | -0.0377 | +| n_updates | 52792 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000142 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1422 | +| iterations | 9245 | +| time_elapsed | 13308 | +| total_timesteps | 18933760 | +| train/ | | +| approx_kl | 0.013108091 | +| clip_fraction | 0.325 | +| clip_range | 0.0703 | +| entropy_loss | -6.28 | +| explained_variance | 0.593 | +| learning_rate | 4.55e-05 | +| loss | -0.0296 | +| n_updates | 52796 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000167 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1422 | +| iterations | 9246 | +| time_elapsed | 13309 | +| total_timesteps | 18935808 | +| train/ | | +| approx_kl | 0.013024757 | +| clip_fraction | 0.353 | +| clip_range | 0.0703 | +| entropy_loss | -6.47 | +| explained_variance | 0.417 | +| learning_rate | 4.55e-05 | +| loss | -0.0246 | +| n_updates | 52800 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000156 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1422 | +| iterations | 9247 | +| time_elapsed | 13310 | +| total_timesteps | 18937856 | +| train/ | | +| approx_kl | 0.01196918 | +| clip_fraction | 0.321 | +| clip_range | 0.0703 | +| entropy_loss | -6.54 | +| explained_variance | 0.445 | +| learning_rate | 4.55e-05 | +| loss | -0.0292 | +| n_updates | 52804 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.00028 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1422 | +| iterations | 9248 | +| time_elapsed | 13312 | +| total_timesteps | 18939904 | +| train/ | | +| approx_kl | 0.011526674 | +| clip_fraction | 0.346 | +| clip_range | 0.0703 | +| entropy_loss | -5.93 | +| explained_variance | 0.709 | +| learning_rate | 4.55e-05 | +| loss | -0.0319 | +| n_updates | 52808 | +| policy_gradient_loss | -0.0208 | +| value_loss | 8.06e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1422 | +| iterations | 9249 | +| time_elapsed | 13313 | +| total_timesteps | 18941952 | +| train/ | | +| approx_kl | 0.012083763 | +| clip_fraction | 0.343 | +| clip_range | 0.0703 | +| entropy_loss | -6.22 | +| explained_variance | 0.0488 | +| learning_rate | 4.55e-05 | +| loss | -0.0289 | +| n_updates | 52812 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000116 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1422 | +| iterations | 9250 | +| time_elapsed | 13315 | +| total_timesteps | 18944000 | +| train/ | | +| approx_kl | 0.012465572 | +| clip_fraction | 0.322 | +| clip_range | 0.0703 | +| entropy_loss | -5.88 | +| explained_variance | 0.528 | +| learning_rate | 4.55e-05 | +| loss | -0.0279 | +| n_updates | 52816 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000179 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1422 | +| iterations | 9251 | +| time_elapsed | 13316 | +| total_timesteps | 18946048 | +| train/ | | +| approx_kl | 0.013083329 | +| clip_fraction | 0.372 | +| clip_range | 0.0703 | +| entropy_loss | -6.89 | +| explained_variance | -0.0756 | +| learning_rate | 4.55e-05 | +| loss | -0.0305 | +| n_updates | 52820 | +| policy_gradient_loss | -0.021 | +| value_loss | 9.6e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1422 | +| iterations | 9252 | +| time_elapsed | 13318 | +| total_timesteps | 18948096 | +| train/ | | +| approx_kl | 0.012772305 | +| clip_fraction | 0.32 | +| clip_range | 0.0703 | +| entropy_loss | -6.99 | +| explained_variance | -0.0156 | +| learning_rate | 4.55e-05 | +| loss | -0.0306 | +| n_updates | 52824 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000248 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1422 | +| iterations | 9253 | +| time_elapsed | 13319 | +| total_timesteps | 18950144 | +| train/ | | +| approx_kl | 0.01333373 | +| clip_fraction | 0.328 | +| clip_range | 0.0703 | +| entropy_loss | -6.19 | +| explained_variance | 0.371 | +| learning_rate | 4.55e-05 | +| loss | -0.025 | +| n_updates | 52828 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000264 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1422 | +| iterations | 9254 | +| time_elapsed | 13321 | +| total_timesteps | 18952192 | +| train/ | | +| approx_kl | 0.012672502 | +| clip_fraction | 0.337 | +| clip_range | 0.0703 | +| entropy_loss | -6.96 | +| explained_variance | -0.143 | +| learning_rate | 4.55e-05 | +| loss | -0.0379 | +| n_updates | 52832 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.00014 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1422 | +| iterations | 9255 | +| time_elapsed | 13322 | +| total_timesteps | 18954240 | +| train/ | | +| approx_kl | 0.014382196 | +| clip_fraction | 0.347 | +| clip_range | 0.0703 | +| entropy_loss | -6.09 | +| explained_variance | 0.676 | +| learning_rate | 4.55e-05 | +| loss | -0.0336 | +| n_updates | 52836 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.00011 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1422 | +| iterations | 9256 | +| time_elapsed | 13323 | +| total_timesteps | 18956288 | +| train/ | | +| approx_kl | 0.014673745 | +| clip_fraction | 0.36 | +| clip_range | 0.0703 | +| entropy_loss | -6.31 | +| explained_variance | 0.291 | +| learning_rate | 4.55e-05 | +| loss | -0.0297 | +| n_updates | 52840 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000194 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1422 | +| iterations | 9257 | +| time_elapsed | 13325 | +| total_timesteps | 18958336 | +| train/ | | +| approx_kl | 0.012706126 | +| clip_fraction | 0.346 | +| clip_range | 0.0703 | +| entropy_loss | -6.4 | +| explained_variance | 0.311 | +| learning_rate | 4.55e-05 | +| loss | -0.0319 | +| n_updates | 52844 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000113 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1422 | +| iterations | 9258 | +| time_elapsed | 13326 | +| total_timesteps | 18960384 | +| train/ | | +| approx_kl | 0.012124688 | +| clip_fraction | 0.35 | +| clip_range | 0.0703 | +| entropy_loss | -6.23 | +| explained_variance | 0.733 | +| learning_rate | 4.55e-05 | +| loss | -0.0275 | +| n_updates | 52848 | +| policy_gradient_loss | -0.0196 | +| value_loss | 7.97e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1422 | +| iterations | 9259 | +| time_elapsed | 13328 | +| total_timesteps | 18962432 | +| train/ | | +| approx_kl | 0.014347125 | +| clip_fraction | 0.328 | +| clip_range | 0.0703 | +| entropy_loss | -6.41 | +| explained_variance | 0.403 | +| learning_rate | 4.55e-05 | +| loss | -0.0261 | +| n_updates | 52852 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000124 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1422 | +| iterations | 9260 | +| time_elapsed | 13329 | +| total_timesteps | 18964480 | +| train/ | | +| approx_kl | 0.011953538 | +| clip_fraction | 0.329 | +| clip_range | 0.0703 | +| entropy_loss | -6.91 | +| explained_variance | -0.0515 | +| learning_rate | 4.55e-05 | +| loss | -0.0318 | +| n_updates | 52856 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000312 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1422 | +| iterations | 9261 | +| time_elapsed | 13331 | +| total_timesteps | 18966528 | +| train/ | | +| approx_kl | 0.011164613 | +| clip_fraction | 0.292 | +| clip_range | 0.0703 | +| entropy_loss | -6.53 | +| explained_variance | 0.481 | +| learning_rate | 4.55e-05 | +| loss | -0.0267 | +| n_updates | 52860 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000183 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1422 | +| iterations | 9262 | +| time_elapsed | 13332 | +| total_timesteps | 18968576 | +| train/ | | +| approx_kl | 0.009663616 | +| clip_fraction | 0.302 | +| clip_range | 0.0703 | +| entropy_loss | -6.4 | +| explained_variance | 0.402 | +| learning_rate | 4.55e-05 | +| loss | -0.0271 | +| n_updates | 52864 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000299 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1422 | +| iterations | 9263 | +| time_elapsed | 13334 | +| total_timesteps | 18970624 | +| train/ | | +| approx_kl | 0.012592845 | +| clip_fraction | 0.342 | +| clip_range | 0.0703 | +| entropy_loss | -6.61 | +| explained_variance | 0.379 | +| learning_rate | 4.55e-05 | +| loss | -0.0363 | +| n_updates | 52868 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.00022 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1422 | +| iterations | 9264 | +| time_elapsed | 13335 | +| total_timesteps | 18972672 | +| train/ | | +| approx_kl | 0.0136148725 | +| clip_fraction | 0.367 | +| clip_range | 0.0703 | +| entropy_loss | -6.54 | +| explained_variance | 0.463 | +| learning_rate | 4.55e-05 | +| loss | -0.0319 | +| n_updates | 52872 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000106 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1422 | +| iterations | 9265 | +| time_elapsed | 13336 | +| total_timesteps | 18974720 | +| train/ | | +| approx_kl | 0.014651889 | +| clip_fraction | 0.358 | +| clip_range | 0.0703 | +| entropy_loss | -6.4 | +| explained_variance | 0.692 | +| learning_rate | 4.55e-05 | +| loss | -0.0386 | +| n_updates | 52876 | +| policy_gradient_loss | -0.0217 | +| value_loss | 7.48e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1422 | +| iterations | 9266 | +| time_elapsed | 13338 | +| total_timesteps | 18976768 | +| train/ | | +| approx_kl | 0.013268356 | +| clip_fraction | 0.333 | +| clip_range | 0.0703 | +| entropy_loss | -6.28 | +| explained_variance | 0.474 | +| learning_rate | 4.55e-05 | +| loss | -0.0316 | +| n_updates | 52880 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000231 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1422 | +| iterations | 9267 | +| time_elapsed | 13339 | +| total_timesteps | 18978816 | +| train/ | | +| approx_kl | 0.012056614 | +| clip_fraction | 0.322 | +| clip_range | 0.0703 | +| entropy_loss | -6.55 | +| explained_variance | 0.254 | +| learning_rate | 4.55e-05 | +| loss | -0.027 | +| n_updates | 52884 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.00015 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1422 | +| iterations | 9268 | +| time_elapsed | 13341 | +| total_timesteps | 18980864 | +| train/ | | +| approx_kl | 0.01259123 | +| clip_fraction | 0.321 | +| clip_range | 0.0703 | +| entropy_loss | -6.78 | +| explained_variance | 0.209 | +| learning_rate | 4.55e-05 | +| loss | -0.03 | +| n_updates | 52888 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.00023 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1422 | +| iterations | 9269 | +| time_elapsed | 13342 | +| total_timesteps | 18982912 | +| train/ | | +| approx_kl | 0.011311193 | +| clip_fraction | 0.335 | +| clip_range | 0.0703 | +| entropy_loss | -6.71 | +| explained_variance | 0.164 | +| learning_rate | 4.55e-05 | +| loss | -0.0251 | +| n_updates | 52892 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000386 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1422 | +| iterations | 9270 | +| time_elapsed | 13344 | +| total_timesteps | 18984960 | +| train/ | | +| approx_kl | 0.013332585 | +| clip_fraction | 0.367 | +| clip_range | 0.0703 | +| entropy_loss | -6.24 | +| explained_variance | 0.331 | +| learning_rate | 4.55e-05 | +| loss | -0.0331 | +| n_updates | 52896 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000128 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1422 | +| iterations | 9271 | +| time_elapsed | 13345 | +| total_timesteps | 18987008 | +| train/ | | +| approx_kl | 0.012279292 | +| clip_fraction | 0.329 | +| clip_range | 0.0703 | +| entropy_loss | -6.38 | +| explained_variance | 0.318 | +| learning_rate | 4.55e-05 | +| loss | -0.0288 | +| n_updates | 52900 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000262 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1422 | +| iterations | 9272 | +| time_elapsed | 13347 | +| total_timesteps | 18989056 | +| train/ | | +| approx_kl | 0.014148135 | +| clip_fraction | 0.341 | +| clip_range | 0.0703 | +| entropy_loss | -6.3 | +| explained_variance | 0.379 | +| learning_rate | 4.55e-05 | +| loss | -0.0282 | +| n_updates | 52904 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000201 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1422 | +| iterations | 9273 | +| time_elapsed | 13348 | +| total_timesteps | 18991104 | +| train/ | | +| approx_kl | 0.015783736 | +| clip_fraction | 0.382 | +| clip_range | 0.0703 | +| entropy_loss | -6.08 | +| explained_variance | 0.412 | +| learning_rate | 4.55e-05 | +| loss | -0.0339 | +| n_updates | 52908 | +| policy_gradient_loss | -0.0227 | +| value_loss | 9.95e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1422 | +| iterations | 9274 | +| time_elapsed | 13349 | +| total_timesteps | 18993152 | +| train/ | | +| approx_kl | 0.016595837 | +| clip_fraction | 0.348 | +| clip_range | 0.0703 | +| entropy_loss | -6.54 | +| explained_variance | 0.314 | +| learning_rate | 4.55e-05 | +| loss | -0.033 | +| n_updates | 52912 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000145 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1422 | +| iterations | 9275 | +| time_elapsed | 13351 | +| total_timesteps | 18995200 | +| train/ | | +| approx_kl | 0.01577724 | +| clip_fraction | 0.384 | +| clip_range | 0.0703 | +| entropy_loss | -6.8 | +| explained_variance | -0.266 | +| learning_rate | 4.55e-05 | +| loss | -0.037 | +| n_updates | 52916 | +| policy_gradient_loss | -0.0243 | +| value_loss | 6.57e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1422 | +| iterations | 9276 | +| time_elapsed | 13352 | +| total_timesteps | 18997248 | +| train/ | | +| approx_kl | 0.011722852 | +| clip_fraction | 0.338 | +| clip_range | 0.0703 | +| entropy_loss | -6.77 | +| explained_variance | 0.0786 | +| learning_rate | 4.55e-05 | +| loss | -0.0244 | +| n_updates | 52920 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000234 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1422 | +| iterations | 9277 | +| time_elapsed | 13354 | +| total_timesteps | 18999296 | +| train/ | | +| approx_kl | 0.013707211 | +| clip_fraction | 0.339 | +| clip_range | 0.0703 | +| entropy_loss | -6.22 | +| explained_variance | 0.652 | +| learning_rate | 4.55e-05 | +| loss | -0.0341 | +| n_updates | 52924 | +| policy_gradient_loss | -0.0205 | +| value_loss | 8.42e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1422 | +| iterations | 9278 | +| time_elapsed | 13355 | +| total_timesteps | 19001344 | +| train/ | | +| approx_kl | 0.014183529 | +| clip_fraction | 0.316 | +| clip_range | 0.0703 | +| entropy_loss | -6.42 | +| explained_variance | 0.304 | +| learning_rate | 4.55e-05 | +| loss | -0.0271 | +| n_updates | 52928 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000155 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1422 | +| iterations | 9279 | +| time_elapsed | 13357 | +| total_timesteps | 19003392 | +| train/ | | +| approx_kl | 0.015559388 | +| clip_fraction | 0.322 | +| clip_range | 0.0702 | +| entropy_loss | -6.46 | +| explained_variance | 0.514 | +| learning_rate | 4.55e-05 | +| loss | -0.0282 | +| n_updates | 52932 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000129 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1422 | +| iterations | 9280 | +| time_elapsed | 13358 | +| total_timesteps | 19005440 | +| train/ | | +| approx_kl | 0.014853838 | +| clip_fraction | 0.338 | +| clip_range | 0.0702 | +| entropy_loss | -6.47 | +| explained_variance | 0.238 | +| learning_rate | 4.55e-05 | +| loss | -0.0273 | +| n_updates | 52936 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000278 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1422 | +| iterations | 9281 | +| time_elapsed | 13360 | +| total_timesteps | 19007488 | +| train/ | | +| approx_kl | 0.01410495 | +| clip_fraction | 0.349 | +| clip_range | 0.0702 | +| entropy_loss | -6.68 | +| explained_variance | 0.277 | +| learning_rate | 4.55e-05 | +| loss | -0.0275 | +| n_updates | 52940 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.0002 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1422 | +| iterations | 9282 | +| time_elapsed | 13361 | +| total_timesteps | 19009536 | +| train/ | | +| approx_kl | 0.013672037 | +| clip_fraction | 0.362 | +| clip_range | 0.0702 | +| entropy_loss | -6.7 | +| explained_variance | 0.379 | +| learning_rate | 4.55e-05 | +| loss | -0.0343 | +| n_updates | 52944 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000114 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1422 | +| iterations | 9283 | +| time_elapsed | 13363 | +| total_timesteps | 19011584 | +| train/ | | +| approx_kl | 0.01251584 | +| clip_fraction | 0.346 | +| clip_range | 0.0702 | +| entropy_loss | -6.81 | +| explained_variance | -0.0152 | +| learning_rate | 4.55e-05 | +| loss | -0.0334 | +| n_updates | 52948 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000118 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1422 | +| iterations | 9284 | +| time_elapsed | 13364 | +| total_timesteps | 19013632 | +| train/ | | +| approx_kl | 0.0118069425 | +| clip_fraction | 0.334 | +| clip_range | 0.0702 | +| entropy_loss | -6.71 | +| explained_variance | 0.692 | +| learning_rate | 4.55e-05 | +| loss | -0.0362 | +| n_updates | 52952 | +| policy_gradient_loss | -0.022 | +| value_loss | 5.84e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1422 | +| iterations | 9285 | +| time_elapsed | 13366 | +| total_timesteps | 19015680 | +| train/ | | +| approx_kl | 0.012386144 | +| clip_fraction | 0.29 | +| clip_range | 0.0702 | +| entropy_loss | -6.42 | +| explained_variance | 0.438 | +| learning_rate | 4.55e-05 | +| loss | -0.0251 | +| n_updates | 52956 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000264 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1422 | +| iterations | 9286 | +| time_elapsed | 13367 | +| total_timesteps | 19017728 | +| train/ | | +| approx_kl | 0.014934254 | +| clip_fraction | 0.332 | +| clip_range | 0.0702 | +| entropy_loss | -6.64 | +| explained_variance | -0.435 | +| learning_rate | 4.55e-05 | +| loss | -0.034 | +| n_updates | 52960 | +| policy_gradient_loss | -0.0203 | +| value_loss | 7.45e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1422 | +| iterations | 9287 | +| time_elapsed | 13369 | +| total_timesteps | 19019776 | +| train/ | | +| approx_kl | 0.010254103 | +| clip_fraction | 0.343 | +| clip_range | 0.0702 | +| entropy_loss | -6.21 | +| explained_variance | 0.408 | +| learning_rate | 4.55e-05 | +| loss | -0.0226 | +| n_updates | 52964 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000246 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1422 | +| iterations | 9288 | +| time_elapsed | 13370 | +| total_timesteps | 19021824 | +| train/ | | +| approx_kl | 0.015084054 | +| clip_fraction | 0.359 | +| clip_range | 0.0702 | +| entropy_loss | -6.13 | +| explained_variance | 0.287 | +| learning_rate | 4.55e-05 | +| loss | -0.0369 | +| n_updates | 52968 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.00018 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1422 | +| iterations | 9289 | +| time_elapsed | 13372 | +| total_timesteps | 19023872 | +| train/ | | +| approx_kl | 0.01476429 | +| clip_fraction | 0.369 | +| clip_range | 0.0702 | +| entropy_loss | -6.68 | +| explained_variance | 0.219 | +| learning_rate | 4.55e-05 | +| loss | -0.0353 | +| n_updates | 52972 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000142 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1422 | +| iterations | 9290 | +| time_elapsed | 13373 | +| total_timesteps | 19025920 | +| train/ | | +| approx_kl | 0.014137114 | +| clip_fraction | 0.352 | +| clip_range | 0.0702 | +| entropy_loss | -6.72 | +| explained_variance | 0.434 | +| learning_rate | 4.55e-05 | +| loss | -0.0352 | +| n_updates | 52976 | +| policy_gradient_loss | -0.0211 | +| value_loss | 8.48e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1422 | +| iterations | 9291 | +| time_elapsed | 13374 | +| total_timesteps | 19027968 | +| train/ | | +| approx_kl | 0.013177093 | +| clip_fraction | 0.343 | +| clip_range | 0.0702 | +| entropy_loss | -6.76 | +| explained_variance | 0.0859 | +| learning_rate | 4.55e-05 | +| loss | -0.0224 | +| n_updates | 52980 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000206 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1422 | +| iterations | 9292 | +| time_elapsed | 13376 | +| total_timesteps | 19030016 | +| train/ | | +| approx_kl | 0.014593835 | +| clip_fraction | 0.336 | +| clip_range | 0.0702 | +| entropy_loss | -6.64 | +| explained_variance | 0.382 | +| learning_rate | 4.55e-05 | +| loss | -0.0291 | +| n_updates | 52984 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000216 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1422 | +| iterations | 9293 | +| time_elapsed | 13377 | +| total_timesteps | 19032064 | +| train/ | | +| approx_kl | 0.014358496 | +| clip_fraction | 0.323 | +| clip_range | 0.0702 | +| entropy_loss | -6.38 | +| explained_variance | 0.19 | +| learning_rate | 4.55e-05 | +| loss | -0.0261 | +| n_updates | 52988 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000395 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1422 | +| iterations | 9294 | +| time_elapsed | 13379 | +| total_timesteps | 19034112 | +| train/ | | +| approx_kl | 0.01198473 | +| clip_fraction | 0.337 | +| clip_range | 0.0702 | +| entropy_loss | -6.75 | +| explained_variance | 0.231 | +| learning_rate | 4.55e-05 | +| loss | -0.03 | +| n_updates | 52992 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000169 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1422 | +| iterations | 9295 | +| time_elapsed | 13380 | +| total_timesteps | 19036160 | +| train/ | | +| approx_kl | 0.012693103 | +| clip_fraction | 0.341 | +| clip_range | 0.0702 | +| entropy_loss | -6.55 | +| explained_variance | 0.254 | +| learning_rate | 4.55e-05 | +| loss | -0.0299 | +| n_updates | 52996 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000196 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1422 | +| iterations | 9296 | +| time_elapsed | 13382 | +| total_timesteps | 19038208 | +| train/ | | +| approx_kl | 0.013144283 | +| clip_fraction | 0.344 | +| clip_range | 0.0702 | +| entropy_loss | -6.53 | +| explained_variance | 0.434 | +| learning_rate | 4.55e-05 | +| loss | -0.0313 | +| n_updates | 53000 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000174 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1422 | +| iterations | 9297 | +| time_elapsed | 13383 | +| total_timesteps | 19040256 | +| train/ | | +| approx_kl | 0.012333557 | +| clip_fraction | 0.332 | +| clip_range | 0.0702 | +| entropy_loss | -6.6 | +| explained_variance | 0.67 | +| learning_rate | 4.55e-05 | +| loss | -0.0294 | +| n_updates | 53004 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000106 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1422 | +| iterations | 9298 | +| time_elapsed | 13385 | +| total_timesteps | 19042304 | +| train/ | | +| approx_kl | 0.012831755 | +| clip_fraction | 0.336 | +| clip_range | 0.0702 | +| entropy_loss | -6.24 | +| explained_variance | 0.609 | +| learning_rate | 4.55e-05 | +| loss | -0.0294 | +| n_updates | 53008 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000102 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1422 | +| iterations | 9299 | +| time_elapsed | 13386 | +| total_timesteps | 19044352 | +| train/ | | +| approx_kl | 0.012642243 | +| clip_fraction | 0.319 | +| clip_range | 0.0702 | +| entropy_loss | -6.2 | +| explained_variance | 0.618 | +| learning_rate | 4.55e-05 | +| loss | -0.0286 | +| n_updates | 53012 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000157 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1422 | +| iterations | 9300 | +| time_elapsed | 13388 | +| total_timesteps | 19046400 | +| train/ | | +| approx_kl | 0.0119089 | +| clip_fraction | 0.34 | +| clip_range | 0.0702 | +| entropy_loss | -6.97 | +| explained_variance | -0.262 | +| learning_rate | 4.55e-05 | +| loss | -0.0325 | +| n_updates | 53016 | +| policy_gradient_loss | -0.0207 | +| value_loss | 7.79e-05 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1422 | +| iterations | 9301 | +| time_elapsed | 13389 | +| total_timesteps | 19048448 | +| train/ | | +| approx_kl | 0.011520296 | +| clip_fraction | 0.35 | +| clip_range | 0.0702 | +| entropy_loss | -6.93 | +| explained_variance | 0.236 | +| learning_rate | 4.55e-05 | +| loss | -0.0333 | +| n_updates | 53020 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000242 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1422 | +| iterations | 9302 | +| time_elapsed | 13390 | +| total_timesteps | 19050496 | +| train/ | | +| approx_kl | 0.010893823 | +| clip_fraction | 0.331 | +| clip_range | 0.0702 | +| entropy_loss | -6.49 | +| explained_variance | 0.273 | +| learning_rate | 4.55e-05 | +| loss | -0.0315 | +| n_updates | 53024 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000447 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1422 | +| iterations | 9303 | +| time_elapsed | 13392 | +| total_timesteps | 19052544 | +| train/ | | +| approx_kl | 0.015153283 | +| clip_fraction | 0.35 | +| clip_range | 0.0702 | +| entropy_loss | -5.96 | +| explained_variance | 0.634 | +| learning_rate | 4.55e-05 | +| loss | -0.0358 | +| n_updates | 53028 | +| policy_gradient_loss | -0.0227 | +| value_loss | 0.00014 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1422 | +| iterations | 9304 | +| time_elapsed | 13393 | +| total_timesteps | 19054592 | +| train/ | | +| approx_kl | 0.013097821 | +| clip_fraction | 0.355 | +| clip_range | 0.0702 | +| entropy_loss | -6.48 | +| explained_variance | 0.461 | +| learning_rate | 4.55e-05 | +| loss | -0.0397 | +| n_updates | 53032 | +| policy_gradient_loss | -0.0229 | +| value_loss | 0.000153 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1422 | +| iterations | 9305 | +| time_elapsed | 13395 | +| total_timesteps | 19056640 | +| train/ | | +| approx_kl | 0.011442961 | +| clip_fraction | 0.322 | +| clip_range | 0.0702 | +| entropy_loss | -6.64 | +| explained_variance | 0.305 | +| learning_rate | 4.55e-05 | +| loss | -0.0311 | +| n_updates | 53036 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000213 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1422 | +| iterations | 9306 | +| time_elapsed | 13397 | +| total_timesteps | 19058688 | +| train/ | | +| approx_kl | 0.010475768 | +| clip_fraction | 0.317 | +| clip_range | 0.0702 | +| entropy_loss | -6.69 | +| explained_variance | -0.0645 | +| learning_rate | 4.55e-05 | +| loss | -0.0261 | +| n_updates | 53040 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000553 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1422 | +| iterations | 9307 | +| time_elapsed | 13398 | +| total_timesteps | 19060736 | +| train/ | | +| approx_kl | 0.014077198 | +| clip_fraction | 0.377 | +| clip_range | 0.0702 | +| entropy_loss | -6.62 | +| explained_variance | 0.238 | +| learning_rate | 4.55e-05 | +| loss | -0.0344 | +| n_updates | 53044 | +| policy_gradient_loss | -0.0235 | +| value_loss | 0.000136 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1422 | +| iterations | 9308 | +| time_elapsed | 13399 | +| total_timesteps | 19062784 | +| train/ | | +| approx_kl | 0.015015956 | +| clip_fraction | 0.371 | +| clip_range | 0.0702 | +| entropy_loss | -6.53 | +| explained_variance | 0.126 | +| learning_rate | 4.55e-05 | +| loss | -0.0328 | +| n_updates | 53048 | +| policy_gradient_loss | -0.0224 | +| value_loss | 0.000214 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1422 | +| iterations | 9309 | +| time_elapsed | 13401 | +| total_timesteps | 19064832 | +| train/ | | +| approx_kl | 0.014809301 | +| clip_fraction | 0.333 | +| clip_range | 0.0702 | +| entropy_loss | -6.71 | +| explained_variance | 0.231 | +| learning_rate | 4.55e-05 | +| loss | -0.0295 | +| n_updates | 53052 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.00022 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1422 | +| iterations | 9310 | +| time_elapsed | 13402 | +| total_timesteps | 19066880 | +| train/ | | +| approx_kl | 0.012453882 | +| clip_fraction | 0.33 | +| clip_range | 0.0702 | +| entropy_loss | -6.54 | +| explained_variance | 0.393 | +| learning_rate | 4.55e-05 | +| loss | -0.0301 | +| n_updates | 53056 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000183 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1422 | +| iterations | 9311 | +| time_elapsed | 13404 | +| total_timesteps | 19068928 | +| train/ | | +| approx_kl | 0.01164435 | +| clip_fraction | 0.33 | +| clip_range | 0.0702 | +| entropy_loss | -6.81 | +| explained_variance | 0.333 | +| learning_rate | 4.55e-05 | +| loss | -0.0323 | +| n_updates | 53060 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.00012 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1422 | +| iterations | 9312 | +| time_elapsed | 13405 | +| total_timesteps | 19070976 | +| train/ | | +| approx_kl | 0.010819004 | +| clip_fraction | 0.325 | +| clip_range | 0.0702 | +| entropy_loss | -6.78 | +| explained_variance | 0.59 | +| learning_rate | 4.55e-05 | +| loss | -0.031 | +| n_updates | 53064 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000106 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1422 | +| iterations | 9313 | +| time_elapsed | 13407 | +| total_timesteps | 19073024 | +| train/ | | +| approx_kl | 0.01055396 | +| clip_fraction | 0.328 | +| clip_range | 0.0702 | +| entropy_loss | -6.83 | +| explained_variance | 0.0661 | +| learning_rate | 4.55e-05 | +| loss | -0.0221 | +| n_updates | 53068 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000212 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1422 | +| iterations | 9314 | +| time_elapsed | 13408 | +| total_timesteps | 19075072 | +| train/ | | +| approx_kl | 0.014432389 | +| clip_fraction | 0.351 | +| clip_range | 0.0702 | +| entropy_loss | -6.5 | +| explained_variance | 0.61 | +| learning_rate | 4.55e-05 | +| loss | -0.0377 | +| n_updates | 53072 | +| policy_gradient_loss | -0.0209 | +| value_loss | 9.61e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1422 | +| iterations | 9315 | +| time_elapsed | 13409 | +| total_timesteps | 19077120 | +| train/ | | +| approx_kl | 0.0151653495 | +| clip_fraction | 0.336 | +| clip_range | 0.0702 | +| entropy_loss | -6.58 | +| explained_variance | 0.266 | +| learning_rate | 4.55e-05 | +| loss | -0.0297 | +| n_updates | 53076 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.00019 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1422 | +| iterations | 9316 | +| time_elapsed | 13411 | +| total_timesteps | 19079168 | +| train/ | | +| approx_kl | 0.013489688 | +| clip_fraction | 0.344 | +| clip_range | 0.0702 | +| entropy_loss | -6.59 | +| explained_variance | 0.501 | +| learning_rate | 4.55e-05 | +| loss | -0.0287 | +| n_updates | 53080 | +| policy_gradient_loss | -0.0199 | +| value_loss | 9.84e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1422 | +| iterations | 9317 | +| time_elapsed | 13412 | +| total_timesteps | 19081216 | +| train/ | | +| approx_kl | 0.013867959 | +| clip_fraction | 0.334 | +| clip_range | 0.0702 | +| entropy_loss | -5.67 | +| explained_variance | 0.781 | +| learning_rate | 4.55e-05 | +| loss | -0.0286 | +| n_updates | 53084 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1422 | +| iterations | 9318 | +| time_elapsed | 13414 | +| total_timesteps | 19083264 | +| train/ | | +| approx_kl | 0.011745512 | +| clip_fraction | 0.317 | +| clip_range | 0.0702 | +| entropy_loss | -6.62 | +| explained_variance | -0.0477 | +| learning_rate | 4.55e-05 | +| loss | -0.0289 | +| n_updates | 53088 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000164 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1422 | +| iterations | 9319 | +| time_elapsed | 13415 | +| total_timesteps | 19085312 | +| train/ | | +| approx_kl | 0.009804765 | +| clip_fraction | 0.322 | +| clip_range | 0.0702 | +| entropy_loss | -6.96 | +| explained_variance | 0.384 | +| learning_rate | 4.55e-05 | +| loss | -0.0265 | +| n_updates | 53092 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000168 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1422 | +| iterations | 9320 | +| time_elapsed | 13417 | +| total_timesteps | 19087360 | +| train/ | | +| approx_kl | 0.011345869 | +| clip_fraction | 0.319 | +| clip_range | 0.0702 | +| entropy_loss | -6.66 | +| explained_variance | 0.358 | +| learning_rate | 4.55e-05 | +| loss | -0.0269 | +| n_updates | 53096 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000216 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1422 | +| iterations | 9321 | +| time_elapsed | 13418 | +| total_timesteps | 19089408 | +| train/ | | +| approx_kl | 0.010238622 | +| clip_fraction | 0.315 | +| clip_range | 0.0702 | +| entropy_loss | -6.63 | +| explained_variance | 0.357 | +| learning_rate | 4.55e-05 | +| loss | -0.0273 | +| n_updates | 53100 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.00024 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1422 | +| iterations | 9322 | +| time_elapsed | 13420 | +| total_timesteps | 19091456 | +| train/ | | +| approx_kl | 0.010095205 | +| clip_fraction | 0.315 | +| clip_range | 0.0702 | +| entropy_loss | -6.17 | +| explained_variance | 0.418 | +| learning_rate | 4.55e-05 | +| loss | -0.0231 | +| n_updates | 53104 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000302 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1422 | +| iterations | 9323 | +| time_elapsed | 13421 | +| total_timesteps | 19093504 | +| train/ | | +| approx_kl | 0.011016257 | +| clip_fraction | 0.332 | +| clip_range | 0.0702 | +| entropy_loss | -6.54 | +| explained_variance | 0.124 | +| learning_rate | 4.55e-05 | +| loss | -0.0279 | +| n_updates | 53108 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000317 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1422 | +| iterations | 9324 | +| time_elapsed | 13423 | +| total_timesteps | 19095552 | +| train/ | | +| approx_kl | 0.010276636 | +| clip_fraction | 0.334 | +| clip_range | 0.0702 | +| entropy_loss | -6.6 | +| explained_variance | 0.46 | +| learning_rate | 4.55e-05 | +| loss | -0.0281 | +| n_updates | 53112 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000162 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1422 | +| iterations | 9325 | +| time_elapsed | 13424 | +| total_timesteps | 19097600 | +| train/ | | +| approx_kl | 0.010962971 | +| clip_fraction | 0.342 | +| clip_range | 0.0702 | +| entropy_loss | -6.57 | +| explained_variance | 0.457 | +| learning_rate | 4.55e-05 | +| loss | -0.029 | +| n_updates | 53116 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000176 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1422 | +| iterations | 9326 | +| time_elapsed | 13425 | +| total_timesteps | 19099648 | +| train/ | | +| approx_kl | 0.013104716 | +| clip_fraction | 0.362 | +| clip_range | 0.0702 | +| entropy_loss | -6.76 | +| explained_variance | 0.401 | +| learning_rate | 4.55e-05 | +| loss | -0.0384 | +| n_updates | 53120 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.0001 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1422 | +| iterations | 9327 | +| time_elapsed | 13427 | +| total_timesteps | 19101696 | +| train/ | | +| approx_kl | 0.013682177 | +| clip_fraction | 0.37 | +| clip_range | 0.0702 | +| entropy_loss | -6.25 | +| explained_variance | 0.825 | +| learning_rate | 4.55e-05 | +| loss | -0.0276 | +| n_updates | 53124 | +| policy_gradient_loss | -0.0224 | +| value_loss | 5.14e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1422 | +| iterations | 9328 | +| time_elapsed | 13428 | +| total_timesteps | 19103744 | +| train/ | | +| approx_kl | 0.012299116 | +| clip_fraction | 0.312 | +| clip_range | 0.0702 | +| entropy_loss | -6.83 | +| explained_variance | 0.0269 | +| learning_rate | 4.55e-05 | +| loss | -0.0274 | +| n_updates | 53128 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000164 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1422 | +| iterations | 9329 | +| time_elapsed | 13430 | +| total_timesteps | 19105792 | +| train/ | | +| approx_kl | 0.010949371 | +| clip_fraction | 0.311 | +| clip_range | 0.0702 | +| entropy_loss | -6.27 | +| explained_variance | 0.436 | +| learning_rate | 4.55e-05 | +| loss | -0.0318 | +| n_updates | 53132 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000249 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1422 | +| iterations | 9330 | +| time_elapsed | 13431 | +| total_timesteps | 19107840 | +| train/ | | +| approx_kl | 0.012914205 | +| clip_fraction | 0.32 | +| clip_range | 0.0702 | +| entropy_loss | -6.49 | +| explained_variance | 0.198 | +| learning_rate | 4.55e-05 | +| loss | -0.0277 | +| n_updates | 53136 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000286 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1422 | +| iterations | 9331 | +| time_elapsed | 13433 | +| total_timesteps | 19109888 | +| train/ | | +| approx_kl | 0.011589877 | +| clip_fraction | 0.341 | +| clip_range | 0.0702 | +| entropy_loss | -6.44 | +| explained_variance | 0.625 | +| learning_rate | 4.55e-05 | +| loss | -0.0351 | +| n_updates | 53140 | +| policy_gradient_loss | -0.0207 | +| value_loss | 9.82e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1422 | +| iterations | 9332 | +| time_elapsed | 13434 | +| total_timesteps | 19111936 | +| train/ | | +| approx_kl | 0.010219317 | +| clip_fraction | 0.324 | +| clip_range | 0.0702 | +| entropy_loss | -6.72 | +| explained_variance | 0.633 | +| learning_rate | 4.55e-05 | +| loss | -0.0319 | +| n_updates | 53144 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000116 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1422 | +| iterations | 9333 | +| time_elapsed | 13435 | +| total_timesteps | 19113984 | +| train/ | | +| approx_kl | 0.010267329 | +| clip_fraction | 0.301 | +| clip_range | 0.0702 | +| entropy_loss | -6.2 | +| explained_variance | 0.498 | +| learning_rate | 4.55e-05 | +| loss | -0.0289 | +| n_updates | 53148 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000205 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1422 | +| iterations | 9334 | +| time_elapsed | 13437 | +| total_timesteps | 19116032 | +| train/ | | +| approx_kl | 0.009761773 | +| clip_fraction | 0.32 | +| clip_range | 0.0702 | +| entropy_loss | -6.56 | +| explained_variance | 0.427 | +| learning_rate | 4.55e-05 | +| loss | -0.0301 | +| n_updates | 53152 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000163 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1422 | +| iterations | 9335 | +| time_elapsed | 13438 | +| total_timesteps | 19118080 | +| train/ | | +| approx_kl | 0.012576318 | +| clip_fraction | 0.333 | +| clip_range | 0.0702 | +| entropy_loss | -6.78 | +| explained_variance | 0.272 | +| learning_rate | 4.55e-05 | +| loss | -0.0315 | +| n_updates | 53156 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000219 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1422 | +| iterations | 9336 | +| time_elapsed | 13440 | +| total_timesteps | 19120128 | +| train/ | | +| approx_kl | 0.013354783 | +| clip_fraction | 0.336 | +| clip_range | 0.0702 | +| entropy_loss | -6.76 | +| explained_variance | 0.279 | +| learning_rate | 4.55e-05 | +| loss | -0.0355 | +| n_updates | 53160 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000114 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1422 | +| iterations | 9337 | +| time_elapsed | 13441 | +| total_timesteps | 19122176 | +| train/ | | +| approx_kl | 0.009306844 | +| clip_fraction | 0.313 | +| clip_range | 0.0702 | +| entropy_loss | -7 | +| explained_variance | -0.0125 | +| learning_rate | 4.55e-05 | +| loss | -0.0281 | +| n_updates | 53164 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000364 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1422 | +| iterations | 9338 | +| time_elapsed | 13443 | +| total_timesteps | 19124224 | +| train/ | | +| approx_kl | 0.012527404 | +| clip_fraction | 0.33 | +| clip_range | 0.0702 | +| entropy_loss | -6.62 | +| explained_variance | 0.468 | +| learning_rate | 4.55e-05 | +| loss | -0.0365 | +| n_updates | 53168 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000134 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1422 | +| iterations | 9339 | +| time_elapsed | 13444 | +| total_timesteps | 19126272 | +| train/ | | +| approx_kl | 0.0101042455 | +| clip_fraction | 0.342 | +| clip_range | 0.0702 | +| entropy_loss | -7.03 | +| explained_variance | 0.0607 | +| learning_rate | 4.55e-05 | +| loss | -0.0268 | +| n_updates | 53172 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000131 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1422 | +| iterations | 9340 | +| time_elapsed | 13446 | +| total_timesteps | 19128320 | +| train/ | | +| approx_kl | 0.014688123 | +| clip_fraction | 0.328 | +| clip_range | 0.0702 | +| entropy_loss | -6 | +| explained_variance | 0.559 | +| learning_rate | 4.55e-05 | +| loss | -0.0256 | +| n_updates | 53176 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000216 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1422 | +| iterations | 9341 | +| time_elapsed | 13447 | +| total_timesteps | 19130368 | +| train/ | | +| approx_kl | 0.011415223 | +| clip_fraction | 0.33 | +| clip_range | 0.0702 | +| entropy_loss | -5.71 | +| explained_variance | 0.659 | +| learning_rate | 4.55e-05 | +| loss | -0.0275 | +| n_updates | 53180 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.00016 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1422 | +| iterations | 9342 | +| time_elapsed | 13449 | +| total_timesteps | 19132416 | +| train/ | | +| approx_kl | 0.010120319 | +| clip_fraction | 0.347 | +| clip_range | 0.0702 | +| entropy_loss | -6.69 | +| explained_variance | 0.275 | +| learning_rate | 4.55e-05 | +| loss | -0.0289 | +| n_updates | 53184 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000149 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1422 | +| iterations | 9343 | +| time_elapsed | 13450 | +| total_timesteps | 19134464 | +| train/ | | +| approx_kl | 0.010644097 | +| clip_fraction | 0.346 | +| clip_range | 0.0702 | +| entropy_loss | -6.64 | +| explained_variance | 0.413 | +| learning_rate | 4.55e-05 | +| loss | -0.034 | +| n_updates | 53188 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000215 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1422 | +| iterations | 9344 | +| time_elapsed | 13451 | +| total_timesteps | 19136512 | +| train/ | | +| approx_kl | 0.012122365 | +| clip_fraction | 0.322 | +| clip_range | 0.0702 | +| entropy_loss | -6.69 | +| explained_variance | 0.224 | +| learning_rate | 4.55e-05 | +| loss | -0.0297 | +| n_updates | 53192 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000155 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1422 | +| iterations | 9345 | +| time_elapsed | 13453 | +| total_timesteps | 19138560 | +| train/ | | +| approx_kl | 0.011623874 | +| clip_fraction | 0.327 | +| clip_range | 0.0702 | +| entropy_loss | -6.8 | +| explained_variance | -0.188 | +| learning_rate | 4.55e-05 | +| loss | -0.0328 | +| n_updates | 53196 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000179 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1422 | +| iterations | 9346 | +| time_elapsed | 13454 | +| total_timesteps | 19140608 | +| train/ | | +| approx_kl | 0.010471011 | +| clip_fraction | 0.319 | +| clip_range | 0.0702 | +| entropy_loss | -6.37 | +| explained_variance | 0.489 | +| learning_rate | 4.55e-05 | +| loss | -0.0244 | +| n_updates | 53200 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000205 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1422 | +| iterations | 9347 | +| time_elapsed | 13456 | +| total_timesteps | 19142656 | +| train/ | | +| approx_kl | 0.01382652 | +| clip_fraction | 0.324 | +| clip_range | 0.0702 | +| entropy_loss | -6.36 | +| explained_variance | 0.383 | +| learning_rate | 4.55e-05 | +| loss | -0.0242 | +| n_updates | 53204 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000275 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1422 | +| iterations | 9348 | +| time_elapsed | 13457 | +| total_timesteps | 19144704 | +| train/ | | +| approx_kl | 0.011431707 | +| clip_fraction | 0.323 | +| clip_range | 0.0702 | +| entropy_loss | -6.67 | +| explained_variance | 0.303 | +| learning_rate | 4.55e-05 | +| loss | -0.0283 | +| n_updates | 53208 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000115 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1422 | +| iterations | 9349 | +| time_elapsed | 13459 | +| total_timesteps | 19146752 | +| train/ | | +| approx_kl | 0.013775161 | +| clip_fraction | 0.333 | +| clip_range | 0.0702 | +| entropy_loss | -6.29 | +| explained_variance | 0.41 | +| learning_rate | 4.55e-05 | +| loss | -0.03 | +| n_updates | 53212 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000303 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1422 | +| iterations | 9350 | +| time_elapsed | 13460 | +| total_timesteps | 19148800 | +| train/ | | +| approx_kl | 0.016552456 | +| clip_fraction | 0.38 | +| clip_range | 0.0702 | +| entropy_loss | -6.31 | +| explained_variance | 0.655 | +| learning_rate | 4.55e-05 | +| loss | -0.0408 | +| n_updates | 53216 | +| policy_gradient_loss | -0.0248 | +| value_loss | 7.31e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1422 | +| iterations | 9351 | +| time_elapsed | 13462 | +| total_timesteps | 19150848 | +| train/ | | +| approx_kl | 0.011462081 | +| clip_fraction | 0.324 | +| clip_range | 0.0702 | +| entropy_loss | -6.8 | +| explained_variance | -0.0386 | +| learning_rate | 4.55e-05 | +| loss | -0.0311 | +| n_updates | 53220 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000262 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1422 | +| iterations | 9352 | +| time_elapsed | 13463 | +| total_timesteps | 19152896 | +| train/ | | +| approx_kl | 0.020121392 | +| clip_fraction | 0.331 | +| clip_range | 0.0702 | +| entropy_loss | -6.56 | +| explained_variance | 0.349 | +| learning_rate | 4.55e-05 | +| loss | -0.0255 | +| n_updates | 53224 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000179 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1422 | +| iterations | 9353 | +| time_elapsed | 13465 | +| total_timesteps | 19154944 | +| train/ | | +| approx_kl | 0.011195932 | +| clip_fraction | 0.358 | +| clip_range | 0.0702 | +| entropy_loss | -6.5 | +| explained_variance | 0.578 | +| learning_rate | 4.55e-05 | +| loss | -0.0378 | +| n_updates | 53228 | +| policy_gradient_loss | -0.0205 | +| value_loss | 9.38e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1422 | +| iterations | 9354 | +| time_elapsed | 13466 | +| total_timesteps | 19156992 | +| train/ | | +| approx_kl | 0.011020121 | +| clip_fraction | 0.334 | +| clip_range | 0.0702 | +| entropy_loss | -6.72 | +| explained_variance | 0.238 | +| learning_rate | 4.55e-05 | +| loss | -0.0302 | +| n_updates | 53232 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000302 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1422 | +| iterations | 9355 | +| time_elapsed | 13467 | +| total_timesteps | 19159040 | +| train/ | | +| approx_kl | 0.014516699 | +| clip_fraction | 0.359 | +| clip_range | 0.0702 | +| entropy_loss | -6.44 | +| explained_variance | 0.48 | +| learning_rate | 4.55e-05 | +| loss | -0.0302 | +| n_updates | 53236 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.00016 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1422 | +| iterations | 9356 | +| time_elapsed | 13469 | +| total_timesteps | 19161088 | +| train/ | | +| approx_kl | 0.011699483 | +| clip_fraction | 0.351 | +| clip_range | 0.0702 | +| entropy_loss | -6.69 | +| explained_variance | 0.282 | +| learning_rate | 4.54e-05 | +| loss | -0.036 | +| n_updates | 53240 | +| policy_gradient_loss | -0.0221 | +| value_loss | 0.000106 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1422 | +| iterations | 9357 | +| time_elapsed | 13470 | +| total_timesteps | 19163136 | +| train/ | | +| approx_kl | 0.013995107 | +| clip_fraction | 0.357 | +| clip_range | 0.0702 | +| entropy_loss | -6.48 | +| explained_variance | 0.417 | +| learning_rate | 4.54e-05 | +| loss | -0.0307 | +| n_updates | 53244 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000166 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1422 | +| iterations | 9358 | +| time_elapsed | 13472 | +| total_timesteps | 19165184 | +| train/ | | +| approx_kl | 0.012095155 | +| clip_fraction | 0.342 | +| clip_range | 0.0702 | +| entropy_loss | -6.4 | +| explained_variance | 0.644 | +| learning_rate | 4.54e-05 | +| loss | -0.0296 | +| n_updates | 53248 | +| policy_gradient_loss | -0.0213 | +| value_loss | 9.13e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1422 | +| iterations | 9359 | +| time_elapsed | 13473 | +| total_timesteps | 19167232 | +| train/ | | +| approx_kl | 0.014491685 | +| clip_fraction | 0.424 | +| clip_range | 0.0702 | +| entropy_loss | -6.33 | +| explained_variance | 0.45 | +| learning_rate | 4.54e-05 | +| loss | -0.0438 | +| n_updates | 53252 | +| policy_gradient_loss | -0.0277 | +| value_loss | 5.09e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1422 | +| iterations | 9360 | +| time_elapsed | 13475 | +| total_timesteps | 19169280 | +| train/ | | +| approx_kl | 0.015413055 | +| clip_fraction | 0.325 | +| clip_range | 0.0702 | +| entropy_loss | -6.6 | +| explained_variance | 0.457 | +| learning_rate | 4.54e-05 | +| loss | -0.0281 | +| n_updates | 53256 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000161 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1422 | +| iterations | 9361 | +| time_elapsed | 13476 | +| total_timesteps | 19171328 | +| train/ | | +| approx_kl | 0.013420853 | +| clip_fraction | 0.352 | +| clip_range | 0.0702 | +| entropy_loss | -6.29 | +| explained_variance | 0.659 | +| learning_rate | 4.54e-05 | +| loss | -0.034 | +| n_updates | 53260 | +| policy_gradient_loss | -0.0212 | +| value_loss | 7.82e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1422 | +| iterations | 9362 | +| time_elapsed | 13477 | +| total_timesteps | 19173376 | +| train/ | | +| approx_kl | 0.013058495 | +| clip_fraction | 0.331 | +| clip_range | 0.0702 | +| entropy_loss | -5.99 | +| explained_variance | 0.636 | +| learning_rate | 4.54e-05 | +| loss | -0.0293 | +| n_updates | 53264 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000136 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1422 | +| iterations | 9363 | +| time_elapsed | 13479 | +| total_timesteps | 19175424 | +| train/ | | +| approx_kl | 0.01206899 | +| clip_fraction | 0.33 | +| clip_range | 0.0702 | +| entropy_loss | -6.69 | +| explained_variance | 0.0695 | +| learning_rate | 4.54e-05 | +| loss | -0.0335 | +| n_updates | 53268 | +| policy_gradient_loss | -0.0186 | +| value_loss | 9.24e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1422 | +| iterations | 9364 | +| time_elapsed | 13480 | +| total_timesteps | 19177472 | +| train/ | | +| approx_kl | 0.011934392 | +| clip_fraction | 0.345 | +| clip_range | 0.0702 | +| entropy_loss | -6.54 | +| explained_variance | 0.341 | +| learning_rate | 4.54e-05 | +| loss | -0.0309 | +| n_updates | 53272 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000124 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1422 | +| iterations | 9365 | +| time_elapsed | 13482 | +| total_timesteps | 19179520 | +| train/ | | +| approx_kl | 0.011550103 | +| clip_fraction | 0.342 | +| clip_range | 0.0702 | +| entropy_loss | -6.78 | +| explained_variance | 0.339 | +| learning_rate | 4.54e-05 | +| loss | -0.0286 | +| n_updates | 53276 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000151 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1422 | +| iterations | 9366 | +| time_elapsed | 13483 | +| total_timesteps | 19181568 | +| train/ | | +| approx_kl | 0.010894279 | +| clip_fraction | 0.341 | +| clip_range | 0.0702 | +| entropy_loss | -6.6 | +| explained_variance | 0.685 | +| learning_rate | 4.54e-05 | +| loss | -0.0379 | +| n_updates | 53280 | +| policy_gradient_loss | -0.0216 | +| value_loss | 7.84e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1422 | +| iterations | 9367 | +| time_elapsed | 13485 | +| total_timesteps | 19183616 | +| train/ | | +| approx_kl | 0.014133634 | +| clip_fraction | 0.337 | +| clip_range | 0.0702 | +| entropy_loss | -6.46 | +| explained_variance | 0.518 | +| learning_rate | 4.54e-05 | +| loss | -0.0273 | +| n_updates | 53284 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000123 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1422 | +| iterations | 9368 | +| time_elapsed | 13486 | +| total_timesteps | 19185664 | +| train/ | | +| approx_kl | 0.012970416 | +| clip_fraction | 0.338 | +| clip_range | 0.0702 | +| entropy_loss | -6.59 | +| explained_variance | 0.229 | +| learning_rate | 4.54e-05 | +| loss | -0.0311 | +| n_updates | 53288 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000124 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1422 | +| iterations | 9369 | +| time_elapsed | 13487 | +| total_timesteps | 19187712 | +| train/ | | +| approx_kl | 0.013382166 | +| clip_fraction | 0.342 | +| clip_range | 0.0702 | +| entropy_loss | -6.4 | +| explained_variance | 0.684 | +| learning_rate | 4.54e-05 | +| loss | -0.0298 | +| n_updates | 53292 | +| policy_gradient_loss | -0.0194 | +| value_loss | 6.94e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1422 | +| iterations | 9370 | +| time_elapsed | 13489 | +| total_timesteps | 19189760 | +| train/ | | +| approx_kl | 0.015300596 | +| clip_fraction | 0.342 | +| clip_range | 0.0702 | +| entropy_loss | -6.18 | +| explained_variance | 0.516 | +| learning_rate | 4.54e-05 | +| loss | -0.0245 | +| n_updates | 53296 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000162 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1422 | +| iterations | 9371 | +| time_elapsed | 13490 | +| total_timesteps | 19191808 | +| train/ | | +| approx_kl | 0.013099269 | +| clip_fraction | 0.34 | +| clip_range | 0.0702 | +| entropy_loss | -5.81 | +| explained_variance | 0.809 | +| learning_rate | 4.54e-05 | +| loss | -0.0296 | +| n_updates | 53300 | +| policy_gradient_loss | -0.0183 | +| value_loss | 8.22e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1422 | +| iterations | 9372 | +| time_elapsed | 13492 | +| total_timesteps | 19193856 | +| train/ | | +| approx_kl | 0.012656931 | +| clip_fraction | 0.326 | +| clip_range | 0.0702 | +| entropy_loss | -6.79 | +| explained_variance | -0.0316 | +| learning_rate | 4.54e-05 | +| loss | -0.0316 | +| n_updates | 53304 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000161 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1422 | +| iterations | 9373 | +| time_elapsed | 13493 | +| total_timesteps | 19195904 | +| train/ | | +| approx_kl | 0.011546118 | +| clip_fraction | 0.3 | +| clip_range | 0.0702 | +| entropy_loss | -6.59 | +| explained_variance | 0.506 | +| learning_rate | 4.54e-05 | +| loss | -0.0268 | +| n_updates | 53308 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000151 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1422 | +| iterations | 9374 | +| time_elapsed | 13495 | +| total_timesteps | 19197952 | +| train/ | | +| approx_kl | 0.013572322 | +| clip_fraction | 0.338 | +| clip_range | 0.0702 | +| entropy_loss | -6.45 | +| explained_variance | 0.498 | +| learning_rate | 4.54e-05 | +| loss | -0.0317 | +| n_updates | 53312 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000154 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1422 | +| iterations | 9375 | +| time_elapsed | 13496 | +| total_timesteps | 19200000 | +| train/ | | +| approx_kl | 0.016555868 | +| clip_fraction | 0.371 | +| clip_range | 0.0702 | +| entropy_loss | -6.6 | +| explained_variance | -0.144 | +| learning_rate | 4.54e-05 | +| loss | -0.0318 | +| n_updates | 53316 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.00011 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1422 | +| iterations | 9376 | +| time_elapsed | 13498 | +| total_timesteps | 19202048 | +| train/ | | +| approx_kl | 0.012417556 | +| clip_fraction | 0.368 | +| clip_range | 0.0702 | +| entropy_loss | -6.96 | +| explained_variance | 0.128 | +| learning_rate | 4.54e-05 | +| loss | -0.0346 | +| n_updates | 53320 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000104 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1422 | +| iterations | 9377 | +| time_elapsed | 13499 | +| total_timesteps | 19204096 | +| train/ | | +| approx_kl | 0.013259001 | +| clip_fraction | 0.367 | +| clip_range | 0.0702 | +| entropy_loss | -6.89 | +| explained_variance | -0.13 | +| learning_rate | 4.54e-05 | +| loss | -0.0351 | +| n_updates | 53324 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000102 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1422 | +| iterations | 9378 | +| time_elapsed | 13500 | +| total_timesteps | 19206144 | +| train/ | | +| approx_kl | 0.010616837 | +| clip_fraction | 0.335 | +| clip_range | 0.0702 | +| entropy_loss | -6.79 | +| explained_variance | 0.186 | +| learning_rate | 4.54e-05 | +| loss | -0.0315 | +| n_updates | 53328 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000255 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1422 | +| iterations | 9379 | +| time_elapsed | 13502 | +| total_timesteps | 19208192 | +| train/ | | +| approx_kl | 0.011971772 | +| clip_fraction | 0.323 | +| clip_range | 0.0702 | +| entropy_loss | -6.4 | +| explained_variance | 0.581 | +| learning_rate | 4.54e-05 | +| loss | -0.0344 | +| n_updates | 53332 | +| policy_gradient_loss | -0.0197 | +| value_loss | 9.98e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1422 | +| iterations | 9380 | +| time_elapsed | 13503 | +| total_timesteps | 19210240 | +| train/ | | +| approx_kl | 0.013697458 | +| clip_fraction | 0.335 | +| clip_range | 0.0702 | +| entropy_loss | -6.61 | +| explained_variance | 0.421 | +| learning_rate | 4.54e-05 | +| loss | -0.0318 | +| n_updates | 53336 | +| policy_gradient_loss | -0.022 | +| value_loss | 9.18e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1422 | +| iterations | 9381 | +| time_elapsed | 13505 | +| total_timesteps | 19212288 | +| train/ | | +| approx_kl | 0.015242234 | +| clip_fraction | 0.331 | +| clip_range | 0.0702 | +| entropy_loss | -5.74 | +| explained_variance | 0.741 | +| learning_rate | 4.54e-05 | +| loss | -0.0247 | +| n_updates | 53340 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000114 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1422 | +| iterations | 9382 | +| time_elapsed | 13506 | +| total_timesteps | 19214336 | +| train/ | | +| approx_kl | 0.014323626 | +| clip_fraction | 0.37 | +| clip_range | 0.0702 | +| entropy_loss | -6.06 | +| explained_variance | 0.562 | +| learning_rate | 4.54e-05 | +| loss | -0.0393 | +| n_updates | 53344 | +| policy_gradient_loss | -0.0218 | +| value_loss | 7.1e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1422 | +| iterations | 9383 | +| time_elapsed | 13508 | +| total_timesteps | 19216384 | +| train/ | | +| approx_kl | 0.017619137 | +| clip_fraction | 0.378 | +| clip_range | 0.0702 | +| entropy_loss | -6.15 | +| explained_variance | 0.674 | +| learning_rate | 4.54e-05 | +| loss | -0.0307 | +| n_updates | 53348 | +| policy_gradient_loss | -0.0197 | +| value_loss | 7.59e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1422 | +| iterations | 9384 | +| time_elapsed | 13509 | +| total_timesteps | 19218432 | +| train/ | | +| approx_kl | 0.016362472 | +| clip_fraction | 0.325 | +| clip_range | 0.0702 | +| entropy_loss | -6.45 | +| explained_variance | 0.489 | +| learning_rate | 4.54e-05 | +| loss | -0.0233 | +| n_updates | 53352 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000143 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1422 | +| iterations | 9385 | +| time_elapsed | 13510 | +| total_timesteps | 19220480 | +| train/ | | +| approx_kl | 0.014672251 | +| clip_fraction | 0.347 | +| clip_range | 0.0702 | +| entropy_loss | -6.57 | +| explained_variance | -0.0875 | +| learning_rate | 4.54e-05 | +| loss | -0.0357 | +| n_updates | 53356 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000136 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1422 | +| iterations | 9386 | +| time_elapsed | 13512 | +| total_timesteps | 19222528 | +| train/ | | +| approx_kl | 0.01223091 | +| clip_fraction | 0.332 | +| clip_range | 0.0702 | +| entropy_loss | -6.6 | +| explained_variance | 0.357 | +| learning_rate | 4.54e-05 | +| loss | -0.0311 | +| n_updates | 53360 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000249 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1422 | +| iterations | 9387 | +| time_elapsed | 13513 | +| total_timesteps | 19224576 | +| train/ | | +| approx_kl | 0.014281331 | +| clip_fraction | 0.364 | +| clip_range | 0.0702 | +| entropy_loss | -6.88 | +| explained_variance | -0.412 | +| learning_rate | 4.54e-05 | +| loss | -0.0354 | +| n_updates | 53364 | +| policy_gradient_loss | -0.0236 | +| value_loss | 0.000104 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1422 | +| iterations | 9388 | +| time_elapsed | 13515 | +| total_timesteps | 19226624 | +| train/ | | +| approx_kl | 0.011394197 | +| clip_fraction | 0.309 | +| clip_range | 0.0702 | +| entropy_loss | -6.55 | +| explained_variance | 0.668 | +| learning_rate | 4.54e-05 | +| loss | -0.0322 | +| n_updates | 53368 | +| policy_gradient_loss | -0.0177 | +| value_loss | 9.09e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1422 | +| iterations | 9389 | +| time_elapsed | 13516 | +| total_timesteps | 19228672 | +| train/ | | +| approx_kl | 0.012264625 | +| clip_fraction | 0.344 | +| clip_range | 0.0702 | +| entropy_loss | -6.11 | +| explained_variance | 0.356 | +| learning_rate | 4.54e-05 | +| loss | -0.0313 | +| n_updates | 53372 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.00024 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1422 | +| iterations | 9390 | +| time_elapsed | 13518 | +| total_timesteps | 19230720 | +| train/ | | +| approx_kl | 0.011056892 | +| clip_fraction | 0.344 | +| clip_range | 0.0702 | +| entropy_loss | -6.68 | +| explained_variance | 0.452 | +| learning_rate | 4.54e-05 | +| loss | -0.028 | +| n_updates | 53376 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000142 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1422 | +| iterations | 9391 | +| time_elapsed | 13519 | +| total_timesteps | 19232768 | +| train/ | | +| approx_kl | 0.009734865 | +| clip_fraction | 0.344 | +| clip_range | 0.0702 | +| entropy_loss | -6.66 | +| explained_variance | 0.435 | +| learning_rate | 4.54e-05 | +| loss | -0.0374 | +| n_updates | 53380 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.00011 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1422 | +| iterations | 9392 | +| time_elapsed | 13520 | +| total_timesteps | 19234816 | +| train/ | | +| approx_kl | 0.00999503 | +| clip_fraction | 0.337 | +| clip_range | 0.0702 | +| entropy_loss | -6.55 | +| explained_variance | 0.593 | +| learning_rate | 4.54e-05 | +| loss | -0.034 | +| n_updates | 53384 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000115 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1422 | +| iterations | 9393 | +| time_elapsed | 13522 | +| total_timesteps | 19236864 | +| train/ | | +| approx_kl | 0.0107976105 | +| clip_fraction | 0.342 | +| clip_range | 0.0702 | +| entropy_loss | -6.45 | +| explained_variance | 0.655 | +| learning_rate | 4.54e-05 | +| loss | -0.0358 | +| n_updates | 53388 | +| policy_gradient_loss | -0.0201 | +| value_loss | 8.52e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1422 | +| iterations | 9394 | +| time_elapsed | 13523 | +| total_timesteps | 19238912 | +| train/ | | +| approx_kl | 0.012185081 | +| clip_fraction | 0.347 | +| clip_range | 0.0702 | +| entropy_loss | -6.32 | +| explained_variance | 0.368 | +| learning_rate | 4.54e-05 | +| loss | -0.0284 | +| n_updates | 53392 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000234 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1422 | +| iterations | 9395 | +| time_elapsed | 13525 | +| total_timesteps | 19240960 | +| train/ | | +| approx_kl | 0.013917202 | +| clip_fraction | 0.359 | +| clip_range | 0.0702 | +| entropy_loss | -5.96 | +| explained_variance | 0.678 | +| learning_rate | 4.54e-05 | +| loss | -0.0268 | +| n_updates | 53396 | +| policy_gradient_loss | -0.0197 | +| value_loss | 9.98e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1422 | +| iterations | 9396 | +| time_elapsed | 13526 | +| total_timesteps | 19243008 | +| train/ | | +| approx_kl | 0.012821445 | +| clip_fraction | 0.353 | +| clip_range | 0.0702 | +| entropy_loss | -6.49 | +| explained_variance | 0.292 | +| learning_rate | 4.54e-05 | +| loss | -0.0342 | +| n_updates | 53400 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000105 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1422 | +| iterations | 9397 | +| time_elapsed | 13528 | +| total_timesteps | 19245056 | +| train/ | | +| approx_kl | 0.011261899 | +| clip_fraction | 0.327 | +| clip_range | 0.0702 | +| entropy_loss | -6.72 | +| explained_variance | 0.328 | +| learning_rate | 4.54e-05 | +| loss | -0.0273 | +| n_updates | 53404 | +| policy_gradient_loss | -0.0186 | +| value_loss | 9.6e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1422 | +| iterations | 9398 | +| time_elapsed | 13529 | +| total_timesteps | 19247104 | +| train/ | | +| approx_kl | 0.013046883 | +| clip_fraction | 0.357 | +| clip_range | 0.0702 | +| entropy_loss | -6.71 | +| explained_variance | 0.433 | +| learning_rate | 4.54e-05 | +| loss | -0.04 | +| n_updates | 53408 | +| policy_gradient_loss | -0.0203 | +| value_loss | 8.45e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1422 | +| iterations | 9399 | +| time_elapsed | 13531 | +| total_timesteps | 19249152 | +| train/ | | +| approx_kl | 0.011117416 | +| clip_fraction | 0.317 | +| clip_range | 0.0702 | +| entropy_loss | -6.63 | +| explained_variance | 0.456 | +| learning_rate | 4.54e-05 | +| loss | -0.0289 | +| n_updates | 53412 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000165 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1422 | +| iterations | 9400 | +| time_elapsed | 13532 | +| total_timesteps | 19251200 | +| train/ | | +| approx_kl | 0.012837763 | +| clip_fraction | 0.333 | +| clip_range | 0.0702 | +| entropy_loss | -6.81 | +| explained_variance | 0.345 | +| learning_rate | 4.54e-05 | +| loss | -0.0338 | +| n_updates | 53416 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000131 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1422 | +| iterations | 9401 | +| time_elapsed | 13534 | +| total_timesteps | 19253248 | +| train/ | | +| approx_kl | 0.008966936 | +| clip_fraction | 0.298 | +| clip_range | 0.0702 | +| entropy_loss | -7.01 | +| explained_variance | 0.185 | +| learning_rate | 4.54e-05 | +| loss | -0.0321 | +| n_updates | 53420 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000219 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1422 | +| iterations | 9402 | +| time_elapsed | 13535 | +| total_timesteps | 19255296 | +| train/ | | +| approx_kl | 0.012621537 | +| clip_fraction | 0.335 | +| clip_range | 0.0702 | +| entropy_loss | -6.24 | +| explained_variance | 0.596 | +| learning_rate | 4.54e-05 | +| loss | -0.033 | +| n_updates | 53424 | +| policy_gradient_loss | -0.0196 | +| value_loss | 8.65e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1422 | +| iterations | 9403 | +| time_elapsed | 13537 | +| total_timesteps | 19257344 | +| train/ | | +| approx_kl | 0.010990562 | +| clip_fraction | 0.322 | +| clip_range | 0.0702 | +| entropy_loss | -6.79 | +| explained_variance | 0.0634 | +| learning_rate | 4.54e-05 | +| loss | -0.0263 | +| n_updates | 53428 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000174 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.315 | +| time/ | | +| fps | 1422 | +| iterations | 9404 | +| time_elapsed | 13538 | +| total_timesteps | 19259392 | +| train/ | | +| approx_kl | 0.01031398 | +| clip_fraction | 0.316 | +| clip_range | 0.0702 | +| entropy_loss | -5.8 | +| explained_variance | 0.465 | +| learning_rate | 4.54e-05 | +| loss | -0.0315 | +| n_updates | 53432 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000287 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1422 | +| iterations | 9405 | +| time_elapsed | 13539 | +| total_timesteps | 19261440 | +| train/ | | +| approx_kl | 0.013327028 | +| clip_fraction | 0.362 | +| clip_range | 0.0702 | +| entropy_loss | -5.96 | +| explained_variance | 0.5 | +| learning_rate | 4.54e-05 | +| loss | -0.035 | +| n_updates | 53436 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000108 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1422 | +| iterations | 9406 | +| time_elapsed | 13541 | +| total_timesteps | 19263488 | +| train/ | | +| approx_kl | 0.011607182 | +| clip_fraction | 0.326 | +| clip_range | 0.0702 | +| entropy_loss | -6.33 | +| explained_variance | 0.311 | +| learning_rate | 4.54e-05 | +| loss | -0.0291 | +| n_updates | 53440 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000352 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1422 | +| iterations | 9407 | +| time_elapsed | 13542 | +| total_timesteps | 19265536 | +| train/ | | +| approx_kl | 0.015194949 | +| clip_fraction | 0.353 | +| clip_range | 0.0702 | +| entropy_loss | -6.13 | +| explained_variance | 0.418 | +| learning_rate | 4.54e-05 | +| loss | -0.0365 | +| n_updates | 53444 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000194 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1422 | +| iterations | 9408 | +| time_elapsed | 13544 | +| total_timesteps | 19267584 | +| train/ | | +| approx_kl | 0.012524394 | +| clip_fraction | 0.344 | +| clip_range | 0.0702 | +| entropy_loss | -6.22 | +| explained_variance | 0.19 | +| learning_rate | 4.54e-05 | +| loss | -0.0309 | +| n_updates | 53448 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000193 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1422 | +| iterations | 9409 | +| time_elapsed | 13545 | +| total_timesteps | 19269632 | +| train/ | | +| approx_kl | 0.01253515 | +| clip_fraction | 0.352 | +| clip_range | 0.0702 | +| entropy_loss | -6.63 | +| explained_variance | 0.277 | +| learning_rate | 4.54e-05 | +| loss | -0.0371 | +| n_updates | 53452 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000134 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1422 | +| iterations | 9410 | +| time_elapsed | 13547 | +| total_timesteps | 19271680 | +| train/ | | +| approx_kl | 0.010316417 | +| clip_fraction | 0.316 | +| clip_range | 0.0702 | +| entropy_loss | -7 | +| explained_variance | 0.121 | +| learning_rate | 4.54e-05 | +| loss | -0.0251 | +| n_updates | 53456 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000261 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1422 | +| iterations | 9411 | +| time_elapsed | 13548 | +| total_timesteps | 19273728 | +| train/ | | +| approx_kl | 0.010779917 | +| clip_fraction | 0.335 | +| clip_range | 0.0702 | +| entropy_loss | -6.83 | +| explained_variance | 0.137 | +| learning_rate | 4.54e-05 | +| loss | -0.0335 | +| n_updates | 53460 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000298 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 1422 | +| iterations | 9412 | +| time_elapsed | 13550 | +| total_timesteps | 19275776 | +| train/ | | +| approx_kl | 0.013516555 | +| clip_fraction | 0.352 | +| clip_range | 0.0702 | +| entropy_loss | -6.77 | +| explained_variance | 0.358 | +| learning_rate | 4.54e-05 | +| loss | -0.0339 | +| n_updates | 53464 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.00021 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1422 | +| iterations | 9413 | +| time_elapsed | 13551 | +| total_timesteps | 19277824 | +| train/ | | +| approx_kl | 0.013111081 | +| clip_fraction | 0.342 | +| clip_range | 0.0702 | +| entropy_loss | -6.27 | +| explained_variance | 0.258 | +| learning_rate | 4.54e-05 | +| loss | -0.0238 | +| n_updates | 53468 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000298 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1422 | +| iterations | 9414 | +| time_elapsed | 13552 | +| total_timesteps | 19279872 | +| train/ | | +| approx_kl | 0.010519141 | +| clip_fraction | 0.315 | +| clip_range | 0.0702 | +| entropy_loss | -6.01 | +| explained_variance | 0.447 | +| learning_rate | 4.54e-05 | +| loss | -0.0347 | +| n_updates | 53472 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.00025 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1422 | +| iterations | 9415 | +| time_elapsed | 13554 | +| total_timesteps | 19281920 | +| train/ | | +| approx_kl | 0.011113891 | +| clip_fraction | 0.342 | +| clip_range | 0.0702 | +| entropy_loss | -6.01 | +| explained_variance | 0.452 | +| learning_rate | 4.54e-05 | +| loss | -0.033 | +| n_updates | 53476 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000331 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1422 | +| iterations | 9416 | +| time_elapsed | 13555 | +| total_timesteps | 19283968 | +| train/ | | +| approx_kl | 0.01572262 | +| clip_fraction | 0.363 | +| clip_range | 0.0702 | +| entropy_loss | -6.31 | +| explained_variance | 0.257 | +| learning_rate | 4.54e-05 | +| loss | -0.0329 | +| n_updates | 53480 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000157 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1422 | +| iterations | 9417 | +| time_elapsed | 13557 | +| total_timesteps | 19286016 | +| train/ | | +| approx_kl | 0.012148365 | +| clip_fraction | 0.333 | +| clip_range | 0.0702 | +| entropy_loss | -6.52 | +| explained_variance | 0.264 | +| learning_rate | 4.54e-05 | +| loss | -0.028 | +| n_updates | 53484 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000154 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1422 | +| iterations | 9418 | +| time_elapsed | 13558 | +| total_timesteps | 19288064 | +| train/ | | +| approx_kl | 0.013419446 | +| clip_fraction | 0.358 | +| clip_range | 0.0702 | +| entropy_loss | -6.44 | +| explained_variance | 0.206 | +| learning_rate | 4.54e-05 | +| loss | -0.0388 | +| n_updates | 53488 | +| policy_gradient_loss | -0.0236 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1422 | +| iterations | 9419 | +| time_elapsed | 13560 | +| total_timesteps | 19290112 | +| train/ | | +| approx_kl | 0.014447937 | +| clip_fraction | 0.339 | +| clip_range | 0.0702 | +| entropy_loss | -6.65 | +| explained_variance | 0.296 | +| learning_rate | 4.54e-05 | +| loss | -0.0307 | +| n_updates | 53492 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000134 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1422 | +| iterations | 9420 | +| time_elapsed | 13561 | +| total_timesteps | 19292160 | +| train/ | | +| approx_kl | 0.012328774 | +| clip_fraction | 0.306 | +| clip_range | 0.0702 | +| entropy_loss | -6.51 | +| explained_variance | 0.253 | +| learning_rate | 4.54e-05 | +| loss | -0.029 | +| n_updates | 53496 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000314 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1422 | +| iterations | 9421 | +| time_elapsed | 13563 | +| total_timesteps | 19294208 | +| train/ | | +| approx_kl | 0.0123773385 | +| clip_fraction | 0.321 | +| clip_range | 0.0702 | +| entropy_loss | -6.13 | +| explained_variance | 0.403 | +| learning_rate | 4.54e-05 | +| loss | -0.0246 | +| n_updates | 53500 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000237 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1422 | +| iterations | 9422 | +| time_elapsed | 13564 | +| total_timesteps | 19296256 | +| train/ | | +| approx_kl | 0.010667339 | +| clip_fraction | 0.331 | +| clip_range | 0.0702 | +| entropy_loss | -6.15 | +| explained_variance | 0.515 | +| learning_rate | 4.54e-05 | +| loss | -0.0322 | +| n_updates | 53504 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000216 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1422 | +| iterations | 9423 | +| time_elapsed | 13566 | +| total_timesteps | 19298304 | +| train/ | | +| approx_kl | 0.014164948 | +| clip_fraction | 0.346 | +| clip_range | 0.0702 | +| entropy_loss | -6.87 | +| explained_variance | -0.141 | +| learning_rate | 4.54e-05 | +| loss | -0.0358 | +| n_updates | 53508 | +| policy_gradient_loss | -0.0223 | +| value_loss | 0.000169 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1422 | +| iterations | 9424 | +| time_elapsed | 13567 | +| total_timesteps | 19300352 | +| train/ | | +| approx_kl | 0.010489015 | +| clip_fraction | 0.325 | +| clip_range | 0.0702 | +| entropy_loss | -6.34 | +| explained_variance | 0.496 | +| learning_rate | 4.54e-05 | +| loss | -0.0298 | +| n_updates | 53512 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.00025 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1422 | +| iterations | 9425 | +| time_elapsed | 13569 | +| total_timesteps | 19302400 | +| train/ | | +| approx_kl | 0.011961739 | +| clip_fraction | 0.354 | +| clip_range | 0.0702 | +| entropy_loss | -6.28 | +| explained_variance | 0.587 | +| learning_rate | 4.54e-05 | +| loss | -0.0372 | +| n_updates | 53516 | +| policy_gradient_loss | -0.0241 | +| value_loss | 0.000101 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1422 | +| iterations | 9426 | +| time_elapsed | 13570 | +| total_timesteps | 19304448 | +| train/ | | +| approx_kl | 0.011188626 | +| clip_fraction | 0.323 | +| clip_range | 0.0702 | +| entropy_loss | -7 | +| explained_variance | -0.0176 | +| learning_rate | 4.54e-05 | +| loss | -0.0302 | +| n_updates | 53520 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000164 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1422 | +| iterations | 9427 | +| time_elapsed | 13571 | +| total_timesteps | 19306496 | +| train/ | | +| approx_kl | 0.012995614 | +| clip_fraction | 0.381 | +| clip_range | 0.0702 | +| entropy_loss | -6.98 | +| explained_variance | 0.582 | +| learning_rate | 4.54e-05 | +| loss | -0.0405 | +| n_updates | 53524 | +| policy_gradient_loss | -0.0268 | +| value_loss | 5.16e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1422 | +| iterations | 9428 | +| time_elapsed | 13573 | +| total_timesteps | 19308544 | +| train/ | | +| approx_kl | 0.012616674 | +| clip_fraction | 0.325 | +| clip_range | 0.0702 | +| entropy_loss | -6.4 | +| explained_variance | 0.455 | +| learning_rate | 4.54e-05 | +| loss | -0.0276 | +| n_updates | 53528 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000265 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1422 | +| iterations | 9429 | +| time_elapsed | 13574 | +| total_timesteps | 19310592 | +| train/ | | +| approx_kl | 0.011498447 | +| clip_fraction | 0.324 | +| clip_range | 0.0702 | +| entropy_loss | -6.33 | +| explained_variance | 0.332 | +| learning_rate | 4.54e-05 | +| loss | -0.023 | +| n_updates | 53532 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000232 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1422 | +| iterations | 9430 | +| time_elapsed | 13576 | +| total_timesteps | 19312640 | +| train/ | | +| approx_kl | 0.014285651 | +| clip_fraction | 0.351 | +| clip_range | 0.0702 | +| entropy_loss | -6.53 | +| explained_variance | 0.49 | +| learning_rate | 4.54e-05 | +| loss | -0.0349 | +| n_updates | 53536 | +| policy_gradient_loss | -0.023 | +| value_loss | 0.000106 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1422 | +| iterations | 9431 | +| time_elapsed | 13577 | +| total_timesteps | 19314688 | +| train/ | | +| approx_kl | 0.01153083 | +| clip_fraction | 0.327 | +| clip_range | 0.0702 | +| entropy_loss | -6.78 | +| explained_variance | 0.231 | +| learning_rate | 4.54e-05 | +| loss | -0.0259 | +| n_updates | 53540 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.00023 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1422 | +| iterations | 9432 | +| time_elapsed | 13579 | +| total_timesteps | 19316736 | +| train/ | | +| approx_kl | 0.0132459635 | +| clip_fraction | 0.372 | +| clip_range | 0.0702 | +| entropy_loss | -6.16 | +| explained_variance | 0.752 | +| learning_rate | 4.54e-05 | +| loss | -0.0302 | +| n_updates | 53544 | +| policy_gradient_loss | -0.0222 | +| value_loss | 9.35e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1422 | +| iterations | 9433 | +| time_elapsed | 13580 | +| total_timesteps | 19318784 | +| train/ | | +| approx_kl | 0.011361951 | +| clip_fraction | 0.332 | +| clip_range | 0.0702 | +| entropy_loss | -6.6 | +| explained_variance | 0.266 | +| learning_rate | 4.54e-05 | +| loss | -0.032 | +| n_updates | 53548 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000216 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1422 | +| iterations | 9434 | +| time_elapsed | 13582 | +| total_timesteps | 19320832 | +| train/ | | +| approx_kl | 0.011664353 | +| clip_fraction | 0.356 | +| clip_range | 0.0702 | +| entropy_loss | -6.75 | +| explained_variance | 0.162 | +| learning_rate | 4.54e-05 | +| loss | -0.032 | +| n_updates | 53552 | +| policy_gradient_loss | -0.0219 | +| value_loss | 0.000215 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1422 | +| iterations | 9435 | +| time_elapsed | 13583 | +| total_timesteps | 19322880 | +| train/ | | +| approx_kl | 0.010873538 | +| clip_fraction | 0.344 | +| clip_range | 0.0702 | +| entropy_loss | -6.59 | +| explained_variance | 0.536 | +| learning_rate | 4.54e-05 | +| loss | -0.032 | +| n_updates | 53556 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000122 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1422 | +| iterations | 9436 | +| time_elapsed | 13585 | +| total_timesteps | 19324928 | +| train/ | | +| approx_kl | 0.011395665 | +| clip_fraction | 0.341 | +| clip_range | 0.0702 | +| entropy_loss | -6.52 | +| explained_variance | 0.394 | +| learning_rate | 4.54e-05 | +| loss | -0.0288 | +| n_updates | 53560 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000101 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1422 | +| iterations | 9437 | +| time_elapsed | 13586 | +| total_timesteps | 19326976 | +| train/ | | +| approx_kl | 0.010444715 | +| clip_fraction | 0.312 | +| clip_range | 0.0702 | +| entropy_loss | -6.52 | +| explained_variance | 0.274 | +| learning_rate | 4.54e-05 | +| loss | -0.0239 | +| n_updates | 53564 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000169 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1422 | +| iterations | 9438 | +| time_elapsed | 13587 | +| total_timesteps | 19329024 | +| train/ | | +| approx_kl | 0.011894825 | +| clip_fraction | 0.321 | +| clip_range | 0.0702 | +| entropy_loss | -6.58 | +| explained_variance | 0.202 | +| learning_rate | 4.54e-05 | +| loss | -0.0285 | +| n_updates | 53568 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000314 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1422 | +| iterations | 9439 | +| time_elapsed | 13589 | +| total_timesteps | 19331072 | +| train/ | | +| approx_kl | 0.012850642 | +| clip_fraction | 0.331 | +| clip_range | 0.0702 | +| entropy_loss | -6.55 | +| explained_variance | 0.394 | +| learning_rate | 4.54e-05 | +| loss | -0.0254 | +| n_updates | 53572 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000219 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1422 | +| iterations | 9440 | +| time_elapsed | 13590 | +| total_timesteps | 19333120 | +| train/ | | +| approx_kl | 0.009958068 | +| clip_fraction | 0.29 | +| clip_range | 0.0702 | +| entropy_loss | -5.72 | +| explained_variance | 0.422 | +| learning_rate | 4.54e-05 | +| loss | -0.0228 | +| n_updates | 53576 | +| policy_gradient_loss | -0.0135 | +| value_loss | 0.000394 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1422 | +| iterations | 9441 | +| time_elapsed | 13592 | +| total_timesteps | 19335168 | +| train/ | | +| approx_kl | 0.012066675 | +| clip_fraction | 0.366 | +| clip_range | 0.0702 | +| entropy_loss | -6.35 | +| explained_variance | 0.204 | +| learning_rate | 4.54e-05 | +| loss | -0.0368 | +| n_updates | 53580 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000157 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1422 | +| iterations | 9442 | +| time_elapsed | 13593 | +| total_timesteps | 19337216 | +| train/ | | +| approx_kl | 0.013375616 | +| clip_fraction | 0.363 | +| clip_range | 0.0702 | +| entropy_loss | -6.47 | +| explained_variance | 0.387 | +| learning_rate | 4.54e-05 | +| loss | -0.0301 | +| n_updates | 53584 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000279 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1422 | +| iterations | 9443 | +| time_elapsed | 13595 | +| total_timesteps | 19339264 | +| train/ | | +| approx_kl | 0.012334114 | +| clip_fraction | 0.337 | +| clip_range | 0.0702 | +| entropy_loss | -6.57 | +| explained_variance | 0.212 | +| learning_rate | 4.54e-05 | +| loss | -0.0251 | +| n_updates | 53588 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.00027 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1422 | +| iterations | 9444 | +| time_elapsed | 13596 | +| total_timesteps | 19341312 | +| train/ | | +| approx_kl | 0.0092667565 | +| clip_fraction | 0.311 | +| clip_range | 0.0702 | +| entropy_loss | -6.52 | +| explained_variance | 0.418 | +| learning_rate | 4.54e-05 | +| loss | -0.0278 | +| n_updates | 53592 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000246 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1422 | +| iterations | 9445 | +| time_elapsed | 13598 | +| total_timesteps | 19343360 | +| train/ | | +| approx_kl | 0.011176845 | +| clip_fraction | 0.333 | +| clip_range | 0.0702 | +| entropy_loss | -6.91 | +| explained_variance | 0.213 | +| learning_rate | 4.54e-05 | +| loss | -0.04 | +| n_updates | 53596 | +| policy_gradient_loss | -0.023 | +| value_loss | 0.00012 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1422 | +| iterations | 9446 | +| time_elapsed | 13599 | +| total_timesteps | 19345408 | +| train/ | | +| approx_kl | 0.011815282 | +| clip_fraction | 0.348 | +| clip_range | 0.0702 | +| entropy_loss | -6.88 | +| explained_variance | 0.283 | +| learning_rate | 4.54e-05 | +| loss | -0.0284 | +| n_updates | 53600 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000183 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1422 | +| iterations | 9447 | +| time_elapsed | 13601 | +| total_timesteps | 19347456 | +| train/ | | +| approx_kl | 0.016185539 | +| clip_fraction | 0.337 | +| clip_range | 0.0702 | +| entropy_loss | -6.59 | +| explained_variance | 0.292 | +| learning_rate | 4.54e-05 | +| loss | -0.0308 | +| n_updates | 53604 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000188 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1422 | +| iterations | 9448 | +| time_elapsed | 13602 | +| total_timesteps | 19349504 | +| train/ | | +| approx_kl | 0.016663725 | +| clip_fraction | 0.365 | +| clip_range | 0.0702 | +| entropy_loss | -6.58 | +| explained_variance | 0.128 | +| learning_rate | 4.54e-05 | +| loss | -0.0371 | +| n_updates | 53608 | +| policy_gradient_loss | -0.0219 | +| value_loss | 0.000191 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1422 | +| iterations | 9449 | +| time_elapsed | 13603 | +| total_timesteps | 19351552 | +| train/ | | +| approx_kl | 0.019221544 | +| clip_fraction | 0.391 | +| clip_range | 0.0702 | +| entropy_loss | -6.69 | +| explained_variance | -0.386 | +| learning_rate | 4.54e-05 | +| loss | -0.0329 | +| n_updates | 53612 | +| policy_gradient_loss | -0.0234 | +| value_loss | 7.48e-05 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1422 | +| iterations | 9450 | +| time_elapsed | 13605 | +| total_timesteps | 19353600 | +| train/ | | +| approx_kl | 0.0141206 | +| clip_fraction | 0.369 | +| clip_range | 0.0702 | +| entropy_loss | -6.31 | +| explained_variance | 0.251 | +| learning_rate | 4.54e-05 | +| loss | -0.0284 | +| n_updates | 53616 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000223 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1422 | +| iterations | 9451 | +| time_elapsed | 13606 | +| total_timesteps | 19355648 | +| train/ | | +| approx_kl | 0.011147449 | +| clip_fraction | 0.306 | +| clip_range | 0.0702 | +| entropy_loss | -5.74 | +| explained_variance | 0.535 | +| learning_rate | 4.54e-05 | +| loss | -0.0248 | +| n_updates | 53620 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000216 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1422 | +| iterations | 9452 | +| time_elapsed | 13608 | +| total_timesteps | 19357696 | +| train/ | | +| approx_kl | 0.011225967 | +| clip_fraction | 0.316 | +| clip_range | 0.0702 | +| entropy_loss | -5.8 | +| explained_variance | 0.564 | +| learning_rate | 4.54e-05 | +| loss | -0.024 | +| n_updates | 53624 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000231 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1422 | +| iterations | 9453 | +| time_elapsed | 13609 | +| total_timesteps | 19359744 | +| train/ | | +| approx_kl | 0.0105106905 | +| clip_fraction | 0.322 | +| clip_range | 0.0702 | +| entropy_loss | -6.41 | +| explained_variance | 0.408 | +| learning_rate | 4.54e-05 | +| loss | -0.0276 | +| n_updates | 53628 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000175 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1422 | +| iterations | 9454 | +| time_elapsed | 13611 | +| total_timesteps | 19361792 | +| train/ | | +| approx_kl | 0.013077896 | +| clip_fraction | 0.359 | +| clip_range | 0.0702 | +| entropy_loss | -6.43 | +| explained_variance | 0.575 | +| learning_rate | 4.54e-05 | +| loss | -0.0376 | +| n_updates | 53632 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000118 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1422 | +| iterations | 9455 | +| time_elapsed | 13612 | +| total_timesteps | 19363840 | +| train/ | | +| approx_kl | 0.0113874795 | +| clip_fraction | 0.343 | +| clip_range | 0.0702 | +| entropy_loss | -6.56 | +| explained_variance | 0.243 | +| learning_rate | 4.54e-05 | +| loss | -0.0281 | +| n_updates | 53636 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000126 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1422 | +| iterations | 9456 | +| time_elapsed | 13614 | +| total_timesteps | 19365888 | +| train/ | | +| approx_kl | 0.012702979 | +| clip_fraction | 0.337 | +| clip_range | 0.0702 | +| entropy_loss | -6.7 | +| explained_variance | 0.266 | +| learning_rate | 4.54e-05 | +| loss | -0.0311 | +| n_updates | 53640 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000214 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1422 | +| iterations | 9457 | +| time_elapsed | 13615 | +| total_timesteps | 19367936 | +| train/ | | +| approx_kl | 0.012858221 | +| clip_fraction | 0.394 | +| clip_range | 0.0702 | +| entropy_loss | -6.42 | +| explained_variance | 0.756 | +| learning_rate | 4.54e-05 | +| loss | -0.0448 | +| n_updates | 53644 | +| policy_gradient_loss | -0.0273 | +| value_loss | 4.79e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1422 | +| iterations | 9458 | +| time_elapsed | 13616 | +| total_timesteps | 19369984 | +| train/ | | +| approx_kl | 0.012609174 | +| clip_fraction | 0.335 | +| clip_range | 0.0702 | +| entropy_loss | -6.87 | +| explained_variance | -0.0269 | +| learning_rate | 4.54e-05 | +| loss | -0.0314 | +| n_updates | 53648 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000141 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1422 | +| iterations | 9459 | +| time_elapsed | 13618 | +| total_timesteps | 19372032 | +| train/ | | +| approx_kl | 0.012357556 | +| clip_fraction | 0.342 | +| clip_range | 0.0702 | +| entropy_loss | -6.7 | +| explained_variance | 0.195 | +| learning_rate | 4.54e-05 | +| loss | -0.0223 | +| n_updates | 53652 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000175 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1422 | +| iterations | 9460 | +| time_elapsed | 13619 | +| total_timesteps | 19374080 | +| train/ | | +| approx_kl | 0.011759625 | +| clip_fraction | 0.332 | +| clip_range | 0.0702 | +| entropy_loss | -6.65 | +| explained_variance | 0.572 | +| learning_rate | 4.54e-05 | +| loss | -0.0288 | +| n_updates | 53656 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000128 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1422 | +| iterations | 9461 | +| time_elapsed | 13621 | +| total_timesteps | 19376128 | +| train/ | | +| approx_kl | 0.010265777 | +| clip_fraction | 0.315 | +| clip_range | 0.0702 | +| entropy_loss | -6.51 | +| explained_variance | 0.345 | +| learning_rate | 4.54e-05 | +| loss | -0.0288 | +| n_updates | 53660 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000151 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.384 | +| time/ | | +| fps | 1422 | +| iterations | 9462 | +| time_elapsed | 13622 | +| total_timesteps | 19378176 | +| train/ | | +| approx_kl | 0.014713969 | +| clip_fraction | 0.32 | +| clip_range | 0.0702 | +| entropy_loss | -6.17 | +| explained_variance | 0.493 | +| learning_rate | 4.54e-05 | +| loss | -0.0296 | +| n_updates | 53664 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000204 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.386 | +| time/ | | +| fps | 1422 | +| iterations | 9463 | +| time_elapsed | 13624 | +| total_timesteps | 19380224 | +| train/ | | +| approx_kl | 0.015291534 | +| clip_fraction | 0.363 | +| clip_range | 0.0702 | +| entropy_loss | -6.49 | +| explained_variance | 0.218 | +| learning_rate | 4.54e-05 | +| loss | -0.0293 | +| n_updates | 53668 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000214 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1422 | +| iterations | 9464 | +| time_elapsed | 13625 | +| total_timesteps | 19382272 | +| train/ | | +| approx_kl | 0.020373538 | +| clip_fraction | 0.385 | +| clip_range | 0.0702 | +| entropy_loss | -6.46 | +| explained_variance | 0.285 | +| learning_rate | 4.54e-05 | +| loss | -0.0362 | +| n_updates | 53672 | +| policy_gradient_loss | -0.0227 | +| value_loss | 0.000126 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1422 | +| iterations | 9465 | +| time_elapsed | 13627 | +| total_timesteps | 19384320 | +| train/ | | +| approx_kl | 0.0125000635 | +| clip_fraction | 0.359 | +| clip_range | 0.0702 | +| entropy_loss | -6.27 | +| explained_variance | 0.603 | +| learning_rate | 4.54e-05 | +| loss | -0.0297 | +| n_updates | 53676 | +| policy_gradient_loss | -0.0214 | +| value_loss | 9.7e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1422 | +| iterations | 9466 | +| time_elapsed | 13628 | +| total_timesteps | 19386368 | +| train/ | | +| approx_kl | 0.010945844 | +| clip_fraction | 0.325 | +| clip_range | 0.0702 | +| entropy_loss | -5.96 | +| explained_variance | 0.771 | +| learning_rate | 4.54e-05 | +| loss | -0.0283 | +| n_updates | 53680 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000109 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1422 | +| iterations | 9467 | +| time_elapsed | 13629 | +| total_timesteps | 19388416 | +| train/ | | +| approx_kl | 0.010604981 | +| clip_fraction | 0.304 | +| clip_range | 0.0702 | +| entropy_loss | -6.46 | +| explained_variance | 0.129 | +| learning_rate | 4.54e-05 | +| loss | -0.019 | +| n_updates | 53684 | +| policy_gradient_loss | -0.0145 | +| value_loss | 0.000325 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1422 | +| iterations | 9468 | +| time_elapsed | 13631 | +| total_timesteps | 19390464 | +| train/ | | +| approx_kl | 0.012815045 | +| clip_fraction | 0.356 | +| clip_range | 0.0702 | +| entropy_loss | -6.77 | +| explained_variance | 0.0367 | +| learning_rate | 4.54e-05 | +| loss | -0.0268 | +| n_updates | 53688 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000302 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1422 | +| iterations | 9469 | +| time_elapsed | 13632 | +| total_timesteps | 19392512 | +| train/ | | +| approx_kl | 0.013486231 | +| clip_fraction | 0.343 | +| clip_range | 0.0702 | +| entropy_loss | -6.37 | +| explained_variance | 0.0266 | +| learning_rate | 4.54e-05 | +| loss | -0.0344 | +| n_updates | 53692 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000213 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1422 | +| iterations | 9470 | +| time_elapsed | 13634 | +| total_timesteps | 19394560 | +| train/ | | +| approx_kl | 0.013245096 | +| clip_fraction | 0.363 | +| clip_range | 0.0702 | +| entropy_loss | -6.69 | +| explained_variance | -0.182 | +| learning_rate | 4.54e-05 | +| loss | -0.0293 | +| n_updates | 53696 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000177 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1422 | +| iterations | 9471 | +| time_elapsed | 13635 | +| total_timesteps | 19396608 | +| train/ | | +| approx_kl | 0.01394318 | +| clip_fraction | 0.319 | +| clip_range | 0.0702 | +| entropy_loss | -6.74 | +| explained_variance | 0.189 | +| learning_rate | 4.54e-05 | +| loss | -0.0316 | +| n_updates | 53700 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000304 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1422 | +| iterations | 9472 | +| time_elapsed | 13637 | +| total_timesteps | 19398656 | +| train/ | | +| approx_kl | 0.014128346 | +| clip_fraction | 0.319 | +| clip_range | 0.0702 | +| entropy_loss | -6.2 | +| explained_variance | 0.358 | +| learning_rate | 4.54e-05 | +| loss | -0.0327 | +| n_updates | 53704 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000189 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1422 | +| iterations | 9473 | +| time_elapsed | 13638 | +| total_timesteps | 19400704 | +| train/ | | +| approx_kl | 0.011376401 | +| clip_fraction | 0.356 | +| clip_range | 0.0702 | +| entropy_loss | -6.35 | +| explained_variance | 0.166 | +| learning_rate | 4.54e-05 | +| loss | -0.0333 | +| n_updates | 53708 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000153 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1422 | +| iterations | 9474 | +| time_elapsed | 13639 | +| total_timesteps | 19402752 | +| train/ | | +| approx_kl | 0.014385557 | +| clip_fraction | 0.393 | +| clip_range | 0.0701 | +| entropy_loss | -6.38 | +| explained_variance | 0.756 | +| learning_rate | 4.54e-05 | +| loss | -0.0424 | +| n_updates | 53712 | +| policy_gradient_loss | -0.0263 | +| value_loss | 3.74e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1422 | +| iterations | 9475 | +| time_elapsed | 13641 | +| total_timesteps | 19404800 | +| train/ | | +| approx_kl | 0.014668364 | +| clip_fraction | 0.335 | +| clip_range | 0.0701 | +| entropy_loss | -6.02 | +| explained_variance | 0.433 | +| learning_rate | 4.54e-05 | +| loss | -0.0247 | +| n_updates | 53716 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000251 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1422 | +| iterations | 9476 | +| time_elapsed | 13642 | +| total_timesteps | 19406848 | +| train/ | | +| approx_kl | 0.013584647 | +| clip_fraction | 0.347 | +| clip_range | 0.0701 | +| entropy_loss | -6.19 | +| explained_variance | 0.584 | +| learning_rate | 4.54e-05 | +| loss | -0.0255 | +| n_updates | 53720 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000102 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1422 | +| iterations | 9477 | +| time_elapsed | 13644 | +| total_timesteps | 19408896 | +| train/ | | +| approx_kl | 0.012947433 | +| clip_fraction | 0.337 | +| clip_range | 0.0701 | +| entropy_loss | -6.61 | +| explained_variance | 0.0188 | +| learning_rate | 4.54e-05 | +| loss | -0.0291 | +| n_updates | 53724 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000132 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1422 | +| iterations | 9478 | +| time_elapsed | 13645 | +| total_timesteps | 19410944 | +| train/ | | +| approx_kl | 0.011015755 | +| clip_fraction | 0.351 | +| clip_range | 0.0701 | +| entropy_loss | -6.64 | +| explained_variance | 0.128 | +| learning_rate | 4.54e-05 | +| loss | -0.0262 | +| n_updates | 53728 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000431 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1422 | +| iterations | 9479 | +| time_elapsed | 13647 | +| total_timesteps | 19412992 | +| train/ | | +| approx_kl | 0.015754405 | +| clip_fraction | 0.369 | +| clip_range | 0.0701 | +| entropy_loss | -6.01 | +| explained_variance | 0.525 | +| learning_rate | 4.54e-05 | +| loss | -0.0299 | +| n_updates | 53732 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000157 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1422 | +| iterations | 9480 | +| time_elapsed | 13648 | +| total_timesteps | 19415040 | +| train/ | | +| approx_kl | 0.015597211 | +| clip_fraction | 0.366 | +| clip_range | 0.0701 | +| entropy_loss | -5.92 | +| explained_variance | 0.527 | +| learning_rate | 4.54e-05 | +| loss | -0.0323 | +| n_updates | 53736 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000185 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1422 | +| iterations | 9481 | +| time_elapsed | 13650 | +| total_timesteps | 19417088 | +| train/ | | +| approx_kl | 0.0141778365 | +| clip_fraction | 0.354 | +| clip_range | 0.0701 | +| entropy_loss | -6.57 | +| explained_variance | 0.0371 | +| learning_rate | 4.54e-05 | +| loss | -0.0334 | +| n_updates | 53740 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000289 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1422 | +| iterations | 9482 | +| time_elapsed | 13651 | +| total_timesteps | 19419136 | +| train/ | | +| approx_kl | 0.012841733 | +| clip_fraction | 0.335 | +| clip_range | 0.0701 | +| entropy_loss | -6.4 | +| explained_variance | 0.532 | +| learning_rate | 4.54e-05 | +| loss | -0.0284 | +| n_updates | 53744 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000208 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1422 | +| iterations | 9483 | +| time_elapsed | 13653 | +| total_timesteps | 19421184 | +| train/ | | +| approx_kl | 0.012313321 | +| clip_fraction | 0.349 | +| clip_range | 0.0701 | +| entropy_loss | -6.06 | +| explained_variance | 0.686 | +| learning_rate | 4.54e-05 | +| loss | -0.0316 | +| n_updates | 53748 | +| policy_gradient_loss | -0.0218 | +| value_loss | 9.95e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1422 | +| iterations | 9484 | +| time_elapsed | 13654 | +| total_timesteps | 19423232 | +| train/ | | +| approx_kl | 0.012017394 | +| clip_fraction | 0.335 | +| clip_range | 0.0701 | +| entropy_loss | -6.45 | +| explained_variance | 0.312 | +| learning_rate | 4.54e-05 | +| loss | -0.0308 | +| n_updates | 53752 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.00016 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1422 | +| iterations | 9485 | +| time_elapsed | 13655 | +| total_timesteps | 19425280 | +| train/ | | +| approx_kl | 0.0111540975 | +| clip_fraction | 0.31 | +| clip_range | 0.0701 | +| entropy_loss | -6.68 | +| explained_variance | 0.182 | +| learning_rate | 4.54e-05 | +| loss | -0.0196 | +| n_updates | 53756 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.0003 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1422 | +| iterations | 9486 | +| time_elapsed | 13657 | +| total_timesteps | 19427328 | +| train/ | | +| approx_kl | 0.012781222 | +| clip_fraction | 0.34 | +| clip_range | 0.0701 | +| entropy_loss | -6.3 | +| explained_variance | 0.48 | +| learning_rate | 4.54e-05 | +| loss | -0.0318 | +| n_updates | 53760 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000243 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1422 | +| iterations | 9487 | +| time_elapsed | 13658 | +| total_timesteps | 19429376 | +| train/ | | +| approx_kl | 0.013057759 | +| clip_fraction | 0.354 | +| clip_range | 0.0701 | +| entropy_loss | -6.57 | +| explained_variance | 0.195 | +| learning_rate | 4.54e-05 | +| loss | -0.0312 | +| n_updates | 53764 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000178 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1422 | +| iterations | 9488 | +| time_elapsed | 13660 | +| total_timesteps | 19431424 | +| train/ | | +| approx_kl | 0.011737547 | +| clip_fraction | 0.325 | +| clip_range | 0.0701 | +| entropy_loss | -6.4 | +| explained_variance | 0.431 | +| learning_rate | 4.54e-05 | +| loss | -0.0323 | +| n_updates | 53768 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000213 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1422 | +| iterations | 9489 | +| time_elapsed | 13661 | +| total_timesteps | 19433472 | +| train/ | | +| approx_kl | 0.013194715 | +| clip_fraction | 0.351 | +| clip_range | 0.0701 | +| entropy_loss | -6.7 | +| explained_variance | 0.542 | +| learning_rate | 4.54e-05 | +| loss | -0.0277 | +| n_updates | 53772 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000107 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1422 | +| iterations | 9490 | +| time_elapsed | 13662 | +| total_timesteps | 19435520 | +| train/ | | +| approx_kl | 0.012624338 | +| clip_fraction | 0.325 | +| clip_range | 0.0701 | +| entropy_loss | -6.37 | +| explained_variance | 0.43 | +| learning_rate | 4.54e-05 | +| loss | -0.0246 | +| n_updates | 53776 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000236 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1422 | +| iterations | 9491 | +| time_elapsed | 13664 | +| total_timesteps | 19437568 | +| train/ | | +| approx_kl | 0.013092704 | +| clip_fraction | 0.33 | +| clip_range | 0.0701 | +| entropy_loss | -5.87 | +| explained_variance | 0.364 | +| learning_rate | 4.54e-05 | +| loss | -0.024 | +| n_updates | 53780 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000328 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1422 | +| iterations | 9492 | +| time_elapsed | 13665 | +| total_timesteps | 19439616 | +| train/ | | +| approx_kl | 0.01477821 | +| clip_fraction | 0.338 | +| clip_range | 0.0701 | +| entropy_loss | -6.7 | +| explained_variance | 0.393 | +| learning_rate | 4.54e-05 | +| loss | -0.0371 | +| n_updates | 53784 | +| policy_gradient_loss | -0.0223 | +| value_loss | 9.37e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1422 | +| iterations | 9493 | +| time_elapsed | 13667 | +| total_timesteps | 19441664 | +| train/ | | +| approx_kl | 0.011439857 | +| clip_fraction | 0.336 | +| clip_range | 0.0701 | +| entropy_loss | -6.23 | +| explained_variance | 0.692 | +| learning_rate | 4.54e-05 | +| loss | -0.0335 | +| n_updates | 53788 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000102 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1422 | +| iterations | 9494 | +| time_elapsed | 13668 | +| total_timesteps | 19443712 | +| train/ | | +| approx_kl | 0.013036286 | +| clip_fraction | 0.337 | +| clip_range | 0.0701 | +| entropy_loss | -6.36 | +| explained_variance | 0.427 | +| learning_rate | 4.54e-05 | +| loss | -0.0281 | +| n_updates | 53792 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000216 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1422 | +| iterations | 9495 | +| time_elapsed | 13670 | +| total_timesteps | 19445760 | +| train/ | | +| approx_kl | 0.013043239 | +| clip_fraction | 0.34 | +| clip_range | 0.0701 | +| entropy_loss | -6.51 | +| explained_variance | 0.204 | +| learning_rate | 4.54e-05 | +| loss | -0.0303 | +| n_updates | 53796 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.00017 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1422 | +| iterations | 9496 | +| time_elapsed | 13671 | +| total_timesteps | 19447808 | +| train/ | | +| approx_kl | 0.013274493 | +| clip_fraction | 0.333 | +| clip_range | 0.0701 | +| entropy_loss | -6.48 | +| explained_variance | 0.404 | +| learning_rate | 4.54e-05 | +| loss | -0.0285 | +| n_updates | 53800 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000194 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1422 | +| iterations | 9497 | +| time_elapsed | 13672 | +| total_timesteps | 19449856 | +| train/ | | +| approx_kl | 0.015813004 | +| clip_fraction | 0.365 | +| clip_range | 0.0701 | +| entropy_loss | -6.55 | +| explained_variance | 0.283 | +| learning_rate | 4.54e-05 | +| loss | -0.0324 | +| n_updates | 53804 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000137 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1422 | +| iterations | 9498 | +| time_elapsed | 13674 | +| total_timesteps | 19451904 | +| train/ | | +| approx_kl | 0.011164077 | +| clip_fraction | 0.336 | +| clip_range | 0.0701 | +| entropy_loss | -6.7 | +| explained_variance | 0.36 | +| learning_rate | 4.54e-05 | +| loss | -0.0306 | +| n_updates | 53808 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000259 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1422 | +| iterations | 9499 | +| time_elapsed | 13675 | +| total_timesteps | 19453952 | +| train/ | | +| approx_kl | 0.013110049 | +| clip_fraction | 0.312 | +| clip_range | 0.0701 | +| entropy_loss | -6.73 | +| explained_variance | 0.274 | +| learning_rate | 4.54e-05 | +| loss | -0.032 | +| n_updates | 53812 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000221 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1422 | +| iterations | 9500 | +| time_elapsed | 13677 | +| total_timesteps | 19456000 | +| train/ | | +| approx_kl | 0.008697222 | +| clip_fraction | 0.313 | +| clip_range | 0.0701 | +| entropy_loss | -6.83 | +| explained_variance | 0.313 | +| learning_rate | 4.54e-05 | +| loss | -0.0231 | +| n_updates | 53816 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000384 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1422 | +| iterations | 9501 | +| time_elapsed | 13678 | +| total_timesteps | 19458048 | +| train/ | | +| approx_kl | 0.009476356 | +| clip_fraction | 0.313 | +| clip_range | 0.0701 | +| entropy_loss | -6.16 | +| explained_variance | 0.449 | +| learning_rate | 4.54e-05 | +| loss | -0.027 | +| n_updates | 53820 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000225 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1422 | +| iterations | 9502 | +| time_elapsed | 13680 | +| total_timesteps | 19460096 | +| train/ | | +| approx_kl | 0.013020637 | +| clip_fraction | 0.351 | +| clip_range | 0.0701 | +| entropy_loss | -6.49 | +| explained_variance | 0.348 | +| learning_rate | 4.54e-05 | +| loss | -0.0375 | +| n_updates | 53824 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000144 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1422 | +| iterations | 9503 | +| time_elapsed | 13681 | +| total_timesteps | 19462144 | +| train/ | | +| approx_kl | 0.012534388 | +| clip_fraction | 0.327 | +| clip_range | 0.0701 | +| entropy_loss | -5.98 | +| explained_variance | 0.567 | +| learning_rate | 4.54e-05 | +| loss | -0.0244 | +| n_updates | 53828 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.0002 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1422 | +| iterations | 9504 | +| time_elapsed | 13683 | +| total_timesteps | 19464192 | +| train/ | | +| approx_kl | 0.011609135 | +| clip_fraction | 0.339 | +| clip_range | 0.0701 | +| entropy_loss | -6.47 | +| explained_variance | 0.186 | +| learning_rate | 4.54e-05 | +| loss | -0.0322 | +| n_updates | 53832 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000164 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1422 | +| iterations | 9505 | +| time_elapsed | 13684 | +| total_timesteps | 19466240 | +| train/ | | +| approx_kl | 0.011301665 | +| clip_fraction | 0.331 | +| clip_range | 0.0701 | +| entropy_loss | -6.37 | +| explained_variance | 0.475 | +| learning_rate | 4.54e-05 | +| loss | -0.0273 | +| n_updates | 53836 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000246 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1422 | +| iterations | 9506 | +| time_elapsed | 13686 | +| total_timesteps | 19468288 | +| train/ | | +| approx_kl | 0.013075603 | +| clip_fraction | 0.342 | +| clip_range | 0.0701 | +| entropy_loss | -6.71 | +| explained_variance | 0.0114 | +| learning_rate | 4.54e-05 | +| loss | -0.0263 | +| n_updates | 53840 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000164 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1422 | +| iterations | 9507 | +| time_elapsed | 13687 | +| total_timesteps | 19470336 | +| train/ | | +| approx_kl | 0.013581794 | +| clip_fraction | 0.325 | +| clip_range | 0.0701 | +| entropy_loss | -6.86 | +| explained_variance | 0.129 | +| learning_rate | 4.54e-05 | +| loss | -0.0386 | +| n_updates | 53844 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.00022 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1422 | +| iterations | 9508 | +| time_elapsed | 13688 | +| total_timesteps | 19472384 | +| train/ | | +| approx_kl | 0.011317171 | +| clip_fraction | 0.304 | +| clip_range | 0.0701 | +| entropy_loss | -6.27 | +| explained_variance | 0.308 | +| learning_rate | 4.54e-05 | +| loss | -0.026 | +| n_updates | 53848 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000301 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1422 | +| iterations | 9509 | +| time_elapsed | 13690 | +| total_timesteps | 19474432 | +| train/ | | +| approx_kl | 0.010092193 | +| clip_fraction | 0.317 | +| clip_range | 0.0701 | +| entropy_loss | -6.28 | +| explained_variance | 0.294 | +| learning_rate | 4.54e-05 | +| loss | -0.0219 | +| n_updates | 53852 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.000513 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1422 | +| iterations | 9510 | +| time_elapsed | 13691 | +| total_timesteps | 19476480 | +| train/ | | +| approx_kl | 0.011936556 | +| clip_fraction | 0.319 | +| clip_range | 0.0701 | +| entropy_loss | -6.31 | +| explained_variance | 0.348 | +| learning_rate | 4.54e-05 | +| loss | -0.0259 | +| n_updates | 53856 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000309 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1422 | +| iterations | 9511 | +| time_elapsed | 13693 | +| total_timesteps | 19478528 | +| train/ | | +| approx_kl | 0.012486508 | +| clip_fraction | 0.38 | +| clip_range | 0.0701 | +| entropy_loss | -6.26 | +| explained_variance | 0.522 | +| learning_rate | 4.54e-05 | +| loss | -0.0397 | +| n_updates | 53860 | +| policy_gradient_loss | -0.0251 | +| value_loss | 0.000112 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1422 | +| iterations | 9512 | +| time_elapsed | 13694 | +| total_timesteps | 19480576 | +| train/ | | +| approx_kl | 0.013131449 | +| clip_fraction | 0.323 | +| clip_range | 0.0701 | +| entropy_loss | -6.71 | +| explained_variance | 0.185 | +| learning_rate | 4.54e-05 | +| loss | -0.0311 | +| n_updates | 53864 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000207 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1422 | +| iterations | 9513 | +| time_elapsed | 13696 | +| total_timesteps | 19482624 | +| train/ | | +| approx_kl | 0.0102329925 | +| clip_fraction | 0.327 | +| clip_range | 0.0701 | +| entropy_loss | -7 | +| explained_variance | 0.0617 | +| learning_rate | 4.54e-05 | +| loss | -0.0401 | +| n_updates | 53868 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000214 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1422 | +| iterations | 9514 | +| time_elapsed | 13697 | +| total_timesteps | 19484672 | +| train/ | | +| approx_kl | 0.012611453 | +| clip_fraction | 0.336 | +| clip_range | 0.0701 | +| entropy_loss | -6.52 | +| explained_variance | 0.413 | +| learning_rate | 4.54e-05 | +| loss | -0.0324 | +| n_updates | 53872 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000197 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1422 | +| iterations | 9515 | +| time_elapsed | 13698 | +| total_timesteps | 19486720 | +| train/ | | +| approx_kl | 0.01295205 | +| clip_fraction | 0.354 | +| clip_range | 0.0701 | +| entropy_loss | -6.45 | +| explained_variance | 0.418 | +| learning_rate | 4.54e-05 | +| loss | -0.0364 | +| n_updates | 53876 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000123 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1422 | +| iterations | 9516 | +| time_elapsed | 13700 | +| total_timesteps | 19488768 | +| train/ | | +| approx_kl | 0.0100373505 | +| clip_fraction | 0.334 | +| clip_range | 0.0701 | +| entropy_loss | -6.27 | +| explained_variance | 0.384 | +| learning_rate | 4.54e-05 | +| loss | -0.0328 | +| n_updates | 53880 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000231 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1422 | +| iterations | 9517 | +| time_elapsed | 13701 | +| total_timesteps | 19490816 | +| train/ | | +| approx_kl | 0.010907056 | +| clip_fraction | 0.318 | +| clip_range | 0.0701 | +| entropy_loss | -7.08 | +| explained_variance | 0.0452 | +| learning_rate | 4.54e-05 | +| loss | -0.0331 | +| n_updates | 53884 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000133 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1422 | +| iterations | 9518 | +| time_elapsed | 13703 | +| total_timesteps | 19492864 | +| train/ | | +| approx_kl | 0.010876037 | +| clip_fraction | 0.336 | +| clip_range | 0.0701 | +| entropy_loss | -6.57 | +| explained_variance | 0.361 | +| learning_rate | 4.54e-05 | +| loss | -0.0338 | +| n_updates | 53888 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000235 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.14e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1422 | +| iterations | 9519 | +| time_elapsed | 13704 | +| total_timesteps | 19494912 | +| train/ | | +| approx_kl | 0.012624964 | +| clip_fraction | 0.352 | +| clip_range | 0.0701 | +| entropy_loss | -6.59 | +| explained_variance | 0.498 | +| learning_rate | 4.54e-05 | +| loss | -0.0316 | +| n_updates | 53892 | +| policy_gradient_loss | -0.0217 | +| value_loss | 9.49e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.14e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1422 | +| iterations | 9520 | +| time_elapsed | 13706 | +| total_timesteps | 19496960 | +| train/ | | +| approx_kl | 0.00837647 | +| clip_fraction | 0.298 | +| clip_range | 0.0701 | +| entropy_loss | -6.61 | +| explained_variance | 0.269 | +| learning_rate | 4.54e-05 | +| loss | -0.0261 | +| n_updates | 53896 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000406 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1422 | +| iterations | 9521 | +| time_elapsed | 13707 | +| total_timesteps | 19499008 | +| train/ | | +| approx_kl | 0.012685271 | +| clip_fraction | 0.348 | +| clip_range | 0.0701 | +| entropy_loss | -6.52 | +| explained_variance | 0.33 | +| learning_rate | 4.54e-05 | +| loss | -0.0346 | +| n_updates | 53900 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000112 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1422 | +| iterations | 9522 | +| time_elapsed | 13709 | +| total_timesteps | 19501056 | +| train/ | | +| approx_kl | 0.01161636 | +| clip_fraction | 0.342 | +| clip_range | 0.0701 | +| entropy_loss | -7.11 | +| explained_variance | -0.197 | +| learning_rate | 4.54e-05 | +| loss | -0.0322 | +| n_updates | 53904 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000118 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1422 | +| iterations | 9523 | +| time_elapsed | 13710 | +| total_timesteps | 19503104 | +| train/ | | +| approx_kl | 0.014261471 | +| clip_fraction | 0.31 | +| clip_range | 0.0701 | +| entropy_loss | -6.34 | +| explained_variance | 0.269 | +| learning_rate | 4.54e-05 | +| loss | -0.0224 | +| n_updates | 53908 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000279 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1422 | +| iterations | 9524 | +| time_elapsed | 13712 | +| total_timesteps | 19505152 | +| train/ | | +| approx_kl | 0.013708517 | +| clip_fraction | 0.345 | +| clip_range | 0.0701 | +| entropy_loss | -6.44 | +| explained_variance | 0.375 | +| learning_rate | 4.54e-05 | +| loss | -0.0341 | +| n_updates | 53912 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000164 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1422 | +| iterations | 9525 | +| time_elapsed | 13713 | +| total_timesteps | 19507200 | +| train/ | | +| approx_kl | 0.013715398 | +| clip_fraction | 0.344 | +| clip_range | 0.0701 | +| entropy_loss | -6.6 | +| explained_variance | 0.52 | +| learning_rate | 4.54e-05 | +| loss | -0.0311 | +| n_updates | 53916 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000129 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1422 | +| iterations | 9526 | +| time_elapsed | 13715 | +| total_timesteps | 19509248 | +| train/ | | +| approx_kl | 0.012662966 | +| clip_fraction | 0.317 | +| clip_range | 0.0701 | +| entropy_loss | -6.05 | +| explained_variance | 0.353 | +| learning_rate | 4.54e-05 | +| loss | -0.024 | +| n_updates | 53920 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000392 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.14e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1422 | +| iterations | 9527 | +| time_elapsed | 13716 | +| total_timesteps | 19511296 | +| train/ | | +| approx_kl | 0.011414183 | +| clip_fraction | 0.35 | +| clip_range | 0.0701 | +| entropy_loss | -6.42 | +| explained_variance | 0.452 | +| learning_rate | 4.54e-05 | +| loss | -0.0331 | +| n_updates | 53924 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000178 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.14e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1422 | +| iterations | 9528 | +| time_elapsed | 13718 | +| total_timesteps | 19513344 | +| train/ | | +| approx_kl | 0.011970819 | +| clip_fraction | 0.333 | +| clip_range | 0.0701 | +| entropy_loss | -6.62 | +| explained_variance | 0.278 | +| learning_rate | 4.54e-05 | +| loss | -0.0331 | +| n_updates | 53928 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000267 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.14e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1422 | +| iterations | 9529 | +| time_elapsed | 13719 | +| total_timesteps | 19515392 | +| train/ | | +| approx_kl | 0.014694871 | +| clip_fraction | 0.352 | +| clip_range | 0.0701 | +| entropy_loss | -6.49 | +| explained_variance | 0.264 | +| learning_rate | 4.54e-05 | +| loss | -0.0381 | +| n_updates | 53932 | +| policy_gradient_loss | -0.0215 | +| value_loss | 9.8e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1422 | +| iterations | 9530 | +| time_elapsed | 13721 | +| total_timesteps | 19517440 | +| train/ | | +| approx_kl | 0.010978127 | +| clip_fraction | 0.318 | +| clip_range | 0.0701 | +| entropy_loss | -6.44 | +| explained_variance | 0.448 | +| learning_rate | 4.54e-05 | +| loss | -0.0261 | +| n_updates | 53936 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000237 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1422 | +| iterations | 9531 | +| time_elapsed | 13722 | +| total_timesteps | 19519488 | +| train/ | | +| approx_kl | 0.012818804 | +| clip_fraction | 0.324 | +| clip_range | 0.0701 | +| entropy_loss | -6.48 | +| explained_variance | 0.152 | +| learning_rate | 4.54e-05 | +| loss | -0.027 | +| n_updates | 53940 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000307 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1422 | +| iterations | 9532 | +| time_elapsed | 13723 | +| total_timesteps | 19521536 | +| train/ | | +| approx_kl | 0.011901209 | +| clip_fraction | 0.309 | +| clip_range | 0.0701 | +| entropy_loss | -6.77 | +| explained_variance | 0.355 | +| learning_rate | 4.54e-05 | +| loss | -0.0335 | +| n_updates | 53944 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000182 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1422 | +| iterations | 9533 | +| time_elapsed | 13725 | +| total_timesteps | 19523584 | +| train/ | | +| approx_kl | 0.0132819265 | +| clip_fraction | 0.349 | +| clip_range | 0.0701 | +| entropy_loss | -6.72 | +| explained_variance | 0.259 | +| learning_rate | 4.54e-05 | +| loss | -0.0306 | +| n_updates | 53948 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000184 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1422 | +| iterations | 9534 | +| time_elapsed | 13726 | +| total_timesteps | 19525632 | +| train/ | | +| approx_kl | 0.010607718 | +| clip_fraction | 0.34 | +| clip_range | 0.0701 | +| entropy_loss | -6.74 | +| explained_variance | 0.329 | +| learning_rate | 4.54e-05 | +| loss | -0.0286 | +| n_updates | 53952 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000189 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1422 | +| iterations | 9535 | +| time_elapsed | 13728 | +| total_timesteps | 19527680 | +| train/ | | +| approx_kl | 0.012978934 | +| clip_fraction | 0.342 | +| clip_range | 0.0701 | +| entropy_loss | -6.82 | +| explained_variance | -0.105 | +| learning_rate | 4.54e-05 | +| loss | -0.026 | +| n_updates | 53956 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000136 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1422 | +| iterations | 9536 | +| time_elapsed | 13729 | +| total_timesteps | 19529728 | +| train/ | | +| approx_kl | 0.010747687 | +| clip_fraction | 0.318 | +| clip_range | 0.0701 | +| entropy_loss | -6.25 | +| explained_variance | 0.229 | +| learning_rate | 4.54e-05 | +| loss | -0.017 | +| n_updates | 53960 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000372 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1422 | +| iterations | 9537 | +| time_elapsed | 13731 | +| total_timesteps | 19531776 | +| train/ | | +| approx_kl | 0.013405255 | +| clip_fraction | 0.326 | +| clip_range | 0.0701 | +| entropy_loss | -6.38 | +| explained_variance | 0.249 | +| learning_rate | 4.54e-05 | +| loss | -0.029 | +| n_updates | 53964 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000175 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1422 | +| iterations | 9538 | +| time_elapsed | 13732 | +| total_timesteps | 19533824 | +| train/ | | +| approx_kl | 0.012267343 | +| clip_fraction | 0.366 | +| clip_range | 0.0701 | +| entropy_loss | -6.52 | +| explained_variance | 0.398 | +| learning_rate | 4.54e-05 | +| loss | -0.0362 | +| n_updates | 53968 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000114 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.384 | +| time/ | | +| fps | 1422 | +| iterations | 9539 | +| time_elapsed | 13733 | +| total_timesteps | 19535872 | +| train/ | | +| approx_kl | 0.013334865 | +| clip_fraction | 0.333 | +| clip_range | 0.0701 | +| entropy_loss | -6.17 | +| explained_variance | 0.445 | +| learning_rate | 4.54e-05 | +| loss | -0.0214 | +| n_updates | 53972 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000163 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.384 | +| time/ | | +| fps | 1422 | +| iterations | 9540 | +| time_elapsed | 13735 | +| total_timesteps | 19537920 | +| train/ | | +| approx_kl | 0.013641283 | +| clip_fraction | 0.342 | +| clip_range | 0.0701 | +| entropy_loss | -6.66 | +| explained_variance | 0.225 | +| learning_rate | 4.54e-05 | +| loss | -0.0288 | +| n_updates | 53976 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.00025 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.384 | +| time/ | | +| fps | 1422 | +| iterations | 9541 | +| time_elapsed | 13736 | +| total_timesteps | 19539968 | +| train/ | | +| approx_kl | 0.013842732 | +| clip_fraction | 0.35 | +| clip_range | 0.0701 | +| entropy_loss | -6.85 | +| explained_variance | -0.0579 | +| learning_rate | 4.54e-05 | +| loss | -0.0364 | +| n_updates | 53980 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.00013 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1422 | +| iterations | 9542 | +| time_elapsed | 13738 | +| total_timesteps | 19542016 | +| train/ | | +| approx_kl | 0.013514564 | +| clip_fraction | 0.329 | +| clip_range | 0.0701 | +| entropy_loss | -7.11 | +| explained_variance | -0.0468 | +| learning_rate | 4.54e-05 | +| loss | -0.0333 | +| n_updates | 53984 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000158 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1422 | +| iterations | 9543 | +| time_elapsed | 13739 | +| total_timesteps | 19544064 | +| train/ | | +| approx_kl | 0.013097672 | +| clip_fraction | 0.33 | +| clip_range | 0.0701 | +| entropy_loss | -6.42 | +| explained_variance | 0.155 | +| learning_rate | 4.54e-05 | +| loss | -0.0255 | +| n_updates | 53988 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000221 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1422 | +| iterations | 9544 | +| time_elapsed | 13741 | +| total_timesteps | 19546112 | +| train/ | | +| approx_kl | 0.012597831 | +| clip_fraction | 0.334 | +| clip_range | 0.0701 | +| entropy_loss | -6.6 | +| explained_variance | 0.229 | +| learning_rate | 4.54e-05 | +| loss | -0.0292 | +| n_updates | 53992 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000239 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1422 | +| iterations | 9545 | +| time_elapsed | 13742 | +| total_timesteps | 19548160 | +| train/ | | +| approx_kl | 0.009869948 | +| clip_fraction | 0.319 | +| clip_range | 0.0701 | +| entropy_loss | -6.75 | +| explained_variance | 0.293 | +| learning_rate | 4.54e-05 | +| loss | -0.0324 | +| n_updates | 53996 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000143 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.384 | +| time/ | | +| fps | 1422 | +| iterations | 9546 | +| time_elapsed | 13744 | +| total_timesteps | 19550208 | +| train/ | | +| approx_kl | 0.011080637 | +| clip_fraction | 0.335 | +| clip_range | 0.0701 | +| entropy_loss | -6.72 | +| explained_variance | 0.076 | +| learning_rate | 4.54e-05 | +| loss | -0.0321 | +| n_updates | 54000 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000252 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1422 | +| iterations | 9547 | +| time_elapsed | 13745 | +| total_timesteps | 19552256 | +| train/ | | +| approx_kl | 0.010900284 | +| clip_fraction | 0.338 | +| clip_range | 0.0701 | +| entropy_loss | -6.54 | +| explained_variance | 0.235 | +| learning_rate | 4.54e-05 | +| loss | -0.0298 | +| n_updates | 54004 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000238 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1422 | +| iterations | 9548 | +| time_elapsed | 13747 | +| total_timesteps | 19554304 | +| train/ | | +| approx_kl | 0.010575754 | +| clip_fraction | 0.335 | +| clip_range | 0.0701 | +| entropy_loss | -6.36 | +| explained_variance | 0.302 | +| learning_rate | 4.54e-05 | +| loss | -0.0286 | +| n_updates | 54008 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000281 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1422 | +| iterations | 9549 | +| time_elapsed | 13748 | +| total_timesteps | 19556352 | +| train/ | | +| approx_kl | 0.011645345 | +| clip_fraction | 0.365 | +| clip_range | 0.0701 | +| entropy_loss | -6.55 | +| explained_variance | 0.216 | +| learning_rate | 4.54e-05 | +| loss | -0.0385 | +| n_updates | 54012 | +| policy_gradient_loss | -0.0222 | +| value_loss | 0.000121 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1422 | +| iterations | 9550 | +| time_elapsed | 13749 | +| total_timesteps | 19558400 | +| train/ | | +| approx_kl | 0.01056863 | +| clip_fraction | 0.332 | +| clip_range | 0.0701 | +| entropy_loss | -5.82 | +| explained_variance | 0.454 | +| learning_rate | 4.54e-05 | +| loss | -0.0264 | +| n_updates | 54016 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000311 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1422 | +| iterations | 9551 | +| time_elapsed | 13751 | +| total_timesteps | 19560448 | +| train/ | | +| approx_kl | 0.015570812 | +| clip_fraction | 0.375 | +| clip_range | 0.0701 | +| entropy_loss | -6.13 | +| explained_variance | 0.496 | +| learning_rate | 4.54e-05 | +| loss | -0.0353 | +| n_updates | 54020 | +| policy_gradient_loss | -0.0225 | +| value_loss | 0.000152 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.385 | +| time/ | | +| fps | 1422 | +| iterations | 9552 | +| time_elapsed | 13752 | +| total_timesteps | 19562496 | +| train/ | | +| approx_kl | 0.011182525 | +| clip_fraction | 0.342 | +| clip_range | 0.0701 | +| entropy_loss | -6.43 | +| explained_variance | 0.322 | +| learning_rate | 4.54e-05 | +| loss | -0.025 | +| n_updates | 54024 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.00035 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.387 | +| time/ | | +| fps | 1422 | +| iterations | 9553 | +| time_elapsed | 13754 | +| total_timesteps | 19564544 | +| train/ | | +| approx_kl | 0.009296389 | +| clip_fraction | 0.329 | +| clip_range | 0.0701 | +| entropy_loss | -6.41 | +| explained_variance | 0.243 | +| learning_rate | 4.54e-05 | +| loss | -0.0268 | +| n_updates | 54028 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000341 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.394 | +| time/ | | +| fps | 1422 | +| iterations | 9554 | +| time_elapsed | 13755 | +| total_timesteps | 19566592 | +| train/ | | +| approx_kl | 0.011141228 | +| clip_fraction | 0.338 | +| clip_range | 0.0701 | +| entropy_loss | -5.99 | +| explained_variance | 0.494 | +| learning_rate | 4.54e-05 | +| loss | -0.0386 | +| n_updates | 54032 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000176 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.398 | +| time/ | | +| fps | 1422 | +| iterations | 9555 | +| time_elapsed | 13757 | +| total_timesteps | 19568640 | +| train/ | | +| approx_kl | 0.008711891 | +| clip_fraction | 0.315 | +| clip_range | 0.0701 | +| entropy_loss | -6.82 | +| explained_variance | 0.323 | +| learning_rate | 4.54e-05 | +| loss | -0.0321 | +| n_updates | 54036 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000308 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.389 | +| time/ | | +| fps | 1422 | +| iterations | 9556 | +| time_elapsed | 13758 | +| total_timesteps | 19570688 | +| train/ | | +| approx_kl | 0.009673307 | +| clip_fraction | 0.307 | +| clip_range | 0.0701 | +| entropy_loss | -6.62 | +| explained_variance | 0.291 | +| learning_rate | 4.54e-05 | +| loss | -0.0284 | +| n_updates | 54040 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000299 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.392 | +| time/ | | +| fps | 1422 | +| iterations | 9557 | +| time_elapsed | 13760 | +| total_timesteps | 19572736 | +| train/ | | +| approx_kl | 0.00969514 | +| clip_fraction | 0.337 | +| clip_range | 0.0701 | +| entropy_loss | -6.53 | +| explained_variance | 0.52 | +| learning_rate | 4.54e-05 | +| loss | -0.0332 | +| n_updates | 54044 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000147 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.389 | +| time/ | | +| fps | 1422 | +| iterations | 9558 | +| time_elapsed | 13761 | +| total_timesteps | 19574784 | +| train/ | | +| approx_kl | 0.010731675 | +| clip_fraction | 0.326 | +| clip_range | 0.0701 | +| entropy_loss | -6.63 | +| explained_variance | 0.578 | +| learning_rate | 4.54e-05 | +| loss | -0.0315 | +| n_updates | 54048 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000123 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.394 | +| time/ | | +| fps | 1422 | +| iterations | 9559 | +| time_elapsed | 13763 | +| total_timesteps | 19576832 | +| train/ | | +| approx_kl | 0.011624968 | +| clip_fraction | 0.351 | +| clip_range | 0.0701 | +| entropy_loss | -6.73 | +| explained_variance | 0.482 | +| learning_rate | 4.54e-05 | +| loss | -0.0401 | +| n_updates | 54052 | +| policy_gradient_loss | -0.0213 | +| value_loss | 8.18e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.394 | +| time/ | | +| fps | 1422 | +| iterations | 9560 | +| time_elapsed | 13764 | +| total_timesteps | 19578880 | +| train/ | | +| approx_kl | 0.012700165 | +| clip_fraction | 0.347 | +| clip_range | 0.0701 | +| entropy_loss | -6.25 | +| explained_variance | 0.421 | +| learning_rate | 4.54e-05 | +| loss | -0.027 | +| n_updates | 54056 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000292 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.388 | +| time/ | | +| fps | 1422 | +| iterations | 9561 | +| time_elapsed | 13766 | +| total_timesteps | 19580928 | +| train/ | | +| approx_kl | 0.014104245 | +| clip_fraction | 0.321 | +| clip_range | 0.0701 | +| entropy_loss | -6.04 | +| explained_variance | 0.452 | +| learning_rate | 4.54e-05 | +| loss | -0.0241 | +| n_updates | 54060 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000205 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.391 | +| time/ | | +| fps | 1422 | +| iterations | 9562 | +| time_elapsed | 13767 | +| total_timesteps | 19582976 | +| train/ | | +| approx_kl | 0.016668644 | +| clip_fraction | 0.357 | +| clip_range | 0.0701 | +| entropy_loss | -6.01 | +| explained_variance | 0.482 | +| learning_rate | 4.53e-05 | +| loss | -0.0334 | +| n_updates | 54064 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000211 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.388 | +| time/ | | +| fps | 1422 | +| iterations | 9563 | +| time_elapsed | 13769 | +| total_timesteps | 19585024 | +| train/ | | +| approx_kl | 0.011592695 | +| clip_fraction | 0.329 | +| clip_range | 0.0701 | +| entropy_loss | -6.41 | +| explained_variance | 0.31 | +| learning_rate | 4.53e-05 | +| loss | -0.034 | +| n_updates | 54068 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000263 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1422 | +| iterations | 9564 | +| time_elapsed | 13770 | +| total_timesteps | 19587072 | +| train/ | | +| approx_kl | 0.012162205 | +| clip_fraction | 0.338 | +| clip_range | 0.0701 | +| entropy_loss | -6.83 | +| explained_variance | -0.0783 | +| learning_rate | 4.53e-05 | +| loss | -0.0348 | +| n_updates | 54072 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000142 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1422 | +| iterations | 9565 | +| time_elapsed | 13772 | +| total_timesteps | 19589120 | +| train/ | | +| approx_kl | 0.012129968 | +| clip_fraction | 0.317 | +| clip_range | 0.0701 | +| entropy_loss | -6.45 | +| explained_variance | 0.649 | +| learning_rate | 4.53e-05 | +| loss | -0.0364 | +| n_updates | 54076 | +| policy_gradient_loss | -0.0213 | +| value_loss | 9.63e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1422 | +| iterations | 9566 | +| time_elapsed | 13773 | +| total_timesteps | 19591168 | +| train/ | | +| approx_kl | 0.012004172 | +| clip_fraction | 0.336 | +| clip_range | 0.0701 | +| entropy_loss | -6.63 | +| explained_variance | 0.403 | +| learning_rate | 4.53e-05 | +| loss | -0.0313 | +| n_updates | 54080 | +| policy_gradient_loss | -0.0207 | +| value_loss | 9.43e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1422 | +| iterations | 9567 | +| time_elapsed | 13775 | +| total_timesteps | 19593216 | +| train/ | | +| approx_kl | 0.009308403 | +| clip_fraction | 0.292 | +| clip_range | 0.0701 | +| entropy_loss | -6.8 | +| explained_variance | 0.197 | +| learning_rate | 4.53e-05 | +| loss | -0.0299 | +| n_updates | 54084 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000346 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1422 | +| iterations | 9568 | +| time_elapsed | 13776 | +| total_timesteps | 19595264 | +| train/ | | +| approx_kl | 0.010540181 | +| clip_fraction | 0.336 | +| clip_range | 0.0701 | +| entropy_loss | -6.45 | +| explained_variance | 0.47 | +| learning_rate | 4.53e-05 | +| loss | -0.0334 | +| n_updates | 54088 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000154 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1422 | +| iterations | 9569 | +| time_elapsed | 13778 | +| total_timesteps | 19597312 | +| train/ | | +| approx_kl | 0.010386203 | +| clip_fraction | 0.319 | +| clip_range | 0.0701 | +| entropy_loss | -6.26 | +| explained_variance | 0.448 | +| learning_rate | 4.53e-05 | +| loss | -0.0321 | +| n_updates | 54092 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000216 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1422 | +| iterations | 9570 | +| time_elapsed | 13779 | +| total_timesteps | 19599360 | +| train/ | | +| approx_kl | 0.010052603 | +| clip_fraction | 0.305 | +| clip_range | 0.0701 | +| entropy_loss | -6.59 | +| explained_variance | 0.485 | +| learning_rate | 4.53e-05 | +| loss | -0.0335 | +| n_updates | 54096 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000158 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1422 | +| iterations | 9571 | +| time_elapsed | 13781 | +| total_timesteps | 19601408 | +| train/ | | +| approx_kl | 0.010185094 | +| clip_fraction | 0.319 | +| clip_range | 0.0701 | +| entropy_loss | -6.37 | +| explained_variance | 0.508 | +| learning_rate | 4.53e-05 | +| loss | -0.0268 | +| n_updates | 54100 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.00022 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1422 | +| iterations | 9572 | +| time_elapsed | 13782 | +| total_timesteps | 19603456 | +| train/ | | +| approx_kl | 0.010811909 | +| clip_fraction | 0.325 | +| clip_range | 0.0701 | +| entropy_loss | -6.24 | +| explained_variance | 0.372 | +| learning_rate | 4.53e-05 | +| loss | -0.0257 | +| n_updates | 54104 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000129 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1422 | +| iterations | 9573 | +| time_elapsed | 13784 | +| total_timesteps | 19605504 | +| train/ | | +| approx_kl | 0.014151527 | +| clip_fraction | 0.341 | +| clip_range | 0.0701 | +| entropy_loss | -6.74 | +| explained_variance | 0.34 | +| learning_rate | 4.53e-05 | +| loss | -0.0332 | +| n_updates | 54108 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000194 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1422 | +| iterations | 9574 | +| time_elapsed | 13785 | +| total_timesteps | 19607552 | +| train/ | | +| approx_kl | 0.011506256 | +| clip_fraction | 0.338 | +| clip_range | 0.0701 | +| entropy_loss | -6.77 | +| explained_variance | 0.203 | +| learning_rate | 4.53e-05 | +| loss | -0.0314 | +| n_updates | 54112 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000175 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1422 | +| iterations | 9575 | +| time_elapsed | 13786 | +| total_timesteps | 19609600 | +| train/ | | +| approx_kl | 0.01476752 | +| clip_fraction | 0.365 | +| clip_range | 0.0701 | +| entropy_loss | -6.74 | +| explained_variance | 0.038 | +| learning_rate | 4.53e-05 | +| loss | -0.0288 | +| n_updates | 54116 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000171 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1422 | +| iterations | 9576 | +| time_elapsed | 13788 | +| total_timesteps | 19611648 | +| train/ | | +| approx_kl | 0.011553636 | +| clip_fraction | 0.326 | +| clip_range | 0.0701 | +| entropy_loss | -6.47 | +| explained_variance | 0.294 | +| learning_rate | 4.53e-05 | +| loss | -0.0302 | +| n_updates | 54120 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000212 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1422 | +| iterations | 9577 | +| time_elapsed | 13789 | +| total_timesteps | 19613696 | +| train/ | | +| approx_kl | 0.013791392 | +| clip_fraction | 0.351 | +| clip_range | 0.0701 | +| entropy_loss | -6.24 | +| explained_variance | 0.526 | +| learning_rate | 4.53e-05 | +| loss | -0.0287 | +| n_updates | 54124 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000107 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1422 | +| iterations | 9578 | +| time_elapsed | 13791 | +| total_timesteps | 19615744 | +| train/ | | +| approx_kl | 0.012593661 | +| clip_fraction | 0.345 | +| clip_range | 0.0701 | +| entropy_loss | -6.32 | +| explained_variance | 0.394 | +| learning_rate | 4.53e-05 | +| loss | -0.0272 | +| n_updates | 54128 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000361 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1422 | +| iterations | 9579 | +| time_elapsed | 13792 | +| total_timesteps | 19617792 | +| train/ | | +| approx_kl | 0.012274179 | +| clip_fraction | 0.342 | +| clip_range | 0.0701 | +| entropy_loss | -6.28 | +| explained_variance | 0.315 | +| learning_rate | 4.53e-05 | +| loss | -0.0315 | +| n_updates | 54132 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000147 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1422 | +| iterations | 9580 | +| time_elapsed | 13794 | +| total_timesteps | 19619840 | +| train/ | | +| approx_kl | 0.013845634 | +| clip_fraction | 0.344 | +| clip_range | 0.0701 | +| entropy_loss | -6.84 | +| explained_variance | -0.0637 | +| learning_rate | 4.53e-05 | +| loss | -0.0333 | +| n_updates | 54136 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000176 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1422 | +| iterations | 9581 | +| time_elapsed | 13795 | +| total_timesteps | 19621888 | +| train/ | | +| approx_kl | 0.011544175 | +| clip_fraction | 0.341 | +| clip_range | 0.0701 | +| entropy_loss | -7.13 | +| explained_variance | -0.134 | +| learning_rate | 4.53e-05 | +| loss | -0.0329 | +| n_updates | 54140 | +| policy_gradient_loss | -0.02 | +| value_loss | 8.98e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1422 | +| iterations | 9582 | +| time_elapsed | 13797 | +| total_timesteps | 19623936 | +| train/ | | +| approx_kl | 0.013794957 | +| clip_fraction | 0.323 | +| clip_range | 0.0701 | +| entropy_loss | -6.39 | +| explained_variance | 0.435 | +| learning_rate | 4.53e-05 | +| loss | -0.0336 | +| n_updates | 54144 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000234 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1422 | +| iterations | 9583 | +| time_elapsed | 13798 | +| total_timesteps | 19625984 | +| train/ | | +| approx_kl | 0.01288116 | +| clip_fraction | 0.346 | +| clip_range | 0.0701 | +| entropy_loss | -5.78 | +| explained_variance | 0.502 | +| learning_rate | 4.53e-05 | +| loss | -0.0253 | +| n_updates | 54148 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000244 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1422 | +| iterations | 9584 | +| time_elapsed | 13799 | +| total_timesteps | 19628032 | +| train/ | | +| approx_kl | 0.014316076 | +| clip_fraction | 0.37 | +| clip_range | 0.0701 | +| entropy_loss | -6.36 | +| explained_variance | 0.312 | +| learning_rate | 4.53e-05 | +| loss | -0.0304 | +| n_updates | 54152 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.00013 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.387 | +| time/ | | +| fps | 1422 | +| iterations | 9585 | +| time_elapsed | 13801 | +| total_timesteps | 19630080 | +| train/ | | +| approx_kl | 0.014563485 | +| clip_fraction | 0.331 | +| clip_range | 0.0701 | +| entropy_loss | -6.92 | +| explained_variance | 0.06 | +| learning_rate | 4.53e-05 | +| loss | -0.0328 | +| n_updates | 54156 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000177 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.387 | +| time/ | | +| fps | 1422 | +| iterations | 9586 | +| time_elapsed | 13802 | +| total_timesteps | 19632128 | +| train/ | | +| approx_kl | 0.012058411 | +| clip_fraction | 0.324 | +| clip_range | 0.0701 | +| entropy_loss | -6.32 | +| explained_variance | 0.513 | +| learning_rate | 4.53e-05 | +| loss | -0.0298 | +| n_updates | 54160 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000198 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.387 | +| time/ | | +| fps | 1422 | +| iterations | 9587 | +| time_elapsed | 13804 | +| total_timesteps | 19634176 | +| train/ | | +| approx_kl | 0.012964753 | +| clip_fraction | 0.351 | +| clip_range | 0.0701 | +| entropy_loss | -6.44 | +| explained_variance | 0.321 | +| learning_rate | 4.53e-05 | +| loss | -0.0348 | +| n_updates | 54164 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000169 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.386 | +| time/ | | +| fps | 1422 | +| iterations | 9588 | +| time_elapsed | 13805 | +| total_timesteps | 19636224 | +| train/ | | +| approx_kl | 0.013286132 | +| clip_fraction | 0.349 | +| clip_range | 0.0701 | +| entropy_loss | -6.97 | +| explained_variance | -0.164 | +| learning_rate | 4.53e-05 | +| loss | -0.0279 | +| n_updates | 54168 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000174 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.386 | +| time/ | | +| fps | 1422 | +| iterations | 9589 | +| time_elapsed | 13807 | +| total_timesteps | 19638272 | +| train/ | | +| approx_kl | 0.01339305 | +| clip_fraction | 0.342 | +| clip_range | 0.0701 | +| entropy_loss | -6.79 | +| explained_variance | 0.353 | +| learning_rate | 4.53e-05 | +| loss | -0.0312 | +| n_updates | 54172 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000133 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1422 | +| iterations | 9590 | +| time_elapsed | 13808 | +| total_timesteps | 19640320 | +| train/ | | +| approx_kl | 0.012693638 | +| clip_fraction | 0.343 | +| clip_range | 0.0701 | +| entropy_loss | -6.85 | +| explained_variance | -0.203 | +| learning_rate | 4.53e-05 | +| loss | -0.0321 | +| n_updates | 54176 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1422 | +| iterations | 9591 | +| time_elapsed | 13809 | +| total_timesteps | 19642368 | +| train/ | | +| approx_kl | 0.011373541 | +| clip_fraction | 0.313 | +| clip_range | 0.0701 | +| entropy_loss | -6.38 | +| explained_variance | 0.606 | +| learning_rate | 4.53e-05 | +| loss | -0.0158 | +| n_updates | 54180 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.00011 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1422 | +| iterations | 9592 | +| time_elapsed | 13811 | +| total_timesteps | 19644416 | +| train/ | | +| approx_kl | 0.011884324 | +| clip_fraction | 0.325 | +| clip_range | 0.0701 | +| entropy_loss | -6.41 | +| explained_variance | 0.566 | +| learning_rate | 4.53e-05 | +| loss | -0.0332 | +| n_updates | 54184 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000122 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1422 | +| iterations | 9593 | +| time_elapsed | 13812 | +| total_timesteps | 19646464 | +| train/ | | +| approx_kl | 0.009995095 | +| clip_fraction | 0.314 | +| clip_range | 0.0701 | +| entropy_loss | -5.33 | +| explained_variance | 0.703 | +| learning_rate | 4.53e-05 | +| loss | -0.0277 | +| n_updates | 54188 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000221 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1422 | +| iterations | 9594 | +| time_elapsed | 13814 | +| total_timesteps | 19648512 | +| train/ | | +| approx_kl | 0.0121525265 | +| clip_fraction | 0.358 | +| clip_range | 0.0701 | +| entropy_loss | -6.32 | +| explained_variance | 0.076 | +| learning_rate | 4.53e-05 | +| loss | -0.0302 | +| n_updates | 54192 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000116 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1422 | +| iterations | 9595 | +| time_elapsed | 13815 | +| total_timesteps | 19650560 | +| train/ | | +| approx_kl | 0.012225974 | +| clip_fraction | 0.349 | +| clip_range | 0.0701 | +| entropy_loss | -6.83 | +| explained_variance | 0.446 | +| learning_rate | 4.53e-05 | +| loss | -0.037 | +| n_updates | 54196 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000116 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1422 | +| iterations | 9596 | +| time_elapsed | 13817 | +| total_timesteps | 19652608 | +| train/ | | +| approx_kl | 0.008265296 | +| clip_fraction | 0.325 | +| clip_range | 0.0701 | +| entropy_loss | -6.56 | +| explained_variance | 0.319 | +| learning_rate | 4.53e-05 | +| loss | -0.0184 | +| n_updates | 54200 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.00031 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1422 | +| iterations | 9597 | +| time_elapsed | 13818 | +| total_timesteps | 19654656 | +| train/ | | +| approx_kl | 0.0089386385 | +| clip_fraction | 0.32 | +| clip_range | 0.0701 | +| entropy_loss | -6.68 | +| explained_variance | 0.251 | +| learning_rate | 4.53e-05 | +| loss | -0.0294 | +| n_updates | 54204 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000251 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1422 | +| iterations | 9598 | +| time_elapsed | 13820 | +| total_timesteps | 19656704 | +| train/ | | +| approx_kl | 0.0101981275 | +| clip_fraction | 0.317 | +| clip_range | 0.0701 | +| entropy_loss | -6.96 | +| explained_variance | 0.0482 | +| learning_rate | 4.53e-05 | +| loss | -0.0236 | +| n_updates | 54208 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000316 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1422 | +| iterations | 9599 | +| time_elapsed | 13821 | +| total_timesteps | 19658752 | +| train/ | | +| approx_kl | 0.011667373 | +| clip_fraction | 0.34 | +| clip_range | 0.0701 | +| entropy_loss | -6.53 | +| explained_variance | 0.49 | +| learning_rate | 4.53e-05 | +| loss | -0.0342 | +| n_updates | 54212 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000129 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1422 | +| iterations | 9600 | +| time_elapsed | 13823 | +| total_timesteps | 19660800 | +| train/ | | +| approx_kl | 0.0114647765 | +| clip_fraction | 0.326 | +| clip_range | 0.0701 | +| entropy_loss | -6.64 | +| explained_variance | 0.2 | +| learning_rate | 4.53e-05 | +| loss | -0.026 | +| n_updates | 54216 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000303 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1422 | +| iterations | 9601 | +| time_elapsed | 13824 | +| total_timesteps | 19662848 | +| train/ | | +| approx_kl | 0.014736383 | +| clip_fraction | 0.339 | +| clip_range | 0.0701 | +| entropy_loss | -5.88 | +| explained_variance | 0.69 | +| learning_rate | 4.53e-05 | +| loss | -0.0327 | +| n_updates | 54220 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000115 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1422 | +| iterations | 9602 | +| time_elapsed | 13825 | +| total_timesteps | 19664896 | +| train/ | | +| approx_kl | 0.011524726 | +| clip_fraction | 0.347 | +| clip_range | 0.0701 | +| entropy_loss | -6.61 | +| explained_variance | 0.174 | +| learning_rate | 4.53e-05 | +| loss | -0.0342 | +| n_updates | 54224 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000266 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1422 | +| iterations | 9603 | +| time_elapsed | 13827 | +| total_timesteps | 19666944 | +| train/ | | +| approx_kl | 0.013401484 | +| clip_fraction | 0.357 | +| clip_range | 0.0701 | +| entropy_loss | -6.02 | +| explained_variance | 0.733 | +| learning_rate | 4.53e-05 | +| loss | -0.0352 | +| n_updates | 54228 | +| policy_gradient_loss | -0.0216 | +| value_loss | 8.56e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.384 | +| time/ | | +| fps | 1422 | +| iterations | 9604 | +| time_elapsed | 13828 | +| total_timesteps | 19668992 | +| train/ | | +| approx_kl | 0.016100796 | +| clip_fraction | 0.36 | +| clip_range | 0.0701 | +| entropy_loss | -6.68 | +| explained_variance | -0.127 | +| learning_rate | 4.53e-05 | +| loss | -0.0288 | +| n_updates | 54232 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.00013 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1422 | +| iterations | 9605 | +| time_elapsed | 13830 | +| total_timesteps | 19671040 | +| train/ | | +| approx_kl | 0.0124111585 | +| clip_fraction | 0.338 | +| clip_range | 0.0701 | +| entropy_loss | -6.27 | +| explained_variance | 0.522 | +| learning_rate | 4.53e-05 | +| loss | -0.0261 | +| n_updates | 54236 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.0003 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1422 | +| iterations | 9606 | +| time_elapsed | 13831 | +| total_timesteps | 19673088 | +| train/ | | +| approx_kl | 0.01531334 | +| clip_fraction | 0.358 | +| clip_range | 0.0701 | +| entropy_loss | -6.16 | +| explained_variance | 0.455 | +| learning_rate | 4.53e-05 | +| loss | -0.0309 | +| n_updates | 54240 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000158 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1422 | +| iterations | 9607 | +| time_elapsed | 13833 | +| total_timesteps | 19675136 | +| train/ | | +| approx_kl | 0.014087535 | +| clip_fraction | 0.351 | +| clip_range | 0.0701 | +| entropy_loss | -6.79 | +| explained_variance | 0.194 | +| learning_rate | 4.53e-05 | +| loss | -0.0353 | +| n_updates | 54244 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000274 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1422 | +| iterations | 9608 | +| time_elapsed | 13834 | +| total_timesteps | 19677184 | +| train/ | | +| approx_kl | 0.012217207 | +| clip_fraction | 0.326 | +| clip_range | 0.0701 | +| entropy_loss | -6.78 | +| explained_variance | 0.243 | +| learning_rate | 4.53e-05 | +| loss | -0.0303 | +| n_updates | 54248 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000197 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1422 | +| iterations | 9609 | +| time_elapsed | 13836 | +| total_timesteps | 19679232 | +| train/ | | +| approx_kl | 0.014243295 | +| clip_fraction | 0.357 | +| clip_range | 0.0701 | +| entropy_loss | -7 | +| explained_variance | -0.0755 | +| learning_rate | 4.53e-05 | +| loss | -0.0325 | +| n_updates | 54252 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000147 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.384 | +| time/ | | +| fps | 1422 | +| iterations | 9610 | +| time_elapsed | 13837 | +| total_timesteps | 19681280 | +| train/ | | +| approx_kl | 0.0100995945 | +| clip_fraction | 0.318 | +| clip_range | 0.0701 | +| entropy_loss | -6.51 | +| explained_variance | 0.233 | +| learning_rate | 4.53e-05 | +| loss | -0.0249 | +| n_updates | 54256 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000411 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.384 | +| time/ | | +| fps | 1422 | +| iterations | 9611 | +| time_elapsed | 13838 | +| total_timesteps | 19683328 | +| train/ | | +| approx_kl | 0.013906063 | +| clip_fraction | 0.328 | +| clip_range | 0.0701 | +| entropy_loss | -6.06 | +| explained_variance | 0.4 | +| learning_rate | 4.53e-05 | +| loss | -0.0212 | +| n_updates | 54260 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000307 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.385 | +| time/ | | +| fps | 1422 | +| iterations | 9612 | +| time_elapsed | 13840 | +| total_timesteps | 19685376 | +| train/ | | +| approx_kl | 0.013911966 | +| clip_fraction | 0.353 | +| clip_range | 0.0701 | +| entropy_loss | -6.89 | +| explained_variance | -0.0829 | +| learning_rate | 4.53e-05 | +| loss | -0.037 | +| n_updates | 54264 | +| policy_gradient_loss | -0.0225 | +| value_loss | 0.000161 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1422 | +| iterations | 9613 | +| time_elapsed | 13841 | +| total_timesteps | 19687424 | +| train/ | | +| approx_kl | 0.012970779 | +| clip_fraction | 0.373 | +| clip_range | 0.0701 | +| entropy_loss | -6.86 | +| explained_variance | 0.277 | +| learning_rate | 4.53e-05 | +| loss | -0.0363 | +| n_updates | 54268 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000132 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1422 | +| iterations | 9614 | +| time_elapsed | 13843 | +| total_timesteps | 19689472 | +| train/ | | +| approx_kl | 0.013629666 | +| clip_fraction | 0.382 | +| clip_range | 0.0701 | +| entropy_loss | -6.39 | +| explained_variance | 0.605 | +| learning_rate | 4.53e-05 | +| loss | -0.0378 | +| n_updates | 54272 | +| policy_gradient_loss | -0.0234 | +| value_loss | 7.28e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1422 | +| iterations | 9615 | +| time_elapsed | 13844 | +| total_timesteps | 19691520 | +| train/ | | +| approx_kl | 0.01458863 | +| clip_fraction | 0.352 | +| clip_range | 0.0701 | +| entropy_loss | -5.99 | +| explained_variance | 0.783 | +| learning_rate | 4.53e-05 | +| loss | -0.033 | +| n_updates | 54276 | +| policy_gradient_loss | -0.0226 | +| value_loss | 6.13e-05 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1422 | +| iterations | 9616 | +| time_elapsed | 13845 | +| total_timesteps | 19693568 | +| train/ | | +| approx_kl | 0.0142947445 | +| clip_fraction | 0.355 | +| clip_range | 0.0701 | +| entropy_loss | -6.57 | +| explained_variance | 0.144 | +| learning_rate | 4.53e-05 | +| loss | -0.0296 | +| n_updates | 54280 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000157 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1422 | +| iterations | 9617 | +| time_elapsed | 13847 | +| total_timesteps | 19695616 | +| train/ | | +| approx_kl | 0.011689446 | +| clip_fraction | 0.329 | +| clip_range | 0.0701 | +| entropy_loss | -6.39 | +| explained_variance | 0.591 | +| learning_rate | 4.53e-05 | +| loss | -0.0264 | +| n_updates | 54284 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1422 | +| iterations | 9618 | +| time_elapsed | 13848 | +| total_timesteps | 19697664 | +| train/ | | +| approx_kl | 0.010745948 | +| clip_fraction | 0.311 | +| clip_range | 0.0701 | +| entropy_loss | -6.48 | +| explained_variance | 0.473 | +| learning_rate | 4.53e-05 | +| loss | -0.0303 | +| n_updates | 54288 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000194 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1422 | +| iterations | 9619 | +| time_elapsed | 13850 | +| total_timesteps | 19699712 | +| train/ | | +| approx_kl | 0.013252411 | +| clip_fraction | 0.363 | +| clip_range | 0.0701 | +| entropy_loss | -6.79 | +| explained_variance | 0.0878 | +| learning_rate | 4.53e-05 | +| loss | -0.0334 | +| n_updates | 54292 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000131 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1422 | +| iterations | 9620 | +| time_elapsed | 13851 | +| total_timesteps | 19701760 | +| train/ | | +| approx_kl | 0.013320452 | +| clip_fraction | 0.322 | +| clip_range | 0.0701 | +| entropy_loss | -6.61 | +| explained_variance | 0.375 | +| learning_rate | 4.53e-05 | +| loss | -0.0328 | +| n_updates | 54296 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.00018 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1422 | +| iterations | 9621 | +| time_elapsed | 13853 | +| total_timesteps | 19703808 | +| train/ | | +| approx_kl | 0.014886765 | +| clip_fraction | 0.354 | +| clip_range | 0.0701 | +| entropy_loss | -6.7 | +| explained_variance | 0.402 | +| learning_rate | 4.53e-05 | +| loss | -0.0314 | +| n_updates | 54300 | +| policy_gradient_loss | -0.022 | +| value_loss | 8.71e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1422 | +| iterations | 9622 | +| time_elapsed | 13854 | +| total_timesteps | 19705856 | +| train/ | | +| approx_kl | 0.014338712 | +| clip_fraction | 0.339 | +| clip_range | 0.0701 | +| entropy_loss | -6.59 | +| explained_variance | 0.31 | +| learning_rate | 4.53e-05 | +| loss | -0.0279 | +| n_updates | 54304 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000299 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1422 | +| iterations | 9623 | +| time_elapsed | 13855 | +| total_timesteps | 19707904 | +| train/ | | +| approx_kl | 0.011216981 | +| clip_fraction | 0.311 | +| clip_range | 0.0701 | +| entropy_loss | -6.35 | +| explained_variance | 0.427 | +| learning_rate | 4.53e-05 | +| loss | -0.0311 | +| n_updates | 54308 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000262 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1422 | +| iterations | 9624 | +| time_elapsed | 13857 | +| total_timesteps | 19709952 | +| train/ | | +| approx_kl | 0.0152995335 | +| clip_fraction | 0.377 | +| clip_range | 0.0701 | +| entropy_loss | -6.35 | +| explained_variance | 0.393 | +| learning_rate | 4.53e-05 | +| loss | -0.0291 | +| n_updates | 54312 | +| policy_gradient_loss | -0.0233 | +| value_loss | 0.000117 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1422 | +| iterations | 9625 | +| time_elapsed | 13858 | +| total_timesteps | 19712000 | +| train/ | | +| approx_kl | 0.013248602 | +| clip_fraction | 0.314 | +| clip_range | 0.0701 | +| entropy_loss | -6.04 | +| explained_variance | 0.564 | +| learning_rate | 4.53e-05 | +| loss | -0.0345 | +| n_updates | 54316 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000247 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1422 | +| iterations | 9626 | +| time_elapsed | 13860 | +| total_timesteps | 19714048 | +| train/ | | +| approx_kl | 0.01355632 | +| clip_fraction | 0.349 | +| clip_range | 0.0701 | +| entropy_loss | -6.41 | +| explained_variance | 0.439 | +| learning_rate | 4.53e-05 | +| loss | -0.03 | +| n_updates | 54320 | +| policy_gradient_loss | -0.0211 | +| value_loss | 8.22e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1422 | +| iterations | 9627 | +| time_elapsed | 13861 | +| total_timesteps | 19716096 | +| train/ | | +| approx_kl | 0.012986057 | +| clip_fraction | 0.336 | +| clip_range | 0.0701 | +| entropy_loss | -6.88 | +| explained_variance | 0.305 | +| learning_rate | 4.53e-05 | +| loss | -0.0282 | +| n_updates | 54324 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000157 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1422 | +| iterations | 9628 | +| time_elapsed | 13863 | +| total_timesteps | 19718144 | +| train/ | | +| approx_kl | 0.010549823 | +| clip_fraction | 0.31 | +| clip_range | 0.0701 | +| entropy_loss | -6.39 | +| explained_variance | 0.52 | +| learning_rate | 4.53e-05 | +| loss | -0.0309 | +| n_updates | 54328 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000145 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1422 | +| iterations | 9629 | +| time_elapsed | 13864 | +| total_timesteps | 19720192 | +| train/ | | +| approx_kl | 0.009295393 | +| clip_fraction | 0.321 | +| clip_range | 0.0701 | +| entropy_loss | -6.3 | +| explained_variance | 0.359 | +| learning_rate | 4.53e-05 | +| loss | -0.0239 | +| n_updates | 54332 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.00031 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1422 | +| iterations | 9630 | +| time_elapsed | 13866 | +| total_timesteps | 19722240 | +| train/ | | +| approx_kl | 0.012011904 | +| clip_fraction | 0.316 | +| clip_range | 0.0701 | +| entropy_loss | -6.37 | +| explained_variance | 0.322 | +| learning_rate | 4.53e-05 | +| loss | -0.0243 | +| n_updates | 54336 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000339 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1422 | +| iterations | 9631 | +| time_elapsed | 13867 | +| total_timesteps | 19724288 | +| train/ | | +| approx_kl | 0.014230002 | +| clip_fraction | 0.372 | +| clip_range | 0.0701 | +| entropy_loss | -6.43 | +| explained_variance | 0.436 | +| learning_rate | 4.53e-05 | +| loss | -0.0359 | +| n_updates | 54340 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000146 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1422 | +| iterations | 9632 | +| time_elapsed | 13869 | +| total_timesteps | 19726336 | +| train/ | | +| approx_kl | 0.013695763 | +| clip_fraction | 0.353 | +| clip_range | 0.0701 | +| entropy_loss | -7.01 | +| explained_variance | -0.213 | +| learning_rate | 4.53e-05 | +| loss | -0.0348 | +| n_updates | 54344 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000154 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1422 | +| iterations | 9633 | +| time_elapsed | 13870 | +| total_timesteps | 19728384 | +| train/ | | +| approx_kl | 0.011821527 | +| clip_fraction | 0.321 | +| clip_range | 0.0701 | +| entropy_loss | -6.29 | +| explained_variance | 0.446 | +| learning_rate | 4.53e-05 | +| loss | -0.0176 | +| n_updates | 54348 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000297 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1422 | +| iterations | 9634 | +| time_elapsed | 13871 | +| total_timesteps | 19730432 | +| train/ | | +| approx_kl | 0.012638816 | +| clip_fraction | 0.337 | +| clip_range | 0.0701 | +| entropy_loss | -6.48 | +| explained_variance | 0.206 | +| learning_rate | 4.53e-05 | +| loss | -0.0396 | +| n_updates | 54352 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000201 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1422 | +| iterations | 9635 | +| time_elapsed | 13873 | +| total_timesteps | 19732480 | +| train/ | | +| approx_kl | 0.013960743 | +| clip_fraction | 0.326 | +| clip_range | 0.0701 | +| entropy_loss | -5.89 | +| explained_variance | 0.497 | +| learning_rate | 4.53e-05 | +| loss | -0.0276 | +| n_updates | 54356 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000283 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1422 | +| iterations | 9636 | +| time_elapsed | 13874 | +| total_timesteps | 19734528 | +| train/ | | +| approx_kl | 0.016440477 | +| clip_fraction | 0.386 | +| clip_range | 0.0701 | +| entropy_loss | -6.48 | +| explained_variance | -0.337 | +| learning_rate | 4.53e-05 | +| loss | -0.035 | +| n_updates | 54360 | +| policy_gradient_loss | -0.0236 | +| value_loss | 0.000144 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1422 | +| iterations | 9637 | +| time_elapsed | 13876 | +| total_timesteps | 19736576 | +| train/ | | +| approx_kl | 0.014919235 | +| clip_fraction | 0.35 | +| clip_range | 0.0701 | +| entropy_loss | -6.14 | +| explained_variance | 0.44 | +| learning_rate | 4.53e-05 | +| loss | -0.0318 | +| n_updates | 54364 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.00024 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1422 | +| iterations | 9638 | +| time_elapsed | 13877 | +| total_timesteps | 19738624 | +| train/ | | +| approx_kl | 0.010957447 | +| clip_fraction | 0.305 | +| clip_range | 0.0701 | +| entropy_loss | -6.35 | +| explained_variance | 0.435 | +| learning_rate | 4.53e-05 | +| loss | -0.0282 | +| n_updates | 54368 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000253 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1422 | +| iterations | 9639 | +| time_elapsed | 13879 | +| total_timesteps | 19740672 | +| train/ | | +| approx_kl | 0.013421745 | +| clip_fraction | 0.336 | +| clip_range | 0.0701 | +| entropy_loss | -6.76 | +| explained_variance | -0.0926 | +| learning_rate | 4.53e-05 | +| loss | -0.0368 | +| n_updates | 54372 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000149 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1422 | +| iterations | 9640 | +| time_elapsed | 13880 | +| total_timesteps | 19742720 | +| train/ | | +| approx_kl | 0.010436709 | +| clip_fraction | 0.315 | +| clip_range | 0.0701 | +| entropy_loss | -7.24 | +| explained_variance | -0.129 | +| learning_rate | 4.53e-05 | +| loss | -0.03 | +| n_updates | 54376 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000132 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1422 | +| iterations | 9641 | +| time_elapsed | 13882 | +| total_timesteps | 19744768 | +| train/ | | +| approx_kl | 0.0142079685 | +| clip_fraction | 0.353 | +| clip_range | 0.0701 | +| entropy_loss | -6.5 | +| explained_variance | 0.585 | +| learning_rate | 4.53e-05 | +| loss | -0.0363 | +| n_updates | 54380 | +| policy_gradient_loss | -0.0205 | +| value_loss | 9.71e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1422 | +| iterations | 9642 | +| time_elapsed | 13883 | +| total_timesteps | 19746816 | +| train/ | | +| approx_kl | 0.013944506 | +| clip_fraction | 0.343 | +| clip_range | 0.0701 | +| entropy_loss | -6.48 | +| explained_variance | 0.334 | +| learning_rate | 4.53e-05 | +| loss | -0.0297 | +| n_updates | 54384 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000176 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1422 | +| iterations | 9643 | +| time_elapsed | 13884 | +| total_timesteps | 19748864 | +| train/ | | +| approx_kl | 0.013128882 | +| clip_fraction | 0.322 | +| clip_range | 0.0701 | +| entropy_loss | -6.37 | +| explained_variance | 0.612 | +| learning_rate | 4.53e-05 | +| loss | -0.0271 | +| n_updates | 54388 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000158 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1422 | +| iterations | 9644 | +| time_elapsed | 13886 | +| total_timesteps | 19750912 | +| train/ | | +| approx_kl | 0.013984034 | +| clip_fraction | 0.362 | +| clip_range | 0.0701 | +| entropy_loss | -6.01 | +| explained_variance | 0.776 | +| learning_rate | 4.53e-05 | +| loss | -0.0312 | +| n_updates | 54392 | +| policy_gradient_loss | -0.0217 | +| value_loss | 7.64e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1422 | +| iterations | 9645 | +| time_elapsed | 13887 | +| total_timesteps | 19752960 | +| train/ | | +| approx_kl | 0.01238954 | +| clip_fraction | 0.341 | +| clip_range | 0.0701 | +| entropy_loss | -6.41 | +| explained_variance | 0.272 | +| learning_rate | 4.53e-05 | +| loss | -0.0288 | +| n_updates | 54396 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000235 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1422 | +| iterations | 9646 | +| time_elapsed | 13889 | +| total_timesteps | 19755008 | +| train/ | | +| approx_kl | 0.009896681 | +| clip_fraction | 0.329 | +| clip_range | 0.0701 | +| entropy_loss | -6.61 | +| explained_variance | 0.331 | +| learning_rate | 4.53e-05 | +| loss | -0.0284 | +| n_updates | 54400 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000184 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1422 | +| iterations | 9647 | +| time_elapsed | 13890 | +| total_timesteps | 19757056 | +| train/ | | +| approx_kl | 0.015650528 | +| clip_fraction | 0.365 | +| clip_range | 0.0701 | +| entropy_loss | -6.42 | +| explained_variance | 0.634 | +| learning_rate | 4.53e-05 | +| loss | -0.0318 | +| n_updates | 54404 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000103 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1422 | +| iterations | 9648 | +| time_elapsed | 13892 | +| total_timesteps | 19759104 | +| train/ | | +| approx_kl | 0.013471555 | +| clip_fraction | 0.371 | +| clip_range | 0.0701 | +| entropy_loss | -6.73 | +| explained_variance | 0.0466 | +| learning_rate | 4.53e-05 | +| loss | -0.0398 | +| n_updates | 54408 | +| policy_gradient_loss | -0.0224 | +| value_loss | 8.75e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1422 | +| iterations | 9649 | +| time_elapsed | 13893 | +| total_timesteps | 19761152 | +| train/ | | +| approx_kl | 0.011050395 | +| clip_fraction | 0.332 | +| clip_range | 0.0701 | +| entropy_loss | -6.78 | +| explained_variance | 0.277 | +| learning_rate | 4.53e-05 | +| loss | -0.0261 | +| n_updates | 54412 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000193 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1422 | +| iterations | 9650 | +| time_elapsed | 13895 | +| total_timesteps | 19763200 | +| train/ | | +| approx_kl | 0.016702544 | +| clip_fraction | 0.357 | +| clip_range | 0.0701 | +| entropy_loss | -6.5 | +| explained_variance | 0.34 | +| learning_rate | 4.53e-05 | +| loss | -0.03 | +| n_updates | 54416 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000129 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1422 | +| iterations | 9651 | +| time_elapsed | 13896 | +| total_timesteps | 19765248 | +| train/ | | +| approx_kl | 0.015089051 | +| clip_fraction | 0.396 | +| clip_range | 0.0701 | +| entropy_loss | -6.29 | +| explained_variance | 0.706 | +| learning_rate | 4.53e-05 | +| loss | -0.0351 | +| n_updates | 54420 | +| policy_gradient_loss | -0.0226 | +| value_loss | 6.51e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1422 | +| iterations | 9652 | +| time_elapsed | 13898 | +| total_timesteps | 19767296 | +| train/ | | +| approx_kl | 0.016715307 | +| clip_fraction | 0.346 | +| clip_range | 0.0701 | +| entropy_loss | -6.29 | +| explained_variance | 0.412 | +| learning_rate | 4.53e-05 | +| loss | -0.0334 | +| n_updates | 54424 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000209 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1422 | +| iterations | 9653 | +| time_elapsed | 13899 | +| total_timesteps | 19769344 | +| train/ | | +| approx_kl | 0.011424892 | +| clip_fraction | 0.323 | +| clip_range | 0.0701 | +| entropy_loss | -6.88 | +| explained_variance | -0.107 | +| learning_rate | 4.53e-05 | +| loss | -0.0289 | +| n_updates | 54428 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000123 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1422 | +| iterations | 9654 | +| time_elapsed | 13900 | +| total_timesteps | 19771392 | +| train/ | | +| approx_kl | 0.014151829 | +| clip_fraction | 0.352 | +| clip_range | 0.0701 | +| entropy_loss | -6.59 | +| explained_variance | 0.522 | +| learning_rate | 4.53e-05 | +| loss | -0.0314 | +| n_updates | 54432 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000152 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1422 | +| iterations | 9655 | +| time_elapsed | 13902 | +| total_timesteps | 19773440 | +| train/ | | +| approx_kl | 0.011105974 | +| clip_fraction | 0.335 | +| clip_range | 0.0701 | +| entropy_loss | -6.46 | +| explained_variance | 0.594 | +| learning_rate | 4.53e-05 | +| loss | -0.0229 | +| n_updates | 54436 | +| policy_gradient_loss | -0.018 | +| value_loss | 8.96e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1422 | +| iterations | 9656 | +| time_elapsed | 13903 | +| total_timesteps | 19775488 | +| train/ | | +| approx_kl | 0.013266714 | +| clip_fraction | 0.338 | +| clip_range | 0.0701 | +| entropy_loss | -6.66 | +| explained_variance | 0.461 | +| learning_rate | 4.53e-05 | +| loss | -0.0284 | +| n_updates | 54440 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000126 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1422 | +| iterations | 9657 | +| time_elapsed | 13905 | +| total_timesteps | 19777536 | +| train/ | | +| approx_kl | 0.012328463 | +| clip_fraction | 0.352 | +| clip_range | 0.0701 | +| entropy_loss | -6.33 | +| explained_variance | 0.769 | +| learning_rate | 4.53e-05 | +| loss | -0.0361 | +| n_updates | 54444 | +| policy_gradient_loss | -0.0209 | +| value_loss | 6.37e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1422 | +| iterations | 9658 | +| time_elapsed | 13906 | +| total_timesteps | 19779584 | +| train/ | | +| approx_kl | 0.014011873 | +| clip_fraction | 0.325 | +| clip_range | 0.0701 | +| entropy_loss | -6.45 | +| explained_variance | 0.357 | +| learning_rate | 4.53e-05 | +| loss | -0.0338 | +| n_updates | 54448 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000146 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1422 | +| iterations | 9659 | +| time_elapsed | 13908 | +| total_timesteps | 19781632 | +| train/ | | +| approx_kl | 0.009542228 | +| clip_fraction | 0.307 | +| clip_range | 0.0701 | +| entropy_loss | -6.06 | +| explained_variance | 0.704 | +| learning_rate | 4.53e-05 | +| loss | -0.0269 | +| n_updates | 54452 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000133 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1422 | +| iterations | 9660 | +| time_elapsed | 13909 | +| total_timesteps | 19783680 | +| train/ | | +| approx_kl | 0.011668136 | +| clip_fraction | 0.324 | +| clip_range | 0.0701 | +| entropy_loss | -5.82 | +| explained_variance | 0.547 | +| learning_rate | 4.53e-05 | +| loss | -0.0183 | +| n_updates | 54456 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000257 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1422 | +| iterations | 9661 | +| time_elapsed | 13911 | +| total_timesteps | 19785728 | +| train/ | | +| approx_kl | 0.014394241 | +| clip_fraction | 0.387 | +| clip_range | 0.0701 | +| entropy_loss | -6.28 | +| explained_variance | 0.221 | +| learning_rate | 4.53e-05 | +| loss | -0.042 | +| n_updates | 54460 | +| policy_gradient_loss | -0.025 | +| value_loss | 8.62e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1422 | +| iterations | 9662 | +| time_elapsed | 13912 | +| total_timesteps | 19787776 | +| train/ | | +| approx_kl | 0.015279377 | +| clip_fraction | 0.366 | +| clip_range | 0.0701 | +| entropy_loss | -6.46 | +| explained_variance | 0.613 | +| learning_rate | 4.53e-05 | +| loss | -0.0352 | +| n_updates | 54464 | +| policy_gradient_loss | -0.0217 | +| value_loss | 7.49e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1422 | +| iterations | 9663 | +| time_elapsed | 13913 | +| total_timesteps | 19789824 | +| train/ | | +| approx_kl | 0.015204906 | +| clip_fraction | 0.354 | +| clip_range | 0.0701 | +| entropy_loss | -6.68 | +| explained_variance | 0.19 | +| learning_rate | 4.53e-05 | +| loss | -0.0297 | +| n_updates | 54468 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000173 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1422 | +| iterations | 9664 | +| time_elapsed | 13915 | +| total_timesteps | 19791872 | +| train/ | | +| approx_kl | 0.017297195 | +| clip_fraction | 0.363 | +| clip_range | 0.0701 | +| entropy_loss | -6.52 | +| explained_variance | 0.269 | +| learning_rate | 4.53e-05 | +| loss | -0.033 | +| n_updates | 54472 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000261 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1422 | +| iterations | 9665 | +| time_elapsed | 13916 | +| total_timesteps | 19793920 | +| train/ | | +| approx_kl | 0.013604044 | +| clip_fraction | 0.324 | +| clip_range | 0.0701 | +| entropy_loss | -6.76 | +| explained_variance | 0.36 | +| learning_rate | 4.53e-05 | +| loss | -0.0289 | +| n_updates | 54476 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000169 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1422 | +| iterations | 9666 | +| time_elapsed | 13918 | +| total_timesteps | 19795968 | +| train/ | | +| approx_kl | 0.012390565 | +| clip_fraction | 0.355 | +| clip_range | 0.0701 | +| entropy_loss | -6.72 | +| explained_variance | 0.0986 | +| learning_rate | 4.53e-05 | +| loss | -0.0279 | +| n_updates | 54480 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.00041 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1422 | +| iterations | 9667 | +| time_elapsed | 13919 | +| total_timesteps | 19798016 | +| train/ | | +| approx_kl | 0.016130304 | +| clip_fraction | 0.341 | +| clip_range | 0.0701 | +| entropy_loss | -5.9 | +| explained_variance | 0.616 | +| learning_rate | 4.53e-05 | +| loss | -0.0312 | +| n_updates | 54484 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000184 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1422 | +| iterations | 9668 | +| time_elapsed | 13921 | +| total_timesteps | 19800064 | +| train/ | | +| approx_kl | 0.017337635 | +| clip_fraction | 0.363 | +| clip_range | 0.0701 | +| entropy_loss | -6.56 | +| explained_variance | 0.27 | +| learning_rate | 4.53e-05 | +| loss | -0.0356 | +| n_updates | 54488 | +| policy_gradient_loss | -0.0224 | +| value_loss | 0.000137 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1422 | +| iterations | 9669 | +| time_elapsed | 13922 | +| total_timesteps | 19802112 | +| train/ | | +| approx_kl | 0.015095945 | +| clip_fraction | 0.366 | +| clip_range | 0.07 | +| entropy_loss | -6.74 | +| explained_variance | -0.0715 | +| learning_rate | 4.53e-05 | +| loss | -0.0324 | +| n_updates | 54492 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000183 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1422 | +| iterations | 9670 | +| time_elapsed | 13924 | +| total_timesteps | 19804160 | +| train/ | | +| approx_kl | 0.014532552 | +| clip_fraction | 0.34 | +| clip_range | 0.07 | +| entropy_loss | -6.59 | +| explained_variance | 0.236 | +| learning_rate | 4.53e-05 | +| loss | -0.0272 | +| n_updates | 54496 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000205 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1422 | +| iterations | 9671 | +| time_elapsed | 13925 | +| total_timesteps | 19806208 | +| train/ | | +| approx_kl | 0.013607709 | +| clip_fraction | 0.347 | +| clip_range | 0.07 | +| entropy_loss | -5.69 | +| explained_variance | 0.707 | +| learning_rate | 4.53e-05 | +| loss | -0.0285 | +| n_updates | 54500 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000161 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1422 | +| iterations | 9672 | +| time_elapsed | 13927 | +| total_timesteps | 19808256 | +| train/ | | +| approx_kl | 0.011386594 | +| clip_fraction | 0.319 | +| clip_range | 0.07 | +| entropy_loss | -6.17 | +| explained_variance | 0.419 | +| learning_rate | 4.53e-05 | +| loss | -0.0275 | +| n_updates | 54504 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000254 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1422 | +| iterations | 9673 | +| time_elapsed | 13928 | +| total_timesteps | 19810304 | +| train/ | | +| approx_kl | 0.011952524 | +| clip_fraction | 0.352 | +| clip_range | 0.07 | +| entropy_loss | -6.25 | +| explained_variance | 0.326 | +| learning_rate | 4.53e-05 | +| loss | -0.0309 | +| n_updates | 54508 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000412 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1422 | +| iterations | 9674 | +| time_elapsed | 13930 | +| total_timesteps | 19812352 | +| train/ | | +| approx_kl | 0.012751978 | +| clip_fraction | 0.382 | +| clip_range | 0.07 | +| entropy_loss | -6.65 | +| explained_variance | 0.38 | +| learning_rate | 4.53e-05 | +| loss | -0.0365 | +| n_updates | 54512 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000143 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1422 | +| iterations | 9675 | +| time_elapsed | 13931 | +| total_timesteps | 19814400 | +| train/ | | +| approx_kl | 0.010230471 | +| clip_fraction | 0.311 | +| clip_range | 0.07 | +| entropy_loss | -6.61 | +| explained_variance | 0.352 | +| learning_rate | 4.53e-05 | +| loss | -0.0289 | +| n_updates | 54516 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000288 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1422 | +| iterations | 9676 | +| time_elapsed | 13933 | +| total_timesteps | 19816448 | +| train/ | | +| approx_kl | 0.016602827 | +| clip_fraction | 0.391 | +| clip_range | 0.07 | +| entropy_loss | -6.8 | +| explained_variance | -0.217 | +| learning_rate | 4.53e-05 | +| loss | -0.0435 | +| n_updates | 54520 | +| policy_gradient_loss | -0.0245 | +| value_loss | 0.000129 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1422 | +| iterations | 9677 | +| time_elapsed | 13934 | +| total_timesteps | 19818496 | +| train/ | | +| approx_kl | 0.011463718 | +| clip_fraction | 0.314 | +| clip_range | 0.07 | +| entropy_loss | -7.06 | +| explained_variance | -0.0487 | +| learning_rate | 4.53e-05 | +| loss | -0.0312 | +| n_updates | 54524 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000264 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1422 | +| iterations | 9678 | +| time_elapsed | 13935 | +| total_timesteps | 19820544 | +| train/ | | +| approx_kl | 0.015395119 | +| clip_fraction | 0.328 | +| clip_range | 0.07 | +| entropy_loss | -6.06 | +| explained_variance | 0.421 | +| learning_rate | 4.53e-05 | +| loss | -0.0225 | +| n_updates | 54528 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000331 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1422 | +| iterations | 9679 | +| time_elapsed | 13937 | +| total_timesteps | 19822592 | +| train/ | | +| approx_kl | 0.014113244 | +| clip_fraction | 0.355 | +| clip_range | 0.07 | +| entropy_loss | -5.99 | +| explained_variance | 0.432 | +| learning_rate | 4.53e-05 | +| loss | -0.0308 | +| n_updates | 54532 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000189 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1422 | +| iterations | 9680 | +| time_elapsed | 13938 | +| total_timesteps | 19824640 | +| train/ | | +| approx_kl | 0.0135428775 | +| clip_fraction | 0.361 | +| clip_range | 0.07 | +| entropy_loss | -6.6 | +| explained_variance | 0.39 | +| learning_rate | 4.53e-05 | +| loss | -0.0354 | +| n_updates | 54536 | +| policy_gradient_loss | -0.0233 | +| value_loss | 0.000123 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1422 | +| iterations | 9681 | +| time_elapsed | 13940 | +| total_timesteps | 19826688 | +| train/ | | +| approx_kl | 0.015638262 | +| clip_fraction | 0.38 | +| clip_range | 0.07 | +| entropy_loss | -6.31 | +| explained_variance | 0.764 | +| learning_rate | 4.53e-05 | +| loss | -0.0278 | +| n_updates | 54540 | +| policy_gradient_loss | -0.0228 | +| value_loss | 6.62e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1422 | +| iterations | 9682 | +| time_elapsed | 13941 | +| total_timesteps | 19828736 | +| train/ | | +| approx_kl | 0.014137096 | +| clip_fraction | 0.346 | +| clip_range | 0.07 | +| entropy_loss | -6.1 | +| explained_variance | 0.404 | +| learning_rate | 4.53e-05 | +| loss | -0.032 | +| n_updates | 54544 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000249 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1422 | +| iterations | 9683 | +| time_elapsed | 13943 | +| total_timesteps | 19830784 | +| train/ | | +| approx_kl | 0.011924667 | +| clip_fraction | 0.339 | +| clip_range | 0.07 | +| entropy_loss | -6.81 | +| explained_variance | 0.2 | +| learning_rate | 4.53e-05 | +| loss | -0.0248 | +| n_updates | 54548 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000258 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1422 | +| iterations | 9684 | +| time_elapsed | 13944 | +| total_timesteps | 19832832 | +| train/ | | +| approx_kl | 0.011344142 | +| clip_fraction | 0.342 | +| clip_range | 0.07 | +| entropy_loss | -6.87 | +| explained_variance | -0.0489 | +| learning_rate | 4.53e-05 | +| loss | -0.0344 | +| n_updates | 54552 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000151 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1422 | +| iterations | 9685 | +| time_elapsed | 13946 | +| total_timesteps | 19834880 | +| train/ | | +| approx_kl | 0.009186696 | +| clip_fraction | 0.317 | +| clip_range | 0.07 | +| entropy_loss | -6.66 | +| explained_variance | 0.386 | +| learning_rate | 4.53e-05 | +| loss | -0.0312 | +| n_updates | 54556 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000216 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1422 | +| iterations | 9686 | +| time_elapsed | 13947 | +| total_timesteps | 19836928 | +| train/ | | +| approx_kl | 0.012665341 | +| clip_fraction | 0.341 | +| clip_range | 0.07 | +| entropy_loss | -6.27 | +| explained_variance | 0.492 | +| learning_rate | 4.53e-05 | +| loss | -0.0244 | +| n_updates | 54560 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000185 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1422 | +| iterations | 9687 | +| time_elapsed | 13948 | +| total_timesteps | 19838976 | +| train/ | | +| approx_kl | 0.012386875 | +| clip_fraction | 0.354 | +| clip_range | 0.07 | +| entropy_loss | -6.4 | +| explained_variance | 0.415 | +| learning_rate | 4.53e-05 | +| loss | -0.0367 | +| n_updates | 54564 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000297 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1422 | +| iterations | 9688 | +| time_elapsed | 13950 | +| total_timesteps | 19841024 | +| train/ | | +| approx_kl | 0.013729333 | +| clip_fraction | 0.359 | +| clip_range | 0.07 | +| entropy_loss | -6.42 | +| explained_variance | 0.378 | +| learning_rate | 4.53e-05 | +| loss | -0.0337 | +| n_updates | 54568 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000147 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1422 | +| iterations | 9689 | +| time_elapsed | 13951 | +| total_timesteps | 19843072 | +| train/ | | +| approx_kl | 0.01653435 | +| clip_fraction | 0.354 | +| clip_range | 0.07 | +| entropy_loss | -6.51 | +| explained_variance | 0.495 | +| learning_rate | 4.53e-05 | +| loss | -0.0266 | +| n_updates | 54572 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.00015 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1422 | +| iterations | 9690 | +| time_elapsed | 13953 | +| total_timesteps | 19845120 | +| train/ | | +| approx_kl | 0.01337849 | +| clip_fraction | 0.349 | +| clip_range | 0.07 | +| entropy_loss | -6.75 | +| explained_variance | 0.0854 | +| learning_rate | 4.53e-05 | +| loss | -0.0322 | +| n_updates | 54576 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000264 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1422 | +| iterations | 9691 | +| time_elapsed | 13954 | +| total_timesteps | 19847168 | +| train/ | | +| approx_kl | 0.013434421 | +| clip_fraction | 0.332 | +| clip_range | 0.07 | +| entropy_loss | -6.48 | +| explained_variance | 0.272 | +| learning_rate | 4.53e-05 | +| loss | -0.032 | +| n_updates | 54580 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000196 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1422 | +| iterations | 9692 | +| time_elapsed | 13956 | +| total_timesteps | 19849216 | +| train/ | | +| approx_kl | 0.015616766 | +| clip_fraction | 0.34 | +| clip_range | 0.07 | +| entropy_loss | -6.22 | +| explained_variance | 0.602 | +| learning_rate | 4.53e-05 | +| loss | -0.0308 | +| n_updates | 54584 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000147 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1422 | +| iterations | 9693 | +| time_elapsed | 13957 | +| total_timesteps | 19851264 | +| train/ | | +| approx_kl | 0.010359772 | +| clip_fraction | 0.319 | +| clip_range | 0.07 | +| entropy_loss | -6.74 | +| explained_variance | 0.234 | +| learning_rate | 4.53e-05 | +| loss | -0.035 | +| n_updates | 54588 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000245 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1422 | +| iterations | 9694 | +| time_elapsed | 13959 | +| total_timesteps | 19853312 | +| train/ | | +| approx_kl | 0.011812218 | +| clip_fraction | 0.32 | +| clip_range | 0.07 | +| entropy_loss | -6.57 | +| explained_variance | 0.139 | +| learning_rate | 4.53e-05 | +| loss | -0.0284 | +| n_updates | 54592 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000223 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1422 | +| iterations | 9695 | +| time_elapsed | 13960 | +| total_timesteps | 19855360 | +| train/ | | +| approx_kl | 0.013746755 | +| clip_fraction | 0.345 | +| clip_range | 0.07 | +| entropy_loss | -6.15 | +| explained_variance | 0.579 | +| learning_rate | 4.53e-05 | +| loss | -0.0285 | +| n_updates | 54596 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000125 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1422 | +| iterations | 9696 | +| time_elapsed | 13961 | +| total_timesteps | 19857408 | +| train/ | | +| approx_kl | 0.012080878 | +| clip_fraction | 0.346 | +| clip_range | 0.07 | +| entropy_loss | -6.75 | +| explained_variance | 0.391 | +| learning_rate | 4.53e-05 | +| loss | -0.0335 | +| n_updates | 54600 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000154 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1422 | +| iterations | 9697 | +| time_elapsed | 13963 | +| total_timesteps | 19859456 | +| train/ | | +| approx_kl | 0.012442032 | +| clip_fraction | 0.359 | +| clip_range | 0.07 | +| entropy_loss | -6.78 | +| explained_variance | 0.195 | +| learning_rate | 4.53e-05 | +| loss | -0.0256 | +| n_updates | 54604 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000235 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1422 | +| iterations | 9698 | +| time_elapsed | 13964 | +| total_timesteps | 19861504 | +| train/ | | +| approx_kl | 0.01160457 | +| clip_fraction | 0.323 | +| clip_range | 0.07 | +| entropy_loss | -6.69 | +| explained_variance | 0.331 | +| learning_rate | 4.53e-05 | +| loss | -0.0227 | +| n_updates | 54608 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000221 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1422 | +| iterations | 9699 | +| time_elapsed | 13966 | +| total_timesteps | 19863552 | +| train/ | | +| approx_kl | 0.012578806 | +| clip_fraction | 0.352 | +| clip_range | 0.07 | +| entropy_loss | -6.32 | +| explained_variance | 0.561 | +| learning_rate | 4.53e-05 | +| loss | -0.0371 | +| n_updates | 54612 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000116 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1422 | +| iterations | 9700 | +| time_elapsed | 13967 | +| total_timesteps | 19865600 | +| train/ | | +| approx_kl | 0.013457857 | +| clip_fraction | 0.357 | +| clip_range | 0.07 | +| entropy_loss | -6.66 | +| explained_variance | 0.272 | +| learning_rate | 4.53e-05 | +| loss | -0.0365 | +| n_updates | 54616 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000139 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1422 | +| iterations | 9701 | +| time_elapsed | 13969 | +| total_timesteps | 19867648 | +| train/ | | +| approx_kl | 0.016178273 | +| clip_fraction | 0.343 | +| clip_range | 0.07 | +| entropy_loss | -6.8 | +| explained_variance | 0.323 | +| learning_rate | 4.53e-05 | +| loss | -0.026 | +| n_updates | 54620 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000137 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1422 | +| iterations | 9702 | +| time_elapsed | 13970 | +| total_timesteps | 19869696 | +| train/ | | +| approx_kl | 0.013092352 | +| clip_fraction | 0.321 | +| clip_range | 0.07 | +| entropy_loss | -6.69 | +| explained_variance | 0.223 | +| learning_rate | 4.53e-05 | +| loss | -0.0206 | +| n_updates | 54624 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.00024 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1422 | +| iterations | 9703 | +| time_elapsed | 13971 | +| total_timesteps | 19871744 | +| train/ | | +| approx_kl | 0.013573064 | +| clip_fraction | 0.332 | +| clip_range | 0.07 | +| entropy_loss | -6 | +| explained_variance | 0.463 | +| learning_rate | 4.53e-05 | +| loss | -0.031 | +| n_updates | 54628 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000295 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1422 | +| iterations | 9704 | +| time_elapsed | 13973 | +| total_timesteps | 19873792 | +| train/ | | +| approx_kl | 0.015396554 | +| clip_fraction | 0.383 | +| clip_range | 0.07 | +| entropy_loss | -5.85 | +| explained_variance | 0.575 | +| learning_rate | 4.53e-05 | +| loss | -0.0362 | +| n_updates | 54632 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000149 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1422 | +| iterations | 9705 | +| time_elapsed | 13974 | +| total_timesteps | 19875840 | +| train/ | | +| approx_kl | 0.012535738 | +| clip_fraction | 0.346 | +| clip_range | 0.07 | +| entropy_loss | -6.78 | +| explained_variance | 0.292 | +| learning_rate | 4.53e-05 | +| loss | -0.0324 | +| n_updates | 54636 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000207 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1422 | +| iterations | 9706 | +| time_elapsed | 13976 | +| total_timesteps | 19877888 | +| train/ | | +| approx_kl | 0.011449838 | +| clip_fraction | 0.329 | +| clip_range | 0.07 | +| entropy_loss | -6.4 | +| explained_variance | 0.538 | +| learning_rate | 4.53e-05 | +| loss | -0.0276 | +| n_updates | 54640 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000189 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.384 | +| time/ | | +| fps | 1422 | +| iterations | 9707 | +| time_elapsed | 13977 | +| total_timesteps | 19879936 | +| train/ | | +| approx_kl | 0.011093104 | +| clip_fraction | 0.325 | +| clip_range | 0.07 | +| entropy_loss | -6.88 | +| explained_variance | -0.108 | +| learning_rate | 4.53e-05 | +| loss | -0.0322 | +| n_updates | 54644 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000143 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.388 | +| time/ | | +| fps | 1422 | +| iterations | 9708 | +| time_elapsed | 13979 | +| total_timesteps | 19881984 | +| train/ | | +| approx_kl | 0.009554364 | +| clip_fraction | 0.294 | +| clip_range | 0.07 | +| entropy_loss | -6.99 | +| explained_variance | 0.268 | +| learning_rate | 4.53e-05 | +| loss | -0.0243 | +| n_updates | 54648 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000374 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1422 | +| iterations | 9709 | +| time_elapsed | 13980 | +| total_timesteps | 19884032 | +| train/ | | +| approx_kl | 0.010880285 | +| clip_fraction | 0.333 | +| clip_range | 0.07 | +| entropy_loss | -6.53 | +| explained_variance | 0.366 | +| learning_rate | 4.53e-05 | +| loss | -0.0288 | +| n_updates | 54652 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000348 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.392 | +| time/ | | +| fps | 1422 | +| iterations | 9710 | +| time_elapsed | 13982 | +| total_timesteps | 19886080 | +| train/ | | +| approx_kl | 0.010629974 | +| clip_fraction | 0.329 | +| clip_range | 0.07 | +| entropy_loss | -6.06 | +| explained_variance | 0.7 | +| learning_rate | 4.53e-05 | +| loss | -0.033 | +| n_updates | 54656 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000124 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.392 | +| time/ | | +| fps | 1422 | +| iterations | 9711 | +| time_elapsed | 13983 | +| total_timesteps | 19888128 | +| train/ | | +| approx_kl | 0.010622815 | +| clip_fraction | 0.321 | +| clip_range | 0.07 | +| entropy_loss | -6.65 | +| explained_variance | 0.251 | +| learning_rate | 4.53e-05 | +| loss | -0.0241 | +| n_updates | 54660 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000463 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.393 | +| time/ | | +| fps | 1422 | +| iterations | 9712 | +| time_elapsed | 13985 | +| total_timesteps | 19890176 | +| train/ | | +| approx_kl | 0.01538944 | +| clip_fraction | 0.372 | +| clip_range | 0.07 | +| entropy_loss | -6.5 | +| explained_variance | 0.222 | +| learning_rate | 4.53e-05 | +| loss | -0.0353 | +| n_updates | 54664 | +| policy_gradient_loss | -0.0222 | +| value_loss | 0.000194 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.396 | +| time/ | | +| fps | 1422 | +| iterations | 9713 | +| time_elapsed | 13986 | +| total_timesteps | 19892224 | +| train/ | | +| approx_kl | 0.014228095 | +| clip_fraction | 0.358 | +| clip_range | 0.07 | +| entropy_loss | -6.84 | +| explained_variance | 0.0241 | +| learning_rate | 4.53e-05 | +| loss | -0.0347 | +| n_updates | 54668 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000179 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.403 | +| time/ | | +| fps | 1422 | +| iterations | 9714 | +| time_elapsed | 13987 | +| total_timesteps | 19894272 | +| train/ | | +| approx_kl | 0.014741989 | +| clip_fraction | 0.347 | +| clip_range | 0.07 | +| entropy_loss | -6.36 | +| explained_variance | 0.473 | +| learning_rate | 4.53e-05 | +| loss | -0.0323 | +| n_updates | 54672 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000198 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.406 | +| time/ | | +| fps | 1422 | +| iterations | 9715 | +| time_elapsed | 13989 | +| total_timesteps | 19896320 | +| train/ | | +| approx_kl | 0.014344228 | +| clip_fraction | 0.292 | +| clip_range | 0.07 | +| entropy_loss | -6.21 | +| explained_variance | 0.5 | +| learning_rate | 4.53e-05 | +| loss | -0.0238 | +| n_updates | 54676 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.000335 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.406 | +| time/ | | +| fps | 1422 | +| iterations | 9716 | +| time_elapsed | 13990 | +| total_timesteps | 19898368 | +| train/ | | +| approx_kl | 0.015549336 | +| clip_fraction | 0.342 | +| clip_range | 0.07 | +| entropy_loss | -6.14 | +| explained_variance | 0.173 | +| learning_rate | 4.53e-05 | +| loss | -0.035 | +| n_updates | 54680 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000384 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.406 | +| time/ | | +| fps | 1422 | +| iterations | 9717 | +| time_elapsed | 13992 | +| total_timesteps | 19900416 | +| train/ | | +| approx_kl | 0.012914803 | +| clip_fraction | 0.381 | +| clip_range | 0.07 | +| entropy_loss | -6.93 | +| explained_variance | -0.418 | +| learning_rate | 4.53e-05 | +| loss | -0.038 | +| n_updates | 54684 | +| policy_gradient_loss | -0.0249 | +| value_loss | 0.000145 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.409 | +| time/ | | +| fps | 1422 | +| iterations | 9718 | +| time_elapsed | 13993 | +| total_timesteps | 19902464 | +| train/ | | +| approx_kl | 0.01014816 | +| clip_fraction | 0.349 | +| clip_range | 0.07 | +| entropy_loss | -7.08 | +| explained_variance | -0.0363 | +| learning_rate | 4.53e-05 | +| loss | -0.0335 | +| n_updates | 54688 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000241 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.427 | +| time/ | | +| fps | 1422 | +| iterations | 9719 | +| time_elapsed | 13995 | +| total_timesteps | 19904512 | +| train/ | | +| approx_kl | 0.011548495 | +| clip_fraction | 0.321 | +| clip_range | 0.07 | +| entropy_loss | -6.84 | +| explained_variance | 0.209 | +| learning_rate | 4.53e-05 | +| loss | -0.0322 | +| n_updates | 54692 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.00018 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.428 | +| time/ | | +| fps | 1422 | +| iterations | 9720 | +| time_elapsed | 13996 | +| total_timesteps | 19906560 | +| train/ | | +| approx_kl | 0.010808276 | +| clip_fraction | 0.301 | +| clip_range | 0.07 | +| entropy_loss | -6.15 | +| explained_variance | 0.306 | +| learning_rate | 4.53e-05 | +| loss | -0.0233 | +| n_updates | 54696 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.00058 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.423 | +| time/ | | +| fps | 1422 | +| iterations | 9721 | +| time_elapsed | 13997 | +| total_timesteps | 19908608 | +| train/ | | +| approx_kl | 0.013314044 | +| clip_fraction | 0.362 | +| clip_range | 0.07 | +| entropy_loss | -6.23 | +| explained_variance | 0.375 | +| learning_rate | 4.53e-05 | +| loss | -0.0378 | +| n_updates | 54700 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000233 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.422 | +| time/ | | +| fps | 1422 | +| iterations | 9722 | +| time_elapsed | 13999 | +| total_timesteps | 19910656 | +| train/ | | +| approx_kl | 0.015866388 | +| clip_fraction | 0.391 | +| clip_range | 0.07 | +| entropy_loss | -6.08 | +| explained_variance | 0.703 | +| learning_rate | 4.53e-05 | +| loss | -0.0411 | +| n_updates | 54704 | +| policy_gradient_loss | -0.0252 | +| value_loss | 7.83e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.422 | +| time/ | | +| fps | 1422 | +| iterations | 9723 | +| time_elapsed | 14000 | +| total_timesteps | 19912704 | +| train/ | | +| approx_kl | 0.01341445 | +| clip_fraction | 0.329 | +| clip_range | 0.07 | +| entropy_loss | -6.39 | +| explained_variance | 0.432 | +| learning_rate | 4.53e-05 | +| loss | -0.021 | +| n_updates | 54708 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000279 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.423 | +| time/ | | +| fps | 1422 | +| iterations | 9724 | +| time_elapsed | 14002 | +| total_timesteps | 19914752 | +| train/ | | +| approx_kl | 0.01618826 | +| clip_fraction | 0.362 | +| clip_range | 0.07 | +| entropy_loss | -6.63 | +| explained_variance | -0.247 | +| learning_rate | 4.53e-05 | +| loss | -0.0367 | +| n_updates | 54712 | +| policy_gradient_loss | -0.023 | +| value_loss | 0.000121 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.426 | +| time/ | | +| fps | 1422 | +| iterations | 9725 | +| time_elapsed | 14003 | +| total_timesteps | 19916800 | +| train/ | | +| approx_kl | 0.013242661 | +| clip_fraction | 0.329 | +| clip_range | 0.07 | +| entropy_loss | -6.93 | +| explained_variance | 0.126 | +| learning_rate | 4.53e-05 | +| loss | -0.0324 | +| n_updates | 54716 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000327 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.426 | +| time/ | | +| fps | 1422 | +| iterations | 9726 | +| time_elapsed | 14005 | +| total_timesteps | 19918848 | +| train/ | | +| approx_kl | 0.013630025 | +| clip_fraction | 0.332 | +| clip_range | 0.07 | +| entropy_loss | -6.66 | +| explained_variance | 0.0876 | +| learning_rate | 4.53e-05 | +| loss | -0.0305 | +| n_updates | 54720 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000135 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.429 | +| time/ | | +| fps | 1422 | +| iterations | 9727 | +| time_elapsed | 14006 | +| total_timesteps | 19920896 | +| train/ | | +| approx_kl | 0.013928806 | +| clip_fraction | 0.35 | +| clip_range | 0.07 | +| entropy_loss | -6.9 | +| explained_variance | 0.104 | +| learning_rate | 4.53e-05 | +| loss | -0.0353 | +| n_updates | 54724 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000102 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.425 | +| time/ | | +| fps | 1422 | +| iterations | 9728 | +| time_elapsed | 14008 | +| total_timesteps | 19922944 | +| train/ | | +| approx_kl | 0.014712485 | +| clip_fraction | 0.305 | +| clip_range | 0.07 | +| entropy_loss | -6.45 | +| explained_variance | 0.338 | +| learning_rate | 4.53e-05 | +| loss | -0.0315 | +| n_updates | 54728 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000228 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.426 | +| time/ | | +| fps | 1422 | +| iterations | 9729 | +| time_elapsed | 14009 | +| total_timesteps | 19924992 | +| train/ | | +| approx_kl | 0.013808461 | +| clip_fraction | 0.334 | +| clip_range | 0.07 | +| entropy_loss | -6.4 | +| explained_variance | 0.646 | +| learning_rate | 4.53e-05 | +| loss | -0.0246 | +| n_updates | 54732 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.00012 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.425 | +| time/ | | +| fps | 1422 | +| iterations | 9730 | +| time_elapsed | 14011 | +| total_timesteps | 19927040 | +| train/ | | +| approx_kl | 0.015136668 | +| clip_fraction | 0.35 | +| clip_range | 0.07 | +| entropy_loss | -5.78 | +| explained_variance | 0.707 | +| learning_rate | 4.53e-05 | +| loss | -0.0313 | +| n_updates | 54736 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000136 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.42 | +| time/ | | +| fps | 1422 | +| iterations | 9731 | +| time_elapsed | 14012 | +| total_timesteps | 19929088 | +| train/ | | +| approx_kl | 0.013214898 | +| clip_fraction | 0.321 | +| clip_range | 0.07 | +| entropy_loss | -6.11 | +| explained_variance | 0.29 | +| learning_rate | 4.53e-05 | +| loss | -0.026 | +| n_updates | 54740 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.0003 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.42 | +| time/ | | +| fps | 1422 | +| iterations | 9732 | +| time_elapsed | 14014 | +| total_timesteps | 19931136 | +| train/ | | +| approx_kl | 0.011548031 | +| clip_fraction | 0.351 | +| clip_range | 0.07 | +| entropy_loss | -6.37 | +| explained_variance | 0.454 | +| learning_rate | 4.53e-05 | +| loss | -0.028 | +| n_updates | 54744 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000192 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.409 | +| time/ | | +| fps | 1422 | +| iterations | 9733 | +| time_elapsed | 14015 | +| total_timesteps | 19933184 | +| train/ | | +| approx_kl | 0.012915022 | +| clip_fraction | 0.365 | +| clip_range | 0.07 | +| entropy_loss | -6.45 | +| explained_variance | 0.61 | +| learning_rate | 4.53e-05 | +| loss | -0.0414 | +| n_updates | 54748 | +| policy_gradient_loss | -0.0229 | +| value_loss | 0.000116 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.409 | +| time/ | | +| fps | 1422 | +| iterations | 9734 | +| time_elapsed | 14016 | +| total_timesteps | 19935232 | +| train/ | | +| approx_kl | 0.013653783 | +| clip_fraction | 0.339 | +| clip_range | 0.07 | +| entropy_loss | -6.56 | +| explained_variance | 0.15 | +| learning_rate | 4.53e-05 | +| loss | -0.0251 | +| n_updates | 54752 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000354 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.405 | +| time/ | | +| fps | 1422 | +| iterations | 9735 | +| time_elapsed | 14018 | +| total_timesteps | 19937280 | +| train/ | | +| approx_kl | 0.012655567 | +| clip_fraction | 0.361 | +| clip_range | 0.07 | +| entropy_loss | -6.43 | +| explained_variance | 0.48 | +| learning_rate | 4.53e-05 | +| loss | -0.0397 | +| n_updates | 54756 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000137 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.411 | +| time/ | | +| fps | 1422 | +| iterations | 9736 | +| time_elapsed | 14019 | +| total_timesteps | 19939328 | +| train/ | | +| approx_kl | 0.0133994175 | +| clip_fraction | 0.336 | +| clip_range | 0.07 | +| entropy_loss | -6.81 | +| explained_variance | 0.172 | +| learning_rate | 4.53e-05 | +| loss | -0.0299 | +| n_updates | 54760 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000191 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.412 | +| time/ | | +| fps | 1422 | +| iterations | 9737 | +| time_elapsed | 14021 | +| total_timesteps | 19941376 | +| train/ | | +| approx_kl | 0.014027615 | +| clip_fraction | 0.299 | +| clip_range | 0.07 | +| entropy_loss | -6.34 | +| explained_variance | 0.393 | +| learning_rate | 4.53e-05 | +| loss | -0.0221 | +| n_updates | 54764 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000373 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.412 | +| time/ | | +| fps | 1422 | +| iterations | 9738 | +| time_elapsed | 14022 | +| total_timesteps | 19943424 | +| train/ | | +| approx_kl | 0.011520449 | +| clip_fraction | 0.357 | +| clip_range | 0.07 | +| entropy_loss | -6.65 | +| explained_variance | 0.536 | +| learning_rate | 4.53e-05 | +| loss | -0.0424 | +| n_updates | 54768 | +| policy_gradient_loss | -0.0224 | +| value_loss | 7.03e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.419 | +| time/ | | +| fps | 1422 | +| iterations | 9739 | +| time_elapsed | 14023 | +| total_timesteps | 19945472 | +| train/ | | +| approx_kl | 0.014806451 | +| clip_fraction | 0.326 | +| clip_range | 0.07 | +| entropy_loss | -7.06 | +| explained_variance | -0.089 | +| learning_rate | 4.53e-05 | +| loss | -0.0334 | +| n_updates | 54772 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000134 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.412 | +| time/ | | +| fps | 1422 | +| iterations | 9740 | +| time_elapsed | 14025 | +| total_timesteps | 19947520 | +| train/ | | +| approx_kl | 0.010250913 | +| clip_fraction | 0.318 | +| clip_range | 0.07 | +| entropy_loss | -6.93 | +| explained_variance | 0.127 | +| learning_rate | 4.53e-05 | +| loss | -0.0321 | +| n_updates | 54776 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000376 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.411 | +| time/ | | +| fps | 1422 | +| iterations | 9741 | +| time_elapsed | 14026 | +| total_timesteps | 19949568 | +| train/ | | +| approx_kl | 0.013747107 | +| clip_fraction | 0.34 | +| clip_range | 0.07 | +| entropy_loss | -5.75 | +| explained_variance | 0.764 | +| learning_rate | 4.53e-05 | +| loss | -0.0295 | +| n_updates | 54780 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000109 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.411 | +| time/ | | +| fps | 1422 | +| iterations | 9742 | +| time_elapsed | 14028 | +| total_timesteps | 19951616 | +| train/ | | +| approx_kl | 0.012202596 | +| clip_fraction | 0.349 | +| clip_range | 0.07 | +| entropy_loss | -6.37 | +| explained_variance | 0.363 | +| learning_rate | 4.53e-05 | +| loss | -0.0378 | +| n_updates | 54784 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000209 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.402 | +| time/ | | +| fps | 1422 | +| iterations | 9743 | +| time_elapsed | 14029 | +| total_timesteps | 19953664 | +| train/ | | +| approx_kl | 0.0134449005 | +| clip_fraction | 0.325 | +| clip_range | 0.07 | +| entropy_loss | -6.92 | +| explained_variance | -0.0948 | +| learning_rate | 4.53e-05 | +| loss | -0.0327 | +| n_updates | 54788 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000192 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.403 | +| time/ | | +| fps | 1422 | +| iterations | 9744 | +| time_elapsed | 14031 | +| total_timesteps | 19955712 | +| train/ | | +| approx_kl | 0.0090144705 | +| clip_fraction | 0.304 | +| clip_range | 0.07 | +| entropy_loss | -6.96 | +| explained_variance | 0.316 | +| learning_rate | 4.53e-05 | +| loss | -0.031 | +| n_updates | 54792 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000188 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.405 | +| time/ | | +| fps | 1422 | +| iterations | 9745 | +| time_elapsed | 14032 | +| total_timesteps | 19957760 | +| train/ | | +| approx_kl | 0.009854299 | +| clip_fraction | 0.331 | +| clip_range | 0.07 | +| entropy_loss | -6.16 | +| explained_variance | 0.65 | +| learning_rate | 4.53e-05 | +| loss | -0.0299 | +| n_updates | 54796 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000187 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.408 | +| time/ | | +| fps | 1422 | +| iterations | 9746 | +| time_elapsed | 14033 | +| total_timesteps | 19959808 | +| train/ | | +| approx_kl | 0.010971398 | +| clip_fraction | 0.311 | +| clip_range | 0.07 | +| entropy_loss | -6.5 | +| explained_variance | 0.352 | +| learning_rate | 4.53e-05 | +| loss | -0.0266 | +| n_updates | 54800 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.0003 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.41 | +| time/ | | +| fps | 1422 | +| iterations | 9747 | +| time_elapsed | 14035 | +| total_timesteps | 19961856 | +| train/ | | +| approx_kl | 0.010030562 | +| clip_fraction | 0.326 | +| clip_range | 0.07 | +| entropy_loss | -7 | +| explained_variance | 0.061 | +| learning_rate | 4.53e-05 | +| loss | -0.0297 | +| n_updates | 54804 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000257 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.411 | +| time/ | | +| fps | 1422 | +| iterations | 9748 | +| time_elapsed | 14036 | +| total_timesteps | 19963904 | +| train/ | | +| approx_kl | 0.01108619 | +| clip_fraction | 0.315 | +| clip_range | 0.07 | +| entropy_loss | -6.84 | +| explained_variance | 0.18 | +| learning_rate | 4.53e-05 | +| loss | -0.0299 | +| n_updates | 54808 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000277 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.409 | +| time/ | | +| fps | 1422 | +| iterations | 9749 | +| time_elapsed | 14038 | +| total_timesteps | 19965952 | +| train/ | | +| approx_kl | 0.012464134 | +| clip_fraction | 0.342 | +| clip_range | 0.07 | +| entropy_loss | -6.7 | +| explained_variance | 0.444 | +| learning_rate | 4.53e-05 | +| loss | -0.0348 | +| n_updates | 54812 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000151 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.404 | +| time/ | | +| fps | 1422 | +| iterations | 9750 | +| time_elapsed | 14039 | +| total_timesteps | 19968000 | +| train/ | | +| approx_kl | 0.0149620455 | +| clip_fraction | 0.362 | +| clip_range | 0.07 | +| entropy_loss | -6.71 | +| explained_variance | 0.317 | +| learning_rate | 4.53e-05 | +| loss | -0.0328 | +| n_updates | 54816 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000128 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.406 | +| time/ | | +| fps | 1422 | +| iterations | 9751 | +| time_elapsed | 14041 | +| total_timesteps | 19970048 | +| train/ | | +| approx_kl | 0.013642706 | +| clip_fraction | 0.321 | +| clip_range | 0.07 | +| entropy_loss | -6.5 | +| explained_variance | 0.589 | +| learning_rate | 4.53e-05 | +| loss | -0.0294 | +| n_updates | 54820 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.00014 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.402 | +| time/ | | +| fps | 1422 | +| iterations | 9752 | +| time_elapsed | 14042 | +| total_timesteps | 19972096 | +| train/ | | +| approx_kl | 0.013210185 | +| clip_fraction | 0.306 | +| clip_range | 0.07 | +| entropy_loss | -5.99 | +| explained_variance | 0.596 | +| learning_rate | 4.53e-05 | +| loss | -0.0306 | +| n_updates | 54824 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000197 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.396 | +| time/ | | +| fps | 1422 | +| iterations | 9753 | +| time_elapsed | 14044 | +| total_timesteps | 19974144 | +| train/ | | +| approx_kl | 0.014042095 | +| clip_fraction | 0.329 | +| clip_range | 0.07 | +| entropy_loss | -6.6 | +| explained_variance | -0.104 | +| learning_rate | 4.53e-05 | +| loss | -0.0278 | +| n_updates | 54828 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.00011 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.395 | +| time/ | | +| fps | 1422 | +| iterations | 9754 | +| time_elapsed | 14045 | +| total_timesteps | 19976192 | +| train/ | | +| approx_kl | 0.013690723 | +| clip_fraction | 0.312 | +| clip_range | 0.07 | +| entropy_loss | -6.18 | +| explained_variance | 0.627 | +| learning_rate | 4.53e-05 | +| loss | -0.0238 | +| n_updates | 54832 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000141 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.395 | +| time/ | | +| fps | 1422 | +| iterations | 9755 | +| time_elapsed | 14047 | +| total_timesteps | 19978240 | +| train/ | | +| approx_kl | 0.01292862 | +| clip_fraction | 0.356 | +| clip_range | 0.07 | +| entropy_loss | -6.38 | +| explained_variance | 0.542 | +| learning_rate | 4.53e-05 | +| loss | -0.0296 | +| n_updates | 54836 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.00018 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.395 | +| time/ | | +| fps | 1422 | +| iterations | 9756 | +| time_elapsed | 14048 | +| total_timesteps | 19980288 | +| train/ | | +| approx_kl | 0.012202238 | +| clip_fraction | 0.333 | +| clip_range | 0.07 | +| entropy_loss | -7.16 | +| explained_variance | -0.0576 | +| learning_rate | 4.53e-05 | +| loss | -0.0284 | +| n_updates | 54840 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000146 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.14e+03 | +| ep_rew_mean | 0.386 | +| time/ | | +| fps | 1422 | +| iterations | 9757 | +| time_elapsed | 14049 | +| total_timesteps | 19982336 | +| train/ | | +| approx_kl | 0.01677825 | +| clip_fraction | 0.354 | +| clip_range | 0.07 | +| entropy_loss | -6.95 | +| explained_variance | 0.36 | +| learning_rate | 4.53e-05 | +| loss | -0.0337 | +| n_updates | 54844 | +| policy_gradient_loss | -0.0215 | +| value_loss | 7.52e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.13e+03 | +| ep_rew_mean | 0.385 | +| time/ | | +| fps | 1422 | +| iterations | 9758 | +| time_elapsed | 14051 | +| total_timesteps | 19984384 | +| train/ | | +| approx_kl | 0.014911155 | +| clip_fraction | 0.325 | +| clip_range | 0.07 | +| entropy_loss | -6.76 | +| explained_variance | 0.0284 | +| learning_rate | 4.53e-05 | +| loss | -0.0323 | +| n_updates | 54848 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000363 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.13e+03 | +| ep_rew_mean | 0.385 | +| time/ | | +| fps | 1422 | +| iterations | 9759 | +| time_elapsed | 14052 | +| total_timesteps | 19986432 | +| train/ | | +| approx_kl | 0.013356331 | +| clip_fraction | 0.33 | +| clip_range | 0.07 | +| entropy_loss | -5.69 | +| explained_variance | 0.678 | +| learning_rate | 4.53e-05 | +| loss | -0.0252 | +| n_updates | 54852 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000215 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.12e+03 | +| ep_rew_mean | 0.387 | +| time/ | | +| fps | 1422 | +| iterations | 9760 | +| time_elapsed | 14054 | +| total_timesteps | 19988480 | +| train/ | | +| approx_kl | 0.01521802 | +| clip_fraction | 0.348 | +| clip_range | 0.07 | +| entropy_loss | -6.72 | +| explained_variance | -0.0706 | +| learning_rate | 4.53e-05 | +| loss | -0.0378 | +| n_updates | 54856 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000145 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.12e+03 | +| ep_rew_mean | 0.387 | +| time/ | | +| fps | 1422 | +| iterations | 9761 | +| time_elapsed | 14055 | +| total_timesteps | 19990528 | +| train/ | | +| approx_kl | 0.012698376 | +| clip_fraction | 0.336 | +| clip_range | 0.07 | +| entropy_loss | -6.8 | +| explained_variance | 0.203 | +| learning_rate | 4.53e-05 | +| loss | -0.0289 | +| n_updates | 54860 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000191 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.13e+03 | +| ep_rew_mean | 0.384 | +| time/ | | +| fps | 1422 | +| iterations | 9762 | +| time_elapsed | 14057 | +| total_timesteps | 19992576 | +| train/ | | +| approx_kl | 0.017238175 | +| clip_fraction | 0.396 | +| clip_range | 0.07 | +| entropy_loss | -6.44 | +| explained_variance | 0.387 | +| learning_rate | 4.53e-05 | +| loss | -0.0334 | +| n_updates | 54864 | +| policy_gradient_loss | -0.0235 | +| value_loss | 7.01e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.13e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1422 | +| iterations | 9763 | +| time_elapsed | 14058 | +| total_timesteps | 19994624 | +| train/ | | +| approx_kl | 0.01360023 | +| clip_fraction | 0.324 | +| clip_range | 0.07 | +| entropy_loss | -6.58 | +| explained_variance | 0.407 | +| learning_rate | 4.53e-05 | +| loss | -0.0261 | +| n_updates | 54868 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000226 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.12e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1422 | +| iterations | 9764 | +| time_elapsed | 14060 | +| total_timesteps | 19996672 | +| train/ | | +| approx_kl | 0.01175656 | +| clip_fraction | 0.329 | +| clip_range | 0.07 | +| entropy_loss | -6.55 | +| explained_variance | 0.453 | +| learning_rate | 4.53e-05 | +| loss | -0.0311 | +| n_updates | 54872 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.00017 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.13e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1422 | +| iterations | 9765 | +| time_elapsed | 14061 | +| total_timesteps | 19998720 | +| train/ | | +| approx_kl | 0.014841231 | +| clip_fraction | 0.307 | +| clip_range | 0.07 | +| entropy_loss | -6.78 | +| explained_variance | 0.382 | +| learning_rate | 4.53e-05 | +| loss | -0.0352 | +| n_updates | 54876 | +| policy_gradient_loss | -0.0208 | +| value_loss | 9.12e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1422 | +| iterations | 9766 | +| time_elapsed | 14063 | +| total_timesteps | 20000768 | +| train/ | | +| approx_kl | 0.012035776 | +| clip_fraction | 0.341 | +| clip_range | 0.07 | +| entropy_loss | -7.08 | +| explained_variance | -0.0041 | +| learning_rate | 4.53e-05 | +| loss | -0.032 | +| n_updates | 54880 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000152 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1422 | +| iterations | 9767 | +| time_elapsed | 14064 | +| total_timesteps | 20002816 | +| train/ | | +| approx_kl | 0.010006585 | +| clip_fraction | 0.323 | +| clip_range | 0.07 | +| entropy_loss | -6.06 | +| explained_variance | 0.517 | +| learning_rate | 4.52e-05 | +| loss | -0.0267 | +| n_updates | 54884 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000342 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1422 | +| iterations | 9768 | +| time_elapsed | 14065 | +| total_timesteps | 20004864 | +| train/ | | +| approx_kl | 0.012624651 | +| clip_fraction | 0.344 | +| clip_range | 0.07 | +| entropy_loss | -5.84 | +| explained_variance | 0.619 | +| learning_rate | 4.52e-05 | +| loss | -0.0264 | +| n_updates | 54888 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000148 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1422 | +| iterations | 9769 | +| time_elapsed | 14067 | +| total_timesteps | 20006912 | +| train/ | | +| approx_kl | 0.010419719 | +| clip_fraction | 0.332 | +| clip_range | 0.07 | +| entropy_loss | -6.67 | +| explained_variance | 0.276 | +| learning_rate | 4.52e-05 | +| loss | -0.0258 | +| n_updates | 54892 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000266 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1422 | +| iterations | 9770 | +| time_elapsed | 14068 | +| total_timesteps | 20008960 | +| train/ | | +| approx_kl | 0.013879235 | +| clip_fraction | 0.367 | +| clip_range | 0.07 | +| entropy_loss | -7 | +| explained_variance | -0.401 | +| learning_rate | 4.52e-05 | +| loss | -0.0372 | +| n_updates | 54896 | +| policy_gradient_loss | -0.0233 | +| value_loss | 8.93e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.14e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1422 | +| iterations | 9771 | +| time_elapsed | 14070 | +| total_timesteps | 20011008 | +| train/ | | +| approx_kl | 0.013578604 | +| clip_fraction | 0.346 | +| clip_range | 0.07 | +| entropy_loss | -6.76 | +| explained_variance | 0.171 | +| learning_rate | 4.52e-05 | +| loss | -0.0345 | +| n_updates | 54900 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000228 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1422 | +| iterations | 9772 | +| time_elapsed | 14071 | +| total_timesteps | 20013056 | +| train/ | | +| approx_kl | 0.011846733 | +| clip_fraction | 0.353 | +| clip_range | 0.07 | +| entropy_loss | -6.7 | +| explained_variance | 0.334 | +| learning_rate | 4.52e-05 | +| loss | -0.0357 | +| n_updates | 54904 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000128 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1422 | +| iterations | 9773 | +| time_elapsed | 14073 | +| total_timesteps | 20015104 | +| train/ | | +| approx_kl | 0.012559348 | +| clip_fraction | 0.339 | +| clip_range | 0.07 | +| entropy_loss | -6.18 | +| explained_variance | 0.742 | +| learning_rate | 4.52e-05 | +| loss | -0.0282 | +| n_updates | 54908 | +| policy_gradient_loss | -0.0184 | +| value_loss | 9.05e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1422 | +| iterations | 9774 | +| time_elapsed | 14074 | +| total_timesteps | 20017152 | +| train/ | | +| approx_kl | 0.014236509 | +| clip_fraction | 0.345 | +| clip_range | 0.07 | +| entropy_loss | -6.11 | +| explained_variance | 0.615 | +| learning_rate | 4.52e-05 | +| loss | -0.0301 | +| n_updates | 54912 | +| policy_gradient_loss | -0.0193 | +| value_loss | 9.89e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1422 | +| iterations | 9775 | +| time_elapsed | 14076 | +| total_timesteps | 20019200 | +| train/ | | +| approx_kl | 0.01269549 | +| clip_fraction | 0.314 | +| clip_range | 0.07 | +| entropy_loss | -6.74 | +| explained_variance | 0.358 | +| learning_rate | 4.52e-05 | +| loss | -0.0264 | +| n_updates | 54916 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000127 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1422 | +| iterations | 9776 | +| time_elapsed | 14077 | +| total_timesteps | 20021248 | +| train/ | | +| approx_kl | 0.013148806 | +| clip_fraction | 0.343 | +| clip_range | 0.07 | +| entropy_loss | -6.48 | +| explained_variance | 0.554 | +| learning_rate | 4.52e-05 | +| loss | -0.0316 | +| n_updates | 54920 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000151 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1422 | +| iterations | 9777 | +| time_elapsed | 14079 | +| total_timesteps | 20023296 | +| train/ | | +| approx_kl | 0.0142370155 | +| clip_fraction | 0.336 | +| clip_range | 0.07 | +| entropy_loss | -6.66 | +| explained_variance | 0.41 | +| learning_rate | 4.52e-05 | +| loss | -0.0264 | +| n_updates | 54924 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000138 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1422 | +| iterations | 9778 | +| time_elapsed | 14080 | +| total_timesteps | 20025344 | +| train/ | | +| approx_kl | 0.011842077 | +| clip_fraction | 0.33 | +| clip_range | 0.07 | +| entropy_loss | -6.66 | +| explained_variance | 0.371 | +| learning_rate | 4.52e-05 | +| loss | -0.035 | +| n_updates | 54928 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000116 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1422 | +| iterations | 9779 | +| time_elapsed | 14082 | +| total_timesteps | 20027392 | +| train/ | | +| approx_kl | 0.013834576 | +| clip_fraction | 0.342 | +| clip_range | 0.07 | +| entropy_loss | -6.55 | +| explained_variance | 0.549 | +| learning_rate | 4.52e-05 | +| loss | -0.0278 | +| n_updates | 54932 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000111 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1422 | +| iterations | 9780 | +| time_elapsed | 14083 | +| total_timesteps | 20029440 | +| train/ | | +| approx_kl | 0.017290425 | +| clip_fraction | 0.329 | +| clip_range | 0.07 | +| entropy_loss | -6.51 | +| explained_variance | 0.357 | +| learning_rate | 4.52e-05 | +| loss | -0.029 | +| n_updates | 54936 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000235 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1422 | +| iterations | 9781 | +| time_elapsed | 14085 | +| total_timesteps | 20031488 | +| train/ | | +| approx_kl | 0.013586231 | +| clip_fraction | 0.326 | +| clip_range | 0.07 | +| entropy_loss | -6.28 | +| explained_variance | 0.597 | +| learning_rate | 4.52e-05 | +| loss | -0.0304 | +| n_updates | 54940 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000132 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1422 | +| iterations | 9782 | +| time_elapsed | 14086 | +| total_timesteps | 20033536 | +| train/ | | +| approx_kl | 0.015015468 | +| clip_fraction | 0.356 | +| clip_range | 0.07 | +| entropy_loss | -6.55 | +| explained_variance | -0.039 | +| learning_rate | 4.52e-05 | +| loss | -0.0363 | +| n_updates | 54944 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000172 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1422 | +| iterations | 9783 | +| time_elapsed | 14087 | +| total_timesteps | 20035584 | +| train/ | | +| approx_kl | 0.013583208 | +| clip_fraction | 0.367 | +| clip_range | 0.07 | +| entropy_loss | -6.62 | +| explained_variance | 0.26 | +| learning_rate | 4.52e-05 | +| loss | -0.0356 | +| n_updates | 54948 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000131 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1422 | +| iterations | 9784 | +| time_elapsed | 14089 | +| total_timesteps | 20037632 | +| train/ | | +| approx_kl | 0.012898395 | +| clip_fraction | 0.356 | +| clip_range | 0.07 | +| entropy_loss | -6.71 | +| explained_variance | 0.404 | +| learning_rate | 4.52e-05 | +| loss | -0.0334 | +| n_updates | 54952 | +| policy_gradient_loss | -0.0206 | +| value_loss | 6.32e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.14e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1422 | +| iterations | 9785 | +| time_elapsed | 14090 | +| total_timesteps | 20039680 | +| train/ | | +| approx_kl | 0.009844057 | +| clip_fraction | 0.32 | +| clip_range | 0.07 | +| entropy_loss | -6.58 | +| explained_variance | 0.569 | +| learning_rate | 4.52e-05 | +| loss | -0.0287 | +| n_updates | 54956 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.00012 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.14e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1422 | +| iterations | 9786 | +| time_elapsed | 14092 | +| total_timesteps | 20041728 | +| train/ | | +| approx_kl | 0.011175733 | +| clip_fraction | 0.346 | +| clip_range | 0.07 | +| entropy_loss | -6.16 | +| explained_variance | 0.685 | +| learning_rate | 4.52e-05 | +| loss | -0.0242 | +| n_updates | 54960 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000101 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1422 | +| iterations | 9787 | +| time_elapsed | 14093 | +| total_timesteps | 20043776 | +| train/ | | +| approx_kl | 0.012824263 | +| clip_fraction | 0.336 | +| clip_range | 0.07 | +| entropy_loss | -6.36 | +| explained_variance | 0.254 | +| learning_rate | 4.52e-05 | +| loss | -0.0245 | +| n_updates | 54964 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.00023 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.13e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1422 | +| iterations | 9788 | +| time_elapsed | 14095 | +| total_timesteps | 20045824 | +| train/ | | +| approx_kl | 0.01203161 | +| clip_fraction | 0.346 | +| clip_range | 0.07 | +| entropy_loss | -6.09 | +| explained_variance | 0.521 | +| learning_rate | 4.52e-05 | +| loss | -0.0243 | +| n_updates | 54968 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000185 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.14e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1422 | +| iterations | 9789 | +| time_elapsed | 14096 | +| total_timesteps | 20047872 | +| train/ | | +| approx_kl | 0.012571206 | +| clip_fraction | 0.341 | +| clip_range | 0.07 | +| entropy_loss | -6.74 | +| explained_variance | 0.3 | +| learning_rate | 4.52e-05 | +| loss | -0.0304 | +| n_updates | 54972 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000177 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.14e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1422 | +| iterations | 9790 | +| time_elapsed | 14098 | +| total_timesteps | 20049920 | +| train/ | | +| approx_kl | 0.010365654 | +| clip_fraction | 0.308 | +| clip_range | 0.07 | +| entropy_loss | -6.49 | +| explained_variance | 0.333 | +| learning_rate | 4.52e-05 | +| loss | -0.0174 | +| n_updates | 54976 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000307 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1422 | +| iterations | 9791 | +| time_elapsed | 14099 | +| total_timesteps | 20051968 | +| train/ | | +| approx_kl | 0.013571415 | +| clip_fraction | 0.34 | +| clip_range | 0.07 | +| entropy_loss | -6.77 | +| explained_variance | 0.401 | +| learning_rate | 4.52e-05 | +| loss | -0.0389 | +| n_updates | 54980 | +| policy_gradient_loss | -0.0237 | +| value_loss | 0.000101 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.14e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1422 | +| iterations | 9792 | +| time_elapsed | 14100 | +| total_timesteps | 20054016 | +| train/ | | +| approx_kl | 0.011378786 | +| clip_fraction | 0.347 | +| clip_range | 0.07 | +| entropy_loss | -6.87 | +| explained_variance | 0.227 | +| learning_rate | 4.52e-05 | +| loss | -0.0305 | +| n_updates | 54984 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.00017 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.14e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1422 | +| iterations | 9793 | +| time_elapsed | 14102 | +| total_timesteps | 20056064 | +| train/ | | +| approx_kl | 0.015836336 | +| clip_fraction | 0.357 | +| clip_range | 0.07 | +| entropy_loss | -6.87 | +| explained_variance | -0.0827 | +| learning_rate | 4.52e-05 | +| loss | -0.0343 | +| n_updates | 54988 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000151 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.14e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1422 | +| iterations | 9794 | +| time_elapsed | 14103 | +| total_timesteps | 20058112 | +| train/ | | +| approx_kl | 0.011932347 | +| clip_fraction | 0.335 | +| clip_range | 0.07 | +| entropy_loss | -5.96 | +| explained_variance | 0.495 | +| learning_rate | 4.52e-05 | +| loss | -0.0257 | +| n_updates | 54992 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000386 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.14e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1422 | +| iterations | 9795 | +| time_elapsed | 14105 | +| total_timesteps | 20060160 | +| train/ | | +| approx_kl | 0.013602663 | +| clip_fraction | 0.33 | +| clip_range | 0.07 | +| entropy_loss | -5.76 | +| explained_variance | 0.533 | +| learning_rate | 4.52e-05 | +| loss | -0.0301 | +| n_updates | 54996 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000208 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.14e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1422 | +| iterations | 9796 | +| time_elapsed | 14106 | +| total_timesteps | 20062208 | +| train/ | | +| approx_kl | 0.014438523 | +| clip_fraction | 0.388 | +| clip_range | 0.07 | +| entropy_loss | -6.46 | +| explained_variance | 0.308 | +| learning_rate | 4.52e-05 | +| loss | -0.0413 | +| n_updates | 55000 | +| policy_gradient_loss | -0.0238 | +| value_loss | 9.93e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1422 | +| iterations | 9797 | +| time_elapsed | 14108 | +| total_timesteps | 20064256 | +| train/ | | +| approx_kl | 0.013580063 | +| clip_fraction | 0.367 | +| clip_range | 0.07 | +| entropy_loss | -6.62 | +| explained_variance | 0.264 | +| learning_rate | 4.52e-05 | +| loss | -0.0375 | +| n_updates | 55004 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000173 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1422 | +| iterations | 9798 | +| time_elapsed | 14109 | +| total_timesteps | 20066304 | +| train/ | | +| approx_kl | 0.014845318 | +| clip_fraction | 0.349 | +| clip_range | 0.07 | +| entropy_loss | -6.84 | +| explained_variance | -0.161 | +| learning_rate | 4.52e-05 | +| loss | -0.0269 | +| n_updates | 55008 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000135 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1422 | +| iterations | 9799 | +| time_elapsed | 14111 | +| total_timesteps | 20068352 | +| train/ | | +| approx_kl | 0.014400786 | +| clip_fraction | 0.326 | +| clip_range | 0.07 | +| entropy_loss | -6.77 | +| explained_variance | 0.597 | +| learning_rate | 4.52e-05 | +| loss | -0.0287 | +| n_updates | 55012 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000103 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.14e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1422 | +| iterations | 9800 | +| time_elapsed | 14112 | +| total_timesteps | 20070400 | +| train/ | | +| approx_kl | 0.01254186 | +| clip_fraction | 0.353 | +| clip_range | 0.07 | +| entropy_loss | -6.95 | +| explained_variance | -0.0569 | +| learning_rate | 4.52e-05 | +| loss | -0.0316 | +| n_updates | 55016 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000201 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.14e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1422 | +| iterations | 9801 | +| time_elapsed | 14114 | +| total_timesteps | 20072448 | +| train/ | | +| approx_kl | 0.010921446 | +| clip_fraction | 0.316 | +| clip_range | 0.07 | +| entropy_loss | -6.76 | +| explained_variance | 0.397 | +| learning_rate | 4.52e-05 | +| loss | -0.0255 | +| n_updates | 55020 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.00021 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1422 | +| iterations | 9802 | +| time_elapsed | 14115 | +| total_timesteps | 20074496 | +| train/ | | +| approx_kl | 0.011509053 | +| clip_fraction | 0.344 | +| clip_range | 0.07 | +| entropy_loss | -6.68 | +| explained_variance | 0.37 | +| learning_rate | 4.52e-05 | +| loss | -0.0313 | +| n_updates | 55024 | +| policy_gradient_loss | -0.0197 | +| value_loss | 9.36e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1422 | +| iterations | 9803 | +| time_elapsed | 14116 | +| total_timesteps | 20076544 | +| train/ | | +| approx_kl | 0.011394149 | +| clip_fraction | 0.342 | +| clip_range | 0.07 | +| entropy_loss | -6.28 | +| explained_variance | 0.455 | +| learning_rate | 4.52e-05 | +| loss | -0.0262 | +| n_updates | 55028 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000266 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1422 | +| iterations | 9804 | +| time_elapsed | 14118 | +| total_timesteps | 20078592 | +| train/ | | +| approx_kl | 0.013068948 | +| clip_fraction | 0.327 | +| clip_range | 0.07 | +| entropy_loss | -5.91 | +| explained_variance | 0.762 | +| learning_rate | 4.52e-05 | +| loss | -0.0305 | +| n_updates | 55032 | +| policy_gradient_loss | -0.0194 | +| value_loss | 8.19e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1422 | +| iterations | 9805 | +| time_elapsed | 14119 | +| total_timesteps | 20080640 | +| train/ | | +| approx_kl | 0.012481753 | +| clip_fraction | 0.336 | +| clip_range | 0.07 | +| entropy_loss | -6.08 | +| explained_variance | 0.542 | +| learning_rate | 4.52e-05 | +| loss | -0.0337 | +| n_updates | 55036 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000135 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1422 | +| iterations | 9806 | +| time_elapsed | 14121 | +| total_timesteps | 20082688 | +| train/ | | +| approx_kl | 0.012351512 | +| clip_fraction | 0.32 | +| clip_range | 0.07 | +| entropy_loss | -6.35 | +| explained_variance | 0.295 | +| learning_rate | 4.52e-05 | +| loss | -0.0264 | +| n_updates | 55040 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000232 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1422 | +| iterations | 9807 | +| time_elapsed | 14122 | +| total_timesteps | 20084736 | +| train/ | | +| approx_kl | 0.014138692 | +| clip_fraction | 0.316 | +| clip_range | 0.07 | +| entropy_loss | -6.65 | +| explained_variance | 0.147 | +| learning_rate | 4.52e-05 | +| loss | -0.0236 | +| n_updates | 55044 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.000522 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1422 | +| iterations | 9808 | +| time_elapsed | 14124 | +| total_timesteps | 20086784 | +| train/ | | +| approx_kl | 0.014679289 | +| clip_fraction | 0.348 | +| clip_range | 0.07 | +| entropy_loss | -6.34 | +| explained_variance | 0.282 | +| learning_rate | 4.52e-05 | +| loss | -0.0234 | +| n_updates | 55048 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000297 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1422 | +| iterations | 9809 | +| time_elapsed | 14126 | +| total_timesteps | 20088832 | +| train/ | | +| approx_kl | 0.013099636 | +| clip_fraction | 0.352 | +| clip_range | 0.07 | +| entropy_loss | -6.18 | +| explained_variance | 0.254 | +| learning_rate | 4.52e-05 | +| loss | -0.0255 | +| n_updates | 55052 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000288 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1422 | +| iterations | 9810 | +| time_elapsed | 14127 | +| total_timesteps | 20090880 | +| train/ | | +| approx_kl | 0.0136777 | +| clip_fraction | 0.368 | +| clip_range | 0.07 | +| entropy_loss | -6.28 | +| explained_variance | 0.551 | +| learning_rate | 4.52e-05 | +| loss | -0.0338 | +| n_updates | 55056 | +| policy_gradient_loss | -0.0219 | +| value_loss | 0.000132 | +--------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.14e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1422 | +| iterations | 9811 | +| time_elapsed | 14128 | +| total_timesteps | 20092928 | +| train/ | | +| approx_kl | 0.01280761 | +| clip_fraction | 0.372 | +| clip_range | 0.07 | +| entropy_loss | -6.8 | +| explained_variance | 0.317 | +| learning_rate | 4.52e-05 | +| loss | -0.038 | +| n_updates | 55060 | +| policy_gradient_loss | -0.0233 | +| value_loss | 0.000117 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.14e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1422 | +| iterations | 9812 | +| time_elapsed | 14130 | +| total_timesteps | 20094976 | +| train/ | | +| approx_kl | 0.013106691 | +| clip_fraction | 0.36 | +| clip_range | 0.07 | +| entropy_loss | -6.04 | +| explained_variance | 0.493 | +| learning_rate | 4.52e-05 | +| loss | -0.031 | +| n_updates | 55064 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000215 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1422 | +| iterations | 9813 | +| time_elapsed | 14131 | +| total_timesteps | 20097024 | +| train/ | | +| approx_kl | 0.017559573 | +| clip_fraction | 0.382 | +| clip_range | 0.07 | +| entropy_loss | -6.2 | +| explained_variance | 0.287 | +| learning_rate | 4.52e-05 | +| loss | -0.0335 | +| n_updates | 55068 | +| policy_gradient_loss | -0.0221 | +| value_loss | 0.000124 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1422 | +| iterations | 9814 | +| time_elapsed | 14133 | +| total_timesteps | 20099072 | +| train/ | | +| approx_kl | 0.014830383 | +| clip_fraction | 0.345 | +| clip_range | 0.07 | +| entropy_loss | -6.09 | +| explained_variance | 0.628 | +| learning_rate | 4.52e-05 | +| loss | -0.03 | +| n_updates | 55072 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.00015 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1422 | +| iterations | 9815 | +| time_elapsed | 14134 | +| total_timesteps | 20101120 | +| train/ | | +| approx_kl | 0.014767953 | +| clip_fraction | 0.37 | +| clip_range | 0.07 | +| entropy_loss | -6.8 | +| explained_variance | -0.018 | +| learning_rate | 4.52e-05 | +| loss | -0.0358 | +| n_updates | 55076 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000176 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1422 | +| iterations | 9816 | +| time_elapsed | 14136 | +| total_timesteps | 20103168 | +| train/ | | +| approx_kl | 0.015253101 | +| clip_fraction | 0.355 | +| clip_range | 0.07 | +| entropy_loss | -6.47 | +| explained_variance | 0.547 | +| learning_rate | 4.52e-05 | +| loss | -0.0296 | +| n_updates | 55080 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000114 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1422 | +| iterations | 9817 | +| time_elapsed | 14137 | +| total_timesteps | 20105216 | +| train/ | | +| approx_kl | 0.012706824 | +| clip_fraction | 0.331 | +| clip_range | 0.07 | +| entropy_loss | -5.83 | +| explained_variance | 0.462 | +| learning_rate | 4.52e-05 | +| loss | -0.022 | +| n_updates | 55084 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.000393 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1422 | +| iterations | 9818 | +| time_elapsed | 14139 | +| total_timesteps | 20107264 | +| train/ | | +| approx_kl | 0.01168731 | +| clip_fraction | 0.337 | +| clip_range | 0.07 | +| entropy_loss | -6.11 | +| explained_variance | 0.377 | +| learning_rate | 4.52e-05 | +| loss | -0.03 | +| n_updates | 55088 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.00027 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.14e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1422 | +| iterations | 9819 | +| time_elapsed | 14140 | +| total_timesteps | 20109312 | +| train/ | | +| approx_kl | 0.012675602 | +| clip_fraction | 0.351 | +| clip_range | 0.07 | +| entropy_loss | -6.75 | +| explained_variance | -0.206 | +| learning_rate | 4.52e-05 | +| loss | -0.0357 | +| n_updates | 55092 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000156 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1422 | +| iterations | 9820 | +| time_elapsed | 14142 | +| total_timesteps | 20111360 | +| train/ | | +| approx_kl | 0.011882393 | +| clip_fraction | 0.331 | +| clip_range | 0.07 | +| entropy_loss | -6.93 | +| explained_variance | 0.156 | +| learning_rate | 4.52e-05 | +| loss | -0.0266 | +| n_updates | 55096 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000271 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1422 | +| iterations | 9821 | +| time_elapsed | 14143 | +| total_timesteps | 20113408 | +| train/ | | +| approx_kl | 0.010606018 | +| clip_fraction | 0.331 | +| clip_range | 0.07 | +| entropy_loss | -7 | +| explained_variance | -0.163 | +| learning_rate | 4.52e-05 | +| loss | -0.0328 | +| n_updates | 55100 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000216 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1422 | +| iterations | 9822 | +| time_elapsed | 14144 | +| total_timesteps | 20115456 | +| train/ | | +| approx_kl | 0.013125559 | +| clip_fraction | 0.345 | +| clip_range | 0.07 | +| entropy_loss | -6.37 | +| explained_variance | 0.595 | +| learning_rate | 4.52e-05 | +| loss | -0.0318 | +| n_updates | 55104 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000151 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1422 | +| iterations | 9823 | +| time_elapsed | 14146 | +| total_timesteps | 20117504 | +| train/ | | +| approx_kl | 0.012608723 | +| clip_fraction | 0.328 | +| clip_range | 0.07 | +| entropy_loss | -6.92 | +| explained_variance | 0.252 | +| learning_rate | 4.52e-05 | +| loss | -0.03 | +| n_updates | 55108 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000181 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1422 | +| iterations | 9824 | +| time_elapsed | 14147 | +| total_timesteps | 20119552 | +| train/ | | +| approx_kl | 0.011957841 | +| clip_fraction | 0.341 | +| clip_range | 0.07 | +| entropy_loss | -6.73 | +| explained_variance | 0.177 | +| learning_rate | 4.52e-05 | +| loss | -0.0346 | +| n_updates | 55112 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1422 | +| iterations | 9825 | +| time_elapsed | 14149 | +| total_timesteps | 20121600 | +| train/ | | +| approx_kl | 0.015576145 | +| clip_fraction | 0.326 | +| clip_range | 0.07 | +| entropy_loss | -5.99 | +| explained_variance | 0.549 | +| learning_rate | 4.52e-05 | +| loss | -0.0253 | +| n_updates | 55116 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000179 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1422 | +| iterations | 9826 | +| time_elapsed | 14150 | +| total_timesteps | 20123648 | +| train/ | | +| approx_kl | 0.014660148 | +| clip_fraction | 0.299 | +| clip_range | 0.07 | +| entropy_loss | -5.76 | +| explained_variance | 0.508 | +| learning_rate | 4.52e-05 | +| loss | -0.0224 | +| n_updates | 55120 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.000261 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1422 | +| iterations | 9827 | +| time_elapsed | 14152 | +| total_timesteps | 20125696 | +| train/ | | +| approx_kl | 0.013786601 | +| clip_fraction | 0.352 | +| clip_range | 0.07 | +| entropy_loss | -6.3 | +| explained_variance | 0.653 | +| learning_rate | 4.52e-05 | +| loss | -0.0291 | +| n_updates | 55124 | +| policy_gradient_loss | -0.0223 | +| value_loss | 6.17e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1422 | +| iterations | 9828 | +| time_elapsed | 14153 | +| total_timesteps | 20127744 | +| train/ | | +| approx_kl | 0.01545584 | +| clip_fraction | 0.374 | +| clip_range | 0.07 | +| entropy_loss | -6.75 | +| explained_variance | 0.0154 | +| learning_rate | 4.52e-05 | +| loss | -0.0364 | +| n_updates | 55128 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000104 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.14e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1422 | +| iterations | 9829 | +| time_elapsed | 14155 | +| total_timesteps | 20129792 | +| train/ | | +| approx_kl | 0.014906236 | +| clip_fraction | 0.38 | +| clip_range | 0.07 | +| entropy_loss | -6.88 | +| explained_variance | -0.0367 | +| learning_rate | 4.52e-05 | +| loss | -0.0336 | +| n_updates | 55132 | +| policy_gradient_loss | -0.0218 | +| value_loss | 7.89e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1422 | +| iterations | 9830 | +| time_elapsed | 14156 | +| total_timesteps | 20131840 | +| train/ | | +| approx_kl | 0.015176716 | +| clip_fraction | 0.386 | +| clip_range | 0.07 | +| entropy_loss | -6.41 | +| explained_variance | 0.603 | +| learning_rate | 4.52e-05 | +| loss | -0.0296 | +| n_updates | 55136 | +| policy_gradient_loss | -0.0202 | +| value_loss | 8.37e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1422 | +| iterations | 9831 | +| time_elapsed | 14158 | +| total_timesteps | 20133888 | +| train/ | | +| approx_kl | 0.012087857 | +| clip_fraction | 0.345 | +| clip_range | 0.07 | +| entropy_loss | -6.63 | +| explained_variance | 0.00113 | +| learning_rate | 4.52e-05 | +| loss | -0.0307 | +| n_updates | 55140 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000131 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1422 | +| iterations | 9832 | +| time_elapsed | 14159 | +| total_timesteps | 20135936 | +| train/ | | +| approx_kl | 0.014114041 | +| clip_fraction | 0.342 | +| clip_range | 0.07 | +| entropy_loss | -6.51 | +| explained_variance | 0.386 | +| learning_rate | 4.52e-05 | +| loss | -0.0329 | +| n_updates | 55144 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000161 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1422 | +| iterations | 9833 | +| time_elapsed | 14160 | +| total_timesteps | 20137984 | +| train/ | | +| approx_kl | 0.012542149 | +| clip_fraction | 0.325 | +| clip_range | 0.07 | +| entropy_loss | -6.17 | +| explained_variance | 0.285 | +| learning_rate | 4.52e-05 | +| loss | -0.0298 | +| n_updates | 55148 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000295 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1422 | +| iterations | 9834 | +| time_elapsed | 14162 | +| total_timesteps | 20140032 | +| train/ | | +| approx_kl | 0.012723566 | +| clip_fraction | 0.355 | +| clip_range | 0.07 | +| entropy_loss | -6.43 | +| explained_variance | 0.258 | +| learning_rate | 4.52e-05 | +| loss | -0.0346 | +| n_updates | 55152 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000117 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.14e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1422 | +| iterations | 9835 | +| time_elapsed | 14163 | +| total_timesteps | 20142080 | +| train/ | | +| approx_kl | 0.0134404 | +| clip_fraction | 0.337 | +| clip_range | 0.07 | +| entropy_loss | -6.93 | +| explained_variance | 0.0144 | +| learning_rate | 4.52e-05 | +| loss | -0.0329 | +| n_updates | 55156 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000153 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1422 | +| iterations | 9836 | +| time_elapsed | 14165 | +| total_timesteps | 20144128 | +| train/ | | +| approx_kl | 0.012098812 | +| clip_fraction | 0.299 | +| clip_range | 0.07 | +| entropy_loss | -6.46 | +| explained_variance | 0.413 | +| learning_rate | 4.52e-05 | +| loss | -0.0253 | +| n_updates | 55160 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000286 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1422 | +| iterations | 9837 | +| time_elapsed | 14166 | +| total_timesteps | 20146176 | +| train/ | | +| approx_kl | 0.0116246315 | +| clip_fraction | 0.295 | +| clip_range | 0.07 | +| entropy_loss | -6.1 | +| explained_variance | 0.166 | +| learning_rate | 4.52e-05 | +| loss | -0.0244 | +| n_updates | 55164 | +| policy_gradient_loss | -0.0136 | +| value_loss | 0.000594 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1422 | +| iterations | 9838 | +| time_elapsed | 14168 | +| total_timesteps | 20148224 | +| train/ | | +| approx_kl | 0.013372067 | +| clip_fraction | 0.368 | +| clip_range | 0.07 | +| entropy_loss | -5.46 | +| explained_variance | 0.61 | +| learning_rate | 4.52e-05 | +| loss | -0.0372 | +| n_updates | 55168 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000176 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1422 | +| iterations | 9839 | +| time_elapsed | 14169 | +| total_timesteps | 20150272 | +| train/ | | +| approx_kl | 0.009112224 | +| clip_fraction | 0.35 | +| clip_range | 0.07 | +| entropy_loss | -6.11 | +| explained_variance | 0.496 | +| learning_rate | 4.52e-05 | +| loss | -0.0282 | +| n_updates | 55172 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000183 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1422 | +| iterations | 9840 | +| time_elapsed | 14171 | +| total_timesteps | 20152320 | +| train/ | | +| approx_kl | 0.011614772 | +| clip_fraction | 0.355 | +| clip_range | 0.07 | +| entropy_loss | -6.85 | +| explained_variance | 0.0942 | +| learning_rate | 4.52e-05 | +| loss | -0.0384 | +| n_updates | 55176 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000162 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1422 | +| iterations | 9841 | +| time_elapsed | 14172 | +| total_timesteps | 20154368 | +| train/ | | +| approx_kl | 0.010019658 | +| clip_fraction | 0.337 | +| clip_range | 0.07 | +| entropy_loss | -6.95 | +| explained_variance | 0.0882 | +| learning_rate | 4.52e-05 | +| loss | -0.0352 | +| n_updates | 55180 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000414 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1422 | +| iterations | 9842 | +| time_elapsed | 14174 | +| total_timesteps | 20156416 | +| train/ | | +| approx_kl | 0.010182632 | +| clip_fraction | 0.329 | +| clip_range | 0.07 | +| entropy_loss | -6.38 | +| explained_variance | 0.291 | +| learning_rate | 4.52e-05 | +| loss | -0.0285 | +| n_updates | 55184 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000549 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1422 | +| iterations | 9843 | +| time_elapsed | 14175 | +| total_timesteps | 20158464 | +| train/ | | +| approx_kl | 0.012519837 | +| clip_fraction | 0.351 | +| clip_range | 0.07 | +| entropy_loss | -6.5 | +| explained_variance | 0.107 | +| learning_rate | 4.52e-05 | +| loss | -0.0423 | +| n_updates | 55188 | +| policy_gradient_loss | -0.0236 | +| value_loss | 0.000142 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1422 | +| iterations | 9844 | +| time_elapsed | 14177 | +| total_timesteps | 20160512 | +| train/ | | +| approx_kl | 0.013586335 | +| clip_fraction | 0.339 | +| clip_range | 0.07 | +| entropy_loss | -6.64 | +| explained_variance | 0.219 | +| learning_rate | 4.52e-05 | +| loss | -0.037 | +| n_updates | 55192 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000281 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1422 | +| iterations | 9845 | +| time_elapsed | 14178 | +| total_timesteps | 20162560 | +| train/ | | +| approx_kl | 0.013070214 | +| clip_fraction | 0.364 | +| clip_range | 0.07 | +| entropy_loss | -6.46 | +| explained_variance | 0.511 | +| learning_rate | 4.52e-05 | +| loss | -0.0265 | +| n_updates | 55196 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.00012 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1422 | +| iterations | 9846 | +| time_elapsed | 14179 | +| total_timesteps | 20164608 | +| train/ | | +| approx_kl | 0.013469437 | +| clip_fraction | 0.32 | +| clip_range | 0.07 | +| entropy_loss | -6.42 | +| explained_variance | 0.331 | +| learning_rate | 4.52e-05 | +| loss | -0.0292 | +| n_updates | 55200 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000217 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1422 | +| iterations | 9847 | +| time_elapsed | 14181 | +| total_timesteps | 20166656 | +| train/ | | +| approx_kl | 0.011091726 | +| clip_fraction | 0.327 | +| clip_range | 0.07 | +| entropy_loss | -6.61 | +| explained_variance | 0.418 | +| learning_rate | 4.52e-05 | +| loss | -0.033 | +| n_updates | 55204 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000156 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1422 | +| iterations | 9848 | +| time_elapsed | 14182 | +| total_timesteps | 20168704 | +| train/ | | +| approx_kl | 0.012535762 | +| clip_fraction | 0.336 | +| clip_range | 0.07 | +| entropy_loss | -6.34 | +| explained_variance | 0.485 | +| learning_rate | 4.52e-05 | +| loss | -0.0305 | +| n_updates | 55208 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000156 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1422 | +| iterations | 9849 | +| time_elapsed | 14184 | +| total_timesteps | 20170752 | +| train/ | | +| approx_kl | 0.012218045 | +| clip_fraction | 0.34 | +| clip_range | 0.07 | +| entropy_loss | -6.48 | +| explained_variance | 0.493 | +| learning_rate | 4.52e-05 | +| loss | -0.0322 | +| n_updates | 55212 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000158 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1422 | +| iterations | 9850 | +| time_elapsed | 14185 | +| total_timesteps | 20172800 | +| train/ | | +| approx_kl | 0.012804074 | +| clip_fraction | 0.346 | +| clip_range | 0.07 | +| entropy_loss | -6.61 | +| explained_variance | 0.312 | +| learning_rate | 4.52e-05 | +| loss | -0.0346 | +| n_updates | 55216 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000141 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1422 | +| iterations | 9851 | +| time_elapsed | 14187 | +| total_timesteps | 20174848 | +| train/ | | +| approx_kl | 0.011249443 | +| clip_fraction | 0.313 | +| clip_range | 0.07 | +| entropy_loss | -6.81 | +| explained_variance | -0.0996 | +| learning_rate | 4.52e-05 | +| loss | -0.0295 | +| n_updates | 55220 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.00029 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1422 | +| iterations | 9852 | +| time_elapsed | 14188 | +| total_timesteps | 20176896 | +| train/ | | +| approx_kl | 0.01142098 | +| clip_fraction | 0.321 | +| clip_range | 0.07 | +| entropy_loss | -5.89 | +| explained_variance | 0.51 | +| learning_rate | 4.52e-05 | +| loss | -0.0283 | +| n_updates | 55224 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000243 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1422 | +| iterations | 9853 | +| time_elapsed | 14190 | +| total_timesteps | 20178944 | +| train/ | | +| approx_kl | 0.013134973 | +| clip_fraction | 0.369 | +| clip_range | 0.07 | +| entropy_loss | -6.7 | +| explained_variance | -0.147 | +| learning_rate | 4.52e-05 | +| loss | -0.041 | +| n_updates | 55228 | +| policy_gradient_loss | -0.0226 | +| value_loss | 0.000104 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1422 | +| iterations | 9854 | +| time_elapsed | 14191 | +| total_timesteps | 20180992 | +| train/ | | +| approx_kl | 0.011473073 | +| clip_fraction | 0.347 | +| clip_range | 0.07 | +| entropy_loss | -6.28 | +| explained_variance | 0.484 | +| learning_rate | 4.52e-05 | +| loss | -0.0347 | +| n_updates | 55232 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000122 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1422 | +| iterations | 9855 | +| time_elapsed | 14193 | +| total_timesteps | 20183040 | +| train/ | | +| approx_kl | 0.01441535 | +| clip_fraction | 0.344 | +| clip_range | 0.07 | +| entropy_loss | -5.87 | +| explained_variance | 0.601 | +| learning_rate | 4.52e-05 | +| loss | -0.0199 | +| n_updates | 55236 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000206 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1422 | +| iterations | 9856 | +| time_elapsed | 14194 | +| total_timesteps | 20185088 | +| train/ | | +| approx_kl | 0.010389735 | +| clip_fraction | 0.337 | +| clip_range | 0.07 | +| entropy_loss | -6.28 | +| explained_variance | 0.359 | +| learning_rate | 4.52e-05 | +| loss | -0.0292 | +| n_updates | 55240 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000136 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1422 | +| iterations | 9857 | +| time_elapsed | 14196 | +| total_timesteps | 20187136 | +| train/ | | +| approx_kl | 0.011342645 | +| clip_fraction | 0.35 | +| clip_range | 0.07 | +| entropy_loss | -6.52 | +| explained_variance | 0.456 | +| learning_rate | 4.52e-05 | +| loss | -0.0309 | +| n_updates | 55244 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000139 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1422 | +| iterations | 9858 | +| time_elapsed | 14197 | +| total_timesteps | 20189184 | +| train/ | | +| approx_kl | 0.015466182 | +| clip_fraction | 0.356 | +| clip_range | 0.07 | +| entropy_loss | -6.55 | +| explained_variance | 0.262 | +| learning_rate | 4.52e-05 | +| loss | -0.0338 | +| n_updates | 55248 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000206 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1422 | +| iterations | 9859 | +| time_elapsed | 14198 | +| total_timesteps | 20191232 | +| train/ | | +| approx_kl | 0.009929039 | +| clip_fraction | 0.333 | +| clip_range | 0.07 | +| entropy_loss | -6.13 | +| explained_variance | 0.647 | +| learning_rate | 4.52e-05 | +| loss | -0.0283 | +| n_updates | 55252 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000169 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1422 | +| iterations | 9860 | +| time_elapsed | 14200 | +| total_timesteps | 20193280 | +| train/ | | +| approx_kl | 0.0093817245 | +| clip_fraction | 0.315 | +| clip_range | 0.07 | +| entropy_loss | -6.5 | +| explained_variance | 0.302 | +| learning_rate | 4.52e-05 | +| loss | -0.027 | +| n_updates | 55256 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000314 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1422 | +| iterations | 9861 | +| time_elapsed | 14201 | +| total_timesteps | 20195328 | +| train/ | | +| approx_kl | 0.013085181 | +| clip_fraction | 0.356 | +| clip_range | 0.07 | +| entropy_loss | -6.56 | +| explained_variance | 0.499 | +| learning_rate | 4.52e-05 | +| loss | -0.0317 | +| n_updates | 55260 | +| policy_gradient_loss | -0.0228 | +| value_loss | 0.000109 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1422 | +| iterations | 9862 | +| time_elapsed | 14203 | +| total_timesteps | 20197376 | +| train/ | | +| approx_kl | 0.010839945 | +| clip_fraction | 0.313 | +| clip_range | 0.07 | +| entropy_loss | -6.44 | +| explained_variance | 0.405 | +| learning_rate | 4.52e-05 | +| loss | -0.025 | +| n_updates | 55264 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000335 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1422 | +| iterations | 9863 | +| time_elapsed | 14204 | +| total_timesteps | 20199424 | +| train/ | | +| approx_kl | 0.011801581 | +| clip_fraction | 0.335 | +| clip_range | 0.07 | +| entropy_loss | -6.77 | +| explained_variance | -0.0798 | +| learning_rate | 4.52e-05 | +| loss | -0.0377 | +| n_updates | 55268 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000108 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1422 | +| iterations | 9864 | +| time_elapsed | 14206 | +| total_timesteps | 20201472 | +| train/ | | +| approx_kl | 0.0111258635 | +| clip_fraction | 0.34 | +| clip_range | 0.07 | +| entropy_loss | -6.58 | +| explained_variance | 0.306 | +| learning_rate | 4.52e-05 | +| loss | -0.0354 | +| n_updates | 55272 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000151 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1422 | +| iterations | 9865 | +| time_elapsed | 14207 | +| total_timesteps | 20203520 | +| train/ | | +| approx_kl | 0.012421023 | +| clip_fraction | 0.344 | +| clip_range | 0.0699 | +| entropy_loss | -6.92 | +| explained_variance | 0.189 | +| learning_rate | 4.52e-05 | +| loss | -0.0275 | +| n_updates | 55276 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000112 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1422 | +| iterations | 9866 | +| time_elapsed | 14209 | +| total_timesteps | 20205568 | +| train/ | | +| approx_kl | 0.014169062 | +| clip_fraction | 0.313 | +| clip_range | 0.0699 | +| entropy_loss | -6.58 | +| explained_variance | 0.323 | +| learning_rate | 4.52e-05 | +| loss | -0.026 | +| n_updates | 55280 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000214 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1422 | +| iterations | 9867 | +| time_elapsed | 14210 | +| total_timesteps | 20207616 | +| train/ | | +| approx_kl | 0.012734809 | +| clip_fraction | 0.333 | +| clip_range | 0.0699 | +| entropy_loss | -6.55 | +| explained_variance | 0.566 | +| learning_rate | 4.52e-05 | +| loss | -0.0341 | +| n_updates | 55284 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000106 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1422 | +| iterations | 9868 | +| time_elapsed | 14211 | +| total_timesteps | 20209664 | +| train/ | | +| approx_kl | 0.013275892 | +| clip_fraction | 0.325 | +| clip_range | 0.0699 | +| entropy_loss | -6.19 | +| explained_variance | 0.396 | +| learning_rate | 4.52e-05 | +| loss | -0.0311 | +| n_updates | 55288 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.00022 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1422 | +| iterations | 9869 | +| time_elapsed | 14213 | +| total_timesteps | 20211712 | +| train/ | | +| approx_kl | 0.011180297 | +| clip_fraction | 0.317 | +| clip_range | 0.0699 | +| entropy_loss | -6.31 | +| explained_variance | 0.363 | +| learning_rate | 4.52e-05 | +| loss | -0.0302 | +| n_updates | 55292 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000182 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1422 | +| iterations | 9870 | +| time_elapsed | 14214 | +| total_timesteps | 20213760 | +| train/ | | +| approx_kl | 0.011604039 | +| clip_fraction | 0.344 | +| clip_range | 0.0699 | +| entropy_loss | -6.31 | +| explained_variance | 0.493 | +| learning_rate | 4.52e-05 | +| loss | -0.0287 | +| n_updates | 55296 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000195 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1422 | +| iterations | 9871 | +| time_elapsed | 14216 | +| total_timesteps | 20215808 | +| train/ | | +| approx_kl | 0.013675703 | +| clip_fraction | 0.343 | +| clip_range | 0.0699 | +| entropy_loss | -6.86 | +| explained_variance | -0.236 | +| learning_rate | 4.52e-05 | +| loss | -0.0308 | +| n_updates | 55300 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.386 | +| time/ | | +| fps | 1422 | +| iterations | 9872 | +| time_elapsed | 14217 | +| total_timesteps | 20217856 | +| train/ | | +| approx_kl | 0.010901032 | +| clip_fraction | 0.307 | +| clip_range | 0.0699 | +| entropy_loss | -6.51 | +| explained_variance | 0.334 | +| learning_rate | 4.52e-05 | +| loss | -0.0279 | +| n_updates | 55304 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000253 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.387 | +| time/ | | +| fps | 1422 | +| iterations | 9873 | +| time_elapsed | 14219 | +| total_timesteps | 20219904 | +| train/ | | +| approx_kl | 0.011723061 | +| clip_fraction | 0.308 | +| clip_range | 0.0699 | +| entropy_loss | -5.9 | +| explained_variance | 0.362 | +| learning_rate | 4.52e-05 | +| loss | -0.0245 | +| n_updates | 55308 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000294 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1422 | +| iterations | 9874 | +| time_elapsed | 14220 | +| total_timesteps | 20221952 | +| train/ | | +| approx_kl | 0.011649347 | +| clip_fraction | 0.348 | +| clip_range | 0.0699 | +| entropy_loss | -5.88 | +| explained_variance | 0.481 | +| learning_rate | 4.52e-05 | +| loss | -0.0318 | +| n_updates | 55312 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000322 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.387 | +| time/ | | +| fps | 1422 | +| iterations | 9875 | +| time_elapsed | 14222 | +| total_timesteps | 20224000 | +| train/ | | +| approx_kl | 0.012356287 | +| clip_fraction | 0.343 | +| clip_range | 0.0699 | +| entropy_loss | -6.54 | +| explained_variance | 0.194 | +| learning_rate | 4.52e-05 | +| loss | -0.0286 | +| n_updates | 55316 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000156 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1422 | +| iterations | 9876 | +| time_elapsed | 14223 | +| total_timesteps | 20226048 | +| train/ | | +| approx_kl | 0.008900092 | +| clip_fraction | 0.302 | +| clip_range | 0.0699 | +| entropy_loss | -6.22 | +| explained_variance | 0.392 | +| learning_rate | 4.52e-05 | +| loss | -0.02 | +| n_updates | 55320 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000336 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1422 | +| iterations | 9877 | +| time_elapsed | 14225 | +| total_timesteps | 20228096 | +| train/ | | +| approx_kl | 0.010977237 | +| clip_fraction | 0.326 | +| clip_range | 0.0699 | +| entropy_loss | -6.93 | +| explained_variance | -0.158 | +| learning_rate | 4.52e-05 | +| loss | -0.0304 | +| n_updates | 55324 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000166 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1422 | +| iterations | 9878 | +| time_elapsed | 14226 | +| total_timesteps | 20230144 | +| train/ | | +| approx_kl | 0.013027795 | +| clip_fraction | 0.341 | +| clip_range | 0.0699 | +| entropy_loss | -6.85 | +| explained_variance | 0.457 | +| learning_rate | 4.52e-05 | +| loss | -0.0364 | +| n_updates | 55328 | +| policy_gradient_loss | -0.0222 | +| value_loss | 6.53e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.384 | +| time/ | | +| fps | 1422 | +| iterations | 9879 | +| time_elapsed | 14227 | +| total_timesteps | 20232192 | +| train/ | | +| approx_kl | 0.013419627 | +| clip_fraction | 0.339 | +| clip_range | 0.0699 | +| entropy_loss | -6.61 | +| explained_variance | 0.409 | +| learning_rate | 4.52e-05 | +| loss | -0.0309 | +| n_updates | 55332 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000154 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.386 | +| time/ | | +| fps | 1422 | +| iterations | 9880 | +| time_elapsed | 14229 | +| total_timesteps | 20234240 | +| train/ | | +| approx_kl | 0.011630302 | +| clip_fraction | 0.328 | +| clip_range | 0.0699 | +| entropy_loss | -6.5 | +| explained_variance | 0.333 | +| learning_rate | 4.52e-05 | +| loss | -0.0251 | +| n_updates | 55336 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000289 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1422 | +| iterations | 9881 | +| time_elapsed | 14230 | +| total_timesteps | 20236288 | +| train/ | | +| approx_kl | 0.020838525 | +| clip_fraction | 0.314 | +| clip_range | 0.0699 | +| entropy_loss | -6.19 | +| explained_variance | 0.487 | +| learning_rate | 4.52e-05 | +| loss | -0.0304 | +| n_updates | 55340 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000209 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1422 | +| iterations | 9882 | +| time_elapsed | 14232 | +| total_timesteps | 20238336 | +| train/ | | +| approx_kl | 0.0137185175 | +| clip_fraction | 0.357 | +| clip_range | 0.0699 | +| entropy_loss | -5.74 | +| explained_variance | 0.743 | +| learning_rate | 4.52e-05 | +| loss | -0.0356 | +| n_updates | 55344 | +| policy_gradient_loss | -0.0229 | +| value_loss | 9.05e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1422 | +| iterations | 9883 | +| time_elapsed | 14233 | +| total_timesteps | 20240384 | +| train/ | | +| approx_kl | 0.016344978 | +| clip_fraction | 0.399 | +| clip_range | 0.0699 | +| entropy_loss | -6.02 | +| explained_variance | 0.483 | +| learning_rate | 4.52e-05 | +| loss | -0.0337 | +| n_updates | 55348 | +| policy_gradient_loss | -0.0238 | +| value_loss | 9.96e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1422 | +| iterations | 9884 | +| time_elapsed | 14235 | +| total_timesteps | 20242432 | +| train/ | | +| approx_kl | 0.0151644265 | +| clip_fraction | 0.354 | +| clip_range | 0.0699 | +| entropy_loss | -6.79 | +| explained_variance | 0.208 | +| learning_rate | 4.52e-05 | +| loss | -0.0319 | +| n_updates | 55352 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000196 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1422 | +| iterations | 9885 | +| time_elapsed | 14236 | +| total_timesteps | 20244480 | +| train/ | | +| approx_kl | 0.016638469 | +| clip_fraction | 0.381 | +| clip_range | 0.0699 | +| entropy_loss | -6.46 | +| explained_variance | 0.344 | +| learning_rate | 4.52e-05 | +| loss | -0.032 | +| n_updates | 55356 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000163 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1422 | +| iterations | 9886 | +| time_elapsed | 14237 | +| total_timesteps | 20246528 | +| train/ | | +| approx_kl | 0.016135555 | +| clip_fraction | 0.352 | +| clip_range | 0.0699 | +| entropy_loss | -6.76 | +| explained_variance | 0.179 | +| learning_rate | 4.52e-05 | +| loss | -0.0293 | +| n_updates | 55360 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000145 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1422 | +| iterations | 9887 | +| time_elapsed | 14239 | +| total_timesteps | 20248576 | +| train/ | | +| approx_kl | 0.013154964 | +| clip_fraction | 0.355 | +| clip_range | 0.0699 | +| entropy_loss | -6.14 | +| explained_variance | 0.339 | +| learning_rate | 4.52e-05 | +| loss | -0.0275 | +| n_updates | 55364 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000312 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.384 | +| time/ | | +| fps | 1422 | +| iterations | 9888 | +| time_elapsed | 14240 | +| total_timesteps | 20250624 | +| train/ | | +| approx_kl | 0.01412341 | +| clip_fraction | 0.358 | +| clip_range | 0.0699 | +| entropy_loss | -6.06 | +| explained_variance | 0.601 | +| learning_rate | 4.52e-05 | +| loss | -0.0319 | +| n_updates | 55368 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000105 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1422 | +| iterations | 9889 | +| time_elapsed | 14242 | +| total_timesteps | 20252672 | +| train/ | | +| approx_kl | 0.010827579 | +| clip_fraction | 0.325 | +| clip_range | 0.0699 | +| entropy_loss | -6.8 | +| explained_variance | 0.219 | +| learning_rate | 4.52e-05 | +| loss | -0.0265 | +| n_updates | 55372 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000255 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1422 | +| iterations | 9890 | +| time_elapsed | 14243 | +| total_timesteps | 20254720 | +| train/ | | +| approx_kl | 0.014282631 | +| clip_fraction | 0.381 | +| clip_range | 0.0699 | +| entropy_loss | -6.47 | +| explained_variance | 0.637 | +| learning_rate | 4.52e-05 | +| loss | -0.0396 | +| n_updates | 55376 | +| policy_gradient_loss | -0.0223 | +| value_loss | 8.5e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1422 | +| iterations | 9891 | +| time_elapsed | 14245 | +| total_timesteps | 20256768 | +| train/ | | +| approx_kl | 0.016404804 | +| clip_fraction | 0.365 | +| clip_range | 0.0699 | +| entropy_loss | -6.55 | +| explained_variance | 0.423 | +| learning_rate | 4.52e-05 | +| loss | -0.0339 | +| n_updates | 55380 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000102 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1422 | +| iterations | 9892 | +| time_elapsed | 14246 | +| total_timesteps | 20258816 | +| train/ | | +| approx_kl | 0.01567556 | +| clip_fraction | 0.381 | +| clip_range | 0.0699 | +| entropy_loss | -6.72 | +| explained_variance | 0.34 | +| learning_rate | 4.52e-05 | +| loss | -0.0359 | +| n_updates | 55384 | +| policy_gradient_loss | -0.0233 | +| value_loss | 8.88e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1422 | +| iterations | 9893 | +| time_elapsed | 14248 | +| total_timesteps | 20260864 | +| train/ | | +| approx_kl | 0.012823929 | +| clip_fraction | 0.327 | +| clip_range | 0.0699 | +| entropy_loss | -6.52 | +| explained_variance | 0.229 | +| learning_rate | 4.52e-05 | +| loss | -0.0241 | +| n_updates | 55388 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000234 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1422 | +| iterations | 9894 | +| time_elapsed | 14249 | +| total_timesteps | 20262912 | +| train/ | | +| approx_kl | 0.012448438 | +| clip_fraction | 0.329 | +| clip_range | 0.0699 | +| entropy_loss | -6.32 | +| explained_variance | 0.426 | +| learning_rate | 4.52e-05 | +| loss | -0.0293 | +| n_updates | 55392 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.00026 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1422 | +| iterations | 9895 | +| time_elapsed | 14251 | +| total_timesteps | 20264960 | +| train/ | | +| approx_kl | 0.010240357 | +| clip_fraction | 0.326 | +| clip_range | 0.0699 | +| entropy_loss | -6.97 | +| explained_variance | 0.0522 | +| learning_rate | 4.52e-05 | +| loss | -0.0298 | +| n_updates | 55396 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000403 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1421 | +| iterations | 9896 | +| time_elapsed | 14252 | +| total_timesteps | 20267008 | +| train/ | | +| approx_kl | 0.011045113 | +| clip_fraction | 0.343 | +| clip_range | 0.0699 | +| entropy_loss | -6.35 | +| explained_variance | 0.377 | +| learning_rate | 4.52e-05 | +| loss | -0.0332 | +| n_updates | 55400 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000296 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1421 | +| iterations | 9897 | +| time_elapsed | 14254 | +| total_timesteps | 20269056 | +| train/ | | +| approx_kl | 0.013952436 | +| clip_fraction | 0.365 | +| clip_range | 0.0699 | +| entropy_loss | -6.48 | +| explained_variance | 0.375 | +| learning_rate | 4.52e-05 | +| loss | -0.0311 | +| n_updates | 55404 | +| policy_gradient_loss | -0.0233 | +| value_loss | 0.000103 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1421 | +| iterations | 9898 | +| time_elapsed | 14255 | +| total_timesteps | 20271104 | +| train/ | | +| approx_kl | 0.014160836 | +| clip_fraction | 0.355 | +| clip_range | 0.0699 | +| entropy_loss | -6.51 | +| explained_variance | 0.502 | +| learning_rate | 4.52e-05 | +| loss | -0.029 | +| n_updates | 55408 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000129 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1421 | +| iterations | 9899 | +| time_elapsed | 14256 | +| total_timesteps | 20273152 | +| train/ | | +| approx_kl | 0.014112723 | +| clip_fraction | 0.342 | +| clip_range | 0.0699 | +| entropy_loss | -6.56 | +| explained_variance | 0.537 | +| learning_rate | 4.52e-05 | +| loss | -0.0324 | +| n_updates | 55412 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.00013 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1421 | +| iterations | 9900 | +| time_elapsed | 14258 | +| total_timesteps | 20275200 | +| train/ | | +| approx_kl | 0.016674353 | +| clip_fraction | 0.353 | +| clip_range | 0.0699 | +| entropy_loss | -6.51 | +| explained_variance | 0.517 | +| learning_rate | 4.52e-05 | +| loss | -0.0343 | +| n_updates | 55416 | +| policy_gradient_loss | -0.0209 | +| value_loss | 8.7e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1421 | +| iterations | 9901 | +| time_elapsed | 14259 | +| total_timesteps | 20277248 | +| train/ | | +| approx_kl | 0.012894909 | +| clip_fraction | 0.33 | +| clip_range | 0.0699 | +| entropy_loss | -6.9 | +| explained_variance | 0.254 | +| learning_rate | 4.52e-05 | +| loss | -0.0328 | +| n_updates | 55420 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000102 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1421 | +| iterations | 9902 | +| time_elapsed | 14261 | +| total_timesteps | 20279296 | +| train/ | | +| approx_kl | 0.008922408 | +| clip_fraction | 0.294 | +| clip_range | 0.0699 | +| entropy_loss | -6.8 | +| explained_variance | 0.283 | +| learning_rate | 4.52e-05 | +| loss | -0.0224 | +| n_updates | 55424 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000182 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1421 | +| iterations | 9903 | +| time_elapsed | 14262 | +| total_timesteps | 20281344 | +| train/ | | +| approx_kl | 0.013921572 | +| clip_fraction | 0.311 | +| clip_range | 0.0699 | +| entropy_loss | -5.63 | +| explained_variance | 0.591 | +| learning_rate | 4.52e-05 | +| loss | -0.0261 | +| n_updates | 55428 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.00018 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1421 | +| iterations | 9904 | +| time_elapsed | 14264 | +| total_timesteps | 20283392 | +| train/ | | +| approx_kl | 0.012339894 | +| clip_fraction | 0.329 | +| clip_range | 0.0699 | +| entropy_loss | -6.28 | +| explained_variance | 0.53 | +| learning_rate | 4.52e-05 | +| loss | -0.0307 | +| n_updates | 55432 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000113 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1421 | +| iterations | 9905 | +| time_elapsed | 14265 | +| total_timesteps | 20285440 | +| train/ | | +| approx_kl | 0.011802692 | +| clip_fraction | 0.349 | +| clip_range | 0.0699 | +| entropy_loss | -6.7 | +| explained_variance | 0.521 | +| learning_rate | 4.52e-05 | +| loss | -0.0319 | +| n_updates | 55436 | +| policy_gradient_loss | -0.0204 | +| value_loss | 6.13e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1421 | +| iterations | 9906 | +| time_elapsed | 14267 | +| total_timesteps | 20287488 | +| train/ | | +| approx_kl | 0.01194579 | +| clip_fraction | 0.349 | +| clip_range | 0.0699 | +| entropy_loss | -6.23 | +| explained_variance | 0.374 | +| learning_rate | 4.52e-05 | +| loss | -0.0274 | +| n_updates | 55440 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000293 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1421 | +| iterations | 9907 | +| time_elapsed | 14268 | +| total_timesteps | 20289536 | +| train/ | | +| approx_kl | 0.011451846 | +| clip_fraction | 0.309 | +| clip_range | 0.0699 | +| entropy_loss | -6.46 | +| explained_variance | 0.207 | +| learning_rate | 4.52e-05 | +| loss | -0.0269 | +| n_updates | 55444 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000239 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1421 | +| iterations | 9908 | +| time_elapsed | 14270 | +| total_timesteps | 20291584 | +| train/ | | +| approx_kl | 0.012738317 | +| clip_fraction | 0.353 | +| clip_range | 0.0699 | +| entropy_loss | -6.73 | +| explained_variance | 0.235 | +| learning_rate | 4.52e-05 | +| loss | -0.0357 | +| n_updates | 55448 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000194 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1421 | +| iterations | 9909 | +| time_elapsed | 14271 | +| total_timesteps | 20293632 | +| train/ | | +| approx_kl | 0.010557594 | +| clip_fraction | 0.337 | +| clip_range | 0.0699 | +| entropy_loss | -6.88 | +| explained_variance | 0.248 | +| learning_rate | 4.52e-05 | +| loss | -0.0283 | +| n_updates | 55452 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000392 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1421 | +| iterations | 9910 | +| time_elapsed | 14272 | +| total_timesteps | 20295680 | +| train/ | | +| approx_kl | 0.011719063 | +| clip_fraction | 0.349 | +| clip_range | 0.0699 | +| entropy_loss | -6.86 | +| explained_variance | 0.333 | +| learning_rate | 4.52e-05 | +| loss | -0.0359 | +| n_updates | 55456 | +| policy_gradient_loss | -0.0219 | +| value_loss | 0.00016 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1421 | +| iterations | 9911 | +| time_elapsed | 14274 | +| total_timesteps | 20297728 | +| train/ | | +| approx_kl | 0.010349108 | +| clip_fraction | 0.343 | +| clip_range | 0.0699 | +| entropy_loss | -7.04 | +| explained_variance | 0.331 | +| learning_rate | 4.52e-05 | +| loss | -0.0279 | +| n_updates | 55460 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000157 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1421 | +| iterations | 9912 | +| time_elapsed | 14275 | +| total_timesteps | 20299776 | +| train/ | | +| approx_kl | 0.010186216 | +| clip_fraction | 0.33 | +| clip_range | 0.0699 | +| entropy_loss | -6.59 | +| explained_variance | 0.645 | +| learning_rate | 4.52e-05 | +| loss | -0.0317 | +| n_updates | 55464 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000131 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1421 | +| iterations | 9913 | +| time_elapsed | 14277 | +| total_timesteps | 20301824 | +| train/ | | +| approx_kl | 0.013011195 | +| clip_fraction | 0.335 | +| clip_range | 0.0699 | +| entropy_loss | -6.67 | +| explained_variance | 0.469 | +| learning_rate | 4.52e-05 | +| loss | -0.0296 | +| n_updates | 55468 | +| policy_gradient_loss | -0.0201 | +| value_loss | 9.37e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1421 | +| iterations | 9914 | +| time_elapsed | 14278 | +| total_timesteps | 20303872 | +| train/ | | +| approx_kl | 0.014383882 | +| clip_fraction | 0.338 | +| clip_range | 0.0699 | +| entropy_loss | -6.92 | +| explained_variance | -0.172 | +| learning_rate | 4.52e-05 | +| loss | -0.0342 | +| n_updates | 55472 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1421 | +| iterations | 9915 | +| time_elapsed | 14280 | +| total_timesteps | 20305920 | +| train/ | | +| approx_kl | 0.009962363 | +| clip_fraction | 0.304 | +| clip_range | 0.0699 | +| entropy_loss | -6.64 | +| explained_variance | 0.252 | +| learning_rate | 4.52e-05 | +| loss | -0.0289 | +| n_updates | 55476 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000343 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1421 | +| iterations | 9916 | +| time_elapsed | 14281 | +| total_timesteps | 20307968 | +| train/ | | +| approx_kl | 0.013569048 | +| clip_fraction | 0.33 | +| clip_range | 0.0699 | +| entropy_loss | -6.22 | +| explained_variance | 0.532 | +| learning_rate | 4.52e-05 | +| loss | -0.0331 | +| n_updates | 55480 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000149 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1421 | +| iterations | 9917 | +| time_elapsed | 14283 | +| total_timesteps | 20310016 | +| train/ | | +| approx_kl | 0.010219479 | +| clip_fraction | 0.307 | +| clip_range | 0.0699 | +| entropy_loss | -6.5 | +| explained_variance | 0.411 | +| learning_rate | 4.52e-05 | +| loss | -0.0266 | +| n_updates | 55484 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.00022 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1421 | +| iterations | 9918 | +| time_elapsed | 14284 | +| total_timesteps | 20312064 | +| train/ | | +| approx_kl | 0.0132623315 | +| clip_fraction | 0.332 | +| clip_range | 0.0699 | +| entropy_loss | -6.3 | +| explained_variance | 0.531 | +| learning_rate | 4.52e-05 | +| loss | -0.0305 | +| n_updates | 55488 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000138 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1421 | +| iterations | 9919 | +| time_elapsed | 14286 | +| total_timesteps | 20314112 | +| train/ | | +| approx_kl | 0.01173762 | +| clip_fraction | 0.348 | +| clip_range | 0.0699 | +| entropy_loss | -6.76 | +| explained_variance | 0.433 | +| learning_rate | 4.52e-05 | +| loss | -0.0318 | +| n_updates | 55492 | +| policy_gradient_loss | -0.0213 | +| value_loss | 7.38e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1421 | +| iterations | 9920 | +| time_elapsed | 14287 | +| total_timesteps | 20316160 | +| train/ | | +| approx_kl | 0.013494466 | +| clip_fraction | 0.362 | +| clip_range | 0.0699 | +| entropy_loss | -6.94 | +| explained_variance | 0.0267 | +| learning_rate | 4.52e-05 | +| loss | -0.0316 | +| n_updates | 55496 | +| policy_gradient_loss | -0.0189 | +| value_loss | 8.99e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1421 | +| iterations | 9921 | +| time_elapsed | 14289 | +| total_timesteps | 20318208 | +| train/ | | +| approx_kl | 0.015494287 | +| clip_fraction | 0.315 | +| clip_range | 0.0699 | +| entropy_loss | -6.55 | +| explained_variance | 0.435 | +| learning_rate | 4.52e-05 | +| loss | -0.0242 | +| n_updates | 55500 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000261 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1421 | +| iterations | 9922 | +| time_elapsed | 14290 | +| total_timesteps | 20320256 | +| train/ | | +| approx_kl | 0.015211658 | +| clip_fraction | 0.339 | +| clip_range | 0.0699 | +| entropy_loss | -6.1 | +| explained_variance | 0.466 | +| learning_rate | 4.52e-05 | +| loss | -0.0345 | +| n_updates | 55504 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000168 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1421 | +| iterations | 9923 | +| time_elapsed | 14291 | +| total_timesteps | 20322304 | +| train/ | | +| approx_kl | 0.011329444 | +| clip_fraction | 0.34 | +| clip_range | 0.0699 | +| entropy_loss | -6.56 | +| explained_variance | 0.48 | +| learning_rate | 4.52e-05 | +| loss | -0.0308 | +| n_updates | 55508 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000157 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1421 | +| iterations | 9924 | +| time_elapsed | 14293 | +| total_timesteps | 20324352 | +| train/ | | +| approx_kl | 0.013780331 | +| clip_fraction | 0.356 | +| clip_range | 0.0699 | +| entropy_loss | -6.79 | +| explained_variance | 0.154 | +| learning_rate | 4.52e-05 | +| loss | -0.0291 | +| n_updates | 55512 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000139 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1421 | +| iterations | 9925 | +| time_elapsed | 14294 | +| total_timesteps | 20326400 | +| train/ | | +| approx_kl | 0.012784474 | +| clip_fraction | 0.35 | +| clip_range | 0.0699 | +| entropy_loss | -6.96 | +| explained_variance | 0.201 | +| learning_rate | 4.52e-05 | +| loss | -0.0332 | +| n_updates | 55516 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000202 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1421 | +| iterations | 9926 | +| time_elapsed | 14296 | +| total_timesteps | 20328448 | +| train/ | | +| approx_kl | 0.013933903 | +| clip_fraction | 0.332 | +| clip_range | 0.0699 | +| entropy_loss | -6.27 | +| explained_variance | 0.418 | +| learning_rate | 4.52e-05 | +| loss | -0.0301 | +| n_updates | 55520 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000229 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1421 | +| iterations | 9927 | +| time_elapsed | 14297 | +| total_timesteps | 20330496 | +| train/ | | +| approx_kl | 0.015284922 | +| clip_fraction | 0.357 | +| clip_range | 0.0699 | +| entropy_loss | -6.22 | +| explained_variance | 0.568 | +| learning_rate | 4.52e-05 | +| loss | -0.0253 | +| n_updates | 55524 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000166 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1421 | +| iterations | 9928 | +| time_elapsed | 14299 | +| total_timesteps | 20332544 | +| train/ | | +| approx_kl | 0.014853355 | +| clip_fraction | 0.334 | +| clip_range | 0.0699 | +| entropy_loss | -6.31 | +| explained_variance | 0.261 | +| learning_rate | 4.52e-05 | +| loss | -0.0287 | +| n_updates | 55528 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000199 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1421 | +| iterations | 9929 | +| time_elapsed | 14300 | +| total_timesteps | 20334592 | +| train/ | | +| approx_kl | 0.012104806 | +| clip_fraction | 0.331 | +| clip_range | 0.0699 | +| entropy_loss | -6.49 | +| explained_variance | 0.529 | +| learning_rate | 4.52e-05 | +| loss | -0.0276 | +| n_updates | 55532 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000139 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1421 | +| iterations | 9930 | +| time_elapsed | 14302 | +| total_timesteps | 20336640 | +| train/ | | +| approx_kl | 0.011470353 | +| clip_fraction | 0.287 | +| clip_range | 0.0699 | +| entropy_loss | -6.09 | +| explained_variance | 0.551 | +| learning_rate | 4.52e-05 | +| loss | -0.0221 | +| n_updates | 55536 | +| policy_gradient_loss | -0.0145 | +| value_loss | 0.000219 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.315 | +| time/ | | +| fps | 1421 | +| iterations | 9931 | +| time_elapsed | 14303 | +| total_timesteps | 20338688 | +| train/ | | +| approx_kl | 0.011107395 | +| clip_fraction | 0.336 | +| clip_range | 0.0699 | +| entropy_loss | -6.3 | +| explained_variance | 0.526 | +| learning_rate | 4.52e-05 | +| loss | -0.0368 | +| n_updates | 55540 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000115 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.315 | +| time/ | | +| fps | 1421 | +| iterations | 9932 | +| time_elapsed | 14305 | +| total_timesteps | 20340736 | +| train/ | | +| approx_kl | 0.013647027 | +| clip_fraction | 0.334 | +| clip_range | 0.0699 | +| entropy_loss | -6.37 | +| explained_variance | 0.124 | +| learning_rate | 4.52e-05 | +| loss | -0.0228 | +| n_updates | 55544 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000316 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.315 | +| time/ | | +| fps | 1421 | +| iterations | 9933 | +| time_elapsed | 14306 | +| total_timesteps | 20342784 | +| train/ | | +| approx_kl | 0.013825893 | +| clip_fraction | 0.388 | +| clip_range | 0.0699 | +| entropy_loss | -6.38 | +| explained_variance | 0.534 | +| learning_rate | 4.52e-05 | +| loss | -0.0357 | +| n_updates | 55548 | +| policy_gradient_loss | -0.0224 | +| value_loss | 0.000125 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1421 | +| iterations | 9934 | +| time_elapsed | 14307 | +| total_timesteps | 20344832 | +| train/ | | +| approx_kl | 0.015551847 | +| clip_fraction | 0.368 | +| clip_range | 0.0699 | +| entropy_loss | -6.46 | +| explained_variance | 0.0891 | +| learning_rate | 4.52e-05 | +| loss | -0.0288 | +| n_updates | 55552 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000209 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1421 | +| iterations | 9935 | +| time_elapsed | 14309 | +| total_timesteps | 20346880 | +| train/ | | +| approx_kl | 0.01055161 | +| clip_fraction | 0.331 | +| clip_range | 0.0699 | +| entropy_loss | -6.62 | +| explained_variance | 0.398 | +| learning_rate | 4.52e-05 | +| loss | -0.0312 | +| n_updates | 55556 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000258 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1421 | +| iterations | 9936 | +| time_elapsed | 14310 | +| total_timesteps | 20348928 | +| train/ | | +| approx_kl | 0.013959086 | +| clip_fraction | 0.317 | +| clip_range | 0.0699 | +| entropy_loss | -6.36 | +| explained_variance | 0.353 | +| learning_rate | 4.52e-05 | +| loss | -0.0295 | +| n_updates | 55560 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000211 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1421 | +| iterations | 9937 | +| time_elapsed | 14312 | +| total_timesteps | 20350976 | +| train/ | | +| approx_kl | 0.011467406 | +| clip_fraction | 0.325 | +| clip_range | 0.0699 | +| entropy_loss | -6.32 | +| explained_variance | 0.161 | +| learning_rate | 4.52e-05 | +| loss | -0.0314 | +| n_updates | 55564 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000267 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1421 | +| iterations | 9938 | +| time_elapsed | 14313 | +| total_timesteps | 20353024 | +| train/ | | +| approx_kl | 0.01558058 | +| clip_fraction | 0.348 | +| clip_range | 0.0699 | +| entropy_loss | -6.6 | +| explained_variance | 0.184 | +| learning_rate | 4.52e-05 | +| loss | -0.0334 | +| n_updates | 55568 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000246 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1421 | +| iterations | 9939 | +| time_elapsed | 14315 | +| total_timesteps | 20355072 | +| train/ | | +| approx_kl | 0.01158228 | +| clip_fraction | 0.345 | +| clip_range | 0.0699 | +| entropy_loss | -7.07 | +| explained_variance | -0.229 | +| learning_rate | 4.52e-05 | +| loss | -0.0348 | +| n_updates | 55572 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000112 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1421 | +| iterations | 9940 | +| time_elapsed | 14316 | +| total_timesteps | 20357120 | +| train/ | | +| approx_kl | 0.012008841 | +| clip_fraction | 0.344 | +| clip_range | 0.0699 | +| entropy_loss | -6.68 | +| explained_variance | 0.286 | +| learning_rate | 4.52e-05 | +| loss | -0.0292 | +| n_updates | 55576 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000167 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1421 | +| iterations | 9941 | +| time_elapsed | 14318 | +| total_timesteps | 20359168 | +| train/ | | +| approx_kl | 0.013407242 | +| clip_fraction | 0.327 | +| clip_range | 0.0699 | +| entropy_loss | -6.57 | +| explained_variance | 0.413 | +| learning_rate | 4.52e-05 | +| loss | -0.0283 | +| n_updates | 55580 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000219 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1421 | +| iterations | 9942 | +| time_elapsed | 14319 | +| total_timesteps | 20361216 | +| train/ | | +| approx_kl | 0.01211065 | +| clip_fraction | 0.354 | +| clip_range | 0.0699 | +| entropy_loss | -6.85 | +| explained_variance | 0.0996 | +| learning_rate | 4.52e-05 | +| loss | -0.0341 | +| n_updates | 55584 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000208 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1421 | +| iterations | 9943 | +| time_elapsed | 14321 | +| total_timesteps | 20363264 | +| train/ | | +| approx_kl | 0.011946419 | +| clip_fraction | 0.343 | +| clip_range | 0.0699 | +| entropy_loss | -6.58 | +| explained_variance | 0.382 | +| learning_rate | 4.52e-05 | +| loss | -0.0337 | +| n_updates | 55588 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.00022 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1421 | +| iterations | 9944 | +| time_elapsed | 14322 | +| total_timesteps | 20365312 | +| train/ | | +| approx_kl | 0.011316763 | +| clip_fraction | 0.352 | +| clip_range | 0.0699 | +| entropy_loss | -5.64 | +| explained_variance | 0.608 | +| learning_rate | 4.52e-05 | +| loss | -0.0251 | +| n_updates | 55592 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000136 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1421 | +| iterations | 9945 | +| time_elapsed | 14323 | +| total_timesteps | 20367360 | +| train/ | | +| approx_kl | 0.013045331 | +| clip_fraction | 0.351 | +| clip_range | 0.0699 | +| entropy_loss | -6.51 | +| explained_variance | 0.266 | +| learning_rate | 4.52e-05 | +| loss | -0.0317 | +| n_updates | 55596 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000193 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1421 | +| iterations | 9946 | +| time_elapsed | 14325 | +| total_timesteps | 20369408 | +| train/ | | +| approx_kl | 0.011666881 | +| clip_fraction | 0.342 | +| clip_range | 0.0699 | +| entropy_loss | -6.55 | +| explained_variance | 0.083 | +| learning_rate | 4.52e-05 | +| loss | -0.0292 | +| n_updates | 55600 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000271 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1421 | +| iterations | 9947 | +| time_elapsed | 14326 | +| total_timesteps | 20371456 | +| train/ | | +| approx_kl | 0.013791107 | +| clip_fraction | 0.36 | +| clip_range | 0.0699 | +| entropy_loss | -6.83 | +| explained_variance | 0.04 | +| learning_rate | 4.52e-05 | +| loss | -0.0329 | +| n_updates | 55604 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000209 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1421 | +| iterations | 9948 | +| time_elapsed | 14328 | +| total_timesteps | 20373504 | +| train/ | | +| approx_kl | 0.014785745 | +| clip_fraction | 0.334 | +| clip_range | 0.0699 | +| entropy_loss | -6.36 | +| explained_variance | 0.455 | +| learning_rate | 4.52e-05 | +| loss | -0.0335 | +| n_updates | 55608 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.00017 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1421 | +| iterations | 9949 | +| time_elapsed | 14329 | +| total_timesteps | 20375552 | +| train/ | | +| approx_kl | 0.01575586 | +| clip_fraction | 0.366 | +| clip_range | 0.0699 | +| entropy_loss | -6.59 | +| explained_variance | 0.409 | +| learning_rate | 4.52e-05 | +| loss | -0.0357 | +| n_updates | 55612 | +| policy_gradient_loss | -0.0224 | +| value_loss | 6.96e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1421 | +| iterations | 9950 | +| time_elapsed | 14331 | +| total_timesteps | 20377600 | +| train/ | | +| approx_kl | 0.016233882 | +| clip_fraction | 0.333 | +| clip_range | 0.0699 | +| entropy_loss | -6.67 | +| explained_variance | 0.339 | +| learning_rate | 4.52e-05 | +| loss | -0.0292 | +| n_updates | 55616 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000189 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1421 | +| iterations | 9951 | +| time_elapsed | 14332 | +| total_timesteps | 20379648 | +| train/ | | +| approx_kl | 0.013680482 | +| clip_fraction | 0.328 | +| clip_range | 0.0699 | +| entropy_loss | -6.31 | +| explained_variance | 0.382 | +| learning_rate | 4.52e-05 | +| loss | -0.0225 | +| n_updates | 55620 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000238 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1421 | +| iterations | 9952 | +| time_elapsed | 14334 | +| total_timesteps | 20381696 | +| train/ | | +| approx_kl | 0.014803579 | +| clip_fraction | 0.351 | +| clip_range | 0.0699 | +| entropy_loss | -6.18 | +| explained_variance | 0.682 | +| learning_rate | 4.52e-05 | +| loss | -0.035 | +| n_updates | 55624 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000115 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1421 | +| iterations | 9953 | +| time_elapsed | 14335 | +| total_timesteps | 20383744 | +| train/ | | +| approx_kl | 0.014973067 | +| clip_fraction | 0.347 | +| clip_range | 0.0699 | +| entropy_loss | -6.54 | +| explained_variance | 0.159 | +| learning_rate | 4.52e-05 | +| loss | -0.0362 | +| n_updates | 55628 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000168 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1421 | +| iterations | 9954 | +| time_elapsed | 14337 | +| total_timesteps | 20385792 | +| train/ | | +| approx_kl | 0.012359172 | +| clip_fraction | 0.342 | +| clip_range | 0.0699 | +| entropy_loss | -6.55 | +| explained_variance | 0.269 | +| learning_rate | 4.52e-05 | +| loss | -0.0314 | +| n_updates | 55632 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000228 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1421 | +| iterations | 9955 | +| time_elapsed | 14338 | +| total_timesteps | 20387840 | +| train/ | | +| approx_kl | 0.016132444 | +| clip_fraction | 0.329 | +| clip_range | 0.0699 | +| entropy_loss | -6.12 | +| explained_variance | 0.338 | +| learning_rate | 4.52e-05 | +| loss | -0.0289 | +| n_updates | 55636 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000195 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1421 | +| iterations | 9956 | +| time_elapsed | 14339 | +| total_timesteps | 20389888 | +| train/ | | +| approx_kl | 0.011710291 | +| clip_fraction | 0.335 | +| clip_range | 0.0699 | +| entropy_loss | -6.69 | +| explained_variance | 0.313 | +| learning_rate | 4.52e-05 | +| loss | -0.0314 | +| n_updates | 55640 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000151 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1421 | +| iterations | 9957 | +| time_elapsed | 14341 | +| total_timesteps | 20391936 | +| train/ | | +| approx_kl | 0.011989215 | +| clip_fraction | 0.332 | +| clip_range | 0.0699 | +| entropy_loss | -6.81 | +| explained_variance | 0.0302 | +| learning_rate | 4.52e-05 | +| loss | -0.0295 | +| n_updates | 55644 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000267 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1421 | +| iterations | 9958 | +| time_elapsed | 14342 | +| total_timesteps | 20393984 | +| train/ | | +| approx_kl | 0.011457444 | +| clip_fraction | 0.34 | +| clip_range | 0.0699 | +| entropy_loss | -6.74 | +| explained_variance | 0.219 | +| learning_rate | 4.52e-05 | +| loss | -0.0313 | +| n_updates | 55648 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.00016 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1421 | +| iterations | 9959 | +| time_elapsed | 14344 | +| total_timesteps | 20396032 | +| train/ | | +| approx_kl | 0.013005672 | +| clip_fraction | 0.353 | +| clip_range | 0.0699 | +| entropy_loss | -6.86 | +| explained_variance | 0.0623 | +| learning_rate | 4.52e-05 | +| loss | -0.0326 | +| n_updates | 55652 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000158 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1421 | +| iterations | 9960 | +| time_elapsed | 14345 | +| total_timesteps | 20398080 | +| train/ | | +| approx_kl | 0.013113163 | +| clip_fraction | 0.348 | +| clip_range | 0.0699 | +| entropy_loss | -6.39 | +| explained_variance | 0.456 | +| learning_rate | 4.52e-05 | +| loss | -0.0347 | +| n_updates | 55656 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000109 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1421 | +| iterations | 9961 | +| time_elapsed | 14347 | +| total_timesteps | 20400128 | +| train/ | | +| approx_kl | 0.011637128 | +| clip_fraction | 0.332 | +| clip_range | 0.0699 | +| entropy_loss | -6.29 | +| explained_variance | 0.263 | +| learning_rate | 4.52e-05 | +| loss | -0.0327 | +| n_updates | 55660 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000345 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1421 | +| iterations | 9962 | +| time_elapsed | 14348 | +| total_timesteps | 20402176 | +| train/ | | +| approx_kl | 0.010329605 | +| clip_fraction | 0.338 | +| clip_range | 0.0699 | +| entropy_loss | -6.81 | +| explained_variance | 0.043 | +| learning_rate | 4.52e-05 | +| loss | -0.0284 | +| n_updates | 55664 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.00033 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1421 | +| iterations | 9963 | +| time_elapsed | 14350 | +| total_timesteps | 20404224 | +| train/ | | +| approx_kl | 0.01207613 | +| clip_fraction | 0.325 | +| clip_range | 0.0699 | +| entropy_loss | -6.29 | +| explained_variance | 0.347 | +| learning_rate | 4.52e-05 | +| loss | -0.0336 | +| n_updates | 55668 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000179 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1421 | +| iterations | 9964 | +| time_elapsed | 14351 | +| total_timesteps | 20406272 | +| train/ | | +| approx_kl | 0.015208073 | +| clip_fraction | 0.378 | +| clip_range | 0.0699 | +| entropy_loss | -6.49 | +| explained_variance | 0.385 | +| learning_rate | 4.52e-05 | +| loss | -0.0342 | +| n_updates | 55672 | +| policy_gradient_loss | -0.022 | +| value_loss | 0.000128 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1421 | +| iterations | 9965 | +| time_elapsed | 14352 | +| total_timesteps | 20408320 | +| train/ | | +| approx_kl | 0.013252586 | +| clip_fraction | 0.346 | +| clip_range | 0.0699 | +| entropy_loss | -6.74 | +| explained_variance | 0.226 | +| learning_rate | 4.52e-05 | +| loss | -0.032 | +| n_updates | 55676 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000162 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1421 | +| iterations | 9966 | +| time_elapsed | 14354 | +| total_timesteps | 20410368 | +| train/ | | +| approx_kl | 0.014017653 | +| clip_fraction | 0.334 | +| clip_range | 0.0699 | +| entropy_loss | -6.95 | +| explained_variance | -0.0211 | +| learning_rate | 4.52e-05 | +| loss | -0.032 | +| n_updates | 55680 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000206 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1421 | +| iterations | 9967 | +| time_elapsed | 14355 | +| total_timesteps | 20412416 | +| train/ | | +| approx_kl | 0.012388131 | +| clip_fraction | 0.35 | +| clip_range | 0.0699 | +| entropy_loss | -6.84 | +| explained_variance | 0.193 | +| learning_rate | 4.52e-05 | +| loss | -0.0278 | +| n_updates | 55684 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000234 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1421 | +| iterations | 9968 | +| time_elapsed | 14357 | +| total_timesteps | 20414464 | +| train/ | | +| approx_kl | 0.011838848 | +| clip_fraction | 0.319 | +| clip_range | 0.0699 | +| entropy_loss | -6.78 | +| explained_variance | 0.264 | +| learning_rate | 4.52e-05 | +| loss | -0.0308 | +| n_updates | 55688 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000176 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1421 | +| iterations | 9969 | +| time_elapsed | 14358 | +| total_timesteps | 20416512 | +| train/ | | +| approx_kl | 0.012329996 | +| clip_fraction | 0.331 | +| clip_range | 0.0699 | +| entropy_loss | -6.41 | +| explained_variance | 0.499 | +| learning_rate | 4.52e-05 | +| loss | -0.0321 | +| n_updates | 55692 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000165 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1421 | +| iterations | 9970 | +| time_elapsed | 14360 | +| total_timesteps | 20418560 | +| train/ | | +| approx_kl | 0.015416088 | +| clip_fraction | 0.327 | +| clip_range | 0.0699 | +| entropy_loss | -6.51 | +| explained_variance | 0.451 | +| learning_rate | 4.52e-05 | +| loss | -0.0221 | +| n_updates | 55696 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000194 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1421 | +| iterations | 9971 | +| time_elapsed | 14361 | +| total_timesteps | 20420608 | +| train/ | | +| approx_kl | 0.016682245 | +| clip_fraction | 0.326 | +| clip_range | 0.0699 | +| entropy_loss | -6.85 | +| explained_variance | 0.285 | +| learning_rate | 4.52e-05 | +| loss | -0.029 | +| n_updates | 55700 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000167 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1421 | +| iterations | 9972 | +| time_elapsed | 14363 | +| total_timesteps | 20422656 | +| train/ | | +| approx_kl | 0.012273221 | +| clip_fraction | 0.346 | +| clip_range | 0.0699 | +| entropy_loss | -6.84 | +| explained_variance | 0.335 | +| learning_rate | 4.52e-05 | +| loss | -0.0371 | +| n_updates | 55704 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000168 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1421 | +| iterations | 9973 | +| time_elapsed | 14364 | +| total_timesteps | 20424704 | +| train/ | | +| approx_kl | 0.012863699 | +| clip_fraction | 0.36 | +| clip_range | 0.0699 | +| entropy_loss | -6.79 | +| explained_variance | 0.494 | +| learning_rate | 4.51e-05 | +| loss | -0.035 | +| n_updates | 55708 | +| policy_gradient_loss | -0.0233 | +| value_loss | 7.74e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1421 | +| iterations | 9974 | +| time_elapsed | 14366 | +| total_timesteps | 20426752 | +| train/ | | +| approx_kl | 0.01320966 | +| clip_fraction | 0.35 | +| clip_range | 0.0699 | +| entropy_loss | -7.09 | +| explained_variance | -0.152 | +| learning_rate | 4.51e-05 | +| loss | -0.0332 | +| n_updates | 55712 | +| policy_gradient_loss | -0.0195 | +| value_loss | 9.47e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1421 | +| iterations | 9975 | +| time_elapsed | 14367 | +| total_timesteps | 20428800 | +| train/ | | +| approx_kl | 0.012863692 | +| clip_fraction | 0.314 | +| clip_range | 0.0699 | +| entropy_loss | -5.84 | +| explained_variance | 0.867 | +| learning_rate | 4.51e-05 | +| loss | -0.0221 | +| n_updates | 55716 | +| policy_gradient_loss | -0.0165 | +| value_loss | 5.81e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1421 | +| iterations | 9976 | +| time_elapsed | 14369 | +| total_timesteps | 20430848 | +| train/ | | +| approx_kl | 0.015441058 | +| clip_fraction | 0.325 | +| clip_range | 0.0699 | +| entropy_loss | -6.27 | +| explained_variance | 0.679 | +| learning_rate | 4.51e-05 | +| loss | -0.0257 | +| n_updates | 55720 | +| policy_gradient_loss | -0.0185 | +| value_loss | 7.72e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1421 | +| iterations | 9977 | +| time_elapsed | 14370 | +| total_timesteps | 20432896 | +| train/ | | +| approx_kl | 0.012974186 | +| clip_fraction | 0.326 | +| clip_range | 0.0699 | +| entropy_loss | -6.61 | +| explained_variance | -0.048 | +| learning_rate | 4.51e-05 | +| loss | -0.0303 | +| n_updates | 55724 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000121 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1421 | +| iterations | 9978 | +| time_elapsed | 14372 | +| total_timesteps | 20434944 | +| train/ | | +| approx_kl | 0.016174773 | +| clip_fraction | 0.354 | +| clip_range | 0.0699 | +| entropy_loss | -6.57 | +| explained_variance | 0.367 | +| learning_rate | 4.51e-05 | +| loss | -0.0313 | +| n_updates | 55728 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000142 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1421 | +| iterations | 9979 | +| time_elapsed | 14373 | +| total_timesteps | 20436992 | +| train/ | | +| approx_kl | 0.013780504 | +| clip_fraction | 0.329 | +| clip_range | 0.0699 | +| entropy_loss | -6.32 | +| explained_variance | 0.287 | +| learning_rate | 4.51e-05 | +| loss | -0.0288 | +| n_updates | 55732 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000193 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1421 | +| iterations | 9980 | +| time_elapsed | 14374 | +| total_timesteps | 20439040 | +| train/ | | +| approx_kl | 0.01289499 | +| clip_fraction | 0.345 | +| clip_range | 0.0699 | +| entropy_loss | -6.81 | +| explained_variance | 0.382 | +| learning_rate | 4.51e-05 | +| loss | -0.0277 | +| n_updates | 55736 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000137 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1421 | +| iterations | 9981 | +| time_elapsed | 14376 | +| total_timesteps | 20441088 | +| train/ | | +| approx_kl | 0.012335653 | +| clip_fraction | 0.343 | +| clip_range | 0.0699 | +| entropy_loss | -7.03 | +| explained_variance | -0.043 | +| learning_rate | 4.51e-05 | +| loss | -0.0307 | +| n_updates | 55740 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000247 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1421 | +| iterations | 9982 | +| time_elapsed | 14377 | +| total_timesteps | 20443136 | +| train/ | | +| approx_kl | 0.012088353 | +| clip_fraction | 0.35 | +| clip_range | 0.0699 | +| entropy_loss | -6.96 | +| explained_variance | 0.409 | +| learning_rate | 4.51e-05 | +| loss | -0.035 | +| n_updates | 55744 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000105 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1421 | +| iterations | 9983 | +| time_elapsed | 14379 | +| total_timesteps | 20445184 | +| train/ | | +| approx_kl | 0.01232709 | +| clip_fraction | 0.297 | +| clip_range | 0.0699 | +| entropy_loss | -6.15 | +| explained_variance | 0.504 | +| learning_rate | 4.51e-05 | +| loss | -0.0222 | +| n_updates | 55748 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000242 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1421 | +| iterations | 9984 | +| time_elapsed | 14380 | +| total_timesteps | 20447232 | +| train/ | | +| approx_kl | 0.015153885 | +| clip_fraction | 0.322 | +| clip_range | 0.0699 | +| entropy_loss | -6.01 | +| explained_variance | 0.679 | +| learning_rate | 4.51e-05 | +| loss | -0.0343 | +| n_updates | 55752 | +| policy_gradient_loss | -0.0195 | +| value_loss | 9.74e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1421 | +| iterations | 9985 | +| time_elapsed | 14382 | +| total_timesteps | 20449280 | +| train/ | | +| approx_kl | 0.01116516 | +| clip_fraction | 0.324 | +| clip_range | 0.0699 | +| entropy_loss | -6.79 | +| explained_variance | 0.463 | +| learning_rate | 4.51e-05 | +| loss | -0.0317 | +| n_updates | 55756 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000152 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1421 | +| iterations | 9986 | +| time_elapsed | 14383 | +| total_timesteps | 20451328 | +| train/ | | +| approx_kl | 0.015260676 | +| clip_fraction | 0.342 | +| clip_range | 0.0699 | +| entropy_loss | -6.02 | +| explained_variance | 0.593 | +| learning_rate | 4.51e-05 | +| loss | -0.0297 | +| n_updates | 55760 | +| policy_gradient_loss | -0.0203 | +| value_loss | 8.72e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1421 | +| iterations | 9987 | +| time_elapsed | 14384 | +| total_timesteps | 20453376 | +| train/ | | +| approx_kl | 0.0142022595 | +| clip_fraction | 0.336 | +| clip_range | 0.0699 | +| entropy_loss | -6.6 | +| explained_variance | 0.351 | +| learning_rate | 4.51e-05 | +| loss | -0.0279 | +| n_updates | 55764 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000136 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1421 | +| iterations | 9988 | +| time_elapsed | 14386 | +| total_timesteps | 20455424 | +| train/ | | +| approx_kl | 0.0144546535 | +| clip_fraction | 0.352 | +| clip_range | 0.0699 | +| entropy_loss | -6.59 | +| explained_variance | 0.469 | +| learning_rate | 4.51e-05 | +| loss | -0.0273 | +| n_updates | 55768 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000106 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1421 | +| iterations | 9989 | +| time_elapsed | 14387 | +| total_timesteps | 20457472 | +| train/ | | +| approx_kl | 0.011554732 | +| clip_fraction | 0.312 | +| clip_range | 0.0699 | +| entropy_loss | -6.9 | +| explained_variance | -0.0376 | +| learning_rate | 4.51e-05 | +| loss | -0.0271 | +| n_updates | 55772 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000225 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1421 | +| iterations | 9990 | +| time_elapsed | 14389 | +| total_timesteps | 20459520 | +| train/ | | +| approx_kl | 0.012609967 | +| clip_fraction | 0.325 | +| clip_range | 0.0699 | +| entropy_loss | -6.99 | +| explained_variance | 0.12 | +| learning_rate | 4.51e-05 | +| loss | -0.0239 | +| n_updates | 55776 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000329 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1421 | +| iterations | 9991 | +| time_elapsed | 14390 | +| total_timesteps | 20461568 | +| train/ | | +| approx_kl | 0.012189029 | +| clip_fraction | 0.355 | +| clip_range | 0.0699 | +| entropy_loss | -6.61 | +| explained_variance | 0.258 | +| learning_rate | 4.51e-05 | +| loss | -0.0304 | +| n_updates | 55780 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000346 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1421 | +| iterations | 9992 | +| time_elapsed | 14392 | +| total_timesteps | 20463616 | +| train/ | | +| approx_kl | 0.013589916 | +| clip_fraction | 0.364 | +| clip_range | 0.0699 | +| entropy_loss | -6.49 | +| explained_variance | 0.42 | +| learning_rate | 4.51e-05 | +| loss | -0.0314 | +| n_updates | 55784 | +| policy_gradient_loss | -0.023 | +| value_loss | 0.000148 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1421 | +| iterations | 9993 | +| time_elapsed | 14393 | +| total_timesteps | 20465664 | +| train/ | | +| approx_kl | 0.012782334 | +| clip_fraction | 0.362 | +| clip_range | 0.0699 | +| entropy_loss | -6.62 | +| explained_variance | 0.536 | +| learning_rate | 4.51e-05 | +| loss | -0.036 | +| n_updates | 55788 | +| policy_gradient_loss | -0.024 | +| value_loss | 0.000104 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1421 | +| iterations | 9994 | +| time_elapsed | 14394 | +| total_timesteps | 20467712 | +| train/ | | +| approx_kl | 0.013503892 | +| clip_fraction | 0.327 | +| clip_range | 0.0699 | +| entropy_loss | -6.19 | +| explained_variance | 0.309 | +| learning_rate | 4.51e-05 | +| loss | -0.0249 | +| n_updates | 55792 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000337 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1421 | +| iterations | 9995 | +| time_elapsed | 14396 | +| total_timesteps | 20469760 | +| train/ | | +| approx_kl | 0.013403221 | +| clip_fraction | 0.357 | +| clip_range | 0.0699 | +| entropy_loss | -5.83 | +| explained_variance | 0.631 | +| learning_rate | 4.51e-05 | +| loss | -0.031 | +| n_updates | 55796 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000115 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1421 | +| iterations | 9996 | +| time_elapsed | 14397 | +| total_timesteps | 20471808 | +| train/ | | +| approx_kl | 0.012295959 | +| clip_fraction | 0.339 | +| clip_range | 0.0699 | +| entropy_loss | -6.05 | +| explained_variance | 0.557 | +| learning_rate | 4.51e-05 | +| loss | -0.0307 | +| n_updates | 55800 | +| policy_gradient_loss | -0.0183 | +| value_loss | 8.75e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1421 | +| iterations | 9997 | +| time_elapsed | 14399 | +| total_timesteps | 20473856 | +| train/ | | +| approx_kl | 0.012861419 | +| clip_fraction | 0.316 | +| clip_range | 0.0699 | +| entropy_loss | -7.07 | +| explained_variance | -0.142 | +| learning_rate | 4.51e-05 | +| loss | -0.0259 | +| n_updates | 55804 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000216 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1421 | +| iterations | 9998 | +| time_elapsed | 14400 | +| total_timesteps | 20475904 | +| train/ | | +| approx_kl | 0.017688833 | +| clip_fraction | 0.355 | +| clip_range | 0.0699 | +| entropy_loss | -6.99 | +| explained_variance | -0.167 | +| learning_rate | 4.51e-05 | +| loss | -0.0326 | +| n_updates | 55808 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000171 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1421 | +| iterations | 9999 | +| time_elapsed | 14402 | +| total_timesteps | 20477952 | +| train/ | | +| approx_kl | 0.013083233 | +| clip_fraction | 0.317 | +| clip_range | 0.0699 | +| entropy_loss | -6.9 | +| explained_variance | 0.312 | +| learning_rate | 4.51e-05 | +| loss | -0.0281 | +| n_updates | 55812 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000142 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1421 | +| iterations | 10000 | +| time_elapsed | 14403 | +| total_timesteps | 20480000 | +| train/ | | +| approx_kl | 0.01336208 | +| clip_fraction | 0.312 | +| clip_range | 0.0699 | +| entropy_loss | -6.24 | +| explained_variance | 0.319 | +| learning_rate | 4.51e-05 | +| loss | -0.0246 | +| n_updates | 55816 | +| policy_gradient_loss | -0.0144 | +| value_loss | 0.000307 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1421 | +| iterations | 10001 | +| time_elapsed | 14405 | +| total_timesteps | 20482048 | +| train/ | | +| approx_kl | 0.012308484 | +| clip_fraction | 0.34 | +| clip_range | 0.0699 | +| entropy_loss | -6.27 | +| explained_variance | 0.368 | +| learning_rate | 4.51e-05 | +| loss | -0.0317 | +| n_updates | 55820 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000196 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1421 | +| iterations | 10002 | +| time_elapsed | 14406 | +| total_timesteps | 20484096 | +| train/ | | +| approx_kl | 0.0087165255 | +| clip_fraction | 0.309 | +| clip_range | 0.0699 | +| entropy_loss | -6.36 | +| explained_variance | 0.516 | +| learning_rate | 4.51e-05 | +| loss | -0.0254 | +| n_updates | 55824 | +| policy_gradient_loss | -0.0143 | +| value_loss | 0.000215 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1421 | +| iterations | 10003 | +| time_elapsed | 14407 | +| total_timesteps | 20486144 | +| train/ | | +| approx_kl | 0.0125529645 | +| clip_fraction | 0.301 | +| clip_range | 0.0699 | +| entropy_loss | -5.68 | +| explained_variance | 0.759 | +| learning_rate | 4.51e-05 | +| loss | -0.0301 | +| n_updates | 55828 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000111 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1421 | +| iterations | 10004 | +| time_elapsed | 14409 | +| total_timesteps | 20488192 | +| train/ | | +| approx_kl | 0.011481345 | +| clip_fraction | 0.322 | +| clip_range | 0.0699 | +| entropy_loss | -6.44 | +| explained_variance | 0.592 | +| learning_rate | 4.51e-05 | +| loss | -0.0358 | +| n_updates | 55832 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000102 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1421 | +| iterations | 10005 | +| time_elapsed | 14410 | +| total_timesteps | 20490240 | +| train/ | | +| approx_kl | 0.015000001 | +| clip_fraction | 0.356 | +| clip_range | 0.0699 | +| entropy_loss | -7.03 | +| explained_variance | -0.066 | +| learning_rate | 4.51e-05 | +| loss | -0.034 | +| n_updates | 55836 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000128 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1421 | +| iterations | 10006 | +| time_elapsed | 14412 | +| total_timesteps | 20492288 | +| train/ | | +| approx_kl | 0.015604271 | +| clip_fraction | 0.328 | +| clip_range | 0.0699 | +| entropy_loss | -6.79 | +| explained_variance | 0.384 | +| learning_rate | 4.51e-05 | +| loss | -0.0281 | +| n_updates | 55840 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000115 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1421 | +| iterations | 10007 | +| time_elapsed | 14413 | +| total_timesteps | 20494336 | +| train/ | | +| approx_kl | 0.015460346 | +| clip_fraction | 0.37 | +| clip_range | 0.0699 | +| entropy_loss | -6.36 | +| explained_variance | 0.668 | +| learning_rate | 4.51e-05 | +| loss | -0.0408 | +| n_updates | 55844 | +| policy_gradient_loss | -0.022 | +| value_loss | 7.4e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1421 | +| iterations | 10008 | +| time_elapsed | 14415 | +| total_timesteps | 20496384 | +| train/ | | +| approx_kl | 0.015766641 | +| clip_fraction | 0.353 | +| clip_range | 0.0699 | +| entropy_loss | -6.88 | +| explained_variance | -0.0651 | +| learning_rate | 4.51e-05 | +| loss | -0.0333 | +| n_updates | 55848 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.00011 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1421 | +| iterations | 10009 | +| time_elapsed | 14416 | +| total_timesteps | 20498432 | +| train/ | | +| approx_kl | 0.012570608 | +| clip_fraction | 0.313 | +| clip_range | 0.0699 | +| entropy_loss | -6.66 | +| explained_variance | 0.415 | +| learning_rate | 4.51e-05 | +| loss | -0.0264 | +| n_updates | 55852 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000204 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1421 | +| iterations | 10010 | +| time_elapsed | 14418 | +| total_timesteps | 20500480 | +| train/ | | +| approx_kl | 0.012455372 | +| clip_fraction | 0.348 | +| clip_range | 0.0699 | +| entropy_loss | -6.54 | +| explained_variance | 0.0799 | +| learning_rate | 4.51e-05 | +| loss | -0.0318 | +| n_updates | 55856 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000165 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1421 | +| iterations | 10011 | +| time_elapsed | 14419 | +| total_timesteps | 20502528 | +| train/ | | +| approx_kl | 0.012912136 | +| clip_fraction | 0.326 | +| clip_range | 0.0699 | +| entropy_loss | -5.81 | +| explained_variance | 0.621 | +| learning_rate | 4.51e-05 | +| loss | -0.0256 | +| n_updates | 55860 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000155 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1421 | +| iterations | 10012 | +| time_elapsed | 14421 | +| total_timesteps | 20504576 | +| train/ | | +| approx_kl | 0.015969198 | +| clip_fraction | 0.348 | +| clip_range | 0.0699 | +| entropy_loss | -5.95 | +| explained_variance | 0.769 | +| learning_rate | 4.51e-05 | +| loss | -0.0391 | +| n_updates | 55864 | +| policy_gradient_loss | -0.0212 | +| value_loss | 6.23e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1421 | +| iterations | 10013 | +| time_elapsed | 14422 | +| total_timesteps | 20506624 | +| train/ | | +| approx_kl | 0.015378196 | +| clip_fraction | 0.321 | +| clip_range | 0.0699 | +| entropy_loss | -5.92 | +| explained_variance | 0.625 | +| learning_rate | 4.51e-05 | +| loss | -0.0233 | +| n_updates | 55868 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000131 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1421 | +| iterations | 10014 | +| time_elapsed | 14424 | +| total_timesteps | 20508672 | +| train/ | | +| approx_kl | 0.012294573 | +| clip_fraction | 0.323 | +| clip_range | 0.0699 | +| entropy_loss | -6.43 | +| explained_variance | 0.453 | +| learning_rate | 4.51e-05 | +| loss | -0.0282 | +| n_updates | 55872 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000189 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1421 | +| iterations | 10015 | +| time_elapsed | 14425 | +| total_timesteps | 20510720 | +| train/ | | +| approx_kl | 0.013341245 | +| clip_fraction | 0.333 | +| clip_range | 0.0699 | +| entropy_loss | -6.46 | +| explained_variance | 0.144 | +| learning_rate | 4.51e-05 | +| loss | -0.0301 | +| n_updates | 55876 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000156 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1421 | +| iterations | 10016 | +| time_elapsed | 14427 | +| total_timesteps | 20512768 | +| train/ | | +| approx_kl | 0.014471998 | +| clip_fraction | 0.349 | +| clip_range | 0.0699 | +| entropy_loss | -6.47 | +| explained_variance | 0.428 | +| learning_rate | 4.51e-05 | +| loss | -0.0283 | +| n_updates | 55880 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000205 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1421 | +| iterations | 10017 | +| time_elapsed | 14428 | +| total_timesteps | 20514816 | +| train/ | | +| approx_kl | 0.014419769 | +| clip_fraction | 0.354 | +| clip_range | 0.0699 | +| entropy_loss | -6.83 | +| explained_variance | -0.0441 | +| learning_rate | 4.51e-05 | +| loss | -0.0339 | +| n_updates | 55884 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000149 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1421 | +| iterations | 10018 | +| time_elapsed | 14429 | +| total_timesteps | 20516864 | +| train/ | | +| approx_kl | 0.011211486 | +| clip_fraction | 0.334 | +| clip_range | 0.0699 | +| entropy_loss | -6.7 | +| explained_variance | 0.445 | +| learning_rate | 4.51e-05 | +| loss | -0.0322 | +| n_updates | 55888 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.00022 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1421 | +| iterations | 10019 | +| time_elapsed | 14431 | +| total_timesteps | 20518912 | +| train/ | | +| approx_kl | 0.012197325 | +| clip_fraction | 0.344 | +| clip_range | 0.0699 | +| entropy_loss | -6.62 | +| explained_variance | 0.346 | +| learning_rate | 4.51e-05 | +| loss | -0.0334 | +| n_updates | 55892 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000139 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1421 | +| iterations | 10020 | +| time_elapsed | 14432 | +| total_timesteps | 20520960 | +| train/ | | +| approx_kl | 0.013473799 | +| clip_fraction | 0.341 | +| clip_range | 0.0699 | +| entropy_loss | -6.11 | +| explained_variance | 0.622 | +| learning_rate | 4.51e-05 | +| loss | -0.0293 | +| n_updates | 55896 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.00011 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1421 | +| iterations | 10021 | +| time_elapsed | 14434 | +| total_timesteps | 20523008 | +| train/ | | +| approx_kl | 0.012211032 | +| clip_fraction | 0.339 | +| clip_range | 0.0699 | +| entropy_loss | -6.59 | +| explained_variance | 0.474 | +| learning_rate | 4.51e-05 | +| loss | -0.0304 | +| n_updates | 55900 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000162 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1421 | +| iterations | 10022 | +| time_elapsed | 14435 | +| total_timesteps | 20525056 | +| train/ | | +| approx_kl | 0.012260893 | +| clip_fraction | 0.325 | +| clip_range | 0.0699 | +| entropy_loss | -6.38 | +| explained_variance | 0.381 | +| learning_rate | 4.51e-05 | +| loss | -0.0254 | +| n_updates | 55904 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1421 | +| iterations | 10023 | +| time_elapsed | 14437 | +| total_timesteps | 20527104 | +| train/ | | +| approx_kl | 0.012334452 | +| clip_fraction | 0.313 | +| clip_range | 0.0699 | +| entropy_loss | -6.17 | +| explained_variance | 0.364 | +| learning_rate | 4.51e-05 | +| loss | -0.0264 | +| n_updates | 55908 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000167 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1421 | +| iterations | 10024 | +| time_elapsed | 14438 | +| total_timesteps | 20529152 | +| train/ | | +| approx_kl | 0.012991451 | +| clip_fraction | 0.295 | +| clip_range | 0.0699 | +| entropy_loss | -6.04 | +| explained_variance | 0.447 | +| learning_rate | 4.51e-05 | +| loss | -0.0201 | +| n_updates | 55912 | +| policy_gradient_loss | -0.0127 | +| value_loss | 0.000367 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1421 | +| iterations | 10025 | +| time_elapsed | 14440 | +| total_timesteps | 20531200 | +| train/ | | +| approx_kl | 0.011213973 | +| clip_fraction | 0.316 | +| clip_range | 0.0699 | +| entropy_loss | -6.38 | +| explained_variance | 0.262 | +| learning_rate | 4.51e-05 | +| loss | -0.0332 | +| n_updates | 55916 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000142 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1421 | +| iterations | 10026 | +| time_elapsed | 14441 | +| total_timesteps | 20533248 | +| train/ | | +| approx_kl | 0.011607768 | +| clip_fraction | 0.341 | +| clip_range | 0.0699 | +| entropy_loss | -7.11 | +| explained_variance | -0.00947 | +| learning_rate | 4.51e-05 | +| loss | -0.0294 | +| n_updates | 55920 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000158 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1421 | +| iterations | 10027 | +| time_elapsed | 14443 | +| total_timesteps | 20535296 | +| train/ | | +| approx_kl | 0.010991379 | +| clip_fraction | 0.331 | +| clip_range | 0.0699 | +| entropy_loss | -6.7 | +| explained_variance | 0.458 | +| learning_rate | 4.51e-05 | +| loss | -0.0302 | +| n_updates | 55924 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000172 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1421 | +| iterations | 10028 | +| time_elapsed | 14444 | +| total_timesteps | 20537344 | +| train/ | | +| approx_kl | 0.01037797 | +| clip_fraction | 0.317 | +| clip_range | 0.0699 | +| entropy_loss | -6.65 | +| explained_variance | 0.239 | +| learning_rate | 4.51e-05 | +| loss | -0.02 | +| n_updates | 55928 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000331 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1421 | +| iterations | 10029 | +| time_elapsed | 14446 | +| total_timesteps | 20539392 | +| train/ | | +| approx_kl | 0.013306208 | +| clip_fraction | 0.356 | +| clip_range | 0.0699 | +| entropy_loss | -6.75 | +| explained_variance | 0.485 | +| learning_rate | 4.51e-05 | +| loss | -0.0388 | +| n_updates | 55932 | +| policy_gradient_loss | -0.0228 | +| value_loss | 9.95e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1421 | +| iterations | 10030 | +| time_elapsed | 14447 | +| total_timesteps | 20541440 | +| train/ | | +| approx_kl | 0.0117786415 | +| clip_fraction | 0.321 | +| clip_range | 0.0699 | +| entropy_loss | -6.69 | +| explained_variance | 0.357 | +| learning_rate | 4.51e-05 | +| loss | -0.024 | +| n_updates | 55936 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000276 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1421 | +| iterations | 10031 | +| time_elapsed | 14448 | +| total_timesteps | 20543488 | +| train/ | | +| approx_kl | 0.011774642 | +| clip_fraction | 0.314 | +| clip_range | 0.0699 | +| entropy_loss | -6.61 | +| explained_variance | 0.228 | +| learning_rate | 4.51e-05 | +| loss | -0.0315 | +| n_updates | 55940 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000202 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1421 | +| iterations | 10032 | +| time_elapsed | 14450 | +| total_timesteps | 20545536 | +| train/ | | +| approx_kl | 0.012445084 | +| clip_fraction | 0.334 | +| clip_range | 0.0699 | +| entropy_loss | -6.49 | +| explained_variance | 0.319 | +| learning_rate | 4.51e-05 | +| loss | -0.0299 | +| n_updates | 55944 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000277 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1421 | +| iterations | 10033 | +| time_elapsed | 14451 | +| total_timesteps | 20547584 | +| train/ | | +| approx_kl | 0.015349154 | +| clip_fraction | 0.355 | +| clip_range | 0.0699 | +| entropy_loss | -6.32 | +| explained_variance | 0.656 | +| learning_rate | 4.51e-05 | +| loss | -0.0364 | +| n_updates | 55948 | +| policy_gradient_loss | -0.0215 | +| value_loss | 9.4e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1421 | +| iterations | 10034 | +| time_elapsed | 14453 | +| total_timesteps | 20549632 | +| train/ | | +| approx_kl | 0.012333106 | +| clip_fraction | 0.321 | +| clip_range | 0.0699 | +| entropy_loss | -6.14 | +| explained_variance | 0.486 | +| learning_rate | 4.51e-05 | +| loss | -0.0313 | +| n_updates | 55952 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000169 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1421 | +| iterations | 10035 | +| time_elapsed | 14454 | +| total_timesteps | 20551680 | +| train/ | | +| approx_kl | 0.0118147405 | +| clip_fraction | 0.335 | +| clip_range | 0.0699 | +| entropy_loss | -6.52 | +| explained_variance | 0.669 | +| learning_rate | 4.51e-05 | +| loss | -0.0349 | +| n_updates | 55956 | +| policy_gradient_loss | -0.0195 | +| value_loss | 8.51e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1421 | +| iterations | 10036 | +| time_elapsed | 14456 | +| total_timesteps | 20553728 | +| train/ | | +| approx_kl | 0.013780339 | +| clip_fraction | 0.312 | +| clip_range | 0.0699 | +| entropy_loss | -6.93 | +| explained_variance | -0.151 | +| learning_rate | 4.51e-05 | +| loss | -0.0343 | +| n_updates | 55960 | +| policy_gradient_loss | -0.0195 | +| value_loss | 8.18e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1421 | +| iterations | 10037 | +| time_elapsed | 14457 | +| total_timesteps | 20555776 | +| train/ | | +| approx_kl | 0.012179822 | +| clip_fraction | 0.33 | +| clip_range | 0.0699 | +| entropy_loss | -6.8 | +| explained_variance | 0.311 | +| learning_rate | 4.51e-05 | +| loss | -0.0289 | +| n_updates | 55964 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000204 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1421 | +| iterations | 10038 | +| time_elapsed | 14459 | +| total_timesteps | 20557824 | +| train/ | | +| approx_kl | 0.0142127145 | +| clip_fraction | 0.319 | +| clip_range | 0.0699 | +| entropy_loss | -6.55 | +| explained_variance | 0.249 | +| learning_rate | 4.51e-05 | +| loss | -0.028 | +| n_updates | 55968 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000214 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1421 | +| iterations | 10039 | +| time_elapsed | 14460 | +| total_timesteps | 20559872 | +| train/ | | +| approx_kl | 0.013076229 | +| clip_fraction | 0.347 | +| clip_range | 0.0699 | +| entropy_loss | -6.65 | +| explained_variance | 0.613 | +| learning_rate | 4.51e-05 | +| loss | -0.0364 | +| n_updates | 55972 | +| policy_gradient_loss | -0.0209 | +| value_loss | 9.5e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1421 | +| iterations | 10040 | +| time_elapsed | 14462 | +| total_timesteps | 20561920 | +| train/ | | +| approx_kl | 0.011901084 | +| clip_fraction | 0.307 | +| clip_range | 0.0699 | +| entropy_loss | -6.34 | +| explained_variance | 0.395 | +| learning_rate | 4.51e-05 | +| loss | -0.0233 | +| n_updates | 55976 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000218 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1421 | +| iterations | 10041 | +| time_elapsed | 14463 | +| total_timesteps | 20563968 | +| train/ | | +| approx_kl | 0.010931932 | +| clip_fraction | 0.334 | +| clip_range | 0.0699 | +| entropy_loss | -6.6 | +| explained_variance | 0.329 | +| learning_rate | 4.51e-05 | +| loss | -0.0277 | +| n_updates | 55980 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000193 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1421 | +| iterations | 10042 | +| time_elapsed | 14465 | +| total_timesteps | 20566016 | +| train/ | | +| approx_kl | 0.015655508 | +| clip_fraction | 0.352 | +| clip_range | 0.0699 | +| entropy_loss | -6.55 | +| explained_variance | 0.567 | +| learning_rate | 4.51e-05 | +| loss | -0.0274 | +| n_updates | 55984 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000111 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1421 | +| iterations | 10043 | +| time_elapsed | 14466 | +| total_timesteps | 20568064 | +| train/ | | +| approx_kl | 0.013309015 | +| clip_fraction | 0.31 | +| clip_range | 0.0699 | +| entropy_loss | -6.21 | +| explained_variance | 0.484 | +| learning_rate | 4.51e-05 | +| loss | -0.0336 | +| n_updates | 55988 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000263 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1421 | +| iterations | 10044 | +| time_elapsed | 14468 | +| total_timesteps | 20570112 | +| train/ | | +| approx_kl | 0.013273157 | +| clip_fraction | 0.327 | +| clip_range | 0.0699 | +| entropy_loss | -6.27 | +| explained_variance | 0.539 | +| learning_rate | 4.51e-05 | +| loss | -0.0239 | +| n_updates | 55992 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000149 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1421 | +| iterations | 10045 | +| time_elapsed | 14469 | +| total_timesteps | 20572160 | +| train/ | | +| approx_kl | 0.013475635 | +| clip_fraction | 0.337 | +| clip_range | 0.0699 | +| entropy_loss | -6.7 | +| explained_variance | 0.365 | +| learning_rate | 4.51e-05 | +| loss | -0.0338 | +| n_updates | 55996 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1421 | +| iterations | 10046 | +| time_elapsed | 14471 | +| total_timesteps | 20574208 | +| train/ | | +| approx_kl | 0.012837919 | +| clip_fraction | 0.324 | +| clip_range | 0.0699 | +| entropy_loss | -6.77 | +| explained_variance | 0.258 | +| learning_rate | 4.51e-05 | +| loss | -0.0306 | +| n_updates | 56000 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000156 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1421 | +| iterations | 10047 | +| time_elapsed | 14472 | +| total_timesteps | 20576256 | +| train/ | | +| approx_kl | 0.015011173 | +| clip_fraction | 0.33 | +| clip_range | 0.0699 | +| entropy_loss | -6.46 | +| explained_variance | 0.332 | +| learning_rate | 4.51e-05 | +| loss | -0.0309 | +| n_updates | 56004 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000318 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1421 | +| iterations | 10048 | +| time_elapsed | 14473 | +| total_timesteps | 20578304 | +| train/ | | +| approx_kl | 0.011254072 | +| clip_fraction | 0.324 | +| clip_range | 0.0699 | +| entropy_loss | -6.21 | +| explained_variance | 0.313 | +| learning_rate | 4.51e-05 | +| loss | -0.0266 | +| n_updates | 56008 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000397 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1421 | +| iterations | 10049 | +| time_elapsed | 14475 | +| total_timesteps | 20580352 | +| train/ | | +| approx_kl | 0.009611518 | +| clip_fraction | 0.296 | +| clip_range | 0.0699 | +| entropy_loss | -6.68 | +| explained_variance | 0.212 | +| learning_rate | 4.51e-05 | +| loss | -0.0196 | +| n_updates | 56012 | +| policy_gradient_loss | -0.0143 | +| value_loss | 0.000388 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1421 | +| iterations | 10050 | +| time_elapsed | 14476 | +| total_timesteps | 20582400 | +| train/ | | +| approx_kl | 0.011421495 | +| clip_fraction | 0.345 | +| clip_range | 0.0699 | +| entropy_loss | -6.59 | +| explained_variance | 0.498 | +| learning_rate | 4.51e-05 | +| loss | -0.0357 | +| n_updates | 56016 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000155 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1421 | +| iterations | 10051 | +| time_elapsed | 14478 | +| total_timesteps | 20584448 | +| train/ | | +| approx_kl | 0.009090427 | +| clip_fraction | 0.305 | +| clip_range | 0.0699 | +| entropy_loss | -6.54 | +| explained_variance | 0.346 | +| learning_rate | 4.51e-05 | +| loss | -0.0261 | +| n_updates | 56020 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000326 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1421 | +| iterations | 10052 | +| time_elapsed | 14479 | +| total_timesteps | 20586496 | +| train/ | | +| approx_kl | 0.012357242 | +| clip_fraction | 0.321 | +| clip_range | 0.0699 | +| entropy_loss | -6.51 | +| explained_variance | 0.486 | +| learning_rate | 4.51e-05 | +| loss | -0.0322 | +| n_updates | 56024 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000166 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1421 | +| iterations | 10053 | +| time_elapsed | 14481 | +| total_timesteps | 20588544 | +| train/ | | +| approx_kl | 0.011384824 | +| clip_fraction | 0.319 | +| clip_range | 0.0699 | +| entropy_loss | -6.54 | +| explained_variance | 0.463 | +| learning_rate | 4.51e-05 | +| loss | -0.0311 | +| n_updates | 56028 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000124 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1421 | +| iterations | 10054 | +| time_elapsed | 14482 | +| total_timesteps | 20590592 | +| train/ | | +| approx_kl | 0.011275087 | +| clip_fraction | 0.315 | +| clip_range | 0.0699 | +| entropy_loss | -6.34 | +| explained_variance | 0.281 | +| learning_rate | 4.51e-05 | +| loss | -0.0226 | +| n_updates | 56032 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000338 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1421 | +| iterations | 10055 | +| time_elapsed | 14484 | +| total_timesteps | 20592640 | +| train/ | | +| approx_kl | 0.012110761 | +| clip_fraction | 0.362 | +| clip_range | 0.0699 | +| entropy_loss | -6.5 | +| explained_variance | 0.61 | +| learning_rate | 4.51e-05 | +| loss | -0.0349 | +| n_updates | 56036 | +| policy_gradient_loss | -0.0211 | +| value_loss | 9.55e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1421 | +| iterations | 10056 | +| time_elapsed | 14485 | +| total_timesteps | 20594688 | +| train/ | | +| approx_kl | 0.011807888 | +| clip_fraction | 0.343 | +| clip_range | 0.0699 | +| entropy_loss | -7 | +| explained_variance | -0.204 | +| learning_rate | 4.51e-05 | +| loss | -0.0338 | +| n_updates | 56040 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000103 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1421 | +| iterations | 10057 | +| time_elapsed | 14486 | +| total_timesteps | 20596736 | +| train/ | | +| approx_kl | 0.0108483005 | +| clip_fraction | 0.293 | +| clip_range | 0.0699 | +| entropy_loss | -6.92 | +| explained_variance | 0.195 | +| learning_rate | 4.51e-05 | +| loss | -0.0248 | +| n_updates | 56044 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000277 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1421 | +| iterations | 10058 | +| time_elapsed | 14488 | +| total_timesteps | 20598784 | +| train/ | | +| approx_kl | 0.011503994 | +| clip_fraction | 0.321 | +| clip_range | 0.0699 | +| entropy_loss | -6.53 | +| explained_variance | 0.406 | +| learning_rate | 4.51e-05 | +| loss | -0.0312 | +| n_updates | 56048 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000236 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1421 | +| iterations | 10059 | +| time_elapsed | 14490 | +| total_timesteps | 20600832 | +| train/ | | +| approx_kl | 0.012942925 | +| clip_fraction | 0.353 | +| clip_range | 0.0699 | +| entropy_loss | -6.17 | +| explained_variance | 0.611 | +| learning_rate | 4.51e-05 | +| loss | -0.0369 | +| n_updates | 56052 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000141 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1421 | +| iterations | 10060 | +| time_elapsed | 14491 | +| total_timesteps | 20602880 | +| train/ | | +| approx_kl | 0.015662298 | +| clip_fraction | 0.339 | +| clip_range | 0.0698 | +| entropy_loss | -6.7 | +| explained_variance | 0.229 | +| learning_rate | 4.51e-05 | +| loss | -0.0292 | +| n_updates | 56056 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000235 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1421 | +| iterations | 10061 | +| time_elapsed | 14492 | +| total_timesteps | 20604928 | +| train/ | | +| approx_kl | 0.010133228 | +| clip_fraction | 0.311 | +| clip_range | 0.0698 | +| entropy_loss | -7.02 | +| explained_variance | -0.0865 | +| learning_rate | 4.51e-05 | +| loss | -0.0352 | +| n_updates | 56060 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1421 | +| iterations | 10062 | +| time_elapsed | 14494 | +| total_timesteps | 20606976 | +| train/ | | +| approx_kl | 0.015404021 | +| clip_fraction | 0.329 | +| clip_range | 0.0698 | +| entropy_loss | -6.86 | +| explained_variance | 0.381 | +| learning_rate | 4.51e-05 | +| loss | -0.0283 | +| n_updates | 56064 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000148 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1421 | +| iterations | 10063 | +| time_elapsed | 14495 | +| total_timesteps | 20609024 | +| train/ | | +| approx_kl | 0.013085617 | +| clip_fraction | 0.361 | +| clip_range | 0.0698 | +| entropy_loss | -6.38 | +| explained_variance | 0.719 | +| learning_rate | 4.51e-05 | +| loss | -0.0269 | +| n_updates | 56068 | +| policy_gradient_loss | -0.0211 | +| value_loss | 6.42e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1421 | +| iterations | 10064 | +| time_elapsed | 14497 | +| total_timesteps | 20611072 | +| train/ | | +| approx_kl | 0.012997098 | +| clip_fraction | 0.35 | +| clip_range | 0.0698 | +| entropy_loss | -5.71 | +| explained_variance | 0.789 | +| learning_rate | 4.51e-05 | +| loss | -0.0373 | +| n_updates | 56072 | +| policy_gradient_loss | -0.0207 | +| value_loss | 8.09e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1421 | +| iterations | 10065 | +| time_elapsed | 14498 | +| total_timesteps | 20613120 | +| train/ | | +| approx_kl | 0.0127059305 | +| clip_fraction | 0.342 | +| clip_range | 0.0698 | +| entropy_loss | -6.93 | +| explained_variance | -0.125 | +| learning_rate | 4.51e-05 | +| loss | -0.029 | +| n_updates | 56076 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000157 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1421 | +| iterations | 10066 | +| time_elapsed | 14500 | +| total_timesteps | 20615168 | +| train/ | | +| approx_kl | 0.013378775 | +| clip_fraction | 0.312 | +| clip_range | 0.0698 | +| entropy_loss | -6.11 | +| explained_variance | 0.646 | +| learning_rate | 4.51e-05 | +| loss | -0.0248 | +| n_updates | 56080 | +| policy_gradient_loss | -0.0145 | +| value_loss | 0.000183 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1421 | +| iterations | 10067 | +| time_elapsed | 14501 | +| total_timesteps | 20617216 | +| train/ | | +| approx_kl | 0.011473779 | +| clip_fraction | 0.316 | +| clip_range | 0.0698 | +| entropy_loss | -5.88 | +| explained_variance | 0.486 | +| learning_rate | 4.51e-05 | +| loss | -0.0264 | +| n_updates | 56084 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000162 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1421 | +| iterations | 10068 | +| time_elapsed | 14503 | +| total_timesteps | 20619264 | +| train/ | | +| approx_kl | 0.013413388 | +| clip_fraction | 0.341 | +| clip_range | 0.0698 | +| entropy_loss | -6.73 | +| explained_variance | 0.0697 | +| learning_rate | 4.51e-05 | +| loss | -0.0263 | +| n_updates | 56088 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000192 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1421 | +| iterations | 10069 | +| time_elapsed | 14504 | +| total_timesteps | 20621312 | +| train/ | | +| approx_kl | 0.013600474 | +| clip_fraction | 0.362 | +| clip_range | 0.0698 | +| entropy_loss | -6.81 | +| explained_variance | 0.304 | +| learning_rate | 4.51e-05 | +| loss | -0.033 | +| n_updates | 56092 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000139 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1421 | +| iterations | 10070 | +| time_elapsed | 14506 | +| total_timesteps | 20623360 | +| train/ | | +| approx_kl | 0.011953438 | +| clip_fraction | 0.349 | +| clip_range | 0.0698 | +| entropy_loss | -6.89 | +| explained_variance | 0.382 | +| learning_rate | 4.51e-05 | +| loss | -0.0314 | +| n_updates | 56096 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000132 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1421 | +| iterations | 10071 | +| time_elapsed | 14507 | +| total_timesteps | 20625408 | +| train/ | | +| approx_kl | 0.013938458 | +| clip_fraction | 0.34 | +| clip_range | 0.0698 | +| entropy_loss | -6.88 | +| explained_variance | -0.252 | +| learning_rate | 4.51e-05 | +| loss | -0.0336 | +| n_updates | 56100 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000104 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1421 | +| iterations | 10072 | +| time_elapsed | 14508 | +| total_timesteps | 20627456 | +| train/ | | +| approx_kl | 0.012909794 | +| clip_fraction | 0.339 | +| clip_range | 0.0698 | +| entropy_loss | -6.81 | +| explained_variance | 0.444 | +| learning_rate | 4.51e-05 | +| loss | -0.0267 | +| n_updates | 56104 | +| policy_gradient_loss | -0.0195 | +| value_loss | 8.69e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1421 | +| iterations | 10073 | +| time_elapsed | 14510 | +| total_timesteps | 20629504 | +| train/ | | +| approx_kl | 0.013415001 | +| clip_fraction | 0.333 | +| clip_range | 0.0698 | +| entropy_loss | -6.57 | +| explained_variance | 0.169 | +| learning_rate | 4.51e-05 | +| loss | -0.0306 | +| n_updates | 56108 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000137 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1421 | +| iterations | 10074 | +| time_elapsed | 14511 | +| total_timesteps | 20631552 | +| train/ | | +| approx_kl | 0.011886043 | +| clip_fraction | 0.308 | +| clip_range | 0.0698 | +| entropy_loss | -6.24 | +| explained_variance | 0.458 | +| learning_rate | 4.51e-05 | +| loss | -0.0278 | +| n_updates | 56112 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000248 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1421 | +| iterations | 10075 | +| time_elapsed | 14513 | +| total_timesteps | 20633600 | +| train/ | | +| approx_kl | 0.015706593 | +| clip_fraction | 0.361 | +| clip_range | 0.0698 | +| entropy_loss | -5.88 | +| explained_variance | 0.705 | +| learning_rate | 4.51e-05 | +| loss | -0.0321 | +| n_updates | 56116 | +| policy_gradient_loss | -0.0201 | +| value_loss | 8.88e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1421 | +| iterations | 10076 | +| time_elapsed | 14514 | +| total_timesteps | 20635648 | +| train/ | | +| approx_kl | 0.01105053 | +| clip_fraction | 0.341 | +| clip_range | 0.0698 | +| entropy_loss | -6.17 | +| explained_variance | 0.627 | +| learning_rate | 4.51e-05 | +| loss | -0.0332 | +| n_updates | 56120 | +| policy_gradient_loss | -0.0193 | +| value_loss | 8.03e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1421 | +| iterations | 10077 | +| time_elapsed | 14516 | +| total_timesteps | 20637696 | +| train/ | | +| approx_kl | 0.013656928 | +| clip_fraction | 0.356 | +| clip_range | 0.0698 | +| entropy_loss | -6.49 | +| explained_variance | 0.589 | +| learning_rate | 4.51e-05 | +| loss | -0.0312 | +| n_updates | 56124 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000102 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1421 | +| iterations | 10078 | +| time_elapsed | 14517 | +| total_timesteps | 20639744 | +| train/ | | +| approx_kl | 0.013874598 | +| clip_fraction | 0.334 | +| clip_range | 0.0698 | +| entropy_loss | -6.55 | +| explained_variance | 0.46 | +| learning_rate | 4.51e-05 | +| loss | -0.0291 | +| n_updates | 56128 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000174 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1421 | +| iterations | 10079 | +| time_elapsed | 14519 | +| total_timesteps | 20641792 | +| train/ | | +| approx_kl | 0.014374401 | +| clip_fraction | 0.361 | +| clip_range | 0.0698 | +| entropy_loss | -6.66 | +| explained_variance | 0.273 | +| learning_rate | 4.51e-05 | +| loss | -0.0318 | +| n_updates | 56132 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000148 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1421 | +| iterations | 10080 | +| time_elapsed | 14520 | +| total_timesteps | 20643840 | +| train/ | | +| approx_kl | 0.015062323 | +| clip_fraction | 0.348 | +| clip_range | 0.0698 | +| entropy_loss | -6.63 | +| explained_variance | 0.45 | +| learning_rate | 4.51e-05 | +| loss | -0.0294 | +| n_updates | 56136 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000177 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1421 | +| iterations | 10081 | +| time_elapsed | 14522 | +| total_timesteps | 20645888 | +| train/ | | +| approx_kl | 0.012379708 | +| clip_fraction | 0.341 | +| clip_range | 0.0698 | +| entropy_loss | -6.69 | +| explained_variance | 0.271 | +| learning_rate | 4.51e-05 | +| loss | -0.0221 | +| n_updates | 56140 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000184 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1421 | +| iterations | 10082 | +| time_elapsed | 14523 | +| total_timesteps | 20647936 | +| train/ | | +| approx_kl | 0.015929826 | +| clip_fraction | 0.339 | +| clip_range | 0.0698 | +| entropy_loss | -6.63 | +| explained_variance | 0.261 | +| learning_rate | 4.51e-05 | +| loss | -0.0304 | +| n_updates | 56144 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000176 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1421 | +| iterations | 10083 | +| time_elapsed | 14524 | +| total_timesteps | 20649984 | +| train/ | | +| approx_kl | 0.015376972 | +| clip_fraction | 0.317 | +| clip_range | 0.0698 | +| entropy_loss | -6.01 | +| explained_variance | 0.595 | +| learning_rate | 4.51e-05 | +| loss | -0.0301 | +| n_updates | 56148 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000187 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1421 | +| iterations | 10084 | +| time_elapsed | 14526 | +| total_timesteps | 20652032 | +| train/ | | +| approx_kl | 0.0143982675 | +| clip_fraction | 0.362 | +| clip_range | 0.0698 | +| entropy_loss | -6.21 | +| explained_variance | 0.206 | +| learning_rate | 4.51e-05 | +| loss | -0.0347 | +| n_updates | 56152 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000166 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1421 | +| iterations | 10085 | +| time_elapsed | 14527 | +| total_timesteps | 20654080 | +| train/ | | +| approx_kl | 0.015216233 | +| clip_fraction | 0.352 | +| clip_range | 0.0698 | +| entropy_loss | -6.65 | +| explained_variance | 0.207 | +| learning_rate | 4.51e-05 | +| loss | -0.0325 | +| n_updates | 56156 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000195 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1421 | +| iterations | 10086 | +| time_elapsed | 14529 | +| total_timesteps | 20656128 | +| train/ | | +| approx_kl | 0.014352333 | +| clip_fraction | 0.35 | +| clip_range | 0.0698 | +| entropy_loss | -6.52 | +| explained_variance | 0.266 | +| learning_rate | 4.51e-05 | +| loss | -0.0306 | +| n_updates | 56160 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000159 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1421 | +| iterations | 10087 | +| time_elapsed | 14530 | +| total_timesteps | 20658176 | +| train/ | | +| approx_kl | 0.012716968 | +| clip_fraction | 0.33 | +| clip_range | 0.0698 | +| entropy_loss | -6.24 | +| explained_variance | 0.464 | +| learning_rate | 4.51e-05 | +| loss | -0.0331 | +| n_updates | 56164 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000165 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1421 | +| iterations | 10088 | +| time_elapsed | 14532 | +| total_timesteps | 20660224 | +| train/ | | +| approx_kl | 0.01363717 | +| clip_fraction | 0.356 | +| clip_range | 0.0698 | +| entropy_loss | -6.07 | +| explained_variance | 0.658 | +| learning_rate | 4.51e-05 | +| loss | -0.0316 | +| n_updates | 56168 | +| policy_gradient_loss | -0.0211 | +| value_loss | 7.19e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1421 | +| iterations | 10089 | +| time_elapsed | 14533 | +| total_timesteps | 20662272 | +| train/ | | +| approx_kl | 0.012593187 | +| clip_fraction | 0.358 | +| clip_range | 0.0698 | +| entropy_loss | -6.61 | +| explained_variance | 0.235 | +| learning_rate | 4.51e-05 | +| loss | -0.0318 | +| n_updates | 56172 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000147 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1421 | +| iterations | 10090 | +| time_elapsed | 14535 | +| total_timesteps | 20664320 | +| train/ | | +| approx_kl | 0.01192001 | +| clip_fraction | 0.352 | +| clip_range | 0.0698 | +| entropy_loss | -6.99 | +| explained_variance | 0.0996 | +| learning_rate | 4.51e-05 | +| loss | -0.0286 | +| n_updates | 56176 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000113 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1421 | +| iterations | 10091 | +| time_elapsed | 14536 | +| total_timesteps | 20666368 | +| train/ | | +| approx_kl | 0.010901926 | +| clip_fraction | 0.297 | +| clip_range | 0.0698 | +| entropy_loss | -6.78 | +| explained_variance | 0.421 | +| learning_rate | 4.51e-05 | +| loss | -0.0294 | +| n_updates | 56180 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000168 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1421 | +| iterations | 10092 | +| time_elapsed | 14537 | +| total_timesteps | 20668416 | +| train/ | | +| approx_kl | 0.010751142 | +| clip_fraction | 0.313 | +| clip_range | 0.0698 | +| entropy_loss | -6.4 | +| explained_variance | 0.549 | +| learning_rate | 4.51e-05 | +| loss | -0.029 | +| n_updates | 56184 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000229 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1421 | +| iterations | 10093 | +| time_elapsed | 14539 | +| total_timesteps | 20670464 | +| train/ | | +| approx_kl | 0.016697943 | +| clip_fraction | 0.329 | +| clip_range | 0.0698 | +| entropy_loss | -6.57 | +| explained_variance | 0.166 | +| learning_rate | 4.51e-05 | +| loss | -0.0276 | +| n_updates | 56188 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1421 | +| iterations | 10094 | +| time_elapsed | 14540 | +| total_timesteps | 20672512 | +| train/ | | +| approx_kl | 0.010171857 | +| clip_fraction | 0.318 | +| clip_range | 0.0698 | +| entropy_loss | -6.68 | +| explained_variance | 0.319 | +| learning_rate | 4.51e-05 | +| loss | -0.0317 | +| n_updates | 56192 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000199 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1421 | +| iterations | 10095 | +| time_elapsed | 14542 | +| total_timesteps | 20674560 | +| train/ | | +| approx_kl | 0.011804972 | +| clip_fraction | 0.35 | +| clip_range | 0.0698 | +| entropy_loss | -6.4 | +| explained_variance | 0.322 | +| learning_rate | 4.51e-05 | +| loss | -0.0294 | +| n_updates | 56196 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000242 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1421 | +| iterations | 10096 | +| time_elapsed | 14543 | +| total_timesteps | 20676608 | +| train/ | | +| approx_kl | 0.012931462 | +| clip_fraction | 0.326 | +| clip_range | 0.0698 | +| entropy_loss | -6.94 | +| explained_variance | 0.338 | +| learning_rate | 4.51e-05 | +| loss | -0.0298 | +| n_updates | 56200 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000145 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1421 | +| iterations | 10097 | +| time_elapsed | 14545 | +| total_timesteps | 20678656 | +| train/ | | +| approx_kl | 0.009940101 | +| clip_fraction | 0.315 | +| clip_range | 0.0698 | +| entropy_loss | -6.84 | +| explained_variance | 0.546 | +| learning_rate | 4.51e-05 | +| loss | -0.0281 | +| n_updates | 56204 | +| policy_gradient_loss | -0.0193 | +| value_loss | 9.76e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1421 | +| iterations | 10098 | +| time_elapsed | 14546 | +| total_timesteps | 20680704 | +| train/ | | +| approx_kl | 0.011605876 | +| clip_fraction | 0.302 | +| clip_range | 0.0698 | +| entropy_loss | -5.64 | +| explained_variance | 0.774 | +| learning_rate | 4.51e-05 | +| loss | -0.0249 | +| n_updates | 56208 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.0001 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1421 | +| iterations | 10099 | +| time_elapsed | 14547 | +| total_timesteps | 20682752 | +| train/ | | +| approx_kl | 0.013233038 | +| clip_fraction | 0.332 | +| clip_range | 0.0698 | +| entropy_loss | -6.63 | +| explained_variance | 0.489 | +| learning_rate | 4.51e-05 | +| loss | -0.0349 | +| n_updates | 56212 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000126 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1421 | +| iterations | 10100 | +| time_elapsed | 14549 | +| total_timesteps | 20684800 | +| train/ | | +| approx_kl | 0.011633361 | +| clip_fraction | 0.309 | +| clip_range | 0.0698 | +| entropy_loss | -6.24 | +| explained_variance | 0.238 | +| learning_rate | 4.51e-05 | +| loss | -0.0284 | +| n_updates | 56216 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000602 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1421 | +| iterations | 10101 | +| time_elapsed | 14550 | +| total_timesteps | 20686848 | +| train/ | | +| approx_kl | 0.014523511 | +| clip_fraction | 0.394 | +| clip_range | 0.0698 | +| entropy_loss | -6.64 | +| explained_variance | -0.0471 | +| learning_rate | 4.51e-05 | +| loss | -0.0414 | +| n_updates | 56220 | +| policy_gradient_loss | -0.0263 | +| value_loss | 9.82e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1421 | +| iterations | 10102 | +| time_elapsed | 14552 | +| total_timesteps | 20688896 | +| train/ | | +| approx_kl | 0.011578914 | +| clip_fraction | 0.317 | +| clip_range | 0.0698 | +| entropy_loss | -7.22 | +| explained_variance | -0.24 | +| learning_rate | 4.51e-05 | +| loss | -0.032 | +| n_updates | 56224 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000146 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1421 | +| iterations | 10103 | +| time_elapsed | 14553 | +| total_timesteps | 20690944 | +| train/ | | +| approx_kl | 0.008696345 | +| clip_fraction | 0.328 | +| clip_range | 0.0698 | +| entropy_loss | -7.02 | +| explained_variance | 0.0816 | +| learning_rate | 4.51e-05 | +| loss | -0.0252 | +| n_updates | 56228 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000211 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1421 | +| iterations | 10104 | +| time_elapsed | 14555 | +| total_timesteps | 20692992 | +| train/ | | +| approx_kl | 0.013736121 | +| clip_fraction | 0.318 | +| clip_range | 0.0698 | +| entropy_loss | -6.64 | +| explained_variance | 0.413 | +| learning_rate | 4.51e-05 | +| loss | -0.0297 | +| n_updates | 56232 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000169 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1421 | +| iterations | 10105 | +| time_elapsed | 14556 | +| total_timesteps | 20695040 | +| train/ | | +| approx_kl | 0.013032123 | +| clip_fraction | 0.34 | +| clip_range | 0.0698 | +| entropy_loss | -6.67 | +| explained_variance | 0.14 | +| learning_rate | 4.51e-05 | +| loss | -0.0271 | +| n_updates | 56236 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000265 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1421 | +| iterations | 10106 | +| time_elapsed | 14558 | +| total_timesteps | 20697088 | +| train/ | | +| approx_kl | 0.009636503 | +| clip_fraction | 0.313 | +| clip_range | 0.0698 | +| entropy_loss | -6 | +| explained_variance | 0.424 | +| learning_rate | 4.51e-05 | +| loss | -0.0268 | +| n_updates | 56240 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000437 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1421 | +| iterations | 10107 | +| time_elapsed | 14559 | +| total_timesteps | 20699136 | +| train/ | | +| approx_kl | 0.010903116 | +| clip_fraction | 0.354 | +| clip_range | 0.0698 | +| entropy_loss | -6.31 | +| explained_variance | 0.173 | +| learning_rate | 4.51e-05 | +| loss | -0.0326 | +| n_updates | 56244 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000141 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1421 | +| iterations | 10108 | +| time_elapsed | 14561 | +| total_timesteps | 20701184 | +| train/ | | +| approx_kl | 0.012904333 | +| clip_fraction | 0.316 | +| clip_range | 0.0698 | +| entropy_loss | -6.55 | +| explained_variance | 0.366 | +| learning_rate | 4.51e-05 | +| loss | -0.0297 | +| n_updates | 56248 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000255 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1421 | +| iterations | 10109 | +| time_elapsed | 14562 | +| total_timesteps | 20703232 | +| train/ | | +| approx_kl | 0.010605171 | +| clip_fraction | 0.306 | +| clip_range | 0.0698 | +| entropy_loss | -6.19 | +| explained_variance | 0.224 | +| learning_rate | 4.51e-05 | +| loss | -0.029 | +| n_updates | 56252 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000438 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1421 | +| iterations | 10110 | +| time_elapsed | 14564 | +| total_timesteps | 20705280 | +| train/ | | +| approx_kl | 0.01474664 | +| clip_fraction | 0.37 | +| clip_range | 0.0698 | +| entropy_loss | -6.81 | +| explained_variance | -0.197 | +| learning_rate | 4.51e-05 | +| loss | -0.0372 | +| n_updates | 56256 | +| policy_gradient_loss | -0.0238 | +| value_loss | 0.000147 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1421 | +| iterations | 10111 | +| time_elapsed | 14565 | +| total_timesteps | 20707328 | +| train/ | | +| approx_kl | 0.012827914 | +| clip_fraction | 0.347 | +| clip_range | 0.0698 | +| entropy_loss | -6.87 | +| explained_variance | 0.311 | +| learning_rate | 4.51e-05 | +| loss | -0.0314 | +| n_updates | 56260 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000187 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1421 | +| iterations | 10112 | +| time_elapsed | 14566 | +| total_timesteps | 20709376 | +| train/ | | +| approx_kl | 0.02431069 | +| clip_fraction | 0.296 | +| clip_range | 0.0698 | +| entropy_loss | -6.42 | +| explained_variance | 0.365 | +| learning_rate | 4.51e-05 | +| loss | -0.0276 | +| n_updates | 56264 | +| policy_gradient_loss | -0.0143 | +| value_loss | 0.00023 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1421 | +| iterations | 10113 | +| time_elapsed | 14568 | +| total_timesteps | 20711424 | +| train/ | | +| approx_kl | 0.013062196 | +| clip_fraction | 0.33 | +| clip_range | 0.0698 | +| entropy_loss | -6.66 | +| explained_variance | 0.153 | +| learning_rate | 4.51e-05 | +| loss | -0.0372 | +| n_updates | 56268 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000284 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1421 | +| iterations | 10114 | +| time_elapsed | 14569 | +| total_timesteps | 20713472 | +| train/ | | +| approx_kl | 0.013017954 | +| clip_fraction | 0.324 | +| clip_range | 0.0698 | +| entropy_loss | -6.22 | +| explained_variance | 0.46 | +| learning_rate | 4.51e-05 | +| loss | -0.0268 | +| n_updates | 56272 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.00022 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1421 | +| iterations | 10115 | +| time_elapsed | 14571 | +| total_timesteps | 20715520 | +| train/ | | +| approx_kl | 0.013487609 | +| clip_fraction | 0.34 | +| clip_range | 0.0698 | +| entropy_loss | -6.27 | +| explained_variance | 0.431 | +| learning_rate | 4.51e-05 | +| loss | -0.0298 | +| n_updates | 56276 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000161 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1421 | +| iterations | 10116 | +| time_elapsed | 14572 | +| total_timesteps | 20717568 | +| train/ | | +| approx_kl | 0.01412523 | +| clip_fraction | 0.36 | +| clip_range | 0.0698 | +| entropy_loss | -6.93 | +| explained_variance | -0.289 | +| learning_rate | 4.51e-05 | +| loss | -0.0364 | +| n_updates | 56280 | +| policy_gradient_loss | -0.0209 | +| value_loss | 9.57e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1421 | +| iterations | 10117 | +| time_elapsed | 14574 | +| total_timesteps | 20719616 | +| train/ | | +| approx_kl | 0.013433066 | +| clip_fraction | 0.341 | +| clip_range | 0.0698 | +| entropy_loss | -6.91 | +| explained_variance | -0.0157 | +| learning_rate | 4.51e-05 | +| loss | -0.0342 | +| n_updates | 56284 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000234 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1421 | +| iterations | 10118 | +| time_elapsed | 14575 | +| total_timesteps | 20721664 | +| train/ | | +| approx_kl | 0.01661876 | +| clip_fraction | 0.337 | +| clip_range | 0.0698 | +| entropy_loss | -6.27 | +| explained_variance | 0.508 | +| learning_rate | 4.51e-05 | +| loss | -0.0302 | +| n_updates | 56288 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000242 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1421 | +| iterations | 10119 | +| time_elapsed | 14577 | +| total_timesteps | 20723712 | +| train/ | | +| approx_kl | 0.017047789 | +| clip_fraction | 0.386 | +| clip_range | 0.0698 | +| entropy_loss | -6.67 | +| explained_variance | -0.254 | +| learning_rate | 4.51e-05 | +| loss | -0.0369 | +| n_updates | 56292 | +| policy_gradient_loss | -0.0233 | +| value_loss | 0.000129 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1421 | +| iterations | 10120 | +| time_elapsed | 14578 | +| total_timesteps | 20725760 | +| train/ | | +| approx_kl | 0.011719318 | +| clip_fraction | 0.357 | +| clip_range | 0.0698 | +| entropy_loss | -6.62 | +| explained_variance | 0.0824 | +| learning_rate | 4.51e-05 | +| loss | -0.0352 | +| n_updates | 56296 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000146 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1421 | +| iterations | 10121 | +| time_elapsed | 14580 | +| total_timesteps | 20727808 | +| train/ | | +| approx_kl | 0.012622567 | +| clip_fraction | 0.314 | +| clip_range | 0.0698 | +| entropy_loss | -6.49 | +| explained_variance | 0.484 | +| learning_rate | 4.51e-05 | +| loss | -0.0226 | +| n_updates | 56300 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000162 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1421 | +| iterations | 10122 | +| time_elapsed | 14581 | +| total_timesteps | 20729856 | +| train/ | | +| approx_kl | 0.013207059 | +| clip_fraction | 0.313 | +| clip_range | 0.0698 | +| entropy_loss | -6.15 | +| explained_variance | 0.467 | +| learning_rate | 4.51e-05 | +| loss | -0.0307 | +| n_updates | 56304 | +| policy_gradient_loss | -0.0144 | +| value_loss | 0.000337 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1421 | +| iterations | 10123 | +| time_elapsed | 14583 | +| total_timesteps | 20731904 | +| train/ | | +| approx_kl | 0.014666359 | +| clip_fraction | 0.351 | +| clip_range | 0.0698 | +| entropy_loss | -6.56 | +| explained_variance | 0.295 | +| learning_rate | 4.51e-05 | +| loss | -0.0336 | +| n_updates | 56308 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000148 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1421 | +| iterations | 10124 | +| time_elapsed | 14584 | +| total_timesteps | 20733952 | +| train/ | | +| approx_kl | 0.0123714525 | +| clip_fraction | 0.338 | +| clip_range | 0.0698 | +| entropy_loss | -6.54 | +| explained_variance | 0.438 | +| learning_rate | 4.51e-05 | +| loss | -0.0235 | +| n_updates | 56312 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000221 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1421 | +| iterations | 10125 | +| time_elapsed | 14585 | +| total_timesteps | 20736000 | +| train/ | | +| approx_kl | 0.010719966 | +| clip_fraction | 0.316 | +| clip_range | 0.0698 | +| entropy_loss | -6.86 | +| explained_variance | 0.329 | +| learning_rate | 4.51e-05 | +| loss | -0.0221 | +| n_updates | 56316 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000278 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1421 | +| iterations | 10126 | +| time_elapsed | 14587 | +| total_timesteps | 20738048 | +| train/ | | +| approx_kl | 0.012002988 | +| clip_fraction | 0.331 | +| clip_range | 0.0698 | +| entropy_loss | -6.62 | +| explained_variance | 0.206 | +| learning_rate | 4.51e-05 | +| loss | -0.0281 | +| n_updates | 56320 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000367 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1421 | +| iterations | 10127 | +| time_elapsed | 14589 | +| total_timesteps | 20740096 | +| train/ | | +| approx_kl | 0.012482302 | +| clip_fraction | 0.348 | +| clip_range | 0.0698 | +| entropy_loss | -6.41 | +| explained_variance | 0.377 | +| learning_rate | 4.51e-05 | +| loss | -0.036 | +| n_updates | 56324 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000155 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1421 | +| iterations | 10128 | +| time_elapsed | 14590 | +| total_timesteps | 20742144 | +| train/ | | +| approx_kl | 0.015510553 | +| clip_fraction | 0.364 | +| clip_range | 0.0698 | +| entropy_loss | -6.25 | +| explained_variance | 0.561 | +| learning_rate | 4.51e-05 | +| loss | -0.0343 | +| n_updates | 56328 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000167 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1421 | +| iterations | 10129 | +| time_elapsed | 14591 | +| total_timesteps | 20744192 | +| train/ | | +| approx_kl | 0.013050756 | +| clip_fraction | 0.328 | +| clip_range | 0.0698 | +| entropy_loss | -6.57 | +| explained_variance | 0.344 | +| learning_rate | 4.51e-05 | +| loss | -0.0294 | +| n_updates | 56332 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000208 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1421 | +| iterations | 10130 | +| time_elapsed | 14593 | +| total_timesteps | 20746240 | +| train/ | | +| approx_kl | 0.009362724 | +| clip_fraction | 0.301 | +| clip_range | 0.0698 | +| entropy_loss | -6.95 | +| explained_variance | 0.126 | +| learning_rate | 4.51e-05 | +| loss | -0.023 | +| n_updates | 56336 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000313 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1421 | +| iterations | 10131 | +| time_elapsed | 14595 | +| total_timesteps | 20748288 | +| train/ | | +| approx_kl | 0.013578042 | +| clip_fraction | 0.339 | +| clip_range | 0.0698 | +| entropy_loss | -6.09 | +| explained_variance | 0.645 | +| learning_rate | 4.51e-05 | +| loss | -0.0257 | +| n_updates | 56340 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000188 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1421 | +| iterations | 10132 | +| time_elapsed | 14596 | +| total_timesteps | 20750336 | +| train/ | | +| approx_kl | 0.013326218 | +| clip_fraction | 0.367 | +| clip_range | 0.0698 | +| entropy_loss | -6.38 | +| explained_variance | 0.5 | +| learning_rate | 4.51e-05 | +| loss | -0.0356 | +| n_updates | 56344 | +| policy_gradient_loss | -0.0235 | +| value_loss | 7.22e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1421 | +| iterations | 10133 | +| time_elapsed | 14597 | +| total_timesteps | 20752384 | +| train/ | | +| approx_kl | 0.011703946 | +| clip_fraction | 0.315 | +| clip_range | 0.0698 | +| entropy_loss | -7.14 | +| explained_variance | -0.0918 | +| learning_rate | 4.51e-05 | +| loss | -0.0282 | +| n_updates | 56348 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000149 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1421 | +| iterations | 10134 | +| time_elapsed | 14599 | +| total_timesteps | 20754432 | +| train/ | | +| approx_kl | 0.011678817 | +| clip_fraction | 0.319 | +| clip_range | 0.0698 | +| entropy_loss | -6.87 | +| explained_variance | 0.596 | +| learning_rate | 4.51e-05 | +| loss | -0.027 | +| n_updates | 56352 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000152 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1421 | +| iterations | 10135 | +| time_elapsed | 14600 | +| total_timesteps | 20756480 | +| train/ | | +| approx_kl | 0.011344177 | +| clip_fraction | 0.316 | +| clip_range | 0.0698 | +| entropy_loss | -6.73 | +| explained_variance | 0.0486 | +| learning_rate | 4.51e-05 | +| loss | -0.0327 | +| n_updates | 56356 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000108 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1421 | +| iterations | 10136 | +| time_elapsed | 14602 | +| total_timesteps | 20758528 | +| train/ | | +| approx_kl | 0.014768204 | +| clip_fraction | 0.317 | +| clip_range | 0.0698 | +| entropy_loss | -6.19 | +| explained_variance | 0.646 | +| learning_rate | 4.51e-05 | +| loss | -0.0214 | +| n_updates | 56360 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000172 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1421 | +| iterations | 10137 | +| time_elapsed | 14603 | +| total_timesteps | 20760576 | +| train/ | | +| approx_kl | 0.015173659 | +| clip_fraction | 0.335 | +| clip_range | 0.0698 | +| entropy_loss | -6.47 | +| explained_variance | 0.551 | +| learning_rate | 4.51e-05 | +| loss | -0.0318 | +| n_updates | 56364 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.00011 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1421 | +| iterations | 10138 | +| time_elapsed | 14605 | +| total_timesteps | 20762624 | +| train/ | | +| approx_kl | 0.012244691 | +| clip_fraction | 0.331 | +| clip_range | 0.0698 | +| entropy_loss | -6.4 | +| explained_variance | 0.523 | +| learning_rate | 4.51e-05 | +| loss | -0.0358 | +| n_updates | 56368 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.00012 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1421 | +| iterations | 10139 | +| time_elapsed | 14606 | +| total_timesteps | 20764672 | +| train/ | | +| approx_kl | 0.012427641 | +| clip_fraction | 0.343 | +| clip_range | 0.0698 | +| entropy_loss | -6.81 | +| explained_variance | -0.119 | +| learning_rate | 4.51e-05 | +| loss | -0.035 | +| n_updates | 56372 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000123 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1421 | +| iterations | 10140 | +| time_elapsed | 14608 | +| total_timesteps | 20766720 | +| train/ | | +| approx_kl | 0.011797752 | +| clip_fraction | 0.333 | +| clip_range | 0.0698 | +| entropy_loss | -6.71 | +| explained_variance | 0.193 | +| learning_rate | 4.51e-05 | +| loss | -0.0222 | +| n_updates | 56376 | +| policy_gradient_loss | -0.0148 | +| value_loss | 0.000332 | +----------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1421 | +| iterations | 10141 | +| time_elapsed | 14609 | +| total_timesteps | 20768768 | +| train/ | | +| approx_kl | 0.015601 | +| clip_fraction | 0.354 | +| clip_range | 0.0698 | +| entropy_loss | -6.38 | +| explained_variance | 0.571 | +| learning_rate | 4.51e-05 | +| loss | -0.0319 | +| n_updates | 56380 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000127 | +-------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1421 | +| iterations | 10142 | +| time_elapsed | 14611 | +| total_timesteps | 20770816 | +| train/ | | +| approx_kl | 0.018908866 | +| clip_fraction | 0.337 | +| clip_range | 0.0698 | +| entropy_loss | -6.69 | +| explained_variance | 0.277 | +| learning_rate | 4.51e-05 | +| loss | -0.0387 | +| n_updates | 56384 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.00016 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1421 | +| iterations | 10143 | +| time_elapsed | 14612 | +| total_timesteps | 20772864 | +| train/ | | +| approx_kl | 0.012623891 | +| clip_fraction | 0.314 | +| clip_range | 0.0698 | +| entropy_loss | -6.07 | +| explained_variance | 0.518 | +| learning_rate | 4.51e-05 | +| loss | -0.0276 | +| n_updates | 56388 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000225 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1421 | +| iterations | 10144 | +| time_elapsed | 14613 | +| total_timesteps | 20774912 | +| train/ | | +| approx_kl | 0.012692984 | +| clip_fraction | 0.346 | +| clip_range | 0.0698 | +| entropy_loss | -6.34 | +| explained_variance | 0.573 | +| learning_rate | 4.51e-05 | +| loss | -0.031 | +| n_updates | 56392 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000167 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1421 | +| iterations | 10145 | +| time_elapsed | 14615 | +| total_timesteps | 20776960 | +| train/ | | +| approx_kl | 0.015578946 | +| clip_fraction | 0.341 | +| clip_range | 0.0698 | +| entropy_loss | -6.52 | +| explained_variance | 0.212 | +| learning_rate | 4.51e-05 | +| loss | -0.0367 | +| n_updates | 56396 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000178 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1421 | +| iterations | 10146 | +| time_elapsed | 14616 | +| total_timesteps | 20779008 | +| train/ | | +| approx_kl | 0.009925092 | +| clip_fraction | 0.328 | +| clip_range | 0.0698 | +| entropy_loss | -6.82 | +| explained_variance | 0.217 | +| learning_rate | 4.51e-05 | +| loss | -0.0281 | +| n_updates | 56400 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000391 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1421 | +| iterations | 10147 | +| time_elapsed | 14618 | +| total_timesteps | 20781056 | +| train/ | | +| approx_kl | 0.013732126 | +| clip_fraction | 0.349 | +| clip_range | 0.0698 | +| entropy_loss | -6.77 | +| explained_variance | 0.264 | +| learning_rate | 4.51e-05 | +| loss | -0.0377 | +| n_updates | 56404 | +| policy_gradient_loss | -0.0232 | +| value_loss | 0.000134 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1421 | +| iterations | 10148 | +| time_elapsed | 14619 | +| total_timesteps | 20783104 | +| train/ | | +| approx_kl | 0.0152814835 | +| clip_fraction | 0.347 | +| clip_range | 0.0698 | +| entropy_loss | -6.78 | +| explained_variance | 0.0343 | +| learning_rate | 4.51e-05 | +| loss | -0.034 | +| n_updates | 56408 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000149 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1421 | +| iterations | 10149 | +| time_elapsed | 14621 | +| total_timesteps | 20785152 | +| train/ | | +| approx_kl | 0.01537229 | +| clip_fraction | 0.371 | +| clip_range | 0.0698 | +| entropy_loss | -6.05 | +| explained_variance | 0.711 | +| learning_rate | 4.51e-05 | +| loss | -0.0353 | +| n_updates | 56412 | +| policy_gradient_loss | -0.0228 | +| value_loss | 6.47e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1421 | +| iterations | 10150 | +| time_elapsed | 14622 | +| total_timesteps | 20787200 | +| train/ | | +| approx_kl | 0.012711902 | +| clip_fraction | 0.329 | +| clip_range | 0.0698 | +| entropy_loss | -7.1 | +| explained_variance | -0.0423 | +| learning_rate | 4.51e-05 | +| loss | -0.0331 | +| n_updates | 56416 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.00013 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1421 | +| iterations | 10151 | +| time_elapsed | 14624 | +| total_timesteps | 20789248 | +| train/ | | +| approx_kl | 0.013357118 | +| clip_fraction | 0.362 | +| clip_range | 0.0698 | +| entropy_loss | -6.91 | +| explained_variance | 0.71 | +| learning_rate | 4.51e-05 | +| loss | -0.0308 | +| n_updates | 56420 | +| policy_gradient_loss | -0.0214 | +| value_loss | 5.91e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1421 | +| iterations | 10152 | +| time_elapsed | 14625 | +| total_timesteps | 20791296 | +| train/ | | +| approx_kl | 0.014816144 | +| clip_fraction | 0.359 | +| clip_range | 0.0698 | +| entropy_loss | -6.32 | +| explained_variance | 0.609 | +| learning_rate | 4.51e-05 | +| loss | -0.026 | +| n_updates | 56424 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000105 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1421 | +| iterations | 10153 | +| time_elapsed | 14627 | +| total_timesteps | 20793344 | +| train/ | | +| approx_kl | 0.011899859 | +| clip_fraction | 0.294 | +| clip_range | 0.0698 | +| entropy_loss | -6.15 | +| explained_variance | 0.425 | +| learning_rate | 4.51e-05 | +| loss | -0.0247 | +| n_updates | 56428 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000345 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1421 | +| iterations | 10154 | +| time_elapsed | 14628 | +| total_timesteps | 20795392 | +| train/ | | +| approx_kl | 0.013056377 | +| clip_fraction | 0.344 | +| clip_range | 0.0698 | +| entropy_loss | -6.08 | +| explained_variance | 0.526 | +| learning_rate | 4.51e-05 | +| loss | -0.0335 | +| n_updates | 56432 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1421 | +| iterations | 10155 | +| time_elapsed | 14630 | +| total_timesteps | 20797440 | +| train/ | | +| approx_kl | 0.008705357 | +| clip_fraction | 0.322 | +| clip_range | 0.0698 | +| entropy_loss | -6.85 | +| explained_variance | 0.391 | +| learning_rate | 4.51e-05 | +| loss | -0.0291 | +| n_updates | 56436 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000151 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1421 | +| iterations | 10156 | +| time_elapsed | 14631 | +| total_timesteps | 20799488 | +| train/ | | +| approx_kl | 0.012439259 | +| clip_fraction | 0.332 | +| clip_range | 0.0698 | +| entropy_loss | -6.6 | +| explained_variance | 0.167 | +| learning_rate | 4.51e-05 | +| loss | -0.0284 | +| n_updates | 56440 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.00018 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1421 | +| iterations | 10157 | +| time_elapsed | 14633 | +| total_timesteps | 20801536 | +| train/ | | +| approx_kl | 0.013260044 | +| clip_fraction | 0.345 | +| clip_range | 0.0698 | +| entropy_loss | -7.12 | +| explained_variance | 0.221 | +| learning_rate | 4.51e-05 | +| loss | -0.0274 | +| n_updates | 56444 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000133 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1421 | +| iterations | 10158 | +| time_elapsed | 14634 | +| total_timesteps | 20803584 | +| train/ | | +| approx_kl | 0.013683294 | +| clip_fraction | 0.298 | +| clip_range | 0.0698 | +| entropy_loss | -6.71 | +| explained_variance | 0.379 | +| learning_rate | 4.51e-05 | +| loss | -0.0264 | +| n_updates | 56448 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000289 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1421 | +| iterations | 10159 | +| time_elapsed | 14636 | +| total_timesteps | 20805632 | +| train/ | | +| approx_kl | 0.013782777 | +| clip_fraction | 0.352 | +| clip_range | 0.0698 | +| entropy_loss | -6.4 | +| explained_variance | 0.514 | +| learning_rate | 4.51e-05 | +| loss | -0.034 | +| n_updates | 56452 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000102 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1421 | +| iterations | 10160 | +| time_elapsed | 14637 | +| total_timesteps | 20807680 | +| train/ | | +| approx_kl | 0.012735885 | +| clip_fraction | 0.335 | +| clip_range | 0.0698 | +| entropy_loss | -6.34 | +| explained_variance | 0.578 | +| learning_rate | 4.51e-05 | +| loss | -0.0278 | +| n_updates | 56456 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000131 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1421 | +| iterations | 10161 | +| time_elapsed | 14639 | +| total_timesteps | 20809728 | +| train/ | | +| approx_kl | 0.0144823305 | +| clip_fraction | 0.354 | +| clip_range | 0.0698 | +| entropy_loss | -6.67 | +| explained_variance | -0.0874 | +| learning_rate | 4.51e-05 | +| loss | -0.0329 | +| n_updates | 56460 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000146 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1421 | +| iterations | 10162 | +| time_elapsed | 14640 | +| total_timesteps | 20811776 | +| train/ | | +| approx_kl | 0.013701398 | +| clip_fraction | 0.348 | +| clip_range | 0.0698 | +| entropy_loss | -6.27 | +| explained_variance | 0.466 | +| learning_rate | 4.51e-05 | +| loss | -0.0304 | +| n_updates | 56464 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000178 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1421 | +| iterations | 10163 | +| time_elapsed | 14642 | +| total_timesteps | 20813824 | +| train/ | | +| approx_kl | 0.01179963 | +| clip_fraction | 0.344 | +| clip_range | 0.0698 | +| entropy_loss | -6.39 | +| explained_variance | 0.255 | +| learning_rate | 4.51e-05 | +| loss | -0.0296 | +| n_updates | 56468 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000268 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1421 | +| iterations | 10164 | +| time_elapsed | 14643 | +| total_timesteps | 20815872 | +| train/ | | +| approx_kl | 0.014353898 | +| clip_fraction | 0.357 | +| clip_range | 0.0698 | +| entropy_loss | -6.63 | +| explained_variance | 0.307 | +| learning_rate | 4.51e-05 | +| loss | -0.0342 | +| n_updates | 56472 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000177 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1421 | +| iterations | 10165 | +| time_elapsed | 14644 | +| total_timesteps | 20817920 | +| train/ | | +| approx_kl | 0.011850601 | +| clip_fraction | 0.308 | +| clip_range | 0.0698 | +| entropy_loss | -6.39 | +| explained_variance | 0.427 | +| learning_rate | 4.51e-05 | +| loss | -0.0282 | +| n_updates | 56476 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000319 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1421 | +| iterations | 10166 | +| time_elapsed | 14646 | +| total_timesteps | 20819968 | +| train/ | | +| approx_kl | 0.013248425 | +| clip_fraction | 0.37 | +| clip_range | 0.0698 | +| entropy_loss | -6.11 | +| explained_variance | 0.659 | +| learning_rate | 4.51e-05 | +| loss | -0.0285 | +| n_updates | 56480 | +| policy_gradient_loss | -0.0209 | +| value_loss | 6.75e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1421 | +| iterations | 10167 | +| time_elapsed | 14647 | +| total_timesteps | 20822016 | +| train/ | | +| approx_kl | 0.014293319 | +| clip_fraction | 0.359 | +| clip_range | 0.0698 | +| entropy_loss | -6.37 | +| explained_variance | 0.413 | +| learning_rate | 4.51e-05 | +| loss | -0.0374 | +| n_updates | 56484 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000216 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1421 | +| iterations | 10168 | +| time_elapsed | 14649 | +| total_timesteps | 20824064 | +| train/ | | +| approx_kl | 0.014922247 | +| clip_fraction | 0.365 | +| clip_range | 0.0698 | +| entropy_loss | -6.64 | +| explained_variance | -0.195 | +| learning_rate | 4.51e-05 | +| loss | -0.0311 | +| n_updates | 56488 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000162 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1421 | +| iterations | 10169 | +| time_elapsed | 14650 | +| total_timesteps | 20826112 | +| train/ | | +| approx_kl | 0.012070023 | +| clip_fraction | 0.344 | +| clip_range | 0.0698 | +| entropy_loss | -7.11 | +| explained_variance | -0.0667 | +| learning_rate | 4.51e-05 | +| loss | -0.0304 | +| n_updates | 56492 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000202 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1421 | +| iterations | 10170 | +| time_elapsed | 14652 | +| total_timesteps | 20828160 | +| train/ | | +| approx_kl | 0.012331175 | +| clip_fraction | 0.348 | +| clip_range | 0.0698 | +| entropy_loss | -6.62 | +| explained_variance | 0.386 | +| learning_rate | 4.51e-05 | +| loss | -0.0324 | +| n_updates | 56496 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000188 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1421 | +| iterations | 10171 | +| time_elapsed | 14653 | +| total_timesteps | 20830208 | +| train/ | | +| approx_kl | 0.0120377755 | +| clip_fraction | 0.326 | +| clip_range | 0.0698 | +| entropy_loss | -6.38 | +| explained_variance | 0.161 | +| learning_rate | 4.51e-05 | +| loss | -0.0221 | +| n_updates | 56500 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000367 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1421 | +| iterations | 10172 | +| time_elapsed | 14655 | +| total_timesteps | 20832256 | +| train/ | | +| approx_kl | 0.012744785 | +| clip_fraction | 0.352 | +| clip_range | 0.0698 | +| entropy_loss | -6.61 | +| explained_variance | 0.331 | +| learning_rate | 4.51e-05 | +| loss | -0.0343 | +| n_updates | 56504 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000199 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1421 | +| iterations | 10173 | +| time_elapsed | 14656 | +| total_timesteps | 20834304 | +| train/ | | +| approx_kl | 0.015350441 | +| clip_fraction | 0.345 | +| clip_range | 0.0698 | +| entropy_loss | -6.15 | +| explained_variance | 0.354 | +| learning_rate | 4.51e-05 | +| loss | -0.0287 | +| n_updates | 56508 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000301 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1421 | +| iterations | 10174 | +| time_elapsed | 14658 | +| total_timesteps | 20836352 | +| train/ | | +| approx_kl | 0.013906463 | +| clip_fraction | 0.375 | +| clip_range | 0.0698 | +| entropy_loss | -6.79 | +| explained_variance | -0.0309 | +| learning_rate | 4.51e-05 | +| loss | -0.029 | +| n_updates | 56512 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000173 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1421 | +| iterations | 10175 | +| time_elapsed | 14659 | +| total_timesteps | 20838400 | +| train/ | | +| approx_kl | 0.012764579 | +| clip_fraction | 0.361 | +| clip_range | 0.0698 | +| entropy_loss | -6.82 | +| explained_variance | 0.177 | +| learning_rate | 4.51e-05 | +| loss | -0.0342 | +| n_updates | 56516 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000131 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1421 | +| iterations | 10176 | +| time_elapsed | 14661 | +| total_timesteps | 20840448 | +| train/ | | +| approx_kl | 0.012026824 | +| clip_fraction | 0.335 | +| clip_range | 0.0698 | +| entropy_loss | -6.8 | +| explained_variance | 0.327 | +| learning_rate | 4.51e-05 | +| loss | -0.0328 | +| n_updates | 56520 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.0001 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1421 | +| iterations | 10177 | +| time_elapsed | 14662 | +| total_timesteps | 20842496 | +| train/ | | +| approx_kl | 0.013465362 | +| clip_fraction | 0.358 | +| clip_range | 0.0698 | +| entropy_loss | -7.02 | +| explained_variance | 0.0178 | +| learning_rate | 4.51e-05 | +| loss | -0.0325 | +| n_updates | 56524 | +| policy_gradient_loss | -0.0218 | +| value_loss | 7.81e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1421 | +| iterations | 10178 | +| time_elapsed | 14664 | +| total_timesteps | 20844544 | +| train/ | | +| approx_kl | 0.0155094415 | +| clip_fraction | 0.326 | +| clip_range | 0.0698 | +| entropy_loss | -6.73 | +| explained_variance | 0.242 | +| learning_rate | 4.5e-05 | +| loss | -0.0285 | +| n_updates | 56528 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000155 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1421 | +| iterations | 10179 | +| time_elapsed | 14665 | +| total_timesteps | 20846592 | +| train/ | | +| approx_kl | 0.013862669 | +| clip_fraction | 0.348 | +| clip_range | 0.0698 | +| entropy_loss | -6.47 | +| explained_variance | 0.494 | +| learning_rate | 4.5e-05 | +| loss | -0.0403 | +| n_updates | 56532 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000121 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1421 | +| iterations | 10180 | +| time_elapsed | 14666 | +| total_timesteps | 20848640 | +| train/ | | +| approx_kl | 0.011088843 | +| clip_fraction | 0.337 | +| clip_range | 0.0698 | +| entropy_loss | -6.44 | +| explained_variance | 0.456 | +| learning_rate | 4.5e-05 | +| loss | -0.0314 | +| n_updates | 56536 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000161 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1421 | +| iterations | 10181 | +| time_elapsed | 14668 | +| total_timesteps | 20850688 | +| train/ | | +| approx_kl | 0.010356782 | +| clip_fraction | 0.306 | +| clip_range | 0.0698 | +| entropy_loss | -6.11 | +| explained_variance | 0.535 | +| learning_rate | 4.5e-05 | +| loss | -0.0308 | +| n_updates | 56540 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000198 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1421 | +| iterations | 10182 | +| time_elapsed | 14669 | +| total_timesteps | 20852736 | +| train/ | | +| approx_kl | 0.013301667 | +| clip_fraction | 0.378 | +| clip_range | 0.0698 | +| entropy_loss | -6.14 | +| explained_variance | 0.762 | +| learning_rate | 4.5e-05 | +| loss | -0.0396 | +| n_updates | 56544 | +| policy_gradient_loss | -0.0244 | +| value_loss | 4.48e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1421 | +| iterations | 10183 | +| time_elapsed | 14671 | +| total_timesteps | 20854784 | +| train/ | | +| approx_kl | 0.011609193 | +| clip_fraction | 0.336 | +| clip_range | 0.0698 | +| entropy_loss | -6.33 | +| explained_variance | 0.432 | +| learning_rate | 4.5e-05 | +| loss | -0.0333 | +| n_updates | 56548 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000287 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1421 | +| iterations | 10184 | +| time_elapsed | 14672 | +| total_timesteps | 20856832 | +| train/ | | +| approx_kl | 0.010306355 | +| clip_fraction | 0.324 | +| clip_range | 0.0698 | +| entropy_loss | -6.22 | +| explained_variance | 0.409 | +| learning_rate | 4.5e-05 | +| loss | -0.0322 | +| n_updates | 56552 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000189 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1421 | +| iterations | 10185 | +| time_elapsed | 14674 | +| total_timesteps | 20858880 | +| train/ | | +| approx_kl | 0.013186237 | +| clip_fraction | 0.387 | +| clip_range | 0.0698 | +| entropy_loss | -6.46 | +| explained_variance | 0.448 | +| learning_rate | 4.5e-05 | +| loss | -0.0362 | +| n_updates | 56556 | +| policy_gradient_loss | -0.0251 | +| value_loss | 9.28e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1421 | +| iterations | 10186 | +| time_elapsed | 14675 | +| total_timesteps | 20860928 | +| train/ | | +| approx_kl | 0.012171245 | +| clip_fraction | 0.345 | +| clip_range | 0.0698 | +| entropy_loss | -6.99 | +| explained_variance | -0.0207 | +| learning_rate | 4.5e-05 | +| loss | -0.0316 | +| n_updates | 56560 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000175 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1421 | +| iterations | 10187 | +| time_elapsed | 14677 | +| total_timesteps | 20862976 | +| train/ | | +| approx_kl | 0.013581663 | +| clip_fraction | 0.333 | +| clip_range | 0.0698 | +| entropy_loss | -6.48 | +| explained_variance | 0.432 | +| learning_rate | 4.5e-05 | +| loss | -0.0329 | +| n_updates | 56564 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000208 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1421 | +| iterations | 10188 | +| time_elapsed | 14678 | +| total_timesteps | 20865024 | +| train/ | | +| approx_kl | 0.016101526 | +| clip_fraction | 0.349 | +| clip_range | 0.0698 | +| entropy_loss | -6.59 | +| explained_variance | 0.393 | +| learning_rate | 4.5e-05 | +| loss | -0.031 | +| n_updates | 56568 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000226 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1421 | +| iterations | 10189 | +| time_elapsed | 14680 | +| total_timesteps | 20867072 | +| train/ | | +| approx_kl | 0.01193041 | +| clip_fraction | 0.33 | +| clip_range | 0.0698 | +| entropy_loss | -5.91 | +| explained_variance | 0.543 | +| learning_rate | 4.5e-05 | +| loss | -0.0285 | +| n_updates | 56572 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000214 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1421 | +| iterations | 10190 | +| time_elapsed | 14681 | +| total_timesteps | 20869120 | +| train/ | | +| approx_kl | 0.013887042 | +| clip_fraction | 0.348 | +| clip_range | 0.0698 | +| entropy_loss | -6.32 | +| explained_variance | 0.558 | +| learning_rate | 4.5e-05 | +| loss | -0.0306 | +| n_updates | 56576 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000136 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1421 | +| iterations | 10191 | +| time_elapsed | 14683 | +| total_timesteps | 20871168 | +| train/ | | +| approx_kl | 0.013279868 | +| clip_fraction | 0.339 | +| clip_range | 0.0698 | +| entropy_loss | -6.63 | +| explained_variance | 0.118 | +| learning_rate | 4.5e-05 | +| loss | -0.0329 | +| n_updates | 56580 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000234 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1421 | +| iterations | 10192 | +| time_elapsed | 14684 | +| total_timesteps | 20873216 | +| train/ | | +| approx_kl | 0.011241732 | +| clip_fraction | 0.342 | +| clip_range | 0.0698 | +| entropy_loss | -6.82 | +| explained_variance | -0.0663 | +| learning_rate | 4.5e-05 | +| loss | -0.0197 | +| n_updates | 56584 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000373 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1421 | +| iterations | 10193 | +| time_elapsed | 14685 | +| total_timesteps | 20875264 | +| train/ | | +| approx_kl | 0.014447121 | +| clip_fraction | 0.352 | +| clip_range | 0.0698 | +| entropy_loss | -6.04 | +| explained_variance | 0.306 | +| learning_rate | 4.5e-05 | +| loss | -0.0245 | +| n_updates | 56588 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000335 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1421 | +| iterations | 10194 | +| time_elapsed | 14687 | +| total_timesteps | 20877312 | +| train/ | | +| approx_kl | 0.0132340705 | +| clip_fraction | 0.311 | +| clip_range | 0.0698 | +| entropy_loss | -6.05 | +| explained_variance | 0.555 | +| learning_rate | 4.5e-05 | +| loss | -0.0292 | +| n_updates | 56592 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000197 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1421 | +| iterations | 10195 | +| time_elapsed | 14688 | +| total_timesteps | 20879360 | +| train/ | | +| approx_kl | 0.012898655 | +| clip_fraction | 0.355 | +| clip_range | 0.0698 | +| entropy_loss | -6.34 | +| explained_variance | 0.74 | +| learning_rate | 4.5e-05 | +| loss | -0.0354 | +| n_updates | 56596 | +| policy_gradient_loss | -0.024 | +| value_loss | 7.57e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1421 | +| iterations | 10196 | +| time_elapsed | 14690 | +| total_timesteps | 20881408 | +| train/ | | +| approx_kl | 0.015635898 | +| clip_fraction | 0.344 | +| clip_range | 0.0698 | +| entropy_loss | -6.85 | +| explained_variance | 0.308 | +| learning_rate | 4.5e-05 | +| loss | -0.0321 | +| n_updates | 56600 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000188 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1421 | +| iterations | 10197 | +| time_elapsed | 14691 | +| total_timesteps | 20883456 | +| train/ | | +| approx_kl | 0.014476072 | +| clip_fraction | 0.333 | +| clip_range | 0.0698 | +| entropy_loss | -7.05 | +| explained_variance | 0.0712 | +| learning_rate | 4.5e-05 | +| loss | -0.0314 | +| n_updates | 56604 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000101 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1421 | +| iterations | 10198 | +| time_elapsed | 14693 | +| total_timesteps | 20885504 | +| train/ | | +| approx_kl | 0.015967263 | +| clip_fraction | 0.333 | +| clip_range | 0.0698 | +| entropy_loss | -6.67 | +| explained_variance | 0.277 | +| learning_rate | 4.5e-05 | +| loss | -0.0288 | +| n_updates | 56608 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000285 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1421 | +| iterations | 10199 | +| time_elapsed | 14694 | +| total_timesteps | 20887552 | +| train/ | | +| approx_kl | 0.012641853 | +| clip_fraction | 0.332 | +| clip_range | 0.0698 | +| entropy_loss | -6.73 | +| explained_variance | 0.267 | +| learning_rate | 4.5e-05 | +| loss | -0.0286 | +| n_updates | 56612 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000228 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1421 | +| iterations | 10200 | +| time_elapsed | 14696 | +| total_timesteps | 20889600 | +| train/ | | +| approx_kl | 0.015497958 | +| clip_fraction | 0.296 | +| clip_range | 0.0698 | +| entropy_loss | -6.1 | +| explained_variance | 0.548 | +| learning_rate | 4.5e-05 | +| loss | -0.0209 | +| n_updates | 56616 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000234 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1421 | +| iterations | 10201 | +| time_elapsed | 14697 | +| total_timesteps | 20891648 | +| train/ | | +| approx_kl | 0.012673574 | +| clip_fraction | 0.366 | +| clip_range | 0.0698 | +| entropy_loss | -6.73 | +| explained_variance | 0.0424 | +| learning_rate | 4.5e-05 | +| loss | -0.0329 | +| n_updates | 56620 | +| policy_gradient_loss | -0.023 | +| value_loss | 0.000145 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1421 | +| iterations | 10202 | +| time_elapsed | 14699 | +| total_timesteps | 20893696 | +| train/ | | +| approx_kl | 0.016430529 | +| clip_fraction | 0.352 | +| clip_range | 0.0698 | +| entropy_loss | -6.93 | +| explained_variance | 0.15 | +| learning_rate | 4.5e-05 | +| loss | -0.0312 | +| n_updates | 56624 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000168 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1421 | +| iterations | 10203 | +| time_elapsed | 14700 | +| total_timesteps | 20895744 | +| train/ | | +| approx_kl | 0.014472819 | +| clip_fraction | 0.334 | +| clip_range | 0.0698 | +| entropy_loss | -6.4 | +| explained_variance | 0.452 | +| learning_rate | 4.5e-05 | +| loss | -0.0322 | +| n_updates | 56628 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000167 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1421 | +| iterations | 10204 | +| time_elapsed | 14701 | +| total_timesteps | 20897792 | +| train/ | | +| approx_kl | 0.012540037 | +| clip_fraction | 0.333 | +| clip_range | 0.0698 | +| entropy_loss | -6.1 | +| explained_variance | 0.545 | +| learning_rate | 4.5e-05 | +| loss | -0.0274 | +| n_updates | 56632 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000207 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1421 | +| iterations | 10205 | +| time_elapsed | 14703 | +| total_timesteps | 20899840 | +| train/ | | +| approx_kl | 0.010979727 | +| clip_fraction | 0.31 | +| clip_range | 0.0698 | +| entropy_loss | -6.16 | +| explained_variance | 0.572 | +| learning_rate | 4.5e-05 | +| loss | -0.0273 | +| n_updates | 56636 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.0002 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1421 | +| iterations | 10206 | +| time_elapsed | 14704 | +| total_timesteps | 20901888 | +| train/ | | +| approx_kl | 0.016417425 | +| clip_fraction | 0.354 | +| clip_range | 0.0698 | +| entropy_loss | -6.51 | +| explained_variance | 0.399 | +| learning_rate | 4.5e-05 | +| loss | -0.0358 | +| n_updates | 56640 | +| policy_gradient_loss | -0.0223 | +| value_loss | 6.33e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1421 | +| iterations | 10207 | +| time_elapsed | 14706 | +| total_timesteps | 20903936 | +| train/ | | +| approx_kl | 0.013309663 | +| clip_fraction | 0.365 | +| clip_range | 0.0698 | +| entropy_loss | -6.84 | +| explained_variance | 0.475 | +| learning_rate | 4.5e-05 | +| loss | -0.0411 | +| n_updates | 56644 | +| policy_gradient_loss | -0.0232 | +| value_loss | 6.23e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1421 | +| iterations | 10208 | +| time_elapsed | 14707 | +| total_timesteps | 20905984 | +| train/ | | +| approx_kl | 0.013523629 | +| clip_fraction | 0.324 | +| clip_range | 0.0698 | +| entropy_loss | -6.47 | +| explained_variance | 0.499 | +| learning_rate | 4.5e-05 | +| loss | -0.0274 | +| n_updates | 56648 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000134 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1421 | +| iterations | 10209 | +| time_elapsed | 14709 | +| total_timesteps | 20908032 | +| train/ | | +| approx_kl | 0.014250054 | +| clip_fraction | 0.338 | +| clip_range | 0.0698 | +| entropy_loss | -6.94 | +| explained_variance | -0.18 | +| learning_rate | 4.5e-05 | +| loss | -0.0252 | +| n_updates | 56652 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1421 | +| iterations | 10210 | +| time_elapsed | 14710 | +| total_timesteps | 20910080 | +| train/ | | +| approx_kl | 0.010857478 | +| clip_fraction | 0.328 | +| clip_range | 0.0698 | +| entropy_loss | -7.27 | +| explained_variance | -0.0948 | +| learning_rate | 4.5e-05 | +| loss | -0.0335 | +| n_updates | 56656 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000141 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1421 | +| iterations | 10211 | +| time_elapsed | 14712 | +| total_timesteps | 20912128 | +| train/ | | +| approx_kl | 0.011170961 | +| clip_fraction | 0.306 | +| clip_range | 0.0698 | +| entropy_loss | -6.16 | +| explained_variance | 0.516 | +| learning_rate | 4.5e-05 | +| loss | -0.0243 | +| n_updates | 56660 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000199 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.389 | +| time/ | | +| fps | 1421 | +| iterations | 10212 | +| time_elapsed | 14713 | +| total_timesteps | 20914176 | +| train/ | | +| approx_kl | 0.015156236 | +| clip_fraction | 0.33 | +| clip_range | 0.0698 | +| entropy_loss | -6.58 | +| explained_variance | 0.391 | +| learning_rate | 4.5e-05 | +| loss | -0.0275 | +| n_updates | 56664 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000221 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.389 | +| time/ | | +| fps | 1421 | +| iterations | 10213 | +| time_elapsed | 14715 | +| total_timesteps | 20916224 | +| train/ | | +| approx_kl | 0.01331312 | +| clip_fraction | 0.323 | +| clip_range | 0.0698 | +| entropy_loss | -6.04 | +| explained_variance | 0.363 | +| learning_rate | 4.5e-05 | +| loss | -0.0317 | +| n_updates | 56668 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000271 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.386 | +| time/ | | +| fps | 1421 | +| iterations | 10214 | +| time_elapsed | 14716 | +| total_timesteps | 20918272 | +| train/ | | +| approx_kl | 0.0139110945 | +| clip_fraction | 0.382 | +| clip_range | 0.0698 | +| entropy_loss | -6.21 | +| explained_variance | 0.609 | +| learning_rate | 4.5e-05 | +| loss | -0.0405 | +| n_updates | 56672 | +| policy_gradient_loss | -0.0251 | +| value_loss | 8.35e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1421 | +| iterations | 10215 | +| time_elapsed | 14718 | +| total_timesteps | 20920320 | +| train/ | | +| approx_kl | 0.016147265 | +| clip_fraction | 0.338 | +| clip_range | 0.0698 | +| entropy_loss | -6.37 | +| explained_variance | 0.373 | +| learning_rate | 4.5e-05 | +| loss | -0.0318 | +| n_updates | 56676 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000189 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.384 | +| time/ | | +| fps | 1421 | +| iterations | 10216 | +| time_elapsed | 14719 | +| total_timesteps | 20922368 | +| train/ | | +| approx_kl | 0.014694059 | +| clip_fraction | 0.353 | +| clip_range | 0.0698 | +| entropy_loss | -6.36 | +| explained_variance | 0.315 | +| learning_rate | 4.5e-05 | +| loss | -0.0331 | +| n_updates | 56680 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000189 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1421 | +| iterations | 10217 | +| time_elapsed | 14721 | +| total_timesteps | 20924416 | +| train/ | | +| approx_kl | 0.019190598 | +| clip_fraction | 0.331 | +| clip_range | 0.0698 | +| entropy_loss | -6.73 | +| explained_variance | 0.246 | +| learning_rate | 4.5e-05 | +| loss | -0.0276 | +| n_updates | 56684 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000167 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1421 | +| iterations | 10218 | +| time_elapsed | 14722 | +| total_timesteps | 20926464 | +| train/ | | +| approx_kl | 0.014947429 | +| clip_fraction | 0.35 | +| clip_range | 0.0698 | +| entropy_loss | -6.59 | +| explained_variance | 0.458 | +| learning_rate | 4.5e-05 | +| loss | -0.0266 | +| n_updates | 56688 | +| policy_gradient_loss | -0.0185 | +| value_loss | 8.25e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1421 | +| iterations | 10219 | +| time_elapsed | 14723 | +| total_timesteps | 20928512 | +| train/ | | +| approx_kl | 0.01291661 | +| clip_fraction | 0.337 | +| clip_range | 0.0698 | +| entropy_loss | -6.25 | +| explained_variance | 0.741 | +| learning_rate | 4.5e-05 | +| loss | -0.0313 | +| n_updates | 56692 | +| policy_gradient_loss | -0.0197 | +| value_loss | 7.79e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.385 | +| time/ | | +| fps | 1421 | +| iterations | 10220 | +| time_elapsed | 14725 | +| total_timesteps | 20930560 | +| train/ | | +| approx_kl | 0.012844452 | +| clip_fraction | 0.333 | +| clip_range | 0.0698 | +| entropy_loss | -6.54 | +| explained_variance | 0.367 | +| learning_rate | 4.5e-05 | +| loss | -0.0301 | +| n_updates | 56696 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.00014 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.385 | +| time/ | | +| fps | 1421 | +| iterations | 10221 | +| time_elapsed | 14726 | +| total_timesteps | 20932608 | +| train/ | | +| approx_kl | 0.01058343 | +| clip_fraction | 0.333 | +| clip_range | 0.0698 | +| entropy_loss | -6.88 | +| explained_variance | 0.127 | +| learning_rate | 4.5e-05 | +| loss | -0.0239 | +| n_updates | 56700 | +| policy_gradient_loss | -0.0143 | +| value_loss | 0.000293 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.385 | +| time/ | | +| fps | 1421 | +| iterations | 10222 | +| time_elapsed | 14728 | +| total_timesteps | 20934656 | +| train/ | | +| approx_kl | 0.013266496 | +| clip_fraction | 0.355 | +| clip_range | 0.0698 | +| entropy_loss | -6.54 | +| explained_variance | 0.0535 | +| learning_rate | 4.5e-05 | +| loss | -0.0287 | +| n_updates | 56704 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000319 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1421 | +| iterations | 10223 | +| time_elapsed | 14729 | +| total_timesteps | 20936704 | +| train/ | | +| approx_kl | 0.015389686 | +| clip_fraction | 0.359 | +| clip_range | 0.0698 | +| entropy_loss | -6.46 | +| explained_variance | 0.36 | +| learning_rate | 4.5e-05 | +| loss | -0.031 | +| n_updates | 56708 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000125 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1421 | +| iterations | 10224 | +| time_elapsed | 14731 | +| total_timesteps | 20938752 | +| train/ | | +| approx_kl | 0.013476265 | +| clip_fraction | 0.352 | +| clip_range | 0.0698 | +| entropy_loss | -6.59 | +| explained_variance | 0.543 | +| learning_rate | 4.5e-05 | +| loss | -0.0271 | +| n_updates | 56712 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000118 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1421 | +| iterations | 10225 | +| time_elapsed | 14732 | +| total_timesteps | 20940800 | +| train/ | | +| approx_kl | 0.011731587 | +| clip_fraction | 0.325 | +| clip_range | 0.0698 | +| entropy_loss | -6.48 | +| explained_variance | 0.336 | +| learning_rate | 4.5e-05 | +| loss | -0.0273 | +| n_updates | 56716 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000138 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1421 | +| iterations | 10226 | +| time_elapsed | 14734 | +| total_timesteps | 20942848 | +| train/ | | +| approx_kl | 0.01145655 | +| clip_fraction | 0.326 | +| clip_range | 0.0698 | +| entropy_loss | -6.74 | +| explained_variance | 0.223 | +| learning_rate | 4.5e-05 | +| loss | -0.0263 | +| n_updates | 56720 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.00027 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1421 | +| iterations | 10227 | +| time_elapsed | 14735 | +| total_timesteps | 20944896 | +| train/ | | +| approx_kl | 0.012565632 | +| clip_fraction | 0.361 | +| clip_range | 0.0698 | +| entropy_loss | -6.28 | +| explained_variance | 0.507 | +| learning_rate | 4.5e-05 | +| loss | -0.0344 | +| n_updates | 56724 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000116 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1421 | +| iterations | 10228 | +| time_elapsed | 14737 | +| total_timesteps | 20946944 | +| train/ | | +| approx_kl | 0.012736887 | +| clip_fraction | 0.334 | +| clip_range | 0.0698 | +| entropy_loss | -6.52 | +| explained_variance | 0.54 | +| learning_rate | 4.5e-05 | +| loss | -0.0321 | +| n_updates | 56728 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.00013 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1421 | +| iterations | 10229 | +| time_elapsed | 14738 | +| total_timesteps | 20948992 | +| train/ | | +| approx_kl | 0.013196786 | +| clip_fraction | 0.307 | +| clip_range | 0.0698 | +| entropy_loss | -6.35 | +| explained_variance | 0.347 | +| learning_rate | 4.5e-05 | +| loss | -0.0247 | +| n_updates | 56732 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000287 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1421 | +| iterations | 10230 | +| time_elapsed | 14739 | +| total_timesteps | 20951040 | +| train/ | | +| approx_kl | 0.013417325 | +| clip_fraction | 0.347 | +| clip_range | 0.0698 | +| entropy_loss | -6.53 | +| explained_variance | 0.307 | +| learning_rate | 4.5e-05 | +| loss | -0.034 | +| n_updates | 56736 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.00014 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1421 | +| iterations | 10231 | +| time_elapsed | 14741 | +| total_timesteps | 20953088 | +| train/ | | +| approx_kl | 0.014773888 | +| clip_fraction | 0.359 | +| clip_range | 0.0698 | +| entropy_loss | -6.22 | +| explained_variance | 0.688 | +| learning_rate | 4.5e-05 | +| loss | -0.0359 | +| n_updates | 56740 | +| policy_gradient_loss | -0.0221 | +| value_loss | 7.69e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1421 | +| iterations | 10232 | +| time_elapsed | 14742 | +| total_timesteps | 20955136 | +| train/ | | +| approx_kl | 0.013300259 | +| clip_fraction | 0.348 | +| clip_range | 0.0698 | +| entropy_loss | -6.58 | +| explained_variance | 0.337 | +| learning_rate | 4.5e-05 | +| loss | -0.0307 | +| n_updates | 56744 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000139 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1421 | +| iterations | 10233 | +| time_elapsed | 14744 | +| total_timesteps | 20957184 | +| train/ | | +| approx_kl | 0.013807917 | +| clip_fraction | 0.344 | +| clip_range | 0.0698 | +| entropy_loss | -6.3 | +| explained_variance | 0.418 | +| learning_rate | 4.5e-05 | +| loss | -0.0203 | +| n_updates | 56748 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000267 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1421 | +| iterations | 10234 | +| time_elapsed | 14745 | +| total_timesteps | 20959232 | +| train/ | | +| approx_kl | 0.012611126 | +| clip_fraction | 0.343 | +| clip_range | 0.0698 | +| entropy_loss | -6.58 | +| explained_variance | 0.418 | +| learning_rate | 4.5e-05 | +| loss | -0.028 | +| n_updates | 56752 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000282 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1421 | +| iterations | 10235 | +| time_elapsed | 14747 | +| total_timesteps | 20961280 | +| train/ | | +| approx_kl | 0.012171859 | +| clip_fraction | 0.328 | +| clip_range | 0.0698 | +| entropy_loss | -6.49 | +| explained_variance | 0.202 | +| learning_rate | 4.5e-05 | +| loss | -0.0323 | +| n_updates | 56756 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000325 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1421 | +| iterations | 10236 | +| time_elapsed | 14748 | +| total_timesteps | 20963328 | +| train/ | | +| approx_kl | 0.014455711 | +| clip_fraction | 0.307 | +| clip_range | 0.0698 | +| entropy_loss | -6.19 | +| explained_variance | 0.48 | +| learning_rate | 4.5e-05 | +| loss | -0.0325 | +| n_updates | 56760 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000209 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1421 | +| iterations | 10237 | +| time_elapsed | 14749 | +| total_timesteps | 20965376 | +| train/ | | +| approx_kl | 0.013964755 | +| clip_fraction | 0.366 | +| clip_range | 0.0698 | +| entropy_loss | -6.75 | +| explained_variance | -0.0648 | +| learning_rate | 4.5e-05 | +| loss | -0.031 | +| n_updates | 56764 | +| policy_gradient_loss | -0.0225 | +| value_loss | 9.04e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1421 | +| iterations | 10238 | +| time_elapsed | 14751 | +| total_timesteps | 20967424 | +| train/ | | +| approx_kl | 0.012484921 | +| clip_fraction | 0.327 | +| clip_range | 0.0698 | +| entropy_loss | -6.14 | +| explained_variance | 0.484 | +| learning_rate | 4.5e-05 | +| loss | -0.0225 | +| n_updates | 56768 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.00028 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1421 | +| iterations | 10239 | +| time_elapsed | 14752 | +| total_timesteps | 20969472 | +| train/ | | +| approx_kl | 0.013426403 | +| clip_fraction | 0.339 | +| clip_range | 0.0698 | +| entropy_loss | -5.78 | +| explained_variance | 0.47 | +| learning_rate | 4.5e-05 | +| loss | -0.0223 | +| n_updates | 56772 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000236 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1421 | +| iterations | 10240 | +| time_elapsed | 14754 | +| total_timesteps | 20971520 | +| train/ | | +| approx_kl | 0.01240552 | +| clip_fraction | 0.348 | +| clip_range | 0.0698 | +| entropy_loss | -6.15 | +| explained_variance | 0.452 | +| learning_rate | 4.5e-05 | +| loss | -0.031 | +| n_updates | 56776 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000215 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1421 | +| iterations | 10241 | +| time_elapsed | 14755 | +| total_timesteps | 20973568 | +| train/ | | +| approx_kl | 0.017316759 | +| clip_fraction | 0.343 | +| clip_range | 0.0698 | +| entropy_loss | -6.6 | +| explained_variance | 0.0958 | +| learning_rate | 4.5e-05 | +| loss | -0.0347 | +| n_updates | 56780 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000133 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1421 | +| iterations | 10242 | +| time_elapsed | 14757 | +| total_timesteps | 20975616 | +| train/ | | +| approx_kl | 0.014603775 | +| clip_fraction | 0.373 | +| clip_range | 0.0698 | +| entropy_loss | -6.79 | +| explained_variance | 0.515 | +| learning_rate | 4.5e-05 | +| loss | -0.0341 | +| n_updates | 56784 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000102 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1421 | +| iterations | 10243 | +| time_elapsed | 14758 | +| total_timesteps | 20977664 | +| train/ | | +| approx_kl | 0.016792184 | +| clip_fraction | 0.357 | +| clip_range | 0.0698 | +| entropy_loss | -6.31 | +| explained_variance | 0.426 | +| learning_rate | 4.5e-05 | +| loss | -0.0297 | +| n_updates | 56788 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.00021 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1421 | +| iterations | 10244 | +| time_elapsed | 14760 | +| total_timesteps | 20979712 | +| train/ | | +| approx_kl | 0.013647411 | +| clip_fraction | 0.323 | +| clip_range | 0.0698 | +| entropy_loss | -6.52 | +| explained_variance | 0.372 | +| learning_rate | 4.5e-05 | +| loss | -0.0286 | +| n_updates | 56792 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000134 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1421 | +| iterations | 10245 | +| time_elapsed | 14761 | +| total_timesteps | 20981760 | +| train/ | | +| approx_kl | 0.011065221 | +| clip_fraction | 0.331 | +| clip_range | 0.0698 | +| entropy_loss | -6.62 | +| explained_variance | 0.425 | +| learning_rate | 4.5e-05 | +| loss | -0.0264 | +| n_updates | 56796 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000173 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1421 | +| iterations | 10246 | +| time_elapsed | 14763 | +| total_timesteps | 20983808 | +| train/ | | +| approx_kl | 0.012608117 | +| clip_fraction | 0.323 | +| clip_range | 0.0698 | +| entropy_loss | -6.35 | +| explained_variance | 0.355 | +| learning_rate | 4.5e-05 | +| loss | -0.0296 | +| n_updates | 56800 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000265 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1421 | +| iterations | 10247 | +| time_elapsed | 14764 | +| total_timesteps | 20985856 | +| train/ | | +| approx_kl | 0.01330757 | +| clip_fraction | 0.382 | +| clip_range | 0.0698 | +| entropy_loss | -6.41 | +| explained_variance | 0.458 | +| learning_rate | 4.5e-05 | +| loss | -0.0393 | +| n_updates | 56804 | +| policy_gradient_loss | -0.0231 | +| value_loss | 0.000134 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1421 | +| iterations | 10248 | +| time_elapsed | 14765 | +| total_timesteps | 20987904 | +| train/ | | +| approx_kl | 0.012782294 | +| clip_fraction | 0.307 | +| clip_range | 0.0698 | +| entropy_loss | -6.96 | +| explained_variance | 0.058 | +| learning_rate | 4.5e-05 | +| loss | -0.0328 | +| n_updates | 56808 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000249 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1421 | +| iterations | 10249 | +| time_elapsed | 14767 | +| total_timesteps | 20989952 | +| train/ | | +| approx_kl | 0.012299439 | +| clip_fraction | 0.323 | +| clip_range | 0.0698 | +| entropy_loss | -6.38 | +| explained_variance | 0.604 | +| learning_rate | 4.5e-05 | +| loss | -0.0285 | +| n_updates | 56812 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.00014 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1421 | +| iterations | 10250 | +| time_elapsed | 14768 | +| total_timesteps | 20992000 | +| train/ | | +| approx_kl | 0.01346152 | +| clip_fraction | 0.306 | +| clip_range | 0.0698 | +| entropy_loss | -5.86 | +| explained_variance | 0.312 | +| learning_rate | 4.5e-05 | +| loss | -0.0248 | +| n_updates | 56816 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000496 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1421 | +| iterations | 10251 | +| time_elapsed | 14770 | +| total_timesteps | 20994048 | +| train/ | | +| approx_kl | 0.016407553 | +| clip_fraction | 0.351 | +| clip_range | 0.0698 | +| entropy_loss | -6.27 | +| explained_variance | 0.226 | +| learning_rate | 4.5e-05 | +| loss | -0.0339 | +| n_updates | 56820 | +| policy_gradient_loss | -0.022 | +| value_loss | 0.0002 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1421 | +| iterations | 10252 | +| time_elapsed | 14771 | +| total_timesteps | 20996096 | +| train/ | | +| approx_kl | 0.015023025 | +| clip_fraction | 0.346 | +| clip_range | 0.0698 | +| entropy_loss | -6.85 | +| explained_variance | -0.29 | +| learning_rate | 4.5e-05 | +| loss | -0.0319 | +| n_updates | 56824 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000189 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1421 | +| iterations | 10253 | +| time_elapsed | 14773 | +| total_timesteps | 20998144 | +| train/ | | +| approx_kl | 0.016627084 | +| clip_fraction | 0.37 | +| clip_range | 0.0698 | +| entropy_loss | -6.7 | +| explained_variance | 0.175 | +| learning_rate | 4.5e-05 | +| loss | -0.0301 | +| n_updates | 56828 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.00012 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1421 | +| iterations | 10254 | +| time_elapsed | 14774 | +| total_timesteps | 21000192 | +| train/ | | +| approx_kl | 0.013131987 | +| clip_fraction | 0.329 | +| clip_range | 0.0698 | +| entropy_loss | -6.69 | +| explained_variance | 0.218 | +| learning_rate | 4.5e-05 | +| loss | -0.0307 | +| n_updates | 56832 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000246 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1421 | +| iterations | 10255 | +| time_elapsed | 14776 | +| total_timesteps | 21002240 | +| train/ | | +| approx_kl | 0.014581716 | +| clip_fraction | 0.331 | +| clip_range | 0.0697 | +| entropy_loss | -6.11 | +| explained_variance | 0.541 | +| learning_rate | 4.5e-05 | +| loss | -0.0297 | +| n_updates | 56836 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000226 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1421 | +| iterations | 10256 | +| time_elapsed | 14777 | +| total_timesteps | 21004288 | +| train/ | | +| approx_kl | 0.015147718 | +| clip_fraction | 0.363 | +| clip_range | 0.0697 | +| entropy_loss | -6.94 | +| explained_variance | -0.177 | +| learning_rate | 4.5e-05 | +| loss | -0.0334 | +| n_updates | 56840 | +| policy_gradient_loss | -0.022 | +| value_loss | 9.94e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1421 | +| iterations | 10257 | +| time_elapsed | 14779 | +| total_timesteps | 21006336 | +| train/ | | +| approx_kl | 0.013600156 | +| clip_fraction | 0.351 | +| clip_range | 0.0697 | +| entropy_loss | -6.9 | +| explained_variance | -0.157 | +| learning_rate | 4.5e-05 | +| loss | -0.0328 | +| n_updates | 56844 | +| policy_gradient_loss | -0.0208 | +| value_loss | 9.18e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1421 | +| iterations | 10258 | +| time_elapsed | 14780 | +| total_timesteps | 21008384 | +| train/ | | +| approx_kl | 0.01284974 | +| clip_fraction | 0.355 | +| clip_range | 0.0697 | +| entropy_loss | -6.08 | +| explained_variance | 0.57 | +| learning_rate | 4.5e-05 | +| loss | -0.0219 | +| n_updates | 56848 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000171 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1421 | +| iterations | 10259 | +| time_elapsed | 14782 | +| total_timesteps | 21010432 | +| train/ | | +| approx_kl | 0.011715036 | +| clip_fraction | 0.325 | +| clip_range | 0.0697 | +| entropy_loss | -6.57 | +| explained_variance | 0.0753 | +| learning_rate | 4.5e-05 | +| loss | -0.0309 | +| n_updates | 56852 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000201 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1421 | +| iterations | 10260 | +| time_elapsed | 14783 | +| total_timesteps | 21012480 | +| train/ | | +| approx_kl | 0.012513026 | +| clip_fraction | 0.305 | +| clip_range | 0.0697 | +| entropy_loss | -6.45 | +| explained_variance | 0.326 | +| learning_rate | 4.5e-05 | +| loss | -0.0287 | +| n_updates | 56856 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000288 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1421 | +| iterations | 10261 | +| time_elapsed | 14784 | +| total_timesteps | 21014528 | +| train/ | | +| approx_kl | 0.012183806 | +| clip_fraction | 0.321 | +| clip_range | 0.0697 | +| entropy_loss | -6.51 | +| explained_variance | 0.261 | +| learning_rate | 4.5e-05 | +| loss | -0.0271 | +| n_updates | 56860 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000362 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1421 | +| iterations | 10262 | +| time_elapsed | 14786 | +| total_timesteps | 21016576 | +| train/ | | +| approx_kl | 0.012082631 | +| clip_fraction | 0.333 | +| clip_range | 0.0697 | +| entropy_loss | -6.19 | +| explained_variance | 0.564 | +| learning_rate | 4.5e-05 | +| loss | -0.0298 | +| n_updates | 56864 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000115 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1421 | +| iterations | 10263 | +| time_elapsed | 14787 | +| total_timesteps | 21018624 | +| train/ | | +| approx_kl | 0.012346425 | +| clip_fraction | 0.349 | +| clip_range | 0.0697 | +| entropy_loss | -6.63 | +| explained_variance | 0.278 | +| learning_rate | 4.5e-05 | +| loss | -0.0301 | +| n_updates | 56868 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000191 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1421 | +| iterations | 10264 | +| time_elapsed | 14789 | +| total_timesteps | 21020672 | +| train/ | | +| approx_kl | 0.012881944 | +| clip_fraction | 0.353 | +| clip_range | 0.0697 | +| entropy_loss | -6.87 | +| explained_variance | 0.259 | +| learning_rate | 4.5e-05 | +| loss | -0.0313 | +| n_updates | 56872 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000156 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1421 | +| iterations | 10265 | +| time_elapsed | 14790 | +| total_timesteps | 21022720 | +| train/ | | +| approx_kl | 0.012082649 | +| clip_fraction | 0.347 | +| clip_range | 0.0697 | +| entropy_loss | -6.73 | +| explained_variance | 0.37 | +| learning_rate | 4.5e-05 | +| loss | -0.0323 | +| n_updates | 56876 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000118 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1421 | +| iterations | 10266 | +| time_elapsed | 14792 | +| total_timesteps | 21024768 | +| train/ | | +| approx_kl | 0.01361926 | +| clip_fraction | 0.311 | +| clip_range | 0.0697 | +| entropy_loss | -6.47 | +| explained_variance | 0.454 | +| learning_rate | 4.5e-05 | +| loss | -0.0226 | +| n_updates | 56880 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000275 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1421 | +| iterations | 10267 | +| time_elapsed | 14793 | +| total_timesteps | 21026816 | +| train/ | | +| approx_kl | 0.015009665 | +| clip_fraction | 0.365 | +| clip_range | 0.0697 | +| entropy_loss | -6.78 | +| explained_variance | 0.0669 | +| learning_rate | 4.5e-05 | +| loss | -0.0356 | +| n_updates | 56884 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.00011 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1421 | +| iterations | 10268 | +| time_elapsed | 14795 | +| total_timesteps | 21028864 | +| train/ | | +| approx_kl | 0.014560267 | +| clip_fraction | 0.35 | +| clip_range | 0.0697 | +| entropy_loss | -6.94 | +| explained_variance | -0.343 | +| learning_rate | 4.5e-05 | +| loss | -0.0366 | +| n_updates | 56888 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000155 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1421 | +| iterations | 10269 | +| time_elapsed | 14796 | +| total_timesteps | 21030912 | +| train/ | | +| approx_kl | 0.01464822 | +| clip_fraction | 0.336 | +| clip_range | 0.0697 | +| entropy_loss | -7.23 | +| explained_variance | -0.097 | +| learning_rate | 4.5e-05 | +| loss | -0.0265 | +| n_updates | 56892 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000144 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1421 | +| iterations | 10270 | +| time_elapsed | 14798 | +| total_timesteps | 21032960 | +| train/ | | +| approx_kl | 0.01429154 | +| clip_fraction | 0.322 | +| clip_range | 0.0697 | +| entropy_loss | -6.59 | +| explained_variance | 0.314 | +| learning_rate | 4.5e-05 | +| loss | -0.0285 | +| n_updates | 56896 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000193 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1421 | +| iterations | 10271 | +| time_elapsed | 14799 | +| total_timesteps | 21035008 | +| train/ | | +| approx_kl | 0.011622295 | +| clip_fraction | 0.342 | +| clip_range | 0.0697 | +| entropy_loss | -5.96 | +| explained_variance | 0.449 | +| learning_rate | 4.5e-05 | +| loss | -0.025 | +| n_updates | 56900 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000302 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1421 | +| iterations | 10272 | +| time_elapsed | 14801 | +| total_timesteps | 21037056 | +| train/ | | +| approx_kl | 0.012664215 | +| clip_fraction | 0.319 | +| clip_range | 0.0697 | +| entropy_loss | -6.5 | +| explained_variance | 0.554 | +| learning_rate | 4.5e-05 | +| loss | -0.0281 | +| n_updates | 56904 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000125 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1421 | +| iterations | 10273 | +| time_elapsed | 14802 | +| total_timesteps | 21039104 | +| train/ | | +| approx_kl | 0.014541728 | +| clip_fraction | 0.352 | +| clip_range | 0.0697 | +| entropy_loss | -6.65 | +| explained_variance | 0.26 | +| learning_rate | 4.5e-05 | +| loss | -0.0337 | +| n_updates | 56908 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000154 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1421 | +| iterations | 10274 | +| time_elapsed | 14804 | +| total_timesteps | 21041152 | +| train/ | | +| approx_kl | 0.013410503 | +| clip_fraction | 0.309 | +| clip_range | 0.0697 | +| entropy_loss | -6.56 | +| explained_variance | 0.459 | +| learning_rate | 4.5e-05 | +| loss | -0.0271 | +| n_updates | 56912 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000163 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1421 | +| iterations | 10275 | +| time_elapsed | 14805 | +| total_timesteps | 21043200 | +| train/ | | +| approx_kl | 0.012955431 | +| clip_fraction | 0.359 | +| clip_range | 0.0697 | +| entropy_loss | -6.63 | +| explained_variance | 0.522 | +| learning_rate | 4.5e-05 | +| loss | -0.0381 | +| n_updates | 56916 | +| policy_gradient_loss | -0.0223 | +| value_loss | 7.93e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1421 | +| iterations | 10276 | +| time_elapsed | 14807 | +| total_timesteps | 21045248 | +| train/ | | +| approx_kl | 0.011350991 | +| clip_fraction | 0.337 | +| clip_range | 0.0697 | +| entropy_loss | -6.67 | +| explained_variance | 0.448 | +| learning_rate | 4.5e-05 | +| loss | -0.0256 | +| n_updates | 56920 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.00018 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1421 | +| iterations | 10277 | +| time_elapsed | 14808 | +| total_timesteps | 21047296 | +| train/ | | +| approx_kl | 0.013479007 | +| clip_fraction | 0.328 | +| clip_range | 0.0697 | +| entropy_loss | -6.71 | +| explained_variance | 0.282 | +| learning_rate | 4.5e-05 | +| loss | -0.0302 | +| n_updates | 56924 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000205 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1421 | +| iterations | 10278 | +| time_elapsed | 14810 | +| total_timesteps | 21049344 | +| train/ | | +| approx_kl | 0.010585571 | +| clip_fraction | 0.324 | +| clip_range | 0.0697 | +| entropy_loss | -6.98 | +| explained_variance | 0.177 | +| learning_rate | 4.5e-05 | +| loss | -0.0308 | +| n_updates | 56928 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.00023 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1421 | +| iterations | 10279 | +| time_elapsed | 14811 | +| total_timesteps | 21051392 | +| train/ | | +| approx_kl | 0.011475768 | +| clip_fraction | 0.348 | +| clip_range | 0.0697 | +| entropy_loss | -7.24 | +| explained_variance | -0.334 | +| learning_rate | 4.5e-05 | +| loss | -0.0421 | +| n_updates | 56932 | +| policy_gradient_loss | -0.0218 | +| value_loss | 6.75e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1421 | +| iterations | 10280 | +| time_elapsed | 14812 | +| total_timesteps | 21053440 | +| train/ | | +| approx_kl | 0.009656232 | +| clip_fraction | 0.291 | +| clip_range | 0.0697 | +| entropy_loss | -6.85 | +| explained_variance | 0.461 | +| learning_rate | 4.5e-05 | +| loss | -0.0261 | +| n_updates | 56936 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000168 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1421 | +| iterations | 10281 | +| time_elapsed | 14814 | +| total_timesteps | 21055488 | +| train/ | | +| approx_kl | 0.015207195 | +| clip_fraction | 0.307 | +| clip_range | 0.0697 | +| entropy_loss | -6.28 | +| explained_variance | 0.498 | +| learning_rate | 4.5e-05 | +| loss | -0.0237 | +| n_updates | 56940 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000256 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1421 | +| iterations | 10282 | +| time_elapsed | 14815 | +| total_timesteps | 21057536 | +| train/ | | +| approx_kl | 0.014067469 | +| clip_fraction | 0.34 | +| clip_range | 0.0697 | +| entropy_loss | -5.7 | +| explained_variance | 0.501 | +| learning_rate | 4.5e-05 | +| loss | -0.0217 | +| n_updates | 56944 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000379 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1421 | +| iterations | 10283 | +| time_elapsed | 14817 | +| total_timesteps | 21059584 | +| train/ | | +| approx_kl | 0.011880681 | +| clip_fraction | 0.352 | +| clip_range | 0.0697 | +| entropy_loss | -6.41 | +| explained_variance | 0.262 | +| learning_rate | 4.5e-05 | +| loss | -0.0336 | +| n_updates | 56948 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.00016 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1421 | +| iterations | 10284 | +| time_elapsed | 14818 | +| total_timesteps | 21061632 | +| train/ | | +| approx_kl | 0.011710849 | +| clip_fraction | 0.326 | +| clip_range | 0.0697 | +| entropy_loss | -6.9 | +| explained_variance | 0.283 | +| learning_rate | 4.5e-05 | +| loss | -0.0299 | +| n_updates | 56952 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000164 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1421 | +| iterations | 10285 | +| time_elapsed | 14820 | +| total_timesteps | 21063680 | +| train/ | | +| approx_kl | 0.012210693 | +| clip_fraction | 0.329 | +| clip_range | 0.0697 | +| entropy_loss | -6.77 | +| explained_variance | 0.285 | +| learning_rate | 4.5e-05 | +| loss | -0.0359 | +| n_updates | 56956 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.385 | +| time/ | | +| fps | 1421 | +| iterations | 10286 | +| time_elapsed | 14821 | +| total_timesteps | 21065728 | +| train/ | | +| approx_kl | 0.014343156 | +| clip_fraction | 0.381 | +| clip_range | 0.0697 | +| entropy_loss | -6.56 | +| explained_variance | 0.532 | +| learning_rate | 4.5e-05 | +| loss | -0.0397 | +| n_updates | 56960 | +| policy_gradient_loss | -0.0221 | +| value_loss | 5.92e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.385 | +| time/ | | +| fps | 1421 | +| iterations | 10287 | +| time_elapsed | 14823 | +| total_timesteps | 21067776 | +| train/ | | +| approx_kl | 0.012627389 | +| clip_fraction | 0.328 | +| clip_range | 0.0697 | +| entropy_loss | -6.69 | +| explained_variance | 0.293 | +| learning_rate | 4.5e-05 | +| loss | -0.0189 | +| n_updates | 56964 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000176 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.386 | +| time/ | | +| fps | 1421 | +| iterations | 10288 | +| time_elapsed | 14824 | +| total_timesteps | 21069824 | +| train/ | | +| approx_kl | 0.013559024 | +| clip_fraction | 0.327 | +| clip_range | 0.0697 | +| entropy_loss | -6.87 | +| explained_variance | -0.0169 | +| learning_rate | 4.5e-05 | +| loss | -0.0295 | +| n_updates | 56968 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000209 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.386 | +| time/ | | +| fps | 1421 | +| iterations | 10289 | +| time_elapsed | 14826 | +| total_timesteps | 21071872 | +| train/ | | +| approx_kl | 0.012133221 | +| clip_fraction | 0.328 | +| clip_range | 0.0697 | +| entropy_loss | -6.55 | +| explained_variance | 0.52 | +| learning_rate | 4.5e-05 | +| loss | -0.0232 | +| n_updates | 56972 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000148 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.385 | +| time/ | | +| fps | 1421 | +| iterations | 10290 | +| time_elapsed | 14827 | +| total_timesteps | 21073920 | +| train/ | | +| approx_kl | 0.015292332 | +| clip_fraction | 0.367 | +| clip_range | 0.0697 | +| entropy_loss | -6.55 | +| explained_variance | 0.5 | +| learning_rate | 4.5e-05 | +| loss | -0.0372 | +| n_updates | 56976 | +| policy_gradient_loss | -0.0227 | +| value_loss | 7.63e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1421 | +| iterations | 10291 | +| time_elapsed | 14829 | +| total_timesteps | 21075968 | +| train/ | | +| approx_kl | 0.012877271 | +| clip_fraction | 0.335 | +| clip_range | 0.0697 | +| entropy_loss | -7.05 | +| explained_variance | -0.0407 | +| learning_rate | 4.5e-05 | +| loss | -0.0298 | +| n_updates | 56980 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000116 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1421 | +| iterations | 10292 | +| time_elapsed | 14830 | +| total_timesteps | 21078016 | +| train/ | | +| approx_kl | 0.012024772 | +| clip_fraction | 0.31 | +| clip_range | 0.0697 | +| entropy_loss | -6.56 | +| explained_variance | 0.614 | +| learning_rate | 4.5e-05 | +| loss | -0.0245 | +| n_updates | 56984 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000137 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1421 | +| iterations | 10293 | +| time_elapsed | 14832 | +| total_timesteps | 21080064 | +| train/ | | +| approx_kl | 0.01019601 | +| clip_fraction | 0.317 | +| clip_range | 0.0697 | +| entropy_loss | -7.04 | +| explained_variance | -0.141 | +| learning_rate | 4.5e-05 | +| loss | -0.0358 | +| n_updates | 56988 | +| policy_gradient_loss | -0.02 | +| value_loss | 8.15e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1421 | +| iterations | 10294 | +| time_elapsed | 14833 | +| total_timesteps | 21082112 | +| train/ | | +| approx_kl | 0.009755739 | +| clip_fraction | 0.298 | +| clip_range | 0.0697 | +| entropy_loss | -6.31 | +| explained_variance | 0.688 | +| learning_rate | 4.5e-05 | +| loss | -0.022 | +| n_updates | 56992 | +| policy_gradient_loss | -0.0146 | +| value_loss | 0.00015 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1421 | +| iterations | 10295 | +| time_elapsed | 14835 | +| total_timesteps | 21084160 | +| train/ | | +| approx_kl | 0.011009874 | +| clip_fraction | 0.313 | +| clip_range | 0.0697 | +| entropy_loss | -5.72 | +| explained_variance | 0.653 | +| learning_rate | 4.5e-05 | +| loss | -0.0271 | +| n_updates | 56996 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000136 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1421 | +| iterations | 10296 | +| time_elapsed | 14836 | +| total_timesteps | 21086208 | +| train/ | | +| approx_kl | 0.013112184 | +| clip_fraction | 0.33 | +| clip_range | 0.0697 | +| entropy_loss | -7.11 | +| explained_variance | 0.0395 | +| learning_rate | 4.5e-05 | +| loss | -0.0334 | +| n_updates | 57000 | +| policy_gradient_loss | -0.0206 | +| value_loss | 8.89e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1421 | +| iterations | 10297 | +| time_elapsed | 14838 | +| total_timesteps | 21088256 | +| train/ | | +| approx_kl | 0.014196662 | +| clip_fraction | 0.342 | +| clip_range | 0.0697 | +| entropy_loss | -6.76 | +| explained_variance | 0.202 | +| learning_rate | 4.5e-05 | +| loss | -0.0168 | +| n_updates | 57004 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000173 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1421 | +| iterations | 10298 | +| time_elapsed | 14839 | +| total_timesteps | 21090304 | +| train/ | | +| approx_kl | 0.012390807 | +| clip_fraction | 0.327 | +| clip_range | 0.0697 | +| entropy_loss | -6.93 | +| explained_variance | -0.0775 | +| learning_rate | 4.5e-05 | +| loss | -0.031 | +| n_updates | 57008 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000232 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1421 | +| iterations | 10299 | +| time_elapsed | 14841 | +| total_timesteps | 21092352 | +| train/ | | +| approx_kl | 0.011587504 | +| clip_fraction | 0.324 | +| clip_range | 0.0697 | +| entropy_loss | -6.13 | +| explained_variance | 0.342 | +| learning_rate | 4.5e-05 | +| loss | -0.0358 | +| n_updates | 57012 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000293 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1421 | +| iterations | 10300 | +| time_elapsed | 14842 | +| total_timesteps | 21094400 | +| train/ | | +| approx_kl | 0.014552394 | +| clip_fraction | 0.349 | +| clip_range | 0.0697 | +| entropy_loss | -6.02 | +| explained_variance | 0.413 | +| learning_rate | 4.5e-05 | +| loss | -0.0333 | +| n_updates | 57016 | +| policy_gradient_loss | -0.022 | +| value_loss | 0.000105 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1421 | +| iterations | 10301 | +| time_elapsed | 14843 | +| total_timesteps | 21096448 | +| train/ | | +| approx_kl | 0.013691286 | +| clip_fraction | 0.362 | +| clip_range | 0.0697 | +| entropy_loss | -6.92 | +| explained_variance | -0.0136 | +| learning_rate | 4.5e-05 | +| loss | -0.0353 | +| n_updates | 57020 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000158 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1421 | +| iterations | 10302 | +| time_elapsed | 14845 | +| total_timesteps | 21098496 | +| train/ | | +| approx_kl | 0.014980108 | +| clip_fraction | 0.329 | +| clip_range | 0.0697 | +| entropy_loss | -6.58 | +| explained_variance | 0.179 | +| learning_rate | 4.5e-05 | +| loss | -0.0291 | +| n_updates | 57024 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000168 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1421 | +| iterations | 10303 | +| time_elapsed | 14846 | +| total_timesteps | 21100544 | +| train/ | | +| approx_kl | 0.016154405 | +| clip_fraction | 0.331 | +| clip_range | 0.0697 | +| entropy_loss | -6.57 | +| explained_variance | 0.173 | +| learning_rate | 4.5e-05 | +| loss | -0.0279 | +| n_updates | 57028 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000254 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1421 | +| iterations | 10304 | +| time_elapsed | 14848 | +| total_timesteps | 21102592 | +| train/ | | +| approx_kl | 0.01525628 | +| clip_fraction | 0.372 | +| clip_range | 0.0697 | +| entropy_loss | -6.48 | +| explained_variance | 0.434 | +| learning_rate | 4.5e-05 | +| loss | -0.0332 | +| n_updates | 57032 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000153 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1421 | +| iterations | 10305 | +| time_elapsed | 14849 | +| total_timesteps | 21104640 | +| train/ | | +| approx_kl | 0.015362415 | +| clip_fraction | 0.353 | +| clip_range | 0.0697 | +| entropy_loss | -6.95 | +| explained_variance | -0.142 | +| learning_rate | 4.5e-05 | +| loss | -0.0331 | +| n_updates | 57036 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000143 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1421 | +| iterations | 10306 | +| time_elapsed | 14851 | +| total_timesteps | 21106688 | +| train/ | | +| approx_kl | 0.013544554 | +| clip_fraction | 0.343 | +| clip_range | 0.0697 | +| entropy_loss | -6.89 | +| explained_variance | 0.169 | +| learning_rate | 4.5e-05 | +| loss | -0.0355 | +| n_updates | 57040 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000194 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1421 | +| iterations | 10307 | +| time_elapsed | 14852 | +| total_timesteps | 21108736 | +| train/ | | +| approx_kl | 0.012485223 | +| clip_fraction | 0.329 | +| clip_range | 0.0697 | +| entropy_loss | -6.2 | +| explained_variance | 0.533 | +| learning_rate | 4.5e-05 | +| loss | -0.0346 | +| n_updates | 57044 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000199 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1421 | +| iterations | 10308 | +| time_elapsed | 14854 | +| total_timesteps | 21110784 | +| train/ | | +| approx_kl | 0.014175036 | +| clip_fraction | 0.313 | +| clip_range | 0.0697 | +| entropy_loss | -6.49 | +| explained_variance | 0.000373 | +| learning_rate | 4.5e-05 | +| loss | -0.032 | +| n_updates | 57048 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.00011 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1421 | +| iterations | 10309 | +| time_elapsed | 14855 | +| total_timesteps | 21112832 | +| train/ | | +| approx_kl | 0.010403916 | +| clip_fraction | 0.323 | +| clip_range | 0.0697 | +| entropy_loss | -6.42 | +| explained_variance | 0.437 | +| learning_rate | 4.5e-05 | +| loss | -0.0259 | +| n_updates | 57052 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000178 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1421 | +| iterations | 10310 | +| time_elapsed | 14857 | +| total_timesteps | 21114880 | +| train/ | | +| approx_kl | 0.013196601 | +| clip_fraction | 0.32 | +| clip_range | 0.0697 | +| entropy_loss | -5.89 | +| explained_variance | 0.654 | +| learning_rate | 4.5e-05 | +| loss | -0.0264 | +| n_updates | 57056 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000136 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1421 | +| iterations | 10311 | +| time_elapsed | 14858 | +| total_timesteps | 21116928 | +| train/ | | +| approx_kl | 0.009397829 | +| clip_fraction | 0.289 | +| clip_range | 0.0697 | +| entropy_loss | -6.96 | +| explained_variance | -0.0425 | +| learning_rate | 4.5e-05 | +| loss | -0.0283 | +| n_updates | 57060 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000179 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1421 | +| iterations | 10312 | +| time_elapsed | 14860 | +| total_timesteps | 21118976 | +| train/ | | +| approx_kl | 0.011908039 | +| clip_fraction | 0.354 | +| clip_range | 0.0697 | +| entropy_loss | -6.79 | +| explained_variance | 0.604 | +| learning_rate | 4.5e-05 | +| loss | -0.0389 | +| n_updates | 57064 | +| policy_gradient_loss | -0.0232 | +| value_loss | 6.73e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1421 | +| iterations | 10313 | +| time_elapsed | 14861 | +| total_timesteps | 21121024 | +| train/ | | +| approx_kl | 0.014931245 | +| clip_fraction | 0.321 | +| clip_range | 0.0697 | +| entropy_loss | -6.91 | +| explained_variance | 0.249 | +| learning_rate | 4.5e-05 | +| loss | -0.0324 | +| n_updates | 57068 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000201 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1421 | +| iterations | 10314 | +| time_elapsed | 14863 | +| total_timesteps | 21123072 | +| train/ | | +| approx_kl | 0.0146335885 | +| clip_fraction | 0.311 | +| clip_range | 0.0697 | +| entropy_loss | -6.63 | +| explained_variance | 0.449 | +| learning_rate | 4.5e-05 | +| loss | -0.0265 | +| n_updates | 57072 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000236 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1421 | +| iterations | 10315 | +| time_elapsed | 14864 | +| total_timesteps | 21125120 | +| train/ | | +| approx_kl | 0.012776416 | +| clip_fraction | 0.317 | +| clip_range | 0.0697 | +| entropy_loss | -6.43 | +| explained_variance | 0.713 | +| learning_rate | 4.5e-05 | +| loss | -0.031 | +| n_updates | 57076 | +| policy_gradient_loss | -0.0213 | +| value_loss | 8.2e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1421 | +| iterations | 10316 | +| time_elapsed | 14866 | +| total_timesteps | 21127168 | +| train/ | | +| approx_kl | 0.018422134 | +| clip_fraction | 0.326 | +| clip_range | 0.0697 | +| entropy_loss | -6.63 | +| explained_variance | -0.269 | +| learning_rate | 4.5e-05 | +| loss | -0.0293 | +| n_updates | 57080 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000123 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1421 | +| iterations | 10317 | +| time_elapsed | 14867 | +| total_timesteps | 21129216 | +| train/ | | +| approx_kl | 0.014284727 | +| clip_fraction | 0.328 | +| clip_range | 0.0697 | +| entropy_loss | -6.65 | +| explained_variance | 0.22 | +| learning_rate | 4.5e-05 | +| loss | -0.0281 | +| n_updates | 57084 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000197 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1421 | +| iterations | 10318 | +| time_elapsed | 14868 | +| total_timesteps | 21131264 | +| train/ | | +| approx_kl | 0.011889454 | +| clip_fraction | 0.328 | +| clip_range | 0.0697 | +| entropy_loss | -6.65 | +| explained_variance | 0.296 | +| learning_rate | 4.5e-05 | +| loss | -0.0343 | +| n_updates | 57088 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000175 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1421 | +| iterations | 10319 | +| time_elapsed | 14870 | +| total_timesteps | 21133312 | +| train/ | | +| approx_kl | 0.012587148 | +| clip_fraction | 0.342 | +| clip_range | 0.0697 | +| entropy_loss | -6.62 | +| explained_variance | 0.383 | +| learning_rate | 4.5e-05 | +| loss | -0.0382 | +| n_updates | 57092 | +| policy_gradient_loss | -0.022 | +| value_loss | 9.95e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1421 | +| iterations | 10320 | +| time_elapsed | 14871 | +| total_timesteps | 21135360 | +| train/ | | +| approx_kl | 0.012576461 | +| clip_fraction | 0.329 | +| clip_range | 0.0697 | +| entropy_loss | -6.34 | +| explained_variance | 0.417 | +| learning_rate | 4.5e-05 | +| loss | -0.0294 | +| n_updates | 57096 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.00027 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1421 | +| iterations | 10321 | +| time_elapsed | 14873 | +| total_timesteps | 21137408 | +| train/ | | +| approx_kl | 0.015900858 | +| clip_fraction | 0.34 | +| clip_range | 0.0697 | +| entropy_loss | -5.96 | +| explained_variance | 0.55 | +| learning_rate | 4.5e-05 | +| loss | -0.0324 | +| n_updates | 57100 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000143 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1421 | +| iterations | 10322 | +| time_elapsed | 14874 | +| total_timesteps | 21139456 | +| train/ | | +| approx_kl | 0.011485657 | +| clip_fraction | 0.326 | +| clip_range | 0.0697 | +| entropy_loss | -6.36 | +| explained_variance | 0.4 | +| learning_rate | 4.5e-05 | +| loss | -0.0278 | +| n_updates | 57104 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000258 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1421 | +| iterations | 10323 | +| time_elapsed | 14876 | +| total_timesteps | 21141504 | +| train/ | | +| approx_kl | 0.010572034 | +| clip_fraction | 0.338 | +| clip_range | 0.0697 | +| entropy_loss | -7.24 | +| explained_variance | -0.558 | +| learning_rate | 4.5e-05 | +| loss | -0.0352 | +| n_updates | 57108 | +| policy_gradient_loss | -0.0231 | +| value_loss | 0.000115 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1421 | +| iterations | 10324 | +| time_elapsed | 14877 | +| total_timesteps | 21143552 | +| train/ | | +| approx_kl | 0.01046475 | +| clip_fraction | 0.306 | +| clip_range | 0.0697 | +| entropy_loss | -7.4 | +| explained_variance | 0.0726 | +| learning_rate | 4.5e-05 | +| loss | -0.0274 | +| n_updates | 57112 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000291 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1421 | +| iterations | 10325 | +| time_elapsed | 14879 | +| total_timesteps | 21145600 | +| train/ | | +| approx_kl | 0.012894695 | +| clip_fraction | 0.323 | +| clip_range | 0.0697 | +| entropy_loss | -7.05 | +| explained_variance | 0.198 | +| learning_rate | 4.5e-05 | +| loss | -0.027 | +| n_updates | 57116 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000218 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1421 | +| iterations | 10326 | +| time_elapsed | 14880 | +| total_timesteps | 21147648 | +| train/ | | +| approx_kl | 0.013397516 | +| clip_fraction | 0.316 | +| clip_range | 0.0697 | +| entropy_loss | -6.34 | +| explained_variance | 0.388 | +| learning_rate | 4.5e-05 | +| loss | -0.0299 | +| n_updates | 57120 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000305 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1421 | +| iterations | 10327 | +| time_elapsed | 14882 | +| total_timesteps | 21149696 | +| train/ | | +| approx_kl | 0.013584368 | +| clip_fraction | 0.377 | +| clip_range | 0.0697 | +| entropy_loss | -6.26 | +| explained_variance | 0.421 | +| learning_rate | 4.5e-05 | +| loss | -0.0317 | +| n_updates | 57124 | +| policy_gradient_loss | -0.0222 | +| value_loss | 0.000169 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1421 | +| iterations | 10328 | +| time_elapsed | 14883 | +| total_timesteps | 21151744 | +| train/ | | +| approx_kl | 0.012945138 | +| clip_fraction | 0.336 | +| clip_range | 0.0697 | +| entropy_loss | -6.41 | +| explained_variance | 0.28 | +| learning_rate | 4.5e-05 | +| loss | -0.0265 | +| n_updates | 57128 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000292 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1421 | +| iterations | 10329 | +| time_elapsed | 14884 | +| total_timesteps | 21153792 | +| train/ | | +| approx_kl | 0.012952348 | +| clip_fraction | 0.328 | +| clip_range | 0.0697 | +| entropy_loss | -5.84 | +| explained_variance | 0.586 | +| learning_rate | 4.5e-05 | +| loss | -0.0309 | +| n_updates | 57132 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000197 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1421 | +| iterations | 10330 | +| time_elapsed | 14886 | +| total_timesteps | 21155840 | +| train/ | | +| approx_kl | 0.014260535 | +| clip_fraction | 0.303 | +| clip_range | 0.0697 | +| entropy_loss | -6.51 | +| explained_variance | 0.198 | +| learning_rate | 4.5e-05 | +| loss | -0.0274 | +| n_updates | 57136 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.00025 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1421 | +| iterations | 10331 | +| time_elapsed | 14887 | +| total_timesteps | 21157888 | +| train/ | | +| approx_kl | 0.012708127 | +| clip_fraction | 0.313 | +| clip_range | 0.0697 | +| entropy_loss | -6.48 | +| explained_variance | 0.485 | +| learning_rate | 4.5e-05 | +| loss | -0.0259 | +| n_updates | 57140 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000217 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1421 | +| iterations | 10332 | +| time_elapsed | 14889 | +| total_timesteps | 21159936 | +| train/ | | +| approx_kl | 0.011232649 | +| clip_fraction | 0.339 | +| clip_range | 0.0697 | +| entropy_loss | -7.01 | +| explained_variance | 0.125 | +| learning_rate | 4.5e-05 | +| loss | -0.0323 | +| n_updates | 57144 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000124 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1421 | +| iterations | 10333 | +| time_elapsed | 14890 | +| total_timesteps | 21161984 | +| train/ | | +| approx_kl | 0.011917612 | +| clip_fraction | 0.324 | +| clip_range | 0.0697 | +| entropy_loss | -7.16 | +| explained_variance | -0.0595 | +| learning_rate | 4.5e-05 | +| loss | -0.0297 | +| n_updates | 57148 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000133 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1421 | +| iterations | 10334 | +| time_elapsed | 14892 | +| total_timesteps | 21164032 | +| train/ | | +| approx_kl | 0.014360244 | +| clip_fraction | 0.32 | +| clip_range | 0.0697 | +| entropy_loss | -6.78 | +| explained_variance | 0.429 | +| learning_rate | 4.5e-05 | +| loss | -0.0249 | +| n_updates | 57152 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.0002 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1421 | +| iterations | 10335 | +| time_elapsed | 14893 | +| total_timesteps | 21166080 | +| train/ | | +| approx_kl | 0.012703971 | +| clip_fraction | 0.317 | +| clip_range | 0.0697 | +| entropy_loss | -6.23 | +| explained_variance | 0.573 | +| learning_rate | 4.5e-05 | +| loss | -0.0331 | +| n_updates | 57156 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000148 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1421 | +| iterations | 10336 | +| time_elapsed | 14895 | +| total_timesteps | 21168128 | +| train/ | | +| approx_kl | 0.013319153 | +| clip_fraction | 0.326 | +| clip_range | 0.0697 | +| entropy_loss | -6.72 | +| explained_variance | 0.325 | +| learning_rate | 4.5e-05 | +| loss | -0.031 | +| n_updates | 57160 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000186 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1421 | +| iterations | 10337 | +| time_elapsed | 14896 | +| total_timesteps | 21170176 | +| train/ | | +| approx_kl | 0.01536832 | +| clip_fraction | 0.332 | +| clip_range | 0.0697 | +| entropy_loss | -6.11 | +| explained_variance | 0.404 | +| learning_rate | 4.5e-05 | +| loss | -0.029 | +| n_updates | 57164 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000239 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1421 | +| iterations | 10338 | +| time_elapsed | 14898 | +| total_timesteps | 21172224 | +| train/ | | +| approx_kl | 0.015380507 | +| clip_fraction | 0.315 | +| clip_range | 0.0697 | +| entropy_loss | -5.33 | +| explained_variance | 0.807 | +| learning_rate | 4.5e-05 | +| loss | -0.0293 | +| n_updates | 57168 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000114 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1421 | +| iterations | 10339 | +| time_elapsed | 14899 | +| total_timesteps | 21174272 | +| train/ | | +| approx_kl | 0.010874895 | +| clip_fraction | 0.354 | +| clip_range | 0.0697 | +| entropy_loss | -6.75 | +| explained_variance | -0.186 | +| learning_rate | 4.5e-05 | +| loss | -0.0369 | +| n_updates | 57172 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000134 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1421 | +| iterations | 10340 | +| time_elapsed | 14900 | +| total_timesteps | 21176320 | +| train/ | | +| approx_kl | 0.015002826 | +| clip_fraction | 0.339 | +| clip_range | 0.0697 | +| entropy_loss | -6.83 | +| explained_variance | 0.0669 | +| learning_rate | 4.5e-05 | +| loss | -0.0369 | +| n_updates | 57176 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000129 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1421 | +| iterations | 10341 | +| time_elapsed | 14902 | +| total_timesteps | 21178368 | +| train/ | | +| approx_kl | 0.012550943 | +| clip_fraction | 0.313 | +| clip_range | 0.0697 | +| entropy_loss | -6.32 | +| explained_variance | 0.436 | +| learning_rate | 4.5e-05 | +| loss | -0.0269 | +| n_updates | 57180 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000293 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1421 | +| iterations | 10342 | +| time_elapsed | 14903 | +| total_timesteps | 21180416 | +| train/ | | +| approx_kl | 0.009961236 | +| clip_fraction | 0.319 | +| clip_range | 0.0697 | +| entropy_loss | -6.45 | +| explained_variance | 0.404 | +| learning_rate | 4.5e-05 | +| loss | -0.032 | +| n_updates | 57184 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000241 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1421 | +| iterations | 10343 | +| time_elapsed | 14905 | +| total_timesteps | 21182464 | +| train/ | | +| approx_kl | 0.009542234 | +| clip_fraction | 0.305 | +| clip_range | 0.0697 | +| entropy_loss | -6.47 | +| explained_variance | 0.305 | +| learning_rate | 4.5e-05 | +| loss | -0.0293 | +| n_updates | 57188 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000416 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1421 | +| iterations | 10344 | +| time_elapsed | 14906 | +| total_timesteps | 21184512 | +| train/ | | +| approx_kl | 0.01162721 | +| clip_fraction | 0.319 | +| clip_range | 0.0697 | +| entropy_loss | -6.94 | +| explained_variance | 0.0589 | +| learning_rate | 4.5e-05 | +| loss | -0.0299 | +| n_updates | 57192 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000209 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1421 | +| iterations | 10345 | +| time_elapsed | 14908 | +| total_timesteps | 21186560 | +| train/ | | +| approx_kl | 0.011150027 | +| clip_fraction | 0.326 | +| clip_range | 0.0697 | +| entropy_loss | -7.1 | +| explained_variance | -0.051 | +| learning_rate | 4.5e-05 | +| loss | -0.0316 | +| n_updates | 57196 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.00017 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1421 | +| iterations | 10346 | +| time_elapsed | 14909 | +| total_timesteps | 21188608 | +| train/ | | +| approx_kl | 0.010316094 | +| clip_fraction | 0.307 | +| clip_range | 0.0697 | +| entropy_loss | -6.55 | +| explained_variance | 0.411 | +| learning_rate | 4.5e-05 | +| loss | -0.0144 | +| n_updates | 57200 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000311 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1421 | +| iterations | 10347 | +| time_elapsed | 14911 | +| total_timesteps | 21190656 | +| train/ | | +| approx_kl | 0.012973717 | +| clip_fraction | 0.309 | +| clip_range | 0.0697 | +| entropy_loss | -6.09 | +| explained_variance | 0.427 | +| learning_rate | 4.5e-05 | +| loss | -0.0289 | +| n_updates | 57204 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000272 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1421 | +| iterations | 10348 | +| time_elapsed | 14912 | +| total_timesteps | 21192704 | +| train/ | | +| approx_kl | 0.013251939 | +| clip_fraction | 0.329 | +| clip_range | 0.0697 | +| entropy_loss | -6.36 | +| explained_variance | 0.424 | +| learning_rate | 4.5e-05 | +| loss | -0.0392 | +| n_updates | 57208 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000194 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1421 | +| iterations | 10349 | +| time_elapsed | 14914 | +| total_timesteps | 21194752 | +| train/ | | +| approx_kl | 0.0166868 | +| clip_fraction | 0.311 | +| clip_range | 0.0697 | +| entropy_loss | -6.44 | +| explained_variance | 0.35 | +| learning_rate | 4.5e-05 | +| loss | -0.0276 | +| n_updates | 57212 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.00028 | +--------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1421 | +| iterations | 10350 | +| time_elapsed | 14915 | +| total_timesteps | 21196800 | +| train/ | | +| approx_kl | 0.0144874435 | +| clip_fraction | 0.391 | +| clip_range | 0.0697 | +| entropy_loss | -6.57 | +| explained_variance | 0.721 | +| learning_rate | 4.5e-05 | +| loss | -0.0428 | +| n_updates | 57216 | +| policy_gradient_loss | -0.0253 | +| value_loss | 6.56e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1421 | +| iterations | 10351 | +| time_elapsed | 14917 | +| total_timesteps | 21198848 | +| train/ | | +| approx_kl | 0.016192287 | +| clip_fraction | 0.342 | +| clip_range | 0.0697 | +| entropy_loss | -6.74 | +| explained_variance | -0.165 | +| learning_rate | 4.5e-05 | +| loss | -0.0353 | +| n_updates | 57220 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000111 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1421 | +| iterations | 10352 | +| time_elapsed | 14918 | +| total_timesteps | 21200896 | +| train/ | | +| approx_kl | 0.013231087 | +| clip_fraction | 0.337 | +| clip_range | 0.0697 | +| entropy_loss | -6.76 | +| explained_variance | 0.201 | +| learning_rate | 4.5e-05 | +| loss | -0.0294 | +| n_updates | 57224 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000192 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1421 | +| iterations | 10353 | +| time_elapsed | 14919 | +| total_timesteps | 21202944 | +| train/ | | +| approx_kl | 0.013170356 | +| clip_fraction | 0.33 | +| clip_range | 0.0697 | +| entropy_loss | -6.47 | +| explained_variance | 0.452 | +| learning_rate | 4.5e-05 | +| loss | -0.0287 | +| n_updates | 57228 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000216 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1421 | +| iterations | 10354 | +| time_elapsed | 14921 | +| total_timesteps | 21204992 | +| train/ | | +| approx_kl | 0.011978975 | +| clip_fraction | 0.328 | +| clip_range | 0.0697 | +| entropy_loss | -6.46 | +| explained_variance | 0.269 | +| learning_rate | 4.5e-05 | +| loss | -0.0284 | +| n_updates | 57232 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000277 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1421 | +| iterations | 10355 | +| time_elapsed | 14922 | +| total_timesteps | 21207040 | +| train/ | | +| approx_kl | 0.011689792 | +| clip_fraction | 0.337 | +| clip_range | 0.0697 | +| entropy_loss | -6.5 | +| explained_variance | 0.307 | +| learning_rate | 4.5e-05 | +| loss | -0.0266 | +| n_updates | 57236 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.0003 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1421 | +| iterations | 10356 | +| time_elapsed | 14924 | +| total_timesteps | 21209088 | +| train/ | | +| approx_kl | 0.01037306 | +| clip_fraction | 0.324 | +| clip_range | 0.0697 | +| entropy_loss | -6.67 | +| explained_variance | 0.39 | +| learning_rate | 4.5e-05 | +| loss | -0.028 | +| n_updates | 57240 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.00019 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1421 | +| iterations | 10357 | +| time_elapsed | 14925 | +| total_timesteps | 21211136 | +| train/ | | +| approx_kl | 0.013996761 | +| clip_fraction | 0.338 | +| clip_range | 0.0697 | +| entropy_loss | -6.51 | +| explained_variance | 0.281 | +| learning_rate | 4.5e-05 | +| loss | -0.0241 | +| n_updates | 57244 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000358 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1421 | +| iterations | 10358 | +| time_elapsed | 14927 | +| total_timesteps | 21213184 | +| train/ | | +| approx_kl | 0.011974915 | +| clip_fraction | 0.31 | +| clip_range | 0.0697 | +| entropy_loss | -6.27 | +| explained_variance | 0.398 | +| learning_rate | 4.5e-05 | +| loss | -0.0249 | +| n_updates | 57248 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000258 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1421 | +| iterations | 10359 | +| time_elapsed | 14928 | +| total_timesteps | 21215232 | +| train/ | | +| approx_kl | 0.013544561 | +| clip_fraction | 0.305 | +| clip_range | 0.0697 | +| entropy_loss | -5.9 | +| explained_variance | 0.644 | +| learning_rate | 4.5e-05 | +| loss | -0.0296 | +| n_updates | 57252 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000186 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.39 | +| time/ | | +| fps | 1421 | +| iterations | 10360 | +| time_elapsed | 14929 | +| total_timesteps | 21217280 | +| train/ | | +| approx_kl | 0.014181714 | +| clip_fraction | 0.309 | +| clip_range | 0.0697 | +| entropy_loss | -6.24 | +| explained_variance | 0.382 | +| learning_rate | 4.5e-05 | +| loss | -0.0181 | +| n_updates | 57256 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.00024 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.395 | +| time/ | | +| fps | 1421 | +| iterations | 10361 | +| time_elapsed | 14931 | +| total_timesteps | 21219328 | +| train/ | | +| approx_kl | 0.015234837 | +| clip_fraction | 0.333 | +| clip_range | 0.0697 | +| entropy_loss | -6.31 | +| explained_variance | 0.289 | +| learning_rate | 4.5e-05 | +| loss | -0.0293 | +| n_updates | 57260 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000226 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.391 | +| time/ | | +| fps | 1421 | +| iterations | 10362 | +| time_elapsed | 14932 | +| total_timesteps | 21221376 | +| train/ | | +| approx_kl | 0.014058913 | +| clip_fraction | 0.353 | +| clip_range | 0.0697 | +| entropy_loss | -6.6 | +| explained_variance | 0.293 | +| learning_rate | 4.5e-05 | +| loss | -0.0293 | +| n_updates | 57264 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000205 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.391 | +| time/ | | +| fps | 1421 | +| iterations | 10363 | +| time_elapsed | 14934 | +| total_timesteps | 21223424 | +| train/ | | +| approx_kl | 0.012783395 | +| clip_fraction | 0.326 | +| clip_range | 0.0697 | +| entropy_loss | -7.01 | +| explained_variance | -0.0653 | +| learning_rate | 4.5e-05 | +| loss | -0.0334 | +| n_updates | 57268 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000163 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.393 | +| time/ | | +| fps | 1421 | +| iterations | 10364 | +| time_elapsed | 14935 | +| total_timesteps | 21225472 | +| train/ | | +| approx_kl | 0.0106495805 | +| clip_fraction | 0.3 | +| clip_range | 0.0697 | +| entropy_loss | -6.53 | +| explained_variance | 0.246 | +| learning_rate | 4.5e-05 | +| loss | -0.0155 | +| n_updates | 57272 | +| policy_gradient_loss | -0.0136 | +| value_loss | 0.000404 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.396 | +| time/ | | +| fps | 1421 | +| iterations | 10365 | +| time_elapsed | 14937 | +| total_timesteps | 21227520 | +| train/ | | +| approx_kl | 0.014241843 | +| clip_fraction | 0.342 | +| clip_range | 0.0697 | +| entropy_loss | -6.03 | +| explained_variance | 0.359 | +| learning_rate | 4.5e-05 | +| loss | -0.0292 | +| n_updates | 57276 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000311 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.396 | +| time/ | | +| fps | 1421 | +| iterations | 10366 | +| time_elapsed | 14938 | +| total_timesteps | 21229568 | +| train/ | | +| approx_kl | 0.01114651 | +| clip_fraction | 0.334 | +| clip_range | 0.0697 | +| entropy_loss | -6.62 | +| explained_variance | 0.127 | +| learning_rate | 4.5e-05 | +| loss | -0.0299 | +| n_updates | 57280 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000216 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.401 | +| time/ | | +| fps | 1421 | +| iterations | 10367 | +| time_elapsed | 14940 | +| total_timesteps | 21231616 | +| train/ | | +| approx_kl | 0.013289569 | +| clip_fraction | 0.363 | +| clip_range | 0.0697 | +| entropy_loss | -6.01 | +| explained_variance | 0.435 | +| learning_rate | 4.5e-05 | +| loss | -0.0299 | +| n_updates | 57284 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.00024 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.4 | +| time/ | | +| fps | 1421 | +| iterations | 10368 | +| time_elapsed | 14941 | +| total_timesteps | 21233664 | +| train/ | | +| approx_kl | 0.014138343 | +| clip_fraction | 0.35 | +| clip_range | 0.0697 | +| entropy_loss | -5.92 | +| explained_variance | 0.314 | +| learning_rate | 4.5e-05 | +| loss | -0.0266 | +| n_updates | 57288 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000289 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.4 | +| time/ | | +| fps | 1421 | +| iterations | 10369 | +| time_elapsed | 14942 | +| total_timesteps | 21235712 | +| train/ | | +| approx_kl | 0.01484099 | +| clip_fraction | 0.375 | +| clip_range | 0.0697 | +| entropy_loss | -6.64 | +| explained_variance | 0.332 | +| learning_rate | 4.5e-05 | +| loss | -0.0332 | +| n_updates | 57292 | +| policy_gradient_loss | -0.022 | +| value_loss | 0.000181 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.399 | +| time/ | | +| fps | 1421 | +| iterations | 10370 | +| time_elapsed | 14944 | +| total_timesteps | 21237760 | +| train/ | | +| approx_kl | 0.014204845 | +| clip_fraction | 0.348 | +| clip_range | 0.0697 | +| entropy_loss | -6.86 | +| explained_variance | 0.0256 | +| learning_rate | 4.5e-05 | +| loss | -0.0357 | +| n_updates | 57296 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000206 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.399 | +| time/ | | +| fps | 1421 | +| iterations | 10371 | +| time_elapsed | 14945 | +| total_timesteps | 21239808 | +| train/ | | +| approx_kl | 0.0144677805 | +| clip_fraction | 0.353 | +| clip_range | 0.0697 | +| entropy_loss | -6.71 | +| explained_variance | 0.23 | +| learning_rate | 4.5e-05 | +| loss | -0.0301 | +| n_updates | 57300 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000167 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.396 | +| time/ | | +| fps | 1421 | +| iterations | 10372 | +| time_elapsed | 14947 | +| total_timesteps | 21241856 | +| train/ | | +| approx_kl | 0.01315626 | +| clip_fraction | 0.339 | +| clip_range | 0.0697 | +| entropy_loss | -6.73 | +| explained_variance | 0.288 | +| learning_rate | 4.5e-05 | +| loss | -0.0366 | +| n_updates | 57304 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000159 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.397 | +| time/ | | +| fps | 1421 | +| iterations | 10373 | +| time_elapsed | 14948 | +| total_timesteps | 21243904 | +| train/ | | +| approx_kl | 0.01074256 | +| clip_fraction | 0.33 | +| clip_range | 0.0697 | +| entropy_loss | -6.49 | +| explained_variance | 0.485 | +| learning_rate | 4.5e-05 | +| loss | -0.0286 | +| n_updates | 57308 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000154 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.395 | +| time/ | | +| fps | 1421 | +| iterations | 10374 | +| time_elapsed | 14950 | +| total_timesteps | 21245952 | +| train/ | | +| approx_kl | 0.013934919 | +| clip_fraction | 0.341 | +| clip_range | 0.0697 | +| entropy_loss | -6.91 | +| explained_variance | -0.283 | +| learning_rate | 4.5e-05 | +| loss | -0.0331 | +| n_updates | 57312 | +| policy_gradient_loss | -0.0228 | +| value_loss | 9.07e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.396 | +| time/ | | +| fps | 1421 | +| iterations | 10375 | +| time_elapsed | 14951 | +| total_timesteps | 21248000 | +| train/ | | +| approx_kl | 0.013596542 | +| clip_fraction | 0.34 | +| clip_range | 0.0697 | +| entropy_loss | -6.31 | +| explained_variance | 0.553 | +| learning_rate | 4.5e-05 | +| loss | -0.0336 | +| n_updates | 57316 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000153 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.396 | +| time/ | | +| fps | 1421 | +| iterations | 10376 | +| time_elapsed | 14953 | +| total_timesteps | 21250048 | +| train/ | | +| approx_kl | 0.013744563 | +| clip_fraction | 0.317 | +| clip_range | 0.0697 | +| entropy_loss | -6.47 | +| explained_variance | 0.327 | +| learning_rate | 4.5e-05 | +| loss | -0.0262 | +| n_updates | 57320 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000217 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.404 | +| time/ | | +| fps | 1421 | +| iterations | 10377 | +| time_elapsed | 14954 | +| total_timesteps | 21252096 | +| train/ | | +| approx_kl | 0.013400459 | +| clip_fraction | 0.352 | +| clip_range | 0.0697 | +| entropy_loss | -6.41 | +| explained_variance | 0.343 | +| learning_rate | 4.5e-05 | +| loss | -0.0338 | +| n_updates | 57324 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.403 | +| time/ | | +| fps | 1421 | +| iterations | 10378 | +| time_elapsed | 14956 | +| total_timesteps | 21254144 | +| train/ | | +| approx_kl | 0.012909848 | +| clip_fraction | 0.303 | +| clip_range | 0.0697 | +| entropy_loss | -6.67 | +| explained_variance | 0.3 | +| learning_rate | 4.5e-05 | +| loss | -0.026 | +| n_updates | 57328 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000283 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.405 | +| time/ | | +| fps | 1421 | +| iterations | 10379 | +| time_elapsed | 14957 | +| total_timesteps | 21256192 | +| train/ | | +| approx_kl | 0.0124851735 | +| clip_fraction | 0.343 | +| clip_range | 0.0697 | +| entropy_loss | -6.53 | +| explained_variance | 0.151 | +| learning_rate | 4.5e-05 | +| loss | -0.0332 | +| n_updates | 57332 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000209 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.404 | +| time/ | | +| fps | 1421 | +| iterations | 10380 | +| time_elapsed | 14958 | +| total_timesteps | 21258240 | +| train/ | | +| approx_kl | 0.014470044 | +| clip_fraction | 0.35 | +| clip_range | 0.0697 | +| entropy_loss | -6.48 | +| explained_variance | 0.631 | +| learning_rate | 4.5e-05 | +| loss | -0.0396 | +| n_updates | 57336 | +| policy_gradient_loss | -0.0232 | +| value_loss | 8.1e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.402 | +| time/ | | +| fps | 1421 | +| iterations | 10381 | +| time_elapsed | 14960 | +| total_timesteps | 21260288 | +| train/ | | +| approx_kl | 0.016094983 | +| clip_fraction | 0.358 | +| clip_range | 0.0697 | +| entropy_loss | -6 | +| explained_variance | 0.595 | +| learning_rate | 4.5e-05 | +| loss | -0.0282 | +| n_updates | 57340 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000186 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.393 | +| time/ | | +| fps | 1421 | +| iterations | 10382 | +| time_elapsed | 14961 | +| total_timesteps | 21262336 | +| train/ | | +| approx_kl | 0.015547074 | +| clip_fraction | 0.328 | +| clip_range | 0.0697 | +| entropy_loss | -6.39 | +| explained_variance | 0.422 | +| learning_rate | 4.5e-05 | +| loss | -0.0336 | +| n_updates | 57344 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000167 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.391 | +| time/ | | +| fps | 1421 | +| iterations | 10383 | +| time_elapsed | 14963 | +| total_timesteps | 21264384 | +| train/ | | +| approx_kl | 0.012544294 | +| clip_fraction | 0.33 | +| clip_range | 0.0697 | +| entropy_loss | -6.63 | +| explained_variance | 0.478 | +| learning_rate | 4.5e-05 | +| loss | -0.028 | +| n_updates | 57348 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000185 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.391 | +| time/ | | +| fps | 1421 | +| iterations | 10384 | +| time_elapsed | 14964 | +| total_timesteps | 21266432 | +| train/ | | +| approx_kl | 0.013495157 | +| clip_fraction | 0.319 | +| clip_range | 0.0697 | +| entropy_loss | -6.37 | +| explained_variance | 0.529 | +| learning_rate | 4.49e-05 | +| loss | -0.0349 | +| n_updates | 57352 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000206 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.394 | +| time/ | | +| fps | 1421 | +| iterations | 10385 | +| time_elapsed | 14966 | +| total_timesteps | 21268480 | +| train/ | | +| approx_kl | 0.01312875 | +| clip_fraction | 0.357 | +| clip_range | 0.0697 | +| entropy_loss | -6.88 | +| explained_variance | 0.0375 | +| learning_rate | 4.49e-05 | +| loss | -0.0289 | +| n_updates | 57356 | +| policy_gradient_loss | -0.0215 | +| value_loss | 8.39e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.394 | +| time/ | | +| fps | 1421 | +| iterations | 10386 | +| time_elapsed | 14967 | +| total_timesteps | 21270528 | +| train/ | | +| approx_kl | 0.011959041 | +| clip_fraction | 0.32 | +| clip_range | 0.0697 | +| entropy_loss | -7.2 | +| explained_variance | 0.0766 | +| learning_rate | 4.49e-05 | +| loss | -0.0336 | +| n_updates | 57360 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000244 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.394 | +| time/ | | +| fps | 1421 | +| iterations | 10387 | +| time_elapsed | 14968 | +| total_timesteps | 21272576 | +| train/ | | +| approx_kl | 0.0132621955 | +| clip_fraction | 0.356 | +| clip_range | 0.0697 | +| entropy_loss | -6.45 | +| explained_variance | 0.701 | +| learning_rate | 4.49e-05 | +| loss | -0.0343 | +| n_updates | 57364 | +| policy_gradient_loss | -0.0229 | +| value_loss | 7.03e-05 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.395 | +| time/ | | +| fps | 1421 | +| iterations | 10388 | +| time_elapsed | 14970 | +| total_timesteps | 21274624 | +| train/ | | +| approx_kl | 0.0146655515 | +| clip_fraction | 0.354 | +| clip_range | 0.0697 | +| entropy_loss | -6.87 | +| explained_variance | -0.1 | +| learning_rate | 4.49e-05 | +| loss | -0.0331 | +| n_updates | 57368 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000137 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.389 | +| time/ | | +| fps | 1421 | +| iterations | 10389 | +| time_elapsed | 14971 | +| total_timesteps | 21276672 | +| train/ | | +| approx_kl | 0.011526024 | +| clip_fraction | 0.291 | +| clip_range | 0.0697 | +| entropy_loss | -6.43 | +| explained_variance | 0.267 | +| learning_rate | 4.49e-05 | +| loss | -0.0231 | +| n_updates | 57372 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000438 | +----------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.386 | +| time/ | | +| fps | 1421 | +| iterations | 10390 | +| time_elapsed | 14973 | +| total_timesteps | 21278720 | +| train/ | | +| approx_kl | 0.014493 | +| clip_fraction | 0.35 | +| clip_range | 0.0697 | +| entropy_loss | -5.87 | +| explained_variance | 0.655 | +| learning_rate | 4.49e-05 | +| loss | -0.0378 | +| n_updates | 57376 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000114 | +-------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.386 | +| time/ | | +| fps | 1421 | +| iterations | 10391 | +| time_elapsed | 14974 | +| total_timesteps | 21280768 | +| train/ | | +| approx_kl | 0.017133504 | +| clip_fraction | 0.346 | +| clip_range | 0.0697 | +| entropy_loss | -5.86 | +| explained_variance | 0.641 | +| learning_rate | 4.49e-05 | +| loss | -0.0267 | +| n_updates | 57380 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000158 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.386 | +| time/ | | +| fps | 1421 | +| iterations | 10392 | +| time_elapsed | 14976 | +| total_timesteps | 21282816 | +| train/ | | +| approx_kl | 0.014073264 | +| clip_fraction | 0.374 | +| clip_range | 0.0697 | +| entropy_loss | -6.66 | +| explained_variance | 0.19 | +| learning_rate | 4.49e-05 | +| loss | -0.0402 | +| n_updates | 57384 | +| policy_gradient_loss | -0.0225 | +| value_loss | 8e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.386 | +| time/ | | +| fps | 1421 | +| iterations | 10393 | +| time_elapsed | 14977 | +| total_timesteps | 21284864 | +| train/ | | +| approx_kl | 0.0107676275 | +| clip_fraction | 0.333 | +| clip_range | 0.0697 | +| entropy_loss | -6.94 | +| explained_variance | 0.359 | +| learning_rate | 4.49e-05 | +| loss | -0.029 | +| n_updates | 57388 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000118 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1421 | +| iterations | 10394 | +| time_elapsed | 14979 | +| total_timesteps | 21286912 | +| train/ | | +| approx_kl | 0.011520842 | +| clip_fraction | 0.318 | +| clip_range | 0.0697 | +| entropy_loss | -6.94 | +| explained_variance | 0.196 | +| learning_rate | 4.49e-05 | +| loss | -0.026 | +| n_updates | 57392 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000222 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.385 | +| time/ | | +| fps | 1421 | +| iterations | 10395 | +| time_elapsed | 14980 | +| total_timesteps | 21288960 | +| train/ | | +| approx_kl | 0.01282378 | +| clip_fraction | 0.343 | +| clip_range | 0.0697 | +| entropy_loss | -6.97 | +| explained_variance | 0.199 | +| learning_rate | 4.49e-05 | +| loss | -0.0355 | +| n_updates | 57396 | +| policy_gradient_loss | -0.0199 | +| value_loss | 8.74e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1421 | +| iterations | 10396 | +| time_elapsed | 14982 | +| total_timesteps | 21291008 | +| train/ | | +| approx_kl | 0.015510479 | +| clip_fraction | 0.321 | +| clip_range | 0.0697 | +| entropy_loss | -6.21 | +| explained_variance | 0.824 | +| learning_rate | 4.49e-05 | +| loss | -0.0335 | +| n_updates | 57400 | +| policy_gradient_loss | -0.0194 | +| value_loss | 6.84e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1421 | +| iterations | 10397 | +| time_elapsed | 14983 | +| total_timesteps | 21293056 | +| train/ | | +| approx_kl | 0.014094027 | +| clip_fraction | 0.34 | +| clip_range | 0.0697 | +| entropy_loss | -6.55 | +| explained_variance | 0.367 | +| learning_rate | 4.49e-05 | +| loss | -0.0328 | +| n_updates | 57404 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000101 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1421 | +| iterations | 10398 | +| time_elapsed | 14985 | +| total_timesteps | 21295104 | +| train/ | | +| approx_kl | 0.012151387 | +| clip_fraction | 0.32 | +| clip_range | 0.0697 | +| entropy_loss | -6.89 | +| explained_variance | 0.209 | +| learning_rate | 4.49e-05 | +| loss | -0.0274 | +| n_updates | 57408 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000108 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1421 | +| iterations | 10399 | +| time_elapsed | 14986 | +| total_timesteps | 21297152 | +| train/ | | +| approx_kl | 0.015713409 | +| clip_fraction | 0.312 | +| clip_range | 0.0697 | +| entropy_loss | -6.59 | +| explained_variance | 0.481 | +| learning_rate | 4.49e-05 | +| loss | -0.031 | +| n_updates | 57412 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.00019 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1421 | +| iterations | 10400 | +| time_elapsed | 14988 | +| total_timesteps | 21299200 | +| train/ | | +| approx_kl | 0.013056427 | +| clip_fraction | 0.366 | +| clip_range | 0.0697 | +| entropy_loss | -6.26 | +| explained_variance | 0.421 | +| learning_rate | 4.49e-05 | +| loss | -0.0316 | +| n_updates | 57416 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1421 | +| iterations | 10401 | +| time_elapsed | 14989 | +| total_timesteps | 21301248 | +| train/ | | +| approx_kl | 0.010954513 | +| clip_fraction | 0.333 | +| clip_range | 0.0697 | +| entropy_loss | -6.92 | +| explained_variance | 0.321 | +| learning_rate | 4.49e-05 | +| loss | -0.0313 | +| n_updates | 57420 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000144 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1421 | +| iterations | 10402 | +| time_elapsed | 14990 | +| total_timesteps | 21303296 | +| train/ | | +| approx_kl | 0.011706589 | +| clip_fraction | 0.309 | +| clip_range | 0.0697 | +| entropy_loss | -6.43 | +| explained_variance | 0.48 | +| learning_rate | 4.49e-05 | +| loss | -0.0248 | +| n_updates | 57424 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.00023 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1421 | +| iterations | 10403 | +| time_elapsed | 14992 | +| total_timesteps | 21305344 | +| train/ | | +| approx_kl | 0.012302646 | +| clip_fraction | 0.335 | +| clip_range | 0.0697 | +| entropy_loss | -6.57 | +| explained_variance | 0.419 | +| learning_rate | 4.49e-05 | +| loss | -0.0343 | +| n_updates | 57428 | +| policy_gradient_loss | -0.0208 | +| value_loss | 9.38e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1421 | +| iterations | 10404 | +| time_elapsed | 14993 | +| total_timesteps | 21307392 | +| train/ | | +| approx_kl | 0.0121631995 | +| clip_fraction | 0.325 | +| clip_range | 0.0697 | +| entropy_loss | -6.51 | +| explained_variance | 0.345 | +| learning_rate | 4.49e-05 | +| loss | -0.0171 | +| n_updates | 57432 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000169 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1421 | +| iterations | 10405 | +| time_elapsed | 14995 | +| total_timesteps | 21309440 | +| train/ | | +| approx_kl | 0.013127926 | +| clip_fraction | 0.334 | +| clip_range | 0.0697 | +| entropy_loss | -6.48 | +| explained_variance | 0.275 | +| learning_rate | 4.49e-05 | +| loss | -0.0246 | +| n_updates | 57436 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000303 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1421 | +| iterations | 10406 | +| time_elapsed | 14996 | +| total_timesteps | 21311488 | +| train/ | | +| approx_kl | 0.009935573 | +| clip_fraction | 0.312 | +| clip_range | 0.0697 | +| entropy_loss | -6.6 | +| explained_variance | 0.278 | +| learning_rate | 4.49e-05 | +| loss | -0.0243 | +| n_updates | 57440 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000202 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1421 | +| iterations | 10407 | +| time_elapsed | 14998 | +| total_timesteps | 21313536 | +| train/ | | +| approx_kl | 0.013036154 | +| clip_fraction | 0.352 | +| clip_range | 0.0697 | +| entropy_loss | -6.95 | +| explained_variance | -0.399 | +| learning_rate | 4.49e-05 | +| loss | -0.031 | +| n_updates | 57444 | +| policy_gradient_loss | -0.0218 | +| value_loss | 8.22e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1421 | +| iterations | 10408 | +| time_elapsed | 14999 | +| total_timesteps | 21315584 | +| train/ | | +| approx_kl | 0.016191516 | +| clip_fraction | 0.32 | +| clip_range | 0.0697 | +| entropy_loss | -6.87 | +| explained_variance | 0.156 | +| learning_rate | 4.49e-05 | +| loss | -0.0244 | +| n_updates | 57448 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000165 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1421 | +| iterations | 10409 | +| time_elapsed | 15001 | +| total_timesteps | 21317632 | +| train/ | | +| approx_kl | 0.0132123865 | +| clip_fraction | 0.345 | +| clip_range | 0.0697 | +| entropy_loss | -6.74 | +| explained_variance | 0.236 | +| learning_rate | 4.49e-05 | +| loss | -0.0275 | +| n_updates | 57452 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000178 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1421 | +| iterations | 10410 | +| time_elapsed | 15002 | +| total_timesteps | 21319680 | +| train/ | | +| approx_kl | 0.009905014 | +| clip_fraction | 0.304 | +| clip_range | 0.0697 | +| entropy_loss | -6.37 | +| explained_variance | 0.52 | +| learning_rate | 4.49e-05 | +| loss | -0.0297 | +| n_updates | 57456 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.00018 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1421 | +| iterations | 10411 | +| time_elapsed | 15003 | +| total_timesteps | 21321728 | +| train/ | | +| approx_kl | 0.011477275 | +| clip_fraction | 0.325 | +| clip_range | 0.0697 | +| entropy_loss | -6.23 | +| explained_variance | 0.382 | +| learning_rate | 4.49e-05 | +| loss | -0.0282 | +| n_updates | 57460 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000163 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1421 | +| iterations | 10412 | +| time_elapsed | 15005 | +| total_timesteps | 21323776 | +| train/ | | +| approx_kl | 0.011406647 | +| clip_fraction | 0.291 | +| clip_range | 0.0697 | +| entropy_loss | -6.38 | +| explained_variance | 0.468 | +| learning_rate | 4.49e-05 | +| loss | -0.0279 | +| n_updates | 57464 | +| policy_gradient_loss | -0.0148 | +| value_loss | 0.000233 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1421 | +| iterations | 10413 | +| time_elapsed | 15006 | +| total_timesteps | 21325824 | +| train/ | | +| approx_kl | 0.015436832 | +| clip_fraction | 0.391 | +| clip_range | 0.0697 | +| entropy_loss | -6.19 | +| explained_variance | 0.661 | +| learning_rate | 4.49e-05 | +| loss | -0.0418 | +| n_updates | 57468 | +| policy_gradient_loss | -0.0253 | +| value_loss | 7.82e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1421 | +| iterations | 10414 | +| time_elapsed | 15008 | +| total_timesteps | 21327872 | +| train/ | | +| approx_kl | 0.015079255 | +| clip_fraction | 0.357 | +| clip_range | 0.0697 | +| entropy_loss | -6.91 | +| explained_variance | -0.333 | +| learning_rate | 4.49e-05 | +| loss | -0.0385 | +| n_updates | 57472 | +| policy_gradient_loss | -0.0219 | +| value_loss | 0.000106 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1421 | +| iterations | 10415 | +| time_elapsed | 15009 | +| total_timesteps | 21329920 | +| train/ | | +| approx_kl | 0.013138079 | +| clip_fraction | 0.352 | +| clip_range | 0.0697 | +| entropy_loss | -6.83 | +| explained_variance | -0.0192 | +| learning_rate | 4.49e-05 | +| loss | -0.03 | +| n_updates | 57476 | +| policy_gradient_loss | -0.0198 | +| value_loss | 9.11e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1421 | +| iterations | 10416 | +| time_elapsed | 15011 | +| total_timesteps | 21331968 | +| train/ | | +| approx_kl | 0.016481042 | +| clip_fraction | 0.332 | +| clip_range | 0.0697 | +| entropy_loss | -6.58 | +| explained_variance | 0.338 | +| learning_rate | 4.49e-05 | +| loss | -0.028 | +| n_updates | 57480 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000159 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1421 | +| iterations | 10417 | +| time_elapsed | 15012 | +| total_timesteps | 21334016 | +| train/ | | +| approx_kl | 0.0134519655 | +| clip_fraction | 0.325 | +| clip_range | 0.0697 | +| entropy_loss | -6.69 | +| explained_variance | 0.254 | +| learning_rate | 4.49e-05 | +| loss | -0.0254 | +| n_updates | 57484 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000231 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1421 | +| iterations | 10418 | +| time_elapsed | 15014 | +| total_timesteps | 21336064 | +| train/ | | +| approx_kl | 0.014013173 | +| clip_fraction | 0.335 | +| clip_range | 0.0697 | +| entropy_loss | -6.69 | +| explained_variance | 0.229 | +| learning_rate | 4.49e-05 | +| loss | -0.0281 | +| n_updates | 57488 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000128 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1421 | +| iterations | 10419 | +| time_elapsed | 15015 | +| total_timesteps | 21338112 | +| train/ | | +| approx_kl | 0.011589024 | +| clip_fraction | 0.337 | +| clip_range | 0.0697 | +| entropy_loss | -6.69 | +| explained_variance | 0.384 | +| learning_rate | 4.49e-05 | +| loss | -0.0267 | +| n_updates | 57492 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000151 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1421 | +| iterations | 10420 | +| time_elapsed | 15017 | +| total_timesteps | 21340160 | +| train/ | | +| approx_kl | 0.015376069 | +| clip_fraction | 0.355 | +| clip_range | 0.0697 | +| entropy_loss | -6.99 | +| explained_variance | -0.2 | +| learning_rate | 4.49e-05 | +| loss | -0.0352 | +| n_updates | 57496 | +| policy_gradient_loss | -0.0208 | +| value_loss | 8.53e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1421 | +| iterations | 10421 | +| time_elapsed | 15018 | +| total_timesteps | 21342208 | +| train/ | | +| approx_kl | 0.014854115 | +| clip_fraction | 0.31 | +| clip_range | 0.0697 | +| entropy_loss | -6.53 | +| explained_variance | 0.484 | +| learning_rate | 4.49e-05 | +| loss | -0.0313 | +| n_updates | 57500 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000154 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1421 | +| iterations | 10422 | +| time_elapsed | 15020 | +| total_timesteps | 21344256 | +| train/ | | +| approx_kl | 0.0126045495 | +| clip_fraction | 0.303 | +| clip_range | 0.0697 | +| entropy_loss | -6.34 | +| explained_variance | 0.358 | +| learning_rate | 4.49e-05 | +| loss | -0.0279 | +| n_updates | 57504 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000316 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1421 | +| iterations | 10423 | +| time_elapsed | 15021 | +| total_timesteps | 21346304 | +| train/ | | +| approx_kl | 0.011497093 | +| clip_fraction | 0.321 | +| clip_range | 0.0697 | +| entropy_loss | -6.04 | +| explained_variance | 0.549 | +| learning_rate | 4.49e-05 | +| loss | -0.029 | +| n_updates | 57508 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1421 | +| iterations | 10424 | +| time_elapsed | 15023 | +| total_timesteps | 21348352 | +| train/ | | +| approx_kl | 0.013896434 | +| clip_fraction | 0.312 | +| clip_range | 0.0697 | +| entropy_loss | -6.52 | +| explained_variance | 0.238 | +| learning_rate | 4.49e-05 | +| loss | -0.0315 | +| n_updates | 57512 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000194 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1421 | +| iterations | 10425 | +| time_elapsed | 15024 | +| total_timesteps | 21350400 | +| train/ | | +| approx_kl | 0.015032457 | +| clip_fraction | 0.329 | +| clip_range | 0.0697 | +| entropy_loss | -6.71 | +| explained_variance | 0.368 | +| learning_rate | 4.49e-05 | +| loss | -0.0284 | +| n_updates | 57516 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000116 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1421 | +| iterations | 10426 | +| time_elapsed | 15025 | +| total_timesteps | 21352448 | +| train/ | | +| approx_kl | 0.011384372 | +| clip_fraction | 0.313 | +| clip_range | 0.0697 | +| entropy_loss | -6.32 | +| explained_variance | 0.512 | +| learning_rate | 4.49e-05 | +| loss | -0.0308 | +| n_updates | 57520 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000195 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1421 | +| iterations | 10427 | +| time_elapsed | 15027 | +| total_timesteps | 21354496 | +| train/ | | +| approx_kl | 0.014566116 | +| clip_fraction | 0.358 | +| clip_range | 0.0697 | +| entropy_loss | -6.64 | +| explained_variance | 0.221 | +| learning_rate | 4.49e-05 | +| loss | -0.0338 | +| n_updates | 57524 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.00015 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1421 | +| iterations | 10428 | +| time_elapsed | 15028 | +| total_timesteps | 21356544 | +| train/ | | +| approx_kl | 0.016332382 | +| clip_fraction | 0.355 | +| clip_range | 0.0697 | +| entropy_loss | -7.01 | +| explained_variance | -0.281 | +| learning_rate | 4.49e-05 | +| loss | -0.0327 | +| n_updates | 57528 | +| policy_gradient_loss | -0.0219 | +| value_loss | 8.59e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1421 | +| iterations | 10429 | +| time_elapsed | 15030 | +| total_timesteps | 21358592 | +| train/ | | +| approx_kl | 0.015008905 | +| clip_fraction | 0.357 | +| clip_range | 0.0697 | +| entropy_loss | -5.77 | +| explained_variance | 0.652 | +| learning_rate | 4.49e-05 | +| loss | -0.0331 | +| n_updates | 57532 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.00012 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1421 | +| iterations | 10430 | +| time_elapsed | 15031 | +| total_timesteps | 21360640 | +| train/ | | +| approx_kl | 0.013100937 | +| clip_fraction | 0.335 | +| clip_range | 0.0697 | +| entropy_loss | -6.69 | +| explained_variance | -0.0164 | +| learning_rate | 4.49e-05 | +| loss | -0.0325 | +| n_updates | 57536 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000165 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1421 | +| iterations | 10431 | +| time_elapsed | 15033 | +| total_timesteps | 21362688 | +| train/ | | +| approx_kl | 0.013907911 | +| clip_fraction | 0.332 | +| clip_range | 0.0697 | +| entropy_loss | -6.69 | +| explained_variance | 0.549 | +| learning_rate | 4.49e-05 | +| loss | -0.0324 | +| n_updates | 57540 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000119 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.315 | +| time/ | | +| fps | 1421 | +| iterations | 10432 | +| time_elapsed | 15034 | +| total_timesteps | 21364736 | +| train/ | | +| approx_kl | 0.013935465 | +| clip_fraction | 0.319 | +| clip_range | 0.0697 | +| entropy_loss | -7.12 | +| explained_variance | -0.0877 | +| learning_rate | 4.49e-05 | +| loss | -0.0268 | +| n_updates | 57544 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000223 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.315 | +| time/ | | +| fps | 1421 | +| iterations | 10433 | +| time_elapsed | 15036 | +| total_timesteps | 21366784 | +| train/ | | +| approx_kl | 0.011541985 | +| clip_fraction | 0.341 | +| clip_range | 0.0697 | +| entropy_loss | -6.17 | +| explained_variance | 0.743 | +| learning_rate | 4.49e-05 | +| loss | -0.0278 | +| n_updates | 57548 | +| policy_gradient_loss | -0.0188 | +| value_loss | 9.61e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1421 | +| iterations | 10434 | +| time_elapsed | 15037 | +| total_timesteps | 21368832 | +| train/ | | +| approx_kl | 0.013602817 | +| clip_fraction | 0.325 | +| clip_range | 0.0697 | +| entropy_loss | -6.61 | +| explained_variance | -0.114 | +| learning_rate | 4.49e-05 | +| loss | -0.0293 | +| n_updates | 57552 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000176 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1421 | +| iterations | 10435 | +| time_elapsed | 15038 | +| total_timesteps | 21370880 | +| train/ | | +| approx_kl | 0.013109781 | +| clip_fraction | 0.319 | +| clip_range | 0.0697 | +| entropy_loss | -7.06 | +| explained_variance | -0.165 | +| learning_rate | 4.49e-05 | +| loss | -0.0306 | +| n_updates | 57556 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000114 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1421 | +| iterations | 10436 | +| time_elapsed | 15040 | +| total_timesteps | 21372928 | +| train/ | | +| approx_kl | 0.015034199 | +| clip_fraction | 0.348 | +| clip_range | 0.0697 | +| entropy_loss | -6.39 | +| explained_variance | 0.531 | +| learning_rate | 4.49e-05 | +| loss | -0.0326 | +| n_updates | 57560 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000102 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1421 | +| iterations | 10437 | +| time_elapsed | 15041 | +| total_timesteps | 21374976 | +| train/ | | +| approx_kl | 0.012849727 | +| clip_fraction | 0.31 | +| clip_range | 0.0697 | +| entropy_loss | -6.41 | +| explained_variance | 0.387 | +| learning_rate | 4.49e-05 | +| loss | -0.0219 | +| n_updates | 57564 | +| policy_gradient_loss | -0.0147 | +| value_loss | 0.000221 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1421 | +| iterations | 10438 | +| time_elapsed | 15043 | +| total_timesteps | 21377024 | +| train/ | | +| approx_kl | 0.012757074 | +| clip_fraction | 0.35 | +| clip_range | 0.0697 | +| entropy_loss | -6.29 | +| explained_variance | 0.646 | +| learning_rate | 4.49e-05 | +| loss | -0.0331 | +| n_updates | 57568 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000104 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1421 | +| iterations | 10439 | +| time_elapsed | 15044 | +| total_timesteps | 21379072 | +| train/ | | +| approx_kl | 0.013820576 | +| clip_fraction | 0.315 | +| clip_range | 0.0697 | +| entropy_loss | -6.33 | +| explained_variance | 0.352 | +| learning_rate | 4.49e-05 | +| loss | -0.025 | +| n_updates | 57572 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000263 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1421 | +| iterations | 10440 | +| time_elapsed | 15046 | +| total_timesteps | 21381120 | +| train/ | | +| approx_kl | 0.015200574 | +| clip_fraction | 0.337 | +| clip_range | 0.0697 | +| entropy_loss | -6.53 | +| explained_variance | 0.396 | +| learning_rate | 4.49e-05 | +| loss | -0.0333 | +| n_updates | 57576 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000124 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1421 | +| iterations | 10441 | +| time_elapsed | 15047 | +| total_timesteps | 21383168 | +| train/ | | +| approx_kl | 0.013309494 | +| clip_fraction | 0.336 | +| clip_range | 0.0697 | +| entropy_loss | -6.89 | +| explained_variance | -0.162 | +| learning_rate | 4.49e-05 | +| loss | -0.0334 | +| n_updates | 57580 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000126 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1421 | +| iterations | 10442 | +| time_elapsed | 15049 | +| total_timesteps | 21385216 | +| train/ | | +| approx_kl | 0.011183687 | +| clip_fraction | 0.324 | +| clip_range | 0.0697 | +| entropy_loss | -6.86 | +| explained_variance | 0.25 | +| learning_rate | 4.49e-05 | +| loss | -0.0229 | +| n_updates | 57584 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000294 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1421 | +| iterations | 10443 | +| time_elapsed | 15050 | +| total_timesteps | 21387264 | +| train/ | | +| approx_kl | 0.01285858 | +| clip_fraction | 0.348 | +| clip_range | 0.0697 | +| entropy_loss | -6.53 | +| explained_variance | 0.611 | +| learning_rate | 4.49e-05 | +| loss | -0.0351 | +| n_updates | 57588 | +| policy_gradient_loss | -0.0216 | +| value_loss | 9.69e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1421 | +| iterations | 10444 | +| time_elapsed | 15052 | +| total_timesteps | 21389312 | +| train/ | | +| approx_kl | 0.011809041 | +| clip_fraction | 0.352 | +| clip_range | 0.0697 | +| entropy_loss | -6.93 | +| explained_variance | 0.282 | +| learning_rate | 4.49e-05 | +| loss | -0.0384 | +| n_updates | 57592 | +| policy_gradient_loss | -0.0216 | +| value_loss | 9.88e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1421 | +| iterations | 10445 | +| time_elapsed | 15053 | +| total_timesteps | 21391360 | +| train/ | | +| approx_kl | 0.013683997 | +| clip_fraction | 0.313 | +| clip_range | 0.0697 | +| entropy_loss | -6.8 | +| explained_variance | 0.418 | +| learning_rate | 4.49e-05 | +| loss | -0.0218 | +| n_updates | 57596 | +| policy_gradient_loss | -0.0178 | +| value_loss | 9.69e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1421 | +| iterations | 10446 | +| time_elapsed | 15055 | +| total_timesteps | 21393408 | +| train/ | | +| approx_kl | 0.011791484 | +| clip_fraction | 0.328 | +| clip_range | 0.0697 | +| entropy_loss | -6.56 | +| explained_variance | 0.599 | +| learning_rate | 4.49e-05 | +| loss | -0.0283 | +| n_updates | 57600 | +| policy_gradient_loss | -0.0184 | +| value_loss | 9.75e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1421 | +| iterations | 10447 | +| time_elapsed | 15056 | +| total_timesteps | 21395456 | +| train/ | | +| approx_kl | 0.014324994 | +| clip_fraction | 0.308 | +| clip_range | 0.0697 | +| entropy_loss | -7.15 | +| explained_variance | -0.0947 | +| learning_rate | 4.49e-05 | +| loss | -0.0283 | +| n_updates | 57604 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000136 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1420 | +| iterations | 10448 | +| time_elapsed | 15058 | +| total_timesteps | 21397504 | +| train/ | | +| approx_kl | 0.01499052 | +| clip_fraction | 0.329 | +| clip_range | 0.0697 | +| entropy_loss | -6.7 | +| explained_variance | -0.0801 | +| learning_rate | 4.49e-05 | +| loss | -0.0326 | +| n_updates | 57608 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000118 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1421 | +| iterations | 10449 | +| time_elapsed | 15059 | +| total_timesteps | 21399552 | +| train/ | | +| approx_kl | 0.015294794 | +| clip_fraction | 0.346 | +| clip_range | 0.0697 | +| entropy_loss | -6.43 | +| explained_variance | 0.17 | +| learning_rate | 4.49e-05 | +| loss | -0.0312 | +| n_updates | 57612 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000224 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1421 | +| iterations | 10450 | +| time_elapsed | 15060 | +| total_timesteps | 21401600 | +| train/ | | +| approx_kl | 0.0101947365 | +| clip_fraction | 0.323 | +| clip_range | 0.0697 | +| entropy_loss | -6.12 | +| explained_variance | 0.634 | +| learning_rate | 4.49e-05 | +| loss | -0.023 | +| n_updates | 57616 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.00015 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1421 | +| iterations | 10451 | +| time_elapsed | 15062 | +| total_timesteps | 21403648 | +| train/ | | +| approx_kl | 0.012585519 | +| clip_fraction | 0.316 | +| clip_range | 0.0696 | +| entropy_loss | -6.42 | +| explained_variance | 0.11 | +| learning_rate | 4.49e-05 | +| loss | -0.0245 | +| n_updates | 57620 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.00029 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1420 | +| iterations | 10452 | +| time_elapsed | 15063 | +| total_timesteps | 21405696 | +| train/ | | +| approx_kl | 0.01315718 | +| clip_fraction | 0.37 | +| clip_range | 0.0696 | +| entropy_loss | -6.57 | +| explained_variance | 0.515 | +| learning_rate | 4.49e-05 | +| loss | -0.0334 | +| n_updates | 57624 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000108 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.315 | +| time/ | | +| fps | 1420 | +| iterations | 10453 | +| time_elapsed | 15065 | +| total_timesteps | 21407744 | +| train/ | | +| approx_kl | 0.013065027 | +| clip_fraction | 0.328 | +| clip_range | 0.0696 | +| entropy_loss | -6.18 | +| explained_variance | 0.344 | +| learning_rate | 4.49e-05 | +| loss | -0.0293 | +| n_updates | 57628 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000263 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1420 | +| iterations | 10454 | +| time_elapsed | 15066 | +| total_timesteps | 21409792 | +| train/ | | +| approx_kl | 0.013853122 | +| clip_fraction | 0.377 | +| clip_range | 0.0696 | +| entropy_loss | -6.45 | +| explained_variance | 0.256 | +| learning_rate | 4.49e-05 | +| loss | -0.0324 | +| n_updates | 57632 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000102 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1420 | +| iterations | 10455 | +| time_elapsed | 15068 | +| total_timesteps | 21411840 | +| train/ | | +| approx_kl | 0.012032623 | +| clip_fraction | 0.341 | +| clip_range | 0.0696 | +| entropy_loss | -6.16 | +| explained_variance | 0.654 | +| learning_rate | 4.49e-05 | +| loss | -0.0277 | +| n_updates | 57636 | +| policy_gradient_loss | -0.0173 | +| value_loss | 9.57e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1420 | +| iterations | 10456 | +| time_elapsed | 15069 | +| total_timesteps | 21413888 | +| train/ | | +| approx_kl | 0.013271515 | +| clip_fraction | 0.328 | +| clip_range | 0.0696 | +| entropy_loss | -6.74 | +| explained_variance | 0.136 | +| learning_rate | 4.49e-05 | +| loss | -0.0282 | +| n_updates | 57640 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000139 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1420 | +| iterations | 10457 | +| time_elapsed | 15071 | +| total_timesteps | 21415936 | +| train/ | | +| approx_kl | 0.014472714 | +| clip_fraction | 0.343 | +| clip_range | 0.0696 | +| entropy_loss | -7.04 | +| explained_variance | -0.225 | +| learning_rate | 4.49e-05 | +| loss | -0.0326 | +| n_updates | 57644 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000148 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1420 | +| iterations | 10458 | +| time_elapsed | 15072 | +| total_timesteps | 21417984 | +| train/ | | +| approx_kl | 0.012237519 | +| clip_fraction | 0.311 | +| clip_range | 0.0696 | +| entropy_loss | -6.92 | +| explained_variance | 0.196 | +| learning_rate | 4.49e-05 | +| loss | -0.0269 | +| n_updates | 57648 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000158 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.315 | +| time/ | | +| fps | 1420 | +| iterations | 10459 | +| time_elapsed | 15074 | +| total_timesteps | 21420032 | +| train/ | | +| approx_kl | 0.013642288 | +| clip_fraction | 0.339 | +| clip_range | 0.0696 | +| entropy_loss | -6.51 | +| explained_variance | 0.376 | +| learning_rate | 4.49e-05 | +| loss | -0.0233 | +| n_updates | 57652 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000151 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1420 | +| iterations | 10460 | +| time_elapsed | 15075 | +| total_timesteps | 21422080 | +| train/ | | +| approx_kl | 0.013108101 | +| clip_fraction | 0.329 | +| clip_range | 0.0696 | +| entropy_loss | -6.4 | +| explained_variance | 0.272 | +| learning_rate | 4.49e-05 | +| loss | -0.0243 | +| n_updates | 57656 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000144 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1420 | +| iterations | 10461 | +| time_elapsed | 15077 | +| total_timesteps | 21424128 | +| train/ | | +| approx_kl | 0.012279604 | +| clip_fraction | 0.336 | +| clip_range | 0.0696 | +| entropy_loss | -6.34 | +| explained_variance | 0.415 | +| learning_rate | 4.49e-05 | +| loss | -0.0308 | +| n_updates | 57660 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000186 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1420 | +| iterations | 10462 | +| time_elapsed | 15078 | +| total_timesteps | 21426176 | +| train/ | | +| approx_kl | 0.012921224 | +| clip_fraction | 0.309 | +| clip_range | 0.0696 | +| entropy_loss | -6.69 | +| explained_variance | 0.286 | +| learning_rate | 4.49e-05 | +| loss | -0.0275 | +| n_updates | 57664 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000229 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1420 | +| iterations | 10463 | +| time_elapsed | 15079 | +| total_timesteps | 21428224 | +| train/ | | +| approx_kl | 0.012746104 | +| clip_fraction | 0.318 | +| clip_range | 0.0696 | +| entropy_loss | -5.98 | +| explained_variance | 0.463 | +| learning_rate | 4.49e-05 | +| loss | -0.0239 | +| n_updates | 57668 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000276 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1420 | +| iterations | 10464 | +| time_elapsed | 15081 | +| total_timesteps | 21430272 | +| train/ | | +| approx_kl | 0.014447968 | +| clip_fraction | 0.385 | +| clip_range | 0.0696 | +| entropy_loss | -6.62 | +| explained_variance | 0.438 | +| learning_rate | 4.49e-05 | +| loss | -0.0422 | +| n_updates | 57672 | +| policy_gradient_loss | -0.0264 | +| value_loss | 5.9e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1420 | +| iterations | 10465 | +| time_elapsed | 15082 | +| total_timesteps | 21432320 | +| train/ | | +| approx_kl | 0.014467878 | +| clip_fraction | 0.378 | +| clip_range | 0.0696 | +| entropy_loss | -6.68 | +| explained_variance | 0.51 | +| learning_rate | 4.49e-05 | +| loss | -0.0364 | +| n_updates | 57676 | +| policy_gradient_loss | -0.0228 | +| value_loss | 5.77e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1420 | +| iterations | 10466 | +| time_elapsed | 15084 | +| total_timesteps | 21434368 | +| train/ | | +| approx_kl | 0.014572355 | +| clip_fraction | 0.355 | +| clip_range | 0.0696 | +| entropy_loss | -6.8 | +| explained_variance | -0.00857 | +| learning_rate | 4.49e-05 | +| loss | -0.0307 | +| n_updates | 57680 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000175 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1420 | +| iterations | 10467 | +| time_elapsed | 15085 | +| total_timesteps | 21436416 | +| train/ | | +| approx_kl | 0.014555186 | +| clip_fraction | 0.318 | +| clip_range | 0.0696 | +| entropy_loss | -6.85 | +| explained_variance | 0.296 | +| learning_rate | 4.49e-05 | +| loss | -0.031 | +| n_updates | 57684 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000147 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.315 | +| time/ | | +| fps | 1420 | +| iterations | 10468 | +| time_elapsed | 15087 | +| total_timesteps | 21438464 | +| train/ | | +| approx_kl | 0.011575238 | +| clip_fraction | 0.323 | +| clip_range | 0.0696 | +| entropy_loss | -6.87 | +| explained_variance | 0.288 | +| learning_rate | 4.49e-05 | +| loss | -0.0298 | +| n_updates | 57688 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000128 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1420 | +| iterations | 10469 | +| time_elapsed | 15088 | +| total_timesteps | 21440512 | +| train/ | | +| approx_kl | 0.01386574 | +| clip_fraction | 0.345 | +| clip_range | 0.0696 | +| entropy_loss | -6.52 | +| explained_variance | 0.307 | +| learning_rate | 4.49e-05 | +| loss | -0.0296 | +| n_updates | 57692 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000181 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1420 | +| iterations | 10470 | +| time_elapsed | 15090 | +| total_timesteps | 21442560 | +| train/ | | +| approx_kl | 0.014118528 | +| clip_fraction | 0.36 | +| clip_range | 0.0696 | +| entropy_loss | -6.35 | +| explained_variance | 0.498 | +| learning_rate | 4.49e-05 | +| loss | -0.0286 | +| n_updates | 57696 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000108 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1420 | +| iterations | 10471 | +| time_elapsed | 15091 | +| total_timesteps | 21444608 | +| train/ | | +| approx_kl | 0.015772022 | +| clip_fraction | 0.37 | +| clip_range | 0.0696 | +| entropy_loss | -6.73 | +| explained_variance | -0.134 | +| learning_rate | 4.49e-05 | +| loss | -0.0355 | +| n_updates | 57700 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000147 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1420 | +| iterations | 10472 | +| time_elapsed | 15093 | +| total_timesteps | 21446656 | +| train/ | | +| approx_kl | 0.012133886 | +| clip_fraction | 0.303 | +| clip_range | 0.0696 | +| entropy_loss | -7 | +| explained_variance | -0.0104 | +| learning_rate | 4.49e-05 | +| loss | -0.0314 | +| n_updates | 57704 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000206 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1420 | +| iterations | 10473 | +| time_elapsed | 15094 | +| total_timesteps | 21448704 | +| train/ | | +| approx_kl | 0.01405116 | +| clip_fraction | 0.34 | +| clip_range | 0.0696 | +| entropy_loss | -6.16 | +| explained_variance | 0.719 | +| learning_rate | 4.49e-05 | +| loss | -0.0221 | +| n_updates | 57708 | +| policy_gradient_loss | -0.019 | +| value_loss | 9.72e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1420 | +| iterations | 10474 | +| time_elapsed | 15095 | +| total_timesteps | 21450752 | +| train/ | | +| approx_kl | 0.012640696 | +| clip_fraction | 0.313 | +| clip_range | 0.0696 | +| entropy_loss | -6.3 | +| explained_variance | 0.601 | +| learning_rate | 4.49e-05 | +| loss | -0.0327 | +| n_updates | 57712 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000115 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1420 | +| iterations | 10475 | +| time_elapsed | 15097 | +| total_timesteps | 21452800 | +| train/ | | +| approx_kl | 0.011095438 | +| clip_fraction | 0.309 | +| clip_range | 0.0696 | +| entropy_loss | -6.65 | +| explained_variance | 0.579 | +| learning_rate | 4.49e-05 | +| loss | -0.0288 | +| n_updates | 57716 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000122 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.315 | +| time/ | | +| fps | 1420 | +| iterations | 10476 | +| time_elapsed | 15098 | +| total_timesteps | 21454848 | +| train/ | | +| approx_kl | 0.011228117 | +| clip_fraction | 0.302 | +| clip_range | 0.0696 | +| entropy_loss | -6.21 | +| explained_variance | 0.556 | +| learning_rate | 4.49e-05 | +| loss | -0.0278 | +| n_updates | 57720 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000119 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1420 | +| iterations | 10477 | +| time_elapsed | 15100 | +| total_timesteps | 21456896 | +| train/ | | +| approx_kl | 0.01912146 | +| clip_fraction | 0.355 | +| clip_range | 0.0696 | +| entropy_loss | -6.07 | +| explained_variance | 0.376 | +| learning_rate | 4.49e-05 | +| loss | -0.0295 | +| n_updates | 57724 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000134 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1420 | +| iterations | 10478 | +| time_elapsed | 15101 | +| total_timesteps | 21458944 | +| train/ | | +| approx_kl | 0.014340991 | +| clip_fraction | 0.365 | +| clip_range | 0.0696 | +| entropy_loss | -6.63 | +| explained_variance | 0.473 | +| learning_rate | 4.49e-05 | +| loss | -0.0364 | +| n_updates | 57728 | +| policy_gradient_loss | -0.0223 | +| value_loss | 7.19e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1420 | +| iterations | 10479 | +| time_elapsed | 15103 | +| total_timesteps | 21460992 | +| train/ | | +| approx_kl | 0.010734247 | +| clip_fraction | 0.324 | +| clip_range | 0.0696 | +| entropy_loss | -6.78 | +| explained_variance | 0.342 | +| learning_rate | 4.49e-05 | +| loss | -0.0323 | +| n_updates | 57732 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000124 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1420 | +| iterations | 10480 | +| time_elapsed | 15104 | +| total_timesteps | 21463040 | +| train/ | | +| approx_kl | 0.011708561 | +| clip_fraction | 0.288 | +| clip_range | 0.0696 | +| entropy_loss | -6.61 | +| explained_variance | 0.214 | +| learning_rate | 4.49e-05 | +| loss | -0.0304 | +| n_updates | 57736 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000211 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1420 | +| iterations | 10481 | +| time_elapsed | 15106 | +| total_timesteps | 21465088 | +| train/ | | +| approx_kl | 0.012334637 | +| clip_fraction | 0.288 | +| clip_range | 0.0696 | +| entropy_loss | -6.69 | +| explained_variance | 0.536 | +| learning_rate | 4.49e-05 | +| loss | -0.0281 | +| n_updates | 57740 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000121 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1420 | +| iterations | 10482 | +| time_elapsed | 15107 | +| total_timesteps | 21467136 | +| train/ | | +| approx_kl | 0.012006909 | +| clip_fraction | 0.299 | +| clip_range | 0.0696 | +| entropy_loss | -6.38 | +| explained_variance | 0.233 | +| learning_rate | 4.49e-05 | +| loss | -0.0294 | +| n_updates | 57744 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000175 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1420 | +| iterations | 10483 | +| time_elapsed | 15108 | +| total_timesteps | 21469184 | +| train/ | | +| approx_kl | 0.016333342 | +| clip_fraction | 0.372 | +| clip_range | 0.0696 | +| entropy_loss | -6.48 | +| explained_variance | -0.174 | +| learning_rate | 4.49e-05 | +| loss | -0.0356 | +| n_updates | 57748 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000106 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1420 | +| iterations | 10484 | +| time_elapsed | 15110 | +| total_timesteps | 21471232 | +| train/ | | +| approx_kl | 0.013297021 | +| clip_fraction | 0.348 | +| clip_range | 0.0696 | +| entropy_loss | -6.58 | +| explained_variance | -0.028 | +| learning_rate | 4.49e-05 | +| loss | -0.028 | +| n_updates | 57752 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000183 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1420 | +| iterations | 10485 | +| time_elapsed | 15111 | +| total_timesteps | 21473280 | +| train/ | | +| approx_kl | 0.012848575 | +| clip_fraction | 0.34 | +| clip_range | 0.0696 | +| entropy_loss | -6.48 | +| explained_variance | 0.429 | +| learning_rate | 4.49e-05 | +| loss | -0.029 | +| n_updates | 57756 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000144 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1420 | +| iterations | 10486 | +| time_elapsed | 15113 | +| total_timesteps | 21475328 | +| train/ | | +| approx_kl | 0.012894351 | +| clip_fraction | 0.327 | +| clip_range | 0.0696 | +| entropy_loss | -6.58 | +| explained_variance | 0.484 | +| learning_rate | 4.49e-05 | +| loss | -0.0301 | +| n_updates | 57760 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.00011 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1420 | +| iterations | 10487 | +| time_elapsed | 15114 | +| total_timesteps | 21477376 | +| train/ | | +| approx_kl | 0.013304435 | +| clip_fraction | 0.345 | +| clip_range | 0.0696 | +| entropy_loss | -6.7 | +| explained_variance | 0.391 | +| learning_rate | 4.49e-05 | +| loss | -0.0313 | +| n_updates | 57764 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000105 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1420 | +| iterations | 10488 | +| time_elapsed | 15116 | +| total_timesteps | 21479424 | +| train/ | | +| approx_kl | 0.01293261 | +| clip_fraction | 0.333 | +| clip_range | 0.0696 | +| entropy_loss | -7.09 | +| explained_variance | -0.302 | +| learning_rate | 4.49e-05 | +| loss | -0.0416 | +| n_updates | 57768 | +| policy_gradient_loss | -0.0208 | +| value_loss | 4.79e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1420 | +| iterations | 10489 | +| time_elapsed | 15117 | +| total_timesteps | 21481472 | +| train/ | | +| approx_kl | 0.011886919 | +| clip_fraction | 0.294 | +| clip_range | 0.0696 | +| entropy_loss | -6.5 | +| explained_variance | 0.309 | +| learning_rate | 4.49e-05 | +| loss | -0.0255 | +| n_updates | 57772 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.00031 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1420 | +| iterations | 10490 | +| time_elapsed | 15118 | +| total_timesteps | 21483520 | +| train/ | | +| approx_kl | 0.013194746 | +| clip_fraction | 0.313 | +| clip_range | 0.0696 | +| entropy_loss | -6.12 | +| explained_variance | 0.52 | +| learning_rate | 4.49e-05 | +| loss | -0.0272 | +| n_updates | 57776 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000178 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1420 | +| iterations | 10491 | +| time_elapsed | 15120 | +| total_timesteps | 21485568 | +| train/ | | +| approx_kl | 0.016990062 | +| clip_fraction | 0.295 | +| clip_range | 0.0696 | +| entropy_loss | -5.91 | +| explained_variance | 0.509 | +| learning_rate | 4.49e-05 | +| loss | -0.03 | +| n_updates | 57780 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000213 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1420 | +| iterations | 10492 | +| time_elapsed | 15121 | +| total_timesteps | 21487616 | +| train/ | | +| approx_kl | 0.012662123 | +| clip_fraction | 0.301 | +| clip_range | 0.0696 | +| entropy_loss | -6.33 | +| explained_variance | 0.268 | +| learning_rate | 4.49e-05 | +| loss | -0.0275 | +| n_updates | 57784 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000224 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1420 | +| iterations | 10493 | +| time_elapsed | 15123 | +| total_timesteps | 21489664 | +| train/ | | +| approx_kl | 0.012993682 | +| clip_fraction | 0.375 | +| clip_range | 0.0696 | +| entropy_loss | -6.69 | +| explained_variance | 0.487 | +| learning_rate | 4.49e-05 | +| loss | -0.0382 | +| n_updates | 57788 | +| policy_gradient_loss | -0.022 | +| value_loss | 5.65e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1420 | +| iterations | 10494 | +| time_elapsed | 15124 | +| total_timesteps | 21491712 | +| train/ | | +| approx_kl | 0.012729479 | +| clip_fraction | 0.348 | +| clip_range | 0.0696 | +| entropy_loss | -6.54 | +| explained_variance | 0.623 | +| learning_rate | 4.49e-05 | +| loss | -0.0388 | +| n_updates | 57792 | +| policy_gradient_loss | -0.0215 | +| value_loss | 8.5e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1420 | +| iterations | 10495 | +| time_elapsed | 15126 | +| total_timesteps | 21493760 | +| train/ | | +| approx_kl | 0.0093741445 | +| clip_fraction | 0.317 | +| clip_range | 0.0696 | +| entropy_loss | -7.21 | +| explained_variance | -0.0049 | +| learning_rate | 4.49e-05 | +| loss | -0.0279 | +| n_updates | 57796 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000163 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1420 | +| iterations | 10496 | +| time_elapsed | 15127 | +| total_timesteps | 21495808 | +| train/ | | +| approx_kl | 0.01179247 | +| clip_fraction | 0.336 | +| clip_range | 0.0696 | +| entropy_loss | -6.89 | +| explained_variance | 0.107 | +| learning_rate | 4.49e-05 | +| loss | -0.0278 | +| n_updates | 57800 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000139 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1420 | +| iterations | 10497 | +| time_elapsed | 15129 | +| total_timesteps | 21497856 | +| train/ | | +| approx_kl | 0.012679496 | +| clip_fraction | 0.331 | +| clip_range | 0.0696 | +| entropy_loss | -6.8 | +| explained_variance | 0.408 | +| learning_rate | 4.49e-05 | +| loss | -0.03 | +| n_updates | 57804 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000156 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1420 | +| iterations | 10498 | +| time_elapsed | 15130 | +| total_timesteps | 21499904 | +| train/ | | +| approx_kl | 0.013542784 | +| clip_fraction | 0.332 | +| clip_range | 0.0696 | +| entropy_loss | -6.88 | +| explained_variance | 0.476 | +| learning_rate | 4.49e-05 | +| loss | -0.036 | +| n_updates | 57808 | +| policy_gradient_loss | -0.0206 | +| value_loss | 7.81e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.3 | +| time/ | | +| fps | 1420 | +| iterations | 10499 | +| time_elapsed | 15132 | +| total_timesteps | 21501952 | +| train/ | | +| approx_kl | 0.0145400595 | +| clip_fraction | 0.305 | +| clip_range | 0.0696 | +| entropy_loss | -6.58 | +| explained_variance | 0.385 | +| learning_rate | 4.49e-05 | +| loss | -0.0275 | +| n_updates | 57812 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.00012 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.302 | +| time/ | | +| fps | 1420 | +| iterations | 10500 | +| time_elapsed | 15133 | +| total_timesteps | 21504000 | +| train/ | | +| approx_kl | 0.012981899 | +| clip_fraction | 0.32 | +| clip_range | 0.0696 | +| entropy_loss | -5.66 | +| explained_variance | 0.384 | +| learning_rate | 4.49e-05 | +| loss | -0.0261 | +| n_updates | 57816 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000349 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.302 | +| time/ | | +| fps | 1420 | +| iterations | 10501 | +| time_elapsed | 15135 | +| total_timesteps | 21506048 | +| train/ | | +| approx_kl | 0.011610952 | +| clip_fraction | 0.348 | +| clip_range | 0.0696 | +| entropy_loss | -6.61 | +| explained_variance | 0.131 | +| learning_rate | 4.49e-05 | +| loss | -0.0325 | +| n_updates | 57820 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000192 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.3 | +| time/ | | +| fps | 1420 | +| iterations | 10502 | +| time_elapsed | 15136 | +| total_timesteps | 21508096 | +| train/ | | +| approx_kl | 0.011645079 | +| clip_fraction | 0.34 | +| clip_range | 0.0696 | +| entropy_loss | -6.87 | +| explained_variance | 0.373 | +| learning_rate | 4.49e-05 | +| loss | -0.0284 | +| n_updates | 57824 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000156 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1420 | +| iterations | 10503 | +| time_elapsed | 15138 | +| total_timesteps | 21510144 | +| train/ | | +| approx_kl | 0.013894843 | +| clip_fraction | 0.355 | +| clip_range | 0.0696 | +| entropy_loss | -6.64 | +| explained_variance | -0.0726 | +| learning_rate | 4.49e-05 | +| loss | -0.027 | +| n_updates | 57828 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.00019 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1420 | +| iterations | 10504 | +| time_elapsed | 15139 | +| total_timesteps | 21512192 | +| train/ | | +| approx_kl | 0.014052586 | +| clip_fraction | 0.308 | +| clip_range | 0.0696 | +| entropy_loss | -6.4 | +| explained_variance | 0.335 | +| learning_rate | 4.49e-05 | +| loss | -0.0289 | +| n_updates | 57832 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000265 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.304 | +| time/ | | +| fps | 1420 | +| iterations | 10505 | +| time_elapsed | 15141 | +| total_timesteps | 21514240 | +| train/ | | +| approx_kl | 0.012719566 | +| clip_fraction | 0.336 | +| clip_range | 0.0696 | +| entropy_loss | -6.98 | +| explained_variance | -0.14 | +| learning_rate | 4.49e-05 | +| loss | -0.0256 | +| n_updates | 57836 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000191 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.306 | +| time/ | | +| fps | 1420 | +| iterations | 10506 | +| time_elapsed | 15142 | +| total_timesteps | 21516288 | +| train/ | | +| approx_kl | 0.014847128 | +| clip_fraction | 0.362 | +| clip_range | 0.0696 | +| entropy_loss | -6.88 | +| explained_variance | 0.326 | +| learning_rate | 4.49e-05 | +| loss | -0.0427 | +| n_updates | 57840 | +| policy_gradient_loss | -0.0225 | +| value_loss | 0.000115 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1420 | +| iterations | 10507 | +| time_elapsed | 15144 | +| total_timesteps | 21518336 | +| train/ | | +| approx_kl | 0.011343897 | +| clip_fraction | 0.308 | +| clip_range | 0.0696 | +| entropy_loss | -6.83 | +| explained_variance | 0.295 | +| learning_rate | 4.49e-05 | +| loss | -0.0279 | +| n_updates | 57844 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000183 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1420 | +| iterations | 10508 | +| time_elapsed | 15145 | +| total_timesteps | 21520384 | +| train/ | | +| approx_kl | 0.00862347 | +| clip_fraction | 0.272 | +| clip_range | 0.0696 | +| entropy_loss | -6.6 | +| explained_variance | 0.309 | +| learning_rate | 4.49e-05 | +| loss | -0.0272 | +| n_updates | 57848 | +| policy_gradient_loss | -0.0148 | +| value_loss | 0.000305 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1420 | +| iterations | 10509 | +| time_elapsed | 15146 | +| total_timesteps | 21522432 | +| train/ | | +| approx_kl | 0.012234455 | +| clip_fraction | 0.328 | +| clip_range | 0.0696 | +| entropy_loss | -6.49 | +| explained_variance | 0.232 | +| learning_rate | 4.49e-05 | +| loss | -0.0286 | +| n_updates | 57852 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000254 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1420 | +| iterations | 10510 | +| time_elapsed | 15148 | +| total_timesteps | 21524480 | +| train/ | | +| approx_kl | 0.013013302 | +| clip_fraction | 0.351 | +| clip_range | 0.0696 | +| entropy_loss | -6.42 | +| explained_variance | 0.324 | +| learning_rate | 4.49e-05 | +| loss | -0.0261 | +| n_updates | 57856 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000234 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1420 | +| iterations | 10511 | +| time_elapsed | 15149 | +| total_timesteps | 21526528 | +| train/ | | +| approx_kl | 0.018125087 | +| clip_fraction | 0.344 | +| clip_range | 0.0696 | +| entropy_loss | -5.87 | +| explained_variance | 0.659 | +| learning_rate | 4.49e-05 | +| loss | -0.0341 | +| n_updates | 57860 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000141 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1420 | +| iterations | 10512 | +| time_elapsed | 15151 | +| total_timesteps | 21528576 | +| train/ | | +| approx_kl | 0.01148939 | +| clip_fraction | 0.324 | +| clip_range | 0.0696 | +| entropy_loss | -6.79 | +| explained_variance | -0.299 | +| learning_rate | 4.49e-05 | +| loss | -0.031 | +| n_updates | 57864 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000136 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1420 | +| iterations | 10513 | +| time_elapsed | 15152 | +| total_timesteps | 21530624 | +| train/ | | +| approx_kl | 0.0111879865 | +| clip_fraction | 0.309 | +| clip_range | 0.0696 | +| entropy_loss | -6.81 | +| explained_variance | 0.103 | +| learning_rate | 4.49e-05 | +| loss | -0.0274 | +| n_updates | 57868 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.00029 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1420 | +| iterations | 10514 | +| time_elapsed | 15154 | +| total_timesteps | 21532672 | +| train/ | | +| approx_kl | 0.01443629 | +| clip_fraction | 0.343 | +| clip_range | 0.0696 | +| entropy_loss | -6.6 | +| explained_variance | 0.177 | +| learning_rate | 4.49e-05 | +| loss | -0.0337 | +| n_updates | 57872 | +| policy_gradient_loss | -0.0219 | +| value_loss | 0.00014 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1420 | +| iterations | 10515 | +| time_elapsed | 15155 | +| total_timesteps | 21534720 | +| train/ | | +| approx_kl | 0.01589699 | +| clip_fraction | 0.359 | +| clip_range | 0.0696 | +| entropy_loss | -7.07 | +| explained_variance | -0.152 | +| learning_rate | 4.49e-05 | +| loss | -0.0383 | +| n_updates | 57876 | +| policy_gradient_loss | -0.0226 | +| value_loss | 9.85e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1420 | +| iterations | 10516 | +| time_elapsed | 15157 | +| total_timesteps | 21536768 | +| train/ | | +| approx_kl | 0.011901366 | +| clip_fraction | 0.333 | +| clip_range | 0.0696 | +| entropy_loss | -7.08 | +| explained_variance | -0.0375 | +| learning_rate | 4.49e-05 | +| loss | -0.0314 | +| n_updates | 57880 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000203 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1420 | +| iterations | 10517 | +| time_elapsed | 15158 | +| total_timesteps | 21538816 | +| train/ | | +| approx_kl | 0.011940441 | +| clip_fraction | 0.357 | +| clip_range | 0.0696 | +| entropy_loss | -6.25 | +| explained_variance | 0.702 | +| learning_rate | 4.49e-05 | +| loss | -0.0353 | +| n_updates | 57884 | +| policy_gradient_loss | -0.0217 | +| value_loss | 5.07e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 1420 | +| iterations | 10518 | +| time_elapsed | 15159 | +| total_timesteps | 21540864 | +| train/ | | +| approx_kl | 0.01133397 | +| clip_fraction | 0.305 | +| clip_range | 0.0696 | +| entropy_loss | -6.8 | +| explained_variance | 0.291 | +| learning_rate | 4.49e-05 | +| loss | -0.0248 | +| n_updates | 57888 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000138 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1420 | +| iterations | 10519 | +| time_elapsed | 15161 | +| total_timesteps | 21542912 | +| train/ | | +| approx_kl | 0.011310143 | +| clip_fraction | 0.309 | +| clip_range | 0.0696 | +| entropy_loss | -6.69 | +| explained_variance | 0.37 | +| learning_rate | 4.49e-05 | +| loss | -0.0259 | +| n_updates | 57892 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000179 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1420 | +| iterations | 10520 | +| time_elapsed | 15162 | +| total_timesteps | 21544960 | +| train/ | | +| approx_kl | 0.0117767975 | +| clip_fraction | 0.3 | +| clip_range | 0.0696 | +| entropy_loss | -6.04 | +| explained_variance | 0.433 | +| learning_rate | 4.49e-05 | +| loss | -0.0244 | +| n_updates | 57896 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000208 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1420 | +| iterations | 10521 | +| time_elapsed | 15164 | +| total_timesteps | 21547008 | +| train/ | | +| approx_kl | 0.012742854 | +| clip_fraction | 0.319 | +| clip_range | 0.0696 | +| entropy_loss | -6.98 | +| explained_variance | -0.0764 | +| learning_rate | 4.49e-05 | +| loss | -0.0304 | +| n_updates | 57900 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000169 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1420 | +| iterations | 10522 | +| time_elapsed | 15165 | +| total_timesteps | 21549056 | +| train/ | | +| approx_kl | 0.011432678 | +| clip_fraction | 0.34 | +| clip_range | 0.0696 | +| entropy_loss | -6.42 | +| explained_variance | 0.28 | +| learning_rate | 4.49e-05 | +| loss | -0.0311 | +| n_updates | 57904 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000436 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1420 | +| iterations | 10523 | +| time_elapsed | 15167 | +| total_timesteps | 21551104 | +| train/ | | +| approx_kl | 0.012321995 | +| clip_fraction | 0.332 | +| clip_range | 0.0696 | +| entropy_loss | -5.98 | +| explained_variance | 0.503 | +| learning_rate | 4.49e-05 | +| loss | -0.0339 | +| n_updates | 57908 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000167 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1420 | +| iterations | 10524 | +| time_elapsed | 15168 | +| total_timesteps | 21553152 | +| train/ | | +| approx_kl | 0.011465112 | +| clip_fraction | 0.345 | +| clip_range | 0.0696 | +| entropy_loss | -6.92 | +| explained_variance | 0.0917 | +| learning_rate | 4.49e-05 | +| loss | -0.0337 | +| n_updates | 57912 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000131 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1420 | +| iterations | 10525 | +| time_elapsed | 15170 | +| total_timesteps | 21555200 | +| train/ | | +| approx_kl | 0.013394259 | +| clip_fraction | 0.317 | +| clip_range | 0.0696 | +| entropy_loss | -6.76 | +| explained_variance | 0.296 | +| learning_rate | 4.49e-05 | +| loss | -0.0312 | +| n_updates | 57916 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000322 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1420 | +| iterations | 10526 | +| time_elapsed | 15171 | +| total_timesteps | 21557248 | +| train/ | | +| approx_kl | 0.0103007145 | +| clip_fraction | 0.318 | +| clip_range | 0.0696 | +| entropy_loss | -6.7 | +| explained_variance | 0.358 | +| learning_rate | 4.49e-05 | +| loss | -0.0358 | +| n_updates | 57920 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000176 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1420 | +| iterations | 10527 | +| time_elapsed | 15173 | +| total_timesteps | 21559296 | +| train/ | | +| approx_kl | 0.011329643 | +| clip_fraction | 0.294 | +| clip_range | 0.0696 | +| entropy_loss | -6.47 | +| explained_variance | 0.326 | +| learning_rate | 4.49e-05 | +| loss | -0.0255 | +| n_updates | 57924 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000266 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1420 | +| iterations | 10528 | +| time_elapsed | 15174 | +| total_timesteps | 21561344 | +| train/ | | +| approx_kl | 0.010640038 | +| clip_fraction | 0.323 | +| clip_range | 0.0696 | +| entropy_loss | -6.18 | +| explained_variance | 0.653 | +| learning_rate | 4.49e-05 | +| loss | -0.0291 | +| n_updates | 57928 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000153 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1420 | +| iterations | 10529 | +| time_elapsed | 15176 | +| total_timesteps | 21563392 | +| train/ | | +| approx_kl | 0.0141745135 | +| clip_fraction | 0.338 | +| clip_range | 0.0696 | +| entropy_loss | -6.41 | +| explained_variance | 0.00223 | +| learning_rate | 4.49e-05 | +| loss | -0.0329 | +| n_updates | 57932 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.0002 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1420 | +| iterations | 10530 | +| time_elapsed | 15177 | +| total_timesteps | 21565440 | +| train/ | | +| approx_kl | 0.012324726 | +| clip_fraction | 0.316 | +| clip_range | 0.0696 | +| entropy_loss | -6.71 | +| explained_variance | 0.347 | +| learning_rate | 4.49e-05 | +| loss | -0.0258 | +| n_updates | 57936 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.00022 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1420 | +| iterations | 10531 | +| time_elapsed | 15179 | +| total_timesteps | 21567488 | +| train/ | | +| approx_kl | 0.012357154 | +| clip_fraction | 0.335 | +| clip_range | 0.0696 | +| entropy_loss | -6.88 | +| explained_variance | 0.187 | +| learning_rate | 4.49e-05 | +| loss | -0.0404 | +| n_updates | 57940 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000131 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1420 | +| iterations | 10532 | +| time_elapsed | 15180 | +| total_timesteps | 21569536 | +| train/ | | +| approx_kl | 0.011156281 | +| clip_fraction | 0.328 | +| clip_range | 0.0696 | +| entropy_loss | -7.25 | +| explained_variance | -0.219 | +| learning_rate | 4.49e-05 | +| loss | -0.0335 | +| n_updates | 57944 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000111 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1420 | +| iterations | 10533 | +| time_elapsed | 15182 | +| total_timesteps | 21571584 | +| train/ | | +| approx_kl | 0.012404678 | +| clip_fraction | 0.302 | +| clip_range | 0.0696 | +| entropy_loss | -6.86 | +| explained_variance | 0.318 | +| learning_rate | 4.49e-05 | +| loss | -0.0277 | +| n_updates | 57948 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000202 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1420 | +| iterations | 10534 | +| time_elapsed | 15183 | +| total_timesteps | 21573632 | +| train/ | | +| approx_kl | 0.009045827 | +| clip_fraction | 0.304 | +| clip_range | 0.0696 | +| entropy_loss | -5.78 | +| explained_variance | 0.831 | +| learning_rate | 4.49e-05 | +| loss | -0.031 | +| n_updates | 57952 | +| policy_gradient_loss | -0.0182 | +| value_loss | 7.57e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1420 | +| iterations | 10535 | +| time_elapsed | 15185 | +| total_timesteps | 21575680 | +| train/ | | +| approx_kl | 0.010584663 | +| clip_fraction | 0.313 | +| clip_range | 0.0696 | +| entropy_loss | -5.99 | +| explained_variance | 0.596 | +| learning_rate | 4.49e-05 | +| loss | -0.0283 | +| n_updates | 57956 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000192 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1420 | +| iterations | 10536 | +| time_elapsed | 15186 | +| total_timesteps | 21577728 | +| train/ | | +| approx_kl | 0.013545802 | +| clip_fraction | 0.298 | +| clip_range | 0.0696 | +| entropy_loss | -6.64 | +| explained_variance | 0.344 | +| learning_rate | 4.49e-05 | +| loss | -0.0274 | +| n_updates | 57960 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000197 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1420 | +| iterations | 10537 | +| time_elapsed | 15188 | +| total_timesteps | 21579776 | +| train/ | | +| approx_kl | 0.011459076 | +| clip_fraction | 0.336 | +| clip_range | 0.0696 | +| entropy_loss | -7.05 | +| explained_variance | 0.0706 | +| learning_rate | 4.49e-05 | +| loss | -0.0275 | +| n_updates | 57964 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.00019 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1420 | +| iterations | 10538 | +| time_elapsed | 15189 | +| total_timesteps | 21581824 | +| train/ | | +| approx_kl | 0.011705828 | +| clip_fraction | 0.316 | +| clip_range | 0.0696 | +| entropy_loss | -6.66 | +| explained_variance | 0.355 | +| learning_rate | 4.49e-05 | +| loss | -0.033 | +| n_updates | 57968 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000259 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1420 | +| iterations | 10539 | +| time_elapsed | 15191 | +| total_timesteps | 21583872 | +| train/ | | +| approx_kl | 0.010250498 | +| clip_fraction | 0.319 | +| clip_range | 0.0696 | +| entropy_loss | -6.69 | +| explained_variance | 0.381 | +| learning_rate | 4.49e-05 | +| loss | -0.0245 | +| n_updates | 57972 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000225 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1420 | +| iterations | 10540 | +| time_elapsed | 15192 | +| total_timesteps | 21585920 | +| train/ | | +| approx_kl | 0.013956526 | +| clip_fraction | 0.317 | +| clip_range | 0.0696 | +| entropy_loss | -6.22 | +| explained_variance | 0.365 | +| learning_rate | 4.49e-05 | +| loss | -0.0242 | +| n_updates | 57976 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000399 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1420 | +| iterations | 10541 | +| time_elapsed | 15194 | +| total_timesteps | 21587968 | +| train/ | | +| approx_kl | 0.014294056 | +| clip_fraction | 0.351 | +| clip_range | 0.0696 | +| entropy_loss | -6.01 | +| explained_variance | 0.657 | +| learning_rate | 4.49e-05 | +| loss | -0.0234 | +| n_updates | 57980 | +| policy_gradient_loss | -0.0203 | +| value_loss | 9.01e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1420 | +| iterations | 10542 | +| time_elapsed | 15195 | +| total_timesteps | 21590016 | +| train/ | | +| approx_kl | 0.011563917 | +| clip_fraction | 0.327 | +| clip_range | 0.0696 | +| entropy_loss | -6.4 | +| explained_variance | 0.303 | +| learning_rate | 4.49e-05 | +| loss | -0.0289 | +| n_updates | 57984 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000239 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1420 | +| iterations | 10543 | +| time_elapsed | 15197 | +| total_timesteps | 21592064 | +| train/ | | +| approx_kl | 0.016362198 | +| clip_fraction | 0.324 | +| clip_range | 0.0696 | +| entropy_loss | -6.31 | +| explained_variance | 0.431 | +| learning_rate | 4.49e-05 | +| loss | -0.0309 | +| n_updates | 57988 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000165 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1420 | +| iterations | 10544 | +| time_elapsed | 15198 | +| total_timesteps | 21594112 | +| train/ | | +| approx_kl | 0.012206853 | +| clip_fraction | 0.347 | +| clip_range | 0.0696 | +| entropy_loss | -6.72 | +| explained_variance | -0.0252 | +| learning_rate | 4.49e-05 | +| loss | -0.0326 | +| n_updates | 57992 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000125 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1420 | +| iterations | 10545 | +| time_elapsed | 15200 | +| total_timesteps | 21596160 | +| train/ | | +| approx_kl | 0.013412939 | +| clip_fraction | 0.35 | +| clip_range | 0.0696 | +| entropy_loss | -6.73 | +| explained_variance | 0.2 | +| learning_rate | 4.49e-05 | +| loss | -0.0362 | +| n_updates | 57996 | +| policy_gradient_loss | -0.0201 | +| value_loss | 8.43e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1420 | +| iterations | 10546 | +| time_elapsed | 15201 | +| total_timesteps | 21598208 | +| train/ | | +| approx_kl | 0.0138122495 | +| clip_fraction | 0.316 | +| clip_range | 0.0696 | +| entropy_loss | -6.85 | +| explained_variance | 0.219 | +| learning_rate | 4.49e-05 | +| loss | -0.0255 | +| n_updates | 58000 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.000232 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1420 | +| iterations | 10547 | +| time_elapsed | 15203 | +| total_timesteps | 21600256 | +| train/ | | +| approx_kl | 0.01431171 | +| clip_fraction | 0.319 | +| clip_range | 0.0696 | +| entropy_loss | -6.82 | +| explained_variance | 0.418 | +| learning_rate | 4.49e-05 | +| loss | -0.0308 | +| n_updates | 58004 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000158 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1420 | +| iterations | 10548 | +| time_elapsed | 15204 | +| total_timesteps | 21602304 | +| train/ | | +| approx_kl | 0.014674248 | +| clip_fraction | 0.354 | +| clip_range | 0.0696 | +| entropy_loss | -6.8 | +| explained_variance | -0.432 | +| learning_rate | 4.49e-05 | +| loss | -0.0337 | +| n_updates | 58008 | +| policy_gradient_loss | -0.0212 | +| value_loss | 7.59e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1420 | +| iterations | 10549 | +| time_elapsed | 15206 | +| total_timesteps | 21604352 | +| train/ | | +| approx_kl | 0.0125950985 | +| clip_fraction | 0.332 | +| clip_range | 0.0696 | +| entropy_loss | -6.23 | +| explained_variance | 0.41 | +| learning_rate | 4.49e-05 | +| loss | -0.0246 | +| n_updates | 58012 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000243 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1420 | +| iterations | 10550 | +| time_elapsed | 15207 | +| total_timesteps | 21606400 | +| train/ | | +| approx_kl | 0.0127508715 | +| clip_fraction | 0.307 | +| clip_range | 0.0696 | +| entropy_loss | -6.5 | +| explained_variance | 0.571 | +| learning_rate | 4.49e-05 | +| loss | -0.0252 | +| n_updates | 58016 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000158 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1420 | +| iterations | 10551 | +| time_elapsed | 15208 | +| total_timesteps | 21608448 | +| train/ | | +| approx_kl | 0.014030497 | +| clip_fraction | 0.361 | +| clip_range | 0.0696 | +| entropy_loss | -6.35 | +| explained_variance | -0.146 | +| learning_rate | 4.49e-05 | +| loss | -0.0337 | +| n_updates | 58020 | +| policy_gradient_loss | -0.0207 | +| value_loss | 7.63e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1420 | +| iterations | 10552 | +| time_elapsed | 15210 | +| total_timesteps | 21610496 | +| train/ | | +| approx_kl | 0.012976417 | +| clip_fraction | 0.346 | +| clip_range | 0.0696 | +| entropy_loss | -6.64 | +| explained_variance | 0.281 | +| learning_rate | 4.49e-05 | +| loss | -0.0296 | +| n_updates | 58024 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000133 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1420 | +| iterations | 10553 | +| time_elapsed | 15211 | +| total_timesteps | 21612544 | +| train/ | | +| approx_kl | 0.015070181 | +| clip_fraction | 0.334 | +| clip_range | 0.0696 | +| entropy_loss | -6.4 | +| explained_variance | 0.605 | +| learning_rate | 4.49e-05 | +| loss | -0.0274 | +| n_updates | 58028 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000112 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1420 | +| iterations | 10554 | +| time_elapsed | 15213 | +| total_timesteps | 21614592 | +| train/ | | +| approx_kl | 0.012736259 | +| clip_fraction | 0.323 | +| clip_range | 0.0696 | +| entropy_loss | -6.38 | +| explained_variance | 0.402 | +| learning_rate | 4.49e-05 | +| loss | -0.0298 | +| n_updates | 58032 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000182 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1420 | +| iterations | 10555 | +| time_elapsed | 15214 | +| total_timesteps | 21616640 | +| train/ | | +| approx_kl | 0.013696125 | +| clip_fraction | 0.328 | +| clip_range | 0.0696 | +| entropy_loss | -6.65 | +| explained_variance | 0.208 | +| learning_rate | 4.49e-05 | +| loss | -0.0237 | +| n_updates | 58036 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000279 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1420 | +| iterations | 10556 | +| time_elapsed | 15216 | +| total_timesteps | 21618688 | +| train/ | | +| approx_kl | 0.015627157 | +| clip_fraction | 0.377 | +| clip_range | 0.0696 | +| entropy_loss | -6.47 | +| explained_variance | 0.616 | +| learning_rate | 4.49e-05 | +| loss | -0.0396 | +| n_updates | 58040 | +| policy_gradient_loss | -0.0236 | +| value_loss | 7.92e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1420 | +| iterations | 10557 | +| time_elapsed | 15217 | +| total_timesteps | 21620736 | +| train/ | | +| approx_kl | 0.012376426 | +| clip_fraction | 0.322 | +| clip_range | 0.0696 | +| entropy_loss | -6.72 | +| explained_variance | 0.29 | +| learning_rate | 4.49e-05 | +| loss | -0.0309 | +| n_updates | 58044 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000189 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1420 | +| iterations | 10558 | +| time_elapsed | 15219 | +| total_timesteps | 21622784 | +| train/ | | +| approx_kl | 0.013766144 | +| clip_fraction | 0.338 | +| clip_range | 0.0696 | +| entropy_loss | -6.16 | +| explained_variance | 0.612 | +| learning_rate | 4.49e-05 | +| loss | -0.0372 | +| n_updates | 58048 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000128 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1420 | +| iterations | 10559 | +| time_elapsed | 15220 | +| total_timesteps | 21624832 | +| train/ | | +| approx_kl | 0.010069883 | +| clip_fraction | 0.306 | +| clip_range | 0.0696 | +| entropy_loss | -6.3 | +| explained_variance | 0.335 | +| learning_rate | 4.49e-05 | +| loss | -0.0308 | +| n_updates | 58052 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000287 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1420 | +| iterations | 10560 | +| time_elapsed | 15222 | +| total_timesteps | 21626880 | +| train/ | | +| approx_kl | 0.011593442 | +| clip_fraction | 0.362 | +| clip_range | 0.0696 | +| entropy_loss | -6.65 | +| explained_variance | -0.198 | +| learning_rate | 4.49e-05 | +| loss | -0.0342 | +| n_updates | 58056 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000102 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1420 | +| iterations | 10561 | +| time_elapsed | 15223 | +| total_timesteps | 21628928 | +| train/ | | +| approx_kl | 0.014041083 | +| clip_fraction | 0.338 | +| clip_range | 0.0696 | +| entropy_loss | -6.81 | +| explained_variance | 0.28 | +| learning_rate | 4.49e-05 | +| loss | -0.028 | +| n_updates | 58060 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000161 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1420 | +| iterations | 10562 | +| time_elapsed | 15225 | +| total_timesteps | 21630976 | +| train/ | | +| approx_kl | 0.011094438 | +| clip_fraction | 0.305 | +| clip_range | 0.0696 | +| entropy_loss | -6.04 | +| explained_variance | 0.477 | +| learning_rate | 4.49e-05 | +| loss | -0.0239 | +| n_updates | 58064 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000295 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1420 | +| iterations | 10563 | +| time_elapsed | 15226 | +| total_timesteps | 21633024 | +| train/ | | +| approx_kl | 0.010505172 | +| clip_fraction | 0.318 | +| clip_range | 0.0696 | +| entropy_loss | -6.59 | +| explained_variance | 0.38 | +| learning_rate | 4.49e-05 | +| loss | -0.0356 | +| n_updates | 58068 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000194 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1420 | +| iterations | 10564 | +| time_elapsed | 15228 | +| total_timesteps | 21635072 | +| train/ | | +| approx_kl | 0.015119923 | +| clip_fraction | 0.344 | +| clip_range | 0.0696 | +| entropy_loss | -6.74 | +| explained_variance | 0.334 | +| learning_rate | 4.49e-05 | +| loss | -0.0319 | +| n_updates | 58072 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000158 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1420 | +| iterations | 10565 | +| time_elapsed | 15229 | +| total_timesteps | 21637120 | +| train/ | | +| approx_kl | 0.011650626 | +| clip_fraction | 0.32 | +| clip_range | 0.0696 | +| entropy_loss | -6.46 | +| explained_variance | 0.36 | +| learning_rate | 4.49e-05 | +| loss | -0.0259 | +| n_updates | 58076 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000202 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1420 | +| iterations | 10566 | +| time_elapsed | 15230 | +| total_timesteps | 21639168 | +| train/ | | +| approx_kl | 0.011732482 | +| clip_fraction | 0.327 | +| clip_range | 0.0696 | +| entropy_loss | -6.65 | +| explained_variance | 0.366 | +| learning_rate | 4.49e-05 | +| loss | -0.0267 | +| n_updates | 58080 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000177 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1420 | +| iterations | 10567 | +| time_elapsed | 15232 | +| total_timesteps | 21641216 | +| train/ | | +| approx_kl | 0.011375485 | +| clip_fraction | 0.334 | +| clip_range | 0.0696 | +| entropy_loss | -6.81 | +| explained_variance | 0.241 | +| learning_rate | 4.49e-05 | +| loss | -0.025 | +| n_updates | 58084 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000327 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1420 | +| iterations | 10568 | +| time_elapsed | 15233 | +| total_timesteps | 21643264 | +| train/ | | +| approx_kl | 0.0137947425 | +| clip_fraction | 0.307 | +| clip_range | 0.0696 | +| entropy_loss | -6.19 | +| explained_variance | 0.366 | +| learning_rate | 4.49e-05 | +| loss | -0.0351 | +| n_updates | 58088 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000292 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1420 | +| iterations | 10569 | +| time_elapsed | 15235 | +| total_timesteps | 21645312 | +| train/ | | +| approx_kl | 0.014737328 | +| clip_fraction | 0.362 | +| clip_range | 0.0696 | +| entropy_loss | -6.16 | +| explained_variance | 0.493 | +| learning_rate | 4.49e-05 | +| loss | -0.0398 | +| n_updates | 58092 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.00016 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1420 | +| iterations | 10570 | +| time_elapsed | 15236 | +| total_timesteps | 21647360 | +| train/ | | +| approx_kl | 0.014088105 | +| clip_fraction | 0.372 | +| clip_range | 0.0696 | +| entropy_loss | -6.66 | +| explained_variance | 0.365 | +| learning_rate | 4.49e-05 | +| loss | -0.0331 | +| n_updates | 58096 | +| policy_gradient_loss | -0.0227 | +| value_loss | 0.000111 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1420 | +| iterations | 10571 | +| time_elapsed | 15238 | +| total_timesteps | 21649408 | +| train/ | | +| approx_kl | 0.011245047 | +| clip_fraction | 0.344 | +| clip_range | 0.0696 | +| entropy_loss | -6.64 | +| explained_variance | 0.528 | +| learning_rate | 4.49e-05 | +| loss | -0.0354 | +| n_updates | 58100 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000107 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1420 | +| iterations | 10572 | +| time_elapsed | 15239 | +| total_timesteps | 21651456 | +| train/ | | +| approx_kl | 0.014603526 | +| clip_fraction | 0.378 | +| clip_range | 0.0696 | +| entropy_loss | -6.71 | +| explained_variance | 0.255 | +| learning_rate | 4.49e-05 | +| loss | -0.0313 | +| n_updates | 58104 | +| policy_gradient_loss | -0.0223 | +| value_loss | 9.55e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1420 | +| iterations | 10573 | +| time_elapsed | 15241 | +| total_timesteps | 21653504 | +| train/ | | +| approx_kl | 0.011942061 | +| clip_fraction | 0.336 | +| clip_range | 0.0696 | +| entropy_loss | -6.43 | +| explained_variance | 0.626 | +| learning_rate | 4.49e-05 | +| loss | -0.0306 | +| n_updates | 58108 | +| policy_gradient_loss | -0.0199 | +| value_loss | 8.1e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1420 | +| iterations | 10574 | +| time_elapsed | 15242 | +| total_timesteps | 21655552 | +| train/ | | +| approx_kl | 0.012167967 | +| clip_fraction | 0.345 | +| clip_range | 0.0696 | +| entropy_loss | -6.58 | +| explained_variance | 0.73 | +| learning_rate | 4.49e-05 | +| loss | -0.0398 | +| n_updates | 58112 | +| policy_gradient_loss | -0.0224 | +| value_loss | 6.4e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1420 | +| iterations | 10575 | +| time_elapsed | 15244 | +| total_timesteps | 21657600 | +| train/ | | +| approx_kl | 0.013881852 | +| clip_fraction | 0.349 | +| clip_range | 0.0696 | +| entropy_loss | -6.22 | +| explained_variance | 0.446 | +| learning_rate | 4.49e-05 | +| loss | -0.0253 | +| n_updates | 58116 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.00013 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1420 | +| iterations | 10576 | +| time_elapsed | 15245 | +| total_timesteps | 21659648 | +| train/ | | +| approx_kl | 0.013688033 | +| clip_fraction | 0.343 | +| clip_range | 0.0696 | +| entropy_loss | -6.12 | +| explained_variance | 0.62 | +| learning_rate | 4.49e-05 | +| loss | -0.0306 | +| n_updates | 58120 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000103 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1420 | +| iterations | 10577 | +| time_elapsed | 15247 | +| total_timesteps | 21661696 | +| train/ | | +| approx_kl | 0.014765312 | +| clip_fraction | 0.285 | +| clip_range | 0.0696 | +| entropy_loss | -5.82 | +| explained_variance | 0.432 | +| learning_rate | 4.49e-05 | +| loss | -0.019 | +| n_updates | 58124 | +| policy_gradient_loss | -0.014 | +| value_loss | 0.000376 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1420 | +| iterations | 10578 | +| time_elapsed | 15248 | +| total_timesteps | 21663744 | +| train/ | | +| approx_kl | 0.014467828 | +| clip_fraction | 0.344 | +| clip_range | 0.0696 | +| entropy_loss | -5.87 | +| explained_variance | 0.433 | +| learning_rate | 4.49e-05 | +| loss | -0.0278 | +| n_updates | 58128 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000269 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1420 | +| iterations | 10579 | +| time_elapsed | 15250 | +| total_timesteps | 21665792 | +| train/ | | +| approx_kl | 0.013183303 | +| clip_fraction | 0.318 | +| clip_range | 0.0696 | +| entropy_loss | -6.77 | +| explained_variance | -0.0848 | +| learning_rate | 4.49e-05 | +| loss | -0.0329 | +| n_updates | 58132 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000156 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1420 | +| iterations | 10580 | +| time_elapsed | 15251 | +| total_timesteps | 21667840 | +| train/ | | +| approx_kl | 0.012166228 | +| clip_fraction | 0.33 | +| clip_range | 0.0696 | +| entropy_loss | -7.12 | +| explained_variance | 0.184 | +| learning_rate | 4.49e-05 | +| loss | -0.0313 | +| n_updates | 58136 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.00023 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1420 | +| iterations | 10581 | +| time_elapsed | 15253 | +| total_timesteps | 21669888 | +| train/ | | +| approx_kl | 0.013208823 | +| clip_fraction | 0.352 | +| clip_range | 0.0696 | +| entropy_loss | -6.55 | +| explained_variance | 0.26 | +| learning_rate | 4.49e-05 | +| loss | -0.033 | +| n_updates | 58140 | +| policy_gradient_loss | -0.0219 | +| value_loss | 0.000134 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1420 | +| iterations | 10582 | +| time_elapsed | 15254 | +| total_timesteps | 21671936 | +| train/ | | +| approx_kl | 0.013533335 | +| clip_fraction | 0.363 | +| clip_range | 0.0696 | +| entropy_loss | -6.95 | +| explained_variance | 0.171 | +| learning_rate | 4.49e-05 | +| loss | -0.033 | +| n_updates | 58144 | +| policy_gradient_loss | -0.022 | +| value_loss | 0.000124 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1420 | +| iterations | 10583 | +| time_elapsed | 15256 | +| total_timesteps | 21673984 | +| train/ | | +| approx_kl | 0.012516037 | +| clip_fraction | 0.319 | +| clip_range | 0.0696 | +| entropy_loss | -6.57 | +| explained_variance | 0.464 | +| learning_rate | 4.49e-05 | +| loss | -0.0256 | +| n_updates | 58148 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000179 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1420 | +| iterations | 10584 | +| time_elapsed | 15257 | +| total_timesteps | 21676032 | +| train/ | | +| approx_kl | 0.015685556 | +| clip_fraction | 0.323 | +| clip_range | 0.0696 | +| entropy_loss | -6.06 | +| explained_variance | 0.502 | +| learning_rate | 4.49e-05 | +| loss | -0.0288 | +| n_updates | 58152 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000218 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1420 | +| iterations | 10585 | +| time_elapsed | 15258 | +| total_timesteps | 21678080 | +| train/ | | +| approx_kl | 0.010353029 | +| clip_fraction | 0.329 | +| clip_range | 0.0696 | +| entropy_loss | -6.9 | +| explained_variance | 0.141 | +| learning_rate | 4.49e-05 | +| loss | -0.0299 | +| n_updates | 58156 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.00017 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1420 | +| iterations | 10586 | +| time_elapsed | 15260 | +| total_timesteps | 21680128 | +| train/ | | +| approx_kl | 0.014778575 | +| clip_fraction | 0.351 | +| clip_range | 0.0696 | +| entropy_loss | -7.15 | +| explained_variance | -0.084 | +| learning_rate | 4.49e-05 | +| loss | -0.0346 | +| n_updates | 58160 | +| policy_gradient_loss | -0.0219 | +| value_loss | 7.46e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1420 | +| iterations | 10587 | +| time_elapsed | 15261 | +| total_timesteps | 21682176 | +| train/ | | +| approx_kl | 0.011462262 | +| clip_fraction | 0.295 | +| clip_range | 0.0696 | +| entropy_loss | -6.27 | +| explained_variance | 0.441 | +| learning_rate | 4.49e-05 | +| loss | -0.0254 | +| n_updates | 58164 | +| policy_gradient_loss | -0.0145 | +| value_loss | 0.000265 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1420 | +| iterations | 10588 | +| time_elapsed | 15263 | +| total_timesteps | 21684224 | +| train/ | | +| approx_kl | 0.013856913 | +| clip_fraction | 0.373 | +| clip_range | 0.0696 | +| entropy_loss | -6.55 | +| explained_variance | 0.541 | +| learning_rate | 4.49e-05 | +| loss | -0.0372 | +| n_updates | 58168 | +| policy_gradient_loss | -0.0238 | +| value_loss | 6.71e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1420 | +| iterations | 10589 | +| time_elapsed | 15264 | +| total_timesteps | 21686272 | +| train/ | | +| approx_kl | 0.01353695 | +| clip_fraction | 0.329 | +| clip_range | 0.0696 | +| entropy_loss | -6.93 | +| explained_variance | -0.0562 | +| learning_rate | 4.48e-05 | +| loss | -0.0343 | +| n_updates | 58172 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000153 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1420 | +| iterations | 10590 | +| time_elapsed | 15266 | +| total_timesteps | 21688320 | +| train/ | | +| approx_kl | 0.013175542 | +| clip_fraction | 0.327 | +| clip_range | 0.0696 | +| entropy_loss | -6.01 | +| explained_variance | 0.69 | +| learning_rate | 4.48e-05 | +| loss | -0.0299 | +| n_updates | 58176 | +| policy_gradient_loss | -0.019 | +| value_loss | 7.61e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1420 | +| iterations | 10591 | +| time_elapsed | 15267 | +| total_timesteps | 21690368 | +| train/ | | +| approx_kl | 0.015767459 | +| clip_fraction | 0.354 | +| clip_range | 0.0696 | +| entropy_loss | -6.19 | +| explained_variance | 0.364 | +| learning_rate | 4.48e-05 | +| loss | -0.033 | +| n_updates | 58180 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000114 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1420 | +| iterations | 10592 | +| time_elapsed | 15269 | +| total_timesteps | 21692416 | +| train/ | | +| approx_kl | 0.013605045 | +| clip_fraction | 0.355 | +| clip_range | 0.0696 | +| entropy_loss | -6.75 | +| explained_variance | 0.408 | +| learning_rate | 4.48e-05 | +| loss | -0.0318 | +| n_updates | 58184 | +| policy_gradient_loss | -0.0212 | +| value_loss | 9.83e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1420 | +| iterations | 10593 | +| time_elapsed | 15270 | +| total_timesteps | 21694464 | +| train/ | | +| approx_kl | 0.012475984 | +| clip_fraction | 0.332 | +| clip_range | 0.0696 | +| entropy_loss | -6.92 | +| explained_variance | -0.19 | +| learning_rate | 4.48e-05 | +| loss | -0.0287 | +| n_updates | 58188 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000118 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1420 | +| iterations | 10594 | +| time_elapsed | 15271 | +| total_timesteps | 21696512 | +| train/ | | +| approx_kl | 0.013828775 | +| clip_fraction | 0.337 | +| clip_range | 0.0696 | +| entropy_loss | -6.28 | +| explained_variance | 0.487 | +| learning_rate | 4.48e-05 | +| loss | -0.0242 | +| n_updates | 58192 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000141 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1420 | +| iterations | 10595 | +| time_elapsed | 15273 | +| total_timesteps | 21698560 | +| train/ | | +| approx_kl | 0.011980861 | +| clip_fraction | 0.336 | +| clip_range | 0.0696 | +| entropy_loss | -6.84 | +| explained_variance | -0.0802 | +| learning_rate | 4.48e-05 | +| loss | -0.0269 | +| n_updates | 58196 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000111 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1420 | +| iterations | 10596 | +| time_elapsed | 15274 | +| total_timesteps | 21700608 | +| train/ | | +| approx_kl | 0.017121274 | +| clip_fraction | 0.363 | +| clip_range | 0.0696 | +| entropy_loss | -6.59 | +| explained_variance | 0.468 | +| learning_rate | 4.48e-05 | +| loss | -0.036 | +| n_updates | 58200 | +| policy_gradient_loss | -0.0209 | +| value_loss | 7.99e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1420 | +| iterations | 10597 | +| time_elapsed | 15276 | +| total_timesteps | 21702656 | +| train/ | | +| approx_kl | 0.014038835 | +| clip_fraction | 0.328 | +| clip_range | 0.0696 | +| entropy_loss | -6.7 | +| explained_variance | 0.416 | +| learning_rate | 4.48e-05 | +| loss | -0.0284 | +| n_updates | 58204 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000125 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1420 | +| iterations | 10598 | +| time_elapsed | 15277 | +| total_timesteps | 21704704 | +| train/ | | +| approx_kl | 0.0127934115 | +| clip_fraction | 0.318 | +| clip_range | 0.0696 | +| entropy_loss | -6.84 | +| explained_variance | 0.424 | +| learning_rate | 4.48e-05 | +| loss | -0.0309 | +| n_updates | 58208 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000131 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1420 | +| iterations | 10599 | +| time_elapsed | 15279 | +| total_timesteps | 21706752 | +| train/ | | +| approx_kl | 0.012270388 | +| clip_fraction | 0.326 | +| clip_range | 0.0696 | +| entropy_loss | -6.08 | +| explained_variance | 0.546 | +| learning_rate | 4.48e-05 | +| loss | -0.0315 | +| n_updates | 58212 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000184 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1420 | +| iterations | 10600 | +| time_elapsed | 15280 | +| total_timesteps | 21708800 | +| train/ | | +| approx_kl | 0.011488535 | +| clip_fraction | 0.321 | +| clip_range | 0.0696 | +| entropy_loss | -6.24 | +| explained_variance | 0.399 | +| learning_rate | 4.48e-05 | +| loss | -0.0212 | +| n_updates | 58216 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000215 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1420 | +| iterations | 10601 | +| time_elapsed | 15282 | +| total_timesteps | 21710848 | +| train/ | | +| approx_kl | 0.013092276 | +| clip_fraction | 0.343 | +| clip_range | 0.0696 | +| entropy_loss | -6.1 | +| explained_variance | 0.657 | +| learning_rate | 4.48e-05 | +| loss | -0.0328 | +| n_updates | 58220 | +| policy_gradient_loss | -0.0205 | +| value_loss | 7.82e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1420 | +| iterations | 10602 | +| time_elapsed | 15283 | +| total_timesteps | 21712896 | +| train/ | | +| approx_kl | 0.012650846 | +| clip_fraction | 0.334 | +| clip_range | 0.0696 | +| entropy_loss | -6.9 | +| explained_variance | 0.163 | +| learning_rate | 4.48e-05 | +| loss | -0.0327 | +| n_updates | 58224 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000205 | +----------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1420 | +| iterations | 10603 | +| time_elapsed | 15285 | +| total_timesteps | 21714944 | +| train/ | | +| approx_kl | 0.011618 | +| clip_fraction | 0.319 | +| clip_range | 0.0696 | +| entropy_loss | -6.82 | +| explained_variance | 0.273 | +| learning_rate | 4.48e-05 | +| loss | -0.0288 | +| n_updates | 58228 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000211 | +-------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1420 | +| iterations | 10604 | +| time_elapsed | 15286 | +| total_timesteps | 21716992 | +| train/ | | +| approx_kl | 0.01159432 | +| clip_fraction | 0.313 | +| clip_range | 0.0696 | +| entropy_loss | -6.38 | +| explained_variance | 0.326 | +| learning_rate | 4.48e-05 | +| loss | -0.0268 | +| n_updates | 58232 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000259 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1420 | +| iterations | 10605 | +| time_elapsed | 15288 | +| total_timesteps | 21719040 | +| train/ | | +| approx_kl | 0.012742883 | +| clip_fraction | 0.317 | +| clip_range | 0.0696 | +| entropy_loss | -6.25 | +| explained_variance | 0.135 | +| learning_rate | 4.48e-05 | +| loss | -0.0316 | +| n_updates | 58236 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000186 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1420 | +| iterations | 10606 | +| time_elapsed | 15289 | +| total_timesteps | 21721088 | +| train/ | | +| approx_kl | 0.011901604 | +| clip_fraction | 0.307 | +| clip_range | 0.0696 | +| entropy_loss | -6.32 | +| explained_variance | 0.451 | +| learning_rate | 4.48e-05 | +| loss | -0.0302 | +| n_updates | 58240 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000199 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1420 | +| iterations | 10607 | +| time_elapsed | 15290 | +| total_timesteps | 21723136 | +| train/ | | +| approx_kl | 0.011956785 | +| clip_fraction | 0.326 | +| clip_range | 0.0696 | +| entropy_loss | -6.35 | +| explained_variance | 0.243 | +| learning_rate | 4.48e-05 | +| loss | -0.0298 | +| n_updates | 58244 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000206 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1420 | +| iterations | 10608 | +| time_elapsed | 15292 | +| total_timesteps | 21725184 | +| train/ | | +| approx_kl | 0.013529109 | +| clip_fraction | 0.311 | +| clip_range | 0.0696 | +| entropy_loss | -6.89 | +| explained_variance | 0.122 | +| learning_rate | 4.48e-05 | +| loss | -0.0318 | +| n_updates | 58248 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000245 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1420 | +| iterations | 10609 | +| time_elapsed | 15293 | +| total_timesteps | 21727232 | +| train/ | | +| approx_kl | 0.016299924 | +| clip_fraction | 0.358 | +| clip_range | 0.0696 | +| entropy_loss | -6.18 | +| explained_variance | 0.396 | +| learning_rate | 4.48e-05 | +| loss | -0.0318 | +| n_updates | 58252 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000152 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1420 | +| iterations | 10610 | +| time_elapsed | 15295 | +| total_timesteps | 21729280 | +| train/ | | +| approx_kl | 0.0137851555 | +| clip_fraction | 0.342 | +| clip_range | 0.0696 | +| entropy_loss | -6.55 | +| explained_variance | 0.333 | +| learning_rate | 4.48e-05 | +| loss | -0.0357 | +| n_updates | 58256 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000183 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1420 | +| iterations | 10611 | +| time_elapsed | 15296 | +| total_timesteps | 21731328 | +| train/ | | +| approx_kl | 0.014216788 | +| clip_fraction | 0.383 | +| clip_range | 0.0696 | +| entropy_loss | -6.79 | +| explained_variance | -0.364 | +| learning_rate | 4.48e-05 | +| loss | -0.0454 | +| n_updates | 58260 | +| policy_gradient_loss | -0.0262 | +| value_loss | 5.36e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1420 | +| iterations | 10612 | +| time_elapsed | 15298 | +| total_timesteps | 21733376 | +| train/ | | +| approx_kl | 0.014012048 | +| clip_fraction | 0.331 | +| clip_range | 0.0696 | +| entropy_loss | -6.79 | +| explained_variance | 0.307 | +| learning_rate | 4.48e-05 | +| loss | -0.0314 | +| n_updates | 58264 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000148 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1420 | +| iterations | 10613 | +| time_elapsed | 15299 | +| total_timesteps | 21735424 | +| train/ | | +| approx_kl | 0.014372993 | +| clip_fraction | 0.326 | +| clip_range | 0.0696 | +| entropy_loss | -6.73 | +| explained_variance | 0.434 | +| learning_rate | 4.48e-05 | +| loss | -0.0358 | +| n_updates | 58268 | +| policy_gradient_loss | -0.0211 | +| value_loss | 9.18e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1420 | +| iterations | 10614 | +| time_elapsed | 15301 | +| total_timesteps | 21737472 | +| train/ | | +| approx_kl | 0.010756461 | +| clip_fraction | 0.314 | +| clip_range | 0.0696 | +| entropy_loss | -6.7 | +| explained_variance | 0.461 | +| learning_rate | 4.48e-05 | +| loss | -0.03 | +| n_updates | 58272 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000174 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1420 | +| iterations | 10615 | +| time_elapsed | 15302 | +| total_timesteps | 21739520 | +| train/ | | +| approx_kl | 0.009412425 | +| clip_fraction | 0.314 | +| clip_range | 0.0696 | +| entropy_loss | -7.04 | +| explained_variance | -0.00743 | +| learning_rate | 4.48e-05 | +| loss | -0.0327 | +| n_updates | 58276 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000185 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1420 | +| iterations | 10616 | +| time_elapsed | 15304 | +| total_timesteps | 21741568 | +| train/ | | +| approx_kl | 0.0105778705 | +| clip_fraction | 0.321 | +| clip_range | 0.0696 | +| entropy_loss | -6.51 | +| explained_variance | 0.459 | +| learning_rate | 4.48e-05 | +| loss | -0.0249 | +| n_updates | 58280 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000213 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1420 | +| iterations | 10617 | +| time_elapsed | 15305 | +| total_timesteps | 21743616 | +| train/ | | +| approx_kl | 0.013431563 | +| clip_fraction | 0.356 | +| clip_range | 0.0696 | +| entropy_loss | -6.36 | +| explained_variance | 0.63 | +| learning_rate | 4.48e-05 | +| loss | -0.0358 | +| n_updates | 58284 | +| policy_gradient_loss | -0.0234 | +| value_loss | 8.45e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1420 | +| iterations | 10618 | +| time_elapsed | 15306 | +| total_timesteps | 21745664 | +| train/ | | +| approx_kl | 0.010857976 | +| clip_fraction | 0.328 | +| clip_range | 0.0696 | +| entropy_loss | -6.24 | +| explained_variance | 0.63 | +| learning_rate | 4.48e-05 | +| loss | -0.0289 | +| n_updates | 58288 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000145 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1420 | +| iterations | 10619 | +| time_elapsed | 15308 | +| total_timesteps | 21747712 | +| train/ | | +| approx_kl | 0.0125286095 | +| clip_fraction | 0.36 | +| clip_range | 0.0696 | +| entropy_loss | -6.12 | +| explained_variance | 0.653 | +| learning_rate | 4.48e-05 | +| loss | -0.0334 | +| n_updates | 58292 | +| policy_gradient_loss | -0.022 | +| value_loss | 7.47e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1420 | +| iterations | 10620 | +| time_elapsed | 15309 | +| total_timesteps | 21749760 | +| train/ | | +| approx_kl | 0.012906725 | +| clip_fraction | 0.355 | +| clip_range | 0.0696 | +| entropy_loss | -6.94 | +| explained_variance | -0.153 | +| learning_rate | 4.48e-05 | +| loss | -0.0332 | +| n_updates | 58296 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000101 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1420 | +| iterations | 10621 | +| time_elapsed | 15311 | +| total_timesteps | 21751808 | +| train/ | | +| approx_kl | 0.011496037 | +| clip_fraction | 0.319 | +| clip_range | 0.0696 | +| entropy_loss | -6.53 | +| explained_variance | 0.455 | +| learning_rate | 4.48e-05 | +| loss | -0.0212 | +| n_updates | 58300 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000148 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1420 | +| iterations | 10622 | +| time_elapsed | 15312 | +| total_timesteps | 21753856 | +| train/ | | +| approx_kl | 0.012606786 | +| clip_fraction | 0.303 | +| clip_range | 0.0696 | +| entropy_loss | -6.12 | +| explained_variance | 0.395 | +| learning_rate | 4.48e-05 | +| loss | -0.0283 | +| n_updates | 58304 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000197 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1420 | +| iterations | 10623 | +| time_elapsed | 15314 | +| total_timesteps | 21755904 | +| train/ | | +| approx_kl | 0.008937319 | +| clip_fraction | 0.311 | +| clip_range | 0.0696 | +| entropy_loss | -6.74 | +| explained_variance | 0.117 | +| learning_rate | 4.48e-05 | +| loss | -0.0265 | +| n_updates | 58308 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.00026 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1420 | +| iterations | 10624 | +| time_elapsed | 15315 | +| total_timesteps | 21757952 | +| train/ | | +| approx_kl | 0.011510334 | +| clip_fraction | 0.351 | +| clip_range | 0.0696 | +| entropy_loss | -6.25 | +| explained_variance | 0.48 | +| learning_rate | 4.48e-05 | +| loss | -0.0323 | +| n_updates | 58312 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000155 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1420 | +| iterations | 10625 | +| time_elapsed | 15317 | +| total_timesteps | 21760000 | +| train/ | | +| approx_kl | 0.01332516 | +| clip_fraction | 0.317 | +| clip_range | 0.0696 | +| entropy_loss | -6.76 | +| explained_variance | 0.222 | +| learning_rate | 4.48e-05 | +| loss | -0.031 | +| n_updates | 58316 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000232 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1420 | +| iterations | 10626 | +| time_elapsed | 15318 | +| total_timesteps | 21762048 | +| train/ | | +| approx_kl | 0.0145702455 | +| clip_fraction | 0.333 | +| clip_range | 0.0696 | +| entropy_loss | -6.46 | +| explained_variance | 0.416 | +| learning_rate | 4.48e-05 | +| loss | -0.0313 | +| n_updates | 58320 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.00018 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1420 | +| iterations | 10627 | +| time_elapsed | 15320 | +| total_timesteps | 21764096 | +| train/ | | +| approx_kl | 0.010615619 | +| clip_fraction | 0.301 | +| clip_range | 0.0696 | +| entropy_loss | -6.71 | +| explained_variance | 0.136 | +| learning_rate | 4.48e-05 | +| loss | -0.0243 | +| n_updates | 58324 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000429 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1420 | +| iterations | 10628 | +| time_elapsed | 15321 | +| total_timesteps | 21766144 | +| train/ | | +| approx_kl | 0.01222302 | +| clip_fraction | 0.342 | +| clip_range | 0.0696 | +| entropy_loss | -6.44 | +| explained_variance | 0.466 | +| learning_rate | 4.48e-05 | +| loss | -0.0344 | +| n_updates | 58328 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000172 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1420 | +| iterations | 10629 | +| time_elapsed | 15323 | +| total_timesteps | 21768192 | +| train/ | | +| approx_kl | 0.013088337 | +| clip_fraction | 0.345 | +| clip_range | 0.0696 | +| entropy_loss | -6.14 | +| explained_variance | 0.38 | +| learning_rate | 4.48e-05 | +| loss | -0.0321 | +| n_updates | 58332 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000313 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1420 | +| iterations | 10630 | +| time_elapsed | 15324 | +| total_timesteps | 21770240 | +| train/ | | +| approx_kl | 0.014397649 | +| clip_fraction | 0.348 | +| clip_range | 0.0696 | +| entropy_loss | -6.01 | +| explained_variance | 0.225 | +| learning_rate | 4.48e-05 | +| loss | -0.0264 | +| n_updates | 58336 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000354 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1420 | +| iterations | 10631 | +| time_elapsed | 15325 | +| total_timesteps | 21772288 | +| train/ | | +| approx_kl | 0.015978366 | +| clip_fraction | 0.385 | +| clip_range | 0.0696 | +| entropy_loss | -6.43 | +| explained_variance | 0.353 | +| learning_rate | 4.48e-05 | +| loss | -0.0403 | +| n_updates | 58340 | +| policy_gradient_loss | -0.0267 | +| value_loss | 8.15e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1420 | +| iterations | 10632 | +| time_elapsed | 15327 | +| total_timesteps | 21774336 | +| train/ | | +| approx_kl | 0.014292688 | +| clip_fraction | 0.343 | +| clip_range | 0.0696 | +| entropy_loss | -6.36 | +| explained_variance | 0.54 | +| learning_rate | 4.48e-05 | +| loss | -0.0309 | +| n_updates | 58344 | +| policy_gradient_loss | -0.0207 | +| value_loss | 9.64e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1420 | +| iterations | 10633 | +| time_elapsed | 15328 | +| total_timesteps | 21776384 | +| train/ | | +| approx_kl | 0.011602538 | +| clip_fraction | 0.334 | +| clip_range | 0.0696 | +| entropy_loss | -6.25 | +| explained_variance | 0.558 | +| learning_rate | 4.48e-05 | +| loss | -0.0289 | +| n_updates | 58348 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.00013 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1420 | +| iterations | 10634 | +| time_elapsed | 15330 | +| total_timesteps | 21778432 | +| train/ | | +| approx_kl | 0.012954205 | +| clip_fraction | 0.344 | +| clip_range | 0.0696 | +| entropy_loss | -6.37 | +| explained_variance | 0.505 | +| learning_rate | 4.48e-05 | +| loss | -0.0284 | +| n_updates | 58352 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000103 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1420 | +| iterations | 10635 | +| time_elapsed | 15331 | +| total_timesteps | 21780480 | +| train/ | | +| approx_kl | 0.013595833 | +| clip_fraction | 0.315 | +| clip_range | 0.0696 | +| entropy_loss | -6.83 | +| explained_variance | 0.352 | +| learning_rate | 4.48e-05 | +| loss | -0.034 | +| n_updates | 58356 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000131 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1420 | +| iterations | 10636 | +| time_elapsed | 15333 | +| total_timesteps | 21782528 | +| train/ | | +| approx_kl | 0.013866135 | +| clip_fraction | 0.318 | +| clip_range | 0.0696 | +| entropy_loss | -6.71 | +| explained_variance | 0.418 | +| learning_rate | 4.48e-05 | +| loss | -0.0232 | +| n_updates | 58360 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000195 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 1420 | +| iterations | 10637 | +| time_elapsed | 15334 | +| total_timesteps | 21784576 | +| train/ | | +| approx_kl | 0.013948817 | +| clip_fraction | 0.348 | +| clip_range | 0.0696 | +| entropy_loss | -6.2 | +| explained_variance | 0.438 | +| learning_rate | 4.48e-05 | +| loss | -0.0259 | +| n_updates | 58364 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000167 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.304 | +| time/ | | +| fps | 1420 | +| iterations | 10638 | +| time_elapsed | 15335 | +| total_timesteps | 21786624 | +| train/ | | +| approx_kl | 0.014990892 | +| clip_fraction | 0.362 | +| clip_range | 0.0696 | +| entropy_loss | -6.31 | +| explained_variance | 0.434 | +| learning_rate | 4.48e-05 | +| loss | -0.0316 | +| n_updates | 58368 | +| policy_gradient_loss | -0.0232 | +| value_loss | 9.28e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.304 | +| time/ | | +| fps | 1420 | +| iterations | 10639 | +| time_elapsed | 15337 | +| total_timesteps | 21788672 | +| train/ | | +| approx_kl | 0.013589455 | +| clip_fraction | 0.337 | +| clip_range | 0.0696 | +| entropy_loss | -6.48 | +| explained_variance | 0.496 | +| learning_rate | 4.48e-05 | +| loss | -0.0301 | +| n_updates | 58372 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1420 | +| iterations | 10640 | +| time_elapsed | 15338 | +| total_timesteps | 21790720 | +| train/ | | +| approx_kl | 0.013994761 | +| clip_fraction | 0.364 | +| clip_range | 0.0696 | +| entropy_loss | -6.88 | +| explained_variance | -0.0646 | +| learning_rate | 4.48e-05 | +| loss | -0.0285 | +| n_updates | 58376 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000115 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 1420 | +| iterations | 10641 | +| time_elapsed | 15340 | +| total_timesteps | 21792768 | +| train/ | | +| approx_kl | 0.012834704 | +| clip_fraction | 0.345 | +| clip_range | 0.0696 | +| entropy_loss | -6.41 | +| explained_variance | 0.454 | +| learning_rate | 4.48e-05 | +| loss | -0.0275 | +| n_updates | 58380 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.00021 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 1420 | +| iterations | 10642 | +| time_elapsed | 15341 | +| total_timesteps | 21794816 | +| train/ | | +| approx_kl | 0.012748847 | +| clip_fraction | 0.32 | +| clip_range | 0.0696 | +| entropy_loss | -6.22 | +| explained_variance | 0.449 | +| learning_rate | 4.48e-05 | +| loss | -0.0277 | +| n_updates | 58384 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000177 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 1420 | +| iterations | 10643 | +| time_elapsed | 15343 | +| total_timesteps | 21796864 | +| train/ | | +| approx_kl | 0.013824971 | +| clip_fraction | 0.349 | +| clip_range | 0.0696 | +| entropy_loss | -6.08 | +| explained_variance | 0.559 | +| learning_rate | 4.48e-05 | +| loss | -0.0301 | +| n_updates | 58388 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000101 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 1420 | +| iterations | 10644 | +| time_elapsed | 15344 | +| total_timesteps | 21798912 | +| train/ | | +| approx_kl | 0.015074389 | +| clip_fraction | 0.37 | +| clip_range | 0.0696 | +| entropy_loss | -6.7 | +| explained_variance | -0.117 | +| learning_rate | 4.48e-05 | +| loss | -0.04 | +| n_updates | 58392 | +| policy_gradient_loss | -0.0236 | +| value_loss | 5.33e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 1420 | +| iterations | 10645 | +| time_elapsed | 15346 | +| total_timesteps | 21800960 | +| train/ | | +| approx_kl | 0.018148636 | +| clip_fraction | 0.304 | +| clip_range | 0.0696 | +| entropy_loss | -5.81 | +| explained_variance | 0.664 | +| learning_rate | 4.48e-05 | +| loss | -0.0225 | +| n_updates | 58396 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000202 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 1420 | +| iterations | 10646 | +| time_elapsed | 15347 | +| total_timesteps | 21803008 | +| train/ | | +| approx_kl | 0.015719121 | +| clip_fraction | 0.321 | +| clip_range | 0.0695 | +| entropy_loss | -6.46 | +| explained_variance | -0.0605 | +| learning_rate | 4.48e-05 | +| loss | -0.0253 | +| n_updates | 58400 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000164 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 1420 | +| iterations | 10647 | +| time_elapsed | 15349 | +| total_timesteps | 21805056 | +| train/ | | +| approx_kl | 0.012079034 | +| clip_fraction | 0.347 | +| clip_range | 0.0695 | +| entropy_loss | -6.99 | +| explained_variance | -0.0549 | +| learning_rate | 4.48e-05 | +| loss | -0.0255 | +| n_updates | 58404 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000177 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1420 | +| iterations | 10648 | +| time_elapsed | 15350 | +| total_timesteps | 21807104 | +| train/ | | +| approx_kl | 0.013948338 | +| clip_fraction | 0.316 | +| clip_range | 0.0695 | +| entropy_loss | -6.46 | +| explained_variance | 0.15 | +| learning_rate | 4.48e-05 | +| loss | -0.0243 | +| n_updates | 58408 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.000509 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1420 | +| iterations | 10649 | +| time_elapsed | 15352 | +| total_timesteps | 21809152 | +| train/ | | +| approx_kl | 0.016870193 | +| clip_fraction | 0.31 | +| clip_range | 0.0695 | +| entropy_loss | -5.51 | +| explained_variance | 0.528 | +| learning_rate | 4.48e-05 | +| loss | -0.0237 | +| n_updates | 58412 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000212 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 1420 | +| iterations | 10650 | +| time_elapsed | 15353 | +| total_timesteps | 21811200 | +| train/ | | +| approx_kl | 0.010870643 | +| clip_fraction | 0.355 | +| clip_range | 0.0695 | +| entropy_loss | -6.15 | +| explained_variance | 0.636 | +| learning_rate | 4.48e-05 | +| loss | -0.0384 | +| n_updates | 58416 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000141 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 1420 | +| iterations | 10651 | +| time_elapsed | 15355 | +| total_timesteps | 21813248 | +| train/ | | +| approx_kl | 0.013938755 | +| clip_fraction | 0.333 | +| clip_range | 0.0695 | +| entropy_loss | -6.65 | +| explained_variance | 0.27 | +| learning_rate | 4.48e-05 | +| loss | -0.0321 | +| n_updates | 58420 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000136 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 1420 | +| iterations | 10652 | +| time_elapsed | 15356 | +| total_timesteps | 21815296 | +| train/ | | +| approx_kl | 0.012883082 | +| clip_fraction | 0.35 | +| clip_range | 0.0695 | +| entropy_loss | -7.02 | +| explained_variance | 0.0172 | +| learning_rate | 4.48e-05 | +| loss | -0.0313 | +| n_updates | 58424 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000167 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 1420 | +| iterations | 10653 | +| time_elapsed | 15358 | +| total_timesteps | 21817344 | +| train/ | | +| approx_kl | 0.0141795175 | +| clip_fraction | 0.364 | +| clip_range | 0.0695 | +| entropy_loss | -6.9 | +| explained_variance | -0.119 | +| learning_rate | 4.48e-05 | +| loss | -0.0284 | +| n_updates | 58428 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000121 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1420 | +| iterations | 10654 | +| time_elapsed | 15359 | +| total_timesteps | 21819392 | +| train/ | | +| approx_kl | 0.014320802 | +| clip_fraction | 0.369 | +| clip_range | 0.0695 | +| entropy_loss | -6.69 | +| explained_variance | -0.17 | +| learning_rate | 4.48e-05 | +| loss | -0.0335 | +| n_updates | 58432 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000106 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1420 | +| iterations | 10655 | +| time_elapsed | 15361 | +| total_timesteps | 21821440 | +| train/ | | +| approx_kl | 0.017937168 | +| clip_fraction | 0.286 | +| clip_range | 0.0695 | +| entropy_loss | -6.43 | +| explained_variance | 0.468 | +| learning_rate | 4.48e-05 | +| loss | -0.0267 | +| n_updates | 58436 | +| policy_gradient_loss | -0.0128 | +| value_loss | 0.000251 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1420 | +| iterations | 10656 | +| time_elapsed | 15362 | +| total_timesteps | 21823488 | +| train/ | | +| approx_kl | 0.012324798 | +| clip_fraction | 0.334 | +| clip_range | 0.0695 | +| entropy_loss | -6.06 | +| explained_variance | 0.517 | +| learning_rate | 4.48e-05 | +| loss | -0.0222 | +| n_updates | 58440 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000128 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1420 | +| iterations | 10657 | +| time_elapsed | 15364 | +| total_timesteps | 21825536 | +| train/ | | +| approx_kl | 0.0121919215 | +| clip_fraction | 0.311 | +| clip_range | 0.0695 | +| entropy_loss | -5.84 | +| explained_variance | 0.495 | +| learning_rate | 4.48e-05 | +| loss | -0.0242 | +| n_updates | 58444 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000287 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1420 | +| iterations | 10658 | +| time_elapsed | 15365 | +| total_timesteps | 21827584 | +| train/ | | +| approx_kl | 0.010358779 | +| clip_fraction | 0.33 | +| clip_range | 0.0695 | +| entropy_loss | -6.28 | +| explained_variance | 0.46 | +| learning_rate | 4.48e-05 | +| loss | -0.0325 | +| n_updates | 58448 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000134 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1420 | +| iterations | 10659 | +| time_elapsed | 15366 | +| total_timesteps | 21829632 | +| train/ | | +| approx_kl | 0.014894107 | +| clip_fraction | 0.364 | +| clip_range | 0.0695 | +| entropy_loss | -6.29 | +| explained_variance | 0.546 | +| learning_rate | 4.48e-05 | +| loss | -0.0371 | +| n_updates | 58452 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000132 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.306 | +| time/ | | +| fps | 1420 | +| iterations | 10660 | +| time_elapsed | 15368 | +| total_timesteps | 21831680 | +| train/ | | +| approx_kl | 0.0146770235 | +| clip_fraction | 0.354 | +| clip_range | 0.0695 | +| entropy_loss | -6.46 | +| explained_variance | 0.347 | +| learning_rate | 4.48e-05 | +| loss | -0.0343 | +| n_updates | 58456 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000141 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 1420 | +| iterations | 10661 | +| time_elapsed | 15369 | +| total_timesteps | 21833728 | +| train/ | | +| approx_kl | 0.00947964 | +| clip_fraction | 0.328 | +| clip_range | 0.0695 | +| entropy_loss | -7 | +| explained_variance | -0.105 | +| learning_rate | 4.48e-05 | +| loss | -0.0292 | +| n_updates | 58460 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000223 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.306 | +| time/ | | +| fps | 1420 | +| iterations | 10662 | +| time_elapsed | 15371 | +| total_timesteps | 21835776 | +| train/ | | +| approx_kl | 0.012835187 | +| clip_fraction | 0.342 | +| clip_range | 0.0695 | +| entropy_loss | -7.09 | +| explained_variance | 0.423 | +| learning_rate | 4.48e-05 | +| loss | -0.036 | +| n_updates | 58464 | +| policy_gradient_loss | -0.0219 | +| value_loss | 0.000103 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 1420 | +| iterations | 10663 | +| time_elapsed | 15372 | +| total_timesteps | 21837824 | +| train/ | | +| approx_kl | 0.012536914 | +| clip_fraction | 0.329 | +| clip_range | 0.0695 | +| entropy_loss | -6.32 | +| explained_variance | 0.555 | +| learning_rate | 4.48e-05 | +| loss | -0.027 | +| n_updates | 58468 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000162 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 1420 | +| iterations | 10664 | +| time_elapsed | 15374 | +| total_timesteps | 21839872 | +| train/ | | +| approx_kl | 0.015316074 | +| clip_fraction | 0.368 | +| clip_range | 0.0695 | +| entropy_loss | -6.35 | +| explained_variance | 0.566 | +| learning_rate | 4.48e-05 | +| loss | -0.0384 | +| n_updates | 58472 | +| policy_gradient_loss | -0.024 | +| value_loss | 4.83e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1420 | +| iterations | 10665 | +| time_elapsed | 15375 | +| total_timesteps | 21841920 | +| train/ | | +| approx_kl | 0.012787173 | +| clip_fraction | 0.346 | +| clip_range | 0.0695 | +| entropy_loss | -7.06 | +| explained_variance | -0.0902 | +| learning_rate | 4.48e-05 | +| loss | -0.0312 | +| n_updates | 58476 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000101 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 1420 | +| iterations | 10666 | +| time_elapsed | 15377 | +| total_timesteps | 21843968 | +| train/ | | +| approx_kl | 0.010903455 | +| clip_fraction | 0.296 | +| clip_range | 0.0695 | +| entropy_loss | -7.02 | +| explained_variance | 0.338 | +| learning_rate | 4.48e-05 | +| loss | -0.0296 | +| n_updates | 58480 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000212 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 1420 | +| iterations | 10667 | +| time_elapsed | 15378 | +| total_timesteps | 21846016 | +| train/ | | +| approx_kl | 0.011162119 | +| clip_fraction | 0.299 | +| clip_range | 0.0695 | +| entropy_loss | -5.93 | +| explained_variance | 0.662 | +| learning_rate | 4.48e-05 | +| loss | -0.0258 | +| n_updates | 58484 | +| policy_gradient_loss | -0.0145 | +| value_loss | 0.000189 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1420 | +| iterations | 10668 | +| time_elapsed | 15380 | +| total_timesteps | 21848064 | +| train/ | | +| approx_kl | 0.01438012 | +| clip_fraction | 0.37 | +| clip_range | 0.0695 | +| entropy_loss | -6.36 | +| explained_variance | 0.542 | +| learning_rate | 4.48e-05 | +| loss | -0.038 | +| n_updates | 58488 | +| policy_gradient_loss | -0.0248 | +| value_loss | 7.79e-05 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1420 | +| iterations | 10669 | +| time_elapsed | 15381 | +| total_timesteps | 21850112 | +| train/ | | +| approx_kl | 0.01205004 | +| clip_fraction | 0.348 | +| clip_range | 0.0695 | +| entropy_loss | -6.27 | +| explained_variance | 0.651 | +| learning_rate | 4.48e-05 | +| loss | -0.0305 | +| n_updates | 58492 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000115 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1420 | +| iterations | 10670 | +| time_elapsed | 15383 | +| total_timesteps | 21852160 | +| train/ | | +| approx_kl | 0.013830716 | +| clip_fraction | 0.36 | +| clip_range | 0.0695 | +| entropy_loss | -6.12 | +| explained_variance | 0.627 | +| learning_rate | 4.48e-05 | +| loss | -0.0233 | +| n_updates | 58496 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000145 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1420 | +| iterations | 10671 | +| time_elapsed | 15384 | +| total_timesteps | 21854208 | +| train/ | | +| approx_kl | 0.01713568 | +| clip_fraction | 0.359 | +| clip_range | 0.0695 | +| entropy_loss | -6.09 | +| explained_variance | -0.164 | +| learning_rate | 4.48e-05 | +| loss | -0.0335 | +| n_updates | 58500 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000179 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 1420 | +| iterations | 10672 | +| time_elapsed | 15386 | +| total_timesteps | 21856256 | +| train/ | | +| approx_kl | 0.014441982 | +| clip_fraction | 0.344 | +| clip_range | 0.0695 | +| entropy_loss | -6.38 | +| explained_variance | 0.188 | +| learning_rate | 4.48e-05 | +| loss | -0.0283 | +| n_updates | 58504 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000233 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.304 | +| time/ | | +| fps | 1420 | +| iterations | 10673 | +| time_elapsed | 15387 | +| total_timesteps | 21858304 | +| train/ | | +| approx_kl | 0.014806153 | +| clip_fraction | 0.358 | +| clip_range | 0.0695 | +| entropy_loss | -6.56 | +| explained_variance | 0.217 | +| learning_rate | 4.48e-05 | +| loss | -0.0383 | +| n_updates | 58508 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000129 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.302 | +| time/ | | +| fps | 1420 | +| iterations | 10674 | +| time_elapsed | 15389 | +| total_timesteps | 21860352 | +| train/ | | +| approx_kl | 0.013029028 | +| clip_fraction | 0.342 | +| clip_range | 0.0695 | +| entropy_loss | -6.51 | +| explained_variance | 0.284 | +| learning_rate | 4.48e-05 | +| loss | -0.0299 | +| n_updates | 58512 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000134 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 1420 | +| iterations | 10675 | +| time_elapsed | 15390 | +| total_timesteps | 21862400 | +| train/ | | +| approx_kl | 0.013406936 | +| clip_fraction | 0.389 | +| clip_range | 0.0695 | +| entropy_loss | -6.76 | +| explained_variance | 0.0196 | +| learning_rate | 4.48e-05 | +| loss | -0.0341 | +| n_updates | 58516 | +| policy_gradient_loss | -0.0201 | +| value_loss | 9.75e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.3 | +| time/ | | +| fps | 1420 | +| iterations | 10676 | +| time_elapsed | 15392 | +| total_timesteps | 21864448 | +| train/ | | +| approx_kl | 0.015050374 | +| clip_fraction | 0.333 | +| clip_range | 0.0695 | +| entropy_loss | -6.49 | +| explained_variance | 0.658 | +| learning_rate | 4.48e-05 | +| loss | -0.0354 | +| n_updates | 58520 | +| policy_gradient_loss | -0.0196 | +| value_loss | 8.36e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.304 | +| time/ | | +| fps | 1420 | +| iterations | 10677 | +| time_elapsed | 15393 | +| total_timesteps | 21866496 | +| train/ | | +| approx_kl | 0.013976378 | +| clip_fraction | 0.339 | +| clip_range | 0.0695 | +| entropy_loss | -6.6 | +| explained_variance | 0.436 | +| learning_rate | 4.48e-05 | +| loss | -0.0309 | +| n_updates | 58524 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.00011 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.302 | +| time/ | | +| fps | 1420 | +| iterations | 10678 | +| time_elapsed | 15395 | +| total_timesteps | 21868544 | +| train/ | | +| approx_kl | 0.012632653 | +| clip_fraction | 0.336 | +| clip_range | 0.0695 | +| entropy_loss | -6.38 | +| explained_variance | 0.461 | +| learning_rate | 4.48e-05 | +| loss | -0.0276 | +| n_updates | 58528 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000165 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.302 | +| time/ | | +| fps | 1420 | +| iterations | 10679 | +| time_elapsed | 15396 | +| total_timesteps | 21870592 | +| train/ | | +| approx_kl | 0.012345236 | +| clip_fraction | 0.363 | +| clip_range | 0.0695 | +| entropy_loss | -6.2 | +| explained_variance | 0.796 | +| learning_rate | 4.48e-05 | +| loss | -0.0318 | +| n_updates | 58532 | +| policy_gradient_loss | -0.0222 | +| value_loss | 6.14e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.306 | +| time/ | | +| fps | 1420 | +| iterations | 10680 | +| time_elapsed | 15397 | +| total_timesteps | 21872640 | +| train/ | | +| approx_kl | 0.013139017 | +| clip_fraction | 0.328 | +| clip_range | 0.0695 | +| entropy_loss | -6.44 | +| explained_variance | 0.439 | +| learning_rate | 4.48e-05 | +| loss | -0.0294 | +| n_updates | 58536 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000159 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1420 | +| iterations | 10681 | +| time_elapsed | 15399 | +| total_timesteps | 21874688 | +| train/ | | +| approx_kl | 0.012664314 | +| clip_fraction | 0.351 | +| clip_range | 0.0695 | +| entropy_loss | -6.76 | +| explained_variance | 0.0358 | +| learning_rate | 4.48e-05 | +| loss | -0.0323 | +| n_updates | 58540 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 1420 | +| iterations | 10682 | +| time_elapsed | 15400 | +| total_timesteps | 21876736 | +| train/ | | +| approx_kl | 0.010314887 | +| clip_fraction | 0.329 | +| clip_range | 0.0695 | +| entropy_loss | -6.68 | +| explained_variance | 0.744 | +| learning_rate | 4.48e-05 | +| loss | -0.0313 | +| n_updates | 58544 | +| policy_gradient_loss | -0.0198 | +| value_loss | 5.43e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 1420 | +| iterations | 10683 | +| time_elapsed | 15402 | +| total_timesteps | 21878784 | +| train/ | | +| approx_kl | 0.012185583 | +| clip_fraction | 0.334 | +| clip_range | 0.0695 | +| entropy_loss | -6.79 | +| explained_variance | 0.374 | +| learning_rate | 4.48e-05 | +| loss | -0.029 | +| n_updates | 58548 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.00011 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.298 | +| time/ | | +| fps | 1420 | +| iterations | 10684 | +| time_elapsed | 15403 | +| total_timesteps | 21880832 | +| train/ | | +| approx_kl | 0.015065465 | +| clip_fraction | 0.329 | +| clip_range | 0.0695 | +| entropy_loss | -5.66 | +| explained_variance | 0.794 | +| learning_rate | 4.48e-05 | +| loss | -0.0308 | +| n_updates | 58552 | +| policy_gradient_loss | -0.0196 | +| value_loss | 8.11e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 1420 | +| iterations | 10685 | +| time_elapsed | 15405 | +| total_timesteps | 21882880 | +| train/ | | +| approx_kl | 0.013608921 | +| clip_fraction | 0.338 | +| clip_range | 0.0695 | +| entropy_loss | -6.46 | +| explained_variance | 0.406 | +| learning_rate | 4.48e-05 | +| loss | -0.0289 | +| n_updates | 58556 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000113 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 1420 | +| iterations | 10686 | +| time_elapsed | 15406 | +| total_timesteps | 21884928 | +| train/ | | +| approx_kl | 0.015395183 | +| clip_fraction | 0.335 | +| clip_range | 0.0695 | +| entropy_loss | -6.76 | +| explained_variance | 0.313 | +| learning_rate | 4.48e-05 | +| loss | -0.035 | +| n_updates | 58560 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000175 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 1420 | +| iterations | 10687 | +| time_elapsed | 15408 | +| total_timesteps | 21886976 | +| train/ | | +| approx_kl | 0.013279834 | +| clip_fraction | 0.35 | +| clip_range | 0.0695 | +| entropy_loss | -6.33 | +| explained_variance | 0.288 | +| learning_rate | 4.48e-05 | +| loss | -0.022 | +| n_updates | 58564 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000351 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 1420 | +| iterations | 10688 | +| time_elapsed | 15409 | +| total_timesteps | 21889024 | +| train/ | | +| approx_kl | 0.0103320945 | +| clip_fraction | 0.307 | +| clip_range | 0.0695 | +| entropy_loss | -6.07 | +| explained_variance | 0.598 | +| learning_rate | 4.48e-05 | +| loss | -0.0308 | +| n_updates | 58568 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000142 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 1420 | +| iterations | 10689 | +| time_elapsed | 15411 | +| total_timesteps | 21891072 | +| train/ | | +| approx_kl | 0.012881864 | +| clip_fraction | 0.32 | +| clip_range | 0.0695 | +| entropy_loss | -6.91 | +| explained_variance | 0.319 | +| learning_rate | 4.48e-05 | +| loss | -0.0292 | +| n_updates | 58572 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000194 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.3 | +| time/ | | +| fps | 1420 | +| iterations | 10690 | +| time_elapsed | 15412 | +| total_timesteps | 21893120 | +| train/ | | +| approx_kl | 0.014281937 | +| clip_fraction | 0.324 | +| clip_range | 0.0695 | +| entropy_loss | -7 | +| explained_variance | -0.138 | +| learning_rate | 4.48e-05 | +| loss | -0.0304 | +| n_updates | 58576 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000191 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.302 | +| time/ | | +| fps | 1420 | +| iterations | 10691 | +| time_elapsed | 15413 | +| total_timesteps | 21895168 | +| train/ | | +| approx_kl | 0.0141745135 | +| clip_fraction | 0.312 | +| clip_range | 0.0695 | +| entropy_loss | -6.8 | +| explained_variance | 0.21 | +| learning_rate | 4.48e-05 | +| loss | -0.0315 | +| n_updates | 58580 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000217 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1420 | +| iterations | 10692 | +| time_elapsed | 15415 | +| total_timesteps | 21897216 | +| train/ | | +| approx_kl | 0.014335171 | +| clip_fraction | 0.333 | +| clip_range | 0.0695 | +| entropy_loss | -6.7 | +| explained_variance | 0.402 | +| learning_rate | 4.48e-05 | +| loss | -0.0335 | +| n_updates | 58584 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 1420 | +| iterations | 10693 | +| time_elapsed | 15416 | +| total_timesteps | 21899264 | +| train/ | | +| approx_kl | 0.011612934 | +| clip_fraction | 0.291 | +| clip_range | 0.0695 | +| entropy_loss | -6.75 | +| explained_variance | 0.239 | +| learning_rate | 4.48e-05 | +| loss | -0.026 | +| n_updates | 58588 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000188 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1420 | +| iterations | 10694 | +| time_elapsed | 15418 | +| total_timesteps | 21901312 | +| train/ | | +| approx_kl | 0.011120096 | +| clip_fraction | 0.32 | +| clip_range | 0.0695 | +| entropy_loss | -6.44 | +| explained_variance | 0.476 | +| learning_rate | 4.48e-05 | +| loss | -0.0335 | +| n_updates | 58592 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000102 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1420 | +| iterations | 10695 | +| time_elapsed | 15419 | +| total_timesteps | 21903360 | +| train/ | | +| approx_kl | 0.01505129 | +| clip_fraction | 0.305 | +| clip_range | 0.0695 | +| entropy_loss | -6.38 | +| explained_variance | 0.454 | +| learning_rate | 4.48e-05 | +| loss | -0.028 | +| n_updates | 58596 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000208 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1420 | +| iterations | 10696 | +| time_elapsed | 15421 | +| total_timesteps | 21905408 | +| train/ | | +| approx_kl | 0.014011888 | +| clip_fraction | 0.358 | +| clip_range | 0.0695 | +| entropy_loss | -6.75 | +| explained_variance | 0.362 | +| learning_rate | 4.48e-05 | +| loss | -0.0322 | +| n_updates | 58600 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000116 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1420 | +| iterations | 10697 | +| time_elapsed | 15422 | +| total_timesteps | 21907456 | +| train/ | | +| approx_kl | 0.013741646 | +| clip_fraction | 0.353 | +| clip_range | 0.0695 | +| entropy_loss | -6.17 | +| explained_variance | 0.356 | +| learning_rate | 4.48e-05 | +| loss | -0.0302 | +| n_updates | 58604 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000305 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1420 | +| iterations | 10698 | +| time_elapsed | 15424 | +| total_timesteps | 21909504 | +| train/ | | +| approx_kl | 0.0126974415 | +| clip_fraction | 0.356 | +| clip_range | 0.0695 | +| entropy_loss | -6.19 | +| explained_variance | 0.595 | +| learning_rate | 4.48e-05 | +| loss | -0.0291 | +| n_updates | 58608 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000109 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1420 | +| iterations | 10699 | +| time_elapsed | 15425 | +| total_timesteps | 21911552 | +| train/ | | +| approx_kl | 0.013643405 | +| clip_fraction | 0.337 | +| clip_range | 0.0695 | +| entropy_loss | -6.71 | +| explained_variance | 0.11 | +| learning_rate | 4.48e-05 | +| loss | -0.0318 | +| n_updates | 58612 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000192 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1420 | +| iterations | 10700 | +| time_elapsed | 15427 | +| total_timesteps | 21913600 | +| train/ | | +| approx_kl | 0.017614923 | +| clip_fraction | 0.367 | +| clip_range | 0.0695 | +| entropy_loss | -6.92 | +| explained_variance | -0.0971 | +| learning_rate | 4.48e-05 | +| loss | -0.0377 | +| n_updates | 58616 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000146 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1420 | +| iterations | 10701 | +| time_elapsed | 15428 | +| total_timesteps | 21915648 | +| train/ | | +| approx_kl | 0.015777156 | +| clip_fraction | 0.355 | +| clip_range | 0.0695 | +| entropy_loss | -6.69 | +| explained_variance | 0.343 | +| learning_rate | 4.48e-05 | +| loss | -0.0317 | +| n_updates | 58620 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000125 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1420 | +| iterations | 10702 | +| time_elapsed | 15430 | +| total_timesteps | 21917696 | +| train/ | | +| approx_kl | 0.014622211 | +| clip_fraction | 0.358 | +| clip_range | 0.0695 | +| entropy_loss | -6.63 | +| explained_variance | 0.3 | +| learning_rate | 4.48e-05 | +| loss | -0.0361 | +| n_updates | 58624 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000114 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1420 | +| iterations | 10703 | +| time_elapsed | 15431 | +| total_timesteps | 21919744 | +| train/ | | +| approx_kl | 0.016494384 | +| clip_fraction | 0.327 | +| clip_range | 0.0695 | +| entropy_loss | -6.37 | +| explained_variance | 0.619 | +| learning_rate | 4.48e-05 | +| loss | -0.0343 | +| n_updates | 58628 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000124 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1420 | +| iterations | 10704 | +| time_elapsed | 15433 | +| total_timesteps | 21921792 | +| train/ | | +| approx_kl | 0.01619083 | +| clip_fraction | 0.331 | +| clip_range | 0.0695 | +| entropy_loss | -6.7 | +| explained_variance | -0.0735 | +| learning_rate | 4.48e-05 | +| loss | -0.0349 | +| n_updates | 58632 | +| policy_gradient_loss | -0.0194 | +| value_loss | 8.83e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1420 | +| iterations | 10705 | +| time_elapsed | 15434 | +| total_timesteps | 21923840 | +| train/ | | +| approx_kl | 0.012650777 | +| clip_fraction | 0.284 | +| clip_range | 0.0695 | +| entropy_loss | -6.88 | +| explained_variance | 0.363 | +| learning_rate | 4.48e-05 | +| loss | -0.0279 | +| n_updates | 58636 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000121 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1420 | +| iterations | 10706 | +| time_elapsed | 15436 | +| total_timesteps | 21925888 | +| train/ | | +| approx_kl | 0.011576235 | +| clip_fraction | 0.335 | +| clip_range | 0.0695 | +| entropy_loss | -7.06 | +| explained_variance | -0.114 | +| learning_rate | 4.48e-05 | +| loss | -0.0303 | +| n_updates | 58640 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.00016 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1420 | +| iterations | 10707 | +| time_elapsed | 15437 | +| total_timesteps | 21927936 | +| train/ | | +| approx_kl | 0.012868039 | +| clip_fraction | 0.327 | +| clip_range | 0.0695 | +| entropy_loss | -6.53 | +| explained_variance | 0.135 | +| learning_rate | 4.48e-05 | +| loss | -0.0262 | +| n_updates | 58644 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000304 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1420 | +| iterations | 10708 | +| time_elapsed | 15439 | +| total_timesteps | 21929984 | +| train/ | | +| approx_kl | 0.01501314 | +| clip_fraction | 0.378 | +| clip_range | 0.0695 | +| entropy_loss | -6.37 | +| explained_variance | 0.534 | +| learning_rate | 4.48e-05 | +| loss | -0.0322 | +| n_updates | 58648 | +| policy_gradient_loss | -0.0202 | +| value_loss | 9.27e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1420 | +| iterations | 10709 | +| time_elapsed | 15440 | +| total_timesteps | 21932032 | +| train/ | | +| approx_kl | 0.013309923 | +| clip_fraction | 0.342 | +| clip_range | 0.0695 | +| entropy_loss | -6.34 | +| explained_variance | 0.643 | +| learning_rate | 4.48e-05 | +| loss | -0.0271 | +| n_updates | 58652 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.00012 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1420 | +| iterations | 10710 | +| time_elapsed | 15442 | +| total_timesteps | 21934080 | +| train/ | | +| approx_kl | 0.010004912 | +| clip_fraction | 0.279 | +| clip_range | 0.0695 | +| entropy_loss | -6.2 | +| explained_variance | 0.423 | +| learning_rate | 4.48e-05 | +| loss | -0.0204 | +| n_updates | 58656 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.000252 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1420 | +| iterations | 10711 | +| time_elapsed | 15443 | +| total_timesteps | 21936128 | +| train/ | | +| approx_kl | 0.012912457 | +| clip_fraction | 0.321 | +| clip_range | 0.0695 | +| entropy_loss | -6.25 | +| explained_variance | 0.639 | +| learning_rate | 4.48e-05 | +| loss | -0.0303 | +| n_updates | 58660 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000144 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1420 | +| iterations | 10712 | +| time_elapsed | 15445 | +| total_timesteps | 21938176 | +| train/ | | +| approx_kl | 0.012621481 | +| clip_fraction | 0.327 | +| clip_range | 0.0695 | +| entropy_loss | -7.15 | +| explained_variance | -0.233 | +| learning_rate | 4.48e-05 | +| loss | -0.0313 | +| n_updates | 58664 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000137 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1420 | +| iterations | 10713 | +| time_elapsed | 15446 | +| total_timesteps | 21940224 | +| train/ | | +| approx_kl | 0.01410019 | +| clip_fraction | 0.339 | +| clip_range | 0.0695 | +| entropy_loss | -6.86 | +| explained_variance | 0.323 | +| learning_rate | 4.48e-05 | +| loss | -0.0337 | +| n_updates | 58668 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000119 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1420 | +| iterations | 10714 | +| time_elapsed | 15447 | +| total_timesteps | 21942272 | +| train/ | | +| approx_kl | 0.01252982 | +| clip_fraction | 0.292 | +| clip_range | 0.0695 | +| entropy_loss | -6.88 | +| explained_variance | 0.29 | +| learning_rate | 4.48e-05 | +| loss | -0.027 | +| n_updates | 58672 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000206 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1420 | +| iterations | 10715 | +| time_elapsed | 15449 | +| total_timesteps | 21944320 | +| train/ | | +| approx_kl | 0.0137769645 | +| clip_fraction | 0.348 | +| clip_range | 0.0695 | +| entropy_loss | -6.84 | +| explained_variance | -0.241 | +| learning_rate | 4.48e-05 | +| loss | -0.0346 | +| n_updates | 58676 | +| policy_gradient_loss | -0.0197 | +| value_loss | 6.74e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1420 | +| iterations | 10716 | +| time_elapsed | 15450 | +| total_timesteps | 21946368 | +| train/ | | +| approx_kl | 0.011825196 | +| clip_fraction | 0.312 | +| clip_range | 0.0695 | +| entropy_loss | -6.56 | +| explained_variance | 0.12 | +| learning_rate | 4.48e-05 | +| loss | -0.0288 | +| n_updates | 58680 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000394 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1420 | +| iterations | 10717 | +| time_elapsed | 15452 | +| total_timesteps | 21948416 | +| train/ | | +| approx_kl | 0.010745667 | +| clip_fraction | 0.312 | +| clip_range | 0.0695 | +| entropy_loss | -6.63 | +| explained_variance | 0.122 | +| learning_rate | 4.48e-05 | +| loss | -0.0329 | +| n_updates | 58684 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000231 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1420 | +| iterations | 10718 | +| time_elapsed | 15453 | +| total_timesteps | 21950464 | +| train/ | | +| approx_kl | 0.011758108 | +| clip_fraction | 0.297 | +| clip_range | 0.0695 | +| entropy_loss | -5.91 | +| explained_variance | 0.618 | +| learning_rate | 4.48e-05 | +| loss | -0.0251 | +| n_updates | 58688 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000177 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1420 | +| iterations | 10719 | +| time_elapsed | 15455 | +| total_timesteps | 21952512 | +| train/ | | +| approx_kl | 0.013026021 | +| clip_fraction | 0.344 | +| clip_range | 0.0695 | +| entropy_loss | -6.7 | +| explained_variance | 0.285 | +| learning_rate | 4.48e-05 | +| loss | -0.0319 | +| n_updates | 58692 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.00012 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1420 | +| iterations | 10720 | +| time_elapsed | 15456 | +| total_timesteps | 21954560 | +| train/ | | +| approx_kl | 0.014179291 | +| clip_fraction | 0.338 | +| clip_range | 0.0695 | +| entropy_loss | -6.6 | +| explained_variance | 0.226 | +| learning_rate | 4.48e-05 | +| loss | -0.0262 | +| n_updates | 58696 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000223 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1420 | +| iterations | 10721 | +| time_elapsed | 15458 | +| total_timesteps | 21956608 | +| train/ | | +| approx_kl | 0.011317121 | +| clip_fraction | 0.346 | +| clip_range | 0.0695 | +| entropy_loss | -6.7 | +| explained_variance | 0.356 | +| learning_rate | 4.48e-05 | +| loss | -0.0358 | +| n_updates | 58700 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000158 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1420 | +| iterations | 10722 | +| time_elapsed | 15459 | +| total_timesteps | 21958656 | +| train/ | | +| approx_kl | 0.00969109 | +| clip_fraction | 0.307 | +| clip_range | 0.0695 | +| entropy_loss | -6.8 | +| explained_variance | 0.227 | +| learning_rate | 4.48e-05 | +| loss | -0.0263 | +| n_updates | 58704 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000357 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1420 | +| iterations | 10723 | +| time_elapsed | 15461 | +| total_timesteps | 21960704 | +| train/ | | +| approx_kl | 0.0091341045 | +| clip_fraction | 0.304 | +| clip_range | 0.0695 | +| entropy_loss | -6.02 | +| explained_variance | 0.514 | +| learning_rate | 4.48e-05 | +| loss | -0.0229 | +| n_updates | 58708 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000273 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1420 | +| iterations | 10724 | +| time_elapsed | 15462 | +| total_timesteps | 21962752 | +| train/ | | +| approx_kl | 0.010127582 | +| clip_fraction | 0.305 | +| clip_range | 0.0695 | +| entropy_loss | -6.53 | +| explained_variance | 0.305 | +| learning_rate | 4.48e-05 | +| loss | -0.024 | +| n_updates | 58712 | +| policy_gradient_loss | -0.0143 | +| value_loss | 0.000244 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1420 | +| iterations | 10725 | +| time_elapsed | 15463 | +| total_timesteps | 21964800 | +| train/ | | +| approx_kl | 0.013003716 | +| clip_fraction | 0.37 | +| clip_range | 0.0695 | +| entropy_loss | -6.33 | +| explained_variance | 0.548 | +| learning_rate | 4.48e-05 | +| loss | -0.0347 | +| n_updates | 58716 | +| policy_gradient_loss | -0.0221 | +| value_loss | 0.000117 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1420 | +| iterations | 10726 | +| time_elapsed | 15465 | +| total_timesteps | 21966848 | +| train/ | | +| approx_kl | 0.01380277 | +| clip_fraction | 0.339 | +| clip_range | 0.0695 | +| entropy_loss | -6.86 | +| explained_variance | 0.0638 | +| learning_rate | 4.48e-05 | +| loss | -0.0333 | +| n_updates | 58720 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000116 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1420 | +| iterations | 10727 | +| time_elapsed | 15466 | +| total_timesteps | 21968896 | +| train/ | | +| approx_kl | 0.014090223 | +| clip_fraction | 0.347 | +| clip_range | 0.0695 | +| entropy_loss | -6.62 | +| explained_variance | 0.353 | +| learning_rate | 4.48e-05 | +| loss | -0.0289 | +| n_updates | 58724 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000119 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1420 | +| iterations | 10728 | +| time_elapsed | 15468 | +| total_timesteps | 21970944 | +| train/ | | +| approx_kl | 0.012781711 | +| clip_fraction | 0.343 | +| clip_range | 0.0695 | +| entropy_loss | -6.95 | +| explained_variance | 0.33 | +| learning_rate | 4.48e-05 | +| loss | -0.0337 | +| n_updates | 58728 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.0002 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1420 | +| iterations | 10729 | +| time_elapsed | 15469 | +| total_timesteps | 21972992 | +| train/ | | +| approx_kl | 0.013727406 | +| clip_fraction | 0.377 | +| clip_range | 0.0695 | +| entropy_loss | -6.71 | +| explained_variance | 0.125 | +| learning_rate | 4.48e-05 | +| loss | -0.0342 | +| n_updates | 58732 | +| policy_gradient_loss | -0.0231 | +| value_loss | 8.63e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1420 | +| iterations | 10730 | +| time_elapsed | 15471 | +| total_timesteps | 21975040 | +| train/ | | +| approx_kl | 0.012647305 | +| clip_fraction | 0.323 | +| clip_range | 0.0695 | +| entropy_loss | -6.51 | +| explained_variance | 0.438 | +| learning_rate | 4.48e-05 | +| loss | -0.0277 | +| n_updates | 58736 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000253 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1420 | +| iterations | 10731 | +| time_elapsed | 15472 | +| total_timesteps | 21977088 | +| train/ | | +| approx_kl | 0.016202508 | +| clip_fraction | 0.332 | +| clip_range | 0.0695 | +| entropy_loss | -6.22 | +| explained_variance | 0.252 | +| learning_rate | 4.48e-05 | +| loss | -0.0303 | +| n_updates | 58740 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000298 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1420 | +| iterations | 10732 | +| time_elapsed | 15474 | +| total_timesteps | 21979136 | +| train/ | | +| approx_kl | 0.015058862 | +| clip_fraction | 0.341 | +| clip_range | 0.0695 | +| entropy_loss | -6.67 | +| explained_variance | 0.413 | +| learning_rate | 4.48e-05 | +| loss | -0.0342 | +| n_updates | 58744 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000137 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1420 | +| iterations | 10733 | +| time_elapsed | 15475 | +| total_timesteps | 21981184 | +| train/ | | +| approx_kl | 0.012530867 | +| clip_fraction | 0.309 | +| clip_range | 0.0695 | +| entropy_loss | -6.41 | +| explained_variance | 0.635 | +| learning_rate | 4.48e-05 | +| loss | -0.0298 | +| n_updates | 58748 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000179 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1420 | +| iterations | 10734 | +| time_elapsed | 15476 | +| total_timesteps | 21983232 | +| train/ | | +| approx_kl | 0.012946592 | +| clip_fraction | 0.332 | +| clip_range | 0.0695 | +| entropy_loss | -6.2 | +| explained_variance | 0.192 | +| learning_rate | 4.48e-05 | +| loss | -0.0254 | +| n_updates | 58752 | +| policy_gradient_loss | -0.0173 | +| value_loss | 9.92e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1420 | +| iterations | 10735 | +| time_elapsed | 15478 | +| total_timesteps | 21985280 | +| train/ | | +| approx_kl | 0.012446404 | +| clip_fraction | 0.321 | +| clip_range | 0.0695 | +| entropy_loss | -6.3 | +| explained_variance | 0.515 | +| learning_rate | 4.48e-05 | +| loss | -0.0307 | +| n_updates | 58756 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000161 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1420 | +| iterations | 10736 | +| time_elapsed | 15479 | +| total_timesteps | 21987328 | +| train/ | | +| approx_kl | 0.014422903 | +| clip_fraction | 0.347 | +| clip_range | 0.0695 | +| entropy_loss | -6.59 | +| explained_variance | 0.338 | +| learning_rate | 4.48e-05 | +| loss | -0.0283 | +| n_updates | 58760 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000111 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1420 | +| iterations | 10737 | +| time_elapsed | 15481 | +| total_timesteps | 21989376 | +| train/ | | +| approx_kl | 0.014160299 | +| clip_fraction | 0.353 | +| clip_range | 0.0695 | +| entropy_loss | -6.78 | +| explained_variance | 0.122 | +| learning_rate | 4.48e-05 | +| loss | -0.0271 | +| n_updates | 58764 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000306 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1420 | +| iterations | 10738 | +| time_elapsed | 15482 | +| total_timesteps | 21991424 | +| train/ | | +| approx_kl | 0.01494478 | +| clip_fraction | 0.357 | +| clip_range | 0.0695 | +| entropy_loss | -6.63 | +| explained_variance | 0.322 | +| learning_rate | 4.48e-05 | +| loss | -0.0317 | +| n_updates | 58768 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000142 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1420 | +| iterations | 10739 | +| time_elapsed | 15484 | +| total_timesteps | 21993472 | +| train/ | | +| approx_kl | 0.012795565 | +| clip_fraction | 0.322 | +| clip_range | 0.0695 | +| entropy_loss | -6.58 | +| explained_variance | 0.23 | +| learning_rate | 4.48e-05 | +| loss | -0.0303 | +| n_updates | 58772 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000366 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1420 | +| iterations | 10740 | +| time_elapsed | 15485 | +| total_timesteps | 21995520 | +| train/ | | +| approx_kl | 0.012369515 | +| clip_fraction | 0.35 | +| clip_range | 0.0695 | +| entropy_loss | -6.6 | +| explained_variance | 0.389 | +| learning_rate | 4.48e-05 | +| loss | -0.039 | +| n_updates | 58776 | +| policy_gradient_loss | -0.0235 | +| value_loss | 0.000174 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1420 | +| iterations | 10741 | +| time_elapsed | 15486 | +| total_timesteps | 21997568 | +| train/ | | +| approx_kl | 0.013241564 | +| clip_fraction | 0.333 | +| clip_range | 0.0695 | +| entropy_loss | -6.82 | +| explained_variance | 0.0761 | +| learning_rate | 4.48e-05 | +| loss | -0.0374 | +| n_updates | 58780 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1420 | +| iterations | 10742 | +| time_elapsed | 15488 | +| total_timesteps | 21999616 | +| train/ | | +| approx_kl | 0.013974002 | +| clip_fraction | 0.374 | +| clip_range | 0.0695 | +| entropy_loss | -6.2 | +| explained_variance | 0.678 | +| learning_rate | 4.48e-05 | +| loss | -0.0363 | +| n_updates | 58784 | +| policy_gradient_loss | -0.0226 | +| value_loss | 6.89e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1420 | +| iterations | 10743 | +| time_elapsed | 15489 | +| total_timesteps | 22001664 | +| train/ | | +| approx_kl | 0.013959163 | +| clip_fraction | 0.337 | +| clip_range | 0.0695 | +| entropy_loss | -6.51 | +| explained_variance | 0.45 | +| learning_rate | 4.48e-05 | +| loss | -0.031 | +| n_updates | 58788 | +| policy_gradient_loss | -0.0213 | +| value_loss | 7.95e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1420 | +| iterations | 10744 | +| time_elapsed | 15491 | +| total_timesteps | 22003712 | +| train/ | | +| approx_kl | 0.013164955 | +| clip_fraction | 0.311 | +| clip_range | 0.0695 | +| entropy_loss | -6.19 | +| explained_variance | 0.484 | +| learning_rate | 4.48e-05 | +| loss | -0.0264 | +| n_updates | 58792 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000224 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1420 | +| iterations | 10745 | +| time_elapsed | 15492 | +| total_timesteps | 22005760 | +| train/ | | +| approx_kl | 0.015236374 | +| clip_fraction | 0.361 | +| clip_range | 0.0695 | +| entropy_loss | -6.71 | +| explained_variance | 0.329 | +| learning_rate | 4.48e-05 | +| loss | -0.0355 | +| n_updates | 58796 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000139 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1420 | +| iterations | 10746 | +| time_elapsed | 15494 | +| total_timesteps | 22007808 | +| train/ | | +| approx_kl | 0.013254872 | +| clip_fraction | 0.341 | +| clip_range | 0.0695 | +| entropy_loss | -5.74 | +| explained_variance | 0.543 | +| learning_rate | 4.48e-05 | +| loss | -0.0296 | +| n_updates | 58800 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000293 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1420 | +| iterations | 10747 | +| time_elapsed | 15495 | +| total_timesteps | 22009856 | +| train/ | | +| approx_kl | 0.014137183 | +| clip_fraction | 0.37 | +| clip_range | 0.0695 | +| entropy_loss | -6.63 | +| explained_variance | 0.153 | +| learning_rate | 4.48e-05 | +| loss | -0.0389 | +| n_updates | 58804 | +| policy_gradient_loss | -0.0225 | +| value_loss | 9.91e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1420 | +| iterations | 10748 | +| time_elapsed | 15497 | +| total_timesteps | 22011904 | +| train/ | | +| approx_kl | 0.012350242 | +| clip_fraction | 0.338 | +| clip_range | 0.0695 | +| entropy_loss | -6.59 | +| explained_variance | 0.403 | +| learning_rate | 4.48e-05 | +| loss | -0.0307 | +| n_updates | 58808 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.00014 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.384 | +| time/ | | +| fps | 1420 | +| iterations | 10749 | +| time_elapsed | 15498 | +| total_timesteps | 22013952 | +| train/ | | +| approx_kl | 0.013539167 | +| clip_fraction | 0.364 | +| clip_range | 0.0695 | +| entropy_loss | -6.99 | +| explained_variance | 0.05 | +| learning_rate | 4.48e-05 | +| loss | -0.0347 | +| n_updates | 58812 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000172 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1420 | +| iterations | 10750 | +| time_elapsed | 15500 | +| total_timesteps | 22016000 | +| train/ | | +| approx_kl | 0.012633194 | +| clip_fraction | 0.327 | +| clip_range | 0.0695 | +| entropy_loss | -6.57 | +| explained_variance | 0.4 | +| learning_rate | 4.48e-05 | +| loss | -0.0231 | +| n_updates | 58816 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.00023 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1420 | +| iterations | 10751 | +| time_elapsed | 15501 | +| total_timesteps | 22018048 | +| train/ | | +| approx_kl | 0.014134401 | +| clip_fraction | 0.354 | +| clip_range | 0.0695 | +| entropy_loss | -6.68 | +| explained_variance | 0.222 | +| learning_rate | 4.48e-05 | +| loss | -0.0316 | +| n_updates | 58820 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000206 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1420 | +| iterations | 10752 | +| time_elapsed | 15503 | +| total_timesteps | 22020096 | +| train/ | | +| approx_kl | 0.01232615 | +| clip_fraction | 0.337 | +| clip_range | 0.0695 | +| entropy_loss | -6.44 | +| explained_variance | 0.646 | +| learning_rate | 4.48e-05 | +| loss | -0.0367 | +| n_updates | 58824 | +| policy_gradient_loss | -0.0221 | +| value_loss | 7.85e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1420 | +| iterations | 10753 | +| time_elapsed | 15504 | +| total_timesteps | 22022144 | +| train/ | | +| approx_kl | 0.013301021 | +| clip_fraction | 0.351 | +| clip_range | 0.0695 | +| entropy_loss | -5.34 | +| explained_variance | 0.572 | +| learning_rate | 4.48e-05 | +| loss | -0.0239 | +| n_updates | 58828 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000315 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1420 | +| iterations | 10754 | +| time_elapsed | 15506 | +| total_timesteps | 22024192 | +| train/ | | +| approx_kl | 0.014961252 | +| clip_fraction | 0.365 | +| clip_range | 0.0695 | +| entropy_loss | -6.2 | +| explained_variance | -0.16 | +| learning_rate | 4.48e-05 | +| loss | -0.0335 | +| n_updates | 58832 | +| policy_gradient_loss | -0.0222 | +| value_loss | 0.000107 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1420 | +| iterations | 10755 | +| time_elapsed | 15507 | +| total_timesteps | 22026240 | +| train/ | | +| approx_kl | 0.010754117 | +| clip_fraction | 0.344 | +| clip_range | 0.0695 | +| entropy_loss | -6.79 | +| explained_variance | -0.0208 | +| learning_rate | 4.48e-05 | +| loss | -0.029 | +| n_updates | 58836 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000202 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1420 | +| iterations | 10756 | +| time_elapsed | 15508 | +| total_timesteps | 22028288 | +| train/ | | +| approx_kl | 0.012050683 | +| clip_fraction | 0.339 | +| clip_range | 0.0695 | +| entropy_loss | -6.36 | +| explained_variance | 0.242 | +| learning_rate | 4.48e-05 | +| loss | -0.0379 | +| n_updates | 58840 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000115 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1420 | +| iterations | 10757 | +| time_elapsed | 15510 | +| total_timesteps | 22030336 | +| train/ | | +| approx_kl | 0.012851806 | +| clip_fraction | 0.358 | +| clip_range | 0.0695 | +| entropy_loss | -6.11 | +| explained_variance | 0.5 | +| learning_rate | 4.48e-05 | +| loss | -0.0328 | +| n_updates | 58844 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000113 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1420 | +| iterations | 10758 | +| time_elapsed | 15511 | +| total_timesteps | 22032384 | +| train/ | | +| approx_kl | 0.011852472 | +| clip_fraction | 0.31 | +| clip_range | 0.0695 | +| entropy_loss | -6.49 | +| explained_variance | 0.292 | +| learning_rate | 4.48e-05 | +| loss | -0.0218 | +| n_updates | 58848 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000322 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1420 | +| iterations | 10759 | +| time_elapsed | 15513 | +| total_timesteps | 22034432 | +| train/ | | +| approx_kl | 0.014442822 | +| clip_fraction | 0.361 | +| clip_range | 0.0695 | +| entropy_loss | -6.41 | +| explained_variance | 0.335 | +| learning_rate | 4.48e-05 | +| loss | -0.0283 | +| n_updates | 58852 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000132 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1420 | +| iterations | 10760 | +| time_elapsed | 15514 | +| total_timesteps | 22036480 | +| train/ | | +| approx_kl | 0.014124723 | +| clip_fraction | 0.367 | +| clip_range | 0.0695 | +| entropy_loss | -6.77 | +| explained_variance | -0.135 | +| learning_rate | 4.48e-05 | +| loss | -0.0316 | +| n_updates | 58856 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000154 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1420 | +| iterations | 10761 | +| time_elapsed | 15516 | +| total_timesteps | 22038528 | +| train/ | | +| approx_kl | 0.0127267465 | +| clip_fraction | 0.324 | +| clip_range | 0.0695 | +| entropy_loss | -6.77 | +| explained_variance | 0.287 | +| learning_rate | 4.48e-05 | +| loss | -0.0296 | +| n_updates | 58860 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000147 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1420 | +| iterations | 10762 | +| time_elapsed | 15517 | +| total_timesteps | 22040576 | +| train/ | | +| approx_kl | 0.0155019555 | +| clip_fraction | 0.376 | +| clip_range | 0.0695 | +| entropy_loss | -6.78 | +| explained_variance | 0.429 | +| learning_rate | 4.48e-05 | +| loss | -0.0403 | +| n_updates | 58864 | +| policy_gradient_loss | -0.024 | +| value_loss | 8.23e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1420 | +| iterations | 10763 | +| time_elapsed | 15519 | +| total_timesteps | 22042624 | +| train/ | | +| approx_kl | 0.012342009 | +| clip_fraction | 0.347 | +| clip_range | 0.0695 | +| entropy_loss | -5.97 | +| explained_variance | 0.733 | +| learning_rate | 4.48e-05 | +| loss | -0.0302 | +| n_updates | 58868 | +| policy_gradient_loss | -0.0198 | +| value_loss | 7.5e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1420 | +| iterations | 10764 | +| time_elapsed | 15520 | +| total_timesteps | 22044672 | +| train/ | | +| approx_kl | 0.01348204 | +| clip_fraction | 0.348 | +| clip_range | 0.0695 | +| entropy_loss | -6.53 | +| explained_variance | 0.37 | +| learning_rate | 4.48e-05 | +| loss | -0.0258 | +| n_updates | 58872 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000148 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1420 | +| iterations | 10765 | +| time_elapsed | 15522 | +| total_timesteps | 22046720 | +| train/ | | +| approx_kl | 0.01509855 | +| clip_fraction | 0.338 | +| clip_range | 0.0695 | +| entropy_loss | -6.47 | +| explained_variance | 0.386 | +| learning_rate | 4.48e-05 | +| loss | -0.0309 | +| n_updates | 58876 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.00014 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1420 | +| iterations | 10766 | +| time_elapsed | 15523 | +| total_timesteps | 22048768 | +| train/ | | +| approx_kl | 0.011828916 | +| clip_fraction | 0.342 | +| clip_range | 0.0695 | +| entropy_loss | -6.05 | +| explained_variance | 0.803 | +| learning_rate | 4.48e-05 | +| loss | -0.0348 | +| n_updates | 58880 | +| policy_gradient_loss | -0.019 | +| value_loss | 7.51e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1420 | +| iterations | 10767 | +| time_elapsed | 15525 | +| total_timesteps | 22050816 | +| train/ | | +| approx_kl | 0.013999402 | +| clip_fraction | 0.317 | +| clip_range | 0.0695 | +| entropy_loss | -6.42 | +| explained_variance | 0.562 | +| learning_rate | 4.48e-05 | +| loss | -0.0269 | +| n_updates | 58884 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000144 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1420 | +| iterations | 10768 | +| time_elapsed | 15526 | +| total_timesteps | 22052864 | +| train/ | | +| approx_kl | 0.015952015 | +| clip_fraction | 0.344 | +| clip_range | 0.0695 | +| entropy_loss | -6.61 | +| explained_variance | -0.0482 | +| learning_rate | 4.48e-05 | +| loss | -0.0295 | +| n_updates | 58888 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1420 | +| iterations | 10769 | +| time_elapsed | 15528 | +| total_timesteps | 22054912 | +| train/ | | +| approx_kl | 0.013915883 | +| clip_fraction | 0.337 | +| clip_range | 0.0695 | +| entropy_loss | -6.91 | +| explained_variance | 0.108 | +| learning_rate | 4.48e-05 | +| loss | -0.0252 | +| n_updates | 58892 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000241 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1420 | +| iterations | 10770 | +| time_elapsed | 15529 | +| total_timesteps | 22056960 | +| train/ | | +| approx_kl | 0.013942759 | +| clip_fraction | 0.318 | +| clip_range | 0.0695 | +| entropy_loss | -5.9 | +| explained_variance | 0.586 | +| learning_rate | 4.48e-05 | +| loss | -0.0264 | +| n_updates | 58896 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000207 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1420 | +| iterations | 10771 | +| time_elapsed | 15531 | +| total_timesteps | 22059008 | +| train/ | | +| approx_kl | 0.013488326 | +| clip_fraction | 0.347 | +| clip_range | 0.0695 | +| entropy_loss | -6.4 | +| explained_variance | 0.43 | +| learning_rate | 4.48e-05 | +| loss | -0.026 | +| n_updates | 58900 | +| policy_gradient_loss | -0.0204 | +| value_loss | 9.3e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1420 | +| iterations | 10772 | +| time_elapsed | 15532 | +| total_timesteps | 22061056 | +| train/ | | +| approx_kl | 0.011799773 | +| clip_fraction | 0.35 | +| clip_range | 0.0695 | +| entropy_loss | -6.64 | +| explained_variance | 0.687 | +| learning_rate | 4.48e-05 | +| loss | -0.0315 | +| n_updates | 58904 | +| policy_gradient_loss | -0.0187 | +| value_loss | 8.23e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1420 | +| iterations | 10773 | +| time_elapsed | 15534 | +| total_timesteps | 22063104 | +| train/ | | +| approx_kl | 0.01707187 | +| clip_fraction | 0.308 | +| clip_range | 0.0695 | +| entropy_loss | -5.88 | +| explained_variance | 0.473 | +| learning_rate | 4.48e-05 | +| loss | -0.0226 | +| n_updates | 58908 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000304 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1420 | +| iterations | 10774 | +| time_elapsed | 15535 | +| total_timesteps | 22065152 | +| train/ | | +| approx_kl | 0.011310594 | +| clip_fraction | 0.332 | +| clip_range | 0.0695 | +| entropy_loss | -6.12 | +| explained_variance | 0.267 | +| learning_rate | 4.48e-05 | +| loss | -0.0249 | +| n_updates | 58912 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000202 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1420 | +| iterations | 10775 | +| time_elapsed | 15536 | +| total_timesteps | 22067200 | +| train/ | | +| approx_kl | 0.013418383 | +| clip_fraction | 0.358 | +| clip_range | 0.0695 | +| entropy_loss | -6.31 | +| explained_variance | 0.606 | +| learning_rate | 4.48e-05 | +| loss | -0.0396 | +| n_updates | 58916 | +| policy_gradient_loss | -0.0222 | +| value_loss | 9.11e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1420 | +| iterations | 10776 | +| time_elapsed | 15538 | +| total_timesteps | 22069248 | +| train/ | | +| approx_kl | 0.013272172 | +| clip_fraction | 0.349 | +| clip_range | 0.0695 | +| entropy_loss | -6.82 | +| explained_variance | -0.0712 | +| learning_rate | 4.48e-05 | +| loss | -0.03 | +| n_updates | 58920 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1420 | +| iterations | 10777 | +| time_elapsed | 15539 | +| total_timesteps | 22071296 | +| train/ | | +| approx_kl | 0.013320452 | +| clip_fraction | 0.299 | +| clip_range | 0.0695 | +| entropy_loss | -7.26 | +| explained_variance | -0.0784 | +| learning_rate | 4.48e-05 | +| loss | -0.0284 | +| n_updates | 58924 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000152 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1420 | +| iterations | 10778 | +| time_elapsed | 15541 | +| total_timesteps | 22073344 | +| train/ | | +| approx_kl | 0.012800882 | +| clip_fraction | 0.314 | +| clip_range | 0.0695 | +| entropy_loss | -6.48 | +| explained_variance | 0.38 | +| learning_rate | 4.48e-05 | +| loss | -0.0314 | +| n_updates | 58928 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000205 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1420 | +| iterations | 10779 | +| time_elapsed | 15542 | +| total_timesteps | 22075392 | +| train/ | | +| approx_kl | 0.013365475 | +| clip_fraction | 0.273 | +| clip_range | 0.0695 | +| entropy_loss | -5.97 | +| explained_variance | 0.399 | +| learning_rate | 4.48e-05 | +| loss | -0.023 | +| n_updates | 58932 | +| policy_gradient_loss | -0.0143 | +| value_loss | 0.0004 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1420 | +| iterations | 10780 | +| time_elapsed | 15544 | +| total_timesteps | 22077440 | +| train/ | | +| approx_kl | 0.013108408 | +| clip_fraction | 0.333 | +| clip_range | 0.0695 | +| entropy_loss | -6.21 | +| explained_variance | 0.549 | +| learning_rate | 4.48e-05 | +| loss | -0.0345 | +| n_updates | 58936 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000135 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1420 | +| iterations | 10781 | +| time_elapsed | 15545 | +| total_timesteps | 22079488 | +| train/ | | +| approx_kl | 0.012966097 | +| clip_fraction | 0.355 | +| clip_range | 0.0695 | +| entropy_loss | -6.5 | +| explained_variance | 0.368 | +| learning_rate | 4.48e-05 | +| loss | -0.0387 | +| n_updates | 58940 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000133 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1420 | +| iterations | 10782 | +| time_elapsed | 15547 | +| total_timesteps | 22081536 | +| train/ | | +| approx_kl | 0.014496949 | +| clip_fraction | 0.371 | +| clip_range | 0.0695 | +| entropy_loss | -7.1 | +| explained_variance | -0.395 | +| learning_rate | 4.48e-05 | +| loss | -0.0345 | +| n_updates | 58944 | +| policy_gradient_loss | -0.0229 | +| value_loss | 0.00011 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1420 | +| iterations | 10783 | +| time_elapsed | 15548 | +| total_timesteps | 22083584 | +| train/ | | +| approx_kl | 0.015487601 | +| clip_fraction | 0.298 | +| clip_range | 0.0695 | +| entropy_loss | -6.37 | +| explained_variance | 0.369 | +| learning_rate | 4.48e-05 | +| loss | -0.0285 | +| n_updates | 58948 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000283 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1420 | +| iterations | 10784 | +| time_elapsed | 15550 | +| total_timesteps | 22085632 | +| train/ | | +| approx_kl | 0.01633133 | +| clip_fraction | 0.338 | +| clip_range | 0.0695 | +| entropy_loss | -6.2 | +| explained_variance | 0.433 | +| learning_rate | 4.48e-05 | +| loss | -0.0344 | +| n_updates | 58952 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000166 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1420 | +| iterations | 10785 | +| time_elapsed | 15551 | +| total_timesteps | 22087680 | +| train/ | | +| approx_kl | 0.01386343 | +| clip_fraction | 0.32 | +| clip_range | 0.0695 | +| entropy_loss | -6.26 | +| explained_variance | 0.45 | +| learning_rate | 4.48e-05 | +| loss | -0.03 | +| n_updates | 58956 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000179 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1420 | +| iterations | 10786 | +| time_elapsed | 15553 | +| total_timesteps | 22089728 | +| train/ | | +| approx_kl | 0.0154031245 | +| clip_fraction | 0.362 | +| clip_range | 0.0695 | +| entropy_loss | -6.82 | +| explained_variance | 0.202 | +| learning_rate | 4.48e-05 | +| loss | -0.0263 | +| n_updates | 58960 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000116 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1420 | +| iterations | 10787 | +| time_elapsed | 15554 | +| total_timesteps | 22091776 | +| train/ | | +| approx_kl | 0.013172943 | +| clip_fraction | 0.328 | +| clip_range | 0.0695 | +| entropy_loss | -6.18 | +| explained_variance | 0.522 | +| learning_rate | 4.48e-05 | +| loss | -0.0304 | +| n_updates | 58964 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.00025 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1420 | +| iterations | 10788 | +| time_elapsed | 15556 | +| total_timesteps | 22093824 | +| train/ | | +| approx_kl | 0.013655094 | +| clip_fraction | 0.337 | +| clip_range | 0.0695 | +| entropy_loss | -6.46 | +| explained_variance | 0.31 | +| learning_rate | 4.48e-05 | +| loss | -0.0261 | +| n_updates | 58968 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000178 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1420 | +| iterations | 10789 | +| time_elapsed | 15557 | +| total_timesteps | 22095872 | +| train/ | | +| approx_kl | 0.012790367 | +| clip_fraction | 0.346 | +| clip_range | 0.0695 | +| entropy_loss | -6.79 | +| explained_variance | 0.334 | +| learning_rate | 4.48e-05 | +| loss | -0.0394 | +| n_updates | 58972 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000128 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1420 | +| iterations | 10790 | +| time_elapsed | 15559 | +| total_timesteps | 22097920 | +| train/ | | +| approx_kl | 0.014155717 | +| clip_fraction | 0.354 | +| clip_range | 0.0695 | +| entropy_loss | -6.89 | +| explained_variance | 0.327 | +| learning_rate | 4.48e-05 | +| loss | -0.0408 | +| n_updates | 58976 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000116 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1420 | +| iterations | 10791 | +| time_elapsed | 15560 | +| total_timesteps | 22099968 | +| train/ | | +| approx_kl | 0.0131598255 | +| clip_fraction | 0.32 | +| clip_range | 0.0695 | +| entropy_loss | -6.15 | +| explained_variance | 0.472 | +| learning_rate | 4.48e-05 | +| loss | -0.0258 | +| n_updates | 58980 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000141 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1420 | +| iterations | 10792 | +| time_elapsed | 15562 | +| total_timesteps | 22102016 | +| train/ | | +| approx_kl | 0.014181584 | +| clip_fraction | 0.356 | +| clip_range | 0.0695 | +| entropy_loss | -6.49 | +| explained_variance | 0.519 | +| learning_rate | 4.48e-05 | +| loss | -0.0343 | +| n_updates | 58984 | +| policy_gradient_loss | -0.0209 | +| value_loss | 9.97e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1420 | +| iterations | 10793 | +| time_elapsed | 15563 | +| total_timesteps | 22104064 | +| train/ | | +| approx_kl | 0.013541683 | +| clip_fraction | 0.325 | +| clip_range | 0.0695 | +| entropy_loss | -6.32 | +| explained_variance | 0.28 | +| learning_rate | 4.48e-05 | +| loss | -0.0231 | +| n_updates | 58988 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.00033 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1420 | +| iterations | 10794 | +| time_elapsed | 15565 | +| total_timesteps | 22106112 | +| train/ | | +| approx_kl | 0.016938306 | +| clip_fraction | 0.358 | +| clip_range | 0.0695 | +| entropy_loss | -6.7 | +| explained_variance | -0.226 | +| learning_rate | 4.48e-05 | +| loss | -0.0417 | +| n_updates | 58992 | +| policy_gradient_loss | -0.0217 | +| value_loss | 9.25e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1420 | +| iterations | 10795 | +| time_elapsed | 15566 | +| total_timesteps | 22108160 | +| train/ | | +| approx_kl | 0.01320381 | +| clip_fraction | 0.334 | +| clip_range | 0.0695 | +| entropy_loss | -6.61 | +| explained_variance | 0.402 | +| learning_rate | 4.47e-05 | +| loss | -0.0285 | +| n_updates | 58996 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000207 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1420 | +| iterations | 10796 | +| time_elapsed | 15568 | +| total_timesteps | 22110208 | +| train/ | | +| approx_kl | 0.010930664 | +| clip_fraction | 0.336 | +| clip_range | 0.0695 | +| entropy_loss | -6.34 | +| explained_variance | 0.243 | +| learning_rate | 4.47e-05 | +| loss | -0.0262 | +| n_updates | 59000 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000401 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1420 | +| iterations | 10797 | +| time_elapsed | 15569 | +| total_timesteps | 22112256 | +| train/ | | +| approx_kl | 0.012735754 | +| clip_fraction | 0.337 | +| clip_range | 0.0695 | +| entropy_loss | -6.23 | +| explained_variance | 0.651 | +| learning_rate | 4.47e-05 | +| loss | -0.0351 | +| n_updates | 59004 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000119 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1420 | +| iterations | 10798 | +| time_elapsed | 15571 | +| total_timesteps | 22114304 | +| train/ | | +| approx_kl | 0.008829621 | +| clip_fraction | 0.297 | +| clip_range | 0.0695 | +| entropy_loss | -6.53 | +| explained_variance | 0.575 | +| learning_rate | 4.47e-05 | +| loss | -0.0385 | +| n_updates | 59008 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000104 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1420 | +| iterations | 10799 | +| time_elapsed | 15572 | +| total_timesteps | 22116352 | +| train/ | | +| approx_kl | 0.014634348 | +| clip_fraction | 0.371 | +| clip_range | 0.0695 | +| entropy_loss | -6.84 | +| explained_variance | 0.141 | +| learning_rate | 4.47e-05 | +| loss | -0.0331 | +| n_updates | 59012 | +| policy_gradient_loss | -0.0221 | +| value_loss | 7.98e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1420 | +| iterations | 10800 | +| time_elapsed | 15574 | +| total_timesteps | 22118400 | +| train/ | | +| approx_kl | 0.011997127 | +| clip_fraction | 0.349 | +| clip_range | 0.0695 | +| entropy_loss | -6.13 | +| explained_variance | 0.375 | +| learning_rate | 4.47e-05 | +| loss | -0.0279 | +| n_updates | 59016 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000406 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1420 | +| iterations | 10801 | +| time_elapsed | 15575 | +| total_timesteps | 22120448 | +| train/ | | +| approx_kl | 0.01170283 | +| clip_fraction | 0.344 | +| clip_range | 0.0695 | +| entropy_loss | -5.97 | +| explained_variance | 0.334 | +| learning_rate | 4.47e-05 | +| loss | -0.0282 | +| n_updates | 59020 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000185 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1420 | +| iterations | 10802 | +| time_elapsed | 15577 | +| total_timesteps | 22122496 | +| train/ | | +| approx_kl | 0.012395406 | +| clip_fraction | 0.358 | +| clip_range | 0.0695 | +| entropy_loss | -6.19 | +| explained_variance | 0.622 | +| learning_rate | 4.47e-05 | +| loss | -0.0381 | +| n_updates | 59024 | +| policy_gradient_loss | -0.0224 | +| value_loss | 9.37e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1420 | +| iterations | 10803 | +| time_elapsed | 15578 | +| total_timesteps | 22124544 | +| train/ | | +| approx_kl | 0.015851319 | +| clip_fraction | 0.383 | +| clip_range | 0.0695 | +| entropy_loss | -6.63 | +| explained_variance | -0.243 | +| learning_rate | 4.47e-05 | +| loss | -0.0282 | +| n_updates | 59028 | +| policy_gradient_loss | -0.0225 | +| value_loss | 9.54e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1420 | +| iterations | 10804 | +| time_elapsed | 15580 | +| total_timesteps | 22126592 | +| train/ | | +| approx_kl | 0.011325914 | +| clip_fraction | 0.322 | +| clip_range | 0.0695 | +| entropy_loss | -7.11 | +| explained_variance | -0.123 | +| learning_rate | 4.47e-05 | +| loss | -0.0267 | +| n_updates | 59032 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000174 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1420 | +| iterations | 10805 | +| time_elapsed | 15581 | +| total_timesteps | 22128640 | +| train/ | | +| approx_kl | 0.013867063 | +| clip_fraction | 0.331 | +| clip_range | 0.0695 | +| entropy_loss | -6.53 | +| explained_variance | 0.549 | +| learning_rate | 4.47e-05 | +| loss | -0.0278 | +| n_updates | 59036 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000172 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1420 | +| iterations | 10806 | +| time_elapsed | 15583 | +| total_timesteps | 22130688 | +| train/ | | +| approx_kl | 0.012783504 | +| clip_fraction | 0.35 | +| clip_range | 0.0695 | +| entropy_loss | -6.58 | +| explained_variance | 0.549 | +| learning_rate | 4.47e-05 | +| loss | -0.0376 | +| n_updates | 59040 | +| policy_gradient_loss | -0.0199 | +| value_loss | 5.79e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1420 | +| iterations | 10807 | +| time_elapsed | 15584 | +| total_timesteps | 22132736 | +| train/ | | +| approx_kl | 0.014415748 | +| clip_fraction | 0.356 | +| clip_range | 0.0695 | +| entropy_loss | -6.62 | +| explained_variance | 0.322 | +| learning_rate | 4.47e-05 | +| loss | -0.0323 | +| n_updates | 59044 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000156 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1420 | +| iterations | 10808 | +| time_elapsed | 15585 | +| total_timesteps | 22134784 | +| train/ | | +| approx_kl | 0.013387631 | +| clip_fraction | 0.323 | +| clip_range | 0.0695 | +| entropy_loss | -6.59 | +| explained_variance | 0.514 | +| learning_rate | 4.47e-05 | +| loss | -0.0334 | +| n_updates | 59048 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000154 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1420 | +| iterations | 10809 | +| time_elapsed | 15587 | +| total_timesteps | 22136832 | +| train/ | | +| approx_kl | 0.013672819 | +| clip_fraction | 0.352 | +| clip_range | 0.0695 | +| entropy_loss | -6.18 | +| explained_variance | 0.673 | +| learning_rate | 4.47e-05 | +| loss | -0.0324 | +| n_updates | 59052 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000105 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1420 | +| iterations | 10810 | +| time_elapsed | 15588 | +| total_timesteps | 22138880 | +| train/ | | +| approx_kl | 0.011986239 | +| clip_fraction | 0.344 | +| clip_range | 0.0695 | +| entropy_loss | -6.48 | +| explained_variance | 0.44 | +| learning_rate | 4.47e-05 | +| loss | -0.0313 | +| n_updates | 59056 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.00011 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1420 | +| iterations | 10811 | +| time_elapsed | 15590 | +| total_timesteps | 22140928 | +| train/ | | +| approx_kl | 0.010571354 | +| clip_fraction | 0.338 | +| clip_range | 0.0695 | +| entropy_loss | -6.69 | +| explained_variance | 0.372 | +| learning_rate | 4.47e-05 | +| loss | -0.0254 | +| n_updates | 59060 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000117 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1420 | +| iterations | 10812 | +| time_elapsed | 15591 | +| total_timesteps | 22142976 | +| train/ | | +| approx_kl | 0.011445718 | +| clip_fraction | 0.33 | +| clip_range | 0.0695 | +| entropy_loss | -6.42 | +| explained_variance | 0.368 | +| learning_rate | 4.47e-05 | +| loss | -0.0298 | +| n_updates | 59064 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000262 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1420 | +| iterations | 10813 | +| time_elapsed | 15593 | +| total_timesteps | 22145024 | +| train/ | | +| approx_kl | 0.011467767 | +| clip_fraction | 0.315 | +| clip_range | 0.0695 | +| entropy_loss | -6.64 | +| explained_variance | 0.386 | +| learning_rate | 4.47e-05 | +| loss | -0.0311 | +| n_updates | 59068 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000202 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1420 | +| iterations | 10814 | +| time_elapsed | 15594 | +| total_timesteps | 22147072 | +| train/ | | +| approx_kl | 0.014603382 | +| clip_fraction | 0.333 | +| clip_range | 0.0695 | +| entropy_loss | -6.5 | +| explained_variance | 0.229 | +| learning_rate | 4.47e-05 | +| loss | -0.0356 | +| n_updates | 59072 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000134 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1420 | +| iterations | 10815 | +| time_elapsed | 15596 | +| total_timesteps | 22149120 | +| train/ | | +| approx_kl | 0.01528758 | +| clip_fraction | 0.306 | +| clip_range | 0.0695 | +| entropy_loss | -6.5 | +| explained_variance | 0.158 | +| learning_rate | 4.47e-05 | +| loss | -0.031 | +| n_updates | 59076 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000305 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1420 | +| iterations | 10816 | +| time_elapsed | 15597 | +| total_timesteps | 22151168 | +| train/ | | +| approx_kl | 0.015113591 | +| clip_fraction | 0.353 | +| clip_range | 0.0695 | +| entropy_loss | -6.13 | +| explained_variance | 0.489 | +| learning_rate | 4.47e-05 | +| loss | -0.0254 | +| n_updates | 59080 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000129 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1420 | +| iterations | 10817 | +| time_elapsed | 15599 | +| total_timesteps | 22153216 | +| train/ | | +| approx_kl | 0.013536969 | +| clip_fraction | 0.363 | +| clip_range | 0.0695 | +| entropy_loss | -6.91 | +| explained_variance | -0.0998 | +| learning_rate | 4.47e-05 | +| loss | -0.0372 | +| n_updates | 59084 | +| policy_gradient_loss | -0.0229 | +| value_loss | 7.96e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1420 | +| iterations | 10818 | +| time_elapsed | 15600 | +| total_timesteps | 22155264 | +| train/ | | +| approx_kl | 0.014379285 | +| clip_fraction | 0.337 | +| clip_range | 0.0695 | +| entropy_loss | -6.4 | +| explained_variance | 0.496 | +| learning_rate | 4.47e-05 | +| loss | -0.0328 | +| n_updates | 59088 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1420 | +| iterations | 10819 | +| time_elapsed | 15602 | +| total_timesteps | 22157312 | +| train/ | | +| approx_kl | 0.015303725 | +| clip_fraction | 0.34 | +| clip_range | 0.0695 | +| entropy_loss | -5.98 | +| explained_variance | 0.324 | +| learning_rate | 4.47e-05 | +| loss | -0.0306 | +| n_updates | 59092 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000218 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1420 | +| iterations | 10820 | +| time_elapsed | 15603 | +| total_timesteps | 22159360 | +| train/ | | +| approx_kl | 0.013053506 | +| clip_fraction | 0.339 | +| clip_range | 0.0695 | +| entropy_loss | -6.69 | +| explained_variance | 0.291 | +| learning_rate | 4.47e-05 | +| loss | -0.0304 | +| n_updates | 59096 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000145 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1420 | +| iterations | 10821 | +| time_elapsed | 15605 | +| total_timesteps | 22161408 | +| train/ | | +| approx_kl | 0.014509361 | +| clip_fraction | 0.319 | +| clip_range | 0.0695 | +| entropy_loss | -5.93 | +| explained_variance | 0.518 | +| learning_rate | 4.47e-05 | +| loss | -0.0295 | +| n_updates | 59100 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000189 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1420 | +| iterations | 10822 | +| time_elapsed | 15606 | +| total_timesteps | 22163456 | +| train/ | | +| approx_kl | 0.01404148 | +| clip_fraction | 0.353 | +| clip_range | 0.0695 | +| entropy_loss | -6.28 | +| explained_variance | 0.591 | +| learning_rate | 4.47e-05 | +| loss | -0.0339 | +| n_updates | 59104 | +| policy_gradient_loss | -0.0196 | +| value_loss | 8.91e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1420 | +| iterations | 10823 | +| time_elapsed | 15608 | +| total_timesteps | 22165504 | +| train/ | | +| approx_kl | 0.015311362 | +| clip_fraction | 0.333 | +| clip_range | 0.0695 | +| entropy_loss | -5.76 | +| explained_variance | 0.516 | +| learning_rate | 4.47e-05 | +| loss | -0.0268 | +| n_updates | 59108 | +| policy_gradient_loss | -0.0146 | +| value_loss | 0.000251 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1420 | +| iterations | 10824 | +| time_elapsed | 15609 | +| total_timesteps | 22167552 | +| train/ | | +| approx_kl | 0.014918477 | +| clip_fraction | 0.336 | +| clip_range | 0.0695 | +| entropy_loss | -6.45 | +| explained_variance | 0.354 | +| learning_rate | 4.47e-05 | +| loss | -0.029 | +| n_updates | 59112 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.00011 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1420 | +| iterations | 10825 | +| time_elapsed | 15610 | +| total_timesteps | 22169600 | +| train/ | | +| approx_kl | 0.009996905 | +| clip_fraction | 0.341 | +| clip_range | 0.0695 | +| entropy_loss | -6.26 | +| explained_variance | 0.264 | +| learning_rate | 4.47e-05 | +| loss | -0.0228 | +| n_updates | 59116 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000315 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1420 | +| iterations | 10826 | +| time_elapsed | 15612 | +| total_timesteps | 22171648 | +| train/ | | +| approx_kl | 0.016343283 | +| clip_fraction | 0.378 | +| clip_range | 0.0695 | +| entropy_loss | -6.54 | +| explained_variance | 0.351 | +| learning_rate | 4.47e-05 | +| loss | -0.0322 | +| n_updates | 59120 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.00012 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1420 | +| iterations | 10827 | +| time_elapsed | 15613 | +| total_timesteps | 22173696 | +| train/ | | +| approx_kl | 0.013309242 | +| clip_fraction | 0.364 | +| clip_range | 0.0695 | +| entropy_loss | -6.51 | +| explained_variance | 0.223 | +| learning_rate | 4.47e-05 | +| loss | -0.0251 | +| n_updates | 59124 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.00031 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1420 | +| iterations | 10828 | +| time_elapsed | 15615 | +| total_timesteps | 22175744 | +| train/ | | +| approx_kl | 0.012471362 | +| clip_fraction | 0.332 | +| clip_range | 0.0695 | +| entropy_loss | -5.92 | +| explained_variance | 0.571 | +| learning_rate | 4.47e-05 | +| loss | -0.0328 | +| n_updates | 59128 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000158 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1420 | +| iterations | 10829 | +| time_elapsed | 15616 | +| total_timesteps | 22177792 | +| train/ | | +| approx_kl | 0.013760792 | +| clip_fraction | 0.353 | +| clip_range | 0.0695 | +| entropy_loss | -6.97 | +| explained_variance | -0.119 | +| learning_rate | 4.47e-05 | +| loss | -0.0313 | +| n_updates | 59132 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000136 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1420 | +| iterations | 10830 | +| time_elapsed | 15618 | +| total_timesteps | 22179840 | +| train/ | | +| approx_kl | 0.015038708 | +| clip_fraction | 0.359 | +| clip_range | 0.0695 | +| entropy_loss | -6.79 | +| explained_variance | 0.309 | +| learning_rate | 4.47e-05 | +| loss | -0.0303 | +| n_updates | 59136 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000156 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1420 | +| iterations | 10831 | +| time_elapsed | 15619 | +| total_timesteps | 22181888 | +| train/ | | +| approx_kl | 0.011777525 | +| clip_fraction | 0.334 | +| clip_range | 0.0695 | +| entropy_loss | -6.5 | +| explained_variance | 0.414 | +| learning_rate | 4.47e-05 | +| loss | -0.027 | +| n_updates | 59140 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000157 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1420 | +| iterations | 10832 | +| time_elapsed | 15621 | +| total_timesteps | 22183936 | +| train/ | | +| approx_kl | 0.0101224 | +| clip_fraction | 0.339 | +| clip_range | 0.0695 | +| entropy_loss | -6.42 | +| explained_variance | 0.499 | +| learning_rate | 4.47e-05 | +| loss | -0.0298 | +| n_updates | 59144 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000116 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1420 | +| iterations | 10833 | +| time_elapsed | 15622 | +| total_timesteps | 22185984 | +| train/ | | +| approx_kl | 0.008253058 | +| clip_fraction | 0.311 | +| clip_range | 0.0695 | +| entropy_loss | -6.23 | +| explained_variance | 0.483 | +| learning_rate | 4.47e-05 | +| loss | -0.0222 | +| n_updates | 59148 | +| policy_gradient_loss | -0.0133 | +| value_loss | 0.000307 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1420 | +| iterations | 10834 | +| time_elapsed | 15624 | +| total_timesteps | 22188032 | +| train/ | | +| approx_kl | 0.010479594 | +| clip_fraction | 0.341 | +| clip_range | 0.0695 | +| entropy_loss | -6.22 | +| explained_variance | 0.309 | +| learning_rate | 4.47e-05 | +| loss | -0.0302 | +| n_updates | 59152 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000117 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1420 | +| iterations | 10835 | +| time_elapsed | 15625 | +| total_timesteps | 22190080 | +| train/ | | +| approx_kl | 0.012545807 | +| clip_fraction | 0.344 | +| clip_range | 0.0695 | +| entropy_loss | -5.82 | +| explained_variance | 0.623 | +| learning_rate | 4.47e-05 | +| loss | -0.0284 | +| n_updates | 59156 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000191 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1420 | +| iterations | 10836 | +| time_elapsed | 15626 | +| total_timesteps | 22192128 | +| train/ | | +| approx_kl | 0.015958829 | +| clip_fraction | 0.382 | +| clip_range | 0.0695 | +| entropy_loss | -6.12 | +| explained_variance | 0.498 | +| learning_rate | 4.47e-05 | +| loss | -0.0296 | +| n_updates | 59160 | +| policy_gradient_loss | -0.0232 | +| value_loss | 7.82e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1420 | +| iterations | 10837 | +| time_elapsed | 15628 | +| total_timesteps | 22194176 | +| train/ | | +| approx_kl | 0.014647566 | +| clip_fraction | 0.358 | +| clip_range | 0.0695 | +| entropy_loss | -6.94 | +| explained_variance | -0.0528 | +| learning_rate | 4.47e-05 | +| loss | -0.03 | +| n_updates | 59164 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000129 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1420 | +| iterations | 10838 | +| time_elapsed | 15629 | +| total_timesteps | 22196224 | +| train/ | | +| approx_kl | 0.01539928 | +| clip_fraction | 0.347 | +| clip_range | 0.0695 | +| entropy_loss | -6.49 | +| explained_variance | 0.421 | +| learning_rate | 4.47e-05 | +| loss | -0.0377 | +| n_updates | 59168 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000102 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1420 | +| iterations | 10839 | +| time_elapsed | 15631 | +| total_timesteps | 22198272 | +| train/ | | +| approx_kl | 0.015037254 | +| clip_fraction | 0.371 | +| clip_range | 0.0695 | +| entropy_loss | -6.27 | +| explained_variance | 0.693 | +| learning_rate | 4.47e-05 | +| loss | -0.0299 | +| n_updates | 59172 | +| policy_gradient_loss | -0.0212 | +| value_loss | 6.53e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1420 | +| iterations | 10840 | +| time_elapsed | 15632 | +| total_timesteps | 22200320 | +| train/ | | +| approx_kl | 0.014031697 | +| clip_fraction | 0.352 | +| clip_range | 0.0695 | +| entropy_loss | -6.56 | +| explained_variance | 0.339 | +| learning_rate | 4.47e-05 | +| loss | -0.0338 | +| n_updates | 59176 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000122 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1420 | +| iterations | 10841 | +| time_elapsed | 15634 | +| total_timesteps | 22202368 | +| train/ | | +| approx_kl | 0.011801256 | +| clip_fraction | 0.328 | +| clip_range | 0.0694 | +| entropy_loss | -6.37 | +| explained_variance | 0.354 | +| learning_rate | 4.47e-05 | +| loss | -0.029 | +| n_updates | 59180 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000243 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1420 | +| iterations | 10842 | +| time_elapsed | 15635 | +| total_timesteps | 22204416 | +| train/ | | +| approx_kl | 0.012859544 | +| clip_fraction | 0.333 | +| clip_range | 0.0694 | +| entropy_loss | -6.08 | +| explained_variance | 0.532 | +| learning_rate | 4.47e-05 | +| loss | -0.0347 | +| n_updates | 59184 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000202 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1420 | +| iterations | 10843 | +| time_elapsed | 15637 | +| total_timesteps | 22206464 | +| train/ | | +| approx_kl | 0.011442723 | +| clip_fraction | 0.333 | +| clip_range | 0.0694 | +| entropy_loss | -6.25 | +| explained_variance | 0.438 | +| learning_rate | 4.47e-05 | +| loss | -0.0234 | +| n_updates | 59188 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000184 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1420 | +| iterations | 10844 | +| time_elapsed | 15638 | +| total_timesteps | 22208512 | +| train/ | | +| approx_kl | 0.017052792 | +| clip_fraction | 0.369 | +| clip_range | 0.0694 | +| entropy_loss | -5.91 | +| explained_variance | 0.488 | +| learning_rate | 4.47e-05 | +| loss | -0.0303 | +| n_updates | 59192 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000152 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1420 | +| iterations | 10845 | +| time_elapsed | 15640 | +| total_timesteps | 22210560 | +| train/ | | +| approx_kl | 0.013168043 | +| clip_fraction | 0.345 | +| clip_range | 0.0694 | +| entropy_loss | -6.18 | +| explained_variance | 0.49 | +| learning_rate | 4.47e-05 | +| loss | -0.0289 | +| n_updates | 59196 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000166 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1420 | +| iterations | 10846 | +| time_elapsed | 15641 | +| total_timesteps | 22212608 | +| train/ | | +| approx_kl | 0.013670017 | +| clip_fraction | 0.341 | +| clip_range | 0.0694 | +| entropy_loss | -6.38 | +| explained_variance | 0.325 | +| learning_rate | 4.47e-05 | +| loss | -0.0347 | +| n_updates | 59200 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.00013 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1420 | +| iterations | 10847 | +| time_elapsed | 15642 | +| total_timesteps | 22214656 | +| train/ | | +| approx_kl | 0.012173009 | +| clip_fraction | 0.319 | +| clip_range | 0.0694 | +| entropy_loss | -6.59 | +| explained_variance | 0.311 | +| learning_rate | 4.47e-05 | +| loss | -0.0308 | +| n_updates | 59204 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000343 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1420 | +| iterations | 10848 | +| time_elapsed | 15644 | +| total_timesteps | 22216704 | +| train/ | | +| approx_kl | 0.011885924 | +| clip_fraction | 0.357 | +| clip_range | 0.0694 | +| entropy_loss | -6.88 | +| explained_variance | 0.0266 | +| learning_rate | 4.47e-05 | +| loss | -0.0351 | +| n_updates | 59208 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000148 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1420 | +| iterations | 10849 | +| time_elapsed | 15645 | +| total_timesteps | 22218752 | +| train/ | | +| approx_kl | 0.0124128135 | +| clip_fraction | 0.339 | +| clip_range | 0.0694 | +| entropy_loss | -6.7 | +| explained_variance | 0.152 | +| learning_rate | 4.47e-05 | +| loss | -0.0303 | +| n_updates | 59212 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000286 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1420 | +| iterations | 10850 | +| time_elapsed | 15647 | +| total_timesteps | 22220800 | +| train/ | | +| approx_kl | 0.016015088 | +| clip_fraction | 0.352 | +| clip_range | 0.0694 | +| entropy_loss | -6.83 | +| explained_variance | -0.2 | +| learning_rate | 4.47e-05 | +| loss | -0.0333 | +| n_updates | 59216 | +| policy_gradient_loss | -0.022 | +| value_loss | 0.000109 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1420 | +| iterations | 10851 | +| time_elapsed | 15648 | +| total_timesteps | 22222848 | +| train/ | | +| approx_kl | 0.012039358 | +| clip_fraction | 0.352 | +| clip_range | 0.0694 | +| entropy_loss | -6.19 | +| explained_variance | 0.745 | +| learning_rate | 4.47e-05 | +| loss | -0.0361 | +| n_updates | 59220 | +| policy_gradient_loss | -0.0222 | +| value_loss | 7.38e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1420 | +| iterations | 10852 | +| time_elapsed | 15650 | +| total_timesteps | 22224896 | +| train/ | | +| approx_kl | 0.013973803 | +| clip_fraction | 0.331 | +| clip_range | 0.0694 | +| entropy_loss | -6.04 | +| explained_variance | 0.503 | +| learning_rate | 4.47e-05 | +| loss | -0.0316 | +| n_updates | 59224 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000232 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1420 | +| iterations | 10853 | +| time_elapsed | 15651 | +| total_timesteps | 22226944 | +| train/ | | +| approx_kl | 0.014299523 | +| clip_fraction | 0.333 | +| clip_range | 0.0694 | +| entropy_loss | -5.76 | +| explained_variance | 0.538 | +| learning_rate | 4.47e-05 | +| loss | -0.0306 | +| n_updates | 59228 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000208 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1420 | +| iterations | 10854 | +| time_elapsed | 15653 | +| total_timesteps | 22228992 | +| train/ | | +| approx_kl | 0.01629071 | +| clip_fraction | 0.362 | +| clip_range | 0.0694 | +| entropy_loss | -6.24 | +| explained_variance | 0.585 | +| learning_rate | 4.47e-05 | +| loss | -0.0314 | +| n_updates | 59232 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000123 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1420 | +| iterations | 10855 | +| time_elapsed | 15654 | +| total_timesteps | 22231040 | +| train/ | | +| approx_kl | 0.013612565 | +| clip_fraction | 0.338 | +| clip_range | 0.0694 | +| entropy_loss | -6.71 | +| explained_variance | 0.15 | +| learning_rate | 4.47e-05 | +| loss | -0.033 | +| n_updates | 59236 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000175 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1420 | +| iterations | 10856 | +| time_elapsed | 15655 | +| total_timesteps | 22233088 | +| train/ | | +| approx_kl | 0.012809403 | +| clip_fraction | 0.328 | +| clip_range | 0.0694 | +| entropy_loss | -6.5 | +| explained_variance | 0.464 | +| learning_rate | 4.47e-05 | +| loss | -0.0324 | +| n_updates | 59240 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000187 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1420 | +| iterations | 10857 | +| time_elapsed | 15657 | +| total_timesteps | 22235136 | +| train/ | | +| approx_kl | 0.012124864 | +| clip_fraction | 0.328 | +| clip_range | 0.0694 | +| entropy_loss | -6.84 | +| explained_variance | 0.177 | +| learning_rate | 4.47e-05 | +| loss | -0.0304 | +| n_updates | 59244 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000232 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1420 | +| iterations | 10858 | +| time_elapsed | 15658 | +| total_timesteps | 22237184 | +| train/ | | +| approx_kl | 0.013774628 | +| clip_fraction | 0.356 | +| clip_range | 0.0694 | +| entropy_loss | -6.98 | +| explained_variance | 0.298 | +| learning_rate | 4.47e-05 | +| loss | -0.0358 | +| n_updates | 59248 | +| policy_gradient_loss | -0.022 | +| value_loss | 0.000104 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1420 | +| iterations | 10859 | +| time_elapsed | 15660 | +| total_timesteps | 22239232 | +| train/ | | +| approx_kl | 0.014611317 | +| clip_fraction | 0.345 | +| clip_range | 0.0694 | +| entropy_loss | -7 | +| explained_variance | -0.256 | +| learning_rate | 4.47e-05 | +| loss | -0.034 | +| n_updates | 59252 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000116 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1420 | +| iterations | 10860 | +| time_elapsed | 15661 | +| total_timesteps | 22241280 | +| train/ | | +| approx_kl | 0.01272836 | +| clip_fraction | 0.33 | +| clip_range | 0.0694 | +| entropy_loss | -6.56 | +| explained_variance | 0.445 | +| learning_rate | 4.47e-05 | +| loss | -0.0274 | +| n_updates | 59256 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000213 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1420 | +| iterations | 10861 | +| time_elapsed | 15663 | +| total_timesteps | 22243328 | +| train/ | | +| approx_kl | 0.013098409 | +| clip_fraction | 0.325 | +| clip_range | 0.0694 | +| entropy_loss | -6.5 | +| explained_variance | 0.395 | +| learning_rate | 4.47e-05 | +| loss | -0.0279 | +| n_updates | 59260 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000198 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1420 | +| iterations | 10862 | +| time_elapsed | 15664 | +| total_timesteps | 22245376 | +| train/ | | +| approx_kl | 0.012109104 | +| clip_fraction | 0.313 | +| clip_range | 0.0694 | +| entropy_loss | -5.97 | +| explained_variance | 0.41 | +| learning_rate | 4.47e-05 | +| loss | -0.0296 | +| n_updates | 59264 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000332 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1420 | +| iterations | 10863 | +| time_elapsed | 15666 | +| total_timesteps | 22247424 | +| train/ | | +| approx_kl | 0.013301445 | +| clip_fraction | 0.33 | +| clip_range | 0.0694 | +| entropy_loss | -5.64 | +| explained_variance | 0.679 | +| learning_rate | 4.47e-05 | +| loss | -0.0299 | +| n_updates | 59268 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000135 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1420 | +| iterations | 10864 | +| time_elapsed | 15667 | +| total_timesteps | 22249472 | +| train/ | | +| approx_kl | 0.015039962 | +| clip_fraction | 0.358 | +| clip_range | 0.0694 | +| entropy_loss | -6.33 | +| explained_variance | 0.228 | +| learning_rate | 4.47e-05 | +| loss | -0.0289 | +| n_updates | 59272 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.00023 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1420 | +| iterations | 10865 | +| time_elapsed | 15668 | +| total_timesteps | 22251520 | +| train/ | | +| approx_kl | 0.012995249 | +| clip_fraction | 0.338 | +| clip_range | 0.0694 | +| entropy_loss | -6.41 | +| explained_variance | 0.485 | +| learning_rate | 4.47e-05 | +| loss | -0.0309 | +| n_updates | 59276 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000148 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1420 | +| iterations | 10866 | +| time_elapsed | 15670 | +| total_timesteps | 22253568 | +| train/ | | +| approx_kl | 0.014791701 | +| clip_fraction | 0.344 | +| clip_range | 0.0694 | +| entropy_loss | -6.96 | +| explained_variance | -0.094 | +| learning_rate | 4.47e-05 | +| loss | -0.0309 | +| n_updates | 59280 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000185 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1420 | +| iterations | 10867 | +| time_elapsed | 15671 | +| total_timesteps | 22255616 | +| train/ | | +| approx_kl | 0.01563934 | +| clip_fraction | 0.359 | +| clip_range | 0.0694 | +| entropy_loss | -6.99 | +| explained_variance | 0.0651 | +| learning_rate | 4.47e-05 | +| loss | -0.0349 | +| n_updates | 59284 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000136 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1420 | +| iterations | 10868 | +| time_elapsed | 15673 | +| total_timesteps | 22257664 | +| train/ | | +| approx_kl | 0.012985294 | +| clip_fraction | 0.358 | +| clip_range | 0.0694 | +| entropy_loss | -6.72 | +| explained_variance | 0.195 | +| learning_rate | 4.47e-05 | +| loss | -0.024 | +| n_updates | 59288 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000254 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.385 | +| time/ | | +| fps | 1420 | +| iterations | 10869 | +| time_elapsed | 15674 | +| total_timesteps | 22259712 | +| train/ | | +| approx_kl | 0.009959916 | +| clip_fraction | 0.301 | +| clip_range | 0.0694 | +| entropy_loss | -6.53 | +| explained_variance | 0.231 | +| learning_rate | 4.47e-05 | +| loss | -0.0299 | +| n_updates | 59292 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000291 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1420 | +| iterations | 10870 | +| time_elapsed | 15676 | +| total_timesteps | 22261760 | +| train/ | | +| approx_kl | 0.012345212 | +| clip_fraction | 0.318 | +| clip_range | 0.0694 | +| entropy_loss | -5.83 | +| explained_variance | 0.508 | +| learning_rate | 4.47e-05 | +| loss | -0.0238 | +| n_updates | 59296 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000353 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1420 | +| iterations | 10871 | +| time_elapsed | 15677 | +| total_timesteps | 22263808 | +| train/ | | +| approx_kl | 0.013344063 | +| clip_fraction | 0.355 | +| clip_range | 0.0694 | +| entropy_loss | -5.98 | +| explained_variance | 0.419 | +| learning_rate | 4.47e-05 | +| loss | -0.0367 | +| n_updates | 59300 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1420 | +| iterations | 10872 | +| time_elapsed | 15679 | +| total_timesteps | 22265856 | +| train/ | | +| approx_kl | 0.012214035 | +| clip_fraction | 0.338 | +| clip_range | 0.0694 | +| entropy_loss | -6.81 | +| explained_variance | 0.33 | +| learning_rate | 4.47e-05 | +| loss | -0.0341 | +| n_updates | 59304 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000115 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1420 | +| iterations | 10873 | +| time_elapsed | 15680 | +| total_timesteps | 22267904 | +| train/ | | +| approx_kl | 0.013030027 | +| clip_fraction | 0.345 | +| clip_range | 0.0694 | +| entropy_loss | -6.64 | +| explained_variance | 0.42 | +| learning_rate | 4.47e-05 | +| loss | -0.0356 | +| n_updates | 59308 | +| policy_gradient_loss | -0.0207 | +| value_loss | 9.78e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1420 | +| iterations | 10874 | +| time_elapsed | 15682 | +| total_timesteps | 22269952 | +| train/ | | +| approx_kl | 0.013053397 | +| clip_fraction | 0.325 | +| clip_range | 0.0694 | +| entropy_loss | -6.2 | +| explained_variance | 0.34 | +| learning_rate | 4.47e-05 | +| loss | -0.0259 | +| n_updates | 59312 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000244 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1420 | +| iterations | 10875 | +| time_elapsed | 15683 | +| total_timesteps | 22272000 | +| train/ | | +| approx_kl | 0.008579075 | +| clip_fraction | 0.317 | +| clip_range | 0.0694 | +| entropy_loss | -6.68 | +| explained_variance | 0.284 | +| learning_rate | 4.47e-05 | +| loss | -0.0215 | +| n_updates | 59316 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.00026 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1420 | +| iterations | 10876 | +| time_elapsed | 15685 | +| total_timesteps | 22274048 | +| train/ | | +| approx_kl | 0.0118282605 | +| clip_fraction | 0.32 | +| clip_range | 0.0694 | +| entropy_loss | -6.38 | +| explained_variance | 0.547 | +| learning_rate | 4.47e-05 | +| loss | -0.0306 | +| n_updates | 59320 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000145 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1420 | +| iterations | 10877 | +| time_elapsed | 15686 | +| total_timesteps | 22276096 | +| train/ | | +| approx_kl | 0.01357987 | +| clip_fraction | 0.344 | +| clip_range | 0.0694 | +| entropy_loss | -6.59 | +| explained_variance | 0.248 | +| learning_rate | 4.47e-05 | +| loss | -0.0313 | +| n_updates | 59324 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000277 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1420 | +| iterations | 10878 | +| time_elapsed | 15688 | +| total_timesteps | 22278144 | +| train/ | | +| approx_kl | 0.0133247115 | +| clip_fraction | 0.364 | +| clip_range | 0.0694 | +| entropy_loss | -6.2 | +| explained_variance | 0.662 | +| learning_rate | 4.47e-05 | +| loss | -0.0345 | +| n_updates | 59328 | +| policy_gradient_loss | -0.0221 | +| value_loss | 0.000107 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1420 | +| iterations | 10879 | +| time_elapsed | 15689 | +| total_timesteps | 22280192 | +| train/ | | +| approx_kl | 0.0075534685 | +| clip_fraction | 0.295 | +| clip_range | 0.0694 | +| entropy_loss | -6.46 | +| explained_variance | 0.288 | +| learning_rate | 4.47e-05 | +| loss | -0.0276 | +| n_updates | 59332 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000352 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1420 | +| iterations | 10880 | +| time_elapsed | 15691 | +| total_timesteps | 22282240 | +| train/ | | +| approx_kl | 0.013250119 | +| clip_fraction | 0.32 | +| clip_range | 0.0694 | +| entropy_loss | -6.05 | +| explained_variance | 0.613 | +| learning_rate | 4.47e-05 | +| loss | -0.0311 | +| n_updates | 59336 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1420 | +| iterations | 10881 | +| time_elapsed | 15692 | +| total_timesteps | 22284288 | +| train/ | | +| approx_kl | 0.011551844 | +| clip_fraction | 0.32 | +| clip_range | 0.0694 | +| entropy_loss | -6.77 | +| explained_variance | 0.0222 | +| learning_rate | 4.47e-05 | +| loss | -0.0253 | +| n_updates | 59340 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000214 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1420 | +| iterations | 10882 | +| time_elapsed | 15694 | +| total_timesteps | 22286336 | +| train/ | | +| approx_kl | 0.011700146 | +| clip_fraction | 0.326 | +| clip_range | 0.0694 | +| entropy_loss | -6.12 | +| explained_variance | 0.552 | +| learning_rate | 4.47e-05 | +| loss | -0.0246 | +| n_updates | 59344 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.00023 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.384 | +| time/ | | +| fps | 1420 | +| iterations | 10883 | +| time_elapsed | 15695 | +| total_timesteps | 22288384 | +| train/ | | +| approx_kl | 0.014498411 | +| clip_fraction | 0.37 | +| clip_range | 0.0694 | +| entropy_loss | -6.43 | +| explained_variance | 0.339 | +| learning_rate | 4.47e-05 | +| loss | -0.0339 | +| n_updates | 59348 | +| policy_gradient_loss | -0.0215 | +| value_loss | 9.88e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.386 | +| time/ | | +| fps | 1420 | +| iterations | 10884 | +| time_elapsed | 15696 | +| total_timesteps | 22290432 | +| train/ | | +| approx_kl | 0.010341883 | +| clip_fraction | 0.328 | +| clip_range | 0.0694 | +| entropy_loss | -6.69 | +| explained_variance | 0.522 | +| learning_rate | 4.47e-05 | +| loss | -0.0309 | +| n_updates | 59352 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000137 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.385 | +| time/ | | +| fps | 1420 | +| iterations | 10885 | +| time_elapsed | 15698 | +| total_timesteps | 22292480 | +| train/ | | +| approx_kl | 0.011496762 | +| clip_fraction | 0.331 | +| clip_range | 0.0694 | +| entropy_loss | -6.8 | +| explained_variance | 0.411 | +| learning_rate | 4.47e-05 | +| loss | -0.0294 | +| n_updates | 59356 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000125 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1420 | +| iterations | 10886 | +| time_elapsed | 15699 | +| total_timesteps | 22294528 | +| train/ | | +| approx_kl | 0.011691794 | +| clip_fraction | 0.311 | +| clip_range | 0.0694 | +| entropy_loss | -6.63 | +| explained_variance | 0.26 | +| learning_rate | 4.47e-05 | +| loss | -0.0294 | +| n_updates | 59360 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000234 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1420 | +| iterations | 10887 | +| time_elapsed | 15701 | +| total_timesteps | 22296576 | +| train/ | | +| approx_kl | 0.012540174 | +| clip_fraction | 0.327 | +| clip_range | 0.0694 | +| entropy_loss | -5.76 | +| explained_variance | 0.83 | +| learning_rate | 4.47e-05 | +| loss | -0.0319 | +| n_updates | 59364 | +| policy_gradient_loss | -0.0208 | +| value_loss | 8.03e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1420 | +| iterations | 10888 | +| time_elapsed | 15702 | +| total_timesteps | 22298624 | +| train/ | | +| approx_kl | 0.012909307 | +| clip_fraction | 0.352 | +| clip_range | 0.0694 | +| entropy_loss | -6.54 | +| explained_variance | 0.372 | +| learning_rate | 4.47e-05 | +| loss | -0.0396 | +| n_updates | 59368 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.0001 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1420 | +| iterations | 10889 | +| time_elapsed | 15704 | +| total_timesteps | 22300672 | +| train/ | | +| approx_kl | 0.012731722 | +| clip_fraction | 0.339 | +| clip_range | 0.0694 | +| entropy_loss | -6.06 | +| explained_variance | 0.516 | +| learning_rate | 4.47e-05 | +| loss | -0.0324 | +| n_updates | 59372 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000128 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.385 | +| time/ | | +| fps | 1420 | +| iterations | 10890 | +| time_elapsed | 15705 | +| total_timesteps | 22302720 | +| train/ | | +| approx_kl | 0.012920628 | +| clip_fraction | 0.313 | +| clip_range | 0.0694 | +| entropy_loss | -6.3 | +| explained_variance | 0.429 | +| learning_rate | 4.47e-05 | +| loss | -0.0255 | +| n_updates | 59376 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000225 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.385 | +| time/ | | +| fps | 1420 | +| iterations | 10891 | +| time_elapsed | 15707 | +| total_timesteps | 22304768 | +| train/ | | +| approx_kl | 0.012244014 | +| clip_fraction | 0.314 | +| clip_range | 0.0694 | +| entropy_loss | -6.65 | +| explained_variance | 0.32 | +| learning_rate | 4.47e-05 | +| loss | -0.0227 | +| n_updates | 59380 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000204 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1420 | +| iterations | 10892 | +| time_elapsed | 15708 | +| total_timesteps | 22306816 | +| train/ | | +| approx_kl | 0.014922777 | +| clip_fraction | 0.354 | +| clip_range | 0.0694 | +| entropy_loss | -6.73 | +| explained_variance | 0.156 | +| learning_rate | 4.47e-05 | +| loss | -0.0308 | +| n_updates | 59384 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.00016 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1420 | +| iterations | 10893 | +| time_elapsed | 15710 | +| total_timesteps | 22308864 | +| train/ | | +| approx_kl | 0.016451878 | +| clip_fraction | 0.356 | +| clip_range | 0.0694 | +| entropy_loss | -6.7 | +| explained_variance | 0.51 | +| learning_rate | 4.47e-05 | +| loss | -0.0344 | +| n_updates | 59388 | +| policy_gradient_loss | -0.0227 | +| value_loss | 6.36e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1420 | +| iterations | 10894 | +| time_elapsed | 15711 | +| total_timesteps | 22310912 | +| train/ | | +| approx_kl | 0.014836067 | +| clip_fraction | 0.342 | +| clip_range | 0.0694 | +| entropy_loss | -6.66 | +| explained_variance | 0.443 | +| learning_rate | 4.47e-05 | +| loss | -0.0334 | +| n_updates | 59392 | +| policy_gradient_loss | -0.0199 | +| value_loss | 9.03e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1420 | +| iterations | 10895 | +| time_elapsed | 15713 | +| total_timesteps | 22312960 | +| train/ | | +| approx_kl | 0.013734867 | +| clip_fraction | 0.327 | +| clip_range | 0.0694 | +| entropy_loss | -6.82 | +| explained_variance | -0.123 | +| learning_rate | 4.47e-05 | +| loss | -0.0305 | +| n_updates | 59396 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.00015 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1420 | +| iterations | 10896 | +| time_elapsed | 15714 | +| total_timesteps | 22315008 | +| train/ | | +| approx_kl | 0.012464663 | +| clip_fraction | 0.336 | +| clip_range | 0.0694 | +| entropy_loss | -6.59 | +| explained_variance | 0.714 | +| learning_rate | 4.47e-05 | +| loss | -0.0313 | +| n_updates | 59400 | +| policy_gradient_loss | -0.0203 | +| value_loss | 7.04e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1419 | +| iterations | 10897 | +| time_elapsed | 15716 | +| total_timesteps | 22317056 | +| train/ | | +| approx_kl | 0.013834838 | +| clip_fraction | 0.338 | +| clip_range | 0.0694 | +| entropy_loss | -6.22 | +| explained_variance | 0.573 | +| learning_rate | 4.47e-05 | +| loss | -0.0325 | +| n_updates | 59404 | +| policy_gradient_loss | -0.0189 | +| value_loss | 8.81e-05 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1419 | +| iterations | 10898 | +| time_elapsed | 15717 | +| total_timesteps | 22319104 | +| train/ | | +| approx_kl | 0.0147512 | +| clip_fraction | 0.351 | +| clip_range | 0.0694 | +| entropy_loss | -6.3 | +| explained_variance | 0.5 | +| learning_rate | 4.47e-05 | +| loss | -0.0302 | +| n_updates | 59408 | +| policy_gradient_loss | -0.0195 | +| value_loss | 7.13e-05 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1419 | +| iterations | 10899 | +| time_elapsed | 15719 | +| total_timesteps | 22321152 | +| train/ | | +| approx_kl | 0.011797179 | +| clip_fraction | 0.322 | +| clip_range | 0.0694 | +| entropy_loss | -6.09 | +| explained_variance | 0.623 | +| learning_rate | 4.47e-05 | +| loss | -0.0279 | +| n_updates | 59412 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000151 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1419 | +| iterations | 10900 | +| time_elapsed | 15720 | +| total_timesteps | 22323200 | +| train/ | | +| approx_kl | 0.011089232 | +| clip_fraction | 0.305 | +| clip_range | 0.0694 | +| entropy_loss | -6.17 | +| explained_variance | 0.475 | +| learning_rate | 4.47e-05 | +| loss | -0.0281 | +| n_updates | 59416 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000156 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1419 | +| iterations | 10901 | +| time_elapsed | 15722 | +| total_timesteps | 22325248 | +| train/ | | +| approx_kl | 0.0129162595 | +| clip_fraction | 0.323 | +| clip_range | 0.0694 | +| entropy_loss | -6.15 | +| explained_variance | 0.7 | +| learning_rate | 4.47e-05 | +| loss | -0.0264 | +| n_updates | 59420 | +| policy_gradient_loss | -0.0169 | +| value_loss | 9.46e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1419 | +| iterations | 10902 | +| time_elapsed | 15723 | +| total_timesteps | 22327296 | +| train/ | | +| approx_kl | 0.013662258 | +| clip_fraction | 0.311 | +| clip_range | 0.0694 | +| entropy_loss | -6.76 | +| explained_variance | 0.0102 | +| learning_rate | 4.47e-05 | +| loss | -0.0344 | +| n_updates | 59424 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.00013 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1419 | +| iterations | 10903 | +| time_elapsed | 15725 | +| total_timesteps | 22329344 | +| train/ | | +| approx_kl | 0.0115753375 | +| clip_fraction | 0.308 | +| clip_range | 0.0694 | +| entropy_loss | -6.81 | +| explained_variance | 0.277 | +| learning_rate | 4.47e-05 | +| loss | -0.0306 | +| n_updates | 59428 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000152 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1419 | +| iterations | 10904 | +| time_elapsed | 15726 | +| total_timesteps | 22331392 | +| train/ | | +| approx_kl | 0.0145936785 | +| clip_fraction | 0.341 | +| clip_range | 0.0694 | +| entropy_loss | -6.59 | +| explained_variance | 0.22 | +| learning_rate | 4.47e-05 | +| loss | -0.0327 | +| n_updates | 59432 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000317 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1419 | +| iterations | 10905 | +| time_elapsed | 15728 | +| total_timesteps | 22333440 | +| train/ | | +| approx_kl | 0.012280957 | +| clip_fraction | 0.33 | +| clip_range | 0.0694 | +| entropy_loss | -6.14 | +| explained_variance | 0.504 | +| learning_rate | 4.47e-05 | +| loss | -0.0343 | +| n_updates | 59436 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000175 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1419 | +| iterations | 10906 | +| time_elapsed | 15729 | +| total_timesteps | 22335488 | +| train/ | | +| approx_kl | 0.012309775 | +| clip_fraction | 0.359 | +| clip_range | 0.0694 | +| entropy_loss | -6.48 | +| explained_variance | 0.426 | +| learning_rate | 4.47e-05 | +| loss | -0.0358 | +| n_updates | 59440 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000249 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1419 | +| iterations | 10907 | +| time_elapsed | 15731 | +| total_timesteps | 22337536 | +| train/ | | +| approx_kl | 0.013492974 | +| clip_fraction | 0.372 | +| clip_range | 0.0694 | +| entropy_loss | -6.63 | +| explained_variance | 0.467 | +| learning_rate | 4.47e-05 | +| loss | -0.0405 | +| n_updates | 59444 | +| policy_gradient_loss | -0.0243 | +| value_loss | 7.79e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1419 | +| iterations | 10908 | +| time_elapsed | 15732 | +| total_timesteps | 22339584 | +| train/ | | +| approx_kl | 0.012764838 | +| clip_fraction | 0.329 | +| clip_range | 0.0694 | +| entropy_loss | -6.31 | +| explained_variance | 0.301 | +| learning_rate | 4.47e-05 | +| loss | -0.03 | +| n_updates | 59448 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000314 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1419 | +| iterations | 10909 | +| time_elapsed | 15734 | +| total_timesteps | 22341632 | +| train/ | | +| approx_kl | 0.013102967 | +| clip_fraction | 0.313 | +| clip_range | 0.0694 | +| entropy_loss | -6.19 | +| explained_variance | 0.346 | +| learning_rate | 4.47e-05 | +| loss | -0.0239 | +| n_updates | 59452 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.000313 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1419 | +| iterations | 10910 | +| time_elapsed | 15735 | +| total_timesteps | 22343680 | +| train/ | | +| approx_kl | 0.01348452 | +| clip_fraction | 0.363 | +| clip_range | 0.0694 | +| entropy_loss | -5.7 | +| explained_variance | 0.621 | +| learning_rate | 4.47e-05 | +| loss | -0.0376 | +| n_updates | 59456 | +| policy_gradient_loss | -0.0225 | +| value_loss | 0.000127 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1419 | +| iterations | 10911 | +| time_elapsed | 15736 | +| total_timesteps | 22345728 | +| train/ | | +| approx_kl | 0.013306394 | +| clip_fraction | 0.348 | +| clip_range | 0.0694 | +| entropy_loss | -6.63 | +| explained_variance | 0.451 | +| learning_rate | 4.47e-05 | +| loss | -0.0345 | +| n_updates | 59460 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000105 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1419 | +| iterations | 10912 | +| time_elapsed | 15738 | +| total_timesteps | 22347776 | +| train/ | | +| approx_kl | 0.016570963 | +| clip_fraction | 0.371 | +| clip_range | 0.0694 | +| entropy_loss | -6.83 | +| explained_variance | 0.246 | +| learning_rate | 4.47e-05 | +| loss | -0.0356 | +| n_updates | 59464 | +| policy_gradient_loss | -0.0226 | +| value_loss | 8.59e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1419 | +| iterations | 10913 | +| time_elapsed | 15739 | +| total_timesteps | 22349824 | +| train/ | | +| approx_kl | 0.011812769 | +| clip_fraction | 0.328 | +| clip_range | 0.0694 | +| entropy_loss | -6.37 | +| explained_variance | 0.507 | +| learning_rate | 4.47e-05 | +| loss | -0.0306 | +| n_updates | 59468 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000188 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1419 | +| iterations | 10914 | +| time_elapsed | 15741 | +| total_timesteps | 22351872 | +| train/ | | +| approx_kl | 0.0138810165 | +| clip_fraction | 0.345 | +| clip_range | 0.0694 | +| entropy_loss | -6.74 | +| explained_variance | -0.0734 | +| learning_rate | 4.47e-05 | +| loss | -0.0282 | +| n_updates | 59472 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000165 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1419 | +| iterations | 10915 | +| time_elapsed | 15742 | +| total_timesteps | 22353920 | +| train/ | | +| approx_kl | 0.013056006 | +| clip_fraction | 0.333 | +| clip_range | 0.0694 | +| entropy_loss | -6.31 | +| explained_variance | 0.587 | +| learning_rate | 4.47e-05 | +| loss | -0.0255 | +| n_updates | 59476 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000154 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1419 | +| iterations | 10916 | +| time_elapsed | 15744 | +| total_timesteps | 22355968 | +| train/ | | +| approx_kl | 0.01184697 | +| clip_fraction | 0.322 | +| clip_range | 0.0694 | +| entropy_loss | -5.96 | +| explained_variance | 0.579 | +| learning_rate | 4.47e-05 | +| loss | -0.0226 | +| n_updates | 59480 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000148 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1419 | +| iterations | 10917 | +| time_elapsed | 15745 | +| total_timesteps | 22358016 | +| train/ | | +| approx_kl | 0.010784841 | +| clip_fraction | 0.331 | +| clip_range | 0.0694 | +| entropy_loss | -5.72 | +| explained_variance | 0.52 | +| learning_rate | 4.47e-05 | +| loss | -0.0273 | +| n_updates | 59484 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000252 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1419 | +| iterations | 10918 | +| time_elapsed | 15747 | +| total_timesteps | 22360064 | +| train/ | | +| approx_kl | 0.0137199685 | +| clip_fraction | 0.348 | +| clip_range | 0.0694 | +| entropy_loss | -6.11 | +| explained_variance | 0.329 | +| learning_rate | 4.47e-05 | +| loss | -0.0297 | +| n_updates | 59488 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000209 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1419 | +| iterations | 10919 | +| time_elapsed | 15748 | +| total_timesteps | 22362112 | +| train/ | | +| approx_kl | 0.010735596 | +| clip_fraction | 0.336 | +| clip_range | 0.0694 | +| entropy_loss | -6.55 | +| explained_variance | 0.318 | +| learning_rate | 4.47e-05 | +| loss | -0.0275 | +| n_updates | 59492 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000162 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1419 | +| iterations | 10920 | +| time_elapsed | 15750 | +| total_timesteps | 22364160 | +| train/ | | +| approx_kl | 0.0135146035 | +| clip_fraction | 0.345 | +| clip_range | 0.0694 | +| entropy_loss | -6.26 | +| explained_variance | 0.533 | +| learning_rate | 4.47e-05 | +| loss | -0.0343 | +| n_updates | 59496 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000197 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1419 | +| iterations | 10921 | +| time_elapsed | 15751 | +| total_timesteps | 22366208 | +| train/ | | +| approx_kl | 0.012950724 | +| clip_fraction | 0.359 | +| clip_range | 0.0694 | +| entropy_loss | -6.38 | +| explained_variance | 0.353 | +| learning_rate | 4.47e-05 | +| loss | -0.0293 | +| n_updates | 59500 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000122 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1419 | +| iterations | 10922 | +| time_elapsed | 15753 | +| total_timesteps | 22368256 | +| train/ | | +| approx_kl | 0.00999817 | +| clip_fraction | 0.327 | +| clip_range | 0.0694 | +| entropy_loss | -7 | +| explained_variance | -0.321 | +| learning_rate | 4.47e-05 | +| loss | -0.034 | +| n_updates | 59504 | +| policy_gradient_loss | -0.0211 | +| value_loss | 7.86e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1419 | +| iterations | 10923 | +| time_elapsed | 15754 | +| total_timesteps | 22370304 | +| train/ | | +| approx_kl | 0.011428525 | +| clip_fraction | 0.314 | +| clip_range | 0.0694 | +| entropy_loss | -6.69 | +| explained_variance | 0.308 | +| learning_rate | 4.47e-05 | +| loss | -0.0279 | +| n_updates | 59508 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000145 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1419 | +| iterations | 10924 | +| time_elapsed | 15756 | +| total_timesteps | 22372352 | +| train/ | | +| approx_kl | 0.01477234 | +| clip_fraction | 0.326 | +| clip_range | 0.0694 | +| entropy_loss | -6.97 | +| explained_variance | -0.0745 | +| learning_rate | 4.47e-05 | +| loss | -0.0282 | +| n_updates | 59512 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000148 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1419 | +| iterations | 10925 | +| time_elapsed | 15757 | +| total_timesteps | 22374400 | +| train/ | | +| approx_kl | 0.012770017 | +| clip_fraction | 0.337 | +| clip_range | 0.0694 | +| entropy_loss | -6.67 | +| explained_variance | 0.391 | +| learning_rate | 4.47e-05 | +| loss | -0.0263 | +| n_updates | 59516 | +| policy_gradient_loss | -0.0194 | +| value_loss | 9.91e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1419 | +| iterations | 10926 | +| time_elapsed | 15759 | +| total_timesteps | 22376448 | +| train/ | | +| approx_kl | 0.011373119 | +| clip_fraction | 0.307 | +| clip_range | 0.0694 | +| entropy_loss | -6 | +| explained_variance | 0.402 | +| learning_rate | 4.47e-05 | +| loss | -0.0257 | +| n_updates | 59520 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000318 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1419 | +| iterations | 10927 | +| time_elapsed | 15760 | +| total_timesteps | 22378496 | +| train/ | | +| approx_kl | 0.012479344 | +| clip_fraction | 0.334 | +| clip_range | 0.0694 | +| entropy_loss | -5.77 | +| explained_variance | 0.566 | +| learning_rate | 4.47e-05 | +| loss | -0.0284 | +| n_updates | 59524 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.00019 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1419 | +| iterations | 10928 | +| time_elapsed | 15761 | +| total_timesteps | 22380544 | +| train/ | | +| approx_kl | 0.013143339 | +| clip_fraction | 0.353 | +| clip_range | 0.0694 | +| entropy_loss | -6.61 | +| explained_variance | 0.339 | +| learning_rate | 4.47e-05 | +| loss | -0.0325 | +| n_updates | 59528 | +| policy_gradient_loss | -0.0219 | +| value_loss | 0.000104 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1419 | +| iterations | 10929 | +| time_elapsed | 15763 | +| total_timesteps | 22382592 | +| train/ | | +| approx_kl | 0.0125864595 | +| clip_fraction | 0.354 | +| clip_range | 0.0694 | +| entropy_loss | -6.33 | +| explained_variance | 0.491 | +| learning_rate | 4.47e-05 | +| loss | -0.0287 | +| n_updates | 59532 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000154 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1419 | +| iterations | 10930 | +| time_elapsed | 15764 | +| total_timesteps | 22384640 | +| train/ | | +| approx_kl | 0.014597475 | +| clip_fraction | 0.349 | +| clip_range | 0.0694 | +| entropy_loss | -6.36 | +| explained_variance | 0.519 | +| learning_rate | 4.47e-05 | +| loss | -0.0312 | +| n_updates | 59536 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1419 | +| iterations | 10931 | +| time_elapsed | 15766 | +| total_timesteps | 22386688 | +| train/ | | +| approx_kl | 0.012848975 | +| clip_fraction | 0.324 | +| clip_range | 0.0694 | +| entropy_loss | -6.15 | +| explained_variance | 0.472 | +| learning_rate | 4.47e-05 | +| loss | -0.0278 | +| n_updates | 59540 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000189 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1419 | +| iterations | 10932 | +| time_elapsed | 15767 | +| total_timesteps | 22388736 | +| train/ | | +| approx_kl | 0.012511438 | +| clip_fraction | 0.306 | +| clip_range | 0.0694 | +| entropy_loss | -6.49 | +| explained_variance | 0.0323 | +| learning_rate | 4.47e-05 | +| loss | -0.0258 | +| n_updates | 59544 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000373 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1419 | +| iterations | 10933 | +| time_elapsed | 15769 | +| total_timesteps | 22390784 | +| train/ | | +| approx_kl | 0.01467021 | +| clip_fraction | 0.369 | +| clip_range | 0.0694 | +| entropy_loss | -6.48 | +| explained_variance | 0.295 | +| learning_rate | 4.47e-05 | +| loss | -0.0366 | +| n_updates | 59548 | +| policy_gradient_loss | -0.0236 | +| value_loss | 0.000124 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1419 | +| iterations | 10934 | +| time_elapsed | 15770 | +| total_timesteps | 22392832 | +| train/ | | +| approx_kl | 0.015999496 | +| clip_fraction | 0.368 | +| clip_range | 0.0694 | +| entropy_loss | -6.63 | +| explained_variance | 0.345 | +| learning_rate | 4.47e-05 | +| loss | -0.0317 | +| n_updates | 59552 | +| policy_gradient_loss | -0.024 | +| value_loss | 0.000105 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1419 | +| iterations | 10935 | +| time_elapsed | 15772 | +| total_timesteps | 22394880 | +| train/ | | +| approx_kl | 0.011917142 | +| clip_fraction | 0.312 | +| clip_range | 0.0694 | +| entropy_loss | -6.58 | +| explained_variance | 0.196 | +| learning_rate | 4.47e-05 | +| loss | -0.018 | +| n_updates | 59556 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000287 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1419 | +| iterations | 10936 | +| time_elapsed | 15773 | +| total_timesteps | 22396928 | +| train/ | | +| approx_kl | 0.0131945275 | +| clip_fraction | 0.321 | +| clip_range | 0.0694 | +| entropy_loss | -5.62 | +| explained_variance | 0.645 | +| learning_rate | 4.47e-05 | +| loss | -0.0295 | +| n_updates | 59560 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000163 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1419 | +| iterations | 10937 | +| time_elapsed | 15775 | +| total_timesteps | 22398976 | +| train/ | | +| approx_kl | 0.011865716 | +| clip_fraction | 0.315 | +| clip_range | 0.0694 | +| entropy_loss | -6.41 | +| explained_variance | 0.417 | +| learning_rate | 4.47e-05 | +| loss | -0.0298 | +| n_updates | 59564 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000275 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1419 | +| iterations | 10938 | +| time_elapsed | 15776 | +| total_timesteps | 22401024 | +| train/ | | +| approx_kl | 0.014332935 | +| clip_fraction | 0.348 | +| clip_range | 0.0694 | +| entropy_loss | -6.27 | +| explained_variance | 0.642 | +| learning_rate | 4.47e-05 | +| loss | -0.0352 | +| n_updates | 59568 | +| policy_gradient_loss | -0.0218 | +| value_loss | 6.88e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1419 | +| iterations | 10939 | +| time_elapsed | 15778 | +| total_timesteps | 22403072 | +| train/ | | +| approx_kl | 0.012899177 | +| clip_fraction | 0.331 | +| clip_range | 0.0694 | +| entropy_loss | -6.04 | +| explained_variance | 0.511 | +| learning_rate | 4.47e-05 | +| loss | -0.0338 | +| n_updates | 59572 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000174 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1419 | +| iterations | 10940 | +| time_elapsed | 15779 | +| total_timesteps | 22405120 | +| train/ | | +| approx_kl | 0.015090127 | +| clip_fraction | 0.348 | +| clip_range | 0.0694 | +| entropy_loss | -6.38 | +| explained_variance | 0.301 | +| learning_rate | 4.47e-05 | +| loss | -0.0299 | +| n_updates | 59576 | +| policy_gradient_loss | -0.0203 | +| value_loss | 8.89e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1419 | +| iterations | 10941 | +| time_elapsed | 15781 | +| total_timesteps | 22407168 | +| train/ | | +| approx_kl | 0.011043852 | +| clip_fraction | 0.309 | +| clip_range | 0.0694 | +| entropy_loss | -6.9 | +| explained_variance | 0.314 | +| learning_rate | 4.47e-05 | +| loss | -0.0267 | +| n_updates | 59580 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000219 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1419 | +| iterations | 10942 | +| time_elapsed | 15782 | +| total_timesteps | 22409216 | +| train/ | | +| approx_kl | 0.014075896 | +| clip_fraction | 0.312 | +| clip_range | 0.0694 | +| entropy_loss | -7.05 | +| explained_variance | 0.173 | +| learning_rate | 4.47e-05 | +| loss | -0.0368 | +| n_updates | 59584 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000142 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1419 | +| iterations | 10943 | +| time_elapsed | 15784 | +| total_timesteps | 22411264 | +| train/ | | +| approx_kl | 0.011691221 | +| clip_fraction | 0.321 | +| clip_range | 0.0694 | +| entropy_loss | -6.97 | +| explained_variance | 0.0507 | +| learning_rate | 4.47e-05 | +| loss | -0.0329 | +| n_updates | 59588 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000257 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1419 | +| iterations | 10944 | +| time_elapsed | 15785 | +| total_timesteps | 22413312 | +| train/ | | +| approx_kl | 0.013055999 | +| clip_fraction | 0.332 | +| clip_range | 0.0694 | +| entropy_loss | -6.77 | +| explained_variance | 0.168 | +| learning_rate | 4.47e-05 | +| loss | -0.0278 | +| n_updates | 59592 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000191 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1419 | +| iterations | 10945 | +| time_elapsed | 15787 | +| total_timesteps | 22415360 | +| train/ | | +| approx_kl | 0.014116071 | +| clip_fraction | 0.331 | +| clip_range | 0.0694 | +| entropy_loss | -5.44 | +| explained_variance | 0.792 | +| learning_rate | 4.47e-05 | +| loss | -0.021 | +| n_updates | 59596 | +| policy_gradient_loss | -0.0186 | +| value_loss | 8.46e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1419 | +| iterations | 10946 | +| time_elapsed | 15788 | +| total_timesteps | 22417408 | +| train/ | | +| approx_kl | 0.014000462 | +| clip_fraction | 0.338 | +| clip_range | 0.0694 | +| entropy_loss | -6.54 | +| explained_variance | 0.358 | +| learning_rate | 4.47e-05 | +| loss | -0.036 | +| n_updates | 59600 | +| policy_gradient_loss | -0.0208 | +| value_loss | 7.36e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1419 | +| iterations | 10947 | +| time_elapsed | 15789 | +| total_timesteps | 22419456 | +| train/ | | +| approx_kl | 0.013475286 | +| clip_fraction | 0.356 | +| clip_range | 0.0694 | +| entropy_loss | -6.91 | +| explained_variance | -0.211 | +| learning_rate | 4.47e-05 | +| loss | -0.0368 | +| n_updates | 59604 | +| policy_gradient_loss | -0.0226 | +| value_loss | 5e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1419 | +| iterations | 10948 | +| time_elapsed | 15791 | +| total_timesteps | 22421504 | +| train/ | | +| approx_kl | 0.013426547 | +| clip_fraction | 0.341 | +| clip_range | 0.0694 | +| entropy_loss | -6.59 | +| explained_variance | 0.396 | +| learning_rate | 4.47e-05 | +| loss | -0.0256 | +| n_updates | 59608 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000226 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1419 | +| iterations | 10949 | +| time_elapsed | 15792 | +| total_timesteps | 22423552 | +| train/ | | +| approx_kl | 0.014511742 | +| clip_fraction | 0.334 | +| clip_range | 0.0694 | +| entropy_loss | -5.71 | +| explained_variance | 0.785 | +| learning_rate | 4.47e-05 | +| loss | -0.0307 | +| n_updates | 59612 | +| policy_gradient_loss | -0.0199 | +| value_loss | 7.98e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1419 | +| iterations | 10950 | +| time_elapsed | 15794 | +| total_timesteps | 22425600 | +| train/ | | +| approx_kl | 0.011439722 | +| clip_fraction | 0.31 | +| clip_range | 0.0694 | +| entropy_loss | -6.15 | +| explained_variance | 0.406 | +| learning_rate | 4.47e-05 | +| loss | -0.0268 | +| n_updates | 59616 | +| policy_gradient_loss | -0.0147 | +| value_loss | 0.00022 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1419 | +| iterations | 10951 | +| time_elapsed | 15795 | +| total_timesteps | 22427648 | +| train/ | | +| approx_kl | 0.011019047 | +| clip_fraction | 0.321 | +| clip_range | 0.0694 | +| entropy_loss | -6.65 | +| explained_variance | 0.363 | +| learning_rate | 4.47e-05 | +| loss | -0.0266 | +| n_updates | 59620 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000128 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1419 | +| iterations | 10952 | +| time_elapsed | 15797 | +| total_timesteps | 22429696 | +| train/ | | +| approx_kl | 0.013102543 | +| clip_fraction | 0.354 | +| clip_range | 0.0694 | +| entropy_loss | -6.3 | +| explained_variance | 0.611 | +| learning_rate | 4.47e-05 | +| loss | -0.0334 | +| n_updates | 59624 | +| policy_gradient_loss | -0.02 | +| value_loss | 9.69e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1419 | +| iterations | 10953 | +| time_elapsed | 15798 | +| total_timesteps | 22431744 | +| train/ | | +| approx_kl | 0.014591802 | +| clip_fraction | 0.352 | +| clip_range | 0.0694 | +| entropy_loss | -6.22 | +| explained_variance | 0.502 | +| learning_rate | 4.47e-05 | +| loss | -0.0413 | +| n_updates | 59628 | +| policy_gradient_loss | -0.0211 | +| value_loss | 6.22e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1419 | +| iterations | 10954 | +| time_elapsed | 15800 | +| total_timesteps | 22433792 | +| train/ | | +| approx_kl | 0.012357568 | +| clip_fraction | 0.343 | +| clip_range | 0.0694 | +| entropy_loss | -7.02 | +| explained_variance | 0.0489 | +| learning_rate | 4.47e-05 | +| loss | -0.0305 | +| n_updates | 59632 | +| policy_gradient_loss | -0.0202 | +| value_loss | 7.48e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1419 | +| iterations | 10955 | +| time_elapsed | 15801 | +| total_timesteps | 22435840 | +| train/ | | +| approx_kl | 0.012434822 | +| clip_fraction | 0.351 | +| clip_range | 0.0694 | +| entropy_loss | -6.63 | +| explained_variance | 0.384 | +| learning_rate | 4.47e-05 | +| loss | -0.0289 | +| n_updates | 59636 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000119 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1419 | +| iterations | 10956 | +| time_elapsed | 15803 | +| total_timesteps | 22437888 | +| train/ | | +| approx_kl | 0.014264016 | +| clip_fraction | 0.338 | +| clip_range | 0.0694 | +| entropy_loss | -6.75 | +| explained_variance | 0.587 | +| learning_rate | 4.47e-05 | +| loss | -0.0361 | +| n_updates | 59640 | +| policy_gradient_loss | -0.0194 | +| value_loss | 5.6e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1419 | +| iterations | 10957 | +| time_elapsed | 15804 | +| total_timesteps | 22439936 | +| train/ | | +| approx_kl | 0.012066916 | +| clip_fraction | 0.285 | +| clip_range | 0.0694 | +| entropy_loss | -5.96 | +| explained_variance | 0.697 | +| learning_rate | 4.47e-05 | +| loss | -0.0198 | +| n_updates | 59644 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.00013 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1419 | +| iterations | 10958 | +| time_elapsed | 15805 | +| total_timesteps | 22441984 | +| train/ | | +| approx_kl | 0.011096987 | +| clip_fraction | 0.299 | +| clip_range | 0.0694 | +| entropy_loss | -6.32 | +| explained_variance | 0.365 | +| learning_rate | 4.47e-05 | +| loss | -0.0274 | +| n_updates | 59648 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000136 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1419 | +| iterations | 10959 | +| time_elapsed | 15807 | +| total_timesteps | 22444032 | +| train/ | | +| approx_kl | 0.014028914 | +| clip_fraction | 0.352 | +| clip_range | 0.0694 | +| entropy_loss | -5.98 | +| explained_variance | 0.688 | +| learning_rate | 4.47e-05 | +| loss | -0.0314 | +| n_updates | 59652 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000107 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1419 | +| iterations | 10960 | +| time_elapsed | 15808 | +| total_timesteps | 22446080 | +| train/ | | +| approx_kl | 0.013065768 | +| clip_fraction | 0.305 | +| clip_range | 0.0694 | +| entropy_loss | -6.32 | +| explained_variance | 0.647 | +| learning_rate | 4.47e-05 | +| loss | -0.0315 | +| n_updates | 59656 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000106 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1419 | +| iterations | 10961 | +| time_elapsed | 15810 | +| total_timesteps | 22448128 | +| train/ | | +| approx_kl | 0.01288021 | +| clip_fraction | 0.34 | +| clip_range | 0.0694 | +| entropy_loss | -6.5 | +| explained_variance | 0.167 | +| learning_rate | 4.47e-05 | +| loss | -0.0295 | +| n_updates | 59660 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000283 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1419 | +| iterations | 10962 | +| time_elapsed | 15811 | +| total_timesteps | 22450176 | +| train/ | | +| approx_kl | 0.012708878 | +| clip_fraction | 0.362 | +| clip_range | 0.0694 | +| entropy_loss | -6.78 | +| explained_variance | 0.323 | +| learning_rate | 4.47e-05 | +| loss | -0.0265 | +| n_updates | 59664 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000157 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1419 | +| iterations | 10963 | +| time_elapsed | 15813 | +| total_timesteps | 22452224 | +| train/ | | +| approx_kl | 0.012176776 | +| clip_fraction | 0.321 | +| clip_range | 0.0694 | +| entropy_loss | -6.68 | +| explained_variance | 0.326 | +| learning_rate | 4.47e-05 | +| loss | -0.0302 | +| n_updates | 59668 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.00015 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1419 | +| iterations | 10964 | +| time_elapsed | 15814 | +| total_timesteps | 22454272 | +| train/ | | +| approx_kl | 0.013002533 | +| clip_fraction | 0.293 | +| clip_range | 0.0694 | +| entropy_loss | -6.36 | +| explained_variance | 0.286 | +| learning_rate | 4.47e-05 | +| loss | -0.0243 | +| n_updates | 59672 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000322 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1419 | +| iterations | 10965 | +| time_elapsed | 15816 | +| total_timesteps | 22456320 | +| train/ | | +| approx_kl | 0.010425066 | +| clip_fraction | 0.347 | +| clip_range | 0.0694 | +| entropy_loss | -6.22 | +| explained_variance | 0.205 | +| learning_rate | 4.47e-05 | +| loss | -0.0251 | +| n_updates | 59676 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000331 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1419 | +| iterations | 10966 | +| time_elapsed | 15817 | +| total_timesteps | 22458368 | +| train/ | | +| approx_kl | 0.0110851675 | +| clip_fraction | 0.359 | +| clip_range | 0.0694 | +| entropy_loss | -6.14 | +| explained_variance | 0.736 | +| learning_rate | 4.47e-05 | +| loss | -0.0327 | +| n_updates | 59680 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000104 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1419 | +| iterations | 10967 | +| time_elapsed | 15819 | +| total_timesteps | 22460416 | +| train/ | | +| approx_kl | 0.013274418 | +| clip_fraction | 0.352 | +| clip_range | 0.0694 | +| entropy_loss | -6.64 | +| explained_variance | -0.227 | +| learning_rate | 4.47e-05 | +| loss | -0.0297 | +| n_updates | 59684 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000183 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1419 | +| iterations | 10968 | +| time_elapsed | 15820 | +| total_timesteps | 22462464 | +| train/ | | +| approx_kl | 0.010966829 | +| clip_fraction | 0.326 | +| clip_range | 0.0694 | +| entropy_loss | -6.32 | +| explained_variance | 0.507 | +| learning_rate | 4.47e-05 | +| loss | -0.0297 | +| n_updates | 59688 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000227 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1419 | +| iterations | 10969 | +| time_elapsed | 15822 | +| total_timesteps | 22464512 | +| train/ | | +| approx_kl | 0.012440138 | +| clip_fraction | 0.339 | +| clip_range | 0.0694 | +| entropy_loss | -5.97 | +| explained_variance | 0.552 | +| learning_rate | 4.47e-05 | +| loss | -0.0401 | +| n_updates | 59692 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000169 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1419 | +| iterations | 10970 | +| time_elapsed | 15823 | +| total_timesteps | 22466560 | +| train/ | | +| approx_kl | 0.012129566 | +| clip_fraction | 0.337 | +| clip_range | 0.0694 | +| entropy_loss | -6.63 | +| explained_variance | 0.409 | +| learning_rate | 4.47e-05 | +| loss | -0.0332 | +| n_updates | 59696 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000139 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1419 | +| iterations | 10971 | +| time_elapsed | 15825 | +| total_timesteps | 22468608 | +| train/ | | +| approx_kl | 0.014966465 | +| clip_fraction | 0.383 | +| clip_range | 0.0694 | +| entropy_loss | -6.89 | +| explained_variance | -0.00681 | +| learning_rate | 4.47e-05 | +| loss | -0.0355 | +| n_updates | 59700 | +| policy_gradient_loss | -0.023 | +| value_loss | 6.99e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1419 | +| iterations | 10972 | +| time_elapsed | 15826 | +| total_timesteps | 22470656 | +| train/ | | +| approx_kl | 0.01077359 | +| clip_fraction | 0.342 | +| clip_range | 0.0694 | +| entropy_loss | -6.74 | +| explained_variance | 0.27 | +| learning_rate | 4.47e-05 | +| loss | -0.0307 | +| n_updates | 59704 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000197 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1419 | +| iterations | 10973 | +| time_elapsed | 15827 | +| total_timesteps | 22472704 | +| train/ | | +| approx_kl | 0.0114049055 | +| clip_fraction | 0.337 | +| clip_range | 0.0694 | +| entropy_loss | -6.52 | +| explained_variance | 0.15 | +| learning_rate | 4.47e-05 | +| loss | -0.0296 | +| n_updates | 59708 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000305 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1419 | +| iterations | 10974 | +| time_elapsed | 15829 | +| total_timesteps | 22474752 | +| train/ | | +| approx_kl | 0.014527068 | +| clip_fraction | 0.372 | +| clip_range | 0.0694 | +| entropy_loss | -6.51 | +| explained_variance | 0.5 | +| learning_rate | 4.47e-05 | +| loss | -0.0395 | +| n_updates | 59712 | +| policy_gradient_loss | -0.0245 | +| value_loss | 6.08e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1419 | +| iterations | 10975 | +| time_elapsed | 15830 | +| total_timesteps | 22476800 | +| train/ | | +| approx_kl | 0.01404444 | +| clip_fraction | 0.346 | +| clip_range | 0.0694 | +| entropy_loss | -6.52 | +| explained_variance | 0.543 | +| learning_rate | 4.47e-05 | +| loss | -0.0347 | +| n_updates | 59716 | +| policy_gradient_loss | -0.0207 | +| value_loss | 8.98e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1419 | +| iterations | 10976 | +| time_elapsed | 15832 | +| total_timesteps | 22478848 | +| train/ | | +| approx_kl | 0.014248835 | +| clip_fraction | 0.327 | +| clip_range | 0.0694 | +| entropy_loss | -5.63 | +| explained_variance | 0.591 | +| learning_rate | 4.47e-05 | +| loss | -0.0243 | +| n_updates | 59720 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000186 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1419 | +| iterations | 10977 | +| time_elapsed | 15833 | +| total_timesteps | 22480896 | +| train/ | | +| approx_kl | 0.0141270785 | +| clip_fraction | 0.334 | +| clip_range | 0.0694 | +| entropy_loss | -6.35 | +| explained_variance | 0.284 | +| learning_rate | 4.47e-05 | +| loss | -0.0277 | +| n_updates | 59724 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.00017 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1419 | +| iterations | 10978 | +| time_elapsed | 15835 | +| total_timesteps | 22482944 | +| train/ | | +| approx_kl | 0.015495665 | +| clip_fraction | 0.358 | +| clip_range | 0.0694 | +| entropy_loss | -6.29 | +| explained_variance | 0.104 | +| learning_rate | 4.47e-05 | +| loss | -0.0336 | +| n_updates | 59728 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000124 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1419 | +| iterations | 10979 | +| time_elapsed | 15836 | +| total_timesteps | 22484992 | +| train/ | | +| approx_kl | 0.011042239 | +| clip_fraction | 0.317 | +| clip_range | 0.0694 | +| entropy_loss | -5.96 | +| explained_variance | 0.516 | +| learning_rate | 4.47e-05 | +| loss | -0.0224 | +| n_updates | 59732 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000233 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1419 | +| iterations | 10980 | +| time_elapsed | 15838 | +| total_timesteps | 22487040 | +| train/ | | +| approx_kl | 0.01479792 | +| clip_fraction | 0.323 | +| clip_range | 0.0694 | +| entropy_loss | -6.51 | +| explained_variance | 0.278 | +| learning_rate | 4.47e-05 | +| loss | -0.0338 | +| n_updates | 59736 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000284 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1419 | +| iterations | 10981 | +| time_elapsed | 15839 | +| total_timesteps | 22489088 | +| train/ | | +| approx_kl | 0.01173934 | +| clip_fraction | 0.33 | +| clip_range | 0.0694 | +| entropy_loss | -6.51 | +| explained_variance | 0.336 | +| learning_rate | 4.47e-05 | +| loss | -0.0332 | +| n_updates | 59740 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000287 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1419 | +| iterations | 10982 | +| time_elapsed | 15840 | +| total_timesteps | 22491136 | +| train/ | | +| approx_kl | 0.013571664 | +| clip_fraction | 0.359 | +| clip_range | 0.0694 | +| entropy_loss | -6.45 | +| explained_variance | 0.303 | +| learning_rate | 4.47e-05 | +| loss | -0.0386 | +| n_updates | 59744 | +| policy_gradient_loss | -0.0228 | +| value_loss | 0.000142 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1419 | +| iterations | 10983 | +| time_elapsed | 15842 | +| total_timesteps | 22493184 | +| train/ | | +| approx_kl | 0.012098789 | +| clip_fraction | 0.365 | +| clip_range | 0.0694 | +| entropy_loss | -6.8 | +| explained_variance | -0.0795 | +| learning_rate | 4.47e-05 | +| loss | -0.0311 | +| n_updates | 59748 | +| policy_gradient_loss | -0.0222 | +| value_loss | 0.000144 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1419 | +| iterations | 10984 | +| time_elapsed | 15843 | +| total_timesteps | 22495232 | +| train/ | | +| approx_kl | 0.009322219 | +| clip_fraction | 0.308 | +| clip_range | 0.0694 | +| entropy_loss | -6.87 | +| explained_variance | 0.273 | +| learning_rate | 4.47e-05 | +| loss | -0.0256 | +| n_updates | 59752 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000276 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1419 | +| iterations | 10985 | +| time_elapsed | 15845 | +| total_timesteps | 22497280 | +| train/ | | +| approx_kl | 0.011671599 | +| clip_fraction | 0.359 | +| clip_range | 0.0694 | +| entropy_loss | -6.65 | +| explained_variance | 0.609 | +| learning_rate | 4.47e-05 | +| loss | -0.0388 | +| n_updates | 59756 | +| policy_gradient_loss | -0.0225 | +| value_loss | 0.000102 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1419 | +| iterations | 10986 | +| time_elapsed | 15846 | +| total_timesteps | 22499328 | +| train/ | | +| approx_kl | 0.011199471 | +| clip_fraction | 0.336 | +| clip_range | 0.0694 | +| entropy_loss | -6.34 | +| explained_variance | 0.622 | +| learning_rate | 4.47e-05 | +| loss | -0.0322 | +| n_updates | 59760 | +| policy_gradient_loss | -0.0201 | +| value_loss | 8.01e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1419 | +| iterations | 10987 | +| time_elapsed | 15848 | +| total_timesteps | 22501376 | +| train/ | | +| approx_kl | 0.014412397 | +| clip_fraction | 0.356 | +| clip_range | 0.0694 | +| entropy_loss | -6.04 | +| explained_variance | 0.765 | +| learning_rate | 4.47e-05 | +| loss | -0.0378 | +| n_updates | 59764 | +| policy_gradient_loss | -0.0213 | +| value_loss | 5.1e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1419 | +| iterations | 10988 | +| time_elapsed | 15849 | +| total_timesteps | 22503424 | +| train/ | | +| approx_kl | 0.011961479 | +| clip_fraction | 0.311 | +| clip_range | 0.0694 | +| entropy_loss | -5.79 | +| explained_variance | 0.766 | +| learning_rate | 4.47e-05 | +| loss | -0.0205 | +| n_updates | 59768 | +| policy_gradient_loss | -0.0164 | +| value_loss | 9.76e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1419 | +| iterations | 10989 | +| time_elapsed | 15851 | +| total_timesteps | 22505472 | +| train/ | | +| approx_kl | 0.011189516 | +| clip_fraction | 0.326 | +| clip_range | 0.0694 | +| entropy_loss | -6.15 | +| explained_variance | 0.497 | +| learning_rate | 4.47e-05 | +| loss | -0.0289 | +| n_updates | 59772 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000114 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1419 | +| iterations | 10990 | +| time_elapsed | 15852 | +| total_timesteps | 22507520 | +| train/ | | +| approx_kl | 0.011921797 | +| clip_fraction | 0.331 | +| clip_range | 0.0694 | +| entropy_loss | -6.51 | +| explained_variance | 0.503 | +| learning_rate | 4.47e-05 | +| loss | -0.0255 | +| n_updates | 59776 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.00012 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1419 | +| iterations | 10991 | +| time_elapsed | 15854 | +| total_timesteps | 22509568 | +| train/ | | +| approx_kl | 0.013811882 | +| clip_fraction | 0.353 | +| clip_range | 0.0694 | +| entropy_loss | -6.37 | +| explained_variance | 0.583 | +| learning_rate | 4.47e-05 | +| loss | -0.0301 | +| n_updates | 59780 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000111 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1419 | +| iterations | 10992 | +| time_elapsed | 15855 | +| total_timesteps | 22511616 | +| train/ | | +| approx_kl | 0.010569852 | +| clip_fraction | 0.334 | +| clip_range | 0.0694 | +| entropy_loss | -6.41 | +| explained_variance | 0.593 | +| learning_rate | 4.47e-05 | +| loss | -0.0349 | +| n_updates | 59784 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000108 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1419 | +| iterations | 10993 | +| time_elapsed | 15856 | +| total_timesteps | 22513664 | +| train/ | | +| approx_kl | 0.010961061 | +| clip_fraction | 0.319 | +| clip_range | 0.0694 | +| entropy_loss | -6.52 | +| explained_variance | 0.344 | +| learning_rate | 4.47e-05 | +| loss | -0.0307 | +| n_updates | 59788 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000128 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1419 | +| iterations | 10994 | +| time_elapsed | 15858 | +| total_timesteps | 22515712 | +| train/ | | +| approx_kl | 0.013707946 | +| clip_fraction | 0.307 | +| clip_range | 0.0694 | +| entropy_loss | -6.31 | +| explained_variance | 0.534 | +| learning_rate | 4.47e-05 | +| loss | -0.0321 | +| n_updates | 59792 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000178 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1419 | +| iterations | 10995 | +| time_elapsed | 15859 | +| total_timesteps | 22517760 | +| train/ | | +| approx_kl | 0.01191359 | +| clip_fraction | 0.339 | +| clip_range | 0.0694 | +| entropy_loss | -6.41 | +| explained_variance | 0.198 | +| learning_rate | 4.47e-05 | +| loss | -0.0318 | +| n_updates | 59796 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000316 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1419 | +| iterations | 10996 | +| time_elapsed | 15861 | +| total_timesteps | 22519808 | +| train/ | | +| approx_kl | 0.015191035 | +| clip_fraction | 0.366 | +| clip_range | 0.0694 | +| entropy_loss | -6.27 | +| explained_variance | 0.541 | +| learning_rate | 4.47e-05 | +| loss | -0.0388 | +| n_updates | 59800 | +| policy_gradient_loss | -0.0233 | +| value_loss | 9.25e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1419 | +| iterations | 10997 | +| time_elapsed | 15862 | +| total_timesteps | 22521856 | +| train/ | | +| approx_kl | 0.014448589 | +| clip_fraction | 0.331 | +| clip_range | 0.0694 | +| entropy_loss | -6.46 | +| explained_variance | 0.214 | +| learning_rate | 4.47e-05 | +| loss | -0.0297 | +| n_updates | 59804 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000242 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1419 | +| iterations | 10998 | +| time_elapsed | 15864 | +| total_timesteps | 22523904 | +| train/ | | +| approx_kl | 0.013641807 | +| clip_fraction | 0.349 | +| clip_range | 0.0694 | +| entropy_loss | -6.83 | +| explained_variance | -0.0543 | +| learning_rate | 4.47e-05 | +| loss | -0.0268 | +| n_updates | 59808 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000173 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1419 | +| iterations | 10999 | +| time_elapsed | 15865 | +| total_timesteps | 22525952 | +| train/ | | +| approx_kl | 0.013487179 | +| clip_fraction | 0.327 | +| clip_range | 0.0694 | +| entropy_loss | -6.32 | +| explained_variance | 0.431 | +| learning_rate | 4.47e-05 | +| loss | -0.0339 | +| n_updates | 59812 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000152 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.315 | +| time/ | | +| fps | 1419 | +| iterations | 11000 | +| time_elapsed | 15867 | +| total_timesteps | 22528000 | +| train/ | | +| approx_kl | 0.013781776 | +| clip_fraction | 0.333 | +| clip_range | 0.0694 | +| entropy_loss | -6.36 | +| explained_variance | 0.462 | +| learning_rate | 4.47e-05 | +| loss | -0.0314 | +| n_updates | 59816 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000164 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1419 | +| iterations | 11001 | +| time_elapsed | 15868 | +| total_timesteps | 22530048 | +| train/ | | +| approx_kl | 0.011771698 | +| clip_fraction | 0.327 | +| clip_range | 0.0694 | +| entropy_loss | -6.25 | +| explained_variance | 0.391 | +| learning_rate | 4.46e-05 | +| loss | -0.0235 | +| n_updates | 59820 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000242 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 1419 | +| iterations | 11002 | +| time_elapsed | 15870 | +| total_timesteps | 22532096 | +| train/ | | +| approx_kl | 0.013564961 | +| clip_fraction | 0.355 | +| clip_range | 0.0694 | +| entropy_loss | -6.36 | +| explained_variance | 0.544 | +| learning_rate | 4.46e-05 | +| loss | -0.0328 | +| n_updates | 59824 | +| policy_gradient_loss | -0.0214 | +| value_loss | 9.17e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1419 | +| iterations | 11003 | +| time_elapsed | 15871 | +| total_timesteps | 22534144 | +| train/ | | +| approx_kl | 0.014006546 | +| clip_fraction | 0.363 | +| clip_range | 0.0694 | +| entropy_loss | -5.93 | +| explained_variance | 0.574 | +| learning_rate | 4.46e-05 | +| loss | -0.0292 | +| n_updates | 59828 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000195 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1419 | +| iterations | 11004 | +| time_elapsed | 15873 | +| total_timesteps | 22536192 | +| train/ | | +| approx_kl | 0.013379281 | +| clip_fraction | 0.363 | +| clip_range | 0.0694 | +| entropy_loss | -6.27 | +| explained_variance | 0.417 | +| learning_rate | 4.46e-05 | +| loss | -0.0328 | +| n_updates | 59832 | +| policy_gradient_loss | -0.0206 | +| value_loss | 8.51e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1419 | +| iterations | 11005 | +| time_elapsed | 15874 | +| total_timesteps | 22538240 | +| train/ | | +| approx_kl | 0.012165671 | +| clip_fraction | 0.365 | +| clip_range | 0.0694 | +| entropy_loss | -6.71 | +| explained_variance | 0.267 | +| learning_rate | 4.46e-05 | +| loss | -0.0323 | +| n_updates | 59836 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000149 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.315 | +| time/ | | +| fps | 1419 | +| iterations | 11006 | +| time_elapsed | 15876 | +| total_timesteps | 22540288 | +| train/ | | +| approx_kl | 0.01118339 | +| clip_fraction | 0.314 | +| clip_range | 0.0694 | +| entropy_loss | -6.55 | +| explained_variance | 0.585 | +| learning_rate | 4.46e-05 | +| loss | -0.0254 | +| n_updates | 59840 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000182 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1419 | +| iterations | 11007 | +| time_elapsed | 15877 | +| total_timesteps | 22542336 | +| train/ | | +| approx_kl | 0.013075734 | +| clip_fraction | 0.336 | +| clip_range | 0.0694 | +| entropy_loss | -5.79 | +| explained_variance | 0.689 | +| learning_rate | 4.46e-05 | +| loss | -0.0312 | +| n_updates | 59844 | +| policy_gradient_loss | -0.0192 | +| value_loss | 8.85e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.315 | +| time/ | | +| fps | 1419 | +| iterations | 11008 | +| time_elapsed | 15879 | +| total_timesteps | 22544384 | +| train/ | | +| approx_kl | 0.011390261 | +| clip_fraction | 0.329 | +| clip_range | 0.0694 | +| entropy_loss | -6.15 | +| explained_variance | 0.507 | +| learning_rate | 4.46e-05 | +| loss | -0.0323 | +| n_updates | 59848 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000116 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1419 | +| iterations | 11009 | +| time_elapsed | 15880 | +| total_timesteps | 22546432 | +| train/ | | +| approx_kl | 0.012694413 | +| clip_fraction | 0.355 | +| clip_range | 0.0694 | +| entropy_loss | -6.54 | +| explained_variance | 0.337 | +| learning_rate | 4.46e-05 | +| loss | -0.0282 | +| n_updates | 59852 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000211 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1419 | +| iterations | 11010 | +| time_elapsed | 15882 | +| total_timesteps | 22548480 | +| train/ | | +| approx_kl | 0.014512183 | +| clip_fraction | 0.38 | +| clip_range | 0.0694 | +| entropy_loss | -6.37 | +| explained_variance | 0.53 | +| learning_rate | 4.46e-05 | +| loss | -0.0359 | +| n_updates | 59856 | +| policy_gradient_loss | -0.0216 | +| value_loss | 8.49e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1419 | +| iterations | 11011 | +| time_elapsed | 15883 | +| total_timesteps | 22550528 | +| train/ | | +| approx_kl | 0.01034018 | +| clip_fraction | 0.31 | +| clip_range | 0.0694 | +| entropy_loss | -6.81 | +| explained_variance | 0.246 | +| learning_rate | 4.46e-05 | +| loss | -0.0216 | +| n_updates | 59860 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000171 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1419 | +| iterations | 11012 | +| time_elapsed | 15885 | +| total_timesteps | 22552576 | +| train/ | | +| approx_kl | 0.011069901 | +| clip_fraction | 0.324 | +| clip_range | 0.0694 | +| entropy_loss | -6.81 | +| explained_variance | 0.413 | +| learning_rate | 4.46e-05 | +| loss | -0.0282 | +| n_updates | 59864 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000104 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.315 | +| time/ | | +| fps | 1419 | +| iterations | 11013 | +| time_elapsed | 15886 | +| total_timesteps | 22554624 | +| train/ | | +| approx_kl | 0.0126186535 | +| clip_fraction | 0.338 | +| clip_range | 0.0694 | +| entropy_loss | -5.83 | +| explained_variance | 0.772 | +| learning_rate | 4.46e-05 | +| loss | -0.0327 | +| n_updates | 59868 | +| policy_gradient_loss | -0.0179 | +| value_loss | 9.33e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.315 | +| time/ | | +| fps | 1419 | +| iterations | 11014 | +| time_elapsed | 15888 | +| total_timesteps | 22556672 | +| train/ | | +| approx_kl | 0.011054099 | +| clip_fraction | 0.318 | +| clip_range | 0.0694 | +| entropy_loss | -6 | +| explained_variance | 0.703 | +| learning_rate | 4.46e-05 | +| loss | -0.0274 | +| n_updates | 59872 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000109 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1419 | +| iterations | 11015 | +| time_elapsed | 15889 | +| total_timesteps | 22558720 | +| train/ | | +| approx_kl | 0.015059372 | +| clip_fraction | 0.383 | +| clip_range | 0.0694 | +| entropy_loss | -6.56 | +| explained_variance | -0.0914 | +| learning_rate | 4.46e-05 | +| loss | -0.0327 | +| n_updates | 59876 | +| policy_gradient_loss | -0.0234 | +| value_loss | 5.3e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.315 | +| time/ | | +| fps | 1419 | +| iterations | 11016 | +| time_elapsed | 15891 | +| total_timesteps | 22560768 | +| train/ | | +| approx_kl | 0.0112455785 | +| clip_fraction | 0.315 | +| clip_range | 0.0694 | +| entropy_loss | -6.55 | +| explained_variance | 0.371 | +| learning_rate | 4.46e-05 | +| loss | -0.0257 | +| n_updates | 59880 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000222 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1419 | +| iterations | 11017 | +| time_elapsed | 15892 | +| total_timesteps | 22562816 | +| train/ | | +| approx_kl | 0.013693949 | +| clip_fraction | 0.379 | +| clip_range | 0.0694 | +| entropy_loss | -6.46 | +| explained_variance | 0.682 | +| learning_rate | 4.46e-05 | +| loss | -0.0436 | +| n_updates | 59884 | +| policy_gradient_loss | -0.0271 | +| value_loss | 3.57e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1419 | +| iterations | 11018 | +| time_elapsed | 15893 | +| total_timesteps | 22564864 | +| train/ | | +| approx_kl | 0.012638141 | +| clip_fraction | 0.309 | +| clip_range | 0.0694 | +| entropy_loss | -6.11 | +| explained_variance | 0.637 | +| learning_rate | 4.46e-05 | +| loss | -0.0269 | +| n_updates | 59888 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.00014 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.315 | +| time/ | | +| fps | 1419 | +| iterations | 11019 | +| time_elapsed | 15895 | +| total_timesteps | 22566912 | +| train/ | | +| approx_kl | 0.013230785 | +| clip_fraction | 0.321 | +| clip_range | 0.0694 | +| entropy_loss | -6.11 | +| explained_variance | 0.448 | +| learning_rate | 4.46e-05 | +| loss | -0.0286 | +| n_updates | 59892 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000171 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1419 | +| iterations | 11020 | +| time_elapsed | 15896 | +| total_timesteps | 22568960 | +| train/ | | +| approx_kl | 0.013134101 | +| clip_fraction | 0.351 | +| clip_range | 0.0694 | +| entropy_loss | -5.96 | +| explained_variance | 0.447 | +| learning_rate | 4.46e-05 | +| loss | -0.0203 | +| n_updates | 59896 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000213 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1419 | +| iterations | 11021 | +| time_elapsed | 15898 | +| total_timesteps | 22571008 | +| train/ | | +| approx_kl | 0.015067192 | +| clip_fraction | 0.369 | +| clip_range | 0.0694 | +| entropy_loss | -6.38 | +| explained_variance | 0.0979 | +| learning_rate | 4.46e-05 | +| loss | -0.0294 | +| n_updates | 59900 | +| policy_gradient_loss | -0.022 | +| value_loss | 8.68e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1419 | +| iterations | 11022 | +| time_elapsed | 15899 | +| total_timesteps | 22573056 | +| train/ | | +| approx_kl | 0.014726182 | +| clip_fraction | 0.343 | +| clip_range | 0.0694 | +| entropy_loss | -6.58 | +| explained_variance | 0.271 | +| learning_rate | 4.46e-05 | +| loss | -0.0263 | +| n_updates | 59904 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.00019 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1419 | +| iterations | 11023 | +| time_elapsed | 15901 | +| total_timesteps | 22575104 | +| train/ | | +| approx_kl | 0.010306498 | +| clip_fraction | 0.328 | +| clip_range | 0.0694 | +| entropy_loss | -6.68 | +| explained_variance | 0.313 | +| learning_rate | 4.46e-05 | +| loss | -0.0313 | +| n_updates | 59908 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000293 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1419 | +| iterations | 11024 | +| time_elapsed | 15902 | +| total_timesteps | 22577152 | +| train/ | | +| approx_kl | 0.010532234 | +| clip_fraction | 0.328 | +| clip_range | 0.0694 | +| entropy_loss | -6.52 | +| explained_variance | 0.227 | +| learning_rate | 4.46e-05 | +| loss | -0.0344 | +| n_updates | 59912 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000407 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1419 | +| iterations | 11025 | +| time_elapsed | 15904 | +| total_timesteps | 22579200 | +| train/ | | +| approx_kl | 0.014385689 | +| clip_fraction | 0.386 | +| clip_range | 0.0694 | +| entropy_loss | -6.58 | +| explained_variance | 0.395 | +| learning_rate | 4.46e-05 | +| loss | -0.0354 | +| n_updates | 59916 | +| policy_gradient_loss | -0.0234 | +| value_loss | 0.0001 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1419 | +| iterations | 11026 | +| time_elapsed | 15905 | +| total_timesteps | 22581248 | +| train/ | | +| approx_kl | 0.014548112 | +| clip_fraction | 0.349 | +| clip_range | 0.0694 | +| entropy_loss | -6.1 | +| explained_variance | 0.712 | +| learning_rate | 4.46e-05 | +| loss | -0.0321 | +| n_updates | 59920 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.00012 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1419 | +| iterations | 11027 | +| time_elapsed | 15907 | +| total_timesteps | 22583296 | +| train/ | | +| approx_kl | 0.010321526 | +| clip_fraction | 0.298 | +| clip_range | 0.0694 | +| entropy_loss | -5.58 | +| explained_variance | 0.465 | +| learning_rate | 4.46e-05 | +| loss | -0.0232 | +| n_updates | 59924 | +| policy_gradient_loss | -0.0138 | +| value_loss | 0.0004 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1419 | +| iterations | 11028 | +| time_elapsed | 15908 | +| total_timesteps | 22585344 | +| train/ | | +| approx_kl | 0.013152572 | +| clip_fraction | 0.366 | +| clip_range | 0.0694 | +| entropy_loss | -5.86 | +| explained_variance | 0.634 | +| learning_rate | 4.46e-05 | +| loss | -0.0319 | +| n_updates | 59928 | +| policy_gradient_loss | -0.0235 | +| value_loss | 7.92e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1419 | +| iterations | 11029 | +| time_elapsed | 15910 | +| total_timesteps | 22587392 | +| train/ | | +| approx_kl | 0.012848139 | +| clip_fraction | 0.335 | +| clip_range | 0.0694 | +| entropy_loss | -6.73 | +| explained_variance | 0.277 | +| learning_rate | 4.46e-05 | +| loss | -0.0329 | +| n_updates | 59932 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000191 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1419 | +| iterations | 11030 | +| time_elapsed | 15911 | +| total_timesteps | 22589440 | +| train/ | | +| approx_kl | 0.015558852 | +| clip_fraction | 0.374 | +| clip_range | 0.0694 | +| entropy_loss | -6.41 | +| explained_variance | 0.238 | +| learning_rate | 4.46e-05 | +| loss | -0.0346 | +| n_updates | 59936 | +| policy_gradient_loss | -0.0224 | +| value_loss | 9.5e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1419 | +| iterations | 11031 | +| time_elapsed | 15913 | +| total_timesteps | 22591488 | +| train/ | | +| approx_kl | 0.0141048115 | +| clip_fraction | 0.336 | +| clip_range | 0.0694 | +| entropy_loss | -6.74 | +| explained_variance | -0.0504 | +| learning_rate | 4.46e-05 | +| loss | -0.0302 | +| n_updates | 59940 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000148 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1419 | +| iterations | 11032 | +| time_elapsed | 15914 | +| total_timesteps | 22593536 | +| train/ | | +| approx_kl | 0.01244357 | +| clip_fraction | 0.312 | +| clip_range | 0.0694 | +| entropy_loss | -6.46 | +| explained_variance | 0.393 | +| learning_rate | 4.46e-05 | +| loss | -0.0225 | +| n_updates | 59944 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000313 | +---------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1419 | +| iterations | 11033 | +| time_elapsed | 15916 | +| total_timesteps | 22595584 | +| train/ | | +| approx_kl | 0.0091435 | +| clip_fraction | 0.328 | +| clip_range | 0.0694 | +| entropy_loss | -5.62 | +| explained_variance | 0.578 | +| learning_rate | 4.46e-05 | +| loss | -0.0188 | +| n_updates | 59948 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000277 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1419 | +| iterations | 11034 | +| time_elapsed | 15917 | +| total_timesteps | 22597632 | +| train/ | | +| approx_kl | 0.013144271 | +| clip_fraction | 0.352 | +| clip_range | 0.0694 | +| entropy_loss | -6.13 | +| explained_variance | 0.313 | +| learning_rate | 4.46e-05 | +| loss | -0.0256 | +| n_updates | 59952 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000179 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1419 | +| iterations | 11035 | +| time_elapsed | 15919 | +| total_timesteps | 22599680 | +| train/ | | +| approx_kl | 0.017278474 | +| clip_fraction | 0.358 | +| clip_range | 0.0694 | +| entropy_loss | -6.18 | +| explained_variance | 0.404 | +| learning_rate | 4.46e-05 | +| loss | -0.0335 | +| n_updates | 59956 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000193 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1419 | +| iterations | 11036 | +| time_elapsed | 15920 | +| total_timesteps | 22601728 | +| train/ | | +| approx_kl | 0.011640424 | +| clip_fraction | 0.359 | +| clip_range | 0.0694 | +| entropy_loss | -6.57 | +| explained_variance | 0.342 | +| learning_rate | 4.46e-05 | +| loss | -0.0285 | +| n_updates | 59960 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000167 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1419 | +| iterations | 11037 | +| time_elapsed | 15922 | +| total_timesteps | 22603776 | +| train/ | | +| approx_kl | 0.014463302 | +| clip_fraction | 0.356 | +| clip_range | 0.0693 | +| entropy_loss | -6.22 | +| explained_variance | 0.466 | +| learning_rate | 4.46e-05 | +| loss | -0.0348 | +| n_updates | 59964 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000156 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1419 | +| iterations | 11038 | +| time_elapsed | 15923 | +| total_timesteps | 22605824 | +| train/ | | +| approx_kl | 0.01084929 | +| clip_fraction | 0.314 | +| clip_range | 0.0693 | +| entropy_loss | -6.8 | +| explained_variance | 0.082 | +| learning_rate | 4.46e-05 | +| loss | -0.0308 | +| n_updates | 59968 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000226 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1419 | +| iterations | 11039 | +| time_elapsed | 15925 | +| total_timesteps | 22607872 | +| train/ | | +| approx_kl | 0.0109572485 | +| clip_fraction | 0.281 | +| clip_range | 0.0693 | +| entropy_loss | -6.41 | +| explained_variance | 0.654 | +| learning_rate | 4.46e-05 | +| loss | -0.0203 | +| n_updates | 59972 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000118 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1419 | +| iterations | 11040 | +| time_elapsed | 15926 | +| total_timesteps | 22609920 | +| train/ | | +| approx_kl | 0.012587186 | +| clip_fraction | 0.31 | +| clip_range | 0.0693 | +| entropy_loss | -6.91 | +| explained_variance | 0.113 | +| learning_rate | 4.46e-05 | +| loss | -0.0342 | +| n_updates | 59976 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000349 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1419 | +| iterations | 11041 | +| time_elapsed | 15928 | +| total_timesteps | 22611968 | +| train/ | | +| approx_kl | 0.011364679 | +| clip_fraction | 0.333 | +| clip_range | 0.0693 | +| entropy_loss | -6.37 | +| explained_variance | 0.659 | +| learning_rate | 4.46e-05 | +| loss | -0.0351 | +| n_updates | 59980 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000115 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1419 | +| iterations | 11042 | +| time_elapsed | 15929 | +| total_timesteps | 22614016 | +| train/ | | +| approx_kl | 0.009137416 | +| clip_fraction | 0.301 | +| clip_range | 0.0693 | +| entropy_loss | -6.33 | +| explained_variance | 0.295 | +| learning_rate | 4.46e-05 | +| loss | -0.0283 | +| n_updates | 59984 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000355 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1419 | +| iterations | 11043 | +| time_elapsed | 15931 | +| total_timesteps | 22616064 | +| train/ | | +| approx_kl | 0.013568251 | +| clip_fraction | 0.368 | +| clip_range | 0.0693 | +| entropy_loss | -6.06 | +| explained_variance | 0.713 | +| learning_rate | 4.46e-05 | +| loss | -0.0387 | +| n_updates | 59988 | +| policy_gradient_loss | -0.0232 | +| value_loss | 7.75e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1419 | +| iterations | 11044 | +| time_elapsed | 15932 | +| total_timesteps | 22618112 | +| train/ | | +| approx_kl | 0.012659581 | +| clip_fraction | 0.366 | +| clip_range | 0.0693 | +| entropy_loss | -6.69 | +| explained_variance | 0.327 | +| learning_rate | 4.46e-05 | +| loss | -0.0301 | +| n_updates | 59992 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000125 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1419 | +| iterations | 11045 | +| time_elapsed | 15934 | +| total_timesteps | 22620160 | +| train/ | | +| approx_kl | 0.014798898 | +| clip_fraction | 0.363 | +| clip_range | 0.0693 | +| entropy_loss | -6.54 | +| explained_variance | 0.432 | +| learning_rate | 4.46e-05 | +| loss | -0.0326 | +| n_updates | 59996 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000146 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1419 | +| iterations | 11046 | +| time_elapsed | 15935 | +| total_timesteps | 22622208 | +| train/ | | +| approx_kl | 0.012677681 | +| clip_fraction | 0.326 | +| clip_range | 0.0693 | +| entropy_loss | -6.53 | +| explained_variance | 0.441 | +| learning_rate | 4.46e-05 | +| loss | -0.0334 | +| n_updates | 60000 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000162 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1419 | +| iterations | 11047 | +| time_elapsed | 15937 | +| total_timesteps | 22624256 | +| train/ | | +| approx_kl | 0.013195742 | +| clip_fraction | 0.326 | +| clip_range | 0.0693 | +| entropy_loss | -5.95 | +| explained_variance | 0.524 | +| learning_rate | 4.46e-05 | +| loss | -0.0285 | +| n_updates | 60004 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000191 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1419 | +| iterations | 11048 | +| time_elapsed | 15938 | +| total_timesteps | 22626304 | +| train/ | | +| approx_kl | 0.0123753585 | +| clip_fraction | 0.329 | +| clip_range | 0.0693 | +| entropy_loss | -6.1 | +| explained_variance | 0.445 | +| learning_rate | 4.46e-05 | +| loss | -0.0209 | +| n_updates | 60008 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000248 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1419 | +| iterations | 11049 | +| time_elapsed | 15940 | +| total_timesteps | 22628352 | +| train/ | | +| approx_kl | 0.015544197 | +| clip_fraction | 0.343 | +| clip_range | 0.0693 | +| entropy_loss | -6.07 | +| explained_variance | 0.409 | +| learning_rate | 4.46e-05 | +| loss | -0.0318 | +| n_updates | 60012 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000166 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1419 | +| iterations | 11050 | +| time_elapsed | 15941 | +| total_timesteps | 22630400 | +| train/ | | +| approx_kl | 0.012327574 | +| clip_fraction | 0.329 | +| clip_range | 0.0693 | +| entropy_loss | -6.52 | +| explained_variance | 0.377 | +| learning_rate | 4.46e-05 | +| loss | -0.032 | +| n_updates | 60016 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000259 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1419 | +| iterations | 11051 | +| time_elapsed | 15942 | +| total_timesteps | 22632448 | +| train/ | | +| approx_kl | 0.015453856 | +| clip_fraction | 0.329 | +| clip_range | 0.0693 | +| entropy_loss | -6.51 | +| explained_variance | 0.404 | +| learning_rate | 4.46e-05 | +| loss | -0.0346 | +| n_updates | 60020 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000119 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1419 | +| iterations | 11052 | +| time_elapsed | 15944 | +| total_timesteps | 22634496 | +| train/ | | +| approx_kl | 0.011743442 | +| clip_fraction | 0.35 | +| clip_range | 0.0693 | +| entropy_loss | -6.55 | +| explained_variance | 0.49 | +| learning_rate | 4.46e-05 | +| loss | -0.0389 | +| n_updates | 60024 | +| policy_gradient_loss | -0.0207 | +| value_loss | 9.49e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1419 | +| iterations | 11053 | +| time_elapsed | 15945 | +| total_timesteps | 22636544 | +| train/ | | +| approx_kl | 0.011478014 | +| clip_fraction | 0.333 | +| clip_range | 0.0693 | +| entropy_loss | -6.77 | +| explained_variance | 0.565 | +| learning_rate | 4.46e-05 | +| loss | -0.0278 | +| n_updates | 60028 | +| policy_gradient_loss | -0.0196 | +| value_loss | 9.46e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1419 | +| iterations | 11054 | +| time_elapsed | 15947 | +| total_timesteps | 22638592 | +| train/ | | +| approx_kl | 0.00979109 | +| clip_fraction | 0.318 | +| clip_range | 0.0693 | +| entropy_loss | -6.38 | +| explained_variance | 0.491 | +| learning_rate | 4.46e-05 | +| loss | -0.0218 | +| n_updates | 60032 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000179 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1419 | +| iterations | 11055 | +| time_elapsed | 15948 | +| total_timesteps | 22640640 | +| train/ | | +| approx_kl | 0.009315407 | +| clip_fraction | 0.275 | +| clip_range | 0.0693 | +| entropy_loss | -6.44 | +| explained_variance | 0.316 | +| learning_rate | 4.46e-05 | +| loss | -0.0292 | +| n_updates | 60036 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000231 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1419 | +| iterations | 11056 | +| time_elapsed | 15950 | +| total_timesteps | 22642688 | +| train/ | | +| approx_kl | 0.009379737 | +| clip_fraction | 0.316 | +| clip_range | 0.0693 | +| entropy_loss | -5.84 | +| explained_variance | 0.623 | +| learning_rate | 4.46e-05 | +| loss | -0.0309 | +| n_updates | 60040 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000184 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1419 | +| iterations | 11057 | +| time_elapsed | 15951 | +| total_timesteps | 22644736 | +| train/ | | +| approx_kl | 0.011224494 | +| clip_fraction | 0.339 | +| clip_range | 0.0693 | +| entropy_loss | -6.33 | +| explained_variance | 0.64 | +| learning_rate | 4.46e-05 | +| loss | -0.0384 | +| n_updates | 60044 | +| policy_gradient_loss | -0.0206 | +| value_loss | 9.63e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1419 | +| iterations | 11058 | +| time_elapsed | 15953 | +| total_timesteps | 22646784 | +| train/ | | +| approx_kl | 0.009156097 | +| clip_fraction | 0.307 | +| clip_range | 0.0693 | +| entropy_loss | -6.39 | +| explained_variance | 0.581 | +| learning_rate | 4.46e-05 | +| loss | -0.0298 | +| n_updates | 60048 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000162 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1419 | +| iterations | 11059 | +| time_elapsed | 15954 | +| total_timesteps | 22648832 | +| train/ | | +| approx_kl | 0.010523477 | +| clip_fraction | 0.318 | +| clip_range | 0.0693 | +| entropy_loss | -6.78 | +| explained_variance | 0.315 | +| learning_rate | 4.46e-05 | +| loss | -0.0237 | +| n_updates | 60052 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000165 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1419 | +| iterations | 11060 | +| time_elapsed | 15955 | +| total_timesteps | 22650880 | +| train/ | | +| approx_kl | 0.012761589 | +| clip_fraction | 0.346 | +| clip_range | 0.0693 | +| entropy_loss | -6.74 | +| explained_variance | 0.227 | +| learning_rate | 4.46e-05 | +| loss | -0.0327 | +| n_updates | 60056 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000199 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1419 | +| iterations | 11061 | +| time_elapsed | 15957 | +| total_timesteps | 22652928 | +| train/ | | +| approx_kl | 0.012739468 | +| clip_fraction | 0.36 | +| clip_range | 0.0693 | +| entropy_loss | -6.75 | +| explained_variance | 0.319 | +| learning_rate | 4.46e-05 | +| loss | -0.0288 | +| n_updates | 60060 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000125 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1419 | +| iterations | 11062 | +| time_elapsed | 15958 | +| total_timesteps | 22654976 | +| train/ | | +| approx_kl | 0.013785887 | +| clip_fraction | 0.338 | +| clip_range | 0.0693 | +| entropy_loss | -6.59 | +| explained_variance | 0.327 | +| learning_rate | 4.46e-05 | +| loss | -0.0346 | +| n_updates | 60064 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000113 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1419 | +| iterations | 11063 | +| time_elapsed | 15960 | +| total_timesteps | 22657024 | +| train/ | | +| approx_kl | 0.011796244 | +| clip_fraction | 0.289 | +| clip_range | 0.0693 | +| entropy_loss | -5.99 | +| explained_variance | 0.577 | +| learning_rate | 4.46e-05 | +| loss | -0.0191 | +| n_updates | 60068 | +| policy_gradient_loss | -0.0137 | +| value_loss | 0.000224 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1419 | +| iterations | 11064 | +| time_elapsed | 15961 | +| total_timesteps | 22659072 | +| train/ | | +| approx_kl | 0.012276186 | +| clip_fraction | 0.338 | +| clip_range | 0.0693 | +| entropy_loss | -6.38 | +| explained_variance | 0.179 | +| learning_rate | 4.46e-05 | +| loss | -0.03 | +| n_updates | 60072 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000152 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1419 | +| iterations | 11065 | +| time_elapsed | 15963 | +| total_timesteps | 22661120 | +| train/ | | +| approx_kl | 0.012742283 | +| clip_fraction | 0.338 | +| clip_range | 0.0693 | +| entropy_loss | -6.35 | +| explained_variance | 0.619 | +| learning_rate | 4.46e-05 | +| loss | -0.0274 | +| n_updates | 60076 | +| policy_gradient_loss | -0.0192 | +| value_loss | 9.63e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1419 | +| iterations | 11066 | +| time_elapsed | 15964 | +| total_timesteps | 22663168 | +| train/ | | +| approx_kl | 0.0122608915 | +| clip_fraction | 0.356 | +| clip_range | 0.0693 | +| entropy_loss | -6.64 | +| explained_variance | 0.00793 | +| learning_rate | 4.46e-05 | +| loss | -0.0255 | +| n_updates | 60080 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000218 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1419 | +| iterations | 11067 | +| time_elapsed | 15966 | +| total_timesteps | 22665216 | +| train/ | | +| approx_kl | 0.013287748 | +| clip_fraction | 0.336 | +| clip_range | 0.0693 | +| entropy_loss | -6.08 | +| explained_variance | 0.629 | +| learning_rate | 4.46e-05 | +| loss | -0.0304 | +| n_updates | 60084 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000111 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1419 | +| iterations | 11068 | +| time_elapsed | 15967 | +| total_timesteps | 22667264 | +| train/ | | +| approx_kl | 0.013757427 | +| clip_fraction | 0.329 | +| clip_range | 0.0693 | +| entropy_loss | -6.49 | +| explained_variance | 0.28 | +| learning_rate | 4.46e-05 | +| loss | -0.0316 | +| n_updates | 60088 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000183 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1419 | +| iterations | 11069 | +| time_elapsed | 15969 | +| total_timesteps | 22669312 | +| train/ | | +| approx_kl | 0.011594888 | +| clip_fraction | 0.35 | +| clip_range | 0.0693 | +| entropy_loss | -6.44 | +| explained_variance | 0.56 | +| learning_rate | 4.46e-05 | +| loss | -0.0353 | +| n_updates | 60092 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000109 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1419 | +| iterations | 11070 | +| time_elapsed | 15970 | +| total_timesteps | 22671360 | +| train/ | | +| approx_kl | 0.01663105 | +| clip_fraction | 0.346 | +| clip_range | 0.0693 | +| entropy_loss | -6.66 | +| explained_variance | 0.36 | +| learning_rate | 4.46e-05 | +| loss | -0.0254 | +| n_updates | 60096 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000147 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1419 | +| iterations | 11071 | +| time_elapsed | 15972 | +| total_timesteps | 22673408 | +| train/ | | +| approx_kl | 0.01288965 | +| clip_fraction | 0.364 | +| clip_range | 0.0693 | +| entropy_loss | -6.85 | +| explained_variance | 0.12 | +| learning_rate | 4.46e-05 | +| loss | -0.0366 | +| n_updates | 60100 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000102 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1419 | +| iterations | 11072 | +| time_elapsed | 15973 | +| total_timesteps | 22675456 | +| train/ | | +| approx_kl | 0.012324989 | +| clip_fraction | 0.346 | +| clip_range | 0.0693 | +| entropy_loss | -6.65 | +| explained_variance | 0.46 | +| learning_rate | 4.46e-05 | +| loss | -0.0316 | +| n_updates | 60104 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000114 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1419 | +| iterations | 11073 | +| time_elapsed | 15974 | +| total_timesteps | 22677504 | +| train/ | | +| approx_kl | 0.010549141 | +| clip_fraction | 0.329 | +| clip_range | 0.0693 | +| entropy_loss | -6.67 | +| explained_variance | 0.492 | +| learning_rate | 4.46e-05 | +| loss | -0.0308 | +| n_updates | 60108 | +| policy_gradient_loss | -0.0188 | +| value_loss | 8.66e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1419 | +| iterations | 11074 | +| time_elapsed | 15976 | +| total_timesteps | 22679552 | +| train/ | | +| approx_kl | 0.012444092 | +| clip_fraction | 0.305 | +| clip_range | 0.0693 | +| entropy_loss | -5.87 | +| explained_variance | 0.672 | +| learning_rate | 4.46e-05 | +| loss | -0.024 | +| n_updates | 60112 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000149 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1419 | +| iterations | 11075 | +| time_elapsed | 15977 | +| total_timesteps | 22681600 | +| train/ | | +| approx_kl | 0.013055652 | +| clip_fraction | 0.307 | +| clip_range | 0.0693 | +| entropy_loss | -6 | +| explained_variance | 0.623 | +| learning_rate | 4.46e-05 | +| loss | -0.0294 | +| n_updates | 60116 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000129 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1419 | +| iterations | 11076 | +| time_elapsed | 15979 | +| total_timesteps | 22683648 | +| train/ | | +| approx_kl | 0.0132699 | +| clip_fraction | 0.358 | +| clip_range | 0.0693 | +| entropy_loss | -6.86 | +| explained_variance | -0.0309 | +| learning_rate | 4.46e-05 | +| loss | -0.0301 | +| n_updates | 60120 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000129 | +--------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1419 | +| iterations | 11077 | +| time_elapsed | 15980 | +| total_timesteps | 22685696 | +| train/ | | +| approx_kl | 0.0136134345 | +| clip_fraction | 0.335 | +| clip_range | 0.0693 | +| entropy_loss | -6.81 | +| explained_variance | 0.197 | +| learning_rate | 4.46e-05 | +| loss | -0.0239 | +| n_updates | 60124 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000286 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1419 | +| iterations | 11078 | +| time_elapsed | 15982 | +| total_timesteps | 22687744 | +| train/ | | +| approx_kl | 0.012619379 | +| clip_fraction | 0.31 | +| clip_range | 0.0693 | +| entropy_loss | -6.25 | +| explained_variance | 0.562 | +| learning_rate | 4.46e-05 | +| loss | -0.0306 | +| n_updates | 60128 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000152 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1419 | +| iterations | 11079 | +| time_elapsed | 15983 | +| total_timesteps | 22689792 | +| train/ | | +| approx_kl | 0.014254561 | +| clip_fraction | 0.344 | +| clip_range | 0.0693 | +| entropy_loss | -5.9 | +| explained_variance | 0.72 | +| learning_rate | 4.46e-05 | +| loss | -0.0339 | +| n_updates | 60132 | +| policy_gradient_loss | -0.0195 | +| value_loss | 8.25e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1419 | +| iterations | 11080 | +| time_elapsed | 15985 | +| total_timesteps | 22691840 | +| train/ | | +| approx_kl | 0.012305388 | +| clip_fraction | 0.326 | +| clip_range | 0.0693 | +| entropy_loss | -6.02 | +| explained_variance | 0.493 | +| learning_rate | 4.46e-05 | +| loss | -0.0277 | +| n_updates | 60136 | +| policy_gradient_loss | -0.0174 | +| value_loss | 9.31e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1419 | +| iterations | 11081 | +| time_elapsed | 15986 | +| total_timesteps | 22693888 | +| train/ | | +| approx_kl | 0.012105411 | +| clip_fraction | 0.31 | +| clip_range | 0.0693 | +| entropy_loss | -5.93 | +| explained_variance | 0.559 | +| learning_rate | 4.46e-05 | +| loss | -0.0244 | +| n_updates | 60140 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000263 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1419 | +| iterations | 11082 | +| time_elapsed | 15988 | +| total_timesteps | 22695936 | +| train/ | | +| approx_kl | 0.013532369 | +| clip_fraction | 0.347 | +| clip_range | 0.0693 | +| entropy_loss | -6.49 | +| explained_variance | 0.374 | +| learning_rate | 4.46e-05 | +| loss | -0.0376 | +| n_updates | 60144 | +| policy_gradient_loss | -0.021 | +| value_loss | 9.79e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1419 | +| iterations | 11083 | +| time_elapsed | 15989 | +| total_timesteps | 22697984 | +| train/ | | +| approx_kl | 0.0132053215 | +| clip_fraction | 0.326 | +| clip_range | 0.0693 | +| entropy_loss | -7.04 | +| explained_variance | 0.21 | +| learning_rate | 4.46e-05 | +| loss | -0.0298 | +| n_updates | 60148 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000146 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1419 | +| iterations | 11084 | +| time_elapsed | 15991 | +| total_timesteps | 22700032 | +| train/ | | +| approx_kl | 0.012325521 | +| clip_fraction | 0.319 | +| clip_range | 0.0693 | +| entropy_loss | -6.9 | +| explained_variance | 0.388 | +| learning_rate | 4.46e-05 | +| loss | -0.0215 | +| n_updates | 60152 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000186 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1419 | +| iterations | 11085 | +| time_elapsed | 15992 | +| total_timesteps | 22702080 | +| train/ | | +| approx_kl | 0.014288116 | +| clip_fraction | 0.36 | +| clip_range | 0.0693 | +| entropy_loss | -6.45 | +| explained_variance | 0.457 | +| learning_rate | 4.46e-05 | +| loss | -0.0337 | +| n_updates | 60156 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000104 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1419 | +| iterations | 11086 | +| time_elapsed | 15993 | +| total_timesteps | 22704128 | +| train/ | | +| approx_kl | 0.011730574 | +| clip_fraction | 0.328 | +| clip_range | 0.0693 | +| entropy_loss | -6.78 | +| explained_variance | 0.0485 | +| learning_rate | 4.46e-05 | +| loss | -0.035 | +| n_updates | 60160 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000121 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1419 | +| iterations | 11087 | +| time_elapsed | 15995 | +| total_timesteps | 22706176 | +| train/ | | +| approx_kl | 0.0129411975 | +| clip_fraction | 0.325 | +| clip_range | 0.0693 | +| entropy_loss | -6.56 | +| explained_variance | 0.642 | +| learning_rate | 4.46e-05 | +| loss | -0.0355 | +| n_updates | 60164 | +| policy_gradient_loss | -0.0191 | +| value_loss | 6.56e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1419 | +| iterations | 11088 | +| time_elapsed | 15996 | +| total_timesteps | 22708224 | +| train/ | | +| approx_kl | 0.012351784 | +| clip_fraction | 0.317 | +| clip_range | 0.0693 | +| entropy_loss | -5.63 | +| explained_variance | 0.465 | +| learning_rate | 4.46e-05 | +| loss | -0.0219 | +| n_updates | 60168 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000375 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1419 | +| iterations | 11089 | +| time_elapsed | 15998 | +| total_timesteps | 22710272 | +| train/ | | +| approx_kl | 0.013786893 | +| clip_fraction | 0.369 | +| clip_range | 0.0693 | +| entropy_loss | -6.56 | +| explained_variance | 0.48 | +| learning_rate | 4.46e-05 | +| loss | -0.0389 | +| n_updates | 60172 | +| policy_gradient_loss | -0.023 | +| value_loss | 9.23e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1419 | +| iterations | 11090 | +| time_elapsed | 15999 | +| total_timesteps | 22712320 | +| train/ | | +| approx_kl | 0.012804622 | +| clip_fraction | 0.37 | +| clip_range | 0.0693 | +| entropy_loss | -6.74 | +| explained_variance | -0.0368 | +| learning_rate | 4.46e-05 | +| loss | -0.0312 | +| n_updates | 60176 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000124 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1419 | +| iterations | 11091 | +| time_elapsed | 16001 | +| total_timesteps | 22714368 | +| train/ | | +| approx_kl | 0.014596289 | +| clip_fraction | 0.37 | +| clip_range | 0.0693 | +| entropy_loss | -6.57 | +| explained_variance | 0.538 | +| learning_rate | 4.46e-05 | +| loss | -0.0355 | +| n_updates | 60180 | +| policy_gradient_loss | -0.0208 | +| value_loss | 7.02e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1419 | +| iterations | 11092 | +| time_elapsed | 16002 | +| total_timesteps | 22716416 | +| train/ | | +| approx_kl | 0.014891788 | +| clip_fraction | 0.352 | +| clip_range | 0.0693 | +| entropy_loss | -6.09 | +| explained_variance | 0.555 | +| learning_rate | 4.46e-05 | +| loss | -0.0275 | +| n_updates | 60184 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000152 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1419 | +| iterations | 11093 | +| time_elapsed | 16004 | +| total_timesteps | 22718464 | +| train/ | | +| approx_kl | 0.01401766 | +| clip_fraction | 0.358 | +| clip_range | 0.0693 | +| entropy_loss | -5.6 | +| explained_variance | 0.801 | +| learning_rate | 4.46e-05 | +| loss | -0.0244 | +| n_updates | 60188 | +| policy_gradient_loss | -0.0201 | +| value_loss | 7.21e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1419 | +| iterations | 11094 | +| time_elapsed | 16005 | +| total_timesteps | 22720512 | +| train/ | | +| approx_kl | 0.012885438 | +| clip_fraction | 0.317 | +| clip_range | 0.0693 | +| entropy_loss | -6.63 | +| explained_variance | 0.15 | +| learning_rate | 4.46e-05 | +| loss | -0.0315 | +| n_updates | 60192 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000159 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1419 | +| iterations | 11095 | +| time_elapsed | 16007 | +| total_timesteps | 22722560 | +| train/ | | +| approx_kl | 0.011377271 | +| clip_fraction | 0.301 | +| clip_range | 0.0693 | +| entropy_loss | -6.8 | +| explained_variance | 0.261 | +| learning_rate | 4.46e-05 | +| loss | -0.0304 | +| n_updates | 60196 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000253 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1419 | +| iterations | 11096 | +| time_elapsed | 16008 | +| total_timesteps | 22724608 | +| train/ | | +| approx_kl | 0.012899682 | +| clip_fraction | 0.361 | +| clip_range | 0.0693 | +| entropy_loss | -6.2 | +| explained_variance | 0.646 | +| learning_rate | 4.46e-05 | +| loss | -0.0369 | +| n_updates | 60200 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000116 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1419 | +| iterations | 11097 | +| time_elapsed | 16009 | +| total_timesteps | 22726656 | +| train/ | | +| approx_kl | 0.012764245 | +| clip_fraction | 0.341 | +| clip_range | 0.0693 | +| entropy_loss | -6.32 | +| explained_variance | 0.394 | +| learning_rate | 4.46e-05 | +| loss | -0.0316 | +| n_updates | 60204 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000218 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1419 | +| iterations | 11098 | +| time_elapsed | 16011 | +| total_timesteps | 22728704 | +| train/ | | +| approx_kl | 0.013126109 | +| clip_fraction | 0.326 | +| clip_range | 0.0693 | +| entropy_loss | -6.43 | +| explained_variance | 0.276 | +| learning_rate | 4.46e-05 | +| loss | -0.0294 | +| n_updates | 60208 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000121 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1419 | +| iterations | 11099 | +| time_elapsed | 16012 | +| total_timesteps | 22730752 | +| train/ | | +| approx_kl | 0.015796017 | +| clip_fraction | 0.348 | +| clip_range | 0.0693 | +| entropy_loss | -6.2 | +| explained_variance | 0.693 | +| learning_rate | 4.46e-05 | +| loss | -0.0318 | +| n_updates | 60212 | +| policy_gradient_loss | -0.0196 | +| value_loss | 8.96e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1419 | +| iterations | 11100 | +| time_elapsed | 16014 | +| total_timesteps | 22732800 | +| train/ | | +| approx_kl | 0.012199822 | +| clip_fraction | 0.332 | +| clip_range | 0.0693 | +| entropy_loss | -6 | +| explained_variance | 0.297 | +| learning_rate | 4.46e-05 | +| loss | -0.0265 | +| n_updates | 60216 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000401 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1419 | +| iterations | 11101 | +| time_elapsed | 16015 | +| total_timesteps | 22734848 | +| train/ | | +| approx_kl | 0.01541917 | +| clip_fraction | 0.358 | +| clip_range | 0.0693 | +| entropy_loss | -5.88 | +| explained_variance | 0.5 | +| learning_rate | 4.46e-05 | +| loss | -0.0304 | +| n_updates | 60220 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000127 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1419 | +| iterations | 11102 | +| time_elapsed | 16017 | +| total_timesteps | 22736896 | +| train/ | | +| approx_kl | 0.012474324 | +| clip_fraction | 0.363 | +| clip_range | 0.0693 | +| entropy_loss | -6.48 | +| explained_variance | 0.355 | +| learning_rate | 4.46e-05 | +| loss | -0.0295 | +| n_updates | 60224 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000151 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1419 | +| iterations | 11103 | +| time_elapsed | 16018 | +| total_timesteps | 22738944 | +| train/ | | +| approx_kl | 0.0144609185 | +| clip_fraction | 0.351 | +| clip_range | 0.0693 | +| entropy_loss | -6.6 | +| explained_variance | 0.316 | +| learning_rate | 4.46e-05 | +| loss | -0.0287 | +| n_updates | 60228 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000158 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1419 | +| iterations | 11104 | +| time_elapsed | 16020 | +| total_timesteps | 22740992 | +| train/ | | +| approx_kl | 0.013493143 | +| clip_fraction | 0.361 | +| clip_range | 0.0693 | +| entropy_loss | -6.52 | +| explained_variance | 0.373 | +| learning_rate | 4.46e-05 | +| loss | -0.0251 | +| n_updates | 60232 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000169 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1419 | +| iterations | 11105 | +| time_elapsed | 16021 | +| total_timesteps | 22743040 | +| train/ | | +| approx_kl | 0.014056977 | +| clip_fraction | 0.354 | +| clip_range | 0.0693 | +| entropy_loss | -6.48 | +| explained_variance | 0.613 | +| learning_rate | 4.46e-05 | +| loss | -0.0331 | +| n_updates | 60236 | +| policy_gradient_loss | -0.02 | +| value_loss | 8.84e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1419 | +| iterations | 11106 | +| time_elapsed | 16023 | +| total_timesteps | 22745088 | +| train/ | | +| approx_kl | 0.012283119 | +| clip_fraction | 0.348 | +| clip_range | 0.0693 | +| entropy_loss | -6.63 | +| explained_variance | 0.55 | +| learning_rate | 4.46e-05 | +| loss | -0.0282 | +| n_updates | 60240 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000126 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1419 | +| iterations | 11107 | +| time_elapsed | 16024 | +| total_timesteps | 22747136 | +| train/ | | +| approx_kl | 0.012277414 | +| clip_fraction | 0.321 | +| clip_range | 0.0693 | +| entropy_loss | -6.28 | +| explained_variance | 0.323 | +| learning_rate | 4.46e-05 | +| loss | -0.0279 | +| n_updates | 60244 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000414 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1419 | +| iterations | 11108 | +| time_elapsed | 16026 | +| total_timesteps | 22749184 | +| train/ | | +| approx_kl | 0.014443393 | +| clip_fraction | 0.368 | +| clip_range | 0.0693 | +| entropy_loss | -6.52 | +| explained_variance | 0.418 | +| learning_rate | 4.46e-05 | +| loss | -0.0403 | +| n_updates | 60248 | +| policy_gradient_loss | -0.0244 | +| value_loss | 8.29e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1419 | +| iterations | 11109 | +| time_elapsed | 16027 | +| total_timesteps | 22751232 | +| train/ | | +| approx_kl | 0.014316766 | +| clip_fraction | 0.316 | +| clip_range | 0.0693 | +| entropy_loss | -5.77 | +| explained_variance | 0.568 | +| learning_rate | 4.46e-05 | +| loss | -0.0267 | +| n_updates | 60252 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000232 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1419 | +| iterations | 11110 | +| time_elapsed | 16029 | +| total_timesteps | 22753280 | +| train/ | | +| approx_kl | 0.013516776 | +| clip_fraction | 0.31 | +| clip_range | 0.0693 | +| entropy_loss | -6.47 | +| explained_variance | 0.0366 | +| learning_rate | 4.46e-05 | +| loss | -0.0338 | +| n_updates | 60256 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000144 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1419 | +| iterations | 11111 | +| time_elapsed | 16030 | +| total_timesteps | 22755328 | +| train/ | | +| approx_kl | 0.011845648 | +| clip_fraction | 0.33 | +| clip_range | 0.0693 | +| entropy_loss | -6.51 | +| explained_variance | 0.429 | +| learning_rate | 4.46e-05 | +| loss | -0.035 | +| n_updates | 60260 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.00014 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1419 | +| iterations | 11112 | +| time_elapsed | 16032 | +| total_timesteps | 22757376 | +| train/ | | +| approx_kl | 0.014358612 | +| clip_fraction | 0.331 | +| clip_range | 0.0693 | +| entropy_loss | -6.23 | +| explained_variance | 0.412 | +| learning_rate | 4.46e-05 | +| loss | -0.027 | +| n_updates | 60264 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000193 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1419 | +| iterations | 11113 | +| time_elapsed | 16033 | +| total_timesteps | 22759424 | +| train/ | | +| approx_kl | 0.013197467 | +| clip_fraction | 0.352 | +| clip_range | 0.0693 | +| entropy_loss | -6.9 | +| explained_variance | -0.255 | +| learning_rate | 4.46e-05 | +| loss | -0.0323 | +| n_updates | 60268 | +| policy_gradient_loss | -0.0211 | +| value_loss | 9.82e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1419 | +| iterations | 11114 | +| time_elapsed | 16035 | +| total_timesteps | 22761472 | +| train/ | | +| approx_kl | 0.013638342 | +| clip_fraction | 0.333 | +| clip_range | 0.0693 | +| entropy_loss | -6.83 | +| explained_variance | 0.381 | +| learning_rate | 4.46e-05 | +| loss | -0.0241 | +| n_updates | 60272 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000136 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1419 | +| iterations | 11115 | +| time_elapsed | 16036 | +| total_timesteps | 22763520 | +| train/ | | +| approx_kl | 0.011839008 | +| clip_fraction | 0.306 | +| clip_range | 0.0693 | +| entropy_loss | -6.04 | +| explained_variance | 0.529 | +| learning_rate | 4.46e-05 | +| loss | -0.0248 | +| n_updates | 60276 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000185 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1419 | +| iterations | 11116 | +| time_elapsed | 16038 | +| total_timesteps | 22765568 | +| train/ | | +| approx_kl | 0.012848165 | +| clip_fraction | 0.335 | +| clip_range | 0.0693 | +| entropy_loss | -6.18 | +| explained_variance | 0.722 | +| learning_rate | 4.46e-05 | +| loss | -0.0293 | +| n_updates | 60280 | +| policy_gradient_loss | -0.0204 | +| value_loss | 8.91e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1419 | +| iterations | 11117 | +| time_elapsed | 16039 | +| total_timesteps | 22767616 | +| train/ | | +| approx_kl | 0.014518651 | +| clip_fraction | 0.348 | +| clip_range | 0.0693 | +| entropy_loss | -6.82 | +| explained_variance | 0.139 | +| learning_rate | 4.46e-05 | +| loss | -0.0303 | +| n_updates | 60284 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000124 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1419 | +| iterations | 11118 | +| time_elapsed | 16040 | +| total_timesteps | 22769664 | +| train/ | | +| approx_kl | 0.014162408 | +| clip_fraction | 0.347 | +| clip_range | 0.0693 | +| entropy_loss | -6.39 | +| explained_variance | 0.339 | +| learning_rate | 4.46e-05 | +| loss | -0.0318 | +| n_updates | 60288 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000172 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1419 | +| iterations | 11119 | +| time_elapsed | 16042 | +| total_timesteps | 22771712 | +| train/ | | +| approx_kl | 0.01612532 | +| clip_fraction | 0.358 | +| clip_range | 0.0693 | +| entropy_loss | -5.87 | +| explained_variance | 0.756 | +| learning_rate | 4.46e-05 | +| loss | -0.0343 | +| n_updates | 60292 | +| policy_gradient_loss | -0.022 | +| value_loss | 7.71e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.315 | +| time/ | | +| fps | 1419 | +| iterations | 11120 | +| time_elapsed | 16043 | +| total_timesteps | 22773760 | +| train/ | | +| approx_kl | 0.013754157 | +| clip_fraction | 0.377 | +| clip_range | 0.0693 | +| entropy_loss | -6.29 | +| explained_variance | 0.487 | +| learning_rate | 4.46e-05 | +| loss | -0.0373 | +| n_updates | 60296 | +| policy_gradient_loss | -0.0227 | +| value_loss | 6.9e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1419 | +| iterations | 11121 | +| time_elapsed | 16045 | +| total_timesteps | 22775808 | +| train/ | | +| approx_kl | 0.0151197305 | +| clip_fraction | 0.334 | +| clip_range | 0.0693 | +| entropy_loss | -6.02 | +| explained_variance | 0.717 | +| learning_rate | 4.46e-05 | +| loss | -0.0245 | +| n_updates | 60300 | +| policy_gradient_loss | -0.0174 | +| value_loss | 9.74e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1419 | +| iterations | 11122 | +| time_elapsed | 16046 | +| total_timesteps | 22777856 | +| train/ | | +| approx_kl | 0.012297317 | +| clip_fraction | 0.376 | +| clip_range | 0.0693 | +| entropy_loss | -6.3 | +| explained_variance | 0.34 | +| learning_rate | 4.46e-05 | +| loss | -0.0307 | +| n_updates | 60304 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.0001 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1419 | +| iterations | 11123 | +| time_elapsed | 16048 | +| total_timesteps | 22779904 | +| train/ | | +| approx_kl | 0.011970196 | +| clip_fraction | 0.284 | +| clip_range | 0.0693 | +| entropy_loss | -6.43 | +| explained_variance | 0.22 | +| learning_rate | 4.46e-05 | +| loss | -0.0165 | +| n_updates | 60308 | +| policy_gradient_loss | -0.0119 | +| value_loss | 0.000349 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1419 | +| iterations | 11124 | +| time_elapsed | 16049 | +| total_timesteps | 22781952 | +| train/ | | +| approx_kl | 0.011367651 | +| clip_fraction | 0.357 | +| clip_range | 0.0693 | +| entropy_loss | -6.96 | +| explained_variance | -0.227 | +| learning_rate | 4.46e-05 | +| loss | -0.0295 | +| n_updates | 60312 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000173 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1419 | +| iterations | 11125 | +| time_elapsed | 16051 | +| total_timesteps | 22784000 | +| train/ | | +| approx_kl | 0.008883284 | +| clip_fraction | 0.28 | +| clip_range | 0.0693 | +| entropy_loss | -6.24 | +| explained_variance | 0.534 | +| learning_rate | 4.46e-05 | +| loss | -0.0193 | +| n_updates | 60316 | +| policy_gradient_loss | -0.0124 | +| value_loss | 0.000265 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1419 | +| iterations | 11126 | +| time_elapsed | 16052 | +| total_timesteps | 22786048 | +| train/ | | +| approx_kl | 0.011634957 | +| clip_fraction | 0.341 | +| clip_range | 0.0693 | +| entropy_loss | -6.55 | +| explained_variance | -0.00185 | +| learning_rate | 4.46e-05 | +| loss | -0.0258 | +| n_updates | 60320 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000215 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1419 | +| iterations | 11127 | +| time_elapsed | 16054 | +| total_timesteps | 22788096 | +| train/ | | +| approx_kl | 0.014953646 | +| clip_fraction | 0.329 | +| clip_range | 0.0693 | +| entropy_loss | -6.02 | +| explained_variance | 0.277 | +| learning_rate | 4.46e-05 | +| loss | -0.0262 | +| n_updates | 60324 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.000302 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1419 | +| iterations | 11128 | +| time_elapsed | 16055 | +| total_timesteps | 22790144 | +| train/ | | +| approx_kl | 0.014651788 | +| clip_fraction | 0.336 | +| clip_range | 0.0693 | +| entropy_loss | -6.43 | +| explained_variance | 0.189 | +| learning_rate | 4.46e-05 | +| loss | -0.0305 | +| n_updates | 60328 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000162 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1419 | +| iterations | 11129 | +| time_elapsed | 16056 | +| total_timesteps | 22792192 | +| train/ | | +| approx_kl | 0.014426948 | +| clip_fraction | 0.323 | +| clip_range | 0.0693 | +| entropy_loss | -5.68 | +| explained_variance | 0.349 | +| learning_rate | 4.46e-05 | +| loss | -0.0224 | +| n_updates | 60332 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000425 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1419 | +| iterations | 11130 | +| time_elapsed | 16058 | +| total_timesteps | 22794240 | +| train/ | | +| approx_kl | 0.014069352 | +| clip_fraction | 0.341 | +| clip_range | 0.0693 | +| entropy_loss | -5.5 | +| explained_variance | 0.554 | +| learning_rate | 4.46e-05 | +| loss | -0.0237 | +| n_updates | 60336 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000181 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1419 | +| iterations | 11131 | +| time_elapsed | 16059 | +| total_timesteps | 22796288 | +| train/ | | +| approx_kl | 0.01470151 | +| clip_fraction | 0.347 | +| clip_range | 0.0693 | +| entropy_loss | -6.89 | +| explained_variance | -0.131 | +| learning_rate | 4.46e-05 | +| loss | -0.028 | +| n_updates | 60340 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.00018 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1419 | +| iterations | 11132 | +| time_elapsed | 16061 | +| total_timesteps | 22798336 | +| train/ | | +| approx_kl | 0.011566063 | +| clip_fraction | 0.33 | +| clip_range | 0.0693 | +| entropy_loss | -6.21 | +| explained_variance | 0.369 | +| learning_rate | 4.46e-05 | +| loss | -0.0226 | +| n_updates | 60344 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000286 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1419 | +| iterations | 11133 | +| time_elapsed | 16062 | +| total_timesteps | 22800384 | +| train/ | | +| approx_kl | 0.0165333 | +| clip_fraction | 0.368 | +| clip_range | 0.0693 | +| entropy_loss | -6.3 | +| explained_variance | 0.201 | +| learning_rate | 4.46e-05 | +| loss | -0.0369 | +| n_updates | 60348 | +| policy_gradient_loss | -0.0225 | +| value_loss | 0.000107 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1419 | +| iterations | 11134 | +| time_elapsed | 16064 | +| total_timesteps | 22802432 | +| train/ | | +| approx_kl | 0.013315617 | +| clip_fraction | 0.365 | +| clip_range | 0.0693 | +| entropy_loss | -6.98 | +| explained_variance | 0.151 | +| learning_rate | 4.46e-05 | +| loss | -0.0364 | +| n_updates | 60352 | +| policy_gradient_loss | -0.0221 | +| value_loss | 0.000107 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1419 | +| iterations | 11135 | +| time_elapsed | 16065 | +| total_timesteps | 22804480 | +| train/ | | +| approx_kl | 0.011705944 | +| clip_fraction | 0.324 | +| clip_range | 0.0693 | +| entropy_loss | -6.37 | +| explained_variance | 0.408 | +| learning_rate | 4.46e-05 | +| loss | -0.0294 | +| n_updates | 60356 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000207 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1419 | +| iterations | 11136 | +| time_elapsed | 16067 | +| total_timesteps | 22806528 | +| train/ | | +| approx_kl | 0.012518546 | +| clip_fraction | 0.332 | +| clip_range | 0.0693 | +| entropy_loss | -6.58 | +| explained_variance | 0.191 | +| learning_rate | 4.46e-05 | +| loss | -0.0251 | +| n_updates | 60360 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000216 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1419 | +| iterations | 11137 | +| time_elapsed | 16068 | +| total_timesteps | 22808576 | +| train/ | | +| approx_kl | 0.01452623 | +| clip_fraction | 0.352 | +| clip_range | 0.0693 | +| entropy_loss | -6.55 | +| explained_variance | 0.118 | +| learning_rate | 4.46e-05 | +| loss | -0.0292 | +| n_updates | 60364 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000281 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1419 | +| iterations | 11138 | +| time_elapsed | 16070 | +| total_timesteps | 22810624 | +| train/ | | +| approx_kl | 0.0154390875 | +| clip_fraction | 0.369 | +| clip_range | 0.0693 | +| entropy_loss | -6.44 | +| explained_variance | 0.213 | +| learning_rate | 4.46e-05 | +| loss | -0.0269 | +| n_updates | 60368 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000163 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1419 | +| iterations | 11139 | +| time_elapsed | 16071 | +| total_timesteps | 22812672 | +| train/ | | +| approx_kl | 0.02174112 | +| clip_fraction | 0.364 | +| clip_range | 0.0693 | +| entropy_loss | -6.46 | +| explained_variance | 0.391 | +| learning_rate | 4.46e-05 | +| loss | -0.0348 | +| n_updates | 60372 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000102 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1419 | +| iterations | 11140 | +| time_elapsed | 16073 | +| total_timesteps | 22814720 | +| train/ | | +| approx_kl | 0.01304573 | +| clip_fraction | 0.339 | +| clip_range | 0.0693 | +| entropy_loss | -6.14 | +| explained_variance | 0.606 | +| learning_rate | 4.46e-05 | +| loss | -0.0297 | +| n_updates | 60376 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000124 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1419 | +| iterations | 11141 | +| time_elapsed | 16074 | +| total_timesteps | 22816768 | +| train/ | | +| approx_kl | 0.012435466 | +| clip_fraction | 0.342 | +| clip_range | 0.0693 | +| entropy_loss | -6.27 | +| explained_variance | 0.356 | +| learning_rate | 4.46e-05 | +| loss | -0.0328 | +| n_updates | 60380 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000151 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1419 | +| iterations | 11142 | +| time_elapsed | 16076 | +| total_timesteps | 22818816 | +| train/ | | +| approx_kl | 0.009722645 | +| clip_fraction | 0.307 | +| clip_range | 0.0693 | +| entropy_loss | -6.13 | +| explained_variance | 0.386 | +| learning_rate | 4.46e-05 | +| loss | -0.0235 | +| n_updates | 60384 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000249 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1419 | +| iterations | 11143 | +| time_elapsed | 16077 | +| total_timesteps | 22820864 | +| train/ | | +| approx_kl | 0.015104741 | +| clip_fraction | 0.326 | +| clip_range | 0.0693 | +| entropy_loss | -6.09 | +| explained_variance | 0.434 | +| learning_rate | 4.46e-05 | +| loss | -0.0256 | +| n_updates | 60388 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000163 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1419 | +| iterations | 11144 | +| time_elapsed | 16079 | +| total_timesteps | 22822912 | +| train/ | | +| approx_kl | 0.011240688 | +| clip_fraction | 0.346 | +| clip_range | 0.0693 | +| entropy_loss | -6.35 | +| explained_variance | 0.317 | +| learning_rate | 4.46e-05 | +| loss | -0.0218 | +| n_updates | 60392 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000283 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1419 | +| iterations | 11145 | +| time_elapsed | 16080 | +| total_timesteps | 22824960 | +| train/ | | +| approx_kl | 0.011483785 | +| clip_fraction | 0.348 | +| clip_range | 0.0693 | +| entropy_loss | -6.08 | +| explained_variance | 0.599 | +| learning_rate | 4.46e-05 | +| loss | -0.0344 | +| n_updates | 60396 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000146 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1419 | +| iterations | 11146 | +| time_elapsed | 16082 | +| total_timesteps | 22827008 | +| train/ | | +| approx_kl | 0.011799855 | +| clip_fraction | 0.341 | +| clip_range | 0.0693 | +| entropy_loss | -7.08 | +| explained_variance | -0.0462 | +| learning_rate | 4.46e-05 | +| loss | -0.0316 | +| n_updates | 60400 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000134 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1419 | +| iterations | 11147 | +| time_elapsed | 16083 | +| total_timesteps | 22829056 | +| train/ | | +| approx_kl | 0.011373794 | +| clip_fraction | 0.326 | +| clip_range | 0.0693 | +| entropy_loss | -7.08 | +| explained_variance | -0.0958 | +| learning_rate | 4.46e-05 | +| loss | -0.0353 | +| n_updates | 60404 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000121 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1419 | +| iterations | 11148 | +| time_elapsed | 16085 | +| total_timesteps | 22831104 | +| train/ | | +| approx_kl | 0.011319954 | +| clip_fraction | 0.303 | +| clip_range | 0.0693 | +| entropy_loss | -6.62 | +| explained_variance | 0.467 | +| learning_rate | 4.46e-05 | +| loss | -0.0263 | +| n_updates | 60408 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000168 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1419 | +| iterations | 11149 | +| time_elapsed | 16086 | +| total_timesteps | 22833152 | +| train/ | | +| approx_kl | 0.010512372 | +| clip_fraction | 0.304 | +| clip_range | 0.0693 | +| entropy_loss | -6.64 | +| explained_variance | 0.198 | +| learning_rate | 4.46e-05 | +| loss | -0.0241 | +| n_updates | 60412 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000319 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1419 | +| iterations | 11150 | +| time_elapsed | 16088 | +| total_timesteps | 22835200 | +| train/ | | +| approx_kl | 0.010346154 | +| clip_fraction | 0.312 | +| clip_range | 0.0693 | +| entropy_loss | -5.87 | +| explained_variance | 0.55 | +| learning_rate | 4.46e-05 | +| loss | -0.0229 | +| n_updates | 60416 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000238 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1419 | +| iterations | 11151 | +| time_elapsed | 16089 | +| total_timesteps | 22837248 | +| train/ | | +| approx_kl | 0.013892408 | +| clip_fraction | 0.339 | +| clip_range | 0.0693 | +| entropy_loss | -5.72 | +| explained_variance | 0.561 | +| learning_rate | 4.46e-05 | +| loss | -0.0286 | +| n_updates | 60420 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000125 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1419 | +| iterations | 11152 | +| time_elapsed | 16091 | +| total_timesteps | 22839296 | +| train/ | | +| approx_kl | 0.012606921 | +| clip_fraction | 0.354 | +| clip_range | 0.0693 | +| entropy_loss | -5.69 | +| explained_variance | 0.647 | +| learning_rate | 4.46e-05 | +| loss | -0.023 | +| n_updates | 60424 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000127 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1419 | +| iterations | 11153 | +| time_elapsed | 16092 | +| total_timesteps | 22841344 | +| train/ | | +| approx_kl | 0.0114685055 | +| clip_fraction | 0.346 | +| clip_range | 0.0693 | +| entropy_loss | -6.45 | +| explained_variance | 0.403 | +| learning_rate | 4.46e-05 | +| loss | -0.0304 | +| n_updates | 60428 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000164 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1419 | +| iterations | 11154 | +| time_elapsed | 16094 | +| total_timesteps | 22843392 | +| train/ | | +| approx_kl | 0.012162937 | +| clip_fraction | 0.368 | +| clip_range | 0.0693 | +| entropy_loss | -6.83 | +| explained_variance | -0.0615 | +| learning_rate | 4.46e-05 | +| loss | -0.0331 | +| n_updates | 60432 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000153 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1419 | +| iterations | 11155 | +| time_elapsed | 16095 | +| total_timesteps | 22845440 | +| train/ | | +| approx_kl | 0.01235413 | +| clip_fraction | 0.338 | +| clip_range | 0.0693 | +| entropy_loss | -6.21 | +| explained_variance | 0.634 | +| learning_rate | 4.46e-05 | +| loss | -0.0328 | +| n_updates | 60436 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000103 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1419 | +| iterations | 11156 | +| time_elapsed | 16097 | +| total_timesteps | 22847488 | +| train/ | | +| approx_kl | 0.013489684 | +| clip_fraction | 0.354 | +| clip_range | 0.0693 | +| entropy_loss | -6.6 | +| explained_variance | 0.411 | +| learning_rate | 4.46e-05 | +| loss | -0.0326 | +| n_updates | 60440 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000114 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1419 | +| iterations | 11157 | +| time_elapsed | 16098 | +| total_timesteps | 22849536 | +| train/ | | +| approx_kl | 0.011477539 | +| clip_fraction | 0.339 | +| clip_range | 0.0693 | +| entropy_loss | -6.54 | +| explained_variance | 0.319 | +| learning_rate | 4.46e-05 | +| loss | -0.034 | +| n_updates | 60444 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000144 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1419 | +| iterations | 11158 | +| time_elapsed | 16099 | +| total_timesteps | 22851584 | +| train/ | | +| approx_kl | 0.011909176 | +| clip_fraction | 0.318 | +| clip_range | 0.0693 | +| entropy_loss | -6.28 | +| explained_variance | 0.445 | +| learning_rate | 4.46e-05 | +| loss | -0.022 | +| n_updates | 60448 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000183 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1419 | +| iterations | 11159 | +| time_elapsed | 16101 | +| total_timesteps | 22853632 | +| train/ | | +| approx_kl | 0.014393993 | +| clip_fraction | 0.329 | +| clip_range | 0.0693 | +| entropy_loss | -6.52 | +| explained_variance | 0.378 | +| learning_rate | 4.46e-05 | +| loss | -0.024 | +| n_updates | 60452 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000167 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1419 | +| iterations | 11160 | +| time_elapsed | 16102 | +| total_timesteps | 22855680 | +| train/ | | +| approx_kl | 0.013817612 | +| clip_fraction | 0.34 | +| clip_range | 0.0693 | +| entropy_loss | -6.85 | +| explained_variance | 0.188 | +| learning_rate | 4.46e-05 | +| loss | -0.0305 | +| n_updates | 60456 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000206 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1419 | +| iterations | 11161 | +| time_elapsed | 16104 | +| total_timesteps | 22857728 | +| train/ | | +| approx_kl | 0.015558194 | +| clip_fraction | 0.361 | +| clip_range | 0.0693 | +| entropy_loss | -6.22 | +| explained_variance | 0.798 | +| learning_rate | 4.46e-05 | +| loss | -0.0317 | +| n_updates | 60460 | +| policy_gradient_loss | -0.0214 | +| value_loss | 7.13e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1419 | +| iterations | 11162 | +| time_elapsed | 16106 | +| total_timesteps | 22859776 | +| train/ | | +| approx_kl | 0.013558095 | +| clip_fraction | 0.382 | +| clip_range | 0.0693 | +| entropy_loss | -6.63 | +| explained_variance | -0.407 | +| learning_rate | 4.46e-05 | +| loss | -0.0362 | +| n_updates | 60464 | +| policy_gradient_loss | -0.0243 | +| value_loss | 4.99e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1419 | +| iterations | 11163 | +| time_elapsed | 16107 | +| total_timesteps | 22861824 | +| train/ | | +| approx_kl | 0.013006577 | +| clip_fraction | 0.363 | +| clip_range | 0.0693 | +| entropy_loss | -6.58 | +| explained_variance | 0.486 | +| learning_rate | 4.46e-05 | +| loss | -0.0265 | +| n_updates | 60468 | +| policy_gradient_loss | -0.0188 | +| value_loss | 6.83e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1419 | +| iterations | 11164 | +| time_elapsed | 16108 | +| total_timesteps | 22863872 | +| train/ | | +| approx_kl | 0.01468261 | +| clip_fraction | 0.33 | +| clip_range | 0.0693 | +| entropy_loss | -5.84 | +| explained_variance | 0.605 | +| learning_rate | 4.46e-05 | +| loss | -0.0264 | +| n_updates | 60472 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000229 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1419 | +| iterations | 11165 | +| time_elapsed | 16110 | +| total_timesteps | 22865920 | +| train/ | | +| approx_kl | 0.01303803 | +| clip_fraction | 0.34 | +| clip_range | 0.0693 | +| entropy_loss | -6.24 | +| explained_variance | 0.555 | +| learning_rate | 4.46e-05 | +| loss | -0.0298 | +| n_updates | 60476 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000109 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1419 | +| iterations | 11166 | +| time_elapsed | 16111 | +| total_timesteps | 22867968 | +| train/ | | +| approx_kl | 0.013587819 | +| clip_fraction | 0.357 | +| clip_range | 0.0693 | +| entropy_loss | -6.29 | +| explained_variance | 0.623 | +| learning_rate | 4.46e-05 | +| loss | -0.0338 | +| n_updates | 60480 | +| policy_gradient_loss | -0.0206 | +| value_loss | 7.34e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1419 | +| iterations | 11167 | +| time_elapsed | 16113 | +| total_timesteps | 22870016 | +| train/ | | +| approx_kl | 0.013161956 | +| clip_fraction | 0.334 | +| clip_range | 0.0693 | +| entropy_loss | -6.88 | +| explained_variance | -0.0391 | +| learning_rate | 4.46e-05 | +| loss | -0.0297 | +| n_updates | 60484 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000179 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1419 | +| iterations | 11168 | +| time_elapsed | 16114 | +| total_timesteps | 22872064 | +| train/ | | +| approx_kl | 0.009707031 | +| clip_fraction | 0.312 | +| clip_range | 0.0693 | +| entropy_loss | -6.95 | +| explained_variance | 0.336 | +| learning_rate | 4.46e-05 | +| loss | -0.0297 | +| n_updates | 60488 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1419 | +| iterations | 11169 | +| time_elapsed | 16116 | +| total_timesteps | 22874112 | +| train/ | | +| approx_kl | 0.012143343 | +| clip_fraction | 0.33 | +| clip_range | 0.0693 | +| entropy_loss | -6.3 | +| explained_variance | 0.537 | +| learning_rate | 4.46e-05 | +| loss | -0.0283 | +| n_updates | 60492 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000129 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1419 | +| iterations | 11170 | +| time_elapsed | 16117 | +| total_timesteps | 22876160 | +| train/ | | +| approx_kl | 0.013467707 | +| clip_fraction | 0.355 | +| clip_range | 0.0693 | +| entropy_loss | -6.42 | +| explained_variance | 0.501 | +| learning_rate | 4.46e-05 | +| loss | -0.0295 | +| n_updates | 60496 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000101 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1419 | +| iterations | 11171 | +| time_elapsed | 16119 | +| total_timesteps | 22878208 | +| train/ | | +| approx_kl | 0.013436346 | +| clip_fraction | 0.33 | +| clip_range | 0.0693 | +| entropy_loss | -6.57 | +| explained_variance | 0.618 | +| learning_rate | 4.46e-05 | +| loss | -0.0296 | +| n_updates | 60500 | +| policy_gradient_loss | -0.0185 | +| value_loss | 8.79e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1419 | +| iterations | 11172 | +| time_elapsed | 16120 | +| total_timesteps | 22880256 | +| train/ | | +| approx_kl | 0.012452221 | +| clip_fraction | 0.316 | +| clip_range | 0.0693 | +| entropy_loss | -6.66 | +| explained_variance | 0.274 | +| learning_rate | 4.46e-05 | +| loss | -0.0338 | +| n_updates | 60504 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000178 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1419 | +| iterations | 11173 | +| time_elapsed | 16122 | +| total_timesteps | 22882304 | +| train/ | | +| approx_kl | 0.012188498 | +| clip_fraction | 0.313 | +| clip_range | 0.0693 | +| entropy_loss | -6.47 | +| explained_variance | 0.4 | +| learning_rate | 4.46e-05 | +| loss | -0.0223 | +| n_updates | 60508 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000244 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1419 | +| iterations | 11174 | +| time_elapsed | 16123 | +| total_timesteps | 22884352 | +| train/ | | +| approx_kl | 0.016247354 | +| clip_fraction | 0.355 | +| clip_range | 0.0693 | +| entropy_loss | -6.3 | +| explained_variance | 0.417 | +| learning_rate | 4.46e-05 | +| loss | -0.0345 | +| n_updates | 60512 | +| policy_gradient_loss | -0.0211 | +| value_loss | 9.32e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1419 | +| iterations | 11175 | +| time_elapsed | 16125 | +| total_timesteps | 22886400 | +| train/ | | +| approx_kl | 0.013913169 | +| clip_fraction | 0.333 | +| clip_range | 0.0693 | +| entropy_loss | -6.11 | +| explained_variance | 0.693 | +| learning_rate | 4.46e-05 | +| loss | -0.0244 | +| n_updates | 60516 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000141 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1419 | +| iterations | 11176 | +| time_elapsed | 16126 | +| total_timesteps | 22888448 | +| train/ | | +| approx_kl | 0.013714586 | +| clip_fraction | 0.38 | +| clip_range | 0.0693 | +| entropy_loss | -5.9 | +| explained_variance | 0.791 | +| learning_rate | 4.46e-05 | +| loss | -0.0397 | +| n_updates | 60520 | +| policy_gradient_loss | -0.0233 | +| value_loss | 4.36e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1419 | +| iterations | 11177 | +| time_elapsed | 16127 | +| total_timesteps | 22890496 | +| train/ | | +| approx_kl | 0.012089631 | +| clip_fraction | 0.327 | +| clip_range | 0.0693 | +| entropy_loss | -6.64 | +| explained_variance | 0.309 | +| learning_rate | 4.46e-05 | +| loss | -0.0288 | +| n_updates | 60524 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000167 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1419 | +| iterations | 11178 | +| time_elapsed | 16129 | +| total_timesteps | 22892544 | +| train/ | | +| approx_kl | 0.013808666 | +| clip_fraction | 0.359 | +| clip_range | 0.0693 | +| entropy_loss | -6.5 | +| explained_variance | 0.351 | +| learning_rate | 4.46e-05 | +| loss | -0.0284 | +| n_updates | 60528 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000125 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1419 | +| iterations | 11179 | +| time_elapsed | 16130 | +| total_timesteps | 22894592 | +| train/ | | +| approx_kl | 0.012625048 | +| clip_fraction | 0.31 | +| clip_range | 0.0693 | +| entropy_loss | -6.49 | +| explained_variance | 0.476 | +| learning_rate | 4.46e-05 | +| loss | -0.0234 | +| n_updates | 60532 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000165 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1419 | +| iterations | 11180 | +| time_elapsed | 16132 | +| total_timesteps | 22896640 | +| train/ | | +| approx_kl | 0.0142078735 | +| clip_fraction | 0.365 | +| clip_range | 0.0693 | +| entropy_loss | -6.68 | +| explained_variance | -0.17 | +| learning_rate | 4.46e-05 | +| loss | -0.0321 | +| n_updates | 60536 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000168 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1419 | +| iterations | 11181 | +| time_elapsed | 16133 | +| total_timesteps | 22898688 | +| train/ | | +| approx_kl | 0.014225587 | +| clip_fraction | 0.375 | +| clip_range | 0.0693 | +| entropy_loss | -6.67 | +| explained_variance | 0.381 | +| learning_rate | 4.46e-05 | +| loss | -0.0315 | +| n_updates | 60540 | +| policy_gradient_loss | -0.0209 | +| value_loss | 8.41e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1419 | +| iterations | 11182 | +| time_elapsed | 16135 | +| total_timesteps | 22900736 | +| train/ | | +| approx_kl | 0.01384466 | +| clip_fraction | 0.346 | +| clip_range | 0.0693 | +| entropy_loss | -6.89 | +| explained_variance | 0.489 | +| learning_rate | 4.46e-05 | +| loss | -0.027 | +| n_updates | 60544 | +| policy_gradient_loss | -0.0195 | +| value_loss | 7.75e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1419 | +| iterations | 11183 | +| time_elapsed | 16136 | +| total_timesteps | 22902784 | +| train/ | | +| approx_kl | 0.015177589 | +| clip_fraction | 0.33 | +| clip_range | 0.0693 | +| entropy_loss | -6.8 | +| explained_variance | 0.287 | +| learning_rate | 4.46e-05 | +| loss | -0.0242 | +| n_updates | 60548 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000155 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1419 | +| iterations | 11184 | +| time_elapsed | 16138 | +| total_timesteps | 22904832 | +| train/ | | +| approx_kl | 0.016076837 | +| clip_fraction | 0.326 | +| clip_range | 0.0693 | +| entropy_loss | -6.55 | +| explained_variance | 0.245 | +| learning_rate | 4.46e-05 | +| loss | -0.0311 | +| n_updates | 60552 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000161 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1419 | +| iterations | 11185 | +| time_elapsed | 16139 | +| total_timesteps | 22906880 | +| train/ | | +| approx_kl | 0.01363819 | +| clip_fraction | 0.319 | +| clip_range | 0.0693 | +| entropy_loss | -5.76 | +| explained_variance | 0.53 | +| learning_rate | 4.46e-05 | +| loss | -0.0255 | +| n_updates | 60556 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000253 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1419 | +| iterations | 11186 | +| time_elapsed | 16141 | +| total_timesteps | 22908928 | +| train/ | | +| approx_kl | 0.012669519 | +| clip_fraction | 0.342 | +| clip_range | 0.0693 | +| entropy_loss | -6.54 | +| explained_variance | 0.34 | +| learning_rate | 4.46e-05 | +| loss | -0.0358 | +| n_updates | 60560 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1419 | +| iterations | 11187 | +| time_elapsed | 16142 | +| total_timesteps | 22910976 | +| train/ | | +| approx_kl | 0.012924177 | +| clip_fraction | 0.312 | +| clip_range | 0.0693 | +| entropy_loss | -6.51 | +| explained_variance | 0.273 | +| learning_rate | 4.46e-05 | +| loss | -0.0253 | +| n_updates | 60564 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000257 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1419 | +| iterations | 11188 | +| time_elapsed | 16144 | +| total_timesteps | 22913024 | +| train/ | | +| approx_kl | 0.014386833 | +| clip_fraction | 0.353 | +| clip_range | 0.0693 | +| entropy_loss | -6.02 | +| explained_variance | 0.665 | +| learning_rate | 4.46e-05 | +| loss | -0.032 | +| n_updates | 60568 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000124 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1419 | +| iterations | 11189 | +| time_elapsed | 16145 | +| total_timesteps | 22915072 | +| train/ | | +| approx_kl | 0.01010205 | +| clip_fraction | 0.319 | +| clip_range | 0.0693 | +| entropy_loss | -6.21 | +| explained_variance | 0.369 | +| learning_rate | 4.46e-05 | +| loss | -0.0236 | +| n_updates | 60572 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.00029 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1419 | +| iterations | 11190 | +| time_elapsed | 16147 | +| total_timesteps | 22917120 | +| train/ | | +| approx_kl | 0.009633779 | +| clip_fraction | 0.309 | +| clip_range | 0.0693 | +| entropy_loss | -6.33 | +| explained_variance | 0.33 | +| learning_rate | 4.46e-05 | +| loss | -0.0313 | +| n_updates | 60576 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000384 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1419 | +| iterations | 11191 | +| time_elapsed | 16148 | +| total_timesteps | 22919168 | +| train/ | | +| approx_kl | 0.009040793 | +| clip_fraction | 0.307 | +| clip_range | 0.0693 | +| entropy_loss | -6.43 | +| explained_variance | 0.391 | +| learning_rate | 4.46e-05 | +| loss | -0.0271 | +| n_updates | 60580 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000398 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1419 | +| iterations | 11192 | +| time_elapsed | 16150 | +| total_timesteps | 22921216 | +| train/ | | +| approx_kl | 0.011283407 | +| clip_fraction | 0.342 | +| clip_range | 0.0693 | +| entropy_loss | -6.15 | +| explained_variance | 0.346 | +| learning_rate | 4.46e-05 | +| loss | -0.0305 | +| n_updates | 60584 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000308 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1419 | +| iterations | 11193 | +| time_elapsed | 16151 | +| total_timesteps | 22923264 | +| train/ | | +| approx_kl | 0.0119466055 | +| clip_fraction | 0.349 | +| clip_range | 0.0693 | +| entropy_loss | -6.6 | +| explained_variance | 0.157 | +| learning_rate | 4.46e-05 | +| loss | -0.0378 | +| n_updates | 60588 | +| policy_gradient_loss | -0.0222 | +| value_loss | 0.000179 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1419 | +| iterations | 11194 | +| time_elapsed | 16153 | +| total_timesteps | 22925312 | +| train/ | | +| approx_kl | 0.011784896 | +| clip_fraction | 0.35 | +| clip_range | 0.0693 | +| entropy_loss | -6.66 | +| explained_variance | 0.136 | +| learning_rate | 4.46e-05 | +| loss | -0.0257 | +| n_updates | 60592 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000313 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1419 | +| iterations | 11195 | +| time_elapsed | 16154 | +| total_timesteps | 22927360 | +| train/ | | +| approx_kl | 0.01329883 | +| clip_fraction | 0.33 | +| clip_range | 0.0693 | +| entropy_loss | -6.53 | +| explained_variance | 0.118 | +| learning_rate | 4.46e-05 | +| loss | -0.024 | +| n_updates | 60596 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000267 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1419 | +| iterations | 11196 | +| time_elapsed | 16155 | +| total_timesteps | 22929408 | +| train/ | | +| approx_kl | 0.01207114 | +| clip_fraction | 0.318 | +| clip_range | 0.0693 | +| entropy_loss | -6.02 | +| explained_variance | 0.435 | +| learning_rate | 4.46e-05 | +| loss | -0.0313 | +| n_updates | 60600 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000257 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1419 | +| iterations | 11197 | +| time_elapsed | 16157 | +| total_timesteps | 22931456 | +| train/ | | +| approx_kl | 0.010833702 | +| clip_fraction | 0.313 | +| clip_range | 0.0693 | +| entropy_loss | -6.32 | +| explained_variance | 0.426 | +| learning_rate | 4.46e-05 | +| loss | -0.0266 | +| n_updates | 60604 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000289 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1419 | +| iterations | 11198 | +| time_elapsed | 16158 | +| total_timesteps | 22933504 | +| train/ | | +| approx_kl | 0.010004151 | +| clip_fraction | 0.331 | +| clip_range | 0.0693 | +| entropy_loss | -6.18 | +| explained_variance | 0.455 | +| learning_rate | 4.46e-05 | +| loss | -0.0328 | +| n_updates | 60608 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.00024 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1419 | +| iterations | 11199 | +| time_elapsed | 16160 | +| total_timesteps | 22935552 | +| train/ | | +| approx_kl | 0.010689137 | +| clip_fraction | 0.296 | +| clip_range | 0.0693 | +| entropy_loss | -6.6 | +| explained_variance | 0.382 | +| learning_rate | 4.46e-05 | +| loss | -0.0385 | +| n_updates | 60612 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000126 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1419 | +| iterations | 11200 | +| time_elapsed | 16161 | +| total_timesteps | 22937600 | +| train/ | | +| approx_kl | 0.010258085 | +| clip_fraction | 0.332 | +| clip_range | 0.0693 | +| entropy_loss | -6.5 | +| explained_variance | 0.361 | +| learning_rate | 4.46e-05 | +| loss | -0.0254 | +| n_updates | 60616 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000264 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1419 | +| iterations | 11201 | +| time_elapsed | 16163 | +| total_timesteps | 22939648 | +| train/ | | +| approx_kl | 0.016912099 | +| clip_fraction | 0.34 | +| clip_range | 0.0693 | +| entropy_loss | -6.62 | +| explained_variance | -0.322 | +| learning_rate | 4.46e-05 | +| loss | -0.0324 | +| n_updates | 60620 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000153 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1419 | +| iterations | 11202 | +| time_elapsed | 16164 | +| total_timesteps | 22941696 | +| train/ | | +| approx_kl | 0.012812758 | +| clip_fraction | 0.344 | +| clip_range | 0.0693 | +| entropy_loss | -5.77 | +| explained_variance | 0.752 | +| learning_rate | 4.46e-05 | +| loss | -0.0341 | +| n_updates | 60624 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000122 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1419 | +| iterations | 11203 | +| time_elapsed | 16166 | +| total_timesteps | 22943744 | +| train/ | | +| approx_kl | 0.013411479 | +| clip_fraction | 0.345 | +| clip_range | 0.0693 | +| entropy_loss | -6.21 | +| explained_variance | 0.506 | +| learning_rate | 4.46e-05 | +| loss | -0.0314 | +| n_updates | 60628 | +| policy_gradient_loss | -0.0213 | +| value_loss | 8.6e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1419 | +| iterations | 11204 | +| time_elapsed | 16167 | +| total_timesteps | 22945792 | +| train/ | | +| approx_kl | 0.013470292 | +| clip_fraction | 0.356 | +| clip_range | 0.0693 | +| entropy_loss | -6.56 | +| explained_variance | 0.376 | +| learning_rate | 4.46e-05 | +| loss | -0.0345 | +| n_updates | 60632 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000141 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1419 | +| iterations | 11205 | +| time_elapsed | 16169 | +| total_timesteps | 22947840 | +| train/ | | +| approx_kl | 0.014143728 | +| clip_fraction | 0.366 | +| clip_range | 0.0693 | +| entropy_loss | -6.89 | +| explained_variance | -0.0609 | +| learning_rate | 4.46e-05 | +| loss | -0.035 | +| n_updates | 60636 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000114 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1419 | +| iterations | 11206 | +| time_elapsed | 16170 | +| total_timesteps | 22949888 | +| train/ | | +| approx_kl | 0.010626047 | +| clip_fraction | 0.322 | +| clip_range | 0.0693 | +| entropy_loss | -7.11 | +| explained_variance | 0.0867 | +| learning_rate | 4.45e-05 | +| loss | -0.0364 | +| n_updates | 60640 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000145 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1419 | +| iterations | 11207 | +| time_elapsed | 16172 | +| total_timesteps | 22951936 | +| train/ | | +| approx_kl | 0.010256578 | +| clip_fraction | 0.295 | +| clip_range | 0.0693 | +| entropy_loss | -7.02 | +| explained_variance | 0.229 | +| learning_rate | 4.45e-05 | +| loss | -0.0296 | +| n_updates | 60644 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000166 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1419 | +| iterations | 11208 | +| time_elapsed | 16173 | +| total_timesteps | 22953984 | +| train/ | | +| approx_kl | 0.010400292 | +| clip_fraction | 0.3 | +| clip_range | 0.0693 | +| entropy_loss | -6 | +| explained_variance | 0.488 | +| learning_rate | 4.45e-05 | +| loss | -0.02 | +| n_updates | 60648 | +| policy_gradient_loss | -0.014 | +| value_loss | 0.000374 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1419 | +| iterations | 11209 | +| time_elapsed | 16175 | +| total_timesteps | 22956032 | +| train/ | | +| approx_kl | 0.013129374 | +| clip_fraction | 0.343 | +| clip_range | 0.0693 | +| entropy_loss | -6.49 | +| explained_variance | -0.186 | +| learning_rate | 4.45e-05 | +| loss | -0.033 | +| n_updates | 60652 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000131 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1419 | +| iterations | 11210 | +| time_elapsed | 16176 | +| total_timesteps | 22958080 | +| train/ | | +| approx_kl | 0.011056785 | +| clip_fraction | 0.326 | +| clip_range | 0.0693 | +| entropy_loss | -5.54 | +| explained_variance | 0.552 | +| learning_rate | 4.45e-05 | +| loss | -0.029 | +| n_updates | 60656 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000287 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1419 | +| iterations | 11211 | +| time_elapsed | 16178 | +| total_timesteps | 22960128 | +| train/ | | +| approx_kl | 0.015843833 | +| clip_fraction | 0.344 | +| clip_range | 0.0693 | +| entropy_loss | -5.67 | +| explained_variance | 0.486 | +| learning_rate | 4.45e-05 | +| loss | -0.0309 | +| n_updates | 60660 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000115 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1419 | +| iterations | 11212 | +| time_elapsed | 16179 | +| total_timesteps | 22962176 | +| train/ | | +| approx_kl | 0.0126125775 | +| clip_fraction | 0.339 | +| clip_range | 0.0693 | +| entropy_loss | -6.47 | +| explained_variance | 0.271 | +| learning_rate | 4.45e-05 | +| loss | -0.0255 | +| n_updates | 60664 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000251 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1419 | +| iterations | 11213 | +| time_elapsed | 16181 | +| total_timesteps | 22964224 | +| train/ | | +| approx_kl | 0.014285766 | +| clip_fraction | 0.342 | +| clip_range | 0.0693 | +| entropy_loss | -6.45 | +| explained_variance | 0.517 | +| learning_rate | 4.45e-05 | +| loss | -0.0359 | +| n_updates | 60668 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000134 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1419 | +| iterations | 11214 | +| time_elapsed | 16182 | +| total_timesteps | 22966272 | +| train/ | | +| approx_kl | 0.012117108 | +| clip_fraction | 0.351 | +| clip_range | 0.0693 | +| entropy_loss | -6.66 | +| explained_variance | 0.0608 | +| learning_rate | 4.45e-05 | +| loss | -0.0348 | +| n_updates | 60672 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000118 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1419 | +| iterations | 11215 | +| time_elapsed | 16184 | +| total_timesteps | 22968320 | +| train/ | | +| approx_kl | 0.011156653 | +| clip_fraction | 0.343 | +| clip_range | 0.0693 | +| entropy_loss | -7.06 | +| explained_variance | -0.127 | +| learning_rate | 4.45e-05 | +| loss | -0.0376 | +| n_updates | 60676 | +| policy_gradient_loss | -0.0198 | +| value_loss | 8.64e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1419 | +| iterations | 11216 | +| time_elapsed | 16185 | +| total_timesteps | 22970368 | +| train/ | | +| approx_kl | 0.013902995 | +| clip_fraction | 0.35 | +| clip_range | 0.0693 | +| entropy_loss | -6.79 | +| explained_variance | 0.135 | +| learning_rate | 4.45e-05 | +| loss | -0.0246 | +| n_updates | 60680 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.00042 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1419 | +| iterations | 11217 | +| time_elapsed | 16187 | +| total_timesteps | 22972416 | +| train/ | | +| approx_kl | 0.012062444 | +| clip_fraction | 0.322 | +| clip_range | 0.0693 | +| entropy_loss | -6.49 | +| explained_variance | 0.131 | +| learning_rate | 4.45e-05 | +| loss | -0.026 | +| n_updates | 60684 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000255 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1419 | +| iterations | 11218 | +| time_elapsed | 16188 | +| total_timesteps | 22974464 | +| train/ | | +| approx_kl | 0.01429644 | +| clip_fraction | 0.312 | +| clip_range | 0.0693 | +| entropy_loss | -6.2 | +| explained_variance | 0.387 | +| learning_rate | 4.45e-05 | +| loss | -0.0258 | +| n_updates | 60688 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000263 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1419 | +| iterations | 11219 | +| time_elapsed | 16190 | +| total_timesteps | 22976512 | +| train/ | | +| approx_kl | 0.012846622 | +| clip_fraction | 0.319 | +| clip_range | 0.0693 | +| entropy_loss | -6.35 | +| explained_variance | 0.507 | +| learning_rate | 4.45e-05 | +| loss | -0.0314 | +| n_updates | 60692 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000151 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1419 | +| iterations | 11220 | +| time_elapsed | 16191 | +| total_timesteps | 22978560 | +| train/ | | +| approx_kl | 0.013706583 | +| clip_fraction | 0.364 | +| clip_range | 0.0693 | +| entropy_loss | -6.76 | +| explained_variance | 0.347 | +| learning_rate | 4.45e-05 | +| loss | -0.0403 | +| n_updates | 60696 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000124 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1419 | +| iterations | 11221 | +| time_elapsed | 16192 | +| total_timesteps | 22980608 | +| train/ | | +| approx_kl | 0.0167923 | +| clip_fraction | 0.339 | +| clip_range | 0.0693 | +| entropy_loss | -6.51 | +| explained_variance | 0.276 | +| learning_rate | 4.45e-05 | +| loss | -0.0307 | +| n_updates | 60700 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000149 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1419 | +| iterations | 11222 | +| time_elapsed | 16194 | +| total_timesteps | 22982656 | +| train/ | | +| approx_kl | 0.011919609 | +| clip_fraction | 0.332 | +| clip_range | 0.0693 | +| entropy_loss | -6.53 | +| explained_variance | 0.573 | +| learning_rate | 4.45e-05 | +| loss | -0.029 | +| n_updates | 60704 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000171 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1419 | +| iterations | 11223 | +| time_elapsed | 16195 | +| total_timesteps | 22984704 | +| train/ | | +| approx_kl | 0.012523561 | +| clip_fraction | 0.346 | +| clip_range | 0.0693 | +| entropy_loss | -6.44 | +| explained_variance | 0.423 | +| learning_rate | 4.45e-05 | +| loss | -0.0322 | +| n_updates | 60708 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000167 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1419 | +| iterations | 11224 | +| time_elapsed | 16197 | +| total_timesteps | 22986752 | +| train/ | | +| approx_kl | 0.011898685 | +| clip_fraction | 0.338 | +| clip_range | 0.0693 | +| entropy_loss | -6.5 | +| explained_variance | 0.391 | +| learning_rate | 4.45e-05 | +| loss | -0.0342 | +| n_updates | 60712 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000235 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1419 | +| iterations | 11225 | +| time_elapsed | 16198 | +| total_timesteps | 22988800 | +| train/ | | +| approx_kl | 0.01301612 | +| clip_fraction | 0.326 | +| clip_range | 0.0693 | +| entropy_loss | -6.64 | +| explained_variance | 0.272 | +| learning_rate | 4.45e-05 | +| loss | -0.0239 | +| n_updates | 60716 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000209 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1419 | +| iterations | 11226 | +| time_elapsed | 16200 | +| total_timesteps | 22990848 | +| train/ | | +| approx_kl | 0.012457742 | +| clip_fraction | 0.336 | +| clip_range | 0.0693 | +| entropy_loss | -6.41 | +| explained_variance | 0.347 | +| learning_rate | 4.45e-05 | +| loss | -0.0254 | +| n_updates | 60720 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.0002 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1419 | +| iterations | 11227 | +| time_elapsed | 16201 | +| total_timesteps | 22992896 | +| train/ | | +| approx_kl | 0.014601643 | +| clip_fraction | 0.354 | +| clip_range | 0.0693 | +| entropy_loss | -6.24 | +| explained_variance | 0.402 | +| learning_rate | 4.45e-05 | +| loss | -0.0321 | +| n_updates | 60724 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000112 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1419 | +| iterations | 11228 | +| time_elapsed | 16203 | +| total_timesteps | 22994944 | +| train/ | | +| approx_kl | 0.012172646 | +| clip_fraction | 0.318 | +| clip_range | 0.0693 | +| entropy_loss | -6.28 | +| explained_variance | 0.349 | +| learning_rate | 4.45e-05 | +| loss | -0.0214 | +| n_updates | 60728 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000417 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1419 | +| iterations | 11229 | +| time_elapsed | 16204 | +| total_timesteps | 22996992 | +| train/ | | +| approx_kl | 0.015319527 | +| clip_fraction | 0.354 | +| clip_range | 0.0693 | +| entropy_loss | -6.87 | +| explained_variance | -0.322 | +| learning_rate | 4.45e-05 | +| loss | -0.0322 | +| n_updates | 60732 | +| policy_gradient_loss | -0.0222 | +| value_loss | 0.000131 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1419 | +| iterations | 11230 | +| time_elapsed | 16206 | +| total_timesteps | 22999040 | +| train/ | | +| approx_kl | 0.016238987 | +| clip_fraction | 0.35 | +| clip_range | 0.0693 | +| entropy_loss | -6.46 | +| explained_variance | 0.541 | +| learning_rate | 4.45e-05 | +| loss | -0.0356 | +| n_updates | 60736 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000123 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1419 | +| iterations | 11231 | +| time_elapsed | 16207 | +| total_timesteps | 23001088 | +| train/ | | +| approx_kl | 0.012749516 | +| clip_fraction | 0.303 | +| clip_range | 0.0693 | +| entropy_loss | -6.11 | +| explained_variance | 0.507 | +| learning_rate | 4.45e-05 | +| loss | -0.0234 | +| n_updates | 60740 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000183 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1419 | +| iterations | 11232 | +| time_elapsed | 16209 | +| total_timesteps | 23003136 | +| train/ | | +| approx_kl | 0.011701711 | +| clip_fraction | 0.315 | +| clip_range | 0.0692 | +| entropy_loss | -6.63 | +| explained_variance | 0.172 | +| learning_rate | 4.45e-05 | +| loss | -0.033 | +| n_updates | 60744 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000397 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.384 | +| time/ | | +| fps | 1419 | +| iterations | 11233 | +| time_elapsed | 16210 | +| total_timesteps | 23005184 | +| train/ | | +| approx_kl | 0.012446523 | +| clip_fraction | 0.34 | +| clip_range | 0.0692 | +| entropy_loss | -6.34 | +| explained_variance | 0.398 | +| learning_rate | 4.45e-05 | +| loss | -0.0331 | +| n_updates | 60748 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000184 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.384 | +| time/ | | +| fps | 1419 | +| iterations | 11234 | +| time_elapsed | 16212 | +| total_timesteps | 23007232 | +| train/ | | +| approx_kl | 0.012826072 | +| clip_fraction | 0.334 | +| clip_range | 0.0692 | +| entropy_loss | -6.5 | +| explained_variance | 0.32 | +| learning_rate | 4.45e-05 | +| loss | -0.0264 | +| n_updates | 60752 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000347 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.384 | +| time/ | | +| fps | 1419 | +| iterations | 11235 | +| time_elapsed | 16213 | +| total_timesteps | 23009280 | +| train/ | | +| approx_kl | 0.013044558 | +| clip_fraction | 0.354 | +| clip_range | 0.0692 | +| entropy_loss | -6.72 | +| explained_variance | 0.0434 | +| learning_rate | 4.45e-05 | +| loss | -0.0303 | +| n_updates | 60756 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000149 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.389 | +| time/ | | +| fps | 1419 | +| iterations | 11236 | +| time_elapsed | 16215 | +| total_timesteps | 23011328 | +| train/ | | +| approx_kl | 0.012991233 | +| clip_fraction | 0.364 | +| clip_range | 0.0692 | +| entropy_loss | -6.93 | +| explained_variance | -0.0905 | +| learning_rate | 4.45e-05 | +| loss | -0.0393 | +| n_updates | 60760 | +| policy_gradient_loss | -0.0226 | +| value_loss | 0.000121 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.393 | +| time/ | | +| fps | 1419 | +| iterations | 11237 | +| time_elapsed | 16216 | +| total_timesteps | 23013376 | +| train/ | | +| approx_kl | 0.0148197 | +| clip_fraction | 0.317 | +| clip_range | 0.0692 | +| entropy_loss | -6.58 | +| explained_variance | 0.422 | +| learning_rate | 4.45e-05 | +| loss | -0.0256 | +| n_updates | 60764 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000218 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.395 | +| time/ | | +| fps | 1419 | +| iterations | 11238 | +| time_elapsed | 16218 | +| total_timesteps | 23015424 | +| train/ | | +| approx_kl | 0.011411073 | +| clip_fraction | 0.326 | +| clip_range | 0.0692 | +| entropy_loss | -6.14 | +| explained_variance | 0.636 | +| learning_rate | 4.45e-05 | +| loss | -0.0302 | +| n_updates | 60768 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000143 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.395 | +| time/ | | +| fps | 1419 | +| iterations | 11239 | +| time_elapsed | 16219 | +| total_timesteps | 23017472 | +| train/ | | +| approx_kl | 0.015144391 | +| clip_fraction | 0.382 | +| clip_range | 0.0692 | +| entropy_loss | -6.29 | +| explained_variance | 0.615 | +| learning_rate | 4.45e-05 | +| loss | -0.0369 | +| n_updates | 60772 | +| policy_gradient_loss | -0.0251 | +| value_loss | 5.56e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.395 | +| time/ | | +| fps | 1419 | +| iterations | 11240 | +| time_elapsed | 16221 | +| total_timesteps | 23019520 | +| train/ | | +| approx_kl | 0.013882734 | +| clip_fraction | 0.322 | +| clip_range | 0.0692 | +| entropy_loss | -6.45 | +| explained_variance | 0.389 | +| learning_rate | 4.45e-05 | +| loss | -0.0306 | +| n_updates | 60776 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000242 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.393 | +| time/ | | +| fps | 1419 | +| iterations | 11241 | +| time_elapsed | 16222 | +| total_timesteps | 23021568 | +| train/ | | +| approx_kl | 0.014062721 | +| clip_fraction | 0.375 | +| clip_range | 0.0692 | +| entropy_loss | -6.4 | +| explained_variance | 0.542 | +| learning_rate | 4.45e-05 | +| loss | -0.033 | +| n_updates | 60780 | +| policy_gradient_loss | -0.0219 | +| value_loss | 0.000129 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.391 | +| time/ | | +| fps | 1419 | +| iterations | 11242 | +| time_elapsed | 16224 | +| total_timesteps | 23023616 | +| train/ | | +| approx_kl | 0.01296635 | +| clip_fraction | 0.345 | +| clip_range | 0.0692 | +| entropy_loss | -6.92 | +| explained_variance | 0.451 | +| learning_rate | 4.45e-05 | +| loss | -0.0262 | +| n_updates | 60784 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000105 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.389 | +| time/ | | +| fps | 1419 | +| iterations | 11243 | +| time_elapsed | 16225 | +| total_timesteps | 23025664 | +| train/ | | +| approx_kl | 0.012906102 | +| clip_fraction | 0.33 | +| clip_range | 0.0692 | +| entropy_loss | -6.14 | +| explained_variance | 0.305 | +| learning_rate | 4.45e-05 | +| loss | -0.0244 | +| n_updates | 60788 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000385 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.39 | +| time/ | | +| fps | 1419 | +| iterations | 11244 | +| time_elapsed | 16227 | +| total_timesteps | 23027712 | +| train/ | | +| approx_kl | 0.012783639 | +| clip_fraction | 0.356 | +| clip_range | 0.0692 | +| entropy_loss | -6.16 | +| explained_variance | 0.676 | +| learning_rate | 4.45e-05 | +| loss | -0.033 | +| n_updates | 60792 | +| policy_gradient_loss | -0.021 | +| value_loss | 7.97e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.39 | +| time/ | | +| fps | 1419 | +| iterations | 11245 | +| time_elapsed | 16228 | +| total_timesteps | 23029760 | +| train/ | | +| approx_kl | 0.016350862 | +| clip_fraction | 0.344 | +| clip_range | 0.0692 | +| entropy_loss | -6.11 | +| explained_variance | 0.67 | +| learning_rate | 4.45e-05 | +| loss | -0.0355 | +| n_updates | 60796 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000106 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.39 | +| time/ | | +| fps | 1419 | +| iterations | 11246 | +| time_elapsed | 16230 | +| total_timesteps | 23031808 | +| train/ | | +| approx_kl | 0.012360893 | +| clip_fraction | 0.339 | +| clip_range | 0.0692 | +| entropy_loss | -6.55 | +| explained_variance | 0.0677 | +| learning_rate | 4.45e-05 | +| loss | -0.0341 | +| n_updates | 60800 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000133 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.394 | +| time/ | | +| fps | 1419 | +| iterations | 11247 | +| time_elapsed | 16231 | +| total_timesteps | 23033856 | +| train/ | | +| approx_kl | 0.01204998 | +| clip_fraction | 0.307 | +| clip_range | 0.0692 | +| entropy_loss | -7 | +| explained_variance | 0.0273 | +| learning_rate | 4.45e-05 | +| loss | -0.0268 | +| n_updates | 60804 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000224 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.395 | +| time/ | | +| fps | 1419 | +| iterations | 11248 | +| time_elapsed | 16232 | +| total_timesteps | 23035904 | +| train/ | | +| approx_kl | 0.011321185 | +| clip_fraction | 0.32 | +| clip_range | 0.0692 | +| entropy_loss | -6.53 | +| explained_variance | 0.337 | +| learning_rate | 4.45e-05 | +| loss | -0.0255 | +| n_updates | 60808 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000249 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.389 | +| time/ | | +| fps | 1419 | +| iterations | 11249 | +| time_elapsed | 16234 | +| total_timesteps | 23037952 | +| train/ | | +| approx_kl | 0.012004819 | +| clip_fraction | 0.329 | +| clip_range | 0.0692 | +| entropy_loss | -6.91 | +| explained_variance | 0.311 | +| learning_rate | 4.45e-05 | +| loss | -0.0329 | +| n_updates | 60812 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.00013 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.389 | +| time/ | | +| fps | 1419 | +| iterations | 11250 | +| time_elapsed | 16235 | +| total_timesteps | 23040000 | +| train/ | | +| approx_kl | 0.014121976 | +| clip_fraction | 0.321 | +| clip_range | 0.0692 | +| entropy_loss | -6.42 | +| explained_variance | 0.602 | +| learning_rate | 4.45e-05 | +| loss | -0.0316 | +| n_updates | 60816 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000106 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.384 | +| time/ | | +| fps | 1419 | +| iterations | 11251 | +| time_elapsed | 16237 | +| total_timesteps | 23042048 | +| train/ | | +| approx_kl | 0.012701188 | +| clip_fraction | 0.322 | +| clip_range | 0.0692 | +| entropy_loss | -6.32 | +| explained_variance | 0.389 | +| learning_rate | 4.45e-05 | +| loss | -0.0251 | +| n_updates | 60820 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000221 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1419 | +| iterations | 11252 | +| time_elapsed | 16238 | +| total_timesteps | 23044096 | +| train/ | | +| approx_kl | 0.012322111 | +| clip_fraction | 0.322 | +| clip_range | 0.0692 | +| entropy_loss | -6.39 | +| explained_variance | 0.29 | +| learning_rate | 4.45e-05 | +| loss | -0.0264 | +| n_updates | 60824 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000184 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1419 | +| iterations | 11253 | +| time_elapsed | 16240 | +| total_timesteps | 23046144 | +| train/ | | +| approx_kl | 0.01236993 | +| clip_fraction | 0.337 | +| clip_range | 0.0692 | +| entropy_loss | -6.29 | +| explained_variance | 0.637 | +| learning_rate | 4.45e-05 | +| loss | -0.0326 | +| n_updates | 60828 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000145 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1419 | +| iterations | 11254 | +| time_elapsed | 16241 | +| total_timesteps | 23048192 | +| train/ | | +| approx_kl | 0.013940069 | +| clip_fraction | 0.347 | +| clip_range | 0.0692 | +| entropy_loss | -6.28 | +| explained_variance | 0.629 | +| learning_rate | 4.45e-05 | +| loss | -0.0307 | +| n_updates | 60832 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000148 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1419 | +| iterations | 11255 | +| time_elapsed | 16243 | +| total_timesteps | 23050240 | +| train/ | | +| approx_kl | 0.014399059 | +| clip_fraction | 0.354 | +| clip_range | 0.0692 | +| entropy_loss | -6.41 | +| explained_variance | 0.373 | +| learning_rate | 4.45e-05 | +| loss | -0.0377 | +| n_updates | 60836 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.00011 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1419 | +| iterations | 11256 | +| time_elapsed | 16244 | +| total_timesteps | 23052288 | +| train/ | | +| approx_kl | 0.012707487 | +| clip_fraction | 0.34 | +| clip_range | 0.0692 | +| entropy_loss | -6.59 | +| explained_variance | 0.622 | +| learning_rate | 4.45e-05 | +| loss | -0.028 | +| n_updates | 60840 | +| policy_gradient_loss | -0.0201 | +| value_loss | 9.87e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1419 | +| iterations | 11257 | +| time_elapsed | 16246 | +| total_timesteps | 23054336 | +| train/ | | +| approx_kl | 0.010389512 | +| clip_fraction | 0.307 | +| clip_range | 0.0692 | +| entropy_loss | -6.71 | +| explained_variance | 0.246 | +| learning_rate | 4.45e-05 | +| loss | -0.0221 | +| n_updates | 60844 | +| policy_gradient_loss | -0.0146 | +| value_loss | 0.000204 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1419 | +| iterations | 11258 | +| time_elapsed | 16247 | +| total_timesteps | 23056384 | +| train/ | | +| approx_kl | 0.011211146 | +| clip_fraction | 0.332 | +| clip_range | 0.0692 | +| entropy_loss | -6.52 | +| explained_variance | 0.526 | +| learning_rate | 4.45e-05 | +| loss | -0.024 | +| n_updates | 60848 | +| policy_gradient_loss | -0.0179 | +| value_loss | 9.94e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1419 | +| iterations | 11259 | +| time_elapsed | 16249 | +| total_timesteps | 23058432 | +| train/ | | +| approx_kl | 0.011786802 | +| clip_fraction | 0.33 | +| clip_range | 0.0692 | +| entropy_loss | -6.34 | +| explained_variance | 0.35 | +| learning_rate | 4.45e-05 | +| loss | -0.026 | +| n_updates | 60852 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000263 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1419 | +| iterations | 11260 | +| time_elapsed | 16250 | +| total_timesteps | 23060480 | +| train/ | | +| approx_kl | 0.016390704 | +| clip_fraction | 0.336 | +| clip_range | 0.0692 | +| entropy_loss | -6.42 | +| explained_variance | 0.396 | +| learning_rate | 4.45e-05 | +| loss | -0.0293 | +| n_updates | 60856 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000165 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1419 | +| iterations | 11261 | +| time_elapsed | 16252 | +| total_timesteps | 23062528 | +| train/ | | +| approx_kl | 0.010815719 | +| clip_fraction | 0.339 | +| clip_range | 0.0692 | +| entropy_loss | -6.73 | +| explained_variance | 0.126 | +| learning_rate | 4.45e-05 | +| loss | -0.0266 | +| n_updates | 60860 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000253 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1419 | +| iterations | 11262 | +| time_elapsed | 16253 | +| total_timesteps | 23064576 | +| train/ | | +| approx_kl | 0.010953233 | +| clip_fraction | 0.336 | +| clip_range | 0.0692 | +| entropy_loss | -6.14 | +| explained_variance | 0.612 | +| learning_rate | 4.45e-05 | +| loss | -0.0324 | +| n_updates | 60864 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000191 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1419 | +| iterations | 11263 | +| time_elapsed | 16255 | +| total_timesteps | 23066624 | +| train/ | | +| approx_kl | 0.014176963 | +| clip_fraction | 0.349 | +| clip_range | 0.0692 | +| entropy_loss | -6.18 | +| explained_variance | 0.441 | +| learning_rate | 4.45e-05 | +| loss | -0.0284 | +| n_updates | 60868 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000172 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1419 | +| iterations | 11264 | +| time_elapsed | 16256 | +| total_timesteps | 23068672 | +| train/ | | +| approx_kl | 0.014003277 | +| clip_fraction | 0.388 | +| clip_range | 0.0692 | +| entropy_loss | -6.68 | +| explained_variance | -0.0893 | +| learning_rate | 4.45e-05 | +| loss | -0.0325 | +| n_updates | 60872 | +| policy_gradient_loss | -0.0224 | +| value_loss | 9.52e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1419 | +| iterations | 11265 | +| time_elapsed | 16258 | +| total_timesteps | 23070720 | +| train/ | | +| approx_kl | 0.013229217 | +| clip_fraction | 0.325 | +| clip_range | 0.0692 | +| entropy_loss | -6.16 | +| explained_variance | 0.535 | +| learning_rate | 4.45e-05 | +| loss | -0.0255 | +| n_updates | 60876 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000165 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1418 | +| iterations | 11266 | +| time_elapsed | 16259 | +| total_timesteps | 23072768 | +| train/ | | +| approx_kl | 0.010814392 | +| clip_fraction | 0.333 | +| clip_range | 0.0692 | +| entropy_loss | -6.54 | +| explained_variance | 0.538 | +| learning_rate | 4.45e-05 | +| loss | -0.033 | +| n_updates | 60880 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.00012 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1418 | +| iterations | 11267 | +| time_elapsed | 16261 | +| total_timesteps | 23074816 | +| train/ | | +| approx_kl | 0.011058307 | +| clip_fraction | 0.328 | +| clip_range | 0.0692 | +| entropy_loss | -6.97 | +| explained_variance | 0.361 | +| learning_rate | 4.45e-05 | +| loss | -0.0258 | +| n_updates | 60884 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1418 | +| iterations | 11268 | +| time_elapsed | 16262 | +| total_timesteps | 23076864 | +| train/ | | +| approx_kl | 0.012928842 | +| clip_fraction | 0.368 | +| clip_range | 0.0692 | +| entropy_loss | -6.76 | +| explained_variance | -0.375 | +| learning_rate | 4.45e-05 | +| loss | -0.034 | +| n_updates | 60888 | +| policy_gradient_loss | -0.0213 | +| value_loss | 6.75e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1418 | +| iterations | 11269 | +| time_elapsed | 16264 | +| total_timesteps | 23078912 | +| train/ | | +| approx_kl | 0.014487114 | +| clip_fraction | 0.343 | +| clip_range | 0.0692 | +| entropy_loss | -6.16 | +| explained_variance | 0.539 | +| learning_rate | 4.45e-05 | +| loss | -0.0298 | +| n_updates | 60892 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000112 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1418 | +| iterations | 11270 | +| time_elapsed | 16265 | +| total_timesteps | 23080960 | +| train/ | | +| approx_kl | 0.012667509 | +| clip_fraction | 0.316 | +| clip_range | 0.0692 | +| entropy_loss | -6.51 | +| explained_variance | 0.465 | +| learning_rate | 4.45e-05 | +| loss | -0.0281 | +| n_updates | 60896 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000164 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.384 | +| time/ | | +| fps | 1418 | +| iterations | 11271 | +| time_elapsed | 16267 | +| total_timesteps | 23083008 | +| train/ | | +| approx_kl | 0.010721144 | +| clip_fraction | 0.339 | +| clip_range | 0.0692 | +| entropy_loss | -6.39 | +| explained_variance | 0.325 | +| learning_rate | 4.45e-05 | +| loss | -0.0256 | +| n_updates | 60900 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000367 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.384 | +| time/ | | +| fps | 1418 | +| iterations | 11272 | +| time_elapsed | 16268 | +| total_timesteps | 23085056 | +| train/ | | +| approx_kl | 0.011610059 | +| clip_fraction | 0.348 | +| clip_range | 0.0692 | +| entropy_loss | -6.15 | +| explained_variance | 0.556 | +| learning_rate | 4.45e-05 | +| loss | -0.0303 | +| n_updates | 60904 | +| policy_gradient_loss | -0.0219 | +| value_loss | 0.00011 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.387 | +| time/ | | +| fps | 1418 | +| iterations | 11273 | +| time_elapsed | 16270 | +| total_timesteps | 23087104 | +| train/ | | +| approx_kl | 0.012309387 | +| clip_fraction | 0.354 | +| clip_range | 0.0692 | +| entropy_loss | -6.71 | +| explained_variance | -0.1 | +| learning_rate | 4.45e-05 | +| loss | -0.0312 | +| n_updates | 60908 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000121 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.387 | +| time/ | | +| fps | 1418 | +| iterations | 11274 | +| time_elapsed | 16271 | +| total_timesteps | 23089152 | +| train/ | | +| approx_kl | 0.013275143 | +| clip_fraction | 0.34 | +| clip_range | 0.0692 | +| entropy_loss | -6.65 | +| explained_variance | 0.371 | +| learning_rate | 4.45e-05 | +| loss | -0.0299 | +| n_updates | 60912 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000266 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.387 | +| time/ | | +| fps | 1418 | +| iterations | 11275 | +| time_elapsed | 16273 | +| total_timesteps | 23091200 | +| train/ | | +| approx_kl | 0.012840854 | +| clip_fraction | 0.336 | +| clip_range | 0.0692 | +| entropy_loss | -6.31 | +| explained_variance | 0.35 | +| learning_rate | 4.45e-05 | +| loss | -0.0316 | +| n_updates | 60916 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000288 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.387 | +| time/ | | +| fps | 1418 | +| iterations | 11276 | +| time_elapsed | 16274 | +| total_timesteps | 23093248 | +| train/ | | +| approx_kl | 0.014461484 | +| clip_fraction | 0.384 | +| clip_range | 0.0692 | +| entropy_loss | -6.75 | +| explained_variance | -0.204 | +| learning_rate | 4.45e-05 | +| loss | -0.0353 | +| n_updates | 60920 | +| policy_gradient_loss | -0.0236 | +| value_loss | 0.000134 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.384 | +| time/ | | +| fps | 1418 | +| iterations | 11277 | +| time_elapsed | 16275 | +| total_timesteps | 23095296 | +| train/ | | +| approx_kl | 0.013300318 | +| clip_fraction | 0.349 | +| clip_range | 0.0692 | +| entropy_loss | -6.8 | +| explained_variance | 0.397 | +| learning_rate | 4.45e-05 | +| loss | -0.031 | +| n_updates | 60924 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.00023 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1418 | +| iterations | 11278 | +| time_elapsed | 16277 | +| total_timesteps | 23097344 | +| train/ | | +| approx_kl | 0.012597365 | +| clip_fraction | 0.356 | +| clip_range | 0.0692 | +| entropy_loss | -6.09 | +| explained_variance | 0.459 | +| learning_rate | 4.45e-05 | +| loss | -0.0386 | +| n_updates | 60928 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.00021 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1418 | +| iterations | 11279 | +| time_elapsed | 16278 | +| total_timesteps | 23099392 | +| train/ | | +| approx_kl | 0.016619246 | +| clip_fraction | 0.353 | +| clip_range | 0.0692 | +| entropy_loss | -6.4 | +| explained_variance | 0.185 | +| learning_rate | 4.45e-05 | +| loss | -0.0261 | +| n_updates | 60932 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000182 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1418 | +| iterations | 11280 | +| time_elapsed | 16280 | +| total_timesteps | 23101440 | +| train/ | | +| approx_kl | 0.01311487 | +| clip_fraction | 0.346 | +| clip_range | 0.0692 | +| entropy_loss | -5.93 | +| explained_variance | 0.533 | +| learning_rate | 4.45e-05 | +| loss | -0.0298 | +| n_updates | 60936 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000268 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1418 | +| iterations | 11281 | +| time_elapsed | 16281 | +| total_timesteps | 23103488 | +| train/ | | +| approx_kl | 0.013030498 | +| clip_fraction | 0.36 | +| clip_range | 0.0692 | +| entropy_loss | -6.71 | +| explained_variance | 0.0129 | +| learning_rate | 4.45e-05 | +| loss | -0.0368 | +| n_updates | 60940 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000201 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1418 | +| iterations | 11282 | +| time_elapsed | 16283 | +| total_timesteps | 23105536 | +| train/ | | +| approx_kl | 0.011464857 | +| clip_fraction | 0.338 | +| clip_range | 0.0692 | +| entropy_loss | -6.52 | +| explained_variance | 0.221 | +| learning_rate | 4.45e-05 | +| loss | -0.027 | +| n_updates | 60944 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.00028 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1418 | +| iterations | 11283 | +| time_elapsed | 16284 | +| total_timesteps | 23107584 | +| train/ | | +| approx_kl | 0.012801599 | +| clip_fraction | 0.324 | +| clip_range | 0.0692 | +| entropy_loss | -6.03 | +| explained_variance | 0.324 | +| learning_rate | 4.45e-05 | +| loss | -0.0282 | +| n_updates | 60948 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.00035 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1418 | +| iterations | 11284 | +| time_elapsed | 16286 | +| total_timesteps | 23109632 | +| train/ | | +| approx_kl | 0.012464755 | +| clip_fraction | 0.364 | +| clip_range | 0.0692 | +| entropy_loss | -6.42 | +| explained_variance | 0.388 | +| learning_rate | 4.45e-05 | +| loss | -0.0267 | +| n_updates | 60952 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000256 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1418 | +| iterations | 11285 | +| time_elapsed | 16287 | +| total_timesteps | 23111680 | +| train/ | | +| approx_kl | 0.00914148 | +| clip_fraction | 0.31 | +| clip_range | 0.0692 | +| entropy_loss | -6.58 | +| explained_variance | 0.157 | +| learning_rate | 4.45e-05 | +| loss | -0.0275 | +| n_updates | 60956 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000315 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1418 | +| iterations | 11286 | +| time_elapsed | 16289 | +| total_timesteps | 23113728 | +| train/ | | +| approx_kl | 0.014045255 | +| clip_fraction | 0.354 | +| clip_range | 0.0692 | +| entropy_loss | -6.13 | +| explained_variance | 0.521 | +| learning_rate | 4.45e-05 | +| loss | -0.0372 | +| n_updates | 60960 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000163 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.386 | +| time/ | | +| fps | 1418 | +| iterations | 11287 | +| time_elapsed | 16290 | +| total_timesteps | 23115776 | +| train/ | | +| approx_kl | 0.012416069 | +| clip_fraction | 0.351 | +| clip_range | 0.0692 | +| entropy_loss | -6.41 | +| explained_variance | 0.287 | +| learning_rate | 4.45e-05 | +| loss | -0.0332 | +| n_updates | 60964 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000207 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1418 | +| iterations | 11288 | +| time_elapsed | 16292 | +| total_timesteps | 23117824 | +| train/ | | +| approx_kl | 0.013232045 | +| clip_fraction | 0.326 | +| clip_range | 0.0692 | +| entropy_loss | -6.32 | +| explained_variance | 0.367 | +| learning_rate | 4.45e-05 | +| loss | -0.0265 | +| n_updates | 60968 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000263 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1418 | +| iterations | 11289 | +| time_elapsed | 16293 | +| total_timesteps | 23119872 | +| train/ | | +| approx_kl | 0.012131374 | +| clip_fraction | 0.329 | +| clip_range | 0.0692 | +| entropy_loss | -6.41 | +| explained_variance | 0.48 | +| learning_rate | 4.45e-05 | +| loss | -0.0333 | +| n_updates | 60972 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000131 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1418 | +| iterations | 11290 | +| time_elapsed | 16295 | +| total_timesteps | 23121920 | +| train/ | | +| approx_kl | 0.011151064 | +| clip_fraction | 0.344 | +| clip_range | 0.0692 | +| entropy_loss | -6.96 | +| explained_variance | -0.00798 | +| learning_rate | 4.45e-05 | +| loss | -0.0287 | +| n_updates | 60976 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.00022 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1418 | +| iterations | 11291 | +| time_elapsed | 16296 | +| total_timesteps | 23123968 | +| train/ | | +| approx_kl | 0.011566741 | +| clip_fraction | 0.324 | +| clip_range | 0.0692 | +| entropy_loss | -6.92 | +| explained_variance | 0.207 | +| learning_rate | 4.45e-05 | +| loss | -0.0296 | +| n_updates | 60980 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000135 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1418 | +| iterations | 11292 | +| time_elapsed | 16298 | +| total_timesteps | 23126016 | +| train/ | | +| approx_kl | 0.012709839 | +| clip_fraction | 0.351 | +| clip_range | 0.0692 | +| entropy_loss | -6.73 | +| explained_variance | 0.427 | +| learning_rate | 4.45e-05 | +| loss | -0.0385 | +| n_updates | 60984 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000101 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1418 | +| iterations | 11293 | +| time_elapsed | 16299 | +| total_timesteps | 23128064 | +| train/ | | +| approx_kl | 0.01124222 | +| clip_fraction | 0.318 | +| clip_range | 0.0692 | +| entropy_loss | -6.11 | +| explained_variance | 0.525 | +| learning_rate | 4.45e-05 | +| loss | -0.0267 | +| n_updates | 60988 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000231 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1418 | +| iterations | 11294 | +| time_elapsed | 16301 | +| total_timesteps | 23130112 | +| train/ | | +| approx_kl | 0.013411179 | +| clip_fraction | 0.344 | +| clip_range | 0.0692 | +| entropy_loss | -5.72 | +| explained_variance | 0.691 | +| learning_rate | 4.45e-05 | +| loss | -0.0279 | +| n_updates | 60992 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000136 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1418 | +| iterations | 11295 | +| time_elapsed | 16302 | +| total_timesteps | 23132160 | +| train/ | | +| approx_kl | 0.016042396 | +| clip_fraction | 0.338 | +| clip_range | 0.0692 | +| entropy_loss | -5.95 | +| explained_variance | 0.591 | +| learning_rate | 4.45e-05 | +| loss | -0.0313 | +| n_updates | 60996 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000106 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1418 | +| iterations | 11296 | +| time_elapsed | 16304 | +| total_timesteps | 23134208 | +| train/ | | +| approx_kl | 0.013044658 | +| clip_fraction | 0.34 | +| clip_range | 0.0692 | +| entropy_loss | -6.28 | +| explained_variance | 0.306 | +| learning_rate | 4.45e-05 | +| loss | -0.0282 | +| n_updates | 61000 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.00011 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1418 | +| iterations | 11297 | +| time_elapsed | 16305 | +| total_timesteps | 23136256 | +| train/ | | +| approx_kl | 0.015916932 | +| clip_fraction | 0.344 | +| clip_range | 0.0692 | +| entropy_loss | -6.3 | +| explained_variance | 0.371 | +| learning_rate | 4.45e-05 | +| loss | -0.0294 | +| n_updates | 61004 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000148 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1418 | +| iterations | 11298 | +| time_elapsed | 16306 | +| total_timesteps | 23138304 | +| train/ | | +| approx_kl | 0.014176797 | +| clip_fraction | 0.39 | +| clip_range | 0.0692 | +| entropy_loss | -6.44 | +| explained_variance | 0.444 | +| learning_rate | 4.45e-05 | +| loss | -0.0317 | +| n_updates | 61008 | +| policy_gradient_loss | -0.0216 | +| value_loss | 7.96e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1418 | +| iterations | 11299 | +| time_elapsed | 16308 | +| total_timesteps | 23140352 | +| train/ | | +| approx_kl | 0.014062762 | +| clip_fraction | 0.354 | +| clip_range | 0.0692 | +| entropy_loss | -6.94 | +| explained_variance | -0.0628 | +| learning_rate | 4.45e-05 | +| loss | -0.0282 | +| n_updates | 61012 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000228 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1418 | +| iterations | 11300 | +| time_elapsed | 16309 | +| total_timesteps | 23142400 | +| train/ | | +| approx_kl | 0.011082819 | +| clip_fraction | 0.334 | +| clip_range | 0.0692 | +| entropy_loss | -6.93 | +| explained_variance | 0.0755 | +| learning_rate | 4.45e-05 | +| loss | -0.0278 | +| n_updates | 61016 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000213 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1418 | +| iterations | 11301 | +| time_elapsed | 16311 | +| total_timesteps | 23144448 | +| train/ | | +| approx_kl | 0.016945638 | +| clip_fraction | 0.299 | +| clip_range | 0.0692 | +| entropy_loss | -6.16 | +| explained_variance | 0.571 | +| learning_rate | 4.45e-05 | +| loss | -0.0279 | +| n_updates | 61020 | +| policy_gradient_loss | -0.0121 | +| value_loss | 0.000229 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1418 | +| iterations | 11302 | +| time_elapsed | 16312 | +| total_timesteps | 23146496 | +| train/ | | +| approx_kl | 0.014621306 | +| clip_fraction | 0.363 | +| clip_range | 0.0692 | +| entropy_loss | -6.43 | +| explained_variance | -0.0011 | +| learning_rate | 4.45e-05 | +| loss | -0.0306 | +| n_updates | 61024 | +| policy_gradient_loss | -0.0207 | +| value_loss | 9.49e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1418 | +| iterations | 11303 | +| time_elapsed | 16314 | +| total_timesteps | 23148544 | +| train/ | | +| approx_kl | 0.014442723 | +| clip_fraction | 0.328 | +| clip_range | 0.0692 | +| entropy_loss | -6.13 | +| explained_variance | 0.591 | +| learning_rate | 4.45e-05 | +| loss | -0.0307 | +| n_updates | 61028 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000172 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1418 | +| iterations | 11304 | +| time_elapsed | 16315 | +| total_timesteps | 23150592 | +| train/ | | +| approx_kl | 0.017020505 | +| clip_fraction | 0.373 | +| clip_range | 0.0692 | +| entropy_loss | -6.03 | +| explained_variance | 0.523 | +| learning_rate | 4.45e-05 | +| loss | -0.0243 | +| n_updates | 61032 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.00016 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1418 | +| iterations | 11305 | +| time_elapsed | 16317 | +| total_timesteps | 23152640 | +| train/ | | +| approx_kl | 0.01523386 | +| clip_fraction | 0.374 | +| clip_range | 0.0692 | +| entropy_loss | -6.29 | +| explained_variance | 0.584 | +| learning_rate | 4.45e-05 | +| loss | -0.0326 | +| n_updates | 61036 | +| policy_gradient_loss | -0.0191 | +| value_loss | 9.85e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1418 | +| iterations | 11306 | +| time_elapsed | 16318 | +| total_timesteps | 23154688 | +| train/ | | +| approx_kl | 0.012813438 | +| clip_fraction | 0.345 | +| clip_range | 0.0692 | +| entropy_loss | -6.38 | +| explained_variance | 0.574 | +| learning_rate | 4.45e-05 | +| loss | -0.0315 | +| n_updates | 61040 | +| policy_gradient_loss | -0.0184 | +| value_loss | 9.45e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1418 | +| iterations | 11307 | +| time_elapsed | 16319 | +| total_timesteps | 23156736 | +| train/ | | +| approx_kl | 0.014378205 | +| clip_fraction | 0.373 | +| clip_range | 0.0692 | +| entropy_loss | -6.49 | +| explained_variance | -0.0806 | +| learning_rate | 4.45e-05 | +| loss | -0.0288 | +| n_updates | 61044 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000125 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1418 | +| iterations | 11308 | +| time_elapsed | 16321 | +| total_timesteps | 23158784 | +| train/ | | +| approx_kl | 0.012281422 | +| clip_fraction | 0.327 | +| clip_range | 0.0692 | +| entropy_loss | -7.02 | +| explained_variance | 0.126 | +| learning_rate | 4.45e-05 | +| loss | -0.0342 | +| n_updates | 61048 | +| policy_gradient_loss | -0.0187 | +| value_loss | 9.61e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1418 | +| iterations | 11309 | +| time_elapsed | 16322 | +| total_timesteps | 23160832 | +| train/ | | +| approx_kl | 0.013751088 | +| clip_fraction | 0.305 | +| clip_range | 0.0692 | +| entropy_loss | -6.54 | +| explained_variance | 0.452 | +| learning_rate | 4.45e-05 | +| loss | -0.0273 | +| n_updates | 61052 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.0002 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1418 | +| iterations | 11310 | +| time_elapsed | 16324 | +| total_timesteps | 23162880 | +| train/ | | +| approx_kl | 0.014425523 | +| clip_fraction | 0.34 | +| clip_range | 0.0692 | +| entropy_loss | -6.95 | +| explained_variance | -0.0653 | +| learning_rate | 4.45e-05 | +| loss | -0.0268 | +| n_updates | 61056 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000133 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1418 | +| iterations | 11311 | +| time_elapsed | 16325 | +| total_timesteps | 23164928 | +| train/ | | +| approx_kl | 0.011356652 | +| clip_fraction | 0.306 | +| clip_range | 0.0692 | +| entropy_loss | -6.69 | +| explained_variance | 0.24 | +| learning_rate | 4.45e-05 | +| loss | -0.0241 | +| n_updates | 61060 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000301 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1418 | +| iterations | 11312 | +| time_elapsed | 16327 | +| total_timesteps | 23166976 | +| train/ | | +| approx_kl | 0.012691382 | +| clip_fraction | 0.356 | +| clip_range | 0.0692 | +| entropy_loss | -6.52 | +| explained_variance | 0.466 | +| learning_rate | 4.45e-05 | +| loss | -0.0274 | +| n_updates | 61064 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000137 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1418 | +| iterations | 11313 | +| time_elapsed | 16328 | +| total_timesteps | 23169024 | +| train/ | | +| approx_kl | 0.013506231 | +| clip_fraction | 0.333 | +| clip_range | 0.0692 | +| entropy_loss | -6.36 | +| explained_variance | 0.435 | +| learning_rate | 4.45e-05 | +| loss | -0.0314 | +| n_updates | 61068 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000146 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1418 | +| iterations | 11314 | +| time_elapsed | 16330 | +| total_timesteps | 23171072 | +| train/ | | +| approx_kl | 0.015022345 | +| clip_fraction | 0.353 | +| clip_range | 0.0692 | +| entropy_loss | -6.14 | +| explained_variance | 0.755 | +| learning_rate | 4.45e-05 | +| loss | -0.0343 | +| n_updates | 61072 | +| policy_gradient_loss | -0.0241 | +| value_loss | 7.05e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1418 | +| iterations | 11315 | +| time_elapsed | 16331 | +| total_timesteps | 23173120 | +| train/ | | +| approx_kl | 0.014015626 | +| clip_fraction | 0.322 | +| clip_range | 0.0692 | +| entropy_loss | -6.2 | +| explained_variance | 0.475 | +| learning_rate | 4.45e-05 | +| loss | -0.0284 | +| n_updates | 61076 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000187 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1418 | +| iterations | 11316 | +| time_elapsed | 16333 | +| total_timesteps | 23175168 | +| train/ | | +| approx_kl | 0.016334191 | +| clip_fraction | 0.358 | +| clip_range | 0.0692 | +| entropy_loss | -5.91 | +| explained_variance | 0.71 | +| learning_rate | 4.45e-05 | +| loss | -0.0384 | +| n_updates | 61080 | +| policy_gradient_loss | -0.0199 | +| value_loss | 9.84e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1418 | +| iterations | 11317 | +| time_elapsed | 16334 | +| total_timesteps | 23177216 | +| train/ | | +| approx_kl | 0.0123078395 | +| clip_fraction | 0.333 | +| clip_range | 0.0692 | +| entropy_loss | -5.96 | +| explained_variance | 0.34 | +| learning_rate | 4.45e-05 | +| loss | -0.0301 | +| n_updates | 61084 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000241 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1418 | +| iterations | 11318 | +| time_elapsed | 16336 | +| total_timesteps | 23179264 | +| train/ | | +| approx_kl | 0.012324307 | +| clip_fraction | 0.333 | +| clip_range | 0.0692 | +| entropy_loss | -6.77 | +| explained_variance | 0.22 | +| learning_rate | 4.45e-05 | +| loss | -0.0317 | +| n_updates | 61088 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000123 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1418 | +| iterations | 11319 | +| time_elapsed | 16337 | +| total_timesteps | 23181312 | +| train/ | | +| approx_kl | 0.010825217 | +| clip_fraction | 0.329 | +| clip_range | 0.0692 | +| entropy_loss | -6.14 | +| explained_variance | 0.663 | +| learning_rate | 4.45e-05 | +| loss | -0.0284 | +| n_updates | 61092 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000133 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1418 | +| iterations | 11320 | +| time_elapsed | 16339 | +| total_timesteps | 23183360 | +| train/ | | +| approx_kl | 0.01281765 | +| clip_fraction | 0.364 | +| clip_range | 0.0692 | +| entropy_loss | -6.47 | +| explained_variance | 0.39 | +| learning_rate | 4.45e-05 | +| loss | -0.0391 | +| n_updates | 61096 | +| policy_gradient_loss | -0.0211 | +| value_loss | 9.65e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1418 | +| iterations | 11321 | +| time_elapsed | 16340 | +| total_timesteps | 23185408 | +| train/ | | +| approx_kl | 0.012165546 | +| clip_fraction | 0.347 | +| clip_range | 0.0692 | +| entropy_loss | -6.56 | +| explained_variance | 0.293 | +| learning_rate | 4.45e-05 | +| loss | -0.0299 | +| n_updates | 61100 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000242 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1418 | +| iterations | 11322 | +| time_elapsed | 16342 | +| total_timesteps | 23187456 | +| train/ | | +| approx_kl | 0.014266389 | +| clip_fraction | 0.346 | +| clip_range | 0.0692 | +| entropy_loss | -6.72 | +| explained_variance | 0.287 | +| learning_rate | 4.45e-05 | +| loss | -0.035 | +| n_updates | 61104 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000133 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1418 | +| iterations | 11323 | +| time_elapsed | 16343 | +| total_timesteps | 23189504 | +| train/ | | +| approx_kl | 0.012731824 | +| clip_fraction | 0.36 | +| clip_range | 0.0692 | +| entropy_loss | -6.83 | +| explained_variance | 0.358 | +| learning_rate | 4.45e-05 | +| loss | -0.0347 | +| n_updates | 61108 | +| policy_gradient_loss | -0.0219 | +| value_loss | 0.000111 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1418 | +| iterations | 11324 | +| time_elapsed | 16345 | +| total_timesteps | 23191552 | +| train/ | | +| approx_kl | 0.009357428 | +| clip_fraction | 0.305 | +| clip_range | 0.0692 | +| entropy_loss | -6.53 | +| explained_variance | 0.296 | +| learning_rate | 4.45e-05 | +| loss | -0.0266 | +| n_updates | 61112 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.00024 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1418 | +| iterations | 11325 | +| time_elapsed | 16346 | +| total_timesteps | 23193600 | +| train/ | | +| approx_kl | 0.013639199 | +| clip_fraction | 0.339 | +| clip_range | 0.0692 | +| entropy_loss | -6.04 | +| explained_variance | 0.58 | +| learning_rate | 4.45e-05 | +| loss | -0.0258 | +| n_updates | 61116 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000142 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1418 | +| iterations | 11326 | +| time_elapsed | 16347 | +| total_timesteps | 23195648 | +| train/ | | +| approx_kl | 0.014470199 | +| clip_fraction | 0.345 | +| clip_range | 0.0692 | +| entropy_loss | -6.68 | +| explained_variance | -0.0282 | +| learning_rate | 4.45e-05 | +| loss | -0.0366 | +| n_updates | 61120 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000153 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1418 | +| iterations | 11327 | +| time_elapsed | 16349 | +| total_timesteps | 23197696 | +| train/ | | +| approx_kl | 0.013150424 | +| clip_fraction | 0.345 | +| clip_range | 0.0692 | +| entropy_loss | -6.91 | +| explained_variance | 0.342 | +| learning_rate | 4.45e-05 | +| loss | -0.0319 | +| n_updates | 61124 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000121 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1418 | +| iterations | 11328 | +| time_elapsed | 16350 | +| total_timesteps | 23199744 | +| train/ | | +| approx_kl | 0.012598904 | +| clip_fraction | 0.302 | +| clip_range | 0.0692 | +| entropy_loss | -6.02 | +| explained_variance | 0.556 | +| learning_rate | 4.45e-05 | +| loss | -0.0239 | +| n_updates | 61128 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.00024 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1418 | +| iterations | 11329 | +| time_elapsed | 16352 | +| total_timesteps | 23201792 | +| train/ | | +| approx_kl | 0.011092169 | +| clip_fraction | 0.314 | +| clip_range | 0.0692 | +| entropy_loss | -6.56 | +| explained_variance | 0.164 | +| learning_rate | 4.45e-05 | +| loss | -0.0232 | +| n_updates | 61132 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000327 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1418 | +| iterations | 11330 | +| time_elapsed | 16353 | +| total_timesteps | 23203840 | +| train/ | | +| approx_kl | 0.010739941 | +| clip_fraction | 0.332 | +| clip_range | 0.0692 | +| entropy_loss | -6.63 | +| explained_variance | 0.152 | +| learning_rate | 4.45e-05 | +| loss | -0.0327 | +| n_updates | 61136 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000194 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1418 | +| iterations | 11331 | +| time_elapsed | 16355 | +| total_timesteps | 23205888 | +| train/ | | +| approx_kl | 0.012135374 | +| clip_fraction | 0.314 | +| clip_range | 0.0692 | +| entropy_loss | -6.29 | +| explained_variance | 0.372 | +| learning_rate | 4.45e-05 | +| loss | -0.0327 | +| n_updates | 61140 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000247 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1418 | +| iterations | 11332 | +| time_elapsed | 16356 | +| total_timesteps | 23207936 | +| train/ | | +| approx_kl | 0.011805578 | +| clip_fraction | 0.338 | +| clip_range | 0.0692 | +| entropy_loss | -6.3 | +| explained_variance | 0.41 | +| learning_rate | 4.45e-05 | +| loss | -0.0354 | +| n_updates | 61144 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000198 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1418 | +| iterations | 11333 | +| time_elapsed | 16358 | +| total_timesteps | 23209984 | +| train/ | | +| approx_kl | 0.0152906515 | +| clip_fraction | 0.351 | +| clip_range | 0.0692 | +| entropy_loss | -6.63 | +| explained_variance | 0.167 | +| learning_rate | 4.45e-05 | +| loss | -0.0362 | +| n_updates | 61148 | +| policy_gradient_loss | -0.0219 | +| value_loss | 0.000104 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1418 | +| iterations | 11334 | +| time_elapsed | 16359 | +| total_timesteps | 23212032 | +| train/ | | +| approx_kl | 0.014433587 | +| clip_fraction | 0.364 | +| clip_range | 0.0692 | +| entropy_loss | -6.07 | +| explained_variance | 0.371 | +| learning_rate | 4.45e-05 | +| loss | -0.0237 | +| n_updates | 61152 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000352 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1418 | +| iterations | 11335 | +| time_elapsed | 16361 | +| total_timesteps | 23214080 | +| train/ | | +| approx_kl | 0.015103524 | +| clip_fraction | 0.363 | +| clip_range | 0.0692 | +| entropy_loss | -5.73 | +| explained_variance | 0.503 | +| learning_rate | 4.45e-05 | +| loss | -0.0355 | +| n_updates | 61156 | +| policy_gradient_loss | -0.0215 | +| value_loss | 8.64e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1418 | +| iterations | 11336 | +| time_elapsed | 16362 | +| total_timesteps | 23216128 | +| train/ | | +| approx_kl | 0.012286084 | +| clip_fraction | 0.35 | +| clip_range | 0.0692 | +| entropy_loss | -6.38 | +| explained_variance | 0.322 | +| learning_rate | 4.45e-05 | +| loss | -0.0251 | +| n_updates | 61160 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000195 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1418 | +| iterations | 11337 | +| time_elapsed | 16364 | +| total_timesteps | 23218176 | +| train/ | | +| approx_kl | 0.01232567 | +| clip_fraction | 0.346 | +| clip_range | 0.0692 | +| entropy_loss | -6 | +| explained_variance | 0.651 | +| learning_rate | 4.45e-05 | +| loss | -0.0271 | +| n_updates | 61164 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000128 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1418 | +| iterations | 11338 | +| time_elapsed | 16365 | +| total_timesteps | 23220224 | +| train/ | | +| approx_kl | 0.011756055 | +| clip_fraction | 0.339 | +| clip_range | 0.0692 | +| entropy_loss | -7.08 | +| explained_variance | -0.05 | +| learning_rate | 4.45e-05 | +| loss | -0.0283 | +| n_updates | 61168 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000193 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1418 | +| iterations | 11339 | +| time_elapsed | 16367 | +| total_timesteps | 23222272 | +| train/ | | +| approx_kl | 0.009506064 | +| clip_fraction | 0.293 | +| clip_range | 0.0692 | +| entropy_loss | -6.23 | +| explained_variance | 0.477 | +| learning_rate | 4.45e-05 | +| loss | -0.0264 | +| n_updates | 61172 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.00035 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1418 | +| iterations | 11340 | +| time_elapsed | 16368 | +| total_timesteps | 23224320 | +| train/ | | +| approx_kl | 0.010666072 | +| clip_fraction | 0.311 | +| clip_range | 0.0692 | +| entropy_loss | -6.09 | +| explained_variance | 0.208 | +| learning_rate | 4.45e-05 | +| loss | -0.027 | +| n_updates | 61176 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000264 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1418 | +| iterations | 11341 | +| time_elapsed | 16370 | +| total_timesteps | 23226368 | +| train/ | | +| approx_kl | 0.008527114 | +| clip_fraction | 0.309 | +| clip_range | 0.0692 | +| entropy_loss | -6.41 | +| explained_variance | 0.483 | +| learning_rate | 4.45e-05 | +| loss | -0.029 | +| n_updates | 61180 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000198 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1418 | +| iterations | 11342 | +| time_elapsed | 16371 | +| total_timesteps | 23228416 | +| train/ | | +| approx_kl | 0.01074168 | +| clip_fraction | 0.365 | +| clip_range | 0.0692 | +| entropy_loss | -6.65 | +| explained_variance | 0.32 | +| learning_rate | 4.45e-05 | +| loss | -0.0326 | +| n_updates | 61184 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.00013 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1418 | +| iterations | 11343 | +| time_elapsed | 16373 | +| total_timesteps | 23230464 | +| train/ | | +| approx_kl | 0.009799642 | +| clip_fraction | 0.333 | +| clip_range | 0.0692 | +| entropy_loss | -6.8 | +| explained_variance | 0.137 | +| learning_rate | 4.45e-05 | +| loss | -0.0257 | +| n_updates | 61188 | +| policy_gradient_loss | -0.0146 | +| value_loss | 0.000352 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1418 | +| iterations | 11344 | +| time_elapsed | 16374 | +| total_timesteps | 23232512 | +| train/ | | +| approx_kl | 0.01558711 | +| clip_fraction | 0.322 | +| clip_range | 0.0692 | +| entropy_loss | -5.88 | +| explained_variance | 0.576 | +| learning_rate | 4.45e-05 | +| loss | -0.0381 | +| n_updates | 61192 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000183 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1418 | +| iterations | 11345 | +| time_elapsed | 16376 | +| total_timesteps | 23234560 | +| train/ | | +| approx_kl | 0.01377124 | +| clip_fraction | 0.379 | +| clip_range | 0.0692 | +| entropy_loss | -6.46 | +| explained_variance | 0.219 | +| learning_rate | 4.45e-05 | +| loss | -0.0341 | +| n_updates | 61196 | +| policy_gradient_loss | -0.0235 | +| value_loss | 0.000121 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1418 | +| iterations | 11346 | +| time_elapsed | 16377 | +| total_timesteps | 23236608 | +| train/ | | +| approx_kl | 0.011764949 | +| clip_fraction | 0.342 | +| clip_range | 0.0692 | +| entropy_loss | -6.19 | +| explained_variance | 0.465 | +| learning_rate | 4.45e-05 | +| loss | -0.0308 | +| n_updates | 61200 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000192 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1418 | +| iterations | 11347 | +| time_elapsed | 16378 | +| total_timesteps | 23238656 | +| train/ | | +| approx_kl | 0.009731989 | +| clip_fraction | 0.314 | +| clip_range | 0.0692 | +| entropy_loss | -6.34 | +| explained_variance | 0.424 | +| learning_rate | 4.45e-05 | +| loss | -0.025 | +| n_updates | 61204 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000232 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1418 | +| iterations | 11348 | +| time_elapsed | 16380 | +| total_timesteps | 23240704 | +| train/ | | +| approx_kl | 0.012320686 | +| clip_fraction | 0.333 | +| clip_range | 0.0692 | +| entropy_loss | -6.31 | +| explained_variance | 0.559 | +| learning_rate | 4.45e-05 | +| loss | -0.0339 | +| n_updates | 61208 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000137 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1418 | +| iterations | 11349 | +| time_elapsed | 16381 | +| total_timesteps | 23242752 | +| train/ | | +| approx_kl | 0.014983408 | +| clip_fraction | 0.386 | +| clip_range | 0.0692 | +| entropy_loss | -5.78 | +| explained_variance | 0.786 | +| learning_rate | 4.45e-05 | +| loss | -0.0378 | +| n_updates | 61212 | +| policy_gradient_loss | -0.0241 | +| value_loss | 5.66e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1418 | +| iterations | 11350 | +| time_elapsed | 16383 | +| total_timesteps | 23244800 | +| train/ | | +| approx_kl | 0.013386142 | +| clip_fraction | 0.368 | +| clip_range | 0.0692 | +| entropy_loss | -6.58 | +| explained_variance | 0.0344 | +| learning_rate | 4.45e-05 | +| loss | -0.0306 | +| n_updates | 61216 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000111 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1418 | +| iterations | 11351 | +| time_elapsed | 16384 | +| total_timesteps | 23246848 | +| train/ | | +| approx_kl | 0.01263748 | +| clip_fraction | 0.336 | +| clip_range | 0.0692 | +| entropy_loss | -6.59 | +| explained_variance | 0.388 | +| learning_rate | 4.45e-05 | +| loss | -0.0271 | +| n_updates | 61220 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000166 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1418 | +| iterations | 11352 | +| time_elapsed | 16386 | +| total_timesteps | 23248896 | +| train/ | | +| approx_kl | 0.014262984 | +| clip_fraction | 0.34 | +| clip_range | 0.0692 | +| entropy_loss | -6.36 | +| explained_variance | -0.0677 | +| learning_rate | 4.45e-05 | +| loss | -0.0322 | +| n_updates | 61224 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000128 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1418 | +| iterations | 11353 | +| time_elapsed | 16387 | +| total_timesteps | 23250944 | +| train/ | | +| approx_kl | 0.01684531 | +| clip_fraction | 0.35 | +| clip_range | 0.0692 | +| entropy_loss | -6.17 | +| explained_variance | 0.523 | +| learning_rate | 4.45e-05 | +| loss | -0.0235 | +| n_updates | 61228 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000124 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1418 | +| iterations | 11354 | +| time_elapsed | 16389 | +| total_timesteps | 23252992 | +| train/ | | +| approx_kl | 0.015663588 | +| clip_fraction | 0.342 | +| clip_range | 0.0692 | +| entropy_loss | -6.44 | +| explained_variance | 0.543 | +| learning_rate | 4.45e-05 | +| loss | -0.0303 | +| n_updates | 61232 | +| policy_gradient_loss | -0.0199 | +| value_loss | 7.39e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1418 | +| iterations | 11355 | +| time_elapsed | 16390 | +| total_timesteps | 23255040 | +| train/ | | +| approx_kl | 0.010441987 | +| clip_fraction | 0.317 | +| clip_range | 0.0692 | +| entropy_loss | -6.08 | +| explained_variance | 0.629 | +| learning_rate | 4.45e-05 | +| loss | -0.0229 | +| n_updates | 61236 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000128 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1418 | +| iterations | 11356 | +| time_elapsed | 16392 | +| total_timesteps | 23257088 | +| train/ | | +| approx_kl | 0.011241569 | +| clip_fraction | 0.302 | +| clip_range | 0.0692 | +| entropy_loss | -5.51 | +| explained_variance | 0.56 | +| learning_rate | 4.45e-05 | +| loss | -0.0242 | +| n_updates | 61240 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.000284 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1418 | +| iterations | 11357 | +| time_elapsed | 16393 | +| total_timesteps | 23259136 | +| train/ | | +| approx_kl | 0.011680414 | +| clip_fraction | 0.33 | +| clip_range | 0.0692 | +| entropy_loss | -5.79 | +| explained_variance | 0.498 | +| learning_rate | 4.45e-05 | +| loss | -0.0323 | +| n_updates | 61244 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000173 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1418 | +| iterations | 11358 | +| time_elapsed | 16395 | +| total_timesteps | 23261184 | +| train/ | | +| approx_kl | 0.011171013 | +| clip_fraction | 0.331 | +| clip_range | 0.0692 | +| entropy_loss | -6.84 | +| explained_variance | -0.0581 | +| learning_rate | 4.45e-05 | +| loss | -0.0314 | +| n_updates | 61248 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000147 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1418 | +| iterations | 11359 | +| time_elapsed | 16396 | +| total_timesteps | 23263232 | +| train/ | | +| approx_kl | 0.010817349 | +| clip_fraction | 0.283 | +| clip_range | 0.0692 | +| entropy_loss | -6.85 | +| explained_variance | 0.246 | +| learning_rate | 4.45e-05 | +| loss | -0.0297 | +| n_updates | 61252 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000341 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1418 | +| iterations | 11360 | +| time_elapsed | 16398 | +| total_timesteps | 23265280 | +| train/ | | +| approx_kl | 0.015520541 | +| clip_fraction | 0.359 | +| clip_range | 0.0692 | +| entropy_loss | -6.6 | +| explained_variance | -0.174 | +| learning_rate | 4.45e-05 | +| loss | -0.0356 | +| n_updates | 61256 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000129 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1418 | +| iterations | 11361 | +| time_elapsed | 16399 | +| total_timesteps | 23267328 | +| train/ | | +| approx_kl | 0.013955687 | +| clip_fraction | 0.364 | +| clip_range | 0.0692 | +| entropy_loss | -6.41 | +| explained_variance | 0.483 | +| learning_rate | 4.45e-05 | +| loss | -0.0294 | +| n_updates | 61260 | +| policy_gradient_loss | -0.0198 | +| value_loss | 8.36e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1418 | +| iterations | 11362 | +| time_elapsed | 16401 | +| total_timesteps | 23269376 | +| train/ | | +| approx_kl | 0.01382399 | +| clip_fraction | 0.35 | +| clip_range | 0.0692 | +| entropy_loss | -6.51 | +| explained_variance | 0.335 | +| learning_rate | 4.45e-05 | +| loss | -0.0282 | +| n_updates | 61264 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000143 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1418 | +| iterations | 11363 | +| time_elapsed | 16402 | +| total_timesteps | 23271424 | +| train/ | | +| approx_kl | 0.0109161865 | +| clip_fraction | 0.341 | +| clip_range | 0.0692 | +| entropy_loss | -6.43 | +| explained_variance | 0.413 | +| learning_rate | 4.45e-05 | +| loss | -0.0289 | +| n_updates | 61268 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000201 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1418 | +| iterations | 11364 | +| time_elapsed | 16404 | +| total_timesteps | 23273472 | +| train/ | | +| approx_kl | 0.009789908 | +| clip_fraction | 0.299 | +| clip_range | 0.0692 | +| entropy_loss | -5.97 | +| explained_variance | 0.651 | +| learning_rate | 4.45e-05 | +| loss | -0.0275 | +| n_updates | 61272 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000135 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1418 | +| iterations | 11365 | +| time_elapsed | 16405 | +| total_timesteps | 23275520 | +| train/ | | +| approx_kl | 0.012288429 | +| clip_fraction | 0.308 | +| clip_range | 0.0692 | +| entropy_loss | -6.14 | +| explained_variance | 0.545 | +| learning_rate | 4.45e-05 | +| loss | -0.0316 | +| n_updates | 61276 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000144 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1418 | +| iterations | 11366 | +| time_elapsed | 16406 | +| total_timesteps | 23277568 | +| train/ | | +| approx_kl | 0.013218285 | +| clip_fraction | 0.349 | +| clip_range | 0.0692 | +| entropy_loss | -6.23 | +| explained_variance | 0.264 | +| learning_rate | 4.45e-05 | +| loss | -0.0249 | +| n_updates | 61280 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000235 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1418 | +| iterations | 11367 | +| time_elapsed | 16408 | +| total_timesteps | 23279616 | +| train/ | | +| approx_kl | 0.0148674 | +| clip_fraction | 0.393 | +| clip_range | 0.0692 | +| entropy_loss | -6.44 | +| explained_variance | 0.555 | +| learning_rate | 4.45e-05 | +| loss | -0.0274 | +| n_updates | 61284 | +| policy_gradient_loss | -0.0236 | +| value_loss | 5.63e-05 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1418 | +| iterations | 11368 | +| time_elapsed | 16409 | +| total_timesteps | 23281664 | +| train/ | | +| approx_kl | 0.012876378 | +| clip_fraction | 0.353 | +| clip_range | 0.0692 | +| entropy_loss | -6.08 | +| explained_variance | 0.676 | +| learning_rate | 4.45e-05 | +| loss | -0.0275 | +| n_updates | 61288 | +| policy_gradient_loss | -0.0189 | +| value_loss | 9.16e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1418 | +| iterations | 11369 | +| time_elapsed | 16411 | +| total_timesteps | 23283712 | +| train/ | | +| approx_kl | 0.012861546 | +| clip_fraction | 0.35 | +| clip_range | 0.0692 | +| entropy_loss | -6.5 | +| explained_variance | 0.348 | +| learning_rate | 4.45e-05 | +| loss | -0.0322 | +| n_updates | 61292 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000109 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1418 | +| iterations | 11370 | +| time_elapsed | 16412 | +| total_timesteps | 23285760 | +| train/ | | +| approx_kl | 0.012176059 | +| clip_fraction | 0.298 | +| clip_range | 0.0692 | +| entropy_loss | -6.35 | +| explained_variance | 0.38 | +| learning_rate | 4.45e-05 | +| loss | -0.0209 | +| n_updates | 61296 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000311 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1418 | +| iterations | 11371 | +| time_elapsed | 16414 | +| total_timesteps | 23287808 | +| train/ | | +| approx_kl | 0.013020271 | +| clip_fraction | 0.289 | +| clip_range | 0.0692 | +| entropy_loss | -6.06 | +| explained_variance | 0.284 | +| learning_rate | 4.45e-05 | +| loss | -0.0242 | +| n_updates | 61300 | +| policy_gradient_loss | -0.0146 | +| value_loss | 0.000427 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1418 | +| iterations | 11372 | +| time_elapsed | 16415 | +| total_timesteps | 23289856 | +| train/ | | +| approx_kl | 0.010574011 | +| clip_fraction | 0.318 | +| clip_range | 0.0692 | +| entropy_loss | -6.05 | +| explained_variance | 0.447 | +| learning_rate | 4.45e-05 | +| loss | -0.0212 | +| n_updates | 61304 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000245 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1418 | +| iterations | 11373 | +| time_elapsed | 16417 | +| total_timesteps | 23291904 | +| train/ | | +| approx_kl | 0.01314356 | +| clip_fraction | 0.307 | +| clip_range | 0.0692 | +| entropy_loss | -6.11 | +| explained_variance | 0.466 | +| learning_rate | 4.45e-05 | +| loss | -0.0274 | +| n_updates | 61308 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000261 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1418 | +| iterations | 11374 | +| time_elapsed | 16418 | +| total_timesteps | 23293952 | +| train/ | | +| approx_kl | 0.012992567 | +| clip_fraction | 0.355 | +| clip_range | 0.0692 | +| entropy_loss | -6.09 | +| explained_variance | 0.277 | +| learning_rate | 4.45e-05 | +| loss | -0.0348 | +| n_updates | 61312 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1418 | +| iterations | 11375 | +| time_elapsed | 16420 | +| total_timesteps | 23296000 | +| train/ | | +| approx_kl | 0.012365369 | +| clip_fraction | 0.348 | +| clip_range | 0.0692 | +| entropy_loss | -6.46 | +| explained_variance | 0.28 | +| learning_rate | 4.45e-05 | +| loss | -0.0359 | +| n_updates | 61316 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.00016 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1418 | +| iterations | 11376 | +| time_elapsed | 16421 | +| total_timesteps | 23298048 | +| train/ | | +| approx_kl | 0.01137216 | +| clip_fraction | 0.337 | +| clip_range | 0.0692 | +| entropy_loss | -6.42 | +| explained_variance | 0.292 | +| learning_rate | 4.45e-05 | +| loss | -0.0244 | +| n_updates | 61320 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000291 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1418 | +| iterations | 11377 | +| time_elapsed | 16423 | +| total_timesteps | 23300096 | +| train/ | | +| approx_kl | 0.013931824 | +| clip_fraction | 0.314 | +| clip_range | 0.0692 | +| entropy_loss | -6.75 | +| explained_variance | -0.0133 | +| learning_rate | 4.45e-05 | +| loss | -0.0325 | +| n_updates | 61324 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000225 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1418 | +| iterations | 11378 | +| time_elapsed | 16424 | +| total_timesteps | 23302144 | +| train/ | | +| approx_kl | 0.011217084 | +| clip_fraction | 0.333 | +| clip_range | 0.0692 | +| entropy_loss | -6.41 | +| explained_variance | 0.531 | +| learning_rate | 4.45e-05 | +| loss | -0.033 | +| n_updates | 61328 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.00014 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1418 | +| iterations | 11379 | +| time_elapsed | 16426 | +| total_timesteps | 23304192 | +| train/ | | +| approx_kl | 0.011801323 | +| clip_fraction | 0.328 | +| clip_range | 0.0692 | +| entropy_loss | -6.32 | +| explained_variance | 0.136 | +| learning_rate | 4.45e-05 | +| loss | -0.0252 | +| n_updates | 61332 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000257 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1418 | +| iterations | 11380 | +| time_elapsed | 16427 | +| total_timesteps | 23306240 | +| train/ | | +| approx_kl | 0.009221628 | +| clip_fraction | 0.295 | +| clip_range | 0.0692 | +| entropy_loss | -6.32 | +| explained_variance | 0.138 | +| learning_rate | 4.45e-05 | +| loss | -0.0216 | +| n_updates | 61336 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000404 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1418 | +| iterations | 11381 | +| time_elapsed | 16428 | +| total_timesteps | 23308288 | +| train/ | | +| approx_kl | 0.013530071 | +| clip_fraction | 0.334 | +| clip_range | 0.0692 | +| entropy_loss | -6.11 | +| explained_variance | 0.403 | +| learning_rate | 4.45e-05 | +| loss | -0.0365 | +| n_updates | 61340 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000185 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1418 | +| iterations | 11382 | +| time_elapsed | 16430 | +| total_timesteps | 23310336 | +| train/ | | +| approx_kl | 0.014359457 | +| clip_fraction | 0.334 | +| clip_range | 0.0692 | +| entropy_loss | -6.61 | +| explained_variance | -0.0191 | +| learning_rate | 4.45e-05 | +| loss | -0.029 | +| n_updates | 61344 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000187 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1418 | +| iterations | 11383 | +| time_elapsed | 16431 | +| total_timesteps | 23312384 | +| train/ | | +| approx_kl | 0.011121765 | +| clip_fraction | 0.323 | +| clip_range | 0.0692 | +| entropy_loss | -6.24 | +| explained_variance | 0.535 | +| learning_rate | 4.45e-05 | +| loss | -0.0243 | +| n_updates | 61348 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000121 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1418 | +| iterations | 11384 | +| time_elapsed | 16433 | +| total_timesteps | 23314432 | +| train/ | | +| approx_kl | 0.014560689 | +| clip_fraction | 0.346 | +| clip_range | 0.0692 | +| entropy_loss | -6.29 | +| explained_variance | 0.614 | +| learning_rate | 4.45e-05 | +| loss | -0.0323 | +| n_updates | 61352 | +| policy_gradient_loss | -0.0202 | +| value_loss | 9.34e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1418 | +| iterations | 11385 | +| time_elapsed | 16434 | +| total_timesteps | 23316480 | +| train/ | | +| approx_kl | 0.012268062 | +| clip_fraction | 0.338 | +| clip_range | 0.0692 | +| entropy_loss | -6.43 | +| explained_variance | 0.693 | +| learning_rate | 4.45e-05 | +| loss | -0.0346 | +| n_updates | 61356 | +| policy_gradient_loss | -0.0182 | +| value_loss | 8.6e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1418 | +| iterations | 11386 | +| time_elapsed | 16436 | +| total_timesteps | 23318528 | +| train/ | | +| approx_kl | 0.0126183005 | +| clip_fraction | 0.317 | +| clip_range | 0.0692 | +| entropy_loss | -6.2 | +| explained_variance | 0.483 | +| learning_rate | 4.45e-05 | +| loss | -0.0251 | +| n_updates | 61360 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000132 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1418 | +| iterations | 11387 | +| time_elapsed | 16437 | +| total_timesteps | 23320576 | +| train/ | | +| approx_kl | 0.013042778 | +| clip_fraction | 0.339 | +| clip_range | 0.0692 | +| entropy_loss | -6.52 | +| explained_variance | 0.321 | +| learning_rate | 4.45e-05 | +| loss | -0.0269 | +| n_updates | 61364 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000122 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1418 | +| iterations | 11388 | +| time_elapsed | 16439 | +| total_timesteps | 23322624 | +| train/ | | +| approx_kl | 0.014065629 | +| clip_fraction | 0.356 | +| clip_range | 0.0692 | +| entropy_loss | -6.11 | +| explained_variance | 0.505 | +| learning_rate | 4.45e-05 | +| loss | -0.0295 | +| n_updates | 61368 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000197 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1418 | +| iterations | 11389 | +| time_elapsed | 16440 | +| total_timesteps | 23324672 | +| train/ | | +| approx_kl | 0.014946272 | +| clip_fraction | 0.362 | +| clip_range | 0.0692 | +| entropy_loss | -6.36 | +| explained_variance | 0.0537 | +| learning_rate | 4.45e-05 | +| loss | -0.0337 | +| n_updates | 61372 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000181 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1418 | +| iterations | 11390 | +| time_elapsed | 16442 | +| total_timesteps | 23326720 | +| train/ | | +| approx_kl | 0.012666504 | +| clip_fraction | 0.32 | +| clip_range | 0.0692 | +| entropy_loss | -6.27 | +| explained_variance | 0.512 | +| learning_rate | 4.45e-05 | +| loss | -0.0314 | +| n_updates | 61376 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.00021 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1418 | +| iterations | 11391 | +| time_elapsed | 16443 | +| total_timesteps | 23328768 | +| train/ | | +| approx_kl | 0.013193972 | +| clip_fraction | 0.342 | +| clip_range | 0.0692 | +| entropy_loss | -6.36 | +| explained_variance | 0.306 | +| learning_rate | 4.45e-05 | +| loss | -0.0343 | +| n_updates | 61380 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000106 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1418 | +| iterations | 11392 | +| time_elapsed | 16445 | +| total_timesteps | 23330816 | +| train/ | | +| approx_kl | 0.011138691 | +| clip_fraction | 0.319 | +| clip_range | 0.0692 | +| entropy_loss | -6.19 | +| explained_variance | 0.512 | +| learning_rate | 4.45e-05 | +| loss | -0.0327 | +| n_updates | 61384 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000182 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1418 | +| iterations | 11393 | +| time_elapsed | 16446 | +| total_timesteps | 23332864 | +| train/ | | +| approx_kl | 0.013073282 | +| clip_fraction | 0.308 | +| clip_range | 0.0692 | +| entropy_loss | -5.95 | +| explained_variance | 0.357 | +| learning_rate | 4.45e-05 | +| loss | -0.0273 | +| n_updates | 61388 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000484 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1418 | +| iterations | 11394 | +| time_elapsed | 16448 | +| total_timesteps | 23334912 | +| train/ | | +| approx_kl | 0.010454113 | +| clip_fraction | 0.336 | +| clip_range | 0.0692 | +| entropy_loss | -6.13 | +| explained_variance | 0.323 | +| learning_rate | 4.45e-05 | +| loss | -0.0298 | +| n_updates | 61392 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000333 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1418 | +| iterations | 11395 | +| time_elapsed | 16449 | +| total_timesteps | 23336960 | +| train/ | | +| approx_kl | 0.0159012 | +| clip_fraction | 0.353 | +| clip_range | 0.0692 | +| entropy_loss | -6.2 | +| explained_variance | 0.197 | +| learning_rate | 4.45e-05 | +| loss | -0.0334 | +| n_updates | 61396 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000354 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1418 | +| iterations | 11396 | +| time_elapsed | 16451 | +| total_timesteps | 23339008 | +| train/ | | +| approx_kl | 0.014640091 | +| clip_fraction | 0.422 | +| clip_range | 0.0692 | +| entropy_loss | -6.56 | +| explained_variance | -0.0171 | +| learning_rate | 4.45e-05 | +| loss | -0.0419 | +| n_updates | 61400 | +| policy_gradient_loss | -0.0283 | +| value_loss | 7.26e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1418 | +| iterations | 11397 | +| time_elapsed | 16452 | +| total_timesteps | 23341056 | +| train/ | | +| approx_kl | 0.01673118 | +| clip_fraction | 0.392 | +| clip_range | 0.0692 | +| entropy_loss | -6.41 | +| explained_variance | 0.33 | +| learning_rate | 4.45e-05 | +| loss | -0.0425 | +| n_updates | 61404 | +| policy_gradient_loss | -0.025 | +| value_loss | 7.83e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1418 | +| iterations | 11398 | +| time_elapsed | 16454 | +| total_timesteps | 23343104 | +| train/ | | +| approx_kl | 0.014192516 | +| clip_fraction | 0.33 | +| clip_range | 0.0692 | +| entropy_loss | -6.4 | +| explained_variance | 0.356 | +| learning_rate | 4.45e-05 | +| loss | -0.0285 | +| n_updates | 61408 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000227 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1418 | +| iterations | 11399 | +| time_elapsed | 16455 | +| total_timesteps | 23345152 | +| train/ | | +| approx_kl | 0.015592485 | +| clip_fraction | 0.358 | +| clip_range | 0.0692 | +| entropy_loss | -5.81 | +| explained_variance | 0.499 | +| learning_rate | 4.45e-05 | +| loss | -0.0298 | +| n_updates | 61412 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000181 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1418 | +| iterations | 11400 | +| time_elapsed | 16457 | +| total_timesteps | 23347200 | +| train/ | | +| approx_kl | 0.01325716 | +| clip_fraction | 0.355 | +| clip_range | 0.0692 | +| entropy_loss | -6.55 | +| explained_variance | 0.0696 | +| learning_rate | 4.45e-05 | +| loss | -0.0334 | +| n_updates | 61416 | +| policy_gradient_loss | -0.022 | +| value_loss | 0.000118 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1418 | +| iterations | 11401 | +| time_elapsed | 16458 | +| total_timesteps | 23349248 | +| train/ | | +| approx_kl | 0.017575538 | +| clip_fraction | 0.332 | +| clip_range | 0.0692 | +| entropy_loss | -6.84 | +| explained_variance | -0.00864 | +| learning_rate | 4.45e-05 | +| loss | -0.0279 | +| n_updates | 61420 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000171 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1418 | +| iterations | 11402 | +| time_elapsed | 16460 | +| total_timesteps | 23351296 | +| train/ | | +| approx_kl | 0.012716397 | +| clip_fraction | 0.344 | +| clip_range | 0.0692 | +| entropy_loss | -5.68 | +| explained_variance | 0.792 | +| learning_rate | 4.45e-05 | +| loss | -0.0296 | +| n_updates | 61424 | +| policy_gradient_loss | -0.0177 | +| value_loss | 5.95e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1418 | +| iterations | 11403 | +| time_elapsed | 16461 | +| total_timesteps | 23353344 | +| train/ | | +| approx_kl | 0.013494523 | +| clip_fraction | 0.342 | +| clip_range | 0.0692 | +| entropy_loss | -6.52 | +| explained_variance | 0.347 | +| learning_rate | 4.45e-05 | +| loss | -0.0278 | +| n_updates | 61428 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000108 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1418 | +| iterations | 11404 | +| time_elapsed | 16463 | +| total_timesteps | 23355392 | +| train/ | | +| approx_kl | 0.015560441 | +| clip_fraction | 0.329 | +| clip_range | 0.0692 | +| entropy_loss | -6.05 | +| explained_variance | 0.552 | +| learning_rate | 4.45e-05 | +| loss | -0.0245 | +| n_updates | 61432 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000134 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1418 | +| iterations | 11405 | +| time_elapsed | 16464 | +| total_timesteps | 23357440 | +| train/ | | +| approx_kl | 0.015702197 | +| clip_fraction | 0.34 | +| clip_range | 0.0692 | +| entropy_loss | -6.31 | +| explained_variance | 0.499 | +| learning_rate | 4.45e-05 | +| loss | -0.0318 | +| n_updates | 61436 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000139 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1418 | +| iterations | 11406 | +| time_elapsed | 16466 | +| total_timesteps | 23359488 | +| train/ | | +| approx_kl | 0.013333135 | +| clip_fraction | 0.335 | +| clip_range | 0.0692 | +| entropy_loss | -6.45 | +| explained_variance | 0.349 | +| learning_rate | 4.45e-05 | +| loss | -0.0289 | +| n_updates | 61440 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000117 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1418 | +| iterations | 11407 | +| time_elapsed | 16467 | +| total_timesteps | 23361536 | +| train/ | | +| approx_kl | 0.014009794 | +| clip_fraction | 0.354 | +| clip_range | 0.0692 | +| entropy_loss | -6.64 | +| explained_variance | 0.129 | +| learning_rate | 4.45e-05 | +| loss | -0.0311 | +| n_updates | 61444 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000216 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1418 | +| iterations | 11408 | +| time_elapsed | 16469 | +| total_timesteps | 23363584 | +| train/ | | +| approx_kl | 0.013383193 | +| clip_fraction | 0.354 | +| clip_range | 0.0692 | +| entropy_loss | -6.45 | +| explained_variance | 0.494 | +| learning_rate | 4.45e-05 | +| loss | -0.0327 | +| n_updates | 61448 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000158 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1418 | +| iterations | 11409 | +| time_elapsed | 16470 | +| total_timesteps | 23365632 | +| train/ | | +| approx_kl | 0.014845489 | +| clip_fraction | 0.363 | +| clip_range | 0.0692 | +| entropy_loss | -6.65 | +| explained_variance | -0.123 | +| learning_rate | 4.45e-05 | +| loss | -0.0312 | +| n_updates | 61452 | +| policy_gradient_loss | -0.021 | +| value_loss | 9.94e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1418 | +| iterations | 11410 | +| time_elapsed | 16472 | +| total_timesteps | 23367680 | +| train/ | | +| approx_kl | 0.0120954355 | +| clip_fraction | 0.34 | +| clip_range | 0.0692 | +| entropy_loss | -6.7 | +| explained_variance | 0.431 | +| learning_rate | 4.45e-05 | +| loss | -0.0268 | +| n_updates | 61456 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000128 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1418 | +| iterations | 11411 | +| time_elapsed | 16473 | +| total_timesteps | 23369728 | +| train/ | | +| approx_kl | 0.015630249 | +| clip_fraction | 0.316 | +| clip_range | 0.0692 | +| entropy_loss | -6.61 | +| explained_variance | 0.199 | +| learning_rate | 4.45e-05 | +| loss | -0.0309 | +| n_updates | 61460 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000292 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1418 | +| iterations | 11412 | +| time_elapsed | 16475 | +| total_timesteps | 23371776 | +| train/ | | +| approx_kl | 0.014250977 | +| clip_fraction | 0.336 | +| clip_range | 0.0692 | +| entropy_loss | -5.37 | +| explained_variance | 0.539 | +| learning_rate | 4.44e-05 | +| loss | -0.0203 | +| n_updates | 61464 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.00027 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1418 | +| iterations | 11413 | +| time_elapsed | 16476 | +| total_timesteps | 23373824 | +| train/ | | +| approx_kl | 0.012117419 | +| clip_fraction | 0.327 | +| clip_range | 0.0692 | +| entropy_loss | -5.66 | +| explained_variance | 0.482 | +| learning_rate | 4.44e-05 | +| loss | -0.0228 | +| n_updates | 61468 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000188 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1418 | +| iterations | 11414 | +| time_elapsed | 16478 | +| total_timesteps | 23375872 | +| train/ | | +| approx_kl | 0.012727812 | +| clip_fraction | 0.344 | +| clip_range | 0.0692 | +| entropy_loss | -5.83 | +| explained_variance | 0.629 | +| learning_rate | 4.44e-05 | +| loss | -0.0346 | +| n_updates | 61472 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000141 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1418 | +| iterations | 11415 | +| time_elapsed | 16479 | +| total_timesteps | 23377920 | +| train/ | | +| approx_kl | 0.014877417 | +| clip_fraction | 0.379 | +| clip_range | 0.0692 | +| entropy_loss | -6.26 | +| explained_variance | 0.451 | +| learning_rate | 4.44e-05 | +| loss | -0.0382 | +| n_updates | 61476 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000139 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1418 | +| iterations | 11416 | +| time_elapsed | 16481 | +| total_timesteps | 23379968 | +| train/ | | +| approx_kl | 0.013717447 | +| clip_fraction | 0.334 | +| clip_range | 0.0692 | +| entropy_loss | -6.73 | +| explained_variance | -0.0916 | +| learning_rate | 4.44e-05 | +| loss | -0.0338 | +| n_updates | 61480 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000164 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1418 | +| iterations | 11417 | +| time_elapsed | 16482 | +| total_timesteps | 23382016 | +| train/ | | +| approx_kl | 0.012143918 | +| clip_fraction | 0.336 | +| clip_range | 0.0692 | +| entropy_loss | -6.5 | +| explained_variance | 0.31 | +| learning_rate | 4.44e-05 | +| loss | -0.0344 | +| n_updates | 61484 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000163 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1418 | +| iterations | 11418 | +| time_elapsed | 16484 | +| total_timesteps | 23384064 | +| train/ | | +| approx_kl | 0.013403912 | +| clip_fraction | 0.354 | +| clip_range | 0.0692 | +| entropy_loss | -6.45 | +| explained_variance | 0.493 | +| learning_rate | 4.44e-05 | +| loss | -0.0291 | +| n_updates | 61488 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000147 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1418 | +| iterations | 11419 | +| time_elapsed | 16485 | +| total_timesteps | 23386112 | +| train/ | | +| approx_kl | 0.010499859 | +| clip_fraction | 0.31 | +| clip_range | 0.0692 | +| entropy_loss | -6.05 | +| explained_variance | 0.512 | +| learning_rate | 4.44e-05 | +| loss | -0.029 | +| n_updates | 61492 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.000255 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1418 | +| iterations | 11420 | +| time_elapsed | 16487 | +| total_timesteps | 23388160 | +| train/ | | +| approx_kl | 0.01234643 | +| clip_fraction | 0.332 | +| clip_range | 0.0692 | +| entropy_loss | -6.43 | +| explained_variance | 0.359 | +| learning_rate | 4.44e-05 | +| loss | -0.0303 | +| n_updates | 61496 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000146 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1418 | +| iterations | 11421 | +| time_elapsed | 16488 | +| total_timesteps | 23390208 | +| train/ | | +| approx_kl | 0.011285419 | +| clip_fraction | 0.343 | +| clip_range | 0.0692 | +| entropy_loss | -6.54 | +| explained_variance | 0.0996 | +| learning_rate | 4.44e-05 | +| loss | -0.0315 | +| n_updates | 61500 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000153 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1418 | +| iterations | 11422 | +| time_elapsed | 16490 | +| total_timesteps | 23392256 | +| train/ | | +| approx_kl | 0.012129024 | +| clip_fraction | 0.315 | +| clip_range | 0.0692 | +| entropy_loss | -6.22 | +| explained_variance | 0.33 | +| learning_rate | 4.44e-05 | +| loss | -0.0221 | +| n_updates | 61504 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000184 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1418 | +| iterations | 11423 | +| time_elapsed | 16491 | +| total_timesteps | 23394304 | +| train/ | | +| approx_kl | 0.011597824 | +| clip_fraction | 0.329 | +| clip_range | 0.0692 | +| entropy_loss | -6.41 | +| explained_variance | 0.317 | +| learning_rate | 4.44e-05 | +| loss | -0.0321 | +| n_updates | 61508 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000111 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1418 | +| iterations | 11424 | +| time_elapsed | 16492 | +| total_timesteps | 23396352 | +| train/ | | +| approx_kl | 0.0144610945 | +| clip_fraction | 0.318 | +| clip_range | 0.0692 | +| entropy_loss | -6.13 | +| explained_variance | 0.452 | +| learning_rate | 4.44e-05 | +| loss | -0.0322 | +| n_updates | 61512 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000219 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1418 | +| iterations | 11425 | +| time_elapsed | 16494 | +| total_timesteps | 23398400 | +| train/ | | +| approx_kl | 0.0145519115 | +| clip_fraction | 0.341 | +| clip_range | 0.0692 | +| entropy_loss | -6.13 | +| explained_variance | 0.345 | +| learning_rate | 4.44e-05 | +| loss | -0.0248 | +| n_updates | 61516 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000299 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1418 | +| iterations | 11426 | +| time_elapsed | 16495 | +| total_timesteps | 23400448 | +| train/ | | +| approx_kl | 0.014101345 | +| clip_fraction | 0.337 | +| clip_range | 0.0692 | +| entropy_loss | -6.3 | +| explained_variance | 0.157 | +| learning_rate | 4.44e-05 | +| loss | -0.0336 | +| n_updates | 61520 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000264 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1418 | +| iterations | 11427 | +| time_elapsed | 16497 | +| total_timesteps | 23402496 | +| train/ | | +| approx_kl | 0.014762791 | +| clip_fraction | 0.348 | +| clip_range | 0.0691 | +| entropy_loss | -6.53 | +| explained_variance | 0.0135 | +| learning_rate | 4.44e-05 | +| loss | -0.0308 | +| n_updates | 61524 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000195 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1418 | +| iterations | 11428 | +| time_elapsed | 16498 | +| total_timesteps | 23404544 | +| train/ | | +| approx_kl | 0.014709232 | +| clip_fraction | 0.39 | +| clip_range | 0.0691 | +| entropy_loss | -6.28 | +| explained_variance | 0.293 | +| learning_rate | 4.44e-05 | +| loss | -0.0403 | +| n_updates | 61528 | +| policy_gradient_loss | -0.0242 | +| value_loss | 9.8e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1418 | +| iterations | 11429 | +| time_elapsed | 16500 | +| total_timesteps | 23406592 | +| train/ | | +| approx_kl | 0.014001493 | +| clip_fraction | 0.354 | +| clip_range | 0.0691 | +| entropy_loss | -6.44 | +| explained_variance | 0.274 | +| learning_rate | 4.44e-05 | +| loss | -0.0278 | +| n_updates | 61532 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000145 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1418 | +| iterations | 11430 | +| time_elapsed | 16501 | +| total_timesteps | 23408640 | +| train/ | | +| approx_kl | 0.012370374 | +| clip_fraction | 0.323 | +| clip_range | 0.0691 | +| entropy_loss | -6.42 | +| explained_variance | 0.264 | +| learning_rate | 4.44e-05 | +| loss | -0.028 | +| n_updates | 61536 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000201 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1418 | +| iterations | 11431 | +| time_elapsed | 16503 | +| total_timesteps | 23410688 | +| train/ | | +| approx_kl | 0.011767942 | +| clip_fraction | 0.328 | +| clip_range | 0.0691 | +| entropy_loss | -6.19 | +| explained_variance | 0.385 | +| learning_rate | 4.44e-05 | +| loss | -0.0264 | +| n_updates | 61540 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000267 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1418 | +| iterations | 11432 | +| time_elapsed | 16504 | +| total_timesteps | 23412736 | +| train/ | | +| approx_kl | 0.01027865 | +| clip_fraction | 0.324 | +| clip_range | 0.0691 | +| entropy_loss | -6.05 | +| explained_variance | 0.294 | +| learning_rate | 4.44e-05 | +| loss | -0.0308 | +| n_updates | 61544 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.00031 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1418 | +| iterations | 11433 | +| time_elapsed | 16506 | +| total_timesteps | 23414784 | +| train/ | | +| approx_kl | 0.012137486 | +| clip_fraction | 0.309 | +| clip_range | 0.0691 | +| entropy_loss | -5.63 | +| explained_variance | 0.603 | +| learning_rate | 4.44e-05 | +| loss | -0.0257 | +| n_updates | 61548 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000196 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1418 | +| iterations | 11434 | +| time_elapsed | 16507 | +| total_timesteps | 23416832 | +| train/ | | +| approx_kl | 0.01161543 | +| clip_fraction | 0.34 | +| clip_range | 0.0691 | +| entropy_loss | -5.6 | +| explained_variance | 0.542 | +| learning_rate | 4.44e-05 | +| loss | -0.0265 | +| n_updates | 61552 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000225 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1418 | +| iterations | 11435 | +| time_elapsed | 16509 | +| total_timesteps | 23418880 | +| train/ | | +| approx_kl | 0.012989355 | +| clip_fraction | 0.362 | +| clip_range | 0.0691 | +| entropy_loss | -6.42 | +| explained_variance | 0.263 | +| learning_rate | 4.44e-05 | +| loss | -0.0301 | +| n_updates | 61556 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000111 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1418 | +| iterations | 11436 | +| time_elapsed | 16510 | +| total_timesteps | 23420928 | +| train/ | | +| approx_kl | 0.0131003335 | +| clip_fraction | 0.344 | +| clip_range | 0.0691 | +| entropy_loss | -6.43 | +| explained_variance | 0.361 | +| learning_rate | 4.44e-05 | +| loss | -0.0349 | +| n_updates | 61560 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000165 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1418 | +| iterations | 11437 | +| time_elapsed | 16512 | +| total_timesteps | 23422976 | +| train/ | | +| approx_kl | 0.009984537 | +| clip_fraction | 0.336 | +| clip_range | 0.0691 | +| entropy_loss | -6.5 | +| explained_variance | 0.229 | +| learning_rate | 4.44e-05 | +| loss | -0.023 | +| n_updates | 61564 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000591 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1418 | +| iterations | 11438 | +| time_elapsed | 16513 | +| total_timesteps | 23425024 | +| train/ | | +| approx_kl | 0.012757532 | +| clip_fraction | 0.381 | +| clip_range | 0.0691 | +| entropy_loss | -6.61 | +| explained_variance | -0.095 | +| learning_rate | 4.44e-05 | +| loss | -0.0343 | +| n_updates | 61568 | +| policy_gradient_loss | -0.0244 | +| value_loss | 0.00012 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1418 | +| iterations | 11439 | +| time_elapsed | 16515 | +| total_timesteps | 23427072 | +| train/ | | +| approx_kl | 0.011741266 | +| clip_fraction | 0.351 | +| clip_range | 0.0691 | +| entropy_loss | -6.66 | +| explained_variance | 0.155 | +| learning_rate | 4.44e-05 | +| loss | -0.0305 | +| n_updates | 61572 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.00025 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1418 | +| iterations | 11440 | +| time_elapsed | 16516 | +| total_timesteps | 23429120 | +| train/ | | +| approx_kl | 0.012948102 | +| clip_fraction | 0.321 | +| clip_range | 0.0691 | +| entropy_loss | -6.43 | +| explained_variance | 0.314 | +| learning_rate | 4.44e-05 | +| loss | -0.026 | +| n_updates | 61576 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000202 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1418 | +| iterations | 11441 | +| time_elapsed | 16518 | +| total_timesteps | 23431168 | +| train/ | | +| approx_kl | 0.01180801 | +| clip_fraction | 0.34 | +| clip_range | 0.0691 | +| entropy_loss | -6.85 | +| explained_variance | 0.206 | +| learning_rate | 4.44e-05 | +| loss | -0.0305 | +| n_updates | 61580 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000236 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1418 | +| iterations | 11442 | +| time_elapsed | 16519 | +| total_timesteps | 23433216 | +| train/ | | +| approx_kl | 0.012109961 | +| clip_fraction | 0.338 | +| clip_range | 0.0691 | +| entropy_loss | -6.6 | +| explained_variance | 0.495 | +| learning_rate | 4.44e-05 | +| loss | -0.0301 | +| n_updates | 61584 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000164 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1418 | +| iterations | 11443 | +| time_elapsed | 16521 | +| total_timesteps | 23435264 | +| train/ | | +| approx_kl | 0.01079802 | +| clip_fraction | 0.342 | +| clip_range | 0.0691 | +| entropy_loss | -6.33 | +| explained_variance | 0.288 | +| learning_rate | 4.44e-05 | +| loss | -0.0275 | +| n_updates | 61588 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000234 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1418 | +| iterations | 11444 | +| time_elapsed | 16522 | +| total_timesteps | 23437312 | +| train/ | | +| approx_kl | 0.00964267 | +| clip_fraction | 0.317 | +| clip_range | 0.0691 | +| entropy_loss | -5.79 | +| explained_variance | 0.47 | +| learning_rate | 4.44e-05 | +| loss | -0.0252 | +| n_updates | 61592 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000258 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1418 | +| iterations | 11445 | +| time_elapsed | 16524 | +| total_timesteps | 23439360 | +| train/ | | +| approx_kl | 0.013275499 | +| clip_fraction | 0.333 | +| clip_range | 0.0691 | +| entropy_loss | -5.62 | +| explained_variance | 0.762 | +| learning_rate | 4.44e-05 | +| loss | -0.0271 | +| n_updates | 61596 | +| policy_gradient_loss | -0.0197 | +| value_loss | 8.97e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1418 | +| iterations | 11446 | +| time_elapsed | 16525 | +| total_timesteps | 23441408 | +| train/ | | +| approx_kl | 0.012271408 | +| clip_fraction | 0.354 | +| clip_range | 0.0691 | +| entropy_loss | -6.17 | +| explained_variance | 0.604 | +| learning_rate | 4.44e-05 | +| loss | -0.0333 | +| n_updates | 61600 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000132 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1418 | +| iterations | 11447 | +| time_elapsed | 16526 | +| total_timesteps | 23443456 | +| train/ | | +| approx_kl | 0.011239832 | +| clip_fraction | 0.316 | +| clip_range | 0.0691 | +| entropy_loss | -6.08 | +| explained_variance | 0.402 | +| learning_rate | 4.44e-05 | +| loss | -0.0223 | +| n_updates | 61604 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000349 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1418 | +| iterations | 11448 | +| time_elapsed | 16528 | +| total_timesteps | 23445504 | +| train/ | | +| approx_kl | 0.01482814 | +| clip_fraction | 0.377 | +| clip_range | 0.0691 | +| entropy_loss | -6.31 | +| explained_variance | 0.331 | +| learning_rate | 4.44e-05 | +| loss | -0.0359 | +| n_updates | 61608 | +| policy_gradient_loss | -0.0242 | +| value_loss | 6.68e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1418 | +| iterations | 11449 | +| time_elapsed | 16529 | +| total_timesteps | 23447552 | +| train/ | | +| approx_kl | 0.013025993 | +| clip_fraction | 0.35 | +| clip_range | 0.0691 | +| entropy_loss | -6.41 | +| explained_variance | 0.353 | +| learning_rate | 4.44e-05 | +| loss | -0.0336 | +| n_updates | 61612 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000137 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1418 | +| iterations | 11450 | +| time_elapsed | 16531 | +| total_timesteps | 23449600 | +| train/ | | +| approx_kl | 0.014899643 | +| clip_fraction | 0.342 | +| clip_range | 0.0691 | +| entropy_loss | -6.69 | +| explained_variance | -0.007 | +| learning_rate | 4.44e-05 | +| loss | -0.0309 | +| n_updates | 61616 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000102 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1418 | +| iterations | 11451 | +| time_elapsed | 16532 | +| total_timesteps | 23451648 | +| train/ | | +| approx_kl | 0.01524295 | +| clip_fraction | 0.343 | +| clip_range | 0.0691 | +| entropy_loss | -6.16 | +| explained_variance | 0.627 | +| learning_rate | 4.44e-05 | +| loss | -0.034 | +| n_updates | 61620 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000108 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1418 | +| iterations | 11452 | +| time_elapsed | 16534 | +| total_timesteps | 23453696 | +| train/ | | +| approx_kl | 0.014980458 | +| clip_fraction | 0.351 | +| clip_range | 0.0691 | +| entropy_loss | -6.09 | +| explained_variance | 0.333 | +| learning_rate | 4.44e-05 | +| loss | -0.032 | +| n_updates | 61624 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000122 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1418 | +| iterations | 11453 | +| time_elapsed | 16535 | +| total_timesteps | 23455744 | +| train/ | | +| approx_kl | 0.013023987 | +| clip_fraction | 0.34 | +| clip_range | 0.0691 | +| entropy_loss | -6.25 | +| explained_variance | 0.287 | +| learning_rate | 4.44e-05 | +| loss | -0.0312 | +| n_updates | 61628 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000154 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1418 | +| iterations | 11454 | +| time_elapsed | 16537 | +| total_timesteps | 23457792 | +| train/ | | +| approx_kl | 0.015478099 | +| clip_fraction | 0.377 | +| clip_range | 0.0691 | +| entropy_loss | -6.07 | +| explained_variance | 0.702 | +| learning_rate | 4.44e-05 | +| loss | -0.0305 | +| n_updates | 61632 | +| policy_gradient_loss | -0.0213 | +| value_loss | 8.72e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1418 | +| iterations | 11455 | +| time_elapsed | 16538 | +| total_timesteps | 23459840 | +| train/ | | +| approx_kl | 0.012128942 | +| clip_fraction | 0.317 | +| clip_range | 0.0691 | +| entropy_loss | -6.6 | +| explained_variance | 0.0416 | +| learning_rate | 4.44e-05 | +| loss | -0.0326 | +| n_updates | 61636 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000152 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1418 | +| iterations | 11456 | +| time_elapsed | 16540 | +| total_timesteps | 23461888 | +| train/ | | +| approx_kl | 0.012793134 | +| clip_fraction | 0.351 | +| clip_range | 0.0691 | +| entropy_loss | -6.59 | +| explained_variance | 0.529 | +| learning_rate | 4.44e-05 | +| loss | -0.0282 | +| n_updates | 61640 | +| policy_gradient_loss | -0.0201 | +| value_loss | 7.22e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1418 | +| iterations | 11457 | +| time_elapsed | 16541 | +| total_timesteps | 23463936 | +| train/ | | +| approx_kl | 0.014591059 | +| clip_fraction | 0.339 | +| clip_range | 0.0691 | +| entropy_loss | -6.94 | +| explained_variance | -0.149 | +| learning_rate | 4.44e-05 | +| loss | -0.0282 | +| n_updates | 61644 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000141 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1418 | +| iterations | 11458 | +| time_elapsed | 16543 | +| total_timesteps | 23465984 | +| train/ | | +| approx_kl | 0.011690345 | +| clip_fraction | 0.33 | +| clip_range | 0.0691 | +| entropy_loss | -6.01 | +| explained_variance | 0.47 | +| learning_rate | 4.44e-05 | +| loss | -0.022 | +| n_updates | 61648 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000204 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1418 | +| iterations | 11459 | +| time_elapsed | 16544 | +| total_timesteps | 23468032 | +| train/ | | +| approx_kl | 0.015004783 | +| clip_fraction | 0.377 | +| clip_range | 0.0691 | +| entropy_loss | -6.58 | +| explained_variance | -0.0377 | +| learning_rate | 4.44e-05 | +| loss | -0.0292 | +| n_updates | 61652 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000131 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1418 | +| iterations | 11460 | +| time_elapsed | 16546 | +| total_timesteps | 23470080 | +| train/ | | +| approx_kl | 0.01414476 | +| clip_fraction | 0.376 | +| clip_range | 0.0691 | +| entropy_loss | -6.51 | +| explained_variance | 0.457 | +| learning_rate | 4.44e-05 | +| loss | -0.0315 | +| n_updates | 61656 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000146 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1418 | +| iterations | 11461 | +| time_elapsed | 16547 | +| total_timesteps | 23472128 | +| train/ | | +| approx_kl | 0.013788487 | +| clip_fraction | 0.345 | +| clip_range | 0.0691 | +| entropy_loss | -6.74 | +| explained_variance | -0.12 | +| learning_rate | 4.44e-05 | +| loss | -0.0278 | +| n_updates | 61660 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000253 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1418 | +| iterations | 11462 | +| time_elapsed | 16548 | +| total_timesteps | 23474176 | +| train/ | | +| approx_kl | 0.014422186 | +| clip_fraction | 0.376 | +| clip_range | 0.0691 | +| entropy_loss | -5.93 | +| explained_variance | 0.692 | +| learning_rate | 4.44e-05 | +| loss | -0.0266 | +| n_updates | 61664 | +| policy_gradient_loss | -0.0207 | +| value_loss | 8e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1418 | +| iterations | 11463 | +| time_elapsed | 16550 | +| total_timesteps | 23476224 | +| train/ | | +| approx_kl | 0.012899011 | +| clip_fraction | 0.339 | +| clip_range | 0.0691 | +| entropy_loss | -6.47 | +| explained_variance | 0.569 | +| learning_rate | 4.44e-05 | +| loss | -0.0281 | +| n_updates | 61668 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000137 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1418 | +| iterations | 11464 | +| time_elapsed | 16551 | +| total_timesteps | 23478272 | +| train/ | | +| approx_kl | 0.013807945 | +| clip_fraction | 0.352 | +| clip_range | 0.0691 | +| entropy_loss | -6.16 | +| explained_variance | 0.59 | +| learning_rate | 4.44e-05 | +| loss | -0.0333 | +| n_updates | 61672 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000116 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1418 | +| iterations | 11465 | +| time_elapsed | 16553 | +| total_timesteps | 23480320 | +| train/ | | +| approx_kl | 0.014205952 | +| clip_fraction | 0.339 | +| clip_range | 0.0691 | +| entropy_loss | -5.91 | +| explained_variance | 0.562 | +| learning_rate | 4.44e-05 | +| loss | -0.0269 | +| n_updates | 61676 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000192 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1418 | +| iterations | 11466 | +| time_elapsed | 16554 | +| total_timesteps | 23482368 | +| train/ | | +| approx_kl | 0.012646372 | +| clip_fraction | 0.333 | +| clip_range | 0.0691 | +| entropy_loss | -6.21 | +| explained_variance | 0.556 | +| learning_rate | 4.44e-05 | +| loss | -0.0309 | +| n_updates | 61680 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000124 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1418 | +| iterations | 11467 | +| time_elapsed | 16556 | +| total_timesteps | 23484416 | +| train/ | | +| approx_kl | 0.013403267 | +| clip_fraction | 0.356 | +| clip_range | 0.0691 | +| entropy_loss | -6.27 | +| explained_variance | 0.662 | +| learning_rate | 4.44e-05 | +| loss | -0.0314 | +| n_updates | 61684 | +| policy_gradient_loss | -0.0208 | +| value_loss | 6.12e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1418 | +| iterations | 11468 | +| time_elapsed | 16557 | +| total_timesteps | 23486464 | +| train/ | | +| approx_kl | 0.011724065 | +| clip_fraction | 0.338 | +| clip_range | 0.0691 | +| entropy_loss | -6.69 | +| explained_variance | -0.102 | +| learning_rate | 4.44e-05 | +| loss | -0.0289 | +| n_updates | 61688 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000148 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1418 | +| iterations | 11469 | +| time_elapsed | 16559 | +| total_timesteps | 23488512 | +| train/ | | +| approx_kl | 0.013382377 | +| clip_fraction | 0.346 | +| clip_range | 0.0691 | +| entropy_loss | -6.97 | +| explained_variance | -0.075 | +| learning_rate | 4.44e-05 | +| loss | -0.0364 | +| n_updates | 61692 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000125 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1418 | +| iterations | 11470 | +| time_elapsed | 16560 | +| total_timesteps | 23490560 | +| train/ | | +| approx_kl | 0.011220584 | +| clip_fraction | 0.32 | +| clip_range | 0.0691 | +| entropy_loss | -6.64 | +| explained_variance | 0.33 | +| learning_rate | 4.44e-05 | +| loss | -0.0277 | +| n_updates | 61696 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000152 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1418 | +| iterations | 11471 | +| time_elapsed | 16562 | +| total_timesteps | 23492608 | +| train/ | | +| approx_kl | 0.0099161435 | +| clip_fraction | 0.346 | +| clip_range | 0.0691 | +| entropy_loss | -6.43 | +| explained_variance | 0.157 | +| learning_rate | 4.44e-05 | +| loss | -0.0236 | +| n_updates | 61700 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000344 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1418 | +| iterations | 11472 | +| time_elapsed | 16563 | +| total_timesteps | 23494656 | +| train/ | | +| approx_kl | 0.014829699 | +| clip_fraction | 0.329 | +| clip_range | 0.0691 | +| entropy_loss | -5.87 | +| explained_variance | 0.531 | +| learning_rate | 4.44e-05 | +| loss | -0.0301 | +| n_updates | 61704 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000166 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1418 | +| iterations | 11473 | +| time_elapsed | 16564 | +| total_timesteps | 23496704 | +| train/ | | +| approx_kl | 0.011824238 | +| clip_fraction | 0.337 | +| clip_range | 0.0691 | +| entropy_loss | -5.98 | +| explained_variance | 0.662 | +| learning_rate | 4.44e-05 | +| loss | -0.0304 | +| n_updates | 61708 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.00012 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1418 | +| iterations | 11474 | +| time_elapsed | 16566 | +| total_timesteps | 23498752 | +| train/ | | +| approx_kl | 0.013270453 | +| clip_fraction | 0.322 | +| clip_range | 0.0691 | +| entropy_loss | -6.09 | +| explained_variance | 0.456 | +| learning_rate | 4.44e-05 | +| loss | -0.0342 | +| n_updates | 61712 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000243 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1418 | +| iterations | 11475 | +| time_elapsed | 16567 | +| total_timesteps | 23500800 | +| train/ | | +| approx_kl | 0.013103366 | +| clip_fraction | 0.324 | +| clip_range | 0.0691 | +| entropy_loss | -6.61 | +| explained_variance | 0.339 | +| learning_rate | 4.44e-05 | +| loss | -0.0317 | +| n_updates | 61716 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000165 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1418 | +| iterations | 11476 | +| time_elapsed | 16569 | +| total_timesteps | 23502848 | +| train/ | | +| approx_kl | 0.010297905 | +| clip_fraction | 0.329 | +| clip_range | 0.0691 | +| entropy_loss | -6.56 | +| explained_variance | 0.312 | +| learning_rate | 4.44e-05 | +| loss | -0.0242 | +| n_updates | 61720 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000404 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1418 | +| iterations | 11477 | +| time_elapsed | 16570 | +| total_timesteps | 23504896 | +| train/ | | +| approx_kl | 0.016361268 | +| clip_fraction | 0.339 | +| clip_range | 0.0691 | +| entropy_loss | -6.82 | +| explained_variance | -0.168 | +| learning_rate | 4.44e-05 | +| loss | -0.0346 | +| n_updates | 61724 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000175 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1418 | +| iterations | 11478 | +| time_elapsed | 16572 | +| total_timesteps | 23506944 | +| train/ | | +| approx_kl | 0.011478569 | +| clip_fraction | 0.321 | +| clip_range | 0.0691 | +| entropy_loss | -6.3 | +| explained_variance | 0.307 | +| learning_rate | 4.44e-05 | +| loss | -0.0217 | +| n_updates | 61728 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.00049 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1418 | +| iterations | 11479 | +| time_elapsed | 16574 | +| total_timesteps | 23508992 | +| train/ | | +| approx_kl | 0.013686077 | +| clip_fraction | 0.347 | +| clip_range | 0.0691 | +| entropy_loss | -5.85 | +| explained_variance | 0.486 | +| learning_rate | 4.44e-05 | +| loss | -0.0344 | +| n_updates | 61732 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000217 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1418 | +| iterations | 11480 | +| time_elapsed | 16575 | +| total_timesteps | 23511040 | +| train/ | | +| approx_kl | 0.012503371 | +| clip_fraction | 0.328 | +| clip_range | 0.0691 | +| entropy_loss | -6.69 | +| explained_variance | -0.257 | +| learning_rate | 4.44e-05 | +| loss | -0.0356 | +| n_updates | 61736 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000143 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1418 | +| iterations | 11481 | +| time_elapsed | 16576 | +| total_timesteps | 23513088 | +| train/ | | +| approx_kl | 0.01165331 | +| clip_fraction | 0.35 | +| clip_range | 0.0691 | +| entropy_loss | -6.46 | +| explained_variance | 0.443 | +| learning_rate | 4.44e-05 | +| loss | -0.0282 | +| n_updates | 61740 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000203 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1418 | +| iterations | 11482 | +| time_elapsed | 16578 | +| total_timesteps | 23515136 | +| train/ | | +| approx_kl | 0.012871691 | +| clip_fraction | 0.338 | +| clip_range | 0.0691 | +| entropy_loss | -6.3 | +| explained_variance | 0.512 | +| learning_rate | 4.44e-05 | +| loss | -0.0257 | +| n_updates | 61744 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000189 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1418 | +| iterations | 11483 | +| time_elapsed | 16579 | +| total_timesteps | 23517184 | +| train/ | | +| approx_kl | 0.011801455 | +| clip_fraction | 0.335 | +| clip_range | 0.0691 | +| entropy_loss | -6.34 | +| explained_variance | 0.306 | +| learning_rate | 4.44e-05 | +| loss | -0.0308 | +| n_updates | 61748 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000187 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1418 | +| iterations | 11484 | +| time_elapsed | 16581 | +| total_timesteps | 23519232 | +| train/ | | +| approx_kl | 0.012834046 | +| clip_fraction | 0.311 | +| clip_range | 0.0691 | +| entropy_loss | -6.78 | +| explained_variance | 0.144 | +| learning_rate | 4.44e-05 | +| loss | -0.0286 | +| n_updates | 61752 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.00022 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1418 | +| iterations | 11485 | +| time_elapsed | 16582 | +| total_timesteps | 23521280 | +| train/ | | +| approx_kl | 0.013187075 | +| clip_fraction | 0.333 | +| clip_range | 0.0691 | +| entropy_loss | -6.7 | +| explained_variance | 0.535 | +| learning_rate | 4.44e-05 | +| loss | -0.027 | +| n_updates | 61756 | +| policy_gradient_loss | -0.0172 | +| value_loss | 9.92e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1418 | +| iterations | 11486 | +| time_elapsed | 16584 | +| total_timesteps | 23523328 | +| train/ | | +| approx_kl | 0.015322711 | +| clip_fraction | 0.339 | +| clip_range | 0.0691 | +| entropy_loss | -6.33 | +| explained_variance | 0.354 | +| learning_rate | 4.44e-05 | +| loss | -0.0324 | +| n_updates | 61760 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.00023 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1418 | +| iterations | 11487 | +| time_elapsed | 16585 | +| total_timesteps | 23525376 | +| train/ | | +| approx_kl | 0.012734538 | +| clip_fraction | 0.317 | +| clip_range | 0.0691 | +| entropy_loss | -6.1 | +| explained_variance | 0.432 | +| learning_rate | 4.44e-05 | +| loss | -0.027 | +| n_updates | 61764 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000241 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1418 | +| iterations | 11488 | +| time_elapsed | 16587 | +| total_timesteps | 23527424 | +| train/ | | +| approx_kl | 0.014761168 | +| clip_fraction | 0.352 | +| clip_range | 0.0691 | +| entropy_loss | -6.57 | +| explained_variance | 0.259 | +| learning_rate | 4.44e-05 | +| loss | -0.0314 | +| n_updates | 61768 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000186 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1418 | +| iterations | 11489 | +| time_elapsed | 16588 | +| total_timesteps | 23529472 | +| train/ | | +| approx_kl | 0.015064302 | +| clip_fraction | 0.36 | +| clip_range | 0.0691 | +| entropy_loss | -6.78 | +| explained_variance | -0.0862 | +| learning_rate | 4.44e-05 | +| loss | -0.0351 | +| n_updates | 61772 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1418 | +| iterations | 11490 | +| time_elapsed | 16590 | +| total_timesteps | 23531520 | +| train/ | | +| approx_kl | 0.013967594 | +| clip_fraction | 0.351 | +| clip_range | 0.0691 | +| entropy_loss | -6.89 | +| explained_variance | 0.0319 | +| learning_rate | 4.44e-05 | +| loss | -0.0337 | +| n_updates | 61776 | +| policy_gradient_loss | -0.0213 | +| value_loss | 9.09e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1418 | +| iterations | 11491 | +| time_elapsed | 16591 | +| total_timesteps | 23533568 | +| train/ | | +| approx_kl | 0.013310598 | +| clip_fraction | 0.36 | +| clip_range | 0.0691 | +| entropy_loss | -6.52 | +| explained_variance | 0.622 | +| learning_rate | 4.44e-05 | +| loss | -0.0371 | +| n_updates | 61780 | +| policy_gradient_loss | -0.0223 | +| value_loss | 6.17e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1418 | +| iterations | 11492 | +| time_elapsed | 16593 | +| total_timesteps | 23535616 | +| train/ | | +| approx_kl | 0.01570011 | +| clip_fraction | 0.326 | +| clip_range | 0.0691 | +| entropy_loss | -6.7 | +| explained_variance | 0.425 | +| learning_rate | 4.44e-05 | +| loss | -0.0251 | +| n_updates | 61784 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.00011 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1418 | +| iterations | 11493 | +| time_elapsed | 16594 | +| total_timesteps | 23537664 | +| train/ | | +| approx_kl | 0.014857681 | +| clip_fraction | 0.337 | +| clip_range | 0.0691 | +| entropy_loss | -5.89 | +| explained_variance | 0.558 | +| learning_rate | 4.44e-05 | +| loss | -0.0268 | +| n_updates | 61788 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000208 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1418 | +| iterations | 11494 | +| time_elapsed | 16596 | +| total_timesteps | 23539712 | +| train/ | | +| approx_kl | 0.013515424 | +| clip_fraction | 0.32 | +| clip_range | 0.0691 | +| entropy_loss | -5.97 | +| explained_variance | 0.395 | +| learning_rate | 4.44e-05 | +| loss | -0.0251 | +| n_updates | 61792 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000306 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1418 | +| iterations | 11495 | +| time_elapsed | 16597 | +| total_timesteps | 23541760 | +| train/ | | +| approx_kl | 0.01100475 | +| clip_fraction | 0.326 | +| clip_range | 0.0691 | +| entropy_loss | -6.1 | +| explained_variance | 0.344 | +| learning_rate | 4.44e-05 | +| loss | -0.026 | +| n_updates | 61796 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000203 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1418 | +| iterations | 11496 | +| time_elapsed | 16599 | +| total_timesteps | 23543808 | +| train/ | | +| approx_kl | 0.010049649 | +| clip_fraction | 0.359 | +| clip_range | 0.0691 | +| entropy_loss | -6.15 | +| explained_variance | 0.559 | +| learning_rate | 4.44e-05 | +| loss | -0.0357 | +| n_updates | 61800 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000148 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1418 | +| iterations | 11497 | +| time_elapsed | 16600 | +| total_timesteps | 23545856 | +| train/ | | +| approx_kl | 0.012731943 | +| clip_fraction | 0.351 | +| clip_range | 0.0691 | +| entropy_loss | -6.68 | +| explained_variance | 0.356 | +| learning_rate | 4.44e-05 | +| loss | -0.0374 | +| n_updates | 61804 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000123 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1418 | +| iterations | 11498 | +| time_elapsed | 16602 | +| total_timesteps | 23547904 | +| train/ | | +| approx_kl | 0.014449722 | +| clip_fraction | 0.334 | +| clip_range | 0.0691 | +| entropy_loss | -7.04 | +| explained_variance | -0.118 | +| learning_rate | 4.44e-05 | +| loss | -0.0315 | +| n_updates | 61808 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000198 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1418 | +| iterations | 11499 | +| time_elapsed | 16603 | +| total_timesteps | 23549952 | +| train/ | | +| approx_kl | 0.012072893 | +| clip_fraction | 0.334 | +| clip_range | 0.0691 | +| entropy_loss | -6.93 | +| explained_variance | 0.196 | +| learning_rate | 4.44e-05 | +| loss | -0.0296 | +| n_updates | 61812 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000221 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1418 | +| iterations | 11500 | +| time_elapsed | 16605 | +| total_timesteps | 23552000 | +| train/ | | +| approx_kl | 0.011870379 | +| clip_fraction | 0.354 | +| clip_range | 0.0691 | +| entropy_loss | -6.75 | +| explained_variance | 0.0703 | +| learning_rate | 4.44e-05 | +| loss | -0.0339 | +| n_updates | 61816 | +| policy_gradient_loss | -0.021 | +| value_loss | 9.84e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1418 | +| iterations | 11501 | +| time_elapsed | 16606 | +| total_timesteps | 23554048 | +| train/ | | +| approx_kl | 0.013711659 | +| clip_fraction | 0.344 | +| clip_range | 0.0691 | +| entropy_loss | -6.35 | +| explained_variance | 0.399 | +| learning_rate | 4.44e-05 | +| loss | -0.0282 | +| n_updates | 61820 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000182 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1418 | +| iterations | 11502 | +| time_elapsed | 16608 | +| total_timesteps | 23556096 | +| train/ | | +| approx_kl | 0.013092478 | +| clip_fraction | 0.327 | +| clip_range | 0.0691 | +| entropy_loss | -6.56 | +| explained_variance | 0.445 | +| learning_rate | 4.44e-05 | +| loss | -0.0307 | +| n_updates | 61824 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000187 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1418 | +| iterations | 11503 | +| time_elapsed | 16609 | +| total_timesteps | 23558144 | +| train/ | | +| approx_kl | 0.012587599 | +| clip_fraction | 0.339 | +| clip_range | 0.0691 | +| entropy_loss | -6.26 | +| explained_variance | 0.509 | +| learning_rate | 4.44e-05 | +| loss | -0.0329 | +| n_updates | 61828 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000128 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1418 | +| iterations | 11504 | +| time_elapsed | 16611 | +| total_timesteps | 23560192 | +| train/ | | +| approx_kl | 0.013276409 | +| clip_fraction | 0.337 | +| clip_range | 0.0691 | +| entropy_loss | -6.32 | +| explained_variance | 0.641 | +| learning_rate | 4.44e-05 | +| loss | -0.0282 | +| n_updates | 61832 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000109 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1418 | +| iterations | 11505 | +| time_elapsed | 16612 | +| total_timesteps | 23562240 | +| train/ | | +| approx_kl | 0.013732305 | +| clip_fraction | 0.324 | +| clip_range | 0.0691 | +| entropy_loss | -6.21 | +| explained_variance | 0.642 | +| learning_rate | 4.44e-05 | +| loss | -0.0271 | +| n_updates | 61836 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000137 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1418 | +| iterations | 11506 | +| time_elapsed | 16614 | +| total_timesteps | 23564288 | +| train/ | | +| approx_kl | 0.010990782 | +| clip_fraction | 0.325 | +| clip_range | 0.0691 | +| entropy_loss | -6.51 | +| explained_variance | 0.447 | +| learning_rate | 4.44e-05 | +| loss | -0.0331 | +| n_updates | 61840 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000106 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1418 | +| iterations | 11507 | +| time_elapsed | 16615 | +| total_timesteps | 23566336 | +| train/ | | +| approx_kl | 0.008864056 | +| clip_fraction | 0.291 | +| clip_range | 0.0691 | +| entropy_loss | -6.59 | +| explained_variance | 0.201 | +| learning_rate | 4.44e-05 | +| loss | -0.021 | +| n_updates | 61844 | +| policy_gradient_loss | -0.0144 | +| value_loss | 0.000491 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1418 | +| iterations | 11508 | +| time_elapsed | 16617 | +| total_timesteps | 23568384 | +| train/ | | +| approx_kl | 0.01216243 | +| clip_fraction | 0.334 | +| clip_range | 0.0691 | +| entropy_loss | -6.13 | +| explained_variance | 0.516 | +| learning_rate | 4.44e-05 | +| loss | -0.0279 | +| n_updates | 61848 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000159 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1418 | +| iterations | 11509 | +| time_elapsed | 16618 | +| total_timesteps | 23570432 | +| train/ | | +| approx_kl | 0.01150188 | +| clip_fraction | 0.331 | +| clip_range | 0.0691 | +| entropy_loss | -6.4 | +| explained_variance | 0.335 | +| learning_rate | 4.44e-05 | +| loss | -0.0269 | +| n_updates | 61852 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000336 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1418 | +| iterations | 11510 | +| time_elapsed | 16619 | +| total_timesteps | 23572480 | +| train/ | | +| approx_kl | 0.012616681 | +| clip_fraction | 0.371 | +| clip_range | 0.0691 | +| entropy_loss | -6.33 | +| explained_variance | 0.568 | +| learning_rate | 4.44e-05 | +| loss | -0.0413 | +| n_updates | 61856 | +| policy_gradient_loss | -0.0251 | +| value_loss | 6.4e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1418 | +| iterations | 11511 | +| time_elapsed | 16621 | +| total_timesteps | 23574528 | +| train/ | | +| approx_kl | 0.0146162165 | +| clip_fraction | 0.37 | +| clip_range | 0.0691 | +| entropy_loss | -6.95 | +| explained_variance | -0.602 | +| learning_rate | 4.44e-05 | +| loss | -0.0402 | +| n_updates | 61860 | +| policy_gradient_loss | -0.0235 | +| value_loss | 5.3e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1418 | +| iterations | 11512 | +| time_elapsed | 16622 | +| total_timesteps | 23576576 | +| train/ | | +| approx_kl | 0.012833836 | +| clip_fraction | 0.312 | +| clip_range | 0.0691 | +| entropy_loss | -6.35 | +| explained_variance | 0.41 | +| learning_rate | 4.44e-05 | +| loss | -0.0297 | +| n_updates | 61864 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000276 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1418 | +| iterations | 11513 | +| time_elapsed | 16624 | +| total_timesteps | 23578624 | +| train/ | | +| approx_kl | 0.011833265 | +| clip_fraction | 0.324 | +| clip_range | 0.0691 | +| entropy_loss | -6.65 | +| explained_variance | -0.147 | +| learning_rate | 4.44e-05 | +| loss | -0.0346 | +| n_updates | 61868 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000156 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1418 | +| iterations | 11514 | +| time_elapsed | 16625 | +| total_timesteps | 23580672 | +| train/ | | +| approx_kl | 0.013074503 | +| clip_fraction | 0.368 | +| clip_range | 0.0691 | +| entropy_loss | -6.31 | +| explained_variance | 0.534 | +| learning_rate | 4.44e-05 | +| loss | -0.0306 | +| n_updates | 61872 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000156 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1418 | +| iterations | 11515 | +| time_elapsed | 16627 | +| total_timesteps | 23582720 | +| train/ | | +| approx_kl | 0.013772251 | +| clip_fraction | 0.333 | +| clip_range | 0.0691 | +| entropy_loss | -6.25 | +| explained_variance | 0.479 | +| learning_rate | 4.44e-05 | +| loss | -0.0325 | +| n_updates | 61876 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000174 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1418 | +| iterations | 11516 | +| time_elapsed | 16628 | +| total_timesteps | 23584768 | +| train/ | | +| approx_kl | 0.011381188 | +| clip_fraction | 0.347 | +| clip_range | 0.0691 | +| entropy_loss | -6.74 | +| explained_variance | 0.347 | +| learning_rate | 4.44e-05 | +| loss | -0.0402 | +| n_updates | 61880 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000104 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1418 | +| iterations | 11517 | +| time_elapsed | 16630 | +| total_timesteps | 23586816 | +| train/ | | +| approx_kl | 0.01185574 | +| clip_fraction | 0.333 | +| clip_range | 0.0691 | +| entropy_loss | -6.58 | +| explained_variance | 0.335 | +| learning_rate | 4.44e-05 | +| loss | -0.0315 | +| n_updates | 61884 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000204 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1418 | +| iterations | 11518 | +| time_elapsed | 16631 | +| total_timesteps | 23588864 | +| train/ | | +| approx_kl | 0.011732962 | +| clip_fraction | 0.354 | +| clip_range | 0.0691 | +| entropy_loss | -6.7 | +| explained_variance | 0.0527 | +| learning_rate | 4.44e-05 | +| loss | -0.0347 | +| n_updates | 61888 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000124 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1418 | +| iterations | 11519 | +| time_elapsed | 16633 | +| total_timesteps | 23590912 | +| train/ | | +| approx_kl | 0.010371122 | +| clip_fraction | 0.315 | +| clip_range | 0.0691 | +| entropy_loss | -6.06 | +| explained_variance | 0.755 | +| learning_rate | 4.44e-05 | +| loss | -0.0248 | +| n_updates | 61892 | +| policy_gradient_loss | -0.0175 | +| value_loss | 9.34e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1418 | +| iterations | 11520 | +| time_elapsed | 16634 | +| total_timesteps | 23592960 | +| train/ | | +| approx_kl | 0.013851607 | +| clip_fraction | 0.296 | +| clip_range | 0.0691 | +| entropy_loss | -5.91 | +| explained_variance | 0.49 | +| learning_rate | 4.44e-05 | +| loss | -0.0255 | +| n_updates | 61896 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000164 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1418 | +| iterations | 11521 | +| time_elapsed | 16636 | +| total_timesteps | 23595008 | +| train/ | | +| approx_kl | 0.010978368 | +| clip_fraction | 0.336 | +| clip_range | 0.0691 | +| entropy_loss | -6.85 | +| explained_variance | 0.206 | +| learning_rate | 4.44e-05 | +| loss | -0.0282 | +| n_updates | 61900 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000139 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1418 | +| iterations | 11522 | +| time_elapsed | 16637 | +| total_timesteps | 23597056 | +| train/ | | +| approx_kl | 0.0104185175 | +| clip_fraction | 0.311 | +| clip_range | 0.0691 | +| entropy_loss | -6.37 | +| explained_variance | 0.475 | +| learning_rate | 4.44e-05 | +| loss | -0.0198 | +| n_updates | 61904 | +| policy_gradient_loss | -0.0147 | +| value_loss | 0.000262 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1418 | +| iterations | 11523 | +| time_elapsed | 16639 | +| total_timesteps | 23599104 | +| train/ | | +| approx_kl | 0.014031062 | +| clip_fraction | 0.323 | +| clip_range | 0.0691 | +| entropy_loss | -5.6 | +| explained_variance | 0.374 | +| learning_rate | 4.44e-05 | +| loss | -0.035 | +| n_updates | 61908 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000187 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1418 | +| iterations | 11524 | +| time_elapsed | 16640 | +| total_timesteps | 23601152 | +| train/ | | +| approx_kl | 0.011446785 | +| clip_fraction | 0.334 | +| clip_range | 0.0691 | +| entropy_loss | -6.15 | +| explained_variance | 0.356 | +| learning_rate | 4.44e-05 | +| loss | -0.0316 | +| n_updates | 61912 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000208 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1418 | +| iterations | 11525 | +| time_elapsed | 16642 | +| total_timesteps | 23603200 | +| train/ | | +| approx_kl | 0.012842065 | +| clip_fraction | 0.35 | +| clip_range | 0.0691 | +| entropy_loss | -6.43 | +| explained_variance | 0.46 | +| learning_rate | 4.44e-05 | +| loss | -0.029 | +| n_updates | 61916 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000141 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1418 | +| iterations | 11526 | +| time_elapsed | 16643 | +| total_timesteps | 23605248 | +| train/ | | +| approx_kl | 0.012331786 | +| clip_fraction | 0.321 | +| clip_range | 0.0691 | +| entropy_loss | -6.7 | +| explained_variance | 0.349 | +| learning_rate | 4.44e-05 | +| loss | -0.031 | +| n_updates | 61920 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000123 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1418 | +| iterations | 11527 | +| time_elapsed | 16645 | +| total_timesteps | 23607296 | +| train/ | | +| approx_kl | 0.014218932 | +| clip_fraction | 0.329 | +| clip_range | 0.0691 | +| entropy_loss | -6.5 | +| explained_variance | 0.191 | +| learning_rate | 4.44e-05 | +| loss | -0.0238 | +| n_updates | 61924 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000229 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1418 | +| iterations | 11528 | +| time_elapsed | 16646 | +| total_timesteps | 23609344 | +| train/ | | +| approx_kl | 0.011502866 | +| clip_fraction | 0.31 | +| clip_range | 0.0691 | +| entropy_loss | -6.86 | +| explained_variance | -0.142 | +| learning_rate | 4.44e-05 | +| loss | -0.0271 | +| n_updates | 61928 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.00021 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1418 | +| iterations | 11529 | +| time_elapsed | 16648 | +| total_timesteps | 23611392 | +| train/ | | +| approx_kl | 0.014496822 | +| clip_fraction | 0.321 | +| clip_range | 0.0691 | +| entropy_loss | -6.58 | +| explained_variance | 0.282 | +| learning_rate | 4.44e-05 | +| loss | -0.0266 | +| n_updates | 61932 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000305 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1418 | +| iterations | 11530 | +| time_elapsed | 16649 | +| total_timesteps | 23613440 | +| train/ | | +| approx_kl | 0.01013972 | +| clip_fraction | 0.304 | +| clip_range | 0.0691 | +| entropy_loss | -6.72 | +| explained_variance | 0.15 | +| learning_rate | 4.44e-05 | +| loss | -0.03 | +| n_updates | 61936 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000237 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1418 | +| iterations | 11531 | +| time_elapsed | 16651 | +| total_timesteps | 23615488 | +| train/ | | +| approx_kl | 0.009516908 | +| clip_fraction | 0.314 | +| clip_range | 0.0691 | +| entropy_loss | -6.72 | +| explained_variance | 0.519 | +| learning_rate | 4.44e-05 | +| loss | -0.0351 | +| n_updates | 61940 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000141 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1418 | +| iterations | 11532 | +| time_elapsed | 16652 | +| total_timesteps | 23617536 | +| train/ | | +| approx_kl | 0.012582131 | +| clip_fraction | 0.33 | +| clip_range | 0.0691 | +| entropy_loss | -6.31 | +| explained_variance | 0.618 | +| learning_rate | 4.44e-05 | +| loss | -0.0304 | +| n_updates | 61944 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000109 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1418 | +| iterations | 11533 | +| time_elapsed | 16654 | +| total_timesteps | 23619584 | +| train/ | | +| approx_kl | 0.012039917 | +| clip_fraction | 0.32 | +| clip_range | 0.0691 | +| entropy_loss | -6.22 | +| explained_variance | 0.443 | +| learning_rate | 4.44e-05 | +| loss | -0.0239 | +| n_updates | 61948 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000167 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1418 | +| iterations | 11534 | +| time_elapsed | 16655 | +| total_timesteps | 23621632 | +| train/ | | +| approx_kl | 0.01206234 | +| clip_fraction | 0.334 | +| clip_range | 0.0691 | +| entropy_loss | -6.28 | +| explained_variance | 0.358 | +| learning_rate | 4.44e-05 | +| loss | -0.0256 | +| n_updates | 61952 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000162 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1418 | +| iterations | 11535 | +| time_elapsed | 16657 | +| total_timesteps | 23623680 | +| train/ | | +| approx_kl | 0.013022674 | +| clip_fraction | 0.339 | +| clip_range | 0.0691 | +| entropy_loss | -6.97 | +| explained_variance | 0.16 | +| learning_rate | 4.44e-05 | +| loss | -0.0309 | +| n_updates | 61956 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000103 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1418 | +| iterations | 11536 | +| time_elapsed | 16658 | +| total_timesteps | 23625728 | +| train/ | | +| approx_kl | 0.015076345 | +| clip_fraction | 0.38 | +| clip_range | 0.0691 | +| entropy_loss | -6.85 | +| explained_variance | -0.235 | +| learning_rate | 4.44e-05 | +| loss | -0.0334 | +| n_updates | 61960 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000104 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1418 | +| iterations | 11537 | +| time_elapsed | 16660 | +| total_timesteps | 23627776 | +| train/ | | +| approx_kl | 0.012729645 | +| clip_fraction | 0.318 | +| clip_range | 0.0691 | +| entropy_loss | -6.22 | +| explained_variance | 0.775 | +| learning_rate | 4.44e-05 | +| loss | -0.0285 | +| n_updates | 61964 | +| policy_gradient_loss | -0.0177 | +| value_loss | 6.09e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1418 | +| iterations | 11538 | +| time_elapsed | 16661 | +| total_timesteps | 23629824 | +| train/ | | +| approx_kl | 0.011609184 | +| clip_fraction | 0.312 | +| clip_range | 0.0691 | +| entropy_loss | -6.39 | +| explained_variance | 0.404 | +| learning_rate | 4.44e-05 | +| loss | -0.0289 | +| n_updates | 61968 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000201 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1418 | +| iterations | 11539 | +| time_elapsed | 16663 | +| total_timesteps | 23631872 | +| train/ | | +| approx_kl | 0.013203088 | +| clip_fraction | 0.33 | +| clip_range | 0.0691 | +| entropy_loss | -6.08 | +| explained_variance | 0.73 | +| learning_rate | 4.44e-05 | +| loss | -0.0269 | +| n_updates | 61972 | +| policy_gradient_loss | -0.0177 | +| value_loss | 9.09e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1418 | +| iterations | 11540 | +| time_elapsed | 16664 | +| total_timesteps | 23633920 | +| train/ | | +| approx_kl | 0.012915274 | +| clip_fraction | 0.333 | +| clip_range | 0.0691 | +| entropy_loss | -6.13 | +| explained_variance | 0.766 | +| learning_rate | 4.44e-05 | +| loss | -0.0311 | +| n_updates | 61976 | +| policy_gradient_loss | -0.0193 | +| value_loss | 9.01e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1418 | +| iterations | 11541 | +| time_elapsed | 16666 | +| total_timesteps | 23635968 | +| train/ | | +| approx_kl | 0.0110771265 | +| clip_fraction | 0.329 | +| clip_range | 0.0691 | +| entropy_loss | -6.34 | +| explained_variance | 0.231 | +| learning_rate | 4.44e-05 | +| loss | -0.0292 | +| n_updates | 61980 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000229 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1418 | +| iterations | 11542 | +| time_elapsed | 16667 | +| total_timesteps | 23638016 | +| train/ | | +| approx_kl | 0.012352228 | +| clip_fraction | 0.343 | +| clip_range | 0.0691 | +| entropy_loss | -6.67 | +| explained_variance | 0.184 | +| learning_rate | 4.44e-05 | +| loss | -0.0318 | +| n_updates | 61984 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000196 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1418 | +| iterations | 11543 | +| time_elapsed | 16669 | +| total_timesteps | 23640064 | +| train/ | | +| approx_kl | 0.0101873465 | +| clip_fraction | 0.287 | +| clip_range | 0.0691 | +| entropy_loss | -6.44 | +| explained_variance | 0.277 | +| learning_rate | 4.44e-05 | +| loss | -0.0205 | +| n_updates | 61988 | +| policy_gradient_loss | -0.0142 | +| value_loss | 0.000384 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1418 | +| iterations | 11544 | +| time_elapsed | 16670 | +| total_timesteps | 23642112 | +| train/ | | +| approx_kl | 0.012623512 | +| clip_fraction | 0.323 | +| clip_range | 0.0691 | +| entropy_loss | -6.45 | +| explained_variance | 0.256 | +| learning_rate | 4.44e-05 | +| loss | -0.0332 | +| n_updates | 61992 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000235 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1418 | +| iterations | 11545 | +| time_elapsed | 16671 | +| total_timesteps | 23644160 | +| train/ | | +| approx_kl | 0.012067859 | +| clip_fraction | 0.355 | +| clip_range | 0.0691 | +| entropy_loss | -6.7 | +| explained_variance | 0.193 | +| learning_rate | 4.44e-05 | +| loss | -0.0316 | +| n_updates | 61996 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000193 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1418 | +| iterations | 11546 | +| time_elapsed | 16673 | +| total_timesteps | 23646208 | +| train/ | | +| approx_kl | 0.010199424 | +| clip_fraction | 0.312 | +| clip_range | 0.0691 | +| entropy_loss | -6.48 | +| explained_variance | 0.337 | +| learning_rate | 4.44e-05 | +| loss | -0.0255 | +| n_updates | 62000 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000381 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1418 | +| iterations | 11547 | +| time_elapsed | 16674 | +| total_timesteps | 23648256 | +| train/ | | +| approx_kl | 0.0136003615 | +| clip_fraction | 0.338 | +| clip_range | 0.0691 | +| entropy_loss | -5.97 | +| explained_variance | 0.436 | +| learning_rate | 4.44e-05 | +| loss | -0.0273 | +| n_updates | 62004 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.00017 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1418 | +| iterations | 11548 | +| time_elapsed | 16676 | +| total_timesteps | 23650304 | +| train/ | | +| approx_kl | 0.012563682 | +| clip_fraction | 0.363 | +| clip_range | 0.0691 | +| entropy_loss | -6.43 | +| explained_variance | 0.227 | +| learning_rate | 4.44e-05 | +| loss | -0.0399 | +| n_updates | 62008 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000136 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1418 | +| iterations | 11549 | +| time_elapsed | 16677 | +| total_timesteps | 23652352 | +| train/ | | +| approx_kl | 0.014022328 | +| clip_fraction | 0.314 | +| clip_range | 0.0691 | +| entropy_loss | -6.44 | +| explained_variance | 0.415 | +| learning_rate | 4.44e-05 | +| loss | -0.032 | +| n_updates | 62012 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000236 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1418 | +| iterations | 11550 | +| time_elapsed | 16679 | +| total_timesteps | 23654400 | +| train/ | | +| approx_kl | 0.012894573 | +| clip_fraction | 0.326 | +| clip_range | 0.0691 | +| entropy_loss | -6.12 | +| explained_variance | 0.581 | +| learning_rate | 4.44e-05 | +| loss | -0.0341 | +| n_updates | 62016 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1418 | +| iterations | 11551 | +| time_elapsed | 16680 | +| total_timesteps | 23656448 | +| train/ | | +| approx_kl | 0.012143891 | +| clip_fraction | 0.311 | +| clip_range | 0.0691 | +| entropy_loss | -6.57 | +| explained_variance | 0.321 | +| learning_rate | 4.44e-05 | +| loss | -0.0298 | +| n_updates | 62020 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.00013 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1418 | +| iterations | 11552 | +| time_elapsed | 16682 | +| total_timesteps | 23658496 | +| train/ | | +| approx_kl | 0.011812588 | +| clip_fraction | 0.304 | +| clip_range | 0.0691 | +| entropy_loss | -6.66 | +| explained_variance | 0.309 | +| learning_rate | 4.44e-05 | +| loss | -0.0249 | +| n_updates | 62024 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000287 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1418 | +| iterations | 11553 | +| time_elapsed | 16683 | +| total_timesteps | 23660544 | +| train/ | | +| approx_kl | 0.012882097 | +| clip_fraction | 0.347 | +| clip_range | 0.0691 | +| entropy_loss | -6.24 | +| explained_variance | 0.637 | +| learning_rate | 4.44e-05 | +| loss | -0.034 | +| n_updates | 62028 | +| policy_gradient_loss | -0.0213 | +| value_loss | 8.33e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1418 | +| iterations | 11554 | +| time_elapsed | 16685 | +| total_timesteps | 23662592 | +| train/ | | +| approx_kl | 0.01208244 | +| clip_fraction | 0.337 | +| clip_range | 0.0691 | +| entropy_loss | -6.79 | +| explained_variance | 0.081 | +| learning_rate | 4.44e-05 | +| loss | -0.0284 | +| n_updates | 62032 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000163 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1418 | +| iterations | 11555 | +| time_elapsed | 16686 | +| total_timesteps | 23664640 | +| train/ | | +| approx_kl | 0.012511982 | +| clip_fraction | 0.343 | +| clip_range | 0.0691 | +| entropy_loss | -6.55 | +| explained_variance | 0.199 | +| learning_rate | 4.44e-05 | +| loss | -0.0247 | +| n_updates | 62036 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.000235 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1418 | +| iterations | 11556 | +| time_elapsed | 16688 | +| total_timesteps | 23666688 | +| train/ | | +| approx_kl | 0.01669254 | +| clip_fraction | 0.335 | +| clip_range | 0.0691 | +| entropy_loss | -6.02 | +| explained_variance | 0.534 | +| learning_rate | 4.44e-05 | +| loss | -0.0315 | +| n_updates | 62040 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000232 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1418 | +| iterations | 11557 | +| time_elapsed | 16689 | +| total_timesteps | 23668736 | +| train/ | | +| approx_kl | 0.011966538 | +| clip_fraction | 0.326 | +| clip_range | 0.0691 | +| entropy_loss | -6.05 | +| explained_variance | 0.346 | +| learning_rate | 4.44e-05 | +| loss | -0.0313 | +| n_updates | 62044 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000175 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1418 | +| iterations | 11558 | +| time_elapsed | 16691 | +| total_timesteps | 23670784 | +| train/ | | +| approx_kl | 0.014379527 | +| clip_fraction | 0.342 | +| clip_range | 0.0691 | +| entropy_loss | -5.92 | +| explained_variance | 0.634 | +| learning_rate | 4.44e-05 | +| loss | -0.029 | +| n_updates | 62048 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000146 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1418 | +| iterations | 11559 | +| time_elapsed | 16692 | +| total_timesteps | 23672832 | +| train/ | | +| approx_kl | 0.013983073 | +| clip_fraction | 0.325 | +| clip_range | 0.0691 | +| entropy_loss | -6.19 | +| explained_variance | 0.368 | +| learning_rate | 4.44e-05 | +| loss | -0.027 | +| n_updates | 62052 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000217 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1418 | +| iterations | 11560 | +| time_elapsed | 16694 | +| total_timesteps | 23674880 | +| train/ | | +| approx_kl | 0.010351826 | +| clip_fraction | 0.305 | +| clip_range | 0.0691 | +| entropy_loss | -6.32 | +| explained_variance | 0.312 | +| learning_rate | 4.44e-05 | +| loss | -0.0257 | +| n_updates | 62056 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000311 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1418 | +| iterations | 11561 | +| time_elapsed | 16695 | +| total_timesteps | 23676928 | +| train/ | | +| approx_kl | 0.014333143 | +| clip_fraction | 0.358 | +| clip_range | 0.0691 | +| entropy_loss | -6.79 | +| explained_variance | 0.0389 | +| learning_rate | 4.44e-05 | +| loss | -0.031 | +| n_updates | 62060 | +| policy_gradient_loss | -0.0224 | +| value_loss | 0.000195 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1418 | +| iterations | 11562 | +| time_elapsed | 16697 | +| total_timesteps | 23678976 | +| train/ | | +| approx_kl | 0.010846304 | +| clip_fraction | 0.323 | +| clip_range | 0.0691 | +| entropy_loss | -6.81 | +| explained_variance | 0.25 | +| learning_rate | 4.44e-05 | +| loss | -0.0306 | +| n_updates | 62064 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000178 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1418 | +| iterations | 11563 | +| time_elapsed | 16698 | +| total_timesteps | 23681024 | +| train/ | | +| approx_kl | 0.014280638 | +| clip_fraction | 0.379 | +| clip_range | 0.0691 | +| entropy_loss | -6.59 | +| explained_variance | 0.6 | +| learning_rate | 4.44e-05 | +| loss | -0.0417 | +| n_updates | 62068 | +| policy_gradient_loss | -0.0251 | +| value_loss | 6.99e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1418 | +| iterations | 11564 | +| time_elapsed | 16699 | +| total_timesteps | 23683072 | +| train/ | | +| approx_kl | 0.0123597095 | +| clip_fraction | 0.338 | +| clip_range | 0.0691 | +| entropy_loss | -6.73 | +| explained_variance | 0.255 | +| learning_rate | 4.44e-05 | +| loss | -0.0367 | +| n_updates | 62072 | +| policy_gradient_loss | -0.0211 | +| value_loss | 9.78e-05 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1418 | +| iterations | 11565 | +| time_elapsed | 16701 | +| total_timesteps | 23685120 | +| train/ | | +| approx_kl | 0.0125168245 | +| clip_fraction | 0.323 | +| clip_range | 0.0691 | +| entropy_loss | -5.96 | +| explained_variance | 0.497 | +| learning_rate | 4.44e-05 | +| loss | -0.0297 | +| n_updates | 62076 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000264 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1418 | +| iterations | 11566 | +| time_elapsed | 16702 | +| total_timesteps | 23687168 | +| train/ | | +| approx_kl | 0.011489336 | +| clip_fraction | 0.341 | +| clip_range | 0.0691 | +| entropy_loss | -6.19 | +| explained_variance | 0.349 | +| learning_rate | 4.44e-05 | +| loss | -0.0359 | +| n_updates | 62080 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.00015 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1418 | +| iterations | 11567 | +| time_elapsed | 16704 | +| total_timesteps | 23689216 | +| train/ | | +| approx_kl | 0.019390259 | +| clip_fraction | 0.331 | +| clip_range | 0.0691 | +| entropy_loss | -6.21 | +| explained_variance | 0.474 | +| learning_rate | 4.44e-05 | +| loss | -0.0328 | +| n_updates | 62084 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000161 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1418 | +| iterations | 11568 | +| time_elapsed | 16705 | +| total_timesteps | 23691264 | +| train/ | | +| approx_kl | 0.013283834 | +| clip_fraction | 0.343 | +| clip_range | 0.0691 | +| entropy_loss | -6.25 | +| explained_variance | 0.525 | +| learning_rate | 4.44e-05 | +| loss | -0.0304 | +| n_updates | 62088 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000139 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1418 | +| iterations | 11569 | +| time_elapsed | 16707 | +| total_timesteps | 23693312 | +| train/ | | +| approx_kl | 0.01443853 | +| clip_fraction | 0.34 | +| clip_range | 0.0691 | +| entropy_loss | -6.75 | +| explained_variance | -0.0981 | +| learning_rate | 4.44e-05 | +| loss | -0.0282 | +| n_updates | 62092 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000134 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1418 | +| iterations | 11570 | +| time_elapsed | 16708 | +| total_timesteps | 23695360 | +| train/ | | +| approx_kl | 0.015225599 | +| clip_fraction | 0.375 | +| clip_range | 0.0691 | +| entropy_loss | -6.15 | +| explained_variance | 0.636 | +| learning_rate | 4.44e-05 | +| loss | -0.0382 | +| n_updates | 62096 | +| policy_gradient_loss | -0.0237 | +| value_loss | 7.63e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1418 | +| iterations | 11571 | +| time_elapsed | 16710 | +| total_timesteps | 23697408 | +| train/ | | +| approx_kl | 0.014142846 | +| clip_fraction | 0.346 | +| clip_range | 0.0691 | +| entropy_loss | -6.01 | +| explained_variance | 0.53 | +| learning_rate | 4.44e-05 | +| loss | -0.0315 | +| n_updates | 62100 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000149 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1418 | +| iterations | 11572 | +| time_elapsed | 16711 | +| total_timesteps | 23699456 | +| train/ | | +| approx_kl | 0.015872179 | +| clip_fraction | 0.351 | +| clip_range | 0.0691 | +| entropy_loss | -6.18 | +| explained_variance | 0.351 | +| learning_rate | 4.44e-05 | +| loss | -0.0313 | +| n_updates | 62104 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000149 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1418 | +| iterations | 11573 | +| time_elapsed | 16713 | +| total_timesteps | 23701504 | +| train/ | | +| approx_kl | 0.011568813 | +| clip_fraction | 0.325 | +| clip_range | 0.0691 | +| entropy_loss | -6.92 | +| explained_variance | 0.144 | +| learning_rate | 4.44e-05 | +| loss | -0.0262 | +| n_updates | 62108 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000203 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1418 | +| iterations | 11574 | +| time_elapsed | 16714 | +| total_timesteps | 23703552 | +| train/ | | +| approx_kl | 0.013714067 | +| clip_fraction | 0.373 | +| clip_range | 0.0691 | +| entropy_loss | -6.63 | +| explained_variance | 0.249 | +| learning_rate | 4.44e-05 | +| loss | -0.0356 | +| n_updates | 62112 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.0001 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1418 | +| iterations | 11575 | +| time_elapsed | 16715 | +| total_timesteps | 23705600 | +| train/ | | +| approx_kl | 0.014800142 | +| clip_fraction | 0.337 | +| clip_range | 0.0691 | +| entropy_loss | -6.21 | +| explained_variance | 0.339 | +| learning_rate | 4.44e-05 | +| loss | -0.0242 | +| n_updates | 62116 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000253 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1418 | +| iterations | 11576 | +| time_elapsed | 16717 | +| total_timesteps | 23707648 | +| train/ | | +| approx_kl | 0.014491709 | +| clip_fraction | 0.317 | +| clip_range | 0.0691 | +| entropy_loss | -6.09 | +| explained_variance | 0.314 | +| learning_rate | 4.44e-05 | +| loss | -0.0206 | +| n_updates | 62120 | +| policy_gradient_loss | -0.014 | +| value_loss | 0.000319 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1418 | +| iterations | 11577 | +| time_elapsed | 16718 | +| total_timesteps | 23709696 | +| train/ | | +| approx_kl | 0.014311505 | +| clip_fraction | 0.334 | +| clip_range | 0.0691 | +| entropy_loss | -5.98 | +| explained_variance | 0.441 | +| learning_rate | 4.44e-05 | +| loss | -0.0297 | +| n_updates | 62124 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000213 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1418 | +| iterations | 11578 | +| time_elapsed | 16720 | +| total_timesteps | 23711744 | +| train/ | | +| approx_kl | 0.011441981 | +| clip_fraction | 0.312 | +| clip_range | 0.0691 | +| entropy_loss | -6.11 | +| explained_variance | 0.442 | +| learning_rate | 4.44e-05 | +| loss | -0.0329 | +| n_updates | 62128 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000228 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1418 | +| iterations | 11579 | +| time_elapsed | 16721 | +| total_timesteps | 23713792 | +| train/ | | +| approx_kl | 0.012751532 | +| clip_fraction | 0.361 | +| clip_range | 0.0691 | +| entropy_loss | -6.26 | +| explained_variance | 0.344 | +| learning_rate | 4.44e-05 | +| loss | -0.0356 | +| n_updates | 62132 | +| policy_gradient_loss | -0.0217 | +| value_loss | 9.39e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1418 | +| iterations | 11580 | +| time_elapsed | 16723 | +| total_timesteps | 23715840 | +| train/ | | +| approx_kl | 0.011924901 | +| clip_fraction | 0.328 | +| clip_range | 0.0691 | +| entropy_loss | -6.63 | +| explained_variance | 0.125 | +| learning_rate | 4.44e-05 | +| loss | -0.0321 | +| n_updates | 62136 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000471 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1418 | +| iterations | 11581 | +| time_elapsed | 16724 | +| total_timesteps | 23717888 | +| train/ | | +| approx_kl | 0.01322844 | +| clip_fraction | 0.355 | +| clip_range | 0.0691 | +| entropy_loss | -6.61 | +| explained_variance | 0.205 | +| learning_rate | 4.44e-05 | +| loss | -0.0357 | +| n_updates | 62140 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000161 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1418 | +| iterations | 11582 | +| time_elapsed | 16726 | +| total_timesteps | 23719936 | +| train/ | | +| approx_kl | 0.01052036 | +| clip_fraction | 0.347 | +| clip_range | 0.0691 | +| entropy_loss | -6.6 | +| explained_variance | 0.314 | +| learning_rate | 4.44e-05 | +| loss | -0.0293 | +| n_updates | 62144 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000302 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1418 | +| iterations | 11583 | +| time_elapsed | 16727 | +| total_timesteps | 23721984 | +| train/ | | +| approx_kl | 0.009264361 | +| clip_fraction | 0.313 | +| clip_range | 0.0691 | +| entropy_loss | -6.55 | +| explained_variance | 0.296 | +| learning_rate | 4.44e-05 | +| loss | -0.0333 | +| n_updates | 62148 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000156 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1418 | +| iterations | 11584 | +| time_elapsed | 16729 | +| total_timesteps | 23724032 | +| train/ | | +| approx_kl | 0.010970467 | +| clip_fraction | 0.313 | +| clip_range | 0.0691 | +| entropy_loss | -6.47 | +| explained_variance | 0.367 | +| learning_rate | 4.44e-05 | +| loss | -0.0328 | +| n_updates | 62152 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000258 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1418 | +| iterations | 11585 | +| time_elapsed | 16730 | +| total_timesteps | 23726080 | +| train/ | | +| approx_kl | 0.0125997495 | +| clip_fraction | 0.361 | +| clip_range | 0.0691 | +| entropy_loss | -6.92 | +| explained_variance | -0.372 | +| learning_rate | 4.44e-05 | +| loss | -0.0416 | +| n_updates | 62156 | +| policy_gradient_loss | -0.0247 | +| value_loss | 5.57e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1418 | +| iterations | 11586 | +| time_elapsed | 16732 | +| total_timesteps | 23728128 | +| train/ | | +| approx_kl | 0.009830479 | +| clip_fraction | 0.318 | +| clip_range | 0.0691 | +| entropy_loss | -6.36 | +| explained_variance | 0.414 | +| learning_rate | 4.44e-05 | +| loss | -0.0279 | +| n_updates | 62160 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000243 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1418 | +| iterations | 11587 | +| time_elapsed | 16733 | +| total_timesteps | 23730176 | +| train/ | | +| approx_kl | 0.015985345 | +| clip_fraction | 0.343 | +| clip_range | 0.0691 | +| entropy_loss | -5.82 | +| explained_variance | 0.503 | +| learning_rate | 4.44e-05 | +| loss | -0.0113 | +| n_updates | 62164 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000149 | +----------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1418 | +| iterations | 11588 | +| time_elapsed | 16735 | +| total_timesteps | 23732224 | +| train/ | | +| approx_kl | 0.012104 | +| clip_fraction | 0.331 | +| clip_range | 0.0691 | +| entropy_loss | -6.49 | +| explained_variance | 0.459 | +| learning_rate | 4.44e-05 | +| loss | -0.0307 | +| n_updates | 62168 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000134 | +-------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1418 | +| iterations | 11589 | +| time_elapsed | 16736 | +| total_timesteps | 23734272 | +| train/ | | +| approx_kl | 0.011749968 | +| clip_fraction | 0.336 | +| clip_range | 0.0691 | +| entropy_loss | -6.56 | +| explained_variance | 0.461 | +| learning_rate | 4.44e-05 | +| loss | -0.0361 | +| n_updates | 62172 | +| policy_gradient_loss | -0.0206 | +| value_loss | 9.54e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1418 | +| iterations | 11590 | +| time_elapsed | 16738 | +| total_timesteps | 23736320 | +| train/ | | +| approx_kl | 0.013598569 | +| clip_fraction | 0.324 | +| clip_range | 0.0691 | +| entropy_loss | -6.22 | +| explained_variance | 0.543 | +| learning_rate | 4.44e-05 | +| loss | -0.0269 | +| n_updates | 62176 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000199 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1418 | +| iterations | 11591 | +| time_elapsed | 16739 | +| total_timesteps | 23738368 | +| train/ | | +| approx_kl | 0.014073812 | +| clip_fraction | 0.363 | +| clip_range | 0.0691 | +| entropy_loss | -6.91 | +| explained_variance | 0.169 | +| learning_rate | 4.44e-05 | +| loss | -0.0325 | +| n_updates | 62180 | +| policy_gradient_loss | -0.0215 | +| value_loss | 8.68e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1418 | +| iterations | 11592 | +| time_elapsed | 16740 | +| total_timesteps | 23740416 | +| train/ | | +| approx_kl | 0.012187049 | +| clip_fraction | 0.335 | +| clip_range | 0.0691 | +| entropy_loss | -6.56 | +| explained_variance | 0.443 | +| learning_rate | 4.44e-05 | +| loss | -0.023 | +| n_updates | 62184 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000152 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1418 | +| iterations | 11593 | +| time_elapsed | 16742 | +| total_timesteps | 23742464 | +| train/ | | +| approx_kl | 0.012640571 | +| clip_fraction | 0.321 | +| clip_range | 0.0691 | +| entropy_loss | -6.86 | +| explained_variance | 0.0626 | +| learning_rate | 4.44e-05 | +| loss | -0.0198 | +| n_updates | 62188 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000172 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1418 | +| iterations | 11594 | +| time_elapsed | 16743 | +| total_timesteps | 23744512 | +| train/ | | +| approx_kl | 0.011503863 | +| clip_fraction | 0.316 | +| clip_range | 0.0691 | +| entropy_loss | -6.53 | +| explained_variance | 0.251 | +| learning_rate | 4.44e-05 | +| loss | -0.0295 | +| n_updates | 62192 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000323 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1418 | +| iterations | 11595 | +| time_elapsed | 16745 | +| total_timesteps | 23746560 | +| train/ | | +| approx_kl | 0.011163294 | +| clip_fraction | 0.315 | +| clip_range | 0.0691 | +| entropy_loss | -6.83 | +| explained_variance | -0.115 | +| learning_rate | 4.44e-05 | +| loss | -0.0335 | +| n_updates | 62196 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000136 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.384 | +| time/ | | +| fps | 1418 | +| iterations | 11596 | +| time_elapsed | 16746 | +| total_timesteps | 23748608 | +| train/ | | +| approx_kl | 0.016074924 | +| clip_fraction | 0.336 | +| clip_range | 0.0691 | +| entropy_loss | -6.58 | +| explained_variance | 0.479 | +| learning_rate | 4.44e-05 | +| loss | -0.0308 | +| n_updates | 62200 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000168 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.385 | +| time/ | | +| fps | 1418 | +| iterations | 11597 | +| time_elapsed | 16748 | +| total_timesteps | 23750656 | +| train/ | | +| approx_kl | 0.013377054 | +| clip_fraction | 0.305 | +| clip_range | 0.0691 | +| entropy_loss | -6.04 | +| explained_variance | 0.249 | +| learning_rate | 4.44e-05 | +| loss | -0.0253 | +| n_updates | 62204 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000391 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1418 | +| iterations | 11598 | +| time_elapsed | 16749 | +| total_timesteps | 23752704 | +| train/ | | +| approx_kl | 0.0129122995 | +| clip_fraction | 0.355 | +| clip_range | 0.0691 | +| entropy_loss | -6.52 | +| explained_variance | 0.227 | +| learning_rate | 4.44e-05 | +| loss | -0.0343 | +| n_updates | 62208 | +| policy_gradient_loss | -0.0221 | +| value_loss | 0.000137 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1418 | +| iterations | 11599 | +| time_elapsed | 16751 | +| total_timesteps | 23754752 | +| train/ | | +| approx_kl | 0.01300743 | +| clip_fraction | 0.352 | +| clip_range | 0.0691 | +| entropy_loss | -6.38 | +| explained_variance | 0.734 | +| learning_rate | 4.44e-05 | +| loss | -0.028 | +| n_updates | 62212 | +| policy_gradient_loss | -0.0209 | +| value_loss | 7.52e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1418 | +| iterations | 11600 | +| time_elapsed | 16752 | +| total_timesteps | 23756800 | +| train/ | | +| approx_kl | 0.014840849 | +| clip_fraction | 0.344 | +| clip_range | 0.0691 | +| entropy_loss | -5.93 | +| explained_variance | 0.685 | +| learning_rate | 4.44e-05 | +| loss | -0.0281 | +| n_updates | 62216 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000108 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1418 | +| iterations | 11601 | +| time_elapsed | 16754 | +| total_timesteps | 23758848 | +| train/ | | +| approx_kl | 0.012246382 | +| clip_fraction | 0.302 | +| clip_range | 0.0691 | +| entropy_loss | -6.49 | +| explained_variance | 0.315 | +| learning_rate | 4.44e-05 | +| loss | -0.0379 | +| n_updates | 62220 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000198 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1418 | +| iterations | 11602 | +| time_elapsed | 16755 | +| total_timesteps | 23760896 | +| train/ | | +| approx_kl | 0.011749187 | +| clip_fraction | 0.336 | +| clip_range | 0.0691 | +| entropy_loss | -6.32 | +| explained_variance | 0.609 | +| learning_rate | 4.44e-05 | +| loss | -0.0365 | +| n_updates | 62224 | +| policy_gradient_loss | -0.0207 | +| value_loss | 7.49e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1418 | +| iterations | 11603 | +| time_elapsed | 16757 | +| total_timesteps | 23762944 | +| train/ | | +| approx_kl | 0.010592605 | +| clip_fraction | 0.328 | +| clip_range | 0.0691 | +| entropy_loss | -6.67 | +| explained_variance | 0.425 | +| learning_rate | 4.44e-05 | +| loss | -0.028 | +| n_updates | 62228 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000169 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1418 | +| iterations | 11604 | +| time_elapsed | 16758 | +| total_timesteps | 23764992 | +| train/ | | +| approx_kl | 0.01247233 | +| clip_fraction | 0.343 | +| clip_range | 0.0691 | +| entropy_loss | -6 | +| explained_variance | 0.577 | +| learning_rate | 4.44e-05 | +| loss | -0.0239 | +| n_updates | 62232 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000219 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1418 | +| iterations | 11605 | +| time_elapsed | 16760 | +| total_timesteps | 23767040 | +| train/ | | +| approx_kl | 0.012126042 | +| clip_fraction | 0.338 | +| clip_range | 0.0691 | +| entropy_loss | -6.15 | +| explained_variance | 0.394 | +| learning_rate | 4.44e-05 | +| loss | -0.0341 | +| n_updates | 62236 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000256 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1418 | +| iterations | 11606 | +| time_elapsed | 16761 | +| total_timesteps | 23769088 | +| train/ | | +| approx_kl | 0.014393769 | +| clip_fraction | 0.355 | +| clip_range | 0.0691 | +| entropy_loss | -6.74 | +| explained_variance | -0.0212 | +| learning_rate | 4.44e-05 | +| loss | -0.0348 | +| n_updates | 62240 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1418 | +| iterations | 11607 | +| time_elapsed | 16763 | +| total_timesteps | 23771136 | +| train/ | | +| approx_kl | 0.013317648 | +| clip_fraction | 0.358 | +| clip_range | 0.0691 | +| entropy_loss | -6.96 | +| explained_variance | 0.413 | +| learning_rate | 4.44e-05 | +| loss | -0.0313 | +| n_updates | 62244 | +| policy_gradient_loss | -0.0229 | +| value_loss | 6.69e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1418 | +| iterations | 11608 | +| time_elapsed | 16764 | +| total_timesteps | 23773184 | +| train/ | | +| approx_kl | 0.011833824 | +| clip_fraction | 0.302 | +| clip_range | 0.0691 | +| entropy_loss | -6.49 | +| explained_variance | 0.417 | +| learning_rate | 4.44e-05 | +| loss | -0.029 | +| n_updates | 62248 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000273 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1418 | +| iterations | 11609 | +| time_elapsed | 16765 | +| total_timesteps | 23775232 | +| train/ | | +| approx_kl | 0.013613145 | +| clip_fraction | 0.335 | +| clip_range | 0.0691 | +| entropy_loss | -6.09 | +| explained_variance | 0.548 | +| learning_rate | 4.44e-05 | +| loss | -0.0291 | +| n_updates | 62252 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000123 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1418 | +| iterations | 11610 | +| time_elapsed | 16767 | +| total_timesteps | 23777280 | +| train/ | | +| approx_kl | 0.01431193 | +| clip_fraction | 0.338 | +| clip_range | 0.0691 | +| entropy_loss | -6.41 | +| explained_variance | -0.0174 | +| learning_rate | 4.44e-05 | +| loss | -0.0316 | +| n_updates | 62256 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000134 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1418 | +| iterations | 11611 | +| time_elapsed | 16768 | +| total_timesteps | 23779328 | +| train/ | | +| approx_kl | 0.013467146 | +| clip_fraction | 0.336 | +| clip_range | 0.0691 | +| entropy_loss | -6.62 | +| explained_variance | 0.107 | +| learning_rate | 4.44e-05 | +| loss | -0.0301 | +| n_updates | 62260 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000226 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1418 | +| iterations | 11612 | +| time_elapsed | 16770 | +| total_timesteps | 23781376 | +| train/ | | +| approx_kl | 0.012548232 | +| clip_fraction | 0.334 | +| clip_range | 0.0691 | +| entropy_loss | -6.24 | +| explained_variance | 0.655 | +| learning_rate | 4.44e-05 | +| loss | -0.0246 | +| n_updates | 62264 | +| policy_gradient_loss | -0.0176 | +| value_loss | 9.4e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1418 | +| iterations | 11613 | +| time_elapsed | 16771 | +| total_timesteps | 23783424 | +| train/ | | +| approx_kl | 0.016539272 | +| clip_fraction | 0.351 | +| clip_range | 0.0691 | +| entropy_loss | -6.24 | +| explained_variance | 0.274 | +| learning_rate | 4.44e-05 | +| loss | -0.0294 | +| n_updates | 62268 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000122 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1418 | +| iterations | 11614 | +| time_elapsed | 16773 | +| total_timesteps | 23785472 | +| train/ | | +| approx_kl | 0.011796974 | +| clip_fraction | 0.323 | +| clip_range | 0.0691 | +| entropy_loss | -7 | +| explained_variance | 0.0588 | +| learning_rate | 4.44e-05 | +| loss | -0.0318 | +| n_updates | 62272 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000137 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1418 | +| iterations | 11615 | +| time_elapsed | 16774 | +| total_timesteps | 23787520 | +| train/ | | +| approx_kl | 0.012652977 | +| clip_fraction | 0.327 | +| clip_range | 0.0691 | +| entropy_loss | -6.3 | +| explained_variance | 0.257 | +| learning_rate | 4.44e-05 | +| loss | -0.0264 | +| n_updates | 62276 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000346 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1418 | +| iterations | 11616 | +| time_elapsed | 16776 | +| total_timesteps | 23789568 | +| train/ | | +| approx_kl | 0.013592616 | +| clip_fraction | 0.361 | +| clip_range | 0.0691 | +| entropy_loss | -6.37 | +| explained_variance | 0.136 | +| learning_rate | 4.44e-05 | +| loss | -0.0335 | +| n_updates | 62280 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000212 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1418 | +| iterations | 11617 | +| time_elapsed | 16777 | +| total_timesteps | 23791616 | +| train/ | | +| approx_kl | 0.014222459 | +| clip_fraction | 0.356 | +| clip_range | 0.0691 | +| entropy_loss | -6.24 | +| explained_variance | 0.697 | +| learning_rate | 4.43e-05 | +| loss | -0.0392 | +| n_updates | 62284 | +| policy_gradient_loss | -0.0213 | +| value_loss | 8.95e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1418 | +| iterations | 11618 | +| time_elapsed | 16779 | +| total_timesteps | 23793664 | +| train/ | | +| approx_kl | 0.0129665695 | +| clip_fraction | 0.336 | +| clip_range | 0.0691 | +| entropy_loss | -5.84 | +| explained_variance | 0.541 | +| learning_rate | 4.43e-05 | +| loss | -0.0215 | +| n_updates | 62288 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.00019 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1418 | +| iterations | 11619 | +| time_elapsed | 16780 | +| total_timesteps | 23795712 | +| train/ | | +| approx_kl | 0.014490995 | +| clip_fraction | 0.325 | +| clip_range | 0.0691 | +| entropy_loss | -5.58 | +| explained_variance | 0.757 | +| learning_rate | 4.43e-05 | +| loss | -0.032 | +| n_updates | 62292 | +| policy_gradient_loss | -0.0194 | +| value_loss | 8.67e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1418 | +| iterations | 11620 | +| time_elapsed | 16782 | +| total_timesteps | 23797760 | +| train/ | | +| approx_kl | 0.014636065 | +| clip_fraction | 0.335 | +| clip_range | 0.0691 | +| entropy_loss | -6.47 | +| explained_variance | -0.382 | +| learning_rate | 4.43e-05 | +| loss | -0.0305 | +| n_updates | 62296 | +| policy_gradient_loss | -0.0197 | +| value_loss | 8.68e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1418 | +| iterations | 11621 | +| time_elapsed | 16783 | +| total_timesteps | 23799808 | +| train/ | | +| approx_kl | 0.01359443 | +| clip_fraction | 0.338 | +| clip_range | 0.0691 | +| entropy_loss | -6.12 | +| explained_variance | 0.612 | +| learning_rate | 4.43e-05 | +| loss | -0.0281 | +| n_updates | 62300 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000124 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1418 | +| iterations | 11622 | +| time_elapsed | 16785 | +| total_timesteps | 23801856 | +| train/ | | +| approx_kl | 0.013233007 | +| clip_fraction | 0.358 | +| clip_range | 0.0691 | +| entropy_loss | -6.48 | +| explained_variance | 0.49 | +| learning_rate | 4.43e-05 | +| loss | -0.0378 | +| n_updates | 62304 | +| policy_gradient_loss | -0.0212 | +| value_loss | 7.26e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1418 | +| iterations | 11623 | +| time_elapsed | 16786 | +| total_timesteps | 23803904 | +| train/ | | +| approx_kl | 0.016170308 | +| clip_fraction | 0.323 | +| clip_range | 0.069 | +| entropy_loss | -6.88 | +| explained_variance | -0.0121 | +| learning_rate | 4.43e-05 | +| loss | -0.0264 | +| n_updates | 62308 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000149 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1418 | +| iterations | 11624 | +| time_elapsed | 16788 | +| total_timesteps | 23805952 | +| train/ | | +| approx_kl | 0.016256671 | +| clip_fraction | 0.341 | +| clip_range | 0.069 | +| entropy_loss | -6.44 | +| explained_variance | 0.426 | +| learning_rate | 4.43e-05 | +| loss | -0.0345 | +| n_updates | 62312 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000147 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1418 | +| iterations | 11625 | +| time_elapsed | 16789 | +| total_timesteps | 23808000 | +| train/ | | +| approx_kl | 0.014463627 | +| clip_fraction | 0.358 | +| clip_range | 0.069 | +| entropy_loss | -6.49 | +| explained_variance | 0.449 | +| learning_rate | 4.43e-05 | +| loss | -0.0262 | +| n_updates | 62316 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000178 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1417 | +| iterations | 11626 | +| time_elapsed | 16791 | +| total_timesteps | 23810048 | +| train/ | | +| approx_kl | 0.01345174 | +| clip_fraction | 0.354 | +| clip_range | 0.069 | +| entropy_loss | -6.67 | +| explained_variance | -0.133 | +| learning_rate | 4.43e-05 | +| loss | -0.0269 | +| n_updates | 62320 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000111 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1417 | +| iterations | 11627 | +| time_elapsed | 16792 | +| total_timesteps | 23812096 | +| train/ | | +| approx_kl | 0.011070022 | +| clip_fraction | 0.32 | +| clip_range | 0.069 | +| entropy_loss | -6.36 | +| explained_variance | 0.31 | +| learning_rate | 4.43e-05 | +| loss | -0.0209 | +| n_updates | 62324 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000396 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1417 | +| iterations | 11628 | +| time_elapsed | 16794 | +| total_timesteps | 23814144 | +| train/ | | +| approx_kl | 0.01593206 | +| clip_fraction | 0.367 | +| clip_range | 0.069 | +| entropy_loss | -5.77 | +| explained_variance | 0.635 | +| learning_rate | 4.43e-05 | +| loss | -0.0335 | +| n_updates | 62328 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000117 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1417 | +| iterations | 11629 | +| time_elapsed | 16795 | +| total_timesteps | 23816192 | +| train/ | | +| approx_kl | 0.015523009 | +| clip_fraction | 0.367 | +| clip_range | 0.069 | +| entropy_loss | -6.63 | +| explained_variance | 0.355 | +| learning_rate | 4.43e-05 | +| loss | -0.0293 | +| n_updates | 62332 | +| policy_gradient_loss | -0.0221 | +| value_loss | 9.55e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1417 | +| iterations | 11630 | +| time_elapsed | 16797 | +| total_timesteps | 23818240 | +| train/ | | +| approx_kl | 0.01192232 | +| clip_fraction | 0.357 | +| clip_range | 0.069 | +| entropy_loss | -6.86 | +| explained_variance | 0.0385 | +| learning_rate | 4.43e-05 | +| loss | -0.0254 | +| n_updates | 62336 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000175 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1417 | +| iterations | 11631 | +| time_elapsed | 16798 | +| total_timesteps | 23820288 | +| train/ | | +| approx_kl | 0.012286751 | +| clip_fraction | 0.326 | +| clip_range | 0.069 | +| entropy_loss | -6.36 | +| explained_variance | 0.343 | +| learning_rate | 4.43e-05 | +| loss | -0.0241 | +| n_updates | 62340 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000392 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1417 | +| iterations | 11632 | +| time_elapsed | 16800 | +| total_timesteps | 23822336 | +| train/ | | +| approx_kl | 0.011003529 | +| clip_fraction | 0.314 | +| clip_range | 0.069 | +| entropy_loss | -6.36 | +| explained_variance | 0.388 | +| learning_rate | 4.43e-05 | +| loss | -0.0259 | +| n_updates | 62344 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000218 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1417 | +| iterations | 11633 | +| time_elapsed | 16802 | +| total_timesteps | 23824384 | +| train/ | | +| approx_kl | 0.012523812 | +| clip_fraction | 0.331 | +| clip_range | 0.069 | +| entropy_loss | -6.37 | +| explained_variance | 0.524 | +| learning_rate | 4.43e-05 | +| loss | -0.0341 | +| n_updates | 62348 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000145 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1417 | +| iterations | 11634 | +| time_elapsed | 16803 | +| total_timesteps | 23826432 | +| train/ | | +| approx_kl | 0.011113547 | +| clip_fraction | 0.336 | +| clip_range | 0.069 | +| entropy_loss | -6.56 | +| explained_variance | 0.489 | +| learning_rate | 4.43e-05 | +| loss | -0.0298 | +| n_updates | 62352 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000164 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1417 | +| iterations | 11635 | +| time_elapsed | 16805 | +| total_timesteps | 23828480 | +| train/ | | +| approx_kl | 0.012238619 | +| clip_fraction | 0.328 | +| clip_range | 0.069 | +| entropy_loss | -5.83 | +| explained_variance | 0.607 | +| learning_rate | 4.43e-05 | +| loss | -0.0245 | +| n_updates | 62356 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000211 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1417 | +| iterations | 11636 | +| time_elapsed | 16806 | +| total_timesteps | 23830528 | +| train/ | | +| approx_kl | 0.013736371 | +| clip_fraction | 0.37 | +| clip_range | 0.069 | +| entropy_loss | -6.45 | +| explained_variance | 0.0694 | +| learning_rate | 4.43e-05 | +| loss | -0.0347 | +| n_updates | 62360 | +| policy_gradient_loss | -0.0222 | +| value_loss | 9.4e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1417 | +| iterations | 11637 | +| time_elapsed | 16807 | +| total_timesteps | 23832576 | +| train/ | | +| approx_kl | 0.009646043 | +| clip_fraction | 0.301 | +| clip_range | 0.069 | +| entropy_loss | -6.34 | +| explained_variance | 0.388 | +| learning_rate | 4.43e-05 | +| loss | -0.0298 | +| n_updates | 62364 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000277 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1417 | +| iterations | 11638 | +| time_elapsed | 16809 | +| total_timesteps | 23834624 | +| train/ | | +| approx_kl | 0.013355098 | +| clip_fraction | 0.365 | +| clip_range | 0.069 | +| entropy_loss | -6.51 | +| explained_variance | 0.329 | +| learning_rate | 4.43e-05 | +| loss | -0.0316 | +| n_updates | 62368 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000135 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1417 | +| iterations | 11639 | +| time_elapsed | 16810 | +| total_timesteps | 23836672 | +| train/ | | +| approx_kl | 0.012607811 | +| clip_fraction | 0.349 | +| clip_range | 0.069 | +| entropy_loss | -6.65 | +| explained_variance | 0.237 | +| learning_rate | 4.43e-05 | +| loss | -0.0304 | +| n_updates | 62372 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000216 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1417 | +| iterations | 11640 | +| time_elapsed | 16812 | +| total_timesteps | 23838720 | +| train/ | | +| approx_kl | 0.016128156 | +| clip_fraction | 0.354 | +| clip_range | 0.069 | +| entropy_loss | -6.19 | +| explained_variance | 0.585 | +| learning_rate | 4.43e-05 | +| loss | -0.0332 | +| n_updates | 62376 | +| policy_gradient_loss | -0.0212 | +| value_loss | 8.77e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1417 | +| iterations | 11641 | +| time_elapsed | 16813 | +| total_timesteps | 23840768 | +| train/ | | +| approx_kl | 0.013925588 | +| clip_fraction | 0.352 | +| clip_range | 0.069 | +| entropy_loss | -6.1 | +| explained_variance | 0.64 | +| learning_rate | 4.43e-05 | +| loss | -0.0351 | +| n_updates | 62380 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.00013 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.315 | +| time/ | | +| fps | 1417 | +| iterations | 11642 | +| time_elapsed | 16815 | +| total_timesteps | 23842816 | +| train/ | | +| approx_kl | 0.011912622 | +| clip_fraction | 0.319 | +| clip_range | 0.069 | +| entropy_loss | -6.1 | +| explained_variance | 0.274 | +| learning_rate | 4.43e-05 | +| loss | -0.0242 | +| n_updates | 62384 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000251 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1417 | +| iterations | 11643 | +| time_elapsed | 16816 | +| total_timesteps | 23844864 | +| train/ | | +| approx_kl | 0.011997096 | +| clip_fraction | 0.315 | +| clip_range | 0.069 | +| entropy_loss | -6.58 | +| explained_variance | 0.442 | +| learning_rate | 4.43e-05 | +| loss | -0.0288 | +| n_updates | 62388 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000154 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1417 | +| iterations | 11644 | +| time_elapsed | 16818 | +| total_timesteps | 23846912 | +| train/ | | +| approx_kl | 0.014772771 | +| clip_fraction | 0.337 | +| clip_range | 0.069 | +| entropy_loss | -6.35 | +| explained_variance | 0.676 | +| learning_rate | 4.43e-05 | +| loss | -0.0366 | +| n_updates | 62392 | +| policy_gradient_loss | -0.0209 | +| value_loss | 7.28e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1417 | +| iterations | 11645 | +| time_elapsed | 16819 | +| total_timesteps | 23848960 | +| train/ | | +| approx_kl | 0.0152697405 | +| clip_fraction | 0.364 | +| clip_range | 0.069 | +| entropy_loss | -6.47 | +| explained_variance | 0.361 | +| learning_rate | 4.43e-05 | +| loss | -0.0333 | +| n_updates | 62396 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.00015 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1417 | +| iterations | 11646 | +| time_elapsed | 16821 | +| total_timesteps | 23851008 | +| train/ | | +| approx_kl | 0.013622795 | +| clip_fraction | 0.316 | +| clip_range | 0.069 | +| entropy_loss | -6.3 | +| explained_variance | 0.498 | +| learning_rate | 4.43e-05 | +| loss | -0.0273 | +| n_updates | 62400 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000223 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1417 | +| iterations | 11647 | +| time_elapsed | 16822 | +| total_timesteps | 23853056 | +| train/ | | +| approx_kl | 0.012269476 | +| clip_fraction | 0.329 | +| clip_range | 0.069 | +| entropy_loss | -6.01 | +| explained_variance | 0.456 | +| learning_rate | 4.43e-05 | +| loss | -0.0254 | +| n_updates | 62404 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000183 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1417 | +| iterations | 11648 | +| time_elapsed | 16824 | +| total_timesteps | 23855104 | +| train/ | | +| approx_kl | 0.011435023 | +| clip_fraction | 0.345 | +| clip_range | 0.069 | +| entropy_loss | -6.18 | +| explained_variance | 0.274 | +| learning_rate | 4.43e-05 | +| loss | -0.0281 | +| n_updates | 62408 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000343 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1417 | +| iterations | 11649 | +| time_elapsed | 16825 | +| total_timesteps | 23857152 | +| train/ | | +| approx_kl | 0.013247382 | +| clip_fraction | 0.375 | +| clip_range | 0.069 | +| entropy_loss | -6.22 | +| explained_variance | 0.286 | +| learning_rate | 4.43e-05 | +| loss | -0.0388 | +| n_updates | 62412 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000133 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1417 | +| iterations | 11650 | +| time_elapsed | 16827 | +| total_timesteps | 23859200 | +| train/ | | +| approx_kl | 0.014952814 | +| clip_fraction | 0.368 | +| clip_range | 0.069 | +| entropy_loss | -6.61 | +| explained_variance | 0.35 | +| learning_rate | 4.43e-05 | +| loss | -0.0328 | +| n_updates | 62416 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000212 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1417 | +| iterations | 11651 | +| time_elapsed | 16828 | +| total_timesteps | 23861248 | +| train/ | | +| approx_kl | 0.013190633 | +| clip_fraction | 0.346 | +| clip_range | 0.069 | +| entropy_loss | -6.51 | +| explained_variance | -0.0534 | +| learning_rate | 4.43e-05 | +| loss | -0.0275 | +| n_updates | 62420 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000156 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1417 | +| iterations | 11652 | +| time_elapsed | 16830 | +| total_timesteps | 23863296 | +| train/ | | +| approx_kl | 0.0130015565 | +| clip_fraction | 0.333 | +| clip_range | 0.069 | +| entropy_loss | -5.99 | +| explained_variance | 0.454 | +| learning_rate | 4.43e-05 | +| loss | -0.0299 | +| n_updates | 62424 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000273 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1417 | +| iterations | 11653 | +| time_elapsed | 16832 | +| total_timesteps | 23865344 | +| train/ | | +| approx_kl | 0.014055973 | +| clip_fraction | 0.328 | +| clip_range | 0.069 | +| entropy_loss | -6.02 | +| explained_variance | 0.521 | +| learning_rate | 4.43e-05 | +| loss | -0.0283 | +| n_updates | 62428 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000173 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1417 | +| iterations | 11654 | +| time_elapsed | 16833 | +| total_timesteps | 23867392 | +| train/ | | +| approx_kl | 0.013264646 | +| clip_fraction | 0.337 | +| clip_range | 0.069 | +| entropy_loss | -6.55 | +| explained_variance | 0.11 | +| learning_rate | 4.43e-05 | +| loss | -0.0286 | +| n_updates | 62432 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000162 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1417 | +| iterations | 11655 | +| time_elapsed | 16835 | +| total_timesteps | 23869440 | +| train/ | | +| approx_kl | 0.013418841 | +| clip_fraction | 0.341 | +| clip_range | 0.069 | +| entropy_loss | -6.37 | +| explained_variance | 0.631 | +| learning_rate | 4.43e-05 | +| loss | -0.0331 | +| n_updates | 62436 | +| policy_gradient_loss | -0.0197 | +| value_loss | 9.77e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1417 | +| iterations | 11656 | +| time_elapsed | 16836 | +| total_timesteps | 23871488 | +| train/ | | +| approx_kl | 0.012716501 | +| clip_fraction | 0.366 | +| clip_range | 0.069 | +| entropy_loss | -6.77 | +| explained_variance | -0.0747 | +| learning_rate | 4.43e-05 | +| loss | -0.03 | +| n_updates | 62440 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000117 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1417 | +| iterations | 11657 | +| time_elapsed | 16838 | +| total_timesteps | 23873536 | +| train/ | | +| approx_kl | 0.012521435 | +| clip_fraction | 0.315 | +| clip_range | 0.069 | +| entropy_loss | -6.44 | +| explained_variance | 0.449 | +| learning_rate | 4.43e-05 | +| loss | -0.0281 | +| n_updates | 62444 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000259 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1417 | +| iterations | 11658 | +| time_elapsed | 16839 | +| total_timesteps | 23875584 | +| train/ | | +| approx_kl | 0.013640936 | +| clip_fraction | 0.324 | +| clip_range | 0.069 | +| entropy_loss | -5.92 | +| explained_variance | 0.331 | +| learning_rate | 4.43e-05 | +| loss | -0.0212 | +| n_updates | 62448 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000297 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1417 | +| iterations | 11659 | +| time_elapsed | 16840 | +| total_timesteps | 23877632 | +| train/ | | +| approx_kl | 0.010656547 | +| clip_fraction | 0.339 | +| clip_range | 0.069 | +| entropy_loss | -6.39 | +| explained_variance | 0.415 | +| learning_rate | 4.43e-05 | +| loss | -0.0361 | +| n_updates | 62452 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000143 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1417 | +| iterations | 11660 | +| time_elapsed | 16842 | +| total_timesteps | 23879680 | +| train/ | | +| approx_kl | 0.013667537 | +| clip_fraction | 0.355 | +| clip_range | 0.069 | +| entropy_loss | -6.49 | +| explained_variance | 0.248 | +| learning_rate | 4.43e-05 | +| loss | -0.0305 | +| n_updates | 62456 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000212 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1417 | +| iterations | 11661 | +| time_elapsed | 16843 | +| total_timesteps | 23881728 | +| train/ | | +| approx_kl | 0.014783418 | +| clip_fraction | 0.387 | +| clip_range | 0.069 | +| entropy_loss | -6.52 | +| explained_variance | 0.716 | +| learning_rate | 4.43e-05 | +| loss | -0.0433 | +| n_updates | 62460 | +| policy_gradient_loss | -0.0254 | +| value_loss | 4.35e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1417 | +| iterations | 11662 | +| time_elapsed | 16845 | +| total_timesteps | 23883776 | +| train/ | | +| approx_kl | 0.009535966 | +| clip_fraction | 0.302 | +| clip_range | 0.069 | +| entropy_loss | -6.2 | +| explained_variance | 0.53 | +| learning_rate | 4.43e-05 | +| loss | -0.0215 | +| n_updates | 62464 | +| policy_gradient_loss | -0.0144 | +| value_loss | 0.000198 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1417 | +| iterations | 11663 | +| time_elapsed | 16846 | +| total_timesteps | 23885824 | +| train/ | | +| approx_kl | 0.012962415 | +| clip_fraction | 0.351 | +| clip_range | 0.069 | +| entropy_loss | -6.44 | +| explained_variance | 0.343 | +| learning_rate | 4.43e-05 | +| loss | -0.0293 | +| n_updates | 62468 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1417 | +| iterations | 11664 | +| time_elapsed | 16848 | +| total_timesteps | 23887872 | +| train/ | | +| approx_kl | 0.012742206 | +| clip_fraction | 0.343 | +| clip_range | 0.069 | +| entropy_loss | -6.54 | +| explained_variance | 0.391 | +| learning_rate | 4.43e-05 | +| loss | -0.037 | +| n_updates | 62472 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000117 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1417 | +| iterations | 11665 | +| time_elapsed | 16849 | +| total_timesteps | 23889920 | +| train/ | | +| approx_kl | 0.01299508 | +| clip_fraction | 0.324 | +| clip_range | 0.069 | +| entropy_loss | -6.48 | +| explained_variance | 0.39 | +| learning_rate | 4.43e-05 | +| loss | -0.0272 | +| n_updates | 62476 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000223 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1417 | +| iterations | 11666 | +| time_elapsed | 16851 | +| total_timesteps | 23891968 | +| train/ | | +| approx_kl | 0.012831268 | +| clip_fraction | 0.322 | +| clip_range | 0.069 | +| entropy_loss | -6.23 | +| explained_variance | 0.525 | +| learning_rate | 4.43e-05 | +| loss | -0.0275 | +| n_updates | 62480 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000126 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1417 | +| iterations | 11667 | +| time_elapsed | 16853 | +| total_timesteps | 23894016 | +| train/ | | +| approx_kl | 0.012688631 | +| clip_fraction | 0.339 | +| clip_range | 0.069 | +| entropy_loss | -6.45 | +| explained_variance | 0.539 | +| learning_rate | 4.43e-05 | +| loss | -0.0317 | +| n_updates | 62484 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000157 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1417 | +| iterations | 11668 | +| time_elapsed | 16854 | +| total_timesteps | 23896064 | +| train/ | | +| approx_kl | 0.011932371 | +| clip_fraction | 0.321 | +| clip_range | 0.069 | +| entropy_loss | -5.74 | +| explained_variance | 0.373 | +| learning_rate | 4.43e-05 | +| loss | -0.0281 | +| n_updates | 62488 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.000318 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1417 | +| iterations | 11669 | +| time_elapsed | 16855 | +| total_timesteps | 23898112 | +| train/ | | +| approx_kl | 0.015218332 | +| clip_fraction | 0.356 | +| clip_range | 0.069 | +| entropy_loss | -6.33 | +| explained_variance | 0.319 | +| learning_rate | 4.43e-05 | +| loss | -0.0334 | +| n_updates | 62492 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.00019 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1417 | +| iterations | 11670 | +| time_elapsed | 16857 | +| total_timesteps | 23900160 | +| train/ | | +| approx_kl | 0.012398313 | +| clip_fraction | 0.346 | +| clip_range | 0.069 | +| entropy_loss | -7.07 | +| explained_variance | -0.123 | +| learning_rate | 4.43e-05 | +| loss | -0.0342 | +| n_updates | 62496 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000173 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1417 | +| iterations | 11671 | +| time_elapsed | 16858 | +| total_timesteps | 23902208 | +| train/ | | +| approx_kl | 0.010429828 | +| clip_fraction | 0.302 | +| clip_range | 0.069 | +| entropy_loss | -6.99 | +| explained_variance | 0.043 | +| learning_rate | 4.43e-05 | +| loss | -0.0233 | +| n_updates | 62500 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.00028 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1417 | +| iterations | 11672 | +| time_elapsed | 16860 | +| total_timesteps | 23904256 | +| train/ | | +| approx_kl | 0.011940955 | +| clip_fraction | 0.353 | +| clip_range | 0.069 | +| entropy_loss | -6.4 | +| explained_variance | 0.539 | +| learning_rate | 4.43e-05 | +| loss | -0.0333 | +| n_updates | 62504 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000112 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1417 | +| iterations | 11673 | +| time_elapsed | 16861 | +| total_timesteps | 23906304 | +| train/ | | +| approx_kl | 0.012435945 | +| clip_fraction | 0.342 | +| clip_range | 0.069 | +| entropy_loss | -6.44 | +| explained_variance | 0.384 | +| learning_rate | 4.43e-05 | +| loss | -0.0338 | +| n_updates | 62508 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000136 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1417 | +| iterations | 11674 | +| time_elapsed | 16863 | +| total_timesteps | 23908352 | +| train/ | | +| approx_kl | 0.0125391465 | +| clip_fraction | 0.322 | +| clip_range | 0.069 | +| entropy_loss | -6.49 | +| explained_variance | 0.493 | +| learning_rate | 4.43e-05 | +| loss | -0.0231 | +| n_updates | 62512 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000181 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1417 | +| iterations | 11675 | +| time_elapsed | 16864 | +| total_timesteps | 23910400 | +| train/ | | +| approx_kl | 0.01687859 | +| clip_fraction | 0.33 | +| clip_range | 0.069 | +| entropy_loss | -5.86 | +| explained_variance | 0.624 | +| learning_rate | 4.43e-05 | +| loss | -0.0316 | +| n_updates | 62516 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000147 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1417 | +| iterations | 11676 | +| time_elapsed | 16866 | +| total_timesteps | 23912448 | +| train/ | | +| approx_kl | 0.014264947 | +| clip_fraction | 0.346 | +| clip_range | 0.069 | +| entropy_loss | -6.7 | +| explained_variance | 0.199 | +| learning_rate | 4.43e-05 | +| loss | -0.0327 | +| n_updates | 62520 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000149 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1417 | +| iterations | 11677 | +| time_elapsed | 16867 | +| total_timesteps | 23914496 | +| train/ | | +| approx_kl | 0.0143123325 | +| clip_fraction | 0.345 | +| clip_range | 0.069 | +| entropy_loss | -6.73 | +| explained_variance | 0.328 | +| learning_rate | 4.43e-05 | +| loss | -0.0272 | +| n_updates | 62524 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000111 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1417 | +| iterations | 11678 | +| time_elapsed | 16869 | +| total_timesteps | 23916544 | +| train/ | | +| approx_kl | 0.011344029 | +| clip_fraction | 0.33 | +| clip_range | 0.069 | +| entropy_loss | -6.74 | +| explained_variance | 0.272 | +| learning_rate | 4.43e-05 | +| loss | -0.0341 | +| n_updates | 62528 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000109 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1417 | +| iterations | 11679 | +| time_elapsed | 16870 | +| total_timesteps | 23918592 | +| train/ | | +| approx_kl | 0.011266792 | +| clip_fraction | 0.311 | +| clip_range | 0.069 | +| entropy_loss | -6.67 | +| explained_variance | 0.42 | +| learning_rate | 4.43e-05 | +| loss | -0.031 | +| n_updates | 62532 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000102 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1417 | +| iterations | 11680 | +| time_elapsed | 16872 | +| total_timesteps | 23920640 | +| train/ | | +| approx_kl | 0.012572862 | +| clip_fraction | 0.335 | +| clip_range | 0.069 | +| entropy_loss | -6.49 | +| explained_variance | 0.599 | +| learning_rate | 4.43e-05 | +| loss | -0.0297 | +| n_updates | 62536 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000109 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1417 | +| iterations | 11681 | +| time_elapsed | 16873 | +| total_timesteps | 23922688 | +| train/ | | +| approx_kl | 0.011948617 | +| clip_fraction | 0.325 | +| clip_range | 0.069 | +| entropy_loss | -6.41 | +| explained_variance | 0.35 | +| learning_rate | 4.43e-05 | +| loss | -0.0243 | +| n_updates | 62540 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000301 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1417 | +| iterations | 11682 | +| time_elapsed | 16875 | +| total_timesteps | 23924736 | +| train/ | | +| approx_kl | 0.012824798 | +| clip_fraction | 0.306 | +| clip_range | 0.069 | +| entropy_loss | -6 | +| explained_variance | 0.388 | +| learning_rate | 4.43e-05 | +| loss | -0.026 | +| n_updates | 62544 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000302 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1417 | +| iterations | 11683 | +| time_elapsed | 16876 | +| total_timesteps | 23926784 | +| train/ | | +| approx_kl | 0.012325399 | +| clip_fraction | 0.349 | +| clip_range | 0.069 | +| entropy_loss | -6.38 | +| explained_variance | -0.000819 | +| learning_rate | 4.43e-05 | +| loss | -0.0328 | +| n_updates | 62548 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000145 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1417 | +| iterations | 11684 | +| time_elapsed | 16878 | +| total_timesteps | 23928832 | +| train/ | | +| approx_kl | 0.01267229 | +| clip_fraction | 0.325 | +| clip_range | 0.069 | +| entropy_loss | -6.03 | +| explained_variance | 0.429 | +| learning_rate | 4.43e-05 | +| loss | -0.0294 | +| n_updates | 62552 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000196 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1417 | +| iterations | 11685 | +| time_elapsed | 16879 | +| total_timesteps | 23930880 | +| train/ | | +| approx_kl | 0.0131867975 | +| clip_fraction | 0.369 | +| clip_range | 0.069 | +| entropy_loss | -6.45 | +| explained_variance | -0.225 | +| learning_rate | 4.43e-05 | +| loss | -0.0341 | +| n_updates | 62556 | +| policy_gradient_loss | -0.0224 | +| value_loss | 9.93e-05 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1417 | +| iterations | 11686 | +| time_elapsed | 16881 | +| total_timesteps | 23932928 | +| train/ | | +| approx_kl | 0.01253042 | +| clip_fraction | 0.341 | +| clip_range | 0.069 | +| entropy_loss | -6.75 | +| explained_variance | -0.24 | +| learning_rate | 4.43e-05 | +| loss | -0.0373 | +| n_updates | 62560 | +| policy_gradient_loss | -0.0214 | +| value_loss | 9.33e-05 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1417 | +| iterations | 11687 | +| time_elapsed | 16882 | +| total_timesteps | 23934976 | +| train/ | | +| approx_kl | 0.0129193505 | +| clip_fraction | 0.325 | +| clip_range | 0.069 | +| entropy_loss | -6.27 | +| explained_variance | 0.417 | +| learning_rate | 4.43e-05 | +| loss | -0.0267 | +| n_updates | 62564 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000206 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1417 | +| iterations | 11688 | +| time_elapsed | 16884 | +| total_timesteps | 23937024 | +| train/ | | +| approx_kl | 0.011866097 | +| clip_fraction | 0.344 | +| clip_range | 0.069 | +| entropy_loss | -6.14 | +| explained_variance | 0.488 | +| learning_rate | 4.43e-05 | +| loss | -0.03 | +| n_updates | 62568 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000165 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1417 | +| iterations | 11689 | +| time_elapsed | 16885 | +| total_timesteps | 23939072 | +| train/ | | +| approx_kl | 0.011241559 | +| clip_fraction | 0.339 | +| clip_range | 0.069 | +| entropy_loss | -6.52 | +| explained_variance | 0.438 | +| learning_rate | 4.43e-05 | +| loss | -0.0339 | +| n_updates | 62572 | +| policy_gradient_loss | -0.0206 | +| value_loss | 8.44e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1417 | +| iterations | 11690 | +| time_elapsed | 16887 | +| total_timesteps | 23941120 | +| train/ | | +| approx_kl | 0.009968044 | +| clip_fraction | 0.319 | +| clip_range | 0.069 | +| entropy_loss | -6.26 | +| explained_variance | 0.483 | +| learning_rate | 4.43e-05 | +| loss | -0.025 | +| n_updates | 62576 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000235 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1417 | +| iterations | 11691 | +| time_elapsed | 16888 | +| total_timesteps | 23943168 | +| train/ | | +| approx_kl | 0.0105444975 | +| clip_fraction | 0.341 | +| clip_range | 0.069 | +| entropy_loss | -6.43 | +| explained_variance | 0.44 | +| learning_rate | 4.43e-05 | +| loss | -0.0321 | +| n_updates | 62580 | +| policy_gradient_loss | -0.0194 | +| value_loss | 9.63e-05 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1417 | +| iterations | 11692 | +| time_elapsed | 16890 | +| total_timesteps | 23945216 | +| train/ | | +| approx_kl | 0.01381476 | +| clip_fraction | 0.356 | +| clip_range | 0.069 | +| entropy_loss | -6.45 | +| explained_variance | 0.214 | +| learning_rate | 4.43e-05 | +| loss | -0.0327 | +| n_updates | 62584 | +| policy_gradient_loss | -0.0205 | +| value_loss | 9.77e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1417 | +| iterations | 11693 | +| time_elapsed | 16891 | +| total_timesteps | 23947264 | +| train/ | | +| approx_kl | 0.014273902 | +| clip_fraction | 0.347 | +| clip_range | 0.069 | +| entropy_loss | -6.43 | +| explained_variance | 0.403 | +| learning_rate | 4.43e-05 | +| loss | -0.0298 | +| n_updates | 62588 | +| policy_gradient_loss | -0.0196 | +| value_loss | 8.95e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1417 | +| iterations | 11694 | +| time_elapsed | 16893 | +| total_timesteps | 23949312 | +| train/ | | +| approx_kl | 0.014141034 | +| clip_fraction | 0.348 | +| clip_range | 0.069 | +| entropy_loss | -6.26 | +| explained_variance | 0.579 | +| learning_rate | 4.43e-05 | +| loss | -0.0308 | +| n_updates | 62592 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000116 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1417 | +| iterations | 11695 | +| time_elapsed | 16894 | +| total_timesteps | 23951360 | +| train/ | | +| approx_kl | 0.01223163 | +| clip_fraction | 0.336 | +| clip_range | 0.069 | +| entropy_loss | -6.17 | +| explained_variance | 0.68 | +| learning_rate | 4.43e-05 | +| loss | -0.0284 | +| n_updates | 62596 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000113 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1417 | +| iterations | 11696 | +| time_elapsed | 16896 | +| total_timesteps | 23953408 | +| train/ | | +| approx_kl | 0.016057014 | +| clip_fraction | 0.346 | +| clip_range | 0.069 | +| entropy_loss | -6.01 | +| explained_variance | 0.482 | +| learning_rate | 4.43e-05 | +| loss | -0.0349 | +| n_updates | 62600 | +| policy_gradient_loss | -0.0194 | +| value_loss | 7.6e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1417 | +| iterations | 11697 | +| time_elapsed | 16897 | +| total_timesteps | 23955456 | +| train/ | | +| approx_kl | 0.013364492 | +| clip_fraction | 0.328 | +| clip_range | 0.069 | +| entropy_loss | -6.63 | +| explained_variance | -0.168 | +| learning_rate | 4.43e-05 | +| loss | -0.0265 | +| n_updates | 62604 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000139 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1417 | +| iterations | 11698 | +| time_elapsed | 16899 | +| total_timesteps | 23957504 | +| train/ | | +| approx_kl | 0.012580855 | +| clip_fraction | 0.358 | +| clip_range | 0.069 | +| entropy_loss | -7.07 | +| explained_variance | -0.0405 | +| learning_rate | 4.43e-05 | +| loss | -0.0303 | +| n_updates | 62608 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000221 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1417 | +| iterations | 11699 | +| time_elapsed | 16900 | +| total_timesteps | 23959552 | +| train/ | | +| approx_kl | 0.011357957 | +| clip_fraction | 0.305 | +| clip_range | 0.069 | +| entropy_loss | -6.42 | +| explained_variance | 0.393 | +| learning_rate | 4.43e-05 | +| loss | -0.0239 | +| n_updates | 62612 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000183 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1417 | +| iterations | 11700 | +| time_elapsed | 16901 | +| total_timesteps | 23961600 | +| train/ | | +| approx_kl | 0.012223816 | +| clip_fraction | 0.306 | +| clip_range | 0.069 | +| entropy_loss | -6.54 | +| explained_variance | 0.28 | +| learning_rate | 4.43e-05 | +| loss | -0.0208 | +| n_updates | 62616 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000215 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1417 | +| iterations | 11701 | +| time_elapsed | 16903 | +| total_timesteps | 23963648 | +| train/ | | +| approx_kl | 0.014278781 | +| clip_fraction | 0.33 | +| clip_range | 0.069 | +| entropy_loss | -6.3 | +| explained_variance | 0.498 | +| learning_rate | 4.43e-05 | +| loss | -0.0337 | +| n_updates | 62620 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000151 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1417 | +| iterations | 11702 | +| time_elapsed | 16904 | +| total_timesteps | 23965696 | +| train/ | | +| approx_kl | 0.012230762 | +| clip_fraction | 0.329 | +| clip_range | 0.069 | +| entropy_loss | -6.26 | +| explained_variance | 0.599 | +| learning_rate | 4.43e-05 | +| loss | -0.0278 | +| n_updates | 62624 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000159 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1417 | +| iterations | 11703 | +| time_elapsed | 16906 | +| total_timesteps | 23967744 | +| train/ | | +| approx_kl | 0.014657028 | +| clip_fraction | 0.358 | +| clip_range | 0.069 | +| entropy_loss | -5.82 | +| explained_variance | 0.636 | +| learning_rate | 4.43e-05 | +| loss | -0.0298 | +| n_updates | 62628 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000134 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1417 | +| iterations | 11704 | +| time_elapsed | 16907 | +| total_timesteps | 23969792 | +| train/ | | +| approx_kl | 0.014257379 | +| clip_fraction | 0.371 | +| clip_range | 0.069 | +| entropy_loss | -6 | +| explained_variance | 0.582 | +| learning_rate | 4.43e-05 | +| loss | -0.0317 | +| n_updates | 62632 | +| policy_gradient_loss | -0.0223 | +| value_loss | 9.99e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1417 | +| iterations | 11705 | +| time_elapsed | 16909 | +| total_timesteps | 23971840 | +| train/ | | +| approx_kl | 0.013815654 | +| clip_fraction | 0.378 | +| clip_range | 0.069 | +| entropy_loss | -6.29 | +| explained_variance | 0.66 | +| learning_rate | 4.43e-05 | +| loss | -0.0337 | +| n_updates | 62636 | +| policy_gradient_loss | -0.0233 | +| value_loss | 5.49e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1417 | +| iterations | 11706 | +| time_elapsed | 16910 | +| total_timesteps | 23973888 | +| train/ | | +| approx_kl | 0.010375249 | +| clip_fraction | 0.35 | +| clip_range | 0.069 | +| entropy_loss | -6.83 | +| explained_variance | 0.0515 | +| learning_rate | 4.43e-05 | +| loss | -0.0296 | +| n_updates | 62640 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000216 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1417 | +| iterations | 11707 | +| time_elapsed | 16912 | +| total_timesteps | 23975936 | +| train/ | | +| approx_kl | 0.015497918 | +| clip_fraction | 0.351 | +| clip_range | 0.069 | +| entropy_loss | -6.52 | +| explained_variance | 0.722 | +| learning_rate | 4.43e-05 | +| loss | -0.0291 | +| n_updates | 62644 | +| policy_gradient_loss | -0.0198 | +| value_loss | 7.43e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1417 | +| iterations | 11708 | +| time_elapsed | 16913 | +| total_timesteps | 23977984 | +| train/ | | +| approx_kl | 0.014583276 | +| clip_fraction | 0.346 | +| clip_range | 0.069 | +| entropy_loss | -6.47 | +| explained_variance | -0.196 | +| learning_rate | 4.43e-05 | +| loss | -0.032 | +| n_updates | 62648 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000118 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1417 | +| iterations | 11709 | +| time_elapsed | 16915 | +| total_timesteps | 23980032 | +| train/ | | +| approx_kl | 0.01391248 | +| clip_fraction | 0.359 | +| clip_range | 0.069 | +| entropy_loss | -6.5 | +| explained_variance | 0.434 | +| learning_rate | 4.43e-05 | +| loss | -0.0305 | +| n_updates | 62652 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000125 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1417 | +| iterations | 11710 | +| time_elapsed | 16916 | +| total_timesteps | 23982080 | +| train/ | | +| approx_kl | 0.012221277 | +| clip_fraction | 0.321 | +| clip_range | 0.069 | +| entropy_loss | -6.36 | +| explained_variance | 0.54 | +| learning_rate | 4.43e-05 | +| loss | -0.0243 | +| n_updates | 62656 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000124 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1417 | +| iterations | 11711 | +| time_elapsed | 16918 | +| total_timesteps | 23984128 | +| train/ | | +| approx_kl | 0.013373792 | +| clip_fraction | 0.332 | +| clip_range | 0.069 | +| entropy_loss | -5.95 | +| explained_variance | 0.678 | +| learning_rate | 4.43e-05 | +| loss | -0.029 | +| n_updates | 62660 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000115 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1417 | +| iterations | 11712 | +| time_elapsed | 16919 | +| total_timesteps | 23986176 | +| train/ | | +| approx_kl | 0.01185569 | +| clip_fraction | 0.336 | +| clip_range | 0.069 | +| entropy_loss | -6.39 | +| explained_variance | 0.707 | +| learning_rate | 4.43e-05 | +| loss | -0.0298 | +| n_updates | 62664 | +| policy_gradient_loss | -0.0196 | +| value_loss | 9.86e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1417 | +| iterations | 11713 | +| time_elapsed | 16921 | +| total_timesteps | 23988224 | +| train/ | | +| approx_kl | 0.009785467 | +| clip_fraction | 0.319 | +| clip_range | 0.069 | +| entropy_loss | -6.04 | +| explained_variance | 0.503 | +| learning_rate | 4.43e-05 | +| loss | -0.0218 | +| n_updates | 62668 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000154 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1417 | +| iterations | 11714 | +| time_elapsed | 16922 | +| total_timesteps | 23990272 | +| train/ | | +| approx_kl | 0.011743572 | +| clip_fraction | 0.273 | +| clip_range | 0.069 | +| entropy_loss | -6.55 | +| explained_variance | 0.22 | +| learning_rate | 4.43e-05 | +| loss | -0.0261 | +| n_updates | 62672 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000257 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1417 | +| iterations | 11715 | +| time_elapsed | 16924 | +| total_timesteps | 23992320 | +| train/ | | +| approx_kl | 0.010702364 | +| clip_fraction | 0.337 | +| clip_range | 0.069 | +| entropy_loss | -6.78 | +| explained_variance | 0.471 | +| learning_rate | 4.43e-05 | +| loss | -0.0339 | +| n_updates | 62676 | +| policy_gradient_loss | -0.0203 | +| value_loss | 8.58e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1417 | +| iterations | 11716 | +| time_elapsed | 16925 | +| total_timesteps | 23994368 | +| train/ | | +| approx_kl | 0.016121073 | +| clip_fraction | 0.341 | +| clip_range | 0.069 | +| entropy_loss | -6.3 | +| explained_variance | 0.561 | +| learning_rate | 4.43e-05 | +| loss | -0.0316 | +| n_updates | 62680 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000116 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1417 | +| iterations | 11717 | +| time_elapsed | 16927 | +| total_timesteps | 23996416 | +| train/ | | +| approx_kl | 0.016872229 | +| clip_fraction | 0.323 | +| clip_range | 0.069 | +| entropy_loss | -6.39 | +| explained_variance | 0.355 | +| learning_rate | 4.43e-05 | +| loss | -0.03 | +| n_updates | 62684 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000172 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1417 | +| iterations | 11718 | +| time_elapsed | 16928 | +| total_timesteps | 23998464 | +| train/ | | +| approx_kl | 0.01367725 | +| clip_fraction | 0.32 | +| clip_range | 0.069 | +| entropy_loss | -6.12 | +| explained_variance | 0.35 | +| learning_rate | 4.43e-05 | +| loss | -0.0255 | +| n_updates | 62688 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.000332 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1417 | +| iterations | 11719 | +| time_elapsed | 16930 | +| total_timesteps | 24000512 | +| train/ | | +| approx_kl | 0.013994905 | +| clip_fraction | 0.344 | +| clip_range | 0.069 | +| entropy_loss | -6.37 | +| explained_variance | 0.176 | +| learning_rate | 4.43e-05 | +| loss | -0.0282 | +| n_updates | 62692 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000158 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1417 | +| iterations | 11720 | +| time_elapsed | 16931 | +| total_timesteps | 24002560 | +| train/ | | +| approx_kl | 0.014932305 | +| clip_fraction | 0.361 | +| clip_range | 0.069 | +| entropy_loss | -6.77 | +| explained_variance | 0.0957 | +| learning_rate | 4.43e-05 | +| loss | -0.0363 | +| n_updates | 62696 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000141 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1417 | +| iterations | 11721 | +| time_elapsed | 16933 | +| total_timesteps | 24004608 | +| train/ | | +| approx_kl | 0.017518442 | +| clip_fraction | 0.388 | +| clip_range | 0.069 | +| entropy_loss | -6.76 | +| explained_variance | -0.231 | +| learning_rate | 4.43e-05 | +| loss | -0.0295 | +| n_updates | 62700 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000109 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1417 | +| iterations | 11722 | +| time_elapsed | 16934 | +| total_timesteps | 24006656 | +| train/ | | +| approx_kl | 0.014089491 | +| clip_fraction | 0.344 | +| clip_range | 0.069 | +| entropy_loss | -6.14 | +| explained_variance | 0.0541 | +| learning_rate | 4.43e-05 | +| loss | -0.0251 | +| n_updates | 62704 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000648 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1417 | +| iterations | 11723 | +| time_elapsed | 16936 | +| total_timesteps | 24008704 | +| train/ | | +| approx_kl | 0.0130287055 | +| clip_fraction | 0.33 | +| clip_range | 0.069 | +| entropy_loss | -5.47 | +| explained_variance | 0.409 | +| learning_rate | 4.43e-05 | +| loss | -0.0167 | +| n_updates | 62708 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000281 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1417 | +| iterations | 11724 | +| time_elapsed | 16937 | +| total_timesteps | 24010752 | +| train/ | | +| approx_kl | 0.012358507 | +| clip_fraction | 0.345 | +| clip_range | 0.069 | +| entropy_loss | -6.33 | +| explained_variance | 0.476 | +| learning_rate | 4.43e-05 | +| loss | -0.0339 | +| n_updates | 62712 | +| policy_gradient_loss | -0.0201 | +| value_loss | 8.84e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1417 | +| iterations | 11725 | +| time_elapsed | 16939 | +| total_timesteps | 24012800 | +| train/ | | +| approx_kl | 0.013929624 | +| clip_fraction | 0.344 | +| clip_range | 0.069 | +| entropy_loss | -6.33 | +| explained_variance | 0.47 | +| learning_rate | 4.43e-05 | +| loss | -0.032 | +| n_updates | 62716 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000162 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1417 | +| iterations | 11726 | +| time_elapsed | 16940 | +| total_timesteps | 24014848 | +| train/ | | +| approx_kl | 0.011503173 | +| clip_fraction | 0.322 | +| clip_range | 0.069 | +| entropy_loss | -6.05 | +| explained_variance | 0.582 | +| learning_rate | 4.43e-05 | +| loss | -0.033 | +| n_updates | 62720 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000114 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1417 | +| iterations | 11727 | +| time_elapsed | 16942 | +| total_timesteps | 24016896 | +| train/ | | +| approx_kl | 0.012168317 | +| clip_fraction | 0.357 | +| clip_range | 0.069 | +| entropy_loss | -6.22 | +| explained_variance | 0.434 | +| learning_rate | 4.43e-05 | +| loss | -0.0356 | +| n_updates | 62724 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000133 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1417 | +| iterations | 11728 | +| time_elapsed | 16943 | +| total_timesteps | 24018944 | +| train/ | | +| approx_kl | 0.01330434 | +| clip_fraction | 0.354 | +| clip_range | 0.069 | +| entropy_loss | -6.54 | +| explained_variance | 0.425 | +| learning_rate | 4.43e-05 | +| loss | -0.0301 | +| n_updates | 62728 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000145 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1417 | +| iterations | 11729 | +| time_elapsed | 16944 | +| total_timesteps | 24020992 | +| train/ | | +| approx_kl | 0.012354326 | +| clip_fraction | 0.348 | +| clip_range | 0.069 | +| entropy_loss | -6.15 | +| explained_variance | 0.364 | +| learning_rate | 4.43e-05 | +| loss | -0.0318 | +| n_updates | 62732 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000253 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1417 | +| iterations | 11730 | +| time_elapsed | 16946 | +| total_timesteps | 24023040 | +| train/ | | +| approx_kl | 0.012210349 | +| clip_fraction | 0.333 | +| clip_range | 0.069 | +| entropy_loss | -6.19 | +| explained_variance | 0.504 | +| learning_rate | 4.43e-05 | +| loss | -0.0308 | +| n_updates | 62736 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1417 | +| iterations | 11731 | +| time_elapsed | 16947 | +| total_timesteps | 24025088 | +| train/ | | +| approx_kl | 0.012308143 | +| clip_fraction | 0.326 | +| clip_range | 0.069 | +| entropy_loss | -6.41 | +| explained_variance | 0.446 | +| learning_rate | 4.43e-05 | +| loss | -0.0304 | +| n_updates | 62740 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000206 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1417 | +| iterations | 11732 | +| time_elapsed | 16949 | +| total_timesteps | 24027136 | +| train/ | | +| approx_kl | 0.011450928 | +| clip_fraction | 0.339 | +| clip_range | 0.069 | +| entropy_loss | -6.55 | +| explained_variance | 0.291 | +| learning_rate | 4.43e-05 | +| loss | -0.0232 | +| n_updates | 62744 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000167 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1417 | +| iterations | 11733 | +| time_elapsed | 16951 | +| total_timesteps | 24029184 | +| train/ | | +| approx_kl | 0.011411324 | +| clip_fraction | 0.311 | +| clip_range | 0.069 | +| entropy_loss | -6.71 | +| explained_variance | 0.134 | +| learning_rate | 4.43e-05 | +| loss | -0.0262 | +| n_updates | 62748 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000174 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1417 | +| iterations | 11734 | +| time_elapsed | 16952 | +| total_timesteps | 24031232 | +| train/ | | +| approx_kl | 0.011948792 | +| clip_fraction | 0.328 | +| clip_range | 0.069 | +| entropy_loss | -5.99 | +| explained_variance | 0.532 | +| learning_rate | 4.43e-05 | +| loss | -0.0255 | +| n_updates | 62752 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000205 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1417 | +| iterations | 11735 | +| time_elapsed | 16954 | +| total_timesteps | 24033280 | +| train/ | | +| approx_kl | 0.01244087 | +| clip_fraction | 0.341 | +| clip_range | 0.069 | +| entropy_loss | -6.46 | +| explained_variance | 0.446 | +| learning_rate | 4.43e-05 | +| loss | -0.0395 | +| n_updates | 62756 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000106 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1417 | +| iterations | 11736 | +| time_elapsed | 16955 | +| total_timesteps | 24035328 | +| train/ | | +| approx_kl | 0.011157296 | +| clip_fraction | 0.335 | +| clip_range | 0.069 | +| entropy_loss | -6.32 | +| explained_variance | 0.419 | +| learning_rate | 4.43e-05 | +| loss | -0.0285 | +| n_updates | 62760 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.0002 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1417 | +| iterations | 11737 | +| time_elapsed | 16956 | +| total_timesteps | 24037376 | +| train/ | | +| approx_kl | 0.013818729 | +| clip_fraction | 0.341 | +| clip_range | 0.069 | +| entropy_loss | -6 | +| explained_variance | 0.701 | +| learning_rate | 4.43e-05 | +| loss | -0.037 | +| n_updates | 62764 | +| policy_gradient_loss | -0.0199 | +| value_loss | 9.77e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1417 | +| iterations | 11738 | +| time_elapsed | 16958 | +| total_timesteps | 24039424 | +| train/ | | +| approx_kl | 0.014479503 | +| clip_fraction | 0.348 | +| clip_range | 0.069 | +| entropy_loss | -6.55 | +| explained_variance | 0.238 | +| learning_rate | 4.43e-05 | +| loss | -0.0301 | +| n_updates | 62768 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000175 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1417 | +| iterations | 11739 | +| time_elapsed | 16959 | +| total_timesteps | 24041472 | +| train/ | | +| approx_kl | 0.015202415 | +| clip_fraction | 0.344 | +| clip_range | 0.069 | +| entropy_loss | -6.35 | +| explained_variance | 0.545 | +| learning_rate | 4.43e-05 | +| loss | -0.0269 | +| n_updates | 62772 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000123 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1417 | +| iterations | 11740 | +| time_elapsed | 16961 | +| total_timesteps | 24043520 | +| train/ | | +| approx_kl | 0.013838591 | +| clip_fraction | 0.305 | +| clip_range | 0.069 | +| entropy_loss | -5.98 | +| explained_variance | 0.431 | +| learning_rate | 4.43e-05 | +| loss | -0.0231 | +| n_updates | 62776 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000293 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1417 | +| iterations | 11741 | +| time_elapsed | 16962 | +| total_timesteps | 24045568 | +| train/ | | +| approx_kl | 0.011368044 | +| clip_fraction | 0.34 | +| clip_range | 0.069 | +| entropy_loss | -6.36 | +| explained_variance | 0.388 | +| learning_rate | 4.43e-05 | +| loss | -0.0303 | +| n_updates | 62780 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000134 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1417 | +| iterations | 11742 | +| time_elapsed | 16964 | +| total_timesteps | 24047616 | +| train/ | | +| approx_kl | 0.013406375 | +| clip_fraction | 0.34 | +| clip_range | 0.069 | +| entropy_loss | -6.65 | +| explained_variance | 0.254 | +| learning_rate | 4.43e-05 | +| loss | -0.0351 | +| n_updates | 62784 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000145 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1417 | +| iterations | 11743 | +| time_elapsed | 16965 | +| total_timesteps | 24049664 | +| train/ | | +| approx_kl | 0.018672364 | +| clip_fraction | 0.329 | +| clip_range | 0.069 | +| entropy_loss | -6.46 | +| explained_variance | 0.128 | +| learning_rate | 4.43e-05 | +| loss | -0.0304 | +| n_updates | 62788 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000293 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1417 | +| iterations | 11744 | +| time_elapsed | 16967 | +| total_timesteps | 24051712 | +| train/ | | +| approx_kl | 0.011607004 | +| clip_fraction | 0.336 | +| clip_range | 0.069 | +| entropy_loss | -6.46 | +| explained_variance | 0.122 | +| learning_rate | 4.43e-05 | +| loss | -0.0246 | +| n_updates | 62792 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000234 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1417 | +| iterations | 11745 | +| time_elapsed | 16968 | +| total_timesteps | 24053760 | +| train/ | | +| approx_kl | 0.0139978435 | +| clip_fraction | 0.375 | +| clip_range | 0.069 | +| entropy_loss | -6.46 | +| explained_variance | 0.343 | +| learning_rate | 4.43e-05 | +| loss | -0.0362 | +| n_updates | 62796 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000124 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1417 | +| iterations | 11746 | +| time_elapsed | 16970 | +| total_timesteps | 24055808 | +| train/ | | +| approx_kl | 0.01040359 | +| clip_fraction | 0.318 | +| clip_range | 0.069 | +| entropy_loss | -6.67 | +| explained_variance | 0.22 | +| learning_rate | 4.43e-05 | +| loss | -0.0286 | +| n_updates | 62800 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000319 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1417 | +| iterations | 11747 | +| time_elapsed | 16971 | +| total_timesteps | 24057856 | +| train/ | | +| approx_kl | 0.013155622 | +| clip_fraction | 0.371 | +| clip_range | 0.069 | +| entropy_loss | -5.99 | +| explained_variance | 0.687 | +| learning_rate | 4.43e-05 | +| loss | -0.0348 | +| n_updates | 62804 | +| policy_gradient_loss | -0.0226 | +| value_loss | 9.91e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1417 | +| iterations | 11748 | +| time_elapsed | 16973 | +| total_timesteps | 24059904 | +| train/ | | +| approx_kl | 0.013262674 | +| clip_fraction | 0.358 | +| clip_range | 0.069 | +| entropy_loss | -6.26 | +| explained_variance | 0.663 | +| learning_rate | 4.43e-05 | +| loss | -0.0281 | +| n_updates | 62808 | +| policy_gradient_loss | -0.0189 | +| value_loss | 8.32e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1417 | +| iterations | 11749 | +| time_elapsed | 16974 | +| total_timesteps | 24061952 | +| train/ | | +| approx_kl | 0.01310011 | +| clip_fraction | 0.318 | +| clip_range | 0.069 | +| entropy_loss | -6.49 | +| explained_variance | 0.387 | +| learning_rate | 4.43e-05 | +| loss | -0.0274 | +| n_updates | 62812 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000223 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1417 | +| iterations | 11750 | +| time_elapsed | 16976 | +| total_timesteps | 24064000 | +| train/ | | +| approx_kl | 0.0134805385 | +| clip_fraction | 0.358 | +| clip_range | 0.069 | +| entropy_loss | -6.51 | +| explained_variance | 0.0728 | +| learning_rate | 4.43e-05 | +| loss | -0.0348 | +| n_updates | 62816 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000162 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1417 | +| iterations | 11751 | +| time_elapsed | 16977 | +| total_timesteps | 24066048 | +| train/ | | +| approx_kl | 0.013832346 | +| clip_fraction | 0.32 | +| clip_range | 0.069 | +| entropy_loss | -6.32 | +| explained_variance | 0.406 | +| learning_rate | 4.43e-05 | +| loss | -0.0242 | +| n_updates | 62820 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000142 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1417 | +| iterations | 11752 | +| time_elapsed | 16979 | +| total_timesteps | 24068096 | +| train/ | | +| approx_kl | 0.014155246 | +| clip_fraction | 0.355 | +| clip_range | 0.069 | +| entropy_loss | -5.79 | +| explained_variance | 0.756 | +| learning_rate | 4.43e-05 | +| loss | -0.0287 | +| n_updates | 62824 | +| policy_gradient_loss | -0.0203 | +| value_loss | 8.01e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1417 | +| iterations | 11753 | +| time_elapsed | 16980 | +| total_timesteps | 24070144 | +| train/ | | +| approx_kl | 0.01577507 | +| clip_fraction | 0.348 | +| clip_range | 0.069 | +| entropy_loss | -6.35 | +| explained_variance | 0.407 | +| learning_rate | 4.43e-05 | +| loss | -0.0336 | +| n_updates | 62828 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.00011 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1417 | +| iterations | 11754 | +| time_elapsed | 16982 | +| total_timesteps | 24072192 | +| train/ | | +| approx_kl | 0.012285121 | +| clip_fraction | 0.332 | +| clip_range | 0.069 | +| entropy_loss | -6.15 | +| explained_variance | 0.603 | +| learning_rate | 4.43e-05 | +| loss | -0.029 | +| n_updates | 62832 | +| policy_gradient_loss | -0.0191 | +| value_loss | 9.3e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1417 | +| iterations | 11755 | +| time_elapsed | 16983 | +| total_timesteps | 24074240 | +| train/ | | +| approx_kl | 0.0123489965 | +| clip_fraction | 0.301 | +| clip_range | 0.069 | +| entropy_loss | -6.44 | +| explained_variance | 0.299 | +| learning_rate | 4.43e-05 | +| loss | -0.0267 | +| n_updates | 62836 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000247 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1417 | +| iterations | 11756 | +| time_elapsed | 16985 | +| total_timesteps | 24076288 | +| train/ | | +| approx_kl | 0.0110200355 | +| clip_fraction | 0.315 | +| clip_range | 0.069 | +| entropy_loss | -5.72 | +| explained_variance | 0.546 | +| learning_rate | 4.43e-05 | +| loss | -0.0234 | +| n_updates | 62840 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.000225 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1417 | +| iterations | 11757 | +| time_elapsed | 16986 | +| total_timesteps | 24078336 | +| train/ | | +| approx_kl | 0.013975571 | +| clip_fraction | 0.358 | +| clip_range | 0.069 | +| entropy_loss | -5.72 | +| explained_variance | 0.804 | +| learning_rate | 4.43e-05 | +| loss | -0.0312 | +| n_updates | 62844 | +| policy_gradient_loss | -0.0219 | +| value_loss | 5.69e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1417 | +| iterations | 11758 | +| time_elapsed | 16988 | +| total_timesteps | 24080384 | +| train/ | | +| approx_kl | 0.014159514 | +| clip_fraction | 0.358 | +| clip_range | 0.069 | +| entropy_loss | -6.41 | +| explained_variance | 0.13 | +| learning_rate | 4.43e-05 | +| loss | -0.0328 | +| n_updates | 62848 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000121 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1417 | +| iterations | 11759 | +| time_elapsed | 16989 | +| total_timesteps | 24082432 | +| train/ | | +| approx_kl | 0.013772376 | +| clip_fraction | 0.355 | +| clip_range | 0.069 | +| entropy_loss | -6.59 | +| explained_variance | 0.235 | +| learning_rate | 4.43e-05 | +| loss | -0.031 | +| n_updates | 62852 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000219 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1417 | +| iterations | 11760 | +| time_elapsed | 16991 | +| total_timesteps | 24084480 | +| train/ | | +| approx_kl | 0.015236665 | +| clip_fraction | 0.327 | +| clip_range | 0.069 | +| entropy_loss | -6.39 | +| explained_variance | 0.399 | +| learning_rate | 4.43e-05 | +| loss | -0.0258 | +| n_updates | 62856 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000143 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1417 | +| iterations | 11761 | +| time_elapsed | 16992 | +| total_timesteps | 24086528 | +| train/ | | +| approx_kl | 0.01362592 | +| clip_fraction | 0.339 | +| clip_range | 0.069 | +| entropy_loss | -6.91 | +| explained_variance | -0.193 | +| learning_rate | 4.43e-05 | +| loss | -0.0287 | +| n_updates | 62860 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000192 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1417 | +| iterations | 11762 | +| time_elapsed | 16994 | +| total_timesteps | 24088576 | +| train/ | | +| approx_kl | 0.0125032645 | +| clip_fraction | 0.319 | +| clip_range | 0.069 | +| entropy_loss | -6.11 | +| explained_variance | 0.58 | +| learning_rate | 4.43e-05 | +| loss | -0.0259 | +| n_updates | 62864 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000224 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1417 | +| iterations | 11763 | +| time_elapsed | 16995 | +| total_timesteps | 24090624 | +| train/ | | +| approx_kl | 0.01308223 | +| clip_fraction | 0.315 | +| clip_range | 0.069 | +| entropy_loss | -5.66 | +| explained_variance | 0.442 | +| learning_rate | 4.43e-05 | +| loss | -0.0246 | +| n_updates | 62868 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000253 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1417 | +| iterations | 11764 | +| time_elapsed | 16997 | +| total_timesteps | 24092672 | +| train/ | | +| approx_kl | 0.014456001 | +| clip_fraction | 0.32 | +| clip_range | 0.069 | +| entropy_loss | -5.36 | +| explained_variance | 0.548 | +| learning_rate | 4.43e-05 | +| loss | -0.0218 | +| n_updates | 62872 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000193 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1417 | +| iterations | 11765 | +| time_elapsed | 16998 | +| total_timesteps | 24094720 | +| train/ | | +| approx_kl | 0.013594685 | +| clip_fraction | 0.351 | +| clip_range | 0.069 | +| entropy_loss | -6.46 | +| explained_variance | 0.344 | +| learning_rate | 4.43e-05 | +| loss | -0.0361 | +| n_updates | 62876 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000199 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1417 | +| iterations | 11766 | +| time_elapsed | 17000 | +| total_timesteps | 24096768 | +| train/ | | +| approx_kl | 0.013682312 | +| clip_fraction | 0.358 | +| clip_range | 0.069 | +| entropy_loss | -6.33 | +| explained_variance | 0.263 | +| learning_rate | 4.43e-05 | +| loss | -0.0354 | +| n_updates | 62880 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000143 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1417 | +| iterations | 11767 | +| time_elapsed | 17001 | +| total_timesteps | 24098816 | +| train/ | | +| approx_kl | 0.014476161 | +| clip_fraction | 0.331 | +| clip_range | 0.069 | +| entropy_loss | -6.43 | +| explained_variance | 0.0182 | +| learning_rate | 4.43e-05 | +| loss | -0.0302 | +| n_updates | 62884 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000315 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1417 | +| iterations | 11768 | +| time_elapsed | 17003 | +| total_timesteps | 24100864 | +| train/ | | +| approx_kl | 0.014102734 | +| clip_fraction | 0.354 | +| clip_range | 0.069 | +| entropy_loss | -6.2 | +| explained_variance | 0.647 | +| learning_rate | 4.43e-05 | +| loss | -0.0346 | +| n_updates | 62888 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000117 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1417 | +| iterations | 11769 | +| time_elapsed | 17004 | +| total_timesteps | 24102912 | +| train/ | | +| approx_kl | 0.014292756 | +| clip_fraction | 0.355 | +| clip_range | 0.069 | +| entropy_loss | -6.91 | +| explained_variance | -0.279 | +| learning_rate | 4.43e-05 | +| loss | -0.0365 | +| n_updates | 62892 | +| policy_gradient_loss | -0.0221 | +| value_loss | 9.62e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1417 | +| iterations | 11770 | +| time_elapsed | 17006 | +| total_timesteps | 24104960 | +| train/ | | +| approx_kl | 0.012860582 | +| clip_fraction | 0.328 | +| clip_range | 0.069 | +| entropy_loss | -6.16 | +| explained_variance | 0.602 | +| learning_rate | 4.43e-05 | +| loss | -0.0326 | +| n_updates | 62896 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000157 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1417 | +| iterations | 11771 | +| time_elapsed | 17007 | +| total_timesteps | 24107008 | +| train/ | | +| approx_kl | 0.0142775085 | +| clip_fraction | 0.306 | +| clip_range | 0.069 | +| entropy_loss | -5.58 | +| explained_variance | 0.523 | +| learning_rate | 4.43e-05 | +| loss | -0.0269 | +| n_updates | 62900 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000251 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1417 | +| iterations | 11772 | +| time_elapsed | 17009 | +| total_timesteps | 24109056 | +| train/ | | +| approx_kl | 0.011117037 | +| clip_fraction | 0.304 | +| clip_range | 0.069 | +| entropy_loss | -6.21 | +| explained_variance | 0.298 | +| learning_rate | 4.43e-05 | +| loss | -0.028 | +| n_updates | 62904 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000273 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1417 | +| iterations | 11773 | +| time_elapsed | 17010 | +| total_timesteps | 24111104 | +| train/ | | +| approx_kl | 0.014253085 | +| clip_fraction | 0.359 | +| clip_range | 0.069 | +| entropy_loss | -6.86 | +| explained_variance | -0.0815 | +| learning_rate | 4.43e-05 | +| loss | -0.0348 | +| n_updates | 62908 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000169 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1417 | +| iterations | 11774 | +| time_elapsed | 17011 | +| total_timesteps | 24113152 | +| train/ | | +| approx_kl | 0.015615187 | +| clip_fraction | 0.342 | +| clip_range | 0.069 | +| entropy_loss | -6.31 | +| explained_variance | 0.469 | +| learning_rate | 4.43e-05 | +| loss | -0.0293 | +| n_updates | 62912 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000144 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1417 | +| iterations | 11775 | +| time_elapsed | 17013 | +| total_timesteps | 24115200 | +| train/ | | +| approx_kl | 0.010985229 | +| clip_fraction | 0.302 | +| clip_range | 0.069 | +| entropy_loss | -6.62 | +| explained_variance | 0.0631 | +| learning_rate | 4.43e-05 | +| loss | -0.0235 | +| n_updates | 62916 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.000407 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1417 | +| iterations | 11776 | +| time_elapsed | 17014 | +| total_timesteps | 24117248 | +| train/ | | +| approx_kl | 0.0125246225 | +| clip_fraction | 0.352 | +| clip_range | 0.069 | +| entropy_loss | -6.77 | +| explained_variance | 0.176 | +| learning_rate | 4.43e-05 | +| loss | -0.0331 | +| n_updates | 62920 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000179 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1417 | +| iterations | 11777 | +| time_elapsed | 17016 | +| total_timesteps | 24119296 | +| train/ | | +| approx_kl | 0.0136943655 | +| clip_fraction | 0.352 | +| clip_range | 0.069 | +| entropy_loss | -7.12 | +| explained_variance | -0.203 | +| learning_rate | 4.43e-05 | +| loss | -0.0339 | +| n_updates | 62924 | +| policy_gradient_loss | -0.022 | +| value_loss | 0.000167 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1417 | +| iterations | 11778 | +| time_elapsed | 17018 | +| total_timesteps | 24121344 | +| train/ | | +| approx_kl | 0.014727717 | +| clip_fraction | 0.384 | +| clip_range | 0.069 | +| entropy_loss | -6.7 | +| explained_variance | 0.294 | +| learning_rate | 4.43e-05 | +| loss | -0.0337 | +| n_updates | 62928 | +| policy_gradient_loss | -0.0224 | +| value_loss | 0.00012 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1417 | +| iterations | 11779 | +| time_elapsed | 17019 | +| total_timesteps | 24123392 | +| train/ | | +| approx_kl | 0.014277986 | +| clip_fraction | 0.339 | +| clip_range | 0.069 | +| entropy_loss | -5.79 | +| explained_variance | 0.785 | +| learning_rate | 4.43e-05 | +| loss | -0.0309 | +| n_updates | 62932 | +| policy_gradient_loss | -0.02 | +| value_loss | 9.47e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1417 | +| iterations | 11780 | +| time_elapsed | 17020 | +| total_timesteps | 24125440 | +| train/ | | +| approx_kl | 0.009738918 | +| clip_fraction | 0.313 | +| clip_range | 0.069 | +| entropy_loss | -5.62 | +| explained_variance | 0.541 | +| learning_rate | 4.43e-05 | +| loss | -0.0283 | +| n_updates | 62936 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000151 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1417 | +| iterations | 11781 | +| time_elapsed | 17022 | +| total_timesteps | 24127488 | +| train/ | | +| approx_kl | 0.013719554 | +| clip_fraction | 0.368 | +| clip_range | 0.069 | +| entropy_loss | -6.15 | +| explained_variance | 0.462 | +| learning_rate | 4.43e-05 | +| loss | -0.0392 | +| n_updates | 62940 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000144 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1417 | +| iterations | 11782 | +| time_elapsed | 17023 | +| total_timesteps | 24129536 | +| train/ | | +| approx_kl | 0.012709167 | +| clip_fraction | 0.316 | +| clip_range | 0.069 | +| entropy_loss | -5.94 | +| explained_variance | 0.683 | +| learning_rate | 4.43e-05 | +| loss | -0.0363 | +| n_updates | 62944 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000118 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1417 | +| iterations | 11783 | +| time_elapsed | 17025 | +| total_timesteps | 24131584 | +| train/ | | +| approx_kl | 0.013708283 | +| clip_fraction | 0.354 | +| clip_range | 0.069 | +| entropy_loss | -6.74 | +| explained_variance | -0.338 | +| learning_rate | 4.43e-05 | +| loss | -0.0416 | +| n_updates | 62948 | +| policy_gradient_loss | -0.0208 | +| value_loss | 9.9e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1417 | +| iterations | 11784 | +| time_elapsed | 17026 | +| total_timesteps | 24133632 | +| train/ | | +| approx_kl | 0.015202874 | +| clip_fraction | 0.344 | +| clip_range | 0.069 | +| entropy_loss | -6.94 | +| explained_variance | -0.191 | +| learning_rate | 4.43e-05 | +| loss | -0.0314 | +| n_updates | 62952 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000136 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1417 | +| iterations | 11785 | +| time_elapsed | 17028 | +| total_timesteps | 24135680 | +| train/ | | +| approx_kl | 0.012725282 | +| clip_fraction | 0.356 | +| clip_range | 0.069 | +| entropy_loss | -6.84 | +| explained_variance | 0.212 | +| learning_rate | 4.43e-05 | +| loss | -0.0292 | +| n_updates | 62956 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000176 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1417 | +| iterations | 11786 | +| time_elapsed | 17029 | +| total_timesteps | 24137728 | +| train/ | | +| approx_kl | 0.012353989 | +| clip_fraction | 0.337 | +| clip_range | 0.069 | +| entropy_loss | -6.44 | +| explained_variance | 0.576 | +| learning_rate | 4.43e-05 | +| loss | -0.0333 | +| n_updates | 62960 | +| policy_gradient_loss | -0.0206 | +| value_loss | 8.26e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1417 | +| iterations | 11787 | +| time_elapsed | 17031 | +| total_timesteps | 24139776 | +| train/ | | +| approx_kl | 0.012068657 | +| clip_fraction | 0.331 | +| clip_range | 0.069 | +| entropy_loss | -6.56 | +| explained_variance | 0.017 | +| learning_rate | 4.43e-05 | +| loss | -0.025 | +| n_updates | 62964 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.00013 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1417 | +| iterations | 11788 | +| time_elapsed | 17032 | +| total_timesteps | 24141824 | +| train/ | | +| approx_kl | 0.013990391 | +| clip_fraction | 0.37 | +| clip_range | 0.069 | +| entropy_loss | -6.6 | +| explained_variance | 0.442 | +| learning_rate | 4.43e-05 | +| loss | -0.0337 | +| n_updates | 62968 | +| policy_gradient_loss | -0.0206 | +| value_loss | 8.03e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1417 | +| iterations | 11789 | +| time_elapsed | 17034 | +| total_timesteps | 24143872 | +| train/ | | +| approx_kl | 0.01533726 | +| clip_fraction | 0.298 | +| clip_range | 0.069 | +| entropy_loss | -6.51 | +| explained_variance | 0.485 | +| learning_rate | 4.43e-05 | +| loss | -0.033 | +| n_updates | 62972 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000125 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1417 | +| iterations | 11790 | +| time_elapsed | 17035 | +| total_timesteps | 24145920 | +| train/ | | +| approx_kl | 0.012895849 | +| clip_fraction | 0.349 | +| clip_range | 0.069 | +| entropy_loss | -6.53 | +| explained_variance | 0.415 | +| learning_rate | 4.43e-05 | +| loss | -0.0333 | +| n_updates | 62976 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000105 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1417 | +| iterations | 11791 | +| time_elapsed | 17037 | +| total_timesteps | 24147968 | +| train/ | | +| approx_kl | 0.010249458 | +| clip_fraction | 0.296 | +| clip_range | 0.069 | +| entropy_loss | -6.21 | +| explained_variance | 0.6 | +| learning_rate | 4.43e-05 | +| loss | -0.024 | +| n_updates | 62980 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000173 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1417 | +| iterations | 11792 | +| time_elapsed | 17038 | +| total_timesteps | 24150016 | +| train/ | | +| approx_kl | 0.011060251 | +| clip_fraction | 0.29 | +| clip_range | 0.069 | +| entropy_loss | -5.21 | +| explained_variance | 0.498 | +| learning_rate | 4.43e-05 | +| loss | -0.0204 | +| n_updates | 62984 | +| policy_gradient_loss | -0.0132 | +| value_loss | 0.00037 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1417 | +| iterations | 11793 | +| time_elapsed | 17040 | +| total_timesteps | 24152064 | +| train/ | | +| approx_kl | 0.010925226 | +| clip_fraction | 0.34 | +| clip_range | 0.069 | +| entropy_loss | -5.99 | +| explained_variance | 0.468 | +| learning_rate | 4.43e-05 | +| loss | -0.033 | +| n_updates | 62988 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000176 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1417 | +| iterations | 11794 | +| time_elapsed | 17041 | +| total_timesteps | 24154112 | +| train/ | | +| approx_kl | 0.01273692 | +| clip_fraction | 0.341 | +| clip_range | 0.069 | +| entropy_loss | -6.53 | +| explained_variance | 0.101 | +| learning_rate | 4.43e-05 | +| loss | -0.0392 | +| n_updates | 62992 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000124 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1417 | +| iterations | 11795 | +| time_elapsed | 17043 | +| total_timesteps | 24156160 | +| train/ | | +| approx_kl | 0.011984821 | +| clip_fraction | 0.326 | +| clip_range | 0.069 | +| entropy_loss | -6.14 | +| explained_variance | 0.403 | +| learning_rate | 4.43e-05 | +| loss | -0.0341 | +| n_updates | 62996 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000307 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1417 | +| iterations | 11796 | +| time_elapsed | 17044 | +| total_timesteps | 24158208 | +| train/ | | +| approx_kl | 0.010951758 | +| clip_fraction | 0.34 | +| clip_range | 0.069 | +| entropy_loss | -6.34 | +| explained_variance | 0.244 | +| learning_rate | 4.43e-05 | +| loss | -0.0369 | +| n_updates | 63000 | +| policy_gradient_loss | -0.022 | +| value_loss | 0.000151 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1417 | +| iterations | 11797 | +| time_elapsed | 17046 | +| total_timesteps | 24160256 | +| train/ | | +| approx_kl | 0.014576882 | +| clip_fraction | 0.387 | +| clip_range | 0.069 | +| entropy_loss | -6.77 | +| explained_variance | -0.139 | +| learning_rate | 4.43e-05 | +| loss | -0.0321 | +| n_updates | 63004 | +| policy_gradient_loss | -0.0219 | +| value_loss | 0.000115 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1417 | +| iterations | 11798 | +| time_elapsed | 17047 | +| total_timesteps | 24162304 | +| train/ | | +| approx_kl | 0.012197937 | +| clip_fraction | 0.34 | +| clip_range | 0.069 | +| entropy_loss | -7.15 | +| explained_variance | -0.22 | +| learning_rate | 4.43e-05 | +| loss | -0.0342 | +| n_updates | 63008 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1417 | +| iterations | 11799 | +| time_elapsed | 17049 | +| total_timesteps | 24164352 | +| train/ | | +| approx_kl | 0.010410318 | +| clip_fraction | 0.308 | +| clip_range | 0.069 | +| entropy_loss | -6.85 | +| explained_variance | 0.203 | +| learning_rate | 4.43e-05 | +| loss | -0.0225 | +| n_updates | 63012 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000284 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1417 | +| iterations | 11800 | +| time_elapsed | 17050 | +| total_timesteps | 24166400 | +| train/ | | +| approx_kl | 0.009138591 | +| clip_fraction | 0.266 | +| clip_range | 0.069 | +| entropy_loss | -5.74 | +| explained_variance | 0.522 | +| learning_rate | 4.43e-05 | +| loss | -0.0211 | +| n_updates | 63016 | +| policy_gradient_loss | -0.0143 | +| value_loss | 0.00031 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1417 | +| iterations | 11801 | +| time_elapsed | 17052 | +| total_timesteps | 24168448 | +| train/ | | +| approx_kl | 0.007897995 | +| clip_fraction | 0.297 | +| clip_range | 0.069 | +| entropy_loss | -6.21 | +| explained_variance | 0.437 | +| learning_rate | 4.43e-05 | +| loss | -0.0274 | +| n_updates | 63020 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000257 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1417 | +| iterations | 11802 | +| time_elapsed | 17053 | +| total_timesteps | 24170496 | +| train/ | | +| approx_kl | 0.011876252 | +| clip_fraction | 0.339 | +| clip_range | 0.069 | +| entropy_loss | -6.34 | +| explained_variance | 0.18 | +| learning_rate | 4.43e-05 | +| loss | -0.0247 | +| n_updates | 63024 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000348 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1417 | +| iterations | 11803 | +| time_elapsed | 17055 | +| total_timesteps | 24172544 | +| train/ | | +| approx_kl | 0.014530897 | +| clip_fraction | 0.342 | +| clip_range | 0.069 | +| entropy_loss | -5.78 | +| explained_variance | 0.477 | +| learning_rate | 4.43e-05 | +| loss | -0.0312 | +| n_updates | 63028 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.00028 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1417 | +| iterations | 11804 | +| time_elapsed | 17056 | +| total_timesteps | 24174592 | +| train/ | | +| approx_kl | 0.012638731 | +| clip_fraction | 0.342 | +| clip_range | 0.069 | +| entropy_loss | -6.08 | +| explained_variance | 0.572 | +| learning_rate | 4.43e-05 | +| loss | -0.0308 | +| n_updates | 63032 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000134 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1417 | +| iterations | 11805 | +| time_elapsed | 17058 | +| total_timesteps | 24176640 | +| train/ | | +| approx_kl | 0.013067864 | +| clip_fraction | 0.336 | +| clip_range | 0.069 | +| entropy_loss | -6.39 | +| explained_variance | 0.477 | +| learning_rate | 4.43e-05 | +| loss | -0.0376 | +| n_updates | 63036 | +| policy_gradient_loss | -0.0234 | +| value_loss | 9.5e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1417 | +| iterations | 11806 | +| time_elapsed | 17059 | +| total_timesteps | 24178688 | +| train/ | | +| approx_kl | 0.013204068 | +| clip_fraction | 0.345 | +| clip_range | 0.069 | +| entropy_loss | -6.51 | +| explained_variance | 0.243 | +| learning_rate | 4.43e-05 | +| loss | -0.0317 | +| n_updates | 63040 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000219 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1417 | +| iterations | 11807 | +| time_elapsed | 17061 | +| total_timesteps | 24180736 | +| train/ | | +| approx_kl | 0.013868045 | +| clip_fraction | 0.338 | +| clip_range | 0.069 | +| entropy_loss | -5.95 | +| explained_variance | 0.391 | +| learning_rate | 4.43e-05 | +| loss | -0.0251 | +| n_updates | 63044 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000369 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1417 | +| iterations | 11808 | +| time_elapsed | 17062 | +| total_timesteps | 24182784 | +| train/ | | +| approx_kl | 0.013312995 | +| clip_fraction | 0.346 | +| clip_range | 0.069 | +| entropy_loss | -6 | +| explained_variance | 0.48 | +| learning_rate | 4.43e-05 | +| loss | -0.0227 | +| n_updates | 63048 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000235 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1417 | +| iterations | 11809 | +| time_elapsed | 17064 | +| total_timesteps | 24184832 | +| train/ | | +| approx_kl | 0.016414948 | +| clip_fraction | 0.361 | +| clip_range | 0.069 | +| entropy_loss | -6.43 | +| explained_variance | 0.205 | +| learning_rate | 4.43e-05 | +| loss | -0.0371 | +| n_updates | 63052 | +| policy_gradient_loss | -0.0221 | +| value_loss | 0.000118 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1417 | +| iterations | 11810 | +| time_elapsed | 17065 | +| total_timesteps | 24186880 | +| train/ | | +| approx_kl | 0.013399215 | +| clip_fraction | 0.349 | +| clip_range | 0.069 | +| entropy_loss | -7.01 | +| explained_variance | -0.0858 | +| learning_rate | 4.43e-05 | +| loss | -0.0316 | +| n_updates | 63056 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000125 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1417 | +| iterations | 11811 | +| time_elapsed | 17067 | +| total_timesteps | 24188928 | +| train/ | | +| approx_kl | 0.013833482 | +| clip_fraction | 0.347 | +| clip_range | 0.069 | +| entropy_loss | -6.39 | +| explained_variance | 0.407 | +| learning_rate | 4.43e-05 | +| loss | -0.0323 | +| n_updates | 63060 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000192 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1417 | +| iterations | 11812 | +| time_elapsed | 17068 | +| total_timesteps | 24190976 | +| train/ | | +| approx_kl | 0.015789503 | +| clip_fraction | 0.344 | +| clip_range | 0.069 | +| entropy_loss | -6.17 | +| explained_variance | 0.276 | +| learning_rate | 4.43e-05 | +| loss | -0.0263 | +| n_updates | 63064 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000183 | +----------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1417 | +| iterations | 11813 | +| time_elapsed | 17070 | +| total_timesteps | 24193024 | +| train/ | | +| approx_kl | 0.016161 | +| clip_fraction | 0.352 | +| clip_range | 0.069 | +| entropy_loss | -6.19 | +| explained_variance | 0.37 | +| learning_rate | 4.43e-05 | +| loss | -0.032 | +| n_updates | 63068 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000139 | +-------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1417 | +| iterations | 11814 | +| time_elapsed | 17071 | +| total_timesteps | 24195072 | +| train/ | | +| approx_kl | 0.014949277 | +| clip_fraction | 0.371 | +| clip_range | 0.069 | +| entropy_loss | -6.36 | +| explained_variance | 0.445 | +| learning_rate | 4.43e-05 | +| loss | -0.0329 | +| n_updates | 63072 | +| policy_gradient_loss | -0.0225 | +| value_loss | 7.08e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1417 | +| iterations | 11815 | +| time_elapsed | 17073 | +| total_timesteps | 24197120 | +| train/ | | +| approx_kl | 0.014274729 | +| clip_fraction | 0.323 | +| clip_range | 0.069 | +| entropy_loss | -6.13 | +| explained_variance | 0.598 | +| learning_rate | 4.43e-05 | +| loss | -0.0263 | +| n_updates | 63076 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.00018 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1417 | +| iterations | 11816 | +| time_elapsed | 17074 | +| total_timesteps | 24199168 | +| train/ | | +| approx_kl | 0.012057189 | +| clip_fraction | 0.344 | +| clip_range | 0.069 | +| entropy_loss | -6.63 | +| explained_variance | -0.0919 | +| learning_rate | 4.43e-05 | +| loss | -0.036 | +| n_updates | 63080 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.00012 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1417 | +| iterations | 11817 | +| time_elapsed | 17076 | +| total_timesteps | 24201216 | +| train/ | | +| approx_kl | 0.01148144 | +| clip_fraction | 0.312 | +| clip_range | 0.069 | +| entropy_loss | -5.46 | +| explained_variance | 0.524 | +| learning_rate | 4.43e-05 | +| loss | -0.0252 | +| n_updates | 63084 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000386 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1417 | +| iterations | 11818 | +| time_elapsed | 17077 | +| total_timesteps | 24203264 | +| train/ | | +| approx_kl | 0.01334781 | +| clip_fraction | 0.349 | +| clip_range | 0.0689 | +| entropy_loss | -6.15 | +| explained_variance | -0.132 | +| learning_rate | 4.43e-05 | +| loss | -0.0351 | +| n_updates | 63088 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000121 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1417 | +| iterations | 11819 | +| time_elapsed | 17078 | +| total_timesteps | 24205312 | +| train/ | | +| approx_kl | 0.013136806 | +| clip_fraction | 0.344 | +| clip_range | 0.0689 | +| entropy_loss | -6.35 | +| explained_variance | 0.406 | +| learning_rate | 4.43e-05 | +| loss | -0.0218 | +| n_updates | 63092 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000292 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1417 | +| iterations | 11820 | +| time_elapsed | 17080 | +| total_timesteps | 24207360 | +| train/ | | +| approx_kl | 0.014269802 | +| clip_fraction | 0.352 | +| clip_range | 0.0689 | +| entropy_loss | -6.84 | +| explained_variance | -0.168 | +| learning_rate | 4.43e-05 | +| loss | -0.0359 | +| n_updates | 63096 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000166 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1417 | +| iterations | 11821 | +| time_elapsed | 17081 | +| total_timesteps | 24209408 | +| train/ | | +| approx_kl | 0.01564489 | +| clip_fraction | 0.376 | +| clip_range | 0.0689 | +| entropy_loss | -6.53 | +| explained_variance | 0.144 | +| learning_rate | 4.43e-05 | +| loss | -0.023 | +| n_updates | 63100 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000236 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1417 | +| iterations | 11822 | +| time_elapsed | 17083 | +| total_timesteps | 24211456 | +| train/ | | +| approx_kl | 0.011782493 | +| clip_fraction | 0.314 | +| clip_range | 0.0689 | +| entropy_loss | -6.61 | +| explained_variance | 0.305 | +| learning_rate | 4.43e-05 | +| loss | -0.0212 | +| n_updates | 63104 | +| policy_gradient_loss | -0.0145 | +| value_loss | 0.00024 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1417 | +| iterations | 11823 | +| time_elapsed | 17084 | +| total_timesteps | 24213504 | +| train/ | | +| approx_kl | 0.012391507 | +| clip_fraction | 0.309 | +| clip_range | 0.0689 | +| entropy_loss | -6.4 | +| explained_variance | 0.463 | +| learning_rate | 4.42e-05 | +| loss | -0.027 | +| n_updates | 63108 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000177 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1417 | +| iterations | 11824 | +| time_elapsed | 17086 | +| total_timesteps | 24215552 | +| train/ | | +| approx_kl | 0.013444314 | +| clip_fraction | 0.332 | +| clip_range | 0.0689 | +| entropy_loss | -6.47 | +| explained_variance | 0.292 | +| learning_rate | 4.42e-05 | +| loss | -0.0321 | +| n_updates | 63112 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000371 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1417 | +| iterations | 11825 | +| time_elapsed | 17087 | +| total_timesteps | 24217600 | +| train/ | | +| approx_kl | 0.01395099 | +| clip_fraction | 0.368 | +| clip_range | 0.0689 | +| entropy_loss | -5.92 | +| explained_variance | 0.681 | +| learning_rate | 4.42e-05 | +| loss | -0.0363 | +| n_updates | 63116 | +| policy_gradient_loss | -0.023 | +| value_loss | 9.72e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1417 | +| iterations | 11826 | +| time_elapsed | 17089 | +| total_timesteps | 24219648 | +| train/ | | +| approx_kl | 0.013442982 | +| clip_fraction | 0.342 | +| clip_range | 0.0689 | +| entropy_loss | -6.32 | +| explained_variance | 0.477 | +| learning_rate | 4.42e-05 | +| loss | -0.0337 | +| n_updates | 63120 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000168 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1417 | +| iterations | 11827 | +| time_elapsed | 17090 | +| total_timesteps | 24221696 | +| train/ | | +| approx_kl | 0.012738342 | +| clip_fraction | 0.33 | +| clip_range | 0.0689 | +| entropy_loss | -6.25 | +| explained_variance | 0.374 | +| learning_rate | 4.42e-05 | +| loss | -0.0237 | +| n_updates | 63124 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000209 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1417 | +| iterations | 11828 | +| time_elapsed | 17092 | +| total_timesteps | 24223744 | +| train/ | | +| approx_kl | 0.011955326 | +| clip_fraction | 0.339 | +| clip_range | 0.0689 | +| entropy_loss | -6.5 | +| explained_variance | 0.257 | +| learning_rate | 4.42e-05 | +| loss | -0.0341 | +| n_updates | 63128 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000209 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1417 | +| iterations | 11829 | +| time_elapsed | 17093 | +| total_timesteps | 24225792 | +| train/ | | +| approx_kl | 0.015091486 | +| clip_fraction | 0.385 | +| clip_range | 0.0689 | +| entropy_loss | -6.39 | +| explained_variance | 0.31 | +| learning_rate | 4.42e-05 | +| loss | -0.0422 | +| n_updates | 63132 | +| policy_gradient_loss | -0.0221 | +| value_loss | 0.000137 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1417 | +| iterations | 11830 | +| time_elapsed | 17095 | +| total_timesteps | 24227840 | +| train/ | | +| approx_kl | 0.013874665 | +| clip_fraction | 0.351 | +| clip_range | 0.0689 | +| entropy_loss | -6.04 | +| explained_variance | 0.462 | +| learning_rate | 4.42e-05 | +| loss | -0.0297 | +| n_updates | 63136 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000134 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1417 | +| iterations | 11831 | +| time_elapsed | 17096 | +| total_timesteps | 24229888 | +| train/ | | +| approx_kl | 0.013790783 | +| clip_fraction | 0.333 | +| clip_range | 0.0689 | +| entropy_loss | -6.42 | +| explained_variance | 0.381 | +| learning_rate | 4.42e-05 | +| loss | -0.0274 | +| n_updates | 63140 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000247 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1417 | +| iterations | 11832 | +| time_elapsed | 17097 | +| total_timesteps | 24231936 | +| train/ | | +| approx_kl | 0.011135545 | +| clip_fraction | 0.339 | +| clip_range | 0.0689 | +| entropy_loss | -6.82 | +| explained_variance | -0.105 | +| learning_rate | 4.42e-05 | +| loss | -0.0325 | +| n_updates | 63144 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000231 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1417 | +| iterations | 11833 | +| time_elapsed | 17099 | +| total_timesteps | 24233984 | +| train/ | | +| approx_kl | 0.011108835 | +| clip_fraction | 0.329 | +| clip_range | 0.0689 | +| entropy_loss | -6.44 | +| explained_variance | 0.462 | +| learning_rate | 4.42e-05 | +| loss | -0.0307 | +| n_updates | 63148 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000165 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1417 | +| iterations | 11834 | +| time_elapsed | 17100 | +| total_timesteps | 24236032 | +| train/ | | +| approx_kl | 0.011126387 | +| clip_fraction | 0.311 | +| clip_range | 0.0689 | +| entropy_loss | -6.46 | +| explained_variance | 0.456 | +| learning_rate | 4.42e-05 | +| loss | -0.0281 | +| n_updates | 63152 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000194 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1417 | +| iterations | 11835 | +| time_elapsed | 17102 | +| total_timesteps | 24238080 | +| train/ | | +| approx_kl | 0.015322427 | +| clip_fraction | 0.325 | +| clip_range | 0.0689 | +| entropy_loss | -6.12 | +| explained_variance | 0.482 | +| learning_rate | 4.42e-05 | +| loss | -0.0301 | +| n_updates | 63156 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000133 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1417 | +| iterations | 11836 | +| time_elapsed | 17103 | +| total_timesteps | 24240128 | +| train/ | | +| approx_kl | 0.015183201 | +| clip_fraction | 0.381 | +| clip_range | 0.0689 | +| entropy_loss | -6.34 | +| explained_variance | 0.289 | +| learning_rate | 4.42e-05 | +| loss | -0.0351 | +| n_updates | 63160 | +| policy_gradient_loss | -0.0228 | +| value_loss | 0.000102 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1417 | +| iterations | 11837 | +| time_elapsed | 17105 | +| total_timesteps | 24242176 | +| train/ | | +| approx_kl | 0.018357847 | +| clip_fraction | 0.346 | +| clip_range | 0.0689 | +| entropy_loss | -6.32 | +| explained_variance | 0.196 | +| learning_rate | 4.42e-05 | +| loss | -0.0308 | +| n_updates | 63164 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.00018 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1417 | +| iterations | 11838 | +| time_elapsed | 17106 | +| total_timesteps | 24244224 | +| train/ | | +| approx_kl | 0.01571616 | +| clip_fraction | 0.358 | +| clip_range | 0.0689 | +| entropy_loss | -6.33 | +| explained_variance | 0.207 | +| learning_rate | 4.42e-05 | +| loss | -0.0383 | +| n_updates | 63168 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000133 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1417 | +| iterations | 11839 | +| time_elapsed | 17108 | +| total_timesteps | 24246272 | +| train/ | | +| approx_kl | 0.017133394 | +| clip_fraction | 0.355 | +| clip_range | 0.0689 | +| entropy_loss | -6.47 | +| explained_variance | 0.535 | +| learning_rate | 4.42e-05 | +| loss | -0.0281 | +| n_updates | 63172 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000102 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1417 | +| iterations | 11840 | +| time_elapsed | 17109 | +| total_timesteps | 24248320 | +| train/ | | +| approx_kl | 0.014809786 | +| clip_fraction | 0.331 | +| clip_range | 0.0689 | +| entropy_loss | -6.38 | +| explained_variance | 0.207 | +| learning_rate | 4.42e-05 | +| loss | -0.0307 | +| n_updates | 63176 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000277 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1417 | +| iterations | 11841 | +| time_elapsed | 17111 | +| total_timesteps | 24250368 | +| train/ | | +| approx_kl | 0.016099416 | +| clip_fraction | 0.358 | +| clip_range | 0.0689 | +| entropy_loss | -6.32 | +| explained_variance | 0.387 | +| learning_rate | 4.42e-05 | +| loss | -0.035 | +| n_updates | 63180 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000187 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1417 | +| iterations | 11842 | +| time_elapsed | 17112 | +| total_timesteps | 24252416 | +| train/ | | +| approx_kl | 0.012942359 | +| clip_fraction | 0.36 | +| clip_range | 0.0689 | +| entropy_loss | -6.22 | +| explained_variance | 0.438 | +| learning_rate | 4.42e-05 | +| loss | -0.0343 | +| n_updates | 63184 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.00021 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1417 | +| iterations | 11843 | +| time_elapsed | 17114 | +| total_timesteps | 24254464 | +| train/ | | +| approx_kl | 0.014040882 | +| clip_fraction | 0.353 | +| clip_range | 0.0689 | +| entropy_loss | -6.86 | +| explained_variance | -0.0442 | +| learning_rate | 4.42e-05 | +| loss | -0.0305 | +| n_updates | 63188 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000211 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1417 | +| iterations | 11844 | +| time_elapsed | 17115 | +| total_timesteps | 24256512 | +| train/ | | +| approx_kl | 0.014166819 | +| clip_fraction | 0.359 | +| clip_range | 0.0689 | +| entropy_loss | -6.59 | +| explained_variance | 0.318 | +| learning_rate | 4.42e-05 | +| loss | -0.0352 | +| n_updates | 63192 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000148 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1417 | +| iterations | 11845 | +| time_elapsed | 17117 | +| total_timesteps | 24258560 | +| train/ | | +| approx_kl | 0.01427822 | +| clip_fraction | 0.354 | +| clip_range | 0.0689 | +| entropy_loss | -6.69 | +| explained_variance | 0.364 | +| learning_rate | 4.42e-05 | +| loss | -0.0349 | +| n_updates | 63196 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000112 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1417 | +| iterations | 11846 | +| time_elapsed | 17118 | +| total_timesteps | 24260608 | +| train/ | | +| approx_kl | 0.014720412 | +| clip_fraction | 0.334 | +| clip_range | 0.0689 | +| entropy_loss | -6.53 | +| explained_variance | 0.287 | +| learning_rate | 4.42e-05 | +| loss | -0.0229 | +| n_updates | 63200 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.00028 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1417 | +| iterations | 11847 | +| time_elapsed | 17120 | +| total_timesteps | 24262656 | +| train/ | | +| approx_kl | 0.015039895 | +| clip_fraction | 0.34 | +| clip_range | 0.0689 | +| entropy_loss | -6.5 | +| explained_variance | 0.437 | +| learning_rate | 4.42e-05 | +| loss | -0.0354 | +| n_updates | 63204 | +| policy_gradient_loss | -0.0222 | +| value_loss | 8.17e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1417 | +| iterations | 11848 | +| time_elapsed | 17121 | +| total_timesteps | 24264704 | +| train/ | | +| approx_kl | 0.013440367 | +| clip_fraction | 0.343 | +| clip_range | 0.0689 | +| entropy_loss | -6.04 | +| explained_variance | 0.629 | +| learning_rate | 4.42e-05 | +| loss | -0.0285 | +| n_updates | 63208 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000115 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1417 | +| iterations | 11849 | +| time_elapsed | 17123 | +| total_timesteps | 24266752 | +| train/ | | +| approx_kl | 0.012410717 | +| clip_fraction | 0.34 | +| clip_range | 0.0689 | +| entropy_loss | -6.02 | +| explained_variance | 0.337 | +| learning_rate | 4.42e-05 | +| loss | -0.0313 | +| n_updates | 63212 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000211 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1417 | +| iterations | 11850 | +| time_elapsed | 17124 | +| total_timesteps | 24268800 | +| train/ | | +| approx_kl | 0.013594938 | +| clip_fraction | 0.295 | +| clip_range | 0.0689 | +| entropy_loss | -6.11 | +| explained_variance | 0.649 | +| learning_rate | 4.42e-05 | +| loss | -0.0294 | +| n_updates | 63216 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000146 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1417 | +| iterations | 11851 | +| time_elapsed | 17126 | +| total_timesteps | 24270848 | +| train/ | | +| approx_kl | 0.01146362 | +| clip_fraction | 0.328 | +| clip_range | 0.0689 | +| entropy_loss | -6.39 | +| explained_variance | 0.0298 | +| learning_rate | 4.42e-05 | +| loss | -0.031 | +| n_updates | 63220 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000173 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1417 | +| iterations | 11852 | +| time_elapsed | 17127 | +| total_timesteps | 24272896 | +| train/ | | +| approx_kl | 0.013645679 | +| clip_fraction | 0.36 | +| clip_range | 0.0689 | +| entropy_loss | -6.71 | +| explained_variance | 0.261 | +| learning_rate | 4.42e-05 | +| loss | -0.0388 | +| n_updates | 63224 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.00012 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1417 | +| iterations | 11853 | +| time_elapsed | 17129 | +| total_timesteps | 24274944 | +| train/ | | +| approx_kl | 0.012942938 | +| clip_fraction | 0.331 | +| clip_range | 0.0689 | +| entropy_loss | -6.51 | +| explained_variance | 0.208 | +| learning_rate | 4.42e-05 | +| loss | -0.0263 | +| n_updates | 63228 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000293 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1417 | +| iterations | 11854 | +| time_elapsed | 17130 | +| total_timesteps | 24276992 | +| train/ | | +| approx_kl | 0.01623879 | +| clip_fraction | 0.343 | +| clip_range | 0.0689 | +| entropy_loss | -6.2 | +| explained_variance | 0.426 | +| learning_rate | 4.42e-05 | +| loss | -0.0247 | +| n_updates | 63232 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000223 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1417 | +| iterations | 11855 | +| time_elapsed | 17132 | +| total_timesteps | 24279040 | +| train/ | | +| approx_kl | 0.016109766 | +| clip_fraction | 0.365 | +| clip_range | 0.0689 | +| entropy_loss | -6.01 | +| explained_variance | 0.538 | +| learning_rate | 4.42e-05 | +| loss | -0.0342 | +| n_updates | 63236 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000173 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1417 | +| iterations | 11856 | +| time_elapsed | 17133 | +| total_timesteps | 24281088 | +| train/ | | +| approx_kl | 0.014695742 | +| clip_fraction | 0.348 | +| clip_range | 0.0689 | +| entropy_loss | -6.76 | +| explained_variance | -0.0842 | +| learning_rate | 4.42e-05 | +| loss | -0.0361 | +| n_updates | 63240 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000219 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1417 | +| iterations | 11857 | +| time_elapsed | 17135 | +| total_timesteps | 24283136 | +| train/ | | +| approx_kl | 0.0125650745 | +| clip_fraction | 0.349 | +| clip_range | 0.0689 | +| entropy_loss | -6.66 | +| explained_variance | 0.139 | +| learning_rate | 4.42e-05 | +| loss | -0.0248 | +| n_updates | 63244 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000169 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1417 | +| iterations | 11858 | +| time_elapsed | 17136 | +| total_timesteps | 24285184 | +| train/ | | +| approx_kl | 0.012958633 | +| clip_fraction | 0.367 | +| clip_range | 0.0689 | +| entropy_loss | -6.4 | +| explained_variance | 0.0976 | +| learning_rate | 4.42e-05 | +| loss | -0.0351 | +| n_updates | 63248 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000144 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1417 | +| iterations | 11859 | +| time_elapsed | 17138 | +| total_timesteps | 24287232 | +| train/ | | +| approx_kl | 0.01218063 | +| clip_fraction | 0.338 | +| clip_range | 0.0689 | +| entropy_loss | -6.54 | +| explained_variance | 0.582 | +| learning_rate | 4.42e-05 | +| loss | -0.031 | +| n_updates | 63252 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000126 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1417 | +| iterations | 11860 | +| time_elapsed | 17139 | +| total_timesteps | 24289280 | +| train/ | | +| approx_kl | 0.012829889 | +| clip_fraction | 0.319 | +| clip_range | 0.0689 | +| entropy_loss | -5.96 | +| explained_variance | 0.452 | +| learning_rate | 4.42e-05 | +| loss | -0.0315 | +| n_updates | 63256 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000303 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1417 | +| iterations | 11861 | +| time_elapsed | 17141 | +| total_timesteps | 24291328 | +| train/ | | +| approx_kl | 0.012985444 | +| clip_fraction | 0.349 | +| clip_range | 0.0689 | +| entropy_loss | -6.55 | +| explained_variance | -0.193 | +| learning_rate | 4.42e-05 | +| loss | -0.0348 | +| n_updates | 63260 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.00012 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1417 | +| iterations | 11862 | +| time_elapsed | 17142 | +| total_timesteps | 24293376 | +| train/ | | +| approx_kl | 0.012934163 | +| clip_fraction | 0.337 | +| clip_range | 0.0689 | +| entropy_loss | -6.69 | +| explained_variance | 0.0414 | +| learning_rate | 4.42e-05 | +| loss | -0.0314 | +| n_updates | 63264 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000339 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1417 | +| iterations | 11863 | +| time_elapsed | 17144 | +| total_timesteps | 24295424 | +| train/ | | +| approx_kl | 0.017110124 | +| clip_fraction | 0.358 | +| clip_range | 0.0689 | +| entropy_loss | -6.67 | +| explained_variance | -0.112 | +| learning_rate | 4.42e-05 | +| loss | -0.0326 | +| n_updates | 63268 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000131 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1417 | +| iterations | 11864 | +| time_elapsed | 17145 | +| total_timesteps | 24297472 | +| train/ | | +| approx_kl | 0.0136985835 | +| clip_fraction | 0.342 | +| clip_range | 0.0689 | +| entropy_loss | -6.63 | +| explained_variance | 0.296 | +| learning_rate | 4.42e-05 | +| loss | -0.0324 | +| n_updates | 63272 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000164 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1417 | +| iterations | 11865 | +| time_elapsed | 17147 | +| total_timesteps | 24299520 | +| train/ | | +| approx_kl | 0.015502757 | +| clip_fraction | 0.361 | +| clip_range | 0.0689 | +| entropy_loss | -5.96 | +| explained_variance | 0.499 | +| learning_rate | 4.42e-05 | +| loss | -0.0307 | +| n_updates | 63276 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000193 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1417 | +| iterations | 11866 | +| time_elapsed | 17148 | +| total_timesteps | 24301568 | +| train/ | | +| approx_kl | 0.0138895195 | +| clip_fraction | 0.345 | +| clip_range | 0.0689 | +| entropy_loss | -6.69 | +| explained_variance | -0.0963 | +| learning_rate | 4.42e-05 | +| loss | -0.032 | +| n_updates | 63280 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000215 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1417 | +| iterations | 11867 | +| time_elapsed | 17149 | +| total_timesteps | 24303616 | +| train/ | | +| approx_kl | 0.012366595 | +| clip_fraction | 0.328 | +| clip_range | 0.0689 | +| entropy_loss | -6.77 | +| explained_variance | 0.321 | +| learning_rate | 4.42e-05 | +| loss | -0.0294 | +| n_updates | 63284 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000183 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1417 | +| iterations | 11868 | +| time_elapsed | 17151 | +| total_timesteps | 24305664 | +| train/ | | +| approx_kl | 0.014780937 | +| clip_fraction | 0.329 | +| clip_range | 0.0689 | +| entropy_loss | -6.26 | +| explained_variance | 0.579 | +| learning_rate | 4.42e-05 | +| loss | -0.0369 | +| n_updates | 63288 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000103 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1417 | +| iterations | 11869 | +| time_elapsed | 17153 | +| total_timesteps | 24307712 | +| train/ | | +| approx_kl | 0.0111827385 | +| clip_fraction | 0.335 | +| clip_range | 0.0689 | +| entropy_loss | -6.77 | +| explained_variance | 0.235 | +| learning_rate | 4.42e-05 | +| loss | -0.0309 | +| n_updates | 63292 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000163 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1417 | +| iterations | 11870 | +| time_elapsed | 17154 | +| total_timesteps | 24309760 | +| train/ | | +| approx_kl | 0.012815794 | +| clip_fraction | 0.3 | +| clip_range | 0.0689 | +| entropy_loss | -5.58 | +| explained_variance | 0.673 | +| learning_rate | 4.42e-05 | +| loss | -0.0203 | +| n_updates | 63296 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000223 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1417 | +| iterations | 11871 | +| time_elapsed | 17156 | +| total_timesteps | 24311808 | +| train/ | | +| approx_kl | 0.014930086 | +| clip_fraction | 0.333 | +| clip_range | 0.0689 | +| entropy_loss | -5.97 | +| explained_variance | 0.504 | +| learning_rate | 4.42e-05 | +| loss | -0.0303 | +| n_updates | 63300 | +| policy_gradient_loss | -0.0192 | +| value_loss | 7.93e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1417 | +| iterations | 11872 | +| time_elapsed | 17157 | +| total_timesteps | 24313856 | +| train/ | | +| approx_kl | 0.011308003 | +| clip_fraction | 0.321 | +| clip_range | 0.0689 | +| entropy_loss | -6.63 | +| explained_variance | 0.276 | +| learning_rate | 4.42e-05 | +| loss | -0.0294 | +| n_updates | 63304 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000196 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1417 | +| iterations | 11873 | +| time_elapsed | 17159 | +| total_timesteps | 24315904 | +| train/ | | +| approx_kl | 0.012659017 | +| clip_fraction | 0.354 | +| clip_range | 0.0689 | +| entropy_loss | -6.78 | +| explained_variance | 0.276 | +| learning_rate | 4.42e-05 | +| loss | -0.0323 | +| n_updates | 63308 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000154 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1417 | +| iterations | 11874 | +| time_elapsed | 17160 | +| total_timesteps | 24317952 | +| train/ | | +| approx_kl | 0.015957035 | +| clip_fraction | 0.333 | +| clip_range | 0.0689 | +| entropy_loss | -6.56 | +| explained_variance | 0.407 | +| learning_rate | 4.42e-05 | +| loss | -0.0323 | +| n_updates | 63312 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000125 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1417 | +| iterations | 11875 | +| time_elapsed | 17162 | +| total_timesteps | 24320000 | +| train/ | | +| approx_kl | 0.010780321 | +| clip_fraction | 0.283 | +| clip_range | 0.0689 | +| entropy_loss | -6.96 | +| explained_variance | 0.167 | +| learning_rate | 4.42e-05 | +| loss | -0.0241 | +| n_updates | 63316 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000369 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1417 | +| iterations | 11876 | +| time_elapsed | 17163 | +| total_timesteps | 24322048 | +| train/ | | +| approx_kl | 0.012792239 | +| clip_fraction | 0.29 | +| clip_range | 0.0689 | +| entropy_loss | -5.98 | +| explained_variance | 0.403 | +| learning_rate | 4.42e-05 | +| loss | -0.019 | +| n_updates | 63320 | +| policy_gradient_loss | -0.0144 | +| value_loss | 0.000299 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1417 | +| iterations | 11877 | +| time_elapsed | 17165 | +| total_timesteps | 24324096 | +| train/ | | +| approx_kl | 0.0129627 | +| clip_fraction | 0.317 | +| clip_range | 0.0689 | +| entropy_loss | -6.34 | +| explained_variance | 0.131 | +| learning_rate | 4.42e-05 | +| loss | -0.0327 | +| n_updates | 63324 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000257 | +--------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1417 | +| iterations | 11878 | +| time_elapsed | 17166 | +| total_timesteps | 24326144 | +| train/ | | +| approx_kl | 0.0122624235 | +| clip_fraction | 0.334 | +| clip_range | 0.0689 | +| entropy_loss | -5.82 | +| explained_variance | 0.533 | +| learning_rate | 4.42e-05 | +| loss | -0.0271 | +| n_updates | 63328 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000222 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1417 | +| iterations | 11879 | +| time_elapsed | 17168 | +| total_timesteps | 24328192 | +| train/ | | +| approx_kl | 0.014317307 | +| clip_fraction | 0.349 | +| clip_range | 0.0689 | +| entropy_loss | -6.43 | +| explained_variance | -0.107 | +| learning_rate | 4.42e-05 | +| loss | -0.0274 | +| n_updates | 63332 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000102 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1417 | +| iterations | 11880 | +| time_elapsed | 17169 | +| total_timesteps | 24330240 | +| train/ | | +| approx_kl | 0.0116018485 | +| clip_fraction | 0.354 | +| clip_range | 0.0689 | +| entropy_loss | -7.1 | +| explained_variance | -0.324 | +| learning_rate | 4.42e-05 | +| loss | -0.0327 | +| n_updates | 63336 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000106 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1417 | +| iterations | 11881 | +| time_elapsed | 17171 | +| total_timesteps | 24332288 | +| train/ | | +| approx_kl | 0.012726509 | +| clip_fraction | 0.319 | +| clip_range | 0.0689 | +| entropy_loss | -6.63 | +| explained_variance | 0.363 | +| learning_rate | 4.42e-05 | +| loss | -0.0234 | +| n_updates | 63340 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000164 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1417 | +| iterations | 11882 | +| time_elapsed | 17172 | +| total_timesteps | 24334336 | +| train/ | | +| approx_kl | 0.01028814 | +| clip_fraction | 0.313 | +| clip_range | 0.0689 | +| entropy_loss | -6.42 | +| explained_variance | 0.541 | +| learning_rate | 4.42e-05 | +| loss | -0.0317 | +| n_updates | 63344 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000183 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1417 | +| iterations | 11883 | +| time_elapsed | 17174 | +| total_timesteps | 24336384 | +| train/ | | +| approx_kl | 0.011247955 | +| clip_fraction | 0.313 | +| clip_range | 0.0689 | +| entropy_loss | -6.36 | +| explained_variance | 0.546 | +| learning_rate | 4.42e-05 | +| loss | -0.0264 | +| n_updates | 63348 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000135 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1417 | +| iterations | 11884 | +| time_elapsed | 17175 | +| total_timesteps | 24338432 | +| train/ | | +| approx_kl | 0.012870381 | +| clip_fraction | 0.328 | +| clip_range | 0.0689 | +| entropy_loss | -6.71 | +| explained_variance | -0.135 | +| learning_rate | 4.42e-05 | +| loss | -0.0296 | +| n_updates | 63352 | +| policy_gradient_loss | -0.0183 | +| value_loss | 9.24e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1417 | +| iterations | 11885 | +| time_elapsed | 17177 | +| total_timesteps | 24340480 | +| train/ | | +| approx_kl | 0.011454815 | +| clip_fraction | 0.319 | +| clip_range | 0.0689 | +| entropy_loss | -6.21 | +| explained_variance | 0.698 | +| learning_rate | 4.42e-05 | +| loss | -0.0299 | +| n_updates | 63356 | +| policy_gradient_loss | -0.0173 | +| value_loss | 9.38e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1417 | +| iterations | 11886 | +| time_elapsed | 17178 | +| total_timesteps | 24342528 | +| train/ | | +| approx_kl | 0.01325382 | +| clip_fraction | 0.336 | +| clip_range | 0.0689 | +| entropy_loss | -5.99 | +| explained_variance | 0.676 | +| learning_rate | 4.42e-05 | +| loss | -0.0281 | +| n_updates | 63360 | +| policy_gradient_loss | -0.02 | +| value_loss | 7.75e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1417 | +| iterations | 11887 | +| time_elapsed | 17180 | +| total_timesteps | 24344576 | +| train/ | | +| approx_kl | 0.012943691 | +| clip_fraction | 0.321 | +| clip_range | 0.0689 | +| entropy_loss | -6.14 | +| explained_variance | 0.553 | +| learning_rate | 4.42e-05 | +| loss | -0.0317 | +| n_updates | 63364 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000154 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1417 | +| iterations | 11888 | +| time_elapsed | 17181 | +| total_timesteps | 24346624 | +| train/ | | +| approx_kl | 0.014053979 | +| clip_fraction | 0.353 | +| clip_range | 0.0689 | +| entropy_loss | -6.49 | +| explained_variance | 0.321 | +| learning_rate | 4.42e-05 | +| loss | -0.0273 | +| n_updates | 63368 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000122 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1417 | +| iterations | 11889 | +| time_elapsed | 17183 | +| total_timesteps | 24348672 | +| train/ | | +| approx_kl | 0.013988778 | +| clip_fraction | 0.323 | +| clip_range | 0.0689 | +| entropy_loss | -6.5 | +| explained_variance | 0.174 | +| learning_rate | 4.42e-05 | +| loss | -0.0311 | +| n_updates | 63372 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000339 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1417 | +| iterations | 11890 | +| time_elapsed | 17184 | +| total_timesteps | 24350720 | +| train/ | | +| approx_kl | 0.011184272 | +| clip_fraction | 0.315 | +| clip_range | 0.0689 | +| entropy_loss | -6.02 | +| explained_variance | 0.341 | +| learning_rate | 4.42e-05 | +| loss | -0.0243 | +| n_updates | 63376 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000461 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1417 | +| iterations | 11891 | +| time_elapsed | 17186 | +| total_timesteps | 24352768 | +| train/ | | +| approx_kl | 0.013908604 | +| clip_fraction | 0.328 | +| clip_range | 0.0689 | +| entropy_loss | -5.86 | +| explained_variance | 0.388 | +| learning_rate | 4.42e-05 | +| loss | -0.0335 | +| n_updates | 63380 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000238 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1416 | +| iterations | 11892 | +| time_elapsed | 17187 | +| total_timesteps | 24354816 | +| train/ | | +| approx_kl | 0.013840639 | +| clip_fraction | 0.315 | +| clip_range | 0.0689 | +| entropy_loss | -6.26 | +| explained_variance | 0.378 | +| learning_rate | 4.42e-05 | +| loss | -0.0254 | +| n_updates | 63384 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000323 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1416 | +| iterations | 11893 | +| time_elapsed | 17189 | +| total_timesteps | 24356864 | +| train/ | | +| approx_kl | 0.014454848 | +| clip_fraction | 0.298 | +| clip_range | 0.0689 | +| entropy_loss | -5.41 | +| explained_variance | 0.387 | +| learning_rate | 4.42e-05 | +| loss | -0.0255 | +| n_updates | 63388 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000422 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1416 | +| iterations | 11894 | +| time_elapsed | 17190 | +| total_timesteps | 24358912 | +| train/ | | +| approx_kl | 0.014214476 | +| clip_fraction | 0.357 | +| clip_range | 0.0689 | +| entropy_loss | -6.11 | +| explained_variance | 0.0519 | +| learning_rate | 4.42e-05 | +| loss | -0.0352 | +| n_updates | 63392 | +| policy_gradient_loss | -0.0221 | +| value_loss | 0.000161 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1416 | +| iterations | 11895 | +| time_elapsed | 17192 | +| total_timesteps | 24360960 | +| train/ | | +| approx_kl | 0.016623948 | +| clip_fraction | 0.375 | +| clip_range | 0.0689 | +| entropy_loss | -5.9 | +| explained_variance | 0.492 | +| learning_rate | 4.42e-05 | +| loss | -0.035 | +| n_updates | 63396 | +| policy_gradient_loss | -0.0224 | +| value_loss | 0.000146 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1416 | +| iterations | 11896 | +| time_elapsed | 17193 | +| total_timesteps | 24363008 | +| train/ | | +| approx_kl | 0.014191594 | +| clip_fraction | 0.321 | +| clip_range | 0.0689 | +| entropy_loss | -6.55 | +| explained_variance | 0.289 | +| learning_rate | 4.42e-05 | +| loss | -0.0195 | +| n_updates | 63400 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000233 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1416 | +| iterations | 11897 | +| time_elapsed | 17195 | +| total_timesteps | 24365056 | +| train/ | | +| approx_kl | 0.013056042 | +| clip_fraction | 0.354 | +| clip_range | 0.0689 | +| entropy_loss | -6.57 | +| explained_variance | 0.259 | +| learning_rate | 4.42e-05 | +| loss | -0.0379 | +| n_updates | 63404 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000164 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1416 | +| iterations | 11898 | +| time_elapsed | 17196 | +| total_timesteps | 24367104 | +| train/ | | +| approx_kl | 0.0120482575 | +| clip_fraction | 0.319 | +| clip_range | 0.0689 | +| entropy_loss | -6.63 | +| explained_variance | 0.234 | +| learning_rate | 4.42e-05 | +| loss | -0.0314 | +| n_updates | 63408 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000313 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1416 | +| iterations | 11899 | +| time_elapsed | 17198 | +| total_timesteps | 24369152 | +| train/ | | +| approx_kl | 0.013643077 | +| clip_fraction | 0.375 | +| clip_range | 0.0689 | +| entropy_loss | -6.68 | +| explained_variance | -0.28 | +| learning_rate | 4.42e-05 | +| loss | -0.0419 | +| n_updates | 63412 | +| policy_gradient_loss | -0.0239 | +| value_loss | 8.06e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1416 | +| iterations | 11900 | +| time_elapsed | 17199 | +| total_timesteps | 24371200 | +| train/ | | +| approx_kl | 0.013243492 | +| clip_fraction | 0.333 | +| clip_range | 0.0689 | +| entropy_loss | -6.07 | +| explained_variance | 0.267 | +| learning_rate | 4.42e-05 | +| loss | -0.0261 | +| n_updates | 63416 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000412 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1416 | +| iterations | 11901 | +| time_elapsed | 17201 | +| total_timesteps | 24373248 | +| train/ | | +| approx_kl | 0.012329215 | +| clip_fraction | 0.339 | +| clip_range | 0.0689 | +| entropy_loss | -6.23 | +| explained_variance | 0.293 | +| learning_rate | 4.42e-05 | +| loss | -0.032 | +| n_updates | 63420 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000196 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1416 | +| iterations | 11902 | +| time_elapsed | 17202 | +| total_timesteps | 24375296 | +| train/ | | +| approx_kl | 0.011319455 | +| clip_fraction | 0.318 | +| clip_range | 0.0689 | +| entropy_loss | -6.28 | +| explained_variance | 0.246 | +| learning_rate | 4.42e-05 | +| loss | -0.0263 | +| n_updates | 63424 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000396 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1416 | +| iterations | 11903 | +| time_elapsed | 17204 | +| total_timesteps | 24377344 | +| train/ | | +| approx_kl | 0.014335651 | +| clip_fraction | 0.353 | +| clip_range | 0.0689 | +| entropy_loss | -6.43 | +| explained_variance | -0.0904 | +| learning_rate | 4.42e-05 | +| loss | -0.0335 | +| n_updates | 63428 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000209 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1416 | +| iterations | 11904 | +| time_elapsed | 17205 | +| total_timesteps | 24379392 | +| train/ | | +| approx_kl | 0.014566534 | +| clip_fraction | 0.334 | +| clip_range | 0.0689 | +| entropy_loss | -5.45 | +| explained_variance | 0.543 | +| learning_rate | 4.42e-05 | +| loss | -0.0258 | +| n_updates | 63432 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000212 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1416 | +| iterations | 11905 | +| time_elapsed | 17206 | +| total_timesteps | 24381440 | +| train/ | | +| approx_kl | 0.012486866 | +| clip_fraction | 0.336 | +| clip_range | 0.0689 | +| entropy_loss | -5.79 | +| explained_variance | 0.509 | +| learning_rate | 4.42e-05 | +| loss | -0.0308 | +| n_updates | 63436 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000225 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1416 | +| iterations | 11906 | +| time_elapsed | 17208 | +| total_timesteps | 24383488 | +| train/ | | +| approx_kl | 0.01111502 | +| clip_fraction | 0.351 | +| clip_range | 0.0689 | +| entropy_loss | -6.12 | +| explained_variance | 0.301 | +| learning_rate | 4.42e-05 | +| loss | -0.0333 | +| n_updates | 63440 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000153 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1416 | +| iterations | 11907 | +| time_elapsed | 17210 | +| total_timesteps | 24385536 | +| train/ | | +| approx_kl | 0.012025793 | +| clip_fraction | 0.35 | +| clip_range | 0.0689 | +| entropy_loss | -6.58 | +| explained_variance | 0.254 | +| learning_rate | 4.42e-05 | +| loss | -0.0361 | +| n_updates | 63444 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000148 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1416 | +| iterations | 11908 | +| time_elapsed | 17211 | +| total_timesteps | 24387584 | +| train/ | | +| approx_kl | 0.011287821 | +| clip_fraction | 0.353 | +| clip_range | 0.0689 | +| entropy_loss | -7.03 | +| explained_variance | -0.143 | +| learning_rate | 4.42e-05 | +| loss | -0.0356 | +| n_updates | 63448 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000159 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1416 | +| iterations | 11909 | +| time_elapsed | 17213 | +| total_timesteps | 24389632 | +| train/ | | +| approx_kl | 0.011307012 | +| clip_fraction | 0.318 | +| clip_range | 0.0689 | +| entropy_loss | -6.74 | +| explained_variance | 0.415 | +| learning_rate | 4.42e-05 | +| loss | -0.0275 | +| n_updates | 63452 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000215 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1416 | +| iterations | 11910 | +| time_elapsed | 17214 | +| total_timesteps | 24391680 | +| train/ | | +| approx_kl | 0.016333587 | +| clip_fraction | 0.333 | +| clip_range | 0.0689 | +| entropy_loss | -6.39 | +| explained_variance | 0.303 | +| learning_rate | 4.42e-05 | +| loss | -0.0349 | +| n_updates | 63456 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000145 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1416 | +| iterations | 11911 | +| time_elapsed | 17215 | +| total_timesteps | 24393728 | +| train/ | | +| approx_kl | 0.012596804 | +| clip_fraction | 0.326 | +| clip_range | 0.0689 | +| entropy_loss | -6.29 | +| explained_variance | 0.365 | +| learning_rate | 4.42e-05 | +| loss | -0.0258 | +| n_updates | 63460 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000259 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1416 | +| iterations | 11912 | +| time_elapsed | 17217 | +| total_timesteps | 24395776 | +| train/ | | +| approx_kl | 0.012208625 | +| clip_fraction | 0.293 | +| clip_range | 0.0689 | +| entropy_loss | -5.47 | +| explained_variance | 0.441 | +| learning_rate | 4.42e-05 | +| loss | -0.0224 | +| n_updates | 63464 | +| policy_gradient_loss | -0.0144 | +| value_loss | 0.000369 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1416 | +| iterations | 11913 | +| time_elapsed | 17218 | +| total_timesteps | 24397824 | +| train/ | | +| approx_kl | 0.010652673 | +| clip_fraction | 0.333 | +| clip_range | 0.0689 | +| entropy_loss | -5.75 | +| explained_variance | 0.574 | +| learning_rate | 4.42e-05 | +| loss | -0.0273 | +| n_updates | 63468 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000195 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1416 | +| iterations | 11914 | +| time_elapsed | 17220 | +| total_timesteps | 24399872 | +| train/ | | +| approx_kl | 0.013358593 | +| clip_fraction | 0.352 | +| clip_range | 0.0689 | +| entropy_loss | -6.27 | +| explained_variance | 0.449 | +| learning_rate | 4.42e-05 | +| loss | -0.0334 | +| n_updates | 63472 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000132 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1416 | +| iterations | 11915 | +| time_elapsed | 17221 | +| total_timesteps | 24401920 | +| train/ | | +| approx_kl | 0.014676297 | +| clip_fraction | 0.339 | +| clip_range | 0.0689 | +| entropy_loss | -6.21 | +| explained_variance | 0.447 | +| learning_rate | 4.42e-05 | +| loss | -0.0317 | +| n_updates | 63476 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000245 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1416 | +| iterations | 11916 | +| time_elapsed | 17223 | +| total_timesteps | 24403968 | +| train/ | | +| approx_kl | 0.018123334 | +| clip_fraction | 0.361 | +| clip_range | 0.0689 | +| entropy_loss | -6.53 | +| explained_variance | -0.093 | +| learning_rate | 4.42e-05 | +| loss | -0.0338 | +| n_updates | 63480 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000188 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1416 | +| iterations | 11917 | +| time_elapsed | 17224 | +| total_timesteps | 24406016 | +| train/ | | +| approx_kl | 0.012401149 | +| clip_fraction | 0.326 | +| clip_range | 0.0689 | +| entropy_loss | -6.83 | +| explained_variance | 0.165 | +| learning_rate | 4.42e-05 | +| loss | -0.0222 | +| n_updates | 63484 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000348 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1416 | +| iterations | 11918 | +| time_elapsed | 17226 | +| total_timesteps | 24408064 | +| train/ | | +| approx_kl | 0.012511351 | +| clip_fraction | 0.348 | +| clip_range | 0.0689 | +| entropy_loss | -6.68 | +| explained_variance | 0.291 | +| learning_rate | 4.42e-05 | +| loss | -0.033 | +| n_updates | 63488 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000156 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1416 | +| iterations | 11919 | +| time_elapsed | 17227 | +| total_timesteps | 24410112 | +| train/ | | +| approx_kl | 0.014007751 | +| clip_fraction | 0.335 | +| clip_range | 0.0689 | +| entropy_loss | -6.71 | +| explained_variance | 0.332 | +| learning_rate | 4.42e-05 | +| loss | -0.0312 | +| n_updates | 63492 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000177 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1416 | +| iterations | 11920 | +| time_elapsed | 17229 | +| total_timesteps | 24412160 | +| train/ | | +| approx_kl | 0.011698821 | +| clip_fraction | 0.314 | +| clip_range | 0.0689 | +| entropy_loss | -6.06 | +| explained_variance | 0.418 | +| learning_rate | 4.42e-05 | +| loss | -0.0273 | +| n_updates | 63496 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000319 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1416 | +| iterations | 11921 | +| time_elapsed | 17230 | +| total_timesteps | 24414208 | +| train/ | | +| approx_kl | 0.013226756 | +| clip_fraction | 0.336 | +| clip_range | 0.0689 | +| entropy_loss | -5.36 | +| explained_variance | 0.814 | +| learning_rate | 4.42e-05 | +| loss | -0.0315 | +| n_updates | 63500 | +| policy_gradient_loss | -0.0216 | +| value_loss | 7.86e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1416 | +| iterations | 11922 | +| time_elapsed | 17232 | +| total_timesteps | 24416256 | +| train/ | | +| approx_kl | 0.013787929 | +| clip_fraction | 0.35 | +| clip_range | 0.0689 | +| entropy_loss | -6.48 | +| explained_variance | 0.553 | +| learning_rate | 4.42e-05 | +| loss | -0.0396 | +| n_updates | 63504 | +| policy_gradient_loss | -0.022 | +| value_loss | 8.12e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1416 | +| iterations | 11923 | +| time_elapsed | 17233 | +| total_timesteps | 24418304 | +| train/ | | +| approx_kl | 0.016167954 | +| clip_fraction | 0.324 | +| clip_range | 0.0689 | +| entropy_loss | -6.17 | +| explained_variance | 0.56 | +| learning_rate | 4.42e-05 | +| loss | -0.03 | +| n_updates | 63508 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000133 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1416 | +| iterations | 11924 | +| time_elapsed | 17235 | +| total_timesteps | 24420352 | +| train/ | | +| approx_kl | 0.013948431 | +| clip_fraction | 0.322 | +| clip_range | 0.0689 | +| entropy_loss | -5.92 | +| explained_variance | 0.501 | +| learning_rate | 4.42e-05 | +| loss | -0.0274 | +| n_updates | 63512 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000226 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1416 | +| iterations | 11925 | +| time_elapsed | 17236 | +| total_timesteps | 24422400 | +| train/ | | +| approx_kl | 0.0123628 | +| clip_fraction | 0.338 | +| clip_range | 0.0689 | +| entropy_loss | -6.54 | +| explained_variance | 0.0975 | +| learning_rate | 4.42e-05 | +| loss | -0.0296 | +| n_updates | 63516 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000178 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1416 | +| iterations | 11926 | +| time_elapsed | 17238 | +| total_timesteps | 24424448 | +| train/ | | +| approx_kl | 0.013401289 | +| clip_fraction | 0.315 | +| clip_range | 0.0689 | +| entropy_loss | -6.79 | +| explained_variance | 0.302 | +| learning_rate | 4.42e-05 | +| loss | -0.0311 | +| n_updates | 63520 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000173 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.14e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1416 | +| iterations | 11927 | +| time_elapsed | 17239 | +| total_timesteps | 24426496 | +| train/ | | +| approx_kl | 0.016629413 | +| clip_fraction | 0.391 | +| clip_range | 0.0689 | +| entropy_loss | -6.63 | +| explained_variance | 0.459 | +| learning_rate | 4.42e-05 | +| loss | -0.0373 | +| n_updates | 63524 | +| policy_gradient_loss | -0.0241 | +| value_loss | 8.77e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1416 | +| iterations | 11928 | +| time_elapsed | 17241 | +| total_timesteps | 24428544 | +| train/ | | +| approx_kl | 0.012050269 | +| clip_fraction | 0.325 | +| clip_range | 0.0689 | +| entropy_loss | -5.85 | +| explained_variance | 0.536 | +| learning_rate | 4.42e-05 | +| loss | -0.0209 | +| n_updates | 63528 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000187 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1416 | +| iterations | 11929 | +| time_elapsed | 17242 | +| total_timesteps | 24430592 | +| train/ | | +| approx_kl | 0.01361842 | +| clip_fraction | 0.278 | +| clip_range | 0.0689 | +| entropy_loss | -6.06 | +| explained_variance | 0.402 | +| learning_rate | 4.42e-05 | +| loss | -0.0225 | +| n_updates | 63532 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.000322 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1416 | +| iterations | 11930 | +| time_elapsed | 17244 | +| total_timesteps | 24432640 | +| train/ | | +| approx_kl | 0.013130606 | +| clip_fraction | 0.343 | +| clip_range | 0.0689 | +| entropy_loss | -6.26 | +| explained_variance | 0.362 | +| learning_rate | 4.42e-05 | +| loss | -0.029 | +| n_updates | 63536 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000286 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.14e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1416 | +| iterations | 11931 | +| time_elapsed | 17245 | +| total_timesteps | 24434688 | +| train/ | | +| approx_kl | 0.012563806 | +| clip_fraction | 0.329 | +| clip_range | 0.0689 | +| entropy_loss | -6.91 | +| explained_variance | 0.192 | +| learning_rate | 4.42e-05 | +| loss | -0.0242 | +| n_updates | 63540 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000299 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.14e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1416 | +| iterations | 11932 | +| time_elapsed | 17247 | +| total_timesteps | 24436736 | +| train/ | | +| approx_kl | 0.0125558125 | +| clip_fraction | 0.358 | +| clip_range | 0.0689 | +| entropy_loss | -6.37 | +| explained_variance | 0.141 | +| learning_rate | 4.42e-05 | +| loss | -0.0305 | +| n_updates | 63544 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.00032 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.14e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1416 | +| iterations | 11933 | +| time_elapsed | 17248 | +| total_timesteps | 24438784 | +| train/ | | +| approx_kl | 0.014112852 | +| clip_fraction | 0.357 | +| clip_range | 0.0689 | +| entropy_loss | -6.11 | +| explained_variance | 0.622 | +| learning_rate | 4.42e-05 | +| loss | -0.0349 | +| n_updates | 63548 | +| policy_gradient_loss | -0.0219 | +| value_loss | 0.000105 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.14e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1416 | +| iterations | 11934 | +| time_elapsed | 17250 | +| total_timesteps | 24440832 | +| train/ | | +| approx_kl | 0.013624914 | +| clip_fraction | 0.328 | +| clip_range | 0.0689 | +| entropy_loss | -6.01 | +| explained_variance | 0.483 | +| learning_rate | 4.42e-05 | +| loss | -0.0269 | +| n_updates | 63552 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000272 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.14e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1416 | +| iterations | 11935 | +| time_elapsed | 17251 | +| total_timesteps | 24442880 | +| train/ | | +| approx_kl | 0.012003023 | +| clip_fraction | 0.329 | +| clip_range | 0.0689 | +| entropy_loss | -6.37 | +| explained_variance | 0.526 | +| learning_rate | 4.42e-05 | +| loss | -0.0341 | +| n_updates | 63556 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000154 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.14e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1416 | +| iterations | 11936 | +| time_elapsed | 17253 | +| total_timesteps | 24444928 | +| train/ | | +| approx_kl | 0.013999567 | +| clip_fraction | 0.351 | +| clip_range | 0.0689 | +| entropy_loss | -6.71 | +| explained_variance | 0.329 | +| learning_rate | 4.42e-05 | +| loss | -0.0309 | +| n_updates | 63560 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000143 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.14e+03 | +| ep_rew_mean | 0.387 | +| time/ | | +| fps | 1416 | +| iterations | 11937 | +| time_elapsed | 17254 | +| total_timesteps | 24446976 | +| train/ | | +| approx_kl | 0.014997869 | +| clip_fraction | 0.351 | +| clip_range | 0.0689 | +| entropy_loss | -6.5 | +| explained_variance | 0.419 | +| learning_rate | 4.42e-05 | +| loss | -0.0271 | +| n_updates | 63564 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000146 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.14e+03 | +| ep_rew_mean | 0.391 | +| time/ | | +| fps | 1416 | +| iterations | 11938 | +| time_elapsed | 17256 | +| total_timesteps | 24449024 | +| train/ | | +| approx_kl | 0.018012475 | +| clip_fraction | 0.333 | +| clip_range | 0.0689 | +| entropy_loss | -6.26 | +| explained_variance | 0.451 | +| learning_rate | 4.42e-05 | +| loss | -0.0297 | +| n_updates | 63568 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000164 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.13e+03 | +| ep_rew_mean | 0.385 | +| time/ | | +| fps | 1416 | +| iterations | 11939 | +| time_elapsed | 17257 | +| total_timesteps | 24451072 | +| train/ | | +| approx_kl | 0.013896901 | +| clip_fraction | 0.318 | +| clip_range | 0.0689 | +| entropy_loss | -5.88 | +| explained_variance | 0.566 | +| learning_rate | 4.42e-05 | +| loss | -0.0217 | +| n_updates | 63572 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.000198 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.13e+03 | +| ep_rew_mean | 0.384 | +| time/ | | +| fps | 1416 | +| iterations | 11940 | +| time_elapsed | 17259 | +| total_timesteps | 24453120 | +| train/ | | +| approx_kl | 0.016100008 | +| clip_fraction | 0.341 | +| clip_range | 0.0689 | +| entropy_loss | -5.88 | +| explained_variance | 0.613 | +| learning_rate | 4.42e-05 | +| loss | -0.0323 | +| n_updates | 63576 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000132 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.12e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1416 | +| iterations | 11941 | +| time_elapsed | 17260 | +| total_timesteps | 24455168 | +| train/ | | +| approx_kl | 0.014476459 | +| clip_fraction | 0.38 | +| clip_range | 0.0689 | +| entropy_loss | -6.52 | +| explained_variance | 0.0411 | +| learning_rate | 4.42e-05 | +| loss | -0.0396 | +| n_updates | 63580 | +| policy_gradient_loss | -0.022 | +| value_loss | 0.000112 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.12e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1416 | +| iterations | 11942 | +| time_elapsed | 17262 | +| total_timesteps | 24457216 | +| train/ | | +| approx_kl | 0.0143388435 | +| clip_fraction | 0.347 | +| clip_range | 0.0689 | +| entropy_loss | -6.13 | +| explained_variance | 0.63 | +| learning_rate | 4.42e-05 | +| loss | -0.0343 | +| n_updates | 63584 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000112 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.12e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1416 | +| iterations | 11943 | +| time_elapsed | 17263 | +| total_timesteps | 24459264 | +| train/ | | +| approx_kl | 0.011229761 | +| clip_fraction | 0.336 | +| clip_range | 0.0689 | +| entropy_loss | -6.36 | +| explained_variance | 0.111 | +| learning_rate | 4.42e-05 | +| loss | -0.0272 | +| n_updates | 63588 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000339 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.11e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1416 | +| iterations | 11944 | +| time_elapsed | 17265 | +| total_timesteps | 24461312 | +| train/ | | +| approx_kl | 0.012373534 | +| clip_fraction | 0.32 | +| clip_range | 0.0689 | +| entropy_loss | -6.77 | +| explained_variance | 0.167 | +| learning_rate | 4.42e-05 | +| loss | -0.0294 | +| n_updates | 63592 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000191 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.12e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1416 | +| iterations | 11945 | +| time_elapsed | 17266 | +| total_timesteps | 24463360 | +| train/ | | +| approx_kl | 0.015845321 | +| clip_fraction | 0.35 | +| clip_range | 0.0689 | +| entropy_loss | -6.28 | +| explained_variance | 0.759 | +| learning_rate | 4.42e-05 | +| loss | -0.0287 | +| n_updates | 63596 | +| policy_gradient_loss | -0.0206 | +| value_loss | 7.55e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.11e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1416 | +| iterations | 11946 | +| time_elapsed | 17268 | +| total_timesteps | 24465408 | +| train/ | | +| approx_kl | 0.012067642 | +| clip_fraction | 0.335 | +| clip_range | 0.0689 | +| entropy_loss | -6 | +| explained_variance | 0.415 | +| learning_rate | 4.42e-05 | +| loss | -0.0313 | +| n_updates | 63600 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000206 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.11e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1416 | +| iterations | 11947 | +| time_elapsed | 17269 | +| total_timesteps | 24467456 | +| train/ | | +| approx_kl | 0.010776217 | +| clip_fraction | 0.319 | +| clip_range | 0.0689 | +| entropy_loss | -5.86 | +| explained_variance | 0.446 | +| learning_rate | 4.42e-05 | +| loss | -0.0199 | +| n_updates | 63604 | +| policy_gradient_loss | -0.0143 | +| value_loss | 0.000316 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.12e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1416 | +| iterations | 11948 | +| time_elapsed | 17271 | +| total_timesteps | 24469504 | +| train/ | | +| approx_kl | 0.011987594 | +| clip_fraction | 0.316 | +| clip_range | 0.0689 | +| entropy_loss | -6.14 | +| explained_variance | 0.256 | +| learning_rate | 4.42e-05 | +| loss | -0.0217 | +| n_updates | 63608 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000252 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.12e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1416 | +| iterations | 11949 | +| time_elapsed | 17272 | +| total_timesteps | 24471552 | +| train/ | | +| approx_kl | 0.013750665 | +| clip_fraction | 0.393 | +| clip_range | 0.0689 | +| entropy_loss | -6.42 | +| explained_variance | 0.564 | +| learning_rate | 4.42e-05 | +| loss | -0.0394 | +| n_updates | 63612 | +| policy_gradient_loss | -0.0241 | +| value_loss | 8.36e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.12e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1416 | +| iterations | 11950 | +| time_elapsed | 17274 | +| total_timesteps | 24473600 | +| train/ | | +| approx_kl | 0.015753785 | +| clip_fraction | 0.365 | +| clip_range | 0.0689 | +| entropy_loss | -6.16 | +| explained_variance | 0.636 | +| learning_rate | 4.42e-05 | +| loss | -0.0317 | +| n_updates | 63616 | +| policy_gradient_loss | -0.0208 | +| value_loss | 8.29e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.13e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1416 | +| iterations | 11951 | +| time_elapsed | 17275 | +| total_timesteps | 24475648 | +| train/ | | +| approx_kl | 0.012394237 | +| clip_fraction | 0.327 | +| clip_range | 0.0689 | +| entropy_loss | -6.37 | +| explained_variance | 0.29 | +| learning_rate | 4.42e-05 | +| loss | -0.0289 | +| n_updates | 63620 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000186 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.13e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1416 | +| iterations | 11952 | +| time_elapsed | 17277 | +| total_timesteps | 24477696 | +| train/ | | +| approx_kl | 0.015217062 | +| clip_fraction | 0.363 | +| clip_range | 0.0689 | +| entropy_loss | -6.64 | +| explained_variance | -0.376 | +| learning_rate | 4.42e-05 | +| loss | -0.026 | +| n_updates | 63624 | +| policy_gradient_loss | -0.0196 | +| value_loss | 9.69e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1416 | +| iterations | 11953 | +| time_elapsed | 17278 | +| total_timesteps | 24479744 | +| train/ | | +| approx_kl | 0.014779013 | +| clip_fraction | 0.364 | +| clip_range | 0.0689 | +| entropy_loss | -6.15 | +| explained_variance | 0.718 | +| learning_rate | 4.42e-05 | +| loss | -0.0309 | +| n_updates | 63628 | +| policy_gradient_loss | -0.0214 | +| value_loss | 5.91e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.14e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1416 | +| iterations | 11954 | +| time_elapsed | 17280 | +| total_timesteps | 24481792 | +| train/ | | +| approx_kl | 0.013370727 | +| clip_fraction | 0.308 | +| clip_range | 0.0689 | +| entropy_loss | -6.03 | +| explained_variance | 0.704 | +| learning_rate | 4.42e-05 | +| loss | -0.0226 | +| n_updates | 63632 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000103 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1416 | +| iterations | 11955 | +| time_elapsed | 17281 | +| total_timesteps | 24483840 | +| train/ | | +| approx_kl | 0.014509793 | +| clip_fraction | 0.326 | +| clip_range | 0.0689 | +| entropy_loss | -5.54 | +| explained_variance | 0.754 | +| learning_rate | 4.42e-05 | +| loss | -0.0287 | +| n_updates | 63636 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000101 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1416 | +| iterations | 11956 | +| time_elapsed | 17283 | +| total_timesteps | 24485888 | +| train/ | | +| approx_kl | 0.013783699 | +| clip_fraction | 0.325 | +| clip_range | 0.0689 | +| entropy_loss | -6.3 | +| explained_variance | 0.294 | +| learning_rate | 4.42e-05 | +| loss | -0.0275 | +| n_updates | 63640 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000165 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1416 | +| iterations | 11957 | +| time_elapsed | 17284 | +| total_timesteps | 24487936 | +| train/ | | +| approx_kl | 0.013806208 | +| clip_fraction | 0.339 | +| clip_range | 0.0689 | +| entropy_loss | -6.6 | +| explained_variance | 0.263 | +| learning_rate | 4.42e-05 | +| loss | -0.0312 | +| n_updates | 63644 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000147 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1416 | +| iterations | 11958 | +| time_elapsed | 17286 | +| total_timesteps | 24489984 | +| train/ | | +| approx_kl | 0.016391877 | +| clip_fraction | 0.344 | +| clip_range | 0.0689 | +| entropy_loss | -6.58 | +| explained_variance | 0.303 | +| learning_rate | 4.42e-05 | +| loss | -0.0318 | +| n_updates | 63648 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000126 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.13e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1416 | +| iterations | 11959 | +| time_elapsed | 17287 | +| total_timesteps | 24492032 | +| train/ | | +| approx_kl | 0.012315776 | +| clip_fraction | 0.311 | +| clip_range | 0.0689 | +| entropy_loss | -6.68 | +| explained_variance | 0.281 | +| learning_rate | 4.42e-05 | +| loss | -0.0271 | +| n_updates | 63652 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000159 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.14e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1416 | +| iterations | 11960 | +| time_elapsed | 17289 | +| total_timesteps | 24494080 | +| train/ | | +| approx_kl | 0.010608111 | +| clip_fraction | 0.305 | +| clip_range | 0.0689 | +| entropy_loss | -6.1 | +| explained_variance | 0.299 | +| learning_rate | 4.42e-05 | +| loss | -0.025 | +| n_updates | 63656 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000463 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.14e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1416 | +| iterations | 11961 | +| time_elapsed | 17290 | +| total_timesteps | 24496128 | +| train/ | | +| approx_kl | 0.011542466 | +| clip_fraction | 0.359 | +| clip_range | 0.0689 | +| entropy_loss | -5.55 | +| explained_variance | 0.455 | +| learning_rate | 4.42e-05 | +| loss | -0.0323 | +| n_updates | 63660 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000223 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.13e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1416 | +| iterations | 11962 | +| time_elapsed | 17292 | +| total_timesteps | 24498176 | +| train/ | | +| approx_kl | 0.012927991 | +| clip_fraction | 0.339 | +| clip_range | 0.0689 | +| entropy_loss | -5.92 | +| explained_variance | 0.355 | +| learning_rate | 4.42e-05 | +| loss | -0.0356 | +| n_updates | 63664 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000235 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.13e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1416 | +| iterations | 11963 | +| time_elapsed | 17293 | +| total_timesteps | 24500224 | +| train/ | | +| approx_kl | 0.013369763 | +| clip_fraction | 0.36 | +| clip_range | 0.0689 | +| entropy_loss | -5.74 | +| explained_variance | 0.737 | +| learning_rate | 4.42e-05 | +| loss | -0.0364 | +| n_updates | 63668 | +| policy_gradient_loss | -0.0206 | +| value_loss | 8.42e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.13e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1416 | +| iterations | 11964 | +| time_elapsed | 17295 | +| total_timesteps | 24502272 | +| train/ | | +| approx_kl | 0.015066022 | +| clip_fraction | 0.351 | +| clip_range | 0.0689 | +| entropy_loss | -6.34 | +| explained_variance | -0.18 | +| learning_rate | 4.42e-05 | +| loss | -0.0307 | +| n_updates | 63672 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000199 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.13e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1416 | +| iterations | 11965 | +| time_elapsed | 17296 | +| total_timesteps | 24504320 | +| train/ | | +| approx_kl | 0.015120139 | +| clip_fraction | 0.344 | +| clip_range | 0.0689 | +| entropy_loss | -6.54 | +| explained_variance | 0.297 | +| learning_rate | 4.42e-05 | +| loss | -0.0361 | +| n_updates | 63676 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000153 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.13e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1416 | +| iterations | 11966 | +| time_elapsed | 17298 | +| total_timesteps | 24506368 | +| train/ | | +| approx_kl | 0.015230263 | +| clip_fraction | 0.331 | +| clip_range | 0.0689 | +| entropy_loss | -6.23 | +| explained_variance | 0.368 | +| learning_rate | 4.42e-05 | +| loss | -0.0285 | +| n_updates | 63680 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000366 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.13e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1416 | +| iterations | 11967 | +| time_elapsed | 17299 | +| total_timesteps | 24508416 | +| train/ | | +| approx_kl | 0.013935158 | +| clip_fraction | 0.353 | +| clip_range | 0.0689 | +| entropy_loss | -6.1 | +| explained_variance | 0.435 | +| learning_rate | 4.42e-05 | +| loss | -0.04 | +| n_updates | 63684 | +| policy_gradient_loss | -0.0225 | +| value_loss | 8.59e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.13e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1416 | +| iterations | 11968 | +| time_elapsed | 17301 | +| total_timesteps | 24510464 | +| train/ | | +| approx_kl | 0.011143157 | +| clip_fraction | 0.34 | +| clip_range | 0.0689 | +| entropy_loss | -6.42 | +| explained_variance | 0.324 | +| learning_rate | 4.42e-05 | +| loss | -0.0265 | +| n_updates | 63688 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000267 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.12e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1416 | +| iterations | 11969 | +| time_elapsed | 17302 | +| total_timesteps | 24512512 | +| train/ | | +| approx_kl | 0.015444262 | +| clip_fraction | 0.341 | +| clip_range | 0.0689 | +| entropy_loss | -5.96 | +| explained_variance | 0.472 | +| learning_rate | 4.42e-05 | +| loss | -0.0351 | +| n_updates | 63692 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000212 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.12e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1416 | +| iterations | 11970 | +| time_elapsed | 17304 | +| total_timesteps | 24514560 | +| train/ | | +| approx_kl | 0.014409763 | +| clip_fraction | 0.345 | +| clip_range | 0.0689 | +| entropy_loss | -5.72 | +| explained_variance | 0.433 | +| learning_rate | 4.42e-05 | +| loss | -0.0299 | +| n_updates | 63696 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.00033 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.12e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1416 | +| iterations | 11971 | +| time_elapsed | 17305 | +| total_timesteps | 24516608 | +| train/ | | +| approx_kl | 0.011966363 | +| clip_fraction | 0.353 | +| clip_range | 0.0689 | +| entropy_loss | -6.66 | +| explained_variance | 0.146 | +| learning_rate | 4.42e-05 | +| loss | -0.0314 | +| n_updates | 63700 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.00022 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.14e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1416 | +| iterations | 11972 | +| time_elapsed | 17307 | +| total_timesteps | 24518656 | +| train/ | | +| approx_kl | 0.014350809 | +| clip_fraction | 0.365 | +| clip_range | 0.0689 | +| entropy_loss | -7.05 | +| explained_variance | -0.233 | +| learning_rate | 4.42e-05 | +| loss | -0.034 | +| n_updates | 63704 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000105 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.14e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1416 | +| iterations | 11973 | +| time_elapsed | 17308 | +| total_timesteps | 24520704 | +| train/ | | +| approx_kl | 0.013149729 | +| clip_fraction | 0.317 | +| clip_range | 0.0689 | +| entropy_loss | -6.5 | +| explained_variance | 0.54 | +| learning_rate | 4.42e-05 | +| loss | -0.0265 | +| n_updates | 63708 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000176 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.14e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1416 | +| iterations | 11974 | +| time_elapsed | 17310 | +| total_timesteps | 24522752 | +| train/ | | +| approx_kl | 0.011464687 | +| clip_fraction | 0.358 | +| clip_range | 0.0689 | +| entropy_loss | -6.44 | +| explained_variance | 0.433 | +| learning_rate | 4.42e-05 | +| loss | -0.0359 | +| n_updates | 63712 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000116 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.14e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1416 | +| iterations | 11975 | +| time_elapsed | 17311 | +| total_timesteps | 24524800 | +| train/ | | +| approx_kl | 0.01306599 | +| clip_fraction | 0.357 | +| clip_range | 0.0689 | +| entropy_loss | -6.67 | +| explained_variance | 0.532 | +| learning_rate | 4.42e-05 | +| loss | -0.0374 | +| n_updates | 63716 | +| policy_gradient_loss | -0.0222 | +| value_loss | 7.81e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.14e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1416 | +| iterations | 11976 | +| time_elapsed | 17313 | +| total_timesteps | 24526848 | +| train/ | | +| approx_kl | 0.012105155 | +| clip_fraction | 0.345 | +| clip_range | 0.0689 | +| entropy_loss | -6.78 | +| explained_variance | -0.163 | +| learning_rate | 4.42e-05 | +| loss | -0.0319 | +| n_updates | 63720 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000149 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.14e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1416 | +| iterations | 11977 | +| time_elapsed | 17314 | +| total_timesteps | 24528896 | +| train/ | | +| approx_kl | 0.013222083 | +| clip_fraction | 0.326 | +| clip_range | 0.0689 | +| entropy_loss | -6.35 | +| explained_variance | 0.315 | +| learning_rate | 4.42e-05 | +| loss | -0.0188 | +| n_updates | 63724 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.00026 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.14e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1416 | +| iterations | 11978 | +| time_elapsed | 17316 | +| total_timesteps | 24530944 | +| train/ | | +| approx_kl | 0.013202345 | +| clip_fraction | 0.348 | +| clip_range | 0.0689 | +| entropy_loss | -6.42 | +| explained_variance | 0.381 | +| learning_rate | 4.42e-05 | +| loss | -0.0338 | +| n_updates | 63728 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000157 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1416 | +| iterations | 11979 | +| time_elapsed | 17317 | +| total_timesteps | 24532992 | +| train/ | | +| approx_kl | 0.011027092 | +| clip_fraction | 0.342 | +| clip_range | 0.0689 | +| entropy_loss | -6.51 | +| explained_variance | 0.401 | +| learning_rate | 4.42e-05 | +| loss | -0.0312 | +| n_updates | 63732 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000228 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1416 | +| iterations | 11980 | +| time_elapsed | 17319 | +| total_timesteps | 24535040 | +| train/ | | +| approx_kl | 0.012706187 | +| clip_fraction | 0.309 | +| clip_range | 0.0689 | +| entropy_loss | -5.67 | +| explained_variance | 0.704 | +| learning_rate | 4.42e-05 | +| loss | -0.0251 | +| n_updates | 63736 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000136 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1416 | +| iterations | 11981 | +| time_elapsed | 17320 | +| total_timesteps | 24537088 | +| train/ | | +| approx_kl | 0.01360454 | +| clip_fraction | 0.355 | +| clip_range | 0.0689 | +| entropy_loss | -5.84 | +| explained_variance | 0.637 | +| learning_rate | 4.42e-05 | +| loss | -0.0366 | +| n_updates | 63740 | +| policy_gradient_loss | -0.0218 | +| value_loss | 6.69e-05 | +---------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1416 | +| iterations | 11982 | +| time_elapsed | 17322 | +| total_timesteps | 24539136 | +| train/ | | +| approx_kl | 0.0171003 | +| clip_fraction | 0.353 | +| clip_range | 0.0689 | +| entropy_loss | -6.5 | +| explained_variance | 0.0634 | +| learning_rate | 4.42e-05 | +| loss | -0.029 | +| n_updates | 63744 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000153 | +--------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1416 | +| iterations | 11983 | +| time_elapsed | 17323 | +| total_timesteps | 24541184 | +| train/ | | +| approx_kl | 0.0152103705 | +| clip_fraction | 0.346 | +| clip_range | 0.0689 | +| entropy_loss | -6.23 | +| explained_variance | 0.591 | +| learning_rate | 4.42e-05 | +| loss | -0.0346 | +| n_updates | 63748 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000122 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1416 | +| iterations | 11984 | +| time_elapsed | 17325 | +| total_timesteps | 24543232 | +| train/ | | +| approx_kl | 0.012409595 | +| clip_fraction | 0.345 | +| clip_range | 0.0689 | +| entropy_loss | -6.65 | +| explained_variance | 0.00336 | +| learning_rate | 4.42e-05 | +| loss | -0.0307 | +| n_updates | 63752 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000108 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1416 | +| iterations | 11985 | +| time_elapsed | 17326 | +| total_timesteps | 24545280 | +| train/ | | +| approx_kl | 0.012406178 | +| clip_fraction | 0.324 | +| clip_range | 0.0689 | +| entropy_loss | -6.55 | +| explained_variance | 0.486 | +| learning_rate | 4.42e-05 | +| loss | -0.0245 | +| n_updates | 63756 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000142 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1416 | +| iterations | 11986 | +| time_elapsed | 17328 | +| total_timesteps | 24547328 | +| train/ | | +| approx_kl | 0.01653507 | +| clip_fraction | 0.341 | +| clip_range | 0.0689 | +| entropy_loss | -6.25 | +| explained_variance | 0.233 | +| learning_rate | 4.42e-05 | +| loss | -0.031 | +| n_updates | 63760 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000204 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1416 | +| iterations | 11987 | +| time_elapsed | 17329 | +| total_timesteps | 24549376 | +| train/ | | +| approx_kl | 0.012499689 | +| clip_fraction | 0.333 | +| clip_range | 0.0689 | +| entropy_loss | -6.33 | +| explained_variance | 0.378 | +| learning_rate | 4.42e-05 | +| loss | -0.0286 | +| n_updates | 63764 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.00024 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1416 | +| iterations | 11988 | +| time_elapsed | 17331 | +| total_timesteps | 24551424 | +| train/ | | +| approx_kl | 0.012695054 | +| clip_fraction | 0.36 | +| clip_range | 0.0689 | +| entropy_loss | -6.76 | +| explained_variance | -0.0708 | +| learning_rate | 4.42e-05 | +| loss | -0.0306 | +| n_updates | 63768 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000112 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1416 | +| iterations | 11989 | +| time_elapsed | 17332 | +| total_timesteps | 24553472 | +| train/ | | +| approx_kl | 0.015044997 | +| clip_fraction | 0.32 | +| clip_range | 0.0689 | +| entropy_loss | -6.12 | +| explained_variance | 0.659 | +| learning_rate | 4.42e-05 | +| loss | -0.0275 | +| n_updates | 63772 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000159 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1416 | +| iterations | 11990 | +| time_elapsed | 17334 | +| total_timesteps | 24555520 | +| train/ | | +| approx_kl | 0.011622909 | +| clip_fraction | 0.31 | +| clip_range | 0.0689 | +| entropy_loss | -6.15 | +| explained_variance | 0.386 | +| learning_rate | 4.42e-05 | +| loss | -0.0239 | +| n_updates | 63776 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000289 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1416 | +| iterations | 11991 | +| time_elapsed | 17335 | +| total_timesteps | 24557568 | +| train/ | | +| approx_kl | 0.012819717 | +| clip_fraction | 0.31 | +| clip_range | 0.0689 | +| entropy_loss | -6.11 | +| explained_variance | 0.562 | +| learning_rate | 4.42e-05 | +| loss | -0.0265 | +| n_updates | 63780 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000186 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1416 | +| iterations | 11992 | +| time_elapsed | 17337 | +| total_timesteps | 24559616 | +| train/ | | +| approx_kl | 0.012730854 | +| clip_fraction | 0.34 | +| clip_range | 0.0689 | +| entropy_loss | -6.39 | +| explained_variance | 0.351 | +| learning_rate | 4.42e-05 | +| loss | -0.0317 | +| n_updates | 63784 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000158 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1416 | +| iterations | 11993 | +| time_elapsed | 17338 | +| total_timesteps | 24561664 | +| train/ | | +| approx_kl | 0.014500124 | +| clip_fraction | 0.36 | +| clip_range | 0.0689 | +| entropy_loss | -6.54 | +| explained_variance | 0.159 | +| learning_rate | 4.42e-05 | +| loss | -0.034 | +| n_updates | 63788 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000149 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 1416 | +| iterations | 11994 | +| time_elapsed | 17340 | +| total_timesteps | 24563712 | +| train/ | | +| approx_kl | 0.012397069 | +| clip_fraction | 0.354 | +| clip_range | 0.0689 | +| entropy_loss | -6.73 | +| explained_variance | -0.0566 | +| learning_rate | 4.42e-05 | +| loss | -0.0345 | +| n_updates | 63792 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000172 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.302 | +| time/ | | +| fps | 1416 | +| iterations | 11995 | +| time_elapsed | 17341 | +| total_timesteps | 24565760 | +| train/ | | +| approx_kl | 0.013496077 | +| clip_fraction | 0.346 | +| clip_range | 0.0689 | +| entropy_loss | -6.42 | +| explained_variance | 0.417 | +| learning_rate | 4.42e-05 | +| loss | -0.0247 | +| n_updates | 63796 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000165 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1416 | +| iterations | 11996 | +| time_elapsed | 17343 | +| total_timesteps | 24567808 | +| train/ | | +| approx_kl | 0.014813755 | +| clip_fraction | 0.366 | +| clip_range | 0.0689 | +| entropy_loss | -5.98 | +| explained_variance | 0.675 | +| learning_rate | 4.42e-05 | +| loss | -0.0324 | +| n_updates | 63800 | +| policy_gradient_loss | -0.0212 | +| value_loss | 8.31e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1416 | +| iterations | 11997 | +| time_elapsed | 17344 | +| total_timesteps | 24569856 | +| train/ | | +| approx_kl | 0.01340383 | +| clip_fraction | 0.333 | +| clip_range | 0.0689 | +| entropy_loss | -6.48 | +| explained_variance | 0.183 | +| learning_rate | 4.42e-05 | +| loss | -0.0263 | +| n_updates | 63804 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000209 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1416 | +| iterations | 11998 | +| time_elapsed | 17346 | +| total_timesteps | 24571904 | +| train/ | | +| approx_kl | 0.012754468 | +| clip_fraction | 0.313 | +| clip_range | 0.0689 | +| entropy_loss | -6.36 | +| explained_variance | 0.361 | +| learning_rate | 4.42e-05 | +| loss | -0.0235 | +| n_updates | 63808 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000301 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1416 | +| iterations | 11999 | +| time_elapsed | 17347 | +| total_timesteps | 24573952 | +| train/ | | +| approx_kl | 0.012033401 | +| clip_fraction | 0.317 | +| clip_range | 0.0689 | +| entropy_loss | -5.39 | +| explained_variance | 0.655 | +| learning_rate | 4.42e-05 | +| loss | -0.0281 | +| n_updates | 63812 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000199 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1416 | +| iterations | 12000 | +| time_elapsed | 17349 | +| total_timesteps | 24576000 | +| train/ | | +| approx_kl | 0.0119568175 | +| clip_fraction | 0.33 | +| clip_range | 0.0689 | +| entropy_loss | -6.19 | +| explained_variance | 0.168 | +| learning_rate | 4.42e-05 | +| loss | -0.0253 | +| n_updates | 63816 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000362 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1416 | +| iterations | 12001 | +| time_elapsed | 17350 | +| total_timesteps | 24578048 | +| train/ | | +| approx_kl | 0.014394445 | +| clip_fraction | 0.371 | +| clip_range | 0.0689 | +| entropy_loss | -6.12 | +| explained_variance | 0.555 | +| learning_rate | 4.42e-05 | +| loss | -0.0357 | +| n_updates | 63820 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.00015 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1416 | +| iterations | 12002 | +| time_elapsed | 17352 | +| total_timesteps | 24580096 | +| train/ | | +| approx_kl | 0.016430035 | +| clip_fraction | 0.378 | +| clip_range | 0.0689 | +| entropy_loss | -6.34 | +| explained_variance | 0.115 | +| learning_rate | 4.42e-05 | +| loss | -0.0377 | +| n_updates | 63824 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000154 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1416 | +| iterations | 12003 | +| time_elapsed | 17354 | +| total_timesteps | 24582144 | +| train/ | | +| approx_kl | 0.014582846 | +| clip_fraction | 0.353 | +| clip_range | 0.0689 | +| entropy_loss | -6.75 | +| explained_variance | -0.00928 | +| learning_rate | 4.42e-05 | +| loss | -0.0296 | +| n_updates | 63828 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000307 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1416 | +| iterations | 12004 | +| time_elapsed | 17355 | +| total_timesteps | 24584192 | +| train/ | | +| approx_kl | 0.016433213 | +| clip_fraction | 0.372 | +| clip_range | 0.0689 | +| entropy_loss | -6.53 | +| explained_variance | 0.248 | +| learning_rate | 4.42e-05 | +| loss | -0.0385 | +| n_updates | 63832 | +| policy_gradient_loss | -0.0226 | +| value_loss | 0.00016 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1416 | +| iterations | 12005 | +| time_elapsed | 17357 | +| total_timesteps | 24586240 | +| train/ | | +| approx_kl | 0.018504031 | +| clip_fraction | 0.364 | +| clip_range | 0.0689 | +| entropy_loss | -6.26 | +| explained_variance | 0.605 | +| learning_rate | 4.42e-05 | +| loss | -0.0317 | +| n_updates | 63836 | +| policy_gradient_loss | -0.0213 | +| value_loss | 8.93e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1416 | +| iterations | 12006 | +| time_elapsed | 17358 | +| total_timesteps | 24588288 | +| train/ | | +| approx_kl | 0.011471458 | +| clip_fraction | 0.319 | +| clip_range | 0.0689 | +| entropy_loss | -6.24 | +| explained_variance | 0.399 | +| learning_rate | 4.42e-05 | +| loss | -0.0255 | +| n_updates | 63840 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.000327 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1416 | +| iterations | 12007 | +| time_elapsed | 17360 | +| total_timesteps | 24590336 | +| train/ | | +| approx_kl | 0.011630015 | +| clip_fraction | 0.319 | +| clip_range | 0.0689 | +| entropy_loss | -5.83 | +| explained_variance | 0.508 | +| learning_rate | 4.42e-05 | +| loss | -0.0305 | +| n_updates | 63844 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000231 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1416 | +| iterations | 12008 | +| time_elapsed | 17361 | +| total_timesteps | 24592384 | +| train/ | | +| approx_kl | 0.0110759195 | +| clip_fraction | 0.336 | +| clip_range | 0.0689 | +| entropy_loss | -6.51 | +| explained_variance | 0.0607 | +| learning_rate | 4.42e-05 | +| loss | -0.0298 | +| n_updates | 63848 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000146 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1416 | +| iterations | 12009 | +| time_elapsed | 17363 | +| total_timesteps | 24594432 | +| train/ | | +| approx_kl | 0.012865532 | +| clip_fraction | 0.342 | +| clip_range | 0.0689 | +| entropy_loss | -6.33 | +| explained_variance | 0.425 | +| learning_rate | 4.42e-05 | +| loss | -0.0308 | +| n_updates | 63852 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000255 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1416 | +| iterations | 12010 | +| time_elapsed | 17364 | +| total_timesteps | 24596480 | +| train/ | | +| approx_kl | 0.012527239 | +| clip_fraction | 0.34 | +| clip_range | 0.0689 | +| entropy_loss | -5.78 | +| explained_variance | 0.343 | +| learning_rate | 4.42e-05 | +| loss | -0.0258 | +| n_updates | 63856 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000403 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1416 | +| iterations | 12011 | +| time_elapsed | 17366 | +| total_timesteps | 24598528 | +| train/ | | +| approx_kl | 0.020083439 | +| clip_fraction | 0.316 | +| clip_range | 0.0689 | +| entropy_loss | -6.3 | +| explained_variance | 0.235 | +| learning_rate | 4.42e-05 | +| loss | -0.025 | +| n_updates | 63860 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000361 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1416 | +| iterations | 12012 | +| time_elapsed | 17367 | +| total_timesteps | 24600576 | +| train/ | | +| approx_kl | 0.016003495 | +| clip_fraction | 0.384 | +| clip_range | 0.0689 | +| entropy_loss | -6.55 | +| explained_variance | -0.427 | +| learning_rate | 4.42e-05 | +| loss | -0.0392 | +| n_updates | 63864 | +| policy_gradient_loss | -0.0237 | +| value_loss | 0.000131 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1416 | +| iterations | 12013 | +| time_elapsed | 17369 | +| total_timesteps | 24602624 | +| train/ | | +| approx_kl | 0.011083475 | +| clip_fraction | 0.349 | +| clip_range | 0.0688 | +| entropy_loss | -7.17 | +| explained_variance | -0.0912 | +| learning_rate | 4.42e-05 | +| loss | -0.0325 | +| n_updates | 63868 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000203 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1416 | +| iterations | 12014 | +| time_elapsed | 17370 | +| total_timesteps | 24604672 | +| train/ | | +| approx_kl | 0.014048994 | +| clip_fraction | 0.344 | +| clip_range | 0.0688 | +| entropy_loss | -5.82 | +| explained_variance | 0.617 | +| learning_rate | 4.42e-05 | +| loss | -0.0303 | +| n_updates | 63872 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000154 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1416 | +| iterations | 12015 | +| time_elapsed | 17372 | +| total_timesteps | 24606720 | +| train/ | | +| approx_kl | 0.012629747 | +| clip_fraction | 0.315 | +| clip_range | 0.0688 | +| entropy_loss | -5.68 | +| explained_variance | 0.403 | +| learning_rate | 4.42e-05 | +| loss | -0.0199 | +| n_updates | 63876 | +| policy_gradient_loss | -0.0132 | +| value_loss | 0.000294 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1416 | +| iterations | 12016 | +| time_elapsed | 17373 | +| total_timesteps | 24608768 | +| train/ | | +| approx_kl | 0.013849245 | +| clip_fraction | 0.348 | +| clip_range | 0.0688 | +| entropy_loss | -6.62 | +| explained_variance | 0.00724 | +| learning_rate | 4.42e-05 | +| loss | -0.0347 | +| n_updates | 63880 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000211 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1416 | +| iterations | 12017 | +| time_elapsed | 17374 | +| total_timesteps | 24610816 | +| train/ | | +| approx_kl | 0.013518812 | +| clip_fraction | 0.363 | +| clip_range | 0.0688 | +| entropy_loss | -6.73 | +| explained_variance | 0.163 | +| learning_rate | 4.42e-05 | +| loss | -0.0316 | +| n_updates | 63884 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000225 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1416 | +| iterations | 12018 | +| time_elapsed | 17376 | +| total_timesteps | 24612864 | +| train/ | | +| approx_kl | 0.013261214 | +| clip_fraction | 0.358 | +| clip_range | 0.0688 | +| entropy_loss | -6.56 | +| explained_variance | 0.0254 | +| learning_rate | 4.42e-05 | +| loss | -0.031 | +| n_updates | 63888 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000232 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1416 | +| iterations | 12019 | +| time_elapsed | 17377 | +| total_timesteps | 24614912 | +| train/ | | +| approx_kl | 0.011104889 | +| clip_fraction | 0.322 | +| clip_range | 0.0688 | +| entropy_loss | -6.24 | +| explained_variance | 0.513 | +| learning_rate | 4.42e-05 | +| loss | -0.0369 | +| n_updates | 63892 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000264 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1416 | +| iterations | 12020 | +| time_elapsed | 17379 | +| total_timesteps | 24616960 | +| train/ | | +| approx_kl | 0.0133133605 | +| clip_fraction | 0.363 | +| clip_range | 0.0688 | +| entropy_loss | -6.12 | +| explained_variance | 0.446 | +| learning_rate | 4.42e-05 | +| loss | -0.0354 | +| n_updates | 63896 | +| policy_gradient_loss | -0.0227 | +| value_loss | 0.000101 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1416 | +| iterations | 12021 | +| time_elapsed | 17380 | +| total_timesteps | 24619008 | +| train/ | | +| approx_kl | 0.01897671 | +| clip_fraction | 0.332 | +| clip_range | 0.0688 | +| entropy_loss | -5.93 | +| explained_variance | 0.631 | +| learning_rate | 4.42e-05 | +| loss | -0.0284 | +| n_updates | 63900 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000158 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1416 | +| iterations | 12022 | +| time_elapsed | 17382 | +| total_timesteps | 24621056 | +| train/ | | +| approx_kl | 0.014692038 | +| clip_fraction | 0.363 | +| clip_range | 0.0688 | +| entropy_loss | -6.32 | +| explained_variance | 0.482 | +| learning_rate | 4.42e-05 | +| loss | -0.0302 | +| n_updates | 63904 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000103 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1416 | +| iterations | 12023 | +| time_elapsed | 17383 | +| total_timesteps | 24623104 | +| train/ | | +| approx_kl | 0.013848917 | +| clip_fraction | 0.341 | +| clip_range | 0.0688 | +| entropy_loss | -5.81 | +| explained_variance | 0.619 | +| learning_rate | 4.42e-05 | +| loss | -0.0332 | +| n_updates | 63908 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.00013 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1416 | +| iterations | 12024 | +| time_elapsed | 17385 | +| total_timesteps | 24625152 | +| train/ | | +| approx_kl | 0.011016828 | +| clip_fraction | 0.326 | +| clip_range | 0.0688 | +| entropy_loss | -6.09 | +| explained_variance | 0.564 | +| learning_rate | 4.42e-05 | +| loss | -0.0291 | +| n_updates | 63912 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000131 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1416 | +| iterations | 12025 | +| time_elapsed | 17386 | +| total_timesteps | 24627200 | +| train/ | | +| approx_kl | 0.012009544 | +| clip_fraction | 0.312 | +| clip_range | 0.0688 | +| entropy_loss | -5.97 | +| explained_variance | 0.388 | +| learning_rate | 4.42e-05 | +| loss | -0.0235 | +| n_updates | 63916 | +| policy_gradient_loss | -0.0147 | +| value_loss | 0.000357 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1416 | +| iterations | 12026 | +| time_elapsed | 17388 | +| total_timesteps | 24629248 | +| train/ | | +| approx_kl | 0.015226565 | +| clip_fraction | 0.343 | +| clip_range | 0.0688 | +| entropy_loss | -5.85 | +| explained_variance | 0.619 | +| learning_rate | 4.42e-05 | +| loss | -0.0332 | +| n_updates | 63920 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000129 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1416 | +| iterations | 12027 | +| time_elapsed | 17390 | +| total_timesteps | 24631296 | +| train/ | | +| approx_kl | 0.012895448 | +| clip_fraction | 0.336 | +| clip_range | 0.0688 | +| entropy_loss | -6.42 | +| explained_variance | 0.0834 | +| learning_rate | 4.42e-05 | +| loss | -0.0315 | +| n_updates | 63924 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000218 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1416 | +| iterations | 12028 | +| time_elapsed | 17391 | +| total_timesteps | 24633344 | +| train/ | | +| approx_kl | 0.013505238 | +| clip_fraction | 0.345 | +| clip_range | 0.0688 | +| entropy_loss | -6.53 | +| explained_variance | 0.523 | +| learning_rate | 4.42e-05 | +| loss | -0.0311 | +| n_updates | 63928 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.00014 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1416 | +| iterations | 12029 | +| time_elapsed | 17392 | +| total_timesteps | 24635392 | +| train/ | | +| approx_kl | 0.009423788 | +| clip_fraction | 0.344 | +| clip_range | 0.0688 | +| entropy_loss | -6.78 | +| explained_variance | 0.0369 | +| learning_rate | 4.41e-05 | +| loss | -0.0243 | +| n_updates | 63932 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000485 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1416 | +| iterations | 12030 | +| time_elapsed | 17394 | +| total_timesteps | 24637440 | +| train/ | | +| approx_kl | 0.012397109 | +| clip_fraction | 0.341 | +| clip_range | 0.0688 | +| entropy_loss | -5.97 | +| explained_variance | 0.505 | +| learning_rate | 4.41e-05 | +| loss | -0.0274 | +| n_updates | 63936 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000274 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1416 | +| iterations | 12031 | +| time_elapsed | 17395 | +| total_timesteps | 24639488 | +| train/ | | +| approx_kl | 0.014745111 | +| clip_fraction | 0.367 | +| clip_range | 0.0688 | +| entropy_loss | -6.21 | +| explained_variance | 0.533 | +| learning_rate | 4.41e-05 | +| loss | -0.0351 | +| n_updates | 63940 | +| policy_gradient_loss | -0.0228 | +| value_loss | 9.65e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1416 | +| iterations | 12032 | +| time_elapsed | 17397 | +| total_timesteps | 24641536 | +| train/ | | +| approx_kl | 0.01933102 | +| clip_fraction | 0.347 | +| clip_range | 0.0688 | +| entropy_loss | -6.18 | +| explained_variance | 0.471 | +| learning_rate | 4.41e-05 | +| loss | -0.0271 | +| n_updates | 63944 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000146 | +---------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1416 | +| iterations | 12033 | +| time_elapsed | 17398 | +| total_timesteps | 24643584 | +| train/ | | +| approx_kl | 0.0150236 | +| clip_fraction | 0.356 | +| clip_range | 0.0688 | +| entropy_loss | -6.27 | +| explained_variance | 0.373 | +| learning_rate | 4.41e-05 | +| loss | -0.0279 | +| n_updates | 63948 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000246 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1416 | +| iterations | 12034 | +| time_elapsed | 17400 | +| total_timesteps | 24645632 | +| train/ | | +| approx_kl | 0.015153922 | +| clip_fraction | 0.344 | +| clip_range | 0.0688 | +| entropy_loss | -6.15 | +| explained_variance | 0.332 | +| learning_rate | 4.41e-05 | +| loss | -0.0328 | +| n_updates | 63952 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000206 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1416 | +| iterations | 12035 | +| time_elapsed | 17401 | +| total_timesteps | 24647680 | +| train/ | | +| approx_kl | 0.015298638 | +| clip_fraction | 0.384 | +| clip_range | 0.0688 | +| entropy_loss | -6.83 | +| explained_variance | -0.356 | +| learning_rate | 4.41e-05 | +| loss | -0.0348 | +| n_updates | 63956 | +| policy_gradient_loss | -0.022 | +| value_loss | 0.000119 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1416 | +| iterations | 12036 | +| time_elapsed | 17403 | +| total_timesteps | 24649728 | +| train/ | | +| approx_kl | 0.015101716 | +| clip_fraction | 0.335 | +| clip_range | 0.0688 | +| entropy_loss | -6.49 | +| explained_variance | 0.511 | +| learning_rate | 4.41e-05 | +| loss | -0.0305 | +| n_updates | 63960 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000143 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1416 | +| iterations | 12037 | +| time_elapsed | 17404 | +| total_timesteps | 24651776 | +| train/ | | +| approx_kl | 0.013056035 | +| clip_fraction | 0.314 | +| clip_range | 0.0688 | +| entropy_loss | -5.99 | +| explained_variance | 0.483 | +| learning_rate | 4.41e-05 | +| loss | -0.029 | +| n_updates | 63964 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000256 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1416 | +| iterations | 12038 | +| time_elapsed | 17406 | +| total_timesteps | 24653824 | +| train/ | | +| approx_kl | 0.016983304 | +| clip_fraction | 0.323 | +| clip_range | 0.0688 | +| entropy_loss | -6.23 | +| explained_variance | 0.38 | +| learning_rate | 4.41e-05 | +| loss | -0.0273 | +| n_updates | 63968 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.00021 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1416 | +| iterations | 12039 | +| time_elapsed | 17407 | +| total_timesteps | 24655872 | +| train/ | | +| approx_kl | 0.012799231 | +| clip_fraction | 0.345 | +| clip_range | 0.0688 | +| entropy_loss | -6.51 | +| explained_variance | 0.22 | +| learning_rate | 4.41e-05 | +| loss | -0.028 | +| n_updates | 63972 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000277 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1416 | +| iterations | 12040 | +| time_elapsed | 17409 | +| total_timesteps | 24657920 | +| train/ | | +| approx_kl | 0.017676633 | +| clip_fraction | 0.324 | +| clip_range | 0.0688 | +| entropy_loss | -5.43 | +| explained_variance | 0.657 | +| learning_rate | 4.41e-05 | +| loss | -0.0272 | +| n_updates | 63976 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000152 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1416 | +| iterations | 12041 | +| time_elapsed | 17410 | +| total_timesteps | 24659968 | +| train/ | | +| approx_kl | 0.013479661 | +| clip_fraction | 0.361 | +| clip_range | 0.0688 | +| entropy_loss | -5.84 | +| explained_variance | 0.585 | +| learning_rate | 4.41e-05 | +| loss | -0.0344 | +| n_updates | 63980 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000109 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1416 | +| iterations | 12042 | +| time_elapsed | 17412 | +| total_timesteps | 24662016 | +| train/ | | +| approx_kl | 0.014317503 | +| clip_fraction | 0.331 | +| clip_range | 0.0688 | +| entropy_loss | -6.16 | +| explained_variance | 0.187 | +| learning_rate | 4.41e-05 | +| loss | -0.0274 | +| n_updates | 63984 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000329 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1416 | +| iterations | 12043 | +| time_elapsed | 17413 | +| total_timesteps | 24664064 | +| train/ | | +| approx_kl | 0.014967211 | +| clip_fraction | 0.374 | +| clip_range | 0.0688 | +| entropy_loss | -6.42 | +| explained_variance | 0.345 | +| learning_rate | 4.41e-05 | +| loss | -0.0355 | +| n_updates | 63988 | +| policy_gradient_loss | -0.022 | +| value_loss | 0.000109 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1416 | +| iterations | 12044 | +| time_elapsed | 17415 | +| total_timesteps | 24666112 | +| train/ | | +| approx_kl | 0.014978265 | +| clip_fraction | 0.344 | +| clip_range | 0.0688 | +| entropy_loss | -6.29 | +| explained_variance | 0.342 | +| learning_rate | 4.41e-05 | +| loss | -0.0318 | +| n_updates | 63992 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000215 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1416 | +| iterations | 12045 | +| time_elapsed | 17416 | +| total_timesteps | 24668160 | +| train/ | | +| approx_kl | 0.016700694 | +| clip_fraction | 0.311 | +| clip_range | 0.0688 | +| entropy_loss | -6.32 | +| explained_variance | 0.298 | +| learning_rate | 4.41e-05 | +| loss | -0.0297 | +| n_updates | 63996 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.00035 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1416 | +| iterations | 12046 | +| time_elapsed | 17418 | +| total_timesteps | 24670208 | +| train/ | | +| approx_kl | 0.013791189 | +| clip_fraction | 0.373 | +| clip_range | 0.0688 | +| entropy_loss | -6.52 | +| explained_variance | 0.336 | +| learning_rate | 4.41e-05 | +| loss | -0.0374 | +| n_updates | 64000 | +| policy_gradient_loss | -0.0236 | +| value_loss | 8.44e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1416 | +| iterations | 12047 | +| time_elapsed | 17419 | +| total_timesteps | 24672256 | +| train/ | | +| approx_kl | 0.013718107 | +| clip_fraction | 0.351 | +| clip_range | 0.0688 | +| entropy_loss | -6.14 | +| explained_variance | 0.264 | +| learning_rate | 4.41e-05 | +| loss | -0.0367 | +| n_updates | 64004 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000181 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1416 | +| iterations | 12048 | +| time_elapsed | 17421 | +| total_timesteps | 24674304 | +| train/ | | +| approx_kl | 0.012470052 | +| clip_fraction | 0.352 | +| clip_range | 0.0688 | +| entropy_loss | -6.32 | +| explained_variance | 0.436 | +| learning_rate | 4.41e-05 | +| loss | -0.0363 | +| n_updates | 64008 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000194 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1416 | +| iterations | 12049 | +| time_elapsed | 17422 | +| total_timesteps | 24676352 | +| train/ | | +| approx_kl | 0.012135589 | +| clip_fraction | 0.337 | +| clip_range | 0.0688 | +| entropy_loss | -6.24 | +| explained_variance | 0.392 | +| learning_rate | 4.41e-05 | +| loss | -0.0291 | +| n_updates | 64012 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000122 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1416 | +| iterations | 12050 | +| time_elapsed | 17423 | +| total_timesteps | 24678400 | +| train/ | | +| approx_kl | 0.014821863 | +| clip_fraction | 0.356 | +| clip_range | 0.0688 | +| entropy_loss | -6.16 | +| explained_variance | 0.374 | +| learning_rate | 4.41e-05 | +| loss | -0.0294 | +| n_updates | 64016 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000218 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1416 | +| iterations | 12051 | +| time_elapsed | 17425 | +| total_timesteps | 24680448 | +| train/ | | +| approx_kl | 0.017094228 | +| clip_fraction | 0.362 | +| clip_range | 0.0688 | +| entropy_loss | -5.74 | +| explained_variance | 0.517 | +| learning_rate | 4.41e-05 | +| loss | -0.0285 | +| n_updates | 64020 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000137 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1416 | +| iterations | 12052 | +| time_elapsed | 17426 | +| total_timesteps | 24682496 | +| train/ | | +| approx_kl | 0.01330757 | +| clip_fraction | 0.354 | +| clip_range | 0.0688 | +| entropy_loss | -6.08 | +| explained_variance | 0.507 | +| learning_rate | 4.41e-05 | +| loss | -0.0329 | +| n_updates | 64024 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.00014 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1416 | +| iterations | 12053 | +| time_elapsed | 17428 | +| total_timesteps | 24684544 | +| train/ | | +| approx_kl | 0.015201141 | +| clip_fraction | 0.347 | +| clip_range | 0.0688 | +| entropy_loss | -6.44 | +| explained_variance | -0.0331 | +| learning_rate | 4.41e-05 | +| loss | -0.0348 | +| n_updates | 64028 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000149 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1416 | +| iterations | 12054 | +| time_elapsed | 17429 | +| total_timesteps | 24686592 | +| train/ | | +| approx_kl | 0.01210054 | +| clip_fraction | 0.342 | +| clip_range | 0.0688 | +| entropy_loss | -6.43 | +| explained_variance | 0.394 | +| learning_rate | 4.41e-05 | +| loss | -0.0263 | +| n_updates | 64032 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000212 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1416 | +| iterations | 12055 | +| time_elapsed | 17431 | +| total_timesteps | 24688640 | +| train/ | | +| approx_kl | 0.013431929 | +| clip_fraction | 0.378 | +| clip_range | 0.0688 | +| entropy_loss | -6.11 | +| explained_variance | 0.542 | +| learning_rate | 4.41e-05 | +| loss | -0.037 | +| n_updates | 64036 | +| policy_gradient_loss | -0.0228 | +| value_loss | 7.49e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1416 | +| iterations | 12056 | +| time_elapsed | 17432 | +| total_timesteps | 24690688 | +| train/ | | +| approx_kl | 0.013063707 | +| clip_fraction | 0.345 | +| clip_range | 0.0688 | +| entropy_loss | -6.81 | +| explained_variance | 0.539 | +| learning_rate | 4.41e-05 | +| loss | -0.0339 | +| n_updates | 64040 | +| policy_gradient_loss | -0.0197 | +| value_loss | 6.61e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1416 | +| iterations | 12057 | +| time_elapsed | 17434 | +| total_timesteps | 24692736 | +| train/ | | +| approx_kl | 0.01004834 | +| clip_fraction | 0.3 | +| clip_range | 0.0688 | +| entropy_loss | -6.17 | +| explained_variance | 0.414 | +| learning_rate | 4.41e-05 | +| loss | -0.0234 | +| n_updates | 64044 | +| policy_gradient_loss | -0.0138 | +| value_loss | 0.000352 | +---------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1416 | +| iterations | 12058 | +| time_elapsed | 17435 | +| total_timesteps | 24694784 | +| train/ | | +| approx_kl | 0.0139775 | +| clip_fraction | 0.338 | +| clip_range | 0.0688 | +| entropy_loss | -6.15 | +| explained_variance | 0.0802 | +| learning_rate | 4.41e-05 | +| loss | -0.0314 | +| n_updates | 64048 | +| policy_gradient_loss | -0.0204 | +| value_loss | 8.96e-05 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1416 | +| iterations | 12059 | +| time_elapsed | 17437 | +| total_timesteps | 24696832 | +| train/ | | +| approx_kl | 0.015358426 | +| clip_fraction | 0.375 | +| clip_range | 0.0688 | +| entropy_loss | -6.67 | +| explained_variance | 0.15 | +| learning_rate | 4.41e-05 | +| loss | -0.0344 | +| n_updates | 64052 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000186 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1416 | +| iterations | 12060 | +| time_elapsed | 17438 | +| total_timesteps | 24698880 | +| train/ | | +| approx_kl | 0.018878812 | +| clip_fraction | 0.377 | +| clip_range | 0.0688 | +| entropy_loss | -6.79 | +| explained_variance | -0.0798 | +| learning_rate | 4.41e-05 | +| loss | -0.034 | +| n_updates | 64056 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000141 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1416 | +| iterations | 12061 | +| time_elapsed | 17440 | +| total_timesteps | 24700928 | +| train/ | | +| approx_kl | 0.015248011 | +| clip_fraction | 0.358 | +| clip_range | 0.0688 | +| entropy_loss | -6.48 | +| explained_variance | 0.619 | +| learning_rate | 4.41e-05 | +| loss | -0.0354 | +| n_updates | 64060 | +| policy_gradient_loss | -0.02 | +| value_loss | 7.42e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1416 | +| iterations | 12062 | +| time_elapsed | 17441 | +| total_timesteps | 24702976 | +| train/ | | +| approx_kl | 0.014279528 | +| clip_fraction | 0.357 | +| clip_range | 0.0688 | +| entropy_loss | -6.06 | +| explained_variance | 0.671 | +| learning_rate | 4.41e-05 | +| loss | -0.0325 | +| n_updates | 64064 | +| policy_gradient_loss | -0.0209 | +| value_loss | 7.42e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1416 | +| iterations | 12063 | +| time_elapsed | 17443 | +| total_timesteps | 24705024 | +| train/ | | +| approx_kl | 0.012099169 | +| clip_fraction | 0.352 | +| clip_range | 0.0688 | +| entropy_loss | -6.83 | +| explained_variance | -0.00658 | +| learning_rate | 4.41e-05 | +| loss | -0.0279 | +| n_updates | 64068 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000121 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1416 | +| iterations | 12064 | +| time_elapsed | 17444 | +| total_timesteps | 24707072 | +| train/ | | +| approx_kl | 0.011135187 | +| clip_fraction | 0.312 | +| clip_range | 0.0688 | +| entropy_loss | -5.74 | +| explained_variance | 0.653 | +| learning_rate | 4.41e-05 | +| loss | -0.0229 | +| n_updates | 64072 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.000185 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1416 | +| iterations | 12065 | +| time_elapsed | 17446 | +| total_timesteps | 24709120 | +| train/ | | +| approx_kl | 0.015737446 | +| clip_fraction | 0.313 | +| clip_range | 0.0688 | +| entropy_loss | -5.98 | +| explained_variance | 0.348 | +| learning_rate | 4.41e-05 | +| loss | -0.0221 | +| n_updates | 64076 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000182 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1416 | +| iterations | 12066 | +| time_elapsed | 17447 | +| total_timesteps | 24711168 | +| train/ | | +| approx_kl | 0.014781363 | +| clip_fraction | 0.331 | +| clip_range | 0.0688 | +| entropy_loss | -5.81 | +| explained_variance | 0.436 | +| learning_rate | 4.41e-05 | +| loss | -0.0251 | +| n_updates | 64080 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000283 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1416 | +| iterations | 12067 | +| time_elapsed | 17449 | +| total_timesteps | 24713216 | +| train/ | | +| approx_kl | 0.012055348 | +| clip_fraction | 0.352 | +| clip_range | 0.0688 | +| entropy_loss | -6.51 | +| explained_variance | 0.267 | +| learning_rate | 4.41e-05 | +| loss | -0.0223 | +| n_updates | 64084 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.00022 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1416 | +| iterations | 12068 | +| time_elapsed | 17450 | +| total_timesteps | 24715264 | +| train/ | | +| approx_kl | 0.017237976 | +| clip_fraction | 0.404 | +| clip_range | 0.0688 | +| entropy_loss | -5.88 | +| explained_variance | 0.719 | +| learning_rate | 4.41e-05 | +| loss | -0.0349 | +| n_updates | 64088 | +| policy_gradient_loss | -0.024 | +| value_loss | 6.06e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1416 | +| iterations | 12069 | +| time_elapsed | 17452 | +| total_timesteps | 24717312 | +| train/ | | +| approx_kl | 0.015202913 | +| clip_fraction | 0.349 | +| clip_range | 0.0688 | +| entropy_loss | -6.32 | +| explained_variance | 0.276 | +| learning_rate | 4.41e-05 | +| loss | -0.0272 | +| n_updates | 64092 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000198 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1416 | +| iterations | 12070 | +| time_elapsed | 17453 | +| total_timesteps | 24719360 | +| train/ | | +| approx_kl | 0.013276294 | +| clip_fraction | 0.336 | +| clip_range | 0.0688 | +| entropy_loss | -6.27 | +| explained_variance | 0.391 | +| learning_rate | 4.41e-05 | +| loss | -0.0273 | +| n_updates | 64096 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000259 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1416 | +| iterations | 12071 | +| time_elapsed | 17455 | +| total_timesteps | 24721408 | +| train/ | | +| approx_kl | 0.014820542 | +| clip_fraction | 0.343 | +| clip_range | 0.0688 | +| entropy_loss | -6.37 | +| explained_variance | 0.275 | +| learning_rate | 4.41e-05 | +| loss | -0.0262 | +| n_updates | 64100 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000194 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1416 | +| iterations | 12072 | +| time_elapsed | 17456 | +| total_timesteps | 24723456 | +| train/ | | +| approx_kl | 0.015887622 | +| clip_fraction | 0.359 | +| clip_range | 0.0688 | +| entropy_loss | -6.41 | +| explained_variance | 0.359 | +| learning_rate | 4.41e-05 | +| loss | -0.0356 | +| n_updates | 64104 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000125 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1416 | +| iterations | 12073 | +| time_elapsed | 17458 | +| total_timesteps | 24725504 | +| train/ | | +| approx_kl | 0.014188009 | +| clip_fraction | 0.332 | +| clip_range | 0.0688 | +| entropy_loss | -5.99 | +| explained_variance | 0.629 | +| learning_rate | 4.41e-05 | +| loss | -0.0319 | +| n_updates | 64108 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000179 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1416 | +| iterations | 12074 | +| time_elapsed | 17459 | +| total_timesteps | 24727552 | +| train/ | | +| approx_kl | 0.018816052 | +| clip_fraction | 0.372 | +| clip_range | 0.0688 | +| entropy_loss | -6.46 | +| explained_variance | 0.413 | +| learning_rate | 4.41e-05 | +| loss | -0.0352 | +| n_updates | 64112 | +| policy_gradient_loss | -0.0218 | +| value_loss | 8.31e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1416 | +| iterations | 12075 | +| time_elapsed | 17461 | +| total_timesteps | 24729600 | +| train/ | | +| approx_kl | 0.016584225 | +| clip_fraction | 0.343 | +| clip_range | 0.0688 | +| entropy_loss | -6.31 | +| explained_variance | 0.29 | +| learning_rate | 4.41e-05 | +| loss | -0.0243 | +| n_updates | 64116 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000184 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1416 | +| iterations | 12076 | +| time_elapsed | 17462 | +| total_timesteps | 24731648 | +| train/ | | +| approx_kl | 0.01300838 | +| clip_fraction | 0.345 | +| clip_range | 0.0688 | +| entropy_loss | -6.53 | +| explained_variance | 0.409 | +| learning_rate | 4.41e-05 | +| loss | -0.0332 | +| n_updates | 64120 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000103 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1416 | +| iterations | 12077 | +| time_elapsed | 17464 | +| total_timesteps | 24733696 | +| train/ | | +| approx_kl | 0.013552561 | +| clip_fraction | 0.355 | +| clip_range | 0.0688 | +| entropy_loss | -6.4 | +| explained_variance | 0.501 | +| learning_rate | 4.41e-05 | +| loss | -0.0303 | +| n_updates | 64124 | +| policy_gradient_loss | -0.0193 | +| value_loss | 9.3e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1416 | +| iterations | 12078 | +| time_elapsed | 17465 | +| total_timesteps | 24735744 | +| train/ | | +| approx_kl | 0.012560977 | +| clip_fraction | 0.336 | +| clip_range | 0.0688 | +| entropy_loss | -6.84 | +| explained_variance | -0.127 | +| learning_rate | 4.41e-05 | +| loss | -0.0297 | +| n_updates | 64128 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000128 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1416 | +| iterations | 12079 | +| time_elapsed | 17467 | +| total_timesteps | 24737792 | +| train/ | | +| approx_kl | 0.014717875 | +| clip_fraction | 0.356 | +| clip_range | 0.0688 | +| entropy_loss | -6.46 | +| explained_variance | 0.24 | +| learning_rate | 4.41e-05 | +| loss | -0.0237 | +| n_updates | 64132 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000232 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1416 | +| iterations | 12080 | +| time_elapsed | 17468 | +| total_timesteps | 24739840 | +| train/ | | +| approx_kl | 0.014279366 | +| clip_fraction | 0.357 | +| clip_range | 0.0688 | +| entropy_loss | -5.63 | +| explained_variance | 0.631 | +| learning_rate | 4.41e-05 | +| loss | -0.0296 | +| n_updates | 64136 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000131 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1416 | +| iterations | 12081 | +| time_elapsed | 17470 | +| total_timesteps | 24741888 | +| train/ | | +| approx_kl | 0.013337423 | +| clip_fraction | 0.318 | +| clip_range | 0.0688 | +| entropy_loss | -6.02 | +| explained_variance | 0.448 | +| learning_rate | 4.41e-05 | +| loss | -0.0299 | +| n_updates | 64140 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000196 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1416 | +| iterations | 12082 | +| time_elapsed | 17471 | +| total_timesteps | 24743936 | +| train/ | | +| approx_kl | 0.015034452 | +| clip_fraction | 0.369 | +| clip_range | 0.0688 | +| entropy_loss | -6.29 | +| explained_variance | 0.423 | +| learning_rate | 4.41e-05 | +| loss | -0.0306 | +| n_updates | 64144 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000158 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1416 | +| iterations | 12083 | +| time_elapsed | 17473 | +| total_timesteps | 24745984 | +| train/ | | +| approx_kl | 0.013646152 | +| clip_fraction | 0.349 | +| clip_range | 0.0688 | +| entropy_loss | -6.41 | +| explained_variance | 0.0185 | +| learning_rate | 4.41e-05 | +| loss | -0.0272 | +| n_updates | 64148 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000253 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1416 | +| iterations | 12084 | +| time_elapsed | 17474 | +| total_timesteps | 24748032 | +| train/ | | +| approx_kl | 0.015188677 | +| clip_fraction | 0.363 | +| clip_range | 0.0688 | +| entropy_loss | -6.38 | +| explained_variance | 0.536 | +| learning_rate | 4.41e-05 | +| loss | -0.0379 | +| n_updates | 64152 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000114 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1416 | +| iterations | 12085 | +| time_elapsed | 17476 | +| total_timesteps | 24750080 | +| train/ | | +| approx_kl | 0.01278403 | +| clip_fraction | 0.346 | +| clip_range | 0.0688 | +| entropy_loss | -6.56 | +| explained_variance | 0.333 | +| learning_rate | 4.41e-05 | +| loss | -0.0326 | +| n_updates | 64156 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000104 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1416 | +| iterations | 12086 | +| time_elapsed | 17477 | +| total_timesteps | 24752128 | +| train/ | | +| approx_kl | 0.013686467 | +| clip_fraction | 0.364 | +| clip_range | 0.0688 | +| entropy_loss | -6.26 | +| explained_variance | 0.552 | +| learning_rate | 4.41e-05 | +| loss | -0.0315 | +| n_updates | 64160 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000114 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1416 | +| iterations | 12087 | +| time_elapsed | 17479 | +| total_timesteps | 24754176 | +| train/ | | +| approx_kl | 0.013297241 | +| clip_fraction | 0.337 | +| clip_range | 0.0688 | +| entropy_loss | -6.62 | +| explained_variance | 0.238 | +| learning_rate | 4.41e-05 | +| loss | -0.0252 | +| n_updates | 64164 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000278 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1416 | +| iterations | 12088 | +| time_elapsed | 17480 | +| total_timesteps | 24756224 | +| train/ | | +| approx_kl | 0.014862866 | +| clip_fraction | 0.353 | +| clip_range | 0.0688 | +| entropy_loss | -6.01 | +| explained_variance | 0.21 | +| learning_rate | 4.41e-05 | +| loss | -0.0305 | +| n_updates | 64168 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000357 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1416 | +| iterations | 12089 | +| time_elapsed | 17482 | +| total_timesteps | 24758272 | +| train/ | | +| approx_kl | 0.017658781 | +| clip_fraction | 0.368 | +| clip_range | 0.0688 | +| entropy_loss | -6.32 | +| explained_variance | 0.184 | +| learning_rate | 4.41e-05 | +| loss | -0.0355 | +| n_updates | 64172 | +| policy_gradient_loss | -0.0231 | +| value_loss | 0.000128 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1416 | +| iterations | 12090 | +| time_elapsed | 17483 | +| total_timesteps | 24760320 | +| train/ | | +| approx_kl | 0.015547387 | +| clip_fraction | 0.358 | +| clip_range | 0.0688 | +| entropy_loss | -6.8 | +| explained_variance | 0.0783 | +| learning_rate | 4.41e-05 | +| loss | -0.0339 | +| n_updates | 64176 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.00012 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1416 | +| iterations | 12091 | +| time_elapsed | 17485 | +| total_timesteps | 24762368 | +| train/ | | +| approx_kl | 0.016243193 | +| clip_fraction | 0.34 | +| clip_range | 0.0688 | +| entropy_loss | -5.8 | +| explained_variance | 0.58 | +| learning_rate | 4.41e-05 | +| loss | -0.0258 | +| n_updates | 64180 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000221 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1416 | +| iterations | 12092 | +| time_elapsed | 17486 | +| total_timesteps | 24764416 | +| train/ | | +| approx_kl | 0.013554592 | +| clip_fraction | 0.326 | +| clip_range | 0.0688 | +| entropy_loss | -6.07 | +| explained_variance | 0.224 | +| learning_rate | 4.41e-05 | +| loss | -0.0263 | +| n_updates | 64184 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000203 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1416 | +| iterations | 12093 | +| time_elapsed | 17488 | +| total_timesteps | 24766464 | +| train/ | | +| approx_kl | 0.013015343 | +| clip_fraction | 0.345 | +| clip_range | 0.0688 | +| entropy_loss | -5.79 | +| explained_variance | 0.489 | +| learning_rate | 4.41e-05 | +| loss | -0.0281 | +| n_updates | 64188 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000292 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1416 | +| iterations | 12094 | +| time_elapsed | 17489 | +| total_timesteps | 24768512 | +| train/ | | +| approx_kl | 0.016579323 | +| clip_fraction | 0.352 | +| clip_range | 0.0688 | +| entropy_loss | -6.5 | +| explained_variance | 0.179 | +| learning_rate | 4.41e-05 | +| loss | -0.0323 | +| n_updates | 64192 | +| policy_gradient_loss | -0.0223 | +| value_loss | 7.19e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1416 | +| iterations | 12095 | +| time_elapsed | 17491 | +| total_timesteps | 24770560 | +| train/ | | +| approx_kl | 0.012340581 | +| clip_fraction | 0.322 | +| clip_range | 0.0688 | +| entropy_loss | -6.33 | +| explained_variance | 0.353 | +| learning_rate | 4.41e-05 | +| loss | -0.0285 | +| n_updates | 64196 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000301 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1416 | +| iterations | 12096 | +| time_elapsed | 17492 | +| total_timesteps | 24772608 | +| train/ | | +| approx_kl | 0.01219576 | +| clip_fraction | 0.308 | +| clip_range | 0.0688 | +| entropy_loss | -6.09 | +| explained_variance | 0.331 | +| learning_rate | 4.41e-05 | +| loss | -0.0299 | +| n_updates | 64200 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.00025 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1416 | +| iterations | 12097 | +| time_elapsed | 17494 | +| total_timesteps | 24774656 | +| train/ | | +| approx_kl | 0.0121173505 | +| clip_fraction | 0.339 | +| clip_range | 0.0688 | +| entropy_loss | -6.38 | +| explained_variance | 0.0686 | +| learning_rate | 4.41e-05 | +| loss | -0.0236 | +| n_updates | 64204 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000348 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1416 | +| iterations | 12098 | +| time_elapsed | 17495 | +| total_timesteps | 24776704 | +| train/ | | +| approx_kl | 0.015491415 | +| clip_fraction | 0.323 | +| clip_range | 0.0688 | +| entropy_loss | -6.04 | +| explained_variance | 0.579 | +| learning_rate | 4.41e-05 | +| loss | -0.033 | +| n_updates | 64208 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000157 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1416 | +| iterations | 12099 | +| time_elapsed | 17497 | +| total_timesteps | 24778752 | +| train/ | | +| approx_kl | 0.016249768 | +| clip_fraction | 0.341 | +| clip_range | 0.0688 | +| entropy_loss | -6.47 | +| explained_variance | -0.144 | +| learning_rate | 4.41e-05 | +| loss | -0.0348 | +| n_updates | 64212 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000189 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1416 | +| iterations | 12100 | +| time_elapsed | 17498 | +| total_timesteps | 24780800 | +| train/ | | +| approx_kl | 0.013285392 | +| clip_fraction | 0.35 | +| clip_range | 0.0688 | +| entropy_loss | -6.36 | +| explained_variance | 0.317 | +| learning_rate | 4.41e-05 | +| loss | -0.0327 | +| n_updates | 64216 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000157 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1416 | +| iterations | 12101 | +| time_elapsed | 17500 | +| total_timesteps | 24782848 | +| train/ | | +| approx_kl | 0.015211892 | +| clip_fraction | 0.369 | +| clip_range | 0.0688 | +| entropy_loss | -6.25 | +| explained_variance | 0.6 | +| learning_rate | 4.41e-05 | +| loss | -0.0351 | +| n_updates | 64220 | +| policy_gradient_loss | -0.0215 | +| value_loss | 8.78e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1416 | +| iterations | 12102 | +| time_elapsed | 17501 | +| total_timesteps | 24784896 | +| train/ | | +| approx_kl | 0.014976804 | +| clip_fraction | 0.358 | +| clip_range | 0.0688 | +| entropy_loss | -5.8 | +| explained_variance | 0.18 | +| learning_rate | 4.41e-05 | +| loss | -0.0268 | +| n_updates | 64224 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.00028 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1416 | +| iterations | 12103 | +| time_elapsed | 17503 | +| total_timesteps | 24786944 | +| train/ | | +| approx_kl | 0.01416479 | +| clip_fraction | 0.332 | +| clip_range | 0.0688 | +| entropy_loss | -5.73 | +| explained_variance | 0.518 | +| learning_rate | 4.41e-05 | +| loss | -0.0256 | +| n_updates | 64228 | +| policy_gradient_loss | -0.0144 | +| value_loss | 0.000186 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1416 | +| iterations | 12104 | +| time_elapsed | 17504 | +| total_timesteps | 24788992 | +| train/ | | +| approx_kl | 0.015488627 | +| clip_fraction | 0.383 | +| clip_range | 0.0688 | +| entropy_loss | -6.24 | +| explained_variance | 0.246 | +| learning_rate | 4.41e-05 | +| loss | -0.0321 | +| n_updates | 64232 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000225 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1416 | +| iterations | 12105 | +| time_elapsed | 17506 | +| total_timesteps | 24791040 | +| train/ | | +| approx_kl | 0.018823856 | +| clip_fraction | 0.339 | +| clip_range | 0.0688 | +| entropy_loss | -6.67 | +| explained_variance | -0.204 | +| learning_rate | 4.41e-05 | +| loss | -0.029 | +| n_updates | 64236 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000173 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1416 | +| iterations | 12106 | +| time_elapsed | 17507 | +| total_timesteps | 24793088 | +| train/ | | +| approx_kl | 0.014368122 | +| clip_fraction | 0.353 | +| clip_range | 0.0688 | +| entropy_loss | -6.53 | +| explained_variance | 0.258 | +| learning_rate | 4.41e-05 | +| loss | -0.0305 | +| n_updates | 64240 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000193 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1416 | +| iterations | 12107 | +| time_elapsed | 17509 | +| total_timesteps | 24795136 | +| train/ | | +| approx_kl | 0.012621115 | +| clip_fraction | 0.327 | +| clip_range | 0.0688 | +| entropy_loss | -6.2 | +| explained_variance | 0.299 | +| learning_rate | 4.41e-05 | +| loss | -0.0264 | +| n_updates | 64244 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000385 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1416 | +| iterations | 12108 | +| time_elapsed | 17510 | +| total_timesteps | 24797184 | +| train/ | | +| approx_kl | 0.014488148 | +| clip_fraction | 0.359 | +| clip_range | 0.0688 | +| entropy_loss | -5.97 | +| explained_variance | 0.219 | +| learning_rate | 4.41e-05 | +| loss | -0.0309 | +| n_updates | 64248 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000221 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1416 | +| iterations | 12109 | +| time_elapsed | 17512 | +| total_timesteps | 24799232 | +| train/ | | +| approx_kl | 0.014997547 | +| clip_fraction | 0.354 | +| clip_range | 0.0688 | +| entropy_loss | -6.3 | +| explained_variance | 0.551 | +| learning_rate | 4.41e-05 | +| loss | -0.0336 | +| n_updates | 64252 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000141 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1416 | +| iterations | 12110 | +| time_elapsed | 17513 | +| total_timesteps | 24801280 | +| train/ | | +| approx_kl | 0.015265685 | +| clip_fraction | 0.346 | +| clip_range | 0.0688 | +| entropy_loss | -5.8 | +| explained_variance | 0.62 | +| learning_rate | 4.41e-05 | +| loss | -0.0343 | +| n_updates | 64256 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000126 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1416 | +| iterations | 12111 | +| time_elapsed | 17515 | +| total_timesteps | 24803328 | +| train/ | | +| approx_kl | 0.010509269 | +| clip_fraction | 0.305 | +| clip_range | 0.0688 | +| entropy_loss | -6.06 | +| explained_variance | 0.435 | +| learning_rate | 4.41e-05 | +| loss | -0.0286 | +| n_updates | 64260 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000237 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1416 | +| iterations | 12112 | +| time_elapsed | 17516 | +| total_timesteps | 24805376 | +| train/ | | +| approx_kl | 0.015321145 | +| clip_fraction | 0.354 | +| clip_range | 0.0688 | +| entropy_loss | -6.27 | +| explained_variance | 0.479 | +| learning_rate | 4.41e-05 | +| loss | -0.0309 | +| n_updates | 64264 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000135 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1416 | +| iterations | 12113 | +| time_elapsed | 17518 | +| total_timesteps | 24807424 | +| train/ | | +| approx_kl | 0.014221858 | +| clip_fraction | 0.352 | +| clip_range | 0.0688 | +| entropy_loss | -6.51 | +| explained_variance | 0.21 | +| learning_rate | 4.41e-05 | +| loss | -0.0347 | +| n_updates | 64268 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000121 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1416 | +| iterations | 12114 | +| time_elapsed | 17519 | +| total_timesteps | 24809472 | +| train/ | | +| approx_kl | 0.014560532 | +| clip_fraction | 0.309 | +| clip_range | 0.0688 | +| entropy_loss | -6.58 | +| explained_variance | 0.135 | +| learning_rate | 4.41e-05 | +| loss | -0.0272 | +| n_updates | 64272 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000205 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1416 | +| iterations | 12115 | +| time_elapsed | 17521 | +| total_timesteps | 24811520 | +| train/ | | +| approx_kl | 0.013270552 | +| clip_fraction | 0.334 | +| clip_range | 0.0688 | +| entropy_loss | -6.4 | +| explained_variance | 0.439 | +| learning_rate | 4.41e-05 | +| loss | -0.0309 | +| n_updates | 64276 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000178 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1416 | +| iterations | 12116 | +| time_elapsed | 17522 | +| total_timesteps | 24813568 | +| train/ | | +| approx_kl | 0.011455772 | +| clip_fraction | 0.312 | +| clip_range | 0.0688 | +| entropy_loss | -5.95 | +| explained_variance | 0.524 | +| learning_rate | 4.41e-05 | +| loss | -0.0219 | +| n_updates | 64280 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000286 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1416 | +| iterations | 12117 | +| time_elapsed | 17524 | +| total_timesteps | 24815616 | +| train/ | | +| approx_kl | 0.01080405 | +| clip_fraction | 0.308 | +| clip_range | 0.0688 | +| entropy_loss | -5.37 | +| explained_variance | 0.414 | +| learning_rate | 4.41e-05 | +| loss | -0.0303 | +| n_updates | 64284 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000317 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1416 | +| iterations | 12118 | +| time_elapsed | 17525 | +| total_timesteps | 24817664 | +| train/ | | +| approx_kl | 0.014449012 | +| clip_fraction | 0.373 | +| clip_range | 0.0688 | +| entropy_loss | -6.22 | +| explained_variance | 0.281 | +| learning_rate | 4.41e-05 | +| loss | -0.0385 | +| n_updates | 64288 | +| policy_gradient_loss | -0.0236 | +| value_loss | 0.000119 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1416 | +| iterations | 12119 | +| time_elapsed | 17527 | +| total_timesteps | 24819712 | +| train/ | | +| approx_kl | 0.0152697 | +| clip_fraction | 0.321 | +| clip_range | 0.0688 | +| entropy_loss | -6.1 | +| explained_variance | 0.361 | +| learning_rate | 4.41e-05 | +| loss | -0.0235 | +| n_updates | 64292 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.00025 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1416 | +| iterations | 12120 | +| time_elapsed | 17528 | +| total_timesteps | 24821760 | +| train/ | | +| approx_kl | 0.013579044 | +| clip_fraction | 0.324 | +| clip_range | 0.0688 | +| entropy_loss | -6.6 | +| explained_variance | -0.114 | +| learning_rate | 4.41e-05 | +| loss | -0.0276 | +| n_updates | 64296 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000304 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1416 | +| iterations | 12121 | +| time_elapsed | 17530 | +| total_timesteps | 24823808 | +| train/ | | +| approx_kl | 0.014481427 | +| clip_fraction | 0.307 | +| clip_range | 0.0688 | +| entropy_loss | -6.47 | +| explained_variance | 0.28 | +| learning_rate | 4.41e-05 | +| loss | -0.0326 | +| n_updates | 64300 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.00033 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1416 | +| iterations | 12122 | +| time_elapsed | 17531 | +| total_timesteps | 24825856 | +| train/ | | +| approx_kl | 0.015231919 | +| clip_fraction | 0.359 | +| clip_range | 0.0688 | +| entropy_loss | -6.54 | +| explained_variance | -0.738 | +| learning_rate | 4.41e-05 | +| loss | -0.0329 | +| n_updates | 64304 | +| policy_gradient_loss | -0.0238 | +| value_loss | 9.84e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1416 | +| iterations | 12123 | +| time_elapsed | 17533 | +| total_timesteps | 24827904 | +| train/ | | +| approx_kl | 0.01513252 | +| clip_fraction | 0.355 | +| clip_range | 0.0688 | +| entropy_loss | -6.78 | +| explained_variance | -0.0508 | +| learning_rate | 4.41e-05 | +| loss | -0.03 | +| n_updates | 64308 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.0002 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1416 | +| iterations | 12124 | +| time_elapsed | 17534 | +| total_timesteps | 24829952 | +| train/ | | +| approx_kl | 0.01668618 | +| clip_fraction | 0.377 | +| clip_range | 0.0688 | +| entropy_loss | -6.53 | +| explained_variance | 0.372 | +| learning_rate | 4.41e-05 | +| loss | -0.0349 | +| n_updates | 64312 | +| policy_gradient_loss | -0.0227 | +| value_loss | 9.28e-05 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1416 | +| iterations | 12125 | +| time_elapsed | 17536 | +| total_timesteps | 24832000 | +| train/ | | +| approx_kl | 0.01347498 | +| clip_fraction | 0.368 | +| clip_range | 0.0688 | +| entropy_loss | -6.92 | +| explained_variance | -0.363 | +| learning_rate | 4.41e-05 | +| loss | -0.0368 | +| n_updates | 64316 | +| policy_gradient_loss | -0.0233 | +| value_loss | 8.43e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1416 | +| iterations | 12126 | +| time_elapsed | 17537 | +| total_timesteps | 24834048 | +| train/ | | +| approx_kl | 0.014249937 | +| clip_fraction | 0.302 | +| clip_range | 0.0688 | +| entropy_loss | -6.14 | +| explained_variance | 0.465 | +| learning_rate | 4.41e-05 | +| loss | -0.0301 | +| n_updates | 64320 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000253 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1416 | +| iterations | 12127 | +| time_elapsed | 17539 | +| total_timesteps | 24836096 | +| train/ | | +| approx_kl | 0.014773257 | +| clip_fraction | 0.337 | +| clip_range | 0.0688 | +| entropy_loss | -4.78 | +| explained_variance | 0.843 | +| learning_rate | 4.41e-05 | +| loss | -0.0244 | +| n_updates | 64324 | +| policy_gradient_loss | -0.0175 | +| value_loss | 7.56e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1416 | +| iterations | 12128 | +| time_elapsed | 17540 | +| total_timesteps | 24838144 | +| train/ | | +| approx_kl | 0.015612064 | +| clip_fraction | 0.347 | +| clip_range | 0.0688 | +| entropy_loss | -6.05 | +| explained_variance | 0.572 | +| learning_rate | 4.41e-05 | +| loss | -0.028 | +| n_updates | 64328 | +| policy_gradient_loss | -0.0189 | +| value_loss | 6.77e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1416 | +| iterations | 12129 | +| time_elapsed | 17542 | +| total_timesteps | 24840192 | +| train/ | | +| approx_kl | 0.0150380945 | +| clip_fraction | 0.344 | +| clip_range | 0.0688 | +| entropy_loss | -6.22 | +| explained_variance | 0.491 | +| learning_rate | 4.41e-05 | +| loss | -0.0283 | +| n_updates | 64332 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000179 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1416 | +| iterations | 12130 | +| time_elapsed | 17543 | +| total_timesteps | 24842240 | +| train/ | | +| approx_kl | 0.015803179 | +| clip_fraction | 0.351 | +| clip_range | 0.0688 | +| entropy_loss | -6.3 | +| explained_variance | 0.488 | +| learning_rate | 4.41e-05 | +| loss | -0.0299 | +| n_updates | 64336 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000113 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1416 | +| iterations | 12131 | +| time_elapsed | 17545 | +| total_timesteps | 24844288 | +| train/ | | +| approx_kl | 0.013562907 | +| clip_fraction | 0.356 | +| clip_range | 0.0688 | +| entropy_loss | -6.5 | +| explained_variance | 0.13 | +| learning_rate | 4.41e-05 | +| loss | -0.0288 | +| n_updates | 64340 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000146 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1416 | +| iterations | 12132 | +| time_elapsed | 17546 | +| total_timesteps | 24846336 | +| train/ | | +| approx_kl | 0.013323043 | +| clip_fraction | 0.335 | +| clip_range | 0.0688 | +| entropy_loss | -6.34 | +| explained_variance | 0.556 | +| learning_rate | 4.41e-05 | +| loss | -0.0331 | +| n_updates | 64344 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000123 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1416 | +| iterations | 12133 | +| time_elapsed | 17548 | +| total_timesteps | 24848384 | +| train/ | | +| approx_kl | 0.015600677 | +| clip_fraction | 0.341 | +| clip_range | 0.0688 | +| entropy_loss | -6.12 | +| explained_variance | 0.709 | +| learning_rate | 4.41e-05 | +| loss | -0.028 | +| n_updates | 64348 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000106 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1416 | +| iterations | 12134 | +| time_elapsed | 17549 | +| total_timesteps | 24850432 | +| train/ | | +| approx_kl | 0.012380985 | +| clip_fraction | 0.323 | +| clip_range | 0.0688 | +| entropy_loss | -6.32 | +| explained_variance | 0.172 | +| learning_rate | 4.41e-05 | +| loss | -0.0303 | +| n_updates | 64352 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000109 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1416 | +| iterations | 12135 | +| time_elapsed | 17551 | +| total_timesteps | 24852480 | +| train/ | | +| approx_kl | 0.012060294 | +| clip_fraction | 0.283 | +| clip_range | 0.0688 | +| entropy_loss | -5.94 | +| explained_variance | 0.621 | +| learning_rate | 4.41e-05 | +| loss | -0.0242 | +| n_updates | 64356 | +| policy_gradient_loss | -0.0146 | +| value_loss | 0.000181 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1416 | +| iterations | 12136 | +| time_elapsed | 17552 | +| total_timesteps | 24854528 | +| train/ | | +| approx_kl | 0.014806809 | +| clip_fraction | 0.348 | +| clip_range | 0.0688 | +| entropy_loss | -6.08 | +| explained_variance | 0.32 | +| learning_rate | 4.41e-05 | +| loss | -0.0307 | +| n_updates | 64360 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000117 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1415 | +| iterations | 12137 | +| time_elapsed | 17554 | +| total_timesteps | 24856576 | +| train/ | | +| approx_kl | 0.014339156 | +| clip_fraction | 0.344 | +| clip_range | 0.0688 | +| entropy_loss | -6.83 | +| explained_variance | 0.182 | +| learning_rate | 4.41e-05 | +| loss | -0.0341 | +| n_updates | 64364 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000304 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1415 | +| iterations | 12138 | +| time_elapsed | 17555 | +| total_timesteps | 24858624 | +| train/ | | +| approx_kl | 0.012851333 | +| clip_fraction | 0.331 | +| clip_range | 0.0688 | +| entropy_loss | -6.33 | +| explained_variance | 0.345 | +| learning_rate | 4.41e-05 | +| loss | -0.0311 | +| n_updates | 64368 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.00011 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1415 | +| iterations | 12139 | +| time_elapsed | 17557 | +| total_timesteps | 24860672 | +| train/ | | +| approx_kl | 0.015636548 | +| clip_fraction | 0.365 | +| clip_range | 0.0688 | +| entropy_loss | -6.44 | +| explained_variance | 0.311 | +| learning_rate | 4.41e-05 | +| loss | -0.0363 | +| n_updates | 64372 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000125 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1415 | +| iterations | 12140 | +| time_elapsed | 17558 | +| total_timesteps | 24862720 | +| train/ | | +| approx_kl | 0.01409496 | +| clip_fraction | 0.341 | +| clip_range | 0.0688 | +| entropy_loss | -6.13 | +| explained_variance | 0.496 | +| learning_rate | 4.41e-05 | +| loss | -0.0308 | +| n_updates | 64376 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.00011 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1415 | +| iterations | 12141 | +| time_elapsed | 17560 | +| total_timesteps | 24864768 | +| train/ | | +| approx_kl | 0.013990335 | +| clip_fraction | 0.335 | +| clip_range | 0.0688 | +| entropy_loss | -6.18 | +| explained_variance | 0.737 | +| learning_rate | 4.41e-05 | +| loss | -0.0354 | +| n_updates | 64380 | +| policy_gradient_loss | -0.0197 | +| value_loss | 7.66e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1415 | +| iterations | 12142 | +| time_elapsed | 17561 | +| total_timesteps | 24866816 | +| train/ | | +| approx_kl | 0.011974169 | +| clip_fraction | 0.326 | +| clip_range | 0.0688 | +| entropy_loss | -6.3 | +| explained_variance | 0.352 | +| learning_rate | 4.41e-05 | +| loss | -0.0289 | +| n_updates | 64384 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000136 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1415 | +| iterations | 12143 | +| time_elapsed | 17563 | +| total_timesteps | 24868864 | +| train/ | | +| approx_kl | 0.014701514 | +| clip_fraction | 0.313 | +| clip_range | 0.0688 | +| entropy_loss | -5.88 | +| explained_variance | 0.596 | +| learning_rate | 4.41e-05 | +| loss | -0.0208 | +| n_updates | 64388 | +| policy_gradient_loss | -0.0139 | +| value_loss | 0.000218 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1415 | +| iterations | 12144 | +| time_elapsed | 17564 | +| total_timesteps | 24870912 | +| train/ | | +| approx_kl | 0.013108715 | +| clip_fraction | 0.326 | +| clip_range | 0.0688 | +| entropy_loss | -5.7 | +| explained_variance | 0.674 | +| learning_rate | 4.41e-05 | +| loss | -0.0331 | +| n_updates | 64392 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.00011 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1415 | +| iterations | 12145 | +| time_elapsed | 17566 | +| total_timesteps | 24872960 | +| train/ | | +| approx_kl | 0.011283722 | +| clip_fraction | 0.328 | +| clip_range | 0.0688 | +| entropy_loss | -6.59 | +| explained_variance | 0.317 | +| learning_rate | 4.41e-05 | +| loss | -0.0265 | +| n_updates | 64396 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000135 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1415 | +| iterations | 12146 | +| time_elapsed | 17567 | +| total_timesteps | 24875008 | +| train/ | | +| approx_kl | 0.012261089 | +| clip_fraction | 0.316 | +| clip_range | 0.0688 | +| entropy_loss | -6.34 | +| explained_variance | 0.248 | +| learning_rate | 4.41e-05 | +| loss | -0.0234 | +| n_updates | 64400 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.000283 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1415 | +| iterations | 12147 | +| time_elapsed | 17569 | +| total_timesteps | 24877056 | +| train/ | | +| approx_kl | 0.012853671 | +| clip_fraction | 0.32 | +| clip_range | 0.0688 | +| entropy_loss | -5.88 | +| explained_variance | 0.316 | +| learning_rate | 4.41e-05 | +| loss | -0.0276 | +| n_updates | 64404 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000409 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1415 | +| iterations | 12148 | +| time_elapsed | 17570 | +| total_timesteps | 24879104 | +| train/ | | +| approx_kl | 0.012732208 | +| clip_fraction | 0.344 | +| clip_range | 0.0688 | +| entropy_loss | -6.35 | +| explained_variance | 0.341 | +| learning_rate | 4.41e-05 | +| loss | -0.0348 | +| n_updates | 64408 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.00013 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1415 | +| iterations | 12149 | +| time_elapsed | 17572 | +| total_timesteps | 24881152 | +| train/ | | +| approx_kl | 0.012360526 | +| clip_fraction | 0.337 | +| clip_range | 0.0688 | +| entropy_loss | -6.25 | +| explained_variance | 0.248 | +| learning_rate | 4.41e-05 | +| loss | -0.0308 | +| n_updates | 64412 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000283 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1415 | +| iterations | 12150 | +| time_elapsed | 17573 | +| total_timesteps | 24883200 | +| train/ | | +| approx_kl | 0.012240782 | +| clip_fraction | 0.35 | +| clip_range | 0.0688 | +| entropy_loss | -6.69 | +| explained_variance | -0.0428 | +| learning_rate | 4.41e-05 | +| loss | -0.0338 | +| n_updates | 64416 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.00014 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1415 | +| iterations | 12151 | +| time_elapsed | 17575 | +| total_timesteps | 24885248 | +| train/ | | +| approx_kl | 0.01237626 | +| clip_fraction | 0.359 | +| clip_range | 0.0688 | +| entropy_loss | -6.62 | +| explained_variance | 0.31 | +| learning_rate | 4.41e-05 | +| loss | -0.0291 | +| n_updates | 64420 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000242 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1415 | +| iterations | 12152 | +| time_elapsed | 17576 | +| total_timesteps | 24887296 | +| train/ | | +| approx_kl | 0.012776473 | +| clip_fraction | 0.345 | +| clip_range | 0.0688 | +| entropy_loss | -6.43 | +| explained_variance | 0.232 | +| learning_rate | 4.41e-05 | +| loss | -0.0183 | +| n_updates | 64424 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000288 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1415 | +| iterations | 12153 | +| time_elapsed | 17578 | +| total_timesteps | 24889344 | +| train/ | | +| approx_kl | 0.014049651 | +| clip_fraction | 0.373 | +| clip_range | 0.0688 | +| entropy_loss | -6.7 | +| explained_variance | -0.101 | +| learning_rate | 4.41e-05 | +| loss | -0.0301 | +| n_updates | 64428 | +| policy_gradient_loss | -0.0224 | +| value_loss | 0.000122 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1415 | +| iterations | 12154 | +| time_elapsed | 17579 | +| total_timesteps | 24891392 | +| train/ | | +| approx_kl | 0.014051389 | +| clip_fraction | 0.334 | +| clip_range | 0.0688 | +| entropy_loss | -5.95 | +| explained_variance | 0.521 | +| learning_rate | 4.41e-05 | +| loss | -0.0292 | +| n_updates | 64432 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000221 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1415 | +| iterations | 12155 | +| time_elapsed | 17581 | +| total_timesteps | 24893440 | +| train/ | | +| approx_kl | 0.0130033195 | +| clip_fraction | 0.353 | +| clip_range | 0.0688 | +| entropy_loss | -5.35 | +| explained_variance | 0.729 | +| learning_rate | 4.41e-05 | +| loss | -0.035 | +| n_updates | 64436 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000108 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1415 | +| iterations | 12156 | +| time_elapsed | 17582 | +| total_timesteps | 24895488 | +| train/ | | +| approx_kl | 0.012778411 | +| clip_fraction | 0.355 | +| clip_range | 0.0688 | +| entropy_loss | -6.12 | +| explained_variance | 0.555 | +| learning_rate | 4.41e-05 | +| loss | -0.0273 | +| n_updates | 64440 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000147 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1415 | +| iterations | 12157 | +| time_elapsed | 17584 | +| total_timesteps | 24897536 | +| train/ | | +| approx_kl | 0.011305086 | +| clip_fraction | 0.316 | +| clip_range | 0.0688 | +| entropy_loss | -6.26 | +| explained_variance | 0.342 | +| learning_rate | 4.41e-05 | +| loss | -0.0247 | +| n_updates | 64444 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000224 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1415 | +| iterations | 12158 | +| time_elapsed | 17585 | +| total_timesteps | 24899584 | +| train/ | | +| approx_kl | 0.0118551785 | +| clip_fraction | 0.313 | +| clip_range | 0.0688 | +| entropy_loss | -5.86 | +| explained_variance | 0.397 | +| learning_rate | 4.41e-05 | +| loss | -0.0218 | +| n_updates | 64448 | +| policy_gradient_loss | -0.0144 | +| value_loss | 0.000354 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1415 | +| iterations | 12159 | +| time_elapsed | 17586 | +| total_timesteps | 24901632 | +| train/ | | +| approx_kl | 0.015122406 | +| clip_fraction | 0.359 | +| clip_range | 0.0688 | +| entropy_loss | -6.32 | +| explained_variance | 0.323 | +| learning_rate | 4.41e-05 | +| loss | -0.0308 | +| n_updates | 64452 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000194 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1415 | +| iterations | 12160 | +| time_elapsed | 17588 | +| total_timesteps | 24903680 | +| train/ | | +| approx_kl | 0.013499904 | +| clip_fraction | 0.323 | +| clip_range | 0.0688 | +| entropy_loss | -6.55 | +| explained_variance | 0.0741 | +| learning_rate | 4.41e-05 | +| loss | -0.0278 | +| n_updates | 64456 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000468 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1415 | +| iterations | 12161 | +| time_elapsed | 17589 | +| total_timesteps | 24905728 | +| train/ | | +| approx_kl | 0.018598542 | +| clip_fraction | 0.365 | +| clip_range | 0.0688 | +| entropy_loss | -5.56 | +| explained_variance | 0.618 | +| learning_rate | 4.41e-05 | +| loss | -0.0326 | +| n_updates | 64460 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000169 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1415 | +| iterations | 12162 | +| time_elapsed | 17591 | +| total_timesteps | 24907776 | +| train/ | | +| approx_kl | 0.0150593575 | +| clip_fraction | 0.369 | +| clip_range | 0.0688 | +| entropy_loss | -6.08 | +| explained_variance | 0.0152 | +| learning_rate | 4.41e-05 | +| loss | -0.0308 | +| n_updates | 64464 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000144 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1415 | +| iterations | 12163 | +| time_elapsed | 17593 | +| total_timesteps | 24909824 | +| train/ | | +| approx_kl | 0.015669223 | +| clip_fraction | 0.364 | +| clip_range | 0.0688 | +| entropy_loss | -6.2 | +| explained_variance | 0.0151 | +| learning_rate | 4.41e-05 | +| loss | -0.0269 | +| n_updates | 64468 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000175 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1415 | +| iterations | 12164 | +| time_elapsed | 17594 | +| total_timesteps | 24911872 | +| train/ | | +| approx_kl | 0.018773181 | +| clip_fraction | 0.388 | +| clip_range | 0.0688 | +| entropy_loss | -6.47 | +| explained_variance | 0.479 | +| learning_rate | 4.41e-05 | +| loss | -0.0367 | +| n_updates | 64472 | +| policy_gradient_loss | -0.0221 | +| value_loss | 7.86e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1415 | +| iterations | 12165 | +| time_elapsed | 17595 | +| total_timesteps | 24913920 | +| train/ | | +| approx_kl | 0.016067166 | +| clip_fraction | 0.348 | +| clip_range | 0.0688 | +| entropy_loss | -6.12 | +| explained_variance | 0.538 | +| learning_rate | 4.41e-05 | +| loss | -0.0289 | +| n_updates | 64476 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000123 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1415 | +| iterations | 12166 | +| time_elapsed | 17597 | +| total_timesteps | 24915968 | +| train/ | | +| approx_kl | 0.010009921 | +| clip_fraction | 0.294 | +| clip_range | 0.0688 | +| entropy_loss | -6.11 | +| explained_variance | 0.522 | +| learning_rate | 4.41e-05 | +| loss | -0.0271 | +| n_updates | 64480 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000213 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1415 | +| iterations | 12167 | +| time_elapsed | 17598 | +| total_timesteps | 24918016 | +| train/ | | +| approx_kl | 0.014063671 | +| clip_fraction | 0.382 | +| clip_range | 0.0688 | +| entropy_loss | -6.09 | +| explained_variance | 0.715 | +| learning_rate | 4.41e-05 | +| loss | -0.0409 | +| n_updates | 64484 | +| policy_gradient_loss | -0.0227 | +| value_loss | 8.28e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1415 | +| iterations | 12168 | +| time_elapsed | 17600 | +| total_timesteps | 24920064 | +| train/ | | +| approx_kl | 0.014558587 | +| clip_fraction | 0.323 | +| clip_range | 0.0688 | +| entropy_loss | -6.03 | +| explained_variance | 0.377 | +| learning_rate | 4.41e-05 | +| loss | -0.0236 | +| n_updates | 64488 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000403 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1415 | +| iterations | 12169 | +| time_elapsed | 17601 | +| total_timesteps | 24922112 | +| train/ | | +| approx_kl | 0.016157877 | +| clip_fraction | 0.372 | +| clip_range | 0.0688 | +| entropy_loss | -5.86 | +| explained_variance | 0.373 | +| learning_rate | 4.41e-05 | +| loss | -0.0347 | +| n_updates | 64492 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000183 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1415 | +| iterations | 12170 | +| time_elapsed | 17603 | +| total_timesteps | 24924160 | +| train/ | | +| approx_kl | 0.014402492 | +| clip_fraction | 0.352 | +| clip_range | 0.0688 | +| entropy_loss | -6.52 | +| explained_variance | 0.294 | +| learning_rate | 4.41e-05 | +| loss | -0.0325 | +| n_updates | 64496 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000155 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1415 | +| iterations | 12171 | +| time_elapsed | 17604 | +| total_timesteps | 24926208 | +| train/ | | +| approx_kl | 0.017176382 | +| clip_fraction | 0.372 | +| clip_range | 0.0688 | +| entropy_loss | -6.41 | +| explained_variance | 0.393 | +| learning_rate | 4.41e-05 | +| loss | -0.0356 | +| n_updates | 64500 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000187 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1415 | +| iterations | 12172 | +| time_elapsed | 17606 | +| total_timesteps | 24928256 | +| train/ | | +| approx_kl | 0.013288584 | +| clip_fraction | 0.35 | +| clip_range | 0.0688 | +| entropy_loss | -6.22 | +| explained_variance | 0.328 | +| learning_rate | 4.41e-05 | +| loss | -0.031 | +| n_updates | 64504 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000283 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1415 | +| iterations | 12173 | +| time_elapsed | 17607 | +| total_timesteps | 24930304 | +| train/ | | +| approx_kl | 0.01431038 | +| clip_fraction | 0.355 | +| clip_range | 0.0688 | +| entropy_loss | -6.06 | +| explained_variance | 0.445 | +| learning_rate | 4.41e-05 | +| loss | -0.037 | +| n_updates | 64508 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000157 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1415 | +| iterations | 12174 | +| time_elapsed | 17609 | +| total_timesteps | 24932352 | +| train/ | | +| approx_kl | 0.011841192 | +| clip_fraction | 0.343 | +| clip_range | 0.0688 | +| entropy_loss | -6.77 | +| explained_variance | 0.214 | +| learning_rate | 4.41e-05 | +| loss | -0.0337 | +| n_updates | 64512 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000171 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1415 | +| iterations | 12175 | +| time_elapsed | 17610 | +| total_timesteps | 24934400 | +| train/ | | +| approx_kl | 0.014993716 | +| clip_fraction | 0.301 | +| clip_range | 0.0688 | +| entropy_loss | -6.47 | +| explained_variance | 0.167 | +| learning_rate | 4.41e-05 | +| loss | -0.0256 | +| n_updates | 64516 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000225 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1415 | +| iterations | 12176 | +| time_elapsed | 17612 | +| total_timesteps | 24936448 | +| train/ | | +| approx_kl | 0.018032491 | +| clip_fraction | 0.365 | +| clip_range | 0.0688 | +| entropy_loss | -6.2 | +| explained_variance | 0.317 | +| learning_rate | 4.41e-05 | +| loss | -0.0306 | +| n_updates | 64520 | +| policy_gradient_loss | -0.0211 | +| value_loss | 9.35e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1415 | +| iterations | 12177 | +| time_elapsed | 17613 | +| total_timesteps | 24938496 | +| train/ | | +| approx_kl | 0.014233078 | +| clip_fraction | 0.358 | +| clip_range | 0.0688 | +| entropy_loss | -6.69 | +| explained_variance | -0.221 | +| learning_rate | 4.41e-05 | +| loss | -0.0354 | +| n_updates | 64524 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000133 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1415 | +| iterations | 12178 | +| time_elapsed | 17615 | +| total_timesteps | 24940544 | +| train/ | | +| approx_kl | 0.014266466 | +| clip_fraction | 0.339 | +| clip_range | 0.0688 | +| entropy_loss | -6.25 | +| explained_variance | 0.606 | +| learning_rate | 4.41e-05 | +| loss | -0.0273 | +| n_updates | 64528 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000108 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1415 | +| iterations | 12179 | +| time_elapsed | 17616 | +| total_timesteps | 24942592 | +| train/ | | +| approx_kl | 0.011823792 | +| clip_fraction | 0.304 | +| clip_range | 0.0688 | +| entropy_loss | -5.53 | +| explained_variance | 0.529 | +| learning_rate | 4.41e-05 | +| loss | -0.0253 | +| n_updates | 64532 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000203 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1415 | +| iterations | 12180 | +| time_elapsed | 17618 | +| total_timesteps | 24944640 | +| train/ | | +| approx_kl | 0.0147758275 | +| clip_fraction | 0.334 | +| clip_range | 0.0688 | +| entropy_loss | -5.92 | +| explained_variance | 0.325 | +| learning_rate | 4.41e-05 | +| loss | -0.032 | +| n_updates | 64536 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000127 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1415 | +| iterations | 12181 | +| time_elapsed | 17619 | +| total_timesteps | 24946688 | +| train/ | | +| approx_kl | 0.011642832 | +| clip_fraction | 0.344 | +| clip_range | 0.0688 | +| entropy_loss | -6.25 | +| explained_variance | 0.459 | +| learning_rate | 4.41e-05 | +| loss | -0.0293 | +| n_updates | 64540 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000115 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1415 | +| iterations | 12182 | +| time_elapsed | 17621 | +| total_timesteps | 24948736 | +| train/ | | +| approx_kl | 0.0135099515 | +| clip_fraction | 0.335 | +| clip_range | 0.0688 | +| entropy_loss | -6.6 | +| explained_variance | 0.147 | +| learning_rate | 4.41e-05 | +| loss | -0.0277 | +| n_updates | 64544 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000219 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1415 | +| iterations | 12183 | +| time_elapsed | 17622 | +| total_timesteps | 24950784 | +| train/ | | +| approx_kl | 0.010940304 | +| clip_fraction | 0.299 | +| clip_range | 0.0688 | +| entropy_loss | -5.85 | +| explained_variance | 0.286 | +| learning_rate | 4.41e-05 | +| loss | -0.0215 | +| n_updates | 64548 | +| policy_gradient_loss | -0.0148 | +| value_loss | 0.000522 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1415 | +| iterations | 12184 | +| time_elapsed | 17624 | +| total_timesteps | 24952832 | +| train/ | | +| approx_kl | 0.01193784 | +| clip_fraction | 0.339 | +| clip_range | 0.0688 | +| entropy_loss | -6.07 | +| explained_variance | 0.415 | +| learning_rate | 4.41e-05 | +| loss | -0.0281 | +| n_updates | 64552 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000184 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1415 | +| iterations | 12185 | +| time_elapsed | 17625 | +| total_timesteps | 24954880 | +| train/ | | +| approx_kl | 0.012694667 | +| clip_fraction | 0.338 | +| clip_range | 0.0688 | +| entropy_loss | -6.11 | +| explained_variance | 0.161 | +| learning_rate | 4.41e-05 | +| loss | -0.0316 | +| n_updates | 64556 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000211 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1415 | +| iterations | 12186 | +| time_elapsed | 17627 | +| total_timesteps | 24956928 | +| train/ | | +| approx_kl | 0.01596899 | +| clip_fraction | 0.35 | +| clip_range | 0.0688 | +| entropy_loss | -5.99 | +| explained_variance | 0.659 | +| learning_rate | 4.41e-05 | +| loss | -0.0342 | +| n_updates | 64560 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000112 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1415 | +| iterations | 12187 | +| time_elapsed | 17628 | +| total_timesteps | 24958976 | +| train/ | | +| approx_kl | 0.014475459 | +| clip_fraction | 0.371 | +| clip_range | 0.0688 | +| entropy_loss | -6.44 | +| explained_variance | -0.0296 | +| learning_rate | 4.41e-05 | +| loss | -0.0293 | +| n_updates | 64564 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000209 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1415 | +| iterations | 12188 | +| time_elapsed | 17630 | +| total_timesteps | 24961024 | +| train/ | | +| approx_kl | 0.011907367 | +| clip_fraction | 0.33 | +| clip_range | 0.0688 | +| entropy_loss | -6.19 | +| explained_variance | 0.241 | +| learning_rate | 4.41e-05 | +| loss | -0.0322 | +| n_updates | 64568 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000372 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1415 | +| iterations | 12189 | +| time_elapsed | 17631 | +| total_timesteps | 24963072 | +| train/ | | +| approx_kl | 0.0129496325 | +| clip_fraction | 0.355 | +| clip_range | 0.0688 | +| entropy_loss | -6.1 | +| explained_variance | 0.449 | +| learning_rate | 4.41e-05 | +| loss | -0.0332 | +| n_updates | 64572 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000145 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1415 | +| iterations | 12190 | +| time_elapsed | 17633 | +| total_timesteps | 24965120 | +| train/ | | +| approx_kl | 0.01406565 | +| clip_fraction | 0.357 | +| clip_range | 0.0688 | +| entropy_loss | -6.35 | +| explained_variance | 0.083 | +| learning_rate | 4.41e-05 | +| loss | -0.0339 | +| n_updates | 64576 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000118 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1415 | +| iterations | 12191 | +| time_elapsed | 17634 | +| total_timesteps | 24967168 | +| train/ | | +| approx_kl | 0.017427737 | +| clip_fraction | 0.368 | +| clip_range | 0.0688 | +| entropy_loss | -5.94 | +| explained_variance | 0.439 | +| learning_rate | 4.41e-05 | +| loss | -0.027 | +| n_updates | 64580 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000179 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1415 | +| iterations | 12192 | +| time_elapsed | 17636 | +| total_timesteps | 24969216 | +| train/ | | +| approx_kl | 0.014619056 | +| clip_fraction | 0.334 | +| clip_range | 0.0688 | +| entropy_loss | -6.06 | +| explained_variance | 0.419 | +| learning_rate | 4.41e-05 | +| loss | -0.0317 | +| n_updates | 64584 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000169 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1415 | +| iterations | 12193 | +| time_elapsed | 17637 | +| total_timesteps | 24971264 | +| train/ | | +| approx_kl | 0.015668346 | +| clip_fraction | 0.37 | +| clip_range | 0.0688 | +| entropy_loss | -5.8 | +| explained_variance | 0.712 | +| learning_rate | 4.41e-05 | +| loss | -0.0369 | +| n_updates | 64588 | +| policy_gradient_loss | -0.0222 | +| value_loss | 6.37e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1415 | +| iterations | 12194 | +| time_elapsed | 17639 | +| total_timesteps | 24973312 | +| train/ | | +| approx_kl | 0.013198858 | +| clip_fraction | 0.358 | +| clip_range | 0.0688 | +| entropy_loss | -6.54 | +| explained_variance | -0.0347 | +| learning_rate | 4.41e-05 | +| loss | -0.0294 | +| n_updates | 64592 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000262 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1415 | +| iterations | 12195 | +| time_elapsed | 17640 | +| total_timesteps | 24975360 | +| train/ | | +| approx_kl | 0.014246105 | +| clip_fraction | 0.341 | +| clip_range | 0.0688 | +| entropy_loss | -6.24 | +| explained_variance | 0.498 | +| learning_rate | 4.41e-05 | +| loss | -0.0286 | +| n_updates | 64596 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000142 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1415 | +| iterations | 12196 | +| time_elapsed | 17642 | +| total_timesteps | 24977408 | +| train/ | | +| approx_kl | 0.013920825 | +| clip_fraction | 0.347 | +| clip_range | 0.0688 | +| entropy_loss | -6.11 | +| explained_variance | 0.39 | +| learning_rate | 4.41e-05 | +| loss | -0.0214 | +| n_updates | 64600 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000237 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1415 | +| iterations | 12197 | +| time_elapsed | 17643 | +| total_timesteps | 24979456 | +| train/ | | +| approx_kl | 0.016228989 | +| clip_fraction | 0.33 | +| clip_range | 0.0688 | +| entropy_loss | -5.66 | +| explained_variance | 0.47 | +| learning_rate | 4.41e-05 | +| loss | -0.0298 | +| n_updates | 64604 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000229 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1415 | +| iterations | 12198 | +| time_elapsed | 17644 | +| total_timesteps | 24981504 | +| train/ | | +| approx_kl | 0.011997795 | +| clip_fraction | 0.34 | +| clip_range | 0.0688 | +| entropy_loss | -6.68 | +| explained_variance | -0.0685 | +| learning_rate | 4.41e-05 | +| loss | -0.0385 | +| n_updates | 64608 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000119 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1415 | +| iterations | 12199 | +| time_elapsed | 17646 | +| total_timesteps | 24983552 | +| train/ | | +| approx_kl | 0.013964355 | +| clip_fraction | 0.353 | +| clip_range | 0.0688 | +| entropy_loss | -6.36 | +| explained_variance | 0.302 | +| learning_rate | 4.41e-05 | +| loss | -0.0306 | +| n_updates | 64612 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000324 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1415 | +| iterations | 12200 | +| time_elapsed | 17647 | +| total_timesteps | 24985600 | +| train/ | | +| approx_kl | 0.015615603 | +| clip_fraction | 0.35 | +| clip_range | 0.0688 | +| entropy_loss | -6.35 | +| explained_variance | 0.189 | +| learning_rate | 4.41e-05 | +| loss | -0.0277 | +| n_updates | 64616 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000187 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1415 | +| iterations | 12201 | +| time_elapsed | 17649 | +| total_timesteps | 24987648 | +| train/ | | +| approx_kl | 0.015092226 | +| clip_fraction | 0.357 | +| clip_range | 0.0688 | +| entropy_loss | -6.43 | +| explained_variance | 0.314 | +| learning_rate | 4.41e-05 | +| loss | -0.0337 | +| n_updates | 64620 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1415 | +| iterations | 12202 | +| time_elapsed | 17650 | +| total_timesteps | 24989696 | +| train/ | | +| approx_kl | 0.014557033 | +| clip_fraction | 0.341 | +| clip_range | 0.0688 | +| entropy_loss | -5.91 | +| explained_variance | 0.712 | +| learning_rate | 4.41e-05 | +| loss | -0.0252 | +| n_updates | 64624 | +| policy_gradient_loss | -0.0192 | +| value_loss | 8.88e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1415 | +| iterations | 12203 | +| time_elapsed | 17652 | +| total_timesteps | 24991744 | +| train/ | | +| approx_kl | 0.015378979 | +| clip_fraction | 0.319 | +| clip_range | 0.0688 | +| entropy_loss | -6.12 | +| explained_variance | 0.292 | +| learning_rate | 4.41e-05 | +| loss | -0.0279 | +| n_updates | 64628 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000194 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1415 | +| iterations | 12204 | +| time_elapsed | 17653 | +| total_timesteps | 24993792 | +| train/ | | +| approx_kl | 0.014729339 | +| clip_fraction | 0.332 | +| clip_range | 0.0688 | +| entropy_loss | -5.55 | +| explained_variance | 0.483 | +| learning_rate | 4.41e-05 | +| loss | -0.0251 | +| n_updates | 64632 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000299 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1415 | +| iterations | 12205 | +| time_elapsed | 17655 | +| total_timesteps | 24995840 | +| train/ | | +| approx_kl | 0.014947145 | +| clip_fraction | 0.366 | +| clip_range | 0.0688 | +| entropy_loss | -6.1 | +| explained_variance | 0.479 | +| learning_rate | 4.41e-05 | +| loss | -0.0303 | +| n_updates | 64636 | +| policy_gradient_loss | -0.0209 | +| value_loss | 9.96e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1415 | +| iterations | 12206 | +| time_elapsed | 17656 | +| total_timesteps | 24997888 | +| train/ | | +| approx_kl | 0.014690486 | +| clip_fraction | 0.375 | +| clip_range | 0.0688 | +| entropy_loss | -6.58 | +| explained_variance | -0.0667 | +| learning_rate | 4.41e-05 | +| loss | -0.0356 | +| n_updates | 64640 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000119 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1415 | +| iterations | 12207 | +| time_elapsed | 17658 | +| total_timesteps | 24999936 | +| train/ | | +| approx_kl | 0.014635238 | +| clip_fraction | 0.329 | +| clip_range | 0.0688 | +| entropy_loss | -6.08 | +| explained_variance | 0.396 | +| learning_rate | 4.41e-05 | +| loss | -0.0337 | +| n_updates | 64644 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000122 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1415 | +| iterations | 12208 | +| time_elapsed | 17659 | +| total_timesteps | 25001984 | +| train/ | | +| approx_kl | 0.010854724 | +| clip_fraction | 0.321 | +| clip_range | 0.0688 | +| entropy_loss | -6.39 | +| explained_variance | 0.171 | +| learning_rate | 4.41e-05 | +| loss | -0.0231 | +| n_updates | 64648 | +| policy_gradient_loss | -0.0136 | +| value_loss | 0.000399 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1415 | +| iterations | 12209 | +| time_elapsed | 17661 | +| total_timesteps | 25004032 | +| train/ | | +| approx_kl | 0.012712818 | +| clip_fraction | 0.344 | +| clip_range | 0.0687 | +| entropy_loss | -6.18 | +| explained_variance | 0.559 | +| learning_rate | 4.41e-05 | +| loss | -0.0246 | +| n_updates | 64652 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000128 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1415 | +| iterations | 12210 | +| time_elapsed | 17662 | +| total_timesteps | 25006080 | +| train/ | | +| approx_kl | 0.013348303 | +| clip_fraction | 0.333 | +| clip_range | 0.0687 | +| entropy_loss | -6.07 | +| explained_variance | 0.569 | +| learning_rate | 4.41e-05 | +| loss | -0.0355 | +| n_updates | 64656 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000177 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1415 | +| iterations | 12211 | +| time_elapsed | 17664 | +| total_timesteps | 25008128 | +| train/ | | +| approx_kl | 0.014657486 | +| clip_fraction | 0.34 | +| clip_range | 0.0687 | +| entropy_loss | -6.07 | +| explained_variance | 0.354 | +| learning_rate | 4.41e-05 | +| loss | -0.0304 | +| n_updates | 64660 | +| policy_gradient_loss | -0.0192 | +| value_loss | 8.85e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1415 | +| iterations | 12212 | +| time_elapsed | 17665 | +| total_timesteps | 25010176 | +| train/ | | +| approx_kl | 0.012182596 | +| clip_fraction | 0.33 | +| clip_range | 0.0687 | +| entropy_loss | -6.31 | +| explained_variance | 0.418 | +| learning_rate | 4.41e-05 | +| loss | -0.0321 | +| n_updates | 64664 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000202 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1415 | +| iterations | 12213 | +| time_elapsed | 17667 | +| total_timesteps | 25012224 | +| train/ | | +| approx_kl | 0.0113588385 | +| clip_fraction | 0.337 | +| clip_range | 0.0687 | +| entropy_loss | -6.28 | +| explained_variance | 0.256 | +| learning_rate | 4.41e-05 | +| loss | -0.0363 | +| n_updates | 64668 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000173 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1415 | +| iterations | 12214 | +| time_elapsed | 17668 | +| total_timesteps | 25014272 | +| train/ | | +| approx_kl | 0.0127472365 | +| clip_fraction | 0.331 | +| clip_range | 0.0687 | +| entropy_loss | -6.14 | +| explained_variance | 0.701 | +| learning_rate | 4.41e-05 | +| loss | -0.0282 | +| n_updates | 64672 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000111 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1415 | +| iterations | 12215 | +| time_elapsed | 17670 | +| total_timesteps | 25016320 | +| train/ | | +| approx_kl | 0.010487126 | +| clip_fraction | 0.324 | +| clip_range | 0.0687 | +| entropy_loss | -6.56 | +| explained_variance | 0.123 | +| learning_rate | 4.41e-05 | +| loss | -0.0272 | +| n_updates | 64676 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000161 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1415 | +| iterations | 12216 | +| time_elapsed | 17671 | +| total_timesteps | 25018368 | +| train/ | | +| approx_kl | 0.011303648 | +| clip_fraction | 0.319 | +| clip_range | 0.0687 | +| entropy_loss | -6.86 | +| explained_variance | 0.267 | +| learning_rate | 4.41e-05 | +| loss | -0.0196 | +| n_updates | 64680 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000168 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1415 | +| iterations | 12217 | +| time_elapsed | 17673 | +| total_timesteps | 25020416 | +| train/ | | +| approx_kl | 0.0105733145 | +| clip_fraction | 0.326 | +| clip_range | 0.0687 | +| entropy_loss | -6.28 | +| explained_variance | 0.466 | +| learning_rate | 4.41e-05 | +| loss | -0.0236 | +| n_updates | 64684 | +| policy_gradient_loss | -0.0147 | +| value_loss | 0.000201 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1415 | +| iterations | 12218 | +| time_elapsed | 17675 | +| total_timesteps | 25022464 | +| train/ | | +| approx_kl | 0.016268581 | +| clip_fraction | 0.294 | +| clip_range | 0.0687 | +| entropy_loss | -5.66 | +| explained_variance | 0.624 | +| learning_rate | 4.41e-05 | +| loss | -0.0303 | +| n_updates | 64688 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000131 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1415 | +| iterations | 12219 | +| time_elapsed | 17676 | +| total_timesteps | 25024512 | +| train/ | | +| approx_kl | 0.013288274 | +| clip_fraction | 0.326 | +| clip_range | 0.0687 | +| entropy_loss | -6.37 | +| explained_variance | 0.353 | +| learning_rate | 4.41e-05 | +| loss | -0.022 | +| n_updates | 64692 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.00011 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1415 | +| iterations | 12220 | +| time_elapsed | 17678 | +| total_timesteps | 25026560 | +| train/ | | +| approx_kl | 0.015093475 | +| clip_fraction | 0.374 | +| clip_range | 0.0687 | +| entropy_loss | -6.4 | +| explained_variance | 0.392 | +| learning_rate | 4.41e-05 | +| loss | -0.0318 | +| n_updates | 64696 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000109 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1415 | +| iterations | 12221 | +| time_elapsed | 17679 | +| total_timesteps | 25028608 | +| train/ | | +| approx_kl | 0.015082128 | +| clip_fraction | 0.329 | +| clip_range | 0.0687 | +| entropy_loss | -6.57 | +| explained_variance | 0.287 | +| learning_rate | 4.41e-05 | +| loss | -0.029 | +| n_updates | 64700 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.00019 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1415 | +| iterations | 12222 | +| time_elapsed | 17681 | +| total_timesteps | 25030656 | +| train/ | | +| approx_kl | 0.017962202 | +| clip_fraction | 0.357 | +| clip_range | 0.0687 | +| entropy_loss | -5.77 | +| explained_variance | 0.592 | +| learning_rate | 4.41e-05 | +| loss | -0.0303 | +| n_updates | 64704 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000146 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1415 | +| iterations | 12223 | +| time_elapsed | 17682 | +| total_timesteps | 25032704 | +| train/ | | +| approx_kl | 0.014753473 | +| clip_fraction | 0.348 | +| clip_range | 0.0687 | +| entropy_loss | -6.14 | +| explained_variance | 0.413 | +| learning_rate | 4.41e-05 | +| loss | -0.034 | +| n_updates | 64708 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000137 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1415 | +| iterations | 12224 | +| time_elapsed | 17684 | +| total_timesteps | 25034752 | +| train/ | | +| approx_kl | 0.014399866 | +| clip_fraction | 0.328 | +| clip_range | 0.0687 | +| entropy_loss | -6.6 | +| explained_variance | 0.408 | +| learning_rate | 4.41e-05 | +| loss | -0.025 | +| n_updates | 64712 | +| policy_gradient_loss | -0.0178 | +| value_loss | 9.32e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1415 | +| iterations | 12225 | +| time_elapsed | 17685 | +| total_timesteps | 25036800 | +| train/ | | +| approx_kl | 0.013057164 | +| clip_fraction | 0.333 | +| clip_range | 0.0687 | +| entropy_loss | -6.56 | +| explained_variance | 0.457 | +| learning_rate | 4.41e-05 | +| loss | -0.0372 | +| n_updates | 64716 | +| policy_gradient_loss | -0.0191 | +| value_loss | 9.69e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1415 | +| iterations | 12226 | +| time_elapsed | 17687 | +| total_timesteps | 25038848 | +| train/ | | +| approx_kl | 0.011028474 | +| clip_fraction | 0.32 | +| clip_range | 0.0687 | +| entropy_loss | -6.26 | +| explained_variance | 0.509 | +| learning_rate | 4.41e-05 | +| loss | -0.0276 | +| n_updates | 64720 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000163 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1415 | +| iterations | 12227 | +| time_elapsed | 17688 | +| total_timesteps | 25040896 | +| train/ | | +| approx_kl | 0.012249429 | +| clip_fraction | 0.324 | +| clip_range | 0.0687 | +| entropy_loss | -6.85 | +| explained_variance | -0.0319 | +| learning_rate | 4.41e-05 | +| loss | -0.0305 | +| n_updates | 64724 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000153 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1415 | +| iterations | 12228 | +| time_elapsed | 17690 | +| total_timesteps | 25042944 | +| train/ | | +| approx_kl | 0.012775622 | +| clip_fraction | 0.323 | +| clip_range | 0.0687 | +| entropy_loss | -6 | +| explained_variance | 0.439 | +| learning_rate | 4.41e-05 | +| loss | -0.0253 | +| n_updates | 64728 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000189 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1415 | +| iterations | 12229 | +| time_elapsed | 17691 | +| total_timesteps | 25044992 | +| train/ | | +| approx_kl | 0.015055204 | +| clip_fraction | 0.36 | +| clip_range | 0.0687 | +| entropy_loss | -6.28 | +| explained_variance | 0.253 | +| learning_rate | 4.41e-05 | +| loss | -0.0333 | +| n_updates | 64732 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000178 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1415 | +| iterations | 12230 | +| time_elapsed | 17693 | +| total_timesteps | 25047040 | +| train/ | | +| approx_kl | 0.013420874 | +| clip_fraction | 0.36 | +| clip_range | 0.0687 | +| entropy_loss | -5.74 | +| explained_variance | 0.612 | +| learning_rate | 4.41e-05 | +| loss | -0.0268 | +| n_updates | 64736 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000172 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1415 | +| iterations | 12231 | +| time_elapsed | 17694 | +| total_timesteps | 25049088 | +| train/ | | +| approx_kl | 0.013408523 | +| clip_fraction | 0.361 | +| clip_range | 0.0687 | +| entropy_loss | -5.75 | +| explained_variance | 0.605 | +| learning_rate | 4.41e-05 | +| loss | -0.0321 | +| n_updates | 64740 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000106 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1415 | +| iterations | 12232 | +| time_elapsed | 17696 | +| total_timesteps | 25051136 | +| train/ | | +| approx_kl | 0.01680591 | +| clip_fraction | 0.334 | +| clip_range | 0.0687 | +| entropy_loss | -6.77 | +| explained_variance | 0.115 | +| learning_rate | 4.41e-05 | +| loss | -0.0315 | +| n_updates | 64744 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000192 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1415 | +| iterations | 12233 | +| time_elapsed | 17697 | +| total_timesteps | 25053184 | +| train/ | | +| approx_kl | 0.014369612 | +| clip_fraction | 0.367 | +| clip_range | 0.0687 | +| entropy_loss | -6.58 | +| explained_variance | 0.358 | +| learning_rate | 4.41e-05 | +| loss | -0.0336 | +| n_updates | 64748 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000132 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1415 | +| iterations | 12234 | +| time_elapsed | 17699 | +| total_timesteps | 25055232 | +| train/ | | +| approx_kl | 0.0135688605 | +| clip_fraction | 0.354 | +| clip_range | 0.0687 | +| entropy_loss | -6.43 | +| explained_variance | 0.356 | +| learning_rate | 4.4e-05 | +| loss | -0.0242 | +| n_updates | 64752 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000296 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1415 | +| iterations | 12235 | +| time_elapsed | 17700 | +| total_timesteps | 25057280 | +| train/ | | +| approx_kl | 0.013812756 | +| clip_fraction | 0.333 | +| clip_range | 0.0687 | +| entropy_loss | -6.03 | +| explained_variance | 0.341 | +| learning_rate | 4.4e-05 | +| loss | -0.0262 | +| n_updates | 64756 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000273 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1415 | +| iterations | 12236 | +| time_elapsed | 17702 | +| total_timesteps | 25059328 | +| train/ | | +| approx_kl | 0.012818976 | +| clip_fraction | 0.351 | +| clip_range | 0.0687 | +| entropy_loss | -6.59 | +| explained_variance | 0.274 | +| learning_rate | 4.4e-05 | +| loss | -0.0327 | +| n_updates | 64760 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000165 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1415 | +| iterations | 12237 | +| time_elapsed | 17703 | +| total_timesteps | 25061376 | +| train/ | | +| approx_kl | 0.012439075 | +| clip_fraction | 0.317 | +| clip_range | 0.0687 | +| entropy_loss | -6.35 | +| explained_variance | 0.326 | +| learning_rate | 4.4e-05 | +| loss | -0.0258 | +| n_updates | 64764 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000344 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1415 | +| iterations | 12238 | +| time_elapsed | 17705 | +| total_timesteps | 25063424 | +| train/ | | +| approx_kl | 0.014194515 | +| clip_fraction | 0.357 | +| clip_range | 0.0687 | +| entropy_loss | -5.55 | +| explained_variance | 0.506 | +| learning_rate | 4.4e-05 | +| loss | -0.0286 | +| n_updates | 64768 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000231 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1415 | +| iterations | 12239 | +| time_elapsed | 17706 | +| total_timesteps | 25065472 | +| train/ | | +| approx_kl | 0.012594589 | +| clip_fraction | 0.331 | +| clip_range | 0.0687 | +| entropy_loss | -5.13 | +| explained_variance | 0.626 | +| learning_rate | 4.4e-05 | +| loss | -0.0268 | +| n_updates | 64772 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000179 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1415 | +| iterations | 12240 | +| time_elapsed | 17708 | +| total_timesteps | 25067520 | +| train/ | | +| approx_kl | 0.01351018 | +| clip_fraction | 0.32 | +| clip_range | 0.0687 | +| entropy_loss | -5.82 | +| explained_variance | 0.508 | +| learning_rate | 4.4e-05 | +| loss | -0.0229 | +| n_updates | 64776 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000174 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1415 | +| iterations | 12241 | +| time_elapsed | 17709 | +| total_timesteps | 25069568 | +| train/ | | +| approx_kl | 0.013190709 | +| clip_fraction | 0.353 | +| clip_range | 0.0687 | +| entropy_loss | -6.61 | +| explained_variance | 0.302 | +| learning_rate | 4.4e-05 | +| loss | -0.036 | +| n_updates | 64780 | +| policy_gradient_loss | -0.0214 | +| value_loss | 8.1e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1415 | +| iterations | 12242 | +| time_elapsed | 17711 | +| total_timesteps | 25071616 | +| train/ | | +| approx_kl | 0.011144216 | +| clip_fraction | 0.34 | +| clip_range | 0.0687 | +| entropy_loss | -7.02 | +| explained_variance | -0.0116 | +| learning_rate | 4.4e-05 | +| loss | -0.0334 | +| n_updates | 64784 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000249 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1415 | +| iterations | 12243 | +| time_elapsed | 17712 | +| total_timesteps | 25073664 | +| train/ | | +| approx_kl | 0.013550974 | +| clip_fraction | 0.315 | +| clip_range | 0.0687 | +| entropy_loss | -6.67 | +| explained_variance | 0.429 | +| learning_rate | 4.4e-05 | +| loss | -0.0221 | +| n_updates | 64788 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000186 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1415 | +| iterations | 12244 | +| time_elapsed | 17714 | +| total_timesteps | 25075712 | +| train/ | | +| approx_kl | 0.016228102 | +| clip_fraction | 0.344 | +| clip_range | 0.0687 | +| entropy_loss | -6.3 | +| explained_variance | -0.171 | +| learning_rate | 4.4e-05 | +| loss | -0.0353 | +| n_updates | 64792 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000283 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1415 | +| iterations | 12245 | +| time_elapsed | 17715 | +| total_timesteps | 25077760 | +| train/ | | +| approx_kl | 0.014717737 | +| clip_fraction | 0.337 | +| clip_range | 0.0687 | +| entropy_loss | -6.16 | +| explained_variance | 0.318 | +| learning_rate | 4.4e-05 | +| loss | -0.0289 | +| n_updates | 64796 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000278 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1415 | +| iterations | 12246 | +| time_elapsed | 17717 | +| total_timesteps | 25079808 | +| train/ | | +| approx_kl | 0.014876131 | +| clip_fraction | 0.365 | +| clip_range | 0.0687 | +| entropy_loss | -5.87 | +| explained_variance | 0.437 | +| learning_rate | 4.4e-05 | +| loss | -0.0368 | +| n_updates | 64800 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000133 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1415 | +| iterations | 12247 | +| time_elapsed | 17718 | +| total_timesteps | 25081856 | +| train/ | | +| approx_kl | 0.01469076 | +| clip_fraction | 0.37 | +| clip_range | 0.0687 | +| entropy_loss | -5.91 | +| explained_variance | 0.702 | +| learning_rate | 4.4e-05 | +| loss | -0.0324 | +| n_updates | 64804 | +| policy_gradient_loss | -0.0204 | +| value_loss | 9.49e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1415 | +| iterations | 12248 | +| time_elapsed | 17720 | +| total_timesteps | 25083904 | +| train/ | | +| approx_kl | 0.016375717 | +| clip_fraction | 0.382 | +| clip_range | 0.0687 | +| entropy_loss | -6.15 | +| explained_variance | 0.0651 | +| learning_rate | 4.4e-05 | +| loss | -0.0346 | +| n_updates | 64808 | +| policy_gradient_loss | -0.0222 | +| value_loss | 0.000142 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1415 | +| iterations | 12249 | +| time_elapsed | 17721 | +| total_timesteps | 25085952 | +| train/ | | +| approx_kl | 0.015113531 | +| clip_fraction | 0.372 | +| clip_range | 0.0687 | +| entropy_loss | -6.21 | +| explained_variance | 0.604 | +| learning_rate | 4.4e-05 | +| loss | -0.0312 | +| n_updates | 64812 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.0001 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1415 | +| iterations | 12250 | +| time_elapsed | 17723 | +| total_timesteps | 25088000 | +| train/ | | +| approx_kl | 0.011703923 | +| clip_fraction | 0.33 | +| clip_range | 0.0687 | +| entropy_loss | -6.03 | +| explained_variance | 0.503 | +| learning_rate | 4.4e-05 | +| loss | -0.0225 | +| n_updates | 64816 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000229 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1415 | +| iterations | 12251 | +| time_elapsed | 17724 | +| total_timesteps | 25090048 | +| train/ | | +| approx_kl | 0.015051359 | +| clip_fraction | 0.337 | +| clip_range | 0.0687 | +| entropy_loss | -6.57 | +| explained_variance | -0.0859 | +| learning_rate | 4.4e-05 | +| loss | -0.0299 | +| n_updates | 64820 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000113 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1415 | +| iterations | 12252 | +| time_elapsed | 17726 | +| total_timesteps | 25092096 | +| train/ | | +| approx_kl | 0.015407562 | +| clip_fraction | 0.353 | +| clip_range | 0.0687 | +| entropy_loss | -6.38 | +| explained_variance | 0.553 | +| learning_rate | 4.4e-05 | +| loss | -0.029 | +| n_updates | 64824 | +| policy_gradient_loss | -0.0203 | +| value_loss | 9.91e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1415 | +| iterations | 12253 | +| time_elapsed | 17727 | +| total_timesteps | 25094144 | +| train/ | | +| approx_kl | 0.017221132 | +| clip_fraction | 0.355 | +| clip_range | 0.0687 | +| entropy_loss | -6.61 | +| explained_variance | 0.422 | +| learning_rate | 4.4e-05 | +| loss | -0.0349 | +| n_updates | 64828 | +| policy_gradient_loss | -0.0219 | +| value_loss | 0.000107 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1415 | +| iterations | 12254 | +| time_elapsed | 17729 | +| total_timesteps | 25096192 | +| train/ | | +| approx_kl | 0.012439026 | +| clip_fraction | 0.338 | +| clip_range | 0.0687 | +| entropy_loss | -6.43 | +| explained_variance | 0.362 | +| learning_rate | 4.4e-05 | +| loss | -0.023 | +| n_updates | 64832 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000188 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1415 | +| iterations | 12255 | +| time_elapsed | 17730 | +| total_timesteps | 25098240 | +| train/ | | +| approx_kl | 0.011990033 | +| clip_fraction | 0.332 | +| clip_range | 0.0687 | +| entropy_loss | -6.09 | +| explained_variance | 0.694 | +| learning_rate | 4.4e-05 | +| loss | -0.033 | +| n_updates | 64836 | +| policy_gradient_loss | -0.0192 | +| value_loss | 9.13e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1415 | +| iterations | 12256 | +| time_elapsed | 17732 | +| total_timesteps | 25100288 | +| train/ | | +| approx_kl | 0.01074573 | +| clip_fraction | 0.315 | +| clip_range | 0.0687 | +| entropy_loss | -6.28 | +| explained_variance | 0.344 | +| learning_rate | 4.4e-05 | +| loss | -0.0253 | +| n_updates | 64840 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000143 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1415 | +| iterations | 12257 | +| time_elapsed | 17733 | +| total_timesteps | 25102336 | +| train/ | | +| approx_kl | 0.011696495 | +| clip_fraction | 0.332 | +| clip_range | 0.0687 | +| entropy_loss | -5.74 | +| explained_variance | 0.732 | +| learning_rate | 4.4e-05 | +| loss | -0.0303 | +| n_updates | 64844 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000129 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1415 | +| iterations | 12258 | +| time_elapsed | 17735 | +| total_timesteps | 25104384 | +| train/ | | +| approx_kl | 0.016694259 | +| clip_fraction | 0.34 | +| clip_range | 0.0687 | +| entropy_loss | -6.11 | +| explained_variance | 0.123 | +| learning_rate | 4.4e-05 | +| loss | -0.0281 | +| n_updates | 64848 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000244 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1415 | +| iterations | 12259 | +| time_elapsed | 17736 | +| total_timesteps | 25106432 | +| train/ | | +| approx_kl | 0.014257203 | +| clip_fraction | 0.361 | +| clip_range | 0.0687 | +| entropy_loss | -6.51 | +| explained_variance | 0.31 | +| learning_rate | 4.4e-05 | +| loss | -0.0335 | +| n_updates | 64852 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000182 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1415 | +| iterations | 12260 | +| time_elapsed | 17738 | +| total_timesteps | 25108480 | +| train/ | | +| approx_kl | 0.017924167 | +| clip_fraction | 0.384 | +| clip_range | 0.0687 | +| entropy_loss | -6.55 | +| explained_variance | 0.286 | +| learning_rate | 4.4e-05 | +| loss | -0.0311 | +| n_updates | 64856 | +| policy_gradient_loss | -0.0222 | +| value_loss | 0.000119 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1415 | +| iterations | 12261 | +| time_elapsed | 17739 | +| total_timesteps | 25110528 | +| train/ | | +| approx_kl | 0.015164921 | +| clip_fraction | 0.355 | +| clip_range | 0.0687 | +| entropy_loss | -6.32 | +| explained_variance | 0.398 | +| learning_rate | 4.4e-05 | +| loss | -0.0304 | +| n_updates | 64860 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000217 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1415 | +| iterations | 12262 | +| time_elapsed | 17741 | +| total_timesteps | 25112576 | +| train/ | | +| approx_kl | 0.0143546425 | +| clip_fraction | 0.341 | +| clip_range | 0.0687 | +| entropy_loss | -5.98 | +| explained_variance | 0.42 | +| learning_rate | 4.4e-05 | +| loss | -0.0235 | +| n_updates | 64864 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000264 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1415 | +| iterations | 12263 | +| time_elapsed | 17742 | +| total_timesteps | 25114624 | +| train/ | | +| approx_kl | 0.011915266 | +| clip_fraction | 0.344 | +| clip_range | 0.0687 | +| entropy_loss | -6.61 | +| explained_variance | 0.378 | +| learning_rate | 4.4e-05 | +| loss | -0.0262 | +| n_updates | 64868 | +| policy_gradient_loss | -0.0193 | +| value_loss | 8.75e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1415 | +| iterations | 12264 | +| time_elapsed | 17744 | +| total_timesteps | 25116672 | +| train/ | | +| approx_kl | 0.014211452 | +| clip_fraction | 0.357 | +| clip_range | 0.0687 | +| entropy_loss | -6.48 | +| explained_variance | 0.0443 | +| learning_rate | 4.4e-05 | +| loss | -0.0314 | +| n_updates | 64872 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000177 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1415 | +| iterations | 12265 | +| time_elapsed | 17745 | +| total_timesteps | 25118720 | +| train/ | | +| approx_kl | 0.010810845 | +| clip_fraction | 0.344 | +| clip_range | 0.0687 | +| entropy_loss | -6.38 | +| explained_variance | 0.511 | +| learning_rate | 4.4e-05 | +| loss | -0.0333 | +| n_updates | 64876 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000131 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1415 | +| iterations | 12266 | +| time_elapsed | 17747 | +| total_timesteps | 25120768 | +| train/ | | +| approx_kl | 0.012331974 | +| clip_fraction | 0.305 | +| clip_range | 0.0687 | +| entropy_loss | -6.43 | +| explained_variance | 0.489 | +| learning_rate | 4.4e-05 | +| loss | -0.0274 | +| n_updates | 64880 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000208 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1415 | +| iterations | 12267 | +| time_elapsed | 17748 | +| total_timesteps | 25122816 | +| train/ | | +| approx_kl | 0.012346795 | +| clip_fraction | 0.319 | +| clip_range | 0.0687 | +| entropy_loss | -5.77 | +| explained_variance | 0.444 | +| learning_rate | 4.4e-05 | +| loss | -0.0283 | +| n_updates | 64884 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000256 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1415 | +| iterations | 12268 | +| time_elapsed | 17750 | +| total_timesteps | 25124864 | +| train/ | | +| approx_kl | 0.017000668 | +| clip_fraction | 0.348 | +| clip_range | 0.0687 | +| entropy_loss | -6.37 | +| explained_variance | 0.32 | +| learning_rate | 4.4e-05 | +| loss | -0.0347 | +| n_updates | 64888 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1415 | +| iterations | 12269 | +| time_elapsed | 17751 | +| total_timesteps | 25126912 | +| train/ | | +| approx_kl | 0.011366922 | +| clip_fraction | 0.333 | +| clip_range | 0.0687 | +| entropy_loss | -5.99 | +| explained_variance | 0.447 | +| learning_rate | 4.4e-05 | +| loss | -0.027 | +| n_updates | 64892 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000209 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1415 | +| iterations | 12270 | +| time_elapsed | 17753 | +| total_timesteps | 25128960 | +| train/ | | +| approx_kl | 0.015786683 | +| clip_fraction | 0.363 | +| clip_range | 0.0687 | +| entropy_loss | -5.95 | +| explained_variance | 0.642 | +| learning_rate | 4.4e-05 | +| loss | -0.0323 | +| n_updates | 64896 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000105 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1415 | +| iterations | 12271 | +| time_elapsed | 17754 | +| total_timesteps | 25131008 | +| train/ | | +| approx_kl | 0.01231158 | +| clip_fraction | 0.336 | +| clip_range | 0.0687 | +| entropy_loss | -6.36 | +| explained_variance | 0.288 | +| learning_rate | 4.4e-05 | +| loss | -0.0327 | +| n_updates | 64900 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000217 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1415 | +| iterations | 12272 | +| time_elapsed | 17756 | +| total_timesteps | 25133056 | +| train/ | | +| approx_kl | 0.015961625 | +| clip_fraction | 0.331 | +| clip_range | 0.0687 | +| entropy_loss | -6 | +| explained_variance | 0.495 | +| learning_rate | 4.4e-05 | +| loss | -0.029 | +| n_updates | 64904 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000188 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1415 | +| iterations | 12273 | +| time_elapsed | 17757 | +| total_timesteps | 25135104 | +| train/ | | +| approx_kl | 0.011884342 | +| clip_fraction | 0.33 | +| clip_range | 0.0687 | +| entropy_loss | -6.56 | +| explained_variance | -0.156 | +| learning_rate | 4.4e-05 | +| loss | -0.0267 | +| n_updates | 64908 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000136 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1415 | +| iterations | 12274 | +| time_elapsed | 17758 | +| total_timesteps | 25137152 | +| train/ | | +| approx_kl | 0.012670741 | +| clip_fraction | 0.344 | +| clip_range | 0.0687 | +| entropy_loss | -6.64 | +| explained_variance | -0.125 | +| learning_rate | 4.4e-05 | +| loss | -0.0296 | +| n_updates | 64912 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000146 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1415 | +| iterations | 12275 | +| time_elapsed | 17760 | +| total_timesteps | 25139200 | +| train/ | | +| approx_kl | 0.014711535 | +| clip_fraction | 0.355 | +| clip_range | 0.0687 | +| entropy_loss | -6.67 | +| explained_variance | 0.309 | +| learning_rate | 4.4e-05 | +| loss | -0.0298 | +| n_updates | 64916 | +| policy_gradient_loss | -0.0198 | +| value_loss | 7.33e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1415 | +| iterations | 12276 | +| time_elapsed | 17761 | +| total_timesteps | 25141248 | +| train/ | | +| approx_kl | 0.011759259 | +| clip_fraction | 0.316 | +| clip_range | 0.0687 | +| entropy_loss | -6.37 | +| explained_variance | 0.527 | +| learning_rate | 4.4e-05 | +| loss | -0.0296 | +| n_updates | 64920 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000116 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1415 | +| iterations | 12277 | +| time_elapsed | 17763 | +| total_timesteps | 25143296 | +| train/ | | +| approx_kl | 0.012191275 | +| clip_fraction | 0.314 | +| clip_range | 0.0687 | +| entropy_loss | -6.7 | +| explained_variance | -0.0963 | +| learning_rate | 4.4e-05 | +| loss | -0.0267 | +| n_updates | 64924 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000114 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1415 | +| iterations | 12278 | +| time_elapsed | 17764 | +| total_timesteps | 25145344 | +| train/ | | +| approx_kl | 0.01330393 | +| clip_fraction | 0.346 | +| clip_range | 0.0687 | +| entropy_loss | -5.91 | +| explained_variance | 0.756 | +| learning_rate | 4.4e-05 | +| loss | -0.0306 | +| n_updates | 64928 | +| policy_gradient_loss | -0.0185 | +| value_loss | 7.33e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1415 | +| iterations | 12279 | +| time_elapsed | 17766 | +| total_timesteps | 25147392 | +| train/ | | +| approx_kl | 0.015428739 | +| clip_fraction | 0.302 | +| clip_range | 0.0687 | +| entropy_loss | -5.34 | +| explained_variance | 0.669 | +| learning_rate | 4.4e-05 | +| loss | -0.0232 | +| n_updates | 64932 | +| policy_gradient_loss | -0.0146 | +| value_loss | 0.000159 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1415 | +| iterations | 12280 | +| time_elapsed | 17767 | +| total_timesteps | 25149440 | +| train/ | | +| approx_kl | 0.014802626 | +| clip_fraction | 0.337 | +| clip_range | 0.0687 | +| entropy_loss | -5.79 | +| explained_variance | 0.763 | +| learning_rate | 4.4e-05 | +| loss | -0.0329 | +| n_updates | 64936 | +| policy_gradient_loss | -0.0199 | +| value_loss | 5.81e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1415 | +| iterations | 12281 | +| time_elapsed | 17769 | +| total_timesteps | 25151488 | +| train/ | | +| approx_kl | 0.01167543 | +| clip_fraction | 0.322 | +| clip_range | 0.0687 | +| entropy_loss | -6.34 | +| explained_variance | 0.489 | +| learning_rate | 4.4e-05 | +| loss | -0.0255 | +| n_updates | 64940 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000156 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1415 | +| iterations | 12282 | +| time_elapsed | 17770 | +| total_timesteps | 25153536 | +| train/ | | +| approx_kl | 0.014610894 | +| clip_fraction | 0.323 | +| clip_range | 0.0687 | +| entropy_loss | -6.38 | +| explained_variance | 0.289 | +| learning_rate | 4.4e-05 | +| loss | -0.0244 | +| n_updates | 64944 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.00013 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1415 | +| iterations | 12283 | +| time_elapsed | 17772 | +| total_timesteps | 25155584 | +| train/ | | +| approx_kl | 0.014305658 | +| clip_fraction | 0.342 | +| clip_range | 0.0687 | +| entropy_loss | -6.58 | +| explained_variance | 0.518 | +| learning_rate | 4.4e-05 | +| loss | -0.0305 | +| n_updates | 64948 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000111 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1415 | +| iterations | 12284 | +| time_elapsed | 17773 | +| total_timesteps | 25157632 | +| train/ | | +| approx_kl | 0.013687247 | +| clip_fraction | 0.31 | +| clip_range | 0.0687 | +| entropy_loss | -6.15 | +| explained_variance | 0.384 | +| learning_rate | 4.4e-05 | +| loss | -0.0209 | +| n_updates | 64952 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000248 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1415 | +| iterations | 12285 | +| time_elapsed | 17775 | +| total_timesteps | 25159680 | +| train/ | | +| approx_kl | 0.0134827625 | +| clip_fraction | 0.34 | +| clip_range | 0.0687 | +| entropy_loss | -5.97 | +| explained_variance | 0.573 | +| learning_rate | 4.4e-05 | +| loss | -0.0352 | +| n_updates | 64956 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000162 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1415 | +| iterations | 12286 | +| time_elapsed | 17777 | +| total_timesteps | 25161728 | +| train/ | | +| approx_kl | 0.013747241 | +| clip_fraction | 0.325 | +| clip_range | 0.0687 | +| entropy_loss | -6.33 | +| explained_variance | 0.304 | +| learning_rate | 4.4e-05 | +| loss | -0.0302 | +| n_updates | 64960 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000161 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1415 | +| iterations | 12287 | +| time_elapsed | 17778 | +| total_timesteps | 25163776 | +| train/ | | +| approx_kl | 0.013067961 | +| clip_fraction | 0.344 | +| clip_range | 0.0687 | +| entropy_loss | -6.75 | +| explained_variance | -0.0763 | +| learning_rate | 4.4e-05 | +| loss | -0.0334 | +| n_updates | 64964 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000106 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1415 | +| iterations | 12288 | +| time_elapsed | 17780 | +| total_timesteps | 25165824 | +| train/ | | +| approx_kl | 0.013738766 | +| clip_fraction | 0.325 | +| clip_range | 0.0687 | +| entropy_loss | -6.82 | +| explained_variance | 0.254 | +| learning_rate | 4.4e-05 | +| loss | -0.0294 | +| n_updates | 64968 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000212 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1415 | +| iterations | 12289 | +| time_elapsed | 17781 | +| total_timesteps | 25167872 | +| train/ | | +| approx_kl | 0.015243454 | +| clip_fraction | 0.343 | +| clip_range | 0.0687 | +| entropy_loss | -6.29 | +| explained_variance | 0.303 | +| learning_rate | 4.4e-05 | +| loss | -0.0276 | +| n_updates | 64972 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000292 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1415 | +| iterations | 12290 | +| time_elapsed | 17783 | +| total_timesteps | 25169920 | +| train/ | | +| approx_kl | 0.013541674 | +| clip_fraction | 0.354 | +| clip_range | 0.0687 | +| entropy_loss | -6.51 | +| explained_variance | 0.576 | +| learning_rate | 4.4e-05 | +| loss | -0.0298 | +| n_updates | 64976 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000106 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1415 | +| iterations | 12291 | +| time_elapsed | 17784 | +| total_timesteps | 25171968 | +| train/ | | +| approx_kl | 0.016178887 | +| clip_fraction | 0.337 | +| clip_range | 0.0687 | +| entropy_loss | -6.12 | +| explained_variance | 0.264 | +| learning_rate | 4.4e-05 | +| loss | -0.0311 | +| n_updates | 64980 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000503 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1415 | +| iterations | 12292 | +| time_elapsed | 17786 | +| total_timesteps | 25174016 | +| train/ | | +| approx_kl | 0.014661537 | +| clip_fraction | 0.355 | +| clip_range | 0.0687 | +| entropy_loss | -5.62 | +| explained_variance | 0.505 | +| learning_rate | 4.4e-05 | +| loss | -0.0278 | +| n_updates | 64984 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000217 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1415 | +| iterations | 12293 | +| time_elapsed | 17787 | +| total_timesteps | 25176064 | +| train/ | | +| approx_kl | 0.017375551 | +| clip_fraction | 0.347 | +| clip_range | 0.0687 | +| entropy_loss | -6.59 | +| explained_variance | -0.175 | +| learning_rate | 4.4e-05 | +| loss | -0.0288 | +| n_updates | 64988 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000198 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1415 | +| iterations | 12294 | +| time_elapsed | 17789 | +| total_timesteps | 25178112 | +| train/ | | +| approx_kl | 0.010860427 | +| clip_fraction | 0.33 | +| clip_range | 0.0687 | +| entropy_loss | -6.36 | +| explained_variance | 0.252 | +| learning_rate | 4.4e-05 | +| loss | -0.0225 | +| n_updates | 64992 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000411 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1415 | +| iterations | 12295 | +| time_elapsed | 17790 | +| total_timesteps | 25180160 | +| train/ | | +| approx_kl | 0.010811126 | +| clip_fraction | 0.34 | +| clip_range | 0.0687 | +| entropy_loss | -5.94 | +| explained_variance | 0.342 | +| learning_rate | 4.4e-05 | +| loss | -0.0317 | +| n_updates | 64996 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000118 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1415 | +| iterations | 12296 | +| time_elapsed | 17792 | +| total_timesteps | 25182208 | +| train/ | | +| approx_kl | 0.0131180715 | +| clip_fraction | 0.334 | +| clip_range | 0.0687 | +| entropy_loss | -5.86 | +| explained_variance | 0.551 | +| learning_rate | 4.4e-05 | +| loss | -0.0319 | +| n_updates | 65000 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000159 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1415 | +| iterations | 12297 | +| time_elapsed | 17793 | +| total_timesteps | 25184256 | +| train/ | | +| approx_kl | 0.015696948 | +| clip_fraction | 0.352 | +| clip_range | 0.0687 | +| entropy_loss | -6.5 | +| explained_variance | -0.104 | +| learning_rate | 4.4e-05 | +| loss | -0.0326 | +| n_updates | 65004 | +| policy_gradient_loss | -0.0208 | +| value_loss | 8.11e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1415 | +| iterations | 12298 | +| time_elapsed | 17795 | +| total_timesteps | 25186304 | +| train/ | | +| approx_kl | 0.017931063 | +| clip_fraction | 0.341 | +| clip_range | 0.0687 | +| entropy_loss | -6.85 | +| explained_variance | -0.00647 | +| learning_rate | 4.4e-05 | +| loss | -0.0295 | +| n_updates | 65008 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000159 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1415 | +| iterations | 12299 | +| time_elapsed | 17796 | +| total_timesteps | 25188352 | +| train/ | | +| approx_kl | 0.01264078 | +| clip_fraction | 0.365 | +| clip_range | 0.0687 | +| entropy_loss | -6.51 | +| explained_variance | 0.293 | +| learning_rate | 4.4e-05 | +| loss | -0.0306 | +| n_updates | 65012 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000256 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1415 | +| iterations | 12300 | +| time_elapsed | 17798 | +| total_timesteps | 25190400 | +| train/ | | +| approx_kl | 0.012339372 | +| clip_fraction | 0.344 | +| clip_range | 0.0687 | +| entropy_loss | -5.94 | +| explained_variance | 0.631 | +| learning_rate | 4.4e-05 | +| loss | -0.0323 | +| n_updates | 65016 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000158 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1415 | +| iterations | 12301 | +| time_elapsed | 17799 | +| total_timesteps | 25192448 | +| train/ | | +| approx_kl | 0.016309489 | +| clip_fraction | 0.363 | +| clip_range | 0.0687 | +| entropy_loss | -6.3 | +| explained_variance | -0.113 | +| learning_rate | 4.4e-05 | +| loss | -0.0312 | +| n_updates | 65020 | +| policy_gradient_loss | -0.0222 | +| value_loss | 0.000125 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1415 | +| iterations | 12302 | +| time_elapsed | 17801 | +| total_timesteps | 25194496 | +| train/ | | +| approx_kl | 0.013610295 | +| clip_fraction | 0.321 | +| clip_range | 0.0687 | +| entropy_loss | -6.05 | +| explained_variance | 0.56 | +| learning_rate | 4.4e-05 | +| loss | -0.0244 | +| n_updates | 65024 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000162 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1415 | +| iterations | 12303 | +| time_elapsed | 17802 | +| total_timesteps | 25196544 | +| train/ | | +| approx_kl | 0.014994697 | +| clip_fraction | 0.371 | +| clip_range | 0.0687 | +| entropy_loss | -6.19 | +| explained_variance | 0.0873 | +| learning_rate | 4.4e-05 | +| loss | -0.0237 | +| n_updates | 65028 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000158 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1415 | +| iterations | 12304 | +| time_elapsed | 17804 | +| total_timesteps | 25198592 | +| train/ | | +| approx_kl | 0.015942706 | +| clip_fraction | 0.337 | +| clip_range | 0.0687 | +| entropy_loss | -6.49 | +| explained_variance | 0.408 | +| learning_rate | 4.4e-05 | +| loss | -0.0322 | +| n_updates | 65032 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000205 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1415 | +| iterations | 12305 | +| time_elapsed | 17805 | +| total_timesteps | 25200640 | +| train/ | | +| approx_kl | 0.016390156 | +| clip_fraction | 0.377 | +| clip_range | 0.0687 | +| entropy_loss | -6.11 | +| explained_variance | 0.595 | +| learning_rate | 4.4e-05 | +| loss | -0.0337 | +| n_updates | 65036 | +| policy_gradient_loss | -0.0208 | +| value_loss | 9.34e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1415 | +| iterations | 12306 | +| time_elapsed | 17807 | +| total_timesteps | 25202688 | +| train/ | | +| approx_kl | 0.014332849 | +| clip_fraction | 0.33 | +| clip_range | 0.0687 | +| entropy_loss | -6.22 | +| explained_variance | 0.554 | +| learning_rate | 4.4e-05 | +| loss | -0.0278 | +| n_updates | 65040 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000172 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1415 | +| iterations | 12307 | +| time_elapsed | 17808 | +| total_timesteps | 25204736 | +| train/ | | +| approx_kl | 0.014679244 | +| clip_fraction | 0.374 | +| clip_range | 0.0687 | +| entropy_loss | -6.05 | +| explained_variance | 0.653 | +| learning_rate | 4.4e-05 | +| loss | -0.0328 | +| n_updates | 65044 | +| policy_gradient_loss | -0.0203 | +| value_loss | 8.91e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1415 | +| iterations | 12308 | +| time_elapsed | 17810 | +| total_timesteps | 25206784 | +| train/ | | +| approx_kl | 0.014665812 | +| clip_fraction | 0.368 | +| clip_range | 0.0687 | +| entropy_loss | -6.55 | +| explained_variance | -0.326 | +| learning_rate | 4.4e-05 | +| loss | -0.0392 | +| n_updates | 65048 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000113 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1415 | +| iterations | 12309 | +| time_elapsed | 17811 | +| total_timesteps | 25208832 | +| train/ | | +| approx_kl | 0.013357337 | +| clip_fraction | 0.33 | +| clip_range | 0.0687 | +| entropy_loss | -6.2 | +| explained_variance | 0.41 | +| learning_rate | 4.4e-05 | +| loss | -0.0289 | +| n_updates | 65052 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000208 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1415 | +| iterations | 12310 | +| time_elapsed | 17813 | +| total_timesteps | 25210880 | +| train/ | | +| approx_kl | 0.012666179 | +| clip_fraction | 0.335 | +| clip_range | 0.0687 | +| entropy_loss | -5.94 | +| explained_variance | 0.582 | +| learning_rate | 4.4e-05 | +| loss | -0.0304 | +| n_updates | 65056 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000129 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1415 | +| iterations | 12311 | +| time_elapsed | 17814 | +| total_timesteps | 25212928 | +| train/ | | +| approx_kl | 0.013035146 | +| clip_fraction | 0.354 | +| clip_range | 0.0687 | +| entropy_loss | -6.01 | +| explained_variance | 0.475 | +| learning_rate | 4.4e-05 | +| loss | -0.0277 | +| n_updates | 65060 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000171 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1415 | +| iterations | 12312 | +| time_elapsed | 17816 | +| total_timesteps | 25214976 | +| train/ | | +| approx_kl | 0.015457618 | +| clip_fraction | 0.348 | +| clip_range | 0.0687 | +| entropy_loss | -6.48 | +| explained_variance | 0.34 | +| learning_rate | 4.4e-05 | +| loss | -0.033 | +| n_updates | 65064 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000153 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1415 | +| iterations | 12313 | +| time_elapsed | 17817 | +| total_timesteps | 25217024 | +| train/ | | +| approx_kl | 0.015102353 | +| clip_fraction | 0.349 | +| clip_range | 0.0687 | +| entropy_loss | -6.16 | +| explained_variance | 0.416 | +| learning_rate | 4.4e-05 | +| loss | -0.0271 | +| n_updates | 65068 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000209 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1415 | +| iterations | 12314 | +| time_elapsed | 17819 | +| total_timesteps | 25219072 | +| train/ | | +| approx_kl | 0.015507504 | +| clip_fraction | 0.338 | +| clip_range | 0.0687 | +| entropy_loss | -6.04 | +| explained_variance | 0.545 | +| learning_rate | 4.4e-05 | +| loss | -0.0301 | +| n_updates | 65072 | +| policy_gradient_loss | -0.0188 | +| value_loss | 9.67e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1415 | +| iterations | 12315 | +| time_elapsed | 17820 | +| total_timesteps | 25221120 | +| train/ | | +| approx_kl | 0.01253808 | +| clip_fraction | 0.334 | +| clip_range | 0.0687 | +| entropy_loss | -5.9 | +| explained_variance | 0.577 | +| learning_rate | 4.4e-05 | +| loss | -0.0329 | +| n_updates | 65076 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000175 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1415 | +| iterations | 12316 | +| time_elapsed | 17821 | +| total_timesteps | 25223168 | +| train/ | | +| approx_kl | 0.015941763 | +| clip_fraction | 0.341 | +| clip_range | 0.0687 | +| entropy_loss | -5.91 | +| explained_variance | 0.421 | +| learning_rate | 4.4e-05 | +| loss | -0.0282 | +| n_updates | 65080 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000125 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1415 | +| iterations | 12317 | +| time_elapsed | 17823 | +| total_timesteps | 25225216 | +| train/ | | +| approx_kl | 0.014544694 | +| clip_fraction | 0.356 | +| clip_range | 0.0687 | +| entropy_loss | -6.59 | +| explained_variance | 0.0472 | +| learning_rate | 4.4e-05 | +| loss | -0.031 | +| n_updates | 65084 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000162 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1415 | +| iterations | 12318 | +| time_elapsed | 17824 | +| total_timesteps | 25227264 | +| train/ | | +| approx_kl | 0.0102473255 | +| clip_fraction | 0.323 | +| clip_range | 0.0687 | +| entropy_loss | -6.61 | +| explained_variance | 0.284 | +| learning_rate | 4.4e-05 | +| loss | -0.0341 | +| n_updates | 65088 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.00018 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1415 | +| iterations | 12319 | +| time_elapsed | 17826 | +| total_timesteps | 25229312 | +| train/ | | +| approx_kl | 0.011676981 | +| clip_fraction | 0.312 | +| clip_range | 0.0687 | +| entropy_loss | -6.09 | +| explained_variance | 0.34 | +| learning_rate | 4.4e-05 | +| loss | -0.02 | +| n_updates | 65092 | +| policy_gradient_loss | -0.0146 | +| value_loss | 0.000422 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1415 | +| iterations | 12320 | +| time_elapsed | 17827 | +| total_timesteps | 25231360 | +| train/ | | +| approx_kl | 0.009686112 | +| clip_fraction | 0.327 | +| clip_range | 0.0687 | +| entropy_loss | -6.47 | +| explained_variance | 0.249 | +| learning_rate | 4.4e-05 | +| loss | -0.0249 | +| n_updates | 65096 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000194 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1415 | +| iterations | 12321 | +| time_elapsed | 17829 | +| total_timesteps | 25233408 | +| train/ | | +| approx_kl | 0.010410931 | +| clip_fraction | 0.325 | +| clip_range | 0.0687 | +| entropy_loss | -6.44 | +| explained_variance | 0.246 | +| learning_rate | 4.4e-05 | +| loss | -0.0308 | +| n_updates | 65100 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000182 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1415 | +| iterations | 12322 | +| time_elapsed | 17830 | +| total_timesteps | 25235456 | +| train/ | | +| approx_kl | 0.012260404 | +| clip_fraction | 0.349 | +| clip_range | 0.0687 | +| entropy_loss | -6.27 | +| explained_variance | 0.5 | +| learning_rate | 4.4e-05 | +| loss | -0.0331 | +| n_updates | 65104 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000155 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1415 | +| iterations | 12323 | +| time_elapsed | 17832 | +| total_timesteps | 25237504 | +| train/ | | +| approx_kl | 0.013880005 | +| clip_fraction | 0.343 | +| clip_range | 0.0687 | +| entropy_loss | -6.45 | +| explained_variance | 0.355 | +| learning_rate | 4.4e-05 | +| loss | -0.0263 | +| n_updates | 65108 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000156 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1415 | +| iterations | 12324 | +| time_elapsed | 17833 | +| total_timesteps | 25239552 | +| train/ | | +| approx_kl | 0.011335946 | +| clip_fraction | 0.324 | +| clip_range | 0.0687 | +| entropy_loss | -6.19 | +| explained_variance | 0.546 | +| learning_rate | 4.4e-05 | +| loss | -0.0246 | +| n_updates | 65112 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000194 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1415 | +| iterations | 12325 | +| time_elapsed | 17835 | +| total_timesteps | 25241600 | +| train/ | | +| approx_kl | 0.010577563 | +| clip_fraction | 0.317 | +| clip_range | 0.0687 | +| entropy_loss | -5.64 | +| explained_variance | 0.545 | +| learning_rate | 4.4e-05 | +| loss | -0.0238 | +| n_updates | 65116 | +| policy_gradient_loss | -0.0142 | +| value_loss | 0.000264 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1415 | +| iterations | 12326 | +| time_elapsed | 17837 | +| total_timesteps | 25243648 | +| train/ | | +| approx_kl | 0.0143888295 | +| clip_fraction | 0.331 | +| clip_range | 0.0687 | +| entropy_loss | -5.86 | +| explained_variance | 0.529 | +| learning_rate | 4.4e-05 | +| loss | -0.032 | +| n_updates | 65120 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000147 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1415 | +| iterations | 12327 | +| time_elapsed | 17838 | +| total_timesteps | 25245696 | +| train/ | | +| approx_kl | 0.012138383 | +| clip_fraction | 0.338 | +| clip_range | 0.0687 | +| entropy_loss | -6.78 | +| explained_variance | -0.00723 | +| learning_rate | 4.4e-05 | +| loss | -0.0311 | +| n_updates | 65124 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000219 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1415 | +| iterations | 12328 | +| time_elapsed | 17840 | +| total_timesteps | 25247744 | +| train/ | | +| approx_kl | 0.012165174 | +| clip_fraction | 0.329 | +| clip_range | 0.0687 | +| entropy_loss | -6.56 | +| explained_variance | 0.24 | +| learning_rate | 4.4e-05 | +| loss | -0.0275 | +| n_updates | 65128 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000255 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1415 | +| iterations | 12329 | +| time_elapsed | 17841 | +| total_timesteps | 25249792 | +| train/ | | +| approx_kl | 0.012152213 | +| clip_fraction | 0.338 | +| clip_range | 0.0687 | +| entropy_loss | -6.1 | +| explained_variance | 0.395 | +| learning_rate | 4.4e-05 | +| loss | -0.0243 | +| n_updates | 65132 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000404 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1415 | +| iterations | 12330 | +| time_elapsed | 17843 | +| total_timesteps | 25251840 | +| train/ | | +| approx_kl | 0.013993984 | +| clip_fraction | 0.375 | +| clip_range | 0.0687 | +| entropy_loss | -6.34 | +| explained_variance | 0.387 | +| learning_rate | 4.4e-05 | +| loss | -0.0372 | +| n_updates | 65136 | +| policy_gradient_loss | -0.0221 | +| value_loss | 0.00011 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1415 | +| iterations | 12331 | +| time_elapsed | 17844 | +| total_timesteps | 25253888 | +| train/ | | +| approx_kl | 0.012828659 | +| clip_fraction | 0.35 | +| clip_range | 0.0687 | +| entropy_loss | -6.52 | +| explained_variance | 0.284 | +| learning_rate | 4.4e-05 | +| loss | -0.0422 | +| n_updates | 65140 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000134 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1415 | +| iterations | 12332 | +| time_elapsed | 17846 | +| total_timesteps | 25255936 | +| train/ | | +| approx_kl | 0.01573669 | +| clip_fraction | 0.35 | +| clip_range | 0.0687 | +| entropy_loss | -5.97 | +| explained_variance | 0.607 | +| learning_rate | 4.4e-05 | +| loss | -0.0279 | +| n_updates | 65144 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000151 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1415 | +| iterations | 12333 | +| time_elapsed | 17847 | +| total_timesteps | 25257984 | +| train/ | | +| approx_kl | 0.018995378 | +| clip_fraction | 0.379 | +| clip_range | 0.0687 | +| entropy_loss | -6.11 | +| explained_variance | 0.374 | +| learning_rate | 4.4e-05 | +| loss | -0.0317 | +| n_updates | 65148 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000125 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1415 | +| iterations | 12334 | +| time_elapsed | 17849 | +| total_timesteps | 25260032 | +| train/ | | +| approx_kl | 0.0162253 | +| clip_fraction | 0.388 | +| clip_range | 0.0687 | +| entropy_loss | -6.5 | +| explained_variance | 0.0771 | +| learning_rate | 4.4e-05 | +| loss | -0.0287 | +| n_updates | 65152 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000163 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1415 | +| iterations | 12335 | +| time_elapsed | 17850 | +| total_timesteps | 25262080 | +| train/ | | +| approx_kl | 0.016567841 | +| clip_fraction | 0.344 | +| clip_range | 0.0687 | +| entropy_loss | -6.2 | +| explained_variance | 0.45 | +| learning_rate | 4.4e-05 | +| loss | -0.0299 | +| n_updates | 65156 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000168 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1415 | +| iterations | 12336 | +| time_elapsed | 17852 | +| total_timesteps | 25264128 | +| train/ | | +| approx_kl | 0.01465109 | +| clip_fraction | 0.339 | +| clip_range | 0.0687 | +| entropy_loss | -6.09 | +| explained_variance | 0.564 | +| learning_rate | 4.4e-05 | +| loss | -0.0314 | +| n_updates | 65160 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000187 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1415 | +| iterations | 12337 | +| time_elapsed | 17853 | +| total_timesteps | 25266176 | +| train/ | | +| approx_kl | 0.016759966 | +| clip_fraction | 0.344 | +| clip_range | 0.0687 | +| entropy_loss | -5.73 | +| explained_variance | 0.447 | +| learning_rate | 4.4e-05 | +| loss | -0.0307 | +| n_updates | 65164 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000161 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1415 | +| iterations | 12338 | +| time_elapsed | 17855 | +| total_timesteps | 25268224 | +| train/ | | +| approx_kl | 0.012549547 | +| clip_fraction | 0.348 | +| clip_range | 0.0687 | +| entropy_loss | -6.75 | +| explained_variance | 0.000388 | +| learning_rate | 4.4e-05 | +| loss | -0.0352 | +| n_updates | 65168 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000109 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1415 | +| iterations | 12339 | +| time_elapsed | 17856 | +| total_timesteps | 25270272 | +| train/ | | +| approx_kl | 0.01449059 | +| clip_fraction | 0.333 | +| clip_range | 0.0687 | +| entropy_loss | -6.13 | +| explained_variance | 0.477 | +| learning_rate | 4.4e-05 | +| loss | -0.0234 | +| n_updates | 65172 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000237 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1415 | +| iterations | 12340 | +| time_elapsed | 17857 | +| total_timesteps | 25272320 | +| train/ | | +| approx_kl | 0.014729419 | +| clip_fraction | 0.371 | +| clip_range | 0.0687 | +| entropy_loss | -6.06 | +| explained_variance | 0.181 | +| learning_rate | 4.4e-05 | +| loss | -0.0359 | +| n_updates | 65176 | +| policy_gradient_loss | -0.0221 | +| value_loss | 8.75e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1415 | +| iterations | 12341 | +| time_elapsed | 17859 | +| total_timesteps | 25274368 | +| train/ | | +| approx_kl | 0.014002656 | +| clip_fraction | 0.35 | +| clip_range | 0.0687 | +| entropy_loss | -6.36 | +| explained_variance | 0.141 | +| learning_rate | 4.4e-05 | +| loss | -0.0274 | +| n_updates | 65180 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000167 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1415 | +| iterations | 12342 | +| time_elapsed | 17860 | +| total_timesteps | 25276416 | +| train/ | | +| approx_kl | 0.01629676 | +| clip_fraction | 0.337 | +| clip_range | 0.0687 | +| entropy_loss | -6.09 | +| explained_variance | 0.55 | +| learning_rate | 4.4e-05 | +| loss | -0.0326 | +| n_updates | 65184 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000204 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1415 | +| iterations | 12343 | +| time_elapsed | 17862 | +| total_timesteps | 25278464 | +| train/ | | +| approx_kl | 0.016127663 | +| clip_fraction | 0.343 | +| clip_range | 0.0687 | +| entropy_loss | -5.46 | +| explained_variance | 0.515 | +| learning_rate | 4.4e-05 | +| loss | -0.0286 | +| n_updates | 65188 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000223 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1415 | +| iterations | 12344 | +| time_elapsed | 17864 | +| total_timesteps | 25280512 | +| train/ | | +| approx_kl | 0.013962661 | +| clip_fraction | 0.354 | +| clip_range | 0.0687 | +| entropy_loss | -6.57 | +| explained_variance | -0.123 | +| learning_rate | 4.4e-05 | +| loss | -0.0258 | +| n_updates | 65192 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.00014 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1415 | +| iterations | 12345 | +| time_elapsed | 17865 | +| total_timesteps | 25282560 | +| train/ | | +| approx_kl | 0.014541001 | +| clip_fraction | 0.323 | +| clip_range | 0.0687 | +| entropy_loss | -6.32 | +| explained_variance | 0.39 | +| learning_rate | 4.4e-05 | +| loss | -0.025 | +| n_updates | 65196 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000176 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1415 | +| iterations | 12346 | +| time_elapsed | 17867 | +| total_timesteps | 25284608 | +| train/ | | +| approx_kl | 0.0141393915 | +| clip_fraction | 0.366 | +| clip_range | 0.0687 | +| entropy_loss | -6.02 | +| explained_variance | 0.462 | +| learning_rate | 4.4e-05 | +| loss | -0.0259 | +| n_updates | 65200 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000144 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1415 | +| iterations | 12347 | +| time_elapsed | 17868 | +| total_timesteps | 25286656 | +| train/ | | +| approx_kl | 0.017923884 | +| clip_fraction | 0.354 | +| clip_range | 0.0687 | +| entropy_loss | -5.99 | +| explained_variance | 0.398 | +| learning_rate | 4.4e-05 | +| loss | -0.0297 | +| n_updates | 65204 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000229 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1415 | +| iterations | 12348 | +| time_elapsed | 17870 | +| total_timesteps | 25288704 | +| train/ | | +| approx_kl | 0.018780407 | +| clip_fraction | 0.382 | +| clip_range | 0.0687 | +| entropy_loss | -6.08 | +| explained_variance | 0.313 | +| learning_rate | 4.4e-05 | +| loss | -0.0362 | +| n_updates | 65208 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000129 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1415 | +| iterations | 12349 | +| time_elapsed | 17871 | +| total_timesteps | 25290752 | +| train/ | | +| approx_kl | 0.0143002095 | +| clip_fraction | 0.357 | +| clip_range | 0.0687 | +| entropy_loss | -5.47 | +| explained_variance | 0.779 | +| learning_rate | 4.4e-05 | +| loss | -0.0265 | +| n_updates | 65212 | +| policy_gradient_loss | -0.0184 | +| value_loss | 9.21e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1415 | +| iterations | 12350 | +| time_elapsed | 17873 | +| total_timesteps | 25292800 | +| train/ | | +| approx_kl | 0.013935575 | +| clip_fraction | 0.342 | +| clip_range | 0.0687 | +| entropy_loss | -6.02 | +| explained_variance | 0.339 | +| learning_rate | 4.4e-05 | +| loss | -0.0247 | +| n_updates | 65216 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.00013 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1415 | +| iterations | 12351 | +| time_elapsed | 17874 | +| total_timesteps | 25294848 | +| train/ | | +| approx_kl | 0.012901778 | +| clip_fraction | 0.332 | +| clip_range | 0.0687 | +| entropy_loss | -6.73 | +| explained_variance | 0.418 | +| learning_rate | 4.4e-05 | +| loss | -0.0307 | +| n_updates | 65220 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000125 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1415 | +| iterations | 12352 | +| time_elapsed | 17876 | +| total_timesteps | 25296896 | +| train/ | | +| approx_kl | 0.012483237 | +| clip_fraction | 0.338 | +| clip_range | 0.0687 | +| entropy_loss | -6.13 | +| explained_variance | 0.517 | +| learning_rate | 4.4e-05 | +| loss | -0.0242 | +| n_updates | 65224 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000134 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1415 | +| iterations | 12353 | +| time_elapsed | 17877 | +| total_timesteps | 25298944 | +| train/ | | +| approx_kl | 0.01439616 | +| clip_fraction | 0.293 | +| clip_range | 0.0687 | +| entropy_loss | -5.74 | +| explained_variance | 0.526 | +| learning_rate | 4.4e-05 | +| loss | -0.0255 | +| n_updates | 65228 | +| policy_gradient_loss | -0.0145 | +| value_loss | 0.000224 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1415 | +| iterations | 12354 | +| time_elapsed | 17879 | +| total_timesteps | 25300992 | +| train/ | | +| approx_kl | 0.015992168 | +| clip_fraction | 0.344 | +| clip_range | 0.0687 | +| entropy_loss | -6.05 | +| explained_variance | 0.476 | +| learning_rate | 4.4e-05 | +| loss | -0.026 | +| n_updates | 65232 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000158 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1415 | +| iterations | 12355 | +| time_elapsed | 17880 | +| total_timesteps | 25303040 | +| train/ | | +| approx_kl | 0.017738806 | +| clip_fraction | 0.353 | +| clip_range | 0.0687 | +| entropy_loss | -5.72 | +| explained_variance | 0.362 | +| learning_rate | 4.4e-05 | +| loss | -0.02 | +| n_updates | 65236 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.000281 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1415 | +| iterations | 12356 | +| time_elapsed | 17882 | +| total_timesteps | 25305088 | +| train/ | | +| approx_kl | 0.01706469 | +| clip_fraction | 0.356 | +| clip_range | 0.0687 | +| entropy_loss | -6.24 | +| explained_variance | 0.221 | +| learning_rate | 4.4e-05 | +| loss | -0.0263 | +| n_updates | 65240 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000215 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1415 | +| iterations | 12357 | +| time_elapsed | 17883 | +| total_timesteps | 25307136 | +| train/ | | +| approx_kl | 0.013652042 | +| clip_fraction | 0.359 | +| clip_range | 0.0687 | +| entropy_loss | -6.78 | +| explained_variance | -0.0777 | +| learning_rate | 4.4e-05 | +| loss | -0.036 | +| n_updates | 65244 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.00014 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1415 | +| iterations | 12358 | +| time_elapsed | 17885 | +| total_timesteps | 25309184 | +| train/ | | +| approx_kl | 0.017298806 | +| clip_fraction | 0.324 | +| clip_range | 0.0687 | +| entropy_loss | -6.44 | +| explained_variance | 0.374 | +| learning_rate | 4.4e-05 | +| loss | -0.0242 | +| n_updates | 65248 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000241 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1415 | +| iterations | 12359 | +| time_elapsed | 17886 | +| total_timesteps | 25311232 | +| train/ | | +| approx_kl | 0.015465882 | +| clip_fraction | 0.37 | +| clip_range | 0.0687 | +| entropy_loss | -6.22 | +| explained_variance | 0.437 | +| learning_rate | 4.4e-05 | +| loss | -0.0321 | +| n_updates | 65252 | +| policy_gradient_loss | -0.0236 | +| value_loss | 8.31e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.14e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1415 | +| iterations | 12360 | +| time_elapsed | 17888 | +| total_timesteps | 25313280 | +| train/ | | +| approx_kl | 0.011818379 | +| clip_fraction | 0.327 | +| clip_range | 0.0687 | +| entropy_loss | -6.27 | +| explained_variance | 0.259 | +| learning_rate | 4.4e-05 | +| loss | -0.0259 | +| n_updates | 65256 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000236 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.14e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1415 | +| iterations | 12361 | +| time_elapsed | 17889 | +| total_timesteps | 25315328 | +| train/ | | +| approx_kl | 0.013279753 | +| clip_fraction | 0.319 | +| clip_range | 0.0687 | +| entropy_loss | -5.71 | +| explained_variance | 0.473 | +| learning_rate | 4.4e-05 | +| loss | -0.0233 | +| n_updates | 65260 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000324 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1415 | +| iterations | 12362 | +| time_elapsed | 17891 | +| total_timesteps | 25317376 | +| train/ | | +| approx_kl | 0.013779424 | +| clip_fraction | 0.325 | +| clip_range | 0.0687 | +| entropy_loss | -6.28 | +| explained_variance | 0.272 | +| learning_rate | 4.4e-05 | +| loss | -0.0372 | +| n_updates | 65264 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000135 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1415 | +| iterations | 12363 | +| time_elapsed | 17892 | +| total_timesteps | 25319424 | +| train/ | | +| approx_kl | 0.012252117 | +| clip_fraction | 0.326 | +| clip_range | 0.0687 | +| entropy_loss | -6.02 | +| explained_variance | 0.403 | +| learning_rate | 4.4e-05 | +| loss | -0.0256 | +| n_updates | 65268 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000221 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1415 | +| iterations | 12364 | +| time_elapsed | 17894 | +| total_timesteps | 25321472 | +| train/ | | +| approx_kl | 0.013379467 | +| clip_fraction | 0.355 | +| clip_range | 0.0687 | +| entropy_loss | -5.9 | +| explained_variance | 0.611 | +| learning_rate | 4.4e-05 | +| loss | -0.0324 | +| n_updates | 65272 | +| policy_gradient_loss | -0.0211 | +| value_loss | 8.5e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1415 | +| iterations | 12365 | +| time_elapsed | 17895 | +| total_timesteps | 25323520 | +| train/ | | +| approx_kl | 0.01426442 | +| clip_fraction | 0.343 | +| clip_range | 0.0687 | +| entropy_loss | -6.8 | +| explained_variance | -0.202 | +| learning_rate | 4.4e-05 | +| loss | -0.0321 | +| n_updates | 65276 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000125 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1415 | +| iterations | 12366 | +| time_elapsed | 17897 | +| total_timesteps | 25325568 | +| train/ | | +| approx_kl | 0.013524618 | +| clip_fraction | 0.375 | +| clip_range | 0.0687 | +| entropy_loss | -6.36 | +| explained_variance | 0.42 | +| learning_rate | 4.4e-05 | +| loss | -0.0351 | +| n_updates | 65280 | +| policy_gradient_loss | -0.0186 | +| value_loss | 9.95e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1415 | +| iterations | 12367 | +| time_elapsed | 17898 | +| total_timesteps | 25327616 | +| train/ | | +| approx_kl | 0.013179854 | +| clip_fraction | 0.354 | +| clip_range | 0.0687 | +| entropy_loss | -6.42 | +| explained_variance | 0.268 | +| learning_rate | 4.4e-05 | +| loss | -0.028 | +| n_updates | 65284 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.0002 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1415 | +| iterations | 12368 | +| time_elapsed | 17900 | +| total_timesteps | 25329664 | +| train/ | | +| approx_kl | 0.01201951 | +| clip_fraction | 0.329 | +| clip_range | 0.0687 | +| entropy_loss | -6.09 | +| explained_variance | 0.538 | +| learning_rate | 4.4e-05 | +| loss | -0.0329 | +| n_updates | 65288 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000196 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1415 | +| iterations | 12369 | +| time_elapsed | 17901 | +| total_timesteps | 25331712 | +| train/ | | +| approx_kl | 0.012981525 | +| clip_fraction | 0.346 | +| clip_range | 0.0687 | +| entropy_loss | -6.27 | +| explained_variance | 0.407 | +| learning_rate | 4.4e-05 | +| loss | -0.026 | +| n_updates | 65292 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1415 | +| iterations | 12370 | +| time_elapsed | 17903 | +| total_timesteps | 25333760 | +| train/ | | +| approx_kl | 0.013755622 | +| clip_fraction | 0.341 | +| clip_range | 0.0687 | +| entropy_loss | -5.6 | +| explained_variance | 0.56 | +| learning_rate | 4.4e-05 | +| loss | -0.0243 | +| n_updates | 65296 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000225 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1415 | +| iterations | 12371 | +| time_elapsed | 17904 | +| total_timesteps | 25335808 | +| train/ | | +| approx_kl | 0.012942646 | +| clip_fraction | 0.371 | +| clip_range | 0.0687 | +| entropy_loss | -5.68 | +| explained_variance | 0.564 | +| learning_rate | 4.4e-05 | +| loss | -0.0342 | +| n_updates | 65300 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000146 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1415 | +| iterations | 12372 | +| time_elapsed | 17906 | +| total_timesteps | 25337856 | +| train/ | | +| approx_kl | 0.01634261 | +| clip_fraction | 0.394 | +| clip_range | 0.0687 | +| entropy_loss | -6.33 | +| explained_variance | 0.37 | +| learning_rate | 4.4e-05 | +| loss | -0.0322 | +| n_updates | 65304 | +| policy_gradient_loss | -0.022 | +| value_loss | 8.9e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1415 | +| iterations | 12373 | +| time_elapsed | 17907 | +| total_timesteps | 25339904 | +| train/ | | +| approx_kl | 0.015111886 | +| clip_fraction | 0.347 | +| clip_range | 0.0687 | +| entropy_loss | -6.41 | +| explained_variance | 0.277 | +| learning_rate | 4.4e-05 | +| loss | -0.0272 | +| n_updates | 65308 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000151 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1415 | +| iterations | 12374 | +| time_elapsed | 17909 | +| total_timesteps | 25341952 | +| train/ | | +| approx_kl | 0.0144794285 | +| clip_fraction | 0.328 | +| clip_range | 0.0687 | +| entropy_loss | -6.26 | +| explained_variance | 0.0879 | +| learning_rate | 4.4e-05 | +| loss | -0.0278 | +| n_updates | 65312 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000154 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1415 | +| iterations | 12375 | +| time_elapsed | 17910 | +| total_timesteps | 25344000 | +| train/ | | +| approx_kl | 0.014186646 | +| clip_fraction | 0.357 | +| clip_range | 0.0687 | +| entropy_loss | -6.12 | +| explained_variance | 0.612 | +| learning_rate | 4.4e-05 | +| loss | -0.0307 | +| n_updates | 65316 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000122 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1415 | +| iterations | 12376 | +| time_elapsed | 17912 | +| total_timesteps | 25346048 | +| train/ | | +| approx_kl | 0.011427097 | +| clip_fraction | 0.313 | +| clip_range | 0.0687 | +| entropy_loss | -6.3 | +| explained_variance | 0.277 | +| learning_rate | 4.4e-05 | +| loss | -0.0254 | +| n_updates | 65320 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000339 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1415 | +| iterations | 12377 | +| time_elapsed | 17913 | +| total_timesteps | 25348096 | +| train/ | | +| approx_kl | 0.013975687 | +| clip_fraction | 0.358 | +| clip_range | 0.0687 | +| entropy_loss | -6.25 | +| explained_variance | 0.552 | +| learning_rate | 4.4e-05 | +| loss | -0.0375 | +| n_updates | 65324 | +| policy_gradient_loss | -0.0219 | +| value_loss | 0.000118 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1415 | +| iterations | 12378 | +| time_elapsed | 17915 | +| total_timesteps | 25350144 | +| train/ | | +| approx_kl | 0.017679933 | +| clip_fraction | 0.342 | +| clip_range | 0.0687 | +| entropy_loss | -6.26 | +| explained_variance | 0.183 | +| learning_rate | 4.4e-05 | +| loss | -0.0299 | +| n_updates | 65328 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000229 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1415 | +| iterations | 12379 | +| time_elapsed | 17916 | +| total_timesteps | 25352192 | +| train/ | | +| approx_kl | 0.015335511 | +| clip_fraction | 0.347 | +| clip_range | 0.0687 | +| entropy_loss | -6.43 | +| explained_variance | 0.17 | +| learning_rate | 4.4e-05 | +| loss | -0.0312 | +| n_updates | 65332 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000199 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1415 | +| iterations | 12380 | +| time_elapsed | 17918 | +| total_timesteps | 25354240 | +| train/ | | +| approx_kl | 0.014853479 | +| clip_fraction | 0.346 | +| clip_range | 0.0687 | +| entropy_loss | -6.22 | +| explained_variance | 0.361 | +| learning_rate | 4.4e-05 | +| loss | -0.0283 | +| n_updates | 65336 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000222 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1415 | +| iterations | 12381 | +| time_elapsed | 17919 | +| total_timesteps | 25356288 | +| train/ | | +| approx_kl | 0.017311353 | +| clip_fraction | 0.362 | +| clip_range | 0.0687 | +| entropy_loss | -6.02 | +| explained_variance | 0.358 | +| learning_rate | 4.4e-05 | +| loss | -0.0259 | +| n_updates | 65340 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000291 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1415 | +| iterations | 12382 | +| time_elapsed | 17921 | +| total_timesteps | 25358336 | +| train/ | | +| approx_kl | 0.018899925 | +| clip_fraction | 0.379 | +| clip_range | 0.0687 | +| entropy_loss | -6.1 | +| explained_variance | 0.166 | +| learning_rate | 4.4e-05 | +| loss | -0.0345 | +| n_updates | 65344 | +| policy_gradient_loss | -0.0225 | +| value_loss | 0.000141 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1415 | +| iterations | 12383 | +| time_elapsed | 17922 | +| total_timesteps | 25360384 | +| train/ | | +| approx_kl | 0.0135349315 | +| clip_fraction | 0.363 | +| clip_range | 0.0687 | +| entropy_loss | -6.89 | +| explained_variance | -0.212 | +| learning_rate | 4.4e-05 | +| loss | -0.036 | +| n_updates | 65348 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000122 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1415 | +| iterations | 12384 | +| time_elapsed | 17923 | +| total_timesteps | 25362432 | +| train/ | | +| approx_kl | 0.0144696245 | +| clip_fraction | 0.347 | +| clip_range | 0.0687 | +| entropy_loss | -6.53 | +| explained_variance | 0.524 | +| learning_rate | 4.4e-05 | +| loss | -0.0301 | +| n_updates | 65352 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000129 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1415 | +| iterations | 12385 | +| time_elapsed | 17925 | +| total_timesteps | 25364480 | +| train/ | | +| approx_kl | 0.015673602 | +| clip_fraction | 0.343 | +| clip_range | 0.0687 | +| entropy_loss | -6.23 | +| explained_variance | 0.28 | +| learning_rate | 4.4e-05 | +| loss | -0.0294 | +| n_updates | 65356 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000174 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1414 | +| iterations | 12386 | +| time_elapsed | 17926 | +| total_timesteps | 25366528 | +| train/ | | +| approx_kl | 0.018199746 | +| clip_fraction | 0.37 | +| clip_range | 0.0687 | +| entropy_loss | -5.59 | +| explained_variance | 0.581 | +| learning_rate | 4.4e-05 | +| loss | -0.0315 | +| n_updates | 65360 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000172 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1414 | +| iterations | 12387 | +| time_elapsed | 17928 | +| total_timesteps | 25368576 | +| train/ | | +| approx_kl | 0.015555093 | +| clip_fraction | 0.356 | +| clip_range | 0.0687 | +| entropy_loss | -5.92 | +| explained_variance | 0.478 | +| learning_rate | 4.4e-05 | +| loss | -0.0347 | +| n_updates | 65364 | +| policy_gradient_loss | -0.0199 | +| value_loss | 9.25e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1414 | +| iterations | 12388 | +| time_elapsed | 17929 | +| total_timesteps | 25370624 | +| train/ | | +| approx_kl | 0.016152248 | +| clip_fraction | 0.364 | +| clip_range | 0.0687 | +| entropy_loss | -6.48 | +| explained_variance | 0.359 | +| learning_rate | 4.4e-05 | +| loss | -0.0334 | +| n_updates | 65368 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.00012 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1414 | +| iterations | 12389 | +| time_elapsed | 17931 | +| total_timesteps | 25372672 | +| train/ | | +| approx_kl | 0.017649325 | +| clip_fraction | 0.329 | +| clip_range | 0.0687 | +| entropy_loss | -6.01 | +| explained_variance | 0.487 | +| learning_rate | 4.4e-05 | +| loss | -0.0268 | +| n_updates | 65372 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000191 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1414 | +| iterations | 12390 | +| time_elapsed | 17932 | +| total_timesteps | 25374720 | +| train/ | | +| approx_kl | 0.0163134 | +| clip_fraction | 0.39 | +| clip_range | 0.0687 | +| entropy_loss | -5.9 | +| explained_variance | 0.603 | +| learning_rate | 4.4e-05 | +| loss | -0.0315 | +| n_updates | 65376 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000127 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1414 | +| iterations | 12391 | +| time_elapsed | 17934 | +| total_timesteps | 25376768 | +| train/ | | +| approx_kl | 0.016383182 | +| clip_fraction | 0.374 | +| clip_range | 0.0687 | +| entropy_loss | -6.33 | +| explained_variance | -0.131 | +| learning_rate | 4.4e-05 | +| loss | -0.0389 | +| n_updates | 65380 | +| policy_gradient_loss | -0.0211 | +| value_loss | 9.03e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1414 | +| iterations | 12392 | +| time_elapsed | 17935 | +| total_timesteps | 25378816 | +| train/ | | +| approx_kl | 0.015339902 | +| clip_fraction | 0.342 | +| clip_range | 0.0687 | +| entropy_loss | -6.8 | +| explained_variance | -0.126 | +| learning_rate | 4.4e-05 | +| loss | -0.032 | +| n_updates | 65384 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000107 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1414 | +| iterations | 12393 | +| time_elapsed | 17937 | +| total_timesteps | 25380864 | +| train/ | | +| approx_kl | 0.016426045 | +| clip_fraction | 0.367 | +| clip_range | 0.0687 | +| entropy_loss | -6.44 | +| explained_variance | -0.119 | +| learning_rate | 4.4e-05 | +| loss | -0.0312 | +| n_updates | 65388 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000151 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1414 | +| iterations | 12394 | +| time_elapsed | 17938 | +| total_timesteps | 25382912 | +| train/ | | +| approx_kl | 0.017192647 | +| clip_fraction | 0.325 | +| clip_range | 0.0687 | +| entropy_loss | -5.97 | +| explained_variance | 0.533 | +| learning_rate | 4.4e-05 | +| loss | -0.0251 | +| n_updates | 65392 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.000152 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1414 | +| iterations | 12395 | +| time_elapsed | 17940 | +| total_timesteps | 25384960 | +| train/ | | +| approx_kl | 0.01667739 | +| clip_fraction | 0.389 | +| clip_range | 0.0687 | +| entropy_loss | -6.29 | +| explained_variance | -0.0102 | +| learning_rate | 4.4e-05 | +| loss | -0.0281 | +| n_updates | 65396 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000175 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1414 | +| iterations | 12396 | +| time_elapsed | 17941 | +| total_timesteps | 25387008 | +| train/ | | +| approx_kl | 0.016875893 | +| clip_fraction | 0.352 | +| clip_range | 0.0687 | +| entropy_loss | -6.08 | +| explained_variance | 0.511 | +| learning_rate | 4.4e-05 | +| loss | -0.029 | +| n_updates | 65400 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000133 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1414 | +| iterations | 12397 | +| time_elapsed | 17943 | +| total_timesteps | 25389056 | +| train/ | | +| approx_kl | 0.013109662 | +| clip_fraction | 0.337 | +| clip_range | 0.0687 | +| entropy_loss | -5.44 | +| explained_variance | 0.529 | +| learning_rate | 4.4e-05 | +| loss | -0.0235 | +| n_updates | 65404 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000256 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1414 | +| iterations | 12398 | +| time_elapsed | 17944 | +| total_timesteps | 25391104 | +| train/ | | +| approx_kl | 0.016482107 | +| clip_fraction | 0.339 | +| clip_range | 0.0687 | +| entropy_loss | -6.09 | +| explained_variance | 0.319 | +| learning_rate | 4.4e-05 | +| loss | -0.0303 | +| n_updates | 65408 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000134 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1414 | +| iterations | 12399 | +| time_elapsed | 17946 | +| total_timesteps | 25393152 | +| train/ | | +| approx_kl | 0.015353169 | +| clip_fraction | 0.36 | +| clip_range | 0.0687 | +| entropy_loss | -5.77 | +| explained_variance | 0.44 | +| learning_rate | 4.4e-05 | +| loss | -0.0291 | +| n_updates | 65412 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000171 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1414 | +| iterations | 12400 | +| time_elapsed | 17947 | +| total_timesteps | 25395200 | +| train/ | | +| approx_kl | 0.015934203 | +| clip_fraction | 0.384 | +| clip_range | 0.0687 | +| entropy_loss | -5.9 | +| explained_variance | 0.614 | +| learning_rate | 4.4e-05 | +| loss | -0.0341 | +| n_updates | 65416 | +| policy_gradient_loss | -0.0208 | +| value_loss | 9.3e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1414 | +| iterations | 12401 | +| time_elapsed | 17949 | +| total_timesteps | 25397248 | +| train/ | | +| approx_kl | 0.01699737 | +| clip_fraction | 0.347 | +| clip_range | 0.0687 | +| entropy_loss | -6.27 | +| explained_variance | -0.00334 | +| learning_rate | 4.4e-05 | +| loss | -0.0287 | +| n_updates | 65420 | +| policy_gradient_loss | -0.02 | +| value_loss | 9.95e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1414 | +| iterations | 12402 | +| time_elapsed | 17950 | +| total_timesteps | 25399296 | +| train/ | | +| approx_kl | 0.013018439 | +| clip_fraction | 0.327 | +| clip_range | 0.0687 | +| entropy_loss | -5.88 | +| explained_variance | 0.396 | +| learning_rate | 4.4e-05 | +| loss | -0.0239 | +| n_updates | 65424 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000311 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1414 | +| iterations | 12403 | +| time_elapsed | 17952 | +| total_timesteps | 25401344 | +| train/ | | +| approx_kl | 0.015507576 | +| clip_fraction | 0.321 | +| clip_range | 0.0687 | +| entropy_loss | -5.95 | +| explained_variance | 0.381 | +| learning_rate | 4.4e-05 | +| loss | -0.0309 | +| n_updates | 65428 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000289 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1414 | +| iterations | 12404 | +| time_elapsed | 17953 | +| total_timesteps | 25403392 | +| train/ | | +| approx_kl | 0.013057546 | +| clip_fraction | 0.357 | +| clip_range | 0.0686 | +| entropy_loss | -6.38 | +| explained_variance | -0.0451 | +| learning_rate | 4.4e-05 | +| loss | -0.0271 | +| n_updates | 65432 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.00031 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1414 | +| iterations | 12405 | +| time_elapsed | 17955 | +| total_timesteps | 25405440 | +| train/ | | +| approx_kl | 0.015343215 | +| clip_fraction | 0.345 | +| clip_range | 0.0686 | +| entropy_loss | -5.37 | +| explained_variance | 0.524 | +| learning_rate | 4.4e-05 | +| loss | -0.0274 | +| n_updates | 65436 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000204 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1414 | +| iterations | 12406 | +| time_elapsed | 17956 | +| total_timesteps | 25407488 | +| train/ | | +| approx_kl | 0.015422676 | +| clip_fraction | 0.384 | +| clip_range | 0.0686 | +| entropy_loss | -6.26 | +| explained_variance | -0.209 | +| learning_rate | 4.4e-05 | +| loss | -0.0336 | +| n_updates | 65440 | +| policy_gradient_loss | -0.0233 | +| value_loss | 9.93e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1414 | +| iterations | 12407 | +| time_elapsed | 17958 | +| total_timesteps | 25409536 | +| train/ | | +| approx_kl | 0.015109482 | +| clip_fraction | 0.366 | +| clip_range | 0.0686 | +| entropy_loss | -6.33 | +| explained_variance | 0.0201 | +| learning_rate | 4.4e-05 | +| loss | -0.029 | +| n_updates | 65444 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000111 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1414 | +| iterations | 12408 | +| time_elapsed | 17959 | +| total_timesteps | 25411584 | +| train/ | | +| approx_kl | 0.012795154 | +| clip_fraction | 0.346 | +| clip_range | 0.0686 | +| entropy_loss | -5.94 | +| explained_variance | 0.418 | +| learning_rate | 4.4e-05 | +| loss | -0.0244 | +| n_updates | 65448 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000238 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1414 | +| iterations | 12409 | +| time_elapsed | 17961 | +| total_timesteps | 25413632 | +| train/ | | +| approx_kl | 0.013060758 | +| clip_fraction | 0.312 | +| clip_range | 0.0686 | +| entropy_loss | -5.42 | +| explained_variance | 0.644 | +| learning_rate | 4.4e-05 | +| loss | -0.0296 | +| n_updates | 65452 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000192 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1414 | +| iterations | 12410 | +| time_elapsed | 17962 | +| total_timesteps | 25415680 | +| train/ | | +| approx_kl | 0.012122345 | +| clip_fraction | 0.36 | +| clip_range | 0.0686 | +| entropy_loss | -5.98 | +| explained_variance | 0.267 | +| learning_rate | 4.4e-05 | +| loss | -0.0268 | +| n_updates | 65456 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000229 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1414 | +| iterations | 12411 | +| time_elapsed | 17964 | +| total_timesteps | 25417728 | +| train/ | | +| approx_kl | 0.013196161 | +| clip_fraction | 0.36 | +| clip_range | 0.0686 | +| entropy_loss | -6.51 | +| explained_variance | -0.179 | +| learning_rate | 4.4e-05 | +| loss | -0.0343 | +| n_updates | 65460 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000144 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1414 | +| iterations | 12412 | +| time_elapsed | 17965 | +| total_timesteps | 25419776 | +| train/ | | +| approx_kl | 0.01529227 | +| clip_fraction | 0.333 | +| clip_range | 0.0686 | +| entropy_loss | -6.06 | +| explained_variance | 0.52 | +| learning_rate | 4.4e-05 | +| loss | -0.0335 | +| n_updates | 65464 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000156 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1414 | +| iterations | 12413 | +| time_elapsed | 17966 | +| total_timesteps | 25421824 | +| train/ | | +| approx_kl | 0.012552902 | +| clip_fraction | 0.311 | +| clip_range | 0.0686 | +| entropy_loss | -5.79 | +| explained_variance | 0.587 | +| learning_rate | 4.4e-05 | +| loss | -0.022 | +| n_updates | 65468 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000177 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1414 | +| iterations | 12414 | +| time_elapsed | 17968 | +| total_timesteps | 25423872 | +| train/ | | +| approx_kl | 0.013612439 | +| clip_fraction | 0.36 | +| clip_range | 0.0686 | +| entropy_loss | -6.13 | +| explained_variance | 0.372 | +| learning_rate | 4.4e-05 | +| loss | -0.0308 | +| n_updates | 65472 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000124 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1414 | +| iterations | 12415 | +| time_elapsed | 17969 | +| total_timesteps | 25425920 | +| train/ | | +| approx_kl | 0.01183556 | +| clip_fraction | 0.353 | +| clip_range | 0.0686 | +| entropy_loss | -6.52 | +| explained_variance | 0.159 | +| learning_rate | 4.4e-05 | +| loss | -0.0328 | +| n_updates | 65476 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000134 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1414 | +| iterations | 12416 | +| time_elapsed | 17971 | +| total_timesteps | 25427968 | +| train/ | | +| approx_kl | 0.01056917 | +| clip_fraction | 0.326 | +| clip_range | 0.0686 | +| entropy_loss | -6.75 | +| explained_variance | 0.0702 | +| learning_rate | 4.4e-05 | +| loss | -0.0285 | +| n_updates | 65480 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000161 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1414 | +| iterations | 12417 | +| time_elapsed | 17972 | +| total_timesteps | 25430016 | +| train/ | | +| approx_kl | 0.009895526 | +| clip_fraction | 0.311 | +| clip_range | 0.0686 | +| entropy_loss | -6.36 | +| explained_variance | 0.45 | +| learning_rate | 4.4e-05 | +| loss | -0.0271 | +| n_updates | 65484 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000112 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1414 | +| iterations | 12418 | +| time_elapsed | 17974 | +| total_timesteps | 25432064 | +| train/ | | +| approx_kl | 0.010858406 | +| clip_fraction | 0.31 | +| clip_range | 0.0686 | +| entropy_loss | -6.24 | +| explained_variance | 0.252 | +| learning_rate | 4.4e-05 | +| loss | -0.0223 | +| n_updates | 65488 | +| policy_gradient_loss | -0.0138 | +| value_loss | 0.000376 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1414 | +| iterations | 12419 | +| time_elapsed | 17975 | +| total_timesteps | 25434112 | +| train/ | | +| approx_kl | 0.017112026 | +| clip_fraction | 0.366 | +| clip_range | 0.0686 | +| entropy_loss | -5.91 | +| explained_variance | 0.435 | +| learning_rate | 4.4e-05 | +| loss | -0.031 | +| n_updates | 65492 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000104 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1414 | +| iterations | 12420 | +| time_elapsed | 17977 | +| total_timesteps | 25436160 | +| train/ | | +| approx_kl | 0.01246331 | +| clip_fraction | 0.343 | +| clip_range | 0.0686 | +| entropy_loss | -6.26 | +| explained_variance | 0.414 | +| learning_rate | 4.4e-05 | +| loss | -0.0295 | +| n_updates | 65496 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000211 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1414 | +| iterations | 12421 | +| time_elapsed | 17978 | +| total_timesteps | 25438208 | +| train/ | | +| approx_kl | 0.016046947 | +| clip_fraction | 0.359 | +| clip_range | 0.0686 | +| entropy_loss | -5 | +| explained_variance | 0.596 | +| learning_rate | 4.4e-05 | +| loss | -0.0309 | +| n_updates | 65500 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000204 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1414 | +| iterations | 12422 | +| time_elapsed | 17980 | +| total_timesteps | 25440256 | +| train/ | | +| approx_kl | 0.014739464 | +| clip_fraction | 0.355 | +| clip_range | 0.0686 | +| entropy_loss | -5.63 | +| explained_variance | 0.49 | +| learning_rate | 4.4e-05 | +| loss | -0.0283 | +| n_updates | 65504 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000239 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1414 | +| iterations | 12423 | +| time_elapsed | 17982 | +| total_timesteps | 25442304 | +| train/ | | +| approx_kl | 0.01441384 | +| clip_fraction | 0.362 | +| clip_range | 0.0686 | +| entropy_loss | -6.2 | +| explained_variance | 0.392 | +| learning_rate | 4.4e-05 | +| loss | -0.0301 | +| n_updates | 65508 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.00016 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1414 | +| iterations | 12424 | +| time_elapsed | 17983 | +| total_timesteps | 25444352 | +| train/ | | +| approx_kl | 0.016617017 | +| clip_fraction | 0.361 | +| clip_range | 0.0686 | +| entropy_loss | -6.23 | +| explained_variance | 0.464 | +| learning_rate | 4.4e-05 | +| loss | -0.0277 | +| n_updates | 65512 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000162 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1414 | +| iterations | 12425 | +| time_elapsed | 17985 | +| total_timesteps | 25446400 | +| train/ | | +| approx_kl | 0.01636452 | +| clip_fraction | 0.326 | +| clip_range | 0.0686 | +| entropy_loss | -5.97 | +| explained_variance | 0.26 | +| learning_rate | 4.4e-05 | +| loss | -0.0305 | +| n_updates | 65516 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000215 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1414 | +| iterations | 12426 | +| time_elapsed | 17986 | +| total_timesteps | 25448448 | +| train/ | | +| approx_kl | 0.016494956 | +| clip_fraction | 0.365 | +| clip_range | 0.0686 | +| entropy_loss | -6.13 | +| explained_variance | 0.224 | +| learning_rate | 4.4e-05 | +| loss | -0.0311 | +| n_updates | 65520 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000168 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1414 | +| iterations | 12427 | +| time_elapsed | 17987 | +| total_timesteps | 25450496 | +| train/ | | +| approx_kl | 0.016174752 | +| clip_fraction | 0.372 | +| clip_range | 0.0686 | +| entropy_loss | -6.29 | +| explained_variance | 0.205 | +| learning_rate | 4.4e-05 | +| loss | -0.0273 | +| n_updates | 65524 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000321 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1414 | +| iterations | 12428 | +| time_elapsed | 17989 | +| total_timesteps | 25452544 | +| train/ | | +| approx_kl | 0.018929046 | +| clip_fraction | 0.379 | +| clip_range | 0.0686 | +| entropy_loss | -6.15 | +| explained_variance | 0.0166 | +| learning_rate | 4.4e-05 | +| loss | -0.0305 | +| n_updates | 65528 | +| policy_gradient_loss | -0.0231 | +| value_loss | 0.000124 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1414 | +| iterations | 12429 | +| time_elapsed | 17990 | +| total_timesteps | 25454592 | +| train/ | | +| approx_kl | 0.013088783 | +| clip_fraction | 0.364 | +| clip_range | 0.0686 | +| entropy_loss | -6.21 | +| explained_variance | 0.167 | +| learning_rate | 4.4e-05 | +| loss | -0.0244 | +| n_updates | 65532 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000316 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1414 | +| iterations | 12430 | +| time_elapsed | 17992 | +| total_timesteps | 25456640 | +| train/ | | +| approx_kl | 0.012176874 | +| clip_fraction | 0.354 | +| clip_range | 0.0686 | +| entropy_loss | -6.39 | +| explained_variance | 0.543 | +| learning_rate | 4.4e-05 | +| loss | -0.0342 | +| n_updates | 65536 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000132 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1414 | +| iterations | 12431 | +| time_elapsed | 17993 | +| total_timesteps | 25458688 | +| train/ | | +| approx_kl | 0.01384908 | +| clip_fraction | 0.347 | +| clip_range | 0.0686 | +| entropy_loss | -5.86 | +| explained_variance | 0.722 | +| learning_rate | 4.4e-05 | +| loss | -0.037 | +| n_updates | 65540 | +| policy_gradient_loss | -0.0206 | +| value_loss | 8.73e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1414 | +| iterations | 12432 | +| time_elapsed | 17995 | +| total_timesteps | 25460736 | +| train/ | | +| approx_kl | 0.012664523 | +| clip_fraction | 0.345 | +| clip_range | 0.0686 | +| entropy_loss | -5.82 | +| explained_variance | 0.654 | +| learning_rate | 4.4e-05 | +| loss | -0.0258 | +| n_updates | 65544 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000133 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1414 | +| iterations | 12433 | +| time_elapsed | 17997 | +| total_timesteps | 25462784 | +| train/ | | +| approx_kl | 0.015481956 | +| clip_fraction | 0.345 | +| clip_range | 0.0686 | +| entropy_loss | -5.75 | +| explained_variance | 0.773 | +| learning_rate | 4.4e-05 | +| loss | -0.0241 | +| n_updates | 65548 | +| policy_gradient_loss | -0.0178 | +| value_loss | 8.98e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1414 | +| iterations | 12434 | +| time_elapsed | 17998 | +| total_timesteps | 25464832 | +| train/ | | +| approx_kl | 0.012023639 | +| clip_fraction | 0.347 | +| clip_range | 0.0686 | +| entropy_loss | -6.11 | +| explained_variance | 0.055 | +| learning_rate | 4.4e-05 | +| loss | -0.0327 | +| n_updates | 65552 | +| policy_gradient_loss | -0.0205 | +| value_loss | 9.14e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1414 | +| iterations | 12435 | +| time_elapsed | 18000 | +| total_timesteps | 25466880 | +| train/ | | +| approx_kl | 0.014911108 | +| clip_fraction | 0.357 | +| clip_range | 0.0686 | +| entropy_loss | -6.29 | +| explained_variance | 0.381 | +| learning_rate | 4.4e-05 | +| loss | -0.0311 | +| n_updates | 65556 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000156 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1414 | +| iterations | 12436 | +| time_elapsed | 18001 | +| total_timesteps | 25468928 | +| train/ | | +| approx_kl | 0.012985036 | +| clip_fraction | 0.363 | +| clip_range | 0.0686 | +| entropy_loss | -6.32 | +| explained_variance | 0.306 | +| learning_rate | 4.4e-05 | +| loss | -0.0324 | +| n_updates | 65560 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000105 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1414 | +| iterations | 12437 | +| time_elapsed | 18002 | +| total_timesteps | 25470976 | +| train/ | | +| approx_kl | 0.01116164 | +| clip_fraction | 0.341 | +| clip_range | 0.0686 | +| entropy_loss | -6.89 | +| explained_variance | -0.0406 | +| learning_rate | 4.4e-05 | +| loss | -0.0277 | +| n_updates | 65564 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000203 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1414 | +| iterations | 12438 | +| time_elapsed | 18004 | +| total_timesteps | 25473024 | +| train/ | | +| approx_kl | 0.0117631685 | +| clip_fraction | 0.314 | +| clip_range | 0.0686 | +| entropy_loss | -6.11 | +| explained_variance | 0.492 | +| learning_rate | 4.4e-05 | +| loss | -0.0235 | +| n_updates | 65568 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.00023 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1414 | +| iterations | 12439 | +| time_elapsed | 18005 | +| total_timesteps | 25475072 | +| train/ | | +| approx_kl | 0.012651047 | +| clip_fraction | 0.331 | +| clip_range | 0.0686 | +| entropy_loss | -6.12 | +| explained_variance | 0.315 | +| learning_rate | 4.4e-05 | +| loss | -0.0312 | +| n_updates | 65572 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000187 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1414 | +| iterations | 12440 | +| time_elapsed | 18007 | +| total_timesteps | 25477120 | +| train/ | | +| approx_kl | 0.014925304 | +| clip_fraction | 0.367 | +| clip_range | 0.0686 | +| entropy_loss | -6.23 | +| explained_variance | 0.546 | +| learning_rate | 4.39e-05 | +| loss | -0.0347 | +| n_updates | 65576 | +| policy_gradient_loss | -0.0208 | +| value_loss | 7.9e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1414 | +| iterations | 12441 | +| time_elapsed | 18008 | +| total_timesteps | 25479168 | +| train/ | | +| approx_kl | 0.015254024 | +| clip_fraction | 0.341 | +| clip_range | 0.0686 | +| entropy_loss | -5.77 | +| explained_variance | 0.64 | +| learning_rate | 4.39e-05 | +| loss | -0.0286 | +| n_updates | 65580 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000136 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1414 | +| iterations | 12442 | +| time_elapsed | 18010 | +| total_timesteps | 25481216 | +| train/ | | +| approx_kl | 0.015024103 | +| clip_fraction | 0.344 | +| clip_range | 0.0686 | +| entropy_loss | -5.7 | +| explained_variance | 0.671 | +| learning_rate | 4.39e-05 | +| loss | -0.0279 | +| n_updates | 65584 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000155 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1414 | +| iterations | 12443 | +| time_elapsed | 18011 | +| total_timesteps | 25483264 | +| train/ | | +| approx_kl | 0.018240139 | +| clip_fraction | 0.39 | +| clip_range | 0.0686 | +| entropy_loss | -6.35 | +| explained_variance | -0.211 | +| learning_rate | 4.39e-05 | +| loss | -0.03 | +| n_updates | 65588 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000107 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1414 | +| iterations | 12444 | +| time_elapsed | 18013 | +| total_timesteps | 25485312 | +| train/ | | +| approx_kl | 0.012932499 | +| clip_fraction | 0.319 | +| clip_range | 0.0686 | +| entropy_loss | -6.34 | +| explained_variance | 0.245 | +| learning_rate | 4.39e-05 | +| loss | -0.0256 | +| n_updates | 65592 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000429 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1414 | +| iterations | 12445 | +| time_elapsed | 18014 | +| total_timesteps | 25487360 | +| train/ | | +| approx_kl | 0.012625046 | +| clip_fraction | 0.336 | +| clip_range | 0.0686 | +| entropy_loss | -5.69 | +| explained_variance | 0.574 | +| learning_rate | 4.39e-05 | +| loss | -0.0293 | +| n_updates | 65596 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000136 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1414 | +| iterations | 12446 | +| time_elapsed | 18016 | +| total_timesteps | 25489408 | +| train/ | | +| approx_kl | 0.01425957 | +| clip_fraction | 0.343 | +| clip_range | 0.0686 | +| entropy_loss | -5.79 | +| explained_variance | 0.603 | +| learning_rate | 4.39e-05 | +| loss | -0.0282 | +| n_updates | 65600 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000121 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1414 | +| iterations | 12447 | +| time_elapsed | 18018 | +| total_timesteps | 25491456 | +| train/ | | +| approx_kl | 0.010262201 | +| clip_fraction | 0.319 | +| clip_range | 0.0686 | +| entropy_loss | -5.85 | +| explained_variance | 0.421 | +| learning_rate | 4.39e-05 | +| loss | -0.0218 | +| n_updates | 65604 | +| policy_gradient_loss | -0.0137 | +| value_loss | 0.000258 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1414 | +| iterations | 12448 | +| time_elapsed | 18019 | +| total_timesteps | 25493504 | +| train/ | | +| approx_kl | 0.016527561 | +| clip_fraction | 0.357 | +| clip_range | 0.0686 | +| entropy_loss | -6.42 | +| explained_variance | 0.0567 | +| learning_rate | 4.39e-05 | +| loss | -0.0361 | +| n_updates | 65608 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000131 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1414 | +| iterations | 12449 | +| time_elapsed | 18021 | +| total_timesteps | 25495552 | +| train/ | | +| approx_kl | 0.014403626 | +| clip_fraction | 0.359 | +| clip_range | 0.0686 | +| entropy_loss | -6.49 | +| explained_variance | 0.399 | +| learning_rate | 4.39e-05 | +| loss | -0.0321 | +| n_updates | 65612 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000125 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1414 | +| iterations | 12450 | +| time_elapsed | 18022 | +| total_timesteps | 25497600 | +| train/ | | +| approx_kl | 0.012053731 | +| clip_fraction | 0.338 | +| clip_range | 0.0686 | +| entropy_loss | -6.29 | +| explained_variance | 0.211 | +| learning_rate | 4.39e-05 | +| loss | -0.0223 | +| n_updates | 65616 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000251 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1414 | +| iterations | 12451 | +| time_elapsed | 18024 | +| total_timesteps | 25499648 | +| train/ | | +| approx_kl | 0.013119402 | +| clip_fraction | 0.352 | +| clip_range | 0.0686 | +| entropy_loss | -5.58 | +| explained_variance | 0.609 | +| learning_rate | 4.39e-05 | +| loss | -0.0321 | +| n_updates | 65620 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000185 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1414 | +| iterations | 12452 | +| time_elapsed | 18025 | +| total_timesteps | 25501696 | +| train/ | | +| approx_kl | 0.016234843 | +| clip_fraction | 0.361 | +| clip_range | 0.0686 | +| entropy_loss | -5.92 | +| explained_variance | 0.476 | +| learning_rate | 4.39e-05 | +| loss | -0.0351 | +| n_updates | 65624 | +| policy_gradient_loss | -0.0196 | +| value_loss | 8.96e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1414 | +| iterations | 12453 | +| time_elapsed | 18027 | +| total_timesteps | 25503744 | +| train/ | | +| approx_kl | 0.016429977 | +| clip_fraction | 0.358 | +| clip_range | 0.0686 | +| entropy_loss | -6.06 | +| explained_variance | 0.337 | +| learning_rate | 4.39e-05 | +| loss | -0.0306 | +| n_updates | 65628 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000145 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1414 | +| iterations | 12454 | +| time_elapsed | 18028 | +| total_timesteps | 25505792 | +| train/ | | +| approx_kl | 0.015292775 | +| clip_fraction | 0.346 | +| clip_range | 0.0686 | +| entropy_loss | -5.74 | +| explained_variance | 0.433 | +| learning_rate | 4.39e-05 | +| loss | -0.0263 | +| n_updates | 65632 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000268 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1414 | +| iterations | 12455 | +| time_elapsed | 18030 | +| total_timesteps | 25507840 | +| train/ | | +| approx_kl | 0.013847665 | +| clip_fraction | 0.359 | +| clip_range | 0.0686 | +| entropy_loss | -6.05 | +| explained_variance | 0.234 | +| learning_rate | 4.39e-05 | +| loss | -0.0319 | +| n_updates | 65636 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000192 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1414 | +| iterations | 12456 | +| time_elapsed | 18031 | +| total_timesteps | 25509888 | +| train/ | | +| approx_kl | 0.017090382 | +| clip_fraction | 0.369 | +| clip_range | 0.0686 | +| entropy_loss | -5.57 | +| explained_variance | 0.725 | +| learning_rate | 4.39e-05 | +| loss | -0.0377 | +| n_updates | 65640 | +| policy_gradient_loss | -0.0227 | +| value_loss | 6.56e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1414 | +| iterations | 12457 | +| time_elapsed | 18033 | +| total_timesteps | 25511936 | +| train/ | | +| approx_kl | 0.01327025 | +| clip_fraction | 0.358 | +| clip_range | 0.0686 | +| entropy_loss | -5.64 | +| explained_variance | 0.405 | +| learning_rate | 4.39e-05 | +| loss | -0.029 | +| n_updates | 65644 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000263 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1414 | +| iterations | 12458 | +| time_elapsed | 18034 | +| total_timesteps | 25513984 | +| train/ | | +| approx_kl | 0.015718967 | +| clip_fraction | 0.374 | +| clip_range | 0.0686 | +| entropy_loss | -6.2 | +| explained_variance | 0.212 | +| learning_rate | 4.39e-05 | +| loss | -0.0347 | +| n_updates | 65648 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000101 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1414 | +| iterations | 12459 | +| time_elapsed | 18036 | +| total_timesteps | 25516032 | +| train/ | | +| approx_kl | 0.015465024 | +| clip_fraction | 0.389 | +| clip_range | 0.0686 | +| entropy_loss | -5.88 | +| explained_variance | 0.511 | +| learning_rate | 4.39e-05 | +| loss | -0.0309 | +| n_updates | 65652 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000137 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1414 | +| iterations | 12460 | +| time_elapsed | 18037 | +| total_timesteps | 25518080 | +| train/ | | +| approx_kl | 0.016402856 | +| clip_fraction | 0.365 | +| clip_range | 0.0686 | +| entropy_loss | -6.05 | +| explained_variance | 0.535 | +| learning_rate | 4.39e-05 | +| loss | -0.0309 | +| n_updates | 65656 | +| policy_gradient_loss | -0.0213 | +| value_loss | 7.43e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1414 | +| iterations | 12461 | +| time_elapsed | 18039 | +| total_timesteps | 25520128 | +| train/ | | +| approx_kl | 0.0145443315 | +| clip_fraction | 0.381 | +| clip_range | 0.0686 | +| entropy_loss | -6.16 | +| explained_variance | 0.139 | +| learning_rate | 4.39e-05 | +| loss | -0.0283 | +| n_updates | 65660 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000152 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1414 | +| iterations | 12462 | +| time_elapsed | 18040 | +| total_timesteps | 25522176 | +| train/ | | +| approx_kl | 0.017574608 | +| clip_fraction | 0.356 | +| clip_range | 0.0686 | +| entropy_loss | -6.34 | +| explained_variance | 0.49 | +| learning_rate | 4.39e-05 | +| loss | -0.0265 | +| n_updates | 65664 | +| policy_gradient_loss | -0.0179 | +| value_loss | 9.79e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1414 | +| iterations | 12463 | +| time_elapsed | 18042 | +| total_timesteps | 25524224 | +| train/ | | +| approx_kl | 0.013741646 | +| clip_fraction | 0.33 | +| clip_range | 0.0686 | +| entropy_loss | -5.11 | +| explained_variance | 0.531 | +| learning_rate | 4.39e-05 | +| loss | -0.0181 | +| n_updates | 65668 | +| policy_gradient_loss | -0.0145 | +| value_loss | 0.000293 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1414 | +| iterations | 12464 | +| time_elapsed | 18043 | +| total_timesteps | 25526272 | +| train/ | | +| approx_kl | 0.018541934 | +| clip_fraction | 0.368 | +| clip_range | 0.0686 | +| entropy_loss | -5.34 | +| explained_variance | 0.623 | +| learning_rate | 4.39e-05 | +| loss | -0.0303 | +| n_updates | 65672 | +| policy_gradient_loss | -0.0201 | +| value_loss | 8.16e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1414 | +| iterations | 12465 | +| time_elapsed | 18045 | +| total_timesteps | 25528320 | +| train/ | | +| approx_kl | 0.01422643 | +| clip_fraction | 0.369 | +| clip_range | 0.0686 | +| entropy_loss | -5.8 | +| explained_variance | 0.628 | +| learning_rate | 4.39e-05 | +| loss | -0.0204 | +| n_updates | 65676 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000119 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1414 | +| iterations | 12466 | +| time_elapsed | 18046 | +| total_timesteps | 25530368 | +| train/ | | +| approx_kl | 0.019341309 | +| clip_fraction | 0.37 | +| clip_range | 0.0686 | +| entropy_loss | -5.81 | +| explained_variance | 0.436 | +| learning_rate | 4.39e-05 | +| loss | -0.029 | +| n_updates | 65680 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000101 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1414 | +| iterations | 12467 | +| time_elapsed | 18048 | +| total_timesteps | 25532416 | +| train/ | | +| approx_kl | 0.017088674 | +| clip_fraction | 0.352 | +| clip_range | 0.0686 | +| entropy_loss | -6.07 | +| explained_variance | -0.129 | +| learning_rate | 4.39e-05 | +| loss | -0.0275 | +| n_updates | 65684 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000144 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1414 | +| iterations | 12468 | +| time_elapsed | 18050 | +| total_timesteps | 25534464 | +| train/ | | +| approx_kl | 0.01643487 | +| clip_fraction | 0.37 | +| clip_range | 0.0686 | +| entropy_loss | -6.16 | +| explained_variance | 0.165 | +| learning_rate | 4.39e-05 | +| loss | -0.0276 | +| n_updates | 65688 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000155 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1414 | +| iterations | 12469 | +| time_elapsed | 18051 | +| total_timesteps | 25536512 | +| train/ | | +| approx_kl | 0.015946746 | +| clip_fraction | 0.369 | +| clip_range | 0.0686 | +| entropy_loss | -6.55 | +| explained_variance | -0.288 | +| learning_rate | 4.39e-05 | +| loss | -0.0373 | +| n_updates | 65692 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000122 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1414 | +| iterations | 12470 | +| time_elapsed | 18053 | +| total_timesteps | 25538560 | +| train/ | | +| approx_kl | 0.015291387 | +| clip_fraction | 0.35 | +| clip_range | 0.0686 | +| entropy_loss | -6.14 | +| explained_variance | 0.218 | +| learning_rate | 4.39e-05 | +| loss | -0.0299 | +| n_updates | 65696 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000182 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1414 | +| iterations | 12471 | +| time_elapsed | 18054 | +| total_timesteps | 25540608 | +| train/ | | +| approx_kl | 0.014877139 | +| clip_fraction | 0.351 | +| clip_range | 0.0686 | +| entropy_loss | -6.16 | +| explained_variance | 0.444 | +| learning_rate | 4.39e-05 | +| loss | -0.0303 | +| n_updates | 65700 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000174 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1414 | +| iterations | 12472 | +| time_elapsed | 18056 | +| total_timesteps | 25542656 | +| train/ | | +| approx_kl | 0.013614373 | +| clip_fraction | 0.348 | +| clip_range | 0.0686 | +| entropy_loss | -6.26 | +| explained_variance | 0.214 | +| learning_rate | 4.39e-05 | +| loss | -0.0268 | +| n_updates | 65704 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000234 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1414 | +| iterations | 12473 | +| time_elapsed | 18057 | +| total_timesteps | 25544704 | +| train/ | | +| approx_kl | 0.01605745 | +| clip_fraction | 0.36 | +| clip_range | 0.0686 | +| entropy_loss | -6.25 | +| explained_variance | 0.433 | +| learning_rate | 4.39e-05 | +| loss | -0.0261 | +| n_updates | 65708 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000101 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1414 | +| iterations | 12474 | +| time_elapsed | 18059 | +| total_timesteps | 25546752 | +| train/ | | +| approx_kl | 0.01363194 | +| clip_fraction | 0.352 | +| clip_range | 0.0686 | +| entropy_loss | -5.66 | +| explained_variance | 0.494 | +| learning_rate | 4.39e-05 | +| loss | -0.0216 | +| n_updates | 65712 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000151 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1414 | +| iterations | 12475 | +| time_elapsed | 18060 | +| total_timesteps | 25548800 | +| train/ | | +| approx_kl | 0.013353927 | +| clip_fraction | 0.323 | +| clip_range | 0.0686 | +| entropy_loss | -5.56 | +| explained_variance | 0.493 | +| learning_rate | 4.39e-05 | +| loss | -0.0239 | +| n_updates | 65716 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000308 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1414 | +| iterations | 12476 | +| time_elapsed | 18062 | +| total_timesteps | 25550848 | +| train/ | | +| approx_kl | 0.011551487 | +| clip_fraction | 0.342 | +| clip_range | 0.0686 | +| entropy_loss | -5.1 | +| explained_variance | 0.723 | +| learning_rate | 4.39e-05 | +| loss | -0.0309 | +| n_updates | 65720 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000107 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1414 | +| iterations | 12477 | +| time_elapsed | 18063 | +| total_timesteps | 25552896 | +| train/ | | +| approx_kl | 0.012552316 | +| clip_fraction | 0.346 | +| clip_range | 0.0686 | +| entropy_loss | -5.92 | +| explained_variance | 0.47 | +| learning_rate | 4.39e-05 | +| loss | -0.0326 | +| n_updates | 65724 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000122 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1414 | +| iterations | 12478 | +| time_elapsed | 18065 | +| total_timesteps | 25554944 | +| train/ | | +| approx_kl | 0.01159571 | +| clip_fraction | 0.333 | +| clip_range | 0.0686 | +| entropy_loss | -6.1 | +| explained_variance | 0.336 | +| learning_rate | 4.39e-05 | +| loss | -0.0186 | +| n_updates | 65728 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000322 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1414 | +| iterations | 12479 | +| time_elapsed | 18066 | +| total_timesteps | 25556992 | +| train/ | | +| approx_kl | 0.013688373 | +| clip_fraction | 0.372 | +| clip_range | 0.0686 | +| entropy_loss | -6.24 | +| explained_variance | 0.15 | +| learning_rate | 4.39e-05 | +| loss | -0.032 | +| n_updates | 65732 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000164 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1414 | +| iterations | 12480 | +| time_elapsed | 18068 | +| total_timesteps | 25559040 | +| train/ | | +| approx_kl | 0.011168069 | +| clip_fraction | 0.333 | +| clip_range | 0.0686 | +| entropy_loss | -5.97 | +| explained_variance | 0.284 | +| learning_rate | 4.39e-05 | +| loss | -0.0249 | +| n_updates | 65736 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000266 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1414 | +| iterations | 12481 | +| time_elapsed | 18069 | +| total_timesteps | 25561088 | +| train/ | | +| approx_kl | 0.01655236 | +| clip_fraction | 0.355 | +| clip_range | 0.0686 | +| entropy_loss | -6.09 | +| explained_variance | 0.271 | +| learning_rate | 4.39e-05 | +| loss | -0.0305 | +| n_updates | 65740 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000197 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1414 | +| iterations | 12482 | +| time_elapsed | 18071 | +| total_timesteps | 25563136 | +| train/ | | +| approx_kl | 0.015115366 | +| clip_fraction | 0.377 | +| clip_range | 0.0686 | +| entropy_loss | -6.14 | +| explained_variance | 0.464 | +| learning_rate | 4.39e-05 | +| loss | -0.033 | +| n_updates | 65744 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000145 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1414 | +| iterations | 12483 | +| time_elapsed | 18072 | +| total_timesteps | 25565184 | +| train/ | | +| approx_kl | 0.013532117 | +| clip_fraction | 0.353 | +| clip_range | 0.0686 | +| entropy_loss | -5.8 | +| explained_variance | 0.548 | +| learning_rate | 4.39e-05 | +| loss | -0.0309 | +| n_updates | 65748 | +| policy_gradient_loss | -0.0191 | +| value_loss | 9.94e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1414 | +| iterations | 12484 | +| time_elapsed | 18074 | +| total_timesteps | 25567232 | +| train/ | | +| approx_kl | 0.014320359 | +| clip_fraction | 0.336 | +| clip_range | 0.0686 | +| entropy_loss | -5.89 | +| explained_variance | 0.36 | +| learning_rate | 4.39e-05 | +| loss | -0.0255 | +| n_updates | 65752 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.00045 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1414 | +| iterations | 12485 | +| time_elapsed | 18075 | +| total_timesteps | 25569280 | +| train/ | | +| approx_kl | 0.013036383 | +| clip_fraction | 0.358 | +| clip_range | 0.0686 | +| entropy_loss | -5.41 | +| explained_variance | 0.575 | +| learning_rate | 4.39e-05 | +| loss | -0.0326 | +| n_updates | 65756 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1414 | +| iterations | 12486 | +| time_elapsed | 18077 | +| total_timesteps | 25571328 | +| train/ | | +| approx_kl | 0.014155736 | +| clip_fraction | 0.322 | +| clip_range | 0.0686 | +| entropy_loss | -5.56 | +| explained_variance | 0.49 | +| learning_rate | 4.39e-05 | +| loss | -0.029 | +| n_updates | 65760 | +| policy_gradient_loss | -0.0139 | +| value_loss | 0.000276 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1414 | +| iterations | 12487 | +| time_elapsed | 18078 | +| total_timesteps | 25573376 | +| train/ | | +| approx_kl | 0.015236749 | +| clip_fraction | 0.363 | +| clip_range | 0.0686 | +| entropy_loss | -5.85 | +| explained_variance | 0.0658 | +| learning_rate | 4.39e-05 | +| loss | -0.0353 | +| n_updates | 65764 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.00025 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1414 | +| iterations | 12488 | +| time_elapsed | 18080 | +| total_timesteps | 25575424 | +| train/ | | +| approx_kl | 0.015722316 | +| clip_fraction | 0.386 | +| clip_range | 0.0686 | +| entropy_loss | -6.03 | +| explained_variance | 0.584 | +| learning_rate | 4.39e-05 | +| loss | -0.0377 | +| n_updates | 65768 | +| policy_gradient_loss | -0.0233 | +| value_loss | 7.86e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1414 | +| iterations | 12489 | +| time_elapsed | 18081 | +| total_timesteps | 25577472 | +| train/ | | +| approx_kl | 0.014369164 | +| clip_fraction | 0.358 | +| clip_range | 0.0686 | +| entropy_loss | -6.42 | +| explained_variance | 0.374 | +| learning_rate | 4.39e-05 | +| loss | -0.0345 | +| n_updates | 65772 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000141 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1414 | +| iterations | 12490 | +| time_elapsed | 18083 | +| total_timesteps | 25579520 | +| train/ | | +| approx_kl | 0.014276398 | +| clip_fraction | 0.358 | +| clip_range | 0.0686 | +| entropy_loss | -5.94 | +| explained_variance | 0.603 | +| learning_rate | 4.39e-05 | +| loss | -0.0302 | +| n_updates | 65776 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.0001 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1414 | +| iterations | 12491 | +| time_elapsed | 18084 | +| total_timesteps | 25581568 | +| train/ | | +| approx_kl | 0.013861082 | +| clip_fraction | 0.351 | +| clip_range | 0.0686 | +| entropy_loss | -6.17 | +| explained_variance | 0.155 | +| learning_rate | 4.39e-05 | +| loss | -0.0298 | +| n_updates | 65780 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000133 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1414 | +| iterations | 12492 | +| time_elapsed | 18086 | +| total_timesteps | 25583616 | +| train/ | | +| approx_kl | 0.017803108 | +| clip_fraction | 0.367 | +| clip_range | 0.0686 | +| entropy_loss | -6.45 | +| explained_variance | 0.25 | +| learning_rate | 4.39e-05 | +| loss | -0.0281 | +| n_updates | 65784 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000127 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1414 | +| iterations | 12493 | +| time_elapsed | 18087 | +| total_timesteps | 25585664 | +| train/ | | +| approx_kl | 0.01783834 | +| clip_fraction | 0.32 | +| clip_range | 0.0686 | +| entropy_loss | -5.63 | +| explained_variance | 0.489 | +| learning_rate | 4.39e-05 | +| loss | -0.0234 | +| n_updates | 65788 | +| policy_gradient_loss | -0.0139 | +| value_loss | 0.000204 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1414 | +| iterations | 12494 | +| time_elapsed | 18089 | +| total_timesteps | 25587712 | +| train/ | | +| approx_kl | 0.016157106 | +| clip_fraction | 0.351 | +| clip_range | 0.0686 | +| entropy_loss | -5.88 | +| explained_variance | 0.617 | +| learning_rate | 4.39e-05 | +| loss | -0.0242 | +| n_updates | 65792 | +| policy_gradient_loss | -0.0189 | +| value_loss | 8.46e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1414 | +| iterations | 12495 | +| time_elapsed | 18090 | +| total_timesteps | 25589760 | +| train/ | | +| approx_kl | 0.0127813015 | +| clip_fraction | 0.347 | +| clip_range | 0.0686 | +| entropy_loss | -6.46 | +| explained_variance | 0.179 | +| learning_rate | 4.39e-05 | +| loss | -0.0365 | +| n_updates | 65796 | +| policy_gradient_loss | -0.02 | +| value_loss | 7.4e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1414 | +| iterations | 12496 | +| time_elapsed | 18092 | +| total_timesteps | 25591808 | +| train/ | | +| approx_kl | 0.013524681 | +| clip_fraction | 0.329 | +| clip_range | 0.0686 | +| entropy_loss | -5.99 | +| explained_variance | 0.487 | +| learning_rate | 4.39e-05 | +| loss | -0.0293 | +| n_updates | 65800 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000186 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1414 | +| iterations | 12497 | +| time_elapsed | 18093 | +| total_timesteps | 25593856 | +| train/ | | +| approx_kl | 0.018275298 | +| clip_fraction | 0.364 | +| clip_range | 0.0686 | +| entropy_loss | -5.95 | +| explained_variance | 0.352 | +| learning_rate | 4.39e-05 | +| loss | -0.0247 | +| n_updates | 65804 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000122 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1414 | +| iterations | 12498 | +| time_elapsed | 18095 | +| total_timesteps | 25595904 | +| train/ | | +| approx_kl | 0.014717215 | +| clip_fraction | 0.351 | +| clip_range | 0.0686 | +| entropy_loss | -5.49 | +| explained_variance | 0.667 | +| learning_rate | 4.39e-05 | +| loss | -0.0275 | +| n_updates | 65808 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000141 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1414 | +| iterations | 12499 | +| time_elapsed | 18096 | +| total_timesteps | 25597952 | +| train/ | | +| approx_kl | 0.01499423 | +| clip_fraction | 0.379 | +| clip_range | 0.0686 | +| entropy_loss | -6.16 | +| explained_variance | -0.0469 | +| learning_rate | 4.39e-05 | +| loss | -0.0355 | +| n_updates | 65812 | +| policy_gradient_loss | -0.0219 | +| value_loss | 0.000119 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1414 | +| iterations | 12500 | +| time_elapsed | 18098 | +| total_timesteps | 25600000 | +| train/ | | +| approx_kl | 0.017484834 | +| clip_fraction | 0.346 | +| clip_range | 0.0686 | +| entropy_loss | -6.11 | +| explained_variance | 0.317 | +| learning_rate | 4.39e-05 | +| loss | -0.0228 | +| n_updates | 65816 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000239 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1414 | +| iterations | 12501 | +| time_elapsed | 18099 | +| total_timesteps | 25602048 | +| train/ | | +| approx_kl | 0.013983948 | +| clip_fraction | 0.358 | +| clip_range | 0.0686 | +| entropy_loss | -5.47 | +| explained_variance | 0.641 | +| learning_rate | 4.39e-05 | +| loss | -0.0335 | +| n_updates | 65820 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.00012 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1414 | +| iterations | 12502 | +| time_elapsed | 18101 | +| total_timesteps | 25604096 | +| train/ | | +| approx_kl | 0.01424896 | +| clip_fraction | 0.352 | +| clip_range | 0.0686 | +| entropy_loss | -5.85 | +| explained_variance | 0.645 | +| learning_rate | 4.39e-05 | +| loss | -0.0302 | +| n_updates | 65824 | +| policy_gradient_loss | -0.02 | +| value_loss | 8.72e-05 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1414 | +| iterations | 12503 | +| time_elapsed | 18102 | +| total_timesteps | 25606144 | +| train/ | | +| approx_kl | 0.01367392 | +| clip_fraction | 0.358 | +| clip_range | 0.0686 | +| entropy_loss | -5.83 | +| explained_variance | 0.493 | +| learning_rate | 4.39e-05 | +| loss | -0.0267 | +| n_updates | 65828 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000191 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1414 | +| iterations | 12504 | +| time_elapsed | 18104 | +| total_timesteps | 25608192 | +| train/ | | +| approx_kl | 0.012056616 | +| clip_fraction | 0.356 | +| clip_range | 0.0686 | +| entropy_loss | -6.41 | +| explained_variance | 0.159 | +| learning_rate | 4.39e-05 | +| loss | -0.0289 | +| n_updates | 65832 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000128 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1414 | +| iterations | 12505 | +| time_elapsed | 18105 | +| total_timesteps | 25610240 | +| train/ | | +| approx_kl | 0.011315933 | +| clip_fraction | 0.329 | +| clip_range | 0.0686 | +| entropy_loss | -6.3 | +| explained_variance | 0.215 | +| learning_rate | 4.39e-05 | +| loss | -0.0292 | +| n_updates | 65836 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000261 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1414 | +| iterations | 12506 | +| time_elapsed | 18107 | +| total_timesteps | 25612288 | +| train/ | | +| approx_kl | 0.011522118 | +| clip_fraction | 0.349 | +| clip_range | 0.0686 | +| entropy_loss | -5.85 | +| explained_variance | 0.641 | +| learning_rate | 4.39e-05 | +| loss | -0.0347 | +| n_updates | 65840 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000119 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1414 | +| iterations | 12507 | +| time_elapsed | 18108 | +| total_timesteps | 25614336 | +| train/ | | +| approx_kl | 0.013417142 | +| clip_fraction | 0.367 | +| clip_range | 0.0686 | +| entropy_loss | -6.17 | +| explained_variance | 0.176 | +| learning_rate | 4.39e-05 | +| loss | -0.0345 | +| n_updates | 65844 | +| policy_gradient_loss | -0.0203 | +| value_loss | 9.84e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1414 | +| iterations | 12508 | +| time_elapsed | 18110 | +| total_timesteps | 25616384 | +| train/ | | +| approx_kl | 0.019385226 | +| clip_fraction | 0.331 | +| clip_range | 0.0686 | +| entropy_loss | -5.99 | +| explained_variance | 0.519 | +| learning_rate | 4.39e-05 | +| loss | -0.0333 | +| n_updates | 65848 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000172 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1414 | +| iterations | 12509 | +| time_elapsed | 18111 | +| total_timesteps | 25618432 | +| train/ | | +| approx_kl | 0.012803034 | +| clip_fraction | 0.336 | +| clip_range | 0.0686 | +| entropy_loss | -6.24 | +| explained_variance | 0.495 | +| learning_rate | 4.39e-05 | +| loss | -0.0297 | +| n_updates | 65852 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000114 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1414 | +| iterations | 12510 | +| time_elapsed | 18113 | +| total_timesteps | 25620480 | +| train/ | | +| approx_kl | 0.0155893965 | +| clip_fraction | 0.381 | +| clip_range | 0.0686 | +| entropy_loss | -6.22 | +| explained_variance | 0.393 | +| learning_rate | 4.39e-05 | +| loss | -0.0352 | +| n_updates | 65856 | +| policy_gradient_loss | -0.0219 | +| value_loss | 0.000104 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1414 | +| iterations | 12511 | +| time_elapsed | 18114 | +| total_timesteps | 25622528 | +| train/ | | +| approx_kl | 0.013457997 | +| clip_fraction | 0.357 | +| clip_range | 0.0686 | +| entropy_loss | -6.5 | +| explained_variance | -0.131 | +| learning_rate | 4.39e-05 | +| loss | -0.0329 | +| n_updates | 65860 | +| policy_gradient_loss | -0.0199 | +| value_loss | 9.55e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1414 | +| iterations | 12512 | +| time_elapsed | 18116 | +| total_timesteps | 25624576 | +| train/ | | +| approx_kl | 0.013795298 | +| clip_fraction | 0.354 | +| clip_range | 0.0686 | +| entropy_loss | -6.19 | +| explained_variance | 0.771 | +| learning_rate | 4.39e-05 | +| loss | -0.0346 | +| n_updates | 65864 | +| policy_gradient_loss | -0.0185 | +| value_loss | 4.63e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1414 | +| iterations | 12513 | +| time_elapsed | 18117 | +| total_timesteps | 25626624 | +| train/ | | +| approx_kl | 0.016675226 | +| clip_fraction | 0.353 | +| clip_range | 0.0686 | +| entropy_loss | -5.5 | +| explained_variance | 0.768 | +| learning_rate | 4.39e-05 | +| loss | -0.0317 | +| n_updates | 65868 | +| policy_gradient_loss | -0.0195 | +| value_loss | 7.64e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1414 | +| iterations | 12514 | +| time_elapsed | 18119 | +| total_timesteps | 25628672 | +| train/ | | +| approx_kl | 0.012715394 | +| clip_fraction | 0.322 | +| clip_range | 0.0686 | +| entropy_loss | -5.99 | +| explained_variance | 0.544 | +| learning_rate | 4.39e-05 | +| loss | -0.0228 | +| n_updates | 65872 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000136 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1414 | +| iterations | 12515 | +| time_elapsed | 18120 | +| total_timesteps | 25630720 | +| train/ | | +| approx_kl | 0.015182379 | +| clip_fraction | 0.378 | +| clip_range | 0.0686 | +| entropy_loss | -6.07 | +| explained_variance | 0.468 | +| learning_rate | 4.39e-05 | +| loss | -0.0263 | +| n_updates | 65876 | +| policy_gradient_loss | -0.0182 | +| value_loss | 9.08e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1414 | +| iterations | 12516 | +| time_elapsed | 18122 | +| total_timesteps | 25632768 | +| train/ | | +| approx_kl | 0.014258638 | +| clip_fraction | 0.334 | +| clip_range | 0.0686 | +| entropy_loss | -5.44 | +| explained_variance | 0.69 | +| learning_rate | 4.39e-05 | +| loss | -0.0295 | +| n_updates | 65880 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000139 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1414 | +| iterations | 12517 | +| time_elapsed | 18123 | +| total_timesteps | 25634816 | +| train/ | | +| approx_kl | 0.01213819 | +| clip_fraction | 0.322 | +| clip_range | 0.0686 | +| entropy_loss | -6.07 | +| explained_variance | 0.495 | +| learning_rate | 4.39e-05 | +| loss | -0.0248 | +| n_updates | 65884 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000102 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1414 | +| iterations | 12518 | +| time_elapsed | 18125 | +| total_timesteps | 25636864 | +| train/ | | +| approx_kl | 0.012717841 | +| clip_fraction | 0.354 | +| clip_range | 0.0686 | +| entropy_loss | -6.09 | +| explained_variance | 0.382 | +| learning_rate | 4.39e-05 | +| loss | -0.0279 | +| n_updates | 65888 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000171 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1414 | +| iterations | 12519 | +| time_elapsed | 18126 | +| total_timesteps | 25638912 | +| train/ | | +| approx_kl | 0.016667958 | +| clip_fraction | 0.374 | +| clip_range | 0.0686 | +| entropy_loss | -6.25 | +| explained_variance | 0.079 | +| learning_rate | 4.39e-05 | +| loss | -0.0327 | +| n_updates | 65892 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000123 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1414 | +| iterations | 12520 | +| time_elapsed | 18128 | +| total_timesteps | 25640960 | +| train/ | | +| approx_kl | 0.012867898 | +| clip_fraction | 0.346 | +| clip_range | 0.0686 | +| entropy_loss | -6.01 | +| explained_variance | 0.397 | +| learning_rate | 4.39e-05 | +| loss | -0.0258 | +| n_updates | 65896 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000349 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1414 | +| iterations | 12521 | +| time_elapsed | 18129 | +| total_timesteps | 25643008 | +| train/ | | +| approx_kl | 0.015230129 | +| clip_fraction | 0.311 | +| clip_range | 0.0686 | +| entropy_loss | -5.74 | +| explained_variance | 0.255 | +| learning_rate | 4.39e-05 | +| loss | -0.0253 | +| n_updates | 65900 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000345 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1414 | +| iterations | 12522 | +| time_elapsed | 18131 | +| total_timesteps | 25645056 | +| train/ | | +| approx_kl | 0.0153973475 | +| clip_fraction | 0.377 | +| clip_range | 0.0686 | +| entropy_loss | -6.02 | +| explained_variance | 0.455 | +| learning_rate | 4.39e-05 | +| loss | -0.0386 | +| n_updates | 65904 | +| policy_gradient_loss | -0.0231 | +| value_loss | 0.000121 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1414 | +| iterations | 12523 | +| time_elapsed | 18132 | +| total_timesteps | 25647104 | +| train/ | | +| approx_kl | 0.012179223 | +| clip_fraction | 0.348 | +| clip_range | 0.0686 | +| entropy_loss | -5.43 | +| explained_variance | 0.441 | +| learning_rate | 4.39e-05 | +| loss | -0.0305 | +| n_updates | 65908 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000322 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1414 | +| iterations | 12524 | +| time_elapsed | 18134 | +| total_timesteps | 25649152 | +| train/ | | +| approx_kl | 0.015277357 | +| clip_fraction | 0.36 | +| clip_range | 0.0686 | +| entropy_loss | -5.68 | +| explained_variance | 0.00383 | +| learning_rate | 4.39e-05 | +| loss | -0.0324 | +| n_updates | 65912 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000149 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1414 | +| iterations | 12525 | +| time_elapsed | 18135 | +| total_timesteps | 25651200 | +| train/ | | +| approx_kl | 0.012918943 | +| clip_fraction | 0.394 | +| clip_range | 0.0686 | +| entropy_loss | -6.34 | +| explained_variance | 0.26 | +| learning_rate | 4.39e-05 | +| loss | -0.0346 | +| n_updates | 65916 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000188 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1414 | +| iterations | 12526 | +| time_elapsed | 18137 | +| total_timesteps | 25653248 | +| train/ | | +| approx_kl | 0.013312278 | +| clip_fraction | 0.366 | +| clip_range | 0.0686 | +| entropy_loss | -6.65 | +| explained_variance | -0.134 | +| learning_rate | 4.39e-05 | +| loss | -0.0333 | +| n_updates | 65920 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000168 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1414 | +| iterations | 12527 | +| time_elapsed | 18138 | +| total_timesteps | 25655296 | +| train/ | | +| approx_kl | 0.012675777 | +| clip_fraction | 0.337 | +| clip_range | 0.0686 | +| entropy_loss | -6 | +| explained_variance | 0.467 | +| learning_rate | 4.39e-05 | +| loss | -0.0289 | +| n_updates | 65924 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000169 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1414 | +| iterations | 12528 | +| time_elapsed | 18140 | +| total_timesteps | 25657344 | +| train/ | | +| approx_kl | 0.020799506 | +| clip_fraction | 0.347 | +| clip_range | 0.0686 | +| entropy_loss | -5.77 | +| explained_variance | 0.393 | +| learning_rate | 4.39e-05 | +| loss | -0.0316 | +| n_updates | 65928 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000175 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1414 | +| iterations | 12529 | +| time_elapsed | 18141 | +| total_timesteps | 25659392 | +| train/ | | +| approx_kl | 0.017349338 | +| clip_fraction | 0.348 | +| clip_range | 0.0686 | +| entropy_loss | -6.19 | +| explained_variance | 0.423 | +| learning_rate | 4.39e-05 | +| loss | -0.0358 | +| n_updates | 65932 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000117 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1414 | +| iterations | 12530 | +| time_elapsed | 18143 | +| total_timesteps | 25661440 | +| train/ | | +| approx_kl | 0.014300529 | +| clip_fraction | 0.366 | +| clip_range | 0.0686 | +| entropy_loss | -5.86 | +| explained_variance | 0.574 | +| learning_rate | 4.39e-05 | +| loss | -0.0362 | +| n_updates | 65936 | +| policy_gradient_loss | -0.0197 | +| value_loss | 6.64e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1414 | +| iterations | 12531 | +| time_elapsed | 18144 | +| total_timesteps | 25663488 | +| train/ | | +| approx_kl | 0.013310591 | +| clip_fraction | 0.347 | +| clip_range | 0.0686 | +| entropy_loss | -5.64 | +| explained_variance | 0.68 | +| learning_rate | 4.39e-05 | +| loss | -0.0289 | +| n_updates | 65940 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000151 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1414 | +| iterations | 12532 | +| time_elapsed | 18146 | +| total_timesteps | 25665536 | +| train/ | | +| approx_kl | 0.012607707 | +| clip_fraction | 0.369 | +| clip_range | 0.0686 | +| entropy_loss | -6.12 | +| explained_variance | 0.196 | +| learning_rate | 4.39e-05 | +| loss | -0.0361 | +| n_updates | 65944 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.00017 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1414 | +| iterations | 12533 | +| time_elapsed | 18147 | +| total_timesteps | 25667584 | +| train/ | | +| approx_kl | 0.016413819 | +| clip_fraction | 0.365 | +| clip_range | 0.0686 | +| entropy_loss | -6.24 | +| explained_variance | 0.186 | +| learning_rate | 4.39e-05 | +| loss | -0.0359 | +| n_updates | 65948 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000143 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1414 | +| iterations | 12534 | +| time_elapsed | 18149 | +| total_timesteps | 25669632 | +| train/ | | +| approx_kl | 0.019072443 | +| clip_fraction | 0.394 | +| clip_range | 0.0686 | +| entropy_loss | -5.97 | +| explained_variance | 0.415 | +| learning_rate | 4.39e-05 | +| loss | -0.0313 | +| n_updates | 65952 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000204 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1414 | +| iterations | 12535 | +| time_elapsed | 18150 | +| total_timesteps | 25671680 | +| train/ | | +| approx_kl | 0.015044051 | +| clip_fraction | 0.335 | +| clip_range | 0.0686 | +| entropy_loss | -5.26 | +| explained_variance | 0.411 | +| learning_rate | 4.39e-05 | +| loss | -0.0245 | +| n_updates | 65956 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000258 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1414 | +| iterations | 12536 | +| time_elapsed | 18152 | +| total_timesteps | 25673728 | +| train/ | | +| approx_kl | 0.016452199 | +| clip_fraction | 0.377 | +| clip_range | 0.0686 | +| entropy_loss | -5.41 | +| explained_variance | 0.711 | +| learning_rate | 4.39e-05 | +| loss | -0.0378 | +| n_updates | 65960 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000105 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1414 | +| iterations | 12537 | +| time_elapsed | 18153 | +| total_timesteps | 25675776 | +| train/ | | +| approx_kl | 0.01604636 | +| clip_fraction | 0.371 | +| clip_range | 0.0686 | +| entropy_loss | -6.4 | +| explained_variance | 0.36 | +| learning_rate | 4.39e-05 | +| loss | -0.0278 | +| n_updates | 65964 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000154 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1414 | +| iterations | 12538 | +| time_elapsed | 18155 | +| total_timesteps | 25677824 | +| train/ | | +| approx_kl | 0.012578454 | +| clip_fraction | 0.336 | +| clip_range | 0.0686 | +| entropy_loss | -5.71 | +| explained_variance | 0.427 | +| learning_rate | 4.39e-05 | +| loss | -0.0215 | +| n_updates | 65968 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.000326 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1414 | +| iterations | 12539 | +| time_elapsed | 18156 | +| total_timesteps | 25679872 | +| train/ | | +| approx_kl | 0.012841167 | +| clip_fraction | 0.339 | +| clip_range | 0.0686 | +| entropy_loss | -5.89 | +| explained_variance | 0.536 | +| learning_rate | 4.39e-05 | +| loss | -0.0273 | +| n_updates | 65972 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000164 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1414 | +| iterations | 12540 | +| time_elapsed | 18158 | +| total_timesteps | 25681920 | +| train/ | | +| approx_kl | 0.013350684 | +| clip_fraction | 0.318 | +| clip_range | 0.0686 | +| entropy_loss | -6.06 | +| explained_variance | 0.223 | +| learning_rate | 4.39e-05 | +| loss | -0.0312 | +| n_updates | 65976 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.00025 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1414 | +| iterations | 12541 | +| time_elapsed | 18159 | +| total_timesteps | 25683968 | +| train/ | | +| approx_kl | 0.013694841 | +| clip_fraction | 0.346 | +| clip_range | 0.0686 | +| entropy_loss | -6.03 | +| explained_variance | 0.306 | +| learning_rate | 4.39e-05 | +| loss | -0.0298 | +| n_updates | 65980 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.00019 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1414 | +| iterations | 12542 | +| time_elapsed | 18161 | +| total_timesteps | 25686016 | +| train/ | | +| approx_kl | 0.013595973 | +| clip_fraction | 0.367 | +| clip_range | 0.0686 | +| entropy_loss | -6.13 | +| explained_variance | 0.316 | +| learning_rate | 4.39e-05 | +| loss | -0.0309 | +| n_updates | 65984 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000286 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1414 | +| iterations | 12543 | +| time_elapsed | 18162 | +| total_timesteps | 25688064 | +| train/ | | +| approx_kl | 0.014699745 | +| clip_fraction | 0.339 | +| clip_range | 0.0686 | +| entropy_loss | -6.1 | +| explained_variance | 0.468 | +| learning_rate | 4.39e-05 | +| loss | -0.0354 | +| n_updates | 65988 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000115 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1414 | +| iterations | 12544 | +| time_elapsed | 18163 | +| total_timesteps | 25690112 | +| train/ | | +| approx_kl | 0.012951663 | +| clip_fraction | 0.351 | +| clip_range | 0.0686 | +| entropy_loss | -6.12 | +| explained_variance | -0.0826 | +| learning_rate | 4.39e-05 | +| loss | -0.0255 | +| n_updates | 65992 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000202 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1414 | +| iterations | 12545 | +| time_elapsed | 18165 | +| total_timesteps | 25692160 | +| train/ | | +| approx_kl | 0.013338369 | +| clip_fraction | 0.384 | +| clip_range | 0.0686 | +| entropy_loss | -6.15 | +| explained_variance | 0.149 | +| learning_rate | 4.39e-05 | +| loss | -0.0337 | +| n_updates | 65996 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000188 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1414 | +| iterations | 12546 | +| time_elapsed | 18166 | +| total_timesteps | 25694208 | +| train/ | | +| approx_kl | 0.015307063 | +| clip_fraction | 0.394 | +| clip_range | 0.0686 | +| entropy_loss | -6.31 | +| explained_variance | 0.42 | +| learning_rate | 4.39e-05 | +| loss | -0.0348 | +| n_updates | 66000 | +| policy_gradient_loss | -0.0219 | +| value_loss | 9.12e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1414 | +| iterations | 12547 | +| time_elapsed | 18168 | +| total_timesteps | 25696256 | +| train/ | | +| approx_kl | 0.013615541 | +| clip_fraction | 0.358 | +| clip_range | 0.0686 | +| entropy_loss | -6.54 | +| explained_variance | -0.16 | +| learning_rate | 4.39e-05 | +| loss | -0.0339 | +| n_updates | 66004 | +| policy_gradient_loss | -0.0205 | +| value_loss | 9.36e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1414 | +| iterations | 12548 | +| time_elapsed | 18169 | +| total_timesteps | 25698304 | +| train/ | | +| approx_kl | 0.013534073 | +| clip_fraction | 0.364 | +| clip_range | 0.0686 | +| entropy_loss | -6.18 | +| explained_variance | -0.0295 | +| learning_rate | 4.39e-05 | +| loss | -0.0273 | +| n_updates | 66008 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000215 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1414 | +| iterations | 12549 | +| time_elapsed | 18171 | +| total_timesteps | 25700352 | +| train/ | | +| approx_kl | 0.015911624 | +| clip_fraction | 0.371 | +| clip_range | 0.0686 | +| entropy_loss | -6.12 | +| explained_variance | 0.469 | +| learning_rate | 4.39e-05 | +| loss | -0.0306 | +| n_updates | 66012 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000119 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1414 | +| iterations | 12550 | +| time_elapsed | 18173 | +| total_timesteps | 25702400 | +| train/ | | +| approx_kl | 0.014667816 | +| clip_fraction | 0.339 | +| clip_range | 0.0686 | +| entropy_loss | -6.5 | +| explained_variance | 0.356 | +| learning_rate | 4.39e-05 | +| loss | -0.0323 | +| n_updates | 66016 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000125 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1414 | +| iterations | 12551 | +| time_elapsed | 18174 | +| total_timesteps | 25704448 | +| train/ | | +| approx_kl | 0.010204479 | +| clip_fraction | 0.339 | +| clip_range | 0.0686 | +| entropy_loss | -6.49 | +| explained_variance | 0.624 | +| learning_rate | 4.39e-05 | +| loss | -0.0308 | +| n_updates | 66020 | +| policy_gradient_loss | -0.0179 | +| value_loss | 8.44e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1414 | +| iterations | 12552 | +| time_elapsed | 18176 | +| total_timesteps | 25706496 | +| train/ | | +| approx_kl | 0.012132885 | +| clip_fraction | 0.33 | +| clip_range | 0.0686 | +| entropy_loss | -5.73 | +| explained_variance | 0.598 | +| learning_rate | 4.39e-05 | +| loss | -0.0303 | +| n_updates | 66024 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.00015 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1414 | +| iterations | 12553 | +| time_elapsed | 18177 | +| total_timesteps | 25708544 | +| train/ | | +| approx_kl | 0.014879213 | +| clip_fraction | 0.33 | +| clip_range | 0.0686 | +| entropy_loss | -5.37 | +| explained_variance | 0.507 | +| learning_rate | 4.39e-05 | +| loss | -0.0236 | +| n_updates | 66028 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000196 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1414 | +| iterations | 12554 | +| time_elapsed | 18179 | +| total_timesteps | 25710592 | +| train/ | | +| approx_kl | 0.012365435 | +| clip_fraction | 0.328 | +| clip_range | 0.0686 | +| entropy_loss | -5.67 | +| explained_variance | 0.683 | +| learning_rate | 4.39e-05 | +| loss | -0.0282 | +| n_updates | 66032 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000119 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1414 | +| iterations | 12555 | +| time_elapsed | 18180 | +| total_timesteps | 25712640 | +| train/ | | +| approx_kl | 0.015600416 | +| clip_fraction | 0.346 | +| clip_range | 0.0686 | +| entropy_loss | -6.3 | +| explained_variance | 0.0909 | +| learning_rate | 4.39e-05 | +| loss | -0.0293 | +| n_updates | 66036 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000145 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1414 | +| iterations | 12556 | +| time_elapsed | 18182 | +| total_timesteps | 25714688 | +| train/ | | +| approx_kl | 0.01414185 | +| clip_fraction | 0.356 | +| clip_range | 0.0686 | +| entropy_loss | -6.14 | +| explained_variance | 0.562 | +| learning_rate | 4.39e-05 | +| loss | -0.0333 | +| n_updates | 66040 | +| policy_gradient_loss | -0.0198 | +| value_loss | 9.97e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1414 | +| iterations | 12557 | +| time_elapsed | 18183 | +| total_timesteps | 25716736 | +| train/ | | +| approx_kl | 0.011829463 | +| clip_fraction | 0.337 | +| clip_range | 0.0686 | +| entropy_loss | -6.58 | +| explained_variance | -0.0618 | +| learning_rate | 4.39e-05 | +| loss | -0.0342 | +| n_updates | 66044 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000135 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1414 | +| iterations | 12558 | +| time_elapsed | 18185 | +| total_timesteps | 25718784 | +| train/ | | +| approx_kl | 0.01007184 | +| clip_fraction | 0.318 | +| clip_range | 0.0686 | +| entropy_loss | -6.89 | +| explained_variance | 0.141 | +| learning_rate | 4.39e-05 | +| loss | -0.0271 | +| n_updates | 66048 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.00017 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1414 | +| iterations | 12559 | +| time_elapsed | 18186 | +| total_timesteps | 25720832 | +| train/ | | +| approx_kl | 0.011024691 | +| clip_fraction | 0.289 | +| clip_range | 0.0686 | +| entropy_loss | -6.07 | +| explained_variance | 0.614 | +| learning_rate | 4.39e-05 | +| loss | -0.022 | +| n_updates | 66052 | +| policy_gradient_loss | -0.0131 | +| value_loss | 0.000187 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1414 | +| iterations | 12560 | +| time_elapsed | 18187 | +| total_timesteps | 25722880 | +| train/ | | +| approx_kl | 0.011628344 | +| clip_fraction | 0.285 | +| clip_range | 0.0686 | +| entropy_loss | -5.31 | +| explained_variance | 0.589 | +| learning_rate | 4.39e-05 | +| loss | -0.0202 | +| n_updates | 66056 | +| policy_gradient_loss | -0.013 | +| value_loss | 0.000215 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1414 | +| iterations | 12561 | +| time_elapsed | 18189 | +| total_timesteps | 25724928 | +| train/ | | +| approx_kl | 0.012421302 | +| clip_fraction | 0.325 | +| clip_range | 0.0686 | +| entropy_loss | -5.43 | +| explained_variance | 0.328 | +| learning_rate | 4.39e-05 | +| loss | -0.0234 | +| n_updates | 66060 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000402 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1414 | +| iterations | 12562 | +| time_elapsed | 18190 | +| total_timesteps | 25726976 | +| train/ | | +| approx_kl | 0.013974411 | +| clip_fraction | 0.348 | +| clip_range | 0.0686 | +| entropy_loss | -5.62 | +| explained_variance | 0.545 | +| learning_rate | 4.39e-05 | +| loss | -0.031 | +| n_updates | 66064 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000123 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1414 | +| iterations | 12563 | +| time_elapsed | 18192 | +| total_timesteps | 25729024 | +| train/ | | +| approx_kl | 0.013633385 | +| clip_fraction | 0.379 | +| clip_range | 0.0686 | +| entropy_loss | -5.98 | +| explained_variance | 0.264 | +| learning_rate | 4.39e-05 | +| loss | -0.0326 | +| n_updates | 66068 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000136 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1414 | +| iterations | 12564 | +| time_elapsed | 18193 | +| total_timesteps | 25731072 | +| train/ | | +| approx_kl | 0.015742052 | +| clip_fraction | 0.36 | +| clip_range | 0.0686 | +| entropy_loss | -6.5 | +| explained_variance | -0.0363 | +| learning_rate | 4.39e-05 | +| loss | -0.0289 | +| n_updates | 66072 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000149 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1414 | +| iterations | 12565 | +| time_elapsed | 18195 | +| total_timesteps | 25733120 | +| train/ | | +| approx_kl | 0.018225817 | +| clip_fraction | 0.363 | +| clip_range | 0.0686 | +| entropy_loss | -6.8 | +| explained_variance | -0.0259 | +| learning_rate | 4.39e-05 | +| loss | -0.0288 | +| n_updates | 66076 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.00014 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1414 | +| iterations | 12566 | +| time_elapsed | 18196 | +| total_timesteps | 25735168 | +| train/ | | +| approx_kl | 0.013689261 | +| clip_fraction | 0.366 | +| clip_range | 0.0686 | +| entropy_loss | -6.58 | +| explained_variance | 0.409 | +| learning_rate | 4.39e-05 | +| loss | -0.027 | +| n_updates | 66080 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000108 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1414 | +| iterations | 12567 | +| time_elapsed | 18198 | +| total_timesteps | 25737216 | +| train/ | | +| approx_kl | 0.013739681 | +| clip_fraction | 0.344 | +| clip_range | 0.0686 | +| entropy_loss | -5.77 | +| explained_variance | 0.458 | +| learning_rate | 4.39e-05 | +| loss | -0.0248 | +| n_updates | 66084 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000274 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1414 | +| iterations | 12568 | +| time_elapsed | 18199 | +| total_timesteps | 25739264 | +| train/ | | +| approx_kl | 0.017726827 | +| clip_fraction | 0.361 | +| clip_range | 0.0686 | +| entropy_loss | -5.94 | +| explained_variance | 0.537 | +| learning_rate | 4.39e-05 | +| loss | -0.03 | +| n_updates | 66088 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000122 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1414 | +| iterations | 12569 | +| time_elapsed | 18201 | +| total_timesteps | 25741312 | +| train/ | | +| approx_kl | 0.017773218 | +| clip_fraction | 0.385 | +| clip_range | 0.0686 | +| entropy_loss | -6.04 | +| explained_variance | -0.19 | +| learning_rate | 4.39e-05 | +| loss | -0.0315 | +| n_updates | 66092 | +| policy_gradient_loss | -0.0199 | +| value_loss | 8.61e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1414 | +| iterations | 12570 | +| time_elapsed | 18202 | +| total_timesteps | 25743360 | +| train/ | | +| approx_kl | 0.01190415 | +| clip_fraction | 0.333 | +| clip_range | 0.0686 | +| entropy_loss | -5.46 | +| explained_variance | 0.473 | +| learning_rate | 4.39e-05 | +| loss | -0.0265 | +| n_updates | 66096 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.00031 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1414 | +| iterations | 12571 | +| time_elapsed | 18204 | +| total_timesteps | 25745408 | +| train/ | | +| approx_kl | 0.014343277 | +| clip_fraction | 0.345 | +| clip_range | 0.0686 | +| entropy_loss | -5.66 | +| explained_variance | 0.57 | +| learning_rate | 4.39e-05 | +| loss | -0.0357 | +| n_updates | 66100 | +| policy_gradient_loss | -0.0207 | +| value_loss | 8.54e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1414 | +| iterations | 12572 | +| time_elapsed | 18206 | +| total_timesteps | 25747456 | +| train/ | | +| approx_kl | 0.0120695075 | +| clip_fraction | 0.343 | +| clip_range | 0.0686 | +| entropy_loss | -6.2 | +| explained_variance | 0.424 | +| learning_rate | 4.39e-05 | +| loss | -0.0295 | +| n_updates | 66104 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000212 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1414 | +| iterations | 12573 | +| time_elapsed | 18207 | +| total_timesteps | 25749504 | +| train/ | | +| approx_kl | 0.01345129 | +| clip_fraction | 0.334 | +| clip_range | 0.0686 | +| entropy_loss | -5.71 | +| explained_variance | 0.566 | +| learning_rate | 4.39e-05 | +| loss | -0.0311 | +| n_updates | 66108 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000118 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1414 | +| iterations | 12574 | +| time_elapsed | 18209 | +| total_timesteps | 25751552 | +| train/ | | +| approx_kl | 0.012904164 | +| clip_fraction | 0.334 | +| clip_range | 0.0686 | +| entropy_loss | -6.3 | +| explained_variance | 0.168 | +| learning_rate | 4.39e-05 | +| loss | -0.0252 | +| n_updates | 66112 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000337 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1414 | +| iterations | 12575 | +| time_elapsed | 18210 | +| total_timesteps | 25753600 | +| train/ | | +| approx_kl | 0.015844151 | +| clip_fraction | 0.347 | +| clip_range | 0.0686 | +| entropy_loss | -6.1 | +| explained_variance | 0.203 | +| learning_rate | 4.39e-05 | +| loss | -0.0308 | +| n_updates | 66116 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000311 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1414 | +| iterations | 12576 | +| time_elapsed | 18212 | +| total_timesteps | 25755648 | +| train/ | | +| approx_kl | 0.015669156 | +| clip_fraction | 0.355 | +| clip_range | 0.0686 | +| entropy_loss | -6.08 | +| explained_variance | 0.364 | +| learning_rate | 4.39e-05 | +| loss | -0.0319 | +| n_updates | 66120 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000224 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1414 | +| iterations | 12577 | +| time_elapsed | 18213 | +| total_timesteps | 25757696 | +| train/ | | +| approx_kl | 0.015842482 | +| clip_fraction | 0.373 | +| clip_range | 0.0686 | +| entropy_loss | -5.89 | +| explained_variance | 0.624 | +| learning_rate | 4.39e-05 | +| loss | -0.0367 | +| n_updates | 66124 | +| policy_gradient_loss | -0.0229 | +| value_loss | 8.53e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1414 | +| iterations | 12578 | +| time_elapsed | 18215 | +| total_timesteps | 25759744 | +| train/ | | +| approx_kl | 0.015256776 | +| clip_fraction | 0.351 | +| clip_range | 0.0686 | +| entropy_loss | -5.64 | +| explained_variance | 0.72 | +| learning_rate | 4.39e-05 | +| loss | -0.0351 | +| n_updates | 66128 | +| policy_gradient_loss | -0.0188 | +| value_loss | 9.37e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1414 | +| iterations | 12579 | +| time_elapsed | 18216 | +| total_timesteps | 25761792 | +| train/ | | +| approx_kl | 0.015392874 | +| clip_fraction | 0.341 | +| clip_range | 0.0686 | +| entropy_loss | -6.03 | +| explained_variance | 0.355 | +| learning_rate | 4.39e-05 | +| loss | -0.0201 | +| n_updates | 66132 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000119 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1414 | +| iterations | 12580 | +| time_elapsed | 18218 | +| total_timesteps | 25763840 | +| train/ | | +| approx_kl | 0.011637259 | +| clip_fraction | 0.331 | +| clip_range | 0.0686 | +| entropy_loss | -5.98 | +| explained_variance | 0.538 | +| learning_rate | 4.39e-05 | +| loss | -0.0279 | +| n_updates | 66136 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000109 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1414 | +| iterations | 12581 | +| time_elapsed | 18219 | +| total_timesteps | 25765888 | +| train/ | | +| approx_kl | 0.0117679 | +| clip_fraction | 0.328 | +| clip_range | 0.0686 | +| entropy_loss | -6.33 | +| explained_variance | 0.195 | +| learning_rate | 4.39e-05 | +| loss | -0.0282 | +| n_updates | 66140 | +| policy_gradient_loss | -0.0146 | +| value_loss | 0.000366 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1414 | +| iterations | 12582 | +| time_elapsed | 18221 | +| total_timesteps | 25767936 | +| train/ | | +| approx_kl | 0.014075551 | +| clip_fraction | 0.365 | +| clip_range | 0.0686 | +| entropy_loss | -5.8 | +| explained_variance | 0.685 | +| learning_rate | 4.39e-05 | +| loss | -0.0348 | +| n_updates | 66144 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000139 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1414 | +| iterations | 12583 | +| time_elapsed | 18222 | +| total_timesteps | 25769984 | +| train/ | | +| approx_kl | 0.01410022 | +| clip_fraction | 0.376 | +| clip_range | 0.0686 | +| entropy_loss | -5.94 | +| explained_variance | 0.798 | +| learning_rate | 4.39e-05 | +| loss | -0.0336 | +| n_updates | 66148 | +| policy_gradient_loss | -0.0236 | +| value_loss | 5.8e-05 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1414 | +| iterations | 12584 | +| time_elapsed | 18224 | +| total_timesteps | 25772032 | +| train/ | | +| approx_kl | 0.0149010215 | +| clip_fraction | 0.32 | +| clip_range | 0.0686 | +| entropy_loss | -5.6 | +| explained_variance | 0.476 | +| learning_rate | 4.39e-05 | +| loss | -0.0185 | +| n_updates | 66152 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000264 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1414 | +| iterations | 12585 | +| time_elapsed | 18225 | +| total_timesteps | 25774080 | +| train/ | | +| approx_kl | 0.014543892 | +| clip_fraction | 0.368 | +| clip_range | 0.0686 | +| entropy_loss | -5.93 | +| explained_variance | -0.0942 | +| learning_rate | 4.39e-05 | +| loss | -0.0347 | +| n_updates | 66156 | +| policy_gradient_loss | -0.0239 | +| value_loss | 5.78e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1414 | +| iterations | 12586 | +| time_elapsed | 18227 | +| total_timesteps | 25776128 | +| train/ | | +| approx_kl | 0.015906962 | +| clip_fraction | 0.368 | +| clip_range | 0.0686 | +| entropy_loss | -6.09 | +| explained_variance | 0.364 | +| learning_rate | 4.39e-05 | +| loss | -0.0293 | +| n_updates | 66160 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000172 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1414 | +| iterations | 12587 | +| time_elapsed | 18228 | +| total_timesteps | 25778176 | +| train/ | | +| approx_kl | 0.016898785 | +| clip_fraction | 0.383 | +| clip_range | 0.0686 | +| entropy_loss | -6.03 | +| explained_variance | 0.363 | +| learning_rate | 4.39e-05 | +| loss | -0.0351 | +| n_updates | 66164 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000125 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1414 | +| iterations | 12588 | +| time_elapsed | 18230 | +| total_timesteps | 25780224 | +| train/ | | +| approx_kl | 0.016092665 | +| clip_fraction | 0.348 | +| clip_range | 0.0686 | +| entropy_loss | -6.75 | +| explained_variance | -0.0669 | +| learning_rate | 4.39e-05 | +| loss | -0.025 | +| n_updates | 66168 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.00011 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1414 | +| iterations | 12589 | +| time_elapsed | 18231 | +| total_timesteps | 25782272 | +| train/ | | +| approx_kl | 0.0138243735 | +| clip_fraction | 0.357 | +| clip_range | 0.0686 | +| entropy_loss | -6.38 | +| explained_variance | 0.256 | +| learning_rate | 4.39e-05 | +| loss | -0.0258 | +| n_updates | 66172 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.00034 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1414 | +| iterations | 12590 | +| time_elapsed | 18233 | +| total_timesteps | 25784320 | +| train/ | | +| approx_kl | 0.014032338 | +| clip_fraction | 0.346 | +| clip_range | 0.0686 | +| entropy_loss | -6.1 | +| explained_variance | 0.161 | +| learning_rate | 4.39e-05 | +| loss | -0.0255 | +| n_updates | 66176 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000281 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1414 | +| iterations | 12591 | +| time_elapsed | 18234 | +| total_timesteps | 25786368 | +| train/ | | +| approx_kl | 0.014796535 | +| clip_fraction | 0.359 | +| clip_range | 0.0686 | +| entropy_loss | -5.7 | +| explained_variance | 0.615 | +| learning_rate | 4.39e-05 | +| loss | -0.0302 | +| n_updates | 66180 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000122 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1414 | +| iterations | 12592 | +| time_elapsed | 18236 | +| total_timesteps | 25788416 | +| train/ | | +| approx_kl | 0.017092332 | +| clip_fraction | 0.392 | +| clip_range | 0.0686 | +| entropy_loss | -5.32 | +| explained_variance | 0.639 | +| learning_rate | 4.39e-05 | +| loss | -0.0366 | +| n_updates | 66184 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.00011 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1414 | +| iterations | 12593 | +| time_elapsed | 18237 | +| total_timesteps | 25790464 | +| train/ | | +| approx_kl | 0.01611631 | +| clip_fraction | 0.344 | +| clip_range | 0.0686 | +| entropy_loss | -5.34 | +| explained_variance | 0.551 | +| learning_rate | 4.39e-05 | +| loss | -0.029 | +| n_updates | 66188 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000182 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1414 | +| iterations | 12594 | +| time_elapsed | 18239 | +| total_timesteps | 25792512 | +| train/ | | +| approx_kl | 0.01353308 | +| clip_fraction | 0.329 | +| clip_range | 0.0686 | +| entropy_loss | -5.84 | +| explained_variance | 0.309 | +| learning_rate | 4.39e-05 | +| loss | -0.0327 | +| n_updates | 66192 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000209 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1414 | +| iterations | 12595 | +| time_elapsed | 18240 | +| total_timesteps | 25794560 | +| train/ | | +| approx_kl | 0.017143564 | +| clip_fraction | 0.383 | +| clip_range | 0.0686 | +| entropy_loss | -6.35 | +| explained_variance | 0.201 | +| learning_rate | 4.39e-05 | +| loss | -0.0391 | +| n_updates | 66196 | +| policy_gradient_loss | -0.0231 | +| value_loss | 9.23e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1414 | +| iterations | 12596 | +| time_elapsed | 18242 | +| total_timesteps | 25796608 | +| train/ | | +| approx_kl | 0.017497897 | +| clip_fraction | 0.384 | +| clip_range | 0.0686 | +| entropy_loss | -5.98 | +| explained_variance | 0.408 | +| learning_rate | 4.39e-05 | +| loss | -0.0273 | +| n_updates | 66200 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000188 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1414 | +| iterations | 12597 | +| time_elapsed | 18243 | +| total_timesteps | 25798656 | +| train/ | | +| approx_kl | 0.0146496985 | +| clip_fraction | 0.368 | +| clip_range | 0.0686 | +| entropy_loss | -6.37 | +| explained_variance | 0.0999 | +| learning_rate | 4.39e-05 | +| loss | -0.0367 | +| n_updates | 66204 | +| policy_gradient_loss | -0.0218 | +| value_loss | 7.73e-05 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1414 | +| iterations | 12598 | +| time_elapsed | 18245 | +| total_timesteps | 25800704 | +| train/ | | +| approx_kl | 0.01619231 | +| clip_fraction | 0.329 | +| clip_range | 0.0686 | +| entropy_loss | -5.96 | +| explained_variance | 0.615 | +| learning_rate | 4.39e-05 | +| loss | -0.0301 | +| n_updates | 66208 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000127 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1414 | +| iterations | 12599 | +| time_elapsed | 18246 | +| total_timesteps | 25802752 | +| train/ | | +| approx_kl | 0.012210449 | +| clip_fraction | 0.327 | +| clip_range | 0.0685 | +| entropy_loss | -6.11 | +| explained_variance | 0.517 | +| learning_rate | 4.39e-05 | +| loss | -0.0313 | +| n_updates | 66212 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000141 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1414 | +| iterations | 12600 | +| time_elapsed | 18248 | +| total_timesteps | 25804800 | +| train/ | | +| approx_kl | 0.015019018 | +| clip_fraction | 0.355 | +| clip_range | 0.0685 | +| entropy_loss | -6.33 | +| explained_variance | 0.571 | +| learning_rate | 4.39e-05 | +| loss | -0.0424 | +| n_updates | 66216 | +| policy_gradient_loss | -0.0232 | +| value_loss | 4.29e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1414 | +| iterations | 12601 | +| time_elapsed | 18249 | +| total_timesteps | 25806848 | +| train/ | | +| approx_kl | 0.012689843 | +| clip_fraction | 0.356 | +| clip_range | 0.0685 | +| entropy_loss | -6.6 | +| explained_variance | 0.267 | +| learning_rate | 4.39e-05 | +| loss | -0.0329 | +| n_updates | 66220 | +| policy_gradient_loss | -0.0193 | +| value_loss | 9.39e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1414 | +| iterations | 12602 | +| time_elapsed | 18251 | +| total_timesteps | 25808896 | +| train/ | | +| approx_kl | 0.015947506 | +| clip_fraction | 0.332 | +| clip_range | 0.0685 | +| entropy_loss | -4.98 | +| explained_variance | 0.814 | +| learning_rate | 4.39e-05 | +| loss | -0.026 | +| n_updates | 66224 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000113 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1414 | +| iterations | 12603 | +| time_elapsed | 18252 | +| total_timesteps | 25810944 | +| train/ | | +| approx_kl | 0.015478204 | +| clip_fraction | 0.348 | +| clip_range | 0.0685 | +| entropy_loss | -5.55 | +| explained_variance | 0.334 | +| learning_rate | 4.39e-05 | +| loss | -0.0298 | +| n_updates | 66228 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.00018 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1414 | +| iterations | 12604 | +| time_elapsed | 18254 | +| total_timesteps | 25812992 | +| train/ | | +| approx_kl | 0.012873815 | +| clip_fraction | 0.345 | +| clip_range | 0.0685 | +| entropy_loss | -6.22 | +| explained_variance | 0.088 | +| learning_rate | 4.39e-05 | +| loss | -0.028 | +| n_updates | 66232 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000213 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1414 | +| iterations | 12605 | +| time_elapsed | 18256 | +| total_timesteps | 25815040 | +| train/ | | +| approx_kl | 0.012323445 | +| clip_fraction | 0.367 | +| clip_range | 0.0685 | +| entropy_loss | -6.44 | +| explained_variance | 0.292 | +| learning_rate | 4.39e-05 | +| loss | -0.033 | +| n_updates | 66236 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1414 | +| iterations | 12606 | +| time_elapsed | 18257 | +| total_timesteps | 25817088 | +| train/ | | +| approx_kl | 0.011130044 | +| clip_fraction | 0.361 | +| clip_range | 0.0685 | +| entropy_loss | -6.75 | +| explained_variance | 0.12 | +| learning_rate | 4.39e-05 | +| loss | -0.0331 | +| n_updates | 66240 | +| policy_gradient_loss | -0.0222 | +| value_loss | 7.21e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1414 | +| iterations | 12607 | +| time_elapsed | 18259 | +| total_timesteps | 25819136 | +| train/ | | +| approx_kl | 0.011938172 | +| clip_fraction | 0.322 | +| clip_range | 0.0685 | +| entropy_loss | -6.07 | +| explained_variance | 0.77 | +| learning_rate | 4.39e-05 | +| loss | -0.0292 | +| n_updates | 66244 | +| policy_gradient_loss | -0.0189 | +| value_loss | 5.96e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1414 | +| iterations | 12608 | +| time_elapsed | 18260 | +| total_timesteps | 25821184 | +| train/ | | +| approx_kl | 0.012282291 | +| clip_fraction | 0.336 | +| clip_range | 0.0685 | +| entropy_loss | -5.46 | +| explained_variance | 0.72 | +| learning_rate | 4.39e-05 | +| loss | -0.0252 | +| n_updates | 66248 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000109 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1414 | +| iterations | 12609 | +| time_elapsed | 18262 | +| total_timesteps | 25823232 | +| train/ | | +| approx_kl | 0.014961829 | +| clip_fraction | 0.362 | +| clip_range | 0.0685 | +| entropy_loss | -5.44 | +| explained_variance | 0.867 | +| learning_rate | 4.39e-05 | +| loss | -0.0372 | +| n_updates | 66252 | +| policy_gradient_loss | -0.0213 | +| value_loss | 4.65e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1414 | +| iterations | 12610 | +| time_elapsed | 18263 | +| total_timesteps | 25825280 | +| train/ | | +| approx_kl | 0.0106190555 | +| clip_fraction | 0.335 | +| clip_range | 0.0685 | +| entropy_loss | -6.15 | +| explained_variance | 0.053 | +| learning_rate | 4.39e-05 | +| loss | -0.0233 | +| n_updates | 66256 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000265 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1414 | +| iterations | 12611 | +| time_elapsed | 18265 | +| total_timesteps | 25827328 | +| train/ | | +| approx_kl | 0.010684697 | +| clip_fraction | 0.329 | +| clip_range | 0.0685 | +| entropy_loss | -5.77 | +| explained_variance | 0.619 | +| learning_rate | 4.39e-05 | +| loss | -0.0292 | +| n_updates | 66260 | +| policy_gradient_loss | -0.019 | +| value_loss | 9.78e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1414 | +| iterations | 12612 | +| time_elapsed | 18266 | +| total_timesteps | 25829376 | +| train/ | | +| approx_kl | 0.01236909 | +| clip_fraction | 0.334 | +| clip_range | 0.0685 | +| entropy_loss | -6.08 | +| explained_variance | 0.374 | +| learning_rate | 4.39e-05 | +| loss | -0.0263 | +| n_updates | 66264 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000172 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1414 | +| iterations | 12613 | +| time_elapsed | 18268 | +| total_timesteps | 25831424 | +| train/ | | +| approx_kl | 0.0124425255 | +| clip_fraction | 0.34 | +| clip_range | 0.0685 | +| entropy_loss | -5.89 | +| explained_variance | 0.661 | +| learning_rate | 4.39e-05 | +| loss | -0.0351 | +| n_updates | 66268 | +| policy_gradient_loss | -0.0217 | +| value_loss | 8.42e-05 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1414 | +| iterations | 12614 | +| time_elapsed | 18269 | +| total_timesteps | 25833472 | +| train/ | | +| approx_kl | 0.01020291 | +| clip_fraction | 0.323 | +| clip_range | 0.0685 | +| entropy_loss | -6.35 | +| explained_variance | 0.502 | +| learning_rate | 4.39e-05 | +| loss | -0.0261 | +| n_updates | 66272 | +| policy_gradient_loss | -0.0166 | +| value_loss | 9.71e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1414 | +| iterations | 12615 | +| time_elapsed | 18271 | +| total_timesteps | 25835520 | +| train/ | | +| approx_kl | 0.011595993 | +| clip_fraction | 0.346 | +| clip_range | 0.0685 | +| entropy_loss | -6.18 | +| explained_variance | 0.19 | +| learning_rate | 4.39e-05 | +| loss | -0.0266 | +| n_updates | 66276 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000259 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1414 | +| iterations | 12616 | +| time_elapsed | 18272 | +| total_timesteps | 25837568 | +| train/ | | +| approx_kl | 0.011802428 | +| clip_fraction | 0.348 | +| clip_range | 0.0685 | +| entropy_loss | -5.95 | +| explained_variance | 0.446 | +| learning_rate | 4.39e-05 | +| loss | -0.0302 | +| n_updates | 66280 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000316 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1413 | +| iterations | 12617 | +| time_elapsed | 18274 | +| total_timesteps | 25839616 | +| train/ | | +| approx_kl | 0.015166499 | +| clip_fraction | 0.366 | +| clip_range | 0.0685 | +| entropy_loss | -5.37 | +| explained_variance | 0.391 | +| learning_rate | 4.39e-05 | +| loss | -0.0296 | +| n_updates | 66284 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000292 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1413 | +| iterations | 12618 | +| time_elapsed | 18275 | +| total_timesteps | 25841664 | +| train/ | | +| approx_kl | 0.012277374 | +| clip_fraction | 0.362 | +| clip_range | 0.0685 | +| entropy_loss | -5.73 | +| explained_variance | 0.312 | +| learning_rate | 4.39e-05 | +| loss | -0.0301 | +| n_updates | 66288 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000332 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1413 | +| iterations | 12619 | +| time_elapsed | 18277 | +| total_timesteps | 25843712 | +| train/ | | +| approx_kl | 0.010829758 | +| clip_fraction | 0.323 | +| clip_range | 0.0685 | +| entropy_loss | -5.98 | +| explained_variance | 0.161 | +| learning_rate | 4.39e-05 | +| loss | -0.0212 | +| n_updates | 66292 | +| policy_gradient_loss | -0.0148 | +| value_loss | 0.000506 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1413 | +| iterations | 12620 | +| time_elapsed | 18278 | +| total_timesteps | 25845760 | +| train/ | | +| approx_kl | 0.011116178 | +| clip_fraction | 0.333 | +| clip_range | 0.0685 | +| entropy_loss | -5.62 | +| explained_variance | 0.454 | +| learning_rate | 4.39e-05 | +| loss | -0.0203 | +| n_updates | 66296 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.00035 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1413 | +| iterations | 12621 | +| time_elapsed | 18280 | +| total_timesteps | 25847808 | +| train/ | | +| approx_kl | 0.015417384 | +| clip_fraction | 0.379 | +| clip_range | 0.0685 | +| entropy_loss | -5.92 | +| explained_variance | 0.221 | +| learning_rate | 4.39e-05 | +| loss | -0.0371 | +| n_updates | 66300 | +| policy_gradient_loss | -0.0229 | +| value_loss | 0.000211 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1413 | +| iterations | 12622 | +| time_elapsed | 18281 | +| total_timesteps | 25849856 | +| train/ | | +| approx_kl | 0.013399897 | +| clip_fraction | 0.364 | +| clip_range | 0.0685 | +| entropy_loss | -6.51 | +| explained_variance | 0.079 | +| learning_rate | 4.39e-05 | +| loss | -0.0305 | +| n_updates | 66304 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000262 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1413 | +| iterations | 12623 | +| time_elapsed | 18283 | +| total_timesteps | 25851904 | +| train/ | | +| approx_kl | 0.010809292 | +| clip_fraction | 0.342 | +| clip_range | 0.0685 | +| entropy_loss | -6.15 | +| explained_variance | 0.481 | +| learning_rate | 4.39e-05 | +| loss | -0.032 | +| n_updates | 66308 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000223 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1413 | +| iterations | 12624 | +| time_elapsed | 18284 | +| total_timesteps | 25853952 | +| train/ | | +| approx_kl | 0.016282635 | +| clip_fraction | 0.366 | +| clip_range | 0.0685 | +| entropy_loss | -5.88 | +| explained_variance | 0.25 | +| learning_rate | 4.39e-05 | +| loss | -0.027 | +| n_updates | 66312 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000206 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1413 | +| iterations | 12625 | +| time_elapsed | 18286 | +| total_timesteps | 25856000 | +| train/ | | +| approx_kl | 0.015622662 | +| clip_fraction | 0.366 | +| clip_range | 0.0685 | +| entropy_loss | -6.33 | +| explained_variance | -0.163 | +| learning_rate | 4.39e-05 | +| loss | -0.0295 | +| n_updates | 66316 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000228 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1413 | +| iterations | 12626 | +| time_elapsed | 18287 | +| total_timesteps | 25858048 | +| train/ | | +| approx_kl | 0.012785302 | +| clip_fraction | 0.338 | +| clip_range | 0.0685 | +| entropy_loss | -6.19 | +| explained_variance | 0.498 | +| learning_rate | 4.39e-05 | +| loss | -0.0293 | +| n_updates | 66320 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000189 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1413 | +| iterations | 12627 | +| time_elapsed | 18289 | +| total_timesteps | 25860096 | +| train/ | | +| approx_kl | 0.016109312 | +| clip_fraction | 0.355 | +| clip_range | 0.0685 | +| entropy_loss | -5.95 | +| explained_variance | 0.669 | +| learning_rate | 4.39e-05 | +| loss | -0.0415 | +| n_updates | 66324 | +| policy_gradient_loss | -0.021 | +| value_loss | 7.01e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1413 | +| iterations | 12628 | +| time_elapsed | 18290 | +| total_timesteps | 25862144 | +| train/ | | +| approx_kl | 0.013653483 | +| clip_fraction | 0.316 | +| clip_range | 0.0685 | +| entropy_loss | -5.89 | +| explained_variance | 0.276 | +| learning_rate | 4.39e-05 | +| loss | -0.0266 | +| n_updates | 66328 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000241 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1413 | +| iterations | 12629 | +| time_elapsed | 18292 | +| total_timesteps | 25864192 | +| train/ | | +| approx_kl | 0.017269377 | +| clip_fraction | 0.358 | +| clip_range | 0.0685 | +| entropy_loss | -5.84 | +| explained_variance | 0.433 | +| learning_rate | 4.39e-05 | +| loss | -0.0323 | +| n_updates | 66332 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000124 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1413 | +| iterations | 12630 | +| time_elapsed | 18293 | +| total_timesteps | 25866240 | +| train/ | | +| approx_kl | 0.012903983 | +| clip_fraction | 0.344 | +| clip_range | 0.0685 | +| entropy_loss | -5.87 | +| explained_variance | 0.5 | +| learning_rate | 4.39e-05 | +| loss | -0.0261 | +| n_updates | 66336 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000183 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1413 | +| iterations | 12631 | +| time_elapsed | 18295 | +| total_timesteps | 25868288 | +| train/ | | +| approx_kl | 0.0147462785 | +| clip_fraction | 0.37 | +| clip_range | 0.0685 | +| entropy_loss | -6.04 | +| explained_variance | 0.489 | +| learning_rate | 4.39e-05 | +| loss | -0.032 | +| n_updates | 66340 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000139 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1413 | +| iterations | 12632 | +| time_elapsed | 18296 | +| total_timesteps | 25870336 | +| train/ | | +| approx_kl | 0.013901052 | +| clip_fraction | 0.359 | +| clip_range | 0.0685 | +| entropy_loss | -5.69 | +| explained_variance | 0.598 | +| learning_rate | 4.39e-05 | +| loss | -0.0304 | +| n_updates | 66344 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000108 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1413 | +| iterations | 12633 | +| time_elapsed | 18298 | +| total_timesteps | 25872384 | +| train/ | | +| approx_kl | 0.013483403 | +| clip_fraction | 0.347 | +| clip_range | 0.0685 | +| entropy_loss | -5.93 | +| explained_variance | 0.504 | +| learning_rate | 4.39e-05 | +| loss | -0.0356 | +| n_updates | 66348 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.00014 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1413 | +| iterations | 12634 | +| time_elapsed | 18300 | +| total_timesteps | 25874432 | +| train/ | | +| approx_kl | 0.015327576 | +| clip_fraction | 0.363 | +| clip_range | 0.0685 | +| entropy_loss | -5.93 | +| explained_variance | 0.39 | +| learning_rate | 4.39e-05 | +| loss | -0.0329 | +| n_updates | 66352 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000138 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1413 | +| iterations | 12635 | +| time_elapsed | 18301 | +| total_timesteps | 25876480 | +| train/ | | +| approx_kl | 0.01193551 | +| clip_fraction | 0.315 | +| clip_range | 0.0685 | +| entropy_loss | -6.03 | +| explained_variance | 0.351 | +| learning_rate | 4.39e-05 | +| loss | -0.0264 | +| n_updates | 66356 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000268 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1413 | +| iterations | 12636 | +| time_elapsed | 18303 | +| total_timesteps | 25878528 | +| train/ | | +| approx_kl | 0.01580215 | +| clip_fraction | 0.363 | +| clip_range | 0.0685 | +| entropy_loss | -5.7 | +| explained_variance | 0.621 | +| learning_rate | 4.39e-05 | +| loss | -0.0342 | +| n_updates | 66360 | +| policy_gradient_loss | -0.0222 | +| value_loss | 9.4e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1413 | +| iterations | 12637 | +| time_elapsed | 18304 | +| total_timesteps | 25880576 | +| train/ | | +| approx_kl | 0.016806703 | +| clip_fraction | 0.374 | +| clip_range | 0.0685 | +| entropy_loss | -5.95 | +| explained_variance | 0.296 | +| learning_rate | 4.39e-05 | +| loss | -0.0287 | +| n_updates | 66364 | +| policy_gradient_loss | -0.0197 | +| value_loss | 9.98e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1413 | +| iterations | 12638 | +| time_elapsed | 18306 | +| total_timesteps | 25882624 | +| train/ | | +| approx_kl | 0.011572567 | +| clip_fraction | 0.328 | +| clip_range | 0.0685 | +| entropy_loss | -6.42 | +| explained_variance | 0.174 | +| learning_rate | 4.39e-05 | +| loss | -0.0228 | +| n_updates | 66368 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.00027 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1413 | +| iterations | 12639 | +| time_elapsed | 18307 | +| total_timesteps | 25884672 | +| train/ | | +| approx_kl | 0.008890284 | +| clip_fraction | 0.321 | +| clip_range | 0.0685 | +| entropy_loss | -6.67 | +| explained_variance | 0.0101 | +| learning_rate | 4.39e-05 | +| loss | -0.0239 | +| n_updates | 66372 | +| policy_gradient_loss | -0.0147 | +| value_loss | 0.000435 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1413 | +| iterations | 12640 | +| time_elapsed | 18309 | +| total_timesteps | 25886720 | +| train/ | | +| approx_kl | 0.014461721 | +| clip_fraction | 0.364 | +| clip_range | 0.0685 | +| entropy_loss | -6.09 | +| explained_variance | 0.554 | +| learning_rate | 4.39e-05 | +| loss | -0.0328 | +| n_updates | 66376 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000134 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1413 | +| iterations | 12641 | +| time_elapsed | 18310 | +| total_timesteps | 25888768 | +| train/ | | +| approx_kl | 0.017347863 | +| clip_fraction | 0.34 | +| clip_range | 0.0685 | +| entropy_loss | -5.47 | +| explained_variance | 0.497 | +| learning_rate | 4.39e-05 | +| loss | -0.0266 | +| n_updates | 66380 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000268 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1413 | +| iterations | 12642 | +| time_elapsed | 18312 | +| total_timesteps | 25890816 | +| train/ | | +| approx_kl | 0.018565927 | +| clip_fraction | 0.383 | +| clip_range | 0.0685 | +| entropy_loss | -5.96 | +| explained_variance | 0.254 | +| learning_rate | 4.39e-05 | +| loss | -0.0311 | +| n_updates | 66384 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000179 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1413 | +| iterations | 12643 | +| time_elapsed | 18313 | +| total_timesteps | 25892864 | +| train/ | | +| approx_kl | 0.01368811 | +| clip_fraction | 0.366 | +| clip_range | 0.0685 | +| entropy_loss | -5.76 | +| explained_variance | 0.682 | +| learning_rate | 4.39e-05 | +| loss | -0.0347 | +| n_updates | 66388 | +| policy_gradient_loss | -0.023 | +| value_loss | 7.94e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1413 | +| iterations | 12644 | +| time_elapsed | 18315 | +| total_timesteps | 25894912 | +| train/ | | +| approx_kl | 0.017502772 | +| clip_fraction | 0.359 | +| clip_range | 0.0685 | +| entropy_loss | -5.4 | +| explained_variance | 0.615 | +| learning_rate | 4.39e-05 | +| loss | -0.0276 | +| n_updates | 66392 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000123 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1413 | +| iterations | 12645 | +| time_elapsed | 18316 | +| total_timesteps | 25896960 | +| train/ | | +| approx_kl | 0.014822069 | +| clip_fraction | 0.382 | +| clip_range | 0.0685 | +| entropy_loss | -6.45 | +| explained_variance | -0.298 | +| learning_rate | 4.38e-05 | +| loss | -0.041 | +| n_updates | 66396 | +| policy_gradient_loss | -0.0235 | +| value_loss | 7.04e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1413 | +| iterations | 12646 | +| time_elapsed | 18318 | +| total_timesteps | 25899008 | +| train/ | | +| approx_kl | 0.012861578 | +| clip_fraction | 0.327 | +| clip_range | 0.0685 | +| entropy_loss | -6.69 | +| explained_variance | 0.077 | +| learning_rate | 4.38e-05 | +| loss | -0.0268 | +| n_updates | 66400 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000177 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1413 | +| iterations | 12647 | +| time_elapsed | 18319 | +| total_timesteps | 25901056 | +| train/ | | +| approx_kl | 0.013610873 | +| clip_fraction | 0.349 | +| clip_range | 0.0685 | +| entropy_loss | -6.37 | +| explained_variance | 0.29 | +| learning_rate | 4.38e-05 | +| loss | -0.0285 | +| n_updates | 66404 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000131 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1413 | +| iterations | 12648 | +| time_elapsed | 18321 | +| total_timesteps | 25903104 | +| train/ | | +| approx_kl | 0.012853224 | +| clip_fraction | 0.32 | +| clip_range | 0.0685 | +| entropy_loss | -6.63 | +| explained_variance | 0.297 | +| learning_rate | 4.38e-05 | +| loss | -0.0257 | +| n_updates | 66408 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000352 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1413 | +| iterations | 12649 | +| time_elapsed | 18322 | +| total_timesteps | 25905152 | +| train/ | | +| approx_kl | 0.014036464 | +| clip_fraction | 0.34 | +| clip_range | 0.0685 | +| entropy_loss | -5.63 | +| explained_variance | 0.479 | +| learning_rate | 4.38e-05 | +| loss | -0.0349 | +| n_updates | 66412 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000247 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1413 | +| iterations | 12650 | +| time_elapsed | 18324 | +| total_timesteps | 25907200 | +| train/ | | +| approx_kl | 0.012988638 | +| clip_fraction | 0.363 | +| clip_range | 0.0685 | +| entropy_loss | -6.21 | +| explained_variance | -0.131 | +| learning_rate | 4.38e-05 | +| loss | -0.0359 | +| n_updates | 66416 | +| policy_gradient_loss | -0.0223 | +| value_loss | 0.000131 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1413 | +| iterations | 12651 | +| time_elapsed | 18325 | +| total_timesteps | 25909248 | +| train/ | | +| approx_kl | 0.015606917 | +| clip_fraction | 0.355 | +| clip_range | 0.0685 | +| entropy_loss | -5.95 | +| explained_variance | 0.465 | +| learning_rate | 4.38e-05 | +| loss | -0.0343 | +| n_updates | 66420 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000256 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1413 | +| iterations | 12652 | +| time_elapsed | 18327 | +| total_timesteps | 25911296 | +| train/ | | +| approx_kl | 0.015718058 | +| clip_fraction | 0.396 | +| clip_range | 0.0685 | +| entropy_loss | -6.27 | +| explained_variance | 0.632 | +| learning_rate | 4.38e-05 | +| loss | -0.0328 | +| n_updates | 66424 | +| policy_gradient_loss | -0.0233 | +| value_loss | 7.21e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1413 | +| iterations | 12653 | +| time_elapsed | 18328 | +| total_timesteps | 25913344 | +| train/ | | +| approx_kl | 0.01852592 | +| clip_fraction | 0.332 | +| clip_range | 0.0685 | +| entropy_loss | -6.19 | +| explained_variance | 0.415 | +| learning_rate | 4.38e-05 | +| loss | -0.028 | +| n_updates | 66428 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000203 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1413 | +| iterations | 12654 | +| time_elapsed | 18330 | +| total_timesteps | 25915392 | +| train/ | | +| approx_kl | 0.010545417 | +| clip_fraction | 0.308 | +| clip_range | 0.0685 | +| entropy_loss | -5.94 | +| explained_variance | 0.428 | +| learning_rate | 4.38e-05 | +| loss | -0.0206 | +| n_updates | 66432 | +| policy_gradient_loss | -0.0145 | +| value_loss | 0.00017 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1413 | +| iterations | 12655 | +| time_elapsed | 18331 | +| total_timesteps | 25917440 | +| train/ | | +| approx_kl | 0.016071886 | +| clip_fraction | 0.338 | +| clip_range | 0.0685 | +| entropy_loss | -5.79 | +| explained_variance | 0.523 | +| learning_rate | 4.38e-05 | +| loss | -0.0314 | +| n_updates | 66436 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.00023 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1413 | +| iterations | 12656 | +| time_elapsed | 18333 | +| total_timesteps | 25919488 | +| train/ | | +| approx_kl | 0.014534842 | +| clip_fraction | 0.392 | +| clip_range | 0.0685 | +| entropy_loss | -6.4 | +| explained_variance | 0.424 | +| learning_rate | 4.38e-05 | +| loss | -0.038 | +| n_updates | 66440 | +| policy_gradient_loss | -0.0242 | +| value_loss | 4.72e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1413 | +| iterations | 12657 | +| time_elapsed | 18334 | +| total_timesteps | 25921536 | +| train/ | | +| approx_kl | 0.01597214 | +| clip_fraction | 0.343 | +| clip_range | 0.0685 | +| entropy_loss | -6.02 | +| explained_variance | 0.436 | +| learning_rate | 4.38e-05 | +| loss | -0.0284 | +| n_updates | 66444 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000235 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1413 | +| iterations | 12658 | +| time_elapsed | 18336 | +| total_timesteps | 25923584 | +| train/ | | +| approx_kl | 0.017674282 | +| clip_fraction | 0.359 | +| clip_range | 0.0685 | +| entropy_loss | -6.33 | +| explained_variance | 0.315 | +| learning_rate | 4.38e-05 | +| loss | -0.0311 | +| n_updates | 66448 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000106 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1413 | +| iterations | 12659 | +| time_elapsed | 18337 | +| total_timesteps | 25925632 | +| train/ | | +| approx_kl | 0.01742844 | +| clip_fraction | 0.333 | +| clip_range | 0.0685 | +| entropy_loss | -6.6 | +| explained_variance | 0.324 | +| learning_rate | 4.38e-05 | +| loss | -0.0276 | +| n_updates | 66452 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000132 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1413 | +| iterations | 12660 | +| time_elapsed | 18339 | +| total_timesteps | 25927680 | +| train/ | | +| approx_kl | 0.010777535 | +| clip_fraction | 0.326 | +| clip_range | 0.0685 | +| entropy_loss | -6.38 | +| explained_variance | 0.368 | +| learning_rate | 4.38e-05 | +| loss | -0.0323 | +| n_updates | 66456 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.00023 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1413 | +| iterations | 12661 | +| time_elapsed | 18340 | +| total_timesteps | 25929728 | +| train/ | | +| approx_kl | 0.011397261 | +| clip_fraction | 0.324 | +| clip_range | 0.0685 | +| entropy_loss | -5.95 | +| explained_variance | 0.467 | +| learning_rate | 4.38e-05 | +| loss | -0.0271 | +| n_updates | 66460 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000228 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1413 | +| iterations | 12662 | +| time_elapsed | 18342 | +| total_timesteps | 25931776 | +| train/ | | +| approx_kl | 0.014154538 | +| clip_fraction | 0.363 | +| clip_range | 0.0685 | +| entropy_loss | -5.69 | +| explained_variance | 0.674 | +| learning_rate | 4.38e-05 | +| loss | -0.0332 | +| n_updates | 66464 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000119 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1413 | +| iterations | 12663 | +| time_elapsed | 18343 | +| total_timesteps | 25933824 | +| train/ | | +| approx_kl | 0.014158316 | +| clip_fraction | 0.343 | +| clip_range | 0.0685 | +| entropy_loss | -5.99 | +| explained_variance | 0.12 | +| learning_rate | 4.38e-05 | +| loss | -0.0309 | +| n_updates | 66468 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000176 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1413 | +| iterations | 12664 | +| time_elapsed | 18345 | +| total_timesteps | 25935872 | +| train/ | | +| approx_kl | 0.015459642 | +| clip_fraction | 0.368 | +| clip_range | 0.0685 | +| entropy_loss | -6.44 | +| explained_variance | -0.0691 | +| learning_rate | 4.38e-05 | +| loss | -0.0303 | +| n_updates | 66472 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000171 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1413 | +| iterations | 12665 | +| time_elapsed | 18346 | +| total_timesteps | 25937920 | +| train/ | | +| approx_kl | 0.017208576 | +| clip_fraction | 0.329 | +| clip_range | 0.0685 | +| entropy_loss | -5.84 | +| explained_variance | 0.516 | +| learning_rate | 4.38e-05 | +| loss | -0.0234 | +| n_updates | 66476 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000166 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1413 | +| iterations | 12666 | +| time_elapsed | 18348 | +| total_timesteps | 25939968 | +| train/ | | +| approx_kl | 0.01503049 | +| clip_fraction | 0.335 | +| clip_range | 0.0685 | +| entropy_loss | -5.89 | +| explained_variance | 0.452 | +| learning_rate | 4.38e-05 | +| loss | -0.0332 | +| n_updates | 66480 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.00017 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1413 | +| iterations | 12667 | +| time_elapsed | 18349 | +| total_timesteps | 25942016 | +| train/ | | +| approx_kl | 0.015627222 | +| clip_fraction | 0.375 | +| clip_range | 0.0685 | +| entropy_loss | -6.22 | +| explained_variance | 0.369 | +| learning_rate | 4.38e-05 | +| loss | -0.0362 | +| n_updates | 66484 | +| policy_gradient_loss | -0.0222 | +| value_loss | 0.000112 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1413 | +| iterations | 12668 | +| time_elapsed | 18351 | +| total_timesteps | 25944064 | +| train/ | | +| approx_kl | 0.016500868 | +| clip_fraction | 0.379 | +| clip_range | 0.0685 | +| entropy_loss | -6.2 | +| explained_variance | -0.112 | +| learning_rate | 4.38e-05 | +| loss | -0.0311 | +| n_updates | 66488 | +| policy_gradient_loss | -0.0194 | +| value_loss | 8.32e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1413 | +| iterations | 12669 | +| time_elapsed | 18352 | +| total_timesteps | 25946112 | +| train/ | | +| approx_kl | 0.015625231 | +| clip_fraction | 0.349 | +| clip_range | 0.0685 | +| entropy_loss | -5.89 | +| explained_variance | 0.381 | +| learning_rate | 4.38e-05 | +| loss | -0.0245 | +| n_updates | 66492 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.00029 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1413 | +| iterations | 12670 | +| time_elapsed | 18354 | +| total_timesteps | 25948160 | +| train/ | | +| approx_kl | 0.015885342 | +| clip_fraction | 0.384 | +| clip_range | 0.0685 | +| entropy_loss | -5.79 | +| explained_variance | 0.518 | +| learning_rate | 4.38e-05 | +| loss | -0.0338 | +| n_updates | 66496 | +| policy_gradient_loss | -0.0243 | +| value_loss | 7.34e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1413 | +| iterations | 12671 | +| time_elapsed | 18355 | +| total_timesteps | 25950208 | +| train/ | | +| approx_kl | 0.012350186 | +| clip_fraction | 0.336 | +| clip_range | 0.0685 | +| entropy_loss | -6.04 | +| explained_variance | 0.494 | +| learning_rate | 4.38e-05 | +| loss | -0.0268 | +| n_updates | 66500 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000226 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1413 | +| iterations | 12672 | +| time_elapsed | 18357 | +| total_timesteps | 25952256 | +| train/ | | +| approx_kl | 0.014681574 | +| clip_fraction | 0.325 | +| clip_range | 0.0685 | +| entropy_loss | -6.17 | +| explained_variance | 0.359 | +| learning_rate | 4.38e-05 | +| loss | -0.0293 | +| n_updates | 66504 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000268 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1413 | +| iterations | 12673 | +| time_elapsed | 18358 | +| total_timesteps | 25954304 | +| train/ | | +| approx_kl | 0.012916723 | +| clip_fraction | 0.327 | +| clip_range | 0.0685 | +| entropy_loss | -6.62 | +| explained_variance | 0.243 | +| learning_rate | 4.38e-05 | +| loss | -0.0331 | +| n_updates | 66508 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000282 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1413 | +| iterations | 12674 | +| time_elapsed | 18360 | +| total_timesteps | 25956352 | +| train/ | | +| approx_kl | 0.019147197 | +| clip_fraction | 0.354 | +| clip_range | 0.0685 | +| entropy_loss | -6.1 | +| explained_variance | 0.362 | +| learning_rate | 4.38e-05 | +| loss | -0.0331 | +| n_updates | 66512 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000139 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1413 | +| iterations | 12675 | +| time_elapsed | 18361 | +| total_timesteps | 25958400 | +| train/ | | +| approx_kl | 0.014737438 | +| clip_fraction | 0.358 | +| clip_range | 0.0685 | +| entropy_loss | -6.38 | +| explained_variance | 0.245 | +| learning_rate | 4.38e-05 | +| loss | -0.0273 | +| n_updates | 66516 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000166 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1413 | +| iterations | 12676 | +| time_elapsed | 18363 | +| total_timesteps | 25960448 | +| train/ | | +| approx_kl | 0.015559515 | +| clip_fraction | 0.341 | +| clip_range | 0.0685 | +| entropy_loss | -6.13 | +| explained_variance | 0.393 | +| learning_rate | 4.38e-05 | +| loss | -0.0278 | +| n_updates | 66520 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000332 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1413 | +| iterations | 12677 | +| time_elapsed | 18364 | +| total_timesteps | 25962496 | +| train/ | | +| approx_kl | 0.018174866 | +| clip_fraction | 0.367 | +| clip_range | 0.0685 | +| entropy_loss | -6.39 | +| explained_variance | -1.34 | +| learning_rate | 4.38e-05 | +| loss | -0.0371 | +| n_updates | 66524 | +| policy_gradient_loss | -0.024 | +| value_loss | 8.71e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1413 | +| iterations | 12678 | +| time_elapsed | 18366 | +| total_timesteps | 25964544 | +| train/ | | +| approx_kl | 0.014330793 | +| clip_fraction | 0.377 | +| clip_range | 0.0685 | +| entropy_loss | -6.44 | +| explained_variance | 0.231 | +| learning_rate | 4.38e-05 | +| loss | -0.0277 | +| n_updates | 66528 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.00018 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1413 | +| iterations | 12679 | +| time_elapsed | 18367 | +| total_timesteps | 25966592 | +| train/ | | +| approx_kl | 0.0154132685 | +| clip_fraction | 0.355 | +| clip_range | 0.0685 | +| entropy_loss | -6.4 | +| explained_variance | 0.39 | +| learning_rate | 4.38e-05 | +| loss | -0.0335 | +| n_updates | 66532 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000109 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1413 | +| iterations | 12680 | +| time_elapsed | 18369 | +| total_timesteps | 25968640 | +| train/ | | +| approx_kl | 0.016640604 | +| clip_fraction | 0.35 | +| clip_range | 0.0685 | +| entropy_loss | -5.89 | +| explained_variance | 0.648 | +| learning_rate | 4.38e-05 | +| loss | -0.0296 | +| n_updates | 66536 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000126 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1413 | +| iterations | 12681 | +| time_elapsed | 18370 | +| total_timesteps | 25970688 | +| train/ | | +| approx_kl | 0.013162947 | +| clip_fraction | 0.356 | +| clip_range | 0.0685 | +| entropy_loss | -5.83 | +| explained_variance | 0.44 | +| learning_rate | 4.38e-05 | +| loss | -0.0298 | +| n_updates | 66540 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000157 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1413 | +| iterations | 12682 | +| time_elapsed | 18372 | +| total_timesteps | 25972736 | +| train/ | | +| approx_kl | 0.01316588 | +| clip_fraction | 0.36 | +| clip_range | 0.0685 | +| entropy_loss | -6.08 | +| explained_variance | 0.579 | +| learning_rate | 4.38e-05 | +| loss | -0.0312 | +| n_updates | 66544 | +| policy_gradient_loss | -0.021 | +| value_loss | 7.98e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1413 | +| iterations | 12683 | +| time_elapsed | 18373 | +| total_timesteps | 25974784 | +| train/ | | +| approx_kl | 0.014271865 | +| clip_fraction | 0.313 | +| clip_range | 0.0685 | +| entropy_loss | -6.22 | +| explained_variance | 0.518 | +| learning_rate | 4.38e-05 | +| loss | -0.0236 | +| n_updates | 66548 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000171 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1413 | +| iterations | 12684 | +| time_elapsed | 18375 | +| total_timesteps | 25976832 | +| train/ | | +| approx_kl | 0.011085385 | +| clip_fraction | 0.328 | +| clip_range | 0.0685 | +| entropy_loss | -6.42 | +| explained_variance | 0.293 | +| learning_rate | 4.38e-05 | +| loss | -0.0296 | +| n_updates | 66552 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000151 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1413 | +| iterations | 12685 | +| time_elapsed | 18376 | +| total_timesteps | 25978880 | +| train/ | | +| approx_kl | 0.01301306 | +| clip_fraction | 0.321 | +| clip_range | 0.0685 | +| entropy_loss | -5.29 | +| explained_variance | 0.515 | +| learning_rate | 4.38e-05 | +| loss | -0.0245 | +| n_updates | 66556 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000365 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1413 | +| iterations | 12686 | +| time_elapsed | 18378 | +| total_timesteps | 25980928 | +| train/ | | +| approx_kl | 0.013134209 | +| clip_fraction | 0.327 | +| clip_range | 0.0685 | +| entropy_loss | -5.47 | +| explained_variance | 0.38 | +| learning_rate | 4.38e-05 | +| loss | -0.0281 | +| n_updates | 66560 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000354 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1413 | +| iterations | 12687 | +| time_elapsed | 18379 | +| total_timesteps | 25982976 | +| train/ | | +| approx_kl | 0.014741765 | +| clip_fraction | 0.332 | +| clip_range | 0.0685 | +| entropy_loss | -6.16 | +| explained_variance | 0.294 | +| learning_rate | 4.38e-05 | +| loss | -0.0303 | +| n_updates | 66564 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000222 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1413 | +| iterations | 12688 | +| time_elapsed | 18381 | +| total_timesteps | 25985024 | +| train/ | | +| approx_kl | 0.012285164 | +| clip_fraction | 0.349 | +| clip_range | 0.0685 | +| entropy_loss | -6.65 | +| explained_variance | 0.376 | +| learning_rate | 4.38e-05 | +| loss | -0.0276 | +| n_updates | 66568 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.00015 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1413 | +| iterations | 12689 | +| time_elapsed | 18382 | +| total_timesteps | 25987072 | +| train/ | | +| approx_kl | 0.013775222 | +| clip_fraction | 0.34 | +| clip_range | 0.0685 | +| entropy_loss | -6.45 | +| explained_variance | 0.105 | +| learning_rate | 4.38e-05 | +| loss | -0.0251 | +| n_updates | 66572 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000202 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1413 | +| iterations | 12690 | +| time_elapsed | 18384 | +| total_timesteps | 25989120 | +| train/ | | +| approx_kl | 0.013868267 | +| clip_fraction | 0.372 | +| clip_range | 0.0685 | +| entropy_loss | -6.04 | +| explained_variance | 0.411 | +| learning_rate | 4.38e-05 | +| loss | -0.0264 | +| n_updates | 66576 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000265 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1413 | +| iterations | 12691 | +| time_elapsed | 18385 | +| total_timesteps | 25991168 | +| train/ | | +| approx_kl | 0.016176902 | +| clip_fraction | 0.402 | +| clip_range | 0.0685 | +| entropy_loss | -6.09 | +| explained_variance | 0.517 | +| learning_rate | 4.38e-05 | +| loss | -0.0367 | +| n_updates | 66580 | +| policy_gradient_loss | -0.0247 | +| value_loss | 6.09e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1413 | +| iterations | 12692 | +| time_elapsed | 18387 | +| total_timesteps | 25993216 | +| train/ | | +| approx_kl | 0.015806172 | +| clip_fraction | 0.341 | +| clip_range | 0.0685 | +| entropy_loss | -6.51 | +| explained_variance | 0.306 | +| learning_rate | 4.38e-05 | +| loss | -0.0265 | +| n_updates | 66584 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000171 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1413 | +| iterations | 12693 | +| time_elapsed | 18388 | +| total_timesteps | 25995264 | +| train/ | | +| approx_kl | 0.01408523 | +| clip_fraction | 0.34 | +| clip_range | 0.0685 | +| entropy_loss | -5.73 | +| explained_variance | 0.514 | +| learning_rate | 4.38e-05 | +| loss | -0.0253 | +| n_updates | 66588 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000221 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1413 | +| iterations | 12694 | +| time_elapsed | 18390 | +| total_timesteps | 25997312 | +| train/ | | +| approx_kl | 0.012594076 | +| clip_fraction | 0.353 | +| clip_range | 0.0685 | +| entropy_loss | -6.06 | +| explained_variance | 0.434 | +| learning_rate | 4.38e-05 | +| loss | -0.0291 | +| n_updates | 66592 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000158 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1413 | +| iterations | 12695 | +| time_elapsed | 18391 | +| total_timesteps | 25999360 | +| train/ | | +| approx_kl | 0.01374862 | +| clip_fraction | 0.332 | +| clip_range | 0.0685 | +| entropy_loss | -6.01 | +| explained_variance | 0.51 | +| learning_rate | 4.38e-05 | +| loss | -0.0338 | +| n_updates | 66596 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000128 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1413 | +| iterations | 12696 | +| time_elapsed | 18393 | +| total_timesteps | 26001408 | +| train/ | | +| approx_kl | 0.012057805 | +| clip_fraction | 0.333 | +| clip_range | 0.0685 | +| entropy_loss | -5.98 | +| explained_variance | 0.437 | +| learning_rate | 4.38e-05 | +| loss | -0.0335 | +| n_updates | 66600 | +| policy_gradient_loss | -0.0145 | +| value_loss | 0.000147 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1413 | +| iterations | 12697 | +| time_elapsed | 18395 | +| total_timesteps | 26003456 | +| train/ | | +| approx_kl | 0.015188731 | +| clip_fraction | 0.361 | +| clip_range | 0.0685 | +| entropy_loss | -6.5 | +| explained_variance | 0.5 | +| learning_rate | 4.38e-05 | +| loss | -0.033 | +| n_updates | 66604 | +| policy_gradient_loss | -0.0211 | +| value_loss | 7.55e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1413 | +| iterations | 12698 | +| time_elapsed | 18396 | +| total_timesteps | 26005504 | +| train/ | | +| approx_kl | 0.014345894 | +| clip_fraction | 0.316 | +| clip_range | 0.0685 | +| entropy_loss | -6.71 | +| explained_variance | 0.0728 | +| learning_rate | 4.38e-05 | +| loss | -0.0254 | +| n_updates | 66608 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000226 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1413 | +| iterations | 12699 | +| time_elapsed | 18398 | +| total_timesteps | 26007552 | +| train/ | | +| approx_kl | 0.015985707 | +| clip_fraction | 0.34 | +| clip_range | 0.0685 | +| entropy_loss | -6.31 | +| explained_variance | 0.428 | +| learning_rate | 4.38e-05 | +| loss | -0.0313 | +| n_updates | 66612 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.00011 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1413 | +| iterations | 12700 | +| time_elapsed | 18399 | +| total_timesteps | 26009600 | +| train/ | | +| approx_kl | 0.015527446 | +| clip_fraction | 0.362 | +| clip_range | 0.0685 | +| entropy_loss | -6.33 | +| explained_variance | 0.288 | +| learning_rate | 4.38e-05 | +| loss | -0.0332 | +| n_updates | 66616 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000183 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1413 | +| iterations | 12701 | +| time_elapsed | 18401 | +| total_timesteps | 26011648 | +| train/ | | +| approx_kl | 0.012577973 | +| clip_fraction | 0.324 | +| clip_range | 0.0685 | +| entropy_loss | -6.25 | +| explained_variance | 0.483 | +| learning_rate | 4.38e-05 | +| loss | -0.0302 | +| n_updates | 66620 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000117 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1413 | +| iterations | 12702 | +| time_elapsed | 18402 | +| total_timesteps | 26013696 | +| train/ | | +| approx_kl | 0.013774581 | +| clip_fraction | 0.333 | +| clip_range | 0.0685 | +| entropy_loss | -6.02 | +| explained_variance | 0.381 | +| learning_rate | 4.38e-05 | +| loss | -0.0241 | +| n_updates | 66624 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.00023 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1413 | +| iterations | 12703 | +| time_elapsed | 18403 | +| total_timesteps | 26015744 | +| train/ | | +| approx_kl | 0.013260086 | +| clip_fraction | 0.363 | +| clip_range | 0.0685 | +| entropy_loss | -5.72 | +| explained_variance | 0.66 | +| learning_rate | 4.38e-05 | +| loss | -0.0283 | +| n_updates | 66628 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000136 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1413 | +| iterations | 12704 | +| time_elapsed | 18405 | +| total_timesteps | 26017792 | +| train/ | | +| approx_kl | 0.015409858 | +| clip_fraction | 0.384 | +| clip_range | 0.0685 | +| entropy_loss | -5.74 | +| explained_variance | 0.479 | +| learning_rate | 4.38e-05 | +| loss | -0.0362 | +| n_updates | 66632 | +| policy_gradient_loss | -0.0192 | +| value_loss | 9.09e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1413 | +| iterations | 12705 | +| time_elapsed | 18406 | +| total_timesteps | 26019840 | +| train/ | | +| approx_kl | 0.013315189 | +| clip_fraction | 0.354 | +| clip_range | 0.0685 | +| entropy_loss | -6.28 | +| explained_variance | 0.225 | +| learning_rate | 4.38e-05 | +| loss | -0.0268 | +| n_updates | 66636 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000129 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1413 | +| iterations | 12706 | +| time_elapsed | 18408 | +| total_timesteps | 26021888 | +| train/ | | +| approx_kl | 0.019576866 | +| clip_fraction | 0.344 | +| clip_range | 0.0685 | +| entropy_loss | -5.95 | +| explained_variance | 0.39 | +| learning_rate | 4.38e-05 | +| loss | -0.0278 | +| n_updates | 66640 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.00019 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1413 | +| iterations | 12707 | +| time_elapsed | 18409 | +| total_timesteps | 26023936 | +| train/ | | +| approx_kl | 0.014275579 | +| clip_fraction | 0.368 | +| clip_range | 0.0685 | +| entropy_loss | -6.34 | +| explained_variance | 0.468 | +| learning_rate | 4.38e-05 | +| loss | -0.0347 | +| n_updates | 66644 | +| policy_gradient_loss | -0.0208 | +| value_loss | 7.28e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1413 | +| iterations | 12708 | +| time_elapsed | 18411 | +| total_timesteps | 26025984 | +| train/ | | +| approx_kl | 0.016262954 | +| clip_fraction | 0.379 | +| clip_range | 0.0685 | +| entropy_loss | -5.9 | +| explained_variance | 0.536 | +| learning_rate | 4.38e-05 | +| loss | -0.0297 | +| n_updates | 66648 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000124 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1413 | +| iterations | 12709 | +| time_elapsed | 18413 | +| total_timesteps | 26028032 | +| train/ | | +| approx_kl | 0.012353402 | +| clip_fraction | 0.328 | +| clip_range | 0.0685 | +| entropy_loss | -6.21 | +| explained_variance | 0.388 | +| learning_rate | 4.38e-05 | +| loss | -0.0287 | +| n_updates | 66652 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000119 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1413 | +| iterations | 12710 | +| time_elapsed | 18414 | +| total_timesteps | 26030080 | +| train/ | | +| approx_kl | 0.011436567 | +| clip_fraction | 0.327 | +| clip_range | 0.0685 | +| entropy_loss | -6.08 | +| explained_variance | 0.386 | +| learning_rate | 4.38e-05 | +| loss | -0.0272 | +| n_updates | 66656 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000284 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1413 | +| iterations | 12711 | +| time_elapsed | 18416 | +| total_timesteps | 26032128 | +| train/ | | +| approx_kl | 0.015170615 | +| clip_fraction | 0.361 | +| clip_range | 0.0685 | +| entropy_loss | -5.88 | +| explained_variance | 0.42 | +| learning_rate | 4.38e-05 | +| loss | -0.0261 | +| n_updates | 66660 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000214 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1413 | +| iterations | 12712 | +| time_elapsed | 18417 | +| total_timesteps | 26034176 | +| train/ | | +| approx_kl | 0.01538853 | +| clip_fraction | 0.336 | +| clip_range | 0.0685 | +| entropy_loss | -5.94 | +| explained_variance | 0.361 | +| learning_rate | 4.38e-05 | +| loss | -0.0239 | +| n_updates | 66664 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000236 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1413 | +| iterations | 12713 | +| time_elapsed | 18419 | +| total_timesteps | 26036224 | +| train/ | | +| approx_kl | 0.017106336 | +| clip_fraction | 0.392 | +| clip_range | 0.0685 | +| entropy_loss | -5.76 | +| explained_variance | 0.444 | +| learning_rate | 4.38e-05 | +| loss | -0.0363 | +| n_updates | 66668 | +| policy_gradient_loss | -0.0231 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1413 | +| iterations | 12714 | +| time_elapsed | 18420 | +| total_timesteps | 26038272 | +| train/ | | +| approx_kl | 0.016711805 | +| clip_fraction | 0.379 | +| clip_range | 0.0685 | +| entropy_loss | -6.01 | +| explained_variance | 0.633 | +| learning_rate | 4.38e-05 | +| loss | -0.0322 | +| n_updates | 66672 | +| policy_gradient_loss | -0.0221 | +| value_loss | 8.41e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1413 | +| iterations | 12715 | +| time_elapsed | 18422 | +| total_timesteps | 26040320 | +| train/ | | +| approx_kl | 0.014652935 | +| clip_fraction | 0.367 | +| clip_range | 0.0685 | +| entropy_loss | -6.52 | +| explained_variance | 0.3 | +| learning_rate | 4.38e-05 | +| loss | -0.0349 | +| n_updates | 66676 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000123 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1413 | +| iterations | 12716 | +| time_elapsed | 18423 | +| total_timesteps | 26042368 | +| train/ | | +| approx_kl | 0.0148173515 | +| clip_fraction | 0.349 | +| clip_range | 0.0685 | +| entropy_loss | -5.93 | +| explained_variance | 0.426 | +| learning_rate | 4.38e-05 | +| loss | -0.0282 | +| n_updates | 66680 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000208 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1413 | +| iterations | 12717 | +| time_elapsed | 18425 | +| total_timesteps | 26044416 | +| train/ | | +| approx_kl | 0.013712206 | +| clip_fraction | 0.368 | +| clip_range | 0.0685 | +| entropy_loss | -5.92 | +| explained_variance | 0.529 | +| learning_rate | 4.38e-05 | +| loss | -0.0276 | +| n_updates | 66684 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000162 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1413 | +| iterations | 12718 | +| time_elapsed | 18427 | +| total_timesteps | 26046464 | +| train/ | | +| approx_kl | 0.018346043 | +| clip_fraction | 0.375 | +| clip_range | 0.0685 | +| entropy_loss | -6.36 | +| explained_variance | 0.00847 | +| learning_rate | 4.38e-05 | +| loss | -0.0334 | +| n_updates | 66688 | +| policy_gradient_loss | -0.0232 | +| value_loss | 7.85e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1413 | +| iterations | 12719 | +| time_elapsed | 18428 | +| total_timesteps | 26048512 | +| train/ | | +| approx_kl | 0.012780279 | +| clip_fraction | 0.333 | +| clip_range | 0.0685 | +| entropy_loss | -6.56 | +| explained_variance | 0.286 | +| learning_rate | 4.38e-05 | +| loss | -0.0299 | +| n_updates | 66692 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.00016 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1413 | +| iterations | 12720 | +| time_elapsed | 18430 | +| total_timesteps | 26050560 | +| train/ | | +| approx_kl | 0.008969823 | +| clip_fraction | 0.308 | +| clip_range | 0.0685 | +| entropy_loss | -6.68 | +| explained_variance | 0.111 | +| learning_rate | 4.38e-05 | +| loss | -0.0249 | +| n_updates | 66696 | +| policy_gradient_loss | -0.013 | +| value_loss | 0.000388 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1413 | +| iterations | 12721 | +| time_elapsed | 18431 | +| total_timesteps | 26052608 | +| train/ | | +| approx_kl | 0.011653516 | +| clip_fraction | 0.331 | +| clip_range | 0.0685 | +| entropy_loss | -6.2 | +| explained_variance | 0.567 | +| learning_rate | 4.38e-05 | +| loss | -0.0272 | +| n_updates | 66700 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000184 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1413 | +| iterations | 12722 | +| time_elapsed | 18433 | +| total_timesteps | 26054656 | +| train/ | | +| approx_kl | 0.0143178515 | +| clip_fraction | 0.334 | +| clip_range | 0.0685 | +| entropy_loss | -5.95 | +| explained_variance | 0.569 | +| learning_rate | 4.38e-05 | +| loss | -0.0328 | +| n_updates | 66704 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000182 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1413 | +| iterations | 12723 | +| time_elapsed | 18434 | +| total_timesteps | 26056704 | +| train/ | | +| approx_kl | 0.013495183 | +| clip_fraction | 0.34 | +| clip_range | 0.0685 | +| entropy_loss | -5.51 | +| explained_variance | 0.647 | +| learning_rate | 4.38e-05 | +| loss | -0.0276 | +| n_updates | 66708 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000152 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1413 | +| iterations | 12724 | +| time_elapsed | 18436 | +| total_timesteps | 26058752 | +| train/ | | +| approx_kl | 0.015084829 | +| clip_fraction | 0.391 | +| clip_range | 0.0685 | +| entropy_loss | -5.92 | +| explained_variance | 0.349 | +| learning_rate | 4.38e-05 | +| loss | -0.0334 | +| n_updates | 66712 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000168 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1413 | +| iterations | 12725 | +| time_elapsed | 18437 | +| total_timesteps | 26060800 | +| train/ | | +| approx_kl | 0.012459948 | +| clip_fraction | 0.328 | +| clip_range | 0.0685 | +| entropy_loss | -6.55 | +| explained_variance | 0.158 | +| learning_rate | 4.38e-05 | +| loss | -0.0298 | +| n_updates | 66716 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000249 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1413 | +| iterations | 12726 | +| time_elapsed | 18439 | +| total_timesteps | 26062848 | +| train/ | | +| approx_kl | 0.016743898 | +| clip_fraction | 0.374 | +| clip_range | 0.0685 | +| entropy_loss | -6.62 | +| explained_variance | 0.463 | +| learning_rate | 4.38e-05 | +| loss | -0.0331 | +| n_updates | 66720 | +| policy_gradient_loss | -0.0217 | +| value_loss | 9.05e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1413 | +| iterations | 12727 | +| time_elapsed | 18440 | +| total_timesteps | 26064896 | +| train/ | | +| approx_kl | 0.012686079 | +| clip_fraction | 0.323 | +| clip_range | 0.0685 | +| entropy_loss | -6.41 | +| explained_variance | 0.216 | +| learning_rate | 4.38e-05 | +| loss | -0.0264 | +| n_updates | 66724 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000268 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1413 | +| iterations | 12728 | +| time_elapsed | 18442 | +| total_timesteps | 26066944 | +| train/ | | +| approx_kl | 0.014672839 | +| clip_fraction | 0.366 | +| clip_range | 0.0685 | +| entropy_loss | -6.2 | +| explained_variance | 0.587 | +| learning_rate | 4.38e-05 | +| loss | -0.0323 | +| n_updates | 66728 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000108 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1413 | +| iterations | 12729 | +| time_elapsed | 18443 | +| total_timesteps | 26068992 | +| train/ | | +| approx_kl | 0.0131175285 | +| clip_fraction | 0.35 | +| clip_range | 0.0685 | +| entropy_loss | -6.47 | +| explained_variance | 0.257 | +| learning_rate | 4.38e-05 | +| loss | -0.0281 | +| n_updates | 66732 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000252 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1413 | +| iterations | 12730 | +| time_elapsed | 18445 | +| total_timesteps | 26071040 | +| train/ | | +| approx_kl | 0.012820648 | +| clip_fraction | 0.339 | +| clip_range | 0.0685 | +| entropy_loss | -5.51 | +| explained_variance | 0.389 | +| learning_rate | 4.38e-05 | +| loss | -0.02 | +| n_updates | 66736 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000474 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1413 | +| iterations | 12731 | +| time_elapsed | 18446 | +| total_timesteps | 26073088 | +| train/ | | +| approx_kl | 0.01423803 | +| clip_fraction | 0.376 | +| clip_range | 0.0685 | +| entropy_loss | -5.8 | +| explained_variance | 0.507 | +| learning_rate | 4.38e-05 | +| loss | -0.0374 | +| n_updates | 66740 | +| policy_gradient_loss | -0.0229 | +| value_loss | 0.000111 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1413 | +| iterations | 12732 | +| time_elapsed | 18448 | +| total_timesteps | 26075136 | +| train/ | | +| approx_kl | 0.0144756725 | +| clip_fraction | 0.378 | +| clip_range | 0.0685 | +| entropy_loss | -6.11 | +| explained_variance | 0.536 | +| learning_rate | 4.38e-05 | +| loss | -0.0352 | +| n_updates | 66744 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.00012 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1413 | +| iterations | 12733 | +| time_elapsed | 18449 | +| total_timesteps | 26077184 | +| train/ | | +| approx_kl | 0.01604096 | +| clip_fraction | 0.349 | +| clip_range | 0.0685 | +| entropy_loss | -5.51 | +| explained_variance | 0.527 | +| learning_rate | 4.38e-05 | +| loss | -0.0267 | +| n_updates | 66748 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000291 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1413 | +| iterations | 12734 | +| time_elapsed | 18451 | +| total_timesteps | 26079232 | +| train/ | | +| approx_kl | 0.017691374 | +| clip_fraction | 0.381 | +| clip_range | 0.0685 | +| entropy_loss | -5.64 | +| explained_variance | 0.328 | +| learning_rate | 4.38e-05 | +| loss | -0.0382 | +| n_updates | 66752 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000119 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1413 | +| iterations | 12735 | +| time_elapsed | 18452 | +| total_timesteps | 26081280 | +| train/ | | +| approx_kl | 0.01597654 | +| clip_fraction | 0.385 | +| clip_range | 0.0685 | +| entropy_loss | -6.36 | +| explained_variance | 0.31 | +| learning_rate | 4.38e-05 | +| loss | -0.0388 | +| n_updates | 66756 | +| policy_gradient_loss | -0.0221 | +| value_loss | 0.000103 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1413 | +| iterations | 12736 | +| time_elapsed | 18454 | +| total_timesteps | 26083328 | +| train/ | | +| approx_kl | 0.016738525 | +| clip_fraction | 0.356 | +| clip_range | 0.0685 | +| entropy_loss | -6.07 | +| explained_variance | 0.315 | +| learning_rate | 4.38e-05 | +| loss | -0.0278 | +| n_updates | 66760 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000203 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1413 | +| iterations | 12737 | +| time_elapsed | 18456 | +| total_timesteps | 26085376 | +| train/ | | +| approx_kl | 0.012182843 | +| clip_fraction | 0.341 | +| clip_range | 0.0685 | +| entropy_loss | -6.56 | +| explained_variance | 0.0225 | +| learning_rate | 4.38e-05 | +| loss | -0.0321 | +| n_updates | 66764 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000172 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1413 | +| iterations | 12738 | +| time_elapsed | 18457 | +| total_timesteps | 26087424 | +| train/ | | +| approx_kl | 0.018036304 | +| clip_fraction | 0.342 | +| clip_range | 0.0685 | +| entropy_loss | -6.87 | +| explained_variance | -0.102 | +| learning_rate | 4.38e-05 | +| loss | -0.0335 | +| n_updates | 66768 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000154 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1413 | +| iterations | 12739 | +| time_elapsed | 18459 | +| total_timesteps | 26089472 | +| train/ | | +| approx_kl | 0.014221996 | +| clip_fraction | 0.358 | +| clip_range | 0.0685 | +| entropy_loss | -6.46 | +| explained_variance | 0.175 | +| learning_rate | 4.38e-05 | +| loss | -0.0295 | +| n_updates | 66772 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000208 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1413 | +| iterations | 12740 | +| time_elapsed | 18460 | +| total_timesteps | 26091520 | +| train/ | | +| approx_kl | 0.015796062 | +| clip_fraction | 0.383 | +| clip_range | 0.0685 | +| entropy_loss | -6.36 | +| explained_variance | 0.576 | +| learning_rate | 4.38e-05 | +| loss | -0.0359 | +| n_updates | 66776 | +| policy_gradient_loss | -0.0256 | +| value_loss | 5.49e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1413 | +| iterations | 12741 | +| time_elapsed | 18462 | +| total_timesteps | 26093568 | +| train/ | | +| approx_kl | 0.016503403 | +| clip_fraction | 0.363 | +| clip_range | 0.0685 | +| entropy_loss | -6.59 | +| explained_variance | 0.314 | +| learning_rate | 4.38e-05 | +| loss | -0.0322 | +| n_updates | 66780 | +| policy_gradient_loss | -0.02 | +| value_loss | 9.17e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1413 | +| iterations | 12742 | +| time_elapsed | 18463 | +| total_timesteps | 26095616 | +| train/ | | +| approx_kl | 0.011695557 | +| clip_fraction | 0.317 | +| clip_range | 0.0685 | +| entropy_loss | -5.94 | +| explained_variance | 0.656 | +| learning_rate | 4.38e-05 | +| loss | -0.0286 | +| n_updates | 66784 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000109 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1413 | +| iterations | 12743 | +| time_elapsed | 18465 | +| total_timesteps | 26097664 | +| train/ | | +| approx_kl | 0.012412187 | +| clip_fraction | 0.325 | +| clip_range | 0.0685 | +| entropy_loss | -5.4 | +| explained_variance | 0.632 | +| learning_rate | 4.38e-05 | +| loss | -0.0218 | +| n_updates | 66788 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000168 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1413 | +| iterations | 12744 | +| time_elapsed | 18466 | +| total_timesteps | 26099712 | +| train/ | | +| approx_kl | 0.014805451 | +| clip_fraction | 0.367 | +| clip_range | 0.0685 | +| entropy_loss | -6.16 | +| explained_variance | 0.366 | +| learning_rate | 4.38e-05 | +| loss | -0.0305 | +| n_updates | 66792 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000116 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1413 | +| iterations | 12745 | +| time_elapsed | 18468 | +| total_timesteps | 26101760 | +| train/ | | +| approx_kl | 0.015321026 | +| clip_fraction | 0.368 | +| clip_range | 0.0685 | +| entropy_loss | -5.86 | +| explained_variance | 0.519 | +| learning_rate | 4.38e-05 | +| loss | -0.0344 | +| n_updates | 66796 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000131 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1413 | +| iterations | 12746 | +| time_elapsed | 18469 | +| total_timesteps | 26103808 | +| train/ | | +| approx_kl | 0.013881053 | +| clip_fraction | 0.355 | +| clip_range | 0.0685 | +| entropy_loss | -6.33 | +| explained_variance | 0.531 | +| learning_rate | 4.38e-05 | +| loss | -0.033 | +| n_updates | 66800 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000113 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1413 | +| iterations | 12747 | +| time_elapsed | 18471 | +| total_timesteps | 26105856 | +| train/ | | +| approx_kl | 0.013918474 | +| clip_fraction | 0.344 | +| clip_range | 0.0685 | +| entropy_loss | -6.35 | +| explained_variance | -0.0781 | +| learning_rate | 4.38e-05 | +| loss | -0.0336 | +| n_updates | 66804 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000149 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1413 | +| iterations | 12748 | +| time_elapsed | 18472 | +| total_timesteps | 26107904 | +| train/ | | +| approx_kl | 0.013236694 | +| clip_fraction | 0.369 | +| clip_range | 0.0685 | +| entropy_loss | -6.74 | +| explained_variance | 0.156 | +| learning_rate | 4.38e-05 | +| loss | -0.0331 | +| n_updates | 66808 | +| policy_gradient_loss | -0.0205 | +| value_loss | 7.55e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1413 | +| iterations | 12749 | +| time_elapsed | 18474 | +| total_timesteps | 26109952 | +| train/ | | +| approx_kl | 0.012117056 | +| clip_fraction | 0.289 | +| clip_range | 0.0685 | +| entropy_loss | -6.04 | +| explained_variance | 0.415 | +| learning_rate | 4.38e-05 | +| loss | -0.0205 | +| n_updates | 66812 | +| policy_gradient_loss | -0.0132 | +| value_loss | 0.00029 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1413 | +| iterations | 12750 | +| time_elapsed | 18475 | +| total_timesteps | 26112000 | +| train/ | | +| approx_kl | 0.010848647 | +| clip_fraction | 0.336 | +| clip_range | 0.0685 | +| entropy_loss | -6.59 | +| explained_variance | 0.49 | +| learning_rate | 4.38e-05 | +| loss | -0.0336 | +| n_updates | 66816 | +| policy_gradient_loss | -0.0215 | +| value_loss | 8.61e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1413 | +| iterations | 12751 | +| time_elapsed | 18477 | +| total_timesteps | 26114048 | +| train/ | | +| approx_kl | 0.01406331 | +| clip_fraction | 0.345 | +| clip_range | 0.0685 | +| entropy_loss | -5.62 | +| explained_variance | 0.484 | +| learning_rate | 4.38e-05 | +| loss | -0.0268 | +| n_updates | 66820 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000184 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1413 | +| iterations | 12752 | +| time_elapsed | 18478 | +| total_timesteps | 26116096 | +| train/ | | +| approx_kl | 0.015693199 | +| clip_fraction | 0.353 | +| clip_range | 0.0685 | +| entropy_loss | -5.94 | +| explained_variance | 0.653 | +| learning_rate | 4.38e-05 | +| loss | -0.0346 | +| n_updates | 66824 | +| policy_gradient_loss | -0.0205 | +| value_loss | 9.33e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1413 | +| iterations | 12753 | +| time_elapsed | 18480 | +| total_timesteps | 26118144 | +| train/ | | +| approx_kl | 0.0154725965 | +| clip_fraction | 0.35 | +| clip_range | 0.0685 | +| entropy_loss | -6.09 | +| explained_variance | 0.556 | +| learning_rate | 4.38e-05 | +| loss | -0.0358 | +| n_updates | 66828 | +| policy_gradient_loss | -0.0207 | +| value_loss | 9.17e-05 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1413 | +| iterations | 12754 | +| time_elapsed | 18481 | +| total_timesteps | 26120192 | +| train/ | | +| approx_kl | 0.01757297 | +| clip_fraction | 0.339 | +| clip_range | 0.0685 | +| entropy_loss | -5.9 | +| explained_variance | 0.807 | +| learning_rate | 4.38e-05 | +| loss | -0.0288 | +| n_updates | 66832 | +| policy_gradient_loss | -0.0191 | +| value_loss | 6.34e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1413 | +| iterations | 12755 | +| time_elapsed | 18483 | +| total_timesteps | 26122240 | +| train/ | | +| approx_kl | 0.014964079 | +| clip_fraction | 0.333 | +| clip_range | 0.0685 | +| entropy_loss | -5.55 | +| explained_variance | 0.591 | +| learning_rate | 4.38e-05 | +| loss | -0.0329 | +| n_updates | 66836 | +| policy_gradient_loss | -0.0179 | +| value_loss | 8.43e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1413 | +| iterations | 12756 | +| time_elapsed | 18484 | +| total_timesteps | 26124288 | +| train/ | | +| approx_kl | 0.015030939 | +| clip_fraction | 0.375 | +| clip_range | 0.0685 | +| entropy_loss | -6.21 | +| explained_variance | 0.474 | +| learning_rate | 4.38e-05 | +| loss | -0.0312 | +| n_updates | 66840 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000102 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1413 | +| iterations | 12757 | +| time_elapsed | 18486 | +| total_timesteps | 26126336 | +| train/ | | +| approx_kl | 0.012767418 | +| clip_fraction | 0.366 | +| clip_range | 0.0685 | +| entropy_loss | -6.61 | +| explained_variance | 0.0816 | +| learning_rate | 4.38e-05 | +| loss | -0.0332 | +| n_updates | 66844 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000126 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1413 | +| iterations | 12758 | +| time_elapsed | 18487 | +| total_timesteps | 26128384 | +| train/ | | +| approx_kl | 0.013085155 | +| clip_fraction | 0.36 | +| clip_range | 0.0685 | +| entropy_loss | -6.91 | +| explained_variance | 0.0261 | +| learning_rate | 4.38e-05 | +| loss | -0.0324 | +| n_updates | 66848 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000313 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1413 | +| iterations | 12759 | +| time_elapsed | 18489 | +| total_timesteps | 26130432 | +| train/ | | +| approx_kl | 0.018208552 | +| clip_fraction | 0.316 | +| clip_range | 0.0685 | +| entropy_loss | -6.45 | +| explained_variance | 0.21 | +| learning_rate | 4.38e-05 | +| loss | -0.03 | +| n_updates | 66852 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.00033 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1413 | +| iterations | 12760 | +| time_elapsed | 18490 | +| total_timesteps | 26132480 | +| train/ | | +| approx_kl | 0.017082764 | +| clip_fraction | 0.346 | +| clip_range | 0.0685 | +| entropy_loss | -5.51 | +| explained_variance | 0.403 | +| learning_rate | 4.38e-05 | +| loss | -0.0235 | +| n_updates | 66856 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000307 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1413 | +| iterations | 12761 | +| time_elapsed | 18492 | +| total_timesteps | 26134528 | +| train/ | | +| approx_kl | 0.015619041 | +| clip_fraction | 0.327 | +| clip_range | 0.0685 | +| entropy_loss | -5.87 | +| explained_variance | 0.442 | +| learning_rate | 4.38e-05 | +| loss | -0.0255 | +| n_updates | 66860 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000253 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1413 | +| iterations | 12762 | +| time_elapsed | 18493 | +| total_timesteps | 26136576 | +| train/ | | +| approx_kl | 0.014513841 | +| clip_fraction | 0.354 | +| clip_range | 0.0685 | +| entropy_loss | -5.98 | +| explained_variance | 0.432 | +| learning_rate | 4.38e-05 | +| loss | -0.0216 | +| n_updates | 66864 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000204 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1413 | +| iterations | 12763 | +| time_elapsed | 18495 | +| total_timesteps | 26138624 | +| train/ | | +| approx_kl | 0.015905745 | +| clip_fraction | 0.307 | +| clip_range | 0.0685 | +| entropy_loss | -5.62 | +| explained_variance | 0.402 | +| learning_rate | 4.38e-05 | +| loss | -0.0333 | +| n_updates | 66868 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000334 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1413 | +| iterations | 12764 | +| time_elapsed | 18496 | +| total_timesteps | 26140672 | +| train/ | | +| approx_kl | 0.016640104 | +| clip_fraction | 0.386 | +| clip_range | 0.0685 | +| entropy_loss | -6.06 | +| explained_variance | 0.658 | +| learning_rate | 4.38e-05 | +| loss | -0.0414 | +| n_updates | 66872 | +| policy_gradient_loss | -0.0262 | +| value_loss | 7.83e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1413 | +| iterations | 12765 | +| time_elapsed | 18498 | +| total_timesteps | 26142720 | +| train/ | | +| approx_kl | 0.015936676 | +| clip_fraction | 0.39 | +| clip_range | 0.0685 | +| entropy_loss | -6.4 | +| explained_variance | -0.149 | +| learning_rate | 4.38e-05 | +| loss | -0.0291 | +| n_updates | 66876 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000254 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1413 | +| iterations | 12766 | +| time_elapsed | 18499 | +| total_timesteps | 26144768 | +| train/ | | +| approx_kl | 0.018085187 | +| clip_fraction | 0.356 | +| clip_range | 0.0685 | +| entropy_loss | -6.54 | +| explained_variance | -0.296 | +| learning_rate | 4.38e-05 | +| loss | -0.0316 | +| n_updates | 66880 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000193 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1413 | +| iterations | 12767 | +| time_elapsed | 18501 | +| total_timesteps | 26146816 | +| train/ | | +| approx_kl | 0.015008995 | +| clip_fraction | 0.358 | +| clip_range | 0.0685 | +| entropy_loss | -6.17 | +| explained_variance | 0.27 | +| learning_rate | 4.38e-05 | +| loss | -0.0305 | +| n_updates | 66884 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000142 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1413 | +| iterations | 12768 | +| time_elapsed | 18502 | +| total_timesteps | 26148864 | +| train/ | | +| approx_kl | 0.013288272 | +| clip_fraction | 0.325 | +| clip_range | 0.0685 | +| entropy_loss | -6.25 | +| explained_variance | 0.323 | +| learning_rate | 4.38e-05 | +| loss | -0.0263 | +| n_updates | 66888 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000255 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1413 | +| iterations | 12769 | +| time_elapsed | 18504 | +| total_timesteps | 26150912 | +| train/ | | +| approx_kl | 0.013416668 | +| clip_fraction | 0.355 | +| clip_range | 0.0685 | +| entropy_loss | -5.53 | +| explained_variance | 0.272 | +| learning_rate | 4.38e-05 | +| loss | -0.0299 | +| n_updates | 66892 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000363 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1413 | +| iterations | 12770 | +| time_elapsed | 18505 | +| total_timesteps | 26152960 | +| train/ | | +| approx_kl | 0.014100545 | +| clip_fraction | 0.346 | +| clip_range | 0.0685 | +| entropy_loss | -5.63 | +| explained_variance | 0.78 | +| learning_rate | 4.38e-05 | +| loss | -0.0331 | +| n_updates | 66896 | +| policy_gradient_loss | -0.0216 | +| value_loss | 6.8e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1413 | +| iterations | 12771 | +| time_elapsed | 18507 | +| total_timesteps | 26155008 | +| train/ | | +| approx_kl | 0.012954769 | +| clip_fraction | 0.323 | +| clip_range | 0.0685 | +| entropy_loss | -5.9 | +| explained_variance | 0.525 | +| learning_rate | 4.38e-05 | +| loss | -0.0213 | +| n_updates | 66900 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000171 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1413 | +| iterations | 12772 | +| time_elapsed | 18508 | +| total_timesteps | 26157056 | +| train/ | | +| approx_kl | 0.017035475 | +| clip_fraction | 0.342 | +| clip_range | 0.0685 | +| entropy_loss | -5.89 | +| explained_variance | 0.566 | +| learning_rate | 4.38e-05 | +| loss | -0.0375 | +| n_updates | 66904 | +| policy_gradient_loss | -0.0198 | +| value_loss | 9.43e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1413 | +| iterations | 12773 | +| time_elapsed | 18510 | +| total_timesteps | 26159104 | +| train/ | | +| approx_kl | 0.014395572 | +| clip_fraction | 0.37 | +| clip_range | 0.0685 | +| entropy_loss | -6.36 | +| explained_variance | 0.252 | +| learning_rate | 4.38e-05 | +| loss | -0.0381 | +| n_updates | 66908 | +| policy_gradient_loss | -0.0228 | +| value_loss | 6.45e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1413 | +| iterations | 12774 | +| time_elapsed | 18511 | +| total_timesteps | 26161152 | +| train/ | | +| approx_kl | 0.015222507 | +| clip_fraction | 0.345 | +| clip_range | 0.0685 | +| entropy_loss | -5.79 | +| explained_variance | 0.636 | +| learning_rate | 4.38e-05 | +| loss | -0.0314 | +| n_updates | 66912 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.00017 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1413 | +| iterations | 12775 | +| time_elapsed | 18513 | +| total_timesteps | 26163200 | +| train/ | | +| approx_kl | 0.0134155145 | +| clip_fraction | 0.312 | +| clip_range | 0.0685 | +| entropy_loss | -5.92 | +| explained_variance | 0.328 | +| learning_rate | 4.38e-05 | +| loss | -0.026 | +| n_updates | 66916 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000231 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1413 | +| iterations | 12776 | +| time_elapsed | 18514 | +| total_timesteps | 26165248 | +| train/ | | +| approx_kl | 0.013630664 | +| clip_fraction | 0.358 | +| clip_range | 0.0685 | +| entropy_loss | -6.42 | +| explained_variance | 0.317 | +| learning_rate | 4.38e-05 | +| loss | -0.0317 | +| n_updates | 66920 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000168 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1413 | +| iterations | 12777 | +| time_elapsed | 18516 | +| total_timesteps | 26167296 | +| train/ | | +| approx_kl | 0.014397567 | +| clip_fraction | 0.365 | +| clip_range | 0.0685 | +| entropy_loss | -6.23 | +| explained_variance | 0.414 | +| learning_rate | 4.38e-05 | +| loss | -0.0283 | +| n_updates | 66924 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000177 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1413 | +| iterations | 12778 | +| time_elapsed | 18517 | +| total_timesteps | 26169344 | +| train/ | | +| approx_kl | 0.018137554 | +| clip_fraction | 0.371 | +| clip_range | 0.0685 | +| entropy_loss | -5.51 | +| explained_variance | 0.444 | +| learning_rate | 4.38e-05 | +| loss | -0.0264 | +| n_updates | 66928 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000191 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1413 | +| iterations | 12779 | +| time_elapsed | 18519 | +| total_timesteps | 26171392 | +| train/ | | +| approx_kl | 0.01427586 | +| clip_fraction | 0.369 | +| clip_range | 0.0685 | +| entropy_loss | -6.09 | +| explained_variance | 0.276 | +| learning_rate | 4.38e-05 | +| loss | -0.0311 | +| n_updates | 66932 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000163 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1413 | +| iterations | 12780 | +| time_elapsed | 18520 | +| total_timesteps | 26173440 | +| train/ | | +| approx_kl | 0.015315093 | +| clip_fraction | 0.335 | +| clip_range | 0.0685 | +| entropy_loss | -6.1 | +| explained_variance | 0.396 | +| learning_rate | 4.38e-05 | +| loss | -0.0264 | +| n_updates | 66936 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000187 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1413 | +| iterations | 12781 | +| time_elapsed | 18522 | +| total_timesteps | 26175488 | +| train/ | | +| approx_kl | 0.014194166 | +| clip_fraction | 0.326 | +| clip_range | 0.0685 | +| entropy_loss | -6.01 | +| explained_variance | 0.428 | +| learning_rate | 4.38e-05 | +| loss | -0.0324 | +| n_updates | 66940 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000199 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1413 | +| iterations | 12782 | +| time_elapsed | 18523 | +| total_timesteps | 26177536 | +| train/ | | +| approx_kl | 0.015063246 | +| clip_fraction | 0.365 | +| clip_range | 0.0685 | +| entropy_loss | -6.29 | +| explained_variance | -0.0596 | +| learning_rate | 4.38e-05 | +| loss | -0.0324 | +| n_updates | 66944 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000144 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1413 | +| iterations | 12783 | +| time_elapsed | 18525 | +| total_timesteps | 26179584 | +| train/ | | +| approx_kl | 0.014158479 | +| clip_fraction | 0.387 | +| clip_range | 0.0685 | +| entropy_loss | -6.43 | +| explained_variance | 0.552 | +| learning_rate | 4.38e-05 | +| loss | -0.0289 | +| n_updates | 66948 | +| policy_gradient_loss | -0.0208 | +| value_loss | 7.21e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1413 | +| iterations | 12784 | +| time_elapsed | 18526 | +| total_timesteps | 26181632 | +| train/ | | +| approx_kl | 0.01309197 | +| clip_fraction | 0.347 | +| clip_range | 0.0685 | +| entropy_loss | -5.89 | +| explained_variance | 0.732 | +| learning_rate | 4.38e-05 | +| loss | -0.0275 | +| n_updates | 66952 | +| policy_gradient_loss | -0.0181 | +| value_loss | 8.73e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1413 | +| iterations | 12785 | +| time_elapsed | 18528 | +| total_timesteps | 26183680 | +| train/ | | +| approx_kl | 0.012196985 | +| clip_fraction | 0.301 | +| clip_range | 0.0685 | +| entropy_loss | -5.6 | +| explained_variance | 0.467 | +| learning_rate | 4.38e-05 | +| loss | -0.023 | +| n_updates | 66956 | +| policy_gradient_loss | -0.0143 | +| value_loss | 0.000267 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1413 | +| iterations | 12786 | +| time_elapsed | 18529 | +| total_timesteps | 26185728 | +| train/ | | +| approx_kl | 0.013038341 | +| clip_fraction | 0.33 | +| clip_range | 0.0685 | +| entropy_loss | -5.45 | +| explained_variance | 0.648 | +| learning_rate | 4.38e-05 | +| loss | -0.023 | +| n_updates | 66960 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000172 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1413 | +| iterations | 12787 | +| time_elapsed | 18531 | +| total_timesteps | 26187776 | +| train/ | | +| approx_kl | 0.015228251 | +| clip_fraction | 0.361 | +| clip_range | 0.0685 | +| entropy_loss | -6.14 | +| explained_variance | 0.171 | +| learning_rate | 4.38e-05 | +| loss | -0.0388 | +| n_updates | 66964 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000119 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1413 | +| iterations | 12788 | +| time_elapsed | 18532 | +| total_timesteps | 26189824 | +| train/ | | +| approx_kl | 0.01362736 | +| clip_fraction | 0.368 | +| clip_range | 0.0685 | +| entropy_loss | -6.4 | +| explained_variance | 0.333 | +| learning_rate | 4.38e-05 | +| loss | -0.0318 | +| n_updates | 66968 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000124 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1413 | +| iterations | 12789 | +| time_elapsed | 18534 | +| total_timesteps | 26191872 | +| train/ | | +| approx_kl | 0.015473221 | +| clip_fraction | 0.365 | +| clip_range | 0.0685 | +| entropy_loss | -6.36 | +| explained_variance | 0.334 | +| learning_rate | 4.38e-05 | +| loss | -0.0328 | +| n_updates | 66972 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000114 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1413 | +| iterations | 12790 | +| time_elapsed | 18535 | +| total_timesteps | 26193920 | +| train/ | | +| approx_kl | 0.015393513 | +| clip_fraction | 0.35 | +| clip_range | 0.0685 | +| entropy_loss | -6.24 | +| explained_variance | 0.319 | +| learning_rate | 4.38e-05 | +| loss | -0.03 | +| n_updates | 66976 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000171 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1413 | +| iterations | 12791 | +| time_elapsed | 18537 | +| total_timesteps | 26195968 | +| train/ | | +| approx_kl | 0.01491814 | +| clip_fraction | 0.349 | +| clip_range | 0.0685 | +| entropy_loss | -6.51 | +| explained_variance | 0.382 | +| learning_rate | 4.38e-05 | +| loss | -0.0314 | +| n_updates | 66980 | +| policy_gradient_loss | -0.0189 | +| value_loss | 9.82e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1413 | +| iterations | 12792 | +| time_elapsed | 18538 | +| total_timesteps | 26198016 | +| train/ | | +| approx_kl | 0.013147341 | +| clip_fraction | 0.369 | +| clip_range | 0.0685 | +| entropy_loss | -6.26 | +| explained_variance | 0.587 | +| learning_rate | 4.38e-05 | +| loss | -0.0295 | +| n_updates | 66984 | +| policy_gradient_loss | -0.0198 | +| value_loss | 9.6e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 1413 | +| iterations | 12793 | +| time_elapsed | 18540 | +| total_timesteps | 26200064 | +| train/ | | +| approx_kl | 0.0147867445 | +| clip_fraction | 0.335 | +| clip_range | 0.0685 | +| entropy_loss | -5.37 | +| explained_variance | 0.761 | +| learning_rate | 4.38e-05 | +| loss | -0.0316 | +| n_updates | 66988 | +| policy_gradient_loss | -0.0187 | +| value_loss | 6.84e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1413 | +| iterations | 12794 | +| time_elapsed | 18541 | +| total_timesteps | 26202112 | +| train/ | | +| approx_kl | 0.012625112 | +| clip_fraction | 0.317 | +| clip_range | 0.0684 | +| entropy_loss | -5.62 | +| explained_variance | 0.7 | +| learning_rate | 4.38e-05 | +| loss | -0.0333 | +| n_updates | 66992 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000117 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.3 | +| time/ | | +| fps | 1413 | +| iterations | 12795 | +| time_elapsed | 18543 | +| total_timesteps | 26204160 | +| train/ | | +| approx_kl | 0.015286641 | +| clip_fraction | 0.352 | +| clip_range | 0.0684 | +| entropy_loss | -5.96 | +| explained_variance | 0.329 | +| learning_rate | 4.38e-05 | +| loss | -0.03 | +| n_updates | 66996 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000136 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 1413 | +| iterations | 12796 | +| time_elapsed | 18544 | +| total_timesteps | 26206208 | +| train/ | | +| approx_kl | 0.0134210205 | +| clip_fraction | 0.314 | +| clip_range | 0.0684 | +| entropy_loss | -5.75 | +| explained_variance | 0.623 | +| learning_rate | 4.38e-05 | +| loss | -0.0272 | +| n_updates | 67000 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000202 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 1413 | +| iterations | 12797 | +| time_elapsed | 18546 | +| total_timesteps | 26208256 | +| train/ | | +| approx_kl | 0.014686044 | +| clip_fraction | 0.355 | +| clip_range | 0.0684 | +| entropy_loss | -5.78 | +| explained_variance | 0.298 | +| learning_rate | 4.38e-05 | +| loss | -0.0299 | +| n_updates | 67004 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000185 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 1413 | +| iterations | 12798 | +| time_elapsed | 18547 | +| total_timesteps | 26210304 | +| train/ | | +| approx_kl | 0.015744127 | +| clip_fraction | 0.351 | +| clip_range | 0.0684 | +| entropy_loss | -6.06 | +| explained_variance | 0.376 | +| learning_rate | 4.38e-05 | +| loss | -0.0321 | +| n_updates | 67008 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000163 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 1413 | +| iterations | 12799 | +| time_elapsed | 18549 | +| total_timesteps | 26212352 | +| train/ | | +| approx_kl | 0.015814774 | +| clip_fraction | 0.38 | +| clip_range | 0.0684 | +| entropy_loss | -6.31 | +| explained_variance | 0.351 | +| learning_rate | 4.38e-05 | +| loss | -0.0304 | +| n_updates | 67012 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000121 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 1413 | +| iterations | 12800 | +| time_elapsed | 18550 | +| total_timesteps | 26214400 | +| train/ | | +| approx_kl | 0.015700752 | +| clip_fraction | 0.374 | +| clip_range | 0.0684 | +| entropy_loss | -6.5 | +| explained_variance | -0.152 | +| learning_rate | 4.38e-05 | +| loss | -0.0342 | +| n_updates | 67016 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000105 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.304 | +| time/ | | +| fps | 1413 | +| iterations | 12801 | +| time_elapsed | 18552 | +| total_timesteps | 26216448 | +| train/ | | +| approx_kl | 0.0111191515 | +| clip_fraction | 0.333 | +| clip_range | 0.0684 | +| entropy_loss | -6.53 | +| explained_variance | 0.233 | +| learning_rate | 4.38e-05 | +| loss | -0.034 | +| n_updates | 67020 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000244 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1413 | +| iterations | 12802 | +| time_elapsed | 18553 | +| total_timesteps | 26218496 | +| train/ | | +| approx_kl | 0.011594335 | +| clip_fraction | 0.331 | +| clip_range | 0.0684 | +| entropy_loss | -5.88 | +| explained_variance | 0.428 | +| learning_rate | 4.38e-05 | +| loss | -0.0332 | +| n_updates | 67024 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000267 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1413 | +| iterations | 12803 | +| time_elapsed | 18555 | +| total_timesteps | 26220544 | +| train/ | | +| approx_kl | 0.013737939 | +| clip_fraction | 0.329 | +| clip_range | 0.0684 | +| entropy_loss | -5.49 | +| explained_variance | 0.503 | +| learning_rate | 4.38e-05 | +| loss | -0.0237 | +| n_updates | 67028 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000256 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1413 | +| iterations | 12804 | +| time_elapsed | 18556 | +| total_timesteps | 26222592 | +| train/ | | +| approx_kl | 0.016352445 | +| clip_fraction | 0.347 | +| clip_range | 0.0684 | +| entropy_loss | -5.98 | +| explained_variance | 0.278 | +| learning_rate | 4.38e-05 | +| loss | -0.0335 | +| n_updates | 67032 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000223 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1413 | +| iterations | 12805 | +| time_elapsed | 18558 | +| total_timesteps | 26224640 | +| train/ | | +| approx_kl | 0.011458097 | +| clip_fraction | 0.331 | +| clip_range | 0.0684 | +| entropy_loss | -6.35 | +| explained_variance | 0.131 | +| learning_rate | 4.38e-05 | +| loss | -0.0308 | +| n_updates | 67036 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000253 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1413 | +| iterations | 12806 | +| time_elapsed | 18559 | +| total_timesteps | 26226688 | +| train/ | | +| approx_kl | 0.011037467 | +| clip_fraction | 0.344 | +| clip_range | 0.0684 | +| entropy_loss | -6.33 | +| explained_variance | 0.279 | +| learning_rate | 4.38e-05 | +| loss | -0.0256 | +| n_updates | 67040 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000298 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1413 | +| iterations | 12807 | +| time_elapsed | 18561 | +| total_timesteps | 26228736 | +| train/ | | +| approx_kl | 0.014488675 | +| clip_fraction | 0.377 | +| clip_range | 0.0684 | +| entropy_loss | -6.32 | +| explained_variance | 0.507 | +| learning_rate | 4.38e-05 | +| loss | -0.0272 | +| n_updates | 67044 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000118 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1413 | +| iterations | 12808 | +| time_elapsed | 18562 | +| total_timesteps | 26230784 | +| train/ | | +| approx_kl | 0.010729825 | +| clip_fraction | 0.33 | +| clip_range | 0.0684 | +| entropy_loss | -6.38 | +| explained_variance | 0.473 | +| learning_rate | 4.38e-05 | +| loss | -0.0302 | +| n_updates | 67048 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000203 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1413 | +| iterations | 12809 | +| time_elapsed | 18564 | +| total_timesteps | 26232832 | +| train/ | | +| approx_kl | 0.01691702 | +| clip_fraction | 0.367 | +| clip_range | 0.0684 | +| entropy_loss | -6.17 | +| explained_variance | 0.315 | +| learning_rate | 4.38e-05 | +| loss | -0.0286 | +| n_updates | 67052 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000165 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1413 | +| iterations | 12810 | +| time_elapsed | 18565 | +| total_timesteps | 26234880 | +| train/ | | +| approx_kl | 0.015666276 | +| clip_fraction | 0.365 | +| clip_range | 0.0684 | +| entropy_loss | -5.71 | +| explained_variance | 0.542 | +| learning_rate | 4.38e-05 | +| loss | -0.0292 | +| n_updates | 67056 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000132 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1413 | +| iterations | 12811 | +| time_elapsed | 18567 | +| total_timesteps | 26236928 | +| train/ | | +| approx_kl | 0.016663177 | +| clip_fraction | 0.328 | +| clip_range | 0.0684 | +| entropy_loss | -5.68 | +| explained_variance | 0.511 | +| learning_rate | 4.38e-05 | +| loss | -0.0306 | +| n_updates | 67060 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000183 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1413 | +| iterations | 12812 | +| time_elapsed | 18568 | +| total_timesteps | 26238976 | +| train/ | | +| approx_kl | 0.01514533 | +| clip_fraction | 0.357 | +| clip_range | 0.0684 | +| entropy_loss | -5.95 | +| explained_variance | 0.452 | +| learning_rate | 4.38e-05 | +| loss | -0.0333 | +| n_updates | 67064 | +| policy_gradient_loss | -0.0193 | +| value_loss | 8.67e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1413 | +| iterations | 12813 | +| time_elapsed | 18570 | +| total_timesteps | 26241024 | +| train/ | | +| approx_kl | 0.014917133 | +| clip_fraction | 0.346 | +| clip_range | 0.0684 | +| entropy_loss | -6.05 | +| explained_variance | 0.382 | +| learning_rate | 4.38e-05 | +| loss | -0.0306 | +| n_updates | 67068 | +| policy_gradient_loss | -0.0205 | +| value_loss | 9.98e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1413 | +| iterations | 12814 | +| time_elapsed | 18571 | +| total_timesteps | 26243072 | +| train/ | | +| approx_kl | 0.012675623 | +| clip_fraction | 0.318 | +| clip_range | 0.0684 | +| entropy_loss | -6.29 | +| explained_variance | 0.365 | +| learning_rate | 4.38e-05 | +| loss | -0.0272 | +| n_updates | 67072 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000134 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1413 | +| iterations | 12815 | +| time_elapsed | 18573 | +| total_timesteps | 26245120 | +| train/ | | +| approx_kl | 0.010248179 | +| clip_fraction | 0.317 | +| clip_range | 0.0684 | +| entropy_loss | -6.01 | +| explained_variance | 0.497 | +| learning_rate | 4.38e-05 | +| loss | -0.0235 | +| n_updates | 67076 | +| policy_gradient_loss | -0.0139 | +| value_loss | 0.000331 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1413 | +| iterations | 12816 | +| time_elapsed | 18574 | +| total_timesteps | 26247168 | +| train/ | | +| approx_kl | 0.01285791 | +| clip_fraction | 0.352 | +| clip_range | 0.0684 | +| entropy_loss | -6.29 | +| explained_variance | -0.156 | +| learning_rate | 4.38e-05 | +| loss | -0.0316 | +| n_updates | 67080 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000162 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1413 | +| iterations | 12817 | +| time_elapsed | 18576 | +| total_timesteps | 26249216 | +| train/ | | +| approx_kl | 0.015116543 | +| clip_fraction | 0.35 | +| clip_range | 0.0684 | +| entropy_loss | -5.58 | +| explained_variance | 0.55 | +| learning_rate | 4.38e-05 | +| loss | -0.0256 | +| n_updates | 67084 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000243 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1413 | +| iterations | 12818 | +| time_elapsed | 18577 | +| total_timesteps | 26251264 | +| train/ | | +| approx_kl | 0.012261784 | +| clip_fraction | 0.324 | +| clip_range | 0.0684 | +| entropy_loss | -5.33 | +| explained_variance | 0.356 | +| learning_rate | 4.38e-05 | +| loss | -0.0225 | +| n_updates | 67088 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000349 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1413 | +| iterations | 12819 | +| time_elapsed | 18579 | +| total_timesteps | 26253312 | +| train/ | | +| approx_kl | 0.012693092 | +| clip_fraction | 0.359 | +| clip_range | 0.0684 | +| entropy_loss | -6.2 | +| explained_variance | 0.33 | +| learning_rate | 4.38e-05 | +| loss | -0.0356 | +| n_updates | 67092 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.00014 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1413 | +| iterations | 12820 | +| time_elapsed | 18580 | +| total_timesteps | 26255360 | +| train/ | | +| approx_kl | 0.01423695 | +| clip_fraction | 0.343 | +| clip_range | 0.0684 | +| entropy_loss | -6.23 | +| explained_variance | 0.485 | +| learning_rate | 4.38e-05 | +| loss | -0.0311 | +| n_updates | 67096 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.00017 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1413 | +| iterations | 12821 | +| time_elapsed | 18582 | +| total_timesteps | 26257408 | +| train/ | | +| approx_kl | 0.010811394 | +| clip_fraction | 0.341 | +| clip_range | 0.0684 | +| entropy_loss | -6.4 | +| explained_variance | 0.364 | +| learning_rate | 4.38e-05 | +| loss | -0.027 | +| n_updates | 67100 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000284 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 1413 | +| iterations | 12822 | +| time_elapsed | 18583 | +| total_timesteps | 26259456 | +| train/ | | +| approx_kl | 0.014285663 | +| clip_fraction | 0.362 | +| clip_range | 0.0684 | +| entropy_loss | -6.47 | +| explained_variance | 0.39 | +| learning_rate | 4.38e-05 | +| loss | -0.0317 | +| n_updates | 67104 | +| policy_gradient_loss | -0.022 | +| value_loss | 9.85e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 1413 | +| iterations | 12823 | +| time_elapsed | 18585 | +| total_timesteps | 26261504 | +| train/ | | +| approx_kl | 0.013185106 | +| clip_fraction | 0.338 | +| clip_range | 0.0684 | +| entropy_loss | -6 | +| explained_variance | 0.482 | +| learning_rate | 4.38e-05 | +| loss | -0.0284 | +| n_updates | 67108 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000154 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 1413 | +| iterations | 12824 | +| time_elapsed | 18586 | +| total_timesteps | 26263552 | +| train/ | | +| approx_kl | 0.015438603 | +| clip_fraction | 0.384 | +| clip_range | 0.0684 | +| entropy_loss | -5.72 | +| explained_variance | 0.731 | +| learning_rate | 4.38e-05 | +| loss | -0.0384 | +| n_updates | 67112 | +| policy_gradient_loss | -0.0236 | +| value_loss | 6.62e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 1413 | +| iterations | 12825 | +| time_elapsed | 18588 | +| total_timesteps | 26265600 | +| train/ | | +| approx_kl | 0.014236001 | +| clip_fraction | 0.328 | +| clip_range | 0.0684 | +| entropy_loss | -6.17 | +| explained_variance | 0.3 | +| learning_rate | 4.38e-05 | +| loss | -0.0289 | +| n_updates | 67116 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.00027 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.298 | +| time/ | | +| fps | 1413 | +| iterations | 12826 | +| time_elapsed | 18589 | +| total_timesteps | 26267648 | +| train/ | | +| approx_kl | 0.013124416 | +| clip_fraction | 0.327 | +| clip_range | 0.0684 | +| entropy_loss | -5.91 | +| explained_variance | 0.326 | +| learning_rate | 4.38e-05 | +| loss | -0.0292 | +| n_updates | 67120 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000218 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.298 | +| time/ | | +| fps | 1413 | +| iterations | 12827 | +| time_elapsed | 18591 | +| total_timesteps | 26269696 | +| train/ | | +| approx_kl | 0.013558643 | +| clip_fraction | 0.351 | +| clip_range | 0.0684 | +| entropy_loss | -5.7 | +| explained_variance | 0.459 | +| learning_rate | 4.38e-05 | +| loss | -0.0337 | +| n_updates | 67124 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000162 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 1413 | +| iterations | 12828 | +| time_elapsed | 18592 | +| total_timesteps | 26271744 | +| train/ | | +| approx_kl | 0.013741912 | +| clip_fraction | 0.382 | +| clip_range | 0.0684 | +| entropy_loss | -6.27 | +| explained_variance | 0.602 | +| learning_rate | 4.38e-05 | +| loss | -0.0319 | +| n_updates | 67128 | +| policy_gradient_loss | -0.0214 | +| value_loss | 8.82e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 1413 | +| iterations | 12829 | +| time_elapsed | 18594 | +| total_timesteps | 26273792 | +| train/ | | +| approx_kl | 0.013865707 | +| clip_fraction | 0.354 | +| clip_range | 0.0684 | +| entropy_loss | -6.35 | +| explained_variance | 0.184 | +| learning_rate | 4.38e-05 | +| loss | -0.0228 | +| n_updates | 67132 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000259 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1413 | +| iterations | 12830 | +| time_elapsed | 18595 | +| total_timesteps | 26275840 | +| train/ | | +| approx_kl | 0.014120549 | +| clip_fraction | 0.373 | +| clip_range | 0.0684 | +| entropy_loss | -6.44 | +| explained_variance | -0.0555 | +| learning_rate | 4.38e-05 | +| loss | -0.0287 | +| n_updates | 67136 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000219 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1413 | +| iterations | 12831 | +| time_elapsed | 18597 | +| total_timesteps | 26277888 | +| train/ | | +| approx_kl | 0.013468274 | +| clip_fraction | 0.354 | +| clip_range | 0.0684 | +| entropy_loss | -6.23 | +| explained_variance | 0.46 | +| learning_rate | 4.38e-05 | +| loss | -0.0309 | +| n_updates | 67140 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000186 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.315 | +| time/ | | +| fps | 1412 | +| iterations | 12832 | +| time_elapsed | 18598 | +| total_timesteps | 26279936 | +| train/ | | +| approx_kl | 0.012771238 | +| clip_fraction | 0.33 | +| clip_range | 0.0684 | +| entropy_loss | -6.13 | +| explained_variance | 0.561 | +| learning_rate | 4.38e-05 | +| loss | -0.0271 | +| n_updates | 67144 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000166 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1412 | +| iterations | 12833 | +| time_elapsed | 18600 | +| total_timesteps | 26281984 | +| train/ | | +| approx_kl | 0.012689384 | +| clip_fraction | 0.339 | +| clip_range | 0.0684 | +| entropy_loss | -5.81 | +| explained_variance | 0.577 | +| learning_rate | 4.38e-05 | +| loss | -0.0225 | +| n_updates | 67148 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000141 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1412 | +| iterations | 12834 | +| time_elapsed | 18601 | +| total_timesteps | 26284032 | +| train/ | | +| approx_kl | 0.013286581 | +| clip_fraction | 0.368 | +| clip_range | 0.0684 | +| entropy_loss | -5.94 | +| explained_variance | 0.637 | +| learning_rate | 4.38e-05 | +| loss | -0.0323 | +| n_updates | 67152 | +| policy_gradient_loss | -0.0199 | +| value_loss | 9.71e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1412 | +| iterations | 12835 | +| time_elapsed | 18603 | +| total_timesteps | 26286080 | +| train/ | | +| approx_kl | 0.018091213 | +| clip_fraction | 0.344 | +| clip_range | 0.0684 | +| entropy_loss | -5.98 | +| explained_variance | 0.529 | +| learning_rate | 4.38e-05 | +| loss | -0.0306 | +| n_updates | 67156 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000152 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1412 | +| iterations | 12836 | +| time_elapsed | 18604 | +| total_timesteps | 26288128 | +| train/ | | +| approx_kl | 0.015592672 | +| clip_fraction | 0.365 | +| clip_range | 0.0684 | +| entropy_loss | -6.26 | +| explained_variance | 0.0343 | +| learning_rate | 4.38e-05 | +| loss | -0.0335 | +| n_updates | 67160 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000183 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1412 | +| iterations | 12837 | +| time_elapsed | 18606 | +| total_timesteps | 26290176 | +| train/ | | +| approx_kl | 0.013730885 | +| clip_fraction | 0.341 | +| clip_range | 0.0684 | +| entropy_loss | -5.92 | +| explained_variance | 0.326 | +| learning_rate | 4.38e-05 | +| loss | -0.0352 | +| n_updates | 67164 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000226 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1412 | +| iterations | 12838 | +| time_elapsed | 18607 | +| total_timesteps | 26292224 | +| train/ | | +| approx_kl | 0.012855123 | +| clip_fraction | 0.345 | +| clip_range | 0.0684 | +| entropy_loss | -6.32 | +| explained_variance | 0.325 | +| learning_rate | 4.38e-05 | +| loss | -0.0256 | +| n_updates | 67168 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000229 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.315 | +| time/ | | +| fps | 1412 | +| iterations | 12839 | +| time_elapsed | 18609 | +| total_timesteps | 26294272 | +| train/ | | +| approx_kl | 0.013448015 | +| clip_fraction | 0.335 | +| clip_range | 0.0684 | +| entropy_loss | -5.91 | +| explained_variance | 0.149 | +| learning_rate | 4.38e-05 | +| loss | -0.0286 | +| n_updates | 67172 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000268 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.315 | +| time/ | | +| fps | 1412 | +| iterations | 12840 | +| time_elapsed | 18611 | +| total_timesteps | 26296320 | +| train/ | | +| approx_kl | 0.012395615 | +| clip_fraction | 0.338 | +| clip_range | 0.0684 | +| entropy_loss | -5.54 | +| explained_variance | 0.715 | +| learning_rate | 4.38e-05 | +| loss | -0.0292 | +| n_updates | 67176 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000121 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1412 | +| iterations | 12841 | +| time_elapsed | 18612 | +| total_timesteps | 26298368 | +| train/ | | +| approx_kl | 0.01667481 | +| clip_fraction | 0.375 | +| clip_range | 0.0684 | +| entropy_loss | -5.97 | +| explained_variance | -0.402 | +| learning_rate | 4.38e-05 | +| loss | -0.0295 | +| n_updates | 67180 | +| policy_gradient_loss | -0.0228 | +| value_loss | 9.32e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1412 | +| iterations | 12842 | +| time_elapsed | 18614 | +| total_timesteps | 26300416 | +| train/ | | +| approx_kl | 0.014074361 | +| clip_fraction | 0.349 | +| clip_range | 0.0684 | +| entropy_loss | -6.12 | +| explained_variance | 0.278 | +| learning_rate | 4.38e-05 | +| loss | -0.0314 | +| n_updates | 67184 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000136 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1412 | +| iterations | 12843 | +| time_elapsed | 18615 | +| total_timesteps | 26302464 | +| train/ | | +| approx_kl | 0.016062409 | +| clip_fraction | 0.35 | +| clip_range | 0.0684 | +| entropy_loss | -6.37 | +| explained_variance | -0.147 | +| learning_rate | 4.38e-05 | +| loss | -0.0253 | +| n_updates | 67188 | +| policy_gradient_loss | -0.0189 | +| value_loss | 9.45e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1412 | +| iterations | 12844 | +| time_elapsed | 18617 | +| total_timesteps | 26304512 | +| train/ | | +| approx_kl | 0.0129895685 | +| clip_fraction | 0.329 | +| clip_range | 0.0684 | +| entropy_loss | -6.39 | +| explained_variance | 0.342 | +| learning_rate | 4.38e-05 | +| loss | -0.0265 | +| n_updates | 67192 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000183 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1412 | +| iterations | 12845 | +| time_elapsed | 18618 | +| total_timesteps | 26306560 | +| train/ | | +| approx_kl | 0.012988979 | +| clip_fraction | 0.348 | +| clip_range | 0.0684 | +| entropy_loss | -5.56 | +| explained_variance | 0.527 | +| learning_rate | 4.38e-05 | +| loss | -0.0286 | +| n_updates | 67196 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000163 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1412 | +| iterations | 12846 | +| time_elapsed | 18620 | +| total_timesteps | 26308608 | +| train/ | | +| approx_kl | 0.012733461 | +| clip_fraction | 0.363 | +| clip_range | 0.0684 | +| entropy_loss | -6.14 | +| explained_variance | 0.441 | +| learning_rate | 4.38e-05 | +| loss | -0.0313 | +| n_updates | 67200 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000187 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1412 | +| iterations | 12847 | +| time_elapsed | 18621 | +| total_timesteps | 26310656 | +| train/ | | +| approx_kl | 0.013624336 | +| clip_fraction | 0.372 | +| clip_range | 0.0684 | +| entropy_loss | -6.21 | +| explained_variance | 0.468 | +| learning_rate | 4.38e-05 | +| loss | -0.0341 | +| n_updates | 67204 | +| policy_gradient_loss | -0.0218 | +| value_loss | 8.05e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1412 | +| iterations | 12848 | +| time_elapsed | 18623 | +| total_timesteps | 26312704 | +| train/ | | +| approx_kl | 0.011961111 | +| clip_fraction | 0.344 | +| clip_range | 0.0684 | +| entropy_loss | -6.11 | +| explained_variance | 0.618 | +| learning_rate | 4.38e-05 | +| loss | -0.0334 | +| n_updates | 67208 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000109 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1412 | +| iterations | 12849 | +| time_elapsed | 18624 | +| total_timesteps | 26314752 | +| train/ | | +| approx_kl | 0.01003071 | +| clip_fraction | 0.303 | +| clip_range | 0.0684 | +| entropy_loss | -6.08 | +| explained_variance | 0.219 | +| learning_rate | 4.38e-05 | +| loss | -0.0284 | +| n_updates | 67212 | +| policy_gradient_loss | -0.014 | +| value_loss | 0.000251 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1412 | +| iterations | 12850 | +| time_elapsed | 18626 | +| total_timesteps | 26316800 | +| train/ | | +| approx_kl | 0.012333337 | +| clip_fraction | 0.351 | +| clip_range | 0.0684 | +| entropy_loss | -5.88 | +| explained_variance | 0.31 | +| learning_rate | 4.38e-05 | +| loss | -0.0329 | +| n_updates | 67216 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000301 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1412 | +| iterations | 12851 | +| time_elapsed | 18627 | +| total_timesteps | 26318848 | +| train/ | | +| approx_kl | 0.013364391 | +| clip_fraction | 0.379 | +| clip_range | 0.0684 | +| entropy_loss | -6.32 | +| explained_variance | 0.411 | +| learning_rate | 4.37e-05 | +| loss | -0.0281 | +| n_updates | 67220 | +| policy_gradient_loss | -0.0217 | +| value_loss | 9.3e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1412 | +| iterations | 12852 | +| time_elapsed | 18629 | +| total_timesteps | 26320896 | +| train/ | | +| approx_kl | 0.011835637 | +| clip_fraction | 0.335 | +| clip_range | 0.0684 | +| entropy_loss | -6.35 | +| explained_variance | 0.488 | +| learning_rate | 4.37e-05 | +| loss | -0.0307 | +| n_updates | 67224 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000154 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1412 | +| iterations | 12853 | +| time_elapsed | 18630 | +| total_timesteps | 26322944 | +| train/ | | +| approx_kl | 0.01473463 | +| clip_fraction | 0.343 | +| clip_range | 0.0684 | +| entropy_loss | -6.23 | +| explained_variance | 0.331 | +| learning_rate | 4.37e-05 | +| loss | -0.0251 | +| n_updates | 67228 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000145 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1412 | +| iterations | 12854 | +| time_elapsed | 18632 | +| total_timesteps | 26324992 | +| train/ | | +| approx_kl | 0.012682231 | +| clip_fraction | 0.345 | +| clip_range | 0.0684 | +| entropy_loss | -5.78 | +| explained_variance | 0.483 | +| learning_rate | 4.37e-05 | +| loss | -0.0213 | +| n_updates | 67232 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.00022 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1412 | +| iterations | 12855 | +| time_elapsed | 18633 | +| total_timesteps | 26327040 | +| train/ | | +| approx_kl | 0.014291121 | +| clip_fraction | 0.345 | +| clip_range | 0.0684 | +| entropy_loss | -5.93 | +| explained_variance | 0.197 | +| learning_rate | 4.37e-05 | +| loss | -0.0264 | +| n_updates | 67236 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000448 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1412 | +| iterations | 12856 | +| time_elapsed | 18635 | +| total_timesteps | 26329088 | +| train/ | | +| approx_kl | 0.0145722125 | +| clip_fraction | 0.368 | +| clip_range | 0.0684 | +| entropy_loss | -5.93 | +| explained_variance | 0.454 | +| learning_rate | 4.37e-05 | +| loss | -0.034 | +| n_updates | 67240 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000115 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1412 | +| iterations | 12857 | +| time_elapsed | 18636 | +| total_timesteps | 26331136 | +| train/ | | +| approx_kl | 0.01686201 | +| clip_fraction | 0.373 | +| clip_range | 0.0684 | +| entropy_loss | -5.56 | +| explained_variance | 0.592 | +| learning_rate | 4.37e-05 | +| loss | -0.0303 | +| n_updates | 67244 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000171 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1412 | +| iterations | 12858 | +| time_elapsed | 18638 | +| total_timesteps | 26333184 | +| train/ | | +| approx_kl | 0.01601123 | +| clip_fraction | 0.401 | +| clip_range | 0.0684 | +| entropy_loss | -5.87 | +| explained_variance | 0.737 | +| learning_rate | 4.37e-05 | +| loss | -0.0367 | +| n_updates | 67248 | +| policy_gradient_loss | -0.0238 | +| value_loss | 4.32e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1412 | +| iterations | 12859 | +| time_elapsed | 18639 | +| total_timesteps | 26335232 | +| train/ | | +| approx_kl | 0.013263997 | +| clip_fraction | 0.353 | +| clip_range | 0.0684 | +| entropy_loss | -5.66 | +| explained_variance | 0.468 | +| learning_rate | 4.37e-05 | +| loss | -0.0327 | +| n_updates | 67252 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000193 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1412 | +| iterations | 12860 | +| time_elapsed | 18641 | +| total_timesteps | 26337280 | +| train/ | | +| approx_kl | 0.0131987715 | +| clip_fraction | 0.347 | +| clip_range | 0.0684 | +| entropy_loss | -6.56 | +| explained_variance | -0.0651 | +| learning_rate | 4.37e-05 | +| loss | -0.025 | +| n_updates | 67256 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000151 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1412 | +| iterations | 12861 | +| time_elapsed | 18642 | +| total_timesteps | 26339328 | +| train/ | | +| approx_kl | 0.014663264 | +| clip_fraction | 0.378 | +| clip_range | 0.0684 | +| entropy_loss | -6.3 | +| explained_variance | 0.175 | +| learning_rate | 4.37e-05 | +| loss | -0.032 | +| n_updates | 67260 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000152 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1412 | +| iterations | 12862 | +| time_elapsed | 18644 | +| total_timesteps | 26341376 | +| train/ | | +| approx_kl | 0.013415348 | +| clip_fraction | 0.347 | +| clip_range | 0.0684 | +| entropy_loss | -6.43 | +| explained_variance | 0.423 | +| learning_rate | 4.37e-05 | +| loss | -0.0324 | +| n_updates | 67264 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000149 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1412 | +| iterations | 12863 | +| time_elapsed | 18645 | +| total_timesteps | 26343424 | +| train/ | | +| approx_kl | 0.013753136 | +| clip_fraction | 0.368 | +| clip_range | 0.0684 | +| entropy_loss | -6.46 | +| explained_variance | 0.268 | +| learning_rate | 4.37e-05 | +| loss | -0.0268 | +| n_updates | 67268 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000148 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1412 | +| iterations | 12864 | +| time_elapsed | 18647 | +| total_timesteps | 26345472 | +| train/ | | +| approx_kl | 0.016383832 | +| clip_fraction | 0.359 | +| clip_range | 0.0684 | +| entropy_loss | -6.06 | +| explained_variance | 0.231 | +| learning_rate | 4.37e-05 | +| loss | -0.0228 | +| n_updates | 67272 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000244 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1412 | +| iterations | 12865 | +| time_elapsed | 18648 | +| total_timesteps | 26347520 | +| train/ | | +| approx_kl | 0.014966464 | +| clip_fraction | 0.352 | +| clip_range | 0.0684 | +| entropy_loss | -5.49 | +| explained_variance | 0.285 | +| learning_rate | 4.37e-05 | +| loss | -0.0286 | +| n_updates | 67276 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000465 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1412 | +| iterations | 12866 | +| time_elapsed | 18650 | +| total_timesteps | 26349568 | +| train/ | | +| approx_kl | 0.011113838 | +| clip_fraction | 0.333 | +| clip_range | 0.0684 | +| entropy_loss | -5.79 | +| explained_variance | 0.271 | +| learning_rate | 4.37e-05 | +| loss | -0.0339 | +| n_updates | 67280 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000302 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1412 | +| iterations | 12867 | +| time_elapsed | 18651 | +| total_timesteps | 26351616 | +| train/ | | +| approx_kl | 0.014177846 | +| clip_fraction | 0.371 | +| clip_range | 0.0684 | +| entropy_loss | -5.72 | +| explained_variance | 0.508 | +| learning_rate | 4.37e-05 | +| loss | -0.0429 | +| n_updates | 67284 | +| policy_gradient_loss | -0.024 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1412 | +| iterations | 12868 | +| time_elapsed | 18653 | +| total_timesteps | 26353664 | +| train/ | | +| approx_kl | 0.016666658 | +| clip_fraction | 0.376 | +| clip_range | 0.0684 | +| entropy_loss | -6.1 | +| explained_variance | 0.308 | +| learning_rate | 4.37e-05 | +| loss | -0.0382 | +| n_updates | 67288 | +| policy_gradient_loss | -0.0227 | +| value_loss | 0.000124 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1412 | +| iterations | 12869 | +| time_elapsed | 18654 | +| total_timesteps | 26355712 | +| train/ | | +| approx_kl | 0.012501966 | +| clip_fraction | 0.363 | +| clip_range | 0.0684 | +| entropy_loss | -6.16 | +| explained_variance | 0.206 | +| learning_rate | 4.37e-05 | +| loss | -0.0387 | +| n_updates | 67292 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000169 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1412 | +| iterations | 12870 | +| time_elapsed | 18656 | +| total_timesteps | 26357760 | +| train/ | | +| approx_kl | 0.014320934 | +| clip_fraction | 0.383 | +| clip_range | 0.0684 | +| entropy_loss | -6.42 | +| explained_variance | 0.000265 | +| learning_rate | 4.37e-05 | +| loss | -0.0259 | +| n_updates | 67296 | +| policy_gradient_loss | -0.022 | +| value_loss | 9.18e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1412 | +| iterations | 12871 | +| time_elapsed | 18657 | +| total_timesteps | 26359808 | +| train/ | | +| approx_kl | 0.014937574 | +| clip_fraction | 0.374 | +| clip_range | 0.0684 | +| entropy_loss | -6.08 | +| explained_variance | 0.561 | +| learning_rate | 4.37e-05 | +| loss | -0.0289 | +| n_updates | 67300 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000118 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1412 | +| iterations | 12872 | +| time_elapsed | 18659 | +| total_timesteps | 26361856 | +| train/ | | +| approx_kl | 0.013023196 | +| clip_fraction | 0.335 | +| clip_range | 0.0684 | +| entropy_loss | -6.27 | +| explained_variance | 0.633 | +| learning_rate | 4.37e-05 | +| loss | -0.0294 | +| n_updates | 67304 | +| policy_gradient_loss | -0.0185 | +| value_loss | 9.76e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1412 | +| iterations | 12873 | +| time_elapsed | 18660 | +| total_timesteps | 26363904 | +| train/ | | +| approx_kl | 0.013249077 | +| clip_fraction | 0.37 | +| clip_range | 0.0684 | +| entropy_loss | -6.02 | +| explained_variance | 0.71 | +| learning_rate | 4.37e-05 | +| loss | -0.0388 | +| n_updates | 67308 | +| policy_gradient_loss | -0.0225 | +| value_loss | 6.59e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1412 | +| iterations | 12874 | +| time_elapsed | 18662 | +| total_timesteps | 26365952 | +| train/ | | +| approx_kl | 0.013643816 | +| clip_fraction | 0.336 | +| clip_range | 0.0684 | +| entropy_loss | -6.07 | +| explained_variance | 0.598 | +| learning_rate | 4.37e-05 | +| loss | -0.029 | +| n_updates | 67312 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000114 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1412 | +| iterations | 12875 | +| time_elapsed | 18663 | +| total_timesteps | 26368000 | +| train/ | | +| approx_kl | 0.015990485 | +| clip_fraction | 0.35 | +| clip_range | 0.0684 | +| entropy_loss | -5.79 | +| explained_variance | 0.528 | +| learning_rate | 4.37e-05 | +| loss | -0.0242 | +| n_updates | 67316 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000151 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1412 | +| iterations | 12876 | +| time_elapsed | 18665 | +| total_timesteps | 26370048 | +| train/ | | +| approx_kl | 0.016033886 | +| clip_fraction | 0.339 | +| clip_range | 0.0684 | +| entropy_loss | -6.04 | +| explained_variance | 0.349 | +| learning_rate | 4.37e-05 | +| loss | -0.0271 | +| n_updates | 67320 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000172 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1412 | +| iterations | 12877 | +| time_elapsed | 18666 | +| total_timesteps | 26372096 | +| train/ | | +| approx_kl | 0.0156462 | +| clip_fraction | 0.37 | +| clip_range | 0.0684 | +| entropy_loss | -6.25 | +| explained_variance | 0.411 | +| learning_rate | 4.37e-05 | +| loss | -0.033 | +| n_updates | 67324 | +| policy_gradient_loss | -0.0218 | +| value_loss | 9.66e-05 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1412 | +| iterations | 12878 | +| time_elapsed | 18668 | +| total_timesteps | 26374144 | +| train/ | | +| approx_kl | 0.012290025 | +| clip_fraction | 0.337 | +| clip_range | 0.0684 | +| entropy_loss | -6.7 | +| explained_variance | 0.0434 | +| learning_rate | 4.37e-05 | +| loss | -0.0303 | +| n_updates | 67328 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000328 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1412 | +| iterations | 12879 | +| time_elapsed | 18669 | +| total_timesteps | 26376192 | +| train/ | | +| approx_kl | 0.014931168 | +| clip_fraction | 0.359 | +| clip_range | 0.0684 | +| entropy_loss | -5.87 | +| explained_variance | 0.595 | +| learning_rate | 4.37e-05 | +| loss | -0.0271 | +| n_updates | 67332 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000123 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1412 | +| iterations | 12880 | +| time_elapsed | 18671 | +| total_timesteps | 26378240 | +| train/ | | +| approx_kl | 0.014625639 | +| clip_fraction | 0.331 | +| clip_range | 0.0684 | +| entropy_loss | -5.91 | +| explained_variance | 0.807 | +| learning_rate | 4.37e-05 | +| loss | -0.0366 | +| n_updates | 67336 | +| policy_gradient_loss | -0.0194 | +| value_loss | 5.68e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1412 | +| iterations | 12881 | +| time_elapsed | 18672 | +| total_timesteps | 26380288 | +| train/ | | +| approx_kl | 0.013836538 | +| clip_fraction | 0.321 | +| clip_range | 0.0684 | +| entropy_loss | -5.65 | +| explained_variance | 0.428 | +| learning_rate | 4.37e-05 | +| loss | -0.0194 | +| n_updates | 67340 | +| policy_gradient_loss | -0.0146 | +| value_loss | 0.000314 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1412 | +| iterations | 12882 | +| time_elapsed | 18674 | +| total_timesteps | 26382336 | +| train/ | | +| approx_kl | 0.015004913 | +| clip_fraction | 0.327 | +| clip_range | 0.0684 | +| entropy_loss | -5.26 | +| explained_variance | 0.696 | +| learning_rate | 4.37e-05 | +| loss | -0.0316 | +| n_updates | 67344 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000124 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1412 | +| iterations | 12883 | +| time_elapsed | 18675 | +| total_timesteps | 26384384 | +| train/ | | +| approx_kl | 0.015885755 | +| clip_fraction | 0.364 | +| clip_range | 0.0684 | +| entropy_loss | -6.08 | +| explained_variance | -0.0727 | +| learning_rate | 4.37e-05 | +| loss | -0.0262 | +| n_updates | 67348 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000212 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1412 | +| iterations | 12884 | +| time_elapsed | 18677 | +| total_timesteps | 26386432 | +| train/ | | +| approx_kl | 0.014121853 | +| clip_fraction | 0.366 | +| clip_range | 0.0684 | +| entropy_loss | -6.33 | +| explained_variance | 0.242 | +| learning_rate | 4.37e-05 | +| loss | -0.0323 | +| n_updates | 67352 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000107 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1412 | +| iterations | 12885 | +| time_elapsed | 18678 | +| total_timesteps | 26388480 | +| train/ | | +| approx_kl | 0.01659821 | +| clip_fraction | 0.396 | +| clip_range | 0.0684 | +| entropy_loss | -6.15 | +| explained_variance | 0.56 | +| learning_rate | 4.37e-05 | +| loss | -0.0413 | +| n_updates | 67356 | +| policy_gradient_loss | -0.0224 | +| value_loss | 5.4e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1412 | +| iterations | 12886 | +| time_elapsed | 18680 | +| total_timesteps | 26390528 | +| train/ | | +| approx_kl | 0.015159835 | +| clip_fraction | 0.34 | +| clip_range | 0.0684 | +| entropy_loss | -6.25 | +| explained_variance | 0.332 | +| learning_rate | 4.37e-05 | +| loss | -0.0307 | +| n_updates | 67360 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000148 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1412 | +| iterations | 12887 | +| time_elapsed | 18681 | +| total_timesteps | 26392576 | +| train/ | | +| approx_kl | 0.013384916 | +| clip_fraction | 0.362 | +| clip_range | 0.0684 | +| entropy_loss | -6.31 | +| explained_variance | 0.494 | +| learning_rate | 4.37e-05 | +| loss | -0.031 | +| n_updates | 67364 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000115 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1412 | +| iterations | 12888 | +| time_elapsed | 18683 | +| total_timesteps | 26394624 | +| train/ | | +| approx_kl | 0.013955362 | +| clip_fraction | 0.329 | +| clip_range | 0.0684 | +| entropy_loss | -6.14 | +| explained_variance | 0.426 | +| learning_rate | 4.37e-05 | +| loss | -0.0318 | +| n_updates | 67368 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000262 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1412 | +| iterations | 12889 | +| time_elapsed | 18684 | +| total_timesteps | 26396672 | +| train/ | | +| approx_kl | 0.013850987 | +| clip_fraction | 0.354 | +| clip_range | 0.0684 | +| entropy_loss | -5.9 | +| explained_variance | 0.517 | +| learning_rate | 4.37e-05 | +| loss | -0.0305 | +| n_updates | 67372 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000137 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1412 | +| iterations | 12890 | +| time_elapsed | 18686 | +| total_timesteps | 26398720 | +| train/ | | +| approx_kl | 0.015304074 | +| clip_fraction | 0.38 | +| clip_range | 0.0684 | +| entropy_loss | -6.22 | +| explained_variance | 0.47 | +| learning_rate | 4.37e-05 | +| loss | -0.0421 | +| n_updates | 67376 | +| policy_gradient_loss | -0.0235 | +| value_loss | 5.55e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1412 | +| iterations | 12891 | +| time_elapsed | 18687 | +| total_timesteps | 26400768 | +| train/ | | +| approx_kl | 0.014544908 | +| clip_fraction | 0.365 | +| clip_range | 0.0684 | +| entropy_loss | -6.09 | +| explained_variance | 0.577 | +| learning_rate | 4.37e-05 | +| loss | -0.031 | +| n_updates | 67380 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000131 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1412 | +| iterations | 12892 | +| time_elapsed | 18689 | +| total_timesteps | 26402816 | +| train/ | | +| approx_kl | 0.013986459 | +| clip_fraction | 0.335 | +| clip_range | 0.0684 | +| entropy_loss | -5.93 | +| explained_variance | 0.448 | +| learning_rate | 4.37e-05 | +| loss | -0.0306 | +| n_updates | 67384 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000205 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1412 | +| iterations | 12893 | +| time_elapsed | 18690 | +| total_timesteps | 26404864 | +| train/ | | +| approx_kl | 0.015713144 | +| clip_fraction | 0.347 | +| clip_range | 0.0684 | +| entropy_loss | -5.74 | +| explained_variance | 0.588 | +| learning_rate | 4.37e-05 | +| loss | -0.031 | +| n_updates | 67388 | +| policy_gradient_loss | -0.0193 | +| value_loss | 9.93e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1412 | +| iterations | 12894 | +| time_elapsed | 18692 | +| total_timesteps | 26406912 | +| train/ | | +| approx_kl | 0.012486229 | +| clip_fraction | 0.332 | +| clip_range | 0.0684 | +| entropy_loss | -5.97 | +| explained_variance | 0.378 | +| learning_rate | 4.37e-05 | +| loss | -0.0219 | +| n_updates | 67392 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000278 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1412 | +| iterations | 12895 | +| time_elapsed | 18693 | +| total_timesteps | 26408960 | +| train/ | | +| approx_kl | 0.012524352 | +| clip_fraction | 0.341 | +| clip_range | 0.0684 | +| entropy_loss | -6.16 | +| explained_variance | 0.24 | +| learning_rate | 4.37e-05 | +| loss | -0.0336 | +| n_updates | 67396 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000143 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1412 | +| iterations | 12896 | +| time_elapsed | 18695 | +| total_timesteps | 26411008 | +| train/ | | +| approx_kl | 0.0123424465 | +| clip_fraction | 0.375 | +| clip_range | 0.0684 | +| entropy_loss | -6.57 | +| explained_variance | 0.111 | +| learning_rate | 4.37e-05 | +| loss | -0.0388 | +| n_updates | 67400 | +| policy_gradient_loss | -0.0227 | +| value_loss | 0.000113 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1412 | +| iterations | 12897 | +| time_elapsed | 18696 | +| total_timesteps | 26413056 | +| train/ | | +| approx_kl | 0.012024476 | +| clip_fraction | 0.323 | +| clip_range | 0.0684 | +| entropy_loss | -6.27 | +| explained_variance | 0.309 | +| learning_rate | 4.37e-05 | +| loss | -0.0319 | +| n_updates | 67404 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.00023 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1412 | +| iterations | 12898 | +| time_elapsed | 18698 | +| total_timesteps | 26415104 | +| train/ | | +| approx_kl | 0.011749375 | +| clip_fraction | 0.336 | +| clip_range | 0.0684 | +| entropy_loss | -6.03 | +| explained_variance | 0.457 | +| learning_rate | 4.37e-05 | +| loss | -0.0285 | +| n_updates | 67408 | +| policy_gradient_loss | -0.0185 | +| value_loss | 7.94e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1412 | +| iterations | 12899 | +| time_elapsed | 18699 | +| total_timesteps | 26417152 | +| train/ | | +| approx_kl | 0.012679549 | +| clip_fraction | 0.339 | +| clip_range | 0.0684 | +| entropy_loss | -6.02 | +| explained_variance | 0.365 | +| learning_rate | 4.37e-05 | +| loss | -0.0313 | +| n_updates | 67412 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000187 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1412 | +| iterations | 12900 | +| time_elapsed | 18701 | +| total_timesteps | 26419200 | +| train/ | | +| approx_kl | 0.014682509 | +| clip_fraction | 0.372 | +| clip_range | 0.0684 | +| entropy_loss | -6.04 | +| explained_variance | 0.451 | +| learning_rate | 4.37e-05 | +| loss | -0.032 | +| n_updates | 67416 | +| policy_gradient_loss | -0.0203 | +| value_loss | 9.04e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1412 | +| iterations | 12901 | +| time_elapsed | 18702 | +| total_timesteps | 26421248 | +| train/ | | +| approx_kl | 0.013016211 | +| clip_fraction | 0.337 | +| clip_range | 0.0684 | +| entropy_loss | -5.02 | +| explained_variance | 0.611 | +| learning_rate | 4.37e-05 | +| loss | -0.0246 | +| n_updates | 67420 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000237 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1412 | +| iterations | 12902 | +| time_elapsed | 18704 | +| total_timesteps | 26423296 | +| train/ | | +| approx_kl | 0.017805481 | +| clip_fraction | 0.313 | +| clip_range | 0.0684 | +| entropy_loss | -4.94 | +| explained_variance | 0.595 | +| learning_rate | 4.37e-05 | +| loss | -0.0257 | +| n_updates | 67424 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.000187 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1412 | +| iterations | 12903 | +| time_elapsed | 18705 | +| total_timesteps | 26425344 | +| train/ | | +| approx_kl | 0.012783974 | +| clip_fraction | 0.347 | +| clip_range | 0.0684 | +| entropy_loss | -6.31 | +| explained_variance | 0.101 | +| learning_rate | 4.37e-05 | +| loss | -0.0329 | +| n_updates | 67428 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000201 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1412 | +| iterations | 12904 | +| time_elapsed | 18706 | +| total_timesteps | 26427392 | +| train/ | | +| approx_kl | 0.01309525 | +| clip_fraction | 0.325 | +| clip_range | 0.0684 | +| entropy_loss | -7.03 | +| explained_variance | -0.225 | +| learning_rate | 4.37e-05 | +| loss | -0.0323 | +| n_updates | 67432 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.00014 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1412 | +| iterations | 12905 | +| time_elapsed | 18708 | +| total_timesteps | 26429440 | +| train/ | | +| approx_kl | 0.01112991 | +| clip_fraction | 0.306 | +| clip_range | 0.0684 | +| entropy_loss | -6.58 | +| explained_variance | 0.206 | +| learning_rate | 4.37e-05 | +| loss | -0.031 | +| n_updates | 67436 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000358 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1412 | +| iterations | 12906 | +| time_elapsed | 18710 | +| total_timesteps | 26431488 | +| train/ | | +| approx_kl | 0.011230102 | +| clip_fraction | 0.345 | +| clip_range | 0.0684 | +| entropy_loss | -5.7 | +| explained_variance | 0.395 | +| learning_rate | 4.37e-05 | +| loss | -0.0242 | +| n_updates | 67440 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.00035 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1412 | +| iterations | 12907 | +| time_elapsed | 18711 | +| total_timesteps | 26433536 | +| train/ | | +| approx_kl | 0.010485525 | +| clip_fraction | 0.337 | +| clip_range | 0.0684 | +| entropy_loss | -5.42 | +| explained_variance | 0.342 | +| learning_rate | 4.37e-05 | +| loss | -0.0238 | +| n_updates | 67444 | +| policy_gradient_loss | -0.0148 | +| value_loss | 0.000521 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1412 | +| iterations | 12908 | +| time_elapsed | 18713 | +| total_timesteps | 26435584 | +| train/ | | +| approx_kl | 0.012511738 | +| clip_fraction | 0.385 | +| clip_range | 0.0684 | +| entropy_loss | -5.52 | +| explained_variance | 0.245 | +| learning_rate | 4.37e-05 | +| loss | -0.0374 | +| n_updates | 67448 | +| policy_gradient_loss | -0.0241 | +| value_loss | 9.83e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1412 | +| iterations | 12909 | +| time_elapsed | 18714 | +| total_timesteps | 26437632 | +| train/ | | +| approx_kl | 0.012912683 | +| clip_fraction | 0.377 | +| clip_range | 0.0684 | +| entropy_loss | -5.99 | +| explained_variance | 0.357 | +| learning_rate | 4.37e-05 | +| loss | -0.0339 | +| n_updates | 67452 | +| policy_gradient_loss | -0.0222 | +| value_loss | 0.000135 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1412 | +| iterations | 12910 | +| time_elapsed | 18716 | +| total_timesteps | 26439680 | +| train/ | | +| approx_kl | 0.014565481 | +| clip_fraction | 0.351 | +| clip_range | 0.0684 | +| entropy_loss | -5.93 | +| explained_variance | 0.268 | +| learning_rate | 4.37e-05 | +| loss | -0.0253 | +| n_updates | 67456 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000334 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1412 | +| iterations | 12911 | +| time_elapsed | 18717 | +| total_timesteps | 26441728 | +| train/ | | +| approx_kl | 0.01368597 | +| clip_fraction | 0.372 | +| clip_range | 0.0684 | +| entropy_loss | -6.21 | +| explained_variance | 0.277 | +| learning_rate | 4.37e-05 | +| loss | -0.0346 | +| n_updates | 67460 | +| policy_gradient_loss | -0.0226 | +| value_loss | 0.000111 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1412 | +| iterations | 12912 | +| time_elapsed | 18719 | +| total_timesteps | 26443776 | +| train/ | | +| approx_kl | 0.012319477 | +| clip_fraction | 0.351 | +| clip_range | 0.0684 | +| entropy_loss | -6.47 | +| explained_variance | 0.262 | +| learning_rate | 4.37e-05 | +| loss | -0.0349 | +| n_updates | 67464 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000113 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1412 | +| iterations | 12913 | +| time_elapsed | 18720 | +| total_timesteps | 26445824 | +| train/ | | +| approx_kl | 0.011830952 | +| clip_fraction | 0.32 | +| clip_range | 0.0684 | +| entropy_loss | -6.09 | +| explained_variance | 0.33 | +| learning_rate | 4.37e-05 | +| loss | -0.0288 | +| n_updates | 67468 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000355 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1412 | +| iterations | 12914 | +| time_elapsed | 18722 | +| total_timesteps | 26447872 | +| train/ | | +| approx_kl | 0.016092584 | +| clip_fraction | 0.343 | +| clip_range | 0.0684 | +| entropy_loss | -5.47 | +| explained_variance | 0.721 | +| learning_rate | 4.37e-05 | +| loss | -0.0271 | +| n_updates | 67472 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000105 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1412 | +| iterations | 12915 | +| time_elapsed | 18723 | +| total_timesteps | 26449920 | +| train/ | | +| approx_kl | 0.014130776 | +| clip_fraction | 0.375 | +| clip_range | 0.0684 | +| entropy_loss | -6.27 | +| explained_variance | 0.0714 | +| learning_rate | 4.37e-05 | +| loss | -0.0388 | +| n_updates | 67476 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000101 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1412 | +| iterations | 12916 | +| time_elapsed | 18725 | +| total_timesteps | 26451968 | +| train/ | | +| approx_kl | 0.011832859 | +| clip_fraction | 0.339 | +| clip_range | 0.0684 | +| entropy_loss | -6.8 | +| explained_variance | -0.123 | +| learning_rate | 4.37e-05 | +| loss | -0.0334 | +| n_updates | 67480 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.00011 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1412 | +| iterations | 12917 | +| time_elapsed | 18726 | +| total_timesteps | 26454016 | +| train/ | | +| approx_kl | 0.014053481 | +| clip_fraction | 0.329 | +| clip_range | 0.0684 | +| entropy_loss | -6.3 | +| explained_variance | 0.492 | +| learning_rate | 4.37e-05 | +| loss | -0.0263 | +| n_updates | 67484 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000162 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1412 | +| iterations | 12918 | +| time_elapsed | 18728 | +| total_timesteps | 26456064 | +| train/ | | +| approx_kl | 0.015155803 | +| clip_fraction | 0.329 | +| clip_range | 0.0684 | +| entropy_loss | -5.61 | +| explained_variance | 0.732 | +| learning_rate | 4.37e-05 | +| loss | -0.03 | +| n_updates | 67488 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000108 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1412 | +| iterations | 12919 | +| time_elapsed | 18729 | +| total_timesteps | 26458112 | +| train/ | | +| approx_kl | 0.013566816 | +| clip_fraction | 0.339 | +| clip_range | 0.0684 | +| entropy_loss | -5.95 | +| explained_variance | -0.392 | +| learning_rate | 4.37e-05 | +| loss | -0.0275 | +| n_updates | 67492 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000124 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1412 | +| iterations | 12920 | +| time_elapsed | 18731 | +| total_timesteps | 26460160 | +| train/ | | +| approx_kl | 0.010441385 | +| clip_fraction | 0.328 | +| clip_range | 0.0684 | +| entropy_loss | -6.46 | +| explained_variance | 0.231 | +| learning_rate | 4.37e-05 | +| loss | -0.0281 | +| n_updates | 67496 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000188 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1412 | +| iterations | 12921 | +| time_elapsed | 18732 | +| total_timesteps | 26462208 | +| train/ | | +| approx_kl | 0.01247407 | +| clip_fraction | 0.345 | +| clip_range | 0.0684 | +| entropy_loss | -6.35 | +| explained_variance | 0.358 | +| learning_rate | 4.37e-05 | +| loss | -0.0314 | +| n_updates | 67500 | +| policy_gradient_loss | -0.0197 | +| value_loss | 9.31e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1412 | +| iterations | 12922 | +| time_elapsed | 18734 | +| total_timesteps | 26464256 | +| train/ | | +| approx_kl | 0.009399756 | +| clip_fraction | 0.321 | +| clip_range | 0.0684 | +| entropy_loss | -6.53 | +| explained_variance | 0.413 | +| learning_rate | 4.37e-05 | +| loss | -0.0287 | +| n_updates | 67504 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000184 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1412 | +| iterations | 12923 | +| time_elapsed | 18735 | +| total_timesteps | 26466304 | +| train/ | | +| approx_kl | 0.014587112 | +| clip_fraction | 0.327 | +| clip_range | 0.0684 | +| entropy_loss | -6.18 | +| explained_variance | 0.385 | +| learning_rate | 4.37e-05 | +| loss | -0.0259 | +| n_updates | 67508 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000112 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1412 | +| iterations | 12924 | +| time_elapsed | 18737 | +| total_timesteps | 26468352 | +| train/ | | +| approx_kl | 0.014055809 | +| clip_fraction | 0.333 | +| clip_range | 0.0684 | +| entropy_loss | -5.86 | +| explained_variance | 0.394 | +| learning_rate | 4.37e-05 | +| loss | -0.022 | +| n_updates | 67512 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000243 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1412 | +| iterations | 12925 | +| time_elapsed | 18738 | +| total_timesteps | 26470400 | +| train/ | | +| approx_kl | 0.0109504685 | +| clip_fraction | 0.307 | +| clip_range | 0.0684 | +| entropy_loss | -5.78 | +| explained_variance | 0.552 | +| learning_rate | 4.37e-05 | +| loss | -0.025 | +| n_updates | 67516 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000167 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1412 | +| iterations | 12926 | +| time_elapsed | 18740 | +| total_timesteps | 26472448 | +| train/ | | +| approx_kl | 0.01076062 | +| clip_fraction | 0.32 | +| clip_range | 0.0684 | +| entropy_loss | -5.95 | +| explained_variance | 0.666 | +| learning_rate | 4.37e-05 | +| loss | -0.0286 | +| n_updates | 67520 | +| policy_gradient_loss | -0.0193 | +| value_loss | 8.07e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1412 | +| iterations | 12927 | +| time_elapsed | 18741 | +| total_timesteps | 26474496 | +| train/ | | +| approx_kl | 0.010096479 | +| clip_fraction | 0.309 | +| clip_range | 0.0684 | +| entropy_loss | -6.32 | +| explained_variance | 0.085 | +| learning_rate | 4.37e-05 | +| loss | -0.0227 | +| n_updates | 67524 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.000316 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1412 | +| iterations | 12928 | +| time_elapsed | 18743 | +| total_timesteps | 26476544 | +| train/ | | +| approx_kl | 0.014876984 | +| clip_fraction | 0.332 | +| clip_range | 0.0684 | +| entropy_loss | -5.81 | +| explained_variance | 0.505 | +| learning_rate | 4.37e-05 | +| loss | -0.027 | +| n_updates | 67528 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000203 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1412 | +| iterations | 12929 | +| time_elapsed | 18744 | +| total_timesteps | 26478592 | +| train/ | | +| approx_kl | 0.01395095 | +| clip_fraction | 0.359 | +| clip_range | 0.0684 | +| entropy_loss | -6.19 | +| explained_variance | 0.341 | +| learning_rate | 4.37e-05 | +| loss | -0.0277 | +| n_updates | 67532 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000123 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1412 | +| iterations | 12930 | +| time_elapsed | 18746 | +| total_timesteps | 26480640 | +| train/ | | +| approx_kl | 0.015550378 | +| clip_fraction | 0.377 | +| clip_range | 0.0684 | +| entropy_loss | -5.91 | +| explained_variance | 0.412 | +| learning_rate | 4.37e-05 | +| loss | -0.0304 | +| n_updates | 67536 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000173 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1412 | +| iterations | 12931 | +| time_elapsed | 18747 | +| total_timesteps | 26482688 | +| train/ | | +| approx_kl | 0.013276422 | +| clip_fraction | 0.36 | +| clip_range | 0.0684 | +| entropy_loss | -5.98 | +| explained_variance | 0.259 | +| learning_rate | 4.37e-05 | +| loss | -0.0278 | +| n_updates | 67540 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000158 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1412 | +| iterations | 12932 | +| time_elapsed | 18749 | +| total_timesteps | 26484736 | +| train/ | | +| approx_kl | 0.01223659 | +| clip_fraction | 0.356 | +| clip_range | 0.0684 | +| entropy_loss | -5.75 | +| explained_variance | 0.507 | +| learning_rate | 4.37e-05 | +| loss | -0.0322 | +| n_updates | 67544 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000121 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1412 | +| iterations | 12933 | +| time_elapsed | 18750 | +| total_timesteps | 26486784 | +| train/ | | +| approx_kl | 0.016375067 | +| clip_fraction | 0.356 | +| clip_range | 0.0684 | +| entropy_loss | -6.33 | +| explained_variance | -0.119 | +| learning_rate | 4.37e-05 | +| loss | -0.0387 | +| n_updates | 67548 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000125 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1412 | +| iterations | 12934 | +| time_elapsed | 18752 | +| total_timesteps | 26488832 | +| train/ | | +| approx_kl | 0.011503309 | +| clip_fraction | 0.345 | +| clip_range | 0.0684 | +| entropy_loss | -6.11 | +| explained_variance | 0.545 | +| learning_rate | 4.37e-05 | +| loss | -0.0341 | +| n_updates | 67552 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.00018 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1412 | +| iterations | 12935 | +| time_elapsed | 18753 | +| total_timesteps | 26490880 | +| train/ | | +| approx_kl | 0.011554379 | +| clip_fraction | 0.328 | +| clip_range | 0.0684 | +| entropy_loss | -5.97 | +| explained_variance | 0.418 | +| learning_rate | 4.37e-05 | +| loss | -0.0346 | +| n_updates | 67556 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000106 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1412 | +| iterations | 12936 | +| time_elapsed | 18755 | +| total_timesteps | 26492928 | +| train/ | | +| approx_kl | 0.0120290965 | +| clip_fraction | 0.324 | +| clip_range | 0.0684 | +| entropy_loss | -6.27 | +| explained_variance | 0.349 | +| learning_rate | 4.37e-05 | +| loss | -0.0277 | +| n_updates | 67560 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.00017 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1412 | +| iterations | 12937 | +| time_elapsed | 18756 | +| total_timesteps | 26494976 | +| train/ | | +| approx_kl | 0.012913628 | +| clip_fraction | 0.352 | +| clip_range | 0.0684 | +| entropy_loss | -6.52 | +| explained_variance | 0.387 | +| learning_rate | 4.37e-05 | +| loss | -0.0272 | +| n_updates | 67564 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000121 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1412 | +| iterations | 12938 | +| time_elapsed | 18758 | +| total_timesteps | 26497024 | +| train/ | | +| approx_kl | 0.012158617 | +| clip_fraction | 0.318 | +| clip_range | 0.0684 | +| entropy_loss | -5.23 | +| explained_variance | 0.714 | +| learning_rate | 4.37e-05 | +| loss | -0.0267 | +| n_updates | 67568 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000134 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1412 | +| iterations | 12939 | +| time_elapsed | 18759 | +| total_timesteps | 26499072 | +| train/ | | +| approx_kl | 0.013437821 | +| clip_fraction | 0.341 | +| clip_range | 0.0684 | +| entropy_loss | -5.8 | +| explained_variance | 0.451 | +| learning_rate | 4.37e-05 | +| loss | -0.0209 | +| n_updates | 67572 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000282 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1412 | +| iterations | 12940 | +| time_elapsed | 18761 | +| total_timesteps | 26501120 | +| train/ | | +| approx_kl | 0.012744582 | +| clip_fraction | 0.381 | +| clip_range | 0.0684 | +| entropy_loss | -6.22 | +| explained_variance | 0.13 | +| learning_rate | 4.37e-05 | +| loss | -0.0391 | +| n_updates | 67576 | +| policy_gradient_loss | -0.0235 | +| value_loss | 8.48e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1412 | +| iterations | 12941 | +| time_elapsed | 18762 | +| total_timesteps | 26503168 | +| train/ | | +| approx_kl | 0.012675009 | +| clip_fraction | 0.347 | +| clip_range | 0.0684 | +| entropy_loss | -6.22 | +| explained_variance | 0.172 | +| learning_rate | 4.37e-05 | +| loss | -0.0265 | +| n_updates | 67580 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000147 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1412 | +| iterations | 12942 | +| time_elapsed | 18764 | +| total_timesteps | 26505216 | +| train/ | | +| approx_kl | 0.015717007 | +| clip_fraction | 0.365 | +| clip_range | 0.0684 | +| entropy_loss | -6.46 | +| explained_variance | 0.405 | +| learning_rate | 4.37e-05 | +| loss | -0.0326 | +| n_updates | 67584 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000132 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1412 | +| iterations | 12943 | +| time_elapsed | 18765 | +| total_timesteps | 26507264 | +| train/ | | +| approx_kl | 0.015410233 | +| clip_fraction | 0.38 | +| clip_range | 0.0684 | +| entropy_loss | -6.57 | +| explained_variance | -0.138 | +| learning_rate | 4.37e-05 | +| loss | -0.0324 | +| n_updates | 67588 | +| policy_gradient_loss | -0.0199 | +| value_loss | 7.95e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1412 | +| iterations | 12944 | +| time_elapsed | 18767 | +| total_timesteps | 26509312 | +| train/ | | +| approx_kl | 0.0103766285 | +| clip_fraction | 0.313 | +| clip_range | 0.0684 | +| entropy_loss | -6.35 | +| explained_variance | 0.383 | +| learning_rate | 4.37e-05 | +| loss | -0.0225 | +| n_updates | 67592 | +| policy_gradient_loss | -0.0133 | +| value_loss | 0.000224 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1412 | +| iterations | 12945 | +| time_elapsed | 18768 | +| total_timesteps | 26511360 | +| train/ | | +| approx_kl | 0.015011218 | +| clip_fraction | 0.367 | +| clip_range | 0.0684 | +| entropy_loss | -5.89 | +| explained_variance | 0.488 | +| learning_rate | 4.37e-05 | +| loss | -0.0316 | +| n_updates | 67596 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000149 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1412 | +| iterations | 12946 | +| time_elapsed | 18770 | +| total_timesteps | 26513408 | +| train/ | | +| approx_kl | 0.011874016 | +| clip_fraction | 0.305 | +| clip_range | 0.0684 | +| entropy_loss | -5.34 | +| explained_variance | 0.633 | +| learning_rate | 4.37e-05 | +| loss | -0.0255 | +| n_updates | 67600 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000198 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1412 | +| iterations | 12947 | +| time_elapsed | 18771 | +| total_timesteps | 26515456 | +| train/ | | +| approx_kl | 0.0126626305 | +| clip_fraction | 0.376 | +| clip_range | 0.0684 | +| entropy_loss | -6.15 | +| explained_variance | 0.0848 | +| learning_rate | 4.37e-05 | +| loss | -0.0351 | +| n_updates | 67604 | +| policy_gradient_loss | -0.0219 | +| value_loss | 7.96e-05 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1412 | +| iterations | 12948 | +| time_elapsed | 18773 | +| total_timesteps | 26517504 | +| train/ | | +| approx_kl | 0.0141867045 | +| clip_fraction | 0.343 | +| clip_range | 0.0684 | +| entropy_loss | -6.23 | +| explained_variance | 0.335 | +| learning_rate | 4.37e-05 | +| loss | -0.027 | +| n_updates | 67608 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000244 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1412 | +| iterations | 12949 | +| time_elapsed | 18775 | +| total_timesteps | 26519552 | +| train/ | | +| approx_kl | 0.014778644 | +| clip_fraction | 0.372 | +| clip_range | 0.0684 | +| entropy_loss | -6.18 | +| explained_variance | 0.588 | +| learning_rate | 4.37e-05 | +| loss | -0.0362 | +| n_updates | 67612 | +| policy_gradient_loss | -0.0228 | +| value_loss | 7.48e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1412 | +| iterations | 12950 | +| time_elapsed | 18776 | +| total_timesteps | 26521600 | +| train/ | | +| approx_kl | 0.015026009 | +| clip_fraction | 0.334 | +| clip_range | 0.0684 | +| entropy_loss | -5.81 | +| explained_variance | 0.418 | +| learning_rate | 4.37e-05 | +| loss | -0.0256 | +| n_updates | 67616 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000215 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1412 | +| iterations | 12951 | +| time_elapsed | 18778 | +| total_timesteps | 26523648 | +| train/ | | +| approx_kl | 0.015241122 | +| clip_fraction | 0.323 | +| clip_range | 0.0684 | +| entropy_loss | -6.57 | +| explained_variance | -0.186 | +| learning_rate | 4.37e-05 | +| loss | -0.0328 | +| n_updates | 67620 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.00014 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1412 | +| iterations | 12952 | +| time_elapsed | 18779 | +| total_timesteps | 26525696 | +| train/ | | +| approx_kl | 0.013214661 | +| clip_fraction | 0.345 | +| clip_range | 0.0684 | +| entropy_loss | -6.71 | +| explained_variance | -0.0515 | +| learning_rate | 4.37e-05 | +| loss | -0.0307 | +| n_updates | 67624 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000116 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1412 | +| iterations | 12953 | +| time_elapsed | 18781 | +| total_timesteps | 26527744 | +| train/ | | +| approx_kl | 0.015411034 | +| clip_fraction | 0.324 | +| clip_range | 0.0684 | +| entropy_loss | -6.08 | +| explained_variance | 0.319 | +| learning_rate | 4.37e-05 | +| loss | -0.0261 | +| n_updates | 67628 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000233 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1412 | +| iterations | 12954 | +| time_elapsed | 18782 | +| total_timesteps | 26529792 | +| train/ | | +| approx_kl | 0.01583023 | +| clip_fraction | 0.361 | +| clip_range | 0.0684 | +| entropy_loss | -5.68 | +| explained_variance | 0.42 | +| learning_rate | 4.37e-05 | +| loss | -0.0249 | +| n_updates | 67632 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.00021 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1412 | +| iterations | 12955 | +| time_elapsed | 18784 | +| total_timesteps | 26531840 | +| train/ | | +| approx_kl | 0.015950762 | +| clip_fraction | 0.356 | +| clip_range | 0.0684 | +| entropy_loss | -6.08 | +| explained_variance | 0.308 | +| learning_rate | 4.37e-05 | +| loss | -0.0258 | +| n_updates | 67636 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000221 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1412 | +| iterations | 12956 | +| time_elapsed | 18785 | +| total_timesteps | 26533888 | +| train/ | | +| approx_kl | 0.014805461 | +| clip_fraction | 0.347 | +| clip_range | 0.0684 | +| entropy_loss | -6.18 | +| explained_variance | 0.325 | +| learning_rate | 4.37e-05 | +| loss | -0.0272 | +| n_updates | 67640 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000284 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1412 | +| iterations | 12957 | +| time_elapsed | 18787 | +| total_timesteps | 26535936 | +| train/ | | +| approx_kl | 0.019026546 | +| clip_fraction | 0.374 | +| clip_range | 0.0684 | +| entropy_loss | -5.74 | +| explained_variance | 0.556 | +| learning_rate | 4.37e-05 | +| loss | -0.0283 | +| n_updates | 67644 | +| policy_gradient_loss | -0.0223 | +| value_loss | 0.000109 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1412 | +| iterations | 12958 | +| time_elapsed | 18788 | +| total_timesteps | 26537984 | +| train/ | | +| approx_kl | 0.015596231 | +| clip_fraction | 0.358 | +| clip_range | 0.0684 | +| entropy_loss | -5.98 | +| explained_variance | 0.422 | +| learning_rate | 4.37e-05 | +| loss | -0.0331 | +| n_updates | 67648 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000128 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1412 | +| iterations | 12959 | +| time_elapsed | 18790 | +| total_timesteps | 26540032 | +| train/ | | +| approx_kl | 0.017006677 | +| clip_fraction | 0.372 | +| clip_range | 0.0684 | +| entropy_loss | -6.14 | +| explained_variance | 0.266 | +| learning_rate | 4.37e-05 | +| loss | -0.0309 | +| n_updates | 67652 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000103 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1412 | +| iterations | 12960 | +| time_elapsed | 18791 | +| total_timesteps | 26542080 | +| train/ | | +| approx_kl | 0.015468461 | +| clip_fraction | 0.383 | +| clip_range | 0.0684 | +| entropy_loss | -6.35 | +| explained_variance | -0.166 | +| learning_rate | 4.37e-05 | +| loss | -0.0315 | +| n_updates | 67656 | +| policy_gradient_loss | -0.0197 | +| value_loss | 9.99e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1412 | +| iterations | 12961 | +| time_elapsed | 18793 | +| total_timesteps | 26544128 | +| train/ | | +| approx_kl | 0.014601818 | +| clip_fraction | 0.365 | +| clip_range | 0.0684 | +| entropy_loss | -6.35 | +| explained_variance | 0.446 | +| learning_rate | 4.37e-05 | +| loss | -0.0329 | +| n_updates | 67660 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000178 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1412 | +| iterations | 12962 | +| time_elapsed | 18794 | +| total_timesteps | 26546176 | +| train/ | | +| approx_kl | 0.012481015 | +| clip_fraction | 0.335 | +| clip_range | 0.0684 | +| entropy_loss | -6.33 | +| explained_variance | 0.314 | +| learning_rate | 4.37e-05 | +| loss | -0.0314 | +| n_updates | 67664 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000133 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1412 | +| iterations | 12963 | +| time_elapsed | 18796 | +| total_timesteps | 26548224 | +| train/ | | +| approx_kl | 0.011423079 | +| clip_fraction | 0.341 | +| clip_range | 0.0684 | +| entropy_loss | -6.63 | +| explained_variance | 0.548 | +| learning_rate | 4.37e-05 | +| loss | -0.0349 | +| n_updates | 67668 | +| policy_gradient_loss | -0.0192 | +| value_loss | 8.27e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1412 | +| iterations | 12964 | +| time_elapsed | 18797 | +| total_timesteps | 26550272 | +| train/ | | +| approx_kl | 0.010637945 | +| clip_fraction | 0.311 | +| clip_range | 0.0684 | +| entropy_loss | -5.82 | +| explained_variance | 0.591 | +| learning_rate | 4.37e-05 | +| loss | -0.0215 | +| n_updates | 67672 | +| policy_gradient_loss | -0.0141 | +| value_loss | 0.000189 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1412 | +| iterations | 12965 | +| time_elapsed | 18799 | +| total_timesteps | 26552320 | +| train/ | | +| approx_kl | 0.012551596 | +| clip_fraction | 0.381 | +| clip_range | 0.0684 | +| entropy_loss | -6.51 | +| explained_variance | -0.197 | +| learning_rate | 4.37e-05 | +| loss | -0.0301 | +| n_updates | 67676 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000106 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1412 | +| iterations | 12966 | +| time_elapsed | 18801 | +| total_timesteps | 26554368 | +| train/ | | +| approx_kl | 0.0122985 | +| clip_fraction | 0.332 | +| clip_range | 0.0684 | +| entropy_loss | -5.91 | +| explained_variance | 0.389 | +| learning_rate | 4.37e-05 | +| loss | -0.0261 | +| n_updates | 67680 | +| policy_gradient_loss | -0.0148 | +| value_loss | 0.000323 | +--------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1412 | +| iterations | 12967 | +| time_elapsed | 18802 | +| total_timesteps | 26556416 | +| train/ | | +| approx_kl | 0.01643354 | +| clip_fraction | 0.36 | +| clip_range | 0.0684 | +| entropy_loss | -5.43 | +| explained_variance | 0.717 | +| learning_rate | 4.37e-05 | +| loss | -0.0363 | +| n_updates | 67684 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000108 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1412 | +| iterations | 12968 | +| time_elapsed | 18804 | +| total_timesteps | 26558464 | +| train/ | | +| approx_kl | 0.013939323 | +| clip_fraction | 0.349 | +| clip_range | 0.0684 | +| entropy_loss | -5.72 | +| explained_variance | 0.344 | +| learning_rate | 4.37e-05 | +| loss | -0.0311 | +| n_updates | 67688 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000214 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1412 | +| iterations | 12969 | +| time_elapsed | 18805 | +| total_timesteps | 26560512 | +| train/ | | +| approx_kl | 0.012889283 | +| clip_fraction | 0.354 | +| clip_range | 0.0684 | +| entropy_loss | -6.45 | +| explained_variance | 0.294 | +| learning_rate | 4.37e-05 | +| loss | -0.0301 | +| n_updates | 67692 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000128 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1412 | +| iterations | 12970 | +| time_elapsed | 18807 | +| total_timesteps | 26562560 | +| train/ | | +| approx_kl | 0.01267343 | +| clip_fraction | 0.363 | +| clip_range | 0.0684 | +| entropy_loss | -6.35 | +| explained_variance | 0.261 | +| learning_rate | 4.37e-05 | +| loss | -0.0373 | +| n_updates | 67696 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000149 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1412 | +| iterations | 12971 | +| time_elapsed | 18808 | +| total_timesteps | 26564608 | +| train/ | | +| approx_kl | 0.014627737 | +| clip_fraction | 0.372 | +| clip_range | 0.0684 | +| entropy_loss | -6.45 | +| explained_variance | 0.233 | +| learning_rate | 4.37e-05 | +| loss | -0.0329 | +| n_updates | 67700 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1412 | +| iterations | 12972 | +| time_elapsed | 18810 | +| total_timesteps | 26566656 | +| train/ | | +| approx_kl | 0.012391198 | +| clip_fraction | 0.361 | +| clip_range | 0.0684 | +| entropy_loss | -6.39 | +| explained_variance | 0.374 | +| learning_rate | 4.37e-05 | +| loss | -0.0278 | +| n_updates | 67704 | +| policy_gradient_loss | -0.0201 | +| value_loss | 9.42e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1412 | +| iterations | 12973 | +| time_elapsed | 18811 | +| total_timesteps | 26568704 | +| train/ | | +| approx_kl | 0.010408418 | +| clip_fraction | 0.315 | +| clip_range | 0.0684 | +| entropy_loss | -5.53 | +| explained_variance | 0.443 | +| learning_rate | 4.37e-05 | +| loss | -0.0195 | +| n_updates | 67708 | +| policy_gradient_loss | -0.0136 | +| value_loss | 0.000395 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1412 | +| iterations | 12974 | +| time_elapsed | 18813 | +| total_timesteps | 26570752 | +| train/ | | +| approx_kl | 0.0146377925 | +| clip_fraction | 0.385 | +| clip_range | 0.0684 | +| entropy_loss | -6 | +| explained_variance | 0.586 | +| learning_rate | 4.37e-05 | +| loss | -0.0382 | +| n_updates | 67712 | +| policy_gradient_loss | -0.0233 | +| value_loss | 8.7e-05 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1412 | +| iterations | 12975 | +| time_elapsed | 18814 | +| total_timesteps | 26572800 | +| train/ | | +| approx_kl | 0.01275398 | +| clip_fraction | 0.358 | +| clip_range | 0.0684 | +| entropy_loss | -6.18 | +| explained_variance | 0.37 | +| learning_rate | 4.37e-05 | +| loss | -0.0324 | +| n_updates | 67716 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.00017 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.315 | +| time/ | | +| fps | 1412 | +| iterations | 12976 | +| time_elapsed | 18816 | +| total_timesteps | 26574848 | +| train/ | | +| approx_kl | 0.015036065 | +| clip_fraction | 0.351 | +| clip_range | 0.0684 | +| entropy_loss | -6.31 | +| explained_variance | 0.259 | +| learning_rate | 4.37e-05 | +| loss | -0.0312 | +| n_updates | 67720 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000145 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1412 | +| iterations | 12977 | +| time_elapsed | 18817 | +| total_timesteps | 26576896 | +| train/ | | +| approx_kl | 0.013999817 | +| clip_fraction | 0.357 | +| clip_range | 0.0684 | +| entropy_loss | -5.74 | +| explained_variance | 0.506 | +| learning_rate | 4.37e-05 | +| loss | -0.0298 | +| n_updates | 67724 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000135 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1412 | +| iterations | 12978 | +| time_elapsed | 18819 | +| total_timesteps | 26578944 | +| train/ | | +| approx_kl | 0.011022611 | +| clip_fraction | 0.336 | +| clip_range | 0.0684 | +| entropy_loss | -6.15 | +| explained_variance | 0.398 | +| learning_rate | 4.37e-05 | +| loss | -0.029 | +| n_updates | 67728 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000222 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1412 | +| iterations | 12979 | +| time_elapsed | 18820 | +| total_timesteps | 26580992 | +| train/ | | +| approx_kl | 0.013532275 | +| clip_fraction | 0.334 | +| clip_range | 0.0684 | +| entropy_loss | -6.01 | +| explained_variance | 0.339 | +| learning_rate | 4.37e-05 | +| loss | -0.0303 | +| n_updates | 67732 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000276 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1412 | +| iterations | 12980 | +| time_elapsed | 18822 | +| total_timesteps | 26583040 | +| train/ | | +| approx_kl | 0.015842691 | +| clip_fraction | 0.352 | +| clip_range | 0.0684 | +| entropy_loss | -5.78 | +| explained_variance | 0.528 | +| learning_rate | 4.37e-05 | +| loss | -0.0261 | +| n_updates | 67736 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000149 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1412 | +| iterations | 12981 | +| time_elapsed | 18823 | +| total_timesteps | 26585088 | +| train/ | | +| approx_kl | 0.012181973 | +| clip_fraction | 0.326 | +| clip_range | 0.0684 | +| entropy_loss | -5.73 | +| explained_variance | 0.631 | +| learning_rate | 4.37e-05 | +| loss | -0.0238 | +| n_updates | 67740 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000159 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1412 | +| iterations | 12982 | +| time_elapsed | 18825 | +| total_timesteps | 26587136 | +| train/ | | +| approx_kl | 0.014477631 | +| clip_fraction | 0.362 | +| clip_range | 0.0684 | +| entropy_loss | -5.99 | +| explained_variance | -0.00325 | +| learning_rate | 4.37e-05 | +| loss | -0.0368 | +| n_updates | 67744 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000146 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1412 | +| iterations | 12983 | +| time_elapsed | 18826 | +| total_timesteps | 26589184 | +| train/ | | +| approx_kl | 0.011974497 | +| clip_fraction | 0.311 | +| clip_range | 0.0684 | +| entropy_loss | -6.64 | +| explained_variance | -0.114 | +| learning_rate | 4.37e-05 | +| loss | -0.0302 | +| n_updates | 67748 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.00026 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1412 | +| iterations | 12984 | +| time_elapsed | 18828 | +| total_timesteps | 26591232 | +| train/ | | +| approx_kl | 0.009850518 | +| clip_fraction | 0.301 | +| clip_range | 0.0684 | +| entropy_loss | -6.04 | +| explained_variance | 0.466 | +| learning_rate | 4.37e-05 | +| loss | -0.0293 | +| n_updates | 67752 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000227 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1412 | +| iterations | 12985 | +| time_elapsed | 18830 | +| total_timesteps | 26593280 | +| train/ | | +| approx_kl | 0.013922583 | +| clip_fraction | 0.356 | +| clip_range | 0.0684 | +| entropy_loss | -6 | +| explained_variance | 0.393 | +| learning_rate | 4.37e-05 | +| loss | -0.027 | +| n_updates | 67756 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.0001 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1412 | +| iterations | 12986 | +| time_elapsed | 18831 | +| total_timesteps | 26595328 | +| train/ | | +| approx_kl | 0.012846774 | +| clip_fraction | 0.315 | +| clip_range | 0.0684 | +| entropy_loss | -5.68 | +| explained_variance | 0.405 | +| learning_rate | 4.37e-05 | +| loss | -0.0223 | +| n_updates | 67760 | +| policy_gradient_loss | -0.0139 | +| value_loss | 0.000372 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1412 | +| iterations | 12987 | +| time_elapsed | 18833 | +| total_timesteps | 26597376 | +| train/ | | +| approx_kl | 0.014785519 | +| clip_fraction | 0.35 | +| clip_range | 0.0684 | +| entropy_loss | -5.31 | +| explained_variance | 0.723 | +| learning_rate | 4.37e-05 | +| loss | -0.031 | +| n_updates | 67764 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000112 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1412 | +| iterations | 12988 | +| time_elapsed | 18834 | +| total_timesteps | 26599424 | +| train/ | | +| approx_kl | 0.010586778 | +| clip_fraction | 0.339 | +| clip_range | 0.0684 | +| entropy_loss | -6.01 | +| explained_variance | 0.623 | +| learning_rate | 4.37e-05 | +| loss | -0.034 | +| n_updates | 67768 | +| policy_gradient_loss | -0.0193 | +| value_loss | 8.84e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1412 | +| iterations | 12989 | +| time_elapsed | 18835 | +| total_timesteps | 26601472 | +| train/ | | +| approx_kl | 0.01073959 | +| clip_fraction | 0.318 | +| clip_range | 0.0684 | +| entropy_loss | -5.62 | +| explained_variance | 0.366 | +| learning_rate | 4.37e-05 | +| loss | -0.0293 | +| n_updates | 67772 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000274 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1412 | +| iterations | 12990 | +| time_elapsed | 18837 | +| total_timesteps | 26603520 | +| train/ | | +| approx_kl | 0.012142519 | +| clip_fraction | 0.365 | +| clip_range | 0.0683 | +| entropy_loss | -6.03 | +| explained_variance | 0.708 | +| learning_rate | 4.37e-05 | +| loss | -0.042 | +| n_updates | 67776 | +| policy_gradient_loss | -0.0233 | +| value_loss | 5.76e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1412 | +| iterations | 12991 | +| time_elapsed | 18838 | +| total_timesteps | 26605568 | +| train/ | | +| approx_kl | 0.011764048 | +| clip_fraction | 0.332 | +| clip_range | 0.0683 | +| entropy_loss | -6.25 | +| explained_variance | 0.338 | +| learning_rate | 4.37e-05 | +| loss | -0.0253 | +| n_updates | 67780 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000203 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1412 | +| iterations | 12992 | +| time_elapsed | 18840 | +| total_timesteps | 26607616 | +| train/ | | +| approx_kl | 0.01005207 | +| clip_fraction | 0.322 | +| clip_range | 0.0683 | +| entropy_loss | -6.38 | +| explained_variance | 0.23 | +| learning_rate | 4.37e-05 | +| loss | -0.0278 | +| n_updates | 67784 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000316 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1412 | +| iterations | 12993 | +| time_elapsed | 18841 | +| total_timesteps | 26609664 | +| train/ | | +| approx_kl | 0.013196209 | +| clip_fraction | 0.357 | +| clip_range | 0.0683 | +| entropy_loss | -6.14 | +| explained_variance | 0.444 | +| learning_rate | 4.37e-05 | +| loss | -0.0204 | +| n_updates | 67788 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000225 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1412 | +| iterations | 12994 | +| time_elapsed | 18843 | +| total_timesteps | 26611712 | +| train/ | | +| approx_kl | 0.015532564 | +| clip_fraction | 0.367 | +| clip_range | 0.0683 | +| entropy_loss | -6.42 | +| explained_variance | 0.193 | +| learning_rate | 4.37e-05 | +| loss | -0.0295 | +| n_updates | 67792 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000176 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1412 | +| iterations | 12995 | +| time_elapsed | 18844 | +| total_timesteps | 26613760 | +| train/ | | +| approx_kl | 0.014409938 | +| clip_fraction | 0.334 | +| clip_range | 0.0683 | +| entropy_loss | -6.43 | +| explained_variance | 0.226 | +| learning_rate | 4.37e-05 | +| loss | -0.0301 | +| n_updates | 67796 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000295 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1412 | +| iterations | 12996 | +| time_elapsed | 18846 | +| total_timesteps | 26615808 | +| train/ | | +| approx_kl | 0.01311891 | +| clip_fraction | 0.36 | +| clip_range | 0.0683 | +| entropy_loss | -6.23 | +| explained_variance | 0.339 | +| learning_rate | 4.37e-05 | +| loss | -0.0223 | +| n_updates | 67800 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000266 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1412 | +| iterations | 12997 | +| time_elapsed | 18847 | +| total_timesteps | 26617856 | +| train/ | | +| approx_kl | 0.014805824 | +| clip_fraction | 0.368 | +| clip_range | 0.0683 | +| entropy_loss | -5.78 | +| explained_variance | 0.61 | +| learning_rate | 4.37e-05 | +| loss | -0.0281 | +| n_updates | 67804 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000156 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1412 | +| iterations | 12998 | +| time_elapsed | 18849 | +| total_timesteps | 26619904 | +| train/ | | +| approx_kl | 0.014008352 | +| clip_fraction | 0.352 | +| clip_range | 0.0683 | +| entropy_loss | -5.88 | +| explained_variance | 0.593 | +| learning_rate | 4.37e-05 | +| loss | -0.0284 | +| n_updates | 67808 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000165 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1412 | +| iterations | 12999 | +| time_elapsed | 18850 | +| total_timesteps | 26621952 | +| train/ | | +| approx_kl | 0.012676469 | +| clip_fraction | 0.329 | +| clip_range | 0.0683 | +| entropy_loss | -6.04 | +| explained_variance | 0.297 | +| learning_rate | 4.37e-05 | +| loss | -0.0305 | +| n_updates | 67812 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000209 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1412 | +| iterations | 13000 | +| time_elapsed | 18852 | +| total_timesteps | 26624000 | +| train/ | | +| approx_kl | 0.011930823 | +| clip_fraction | 0.337 | +| clip_range | 0.0683 | +| entropy_loss | -6.15 | +| explained_variance | 0.437 | +| learning_rate | 4.37e-05 | +| loss | -0.0311 | +| n_updates | 67816 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000166 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1412 | +| iterations | 13001 | +| time_elapsed | 18853 | +| total_timesteps | 26626048 | +| train/ | | +| approx_kl | 0.012857647 | +| clip_fraction | 0.323 | +| clip_range | 0.0683 | +| entropy_loss | -6.37 | +| explained_variance | 0.288 | +| learning_rate | 4.37e-05 | +| loss | -0.0215 | +| n_updates | 67820 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000335 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1412 | +| iterations | 13002 | +| time_elapsed | 18855 | +| total_timesteps | 26628096 | +| train/ | | +| approx_kl | 0.012772603 | +| clip_fraction | 0.313 | +| clip_range | 0.0683 | +| entropy_loss | -6.2 | +| explained_variance | 0.323 | +| learning_rate | 4.37e-05 | +| loss | -0.0273 | +| n_updates | 67824 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000268 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1412 | +| iterations | 13003 | +| time_elapsed | 18856 | +| total_timesteps | 26630144 | +| train/ | | +| approx_kl | 0.012424749 | +| clip_fraction | 0.322 | +| clip_range | 0.0683 | +| entropy_loss | -5.61 | +| explained_variance | 0.532 | +| learning_rate | 4.37e-05 | +| loss | -0.031 | +| n_updates | 67828 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000211 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1412 | +| iterations | 13004 | +| time_elapsed | 18858 | +| total_timesteps | 26632192 | +| train/ | | +| approx_kl | 0.015552058 | +| clip_fraction | 0.358 | +| clip_range | 0.0683 | +| entropy_loss | -5.99 | +| explained_variance | 0.0972 | +| learning_rate | 4.37e-05 | +| loss | -0.0349 | +| n_updates | 67832 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000134 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1412 | +| iterations | 13005 | +| time_elapsed | 18859 | +| total_timesteps | 26634240 | +| train/ | | +| approx_kl | 0.013718076 | +| clip_fraction | 0.339 | +| clip_range | 0.0683 | +| entropy_loss | -6.01 | +| explained_variance | 0.536 | +| learning_rate | 4.37e-05 | +| loss | -0.0273 | +| n_updates | 67836 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000134 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1412 | +| iterations | 13006 | +| time_elapsed | 18861 | +| total_timesteps | 26636288 | +| train/ | | +| approx_kl | 0.013863165 | +| clip_fraction | 0.334 | +| clip_range | 0.0683 | +| entropy_loss | -6.58 | +| explained_variance | -0.309 | +| learning_rate | 4.37e-05 | +| loss | -0.0313 | +| n_updates | 67840 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000116 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1412 | +| iterations | 13007 | +| time_elapsed | 18862 | +| total_timesteps | 26638336 | +| train/ | | +| approx_kl | 0.013862569 | +| clip_fraction | 0.337 | +| clip_range | 0.0683 | +| entropy_loss | -6.23 | +| explained_variance | 0.543 | +| learning_rate | 4.37e-05 | +| loss | -0.0316 | +| n_updates | 67844 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000111 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1412 | +| iterations | 13008 | +| time_elapsed | 18864 | +| total_timesteps | 26640384 | +| train/ | | +| approx_kl | 0.013485834 | +| clip_fraction | 0.329 | +| clip_range | 0.0683 | +| entropy_loss | -5.71 | +| explained_variance | 0.52 | +| learning_rate | 4.37e-05 | +| loss | -0.0308 | +| n_updates | 67848 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000132 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1412 | +| iterations | 13009 | +| time_elapsed | 18865 | +| total_timesteps | 26642432 | +| train/ | | +| approx_kl | 0.012055283 | +| clip_fraction | 0.357 | +| clip_range | 0.0683 | +| entropy_loss | -5.87 | +| explained_variance | 0.748 | +| learning_rate | 4.37e-05 | +| loss | -0.0343 | +| n_updates | 67852 | +| policy_gradient_loss | -0.0209 | +| value_loss | 7.88e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1412 | +| iterations | 13010 | +| time_elapsed | 18867 | +| total_timesteps | 26644480 | +| train/ | | +| approx_kl | 0.011496697 | +| clip_fraction | 0.317 | +| clip_range | 0.0683 | +| entropy_loss | -6.19 | +| explained_variance | 0.375 | +| learning_rate | 4.37e-05 | +| loss | -0.0291 | +| n_updates | 67856 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000295 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1412 | +| iterations | 13011 | +| time_elapsed | 18868 | +| total_timesteps | 26646528 | +| train/ | | +| approx_kl | 0.011301573 | +| clip_fraction | 0.314 | +| clip_range | 0.0683 | +| entropy_loss | -6.2 | +| explained_variance | 0.273 | +| learning_rate | 4.37e-05 | +| loss | -0.0289 | +| n_updates | 67860 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000144 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1412 | +| iterations | 13012 | +| time_elapsed | 18870 | +| total_timesteps | 26648576 | +| train/ | | +| approx_kl | 0.011228131 | +| clip_fraction | 0.336 | +| clip_range | 0.0683 | +| entropy_loss | -6.21 | +| explained_variance | 0.409 | +| learning_rate | 4.37e-05 | +| loss | -0.0344 | +| n_updates | 67864 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000134 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1412 | +| iterations | 13013 | +| time_elapsed | 18871 | +| total_timesteps | 26650624 | +| train/ | | +| approx_kl | 0.013803732 | +| clip_fraction | 0.344 | +| clip_range | 0.0683 | +| entropy_loss | -6.1 | +| explained_variance | 0.547 | +| learning_rate | 4.37e-05 | +| loss | -0.0282 | +| n_updates | 67868 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000136 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1412 | +| iterations | 13014 | +| time_elapsed | 18873 | +| total_timesteps | 26652672 | +| train/ | | +| approx_kl | 0.015112298 | +| clip_fraction | 0.36 | +| clip_range | 0.0683 | +| entropy_loss | -6.53 | +| explained_variance | -0.139 | +| learning_rate | 4.37e-05 | +| loss | -0.0293 | +| n_updates | 67872 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000102 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1412 | +| iterations | 13015 | +| time_elapsed | 18875 | +| total_timesteps | 26654720 | +| train/ | | +| approx_kl | 0.013019988 | +| clip_fraction | 0.349 | +| clip_range | 0.0683 | +| entropy_loss | -6.59 | +| explained_variance | 0.5 | +| learning_rate | 4.37e-05 | +| loss | -0.0339 | +| n_updates | 67876 | +| policy_gradient_loss | -0.0211 | +| value_loss | 8.14e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1412 | +| iterations | 13016 | +| time_elapsed | 18876 | +| total_timesteps | 26656768 | +| train/ | | +| approx_kl | 0.014816819 | +| clip_fraction | 0.36 | +| clip_range | 0.0683 | +| entropy_loss | -6.29 | +| explained_variance | 0.369 | +| learning_rate | 4.37e-05 | +| loss | -0.0274 | +| n_updates | 67880 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000115 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1412 | +| iterations | 13017 | +| time_elapsed | 18878 | +| total_timesteps | 26658816 | +| train/ | | +| approx_kl | 0.017432626 | +| clip_fraction | 0.325 | +| clip_range | 0.0683 | +| entropy_loss | -5.63 | +| explained_variance | 0.645 | +| learning_rate | 4.37e-05 | +| loss | -0.031 | +| n_updates | 67884 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.00012 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1412 | +| iterations | 13018 | +| time_elapsed | 18879 | +| total_timesteps | 26660864 | +| train/ | | +| approx_kl | 0.013109389 | +| clip_fraction | 0.357 | +| clip_range | 0.0683 | +| entropy_loss | -5.86 | +| explained_variance | 0.488 | +| learning_rate | 4.37e-05 | +| loss | -0.0284 | +| n_updates | 67888 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000142 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1412 | +| iterations | 13019 | +| time_elapsed | 18881 | +| total_timesteps | 26662912 | +| train/ | | +| approx_kl | 0.01578712 | +| clip_fraction | 0.343 | +| clip_range | 0.0683 | +| entropy_loss | -5.84 | +| explained_variance | 0.595 | +| learning_rate | 4.37e-05 | +| loss | -0.0268 | +| n_updates | 67892 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000125 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1412 | +| iterations | 13020 | +| time_elapsed | 18882 | +| total_timesteps | 26664960 | +| train/ | | +| approx_kl | 0.011430925 | +| clip_fraction | 0.317 | +| clip_range | 0.0683 | +| entropy_loss | -5.93 | +| explained_variance | 0.488 | +| learning_rate | 4.37e-05 | +| loss | -0.0314 | +| n_updates | 67896 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000169 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1412 | +| iterations | 13021 | +| time_elapsed | 18884 | +| total_timesteps | 26667008 | +| train/ | | +| approx_kl | 0.0120904865 | +| clip_fraction | 0.352 | +| clip_range | 0.0683 | +| entropy_loss | -6.13 | +| explained_variance | 0.452 | +| learning_rate | 4.37e-05 | +| loss | -0.0306 | +| n_updates | 67900 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000141 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1412 | +| iterations | 13022 | +| time_elapsed | 18885 | +| total_timesteps | 26669056 | +| train/ | | +| approx_kl | 0.013571441 | +| clip_fraction | 0.324 | +| clip_range | 0.0683 | +| entropy_loss | -6.01 | +| explained_variance | 0.328 | +| learning_rate | 4.37e-05 | +| loss | -0.0187 | +| n_updates | 67904 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000405 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1412 | +| iterations | 13023 | +| time_elapsed | 18887 | +| total_timesteps | 26671104 | +| train/ | | +| approx_kl | 0.016220015 | +| clip_fraction | 0.386 | +| clip_range | 0.0683 | +| entropy_loss | -6.19 | +| explained_variance | 0.0915 | +| learning_rate | 4.37e-05 | +| loss | -0.0371 | +| n_updates | 67908 | +| policy_gradient_loss | -0.0238 | +| value_loss | 0.000102 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1412 | +| iterations | 13024 | +| time_elapsed | 18888 | +| total_timesteps | 26673152 | +| train/ | | +| approx_kl | 0.013458895 | +| clip_fraction | 0.351 | +| clip_range | 0.0683 | +| entropy_loss | -6.09 | +| explained_variance | 0.303 | +| learning_rate | 4.37e-05 | +| loss | -0.0288 | +| n_updates | 67912 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000223 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1412 | +| iterations | 13025 | +| time_elapsed | 18890 | +| total_timesteps | 26675200 | +| train/ | | +| approx_kl | 0.013230909 | +| clip_fraction | 0.328 | +| clip_range | 0.0683 | +| entropy_loss | -5.53 | +| explained_variance | 0.606 | +| learning_rate | 4.37e-05 | +| loss | -0.0268 | +| n_updates | 67916 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000164 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1412 | +| iterations | 13026 | +| time_elapsed | 18891 | +| total_timesteps | 26677248 | +| train/ | | +| approx_kl | 0.012488551 | +| clip_fraction | 0.363 | +| clip_range | 0.0683 | +| entropy_loss | -6.35 | +| explained_variance | 0.108 | +| learning_rate | 4.37e-05 | +| loss | -0.0333 | +| n_updates | 67920 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000145 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1412 | +| iterations | 13027 | +| time_elapsed | 18893 | +| total_timesteps | 26679296 | +| train/ | | +| approx_kl | 0.015847983 | +| clip_fraction | 0.358 | +| clip_range | 0.0683 | +| entropy_loss | -6.36 | +| explained_variance | 0.282 | +| learning_rate | 4.37e-05 | +| loss | -0.0377 | +| n_updates | 67924 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000176 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1412 | +| iterations | 13028 | +| time_elapsed | 18894 | +| total_timesteps | 26681344 | +| train/ | | +| approx_kl | 0.014539646 | +| clip_fraction | 0.354 | +| clip_range | 0.0683 | +| entropy_loss | -6.18 | +| explained_variance | 0.487 | +| learning_rate | 4.37e-05 | +| loss | -0.0311 | +| n_updates | 67928 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000116 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1412 | +| iterations | 13029 | +| time_elapsed | 18896 | +| total_timesteps | 26683392 | +| train/ | | +| approx_kl | 0.015158789 | +| clip_fraction | 0.359 | +| clip_range | 0.0683 | +| entropy_loss | -5.96 | +| explained_variance | 0.698 | +| learning_rate | 4.37e-05 | +| loss | -0.0298 | +| n_updates | 67932 | +| policy_gradient_loss | -0.0207 | +| value_loss | 7.68e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1412 | +| iterations | 13030 | +| time_elapsed | 18897 | +| total_timesteps | 26685440 | +| train/ | | +| approx_kl | 0.013310209 | +| clip_fraction | 0.328 | +| clip_range | 0.0683 | +| entropy_loss | -6.27 | +| explained_variance | 0.248 | +| learning_rate | 4.37e-05 | +| loss | -0.0245 | +| n_updates | 67936 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.00031 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1412 | +| iterations | 13031 | +| time_elapsed | 18899 | +| total_timesteps | 26687488 | +| train/ | | +| approx_kl | 0.011798982 | +| clip_fraction | 0.312 | +| clip_range | 0.0683 | +| entropy_loss | -6.39 | +| explained_variance | 0.387 | +| learning_rate | 4.37e-05 | +| loss | -0.0252 | +| n_updates | 67940 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000232 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1412 | +| iterations | 13032 | +| time_elapsed | 18900 | +| total_timesteps | 26689536 | +| train/ | | +| approx_kl | 0.009444226 | +| clip_fraction | 0.331 | +| clip_range | 0.0683 | +| entropy_loss | -6.77 | +| explained_variance | -0.23 | +| learning_rate | 4.37e-05 | +| loss | -0.0305 | +| n_updates | 67944 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000231 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1412 | +| iterations | 13033 | +| time_elapsed | 18902 | +| total_timesteps | 26691584 | +| train/ | | +| approx_kl | 0.011605906 | +| clip_fraction | 0.345 | +| clip_range | 0.0683 | +| entropy_loss | -6.6 | +| explained_variance | 0.0817 | +| learning_rate | 4.37e-05 | +| loss | -0.0261 | +| n_updates | 67948 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000466 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1412 | +| iterations | 13034 | +| time_elapsed | 18903 | +| total_timesteps | 26693632 | +| train/ | | +| approx_kl | 0.014154367 | +| clip_fraction | 0.345 | +| clip_range | 0.0683 | +| entropy_loss | -5.99 | +| explained_variance | 0.356 | +| learning_rate | 4.37e-05 | +| loss | -0.0305 | +| n_updates | 67952 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000283 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1412 | +| iterations | 13035 | +| time_elapsed | 18905 | +| total_timesteps | 26695680 | +| train/ | | +| approx_kl | 0.010734519 | +| clip_fraction | 0.317 | +| clip_range | 0.0683 | +| entropy_loss | -5.64 | +| explained_variance | 0.357 | +| learning_rate | 4.37e-05 | +| loss | -0.0267 | +| n_updates | 67956 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000433 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1412 | +| iterations | 13036 | +| time_elapsed | 18906 | +| total_timesteps | 26697728 | +| train/ | | +| approx_kl | 0.014512329 | +| clip_fraction | 0.358 | +| clip_range | 0.0683 | +| entropy_loss | -5.53 | +| explained_variance | 0.666 | +| learning_rate | 4.37e-05 | +| loss | -0.0391 | +| n_updates | 67960 | +| policy_gradient_loss | -0.0224 | +| value_loss | 8.23e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1412 | +| iterations | 13037 | +| time_elapsed | 18908 | +| total_timesteps | 26699776 | +| train/ | | +| approx_kl | 0.013739024 | +| clip_fraction | 0.359 | +| clip_range | 0.0683 | +| entropy_loss | -6.33 | +| explained_variance | -0.0549 | +| learning_rate | 4.37e-05 | +| loss | -0.0365 | +| n_updates | 67964 | +| policy_gradient_loss | -0.0218 | +| value_loss | 9.86e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1412 | +| iterations | 13038 | +| time_elapsed | 18909 | +| total_timesteps | 26701824 | +| train/ | | +| approx_kl | 0.014613689 | +| clip_fraction | 0.333 | +| clip_range | 0.0683 | +| entropy_loss | -5.86 | +| explained_variance | 0.447 | +| learning_rate | 4.37e-05 | +| loss | -0.0266 | +| n_updates | 67968 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000244 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1412 | +| iterations | 13039 | +| time_elapsed | 18911 | +| total_timesteps | 26703872 | +| train/ | | +| approx_kl | 0.014056861 | +| clip_fraction | 0.358 | +| clip_range | 0.0683 | +| entropy_loss | -6.12 | +| explained_variance | 0.214 | +| learning_rate | 4.37e-05 | +| loss | -0.0311 | +| n_updates | 67972 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.00024 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1412 | +| iterations | 13040 | +| time_elapsed | 18912 | +| total_timesteps | 26705920 | +| train/ | | +| approx_kl | 0.0146439355 | +| clip_fraction | 0.353 | +| clip_range | 0.0683 | +| entropy_loss | -6.31 | +| explained_variance | 0.28 | +| learning_rate | 4.37e-05 | +| loss | -0.0383 | +| n_updates | 67976 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000153 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1412 | +| iterations | 13041 | +| time_elapsed | 18914 | +| total_timesteps | 26707968 | +| train/ | | +| approx_kl | 0.015594453 | +| clip_fraction | 0.36 | +| clip_range | 0.0683 | +| entropy_loss | -6.15 | +| explained_variance | 0.383 | +| learning_rate | 4.37e-05 | +| loss | -0.0296 | +| n_updates | 67980 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.00011 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1412 | +| iterations | 13042 | +| time_elapsed | 18915 | +| total_timesteps | 26710016 | +| train/ | | +| approx_kl | 0.014292883 | +| clip_fraction | 0.329 | +| clip_range | 0.0683 | +| entropy_loss | -6.26 | +| explained_variance | 0.358 | +| learning_rate | 4.37e-05 | +| loss | -0.029 | +| n_updates | 67984 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000232 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1412 | +| iterations | 13043 | +| time_elapsed | 18917 | +| total_timesteps | 26712064 | +| train/ | | +| approx_kl | 0.011188731 | +| clip_fraction | 0.296 | +| clip_range | 0.0683 | +| entropy_loss | -5.84 | +| explained_variance | 0.429 | +| learning_rate | 4.37e-05 | +| loss | -0.0238 | +| n_updates | 67988 | +| policy_gradient_loss | -0.014 | +| value_loss | 0.000333 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1412 | +| iterations | 13044 | +| time_elapsed | 18918 | +| total_timesteps | 26714112 | +| train/ | | +| approx_kl | 0.015427436 | +| clip_fraction | 0.367 | +| clip_range | 0.0683 | +| entropy_loss | -5.96 | +| explained_variance | 0.583 | +| learning_rate | 4.37e-05 | +| loss | -0.0321 | +| n_updates | 67992 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000106 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1412 | +| iterations | 13045 | +| time_elapsed | 18920 | +| total_timesteps | 26716160 | +| train/ | | +| approx_kl | 0.013990194 | +| clip_fraction | 0.347 | +| clip_range | 0.0683 | +| entropy_loss | -5.99 | +| explained_variance | 0.407 | +| learning_rate | 4.37e-05 | +| loss | -0.0366 | +| n_updates | 67996 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.00015 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1412 | +| iterations | 13046 | +| time_elapsed | 18921 | +| total_timesteps | 26718208 | +| train/ | | +| approx_kl | 0.011232622 | +| clip_fraction | 0.317 | +| clip_range | 0.0683 | +| entropy_loss | -5.93 | +| explained_variance | 0.491 | +| learning_rate | 4.37e-05 | +| loss | -0.0301 | +| n_updates | 68000 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000235 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1412 | +| iterations | 13047 | +| time_elapsed | 18923 | +| total_timesteps | 26720256 | +| train/ | | +| approx_kl | 0.01499738 | +| clip_fraction | 0.362 | +| clip_range | 0.0683 | +| entropy_loss | -6.22 | +| explained_variance | 0.389 | +| learning_rate | 4.37e-05 | +| loss | -0.0337 | +| n_updates | 68004 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000114 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1412 | +| iterations | 13048 | +| time_elapsed | 18924 | +| total_timesteps | 26722304 | +| train/ | | +| approx_kl | 0.016282614 | +| clip_fraction | 0.368 | +| clip_range | 0.0683 | +| entropy_loss | -5.28 | +| explained_variance | 0.497 | +| learning_rate | 4.37e-05 | +| loss | -0.0293 | +| n_updates | 68008 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000187 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1412 | +| iterations | 13049 | +| time_elapsed | 18926 | +| total_timesteps | 26724352 | +| train/ | | +| approx_kl | 0.015949678 | +| clip_fraction | 0.385 | +| clip_range | 0.0683 | +| entropy_loss | -5.65 | +| explained_variance | 0.692 | +| learning_rate | 4.37e-05 | +| loss | -0.0379 | +| n_updates | 68012 | +| policy_gradient_loss | -0.0228 | +| value_loss | 9.77e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1412 | +| iterations | 13050 | +| time_elapsed | 18927 | +| total_timesteps | 26726400 | +| train/ | | +| approx_kl | 0.011207402 | +| clip_fraction | 0.321 | +| clip_range | 0.0683 | +| entropy_loss | -5.96 | +| explained_variance | 0.342 | +| learning_rate | 4.37e-05 | +| loss | -0.0263 | +| n_updates | 68016 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000289 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1412 | +| iterations | 13051 | +| time_elapsed | 18929 | +| total_timesteps | 26728448 | +| train/ | | +| approx_kl | 0.011448042 | +| clip_fraction | 0.315 | +| clip_range | 0.0683 | +| entropy_loss | -6.23 | +| explained_variance | 0.208 | +| learning_rate | 4.37e-05 | +| loss | -0.0313 | +| n_updates | 68020 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000276 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1412 | +| iterations | 13052 | +| time_elapsed | 18930 | +| total_timesteps | 26730496 | +| train/ | | +| approx_kl | 0.0108993 | +| clip_fraction | 0.333 | +| clip_range | 0.0683 | +| entropy_loss | -6.41 | +| explained_variance | 0.324 | +| learning_rate | 4.37e-05 | +| loss | -0.0294 | +| n_updates | 68024 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000212 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1412 | +| iterations | 13053 | +| time_elapsed | 18932 | +| total_timesteps | 26732544 | +| train/ | | +| approx_kl | 0.012900783 | +| clip_fraction | 0.34 | +| clip_range | 0.0683 | +| entropy_loss | -6.39 | +| explained_variance | 0.256 | +| learning_rate | 4.37e-05 | +| loss | -0.0277 | +| n_updates | 68028 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000265 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1412 | +| iterations | 13054 | +| time_elapsed | 18933 | +| total_timesteps | 26734592 | +| train/ | | +| approx_kl | 0.015619565 | +| clip_fraction | 0.366 | +| clip_range | 0.0683 | +| entropy_loss | -5.79 | +| explained_variance | 0.211 | +| learning_rate | 4.37e-05 | +| loss | -0.0318 | +| n_updates | 68032 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000417 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1411 | +| iterations | 13055 | +| time_elapsed | 18935 | +| total_timesteps | 26736640 | +| train/ | | +| approx_kl | 0.01654815 | +| clip_fraction | 0.365 | +| clip_range | 0.0683 | +| entropy_loss | -6.07 | +| explained_variance | -0.302 | +| learning_rate | 4.37e-05 | +| loss | -0.0328 | +| n_updates | 68036 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000145 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1411 | +| iterations | 13056 | +| time_elapsed | 18936 | +| total_timesteps | 26738688 | +| train/ | | +| approx_kl | 0.014549378 | +| clip_fraction | 0.367 | +| clip_range | 0.0683 | +| entropy_loss | -6.02 | +| explained_variance | 0.497 | +| learning_rate | 4.37e-05 | +| loss | -0.0297 | +| n_updates | 68040 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000132 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1411 | +| iterations | 13057 | +| time_elapsed | 18938 | +| total_timesteps | 26740736 | +| train/ | | +| approx_kl | 0.016049903 | +| clip_fraction | 0.359 | +| clip_range | 0.0683 | +| entropy_loss | -6.16 | +| explained_variance | -0.0586 | +| learning_rate | 4.36e-05 | +| loss | -0.0287 | +| n_updates | 68044 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.00015 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1411 | +| iterations | 13058 | +| time_elapsed | 18939 | +| total_timesteps | 26742784 | +| train/ | | +| approx_kl | 0.014475258 | +| clip_fraction | 0.347 | +| clip_range | 0.0683 | +| entropy_loss | -6.51 | +| explained_variance | 0.262 | +| learning_rate | 4.36e-05 | +| loss | -0.0308 | +| n_updates | 68048 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000228 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1411 | +| iterations | 13059 | +| time_elapsed | 18941 | +| total_timesteps | 26744832 | +| train/ | | +| approx_kl | 0.013979465 | +| clip_fraction | 0.335 | +| clip_range | 0.0683 | +| entropy_loss | -5.8 | +| explained_variance | 0.508 | +| learning_rate | 4.36e-05 | +| loss | -0.0362 | +| n_updates | 68052 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000191 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1411 | +| iterations | 13060 | +| time_elapsed | 18942 | +| total_timesteps | 26746880 | +| train/ | | +| approx_kl | 0.012092367 | +| clip_fraction | 0.341 | +| clip_range | 0.0683 | +| entropy_loss | -5.4 | +| explained_variance | 0.363 | +| learning_rate | 4.36e-05 | +| loss | -0.0308 | +| n_updates | 68056 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000343 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1411 | +| iterations | 13061 | +| time_elapsed | 18944 | +| total_timesteps | 26748928 | +| train/ | | +| approx_kl | 0.012770899 | +| clip_fraction | 0.348 | +| clip_range | 0.0683 | +| entropy_loss | -6.38 | +| explained_variance | 0.237 | +| learning_rate | 4.36e-05 | +| loss | -0.0259 | +| n_updates | 68060 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000199 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1411 | +| iterations | 13062 | +| time_elapsed | 18945 | +| total_timesteps | 26750976 | +| train/ | | +| approx_kl | 0.010059567 | +| clip_fraction | 0.332 | +| clip_range | 0.0683 | +| entropy_loss | -6.53 | +| explained_variance | 0.141 | +| learning_rate | 4.36e-05 | +| loss | -0.0244 | +| n_updates | 68064 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000437 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1411 | +| iterations | 13063 | +| time_elapsed | 18947 | +| total_timesteps | 26753024 | +| train/ | | +| approx_kl | 0.012870306 | +| clip_fraction | 0.34 | +| clip_range | 0.0683 | +| entropy_loss | -5.78 | +| explained_variance | 0.682 | +| learning_rate | 4.36e-05 | +| loss | -0.0296 | +| n_updates | 68068 | +| policy_gradient_loss | -0.0203 | +| value_loss | 9.42e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1411 | +| iterations | 13064 | +| time_elapsed | 18948 | +| total_timesteps | 26755072 | +| train/ | | +| approx_kl | 0.01452304 | +| clip_fraction | 0.357 | +| clip_range | 0.0683 | +| entropy_loss | -6.26 | +| explained_variance | 0.459 | +| learning_rate | 4.36e-05 | +| loss | -0.0278 | +| n_updates | 68072 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000106 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1411 | +| iterations | 13065 | +| time_elapsed | 18950 | +| total_timesteps | 26757120 | +| train/ | | +| approx_kl | 0.012728475 | +| clip_fraction | 0.355 | +| clip_range | 0.0683 | +| entropy_loss | -6.29 | +| explained_variance | 0.382 | +| learning_rate | 4.36e-05 | +| loss | -0.0255 | +| n_updates | 68076 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000177 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1411 | +| iterations | 13066 | +| time_elapsed | 18951 | +| total_timesteps | 26759168 | +| train/ | | +| approx_kl | 0.012588103 | +| clip_fraction | 0.328 | +| clip_range | 0.0683 | +| entropy_loss | -5.63 | +| explained_variance | 0.708 | +| learning_rate | 4.36e-05 | +| loss | -0.0265 | +| n_updates | 68080 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000126 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1411 | +| iterations | 13067 | +| time_elapsed | 18953 | +| total_timesteps | 26761216 | +| train/ | | +| approx_kl | 0.014382429 | +| clip_fraction | 0.323 | +| clip_range | 0.0683 | +| entropy_loss | -5.77 | +| explained_variance | 0.571 | +| learning_rate | 4.36e-05 | +| loss | -0.0292 | +| n_updates | 68084 | +| policy_gradient_loss | -0.0184 | +| value_loss | 9.11e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1411 | +| iterations | 13068 | +| time_elapsed | 18954 | +| total_timesteps | 26763264 | +| train/ | | +| approx_kl | 0.018144865 | +| clip_fraction | 0.357 | +| clip_range | 0.0683 | +| entropy_loss | -6.49 | +| explained_variance | -0.0127 | +| learning_rate | 4.36e-05 | +| loss | -0.0283 | +| n_updates | 68088 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000202 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1411 | +| iterations | 13069 | +| time_elapsed | 18956 | +| total_timesteps | 26765312 | +| train/ | | +| approx_kl | 0.015820852 | +| clip_fraction | 0.324 | +| clip_range | 0.0683 | +| entropy_loss | -6.19 | +| explained_variance | 0.298 | +| learning_rate | 4.36e-05 | +| loss | -0.0215 | +| n_updates | 68092 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.000234 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1411 | +| iterations | 13070 | +| time_elapsed | 18957 | +| total_timesteps | 26767360 | +| train/ | | +| approx_kl | 0.01805612 | +| clip_fraction | 0.375 | +| clip_range | 0.0683 | +| entropy_loss | -6.4 | +| explained_variance | 0.0995 | +| learning_rate | 4.36e-05 | +| loss | -0.0292 | +| n_updates | 68096 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000252 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1411 | +| iterations | 13071 | +| time_elapsed | 18959 | +| total_timesteps | 26769408 | +| train/ | | +| approx_kl | 0.015549958 | +| clip_fraction | 0.347 | +| clip_range | 0.0683 | +| entropy_loss | -5.37 | +| explained_variance | 0.67 | +| learning_rate | 4.36e-05 | +| loss | -0.0299 | +| n_updates | 68100 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000124 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1411 | +| iterations | 13072 | +| time_elapsed | 18960 | +| total_timesteps | 26771456 | +| train/ | | +| approx_kl | 0.013475118 | +| clip_fraction | 0.345 | +| clip_range | 0.0683 | +| entropy_loss | -6.15 | +| explained_variance | -0.0575 | +| learning_rate | 4.36e-05 | +| loss | -0.0261 | +| n_updates | 68104 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000157 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1411 | +| iterations | 13073 | +| time_elapsed | 18962 | +| total_timesteps | 26773504 | +| train/ | | +| approx_kl | 0.011896022 | +| clip_fraction | 0.371 | +| clip_range | 0.0683 | +| entropy_loss | -6.23 | +| explained_variance | 0.315 | +| learning_rate | 4.36e-05 | +| loss | -0.0318 | +| n_updates | 68108 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000165 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1411 | +| iterations | 13074 | +| time_elapsed | 18963 | +| total_timesteps | 26775552 | +| train/ | | +| approx_kl | 0.012008059 | +| clip_fraction | 0.354 | +| clip_range | 0.0683 | +| entropy_loss | -6.38 | +| explained_variance | 0.268 | +| learning_rate | 4.36e-05 | +| loss | -0.0253 | +| n_updates | 68112 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000227 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1411 | +| iterations | 13075 | +| time_elapsed | 18965 | +| total_timesteps | 26777600 | +| train/ | | +| approx_kl | 0.010520217 | +| clip_fraction | 0.341 | +| clip_range | 0.0683 | +| entropy_loss | -6.48 | +| explained_variance | 0.236 | +| learning_rate | 4.36e-05 | +| loss | -0.026 | +| n_updates | 68116 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000284 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1411 | +| iterations | 13076 | +| time_elapsed | 18966 | +| total_timesteps | 26779648 | +| train/ | | +| approx_kl | 0.01114686 | +| clip_fraction | 0.341 | +| clip_range | 0.0683 | +| entropy_loss | -6.22 | +| explained_variance | 0.346 | +| learning_rate | 4.36e-05 | +| loss | -0.0285 | +| n_updates | 68120 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000281 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1411 | +| iterations | 13077 | +| time_elapsed | 18968 | +| total_timesteps | 26781696 | +| train/ | | +| approx_kl | 0.012242038 | +| clip_fraction | 0.339 | +| clip_range | 0.0683 | +| entropy_loss | -6.06 | +| explained_variance | 0.603 | +| learning_rate | 4.36e-05 | +| loss | -0.03 | +| n_updates | 68124 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000118 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.388 | +| time/ | | +| fps | 1411 | +| iterations | 13078 | +| time_elapsed | 18969 | +| total_timesteps | 26783744 | +| train/ | | +| approx_kl | 0.012085206 | +| clip_fraction | 0.317 | +| clip_range | 0.0683 | +| entropy_loss | -5.88 | +| explained_variance | 0.472 | +| learning_rate | 4.36e-05 | +| loss | -0.032 | +| n_updates | 68128 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000176 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.397 | +| time/ | | +| fps | 1411 | +| iterations | 13079 | +| time_elapsed | 18971 | +| total_timesteps | 26785792 | +| train/ | | +| approx_kl | 0.013903864 | +| clip_fraction | 0.319 | +| clip_range | 0.0683 | +| entropy_loss | -6.33 | +| explained_variance | 0.185 | +| learning_rate | 4.36e-05 | +| loss | -0.0222 | +| n_updates | 68132 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000373 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.397 | +| time/ | | +| fps | 1411 | +| iterations | 13080 | +| time_elapsed | 18973 | +| total_timesteps | 26787840 | +| train/ | | +| approx_kl | 0.012366409 | +| clip_fraction | 0.326 | +| clip_range | 0.0683 | +| entropy_loss | -5.46 | +| explained_variance | 0.446 | +| learning_rate | 4.36e-05 | +| loss | -0.0244 | +| n_updates | 68136 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000396 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.398 | +| time/ | | +| fps | 1411 | +| iterations | 13081 | +| time_elapsed | 18974 | +| total_timesteps | 26789888 | +| train/ | | +| approx_kl | 0.013484941 | +| clip_fraction | 0.362 | +| clip_range | 0.0683 | +| entropy_loss | -5.88 | +| explained_variance | 0.394 | +| learning_rate | 4.36e-05 | +| loss | -0.033 | +| n_updates | 68140 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000158 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.398 | +| time/ | | +| fps | 1411 | +| iterations | 13082 | +| time_elapsed | 18976 | +| total_timesteps | 26791936 | +| train/ | | +| approx_kl | 0.01029497 | +| clip_fraction | 0.346 | +| clip_range | 0.0683 | +| entropy_loss | -6.34 | +| explained_variance | 0.45 | +| learning_rate | 4.36e-05 | +| loss | -0.0264 | +| n_updates | 68144 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000184 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.401 | +| time/ | | +| fps | 1411 | +| iterations | 13083 | +| time_elapsed | 18977 | +| total_timesteps | 26793984 | +| train/ | | +| approx_kl | 0.011114155 | +| clip_fraction | 0.325 | +| clip_range | 0.0683 | +| entropy_loss | -6.43 | +| explained_variance | 0.28 | +| learning_rate | 4.36e-05 | +| loss | -0.0305 | +| n_updates | 68148 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000191 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.408 | +| time/ | | +| fps | 1411 | +| iterations | 13084 | +| time_elapsed | 18979 | +| total_timesteps | 26796032 | +| train/ | | +| approx_kl | 0.010061106 | +| clip_fraction | 0.328 | +| clip_range | 0.0683 | +| entropy_loss | -6.55 | +| explained_variance | 0.164 | +| learning_rate | 4.36e-05 | +| loss | -0.0245 | +| n_updates | 68152 | +| policy_gradient_loss | -0.0143 | +| value_loss | 0.000365 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.405 | +| time/ | | +| fps | 1411 | +| iterations | 13085 | +| time_elapsed | 18980 | +| total_timesteps | 26798080 | +| train/ | | +| approx_kl | 0.014124699 | +| clip_fraction | 0.335 | +| clip_range | 0.0683 | +| entropy_loss | -6.02 | +| explained_variance | 0.267 | +| learning_rate | 4.36e-05 | +| loss | -0.03 | +| n_updates | 68156 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000278 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.406 | +| time/ | | +| fps | 1411 | +| iterations | 13086 | +| time_elapsed | 18982 | +| total_timesteps | 26800128 | +| train/ | | +| approx_kl | 0.01228294 | +| clip_fraction | 0.361 | +| clip_range | 0.0683 | +| entropy_loss | -5.85 | +| explained_variance | 0.536 | +| learning_rate | 4.36e-05 | +| loss | -0.0332 | +| n_updates | 68160 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000126 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.404 | +| time/ | | +| fps | 1411 | +| iterations | 13087 | +| time_elapsed | 18983 | +| total_timesteps | 26802176 | +| train/ | | +| approx_kl | 0.01179196 | +| clip_fraction | 0.336 | +| clip_range | 0.0683 | +| entropy_loss | -5.62 | +| explained_variance | 0.554 | +| learning_rate | 4.36e-05 | +| loss | -0.03 | +| n_updates | 68164 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000251 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.403 | +| time/ | | +| fps | 1411 | +| iterations | 13088 | +| time_elapsed | 18985 | +| total_timesteps | 26804224 | +| train/ | | +| approx_kl | 0.015592557 | +| clip_fraction | 0.377 | +| clip_range | 0.0683 | +| entropy_loss | -6.1 | +| explained_variance | 0.315 | +| learning_rate | 4.36e-05 | +| loss | -0.0315 | +| n_updates | 68168 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000173 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.395 | +| time/ | | +| fps | 1411 | +| iterations | 13089 | +| time_elapsed | 18986 | +| total_timesteps | 26806272 | +| train/ | | +| approx_kl | 0.013825426 | +| clip_fraction | 0.357 | +| clip_range | 0.0683 | +| entropy_loss | -6.08 | +| explained_variance | 0.546 | +| learning_rate | 4.36e-05 | +| loss | -0.0348 | +| n_updates | 68172 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000128 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.399 | +| time/ | | +| fps | 1411 | +| iterations | 13090 | +| time_elapsed | 18988 | +| total_timesteps | 26808320 | +| train/ | | +| approx_kl | 0.013426112 | +| clip_fraction | 0.31 | +| clip_range | 0.0683 | +| entropy_loss | -6.21 | +| explained_variance | 0.447 | +| learning_rate | 4.36e-05 | +| loss | -0.0297 | +| n_updates | 68176 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000193 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.396 | +| time/ | | +| fps | 1411 | +| iterations | 13091 | +| time_elapsed | 18989 | +| total_timesteps | 26810368 | +| train/ | | +| approx_kl | 0.014920868 | +| clip_fraction | 0.361 | +| clip_range | 0.0683 | +| entropy_loss | -6.02 | +| explained_variance | 0.17 | +| learning_rate | 4.36e-05 | +| loss | -0.026 | +| n_updates | 68180 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000366 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.395 | +| time/ | | +| fps | 1411 | +| iterations | 13092 | +| time_elapsed | 18991 | +| total_timesteps | 26812416 | +| train/ | | +| approx_kl | 0.014138803 | +| clip_fraction | 0.353 | +| clip_range | 0.0683 | +| entropy_loss | -6.53 | +| explained_variance | -0.259 | +| learning_rate | 4.36e-05 | +| loss | -0.0313 | +| n_updates | 68184 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000132 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.399 | +| time/ | | +| fps | 1411 | +| iterations | 13093 | +| time_elapsed | 18992 | +| total_timesteps | 26814464 | +| train/ | | +| approx_kl | 0.0136830835 | +| clip_fraction | 0.335 | +| clip_range | 0.0683 | +| entropy_loss | -6.35 | +| explained_variance | 0.445 | +| learning_rate | 4.36e-05 | +| loss | -0.028 | +| n_updates | 68188 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.00016 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.399 | +| time/ | | +| fps | 1411 | +| iterations | 13094 | +| time_elapsed | 18994 | +| total_timesteps | 26816512 | +| train/ | | +| approx_kl | 0.010511145 | +| clip_fraction | 0.308 | +| clip_range | 0.0683 | +| entropy_loss | -6.25 | +| explained_variance | 0.26 | +| learning_rate | 4.36e-05 | +| loss | -0.0241 | +| n_updates | 68192 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000289 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.406 | +| time/ | | +| fps | 1411 | +| iterations | 13095 | +| time_elapsed | 18995 | +| total_timesteps | 26818560 | +| train/ | | +| approx_kl | 0.013805499 | +| clip_fraction | 0.32 | +| clip_range | 0.0683 | +| entropy_loss | -5.65 | +| explained_variance | 0.616 | +| learning_rate | 4.36e-05 | +| loss | -0.0255 | +| n_updates | 68196 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000189 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.4 | +| time/ | | +| fps | 1411 | +| iterations | 13096 | +| time_elapsed | 18997 | +| total_timesteps | 26820608 | +| train/ | | +| approx_kl | 0.012059612 | +| clip_fraction | 0.326 | +| clip_range | 0.0683 | +| entropy_loss | -6.09 | +| explained_variance | 0.139 | +| learning_rate | 4.36e-05 | +| loss | -0.034 | +| n_updates | 68200 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.00029 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.395 | +| time/ | | +| fps | 1411 | +| iterations | 13097 | +| time_elapsed | 18998 | +| total_timesteps | 26822656 | +| train/ | | +| approx_kl | 0.014985098 | +| clip_fraction | 0.363 | +| clip_range | 0.0683 | +| entropy_loss | -6.32 | +| explained_variance | 0.218 | +| learning_rate | 4.36e-05 | +| loss | -0.0315 | +| n_updates | 68204 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000182 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.401 | +| time/ | | +| fps | 1411 | +| iterations | 13098 | +| time_elapsed | 19000 | +| total_timesteps | 26824704 | +| train/ | | +| approx_kl | 0.014706101 | +| clip_fraction | 0.374 | +| clip_range | 0.0683 | +| entropy_loss | -5.81 | +| explained_variance | 0.802 | +| learning_rate | 4.36e-05 | +| loss | -0.0362 | +| n_updates | 68208 | +| policy_gradient_loss | -0.0238 | +| value_loss | 7.05e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.401 | +| time/ | | +| fps | 1411 | +| iterations | 13099 | +| time_elapsed | 19001 | +| total_timesteps | 26826752 | +| train/ | | +| approx_kl | 0.014225319 | +| clip_fraction | 0.337 | +| clip_range | 0.0683 | +| entropy_loss | -6.2 | +| explained_variance | 0.127 | +| learning_rate | 4.36e-05 | +| loss | -0.0295 | +| n_updates | 68212 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000211 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.401 | +| time/ | | +| fps | 1411 | +| iterations | 13100 | +| time_elapsed | 19003 | +| total_timesteps | 26828800 | +| train/ | | +| approx_kl | 0.013116699 | +| clip_fraction | 0.352 | +| clip_range | 0.0683 | +| entropy_loss | -6.3 | +| explained_variance | 0.462 | +| learning_rate | 4.36e-05 | +| loss | -0.0365 | +| n_updates | 68216 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000102 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.392 | +| time/ | | +| fps | 1411 | +| iterations | 13101 | +| time_elapsed | 19004 | +| total_timesteps | 26830848 | +| train/ | | +| approx_kl | 0.012964203 | +| clip_fraction | 0.353 | +| clip_range | 0.0683 | +| entropy_loss | -6.39 | +| explained_variance | 0.141 | +| learning_rate | 4.36e-05 | +| loss | -0.0315 | +| n_updates | 68220 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.392 | +| time/ | | +| fps | 1411 | +| iterations | 13102 | +| time_elapsed | 19006 | +| total_timesteps | 26832896 | +| train/ | | +| approx_kl | 0.011208986 | +| clip_fraction | 0.328 | +| clip_range | 0.0683 | +| entropy_loss | -5.67 | +| explained_variance | 0.647 | +| learning_rate | 4.36e-05 | +| loss | -0.0219 | +| n_updates | 68224 | +| policy_gradient_loss | -0.0142 | +| value_loss | 0.000186 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.392 | +| time/ | | +| fps | 1411 | +| iterations | 13103 | +| time_elapsed | 19008 | +| total_timesteps | 26834944 | +| train/ | | +| approx_kl | 0.017657716 | +| clip_fraction | 0.331 | +| clip_range | 0.0683 | +| entropy_loss | -5.71 | +| explained_variance | 0.627 | +| learning_rate | 4.36e-05 | +| loss | -0.0364 | +| n_updates | 68228 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000108 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.392 | +| time/ | | +| fps | 1411 | +| iterations | 13104 | +| time_elapsed | 19009 | +| total_timesteps | 26836992 | +| train/ | | +| approx_kl | 0.012303259 | +| clip_fraction | 0.325 | +| clip_range | 0.0683 | +| entropy_loss | -6.34 | +| explained_variance | 0.354 | +| learning_rate | 4.36e-05 | +| loss | -0.0278 | +| n_updates | 68232 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000137 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.394 | +| time/ | | +| fps | 1411 | +| iterations | 13105 | +| time_elapsed | 19010 | +| total_timesteps | 26839040 | +| train/ | | +| approx_kl | 0.01286673 | +| clip_fraction | 0.358 | +| clip_range | 0.0683 | +| entropy_loss | -6.24 | +| explained_variance | 0.342 | +| learning_rate | 4.36e-05 | +| loss | -0.0305 | +| n_updates | 68236 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000154 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.394 | +| time/ | | +| fps | 1411 | +| iterations | 13106 | +| time_elapsed | 19012 | +| total_timesteps | 26841088 | +| train/ | | +| approx_kl | 0.01110678 | +| clip_fraction | 0.314 | +| clip_range | 0.0683 | +| entropy_loss | -6.31 | +| explained_variance | 0.438 | +| learning_rate | 4.36e-05 | +| loss | -0.027 | +| n_updates | 68240 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000194 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.393 | +| time/ | | +| fps | 1411 | +| iterations | 13107 | +| time_elapsed | 19013 | +| total_timesteps | 26843136 | +| train/ | | +| approx_kl | 0.013165808 | +| clip_fraction | 0.355 | +| clip_range | 0.0683 | +| entropy_loss | -6.77 | +| explained_variance | -0.026 | +| learning_rate | 4.36e-05 | +| loss | -0.0303 | +| n_updates | 68244 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000216 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.397 | +| time/ | | +| fps | 1411 | +| iterations | 13108 | +| time_elapsed | 19015 | +| total_timesteps | 26845184 | +| train/ | | +| approx_kl | 0.012605999 | +| clip_fraction | 0.357 | +| clip_range | 0.0683 | +| entropy_loss | -6.34 | +| explained_variance | 0.475 | +| learning_rate | 4.36e-05 | +| loss | -0.0257 | +| n_updates | 68248 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000164 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.39 | +| time/ | | +| fps | 1411 | +| iterations | 13109 | +| time_elapsed | 19017 | +| total_timesteps | 26847232 | +| train/ | | +| approx_kl | 0.015822366 | +| clip_fraction | 0.364 | +| clip_range | 0.0683 | +| entropy_loss | -6.21 | +| explained_variance | 0.672 | +| learning_rate | 4.36e-05 | +| loss | -0.0331 | +| n_updates | 68252 | +| policy_gradient_loss | -0.0217 | +| value_loss | 7.05e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.385 | +| time/ | | +| fps | 1411 | +| iterations | 13110 | +| time_elapsed | 19018 | +| total_timesteps | 26849280 | +| train/ | | +| approx_kl | 0.012897923 | +| clip_fraction | 0.358 | +| clip_range | 0.0683 | +| entropy_loss | -5.93 | +| explained_variance | 0.655 | +| learning_rate | 4.36e-05 | +| loss | -0.0257 | +| n_updates | 68256 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000142 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.385 | +| time/ | | +| fps | 1411 | +| iterations | 13111 | +| time_elapsed | 19020 | +| total_timesteps | 26851328 | +| train/ | | +| approx_kl | 0.01555752 | +| clip_fraction | 0.369 | +| clip_range | 0.0683 | +| entropy_loss | -6.01 | +| explained_variance | 0.41 | +| learning_rate | 4.36e-05 | +| loss | -0.026 | +| n_updates | 68260 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000103 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.389 | +| time/ | | +| fps | 1411 | +| iterations | 13112 | +| time_elapsed | 19021 | +| total_timesteps | 26853376 | +| train/ | | +| approx_kl | 0.016185151 | +| clip_fraction | 0.362 | +| clip_range | 0.0683 | +| entropy_loss | -6.43 | +| explained_variance | 0.364 | +| learning_rate | 4.36e-05 | +| loss | -0.0268 | +| n_updates | 68264 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000122 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1411 | +| iterations | 13113 | +| time_elapsed | 19023 | +| total_timesteps | 26855424 | +| train/ | | +| approx_kl | 0.015680032 | +| clip_fraction | 0.35 | +| clip_range | 0.0683 | +| entropy_loss | -6.13 | +| explained_variance | 0.0999 | +| learning_rate | 4.36e-05 | +| loss | -0.0314 | +| n_updates | 68268 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000147 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1411 | +| iterations | 13114 | +| time_elapsed | 19024 | +| total_timesteps | 26857472 | +| train/ | | +| approx_kl | 0.016196303 | +| clip_fraction | 0.36 | +| clip_range | 0.0683 | +| entropy_loss | -5.44 | +| explained_variance | 0.597 | +| learning_rate | 4.36e-05 | +| loss | -0.0297 | +| n_updates | 68272 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000144 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1411 | +| iterations | 13115 | +| time_elapsed | 19025 | +| total_timesteps | 26859520 | +| train/ | | +| approx_kl | 0.015325368 | +| clip_fraction | 0.369 | +| clip_range | 0.0683 | +| entropy_loss | -5.48 | +| explained_variance | 0.54 | +| learning_rate | 4.36e-05 | +| loss | -0.0318 | +| n_updates | 68276 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000136 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1411 | +| iterations | 13116 | +| time_elapsed | 19027 | +| total_timesteps | 26861568 | +| train/ | | +| approx_kl | 0.015544368 | +| clip_fraction | 0.363 | +| clip_range | 0.0683 | +| entropy_loss | -5.85 | +| explained_variance | 0.667 | +| learning_rate | 4.36e-05 | +| loss | -0.0339 | +| n_updates | 68280 | +| policy_gradient_loss | -0.0201 | +| value_loss | 5.13e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1411 | +| iterations | 13117 | +| time_elapsed | 19028 | +| total_timesteps | 26863616 | +| train/ | | +| approx_kl | 0.01435989 | +| clip_fraction | 0.358 | +| clip_range | 0.0683 | +| entropy_loss | -6.11 | +| explained_variance | 0.412 | +| learning_rate | 4.36e-05 | +| loss | -0.031 | +| n_updates | 68284 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000128 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1411 | +| iterations | 13118 | +| time_elapsed | 19030 | +| total_timesteps | 26865664 | +| train/ | | +| approx_kl | 0.01442291 | +| clip_fraction | 0.336 | +| clip_range | 0.0683 | +| entropy_loss | -6.28 | +| explained_variance | 0.316 | +| learning_rate | 4.36e-05 | +| loss | -0.0289 | +| n_updates | 68288 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.00025 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1411 | +| iterations | 13119 | +| time_elapsed | 19031 | +| total_timesteps | 26867712 | +| train/ | | +| approx_kl | 0.0129834805 | +| clip_fraction | 0.381 | +| clip_range | 0.0683 | +| entropy_loss | -6 | +| explained_variance | 0.506 | +| learning_rate | 4.36e-05 | +| loss | -0.0233 | +| n_updates | 68292 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000128 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1411 | +| iterations | 13120 | +| time_elapsed | 19033 | +| total_timesteps | 26869760 | +| train/ | | +| approx_kl | 0.010933434 | +| clip_fraction | 0.306 | +| clip_range | 0.0683 | +| entropy_loss | -5.45 | +| explained_variance | 0.417 | +| learning_rate | 4.36e-05 | +| loss | -0.0196 | +| n_updates | 68296 | +| policy_gradient_loss | -0.0143 | +| value_loss | 0.000416 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1411 | +| iterations | 13121 | +| time_elapsed | 19034 | +| total_timesteps | 26871808 | +| train/ | | +| approx_kl | 0.010856273 | +| clip_fraction | 0.343 | +| clip_range | 0.0683 | +| entropy_loss | -6.66 | +| explained_variance | -0.221 | +| learning_rate | 4.36e-05 | +| loss | -0.0321 | +| n_updates | 68300 | +| policy_gradient_loss | -0.0222 | +| value_loss | 0.000158 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.384 | +| time/ | | +| fps | 1411 | +| iterations | 13122 | +| time_elapsed | 19036 | +| total_timesteps | 26873856 | +| train/ | | +| approx_kl | 0.011892636 | +| clip_fraction | 0.378 | +| clip_range | 0.0683 | +| entropy_loss | -6.52 | +| explained_variance | 0.413 | +| learning_rate | 4.36e-05 | +| loss | -0.0351 | +| n_updates | 68304 | +| policy_gradient_loss | -0.0227 | +| value_loss | 9.93e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1411 | +| iterations | 13123 | +| time_elapsed | 19038 | +| total_timesteps | 26875904 | +| train/ | | +| approx_kl | 0.010665149 | +| clip_fraction | 0.332 | +| clip_range | 0.0683 | +| entropy_loss | -6.41 | +| explained_variance | 0.265 | +| learning_rate | 4.36e-05 | +| loss | -0.029 | +| n_updates | 68308 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000206 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1411 | +| iterations | 13124 | +| time_elapsed | 19039 | +| total_timesteps | 26877952 | +| train/ | | +| approx_kl | 0.017963398 | +| clip_fraction | 0.325 | +| clip_range | 0.0683 | +| entropy_loss | -6.27 | +| explained_variance | 0.359 | +| learning_rate | 4.36e-05 | +| loss | -0.0245 | +| n_updates | 68312 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000228 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1411 | +| iterations | 13125 | +| time_elapsed | 19041 | +| total_timesteps | 26880000 | +| train/ | | +| approx_kl | 0.012208281 | +| clip_fraction | 0.358 | +| clip_range | 0.0683 | +| entropy_loss | -6.02 | +| explained_variance | 0.515 | +| learning_rate | 4.36e-05 | +| loss | -0.0262 | +| n_updates | 68316 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000155 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1411 | +| iterations | 13126 | +| time_elapsed | 19042 | +| total_timesteps | 26882048 | +| train/ | | +| approx_kl | 0.012607064 | +| clip_fraction | 0.381 | +| clip_range | 0.0683 | +| entropy_loss | -6.4 | +| explained_variance | 0.474 | +| learning_rate | 4.36e-05 | +| loss | -0.031 | +| n_updates | 68320 | +| policy_gradient_loss | -0.0218 | +| value_loss | 9.55e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1411 | +| iterations | 13127 | +| time_elapsed | 19044 | +| total_timesteps | 26884096 | +| train/ | | +| approx_kl | 0.011982776 | +| clip_fraction | 0.351 | +| clip_range | 0.0683 | +| entropy_loss | -6.2 | +| explained_variance | 0.422 | +| learning_rate | 4.36e-05 | +| loss | -0.0259 | +| n_updates | 68324 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000112 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1411 | +| iterations | 13128 | +| time_elapsed | 19045 | +| total_timesteps | 26886144 | +| train/ | | +| approx_kl | 0.01353526 | +| clip_fraction | 0.318 | +| clip_range | 0.0683 | +| entropy_loss | -6.36 | +| explained_variance | 0.462 | +| learning_rate | 4.36e-05 | +| loss | -0.0275 | +| n_updates | 68328 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000156 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1411 | +| iterations | 13129 | +| time_elapsed | 19047 | +| total_timesteps | 26888192 | +| train/ | | +| approx_kl | 0.012316257 | +| clip_fraction | 0.343 | +| clip_range | 0.0683 | +| entropy_loss | -6.32 | +| explained_variance | 0.484 | +| learning_rate | 4.36e-05 | +| loss | -0.0292 | +| n_updates | 68332 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000165 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.384 | +| time/ | | +| fps | 1411 | +| iterations | 13130 | +| time_elapsed | 19048 | +| total_timesteps | 26890240 | +| train/ | | +| approx_kl | 0.012214264 | +| clip_fraction | 0.343 | +| clip_range | 0.0683 | +| entropy_loss | -6.15 | +| explained_variance | 0.549 | +| learning_rate | 4.36e-05 | +| loss | -0.022 | +| n_updates | 68336 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000129 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1411 | +| iterations | 13131 | +| time_elapsed | 19050 | +| total_timesteps | 26892288 | +| train/ | | +| approx_kl | 0.012726874 | +| clip_fraction | 0.339 | +| clip_range | 0.0683 | +| entropy_loss | -5.62 | +| explained_variance | 0.516 | +| learning_rate | 4.36e-05 | +| loss | -0.0253 | +| n_updates | 68340 | +| policy_gradient_loss | -0.0143 | +| value_loss | 0.000242 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1411 | +| iterations | 13132 | +| time_elapsed | 19051 | +| total_timesteps | 26894336 | +| train/ | | +| approx_kl | 0.014159292 | +| clip_fraction | 0.335 | +| clip_range | 0.0683 | +| entropy_loss | -6.08 | +| explained_variance | 0.486 | +| learning_rate | 4.36e-05 | +| loss | -0.0277 | +| n_updates | 68344 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1411 | +| iterations | 13133 | +| time_elapsed | 19053 | +| total_timesteps | 26896384 | +| train/ | | +| approx_kl | 0.014326248 | +| clip_fraction | 0.33 | +| clip_range | 0.0683 | +| entropy_loss | -6.34 | +| explained_variance | 0.539 | +| learning_rate | 4.36e-05 | +| loss | -0.031 | +| n_updates | 68348 | +| policy_gradient_loss | -0.0201 | +| value_loss | 9.95e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1411 | +| iterations | 13134 | +| time_elapsed | 19054 | +| total_timesteps | 26898432 | +| train/ | | +| approx_kl | 0.012586983 | +| clip_fraction | 0.321 | +| clip_range | 0.0683 | +| entropy_loss | -5.87 | +| explained_variance | 0.564 | +| learning_rate | 4.36e-05 | +| loss | -0.029 | +| n_updates | 68352 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000174 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1411 | +| iterations | 13135 | +| time_elapsed | 19056 | +| total_timesteps | 26900480 | +| train/ | | +| approx_kl | 0.015115968 | +| clip_fraction | 0.34 | +| clip_range | 0.0683 | +| entropy_loss | -6.2 | +| explained_variance | 0.229 | +| learning_rate | 4.36e-05 | +| loss | -0.0268 | +| n_updates | 68356 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.00016 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1411 | +| iterations | 13136 | +| time_elapsed | 19057 | +| total_timesteps | 26902528 | +| train/ | | +| approx_kl | 0.014930122 | +| clip_fraction | 0.33 | +| clip_range | 0.0683 | +| entropy_loss | -6.25 | +| explained_variance | 0.296 | +| learning_rate | 4.36e-05 | +| loss | -0.0319 | +| n_updates | 68360 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000246 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1411 | +| iterations | 13137 | +| time_elapsed | 19059 | +| total_timesteps | 26904576 | +| train/ | | +| approx_kl | 0.011470112 | +| clip_fraction | 0.315 | +| clip_range | 0.0683 | +| entropy_loss | -6.29 | +| explained_variance | 0.39 | +| learning_rate | 4.36e-05 | +| loss | -0.0335 | +| n_updates | 68364 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000242 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1411 | +| iterations | 13138 | +| time_elapsed | 19060 | +| total_timesteps | 26906624 | +| train/ | | +| approx_kl | 0.01136531 | +| clip_fraction | 0.333 | +| clip_range | 0.0683 | +| entropy_loss | -6.53 | +| explained_variance | 0.204 | +| learning_rate | 4.36e-05 | +| loss | -0.029 | +| n_updates | 68368 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000231 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1411 | +| iterations | 13139 | +| time_elapsed | 19062 | +| total_timesteps | 26908672 | +| train/ | | +| approx_kl | 0.011330526 | +| clip_fraction | 0.309 | +| clip_range | 0.0683 | +| entropy_loss | -5.94 | +| explained_variance | 0.341 | +| learning_rate | 4.36e-05 | +| loss | -0.0244 | +| n_updates | 68372 | +| policy_gradient_loss | -0.0141 | +| value_loss | 0.000304 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1411 | +| iterations | 13140 | +| time_elapsed | 19063 | +| total_timesteps | 26910720 | +| train/ | | +| approx_kl | 0.01224773 | +| clip_fraction | 0.358 | +| clip_range | 0.0683 | +| entropy_loss | -5.51 | +| explained_variance | 0.65 | +| learning_rate | 4.36e-05 | +| loss | -0.0377 | +| n_updates | 68376 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000132 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1411 | +| iterations | 13141 | +| time_elapsed | 19065 | +| total_timesteps | 26912768 | +| train/ | | +| approx_kl | 0.012509705 | +| clip_fraction | 0.37 | +| clip_range | 0.0683 | +| entropy_loss | -5.81 | +| explained_variance | 0.537 | +| learning_rate | 4.36e-05 | +| loss | -0.0342 | +| n_updates | 68380 | +| policy_gradient_loss | -0.0221 | +| value_loss | 0.000103 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1411 | +| iterations | 13142 | +| time_elapsed | 19066 | +| total_timesteps | 26914816 | +| train/ | | +| approx_kl | 0.011431616 | +| clip_fraction | 0.35 | +| clip_range | 0.0683 | +| entropy_loss | -5.77 | +| explained_variance | 0.565 | +| learning_rate | 4.36e-05 | +| loss | -0.0203 | +| n_updates | 68384 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000219 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1411 | +| iterations | 13143 | +| time_elapsed | 19068 | +| total_timesteps | 26916864 | +| train/ | | +| approx_kl | 0.014700387 | +| clip_fraction | 0.338 | +| clip_range | 0.0683 | +| entropy_loss | -6.29 | +| explained_variance | 0.198 | +| learning_rate | 4.36e-05 | +| loss | -0.0267 | +| n_updates | 68388 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000141 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1411 | +| iterations | 13144 | +| time_elapsed | 19069 | +| total_timesteps | 26918912 | +| train/ | | +| approx_kl | 0.012523232 | +| clip_fraction | 0.371 | +| clip_range | 0.0683 | +| entropy_loss | -6.39 | +| explained_variance | 0.508 | +| learning_rate | 4.36e-05 | +| loss | -0.0352 | +| n_updates | 68392 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000111 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1411 | +| iterations | 13145 | +| time_elapsed | 19071 | +| total_timesteps | 26920960 | +| train/ | | +| approx_kl | 0.011255544 | +| clip_fraction | 0.333 | +| clip_range | 0.0683 | +| entropy_loss | -6.17 | +| explained_variance | 0.325 | +| learning_rate | 4.36e-05 | +| loss | -0.0302 | +| n_updates | 68396 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000162 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1411 | +| iterations | 13146 | +| time_elapsed | 19072 | +| total_timesteps | 26923008 | +| train/ | | +| approx_kl | 0.01500084 | +| clip_fraction | 0.347 | +| clip_range | 0.0683 | +| entropy_loss | -6.56 | +| explained_variance | 0.135 | +| learning_rate | 4.36e-05 | +| loss | -0.03 | +| n_updates | 68400 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000219 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1411 | +| iterations | 13147 | +| time_elapsed | 19074 | +| total_timesteps | 26925056 | +| train/ | | +| approx_kl | 0.01273674 | +| clip_fraction | 0.351 | +| clip_range | 0.0683 | +| entropy_loss | -6.28 | +| explained_variance | 0.492 | +| learning_rate | 4.36e-05 | +| loss | -0.0355 | +| n_updates | 68404 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000148 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1411 | +| iterations | 13148 | +| time_elapsed | 19075 | +| total_timesteps | 26927104 | +| train/ | | +| approx_kl | 0.013917434 | +| clip_fraction | 0.326 | +| clip_range | 0.0683 | +| entropy_loss | -6.04 | +| explained_variance | 0.555 | +| learning_rate | 4.36e-05 | +| loss | -0.0259 | +| n_updates | 68408 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000118 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1411 | +| iterations | 13149 | +| time_elapsed | 19077 | +| total_timesteps | 26929152 | +| train/ | | +| approx_kl | 0.011983365 | +| clip_fraction | 0.32 | +| clip_range | 0.0683 | +| entropy_loss | -6.28 | +| explained_variance | 0.417 | +| learning_rate | 4.36e-05 | +| loss | -0.032 | +| n_updates | 68412 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000139 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1411 | +| iterations | 13150 | +| time_elapsed | 19078 | +| total_timesteps | 26931200 | +| train/ | | +| approx_kl | 0.01596681 | +| clip_fraction | 0.325 | +| clip_range | 0.0683 | +| entropy_loss | -5.74 | +| explained_variance | 0.51 | +| learning_rate | 4.36e-05 | +| loss | -0.0269 | +| n_updates | 68416 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000172 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1411 | +| iterations | 13151 | +| time_elapsed | 19080 | +| total_timesteps | 26933248 | +| train/ | | +| approx_kl | 0.013272434 | +| clip_fraction | 0.339 | +| clip_range | 0.0683 | +| entropy_loss | -6.29 | +| explained_variance | 0.332 | +| learning_rate | 4.36e-05 | +| loss | -0.0328 | +| n_updates | 68420 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000128 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1411 | +| iterations | 13152 | +| time_elapsed | 19081 | +| total_timesteps | 26935296 | +| train/ | | +| approx_kl | 0.013939219 | +| clip_fraction | 0.39 | +| clip_range | 0.0683 | +| entropy_loss | -6.52 | +| explained_variance | -0.375 | +| learning_rate | 4.36e-05 | +| loss | -0.0378 | +| n_updates | 68424 | +| policy_gradient_loss | -0.0223 | +| value_loss | 6.66e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1411 | +| iterations | 13153 | +| time_elapsed | 19083 | +| total_timesteps | 26937344 | +| train/ | | +| approx_kl | 0.013910114 | +| clip_fraction | 0.329 | +| clip_range | 0.0683 | +| entropy_loss | -6.65 | +| explained_variance | 0.297 | +| learning_rate | 4.36e-05 | +| loss | -0.0261 | +| n_updates | 68428 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000158 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1411 | +| iterations | 13154 | +| time_elapsed | 19084 | +| total_timesteps | 26939392 | +| train/ | | +| approx_kl | 0.010941351 | +| clip_fraction | 0.319 | +| clip_range | 0.0683 | +| entropy_loss | -6.47 | +| explained_variance | 0.301 | +| learning_rate | 4.36e-05 | +| loss | -0.0291 | +| n_updates | 68432 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000173 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1411 | +| iterations | 13155 | +| time_elapsed | 19086 | +| total_timesteps | 26941440 | +| train/ | | +| approx_kl | 0.010988766 | +| clip_fraction | 0.321 | +| clip_range | 0.0683 | +| entropy_loss | -5.85 | +| explained_variance | 0.505 | +| learning_rate | 4.36e-05 | +| loss | -0.0307 | +| n_updates | 68436 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000183 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1411 | +| iterations | 13156 | +| time_elapsed | 19087 | +| total_timesteps | 26943488 | +| train/ | | +| approx_kl | 0.014093781 | +| clip_fraction | 0.353 | +| clip_range | 0.0683 | +| entropy_loss | -5.48 | +| explained_variance | 0.592 | +| learning_rate | 4.36e-05 | +| loss | -0.0269 | +| n_updates | 68440 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000103 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1411 | +| iterations | 13157 | +| time_elapsed | 19089 | +| total_timesteps | 26945536 | +| train/ | | +| approx_kl | 0.014951952 | +| clip_fraction | 0.314 | +| clip_range | 0.0683 | +| entropy_loss | -5.87 | +| explained_variance | 0.28 | +| learning_rate | 4.36e-05 | +| loss | -0.0272 | +| n_updates | 68444 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000318 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1411 | +| iterations | 13158 | +| time_elapsed | 19090 | +| total_timesteps | 26947584 | +| train/ | | +| approx_kl | 0.015906718 | +| clip_fraction | 0.339 | +| clip_range | 0.0683 | +| entropy_loss | -5.61 | +| explained_variance | 0.413 | +| learning_rate | 4.36e-05 | +| loss | -0.0295 | +| n_updates | 68448 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000144 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1411 | +| iterations | 13159 | +| time_elapsed | 19092 | +| total_timesteps | 26949632 | +| train/ | | +| approx_kl | 0.015216315 | +| clip_fraction | 0.36 | +| clip_range | 0.0683 | +| entropy_loss | -6.21 | +| explained_variance | 0.0669 | +| learning_rate | 4.36e-05 | +| loss | -0.0281 | +| n_updates | 68452 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000207 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1411 | +| iterations | 13160 | +| time_elapsed | 19093 | +| total_timesteps | 26951680 | +| train/ | | +| approx_kl | 0.013370572 | +| clip_fraction | 0.34 | +| clip_range | 0.0683 | +| entropy_loss | -6.12 | +| explained_variance | 0.453 | +| learning_rate | 4.36e-05 | +| loss | -0.0262 | +| n_updates | 68456 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000157 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1411 | +| iterations | 13161 | +| time_elapsed | 19095 | +| total_timesteps | 26953728 | +| train/ | | +| approx_kl | 0.012605205 | +| clip_fraction | 0.351 | +| clip_range | 0.0683 | +| entropy_loss | -6.61 | +| explained_variance | -0.0737 | +| learning_rate | 4.36e-05 | +| loss | -0.0303 | +| n_updates | 68460 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000178 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1411 | +| iterations | 13162 | +| time_elapsed | 19096 | +| total_timesteps | 26955776 | +| train/ | | +| approx_kl | 0.012233848 | +| clip_fraction | 0.343 | +| clip_range | 0.0683 | +| entropy_loss | -6.77 | +| explained_variance | 0.0784 | +| learning_rate | 4.36e-05 | +| loss | -0.0347 | +| n_updates | 68464 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000112 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1411 | +| iterations | 13163 | +| time_elapsed | 19098 | +| total_timesteps | 26957824 | +| train/ | | +| approx_kl | 0.017645257 | +| clip_fraction | 0.337 | +| clip_range | 0.0683 | +| entropy_loss | -6.01 | +| explained_variance | 0.472 | +| learning_rate | 4.36e-05 | +| loss | -0.0173 | +| n_updates | 68468 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.000197 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1411 | +| iterations | 13164 | +| time_elapsed | 19099 | +| total_timesteps | 26959872 | +| train/ | | +| approx_kl | 0.01297327 | +| clip_fraction | 0.349 | +| clip_range | 0.0683 | +| entropy_loss | -6.06 | +| explained_variance | 0.759 | +| learning_rate | 4.36e-05 | +| loss | -0.0268 | +| n_updates | 68472 | +| policy_gradient_loss | -0.0189 | +| value_loss | 8.64e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1411 | +| iterations | 13165 | +| time_elapsed | 19101 | +| total_timesteps | 26961920 | +| train/ | | +| approx_kl | 0.016833996 | +| clip_fraction | 0.32 | +| clip_range | 0.0683 | +| entropy_loss | -6.01 | +| explained_variance | 0.259 | +| learning_rate | 4.36e-05 | +| loss | -0.0213 | +| n_updates | 68476 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000282 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1411 | +| iterations | 13166 | +| time_elapsed | 19102 | +| total_timesteps | 26963968 | +| train/ | | +| approx_kl | 0.015330995 | +| clip_fraction | 0.339 | +| clip_range | 0.0683 | +| entropy_loss | -5.68 | +| explained_variance | 0.552 | +| learning_rate | 4.36e-05 | +| loss | -0.0308 | +| n_updates | 68480 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000166 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1411 | +| iterations | 13167 | +| time_elapsed | 19104 | +| total_timesteps | 26966016 | +| train/ | | +| approx_kl | 0.010606354 | +| clip_fraction | 0.335 | +| clip_range | 0.0683 | +| entropy_loss | -6.39 | +| explained_variance | 0.201 | +| learning_rate | 4.36e-05 | +| loss | -0.0287 | +| n_updates | 68484 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000162 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1411 | +| iterations | 13168 | +| time_elapsed | 19105 | +| total_timesteps | 26968064 | +| train/ | | +| approx_kl | 0.011056068 | +| clip_fraction | 0.326 | +| clip_range | 0.0683 | +| entropy_loss | -5.58 | +| explained_variance | 0.749 | +| learning_rate | 4.36e-05 | +| loss | -0.0293 | +| n_updates | 68488 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000113 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1411 | +| iterations | 13169 | +| time_elapsed | 19107 | +| total_timesteps | 26970112 | +| train/ | | +| approx_kl | 0.01231005 | +| clip_fraction | 0.331 | +| clip_range | 0.0683 | +| entropy_loss | -6.08 | +| explained_variance | 0.308 | +| learning_rate | 4.36e-05 | +| loss | -0.0247 | +| n_updates | 68492 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000181 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1411 | +| iterations | 13170 | +| time_elapsed | 19108 | +| total_timesteps | 26972160 | +| train/ | | +| approx_kl | 0.011401471 | +| clip_fraction | 0.335 | +| clip_range | 0.0683 | +| entropy_loss | -6.33 | +| explained_variance | 0.308 | +| learning_rate | 4.36e-05 | +| loss | -0.0293 | +| n_updates | 68496 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000256 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1411 | +| iterations | 13171 | +| time_elapsed | 19110 | +| total_timesteps | 26974208 | +| train/ | | +| approx_kl | 0.012397509 | +| clip_fraction | 0.357 | +| clip_range | 0.0683 | +| entropy_loss | -6.55 | +| explained_variance | -0.323 | +| learning_rate | 4.36e-05 | +| loss | -0.0343 | +| n_updates | 68500 | +| policy_gradient_loss | -0.0213 | +| value_loss | 9.34e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1411 | +| iterations | 13172 | +| time_elapsed | 19111 | +| total_timesteps | 26976256 | +| train/ | | +| approx_kl | 0.014563164 | +| clip_fraction | 0.332 | +| clip_range | 0.0683 | +| entropy_loss | -6.47 | +| explained_variance | 0.066 | +| learning_rate | 4.36e-05 | +| loss | -0.0255 | +| n_updates | 68504 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000297 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1411 | +| iterations | 13173 | +| time_elapsed | 19113 | +| total_timesteps | 26978304 | +| train/ | | +| approx_kl | 0.015125029 | +| clip_fraction | 0.341 | +| clip_range | 0.0683 | +| entropy_loss | -6.32 | +| explained_variance | 0.326 | +| learning_rate | 4.36e-05 | +| loss | -0.0316 | +| n_updates | 68508 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000212 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1411 | +| iterations | 13174 | +| time_elapsed | 19114 | +| total_timesteps | 26980352 | +| train/ | | +| approx_kl | 0.015600774 | +| clip_fraction | 0.358 | +| clip_range | 0.0683 | +| entropy_loss | -5.83 | +| explained_variance | 0.606 | +| learning_rate | 4.36e-05 | +| loss | -0.0358 | +| n_updates | 68512 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000118 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1411 | +| iterations | 13175 | +| time_elapsed | 19116 | +| total_timesteps | 26982400 | +| train/ | | +| approx_kl | 0.0148107335 | +| clip_fraction | 0.378 | +| clip_range | 0.0683 | +| entropy_loss | -5.49 | +| explained_variance | 0.832 | +| learning_rate | 4.36e-05 | +| loss | -0.0371 | +| n_updates | 68516 | +| policy_gradient_loss | -0.0221 | +| value_loss | 5.94e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1411 | +| iterations | 13176 | +| time_elapsed | 19118 | +| total_timesteps | 26984448 | +| train/ | | +| approx_kl | 0.011568887 | +| clip_fraction | 0.346 | +| clip_range | 0.0683 | +| entropy_loss | -5.74 | +| explained_variance | 0.601 | +| learning_rate | 4.36e-05 | +| loss | -0.0309 | +| n_updates | 68520 | +| policy_gradient_loss | -0.0188 | +| value_loss | 7.65e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1411 | +| iterations | 13177 | +| time_elapsed | 19119 | +| total_timesteps | 26986496 | +| train/ | | +| approx_kl | 0.012368418 | +| clip_fraction | 0.324 | +| clip_range | 0.0683 | +| entropy_loss | -5.91 | +| explained_variance | 0.642 | +| learning_rate | 4.36e-05 | +| loss | -0.0222 | +| n_updates | 68524 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000113 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1411 | +| iterations | 13178 | +| time_elapsed | 19121 | +| total_timesteps | 26988544 | +| train/ | | +| approx_kl | 0.010500976 | +| clip_fraction | 0.322 | +| clip_range | 0.0683 | +| entropy_loss | -5.96 | +| explained_variance | 0.397 | +| learning_rate | 4.36e-05 | +| loss | -0.0273 | +| n_updates | 68528 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000299 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1411 | +| iterations | 13179 | +| time_elapsed | 19122 | +| total_timesteps | 26990592 | +| train/ | | +| approx_kl | 0.009148515 | +| clip_fraction | 0.303 | +| clip_range | 0.0683 | +| entropy_loss | -6.52 | +| explained_variance | 0.0429 | +| learning_rate | 4.36e-05 | +| loss | -0.0329 | +| n_updates | 68532 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000379 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1411 | +| iterations | 13180 | +| time_elapsed | 19124 | +| total_timesteps | 26992640 | +| train/ | | +| approx_kl | 0.015015835 | +| clip_fraction | 0.344 | +| clip_range | 0.0683 | +| entropy_loss | -6.46 | +| explained_variance | 0.439 | +| learning_rate | 4.36e-05 | +| loss | -0.0352 | +| n_updates | 68536 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000201 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1411 | +| iterations | 13181 | +| time_elapsed | 19125 | +| total_timesteps | 26994688 | +| train/ | | +| approx_kl | 0.01329542 | +| clip_fraction | 0.316 | +| clip_range | 0.0683 | +| entropy_loss | -6.42 | +| explained_variance | -0.018 | +| learning_rate | 4.36e-05 | +| loss | -0.0284 | +| n_updates | 68540 | +| policy_gradient_loss | -0.0146 | +| value_loss | 0.000318 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1411 | +| iterations | 13182 | +| time_elapsed | 19127 | +| total_timesteps | 26996736 | +| train/ | | +| approx_kl | 0.015745964 | +| clip_fraction | 0.339 | +| clip_range | 0.0683 | +| entropy_loss | -6.12 | +| explained_variance | 0.264 | +| learning_rate | 4.36e-05 | +| loss | -0.0285 | +| n_updates | 68544 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000228 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1411 | +| iterations | 13183 | +| time_elapsed | 19128 | +| total_timesteps | 26998784 | +| train/ | | +| approx_kl | 0.01448944 | +| clip_fraction | 0.367 | +| clip_range | 0.0683 | +| entropy_loss | -6.51 | +| explained_variance | -0.454 | +| learning_rate | 4.36e-05 | +| loss | -0.0321 | +| n_updates | 68548 | +| policy_gradient_loss | -0.0228 | +| value_loss | 8.62e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1411 | +| iterations | 13184 | +| time_elapsed | 19130 | +| total_timesteps | 27000832 | +| train/ | | +| approx_kl | 0.014707932 | +| clip_fraction | 0.34 | +| clip_range | 0.0683 | +| entropy_loss | -6.64 | +| explained_variance | 0.113 | +| learning_rate | 4.36e-05 | +| loss | -0.0283 | +| n_updates | 68552 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000287 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1411 | +| iterations | 13185 | +| time_elapsed | 19131 | +| total_timesteps | 27002880 | +| train/ | | +| approx_kl | 0.013343164 | +| clip_fraction | 0.336 | +| clip_range | 0.0682 | +| entropy_loss | -6.01 | +| explained_variance | 0.509 | +| learning_rate | 4.36e-05 | +| loss | -0.0251 | +| n_updates | 68556 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000222 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1411 | +| iterations | 13186 | +| time_elapsed | 19133 | +| total_timesteps | 27004928 | +| train/ | | +| approx_kl | 0.012979885 | +| clip_fraction | 0.328 | +| clip_range | 0.0682 | +| entropy_loss | -6.02 | +| explained_variance | 0.439 | +| learning_rate | 4.36e-05 | +| loss | -0.0239 | +| n_updates | 68560 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000144 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1411 | +| iterations | 13187 | +| time_elapsed | 19134 | +| total_timesteps | 27006976 | +| train/ | | +| approx_kl | 0.015440235 | +| clip_fraction | 0.348 | +| clip_range | 0.0682 | +| entropy_loss | -6.2 | +| explained_variance | 0.706 | +| learning_rate | 4.36e-05 | +| loss | -0.0392 | +| n_updates | 68564 | +| policy_gradient_loss | -0.0221 | +| value_loss | 6.75e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1411 | +| iterations | 13188 | +| time_elapsed | 19136 | +| total_timesteps | 27009024 | +| train/ | | +| approx_kl | 0.015009283 | +| clip_fraction | 0.341 | +| clip_range | 0.0682 | +| entropy_loss | -6.27 | +| explained_variance | 0.653 | +| learning_rate | 4.36e-05 | +| loss | -0.0302 | +| n_updates | 68568 | +| policy_gradient_loss | -0.0179 | +| value_loss | 8.76e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1411 | +| iterations | 13189 | +| time_elapsed | 19137 | +| total_timesteps | 27011072 | +| train/ | | +| approx_kl | 0.014166253 | +| clip_fraction | 0.343 | +| clip_range | 0.0682 | +| entropy_loss | -5.62 | +| explained_variance | 0.642 | +| learning_rate | 4.36e-05 | +| loss | -0.0166 | +| n_updates | 68572 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000168 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1411 | +| iterations | 13190 | +| time_elapsed | 19139 | +| total_timesteps | 27013120 | +| train/ | | +| approx_kl | 0.01646484 | +| clip_fraction | 0.371 | +| clip_range | 0.0682 | +| entropy_loss | -5.86 | +| explained_variance | -0.0222 | +| learning_rate | 4.36e-05 | +| loss | -0.0311 | +| n_updates | 68576 | +| policy_gradient_loss | -0.0204 | +| value_loss | 8.53e-05 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1411 | +| iterations | 13191 | +| time_elapsed | 19141 | +| total_timesteps | 27015168 | +| train/ | | +| approx_kl | 0.01519023 | +| clip_fraction | 0.33 | +| clip_range | 0.0682 | +| entropy_loss | -6.21 | +| explained_variance | 0.377 | +| learning_rate | 4.36e-05 | +| loss | -0.0298 | +| n_updates | 68580 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000265 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1411 | +| iterations | 13192 | +| time_elapsed | 19142 | +| total_timesteps | 27017216 | +| train/ | | +| approx_kl | 0.011607623 | +| clip_fraction | 0.332 | +| clip_range | 0.0682 | +| entropy_loss | -6.54 | +| explained_variance | 0.00613 | +| learning_rate | 4.36e-05 | +| loss | -0.0281 | +| n_updates | 68584 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000219 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1411 | +| iterations | 13193 | +| time_elapsed | 19144 | +| total_timesteps | 27019264 | +| train/ | | +| approx_kl | 0.013248219 | +| clip_fraction | 0.343 | +| clip_range | 0.0682 | +| entropy_loss | -7.04 | +| explained_variance | -0.048 | +| learning_rate | 4.36e-05 | +| loss | -0.0305 | +| n_updates | 68588 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000129 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1411 | +| iterations | 13194 | +| time_elapsed | 19145 | +| total_timesteps | 27021312 | +| train/ | | +| approx_kl | 0.010218202 | +| clip_fraction | 0.323 | +| clip_range | 0.0682 | +| entropy_loss | -6.64 | +| explained_variance | 0.251 | +| learning_rate | 4.36e-05 | +| loss | -0.0204 | +| n_updates | 68592 | +| policy_gradient_loss | -0.0146 | +| value_loss | 0.000368 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1411 | +| iterations | 13195 | +| time_elapsed | 19147 | +| total_timesteps | 27023360 | +| train/ | | +| approx_kl | 0.012270676 | +| clip_fraction | 0.328 | +| clip_range | 0.0682 | +| entropy_loss | -6.18 | +| explained_variance | 0.388 | +| learning_rate | 4.36e-05 | +| loss | -0.0278 | +| n_updates | 68596 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000199 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1411 | +| iterations | 13196 | +| time_elapsed | 19148 | +| total_timesteps | 27025408 | +| train/ | | +| approx_kl | 0.01233675 | +| clip_fraction | 0.312 | +| clip_range | 0.0682 | +| entropy_loss | -6.11 | +| explained_variance | 0.417 | +| learning_rate | 4.36e-05 | +| loss | -0.0331 | +| n_updates | 68600 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000181 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1411 | +| iterations | 13197 | +| time_elapsed | 19150 | +| total_timesteps | 27027456 | +| train/ | | +| approx_kl | 0.013621664 | +| clip_fraction | 0.348 | +| clip_range | 0.0682 | +| entropy_loss | -5.93 | +| explained_variance | 0.604 | +| learning_rate | 4.36e-05 | +| loss | -0.033 | +| n_updates | 68604 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000104 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1411 | +| iterations | 13198 | +| time_elapsed | 19151 | +| total_timesteps | 27029504 | +| train/ | | +| approx_kl | 0.013512332 | +| clip_fraction | 0.352 | +| clip_range | 0.0682 | +| entropy_loss | -6.57 | +| explained_variance | 0.297 | +| learning_rate | 4.36e-05 | +| loss | -0.032 | +| n_updates | 68608 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000152 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1411 | +| iterations | 13199 | +| time_elapsed | 19153 | +| total_timesteps | 27031552 | +| train/ | | +| approx_kl | 0.009761896 | +| clip_fraction | 0.322 | +| clip_range | 0.0682 | +| entropy_loss | -6.45 | +| explained_variance | 0.202 | +| learning_rate | 4.36e-05 | +| loss | -0.0297 | +| n_updates | 68612 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000276 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1411 | +| iterations | 13200 | +| time_elapsed | 19154 | +| total_timesteps | 27033600 | +| train/ | | +| approx_kl | 0.010477826 | +| clip_fraction | 0.321 | +| clip_range | 0.0682 | +| entropy_loss | -6.26 | +| explained_variance | 0.673 | +| learning_rate | 4.36e-05 | +| loss | -0.0308 | +| n_updates | 68616 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000122 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1411 | +| iterations | 13201 | +| time_elapsed | 19156 | +| total_timesteps | 27035648 | +| train/ | | +| approx_kl | 0.013168857 | +| clip_fraction | 0.333 | +| clip_range | 0.0682 | +| entropy_loss | -6.29 | +| explained_variance | 0.316 | +| learning_rate | 4.36e-05 | +| loss | -0.0259 | +| n_updates | 68620 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000178 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1411 | +| iterations | 13202 | +| time_elapsed | 19157 | +| total_timesteps | 27037696 | +| train/ | | +| approx_kl | 0.0134426765 | +| clip_fraction | 0.337 | +| clip_range | 0.0682 | +| entropy_loss | -6.24 | +| explained_variance | 0.227 | +| learning_rate | 4.36e-05 | +| loss | -0.0295 | +| n_updates | 68624 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.00018 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1411 | +| iterations | 13203 | +| time_elapsed | 19159 | +| total_timesteps | 27039744 | +| train/ | | +| approx_kl | 0.014187861 | +| clip_fraction | 0.336 | +| clip_range | 0.0682 | +| entropy_loss | -6.43 | +| explained_variance | 0.328 | +| learning_rate | 4.36e-05 | +| loss | -0.0273 | +| n_updates | 68628 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000135 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1411 | +| iterations | 13204 | +| time_elapsed | 19160 | +| total_timesteps | 27041792 | +| train/ | | +| approx_kl | 0.012297689 | +| clip_fraction | 0.322 | +| clip_range | 0.0682 | +| entropy_loss | -6.37 | +| explained_variance | 0.484 | +| learning_rate | 4.36e-05 | +| loss | -0.0225 | +| n_updates | 68632 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000121 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1411 | +| iterations | 13205 | +| time_elapsed | 19162 | +| total_timesteps | 27043840 | +| train/ | | +| approx_kl | 0.0128053725 | +| clip_fraction | 0.35 | +| clip_range | 0.0682 | +| entropy_loss | -6.11 | +| explained_variance | 0.495 | +| learning_rate | 4.36e-05 | +| loss | -0.0199 | +| n_updates | 68636 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000128 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1411 | +| iterations | 13206 | +| time_elapsed | 19163 | +| total_timesteps | 27045888 | +| train/ | | +| approx_kl | 0.014016453 | +| clip_fraction | 0.323 | +| clip_range | 0.0682 | +| entropy_loss | -6.57 | +| explained_variance | -0.0747 | +| learning_rate | 4.36e-05 | +| loss | -0.024 | +| n_updates | 68640 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000229 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1411 | +| iterations | 13207 | +| time_elapsed | 19165 | +| total_timesteps | 27047936 | +| train/ | | +| approx_kl | 0.010783473 | +| clip_fraction | 0.328 | +| clip_range | 0.0682 | +| entropy_loss | -5.8 | +| explained_variance | 0.346 | +| learning_rate | 4.36e-05 | +| loss | -0.022 | +| n_updates | 68644 | +| policy_gradient_loss | -0.0142 | +| value_loss | 0.000198 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1411 | +| iterations | 13208 | +| time_elapsed | 19167 | +| total_timesteps | 27049984 | +| train/ | | +| approx_kl | 0.013341207 | +| clip_fraction | 0.343 | +| clip_range | 0.0682 | +| entropy_loss | -6.25 | +| explained_variance | 0.451 | +| learning_rate | 4.36e-05 | +| loss | -0.0334 | +| n_updates | 68648 | +| policy_gradient_loss | -0.0198 | +| value_loss | 8.54e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1411 | +| iterations | 13209 | +| time_elapsed | 19168 | +| total_timesteps | 27052032 | +| train/ | | +| approx_kl | 0.011907699 | +| clip_fraction | 0.336 | +| clip_range | 0.0682 | +| entropy_loss | -6.06 | +| explained_variance | 0.297 | +| learning_rate | 4.36e-05 | +| loss | -0.0299 | +| n_updates | 68652 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.00022 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1411 | +| iterations | 13210 | +| time_elapsed | 19170 | +| total_timesteps | 27054080 | +| train/ | | +| approx_kl | 0.012854368 | +| clip_fraction | 0.345 | +| clip_range | 0.0682 | +| entropy_loss | -6.58 | +| explained_variance | 0.102 | +| learning_rate | 4.36e-05 | +| loss | -0.0299 | +| n_updates | 68656 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.00019 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1411 | +| iterations | 13211 | +| time_elapsed | 19171 | +| total_timesteps | 27056128 | +| train/ | | +| approx_kl | 0.013964723 | +| clip_fraction | 0.349 | +| clip_range | 0.0682 | +| entropy_loss | -6.39 | +| explained_variance | 0.452 | +| learning_rate | 4.36e-05 | +| loss | -0.0283 | +| n_updates | 68660 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1411 | +| iterations | 13212 | +| time_elapsed | 19173 | +| total_timesteps | 27058176 | +| train/ | | +| approx_kl | 0.013980061 | +| clip_fraction | 0.347 | +| clip_range | 0.0682 | +| entropy_loss | -6.08 | +| explained_variance | 0.58 | +| learning_rate | 4.36e-05 | +| loss | -0.0374 | +| n_updates | 68664 | +| policy_gradient_loss | -0.0195 | +| value_loss | 8.87e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1411 | +| iterations | 13213 | +| time_elapsed | 19174 | +| total_timesteps | 27060224 | +| train/ | | +| approx_kl | 0.012844357 | +| clip_fraction | 0.32 | +| clip_range | 0.0682 | +| entropy_loss | -5.95 | +| explained_variance | 0.259 | +| learning_rate | 4.36e-05 | +| loss | -0.0263 | +| n_updates | 68668 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000271 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1411 | +| iterations | 13214 | +| time_elapsed | 19176 | +| total_timesteps | 27062272 | +| train/ | | +| approx_kl | 0.013291388 | +| clip_fraction | 0.346 | +| clip_range | 0.0682 | +| entropy_loss | -6.27 | +| explained_variance | 0.327 | +| learning_rate | 4.36e-05 | +| loss | -0.0305 | +| n_updates | 68672 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000283 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1411 | +| iterations | 13215 | +| time_elapsed | 19177 | +| total_timesteps | 27064320 | +| train/ | | +| approx_kl | 0.013573208 | +| clip_fraction | 0.356 | +| clip_range | 0.0682 | +| entropy_loss | -6.72 | +| explained_variance | -0.225 | +| learning_rate | 4.36e-05 | +| loss | -0.0312 | +| n_updates | 68676 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000118 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1411 | +| iterations | 13216 | +| time_elapsed | 19179 | +| total_timesteps | 27066368 | +| train/ | | +| approx_kl | 0.012314215 | +| clip_fraction | 0.333 | +| clip_range | 0.0682 | +| entropy_loss | -6.73 | +| explained_variance | 0.287 | +| learning_rate | 4.36e-05 | +| loss | -0.0349 | +| n_updates | 68680 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000122 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1411 | +| iterations | 13217 | +| time_elapsed | 19180 | +| total_timesteps | 27068416 | +| train/ | | +| approx_kl | 0.016549822 | +| clip_fraction | 0.304 | +| clip_range | 0.0682 | +| entropy_loss | -6.49 | +| explained_variance | 0.472 | +| learning_rate | 4.36e-05 | +| loss | -0.0294 | +| n_updates | 68684 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.00016 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1411 | +| iterations | 13218 | +| time_elapsed | 19182 | +| total_timesteps | 27070464 | +| train/ | | +| approx_kl | 0.011680606 | +| clip_fraction | 0.317 | +| clip_range | 0.0682 | +| entropy_loss | -5.64 | +| explained_variance | 0.396 | +| learning_rate | 4.36e-05 | +| loss | -0.0281 | +| n_updates | 68688 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000303 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1411 | +| iterations | 13219 | +| time_elapsed | 19183 | +| total_timesteps | 27072512 | +| train/ | | +| approx_kl | 0.009289131 | +| clip_fraction | 0.346 | +| clip_range | 0.0682 | +| entropy_loss | -5.78 | +| explained_variance | 0.355 | +| learning_rate | 4.36e-05 | +| loss | -0.0222 | +| n_updates | 68692 | +| policy_gradient_loss | -0.0147 | +| value_loss | 0.000279 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1411 | +| iterations | 13220 | +| time_elapsed | 19185 | +| total_timesteps | 27074560 | +| train/ | | +| approx_kl | 0.0121075455 | +| clip_fraction | 0.362 | +| clip_range | 0.0682 | +| entropy_loss | -5.72 | +| explained_variance | 0.434 | +| learning_rate | 4.36e-05 | +| loss | -0.037 | +| n_updates | 68696 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000264 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1411 | +| iterations | 13221 | +| time_elapsed | 19186 | +| total_timesteps | 27076608 | +| train/ | | +| approx_kl | 0.016460314 | +| clip_fraction | 0.38 | +| clip_range | 0.0682 | +| entropy_loss | -5.95 | +| explained_variance | 0.315 | +| learning_rate | 4.36e-05 | +| loss | -0.0356 | +| n_updates | 68700 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000175 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1411 | +| iterations | 13222 | +| time_elapsed | 19188 | +| total_timesteps | 27078656 | +| train/ | | +| approx_kl | 0.013325248 | +| clip_fraction | 0.381 | +| clip_range | 0.0682 | +| entropy_loss | -6.35 | +| explained_variance | 0.276 | +| learning_rate | 4.36e-05 | +| loss | -0.0294 | +| n_updates | 68704 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1411 | +| iterations | 13223 | +| time_elapsed | 19189 | +| total_timesteps | 27080704 | +| train/ | | +| approx_kl | 0.010772494 | +| clip_fraction | 0.336 | +| clip_range | 0.0682 | +| entropy_loss | -6.45 | +| explained_variance | 0.472 | +| learning_rate | 4.36e-05 | +| loss | -0.032 | +| n_updates | 68708 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000147 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1411 | +| iterations | 13224 | +| time_elapsed | 19191 | +| total_timesteps | 27082752 | +| train/ | | +| approx_kl | 0.007925425 | +| clip_fraction | 0.29 | +| clip_range | 0.0682 | +| entropy_loss | -6.34 | +| explained_variance | 0.377 | +| learning_rate | 4.36e-05 | +| loss | -0.0218 | +| n_updates | 68712 | +| policy_gradient_loss | -0.0144 | +| value_loss | 0.000295 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1411 | +| iterations | 13225 | +| time_elapsed | 19192 | +| total_timesteps | 27084800 | +| train/ | | +| approx_kl | 0.0095494995 | +| clip_fraction | 0.326 | +| clip_range | 0.0682 | +| entropy_loss | -6.07 | +| explained_variance | 0.436 | +| learning_rate | 4.36e-05 | +| loss | -0.0356 | +| n_updates | 68716 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.00018 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1411 | +| iterations | 13226 | +| time_elapsed | 19194 | +| total_timesteps | 27086848 | +| train/ | | +| approx_kl | 0.0118108485 | +| clip_fraction | 0.304 | +| clip_range | 0.0682 | +| entropy_loss | -5.98 | +| explained_variance | 0.327 | +| learning_rate | 4.36e-05 | +| loss | -0.0261 | +| n_updates | 68720 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000259 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1411 | +| iterations | 13227 | +| time_elapsed | 19195 | +| total_timesteps | 27088896 | +| train/ | | +| approx_kl | 0.011505775 | +| clip_fraction | 0.31 | +| clip_range | 0.0682 | +| entropy_loss | -6.72 | +| explained_variance | 0.0611 | +| learning_rate | 4.36e-05 | +| loss | -0.0265 | +| n_updates | 68724 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000425 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1411 | +| iterations | 13228 | +| time_elapsed | 19197 | +| total_timesteps | 27090944 | +| train/ | | +| approx_kl | 0.014558556 | +| clip_fraction | 0.351 | +| clip_range | 0.0682 | +| entropy_loss | -6.33 | +| explained_variance | 0.34 | +| learning_rate | 4.36e-05 | +| loss | -0.028 | +| n_updates | 68728 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000253 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1411 | +| iterations | 13229 | +| time_elapsed | 19198 | +| total_timesteps | 27092992 | +| train/ | | +| approx_kl | 0.013193738 | +| clip_fraction | 0.361 | +| clip_range | 0.0682 | +| entropy_loss | -5.92 | +| explained_variance | 0.637 | +| learning_rate | 4.36e-05 | +| loss | -0.03 | +| n_updates | 68732 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000134 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1411 | +| iterations | 13230 | +| time_elapsed | 19200 | +| total_timesteps | 27095040 | +| train/ | | +| approx_kl | 0.011337136 | +| clip_fraction | 0.339 | +| clip_range | 0.0682 | +| entropy_loss | -6.28 | +| explained_variance | 0.131 | +| learning_rate | 4.36e-05 | +| loss | -0.0218 | +| n_updates | 68736 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000369 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1411 | +| iterations | 13231 | +| time_elapsed | 19201 | +| total_timesteps | 27097088 | +| train/ | | +| approx_kl | 0.01471969 | +| clip_fraction | 0.343 | +| clip_range | 0.0682 | +| entropy_loss | -6.4 | +| explained_variance | 0.28 | +| learning_rate | 4.36e-05 | +| loss | -0.0308 | +| n_updates | 68740 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000203 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1411 | +| iterations | 13232 | +| time_elapsed | 19203 | +| total_timesteps | 27099136 | +| train/ | | +| approx_kl | 0.015057461 | +| clip_fraction | 0.322 | +| clip_range | 0.0682 | +| entropy_loss | -6.15 | +| explained_variance | 0.0879 | +| learning_rate | 4.36e-05 | +| loss | -0.0249 | +| n_updates | 68744 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000297 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.385 | +| time/ | | +| fps | 1411 | +| iterations | 13233 | +| time_elapsed | 19204 | +| total_timesteps | 27101184 | +| train/ | | +| approx_kl | 0.014975596 | +| clip_fraction | 0.335 | +| clip_range | 0.0682 | +| entropy_loss | -5.67 | +| explained_variance | 0.564 | +| learning_rate | 4.36e-05 | +| loss | -0.0318 | +| n_updates | 68748 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.00019 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.395 | +| time/ | | +| fps | 1411 | +| iterations | 13234 | +| time_elapsed | 19206 | +| total_timesteps | 27103232 | +| train/ | | +| approx_kl | 0.01415823 | +| clip_fraction | 0.354 | +| clip_range | 0.0682 | +| entropy_loss | -6.53 | +| explained_variance | 0.0641 | +| learning_rate | 4.36e-05 | +| loss | -0.0305 | +| n_updates | 68752 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000192 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.392 | +| time/ | | +| fps | 1411 | +| iterations | 13235 | +| time_elapsed | 19207 | +| total_timesteps | 27105280 | +| train/ | | +| approx_kl | 0.011937968 | +| clip_fraction | 0.338 | +| clip_range | 0.0682 | +| entropy_loss | -6.26 | +| explained_variance | 0.515 | +| learning_rate | 4.36e-05 | +| loss | -0.0337 | +| n_updates | 68756 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000183 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.392 | +| time/ | | +| fps | 1411 | +| iterations | 13236 | +| time_elapsed | 19209 | +| total_timesteps | 27107328 | +| train/ | | +| approx_kl | 0.011506546 | +| clip_fraction | 0.326 | +| clip_range | 0.0682 | +| entropy_loss | -5.62 | +| explained_variance | 0.626 | +| learning_rate | 4.36e-05 | +| loss | -0.0211 | +| n_updates | 68760 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000215 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.39 | +| time/ | | +| fps | 1411 | +| iterations | 13237 | +| time_elapsed | 19210 | +| total_timesteps | 27109376 | +| train/ | | +| approx_kl | 0.012964365 | +| clip_fraction | 0.312 | +| clip_range | 0.0682 | +| entropy_loss | -6.11 | +| explained_variance | 0.19 | +| learning_rate | 4.36e-05 | +| loss | -0.0313 | +| n_updates | 68764 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000141 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.39 | +| time/ | | +| fps | 1411 | +| iterations | 13238 | +| time_elapsed | 19212 | +| total_timesteps | 27111424 | +| train/ | | +| approx_kl | 0.012912397 | +| clip_fraction | 0.339 | +| clip_range | 0.0682 | +| entropy_loss | -6.92 | +| explained_variance | 0.228 | +| learning_rate | 4.36e-05 | +| loss | -0.031 | +| n_updates | 68768 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000187 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.386 | +| time/ | | +| fps | 1411 | +| iterations | 13239 | +| time_elapsed | 19213 | +| total_timesteps | 27113472 | +| train/ | | +| approx_kl | 0.013032446 | +| clip_fraction | 0.34 | +| clip_range | 0.0682 | +| entropy_loss | -6.71 | +| explained_variance | -0.112 | +| learning_rate | 4.36e-05 | +| loss | -0.0275 | +| n_updates | 68772 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000139 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1411 | +| iterations | 13240 | +| time_elapsed | 19215 | +| total_timesteps | 27115520 | +| train/ | | +| approx_kl | 0.018954378 | +| clip_fraction | 0.313 | +| clip_range | 0.0682 | +| entropy_loss | -6.28 | +| explained_variance | 0.386 | +| learning_rate | 4.36e-05 | +| loss | -0.0248 | +| n_updates | 68776 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000233 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1411 | +| iterations | 13241 | +| time_elapsed | 19216 | +| total_timesteps | 27117568 | +| train/ | | +| approx_kl | 0.013979737 | +| clip_fraction | 0.338 | +| clip_range | 0.0682 | +| entropy_loss | -6.15 | +| explained_variance | 0.317 | +| learning_rate | 4.36e-05 | +| loss | -0.029 | +| n_updates | 68780 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000125 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1411 | +| iterations | 13242 | +| time_elapsed | 19218 | +| total_timesteps | 27119616 | +| train/ | | +| approx_kl | 0.01574883 | +| clip_fraction | 0.331 | +| clip_range | 0.0682 | +| entropy_loss | -6.66 | +| explained_variance | 0.276 | +| learning_rate | 4.36e-05 | +| loss | -0.029 | +| n_updates | 68784 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000219 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1411 | +| iterations | 13243 | +| time_elapsed | 19219 | +| total_timesteps | 27121664 | +| train/ | | +| approx_kl | 0.01575566 | +| clip_fraction | 0.325 | +| clip_range | 0.0682 | +| entropy_loss | -6.14 | +| explained_variance | 0.334 | +| learning_rate | 4.36e-05 | +| loss | -0.0307 | +| n_updates | 68788 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000282 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.388 | +| time/ | | +| fps | 1411 | +| iterations | 13244 | +| time_elapsed | 19221 | +| total_timesteps | 27123712 | +| train/ | | +| approx_kl | 0.017221661 | +| clip_fraction | 0.36 | +| clip_range | 0.0682 | +| entropy_loss | -5.94 | +| explained_variance | 0.46 | +| learning_rate | 4.36e-05 | +| loss | -0.0277 | +| n_updates | 68792 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000208 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1411 | +| iterations | 13245 | +| time_elapsed | 19222 | +| total_timesteps | 27125760 | +| train/ | | +| approx_kl | 0.016399395 | +| clip_fraction | 0.304 | +| clip_range | 0.0682 | +| entropy_loss | -5.52 | +| explained_variance | 0.408 | +| learning_rate | 4.36e-05 | +| loss | -0.0338 | +| n_updates | 68796 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.000285 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1411 | +| iterations | 13246 | +| time_elapsed | 19224 | +| total_timesteps | 27127808 | +| train/ | | +| approx_kl | 0.012612747 | +| clip_fraction | 0.338 | +| clip_range | 0.0682 | +| entropy_loss | -5.03 | +| explained_variance | 0.609 | +| learning_rate | 4.36e-05 | +| loss | -0.0314 | +| n_updates | 68800 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000143 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.384 | +| time/ | | +| fps | 1411 | +| iterations | 13247 | +| time_elapsed | 19225 | +| total_timesteps | 27129856 | +| train/ | | +| approx_kl | 0.015845353 | +| clip_fraction | 0.343 | +| clip_range | 0.0682 | +| entropy_loss | -5.95 | +| explained_variance | 0.351 | +| learning_rate | 4.36e-05 | +| loss | -0.0297 | +| n_updates | 68804 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000212 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.384 | +| time/ | | +| fps | 1411 | +| iterations | 13248 | +| time_elapsed | 19227 | +| total_timesteps | 27131904 | +| train/ | | +| approx_kl | 0.011713448 | +| clip_fraction | 0.363 | +| clip_range | 0.0682 | +| entropy_loss | -6.34 | +| explained_variance | 0.26 | +| learning_rate | 4.36e-05 | +| loss | -0.0255 | +| n_updates | 68808 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000235 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1411 | +| iterations | 13249 | +| time_elapsed | 19228 | +| total_timesteps | 27133952 | +| train/ | | +| approx_kl | 0.014819043 | +| clip_fraction | 0.347 | +| clip_range | 0.0682 | +| entropy_loss | -6.75 | +| explained_variance | -0.0135 | +| learning_rate | 4.36e-05 | +| loss | -0.0322 | +| n_updates | 68812 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000137 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1411 | +| iterations | 13250 | +| time_elapsed | 19230 | +| total_timesteps | 27136000 | +| train/ | | +| approx_kl | 0.011607431 | +| clip_fraction | 0.333 | +| clip_range | 0.0682 | +| entropy_loss | -6.13 | +| explained_variance | 0.489 | +| learning_rate | 4.36e-05 | +| loss | -0.027 | +| n_updates | 68816 | +| policy_gradient_loss | -0.0148 | +| value_loss | 0.000195 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1411 | +| iterations | 13251 | +| time_elapsed | 19231 | +| total_timesteps | 27138048 | +| train/ | | +| approx_kl | 0.013910406 | +| clip_fraction | 0.31 | +| clip_range | 0.0682 | +| entropy_loss | -6.28 | +| explained_variance | 0.363 | +| learning_rate | 4.36e-05 | +| loss | -0.0296 | +| n_updates | 68820 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000164 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1411 | +| iterations | 13252 | +| time_elapsed | 19233 | +| total_timesteps | 27140096 | +| train/ | | +| approx_kl | 0.012732035 | +| clip_fraction | 0.346 | +| clip_range | 0.0682 | +| entropy_loss | -6.69 | +| explained_variance | 0.342 | +| learning_rate | 4.36e-05 | +| loss | -0.0282 | +| n_updates | 68824 | +| policy_gradient_loss | -0.0188 | +| value_loss | 9.35e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1411 | +| iterations | 13253 | +| time_elapsed | 19234 | +| total_timesteps | 27142144 | +| train/ | | +| approx_kl | 0.010343219 | +| clip_fraction | 0.33 | +| clip_range | 0.0682 | +| entropy_loss | -6.72 | +| explained_variance | 0.0571 | +| learning_rate | 4.36e-05 | +| loss | -0.0324 | +| n_updates | 68828 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.000204 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1411 | +| iterations | 13254 | +| time_elapsed | 19236 | +| total_timesteps | 27144192 | +| train/ | | +| approx_kl | 0.011520043 | +| clip_fraction | 0.331 | +| clip_range | 0.0682 | +| entropy_loss | -5.96 | +| explained_variance | 0.517 | +| learning_rate | 4.36e-05 | +| loss | -0.0299 | +| n_updates | 68832 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000192 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1411 | +| iterations | 13255 | +| time_elapsed | 19237 | +| total_timesteps | 27146240 | +| train/ | | +| approx_kl | 0.014100586 | +| clip_fraction | 0.35 | +| clip_range | 0.0682 | +| entropy_loss | -6.34 | +| explained_variance | 0.348 | +| learning_rate | 4.36e-05 | +| loss | -0.0344 | +| n_updates | 68836 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000108 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1411 | +| iterations | 13256 | +| time_elapsed | 19239 | +| total_timesteps | 27148288 | +| train/ | | +| approx_kl | 0.009333924 | +| clip_fraction | 0.318 | +| clip_range | 0.0682 | +| entropy_loss | -6.5 | +| explained_variance | 0.329 | +| learning_rate | 4.36e-05 | +| loss | -0.0233 | +| n_updates | 68840 | +| policy_gradient_loss | -0.0148 | +| value_loss | 0.000323 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1411 | +| iterations | 13257 | +| time_elapsed | 19240 | +| total_timesteps | 27150336 | +| train/ | | +| approx_kl | 0.0110078035 | +| clip_fraction | 0.317 | +| clip_range | 0.0682 | +| entropy_loss | -5.8 | +| explained_variance | 0.63 | +| learning_rate | 4.36e-05 | +| loss | -0.0261 | +| n_updates | 68844 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000149 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1411 | +| iterations | 13258 | +| time_elapsed | 19242 | +| total_timesteps | 27152384 | +| train/ | | +| approx_kl | 0.013061015 | +| clip_fraction | 0.341 | +| clip_range | 0.0682 | +| entropy_loss | -5.22 | +| explained_variance | 0.536 | +| learning_rate | 4.36e-05 | +| loss | -0.0247 | +| n_updates | 68848 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000244 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1411 | +| iterations | 13259 | +| time_elapsed | 19243 | +| total_timesteps | 27154432 | +| train/ | | +| approx_kl | 0.014269249 | +| clip_fraction | 0.37 | +| clip_range | 0.0682 | +| entropy_loss | -6.11 | +| explained_variance | 0.163 | +| learning_rate | 4.36e-05 | +| loss | -0.0385 | +| n_updates | 68852 | +| policy_gradient_loss | -0.0232 | +| value_loss | 8.41e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1411 | +| iterations | 13260 | +| time_elapsed | 19245 | +| total_timesteps | 27156480 | +| train/ | | +| approx_kl | 0.011906156 | +| clip_fraction | 0.365 | +| clip_range | 0.0682 | +| entropy_loss | -6.84 | +| explained_variance | -0.119 | +| learning_rate | 4.36e-05 | +| loss | -0.036 | +| n_updates | 68856 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000108 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1411 | +| iterations | 13261 | +| time_elapsed | 19246 | +| total_timesteps | 27158528 | +| train/ | | +| approx_kl | 0.008234685 | +| clip_fraction | 0.309 | +| clip_range | 0.0682 | +| entropy_loss | -6.48 | +| explained_variance | 0.275 | +| learning_rate | 4.36e-05 | +| loss | -0.0228 | +| n_updates | 68860 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.000402 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1411 | +| iterations | 13262 | +| time_elapsed | 19248 | +| total_timesteps | 27160576 | +| train/ | | +| approx_kl | 0.012376552 | +| clip_fraction | 0.353 | +| clip_range | 0.0682 | +| entropy_loss | -6.47 | +| explained_variance | 0.253 | +| learning_rate | 4.35e-05 | +| loss | -0.0303 | +| n_updates | 68864 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000128 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1411 | +| iterations | 13263 | +| time_elapsed | 19249 | +| total_timesteps | 27162624 | +| train/ | | +| approx_kl | 0.013929082 | +| clip_fraction | 0.32 | +| clip_range | 0.0682 | +| entropy_loss | -5.9 | +| explained_variance | 0.424 | +| learning_rate | 4.35e-05 | +| loss | -0.022 | +| n_updates | 68868 | +| policy_gradient_loss | -0.0147 | +| value_loss | 0.000272 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1411 | +| iterations | 13264 | +| time_elapsed | 19251 | +| total_timesteps | 27164672 | +| train/ | | +| approx_kl | 0.019541338 | +| clip_fraction | 0.35 | +| clip_range | 0.0682 | +| entropy_loss | -6.66 | +| explained_variance | -0.0951 | +| learning_rate | 4.35e-05 | +| loss | -0.0348 | +| n_updates | 68872 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000119 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1411 | +| iterations | 13265 | +| time_elapsed | 19252 | +| total_timesteps | 27166720 | +| train/ | | +| approx_kl | 0.015403319 | +| clip_fraction | 0.374 | +| clip_range | 0.0682 | +| entropy_loss | -6.34 | +| explained_variance | 0.327 | +| learning_rate | 4.35e-05 | +| loss | -0.0285 | +| n_updates | 68876 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1411 | +| iterations | 13266 | +| time_elapsed | 19254 | +| total_timesteps | 27168768 | +| train/ | | +| approx_kl | 0.018204253 | +| clip_fraction | 0.381 | +| clip_range | 0.0682 | +| entropy_loss | -6.01 | +| explained_variance | 0.684 | +| learning_rate | 4.35e-05 | +| loss | -0.0347 | +| n_updates | 68880 | +| policy_gradient_loss | -0.0241 | +| value_loss | 5.71e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1411 | +| iterations | 13267 | +| time_elapsed | 19255 | +| total_timesteps | 27170816 | +| train/ | | +| approx_kl | 0.011374763 | +| clip_fraction | 0.329 | +| clip_range | 0.0682 | +| entropy_loss | -6.39 | +| explained_variance | 0.521 | +| learning_rate | 4.35e-05 | +| loss | -0.0317 | +| n_updates | 68884 | +| policy_gradient_loss | -0.0208 | +| value_loss | 6.58e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1411 | +| iterations | 13268 | +| time_elapsed | 19257 | +| total_timesteps | 27172864 | +| train/ | | +| approx_kl | 0.008676562 | +| clip_fraction | 0.299 | +| clip_range | 0.0682 | +| entropy_loss | -5.92 | +| explained_variance | 0.415 | +| learning_rate | 4.35e-05 | +| loss | -0.0187 | +| n_updates | 68888 | +| policy_gradient_loss | -0.0133 | +| value_loss | 0.000385 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1411 | +| iterations | 13269 | +| time_elapsed | 19258 | +| total_timesteps | 27174912 | +| train/ | | +| approx_kl | 0.010487337 | +| clip_fraction | 0.334 | +| clip_range | 0.0682 | +| entropy_loss | -5.49 | +| explained_variance | 0.597 | +| learning_rate | 4.35e-05 | +| loss | -0.0271 | +| n_updates | 68892 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000208 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1411 | +| iterations | 13270 | +| time_elapsed | 19260 | +| total_timesteps | 27176960 | +| train/ | | +| approx_kl | 0.014217483 | +| clip_fraction | 0.377 | +| clip_range | 0.0682 | +| entropy_loss | -5.95 | +| explained_variance | 0.213 | +| learning_rate | 4.35e-05 | +| loss | -0.0293 | +| n_updates | 68896 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.00013 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1411 | +| iterations | 13271 | +| time_elapsed | 19261 | +| total_timesteps | 27179008 | +| train/ | | +| approx_kl | 0.012541734 | +| clip_fraction | 0.338 | +| clip_range | 0.0682 | +| entropy_loss | -6.17 | +| explained_variance | 0.361 | +| learning_rate | 4.35e-05 | +| loss | -0.0244 | +| n_updates | 68900 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000184 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1411 | +| iterations | 13272 | +| time_elapsed | 19263 | +| total_timesteps | 27181056 | +| train/ | | +| approx_kl | 0.013770685 | +| clip_fraction | 0.356 | +| clip_range | 0.0682 | +| entropy_loss | -6.34 | +| explained_variance | 0.257 | +| learning_rate | 4.35e-05 | +| loss | -0.0329 | +| n_updates | 68904 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000227 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.386 | +| time/ | | +| fps | 1411 | +| iterations | 13273 | +| time_elapsed | 19264 | +| total_timesteps | 27183104 | +| train/ | | +| approx_kl | 0.01803271 | +| clip_fraction | 0.349 | +| clip_range | 0.0682 | +| entropy_loss | -6.19 | +| explained_variance | 0.169 | +| learning_rate | 4.35e-05 | +| loss | -0.0309 | +| n_updates | 68908 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000259 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.386 | +| time/ | | +| fps | 1411 | +| iterations | 13274 | +| time_elapsed | 19266 | +| total_timesteps | 27185152 | +| train/ | | +| approx_kl | 0.010955464 | +| clip_fraction | 0.323 | +| clip_range | 0.0682 | +| entropy_loss | -6.54 | +| explained_variance | -0.0236 | +| learning_rate | 4.35e-05 | +| loss | -0.0265 | +| n_updates | 68912 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000379 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.387 | +| time/ | | +| fps | 1411 | +| iterations | 13275 | +| time_elapsed | 19267 | +| total_timesteps | 27187200 | +| train/ | | +| approx_kl | 0.013559755 | +| clip_fraction | 0.352 | +| clip_range | 0.0682 | +| entropy_loss | -6 | +| explained_variance | 0.459 | +| learning_rate | 4.35e-05 | +| loss | -0.0321 | +| n_updates | 68916 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000174 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1411 | +| iterations | 13276 | +| time_elapsed | 19269 | +| total_timesteps | 27189248 | +| train/ | | +| approx_kl | 0.012513625 | +| clip_fraction | 0.331 | +| clip_range | 0.0682 | +| entropy_loss | -6.22 | +| explained_variance | 0.457 | +| learning_rate | 4.35e-05 | +| loss | -0.0313 | +| n_updates | 68920 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000178 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1411 | +| iterations | 13277 | +| time_elapsed | 19270 | +| total_timesteps | 27191296 | +| train/ | | +| approx_kl | 0.013591688 | +| clip_fraction | 0.359 | +| clip_range | 0.0682 | +| entropy_loss | -6.28 | +| explained_variance | 0.328 | +| learning_rate | 4.35e-05 | +| loss | -0.0314 | +| n_updates | 68924 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000151 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.384 | +| time/ | | +| fps | 1411 | +| iterations | 13278 | +| time_elapsed | 19272 | +| total_timesteps | 27193344 | +| train/ | | +| approx_kl | 0.01515128 | +| clip_fraction | 0.339 | +| clip_range | 0.0682 | +| entropy_loss | -6.45 | +| explained_variance | 0.287 | +| learning_rate | 4.35e-05 | +| loss | -0.0257 | +| n_updates | 68928 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000148 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1411 | +| iterations | 13279 | +| time_elapsed | 19273 | +| total_timesteps | 27195392 | +| train/ | | +| approx_kl | 0.013780955 | +| clip_fraction | 0.319 | +| clip_range | 0.0682 | +| entropy_loss | -5.81 | +| explained_variance | 0.509 | +| learning_rate | 4.35e-05 | +| loss | -0.0264 | +| n_updates | 68932 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.00024 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1411 | +| iterations | 13280 | +| time_elapsed | 19275 | +| total_timesteps | 27197440 | +| train/ | | +| approx_kl | 0.013652261 | +| clip_fraction | 0.352 | +| clip_range | 0.0682 | +| entropy_loss | -5.62 | +| explained_variance | 0.393 | +| learning_rate | 4.35e-05 | +| loss | -0.0298 | +| n_updates | 68936 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000247 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1411 | +| iterations | 13281 | +| time_elapsed | 19276 | +| total_timesteps | 27199488 | +| train/ | | +| approx_kl | 0.014075592 | +| clip_fraction | 0.353 | +| clip_range | 0.0682 | +| entropy_loss | -5.71 | +| explained_variance | 0.57 | +| learning_rate | 4.35e-05 | +| loss | -0.0321 | +| n_updates | 68940 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000168 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1411 | +| iterations | 13282 | +| time_elapsed | 19278 | +| total_timesteps | 27201536 | +| train/ | | +| approx_kl | 0.019089334 | +| clip_fraction | 0.348 | +| clip_range | 0.0682 | +| entropy_loss | -6.1 | +| explained_variance | 0.33 | +| learning_rate | 4.35e-05 | +| loss | -0.0283 | +| n_updates | 68944 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000152 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.39 | +| time/ | | +| fps | 1410 | +| iterations | 13283 | +| time_elapsed | 19279 | +| total_timesteps | 27203584 | +| train/ | | +| approx_kl | 0.012375883 | +| clip_fraction | 0.335 | +| clip_range | 0.0682 | +| entropy_loss | -6.57 | +| explained_variance | 0.0725 | +| learning_rate | 4.35e-05 | +| loss | -0.0289 | +| n_updates | 68948 | +| policy_gradient_loss | -0.0145 | +| value_loss | 0.00025 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.391 | +| time/ | | +| fps | 1410 | +| iterations | 13284 | +| time_elapsed | 19281 | +| total_timesteps | 27205632 | +| train/ | | +| approx_kl | 0.011253175 | +| clip_fraction | 0.333 | +| clip_range | 0.0682 | +| entropy_loss | -6.03 | +| explained_variance | 0.258 | +| learning_rate | 4.35e-05 | +| loss | -0.0212 | +| n_updates | 68952 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000388 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.39 | +| time/ | | +| fps | 1410 | +| iterations | 13285 | +| time_elapsed | 19282 | +| total_timesteps | 27207680 | +| train/ | | +| approx_kl | 0.016453877 | +| clip_fraction | 0.365 | +| clip_range | 0.0682 | +| entropy_loss | -5.85 | +| explained_variance | 0.595 | +| learning_rate | 4.35e-05 | +| loss | -0.034 | +| n_updates | 68956 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.00011 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1410 | +| iterations | 13286 | +| time_elapsed | 19284 | +| total_timesteps | 27209728 | +| train/ | | +| approx_kl | 0.017309498 | +| clip_fraction | 0.342 | +| clip_range | 0.0682 | +| entropy_loss | -6.6 | +| explained_variance | -0.102 | +| learning_rate | 4.35e-05 | +| loss | -0.034 | +| n_updates | 68960 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000204 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1410 | +| iterations | 13287 | +| time_elapsed | 19285 | +| total_timesteps | 27211776 | +| train/ | | +| approx_kl | 0.0130069945 | +| clip_fraction | 0.318 | +| clip_range | 0.0682 | +| entropy_loss | -6.59 | +| explained_variance | 0.435 | +| learning_rate | 4.35e-05 | +| loss | -0.0277 | +| n_updates | 68964 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000128 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.386 | +| time/ | | +| fps | 1410 | +| iterations | 13288 | +| time_elapsed | 19287 | +| total_timesteps | 27213824 | +| train/ | | +| approx_kl | 0.013011277 | +| clip_fraction | 0.338 | +| clip_range | 0.0682 | +| entropy_loss | -6.44 | +| explained_variance | 0.359 | +| learning_rate | 4.35e-05 | +| loss | -0.0298 | +| n_updates | 68968 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000136 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.388 | +| time/ | | +| fps | 1410 | +| iterations | 13289 | +| time_elapsed | 19288 | +| total_timesteps | 27215872 | +| train/ | | +| approx_kl | 0.010573782 | +| clip_fraction | 0.328 | +| clip_range | 0.0682 | +| entropy_loss | -6.42 | +| explained_variance | 0.288 | +| learning_rate | 4.35e-05 | +| loss | -0.0283 | +| n_updates | 68972 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000237 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.386 | +| time/ | | +| fps | 1410 | +| iterations | 13290 | +| time_elapsed | 19290 | +| total_timesteps | 27217920 | +| train/ | | +| approx_kl | 0.013780713 | +| clip_fraction | 0.37 | +| clip_range | 0.0682 | +| entropy_loss | -6.25 | +| explained_variance | 0.651 | +| learning_rate | 4.35e-05 | +| loss | -0.0398 | +| n_updates | 68976 | +| policy_gradient_loss | -0.0224 | +| value_loss | 8.3e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.385 | +| time/ | | +| fps | 1410 | +| iterations | 13291 | +| time_elapsed | 19291 | +| total_timesteps | 27219968 | +| train/ | | +| approx_kl | 0.013452883 | +| clip_fraction | 0.353 | +| clip_range | 0.0682 | +| entropy_loss | -6.28 | +| explained_variance | 0.0249 | +| learning_rate | 4.35e-05 | +| loss | -0.0245 | +| n_updates | 68980 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000113 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.384 | +| time/ | | +| fps | 1410 | +| iterations | 13292 | +| time_elapsed | 19293 | +| total_timesteps | 27222016 | +| train/ | | +| approx_kl | 0.010835025 | +| clip_fraction | 0.32 | +| clip_range | 0.0682 | +| entropy_loss | -6.45 | +| explained_variance | 0.403 | +| learning_rate | 4.35e-05 | +| loss | -0.0229 | +| n_updates | 68984 | +| policy_gradient_loss | -0.0147 | +| value_loss | 0.000213 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1410 | +| iterations | 13293 | +| time_elapsed | 19294 | +| total_timesteps | 27224064 | +| train/ | | +| approx_kl | 0.016080506 | +| clip_fraction | 0.362 | +| clip_range | 0.0682 | +| entropy_loss | -6.32 | +| explained_variance | 0.535 | +| learning_rate | 4.35e-05 | +| loss | -0.0336 | +| n_updates | 68988 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000128 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1410 | +| iterations | 13294 | +| time_elapsed | 19296 | +| total_timesteps | 27226112 | +| train/ | | +| approx_kl | 0.0114820395 | +| clip_fraction | 0.326 | +| clip_range | 0.0682 | +| entropy_loss | -5.68 | +| explained_variance | 0.64 | +| learning_rate | 4.35e-05 | +| loss | -0.0256 | +| n_updates | 68992 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000181 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1410 | +| iterations | 13295 | +| time_elapsed | 19297 | +| total_timesteps | 27228160 | +| train/ | | +| approx_kl | 0.013522776 | +| clip_fraction | 0.35 | +| clip_range | 0.0682 | +| entropy_loss | -6.09 | +| explained_variance | 0.549 | +| learning_rate | 4.35e-05 | +| loss | -0.0295 | +| n_updates | 68996 | +| policy_gradient_loss | -0.0201 | +| value_loss | 9e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1410 | +| iterations | 13296 | +| time_elapsed | 19299 | +| total_timesteps | 27230208 | +| train/ | | +| approx_kl | 0.013188595 | +| clip_fraction | 0.355 | +| clip_range | 0.0682 | +| entropy_loss | -6.19 | +| explained_variance | 0.28 | +| learning_rate | 4.35e-05 | +| loss | -0.0258 | +| n_updates | 69000 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000235 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1410 | +| iterations | 13297 | +| time_elapsed | 19300 | +| total_timesteps | 27232256 | +| train/ | | +| approx_kl | 0.01390426 | +| clip_fraction | 0.348 | +| clip_range | 0.0682 | +| entropy_loss | -6.63 | +| explained_variance | 0.254 | +| learning_rate | 4.35e-05 | +| loss | -0.0306 | +| n_updates | 69004 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000178 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1410 | +| iterations | 13298 | +| time_elapsed | 19302 | +| total_timesteps | 27234304 | +| train/ | | +| approx_kl | 0.010707155 | +| clip_fraction | 0.333 | +| clip_range | 0.0682 | +| entropy_loss | -6.33 | +| explained_variance | 0.483 | +| learning_rate | 4.35e-05 | +| loss | -0.0326 | +| n_updates | 69008 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000183 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1410 | +| iterations | 13299 | +| time_elapsed | 19303 | +| total_timesteps | 27236352 | +| train/ | | +| approx_kl | 0.008972711 | +| clip_fraction | 0.318 | +| clip_range | 0.0682 | +| entropy_loss | -5.93 | +| explained_variance | 0.369 | +| learning_rate | 4.35e-05 | +| loss | -0.0248 | +| n_updates | 69012 | +| policy_gradient_loss | -0.0144 | +| value_loss | 0.000284 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1410 | +| iterations | 13300 | +| time_elapsed | 19305 | +| total_timesteps | 27238400 | +| train/ | | +| approx_kl | 0.011527428 | +| clip_fraction | 0.342 | +| clip_range | 0.0682 | +| entropy_loss | -6.21 | +| explained_variance | 0.367 | +| learning_rate | 4.35e-05 | +| loss | -0.0322 | +| n_updates | 69016 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000117 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1410 | +| iterations | 13301 | +| time_elapsed | 19306 | +| total_timesteps | 27240448 | +| train/ | | +| approx_kl | 0.010978075 | +| clip_fraction | 0.327 | +| clip_range | 0.0682 | +| entropy_loss | -5.57 | +| explained_variance | 0.584 | +| learning_rate | 4.35e-05 | +| loss | -0.0252 | +| n_updates | 69020 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.00024 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1410 | +| iterations | 13302 | +| time_elapsed | 19308 | +| total_timesteps | 27242496 | +| train/ | | +| approx_kl | 0.011335827 | +| clip_fraction | 0.363 | +| clip_range | 0.0682 | +| entropy_loss | -6.35 | +| explained_variance | 0.226 | +| learning_rate | 4.35e-05 | +| loss | -0.0401 | +| n_updates | 69024 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000113 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1410 | +| iterations | 13303 | +| time_elapsed | 19309 | +| total_timesteps | 27244544 | +| train/ | | +| approx_kl | 0.0084172785 | +| clip_fraction | 0.31 | +| clip_range | 0.0682 | +| entropy_loss | -5.95 | +| explained_variance | 0.424 | +| learning_rate | 4.35e-05 | +| loss | -0.0226 | +| n_updates | 69028 | +| policy_gradient_loss | -0.014 | +| value_loss | 0.000356 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1410 | +| iterations | 13304 | +| time_elapsed | 19311 | +| total_timesteps | 27246592 | +| train/ | | +| approx_kl | 0.011960096 | +| clip_fraction | 0.32 | +| clip_range | 0.0682 | +| entropy_loss | -5.83 | +| explained_variance | 0.502 | +| learning_rate | 4.35e-05 | +| loss | -0.0334 | +| n_updates | 69032 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000125 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1410 | +| iterations | 13305 | +| time_elapsed | 19312 | +| total_timesteps | 27248640 | +| train/ | | +| approx_kl | 0.011180417 | +| clip_fraction | 0.32 | +| clip_range | 0.0682 | +| entropy_loss | -6.54 | +| explained_variance | 0.186 | +| learning_rate | 4.35e-05 | +| loss | -0.0307 | +| n_updates | 69036 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.00017 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1410 | +| iterations | 13306 | +| time_elapsed | 19314 | +| total_timesteps | 27250688 | +| train/ | | +| approx_kl | 0.012215406 | +| clip_fraction | 0.312 | +| clip_range | 0.0682 | +| entropy_loss | -6.4 | +| explained_variance | 0.435 | +| learning_rate | 4.35e-05 | +| loss | -0.0232 | +| n_updates | 69040 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000188 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1410 | +| iterations | 13307 | +| time_elapsed | 19315 | +| total_timesteps | 27252736 | +| train/ | | +| approx_kl | 0.011505637 | +| clip_fraction | 0.345 | +| clip_range | 0.0682 | +| entropy_loss | -5.66 | +| explained_variance | 0.401 | +| learning_rate | 4.35e-05 | +| loss | -0.0322 | +| n_updates | 69044 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000304 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1410 | +| iterations | 13308 | +| time_elapsed | 19317 | +| total_timesteps | 27254784 | +| train/ | | +| approx_kl | 0.013940698 | +| clip_fraction | 0.371 | +| clip_range | 0.0682 | +| entropy_loss | -5.65 | +| explained_variance | 0.635 | +| learning_rate | 4.35e-05 | +| loss | -0.0375 | +| n_updates | 69048 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000125 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1410 | +| iterations | 13309 | +| time_elapsed | 19318 | +| total_timesteps | 27256832 | +| train/ | | +| approx_kl | 0.011484601 | +| clip_fraction | 0.32 | +| clip_range | 0.0682 | +| entropy_loss | -5.72 | +| explained_variance | 0.512 | +| learning_rate | 4.35e-05 | +| loss | -0.0217 | +| n_updates | 69052 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000249 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1410 | +| iterations | 13310 | +| time_elapsed | 19320 | +| total_timesteps | 27258880 | +| train/ | | +| approx_kl | 0.01144883 | +| clip_fraction | 0.353 | +| clip_range | 0.0682 | +| entropy_loss | -6.49 | +| explained_variance | -0.00837 | +| learning_rate | 4.35e-05 | +| loss | -0.0343 | +| n_updates | 69056 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.00019 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1410 | +| iterations | 13311 | +| time_elapsed | 19321 | +| total_timesteps | 27260928 | +| train/ | | +| approx_kl | 0.017513644 | +| clip_fraction | 0.33 | +| clip_range | 0.0682 | +| entropy_loss | -6.1 | +| explained_variance | 0.328 | +| learning_rate | 4.35e-05 | +| loss | -0.0178 | +| n_updates | 69060 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000368 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1410 | +| iterations | 13312 | +| time_elapsed | 19323 | +| total_timesteps | 27262976 | +| train/ | | +| approx_kl | 0.017477425 | +| clip_fraction | 0.35 | +| clip_range | 0.0682 | +| entropy_loss | -5.67 | +| explained_variance | 0.581 | +| learning_rate | 4.35e-05 | +| loss | -0.0381 | +| n_updates | 69064 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000158 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1410 | +| iterations | 13313 | +| time_elapsed | 19324 | +| total_timesteps | 27265024 | +| train/ | | +| approx_kl | 0.016089357 | +| clip_fraction | 0.363 | +| clip_range | 0.0682 | +| entropy_loss | -6.49 | +| explained_variance | 0.351 | +| learning_rate | 4.35e-05 | +| loss | -0.0326 | +| n_updates | 69068 | +| policy_gradient_loss | -0.0222 | +| value_loss | 0.000122 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1410 | +| iterations | 13314 | +| time_elapsed | 19326 | +| total_timesteps | 27267072 | +| train/ | | +| approx_kl | 0.012000866 | +| clip_fraction | 0.343 | +| clip_range | 0.0682 | +| entropy_loss | -6.11 | +| explained_variance | 0.463 | +| learning_rate | 4.35e-05 | +| loss | -0.0275 | +| n_updates | 69072 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000169 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1410 | +| iterations | 13315 | +| time_elapsed | 19327 | +| total_timesteps | 27269120 | +| train/ | | +| approx_kl | 0.009154767 | +| clip_fraction | 0.298 | +| clip_range | 0.0682 | +| entropy_loss | -6.27 | +| explained_variance | 0.465 | +| learning_rate | 4.35e-05 | +| loss | -0.0314 | +| n_updates | 69076 | +| policy_gradient_loss | -0.0136 | +| value_loss | 0.000356 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1410 | +| iterations | 13316 | +| time_elapsed | 19329 | +| total_timesteps | 27271168 | +| train/ | | +| approx_kl | 0.010083864 | +| clip_fraction | 0.307 | +| clip_range | 0.0682 | +| entropy_loss | -6.64 | +| explained_variance | -0.189 | +| learning_rate | 4.35e-05 | +| loss | -0.0295 | +| n_updates | 69080 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000192 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1410 | +| iterations | 13317 | +| time_elapsed | 19331 | +| total_timesteps | 27273216 | +| train/ | | +| approx_kl | 0.0122459205 | +| clip_fraction | 0.333 | +| clip_range | 0.0682 | +| entropy_loss | -6.44 | +| explained_variance | 0.318 | +| learning_rate | 4.35e-05 | +| loss | -0.0241 | +| n_updates | 69084 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000238 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1410 | +| iterations | 13318 | +| time_elapsed | 19332 | +| total_timesteps | 27275264 | +| train/ | | +| approx_kl | 0.011877738 | +| clip_fraction | 0.322 | +| clip_range | 0.0682 | +| entropy_loss | -5.91 | +| explained_variance | 0.4 | +| learning_rate | 4.35e-05 | +| loss | -0.0301 | +| n_updates | 69088 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000248 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1410 | +| iterations | 13319 | +| time_elapsed | 19334 | +| total_timesteps | 27277312 | +| train/ | | +| approx_kl | 0.011509193 | +| clip_fraction | 0.341 | +| clip_range | 0.0682 | +| entropy_loss | -5.73 | +| explained_variance | 0.443 | +| learning_rate | 4.35e-05 | +| loss | -0.0253 | +| n_updates | 69092 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000241 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1410 | +| iterations | 13320 | +| time_elapsed | 19335 | +| total_timesteps | 27279360 | +| train/ | | +| approx_kl | 0.017529465 | +| clip_fraction | 0.348 | +| clip_range | 0.0682 | +| entropy_loss | -5.83 | +| explained_variance | 0.613 | +| learning_rate | 4.35e-05 | +| loss | -0.0271 | +| n_updates | 69096 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000121 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1410 | +| iterations | 13321 | +| time_elapsed | 19337 | +| total_timesteps | 27281408 | +| train/ | | +| approx_kl | 0.011675522 | +| clip_fraction | 0.309 | +| clip_range | 0.0682 | +| entropy_loss | -5.9 | +| explained_variance | 0.311 | +| learning_rate | 4.35e-05 | +| loss | -0.0309 | +| n_updates | 69100 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000298 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1410 | +| iterations | 13322 | +| time_elapsed | 19338 | +| total_timesteps | 27283456 | +| train/ | | +| approx_kl | 0.010897066 | +| clip_fraction | 0.35 | +| clip_range | 0.0682 | +| entropy_loss | -6.36 | +| explained_variance | 0.298 | +| learning_rate | 4.35e-05 | +| loss | -0.0318 | +| n_updates | 69104 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000197 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1410 | +| iterations | 13323 | +| time_elapsed | 19340 | +| total_timesteps | 27285504 | +| train/ | | +| approx_kl | 0.0102749895 | +| clip_fraction | 0.302 | +| clip_range | 0.0682 | +| entropy_loss | -6.5 | +| explained_variance | 0.368 | +| learning_rate | 4.35e-05 | +| loss | -0.031 | +| n_updates | 69108 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000257 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1410 | +| iterations | 13324 | +| time_elapsed | 19341 | +| total_timesteps | 27287552 | +| train/ | | +| approx_kl | 0.011730291 | +| clip_fraction | 0.332 | +| clip_range | 0.0682 | +| entropy_loss | -6.38 | +| explained_variance | 0.161 | +| learning_rate | 4.35e-05 | +| loss | -0.0246 | +| n_updates | 69112 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000323 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1410 | +| iterations | 13325 | +| time_elapsed | 19343 | +| total_timesteps | 27289600 | +| train/ | | +| approx_kl | 0.01270449 | +| clip_fraction | 0.35 | +| clip_range | 0.0682 | +| entropy_loss | -6.25 | +| explained_variance | 0.673 | +| learning_rate | 4.35e-05 | +| loss | -0.0358 | +| n_updates | 69116 | +| policy_gradient_loss | -0.0227 | +| value_loss | 7.09e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1410 | +| iterations | 13326 | +| time_elapsed | 19344 | +| total_timesteps | 27291648 | +| train/ | | +| approx_kl | 0.013741366 | +| clip_fraction | 0.358 | +| clip_range | 0.0682 | +| entropy_loss | -6.62 | +| explained_variance | 0.00273 | +| learning_rate | 4.35e-05 | +| loss | -0.0336 | +| n_updates | 69120 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000168 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1410 | +| iterations | 13327 | +| time_elapsed | 19346 | +| total_timesteps | 27293696 | +| train/ | | +| approx_kl | 0.011729918 | +| clip_fraction | 0.358 | +| clip_range | 0.0682 | +| entropy_loss | -6.85 | +| explained_variance | 0.281 | +| learning_rate | 4.35e-05 | +| loss | -0.0398 | +| n_updates | 69124 | +| policy_gradient_loss | -0.0215 | +| value_loss | 9.1e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.14e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1410 | +| iterations | 13328 | +| time_elapsed | 19347 | +| total_timesteps | 27295744 | +| train/ | | +| approx_kl | 0.0103570465 | +| clip_fraction | 0.296 | +| clip_range | 0.0682 | +| entropy_loss | -6.77 | +| explained_variance | 0.548 | +| learning_rate | 4.35e-05 | +| loss | -0.0272 | +| n_updates | 69128 | +| policy_gradient_loss | -0.0177 | +| value_loss | 9.89e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.14e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1410 | +| iterations | 13329 | +| time_elapsed | 19349 | +| total_timesteps | 27297792 | +| train/ | | +| approx_kl | 0.011601975 | +| clip_fraction | 0.332 | +| clip_range | 0.0682 | +| entropy_loss | -6.79 | +| explained_variance | 0.0112 | +| learning_rate | 4.35e-05 | +| loss | -0.0275 | +| n_updates | 69132 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000272 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1410 | +| iterations | 13330 | +| time_elapsed | 19350 | +| total_timesteps | 27299840 | +| train/ | | +| approx_kl | 0.0114564095 | +| clip_fraction | 0.307 | +| clip_range | 0.0682 | +| entropy_loss | -5.41 | +| explained_variance | 0.678 | +| learning_rate | 4.35e-05 | +| loss | -0.0287 | +| n_updates | 69136 | +| policy_gradient_loss | -0.0126 | +| value_loss | 0.000233 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1410 | +| iterations | 13331 | +| time_elapsed | 19352 | +| total_timesteps | 27301888 | +| train/ | | +| approx_kl | 0.014926583 | +| clip_fraction | 0.349 | +| clip_range | 0.0682 | +| entropy_loss | -5.4 | +| explained_variance | 0.664 | +| learning_rate | 4.35e-05 | +| loss | -0.0325 | +| n_updates | 69140 | +| policy_gradient_loss | -0.0208 | +| value_loss | 8.21e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.14e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1410 | +| iterations | 13332 | +| time_elapsed | 19353 | +| total_timesteps | 27303936 | +| train/ | | +| approx_kl | 0.013145108 | +| clip_fraction | 0.336 | +| clip_range | 0.0682 | +| entropy_loss | -5.66 | +| explained_variance | 0.653 | +| learning_rate | 4.35e-05 | +| loss | -0.0311 | +| n_updates | 69144 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.00012 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.14e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1410 | +| iterations | 13333 | +| time_elapsed | 19355 | +| total_timesteps | 27305984 | +| train/ | | +| approx_kl | 0.013294206 | +| clip_fraction | 0.351 | +| clip_range | 0.0682 | +| entropy_loss | -6.61 | +| explained_variance | 0.418 | +| learning_rate | 4.35e-05 | +| loss | -0.0311 | +| n_updates | 69148 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000143 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1410 | +| iterations | 13334 | +| time_elapsed | 19356 | +| total_timesteps | 27308032 | +| train/ | | +| approx_kl | 0.012795391 | +| clip_fraction | 0.341 | +| clip_range | 0.0682 | +| entropy_loss | -6.77 | +| explained_variance | 0.0157 | +| learning_rate | 4.35e-05 | +| loss | -0.0285 | +| n_updates | 69152 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000195 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1410 | +| iterations | 13335 | +| time_elapsed | 19358 | +| total_timesteps | 27310080 | +| train/ | | +| approx_kl | 0.0141959945 | +| clip_fraction | 0.375 | +| clip_range | 0.0682 | +| entropy_loss | -6.38 | +| explained_variance | 0.46 | +| learning_rate | 4.35e-05 | +| loss | -0.0325 | +| n_updates | 69156 | +| policy_gradient_loss | -0.0211 | +| value_loss | 8e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1410 | +| iterations | 13336 | +| time_elapsed | 19359 | +| total_timesteps | 27312128 | +| train/ | | +| approx_kl | 0.015008599 | +| clip_fraction | 0.357 | +| clip_range | 0.0682 | +| entropy_loss | -6.34 | +| explained_variance | 0.313 | +| learning_rate | 4.35e-05 | +| loss | -0.0273 | +| n_updates | 69160 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000135 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.14e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1410 | +| iterations | 13337 | +| time_elapsed | 19361 | +| total_timesteps | 27314176 | +| train/ | | +| approx_kl | 0.013256321 | +| clip_fraction | 0.355 | +| clip_range | 0.0682 | +| entropy_loss | -6.86 | +| explained_variance | -0.0156 | +| learning_rate | 4.35e-05 | +| loss | -0.0252 | +| n_updates | 69164 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000146 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.14e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1410 | +| iterations | 13338 | +| time_elapsed | 19362 | +| total_timesteps | 27316224 | +| train/ | | +| approx_kl | 0.011039095 | +| clip_fraction | 0.316 | +| clip_range | 0.0682 | +| entropy_loss | -6.52 | +| explained_variance | 0.333 | +| learning_rate | 4.35e-05 | +| loss | -0.0168 | +| n_updates | 69168 | +| policy_gradient_loss | -0.0138 | +| value_loss | 0.000293 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.14e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1410 | +| iterations | 13339 | +| time_elapsed | 19364 | +| total_timesteps | 27318272 | +| train/ | | +| approx_kl | 0.00946198 | +| clip_fraction | 0.287 | +| clip_range | 0.0682 | +| entropy_loss | -5.87 | +| explained_variance | 0.541 | +| learning_rate | 4.35e-05 | +| loss | -0.0257 | +| n_updates | 69172 | +| policy_gradient_loss | -0.0129 | +| value_loss | 0.000276 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1410 | +| iterations | 13340 | +| time_elapsed | 19365 | +| total_timesteps | 27320320 | +| train/ | | +| approx_kl | 0.015355505 | +| clip_fraction | 0.353 | +| clip_range | 0.0682 | +| entropy_loss | -5.63 | +| explained_variance | 0.595 | +| learning_rate | 4.35e-05 | +| loss | -0.0343 | +| n_updates | 69176 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000155 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1410 | +| iterations | 13341 | +| time_elapsed | 19367 | +| total_timesteps | 27322368 | +| train/ | | +| approx_kl | 0.013551017 | +| clip_fraction | 0.367 | +| clip_range | 0.0682 | +| entropy_loss | -6.19 | +| explained_variance | 0.557 | +| learning_rate | 4.35e-05 | +| loss | -0.0319 | +| n_updates | 69180 | +| policy_gradient_loss | -0.0209 | +| value_loss | 9.03e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1410 | +| iterations | 13342 | +| time_elapsed | 19368 | +| total_timesteps | 27324416 | +| train/ | | +| approx_kl | 0.016123721 | +| clip_fraction | 0.363 | +| clip_range | 0.0682 | +| entropy_loss | -6.25 | +| explained_variance | 0.565 | +| learning_rate | 4.35e-05 | +| loss | -0.0354 | +| n_updates | 69184 | +| policy_gradient_loss | -0.0214 | +| value_loss | 9.82e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1410 | +| iterations | 13343 | +| time_elapsed | 19370 | +| total_timesteps | 27326464 | +| train/ | | +| approx_kl | 0.0154689485 | +| clip_fraction | 0.333 | +| clip_range | 0.0682 | +| entropy_loss | -6.44 | +| explained_variance | 0.203 | +| learning_rate | 4.35e-05 | +| loss | -0.03 | +| n_updates | 69188 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000188 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.14e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1410 | +| iterations | 13344 | +| time_elapsed | 19371 | +| total_timesteps | 27328512 | +| train/ | | +| approx_kl | 0.015363823 | +| clip_fraction | 0.337 | +| clip_range | 0.0682 | +| entropy_loss | -6.36 | +| explained_variance | 0.26 | +| learning_rate | 4.35e-05 | +| loss | -0.0316 | +| n_updates | 69192 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000228 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.14e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1410 | +| iterations | 13345 | +| time_elapsed | 19373 | +| total_timesteps | 27330560 | +| train/ | | +| approx_kl | 0.013588933 | +| clip_fraction | 0.356 | +| clip_range | 0.0682 | +| entropy_loss | -5.97 | +| explained_variance | 0.468 | +| learning_rate | 4.35e-05 | +| loss | -0.0355 | +| n_updates | 69196 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000238 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.13e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1410 | +| iterations | 13346 | +| time_elapsed | 19375 | +| total_timesteps | 27332608 | +| train/ | | +| approx_kl | 0.012167098 | +| clip_fraction | 0.342 | +| clip_range | 0.0682 | +| entropy_loss | -6.64 | +| explained_variance | 0.222 | +| learning_rate | 4.35e-05 | +| loss | -0.0289 | +| n_updates | 69200 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000123 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.13e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1410 | +| iterations | 13347 | +| time_elapsed | 19376 | +| total_timesteps | 27334656 | +| train/ | | +| approx_kl | 0.014195144 | +| clip_fraction | 0.326 | +| clip_range | 0.0682 | +| entropy_loss | -6.18 | +| explained_variance | 0.648 | +| learning_rate | 4.35e-05 | +| loss | -0.0318 | +| n_updates | 69204 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000148 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.12e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1410 | +| iterations | 13348 | +| time_elapsed | 19378 | +| total_timesteps | 27336704 | +| train/ | | +| approx_kl | 0.013331895 | +| clip_fraction | 0.345 | +| clip_range | 0.0682 | +| entropy_loss | -6.54 | +| explained_variance | 0.114 | +| learning_rate | 4.35e-05 | +| loss | -0.0357 | +| n_updates | 69208 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000137 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.13e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1410 | +| iterations | 13349 | +| time_elapsed | 19379 | +| total_timesteps | 27338752 | +| train/ | | +| approx_kl | 0.010559363 | +| clip_fraction | 0.314 | +| clip_range | 0.0682 | +| entropy_loss | -6.4 | +| explained_variance | 0.291 | +| learning_rate | 4.35e-05 | +| loss | -0.0206 | +| n_updates | 69212 | +| policy_gradient_loss | -0.0148 | +| value_loss | 0.000334 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.13e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1410 | +| iterations | 13350 | +| time_elapsed | 19381 | +| total_timesteps | 27340800 | +| train/ | | +| approx_kl | 0.013249925 | +| clip_fraction | 0.365 | +| clip_range | 0.0682 | +| entropy_loss | -6.4 | +| explained_variance | 0.32 | +| learning_rate | 4.35e-05 | +| loss | -0.0339 | +| n_updates | 69216 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000105 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.12e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1410 | +| iterations | 13351 | +| time_elapsed | 19382 | +| total_timesteps | 27342848 | +| train/ | | +| approx_kl | 0.017511845 | +| clip_fraction | 0.348 | +| clip_range | 0.0682 | +| entropy_loss | -5.64 | +| explained_variance | 0.507 | +| learning_rate | 4.35e-05 | +| loss | -0.0299 | +| n_updates | 69220 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000197 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.13e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1410 | +| iterations | 13352 | +| time_elapsed | 19384 | +| total_timesteps | 27344896 | +| train/ | | +| approx_kl | 0.014737804 | +| clip_fraction | 0.293 | +| clip_range | 0.0682 | +| entropy_loss | -5.78 | +| explained_variance | 0.477 | +| learning_rate | 4.35e-05 | +| loss | -0.0265 | +| n_updates | 69224 | +| policy_gradient_loss | -0.0147 | +| value_loss | 0.00025 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.13e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1410 | +| iterations | 13353 | +| time_elapsed | 19385 | +| total_timesteps | 27346944 | +| train/ | | +| approx_kl | 0.010592304 | +| clip_fraction | 0.321 | +| clip_range | 0.0682 | +| entropy_loss | -6.38 | +| explained_variance | 0.378 | +| learning_rate | 4.35e-05 | +| loss | -0.0269 | +| n_updates | 69228 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000118 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.13e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1410 | +| iterations | 13354 | +| time_elapsed | 19387 | +| total_timesteps | 27348992 | +| train/ | | +| approx_kl | 0.007973963 | +| clip_fraction | 0.303 | +| clip_range | 0.0682 | +| entropy_loss | -6.34 | +| explained_variance | 0.397 | +| learning_rate | 4.35e-05 | +| loss | -0.0222 | +| n_updates | 69232 | +| policy_gradient_loss | -0.0138 | +| value_loss | 0.000281 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.13e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1410 | +| iterations | 13355 | +| time_elapsed | 19388 | +| total_timesteps | 27351040 | +| train/ | | +| approx_kl | 0.014539301 | +| clip_fraction | 0.336 | +| clip_range | 0.0682 | +| entropy_loss | -5.86 | +| explained_variance | 0.767 | +| learning_rate | 4.35e-05 | +| loss | -0.0367 | +| n_updates | 69236 | +| policy_gradient_loss | -0.0219 | +| value_loss | 6.33e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.12e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1410 | +| iterations | 13356 | +| time_elapsed | 19390 | +| total_timesteps | 27353088 | +| train/ | | +| approx_kl | 0.015717052 | +| clip_fraction | 0.326 | +| clip_range | 0.0682 | +| entropy_loss | -6.29 | +| explained_variance | 0.412 | +| learning_rate | 4.35e-05 | +| loss | -0.0328 | +| n_updates | 69240 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000101 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.12e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1410 | +| iterations | 13357 | +| time_elapsed | 19391 | +| total_timesteps | 27355136 | +| train/ | | +| approx_kl | 0.012482934 | +| clip_fraction | 0.339 | +| clip_range | 0.0682 | +| entropy_loss | -5.8 | +| explained_variance | 0.564 | +| learning_rate | 4.35e-05 | +| loss | -0.029 | +| n_updates | 69244 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000199 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.13e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1410 | +| iterations | 13358 | +| time_elapsed | 19393 | +| total_timesteps | 27357184 | +| train/ | | +| approx_kl | 0.015226606 | +| clip_fraction | 0.364 | +| clip_range | 0.0682 | +| entropy_loss | -5.99 | +| explained_variance | 0.431 | +| learning_rate | 4.35e-05 | +| loss | -0.0323 | +| n_updates | 69248 | +| policy_gradient_loss | -0.021 | +| value_loss | 7.83e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.13e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1410 | +| iterations | 13359 | +| time_elapsed | 19394 | +| total_timesteps | 27359232 | +| train/ | | +| approx_kl | 0.014921365 | +| clip_fraction | 0.339 | +| clip_range | 0.0682 | +| entropy_loss | -6.2 | +| explained_variance | 0.599 | +| learning_rate | 4.35e-05 | +| loss | -0.0293 | +| n_updates | 69252 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000121 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.13e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1410 | +| iterations | 13360 | +| time_elapsed | 19396 | +| total_timesteps | 27361280 | +| train/ | | +| approx_kl | 0.012063134 | +| clip_fraction | 0.315 | +| clip_range | 0.0682 | +| entropy_loss | -6.3 | +| explained_variance | 0.257 | +| learning_rate | 4.35e-05 | +| loss | -0.0261 | +| n_updates | 69256 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000198 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.14e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1410 | +| iterations | 13361 | +| time_elapsed | 19397 | +| total_timesteps | 27363328 | +| train/ | | +| approx_kl | 0.013099924 | +| clip_fraction | 0.368 | +| clip_range | 0.0682 | +| entropy_loss | -6.81 | +| explained_variance | -0.064 | +| learning_rate | 4.35e-05 | +| loss | -0.0339 | +| n_updates | 69260 | +| policy_gradient_loss | -0.0213 | +| value_loss | 8.55e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.14e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1410 | +| iterations | 13362 | +| time_elapsed | 19399 | +| total_timesteps | 27365376 | +| train/ | | +| approx_kl | 0.012530537 | +| clip_fraction | 0.342 | +| clip_range | 0.0682 | +| entropy_loss | -6.44 | +| explained_variance | 0.579 | +| learning_rate | 4.35e-05 | +| loss | -0.0277 | +| n_updates | 69264 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000103 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.13e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1410 | +| iterations | 13363 | +| time_elapsed | 19400 | +| total_timesteps | 27367424 | +| train/ | | +| approx_kl | 0.0125594335 | +| clip_fraction | 0.332 | +| clip_range | 0.0682 | +| entropy_loss | -6.43 | +| explained_variance | 0.175 | +| learning_rate | 4.35e-05 | +| loss | -0.0267 | +| n_updates | 69268 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000331 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.13e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1410 | +| iterations | 13364 | +| time_elapsed | 19402 | +| total_timesteps | 27369472 | +| train/ | | +| approx_kl | 0.015284217 | +| clip_fraction | 0.316 | +| clip_range | 0.0682 | +| entropy_loss | -5.5 | +| explained_variance | 0.599 | +| learning_rate | 4.35e-05 | +| loss | -0.0303 | +| n_updates | 69272 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000263 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.14e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1410 | +| iterations | 13365 | +| time_elapsed | 19403 | +| total_timesteps | 27371520 | +| train/ | | +| approx_kl | 0.016117437 | +| clip_fraction | 0.338 | +| clip_range | 0.0682 | +| entropy_loss | -5.78 | +| explained_variance | 0.529 | +| learning_rate | 4.35e-05 | +| loss | -0.033 | +| n_updates | 69276 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000174 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.14e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1410 | +| iterations | 13366 | +| time_elapsed | 19405 | +| total_timesteps | 27373568 | +| train/ | | +| approx_kl | 0.014215854 | +| clip_fraction | 0.318 | +| clip_range | 0.0682 | +| entropy_loss | -6.35 | +| explained_variance | 0.282 | +| learning_rate | 4.35e-05 | +| loss | -0.0285 | +| n_updates | 69280 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000134 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1410 | +| iterations | 13367 | +| time_elapsed | 19406 | +| total_timesteps | 27375616 | +| train/ | | +| approx_kl | 0.011822407 | +| clip_fraction | 0.333 | +| clip_range | 0.0682 | +| entropy_loss | -6.27 | +| explained_variance | 0.17 | +| learning_rate | 4.35e-05 | +| loss | -0.0225 | +| n_updates | 69284 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000206 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1410 | +| iterations | 13368 | +| time_elapsed | 19408 | +| total_timesteps | 27377664 | +| train/ | | +| approx_kl | 0.01549953 | +| clip_fraction | 0.323 | +| clip_range | 0.0682 | +| entropy_loss | -6.38 | +| explained_variance | 0.117 | +| learning_rate | 4.35e-05 | +| loss | -0.0287 | +| n_updates | 69288 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.00025 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1410 | +| iterations | 13369 | +| time_elapsed | 19409 | +| total_timesteps | 27379712 | +| train/ | | +| approx_kl | 0.016072875 | +| clip_fraction | 0.348 | +| clip_range | 0.0682 | +| entropy_loss | -6.25 | +| explained_variance | 0.429 | +| learning_rate | 4.35e-05 | +| loss | -0.0358 | +| n_updates | 69292 | +| policy_gradient_loss | -0.02 | +| value_loss | 9.89e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1410 | +| iterations | 13370 | +| time_elapsed | 19411 | +| total_timesteps | 27381760 | +| train/ | | +| approx_kl | 0.015608549 | +| clip_fraction | 0.323 | +| clip_range | 0.0682 | +| entropy_loss | -6.08 | +| explained_variance | 0.411 | +| learning_rate | 4.35e-05 | +| loss | -0.0254 | +| n_updates | 69296 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000288 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1410 | +| iterations | 13371 | +| time_elapsed | 19412 | +| total_timesteps | 27383808 | +| train/ | | +| approx_kl | 0.016133491 | +| clip_fraction | 0.334 | +| clip_range | 0.0682 | +| entropy_loss | -6.52 | +| explained_variance | 0.309 | +| learning_rate | 4.35e-05 | +| loss | -0.0369 | +| n_updates | 69300 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000137 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1410 | +| iterations | 13372 | +| time_elapsed | 19414 | +| total_timesteps | 27385856 | +| train/ | | +| approx_kl | 0.011882646 | +| clip_fraction | 0.338 | +| clip_range | 0.0682 | +| entropy_loss | -6.29 | +| explained_variance | 0.379 | +| learning_rate | 4.35e-05 | +| loss | -0.0282 | +| n_updates | 69304 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000285 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1410 | +| iterations | 13373 | +| time_elapsed | 19415 | +| total_timesteps | 27387904 | +| train/ | | +| approx_kl | 0.014010603 | +| clip_fraction | 0.34 | +| clip_range | 0.0682 | +| entropy_loss | -6.21 | +| explained_variance | 0.371 | +| learning_rate | 4.35e-05 | +| loss | -0.0299 | +| n_updates | 69308 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000132 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1410 | +| iterations | 13374 | +| time_elapsed | 19417 | +| total_timesteps | 27389952 | +| train/ | | +| approx_kl | 0.010363812 | +| clip_fraction | 0.324 | +| clip_range | 0.0682 | +| entropy_loss | -6.62 | +| explained_variance | 0.271 | +| learning_rate | 4.35e-05 | +| loss | -0.0248 | +| n_updates | 69312 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000271 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1410 | +| iterations | 13375 | +| time_elapsed | 19418 | +| total_timesteps | 27392000 | +| train/ | | +| approx_kl | 0.013025018 | +| clip_fraction | 0.349 | +| clip_range | 0.0682 | +| entropy_loss | -6.44 | +| explained_variance | 0.288 | +| learning_rate | 4.35e-05 | +| loss | -0.0275 | +| n_updates | 69316 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000118 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1410 | +| iterations | 13376 | +| time_elapsed | 19420 | +| total_timesteps | 27394048 | +| train/ | | +| approx_kl | 0.01272567 | +| clip_fraction | 0.332 | +| clip_range | 0.0682 | +| entropy_loss | -6.57 | +| explained_variance | 0.343 | +| learning_rate | 4.35e-05 | +| loss | -0.026 | +| n_updates | 69320 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000205 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1410 | +| iterations | 13377 | +| time_elapsed | 19421 | +| total_timesteps | 27396096 | +| train/ | | +| approx_kl | 0.012712676 | +| clip_fraction | 0.328 | +| clip_range | 0.0682 | +| entropy_loss | -6.66 | +| explained_variance | 0.321 | +| learning_rate | 4.35e-05 | +| loss | -0.0281 | +| n_updates | 69324 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000177 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1410 | +| iterations | 13378 | +| time_elapsed | 19423 | +| total_timesteps | 27398144 | +| train/ | | +| approx_kl | 0.012103917 | +| clip_fraction | 0.32 | +| clip_range | 0.0682 | +| entropy_loss | -6.07 | +| explained_variance | 0.732 | +| learning_rate | 4.35e-05 | +| loss | -0.0304 | +| n_updates | 69328 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.00011 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1410 | +| iterations | 13379 | +| time_elapsed | 19424 | +| total_timesteps | 27400192 | +| train/ | | +| approx_kl | 0.012063087 | +| clip_fraction | 0.318 | +| clip_range | 0.0682 | +| entropy_loss | -5.85 | +| explained_variance | 0.475 | +| learning_rate | 4.35e-05 | +| loss | -0.0242 | +| n_updates | 69332 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000221 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1410 | +| iterations | 13380 | +| time_elapsed | 19426 | +| total_timesteps | 27402240 | +| train/ | | +| approx_kl | 0.012182782 | +| clip_fraction | 0.33 | +| clip_range | 0.0681 | +| entropy_loss | -6.32 | +| explained_variance | 0.254 | +| learning_rate | 4.35e-05 | +| loss | -0.0253 | +| n_updates | 69336 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.0003 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1410 | +| iterations | 13381 | +| time_elapsed | 19427 | +| total_timesteps | 27404288 | +| train/ | | +| approx_kl | 0.01603602 | +| clip_fraction | 0.306 | +| clip_range | 0.0681 | +| entropy_loss | -6.41 | +| explained_variance | 0.38 | +| learning_rate | 4.35e-05 | +| loss | -0.0275 | +| n_updates | 69340 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000166 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1410 | +| iterations | 13382 | +| time_elapsed | 19429 | +| total_timesteps | 27406336 | +| train/ | | +| approx_kl | 0.014098134 | +| clip_fraction | 0.368 | +| clip_range | 0.0681 | +| entropy_loss | -6.84 | +| explained_variance | -0.162 | +| learning_rate | 4.35e-05 | +| loss | -0.0346 | +| n_updates | 69344 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000131 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1410 | +| iterations | 13383 | +| time_elapsed | 19430 | +| total_timesteps | 27408384 | +| train/ | | +| approx_kl | 0.01358016 | +| clip_fraction | 0.337 | +| clip_range | 0.0681 | +| entropy_loss | -6.51 | +| explained_variance | 0.222 | +| learning_rate | 4.35e-05 | +| loss | -0.0349 | +| n_updates | 69348 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000177 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1410 | +| iterations | 13384 | +| time_elapsed | 19432 | +| total_timesteps | 27410432 | +| train/ | | +| approx_kl | 0.013737878 | +| clip_fraction | 0.343 | +| clip_range | 0.0681 | +| entropy_loss | -6.47 | +| explained_variance | 0.334 | +| learning_rate | 4.35e-05 | +| loss | -0.0319 | +| n_updates | 69352 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000132 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1410 | +| iterations | 13385 | +| time_elapsed | 19433 | +| total_timesteps | 27412480 | +| train/ | | +| approx_kl | 0.012008015 | +| clip_fraction | 0.306 | +| clip_range | 0.0681 | +| entropy_loss | -5.81 | +| explained_variance | 0.539 | +| learning_rate | 4.35e-05 | +| loss | -0.0266 | +| n_updates | 69356 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000185 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1410 | +| iterations | 13386 | +| time_elapsed | 19435 | +| total_timesteps | 27414528 | +| train/ | | +| approx_kl | 0.014535966 | +| clip_fraction | 0.351 | +| clip_range | 0.0681 | +| entropy_loss | -5.2 | +| explained_variance | 0.679 | +| learning_rate | 4.35e-05 | +| loss | -0.031 | +| n_updates | 69360 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000117 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1410 | +| iterations | 13387 | +| time_elapsed | 19436 | +| total_timesteps | 27416576 | +| train/ | | +| approx_kl | 0.016176324 | +| clip_fraction | 0.385 | +| clip_range | 0.0681 | +| entropy_loss | -6.25 | +| explained_variance | 0.311 | +| learning_rate | 4.35e-05 | +| loss | -0.0343 | +| n_updates | 69364 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000111 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1410 | +| iterations | 13388 | +| time_elapsed | 19438 | +| total_timesteps | 27418624 | +| train/ | | +| approx_kl | 0.013413778 | +| clip_fraction | 0.348 | +| clip_range | 0.0681 | +| entropy_loss | -6.23 | +| explained_variance | 0.467 | +| learning_rate | 4.35e-05 | +| loss | -0.0323 | +| n_updates | 69368 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000133 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1410 | +| iterations | 13389 | +| time_elapsed | 19439 | +| total_timesteps | 27420672 | +| train/ | | +| approx_kl | 0.014733554 | +| clip_fraction | 0.336 | +| clip_range | 0.0681 | +| entropy_loss | -6.27 | +| explained_variance | 0.477 | +| learning_rate | 4.35e-05 | +| loss | -0.0291 | +| n_updates | 69372 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000173 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1410 | +| iterations | 13390 | +| time_elapsed | 19441 | +| total_timesteps | 27422720 | +| train/ | | +| approx_kl | 0.010558435 | +| clip_fraction | 0.336 | +| clip_range | 0.0681 | +| entropy_loss | -6.43 | +| explained_variance | 0.147 | +| learning_rate | 4.35e-05 | +| loss | -0.0289 | +| n_updates | 69376 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000372 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1410 | +| iterations | 13391 | +| time_elapsed | 19442 | +| total_timesteps | 27424768 | +| train/ | | +| approx_kl | 0.01284566 | +| clip_fraction | 0.352 | +| clip_range | 0.0681 | +| entropy_loss | -6.58 | +| explained_variance | 0.037 | +| learning_rate | 4.35e-05 | +| loss | -0.0336 | +| n_updates | 69380 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.00014 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1410 | +| iterations | 13392 | +| time_elapsed | 19444 | +| total_timesteps | 27426816 | +| train/ | | +| approx_kl | 0.014451618 | +| clip_fraction | 0.365 | +| clip_range | 0.0681 | +| entropy_loss | -6.46 | +| explained_variance | 0.352 | +| learning_rate | 4.35e-05 | +| loss | -0.0366 | +| n_updates | 69384 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.00013 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1410 | +| iterations | 13393 | +| time_elapsed | 19445 | +| total_timesteps | 27428864 | +| train/ | | +| approx_kl | 0.0144000575 | +| clip_fraction | 0.376 | +| clip_range | 0.0681 | +| entropy_loss | -6.4 | +| explained_variance | 0.617 | +| learning_rate | 4.35e-05 | +| loss | -0.0316 | +| n_updates | 69388 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000102 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1410 | +| iterations | 13394 | +| time_elapsed | 19447 | +| total_timesteps | 27430912 | +| train/ | | +| approx_kl | 0.01089061 | +| clip_fraction | 0.319 | +| clip_range | 0.0681 | +| entropy_loss | -5.29 | +| explained_variance | 0.488 | +| learning_rate | 4.35e-05 | +| loss | -0.0229 | +| n_updates | 69392 | +| policy_gradient_loss | -0.0136 | +| value_loss | 0.000318 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1410 | +| iterations | 13395 | +| time_elapsed | 19448 | +| total_timesteps | 27432960 | +| train/ | | +| approx_kl | 0.012984119 | +| clip_fraction | 0.345 | +| clip_range | 0.0681 | +| entropy_loss | -5.92 | +| explained_variance | 0.48 | +| learning_rate | 4.35e-05 | +| loss | -0.0297 | +| n_updates | 69396 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.00017 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1410 | +| iterations | 13396 | +| time_elapsed | 19450 | +| total_timesteps | 27435008 | +| train/ | | +| approx_kl | 0.016005997 | +| clip_fraction | 0.363 | +| clip_range | 0.0681 | +| entropy_loss | -6.02 | +| explained_variance | 0.587 | +| learning_rate | 4.35e-05 | +| loss | -0.03 | +| n_updates | 69400 | +| policy_gradient_loss | -0.0201 | +| value_loss | 8.84e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1410 | +| iterations | 13397 | +| time_elapsed | 19451 | +| total_timesteps | 27437056 | +| train/ | | +| approx_kl | 0.014063729 | +| clip_fraction | 0.353 | +| clip_range | 0.0681 | +| entropy_loss | -6.44 | +| explained_variance | 0.395 | +| learning_rate | 4.35e-05 | +| loss | -0.0264 | +| n_updates | 69404 | +| policy_gradient_loss | -0.0181 | +| value_loss | 9.72e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1410 | +| iterations | 13398 | +| time_elapsed | 19453 | +| total_timesteps | 27439104 | +| train/ | | +| approx_kl | 0.015406995 | +| clip_fraction | 0.357 | +| clip_range | 0.0681 | +| entropy_loss | -6.62 | +| explained_variance | 0.184 | +| learning_rate | 4.35e-05 | +| loss | -0.0259 | +| n_updates | 69408 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.00027 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1410 | +| iterations | 13399 | +| time_elapsed | 19454 | +| total_timesteps | 27441152 | +| train/ | | +| approx_kl | 0.01120656 | +| clip_fraction | 0.314 | +| clip_range | 0.0681 | +| entropy_loss | -6.35 | +| explained_variance | 0.144 | +| learning_rate | 4.35e-05 | +| loss | -0.0237 | +| n_updates | 69412 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000309 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1410 | +| iterations | 13400 | +| time_elapsed | 19456 | +| total_timesteps | 27443200 | +| train/ | | +| approx_kl | 0.012918131 | +| clip_fraction | 0.347 | +| clip_range | 0.0681 | +| entropy_loss | -6.31 | +| explained_variance | 0.286 | +| learning_rate | 4.35e-05 | +| loss | -0.0275 | +| n_updates | 69416 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000275 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1410 | +| iterations | 13401 | +| time_elapsed | 19457 | +| total_timesteps | 27445248 | +| train/ | | +| approx_kl | 0.011969026 | +| clip_fraction | 0.329 | +| clip_range | 0.0681 | +| entropy_loss | -5.95 | +| explained_variance | 0.486 | +| learning_rate | 4.35e-05 | +| loss | -0.0251 | +| n_updates | 69420 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000257 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1410 | +| iterations | 13402 | +| time_elapsed | 19459 | +| total_timesteps | 27447296 | +| train/ | | +| approx_kl | 0.012535719 | +| clip_fraction | 0.363 | +| clip_range | 0.0681 | +| entropy_loss | -5.69 | +| explained_variance | 0.542 | +| learning_rate | 4.35e-05 | +| loss | -0.0348 | +| n_updates | 69424 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000111 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1410 | +| iterations | 13403 | +| time_elapsed | 19460 | +| total_timesteps | 27449344 | +| train/ | | +| approx_kl | 0.013867182 | +| clip_fraction | 0.325 | +| clip_range | 0.0681 | +| entropy_loss | -6.28 | +| explained_variance | 0.269 | +| learning_rate | 4.35e-05 | +| loss | -0.0291 | +| n_updates | 69428 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000291 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1410 | +| iterations | 13404 | +| time_elapsed | 19462 | +| total_timesteps | 27451392 | +| train/ | | +| approx_kl | 0.013487257 | +| clip_fraction | 0.32 | +| clip_range | 0.0681 | +| entropy_loss | -5.77 | +| explained_variance | 0.626 | +| learning_rate | 4.35e-05 | +| loss | -0.0299 | +| n_updates | 69432 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000171 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1410 | +| iterations | 13405 | +| time_elapsed | 19464 | +| total_timesteps | 27453440 | +| train/ | | +| approx_kl | 0.012717415 | +| clip_fraction | 0.334 | +| clip_range | 0.0681 | +| entropy_loss | -6.61 | +| explained_variance | 0.049 | +| learning_rate | 4.35e-05 | +| loss | -0.03 | +| n_updates | 69436 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000153 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1410 | +| iterations | 13406 | +| time_elapsed | 19465 | +| total_timesteps | 27455488 | +| train/ | | +| approx_kl | 0.014525552 | +| clip_fraction | 0.37 | +| clip_range | 0.0681 | +| entropy_loss | -6.84 | +| explained_variance | -0.31 | +| learning_rate | 4.35e-05 | +| loss | -0.0305 | +| n_updates | 69440 | +| policy_gradient_loss | -0.021 | +| value_loss | 9.49e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1410 | +| iterations | 13407 | +| time_elapsed | 19467 | +| total_timesteps | 27457536 | +| train/ | | +| approx_kl | 0.011240751 | +| clip_fraction | 0.354 | +| clip_range | 0.0681 | +| entropy_loss | -6.59 | +| explained_variance | 0.522 | +| learning_rate | 4.35e-05 | +| loss | -0.0297 | +| n_updates | 69444 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000103 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1410 | +| iterations | 13408 | +| time_elapsed | 19468 | +| total_timesteps | 27459584 | +| train/ | | +| approx_kl | 0.015102885 | +| clip_fraction | 0.342 | +| clip_range | 0.0681 | +| entropy_loss | -6.4 | +| explained_variance | 0.206 | +| learning_rate | 4.35e-05 | +| loss | -0.031 | +| n_updates | 69448 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000106 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1410 | +| iterations | 13409 | +| time_elapsed | 19470 | +| total_timesteps | 27461632 | +| train/ | | +| approx_kl | 0.017429449 | +| clip_fraction | 0.308 | +| clip_range | 0.0681 | +| entropy_loss | -6.42 | +| explained_variance | 0.426 | +| learning_rate | 4.35e-05 | +| loss | -0.0268 | +| n_updates | 69452 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000169 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1410 | +| iterations | 13410 | +| time_elapsed | 19471 | +| total_timesteps | 27463680 | +| train/ | | +| approx_kl | 0.013288307 | +| clip_fraction | 0.337 | +| clip_range | 0.0681 | +| entropy_loss | -6.57 | +| explained_variance | 0.357 | +| learning_rate | 4.35e-05 | +| loss | -0.0282 | +| n_updates | 69456 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000207 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1410 | +| iterations | 13411 | +| time_elapsed | 19473 | +| total_timesteps | 27465728 | +| train/ | | +| approx_kl | 0.013718428 | +| clip_fraction | 0.337 | +| clip_range | 0.0681 | +| entropy_loss | -6.09 | +| explained_variance | 0.446 | +| learning_rate | 4.35e-05 | +| loss | -0.0306 | +| n_updates | 69460 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.00023 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1410 | +| iterations | 13412 | +| time_elapsed | 19474 | +| total_timesteps | 27467776 | +| train/ | | +| approx_kl | 0.013259308 | +| clip_fraction | 0.363 | +| clip_range | 0.0681 | +| entropy_loss | -6.37 | +| explained_variance | 0.409 | +| learning_rate | 4.35e-05 | +| loss | -0.0334 | +| n_updates | 69464 | +| policy_gradient_loss | -0.022 | +| value_loss | 7.75e-05 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1410 | +| iterations | 13413 | +| time_elapsed | 19476 | +| total_timesteps | 27469824 | +| train/ | | +| approx_kl | 0.0109808 | +| clip_fraction | 0.303 | +| clip_range | 0.0681 | +| entropy_loss | -5.35 | +| explained_variance | 0.562 | +| learning_rate | 4.35e-05 | +| loss | -0.0252 | +| n_updates | 69468 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000289 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1410 | +| iterations | 13414 | +| time_elapsed | 19477 | +| total_timesteps | 27471872 | +| train/ | | +| approx_kl | 0.011831266 | +| clip_fraction | 0.358 | +| clip_range | 0.0681 | +| entropy_loss | -6.31 | +| explained_variance | 0.0918 | +| learning_rate | 4.35e-05 | +| loss | -0.0279 | +| n_updates | 69472 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000124 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1410 | +| iterations | 13415 | +| time_elapsed | 19479 | +| total_timesteps | 27473920 | +| train/ | | +| approx_kl | 0.010633196 | +| clip_fraction | 0.331 | +| clip_range | 0.0681 | +| entropy_loss | -6.52 | +| explained_variance | 0.549 | +| learning_rate | 4.35e-05 | +| loss | -0.0292 | +| n_updates | 69476 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000171 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1410 | +| iterations | 13416 | +| time_elapsed | 19480 | +| total_timesteps | 27475968 | +| train/ | | +| approx_kl | 0.011222302 | +| clip_fraction | 0.32 | +| clip_range | 0.0681 | +| entropy_loss | -6.53 | +| explained_variance | -0.0673 | +| learning_rate | 4.35e-05 | +| loss | -0.0322 | +| n_updates | 69480 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000104 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1410 | +| iterations | 13417 | +| time_elapsed | 19482 | +| total_timesteps | 27478016 | +| train/ | | +| approx_kl | 0.009395809 | +| clip_fraction | 0.331 | +| clip_range | 0.0681 | +| entropy_loss | -6.68 | +| explained_variance | 0.353 | +| learning_rate | 4.35e-05 | +| loss | -0.0264 | +| n_updates | 69484 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000117 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1410 | +| iterations | 13418 | +| time_elapsed | 19483 | +| total_timesteps | 27480064 | +| train/ | | +| approx_kl | 0.009615889 | +| clip_fraction | 0.296 | +| clip_range | 0.0681 | +| entropy_loss | -5.91 | +| explained_variance | 0.458 | +| learning_rate | 4.35e-05 | +| loss | -0.021 | +| n_updates | 69488 | +| policy_gradient_loss | -0.0125 | +| value_loss | 0.000281 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1410 | +| iterations | 13419 | +| time_elapsed | 19485 | +| total_timesteps | 27482112 | +| train/ | | +| approx_kl | 0.013115222 | +| clip_fraction | 0.351 | +| clip_range | 0.0681 | +| entropy_loss | -6.34 | +| explained_variance | 0.299 | +| learning_rate | 4.35e-05 | +| loss | -0.0307 | +| n_updates | 69492 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000121 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1410 | +| iterations | 13420 | +| time_elapsed | 19486 | +| total_timesteps | 27484160 | +| train/ | | +| approx_kl | 0.0135034565 | +| clip_fraction | 0.33 | +| clip_range | 0.0681 | +| entropy_loss | -6.48 | +| explained_variance | 0.22 | +| learning_rate | 4.35e-05 | +| loss | -0.0249 | +| n_updates | 69496 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.00021 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1410 | +| iterations | 13421 | +| time_elapsed | 19488 | +| total_timesteps | 27486208 | +| train/ | | +| approx_kl | 0.014908491 | +| clip_fraction | 0.312 | +| clip_range | 0.0681 | +| entropy_loss | -6.52 | +| explained_variance | 0.291 | +| learning_rate | 4.35e-05 | +| loss | -0.0325 | +| n_updates | 69500 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000157 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1410 | +| iterations | 13422 | +| time_elapsed | 19490 | +| total_timesteps | 27488256 | +| train/ | | +| approx_kl | 0.012519876 | +| clip_fraction | 0.334 | +| clip_range | 0.0681 | +| entropy_loss | -5.86 | +| explained_variance | 0.502 | +| learning_rate | 4.35e-05 | +| loss | -0.0303 | +| n_updates | 69504 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000165 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1410 | +| iterations | 13423 | +| time_elapsed | 19491 | +| total_timesteps | 27490304 | +| train/ | | +| approx_kl | 0.014495072 | +| clip_fraction | 0.325 | +| clip_range | 0.0681 | +| entropy_loss | -5.93 | +| explained_variance | 0.335 | +| learning_rate | 4.35e-05 | +| loss | -0.0256 | +| n_updates | 69508 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000298 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1410 | +| iterations | 13424 | +| time_elapsed | 19493 | +| total_timesteps | 27492352 | +| train/ | | +| approx_kl | 0.01738122 | +| clip_fraction | 0.334 | +| clip_range | 0.0681 | +| entropy_loss | -6.32 | +| explained_variance | 0.245 | +| learning_rate | 4.35e-05 | +| loss | -0.0299 | +| n_updates | 69512 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000142 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1410 | +| iterations | 13425 | +| time_elapsed | 19494 | +| total_timesteps | 27494400 | +| train/ | | +| approx_kl | 0.016975503 | +| clip_fraction | 0.344 | +| clip_range | 0.0681 | +| entropy_loss | -6.32 | +| explained_variance | 0.453 | +| learning_rate | 4.35e-05 | +| loss | -0.0313 | +| n_updates | 69516 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000148 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1410 | +| iterations | 13426 | +| time_elapsed | 19496 | +| total_timesteps | 27496448 | +| train/ | | +| approx_kl | 0.015839247 | +| clip_fraction | 0.393 | +| clip_range | 0.0681 | +| entropy_loss | -5.86 | +| explained_variance | 0.663 | +| learning_rate | 4.35e-05 | +| loss | -0.0392 | +| n_updates | 69520 | +| policy_gradient_loss | -0.0217 | +| value_loss | 7.35e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1410 | +| iterations | 13427 | +| time_elapsed | 19497 | +| total_timesteps | 27498496 | +| train/ | | +| approx_kl | 0.016005311 | +| clip_fraction | 0.364 | +| clip_range | 0.0681 | +| entropy_loss | -5.95 | +| explained_variance | 0.581 | +| learning_rate | 4.35e-05 | +| loss | -0.0285 | +| n_updates | 69524 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000105 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1410 | +| iterations | 13428 | +| time_elapsed | 19499 | +| total_timesteps | 27500544 | +| train/ | | +| approx_kl | 0.012267385 | +| clip_fraction | 0.36 | +| clip_range | 0.0681 | +| entropy_loss | -6.56 | +| explained_variance | 0.0264 | +| learning_rate | 4.35e-05 | +| loss | -0.029 | +| n_updates | 69528 | +| policy_gradient_loss | -0.0192 | +| value_loss | 7.3e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1410 | +| iterations | 13429 | +| time_elapsed | 19500 | +| total_timesteps | 27502592 | +| train/ | | +| approx_kl | 0.010947501 | +| clip_fraction | 0.318 | +| clip_range | 0.0681 | +| entropy_loss | -6.4 | +| explained_variance | 0.529 | +| learning_rate | 4.35e-05 | +| loss | -0.0273 | +| n_updates | 69532 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000155 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1410 | +| iterations | 13430 | +| time_elapsed | 19502 | +| total_timesteps | 27504640 | +| train/ | | +| approx_kl | 0.012033532 | +| clip_fraction | 0.304 | +| clip_range | 0.0681 | +| entropy_loss | -5.87 | +| explained_variance | 0.453 | +| learning_rate | 4.35e-05 | +| loss | -0.0188 | +| n_updates | 69536 | +| policy_gradient_loss | -0.0141 | +| value_loss | 0.000236 | +----------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1410 | +| iterations | 13431 | +| time_elapsed | 19503 | +| total_timesteps | 27506688 | +| train/ | | +| approx_kl | 0.01146 | +| clip_fraction | 0.333 | +| clip_range | 0.0681 | +| entropy_loss | -6.32 | +| explained_variance | 0.26 | +| learning_rate | 4.35e-05 | +| loss | -0.0276 | +| n_updates | 69540 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.00014 | +-------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1410 | +| iterations | 13432 | +| time_elapsed | 19505 | +| total_timesteps | 27508736 | +| train/ | | +| approx_kl | 0.013944183 | +| clip_fraction | 0.338 | +| clip_range | 0.0681 | +| entropy_loss | -6.51 | +| explained_variance | 0.305 | +| learning_rate | 4.35e-05 | +| loss | -0.0317 | +| n_updates | 69544 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000172 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1410 | +| iterations | 13433 | +| time_elapsed | 19506 | +| total_timesteps | 27510784 | +| train/ | | +| approx_kl | 0.011507961 | +| clip_fraction | 0.317 | +| clip_range | 0.0681 | +| entropy_loss | -6.18 | +| explained_variance | 0.415 | +| learning_rate | 4.35e-05 | +| loss | -0.0266 | +| n_updates | 69548 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000299 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1410 | +| iterations | 13434 | +| time_elapsed | 19508 | +| total_timesteps | 27512832 | +| train/ | | +| approx_kl | 0.012005949 | +| clip_fraction | 0.344 | +| clip_range | 0.0681 | +| entropy_loss | -6.51 | +| explained_variance | -0.13 | +| learning_rate | 4.35e-05 | +| loss | -0.0325 | +| n_updates | 69552 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000136 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1410 | +| iterations | 13435 | +| time_elapsed | 19509 | +| total_timesteps | 27514880 | +| train/ | | +| approx_kl | 0.015366452 | +| clip_fraction | 0.376 | +| clip_range | 0.0681 | +| entropy_loss | -6.09 | +| explained_variance | 0.815 | +| learning_rate | 4.35e-05 | +| loss | -0.0347 | +| n_updates | 69556 | +| policy_gradient_loss | -0.023 | +| value_loss | 4.19e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1410 | +| iterations | 13436 | +| time_elapsed | 19511 | +| total_timesteps | 27516928 | +| train/ | | +| approx_kl | 0.019938717 | +| clip_fraction | 0.333 | +| clip_range | 0.0681 | +| entropy_loss | -5.54 | +| explained_variance | 0.506 | +| learning_rate | 4.35e-05 | +| loss | -0.0184 | +| n_updates | 69560 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000236 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1410 | +| iterations | 13437 | +| time_elapsed | 19512 | +| total_timesteps | 27518976 | +| train/ | | +| approx_kl | 0.015818814 | +| clip_fraction | 0.362 | +| clip_range | 0.0681 | +| entropy_loss | -5.62 | +| explained_variance | 0.624 | +| learning_rate | 4.35e-05 | +| loss | -0.0305 | +| n_updates | 69564 | +| policy_gradient_loss | -0.0199 | +| value_loss | 9.09e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1410 | +| iterations | 13438 | +| time_elapsed | 19514 | +| total_timesteps | 27521024 | +| train/ | | +| approx_kl | 0.01307101 | +| clip_fraction | 0.337 | +| clip_range | 0.0681 | +| entropy_loss | -6.84 | +| explained_variance | -0.077 | +| learning_rate | 4.35e-05 | +| loss | -0.0296 | +| n_updates | 69568 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000116 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1410 | +| iterations | 13439 | +| time_elapsed | 19516 | +| total_timesteps | 27523072 | +| train/ | | +| approx_kl | 0.014416188 | +| clip_fraction | 0.362 | +| clip_range | 0.0681 | +| entropy_loss | -6.09 | +| explained_variance | 0.394 | +| learning_rate | 4.35e-05 | +| loss | -0.0279 | +| n_updates | 69572 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000157 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1410 | +| iterations | 13440 | +| time_elapsed | 19517 | +| total_timesteps | 27525120 | +| train/ | | +| approx_kl | 0.015068314 | +| clip_fraction | 0.358 | +| clip_range | 0.0681 | +| entropy_loss | -6.36 | +| explained_variance | -0.0807 | +| learning_rate | 4.35e-05 | +| loss | -0.0321 | +| n_updates | 69576 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000154 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1410 | +| iterations | 13441 | +| time_elapsed | 19519 | +| total_timesteps | 27527168 | +| train/ | | +| approx_kl | 0.015749395 | +| clip_fraction | 0.329 | +| clip_range | 0.0681 | +| entropy_loss | -6.51 | +| explained_variance | 0.467 | +| learning_rate | 4.35e-05 | +| loss | -0.0319 | +| n_updates | 69580 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000178 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1410 | +| iterations | 13442 | +| time_elapsed | 19520 | +| total_timesteps | 27529216 | +| train/ | | +| approx_kl | 0.013664987 | +| clip_fraction | 0.326 | +| clip_range | 0.0681 | +| entropy_loss | -6.2 | +| explained_variance | 0.328 | +| learning_rate | 4.35e-05 | +| loss | -0.029 | +| n_updates | 69584 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000257 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1410 | +| iterations | 13443 | +| time_elapsed | 19522 | +| total_timesteps | 27531264 | +| train/ | | +| approx_kl | 0.011010371 | +| clip_fraction | 0.342 | +| clip_range | 0.0681 | +| entropy_loss | -6.63 | +| explained_variance | 0.0513 | +| learning_rate | 4.35e-05 | +| loss | -0.0311 | +| n_updates | 69588 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000153 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1410 | +| iterations | 13444 | +| time_elapsed | 19523 | +| total_timesteps | 27533312 | +| train/ | | +| approx_kl | 0.01185062 | +| clip_fraction | 0.328 | +| clip_range | 0.0681 | +| entropy_loss | -6.62 | +| explained_variance | 0.263 | +| learning_rate | 4.35e-05 | +| loss | -0.03 | +| n_updates | 69592 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000199 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1410 | +| iterations | 13445 | +| time_elapsed | 19525 | +| total_timesteps | 27535360 | +| train/ | | +| approx_kl | 0.009763887 | +| clip_fraction | 0.302 | +| clip_range | 0.0681 | +| entropy_loss | -6.63 | +| explained_variance | 0.0679 | +| learning_rate | 4.35e-05 | +| loss | -0.017 | +| n_updates | 69596 | +| policy_gradient_loss | -0.0145 | +| value_loss | 0.000392 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1410 | +| iterations | 13446 | +| time_elapsed | 19526 | +| total_timesteps | 27537408 | +| train/ | | +| approx_kl | 0.012966781 | +| clip_fraction | 0.321 | +| clip_range | 0.0681 | +| entropy_loss | -5.22 | +| explained_variance | 0.548 | +| learning_rate | 4.35e-05 | +| loss | -0.0216 | +| n_updates | 69600 | +| policy_gradient_loss | -0.0143 | +| value_loss | 0.000346 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1410 | +| iterations | 13447 | +| time_elapsed | 19528 | +| total_timesteps | 27539456 | +| train/ | | +| approx_kl | 0.015017847 | +| clip_fraction | 0.377 | +| clip_range | 0.0681 | +| entropy_loss | -5.87 | +| explained_variance | -0.313 | +| learning_rate | 4.35e-05 | +| loss | -0.0397 | +| n_updates | 69604 | +| policy_gradient_loss | -0.0234 | +| value_loss | 9.74e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1410 | +| iterations | 13448 | +| time_elapsed | 19529 | +| total_timesteps | 27541504 | +| train/ | | +| approx_kl | 0.013113756 | +| clip_fraction | 0.359 | +| clip_range | 0.0681 | +| entropy_loss | -5.94 | +| explained_variance | 0.417 | +| learning_rate | 4.35e-05 | +| loss | -0.0352 | +| n_updates | 69608 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000257 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1410 | +| iterations | 13449 | +| time_elapsed | 19531 | +| total_timesteps | 27543552 | +| train/ | | +| approx_kl | 0.013882015 | +| clip_fraction | 0.357 | +| clip_range | 0.0681 | +| entropy_loss | -6.39 | +| explained_variance | 0.332 | +| learning_rate | 4.35e-05 | +| loss | -0.0367 | +| n_updates | 69612 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000192 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1410 | +| iterations | 13450 | +| time_elapsed | 19532 | +| total_timesteps | 27545600 | +| train/ | | +| approx_kl | 0.014541475 | +| clip_fraction | 0.364 | +| clip_range | 0.0681 | +| entropy_loss | -6.53 | +| explained_variance | 0.315 | +| learning_rate | 4.35e-05 | +| loss | -0.0319 | +| n_updates | 69616 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000131 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1410 | +| iterations | 13451 | +| time_elapsed | 19534 | +| total_timesteps | 27547648 | +| train/ | | +| approx_kl | 0.012427179 | +| clip_fraction | 0.341 | +| clip_range | 0.0681 | +| entropy_loss | -6.55 | +| explained_variance | 0.22 | +| learning_rate | 4.35e-05 | +| loss | -0.0253 | +| n_updates | 69620 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000274 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1410 | +| iterations | 13452 | +| time_elapsed | 19535 | +| total_timesteps | 27549696 | +| train/ | | +| approx_kl | 0.014270574 | +| clip_fraction | 0.337 | +| clip_range | 0.0681 | +| entropy_loss | -6.08 | +| explained_variance | 0.468 | +| learning_rate | 4.35e-05 | +| loss | -0.0225 | +| n_updates | 69624 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000152 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1410 | +| iterations | 13453 | +| time_elapsed | 19537 | +| total_timesteps | 27551744 | +| train/ | | +| approx_kl | 0.015443116 | +| clip_fraction | 0.349 | +| clip_range | 0.0681 | +| entropy_loss | -6.5 | +| explained_variance | -0.0459 | +| learning_rate | 4.35e-05 | +| loss | -0.0338 | +| n_updates | 69628 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000126 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1410 | +| iterations | 13454 | +| time_elapsed | 19539 | +| total_timesteps | 27553792 | +| train/ | | +| approx_kl | 0.013685022 | +| clip_fraction | 0.372 | +| clip_range | 0.0681 | +| entropy_loss | -6.29 | +| explained_variance | 0.463 | +| learning_rate | 4.35e-05 | +| loss | -0.0308 | +| n_updates | 69632 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000118 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1410 | +| iterations | 13455 | +| time_elapsed | 19540 | +| total_timesteps | 27555840 | +| train/ | | +| approx_kl | 0.0146168545 | +| clip_fraction | 0.347 | +| clip_range | 0.0681 | +| entropy_loss | -5.84 | +| explained_variance | 0.643 | +| learning_rate | 4.35e-05 | +| loss | -0.0309 | +| n_updates | 69636 | +| policy_gradient_loss | -0.0183 | +| value_loss | 8.78e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1410 | +| iterations | 13456 | +| time_elapsed | 19542 | +| total_timesteps | 27557888 | +| train/ | | +| approx_kl | 0.014069291 | +| clip_fraction | 0.345 | +| clip_range | 0.0681 | +| entropy_loss | -5.91 | +| explained_variance | 0.562 | +| learning_rate | 4.35e-05 | +| loss | -0.0284 | +| n_updates | 69640 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000117 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1410 | +| iterations | 13457 | +| time_elapsed | 19543 | +| total_timesteps | 27559936 | +| train/ | | +| approx_kl | 0.013453553 | +| clip_fraction | 0.34 | +| clip_range | 0.0681 | +| entropy_loss | -5.76 | +| explained_variance | 0.791 | +| learning_rate | 4.35e-05 | +| loss | -0.0299 | +| n_updates | 69644 | +| policy_gradient_loss | -0.0191 | +| value_loss | 6.49e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1410 | +| iterations | 13458 | +| time_elapsed | 19545 | +| total_timesteps | 27561984 | +| train/ | | +| approx_kl | 0.010927279 | +| clip_fraction | 0.333 | +| clip_range | 0.0681 | +| entropy_loss | -6.18 | +| explained_variance | 0.437 | +| learning_rate | 4.35e-05 | +| loss | -0.0242 | +| n_updates | 69648 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000142 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1410 | +| iterations | 13459 | +| time_elapsed | 19546 | +| total_timesteps | 27564032 | +| train/ | | +| approx_kl | 0.013787273 | +| clip_fraction | 0.339 | +| clip_range | 0.0681 | +| entropy_loss | -6.35 | +| explained_variance | 0.491 | +| learning_rate | 4.35e-05 | +| loss | -0.0293 | +| n_updates | 69652 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000167 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1410 | +| iterations | 13460 | +| time_elapsed | 19548 | +| total_timesteps | 27566080 | +| train/ | | +| approx_kl | 0.013097178 | +| clip_fraction | 0.326 | +| clip_range | 0.0681 | +| entropy_loss | -6.49 | +| explained_variance | 0.315 | +| learning_rate | 4.35e-05 | +| loss | -0.0262 | +| n_updates | 69656 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.00017 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1410 | +| iterations | 13461 | +| time_elapsed | 19549 | +| total_timesteps | 27568128 | +| train/ | | +| approx_kl | 0.013372394 | +| clip_fraction | 0.343 | +| clip_range | 0.0681 | +| entropy_loss | -6.45 | +| explained_variance | 0.329 | +| learning_rate | 4.35e-05 | +| loss | -0.0334 | +| n_updates | 69660 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000137 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1410 | +| iterations | 13462 | +| time_elapsed | 19551 | +| total_timesteps | 27570176 | +| train/ | | +| approx_kl | 0.014493194 | +| clip_fraction | 0.325 | +| clip_range | 0.0681 | +| entropy_loss | -6.53 | +| explained_variance | 0.094 | +| learning_rate | 4.35e-05 | +| loss | -0.0236 | +| n_updates | 69664 | +| policy_gradient_loss | -0.0144 | +| value_loss | 0.000414 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1410 | +| iterations | 13463 | +| time_elapsed | 19552 | +| total_timesteps | 27572224 | +| train/ | | +| approx_kl | 0.016914865 | +| clip_fraction | 0.343 | +| clip_range | 0.0681 | +| entropy_loss | -6.02 | +| explained_variance | 0.479 | +| learning_rate | 4.35e-05 | +| loss | -0.0306 | +| n_updates | 69668 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000237 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1410 | +| iterations | 13464 | +| time_elapsed | 19554 | +| total_timesteps | 27574272 | +| train/ | | +| approx_kl | 0.013423881 | +| clip_fraction | 0.317 | +| clip_range | 0.0681 | +| entropy_loss | -5.58 | +| explained_variance | 0.462 | +| learning_rate | 4.35e-05 | +| loss | -0.025 | +| n_updates | 69672 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000231 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1410 | +| iterations | 13465 | +| time_elapsed | 19555 | +| total_timesteps | 27576320 | +| train/ | | +| approx_kl | 0.012600404 | +| clip_fraction | 0.337 | +| clip_range | 0.0681 | +| entropy_loss | -5.87 | +| explained_variance | 0.514 | +| learning_rate | 4.35e-05 | +| loss | -0.0296 | +| n_updates | 69676 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000161 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1410 | +| iterations | 13466 | +| time_elapsed | 19557 | +| total_timesteps | 27578368 | +| train/ | | +| approx_kl | 0.01082385 | +| clip_fraction | 0.345 | +| clip_range | 0.0681 | +| entropy_loss | -6.47 | +| explained_variance | 0.26 | +| learning_rate | 4.35e-05 | +| loss | -0.0223 | +| n_updates | 69680 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000233 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1410 | +| iterations | 13467 | +| time_elapsed | 19558 | +| total_timesteps | 27580416 | +| train/ | | +| approx_kl | 0.01295929 | +| clip_fraction | 0.349 | +| clip_range | 0.0681 | +| entropy_loss | -5.9 | +| explained_variance | 0.565 | +| learning_rate | 4.35e-05 | +| loss | -0.0281 | +| n_updates | 69684 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000163 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1410 | +| iterations | 13468 | +| time_elapsed | 19560 | +| total_timesteps | 27582464 | +| train/ | | +| approx_kl | 0.01266602 | +| clip_fraction | 0.359 | +| clip_range | 0.0681 | +| entropy_loss | -6.54 | +| explained_variance | 0.154 | +| learning_rate | 4.34e-05 | +| loss | -0.0303 | +| n_updates | 69688 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000109 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1410 | +| iterations | 13469 | +| time_elapsed | 19562 | +| total_timesteps | 27584512 | +| train/ | | +| approx_kl | 0.015763652 | +| clip_fraction | 0.359 | +| clip_range | 0.0681 | +| entropy_loss | -6.75 | +| explained_variance | 0.241 | +| learning_rate | 4.34e-05 | +| loss | -0.0293 | +| n_updates | 69692 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000117 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1410 | +| iterations | 13470 | +| time_elapsed | 19563 | +| total_timesteps | 27586560 | +| train/ | | +| approx_kl | 0.0126486 | +| clip_fraction | 0.327 | +| clip_range | 0.0681 | +| entropy_loss | -5.84 | +| explained_variance | 0.506 | +| learning_rate | 4.34e-05 | +| loss | -0.0189 | +| n_updates | 69696 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.000267 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1410 | +| iterations | 13471 | +| time_elapsed | 19565 | +| total_timesteps | 27588608 | +| train/ | | +| approx_kl | 0.016513722 | +| clip_fraction | 0.378 | +| clip_range | 0.0681 | +| entropy_loss | -5.99 | +| explained_variance | 0.36 | +| learning_rate | 4.34e-05 | +| loss | -0.0364 | +| n_updates | 69700 | +| policy_gradient_loss | -0.0221 | +| value_loss | 9.53e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1410 | +| iterations | 13472 | +| time_elapsed | 19566 | +| total_timesteps | 27590656 | +| train/ | | +| approx_kl | 0.014128629 | +| clip_fraction | 0.354 | +| clip_range | 0.0681 | +| entropy_loss | -6.28 | +| explained_variance | 0.226 | +| learning_rate | 4.34e-05 | +| loss | -0.0291 | +| n_updates | 69704 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000212 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1410 | +| iterations | 13473 | +| time_elapsed | 19568 | +| total_timesteps | 27592704 | +| train/ | | +| approx_kl | 0.01927358 | +| clip_fraction | 0.348 | +| clip_range | 0.0681 | +| entropy_loss | -5.19 | +| explained_variance | 0.682 | +| learning_rate | 4.34e-05 | +| loss | -0.0302 | +| n_updates | 69708 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000114 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1410 | +| iterations | 13474 | +| time_elapsed | 19569 | +| total_timesteps | 27594752 | +| train/ | | +| approx_kl | 0.01663106 | +| clip_fraction | 0.377 | +| clip_range | 0.0681 | +| entropy_loss | -5.74 | +| explained_variance | 0.628 | +| learning_rate | 4.34e-05 | +| loss | -0.0356 | +| n_updates | 69712 | +| policy_gradient_loss | -0.0227 | +| value_loss | 7.55e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1410 | +| iterations | 13475 | +| time_elapsed | 19571 | +| total_timesteps | 27596800 | +| train/ | | +| approx_kl | 0.010706613 | +| clip_fraction | 0.308 | +| clip_range | 0.0681 | +| entropy_loss | -6.44 | +| explained_variance | 0.325 | +| learning_rate | 4.34e-05 | +| loss | -0.0314 | +| n_updates | 69716 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000171 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1410 | +| iterations | 13476 | +| time_elapsed | 19572 | +| total_timesteps | 27598848 | +| train/ | | +| approx_kl | 0.012445895 | +| clip_fraction | 0.316 | +| clip_range | 0.0681 | +| entropy_loss | -6.85 | +| explained_variance | -0.0131 | +| learning_rate | 4.34e-05 | +| loss | -0.0324 | +| n_updates | 69720 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000205 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1410 | +| iterations | 13477 | +| time_elapsed | 19574 | +| total_timesteps | 27600896 | +| train/ | | +| approx_kl | 0.013118111 | +| clip_fraction | 0.304 | +| clip_range | 0.0681 | +| entropy_loss | -6.44 | +| explained_variance | 0.311 | +| learning_rate | 4.34e-05 | +| loss | -0.0261 | +| n_updates | 69724 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000303 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1410 | +| iterations | 13478 | +| time_elapsed | 19575 | +| total_timesteps | 27602944 | +| train/ | | +| approx_kl | 0.013708301 | +| clip_fraction | 0.344 | +| clip_range | 0.0681 | +| entropy_loss | -6.21 | +| explained_variance | 0.336 | +| learning_rate | 4.34e-05 | +| loss | -0.0374 | +| n_updates | 69728 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000185 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1410 | +| iterations | 13479 | +| time_elapsed | 19577 | +| total_timesteps | 27604992 | +| train/ | | +| approx_kl | 0.011463476 | +| clip_fraction | 0.344 | +| clip_range | 0.0681 | +| entropy_loss | -6.87 | +| explained_variance | 0.174 | +| learning_rate | 4.34e-05 | +| loss | -0.0332 | +| n_updates | 69732 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000116 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1410 | +| iterations | 13480 | +| time_elapsed | 19578 | +| total_timesteps | 27607040 | +| train/ | | +| approx_kl | 0.011430722 | +| clip_fraction | 0.323 | +| clip_range | 0.0681 | +| entropy_loss | -5.84 | +| explained_variance | 0.442 | +| learning_rate | 4.34e-05 | +| loss | -0.0223 | +| n_updates | 69736 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.000321 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1410 | +| iterations | 13481 | +| time_elapsed | 19580 | +| total_timesteps | 27609088 | +| train/ | | +| approx_kl | 0.012553889 | +| clip_fraction | 0.318 | +| clip_range | 0.0681 | +| entropy_loss | -5.92 | +| explained_variance | 0.223 | +| learning_rate | 4.34e-05 | +| loss | -0.0251 | +| n_updates | 69740 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000276 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1410 | +| iterations | 13482 | +| time_elapsed | 19581 | +| total_timesteps | 27611136 | +| train/ | | +| approx_kl | 0.012652612 | +| clip_fraction | 0.332 | +| clip_range | 0.0681 | +| entropy_loss | -5.84 | +| explained_variance | 0.518 | +| learning_rate | 4.34e-05 | +| loss | -0.0262 | +| n_updates | 69744 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000207 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1410 | +| iterations | 13483 | +| time_elapsed | 19583 | +| total_timesteps | 27613184 | +| train/ | | +| approx_kl | 0.013551949 | +| clip_fraction | 0.339 | +| clip_range | 0.0681 | +| entropy_loss | -5.31 | +| explained_variance | 0.717 | +| learning_rate | 4.34e-05 | +| loss | -0.0221 | +| n_updates | 69748 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000116 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1410 | +| iterations | 13484 | +| time_elapsed | 19585 | +| total_timesteps | 27615232 | +| train/ | | +| approx_kl | 0.01770657 | +| clip_fraction | 0.348 | +| clip_range | 0.0681 | +| entropy_loss | -6.32 | +| explained_variance | 0.075 | +| learning_rate | 4.34e-05 | +| loss | -0.0354 | +| n_updates | 69752 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000137 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1410 | +| iterations | 13485 | +| time_elapsed | 19586 | +| total_timesteps | 27617280 | +| train/ | | +| approx_kl | 0.0144633865 | +| clip_fraction | 0.357 | +| clip_range | 0.0681 | +| entropy_loss | -6.65 | +| explained_variance | -0.0731 | +| learning_rate | 4.34e-05 | +| loss | -0.0288 | +| n_updates | 69756 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000184 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1410 | +| iterations | 13486 | +| time_elapsed | 19588 | +| total_timesteps | 27619328 | +| train/ | | +| approx_kl | 0.017207237 | +| clip_fraction | 0.377 | +| clip_range | 0.0681 | +| entropy_loss | -6.29 | +| explained_variance | -0.114 | +| learning_rate | 4.34e-05 | +| loss | -0.0346 | +| n_updates | 69760 | +| policy_gradient_loss | -0.0218 | +| value_loss | 8e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1410 | +| iterations | 13487 | +| time_elapsed | 19589 | +| total_timesteps | 27621376 | +| train/ | | +| approx_kl | 0.014025183 | +| clip_fraction | 0.32 | +| clip_range | 0.0681 | +| entropy_loss | -5.97 | +| explained_variance | 0.485 | +| learning_rate | 4.34e-05 | +| loss | -0.0203 | +| n_updates | 69764 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000158 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1409 | +| iterations | 13488 | +| time_elapsed | 19591 | +| total_timesteps | 27623424 | +| train/ | | +| approx_kl | 0.01504276 | +| clip_fraction | 0.35 | +| clip_range | 0.0681 | +| entropy_loss | -6.52 | +| explained_variance | -0.135 | +| learning_rate | 4.34e-05 | +| loss | -0.0335 | +| n_updates | 69768 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000115 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1409 | +| iterations | 13489 | +| time_elapsed | 19592 | +| total_timesteps | 27625472 | +| train/ | | +| approx_kl | 0.011721868 | +| clip_fraction | 0.334 | +| clip_range | 0.0681 | +| entropy_loss | -6.39 | +| explained_variance | 0.358 | +| learning_rate | 4.34e-05 | +| loss | -0.0272 | +| n_updates | 69772 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000264 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1409 | +| iterations | 13490 | +| time_elapsed | 19594 | +| total_timesteps | 27627520 | +| train/ | | +| approx_kl | 0.015824027 | +| clip_fraction | 0.374 | +| clip_range | 0.0681 | +| entropy_loss | -6.43 | +| explained_variance | 0.486 | +| learning_rate | 4.34e-05 | +| loss | -0.039 | +| n_updates | 69776 | +| policy_gradient_loss | -0.0218 | +| value_loss | 7.74e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1409 | +| iterations | 13491 | +| time_elapsed | 19595 | +| total_timesteps | 27629568 | +| train/ | | +| approx_kl | 0.012389053 | +| clip_fraction | 0.32 | +| clip_range | 0.0681 | +| entropy_loss | -6.08 | +| explained_variance | 0.661 | +| learning_rate | 4.34e-05 | +| loss | -0.0224 | +| n_updates | 69780 | +| policy_gradient_loss | -0.0177 | +| value_loss | 8.34e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1409 | +| iterations | 13492 | +| time_elapsed | 19597 | +| total_timesteps | 27631616 | +| train/ | | +| approx_kl | 0.014534503 | +| clip_fraction | 0.324 | +| clip_range | 0.0681 | +| entropy_loss | -5.86 | +| explained_variance | 0.302 | +| learning_rate | 4.34e-05 | +| loss | -0.0277 | +| n_updates | 69784 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000257 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1409 | +| iterations | 13493 | +| time_elapsed | 19598 | +| total_timesteps | 27633664 | +| train/ | | +| approx_kl | 0.015230861 | +| clip_fraction | 0.368 | +| clip_range | 0.0681 | +| entropy_loss | -5.74 | +| explained_variance | 0.24 | +| learning_rate | 4.34e-05 | +| loss | -0.0303 | +| n_updates | 69788 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000211 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1409 | +| iterations | 13494 | +| time_elapsed | 19600 | +| total_timesteps | 27635712 | +| train/ | | +| approx_kl | 0.016112585 | +| clip_fraction | 0.395 | +| clip_range | 0.0681 | +| entropy_loss | -6.03 | +| explained_variance | 0.733 | +| learning_rate | 4.34e-05 | +| loss | -0.0356 | +| n_updates | 69792 | +| policy_gradient_loss | -0.0232 | +| value_loss | 3.95e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1409 | +| iterations | 13495 | +| time_elapsed | 19601 | +| total_timesteps | 27637760 | +| train/ | | +| approx_kl | 0.0110351145 | +| clip_fraction | 0.315 | +| clip_range | 0.0681 | +| entropy_loss | -6.24 | +| explained_variance | 0.38 | +| learning_rate | 4.34e-05 | +| loss | -0.0247 | +| n_updates | 69796 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000233 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1409 | +| iterations | 13496 | +| time_elapsed | 19603 | +| total_timesteps | 27639808 | +| train/ | | +| approx_kl | 0.013196218 | +| clip_fraction | 0.372 | +| clip_range | 0.0681 | +| entropy_loss | -6.21 | +| explained_variance | 0.505 | +| learning_rate | 4.34e-05 | +| loss | -0.0348 | +| n_updates | 69800 | +| policy_gradient_loss | -0.0226 | +| value_loss | 6.03e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1409 | +| iterations | 13497 | +| time_elapsed | 19604 | +| total_timesteps | 27641856 | +| train/ | | +| approx_kl | 0.011602878 | +| clip_fraction | 0.302 | +| clip_range | 0.0681 | +| entropy_loss | -5.9 | +| explained_variance | 0.586 | +| learning_rate | 4.34e-05 | +| loss | -0.0205 | +| n_updates | 69804 | +| policy_gradient_loss | -0.0144 | +| value_loss | 0.000211 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1409 | +| iterations | 13498 | +| time_elapsed | 19606 | +| total_timesteps | 27643904 | +| train/ | | +| approx_kl | 0.01201845 | +| clip_fraction | 0.328 | +| clip_range | 0.0681 | +| entropy_loss | -6.29 | +| explained_variance | 0.209 | +| learning_rate | 4.34e-05 | +| loss | -0.0278 | +| n_updates | 69808 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000183 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1409 | +| iterations | 13499 | +| time_elapsed | 19607 | +| total_timesteps | 27645952 | +| train/ | | +| approx_kl | 0.010879228 | +| clip_fraction | 0.308 | +| clip_range | 0.0681 | +| entropy_loss | -6.16 | +| explained_variance | 0.336 | +| learning_rate | 4.34e-05 | +| loss | -0.0243 | +| n_updates | 69812 | +| policy_gradient_loss | -0.0145 | +| value_loss | 0.000427 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1409 | +| iterations | 13500 | +| time_elapsed | 19609 | +| total_timesteps | 27648000 | +| train/ | | +| approx_kl | 0.014983958 | +| clip_fraction | 0.355 | +| clip_range | 0.0681 | +| entropy_loss | -5.5 | +| explained_variance | 0.708 | +| learning_rate | 4.34e-05 | +| loss | -0.0319 | +| n_updates | 69816 | +| policy_gradient_loss | -0.0218 | +| value_loss | 8.68e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1409 | +| iterations | 13501 | +| time_elapsed | 19610 | +| total_timesteps | 27650048 | +| train/ | | +| approx_kl | 0.014956115 | +| clip_fraction | 0.374 | +| clip_range | 0.0681 | +| entropy_loss | -5.36 | +| explained_variance | 0.782 | +| learning_rate | 4.34e-05 | +| loss | -0.0356 | +| n_updates | 69820 | +| policy_gradient_loss | -0.0223 | +| value_loss | 5.88e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1409 | +| iterations | 13502 | +| time_elapsed | 19612 | +| total_timesteps | 27652096 | +| train/ | | +| approx_kl | 0.020032521 | +| clip_fraction | 0.374 | +| clip_range | 0.0681 | +| entropy_loss | -5.23 | +| explained_variance | 0.45 | +| learning_rate | 4.34e-05 | +| loss | -0.0281 | +| n_updates | 69824 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000288 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1409 | +| iterations | 13503 | +| time_elapsed | 19613 | +| total_timesteps | 27654144 | +| train/ | | +| approx_kl | 0.016923975 | +| clip_fraction | 0.411 | +| clip_range | 0.0681 | +| entropy_loss | -6.18 | +| explained_variance | -0.268 | +| learning_rate | 4.34e-05 | +| loss | -0.0383 | +| n_updates | 69828 | +| policy_gradient_loss | -0.0227 | +| value_loss | 9.24e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1409 | +| iterations | 13504 | +| time_elapsed | 19615 | +| total_timesteps | 27656192 | +| train/ | | +| approx_kl | 0.0143074645 | +| clip_fraction | 0.357 | +| clip_range | 0.0681 | +| entropy_loss | -6.79 | +| explained_variance | -0.171 | +| learning_rate | 4.34e-05 | +| loss | -0.0294 | +| n_updates | 69832 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000142 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1409 | +| iterations | 13505 | +| time_elapsed | 19616 | +| total_timesteps | 27658240 | +| train/ | | +| approx_kl | 0.012992887 | +| clip_fraction | 0.351 | +| clip_range | 0.0681 | +| entropy_loss | -6.61 | +| explained_variance | 0.308 | +| learning_rate | 4.34e-05 | +| loss | -0.0343 | +| n_updates | 69836 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000136 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1409 | +| iterations | 13506 | +| time_elapsed | 19618 | +| total_timesteps | 27660288 | +| train/ | | +| approx_kl | 0.014443651 | +| clip_fraction | 0.348 | +| clip_range | 0.0681 | +| entropy_loss | -6.77 | +| explained_variance | -0.0302 | +| learning_rate | 4.34e-05 | +| loss | -0.0325 | +| n_updates | 69840 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000193 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1409 | +| iterations | 13507 | +| time_elapsed | 19619 | +| total_timesteps | 27662336 | +| train/ | | +| approx_kl | 0.009302137 | +| clip_fraction | 0.325 | +| clip_range | 0.0681 | +| entropy_loss | -6.77 | +| explained_variance | 0.366 | +| learning_rate | 4.34e-05 | +| loss | -0.0296 | +| n_updates | 69844 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000241 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1409 | +| iterations | 13508 | +| time_elapsed | 19621 | +| total_timesteps | 27664384 | +| train/ | | +| approx_kl | 0.013621226 | +| clip_fraction | 0.324 | +| clip_range | 0.0681 | +| entropy_loss | -5.94 | +| explained_variance | 0.403 | +| learning_rate | 4.34e-05 | +| loss | -0.0249 | +| n_updates | 69848 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000213 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1409 | +| iterations | 13509 | +| time_elapsed | 19622 | +| total_timesteps | 27666432 | +| train/ | | +| approx_kl | 0.011585464 | +| clip_fraction | 0.326 | +| clip_range | 0.0681 | +| entropy_loss | -6.08 | +| explained_variance | 0.573 | +| learning_rate | 4.34e-05 | +| loss | -0.0336 | +| n_updates | 69852 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000124 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1409 | +| iterations | 13510 | +| time_elapsed | 19624 | +| total_timesteps | 27668480 | +| train/ | | +| approx_kl | 0.012939809 | +| clip_fraction | 0.321 | +| clip_range | 0.0681 | +| entropy_loss | -5.38 | +| explained_variance | 0.247 | +| learning_rate | 4.34e-05 | +| loss | -0.0231 | +| n_updates | 69856 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000294 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1409 | +| iterations | 13511 | +| time_elapsed | 19625 | +| total_timesteps | 27670528 | +| train/ | | +| approx_kl | 0.0129463095 | +| clip_fraction | 0.345 | +| clip_range | 0.0681 | +| entropy_loss | -5.67 | +| explained_variance | 0.566 | +| learning_rate | 4.34e-05 | +| loss | -0.0287 | +| n_updates | 69860 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000165 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1409 | +| iterations | 13512 | +| time_elapsed | 19627 | +| total_timesteps | 27672576 | +| train/ | | +| approx_kl | 0.012892884 | +| clip_fraction | 0.348 | +| clip_range | 0.0681 | +| entropy_loss | -6.25 | +| explained_variance | 0.495 | +| learning_rate | 4.34e-05 | +| loss | -0.0283 | +| n_updates | 69864 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000161 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1409 | +| iterations | 13513 | +| time_elapsed | 19628 | +| total_timesteps | 27674624 | +| train/ | | +| approx_kl | 0.014555222 | +| clip_fraction | 0.353 | +| clip_range | 0.0681 | +| entropy_loss | -6.41 | +| explained_variance | -0.0595 | +| learning_rate | 4.34e-05 | +| loss | -0.0336 | +| n_updates | 69868 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000195 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1409 | +| iterations | 13514 | +| time_elapsed | 19630 | +| total_timesteps | 27676672 | +| train/ | | +| approx_kl | 0.011328537 | +| clip_fraction | 0.31 | +| clip_range | 0.0681 | +| entropy_loss | -6.27 | +| explained_variance | 0.442 | +| learning_rate | 4.34e-05 | +| loss | -0.0218 | +| n_updates | 69872 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.00026 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1409 | +| iterations | 13515 | +| time_elapsed | 19631 | +| total_timesteps | 27678720 | +| train/ | | +| approx_kl | 0.015818998 | +| clip_fraction | 0.353 | +| clip_range | 0.0681 | +| entropy_loss | -6.04 | +| explained_variance | 0.239 | +| learning_rate | 4.34e-05 | +| loss | -0.0312 | +| n_updates | 69876 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000272 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1409 | +| iterations | 13516 | +| time_elapsed | 19633 | +| total_timesteps | 27680768 | +| train/ | | +| approx_kl | 0.013829696 | +| clip_fraction | 0.363 | +| clip_range | 0.0681 | +| entropy_loss | -6.63 | +| explained_variance | 0.325 | +| learning_rate | 4.34e-05 | +| loss | -0.0342 | +| n_updates | 69880 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000149 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1409 | +| iterations | 13517 | +| time_elapsed | 19634 | +| total_timesteps | 27682816 | +| train/ | | +| approx_kl | 0.016197033 | +| clip_fraction | 0.353 | +| clip_range | 0.0681 | +| entropy_loss | -6 | +| explained_variance | 0.459 | +| learning_rate | 4.34e-05 | +| loss | -0.0319 | +| n_updates | 69884 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000179 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1409 | +| iterations | 13518 | +| time_elapsed | 19636 | +| total_timesteps | 27684864 | +| train/ | | +| approx_kl | 0.016581405 | +| clip_fraction | 0.354 | +| clip_range | 0.0681 | +| entropy_loss | -5.97 | +| explained_variance | 0.546 | +| learning_rate | 4.34e-05 | +| loss | -0.0308 | +| n_updates | 69888 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000115 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1409 | +| iterations | 13519 | +| time_elapsed | 19637 | +| total_timesteps | 27686912 | +| train/ | | +| approx_kl | 0.013792014 | +| clip_fraction | 0.359 | +| clip_range | 0.0681 | +| entropy_loss | -5.85 | +| explained_variance | 0.713 | +| learning_rate | 4.34e-05 | +| loss | -0.0363 | +| n_updates | 69892 | +| policy_gradient_loss | -0.0203 | +| value_loss | 7.71e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1409 | +| iterations | 13520 | +| time_elapsed | 19639 | +| total_timesteps | 27688960 | +| train/ | | +| approx_kl | 0.016910411 | +| clip_fraction | 0.365 | +| clip_range | 0.0681 | +| entropy_loss | -5.67 | +| explained_variance | 0.746 | +| learning_rate | 4.34e-05 | +| loss | -0.0276 | +| n_updates | 69896 | +| policy_gradient_loss | -0.0192 | +| value_loss | 6.25e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1409 | +| iterations | 13521 | +| time_elapsed | 19640 | +| total_timesteps | 27691008 | +| train/ | | +| approx_kl | 0.0123673035 | +| clip_fraction | 0.314 | +| clip_range | 0.0681 | +| entropy_loss | -6.42 | +| explained_variance | 0.378 | +| learning_rate | 4.34e-05 | +| loss | -0.0249 | +| n_updates | 69900 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000157 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1409 | +| iterations | 13522 | +| time_elapsed | 19642 | +| total_timesteps | 27693056 | +| train/ | | +| approx_kl | 0.012570322 | +| clip_fraction | 0.33 | +| clip_range | 0.0681 | +| entropy_loss | -5.99 | +| explained_variance | 0.755 | +| learning_rate | 4.34e-05 | +| loss | -0.026 | +| n_updates | 69904 | +| policy_gradient_loss | -0.0174 | +| value_loss | 6.25e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1409 | +| iterations | 13523 | +| time_elapsed | 19643 | +| total_timesteps | 27695104 | +| train/ | | +| approx_kl | 0.023556128 | +| clip_fraction | 0.327 | +| clip_range | 0.0681 | +| entropy_loss | -6.14 | +| explained_variance | 0.41 | +| learning_rate | 4.34e-05 | +| loss | -0.0291 | +| n_updates | 69908 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000187 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1409 | +| iterations | 13524 | +| time_elapsed | 19645 | +| total_timesteps | 27697152 | +| train/ | | +| approx_kl | 0.014215043 | +| clip_fraction | 0.363 | +| clip_range | 0.0681 | +| entropy_loss | -6.65 | +| explained_variance | -0.0299 | +| learning_rate | 4.34e-05 | +| loss | -0.0312 | +| n_updates | 69912 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000112 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1409 | +| iterations | 13525 | +| time_elapsed | 19646 | +| total_timesteps | 27699200 | +| train/ | | +| approx_kl | 0.01564357 | +| clip_fraction | 0.366 | +| clip_range | 0.0681 | +| entropy_loss | -6.53 | +| explained_variance | 0.229 | +| learning_rate | 4.34e-05 | +| loss | -0.0302 | +| n_updates | 69916 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000173 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1409 | +| iterations | 13526 | +| time_elapsed | 19648 | +| total_timesteps | 27701248 | +| train/ | | +| approx_kl | 0.011400133 | +| clip_fraction | 0.321 | +| clip_range | 0.0681 | +| entropy_loss | -6.5 | +| explained_variance | 0.104 | +| learning_rate | 4.34e-05 | +| loss | -0.0319 | +| n_updates | 69920 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.0001 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1409 | +| iterations | 13527 | +| time_elapsed | 19649 | +| total_timesteps | 27703296 | +| train/ | | +| approx_kl | 0.013067277 | +| clip_fraction | 0.298 | +| clip_range | 0.0681 | +| entropy_loss | -6.23 | +| explained_variance | 0.389 | +| learning_rate | 4.34e-05 | +| loss | -0.0222 | +| n_updates | 69924 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.000238 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1409 | +| iterations | 13528 | +| time_elapsed | 19651 | +| total_timesteps | 27705344 | +| train/ | | +| approx_kl | 0.013714682 | +| clip_fraction | 0.359 | +| clip_range | 0.0681 | +| entropy_loss | -5.87 | +| explained_variance | 0.489 | +| learning_rate | 4.34e-05 | +| loss | -0.0303 | +| n_updates | 69928 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.00015 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1409 | +| iterations | 13529 | +| time_elapsed | 19652 | +| total_timesteps | 27707392 | +| train/ | | +| approx_kl | 0.015468217 | +| clip_fraction | 0.383 | +| clip_range | 0.0681 | +| entropy_loss | -6.02 | +| explained_variance | 0.653 | +| learning_rate | 4.34e-05 | +| loss | -0.0351 | +| n_updates | 69932 | +| policy_gradient_loss | -0.0213 | +| value_loss | 6.99e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1409 | +| iterations | 13530 | +| time_elapsed | 19654 | +| total_timesteps | 27709440 | +| train/ | | +| approx_kl | 0.014818782 | +| clip_fraction | 0.335 | +| clip_range | 0.0681 | +| entropy_loss | -6.48 | +| explained_variance | 0.452 | +| learning_rate | 4.34e-05 | +| loss | -0.0255 | +| n_updates | 69936 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000151 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1409 | +| iterations | 13531 | +| time_elapsed | 19655 | +| total_timesteps | 27711488 | +| train/ | | +| approx_kl | 0.013279458 | +| clip_fraction | 0.316 | +| clip_range | 0.0681 | +| entropy_loss | -6.21 | +| explained_variance | -0.131 | +| learning_rate | 4.34e-05 | +| loss | -0.0242 | +| n_updates | 69940 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000193 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1409 | +| iterations | 13532 | +| time_elapsed | 19657 | +| total_timesteps | 27713536 | +| train/ | | +| approx_kl | 0.0132724475 | +| clip_fraction | 0.327 | +| clip_range | 0.0681 | +| entropy_loss | -6.15 | +| explained_variance | 0.483 | +| learning_rate | 4.34e-05 | +| loss | -0.0263 | +| n_updates | 69944 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000137 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1409 | +| iterations | 13533 | +| time_elapsed | 19658 | +| total_timesteps | 27715584 | +| train/ | | +| approx_kl | 0.015455465 | +| clip_fraction | 0.338 | +| clip_range | 0.0681 | +| entropy_loss | -6.65 | +| explained_variance | -0.0821 | +| learning_rate | 4.34e-05 | +| loss | -0.0298 | +| n_updates | 69948 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000117 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1409 | +| iterations | 13534 | +| time_elapsed | 19660 | +| total_timesteps | 27717632 | +| train/ | | +| approx_kl | 0.009538833 | +| clip_fraction | 0.32 | +| clip_range | 0.0681 | +| entropy_loss | -6.52 | +| explained_variance | 0.0942 | +| learning_rate | 4.34e-05 | +| loss | -0.0286 | +| n_updates | 69952 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000447 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1409 | +| iterations | 13535 | +| time_elapsed | 19661 | +| total_timesteps | 27719680 | +| train/ | | +| approx_kl | 0.013578993 | +| clip_fraction | 0.373 | +| clip_range | 0.0681 | +| entropy_loss | -5.51 | +| explained_variance | 0.579 | +| learning_rate | 4.34e-05 | +| loss | -0.0352 | +| n_updates | 69956 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000125 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1409 | +| iterations | 13536 | +| time_elapsed | 19663 | +| total_timesteps | 27721728 | +| train/ | | +| approx_kl | 0.0137134725 | +| clip_fraction | 0.374 | +| clip_range | 0.0681 | +| entropy_loss | -5.84 | +| explained_variance | 0.456 | +| learning_rate | 4.34e-05 | +| loss | -0.0288 | +| n_updates | 69960 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000218 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1409 | +| iterations | 13537 | +| time_elapsed | 19664 | +| total_timesteps | 27723776 | +| train/ | | +| approx_kl | 0.015634779 | +| clip_fraction | 0.387 | +| clip_range | 0.0681 | +| entropy_loss | -6.09 | +| explained_variance | 0.44 | +| learning_rate | 4.34e-05 | +| loss | -0.0355 | +| n_updates | 69964 | +| policy_gradient_loss | -0.0226 | +| value_loss | 9.32e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1409 | +| iterations | 13538 | +| time_elapsed | 19666 | +| total_timesteps | 27725824 | +| train/ | | +| approx_kl | 0.015615762 | +| clip_fraction | 0.392 | +| clip_range | 0.0681 | +| entropy_loss | -6.16 | +| explained_variance | 0.387 | +| learning_rate | 4.34e-05 | +| loss | -0.0336 | +| n_updates | 69968 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000101 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1409 | +| iterations | 13539 | +| time_elapsed | 19667 | +| total_timesteps | 27727872 | +| train/ | | +| approx_kl | 0.0124146305 | +| clip_fraction | 0.319 | +| clip_range | 0.0681 | +| entropy_loss | -6.31 | +| explained_variance | 0.389 | +| learning_rate | 4.34e-05 | +| loss | -0.0264 | +| n_updates | 69972 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000278 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1409 | +| iterations | 13540 | +| time_elapsed | 19669 | +| total_timesteps | 27729920 | +| train/ | | +| approx_kl | 0.011702501 | +| clip_fraction | 0.328 | +| clip_range | 0.0681 | +| entropy_loss | -6.27 | +| explained_variance | 0.232 | +| learning_rate | 4.34e-05 | +| loss | -0.0257 | +| n_updates | 69976 | +| policy_gradient_loss | -0.0145 | +| value_loss | 0.000309 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1409 | +| iterations | 13541 | +| time_elapsed | 19670 | +| total_timesteps | 27731968 | +| train/ | | +| approx_kl | 0.014141409 | +| clip_fraction | 0.369 | +| clip_range | 0.0681 | +| entropy_loss | -6.26 | +| explained_variance | 0.497 | +| learning_rate | 4.34e-05 | +| loss | -0.0339 | +| n_updates | 69980 | +| policy_gradient_loss | -0.0225 | +| value_loss | 0.000139 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1409 | +| iterations | 13542 | +| time_elapsed | 19672 | +| total_timesteps | 27734016 | +| train/ | | +| approx_kl | 0.013759797 | +| clip_fraction | 0.369 | +| clip_range | 0.0681 | +| entropy_loss | -6.34 | +| explained_variance | 0.348 | +| learning_rate | 4.34e-05 | +| loss | -0.0356 | +| n_updates | 69984 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000118 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1409 | +| iterations | 13543 | +| time_elapsed | 19673 | +| total_timesteps | 27736064 | +| train/ | | +| approx_kl | 0.009433698 | +| clip_fraction | 0.3 | +| clip_range | 0.0681 | +| entropy_loss | -6.21 | +| explained_variance | 0.365 | +| learning_rate | 4.34e-05 | +| loss | -0.0317 | +| n_updates | 69988 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000282 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1409 | +| iterations | 13544 | +| time_elapsed | 19675 | +| total_timesteps | 27738112 | +| train/ | | +| approx_kl | 0.013286152 | +| clip_fraction | 0.356 | +| clip_range | 0.0681 | +| entropy_loss | -6.53 | +| explained_variance | 0.311 | +| learning_rate | 4.34e-05 | +| loss | -0.0329 | +| n_updates | 69992 | +| policy_gradient_loss | -0.0222 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1409 | +| iterations | 13545 | +| time_elapsed | 19676 | +| total_timesteps | 27740160 | +| train/ | | +| approx_kl | 0.012437247 | +| clip_fraction | 0.352 | +| clip_range | 0.0681 | +| entropy_loss | -6.48 | +| explained_variance | 0.381 | +| learning_rate | 4.34e-05 | +| loss | -0.031 | +| n_updates | 69996 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000194 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1409 | +| iterations | 13546 | +| time_elapsed | 19678 | +| total_timesteps | 27742208 | +| train/ | | +| approx_kl | 0.014739644 | +| clip_fraction | 0.365 | +| clip_range | 0.0681 | +| entropy_loss | -5.51 | +| explained_variance | 0.587 | +| learning_rate | 4.34e-05 | +| loss | -0.0292 | +| n_updates | 70000 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000147 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1409 | +| iterations | 13547 | +| time_elapsed | 19679 | +| total_timesteps | 27744256 | +| train/ | | +| approx_kl | 0.015393394 | +| clip_fraction | 0.344 | +| clip_range | 0.0681 | +| entropy_loss | -6.28 | +| explained_variance | 0.208 | +| learning_rate | 4.34e-05 | +| loss | -0.0313 | +| n_updates | 70004 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000206 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1409 | +| iterations | 13548 | +| time_elapsed | 19681 | +| total_timesteps | 27746304 | +| train/ | | +| approx_kl | 0.016540177 | +| clip_fraction | 0.349 | +| clip_range | 0.0681 | +| entropy_loss | -6.33 | +| explained_variance | 0.567 | +| learning_rate | 4.34e-05 | +| loss | -0.0274 | +| n_updates | 70008 | +| policy_gradient_loss | -0.0212 | +| value_loss | 6.07e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1409 | +| iterations | 13549 | +| time_elapsed | 19682 | +| total_timesteps | 27748352 | +| train/ | | +| approx_kl | 0.01306074 | +| clip_fraction | 0.334 | +| clip_range | 0.0681 | +| entropy_loss | -6.25 | +| explained_variance | 0.257 | +| learning_rate | 4.34e-05 | +| loss | -0.0289 | +| n_updates | 70012 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000204 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1409 | +| iterations | 13550 | +| time_elapsed | 19684 | +| total_timesteps | 27750400 | +| train/ | | +| approx_kl | 0.014174351 | +| clip_fraction | 0.364 | +| clip_range | 0.0681 | +| entropy_loss | -6.58 | +| explained_variance | -0.0277 | +| learning_rate | 4.34e-05 | +| loss | -0.0309 | +| n_updates | 70016 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000154 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1409 | +| iterations | 13551 | +| time_elapsed | 19685 | +| total_timesteps | 27752448 | +| train/ | | +| approx_kl | 0.011243667 | +| clip_fraction | 0.316 | +| clip_range | 0.0681 | +| entropy_loss | -6.26 | +| explained_variance | 0.563 | +| learning_rate | 4.34e-05 | +| loss | -0.0277 | +| n_updates | 70020 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000151 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1409 | +| iterations | 13552 | +| time_elapsed | 19687 | +| total_timesteps | 27754496 | +| train/ | | +| approx_kl | 0.011981932 | +| clip_fraction | 0.311 | +| clip_range | 0.0681 | +| entropy_loss | -6.45 | +| explained_variance | 0.266 | +| learning_rate | 4.34e-05 | +| loss | -0.0299 | +| n_updates | 70024 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.0002 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1409 | +| iterations | 13553 | +| time_elapsed | 19688 | +| total_timesteps | 27756544 | +| train/ | | +| approx_kl | 0.012484034 | +| clip_fraction | 0.34 | +| clip_range | 0.0681 | +| entropy_loss | -6.67 | +| explained_variance | 0.327 | +| learning_rate | 4.34e-05 | +| loss | -0.0362 | +| n_updates | 70028 | +| policy_gradient_loss | -0.0203 | +| value_loss | 9.86e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1409 | +| iterations | 13554 | +| time_elapsed | 19690 | +| total_timesteps | 27758592 | +| train/ | | +| approx_kl | 0.012871385 | +| clip_fraction | 0.34 | +| clip_range | 0.0681 | +| entropy_loss | -6.02 | +| explained_variance | 0.729 | +| learning_rate | 4.34e-05 | +| loss | -0.0271 | +| n_updates | 70032 | +| policy_gradient_loss | -0.0186 | +| value_loss | 9.67e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1409 | +| iterations | 13555 | +| time_elapsed | 19692 | +| total_timesteps | 27760640 | +| train/ | | +| approx_kl | 0.010669982 | +| clip_fraction | 0.306 | +| clip_range | 0.0681 | +| entropy_loss | -6.27 | +| explained_variance | 0.355 | +| learning_rate | 4.34e-05 | +| loss | -0.0269 | +| n_updates | 70036 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000192 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1409 | +| iterations | 13556 | +| time_elapsed | 19693 | +| total_timesteps | 27762688 | +| train/ | | +| approx_kl | 0.013184514 | +| clip_fraction | 0.338 | +| clip_range | 0.0681 | +| entropy_loss | -5.73 | +| explained_variance | 0.689 | +| learning_rate | 4.34e-05 | +| loss | -0.0232 | +| n_updates | 70040 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.00011 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1409 | +| iterations | 13557 | +| time_elapsed | 19695 | +| total_timesteps | 27764736 | +| train/ | | +| approx_kl | 0.012620884 | +| clip_fraction | 0.346 | +| clip_range | 0.0681 | +| entropy_loss | -5.8 | +| explained_variance | 0.244 | +| learning_rate | 4.34e-05 | +| loss | -0.0219 | +| n_updates | 70044 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000269 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1409 | +| iterations | 13558 | +| time_elapsed | 19696 | +| total_timesteps | 27766784 | +| train/ | | +| approx_kl | 0.016923923 | +| clip_fraction | 0.361 | +| clip_range | 0.0681 | +| entropy_loss | -6.06 | +| explained_variance | 0.37 | +| learning_rate | 4.34e-05 | +| loss | -0.0318 | +| n_updates | 70048 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000101 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1409 | +| iterations | 13559 | +| time_elapsed | 19698 | +| total_timesteps | 27768832 | +| train/ | | +| approx_kl | 0.016342204 | +| clip_fraction | 0.312 | +| clip_range | 0.0681 | +| entropy_loss | -6.4 | +| explained_variance | 0.307 | +| learning_rate | 4.34e-05 | +| loss | -0.0241 | +| n_updates | 70052 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000214 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1409 | +| iterations | 13560 | +| time_elapsed | 19699 | +| total_timesteps | 27770880 | +| train/ | | +| approx_kl | 0.0120736435 | +| clip_fraction | 0.312 | +| clip_range | 0.0681 | +| entropy_loss | -6.21 | +| explained_variance | 0.393 | +| learning_rate | 4.34e-05 | +| loss | -0.0308 | +| n_updates | 70056 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000236 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1409 | +| iterations | 13561 | +| time_elapsed | 19701 | +| total_timesteps | 27772928 | +| train/ | | +| approx_kl | 0.015044379 | +| clip_fraction | 0.366 | +| clip_range | 0.0681 | +| entropy_loss | -6.47 | +| explained_variance | -0.0565 | +| learning_rate | 4.34e-05 | +| loss | -0.0363 | +| n_updates | 70060 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000101 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1409 | +| iterations | 13562 | +| time_elapsed | 19702 | +| total_timesteps | 27774976 | +| train/ | | +| approx_kl | 0.012425929 | +| clip_fraction | 0.324 | +| clip_range | 0.0681 | +| entropy_loss | -6.39 | +| explained_variance | 0.417 | +| learning_rate | 4.34e-05 | +| loss | -0.0329 | +| n_updates | 70064 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000229 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1409 | +| iterations | 13563 | +| time_elapsed | 19704 | +| total_timesteps | 27777024 | +| train/ | | +| approx_kl | 0.009949722 | +| clip_fraction | 0.319 | +| clip_range | 0.0681 | +| entropy_loss | -5.82 | +| explained_variance | 0.541 | +| learning_rate | 4.34e-05 | +| loss | -0.0305 | +| n_updates | 70068 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000196 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1409 | +| iterations | 13564 | +| time_elapsed | 19705 | +| total_timesteps | 27779072 | +| train/ | | +| approx_kl | 0.013761852 | +| clip_fraction | 0.381 | +| clip_range | 0.0681 | +| entropy_loss | -6.06 | +| explained_variance | 0.516 | +| learning_rate | 4.34e-05 | +| loss | -0.0378 | +| n_updates | 70072 | +| policy_gradient_loss | -0.0216 | +| value_loss | 8.93e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1409 | +| iterations | 13565 | +| time_elapsed | 19707 | +| total_timesteps | 27781120 | +| train/ | | +| approx_kl | 0.014113297 | +| clip_fraction | 0.32 | +| clip_range | 0.0681 | +| entropy_loss | -6.01 | +| explained_variance | 0.394 | +| learning_rate | 4.34e-05 | +| loss | -0.0274 | +| n_updates | 70076 | +| policy_gradient_loss | -0.0148 | +| value_loss | 0.00024 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1409 | +| iterations | 13566 | +| time_elapsed | 19708 | +| total_timesteps | 27783168 | +| train/ | | +| approx_kl | 0.014990222 | +| clip_fraction | 0.349 | +| clip_range | 0.0681 | +| entropy_loss | -5.89 | +| explained_variance | 0.265 | +| learning_rate | 4.34e-05 | +| loss | -0.0385 | +| n_updates | 70080 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000259 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1409 | +| iterations | 13567 | +| time_elapsed | 19710 | +| total_timesteps | 27785216 | +| train/ | | +| approx_kl | 0.018198334 | +| clip_fraction | 0.378 | +| clip_range | 0.0681 | +| entropy_loss | -6.05 | +| explained_variance | 0.431 | +| learning_rate | 4.34e-05 | +| loss | -0.0277 | +| n_updates | 70084 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000133 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1409 | +| iterations | 13568 | +| time_elapsed | 19711 | +| total_timesteps | 27787264 | +| train/ | | +| approx_kl | 0.018578125 | +| clip_fraction | 0.368 | +| clip_range | 0.0681 | +| entropy_loss | -6.34 | +| explained_variance | 0.398 | +| learning_rate | 4.34e-05 | +| loss | -0.0296 | +| n_updates | 70088 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000125 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1409 | +| iterations | 13569 | +| time_elapsed | 19713 | +| total_timesteps | 27789312 | +| train/ | | +| approx_kl | 0.01572847 | +| clip_fraction | 0.366 | +| clip_range | 0.0681 | +| entropy_loss | -6.33 | +| explained_variance | 0.239 | +| learning_rate | 4.34e-05 | +| loss | -0.0322 | +| n_updates | 70092 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000156 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1409 | +| iterations | 13570 | +| time_elapsed | 19714 | +| total_timesteps | 27791360 | +| train/ | | +| approx_kl | 0.019212835 | +| clip_fraction | 0.373 | +| clip_range | 0.0681 | +| entropy_loss | -6.18 | +| explained_variance | 0.604 | +| learning_rate | 4.34e-05 | +| loss | -0.0294 | +| n_updates | 70096 | +| policy_gradient_loss | -0.0194 | +| value_loss | 8.77e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1409 | +| iterations | 13571 | +| time_elapsed | 19716 | +| total_timesteps | 27793408 | +| train/ | | +| approx_kl | 0.014783309 | +| clip_fraction | 0.349 | +| clip_range | 0.0681 | +| entropy_loss | -6.81 | +| explained_variance | -0.115 | +| learning_rate | 4.34e-05 | +| loss | -0.0289 | +| n_updates | 70100 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000151 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1409 | +| iterations | 13572 | +| time_elapsed | 19717 | +| total_timesteps | 27795456 | +| train/ | | +| approx_kl | 0.012242492 | +| clip_fraction | 0.349 | +| clip_range | 0.0681 | +| entropy_loss | -6.45 | +| explained_variance | 0.289 | +| learning_rate | 4.34e-05 | +| loss | -0.0291 | +| n_updates | 70104 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000185 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1409 | +| iterations | 13573 | +| time_elapsed | 19719 | +| total_timesteps | 27797504 | +| train/ | | +| approx_kl | 0.014145294 | +| clip_fraction | 0.345 | +| clip_range | 0.0681 | +| entropy_loss | -6.12 | +| explained_variance | 0.578 | +| learning_rate | 4.34e-05 | +| loss | -0.0318 | +| n_updates | 70108 | +| policy_gradient_loss | -0.019 | +| value_loss | 9.07e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1409 | +| iterations | 13574 | +| time_elapsed | 19720 | +| total_timesteps | 27799552 | +| train/ | | +| approx_kl | 0.015501599 | +| clip_fraction | 0.347 | +| clip_range | 0.0681 | +| entropy_loss | -6.22 | +| explained_variance | 0.297 | +| learning_rate | 4.34e-05 | +| loss | -0.0374 | +| n_updates | 70112 | +| policy_gradient_loss | -0.0204 | +| value_loss | 4.58e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1409 | +| iterations | 13575 | +| time_elapsed | 19722 | +| total_timesteps | 27801600 | +| train/ | | +| approx_kl | 0.018646993 | +| clip_fraction | 0.337 | +| clip_range | 0.0681 | +| entropy_loss | -5.83 | +| explained_variance | 0.399 | +| learning_rate | 4.34e-05 | +| loss | -0.0228 | +| n_updates | 70116 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000328 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1409 | +| iterations | 13576 | +| time_elapsed | 19723 | +| total_timesteps | 27803648 | +| train/ | | +| approx_kl | 0.016555581 | +| clip_fraction | 0.392 | +| clip_range | 0.068 | +| entropy_loss | -5.76 | +| explained_variance | 0.605 | +| learning_rate | 4.34e-05 | +| loss | -0.0319 | +| n_updates | 70120 | +| policy_gradient_loss | -0.022 | +| value_loss | 9.15e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1409 | +| iterations | 13577 | +| time_elapsed | 19725 | +| total_timesteps | 27805696 | +| train/ | | +| approx_kl | 0.016510095 | +| clip_fraction | 0.37 | +| clip_range | 0.068 | +| entropy_loss | -5.78 | +| explained_variance | 0.537 | +| learning_rate | 4.34e-05 | +| loss | -0.0307 | +| n_updates | 70124 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.00011 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1409 | +| iterations | 13578 | +| time_elapsed | 19726 | +| total_timesteps | 27807744 | +| train/ | | +| approx_kl | 0.015395166 | +| clip_fraction | 0.367 | +| clip_range | 0.068 | +| entropy_loss | -5.65 | +| explained_variance | 0.696 | +| learning_rate | 4.34e-05 | +| loss | -0.03 | +| n_updates | 70128 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000119 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1409 | +| iterations | 13579 | +| time_elapsed | 19728 | +| total_timesteps | 27809792 | +| train/ | | +| approx_kl | 0.01722603 | +| clip_fraction | 0.36 | +| clip_range | 0.068 | +| entropy_loss | -5.77 | +| explained_variance | 0.428 | +| learning_rate | 4.34e-05 | +| loss | -0.0344 | +| n_updates | 70132 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.0002 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1409 | +| iterations | 13580 | +| time_elapsed | 19729 | +| total_timesteps | 27811840 | +| train/ | | +| approx_kl | 0.015793419 | +| clip_fraction | 0.382 | +| clip_range | 0.068 | +| entropy_loss | -6.05 | +| explained_variance | 0.552 | +| learning_rate | 4.34e-05 | +| loss | -0.0361 | +| n_updates | 70136 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000102 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1409 | +| iterations | 13581 | +| time_elapsed | 19731 | +| total_timesteps | 27813888 | +| train/ | | +| approx_kl | 0.012453706 | +| clip_fraction | 0.34 | +| clip_range | 0.068 | +| entropy_loss | -6.65 | +| explained_variance | -0.0625 | +| learning_rate | 4.34e-05 | +| loss | -0.0293 | +| n_updates | 70140 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000102 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1409 | +| iterations | 13582 | +| time_elapsed | 19732 | +| total_timesteps | 27815936 | +| train/ | | +| approx_kl | 0.013041291 | +| clip_fraction | 0.363 | +| clip_range | 0.068 | +| entropy_loss | -6.5 | +| explained_variance | 0.234 | +| learning_rate | 4.34e-05 | +| loss | -0.0294 | +| n_updates | 70144 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.0002 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1409 | +| iterations | 13583 | +| time_elapsed | 19734 | +| total_timesteps | 27817984 | +| train/ | | +| approx_kl | 0.012776168 | +| clip_fraction | 0.345 | +| clip_range | 0.068 | +| entropy_loss | -6.09 | +| explained_variance | 0.397 | +| learning_rate | 4.34e-05 | +| loss | -0.0279 | +| n_updates | 70148 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000198 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1409 | +| iterations | 13584 | +| time_elapsed | 19735 | +| total_timesteps | 27820032 | +| train/ | | +| approx_kl | 0.013419958 | +| clip_fraction | 0.347 | +| clip_range | 0.068 | +| entropy_loss | -6.24 | +| explained_variance | 0.271 | +| learning_rate | 4.34e-05 | +| loss | -0.0293 | +| n_updates | 70152 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.00019 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1409 | +| iterations | 13585 | +| time_elapsed | 19737 | +| total_timesteps | 27822080 | +| train/ | | +| approx_kl | 0.014102816 | +| clip_fraction | 0.366 | +| clip_range | 0.068 | +| entropy_loss | -6.37 | +| explained_variance | 0.557 | +| learning_rate | 4.34e-05 | +| loss | -0.0276 | +| n_updates | 70156 | +| policy_gradient_loss | -0.0199 | +| value_loss | 8.07e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1409 | +| iterations | 13586 | +| time_elapsed | 19738 | +| total_timesteps | 27824128 | +| train/ | | +| approx_kl | 0.014484807 | +| clip_fraction | 0.369 | +| clip_range | 0.068 | +| entropy_loss | -6.26 | +| explained_variance | 0.761 | +| learning_rate | 4.34e-05 | +| loss | -0.0312 | +| n_updates | 70160 | +| policy_gradient_loss | -0.0188 | +| value_loss | 7.67e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1409 | +| iterations | 13587 | +| time_elapsed | 19740 | +| total_timesteps | 27826176 | +| train/ | | +| approx_kl | 0.013927016 | +| clip_fraction | 0.349 | +| clip_range | 0.068 | +| entropy_loss | -5.69 | +| explained_variance | 0.296 | +| learning_rate | 4.34e-05 | +| loss | -0.0254 | +| n_updates | 70164 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000182 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1409 | +| iterations | 13588 | +| time_elapsed | 19741 | +| total_timesteps | 27828224 | +| train/ | | +| approx_kl | 0.013487232 | +| clip_fraction | 0.349 | +| clip_range | 0.068 | +| entropy_loss | -5.6 | +| explained_variance | 0.457 | +| learning_rate | 4.34e-05 | +| loss | -0.0225 | +| n_updates | 70168 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000371 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1409 | +| iterations | 13589 | +| time_elapsed | 19743 | +| total_timesteps | 27830272 | +| train/ | | +| approx_kl | 0.017172791 | +| clip_fraction | 0.395 | +| clip_range | 0.068 | +| entropy_loss | -5.95 | +| explained_variance | 0.0228 | +| learning_rate | 4.34e-05 | +| loss | -0.0343 | +| n_updates | 70172 | +| policy_gradient_loss | -0.0234 | +| value_loss | 0.000132 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1409 | +| iterations | 13590 | +| time_elapsed | 19744 | +| total_timesteps | 27832320 | +| train/ | | +| approx_kl | 0.015879728 | +| clip_fraction | 0.333 | +| clip_range | 0.068 | +| entropy_loss | -5.92 | +| explained_variance | 0.491 | +| learning_rate | 4.34e-05 | +| loss | -0.0312 | +| n_updates | 70176 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000271 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1409 | +| iterations | 13591 | +| time_elapsed | 19746 | +| total_timesteps | 27834368 | +| train/ | | +| approx_kl | 0.014184399 | +| clip_fraction | 0.358 | +| clip_range | 0.068 | +| entropy_loss | -6.24 | +| explained_variance | -0.155 | +| learning_rate | 4.34e-05 | +| loss | -0.0353 | +| n_updates | 70180 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000229 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1409 | +| iterations | 13592 | +| time_elapsed | 19747 | +| total_timesteps | 27836416 | +| train/ | | +| approx_kl | 0.013509135 | +| clip_fraction | 0.345 | +| clip_range | 0.068 | +| entropy_loss | -6.74 | +| explained_variance | -0.24 | +| learning_rate | 4.34e-05 | +| loss | -0.0298 | +| n_updates | 70184 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000179 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1409 | +| iterations | 13593 | +| time_elapsed | 19749 | +| total_timesteps | 27838464 | +| train/ | | +| approx_kl | 0.011160519 | +| clip_fraction | 0.318 | +| clip_range | 0.068 | +| entropy_loss | -6.36 | +| explained_variance | 0.227 | +| learning_rate | 4.34e-05 | +| loss | -0.0253 | +| n_updates | 70188 | +| policy_gradient_loss | -0.0144 | +| value_loss | 0.000306 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1409 | +| iterations | 13594 | +| time_elapsed | 19750 | +| total_timesteps | 27840512 | +| train/ | | +| approx_kl | 0.014996175 | +| clip_fraction | 0.355 | +| clip_range | 0.068 | +| entropy_loss | -5.43 | +| explained_variance | 0.741 | +| learning_rate | 4.34e-05 | +| loss | -0.0273 | +| n_updates | 70192 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000111 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1409 | +| iterations | 13595 | +| time_elapsed | 19752 | +| total_timesteps | 27842560 | +| train/ | | +| approx_kl | 0.014973767 | +| clip_fraction | 0.343 | +| clip_range | 0.068 | +| entropy_loss | -5.55 | +| explained_variance | 0.542 | +| learning_rate | 4.34e-05 | +| loss | -0.0303 | +| n_updates | 70196 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.0002 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1409 | +| iterations | 13596 | +| time_elapsed | 19753 | +| total_timesteps | 27844608 | +| train/ | | +| approx_kl | 0.01280291 | +| clip_fraction | 0.34 | +| clip_range | 0.068 | +| entropy_loss | -6.22 | +| explained_variance | 0.504 | +| learning_rate | 4.34e-05 | +| loss | -0.0302 | +| n_updates | 70200 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.00012 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1409 | +| iterations | 13597 | +| time_elapsed | 19755 | +| total_timesteps | 27846656 | +| train/ | | +| approx_kl | 0.01501134 | +| clip_fraction | 0.362 | +| clip_range | 0.068 | +| entropy_loss | -5.58 | +| explained_variance | 0.704 | +| learning_rate | 4.34e-05 | +| loss | -0.0276 | +| n_updates | 70204 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000102 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1409 | +| iterations | 13598 | +| time_elapsed | 19756 | +| total_timesteps | 27848704 | +| train/ | | +| approx_kl | 0.011941585 | +| clip_fraction | 0.349 | +| clip_range | 0.068 | +| entropy_loss | -6.16 | +| explained_variance | 0.0606 | +| learning_rate | 4.34e-05 | +| loss | -0.0307 | +| n_updates | 70208 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000107 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1409 | +| iterations | 13599 | +| time_elapsed | 19758 | +| total_timesteps | 27850752 | +| train/ | | +| approx_kl | 0.011996305 | +| clip_fraction | 0.327 | +| clip_range | 0.068 | +| entropy_loss | -6.3 | +| explained_variance | 0.39 | +| learning_rate | 4.34e-05 | +| loss | -0.0262 | +| n_updates | 70212 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000314 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1409 | +| iterations | 13600 | +| time_elapsed | 19759 | +| total_timesteps | 27852800 | +| train/ | | +| approx_kl | 0.015095565 | +| clip_fraction | 0.357 | +| clip_range | 0.068 | +| entropy_loss | -5.63 | +| explained_variance | 0.619 | +| learning_rate | 4.34e-05 | +| loss | -0.0337 | +| n_updates | 70216 | +| policy_gradient_loss | -0.02 | +| value_loss | 9.07e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1409 | +| iterations | 13601 | +| time_elapsed | 19761 | +| total_timesteps | 27854848 | +| train/ | | +| approx_kl | 0.014480108 | +| clip_fraction | 0.362 | +| clip_range | 0.068 | +| entropy_loss | -6.28 | +| explained_variance | -0.29 | +| learning_rate | 4.34e-05 | +| loss | -0.033 | +| n_updates | 70220 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000136 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1409 | +| iterations | 13602 | +| time_elapsed | 19762 | +| total_timesteps | 27856896 | +| train/ | | +| approx_kl | 0.0143722035 | +| clip_fraction | 0.355 | +| clip_range | 0.068 | +| entropy_loss | -6.23 | +| explained_variance | 0.566 | +| learning_rate | 4.34e-05 | +| loss | -0.0351 | +| n_updates | 70224 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000103 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1409 | +| iterations | 13603 | +| time_elapsed | 19764 | +| total_timesteps | 27858944 | +| train/ | | +| approx_kl | 0.011908267 | +| clip_fraction | 0.318 | +| clip_range | 0.068 | +| entropy_loss | -6.46 | +| explained_variance | 0.24 | +| learning_rate | 4.34e-05 | +| loss | -0.0198 | +| n_updates | 70228 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000225 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1409 | +| iterations | 13604 | +| time_elapsed | 19765 | +| total_timesteps | 27860992 | +| train/ | | +| approx_kl | 0.013085416 | +| clip_fraction | 0.307 | +| clip_range | 0.068 | +| entropy_loss | -6.12 | +| explained_variance | 0.322 | +| learning_rate | 4.34e-05 | +| loss | -0.0261 | +| n_updates | 70232 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000314 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1409 | +| iterations | 13605 | +| time_elapsed | 19767 | +| total_timesteps | 27863040 | +| train/ | | +| approx_kl | 0.012328101 | +| clip_fraction | 0.331 | +| clip_range | 0.068 | +| entropy_loss | -5.61 | +| explained_variance | 0.679 | +| learning_rate | 4.34e-05 | +| loss | -0.0295 | +| n_updates | 70236 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000158 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1409 | +| iterations | 13606 | +| time_elapsed | 19768 | +| total_timesteps | 27865088 | +| train/ | | +| approx_kl | 0.010343991 | +| clip_fraction | 0.339 | +| clip_range | 0.068 | +| entropy_loss | -5.47 | +| explained_variance | 0.441 | +| learning_rate | 4.34e-05 | +| loss | -0.0256 | +| n_updates | 70240 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.00018 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1409 | +| iterations | 13607 | +| time_elapsed | 19770 | +| total_timesteps | 27867136 | +| train/ | | +| approx_kl | 0.011522562 | +| clip_fraction | 0.362 | +| clip_range | 0.068 | +| entropy_loss | -5.84 | +| explained_variance | 0.463 | +| learning_rate | 4.34e-05 | +| loss | -0.0252 | +| n_updates | 70244 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000126 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1409 | +| iterations | 13608 | +| time_elapsed | 19771 | +| total_timesteps | 27869184 | +| train/ | | +| approx_kl | 0.017432647 | +| clip_fraction | 0.303 | +| clip_range | 0.068 | +| entropy_loss | -5.37 | +| explained_variance | 0.418 | +| learning_rate | 4.34e-05 | +| loss | -0.0213 | +| n_updates | 70248 | +| policy_gradient_loss | -0.0144 | +| value_loss | 0.000307 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1409 | +| iterations | 13609 | +| time_elapsed | 19773 | +| total_timesteps | 27871232 | +| train/ | | +| approx_kl | 0.010877454 | +| clip_fraction | 0.341 | +| clip_range | 0.068 | +| entropy_loss | -6.31 | +| explained_variance | 0.411 | +| learning_rate | 4.34e-05 | +| loss | -0.0307 | +| n_updates | 70252 | +| policy_gradient_loss | -0.0202 | +| value_loss | 8.81e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1409 | +| iterations | 13610 | +| time_elapsed | 19774 | +| total_timesteps | 27873280 | +| train/ | | +| approx_kl | 0.011778875 | +| clip_fraction | 0.344 | +| clip_range | 0.068 | +| entropy_loss | -6.49 | +| explained_variance | 0.269 | +| learning_rate | 4.34e-05 | +| loss | -0.0247 | +| n_updates | 70256 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000368 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1409 | +| iterations | 13611 | +| time_elapsed | 19776 | +| total_timesteps | 27875328 | +| train/ | | +| approx_kl | 0.013114954 | +| clip_fraction | 0.361 | +| clip_range | 0.068 | +| entropy_loss | -6.3 | +| explained_variance | 0.399 | +| learning_rate | 4.34e-05 | +| loss | -0.034 | +| n_updates | 70260 | +| policy_gradient_loss | -0.0207 | +| value_loss | 9.98e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1409 | +| iterations | 13612 | +| time_elapsed | 19777 | +| total_timesteps | 27877376 | +| train/ | | +| approx_kl | 0.012088358 | +| clip_fraction | 0.34 | +| clip_range | 0.068 | +| entropy_loss | -6.33 | +| explained_variance | 0.348 | +| learning_rate | 4.34e-05 | +| loss | -0.0315 | +| n_updates | 70264 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000119 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1409 | +| iterations | 13613 | +| time_elapsed | 19779 | +| total_timesteps | 27879424 | +| train/ | | +| approx_kl | 0.01108175 | +| clip_fraction | 0.324 | +| clip_range | 0.068 | +| entropy_loss | -6.3 | +| explained_variance | 0.344 | +| learning_rate | 4.34e-05 | +| loss | -0.0258 | +| n_updates | 70268 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000272 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1409 | +| iterations | 13614 | +| time_elapsed | 19780 | +| total_timesteps | 27881472 | +| train/ | | +| approx_kl | 0.013589075 | +| clip_fraction | 0.356 | +| clip_range | 0.068 | +| entropy_loss | -5.88 | +| explained_variance | 0.384 | +| learning_rate | 4.34e-05 | +| loss | -0.0311 | +| n_updates | 70272 | +| policy_gradient_loss | -0.0214 | +| value_loss | 9.75e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1409 | +| iterations | 13615 | +| time_elapsed | 19782 | +| total_timesteps | 27883520 | +| train/ | | +| approx_kl | 0.01259549 | +| clip_fraction | 0.323 | +| clip_range | 0.068 | +| entropy_loss | -6.51 | +| explained_variance | 0.262 | +| learning_rate | 4.34e-05 | +| loss | -0.0315 | +| n_updates | 70276 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000151 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1409 | +| iterations | 13616 | +| time_elapsed | 19784 | +| total_timesteps | 27885568 | +| train/ | | +| approx_kl | 0.012286276 | +| clip_fraction | 0.353 | +| clip_range | 0.068 | +| entropy_loss | -6.29 | +| explained_variance | 0.315 | +| learning_rate | 4.34e-05 | +| loss | -0.0311 | +| n_updates | 70280 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000153 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1409 | +| iterations | 13617 | +| time_elapsed | 19785 | +| total_timesteps | 27887616 | +| train/ | | +| approx_kl | 0.012616642 | +| clip_fraction | 0.331 | +| clip_range | 0.068 | +| entropy_loss | -5.73 | +| explained_variance | 0.502 | +| learning_rate | 4.34e-05 | +| loss | -0.0277 | +| n_updates | 70284 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000223 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1409 | +| iterations | 13618 | +| time_elapsed | 19787 | +| total_timesteps | 27889664 | +| train/ | | +| approx_kl | 0.015177419 | +| clip_fraction | 0.362 | +| clip_range | 0.068 | +| entropy_loss | -5.94 | +| explained_variance | 0.494 | +| learning_rate | 4.34e-05 | +| loss | -0.0318 | +| n_updates | 70288 | +| policy_gradient_loss | -0.0212 | +| value_loss | 7.24e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1409 | +| iterations | 13619 | +| time_elapsed | 19788 | +| total_timesteps | 27891712 | +| train/ | | +| approx_kl | 0.014536305 | +| clip_fraction | 0.329 | +| clip_range | 0.068 | +| entropy_loss | -6.21 | +| explained_variance | 0.305 | +| learning_rate | 4.34e-05 | +| loss | -0.0291 | +| n_updates | 70292 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000179 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1409 | +| iterations | 13620 | +| time_elapsed | 19790 | +| total_timesteps | 27893760 | +| train/ | | +| approx_kl | 0.014976359 | +| clip_fraction | 0.345 | +| clip_range | 0.068 | +| entropy_loss | -6.41 | +| explained_variance | -0.115 | +| learning_rate | 4.34e-05 | +| loss | -0.0244 | +| n_updates | 70296 | +| policy_gradient_loss | -0.0173 | +| value_loss | 9.86e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1409 | +| iterations | 13621 | +| time_elapsed | 19791 | +| total_timesteps | 27895808 | +| train/ | | +| approx_kl | 0.01175515 | +| clip_fraction | 0.347 | +| clip_range | 0.068 | +| entropy_loss | -5.09 | +| explained_variance | 0.581 | +| learning_rate | 4.34e-05 | +| loss | -0.0249 | +| n_updates | 70300 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000288 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1409 | +| iterations | 13622 | +| time_elapsed | 19793 | +| total_timesteps | 27897856 | +| train/ | | +| approx_kl | 0.012043282 | +| clip_fraction | 0.364 | +| clip_range | 0.068 | +| entropy_loss | -4.7 | +| explained_variance | 0.857 | +| learning_rate | 4.34e-05 | +| loss | -0.0343 | +| n_updates | 70304 | +| policy_gradient_loss | -0.02 | +| value_loss | 5.13e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1409 | +| iterations | 13623 | +| time_elapsed | 19794 | +| total_timesteps | 27899904 | +| train/ | | +| approx_kl | 0.01321831 | +| clip_fraction | 0.335 | +| clip_range | 0.068 | +| entropy_loss | -5.71 | +| explained_variance | 0.344 | +| learning_rate | 4.34e-05 | +| loss | -0.0264 | +| n_updates | 70308 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000195 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1409 | +| iterations | 13624 | +| time_elapsed | 19796 | +| total_timesteps | 27901952 | +| train/ | | +| approx_kl | 0.01308725 | +| clip_fraction | 0.362 | +| clip_range | 0.068 | +| entropy_loss | -6.54 | +| explained_variance | 0.115 | +| learning_rate | 4.34e-05 | +| loss | -0.0324 | +| n_updates | 70312 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.00011 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1409 | +| iterations | 13625 | +| time_elapsed | 19797 | +| total_timesteps | 27904000 | +| train/ | | +| approx_kl | 0.012925126 | +| clip_fraction | 0.319 | +| clip_range | 0.068 | +| entropy_loss | -6.72 | +| explained_variance | 0.0017 | +| learning_rate | 4.34e-05 | +| loss | -0.0283 | +| n_updates | 70316 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000163 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1409 | +| iterations | 13626 | +| time_elapsed | 19799 | +| total_timesteps | 27906048 | +| train/ | | +| approx_kl | 0.013384566 | +| clip_fraction | 0.308 | +| clip_range | 0.068 | +| entropy_loss | -6.33 | +| explained_variance | 0.527 | +| learning_rate | 4.34e-05 | +| loss | -0.0228 | +| n_updates | 70320 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000239 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1409 | +| iterations | 13627 | +| time_elapsed | 19800 | +| total_timesteps | 27908096 | +| train/ | | +| approx_kl | 0.012066508 | +| clip_fraction | 0.31 | +| clip_range | 0.068 | +| entropy_loss | -5.28 | +| explained_variance | 0.479 | +| learning_rate | 4.34e-05 | +| loss | -0.0234 | +| n_updates | 70324 | +| policy_gradient_loss | -0.0131 | +| value_loss | 0.000241 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1409 | +| iterations | 13628 | +| time_elapsed | 19802 | +| total_timesteps | 27910144 | +| train/ | | +| approx_kl | 0.015654357 | +| clip_fraction | 0.362 | +| clip_range | 0.068 | +| entropy_loss | -5.83 | +| explained_variance | 0.53 | +| learning_rate | 4.34e-05 | +| loss | -0.0349 | +| n_updates | 70328 | +| policy_gradient_loss | -0.0213 | +| value_loss | 8.53e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1409 | +| iterations | 13629 | +| time_elapsed | 19803 | +| total_timesteps | 27912192 | +| train/ | | +| approx_kl | 0.01960484 | +| clip_fraction | 0.368 | +| clip_range | 0.068 | +| entropy_loss | -5.94 | +| explained_variance | 0.277 | +| learning_rate | 4.34e-05 | +| loss | -0.0275 | +| n_updates | 70332 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000163 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1409 | +| iterations | 13630 | +| time_elapsed | 19805 | +| total_timesteps | 27914240 | +| train/ | | +| approx_kl | 0.01666536 | +| clip_fraction | 0.351 | +| clip_range | 0.068 | +| entropy_loss | -5.86 | +| explained_variance | 0.63 | +| learning_rate | 4.34e-05 | +| loss | -0.0313 | +| n_updates | 70336 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000125 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1409 | +| iterations | 13631 | +| time_elapsed | 19806 | +| total_timesteps | 27916288 | +| train/ | | +| approx_kl | 0.016709428 | +| clip_fraction | 0.332 | +| clip_range | 0.068 | +| entropy_loss | -6.2 | +| explained_variance | 0.28 | +| learning_rate | 4.34e-05 | +| loss | -0.0303 | +| n_updates | 70340 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000193 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1409 | +| iterations | 13632 | +| time_elapsed | 19808 | +| total_timesteps | 27918336 | +| train/ | | +| approx_kl | 0.012522405 | +| clip_fraction | 0.331 | +| clip_range | 0.068 | +| entropy_loss | -6.13 | +| explained_variance | 0.309 | +| learning_rate | 4.34e-05 | +| loss | -0.0279 | +| n_updates | 70344 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000329 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1409 | +| iterations | 13633 | +| time_elapsed | 19809 | +| total_timesteps | 27920384 | +| train/ | | +| approx_kl | 0.012979068 | +| clip_fraction | 0.328 | +| clip_range | 0.068 | +| entropy_loss | -6.09 | +| explained_variance | 0.439 | +| learning_rate | 4.34e-05 | +| loss | -0.0214 | +| n_updates | 70348 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.000213 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1409 | +| iterations | 13634 | +| time_elapsed | 19811 | +| total_timesteps | 27922432 | +| train/ | | +| approx_kl | 0.012336882 | +| clip_fraction | 0.351 | +| clip_range | 0.068 | +| entropy_loss | -6.59 | +| explained_variance | 0.0425 | +| learning_rate | 4.34e-05 | +| loss | -0.0266 | +| n_updates | 70352 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000162 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1409 | +| iterations | 13635 | +| time_elapsed | 19812 | +| total_timesteps | 27924480 | +| train/ | | +| approx_kl | 0.013426847 | +| clip_fraction | 0.303 | +| clip_range | 0.068 | +| entropy_loss | -5.82 | +| explained_variance | 0.448 | +| learning_rate | 4.34e-05 | +| loss | -0.0191 | +| n_updates | 70356 | +| policy_gradient_loss | -0.0148 | +| value_loss | 0.000271 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1409 | +| iterations | 13636 | +| time_elapsed | 19814 | +| total_timesteps | 27926528 | +| train/ | | +| approx_kl | 0.01613539 | +| clip_fraction | 0.346 | +| clip_range | 0.068 | +| entropy_loss | -5.63 | +| explained_variance | 0.52 | +| learning_rate | 4.34e-05 | +| loss | -0.0275 | +| n_updates | 70360 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000162 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1409 | +| iterations | 13637 | +| time_elapsed | 19815 | +| total_timesteps | 27928576 | +| train/ | | +| approx_kl | 0.015495144 | +| clip_fraction | 0.368 | +| clip_range | 0.068 | +| entropy_loss | -6.01 | +| explained_variance | 0.23 | +| learning_rate | 4.34e-05 | +| loss | -0.0315 | +| n_updates | 70364 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.00017 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1409 | +| iterations | 13638 | +| time_elapsed | 19817 | +| total_timesteps | 27930624 | +| train/ | | +| approx_kl | 0.0117546255 | +| clip_fraction | 0.331 | +| clip_range | 0.068 | +| entropy_loss | -6.65 | +| explained_variance | 0.258 | +| learning_rate | 4.34e-05 | +| loss | -0.0256 | +| n_updates | 70368 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000159 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1409 | +| iterations | 13639 | +| time_elapsed | 19818 | +| total_timesteps | 27932672 | +| train/ | | +| approx_kl | 0.011386501 | +| clip_fraction | 0.329 | +| clip_range | 0.068 | +| entropy_loss | -6.41 | +| explained_variance | 0.168 | +| learning_rate | 4.34e-05 | +| loss | -0.0227 | +| n_updates | 70372 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000237 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1409 | +| iterations | 13640 | +| time_elapsed | 19820 | +| total_timesteps | 27934720 | +| train/ | | +| approx_kl | 0.013407664 | +| clip_fraction | 0.365 | +| clip_range | 0.068 | +| entropy_loss | -6.39 | +| explained_variance | 0.362 | +| learning_rate | 4.34e-05 | +| loss | -0.0327 | +| n_updates | 70376 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000195 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1409 | +| iterations | 13641 | +| time_elapsed | 19821 | +| total_timesteps | 27936768 | +| train/ | | +| approx_kl | 0.016882448 | +| clip_fraction | 0.32 | +| clip_range | 0.068 | +| entropy_loss | -5.87 | +| explained_variance | 0.756 | +| learning_rate | 4.34e-05 | +| loss | -0.0321 | +| n_updates | 70380 | +| policy_gradient_loss | -0.0183 | +| value_loss | 6.93e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1409 | +| iterations | 13642 | +| time_elapsed | 19823 | +| total_timesteps | 27938816 | +| train/ | | +| approx_kl | 0.012675146 | +| clip_fraction | 0.308 | +| clip_range | 0.068 | +| entropy_loss | -6.09 | +| explained_variance | 0.642 | +| learning_rate | 4.34e-05 | +| loss | -0.0256 | +| n_updates | 70384 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.00014 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1409 | +| iterations | 13643 | +| time_elapsed | 19824 | +| total_timesteps | 27940864 | +| train/ | | +| approx_kl | 0.013761948 | +| clip_fraction | 0.365 | +| clip_range | 0.068 | +| entropy_loss | -6.21 | +| explained_variance | -0.0638 | +| learning_rate | 4.34e-05 | +| loss | -0.032 | +| n_updates | 70388 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000144 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1409 | +| iterations | 13644 | +| time_elapsed | 19826 | +| total_timesteps | 27942912 | +| train/ | | +| approx_kl | 0.0135614965 | +| clip_fraction | 0.355 | +| clip_range | 0.068 | +| entropy_loss | -6.03 | +| explained_variance | 0.495 | +| learning_rate | 4.34e-05 | +| loss | -0.031 | +| n_updates | 70392 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000143 | +------------------------------------------ +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1409 | +| iterations | 13645 | +| time_elapsed | 19827 | +| total_timesteps | 27944960 | +| train/ | | +| approx_kl | 0.0134592 | +| clip_fraction | 0.341 | +| clip_range | 0.068 | +| entropy_loss | -5.64 | +| explained_variance | 0.297 | +| learning_rate | 4.34e-05 | +| loss | -0.0315 | +| n_updates | 70396 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000319 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1409 | +| iterations | 13646 | +| time_elapsed | 19829 | +| total_timesteps | 27947008 | +| train/ | | +| approx_kl | 0.014275419 | +| clip_fraction | 0.375 | +| clip_range | 0.068 | +| entropy_loss | -6.06 | +| explained_variance | 0.49 | +| learning_rate | 4.34e-05 | +| loss | -0.0327 | +| n_updates | 70400 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000132 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1409 | +| iterations | 13647 | +| time_elapsed | 19830 | +| total_timesteps | 27949056 | +| train/ | | +| approx_kl | 0.012668512 | +| clip_fraction | 0.371 | +| clip_range | 0.068 | +| entropy_loss | -5.85 | +| explained_variance | 0.602 | +| learning_rate | 4.34e-05 | +| loss | -0.0377 | +| n_updates | 70404 | +| policy_gradient_loss | -0.0197 | +| value_loss | 9.52e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1409 | +| iterations | 13648 | +| time_elapsed | 19832 | +| total_timesteps | 27951104 | +| train/ | | +| approx_kl | 0.015535425 | +| clip_fraction | 0.329 | +| clip_range | 0.068 | +| entropy_loss | -6.14 | +| explained_variance | 0.434 | +| learning_rate | 4.34e-05 | +| loss | -0.0226 | +| n_updates | 70408 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000189 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1409 | +| iterations | 13649 | +| time_elapsed | 19833 | +| total_timesteps | 27953152 | +| train/ | | +| approx_kl | 0.013352236 | +| clip_fraction | 0.357 | +| clip_range | 0.068 | +| entropy_loss | -6.24 | +| explained_variance | 0.31 | +| learning_rate | 4.34e-05 | +| loss | -0.0291 | +| n_updates | 70412 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000246 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1409 | +| iterations | 13650 | +| time_elapsed | 19835 | +| total_timesteps | 27955200 | +| train/ | | +| approx_kl | 0.011988847 | +| clip_fraction | 0.346 | +| clip_range | 0.068 | +| entropy_loss | -6.19 | +| explained_variance | 0.313 | +| learning_rate | 4.34e-05 | +| loss | -0.0381 | +| n_updates | 70416 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000164 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1409 | +| iterations | 13651 | +| time_elapsed | 19836 | +| total_timesteps | 27957248 | +| train/ | | +| approx_kl | 0.016352184 | +| clip_fraction | 0.361 | +| clip_range | 0.068 | +| entropy_loss | -6.19 | +| explained_variance | 0.323 | +| learning_rate | 4.34e-05 | +| loss | -0.0337 | +| n_updates | 70420 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000129 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1409 | +| iterations | 13652 | +| time_elapsed | 19838 | +| total_timesteps | 27959296 | +| train/ | | +| approx_kl | 0.01565848 | +| clip_fraction | 0.382 | +| clip_range | 0.068 | +| entropy_loss | -6.23 | +| explained_variance | 0.252 | +| learning_rate | 4.34e-05 | +| loss | -0.0295 | +| n_updates | 70424 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000165 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1409 | +| iterations | 13653 | +| time_elapsed | 19840 | +| total_timesteps | 27961344 | +| train/ | | +| approx_kl | 0.009188153 | +| clip_fraction | 0.309 | +| clip_range | 0.068 | +| entropy_loss | -6.51 | +| explained_variance | 0.427 | +| learning_rate | 4.34e-05 | +| loss | -0.0259 | +| n_updates | 70428 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000245 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1409 | +| iterations | 13654 | +| time_elapsed | 19841 | +| total_timesteps | 27963392 | +| train/ | | +| approx_kl | 0.010235929 | +| clip_fraction | 0.254 | +| clip_range | 0.068 | +| entropy_loss | -5.71 | +| explained_variance | 0.486 | +| learning_rate | 4.34e-05 | +| loss | -0.0274 | +| n_updates | 70432 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000228 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1409 | +| iterations | 13655 | +| time_elapsed | 19843 | +| total_timesteps | 27965440 | +| train/ | | +| approx_kl | 0.016379211 | +| clip_fraction | 0.358 | +| clip_range | 0.068 | +| entropy_loss | -6.2 | +| explained_variance | 0.404 | +| learning_rate | 4.34e-05 | +| loss | -0.0337 | +| n_updates | 70436 | +| policy_gradient_loss | -0.0209 | +| value_loss | 8e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1409 | +| iterations | 13656 | +| time_elapsed | 19844 | +| total_timesteps | 27967488 | +| train/ | | +| approx_kl | 0.012118636 | +| clip_fraction | 0.33 | +| clip_range | 0.068 | +| entropy_loss | -6.64 | +| explained_variance | 0.375 | +| learning_rate | 4.34e-05 | +| loss | -0.0316 | +| n_updates | 70440 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000202 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1409 | +| iterations | 13657 | +| time_elapsed | 19846 | +| total_timesteps | 27969536 | +| train/ | | +| approx_kl | 0.0128531065 | +| clip_fraction | 0.344 | +| clip_range | 0.068 | +| entropy_loss | -5.92 | +| explained_variance | 0.756 | +| learning_rate | 4.34e-05 | +| loss | -0.0296 | +| n_updates | 70444 | +| policy_gradient_loss | -0.0189 | +| value_loss | 6.34e-05 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1409 | +| iterations | 13658 | +| time_elapsed | 19847 | +| total_timesteps | 27971584 | +| train/ | | +| approx_kl | 0.0151361255 | +| clip_fraction | 0.343 | +| clip_range | 0.068 | +| entropy_loss | -5.79 | +| explained_variance | 0.548 | +| learning_rate | 4.34e-05 | +| loss | -0.0286 | +| n_updates | 70448 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000136 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1409 | +| iterations | 13659 | +| time_elapsed | 19849 | +| total_timesteps | 27973632 | +| train/ | | +| approx_kl | 0.011483519 | +| clip_fraction | 0.324 | +| clip_range | 0.068 | +| entropy_loss | -5.79 | +| explained_variance | 0.722 | +| learning_rate | 4.34e-05 | +| loss | -0.0225 | +| n_updates | 70452 | +| policy_gradient_loss | -0.0155 | +| value_loss | 9.2e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1409 | +| iterations | 13660 | +| time_elapsed | 19850 | +| total_timesteps | 27975680 | +| train/ | | +| approx_kl | 0.011937713 | +| clip_fraction | 0.312 | +| clip_range | 0.068 | +| entropy_loss | -6.16 | +| explained_variance | -0.0544 | +| learning_rate | 4.34e-05 | +| loss | -0.0266 | +| n_updates | 70456 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000101 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1409 | +| iterations | 13661 | +| time_elapsed | 19852 | +| total_timesteps | 27977728 | +| train/ | | +| approx_kl | 0.012866022 | +| clip_fraction | 0.364 | +| clip_range | 0.068 | +| entropy_loss | -6.48 | +| explained_variance | 0.629 | +| learning_rate | 4.34e-05 | +| loss | -0.0302 | +| n_updates | 70460 | +| policy_gradient_loss | -0.0196 | +| value_loss | 6.22e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1409 | +| iterations | 13662 | +| time_elapsed | 19853 | +| total_timesteps | 27979776 | +| train/ | | +| approx_kl | 0.012865229 | +| clip_fraction | 0.351 | +| clip_range | 0.068 | +| entropy_loss | -5.95 | +| explained_variance | 0.538 | +| learning_rate | 4.34e-05 | +| loss | -0.0283 | +| n_updates | 70464 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000157 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1409 | +| iterations | 13663 | +| time_elapsed | 19855 | +| total_timesteps | 27981824 | +| train/ | | +| approx_kl | 0.012730932 | +| clip_fraction | 0.316 | +| clip_range | 0.068 | +| entropy_loss | -5.09 | +| explained_variance | 0.697 | +| learning_rate | 4.34e-05 | +| loss | -0.022 | +| n_updates | 70468 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.00016 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1409 | +| iterations | 13664 | +| time_elapsed | 19856 | +| total_timesteps | 27983872 | +| train/ | | +| approx_kl | 0.010209026 | +| clip_fraction | 0.309 | +| clip_range | 0.068 | +| entropy_loss | -5.77 | +| explained_variance | 0.509 | +| learning_rate | 4.34e-05 | +| loss | -0.027 | +| n_updates | 70472 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000183 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1409 | +| iterations | 13665 | +| time_elapsed | 19858 | +| total_timesteps | 27985920 | +| train/ | | +| approx_kl | 0.011371117 | +| clip_fraction | 0.345 | +| clip_range | 0.068 | +| entropy_loss | -6.06 | +| explained_variance | 0.221 | +| learning_rate | 4.34e-05 | +| loss | -0.0311 | +| n_updates | 70476 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000207 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1409 | +| iterations | 13666 | +| time_elapsed | 19859 | +| total_timesteps | 27987968 | +| train/ | | +| approx_kl | 0.015609126 | +| clip_fraction | 0.343 | +| clip_range | 0.068 | +| entropy_loss | -6.2 | +| explained_variance | 0.437 | +| learning_rate | 4.34e-05 | +| loss | -0.0366 | +| n_updates | 70480 | +| policy_gradient_loss | -0.0185 | +| value_loss | 8.69e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1409 | +| iterations | 13667 | +| time_elapsed | 19861 | +| total_timesteps | 27990016 | +| train/ | | +| approx_kl | 0.012237361 | +| clip_fraction | 0.358 | +| clip_range | 0.068 | +| entropy_loss | -6.02 | +| explained_variance | 0.376 | +| learning_rate | 4.34e-05 | +| loss | -0.0249 | +| n_updates | 70484 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000226 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1409 | +| iterations | 13668 | +| time_elapsed | 19862 | +| total_timesteps | 27992064 | +| train/ | | +| approx_kl | 0.014471546 | +| clip_fraction | 0.357 | +| clip_range | 0.068 | +| entropy_loss | -6.11 | +| explained_variance | 0.336 | +| learning_rate | 4.34e-05 | +| loss | -0.0346 | +| n_updates | 70488 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000117 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1409 | +| iterations | 13669 | +| time_elapsed | 19864 | +| total_timesteps | 27994112 | +| train/ | | +| approx_kl | 0.014397693 | +| clip_fraction | 0.352 | +| clip_range | 0.068 | +| entropy_loss | -6.28 | +| explained_variance | 0.247 | +| learning_rate | 4.34e-05 | +| loss | -0.0276 | +| n_updates | 70492 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000191 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1409 | +| iterations | 13670 | +| time_elapsed | 19865 | +| total_timesteps | 27996160 | +| train/ | | +| approx_kl | 0.013959117 | +| clip_fraction | 0.378 | +| clip_range | 0.068 | +| entropy_loss | -6.03 | +| explained_variance | 0.375 | +| learning_rate | 4.34e-05 | +| loss | -0.0345 | +| n_updates | 70496 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000114 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1409 | +| iterations | 13671 | +| time_elapsed | 19867 | +| total_timesteps | 27998208 | +| train/ | | +| approx_kl | 0.007976601 | +| clip_fraction | 0.308 | +| clip_range | 0.068 | +| entropy_loss | -5.79 | +| explained_variance | 0.488 | +| learning_rate | 4.34e-05 | +| loss | -0.0221 | +| n_updates | 70500 | +| policy_gradient_loss | -0.0134 | +| value_loss | 0.000315 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1409 | +| iterations | 13672 | +| time_elapsed | 19869 | +| total_timesteps | 28000256 | +| train/ | | +| approx_kl | 0.011495229 | +| clip_fraction | 0.331 | +| clip_range | 0.068 | +| entropy_loss | -5.8 | +| explained_variance | 0.604 | +| learning_rate | 4.34e-05 | +| loss | -0.0252 | +| n_updates | 70504 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000141 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1409 | +| iterations | 13673 | +| time_elapsed | 19870 | +| total_timesteps | 28002304 | +| train/ | | +| approx_kl | 0.0136976 | +| clip_fraction | 0.367 | +| clip_range | 0.068 | +| entropy_loss | -6.46 | +| explained_variance | 0.472 | +| learning_rate | 4.33e-05 | +| loss | -0.0388 | +| n_updates | 70508 | +| policy_gradient_loss | -0.023 | +| value_loss | 7.89e-05 | +--------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1409 | +| iterations | 13674 | +| time_elapsed | 19872 | +| total_timesteps | 28004352 | +| train/ | | +| approx_kl | 0.01403687 | +| clip_fraction | 0.358 | +| clip_range | 0.068 | +| entropy_loss | -6.15 | +| explained_variance | 0.517 | +| learning_rate | 4.33e-05 | +| loss | -0.0336 | +| n_updates | 70512 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000129 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1409 | +| iterations | 13675 | +| time_elapsed | 19873 | +| total_timesteps | 28006400 | +| train/ | | +| approx_kl | 0.012840161 | +| clip_fraction | 0.344 | +| clip_range | 0.068 | +| entropy_loss | -6.43 | +| explained_variance | 0.429 | +| learning_rate | 4.33e-05 | +| loss | -0.0317 | +| n_updates | 70516 | +| policy_gradient_loss | -0.0196 | +| value_loss | 9.93e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1409 | +| iterations | 13676 | +| time_elapsed | 19875 | +| total_timesteps | 28008448 | +| train/ | | +| approx_kl | 0.01487876 | +| clip_fraction | 0.341 | +| clip_range | 0.068 | +| entropy_loss | -6.46 | +| explained_variance | 0.255 | +| learning_rate | 4.33e-05 | +| loss | -0.0257 | +| n_updates | 70520 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000156 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1409 | +| iterations | 13677 | +| time_elapsed | 19876 | +| total_timesteps | 28010496 | +| train/ | | +| approx_kl | 0.01180864 | +| clip_fraction | 0.342 | +| clip_range | 0.068 | +| entropy_loss | -6.12 | +| explained_variance | 0.339 | +| learning_rate | 4.33e-05 | +| loss | -0.0239 | +| n_updates | 70524 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000361 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1409 | +| iterations | 13678 | +| time_elapsed | 19878 | +| total_timesteps | 28012544 | +| train/ | | +| approx_kl | 0.012231775 | +| clip_fraction | 0.351 | +| clip_range | 0.068 | +| entropy_loss | -6.09 | +| explained_variance | 0.547 | +| learning_rate | 4.33e-05 | +| loss | -0.0313 | +| n_updates | 70528 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000107 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1409 | +| iterations | 13679 | +| time_elapsed | 19879 | +| total_timesteps | 28014592 | +| train/ | | +| approx_kl | 0.010544397 | +| clip_fraction | 0.314 | +| clip_range | 0.068 | +| entropy_loss | -5.66 | +| explained_variance | 0.418 | +| learning_rate | 4.33e-05 | +| loss | -0.0256 | +| n_updates | 70532 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.000355 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1409 | +| iterations | 13680 | +| time_elapsed | 19881 | +| total_timesteps | 28016640 | +| train/ | | +| approx_kl | 0.012909317 | +| clip_fraction | 0.377 | +| clip_range | 0.068 | +| entropy_loss | -5.73 | +| explained_variance | 0.608 | +| learning_rate | 4.33e-05 | +| loss | -0.039 | +| n_updates | 70536 | +| policy_gradient_loss | -0.0221 | +| value_loss | 7.61e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1409 | +| iterations | 13681 | +| time_elapsed | 19882 | +| total_timesteps | 28018688 | +| train/ | | +| approx_kl | 0.014798122 | +| clip_fraction | 0.375 | +| clip_range | 0.068 | +| entropy_loss | -6.69 | +| explained_variance | -0.196 | +| learning_rate | 4.33e-05 | +| loss | -0.0323 | +| n_updates | 70540 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000132 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1409 | +| iterations | 13682 | +| time_elapsed | 19884 | +| total_timesteps | 28020736 | +| train/ | | +| approx_kl | 0.015794095 | +| clip_fraction | 0.369 | +| clip_range | 0.068 | +| entropy_loss | -6.29 | +| explained_variance | 0.466 | +| learning_rate | 4.33e-05 | +| loss | -0.0359 | +| n_updates | 70544 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000121 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1409 | +| iterations | 13683 | +| time_elapsed | 19885 | +| total_timesteps | 28022784 | +| train/ | | +| approx_kl | 0.014700025 | +| clip_fraction | 0.351 | +| clip_range | 0.068 | +| entropy_loss | -5.42 | +| explained_variance | 0.578 | +| learning_rate | 4.33e-05 | +| loss | -0.0247 | +| n_updates | 70548 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000233 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1409 | +| iterations | 13684 | +| time_elapsed | 19887 | +| total_timesteps | 28024832 | +| train/ | | +| approx_kl | 0.01612062 | +| clip_fraction | 0.307 | +| clip_range | 0.068 | +| entropy_loss | -5.52 | +| explained_variance | 0.356 | +| learning_rate | 4.33e-05 | +| loss | -0.0273 | +| n_updates | 70552 | +| policy_gradient_loss | -0.0148 | +| value_loss | 0.000296 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1409 | +| iterations | 13685 | +| time_elapsed | 19888 | +| total_timesteps | 28026880 | +| train/ | | +| approx_kl | 0.014023455 | +| clip_fraction | 0.339 | +| clip_range | 0.068 | +| entropy_loss | -5.53 | +| explained_variance | 0.696 | +| learning_rate | 4.33e-05 | +| loss | -0.0293 | +| n_updates | 70556 | +| policy_gradient_loss | -0.02 | +| value_loss | 7.74e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1409 | +| iterations | 13686 | +| time_elapsed | 19890 | +| total_timesteps | 28028928 | +| train/ | | +| approx_kl | 0.015414969 | +| clip_fraction | 0.363 | +| clip_range | 0.068 | +| entropy_loss | -6.11 | +| explained_variance | 0.323 | +| learning_rate | 4.33e-05 | +| loss | -0.0338 | +| n_updates | 70560 | +| policy_gradient_loss | -0.0212 | +| value_loss | 9.81e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1409 | +| iterations | 13687 | +| time_elapsed | 19891 | +| total_timesteps | 28030976 | +| train/ | | +| approx_kl | 0.017006993 | +| clip_fraction | 0.375 | +| clip_range | 0.068 | +| entropy_loss | -6.2 | +| explained_variance | 0.24 | +| learning_rate | 4.33e-05 | +| loss | -0.033 | +| n_updates | 70564 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000191 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1409 | +| iterations | 13688 | +| time_elapsed | 19893 | +| total_timesteps | 28033024 | +| train/ | | +| approx_kl | 0.018130511 | +| clip_fraction | 0.387 | +| clip_range | 0.068 | +| entropy_loss | -6.19 | +| explained_variance | 0.489 | +| learning_rate | 4.33e-05 | +| loss | -0.0352 | +| n_updates | 70568 | +| policy_gradient_loss | -0.0227 | +| value_loss | 7.86e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1409 | +| iterations | 13689 | +| time_elapsed | 19894 | +| total_timesteps | 28035072 | +| train/ | | +| approx_kl | 0.017278556 | +| clip_fraction | 0.404 | +| clip_range | 0.068 | +| entropy_loss | -6.08 | +| explained_variance | 0.0215 | +| learning_rate | 4.33e-05 | +| loss | -0.0354 | +| n_updates | 70572 | +| policy_gradient_loss | -0.0229 | +| value_loss | 7e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1409 | +| iterations | 13690 | +| time_elapsed | 19896 | +| total_timesteps | 28037120 | +| train/ | | +| approx_kl | 0.01439292 | +| clip_fraction | 0.326 | +| clip_range | 0.068 | +| entropy_loss | -6.26 | +| explained_variance | 0.2 | +| learning_rate | 4.33e-05 | +| loss | -0.0258 | +| n_updates | 70576 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000159 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1409 | +| iterations | 13691 | +| time_elapsed | 19898 | +| total_timesteps | 28039168 | +| train/ | | +| approx_kl | 0.017153332 | +| clip_fraction | 0.326 | +| clip_range | 0.068 | +| entropy_loss | -5.79 | +| explained_variance | 0.522 | +| learning_rate | 4.33e-05 | +| loss | -0.0281 | +| n_updates | 70580 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000173 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1409 | +| iterations | 13692 | +| time_elapsed | 19899 | +| total_timesteps | 28041216 | +| train/ | | +| approx_kl | 0.016051047 | +| clip_fraction | 0.353 | +| clip_range | 0.068 | +| entropy_loss | -6.27 | +| explained_variance | -0.224 | +| learning_rate | 4.33e-05 | +| loss | -0.0336 | +| n_updates | 70584 | +| policy_gradient_loss | -0.0223 | +| value_loss | 8.65e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1409 | +| iterations | 13693 | +| time_elapsed | 19901 | +| total_timesteps | 28043264 | +| train/ | | +| approx_kl | 0.013955903 | +| clip_fraction | 0.333 | +| clip_range | 0.068 | +| entropy_loss | -5.92 | +| explained_variance | 0.664 | +| learning_rate | 4.33e-05 | +| loss | -0.0242 | +| n_updates | 70588 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000163 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1409 | +| iterations | 13694 | +| time_elapsed | 19902 | +| total_timesteps | 28045312 | +| train/ | | +| approx_kl | 0.015605909 | +| clip_fraction | 0.341 | +| clip_range | 0.068 | +| entropy_loss | -5.54 | +| explained_variance | 0.248 | +| learning_rate | 4.33e-05 | +| loss | -0.0278 | +| n_updates | 70592 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000159 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1409 | +| iterations | 13695 | +| time_elapsed | 19904 | +| total_timesteps | 28047360 | +| train/ | | +| approx_kl | 0.0144690955 | +| clip_fraction | 0.346 | +| clip_range | 0.068 | +| entropy_loss | -5.85 | +| explained_variance | 0.425 | +| learning_rate | 4.33e-05 | +| loss | -0.0316 | +| n_updates | 70596 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000173 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1409 | +| iterations | 13696 | +| time_elapsed | 19905 | +| total_timesteps | 28049408 | +| train/ | | +| approx_kl | 0.017501116 | +| clip_fraction | 0.358 | +| clip_range | 0.068 | +| entropy_loss | -5.87 | +| explained_variance | 0.293 | +| learning_rate | 4.33e-05 | +| loss | -0.0337 | +| n_updates | 70600 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000126 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1409 | +| iterations | 13697 | +| time_elapsed | 19907 | +| total_timesteps | 28051456 | +| train/ | | +| approx_kl | 0.0110753905 | +| clip_fraction | 0.34 | +| clip_range | 0.068 | +| entropy_loss | -6.7 | +| explained_variance | 0.168 | +| learning_rate | 4.33e-05 | +| loss | -0.0267 | +| n_updates | 70604 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000301 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1409 | +| iterations | 13698 | +| time_elapsed | 19908 | +| total_timesteps | 28053504 | +| train/ | | +| approx_kl | 0.011442119 | +| clip_fraction | 0.321 | +| clip_range | 0.068 | +| entropy_loss | -5.98 | +| explained_variance | 0.37 | +| learning_rate | 4.33e-05 | +| loss | -0.0246 | +| n_updates | 70608 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000364 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1409 | +| iterations | 13699 | +| time_elapsed | 19910 | +| total_timesteps | 28055552 | +| train/ | | +| approx_kl | 0.010150755 | +| clip_fraction | 0.335 | +| clip_range | 0.068 | +| entropy_loss | -6.41 | +| explained_variance | 0.382 | +| learning_rate | 4.33e-05 | +| loss | -0.0284 | +| n_updates | 70612 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000184 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1409 | +| iterations | 13700 | +| time_elapsed | 19911 | +| total_timesteps | 28057600 | +| train/ | | +| approx_kl | 0.014265591 | +| clip_fraction | 0.353 | +| clip_range | 0.068 | +| entropy_loss | -6.45 | +| explained_variance | 0.475 | +| learning_rate | 4.33e-05 | +| loss | -0.0348 | +| n_updates | 70616 | +| policy_gradient_loss | -0.0198 | +| value_loss | 7.91e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1409 | +| iterations | 13701 | +| time_elapsed | 19913 | +| total_timesteps | 28059648 | +| train/ | | +| approx_kl | 0.018190008 | +| clip_fraction | 0.347 | +| clip_range | 0.068 | +| entropy_loss | -6.32 | +| explained_variance | 0.173 | +| learning_rate | 4.33e-05 | +| loss | -0.0318 | +| n_updates | 70620 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000227 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1409 | +| iterations | 13702 | +| time_elapsed | 19914 | +| total_timesteps | 28061696 | +| train/ | | +| approx_kl | 0.017401997 | +| clip_fraction | 0.356 | +| clip_range | 0.068 | +| entropy_loss | -6.52 | +| explained_variance | 0.498 | +| learning_rate | 4.33e-05 | +| loss | -0.0266 | +| n_updates | 70624 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000112 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1409 | +| iterations | 13703 | +| time_elapsed | 19916 | +| total_timesteps | 28063744 | +| train/ | | +| approx_kl | 0.01285679 | +| clip_fraction | 0.319 | +| clip_range | 0.068 | +| entropy_loss | -6.3 | +| explained_variance | 0.377 | +| learning_rate | 4.33e-05 | +| loss | -0.0188 | +| n_updates | 70628 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000121 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1409 | +| iterations | 13704 | +| time_elapsed | 19917 | +| total_timesteps | 28065792 | +| train/ | | +| approx_kl | 0.013956735 | +| clip_fraction | 0.325 | +| clip_range | 0.068 | +| entropy_loss | -5.32 | +| explained_variance | 0.652 | +| learning_rate | 4.33e-05 | +| loss | -0.0252 | +| n_updates | 70632 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000196 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1409 | +| iterations | 13705 | +| time_elapsed | 19919 | +| total_timesteps | 28067840 | +| train/ | | +| approx_kl | 0.014474793 | +| clip_fraction | 0.363 | +| clip_range | 0.068 | +| entropy_loss | -6.04 | +| explained_variance | -0.0999 | +| learning_rate | 4.33e-05 | +| loss | -0.0308 | +| n_updates | 70636 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000187 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1409 | +| iterations | 13706 | +| time_elapsed | 19920 | +| total_timesteps | 28069888 | +| train/ | | +| approx_kl | 0.014423764 | +| clip_fraction | 0.326 | +| clip_range | 0.068 | +| entropy_loss | -5.65 | +| explained_variance | 0.59 | +| learning_rate | 4.33e-05 | +| loss | -0.0276 | +| n_updates | 70640 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000205 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1409 | +| iterations | 13707 | +| time_elapsed | 19922 | +| total_timesteps | 28071936 | +| train/ | | +| approx_kl | 0.017908413 | +| clip_fraction | 0.364 | +| clip_range | 0.068 | +| entropy_loss | -6.21 | +| explained_variance | 0.00721 | +| learning_rate | 4.33e-05 | +| loss | -0.0327 | +| n_updates | 70644 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000275 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1409 | +| iterations | 13708 | +| time_elapsed | 19923 | +| total_timesteps | 28073984 | +| train/ | | +| approx_kl | 0.011192877 | +| clip_fraction | 0.342 | +| clip_range | 0.068 | +| entropy_loss | -6.5 | +| explained_variance | 0.245 | +| learning_rate | 4.33e-05 | +| loss | -0.025 | +| n_updates | 70648 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000277 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1409 | +| iterations | 13709 | +| time_elapsed | 19925 | +| total_timesteps | 28076032 | +| train/ | | +| approx_kl | 0.010355132 | +| clip_fraction | 0.309 | +| clip_range | 0.068 | +| entropy_loss | -5.99 | +| explained_variance | 0.49 | +| learning_rate | 4.33e-05 | +| loss | -0.0268 | +| n_updates | 70652 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000304 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1409 | +| iterations | 13710 | +| time_elapsed | 19926 | +| total_timesteps | 28078080 | +| train/ | | +| approx_kl | 0.0143664805 | +| clip_fraction | 0.367 | +| clip_range | 0.068 | +| entropy_loss | -6.42 | +| explained_variance | 0.384 | +| learning_rate | 4.33e-05 | +| loss | -0.0322 | +| n_updates | 70656 | +| policy_gradient_loss | -0.0223 | +| value_loss | 0.000102 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1409 | +| iterations | 13711 | +| time_elapsed | 19928 | +| total_timesteps | 28080128 | +| train/ | | +| approx_kl | 0.01062611 | +| clip_fraction | 0.323 | +| clip_range | 0.068 | +| entropy_loss | -6.23 | +| explained_variance | 0.226 | +| learning_rate | 4.33e-05 | +| loss | -0.0273 | +| n_updates | 70660 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000336 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1409 | +| iterations | 13712 | +| time_elapsed | 19929 | +| total_timesteps | 28082176 | +| train/ | | +| approx_kl | 0.01226128 | +| clip_fraction | 0.315 | +| clip_range | 0.068 | +| entropy_loss | -5.62 | +| explained_variance | 0.504 | +| learning_rate | 4.33e-05 | +| loss | -0.0235 | +| n_updates | 70664 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000308 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1409 | +| iterations | 13713 | +| time_elapsed | 19931 | +| total_timesteps | 28084224 | +| train/ | | +| approx_kl | 0.012206119 | +| clip_fraction | 0.341 | +| clip_range | 0.068 | +| entropy_loss | -5.88 | +| explained_variance | 0.289 | +| learning_rate | 4.33e-05 | +| loss | -0.0278 | +| n_updates | 70668 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000213 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1409 | +| iterations | 13714 | +| time_elapsed | 19932 | +| total_timesteps | 28086272 | +| train/ | | +| approx_kl | 0.015598364 | +| clip_fraction | 0.373 | +| clip_range | 0.068 | +| entropy_loss | -6.46 | +| explained_variance | -0.0633 | +| learning_rate | 4.33e-05 | +| loss | -0.0353 | +| n_updates | 70672 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000178 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1409 | +| iterations | 13715 | +| time_elapsed | 19934 | +| total_timesteps | 28088320 | +| train/ | | +| approx_kl | 0.016373929 | +| clip_fraction | 0.338 | +| clip_range | 0.068 | +| entropy_loss | -6.52 | +| explained_variance | 0.234 | +| learning_rate | 4.33e-05 | +| loss | -0.0292 | +| n_updates | 70676 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000209 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1409 | +| iterations | 13716 | +| time_elapsed | 19935 | +| total_timesteps | 28090368 | +| train/ | | +| approx_kl | 0.012907878 | +| clip_fraction | 0.339 | +| clip_range | 0.068 | +| entropy_loss | -6.49 | +| explained_variance | 0.458 | +| learning_rate | 4.33e-05 | +| loss | -0.0278 | +| n_updates | 70680 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000191 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1409 | +| iterations | 13717 | +| time_elapsed | 19937 | +| total_timesteps | 28092416 | +| train/ | | +| approx_kl | 0.014222905 | +| clip_fraction | 0.354 | +| clip_range | 0.068 | +| entropy_loss | -5.97 | +| explained_variance | 0.531 | +| learning_rate | 4.33e-05 | +| loss | -0.032 | +| n_updates | 70684 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000135 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1409 | +| iterations | 13718 | +| time_elapsed | 19938 | +| total_timesteps | 28094464 | +| train/ | | +| approx_kl | 0.01863141 | +| clip_fraction | 0.343 | +| clip_range | 0.068 | +| entropy_loss | -6.05 | +| explained_variance | 0.47 | +| learning_rate | 4.33e-05 | +| loss | -0.026 | +| n_updates | 70688 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000151 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1409 | +| iterations | 13719 | +| time_elapsed | 19940 | +| total_timesteps | 28096512 | +| train/ | | +| approx_kl | 0.018207807 | +| clip_fraction | 0.349 | +| clip_range | 0.068 | +| entropy_loss | -6.17 | +| explained_variance | 0.419 | +| learning_rate | 4.33e-05 | +| loss | -0.0319 | +| n_updates | 70692 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000143 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1409 | +| iterations | 13720 | +| time_elapsed | 19941 | +| total_timesteps | 28098560 | +| train/ | | +| approx_kl | 0.013580757 | +| clip_fraction | 0.376 | +| clip_range | 0.068 | +| entropy_loss | -6.26 | +| explained_variance | 0.592 | +| learning_rate | 4.33e-05 | +| loss | -0.0395 | +| n_updates | 70696 | +| policy_gradient_loss | -0.021 | +| value_loss | 9.05e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1409 | +| iterations | 13721 | +| time_elapsed | 19943 | +| total_timesteps | 28100608 | +| train/ | | +| approx_kl | 0.011972477 | +| clip_fraction | 0.353 | +| clip_range | 0.068 | +| entropy_loss | -6.97 | +| explained_variance | -0.172 | +| learning_rate | 4.33e-05 | +| loss | -0.0266 | +| n_updates | 70700 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000165 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1409 | +| iterations | 13722 | +| time_elapsed | 19944 | +| total_timesteps | 28102656 | +| train/ | | +| approx_kl | 0.012406435 | +| clip_fraction | 0.313 | +| clip_range | 0.068 | +| entropy_loss | -6.21 | +| explained_variance | 0.482 | +| learning_rate | 4.33e-05 | +| loss | -0.0322 | +| n_updates | 70704 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000249 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1409 | +| iterations | 13723 | +| time_elapsed | 19946 | +| total_timesteps | 28104704 | +| train/ | | +| approx_kl | 0.017795125 | +| clip_fraction | 0.375 | +| clip_range | 0.068 | +| entropy_loss | -5.84 | +| explained_variance | 0.629 | +| learning_rate | 4.33e-05 | +| loss | -0.0369 | +| n_updates | 70708 | +| policy_gradient_loss | -0.0222 | +| value_loss | 8.14e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1409 | +| iterations | 13724 | +| time_elapsed | 19947 | +| total_timesteps | 28106752 | +| train/ | | +| approx_kl | 0.018139835 | +| clip_fraction | 0.355 | +| clip_range | 0.068 | +| entropy_loss | -6.21 | +| explained_variance | 0.343 | +| learning_rate | 4.33e-05 | +| loss | -0.0285 | +| n_updates | 70712 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000136 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1408 | +| iterations | 13725 | +| time_elapsed | 19949 | +| total_timesteps | 28108800 | +| train/ | | +| approx_kl | 0.012774057 | +| clip_fraction | 0.353 | +| clip_range | 0.068 | +| entropy_loss | -5.78 | +| explained_variance | 0.394 | +| learning_rate | 4.33e-05 | +| loss | -0.0301 | +| n_updates | 70716 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000199 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1408 | +| iterations | 13726 | +| time_elapsed | 19951 | +| total_timesteps | 28110848 | +| train/ | | +| approx_kl | 0.011478538 | +| clip_fraction | 0.338 | +| clip_range | 0.068 | +| entropy_loss | -6.11 | +| explained_variance | 0.563 | +| learning_rate | 4.33e-05 | +| loss | -0.0335 | +| n_updates | 70720 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000116 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1408 | +| iterations | 13727 | +| time_elapsed | 19952 | +| total_timesteps | 28112896 | +| train/ | | +| approx_kl | 0.011504205 | +| clip_fraction | 0.343 | +| clip_range | 0.068 | +| entropy_loss | -6.55 | +| explained_variance | 0.404 | +| learning_rate | 4.33e-05 | +| loss | -0.0294 | +| n_updates | 70724 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000101 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1408 | +| iterations | 13728 | +| time_elapsed | 19954 | +| total_timesteps | 28114944 | +| train/ | | +| approx_kl | 0.014259428 | +| clip_fraction | 0.313 | +| clip_range | 0.068 | +| entropy_loss | -6.12 | +| explained_variance | 0.774 | +| learning_rate | 4.33e-05 | +| loss | -0.0221 | +| n_updates | 70728 | +| policy_gradient_loss | -0.0165 | +| value_loss | 6.82e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1408 | +| iterations | 13729 | +| time_elapsed | 19955 | +| total_timesteps | 28116992 | +| train/ | | +| approx_kl | 0.008767281 | +| clip_fraction | 0.293 | +| clip_range | 0.068 | +| entropy_loss | -6.2 | +| explained_variance | 0.439 | +| learning_rate | 4.33e-05 | +| loss | -0.0275 | +| n_updates | 70732 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000226 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1408 | +| iterations | 13730 | +| time_elapsed | 19957 | +| total_timesteps | 28119040 | +| train/ | | +| approx_kl | 0.011618203 | +| clip_fraction | 0.321 | +| clip_range | 0.068 | +| entropy_loss | -6.48 | +| explained_variance | 0.0839 | +| learning_rate | 4.33e-05 | +| loss | -0.0251 | +| n_updates | 70736 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000183 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1408 | +| iterations | 13731 | +| time_elapsed | 19958 | +| total_timesteps | 28121088 | +| train/ | | +| approx_kl | 0.012438105 | +| clip_fraction | 0.366 | +| clip_range | 0.068 | +| entropy_loss | -5.99 | +| explained_variance | 0.766 | +| learning_rate | 4.33e-05 | +| loss | -0.0289 | +| n_updates | 70740 | +| policy_gradient_loss | -0.0204 | +| value_loss | 8.17e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1408 | +| iterations | 13732 | +| time_elapsed | 19960 | +| total_timesteps | 28123136 | +| train/ | | +| approx_kl | 0.015516804 | +| clip_fraction | 0.337 | +| clip_range | 0.068 | +| entropy_loss | -6.19 | +| explained_variance | 0.252 | +| learning_rate | 4.33e-05 | +| loss | -0.0264 | +| n_updates | 70744 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000202 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1408 | +| iterations | 13733 | +| time_elapsed | 19961 | +| total_timesteps | 28125184 | +| train/ | | +| approx_kl | 0.013670188 | +| clip_fraction | 0.351 | +| clip_range | 0.068 | +| entropy_loss | -6.41 | +| explained_variance | 0.367 | +| learning_rate | 4.33e-05 | +| loss | -0.0266 | +| n_updates | 70748 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000127 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1408 | +| iterations | 13734 | +| time_elapsed | 19963 | +| total_timesteps | 28127232 | +| train/ | | +| approx_kl | 0.01341692 | +| clip_fraction | 0.337 | +| clip_range | 0.068 | +| entropy_loss | -6.52 | +| explained_variance | -0.00218 | +| learning_rate | 4.33e-05 | +| loss | -0.0293 | +| n_updates | 70752 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000123 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1408 | +| iterations | 13735 | +| time_elapsed | 19964 | +| total_timesteps | 28129280 | +| train/ | | +| approx_kl | 0.013876241 | +| clip_fraction | 0.323 | +| clip_range | 0.068 | +| entropy_loss | -6.11 | +| explained_variance | 0.513 | +| learning_rate | 4.33e-05 | +| loss | -0.031 | +| n_updates | 70756 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000191 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1408 | +| iterations | 13736 | +| time_elapsed | 19966 | +| total_timesteps | 28131328 | +| train/ | | +| approx_kl | 0.015096536 | +| clip_fraction | 0.325 | +| clip_range | 0.068 | +| entropy_loss | -6.44 | +| explained_variance | 0.452 | +| learning_rate | 4.33e-05 | +| loss | -0.0306 | +| n_updates | 70760 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000118 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1408 | +| iterations | 13737 | +| time_elapsed | 19967 | +| total_timesteps | 28133376 | +| train/ | | +| approx_kl | 0.014634369 | +| clip_fraction | 0.325 | +| clip_range | 0.068 | +| entropy_loss | -6.06 | +| explained_variance | 0.427 | +| learning_rate | 4.33e-05 | +| loss | -0.0301 | +| n_updates | 70764 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000359 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1408 | +| iterations | 13738 | +| time_elapsed | 19969 | +| total_timesteps | 28135424 | +| train/ | | +| approx_kl | 0.015702382 | +| clip_fraction | 0.362 | +| clip_range | 0.068 | +| entropy_loss | -6.08 | +| explained_variance | 0.297 | +| learning_rate | 4.33e-05 | +| loss | -0.0333 | +| n_updates | 70768 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000122 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1408 | +| iterations | 13739 | +| time_elapsed | 19970 | +| total_timesteps | 28137472 | +| train/ | | +| approx_kl | 0.013273085 | +| clip_fraction | 0.304 | +| clip_range | 0.068 | +| entropy_loss | -6.26 | +| explained_variance | 0.31 | +| learning_rate | 4.33e-05 | +| loss | -0.0212 | +| n_updates | 70772 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000246 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1408 | +| iterations | 13740 | +| time_elapsed | 19972 | +| total_timesteps | 28139520 | +| train/ | | +| approx_kl | 0.015663527 | +| clip_fraction | 0.332 | +| clip_range | 0.068 | +| entropy_loss | -6.3 | +| explained_variance | 0.386 | +| learning_rate | 4.33e-05 | +| loss | -0.0283 | +| n_updates | 70776 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000213 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1408 | +| iterations | 13741 | +| time_elapsed | 19973 | +| total_timesteps | 28141568 | +| train/ | | +| approx_kl | 0.012297774 | +| clip_fraction | 0.335 | +| clip_range | 0.068 | +| entropy_loss | -5.72 | +| explained_variance | 0.446 | +| learning_rate | 4.33e-05 | +| loss | -0.0283 | +| n_updates | 70780 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000256 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1408 | +| iterations | 13742 | +| time_elapsed | 19975 | +| total_timesteps | 28143616 | +| train/ | | +| approx_kl | 0.014869218 | +| clip_fraction | 0.389 | +| clip_range | 0.068 | +| entropy_loss | -6.45 | +| explained_variance | 0.476 | +| learning_rate | 4.33e-05 | +| loss | -0.0347 | +| n_updates | 70784 | +| policy_gradient_loss | -0.0232 | +| value_loss | 0.000131 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1408 | +| iterations | 13743 | +| time_elapsed | 19976 | +| total_timesteps | 28145664 | +| train/ | | +| approx_kl | 0.013574893 | +| clip_fraction | 0.373 | +| clip_range | 0.068 | +| entropy_loss | -6.69 | +| explained_variance | 0.245 | +| learning_rate | 4.33e-05 | +| loss | -0.0349 | +| n_updates | 70788 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000157 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1408 | +| iterations | 13744 | +| time_elapsed | 19978 | +| total_timesteps | 28147712 | +| train/ | | +| approx_kl | 0.014432359 | +| clip_fraction | 0.362 | +| clip_range | 0.068 | +| entropy_loss | -6.75 | +| explained_variance | 0.401 | +| learning_rate | 4.33e-05 | +| loss | -0.0339 | +| n_updates | 70792 | +| policy_gradient_loss | -0.0209 | +| value_loss | 6.85e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1408 | +| iterations | 13745 | +| time_elapsed | 19979 | +| total_timesteps | 28149760 | +| train/ | | +| approx_kl | 0.017751485 | +| clip_fraction | 0.323 | +| clip_range | 0.068 | +| entropy_loss | -5.8 | +| explained_variance | 0.653 | +| learning_rate | 4.33e-05 | +| loss | -0.0207 | +| n_updates | 70796 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000143 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1408 | +| iterations | 13746 | +| time_elapsed | 19981 | +| total_timesteps | 28151808 | +| train/ | | +| approx_kl | 0.016292997 | +| clip_fraction | 0.365 | +| clip_range | 0.068 | +| entropy_loss | -5.95 | +| explained_variance | 0.104 | +| learning_rate | 4.33e-05 | +| loss | -0.0294 | +| n_updates | 70800 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000121 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1408 | +| iterations | 13747 | +| time_elapsed | 19982 | +| total_timesteps | 28153856 | +| train/ | | +| approx_kl | 0.013700608 | +| clip_fraction | 0.368 | +| clip_range | 0.068 | +| entropy_loss | -6.47 | +| explained_variance | 0.19 | +| learning_rate | 4.33e-05 | +| loss | -0.0273 | +| n_updates | 70804 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.00029 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1408 | +| iterations | 13748 | +| time_elapsed | 19984 | +| total_timesteps | 28155904 | +| train/ | | +| approx_kl | 0.01242048 | +| clip_fraction | 0.32 | +| clip_range | 0.068 | +| entropy_loss | -6.72 | +| explained_variance | 0.183 | +| learning_rate | 4.33e-05 | +| loss | -0.028 | +| n_updates | 70808 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000248 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1408 | +| iterations | 13749 | +| time_elapsed | 19985 | +| total_timesteps | 28157952 | +| train/ | | +| approx_kl | 0.012932444 | +| clip_fraction | 0.338 | +| clip_range | 0.068 | +| entropy_loss | -6.11 | +| explained_variance | 0.515 | +| learning_rate | 4.33e-05 | +| loss | -0.0271 | +| n_updates | 70812 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000163 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1408 | +| iterations | 13750 | +| time_elapsed | 19987 | +| total_timesteps | 28160000 | +| train/ | | +| approx_kl | 0.013033463 | +| clip_fraction | 0.349 | +| clip_range | 0.068 | +| entropy_loss | -6.29 | +| explained_variance | 0.378 | +| learning_rate | 4.33e-05 | +| loss | -0.025 | +| n_updates | 70816 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000149 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1408 | +| iterations | 13751 | +| time_elapsed | 19988 | +| total_timesteps | 28162048 | +| train/ | | +| approx_kl | 0.015652701 | +| clip_fraction | 0.359 | +| clip_range | 0.068 | +| entropy_loss | -6.35 | +| explained_variance | 0.304 | +| learning_rate | 4.33e-05 | +| loss | -0.0291 | +| n_updates | 70820 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000116 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1408 | +| iterations | 13752 | +| time_elapsed | 19990 | +| total_timesteps | 28164096 | +| train/ | | +| approx_kl | 0.013951831 | +| clip_fraction | 0.339 | +| clip_range | 0.068 | +| entropy_loss | -6.29 | +| explained_variance | 0.601 | +| learning_rate | 4.33e-05 | +| loss | -0.0296 | +| n_updates | 70824 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.00011 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1408 | +| iterations | 13753 | +| time_elapsed | 19991 | +| total_timesteps | 28166144 | +| train/ | | +| approx_kl | 0.011535136 | +| clip_fraction | 0.307 | +| clip_range | 0.068 | +| entropy_loss | -6.64 | +| explained_variance | 0.158 | +| learning_rate | 4.33e-05 | +| loss | -0.0254 | +| n_updates | 70828 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.00028 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1408 | +| iterations | 13754 | +| time_elapsed | 19993 | +| total_timesteps | 28168192 | +| train/ | | +| approx_kl | 0.011101019 | +| clip_fraction | 0.329 | +| clip_range | 0.068 | +| entropy_loss | -6.64 | +| explained_variance | 0.432 | +| learning_rate | 4.33e-05 | +| loss | -0.0306 | +| n_updates | 70832 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000103 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1408 | +| iterations | 13755 | +| time_elapsed | 19994 | +| total_timesteps | 28170240 | +| train/ | | +| approx_kl | 0.012779577 | +| clip_fraction | 0.333 | +| clip_range | 0.068 | +| entropy_loss | -6.4 | +| explained_variance | 0.614 | +| learning_rate | 4.33e-05 | +| loss | -0.0298 | +| n_updates | 70836 | +| policy_gradient_loss | -0.0193 | +| value_loss | 8.49e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1408 | +| iterations | 13756 | +| time_elapsed | 19996 | +| total_timesteps | 28172288 | +| train/ | | +| approx_kl | 0.012403964 | +| clip_fraction | 0.368 | +| clip_range | 0.068 | +| entropy_loss | -6.84 | +| explained_variance | -0.113 | +| learning_rate | 4.33e-05 | +| loss | -0.0308 | +| n_updates | 70840 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000148 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1408 | +| iterations | 13757 | +| time_elapsed | 19997 | +| total_timesteps | 28174336 | +| train/ | | +| approx_kl | 0.013996096 | +| clip_fraction | 0.368 | +| clip_range | 0.068 | +| entropy_loss | -6.61 | +| explained_variance | 0.534 | +| learning_rate | 4.33e-05 | +| loss | -0.0321 | +| n_updates | 70844 | +| policy_gradient_loss | -0.021 | +| value_loss | 6.62e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1408 | +| iterations | 13758 | +| time_elapsed | 19999 | +| total_timesteps | 28176384 | +| train/ | | +| approx_kl | 0.011256551 | +| clip_fraction | 0.334 | +| clip_range | 0.068 | +| entropy_loss | -6.89 | +| explained_variance | 0.119 | +| learning_rate | 4.33e-05 | +| loss | -0.0268 | +| n_updates | 70848 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000113 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1408 | +| iterations | 13759 | +| time_elapsed | 20000 | +| total_timesteps | 28178432 | +| train/ | | +| approx_kl | 0.0144604 | +| clip_fraction | 0.329 | +| clip_range | 0.068 | +| entropy_loss | -6.38 | +| explained_variance | 0.719 | +| learning_rate | 4.33e-05 | +| loss | -0.0276 | +| n_updates | 70852 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000101 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1408 | +| iterations | 13760 | +| time_elapsed | 20002 | +| total_timesteps | 28180480 | +| train/ | | +| approx_kl | 0.013255313 | +| clip_fraction | 0.294 | +| clip_range | 0.068 | +| entropy_loss | -5.5 | +| explained_variance | 0.612 | +| learning_rate | 4.33e-05 | +| loss | -0.0262 | +| n_updates | 70856 | +| policy_gradient_loss | -0.0146 | +| value_loss | 0.000254 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1408 | +| iterations | 13761 | +| time_elapsed | 20003 | +| total_timesteps | 28182528 | +| train/ | | +| approx_kl | 0.011597094 | +| clip_fraction | 0.327 | +| clip_range | 0.068 | +| entropy_loss | -5.89 | +| explained_variance | 0.403 | +| learning_rate | 4.33e-05 | +| loss | -0.0239 | +| n_updates | 70860 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000168 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1408 | +| iterations | 13762 | +| time_elapsed | 20005 | +| total_timesteps | 28184576 | +| train/ | | +| approx_kl | 0.012182888 | +| clip_fraction | 0.337 | +| clip_range | 0.068 | +| entropy_loss | -6.45 | +| explained_variance | 0.571 | +| learning_rate | 4.33e-05 | +| loss | -0.029 | +| n_updates | 70864 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000121 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1408 | +| iterations | 13763 | +| time_elapsed | 20006 | +| total_timesteps | 28186624 | +| train/ | | +| approx_kl | 0.011117082 | +| clip_fraction | 0.326 | +| clip_range | 0.068 | +| entropy_loss | -6.13 | +| explained_variance | 0.343 | +| learning_rate | 4.33e-05 | +| loss | -0.0282 | +| n_updates | 70868 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000167 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1408 | +| iterations | 13764 | +| time_elapsed | 20008 | +| total_timesteps | 28188672 | +| train/ | | +| approx_kl | 0.012160761 | +| clip_fraction | 0.3 | +| clip_range | 0.068 | +| entropy_loss | -6.14 | +| explained_variance | 0.468 | +| learning_rate | 4.33e-05 | +| loss | -0.0244 | +| n_updates | 70872 | +| policy_gradient_loss | -0.0141 | +| value_loss | 0.000198 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1408 | +| iterations | 13765 | +| time_elapsed | 20009 | +| total_timesteps | 28190720 | +| train/ | | +| approx_kl | 0.01566261 | +| clip_fraction | 0.357 | +| clip_range | 0.068 | +| entropy_loss | -6.24 | +| explained_variance | 0.334 | +| learning_rate | 4.33e-05 | +| loss | -0.0321 | +| n_updates | 70876 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000119 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1408 | +| iterations | 13766 | +| time_elapsed | 20011 | +| total_timesteps | 28192768 | +| train/ | | +| approx_kl | 0.016649067 | +| clip_fraction | 0.35 | +| clip_range | 0.068 | +| entropy_loss | -5.9 | +| explained_variance | 0.325 | +| learning_rate | 4.33e-05 | +| loss | -0.0298 | +| n_updates | 70880 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.00027 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1408 | +| iterations | 13767 | +| time_elapsed | 20012 | +| total_timesteps | 28194816 | +| train/ | | +| approx_kl | 0.014139244 | +| clip_fraction | 0.37 | +| clip_range | 0.068 | +| entropy_loss | -6.59 | +| explained_variance | -0.0868 | +| learning_rate | 4.33e-05 | +| loss | -0.0329 | +| n_updates | 70884 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000171 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1408 | +| iterations | 13768 | +| time_elapsed | 20014 | +| total_timesteps | 28196864 | +| train/ | | +| approx_kl | 0.014311733 | +| clip_fraction | 0.361 | +| clip_range | 0.068 | +| entropy_loss | -6.28 | +| explained_variance | 0.333 | +| learning_rate | 4.33e-05 | +| loss | -0.0309 | +| n_updates | 70888 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000174 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1408 | +| iterations | 13769 | +| time_elapsed | 20016 | +| total_timesteps | 28198912 | +| train/ | | +| approx_kl | 0.013776597 | +| clip_fraction | 0.345 | +| clip_range | 0.068 | +| entropy_loss | -6.01 | +| explained_variance | 0.606 | +| learning_rate | 4.33e-05 | +| loss | -0.0378 | +| n_updates | 70892 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000125 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1408 | +| iterations | 13770 | +| time_elapsed | 20017 | +| total_timesteps | 28200960 | +| train/ | | +| approx_kl | 0.017770536 | +| clip_fraction | 0.402 | +| clip_range | 0.068 | +| entropy_loss | -5.98 | +| explained_variance | 0.61 | +| learning_rate | 4.33e-05 | +| loss | -0.0283 | +| n_updates | 70896 | +| policy_gradient_loss | -0.0198 | +| value_loss | 9.13e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1408 | +| iterations | 13771 | +| time_elapsed | 20019 | +| total_timesteps | 28203008 | +| train/ | | +| approx_kl | 0.019331587 | +| clip_fraction | 0.329 | +| clip_range | 0.0679 | +| entropy_loss | -5.64 | +| explained_variance | 0.671 | +| learning_rate | 4.33e-05 | +| loss | -0.0235 | +| n_updates | 70900 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.000156 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1408 | +| iterations | 13772 | +| time_elapsed | 20020 | +| total_timesteps | 28205056 | +| train/ | | +| approx_kl | 0.018380674 | +| clip_fraction | 0.376 | +| clip_range | 0.0679 | +| entropy_loss | -5.77 | +| explained_variance | 0.469 | +| learning_rate | 4.33e-05 | +| loss | -0.0325 | +| n_updates | 70904 | +| policy_gradient_loss | -0.0201 | +| value_loss | 8.43e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1408 | +| iterations | 13773 | +| time_elapsed | 20022 | +| total_timesteps | 28207104 | +| train/ | | +| approx_kl | 0.012271797 | +| clip_fraction | 0.328 | +| clip_range | 0.0679 | +| entropy_loss | -6.58 | +| explained_variance | 0.197 | +| learning_rate | 4.33e-05 | +| loss | -0.0286 | +| n_updates | 70908 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000243 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1408 | +| iterations | 13774 | +| time_elapsed | 20023 | +| total_timesteps | 28209152 | +| train/ | | +| approx_kl | 0.012118884 | +| clip_fraction | 0.333 | +| clip_range | 0.0679 | +| entropy_loss | -6.29 | +| explained_variance | 0.356 | +| learning_rate | 4.33e-05 | +| loss | -0.0278 | +| n_updates | 70912 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000289 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1408 | +| iterations | 13775 | +| time_elapsed | 20025 | +| total_timesteps | 28211200 | +| train/ | | +| approx_kl | 0.013691808 | +| clip_fraction | 0.337 | +| clip_range | 0.0679 | +| entropy_loss | -5.79 | +| explained_variance | 0.581 | +| learning_rate | 4.33e-05 | +| loss | -0.0294 | +| n_updates | 70916 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000123 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1408 | +| iterations | 13776 | +| time_elapsed | 20026 | +| total_timesteps | 28213248 | +| train/ | | +| approx_kl | 0.016058994 | +| clip_fraction | 0.364 | +| clip_range | 0.0679 | +| entropy_loss | -6.24 | +| explained_variance | 0.351 | +| learning_rate | 4.33e-05 | +| loss | -0.0312 | +| n_updates | 70920 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000164 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1408 | +| iterations | 13777 | +| time_elapsed | 20028 | +| total_timesteps | 28215296 | +| train/ | | +| approx_kl | 0.011135099 | +| clip_fraction | 0.326 | +| clip_range | 0.0679 | +| entropy_loss | -6.74 | +| explained_variance | -0.00516 | +| learning_rate | 4.33e-05 | +| loss | -0.0229 | +| n_updates | 70924 | +| policy_gradient_loss | -0.0138 | +| value_loss | 0.000239 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1408 | +| iterations | 13778 | +| time_elapsed | 20029 | +| total_timesteps | 28217344 | +| train/ | | +| approx_kl | 0.015621405 | +| clip_fraction | 0.332 | +| clip_range | 0.0679 | +| entropy_loss | -5.9 | +| explained_variance | 0.534 | +| learning_rate | 4.33e-05 | +| loss | -0.0287 | +| n_updates | 70928 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000189 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1408 | +| iterations | 13779 | +| time_elapsed | 20031 | +| total_timesteps | 28219392 | +| train/ | | +| approx_kl | 0.012767613 | +| clip_fraction | 0.355 | +| clip_range | 0.0679 | +| entropy_loss | -6.52 | +| explained_variance | 0.248 | +| learning_rate | 4.33e-05 | +| loss | -0.0358 | +| n_updates | 70932 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000161 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1408 | +| iterations | 13780 | +| time_elapsed | 20032 | +| total_timesteps | 28221440 | +| train/ | | +| approx_kl | 0.014645307 | +| clip_fraction | 0.355 | +| clip_range | 0.0679 | +| entropy_loss | -6.56 | +| explained_variance | 0.305 | +| learning_rate | 4.33e-05 | +| loss | -0.0328 | +| n_updates | 70936 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000115 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1408 | +| iterations | 13781 | +| time_elapsed | 20034 | +| total_timesteps | 28223488 | +| train/ | | +| approx_kl | 0.011579724 | +| clip_fraction | 0.326 | +| clip_range | 0.0679 | +| entropy_loss | -6.75 | +| explained_variance | 0.3 | +| learning_rate | 4.33e-05 | +| loss | -0.0303 | +| n_updates | 70940 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000139 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1408 | +| iterations | 13782 | +| time_elapsed | 20035 | +| total_timesteps | 28225536 | +| train/ | | +| approx_kl | 0.010620234 | +| clip_fraction | 0.33 | +| clip_range | 0.0679 | +| entropy_loss | -6.71 | +| explained_variance | -0.0417 | +| learning_rate | 4.33e-05 | +| loss | -0.0281 | +| n_updates | 70944 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000244 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1408 | +| iterations | 13783 | +| time_elapsed | 20037 | +| total_timesteps | 28227584 | +| train/ | | +| approx_kl | 0.014833964 | +| clip_fraction | 0.33 | +| clip_range | 0.0679 | +| entropy_loss | -5.25 | +| explained_variance | 0.734 | +| learning_rate | 4.33e-05 | +| loss | -0.0249 | +| n_updates | 70948 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000139 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1408 | +| iterations | 13784 | +| time_elapsed | 20038 | +| total_timesteps | 28229632 | +| train/ | | +| approx_kl | 0.012432435 | +| clip_fraction | 0.337 | +| clip_range | 0.0679 | +| entropy_loss | -5.41 | +| explained_variance | 0.429 | +| learning_rate | 4.33e-05 | +| loss | -0.0237 | +| n_updates | 70952 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000275 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1408 | +| iterations | 13785 | +| time_elapsed | 20040 | +| total_timesteps | 28231680 | +| train/ | | +| approx_kl | 0.011316445 | +| clip_fraction | 0.35 | +| clip_range | 0.0679 | +| entropy_loss | -6.11 | +| explained_variance | 0.314 | +| learning_rate | 4.33e-05 | +| loss | -0.0245 | +| n_updates | 70956 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000214 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1408 | +| iterations | 13786 | +| time_elapsed | 20042 | +| total_timesteps | 28233728 | +| train/ | | +| approx_kl | 0.015965082 | +| clip_fraction | 0.382 | +| clip_range | 0.0679 | +| entropy_loss | -6.21 | +| explained_variance | 0.518 | +| learning_rate | 4.33e-05 | +| loss | -0.0363 | +| n_updates | 70960 | +| policy_gradient_loss | -0.0226 | +| value_loss | 7.99e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1408 | +| iterations | 13787 | +| time_elapsed | 20043 | +| total_timesteps | 28235776 | +| train/ | | +| approx_kl | 0.015648592 | +| clip_fraction | 0.352 | +| clip_range | 0.0679 | +| entropy_loss | -6.3 | +| explained_variance | 0.24 | +| learning_rate | 4.33e-05 | +| loss | -0.0314 | +| n_updates | 70964 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000258 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1408 | +| iterations | 13788 | +| time_elapsed | 20045 | +| total_timesteps | 28237824 | +| train/ | | +| approx_kl | 0.014409292 | +| clip_fraction | 0.374 | +| clip_range | 0.0679 | +| entropy_loss | -6.46 | +| explained_variance | -0.112 | +| learning_rate | 4.33e-05 | +| loss | -0.0341 | +| n_updates | 70968 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000199 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1408 | +| iterations | 13789 | +| time_elapsed | 20046 | +| total_timesteps | 28239872 | +| train/ | | +| approx_kl | 0.015933475 | +| clip_fraction | 0.347 | +| clip_range | 0.0679 | +| entropy_loss | -6.7 | +| explained_variance | 0.377 | +| learning_rate | 4.33e-05 | +| loss | -0.0353 | +| n_updates | 70972 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000117 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1408 | +| iterations | 13790 | +| time_elapsed | 20048 | +| total_timesteps | 28241920 | +| train/ | | +| approx_kl | 0.011196473 | +| clip_fraction | 0.323 | +| clip_range | 0.0679 | +| entropy_loss | -6.38 | +| explained_variance | 0.364 | +| learning_rate | 4.33e-05 | +| loss | -0.0221 | +| n_updates | 70976 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000236 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1408 | +| iterations | 13791 | +| time_elapsed | 20049 | +| total_timesteps | 28243968 | +| train/ | | +| approx_kl | 0.015107626 | +| clip_fraction | 0.328 | +| clip_range | 0.0679 | +| entropy_loss | -6.16 | +| explained_variance | 0.289 | +| learning_rate | 4.33e-05 | +| loss | -0.0231 | +| n_updates | 70980 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000311 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1408 | +| iterations | 13792 | +| time_elapsed | 20051 | +| total_timesteps | 28246016 | +| train/ | | +| approx_kl | 0.015850645 | +| clip_fraction | 0.352 | +| clip_range | 0.0679 | +| entropy_loss | -6.35 | +| explained_variance | 0.322 | +| learning_rate | 4.33e-05 | +| loss | -0.0278 | +| n_updates | 70984 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000176 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1408 | +| iterations | 13793 | +| time_elapsed | 20052 | +| total_timesteps | 28248064 | +| train/ | | +| approx_kl | 0.013601156 | +| clip_fraction | 0.366 | +| clip_range | 0.0679 | +| entropy_loss | -5.88 | +| explained_variance | 0.447 | +| learning_rate | 4.33e-05 | +| loss | -0.0373 | +| n_updates | 70988 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.00021 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1408 | +| iterations | 13794 | +| time_elapsed | 20054 | +| total_timesteps | 28250112 | +| train/ | | +| approx_kl | 0.013356721 | +| clip_fraction | 0.367 | +| clip_range | 0.0679 | +| entropy_loss | -6.31 | +| explained_variance | 0.695 | +| learning_rate | 4.33e-05 | +| loss | -0.0318 | +| n_updates | 70992 | +| policy_gradient_loss | -0.0203 | +| value_loss | 7.11e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1408 | +| iterations | 13795 | +| time_elapsed | 20055 | +| total_timesteps | 28252160 | +| train/ | | +| approx_kl | 0.012248905 | +| clip_fraction | 0.319 | +| clip_range | 0.0679 | +| entropy_loss | -5.66 | +| explained_variance | 0.494 | +| learning_rate | 4.33e-05 | +| loss | -0.0268 | +| n_updates | 70996 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.00026 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1408 | +| iterations | 13796 | +| time_elapsed | 20057 | +| total_timesteps | 28254208 | +| train/ | | +| approx_kl | 0.014890407 | +| clip_fraction | 0.322 | +| clip_range | 0.0679 | +| entropy_loss | -6 | +| explained_variance | 0.44 | +| learning_rate | 4.33e-05 | +| loss | -0.0305 | +| n_updates | 71000 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000198 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1408 | +| iterations | 13797 | +| time_elapsed | 20058 | +| total_timesteps | 28256256 | +| train/ | | +| approx_kl | 0.012992074 | +| clip_fraction | 0.358 | +| clip_range | 0.0679 | +| entropy_loss | -6.92 | +| explained_variance | -0.128 | +| learning_rate | 4.33e-05 | +| loss | -0.0293 | +| n_updates | 71004 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000137 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1408 | +| iterations | 13798 | +| time_elapsed | 20060 | +| total_timesteps | 28258304 | +| train/ | | +| approx_kl | 0.012385145 | +| clip_fraction | 0.356 | +| clip_range | 0.0679 | +| entropy_loss | -6.72 | +| explained_variance | 0.426 | +| learning_rate | 4.33e-05 | +| loss | -0.0332 | +| n_updates | 71008 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000102 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1408 | +| iterations | 13799 | +| time_elapsed | 20062 | +| total_timesteps | 28260352 | +| train/ | | +| approx_kl | 0.011219736 | +| clip_fraction | 0.347 | +| clip_range | 0.0679 | +| entropy_loss | -6.86 | +| explained_variance | 0.0201 | +| learning_rate | 4.33e-05 | +| loss | -0.0262 | +| n_updates | 71012 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000213 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1408 | +| iterations | 13800 | +| time_elapsed | 20063 | +| total_timesteps | 28262400 | +| train/ | | +| approx_kl | 0.014729591 | +| clip_fraction | 0.367 | +| clip_range | 0.0679 | +| entropy_loss | -6.52 | +| explained_variance | 0.356 | +| learning_rate | 4.33e-05 | +| loss | -0.0351 | +| n_updates | 71016 | +| policy_gradient_loss | -0.0199 | +| value_loss | 9.29e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1408 | +| iterations | 13801 | +| time_elapsed | 20065 | +| total_timesteps | 28264448 | +| train/ | | +| approx_kl | 0.01317691 | +| clip_fraction | 0.328 | +| clip_range | 0.0679 | +| entropy_loss | -5.97 | +| explained_variance | 0.717 | +| learning_rate | 4.33e-05 | +| loss | -0.0284 | +| n_updates | 71020 | +| policy_gradient_loss | -0.0173 | +| value_loss | 9.04e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1408 | +| iterations | 13802 | +| time_elapsed | 20066 | +| total_timesteps | 28266496 | +| train/ | | +| approx_kl | 0.011922609 | +| clip_fraction | 0.306 | +| clip_range | 0.0679 | +| entropy_loss | -6.27 | +| explained_variance | 0.363 | +| learning_rate | 4.33e-05 | +| loss | -0.03 | +| n_updates | 71024 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000134 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1408 | +| iterations | 13803 | +| time_elapsed | 20068 | +| total_timesteps | 28268544 | +| train/ | | +| approx_kl | 0.013989691 | +| clip_fraction | 0.345 | +| clip_range | 0.0679 | +| entropy_loss | -5.64 | +| explained_variance | 0.803 | +| learning_rate | 4.33e-05 | +| loss | -0.0329 | +| n_updates | 71028 | +| policy_gradient_loss | -0.0169 | +| value_loss | 8.41e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1408 | +| iterations | 13804 | +| time_elapsed | 20069 | +| total_timesteps | 28270592 | +| train/ | | +| approx_kl | 0.015278167 | +| clip_fraction | 0.315 | +| clip_range | 0.0679 | +| entropy_loss | -5.85 | +| explained_variance | 0.362 | +| learning_rate | 4.33e-05 | +| loss | -0.0269 | +| n_updates | 71032 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000176 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1408 | +| iterations | 13805 | +| time_elapsed | 20071 | +| total_timesteps | 28272640 | +| train/ | | +| approx_kl | 0.014277522 | +| clip_fraction | 0.344 | +| clip_range | 0.0679 | +| entropy_loss | -6.36 | +| explained_variance | 0.373 | +| learning_rate | 4.33e-05 | +| loss | -0.0316 | +| n_updates | 71036 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000213 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1408 | +| iterations | 13806 | +| time_elapsed | 20072 | +| total_timesteps | 28274688 | +| train/ | | +| approx_kl | 0.013899953 | +| clip_fraction | 0.313 | +| clip_range | 0.0679 | +| entropy_loss | -6.18 | +| explained_variance | 0.553 | +| learning_rate | 4.33e-05 | +| loss | -0.0229 | +| n_updates | 71040 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000195 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1408 | +| iterations | 13807 | +| time_elapsed | 20074 | +| total_timesteps | 28276736 | +| train/ | | +| approx_kl | 0.011763195 | +| clip_fraction | 0.348 | +| clip_range | 0.0679 | +| entropy_loss | -6.51 | +| explained_variance | -0.0481 | +| learning_rate | 4.33e-05 | +| loss | -0.0263 | +| n_updates | 71044 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000397 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1408 | +| iterations | 13808 | +| time_elapsed | 20075 | +| total_timesteps | 28278784 | +| train/ | | +| approx_kl | 0.01831379 | +| clip_fraction | 0.362 | +| clip_range | 0.0679 | +| entropy_loss | -6.01 | +| explained_variance | 0.516 | +| learning_rate | 4.33e-05 | +| loss | -0.0308 | +| n_updates | 71048 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000177 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1408 | +| iterations | 13809 | +| time_elapsed | 20077 | +| total_timesteps | 28280832 | +| train/ | | +| approx_kl | 0.016099289 | +| clip_fraction | 0.338 | +| clip_range | 0.0679 | +| entropy_loss | -6.13 | +| explained_variance | 0.407 | +| learning_rate | 4.33e-05 | +| loss | -0.0241 | +| n_updates | 71052 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.00025 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1408 | +| iterations | 13810 | +| time_elapsed | 20078 | +| total_timesteps | 28282880 | +| train/ | | +| approx_kl | 0.0142326 | +| clip_fraction | 0.356 | +| clip_range | 0.0679 | +| entropy_loss | -5.49 | +| explained_variance | 0.372 | +| learning_rate | 4.33e-05 | +| loss | -0.0203 | +| n_updates | 71056 | +| policy_gradient_loss | -0.0148 | +| value_loss | 0.000452 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1408 | +| iterations | 13811 | +| time_elapsed | 20080 | +| total_timesteps | 28284928 | +| train/ | | +| approx_kl | 0.018831303 | +| clip_fraction | 0.404 | +| clip_range | 0.0679 | +| entropy_loss | -5.86 | +| explained_variance | 0.313 | +| learning_rate | 4.33e-05 | +| loss | -0.0364 | +| n_updates | 71060 | +| policy_gradient_loss | -0.0241 | +| value_loss | 7.96e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1408 | +| iterations | 13812 | +| time_elapsed | 20081 | +| total_timesteps | 28286976 | +| train/ | | +| approx_kl | 0.013890138 | +| clip_fraction | 0.382 | +| clip_range | 0.0679 | +| entropy_loss | -6.77 | +| explained_variance | -0.0936 | +| learning_rate | 4.33e-05 | +| loss | -0.0353 | +| n_updates | 71064 | +| policy_gradient_loss | -0.024 | +| value_loss | 7.79e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1408 | +| iterations | 13813 | +| time_elapsed | 20083 | +| total_timesteps | 28289024 | +| train/ | | +| approx_kl | 0.013439523 | +| clip_fraction | 0.359 | +| clip_range | 0.0679 | +| entropy_loss | -6.61 | +| explained_variance | 0.411 | +| learning_rate | 4.33e-05 | +| loss | -0.0291 | +| n_updates | 71068 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000113 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1408 | +| iterations | 13814 | +| time_elapsed | 20085 | +| total_timesteps | 28291072 | +| train/ | | +| approx_kl | 0.013026204 | +| clip_fraction | 0.343 | +| clip_range | 0.0679 | +| entropy_loss | -6.52 | +| explained_variance | 0.26 | +| learning_rate | 4.33e-05 | +| loss | -0.0291 | +| n_updates | 71072 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000171 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1408 | +| iterations | 13815 | +| time_elapsed | 20086 | +| total_timesteps | 28293120 | +| train/ | | +| approx_kl | 0.014541166 | +| clip_fraction | 0.341 | +| clip_range | 0.0679 | +| entropy_loss | -6.34 | +| explained_variance | 0.564 | +| learning_rate | 4.33e-05 | +| loss | -0.0339 | +| n_updates | 71076 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000125 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1408 | +| iterations | 13816 | +| time_elapsed | 20088 | +| total_timesteps | 28295168 | +| train/ | | +| approx_kl | 0.012924884 | +| clip_fraction | 0.313 | +| clip_range | 0.0679 | +| entropy_loss | -5.69 | +| explained_variance | 0.548 | +| learning_rate | 4.33e-05 | +| loss | -0.0254 | +| n_updates | 71080 | +| policy_gradient_loss | -0.0143 | +| value_loss | 0.000222 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1408 | +| iterations | 13817 | +| time_elapsed | 20089 | +| total_timesteps | 28297216 | +| train/ | | +| approx_kl | 0.014934847 | +| clip_fraction | 0.376 | +| clip_range | 0.0679 | +| entropy_loss | -6 | +| explained_variance | 0.555 | +| learning_rate | 4.33e-05 | +| loss | -0.0291 | +| n_updates | 71084 | +| policy_gradient_loss | -0.0214 | +| value_loss | 9.61e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1408 | +| iterations | 13818 | +| time_elapsed | 20091 | +| total_timesteps | 28299264 | +| train/ | | +| approx_kl | 0.012213942 | +| clip_fraction | 0.357 | +| clip_range | 0.0679 | +| entropy_loss | -6.85 | +| explained_variance | 0.101 | +| learning_rate | 4.33e-05 | +| loss | -0.0313 | +| n_updates | 71088 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000124 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1408 | +| iterations | 13819 | +| time_elapsed | 20092 | +| total_timesteps | 28301312 | +| train/ | | +| approx_kl | 0.013823628 | +| clip_fraction | 0.333 | +| clip_range | 0.0679 | +| entropy_loss | -6.27 | +| explained_variance | 0.547 | +| learning_rate | 4.33e-05 | +| loss | -0.027 | +| n_updates | 71092 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000174 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1408 | +| iterations | 13820 | +| time_elapsed | 20094 | +| total_timesteps | 28303360 | +| train/ | | +| approx_kl | 0.010448579 | +| clip_fraction | 0.326 | +| clip_range | 0.0679 | +| entropy_loss | -6.65 | +| explained_variance | 0.0695 | +| learning_rate | 4.33e-05 | +| loss | -0.0258 | +| n_updates | 71096 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.00019 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1408 | +| iterations | 13821 | +| time_elapsed | 20095 | +| total_timesteps | 28305408 | +| train/ | | +| approx_kl | 0.010905669 | +| clip_fraction | 0.313 | +| clip_range | 0.0679 | +| entropy_loss | -6.15 | +| explained_variance | 0.602 | +| learning_rate | 4.33e-05 | +| loss | -0.0269 | +| n_updates | 71100 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000174 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1408 | +| iterations | 13822 | +| time_elapsed | 20097 | +| total_timesteps | 28307456 | +| train/ | | +| approx_kl | 0.017502181 | +| clip_fraction | 0.334 | +| clip_range | 0.0679 | +| entropy_loss | -6.04 | +| explained_variance | 0.499 | +| learning_rate | 4.33e-05 | +| loss | -0.0365 | +| n_updates | 71104 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000102 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1408 | +| iterations | 13823 | +| time_elapsed | 20098 | +| total_timesteps | 28309504 | +| train/ | | +| approx_kl | 0.0109445825 | +| clip_fraction | 0.328 | +| clip_range | 0.0679 | +| entropy_loss | -6.21 | +| explained_variance | 0.355 | +| learning_rate | 4.33e-05 | +| loss | -0.024 | +| n_updates | 71108 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000278 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1408 | +| iterations | 13824 | +| time_elapsed | 20100 | +| total_timesteps | 28311552 | +| train/ | | +| approx_kl | 0.012404728 | +| clip_fraction | 0.343 | +| clip_range | 0.0679 | +| entropy_loss | -5.79 | +| explained_variance | 0.659 | +| learning_rate | 4.33e-05 | +| loss | -0.0286 | +| n_updates | 71112 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000125 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1408 | +| iterations | 13825 | +| time_elapsed | 20101 | +| total_timesteps | 28313600 | +| train/ | | +| approx_kl | 0.012183874 | +| clip_fraction | 0.336 | +| clip_range | 0.0679 | +| entropy_loss | -6.35 | +| explained_variance | 0.319 | +| learning_rate | 4.33e-05 | +| loss | -0.0256 | +| n_updates | 71116 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000157 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1408 | +| iterations | 13826 | +| time_elapsed | 20103 | +| total_timesteps | 28315648 | +| train/ | | +| approx_kl | 0.014541255 | +| clip_fraction | 0.346 | +| clip_range | 0.0679 | +| entropy_loss | -6.76 | +| explained_variance | 0.265 | +| learning_rate | 4.33e-05 | +| loss | -0.0337 | +| n_updates | 71120 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000133 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1408 | +| iterations | 13827 | +| time_elapsed | 20104 | +| total_timesteps | 28317696 | +| train/ | | +| approx_kl | 0.013202433 | +| clip_fraction | 0.349 | +| clip_range | 0.0679 | +| entropy_loss | -6.65 | +| explained_variance | 0.239 | +| learning_rate | 4.33e-05 | +| loss | -0.0278 | +| n_updates | 71124 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000171 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1408 | +| iterations | 13828 | +| time_elapsed | 20106 | +| total_timesteps | 28319744 | +| train/ | | +| approx_kl | 0.01497172 | +| clip_fraction | 0.355 | +| clip_range | 0.0679 | +| entropy_loss | -6.42 | +| explained_variance | 0.325 | +| learning_rate | 4.33e-05 | +| loss | -0.0306 | +| n_updates | 71128 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000125 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1408 | +| iterations | 13829 | +| time_elapsed | 20107 | +| total_timesteps | 28321792 | +| train/ | | +| approx_kl | 0.01499881 | +| clip_fraction | 0.347 | +| clip_range | 0.0679 | +| entropy_loss | -6 | +| explained_variance | 0.125 | +| learning_rate | 4.33e-05 | +| loss | -0.0232 | +| n_updates | 71132 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000522 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1408 | +| iterations | 13830 | +| time_elapsed | 20109 | +| total_timesteps | 28323840 | +| train/ | | +| approx_kl | 0.017974813 | +| clip_fraction | 0.386 | +| clip_range | 0.0679 | +| entropy_loss | -5.82 | +| explained_variance | 0.589 | +| learning_rate | 4.33e-05 | +| loss | -0.03 | +| n_updates | 71136 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000164 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1408 | +| iterations | 13831 | +| time_elapsed | 20110 | +| total_timesteps | 28325888 | +| train/ | | +| approx_kl | 0.015030604 | +| clip_fraction | 0.373 | +| clip_range | 0.0679 | +| entropy_loss | -6.43 | +| explained_variance | 0.286 | +| learning_rate | 4.33e-05 | +| loss | -0.0355 | +| n_updates | 71140 | +| policy_gradient_loss | -0.0231 | +| value_loss | 0.00011 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1408 | +| iterations | 13832 | +| time_elapsed | 20112 | +| total_timesteps | 28327936 | +| train/ | | +| approx_kl | 0.012050432 | +| clip_fraction | 0.342 | +| clip_range | 0.0679 | +| entropy_loss | -6.34 | +| explained_variance | 0.518 | +| learning_rate | 4.33e-05 | +| loss | -0.0372 | +| n_updates | 71144 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000112 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1408 | +| iterations | 13833 | +| time_elapsed | 20113 | +| total_timesteps | 28329984 | +| train/ | | +| approx_kl | 0.014434177 | +| clip_fraction | 0.356 | +| clip_range | 0.0679 | +| entropy_loss | -6.5 | +| explained_variance | 0.302 | +| learning_rate | 4.33e-05 | +| loss | -0.0327 | +| n_updates | 71148 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000137 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1408 | +| iterations | 13834 | +| time_elapsed | 20115 | +| total_timesteps | 28332032 | +| train/ | | +| approx_kl | 0.0115027875 | +| clip_fraction | 0.315 | +| clip_range | 0.0679 | +| entropy_loss | -6.02 | +| explained_variance | 0.397 | +| learning_rate | 4.33e-05 | +| loss | -0.0256 | +| n_updates | 71152 | +| policy_gradient_loss | -0.0129 | +| value_loss | 0.000354 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1408 | +| iterations | 13835 | +| time_elapsed | 20116 | +| total_timesteps | 28334080 | +| train/ | | +| approx_kl | 0.014102169 | +| clip_fraction | 0.375 | +| clip_range | 0.0679 | +| entropy_loss | -5.77 | +| explained_variance | 0.507 | +| learning_rate | 4.33e-05 | +| loss | -0.0374 | +| n_updates | 71156 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000165 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1408 | +| iterations | 13836 | +| time_elapsed | 20118 | +| total_timesteps | 28336128 | +| train/ | | +| approx_kl | 0.014571167 | +| clip_fraction | 0.34 | +| clip_range | 0.0679 | +| entropy_loss | -6.34 | +| explained_variance | 0.233 | +| learning_rate | 4.33e-05 | +| loss | -0.0253 | +| n_updates | 71160 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000218 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1408 | +| iterations | 13837 | +| time_elapsed | 20119 | +| total_timesteps | 28338176 | +| train/ | | +| approx_kl | 0.016266936 | +| clip_fraction | 0.363 | +| clip_range | 0.0679 | +| entropy_loss | -6.29 | +| explained_variance | 0.389 | +| learning_rate | 4.33e-05 | +| loss | -0.0348 | +| n_updates | 71164 | +| policy_gradient_loss | -0.0214 | +| value_loss | 9.46e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1408 | +| iterations | 13838 | +| time_elapsed | 20121 | +| total_timesteps | 28340224 | +| train/ | | +| approx_kl | 0.017414544 | +| clip_fraction | 0.333 | +| clip_range | 0.0679 | +| entropy_loss | -6.12 | +| explained_variance | 0.437 | +| learning_rate | 4.33e-05 | +| loss | -0.0267 | +| n_updates | 71168 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000182 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1408 | +| iterations | 13839 | +| time_elapsed | 20123 | +| total_timesteps | 28342272 | +| train/ | | +| approx_kl | 0.0131081045 | +| clip_fraction | 0.34 | +| clip_range | 0.0679 | +| entropy_loss | -6.4 | +| explained_variance | 0.367 | +| learning_rate | 4.33e-05 | +| loss | -0.0195 | +| n_updates | 71172 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000241 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1408 | +| iterations | 13840 | +| time_elapsed | 20124 | +| total_timesteps | 28344320 | +| train/ | | +| approx_kl | 0.01342712 | +| clip_fraction | 0.355 | +| clip_range | 0.0679 | +| entropy_loss | -6.33 | +| explained_variance | 0.639 | +| learning_rate | 4.33e-05 | +| loss | -0.0288 | +| n_updates | 71176 | +| policy_gradient_loss | -0.0198 | +| value_loss | 8.32e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1408 | +| iterations | 13841 | +| time_elapsed | 20126 | +| total_timesteps | 28346368 | +| train/ | | +| approx_kl | 0.014790253 | +| clip_fraction | 0.362 | +| clip_range | 0.0679 | +| entropy_loss | -6.08 | +| explained_variance | 0.33 | +| learning_rate | 4.33e-05 | +| loss | -0.0284 | +| n_updates | 71180 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.00015 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1408 | +| iterations | 13842 | +| time_elapsed | 20127 | +| total_timesteps | 28348416 | +| train/ | | +| approx_kl | 0.011324947 | +| clip_fraction | 0.338 | +| clip_range | 0.0679 | +| entropy_loss | -6.63 | +| explained_variance | 0.257 | +| learning_rate | 4.33e-05 | +| loss | -0.0342 | +| n_updates | 71184 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000232 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1408 | +| iterations | 13843 | +| time_elapsed | 20129 | +| total_timesteps | 28350464 | +| train/ | | +| approx_kl | 0.0096304 | +| clip_fraction | 0.312 | +| clip_range | 0.0679 | +| entropy_loss | -6.96 | +| explained_variance | -0.0132 | +| learning_rate | 4.33e-05 | +| loss | -0.0326 | +| n_updates | 71188 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000214 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1408 | +| iterations | 13844 | +| time_elapsed | 20130 | +| total_timesteps | 28352512 | +| train/ | | +| approx_kl | 0.013111837 | +| clip_fraction | 0.338 | +| clip_range | 0.0679 | +| entropy_loss | -6.03 | +| explained_variance | 0.564 | +| learning_rate | 4.33e-05 | +| loss | -0.0286 | +| n_updates | 71192 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000152 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1408 | +| iterations | 13845 | +| time_elapsed | 20132 | +| total_timesteps | 28354560 | +| train/ | | +| approx_kl | 0.014610887 | +| clip_fraction | 0.309 | +| clip_range | 0.0679 | +| entropy_loss | -5.98 | +| explained_variance | 0.353 | +| learning_rate | 4.33e-05 | +| loss | -0.0231 | +| n_updates | 71196 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000174 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1408 | +| iterations | 13846 | +| time_elapsed | 20133 | +| total_timesteps | 28356608 | +| train/ | | +| approx_kl | 0.017048927 | +| clip_fraction | 0.379 | +| clip_range | 0.0679 | +| entropy_loss | -5.48 | +| explained_variance | 0.741 | +| learning_rate | 4.33e-05 | +| loss | -0.0313 | +| n_updates | 71200 | +| policy_gradient_loss | -0.0197 | +| value_loss | 9.83e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1408 | +| iterations | 13847 | +| time_elapsed | 20135 | +| total_timesteps | 28358656 | +| train/ | | +| approx_kl | 0.015437386 | +| clip_fraction | 0.368 | +| clip_range | 0.0679 | +| entropy_loss | -6.52 | +| explained_variance | -0.181 | +| learning_rate | 4.33e-05 | +| loss | -0.0337 | +| n_updates | 71204 | +| policy_gradient_loss | -0.0201 | +| value_loss | 7.81e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1408 | +| iterations | 13848 | +| time_elapsed | 20136 | +| total_timesteps | 28360704 | +| train/ | | +| approx_kl | 0.014706898 | +| clip_fraction | 0.351 | +| clip_range | 0.0679 | +| entropy_loss | -6.46 | +| explained_variance | 0.63 | +| learning_rate | 4.33e-05 | +| loss | -0.0305 | +| n_updates | 71208 | +| policy_gradient_loss | -0.0188 | +| value_loss | 9.06e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1408 | +| iterations | 13849 | +| time_elapsed | 20138 | +| total_timesteps | 28362752 | +| train/ | | +| approx_kl | 0.0141308475 | +| clip_fraction | 0.337 | +| clip_range | 0.0679 | +| entropy_loss | -6.06 | +| explained_variance | 0.396 | +| learning_rate | 4.33e-05 | +| loss | -0.0285 | +| n_updates | 71212 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000123 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1408 | +| iterations | 13850 | +| time_elapsed | 20139 | +| total_timesteps | 28364800 | +| train/ | | +| approx_kl | 0.016803976 | +| clip_fraction | 0.378 | +| clip_range | 0.0679 | +| entropy_loss | -6.27 | +| explained_variance | 0.229 | +| learning_rate | 4.33e-05 | +| loss | -0.0337 | +| n_updates | 71216 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000119 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1408 | +| iterations | 13851 | +| time_elapsed | 20141 | +| total_timesteps | 28366848 | +| train/ | | +| approx_kl | 0.017847009 | +| clip_fraction | 0.319 | +| clip_range | 0.0679 | +| entropy_loss | -5.54 | +| explained_variance | 0.531 | +| learning_rate | 4.33e-05 | +| loss | -0.0206 | +| n_updates | 71220 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000298 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1408 | +| iterations | 13852 | +| time_elapsed | 20142 | +| total_timesteps | 28368896 | +| train/ | | +| approx_kl | 0.017954731 | +| clip_fraction | 0.368 | +| clip_range | 0.0679 | +| entropy_loss | -6.1 | +| explained_variance | 0.433 | +| learning_rate | 4.33e-05 | +| loss | -0.0277 | +| n_updates | 71224 | +| policy_gradient_loss | -0.0213 | +| value_loss | 8.57e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1408 | +| iterations | 13853 | +| time_elapsed | 20144 | +| total_timesteps | 28370944 | +| train/ | | +| approx_kl | 0.016109355 | +| clip_fraction | 0.35 | +| clip_range | 0.0679 | +| entropy_loss | -6.72 | +| explained_variance | -0.0407 | +| learning_rate | 4.33e-05 | +| loss | -0.0312 | +| n_updates | 71228 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.00014 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1408 | +| iterations | 13854 | +| time_elapsed | 20145 | +| total_timesteps | 28372992 | +| train/ | | +| approx_kl | 0.015835548 | +| clip_fraction | 0.366 | +| clip_range | 0.0679 | +| entropy_loss | -6.35 | +| explained_variance | 0.317 | +| learning_rate | 4.33e-05 | +| loss | -0.0317 | +| n_updates | 71232 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000173 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1408 | +| iterations | 13855 | +| time_elapsed | 20147 | +| total_timesteps | 28375040 | +| train/ | | +| approx_kl | 0.015880669 | +| clip_fraction | 0.339 | +| clip_range | 0.0679 | +| entropy_loss | -6.33 | +| explained_variance | 0.439 | +| learning_rate | 4.33e-05 | +| loss | -0.0274 | +| n_updates | 71236 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000147 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1408 | +| iterations | 13856 | +| time_elapsed | 20148 | +| total_timesteps | 28377088 | +| train/ | | +| approx_kl | 0.013595602 | +| clip_fraction | 0.341 | +| clip_range | 0.0679 | +| entropy_loss | -6.45 | +| explained_variance | 0.309 | +| learning_rate | 4.33e-05 | +| loss | -0.0285 | +| n_updates | 71240 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000113 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1408 | +| iterations | 13857 | +| time_elapsed | 20150 | +| total_timesteps | 28379136 | +| train/ | | +| approx_kl | 0.015187543 | +| clip_fraction | 0.356 | +| clip_range | 0.0679 | +| entropy_loss | -6.78 | +| explained_variance | -0.152 | +| learning_rate | 4.33e-05 | +| loss | -0.0264 | +| n_updates | 71244 | +| policy_gradient_loss | -0.0189 | +| value_loss | 9.87e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1408 | +| iterations | 13858 | +| time_elapsed | 20151 | +| total_timesteps | 28381184 | +| train/ | | +| approx_kl | 0.015700024 | +| clip_fraction | 0.328 | +| clip_range | 0.0679 | +| entropy_loss | -6.65 | +| explained_variance | 0.371 | +| learning_rate | 4.33e-05 | +| loss | -0.017 | +| n_updates | 71248 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000135 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1408 | +| iterations | 13859 | +| time_elapsed | 20153 | +| total_timesteps | 28383232 | +| train/ | | +| approx_kl | 0.014681075 | +| clip_fraction | 0.348 | +| clip_range | 0.0679 | +| entropy_loss | -5.97 | +| explained_variance | 0.571 | +| learning_rate | 4.33e-05 | +| loss | -0.0271 | +| n_updates | 71252 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000106 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1408 | +| iterations | 13860 | +| time_elapsed | 20154 | +| total_timesteps | 28385280 | +| train/ | | +| approx_kl | 0.015943611 | +| clip_fraction | 0.34 | +| clip_range | 0.0679 | +| entropy_loss | -6.03 | +| explained_variance | 0.558 | +| learning_rate | 4.33e-05 | +| loss | -0.0274 | +| n_updates | 71256 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000128 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1408 | +| iterations | 13861 | +| time_elapsed | 20156 | +| total_timesteps | 28387328 | +| train/ | | +| approx_kl | 0.014970547 | +| clip_fraction | 0.346 | +| clip_range | 0.0679 | +| entropy_loss | -6.28 | +| explained_variance | 0.399 | +| learning_rate | 4.33e-05 | +| loss | -0.0234 | +| n_updates | 71260 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000315 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1408 | +| iterations | 13862 | +| time_elapsed | 20157 | +| total_timesteps | 28389376 | +| train/ | | +| approx_kl | 0.01470541 | +| clip_fraction | 0.333 | +| clip_range | 0.0679 | +| entropy_loss | -5.87 | +| explained_variance | 0.421 | +| learning_rate | 4.33e-05 | +| loss | -0.0314 | +| n_updates | 71264 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000143 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1408 | +| iterations | 13863 | +| time_elapsed | 20159 | +| total_timesteps | 28391424 | +| train/ | | +| approx_kl | 0.012442346 | +| clip_fraction | 0.336 | +| clip_range | 0.0679 | +| entropy_loss | -5.56 | +| explained_variance | 0.563 | +| learning_rate | 4.33e-05 | +| loss | -0.0235 | +| n_updates | 71268 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000152 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1408 | +| iterations | 13864 | +| time_elapsed | 20160 | +| total_timesteps | 28393472 | +| train/ | | +| approx_kl | 0.013116443 | +| clip_fraction | 0.334 | +| clip_range | 0.0679 | +| entropy_loss | -6.12 | +| explained_variance | 0.196 | +| learning_rate | 4.33e-05 | +| loss | -0.0187 | +| n_updates | 71272 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000245 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1408 | +| iterations | 13865 | +| time_elapsed | 20162 | +| total_timesteps | 28395520 | +| train/ | | +| approx_kl | 0.013209632 | +| clip_fraction | 0.326 | +| clip_range | 0.0679 | +| entropy_loss | -6.69 | +| explained_variance | 0.209 | +| learning_rate | 4.33e-05 | +| loss | -0.0314 | +| n_updates | 71276 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000256 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1408 | +| iterations | 13866 | +| time_elapsed | 20163 | +| total_timesteps | 28397568 | +| train/ | | +| approx_kl | 0.012240252 | +| clip_fraction | 0.322 | +| clip_range | 0.0679 | +| entropy_loss | -6.8 | +| explained_variance | 0.368 | +| learning_rate | 4.33e-05 | +| loss | -0.0301 | +| n_updates | 71280 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.00012 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1408 | +| iterations | 13867 | +| time_elapsed | 20165 | +| total_timesteps | 28399616 | +| train/ | | +| approx_kl | 0.012697759 | +| clip_fraction | 0.328 | +| clip_range | 0.0679 | +| entropy_loss | -6.18 | +| explained_variance | 0.515 | +| learning_rate | 4.33e-05 | +| loss | -0.03 | +| n_updates | 71284 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000156 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1408 | +| iterations | 13868 | +| time_elapsed | 20166 | +| total_timesteps | 28401664 | +| train/ | | +| approx_kl | 0.01523805 | +| clip_fraction | 0.348 | +| clip_range | 0.0679 | +| entropy_loss | -5.96 | +| explained_variance | 0.525 | +| learning_rate | 4.33e-05 | +| loss | -0.0324 | +| n_updates | 71288 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000153 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1408 | +| iterations | 13869 | +| time_elapsed | 20168 | +| total_timesteps | 28403712 | +| train/ | | +| approx_kl | 0.011839062 | +| clip_fraction | 0.326 | +| clip_range | 0.0679 | +| entropy_loss | -5.86 | +| explained_variance | 0.348 | +| learning_rate | 4.33e-05 | +| loss | -0.0179 | +| n_updates | 71292 | +| policy_gradient_loss | -0.0144 | +| value_loss | 0.000364 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1408 | +| iterations | 13870 | +| time_elapsed | 20169 | +| total_timesteps | 28405760 | +| train/ | | +| approx_kl | 0.01329805 | +| clip_fraction | 0.359 | +| clip_range | 0.0679 | +| entropy_loss | -6.59 | +| explained_variance | 0.367 | +| learning_rate | 4.33e-05 | +| loss | -0.0314 | +| n_updates | 71296 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000118 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1408 | +| iterations | 13871 | +| time_elapsed | 20171 | +| total_timesteps | 28407808 | +| train/ | | +| approx_kl | 0.013573121 | +| clip_fraction | 0.339 | +| clip_range | 0.0679 | +| entropy_loss | -6.34 | +| explained_variance | 0.196 | +| learning_rate | 4.33e-05 | +| loss | -0.0313 | +| n_updates | 71300 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000257 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1408 | +| iterations | 13872 | +| time_elapsed | 20172 | +| total_timesteps | 28409856 | +| train/ | | +| approx_kl | 0.014019409 | +| clip_fraction | 0.356 | +| clip_range | 0.0679 | +| entropy_loss | -6.49 | +| explained_variance | -0.143 | +| learning_rate | 4.33e-05 | +| loss | -0.0308 | +| n_updates | 71304 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000193 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1408 | +| iterations | 13873 | +| time_elapsed | 20174 | +| total_timesteps | 28411904 | +| train/ | | +| approx_kl | 0.013743268 | +| clip_fraction | 0.353 | +| clip_range | 0.0679 | +| entropy_loss | -5.9 | +| explained_variance | 0.367 | +| learning_rate | 4.33e-05 | +| loss | -0.0307 | +| n_updates | 71308 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.00029 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1408 | +| iterations | 13874 | +| time_elapsed | 20175 | +| total_timesteps | 28413952 | +| train/ | | +| approx_kl | 0.016914483 | +| clip_fraction | 0.36 | +| clip_range | 0.0679 | +| entropy_loss | -5.72 | +| explained_variance | 0.475 | +| learning_rate | 4.33e-05 | +| loss | -0.0379 | +| n_updates | 71312 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000154 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1408 | +| iterations | 13875 | +| time_elapsed | 20177 | +| total_timesteps | 28416000 | +| train/ | | +| approx_kl | 0.017304173 | +| clip_fraction | 0.4 | +| clip_range | 0.0679 | +| entropy_loss | -6.39 | +| explained_variance | 0.375 | +| learning_rate | 4.33e-05 | +| loss | -0.0374 | +| n_updates | 71316 | +| policy_gradient_loss | -0.0238 | +| value_loss | 9.52e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1408 | +| iterations | 13876 | +| time_elapsed | 20178 | +| total_timesteps | 28418048 | +| train/ | | +| approx_kl | 0.013362577 | +| clip_fraction | 0.366 | +| clip_range | 0.0679 | +| entropy_loss | -6.39 | +| explained_variance | 0.235 | +| learning_rate | 4.33e-05 | +| loss | -0.0266 | +| n_updates | 71320 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000259 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1408 | +| iterations | 13877 | +| time_elapsed | 20180 | +| total_timesteps | 28420096 | +| train/ | | +| approx_kl | 0.01518143 | +| clip_fraction | 0.331 | +| clip_range | 0.0679 | +| entropy_loss | -6.01 | +| explained_variance | 0.277 | +| learning_rate | 4.33e-05 | +| loss | -0.0208 | +| n_updates | 71324 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000424 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1408 | +| iterations | 13878 | +| time_elapsed | 20181 | +| total_timesteps | 28422144 | +| train/ | | +| approx_kl | 0.013325025 | +| clip_fraction | 0.353 | +| clip_range | 0.0679 | +| entropy_loss | -6.22 | +| explained_variance | 0.453 | +| learning_rate | 4.33e-05 | +| loss | -0.0344 | +| n_updates | 71328 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000144 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1408 | +| iterations | 13879 | +| time_elapsed | 20183 | +| total_timesteps | 28424192 | +| train/ | | +| approx_kl | 0.012221683 | +| clip_fraction | 0.329 | +| clip_range | 0.0679 | +| entropy_loss | -6.06 | +| explained_variance | 0.365 | +| learning_rate | 4.32e-05 | +| loss | -0.0246 | +| n_updates | 71332 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000268 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1408 | +| iterations | 13880 | +| time_elapsed | 20185 | +| total_timesteps | 28426240 | +| train/ | | +| approx_kl | 0.015106838 | +| clip_fraction | 0.36 | +| clip_range | 0.0679 | +| entropy_loss | -6.1 | +| explained_variance | 0.537 | +| learning_rate | 4.32e-05 | +| loss | -0.0317 | +| n_updates | 71336 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000117 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1408 | +| iterations | 13881 | +| time_elapsed | 20186 | +| total_timesteps | 28428288 | +| train/ | | +| approx_kl | 0.012791797 | +| clip_fraction | 0.323 | +| clip_range | 0.0679 | +| entropy_loss | -6.09 | +| explained_variance | 0.587 | +| learning_rate | 4.32e-05 | +| loss | -0.0287 | +| n_updates | 71340 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000136 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1408 | +| iterations | 13882 | +| time_elapsed | 20188 | +| total_timesteps | 28430336 | +| train/ | | +| approx_kl | 0.014083341 | +| clip_fraction | 0.368 | +| clip_range | 0.0679 | +| entropy_loss | -6.15 | +| explained_variance | 0.33 | +| learning_rate | 4.32e-05 | +| loss | -0.0319 | +| n_updates | 71344 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.00011 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1408 | +| iterations | 13883 | +| time_elapsed | 20189 | +| total_timesteps | 28432384 | +| train/ | | +| approx_kl | 0.012027454 | +| clip_fraction | 0.321 | +| clip_range | 0.0679 | +| entropy_loss | -5.85 | +| explained_variance | 0.721 | +| learning_rate | 4.32e-05 | +| loss | -0.028 | +| n_updates | 71348 | +| policy_gradient_loss | -0.0172 | +| value_loss | 9.73e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1408 | +| iterations | 13884 | +| time_elapsed | 20191 | +| total_timesteps | 28434432 | +| train/ | | +| approx_kl | 0.011711868 | +| clip_fraction | 0.34 | +| clip_range | 0.0679 | +| entropy_loss | -6.1 | +| explained_variance | 0.494 | +| learning_rate | 4.32e-05 | +| loss | -0.0296 | +| n_updates | 71352 | +| policy_gradient_loss | -0.0196 | +| value_loss | 8.21e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1408 | +| iterations | 13885 | +| time_elapsed | 20192 | +| total_timesteps | 28436480 | +| train/ | | +| approx_kl | 0.013463917 | +| clip_fraction | 0.357 | +| clip_range | 0.0679 | +| entropy_loss | -6.04 | +| explained_variance | 0.411 | +| learning_rate | 4.32e-05 | +| loss | -0.0299 | +| n_updates | 71356 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000185 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1408 | +| iterations | 13886 | +| time_elapsed | 20194 | +| total_timesteps | 28438528 | +| train/ | | +| approx_kl | 0.0154360365 | +| clip_fraction | 0.373 | +| clip_range | 0.0679 | +| entropy_loss | -6.71 | +| explained_variance | -0.00623 | +| learning_rate | 4.32e-05 | +| loss | -0.0293 | +| n_updates | 71360 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000113 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1408 | +| iterations | 13887 | +| time_elapsed | 20195 | +| total_timesteps | 28440576 | +| train/ | | +| approx_kl | 0.010251645 | +| clip_fraction | 0.306 | +| clip_range | 0.0679 | +| entropy_loss | -6.89 | +| explained_variance | 0.085 | +| learning_rate | 4.32e-05 | +| loss | -0.0247 | +| n_updates | 71364 | +| policy_gradient_loss | -0.0146 | +| value_loss | 0.000163 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1408 | +| iterations | 13888 | +| time_elapsed | 20197 | +| total_timesteps | 28442624 | +| train/ | | +| approx_kl | 0.013427045 | +| clip_fraction | 0.34 | +| clip_range | 0.0679 | +| entropy_loss | -5.69 | +| explained_variance | 0.739 | +| learning_rate | 4.32e-05 | +| loss | -0.0316 | +| n_updates | 71368 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000108 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1408 | +| iterations | 13889 | +| time_elapsed | 20198 | +| total_timesteps | 28444672 | +| train/ | | +| approx_kl | 0.014588166 | +| clip_fraction | 0.369 | +| clip_range | 0.0679 | +| entropy_loss | -6.08 | +| explained_variance | 0.628 | +| learning_rate | 4.32e-05 | +| loss | -0.0269 | +| n_updates | 71372 | +| policy_gradient_loss | -0.0204 | +| value_loss | 9.48e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1408 | +| iterations | 13890 | +| time_elapsed | 20200 | +| total_timesteps | 28446720 | +| train/ | | +| approx_kl | 0.014357176 | +| clip_fraction | 0.329 | +| clip_range | 0.0679 | +| entropy_loss | -5.94 | +| explained_variance | 0.194 | +| learning_rate | 4.32e-05 | +| loss | -0.0295 | +| n_updates | 71376 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000222 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1408 | +| iterations | 13891 | +| time_elapsed | 20202 | +| total_timesteps | 28448768 | +| train/ | | +| approx_kl | 0.013388753 | +| clip_fraction | 0.378 | +| clip_range | 0.0679 | +| entropy_loss | -5.96 | +| explained_variance | 0.529 | +| learning_rate | 4.32e-05 | +| loss | -0.029 | +| n_updates | 71380 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1408 | +| iterations | 13892 | +| time_elapsed | 20203 | +| total_timesteps | 28450816 | +| train/ | | +| approx_kl | 0.015088299 | +| clip_fraction | 0.367 | +| clip_range | 0.0679 | +| entropy_loss | -5.6 | +| explained_variance | 0.76 | +| learning_rate | 4.32e-05 | +| loss | -0.0324 | +| n_updates | 71384 | +| policy_gradient_loss | -0.0221 | +| value_loss | 6.58e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1408 | +| iterations | 13893 | +| time_elapsed | 20205 | +| total_timesteps | 28452864 | +| train/ | | +| approx_kl | 0.015281616 | +| clip_fraction | 0.325 | +| clip_range | 0.0679 | +| entropy_loss | -5.96 | +| explained_variance | 0.0945 | +| learning_rate | 4.32e-05 | +| loss | -0.0287 | +| n_updates | 71388 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000154 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1408 | +| iterations | 13894 | +| time_elapsed | 20206 | +| total_timesteps | 28454912 | +| train/ | | +| approx_kl | 0.014288897 | +| clip_fraction | 0.352 | +| clip_range | 0.0679 | +| entropy_loss | -5.95 | +| explained_variance | 0.258 | +| learning_rate | 4.32e-05 | +| loss | -0.0232 | +| n_updates | 71392 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000324 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1408 | +| iterations | 13895 | +| time_elapsed | 20208 | +| total_timesteps | 28456960 | +| train/ | | +| approx_kl | 0.014908488 | +| clip_fraction | 0.359 | +| clip_range | 0.0679 | +| entropy_loss | -6.13 | +| explained_variance | 0.475 | +| learning_rate | 4.32e-05 | +| loss | -0.0303 | +| n_updates | 71396 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000168 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1408 | +| iterations | 13896 | +| time_elapsed | 20209 | +| total_timesteps | 28459008 | +| train/ | | +| approx_kl | 0.014158158 | +| clip_fraction | 0.381 | +| clip_range | 0.0679 | +| entropy_loss | -6.52 | +| explained_variance | -0.164 | +| learning_rate | 4.32e-05 | +| loss | -0.0317 | +| n_updates | 71400 | +| policy_gradient_loss | -0.0223 | +| value_loss | 9.87e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1408 | +| iterations | 13897 | +| time_elapsed | 20211 | +| total_timesteps | 28461056 | +| train/ | | +| approx_kl | 0.012500437 | +| clip_fraction | 0.334 | +| clip_range | 0.0679 | +| entropy_loss | -6.42 | +| explained_variance | 0.571 | +| learning_rate | 4.32e-05 | +| loss | -0.029 | +| n_updates | 71404 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000102 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1408 | +| iterations | 13898 | +| time_elapsed | 20212 | +| total_timesteps | 28463104 | +| train/ | | +| approx_kl | 0.012206414 | +| clip_fraction | 0.347 | +| clip_range | 0.0679 | +| entropy_loss | -6.6 | +| explained_variance | -0.0452 | +| learning_rate | 4.32e-05 | +| loss | -0.0287 | +| n_updates | 71408 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000224 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1408 | +| iterations | 13899 | +| time_elapsed | 20214 | +| total_timesteps | 28465152 | +| train/ | | +| approx_kl | 0.011668875 | +| clip_fraction | 0.351 | +| clip_range | 0.0679 | +| entropy_loss | -6.51 | +| explained_variance | 0.513 | +| learning_rate | 4.32e-05 | +| loss | -0.0355 | +| n_updates | 71412 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000129 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1408 | +| iterations | 13900 | +| time_elapsed | 20215 | +| total_timesteps | 28467200 | +| train/ | | +| approx_kl | 0.011634203 | +| clip_fraction | 0.324 | +| clip_range | 0.0679 | +| entropy_loss | -6.54 | +| explained_variance | 0.37 | +| learning_rate | 4.32e-05 | +| loss | -0.0298 | +| n_updates | 71416 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000183 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1408 | +| iterations | 13901 | +| time_elapsed | 20217 | +| total_timesteps | 28469248 | +| train/ | | +| approx_kl | 0.011624757 | +| clip_fraction | 0.348 | +| clip_range | 0.0679 | +| entropy_loss | -6.81 | +| explained_variance | 0.435 | +| learning_rate | 4.32e-05 | +| loss | -0.0318 | +| n_updates | 71420 | +| policy_gradient_loss | -0.0185 | +| value_loss | 9.61e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1408 | +| iterations | 13902 | +| time_elapsed | 20218 | +| total_timesteps | 28471296 | +| train/ | | +| approx_kl | 0.013793138 | +| clip_fraction | 0.335 | +| clip_range | 0.0679 | +| entropy_loss | -5.82 | +| explained_variance | 0.561 | +| learning_rate | 4.32e-05 | +| loss | -0.0288 | +| n_updates | 71424 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000206 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1408 | +| iterations | 13903 | +| time_elapsed | 20220 | +| total_timesteps | 28473344 | +| train/ | | +| approx_kl | 0.012393678 | +| clip_fraction | 0.342 | +| clip_range | 0.0679 | +| entropy_loss | -5.88 | +| explained_variance | 0.721 | +| learning_rate | 4.32e-05 | +| loss | -0.0319 | +| n_updates | 71428 | +| policy_gradient_loss | -0.0203 | +| value_loss | 6.37e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1408 | +| iterations | 13904 | +| time_elapsed | 20222 | +| total_timesteps | 28475392 | +| train/ | | +| approx_kl | 0.012872791 | +| clip_fraction | 0.305 | +| clip_range | 0.0679 | +| entropy_loss | -6.16 | +| explained_variance | 0.269 | +| learning_rate | 4.32e-05 | +| loss | -0.022 | +| n_updates | 71432 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000274 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1408 | +| iterations | 13905 | +| time_elapsed | 20223 | +| total_timesteps | 28477440 | +| train/ | | +| approx_kl | 0.011374308 | +| clip_fraction | 0.333 | +| clip_range | 0.0679 | +| entropy_loss | -6.04 | +| explained_variance | 0.62 | +| learning_rate | 4.32e-05 | +| loss | -0.0322 | +| n_updates | 71436 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000101 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1408 | +| iterations | 13906 | +| time_elapsed | 20225 | +| total_timesteps | 28479488 | +| train/ | | +| approx_kl | 0.016660195 | +| clip_fraction | 0.355 | +| clip_range | 0.0679 | +| entropy_loss | -6.27 | +| explained_variance | 0.289 | +| learning_rate | 4.32e-05 | +| loss | -0.0368 | +| n_updates | 71440 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000171 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1408 | +| iterations | 13907 | +| time_elapsed | 20226 | +| total_timesteps | 28481536 | +| train/ | | +| approx_kl | 0.013237057 | +| clip_fraction | 0.338 | +| clip_range | 0.0679 | +| entropy_loss | -6.11 | +| explained_variance | 0.522 | +| learning_rate | 4.32e-05 | +| loss | -0.0245 | +| n_updates | 71444 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000145 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1408 | +| iterations | 13908 | +| time_elapsed | 20228 | +| total_timesteps | 28483584 | +| train/ | | +| approx_kl | 0.015379717 | +| clip_fraction | 0.364 | +| clip_range | 0.0679 | +| entropy_loss | -6.21 | +| explained_variance | -0.141 | +| learning_rate | 4.32e-05 | +| loss | -0.0304 | +| n_updates | 71448 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000145 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1408 | +| iterations | 13909 | +| time_elapsed | 20229 | +| total_timesteps | 28485632 | +| train/ | | +| approx_kl | 0.014840754 | +| clip_fraction | 0.316 | +| clip_range | 0.0679 | +| entropy_loss | -5.89 | +| explained_variance | 0.481 | +| learning_rate | 4.32e-05 | +| loss | -0.0288 | +| n_updates | 71452 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000239 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1408 | +| iterations | 13910 | +| time_elapsed | 20231 | +| total_timesteps | 28487680 | +| train/ | | +| approx_kl | 0.015367131 | +| clip_fraction | 0.353 | +| clip_range | 0.0679 | +| entropy_loss | -6.01 | +| explained_variance | 0.228 | +| learning_rate | 4.32e-05 | +| loss | -0.0313 | +| n_updates | 71456 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.00021 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1408 | +| iterations | 13911 | +| time_elapsed | 20232 | +| total_timesteps | 28489728 | +| train/ | | +| approx_kl | 0.014360583 | +| clip_fraction | 0.349 | +| clip_range | 0.0679 | +| entropy_loss | -5.97 | +| explained_variance | 0.399 | +| learning_rate | 4.32e-05 | +| loss | -0.0339 | +| n_updates | 71460 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000193 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1408 | +| iterations | 13912 | +| time_elapsed | 20234 | +| total_timesteps | 28491776 | +| train/ | | +| approx_kl | 0.0137082245 | +| clip_fraction | 0.357 | +| clip_range | 0.0679 | +| entropy_loss | -6.17 | +| explained_variance | 0.43 | +| learning_rate | 4.32e-05 | +| loss | -0.0297 | +| n_updates | 71464 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.00018 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1408 | +| iterations | 13913 | +| time_elapsed | 20235 | +| total_timesteps | 28493824 | +| train/ | | +| approx_kl | 0.013832524 | +| clip_fraction | 0.336 | +| clip_range | 0.0679 | +| entropy_loss | -6.33 | +| explained_variance | 0.515 | +| learning_rate | 4.32e-05 | +| loss | -0.0263 | +| n_updates | 71468 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000126 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1408 | +| iterations | 13914 | +| time_elapsed | 20237 | +| total_timesteps | 28495872 | +| train/ | | +| approx_kl | 0.016436625 | +| clip_fraction | 0.321 | +| clip_range | 0.0679 | +| entropy_loss | -5.86 | +| explained_variance | 0.274 | +| learning_rate | 4.32e-05 | +| loss | -0.0315 | +| n_updates | 71472 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.00037 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1408 | +| iterations | 13915 | +| time_elapsed | 20238 | +| total_timesteps | 28497920 | +| train/ | | +| approx_kl | 0.011149914 | +| clip_fraction | 0.326 | +| clip_range | 0.0679 | +| entropy_loss | -5.97 | +| explained_variance | 0.335 | +| learning_rate | 4.32e-05 | +| loss | -0.0281 | +| n_updates | 71476 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.000305 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1408 | +| iterations | 13916 | +| time_elapsed | 20240 | +| total_timesteps | 28499968 | +| train/ | | +| approx_kl | 0.013277306 | +| clip_fraction | 0.35 | +| clip_range | 0.0679 | +| entropy_loss | -6.4 | +| explained_variance | -0.314 | +| learning_rate | 4.32e-05 | +| loss | -0.0342 | +| n_updates | 71480 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.00017 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1408 | +| iterations | 13917 | +| time_elapsed | 20241 | +| total_timesteps | 28502016 | +| train/ | | +| approx_kl | 0.015391992 | +| clip_fraction | 0.354 | +| clip_range | 0.0679 | +| entropy_loss | -6.44 | +| explained_variance | 0.395 | +| learning_rate | 4.32e-05 | +| loss | -0.0284 | +| n_updates | 71484 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000183 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1408 | +| iterations | 13918 | +| time_elapsed | 20243 | +| total_timesteps | 28504064 | +| train/ | | +| approx_kl | 0.012669468 | +| clip_fraction | 0.34 | +| clip_range | 0.0679 | +| entropy_loss | -6.09 | +| explained_variance | 0.551 | +| learning_rate | 4.32e-05 | +| loss | -0.0343 | +| n_updates | 71488 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000121 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1408 | +| iterations | 13919 | +| time_elapsed | 20244 | +| total_timesteps | 28506112 | +| train/ | | +| approx_kl | 0.013255786 | +| clip_fraction | 0.358 | +| clip_range | 0.0679 | +| entropy_loss | -6.72 | +| explained_variance | 0.000527 | +| learning_rate | 4.32e-05 | +| loss | -0.0309 | +| n_updates | 71492 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000133 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1408 | +| iterations | 13920 | +| time_elapsed | 20246 | +| total_timesteps | 28508160 | +| train/ | | +| approx_kl | 0.010688418 | +| clip_fraction | 0.321 | +| clip_range | 0.0679 | +| entropy_loss | -6.29 | +| explained_variance | 0.438 | +| learning_rate | 4.32e-05 | +| loss | -0.0225 | +| n_updates | 71496 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.000228 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1408 | +| iterations | 13921 | +| time_elapsed | 20248 | +| total_timesteps | 28510208 | +| train/ | | +| approx_kl | 0.011672148 | +| clip_fraction | 0.312 | +| clip_range | 0.0679 | +| entropy_loss | -6.7 | +| explained_variance | 0.3 | +| learning_rate | 4.32e-05 | +| loss | -0.0322 | +| n_updates | 71500 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.00017 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1408 | +| iterations | 13922 | +| time_elapsed | 20249 | +| total_timesteps | 28512256 | +| train/ | | +| approx_kl | 0.012366756 | +| clip_fraction | 0.355 | +| clip_range | 0.0679 | +| entropy_loss | -6.46 | +| explained_variance | 0.344 | +| learning_rate | 4.32e-05 | +| loss | -0.03 | +| n_updates | 71504 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000259 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1408 | +| iterations | 13923 | +| time_elapsed | 20251 | +| total_timesteps | 28514304 | +| train/ | | +| approx_kl | 0.010345902 | +| clip_fraction | 0.328 | +| clip_range | 0.0679 | +| entropy_loss | -6.7 | +| explained_variance | 0.0793 | +| learning_rate | 4.32e-05 | +| loss | -0.022 | +| n_updates | 71508 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000281 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1408 | +| iterations | 13924 | +| time_elapsed | 20252 | +| total_timesteps | 28516352 | +| train/ | | +| approx_kl | 0.010503732 | +| clip_fraction | 0.335 | +| clip_range | 0.0679 | +| entropy_loss | -6.33 | +| explained_variance | 0.475 | +| learning_rate | 4.32e-05 | +| loss | -0.03 | +| n_updates | 71512 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000202 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1408 | +| iterations | 13925 | +| time_elapsed | 20254 | +| total_timesteps | 28518400 | +| train/ | | +| approx_kl | 0.013085278 | +| clip_fraction | 0.323 | +| clip_range | 0.0679 | +| entropy_loss | -5.98 | +| explained_variance | 0.426 | +| learning_rate | 4.32e-05 | +| loss | -0.0241 | +| n_updates | 71516 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000323 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1408 | +| iterations | 13926 | +| time_elapsed | 20255 | +| total_timesteps | 28520448 | +| train/ | | +| approx_kl | 0.015589318 | +| clip_fraction | 0.383 | +| clip_range | 0.0679 | +| entropy_loss | -5.41 | +| explained_variance | 0.777 | +| learning_rate | 4.32e-05 | +| loss | -0.0361 | +| n_updates | 71520 | +| policy_gradient_loss | -0.0227 | +| value_loss | 8.51e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1408 | +| iterations | 13927 | +| time_elapsed | 20257 | +| total_timesteps | 28522496 | +| train/ | | +| approx_kl | 0.013891826 | +| clip_fraction | 0.354 | +| clip_range | 0.0679 | +| entropy_loss | -6.78 | +| explained_variance | 0.0913 | +| learning_rate | 4.32e-05 | +| loss | -0.031 | +| n_updates | 71524 | +| policy_gradient_loss | -0.0193 | +| value_loss | 9.51e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1408 | +| iterations | 13928 | +| time_elapsed | 20258 | +| total_timesteps | 28524544 | +| train/ | | +| approx_kl | 0.010572026 | +| clip_fraction | 0.331 | +| clip_range | 0.0679 | +| entropy_loss | -6.7 | +| explained_variance | 0.387 | +| learning_rate | 4.32e-05 | +| loss | -0.0257 | +| n_updates | 71528 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000218 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1408 | +| iterations | 13929 | +| time_elapsed | 20260 | +| total_timesteps | 28526592 | +| train/ | | +| approx_kl | 0.01189984 | +| clip_fraction | 0.332 | +| clip_range | 0.0679 | +| entropy_loss | -5.81 | +| explained_variance | 0.407 | +| learning_rate | 4.32e-05 | +| loss | -0.0273 | +| n_updates | 71532 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000379 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1407 | +| iterations | 13930 | +| time_elapsed | 20261 | +| total_timesteps | 28528640 | +| train/ | | +| approx_kl | 0.011673664 | +| clip_fraction | 0.306 | +| clip_range | 0.0679 | +| entropy_loss | -6.1 | +| explained_variance | 0.216 | +| learning_rate | 4.32e-05 | +| loss | -0.0237 | +| n_updates | 71536 | +| policy_gradient_loss | -0.0146 | +| value_loss | 0.000564 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1407 | +| iterations | 13931 | +| time_elapsed | 20263 | +| total_timesteps | 28530688 | +| train/ | | +| approx_kl | 0.012684658 | +| clip_fraction | 0.343 | +| clip_range | 0.0679 | +| entropy_loss | -5.48 | +| explained_variance | 0.628 | +| learning_rate | 4.32e-05 | +| loss | -0.0303 | +| n_updates | 71540 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000196 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1407 | +| iterations | 13932 | +| time_elapsed | 20264 | +| total_timesteps | 28532736 | +| train/ | | +| approx_kl | 0.012699612 | +| clip_fraction | 0.336 | +| clip_range | 0.0679 | +| entropy_loss | -6.45 | +| explained_variance | -0.184 | +| learning_rate | 4.32e-05 | +| loss | -0.0313 | +| n_updates | 71544 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000178 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1407 | +| iterations | 13933 | +| time_elapsed | 20266 | +| total_timesteps | 28534784 | +| train/ | | +| approx_kl | 0.015973657 | +| clip_fraction | 0.356 | +| clip_range | 0.0679 | +| entropy_loss | -6.91 | +| explained_variance | -0.162 | +| learning_rate | 4.32e-05 | +| loss | -0.0309 | +| n_updates | 71548 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000202 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1407 | +| iterations | 13934 | +| time_elapsed | 20268 | +| total_timesteps | 28536832 | +| train/ | | +| approx_kl | 0.012957996 | +| clip_fraction | 0.345 | +| clip_range | 0.0679 | +| entropy_loss | -7.12 | +| explained_variance | -0.111 | +| learning_rate | 4.32e-05 | +| loss | -0.0328 | +| n_updates | 71552 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000142 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1407 | +| iterations | 13935 | +| time_elapsed | 20269 | +| total_timesteps | 28538880 | +| train/ | | +| approx_kl | 0.010308892 | +| clip_fraction | 0.331 | +| clip_range | 0.0679 | +| entropy_loss | -7.15 | +| explained_variance | -0.111 | +| learning_rate | 4.32e-05 | +| loss | -0.0265 | +| n_updates | 71556 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000191 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1407 | +| iterations | 13936 | +| time_elapsed | 20271 | +| total_timesteps | 28540928 | +| train/ | | +| approx_kl | 0.013390742 | +| clip_fraction | 0.349 | +| clip_range | 0.0679 | +| entropy_loss | -6.19 | +| explained_variance | 0.585 | +| learning_rate | 4.32e-05 | +| loss | -0.0258 | +| n_updates | 71560 | +| policy_gradient_loss | -0.0178 | +| value_loss | 6.86e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1407 | +| iterations | 13937 | +| time_elapsed | 20272 | +| total_timesteps | 28542976 | +| train/ | | +| approx_kl | 0.012975998 | +| clip_fraction | 0.354 | +| clip_range | 0.0679 | +| entropy_loss | -6.47 | +| explained_variance | 0.319 | +| learning_rate | 4.32e-05 | +| loss | -0.0257 | +| n_updates | 71564 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000228 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1407 | +| iterations | 13938 | +| time_elapsed | 20274 | +| total_timesteps | 28545024 | +| train/ | | +| approx_kl | 0.010841744 | +| clip_fraction | 0.304 | +| clip_range | 0.0679 | +| entropy_loss | -6.1 | +| explained_variance | 0.399 | +| learning_rate | 4.32e-05 | +| loss | -0.0171 | +| n_updates | 71568 | +| policy_gradient_loss | -0.0134 | +| value_loss | 0.000212 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1407 | +| iterations | 13939 | +| time_elapsed | 20275 | +| total_timesteps | 28547072 | +| train/ | | +| approx_kl | 0.013451643 | +| clip_fraction | 0.356 | +| clip_range | 0.0679 | +| entropy_loss | -5.53 | +| explained_variance | 0.639 | +| learning_rate | 4.32e-05 | +| loss | -0.0261 | +| n_updates | 71572 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000164 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1407 | +| iterations | 13940 | +| time_elapsed | 20277 | +| total_timesteps | 28549120 | +| train/ | | +| approx_kl | 0.016496692 | +| clip_fraction | 0.368 | +| clip_range | 0.0679 | +| entropy_loss | -5.86 | +| explained_variance | 0.438 | +| learning_rate | 4.32e-05 | +| loss | -0.035 | +| n_updates | 71576 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000102 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1407 | +| iterations | 13941 | +| time_elapsed | 20278 | +| total_timesteps | 28551168 | +| train/ | | +| approx_kl | 0.016130708 | +| clip_fraction | 0.355 | +| clip_range | 0.0679 | +| entropy_loss | -6.35 | +| explained_variance | 0.0841 | +| learning_rate | 4.32e-05 | +| loss | -0.0302 | +| n_updates | 71580 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.00015 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1407 | +| iterations | 13942 | +| time_elapsed | 20280 | +| total_timesteps | 28553216 | +| train/ | | +| approx_kl | 0.014846562 | +| clip_fraction | 0.335 | +| clip_range | 0.0679 | +| entropy_loss | -6.24 | +| explained_variance | 0.305 | +| learning_rate | 4.32e-05 | +| loss | -0.0259 | +| n_updates | 71584 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000329 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1407 | +| iterations | 13943 | +| time_elapsed | 20281 | +| total_timesteps | 28555264 | +| train/ | | +| approx_kl | 0.017479282 | +| clip_fraction | 0.403 | +| clip_range | 0.0679 | +| entropy_loss | -5.87 | +| explained_variance | 0.474 | +| learning_rate | 4.32e-05 | +| loss | -0.0306 | +| n_updates | 71588 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000151 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1407 | +| iterations | 13944 | +| time_elapsed | 20283 | +| total_timesteps | 28557312 | +| train/ | | +| approx_kl | 0.012657537 | +| clip_fraction | 0.358 | +| clip_range | 0.0679 | +| entropy_loss | -6.69 | +| explained_variance | -0.00511 | +| learning_rate | 4.32e-05 | +| loss | -0.0332 | +| n_updates | 71592 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.00017 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1407 | +| iterations | 13945 | +| time_elapsed | 20284 | +| total_timesteps | 28559360 | +| train/ | | +| approx_kl | 0.012524316 | +| clip_fraction | 0.333 | +| clip_range | 0.0679 | +| entropy_loss | -6.46 | +| explained_variance | 0.474 | +| learning_rate | 4.32e-05 | +| loss | -0.0376 | +| n_updates | 71596 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000132 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1407 | +| iterations | 13946 | +| time_elapsed | 20286 | +| total_timesteps | 28561408 | +| train/ | | +| approx_kl | 0.013145706 | +| clip_fraction | 0.363 | +| clip_range | 0.0679 | +| entropy_loss | -6.82 | +| explained_variance | -0.197 | +| learning_rate | 4.32e-05 | +| loss | -0.0337 | +| n_updates | 71600 | +| policy_gradient_loss | -0.0213 | +| value_loss | 8.1e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1407 | +| iterations | 13947 | +| time_elapsed | 20287 | +| total_timesteps | 28563456 | +| train/ | | +| approx_kl | 0.0149245085 | +| clip_fraction | 0.331 | +| clip_range | 0.0679 | +| entropy_loss | -6.25 | +| explained_variance | 0.462 | +| learning_rate | 4.32e-05 | +| loss | -0.0282 | +| n_updates | 71604 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000193 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1407 | +| iterations | 13948 | +| time_elapsed | 20289 | +| total_timesteps | 28565504 | +| train/ | | +| approx_kl | 0.01792003 | +| clip_fraction | 0.306 | +| clip_range | 0.0679 | +| entropy_loss | -5.91 | +| explained_variance | 0.438 | +| learning_rate | 4.32e-05 | +| loss | -0.027 | +| n_updates | 71608 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000264 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1407 | +| iterations | 13949 | +| time_elapsed | 20290 | +| total_timesteps | 28567552 | +| train/ | | +| approx_kl | 0.01213835 | +| clip_fraction | 0.324 | +| clip_range | 0.0679 | +| entropy_loss | -5.67 | +| explained_variance | 0.584 | +| learning_rate | 4.32e-05 | +| loss | -0.0269 | +| n_updates | 71612 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000151 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1407 | +| iterations | 13950 | +| time_elapsed | 20292 | +| total_timesteps | 28569600 | +| train/ | | +| approx_kl | 0.016241223 | +| clip_fraction | 0.37 | +| clip_range | 0.0679 | +| entropy_loss | -6.51 | +| explained_variance | -0.156 | +| learning_rate | 4.32e-05 | +| loss | -0.0327 | +| n_updates | 71616 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000129 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1407 | +| iterations | 13951 | +| time_elapsed | 20293 | +| total_timesteps | 28571648 | +| train/ | | +| approx_kl | 0.012752803 | +| clip_fraction | 0.365 | +| clip_range | 0.0679 | +| entropy_loss | -6.65 | +| explained_variance | 0.384 | +| learning_rate | 4.32e-05 | +| loss | -0.0314 | +| n_updates | 71620 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000162 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1407 | +| iterations | 13952 | +| time_elapsed | 20295 | +| total_timesteps | 28573696 | +| train/ | | +| approx_kl | 0.01476733 | +| clip_fraction | 0.352 | +| clip_range | 0.0679 | +| entropy_loss | -5.84 | +| explained_variance | 0.784 | +| learning_rate | 4.32e-05 | +| loss | -0.0296 | +| n_updates | 71624 | +| policy_gradient_loss | -0.0192 | +| value_loss | 6.73e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1407 | +| iterations | 13953 | +| time_elapsed | 20296 | +| total_timesteps | 28575744 | +| train/ | | +| approx_kl | 0.013639975 | +| clip_fraction | 0.343 | +| clip_range | 0.0679 | +| entropy_loss | -6.09 | +| explained_variance | 0.111 | +| learning_rate | 4.32e-05 | +| loss | -0.0291 | +| n_updates | 71628 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1407 | +| iterations | 13954 | +| time_elapsed | 20298 | +| total_timesteps | 28577792 | +| train/ | | +| approx_kl | 0.012368441 | +| clip_fraction | 0.348 | +| clip_range | 0.0679 | +| entropy_loss | -6.38 | +| explained_variance | 0.466 | +| learning_rate | 4.32e-05 | +| loss | -0.0323 | +| n_updates | 71632 | +| policy_gradient_loss | -0.0176 | +| value_loss | 7.35e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1407 | +| iterations | 13955 | +| time_elapsed | 20299 | +| total_timesteps | 28579840 | +| train/ | | +| approx_kl | 0.013282183 | +| clip_fraction | 0.332 | +| clip_range | 0.0679 | +| entropy_loss | -6.5 | +| explained_variance | 0.425 | +| learning_rate | 4.32e-05 | +| loss | -0.0266 | +| n_updates | 71636 | +| policy_gradient_loss | -0.0171 | +| value_loss | 9.95e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1407 | +| iterations | 13956 | +| time_elapsed | 20301 | +| total_timesteps | 28581888 | +| train/ | | +| approx_kl | 0.015045783 | +| clip_fraction | 0.326 | +| clip_range | 0.0679 | +| entropy_loss | -6.39 | +| explained_variance | 0.508 | +| learning_rate | 4.32e-05 | +| loss | -0.0292 | +| n_updates | 71640 | +| policy_gradient_loss | -0.0175 | +| value_loss | 8.72e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1407 | +| iterations | 13957 | +| time_elapsed | 20302 | +| total_timesteps | 28583936 | +| train/ | | +| approx_kl | 0.014042576 | +| clip_fraction | 0.319 | +| clip_range | 0.0679 | +| entropy_loss | -6.24 | +| explained_variance | 0.521 | +| learning_rate | 4.32e-05 | +| loss | -0.0261 | +| n_updates | 71644 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000114 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1407 | +| iterations | 13958 | +| time_elapsed | 20304 | +| total_timesteps | 28585984 | +| train/ | | +| approx_kl | 0.011070204 | +| clip_fraction | 0.288 | +| clip_range | 0.0679 | +| entropy_loss | -5.45 | +| explained_variance | 0.449 | +| learning_rate | 4.32e-05 | +| loss | -0.019 | +| n_updates | 71648 | +| policy_gradient_loss | -0.0121 | +| value_loss | 0.000399 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1407 | +| iterations | 13959 | +| time_elapsed | 20306 | +| total_timesteps | 28588032 | +| train/ | | +| approx_kl | 0.01396294 | +| clip_fraction | 0.356 | +| clip_range | 0.0679 | +| entropy_loss | -6 | +| explained_variance | 0.472 | +| learning_rate | 4.32e-05 | +| loss | -0.0321 | +| n_updates | 71652 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000177 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1407 | +| iterations | 13960 | +| time_elapsed | 20307 | +| total_timesteps | 28590080 | +| train/ | | +| approx_kl | 0.012537809 | +| clip_fraction | 0.328 | +| clip_range | 0.0679 | +| entropy_loss | -6.79 | +| explained_variance | 0.0626 | +| learning_rate | 4.32e-05 | +| loss | -0.0278 | +| n_updates | 71656 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000254 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1407 | +| iterations | 13961 | +| time_elapsed | 20309 | +| total_timesteps | 28592128 | +| train/ | | +| approx_kl | 0.011454571 | +| clip_fraction | 0.319 | +| clip_range | 0.0679 | +| entropy_loss | -5.93 | +| explained_variance | 0.563 | +| learning_rate | 4.32e-05 | +| loss | -0.0308 | +| n_updates | 71660 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000215 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1407 | +| iterations | 13962 | +| time_elapsed | 20310 | +| total_timesteps | 28594176 | +| train/ | | +| approx_kl | 0.0137429405 | +| clip_fraction | 0.33 | +| clip_range | 0.0679 | +| entropy_loss | -6.01 | +| explained_variance | 0.17 | +| learning_rate | 4.32e-05 | +| loss | -0.0376 | +| n_updates | 71664 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000256 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.385 | +| time/ | | +| fps | 1407 | +| iterations | 13963 | +| time_elapsed | 20312 | +| total_timesteps | 28596224 | +| train/ | | +| approx_kl | 0.013387155 | +| clip_fraction | 0.33 | +| clip_range | 0.0679 | +| entropy_loss | -5.89 | +| explained_variance | 0.266 | +| learning_rate | 4.32e-05 | +| loss | -0.0235 | +| n_updates | 71668 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000412 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1407 | +| iterations | 13964 | +| time_elapsed | 20313 | +| total_timesteps | 28598272 | +| train/ | | +| approx_kl | 0.012813633 | +| clip_fraction | 0.337 | +| clip_range | 0.0679 | +| entropy_loss | -5.9 | +| explained_variance | 0.392 | +| learning_rate | 4.32e-05 | +| loss | -0.0332 | +| n_updates | 71672 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000162 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1407 | +| iterations | 13965 | +| time_elapsed | 20315 | +| total_timesteps | 28600320 | +| train/ | | +| approx_kl | 0.01669054 | +| clip_fraction | 0.352 | +| clip_range | 0.0679 | +| entropy_loss | -5.85 | +| explained_variance | 0.688 | +| learning_rate | 4.32e-05 | +| loss | -0.0274 | +| n_updates | 71676 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000116 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1407 | +| iterations | 13966 | +| time_elapsed | 20316 | +| total_timesteps | 28602368 | +| train/ | | +| approx_kl | 0.013956312 | +| clip_fraction | 0.371 | +| clip_range | 0.0678 | +| entropy_loss | -6.87 | +| explained_variance | -0.48 | +| learning_rate | 4.32e-05 | +| loss | -0.0379 | +| n_updates | 71680 | +| policy_gradient_loss | -0.0231 | +| value_loss | 5.63e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1407 | +| iterations | 13967 | +| time_elapsed | 20318 | +| total_timesteps | 28604416 | +| train/ | | +| approx_kl | 0.011820877 | +| clip_fraction | 0.315 | +| clip_range | 0.0678 | +| entropy_loss | -6.21 | +| explained_variance | 0.703 | +| learning_rate | 4.32e-05 | +| loss | -0.0323 | +| n_updates | 71684 | +| policy_gradient_loss | -0.019 | +| value_loss | 9.45e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1407 | +| iterations | 13968 | +| time_elapsed | 20319 | +| total_timesteps | 28606464 | +| train/ | | +| approx_kl | 0.012545933 | +| clip_fraction | 0.333 | +| clip_range | 0.0678 | +| entropy_loss | -6.22 | +| explained_variance | 0.681 | +| learning_rate | 4.32e-05 | +| loss | -0.0302 | +| n_updates | 71688 | +| policy_gradient_loss | -0.0202 | +| value_loss | 7.53e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1407 | +| iterations | 13969 | +| time_elapsed | 20321 | +| total_timesteps | 28608512 | +| train/ | | +| approx_kl | 0.015112618 | +| clip_fraction | 0.343 | +| clip_range | 0.0678 | +| entropy_loss | -6.3 | +| explained_variance | 0.146 | +| learning_rate | 4.32e-05 | +| loss | -0.0289 | +| n_updates | 71692 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000123 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1407 | +| iterations | 13970 | +| time_elapsed | 20322 | +| total_timesteps | 28610560 | +| train/ | | +| approx_kl | 0.013487174 | +| clip_fraction | 0.322 | +| clip_range | 0.0678 | +| entropy_loss | -5.66 | +| explained_variance | 0.711 | +| learning_rate | 4.32e-05 | +| loss | -0.0255 | +| n_updates | 71696 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000114 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1407 | +| iterations | 13971 | +| time_elapsed | 20324 | +| total_timesteps | 28612608 | +| train/ | | +| approx_kl | 0.015223741 | +| clip_fraction | 0.366 | +| clip_range | 0.0678 | +| entropy_loss | -6.22 | +| explained_variance | 0.367 | +| learning_rate | 4.32e-05 | +| loss | -0.0277 | +| n_updates | 71700 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000132 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1407 | +| iterations | 13972 | +| time_elapsed | 20325 | +| total_timesteps | 28614656 | +| train/ | | +| approx_kl | 0.012464599 | +| clip_fraction | 0.347 | +| clip_range | 0.0678 | +| entropy_loss | -6.46 | +| explained_variance | 0.435 | +| learning_rate | 4.32e-05 | +| loss | -0.0217 | +| n_updates | 71704 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000196 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1407 | +| iterations | 13973 | +| time_elapsed | 20327 | +| total_timesteps | 28616704 | +| train/ | | +| approx_kl | 0.010654321 | +| clip_fraction | 0.309 | +| clip_range | 0.0678 | +| entropy_loss | -6.06 | +| explained_variance | 0.346 | +| learning_rate | 4.32e-05 | +| loss | -0.0255 | +| n_updates | 71708 | +| policy_gradient_loss | -0.0145 | +| value_loss | 0.000252 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1407 | +| iterations | 13974 | +| time_elapsed | 20328 | +| total_timesteps | 28618752 | +| train/ | | +| approx_kl | 0.010353748 | +| clip_fraction | 0.298 | +| clip_range | 0.0678 | +| entropy_loss | -6.23 | +| explained_variance | 0.319 | +| learning_rate | 4.32e-05 | +| loss | -0.0271 | +| n_updates | 71712 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000212 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1407 | +| iterations | 13975 | +| time_elapsed | 20330 | +| total_timesteps | 28620800 | +| train/ | | +| approx_kl | 0.012931228 | +| clip_fraction | 0.339 | +| clip_range | 0.0678 | +| entropy_loss | -6.08 | +| explained_variance | 0.536 | +| learning_rate | 4.32e-05 | +| loss | -0.025 | +| n_updates | 71716 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000129 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1407 | +| iterations | 13976 | +| time_elapsed | 20331 | +| total_timesteps | 28622848 | +| train/ | | +| approx_kl | 0.012815371 | +| clip_fraction | 0.333 | +| clip_range | 0.0678 | +| entropy_loss | -6.1 | +| explained_variance | 0.46 | +| learning_rate | 4.32e-05 | +| loss | -0.0247 | +| n_updates | 71720 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000181 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1407 | +| iterations | 13977 | +| time_elapsed | 20333 | +| total_timesteps | 28624896 | +| train/ | | +| approx_kl | 0.012756737 | +| clip_fraction | 0.337 | +| clip_range | 0.0678 | +| entropy_loss | -5.91 | +| explained_variance | 0.549 | +| learning_rate | 4.32e-05 | +| loss | -0.0283 | +| n_updates | 71724 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000154 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1407 | +| iterations | 13978 | +| time_elapsed | 20334 | +| total_timesteps | 28626944 | +| train/ | | +| approx_kl | 0.009593774 | +| clip_fraction | 0.29 | +| clip_range | 0.0678 | +| entropy_loss | -6.63 | +| explained_variance | 0.23 | +| learning_rate | 4.32e-05 | +| loss | -0.0278 | +| n_updates | 71728 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000295 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1407 | +| iterations | 13979 | +| time_elapsed | 20336 | +| total_timesteps | 28628992 | +| train/ | | +| approx_kl | 0.010137849 | +| clip_fraction | 0.315 | +| clip_range | 0.0678 | +| entropy_loss | -6.64 | +| explained_variance | 0.175 | +| learning_rate | 4.32e-05 | +| loss | -0.0238 | +| n_updates | 71732 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000255 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1407 | +| iterations | 13980 | +| time_elapsed | 20337 | +| total_timesteps | 28631040 | +| train/ | | +| approx_kl | 0.0116925575 | +| clip_fraction | 0.34 | +| clip_range | 0.0678 | +| entropy_loss | -6.46 | +| explained_variance | 0.273 | +| learning_rate | 4.32e-05 | +| loss | -0.0262 | +| n_updates | 71736 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.00031 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1407 | +| iterations | 13981 | +| time_elapsed | 20339 | +| total_timesteps | 28633088 | +| train/ | | +| approx_kl | 0.015441949 | +| clip_fraction | 0.358 | +| clip_range | 0.0678 | +| entropy_loss | -6.09 | +| explained_variance | 0.0948 | +| learning_rate | 4.32e-05 | +| loss | -0.03 | +| n_updates | 71740 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000195 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1407 | +| iterations | 13982 | +| time_elapsed | 20340 | +| total_timesteps | 28635136 | +| train/ | | +| approx_kl | 0.015445389 | +| clip_fraction | 0.376 | +| clip_range | 0.0678 | +| entropy_loss | -6.03 | +| explained_variance | 0.585 | +| learning_rate | 4.32e-05 | +| loss | -0.0366 | +| n_updates | 71744 | +| policy_gradient_loss | -0.0235 | +| value_loss | 7.38e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1407 | +| iterations | 13983 | +| time_elapsed | 20342 | +| total_timesteps | 28637184 | +| train/ | | +| approx_kl | 0.013636588 | +| clip_fraction | 0.348 | +| clip_range | 0.0678 | +| entropy_loss | -6.08 | +| explained_variance | 0.572 | +| learning_rate | 4.32e-05 | +| loss | -0.0281 | +| n_updates | 71748 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000122 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1407 | +| iterations | 13984 | +| time_elapsed | 20343 | +| total_timesteps | 28639232 | +| train/ | | +| approx_kl | 0.008883196 | +| clip_fraction | 0.291 | +| clip_range | 0.0678 | +| entropy_loss | -6.21 | +| explained_variance | 0.395 | +| learning_rate | 4.32e-05 | +| loss | -0.0236 | +| n_updates | 71752 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.000268 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1407 | +| iterations | 13985 | +| time_elapsed | 20345 | +| total_timesteps | 28641280 | +| train/ | | +| approx_kl | 0.010676088 | +| clip_fraction | 0.304 | +| clip_range | 0.0678 | +| entropy_loss | -6.26 | +| explained_variance | 0.355 | +| learning_rate | 4.32e-05 | +| loss | -0.0252 | +| n_updates | 71756 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000203 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1407 | +| iterations | 13986 | +| time_elapsed | 20346 | +| total_timesteps | 28643328 | +| train/ | | +| approx_kl | 0.0093180295 | +| clip_fraction | 0.337 | +| clip_range | 0.0678 | +| entropy_loss | -6.55 | +| explained_variance | 0.307 | +| learning_rate | 4.32e-05 | +| loss | -0.0283 | +| n_updates | 71760 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000417 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1407 | +| iterations | 13987 | +| time_elapsed | 20348 | +| total_timesteps | 28645376 | +| train/ | | +| approx_kl | 0.0136785135 | +| clip_fraction | 0.353 | +| clip_range | 0.0678 | +| entropy_loss | -5.97 | +| explained_variance | 0.537 | +| learning_rate | 4.32e-05 | +| loss | -0.0253 | +| n_updates | 71764 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000121 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1407 | +| iterations | 13988 | +| time_elapsed | 20350 | +| total_timesteps | 28647424 | +| train/ | | +| approx_kl | 0.015032181 | +| clip_fraction | 0.318 | +| clip_range | 0.0678 | +| entropy_loss | -6 | +| explained_variance | 0.241 | +| learning_rate | 4.32e-05 | +| loss | -0.0287 | +| n_updates | 71768 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000228 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1407 | +| iterations | 13989 | +| time_elapsed | 20351 | +| total_timesteps | 28649472 | +| train/ | | +| approx_kl | 0.012808518 | +| clip_fraction | 0.354 | +| clip_range | 0.0678 | +| entropy_loss | -5.93 | +| explained_variance | 0.51 | +| learning_rate | 4.32e-05 | +| loss | -0.0296 | +| n_updates | 71772 | +| policy_gradient_loss | -0.0191 | +| value_loss | 9.72e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1407 | +| iterations | 13990 | +| time_elapsed | 20353 | +| total_timesteps | 28651520 | +| train/ | | +| approx_kl | 0.012321049 | +| clip_fraction | 0.314 | +| clip_range | 0.0678 | +| entropy_loss | -6.25 | +| explained_variance | 0.366 | +| learning_rate | 4.32e-05 | +| loss | -0.0238 | +| n_updates | 71776 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000251 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1407 | +| iterations | 13991 | +| time_elapsed | 20354 | +| total_timesteps | 28653568 | +| train/ | | +| approx_kl | 0.01040056 | +| clip_fraction | 0.323 | +| clip_range | 0.0678 | +| entropy_loss | -6.19 | +| explained_variance | 0.313 | +| learning_rate | 4.32e-05 | +| loss | -0.0284 | +| n_updates | 71780 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000246 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1407 | +| iterations | 13992 | +| time_elapsed | 20356 | +| total_timesteps | 28655616 | +| train/ | | +| approx_kl | 0.015324837 | +| clip_fraction | 0.335 | +| clip_range | 0.0678 | +| entropy_loss | -5.89 | +| explained_variance | 0.385 | +| learning_rate | 4.32e-05 | +| loss | -0.0277 | +| n_updates | 71784 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000255 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1407 | +| iterations | 13993 | +| time_elapsed | 20357 | +| total_timesteps | 28657664 | +| train/ | | +| approx_kl | 0.014281129 | +| clip_fraction | 0.344 | +| clip_range | 0.0678 | +| entropy_loss | -6.15 | +| explained_variance | 0.294 | +| learning_rate | 4.32e-05 | +| loss | -0.0249 | +| n_updates | 71788 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000343 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1407 | +| iterations | 13994 | +| time_elapsed | 20359 | +| total_timesteps | 28659712 | +| train/ | | +| approx_kl | 0.0120640285 | +| clip_fraction | 0.314 | +| clip_range | 0.0678 | +| entropy_loss | -5.93 | +| explained_variance | 0.478 | +| learning_rate | 4.32e-05 | +| loss | -0.0262 | +| n_updates | 71792 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000315 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1407 | +| iterations | 13995 | +| time_elapsed | 20360 | +| total_timesteps | 28661760 | +| train/ | | +| approx_kl | 0.011836259 | +| clip_fraction | 0.333 | +| clip_range | 0.0678 | +| entropy_loss | -5.97 | +| explained_variance | 0.367 | +| learning_rate | 4.32e-05 | +| loss | -0.032 | +| n_updates | 71796 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000123 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1407 | +| iterations | 13996 | +| time_elapsed | 20362 | +| total_timesteps | 28663808 | +| train/ | | +| approx_kl | 0.014453579 | +| clip_fraction | 0.375 | +| clip_range | 0.0678 | +| entropy_loss | -6.5 | +| explained_variance | 0.367 | +| learning_rate | 4.32e-05 | +| loss | -0.0338 | +| n_updates | 71800 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000122 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1407 | +| iterations | 13997 | +| time_elapsed | 20363 | +| total_timesteps | 28665856 | +| train/ | | +| approx_kl | 0.014939359 | +| clip_fraction | 0.363 | +| clip_range | 0.0678 | +| entropy_loss | -6.43 | +| explained_variance | 0.314 | +| learning_rate | 4.32e-05 | +| loss | -0.0256 | +| n_updates | 71804 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000164 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1407 | +| iterations | 13998 | +| time_elapsed | 20365 | +| total_timesteps | 28667904 | +| train/ | | +| approx_kl | 0.014079621 | +| clip_fraction | 0.38 | +| clip_range | 0.0678 | +| entropy_loss | -6.62 | +| explained_variance | 0.386 | +| learning_rate | 4.32e-05 | +| loss | -0.0317 | +| n_updates | 71808 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000135 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1407 | +| iterations | 13999 | +| time_elapsed | 20366 | +| total_timesteps | 28669952 | +| train/ | | +| approx_kl | 0.014963285 | +| clip_fraction | 0.357 | +| clip_range | 0.0678 | +| entropy_loss | -6.71 | +| explained_variance | -0.0118 | +| learning_rate | 4.32e-05 | +| loss | -0.0298 | +| n_updates | 71812 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000158 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1407 | +| iterations | 14000 | +| time_elapsed | 20368 | +| total_timesteps | 28672000 | +| train/ | | +| approx_kl | 0.010678884 | +| clip_fraction | 0.324 | +| clip_range | 0.0678 | +| entropy_loss | -6.38 | +| explained_variance | 0.472 | +| learning_rate | 4.32e-05 | +| loss | -0.0307 | +| n_updates | 71816 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000171 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1407 | +| iterations | 14001 | +| time_elapsed | 20369 | +| total_timesteps | 28674048 | +| train/ | | +| approx_kl | 0.010707625 | +| clip_fraction | 0.305 | +| clip_range | 0.0678 | +| entropy_loss | -5.95 | +| explained_variance | 0.459 | +| learning_rate | 4.32e-05 | +| loss | -0.0252 | +| n_updates | 71820 | +| policy_gradient_loss | -0.0132 | +| value_loss | 0.000254 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1407 | +| iterations | 14002 | +| time_elapsed | 20371 | +| total_timesteps | 28676096 | +| train/ | | +| approx_kl | 0.012533695 | +| clip_fraction | 0.343 | +| clip_range | 0.0678 | +| entropy_loss | -5.45 | +| explained_variance | 0.767 | +| learning_rate | 4.32e-05 | +| loss | -0.0343 | +| n_updates | 71824 | +| policy_gradient_loss | -0.0202 | +| value_loss | 9.74e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1407 | +| iterations | 14003 | +| time_elapsed | 20372 | +| total_timesteps | 28678144 | +| train/ | | +| approx_kl | 0.016121324 | +| clip_fraction | 0.357 | +| clip_range | 0.0678 | +| entropy_loss | -5.51 | +| explained_variance | 0.402 | +| learning_rate | 4.32e-05 | +| loss | -0.0292 | +| n_updates | 71828 | +| policy_gradient_loss | -0.0206 | +| value_loss | 8.8e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1407 | +| iterations | 14004 | +| time_elapsed | 20374 | +| total_timesteps | 28680192 | +| train/ | | +| approx_kl | 0.016110063 | +| clip_fraction | 0.39 | +| clip_range | 0.0678 | +| entropy_loss | -6.11 | +| explained_variance | 0.732 | +| learning_rate | 4.32e-05 | +| loss | -0.0303 | +| n_updates | 71832 | +| policy_gradient_loss | -0.0186 | +| value_loss | 8.26e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1407 | +| iterations | 14005 | +| time_elapsed | 20375 | +| total_timesteps | 28682240 | +| train/ | | +| approx_kl | 0.01702021 | +| clip_fraction | 0.35 | +| clip_range | 0.0678 | +| entropy_loss | -5.89 | +| explained_variance | 0.501 | +| learning_rate | 4.32e-05 | +| loss | -0.0274 | +| n_updates | 71836 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000147 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1407 | +| iterations | 14006 | +| time_elapsed | 20377 | +| total_timesteps | 28684288 | +| train/ | | +| approx_kl | 0.011272914 | +| clip_fraction | 0.338 | +| clip_range | 0.0678 | +| entropy_loss | -6.56 | +| explained_variance | 0.418 | +| learning_rate | 4.32e-05 | +| loss | -0.0315 | +| n_updates | 71840 | +| policy_gradient_loss | -0.0189 | +| value_loss | 9.9e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1407 | +| iterations | 14007 | +| time_elapsed | 20379 | +| total_timesteps | 28686336 | +| train/ | | +| approx_kl | 0.012982786 | +| clip_fraction | 0.329 | +| clip_range | 0.0678 | +| entropy_loss | -6.43 | +| explained_variance | 0.41 | +| learning_rate | 4.32e-05 | +| loss | -0.033 | +| n_updates | 71844 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.00019 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1407 | +| iterations | 14008 | +| time_elapsed | 20380 | +| total_timesteps | 28688384 | +| train/ | | +| approx_kl | 0.013302947 | +| clip_fraction | 0.354 | +| clip_range | 0.0678 | +| entropy_loss | -6.21 | +| explained_variance | 0.429 | +| learning_rate | 4.32e-05 | +| loss | -0.0299 | +| n_updates | 71848 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000134 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1407 | +| iterations | 14009 | +| time_elapsed | 20382 | +| total_timesteps | 28690432 | +| train/ | | +| approx_kl | 0.016553178 | +| clip_fraction | 0.318 | +| clip_range | 0.0678 | +| entropy_loss | -6.27 | +| explained_variance | 0.326 | +| learning_rate | 4.32e-05 | +| loss | -0.0313 | +| n_updates | 71852 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000228 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1407 | +| iterations | 14010 | +| time_elapsed | 20383 | +| total_timesteps | 28692480 | +| train/ | | +| approx_kl | 0.014826102 | +| clip_fraction | 0.378 | +| clip_range | 0.0678 | +| entropy_loss | -6.76 | +| explained_variance | -0.174 | +| learning_rate | 4.32e-05 | +| loss | -0.0294 | +| n_updates | 71856 | +| policy_gradient_loss | -0.0218 | +| value_loss | 7.34e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1407 | +| iterations | 14011 | +| time_elapsed | 20385 | +| total_timesteps | 28694528 | +| train/ | | +| approx_kl | 0.01257801 | +| clip_fraction | 0.38 | +| clip_range | 0.0678 | +| entropy_loss | -6.51 | +| explained_variance | 0.145 | +| learning_rate | 4.32e-05 | +| loss | -0.0243 | +| n_updates | 71860 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000115 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1407 | +| iterations | 14012 | +| time_elapsed | 20386 | +| total_timesteps | 28696576 | +| train/ | | +| approx_kl | 0.016261967 | +| clip_fraction | 0.346 | +| clip_range | 0.0678 | +| entropy_loss | -5.3 | +| explained_variance | 0.676 | +| learning_rate | 4.32e-05 | +| loss | -0.0244 | +| n_updates | 71864 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000171 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1407 | +| iterations | 14013 | +| time_elapsed | 20388 | +| total_timesteps | 28698624 | +| train/ | | +| approx_kl | 0.014462249 | +| clip_fraction | 0.361 | +| clip_range | 0.0678 | +| entropy_loss | -5.76 | +| explained_variance | 0.59 | +| learning_rate | 4.32e-05 | +| loss | -0.0267 | +| n_updates | 71868 | +| policy_gradient_loss | -0.0182 | +| value_loss | 9.92e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1407 | +| iterations | 14014 | +| time_elapsed | 20389 | +| total_timesteps | 28700672 | +| train/ | | +| approx_kl | 0.013325553 | +| clip_fraction | 0.341 | +| clip_range | 0.0678 | +| entropy_loss | -6.23 | +| explained_variance | 0.221 | +| learning_rate | 4.32e-05 | +| loss | -0.026 | +| n_updates | 71872 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000152 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1407 | +| iterations | 14015 | +| time_elapsed | 20391 | +| total_timesteps | 28702720 | +| train/ | | +| approx_kl | 0.014156699 | +| clip_fraction | 0.346 | +| clip_range | 0.0678 | +| entropy_loss | -6.15 | +| explained_variance | 0.571 | +| learning_rate | 4.32e-05 | +| loss | -0.029 | +| n_updates | 71876 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000125 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1407 | +| iterations | 14016 | +| time_elapsed | 20392 | +| total_timesteps | 28704768 | +| train/ | | +| approx_kl | 0.01298272 | +| clip_fraction | 0.321 | +| clip_range | 0.0678 | +| entropy_loss | -6.4 | +| explained_variance | 0.395 | +| learning_rate | 4.32e-05 | +| loss | -0.0256 | +| n_updates | 71880 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000236 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1407 | +| iterations | 14017 | +| time_elapsed | 20394 | +| total_timesteps | 28706816 | +| train/ | | +| approx_kl | 0.014040155 | +| clip_fraction | 0.335 | +| clip_range | 0.0678 | +| entropy_loss | -5.74 | +| explained_variance | 0.619 | +| learning_rate | 4.32e-05 | +| loss | -0.027 | +| n_updates | 71884 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000141 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1407 | +| iterations | 14018 | +| time_elapsed | 20395 | +| total_timesteps | 28708864 | +| train/ | | +| approx_kl | 0.01348081 | +| clip_fraction | 0.336 | +| clip_range | 0.0678 | +| entropy_loss | -6.44 | +| explained_variance | -0.0512 | +| learning_rate | 4.32e-05 | +| loss | -0.0274 | +| n_updates | 71888 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000144 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1407 | +| iterations | 14019 | +| time_elapsed | 20397 | +| total_timesteps | 28710912 | +| train/ | | +| approx_kl | 0.011637653 | +| clip_fraction | 0.331 | +| clip_range | 0.0678 | +| entropy_loss | -6.6 | +| explained_variance | 0.621 | +| learning_rate | 4.32e-05 | +| loss | -0.0248 | +| n_updates | 71892 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000106 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1407 | +| iterations | 14020 | +| time_elapsed | 20398 | +| total_timesteps | 28712960 | +| train/ | | +| approx_kl | 0.012768459 | +| clip_fraction | 0.344 | +| clip_range | 0.0678 | +| entropy_loss | -6.03 | +| explained_variance | 0.522 | +| learning_rate | 4.32e-05 | +| loss | -0.0285 | +| n_updates | 71896 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000151 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1407 | +| iterations | 14021 | +| time_elapsed | 20400 | +| total_timesteps | 28715008 | +| train/ | | +| approx_kl | 0.013126899 | +| clip_fraction | 0.337 | +| clip_range | 0.0678 | +| entropy_loss | -6.71 | +| explained_variance | -0.028 | +| learning_rate | 4.32e-05 | +| loss | -0.0288 | +| n_updates | 71900 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000141 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1407 | +| iterations | 14022 | +| time_elapsed | 20401 | +| total_timesteps | 28717056 | +| train/ | | +| approx_kl | 0.016291667 | +| clip_fraction | 0.32 | +| clip_range | 0.0678 | +| entropy_loss | -6.34 | +| explained_variance | 0.353 | +| learning_rate | 4.32e-05 | +| loss | -0.0262 | +| n_updates | 71904 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000175 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1407 | +| iterations | 14023 | +| time_elapsed | 20403 | +| total_timesteps | 28719104 | +| train/ | | +| approx_kl | 0.017135948 | +| clip_fraction | 0.333 | +| clip_range | 0.0678 | +| entropy_loss | -6.28 | +| explained_variance | 0.575 | +| learning_rate | 4.32e-05 | +| loss | -0.0354 | +| n_updates | 71908 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000105 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1407 | +| iterations | 14024 | +| time_elapsed | 20404 | +| total_timesteps | 28721152 | +| train/ | | +| approx_kl | 0.017814122 | +| clip_fraction | 0.35 | +| clip_range | 0.0678 | +| entropy_loss | -6.04 | +| explained_variance | 0.481 | +| learning_rate | 4.32e-05 | +| loss | -0.0358 | +| n_updates | 71912 | +| policy_gradient_loss | -0.0209 | +| value_loss | 8.01e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1407 | +| iterations | 14025 | +| time_elapsed | 20406 | +| total_timesteps | 28723200 | +| train/ | | +| approx_kl | 0.021190796 | +| clip_fraction | 0.369 | +| clip_range | 0.0678 | +| entropy_loss | -6.02 | +| explained_variance | 0.511 | +| learning_rate | 4.32e-05 | +| loss | -0.0311 | +| n_updates | 71916 | +| policy_gradient_loss | -0.0188 | +| value_loss | 8.34e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1407 | +| iterations | 14026 | +| time_elapsed | 20408 | +| total_timesteps | 28725248 | +| train/ | | +| approx_kl | 0.011618236 | +| clip_fraction | 0.341 | +| clip_range | 0.0678 | +| entropy_loss | -5.91 | +| explained_variance | 0.503 | +| learning_rate | 4.32e-05 | +| loss | -0.0248 | +| n_updates | 71920 | +| policy_gradient_loss | -0.0144 | +| value_loss | 0.000165 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1407 | +| iterations | 14027 | +| time_elapsed | 20409 | +| total_timesteps | 28727296 | +| train/ | | +| approx_kl | 0.014055962 | +| clip_fraction | 0.342 | +| clip_range | 0.0678 | +| entropy_loss | -6.14 | +| explained_variance | 0.398 | +| learning_rate | 4.32e-05 | +| loss | -0.0288 | +| n_updates | 71924 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000119 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1407 | +| iterations | 14028 | +| time_elapsed | 20411 | +| total_timesteps | 28729344 | +| train/ | | +| approx_kl | 0.011908471 | +| clip_fraction | 0.33 | +| clip_range | 0.0678 | +| entropy_loss | -6.06 | +| explained_variance | 0.61 | +| learning_rate | 4.32e-05 | +| loss | -0.0345 | +| n_updates | 71928 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000122 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1407 | +| iterations | 14029 | +| time_elapsed | 20412 | +| total_timesteps | 28731392 | +| train/ | | +| approx_kl | 0.012463273 | +| clip_fraction | 0.33 | +| clip_range | 0.0678 | +| entropy_loss | -6.11 | +| explained_variance | 0.582 | +| learning_rate | 4.32e-05 | +| loss | -0.0253 | +| n_updates | 71932 | +| policy_gradient_loss | -0.0182 | +| value_loss | 9.11e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1407 | +| iterations | 14030 | +| time_elapsed | 20414 | +| total_timesteps | 28733440 | +| train/ | | +| approx_kl | 0.010609325 | +| clip_fraction | 0.318 | +| clip_range | 0.0678 | +| entropy_loss | -5.62 | +| explained_variance | 0.404 | +| learning_rate | 4.32e-05 | +| loss | -0.027 | +| n_updates | 71936 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.000387 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1407 | +| iterations | 14031 | +| time_elapsed | 20415 | +| total_timesteps | 28735488 | +| train/ | | +| approx_kl | 0.01328248 | +| clip_fraction | 0.327 | +| clip_range | 0.0678 | +| entropy_loss | -5.93 | +| explained_variance | 0.406 | +| learning_rate | 4.32e-05 | +| loss | -0.0195 | +| n_updates | 71940 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000244 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1407 | +| iterations | 14032 | +| time_elapsed | 20417 | +| total_timesteps | 28737536 | +| train/ | | +| approx_kl | 0.015505895 | +| clip_fraction | 0.39 | +| clip_range | 0.0678 | +| entropy_loss | -5.88 | +| explained_variance | 0.257 | +| learning_rate | 4.32e-05 | +| loss | -0.0345 | +| n_updates | 71944 | +| policy_gradient_loss | -0.0233 | +| value_loss | 0.00014 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1407 | +| iterations | 14033 | +| time_elapsed | 20418 | +| total_timesteps | 28739584 | +| train/ | | +| approx_kl | 0.011200873 | +| clip_fraction | 0.312 | +| clip_range | 0.0678 | +| entropy_loss | -6.64 | +| explained_variance | 0.424 | +| learning_rate | 4.32e-05 | +| loss | -0.0289 | +| n_updates | 71948 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.00019 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1407 | +| iterations | 14034 | +| time_elapsed | 20420 | +| total_timesteps | 28741632 | +| train/ | | +| approx_kl | 0.013518792 | +| clip_fraction | 0.364 | +| clip_range | 0.0678 | +| entropy_loss | -6.54 | +| explained_variance | 0.314 | +| learning_rate | 4.32e-05 | +| loss | -0.0338 | +| n_updates | 71952 | +| policy_gradient_loss | -0.0229 | +| value_loss | 9.9e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1407 | +| iterations | 14035 | +| time_elapsed | 20421 | +| total_timesteps | 28743680 | +| train/ | | +| approx_kl | 0.012053116 | +| clip_fraction | 0.335 | +| clip_range | 0.0678 | +| entropy_loss | -5.63 | +| explained_variance | 0.819 | +| learning_rate | 4.32e-05 | +| loss | -0.0243 | +| n_updates | 71956 | +| policy_gradient_loss | -0.0175 | +| value_loss | 7.09e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1407 | +| iterations | 14036 | +| time_elapsed | 20423 | +| total_timesteps | 28745728 | +| train/ | | +| approx_kl | 0.014163936 | +| clip_fraction | 0.321 | +| clip_range | 0.0678 | +| entropy_loss | -5.55 | +| explained_variance | 0.636 | +| learning_rate | 4.32e-05 | +| loss | -0.0279 | +| n_updates | 71960 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000148 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1407 | +| iterations | 14037 | +| time_elapsed | 20424 | +| total_timesteps | 28747776 | +| train/ | | +| approx_kl | 0.014969512 | +| clip_fraction | 0.37 | +| clip_range | 0.0678 | +| entropy_loss | -6.03 | +| explained_variance | 0.299 | +| learning_rate | 4.32e-05 | +| loss | -0.0227 | +| n_updates | 71964 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000141 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1407 | +| iterations | 14038 | +| time_elapsed | 20426 | +| total_timesteps | 28749824 | +| train/ | | +| approx_kl | 0.013240472 | +| clip_fraction | 0.367 | +| clip_range | 0.0678 | +| entropy_loss | -6.79 | +| explained_variance | -0.0224 | +| learning_rate | 4.32e-05 | +| loss | -0.0287 | +| n_updates | 71968 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000116 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1407 | +| iterations | 14039 | +| time_elapsed | 20428 | +| total_timesteps | 28751872 | +| train/ | | +| approx_kl | 0.012136165 | +| clip_fraction | 0.351 | +| clip_range | 0.0678 | +| entropy_loss | -7.06 | +| explained_variance | -0.0659 | +| learning_rate | 4.32e-05 | +| loss | -0.0301 | +| n_updates | 71972 | +| policy_gradient_loss | -0.0192 | +| value_loss | 9.87e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1407 | +| iterations | 14040 | +| time_elapsed | 20429 | +| total_timesteps | 28753920 | +| train/ | | +| approx_kl | 0.01153318 | +| clip_fraction | 0.305 | +| clip_range | 0.0678 | +| entropy_loss | -6.27 | +| explained_variance | 0.322 | +| learning_rate | 4.32e-05 | +| loss | -0.026 | +| n_updates | 71976 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000216 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1407 | +| iterations | 14041 | +| time_elapsed | 20431 | +| total_timesteps | 28755968 | +| train/ | | +| approx_kl | 0.0105308555 | +| clip_fraction | 0.338 | +| clip_range | 0.0678 | +| entropy_loss | -5.92 | +| explained_variance | 0.512 | +| learning_rate | 4.32e-05 | +| loss | -0.0291 | +| n_updates | 71980 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000209 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1407 | +| iterations | 14042 | +| time_elapsed | 20432 | +| total_timesteps | 28758016 | +| train/ | | +| approx_kl | 0.011052334 | +| clip_fraction | 0.315 | +| clip_range | 0.0678 | +| entropy_loss | -6.5 | +| explained_variance | -0.0666 | +| learning_rate | 4.32e-05 | +| loss | -0.0288 | +| n_updates | 71984 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000315 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1407 | +| iterations | 14043 | +| time_elapsed | 20434 | +| total_timesteps | 28760064 | +| train/ | | +| approx_kl | 0.014196755 | +| clip_fraction | 0.35 | +| clip_range | 0.0678 | +| entropy_loss | -5.23 | +| explained_variance | 0.746 | +| learning_rate | 4.32e-05 | +| loss | -0.0294 | +| n_updates | 71988 | +| policy_gradient_loss | -0.018 | +| value_loss | 8.2e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1407 | +| iterations | 14044 | +| time_elapsed | 20435 | +| total_timesteps | 28762112 | +| train/ | | +| approx_kl | 0.013768788 | +| clip_fraction | 0.367 | +| clip_range | 0.0678 | +| entropy_loss | -6.07 | +| explained_variance | 0.18 | +| learning_rate | 4.32e-05 | +| loss | -0.0294 | +| n_updates | 71992 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000181 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1407 | +| iterations | 14045 | +| time_elapsed | 20437 | +| total_timesteps | 28764160 | +| train/ | | +| approx_kl | 0.0166764 | +| clip_fraction | 0.339 | +| clip_range | 0.0678 | +| entropy_loss | -5.97 | +| explained_variance | 0.579 | +| learning_rate | 4.32e-05 | +| loss | -0.028 | +| n_updates | 71996 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000164 | +--------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1407 | +| iterations | 14046 | +| time_elapsed | 20438 | +| total_timesteps | 28766208 | +| train/ | | +| approx_kl | 0.0094152745 | +| clip_fraction | 0.318 | +| clip_range | 0.0678 | +| entropy_loss | -6.21 | +| explained_variance | 0.494 | +| learning_rate | 4.32e-05 | +| loss | -0.0244 | +| n_updates | 72000 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000205 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1407 | +| iterations | 14047 | +| time_elapsed | 20440 | +| total_timesteps | 28768256 | +| train/ | | +| approx_kl | 0.013997703 | +| clip_fraction | 0.315 | +| clip_range | 0.0678 | +| entropy_loss | -5.88 | +| explained_variance | 0.488 | +| learning_rate | 4.32e-05 | +| loss | -0.0225 | +| n_updates | 72004 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000215 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1407 | +| iterations | 14048 | +| time_elapsed | 20441 | +| total_timesteps | 28770304 | +| train/ | | +| approx_kl | 0.010336833 | +| clip_fraction | 0.328 | +| clip_range | 0.0678 | +| entropy_loss | -6.07 | +| explained_variance | 0.325 | +| learning_rate | 4.32e-05 | +| loss | -0.0325 | +| n_updates | 72008 | +| policy_gradient_loss | -0.0146 | +| value_loss | 0.0003 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1407 | +| iterations | 14049 | +| time_elapsed | 20443 | +| total_timesteps | 28772352 | +| train/ | | +| approx_kl | 0.01578693 | +| clip_fraction | 0.341 | +| clip_range | 0.0678 | +| entropy_loss | -6.46 | +| explained_variance | -0.0759 | +| learning_rate | 4.32e-05 | +| loss | -0.029 | +| n_updates | 72012 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000203 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1407 | +| iterations | 14050 | +| time_elapsed | 20444 | +| total_timesteps | 28774400 | +| train/ | | +| approx_kl | 0.013354588 | +| clip_fraction | 0.356 | +| clip_range | 0.0678 | +| entropy_loss | -6.56 | +| explained_variance | 0.28 | +| learning_rate | 4.32e-05 | +| loss | -0.0285 | +| n_updates | 72016 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000263 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1407 | +| iterations | 14051 | +| time_elapsed | 20446 | +| total_timesteps | 28776448 | +| train/ | | +| approx_kl | 0.014496116 | +| clip_fraction | 0.332 | +| clip_range | 0.0678 | +| entropy_loss | -5.6 | +| explained_variance | 0.392 | +| learning_rate | 4.32e-05 | +| loss | -0.0293 | +| n_updates | 72020 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000395 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1407 | +| iterations | 14052 | +| time_elapsed | 20447 | +| total_timesteps | 28778496 | +| train/ | | +| approx_kl | 0.015585959 | +| clip_fraction | 0.364 | +| clip_range | 0.0678 | +| entropy_loss | -5.86 | +| explained_variance | 0.114 | +| learning_rate | 4.32e-05 | +| loss | -0.0308 | +| n_updates | 72024 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000207 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1407 | +| iterations | 14053 | +| time_elapsed | 20449 | +| total_timesteps | 28780544 | +| train/ | | +| approx_kl | 0.017358007 | +| clip_fraction | 0.358 | +| clip_range | 0.0678 | +| entropy_loss | -5.83 | +| explained_variance | 0.422 | +| learning_rate | 4.32e-05 | +| loss | -0.0332 | +| n_updates | 72028 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000243 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1407 | +| iterations | 14054 | +| time_elapsed | 20450 | +| total_timesteps | 28782592 | +| train/ | | +| approx_kl | 0.014565486 | +| clip_fraction | 0.37 | +| clip_range | 0.0678 | +| entropy_loss | -6.02 | +| explained_variance | 0.274 | +| learning_rate | 4.32e-05 | +| loss | -0.0326 | +| n_updates | 72032 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000204 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1407 | +| iterations | 14055 | +| time_elapsed | 20452 | +| total_timesteps | 28784640 | +| train/ | | +| approx_kl | 0.0141562 | +| clip_fraction | 0.363 | +| clip_range | 0.0678 | +| entropy_loss | -6.48 | +| explained_variance | 0.323 | +| learning_rate | 4.32e-05 | +| loss | -0.0372 | +| n_updates | 72036 | +| policy_gradient_loss | -0.0228 | +| value_loss | 0.000103 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1407 | +| iterations | 14056 | +| time_elapsed | 20453 | +| total_timesteps | 28786688 | +| train/ | | +| approx_kl | 0.013940392 | +| clip_fraction | 0.377 | +| clip_range | 0.0678 | +| entropy_loss | -6.59 | +| explained_variance | -0.132 | +| learning_rate | 4.32e-05 | +| loss | -0.0287 | +| n_updates | 72040 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.00013 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1407 | +| iterations | 14057 | +| time_elapsed | 20455 | +| total_timesteps | 28788736 | +| train/ | | +| approx_kl | 0.017442713 | +| clip_fraction | 0.349 | +| clip_range | 0.0678 | +| entropy_loss | -6.28 | +| explained_variance | 0.306 | +| learning_rate | 4.32e-05 | +| loss | -0.0287 | +| n_updates | 72044 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000271 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1407 | +| iterations | 14058 | +| time_elapsed | 20456 | +| total_timesteps | 28790784 | +| train/ | | +| approx_kl | 0.015469854 | +| clip_fraction | 0.331 | +| clip_range | 0.0678 | +| entropy_loss | -5.9 | +| explained_variance | 0.489 | +| learning_rate | 4.32e-05 | +| loss | -0.0298 | +| n_updates | 72048 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000213 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1407 | +| iterations | 14059 | +| time_elapsed | 20458 | +| total_timesteps | 28792832 | +| train/ | | +| approx_kl | 0.013520834 | +| clip_fraction | 0.345 | +| clip_range | 0.0678 | +| entropy_loss | -6.09 | +| explained_variance | 0.452 | +| learning_rate | 4.32e-05 | +| loss | -0.0333 | +| n_updates | 72052 | +| policy_gradient_loss | -0.0203 | +| value_loss | 8.47e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1407 | +| iterations | 14060 | +| time_elapsed | 20459 | +| total_timesteps | 28794880 | +| train/ | | +| approx_kl | 0.013740579 | +| clip_fraction | 0.326 | +| clip_range | 0.0678 | +| entropy_loss | -6.47 | +| explained_variance | 0.298 | +| learning_rate | 4.32e-05 | +| loss | -0.0263 | +| n_updates | 72056 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000123 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1407 | +| iterations | 14061 | +| time_elapsed | 20461 | +| total_timesteps | 28796928 | +| train/ | | +| approx_kl | 0.01131848 | +| clip_fraction | 0.35 | +| clip_range | 0.0678 | +| entropy_loss | -6.68 | +| explained_variance | 0.152 | +| learning_rate | 4.32e-05 | +| loss | -0.0296 | +| n_updates | 72060 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000116 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1407 | +| iterations | 14062 | +| time_elapsed | 20462 | +| total_timesteps | 28798976 | +| train/ | | +| approx_kl | 0.013156597 | +| clip_fraction | 0.333 | +| clip_range | 0.0678 | +| entropy_loss | -6.34 | +| explained_variance | 0.348 | +| learning_rate | 4.32e-05 | +| loss | -0.0262 | +| n_updates | 72064 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.00026 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1407 | +| iterations | 14063 | +| time_elapsed | 20464 | +| total_timesteps | 28801024 | +| train/ | | +| approx_kl | 0.011692809 | +| clip_fraction | 0.336 | +| clip_range | 0.0678 | +| entropy_loss | -6.4 | +| explained_variance | 0.247 | +| learning_rate | 4.32e-05 | +| loss | -0.0247 | +| n_updates | 72068 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000254 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1407 | +| iterations | 14064 | +| time_elapsed | 20465 | +| total_timesteps | 28803072 | +| train/ | | +| approx_kl | 0.012799535 | +| clip_fraction | 0.343 | +| clip_range | 0.0678 | +| entropy_loss | -5.79 | +| explained_variance | 0.526 | +| learning_rate | 4.32e-05 | +| loss | -0.0278 | +| n_updates | 72072 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000258 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1407 | +| iterations | 14065 | +| time_elapsed | 20467 | +| total_timesteps | 28805120 | +| train/ | | +| approx_kl | 0.011112821 | +| clip_fraction | 0.338 | +| clip_range | 0.0678 | +| entropy_loss | -6.36 | +| explained_variance | 0.317 | +| learning_rate | 4.32e-05 | +| loss | -0.0312 | +| n_updates | 72076 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000163 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1407 | +| iterations | 14066 | +| time_elapsed | 20468 | +| total_timesteps | 28807168 | +| train/ | | +| approx_kl | 0.012150633 | +| clip_fraction | 0.324 | +| clip_range | 0.0678 | +| entropy_loss | -6.11 | +| explained_variance | 0.37 | +| learning_rate | 4.32e-05 | +| loss | -0.0285 | +| n_updates | 72080 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000231 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1407 | +| iterations | 14067 | +| time_elapsed | 20470 | +| total_timesteps | 28809216 | +| train/ | | +| approx_kl | 0.01617035 | +| clip_fraction | 0.346 | +| clip_range | 0.0678 | +| entropy_loss | -6.14 | +| explained_variance | 0.444 | +| learning_rate | 4.32e-05 | +| loss | -0.0301 | +| n_updates | 72084 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000176 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1407 | +| iterations | 14068 | +| time_elapsed | 20471 | +| total_timesteps | 28811264 | +| train/ | | +| approx_kl | 0.015232919 | +| clip_fraction | 0.346 | +| clip_range | 0.0678 | +| entropy_loss | -6.15 | +| explained_variance | 0.288 | +| learning_rate | 4.32e-05 | +| loss | -0.0333 | +| n_updates | 72088 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000175 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1407 | +| iterations | 14069 | +| time_elapsed | 20473 | +| total_timesteps | 28813312 | +| train/ | | +| approx_kl | 0.01173073 | +| clip_fraction | 0.35 | +| clip_range | 0.0678 | +| entropy_loss | -6.26 | +| explained_variance | 0.241 | +| learning_rate | 4.32e-05 | +| loss | -0.0326 | +| n_updates | 72092 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000341 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1407 | +| iterations | 14070 | +| time_elapsed | 20474 | +| total_timesteps | 28815360 | +| train/ | | +| approx_kl | 0.011864808 | +| clip_fraction | 0.33 | +| clip_range | 0.0678 | +| entropy_loss | -6.15 | +| explained_variance | 0.299 | +| learning_rate | 4.32e-05 | +| loss | -0.0241 | +| n_updates | 72096 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000255 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1407 | +| iterations | 14071 | +| time_elapsed | 20476 | +| total_timesteps | 28817408 | +| train/ | | +| approx_kl | 0.0141798 | +| clip_fraction | 0.368 | +| clip_range | 0.0678 | +| entropy_loss | -5.98 | +| explained_variance | 0.49 | +| learning_rate | 4.32e-05 | +| loss | -0.0346 | +| n_updates | 72100 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000135 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1407 | +| iterations | 14072 | +| time_elapsed | 20478 | +| total_timesteps | 28819456 | +| train/ | | +| approx_kl | 0.012692725 | +| clip_fraction | 0.334 | +| clip_range | 0.0678 | +| entropy_loss | -5.9 | +| explained_variance | 0.486 | +| learning_rate | 4.32e-05 | +| loss | -0.0292 | +| n_updates | 72104 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000289 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1407 | +| iterations | 14073 | +| time_elapsed | 20479 | +| total_timesteps | 28821504 | +| train/ | | +| approx_kl | 0.020394363 | +| clip_fraction | 0.366 | +| clip_range | 0.0678 | +| entropy_loss | -5.9 | +| explained_variance | 0.258 | +| learning_rate | 4.32e-05 | +| loss | -0.0344 | +| n_updates | 72108 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000205 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1407 | +| iterations | 14074 | +| time_elapsed | 20481 | +| total_timesteps | 28823552 | +| train/ | | +| approx_kl | 0.013228262 | +| clip_fraction | 0.348 | +| clip_range | 0.0678 | +| entropy_loss | -6.06 | +| explained_variance | 0.414 | +| learning_rate | 4.32e-05 | +| loss | -0.0241 | +| n_updates | 72112 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000178 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1407 | +| iterations | 14075 | +| time_elapsed | 20482 | +| total_timesteps | 28825600 | +| train/ | | +| approx_kl | 0.012551816 | +| clip_fraction | 0.344 | +| clip_range | 0.0678 | +| entropy_loss | -6.53 | +| explained_variance | 0.311 | +| learning_rate | 4.32e-05 | +| loss | -0.0282 | +| n_updates | 72116 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000182 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1407 | +| iterations | 14076 | +| time_elapsed | 20484 | +| total_timesteps | 28827648 | +| train/ | | +| approx_kl | 0.013376238 | +| clip_fraction | 0.386 | +| clip_range | 0.0678 | +| entropy_loss | -6.8 | +| explained_variance | -0.161 | +| learning_rate | 4.32e-05 | +| loss | -0.0316 | +| n_updates | 72120 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000131 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1407 | +| iterations | 14077 | +| time_elapsed | 20485 | +| total_timesteps | 28829696 | +| train/ | | +| approx_kl | 0.013988392 | +| clip_fraction | 0.355 | +| clip_range | 0.0678 | +| entropy_loss | -6.77 | +| explained_variance | 0.281 | +| learning_rate | 4.32e-05 | +| loss | -0.0287 | +| n_updates | 72124 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000139 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1407 | +| iterations | 14078 | +| time_elapsed | 20487 | +| total_timesteps | 28831744 | +| train/ | | +| approx_kl | 0.012098122 | +| clip_fraction | 0.338 | +| clip_range | 0.0678 | +| entropy_loss | -6.45 | +| explained_variance | 0.691 | +| learning_rate | 4.32e-05 | +| loss | -0.0338 | +| n_updates | 72128 | +| policy_gradient_loss | -0.0197 | +| value_loss | 8.4e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1407 | +| iterations | 14079 | +| time_elapsed | 20488 | +| total_timesteps | 28833792 | +| train/ | | +| approx_kl | 0.012600677 | +| clip_fraction | 0.327 | +| clip_range | 0.0678 | +| entropy_loss | -6.5 | +| explained_variance | 0.388 | +| learning_rate | 4.32e-05 | +| loss | -0.0291 | +| n_updates | 72132 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000111 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1407 | +| iterations | 14080 | +| time_elapsed | 20490 | +| total_timesteps | 28835840 | +| train/ | | +| approx_kl | 0.013959285 | +| clip_fraction | 0.306 | +| clip_range | 0.0678 | +| entropy_loss | -6.3 | +| explained_variance | 0.52 | +| learning_rate | 4.32e-05 | +| loss | -0.0246 | +| n_updates | 72136 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000135 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1407 | +| iterations | 14081 | +| time_elapsed | 20491 | +| total_timesteps | 28837888 | +| train/ | | +| approx_kl | 0.012970626 | +| clip_fraction | 0.309 | +| clip_range | 0.0678 | +| entropy_loss | -6.02 | +| explained_variance | 0.72 | +| learning_rate | 4.32e-05 | +| loss | -0.021 | +| n_updates | 72140 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000107 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1407 | +| iterations | 14082 | +| time_elapsed | 20493 | +| total_timesteps | 28839936 | +| train/ | | +| approx_kl | 0.0128114335 | +| clip_fraction | 0.32 | +| clip_range | 0.0678 | +| entropy_loss | -6.09 | +| explained_variance | 0.466 | +| learning_rate | 4.32e-05 | +| loss | -0.0318 | +| n_updates | 72144 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000195 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1407 | +| iterations | 14083 | +| time_elapsed | 20494 | +| total_timesteps | 28841984 | +| train/ | | +| approx_kl | 0.013557015 | +| clip_fraction | 0.325 | +| clip_range | 0.0678 | +| entropy_loss | -6.02 | +| explained_variance | 0.245 | +| learning_rate | 4.32e-05 | +| loss | -0.0244 | +| n_updates | 72148 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000295 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1407 | +| iterations | 14084 | +| time_elapsed | 20496 | +| total_timesteps | 28844032 | +| train/ | | +| approx_kl | 0.012410745 | +| clip_fraction | 0.323 | +| clip_range | 0.0678 | +| entropy_loss | -5.74 | +| explained_variance | 0.436 | +| learning_rate | 4.32e-05 | +| loss | -0.0264 | +| n_updates | 72152 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000322 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1407 | +| iterations | 14085 | +| time_elapsed | 20498 | +| total_timesteps | 28846080 | +| train/ | | +| approx_kl | 0.013619596 | +| clip_fraction | 0.358 | +| clip_range | 0.0678 | +| entropy_loss | -6.46 | +| explained_variance | 0.257 | +| learning_rate | 4.31e-05 | +| loss | -0.0325 | +| n_updates | 72156 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000152 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1407 | +| iterations | 14086 | +| time_elapsed | 20499 | +| total_timesteps | 28848128 | +| train/ | | +| approx_kl | 0.014326317 | +| clip_fraction | 0.345 | +| clip_range | 0.0678 | +| entropy_loss | -6.4 | +| explained_variance | 0.376 | +| learning_rate | 4.31e-05 | +| loss | -0.0337 | +| n_updates | 72160 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000147 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1407 | +| iterations | 14087 | +| time_elapsed | 20501 | +| total_timesteps | 28850176 | +| train/ | | +| approx_kl | 0.011789469 | +| clip_fraction | 0.326 | +| clip_range | 0.0678 | +| entropy_loss | -6.45 | +| explained_variance | 0.354 | +| learning_rate | 4.31e-05 | +| loss | -0.0289 | +| n_updates | 72164 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000223 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1407 | +| iterations | 14088 | +| time_elapsed | 20502 | +| total_timesteps | 28852224 | +| train/ | | +| approx_kl | 0.015258173 | +| clip_fraction | 0.356 | +| clip_range | 0.0678 | +| entropy_loss | -6.03 | +| explained_variance | 0.207 | +| learning_rate | 4.31e-05 | +| loss | -0.0208 | +| n_updates | 72168 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000185 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1407 | +| iterations | 14089 | +| time_elapsed | 20504 | +| total_timesteps | 28854272 | +| train/ | | +| approx_kl | 0.012138283 | +| clip_fraction | 0.315 | +| clip_range | 0.0678 | +| entropy_loss | -6.01 | +| explained_variance | 0.325 | +| learning_rate | 4.31e-05 | +| loss | -0.0253 | +| n_updates | 72172 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000238 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1407 | +| iterations | 14090 | +| time_elapsed | 20505 | +| total_timesteps | 28856320 | +| train/ | | +| approx_kl | 0.015850555 | +| clip_fraction | 0.362 | +| clip_range | 0.0678 | +| entropy_loss | -6.16 | +| explained_variance | 0.317 | +| learning_rate | 4.31e-05 | +| loss | -0.0275 | +| n_updates | 72176 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000126 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1407 | +| iterations | 14091 | +| time_elapsed | 20507 | +| total_timesteps | 28858368 | +| train/ | | +| approx_kl | 0.015131343 | +| clip_fraction | 0.381 | +| clip_range | 0.0678 | +| entropy_loss | -6.33 | +| explained_variance | 0.315 | +| learning_rate | 4.31e-05 | +| loss | -0.038 | +| n_updates | 72180 | +| policy_gradient_loss | -0.0228 | +| value_loss | 9.09e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1407 | +| iterations | 14092 | +| time_elapsed | 20508 | +| total_timesteps | 28860416 | +| train/ | | +| approx_kl | 0.012575873 | +| clip_fraction | 0.346 | +| clip_range | 0.0678 | +| entropy_loss | -6.51 | +| explained_variance | 0.29 | +| learning_rate | 4.31e-05 | +| loss | -0.0311 | +| n_updates | 72184 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000142 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1407 | +| iterations | 14093 | +| time_elapsed | 20510 | +| total_timesteps | 28862464 | +| train/ | | +| approx_kl | 0.011303145 | +| clip_fraction | 0.347 | +| clip_range | 0.0678 | +| entropy_loss | -6.42 | +| explained_variance | 0.378 | +| learning_rate | 4.31e-05 | +| loss | -0.0319 | +| n_updates | 72188 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000247 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1407 | +| iterations | 14094 | +| time_elapsed | 20511 | +| total_timesteps | 28864512 | +| train/ | | +| approx_kl | 0.013708378 | +| clip_fraction | 0.337 | +| clip_range | 0.0678 | +| entropy_loss | -6.19 | +| explained_variance | 0.452 | +| learning_rate | 4.31e-05 | +| loss | -0.0245 | +| n_updates | 72192 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000166 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1407 | +| iterations | 14095 | +| time_elapsed | 20513 | +| total_timesteps | 28866560 | +| train/ | | +| approx_kl | 0.01659235 | +| clip_fraction | 0.329 | +| clip_range | 0.0678 | +| entropy_loss | -5.9 | +| explained_variance | 0.714 | +| learning_rate | 4.31e-05 | +| loss | -0.0279 | +| n_updates | 72196 | +| policy_gradient_loss | -0.0189 | +| value_loss | 9.59e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1407 | +| iterations | 14096 | +| time_elapsed | 20514 | +| total_timesteps | 28868608 | +| train/ | | +| approx_kl | 0.012387684 | +| clip_fraction | 0.338 | +| clip_range | 0.0678 | +| entropy_loss | -6.4 | +| explained_variance | 0.286 | +| learning_rate | 4.31e-05 | +| loss | -0.0334 | +| n_updates | 72200 | +| policy_gradient_loss | -0.0201 | +| value_loss | 7.19e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1407 | +| iterations | 14097 | +| time_elapsed | 20516 | +| total_timesteps | 28870656 | +| train/ | | +| approx_kl | 0.013017952 | +| clip_fraction | 0.342 | +| clip_range | 0.0678 | +| entropy_loss | -6.43 | +| explained_variance | 0.372 | +| learning_rate | 4.31e-05 | +| loss | -0.0287 | +| n_updates | 72204 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000137 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.386 | +| time/ | | +| fps | 1407 | +| iterations | 14098 | +| time_elapsed | 20517 | +| total_timesteps | 28872704 | +| train/ | | +| approx_kl | 0.00905618 | +| clip_fraction | 0.307 | +| clip_range | 0.0678 | +| entropy_loss | -6.34 | +| explained_variance | 0.328 | +| learning_rate | 4.31e-05 | +| loss | -0.0293 | +| n_updates | 72208 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.00029 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.39 | +| time/ | | +| fps | 1407 | +| iterations | 14099 | +| time_elapsed | 20519 | +| total_timesteps | 28874752 | +| train/ | | +| approx_kl | 0.011804733 | +| clip_fraction | 0.324 | +| clip_range | 0.0678 | +| entropy_loss | -6.04 | +| explained_variance | 0.387 | +| learning_rate | 4.31e-05 | +| loss | -0.0288 | +| n_updates | 72212 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000251 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.39 | +| time/ | | +| fps | 1407 | +| iterations | 14100 | +| time_elapsed | 20520 | +| total_timesteps | 28876800 | +| train/ | | +| approx_kl | 0.009939948 | +| clip_fraction | 0.306 | +| clip_range | 0.0678 | +| entropy_loss | -5.94 | +| explained_variance | 0.444 | +| learning_rate | 4.31e-05 | +| loss | -0.0281 | +| n_updates | 72216 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.00024 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.394 | +| time/ | | +| fps | 1407 | +| iterations | 14101 | +| time_elapsed | 20522 | +| total_timesteps | 28878848 | +| train/ | | +| approx_kl | 0.011412782 | +| clip_fraction | 0.359 | +| clip_range | 0.0678 | +| entropy_loss | -6.7 | +| explained_variance | -0.0156 | +| learning_rate | 4.31e-05 | +| loss | -0.0406 | +| n_updates | 72220 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000178 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.385 | +| time/ | | +| fps | 1407 | +| iterations | 14102 | +| time_elapsed | 20524 | +| total_timesteps | 28880896 | +| train/ | | +| approx_kl | 0.015222423 | +| clip_fraction | 0.338 | +| clip_range | 0.0678 | +| entropy_loss | -6.91 | +| explained_variance | -0.106 | +| learning_rate | 4.31e-05 | +| loss | -0.0329 | +| n_updates | 72224 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000233 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.386 | +| time/ | | +| fps | 1407 | +| iterations | 14103 | +| time_elapsed | 20525 | +| total_timesteps | 28882944 | +| train/ | | +| approx_kl | 0.010004727 | +| clip_fraction | 0.333 | +| clip_range | 0.0678 | +| entropy_loss | -5.73 | +| explained_variance | 0.715 | +| learning_rate | 4.31e-05 | +| loss | -0.0259 | +| n_updates | 72228 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000128 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.391 | +| time/ | | +| fps | 1407 | +| iterations | 14104 | +| time_elapsed | 20527 | +| total_timesteps | 28884992 | +| train/ | | +| approx_kl | 0.010662047 | +| clip_fraction | 0.328 | +| clip_range | 0.0678 | +| entropy_loss | -6.04 | +| explained_variance | 0.336 | +| learning_rate | 4.31e-05 | +| loss | -0.0246 | +| n_updates | 72232 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000172 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.391 | +| time/ | | +| fps | 1407 | +| iterations | 14105 | +| time_elapsed | 20528 | +| total_timesteps | 28887040 | +| train/ | | +| approx_kl | 0.008873597 | +| clip_fraction | 0.29 | +| clip_range | 0.0678 | +| entropy_loss | -6.48 | +| explained_variance | 0.29 | +| learning_rate | 4.31e-05 | +| loss | -0.0236 | +| n_updates | 72236 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000339 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.386 | +| time/ | | +| fps | 1407 | +| iterations | 14106 | +| time_elapsed | 20530 | +| total_timesteps | 28889088 | +| train/ | | +| approx_kl | 0.009552988 | +| clip_fraction | 0.313 | +| clip_range | 0.0678 | +| entropy_loss | -5.82 | +| explained_variance | 0.487 | +| learning_rate | 4.31e-05 | +| loss | -0.0204 | +| n_updates | 72240 | +| policy_gradient_loss | -0.0147 | +| value_loss | 0.000199 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.387 | +| time/ | | +| fps | 1407 | +| iterations | 14107 | +| time_elapsed | 20531 | +| total_timesteps | 28891136 | +| train/ | | +| approx_kl | 0.013750632 | +| clip_fraction | 0.326 | +| clip_range | 0.0678 | +| entropy_loss | -5.83 | +| explained_variance | 0.615 | +| learning_rate | 4.31e-05 | +| loss | -0.0343 | +| n_updates | 72244 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000101 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.39 | +| time/ | | +| fps | 1407 | +| iterations | 14108 | +| time_elapsed | 20533 | +| total_timesteps | 28893184 | +| train/ | | +| approx_kl | 0.0123494305 | +| clip_fraction | 0.336 | +| clip_range | 0.0678 | +| entropy_loss | -5.88 | +| explained_variance | 0.715 | +| learning_rate | 4.31e-05 | +| loss | -0.0298 | +| n_updates | 72248 | +| policy_gradient_loss | -0.0194 | +| value_loss | 9.56e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.386 | +| time/ | | +| fps | 1407 | +| iterations | 14109 | +| time_elapsed | 20534 | +| total_timesteps | 28895232 | +| train/ | | +| approx_kl | 0.014971938 | +| clip_fraction | 0.361 | +| clip_range | 0.0678 | +| entropy_loss | -6.21 | +| explained_variance | 0.378 | +| learning_rate | 4.31e-05 | +| loss | -0.0313 | +| n_updates | 72252 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.0001 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.385 | +| time/ | | +| fps | 1407 | +| iterations | 14110 | +| time_elapsed | 20536 | +| total_timesteps | 28897280 | +| train/ | | +| approx_kl | 0.013619902 | +| clip_fraction | 0.341 | +| clip_range | 0.0678 | +| entropy_loss | -6.48 | +| explained_variance | 0.303 | +| learning_rate | 4.31e-05 | +| loss | -0.0321 | +| n_updates | 72256 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000157 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.387 | +| time/ | | +| fps | 1407 | +| iterations | 14111 | +| time_elapsed | 20537 | +| total_timesteps | 28899328 | +| train/ | | +| approx_kl | 0.013909422 | +| clip_fraction | 0.335 | +| clip_range | 0.0678 | +| entropy_loss | -6.27 | +| explained_variance | 0.139 | +| learning_rate | 4.31e-05 | +| loss | -0.026 | +| n_updates | 72260 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000186 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.386 | +| time/ | | +| fps | 1407 | +| iterations | 14112 | +| time_elapsed | 20539 | +| total_timesteps | 28901376 | +| train/ | | +| approx_kl | 0.011947372 | +| clip_fraction | 0.32 | +| clip_range | 0.0678 | +| entropy_loss | -6.26 | +| explained_variance | 0.392 | +| learning_rate | 4.31e-05 | +| loss | -0.0225 | +| n_updates | 72264 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000175 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1407 | +| iterations | 14113 | +| time_elapsed | 20540 | +| total_timesteps | 28903424 | +| train/ | | +| approx_kl | 0.01619206 | +| clip_fraction | 0.341 | +| clip_range | 0.0678 | +| entropy_loss | -5.89 | +| explained_variance | 0.336 | +| learning_rate | 4.31e-05 | +| loss | -0.0278 | +| n_updates | 72268 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.00042 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1407 | +| iterations | 14114 | +| time_elapsed | 20542 | +| total_timesteps | 28905472 | +| train/ | | +| approx_kl | 0.01350644 | +| clip_fraction | 0.337 | +| clip_range | 0.0678 | +| entropy_loss | -5.69 | +| explained_variance | 0.473 | +| learning_rate | 4.31e-05 | +| loss | -0.0259 | +| n_updates | 72272 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000231 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1407 | +| iterations | 14115 | +| time_elapsed | 20544 | +| total_timesteps | 28907520 | +| train/ | | +| approx_kl | 0.014016626 | +| clip_fraction | 0.345 | +| clip_range | 0.0678 | +| entropy_loss | -6.09 | +| explained_variance | 0.25 | +| learning_rate | 4.31e-05 | +| loss | -0.0327 | +| n_updates | 72276 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000169 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.384 | +| time/ | | +| fps | 1407 | +| iterations | 14116 | +| time_elapsed | 20545 | +| total_timesteps | 28909568 | +| train/ | | +| approx_kl | 0.016274737 | +| clip_fraction | 0.354 | +| clip_range | 0.0678 | +| entropy_loss | -6.43 | +| explained_variance | 0.161 | +| learning_rate | 4.31e-05 | +| loss | -0.0275 | +| n_updates | 72280 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000168 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1407 | +| iterations | 14117 | +| time_elapsed | 20547 | +| total_timesteps | 28911616 | +| train/ | | +| approx_kl | 0.01127344 | +| clip_fraction | 0.32 | +| clip_range | 0.0678 | +| entropy_loss | -5.3 | +| explained_variance | 0.675 | +| learning_rate | 4.31e-05 | +| loss | -0.0247 | +| n_updates | 72284 | +| policy_gradient_loss | -0.0142 | +| value_loss | 0.000124 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1407 | +| iterations | 14118 | +| time_elapsed | 20548 | +| total_timesteps | 28913664 | +| train/ | | +| approx_kl | 0.014908163 | +| clip_fraction | 0.337 | +| clip_range | 0.0678 | +| entropy_loss | -6.03 | +| explained_variance | 0.496 | +| learning_rate | 4.31e-05 | +| loss | -0.0264 | +| n_updates | 72288 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000166 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1407 | +| iterations | 14119 | +| time_elapsed | 20550 | +| total_timesteps | 28915712 | +| train/ | | +| approx_kl | 0.013316905 | +| clip_fraction | 0.332 | +| clip_range | 0.0678 | +| entropy_loss | -6.54 | +| explained_variance | -0.0366 | +| learning_rate | 4.31e-05 | +| loss | -0.0306 | +| n_updates | 72292 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000177 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1407 | +| iterations | 14120 | +| time_elapsed | 20551 | +| total_timesteps | 28917760 | +| train/ | | +| approx_kl | 0.01636641 | +| clip_fraction | 0.387 | +| clip_range | 0.0678 | +| entropy_loss | -6.13 | +| explained_variance | 0.685 | +| learning_rate | 4.31e-05 | +| loss | -0.0301 | +| n_updates | 72296 | +| policy_gradient_loss | -0.022 | +| value_loss | 6.92e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1407 | +| iterations | 14121 | +| time_elapsed | 20553 | +| total_timesteps | 28919808 | +| train/ | | +| approx_kl | 0.015524277 | +| clip_fraction | 0.373 | +| clip_range | 0.0678 | +| entropy_loss | -5.68 | +| explained_variance | 0.594 | +| learning_rate | 4.31e-05 | +| loss | -0.0347 | +| n_updates | 72300 | +| policy_gradient_loss | -0.0186 | +| value_loss | 9.87e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1407 | +| iterations | 14122 | +| time_elapsed | 20554 | +| total_timesteps | 28921856 | +| train/ | | +| approx_kl | 0.014648715 | +| clip_fraction | 0.36 | +| clip_range | 0.0678 | +| entropy_loss | -5.83 | +| explained_variance | 0.569 | +| learning_rate | 4.31e-05 | +| loss | -0.03 | +| n_updates | 72304 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000137 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1407 | +| iterations | 14123 | +| time_elapsed | 20556 | +| total_timesteps | 28923904 | +| train/ | | +| approx_kl | 0.011712059 | +| clip_fraction | 0.344 | +| clip_range | 0.0678 | +| entropy_loss | -6.64 | +| explained_variance | 0.0399 | +| learning_rate | 4.31e-05 | +| loss | -0.0308 | +| n_updates | 72308 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000133 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1407 | +| iterations | 14124 | +| time_elapsed | 20557 | +| total_timesteps | 28925952 | +| train/ | | +| approx_kl | 0.013642923 | +| clip_fraction | 0.322 | +| clip_range | 0.0678 | +| entropy_loss | -6.16 | +| explained_variance | 0.478 | +| learning_rate | 4.31e-05 | +| loss | -0.0268 | +| n_updates | 72312 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000213 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1407 | +| iterations | 14125 | +| time_elapsed | 20559 | +| total_timesteps | 28928000 | +| train/ | | +| approx_kl | 0.016328007 | +| clip_fraction | 0.342 | +| clip_range | 0.0678 | +| entropy_loss | -5.67 | +| explained_variance | 0.681 | +| learning_rate | 4.31e-05 | +| loss | -0.0312 | +| n_updates | 72316 | +| policy_gradient_loss | -0.0203 | +| value_loss | 7.25e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1407 | +| iterations | 14126 | +| time_elapsed | 20560 | +| total_timesteps | 28930048 | +| train/ | | +| approx_kl | 0.019794874 | +| clip_fraction | 0.325 | +| clip_range | 0.0678 | +| entropy_loss | -5.13 | +| explained_variance | 0.39 | +| learning_rate | 4.31e-05 | +| loss | -0.02 | +| n_updates | 72320 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000308 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1407 | +| iterations | 14127 | +| time_elapsed | 20562 | +| total_timesteps | 28932096 | +| train/ | | +| approx_kl | 0.012811895 | +| clip_fraction | 0.35 | +| clip_range | 0.0678 | +| entropy_loss | -6.06 | +| explained_variance | 0.211 | +| learning_rate | 4.31e-05 | +| loss | -0.0353 | +| n_updates | 72324 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000137 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1407 | +| iterations | 14128 | +| time_elapsed | 20563 | +| total_timesteps | 28934144 | +| train/ | | +| approx_kl | 0.0133303115 | +| clip_fraction | 0.344 | +| clip_range | 0.0678 | +| entropy_loss | -6.07 | +| explained_variance | 0.696 | +| learning_rate | 4.31e-05 | +| loss | -0.0352 | +| n_updates | 72328 | +| policy_gradient_loss | -0.0203 | +| value_loss | 7.49e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1407 | +| iterations | 14129 | +| time_elapsed | 20565 | +| total_timesteps | 28936192 | +| train/ | | +| approx_kl | 0.012260772 | +| clip_fraction | 0.33 | +| clip_range | 0.0678 | +| entropy_loss | -6.51 | +| explained_variance | 0.0581 | +| learning_rate | 4.31e-05 | +| loss | -0.0288 | +| n_updates | 72332 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000146 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1407 | +| iterations | 14130 | +| time_elapsed | 20566 | +| total_timesteps | 28938240 | +| train/ | | +| approx_kl | 0.010665517 | +| clip_fraction | 0.316 | +| clip_range | 0.0678 | +| entropy_loss | -6.26 | +| explained_variance | 0.37 | +| learning_rate | 4.31e-05 | +| loss | -0.0334 | +| n_updates | 72336 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000234 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1407 | +| iterations | 14131 | +| time_elapsed | 20568 | +| total_timesteps | 28940288 | +| train/ | | +| approx_kl | 0.013517614 | +| clip_fraction | 0.357 | +| clip_range | 0.0678 | +| entropy_loss | -6.03 | +| explained_variance | 0.648 | +| learning_rate | 4.31e-05 | +| loss | -0.034 | +| n_updates | 72340 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000112 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1407 | +| iterations | 14132 | +| time_elapsed | 20570 | +| total_timesteps | 28942336 | +| train/ | | +| approx_kl | 0.010123259 | +| clip_fraction | 0.339 | +| clip_range | 0.0678 | +| entropy_loss | -6.15 | +| explained_variance | 0.373 | +| learning_rate | 4.31e-05 | +| loss | -0.028 | +| n_updates | 72344 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000147 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1407 | +| iterations | 14133 | +| time_elapsed | 20571 | +| total_timesteps | 28944384 | +| train/ | | +| approx_kl | 0.012001346 | +| clip_fraction | 0.299 | +| clip_range | 0.0678 | +| entropy_loss | -5.58 | +| explained_variance | 0.472 | +| learning_rate | 4.31e-05 | +| loss | -0.0264 | +| n_updates | 72348 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000334 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1406 | +| iterations | 14134 | +| time_elapsed | 20573 | +| total_timesteps | 28946432 | +| train/ | | +| approx_kl | 0.013685761 | +| clip_fraction | 0.324 | +| clip_range | 0.0678 | +| entropy_loss | -5.79 | +| explained_variance | 0.425 | +| learning_rate | 4.31e-05 | +| loss | -0.0255 | +| n_updates | 72352 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000241 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1406 | +| iterations | 14135 | +| time_elapsed | 20574 | +| total_timesteps | 28948480 | +| train/ | | +| approx_kl | 0.011928946 | +| clip_fraction | 0.316 | +| clip_range | 0.0678 | +| entropy_loss | -5.53 | +| explained_variance | 0.427 | +| learning_rate | 4.31e-05 | +| loss | -0.0214 | +| n_updates | 72356 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.00026 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1406 | +| iterations | 14136 | +| time_elapsed | 20576 | +| total_timesteps | 28950528 | +| train/ | | +| approx_kl | 0.015657473 | +| clip_fraction | 0.366 | +| clip_range | 0.0678 | +| entropy_loss | -6.33 | +| explained_variance | -0.144 | +| learning_rate | 4.31e-05 | +| loss | -0.0346 | +| n_updates | 72360 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000111 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1406 | +| iterations | 14137 | +| time_elapsed | 20577 | +| total_timesteps | 28952576 | +| train/ | | +| approx_kl | 0.016257133 | +| clip_fraction | 0.376 | +| clip_range | 0.0678 | +| entropy_loss | -6.82 | +| explained_variance | -0.148 | +| learning_rate | 4.31e-05 | +| loss | -0.0322 | +| n_updates | 72364 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.00015 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1406 | +| iterations | 14138 | +| time_elapsed | 20579 | +| total_timesteps | 28954624 | +| train/ | | +| approx_kl | 0.012457829 | +| clip_fraction | 0.363 | +| clip_range | 0.0678 | +| entropy_loss | -6.17 | +| explained_variance | 0.301 | +| learning_rate | 4.31e-05 | +| loss | -0.0248 | +| n_updates | 72368 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000303 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1406 | +| iterations | 14139 | +| time_elapsed | 20580 | +| total_timesteps | 28956672 | +| train/ | | +| approx_kl | 0.016852485 | +| clip_fraction | 0.34 | +| clip_range | 0.0678 | +| entropy_loss | -5.65 | +| explained_variance | 0.362 | +| learning_rate | 4.31e-05 | +| loss | -0.0274 | +| n_updates | 72372 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000231 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1406 | +| iterations | 14140 | +| time_elapsed | 20582 | +| total_timesteps | 28958720 | +| train/ | | +| approx_kl | 0.012499261 | +| clip_fraction | 0.346 | +| clip_range | 0.0678 | +| entropy_loss | -6.14 | +| explained_variance | 0.358 | +| learning_rate | 4.31e-05 | +| loss | -0.0344 | +| n_updates | 72376 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000121 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1406 | +| iterations | 14141 | +| time_elapsed | 20583 | +| total_timesteps | 28960768 | +| train/ | | +| approx_kl | 0.013448544 | +| clip_fraction | 0.335 | +| clip_range | 0.0678 | +| entropy_loss | -6.01 | +| explained_variance | 0.501 | +| learning_rate | 4.31e-05 | +| loss | -0.0283 | +| n_updates | 72380 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.00014 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1406 | +| iterations | 14142 | +| time_elapsed | 20585 | +| total_timesteps | 28962816 | +| train/ | | +| approx_kl | 0.01700224 | +| clip_fraction | 0.376 | +| clip_range | 0.0678 | +| entropy_loss | -6.3 | +| explained_variance | 0.465 | +| learning_rate | 4.31e-05 | +| loss | -0.0353 | +| n_updates | 72384 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000126 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1406 | +| iterations | 14143 | +| time_elapsed | 20587 | +| total_timesteps | 28964864 | +| train/ | | +| approx_kl | 0.015786149 | +| clip_fraction | 0.363 | +| clip_range | 0.0678 | +| entropy_loss | -6.18 | +| explained_variance | 0.489 | +| learning_rate | 4.31e-05 | +| loss | -0.0321 | +| n_updates | 72388 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1406 | +| iterations | 14144 | +| time_elapsed | 20588 | +| total_timesteps | 28966912 | +| train/ | | +| approx_kl | 0.011749641 | +| clip_fraction | 0.339 | +| clip_range | 0.0678 | +| entropy_loss | -6.21 | +| explained_variance | 0.235 | +| learning_rate | 4.31e-05 | +| loss | -0.0228 | +| n_updates | 72392 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000303 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1406 | +| iterations | 14145 | +| time_elapsed | 20590 | +| total_timesteps | 28968960 | +| train/ | | +| approx_kl | 0.0123307975 | +| clip_fraction | 0.341 | +| clip_range | 0.0678 | +| entropy_loss | -6.02 | +| explained_variance | 0.52 | +| learning_rate | 4.31e-05 | +| loss | -0.0326 | +| n_updates | 72396 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.00012 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1406 | +| iterations | 14146 | +| time_elapsed | 20591 | +| total_timesteps | 28971008 | +| train/ | | +| approx_kl | 0.012765318 | +| clip_fraction | 0.328 | +| clip_range | 0.0678 | +| entropy_loss | -5.81 | +| explained_variance | 0.475 | +| learning_rate | 4.31e-05 | +| loss | -0.0275 | +| n_updates | 72400 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.000197 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1406 | +| iterations | 14147 | +| time_elapsed | 20593 | +| total_timesteps | 28973056 | +| train/ | | +| approx_kl | 0.011027269 | +| clip_fraction | 0.319 | +| clip_range | 0.0678 | +| entropy_loss | -6.1 | +| explained_variance | 0.474 | +| learning_rate | 4.31e-05 | +| loss | -0.0255 | +| n_updates | 72404 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000158 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1406 | +| iterations | 14148 | +| time_elapsed | 20594 | +| total_timesteps | 28975104 | +| train/ | | +| approx_kl | 0.0141608445 | +| clip_fraction | 0.333 | +| clip_range | 0.0678 | +| entropy_loss | -6.44 | +| explained_variance | 0.271 | +| learning_rate | 4.31e-05 | +| loss | -0.0335 | +| n_updates | 72408 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000181 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1406 | +| iterations | 14149 | +| time_elapsed | 20596 | +| total_timesteps | 28977152 | +| train/ | | +| approx_kl | 0.013139134 | +| clip_fraction | 0.316 | +| clip_range | 0.0678 | +| entropy_loss | -5.46 | +| explained_variance | 0.398 | +| learning_rate | 4.31e-05 | +| loss | -0.0238 | +| n_updates | 72412 | +| policy_gradient_loss | -0.0147 | +| value_loss | 0.000365 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1406 | +| iterations | 14150 | +| time_elapsed | 20597 | +| total_timesteps | 28979200 | +| train/ | | +| approx_kl | 0.015906384 | +| clip_fraction | 0.359 | +| clip_range | 0.0678 | +| entropy_loss | -5.88 | +| explained_variance | 0.197 | +| learning_rate | 4.31e-05 | +| loss | -0.0291 | +| n_updates | 72416 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000248 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1406 | +| iterations | 14151 | +| time_elapsed | 20599 | +| total_timesteps | 28981248 | +| train/ | | +| approx_kl | 0.014807599 | +| clip_fraction | 0.359 | +| clip_range | 0.0678 | +| entropy_loss | -5.29 | +| explained_variance | 0.421 | +| learning_rate | 4.31e-05 | +| loss | -0.0274 | +| n_updates | 72420 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000272 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1406 | +| iterations | 14152 | +| time_elapsed | 20600 | +| total_timesteps | 28983296 | +| train/ | | +| approx_kl | 0.017587852 | +| clip_fraction | 0.35 | +| clip_range | 0.0678 | +| entropy_loss | -5.94 | +| explained_variance | 0.336 | +| learning_rate | 4.31e-05 | +| loss | -0.0372 | +| n_updates | 72424 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000242 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1406 | +| iterations | 14153 | +| time_elapsed | 20602 | +| total_timesteps | 28985344 | +| train/ | | +| approx_kl | 0.012100327 | +| clip_fraction | 0.355 | +| clip_range | 0.0678 | +| entropy_loss | -6.45 | +| explained_variance | 0.197 | +| learning_rate | 4.31e-05 | +| loss | -0.029 | +| n_updates | 72428 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000235 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1406 | +| iterations | 14154 | +| time_elapsed | 20604 | +| total_timesteps | 28987392 | +| train/ | | +| approx_kl | 0.016463276 | +| clip_fraction | 0.406 | +| clip_range | 0.0678 | +| entropy_loss | -6.67 | +| explained_variance | 0.127 | +| learning_rate | 4.31e-05 | +| loss | -0.0359 | +| n_updates | 72432 | +| policy_gradient_loss | -0.0239 | +| value_loss | 0.000111 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1406 | +| iterations | 14155 | +| time_elapsed | 20605 | +| total_timesteps | 28989440 | +| train/ | | +| approx_kl | 0.014384091 | +| clip_fraction | 0.369 | +| clip_range | 0.0678 | +| entropy_loss | -6.33 | +| explained_variance | 0.606 | +| learning_rate | 4.31e-05 | +| loss | -0.0425 | +| n_updates | 72436 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000115 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1406 | +| iterations | 14156 | +| time_elapsed | 20607 | +| total_timesteps | 28991488 | +| train/ | | +| approx_kl | 0.015090022 | +| clip_fraction | 0.324 | +| clip_range | 0.0678 | +| entropy_loss | -6.66 | +| explained_variance | -0.0543 | +| learning_rate | 4.31e-05 | +| loss | -0.0198 | +| n_updates | 72440 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000195 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1406 | +| iterations | 14157 | +| time_elapsed | 20608 | +| total_timesteps | 28993536 | +| train/ | | +| approx_kl | 0.01310407 | +| clip_fraction | 0.335 | +| clip_range | 0.0678 | +| entropy_loss | -6.42 | +| explained_variance | 0.62 | +| learning_rate | 4.31e-05 | +| loss | -0.0296 | +| n_updates | 72444 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000105 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1406 | +| iterations | 14158 | +| time_elapsed | 20610 | +| total_timesteps | 28995584 | +| train/ | | +| approx_kl | 0.014362933 | +| clip_fraction | 0.344 | +| clip_range | 0.0678 | +| entropy_loss | -5.69 | +| explained_variance | 0.72 | +| learning_rate | 4.31e-05 | +| loss | -0.0271 | +| n_updates | 72448 | +| policy_gradient_loss | -0.0147 | +| value_loss | 0.0001 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1406 | +| iterations | 14159 | +| time_elapsed | 20611 | +| total_timesteps | 28997632 | +| train/ | | +| approx_kl | 0.01707584 | +| clip_fraction | 0.377 | +| clip_range | 0.0678 | +| entropy_loss | -5.87 | +| explained_variance | 0.715 | +| learning_rate | 4.31e-05 | +| loss | -0.0366 | +| n_updates | 72452 | +| policy_gradient_loss | -0.0222 | +| value_loss | 5.15e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1406 | +| iterations | 14160 | +| time_elapsed | 20613 | +| total_timesteps | 28999680 | +| train/ | | +| approx_kl | 0.013724398 | +| clip_fraction | 0.344 | +| clip_range | 0.0678 | +| entropy_loss | -5.99 | +| explained_variance | 0.679 | +| learning_rate | 4.31e-05 | +| loss | -0.0305 | +| n_updates | 72456 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000114 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1406 | +| iterations | 14161 | +| time_elapsed | 20614 | +| total_timesteps | 29001728 | +| train/ | | +| approx_kl | 0.015738878 | +| clip_fraction | 0.356 | +| clip_range | 0.0678 | +| entropy_loss | -5.65 | +| explained_variance | 0.544 | +| learning_rate | 4.31e-05 | +| loss | -0.0282 | +| n_updates | 72460 | +| policy_gradient_loss | -0.0196 | +| value_loss | 5.48e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1406 | +| iterations | 14162 | +| time_elapsed | 20616 | +| total_timesteps | 29003776 | +| train/ | | +| approx_kl | 0.016480304 | +| clip_fraction | 0.341 | +| clip_range | 0.0677 | +| entropy_loss | -5.96 | +| explained_variance | 0.528 | +| learning_rate | 4.31e-05 | +| loss | -0.0266 | +| n_updates | 72464 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000143 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1406 | +| iterations | 14163 | +| time_elapsed | 20617 | +| total_timesteps | 29005824 | +| train/ | | +| approx_kl | 0.0140686 | +| clip_fraction | 0.349 | +| clip_range | 0.0677 | +| entropy_loss | -6.58 | +| explained_variance | -0.179 | +| learning_rate | 4.31e-05 | +| loss | -0.0341 | +| n_updates | 72468 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000146 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1406 | +| iterations | 14164 | +| time_elapsed | 20619 | +| total_timesteps | 29007872 | +| train/ | | +| approx_kl | 0.014522973 | +| clip_fraction | 0.335 | +| clip_range | 0.0677 | +| entropy_loss | -6.79 | +| explained_variance | 0.038 | +| learning_rate | 4.31e-05 | +| loss | -0.0321 | +| n_updates | 72472 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000156 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1406 | +| iterations | 14165 | +| time_elapsed | 20621 | +| total_timesteps | 29009920 | +| train/ | | +| approx_kl | 0.018642735 | +| clip_fraction | 0.34 | +| clip_range | 0.0677 | +| entropy_loss | -6.28 | +| explained_variance | 0.292 | +| learning_rate | 4.31e-05 | +| loss | -0.0316 | +| n_updates | 72476 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000186 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1406 | +| iterations | 14166 | +| time_elapsed | 20622 | +| total_timesteps | 29011968 | +| train/ | | +| approx_kl | 0.015842702 | +| clip_fraction | 0.335 | +| clip_range | 0.0677 | +| entropy_loss | -6.27 | +| explained_variance | -0.167 | +| learning_rate | 4.31e-05 | +| loss | -0.0269 | +| n_updates | 72480 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000206 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1406 | +| iterations | 14167 | +| time_elapsed | 20624 | +| total_timesteps | 29014016 | +| train/ | | +| approx_kl | 0.01174875 | +| clip_fraction | 0.339 | +| clip_range | 0.0677 | +| entropy_loss | -5.77 | +| explained_variance | 0.456 | +| learning_rate | 4.31e-05 | +| loss | -0.0179 | +| n_updates | 72484 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000205 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1406 | +| iterations | 14168 | +| time_elapsed | 20625 | +| total_timesteps | 29016064 | +| train/ | | +| approx_kl | 0.014220144 | +| clip_fraction | 0.363 | +| clip_range | 0.0677 | +| entropy_loss | -5.51 | +| explained_variance | 0.732 | +| learning_rate | 4.31e-05 | +| loss | -0.0307 | +| n_updates | 72488 | +| policy_gradient_loss | -0.0208 | +| value_loss | 7.81e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1406 | +| iterations | 14169 | +| time_elapsed | 20627 | +| total_timesteps | 29018112 | +| train/ | | +| approx_kl | 0.014623308 | +| clip_fraction | 0.362 | +| clip_range | 0.0677 | +| entropy_loss | -6.25 | +| explained_variance | -0.0823 | +| learning_rate | 4.31e-05 | +| loss | -0.0295 | +| n_updates | 72492 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000129 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1406 | +| iterations | 14170 | +| time_elapsed | 20628 | +| total_timesteps | 29020160 | +| train/ | | +| approx_kl | 0.014105562 | +| clip_fraction | 0.35 | +| clip_range | 0.0677 | +| entropy_loss | -6.09 | +| explained_variance | 0.439 | +| learning_rate | 4.31e-05 | +| loss | -0.0327 | +| n_updates | 72496 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000158 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1406 | +| iterations | 14171 | +| time_elapsed | 20630 | +| total_timesteps | 29022208 | +| train/ | | +| approx_kl | 0.014953546 | +| clip_fraction | 0.326 | +| clip_range | 0.0677 | +| entropy_loss | -6.54 | +| explained_variance | 0.114 | +| learning_rate | 4.31e-05 | +| loss | -0.0272 | +| n_updates | 72500 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000108 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1406 | +| iterations | 14172 | +| time_elapsed | 20631 | +| total_timesteps | 29024256 | +| train/ | | +| approx_kl | 0.011771817 | +| clip_fraction | 0.365 | +| clip_range | 0.0677 | +| entropy_loss | -6 | +| explained_variance | 0.562 | +| learning_rate | 4.31e-05 | +| loss | -0.0287 | +| n_updates | 72504 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000156 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 1406 | +| iterations | 14173 | +| time_elapsed | 20633 | +| total_timesteps | 29026304 | +| train/ | | +| approx_kl | 0.014798168 | +| clip_fraction | 0.339 | +| clip_range | 0.0677 | +| entropy_loss | -5.61 | +| explained_variance | 0.511 | +| learning_rate | 4.31e-05 | +| loss | -0.0304 | +| n_updates | 72508 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000148 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 1406 | +| iterations | 14174 | +| time_elapsed | 20634 | +| total_timesteps | 29028352 | +| train/ | | +| approx_kl | 0.013366532 | +| clip_fraction | 0.329 | +| clip_range | 0.0677 | +| entropy_loss | -5.89 | +| explained_variance | 0.476 | +| learning_rate | 4.31e-05 | +| loss | -0.029 | +| n_updates | 72512 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000215 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.306 | +| time/ | | +| fps | 1406 | +| iterations | 14175 | +| time_elapsed | 20636 | +| total_timesteps | 29030400 | +| train/ | | +| approx_kl | 0.011960753 | +| clip_fraction | 0.32 | +| clip_range | 0.0677 | +| entropy_loss | -5.61 | +| explained_variance | 0.481 | +| learning_rate | 4.31e-05 | +| loss | -0.0214 | +| n_updates | 72516 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000203 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.306 | +| time/ | | +| fps | 1406 | +| iterations | 14176 | +| time_elapsed | 20638 | +| total_timesteps | 29032448 | +| train/ | | +| approx_kl | 0.015398745 | +| clip_fraction | 0.373 | +| clip_range | 0.0677 | +| entropy_loss | -5.9 | +| explained_variance | 0.45 | +| learning_rate | 4.31e-05 | +| loss | -0.033 | +| n_updates | 72520 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000122 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1406 | +| iterations | 14177 | +| time_elapsed | 20639 | +| total_timesteps | 29034496 | +| train/ | | +| approx_kl | 0.017339267 | +| clip_fraction | 0.387 | +| clip_range | 0.0677 | +| entropy_loss | -6.37 | +| explained_variance | -0.187 | +| learning_rate | 4.31e-05 | +| loss | -0.0339 | +| n_updates | 72524 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.00019 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1406 | +| iterations | 14178 | +| time_elapsed | 20641 | +| total_timesteps | 29036544 | +| train/ | | +| approx_kl | 0.01338691 | +| clip_fraction | 0.378 | +| clip_range | 0.0677 | +| entropy_loss | -6.46 | +| explained_variance | 0.175 | +| learning_rate | 4.31e-05 | +| loss | -0.0303 | +| n_updates | 72528 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000207 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1406 | +| iterations | 14179 | +| time_elapsed | 20642 | +| total_timesteps | 29038592 | +| train/ | | +| approx_kl | 0.015970167 | +| clip_fraction | 0.354 | +| clip_range | 0.0677 | +| entropy_loss | -5.72 | +| explained_variance | 0.462 | +| learning_rate | 4.31e-05 | +| loss | -0.0304 | +| n_updates | 72532 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000246 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1406 | +| iterations | 14180 | +| time_elapsed | 20644 | +| total_timesteps | 29040640 | +| train/ | | +| approx_kl | 0.015380391 | +| clip_fraction | 0.332 | +| clip_range | 0.0677 | +| entropy_loss | -5.96 | +| explained_variance | 0.0895 | +| learning_rate | 4.31e-05 | +| loss | -0.0275 | +| n_updates | 72536 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000499 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1406 | +| iterations | 14181 | +| time_elapsed | 20645 | +| total_timesteps | 29042688 | +| train/ | | +| approx_kl | 0.016288457 | +| clip_fraction | 0.371 | +| clip_range | 0.0677 | +| entropy_loss | -5.05 | +| explained_variance | 0.64 | +| learning_rate | 4.31e-05 | +| loss | -0.032 | +| n_updates | 72540 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1406 | +| iterations | 14182 | +| time_elapsed | 20647 | +| total_timesteps | 29044736 | +| train/ | | +| approx_kl | 0.014909058 | +| clip_fraction | 0.371 | +| clip_range | 0.0677 | +| entropy_loss | -5.41 | +| explained_variance | 0.574 | +| learning_rate | 4.31e-05 | +| loss | -0.0357 | +| n_updates | 72544 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000111 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1406 | +| iterations | 14183 | +| time_elapsed | 20648 | +| total_timesteps | 29046784 | +| train/ | | +| approx_kl | 0.0127743315 | +| clip_fraction | 0.353 | +| clip_range | 0.0677 | +| entropy_loss | -6.21 | +| explained_variance | 0.116 | +| learning_rate | 4.31e-05 | +| loss | -0.0303 | +| n_updates | 72548 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000222 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1406 | +| iterations | 14184 | +| time_elapsed | 20650 | +| total_timesteps | 29048832 | +| train/ | | +| approx_kl | 0.0115113035 | +| clip_fraction | 0.365 | +| clip_range | 0.0677 | +| entropy_loss | -6.87 | +| explained_variance | 0.00548 | +| learning_rate | 4.31e-05 | +| loss | -0.0238 | +| n_updates | 72552 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000155 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1406 | +| iterations | 14185 | +| time_elapsed | 20651 | +| total_timesteps | 29050880 | +| train/ | | +| approx_kl | 0.012747929 | +| clip_fraction | 0.35 | +| clip_range | 0.0677 | +| entropy_loss | -6.56 | +| explained_variance | 0.557 | +| learning_rate | 4.31e-05 | +| loss | -0.0338 | +| n_updates | 72556 | +| policy_gradient_loss | -0.0197 | +| value_loss | 6.85e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1406 | +| iterations | 14186 | +| time_elapsed | 20653 | +| total_timesteps | 29052928 | +| train/ | | +| approx_kl | 0.011713328 | +| clip_fraction | 0.331 | +| clip_range | 0.0677 | +| entropy_loss | -6.49 | +| explained_variance | 0.278 | +| learning_rate | 4.31e-05 | +| loss | -0.0327 | +| n_updates | 72560 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000213 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1406 | +| iterations | 14187 | +| time_elapsed | 20654 | +| total_timesteps | 29054976 | +| train/ | | +| approx_kl | 0.01624106 | +| clip_fraction | 0.336 | +| clip_range | 0.0677 | +| entropy_loss | -6.43 | +| explained_variance | 0.365 | +| learning_rate | 4.31e-05 | +| loss | -0.0349 | +| n_updates | 72564 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000139 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1406 | +| iterations | 14188 | +| time_elapsed | 20656 | +| total_timesteps | 29057024 | +| train/ | | +| approx_kl | 0.014724927 | +| clip_fraction | 0.353 | +| clip_range | 0.0677 | +| entropy_loss | -6.26 | +| explained_variance | 0.45 | +| learning_rate | 4.31e-05 | +| loss | -0.0298 | +| n_updates | 72568 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000136 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1406 | +| iterations | 14189 | +| time_elapsed | 20657 | +| total_timesteps | 29059072 | +| train/ | | +| approx_kl | 0.013613555 | +| clip_fraction | 0.344 | +| clip_range | 0.0677 | +| entropy_loss | -6.22 | +| explained_variance | 0.536 | +| learning_rate | 4.31e-05 | +| loss | -0.0329 | +| n_updates | 72572 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000126 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1406 | +| iterations | 14190 | +| time_elapsed | 20659 | +| total_timesteps | 29061120 | +| train/ | | +| approx_kl | 0.015583947 | +| clip_fraction | 0.376 | +| clip_range | 0.0677 | +| entropy_loss | -5.92 | +| explained_variance | 0.653 | +| learning_rate | 4.31e-05 | +| loss | -0.0354 | +| n_updates | 72576 | +| policy_gradient_loss | -0.0217 | +| value_loss | 8.05e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1406 | +| iterations | 14191 | +| time_elapsed | 20660 | +| total_timesteps | 29063168 | +| train/ | | +| approx_kl | 0.011669452 | +| clip_fraction | 0.341 | +| clip_range | 0.0677 | +| entropy_loss | -5.75 | +| explained_variance | 0.67 | +| learning_rate | 4.31e-05 | +| loss | -0.0313 | +| n_updates | 72580 | +| policy_gradient_loss | -0.0186 | +| value_loss | 9.04e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.315 | +| time/ | | +| fps | 1406 | +| iterations | 14192 | +| time_elapsed | 20662 | +| total_timesteps | 29065216 | +| train/ | | +| approx_kl | 0.01213643 | +| clip_fraction | 0.356 | +| clip_range | 0.0677 | +| entropy_loss | -5.7 | +| explained_variance | 0.805 | +| learning_rate | 4.31e-05 | +| loss | -0.0256 | +| n_updates | 72584 | +| policy_gradient_loss | -0.0171 | +| value_loss | 5.21e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1406 | +| iterations | 14193 | +| time_elapsed | 20663 | +| total_timesteps | 29067264 | +| train/ | | +| approx_kl | 0.012557825 | +| clip_fraction | 0.337 | +| clip_range | 0.0677 | +| entropy_loss | -6.39 | +| explained_variance | 0.337 | +| learning_rate | 4.31e-05 | +| loss | -0.0277 | +| n_updates | 72588 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000147 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1406 | +| iterations | 14194 | +| time_elapsed | 20665 | +| total_timesteps | 29069312 | +| train/ | | +| approx_kl | 0.016023342 | +| clip_fraction | 0.359 | +| clip_range | 0.0677 | +| entropy_loss | -5.97 | +| explained_variance | 0.559 | +| learning_rate | 4.31e-05 | +| loss | -0.0258 | +| n_updates | 72592 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1406 | +| iterations | 14195 | +| time_elapsed | 20666 | +| total_timesteps | 29071360 | +| train/ | | +| approx_kl | 0.013691943 | +| clip_fraction | 0.371 | +| clip_range | 0.0677 | +| entropy_loss | -6.56 | +| explained_variance | 0.438 | +| learning_rate | 4.31e-05 | +| loss | -0.0366 | +| n_updates | 72596 | +| policy_gradient_loss | -0.0206 | +| value_loss | 8.75e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1406 | +| iterations | 14196 | +| time_elapsed | 20668 | +| total_timesteps | 29073408 | +| train/ | | +| approx_kl | 0.014210796 | +| clip_fraction | 0.341 | +| clip_range | 0.0677 | +| entropy_loss | -6.53 | +| explained_variance | 0.38 | +| learning_rate | 4.31e-05 | +| loss | -0.0275 | +| n_updates | 72600 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000122 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1406 | +| iterations | 14197 | +| time_elapsed | 20669 | +| total_timesteps | 29075456 | +| train/ | | +| approx_kl | 0.0146123255 | +| clip_fraction | 0.319 | +| clip_range | 0.0677 | +| entropy_loss | -6.47 | +| explained_variance | -0.148 | +| learning_rate | 4.31e-05 | +| loss | -0.0292 | +| n_updates | 72604 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000154 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1406 | +| iterations | 14198 | +| time_elapsed | 20671 | +| total_timesteps | 29077504 | +| train/ | | +| approx_kl | 0.014931885 | +| clip_fraction | 0.357 | +| clip_range | 0.0677 | +| entropy_loss | -6.49 | +| explained_variance | 0.19 | +| learning_rate | 4.31e-05 | +| loss | -0.033 | +| n_updates | 72608 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000282 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1406 | +| iterations | 14199 | +| time_elapsed | 20673 | +| total_timesteps | 29079552 | +| train/ | | +| approx_kl | 0.0148701565 | +| clip_fraction | 0.376 | +| clip_range | 0.0677 | +| entropy_loss | -6.4 | +| explained_variance | 0.384 | +| learning_rate | 4.31e-05 | +| loss | -0.036 | +| n_updates | 72612 | +| policy_gradient_loss | -0.0216 | +| value_loss | 9.93e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1406 | +| iterations | 14200 | +| time_elapsed | 20674 | +| total_timesteps | 29081600 | +| train/ | | +| approx_kl | 0.014203444 | +| clip_fraction | 0.354 | +| clip_range | 0.0677 | +| entropy_loss | -6.52 | +| explained_variance | -0.436 | +| learning_rate | 4.31e-05 | +| loss | -0.0329 | +| n_updates | 72616 | +| policy_gradient_loss | -0.022 | +| value_loss | 9.02e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.315 | +| time/ | | +| fps | 1406 | +| iterations | 14201 | +| time_elapsed | 20676 | +| total_timesteps | 29083648 | +| train/ | | +| approx_kl | 0.01553282 | +| clip_fraction | 0.369 | +| clip_range | 0.0677 | +| entropy_loss | -6.5 | +| explained_variance | 0.313 | +| learning_rate | 4.31e-05 | +| loss | -0.034 | +| n_updates | 72620 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000112 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1406 | +| iterations | 14202 | +| time_elapsed | 20677 | +| total_timesteps | 29085696 | +| train/ | | +| approx_kl | 0.015933298 | +| clip_fraction | 0.358 | +| clip_range | 0.0677 | +| entropy_loss | -6.01 | +| explained_variance | 0.501 | +| learning_rate | 4.31e-05 | +| loss | -0.026 | +| n_updates | 72624 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000246 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1406 | +| iterations | 14203 | +| time_elapsed | 20679 | +| total_timesteps | 29087744 | +| train/ | | +| approx_kl | 0.014672345 | +| clip_fraction | 0.321 | +| clip_range | 0.0677 | +| entropy_loss | -5.09 | +| explained_variance | 0.252 | +| learning_rate | 4.31e-05 | +| loss | -0.0284 | +| n_updates | 72628 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000156 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1406 | +| iterations | 14204 | +| time_elapsed | 20680 | +| total_timesteps | 29089792 | +| train/ | | +| approx_kl | 0.013645772 | +| clip_fraction | 0.346 | +| clip_range | 0.0677 | +| entropy_loss | -5.43 | +| explained_variance | 0.572 | +| learning_rate | 4.31e-05 | +| loss | -0.0245 | +| n_updates | 72632 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000103 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1406 | +| iterations | 14205 | +| time_elapsed | 20682 | +| total_timesteps | 29091840 | +| train/ | | +| approx_kl | 0.015020917 | +| clip_fraction | 0.35 | +| clip_range | 0.0677 | +| entropy_loss | -6.06 | +| explained_variance | 0.256 | +| learning_rate | 4.31e-05 | +| loss | -0.0249 | +| n_updates | 72636 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000231 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1406 | +| iterations | 14206 | +| time_elapsed | 20683 | +| total_timesteps | 29093888 | +| train/ | | +| approx_kl | 0.01432876 | +| clip_fraction | 0.372 | +| clip_range | 0.0677 | +| entropy_loss | -6.26 | +| explained_variance | 0.346 | +| learning_rate | 4.31e-05 | +| loss | -0.0396 | +| n_updates | 72640 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000105 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1406 | +| iterations | 14207 | +| time_elapsed | 20685 | +| total_timesteps | 29095936 | +| train/ | | +| approx_kl | 0.016239498 | +| clip_fraction | 0.355 | +| clip_range | 0.0677 | +| entropy_loss | -6.33 | +| explained_variance | 0.35 | +| learning_rate | 4.31e-05 | +| loss | -0.0305 | +| n_updates | 72644 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000165 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 1406 | +| iterations | 14208 | +| time_elapsed | 20686 | +| total_timesteps | 29097984 | +| train/ | | +| approx_kl | 0.019314632 | +| clip_fraction | 0.363 | +| clip_range | 0.0677 | +| entropy_loss | -5.7 | +| explained_variance | 0.661 | +| learning_rate | 4.31e-05 | +| loss | -0.0306 | +| n_updates | 72648 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000105 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.294 | +| time/ | | +| fps | 1406 | +| iterations | 14209 | +| time_elapsed | 20688 | +| total_timesteps | 29100032 | +| train/ | | +| approx_kl | 0.013602341 | +| clip_fraction | 0.328 | +| clip_range | 0.0677 | +| entropy_loss | -5.91 | +| explained_variance | 0.557 | +| learning_rate | 4.31e-05 | +| loss | -0.0288 | +| n_updates | 72652 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000119 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.294 | +| time/ | | +| fps | 1406 | +| iterations | 14210 | +| time_elapsed | 20689 | +| total_timesteps | 29102080 | +| train/ | | +| approx_kl | 0.0108254645 | +| clip_fraction | 0.345 | +| clip_range | 0.0677 | +| entropy_loss | -6.24 | +| explained_variance | 0.397 | +| learning_rate | 4.31e-05 | +| loss | -0.0273 | +| n_updates | 72656 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.00016 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.295 | +| time/ | | +| fps | 1406 | +| iterations | 14211 | +| time_elapsed | 20691 | +| total_timesteps | 29104128 | +| train/ | | +| approx_kl | 0.013930382 | +| clip_fraction | 0.326 | +| clip_range | 0.0677 | +| entropy_loss | -6.49 | +| explained_variance | -0.0244 | +| learning_rate | 4.31e-05 | +| loss | -0.0283 | +| n_updates | 72660 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000266 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.287 | +| time/ | | +| fps | 1406 | +| iterations | 14212 | +| time_elapsed | 20692 | +| total_timesteps | 29106176 | +| train/ | | +| approx_kl | 0.014568934 | +| clip_fraction | 0.37 | +| clip_range | 0.0677 | +| entropy_loss | -6.43 | +| explained_variance | 0.192 | +| learning_rate | 4.31e-05 | +| loss | -0.0309 | +| n_updates | 72664 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000158 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.294 | +| time/ | | +| fps | 1406 | +| iterations | 14213 | +| time_elapsed | 20694 | +| total_timesteps | 29108224 | +| train/ | | +| approx_kl | 0.0110673765 | +| clip_fraction | 0.333 | +| clip_range | 0.0677 | +| entropy_loss | -5.96 | +| explained_variance | 0.37 | +| learning_rate | 4.31e-05 | +| loss | -0.0191 | +| n_updates | 72668 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000283 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.304 | +| time/ | | +| fps | 1406 | +| iterations | 14214 | +| time_elapsed | 20695 | +| total_timesteps | 29110272 | +| train/ | | +| approx_kl | 0.011130519 | +| clip_fraction | 0.32 | +| clip_range | 0.0677 | +| entropy_loss | -5.67 | +| explained_variance | 0.468 | +| learning_rate | 4.31e-05 | +| loss | -0.0245 | +| n_updates | 72672 | +| policy_gradient_loss | -0.0143 | +| value_loss | 0.00036 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1406 | +| iterations | 14215 | +| time_elapsed | 20697 | +| total_timesteps | 29112320 | +| train/ | | +| approx_kl | 0.013707185 | +| clip_fraction | 0.331 | +| clip_range | 0.0677 | +| entropy_loss | -5.68 | +| explained_variance | 0.351 | +| learning_rate | 4.31e-05 | +| loss | -0.0278 | +| n_updates | 72676 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000416 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1406 | +| iterations | 14216 | +| time_elapsed | 20698 | +| total_timesteps | 29114368 | +| train/ | | +| approx_kl | 0.012961766 | +| clip_fraction | 0.354 | +| clip_range | 0.0677 | +| entropy_loss | -5.27 | +| explained_variance | 0.512 | +| learning_rate | 4.31e-05 | +| loss | -0.0269 | +| n_updates | 72680 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000189 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1406 | +| iterations | 14217 | +| time_elapsed | 20700 | +| total_timesteps | 29116416 | +| train/ | | +| approx_kl | 0.012842296 | +| clip_fraction | 0.382 | +| clip_range | 0.0677 | +| entropy_loss | -5.95 | +| explained_variance | 0.384 | +| learning_rate | 4.31e-05 | +| loss | -0.0392 | +| n_updates | 72684 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000116 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.306 | +| time/ | | +| fps | 1406 | +| iterations | 14218 | +| time_elapsed | 20701 | +| total_timesteps | 29118464 | +| train/ | | +| approx_kl | 0.012313943 | +| clip_fraction | 0.369 | +| clip_range | 0.0677 | +| entropy_loss | -6.94 | +| explained_variance | -0.0898 | +| learning_rate | 4.31e-05 | +| loss | -0.0306 | +| n_updates | 72688 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000136 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1406 | +| iterations | 14219 | +| time_elapsed | 20703 | +| total_timesteps | 29120512 | +| train/ | | +| approx_kl | 0.0126259755 | +| clip_fraction | 0.36 | +| clip_range | 0.0677 | +| entropy_loss | -6.66 | +| explained_variance | -0.033 | +| learning_rate | 4.31e-05 | +| loss | -0.0307 | +| n_updates | 72692 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000164 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1406 | +| iterations | 14220 | +| time_elapsed | 20705 | +| total_timesteps | 29122560 | +| train/ | | +| approx_kl | 0.013141185 | +| clip_fraction | 0.299 | +| clip_range | 0.0677 | +| entropy_loss | -5.95 | +| explained_variance | 0.409 | +| learning_rate | 4.31e-05 | +| loss | -0.0208 | +| n_updates | 72696 | +| policy_gradient_loss | -0.0147 | +| value_loss | 0.000321 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.302 | +| time/ | | +| fps | 1406 | +| iterations | 14221 | +| time_elapsed | 20706 | +| total_timesteps | 29124608 | +| train/ | | +| approx_kl | 0.014401597 | +| clip_fraction | 0.334 | +| clip_range | 0.0677 | +| entropy_loss | -5.99 | +| explained_variance | 0.324 | +| learning_rate | 4.31e-05 | +| loss | -0.0281 | +| n_updates | 72700 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000164 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1406 | +| iterations | 14222 | +| time_elapsed | 20708 | +| total_timesteps | 29126656 | +| train/ | | +| approx_kl | 0.01696229 | +| clip_fraction | 0.369 | +| clip_range | 0.0677 | +| entropy_loss | -5.48 | +| explained_variance | 0.77 | +| learning_rate | 4.31e-05 | +| loss | -0.0347 | +| n_updates | 72704 | +| policy_gradient_loss | -0.0226 | +| value_loss | 7.88e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1406 | +| iterations | 14223 | +| time_elapsed | 20709 | +| total_timesteps | 29128704 | +| train/ | | +| approx_kl | 0.015207648 | +| clip_fraction | 0.337 | +| clip_range | 0.0677 | +| entropy_loss | -5.8 | +| explained_variance | 0.304 | +| learning_rate | 4.31e-05 | +| loss | -0.0267 | +| n_updates | 72708 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000279 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1406 | +| iterations | 14224 | +| time_elapsed | 20711 | +| total_timesteps | 29130752 | +| train/ | | +| approx_kl | 0.017469198 | +| clip_fraction | 0.385 | +| clip_range | 0.0677 | +| entropy_loss | -6.17 | +| explained_variance | 0.0422 | +| learning_rate | 4.31e-05 | +| loss | -0.034 | +| n_updates | 72712 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000178 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1406 | +| iterations | 14225 | +| time_elapsed | 20712 | +| total_timesteps | 29132800 | +| train/ | | +| approx_kl | 0.01620923 | +| clip_fraction | 0.381 | +| clip_range | 0.0677 | +| entropy_loss | -6.37 | +| explained_variance | 0.399 | +| learning_rate | 4.31e-05 | +| loss | -0.0306 | +| n_updates | 72716 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000109 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1406 | +| iterations | 14226 | +| time_elapsed | 20714 | +| total_timesteps | 29134848 | +| train/ | | +| approx_kl | 0.014285244 | +| clip_fraction | 0.369 | +| clip_range | 0.0677 | +| entropy_loss | -6.38 | +| explained_variance | 0.339 | +| learning_rate | 4.31e-05 | +| loss | -0.0311 | +| n_updates | 72720 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000115 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1406 | +| iterations | 14227 | +| time_elapsed | 20715 | +| total_timesteps | 29136896 | +| train/ | | +| approx_kl | 0.015166143 | +| clip_fraction | 0.342 | +| clip_range | 0.0677 | +| entropy_loss | -5.75 | +| explained_variance | 0.517 | +| learning_rate | 4.31e-05 | +| loss | -0.0247 | +| n_updates | 72724 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000216 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1406 | +| iterations | 14228 | +| time_elapsed | 20717 | +| total_timesteps | 29138944 | +| train/ | | +| approx_kl | 0.015500569 | +| clip_fraction | 0.358 | +| clip_range | 0.0677 | +| entropy_loss | -5.93 | +| explained_variance | 0.303 | +| learning_rate | 4.31e-05 | +| loss | -0.035 | +| n_updates | 72728 | +| policy_gradient_loss | -0.022 | +| value_loss | 8.05e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1406 | +| iterations | 14229 | +| time_elapsed | 20718 | +| total_timesteps | 29140992 | +| train/ | | +| approx_kl | 0.015906047 | +| clip_fraction | 0.335 | +| clip_range | 0.0677 | +| entropy_loss | -6.24 | +| explained_variance | 0.518 | +| learning_rate | 4.31e-05 | +| loss | -0.0287 | +| n_updates | 72732 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000123 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1406 | +| iterations | 14230 | +| time_elapsed | 20720 | +| total_timesteps | 29143040 | +| train/ | | +| approx_kl | 0.014228437 | +| clip_fraction | 0.356 | +| clip_range | 0.0677 | +| entropy_loss | -6.25 | +| explained_variance | 0.48 | +| learning_rate | 4.31e-05 | +| loss | -0.0281 | +| n_updates | 72736 | +| policy_gradient_loss | -0.0194 | +| value_loss | 8.96e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1406 | +| iterations | 14231 | +| time_elapsed | 20721 | +| total_timesteps | 29145088 | +| train/ | | +| approx_kl | 0.013043251 | +| clip_fraction | 0.295 | +| clip_range | 0.0677 | +| entropy_loss | -6.16 | +| explained_variance | 0.517 | +| learning_rate | 4.31e-05 | +| loss | -0.0296 | +| n_updates | 72740 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000224 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1406 | +| iterations | 14232 | +| time_elapsed | 20723 | +| total_timesteps | 29147136 | +| train/ | | +| approx_kl | 0.01176941 | +| clip_fraction | 0.322 | +| clip_range | 0.0677 | +| entropy_loss | -5.65 | +| explained_variance | 0.516 | +| learning_rate | 4.31e-05 | +| loss | -0.0277 | +| n_updates | 72744 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000117 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1406 | +| iterations | 14233 | +| time_elapsed | 20724 | +| total_timesteps | 29149184 | +| train/ | | +| approx_kl | 0.012872314 | +| clip_fraction | 0.319 | +| clip_range | 0.0677 | +| entropy_loss | -6.25 | +| explained_variance | 0.204 | +| learning_rate | 4.31e-05 | +| loss | -0.0279 | +| n_updates | 72748 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.0003 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1406 | +| iterations | 14234 | +| time_elapsed | 20726 | +| total_timesteps | 29151232 | +| train/ | | +| approx_kl | 0.013067851 | +| clip_fraction | 0.361 | +| clip_range | 0.0677 | +| entropy_loss | -6.01 | +| explained_variance | 0.572 | +| learning_rate | 4.31e-05 | +| loss | -0.0342 | +| n_updates | 72752 | +| policy_gradient_loss | -0.0219 | +| value_loss | 0.000109 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1406 | +| iterations | 14235 | +| time_elapsed | 20727 | +| total_timesteps | 29153280 | +| train/ | | +| approx_kl | 0.012777555 | +| clip_fraction | 0.347 | +| clip_range | 0.0677 | +| entropy_loss | -6 | +| explained_variance | 0.391 | +| learning_rate | 4.31e-05 | +| loss | -0.0308 | +| n_updates | 72756 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000234 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1406 | +| iterations | 14236 | +| time_elapsed | 20729 | +| total_timesteps | 29155328 | +| train/ | | +| approx_kl | 0.012341339 | +| clip_fraction | 0.334 | +| clip_range | 0.0677 | +| entropy_loss | -6.4 | +| explained_variance | 0.312 | +| learning_rate | 4.31e-05 | +| loss | -0.0331 | +| n_updates | 72760 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000171 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1406 | +| iterations | 14237 | +| time_elapsed | 20730 | +| total_timesteps | 29157376 | +| train/ | | +| approx_kl | 0.011900039 | +| clip_fraction | 0.331 | +| clip_range | 0.0677 | +| entropy_loss | -6.32 | +| explained_variance | 0.263 | +| learning_rate | 4.31e-05 | +| loss | -0.0298 | +| n_updates | 72764 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000212 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1406 | +| iterations | 14238 | +| time_elapsed | 20732 | +| total_timesteps | 29159424 | +| train/ | | +| approx_kl | 0.016293958 | +| clip_fraction | 0.348 | +| clip_range | 0.0677 | +| entropy_loss | -5.82 | +| explained_variance | 0.575 | +| learning_rate | 4.31e-05 | +| loss | -0.0302 | +| n_updates | 72768 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000156 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1406 | +| iterations | 14239 | +| time_elapsed | 20733 | +| total_timesteps | 29161472 | +| train/ | | +| approx_kl | 0.011629851 | +| clip_fraction | 0.329 | +| clip_range | 0.0677 | +| entropy_loss | -6.27 | +| explained_variance | 0.247 | +| learning_rate | 4.31e-05 | +| loss | -0.0335 | +| n_updates | 72772 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000195 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1406 | +| iterations | 14240 | +| time_elapsed | 20735 | +| total_timesteps | 29163520 | +| train/ | | +| approx_kl | 0.010188976 | +| clip_fraction | 0.303 | +| clip_range | 0.0677 | +| entropy_loss | -5.65 | +| explained_variance | 0.499 | +| learning_rate | 4.31e-05 | +| loss | -0.0274 | +| n_updates | 72776 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000323 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1406 | +| iterations | 14241 | +| time_elapsed | 20737 | +| total_timesteps | 29165568 | +| train/ | | +| approx_kl | 0.01200141 | +| clip_fraction | 0.314 | +| clip_range | 0.0677 | +| entropy_loss | -5.53 | +| explained_variance | 0.338 | +| learning_rate | 4.31e-05 | +| loss | -0.0317 | +| n_updates | 72780 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000506 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1406 | +| iterations | 14242 | +| time_elapsed | 20738 | +| total_timesteps | 29167616 | +| train/ | | +| approx_kl | 0.019667555 | +| clip_fraction | 0.354 | +| clip_range | 0.0677 | +| entropy_loss | -5.05 | +| explained_variance | 0.534 | +| learning_rate | 4.31e-05 | +| loss | -0.0269 | +| n_updates | 72784 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000189 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1406 | +| iterations | 14243 | +| time_elapsed | 20740 | +| total_timesteps | 29169664 | +| train/ | | +| approx_kl | 0.012749877 | +| clip_fraction | 0.381 | +| clip_range | 0.0677 | +| entropy_loss | -6.08 | +| explained_variance | 0.127 | +| learning_rate | 4.31e-05 | +| loss | -0.0321 | +| n_updates | 72788 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000305 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1406 | +| iterations | 14244 | +| time_elapsed | 20741 | +| total_timesteps | 29171712 | +| train/ | | +| approx_kl | 0.014417835 | +| clip_fraction | 0.376 | +| clip_range | 0.0677 | +| entropy_loss | -6.55 | +| explained_variance | -0.229 | +| learning_rate | 4.31e-05 | +| loss | -0.0373 | +| n_updates | 72792 | +| policy_gradient_loss | -0.0236 | +| value_loss | 0.000109 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1406 | +| iterations | 14245 | +| time_elapsed | 20743 | +| total_timesteps | 29173760 | +| train/ | | +| approx_kl | 0.0136127155 | +| clip_fraction | 0.342 | +| clip_range | 0.0677 | +| entropy_loss | -6.43 | +| explained_variance | 0.291 | +| learning_rate | 4.31e-05 | +| loss | -0.0282 | +| n_updates | 72796 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000365 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1406 | +| iterations | 14246 | +| time_elapsed | 20744 | +| total_timesteps | 29175808 | +| train/ | | +| approx_kl | 0.012155954 | +| clip_fraction | 0.343 | +| clip_range | 0.0677 | +| entropy_loss | -6.56 | +| explained_variance | 0.19 | +| learning_rate | 4.31e-05 | +| loss | -0.0304 | +| n_updates | 72800 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000276 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1406 | +| iterations | 14247 | +| time_elapsed | 20746 | +| total_timesteps | 29177856 | +| train/ | | +| approx_kl | 0.012774054 | +| clip_fraction | 0.374 | +| clip_range | 0.0677 | +| entropy_loss | -6.46 | +| explained_variance | 0.288 | +| learning_rate | 4.31e-05 | +| loss | -0.0351 | +| n_updates | 72804 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000158 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1406 | +| iterations | 14248 | +| time_elapsed | 20747 | +| total_timesteps | 29179904 | +| train/ | | +| approx_kl | 0.012614565 | +| clip_fraction | 0.352 | +| clip_range | 0.0677 | +| entropy_loss | -6.54 | +| explained_variance | 0.32 | +| learning_rate | 4.31e-05 | +| loss | -0.036 | +| n_updates | 72808 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000112 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1406 | +| iterations | 14249 | +| time_elapsed | 20749 | +| total_timesteps | 29181952 | +| train/ | | +| approx_kl | 0.015039885 | +| clip_fraction | 0.324 | +| clip_range | 0.0677 | +| entropy_loss | -5.95 | +| explained_variance | 0.439 | +| learning_rate | 4.31e-05 | +| loss | -0.0228 | +| n_updates | 72812 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000204 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1406 | +| iterations | 14250 | +| time_elapsed | 20751 | +| total_timesteps | 29184000 | +| train/ | | +| approx_kl | 0.014922595 | +| clip_fraction | 0.391 | +| clip_range | 0.0677 | +| entropy_loss | -6.42 | +| explained_variance | 0.301 | +| learning_rate | 4.31e-05 | +| loss | -0.034 | +| n_updates | 72816 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000131 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1406 | +| iterations | 14251 | +| time_elapsed | 20752 | +| total_timesteps | 29186048 | +| train/ | | +| approx_kl | 0.012477432 | +| clip_fraction | 0.353 | +| clip_range | 0.0677 | +| entropy_loss | -6.58 | +| explained_variance | 0.355 | +| learning_rate | 4.31e-05 | +| loss | -0.0231 | +| n_updates | 72820 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000213 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1406 | +| iterations | 14252 | +| time_elapsed | 20754 | +| total_timesteps | 29188096 | +| train/ | | +| approx_kl | 0.014394659 | +| clip_fraction | 0.338 | +| clip_range | 0.0677 | +| entropy_loss | -5.57 | +| explained_variance | 0.516 | +| learning_rate | 4.31e-05 | +| loss | -0.0339 | +| n_updates | 72824 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.00014 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1406 | +| iterations | 14253 | +| time_elapsed | 20755 | +| total_timesteps | 29190144 | +| train/ | | +| approx_kl | 0.014154799 | +| clip_fraction | 0.367 | +| clip_range | 0.0677 | +| entropy_loss | -5.37 | +| explained_variance | 0.831 | +| learning_rate | 4.31e-05 | +| loss | -0.0365 | +| n_updates | 72828 | +| policy_gradient_loss | -0.0232 | +| value_loss | 4.58e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1406 | +| iterations | 14254 | +| time_elapsed | 20757 | +| total_timesteps | 29192192 | +| train/ | | +| approx_kl | 0.0127574615 | +| clip_fraction | 0.355 | +| clip_range | 0.0677 | +| entropy_loss | -5.92 | +| explained_variance | 0.576 | +| learning_rate | 4.31e-05 | +| loss | -0.0268 | +| n_updates | 72832 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000134 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1406 | +| iterations | 14255 | +| time_elapsed | 20758 | +| total_timesteps | 29194240 | +| train/ | | +| approx_kl | 0.014093649 | +| clip_fraction | 0.337 | +| clip_range | 0.0677 | +| entropy_loss | -6.31 | +| explained_variance | 0.338 | +| learning_rate | 4.31e-05 | +| loss | -0.0333 | +| n_updates | 72836 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000186 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1406 | +| iterations | 14256 | +| time_elapsed | 20760 | +| total_timesteps | 29196288 | +| train/ | | +| approx_kl | 0.0145456325 | +| clip_fraction | 0.354 | +| clip_range | 0.0677 | +| entropy_loss | -6.15 | +| explained_variance | 0.233 | +| learning_rate | 4.31e-05 | +| loss | -0.0299 | +| n_updates | 72840 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000191 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1406 | +| iterations | 14257 | +| time_elapsed | 20761 | +| total_timesteps | 29198336 | +| train/ | | +| approx_kl | 0.015764795 | +| clip_fraction | 0.381 | +| clip_range | 0.0677 | +| entropy_loss | -6.6 | +| explained_variance | -0.0344 | +| learning_rate | 4.31e-05 | +| loss | -0.0278 | +| n_updates | 72844 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.00017 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1406 | +| iterations | 14258 | +| time_elapsed | 20763 | +| total_timesteps | 29200384 | +| train/ | | +| approx_kl | 0.013261899 | +| clip_fraction | 0.377 | +| clip_range | 0.0677 | +| entropy_loss | -6.43 | +| explained_variance | 0.233 | +| learning_rate | 4.31e-05 | +| loss | -0.0335 | +| n_updates | 72848 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000128 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1406 | +| iterations | 14259 | +| time_elapsed | 20764 | +| total_timesteps | 29202432 | +| train/ | | +| approx_kl | 0.012134969 | +| clip_fraction | 0.343 | +| clip_range | 0.0677 | +| entropy_loss | -6.12 | +| explained_variance | 0.355 | +| learning_rate | 4.31e-05 | +| loss | -0.0274 | +| n_updates | 72852 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000218 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1406 | +| iterations | 14260 | +| time_elapsed | 20766 | +| total_timesteps | 29204480 | +| train/ | | +| approx_kl | 0.011009805 | +| clip_fraction | 0.319 | +| clip_range | 0.0677 | +| entropy_loss | -6.16 | +| explained_variance | 0.212 | +| learning_rate | 4.31e-05 | +| loss | -0.0238 | +| n_updates | 72856 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000299 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1406 | +| iterations | 14261 | +| time_elapsed | 20767 | +| total_timesteps | 29206528 | +| train/ | | +| approx_kl | 0.0125490185 | +| clip_fraction | 0.332 | +| clip_range | 0.0677 | +| entropy_loss | -6.4 | +| explained_variance | -0.00639 | +| learning_rate | 4.31e-05 | +| loss | -0.0269 | +| n_updates | 72860 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000252 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1406 | +| iterations | 14262 | +| time_elapsed | 20769 | +| total_timesteps | 29208576 | +| train/ | | +| approx_kl | 0.012179484 | +| clip_fraction | 0.349 | +| clip_range | 0.0677 | +| entropy_loss | -6.13 | +| explained_variance | 0.195 | +| learning_rate | 4.31e-05 | +| loss | -0.0307 | +| n_updates | 72864 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000236 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1406 | +| iterations | 14263 | +| time_elapsed | 20771 | +| total_timesteps | 29210624 | +| train/ | | +| approx_kl | 0.018631663 | +| clip_fraction | 0.36 | +| clip_range | 0.0677 | +| entropy_loss | -6.22 | +| explained_variance | 0.367 | +| learning_rate | 4.31e-05 | +| loss | -0.0277 | +| n_updates | 72868 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000156 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1406 | +| iterations | 14264 | +| time_elapsed | 20772 | +| total_timesteps | 29212672 | +| train/ | | +| approx_kl | 0.0128713 | +| clip_fraction | 0.361 | +| clip_range | 0.0677 | +| entropy_loss | -6.52 | +| explained_variance | -0.164 | +| learning_rate | 4.31e-05 | +| loss | -0.0295 | +| n_updates | 72872 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000187 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1406 | +| iterations | 14265 | +| time_elapsed | 20774 | +| total_timesteps | 29214720 | +| train/ | | +| approx_kl | 0.015375873 | +| clip_fraction | 0.368 | +| clip_range | 0.0677 | +| entropy_loss | -6.37 | +| explained_variance | 0.237 | +| learning_rate | 4.31e-05 | +| loss | -0.0309 | +| n_updates | 72876 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000221 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1406 | +| iterations | 14266 | +| time_elapsed | 20775 | +| total_timesteps | 29216768 | +| train/ | | +| approx_kl | 0.01443582 | +| clip_fraction | 0.373 | +| clip_range | 0.0677 | +| entropy_loss | -6.51 | +| explained_variance | -0.169 | +| learning_rate | 4.31e-05 | +| loss | -0.0376 | +| n_updates | 72880 | +| policy_gradient_loss | -0.0219 | +| value_loss | 8.48e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1406 | +| iterations | 14267 | +| time_elapsed | 20777 | +| total_timesteps | 29218816 | +| train/ | | +| approx_kl | 0.011263141 | +| clip_fraction | 0.334 | +| clip_range | 0.0677 | +| entropy_loss | -5.91 | +| explained_variance | 0.385 | +| learning_rate | 4.31e-05 | +| loss | -0.0279 | +| n_updates | 72884 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000263 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.384 | +| time/ | | +| fps | 1406 | +| iterations | 14268 | +| time_elapsed | 20778 | +| total_timesteps | 29220864 | +| train/ | | +| approx_kl | 0.011848129 | +| clip_fraction | 0.305 | +| clip_range | 0.0677 | +| entropy_loss | -5.77 | +| explained_variance | 0.301 | +| learning_rate | 4.31e-05 | +| loss | -0.0299 | +| n_updates | 72888 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000334 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.387 | +| time/ | | +| fps | 1406 | +| iterations | 14269 | +| time_elapsed | 20780 | +| total_timesteps | 29222912 | +| train/ | | +| approx_kl | 0.012952707 | +| clip_fraction | 0.312 | +| clip_range | 0.0677 | +| entropy_loss | -5.99 | +| explained_variance | 0.211 | +| learning_rate | 4.31e-05 | +| loss | -0.0233 | +| n_updates | 72892 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000319 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.384 | +| time/ | | +| fps | 1406 | +| iterations | 14270 | +| time_elapsed | 20781 | +| total_timesteps | 29224960 | +| train/ | | +| approx_kl | 0.0133823985 | +| clip_fraction | 0.362 | +| clip_range | 0.0677 | +| entropy_loss | -6.03 | +| explained_variance | 0.414 | +| learning_rate | 4.31e-05 | +| loss | -0.0329 | +| n_updates | 72896 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000173 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.384 | +| time/ | | +| fps | 1406 | +| iterations | 14271 | +| time_elapsed | 20783 | +| total_timesteps | 29227008 | +| train/ | | +| approx_kl | 0.015383944 | +| clip_fraction | 0.352 | +| clip_range | 0.0677 | +| entropy_loss | -5.91 | +| explained_variance | 0.61 | +| learning_rate | 4.31e-05 | +| loss | -0.0313 | +| n_updates | 72900 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000103 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1406 | +| iterations | 14272 | +| time_elapsed | 20785 | +| total_timesteps | 29229056 | +| train/ | | +| approx_kl | 0.016694006 | +| clip_fraction | 0.365 | +| clip_range | 0.0677 | +| entropy_loss | -6.56 | +| explained_variance | -0.0525 | +| learning_rate | 4.31e-05 | +| loss | -0.0326 | +| n_updates | 72904 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.00017 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1406 | +| iterations | 14273 | +| time_elapsed | 20786 | +| total_timesteps | 29231104 | +| train/ | | +| approx_kl | 0.015339842 | +| clip_fraction | 0.388 | +| clip_range | 0.0677 | +| entropy_loss | -6.69 | +| explained_variance | 0.337 | +| learning_rate | 4.31e-05 | +| loss | -0.0358 | +| n_updates | 72908 | +| policy_gradient_loss | -0.0222 | +| value_loss | 6.86e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1406 | +| iterations | 14274 | +| time_elapsed | 20788 | +| total_timesteps | 29233152 | +| train/ | | +| approx_kl | 0.01668486 | +| clip_fraction | 0.369 | +| clip_range | 0.0677 | +| entropy_loss | -6.28 | +| explained_variance | 0.425 | +| learning_rate | 4.31e-05 | +| loss | -0.0284 | +| n_updates | 72912 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000145 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1406 | +| iterations | 14275 | +| time_elapsed | 20789 | +| total_timesteps | 29235200 | +| train/ | | +| approx_kl | 0.017795086 | +| clip_fraction | 0.361 | +| clip_range | 0.0677 | +| entropy_loss | -5.8 | +| explained_variance | 0.399 | +| learning_rate | 4.31e-05 | +| loss | -0.0233 | +| n_updates | 72916 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.00021 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1406 | +| iterations | 14276 | +| time_elapsed | 20791 | +| total_timesteps | 29237248 | +| train/ | | +| approx_kl | 0.017542128 | +| clip_fraction | 0.368 | +| clip_range | 0.0677 | +| entropy_loss | -5.85 | +| explained_variance | 0.289 | +| learning_rate | 4.31e-05 | +| loss | -0.0283 | +| n_updates | 72920 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000132 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1406 | +| iterations | 14277 | +| time_elapsed | 20792 | +| total_timesteps | 29239296 | +| train/ | | +| approx_kl | 0.015337049 | +| clip_fraction | 0.381 | +| clip_range | 0.0677 | +| entropy_loss | -5.88 | +| explained_variance | 0.283 | +| learning_rate | 4.31e-05 | +| loss | -0.0329 | +| n_updates | 72924 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000177 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1406 | +| iterations | 14278 | +| time_elapsed | 20794 | +| total_timesteps | 29241344 | +| train/ | | +| approx_kl | 0.016381552 | +| clip_fraction | 0.328 | +| clip_range | 0.0677 | +| entropy_loss | -5.69 | +| explained_variance | 0.445 | +| learning_rate | 4.31e-05 | +| loss | -0.0195 | +| n_updates | 72928 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000224 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1406 | +| iterations | 14279 | +| time_elapsed | 20795 | +| total_timesteps | 29243392 | +| train/ | | +| approx_kl | 0.0153140705 | +| clip_fraction | 0.36 | +| clip_range | 0.0677 | +| entropy_loss | -5.32 | +| explained_variance | 0.761 | +| learning_rate | 4.31e-05 | +| loss | -0.0316 | +| n_updates | 72932 | +| policy_gradient_loss | -0.0202 | +| value_loss | 9.18e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1406 | +| iterations | 14280 | +| time_elapsed | 20797 | +| total_timesteps | 29245440 | +| train/ | | +| approx_kl | 0.014955683 | +| clip_fraction | 0.368 | +| clip_range | 0.0677 | +| entropy_loss | -6.33 | +| explained_variance | -0.0689 | +| learning_rate | 4.31e-05 | +| loss | -0.0311 | +| n_updates | 72936 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000137 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1406 | +| iterations | 14281 | +| time_elapsed | 20798 | +| total_timesteps | 29247488 | +| train/ | | +| approx_kl | 0.012387449 | +| clip_fraction | 0.332 | +| clip_range | 0.0677 | +| entropy_loss | -6.26 | +| explained_variance | 0.389 | +| learning_rate | 4.31e-05 | +| loss | -0.0322 | +| n_updates | 72940 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000155 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1406 | +| iterations | 14282 | +| time_elapsed | 20800 | +| total_timesteps | 29249536 | +| train/ | | +| approx_kl | 0.016547956 | +| clip_fraction | 0.365 | +| clip_range | 0.0677 | +| entropy_loss | -6.66 | +| explained_variance | -0.0915 | +| learning_rate | 4.31e-05 | +| loss | -0.0344 | +| n_updates | 72944 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000166 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1406 | +| iterations | 14283 | +| time_elapsed | 20801 | +| total_timesteps | 29251584 | +| train/ | | +| approx_kl | 0.01359123 | +| clip_fraction | 0.339 | +| clip_range | 0.0677 | +| entropy_loss | -6.23 | +| explained_variance | 0.34 | +| learning_rate | 4.31e-05 | +| loss | -0.0254 | +| n_updates | 72948 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.000375 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1406 | +| iterations | 14284 | +| time_elapsed | 20803 | +| total_timesteps | 29253632 | +| train/ | | +| approx_kl | 0.016637418 | +| clip_fraction | 0.374 | +| clip_range | 0.0677 | +| entropy_loss | -6.35 | +| explained_variance | -0.278 | +| learning_rate | 4.31e-05 | +| loss | -0.0313 | +| n_updates | 72952 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000201 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1406 | +| iterations | 14285 | +| time_elapsed | 20804 | +| total_timesteps | 29255680 | +| train/ | | +| approx_kl | 0.013609916 | +| clip_fraction | 0.363 | +| clip_range | 0.0677 | +| entropy_loss | -6.75 | +| explained_variance | 0.332 | +| learning_rate | 4.31e-05 | +| loss | -0.0302 | +| n_updates | 72956 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000132 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1406 | +| iterations | 14286 | +| time_elapsed | 20806 | +| total_timesteps | 29257728 | +| train/ | | +| approx_kl | 0.014681332 | +| clip_fraction | 0.331 | +| clip_range | 0.0677 | +| entropy_loss | -5.95 | +| explained_variance | 0.486 | +| learning_rate | 4.31e-05 | +| loss | -0.0289 | +| n_updates | 72960 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000265 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1406 | +| iterations | 14287 | +| time_elapsed | 20807 | +| total_timesteps | 29259776 | +| train/ | | +| approx_kl | 0.017801883 | +| clip_fraction | 0.357 | +| clip_range | 0.0677 | +| entropy_loss | -6.04 | +| explained_variance | 0.44 | +| learning_rate | 4.31e-05 | +| loss | -0.0322 | +| n_updates | 72964 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000129 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1406 | +| iterations | 14288 | +| time_elapsed | 20809 | +| total_timesteps | 29261824 | +| train/ | | +| approx_kl | 0.012800912 | +| clip_fraction | 0.35 | +| clip_range | 0.0677 | +| entropy_loss | -6.37 | +| explained_variance | 0.28 | +| learning_rate | 4.31e-05 | +| loss | -0.0275 | +| n_updates | 72968 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000358 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1406 | +| iterations | 14289 | +| time_elapsed | 20810 | +| total_timesteps | 29263872 | +| train/ | | +| approx_kl | 0.013916567 | +| clip_fraction | 0.35 | +| clip_range | 0.0677 | +| entropy_loss | -5.94 | +| explained_variance | 0.434 | +| learning_rate | 4.31e-05 | +| loss | -0.0282 | +| n_updates | 72972 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000207 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1406 | +| iterations | 14290 | +| time_elapsed | 20812 | +| total_timesteps | 29265920 | +| train/ | | +| approx_kl | 0.012527417 | +| clip_fraction | 0.356 | +| clip_range | 0.0677 | +| entropy_loss | -6.62 | +| explained_variance | 0.478 | +| learning_rate | 4.3e-05 | +| loss | -0.0377 | +| n_updates | 72976 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000154 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1406 | +| iterations | 14291 | +| time_elapsed | 20814 | +| total_timesteps | 29267968 | +| train/ | | +| approx_kl | 0.014331363 | +| clip_fraction | 0.336 | +| clip_range | 0.0677 | +| entropy_loss | -6.15 | +| explained_variance | 0.33 | +| learning_rate | 4.3e-05 | +| loss | -0.0365 | +| n_updates | 72980 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.00032 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1406 | +| iterations | 14292 | +| time_elapsed | 20815 | +| total_timesteps | 29270016 | +| train/ | | +| approx_kl | 0.017902372 | +| clip_fraction | 0.332 | +| clip_range | 0.0677 | +| entropy_loss | -5.68 | +| explained_variance | 0.321 | +| learning_rate | 4.3e-05 | +| loss | -0.0259 | +| n_updates | 72984 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000346 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1406 | +| iterations | 14293 | +| time_elapsed | 20817 | +| total_timesteps | 29272064 | +| train/ | | +| approx_kl | 0.014370544 | +| clip_fraction | 0.366 | +| clip_range | 0.0677 | +| entropy_loss | -6.24 | +| explained_variance | 0.223 | +| learning_rate | 4.3e-05 | +| loss | -0.0299 | +| n_updates | 72988 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000284 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1406 | +| iterations | 14294 | +| time_elapsed | 20818 | +| total_timesteps | 29274112 | +| train/ | | +| approx_kl | 0.014601093 | +| clip_fraction | 0.331 | +| clip_range | 0.0677 | +| entropy_loss | -6.16 | +| explained_variance | 0.53 | +| learning_rate | 4.3e-05 | +| loss | -0.0321 | +| n_updates | 72992 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000174 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1406 | +| iterations | 14295 | +| time_elapsed | 20820 | +| total_timesteps | 29276160 | +| train/ | | +| approx_kl | 0.011893095 | +| clip_fraction | 0.338 | +| clip_range | 0.0677 | +| entropy_loss | -6.28 | +| explained_variance | 0.00275 | +| learning_rate | 4.3e-05 | +| loss | -0.0264 | +| n_updates | 72996 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000315 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.384 | +| time/ | | +| fps | 1406 | +| iterations | 14296 | +| time_elapsed | 20821 | +| total_timesteps | 29278208 | +| train/ | | +| approx_kl | 0.013342022 | +| clip_fraction | 0.373 | +| clip_range | 0.0677 | +| entropy_loss | -6.15 | +| explained_variance | 0.498 | +| learning_rate | 4.3e-05 | +| loss | -0.0343 | +| n_updates | 73000 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000126 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1406 | +| iterations | 14297 | +| time_elapsed | 20823 | +| total_timesteps | 29280256 | +| train/ | | +| approx_kl | 0.0147750275 | +| clip_fraction | 0.35 | +| clip_range | 0.0677 | +| entropy_loss | -7.02 | +| explained_variance | -0.128 | +| learning_rate | 4.3e-05 | +| loss | -0.0381 | +| n_updates | 73004 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000116 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1406 | +| iterations | 14298 | +| time_elapsed | 20824 | +| total_timesteps | 29282304 | +| train/ | | +| approx_kl | 0.01653294 | +| clip_fraction | 0.353 | +| clip_range | 0.0677 | +| entropy_loss | -6.28 | +| explained_variance | 0.477 | +| learning_rate | 4.3e-05 | +| loss | -0.0277 | +| n_updates | 73008 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000186 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1406 | +| iterations | 14299 | +| time_elapsed | 20826 | +| total_timesteps | 29284352 | +| train/ | | +| approx_kl | 0.01729675 | +| clip_fraction | 0.349 | +| clip_range | 0.0677 | +| entropy_loss | -6.13 | +| explained_variance | 0.604 | +| learning_rate | 4.3e-05 | +| loss | -0.0335 | +| n_updates | 73012 | +| policy_gradient_loss | -0.0209 | +| value_loss | 6.37e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1406 | +| iterations | 14300 | +| time_elapsed | 20827 | +| total_timesteps | 29286400 | +| train/ | | +| approx_kl | 0.015522197 | +| clip_fraction | 0.363 | +| clip_range | 0.0677 | +| entropy_loss | -6.66 | +| explained_variance | 0.386 | +| learning_rate | 4.3e-05 | +| loss | -0.0256 | +| n_updates | 73016 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000116 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1406 | +| iterations | 14301 | +| time_elapsed | 20829 | +| total_timesteps | 29288448 | +| train/ | | +| approx_kl | 0.013559034 | +| clip_fraction | 0.36 | +| clip_range | 0.0677 | +| entropy_loss | -5.66 | +| explained_variance | 0.497 | +| learning_rate | 4.3e-05 | +| loss | -0.0299 | +| n_updates | 73020 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000239 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1406 | +| iterations | 14302 | +| time_elapsed | 20830 | +| total_timesteps | 29290496 | +| train/ | | +| approx_kl | 0.017291985 | +| clip_fraction | 0.338 | +| clip_range | 0.0677 | +| entropy_loss | -6.25 | +| explained_variance | 0.635 | +| learning_rate | 4.3e-05 | +| loss | -0.0385 | +| n_updates | 73024 | +| policy_gradient_loss | -0.0203 | +| value_loss | 6.6e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1406 | +| iterations | 14303 | +| time_elapsed | 20832 | +| total_timesteps | 29292544 | +| train/ | | +| approx_kl | 0.013861444 | +| clip_fraction | 0.343 | +| clip_range | 0.0677 | +| entropy_loss | -6.07 | +| explained_variance | 0.456 | +| learning_rate | 4.3e-05 | +| loss | -0.0285 | +| n_updates | 73028 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000157 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1406 | +| iterations | 14304 | +| time_elapsed | 20834 | +| total_timesteps | 29294592 | +| train/ | | +| approx_kl | 0.01288045 | +| clip_fraction | 0.361 | +| clip_range | 0.0677 | +| entropy_loss | -6.33 | +| explained_variance | 0.318 | +| learning_rate | 4.3e-05 | +| loss | -0.0259 | +| n_updates | 73032 | +| policy_gradient_loss | -0.0189 | +| value_loss | 9.27e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1406 | +| iterations | 14305 | +| time_elapsed | 20835 | +| total_timesteps | 29296640 | +| train/ | | +| approx_kl | 0.013930089 | +| clip_fraction | 0.355 | +| clip_range | 0.0677 | +| entropy_loss | -6.65 | +| explained_variance | -0.0744 | +| learning_rate | 4.3e-05 | +| loss | -0.0314 | +| n_updates | 73036 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000203 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1406 | +| iterations | 14306 | +| time_elapsed | 20837 | +| total_timesteps | 29298688 | +| train/ | | +| approx_kl | 0.015195527 | +| clip_fraction | 0.354 | +| clip_range | 0.0677 | +| entropy_loss | -6.4 | +| explained_variance | 0.326 | +| learning_rate | 4.3e-05 | +| loss | -0.03 | +| n_updates | 73040 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000145 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1406 | +| iterations | 14307 | +| time_elapsed | 20838 | +| total_timesteps | 29300736 | +| train/ | | +| approx_kl | 0.015384617 | +| clip_fraction | 0.353 | +| clip_range | 0.0677 | +| entropy_loss | -6.39 | +| explained_variance | 0.36 | +| learning_rate | 4.3e-05 | +| loss | -0.0389 | +| n_updates | 73044 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000111 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1406 | +| iterations | 14308 | +| time_elapsed | 20840 | +| total_timesteps | 29302784 | +| train/ | | +| approx_kl | 0.01358326 | +| clip_fraction | 0.339 | +| clip_range | 0.0677 | +| entropy_loss | -5.61 | +| explained_variance | 0.688 | +| learning_rate | 4.3e-05 | +| loss | -0.0293 | +| n_updates | 73048 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000182 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1406 | +| iterations | 14309 | +| time_elapsed | 20841 | +| total_timesteps | 29304832 | +| train/ | | +| approx_kl | 0.011004966 | +| clip_fraction | 0.313 | +| clip_range | 0.0677 | +| entropy_loss | -5.99 | +| explained_variance | 0.0593 | +| learning_rate | 4.3e-05 | +| loss | -0.022 | +| n_updates | 73052 | +| policy_gradient_loss | -0.0145 | +| value_loss | 0.000256 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1406 | +| iterations | 14310 | +| time_elapsed | 20843 | +| total_timesteps | 29306880 | +| train/ | | +| approx_kl | 0.0134798065 | +| clip_fraction | 0.319 | +| clip_range | 0.0677 | +| entropy_loss | -6.18 | +| explained_variance | 0.551 | +| learning_rate | 4.3e-05 | +| loss | -0.0289 | +| n_updates | 73056 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000162 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1406 | +| iterations | 14311 | +| time_elapsed | 20844 | +| total_timesteps | 29308928 | +| train/ | | +| approx_kl | 0.01302217 | +| clip_fraction | 0.331 | +| clip_range | 0.0677 | +| entropy_loss | -6.26 | +| explained_variance | 0.0807 | +| learning_rate | 4.3e-05 | +| loss | -0.0254 | +| n_updates | 73060 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.00034 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1406 | +| iterations | 14312 | +| time_elapsed | 20846 | +| total_timesteps | 29310976 | +| train/ | | +| approx_kl | 0.013721278 | +| clip_fraction | 0.365 | +| clip_range | 0.0677 | +| entropy_loss | -6.21 | +| explained_variance | 0.489 | +| learning_rate | 4.3e-05 | +| loss | -0.0359 | +| n_updates | 73064 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000111 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1406 | +| iterations | 14313 | +| time_elapsed | 20847 | +| total_timesteps | 29313024 | +| train/ | | +| approx_kl | 0.013517314 | +| clip_fraction | 0.354 | +| clip_range | 0.0677 | +| entropy_loss | -6.52 | +| explained_variance | 0.225 | +| learning_rate | 4.3e-05 | +| loss | -0.0201 | +| n_updates | 73068 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000317 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1406 | +| iterations | 14314 | +| time_elapsed | 20849 | +| total_timesteps | 29315072 | +| train/ | | +| approx_kl | 0.01525772 | +| clip_fraction | 0.353 | +| clip_range | 0.0677 | +| entropy_loss | -6.59 | +| explained_variance | -0.176 | +| learning_rate | 4.3e-05 | +| loss | -0.0304 | +| n_updates | 73072 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000148 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1406 | +| iterations | 14315 | +| time_elapsed | 20850 | +| total_timesteps | 29317120 | +| train/ | | +| approx_kl | 0.015176922 | +| clip_fraction | 0.378 | +| clip_range | 0.0677 | +| entropy_loss | -6.41 | +| explained_variance | 0.426 | +| learning_rate | 4.3e-05 | +| loss | -0.0283 | +| n_updates | 73076 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000163 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1406 | +| iterations | 14316 | +| time_elapsed | 20852 | +| total_timesteps | 29319168 | +| train/ | | +| approx_kl | 0.017588751 | +| clip_fraction | 0.366 | +| clip_range | 0.0677 | +| entropy_loss | -5.89 | +| explained_variance | 0.619 | +| learning_rate | 4.3e-05 | +| loss | -0.0326 | +| n_updates | 73080 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000142 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1406 | +| iterations | 14317 | +| time_elapsed | 20854 | +| total_timesteps | 29321216 | +| train/ | | +| approx_kl | 0.0130782835 | +| clip_fraction | 0.356 | +| clip_range | 0.0677 | +| entropy_loss | -6.02 | +| explained_variance | 0.727 | +| learning_rate | 4.3e-05 | +| loss | -0.0262 | +| n_updates | 73084 | +| policy_gradient_loss | -0.0205 | +| value_loss | 6.03e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1406 | +| iterations | 14318 | +| time_elapsed | 20855 | +| total_timesteps | 29323264 | +| train/ | | +| approx_kl | 0.012832034 | +| clip_fraction | 0.325 | +| clip_range | 0.0677 | +| entropy_loss | -6.12 | +| explained_variance | 0.576 | +| learning_rate | 4.3e-05 | +| loss | -0.0329 | +| n_updates | 73088 | +| policy_gradient_loss | -0.0178 | +| value_loss | 9.08e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1406 | +| iterations | 14319 | +| time_elapsed | 20857 | +| total_timesteps | 29325312 | +| train/ | | +| approx_kl | 0.011699853 | +| clip_fraction | 0.324 | +| clip_range | 0.0677 | +| entropy_loss | -6.53 | +| explained_variance | 0.225 | +| learning_rate | 4.3e-05 | +| loss | -0.0254 | +| n_updates | 73092 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000207 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1406 | +| iterations | 14320 | +| time_elapsed | 20858 | +| total_timesteps | 29327360 | +| train/ | | +| approx_kl | 0.012661808 | +| clip_fraction | 0.339 | +| clip_range | 0.0677 | +| entropy_loss | -6.5 | +| explained_variance | 0.303 | +| learning_rate | 4.3e-05 | +| loss | -0.0254 | +| n_updates | 73096 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000294 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1406 | +| iterations | 14321 | +| time_elapsed | 20860 | +| total_timesteps | 29329408 | +| train/ | | +| approx_kl | 0.009672315 | +| clip_fraction | 0.315 | +| clip_range | 0.0677 | +| entropy_loss | -6.73 | +| explained_variance | 0.387 | +| learning_rate | 4.3e-05 | +| loss | -0.0283 | +| n_updates | 73100 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000127 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1406 | +| iterations | 14322 | +| time_elapsed | 20861 | +| total_timesteps | 29331456 | +| train/ | | +| approx_kl | 0.0075958027 | +| clip_fraction | 0.305 | +| clip_range | 0.0677 | +| entropy_loss | -6.56 | +| explained_variance | 0.262 | +| learning_rate | 4.3e-05 | +| loss | -0.0201 | +| n_updates | 73104 | +| policy_gradient_loss | -0.0128 | +| value_loss | 0.000397 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1405 | +| iterations | 14323 | +| time_elapsed | 20863 | +| total_timesteps | 29333504 | +| train/ | | +| approx_kl | 0.011475919 | +| clip_fraction | 0.306 | +| clip_range | 0.0677 | +| entropy_loss | -6.41 | +| explained_variance | 0.414 | +| learning_rate | 4.3e-05 | +| loss | -0.0259 | +| n_updates | 73108 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000267 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1405 | +| iterations | 14324 | +| time_elapsed | 20864 | +| total_timesteps | 29335552 | +| train/ | | +| approx_kl | 0.01098381 | +| clip_fraction | 0.342 | +| clip_range | 0.0677 | +| entropy_loss | -6.5 | +| explained_variance | 0.291 | +| learning_rate | 4.3e-05 | +| loss | -0.0322 | +| n_updates | 73112 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.00015 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1405 | +| iterations | 14325 | +| time_elapsed | 20866 | +| total_timesteps | 29337600 | +| train/ | | +| approx_kl | 0.010815488 | +| clip_fraction | 0.334 | +| clip_range | 0.0677 | +| entropy_loss | -6.87 | +| explained_variance | -0.0694 | +| learning_rate | 4.3e-05 | +| loss | -0.0321 | +| n_updates | 73116 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000133 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1405 | +| iterations | 14326 | +| time_elapsed | 20867 | +| total_timesteps | 29339648 | +| train/ | | +| approx_kl | 0.015297563 | +| clip_fraction | 0.318 | +| clip_range | 0.0677 | +| entropy_loss | -5.67 | +| explained_variance | 0.507 | +| learning_rate | 4.3e-05 | +| loss | -0.0231 | +| n_updates | 73120 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000281 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1405 | +| iterations | 14327 | +| time_elapsed | 20869 | +| total_timesteps | 29341696 | +| train/ | | +| approx_kl | 0.014554763 | +| clip_fraction | 0.353 | +| clip_range | 0.0677 | +| entropy_loss | -5.55 | +| explained_variance | 0.392 | +| learning_rate | 4.3e-05 | +| loss | -0.0329 | +| n_updates | 73124 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000102 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1405 | +| iterations | 14328 | +| time_elapsed | 20870 | +| total_timesteps | 29343744 | +| train/ | | +| approx_kl | 0.018301051 | +| clip_fraction | 0.366 | +| clip_range | 0.0677 | +| entropy_loss | -6.65 | +| explained_variance | -0.24 | +| learning_rate | 4.3e-05 | +| loss | -0.0344 | +| n_updates | 73128 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.00014 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1405 | +| iterations | 14329 | +| time_elapsed | 20872 | +| total_timesteps | 29345792 | +| train/ | | +| approx_kl | 0.0142257605 | +| clip_fraction | 0.307 | +| clip_range | 0.0677 | +| entropy_loss | -6.5 | +| explained_variance | 0.289 | +| learning_rate | 4.3e-05 | +| loss | -0.0265 | +| n_updates | 73132 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000353 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1405 | +| iterations | 14330 | +| time_elapsed | 20873 | +| total_timesteps | 29347840 | +| train/ | | +| approx_kl | 0.014402283 | +| clip_fraction | 0.37 | +| clip_range | 0.0677 | +| entropy_loss | -6.08 | +| explained_variance | 0.585 | +| learning_rate | 4.3e-05 | +| loss | -0.0339 | +| n_updates | 73136 | +| policy_gradient_loss | -0.0206 | +| value_loss | 9.96e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1405 | +| iterations | 14331 | +| time_elapsed | 20875 | +| total_timesteps | 29349888 | +| train/ | | +| approx_kl | 0.015609065 | +| clip_fraction | 0.323 | +| clip_range | 0.0677 | +| entropy_loss | -6.29 | +| explained_variance | 0.476 | +| learning_rate | 4.3e-05 | +| loss | -0.0301 | +| n_updates | 73140 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000205 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1405 | +| iterations | 14332 | +| time_elapsed | 20876 | +| total_timesteps | 29351936 | +| train/ | | +| approx_kl | 0.013304624 | +| clip_fraction | 0.349 | +| clip_range | 0.0677 | +| entropy_loss | -6.24 | +| explained_variance | 0.501 | +| learning_rate | 4.3e-05 | +| loss | -0.0311 | +| n_updates | 73144 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.00014 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1405 | +| iterations | 14333 | +| time_elapsed | 20878 | +| total_timesteps | 29353984 | +| train/ | | +| approx_kl | 0.014983969 | +| clip_fraction | 0.379 | +| clip_range | 0.0677 | +| entropy_loss | -6.38 | +| explained_variance | 0.331 | +| learning_rate | 4.3e-05 | +| loss | -0.036 | +| n_updates | 73148 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000113 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1405 | +| iterations | 14334 | +| time_elapsed | 20879 | +| total_timesteps | 29356032 | +| train/ | | +| approx_kl | 0.019299675 | +| clip_fraction | 0.331 | +| clip_range | 0.0677 | +| entropy_loss | -6.3 | +| explained_variance | 0.368 | +| learning_rate | 4.3e-05 | +| loss | -0.0247 | +| n_updates | 73152 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000239 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1405 | +| iterations | 14335 | +| time_elapsed | 20881 | +| total_timesteps | 29358080 | +| train/ | | +| approx_kl | 0.01700206 | +| clip_fraction | 0.377 | +| clip_range | 0.0677 | +| entropy_loss | -5.7 | +| explained_variance | 0.609 | +| learning_rate | 4.3e-05 | +| loss | -0.0369 | +| n_updates | 73156 | +| policy_gradient_loss | -0.0217 | +| value_loss | 9.06e-05 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1405 | +| iterations | 14336 | +| time_elapsed | 20882 | +| total_timesteps | 29360128 | +| train/ | | +| approx_kl | 0.01278328 | +| clip_fraction | 0.344 | +| clip_range | 0.0677 | +| entropy_loss | -6.24 | +| explained_variance | 0.29 | +| learning_rate | 4.3e-05 | +| loss | -0.0278 | +| n_updates | 73160 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000169 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1405 | +| iterations | 14337 | +| time_elapsed | 20884 | +| total_timesteps | 29362176 | +| train/ | | +| approx_kl | 0.012082883 | +| clip_fraction | 0.326 | +| clip_range | 0.0677 | +| entropy_loss | -6.38 | +| explained_variance | 0.445 | +| learning_rate | 4.3e-05 | +| loss | -0.0272 | +| n_updates | 73164 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000184 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1405 | +| iterations | 14338 | +| time_elapsed | 20885 | +| total_timesteps | 29364224 | +| train/ | | +| approx_kl | 0.013569224 | +| clip_fraction | 0.311 | +| clip_range | 0.0677 | +| entropy_loss | -6.12 | +| explained_variance | 0.268 | +| learning_rate | 4.3e-05 | +| loss | -0.0244 | +| n_updates | 73168 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000199 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1405 | +| iterations | 14339 | +| time_elapsed | 20887 | +| total_timesteps | 29366272 | +| train/ | | +| approx_kl | 0.011634161 | +| clip_fraction | 0.318 | +| clip_range | 0.0677 | +| entropy_loss | -6.08 | +| explained_variance | 0.27 | +| learning_rate | 4.3e-05 | +| loss | -0.0224 | +| n_updates | 73172 | +| policy_gradient_loss | -0.0138 | +| value_loss | 0.000417 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1405 | +| iterations | 14340 | +| time_elapsed | 20888 | +| total_timesteps | 29368320 | +| train/ | | +| approx_kl | 0.01286832 | +| clip_fraction | 0.365 | +| clip_range | 0.0677 | +| entropy_loss | -6.47 | +| explained_variance | -0.495 | +| learning_rate | 4.3e-05 | +| loss | -0.037 | +| n_updates | 73176 | +| policy_gradient_loss | -0.0227 | +| value_loss | 0.000141 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1405 | +| iterations | 14341 | +| time_elapsed | 20890 | +| total_timesteps | 29370368 | +| train/ | | +| approx_kl | 0.012481419 | +| clip_fraction | 0.329 | +| clip_range | 0.0677 | +| entropy_loss | -6.24 | +| explained_variance | 0.283 | +| learning_rate | 4.3e-05 | +| loss | -0.0232 | +| n_updates | 73180 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000335 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1405 | +| iterations | 14342 | +| time_elapsed | 20891 | +| total_timesteps | 29372416 | +| train/ | | +| approx_kl | 0.014969391 | +| clip_fraction | 0.344 | +| clip_range | 0.0677 | +| entropy_loss | -5.9 | +| explained_variance | 0.388 | +| learning_rate | 4.3e-05 | +| loss | -0.0268 | +| n_updates | 73184 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000189 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1405 | +| iterations | 14343 | +| time_elapsed | 20893 | +| total_timesteps | 29374464 | +| train/ | | +| approx_kl | 0.015156105 | +| clip_fraction | 0.382 | +| clip_range | 0.0677 | +| entropy_loss | -6.54 | +| explained_variance | -0.144 | +| learning_rate | 4.3e-05 | +| loss | -0.0432 | +| n_updates | 73188 | +| policy_gradient_loss | -0.0228 | +| value_loss | 0.000101 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1405 | +| iterations | 14344 | +| time_elapsed | 20894 | +| total_timesteps | 29376512 | +| train/ | | +| approx_kl | 0.011341846 | +| clip_fraction | 0.36 | +| clip_range | 0.0677 | +| entropy_loss | -6.1 | +| explained_variance | 0.373 | +| learning_rate | 4.3e-05 | +| loss | -0.0234 | +| n_updates | 73192 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000341 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1405 | +| iterations | 14345 | +| time_elapsed | 20896 | +| total_timesteps | 29378560 | +| train/ | | +| approx_kl | 0.016313571 | +| clip_fraction | 0.352 | +| clip_range | 0.0677 | +| entropy_loss | -5.7 | +| explained_variance | 0.4 | +| learning_rate | 4.3e-05 | +| loss | -0.0257 | +| n_updates | 73196 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000318 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1405 | +| iterations | 14346 | +| time_elapsed | 20898 | +| total_timesteps | 29380608 | +| train/ | | +| approx_kl | 0.0137419645 | +| clip_fraction | 0.354 | +| clip_range | 0.0677 | +| entropy_loss | -5.87 | +| explained_variance | 0.209 | +| learning_rate | 4.3e-05 | +| loss | -0.0335 | +| n_updates | 73200 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000186 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1405 | +| iterations | 14347 | +| time_elapsed | 20899 | +| total_timesteps | 29382656 | +| train/ | | +| approx_kl | 0.014059411 | +| clip_fraction | 0.32 | +| clip_range | 0.0677 | +| entropy_loss | -5.68 | +| explained_variance | 0.493 | +| learning_rate | 4.3e-05 | +| loss | -0.028 | +| n_updates | 73204 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000189 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1405 | +| iterations | 14348 | +| time_elapsed | 20901 | +| total_timesteps | 29384704 | +| train/ | | +| approx_kl | 0.012016821 | +| clip_fraction | 0.355 | +| clip_range | 0.0677 | +| entropy_loss | -6.45 | +| explained_variance | 0.287 | +| learning_rate | 4.3e-05 | +| loss | -0.0289 | +| n_updates | 73208 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000139 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1405 | +| iterations | 14349 | +| time_elapsed | 20902 | +| total_timesteps | 29386752 | +| train/ | | +| approx_kl | 0.013205375 | +| clip_fraction | 0.364 | +| clip_range | 0.0677 | +| entropy_loss | -6.81 | +| explained_variance | -0.112 | +| learning_rate | 4.3e-05 | +| loss | -0.0321 | +| n_updates | 73212 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000125 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1405 | +| iterations | 14350 | +| time_elapsed | 20904 | +| total_timesteps | 29388800 | +| train/ | | +| approx_kl | 0.014072574 | +| clip_fraction | 0.364 | +| clip_range | 0.0677 | +| entropy_loss | -6.39 | +| explained_variance | 0.324 | +| learning_rate | 4.3e-05 | +| loss | -0.031 | +| n_updates | 73216 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000148 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1405 | +| iterations | 14351 | +| time_elapsed | 20905 | +| total_timesteps | 29390848 | +| train/ | | +| approx_kl | 0.014365837 | +| clip_fraction | 0.329 | +| clip_range | 0.0677 | +| entropy_loss | -6.06 | +| explained_variance | 0.283 | +| learning_rate | 4.3e-05 | +| loss | -0.0274 | +| n_updates | 73220 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000289 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1405 | +| iterations | 14352 | +| time_elapsed | 20907 | +| total_timesteps | 29392896 | +| train/ | | +| approx_kl | 0.013442828 | +| clip_fraction | 0.348 | +| clip_range | 0.0677 | +| entropy_loss | -5.65 | +| explained_variance | 0.655 | +| learning_rate | 4.3e-05 | +| loss | -0.0301 | +| n_updates | 73224 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000145 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1405 | +| iterations | 14353 | +| time_elapsed | 20908 | +| total_timesteps | 29394944 | +| train/ | | +| approx_kl | 0.014031673 | +| clip_fraction | 0.371 | +| clip_range | 0.0677 | +| entropy_loss | -6.11 | +| explained_variance | 0.403 | +| learning_rate | 4.3e-05 | +| loss | -0.0318 | +| n_updates | 73228 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000123 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1405 | +| iterations | 14354 | +| time_elapsed | 20910 | +| total_timesteps | 29396992 | +| train/ | | +| approx_kl | 0.016148306 | +| clip_fraction | 0.369 | +| clip_range | 0.0677 | +| entropy_loss | -6.38 | +| explained_variance | 0.195 | +| learning_rate | 4.3e-05 | +| loss | -0.0274 | +| n_updates | 73232 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000203 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1405 | +| iterations | 14355 | +| time_elapsed | 20911 | +| total_timesteps | 29399040 | +| train/ | | +| approx_kl | 0.013148887 | +| clip_fraction | 0.328 | +| clip_range | 0.0677 | +| entropy_loss | -6.83 | +| explained_variance | 0.168 | +| learning_rate | 4.3e-05 | +| loss | -0.0241 | +| n_updates | 73236 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000284 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1405 | +| iterations | 14356 | +| time_elapsed | 20913 | +| total_timesteps | 29401088 | +| train/ | | +| approx_kl | 0.016635329 | +| clip_fraction | 0.33 | +| clip_range | 0.0677 | +| entropy_loss | -6.32 | +| explained_variance | 0.246 | +| learning_rate | 4.3e-05 | +| loss | -0.0282 | +| n_updates | 73240 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000209 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1405 | +| iterations | 14357 | +| time_elapsed | 20914 | +| total_timesteps | 29403136 | +| train/ | | +| approx_kl | 0.016368682 | +| clip_fraction | 0.343 | +| clip_range | 0.0676 | +| entropy_loss | -5.33 | +| explained_variance | 0.727 | +| learning_rate | 4.3e-05 | +| loss | -0.0298 | +| n_updates | 73244 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000114 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1405 | +| iterations | 14358 | +| time_elapsed | 20916 | +| total_timesteps | 29405184 | +| train/ | | +| approx_kl | 0.01502937 | +| clip_fraction | 0.364 | +| clip_range | 0.0676 | +| entropy_loss | -6.26 | +| explained_variance | -0.19 | +| learning_rate | 4.3e-05 | +| loss | -0.0329 | +| n_updates | 73248 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000133 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1405 | +| iterations | 14359 | +| time_elapsed | 20918 | +| total_timesteps | 29407232 | +| train/ | | +| approx_kl | 0.0142415855 | +| clip_fraction | 0.336 | +| clip_range | 0.0676 | +| entropy_loss | -5.94 | +| explained_variance | 0.291 | +| learning_rate | 4.3e-05 | +| loss | -0.0209 | +| n_updates | 73252 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000333 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1405 | +| iterations | 14360 | +| time_elapsed | 20919 | +| total_timesteps | 29409280 | +| train/ | | +| approx_kl | 0.013756871 | +| clip_fraction | 0.373 | +| clip_range | 0.0676 | +| entropy_loss | -6.48 | +| explained_variance | -0.0472 | +| learning_rate | 4.3e-05 | +| loss | -0.0373 | +| n_updates | 73256 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000106 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1405 | +| iterations | 14361 | +| time_elapsed | 20921 | +| total_timesteps | 29411328 | +| train/ | | +| approx_kl | 0.0123183485 | +| clip_fraction | 0.367 | +| clip_range | 0.0676 | +| entropy_loss | -6.71 | +| explained_variance | -0.198 | +| learning_rate | 4.3e-05 | +| loss | -0.0249 | +| n_updates | 73260 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000116 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1405 | +| iterations | 14362 | +| time_elapsed | 20922 | +| total_timesteps | 29413376 | +| train/ | | +| approx_kl | 0.009724196 | +| clip_fraction | 0.324 | +| clip_range | 0.0676 | +| entropy_loss | -6.52 | +| explained_variance | 0.318 | +| learning_rate | 4.3e-05 | +| loss | -0.0204 | +| n_updates | 73264 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.000364 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1405 | +| iterations | 14363 | +| time_elapsed | 20924 | +| total_timesteps | 29415424 | +| train/ | | +| approx_kl | 0.012173187 | +| clip_fraction | 0.342 | +| clip_range | 0.0676 | +| entropy_loss | -5.72 | +| explained_variance | 0.356 | +| learning_rate | 4.3e-05 | +| loss | -0.0242 | +| n_updates | 73268 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000335 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1405 | +| iterations | 14364 | +| time_elapsed | 20925 | +| total_timesteps | 29417472 | +| train/ | | +| approx_kl | 0.011814866 | +| clip_fraction | 0.333 | +| clip_range | 0.0676 | +| entropy_loss | -5.87 | +| explained_variance | 0.394 | +| learning_rate | 4.3e-05 | +| loss | -0.032 | +| n_updates | 73272 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000233 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1405 | +| iterations | 14365 | +| time_elapsed | 20927 | +| total_timesteps | 29419520 | +| train/ | | +| approx_kl | 0.009717419 | +| clip_fraction | 0.324 | +| clip_range | 0.0676 | +| entropy_loss | -6.09 | +| explained_variance | 0.198 | +| learning_rate | 4.3e-05 | +| loss | -0.0205 | +| n_updates | 73276 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000195 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1405 | +| iterations | 14366 | +| time_elapsed | 20928 | +| total_timesteps | 29421568 | +| train/ | | +| approx_kl | 0.016078278 | +| clip_fraction | 0.354 | +| clip_range | 0.0676 | +| entropy_loss | -6.43 | +| explained_variance | -0.175 | +| learning_rate | 4.3e-05 | +| loss | -0.0336 | +| n_updates | 73280 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000146 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1405 | +| iterations | 14367 | +| time_elapsed | 20930 | +| total_timesteps | 29423616 | +| train/ | | +| approx_kl | 0.013775116 | +| clip_fraction | 0.365 | +| clip_range | 0.0676 | +| entropy_loss | -6.85 | +| explained_variance | -0.0812 | +| learning_rate | 4.3e-05 | +| loss | -0.0347 | +| n_updates | 73284 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000271 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1405 | +| iterations | 14368 | +| time_elapsed | 20931 | +| total_timesteps | 29425664 | +| train/ | | +| approx_kl | 0.013796154 | +| clip_fraction | 0.348 | +| clip_range | 0.0676 | +| entropy_loss | -6.62 | +| explained_variance | 0.259 | +| learning_rate | 4.3e-05 | +| loss | -0.0313 | +| n_updates | 73288 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000182 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1405 | +| iterations | 14369 | +| time_elapsed | 20933 | +| total_timesteps | 29427712 | +| train/ | | +| approx_kl | 0.012229327 | +| clip_fraction | 0.316 | +| clip_range | 0.0676 | +| entropy_loss | -6.35 | +| explained_variance | 0.337 | +| learning_rate | 4.3e-05 | +| loss | -0.0277 | +| n_updates | 73292 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000192 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1405 | +| iterations | 14370 | +| time_elapsed | 20934 | +| total_timesteps | 29429760 | +| train/ | | +| approx_kl | 0.011640841 | +| clip_fraction | 0.355 | +| clip_range | 0.0676 | +| entropy_loss | -6.06 | +| explained_variance | 0.628 | +| learning_rate | 4.3e-05 | +| loss | -0.0328 | +| n_updates | 73296 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000131 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1405 | +| iterations | 14371 | +| time_elapsed | 20936 | +| total_timesteps | 29431808 | +| train/ | | +| approx_kl | 0.011393031 | +| clip_fraction | 0.341 | +| clip_range | 0.0676 | +| entropy_loss | -6.24 | +| explained_variance | 0.375 | +| learning_rate | 4.3e-05 | +| loss | -0.0298 | +| n_updates | 73300 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000206 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1405 | +| iterations | 14372 | +| time_elapsed | 20937 | +| total_timesteps | 29433856 | +| train/ | | +| approx_kl | 0.010553832 | +| clip_fraction | 0.341 | +| clip_range | 0.0676 | +| entropy_loss | -5.55 | +| explained_variance | 0.635 | +| learning_rate | 4.3e-05 | +| loss | -0.0319 | +| n_updates | 73304 | +| policy_gradient_loss | -0.0189 | +| value_loss | 8.46e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1405 | +| iterations | 14373 | +| time_elapsed | 20939 | +| total_timesteps | 29435904 | +| train/ | | +| approx_kl | 0.010300742 | +| clip_fraction | 0.311 | +| clip_range | 0.0676 | +| entropy_loss | -5.88 | +| explained_variance | 0.617 | +| learning_rate | 4.3e-05 | +| loss | -0.0245 | +| n_updates | 73308 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000139 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1405 | +| iterations | 14374 | +| time_elapsed | 20941 | +| total_timesteps | 29437952 | +| train/ | | +| approx_kl | 0.012179425 | +| clip_fraction | 0.319 | +| clip_range | 0.0676 | +| entropy_loss | -5.93 | +| explained_variance | 0.461 | +| learning_rate | 4.3e-05 | +| loss | -0.0305 | +| n_updates | 73312 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000182 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1405 | +| iterations | 14375 | +| time_elapsed | 20942 | +| total_timesteps | 29440000 | +| train/ | | +| approx_kl | 0.014808662 | +| clip_fraction | 0.347 | +| clip_range | 0.0676 | +| entropy_loss | -5.99 | +| explained_variance | 0.326 | +| learning_rate | 4.3e-05 | +| loss | -0.0274 | +| n_updates | 73316 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000141 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1405 | +| iterations | 14376 | +| time_elapsed | 20944 | +| total_timesteps | 29442048 | +| train/ | | +| approx_kl | 0.01197649 | +| clip_fraction | 0.347 | +| clip_range | 0.0676 | +| entropy_loss | -6.29 | +| explained_variance | 0.466 | +| learning_rate | 4.3e-05 | +| loss | -0.0263 | +| n_updates | 73320 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000162 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1405 | +| iterations | 14377 | +| time_elapsed | 20945 | +| total_timesteps | 29444096 | +| train/ | | +| approx_kl | 0.013173118 | +| clip_fraction | 0.344 | +| clip_range | 0.0676 | +| entropy_loss | -6.08 | +| explained_variance | 0.347 | +| learning_rate | 4.3e-05 | +| loss | -0.026 | +| n_updates | 73324 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000248 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1405 | +| iterations | 14378 | +| time_elapsed | 20947 | +| total_timesteps | 29446144 | +| train/ | | +| approx_kl | 0.011985482 | +| clip_fraction | 0.356 | +| clip_range | 0.0676 | +| entropy_loss | -6.85 | +| explained_variance | 0.0132 | +| learning_rate | 4.3e-05 | +| loss | -0.0297 | +| n_updates | 73328 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000328 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1405 | +| iterations | 14379 | +| time_elapsed | 20948 | +| total_timesteps | 29448192 | +| train/ | | +| approx_kl | 0.012907407 | +| clip_fraction | 0.33 | +| clip_range | 0.0676 | +| entropy_loss | -6.33 | +| explained_variance | 0.235 | +| learning_rate | 4.3e-05 | +| loss | -0.0254 | +| n_updates | 73332 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000466 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1405 | +| iterations | 14380 | +| time_elapsed | 20950 | +| total_timesteps | 29450240 | +| train/ | | +| approx_kl | 0.011285238 | +| clip_fraction | 0.367 | +| clip_range | 0.0676 | +| entropy_loss | -6.29 | +| explained_variance | 0.311 | +| learning_rate | 4.3e-05 | +| loss | -0.0305 | +| n_updates | 73336 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.00019 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1405 | +| iterations | 14381 | +| time_elapsed | 20951 | +| total_timesteps | 29452288 | +| train/ | | +| approx_kl | 0.011852807 | +| clip_fraction | 0.314 | +| clip_range | 0.0676 | +| entropy_loss | -6.09 | +| explained_variance | 0.641 | +| learning_rate | 4.3e-05 | +| loss | -0.0334 | +| n_updates | 73340 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.00014 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1405 | +| iterations | 14382 | +| time_elapsed | 20953 | +| total_timesteps | 29454336 | +| train/ | | +| approx_kl | 0.010940946 | +| clip_fraction | 0.323 | +| clip_range | 0.0676 | +| entropy_loss | -6.36 | +| explained_variance | 0.145 | +| learning_rate | 4.3e-05 | +| loss | -0.0326 | +| n_updates | 73344 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000237 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1405 | +| iterations | 14383 | +| time_elapsed | 20954 | +| total_timesteps | 29456384 | +| train/ | | +| approx_kl | 0.010166941 | +| clip_fraction | 0.318 | +| clip_range | 0.0676 | +| entropy_loss | -5.92 | +| explained_variance | 0.547 | +| learning_rate | 4.3e-05 | +| loss | -0.024 | +| n_updates | 73348 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000234 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1405 | +| iterations | 14384 | +| time_elapsed | 20956 | +| total_timesteps | 29458432 | +| train/ | | +| approx_kl | 0.011790801 | +| clip_fraction | 0.332 | +| clip_range | 0.0676 | +| entropy_loss | -5.93 | +| explained_variance | 0.451 | +| learning_rate | 4.3e-05 | +| loss | -0.0206 | +| n_updates | 73352 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000178 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1405 | +| iterations | 14385 | +| time_elapsed | 20957 | +| total_timesteps | 29460480 | +| train/ | | +| approx_kl | 0.013692372 | +| clip_fraction | 0.358 | +| clip_range | 0.0676 | +| entropy_loss | -6.3 | +| explained_variance | 0.296 | +| learning_rate | 4.3e-05 | +| loss | -0.036 | +| n_updates | 73356 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000147 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1405 | +| iterations | 14386 | +| time_elapsed | 20959 | +| total_timesteps | 29462528 | +| train/ | | +| approx_kl | 0.015799614 | +| clip_fraction | 0.353 | +| clip_range | 0.0676 | +| entropy_loss | -6.69 | +| explained_variance | -0.00822 | +| learning_rate | 4.3e-05 | +| loss | -0.0331 | +| n_updates | 73360 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000155 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1405 | +| iterations | 14387 | +| time_elapsed | 20961 | +| total_timesteps | 29464576 | +| train/ | | +| approx_kl | 0.013978413 | +| clip_fraction | 0.343 | +| clip_range | 0.0676 | +| entropy_loss | -6.29 | +| explained_variance | 0.654 | +| learning_rate | 4.3e-05 | +| loss | -0.0335 | +| n_updates | 73364 | +| policy_gradient_loss | -0.0206 | +| value_loss | 7.93e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1405 | +| iterations | 14388 | +| time_elapsed | 20962 | +| total_timesteps | 29466624 | +| train/ | | +| approx_kl | 0.017526869 | +| clip_fraction | 0.348 | +| clip_range | 0.0676 | +| entropy_loss | -6.47 | +| explained_variance | 0.195 | +| learning_rate | 4.3e-05 | +| loss | -0.0285 | +| n_updates | 73368 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.0002 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1405 | +| iterations | 14389 | +| time_elapsed | 20964 | +| total_timesteps | 29468672 | +| train/ | | +| approx_kl | 0.0132383015 | +| clip_fraction | 0.313 | +| clip_range | 0.0676 | +| entropy_loss | -6.83 | +| explained_variance | -0.0401 | +| learning_rate | 4.3e-05 | +| loss | -0.0282 | +| n_updates | 73372 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000171 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1405 | +| iterations | 14390 | +| time_elapsed | 20965 | +| total_timesteps | 29470720 | +| train/ | | +| approx_kl | 0.012584981 | +| clip_fraction | 0.358 | +| clip_range | 0.0676 | +| entropy_loss | -6.72 | +| explained_variance | 0.0214 | +| learning_rate | 4.3e-05 | +| loss | -0.0357 | +| n_updates | 73376 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.00016 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1405 | +| iterations | 14391 | +| time_elapsed | 20967 | +| total_timesteps | 29472768 | +| train/ | | +| approx_kl | 0.01644396 | +| clip_fraction | 0.31 | +| clip_range | 0.0676 | +| entropy_loss | -5.68 | +| explained_variance | 0.543 | +| learning_rate | 4.3e-05 | +| loss | -0.0257 | +| n_updates | 73380 | +| policy_gradient_loss | -0.0143 | +| value_loss | 0.000268 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1405 | +| iterations | 14392 | +| time_elapsed | 20968 | +| total_timesteps | 29474816 | +| train/ | | +| approx_kl | 0.014830109 | +| clip_fraction | 0.356 | +| clip_range | 0.0676 | +| entropy_loss | -5.39 | +| explained_variance | 0.581 | +| learning_rate | 4.3e-05 | +| loss | -0.0308 | +| n_updates | 73384 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.00011 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1405 | +| iterations | 14393 | +| time_elapsed | 20970 | +| total_timesteps | 29476864 | +| train/ | | +| approx_kl | 0.009754693 | +| clip_fraction | 0.296 | +| clip_range | 0.0676 | +| entropy_loss | -6.17 | +| explained_variance | 0.547 | +| learning_rate | 4.3e-05 | +| loss | -0.025 | +| n_updates | 73388 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000227 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1405 | +| iterations | 14394 | +| time_elapsed | 20972 | +| total_timesteps | 29478912 | +| train/ | | +| approx_kl | 0.012028063 | +| clip_fraction | 0.318 | +| clip_range | 0.0676 | +| entropy_loss | -6 | +| explained_variance | 0.452 | +| learning_rate | 4.3e-05 | +| loss | -0.0323 | +| n_updates | 73392 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000128 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1405 | +| iterations | 14395 | +| time_elapsed | 20973 | +| total_timesteps | 29480960 | +| train/ | | +| approx_kl | 0.012144921 | +| clip_fraction | 0.351 | +| clip_range | 0.0676 | +| entropy_loss | -6.4 | +| explained_variance | 0.35 | +| learning_rate | 4.3e-05 | +| loss | -0.028 | +| n_updates | 73396 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000131 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1405 | +| iterations | 14396 | +| time_elapsed | 20975 | +| total_timesteps | 29483008 | +| train/ | | +| approx_kl | 0.013778312 | +| clip_fraction | 0.346 | +| clip_range | 0.0676 | +| entropy_loss | -6.49 | +| explained_variance | 0.278 | +| learning_rate | 4.3e-05 | +| loss | -0.028 | +| n_updates | 73400 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000192 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1405 | +| iterations | 14397 | +| time_elapsed | 20976 | +| total_timesteps | 29485056 | +| train/ | | +| approx_kl | 0.014868349 | +| clip_fraction | 0.362 | +| clip_range | 0.0676 | +| entropy_loss | -6.2 | +| explained_variance | 0.237 | +| learning_rate | 4.3e-05 | +| loss | -0.0251 | +| n_updates | 73404 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000313 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1405 | +| iterations | 14398 | +| time_elapsed | 20978 | +| total_timesteps | 29487104 | +| train/ | | +| approx_kl | 0.012941634 | +| clip_fraction | 0.336 | +| clip_range | 0.0676 | +| entropy_loss | -6.13 | +| explained_variance | 0.437 | +| learning_rate | 4.3e-05 | +| loss | -0.0307 | +| n_updates | 73408 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000184 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1405 | +| iterations | 14399 | +| time_elapsed | 20979 | +| total_timesteps | 29489152 | +| train/ | | +| approx_kl | 0.014686053 | +| clip_fraction | 0.373 | +| clip_range | 0.0676 | +| entropy_loss | -6.46 | +| explained_variance | 0.327 | +| learning_rate | 4.3e-05 | +| loss | -0.0293 | +| n_updates | 73412 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000159 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1405 | +| iterations | 14400 | +| time_elapsed | 20981 | +| total_timesteps | 29491200 | +| train/ | | +| approx_kl | 0.012381708 | +| clip_fraction | 0.323 | +| clip_range | 0.0676 | +| entropy_loss | -6.4 | +| explained_variance | 0.471 | +| learning_rate | 4.3e-05 | +| loss | -0.0344 | +| n_updates | 73416 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000185 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1405 | +| iterations | 14401 | +| time_elapsed | 20982 | +| total_timesteps | 29493248 | +| train/ | | +| approx_kl | 0.011354497 | +| clip_fraction | 0.338 | +| clip_range | 0.0676 | +| entropy_loss | -6.63 | +| explained_variance | 0.14 | +| learning_rate | 4.3e-05 | +| loss | -0.0288 | +| n_updates | 73420 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000134 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1405 | +| iterations | 14402 | +| time_elapsed | 20984 | +| total_timesteps | 29495296 | +| train/ | | +| approx_kl | 0.014349991 | +| clip_fraction | 0.332 | +| clip_range | 0.0676 | +| entropy_loss | -6.52 | +| explained_variance | 0.391 | +| learning_rate | 4.3e-05 | +| loss | -0.03 | +| n_updates | 73424 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000175 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.384 | +| time/ | | +| fps | 1405 | +| iterations | 14403 | +| time_elapsed | 20985 | +| total_timesteps | 29497344 | +| train/ | | +| approx_kl | 0.011446075 | +| clip_fraction | 0.311 | +| clip_range | 0.0676 | +| entropy_loss | -6.1 | +| explained_variance | 0.407 | +| learning_rate | 4.3e-05 | +| loss | -0.017 | +| n_updates | 73428 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000235 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1405 | +| iterations | 14404 | +| time_elapsed | 20987 | +| total_timesteps | 29499392 | +| train/ | | +| approx_kl | 0.014043502 | +| clip_fraction | 0.337 | +| clip_range | 0.0676 | +| entropy_loss | -6.56 | +| explained_variance | 0.36 | +| learning_rate | 4.3e-05 | +| loss | -0.0382 | +| n_updates | 73432 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000112 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1405 | +| iterations | 14405 | +| time_elapsed | 20988 | +| total_timesteps | 29501440 | +| train/ | | +| approx_kl | 0.012285561 | +| clip_fraction | 0.323 | +| clip_range | 0.0676 | +| entropy_loss | -6.28 | +| explained_variance | 0.552 | +| learning_rate | 4.3e-05 | +| loss | -0.0242 | +| n_updates | 73436 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000168 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.385 | +| time/ | | +| fps | 1405 | +| iterations | 14406 | +| time_elapsed | 20990 | +| total_timesteps | 29503488 | +| train/ | | +| approx_kl | 0.012444353 | +| clip_fraction | 0.344 | +| clip_range | 0.0676 | +| entropy_loss | -6.23 | +| explained_variance | 0.37 | +| learning_rate | 4.3e-05 | +| loss | -0.0258 | +| n_updates | 73440 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.00013 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.384 | +| time/ | | +| fps | 1405 | +| iterations | 14407 | +| time_elapsed | 20991 | +| total_timesteps | 29505536 | +| train/ | | +| approx_kl | 0.013636586 | +| clip_fraction | 0.332 | +| clip_range | 0.0676 | +| entropy_loss | -5.2 | +| explained_variance | 0.812 | +| learning_rate | 4.3e-05 | +| loss | -0.0281 | +| n_updates | 73444 | +| policy_gradient_loss | -0.0181 | +| value_loss | 8.91e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1405 | +| iterations | 14408 | +| time_elapsed | 20993 | +| total_timesteps | 29507584 | +| train/ | | +| approx_kl | 0.010096442 | +| clip_fraction | 0.306 | +| clip_range | 0.0676 | +| entropy_loss | -6.75 | +| explained_variance | 0.0275 | +| learning_rate | 4.3e-05 | +| loss | -0.0273 | +| n_updates | 73448 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000218 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1405 | +| iterations | 14409 | +| time_elapsed | 20995 | +| total_timesteps | 29509632 | +| train/ | | +| approx_kl | 0.011105211 | +| clip_fraction | 0.322 | +| clip_range | 0.0676 | +| entropy_loss | -6.49 | +| explained_variance | 0.533 | +| learning_rate | 4.3e-05 | +| loss | -0.03 | +| n_updates | 73452 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000168 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.386 | +| time/ | | +| fps | 1405 | +| iterations | 14410 | +| time_elapsed | 20996 | +| total_timesteps | 29511680 | +| train/ | | +| approx_kl | 0.012306872 | +| clip_fraction | 0.36 | +| clip_range | 0.0676 | +| entropy_loss | -6.44 | +| explained_variance | -0.566 | +| learning_rate | 4.3e-05 | +| loss | -0.0323 | +| n_updates | 73456 | +| policy_gradient_loss | -0.022 | +| value_loss | 6.14e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.391 | +| time/ | | +| fps | 1405 | +| iterations | 14411 | +| time_elapsed | 20998 | +| total_timesteps | 29513728 | +| train/ | | +| approx_kl | 0.012861891 | +| clip_fraction | 0.368 | +| clip_range | 0.0676 | +| entropy_loss | -6.61 | +| explained_variance | 0.332 | +| learning_rate | 4.3e-05 | +| loss | -0.0261 | +| n_updates | 73460 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.00021 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.394 | +| time/ | | +| fps | 1405 | +| iterations | 14412 | +| time_elapsed | 20999 | +| total_timesteps | 29515776 | +| train/ | | +| approx_kl | 0.013767239 | +| clip_fraction | 0.334 | +| clip_range | 0.0676 | +| entropy_loss | -6.48 | +| explained_variance | 0.208 | +| learning_rate | 4.3e-05 | +| loss | -0.0276 | +| n_updates | 73464 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000311 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.396 | +| time/ | | +| fps | 1405 | +| iterations | 14413 | +| time_elapsed | 21001 | +| total_timesteps | 29517824 | +| train/ | | +| approx_kl | 0.01265147 | +| clip_fraction | 0.332 | +| clip_range | 0.0676 | +| entropy_loss | -6.1 | +| explained_variance | 0.609 | +| learning_rate | 4.3e-05 | +| loss | -0.0308 | +| n_updates | 73468 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000196 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.391 | +| time/ | | +| fps | 1405 | +| iterations | 14414 | +| time_elapsed | 21002 | +| total_timesteps | 29519872 | +| train/ | | +| approx_kl | 0.01112468 | +| clip_fraction | 0.324 | +| clip_range | 0.0676 | +| entropy_loss | -6.15 | +| explained_variance | 0.285 | +| learning_rate | 4.3e-05 | +| loss | -0.0308 | +| n_updates | 73472 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000148 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.391 | +| time/ | | +| fps | 1405 | +| iterations | 14415 | +| time_elapsed | 21004 | +| total_timesteps | 29521920 | +| train/ | | +| approx_kl | 0.012119561 | +| clip_fraction | 0.346 | +| clip_range | 0.0676 | +| entropy_loss | -6.08 | +| explained_variance | 0.582 | +| learning_rate | 4.3e-05 | +| loss | -0.0319 | +| n_updates | 73476 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000152 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.386 | +| time/ | | +| fps | 1405 | +| iterations | 14416 | +| time_elapsed | 21005 | +| total_timesteps | 29523968 | +| train/ | | +| approx_kl | 0.010985083 | +| clip_fraction | 0.329 | +| clip_range | 0.0676 | +| entropy_loss | -6.61 | +| explained_variance | 0.239 | +| learning_rate | 4.3e-05 | +| loss | -0.0327 | +| n_updates | 73480 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000133 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.388 | +| time/ | | +| fps | 1405 | +| iterations | 14417 | +| time_elapsed | 21007 | +| total_timesteps | 29526016 | +| train/ | | +| approx_kl | 0.01512731 | +| clip_fraction | 0.325 | +| clip_range | 0.0676 | +| entropy_loss | -6.43 | +| explained_variance | 0.209 | +| learning_rate | 4.3e-05 | +| loss | -0.0318 | +| n_updates | 73484 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000205 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.387 | +| time/ | | +| fps | 1405 | +| iterations | 14418 | +| time_elapsed | 21008 | +| total_timesteps | 29528064 | +| train/ | | +| approx_kl | 0.014159913 | +| clip_fraction | 0.34 | +| clip_range | 0.0676 | +| entropy_loss | -6.48 | +| explained_variance | -0.121 | +| learning_rate | 4.3e-05 | +| loss | -0.0266 | +| n_updates | 73488 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000124 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.387 | +| time/ | | +| fps | 1405 | +| iterations | 14419 | +| time_elapsed | 21010 | +| total_timesteps | 29530112 | +| train/ | | +| approx_kl | 0.016451918 | +| clip_fraction | 0.313 | +| clip_range | 0.0676 | +| entropy_loss | -5.9 | +| explained_variance | 0.627 | +| learning_rate | 4.3e-05 | +| loss | -0.0265 | +| n_updates | 73492 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000165 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.387 | +| time/ | | +| fps | 1405 | +| iterations | 14420 | +| time_elapsed | 21011 | +| total_timesteps | 29532160 | +| train/ | | +| approx_kl | 0.0139374 | +| clip_fraction | 0.335 | +| clip_range | 0.0676 | +| entropy_loss | -6 | +| explained_variance | 0.268 | +| learning_rate | 4.3e-05 | +| loss | -0.0252 | +| n_updates | 73496 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000128 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1405 | +| iterations | 14421 | +| time_elapsed | 21013 | +| total_timesteps | 29534208 | +| train/ | | +| approx_kl | 0.013586985 | +| clip_fraction | 0.34 | +| clip_range | 0.0676 | +| entropy_loss | -6.7 | +| explained_variance | 0.0997 | +| learning_rate | 4.3e-05 | +| loss | -0.03 | +| n_updates | 73500 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000166 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1405 | +| iterations | 14422 | +| time_elapsed | 21014 | +| total_timesteps | 29536256 | +| train/ | | +| approx_kl | 0.011232653 | +| clip_fraction | 0.342 | +| clip_range | 0.0676 | +| entropy_loss | -6.57 | +| explained_variance | -0.0371 | +| learning_rate | 4.3e-05 | +| loss | -0.0316 | +| n_updates | 73504 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000214 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1405 | +| iterations | 14423 | +| time_elapsed | 21016 | +| total_timesteps | 29538304 | +| train/ | | +| approx_kl | 0.01462651 | +| clip_fraction | 0.356 | +| clip_range | 0.0676 | +| entropy_loss | -6.47 | +| explained_variance | 0.319 | +| learning_rate | 4.3e-05 | +| loss | -0.0354 | +| n_updates | 73508 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000151 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1405 | +| iterations | 14424 | +| time_elapsed | 21017 | +| total_timesteps | 29540352 | +| train/ | | +| approx_kl | 0.014509868 | +| clip_fraction | 0.36 | +| clip_range | 0.0676 | +| entropy_loss | -6.53 | +| explained_variance | -0.0996 | +| learning_rate | 4.3e-05 | +| loss | -0.0254 | +| n_updates | 73512 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000299 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1405 | +| iterations | 14425 | +| time_elapsed | 21019 | +| total_timesteps | 29542400 | +| train/ | | +| approx_kl | 0.0114355795 | +| clip_fraction | 0.316 | +| clip_range | 0.0676 | +| entropy_loss | -5.98 | +| explained_variance | 0.483 | +| learning_rate | 4.3e-05 | +| loss | -0.0292 | +| n_updates | 73516 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000157 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1405 | +| iterations | 14426 | +| time_elapsed | 21020 | +| total_timesteps | 29544448 | +| train/ | | +| approx_kl | 0.014400259 | +| clip_fraction | 0.391 | +| clip_range | 0.0676 | +| entropy_loss | -6.87 | +| explained_variance | -0.588 | +| learning_rate | 4.3e-05 | +| loss | -0.0407 | +| n_updates | 73520 | +| policy_gradient_loss | -0.0245 | +| value_loss | 5.56e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1405 | +| iterations | 14427 | +| time_elapsed | 21022 | +| total_timesteps | 29546496 | +| train/ | | +| approx_kl | 0.015603653 | +| clip_fraction | 0.366 | +| clip_range | 0.0676 | +| entropy_loss | -6.28 | +| explained_variance | 0.376 | +| learning_rate | 4.3e-05 | +| loss | -0.0339 | +| n_updates | 73524 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000122 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1405 | +| iterations | 14428 | +| time_elapsed | 21023 | +| total_timesteps | 29548544 | +| train/ | | +| approx_kl | 0.015997566 | +| clip_fraction | 0.334 | +| clip_range | 0.0676 | +| entropy_loss | -5.37 | +| explained_variance | 0.566 | +| learning_rate | 4.3e-05 | +| loss | -0.0231 | +| n_updates | 73528 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.0002 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1405 | +| iterations | 14429 | +| time_elapsed | 21025 | +| total_timesteps | 29550592 | +| train/ | | +| approx_kl | 0.011861587 | +| clip_fraction | 0.329 | +| clip_range | 0.0676 | +| entropy_loss | -5.89 | +| explained_variance | 0.181 | +| learning_rate | 4.3e-05 | +| loss | -0.0289 | +| n_updates | 73532 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.00021 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1405 | +| iterations | 14430 | +| time_elapsed | 21027 | +| total_timesteps | 29552640 | +| train/ | | +| approx_kl | 0.013399338 | +| clip_fraction | 0.372 | +| clip_range | 0.0676 | +| entropy_loss | -6.27 | +| explained_variance | 0.492 | +| learning_rate | 4.3e-05 | +| loss | -0.0311 | +| n_updates | 73536 | +| policy_gradient_loss | -0.0204 | +| value_loss | 9.3e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.385 | +| time/ | | +| fps | 1405 | +| iterations | 14431 | +| time_elapsed | 21028 | +| total_timesteps | 29554688 | +| train/ | | +| approx_kl | 0.013239569 | +| clip_fraction | 0.315 | +| clip_range | 0.0676 | +| entropy_loss | -6.61 | +| explained_variance | -0.103 | +| learning_rate | 4.3e-05 | +| loss | -0.0273 | +| n_updates | 73540 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.00025 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1405 | +| iterations | 14432 | +| time_elapsed | 21030 | +| total_timesteps | 29556736 | +| train/ | | +| approx_kl | 0.015941257 | +| clip_fraction | 0.312 | +| clip_range | 0.0676 | +| entropy_loss | -6.54 | +| explained_variance | 0.117 | +| learning_rate | 4.3e-05 | +| loss | -0.0278 | +| n_updates | 73544 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000327 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1405 | +| iterations | 14433 | +| time_elapsed | 21031 | +| total_timesteps | 29558784 | +| train/ | | +| approx_kl | 0.012516291 | +| clip_fraction | 0.328 | +| clip_range | 0.0676 | +| entropy_loss | -6.1 | +| explained_variance | 0.235 | +| learning_rate | 4.3e-05 | +| loss | -0.0251 | +| n_updates | 73548 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000389 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1405 | +| iterations | 14434 | +| time_elapsed | 21033 | +| total_timesteps | 29560832 | +| train/ | | +| approx_kl | 0.015695222 | +| clip_fraction | 0.359 | +| clip_range | 0.0676 | +| entropy_loss | -5.77 | +| explained_variance | 0.613 | +| learning_rate | 4.3e-05 | +| loss | -0.0335 | +| n_updates | 73552 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000104 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1405 | +| iterations | 14435 | +| time_elapsed | 21034 | +| total_timesteps | 29562880 | +| train/ | | +| approx_kl | 0.014694141 | +| clip_fraction | 0.344 | +| clip_range | 0.0676 | +| entropy_loss | -5.8 | +| explained_variance | 0.429 | +| learning_rate | 4.3e-05 | +| loss | -0.0343 | +| n_updates | 73556 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000182 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1405 | +| iterations | 14436 | +| time_elapsed | 21036 | +| total_timesteps | 29564928 | +| train/ | | +| approx_kl | 0.017843943 | +| clip_fraction | 0.376 | +| clip_range | 0.0676 | +| entropy_loss | -6.23 | +| explained_variance | 0.105 | +| learning_rate | 4.3e-05 | +| loss | -0.0352 | +| n_updates | 73560 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000237 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1405 | +| iterations | 14437 | +| time_elapsed | 21037 | +| total_timesteps | 29566976 | +| train/ | | +| approx_kl | 0.013563136 | +| clip_fraction | 0.366 | +| clip_range | 0.0676 | +| entropy_loss | -6.43 | +| explained_variance | -0.205 | +| learning_rate | 4.3e-05 | +| loss | -0.0335 | +| n_updates | 73564 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000117 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1405 | +| iterations | 14438 | +| time_elapsed | 21039 | +| total_timesteps | 29569024 | +| train/ | | +| approx_kl | 0.012238199 | +| clip_fraction | 0.326 | +| clip_range | 0.0676 | +| entropy_loss | -6.51 | +| explained_variance | 0.32 | +| learning_rate | 4.3e-05 | +| loss | -0.0283 | +| n_updates | 73568 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000137 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1405 | +| iterations | 14439 | +| time_elapsed | 21040 | +| total_timesteps | 29571072 | +| train/ | | +| approx_kl | 0.011296803 | +| clip_fraction | 0.337 | +| clip_range | 0.0676 | +| entropy_loss | -6.42 | +| explained_variance | 0.607 | +| learning_rate | 4.3e-05 | +| loss | -0.0285 | +| n_updates | 73572 | +| policy_gradient_loss | -0.0198 | +| value_loss | 9.66e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1405 | +| iterations | 14440 | +| time_elapsed | 21042 | +| total_timesteps | 29573120 | +| train/ | | +| approx_kl | 0.012897655 | +| clip_fraction | 0.333 | +| clip_range | 0.0676 | +| entropy_loss | -6.6 | +| explained_variance | 0.644 | +| learning_rate | 4.3e-05 | +| loss | -0.0325 | +| n_updates | 73576 | +| policy_gradient_loss | -0.0191 | +| value_loss | 8.55e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1405 | +| iterations | 14441 | +| time_elapsed | 21043 | +| total_timesteps | 29575168 | +| train/ | | +| approx_kl | 0.0124006905 | +| clip_fraction | 0.307 | +| clip_range | 0.0676 | +| entropy_loss | -5.92 | +| explained_variance | 0.669 | +| learning_rate | 4.3e-05 | +| loss | -0.0282 | +| n_updates | 73580 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000121 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1405 | +| iterations | 14442 | +| time_elapsed | 21045 | +| total_timesteps | 29577216 | +| train/ | | +| approx_kl | 0.0141063705 | +| clip_fraction | 0.326 | +| clip_range | 0.0676 | +| entropy_loss | -6.47 | +| explained_variance | 0.195 | +| learning_rate | 4.3e-05 | +| loss | -0.0274 | +| n_updates | 73584 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000162 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1405 | +| iterations | 14443 | +| time_elapsed | 21046 | +| total_timesteps | 29579264 | +| train/ | | +| approx_kl | 0.011306497 | +| clip_fraction | 0.287 | +| clip_range | 0.0676 | +| entropy_loss | -5.67 | +| explained_variance | 0.496 | +| learning_rate | 4.3e-05 | +| loss | -0.0247 | +| n_updates | 73588 | +| policy_gradient_loss | -0.0129 | +| value_loss | 0.00032 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1405 | +| iterations | 14444 | +| time_elapsed | 21048 | +| total_timesteps | 29581312 | +| train/ | | +| approx_kl | 0.012277573 | +| clip_fraction | 0.355 | +| clip_range | 0.0676 | +| entropy_loss | -6.37 | +| explained_variance | 0.12 | +| learning_rate | 4.3e-05 | +| loss | -0.0311 | +| n_updates | 73592 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000177 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1405 | +| iterations | 14445 | +| time_elapsed | 21049 | +| total_timesteps | 29583360 | +| train/ | | +| approx_kl | 0.0125666205 | +| clip_fraction | 0.325 | +| clip_range | 0.0676 | +| entropy_loss | -6.35 | +| explained_variance | 0.449 | +| learning_rate | 4.3e-05 | +| loss | -0.0271 | +| n_updates | 73596 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000162 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1405 | +| iterations | 14446 | +| time_elapsed | 21051 | +| total_timesteps | 29585408 | +| train/ | | +| approx_kl | 0.014279379 | +| clip_fraction | 0.32 | +| clip_range | 0.0676 | +| entropy_loss | -6.74 | +| explained_variance | -0.057 | +| learning_rate | 4.3e-05 | +| loss | -0.0309 | +| n_updates | 73600 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000308 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1405 | +| iterations | 14447 | +| time_elapsed | 21052 | +| total_timesteps | 29587456 | +| train/ | | +| approx_kl | 0.012867551 | +| clip_fraction | 0.351 | +| clip_range | 0.0676 | +| entropy_loss | -6.8 | +| explained_variance | 0.196 | +| learning_rate | 4.3e-05 | +| loss | -0.0311 | +| n_updates | 73604 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000161 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1405 | +| iterations | 14448 | +| time_elapsed | 21054 | +| total_timesteps | 29589504 | +| train/ | | +| approx_kl | 0.011397274 | +| clip_fraction | 0.321 | +| clip_range | 0.0676 | +| entropy_loss | -6.4 | +| explained_variance | 0.238 | +| learning_rate | 4.3e-05 | +| loss | -0.0258 | +| n_updates | 73608 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000433 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1405 | +| iterations | 14449 | +| time_elapsed | 21055 | +| total_timesteps | 29591552 | +| train/ | | +| approx_kl | 0.011239774 | +| clip_fraction | 0.341 | +| clip_range | 0.0676 | +| entropy_loss | -5.81 | +| explained_variance | 0.415 | +| learning_rate | 4.3e-05 | +| loss | -0.0307 | +| n_updates | 73612 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000134 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1405 | +| iterations | 14450 | +| time_elapsed | 21057 | +| total_timesteps | 29593600 | +| train/ | | +| approx_kl | 0.013356105 | +| clip_fraction | 0.359 | +| clip_range | 0.0676 | +| entropy_loss | -6.32 | +| explained_variance | 0.219 | +| learning_rate | 4.3e-05 | +| loss | -0.0316 | +| n_updates | 73616 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000227 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1405 | +| iterations | 14451 | +| time_elapsed | 21059 | +| total_timesteps | 29595648 | +| train/ | | +| approx_kl | 0.014602661 | +| clip_fraction | 0.343 | +| clip_range | 0.0676 | +| entropy_loss | -6.5 | +| explained_variance | 0.383 | +| learning_rate | 4.3e-05 | +| loss | -0.033 | +| n_updates | 73620 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.00014 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1405 | +| iterations | 14452 | +| time_elapsed | 21060 | +| total_timesteps | 29597696 | +| train/ | | +| approx_kl | 0.013006853 | +| clip_fraction | 0.354 | +| clip_range | 0.0676 | +| entropy_loss | -6.52 | +| explained_variance | 0.505 | +| learning_rate | 4.3e-05 | +| loss | -0.0321 | +| n_updates | 73624 | +| policy_gradient_loss | -0.0205 | +| value_loss | 8.68e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1405 | +| iterations | 14453 | +| time_elapsed | 21061 | +| total_timesteps | 29599744 | +| train/ | | +| approx_kl | 0.014358711 | +| clip_fraction | 0.331 | +| clip_range | 0.0676 | +| entropy_loss | -6.37 | +| explained_variance | 0.371 | +| learning_rate | 4.3e-05 | +| loss | -0.0175 | +| n_updates | 73628 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000144 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1405 | +| iterations | 14454 | +| time_elapsed | 21063 | +| total_timesteps | 29601792 | +| train/ | | +| approx_kl | 0.016620196 | +| clip_fraction | 0.317 | +| clip_range | 0.0676 | +| entropy_loss | -6.3 | +| explained_variance | 0.612 | +| learning_rate | 4.3e-05 | +| loss | -0.0287 | +| n_updates | 73632 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000141 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1405 | +| iterations | 14455 | +| time_elapsed | 21065 | +| total_timesteps | 29603840 | +| train/ | | +| approx_kl | 0.010603991 | +| clip_fraction | 0.325 | +| clip_range | 0.0676 | +| entropy_loss | -6.54 | +| explained_variance | 0.487 | +| learning_rate | 4.3e-05 | +| loss | -0.0228 | +| n_updates | 73636 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000186 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1405 | +| iterations | 14456 | +| time_elapsed | 21066 | +| total_timesteps | 29605888 | +| train/ | | +| approx_kl | 0.01346832 | +| clip_fraction | 0.342 | +| clip_range | 0.0676 | +| entropy_loss | -6.61 | +| explained_variance | -0.0905 | +| learning_rate | 4.3e-05 | +| loss | -0.029 | +| n_updates | 73640 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000208 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1405 | +| iterations | 14457 | +| time_elapsed | 21068 | +| total_timesteps | 29607936 | +| train/ | | +| approx_kl | 0.0138762165 | +| clip_fraction | 0.34 | +| clip_range | 0.0676 | +| entropy_loss | -6.51 | +| explained_variance | 0.547 | +| learning_rate | 4.3e-05 | +| loss | -0.0396 | +| n_updates | 73644 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.00012 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1405 | +| iterations | 14458 | +| time_elapsed | 21069 | +| total_timesteps | 29609984 | +| train/ | | +| approx_kl | 0.012117091 | +| clip_fraction | 0.321 | +| clip_range | 0.0676 | +| entropy_loss | -6 | +| explained_variance | 0.482 | +| learning_rate | 4.3e-05 | +| loss | -0.03 | +| n_updates | 73648 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000184 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1405 | +| iterations | 14459 | +| time_elapsed | 21071 | +| total_timesteps | 29612032 | +| train/ | | +| approx_kl | 0.01348094 | +| clip_fraction | 0.357 | +| clip_range | 0.0676 | +| entropy_loss | -5.97 | +| explained_variance | 0.672 | +| learning_rate | 4.3e-05 | +| loss | -0.0333 | +| n_updates | 73652 | +| policy_gradient_loss | -0.0224 | +| value_loss | 7.64e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1405 | +| iterations | 14460 | +| time_elapsed | 21072 | +| total_timesteps | 29614080 | +| train/ | | +| approx_kl | 0.015661212 | +| clip_fraction | 0.351 | +| clip_range | 0.0676 | +| entropy_loss | -6.64 | +| explained_variance | 0.428 | +| learning_rate | 4.3e-05 | +| loss | -0.0373 | +| n_updates | 73656 | +| policy_gradient_loss | -0.0204 | +| value_loss | 9.7e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1405 | +| iterations | 14461 | +| time_elapsed | 21074 | +| total_timesteps | 29616128 | +| train/ | | +| approx_kl | 0.011741514 | +| clip_fraction | 0.32 | +| clip_range | 0.0676 | +| entropy_loss | -6.57 | +| explained_variance | 0.315 | +| learning_rate | 4.3e-05 | +| loss | -0.0269 | +| n_updates | 73660 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000175 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1405 | +| iterations | 14462 | +| time_elapsed | 21075 | +| total_timesteps | 29618176 | +| train/ | | +| approx_kl | 0.013992696 | +| clip_fraction | 0.335 | +| clip_range | 0.0676 | +| entropy_loss | -5.96 | +| explained_variance | 0.709 | +| learning_rate | 4.3e-05 | +| loss | -0.0356 | +| n_updates | 73664 | +| policy_gradient_loss | -0.0203 | +| value_loss | 7.97e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1405 | +| iterations | 14463 | +| time_elapsed | 21077 | +| total_timesteps | 29620224 | +| train/ | | +| approx_kl | 0.012045879 | +| clip_fraction | 0.31 | +| clip_range | 0.0676 | +| entropy_loss | -6.14 | +| explained_variance | 0.188 | +| learning_rate | 4.3e-05 | +| loss | -0.0261 | +| n_updates | 73668 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.00027 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1405 | +| iterations | 14464 | +| time_elapsed | 21078 | +| total_timesteps | 29622272 | +| train/ | | +| approx_kl | 0.014201185 | +| clip_fraction | 0.319 | +| clip_range | 0.0676 | +| entropy_loss | -5.74 | +| explained_variance | 0.711 | +| learning_rate | 4.3e-05 | +| loss | -0.0352 | +| n_updates | 73672 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000114 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1405 | +| iterations | 14465 | +| time_elapsed | 21080 | +| total_timesteps | 29624320 | +| train/ | | +| approx_kl | 0.011680227 | +| clip_fraction | 0.329 | +| clip_range | 0.0676 | +| entropy_loss | -5.85 | +| explained_variance | 0.678 | +| learning_rate | 4.3e-05 | +| loss | -0.0246 | +| n_updates | 73676 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000129 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1405 | +| iterations | 14466 | +| time_elapsed | 21081 | +| total_timesteps | 29626368 | +| train/ | | +| approx_kl | 0.0135524 | +| clip_fraction | 0.359 | +| clip_range | 0.0676 | +| entropy_loss | -6.45 | +| explained_variance | -0.249 | +| learning_rate | 4.3e-05 | +| loss | -0.0395 | +| n_updates | 73680 | +| policy_gradient_loss | -0.0212 | +| value_loss | 6.5e-05 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1405 | +| iterations | 14467 | +| time_elapsed | 21083 | +| total_timesteps | 29628416 | +| train/ | | +| approx_kl | 0.011970586 | +| clip_fraction | 0.322 | +| clip_range | 0.0676 | +| entropy_loss | -6.92 | +| explained_variance | 0.12 | +| learning_rate | 4.3e-05 | +| loss | -0.031 | +| n_updates | 73684 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000135 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1405 | +| iterations | 14468 | +| time_elapsed | 21084 | +| total_timesteps | 29630464 | +| train/ | | +| approx_kl | 0.011928012 | +| clip_fraction | 0.336 | +| clip_range | 0.0676 | +| entropy_loss | -7.04 | +| explained_variance | -0.0729 | +| learning_rate | 4.3e-05 | +| loss | -0.0273 | +| n_updates | 73688 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000213 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1405 | +| iterations | 14469 | +| time_elapsed | 21086 | +| total_timesteps | 29632512 | +| train/ | | +| approx_kl | 0.0146639105 | +| clip_fraction | 0.309 | +| clip_range | 0.0676 | +| entropy_loss | -6.36 | +| explained_variance | 0.35 | +| learning_rate | 4.3e-05 | +| loss | -0.0293 | +| n_updates | 73692 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000298 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1405 | +| iterations | 14470 | +| time_elapsed | 21087 | +| total_timesteps | 29634560 | +| train/ | | +| approx_kl | 0.010679778 | +| clip_fraction | 0.334 | +| clip_range | 0.0676 | +| entropy_loss | -5.97 | +| explained_variance | 0.409 | +| learning_rate | 4.3e-05 | +| loss | -0.0292 | +| n_updates | 73696 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000411 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1405 | +| iterations | 14471 | +| time_elapsed | 21089 | +| total_timesteps | 29636608 | +| train/ | | +| approx_kl | 0.013470679 | +| clip_fraction | 0.339 | +| clip_range | 0.0676 | +| entropy_loss | -5.69 | +| explained_variance | 0.47 | +| learning_rate | 4.3e-05 | +| loss | -0.0357 | +| n_updates | 73700 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000189 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1405 | +| iterations | 14472 | +| time_elapsed | 21090 | +| total_timesteps | 29638656 | +| train/ | | +| approx_kl | 0.013292899 | +| clip_fraction | 0.373 | +| clip_range | 0.0676 | +| entropy_loss | -6 | +| explained_variance | 0.6 | +| learning_rate | 4.3e-05 | +| loss | -0.0395 | +| n_updates | 73704 | +| policy_gradient_loss | -0.0228 | +| value_loss | 8.64e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1405 | +| iterations | 14473 | +| time_elapsed | 21092 | +| total_timesteps | 29640704 | +| train/ | | +| approx_kl | 0.014348073 | +| clip_fraction | 0.339 | +| clip_range | 0.0676 | +| entropy_loss | -6.38 | +| explained_variance | 0.223 | +| learning_rate | 4.3e-05 | +| loss | -0.0249 | +| n_updates | 73708 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000212 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1405 | +| iterations | 14474 | +| time_elapsed | 21093 | +| total_timesteps | 29642752 | +| train/ | | +| approx_kl | 0.012319086 | +| clip_fraction | 0.322 | +| clip_range | 0.0676 | +| entropy_loss | -6.28 | +| explained_variance | 0.518 | +| learning_rate | 4.3e-05 | +| loss | -0.0271 | +| n_updates | 73712 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000124 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1405 | +| iterations | 14475 | +| time_elapsed | 21095 | +| total_timesteps | 29644800 | +| train/ | | +| approx_kl | 0.015430737 | +| clip_fraction | 0.361 | +| clip_range | 0.0676 | +| entropy_loss | -6.38 | +| explained_variance | 0.55 | +| learning_rate | 4.3e-05 | +| loss | -0.0303 | +| n_updates | 73716 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000104 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1405 | +| iterations | 14476 | +| time_elapsed | 21096 | +| total_timesteps | 29646848 | +| train/ | | +| approx_kl | 0.011057135 | +| clip_fraction | 0.32 | +| clip_range | 0.0676 | +| entropy_loss | -6.44 | +| explained_variance | 0.535 | +| learning_rate | 4.3e-05 | +| loss | -0.0252 | +| n_updates | 73720 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000199 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1405 | +| iterations | 14477 | +| time_elapsed | 21098 | +| total_timesteps | 29648896 | +| train/ | | +| approx_kl | 0.013014523 | +| clip_fraction | 0.377 | +| clip_range | 0.0676 | +| entropy_loss | -6.57 | +| explained_variance | -0.117 | +| learning_rate | 4.3e-05 | +| loss | -0.0309 | +| n_updates | 73724 | +| policy_gradient_loss | -0.0233 | +| value_loss | 6.3e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1405 | +| iterations | 14478 | +| time_elapsed | 21100 | +| total_timesteps | 29650944 | +| train/ | | +| approx_kl | 0.0101101305 | +| clip_fraction | 0.31 | +| clip_range | 0.0676 | +| entropy_loss | -6.4 | +| explained_variance | 0.492 | +| learning_rate | 4.3e-05 | +| loss | -0.0249 | +| n_updates | 73728 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000197 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1405 | +| iterations | 14479 | +| time_elapsed | 21101 | +| total_timesteps | 29652992 | +| train/ | | +| approx_kl | 0.015644081 | +| clip_fraction | 0.317 | +| clip_range | 0.0676 | +| entropy_loss | -6.57 | +| explained_variance | 0.197 | +| learning_rate | 4.3e-05 | +| loss | -0.0271 | +| n_updates | 73732 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000122 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1405 | +| iterations | 14480 | +| time_elapsed | 21103 | +| total_timesteps | 29655040 | +| train/ | | +| approx_kl | 0.012590626 | +| clip_fraction | 0.345 | +| clip_range | 0.0676 | +| entropy_loss | -6.87 | +| explained_variance | 0.328 | +| learning_rate | 4.3e-05 | +| loss | -0.0337 | +| n_updates | 73736 | +| policy_gradient_loss | -0.0213 | +| value_loss | 8.8e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1405 | +| iterations | 14481 | +| time_elapsed | 21104 | +| total_timesteps | 29657088 | +| train/ | | +| approx_kl | 0.012604805 | +| clip_fraction | 0.319 | +| clip_range | 0.0676 | +| entropy_loss | -6.48 | +| explained_variance | 0.465 | +| learning_rate | 4.3e-05 | +| loss | -0.0273 | +| n_updates | 73740 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000266 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1405 | +| iterations | 14482 | +| time_elapsed | 21106 | +| total_timesteps | 29659136 | +| train/ | | +| approx_kl | 0.014968414 | +| clip_fraction | 0.362 | +| clip_range | 0.0676 | +| entropy_loss | -6.03 | +| explained_variance | 0.607 | +| learning_rate | 4.3e-05 | +| loss | -0.0376 | +| n_updates | 73744 | +| policy_gradient_loss | -0.0225 | +| value_loss | 7.19e-05 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1405 | +| iterations | 14483 | +| time_elapsed | 21107 | +| total_timesteps | 29661184 | +| train/ | | +| approx_kl | 0.0162282 | +| clip_fraction | 0.354 | +| clip_range | 0.0676 | +| entropy_loss | -6.4 | +| explained_variance | 0.13 | +| learning_rate | 4.3e-05 | +| loss | -0.0262 | +| n_updates | 73748 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000199 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1405 | +| iterations | 14484 | +| time_elapsed | 21109 | +| total_timesteps | 29663232 | +| train/ | | +| approx_kl | 0.013008838 | +| clip_fraction | 0.355 | +| clip_range | 0.0676 | +| entropy_loss | -6.57 | +| explained_variance | 0.574 | +| learning_rate | 4.3e-05 | +| loss | -0.0332 | +| n_updates | 73752 | +| policy_gradient_loss | -0.0192 | +| value_loss | 9.91e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1405 | +| iterations | 14485 | +| time_elapsed | 21110 | +| total_timesteps | 29665280 | +| train/ | | +| approx_kl | 0.011543052 | +| clip_fraction | 0.346 | +| clip_range | 0.0676 | +| entropy_loss | -6.34 | +| explained_variance | 0.464 | +| learning_rate | 4.3e-05 | +| loss | -0.0324 | +| n_updates | 73756 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000143 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1405 | +| iterations | 14486 | +| time_elapsed | 21112 | +| total_timesteps | 29667328 | +| train/ | | +| approx_kl | 0.010933064 | +| clip_fraction | 0.307 | +| clip_range | 0.0676 | +| entropy_loss | -5.77 | +| explained_variance | 0.317 | +| learning_rate | 4.3e-05 | +| loss | -0.0214 | +| n_updates | 73760 | +| policy_gradient_loss | -0.0142 | +| value_loss | 0.000465 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1405 | +| iterations | 14487 | +| time_elapsed | 21113 | +| total_timesteps | 29669376 | +| train/ | | +| approx_kl | 0.014295479 | +| clip_fraction | 0.333 | +| clip_range | 0.0676 | +| entropy_loss | -5.87 | +| explained_variance | 0.457 | +| learning_rate | 4.3e-05 | +| loss | -0.029 | +| n_updates | 73764 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000177 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1405 | +| iterations | 14488 | +| time_elapsed | 21115 | +| total_timesteps | 29671424 | +| train/ | | +| approx_kl | 0.013839159 | +| clip_fraction | 0.368 | +| clip_range | 0.0676 | +| entropy_loss | -6.73 | +| explained_variance | -0.153 | +| learning_rate | 4.3e-05 | +| loss | -0.0329 | +| n_updates | 73768 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000104 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1405 | +| iterations | 14489 | +| time_elapsed | 21116 | +| total_timesteps | 29673472 | +| train/ | | +| approx_kl | 0.01261268 | +| clip_fraction | 0.339 | +| clip_range | 0.0676 | +| entropy_loss | -6.53 | +| explained_variance | 0.515 | +| learning_rate | 4.3e-05 | +| loss | -0.0334 | +| n_updates | 73772 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.00014 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1405 | +| iterations | 14490 | +| time_elapsed | 21118 | +| total_timesteps | 29675520 | +| train/ | | +| approx_kl | 0.010964936 | +| clip_fraction | 0.313 | +| clip_range | 0.0676 | +| entropy_loss | -6.03 | +| explained_variance | 0.443 | +| learning_rate | 4.3e-05 | +| loss | -0.0227 | +| n_updates | 73776 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000193 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1405 | +| iterations | 14491 | +| time_elapsed | 21119 | +| total_timesteps | 29677568 | +| train/ | | +| approx_kl | 0.010762169 | +| clip_fraction | 0.348 | +| clip_range | 0.0676 | +| entropy_loss | -6.61 | +| explained_variance | 0.177 | +| learning_rate | 4.3e-05 | +| loss | -0.0292 | +| n_updates | 73780 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000116 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1405 | +| iterations | 14492 | +| time_elapsed | 21121 | +| total_timesteps | 29679616 | +| train/ | | +| approx_kl | 0.014884608 | +| clip_fraction | 0.371 | +| clip_range | 0.0676 | +| entropy_loss | -6.86 | +| explained_variance | -0.0742 | +| learning_rate | 4.3e-05 | +| loss | -0.0281 | +| n_updates | 73784 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000134 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1405 | +| iterations | 14493 | +| time_elapsed | 21123 | +| total_timesteps | 29681664 | +| train/ | | +| approx_kl | 0.012338787 | +| clip_fraction | 0.318 | +| clip_range | 0.0676 | +| entropy_loss | -5.9 | +| explained_variance | 0.543 | +| learning_rate | 4.3e-05 | +| loss | -0.0237 | +| n_updates | 73788 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.000252 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1405 | +| iterations | 14494 | +| time_elapsed | 21124 | +| total_timesteps | 29683712 | +| train/ | | +| approx_kl | 0.013023842 | +| clip_fraction | 0.332 | +| clip_range | 0.0676 | +| entropy_loss | -6.3 | +| explained_variance | -0.151 | +| learning_rate | 4.3e-05 | +| loss | -0.0293 | +| n_updates | 73792 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000118 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1405 | +| iterations | 14495 | +| time_elapsed | 21126 | +| total_timesteps | 29685760 | +| train/ | | +| approx_kl | 0.010926869 | +| clip_fraction | 0.337 | +| clip_range | 0.0676 | +| entropy_loss | -6.19 | +| explained_variance | 0.364 | +| learning_rate | 4.3e-05 | +| loss | -0.0279 | +| n_updates | 73796 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000162 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1405 | +| iterations | 14496 | +| time_elapsed | 21127 | +| total_timesteps | 29687808 | +| train/ | | +| approx_kl | 0.01574263 | +| clip_fraction | 0.364 | +| clip_range | 0.0676 | +| entropy_loss | -5.92 | +| explained_variance | 0.59 | +| learning_rate | 4.29e-05 | +| loss | -0.0279 | +| n_updates | 73800 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000111 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1405 | +| iterations | 14497 | +| time_elapsed | 21129 | +| total_timesteps | 29689856 | +| train/ | | +| approx_kl | 0.011623335 | +| clip_fraction | 0.322 | +| clip_range | 0.0676 | +| entropy_loss | -6.26 | +| explained_variance | 0.232 | +| learning_rate | 4.29e-05 | +| loss | -0.0255 | +| n_updates | 73804 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000463 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1405 | +| iterations | 14498 | +| time_elapsed | 21130 | +| total_timesteps | 29691904 | +| train/ | | +| approx_kl | 0.013743224 | +| clip_fraction | 0.328 | +| clip_range | 0.0676 | +| entropy_loss | -5.94 | +| explained_variance | 0.388 | +| learning_rate | 4.29e-05 | +| loss | -0.0333 | +| n_updates | 73808 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.00022 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1405 | +| iterations | 14499 | +| time_elapsed | 21132 | +| total_timesteps | 29693952 | +| train/ | | +| approx_kl | 0.01506785 | +| clip_fraction | 0.361 | +| clip_range | 0.0676 | +| entropy_loss | -6.49 | +| explained_variance | 0.134 | +| learning_rate | 4.29e-05 | +| loss | -0.0342 | +| n_updates | 73812 | +| policy_gradient_loss | -0.0229 | +| value_loss | 0.000197 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1405 | +| iterations | 14500 | +| time_elapsed | 21133 | +| total_timesteps | 29696000 | +| train/ | | +| approx_kl | 0.013631591 | +| clip_fraction | 0.372 | +| clip_range | 0.0676 | +| entropy_loss | -6.3 | +| explained_variance | 0.447 | +| learning_rate | 4.29e-05 | +| loss | -0.0297 | +| n_updates | 73816 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000105 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1405 | +| iterations | 14501 | +| time_elapsed | 21135 | +| total_timesteps | 29698048 | +| train/ | | +| approx_kl | 0.013679378 | +| clip_fraction | 0.364 | +| clip_range | 0.0676 | +| entropy_loss | -6.4 | +| explained_variance | 0.637 | +| learning_rate | 4.29e-05 | +| loss | -0.0321 | +| n_updates | 73820 | +| policy_gradient_loss | -0.0226 | +| value_loss | 7.03e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1405 | +| iterations | 14502 | +| time_elapsed | 21136 | +| total_timesteps | 29700096 | +| train/ | | +| approx_kl | 0.014938867 | +| clip_fraction | 0.386 | +| clip_range | 0.0676 | +| entropy_loss | -6.45 | +| explained_variance | 0.52 | +| learning_rate | 4.29e-05 | +| loss | -0.0364 | +| n_updates | 73824 | +| policy_gradient_loss | -0.0236 | +| value_loss | 5.53e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1405 | +| iterations | 14503 | +| time_elapsed | 21138 | +| total_timesteps | 29702144 | +| train/ | | +| approx_kl | 0.012867789 | +| clip_fraction | 0.324 | +| clip_range | 0.0676 | +| entropy_loss | -6.08 | +| explained_variance | 0.332 | +| learning_rate | 4.29e-05 | +| loss | -0.0251 | +| n_updates | 73828 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000258 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1405 | +| iterations | 14504 | +| time_elapsed | 21140 | +| total_timesteps | 29704192 | +| train/ | | +| approx_kl | 0.015032813 | +| clip_fraction | 0.332 | +| clip_range | 0.0676 | +| entropy_loss | -6 | +| explained_variance | 0.344 | +| learning_rate | 4.29e-05 | +| loss | -0.0306 | +| n_updates | 73832 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000205 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1405 | +| iterations | 14505 | +| time_elapsed | 21141 | +| total_timesteps | 29706240 | +| train/ | | +| approx_kl | 0.013345367 | +| clip_fraction | 0.343 | +| clip_range | 0.0676 | +| entropy_loss | -6.88 | +| explained_variance | -0.106 | +| learning_rate | 4.29e-05 | +| loss | -0.0287 | +| n_updates | 73836 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000143 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1405 | +| iterations | 14506 | +| time_elapsed | 21143 | +| total_timesteps | 29708288 | +| train/ | | +| approx_kl | 0.014782331 | +| clip_fraction | 0.352 | +| clip_range | 0.0676 | +| entropy_loss | -6.6 | +| explained_variance | 0.453 | +| learning_rate | 4.29e-05 | +| loss | -0.0269 | +| n_updates | 73840 | +| policy_gradient_loss | -0.0195 | +| value_loss | 8.47e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1405 | +| iterations | 14507 | +| time_elapsed | 21144 | +| total_timesteps | 29710336 | +| train/ | | +| approx_kl | 0.010338951 | +| clip_fraction | 0.319 | +| clip_range | 0.0676 | +| entropy_loss | -6.76 | +| explained_variance | 0.304 | +| learning_rate | 4.29e-05 | +| loss | -0.0239 | +| n_updates | 73844 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000171 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1405 | +| iterations | 14508 | +| time_elapsed | 21146 | +| total_timesteps | 29712384 | +| train/ | | +| approx_kl | 0.012709323 | +| clip_fraction | 0.297 | +| clip_range | 0.0676 | +| entropy_loss | -5.75 | +| explained_variance | 0.443 | +| learning_rate | 4.29e-05 | +| loss | -0.0181 | +| n_updates | 73848 | +| policy_gradient_loss | -0.0126 | +| value_loss | 0.000327 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1405 | +| iterations | 14509 | +| time_elapsed | 21147 | +| total_timesteps | 29714432 | +| train/ | | +| approx_kl | 0.011931564 | +| clip_fraction | 0.359 | +| clip_range | 0.0676 | +| entropy_loss | -5.42 | +| explained_variance | 0.747 | +| learning_rate | 4.29e-05 | +| loss | -0.0324 | +| n_updates | 73852 | +| policy_gradient_loss | -0.0204 | +| value_loss | 8.82e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1405 | +| iterations | 14510 | +| time_elapsed | 21149 | +| total_timesteps | 29716480 | +| train/ | | +| approx_kl | 0.013001934 | +| clip_fraction | 0.341 | +| clip_range | 0.0676 | +| entropy_loss | -6.56 | +| explained_variance | 0.181 | +| learning_rate | 4.29e-05 | +| loss | -0.0329 | +| n_updates | 73856 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000212 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1405 | +| iterations | 14511 | +| time_elapsed | 21150 | +| total_timesteps | 29718528 | +| train/ | | +| approx_kl | 0.011643624 | +| clip_fraction | 0.32 | +| clip_range | 0.0676 | +| entropy_loss | -6.37 | +| explained_variance | 0.429 | +| learning_rate | 4.29e-05 | +| loss | -0.0255 | +| n_updates | 73860 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000189 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1405 | +| iterations | 14512 | +| time_elapsed | 21152 | +| total_timesteps | 29720576 | +| train/ | | +| approx_kl | 0.013081387 | +| clip_fraction | 0.353 | +| clip_range | 0.0676 | +| entropy_loss | -6.27 | +| explained_variance | 0.301 | +| learning_rate | 4.29e-05 | +| loss | -0.0297 | +| n_updates | 73864 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000134 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1405 | +| iterations | 14513 | +| time_elapsed | 21153 | +| total_timesteps | 29722624 | +| train/ | | +| approx_kl | 0.013508966 | +| clip_fraction | 0.361 | +| clip_range | 0.0676 | +| entropy_loss | -6.65 | +| explained_variance | -0.27 | +| learning_rate | 4.29e-05 | +| loss | -0.034 | +| n_updates | 73868 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000117 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1405 | +| iterations | 14514 | +| time_elapsed | 21155 | +| total_timesteps | 29724672 | +| train/ | | +| approx_kl | 0.011885574 | +| clip_fraction | 0.338 | +| clip_range | 0.0676 | +| entropy_loss | -6.58 | +| explained_variance | 0.155 | +| learning_rate | 4.29e-05 | +| loss | -0.0279 | +| n_updates | 73872 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000204 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1405 | +| iterations | 14515 | +| time_elapsed | 21156 | +| total_timesteps | 29726720 | +| train/ | | +| approx_kl | 0.010264748 | +| clip_fraction | 0.334 | +| clip_range | 0.0676 | +| entropy_loss | -6.23 | +| explained_variance | 0.566 | +| learning_rate | 4.29e-05 | +| loss | -0.0309 | +| n_updates | 73876 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000118 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1405 | +| iterations | 14516 | +| time_elapsed | 21158 | +| total_timesteps | 29728768 | +| train/ | | +| approx_kl | 0.011804033 | +| clip_fraction | 0.307 | +| clip_range | 0.0676 | +| entropy_loss | -5.37 | +| explained_variance | 0.656 | +| learning_rate | 4.29e-05 | +| loss | -0.0216 | +| n_updates | 73880 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000182 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1405 | +| iterations | 14517 | +| time_elapsed | 21160 | +| total_timesteps | 29730816 | +| train/ | | +| approx_kl | 0.009593504 | +| clip_fraction | 0.314 | +| clip_range | 0.0676 | +| entropy_loss | -6.1 | +| explained_variance | 0.44 | +| learning_rate | 4.29e-05 | +| loss | -0.0262 | +| n_updates | 73884 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000211 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1405 | +| iterations | 14518 | +| time_elapsed | 21161 | +| total_timesteps | 29732864 | +| train/ | | +| approx_kl | 0.012710545 | +| clip_fraction | 0.318 | +| clip_range | 0.0676 | +| entropy_loss | -6.58 | +| explained_variance | 0.245 | +| learning_rate | 4.29e-05 | +| loss | -0.0302 | +| n_updates | 73888 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000284 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1405 | +| iterations | 14519 | +| time_elapsed | 21163 | +| total_timesteps | 29734912 | +| train/ | | +| approx_kl | 0.01217284 | +| clip_fraction | 0.348 | +| clip_range | 0.0676 | +| entropy_loss | -6.22 | +| explained_variance | 0.27 | +| learning_rate | 4.29e-05 | +| loss | -0.0248 | +| n_updates | 73892 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000197 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1405 | +| iterations | 14520 | +| time_elapsed | 21164 | +| total_timesteps | 29736960 | +| train/ | | +| approx_kl | 0.014536547 | +| clip_fraction | 0.35 | +| clip_range | 0.0676 | +| entropy_loss | -6.87 | +| explained_variance | 0.0737 | +| learning_rate | 4.29e-05 | +| loss | -0.0334 | +| n_updates | 73896 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000137 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1405 | +| iterations | 14521 | +| time_elapsed | 21166 | +| total_timesteps | 29739008 | +| train/ | | +| approx_kl | 0.014056139 | +| clip_fraction | 0.337 | +| clip_range | 0.0676 | +| entropy_loss | -6.8 | +| explained_variance | 0.252 | +| learning_rate | 4.29e-05 | +| loss | -0.0324 | +| n_updates | 73900 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000147 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1405 | +| iterations | 14522 | +| time_elapsed | 21167 | +| total_timesteps | 29741056 | +| train/ | | +| approx_kl | 0.013981286 | +| clip_fraction | 0.344 | +| clip_range | 0.0676 | +| entropy_loss | -6.67 | +| explained_variance | 0.576 | +| learning_rate | 4.29e-05 | +| loss | -0.0335 | +| n_updates | 73904 | +| policy_gradient_loss | -0.0209 | +| value_loss | 7.62e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1405 | +| iterations | 14523 | +| time_elapsed | 21169 | +| total_timesteps | 29743104 | +| train/ | | +| approx_kl | 0.013368603 | +| clip_fraction | 0.318 | +| clip_range | 0.0676 | +| entropy_loss | -6.5 | +| explained_variance | 0.365 | +| learning_rate | 4.29e-05 | +| loss | -0.0198 | +| n_updates | 73908 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000245 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1405 | +| iterations | 14524 | +| time_elapsed | 21170 | +| total_timesteps | 29745152 | +| train/ | | +| approx_kl | 0.012656515 | +| clip_fraction | 0.338 | +| clip_range | 0.0676 | +| entropy_loss | -5.95 | +| explained_variance | 0.431 | +| learning_rate | 4.29e-05 | +| loss | -0.026 | +| n_updates | 73912 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000218 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1404 | +| iterations | 14525 | +| time_elapsed | 21172 | +| total_timesteps | 29747200 | +| train/ | | +| approx_kl | 0.011008835 | +| clip_fraction | 0.293 | +| clip_range | 0.0676 | +| entropy_loss | -6.07 | +| explained_variance | 0.38 | +| learning_rate | 4.29e-05 | +| loss | -0.0231 | +| n_updates | 73916 | +| policy_gradient_loss | -0.0136 | +| value_loss | 0.000379 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1404 | +| iterations | 14526 | +| time_elapsed | 21173 | +| total_timesteps | 29749248 | +| train/ | | +| approx_kl | 0.011811662 | +| clip_fraction | 0.335 | +| clip_range | 0.0676 | +| entropy_loss | -6.07 | +| explained_variance | 0.532 | +| learning_rate | 4.29e-05 | +| loss | -0.0274 | +| n_updates | 73920 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000142 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1404 | +| iterations | 14527 | +| time_elapsed | 21175 | +| total_timesteps | 29751296 | +| train/ | | +| approx_kl | 0.013494987 | +| clip_fraction | 0.34 | +| clip_range | 0.0676 | +| entropy_loss | -6.38 | +| explained_variance | 0.259 | +| learning_rate | 4.29e-05 | +| loss | -0.0303 | +| n_updates | 73924 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000138 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1404 | +| iterations | 14528 | +| time_elapsed | 21177 | +| total_timesteps | 29753344 | +| train/ | | +| approx_kl | 0.01060874 | +| clip_fraction | 0.336 | +| clip_range | 0.0676 | +| entropy_loss | -6.57 | +| explained_variance | 0.405 | +| learning_rate | 4.29e-05 | +| loss | -0.0312 | +| n_updates | 73928 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000265 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1404 | +| iterations | 14529 | +| time_elapsed | 21178 | +| total_timesteps | 29755392 | +| train/ | | +| approx_kl | 0.013117474 | +| clip_fraction | 0.316 | +| clip_range | 0.0676 | +| entropy_loss | -6.47 | +| explained_variance | -0.069 | +| learning_rate | 4.29e-05 | +| loss | -0.0297 | +| n_updates | 73932 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.00021 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1404 | +| iterations | 14530 | +| time_elapsed | 21180 | +| total_timesteps | 29757440 | +| train/ | | +| approx_kl | 0.012118037 | +| clip_fraction | 0.358 | +| clip_range | 0.0676 | +| entropy_loss | -6.38 | +| explained_variance | 0.343 | +| learning_rate | 4.29e-05 | +| loss | -0.0302 | +| n_updates | 73936 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000125 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1404 | +| iterations | 14531 | +| time_elapsed | 21181 | +| total_timesteps | 29759488 | +| train/ | | +| approx_kl | 0.014397645 | +| clip_fraction | 0.328 | +| clip_range | 0.0676 | +| entropy_loss | -6.22 | +| explained_variance | 0.242 | +| learning_rate | 4.29e-05 | +| loss | -0.0232 | +| n_updates | 73940 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000404 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1404 | +| iterations | 14532 | +| time_elapsed | 21183 | +| total_timesteps | 29761536 | +| train/ | | +| approx_kl | 0.014879207 | +| clip_fraction | 0.356 | +| clip_range | 0.0676 | +| entropy_loss | -5.84 | +| explained_variance | 0.342 | +| learning_rate | 4.29e-05 | +| loss | -0.0268 | +| n_updates | 73944 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000225 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1404 | +| iterations | 14533 | +| time_elapsed | 21184 | +| total_timesteps | 29763584 | +| train/ | | +| approx_kl | 0.013467019 | +| clip_fraction | 0.35 | +| clip_range | 0.0676 | +| entropy_loss | -6.41 | +| explained_variance | 0.362 | +| learning_rate | 4.29e-05 | +| loss | -0.0342 | +| n_updates | 73948 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000133 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1404 | +| iterations | 14534 | +| time_elapsed | 21186 | +| total_timesteps | 29765632 | +| train/ | | +| approx_kl | 0.014249155 | +| clip_fraction | 0.319 | +| clip_range | 0.0676 | +| entropy_loss | -5.96 | +| explained_variance | 0.642 | +| learning_rate | 4.29e-05 | +| loss | -0.0307 | +| n_updates | 73952 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000141 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1404 | +| iterations | 14535 | +| time_elapsed | 21187 | +| total_timesteps | 29767680 | +| train/ | | +| approx_kl | 0.011539235 | +| clip_fraction | 0.32 | +| clip_range | 0.0676 | +| entropy_loss | -5.76 | +| explained_variance | 0.402 | +| learning_rate | 4.29e-05 | +| loss | -0.0218 | +| n_updates | 73956 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000335 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1404 | +| iterations | 14536 | +| time_elapsed | 21189 | +| total_timesteps | 29769728 | +| train/ | | +| approx_kl | 0.0106961895 | +| clip_fraction | 0.308 | +| clip_range | 0.0676 | +| entropy_loss | -6.21 | +| explained_variance | 0.438 | +| learning_rate | 4.29e-05 | +| loss | -0.0298 | +| n_updates | 73960 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000237 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1404 | +| iterations | 14537 | +| time_elapsed | 21190 | +| total_timesteps | 29771776 | +| train/ | | +| approx_kl | 0.013210486 | +| clip_fraction | 0.33 | +| clip_range | 0.0676 | +| entropy_loss | -6.61 | +| explained_variance | 0.145 | +| learning_rate | 4.29e-05 | +| loss | -0.0286 | +| n_updates | 73964 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000239 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1404 | +| iterations | 14538 | +| time_elapsed | 21192 | +| total_timesteps | 29773824 | +| train/ | | +| approx_kl | 0.010538432 | +| clip_fraction | 0.352 | +| clip_range | 0.0676 | +| entropy_loss | -7.03 | +| explained_variance | 0.0116 | +| learning_rate | 4.29e-05 | +| loss | -0.0318 | +| n_updates | 73968 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000249 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1404 | +| iterations | 14539 | +| time_elapsed | 21193 | +| total_timesteps | 29775872 | +| train/ | | +| approx_kl | 0.009361676 | +| clip_fraction | 0.318 | +| clip_range | 0.0676 | +| entropy_loss | -6.82 | +| explained_variance | 0.239 | +| learning_rate | 4.29e-05 | +| loss | -0.0337 | +| n_updates | 73972 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000132 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1404 | +| iterations | 14540 | +| time_elapsed | 21195 | +| total_timesteps | 29777920 | +| train/ | | +| approx_kl | 0.011290662 | +| clip_fraction | 0.315 | +| clip_range | 0.0676 | +| entropy_loss | -6.23 | +| explained_variance | 0.379 | +| learning_rate | 4.29e-05 | +| loss | -0.0225 | +| n_updates | 73976 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.00025 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1404 | +| iterations | 14541 | +| time_elapsed | 21196 | +| total_timesteps | 29779968 | +| train/ | | +| approx_kl | 0.01052776 | +| clip_fraction | 0.31 | +| clip_range | 0.0676 | +| entropy_loss | -6.14 | +| explained_variance | 0.316 | +| learning_rate | 4.29e-05 | +| loss | -0.0214 | +| n_updates | 73980 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000334 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1404 | +| iterations | 14542 | +| time_elapsed | 21198 | +| total_timesteps | 29782016 | +| train/ | | +| approx_kl | 0.009910919 | +| clip_fraction | 0.329 | +| clip_range | 0.0676 | +| entropy_loss | -6.04 | +| explained_variance | 0.483 | +| learning_rate | 4.29e-05 | +| loss | -0.026 | +| n_updates | 73984 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000295 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1404 | +| iterations | 14543 | +| time_elapsed | 21199 | +| total_timesteps | 29784064 | +| train/ | | +| approx_kl | 0.010880075 | +| clip_fraction | 0.334 | +| clip_range | 0.0676 | +| entropy_loss | -6.17 | +| explained_variance | 0.381 | +| learning_rate | 4.29e-05 | +| loss | -0.0353 | +| n_updates | 73988 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000179 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1404 | +| iterations | 14544 | +| time_elapsed | 21201 | +| total_timesteps | 29786112 | +| train/ | | +| approx_kl | 0.0151638035 | +| clip_fraction | 0.355 | +| clip_range | 0.0676 | +| entropy_loss | -6.43 | +| explained_variance | 0.295 | +| learning_rate | 4.29e-05 | +| loss | -0.0352 | +| n_updates | 73992 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000134 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1404 | +| iterations | 14545 | +| time_elapsed | 21202 | +| total_timesteps | 29788160 | +| train/ | | +| approx_kl | 0.013353308 | +| clip_fraction | 0.328 | +| clip_range | 0.0676 | +| entropy_loss | -6.5 | +| explained_variance | 0.35 | +| learning_rate | 4.29e-05 | +| loss | -0.0335 | +| n_updates | 73996 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000187 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1404 | +| iterations | 14546 | +| time_elapsed | 21204 | +| total_timesteps | 29790208 | +| train/ | | +| approx_kl | 0.011012348 | +| clip_fraction | 0.307 | +| clip_range | 0.0676 | +| entropy_loss | -5.93 | +| explained_variance | 0.661 | +| learning_rate | 4.29e-05 | +| loss | -0.0247 | +| n_updates | 74000 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000151 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1404 | +| iterations | 14547 | +| time_elapsed | 21205 | +| total_timesteps | 29792256 | +| train/ | | +| approx_kl | 0.013919572 | +| clip_fraction | 0.342 | +| clip_range | 0.0676 | +| entropy_loss | -5.88 | +| explained_variance | 0.54 | +| learning_rate | 4.29e-05 | +| loss | -0.0297 | +| n_updates | 74004 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000144 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1404 | +| iterations | 14548 | +| time_elapsed | 21207 | +| total_timesteps | 29794304 | +| train/ | | +| approx_kl | 0.014389536 | +| clip_fraction | 0.361 | +| clip_range | 0.0676 | +| entropy_loss | -6.39 | +| explained_variance | 0.317 | +| learning_rate | 4.29e-05 | +| loss | -0.0331 | +| n_updates | 74008 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000211 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1404 | +| iterations | 14549 | +| time_elapsed | 21209 | +| total_timesteps | 29796352 | +| train/ | | +| approx_kl | 0.0112636015 | +| clip_fraction | 0.302 | +| clip_range | 0.0676 | +| entropy_loss | -6.11 | +| explained_variance | 0.404 | +| learning_rate | 4.29e-05 | +| loss | -0.0256 | +| n_updates | 74012 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.000354 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1404 | +| iterations | 14550 | +| time_elapsed | 21210 | +| total_timesteps | 29798400 | +| train/ | | +| approx_kl | 0.011217851 | +| clip_fraction | 0.31 | +| clip_range | 0.0676 | +| entropy_loss | -6.26 | +| explained_variance | 0.528 | +| learning_rate | 4.29e-05 | +| loss | -0.0301 | +| n_updates | 74016 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000154 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1404 | +| iterations | 14551 | +| time_elapsed | 21212 | +| total_timesteps | 29800448 | +| train/ | | +| approx_kl | 0.01094529 | +| clip_fraction | 0.324 | +| clip_range | 0.0676 | +| entropy_loss | -6.31 | +| explained_variance | 0.16 | +| learning_rate | 4.29e-05 | +| loss | -0.0317 | +| n_updates | 74020 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000356 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1404 | +| iterations | 14552 | +| time_elapsed | 21213 | +| total_timesteps | 29802496 | +| train/ | | +| approx_kl | 0.015000334 | +| clip_fraction | 0.349 | +| clip_range | 0.0675 | +| entropy_loss | -6.06 | +| explained_variance | 0.398 | +| learning_rate | 4.29e-05 | +| loss | -0.0333 | +| n_updates | 74024 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.0002 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1404 | +| iterations | 14553 | +| time_elapsed | 21215 | +| total_timesteps | 29804544 | +| train/ | | +| approx_kl | 0.014344465 | +| clip_fraction | 0.364 | +| clip_range | 0.0675 | +| entropy_loss | -6.5 | +| explained_variance | 0.289 | +| learning_rate | 4.29e-05 | +| loss | -0.0422 | +| n_updates | 74028 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000134 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1404 | +| iterations | 14554 | +| time_elapsed | 21216 | +| total_timesteps | 29806592 | +| train/ | | +| approx_kl | 0.011562638 | +| clip_fraction | 0.318 | +| clip_range | 0.0675 | +| entropy_loss | -6.76 | +| explained_variance | 0.141 | +| learning_rate | 4.29e-05 | +| loss | -0.0294 | +| n_updates | 74032 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000221 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.386 | +| time/ | | +| fps | 1404 | +| iterations | 14555 | +| time_elapsed | 21218 | +| total_timesteps | 29808640 | +| train/ | | +| approx_kl | 0.011143797 | +| clip_fraction | 0.309 | +| clip_range | 0.0675 | +| entropy_loss | -6.4 | +| explained_variance | 0.312 | +| learning_rate | 4.29e-05 | +| loss | -0.023 | +| n_updates | 74036 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000382 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.388 | +| time/ | | +| fps | 1404 | +| iterations | 14556 | +| time_elapsed | 21219 | +| total_timesteps | 29810688 | +| train/ | | +| approx_kl | 0.015799537 | +| clip_fraction | 0.319 | +| clip_range | 0.0675 | +| entropy_loss | -5.64 | +| explained_variance | 0.344 | +| learning_rate | 4.29e-05 | +| loss | -0.0281 | +| n_updates | 74040 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.00035 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.388 | +| time/ | | +| fps | 1404 | +| iterations | 14557 | +| time_elapsed | 21221 | +| total_timesteps | 29812736 | +| train/ | | +| approx_kl | 0.013130423 | +| clip_fraction | 0.333 | +| clip_range | 0.0675 | +| entropy_loss | -5.97 | +| explained_variance | 0.387 | +| learning_rate | 4.29e-05 | +| loss | -0.0321 | +| n_updates | 74044 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.00033 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.386 | +| time/ | | +| fps | 1404 | +| iterations | 14558 | +| time_elapsed | 21222 | +| total_timesteps | 29814784 | +| train/ | | +| approx_kl | 0.012404703 | +| clip_fraction | 0.357 | +| clip_range | 0.0675 | +| entropy_loss | -6.85 | +| explained_variance | -0.307 | +| learning_rate | 4.29e-05 | +| loss | -0.0374 | +| n_updates | 74048 | +| policy_gradient_loss | -0.0232 | +| value_loss | 8.4e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.386 | +| time/ | | +| fps | 1404 | +| iterations | 14559 | +| time_elapsed | 21224 | +| total_timesteps | 29816832 | +| train/ | | +| approx_kl | 0.012016302 | +| clip_fraction | 0.336 | +| clip_range | 0.0675 | +| entropy_loss | -6.75 | +| explained_variance | 0.417 | +| learning_rate | 4.29e-05 | +| loss | -0.0307 | +| n_updates | 74052 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000207 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1404 | +| iterations | 14560 | +| time_elapsed | 21225 | +| total_timesteps | 29818880 | +| train/ | | +| approx_kl | 0.01498603 | +| clip_fraction | 0.328 | +| clip_range | 0.0675 | +| entropy_loss | -5.68 | +| explained_variance | 0.58 | +| learning_rate | 4.29e-05 | +| loss | -0.0274 | +| n_updates | 74056 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000164 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1404 | +| iterations | 14561 | +| time_elapsed | 21227 | +| total_timesteps | 29820928 | +| train/ | | +| approx_kl | 0.014545698 | +| clip_fraction | 0.363 | +| clip_range | 0.0675 | +| entropy_loss | -5.93 | +| explained_variance | 0.602 | +| learning_rate | 4.29e-05 | +| loss | -0.0387 | +| n_updates | 74060 | +| policy_gradient_loss | -0.0225 | +| value_loss | 7.89e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1404 | +| iterations | 14562 | +| time_elapsed | 21228 | +| total_timesteps | 29822976 | +| train/ | | +| approx_kl | 0.014108205 | +| clip_fraction | 0.332 | +| clip_range | 0.0675 | +| entropy_loss | -6.65 | +| explained_variance | 0.379 | +| learning_rate | 4.29e-05 | +| loss | -0.0263 | +| n_updates | 74064 | +| policy_gradient_loss | -0.0182 | +| value_loss | 8.31e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1404 | +| iterations | 14563 | +| time_elapsed | 21230 | +| total_timesteps | 29825024 | +| train/ | | +| approx_kl | 0.012574699 | +| clip_fraction | 0.347 | +| clip_range | 0.0675 | +| entropy_loss | -6.47 | +| explained_variance | 0.326 | +| learning_rate | 4.29e-05 | +| loss | -0.0303 | +| n_updates | 74068 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1404 | +| iterations | 14564 | +| time_elapsed | 21231 | +| total_timesteps | 29827072 | +| train/ | | +| approx_kl | 0.012489895 | +| clip_fraction | 0.333 | +| clip_range | 0.0675 | +| entropy_loss | -6.48 | +| explained_variance | 0.285 | +| learning_rate | 4.29e-05 | +| loss | -0.0312 | +| n_updates | 74072 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000184 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1404 | +| iterations | 14565 | +| time_elapsed | 21233 | +| total_timesteps | 29829120 | +| train/ | | +| approx_kl | 0.014290286 | +| clip_fraction | 0.363 | +| clip_range | 0.0675 | +| entropy_loss | -6.02 | +| explained_variance | 0.654 | +| learning_rate | 4.29e-05 | +| loss | -0.0367 | +| n_updates | 74076 | +| policy_gradient_loss | -0.0228 | +| value_loss | 5.73e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1404 | +| iterations | 14566 | +| time_elapsed | 21234 | +| total_timesteps | 29831168 | +| train/ | | +| approx_kl | 0.015450345 | +| clip_fraction | 0.339 | +| clip_range | 0.0675 | +| entropy_loss | -6.09 | +| explained_variance | 0.65 | +| learning_rate | 4.29e-05 | +| loss | -0.0308 | +| n_updates | 74080 | +| policy_gradient_loss | -0.0197 | +| value_loss | 7.85e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1404 | +| iterations | 14567 | +| time_elapsed | 21236 | +| total_timesteps | 29833216 | +| train/ | | +| approx_kl | 0.015770286 | +| clip_fraction | 0.367 | +| clip_range | 0.0675 | +| entropy_loss | -6.38 | +| explained_variance | -0.0289 | +| learning_rate | 4.29e-05 | +| loss | -0.0277 | +| n_updates | 74084 | +| policy_gradient_loss | -0.0213 | +| value_loss | 6.37e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1404 | +| iterations | 14568 | +| time_elapsed | 21237 | +| total_timesteps | 29835264 | +| train/ | | +| approx_kl | 0.019254237 | +| clip_fraction | 0.305 | +| clip_range | 0.0675 | +| entropy_loss | -5.97 | +| explained_variance | 0.672 | +| learning_rate | 4.29e-05 | +| loss | -0.0254 | +| n_updates | 74088 | +| policy_gradient_loss | -0.0169 | +| value_loss | 9.9e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1404 | +| iterations | 14569 | +| time_elapsed | 21239 | +| total_timesteps | 29837312 | +| train/ | | +| approx_kl | 0.01488742 | +| clip_fraction | 0.331 | +| clip_range | 0.0675 | +| entropy_loss | -6.09 | +| explained_variance | 0.486 | +| learning_rate | 4.29e-05 | +| loss | -0.0285 | +| n_updates | 74092 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000173 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1404 | +| iterations | 14570 | +| time_elapsed | 21240 | +| total_timesteps | 29839360 | +| train/ | | +| approx_kl | 0.0113388095 | +| clip_fraction | 0.317 | +| clip_range | 0.0675 | +| entropy_loss | -5.86 | +| explained_variance | 0.63 | +| learning_rate | 4.29e-05 | +| loss | -0.0257 | +| n_updates | 74096 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000127 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1404 | +| iterations | 14571 | +| time_elapsed | 21242 | +| total_timesteps | 29841408 | +| train/ | | +| approx_kl | 0.011852382 | +| clip_fraction | 0.305 | +| clip_range | 0.0675 | +| entropy_loss | -6.69 | +| explained_variance | 0.405 | +| learning_rate | 4.29e-05 | +| loss | -0.0284 | +| n_updates | 74100 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.00019 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1404 | +| iterations | 14572 | +| time_elapsed | 21244 | +| total_timesteps | 29843456 | +| train/ | | +| approx_kl | 0.0106089525 | +| clip_fraction | 0.324 | +| clip_range | 0.0675 | +| entropy_loss | -6.94 | +| explained_variance | 0.32 | +| learning_rate | 4.29e-05 | +| loss | -0.034 | +| n_updates | 74104 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000145 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1404 | +| iterations | 14573 | +| time_elapsed | 21245 | +| total_timesteps | 29845504 | +| train/ | | +| approx_kl | 0.014628557 | +| clip_fraction | 0.357 | +| clip_range | 0.0675 | +| entropy_loss | -6.55 | +| explained_variance | 0.459 | +| learning_rate | 4.29e-05 | +| loss | -0.033 | +| n_updates | 74108 | +| policy_gradient_loss | -0.021 | +| value_loss | 8.2e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1404 | +| iterations | 14574 | +| time_elapsed | 21247 | +| total_timesteps | 29847552 | +| train/ | | +| approx_kl | 0.015076063 | +| clip_fraction | 0.335 | +| clip_range | 0.0675 | +| entropy_loss | -6.29 | +| explained_variance | 0.546 | +| learning_rate | 4.29e-05 | +| loss | -0.0275 | +| n_updates | 74112 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000141 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1404 | +| iterations | 14575 | +| time_elapsed | 21248 | +| total_timesteps | 29849600 | +| train/ | | +| approx_kl | 0.012610242 | +| clip_fraction | 0.327 | +| clip_range | 0.0675 | +| entropy_loss | -6.47 | +| explained_variance | 0.331 | +| learning_rate | 4.29e-05 | +| loss | -0.0311 | +| n_updates | 74116 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000123 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1404 | +| iterations | 14576 | +| time_elapsed | 21249 | +| total_timesteps | 29851648 | +| train/ | | +| approx_kl | 0.01210432 | +| clip_fraction | 0.302 | +| clip_range | 0.0675 | +| entropy_loss | -6.27 | +| explained_variance | 0.764 | +| learning_rate | 4.29e-05 | +| loss | -0.0292 | +| n_updates | 74120 | +| policy_gradient_loss | -0.0167 | +| value_loss | 9.16e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1404 | +| iterations | 14577 | +| time_elapsed | 21251 | +| total_timesteps | 29853696 | +| train/ | | +| approx_kl | 0.011424139 | +| clip_fraction | 0.31 | +| clip_range | 0.0675 | +| entropy_loss | -6 | +| explained_variance | 0.309 | +| learning_rate | 4.29e-05 | +| loss | -0.0262 | +| n_updates | 74124 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000235 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1404 | +| iterations | 14578 | +| time_elapsed | 21252 | +| total_timesteps | 29855744 | +| train/ | | +| approx_kl | 0.014049647 | +| clip_fraction | 0.329 | +| clip_range | 0.0675 | +| entropy_loss | -6.24 | +| explained_variance | 0.499 | +| learning_rate | 4.29e-05 | +| loss | -0.0229 | +| n_updates | 74128 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000233 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1404 | +| iterations | 14579 | +| time_elapsed | 21254 | +| total_timesteps | 29857792 | +| train/ | | +| approx_kl | 0.013563357 | +| clip_fraction | 0.348 | +| clip_range | 0.0675 | +| entropy_loss | -6.64 | +| explained_variance | 0.121 | +| learning_rate | 4.29e-05 | +| loss | -0.0305 | +| n_updates | 74132 | +| policy_gradient_loss | -0.0208 | +| value_loss | 8.82e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1404 | +| iterations | 14580 | +| time_elapsed | 21256 | +| total_timesteps | 29859840 | +| train/ | | +| approx_kl | 0.0138599975 | +| clip_fraction | 0.314 | +| clip_range | 0.0675 | +| entropy_loss | -6.1 | +| explained_variance | 0.472 | +| learning_rate | 4.29e-05 | +| loss | -0.0272 | +| n_updates | 74136 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000241 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1404 | +| iterations | 14581 | +| time_elapsed | 21257 | +| total_timesteps | 29861888 | +| train/ | | +| approx_kl | 0.014459301 | +| clip_fraction | 0.373 | +| clip_range | 0.0675 | +| entropy_loss | -6.25 | +| explained_variance | -0.17 | +| learning_rate | 4.29e-05 | +| loss | -0.0364 | +| n_updates | 74140 | +| policy_gradient_loss | -0.0228 | +| value_loss | 0.000108 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1404 | +| iterations | 14582 | +| time_elapsed | 21259 | +| total_timesteps | 29863936 | +| train/ | | +| approx_kl | 0.011382416 | +| clip_fraction | 0.313 | +| clip_range | 0.0675 | +| entropy_loss | -6.36 | +| explained_variance | 0.461 | +| learning_rate | 4.29e-05 | +| loss | -0.0254 | +| n_updates | 74144 | +| policy_gradient_loss | -0.0148 | +| value_loss | 0.000196 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1404 | +| iterations | 14583 | +| time_elapsed | 21260 | +| total_timesteps | 29865984 | +| train/ | | +| approx_kl | 0.012631983 | +| clip_fraction | 0.294 | +| clip_range | 0.0675 | +| entropy_loss | -5.94 | +| explained_variance | 0.403 | +| learning_rate | 4.29e-05 | +| loss | -0.0179 | +| n_updates | 74148 | +| policy_gradient_loss | -0.0146 | +| value_loss | 0.000221 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1404 | +| iterations | 14584 | +| time_elapsed | 21262 | +| total_timesteps | 29868032 | +| train/ | | +| approx_kl | 0.013086079 | +| clip_fraction | 0.343 | +| clip_range | 0.0675 | +| entropy_loss | -6.34 | +| explained_variance | 0.372 | +| learning_rate | 4.29e-05 | +| loss | -0.0327 | +| n_updates | 74152 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000147 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1404 | +| iterations | 14585 | +| time_elapsed | 21263 | +| total_timesteps | 29870080 | +| train/ | | +| approx_kl | 0.014461938 | +| clip_fraction | 0.335 | +| clip_range | 0.0675 | +| entropy_loss | -6.39 | +| explained_variance | 0.411 | +| learning_rate | 4.29e-05 | +| loss | -0.026 | +| n_updates | 74156 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000188 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1404 | +| iterations | 14586 | +| time_elapsed | 21265 | +| total_timesteps | 29872128 | +| train/ | | +| approx_kl | 0.0110735055 | +| clip_fraction | 0.332 | +| clip_range | 0.0675 | +| entropy_loss | -6.13 | +| explained_variance | 0.571 | +| learning_rate | 4.29e-05 | +| loss | -0.033 | +| n_updates | 74160 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000188 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1404 | +| iterations | 14587 | +| time_elapsed | 21266 | +| total_timesteps | 29874176 | +| train/ | | +| approx_kl | 0.010142256 | +| clip_fraction | 0.3 | +| clip_range | 0.0675 | +| entropy_loss | -6.43 | +| explained_variance | 0.272 | +| learning_rate | 4.29e-05 | +| loss | -0.0236 | +| n_updates | 74164 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000258 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1404 | +| iterations | 14588 | +| time_elapsed | 21268 | +| total_timesteps | 29876224 | +| train/ | | +| approx_kl | 0.0123564135 | +| clip_fraction | 0.32 | +| clip_range | 0.0675 | +| entropy_loss | -6.37 | +| explained_variance | 0.511 | +| learning_rate | 4.29e-05 | +| loss | -0.0304 | +| n_updates | 74168 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000173 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1404 | +| iterations | 14589 | +| time_elapsed | 21269 | +| total_timesteps | 29878272 | +| train/ | | +| approx_kl | 0.0117392065 | +| clip_fraction | 0.318 | +| clip_range | 0.0675 | +| entropy_loss | -6.07 | +| explained_variance | 0.36 | +| learning_rate | 4.29e-05 | +| loss | -0.0212 | +| n_updates | 74172 | +| policy_gradient_loss | -0.0139 | +| value_loss | 0.000389 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1404 | +| iterations | 14590 | +| time_elapsed | 21271 | +| total_timesteps | 29880320 | +| train/ | | +| approx_kl | 0.012753172 | +| clip_fraction | 0.332 | +| clip_range | 0.0675 | +| entropy_loss | -6.43 | +| explained_variance | 0.294 | +| learning_rate | 4.29e-05 | +| loss | -0.0345 | +| n_updates | 74176 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.00017 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1404 | +| iterations | 14591 | +| time_elapsed | 21272 | +| total_timesteps | 29882368 | +| train/ | | +| approx_kl | 0.009645037 | +| clip_fraction | 0.315 | +| clip_range | 0.0675 | +| entropy_loss | -6.04 | +| explained_variance | 0.628 | +| learning_rate | 4.29e-05 | +| loss | -0.0307 | +| n_updates | 74180 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000192 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1404 | +| iterations | 14592 | +| time_elapsed | 21274 | +| total_timesteps | 29884416 | +| train/ | | +| approx_kl | 0.012115761 | +| clip_fraction | 0.354 | +| clip_range | 0.0675 | +| entropy_loss | -6.02 | +| explained_variance | 0.414 | +| learning_rate | 4.29e-05 | +| loss | -0.0288 | +| n_updates | 74184 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000154 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1404 | +| iterations | 14593 | +| time_elapsed | 21276 | +| total_timesteps | 29886464 | +| train/ | | +| approx_kl | 0.0126434425 | +| clip_fraction | 0.359 | +| clip_range | 0.0675 | +| entropy_loss | -6.85 | +| explained_variance | 0.117 | +| learning_rate | 4.29e-05 | +| loss | -0.0307 | +| n_updates | 74188 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000165 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1404 | +| iterations | 14594 | +| time_elapsed | 21277 | +| total_timesteps | 29888512 | +| train/ | | +| approx_kl | 0.01412197 | +| clip_fraction | 0.349 | +| clip_range | 0.0675 | +| entropy_loss | -6.82 | +| explained_variance | 0.634 | +| learning_rate | 4.29e-05 | +| loss | -0.0371 | +| n_updates | 74192 | +| policy_gradient_loss | -0.0221 | +| value_loss | 6.08e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1404 | +| iterations | 14595 | +| time_elapsed | 21279 | +| total_timesteps | 29890560 | +| train/ | | +| approx_kl | 0.012839006 | +| clip_fraction | 0.306 | +| clip_range | 0.0675 | +| entropy_loss | -6.56 | +| explained_variance | 0.331 | +| learning_rate | 4.29e-05 | +| loss | -0.0292 | +| n_updates | 74196 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000161 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1404 | +| iterations | 14596 | +| time_elapsed | 21280 | +| total_timesteps | 29892608 | +| train/ | | +| approx_kl | 0.013847537 | +| clip_fraction | 0.294 | +| clip_range | 0.0675 | +| entropy_loss | -6.33 | +| explained_variance | 0.441 | +| learning_rate | 4.29e-05 | +| loss | -0.0224 | +| n_updates | 74200 | +| policy_gradient_loss | -0.0147 | +| value_loss | 0.000307 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1404 | +| iterations | 14597 | +| time_elapsed | 21282 | +| total_timesteps | 29894656 | +| train/ | | +| approx_kl | 0.01251759 | +| clip_fraction | 0.334 | +| clip_range | 0.0675 | +| entropy_loss | -6.34 | +| explained_variance | 0.201 | +| learning_rate | 4.29e-05 | +| loss | -0.032 | +| n_updates | 74204 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000137 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1404 | +| iterations | 14598 | +| time_elapsed | 21283 | +| total_timesteps | 29896704 | +| train/ | | +| approx_kl | 0.011507166 | +| clip_fraction | 0.326 | +| clip_range | 0.0675 | +| entropy_loss | -6.34 | +| explained_variance | 0.522 | +| learning_rate | 4.29e-05 | +| loss | -0.0335 | +| n_updates | 74208 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000169 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1404 | +| iterations | 14599 | +| time_elapsed | 21285 | +| total_timesteps | 29898752 | +| train/ | | +| approx_kl | 0.013777618 | +| clip_fraction | 0.306 | +| clip_range | 0.0675 | +| entropy_loss | -6.66 | +| explained_variance | 0.443 | +| learning_rate | 4.29e-05 | +| loss | -0.0323 | +| n_updates | 74212 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000175 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1404 | +| iterations | 14600 | +| time_elapsed | 21287 | +| total_timesteps | 29900800 | +| train/ | | +| approx_kl | 0.012033353 | +| clip_fraction | 0.312 | +| clip_range | 0.0675 | +| entropy_loss | -6.09 | +| explained_variance | 0.641 | +| learning_rate | 4.29e-05 | +| loss | -0.0316 | +| n_updates | 74216 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000128 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1404 | +| iterations | 14601 | +| time_elapsed | 21288 | +| total_timesteps | 29902848 | +| train/ | | +| approx_kl | 0.009334356 | +| clip_fraction | 0.332 | +| clip_range | 0.0675 | +| entropy_loss | -6.12 | +| explained_variance | 0.311 | +| learning_rate | 4.29e-05 | +| loss | -0.031 | +| n_updates | 74220 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000289 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1404 | +| iterations | 14602 | +| time_elapsed | 21290 | +| total_timesteps | 29904896 | +| train/ | | +| approx_kl | 0.0128004905 | +| clip_fraction | 0.332 | +| clip_range | 0.0675 | +| entropy_loss | -5.95 | +| explained_variance | 0.682 | +| learning_rate | 4.29e-05 | +| loss | -0.0228 | +| n_updates | 74224 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000126 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1404 | +| iterations | 14603 | +| time_elapsed | 21291 | +| total_timesteps | 29906944 | +| train/ | | +| approx_kl | 0.012923509 | +| clip_fraction | 0.349 | +| clip_range | 0.0675 | +| entropy_loss | -6.24 | +| explained_variance | 0.403 | +| learning_rate | 4.29e-05 | +| loss | -0.0312 | +| n_updates | 74228 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.00011 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1404 | +| iterations | 14604 | +| time_elapsed | 21293 | +| total_timesteps | 29908992 | +| train/ | | +| approx_kl | 0.015598029 | +| clip_fraction | 0.359 | +| clip_range | 0.0675 | +| entropy_loss | -6.26 | +| explained_variance | 0.342 | +| learning_rate | 4.29e-05 | +| loss | -0.0254 | +| n_updates | 74232 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000136 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1404 | +| iterations | 14605 | +| time_elapsed | 21294 | +| total_timesteps | 29911040 | +| train/ | | +| approx_kl | 0.014029032 | +| clip_fraction | 0.303 | +| clip_range | 0.0675 | +| entropy_loss | -6.33 | +| explained_variance | 0.491 | +| learning_rate | 4.29e-05 | +| loss | -0.0258 | +| n_updates | 74236 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000176 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1404 | +| iterations | 14606 | +| time_elapsed | 21296 | +| total_timesteps | 29913088 | +| train/ | | +| approx_kl | 0.015068069 | +| clip_fraction | 0.331 | +| clip_range | 0.0675 | +| entropy_loss | -5.85 | +| explained_variance | 0.523 | +| learning_rate | 4.29e-05 | +| loss | -0.0305 | +| n_updates | 74240 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000104 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1404 | +| iterations | 14607 | +| time_elapsed | 21297 | +| total_timesteps | 29915136 | +| train/ | | +| approx_kl | 0.018259028 | +| clip_fraction | 0.369 | +| clip_range | 0.0675 | +| entropy_loss | -6.32 | +| explained_variance | 0.237 | +| learning_rate | 4.29e-05 | +| loss | -0.0345 | +| n_updates | 74244 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000211 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1404 | +| iterations | 14608 | +| time_elapsed | 21299 | +| total_timesteps | 29917184 | +| train/ | | +| approx_kl | 0.014050431 | +| clip_fraction | 0.349 | +| clip_range | 0.0675 | +| entropy_loss | -7.06 | +| explained_variance | -0.164 | +| learning_rate | 4.29e-05 | +| loss | -0.0278 | +| n_updates | 74248 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000157 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1404 | +| iterations | 14609 | +| time_elapsed | 21300 | +| total_timesteps | 29919232 | +| train/ | | +| approx_kl | 0.0105108535 | +| clip_fraction | 0.327 | +| clip_range | 0.0675 | +| entropy_loss | -6.24 | +| explained_variance | 0.435 | +| learning_rate | 4.29e-05 | +| loss | -0.0224 | +| n_updates | 74252 | +| policy_gradient_loss | -0.0146 | +| value_loss | 0.000239 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1404 | +| iterations | 14610 | +| time_elapsed | 21302 | +| total_timesteps | 29921280 | +| train/ | | +| approx_kl | 0.016195621 | +| clip_fraction | 0.336 | +| clip_range | 0.0675 | +| entropy_loss | -6.38 | +| explained_variance | -0.129 | +| learning_rate | 4.29e-05 | +| loss | -0.0294 | +| n_updates | 74256 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000161 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1404 | +| iterations | 14611 | +| time_elapsed | 21303 | +| total_timesteps | 29923328 | +| train/ | | +| approx_kl | 0.012910997 | +| clip_fraction | 0.375 | +| clip_range | 0.0675 | +| entropy_loss | -6.2 | +| explained_variance | 0.499 | +| learning_rate | 4.29e-05 | +| loss | -0.0345 | +| n_updates | 74260 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000182 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1404 | +| iterations | 14612 | +| time_elapsed | 21305 | +| total_timesteps | 29925376 | +| train/ | | +| approx_kl | 0.01537726 | +| clip_fraction | 0.336 | +| clip_range | 0.0675 | +| entropy_loss | -5.92 | +| explained_variance | 0.58 | +| learning_rate | 4.29e-05 | +| loss | -0.0233 | +| n_updates | 74264 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000124 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1404 | +| iterations | 14613 | +| time_elapsed | 21306 | +| total_timesteps | 29927424 | +| train/ | | +| approx_kl | 0.015587738 | +| clip_fraction | 0.365 | +| clip_range | 0.0675 | +| entropy_loss | -6.33 | +| explained_variance | -0.0123 | +| learning_rate | 4.29e-05 | +| loss | -0.0355 | +| n_updates | 74268 | +| policy_gradient_loss | -0.0211 | +| value_loss | 6.57e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1404 | +| iterations | 14614 | +| time_elapsed | 21308 | +| total_timesteps | 29929472 | +| train/ | | +| approx_kl | 0.013491664 | +| clip_fraction | 0.338 | +| clip_range | 0.0675 | +| entropy_loss | -5.8 | +| explained_variance | 0.592 | +| learning_rate | 4.29e-05 | +| loss | -0.0288 | +| n_updates | 74272 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000215 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1404 | +| iterations | 14615 | +| time_elapsed | 21310 | +| total_timesteps | 29931520 | +| train/ | | +| approx_kl | 0.013449185 | +| clip_fraction | 0.35 | +| clip_range | 0.0675 | +| entropy_loss | -5.89 | +| explained_variance | 0.438 | +| learning_rate | 4.29e-05 | +| loss | -0.0292 | +| n_updates | 74276 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000121 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1404 | +| iterations | 14616 | +| time_elapsed | 21311 | +| total_timesteps | 29933568 | +| train/ | | +| approx_kl | 0.011555359 | +| clip_fraction | 0.321 | +| clip_range | 0.0675 | +| entropy_loss | -6.03 | +| explained_variance | 0.732 | +| learning_rate | 4.29e-05 | +| loss | -0.0322 | +| n_updates | 74280 | +| policy_gradient_loss | -0.0181 | +| value_loss | 8.41e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1404 | +| iterations | 14617 | +| time_elapsed | 21313 | +| total_timesteps | 29935616 | +| train/ | | +| approx_kl | 0.014168967 | +| clip_fraction | 0.341 | +| clip_range | 0.0675 | +| entropy_loss | -6.13 | +| explained_variance | 0.225 | +| learning_rate | 4.29e-05 | +| loss | -0.0298 | +| n_updates | 74284 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000137 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1404 | +| iterations | 14618 | +| time_elapsed | 21314 | +| total_timesteps | 29937664 | +| train/ | | +| approx_kl | 0.0146483425 | +| clip_fraction | 0.374 | +| clip_range | 0.0675 | +| entropy_loss | -5.89 | +| explained_variance | 0.529 | +| learning_rate | 4.29e-05 | +| loss | -0.0323 | +| n_updates | 74288 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000137 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1404 | +| iterations | 14619 | +| time_elapsed | 21316 | +| total_timesteps | 29939712 | +| train/ | | +| approx_kl | 0.014973011 | +| clip_fraction | 0.353 | +| clip_range | 0.0675 | +| entropy_loss | -6.51 | +| explained_variance | -0.0817 | +| learning_rate | 4.29e-05 | +| loss | -0.0288 | +| n_updates | 74292 | +| policy_gradient_loss | -0.0203 | +| value_loss | 7.55e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1404 | +| iterations | 14620 | +| time_elapsed | 21317 | +| total_timesteps | 29941760 | +| train/ | | +| approx_kl | 0.017651627 | +| clip_fraction | 0.335 | +| clip_range | 0.0675 | +| entropy_loss | -6.91 | +| explained_variance | -0.0632 | +| learning_rate | 4.29e-05 | +| loss | -0.0306 | +| n_updates | 74296 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000163 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1404 | +| iterations | 14621 | +| time_elapsed | 21319 | +| total_timesteps | 29943808 | +| train/ | | +| approx_kl | 0.01579703 | +| clip_fraction | 0.346 | +| clip_range | 0.0675 | +| entropy_loss | -7.08 | +| explained_variance | -0.0991 | +| learning_rate | 4.29e-05 | +| loss | -0.035 | +| n_updates | 74300 | +| policy_gradient_loss | -0.0191 | +| value_loss | 8.91e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1404 | +| iterations | 14622 | +| time_elapsed | 21320 | +| total_timesteps | 29945856 | +| train/ | | +| approx_kl | 0.012240009 | +| clip_fraction | 0.317 | +| clip_range | 0.0675 | +| entropy_loss | -6.21 | +| explained_variance | 0.598 | +| learning_rate | 4.29e-05 | +| loss | -0.0248 | +| n_updates | 74304 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000126 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1404 | +| iterations | 14623 | +| time_elapsed | 21322 | +| total_timesteps | 29947904 | +| train/ | | +| approx_kl | 0.013562984 | +| clip_fraction | 0.333 | +| clip_range | 0.0675 | +| entropy_loss | -5.55 | +| explained_variance | 0.411 | +| learning_rate | 4.29e-05 | +| loss | -0.028 | +| n_updates | 74308 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000362 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1404 | +| iterations | 14624 | +| time_elapsed | 21323 | +| total_timesteps | 29949952 | +| train/ | | +| approx_kl | 0.0107678035 | +| clip_fraction | 0.325 | +| clip_range | 0.0675 | +| entropy_loss | -5.42 | +| explained_variance | 0.578 | +| learning_rate | 4.29e-05 | +| loss | -0.0202 | +| n_updates | 74312 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000222 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1404 | +| iterations | 14625 | +| time_elapsed | 21325 | +| total_timesteps | 29952000 | +| train/ | | +| approx_kl | 0.014675755 | +| clip_fraction | 0.362 | +| clip_range | 0.0675 | +| entropy_loss | -6.25 | +| explained_variance | 0.345 | +| learning_rate | 4.29e-05 | +| loss | -0.0325 | +| n_updates | 74316 | +| policy_gradient_loss | -0.0231 | +| value_loss | 9.67e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1404 | +| iterations | 14626 | +| time_elapsed | 21326 | +| total_timesteps | 29954048 | +| train/ | | +| approx_kl | 0.013316932 | +| clip_fraction | 0.339 | +| clip_range | 0.0675 | +| entropy_loss | -6.94 | +| explained_variance | 0.0428 | +| learning_rate | 4.29e-05 | +| loss | -0.0316 | +| n_updates | 74320 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000241 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1404 | +| iterations | 14627 | +| time_elapsed | 21328 | +| total_timesteps | 29956096 | +| train/ | | +| approx_kl | 0.014637822 | +| clip_fraction | 0.364 | +| clip_range | 0.0675 | +| entropy_loss | -6.52 | +| explained_variance | 0.281 | +| learning_rate | 4.29e-05 | +| loss | -0.0344 | +| n_updates | 74324 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000122 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1404 | +| iterations | 14628 | +| time_elapsed | 21330 | +| total_timesteps | 29958144 | +| train/ | | +| approx_kl | 0.013538629 | +| clip_fraction | 0.35 | +| clip_range | 0.0675 | +| entropy_loss | -6.43 | +| explained_variance | 0.31 | +| learning_rate | 4.29e-05 | +| loss | -0.03 | +| n_updates | 74328 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000158 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1404 | +| iterations | 14629 | +| time_elapsed | 21331 | +| total_timesteps | 29960192 | +| train/ | | +| approx_kl | 0.013479194 | +| clip_fraction | 0.348 | +| clip_range | 0.0675 | +| entropy_loss | -6.35 | +| explained_variance | 0.407 | +| learning_rate | 4.29e-05 | +| loss | -0.0359 | +| n_updates | 74332 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000155 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1404 | +| iterations | 14630 | +| time_elapsed | 21333 | +| total_timesteps | 29962240 | +| train/ | | +| approx_kl | 0.0138181625 | +| clip_fraction | 0.354 | +| clip_range | 0.0675 | +| entropy_loss | -6.57 | +| explained_variance | 0.165 | +| learning_rate | 4.29e-05 | +| loss | -0.0273 | +| n_updates | 74336 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000182 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1404 | +| iterations | 14631 | +| time_elapsed | 21334 | +| total_timesteps | 29964288 | +| train/ | | +| approx_kl | 0.013350413 | +| clip_fraction | 0.324 | +| clip_range | 0.0675 | +| entropy_loss | -6 | +| explained_variance | 0.499 | +| learning_rate | 4.29e-05 | +| loss | -0.0318 | +| n_updates | 74340 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000201 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1404 | +| iterations | 14632 | +| time_elapsed | 21336 | +| total_timesteps | 29966336 | +| train/ | | +| approx_kl | 0.012687903 | +| clip_fraction | 0.323 | +| clip_range | 0.0675 | +| entropy_loss | -5.65 | +| explained_variance | 0.527 | +| learning_rate | 4.29e-05 | +| loss | -0.0236 | +| n_updates | 74344 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000187 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1404 | +| iterations | 14633 | +| time_elapsed | 21337 | +| total_timesteps | 29968384 | +| train/ | | +| approx_kl | 0.017102778 | +| clip_fraction | 0.329 | +| clip_range | 0.0675 | +| entropy_loss | -5.65 | +| explained_variance | 0.594 | +| learning_rate | 4.29e-05 | +| loss | -0.0326 | +| n_updates | 74348 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000151 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1404 | +| iterations | 14634 | +| time_elapsed | 21339 | +| total_timesteps | 29970432 | +| train/ | | +| approx_kl | 0.013482226 | +| clip_fraction | 0.336 | +| clip_range | 0.0675 | +| entropy_loss | -6.32 | +| explained_variance | 0.333 | +| learning_rate | 4.29e-05 | +| loss | -0.0312 | +| n_updates | 74352 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000287 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1404 | +| iterations | 14635 | +| time_elapsed | 21340 | +| total_timesteps | 29972480 | +| train/ | | +| approx_kl | 0.011761839 | +| clip_fraction | 0.328 | +| clip_range | 0.0675 | +| entropy_loss | -6.54 | +| explained_variance | 0.257 | +| learning_rate | 4.29e-05 | +| loss | -0.0258 | +| n_updates | 74356 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000254 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1404 | +| iterations | 14636 | +| time_elapsed | 21342 | +| total_timesteps | 29974528 | +| train/ | | +| approx_kl | 0.01215124 | +| clip_fraction | 0.329 | +| clip_range | 0.0675 | +| entropy_loss | -6.3 | +| explained_variance | 0.482 | +| learning_rate | 4.29e-05 | +| loss | -0.0329 | +| n_updates | 74360 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.0002 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1404 | +| iterations | 14637 | +| time_elapsed | 21344 | +| total_timesteps | 29976576 | +| train/ | | +| approx_kl | 0.0075833136 | +| clip_fraction | 0.3 | +| clip_range | 0.0675 | +| entropy_loss | -6.83 | +| explained_variance | 0.363 | +| learning_rate | 4.29e-05 | +| loss | -0.0254 | +| n_updates | 74364 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000216 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1404 | +| iterations | 14638 | +| time_elapsed | 21345 | +| total_timesteps | 29978624 | +| train/ | | +| approx_kl | 0.008818876 | +| clip_fraction | 0.301 | +| clip_range | 0.0675 | +| entropy_loss | -6.68 | +| explained_variance | 0.552 | +| learning_rate | 4.29e-05 | +| loss | -0.0309 | +| n_updates | 74368 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.00012 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1404 | +| iterations | 14639 | +| time_elapsed | 21347 | +| total_timesteps | 29980672 | +| train/ | | +| approx_kl | 0.0092201205 | +| clip_fraction | 0.3 | +| clip_range | 0.0675 | +| entropy_loss | -6.03 | +| explained_variance | 0.33 | +| learning_rate | 4.29e-05 | +| loss | -0.0246 | +| n_updates | 74372 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000355 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1404 | +| iterations | 14640 | +| time_elapsed | 21348 | +| total_timesteps | 29982720 | +| train/ | | +| approx_kl | 0.011878895 | +| clip_fraction | 0.316 | +| clip_range | 0.0675 | +| entropy_loss | -6.41 | +| explained_variance | 0.518 | +| learning_rate | 4.29e-05 | +| loss | -0.0287 | +| n_updates | 74376 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000142 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1404 | +| iterations | 14641 | +| time_elapsed | 21350 | +| total_timesteps | 29984768 | +| train/ | | +| approx_kl | 0.01126237 | +| clip_fraction | 0.294 | +| clip_range | 0.0675 | +| entropy_loss | -5.79 | +| explained_variance | 0.416 | +| learning_rate | 4.29e-05 | +| loss | -0.0286 | +| n_updates | 74380 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000328 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1404 | +| iterations | 14642 | +| time_elapsed | 21351 | +| total_timesteps | 29986816 | +| train/ | | +| approx_kl | 0.013632825 | +| clip_fraction | 0.316 | +| clip_range | 0.0675 | +| entropy_loss | -5.74 | +| explained_variance | 0.353 | +| learning_rate | 4.29e-05 | +| loss | -0.0293 | +| n_updates | 74384 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000222 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1404 | +| iterations | 14643 | +| time_elapsed | 21353 | +| total_timesteps | 29988864 | +| train/ | | +| approx_kl | 0.013080176 | +| clip_fraction | 0.359 | +| clip_range | 0.0675 | +| entropy_loss | -6.35 | +| explained_variance | 0.149 | +| learning_rate | 4.29e-05 | +| loss | -0.0227 | +| n_updates | 74388 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000315 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1404 | +| iterations | 14644 | +| time_elapsed | 21354 | +| total_timesteps | 29990912 | +| train/ | | +| approx_kl | 0.014993535 | +| clip_fraction | 0.346 | +| clip_range | 0.0675 | +| entropy_loss | -6.65 | +| explained_variance | 0.236 | +| learning_rate | 4.29e-05 | +| loss | -0.0353 | +| n_updates | 74392 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000167 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1404 | +| iterations | 14645 | +| time_elapsed | 21356 | +| total_timesteps | 29992960 | +| train/ | | +| approx_kl | 0.012390697 | +| clip_fraction | 0.34 | +| clip_range | 0.0675 | +| entropy_loss | -6.24 | +| explained_variance | 0.328 | +| learning_rate | 4.29e-05 | +| loss | -0.0239 | +| n_updates | 74396 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000262 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1404 | +| iterations | 14646 | +| time_elapsed | 21357 | +| total_timesteps | 29995008 | +| train/ | | +| approx_kl | 0.011974685 | +| clip_fraction | 0.331 | +| clip_range | 0.0675 | +| entropy_loss | -6.24 | +| explained_variance | 0.463 | +| learning_rate | 4.29e-05 | +| loss | -0.0252 | +| n_updates | 74400 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000151 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1404 | +| iterations | 14647 | +| time_elapsed | 21359 | +| total_timesteps | 29997056 | +| train/ | | +| approx_kl | 0.012266004 | +| clip_fraction | 0.351 | +| clip_range | 0.0675 | +| entropy_loss | -6.41 | +| explained_variance | 0.318 | +| learning_rate | 4.29e-05 | +| loss | -0.0392 | +| n_updates | 74404 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000103 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1404 | +| iterations | 14648 | +| time_elapsed | 21360 | +| total_timesteps | 29999104 | +| train/ | | +| approx_kl | 0.013444323 | +| clip_fraction | 0.337 | +| clip_range | 0.0675 | +| entropy_loss | -5.88 | +| explained_variance | 0.611 | +| learning_rate | 4.29e-05 | +| loss | -0.034 | +| n_updates | 74408 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000133 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1404 | +| iterations | 14649 | +| time_elapsed | 21362 | +| total_timesteps | 30001152 | +| train/ | | +| approx_kl | 0.011748312 | +| clip_fraction | 0.315 | +| clip_range | 0.0675 | +| entropy_loss | -6.22 | +| explained_variance | 0.306 | +| learning_rate | 4.29e-05 | +| loss | -0.0285 | +| n_updates | 74412 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000121 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1404 | +| iterations | 14650 | +| time_elapsed | 21363 | +| total_timesteps | 30003200 | +| train/ | | +| approx_kl | 0.012046495 | +| clip_fraction | 0.333 | +| clip_range | 0.0675 | +| entropy_loss | -6.29 | +| explained_variance | 0.436 | +| learning_rate | 4.29e-05 | +| loss | -0.0244 | +| n_updates | 74416 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000171 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1404 | +| iterations | 14651 | +| time_elapsed | 21365 | +| total_timesteps | 30005248 | +| train/ | | +| approx_kl | 0.012305599 | +| clip_fraction | 0.326 | +| clip_range | 0.0675 | +| entropy_loss | -6.31 | +| explained_variance | 0.481 | +| learning_rate | 4.29e-05 | +| loss | -0.0296 | +| n_updates | 74420 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000178 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1404 | +| iterations | 14652 | +| time_elapsed | 21366 | +| total_timesteps | 30007296 | +| train/ | | +| approx_kl | 0.013743028 | +| clip_fraction | 0.336 | +| clip_range | 0.0675 | +| entropy_loss | -6.36 | +| explained_variance | 0.323 | +| learning_rate | 4.29e-05 | +| loss | -0.0281 | +| n_updates | 74424 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000174 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1404 | +| iterations | 14653 | +| time_elapsed | 21368 | +| total_timesteps | 30009344 | +| train/ | | +| approx_kl | 0.011839595 | +| clip_fraction | 0.325 | +| clip_range | 0.0675 | +| entropy_loss | -6.02 | +| explained_variance | 0.466 | +| learning_rate | 4.29e-05 | +| loss | -0.034 | +| n_updates | 74428 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000155 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1404 | +| iterations | 14654 | +| time_elapsed | 21370 | +| total_timesteps | 30011392 | +| train/ | | +| approx_kl | 0.014833852 | +| clip_fraction | 0.335 | +| clip_range | 0.0675 | +| entropy_loss | -5.93 | +| explained_variance | 0.37 | +| learning_rate | 4.29e-05 | +| loss | -0.0314 | +| n_updates | 74432 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000256 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1404 | +| iterations | 14655 | +| time_elapsed | 21371 | +| total_timesteps | 30013440 | +| train/ | | +| approx_kl | 0.013783444 | +| clip_fraction | 0.349 | +| clip_range | 0.0675 | +| entropy_loss | -6.63 | +| explained_variance | -0.171 | +| learning_rate | 4.29e-05 | +| loss | -0.0342 | +| n_updates | 74436 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000148 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1404 | +| iterations | 14656 | +| time_elapsed | 21373 | +| total_timesteps | 30015488 | +| train/ | | +| approx_kl | 0.013394104 | +| clip_fraction | 0.327 | +| clip_range | 0.0675 | +| entropy_loss | -6.58 | +| explained_variance | 0.347 | +| learning_rate | 4.29e-05 | +| loss | -0.0262 | +| n_updates | 74440 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000199 | +----------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1404 | +| iterations | 14657 | +| time_elapsed | 21374 | +| total_timesteps | 30017536 | +| train/ | | +| approx_kl | 0.015595 | +| clip_fraction | 0.385 | +| clip_range | 0.0675 | +| entropy_loss | -5.74 | +| explained_variance | 0.323 | +| learning_rate | 4.29e-05 | +| loss | -0.0258 | +| n_updates | 74444 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000147 | +-------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1404 | +| iterations | 14658 | +| time_elapsed | 21376 | +| total_timesteps | 30019584 | +| train/ | | +| approx_kl | 0.014206564 | +| clip_fraction | 0.337 | +| clip_range | 0.0675 | +| entropy_loss | -5.96 | +| explained_variance | 0.453 | +| learning_rate | 4.29e-05 | +| loss | -0.0297 | +| n_updates | 74448 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.00016 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1404 | +| iterations | 14659 | +| time_elapsed | 21377 | +| total_timesteps | 30021632 | +| train/ | | +| approx_kl | 0.012853531 | +| clip_fraction | 0.35 | +| clip_range | 0.0675 | +| entropy_loss | -6.26 | +| explained_variance | 0.34 | +| learning_rate | 4.29e-05 | +| loss | -0.0289 | +| n_updates | 74452 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000174 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1404 | +| iterations | 14660 | +| time_elapsed | 21379 | +| total_timesteps | 30023680 | +| train/ | | +| approx_kl | 0.0124591645 | +| clip_fraction | 0.347 | +| clip_range | 0.0675 | +| entropy_loss | -6.59 | +| explained_variance | 0.195 | +| learning_rate | 4.29e-05 | +| loss | -0.0283 | +| n_updates | 74456 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000234 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1404 | +| iterations | 14661 | +| time_elapsed | 21380 | +| total_timesteps | 30025728 | +| train/ | | +| approx_kl | 0.011798343 | +| clip_fraction | 0.31 | +| clip_range | 0.0675 | +| entropy_loss | -6.66 | +| explained_variance | 0.385 | +| learning_rate | 4.29e-05 | +| loss | -0.0242 | +| n_updates | 74460 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000109 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1404 | +| iterations | 14662 | +| time_elapsed | 21382 | +| total_timesteps | 30027776 | +| train/ | | +| approx_kl | 0.0138660045 | +| clip_fraction | 0.324 | +| clip_range | 0.0675 | +| entropy_loss | -6.12 | +| explained_variance | 0.188 | +| learning_rate | 4.29e-05 | +| loss | -0.0203 | +| n_updates | 74464 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000527 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1404 | +| iterations | 14663 | +| time_elapsed | 21383 | +| total_timesteps | 30029824 | +| train/ | | +| approx_kl | 0.013669979 | +| clip_fraction | 0.353 | +| clip_range | 0.0675 | +| entropy_loss | -5.9 | +| explained_variance | 0.578 | +| learning_rate | 4.29e-05 | +| loss | -0.0348 | +| n_updates | 74468 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000146 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1404 | +| iterations | 14664 | +| time_elapsed | 21385 | +| total_timesteps | 30031872 | +| train/ | | +| approx_kl | 0.010557527 | +| clip_fraction | 0.351 | +| clip_range | 0.0675 | +| entropy_loss | -6.61 | +| explained_variance | 0.35 | +| learning_rate | 4.29e-05 | +| loss | -0.0281 | +| n_updates | 74472 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000166 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1404 | +| iterations | 14665 | +| time_elapsed | 21386 | +| total_timesteps | 30033920 | +| train/ | | +| approx_kl | 0.013785659 | +| clip_fraction | 0.322 | +| clip_range | 0.0675 | +| entropy_loss | -6.05 | +| explained_variance | 0.491 | +| learning_rate | 4.29e-05 | +| loss | -0.0288 | +| n_updates | 74476 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000244 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1404 | +| iterations | 14666 | +| time_elapsed | 21388 | +| total_timesteps | 30035968 | +| train/ | | +| approx_kl | 0.012995686 | +| clip_fraction | 0.344 | +| clip_range | 0.0675 | +| entropy_loss | -5.96 | +| explained_variance | 0.511 | +| learning_rate | 4.29e-05 | +| loss | -0.0318 | +| n_updates | 74480 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000194 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1404 | +| iterations | 14667 | +| time_elapsed | 21389 | +| total_timesteps | 30038016 | +| train/ | | +| approx_kl | 0.014136689 | +| clip_fraction | 0.377 | +| clip_range | 0.0675 | +| entropy_loss | -6.34 | +| explained_variance | 0.476 | +| learning_rate | 4.29e-05 | +| loss | -0.0356 | +| n_updates | 74484 | +| policy_gradient_loss | -0.0233 | +| value_loss | 6.76e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1404 | +| iterations | 14668 | +| time_elapsed | 21391 | +| total_timesteps | 30040064 | +| train/ | | +| approx_kl | 0.011199806 | +| clip_fraction | 0.327 | +| clip_range | 0.0675 | +| entropy_loss | -6.29 | +| explained_variance | 0.273 | +| learning_rate | 4.29e-05 | +| loss | -0.0333 | +| n_updates | 74488 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000314 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1404 | +| iterations | 14669 | +| time_elapsed | 21393 | +| total_timesteps | 30042112 | +| train/ | | +| approx_kl | 0.013841667 | +| clip_fraction | 0.343 | +| clip_range | 0.0675 | +| entropy_loss | -5.97 | +| explained_variance | 0.579 | +| learning_rate | 4.29e-05 | +| loss | -0.0249 | +| n_updates | 74492 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000128 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1404 | +| iterations | 14670 | +| time_elapsed | 21394 | +| total_timesteps | 30044160 | +| train/ | | +| approx_kl | 0.012379169 | +| clip_fraction | 0.32 | +| clip_range | 0.0675 | +| entropy_loss | -6.28 | +| explained_variance | 0.176 | +| learning_rate | 4.29e-05 | +| loss | -0.0289 | +| n_updates | 74496 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000377 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1404 | +| iterations | 14671 | +| time_elapsed | 21396 | +| total_timesteps | 30046208 | +| train/ | | +| approx_kl | 0.01776276 | +| clip_fraction | 0.339 | +| clip_range | 0.0675 | +| entropy_loss | -5.92 | +| explained_variance | 0.4 | +| learning_rate | 4.29e-05 | +| loss | -0.0277 | +| n_updates | 74500 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000184 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1404 | +| iterations | 14672 | +| time_elapsed | 21397 | +| total_timesteps | 30048256 | +| train/ | | +| approx_kl | 0.014675184 | +| clip_fraction | 0.343 | +| clip_range | 0.0675 | +| entropy_loss | -6.26 | +| explained_variance | 0.418 | +| learning_rate | 4.29e-05 | +| loss | -0.0302 | +| n_updates | 74504 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000173 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1404 | +| iterations | 14673 | +| time_elapsed | 21399 | +| total_timesteps | 30050304 | +| train/ | | +| approx_kl | 0.013283204 | +| clip_fraction | 0.325 | +| clip_range | 0.0675 | +| entropy_loss | -6 | +| explained_variance | 0.389 | +| learning_rate | 4.29e-05 | +| loss | -0.0254 | +| n_updates | 74508 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000426 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1404 | +| iterations | 14674 | +| time_elapsed | 21400 | +| total_timesteps | 30052352 | +| train/ | | +| approx_kl | 0.012149145 | +| clip_fraction | 0.348 | +| clip_range | 0.0675 | +| entropy_loss | -6.18 | +| explained_variance | -0.0477 | +| learning_rate | 4.29e-05 | +| loss | -0.0332 | +| n_updates | 74512 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000168 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1404 | +| iterations | 14675 | +| time_elapsed | 21402 | +| total_timesteps | 30054400 | +| train/ | | +| approx_kl | 0.011427667 | +| clip_fraction | 0.338 | +| clip_range | 0.0675 | +| entropy_loss | -6.06 | +| explained_variance | 0.334 | +| learning_rate | 4.29e-05 | +| loss | -0.0274 | +| n_updates | 74516 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000372 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1404 | +| iterations | 14676 | +| time_elapsed | 21403 | +| total_timesteps | 30056448 | +| train/ | | +| approx_kl | 0.012885245 | +| clip_fraction | 0.348 | +| clip_range | 0.0675 | +| entropy_loss | -6.46 | +| explained_variance | -0.0945 | +| learning_rate | 4.29e-05 | +| loss | -0.0396 | +| n_updates | 74520 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000121 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1404 | +| iterations | 14677 | +| time_elapsed | 21405 | +| total_timesteps | 30058496 | +| train/ | | +| approx_kl | 0.012470253 | +| clip_fraction | 0.326 | +| clip_range | 0.0675 | +| entropy_loss | -6.82 | +| explained_variance | 0.349 | +| learning_rate | 4.29e-05 | +| loss | -0.0272 | +| n_updates | 74524 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000145 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1404 | +| iterations | 14678 | +| time_elapsed | 21406 | +| total_timesteps | 30060544 | +| train/ | | +| approx_kl | 0.013207927 | +| clip_fraction | 0.363 | +| clip_range | 0.0675 | +| entropy_loss | -6.27 | +| explained_variance | 0.746 | +| learning_rate | 4.29e-05 | +| loss | -0.0306 | +| n_updates | 74528 | +| policy_gradient_loss | -0.0207 | +| value_loss | 7.48e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1404 | +| iterations | 14679 | +| time_elapsed | 21408 | +| total_timesteps | 30062592 | +| train/ | | +| approx_kl | 0.011361955 | +| clip_fraction | 0.325 | +| clip_range | 0.0675 | +| entropy_loss | -6.28 | +| explained_variance | 0.284 | +| learning_rate | 4.29e-05 | +| loss | -0.0237 | +| n_updates | 74532 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000185 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1404 | +| iterations | 14680 | +| time_elapsed | 21409 | +| total_timesteps | 30064640 | +| train/ | | +| approx_kl | 0.010456103 | +| clip_fraction | 0.319 | +| clip_range | 0.0675 | +| entropy_loss | -6.56 | +| explained_variance | 0.616 | +| learning_rate | 4.29e-05 | +| loss | -0.0283 | +| n_updates | 74536 | +| policy_gradient_loss | -0.0183 | +| value_loss | 8.49e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1404 | +| iterations | 14681 | +| time_elapsed | 21411 | +| total_timesteps | 30066688 | +| train/ | | +| approx_kl | 0.0125987595 | +| clip_fraction | 0.298 | +| clip_range | 0.0675 | +| entropy_loss | -6.56 | +| explained_variance | 0.0966 | +| learning_rate | 4.29e-05 | +| loss | -0.0298 | +| n_updates | 74540 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000167 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1404 | +| iterations | 14682 | +| time_elapsed | 21412 | +| total_timesteps | 30068736 | +| train/ | | +| approx_kl | 0.011660829 | +| clip_fraction | 0.337 | +| clip_range | 0.0675 | +| entropy_loss | -6.59 | +| explained_variance | 0.508 | +| learning_rate | 4.29e-05 | +| loss | -0.0298 | +| n_updates | 74544 | +| policy_gradient_loss | -0.0181 | +| value_loss | 8.34e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1404 | +| iterations | 14683 | +| time_elapsed | 21414 | +| total_timesteps | 30070784 | +| train/ | | +| approx_kl | 0.01459014 | +| clip_fraction | 0.347 | +| clip_range | 0.0675 | +| entropy_loss | -6.03 | +| explained_variance | 0.62 | +| learning_rate | 4.29e-05 | +| loss | -0.0263 | +| n_updates | 74548 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000126 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1404 | +| iterations | 14684 | +| time_elapsed | 21415 | +| total_timesteps | 30072832 | +| train/ | | +| approx_kl | 0.011758605 | +| clip_fraction | 0.385 | +| clip_range | 0.0675 | +| entropy_loss | -6.64 | +| explained_variance | 0.0761 | +| learning_rate | 4.29e-05 | +| loss | -0.0395 | +| n_updates | 74552 | +| policy_gradient_loss | -0.0243 | +| value_loss | 3.42e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1404 | +| iterations | 14685 | +| time_elapsed | 21417 | +| total_timesteps | 30074880 | +| train/ | | +| approx_kl | 0.012874175 | +| clip_fraction | 0.304 | +| clip_range | 0.0675 | +| entropy_loss | -6.55 | +| explained_variance | 0.488 | +| learning_rate | 4.29e-05 | +| loss | -0.0243 | +| n_updates | 74556 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000186 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1404 | +| iterations | 14686 | +| time_elapsed | 21418 | +| total_timesteps | 30076928 | +| train/ | | +| approx_kl | 0.011924336 | +| clip_fraction | 0.327 | +| clip_range | 0.0675 | +| entropy_loss | -6 | +| explained_variance | 0.557 | +| learning_rate | 4.29e-05 | +| loss | -0.0266 | +| n_updates | 74560 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000195 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1404 | +| iterations | 14687 | +| time_elapsed | 21420 | +| total_timesteps | 30078976 | +| train/ | | +| approx_kl | 0.013675839 | +| clip_fraction | 0.326 | +| clip_range | 0.0675 | +| entropy_loss | -6.2 | +| explained_variance | 0.579 | +| learning_rate | 4.29e-05 | +| loss | -0.02 | +| n_updates | 74564 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1404 | +| iterations | 14688 | +| time_elapsed | 21421 | +| total_timesteps | 30081024 | +| train/ | | +| approx_kl | 0.012698507 | +| clip_fraction | 0.353 | +| clip_range | 0.0675 | +| entropy_loss | -6.59 | +| explained_variance | 0.423 | +| learning_rate | 4.29e-05 | +| loss | -0.0355 | +| n_updates | 74568 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000129 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1404 | +| iterations | 14689 | +| time_elapsed | 21423 | +| total_timesteps | 30083072 | +| train/ | | +| approx_kl | 0.013763208 | +| clip_fraction | 0.305 | +| clip_range | 0.0675 | +| entropy_loss | -6.6 | +| explained_variance | 0.391 | +| learning_rate | 4.29e-05 | +| loss | -0.0276 | +| n_updates | 74572 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000177 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1404 | +| iterations | 14690 | +| time_elapsed | 21424 | +| total_timesteps | 30085120 | +| train/ | | +| approx_kl | 0.013542176 | +| clip_fraction | 0.337 | +| clip_range | 0.0675 | +| entropy_loss | -5.98 | +| explained_variance | 0.673 | +| learning_rate | 4.29e-05 | +| loss | -0.0254 | +| n_updates | 74576 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000123 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1404 | +| iterations | 14691 | +| time_elapsed | 21426 | +| total_timesteps | 30087168 | +| train/ | | +| approx_kl | 0.010402625 | +| clip_fraction | 0.313 | +| clip_range | 0.0675 | +| entropy_loss | -6.01 | +| explained_variance | 0.489 | +| learning_rate | 4.29e-05 | +| loss | -0.0207 | +| n_updates | 74580 | +| policy_gradient_loss | -0.014 | +| value_loss | 0.000339 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1404 | +| iterations | 14692 | +| time_elapsed | 21427 | +| total_timesteps | 30089216 | +| train/ | | +| approx_kl | 0.010826722 | +| clip_fraction | 0.325 | +| clip_range | 0.0675 | +| entropy_loss | -6.44 | +| explained_variance | 0.245 | +| learning_rate | 4.29e-05 | +| loss | -0.0308 | +| n_updates | 74584 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.00026 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1404 | +| iterations | 14693 | +| time_elapsed | 21429 | +| total_timesteps | 30091264 | +| train/ | | +| approx_kl | 0.014109028 | +| clip_fraction | 0.341 | +| clip_range | 0.0675 | +| entropy_loss | -6.54 | +| explained_variance | 0.343 | +| learning_rate | 4.29e-05 | +| loss | -0.0314 | +| n_updates | 74588 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000126 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1404 | +| iterations | 14694 | +| time_elapsed | 21431 | +| total_timesteps | 30093312 | +| train/ | | +| approx_kl | 0.0144761875 | +| clip_fraction | 0.352 | +| clip_range | 0.0675 | +| entropy_loss | -6.24 | +| explained_variance | 0.19 | +| learning_rate | 4.29e-05 | +| loss | -0.0272 | +| n_updates | 74592 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000246 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1404 | +| iterations | 14695 | +| time_elapsed | 21432 | +| total_timesteps | 30095360 | +| train/ | | +| approx_kl | 0.0149745345 | +| clip_fraction | 0.361 | +| clip_range | 0.0675 | +| entropy_loss | -6.44 | +| explained_variance | 0.236 | +| learning_rate | 4.29e-05 | +| loss | -0.0317 | +| n_updates | 74596 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000161 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1404 | +| iterations | 14696 | +| time_elapsed | 21434 | +| total_timesteps | 30097408 | +| train/ | | +| approx_kl | 0.014191904 | +| clip_fraction | 0.359 | +| clip_range | 0.0675 | +| entropy_loss | -6.71 | +| explained_variance | 0.26 | +| learning_rate | 4.29e-05 | +| loss | -0.0289 | +| n_updates | 74600 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000159 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1404 | +| iterations | 14697 | +| time_elapsed | 21435 | +| total_timesteps | 30099456 | +| train/ | | +| approx_kl | 0.01752916 | +| clip_fraction | 0.313 | +| clip_range | 0.0675 | +| entropy_loss | -5.89 | +| explained_variance | 0.428 | +| learning_rate | 4.29e-05 | +| loss | -0.0269 | +| n_updates | 74604 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.00026 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1404 | +| iterations | 14698 | +| time_elapsed | 21437 | +| total_timesteps | 30101504 | +| train/ | | +| approx_kl | 0.014432797 | +| clip_fraction | 0.348 | +| clip_range | 0.0675 | +| entropy_loss | -5.87 | +| explained_variance | 0.48 | +| learning_rate | 4.29e-05 | +| loss | -0.0297 | +| n_updates | 74608 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000154 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1404 | +| iterations | 14699 | +| time_elapsed | 21438 | +| total_timesteps | 30103552 | +| train/ | | +| approx_kl | 0.016153699 | +| clip_fraction | 0.376 | +| clip_range | 0.0675 | +| entropy_loss | -6.46 | +| explained_variance | 0.472 | +| learning_rate | 4.29e-05 | +| loss | -0.0356 | +| n_updates | 74612 | +| policy_gradient_loss | -0.0221 | +| value_loss | 9.7e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1404 | +| iterations | 14700 | +| time_elapsed | 21440 | +| total_timesteps | 30105600 | +| train/ | | +| approx_kl | 0.015342279 | +| clip_fraction | 0.339 | +| clip_range | 0.0675 | +| entropy_loss | -6.1 | +| explained_variance | 0.456 | +| learning_rate | 4.29e-05 | +| loss | -0.0338 | +| n_updates | 74616 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000163 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1404 | +| iterations | 14701 | +| time_elapsed | 21441 | +| total_timesteps | 30107648 | +| train/ | | +| approx_kl | 0.018820586 | +| clip_fraction | 0.353 | +| clip_range | 0.0675 | +| entropy_loss | -5.87 | +| explained_variance | 0.419 | +| learning_rate | 4.28e-05 | +| loss | -0.0325 | +| n_updates | 74620 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000103 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1404 | +| iterations | 14702 | +| time_elapsed | 21443 | +| total_timesteps | 30109696 | +| train/ | | +| approx_kl | 0.014586411 | +| clip_fraction | 0.333 | +| clip_range | 0.0675 | +| entropy_loss | -6.48 | +| explained_variance | 0.125 | +| learning_rate | 4.28e-05 | +| loss | -0.0322 | +| n_updates | 74624 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000164 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1404 | +| iterations | 14703 | +| time_elapsed | 21444 | +| total_timesteps | 30111744 | +| train/ | | +| approx_kl | 0.016115513 | +| clip_fraction | 0.366 | +| clip_range | 0.0675 | +| entropy_loss | -5.9 | +| explained_variance | 0.664 | +| learning_rate | 4.28e-05 | +| loss | -0.0329 | +| n_updates | 74628 | +| policy_gradient_loss | -0.0189 | +| value_loss | 9.73e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1404 | +| iterations | 14704 | +| time_elapsed | 21446 | +| total_timesteps | 30113792 | +| train/ | | +| approx_kl | 0.013303859 | +| clip_fraction | 0.335 | +| clip_range | 0.0675 | +| entropy_loss | -6.48 | +| explained_variance | 0.345 | +| learning_rate | 4.28e-05 | +| loss | -0.0301 | +| n_updates | 74632 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000126 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1404 | +| iterations | 14705 | +| time_elapsed | 21447 | +| total_timesteps | 30115840 | +| train/ | | +| approx_kl | 0.013122297 | +| clip_fraction | 0.354 | +| clip_range | 0.0675 | +| entropy_loss | -6.65 | +| explained_variance | 0.409 | +| learning_rate | 4.28e-05 | +| loss | -0.0297 | +| n_updates | 74636 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000109 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1404 | +| iterations | 14706 | +| time_elapsed | 21449 | +| total_timesteps | 30117888 | +| train/ | | +| approx_kl | 0.01264109 | +| clip_fraction | 0.36 | +| clip_range | 0.0675 | +| entropy_loss | -6.18 | +| explained_variance | 0.743 | +| learning_rate | 4.28e-05 | +| loss | -0.0265 | +| n_updates | 74640 | +| policy_gradient_loss | -0.0184 | +| value_loss | 4.72e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1404 | +| iterations | 14707 | +| time_elapsed | 21450 | +| total_timesteps | 30119936 | +| train/ | | +| approx_kl | 0.011049134 | +| clip_fraction | 0.281 | +| clip_range | 0.0675 | +| entropy_loss | -5.5 | +| explained_variance | 0.388 | +| learning_rate | 4.28e-05 | +| loss | -0.0172 | +| n_updates | 74644 | +| policy_gradient_loss | -0.0134 | +| value_loss | 0.000459 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1404 | +| iterations | 14708 | +| time_elapsed | 21452 | +| total_timesteps | 30121984 | +| train/ | | +| approx_kl | 0.011129525 | +| clip_fraction | 0.351 | +| clip_range | 0.0675 | +| entropy_loss | -5.87 | +| explained_variance | 0.706 | +| learning_rate | 4.28e-05 | +| loss | -0.0326 | +| n_updates | 74648 | +| policy_gradient_loss | -0.0223 | +| value_loss | 8.5e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1404 | +| iterations | 14709 | +| time_elapsed | 21453 | +| total_timesteps | 30124032 | +| train/ | | +| approx_kl | 0.010445777 | +| clip_fraction | 0.328 | +| clip_range | 0.0675 | +| entropy_loss | -6.14 | +| explained_variance | 0.318 | +| learning_rate | 4.28e-05 | +| loss | -0.0271 | +| n_updates | 74652 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000213 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1404 | +| iterations | 14710 | +| time_elapsed | 21455 | +| total_timesteps | 30126080 | +| train/ | | +| approx_kl | 0.015101328 | +| clip_fraction | 0.314 | +| clip_range | 0.0675 | +| entropy_loss | -6.73 | +| explained_variance | 0.19 | +| learning_rate | 4.28e-05 | +| loss | -0.0299 | +| n_updates | 74656 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000238 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1404 | +| iterations | 14711 | +| time_elapsed | 21456 | +| total_timesteps | 30128128 | +| train/ | | +| approx_kl | 0.012388447 | +| clip_fraction | 0.34 | +| clip_range | 0.0675 | +| entropy_loss | -6.75 | +| explained_variance | 0.282 | +| learning_rate | 4.28e-05 | +| loss | -0.0386 | +| n_updates | 74660 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000162 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1404 | +| iterations | 14712 | +| time_elapsed | 21458 | +| total_timesteps | 30130176 | +| train/ | | +| approx_kl | 0.011105122 | +| clip_fraction | 0.326 | +| clip_range | 0.0675 | +| entropy_loss | -6.3 | +| explained_variance | 0.392 | +| learning_rate | 4.28e-05 | +| loss | -0.0257 | +| n_updates | 74664 | +| policy_gradient_loss | -0.0138 | +| value_loss | 0.00029 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1404 | +| iterations | 14713 | +| time_elapsed | 21460 | +| total_timesteps | 30132224 | +| train/ | | +| approx_kl | 0.015203757 | +| clip_fraction | 0.356 | +| clip_range | 0.0675 | +| entropy_loss | -6.12 | +| explained_variance | 0.255 | +| learning_rate | 4.28e-05 | +| loss | -0.0293 | +| n_updates | 74668 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.00016 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1404 | +| iterations | 14714 | +| time_elapsed | 21461 | +| total_timesteps | 30134272 | +| train/ | | +| approx_kl | 0.014425281 | +| clip_fraction | 0.352 | +| clip_range | 0.0675 | +| entropy_loss | -6.42 | +| explained_variance | -0.0717 | +| learning_rate | 4.28e-05 | +| loss | -0.0261 | +| n_updates | 74672 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000217 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1404 | +| iterations | 14715 | +| time_elapsed | 21463 | +| total_timesteps | 30136320 | +| train/ | | +| approx_kl | 0.016249862 | +| clip_fraction | 0.331 | +| clip_range | 0.0675 | +| entropy_loss | -6.12 | +| explained_variance | 0.36 | +| learning_rate | 4.28e-05 | +| loss | -0.0208 | +| n_updates | 74676 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000227 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1404 | +| iterations | 14716 | +| time_elapsed | 21464 | +| total_timesteps | 30138368 | +| train/ | | +| approx_kl | 0.013161531 | +| clip_fraction | 0.357 | +| clip_range | 0.0675 | +| entropy_loss | -6.13 | +| explained_variance | 0.406 | +| learning_rate | 4.28e-05 | +| loss | -0.0243 | +| n_updates | 74680 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000217 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1404 | +| iterations | 14717 | +| time_elapsed | 21466 | +| total_timesteps | 30140416 | +| train/ | | +| approx_kl | 0.012460543 | +| clip_fraction | 0.349 | +| clip_range | 0.0675 | +| entropy_loss | -6.23 | +| explained_variance | 0.499 | +| learning_rate | 4.28e-05 | +| loss | -0.0275 | +| n_updates | 74684 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000126 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1404 | +| iterations | 14718 | +| time_elapsed | 21467 | +| total_timesteps | 30142464 | +| train/ | | +| approx_kl | 0.013222599 | +| clip_fraction | 0.36 | +| clip_range | 0.0675 | +| entropy_loss | -5.69 | +| explained_variance | 0.651 | +| learning_rate | 4.28e-05 | +| loss | -0.0292 | +| n_updates | 74688 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000135 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1404 | +| iterations | 14719 | +| time_elapsed | 21469 | +| total_timesteps | 30144512 | +| train/ | | +| approx_kl | 0.013454571 | +| clip_fraction | 0.337 | +| clip_range | 0.0675 | +| entropy_loss | -6.42 | +| explained_variance | -0.0181 | +| learning_rate | 4.28e-05 | +| loss | -0.0333 | +| n_updates | 74692 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000248 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1404 | +| iterations | 14720 | +| time_elapsed | 21470 | +| total_timesteps | 30146560 | +| train/ | | +| approx_kl | 0.016460286 | +| clip_fraction | 0.348 | +| clip_range | 0.0675 | +| entropy_loss | -6.71 | +| explained_variance | 0.188 | +| learning_rate | 4.28e-05 | +| loss | -0.0321 | +| n_updates | 74696 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000188 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1404 | +| iterations | 14721 | +| time_elapsed | 21472 | +| total_timesteps | 30148608 | +| train/ | | +| approx_kl | 0.012059724 | +| clip_fraction | 0.331 | +| clip_range | 0.0675 | +| entropy_loss | -6.14 | +| explained_variance | 0.445 | +| learning_rate | 4.28e-05 | +| loss | -0.0294 | +| n_updates | 74700 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000233 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1404 | +| iterations | 14722 | +| time_elapsed | 21474 | +| total_timesteps | 30150656 | +| train/ | | +| approx_kl | 0.013755494 | +| clip_fraction | 0.326 | +| clip_range | 0.0675 | +| entropy_loss | -6.18 | +| explained_variance | 0.31 | +| learning_rate | 4.28e-05 | +| loss | -0.0232 | +| n_updates | 74704 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.00029 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1404 | +| iterations | 14723 | +| time_elapsed | 21475 | +| total_timesteps | 30152704 | +| train/ | | +| approx_kl | 0.014619122 | +| clip_fraction | 0.336 | +| clip_range | 0.0675 | +| entropy_loss | -6.28 | +| explained_variance | 0.201 | +| learning_rate | 4.28e-05 | +| loss | -0.026 | +| n_updates | 74708 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000267 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1404 | +| iterations | 14724 | +| time_elapsed | 21477 | +| total_timesteps | 30154752 | +| train/ | | +| approx_kl | 0.013728986 | +| clip_fraction | 0.359 | +| clip_range | 0.0675 | +| entropy_loss | -5.95 | +| explained_variance | 0.402 | +| learning_rate | 4.28e-05 | +| loss | -0.0296 | +| n_updates | 74712 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000287 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1404 | +| iterations | 14725 | +| time_elapsed | 21478 | +| total_timesteps | 30156800 | +| train/ | | +| approx_kl | 0.014959548 | +| clip_fraction | 0.377 | +| clip_range | 0.0675 | +| entropy_loss | -6.31 | +| explained_variance | -0.128 | +| learning_rate | 4.28e-05 | +| loss | -0.0395 | +| n_updates | 74716 | +| policy_gradient_loss | -0.0238 | +| value_loss | 9.6e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1404 | +| iterations | 14726 | +| time_elapsed | 21480 | +| total_timesteps | 30158848 | +| train/ | | +| approx_kl | 0.0113929715 | +| clip_fraction | 0.364 | +| clip_range | 0.0675 | +| entropy_loss | -6.64 | +| explained_variance | 0.208 | +| learning_rate | 4.28e-05 | +| loss | -0.0299 | +| n_updates | 74720 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000164 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1404 | +| iterations | 14727 | +| time_elapsed | 21481 | +| total_timesteps | 30160896 | +| train/ | | +| approx_kl | 0.012392998 | +| clip_fraction | 0.336 | +| clip_range | 0.0675 | +| entropy_loss | -6.1 | +| explained_variance | 0.554 | +| learning_rate | 4.28e-05 | +| loss | -0.0272 | +| n_updates | 74724 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.00014 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1404 | +| iterations | 14728 | +| time_elapsed | 21483 | +| total_timesteps | 30162944 | +| train/ | | +| approx_kl | 0.013796602 | +| clip_fraction | 0.352 | +| clip_range | 0.0675 | +| entropy_loss | -6.35 | +| explained_variance | 0.21 | +| learning_rate | 4.28e-05 | +| loss | -0.0285 | +| n_updates | 74728 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000147 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1404 | +| iterations | 14729 | +| time_elapsed | 21484 | +| total_timesteps | 30164992 | +| train/ | | +| approx_kl | 0.01841063 | +| clip_fraction | 0.326 | +| clip_range | 0.0675 | +| entropy_loss | -6.2 | +| explained_variance | 0.462 | +| learning_rate | 4.28e-05 | +| loss | -0.0284 | +| n_updates | 74732 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000164 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1404 | +| iterations | 14730 | +| time_elapsed | 21486 | +| total_timesteps | 30167040 | +| train/ | | +| approx_kl | 0.01698224 | +| clip_fraction | 0.337 | +| clip_range | 0.0675 | +| entropy_loss | -5.93 | +| explained_variance | 0.324 | +| learning_rate | 4.28e-05 | +| loss | -0.0252 | +| n_updates | 74736 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000248 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1403 | +| iterations | 14731 | +| time_elapsed | 21488 | +| total_timesteps | 30169088 | +| train/ | | +| approx_kl | 0.014427977 | +| clip_fraction | 0.313 | +| clip_range | 0.0675 | +| entropy_loss | -6.06 | +| explained_variance | 0.339 | +| learning_rate | 4.28e-05 | +| loss | -0.0253 | +| n_updates | 74740 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000311 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1403 | +| iterations | 14732 | +| time_elapsed | 21489 | +| total_timesteps | 30171136 | +| train/ | | +| approx_kl | 0.0156227425 | +| clip_fraction | 0.369 | +| clip_range | 0.0675 | +| entropy_loss | -6.13 | +| explained_variance | 0.391 | +| learning_rate | 4.28e-05 | +| loss | -0.0331 | +| n_updates | 74744 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000222 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1403 | +| iterations | 14733 | +| time_elapsed | 21491 | +| total_timesteps | 30173184 | +| train/ | | +| approx_kl | 0.01712244 | +| clip_fraction | 0.372 | +| clip_range | 0.0675 | +| entropy_loss | -6.02 | +| explained_variance | -0.0542 | +| learning_rate | 4.28e-05 | +| loss | -0.034 | +| n_updates | 74748 | +| policy_gradient_loss | -0.0227 | +| value_loss | 8.96e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1403 | +| iterations | 14734 | +| time_elapsed | 21492 | +| total_timesteps | 30175232 | +| train/ | | +| approx_kl | 0.015873656 | +| clip_fraction | 0.349 | +| clip_range | 0.0675 | +| entropy_loss | -6.32 | +| explained_variance | 0.104 | +| learning_rate | 4.28e-05 | +| loss | -0.0389 | +| n_updates | 74752 | +| policy_gradient_loss | -0.022 | +| value_loss | 8.79e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1403 | +| iterations | 14735 | +| time_elapsed | 21494 | +| total_timesteps | 30177280 | +| train/ | | +| approx_kl | 0.0153510235 | +| clip_fraction | 0.348 | +| clip_range | 0.0675 | +| entropy_loss | -6.33 | +| explained_variance | 0.557 | +| learning_rate | 4.28e-05 | +| loss | -0.0265 | +| n_updates | 74756 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000115 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1403 | +| iterations | 14736 | +| time_elapsed | 21495 | +| total_timesteps | 30179328 | +| train/ | | +| approx_kl | 0.013039655 | +| clip_fraction | 0.305 | +| clip_range | 0.0675 | +| entropy_loss | -5.35 | +| explained_variance | 0.643 | +| learning_rate | 4.28e-05 | +| loss | -0.0222 | +| n_updates | 74760 | +| policy_gradient_loss | -0.0143 | +| value_loss | 0.000205 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1403 | +| iterations | 14737 | +| time_elapsed | 21497 | +| total_timesteps | 30181376 | +| train/ | | +| approx_kl | 0.012314679 | +| clip_fraction | 0.339 | +| clip_range | 0.0675 | +| entropy_loss | -6.22 | +| explained_variance | 0.248 | +| learning_rate | 4.28e-05 | +| loss | -0.0281 | +| n_updates | 74764 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000279 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1403 | +| iterations | 14738 | +| time_elapsed | 21499 | +| total_timesteps | 30183424 | +| train/ | | +| approx_kl | 0.011719498 | +| clip_fraction | 0.332 | +| clip_range | 0.0675 | +| entropy_loss | -6.41 | +| explained_variance | 0.454 | +| learning_rate | 4.28e-05 | +| loss | -0.0307 | +| n_updates | 74768 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.00016 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1403 | +| iterations | 14739 | +| time_elapsed | 21500 | +| total_timesteps | 30185472 | +| train/ | | +| approx_kl | 0.0139806345 | +| clip_fraction | 0.328 | +| clip_range | 0.0675 | +| entropy_loss | -6.15 | +| explained_variance | 0.434 | +| learning_rate | 4.28e-05 | +| loss | -0.0261 | +| n_updates | 74772 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000119 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1403 | +| iterations | 14740 | +| time_elapsed | 21502 | +| total_timesteps | 30187520 | +| train/ | | +| approx_kl | 0.014618149 | +| clip_fraction | 0.358 | +| clip_range | 0.0675 | +| entropy_loss | -6.09 | +| explained_variance | 0.459 | +| learning_rate | 4.28e-05 | +| loss | -0.0287 | +| n_updates | 74776 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000155 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1403 | +| iterations | 14741 | +| time_elapsed | 21503 | +| total_timesteps | 30189568 | +| train/ | | +| approx_kl | 0.01453794 | +| clip_fraction | 0.355 | +| clip_range | 0.0675 | +| entropy_loss | -6.28 | +| explained_variance | 0.393 | +| learning_rate | 4.28e-05 | +| loss | -0.0295 | +| n_updates | 74780 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000124 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1403 | +| iterations | 14742 | +| time_elapsed | 21505 | +| total_timesteps | 30191616 | +| train/ | | +| approx_kl | 0.015716778 | +| clip_fraction | 0.381 | +| clip_range | 0.0675 | +| entropy_loss | -6.76 | +| explained_variance | -0.0713 | +| learning_rate | 4.28e-05 | +| loss | -0.0411 | +| n_updates | 74784 | +| policy_gradient_loss | -0.0221 | +| value_loss | 6.96e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1403 | +| iterations | 14743 | +| time_elapsed | 21506 | +| total_timesteps | 30193664 | +| train/ | | +| approx_kl | 0.012336565 | +| clip_fraction | 0.338 | +| clip_range | 0.0675 | +| entropy_loss | -6.43 | +| explained_variance | 0.218 | +| learning_rate | 4.28e-05 | +| loss | -0.0248 | +| n_updates | 74788 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000356 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1403 | +| iterations | 14744 | +| time_elapsed | 21508 | +| total_timesteps | 30195712 | +| train/ | | +| approx_kl | 0.01642821 | +| clip_fraction | 0.327 | +| clip_range | 0.0675 | +| entropy_loss | -6.24 | +| explained_variance | 0.548 | +| learning_rate | 4.28e-05 | +| loss | -0.0302 | +| n_updates | 74792 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000118 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1403 | +| iterations | 14745 | +| time_elapsed | 21509 | +| total_timesteps | 30197760 | +| train/ | | +| approx_kl | 0.012519515 | +| clip_fraction | 0.341 | +| clip_range | 0.0675 | +| entropy_loss | -6.11 | +| explained_variance | 0.41 | +| learning_rate | 4.28e-05 | +| loss | -0.0323 | +| n_updates | 74796 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000168 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1403 | +| iterations | 14746 | +| time_elapsed | 21511 | +| total_timesteps | 30199808 | +| train/ | | +| approx_kl | 0.014183312 | +| clip_fraction | 0.331 | +| clip_range | 0.0675 | +| entropy_loss | -5.79 | +| explained_variance | 0.474 | +| learning_rate | 4.28e-05 | +| loss | -0.0239 | +| n_updates | 74800 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000251 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1403 | +| iterations | 14747 | +| time_elapsed | 21513 | +| total_timesteps | 30201856 | +| train/ | | +| approx_kl | 0.012343712 | +| clip_fraction | 0.359 | +| clip_range | 0.0675 | +| entropy_loss | -6.24 | +| explained_variance | 0.478 | +| learning_rate | 4.28e-05 | +| loss | -0.0339 | +| n_updates | 74804 | +| policy_gradient_loss | -0.0222 | +| value_loss | 7.94e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1403 | +| iterations | 14748 | +| time_elapsed | 21514 | +| total_timesteps | 30203904 | +| train/ | | +| approx_kl | 0.014658818 | +| clip_fraction | 0.352 | +| clip_range | 0.0674 | +| entropy_loss | -6.74 | +| explained_variance | 0.103 | +| learning_rate | 4.28e-05 | +| loss | -0.0303 | +| n_updates | 74808 | +| policy_gradient_loss | -0.0199 | +| value_loss | 9.39e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1403 | +| iterations | 14749 | +| time_elapsed | 21516 | +| total_timesteps | 30205952 | +| train/ | | +| approx_kl | 0.010630856 | +| clip_fraction | 0.301 | +| clip_range | 0.0674 | +| entropy_loss | -6.14 | +| explained_variance | 0.354 | +| learning_rate | 4.28e-05 | +| loss | -0.0201 | +| n_updates | 74812 | +| policy_gradient_loss | -0.014 | +| value_loss | 0.000327 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1403 | +| iterations | 14750 | +| time_elapsed | 21517 | +| total_timesteps | 30208000 | +| train/ | | +| approx_kl | 0.015775004 | +| clip_fraction | 0.346 | +| clip_range | 0.0674 | +| entropy_loss | -5.76 | +| explained_variance | 0.45 | +| learning_rate | 4.28e-05 | +| loss | -0.0241 | +| n_updates | 74816 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000198 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1403 | +| iterations | 14751 | +| time_elapsed | 21519 | +| total_timesteps | 30210048 | +| train/ | | +| approx_kl | 0.01538154 | +| clip_fraction | 0.33 | +| clip_range | 0.0674 | +| entropy_loss | -5.45 | +| explained_variance | 0.592 | +| learning_rate | 4.28e-05 | +| loss | -0.0294 | +| n_updates | 74820 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000179 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1403 | +| iterations | 14752 | +| time_elapsed | 21520 | +| total_timesteps | 30212096 | +| train/ | | +| approx_kl | 0.011150287 | +| clip_fraction | 0.324 | +| clip_range | 0.0674 | +| entropy_loss | -6.19 | +| explained_variance | 0.315 | +| learning_rate | 4.28e-05 | +| loss | -0.0299 | +| n_updates | 74824 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000213 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1403 | +| iterations | 14753 | +| time_elapsed | 21522 | +| total_timesteps | 30214144 | +| train/ | | +| approx_kl | 0.010727877 | +| clip_fraction | 0.344 | +| clip_range | 0.0674 | +| entropy_loss | -6.73 | +| explained_variance | 0.0526 | +| learning_rate | 4.28e-05 | +| loss | -0.0338 | +| n_updates | 74828 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.00032 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1403 | +| iterations | 14754 | +| time_elapsed | 21523 | +| total_timesteps | 30216192 | +| train/ | | +| approx_kl | 0.010181533 | +| clip_fraction | 0.323 | +| clip_range | 0.0674 | +| entropy_loss | -6.4 | +| explained_variance | 0.43 | +| learning_rate | 4.28e-05 | +| loss | -0.0277 | +| n_updates | 74832 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000217 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1403 | +| iterations | 14755 | +| time_elapsed | 21525 | +| total_timesteps | 30218240 | +| train/ | | +| approx_kl | 0.012119366 | +| clip_fraction | 0.326 | +| clip_range | 0.0674 | +| entropy_loss | -6.17 | +| explained_variance | 0.3 | +| learning_rate | 4.28e-05 | +| loss | -0.0271 | +| n_updates | 74836 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000274 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1403 | +| iterations | 14756 | +| time_elapsed | 21526 | +| total_timesteps | 30220288 | +| train/ | | +| approx_kl | 0.013595475 | +| clip_fraction | 0.378 | +| clip_range | 0.0674 | +| entropy_loss | -5.85 | +| explained_variance | 0.73 | +| learning_rate | 4.28e-05 | +| loss | -0.0359 | +| n_updates | 74840 | +| policy_gradient_loss | -0.0229 | +| value_loss | 6.05e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1403 | +| iterations | 14757 | +| time_elapsed | 21528 | +| total_timesteps | 30222336 | +| train/ | | +| approx_kl | 0.012897847 | +| clip_fraction | 0.314 | +| clip_range | 0.0674 | +| entropy_loss | -6.02 | +| explained_variance | 0.35 | +| learning_rate | 4.28e-05 | +| loss | -0.0267 | +| n_updates | 74844 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000413 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1403 | +| iterations | 14758 | +| time_elapsed | 21529 | +| total_timesteps | 30224384 | +| train/ | | +| approx_kl | 0.013593157 | +| clip_fraction | 0.331 | +| clip_range | 0.0674 | +| entropy_loss | -5.91 | +| explained_variance | 0.349 | +| learning_rate | 4.28e-05 | +| loss | -0.031 | +| n_updates | 74848 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000153 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1403 | +| iterations | 14759 | +| time_elapsed | 21531 | +| total_timesteps | 30226432 | +| train/ | | +| approx_kl | 0.014807307 | +| clip_fraction | 0.312 | +| clip_range | 0.0674 | +| entropy_loss | -6.33 | +| explained_variance | 0.321 | +| learning_rate | 4.28e-05 | +| loss | -0.0227 | +| n_updates | 74852 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000308 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1403 | +| iterations | 14760 | +| time_elapsed | 21533 | +| total_timesteps | 30228480 | +| train/ | | +| approx_kl | 0.012002745 | +| clip_fraction | 0.35 | +| clip_range | 0.0674 | +| entropy_loss | -6.24 | +| explained_variance | 0.338 | +| learning_rate | 4.28e-05 | +| loss | -0.0274 | +| n_updates | 74856 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000143 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1403 | +| iterations | 14761 | +| time_elapsed | 21534 | +| total_timesteps | 30230528 | +| train/ | | +| approx_kl | 0.011485861 | +| clip_fraction | 0.326 | +| clip_range | 0.0674 | +| entropy_loss | -6.35 | +| explained_variance | 0.522 | +| learning_rate | 4.28e-05 | +| loss | -0.025 | +| n_updates | 74860 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.00015 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1403 | +| iterations | 14762 | +| time_elapsed | 21536 | +| total_timesteps | 30232576 | +| train/ | | +| approx_kl | 0.011749215 | +| clip_fraction | 0.323 | +| clip_range | 0.0674 | +| entropy_loss | -6.28 | +| explained_variance | 0.37 | +| learning_rate | 4.28e-05 | +| loss | -0.0332 | +| n_updates | 74864 | +| policy_gradient_loss | -0.0189 | +| value_loss | 8.45e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1403 | +| iterations | 14763 | +| time_elapsed | 21537 | +| total_timesteps | 30234624 | +| train/ | | +| approx_kl | 0.015126506 | +| clip_fraction | 0.348 | +| clip_range | 0.0674 | +| entropy_loss | -6.39 | +| explained_variance | 0.663 | +| learning_rate | 4.28e-05 | +| loss | -0.031 | +| n_updates | 74868 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000107 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1403 | +| iterations | 14764 | +| time_elapsed | 21539 | +| total_timesteps | 30236672 | +| train/ | | +| approx_kl | 0.01550881 | +| clip_fraction | 0.372 | +| clip_range | 0.0674 | +| entropy_loss | -6.28 | +| explained_variance | -0.651 | +| learning_rate | 4.28e-05 | +| loss | -0.0324 | +| n_updates | 74872 | +| policy_gradient_loss | -0.0222 | +| value_loss | 5.64e-05 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1403 | +| iterations | 14765 | +| time_elapsed | 21540 | +| total_timesteps | 30238720 | +| train/ | | +| approx_kl | 0.01562858 | +| clip_fraction | 0.343 | +| clip_range | 0.0674 | +| entropy_loss | -5.65 | +| explained_variance | 0.687 | +| learning_rate | 4.28e-05 | +| loss | -0.0293 | +| n_updates | 74876 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000106 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1403 | +| iterations | 14766 | +| time_elapsed | 21542 | +| total_timesteps | 30240768 | +| train/ | | +| approx_kl | 0.013702187 | +| clip_fraction | 0.349 | +| clip_range | 0.0674 | +| entropy_loss | -6.3 | +| explained_variance | 0.491 | +| learning_rate | 4.28e-05 | +| loss | -0.0285 | +| n_updates | 74880 | +| policy_gradient_loss | -0.0181 | +| value_loss | 8.51e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1403 | +| iterations | 14767 | +| time_elapsed | 21543 | +| total_timesteps | 30242816 | +| train/ | | +| approx_kl | 0.01343862 | +| clip_fraction | 0.328 | +| clip_range | 0.0674 | +| entropy_loss | -6.54 | +| explained_variance | 0.666 | +| learning_rate | 4.28e-05 | +| loss | -0.0351 | +| n_updates | 74884 | +| policy_gradient_loss | -0.0181 | +| value_loss | 9.42e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1403 | +| iterations | 14768 | +| time_elapsed | 21545 | +| total_timesteps | 30244864 | +| train/ | | +| approx_kl | 0.013364669 | +| clip_fraction | 0.345 | +| clip_range | 0.0674 | +| entropy_loss | -6.29 | +| explained_variance | 0.229 | +| learning_rate | 4.28e-05 | +| loss | -0.0334 | +| n_updates | 74888 | +| policy_gradient_loss | -0.0187 | +| value_loss | 8.82e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1403 | +| iterations | 14769 | +| time_elapsed | 21546 | +| total_timesteps | 30246912 | +| train/ | | +| approx_kl | 0.010232624 | +| clip_fraction | 0.302 | +| clip_range | 0.0674 | +| entropy_loss | -6.24 | +| explained_variance | 0.591 | +| learning_rate | 4.28e-05 | +| loss | -0.0284 | +| n_updates | 74892 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000106 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1403 | +| iterations | 14770 | +| time_elapsed | 21548 | +| total_timesteps | 30248960 | +| train/ | | +| approx_kl | 0.011761623 | +| clip_fraction | 0.311 | +| clip_range | 0.0674 | +| entropy_loss | -6.39 | +| explained_variance | 0.309 | +| learning_rate | 4.28e-05 | +| loss | -0.0332 | +| n_updates | 74896 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000169 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1403 | +| iterations | 14771 | +| time_elapsed | 21549 | +| total_timesteps | 30251008 | +| train/ | | +| approx_kl | 0.014388772 | +| clip_fraction | 0.362 | +| clip_range | 0.0674 | +| entropy_loss | -6.12 | +| explained_variance | 0.59 | +| learning_rate | 4.28e-05 | +| loss | -0.031 | +| n_updates | 74900 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000107 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1403 | +| iterations | 14772 | +| time_elapsed | 21551 | +| total_timesteps | 30253056 | +| train/ | | +| approx_kl | 0.014738153 | +| clip_fraction | 0.346 | +| clip_range | 0.0674 | +| entropy_loss | -5.55 | +| explained_variance | 0.751 | +| learning_rate | 4.28e-05 | +| loss | -0.0288 | +| n_updates | 74904 | +| policy_gradient_loss | -0.0185 | +| value_loss | 9.64e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1403 | +| iterations | 14773 | +| time_elapsed | 21552 | +| total_timesteps | 30255104 | +| train/ | | +| approx_kl | 0.0120620895 | +| clip_fraction | 0.338 | +| clip_range | 0.0674 | +| entropy_loss | -6 | +| explained_variance | 0.335 | +| learning_rate | 4.28e-05 | +| loss | -0.0324 | +| n_updates | 74908 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000157 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1403 | +| iterations | 14774 | +| time_elapsed | 21554 | +| total_timesteps | 30257152 | +| train/ | | +| approx_kl | 0.011931901 | +| clip_fraction | 0.347 | +| clip_range | 0.0674 | +| entropy_loss | -6.45 | +| explained_variance | 0.58 | +| learning_rate | 4.28e-05 | +| loss | -0.0363 | +| n_updates | 74912 | +| policy_gradient_loss | -0.0203 | +| value_loss | 6.44e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1403 | +| iterations | 14775 | +| time_elapsed | 21555 | +| total_timesteps | 30259200 | +| train/ | | +| approx_kl | 0.015679907 | +| clip_fraction | 0.332 | +| clip_range | 0.0674 | +| entropy_loss | -6.42 | +| explained_variance | 0.261 | +| learning_rate | 4.28e-05 | +| loss | -0.0292 | +| n_updates | 74916 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000167 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1403 | +| iterations | 14776 | +| time_elapsed | 21557 | +| total_timesteps | 30261248 | +| train/ | | +| approx_kl | 0.011471704 | +| clip_fraction | 0.301 | +| clip_range | 0.0674 | +| entropy_loss | -6.63 | +| explained_variance | 0.441 | +| learning_rate | 4.28e-05 | +| loss | -0.0267 | +| n_updates | 74920 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000171 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1403 | +| iterations | 14777 | +| time_elapsed | 21558 | +| total_timesteps | 30263296 | +| train/ | | +| approx_kl | 0.014583088 | +| clip_fraction | 0.359 | +| clip_range | 0.0674 | +| entropy_loss | -6.51 | +| explained_variance | 0.507 | +| learning_rate | 4.28e-05 | +| loss | -0.027 | +| n_updates | 74924 | +| policy_gradient_loss | -0.0189 | +| value_loss | 7.4e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1403 | +| iterations | 14778 | +| time_elapsed | 21560 | +| total_timesteps | 30265344 | +| train/ | | +| approx_kl | 0.010908272 | +| clip_fraction | 0.33 | +| clip_range | 0.0674 | +| entropy_loss | -5.9 | +| explained_variance | 0.639 | +| learning_rate | 4.28e-05 | +| loss | -0.0247 | +| n_updates | 74928 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000118 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1403 | +| iterations | 14779 | +| time_elapsed | 21561 | +| total_timesteps | 30267392 | +| train/ | | +| approx_kl | 0.011055917 | +| clip_fraction | 0.33 | +| clip_range | 0.0674 | +| entropy_loss | -6.5 | +| explained_variance | 0.351 | +| learning_rate | 4.28e-05 | +| loss | -0.0246 | +| n_updates | 74932 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000152 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1403 | +| iterations | 14780 | +| time_elapsed | 21563 | +| total_timesteps | 30269440 | +| train/ | | +| approx_kl | 0.008215582 | +| clip_fraction | 0.303 | +| clip_range | 0.0674 | +| entropy_loss | -6.29 | +| explained_variance | 0.415 | +| learning_rate | 4.28e-05 | +| loss | -0.0276 | +| n_updates | 74936 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000221 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1403 | +| iterations | 14781 | +| time_elapsed | 21564 | +| total_timesteps | 30271488 | +| train/ | | +| approx_kl | 0.012683498 | +| clip_fraction | 0.317 | +| clip_range | 0.0674 | +| entropy_loss | -6.08 | +| explained_variance | 0.569 | +| learning_rate | 4.28e-05 | +| loss | -0.0305 | +| n_updates | 74940 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000144 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1403 | +| iterations | 14782 | +| time_elapsed | 21566 | +| total_timesteps | 30273536 | +| train/ | | +| approx_kl | 0.014301563 | +| clip_fraction | 0.364 | +| clip_range | 0.0674 | +| entropy_loss | -6.47 | +| explained_variance | 0.076 | +| learning_rate | 4.28e-05 | +| loss | -0.0285 | +| n_updates | 74944 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000103 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1403 | +| iterations | 14783 | +| time_elapsed | 21567 | +| total_timesteps | 30275584 | +| train/ | | +| approx_kl | 0.014390109 | +| clip_fraction | 0.309 | +| clip_range | 0.0674 | +| entropy_loss | -6.44 | +| explained_variance | 0.508 | +| learning_rate | 4.28e-05 | +| loss | -0.0276 | +| n_updates | 74948 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000198 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1403 | +| iterations | 14784 | +| time_elapsed | 21569 | +| total_timesteps | 30277632 | +| train/ | | +| approx_kl | 0.013647504 | +| clip_fraction | 0.352 | +| clip_range | 0.0674 | +| entropy_loss | -6.06 | +| explained_variance | 0.51 | +| learning_rate | 4.28e-05 | +| loss | -0.0312 | +| n_updates | 74952 | +| policy_gradient_loss | -0.0185 | +| value_loss | 9.63e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1403 | +| iterations | 14785 | +| time_elapsed | 21571 | +| total_timesteps | 30279680 | +| train/ | | +| approx_kl | 0.01102945 | +| clip_fraction | 0.342 | +| clip_range | 0.0674 | +| entropy_loss | -6.52 | +| explained_variance | 0.592 | +| learning_rate | 4.28e-05 | +| loss | -0.0264 | +| n_updates | 74956 | +| policy_gradient_loss | -0.02 | +| value_loss | 6.47e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1403 | +| iterations | 14786 | +| time_elapsed | 21572 | +| total_timesteps | 30281728 | +| train/ | | +| approx_kl | 0.011703889 | +| clip_fraction | 0.324 | +| clip_range | 0.0674 | +| entropy_loss | -6.71 | +| explained_variance | 0.318 | +| learning_rate | 4.28e-05 | +| loss | -0.0308 | +| n_updates | 74960 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000131 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1403 | +| iterations | 14787 | +| time_elapsed | 21574 | +| total_timesteps | 30283776 | +| train/ | | +| approx_kl | 0.0125142 | +| clip_fraction | 0.334 | +| clip_range | 0.0674 | +| entropy_loss | -6.47 | +| explained_variance | 0.208 | +| learning_rate | 4.28e-05 | +| loss | -0.018 | +| n_updates | 74964 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.00023 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1403 | +| iterations | 14788 | +| time_elapsed | 21575 | +| total_timesteps | 30285824 | +| train/ | | +| approx_kl | 0.014554354 | +| clip_fraction | 0.365 | +| clip_range | 0.0674 | +| entropy_loss | -5.8 | +| explained_variance | 0.739 | +| learning_rate | 4.28e-05 | +| loss | -0.0272 | +| n_updates | 74968 | +| policy_gradient_loss | -0.0185 | +| value_loss | 7.67e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1403 | +| iterations | 14789 | +| time_elapsed | 21577 | +| total_timesteps | 30287872 | +| train/ | | +| approx_kl | 0.012663844 | +| clip_fraction | 0.305 | +| clip_range | 0.0674 | +| entropy_loss | -6.66 | +| explained_variance | -0.00862 | +| learning_rate | 4.28e-05 | +| loss | -0.0231 | +| n_updates | 74972 | +| policy_gradient_loss | -0.0144 | +| value_loss | 0.000212 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1403 | +| iterations | 14790 | +| time_elapsed | 21578 | +| total_timesteps | 30289920 | +| train/ | | +| approx_kl | 0.011266267 | +| clip_fraction | 0.316 | +| clip_range | 0.0674 | +| entropy_loss | -7.03 | +| explained_variance | -0.103 | +| learning_rate | 4.28e-05 | +| loss | -0.0277 | +| n_updates | 74976 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000179 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 1403 | +| iterations | 14791 | +| time_elapsed | 21580 | +| total_timesteps | 30291968 | +| train/ | | +| approx_kl | 0.0125521775 | +| clip_fraction | 0.341 | +| clip_range | 0.0674 | +| entropy_loss | -6.32 | +| explained_variance | 0.455 | +| learning_rate | 4.28e-05 | +| loss | -0.0238 | +| n_updates | 74980 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000112 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.304 | +| time/ | | +| fps | 1403 | +| iterations | 14792 | +| time_elapsed | 21581 | +| total_timesteps | 30294016 | +| train/ | | +| approx_kl | 0.011588733 | +| clip_fraction | 0.346 | +| clip_range | 0.0674 | +| entropy_loss | -6.27 | +| explained_variance | 0.424 | +| learning_rate | 4.28e-05 | +| loss | -0.0349 | +| n_updates | 74984 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000114 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1403 | +| iterations | 14793 | +| time_elapsed | 21583 | +| total_timesteps | 30296064 | +| train/ | | +| approx_kl | 0.011331636 | +| clip_fraction | 0.329 | +| clip_range | 0.0674 | +| entropy_loss | -6.68 | +| explained_variance | 0.48 | +| learning_rate | 4.28e-05 | +| loss | -0.0271 | +| n_updates | 74988 | +| policy_gradient_loss | -0.0163 | +| value_loss | 7.47e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 1403 | +| iterations | 14794 | +| time_elapsed | 21584 | +| total_timesteps | 30298112 | +| train/ | | +| approx_kl | 0.013595337 | +| clip_fraction | 0.312 | +| clip_range | 0.0674 | +| entropy_loss | -6.12 | +| explained_variance | 0.47 | +| learning_rate | 4.28e-05 | +| loss | -0.0207 | +| n_updates | 74992 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000266 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1403 | +| iterations | 14795 | +| time_elapsed | 21586 | +| total_timesteps | 30300160 | +| train/ | | +| approx_kl | 0.0134030115 | +| clip_fraction | 0.315 | +| clip_range | 0.0674 | +| entropy_loss | -5.95 | +| explained_variance | 0.488 | +| learning_rate | 4.28e-05 | +| loss | -0.0261 | +| n_updates | 74996 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000131 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.304 | +| time/ | | +| fps | 1403 | +| iterations | 14796 | +| time_elapsed | 21587 | +| total_timesteps | 30302208 | +| train/ | | +| approx_kl | 0.015250272 | +| clip_fraction | 0.348 | +| clip_range | 0.0674 | +| entropy_loss | -6.1 | +| explained_variance | 0.502 | +| learning_rate | 4.28e-05 | +| loss | -0.0293 | +| n_updates | 75000 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000149 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.304 | +| time/ | | +| fps | 1403 | +| iterations | 14797 | +| time_elapsed | 21589 | +| total_timesteps | 30304256 | +| train/ | | +| approx_kl | 0.015762657 | +| clip_fraction | 0.378 | +| clip_range | 0.0674 | +| entropy_loss | -6.02 | +| explained_variance | 0.425 | +| learning_rate | 4.28e-05 | +| loss | -0.0422 | +| n_updates | 75004 | +| policy_gradient_loss | -0.0246 | +| value_loss | 3.31e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1403 | +| iterations | 14798 | +| time_elapsed | 21590 | +| total_timesteps | 30306304 | +| train/ | | +| approx_kl | 0.0088356435 | +| clip_fraction | 0.293 | +| clip_range | 0.0674 | +| entropy_loss | -6.52 | +| explained_variance | 0.347 | +| learning_rate | 4.28e-05 | +| loss | -0.0235 | +| n_updates | 75008 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000235 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 1403 | +| iterations | 14799 | +| time_elapsed | 21592 | +| total_timesteps | 30308352 | +| train/ | | +| approx_kl | 0.011407537 | +| clip_fraction | 0.314 | +| clip_range | 0.0674 | +| entropy_loss | -6.4 | +| explained_variance | 0.532 | +| learning_rate | 4.28e-05 | +| loss | -0.0285 | +| n_updates | 75012 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000134 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 1403 | +| iterations | 14800 | +| time_elapsed | 21594 | +| total_timesteps | 30310400 | +| train/ | | +| approx_kl | 0.012497002 | +| clip_fraction | 0.347 | +| clip_range | 0.0674 | +| entropy_loss | -6.17 | +| explained_variance | 0.628 | +| learning_rate | 4.28e-05 | +| loss | -0.0353 | +| n_updates | 75016 | +| policy_gradient_loss | -0.0203 | +| value_loss | 9.65e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 1403 | +| iterations | 14801 | +| time_elapsed | 21595 | +| total_timesteps | 30312448 | +| train/ | | +| approx_kl | 0.012528614 | +| clip_fraction | 0.322 | +| clip_range | 0.0674 | +| entropy_loss | -6.45 | +| explained_variance | 0.211 | +| learning_rate | 4.28e-05 | +| loss | -0.0258 | +| n_updates | 75020 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000116 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 1403 | +| iterations | 14802 | +| time_elapsed | 21597 | +| total_timesteps | 30314496 | +| train/ | | +| approx_kl | 0.01096352 | +| clip_fraction | 0.332 | +| clip_range | 0.0674 | +| entropy_loss | -7.03 | +| explained_variance | -0.0532 | +| learning_rate | 4.28e-05 | +| loss | -0.0233 | +| n_updates | 75024 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000112 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1403 | +| iterations | 14803 | +| time_elapsed | 21598 | +| total_timesteps | 30316544 | +| train/ | | +| approx_kl | 0.011355173 | +| clip_fraction | 0.324 | +| clip_range | 0.0674 | +| entropy_loss | -6.49 | +| explained_variance | 0.399 | +| learning_rate | 4.28e-05 | +| loss | -0.0246 | +| n_updates | 75028 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000219 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1403 | +| iterations | 14804 | +| time_elapsed | 21600 | +| total_timesteps | 30318592 | +| train/ | | +| approx_kl | 0.011816719 | +| clip_fraction | 0.307 | +| clip_range | 0.0674 | +| entropy_loss | -5.78 | +| explained_variance | 0.629 | +| learning_rate | 4.28e-05 | +| loss | -0.0236 | +| n_updates | 75032 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000123 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1403 | +| iterations | 14805 | +| time_elapsed | 21601 | +| total_timesteps | 30320640 | +| train/ | | +| approx_kl | 0.012926184 | +| clip_fraction | 0.352 | +| clip_range | 0.0674 | +| entropy_loss | -5.68 | +| explained_variance | 0.671 | +| learning_rate | 4.28e-05 | +| loss | -0.0322 | +| n_updates | 75036 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000116 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1403 | +| iterations | 14806 | +| time_elapsed | 21603 | +| total_timesteps | 30322688 | +| train/ | | +| approx_kl | 0.011252569 | +| clip_fraction | 0.364 | +| clip_range | 0.0674 | +| entropy_loss | -6.29 | +| explained_variance | 0.566 | +| learning_rate | 4.28e-05 | +| loss | -0.0333 | +| n_updates | 75040 | +| policy_gradient_loss | -0.0209 | +| value_loss | 6.01e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1403 | +| iterations | 14807 | +| time_elapsed | 21604 | +| total_timesteps | 30324736 | +| train/ | | +| approx_kl | 0.013983531 | +| clip_fraction | 0.308 | +| clip_range | 0.0674 | +| entropy_loss | -5.85 | +| explained_variance | 0.589 | +| learning_rate | 4.28e-05 | +| loss | -0.0258 | +| n_updates | 75044 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000211 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1403 | +| iterations | 14808 | +| time_elapsed | 21606 | +| total_timesteps | 30326784 | +| train/ | | +| approx_kl | 0.013992326 | +| clip_fraction | 0.35 | +| clip_range | 0.0674 | +| entropy_loss | -6.28 | +| explained_variance | 0.0846 | +| learning_rate | 4.28e-05 | +| loss | -0.0286 | +| n_updates | 75048 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000114 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1403 | +| iterations | 14809 | +| time_elapsed | 21607 | +| total_timesteps | 30328832 | +| train/ | | +| approx_kl | 0.016430752 | +| clip_fraction | 0.357 | +| clip_range | 0.0674 | +| entropy_loss | -5.75 | +| explained_variance | 0.526 | +| learning_rate | 4.28e-05 | +| loss | -0.0273 | +| n_updates | 75052 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000236 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1403 | +| iterations | 14810 | +| time_elapsed | 21609 | +| total_timesteps | 30330880 | +| train/ | | +| approx_kl | 0.015900806 | +| clip_fraction | 0.342 | +| clip_range | 0.0674 | +| entropy_loss | -6.06 | +| explained_variance | -0.23 | +| learning_rate | 4.28e-05 | +| loss | -0.0309 | +| n_updates | 75056 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000105 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1403 | +| iterations | 14811 | +| time_elapsed | 21610 | +| total_timesteps | 30332928 | +| train/ | | +| approx_kl | 0.02079976 | +| clip_fraction | 0.387 | +| clip_range | 0.0674 | +| entropy_loss | -6.49 | +| explained_variance | -0.114 | +| learning_rate | 4.28e-05 | +| loss | -0.0303 | +| n_updates | 75060 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000126 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1403 | +| iterations | 14812 | +| time_elapsed | 21612 | +| total_timesteps | 30334976 | +| train/ | | +| approx_kl | 0.013254235 | +| clip_fraction | 0.332 | +| clip_range | 0.0674 | +| entropy_loss | -6.26 | +| explained_variance | 0.336 | +| learning_rate | 4.28e-05 | +| loss | -0.0221 | +| n_updates | 75064 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000241 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1403 | +| iterations | 14813 | +| time_elapsed | 21614 | +| total_timesteps | 30337024 | +| train/ | | +| approx_kl | 0.013573116 | +| clip_fraction | 0.346 | +| clip_range | 0.0674 | +| entropy_loss | -6.51 | +| explained_variance | 0.108 | +| learning_rate | 4.28e-05 | +| loss | -0.0323 | +| n_updates | 75068 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.00011 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.3 | +| time/ | | +| fps | 1403 | +| iterations | 14814 | +| time_elapsed | 21615 | +| total_timesteps | 30339072 | +| train/ | | +| approx_kl | 0.01084668 | +| clip_fraction | 0.32 | +| clip_range | 0.0674 | +| entropy_loss | -6.67 | +| explained_variance | 0.0584 | +| learning_rate | 4.28e-05 | +| loss | -0.0254 | +| n_updates | 75072 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000226 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.295 | +| time/ | | +| fps | 1403 | +| iterations | 14815 | +| time_elapsed | 21617 | +| total_timesteps | 30341120 | +| train/ | | +| approx_kl | 0.013980836 | +| clip_fraction | 0.32 | +| clip_range | 0.0674 | +| entropy_loss | -5.92 | +| explained_variance | 0.35 | +| learning_rate | 4.28e-05 | +| loss | -0.0255 | +| n_updates | 75076 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000211 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.295 | +| time/ | | +| fps | 1403 | +| iterations | 14816 | +| time_elapsed | 21618 | +| total_timesteps | 30343168 | +| train/ | | +| approx_kl | 0.012130836 | +| clip_fraction | 0.333 | +| clip_range | 0.0674 | +| entropy_loss | -5.37 | +| explained_variance | 0.774 | +| learning_rate | 4.28e-05 | +| loss | -0.0288 | +| n_updates | 75080 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000103 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.295 | +| time/ | | +| fps | 1403 | +| iterations | 14817 | +| time_elapsed | 21620 | +| total_timesteps | 30345216 | +| train/ | | +| approx_kl | 0.011750216 | +| clip_fraction | 0.358 | +| clip_range | 0.0674 | +| entropy_loss | -6.25 | +| explained_variance | -0.177 | +| learning_rate | 4.28e-05 | +| loss | -0.0319 | +| n_updates | 75084 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000125 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.295 | +| time/ | | +| fps | 1403 | +| iterations | 14818 | +| time_elapsed | 21621 | +| total_timesteps | 30347264 | +| train/ | | +| approx_kl | 0.011518717 | +| clip_fraction | 0.313 | +| clip_range | 0.0674 | +| entropy_loss | -6.86 | +| explained_variance | 0.158 | +| learning_rate | 4.28e-05 | +| loss | -0.0252 | +| n_updates | 75088 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000149 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.294 | +| time/ | | +| fps | 1403 | +| iterations | 14819 | +| time_elapsed | 21623 | +| total_timesteps | 30349312 | +| train/ | | +| approx_kl | 0.012083783 | +| clip_fraction | 0.35 | +| clip_range | 0.0674 | +| entropy_loss | -6.28 | +| explained_variance | 0.472 | +| learning_rate | 4.28e-05 | +| loss | -0.0293 | +| n_updates | 75092 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.00017 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.29 | +| time/ | | +| fps | 1403 | +| iterations | 14820 | +| time_elapsed | 21624 | +| total_timesteps | 30351360 | +| train/ | | +| approx_kl | 0.0113853095 | +| clip_fraction | 0.334 | +| clip_range | 0.0674 | +| entropy_loss | -6.19 | +| explained_variance | 0.493 | +| learning_rate | 4.28e-05 | +| loss | -0.0254 | +| n_updates | 75096 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000157 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.289 | +| time/ | | +| fps | 1403 | +| iterations | 14821 | +| time_elapsed | 21626 | +| total_timesteps | 30353408 | +| train/ | | +| approx_kl | 0.012095361 | +| clip_fraction | 0.354 | +| clip_range | 0.0674 | +| entropy_loss | -6.12 | +| explained_variance | 0.651 | +| learning_rate | 4.28e-05 | +| loss | -0.0324 | +| n_updates | 75100 | +| policy_gradient_loss | -0.0198 | +| value_loss | 8.52e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.293 | +| time/ | | +| fps | 1403 | +| iterations | 14822 | +| time_elapsed | 21627 | +| total_timesteps | 30355456 | +| train/ | | +| approx_kl | 0.009596978 | +| clip_fraction | 0.314 | +| clip_range | 0.0674 | +| entropy_loss | -6.14 | +| explained_variance | 0.465 | +| learning_rate | 4.28e-05 | +| loss | -0.0212 | +| n_updates | 75104 | +| policy_gradient_loss | -0.0145 | +| value_loss | 0.000159 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.291 | +| time/ | | +| fps | 1403 | +| iterations | 14823 | +| time_elapsed | 21629 | +| total_timesteps | 30357504 | +| train/ | | +| approx_kl | 0.008995849 | +| clip_fraction | 0.281 | +| clip_range | 0.0674 | +| entropy_loss | -6.17 | +| explained_variance | 0.423 | +| learning_rate | 4.28e-05 | +| loss | -0.0243 | +| n_updates | 75108 | +| policy_gradient_loss | -0.0143 | +| value_loss | 0.000247 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.294 | +| time/ | | +| fps | 1403 | +| iterations | 14824 | +| time_elapsed | 21630 | +| total_timesteps | 30359552 | +| train/ | | +| approx_kl | 0.0089683235 | +| clip_fraction | 0.3 | +| clip_range | 0.0674 | +| entropy_loss | -6.42 | +| explained_variance | 0.2 | +| learning_rate | 4.28e-05 | +| loss | -0.0301 | +| n_updates | 75112 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000178 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 1403 | +| iterations | 14825 | +| time_elapsed | 21632 | +| total_timesteps | 30361600 | +| train/ | | +| approx_kl | 0.012325573 | +| clip_fraction | 0.342 | +| clip_range | 0.0674 | +| entropy_loss | -6.14 | +| explained_variance | 0.66 | +| learning_rate | 4.28e-05 | +| loss | -0.0269 | +| n_updates | 75116 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000102 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 1403 | +| iterations | 14826 | +| time_elapsed | 21633 | +| total_timesteps | 30363648 | +| train/ | | +| approx_kl | 0.009203006 | +| clip_fraction | 0.292 | +| clip_range | 0.0674 | +| entropy_loss | -5.85 | +| explained_variance | 0.549 | +| learning_rate | 4.28e-05 | +| loss | -0.018 | +| n_updates | 75120 | +| policy_gradient_loss | -0.0119 | +| value_loss | 0.000265 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 1403 | +| iterations | 14827 | +| time_elapsed | 21635 | +| total_timesteps | 30365696 | +| train/ | | +| approx_kl | 0.014007329 | +| clip_fraction | 0.392 | +| clip_range | 0.0674 | +| entropy_loss | -6.3 | +| explained_variance | -0.267 | +| learning_rate | 4.28e-05 | +| loss | -0.0336 | +| n_updates | 75124 | +| policy_gradient_loss | -0.0223 | +| value_loss | 9.98e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 1403 | +| iterations | 14828 | +| time_elapsed | 21637 | +| total_timesteps | 30367744 | +| train/ | | +| approx_kl | 0.01224968 | +| clip_fraction | 0.361 | +| clip_range | 0.0674 | +| entropy_loss | -6.54 | +| explained_variance | 0.315 | +| learning_rate | 4.28e-05 | +| loss | -0.0305 | +| n_updates | 75128 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.00012 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 1403 | +| iterations | 14829 | +| time_elapsed | 21638 | +| total_timesteps | 30369792 | +| train/ | | +| approx_kl | 0.012224236 | +| clip_fraction | 0.366 | +| clip_range | 0.0674 | +| entropy_loss | -6.67 | +| explained_variance | -0.0245 | +| learning_rate | 4.28e-05 | +| loss | -0.0252 | +| n_updates | 75132 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000117 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1403 | +| iterations | 14830 | +| time_elapsed | 21640 | +| total_timesteps | 30371840 | +| train/ | | +| approx_kl | 0.013581464 | +| clip_fraction | 0.355 | +| clip_range | 0.0674 | +| entropy_loss | -6.63 | +| explained_variance | -0.0781 | +| learning_rate | 4.28e-05 | +| loss | -0.0223 | +| n_updates | 75136 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000118 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1403 | +| iterations | 14831 | +| time_elapsed | 21641 | +| total_timesteps | 30373888 | +| train/ | | +| approx_kl | 0.017586686 | +| clip_fraction | 0.358 | +| clip_range | 0.0674 | +| entropy_loss | -6.31 | +| explained_variance | 0.28 | +| learning_rate | 4.28e-05 | +| loss | -0.027 | +| n_updates | 75140 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000134 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1403 | +| iterations | 14832 | +| time_elapsed | 21643 | +| total_timesteps | 30375936 | +| train/ | | +| approx_kl | 0.013546307 | +| clip_fraction | 0.375 | +| clip_range | 0.0674 | +| entropy_loss | -6.42 | +| explained_variance | -0.0821 | +| learning_rate | 4.28e-05 | +| loss | -0.0373 | +| n_updates | 75144 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.00011 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.315 | +| time/ | | +| fps | 1403 | +| iterations | 14833 | +| time_elapsed | 21644 | +| total_timesteps | 30377984 | +| train/ | | +| approx_kl | 0.013791233 | +| clip_fraction | 0.369 | +| clip_range | 0.0674 | +| entropy_loss | -6.48 | +| explained_variance | -0.069 | +| learning_rate | 4.28e-05 | +| loss | -0.032 | +| n_updates | 75148 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000175 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.315 | +| time/ | | +| fps | 1403 | +| iterations | 14834 | +| time_elapsed | 21646 | +| total_timesteps | 30380032 | +| train/ | | +| approx_kl | 0.010818886 | +| clip_fraction | 0.277 | +| clip_range | 0.0674 | +| entropy_loss | -6.09 | +| explained_variance | 0.485 | +| learning_rate | 4.28e-05 | +| loss | -0.0187 | +| n_updates | 75152 | +| policy_gradient_loss | -0.0133 | +| value_loss | 0.000164 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1403 | +| iterations | 14835 | +| time_elapsed | 21648 | +| total_timesteps | 30382080 | +| train/ | | +| approx_kl | 0.011364065 | +| clip_fraction | 0.333 | +| clip_range | 0.0674 | +| entropy_loss | -6.74 | +| explained_variance | -0.36 | +| learning_rate | 4.28e-05 | +| loss | -0.0366 | +| n_updates | 75156 | +| policy_gradient_loss | -0.0208 | +| value_loss | 8.2e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1403 | +| iterations | 14836 | +| time_elapsed | 21649 | +| total_timesteps | 30384128 | +| train/ | | +| approx_kl | 0.011660863 | +| clip_fraction | 0.313 | +| clip_range | 0.0674 | +| entropy_loss | -6.1 | +| explained_variance | 0.632 | +| learning_rate | 4.28e-05 | +| loss | -0.0226 | +| n_updates | 75160 | +| policy_gradient_loss | -0.0157 | +| value_loss | 9.81e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1403 | +| iterations | 14837 | +| time_elapsed | 21651 | +| total_timesteps | 30386176 | +| train/ | | +| approx_kl | 0.012282011 | +| clip_fraction | 0.31 | +| clip_range | 0.0674 | +| entropy_loss | -6.36 | +| explained_variance | 0.301 | +| learning_rate | 4.28e-05 | +| loss | -0.0253 | +| n_updates | 75164 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.0002 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1403 | +| iterations | 14838 | +| time_elapsed | 21652 | +| total_timesteps | 30388224 | +| train/ | | +| approx_kl | 0.012368295 | +| clip_fraction | 0.347 | +| clip_range | 0.0674 | +| entropy_loss | -6.41 | +| explained_variance | 0.506 | +| learning_rate | 4.28e-05 | +| loss | -0.0353 | +| n_updates | 75168 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000151 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1403 | +| iterations | 14839 | +| time_elapsed | 21654 | +| total_timesteps | 30390272 | +| train/ | | +| approx_kl | 0.013845766 | +| clip_fraction | 0.348 | +| clip_range | 0.0674 | +| entropy_loss | -6.51 | +| explained_variance | -0.107 | +| learning_rate | 4.28e-05 | +| loss | -0.0257 | +| n_updates | 75172 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000161 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1403 | +| iterations | 14840 | +| time_elapsed | 21655 | +| total_timesteps | 30392320 | +| train/ | | +| approx_kl | 0.014708387 | +| clip_fraction | 0.347 | +| clip_range | 0.0674 | +| entropy_loss | -6.58 | +| explained_variance | 0.412 | +| learning_rate | 4.28e-05 | +| loss | -0.0309 | +| n_updates | 75176 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000104 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1403 | +| iterations | 14841 | +| time_elapsed | 21657 | +| total_timesteps | 30394368 | +| train/ | | +| approx_kl | 0.0134217525 | +| clip_fraction | 0.344 | +| clip_range | 0.0674 | +| entropy_loss | -6.47 | +| explained_variance | 0.466 | +| learning_rate | 4.28e-05 | +| loss | -0.0209 | +| n_updates | 75180 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000143 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1403 | +| iterations | 14842 | +| time_elapsed | 21658 | +| total_timesteps | 30396416 | +| train/ | | +| approx_kl | 0.014131748 | +| clip_fraction | 0.337 | +| clip_range | 0.0674 | +| entropy_loss | -6.57 | +| explained_variance | 0.00606 | +| learning_rate | 4.28e-05 | +| loss | -0.0285 | +| n_updates | 75184 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000104 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1403 | +| iterations | 14843 | +| time_elapsed | 21660 | +| total_timesteps | 30398464 | +| train/ | | +| approx_kl | 0.014561964 | +| clip_fraction | 0.36 | +| clip_range | 0.0674 | +| entropy_loss | -6.4 | +| explained_variance | 0.575 | +| learning_rate | 4.28e-05 | +| loss | -0.0279 | +| n_updates | 75188 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000111 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1403 | +| iterations | 14844 | +| time_elapsed | 21661 | +| total_timesteps | 30400512 | +| train/ | | +| approx_kl | 0.013622175 | +| clip_fraction | 0.343 | +| clip_range | 0.0674 | +| entropy_loss | -6.8 | +| explained_variance | 0.0973 | +| learning_rate | 4.28e-05 | +| loss | -0.0301 | +| n_updates | 75192 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000222 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1403 | +| iterations | 14845 | +| time_elapsed | 21663 | +| total_timesteps | 30402560 | +| train/ | | +| approx_kl | 0.014542185 | +| clip_fraction | 0.351 | +| clip_range | 0.0674 | +| entropy_loss | -6.27 | +| explained_variance | 0.44 | +| learning_rate | 4.28e-05 | +| loss | -0.0224 | +| n_updates | 75196 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000199 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1403 | +| iterations | 14846 | +| time_elapsed | 21665 | +| total_timesteps | 30404608 | +| train/ | | +| approx_kl | 0.015456539 | +| clip_fraction | 0.34 | +| clip_range | 0.0674 | +| entropy_loss | -6.29 | +| explained_variance | 0.431 | +| learning_rate | 4.28e-05 | +| loss | -0.0322 | +| n_updates | 75200 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000177 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1403 | +| iterations | 14847 | +| time_elapsed | 21666 | +| total_timesteps | 30406656 | +| train/ | | +| approx_kl | 0.010699137 | +| clip_fraction | 0.308 | +| clip_range | 0.0674 | +| entropy_loss | -5.86 | +| explained_variance | 0.449 | +| learning_rate | 4.28e-05 | +| loss | -0.0255 | +| n_updates | 75204 | +| policy_gradient_loss | -0.0148 | +| value_loss | 0.000264 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1403 | +| iterations | 14848 | +| time_elapsed | 21668 | +| total_timesteps | 30408704 | +| train/ | | +| approx_kl | 0.011523372 | +| clip_fraction | 0.345 | +| clip_range | 0.0674 | +| entropy_loss | -5.83 | +| explained_variance | 0.616 | +| learning_rate | 4.28e-05 | +| loss | -0.0362 | +| n_updates | 75208 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000128 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1403 | +| iterations | 14849 | +| time_elapsed | 21669 | +| total_timesteps | 30410752 | +| train/ | | +| approx_kl | 0.016010407 | +| clip_fraction | 0.339 | +| clip_range | 0.0674 | +| entropy_loss | -6.31 | +| explained_variance | 0.262 | +| learning_rate | 4.28e-05 | +| loss | -0.0279 | +| n_updates | 75212 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000169 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1403 | +| iterations | 14850 | +| time_elapsed | 21671 | +| total_timesteps | 30412800 | +| train/ | | +| approx_kl | 0.011187363 | +| clip_fraction | 0.342 | +| clip_range | 0.0674 | +| entropy_loss | -6.89 | +| explained_variance | -0.244 | +| learning_rate | 4.28e-05 | +| loss | -0.031 | +| n_updates | 75216 | +| policy_gradient_loss | -0.0204 | +| value_loss | 8.55e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1403 | +| iterations | 14851 | +| time_elapsed | 21672 | +| total_timesteps | 30414848 | +| train/ | | +| approx_kl | 0.013485407 | +| clip_fraction | 0.346 | +| clip_range | 0.0674 | +| entropy_loss | -6.38 | +| explained_variance | 0.706 | +| learning_rate | 4.28e-05 | +| loss | -0.0302 | +| n_updates | 75220 | +| policy_gradient_loss | -0.0199 | +| value_loss | 7.9e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1403 | +| iterations | 14852 | +| time_elapsed | 21674 | +| total_timesteps | 30416896 | +| train/ | | +| approx_kl | 0.010951925 | +| clip_fraction | 0.316 | +| clip_range | 0.0674 | +| entropy_loss | -6.41 | +| explained_variance | 0.416 | +| learning_rate | 4.28e-05 | +| loss | -0.0272 | +| n_updates | 75224 | +| policy_gradient_loss | -0.0165 | +| value_loss | 9.68e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1403 | +| iterations | 14853 | +| time_elapsed | 21675 | +| total_timesteps | 30418944 | +| train/ | | +| approx_kl | 0.01044712 | +| clip_fraction | 0.339 | +| clip_range | 0.0674 | +| entropy_loss | -6.5 | +| explained_variance | 0.611 | +| learning_rate | 4.28e-05 | +| loss | -0.0304 | +| n_updates | 75228 | +| policy_gradient_loss | -0.0189 | +| value_loss | 9.36e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1403 | +| iterations | 14854 | +| time_elapsed | 21677 | +| total_timesteps | 30420992 | +| train/ | | +| approx_kl | 0.014447082 | +| clip_fraction | 0.298 | +| clip_range | 0.0674 | +| entropy_loss | -6.44 | +| explained_variance | 0.351 | +| learning_rate | 4.28e-05 | +| loss | -0.0212 | +| n_updates | 75232 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000151 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1403 | +| iterations | 14855 | +| time_elapsed | 21678 | +| total_timesteps | 30423040 | +| train/ | | +| approx_kl | 0.015119681 | +| clip_fraction | 0.333 | +| clip_range | 0.0674 | +| entropy_loss | -6.4 | +| explained_variance | 0.371 | +| learning_rate | 4.28e-05 | +| loss | -0.0304 | +| n_updates | 75236 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000107 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1403 | +| iterations | 14856 | +| time_elapsed | 21680 | +| total_timesteps | 30425088 | +| train/ | | +| approx_kl | 0.012251974 | +| clip_fraction | 0.344 | +| clip_range | 0.0674 | +| entropy_loss | -6.09 | +| explained_variance | 0.447 | +| learning_rate | 4.28e-05 | +| loss | -0.0269 | +| n_updates | 75240 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000288 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1403 | +| iterations | 14857 | +| time_elapsed | 21682 | +| total_timesteps | 30427136 | +| train/ | | +| approx_kl | 0.014319327 | +| clip_fraction | 0.338 | +| clip_range | 0.0674 | +| entropy_loss | -5.99 | +| explained_variance | 0.528 | +| learning_rate | 4.28e-05 | +| loss | -0.031 | +| n_updates | 75244 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000131 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1403 | +| iterations | 14858 | +| time_elapsed | 21683 | +| total_timesteps | 30429184 | +| train/ | | +| approx_kl | 0.010962393 | +| clip_fraction | 0.338 | +| clip_range | 0.0674 | +| entropy_loss | -6.47 | +| explained_variance | 0.31 | +| learning_rate | 4.28e-05 | +| loss | -0.0312 | +| n_updates | 75248 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000113 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1403 | +| iterations | 14859 | +| time_elapsed | 21685 | +| total_timesteps | 30431232 | +| train/ | | +| approx_kl | 0.0105956625 | +| clip_fraction | 0.327 | +| clip_range | 0.0674 | +| entropy_loss | -6.55 | +| explained_variance | 0.445 | +| learning_rate | 4.28e-05 | +| loss | -0.0282 | +| n_updates | 75252 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000118 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1403 | +| iterations | 14860 | +| time_elapsed | 21686 | +| total_timesteps | 30433280 | +| train/ | | +| approx_kl | 0.011318553 | +| clip_fraction | 0.301 | +| clip_range | 0.0674 | +| entropy_loss | -6.5 | +| explained_variance | 0.314 | +| learning_rate | 4.28e-05 | +| loss | -0.0239 | +| n_updates | 75256 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000248 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1403 | +| iterations | 14861 | +| time_elapsed | 21688 | +| total_timesteps | 30435328 | +| train/ | | +| approx_kl | 0.014589681 | +| clip_fraction | 0.333 | +| clip_range | 0.0674 | +| entropy_loss | -5.47 | +| explained_variance | 0.485 | +| learning_rate | 4.28e-05 | +| loss | -0.0289 | +| n_updates | 75260 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000256 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1403 | +| iterations | 14862 | +| time_elapsed | 21689 | +| total_timesteps | 30437376 | +| train/ | | +| approx_kl | 0.016387431 | +| clip_fraction | 0.373 | +| clip_range | 0.0674 | +| entropy_loss | -5.46 | +| explained_variance | 0.506 | +| learning_rate | 4.28e-05 | +| loss | -0.032 | +| n_updates | 75264 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000159 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1403 | +| iterations | 14863 | +| time_elapsed | 21691 | +| total_timesteps | 30439424 | +| train/ | | +| approx_kl | 0.013372821 | +| clip_fraction | 0.341 | +| clip_range | 0.0674 | +| entropy_loss | -5.66 | +| explained_variance | 0.336 | +| learning_rate | 4.28e-05 | +| loss | -0.0261 | +| n_updates | 75268 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000239 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1403 | +| iterations | 14864 | +| time_elapsed | 21693 | +| total_timesteps | 30441472 | +| train/ | | +| approx_kl | 0.016953094 | +| clip_fraction | 0.372 | +| clip_range | 0.0674 | +| entropy_loss | -5.94 | +| explained_variance | 0.412 | +| learning_rate | 4.28e-05 | +| loss | -0.0389 | +| n_updates | 75272 | +| policy_gradient_loss | -0.0224 | +| value_loss | 9.09e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1403 | +| iterations | 14865 | +| time_elapsed | 21694 | +| total_timesteps | 30443520 | +| train/ | | +| approx_kl | 0.016009394 | +| clip_fraction | 0.339 | +| clip_range | 0.0674 | +| entropy_loss | -6.27 | +| explained_variance | 0.356 | +| learning_rate | 4.28e-05 | +| loss | -0.0303 | +| n_updates | 75276 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000257 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1403 | +| iterations | 14866 | +| time_elapsed | 21696 | +| total_timesteps | 30445568 | +| train/ | | +| approx_kl | 0.012080849 | +| clip_fraction | 0.313 | +| clip_range | 0.0674 | +| entropy_loss | -5.84 | +| explained_variance | 0.594 | +| learning_rate | 4.28e-05 | +| loss | -0.0269 | +| n_updates | 75280 | +| policy_gradient_loss | -0.0138 | +| value_loss | 0.000177 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1403 | +| iterations | 14867 | +| time_elapsed | 21697 | +| total_timesteps | 30447616 | +| train/ | | +| approx_kl | 0.009621864 | +| clip_fraction | 0.327 | +| clip_range | 0.0674 | +| entropy_loss | -6.05 | +| explained_variance | 0.6 | +| learning_rate | 4.28e-05 | +| loss | -0.0298 | +| n_updates | 75284 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000167 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1403 | +| iterations | 14868 | +| time_elapsed | 21699 | +| total_timesteps | 30449664 | +| train/ | | +| approx_kl | 0.013569487 | +| clip_fraction | 0.329 | +| clip_range | 0.0674 | +| entropy_loss | -6.13 | +| explained_variance | 0.536 | +| learning_rate | 4.28e-05 | +| loss | -0.0268 | +| n_updates | 75288 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000104 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1403 | +| iterations | 14869 | +| time_elapsed | 21700 | +| total_timesteps | 30451712 | +| train/ | | +| approx_kl | 0.014845038 | +| clip_fraction | 0.366 | +| clip_range | 0.0674 | +| entropy_loss | -6.32 | +| explained_variance | -0.0752 | +| learning_rate | 4.28e-05 | +| loss | -0.0224 | +| n_updates | 75292 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000192 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1403 | +| iterations | 14870 | +| time_elapsed | 21702 | +| total_timesteps | 30453760 | +| train/ | | +| approx_kl | 0.015000664 | +| clip_fraction | 0.337 | +| clip_range | 0.0674 | +| entropy_loss | -6.45 | +| explained_variance | 0.429 | +| learning_rate | 4.28e-05 | +| loss | -0.0269 | +| n_updates | 75296 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000124 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1403 | +| iterations | 14871 | +| time_elapsed | 21703 | +| total_timesteps | 30455808 | +| train/ | | +| approx_kl | 0.011130532 | +| clip_fraction | 0.344 | +| clip_range | 0.0674 | +| entropy_loss | -6.69 | +| explained_variance | 0.349 | +| learning_rate | 4.28e-05 | +| loss | -0.033 | +| n_updates | 75300 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000105 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1403 | +| iterations | 14872 | +| time_elapsed | 21705 | +| total_timesteps | 30457856 | +| train/ | | +| approx_kl | 0.013481214 | +| clip_fraction | 0.327 | +| clip_range | 0.0674 | +| entropy_loss | -6.36 | +| explained_variance | 0.301 | +| learning_rate | 4.28e-05 | +| loss | -0.022 | +| n_updates | 75304 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000207 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1403 | +| iterations | 14873 | +| time_elapsed | 21706 | +| total_timesteps | 30459904 | +| train/ | | +| approx_kl | 0.011478502 | +| clip_fraction | 0.324 | +| clip_range | 0.0674 | +| entropy_loss | -5.18 | +| explained_variance | 0.745 | +| learning_rate | 4.28e-05 | +| loss | -0.0165 | +| n_updates | 75308 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000149 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1403 | +| iterations | 14874 | +| time_elapsed | 21708 | +| total_timesteps | 30461952 | +| train/ | | +| approx_kl | 0.013640761 | +| clip_fraction | 0.376 | +| clip_range | 0.0674 | +| entropy_loss | -5.94 | +| explained_variance | 0.562 | +| learning_rate | 4.28e-05 | +| loss | -0.0371 | +| n_updates | 75312 | +| policy_gradient_loss | -0.021 | +| value_loss | 8.53e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1403 | +| iterations | 14875 | +| time_elapsed | 21710 | +| total_timesteps | 30464000 | +| train/ | | +| approx_kl | 0.013955261 | +| clip_fraction | 0.345 | +| clip_range | 0.0674 | +| entropy_loss | -5.75 | +| explained_variance | 0.525 | +| learning_rate | 4.28e-05 | +| loss | -0.0245 | +| n_updates | 75316 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000172 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1403 | +| iterations | 14876 | +| time_elapsed | 21711 | +| total_timesteps | 30466048 | +| train/ | | +| approx_kl | 0.015108032 | +| clip_fraction | 0.341 | +| clip_range | 0.0674 | +| entropy_loss | -6.11 | +| explained_variance | 0.455 | +| learning_rate | 4.28e-05 | +| loss | -0.0324 | +| n_updates | 75320 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.00012 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1403 | +| iterations | 14877 | +| time_elapsed | 21713 | +| total_timesteps | 30468096 | +| train/ | | +| approx_kl | 0.01364163 | +| clip_fraction | 0.356 | +| clip_range | 0.0674 | +| entropy_loss | -6.05 | +| explained_variance | 0.403 | +| learning_rate | 4.28e-05 | +| loss | -0.0314 | +| n_updates | 75324 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000154 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1403 | +| iterations | 14878 | +| time_elapsed | 21714 | +| total_timesteps | 30470144 | +| train/ | | +| approx_kl | 0.01720789 | +| clip_fraction | 0.366 | +| clip_range | 0.0674 | +| entropy_loss | -6.42 | +| explained_variance | -0.16 | +| learning_rate | 4.28e-05 | +| loss | -0.0282 | +| n_updates | 75328 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000137 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1403 | +| iterations | 14879 | +| time_elapsed | 21716 | +| total_timesteps | 30472192 | +| train/ | | +| approx_kl | 0.014358648 | +| clip_fraction | 0.327 | +| clip_range | 0.0674 | +| entropy_loss | -5.74 | +| explained_variance | 0.482 | +| learning_rate | 4.28e-05 | +| loss | -0.0268 | +| n_updates | 75332 | +| policy_gradient_loss | -0.0145 | +| value_loss | 0.000223 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1403 | +| iterations | 14880 | +| time_elapsed | 21717 | +| total_timesteps | 30474240 | +| train/ | | +| approx_kl | 0.013683924 | +| clip_fraction | 0.348 | +| clip_range | 0.0674 | +| entropy_loss | -6.55 | +| explained_variance | -0.0509 | +| learning_rate | 4.28e-05 | +| loss | -0.0308 | +| n_updates | 75336 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000111 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1403 | +| iterations | 14881 | +| time_elapsed | 21719 | +| total_timesteps | 30476288 | +| train/ | | +| approx_kl | 0.013355428 | +| clip_fraction | 0.357 | +| clip_range | 0.0674 | +| entropy_loss | -6.05 | +| explained_variance | 0.451 | +| learning_rate | 4.28e-05 | +| loss | -0.0251 | +| n_updates | 75340 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000183 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1403 | +| iterations | 14882 | +| time_elapsed | 21720 | +| total_timesteps | 30478336 | +| train/ | | +| approx_kl | 0.0134388115 | +| clip_fraction | 0.356 | +| clip_range | 0.0674 | +| entropy_loss | -5.93 | +| explained_variance | 0.683 | +| learning_rate | 4.28e-05 | +| loss | -0.0343 | +| n_updates | 75344 | +| policy_gradient_loss | -0.0208 | +| value_loss | 7.76e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1403 | +| iterations | 14883 | +| time_elapsed | 21722 | +| total_timesteps | 30480384 | +| train/ | | +| approx_kl | 0.019347113 | +| clip_fraction | 0.34 | +| clip_range | 0.0674 | +| entropy_loss | -6.11 | +| explained_variance | 0.505 | +| learning_rate | 4.28e-05 | +| loss | -0.0261 | +| n_updates | 75348 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000119 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1403 | +| iterations | 14884 | +| time_elapsed | 21723 | +| total_timesteps | 30482432 | +| train/ | | +| approx_kl | 0.012970109 | +| clip_fraction | 0.335 | +| clip_range | 0.0674 | +| entropy_loss | -5.5 | +| explained_variance | 0.618 | +| learning_rate | 4.28e-05 | +| loss | -0.0245 | +| n_updates | 75352 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000185 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1403 | +| iterations | 14885 | +| time_elapsed | 21725 | +| total_timesteps | 30484480 | +| train/ | | +| approx_kl | 0.014190419 | +| clip_fraction | 0.335 | +| clip_range | 0.0674 | +| entropy_loss | -6.25 | +| explained_variance | 0.0791 | +| learning_rate | 4.28e-05 | +| loss | -0.0296 | +| n_updates | 75356 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000172 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1403 | +| iterations | 14886 | +| time_elapsed | 21727 | +| total_timesteps | 30486528 | +| train/ | | +| approx_kl | 0.0105188005 | +| clip_fraction | 0.33 | +| clip_range | 0.0674 | +| entropy_loss | -7.04 | +| explained_variance | 0.0568 | +| learning_rate | 4.28e-05 | +| loss | -0.0296 | +| n_updates | 75360 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000279 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1403 | +| iterations | 14887 | +| time_elapsed | 21728 | +| total_timesteps | 30488576 | +| train/ | | +| approx_kl | 0.012735467 | +| clip_fraction | 0.332 | +| clip_range | 0.0674 | +| entropy_loss | -5.96 | +| explained_variance | 0.761 | +| learning_rate | 4.28e-05 | +| loss | -0.0322 | +| n_updates | 75364 | +| policy_gradient_loss | -0.0193 | +| value_loss | 8.91e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1403 | +| iterations | 14888 | +| time_elapsed | 21730 | +| total_timesteps | 30490624 | +| train/ | | +| approx_kl | 0.01036525 | +| clip_fraction | 0.333 | +| clip_range | 0.0674 | +| entropy_loss | -5.52 | +| explained_variance | 0.567 | +| learning_rate | 4.28e-05 | +| loss | -0.0232 | +| n_updates | 75368 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000169 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1403 | +| iterations | 14889 | +| time_elapsed | 21731 | +| total_timesteps | 30492672 | +| train/ | | +| approx_kl | 0.013449347 | +| clip_fraction | 0.369 | +| clip_range | 0.0674 | +| entropy_loss | -6.2 | +| explained_variance | 0.25 | +| learning_rate | 4.28e-05 | +| loss | -0.0312 | +| n_updates | 75372 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000149 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1403 | +| iterations | 14890 | +| time_elapsed | 21733 | +| total_timesteps | 30494720 | +| train/ | | +| approx_kl | 0.015811779 | +| clip_fraction | 0.341 | +| clip_range | 0.0674 | +| entropy_loss | -6.04 | +| explained_variance | 0.279 | +| learning_rate | 4.28e-05 | +| loss | -0.0274 | +| n_updates | 75376 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000276 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1403 | +| iterations | 14891 | +| time_elapsed | 21734 | +| total_timesteps | 30496768 | +| train/ | | +| approx_kl | 0.015255289 | +| clip_fraction | 0.376 | +| clip_range | 0.0674 | +| entropy_loss | -6.23 | +| explained_variance | 0.664 | +| learning_rate | 4.28e-05 | +| loss | -0.0348 | +| n_updates | 75380 | +| policy_gradient_loss | -0.023 | +| value_loss | 7.07e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1403 | +| iterations | 14892 | +| time_elapsed | 21736 | +| total_timesteps | 30498816 | +| train/ | | +| approx_kl | 0.013211215 | +| clip_fraction | 0.339 | +| clip_range | 0.0674 | +| entropy_loss | -6.54 | +| explained_variance | 0.147 | +| learning_rate | 4.28e-05 | +| loss | -0.0331 | +| n_updates | 75384 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000286 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1403 | +| iterations | 14893 | +| time_elapsed | 21737 | +| total_timesteps | 30500864 | +| train/ | | +| approx_kl | 0.011571007 | +| clip_fraction | 0.345 | +| clip_range | 0.0674 | +| entropy_loss | -6.04 | +| explained_variance | 0.54 | +| learning_rate | 4.28e-05 | +| loss | -0.0275 | +| n_updates | 75388 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.00019 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1403 | +| iterations | 14894 | +| time_elapsed | 21739 | +| total_timesteps | 30502912 | +| train/ | | +| approx_kl | 0.014802406 | +| clip_fraction | 0.352 | +| clip_range | 0.0674 | +| entropy_loss | -6.07 | +| explained_variance | 0.268 | +| learning_rate | 4.28e-05 | +| loss | -0.0341 | +| n_updates | 75392 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000166 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1403 | +| iterations | 14895 | +| time_elapsed | 21740 | +| total_timesteps | 30504960 | +| train/ | | +| approx_kl | 0.0157022 | +| clip_fraction | 0.369 | +| clip_range | 0.0674 | +| entropy_loss | -6.41 | +| explained_variance | 0.386 | +| learning_rate | 4.28e-05 | +| loss | -0.0333 | +| n_updates | 75396 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000104 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1403 | +| iterations | 14896 | +| time_elapsed | 21742 | +| total_timesteps | 30507008 | +| train/ | | +| approx_kl | 0.014883692 | +| clip_fraction | 0.386 | +| clip_range | 0.0674 | +| entropy_loss | -6.08 | +| explained_variance | 0.587 | +| learning_rate | 4.28e-05 | +| loss | -0.0287 | +| n_updates | 75400 | +| policy_gradient_loss | -0.0198 | +| value_loss | 9.12e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1403 | +| iterations | 14897 | +| time_elapsed | 21743 | +| total_timesteps | 30509056 | +| train/ | | +| approx_kl | 0.017133817 | +| clip_fraction | 0.353 | +| clip_range | 0.0674 | +| entropy_loss | -6.64 | +| explained_variance | -0.215 | +| learning_rate | 4.28e-05 | +| loss | -0.0336 | +| n_updates | 75404 | +| policy_gradient_loss | -0.0201 | +| value_loss | 7.05e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1403 | +| iterations | 14898 | +| time_elapsed | 21745 | +| total_timesteps | 30511104 | +| train/ | | +| approx_kl | 0.01256091 | +| clip_fraction | 0.328 | +| clip_range | 0.0674 | +| entropy_loss | -6.5 | +| explained_variance | 0.312 | +| learning_rate | 4.28e-05 | +| loss | -0.0282 | +| n_updates | 75408 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000137 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1403 | +| iterations | 14899 | +| time_elapsed | 21746 | +| total_timesteps | 30513152 | +| train/ | | +| approx_kl | 0.012486664 | +| clip_fraction | 0.319 | +| clip_range | 0.0674 | +| entropy_loss | -6.25 | +| explained_variance | 0.449 | +| learning_rate | 4.28e-05 | +| loss | -0.0259 | +| n_updates | 75412 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000181 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1403 | +| iterations | 14900 | +| time_elapsed | 21748 | +| total_timesteps | 30515200 | +| train/ | | +| approx_kl | 0.012608811 | +| clip_fraction | 0.358 | +| clip_range | 0.0674 | +| entropy_loss | -5.4 | +| explained_variance | 0.875 | +| learning_rate | 4.28e-05 | +| loss | -0.0299 | +| n_updates | 75416 | +| policy_gradient_loss | -0.0211 | +| value_loss | 3.97e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1403 | +| iterations | 14901 | +| time_elapsed | 21750 | +| total_timesteps | 30517248 | +| train/ | | +| approx_kl | 0.014078195 | +| clip_fraction | 0.338 | +| clip_range | 0.0674 | +| entropy_loss | -5.81 | +| explained_variance | 0.566 | +| learning_rate | 4.28e-05 | +| loss | -0.0291 | +| n_updates | 75420 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000116 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1403 | +| iterations | 14902 | +| time_elapsed | 21751 | +| total_timesteps | 30519296 | +| train/ | | +| approx_kl | 0.013430404 | +| clip_fraction | 0.358 | +| clip_range | 0.0674 | +| entropy_loss | -6.43 | +| explained_variance | 0.0171 | +| learning_rate | 4.28e-05 | +| loss | -0.0254 | +| n_updates | 75424 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000174 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1403 | +| iterations | 14903 | +| time_elapsed | 21753 | +| total_timesteps | 30521344 | +| train/ | | +| approx_kl | 0.013568568 | +| clip_fraction | 0.343 | +| clip_range | 0.0674 | +| entropy_loss | -6.46 | +| explained_variance | 0.411 | +| learning_rate | 4.28e-05 | +| loss | -0.0305 | +| n_updates | 75428 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000143 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1403 | +| iterations | 14904 | +| time_elapsed | 21754 | +| total_timesteps | 30523392 | +| train/ | | +| approx_kl | 0.01720684 | +| clip_fraction | 0.376 | +| clip_range | 0.0674 | +| entropy_loss | -6.28 | +| explained_variance | -0.207 | +| learning_rate | 4.28e-05 | +| loss | -0.0347 | +| n_updates | 75432 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000101 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1403 | +| iterations | 14905 | +| time_elapsed | 21756 | +| total_timesteps | 30525440 | +| train/ | | +| approx_kl | 0.014079992 | +| clip_fraction | 0.334 | +| clip_range | 0.0674 | +| entropy_loss | -5.93 | +| explained_variance | 0.486 | +| learning_rate | 4.28e-05 | +| loss | -0.0266 | +| n_updates | 75436 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000209 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1403 | +| iterations | 14906 | +| time_elapsed | 21757 | +| total_timesteps | 30527488 | +| train/ | | +| approx_kl | 0.012311321 | +| clip_fraction | 0.325 | +| clip_range | 0.0674 | +| entropy_loss | -6.22 | +| explained_variance | 0.21 | +| learning_rate | 4.28e-05 | +| loss | -0.0276 | +| n_updates | 75440 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000157 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1403 | +| iterations | 14907 | +| time_elapsed | 21759 | +| total_timesteps | 30529536 | +| train/ | | +| approx_kl | 0.013507429 | +| clip_fraction | 0.35 | +| clip_range | 0.0674 | +| entropy_loss | -6.18 | +| explained_variance | 0.346 | +| learning_rate | 4.27e-05 | +| loss | -0.0342 | +| n_updates | 75444 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000156 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1403 | +| iterations | 14908 | +| time_elapsed | 21760 | +| total_timesteps | 30531584 | +| train/ | | +| approx_kl | 0.012085637 | +| clip_fraction | 0.339 | +| clip_range | 0.0674 | +| entropy_loss | -6.54 | +| explained_variance | 0.278 | +| learning_rate | 4.27e-05 | +| loss | -0.0326 | +| n_updates | 75448 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000158 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1403 | +| iterations | 14909 | +| time_elapsed | 21762 | +| total_timesteps | 30533632 | +| train/ | | +| approx_kl | 0.015782606 | +| clip_fraction | 0.311 | +| clip_range | 0.0674 | +| entropy_loss | -6.12 | +| explained_variance | 0.482 | +| learning_rate | 4.27e-05 | +| loss | -0.0268 | +| n_updates | 75452 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000231 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1403 | +| iterations | 14910 | +| time_elapsed | 21763 | +| total_timesteps | 30535680 | +| train/ | | +| approx_kl | 0.010059708 | +| clip_fraction | 0.3 | +| clip_range | 0.0674 | +| entropy_loss | -5.53 | +| explained_variance | 0.32 | +| learning_rate | 4.27e-05 | +| loss | -0.0221 | +| n_updates | 75456 | +| policy_gradient_loss | -0.0134 | +| value_loss | 0.000454 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1403 | +| iterations | 14911 | +| time_elapsed | 21765 | +| total_timesteps | 30537728 | +| train/ | | +| approx_kl | 0.013245295 | +| clip_fraction | 0.345 | +| clip_range | 0.0674 | +| entropy_loss | -5.71 | +| explained_variance | 0.225 | +| learning_rate | 4.27e-05 | +| loss | -0.0297 | +| n_updates | 75460 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000197 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1403 | +| iterations | 14912 | +| time_elapsed | 21766 | +| total_timesteps | 30539776 | +| train/ | | +| approx_kl | 0.011905413 | +| clip_fraction | 0.35 | +| clip_range | 0.0674 | +| entropy_loss | -5.9 | +| explained_variance | 0.426 | +| learning_rate | 4.27e-05 | +| loss | -0.0334 | +| n_updates | 75464 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000236 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1403 | +| iterations | 14913 | +| time_elapsed | 21768 | +| total_timesteps | 30541824 | +| train/ | | +| approx_kl | 0.0132016465 | +| clip_fraction | 0.356 | +| clip_range | 0.0674 | +| entropy_loss | -6.02 | +| explained_variance | 0.192 | +| learning_rate | 4.27e-05 | +| loss | -0.0351 | +| n_updates | 75468 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000216 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1403 | +| iterations | 14914 | +| time_elapsed | 21769 | +| total_timesteps | 30543872 | +| train/ | | +| approx_kl | 0.012684674 | +| clip_fraction | 0.339 | +| clip_range | 0.0674 | +| entropy_loss | -6.58 | +| explained_variance | 0.238 | +| learning_rate | 4.27e-05 | +| loss | -0.0304 | +| n_updates | 75472 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000196 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1403 | +| iterations | 14915 | +| time_elapsed | 21771 | +| total_timesteps | 30545920 | +| train/ | | +| approx_kl | 0.015808769 | +| clip_fraction | 0.341 | +| clip_range | 0.0674 | +| entropy_loss | -6.46 | +| explained_variance | 0.192 | +| learning_rate | 4.27e-05 | +| loss | -0.03 | +| n_updates | 75476 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000198 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1403 | +| iterations | 14916 | +| time_elapsed | 21772 | +| total_timesteps | 30547968 | +| train/ | | +| approx_kl | 0.015629986 | +| clip_fraction | 0.361 | +| clip_range | 0.0674 | +| entropy_loss | -5.87 | +| explained_variance | 0.381 | +| learning_rate | 4.27e-05 | +| loss | -0.0239 | +| n_updates | 75480 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000221 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1403 | +| iterations | 14917 | +| time_elapsed | 21774 | +| total_timesteps | 30550016 | +| train/ | | +| approx_kl | 0.016819814 | +| clip_fraction | 0.358 | +| clip_range | 0.0674 | +| entropy_loss | -6.02 | +| explained_variance | 0.464 | +| learning_rate | 4.27e-05 | +| loss | -0.0291 | +| n_updates | 75484 | +| policy_gradient_loss | -0.0212 | +| value_loss | 9.85e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1403 | +| iterations | 14918 | +| time_elapsed | 21775 | +| total_timesteps | 30552064 | +| train/ | | +| approx_kl | 0.010758102 | +| clip_fraction | 0.328 | +| clip_range | 0.0674 | +| entropy_loss | -6.01 | +| explained_variance | 0.488 | +| learning_rate | 4.27e-05 | +| loss | -0.0232 | +| n_updates | 75488 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000179 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1403 | +| iterations | 14919 | +| time_elapsed | 21777 | +| total_timesteps | 30554112 | +| train/ | | +| approx_kl | 0.009706513 | +| clip_fraction | 0.291 | +| clip_range | 0.0674 | +| entropy_loss | -5.99 | +| explained_variance | 0.468 | +| learning_rate | 4.27e-05 | +| loss | -0.0273 | +| n_updates | 75492 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.000276 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1403 | +| iterations | 14920 | +| time_elapsed | 21778 | +| total_timesteps | 30556160 | +| train/ | | +| approx_kl | 0.009923442 | +| clip_fraction | 0.323 | +| clip_range | 0.0674 | +| entropy_loss | -6.25 | +| explained_variance | 0.319 | +| learning_rate | 4.27e-05 | +| loss | -0.0251 | +| n_updates | 75496 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000165 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1403 | +| iterations | 14921 | +| time_elapsed | 21780 | +| total_timesteps | 30558208 | +| train/ | | +| approx_kl | 0.011590085 | +| clip_fraction | 0.316 | +| clip_range | 0.0674 | +| entropy_loss | -6.05 | +| explained_variance | 0.468 | +| learning_rate | 4.27e-05 | +| loss | -0.0266 | +| n_updates | 75500 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.0002 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1403 | +| iterations | 14922 | +| time_elapsed | 21781 | +| total_timesteps | 30560256 | +| train/ | | +| approx_kl | 0.012437019 | +| clip_fraction | 0.336 | +| clip_range | 0.0674 | +| entropy_loss | -6.22 | +| explained_variance | 0.217 | +| learning_rate | 4.27e-05 | +| loss | -0.0318 | +| n_updates | 75504 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000227 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1403 | +| iterations | 14923 | +| time_elapsed | 21783 | +| total_timesteps | 30562304 | +| train/ | | +| approx_kl | 0.012862479 | +| clip_fraction | 0.292 | +| clip_range | 0.0674 | +| entropy_loss | -6.1 | +| explained_variance | 0.464 | +| learning_rate | 4.27e-05 | +| loss | -0.0248 | +| n_updates | 75508 | +| policy_gradient_loss | -0.0143 | +| value_loss | 0.000293 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1403 | +| iterations | 14924 | +| time_elapsed | 21784 | +| total_timesteps | 30564352 | +| train/ | | +| approx_kl | 0.011623727 | +| clip_fraction | 0.361 | +| clip_range | 0.0674 | +| entropy_loss | -6.5 | +| explained_variance | -0.0536 | +| learning_rate | 4.27e-05 | +| loss | -0.0321 | +| n_updates | 75512 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000131 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1403 | +| iterations | 14925 | +| time_elapsed | 21786 | +| total_timesteps | 30566400 | +| train/ | | +| approx_kl | 0.011616573 | +| clip_fraction | 0.326 | +| clip_range | 0.0674 | +| entropy_loss | -7.03 | +| explained_variance | 0.0025 | +| learning_rate | 4.27e-05 | +| loss | -0.0272 | +| n_updates | 75516 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000178 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1403 | +| iterations | 14926 | +| time_elapsed | 21787 | +| total_timesteps | 30568448 | +| train/ | | +| approx_kl | 0.010288963 | +| clip_fraction | 0.306 | +| clip_range | 0.0674 | +| entropy_loss | -6.54 | +| explained_variance | 0.246 | +| learning_rate | 4.27e-05 | +| loss | -0.0276 | +| n_updates | 75520 | +| policy_gradient_loss | -0.0146 | +| value_loss | 0.00048 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1402 | +| iterations | 14927 | +| time_elapsed | 21789 | +| total_timesteps | 30570496 | +| train/ | | +| approx_kl | 0.013423649 | +| clip_fraction | 0.349 | +| clip_range | 0.0674 | +| entropy_loss | -6.43 | +| explained_variance | 0.242 | +| learning_rate | 4.27e-05 | +| loss | -0.0275 | +| n_updates | 75524 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000257 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1402 | +| iterations | 14928 | +| time_elapsed | 21790 | +| total_timesteps | 30572544 | +| train/ | | +| approx_kl | 0.011723745 | +| clip_fraction | 0.33 | +| clip_range | 0.0674 | +| entropy_loss | -5.64 | +| explained_variance | 0.601 | +| learning_rate | 4.27e-05 | +| loss | -0.0271 | +| n_updates | 75528 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000228 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1402 | +| iterations | 14929 | +| time_elapsed | 21792 | +| total_timesteps | 30574592 | +| train/ | | +| approx_kl | 0.011694435 | +| clip_fraction | 0.332 | +| clip_range | 0.0674 | +| entropy_loss | -5.62 | +| explained_variance | 0.278 | +| learning_rate | 4.27e-05 | +| loss | -0.0287 | +| n_updates | 75532 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000267 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1402 | +| iterations | 14930 | +| time_elapsed | 21793 | +| total_timesteps | 30576640 | +| train/ | | +| approx_kl | 0.0113173 | +| clip_fraction | 0.342 | +| clip_range | 0.0674 | +| entropy_loss | -5.76 | +| explained_variance | 0.484 | +| learning_rate | 4.27e-05 | +| loss | -0.0267 | +| n_updates | 75536 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000207 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1402 | +| iterations | 14931 | +| time_elapsed | 21795 | +| total_timesteps | 30578688 | +| train/ | | +| approx_kl | 0.015341728 | +| clip_fraction | 0.391 | +| clip_range | 0.0674 | +| entropy_loss | -6.15 | +| explained_variance | 0.409 | +| learning_rate | 4.27e-05 | +| loss | -0.0392 | +| n_updates | 75540 | +| policy_gradient_loss | -0.0224 | +| value_loss | 8.19e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1402 | +| iterations | 14932 | +| time_elapsed | 21797 | +| total_timesteps | 30580736 | +| train/ | | +| approx_kl | 0.015398683 | +| clip_fraction | 0.381 | +| clip_range | 0.0674 | +| entropy_loss | -6.5 | +| explained_variance | -0.033 | +| learning_rate | 4.27e-05 | +| loss | -0.0354 | +| n_updates | 75544 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000162 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1402 | +| iterations | 14933 | +| time_elapsed | 21798 | +| total_timesteps | 30582784 | +| train/ | | +| approx_kl | 0.01590641 | +| clip_fraction | 0.391 | +| clip_range | 0.0674 | +| entropy_loss | -6.35 | +| explained_variance | 0.347 | +| learning_rate | 4.27e-05 | +| loss | -0.0294 | +| n_updates | 75548 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.00011 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1402 | +| iterations | 14934 | +| time_elapsed | 21800 | +| total_timesteps | 30584832 | +| train/ | | +| approx_kl | 0.014318841 | +| clip_fraction | 0.36 | +| clip_range | 0.0674 | +| entropy_loss | -6.62 | +| explained_variance | -0.176 | +| learning_rate | 4.27e-05 | +| loss | -0.0323 | +| n_updates | 75552 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000135 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1402 | +| iterations | 14935 | +| time_elapsed | 21801 | +| total_timesteps | 30586880 | +| train/ | | +| approx_kl | 0.016525866 | +| clip_fraction | 0.37 | +| clip_range | 0.0674 | +| entropy_loss | -5.9 | +| explained_variance | 0.713 | +| learning_rate | 4.27e-05 | +| loss | -0.0302 | +| n_updates | 75556 | +| policy_gradient_loss | -0.0201 | +| value_loss | 8.86e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1402 | +| iterations | 14936 | +| time_elapsed | 21803 | +| total_timesteps | 30588928 | +| train/ | | +| approx_kl | 0.01170152 | +| clip_fraction | 0.31 | +| clip_range | 0.0674 | +| entropy_loss | -5.64 | +| explained_variance | 0.48 | +| learning_rate | 4.27e-05 | +| loss | -0.0209 | +| n_updates | 75560 | +| policy_gradient_loss | -0.0146 | +| value_loss | 0.000249 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1402 | +| iterations | 14937 | +| time_elapsed | 21804 | +| total_timesteps | 30590976 | +| train/ | | +| approx_kl | 0.013818379 | +| clip_fraction | 0.369 | +| clip_range | 0.0674 | +| entropy_loss | -5.76 | +| explained_variance | 0.725 | +| learning_rate | 4.27e-05 | +| loss | -0.032 | +| n_updates | 75564 | +| policy_gradient_loss | -0.0231 | +| value_loss | 8.06e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1402 | +| iterations | 14938 | +| time_elapsed | 21806 | +| total_timesteps | 30593024 | +| train/ | | +| approx_kl | 0.01112886 | +| clip_fraction | 0.332 | +| clip_range | 0.0674 | +| entropy_loss | -6.29 | +| explained_variance | 0.47 | +| learning_rate | 4.27e-05 | +| loss | -0.0256 | +| n_updates | 75568 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.00017 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1402 | +| iterations | 14939 | +| time_elapsed | 21807 | +| total_timesteps | 30595072 | +| train/ | | +| approx_kl | 0.013311895 | +| clip_fraction | 0.333 | +| clip_range | 0.0674 | +| entropy_loss | -6.33 | +| explained_variance | 0.512 | +| learning_rate | 4.27e-05 | +| loss | -0.0249 | +| n_updates | 75572 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000117 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1402 | +| iterations | 14940 | +| time_elapsed | 21809 | +| total_timesteps | 30597120 | +| train/ | | +| approx_kl | 0.010810763 | +| clip_fraction | 0.329 | +| clip_range | 0.0674 | +| entropy_loss | -6.45 | +| explained_variance | 0.195 | +| learning_rate | 4.27e-05 | +| loss | -0.0302 | +| n_updates | 75576 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000214 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1402 | +| iterations | 14941 | +| time_elapsed | 21810 | +| total_timesteps | 30599168 | +| train/ | | +| approx_kl | 0.011547001 | +| clip_fraction | 0.318 | +| clip_range | 0.0674 | +| entropy_loss | -5.71 | +| explained_variance | 0.564 | +| learning_rate | 4.27e-05 | +| loss | -0.0226 | +| n_updates | 75580 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000227 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1402 | +| iterations | 14942 | +| time_elapsed | 21812 | +| total_timesteps | 30601216 | +| train/ | | +| approx_kl | 0.017560564 | +| clip_fraction | 0.343 | +| clip_range | 0.0674 | +| entropy_loss | -6.02 | +| explained_variance | 0.441 | +| learning_rate | 4.27e-05 | +| loss | -0.0309 | +| n_updates | 75584 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000178 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1402 | +| iterations | 14943 | +| time_elapsed | 21813 | +| total_timesteps | 30603264 | +| train/ | | +| approx_kl | 0.013040794 | +| clip_fraction | 0.337 | +| clip_range | 0.0673 | +| entropy_loss | -6.25 | +| explained_variance | 0.235 | +| learning_rate | 4.27e-05 | +| loss | -0.0262 | +| n_updates | 75588 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000199 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1402 | +| iterations | 14944 | +| time_elapsed | 21815 | +| total_timesteps | 30605312 | +| train/ | | +| approx_kl | 0.016578391 | +| clip_fraction | 0.344 | +| clip_range | 0.0673 | +| entropy_loss | -6.28 | +| explained_variance | 0.29 | +| learning_rate | 4.27e-05 | +| loss | -0.0316 | +| n_updates | 75592 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000245 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1402 | +| iterations | 14945 | +| time_elapsed | 21816 | +| total_timesteps | 30607360 | +| train/ | | +| approx_kl | 0.012716433 | +| clip_fraction | 0.327 | +| clip_range | 0.0673 | +| entropy_loss | -5.9 | +| explained_variance | 0.32 | +| learning_rate | 4.27e-05 | +| loss | -0.0237 | +| n_updates | 75596 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000289 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1402 | +| iterations | 14946 | +| time_elapsed | 21818 | +| total_timesteps | 30609408 | +| train/ | | +| approx_kl | 0.014146063 | +| clip_fraction | 0.351 | +| clip_range | 0.0673 | +| entropy_loss | -5.37 | +| explained_variance | 0.765 | +| learning_rate | 4.27e-05 | +| loss | -0.0348 | +| n_updates | 75600 | +| policy_gradient_loss | -0.0213 | +| value_loss | 9.49e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1402 | +| iterations | 14947 | +| time_elapsed | 21819 | +| total_timesteps | 30611456 | +| train/ | | +| approx_kl | 0.012473935 | +| clip_fraction | 0.364 | +| clip_range | 0.0673 | +| entropy_loss | -6.24 | +| explained_variance | 0.438 | +| learning_rate | 4.27e-05 | +| loss | -0.0349 | +| n_updates | 75604 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000102 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1402 | +| iterations | 14948 | +| time_elapsed | 21821 | +| total_timesteps | 30613504 | +| train/ | | +| approx_kl | 0.013003582 | +| clip_fraction | 0.329 | +| clip_range | 0.0673 | +| entropy_loss | -6.2 | +| explained_variance | 0.214 | +| learning_rate | 4.27e-05 | +| loss | -0.032 | +| n_updates | 75608 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000197 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1402 | +| iterations | 14949 | +| time_elapsed | 21823 | +| total_timesteps | 30615552 | +| train/ | | +| approx_kl | 0.012403281 | +| clip_fraction | 0.352 | +| clip_range | 0.0673 | +| entropy_loss | -6.19 | +| explained_variance | 0.389 | +| learning_rate | 4.27e-05 | +| loss | -0.0319 | +| n_updates | 75612 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000207 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1402 | +| iterations | 14950 | +| time_elapsed | 21824 | +| total_timesteps | 30617600 | +| train/ | | +| approx_kl | 0.012427093 | +| clip_fraction | 0.324 | +| clip_range | 0.0673 | +| entropy_loss | -6.31 | +| explained_variance | 0.395 | +| learning_rate | 4.27e-05 | +| loss | -0.0263 | +| n_updates | 75616 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000163 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1402 | +| iterations | 14951 | +| time_elapsed | 21826 | +| total_timesteps | 30619648 | +| train/ | | +| approx_kl | 0.01259545 | +| clip_fraction | 0.313 | +| clip_range | 0.0673 | +| entropy_loss | -6.38 | +| explained_variance | 0.301 | +| learning_rate | 4.27e-05 | +| loss | -0.0231 | +| n_updates | 75620 | +| policy_gradient_loss | -0.0145 | +| value_loss | 0.000341 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1402 | +| iterations | 14952 | +| time_elapsed | 21827 | +| total_timesteps | 30621696 | +| train/ | | +| approx_kl | 0.010460757 | +| clip_fraction | 0.327 | +| clip_range | 0.0673 | +| entropy_loss | -6.08 | +| explained_variance | 0.466 | +| learning_rate | 4.27e-05 | +| loss | -0.0294 | +| n_updates | 75624 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000196 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1402 | +| iterations | 14953 | +| time_elapsed | 21829 | +| total_timesteps | 30623744 | +| train/ | | +| approx_kl | 0.009901441 | +| clip_fraction | 0.304 | +| clip_range | 0.0673 | +| entropy_loss | -5.89 | +| explained_variance | 0.369 | +| learning_rate | 4.27e-05 | +| loss | -0.0287 | +| n_updates | 75628 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.00027 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1402 | +| iterations | 14954 | +| time_elapsed | 21830 | +| total_timesteps | 30625792 | +| train/ | | +| approx_kl | 0.012920005 | +| clip_fraction | 0.326 | +| clip_range | 0.0673 | +| entropy_loss | -6.31 | +| explained_variance | 0.337 | +| learning_rate | 4.27e-05 | +| loss | -0.03 | +| n_updates | 75632 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000253 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1402 | +| iterations | 14955 | +| time_elapsed | 21832 | +| total_timesteps | 30627840 | +| train/ | | +| approx_kl | 0.010320144 | +| clip_fraction | 0.307 | +| clip_range | 0.0673 | +| entropy_loss | -6.55 | +| explained_variance | 0.0485 | +| learning_rate | 4.27e-05 | +| loss | -0.0255 | +| n_updates | 75636 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000237 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1402 | +| iterations | 14956 | +| time_elapsed | 21833 | +| total_timesteps | 30629888 | +| train/ | | +| approx_kl | 0.010491047 | +| clip_fraction | 0.291 | +| clip_range | 0.0673 | +| entropy_loss | -5.88 | +| explained_variance | 0.496 | +| learning_rate | 4.27e-05 | +| loss | -0.0234 | +| n_updates | 75640 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.000289 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1402 | +| iterations | 14957 | +| time_elapsed | 21835 | +| total_timesteps | 30631936 | +| train/ | | +| approx_kl | 0.014007243 | +| clip_fraction | 0.36 | +| clip_range | 0.0673 | +| entropy_loss | -5.47 | +| explained_variance | 0.531 | +| learning_rate | 4.27e-05 | +| loss | -0.0296 | +| n_updates | 75644 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000162 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1402 | +| iterations | 14958 | +| time_elapsed | 21836 | +| total_timesteps | 30633984 | +| train/ | | +| approx_kl | 0.0148494765 | +| clip_fraction | 0.356 | +| clip_range | 0.0673 | +| entropy_loss | -5.61 | +| explained_variance | 0.454 | +| learning_rate | 4.27e-05 | +| loss | -0.0325 | +| n_updates | 75648 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000175 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1402 | +| iterations | 14959 | +| time_elapsed | 21838 | +| total_timesteps | 30636032 | +| train/ | | +| approx_kl | 0.013275946 | +| clip_fraction | 0.344 | +| clip_range | 0.0673 | +| entropy_loss | -6.59 | +| explained_variance | -0.00446 | +| learning_rate | 4.27e-05 | +| loss | -0.0257 | +| n_updates | 75652 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000137 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.384 | +| time/ | | +| fps | 1402 | +| iterations | 14960 | +| time_elapsed | 21839 | +| total_timesteps | 30638080 | +| train/ | | +| approx_kl | 0.014210478 | +| clip_fraction | 0.352 | +| clip_range | 0.0673 | +| entropy_loss | -6.85 | +| explained_variance | -0.0952 | +| learning_rate | 4.27e-05 | +| loss | -0.0386 | +| n_updates | 75656 | +| policy_gradient_loss | -0.0205 | +| value_loss | 9.38e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.39 | +| time/ | | +| fps | 1402 | +| iterations | 14961 | +| time_elapsed | 21841 | +| total_timesteps | 30640128 | +| train/ | | +| approx_kl | 0.016735656 | +| clip_fraction | 0.362 | +| clip_range | 0.0673 | +| entropy_loss | -6.44 | +| explained_variance | 0.0459 | +| learning_rate | 4.27e-05 | +| loss | -0.0259 | +| n_updates | 75660 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000109 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.389 | +| time/ | | +| fps | 1402 | +| iterations | 14962 | +| time_elapsed | 21843 | +| total_timesteps | 30642176 | +| train/ | | +| approx_kl | 0.008408509 | +| clip_fraction | 0.276 | +| clip_range | 0.0673 | +| entropy_loss | -5.79 | +| explained_variance | 0.432 | +| learning_rate | 4.27e-05 | +| loss | -0.019 | +| n_updates | 75664 | +| policy_gradient_loss | -0.012 | +| value_loss | 0.000455 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.389 | +| time/ | | +| fps | 1402 | +| iterations | 14963 | +| time_elapsed | 21844 | +| total_timesteps | 30644224 | +| train/ | | +| approx_kl | 0.012462249 | +| clip_fraction | 0.345 | +| clip_range | 0.0673 | +| entropy_loss | -5.9 | +| explained_variance | 0.479 | +| learning_rate | 4.27e-05 | +| loss | -0.0373 | +| n_updates | 75668 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.392 | +| time/ | | +| fps | 1402 | +| iterations | 14964 | +| time_elapsed | 21846 | +| total_timesteps | 30646272 | +| train/ | | +| approx_kl | 0.012427559 | +| clip_fraction | 0.353 | +| clip_range | 0.0673 | +| entropy_loss | -6.61 | +| explained_variance | 0.167 | +| learning_rate | 4.27e-05 | +| loss | -0.0341 | +| n_updates | 75672 | +| policy_gradient_loss | -0.0224 | +| value_loss | 7.6e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.395 | +| time/ | | +| fps | 1402 | +| iterations | 14965 | +| time_elapsed | 21847 | +| total_timesteps | 30648320 | +| train/ | | +| approx_kl | 0.010857555 | +| clip_fraction | 0.351 | +| clip_range | 0.0673 | +| entropy_loss | -6.62 | +| explained_variance | -0.0596 | +| learning_rate | 4.27e-05 | +| loss | -0.0245 | +| n_updates | 75676 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000244 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.393 | +| time/ | | +| fps | 1402 | +| iterations | 14966 | +| time_elapsed | 21849 | +| total_timesteps | 30650368 | +| train/ | | +| approx_kl | 0.010883937 | +| clip_fraction | 0.327 | +| clip_range | 0.0673 | +| entropy_loss | -5.53 | +| explained_variance | 0.377 | +| learning_rate | 4.27e-05 | +| loss | -0.0204 | +| n_updates | 75680 | +| policy_gradient_loss | -0.0135 | +| value_loss | 0.00033 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.39 | +| time/ | | +| fps | 1402 | +| iterations | 14967 | +| time_elapsed | 21850 | +| total_timesteps | 30652416 | +| train/ | | +| approx_kl | 0.014010639 | +| clip_fraction | 0.37 | +| clip_range | 0.0673 | +| entropy_loss | -6.32 | +| explained_variance | 0.108 | +| learning_rate | 4.27e-05 | +| loss | -0.0358 | +| n_updates | 75684 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000126 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.384 | +| time/ | | +| fps | 1402 | +| iterations | 14968 | +| time_elapsed | 21852 | +| total_timesteps | 30654464 | +| train/ | | +| approx_kl | 0.011421312 | +| clip_fraction | 0.335 | +| clip_range | 0.0673 | +| entropy_loss | -6.31 | +| explained_variance | 0.451 | +| learning_rate | 4.27e-05 | +| loss | -0.0311 | +| n_updates | 75688 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000151 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1402 | +| iterations | 14969 | +| time_elapsed | 21853 | +| total_timesteps | 30656512 | +| train/ | | +| approx_kl | 0.013481703 | +| clip_fraction | 0.369 | +| clip_range | 0.0673 | +| entropy_loss | -6.24 | +| explained_variance | 0.405 | +| learning_rate | 4.27e-05 | +| loss | -0.0317 | +| n_updates | 75692 | +| policy_gradient_loss | -0.0221 | +| value_loss | 7.58e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1402 | +| iterations | 14970 | +| time_elapsed | 21855 | +| total_timesteps | 30658560 | +| train/ | | +| approx_kl | 0.011891836 | +| clip_fraction | 0.335 | +| clip_range | 0.0673 | +| entropy_loss | -5.96 | +| explained_variance | 0.735 | +| learning_rate | 4.27e-05 | +| loss | -0.0289 | +| n_updates | 75696 | +| policy_gradient_loss | -0.0186 | +| value_loss | 8.5e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1402 | +| iterations | 14971 | +| time_elapsed | 21857 | +| total_timesteps | 30660608 | +| train/ | | +| approx_kl | 0.011568099 | +| clip_fraction | 0.339 | +| clip_range | 0.0673 | +| entropy_loss | -6.6 | +| explained_variance | 0.277 | +| learning_rate | 4.27e-05 | +| loss | -0.0318 | +| n_updates | 75700 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.0002 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1402 | +| iterations | 14972 | +| time_elapsed | 21858 | +| total_timesteps | 30662656 | +| train/ | | +| approx_kl | 0.011616521 | +| clip_fraction | 0.312 | +| clip_range | 0.0673 | +| entropy_loss | -6.51 | +| explained_variance | 0.398 | +| learning_rate | 4.27e-05 | +| loss | -0.0265 | +| n_updates | 75704 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000113 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1402 | +| iterations | 14973 | +| time_elapsed | 21860 | +| total_timesteps | 30664704 | +| train/ | | +| approx_kl | 0.013577841 | +| clip_fraction | 0.344 | +| clip_range | 0.0673 | +| entropy_loss | -6.32 | +| explained_variance | 0.476 | +| learning_rate | 4.27e-05 | +| loss | -0.0275 | +| n_updates | 75708 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000167 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1402 | +| iterations | 14974 | +| time_elapsed | 21861 | +| total_timesteps | 30666752 | +| train/ | | +| approx_kl | 0.014612168 | +| clip_fraction | 0.384 | +| clip_range | 0.0673 | +| entropy_loss | -5.79 | +| explained_variance | 0.801 | +| learning_rate | 4.27e-05 | +| loss | -0.0392 | +| n_updates | 75712 | +| policy_gradient_loss | -0.0199 | +| value_loss | 6.03e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1402 | +| iterations | 14975 | +| time_elapsed | 21863 | +| total_timesteps | 30668800 | +| train/ | | +| approx_kl | 0.013092192 | +| clip_fraction | 0.322 | +| clip_range | 0.0673 | +| entropy_loss | -6.42 | +| explained_variance | 0.362 | +| learning_rate | 4.27e-05 | +| loss | -0.0255 | +| n_updates | 75716 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000123 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1402 | +| iterations | 14976 | +| time_elapsed | 21864 | +| total_timesteps | 30670848 | +| train/ | | +| approx_kl | 0.012172036 | +| clip_fraction | 0.345 | +| clip_range | 0.0673 | +| entropy_loss | -6.77 | +| explained_variance | 0.00747 | +| learning_rate | 4.27e-05 | +| loss | -0.0311 | +| n_updates | 75720 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000209 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1402 | +| iterations | 14977 | +| time_elapsed | 21866 | +| total_timesteps | 30672896 | +| train/ | | +| approx_kl | 0.011749029 | +| clip_fraction | 0.344 | +| clip_range | 0.0673 | +| entropy_loss | -6.27 | +| explained_variance | 0.534 | +| learning_rate | 4.27e-05 | +| loss | -0.029 | +| n_updates | 75724 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000169 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1402 | +| iterations | 14978 | +| time_elapsed | 21867 | +| total_timesteps | 30674944 | +| train/ | | +| approx_kl | 0.016276672 | +| clip_fraction | 0.348 | +| clip_range | 0.0673 | +| entropy_loss | -5.86 | +| explained_variance | 0.646 | +| learning_rate | 4.27e-05 | +| loss | -0.0316 | +| n_updates | 75728 | +| policy_gradient_loss | -0.019 | +| value_loss | 7.84e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1402 | +| iterations | 14979 | +| time_elapsed | 21869 | +| total_timesteps | 30676992 | +| train/ | | +| approx_kl | 0.015442808 | +| clip_fraction | 0.304 | +| clip_range | 0.0673 | +| entropy_loss | -6.5 | +| explained_variance | 0.412 | +| learning_rate | 4.27e-05 | +| loss | -0.0256 | +| n_updates | 75732 | +| policy_gradient_loss | -0.0142 | +| value_loss | 0.000199 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1402 | +| iterations | 14980 | +| time_elapsed | 21871 | +| total_timesteps | 30679040 | +| train/ | | +| approx_kl | 0.013428872 | +| clip_fraction | 0.346 | +| clip_range | 0.0673 | +| entropy_loss | -6.17 | +| explained_variance | 0.352 | +| learning_rate | 4.27e-05 | +| loss | -0.0264 | +| n_updates | 75736 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000237 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1402 | +| iterations | 14981 | +| time_elapsed | 21872 | +| total_timesteps | 30681088 | +| train/ | | +| approx_kl | 0.016259521 | +| clip_fraction | 0.374 | +| clip_range | 0.0673 | +| entropy_loss | -6.04 | +| explained_variance | 0.362 | +| learning_rate | 4.27e-05 | +| loss | -0.0359 | +| n_updates | 75740 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000115 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1402 | +| iterations | 14982 | +| time_elapsed | 21874 | +| total_timesteps | 30683136 | +| train/ | | +| approx_kl | 0.015228761 | +| clip_fraction | 0.408 | +| clip_range | 0.0673 | +| entropy_loss | -6.12 | +| explained_variance | 0.435 | +| learning_rate | 4.27e-05 | +| loss | -0.032 | +| n_updates | 75744 | +| policy_gradient_loss | -0.0241 | +| value_loss | 6.31e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1402 | +| iterations | 14983 | +| time_elapsed | 21875 | +| total_timesteps | 30685184 | +| train/ | | +| approx_kl | 0.01707444 | +| clip_fraction | 0.378 | +| clip_range | 0.0673 | +| entropy_loss | -6.47 | +| explained_variance | 0.104 | +| learning_rate | 4.27e-05 | +| loss | -0.0336 | +| n_updates | 75748 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000274 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1402 | +| iterations | 14984 | +| time_elapsed | 21877 | +| total_timesteps | 30687232 | +| train/ | | +| approx_kl | 0.014379106 | +| clip_fraction | 0.324 | +| clip_range | 0.0673 | +| entropy_loss | -5.95 | +| explained_variance | 0.367 | +| learning_rate | 4.27e-05 | +| loss | -0.0275 | +| n_updates | 75752 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000274 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1402 | +| iterations | 14985 | +| time_elapsed | 21878 | +| total_timesteps | 30689280 | +| train/ | | +| approx_kl | 0.0176826 | +| clip_fraction | 0.363 | +| clip_range | 0.0673 | +| entropy_loss | -6.26 | +| explained_variance | 0.202 | +| learning_rate | 4.27e-05 | +| loss | -0.0346 | +| n_updates | 75756 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000178 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1402 | +| iterations | 14986 | +| time_elapsed | 21880 | +| total_timesteps | 30691328 | +| train/ | | +| approx_kl | 0.017174404 | +| clip_fraction | 0.393 | +| clip_range | 0.0673 | +| entropy_loss | -6.11 | +| explained_variance | 0.735 | +| learning_rate | 4.27e-05 | +| loss | -0.0374 | +| n_updates | 75760 | +| policy_gradient_loss | -0.0238 | +| value_loss | 7.29e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1402 | +| iterations | 14987 | +| time_elapsed | 21881 | +| total_timesteps | 30693376 | +| train/ | | +| approx_kl | 0.015215005 | +| clip_fraction | 0.339 | +| clip_range | 0.0673 | +| entropy_loss | -6.03 | +| explained_variance | 0.463 | +| learning_rate | 4.27e-05 | +| loss | -0.0295 | +| n_updates | 75764 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000163 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1402 | +| iterations | 14988 | +| time_elapsed | 21883 | +| total_timesteps | 30695424 | +| train/ | | +| approx_kl | 0.012216512 | +| clip_fraction | 0.35 | +| clip_range | 0.0673 | +| entropy_loss | -6.16 | +| explained_variance | 0.265 | +| learning_rate | 4.27e-05 | +| loss | -0.0261 | +| n_updates | 75768 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000171 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1402 | +| iterations | 14989 | +| time_elapsed | 21884 | +| total_timesteps | 30697472 | +| train/ | | +| approx_kl | 0.015860992 | +| clip_fraction | 0.365 | +| clip_range | 0.0673 | +| entropy_loss | -6.38 | +| explained_variance | 0.454 | +| learning_rate | 4.27e-05 | +| loss | -0.0314 | +| n_updates | 75772 | +| policy_gradient_loss | -0.0209 | +| value_loss | 9.39e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1402 | +| iterations | 14990 | +| time_elapsed | 21886 | +| total_timesteps | 30699520 | +| train/ | | +| approx_kl | 0.015037572 | +| clip_fraction | 0.347 | +| clip_range | 0.0673 | +| entropy_loss | -5.7 | +| explained_variance | 0.447 | +| learning_rate | 4.27e-05 | +| loss | -0.0233 | +| n_updates | 75776 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1402 | +| iterations | 14991 | +| time_elapsed | 21887 | +| total_timesteps | 30701568 | +| train/ | | +| approx_kl | 0.015533768 | +| clip_fraction | 0.362 | +| clip_range | 0.0673 | +| entropy_loss | -6.06 | +| explained_variance | 0.321 | +| learning_rate | 4.27e-05 | +| loss | -0.0264 | +| n_updates | 75780 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000251 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1402 | +| iterations | 14992 | +| time_elapsed | 21889 | +| total_timesteps | 30703616 | +| train/ | | +| approx_kl | 0.011256034 | +| clip_fraction | 0.318 | +| clip_range | 0.0673 | +| entropy_loss | -5.39 | +| explained_variance | 0.481 | +| learning_rate | 4.27e-05 | +| loss | -0.0251 | +| n_updates | 75784 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.000284 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1402 | +| iterations | 14993 | +| time_elapsed | 21890 | +| total_timesteps | 30705664 | +| train/ | | +| approx_kl | 0.014011615 | +| clip_fraction | 0.36 | +| clip_range | 0.0673 | +| entropy_loss | -5.7 | +| explained_variance | 0.562 | +| learning_rate | 4.27e-05 | +| loss | -0.0341 | +| n_updates | 75788 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000132 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1402 | +| iterations | 14994 | +| time_elapsed | 21892 | +| total_timesteps | 30707712 | +| train/ | | +| approx_kl | 0.012578142 | +| clip_fraction | 0.36 | +| clip_range | 0.0673 | +| entropy_loss | -5.91 | +| explained_variance | 0.357 | +| learning_rate | 4.27e-05 | +| loss | -0.0334 | +| n_updates | 75792 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000115 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1402 | +| iterations | 14995 | +| time_elapsed | 21893 | +| total_timesteps | 30709760 | +| train/ | | +| approx_kl | 0.014358491 | +| clip_fraction | 0.352 | +| clip_range | 0.0673 | +| entropy_loss | -5.66 | +| explained_variance | 0.499 | +| learning_rate | 4.27e-05 | +| loss | -0.0195 | +| n_updates | 75796 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000219 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1402 | +| iterations | 14996 | +| time_elapsed | 21895 | +| total_timesteps | 30711808 | +| train/ | | +| approx_kl | 0.015650656 | +| clip_fraction | 0.362 | +| clip_range | 0.0673 | +| entropy_loss | -6 | +| explained_variance | 0.566 | +| learning_rate | 4.27e-05 | +| loss | -0.0272 | +| n_updates | 75800 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000131 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1402 | +| iterations | 14997 | +| time_elapsed | 21896 | +| total_timesteps | 30713856 | +| train/ | | +| approx_kl | 0.015572308 | +| clip_fraction | 0.379 | +| clip_range | 0.0673 | +| entropy_loss | -5.77 | +| explained_variance | 0.729 | +| learning_rate | 4.27e-05 | +| loss | -0.0315 | +| n_updates | 75804 | +| policy_gradient_loss | -0.0219 | +| value_loss | 7.17e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1402 | +| iterations | 14998 | +| time_elapsed | 21898 | +| total_timesteps | 30715904 | +| train/ | | +| approx_kl | 0.012264686 | +| clip_fraction | 0.342 | +| clip_range | 0.0673 | +| entropy_loss | -6.27 | +| explained_variance | 0.192 | +| learning_rate | 4.27e-05 | +| loss | -0.0302 | +| n_updates | 75808 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000111 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1402 | +| iterations | 14999 | +| time_elapsed | 21900 | +| total_timesteps | 30717952 | +| train/ | | +| approx_kl | 0.011685482 | +| clip_fraction | 0.325 | +| clip_range | 0.0673 | +| entropy_loss | -6.24 | +| explained_variance | 0.399 | +| learning_rate | 4.27e-05 | +| loss | -0.0301 | +| n_updates | 75812 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000152 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1402 | +| iterations | 15000 | +| time_elapsed | 21901 | +| total_timesteps | 30720000 | +| train/ | | +| approx_kl | 0.019529998 | +| clip_fraction | 0.373 | +| clip_range | 0.0673 | +| entropy_loss | -6.49 | +| explained_variance | 0.312 | +| learning_rate | 4.27e-05 | +| loss | -0.0316 | +| n_updates | 75816 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000106 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1402 | +| iterations | 15001 | +| time_elapsed | 21903 | +| total_timesteps | 30722048 | +| train/ | | +| approx_kl | 0.01543197 | +| clip_fraction | 0.318 | +| clip_range | 0.0673 | +| entropy_loss | -6.46 | +| explained_variance | 0.48 | +| learning_rate | 4.27e-05 | +| loss | -0.0258 | +| n_updates | 75820 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000154 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1402 | +| iterations | 15002 | +| time_elapsed | 21904 | +| total_timesteps | 30724096 | +| train/ | | +| approx_kl | 0.012671058 | +| clip_fraction | 0.341 | +| clip_range | 0.0673 | +| entropy_loss | -6.05 | +| explained_variance | 0.264 | +| learning_rate | 4.27e-05 | +| loss | -0.0315 | +| n_updates | 75824 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000136 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1402 | +| iterations | 15003 | +| time_elapsed | 21906 | +| total_timesteps | 30726144 | +| train/ | | +| approx_kl | 0.013026318 | +| clip_fraction | 0.347 | +| clip_range | 0.0673 | +| entropy_loss | -6.47 | +| explained_variance | 0.188 | +| learning_rate | 4.27e-05 | +| loss | -0.0231 | +| n_updates | 75828 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000192 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1402 | +| iterations | 15004 | +| time_elapsed | 21907 | +| total_timesteps | 30728192 | +| train/ | | +| approx_kl | 0.014877474 | +| clip_fraction | 0.319 | +| clip_range | 0.0673 | +| entropy_loss | -6.02 | +| explained_variance | 0.555 | +| learning_rate | 4.27e-05 | +| loss | -0.0268 | +| n_updates | 75832 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000163 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1402 | +| iterations | 15005 | +| time_elapsed | 21909 | +| total_timesteps | 30730240 | +| train/ | | +| approx_kl | 0.0160696 | +| clip_fraction | 0.371 | +| clip_range | 0.0673 | +| entropy_loss | -5.99 | +| explained_variance | 0.756 | +| learning_rate | 4.27e-05 | +| loss | -0.0358 | +| n_updates | 75836 | +| policy_gradient_loss | -0.0212 | +| value_loss | 4.82e-05 | +--------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1402 | +| iterations | 15006 | +| time_elapsed | 21910 | +| total_timesteps | 30732288 | +| train/ | | +| approx_kl | 0.01198489 | +| clip_fraction | 0.315 | +| clip_range | 0.0673 | +| entropy_loss | -6.47 | +| explained_variance | 0.0124 | +| learning_rate | 4.27e-05 | +| loss | -0.0286 | +| n_updates | 75840 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000165 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1402 | +| iterations | 15007 | +| time_elapsed | 21912 | +| total_timesteps | 30734336 | +| train/ | | +| approx_kl | 0.014043262 | +| clip_fraction | 0.366 | +| clip_range | 0.0673 | +| entropy_loss | -6.51 | +| explained_variance | 0.37 | +| learning_rate | 4.27e-05 | +| loss | -0.0304 | +| n_updates | 75844 | +| policy_gradient_loss | -0.0194 | +| value_loss | 9.43e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1402 | +| iterations | 15008 | +| time_elapsed | 21913 | +| total_timesteps | 30736384 | +| train/ | | +| approx_kl | 0.012793206 | +| clip_fraction | 0.336 | +| clip_range | 0.0673 | +| entropy_loss | -6.08 | +| explained_variance | 0.428 | +| learning_rate | 4.27e-05 | +| loss | -0.0267 | +| n_updates | 75848 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000179 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1402 | +| iterations | 15009 | +| time_elapsed | 21915 | +| total_timesteps | 30738432 | +| train/ | | +| approx_kl | 0.012043641 | +| clip_fraction | 0.338 | +| clip_range | 0.0673 | +| entropy_loss | -5.83 | +| explained_variance | 0.498 | +| learning_rate | 4.27e-05 | +| loss | -0.0218 | +| n_updates | 75852 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000162 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1402 | +| iterations | 15010 | +| time_elapsed | 21916 | +| total_timesteps | 30740480 | +| train/ | | +| approx_kl | 0.014219447 | +| clip_fraction | 0.361 | +| clip_range | 0.0673 | +| entropy_loss | -5.94 | +| explained_variance | 0.602 | +| learning_rate | 4.27e-05 | +| loss | -0.0328 | +| n_updates | 75856 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000118 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1402 | +| iterations | 15011 | +| time_elapsed | 21918 | +| total_timesteps | 30742528 | +| train/ | | +| approx_kl | 0.010554766 | +| clip_fraction | 0.3 | +| clip_range | 0.0673 | +| entropy_loss | -5.91 | +| explained_variance | 0.44 | +| learning_rate | 4.27e-05 | +| loss | -0.0163 | +| n_updates | 75860 | +| policy_gradient_loss | -0.0131 | +| value_loss | 0.000225 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1402 | +| iterations | 15012 | +| time_elapsed | 21919 | +| total_timesteps | 30744576 | +| train/ | | +| approx_kl | 0.017170485 | +| clip_fraction | 0.356 | +| clip_range | 0.0673 | +| entropy_loss | -6.38 | +| explained_variance | -0.00377 | +| learning_rate | 4.27e-05 | +| loss | -0.0289 | +| n_updates | 75864 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000174 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1402 | +| iterations | 15013 | +| time_elapsed | 21921 | +| total_timesteps | 30746624 | +| train/ | | +| approx_kl | 0.015527486 | +| clip_fraction | 0.362 | +| clip_range | 0.0673 | +| entropy_loss | -6.19 | +| explained_variance | 0.475 | +| learning_rate | 4.27e-05 | +| loss | -0.0302 | +| n_updates | 75868 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000157 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1402 | +| iterations | 15014 | +| time_elapsed | 21922 | +| total_timesteps | 30748672 | +| train/ | | +| approx_kl | 0.0149360355 | +| clip_fraction | 0.32 | +| clip_range | 0.0673 | +| entropy_loss | -6.32 | +| explained_variance | 0.292 | +| learning_rate | 4.27e-05 | +| loss | -0.0273 | +| n_updates | 75872 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000259 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1402 | +| iterations | 15015 | +| time_elapsed | 21924 | +| total_timesteps | 30750720 | +| train/ | | +| approx_kl | 0.011288984 | +| clip_fraction | 0.337 | +| clip_range | 0.0673 | +| entropy_loss | -6.54 | +| explained_variance | 0.118 | +| learning_rate | 4.27e-05 | +| loss | -0.0334 | +| n_updates | 75876 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000153 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1402 | +| iterations | 15016 | +| time_elapsed | 21925 | +| total_timesteps | 30752768 | +| train/ | | +| approx_kl | 0.009906266 | +| clip_fraction | 0.304 | +| clip_range | 0.0673 | +| entropy_loss | -6.95 | +| explained_variance | -0.0208 | +| learning_rate | 4.27e-05 | +| loss | -0.0285 | +| n_updates | 75880 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000177 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1402 | +| iterations | 15017 | +| time_elapsed | 21927 | +| total_timesteps | 30754816 | +| train/ | | +| approx_kl | 0.009204531 | +| clip_fraction | 0.315 | +| clip_range | 0.0673 | +| entropy_loss | -6.79 | +| explained_variance | 0.222 | +| learning_rate | 4.27e-05 | +| loss | -0.0268 | +| n_updates | 75884 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000243 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1402 | +| iterations | 15018 | +| time_elapsed | 21928 | +| total_timesteps | 30756864 | +| train/ | | +| approx_kl | 0.013477642 | +| clip_fraction | 0.322 | +| clip_range | 0.0673 | +| entropy_loss | -6.41 | +| explained_variance | 0.236 | +| learning_rate | 4.27e-05 | +| loss | -0.0294 | +| n_updates | 75888 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000207 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1402 | +| iterations | 15019 | +| time_elapsed | 21930 | +| total_timesteps | 30758912 | +| train/ | | +| approx_kl | 0.012246661 | +| clip_fraction | 0.347 | +| clip_range | 0.0673 | +| entropy_loss | -6.11 | +| explained_variance | 0.768 | +| learning_rate | 4.27e-05 | +| loss | -0.0354 | +| n_updates | 75892 | +| policy_gradient_loss | -0.021 | +| value_loss | 6.22e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1402 | +| iterations | 15020 | +| time_elapsed | 21931 | +| total_timesteps | 30760960 | +| train/ | | +| approx_kl | 0.017242953 | +| clip_fraction | 0.333 | +| clip_range | 0.0673 | +| entropy_loss | -6.42 | +| explained_variance | 0.476 | +| learning_rate | 4.27e-05 | +| loss | -0.0343 | +| n_updates | 75896 | +| policy_gradient_loss | -0.0194 | +| value_loss | 7.57e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1402 | +| iterations | 15021 | +| time_elapsed | 21933 | +| total_timesteps | 30763008 | +| train/ | | +| approx_kl | 0.0156227825 | +| clip_fraction | 0.326 | +| clip_range | 0.0673 | +| entropy_loss | -6.55 | +| explained_variance | 0.382 | +| learning_rate | 4.27e-05 | +| loss | -0.0274 | +| n_updates | 75900 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000224 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1402 | +| iterations | 15022 | +| time_elapsed | 21934 | +| total_timesteps | 30765056 | +| train/ | | +| approx_kl | 0.014369324 | +| clip_fraction | 0.316 | +| clip_range | 0.0673 | +| entropy_loss | -6.31 | +| explained_variance | 0.487 | +| learning_rate | 4.27e-05 | +| loss | -0.0263 | +| n_updates | 75904 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.00017 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1402 | +| iterations | 15023 | +| time_elapsed | 21936 | +| total_timesteps | 30767104 | +| train/ | | +| approx_kl | 0.01227136 | +| clip_fraction | 0.303 | +| clip_range | 0.0673 | +| entropy_loss | -6.41 | +| explained_variance | 0.23 | +| learning_rate | 4.27e-05 | +| loss | -0.0283 | +| n_updates | 75908 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.00027 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1402 | +| iterations | 15024 | +| time_elapsed | 21937 | +| total_timesteps | 30769152 | +| train/ | | +| approx_kl | 0.017193768 | +| clip_fraction | 0.327 | +| clip_range | 0.0673 | +| entropy_loss | -5.85 | +| explained_variance | 0.563 | +| learning_rate | 4.27e-05 | +| loss | -0.0269 | +| n_updates | 75912 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000158 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1402 | +| iterations | 15025 | +| time_elapsed | 21939 | +| total_timesteps | 30771200 | +| train/ | | +| approx_kl | 0.013315877 | +| clip_fraction | 0.323 | +| clip_range | 0.0673 | +| entropy_loss | -6.1 | +| explained_variance | 0.224 | +| learning_rate | 4.27e-05 | +| loss | -0.0276 | +| n_updates | 75916 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000365 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1402 | +| iterations | 15026 | +| time_elapsed | 21940 | +| total_timesteps | 30773248 | +| train/ | | +| approx_kl | 0.0103049055 | +| clip_fraction | 0.316 | +| clip_range | 0.0673 | +| entropy_loss | -6.02 | +| explained_variance | 0.155 | +| learning_rate | 4.27e-05 | +| loss | -0.0365 | +| n_updates | 75920 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000383 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1402 | +| iterations | 15027 | +| time_elapsed | 21942 | +| total_timesteps | 30775296 | +| train/ | | +| approx_kl | 0.010596919 | +| clip_fraction | 0.315 | +| clip_range | 0.0673 | +| entropy_loss | -6.28 | +| explained_variance | 0.391 | +| learning_rate | 4.27e-05 | +| loss | -0.0273 | +| n_updates | 75924 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000122 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1402 | +| iterations | 15028 | +| time_elapsed | 21943 | +| total_timesteps | 30777344 | +| train/ | | +| approx_kl | 0.0121606635 | +| clip_fraction | 0.325 | +| clip_range | 0.0673 | +| entropy_loss | -6.69 | +| explained_variance | 0.239 | +| learning_rate | 4.27e-05 | +| loss | -0.0346 | +| n_updates | 75928 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000252 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1402 | +| iterations | 15029 | +| time_elapsed | 21945 | +| total_timesteps | 30779392 | +| train/ | | +| approx_kl | 0.011480352 | +| clip_fraction | 0.315 | +| clip_range | 0.0673 | +| entropy_loss | -6.47 | +| explained_variance | 0.386 | +| learning_rate | 4.27e-05 | +| loss | -0.0323 | +| n_updates | 75932 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000209 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1402 | +| iterations | 15030 | +| time_elapsed | 21946 | +| total_timesteps | 30781440 | +| train/ | | +| approx_kl | 0.013696145 | +| clip_fraction | 0.343 | +| clip_range | 0.0673 | +| entropy_loss | -6.75 | +| explained_variance | -0.294 | +| learning_rate | 4.27e-05 | +| loss | -0.0375 | +| n_updates | 75936 | +| policy_gradient_loss | -0.0213 | +| value_loss | 8.41e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1402 | +| iterations | 15031 | +| time_elapsed | 21948 | +| total_timesteps | 30783488 | +| train/ | | +| approx_kl | 0.015082136 | +| clip_fraction | 0.298 | +| clip_range | 0.0673 | +| entropy_loss | -7.06 | +| explained_variance | 0.113 | +| learning_rate | 4.27e-05 | +| loss | -0.0266 | +| n_updates | 75940 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000194 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1402 | +| iterations | 15032 | +| time_elapsed | 21950 | +| total_timesteps | 30785536 | +| train/ | | +| approx_kl | 0.010264964 | +| clip_fraction | 0.314 | +| clip_range | 0.0673 | +| entropy_loss | -5.29 | +| explained_variance | 0.659 | +| learning_rate | 4.27e-05 | +| loss | -0.0198 | +| n_updates | 75944 | +| policy_gradient_loss | -0.0141 | +| value_loss | 0.000183 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1402 | +| iterations | 15033 | +| time_elapsed | 21951 | +| total_timesteps | 30787584 | +| train/ | | +| approx_kl | 0.014129231 | +| clip_fraction | 0.321 | +| clip_range | 0.0673 | +| entropy_loss | -5.78 | +| explained_variance | 0.443 | +| learning_rate | 4.27e-05 | +| loss | -0.0289 | +| n_updates | 75948 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000162 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1402 | +| iterations | 15034 | +| time_elapsed | 21953 | +| total_timesteps | 30789632 | +| train/ | | +| approx_kl | 0.011013416 | +| clip_fraction | 0.312 | +| clip_range | 0.0673 | +| entropy_loss | -6.37 | +| explained_variance | 0.37 | +| learning_rate | 4.27e-05 | +| loss | -0.0302 | +| n_updates | 75952 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000172 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1402 | +| iterations | 15035 | +| time_elapsed | 21954 | +| total_timesteps | 30791680 | +| train/ | | +| approx_kl | 0.013193806 | +| clip_fraction | 0.345 | +| clip_range | 0.0673 | +| entropy_loss | -6.33 | +| explained_variance | 0.264 | +| learning_rate | 4.27e-05 | +| loss | -0.0327 | +| n_updates | 75956 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000368 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1402 | +| iterations | 15036 | +| time_elapsed | 21956 | +| total_timesteps | 30793728 | +| train/ | | +| approx_kl | 0.010300336 | +| clip_fraction | 0.33 | +| clip_range | 0.0673 | +| entropy_loss | -6.72 | +| explained_variance | 0.196 | +| learning_rate | 4.27e-05 | +| loss | -0.0275 | +| n_updates | 75960 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000237 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1402 | +| iterations | 15037 | +| time_elapsed | 21957 | +| total_timesteps | 30795776 | +| train/ | | +| approx_kl | 0.008738045 | +| clip_fraction | 0.308 | +| clip_range | 0.0673 | +| entropy_loss | -6.46 | +| explained_variance | 0.281 | +| learning_rate | 4.27e-05 | +| loss | -0.0283 | +| n_updates | 75964 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000451 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1402 | +| iterations | 15038 | +| time_elapsed | 21959 | +| total_timesteps | 30797824 | +| train/ | | +| approx_kl | 0.011467822 | +| clip_fraction | 0.325 | +| clip_range | 0.0673 | +| entropy_loss | -5.78 | +| explained_variance | 0.489 | +| learning_rate | 4.27e-05 | +| loss | -0.0374 | +| n_updates | 75968 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000216 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1402 | +| iterations | 15039 | +| time_elapsed | 21960 | +| total_timesteps | 30799872 | +| train/ | | +| approx_kl | 0.013296615 | +| clip_fraction | 0.35 | +| clip_range | 0.0673 | +| entropy_loss | -5.78 | +| explained_variance | 0.588 | +| learning_rate | 4.27e-05 | +| loss | -0.0311 | +| n_updates | 75972 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000131 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1402 | +| iterations | 15040 | +| time_elapsed | 21962 | +| total_timesteps | 30801920 | +| train/ | | +| approx_kl | 0.014215745 | +| clip_fraction | 0.32 | +| clip_range | 0.0673 | +| entropy_loss | -6.63 | +| explained_variance | -0.0525 | +| learning_rate | 4.27e-05 | +| loss | -0.0294 | +| n_updates | 75976 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000372 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1402 | +| iterations | 15041 | +| time_elapsed | 21963 | +| total_timesteps | 30803968 | +| train/ | | +| approx_kl | 0.011030974 | +| clip_fraction | 0.309 | +| clip_range | 0.0673 | +| entropy_loss | -6.42 | +| explained_variance | 0.397 | +| learning_rate | 4.27e-05 | +| loss | -0.0264 | +| n_updates | 75980 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000255 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1402 | +| iterations | 15042 | +| time_elapsed | 21965 | +| total_timesteps | 30806016 | +| train/ | | +| approx_kl | 0.011130208 | +| clip_fraction | 0.321 | +| clip_range | 0.0673 | +| entropy_loss | -5.95 | +| explained_variance | 0.515 | +| learning_rate | 4.27e-05 | +| loss | -0.0301 | +| n_updates | 75984 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000208 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1402 | +| iterations | 15043 | +| time_elapsed | 21966 | +| total_timesteps | 30808064 | +| train/ | | +| approx_kl | 0.012119977 | +| clip_fraction | 0.308 | +| clip_range | 0.0673 | +| entropy_loss | -6.79 | +| explained_variance | 0.173 | +| learning_rate | 4.27e-05 | +| loss | -0.0284 | +| n_updates | 75988 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000329 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1402 | +| iterations | 15044 | +| time_elapsed | 21968 | +| total_timesteps | 30810112 | +| train/ | | +| approx_kl | 0.012692409 | +| clip_fraction | 0.341 | +| clip_range | 0.0673 | +| entropy_loss | -6.68 | +| explained_variance | 0.367 | +| learning_rate | 4.27e-05 | +| loss | -0.0345 | +| n_updates | 75992 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000143 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1402 | +| iterations | 15045 | +| time_elapsed | 21969 | +| total_timesteps | 30812160 | +| train/ | | +| approx_kl | 0.012379055 | +| clip_fraction | 0.311 | +| clip_range | 0.0673 | +| entropy_loss | -6.36 | +| explained_variance | 0.463 | +| learning_rate | 4.27e-05 | +| loss | -0.0258 | +| n_updates | 75996 | +| policy_gradient_loss | -0.0144 | +| value_loss | 0.000274 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1402 | +| iterations | 15046 | +| time_elapsed | 21971 | +| total_timesteps | 30814208 | +| train/ | | +| approx_kl | 0.011838429 | +| clip_fraction | 0.361 | +| clip_range | 0.0673 | +| entropy_loss | -6.46 | +| explained_variance | 0.00705 | +| learning_rate | 4.27e-05 | +| loss | -0.0327 | +| n_updates | 76000 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000162 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1402 | +| iterations | 15047 | +| time_elapsed | 21972 | +| total_timesteps | 30816256 | +| train/ | | +| approx_kl | 0.0158767 | +| clip_fraction | 0.351 | +| clip_range | 0.0673 | +| entropy_loss | -6.14 | +| explained_variance | 0.64 | +| learning_rate | 4.27e-05 | +| loss | -0.0322 | +| n_updates | 76004 | +| policy_gradient_loss | -0.0199 | +| value_loss | 8.16e-05 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1402 | +| iterations | 15048 | +| time_elapsed | 21974 | +| total_timesteps | 30818304 | +| train/ | | +| approx_kl | 0.012017617 | +| clip_fraction | 0.323 | +| clip_range | 0.0673 | +| entropy_loss | -5.48 | +| explained_variance | 0.743 | +| learning_rate | 4.27e-05 | +| loss | -0.0231 | +| n_updates | 76008 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000122 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1402 | +| iterations | 15049 | +| time_elapsed | 21975 | +| total_timesteps | 30820352 | +| train/ | | +| approx_kl | 0.01559224 | +| clip_fraction | 0.326 | +| clip_range | 0.0673 | +| entropy_loss | -6.24 | +| explained_variance | 0.186 | +| learning_rate | 4.27e-05 | +| loss | -0.0296 | +| n_updates | 76012 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000234 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1402 | +| iterations | 15050 | +| time_elapsed | 21977 | +| total_timesteps | 30822400 | +| train/ | | +| approx_kl | 0.010447238 | +| clip_fraction | 0.321 | +| clip_range | 0.0673 | +| entropy_loss | -6.89 | +| explained_variance | -0.2 | +| learning_rate | 4.27e-05 | +| loss | -0.0307 | +| n_updates | 76016 | +| policy_gradient_loss | -0.0182 | +| value_loss | 8.66e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1402 | +| iterations | 15051 | +| time_elapsed | 21978 | +| total_timesteps | 30824448 | +| train/ | | +| approx_kl | 0.012215766 | +| clip_fraction | 0.308 | +| clip_range | 0.0673 | +| entropy_loss | -6.05 | +| explained_variance | 0.49 | +| learning_rate | 4.27e-05 | +| loss | -0.0174 | +| n_updates | 76020 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000308 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1402 | +| iterations | 15052 | +| time_elapsed | 21980 | +| total_timesteps | 30826496 | +| train/ | | +| approx_kl | 0.011440555 | +| clip_fraction | 0.352 | +| clip_range | 0.0673 | +| entropy_loss | -5.54 | +| explained_variance | 0.727 | +| learning_rate | 4.27e-05 | +| loss | -0.0251 | +| n_updates | 76024 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000109 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1402 | +| iterations | 15053 | +| time_elapsed | 21981 | +| total_timesteps | 30828544 | +| train/ | | +| approx_kl | 0.008693157 | +| clip_fraction | 0.315 | +| clip_range | 0.0673 | +| entropy_loss | -6.35 | +| explained_variance | 0.403 | +| learning_rate | 4.27e-05 | +| loss | -0.0265 | +| n_updates | 76028 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.00013 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1402 | +| iterations | 15054 | +| time_elapsed | 21983 | +| total_timesteps | 30830592 | +| train/ | | +| approx_kl | 0.010917896 | +| clip_fraction | 0.295 | +| clip_range | 0.0673 | +| entropy_loss | -6.56 | +| explained_variance | 0.26 | +| learning_rate | 4.27e-05 | +| loss | -0.0191 | +| n_updates | 76032 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000317 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1402 | +| iterations | 15055 | +| time_elapsed | 21985 | +| total_timesteps | 30832640 | +| train/ | | +| approx_kl | 0.011729571 | +| clip_fraction | 0.328 | +| clip_range | 0.0673 | +| entropy_loss | -6.41 | +| explained_variance | 0.502 | +| learning_rate | 4.27e-05 | +| loss | -0.0305 | +| n_updates | 76036 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000175 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1402 | +| iterations | 15056 | +| time_elapsed | 21986 | +| total_timesteps | 30834688 | +| train/ | | +| approx_kl | 0.011124203 | +| clip_fraction | 0.332 | +| clip_range | 0.0673 | +| entropy_loss | -6.23 | +| explained_variance | 0.295 | +| learning_rate | 4.27e-05 | +| loss | -0.0314 | +| n_updates | 76040 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000156 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1402 | +| iterations | 15057 | +| time_elapsed | 21988 | +| total_timesteps | 30836736 | +| train/ | | +| approx_kl | 0.010507939 | +| clip_fraction | 0.311 | +| clip_range | 0.0673 | +| entropy_loss | -6.86 | +| explained_variance | 0.0727 | +| learning_rate | 4.27e-05 | +| loss | -0.0274 | +| n_updates | 76044 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000174 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1402 | +| iterations | 15058 | +| time_elapsed | 21989 | +| total_timesteps | 30838784 | +| train/ | | +| approx_kl | 0.011122594 | +| clip_fraction | 0.354 | +| clip_range | 0.0673 | +| entropy_loss | -7.01 | +| explained_variance | 0.00141 | +| learning_rate | 4.27e-05 | +| loss | -0.0342 | +| n_updates | 76048 | +| policy_gradient_loss | -0.0218 | +| value_loss | 8.45e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1402 | +| iterations | 15059 | +| time_elapsed | 21991 | +| total_timesteps | 30840832 | +| train/ | | +| approx_kl | 0.008987275 | +| clip_fraction | 0.33 | +| clip_range | 0.0673 | +| entropy_loss | -6.47 | +| explained_variance | 0.258 | +| learning_rate | 4.27e-05 | +| loss | -0.0287 | +| n_updates | 76052 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000158 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1402 | +| iterations | 15060 | +| time_elapsed | 21992 | +| total_timesteps | 30842880 | +| train/ | | +| approx_kl | 0.010037907 | +| clip_fraction | 0.307 | +| clip_range | 0.0673 | +| entropy_loss | -6.04 | +| explained_variance | 0.491 | +| learning_rate | 4.27e-05 | +| loss | -0.0273 | +| n_updates | 76056 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.000273 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1402 | +| iterations | 15061 | +| time_elapsed | 21994 | +| total_timesteps | 30844928 | +| train/ | | +| approx_kl | 0.009162499 | +| clip_fraction | 0.312 | +| clip_range | 0.0673 | +| entropy_loss | -5.98 | +| explained_variance | 0.542 | +| learning_rate | 4.27e-05 | +| loss | -0.0363 | +| n_updates | 76060 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.00014 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1402 | +| iterations | 15062 | +| time_elapsed | 21995 | +| total_timesteps | 30846976 | +| train/ | | +| approx_kl | 0.012245877 | +| clip_fraction | 0.33 | +| clip_range | 0.0673 | +| entropy_loss | -5.83 | +| explained_variance | 0.641 | +| learning_rate | 4.27e-05 | +| loss | -0.0266 | +| n_updates | 76064 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000128 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1402 | +| iterations | 15063 | +| time_elapsed | 21997 | +| total_timesteps | 30849024 | +| train/ | | +| approx_kl | 0.012809312 | +| clip_fraction | 0.322 | +| clip_range | 0.0673 | +| entropy_loss | -5.97 | +| explained_variance | 0.554 | +| learning_rate | 4.27e-05 | +| loss | -0.0266 | +| n_updates | 76068 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000125 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1402 | +| iterations | 15064 | +| time_elapsed | 21998 | +| total_timesteps | 30851072 | +| train/ | | +| approx_kl | 0.013599041 | +| clip_fraction | 0.336 | +| clip_range | 0.0673 | +| entropy_loss | -6.29 | +| explained_variance | 0.48 | +| learning_rate | 4.27e-05 | +| loss | -0.0258 | +| n_updates | 76072 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000157 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1402 | +| iterations | 15065 | +| time_elapsed | 22000 | +| total_timesteps | 30853120 | +| train/ | | +| approx_kl | 0.011811258 | +| clip_fraction | 0.319 | +| clip_range | 0.0673 | +| entropy_loss | -6.61 | +| explained_variance | 0.461 | +| learning_rate | 4.27e-05 | +| loss | -0.0295 | +| n_updates | 76076 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000142 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1402 | +| iterations | 15066 | +| time_elapsed | 22002 | +| total_timesteps | 30855168 | +| train/ | | +| approx_kl | 0.00937807 | +| clip_fraction | 0.299 | +| clip_range | 0.0673 | +| entropy_loss | -6.56 | +| explained_variance | 0.248 | +| learning_rate | 4.27e-05 | +| loss | -0.0198 | +| n_updates | 76080 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000373 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1402 | +| iterations | 15067 | +| time_elapsed | 22003 | +| total_timesteps | 30857216 | +| train/ | | +| approx_kl | 0.014611911 | +| clip_fraction | 0.364 | +| clip_range | 0.0673 | +| entropy_loss | -6.16 | +| explained_variance | 0.645 | +| learning_rate | 4.27e-05 | +| loss | -0.0316 | +| n_updates | 76084 | +| policy_gradient_loss | -0.0223 | +| value_loss | 7.83e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1402 | +| iterations | 15068 | +| time_elapsed | 22005 | +| total_timesteps | 30859264 | +| train/ | | +| approx_kl | 0.012929586 | +| clip_fraction | 0.369 | +| clip_range | 0.0673 | +| entropy_loss | -6.3 | +| explained_variance | 0.522 | +| learning_rate | 4.27e-05 | +| loss | -0.0365 | +| n_updates | 76088 | +| policy_gradient_loss | -0.021 | +| value_loss | 9.37e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1402 | +| iterations | 15069 | +| time_elapsed | 22006 | +| total_timesteps | 30861312 | +| train/ | | +| approx_kl | 0.01025231 | +| clip_fraction | 0.301 | +| clip_range | 0.0673 | +| entropy_loss | -5.74 | +| explained_variance | 0.716 | +| learning_rate | 4.27e-05 | +| loss | -0.0299 | +| n_updates | 76092 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000102 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1402 | +| iterations | 15070 | +| time_elapsed | 22008 | +| total_timesteps | 30863360 | +| train/ | | +| approx_kl | 0.012299014 | +| clip_fraction | 0.323 | +| clip_range | 0.0673 | +| entropy_loss | -6.52 | +| explained_variance | 0.495 | +| learning_rate | 4.27e-05 | +| loss | -0.0287 | +| n_updates | 76096 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000105 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1402 | +| iterations | 15071 | +| time_elapsed | 22009 | +| total_timesteps | 30865408 | +| train/ | | +| approx_kl | 0.014843712 | +| clip_fraction | 0.373 | +| clip_range | 0.0673 | +| entropy_loss | -6.23 | +| explained_variance | 0.657 | +| learning_rate | 4.27e-05 | +| loss | -0.0355 | +| n_updates | 76100 | +| policy_gradient_loss | -0.0228 | +| value_loss | 4.29e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1402 | +| iterations | 15072 | +| time_elapsed | 22011 | +| total_timesteps | 30867456 | +| train/ | | +| approx_kl | 0.012082884 | +| clip_fraction | 0.324 | +| clip_range | 0.0673 | +| entropy_loss | -6.07 | +| explained_variance | 0.372 | +| learning_rate | 4.27e-05 | +| loss | -0.0219 | +| n_updates | 76104 | +| policy_gradient_loss | -0.0143 | +| value_loss | 0.000262 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1402 | +| iterations | 15073 | +| time_elapsed | 22012 | +| total_timesteps | 30869504 | +| train/ | | +| approx_kl | 0.011544342 | +| clip_fraction | 0.342 | +| clip_range | 0.0673 | +| entropy_loss | -6.26 | +| explained_variance | 0.557 | +| learning_rate | 4.27e-05 | +| loss | -0.0274 | +| n_updates | 76108 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.00015 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1402 | +| iterations | 15074 | +| time_elapsed | 22014 | +| total_timesteps | 30871552 | +| train/ | | +| approx_kl | 0.011981073 | +| clip_fraction | 0.337 | +| clip_range | 0.0673 | +| entropy_loss | -6.56 | +| explained_variance | 0.0192 | +| learning_rate | 4.27e-05 | +| loss | -0.0322 | +| n_updates | 76112 | +| policy_gradient_loss | -0.0208 | +| value_loss | 8.93e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.14e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1402 | +| iterations | 15075 | +| time_elapsed | 22016 | +| total_timesteps | 30873600 | +| train/ | | +| approx_kl | 0.010621207 | +| clip_fraction | 0.321 | +| clip_range | 0.0673 | +| entropy_loss | -6.64 | +| explained_variance | 0.19 | +| learning_rate | 4.27e-05 | +| loss | -0.0308 | +| n_updates | 76116 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000297 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1402 | +| iterations | 15076 | +| time_elapsed | 22017 | +| total_timesteps | 30875648 | +| train/ | | +| approx_kl | 0.010799291 | +| clip_fraction | 0.324 | +| clip_range | 0.0673 | +| entropy_loss | -6.52 | +| explained_variance | 0.425 | +| learning_rate | 4.27e-05 | +| loss | -0.0288 | +| n_updates | 76120 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.00017 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1402 | +| iterations | 15077 | +| time_elapsed | 22019 | +| total_timesteps | 30877696 | +| train/ | | +| approx_kl | 0.014994085 | +| clip_fraction | 0.351 | +| clip_range | 0.0673 | +| entropy_loss | -5.78 | +| explained_variance | 0.754 | +| learning_rate | 4.27e-05 | +| loss | -0.0317 | +| n_updates | 76124 | +| policy_gradient_loss | -0.0205 | +| value_loss | 6.37e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.14e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1402 | +| iterations | 15078 | +| time_elapsed | 22020 | +| total_timesteps | 30879744 | +| train/ | | +| approx_kl | 0.016956734 | +| clip_fraction | 0.355 | +| clip_range | 0.0673 | +| entropy_loss | -5.65 | +| explained_variance | 0.575 | +| learning_rate | 4.27e-05 | +| loss | -0.0323 | +| n_updates | 76128 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000111 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.13e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1402 | +| iterations | 15079 | +| time_elapsed | 22022 | +| total_timesteps | 30881792 | +| train/ | | +| approx_kl | 0.01314416 | +| clip_fraction | 0.323 | +| clip_range | 0.0673 | +| entropy_loss | -5.96 | +| explained_variance | 0.572 | +| learning_rate | 4.27e-05 | +| loss | -0.0289 | +| n_updates | 76132 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000137 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.14e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1402 | +| iterations | 15080 | +| time_elapsed | 22023 | +| total_timesteps | 30883840 | +| train/ | | +| approx_kl | 0.013116183 | +| clip_fraction | 0.366 | +| clip_range | 0.0673 | +| entropy_loss | -6.4 | +| explained_variance | 0.278 | +| learning_rate | 4.27e-05 | +| loss | -0.0293 | +| n_updates | 76136 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.00023 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.14e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1402 | +| iterations | 15081 | +| time_elapsed | 22025 | +| total_timesteps | 30885888 | +| train/ | | +| approx_kl | 0.015512047 | +| clip_fraction | 0.365 | +| clip_range | 0.0673 | +| entropy_loss | -6.27 | +| explained_variance | 0.529 | +| learning_rate | 4.27e-05 | +| loss | -0.0376 | +| n_updates | 76140 | +| policy_gradient_loss | -0.0235 | +| value_loss | 5.74e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.14e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1402 | +| iterations | 15082 | +| time_elapsed | 22026 | +| total_timesteps | 30887936 | +| train/ | | +| approx_kl | 0.011486469 | +| clip_fraction | 0.321 | +| clip_range | 0.0673 | +| entropy_loss | -6.71 | +| explained_variance | 0.334 | +| learning_rate | 4.27e-05 | +| loss | -0.0253 | +| n_updates | 76144 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000215 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1402 | +| iterations | 15083 | +| time_elapsed | 22028 | +| total_timesteps | 30889984 | +| train/ | | +| approx_kl | 0.012196368 | +| clip_fraction | 0.327 | +| clip_range | 0.0673 | +| entropy_loss | -6.43 | +| explained_variance | 0.61 | +| learning_rate | 4.27e-05 | +| loss | -0.0268 | +| n_updates | 76148 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000142 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1402 | +| iterations | 15084 | +| time_elapsed | 22029 | +| total_timesteps | 30892032 | +| train/ | | +| approx_kl | 0.016342495 | +| clip_fraction | 0.298 | +| clip_range | 0.0673 | +| entropy_loss | -6.13 | +| explained_variance | 0.4 | +| learning_rate | 4.27e-05 | +| loss | -0.0298 | +| n_updates | 76152 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000251 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.14e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1402 | +| iterations | 15085 | +| time_elapsed | 22031 | +| total_timesteps | 30894080 | +| train/ | | +| approx_kl | 0.01225514 | +| clip_fraction | 0.335 | +| clip_range | 0.0673 | +| entropy_loss | -6.75 | +| explained_variance | -0.166 | +| learning_rate | 4.27e-05 | +| loss | -0.0331 | +| n_updates | 76156 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000158 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.14e+03 | +| ep_rew_mean | 0.315 | +| time/ | | +| fps | 1402 | +| iterations | 15086 | +| time_elapsed | 22033 | +| total_timesteps | 30896128 | +| train/ | | +| approx_kl | 0.017556898 | +| clip_fraction | 0.405 | +| clip_range | 0.0673 | +| entropy_loss | -6.48 | +| explained_variance | 0.38 | +| learning_rate | 4.27e-05 | +| loss | -0.0369 | +| n_updates | 76160 | +| policy_gradient_loss | -0.0242 | +| value_loss | 6.74e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1402 | +| iterations | 15087 | +| time_elapsed | 22034 | +| total_timesteps | 30898176 | +| train/ | | +| approx_kl | 0.015537585 | +| clip_fraction | 0.34 | +| clip_range | 0.0673 | +| entropy_loss | -6.37 | +| explained_variance | 0.62 | +| learning_rate | 4.27e-05 | +| loss | -0.0326 | +| n_updates | 76164 | +| policy_gradient_loss | -0.0175 | +| value_loss | 8.83e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1402 | +| iterations | 15088 | +| time_elapsed | 22036 | +| total_timesteps | 30900224 | +| train/ | | +| approx_kl | 0.012613907 | +| clip_fraction | 0.347 | +| clip_range | 0.0673 | +| entropy_loss | -6.21 | +| explained_variance | 0.579 | +| learning_rate | 4.27e-05 | +| loss | -0.0259 | +| n_updates | 76168 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000123 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.14e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1402 | +| iterations | 15089 | +| time_elapsed | 22037 | +| total_timesteps | 30902272 | +| train/ | | +| approx_kl | 0.011561897 | +| clip_fraction | 0.31 | +| clip_range | 0.0673 | +| entropy_loss | -5.88 | +| explained_variance | 0.397 | +| learning_rate | 4.27e-05 | +| loss | -0.0239 | +| n_updates | 76172 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000315 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.14e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1402 | +| iterations | 15090 | +| time_elapsed | 22039 | +| total_timesteps | 30904320 | +| train/ | | +| approx_kl | 0.012383696 | +| clip_fraction | 0.333 | +| clip_range | 0.0673 | +| entropy_loss | -6.27 | +| explained_variance | 0.0784 | +| learning_rate | 4.27e-05 | +| loss | -0.0349 | +| n_updates | 76176 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000261 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.14e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1402 | +| iterations | 15091 | +| time_elapsed | 22040 | +| total_timesteps | 30906368 | +| train/ | | +| approx_kl | 0.012794754 | +| clip_fraction | 0.332 | +| clip_range | 0.0673 | +| entropy_loss | -5.86 | +| explained_variance | 0.353 | +| learning_rate | 4.27e-05 | +| loss | -0.0349 | +| n_updates | 76180 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000336 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1402 | +| iterations | 15092 | +| time_elapsed | 22042 | +| total_timesteps | 30908416 | +| train/ | | +| approx_kl | 0.013020149 | +| clip_fraction | 0.366 | +| clip_range | 0.0673 | +| entropy_loss | -5.99 | +| explained_variance | 0.47 | +| learning_rate | 4.27e-05 | +| loss | -0.0374 | +| n_updates | 76184 | +| policy_gradient_loss | -0.0222 | +| value_loss | 0.000129 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 1402 | +| iterations | 15093 | +| time_elapsed | 22043 | +| total_timesteps | 30910464 | +| train/ | | +| approx_kl | 0.016071765 | +| clip_fraction | 0.259 | +| clip_range | 0.0673 | +| entropy_loss | -6.37 | +| explained_variance | 0.382 | +| learning_rate | 4.27e-05 | +| loss | -0.0293 | +| n_updates | 76188 | +| policy_gradient_loss | -0.0134 | +| value_loss | 0.00032 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 1402 | +| iterations | 15094 | +| time_elapsed | 22045 | +| total_timesteps | 30912512 | +| train/ | | +| approx_kl | 0.016114825 | +| clip_fraction | 0.366 | +| clip_range | 0.0673 | +| entropy_loss | -5.91 | +| explained_variance | 0.484 | +| learning_rate | 4.27e-05 | +| loss | -0.0313 | +| n_updates | 76192 | +| policy_gradient_loss | -0.022 | +| value_loss | 9.81e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 1402 | +| iterations | 15095 | +| time_elapsed | 22046 | +| total_timesteps | 30914560 | +| train/ | | +| approx_kl | 0.014212592 | +| clip_fraction | 0.324 | +| clip_range | 0.0673 | +| entropy_loss | -6.56 | +| explained_variance | 0.0988 | +| learning_rate | 4.27e-05 | +| loss | -0.029 | +| n_updates | 76196 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000223 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1402 | +| iterations | 15096 | +| time_elapsed | 22048 | +| total_timesteps | 30916608 | +| train/ | | +| approx_kl | 0.012172208 | +| clip_fraction | 0.325 | +| clip_range | 0.0673 | +| entropy_loss | -7.06 | +| explained_variance | 0.028 | +| learning_rate | 4.27e-05 | +| loss | -0.0332 | +| n_updates | 76200 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000104 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1402 | +| iterations | 15097 | +| time_elapsed | 22049 | +| total_timesteps | 30918656 | +| train/ | | +| approx_kl | 0.014091799 | +| clip_fraction | 0.338 | +| clip_range | 0.0673 | +| entropy_loss | -6.63 | +| explained_variance | 0.218 | +| learning_rate | 4.27e-05 | +| loss | -0.0294 | +| n_updates | 76204 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000134 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1402 | +| iterations | 15098 | +| time_elapsed | 22051 | +| total_timesteps | 30920704 | +| train/ | | +| approx_kl | 0.013459682 | +| clip_fraction | 0.348 | +| clip_range | 0.0673 | +| entropy_loss | -6.84 | +| explained_variance | 0.0582 | +| learning_rate | 4.27e-05 | +| loss | -0.0313 | +| n_updates | 76208 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.0001 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1402 | +| iterations | 15099 | +| time_elapsed | 22053 | +| total_timesteps | 30922752 | +| train/ | | +| approx_kl | 0.012270458 | +| clip_fraction | 0.328 | +| clip_range | 0.0673 | +| entropy_loss | -6.38 | +| explained_variance | 0.434 | +| learning_rate | 4.27e-05 | +| loss | -0.0325 | +| n_updates | 76212 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000197 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1402 | +| iterations | 15100 | +| time_elapsed | 22054 | +| total_timesteps | 30924800 | +| train/ | | +| approx_kl | 0.013463857 | +| clip_fraction | 0.326 | +| clip_range | 0.0673 | +| entropy_loss | -6.41 | +| explained_variance | 0.318 | +| learning_rate | 4.27e-05 | +| loss | -0.0257 | +| n_updates | 76216 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000247 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1402 | +| iterations | 15101 | +| time_elapsed | 22056 | +| total_timesteps | 30926848 | +| train/ | | +| approx_kl | 0.0140178185 | +| clip_fraction | 0.309 | +| clip_range | 0.0673 | +| entropy_loss | -5.8 | +| explained_variance | 0.5 | +| learning_rate | 4.27e-05 | +| loss | -0.0286 | +| n_updates | 76220 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.00032 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1402 | +| iterations | 15102 | +| time_elapsed | 22057 | +| total_timesteps | 30928896 | +| train/ | | +| approx_kl | 0.012340572 | +| clip_fraction | 0.335 | +| clip_range | 0.0673 | +| entropy_loss | -6.22 | +| explained_variance | 0.398 | +| learning_rate | 4.27e-05 | +| loss | -0.0278 | +| n_updates | 76224 | +| policy_gradient_loss | -0.019 | +| value_loss | 9.75e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1402 | +| iterations | 15103 | +| time_elapsed | 22059 | +| total_timesteps | 30930944 | +| train/ | | +| approx_kl | 0.010300601 | +| clip_fraction | 0.353 | +| clip_range | 0.0673 | +| entropy_loss | -6.24 | +| explained_variance | 0.488 | +| learning_rate | 4.27e-05 | +| loss | -0.0289 | +| n_updates | 76228 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000178 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1402 | +| iterations | 15104 | +| time_elapsed | 22060 | +| total_timesteps | 30932992 | +| train/ | | +| approx_kl | 0.013015296 | +| clip_fraction | 0.339 | +| clip_range | 0.0673 | +| entropy_loss | -6.2 | +| explained_variance | 0.408 | +| learning_rate | 4.27e-05 | +| loss | -0.0313 | +| n_updates | 76232 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000121 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1402 | +| iterations | 15105 | +| time_elapsed | 22062 | +| total_timesteps | 30935040 | +| train/ | | +| approx_kl | 0.010116553 | +| clip_fraction | 0.316 | +| clip_range | 0.0673 | +| entropy_loss | -6.73 | +| explained_variance | 0.482 | +| learning_rate | 4.27e-05 | +| loss | -0.0311 | +| n_updates | 76236 | +| policy_gradient_loss | -0.0196 | +| value_loss | 9.89e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1402 | +| iterations | 15106 | +| time_elapsed | 22063 | +| total_timesteps | 30937088 | +| train/ | | +| approx_kl | 0.009619118 | +| clip_fraction | 0.333 | +| clip_range | 0.0673 | +| entropy_loss | -6.44 | +| explained_variance | 0.416 | +| learning_rate | 4.27e-05 | +| loss | -0.0286 | +| n_updates | 76240 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000171 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1402 | +| iterations | 15107 | +| time_elapsed | 22065 | +| total_timesteps | 30939136 | +| train/ | | +| approx_kl | 0.010602317 | +| clip_fraction | 0.31 | +| clip_range | 0.0673 | +| entropy_loss | -6.35 | +| explained_variance | 0.433 | +| learning_rate | 4.27e-05 | +| loss | -0.0318 | +| n_updates | 76244 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1402 | +| iterations | 15108 | +| time_elapsed | 22066 | +| total_timesteps | 30941184 | +| train/ | | +| approx_kl | 0.010661507 | +| clip_fraction | 0.319 | +| clip_range | 0.0673 | +| entropy_loss | -6.37 | +| explained_variance | 0.442 | +| learning_rate | 4.27e-05 | +| loss | -0.0283 | +| n_updates | 76248 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000178 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1402 | +| iterations | 15109 | +| time_elapsed | 22068 | +| total_timesteps | 30943232 | +| train/ | | +| approx_kl | 0.012442545 | +| clip_fraction | 0.307 | +| clip_range | 0.0673 | +| entropy_loss | -6.05 | +| explained_variance | 0.599 | +| learning_rate | 4.27e-05 | +| loss | -0.0268 | +| n_updates | 76252 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000147 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1402 | +| iterations | 15110 | +| time_elapsed | 22069 | +| total_timesteps | 30945280 | +| train/ | | +| approx_kl | 0.0093412325 | +| clip_fraction | 0.302 | +| clip_range | 0.0673 | +| entropy_loss | -6.56 | +| explained_variance | 0.292 | +| learning_rate | 4.27e-05 | +| loss | -0.0234 | +| n_updates | 76256 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000179 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1402 | +| iterations | 15111 | +| time_elapsed | 22071 | +| total_timesteps | 30947328 | +| train/ | | +| approx_kl | 0.009647656 | +| clip_fraction | 0.299 | +| clip_range | 0.0673 | +| entropy_loss | -6.52 | +| explained_variance | 0.343 | +| learning_rate | 4.27e-05 | +| loss | -0.0266 | +| n_updates | 76260 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000145 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1402 | +| iterations | 15112 | +| time_elapsed | 22072 | +| total_timesteps | 30949376 | +| train/ | | +| approx_kl | 0.014314953 | +| clip_fraction | 0.363 | +| clip_range | 0.0673 | +| entropy_loss | -6.67 | +| explained_variance | 0.563 | +| learning_rate | 4.27e-05 | +| loss | -0.0321 | +| n_updates | 76264 | +| policy_gradient_loss | -0.0209 | +| value_loss | 5.98e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1402 | +| iterations | 15113 | +| time_elapsed | 22074 | +| total_timesteps | 30951424 | +| train/ | | +| approx_kl | 0.020711176 | +| clip_fraction | 0.308 | +| clip_range | 0.0673 | +| entropy_loss | -6.42 | +| explained_variance | 0.28 | +| learning_rate | 4.26e-05 | +| loss | -0.0269 | +| n_updates | 76268 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000162 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1402 | +| iterations | 15114 | +| time_elapsed | 22076 | +| total_timesteps | 30953472 | +| train/ | | +| approx_kl | 0.015340488 | +| clip_fraction | 0.366 | +| clip_range | 0.0673 | +| entropy_loss | -6.74 | +| explained_variance | 0.471 | +| learning_rate | 4.26e-05 | +| loss | -0.0325 | +| n_updates | 76272 | +| policy_gradient_loss | -0.0214 | +| value_loss | 8.03e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1402 | +| iterations | 15115 | +| time_elapsed | 22077 | +| total_timesteps | 30955520 | +| train/ | | +| approx_kl | 0.013670879 | +| clip_fraction | 0.324 | +| clip_range | 0.0673 | +| entropy_loss | -5.57 | +| explained_variance | 0.614 | +| learning_rate | 4.26e-05 | +| loss | -0.0306 | +| n_updates | 76276 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.00019 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1402 | +| iterations | 15116 | +| time_elapsed | 22079 | +| total_timesteps | 30957568 | +| train/ | | +| approx_kl | 0.016122466 | +| clip_fraction | 0.324 | +| clip_range | 0.0673 | +| entropy_loss | -5.85 | +| explained_variance | 0.504 | +| learning_rate | 4.26e-05 | +| loss | -0.0257 | +| n_updates | 76280 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000153 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1402 | +| iterations | 15117 | +| time_elapsed | 22080 | +| total_timesteps | 30959616 | +| train/ | | +| approx_kl | 0.012258016 | +| clip_fraction | 0.322 | +| clip_range | 0.0673 | +| entropy_loss | -6.52 | +| explained_variance | 0.028 | +| learning_rate | 4.26e-05 | +| loss | -0.0284 | +| n_updates | 76284 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000259 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1402 | +| iterations | 15118 | +| time_elapsed | 22082 | +| total_timesteps | 30961664 | +| train/ | | +| approx_kl | 0.013897105 | +| clip_fraction | 0.325 | +| clip_range | 0.0673 | +| entropy_loss | -5.84 | +| explained_variance | 0.682 | +| learning_rate | 4.26e-05 | +| loss | -0.0249 | +| n_updates | 76288 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000125 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1402 | +| iterations | 15119 | +| time_elapsed | 22083 | +| total_timesteps | 30963712 | +| train/ | | +| approx_kl | 0.010945067 | +| clip_fraction | 0.316 | +| clip_range | 0.0673 | +| entropy_loss | -6.14 | +| explained_variance | 0.471 | +| learning_rate | 4.26e-05 | +| loss | -0.0236 | +| n_updates | 76292 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000174 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1402 | +| iterations | 15120 | +| time_elapsed | 22085 | +| total_timesteps | 30965760 | +| train/ | | +| approx_kl | 0.009058418 | +| clip_fraction | 0.273 | +| clip_range | 0.0673 | +| entropy_loss | -6.24 | +| explained_variance | 0.246 | +| learning_rate | 4.26e-05 | +| loss | -0.0225 | +| n_updates | 76296 | +| policy_gradient_loss | -0.0148 | +| value_loss | 0.000434 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1402 | +| iterations | 15121 | +| time_elapsed | 22086 | +| total_timesteps | 30967808 | +| train/ | | +| approx_kl | 0.009167708 | +| clip_fraction | 0.313 | +| clip_range | 0.0673 | +| entropy_loss | -6.31 | +| explained_variance | 0.462 | +| learning_rate | 4.26e-05 | +| loss | -0.0237 | +| n_updates | 76300 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000239 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1402 | +| iterations | 15122 | +| time_elapsed | 22088 | +| total_timesteps | 30969856 | +| train/ | | +| approx_kl | 0.011649179 | +| clip_fraction | 0.361 | +| clip_range | 0.0673 | +| entropy_loss | -6.75 | +| explained_variance | -0.0624 | +| learning_rate | 4.26e-05 | +| loss | -0.0386 | +| n_updates | 76304 | +| policy_gradient_loss | -0.0229 | +| value_loss | 9e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1402 | +| iterations | 15123 | +| time_elapsed | 22089 | +| total_timesteps | 30971904 | +| train/ | | +| approx_kl | 0.013351923 | +| clip_fraction | 0.351 | +| clip_range | 0.0673 | +| entropy_loss | -6.37 | +| explained_variance | 0.55 | +| learning_rate | 4.26e-05 | +| loss | -0.0336 | +| n_updates | 76308 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000104 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1402 | +| iterations | 15124 | +| time_elapsed | 22091 | +| total_timesteps | 30973952 | +| train/ | | +| approx_kl | 0.015467968 | +| clip_fraction | 0.347 | +| clip_range | 0.0673 | +| entropy_loss | -6.31 | +| explained_variance | 0.416 | +| learning_rate | 4.26e-05 | +| loss | -0.0297 | +| n_updates | 76312 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000106 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1402 | +| iterations | 15125 | +| time_elapsed | 22093 | +| total_timesteps | 30976000 | +| train/ | | +| approx_kl | 0.0140170185 | +| clip_fraction | 0.318 | +| clip_range | 0.0673 | +| entropy_loss | -5.74 | +| explained_variance | 0.603 | +| learning_rate | 4.26e-05 | +| loss | -0.0289 | +| n_updates | 76316 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000154 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1402 | +| iterations | 15126 | +| time_elapsed | 22094 | +| total_timesteps | 30978048 | +| train/ | | +| approx_kl | 0.012907341 | +| clip_fraction | 0.363 | +| clip_range | 0.0673 | +| entropy_loss | -6.69 | +| explained_variance | -0.0414 | +| learning_rate | 4.26e-05 | +| loss | -0.0316 | +| n_updates | 76320 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000108 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1402 | +| iterations | 15127 | +| time_elapsed | 22096 | +| total_timesteps | 30980096 | +| train/ | | +| approx_kl | 0.013707393 | +| clip_fraction | 0.357 | +| clip_range | 0.0673 | +| entropy_loss | -6.12 | +| explained_variance | 0.625 | +| learning_rate | 4.26e-05 | +| loss | -0.0308 | +| n_updates | 76324 | +| policy_gradient_loss | -0.0195 | +| value_loss | 9.58e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1402 | +| iterations | 15128 | +| time_elapsed | 22097 | +| total_timesteps | 30982144 | +| train/ | | +| approx_kl | 0.01166857 | +| clip_fraction | 0.309 | +| clip_range | 0.0673 | +| entropy_loss | -5.82 | +| explained_variance | 0.579 | +| learning_rate | 4.26e-05 | +| loss | -0.0252 | +| n_updates | 76328 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000138 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1402 | +| iterations | 15129 | +| time_elapsed | 22099 | +| total_timesteps | 30984192 | +| train/ | | +| approx_kl | 0.015216986 | +| clip_fraction | 0.361 | +| clip_range | 0.0673 | +| entropy_loss | -6.47 | +| explained_variance | -0.054 | +| learning_rate | 4.26e-05 | +| loss | -0.0297 | +| n_updates | 76332 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000145 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1402 | +| iterations | 15130 | +| time_elapsed | 22100 | +| total_timesteps | 30986240 | +| train/ | | +| approx_kl | 0.016562201 | +| clip_fraction | 0.362 | +| clip_range | 0.0673 | +| entropy_loss | -6.14 | +| explained_variance | 0.669 | +| learning_rate | 4.26e-05 | +| loss | -0.0344 | +| n_updates | 76336 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000103 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1402 | +| iterations | 15131 | +| time_elapsed | 22102 | +| total_timesteps | 30988288 | +| train/ | | +| approx_kl | 0.014485446 | +| clip_fraction | 0.32 | +| clip_range | 0.0673 | +| entropy_loss | -6.49 | +| explained_variance | -0.0268 | +| learning_rate | 4.26e-05 | +| loss | -0.0302 | +| n_updates | 76340 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000137 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1402 | +| iterations | 15132 | +| time_elapsed | 22103 | +| total_timesteps | 30990336 | +| train/ | | +| approx_kl | 0.0109350635 | +| clip_fraction | 0.311 | +| clip_range | 0.0673 | +| entropy_loss | -6.96 | +| explained_variance | 0.0714 | +| learning_rate | 4.26e-05 | +| loss | -0.0231 | +| n_updates | 76344 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000117 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1402 | +| iterations | 15133 | +| time_elapsed | 22105 | +| total_timesteps | 30992384 | +| train/ | | +| approx_kl | 0.0134815695 | +| clip_fraction | 0.317 | +| clip_range | 0.0673 | +| entropy_loss | -6.68 | +| explained_variance | 0.284 | +| learning_rate | 4.26e-05 | +| loss | -0.0197 | +| n_updates | 76348 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000138 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1402 | +| iterations | 15134 | +| time_elapsed | 22106 | +| total_timesteps | 30994432 | +| train/ | | +| approx_kl | 0.010918717 | +| clip_fraction | 0.322 | +| clip_range | 0.0673 | +| entropy_loss | -6.73 | +| explained_variance | -0.0844 | +| learning_rate | 4.26e-05 | +| loss | -0.0231 | +| n_updates | 76352 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000237 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1402 | +| iterations | 15135 | +| time_elapsed | 22108 | +| total_timesteps | 30996480 | +| train/ | | +| approx_kl | 0.011430094 | +| clip_fraction | 0.337 | +| clip_range | 0.0673 | +| entropy_loss | -6.34 | +| explained_variance | 0.557 | +| learning_rate | 4.26e-05 | +| loss | -0.0263 | +| n_updates | 76356 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000132 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1402 | +| iterations | 15136 | +| time_elapsed | 22109 | +| total_timesteps | 30998528 | +| train/ | | +| approx_kl | 0.011814932 | +| clip_fraction | 0.303 | +| clip_range | 0.0673 | +| entropy_loss | -5.9 | +| explained_variance | 0.696 | +| learning_rate | 4.26e-05 | +| loss | -0.0298 | +| n_updates | 76360 | +| policy_gradient_loss | -0.0169 | +| value_loss | 9.5e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1402 | +| iterations | 15137 | +| time_elapsed | 22111 | +| total_timesteps | 31000576 | +| train/ | | +| approx_kl | 0.01060485 | +| clip_fraction | 0.335 | +| clip_range | 0.0673 | +| entropy_loss | -5.87 | +| explained_variance | 0.535 | +| learning_rate | 4.26e-05 | +| loss | -0.0246 | +| n_updates | 76364 | +| policy_gradient_loss | -0.0179 | +| value_loss | 8.66e-05 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1402 | +| iterations | 15138 | +| time_elapsed | 22112 | +| total_timesteps | 31002624 | +| train/ | | +| approx_kl | 0.01302464 | +| clip_fraction | 0.344 | +| clip_range | 0.0672 | +| entropy_loss | -5.73 | +| explained_variance | 0.56 | +| learning_rate | 4.26e-05 | +| loss | -0.0292 | +| n_updates | 76368 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.00021 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1402 | +| iterations | 15139 | +| time_elapsed | 22114 | +| total_timesteps | 31004672 | +| train/ | | +| approx_kl | 0.014872126 | +| clip_fraction | 0.34 | +| clip_range | 0.0672 | +| entropy_loss | -6.29 | +| explained_variance | 0.4 | +| learning_rate | 4.26e-05 | +| loss | -0.0314 | +| n_updates | 76372 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000107 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1402 | +| iterations | 15140 | +| time_elapsed | 22116 | +| total_timesteps | 31006720 | +| train/ | | +| approx_kl | 0.014242337 | +| clip_fraction | 0.372 | +| clip_range | 0.0672 | +| entropy_loss | -6.92 | +| explained_variance | 0.388 | +| learning_rate | 4.26e-05 | +| loss | -0.0381 | +| n_updates | 76376 | +| policy_gradient_loss | -0.0225 | +| value_loss | 5.55e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1401 | +| iterations | 15141 | +| time_elapsed | 22117 | +| total_timesteps | 31008768 | +| train/ | | +| approx_kl | 0.011700703 | +| clip_fraction | 0.322 | +| clip_range | 0.0672 | +| entropy_loss | -6.28 | +| explained_variance | 0.607 | +| learning_rate | 4.26e-05 | +| loss | -0.0241 | +| n_updates | 76380 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000123 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1401 | +| iterations | 15142 | +| time_elapsed | 22119 | +| total_timesteps | 31010816 | +| train/ | | +| approx_kl | 0.019442663 | +| clip_fraction | 0.318 | +| clip_range | 0.0672 | +| entropy_loss | -6.45 | +| explained_variance | 0.25 | +| learning_rate | 4.26e-05 | +| loss | -0.0303 | +| n_updates | 76384 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000175 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1401 | +| iterations | 15143 | +| time_elapsed | 22120 | +| total_timesteps | 31012864 | +| train/ | | +| approx_kl | 0.014127247 | +| clip_fraction | 0.352 | +| clip_range | 0.0672 | +| entropy_loss | -6.57 | +| explained_variance | -0.0411 | +| learning_rate | 4.26e-05 | +| loss | -0.0336 | +| n_updates | 76388 | +| policy_gradient_loss | -0.0203 | +| value_loss | 6.9e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1401 | +| iterations | 15144 | +| time_elapsed | 22122 | +| total_timesteps | 31014912 | +| train/ | | +| approx_kl | 0.011854985 | +| clip_fraction | 0.354 | +| clip_range | 0.0672 | +| entropy_loss | -6.84 | +| explained_variance | 0.108 | +| learning_rate | 4.26e-05 | +| loss | -0.0292 | +| n_updates | 76392 | +| policy_gradient_loss | -0.0201 | +| value_loss | 8.36e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1401 | +| iterations | 15145 | +| time_elapsed | 22123 | +| total_timesteps | 31016960 | +| train/ | | +| approx_kl | 0.0129916705 | +| clip_fraction | 0.309 | +| clip_range | 0.0672 | +| entropy_loss | -6.49 | +| explained_variance | 0.56 | +| learning_rate | 4.26e-05 | +| loss | -0.0231 | +| n_updates | 76396 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000125 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1401 | +| iterations | 15146 | +| time_elapsed | 22125 | +| total_timesteps | 31019008 | +| train/ | | +| approx_kl | 0.012303045 | +| clip_fraction | 0.311 | +| clip_range | 0.0672 | +| entropy_loss | -6.79 | +| explained_variance | -0.0276 | +| learning_rate | 4.26e-05 | +| loss | -0.0256 | +| n_updates | 76400 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000105 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1401 | +| iterations | 15147 | +| time_elapsed | 22126 | +| total_timesteps | 31021056 | +| train/ | | +| approx_kl | 0.0140173435 | +| clip_fraction | 0.325 | +| clip_range | 0.0672 | +| entropy_loss | -6.37 | +| explained_variance | 0.454 | +| learning_rate | 4.26e-05 | +| loss | -0.0276 | +| n_updates | 76404 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000169 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1401 | +| iterations | 15148 | +| time_elapsed | 22128 | +| total_timesteps | 31023104 | +| train/ | | +| approx_kl | 0.014499916 | +| clip_fraction | 0.361 | +| clip_range | 0.0672 | +| entropy_loss | -6.08 | +| explained_variance | 0.778 | +| learning_rate | 4.26e-05 | +| loss | -0.0327 | +| n_updates | 76408 | +| policy_gradient_loss | -0.0204 | +| value_loss | 4.49e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1401 | +| iterations | 15149 | +| time_elapsed | 22129 | +| total_timesteps | 31025152 | +| train/ | | +| approx_kl | 0.010852655 | +| clip_fraction | 0.308 | +| clip_range | 0.0672 | +| entropy_loss | -6.1 | +| explained_variance | 0.406 | +| learning_rate | 4.26e-05 | +| loss | -0.0229 | +| n_updates | 76412 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000131 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1401 | +| iterations | 15150 | +| time_elapsed | 22131 | +| total_timesteps | 31027200 | +| train/ | | +| approx_kl | 0.011828506 | +| clip_fraction | 0.31 | +| clip_range | 0.0672 | +| entropy_loss | -5.82 | +| explained_variance | 0.646 | +| learning_rate | 4.26e-05 | +| loss | -0.0293 | +| n_updates | 76416 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000114 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1401 | +| iterations | 15151 | +| time_elapsed | 22132 | +| total_timesteps | 31029248 | +| train/ | | +| approx_kl | 0.01388933 | +| clip_fraction | 0.314 | +| clip_range | 0.0672 | +| entropy_loss | -5.84 | +| explained_variance | 0.37 | +| learning_rate | 4.26e-05 | +| loss | -0.0258 | +| n_updates | 76420 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000195 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1401 | +| iterations | 15152 | +| time_elapsed | 22134 | +| total_timesteps | 31031296 | +| train/ | | +| approx_kl | 0.014360976 | +| clip_fraction | 0.343 | +| clip_range | 0.0672 | +| entropy_loss | -6.13 | +| explained_variance | 0.3 | +| learning_rate | 4.26e-05 | +| loss | -0.0337 | +| n_updates | 76424 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000149 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1401 | +| iterations | 15153 | +| time_elapsed | 22135 | +| total_timesteps | 31033344 | +| train/ | | +| approx_kl | 0.01741042 | +| clip_fraction | 0.346 | +| clip_range | 0.0672 | +| entropy_loss | -6.53 | +| explained_variance | 0.417 | +| learning_rate | 4.26e-05 | +| loss | -0.0353 | +| n_updates | 76428 | +| policy_gradient_loss | -0.0202 | +| value_loss | 7.73e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1401 | +| iterations | 15154 | +| time_elapsed | 22137 | +| total_timesteps | 31035392 | +| train/ | | +| approx_kl | 0.012012545 | +| clip_fraction | 0.334 | +| clip_range | 0.0672 | +| entropy_loss | -6.2 | +| explained_variance | 0.425 | +| learning_rate | 4.26e-05 | +| loss | -0.0325 | +| n_updates | 76432 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000277 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1401 | +| iterations | 15155 | +| time_elapsed | 22138 | +| total_timesteps | 31037440 | +| train/ | | +| approx_kl | 0.013293449 | +| clip_fraction | 0.348 | +| clip_range | 0.0672 | +| entropy_loss | -5.99 | +| explained_variance | 0.424 | +| learning_rate | 4.26e-05 | +| loss | -0.0322 | +| n_updates | 76436 | +| policy_gradient_loss | -0.0222 | +| value_loss | 8.58e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1401 | +| iterations | 15156 | +| time_elapsed | 22140 | +| total_timesteps | 31039488 | +| train/ | | +| approx_kl | 0.013797846 | +| clip_fraction | 0.353 | +| clip_range | 0.0672 | +| entropy_loss | -6.45 | +| explained_variance | 0.023 | +| learning_rate | 4.26e-05 | +| loss | -0.0371 | +| n_updates | 76440 | +| policy_gradient_loss | -0.0233 | +| value_loss | 5.95e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1401 | +| iterations | 15157 | +| time_elapsed | 22141 | +| total_timesteps | 31041536 | +| train/ | | +| approx_kl | 0.015402048 | +| clip_fraction | 0.344 | +| clip_range | 0.0672 | +| entropy_loss | -5.95 | +| explained_variance | 0.85 | +| learning_rate | 4.26e-05 | +| loss | -0.0332 | +| n_updates | 76444 | +| policy_gradient_loss | -0.0211 | +| value_loss | 3.98e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1401 | +| iterations | 15158 | +| time_elapsed | 22143 | +| total_timesteps | 31043584 | +| train/ | | +| approx_kl | 0.015848298 | +| clip_fraction | 0.354 | +| clip_range | 0.0672 | +| entropy_loss | -6.49 | +| explained_variance | -0.0994 | +| learning_rate | 4.26e-05 | +| loss | -0.034 | +| n_updates | 76448 | +| policy_gradient_loss | -0.0205 | +| value_loss | 5.98e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1401 | +| iterations | 15159 | +| time_elapsed | 22144 | +| total_timesteps | 31045632 | +| train/ | | +| approx_kl | 0.01058149 | +| clip_fraction | 0.311 | +| clip_range | 0.0672 | +| entropy_loss | -6.69 | +| explained_variance | 0.317 | +| learning_rate | 4.26e-05 | +| loss | -0.03 | +| n_updates | 76452 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.00014 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1401 | +| iterations | 15160 | +| time_elapsed | 22146 | +| total_timesteps | 31047680 | +| train/ | | +| approx_kl | 0.014003811 | +| clip_fraction | 0.32 | +| clip_range | 0.0672 | +| entropy_loss | -6.74 | +| explained_variance | -0.0739 | +| learning_rate | 4.26e-05 | +| loss | -0.0261 | +| n_updates | 76456 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.00011 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1401 | +| iterations | 15161 | +| time_elapsed | 22147 | +| total_timesteps | 31049728 | +| train/ | | +| approx_kl | 0.012862764 | +| clip_fraction | 0.346 | +| clip_range | 0.0672 | +| entropy_loss | -6.54 | +| explained_variance | -0.0837 | +| learning_rate | 4.26e-05 | +| loss | -0.0291 | +| n_updates | 76460 | +| policy_gradient_loss | -0.0192 | +| value_loss | 9.11e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1401 | +| iterations | 15162 | +| time_elapsed | 22149 | +| total_timesteps | 31051776 | +| train/ | | +| approx_kl | 0.009838594 | +| clip_fraction | 0.287 | +| clip_range | 0.0672 | +| entropy_loss | -6.02 | +| explained_variance | 0.608 | +| learning_rate | 4.26e-05 | +| loss | -0.0271 | +| n_updates | 76464 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 1401 | +| iterations | 15163 | +| time_elapsed | 22151 | +| total_timesteps | 31053824 | +| train/ | | +| approx_kl | 0.009659929 | +| clip_fraction | 0.295 | +| clip_range | 0.0672 | +| entropy_loss | -5.05 | +| explained_variance | 0.82 | +| learning_rate | 4.26e-05 | +| loss | -0.0283 | +| n_updates | 76468 | +| policy_gradient_loss | -0.0155 | +| value_loss | 8.13e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.306 | +| time/ | | +| fps | 1401 | +| iterations | 15164 | +| time_elapsed | 22152 | +| total_timesteps | 31055872 | +| train/ | | +| approx_kl | 0.01237038 | +| clip_fraction | 0.282 | +| clip_range | 0.0672 | +| entropy_loss | -6 | +| explained_variance | 0.43 | +| learning_rate | 4.26e-05 | +| loss | -0.0193 | +| n_updates | 76472 | +| policy_gradient_loss | -0.0129 | +| value_loss | 0.000185 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.306 | +| time/ | | +| fps | 1401 | +| iterations | 15165 | +| time_elapsed | 22154 | +| total_timesteps | 31057920 | +| train/ | | +| approx_kl | 0.009918664 | +| clip_fraction | 0.32 | +| clip_range | 0.0672 | +| entropy_loss | -6.08 | +| explained_variance | 0.47 | +| learning_rate | 4.26e-05 | +| loss | -0.0272 | +| n_updates | 76476 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000181 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.304 | +| time/ | | +| fps | 1401 | +| iterations | 15166 | +| time_elapsed | 22155 | +| total_timesteps | 31059968 | +| train/ | | +| approx_kl | 0.009858523 | +| clip_fraction | 0.302 | +| clip_range | 0.0672 | +| entropy_loss | -6.68 | +| explained_variance | 0.423 | +| learning_rate | 4.26e-05 | +| loss | -0.0293 | +| n_updates | 76480 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000143 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.304 | +| time/ | | +| fps | 1401 | +| iterations | 15167 | +| time_elapsed | 22157 | +| total_timesteps | 31062016 | +| train/ | | +| approx_kl | 0.012661852 | +| clip_fraction | 0.338 | +| clip_range | 0.0672 | +| entropy_loss | -6.75 | +| explained_variance | -0.135 | +| learning_rate | 4.26e-05 | +| loss | -0.0304 | +| n_updates | 76484 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000123 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.304 | +| time/ | | +| fps | 1401 | +| iterations | 15168 | +| time_elapsed | 22158 | +| total_timesteps | 31064064 | +| train/ | | +| approx_kl | 0.014708919 | +| clip_fraction | 0.344 | +| clip_range | 0.0672 | +| entropy_loss | -6.14 | +| explained_variance | 0.318 | +| learning_rate | 4.26e-05 | +| loss | -0.027 | +| n_updates | 76488 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000268 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 1401 | +| iterations | 15169 | +| time_elapsed | 22160 | +| total_timesteps | 31066112 | +| train/ | | +| approx_kl | 0.012922818 | +| clip_fraction | 0.349 | +| clip_range | 0.0672 | +| entropy_loss | -6.11 | +| explained_variance | 0.453 | +| learning_rate | 4.26e-05 | +| loss | -0.0305 | +| n_updates | 76492 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000143 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.298 | +| time/ | | +| fps | 1401 | +| iterations | 15170 | +| time_elapsed | 22161 | +| total_timesteps | 31068160 | +| train/ | | +| approx_kl | 0.012386663 | +| clip_fraction | 0.349 | +| clip_range | 0.0672 | +| entropy_loss | -6.78 | +| explained_variance | -0.0343 | +| learning_rate | 4.26e-05 | +| loss | -0.0312 | +| n_updates | 76496 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000129 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.306 | +| time/ | | +| fps | 1401 | +| iterations | 15171 | +| time_elapsed | 22163 | +| total_timesteps | 31070208 | +| train/ | | +| approx_kl | 0.01037637 | +| clip_fraction | 0.299 | +| clip_range | 0.0672 | +| entropy_loss | -5.93 | +| explained_variance | 0.602 | +| learning_rate | 4.26e-05 | +| loss | -0.0233 | +| n_updates | 76500 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.000185 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 1401 | +| iterations | 15172 | +| time_elapsed | 22164 | +| total_timesteps | 31072256 | +| train/ | | +| approx_kl | 0.014394246 | +| clip_fraction | 0.31 | +| clip_range | 0.0672 | +| entropy_loss | -5.75 | +| explained_variance | 0.455 | +| learning_rate | 4.26e-05 | +| loss | -0.0248 | +| n_updates | 76504 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000269 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.304 | +| time/ | | +| fps | 1401 | +| iterations | 15173 | +| time_elapsed | 22166 | +| total_timesteps | 31074304 | +| train/ | | +| approx_kl | 0.011504457 | +| clip_fraction | 0.33 | +| clip_range | 0.0672 | +| entropy_loss | -5.78 | +| explained_variance | 0.455 | +| learning_rate | 4.26e-05 | +| loss | -0.0201 | +| n_updates | 76508 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.000267 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1401 | +| iterations | 15174 | +| time_elapsed | 22167 | +| total_timesteps | 31076352 | +| train/ | | +| approx_kl | 0.014581921 | +| clip_fraction | 0.353 | +| clip_range | 0.0672 | +| entropy_loss | -5.95 | +| explained_variance | 0.453 | +| learning_rate | 4.26e-05 | +| loss | -0.0322 | +| n_updates | 76512 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000141 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1401 | +| iterations | 15175 | +| time_elapsed | 22169 | +| total_timesteps | 31078400 | +| train/ | | +| approx_kl | 0.01377936 | +| clip_fraction | 0.313 | +| clip_range | 0.0672 | +| entropy_loss | -6.18 | +| explained_variance | 0.232 | +| learning_rate | 4.26e-05 | +| loss | -0.0264 | +| n_updates | 76516 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000266 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1401 | +| iterations | 15176 | +| time_elapsed | 22171 | +| total_timesteps | 31080448 | +| train/ | | +| approx_kl | 0.011173506 | +| clip_fraction | 0.346 | +| clip_range | 0.0672 | +| entropy_loss | -6.85 | +| explained_variance | -0.147 | +| learning_rate | 4.26e-05 | +| loss | -0.0291 | +| n_updates | 76520 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000166 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1401 | +| iterations | 15177 | +| time_elapsed | 22172 | +| total_timesteps | 31082496 | +| train/ | | +| approx_kl | 0.014999611 | +| clip_fraction | 0.36 | +| clip_range | 0.0672 | +| entropy_loss | -6.67 | +| explained_variance | 0.234 | +| learning_rate | 4.26e-05 | +| loss | -0.0334 | +| n_updates | 76524 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000182 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1401 | +| iterations | 15178 | +| time_elapsed | 22174 | +| total_timesteps | 31084544 | +| train/ | | +| approx_kl | 0.013494009 | +| clip_fraction | 0.342 | +| clip_range | 0.0672 | +| entropy_loss | -6.6 | +| explained_variance | -0.0913 | +| learning_rate | 4.26e-05 | +| loss | -0.0316 | +| n_updates | 76528 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000178 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1401 | +| iterations | 15179 | +| time_elapsed | 22175 | +| total_timesteps | 31086592 | +| train/ | | +| approx_kl | 0.010686735 | +| clip_fraction | 0.285 | +| clip_range | 0.0672 | +| entropy_loss | -6.52 | +| explained_variance | 0.424 | +| learning_rate | 4.26e-05 | +| loss | -0.0238 | +| n_updates | 76532 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000215 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1401 | +| iterations | 15180 | +| time_elapsed | 22177 | +| total_timesteps | 31088640 | +| train/ | | +| approx_kl | 0.016491652 | +| clip_fraction | 0.322 | +| clip_range | 0.0672 | +| entropy_loss | -6.02 | +| explained_variance | 0.272 | +| learning_rate | 4.26e-05 | +| loss | -0.0253 | +| n_updates | 76536 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.000279 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1401 | +| iterations | 15181 | +| time_elapsed | 22178 | +| total_timesteps | 31090688 | +| train/ | | +| approx_kl | 0.012725309 | +| clip_fraction | 0.349 | +| clip_range | 0.0672 | +| entropy_loss | -6.16 | +| explained_variance | 0.438 | +| learning_rate | 4.26e-05 | +| loss | -0.0326 | +| n_updates | 76540 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1401 | +| iterations | 15182 | +| time_elapsed | 22180 | +| total_timesteps | 31092736 | +| train/ | | +| approx_kl | 0.013068731 | +| clip_fraction | 0.336 | +| clip_range | 0.0672 | +| entropy_loss | -5.94 | +| explained_variance | 0.283 | +| learning_rate | 4.26e-05 | +| loss | -0.0247 | +| n_updates | 76544 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000348 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1401 | +| iterations | 15183 | +| time_elapsed | 22181 | +| total_timesteps | 31094784 | +| train/ | | +| approx_kl | 0.016714765 | +| clip_fraction | 0.367 | +| clip_range | 0.0672 | +| entropy_loss | -5.4 | +| explained_variance | 0.693 | +| learning_rate | 4.26e-05 | +| loss | -0.0297 | +| n_updates | 76548 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000128 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1401 | +| iterations | 15184 | +| time_elapsed | 22183 | +| total_timesteps | 31096832 | +| train/ | | +| approx_kl | 0.014678646 | +| clip_fraction | 0.371 | +| clip_range | 0.0672 | +| entropy_loss | -6.42 | +| explained_variance | -0.106 | +| learning_rate | 4.26e-05 | +| loss | -0.0316 | +| n_updates | 76552 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000221 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1401 | +| iterations | 15185 | +| time_elapsed | 22185 | +| total_timesteps | 31098880 | +| train/ | | +| approx_kl | 0.01462489 | +| clip_fraction | 0.352 | +| clip_range | 0.0672 | +| entropy_loss | -6.64 | +| explained_variance | 0.273 | +| learning_rate | 4.26e-05 | +| loss | -0.033 | +| n_updates | 76556 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000111 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1401 | +| iterations | 15186 | +| time_elapsed | 22186 | +| total_timesteps | 31100928 | +| train/ | | +| approx_kl | 0.014312087 | +| clip_fraction | 0.341 | +| clip_range | 0.0672 | +| entropy_loss | -5.9 | +| explained_variance | 0.566 | +| learning_rate | 4.26e-05 | +| loss | -0.0225 | +| n_updates | 76560 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000166 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1401 | +| iterations | 15187 | +| time_elapsed | 22188 | +| total_timesteps | 31102976 | +| train/ | | +| approx_kl | 0.016937582 | +| clip_fraction | 0.378 | +| clip_range | 0.0672 | +| entropy_loss | -6.11 | +| explained_variance | 0.383 | +| learning_rate | 4.26e-05 | +| loss | -0.0354 | +| n_updates | 76564 | +| policy_gradient_loss | -0.0219 | +| value_loss | 5.61e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1401 | +| iterations | 15188 | +| time_elapsed | 22189 | +| total_timesteps | 31105024 | +| train/ | | +| approx_kl | 0.012454807 | +| clip_fraction | 0.338 | +| clip_range | 0.0672 | +| entropy_loss | -6.58 | +| explained_variance | 0.224 | +| learning_rate | 4.26e-05 | +| loss | -0.0305 | +| n_updates | 76568 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000154 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.315 | +| time/ | | +| fps | 1401 | +| iterations | 15189 | +| time_elapsed | 22191 | +| total_timesteps | 31107072 | +| train/ | | +| approx_kl | 0.009799353 | +| clip_fraction | 0.301 | +| clip_range | 0.0672 | +| entropy_loss | -6.76 | +| explained_variance | -0.0477 | +| learning_rate | 4.26e-05 | +| loss | -0.0303 | +| n_updates | 76572 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000148 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1401 | +| iterations | 15190 | +| time_elapsed | 22192 | +| total_timesteps | 31109120 | +| train/ | | +| approx_kl | 0.01147411 | +| clip_fraction | 0.328 | +| clip_range | 0.0672 | +| entropy_loss | -6.58 | +| explained_variance | 0.259 | +| learning_rate | 4.26e-05 | +| loss | -0.0334 | +| n_updates | 76576 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.00022 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1401 | +| iterations | 15191 | +| time_elapsed | 22194 | +| total_timesteps | 31111168 | +| train/ | | +| approx_kl | 0.011852807 | +| clip_fraction | 0.323 | +| clip_range | 0.0672 | +| entropy_loss | -6.06 | +| explained_variance | 0.436 | +| learning_rate | 4.26e-05 | +| loss | -0.0283 | +| n_updates | 76580 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000255 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1401 | +| iterations | 15192 | +| time_elapsed | 22195 | +| total_timesteps | 31113216 | +| train/ | | +| approx_kl | 0.0124824755 | +| clip_fraction | 0.3 | +| clip_range | 0.0672 | +| entropy_loss | -5.68 | +| explained_variance | 0.439 | +| learning_rate | 4.26e-05 | +| loss | -0.0244 | +| n_updates | 76584 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.000264 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1401 | +| iterations | 15193 | +| time_elapsed | 22197 | +| total_timesteps | 31115264 | +| train/ | | +| approx_kl | 0.012673165 | +| clip_fraction | 0.35 | +| clip_range | 0.0672 | +| entropy_loss | -6 | +| explained_variance | 0.389 | +| learning_rate | 4.26e-05 | +| loss | -0.0335 | +| n_updates | 76588 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000167 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1401 | +| iterations | 15194 | +| time_elapsed | 22198 | +| total_timesteps | 31117312 | +| train/ | | +| approx_kl | 0.015602718 | +| clip_fraction | 0.365 | +| clip_range | 0.0672 | +| entropy_loss | -6.62 | +| explained_variance | 0.367 | +| learning_rate | 4.26e-05 | +| loss | -0.0348 | +| n_updates | 76592 | +| policy_gradient_loss | -0.0212 | +| value_loss | 9.71e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1401 | +| iterations | 15195 | +| time_elapsed | 22200 | +| total_timesteps | 31119360 | +| train/ | | +| approx_kl | 0.014584235 | +| clip_fraction | 0.343 | +| clip_range | 0.0672 | +| entropy_loss | -6.67 | +| explained_variance | 0.215 | +| learning_rate | 4.26e-05 | +| loss | -0.0299 | +| n_updates | 76596 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000235 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1401 | +| iterations | 15196 | +| time_elapsed | 22201 | +| total_timesteps | 31121408 | +| train/ | | +| approx_kl | 0.014516314 | +| clip_fraction | 0.36 | +| clip_range | 0.0672 | +| entropy_loss | -6.25 | +| explained_variance | 0.552 | +| learning_rate | 4.26e-05 | +| loss | -0.0278 | +| n_updates | 76600 | +| policy_gradient_loss | -0.0196 | +| value_loss | 9.76e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1401 | +| iterations | 15197 | +| time_elapsed | 22203 | +| total_timesteps | 31123456 | +| train/ | | +| approx_kl | 0.014736609 | +| clip_fraction | 0.322 | +| clip_range | 0.0672 | +| entropy_loss | -6.14 | +| explained_variance | 0.219 | +| learning_rate | 4.26e-05 | +| loss | -0.0281 | +| n_updates | 76604 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000281 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1401 | +| iterations | 15198 | +| time_elapsed | 22204 | +| total_timesteps | 31125504 | +| train/ | | +| approx_kl | 0.015900433 | +| clip_fraction | 0.333 | +| clip_range | 0.0672 | +| entropy_loss | -6.15 | +| explained_variance | 0.46 | +| learning_rate | 4.26e-05 | +| loss | -0.0332 | +| n_updates | 76608 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000121 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1401 | +| iterations | 15199 | +| time_elapsed | 22206 | +| total_timesteps | 31127552 | +| train/ | | +| approx_kl | 0.016513212 | +| clip_fraction | 0.36 | +| clip_range | 0.0672 | +| entropy_loss | -6.02 | +| explained_variance | 0.615 | +| learning_rate | 4.26e-05 | +| loss | -0.0304 | +| n_updates | 76612 | +| policy_gradient_loss | -0.0213 | +| value_loss | 8.4e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1401 | +| iterations | 15200 | +| time_elapsed | 22208 | +| total_timesteps | 31129600 | +| train/ | | +| approx_kl | 0.01827481 | +| clip_fraction | 0.344 | +| clip_range | 0.0672 | +| entropy_loss | -6.51 | +| explained_variance | 0.145 | +| learning_rate | 4.26e-05 | +| loss | -0.0298 | +| n_updates | 76616 | +| policy_gradient_loss | -0.0181 | +| value_loss | 9.98e-05 | +---------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1401 | +| iterations | 15201 | +| time_elapsed | 22209 | +| total_timesteps | 31131648 | +| train/ | | +| approx_kl | 0.0141297 | +| clip_fraction | 0.351 | +| clip_range | 0.0672 | +| entropy_loss | -5.92 | +| explained_variance | 0.637 | +| learning_rate | 4.26e-05 | +| loss | -0.0279 | +| n_updates | 76620 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.00012 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1401 | +| iterations | 15202 | +| time_elapsed | 22211 | +| total_timesteps | 31133696 | +| train/ | | +| approx_kl | 0.012512032 | +| clip_fraction | 0.327 | +| clip_range | 0.0672 | +| entropy_loss | -5.89 | +| explained_variance | 0.431 | +| learning_rate | 4.26e-05 | +| loss | -0.0263 | +| n_updates | 76624 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000204 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1401 | +| iterations | 15203 | +| time_elapsed | 22212 | +| total_timesteps | 31135744 | +| train/ | | +| approx_kl | 0.012220159 | +| clip_fraction | 0.338 | +| clip_range | 0.0672 | +| entropy_loss | -5.83 | +| explained_variance | 0.554 | +| learning_rate | 4.26e-05 | +| loss | -0.0285 | +| n_updates | 76628 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000105 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1401 | +| iterations | 15204 | +| time_elapsed | 22214 | +| total_timesteps | 31137792 | +| train/ | | +| approx_kl | 0.014555821 | +| clip_fraction | 0.369 | +| clip_range | 0.0672 | +| entropy_loss | -5.91 | +| explained_variance | 0.331 | +| learning_rate | 4.26e-05 | +| loss | -0.0354 | +| n_updates | 76632 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000132 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1401 | +| iterations | 15205 | +| time_elapsed | 22215 | +| total_timesteps | 31139840 | +| train/ | | +| approx_kl | 0.015245354 | +| clip_fraction | 0.36 | +| clip_range | 0.0672 | +| entropy_loss | -6.74 | +| explained_variance | -0.248 | +| learning_rate | 4.26e-05 | +| loss | -0.0325 | +| n_updates | 76636 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000108 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1401 | +| iterations | 15206 | +| time_elapsed | 22217 | +| total_timesteps | 31141888 | +| train/ | | +| approx_kl | 0.013771163 | +| clip_fraction | 0.337 | +| clip_range | 0.0672 | +| entropy_loss | -5.85 | +| explained_variance | 0.488 | +| learning_rate | 4.26e-05 | +| loss | -0.0243 | +| n_updates | 76640 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000236 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1401 | +| iterations | 15207 | +| time_elapsed | 22218 | +| total_timesteps | 31143936 | +| train/ | | +| approx_kl | 0.012620027 | +| clip_fraction | 0.311 | +| clip_range | 0.0672 | +| entropy_loss | -6.23 | +| explained_variance | -0.0327 | +| learning_rate | 4.26e-05 | +| loss | -0.0293 | +| n_updates | 76644 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000125 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1401 | +| iterations | 15208 | +| time_elapsed | 22220 | +| total_timesteps | 31145984 | +| train/ | | +| approx_kl | 0.016818777 | +| clip_fraction | 0.377 | +| clip_range | 0.0672 | +| entropy_loss | -6.55 | +| explained_variance | 0.186 | +| learning_rate | 4.26e-05 | +| loss | -0.0336 | +| n_updates | 76648 | +| policy_gradient_loss | -0.0226 | +| value_loss | 6.88e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1401 | +| iterations | 15209 | +| time_elapsed | 22222 | +| total_timesteps | 31148032 | +| train/ | | +| approx_kl | 0.014027363 | +| clip_fraction | 0.331 | +| clip_range | 0.0672 | +| entropy_loss | -6.1 | +| explained_variance | 0.331 | +| learning_rate | 4.26e-05 | +| loss | -0.0278 | +| n_updates | 76652 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000261 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1401 | +| iterations | 15210 | +| time_elapsed | 22223 | +| total_timesteps | 31150080 | +| train/ | | +| approx_kl | 0.011596257 | +| clip_fraction | 0.313 | +| clip_range | 0.0672 | +| entropy_loss | -6.29 | +| explained_variance | 0.314 | +| learning_rate | 4.26e-05 | +| loss | -0.0294 | +| n_updates | 76656 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000147 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1401 | +| iterations | 15211 | +| time_elapsed | 22225 | +| total_timesteps | 31152128 | +| train/ | | +| approx_kl | 0.013722984 | +| clip_fraction | 0.349 | +| clip_range | 0.0672 | +| entropy_loss | -6.37 | +| explained_variance | 0.534 | +| learning_rate | 4.26e-05 | +| loss | -0.0272 | +| n_updates | 76660 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000115 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1401 | +| iterations | 15212 | +| time_elapsed | 22226 | +| total_timesteps | 31154176 | +| train/ | | +| approx_kl | 0.013489302 | +| clip_fraction | 0.326 | +| clip_range | 0.0672 | +| entropy_loss | -6.59 | +| explained_variance | 0.227 | +| learning_rate | 4.26e-05 | +| loss | -0.0264 | +| n_updates | 76664 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.00011 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1401 | +| iterations | 15213 | +| time_elapsed | 22228 | +| total_timesteps | 31156224 | +| train/ | | +| approx_kl | 0.011729251 | +| clip_fraction | 0.321 | +| clip_range | 0.0672 | +| entropy_loss | -6 | +| explained_variance | 0.617 | +| learning_rate | 4.26e-05 | +| loss | -0.025 | +| n_updates | 76668 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.00017 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1401 | +| iterations | 15214 | +| time_elapsed | 22229 | +| total_timesteps | 31158272 | +| train/ | | +| approx_kl | 0.014155052 | +| clip_fraction | 0.312 | +| clip_range | 0.0672 | +| entropy_loss | -6.13 | +| explained_variance | 0.316 | +| learning_rate | 4.26e-05 | +| loss | -0.027 | +| n_updates | 76672 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000183 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1401 | +| iterations | 15215 | +| time_elapsed | 22231 | +| total_timesteps | 31160320 | +| train/ | | +| approx_kl | 0.014234043 | +| clip_fraction | 0.349 | +| clip_range | 0.0672 | +| entropy_loss | -6.48 | +| explained_variance | 0.181 | +| learning_rate | 4.26e-05 | +| loss | -0.033 | +| n_updates | 76676 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000179 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1401 | +| iterations | 15216 | +| time_elapsed | 22232 | +| total_timesteps | 31162368 | +| train/ | | +| approx_kl | 0.010996301 | +| clip_fraction | 0.333 | +| clip_range | 0.0672 | +| entropy_loss | -6.77 | +| explained_variance | 0.285 | +| learning_rate | 4.26e-05 | +| loss | -0.0292 | +| n_updates | 76680 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.00016 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1401 | +| iterations | 15217 | +| time_elapsed | 22234 | +| total_timesteps | 31164416 | +| train/ | | +| approx_kl | 0.012931513 | +| clip_fraction | 0.343 | +| clip_range | 0.0672 | +| entropy_loss | -6.84 | +| explained_variance | 0.144 | +| learning_rate | 4.26e-05 | +| loss | -0.0333 | +| n_updates | 76684 | +| policy_gradient_loss | -0.0209 | +| value_loss | 9.49e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1401 | +| iterations | 15218 | +| time_elapsed | 22235 | +| total_timesteps | 31166464 | +| train/ | | +| approx_kl | 0.014096388 | +| clip_fraction | 0.327 | +| clip_range | 0.0672 | +| entropy_loss | -6.68 | +| explained_variance | 0.113 | +| learning_rate | 4.26e-05 | +| loss | -0.0286 | +| n_updates | 76688 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.0001 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1401 | +| iterations | 15219 | +| time_elapsed | 22237 | +| total_timesteps | 31168512 | +| train/ | | +| approx_kl | 0.015194249 | +| clip_fraction | 0.372 | +| clip_range | 0.0672 | +| entropy_loss | -6.68 | +| explained_variance | -0.0466 | +| learning_rate | 4.26e-05 | +| loss | -0.0338 | +| n_updates | 76692 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000147 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1401 | +| iterations | 15220 | +| time_elapsed | 22238 | +| total_timesteps | 31170560 | +| train/ | | +| approx_kl | 0.014161168 | +| clip_fraction | 0.318 | +| clip_range | 0.0672 | +| entropy_loss | -6.73 | +| explained_variance | 0.209 | +| learning_rate | 4.26e-05 | +| loss | -0.023 | +| n_updates | 76696 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000164 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1401 | +| iterations | 15221 | +| time_elapsed | 22240 | +| total_timesteps | 31172608 | +| train/ | | +| approx_kl | 0.012568463 | +| clip_fraction | 0.346 | +| clip_range | 0.0672 | +| entropy_loss | -6.13 | +| explained_variance | 0.476 | +| learning_rate | 4.26e-05 | +| loss | -0.0292 | +| n_updates | 76700 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000143 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1401 | +| iterations | 15222 | +| time_elapsed | 22241 | +| total_timesteps | 31174656 | +| train/ | | +| approx_kl | 0.01207287 | +| clip_fraction | 0.308 | +| clip_range | 0.0672 | +| entropy_loss | -5.51 | +| explained_variance | 0.625 | +| learning_rate | 4.26e-05 | +| loss | -0.0286 | +| n_updates | 76704 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000161 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1401 | +| iterations | 15223 | +| time_elapsed | 22243 | +| total_timesteps | 31176704 | +| train/ | | +| approx_kl | 0.009850832 | +| clip_fraction | 0.314 | +| clip_range | 0.0672 | +| entropy_loss | -5.22 | +| explained_variance | 0.507 | +| learning_rate | 4.26e-05 | +| loss | -0.0284 | +| n_updates | 76708 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000328 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1401 | +| iterations | 15224 | +| time_elapsed | 22244 | +| total_timesteps | 31178752 | +| train/ | | +| approx_kl | 0.010964207 | +| clip_fraction | 0.343 | +| clip_range | 0.0672 | +| entropy_loss | -5.18 | +| explained_variance | 0.727 | +| learning_rate | 4.26e-05 | +| loss | -0.0347 | +| n_updates | 76712 | +| policy_gradient_loss | -0.0203 | +| value_loss | 9.43e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1401 | +| iterations | 15225 | +| time_elapsed | 22246 | +| total_timesteps | 31180800 | +| train/ | | +| approx_kl | 0.011662806 | +| clip_fraction | 0.345 | +| clip_range | 0.0672 | +| entropy_loss | -6.48 | +| explained_variance | 0.295 | +| learning_rate | 4.26e-05 | +| loss | -0.031 | +| n_updates | 76716 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000197 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1401 | +| iterations | 15226 | +| time_elapsed | 22248 | +| total_timesteps | 31182848 | +| train/ | | +| approx_kl | 0.01251009 | +| clip_fraction | 0.346 | +| clip_range | 0.0672 | +| entropy_loss | -6.72 | +| explained_variance | 0.483 | +| learning_rate | 4.26e-05 | +| loss | -0.0369 | +| n_updates | 76720 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000115 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1401 | +| iterations | 15227 | +| time_elapsed | 22249 | +| total_timesteps | 31184896 | +| train/ | | +| approx_kl | 0.013003323 | +| clip_fraction | 0.323 | +| clip_range | 0.0672 | +| entropy_loss | -6.48 | +| explained_variance | 0.262 | +| learning_rate | 4.26e-05 | +| loss | -0.0309 | +| n_updates | 76724 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000187 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1401 | +| iterations | 15228 | +| time_elapsed | 22250 | +| total_timesteps | 31186944 | +| train/ | | +| approx_kl | 0.011363942 | +| clip_fraction | 0.317 | +| clip_range | 0.0672 | +| entropy_loss | -7 | +| explained_variance | 0.344 | +| learning_rate | 4.26e-05 | +| loss | -0.0275 | +| n_updates | 76728 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000112 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1401 | +| iterations | 15229 | +| time_elapsed | 22252 | +| total_timesteps | 31188992 | +| train/ | | +| approx_kl | 0.008203024 | +| clip_fraction | 0.278 | +| clip_range | 0.0672 | +| entropy_loss | -6.43 | +| explained_variance | 0.407 | +| learning_rate | 4.26e-05 | +| loss | -0.0199 | +| n_updates | 76732 | +| policy_gradient_loss | -0.0137 | +| value_loss | 0.000244 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1401 | +| iterations | 15230 | +| time_elapsed | 22253 | +| total_timesteps | 31191040 | +| train/ | | +| approx_kl | 0.013197252 | +| clip_fraction | 0.332 | +| clip_range | 0.0672 | +| entropy_loss | -6.51 | +| explained_variance | 0.271 | +| learning_rate | 4.26e-05 | +| loss | -0.0335 | +| n_updates | 76736 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000115 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1401 | +| iterations | 15231 | +| time_elapsed | 22255 | +| total_timesteps | 31193088 | +| train/ | | +| approx_kl | 0.010688454 | +| clip_fraction | 0.309 | +| clip_range | 0.0672 | +| entropy_loss | -5.8 | +| explained_variance | 0.592 | +| learning_rate | 4.26e-05 | +| loss | -0.0195 | +| n_updates | 76740 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000204 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1401 | +| iterations | 15232 | +| time_elapsed | 22256 | +| total_timesteps | 31195136 | +| train/ | | +| approx_kl | 0.010960337 | +| clip_fraction | 0.327 | +| clip_range | 0.0672 | +| entropy_loss | -5.39 | +| explained_variance | 0.607 | +| learning_rate | 4.26e-05 | +| loss | -0.0257 | +| n_updates | 76744 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000174 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1401 | +| iterations | 15233 | +| time_elapsed | 22258 | +| total_timesteps | 31197184 | +| train/ | | +| approx_kl | 0.012695213 | +| clip_fraction | 0.338 | +| clip_range | 0.0672 | +| entropy_loss | -5.34 | +| explained_variance | 0.447 | +| learning_rate | 4.26e-05 | +| loss | -0.0231 | +| n_updates | 76748 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000359 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1401 | +| iterations | 15234 | +| time_elapsed | 22259 | +| total_timesteps | 31199232 | +| train/ | | +| approx_kl | 0.012932659 | +| clip_fraction | 0.304 | +| clip_range | 0.0672 | +| entropy_loss | -5.94 | +| explained_variance | 0.0274 | +| learning_rate | 4.26e-05 | +| loss | -0.0295 | +| n_updates | 76752 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000155 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1401 | +| iterations | 15235 | +| time_elapsed | 22261 | +| total_timesteps | 31201280 | +| train/ | | +| approx_kl | 0.0139711425 | +| clip_fraction | 0.389 | +| clip_range | 0.0672 | +| entropy_loss | -6.8 | +| explained_variance | -0.414 | +| learning_rate | 4.26e-05 | +| loss | -0.0348 | +| n_updates | 76756 | +| policy_gradient_loss | -0.0234 | +| value_loss | 8.48e-05 | +------------------------------------------ +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1401 | +| iterations | 15236 | +| time_elapsed | 22262 | +| total_timesteps | 31203328 | +| train/ | | +| approx_kl | 0.0106095 | +| clip_fraction | 0.326 | +| clip_range | 0.0672 | +| entropy_loss | -6.71 | +| explained_variance | 0.265 | +| learning_rate | 4.26e-05 | +| loss | -0.0239 | +| n_updates | 76760 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000222 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1401 | +| iterations | 15237 | +| time_elapsed | 22264 | +| total_timesteps | 31205376 | +| train/ | | +| approx_kl | 0.015662124 | +| clip_fraction | 0.323 | +| clip_range | 0.0672 | +| entropy_loss | -6.51 | +| explained_variance | 0.135 | +| learning_rate | 4.26e-05 | +| loss | -0.0275 | +| n_updates | 76764 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000413 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1401 | +| iterations | 15238 | +| time_elapsed | 22266 | +| total_timesteps | 31207424 | +| train/ | | +| approx_kl | 0.01197877 | +| clip_fraction | 0.316 | +| clip_range | 0.0672 | +| entropy_loss | -6.38 | +| explained_variance | 0.194 | +| learning_rate | 4.26e-05 | +| loss | -0.0309 | +| n_updates | 76768 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000188 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1401 | +| iterations | 15239 | +| time_elapsed | 22267 | +| total_timesteps | 31209472 | +| train/ | | +| approx_kl | 0.010861548 | +| clip_fraction | 0.339 | +| clip_range | 0.0672 | +| entropy_loss | -6.43 | +| explained_variance | 0.39 | +| learning_rate | 4.26e-05 | +| loss | -0.0271 | +| n_updates | 76772 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.00023 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1401 | +| iterations | 15240 | +| time_elapsed | 22269 | +| total_timesteps | 31211520 | +| train/ | | +| approx_kl | 0.011577796 | +| clip_fraction | 0.348 | +| clip_range | 0.0672 | +| entropy_loss | -6.81 | +| explained_variance | -0.158 | +| learning_rate | 4.26e-05 | +| loss | -0.0362 | +| n_updates | 76776 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.00012 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1401 | +| iterations | 15241 | +| time_elapsed | 22270 | +| total_timesteps | 31213568 | +| train/ | | +| approx_kl | 0.015166971 | +| clip_fraction | 0.35 | +| clip_range | 0.0672 | +| entropy_loss | -6.35 | +| explained_variance | 0.462 | +| learning_rate | 4.26e-05 | +| loss | -0.0284 | +| n_updates | 76780 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000154 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1401 | +| iterations | 15242 | +| time_elapsed | 22272 | +| total_timesteps | 31215616 | +| train/ | | +| approx_kl | 0.011307254 | +| clip_fraction | 0.326 | +| clip_range | 0.0672 | +| entropy_loss | -5.9 | +| explained_variance | 0.577 | +| learning_rate | 4.26e-05 | +| loss | -0.0306 | +| n_updates | 76784 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000161 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1401 | +| iterations | 15243 | +| time_elapsed | 22273 | +| total_timesteps | 31217664 | +| train/ | | +| approx_kl | 0.012583947 | +| clip_fraction | 0.316 | +| clip_range | 0.0672 | +| entropy_loss | -5.49 | +| explained_variance | 0.748 | +| learning_rate | 4.26e-05 | +| loss | -0.0202 | +| n_updates | 76788 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000119 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1401 | +| iterations | 15244 | +| time_elapsed | 22275 | +| total_timesteps | 31219712 | +| train/ | | +| approx_kl | 0.01083048 | +| clip_fraction | 0.317 | +| clip_range | 0.0672 | +| entropy_loss | -6.18 | +| explained_variance | -0.214 | +| learning_rate | 4.26e-05 | +| loss | -0.0278 | +| n_updates | 76792 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000186 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1401 | +| iterations | 15245 | +| time_elapsed | 22276 | +| total_timesteps | 31221760 | +| train/ | | +| approx_kl | 0.014617918 | +| clip_fraction | 0.344 | +| clip_range | 0.0672 | +| entropy_loss | -6.47 | +| explained_variance | 0.3 | +| learning_rate | 4.26e-05 | +| loss | -0.029 | +| n_updates | 76796 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000182 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1401 | +| iterations | 15246 | +| time_elapsed | 22278 | +| total_timesteps | 31223808 | +| train/ | | +| approx_kl | 0.012335419 | +| clip_fraction | 0.335 | +| clip_range | 0.0672 | +| entropy_loss | -6.33 | +| explained_variance | 0.49 | +| learning_rate | 4.26e-05 | +| loss | -0.0269 | +| n_updates | 76800 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000155 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1401 | +| iterations | 15247 | +| time_elapsed | 22279 | +| total_timesteps | 31225856 | +| train/ | | +| approx_kl | 0.013913693 | +| clip_fraction | 0.303 | +| clip_range | 0.0672 | +| entropy_loss | -5.62 | +| explained_variance | 0.466 | +| learning_rate | 4.26e-05 | +| loss | -0.0244 | +| n_updates | 76804 | +| policy_gradient_loss | -0.014 | +| value_loss | 0.000296 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1401 | +| iterations | 15248 | +| time_elapsed | 22281 | +| total_timesteps | 31227904 | +| train/ | | +| approx_kl | 0.014099456 | +| clip_fraction | 0.333 | +| clip_range | 0.0672 | +| entropy_loss | -5.69 | +| explained_variance | 0.607 | +| learning_rate | 4.26e-05 | +| loss | -0.0315 | +| n_updates | 76808 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000133 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1401 | +| iterations | 15249 | +| time_elapsed | 22282 | +| total_timesteps | 31229952 | +| train/ | | +| approx_kl | 0.012255726 | +| clip_fraction | 0.327 | +| clip_range | 0.0672 | +| entropy_loss | -5.78 | +| explained_variance | 0.351 | +| learning_rate | 4.26e-05 | +| loss | -0.0212 | +| n_updates | 76812 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.000258 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1401 | +| iterations | 15250 | +| time_elapsed | 22284 | +| total_timesteps | 31232000 | +| train/ | | +| approx_kl | 0.015863275 | +| clip_fraction | 0.38 | +| clip_range | 0.0672 | +| entropy_loss | -5.62 | +| explained_variance | 0.581 | +| learning_rate | 4.26e-05 | +| loss | -0.0282 | +| n_updates | 76816 | +| policy_gradient_loss | -0.02 | +| value_loss | 8.8e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1401 | +| iterations | 15251 | +| time_elapsed | 22285 | +| total_timesteps | 31234048 | +| train/ | | +| approx_kl | 0.013476051 | +| clip_fraction | 0.374 | +| clip_range | 0.0672 | +| entropy_loss | -6.47 | +| explained_variance | -0.0122 | +| learning_rate | 4.26e-05 | +| loss | -0.032 | +| n_updates | 76820 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000205 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1401 | +| iterations | 15252 | +| time_elapsed | 22287 | +| total_timesteps | 31236096 | +| train/ | | +| approx_kl | 0.015350422 | +| clip_fraction | 0.328 | +| clip_range | 0.0672 | +| entropy_loss | -6.6 | +| explained_variance | 0.395 | +| learning_rate | 4.26e-05 | +| loss | -0.0261 | +| n_updates | 76824 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000145 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1401 | +| iterations | 15253 | +| time_elapsed | 22288 | +| total_timesteps | 31238144 | +| train/ | | +| approx_kl | 0.016318979 | +| clip_fraction | 0.365 | +| clip_range | 0.0672 | +| entropy_loss | -6.23 | +| explained_variance | 0.698 | +| learning_rate | 4.26e-05 | +| loss | -0.0331 | +| n_updates | 76828 | +| policy_gradient_loss | -0.0219 | +| value_loss | 7.33e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1401 | +| iterations | 15254 | +| time_elapsed | 22290 | +| total_timesteps | 31240192 | +| train/ | | +| approx_kl | 0.013768831 | +| clip_fraction | 0.371 | +| clip_range | 0.0672 | +| entropy_loss | -5.75 | +| explained_variance | 0.611 | +| learning_rate | 4.26e-05 | +| loss | -0.0308 | +| n_updates | 76832 | +| policy_gradient_loss | -0.0181 | +| value_loss | 8.79e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1401 | +| iterations | 15255 | +| time_elapsed | 22291 | +| total_timesteps | 31242240 | +| train/ | | +| approx_kl | 0.014777932 | +| clip_fraction | 0.329 | +| clip_range | 0.0672 | +| entropy_loss | -6.39 | +| explained_variance | 0.32 | +| learning_rate | 4.26e-05 | +| loss | -0.0276 | +| n_updates | 76836 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000212 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1401 | +| iterations | 15256 | +| time_elapsed | 22293 | +| total_timesteps | 31244288 | +| train/ | | +| approx_kl | 0.014021328 | +| clip_fraction | 0.354 | +| clip_range | 0.0672 | +| entropy_loss | -6.28 | +| explained_variance | 0.351 | +| learning_rate | 4.26e-05 | +| loss | -0.0319 | +| n_updates | 76840 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1401 | +| iterations | 15257 | +| time_elapsed | 22295 | +| total_timesteps | 31246336 | +| train/ | | +| approx_kl | 0.011187896 | +| clip_fraction | 0.314 | +| clip_range | 0.0672 | +| entropy_loss | -6.18 | +| explained_variance | 0.313 | +| learning_rate | 4.26e-05 | +| loss | -0.0284 | +| n_updates | 76844 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.0003 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1401 | +| iterations | 15258 | +| time_elapsed | 22296 | +| total_timesteps | 31248384 | +| train/ | | +| approx_kl | 0.014236135 | +| clip_fraction | 0.342 | +| clip_range | 0.0672 | +| entropy_loss | -6.21 | +| explained_variance | 0.27 | +| learning_rate | 4.26e-05 | +| loss | -0.0265 | +| n_updates | 76848 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000156 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1401 | +| iterations | 15259 | +| time_elapsed | 22298 | +| total_timesteps | 31250432 | +| train/ | | +| approx_kl | 0.013194735 | +| clip_fraction | 0.336 | +| clip_range | 0.0672 | +| entropy_loss | -5.51 | +| explained_variance | 0.509 | +| learning_rate | 4.26e-05 | +| loss | -0.0279 | +| n_updates | 76852 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000186 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1401 | +| iterations | 15260 | +| time_elapsed | 22299 | +| total_timesteps | 31252480 | +| train/ | | +| approx_kl | 0.012376418 | +| clip_fraction | 0.34 | +| clip_range | 0.0672 | +| entropy_loss | -6.01 | +| explained_variance | 0.381 | +| learning_rate | 4.26e-05 | +| loss | -0.0295 | +| n_updates | 76856 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000117 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1401 | +| iterations | 15261 | +| time_elapsed | 22301 | +| total_timesteps | 31254528 | +| train/ | | +| approx_kl | 0.010311969 | +| clip_fraction | 0.326 | +| clip_range | 0.0672 | +| entropy_loss | -5.99 | +| explained_variance | 0.604 | +| learning_rate | 4.26e-05 | +| loss | -0.0252 | +| n_updates | 76860 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000143 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1401 | +| iterations | 15262 | +| time_elapsed | 22302 | +| total_timesteps | 31256576 | +| train/ | | +| approx_kl | 0.014103644 | +| clip_fraction | 0.348 | +| clip_range | 0.0672 | +| entropy_loss | -6.28 | +| explained_variance | 0.331 | +| learning_rate | 4.26e-05 | +| loss | -0.0283 | +| n_updates | 76864 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000113 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1401 | +| iterations | 15263 | +| time_elapsed | 22304 | +| total_timesteps | 31258624 | +| train/ | | +| approx_kl | 0.009691446 | +| clip_fraction | 0.32 | +| clip_range | 0.0672 | +| entropy_loss | -6.58 | +| explained_variance | 0.374 | +| learning_rate | 4.26e-05 | +| loss | -0.031 | +| n_updates | 76868 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000159 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1401 | +| iterations | 15264 | +| time_elapsed | 22305 | +| total_timesteps | 31260672 | +| train/ | | +| approx_kl | 0.012290884 | +| clip_fraction | 0.328 | +| clip_range | 0.0672 | +| entropy_loss | -6.66 | +| explained_variance | 0.357 | +| learning_rate | 4.26e-05 | +| loss | -0.0236 | +| n_updates | 76872 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000135 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1401 | +| iterations | 15265 | +| time_elapsed | 22307 | +| total_timesteps | 31262720 | +| train/ | | +| approx_kl | 0.012693181 | +| clip_fraction | 0.339 | +| clip_range | 0.0672 | +| entropy_loss | -6.38 | +| explained_variance | 0.293 | +| learning_rate | 4.26e-05 | +| loss | -0.0219 | +| n_updates | 76876 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000176 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1401 | +| iterations | 15266 | +| time_elapsed | 22308 | +| total_timesteps | 31264768 | +| train/ | | +| approx_kl | 0.012417139 | +| clip_fraction | 0.305 | +| clip_range | 0.0672 | +| entropy_loss | -5.99 | +| explained_variance | 0.393 | +| learning_rate | 4.26e-05 | +| loss | -0.0283 | +| n_updates | 76880 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000225 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1401 | +| iterations | 15267 | +| time_elapsed | 22310 | +| total_timesteps | 31266816 | +| train/ | | +| approx_kl | 0.012001855 | +| clip_fraction | 0.301 | +| clip_range | 0.0672 | +| entropy_loss | -5.67 | +| explained_variance | 0.484 | +| learning_rate | 4.26e-05 | +| loss | -0.0281 | +| n_updates | 76884 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000214 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1401 | +| iterations | 15268 | +| time_elapsed | 22311 | +| total_timesteps | 31268864 | +| train/ | | +| approx_kl | 0.015016405 | +| clip_fraction | 0.347 | +| clip_range | 0.0672 | +| entropy_loss | -5.93 | +| explained_variance | 0.079 | +| learning_rate | 4.26e-05 | +| loss | -0.0342 | +| n_updates | 76888 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000117 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1401 | +| iterations | 15269 | +| time_elapsed | 22313 | +| total_timesteps | 31270912 | +| train/ | | +| approx_kl | 0.014699463 | +| clip_fraction | 0.356 | +| clip_range | 0.0672 | +| entropy_loss | -6.11 | +| explained_variance | 0.356 | +| learning_rate | 4.26e-05 | +| loss | -0.023 | +| n_updates | 76892 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000301 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1401 | +| iterations | 15270 | +| time_elapsed | 22314 | +| total_timesteps | 31272960 | +| train/ | | +| approx_kl | 0.013859327 | +| clip_fraction | 0.346 | +| clip_range | 0.0672 | +| entropy_loss | -5.64 | +| explained_variance | 0.529 | +| learning_rate | 4.26e-05 | +| loss | -0.0307 | +| n_updates | 76896 | +| policy_gradient_loss | -0.0216 | +| value_loss | 9.9e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1401 | +| iterations | 15271 | +| time_elapsed | 22316 | +| total_timesteps | 31275008 | +| train/ | | +| approx_kl | 0.012518026 | +| clip_fraction | 0.333 | +| clip_range | 0.0672 | +| entropy_loss | -6.01 | +| explained_variance | 0.303 | +| learning_rate | 4.26e-05 | +| loss | -0.0309 | +| n_updates | 76900 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000132 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1401 | +| iterations | 15272 | +| time_elapsed | 22317 | +| total_timesteps | 31277056 | +| train/ | | +| approx_kl | 0.0113807 | +| clip_fraction | 0.334 | +| clip_range | 0.0672 | +| entropy_loss | -6.48 | +| explained_variance | 0.406 | +| learning_rate | 4.26e-05 | +| loss | -0.0302 | +| n_updates | 76904 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000231 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1401 | +| iterations | 15273 | +| time_elapsed | 22319 | +| total_timesteps | 31279104 | +| train/ | | +| approx_kl | 0.013442555 | +| clip_fraction | 0.336 | +| clip_range | 0.0672 | +| entropy_loss | -6.38 | +| explained_variance | -0.0767 | +| learning_rate | 4.26e-05 | +| loss | -0.0299 | +| n_updates | 76908 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000148 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1401 | +| iterations | 15274 | +| time_elapsed | 22320 | +| total_timesteps | 31281152 | +| train/ | | +| approx_kl | 0.012939852 | +| clip_fraction | 0.351 | +| clip_range | 0.0672 | +| entropy_loss | -5.88 | +| explained_variance | 0.72 | +| learning_rate | 4.26e-05 | +| loss | -0.0266 | +| n_updates | 76912 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000105 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1401 | +| iterations | 15275 | +| time_elapsed | 22322 | +| total_timesteps | 31283200 | +| train/ | | +| approx_kl | 0.014388328 | +| clip_fraction | 0.303 | +| clip_range | 0.0672 | +| entropy_loss | -6.56 | +| explained_variance | 0.184 | +| learning_rate | 4.26e-05 | +| loss | -0.0282 | +| n_updates | 76916 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000103 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1401 | +| iterations | 15276 | +| time_elapsed | 22323 | +| total_timesteps | 31285248 | +| train/ | | +| approx_kl | 0.013744114 | +| clip_fraction | 0.351 | +| clip_range | 0.0672 | +| entropy_loss | -6.32 | +| explained_variance | 0.266 | +| learning_rate | 4.26e-05 | +| loss | -0.0314 | +| n_updates | 76920 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000224 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1401 | +| iterations | 15277 | +| time_elapsed | 22325 | +| total_timesteps | 31287296 | +| train/ | | +| approx_kl | 0.014607306 | +| clip_fraction | 0.334 | +| clip_range | 0.0672 | +| entropy_loss | -6.26 | +| explained_variance | 0.286 | +| learning_rate | 4.26e-05 | +| loss | -0.0312 | +| n_updates | 76924 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000136 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1401 | +| iterations | 15278 | +| time_elapsed | 22326 | +| total_timesteps | 31289344 | +| train/ | | +| approx_kl | 0.01486497 | +| clip_fraction | 0.355 | +| clip_range | 0.0672 | +| entropy_loss | -5.98 | +| explained_variance | 0.161 | +| learning_rate | 4.26e-05 | +| loss | -0.0319 | +| n_updates | 76928 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000249 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1401 | +| iterations | 15279 | +| time_elapsed | 22328 | +| total_timesteps | 31291392 | +| train/ | | +| approx_kl | 0.013736214 | +| clip_fraction | 0.347 | +| clip_range | 0.0672 | +| entropy_loss | -5.78 | +| explained_variance | 0.402 | +| learning_rate | 4.26e-05 | +| loss | -0.0275 | +| n_updates | 76932 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000269 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1401 | +| iterations | 15280 | +| time_elapsed | 22329 | +| total_timesteps | 31293440 | +| train/ | | +| approx_kl | 0.013920767 | +| clip_fraction | 0.332 | +| clip_range | 0.0672 | +| entropy_loss | -5.75 | +| explained_variance | 0.561 | +| learning_rate | 4.26e-05 | +| loss | -0.0319 | +| n_updates | 76936 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000109 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1401 | +| iterations | 15281 | +| time_elapsed | 22331 | +| total_timesteps | 31295488 | +| train/ | | +| approx_kl | 0.016678784 | +| clip_fraction | 0.362 | +| clip_range | 0.0672 | +| entropy_loss | -6.04 | +| explained_variance | 0.63 | +| learning_rate | 4.26e-05 | +| loss | -0.0308 | +| n_updates | 76940 | +| policy_gradient_loss | -0.0213 | +| value_loss | 9.33e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1401 | +| iterations | 15282 | +| time_elapsed | 22332 | +| total_timesteps | 31297536 | +| train/ | | +| approx_kl | 0.013343476 | +| clip_fraction | 0.311 | +| clip_range | 0.0672 | +| entropy_loss | -6.57 | +| explained_variance | 0.0274 | +| learning_rate | 4.26e-05 | +| loss | -0.0276 | +| n_updates | 76944 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000159 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1401 | +| iterations | 15283 | +| time_elapsed | 22334 | +| total_timesteps | 31299584 | +| train/ | | +| approx_kl | 0.014338169 | +| clip_fraction | 0.334 | +| clip_range | 0.0672 | +| entropy_loss | -6.11 | +| explained_variance | 0.566 | +| learning_rate | 4.26e-05 | +| loss | -0.0279 | +| n_updates | 76948 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000158 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1401 | +| iterations | 15284 | +| time_elapsed | 22335 | +| total_timesteps | 31301632 | +| train/ | | +| approx_kl | 0.01257685 | +| clip_fraction | 0.333 | +| clip_range | 0.0672 | +| entropy_loss | -6.3 | +| explained_variance | 0.506 | +| learning_rate | 4.26e-05 | +| loss | -0.0304 | +| n_updates | 76952 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000125 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1401 | +| iterations | 15285 | +| time_elapsed | 22337 | +| total_timesteps | 31303680 | +| train/ | | +| approx_kl | 0.013638305 | +| clip_fraction | 0.31 | +| clip_range | 0.0672 | +| entropy_loss | -6.26 | +| explained_variance | 0.343 | +| learning_rate | 4.26e-05 | +| loss | -0.0201 | +| n_updates | 76956 | +| policy_gradient_loss | -0.0144 | +| value_loss | 0.000292 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1401 | +| iterations | 15286 | +| time_elapsed | 22338 | +| total_timesteps | 31305728 | +| train/ | | +| approx_kl | 0.017133603 | +| clip_fraction | 0.327 | +| clip_range | 0.0672 | +| entropy_loss | -5.73 | +| explained_variance | 0.521 | +| learning_rate | 4.26e-05 | +| loss | -0.0315 | +| n_updates | 76960 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.00014 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1401 | +| iterations | 15287 | +| time_elapsed | 22340 | +| total_timesteps | 31307776 | +| train/ | | +| approx_kl | 0.017220298 | +| clip_fraction | 0.321 | +| clip_range | 0.0672 | +| entropy_loss | -6.1 | +| explained_variance | 0.189 | +| learning_rate | 4.26e-05 | +| loss | -0.0222 | +| n_updates | 76964 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000298 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1401 | +| iterations | 15288 | +| time_elapsed | 22341 | +| total_timesteps | 31309824 | +| train/ | | +| approx_kl | 0.012347218 | +| clip_fraction | 0.346 | +| clip_range | 0.0672 | +| entropy_loss | -6.46 | +| explained_variance | -0.0839 | +| learning_rate | 4.26e-05 | +| loss | -0.0288 | +| n_updates | 76968 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000213 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1401 | +| iterations | 15289 | +| time_elapsed | 22343 | +| total_timesteps | 31311872 | +| train/ | | +| approx_kl | 0.01537781 | +| clip_fraction | 0.372 | +| clip_range | 0.0672 | +| entropy_loss | -6.06 | +| explained_variance | 0.708 | +| learning_rate | 4.26e-05 | +| loss | -0.0393 | +| n_updates | 76972 | +| policy_gradient_loss | -0.0217 | +| value_loss | 8.01e-05 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1401 | +| iterations | 15290 | +| time_elapsed | 22345 | +| total_timesteps | 31313920 | +| train/ | | +| approx_kl | 0.01146571 | +| clip_fraction | 0.341 | +| clip_range | 0.0672 | +| entropy_loss | -6.43 | +| explained_variance | 0.698 | +| learning_rate | 4.26e-05 | +| loss | -0.0327 | +| n_updates | 76976 | +| policy_gradient_loss | -0.0211 | +| value_loss | 5.74e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1401 | +| iterations | 15291 | +| time_elapsed | 22346 | +| total_timesteps | 31315968 | +| train/ | | +| approx_kl | 0.011779462 | +| clip_fraction | 0.31 | +| clip_range | 0.0672 | +| entropy_loss | -6.77 | +| explained_variance | -0.055 | +| learning_rate | 4.26e-05 | +| loss | -0.0272 | +| n_updates | 76980 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000209 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1401 | +| iterations | 15292 | +| time_elapsed | 22348 | +| total_timesteps | 31318016 | +| train/ | | +| approx_kl | 0.010176588 | +| clip_fraction | 0.318 | +| clip_range | 0.0672 | +| entropy_loss | -6.34 | +| explained_variance | 0.743 | +| learning_rate | 4.26e-05 | +| loss | -0.0292 | +| n_updates | 76984 | +| policy_gradient_loss | -0.0169 | +| value_loss | 7.89e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1401 | +| iterations | 15293 | +| time_elapsed | 22349 | +| total_timesteps | 31320064 | +| train/ | | +| approx_kl | 0.015487628 | +| clip_fraction | 0.32 | +| clip_range | 0.0672 | +| entropy_loss | -5.93 | +| explained_variance | 0.499 | +| learning_rate | 4.26e-05 | +| loss | -0.0286 | +| n_updates | 76988 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000233 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1401 | +| iterations | 15294 | +| time_elapsed | 22351 | +| total_timesteps | 31322112 | +| train/ | | +| approx_kl | 0.010085482 | +| clip_fraction | 0.312 | +| clip_range | 0.0672 | +| entropy_loss | -6.51 | +| explained_variance | 0.029 | +| learning_rate | 4.26e-05 | +| loss | -0.0313 | +| n_updates | 76992 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000232 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1401 | +| iterations | 15295 | +| time_elapsed | 22352 | +| total_timesteps | 31324160 | +| train/ | | +| approx_kl | 0.015981019 | +| clip_fraction | 0.314 | +| clip_range | 0.0672 | +| entropy_loss | -6.86 | +| explained_variance | -0.23 | +| learning_rate | 4.26e-05 | +| loss | -0.0283 | +| n_updates | 76996 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000191 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1401 | +| iterations | 15296 | +| time_elapsed | 22354 | +| total_timesteps | 31326208 | +| train/ | | +| approx_kl | 0.012966839 | +| clip_fraction | 0.333 | +| clip_range | 0.0672 | +| entropy_loss | -6.66 | +| explained_variance | 0.277 | +| learning_rate | 4.26e-05 | +| loss | -0.028 | +| n_updates | 77000 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000171 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1401 | +| iterations | 15297 | +| time_elapsed | 22355 | +| total_timesteps | 31328256 | +| train/ | | +| approx_kl | 0.009189931 | +| clip_fraction | 0.299 | +| clip_range | 0.0672 | +| entropy_loss | -6.37 | +| explained_variance | 0.308 | +| learning_rate | 4.26e-05 | +| loss | -0.0233 | +| n_updates | 77004 | +| policy_gradient_loss | -0.0137 | +| value_loss | 0.00029 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1401 | +| iterations | 15298 | +| time_elapsed | 22357 | +| total_timesteps | 31330304 | +| train/ | | +| approx_kl | 0.008760274 | +| clip_fraction | 0.312 | +| clip_range | 0.0672 | +| entropy_loss | -6.08 | +| explained_variance | 0.567 | +| learning_rate | 4.26e-05 | +| loss | -0.027 | +| n_updates | 77008 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000115 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1401 | +| iterations | 15299 | +| time_elapsed | 22358 | +| total_timesteps | 31332352 | +| train/ | | +| approx_kl | 0.011273105 | +| clip_fraction | 0.315 | +| clip_range | 0.0672 | +| entropy_loss | -6.44 | +| explained_variance | 0.266 | +| learning_rate | 4.26e-05 | +| loss | -0.0269 | +| n_updates | 77012 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000199 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1401 | +| iterations | 15300 | +| time_elapsed | 22360 | +| total_timesteps | 31334400 | +| train/ | | +| approx_kl | 0.013112487 | +| clip_fraction | 0.346 | +| clip_range | 0.0672 | +| entropy_loss | -5.84 | +| explained_variance | 0.712 | +| learning_rate | 4.26e-05 | +| loss | -0.0292 | +| n_updates | 77016 | +| policy_gradient_loss | -0.0182 | +| value_loss | 7.1e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1401 | +| iterations | 15301 | +| time_elapsed | 22361 | +| total_timesteps | 31336448 | +| train/ | | +| approx_kl | 0.017315727 | +| clip_fraction | 0.32 | +| clip_range | 0.0672 | +| entropy_loss | -6.29 | +| explained_variance | 0.374 | +| learning_rate | 4.26e-05 | +| loss | -0.0291 | +| n_updates | 77020 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000156 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1401 | +| iterations | 15302 | +| time_elapsed | 22363 | +| total_timesteps | 31338496 | +| train/ | | +| approx_kl | 0.012375432 | +| clip_fraction | 0.325 | +| clip_range | 0.0672 | +| entropy_loss | -5.84 | +| explained_variance | 0.49 | +| learning_rate | 4.26e-05 | +| loss | -0.0277 | +| n_updates | 77024 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.00026 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1401 | +| iterations | 15303 | +| time_elapsed | 22365 | +| total_timesteps | 31340544 | +| train/ | | +| approx_kl | 0.015321668 | +| clip_fraction | 0.34 | +| clip_range | 0.0672 | +| entropy_loss | -6.31 | +| explained_variance | -0.143 | +| learning_rate | 4.26e-05 | +| loss | -0.0292 | +| n_updates | 77028 | +| policy_gradient_loss | -0.0191 | +| value_loss | 9.83e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1401 | +| iterations | 15304 | +| time_elapsed | 22366 | +| total_timesteps | 31342592 | +| train/ | | +| approx_kl | 0.011444392 | +| clip_fraction | 0.319 | +| clip_range | 0.0672 | +| entropy_loss | -6.3 | +| explained_variance | 0.273 | +| learning_rate | 4.26e-05 | +| loss | -0.0284 | +| n_updates | 77032 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000537 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1401 | +| iterations | 15305 | +| time_elapsed | 22368 | +| total_timesteps | 31344640 | +| train/ | | +| approx_kl | 0.010276965 | +| clip_fraction | 0.332 | +| clip_range | 0.0672 | +| entropy_loss | -5.4 | +| explained_variance | 0.458 | +| learning_rate | 4.26e-05 | +| loss | -0.0275 | +| n_updates | 77036 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.00017 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1401 | +| iterations | 15306 | +| time_elapsed | 22369 | +| total_timesteps | 31346688 | +| train/ | | +| approx_kl | 0.012362689 | +| clip_fraction | 0.377 | +| clip_range | 0.0672 | +| entropy_loss | -6.15 | +| explained_variance | 0.542 | +| learning_rate | 4.26e-05 | +| loss | -0.0355 | +| n_updates | 77040 | +| policy_gradient_loss | -0.0231 | +| value_loss | 9.13e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1401 | +| iterations | 15307 | +| time_elapsed | 22371 | +| total_timesteps | 31348736 | +| train/ | | +| approx_kl | 0.01844837 | +| clip_fraction | 0.345 | +| clip_range | 0.0672 | +| entropy_loss | -5.69 | +| explained_variance | 0.289 | +| learning_rate | 4.26e-05 | +| loss | -0.0301 | +| n_updates | 77044 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000101 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1401 | +| iterations | 15308 | +| time_elapsed | 22372 | +| total_timesteps | 31350784 | +| train/ | | +| approx_kl | 0.015158782 | +| clip_fraction | 0.361 | +| clip_range | 0.0672 | +| entropy_loss | -6.28 | +| explained_variance | 0.259 | +| learning_rate | 4.26e-05 | +| loss | -0.0354 | +| n_updates | 77048 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.00016 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1401 | +| iterations | 15309 | +| time_elapsed | 22374 | +| total_timesteps | 31352832 | +| train/ | | +| approx_kl | 0.011886361 | +| clip_fraction | 0.333 | +| clip_range | 0.0672 | +| entropy_loss | -6.71 | +| explained_variance | -0.337 | +| learning_rate | 4.26e-05 | +| loss | -0.036 | +| n_updates | 77052 | +| policy_gradient_loss | -0.0204 | +| value_loss | 5.94e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1401 | +| iterations | 15310 | +| time_elapsed | 22375 | +| total_timesteps | 31354880 | +| train/ | | +| approx_kl | 0.012200974 | +| clip_fraction | 0.328 | +| clip_range | 0.0672 | +| entropy_loss | -6.64 | +| explained_variance | 0.0176 | +| learning_rate | 4.26e-05 | +| loss | -0.0297 | +| n_updates | 77056 | +| policy_gradient_loss | -0.0178 | +| value_loss | 9.06e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1401 | +| iterations | 15311 | +| time_elapsed | 22377 | +| total_timesteps | 31356928 | +| train/ | | +| approx_kl | 0.009234124 | +| clip_fraction | 0.3 | +| clip_range | 0.0672 | +| entropy_loss | -6.99 | +| explained_variance | -0.0841 | +| learning_rate | 4.26e-05 | +| loss | -0.0282 | +| n_updates | 77060 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000116 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1401 | +| iterations | 15312 | +| time_elapsed | 22378 | +| total_timesteps | 31358976 | +| train/ | | +| approx_kl | 0.008907475 | +| clip_fraction | 0.335 | +| clip_range | 0.0672 | +| entropy_loss | -6.75 | +| explained_variance | 0.167 | +| learning_rate | 4.26e-05 | +| loss | -0.0281 | +| n_updates | 77064 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000261 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1401 | +| iterations | 15313 | +| time_elapsed | 22380 | +| total_timesteps | 31361024 | +| train/ | | +| approx_kl | 0.011204293 | +| clip_fraction | 0.296 | +| clip_range | 0.0672 | +| entropy_loss | -6.03 | +| explained_variance | 0.537 | +| learning_rate | 4.26e-05 | +| loss | -0.0272 | +| n_updates | 77068 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000173 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1401 | +| iterations | 15314 | +| time_elapsed | 22381 | +| total_timesteps | 31363072 | +| train/ | | +| approx_kl | 0.009859785 | +| clip_fraction | 0.332 | +| clip_range | 0.0672 | +| entropy_loss | -5.71 | +| explained_variance | 0.645 | +| learning_rate | 4.26e-05 | +| loss | -0.0325 | +| n_updates | 77072 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000123 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1401 | +| iterations | 15315 | +| time_elapsed | 22383 | +| total_timesteps | 31365120 | +| train/ | | +| approx_kl | 0.011562588 | +| clip_fraction | 0.326 | +| clip_range | 0.0672 | +| entropy_loss | -6.2 | +| explained_variance | 0.329 | +| learning_rate | 4.26e-05 | +| loss | -0.028 | +| n_updates | 77076 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000136 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1401 | +| iterations | 15316 | +| time_elapsed | 22385 | +| total_timesteps | 31367168 | +| train/ | | +| approx_kl | 0.012409737 | +| clip_fraction | 0.322 | +| clip_range | 0.0672 | +| entropy_loss | -5.87 | +| explained_variance | 0.538 | +| learning_rate | 4.26e-05 | +| loss | -0.0242 | +| n_updates | 77080 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.00018 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1401 | +| iterations | 15317 | +| time_elapsed | 22386 | +| total_timesteps | 31369216 | +| train/ | | +| approx_kl | 0.015775241 | +| clip_fraction | 0.329 | +| clip_range | 0.0672 | +| entropy_loss | -5.99 | +| explained_variance | 0.389 | +| learning_rate | 4.26e-05 | +| loss | -0.0299 | +| n_updates | 77084 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.00017 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1401 | +| iterations | 15318 | +| time_elapsed | 22388 | +| total_timesteps | 31371264 | +| train/ | | +| approx_kl | 0.014135138 | +| clip_fraction | 0.342 | +| clip_range | 0.0672 | +| entropy_loss | -6.41 | +| explained_variance | 0.514 | +| learning_rate | 4.25e-05 | +| loss | -0.0258 | +| n_updates | 77088 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.00013 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1401 | +| iterations | 15319 | +| time_elapsed | 22389 | +| total_timesteps | 31373312 | +| train/ | | +| approx_kl | 0.014379317 | +| clip_fraction | 0.325 | +| clip_range | 0.0672 | +| entropy_loss | -6.23 | +| explained_variance | 0.349 | +| learning_rate | 4.25e-05 | +| loss | -0.0282 | +| n_updates | 77092 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000156 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1401 | +| iterations | 15320 | +| time_elapsed | 22391 | +| total_timesteps | 31375360 | +| train/ | | +| approx_kl | 0.014522091 | +| clip_fraction | 0.346 | +| clip_range | 0.0672 | +| entropy_loss | -6.95 | +| explained_variance | -0.239 | +| learning_rate | 4.25e-05 | +| loss | -0.0341 | +| n_updates | 77096 | +| policy_gradient_loss | -0.0213 | +| value_loss | 7.26e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1401 | +| iterations | 15321 | +| time_elapsed | 22392 | +| total_timesteps | 31377408 | +| train/ | | +| approx_kl | 0.011680444 | +| clip_fraction | 0.34 | +| clip_range | 0.0672 | +| entropy_loss | -6.87 | +| explained_variance | 0.0972 | +| learning_rate | 4.25e-05 | +| loss | -0.0287 | +| n_updates | 77100 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000135 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1401 | +| iterations | 15322 | +| time_elapsed | 22394 | +| total_timesteps | 31379456 | +| train/ | | +| approx_kl | 0.010973087 | +| clip_fraction | 0.303 | +| clip_range | 0.0672 | +| entropy_loss | -6.2 | +| explained_variance | 0.706 | +| learning_rate | 4.25e-05 | +| loss | -0.026 | +| n_updates | 77104 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000112 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1401 | +| iterations | 15323 | +| time_elapsed | 22395 | +| total_timesteps | 31381504 | +| train/ | | +| approx_kl | 0.011996305 | +| clip_fraction | 0.326 | +| clip_range | 0.0672 | +| entropy_loss | -5.86 | +| explained_variance | 0.402 | +| learning_rate | 4.25e-05 | +| loss | -0.0304 | +| n_updates | 77108 | +| policy_gradient_loss | -0.0186 | +| value_loss | 9.09e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1401 | +| iterations | 15324 | +| time_elapsed | 22397 | +| total_timesteps | 31383552 | +| train/ | | +| approx_kl | 0.014051507 | +| clip_fraction | 0.32 | +| clip_range | 0.0672 | +| entropy_loss | -6.39 | +| explained_variance | 0.167 | +| learning_rate | 4.25e-05 | +| loss | -0.03 | +| n_updates | 77112 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000115 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1401 | +| iterations | 15325 | +| time_elapsed | 22398 | +| total_timesteps | 31385600 | +| train/ | | +| approx_kl | 0.01548027 | +| clip_fraction | 0.39 | +| clip_range | 0.0672 | +| entropy_loss | -6.37 | +| explained_variance | 0.528 | +| learning_rate | 4.25e-05 | +| loss | -0.0331 | +| n_updates | 77116 | +| policy_gradient_loss | -0.0223 | +| value_loss | 5.17e-05 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1401 | +| iterations | 15326 | +| time_elapsed | 22400 | +| total_timesteps | 31387648 | +| train/ | | +| approx_kl | 0.01384898 | +| clip_fraction | 0.315 | +| clip_range | 0.0672 | +| entropy_loss | -4.88 | +| explained_variance | 0.732 | +| learning_rate | 4.25e-05 | +| loss | -0.024 | +| n_updates | 77120 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.000153 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1401 | +| iterations | 15327 | +| time_elapsed | 22401 | +| total_timesteps | 31389696 | +| train/ | | +| approx_kl | 0.01786702 | +| clip_fraction | 0.362 | +| clip_range | 0.0672 | +| entropy_loss | -5.42 | +| explained_variance | 0.477 | +| learning_rate | 4.25e-05 | +| loss | -0.0277 | +| n_updates | 77124 | +| policy_gradient_loss | -0.0209 | +| value_loss | 7.88e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1401 | +| iterations | 15328 | +| time_elapsed | 22403 | +| total_timesteps | 31391744 | +| train/ | | +| approx_kl | 0.013789501 | +| clip_fraction | 0.347 | +| clip_range | 0.0672 | +| entropy_loss | -5.85 | +| explained_variance | 0.524 | +| learning_rate | 4.25e-05 | +| loss | -0.026 | +| n_updates | 77128 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000167 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1401 | +| iterations | 15329 | +| time_elapsed | 22404 | +| total_timesteps | 31393792 | +| train/ | | +| approx_kl | 0.014002526 | +| clip_fraction | 0.344 | +| clip_range | 0.0672 | +| entropy_loss | -5.67 | +| explained_variance | 0.629 | +| learning_rate | 4.25e-05 | +| loss | -0.0262 | +| n_updates | 77132 | +| policy_gradient_loss | -0.0189 | +| value_loss | 7.62e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1401 | +| iterations | 15330 | +| time_elapsed | 22406 | +| total_timesteps | 31395840 | +| train/ | | +| approx_kl | 0.012779424 | +| clip_fraction | 0.35 | +| clip_range | 0.0672 | +| entropy_loss | -6.41 | +| explained_variance | -0.151 | +| learning_rate | 4.25e-05 | +| loss | -0.0299 | +| n_updates | 77136 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000126 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1401 | +| iterations | 15331 | +| time_elapsed | 22407 | +| total_timesteps | 31397888 | +| train/ | | +| approx_kl | 0.010127691 | +| clip_fraction | 0.343 | +| clip_range | 0.0672 | +| entropy_loss | -6.9 | +| explained_variance | -0.101 | +| learning_rate | 4.25e-05 | +| loss | -0.0276 | +| n_updates | 77140 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000122 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1401 | +| iterations | 15332 | +| time_elapsed | 22409 | +| total_timesteps | 31399936 | +| train/ | | +| approx_kl | 0.010939575 | +| clip_fraction | 0.329 | +| clip_range | 0.0672 | +| entropy_loss | -6.69 | +| explained_variance | 0.3 | +| learning_rate | 4.25e-05 | +| loss | -0.026 | +| n_updates | 77144 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000128 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1401 | +| iterations | 15333 | +| time_elapsed | 22411 | +| total_timesteps | 31401984 | +| train/ | | +| approx_kl | 0.012723822 | +| clip_fraction | 0.348 | +| clip_range | 0.0672 | +| entropy_loss | -6.54 | +| explained_variance | 0.103 | +| learning_rate | 4.25e-05 | +| loss | -0.0319 | +| n_updates | 77148 | +| policy_gradient_loss | -0.0199 | +| value_loss | 9.17e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1401 | +| iterations | 15334 | +| time_elapsed | 22412 | +| total_timesteps | 31404032 | +| train/ | | +| approx_kl | 0.014250965 | +| clip_fraction | 0.338 | +| clip_range | 0.0671 | +| entropy_loss | -6.07 | +| explained_variance | 0.632 | +| learning_rate | 4.25e-05 | +| loss | -0.0284 | +| n_updates | 77152 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000102 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1401 | +| iterations | 15335 | +| time_elapsed | 22414 | +| total_timesteps | 31406080 | +| train/ | | +| approx_kl | 0.012473644 | +| clip_fraction | 0.319 | +| clip_range | 0.0671 | +| entropy_loss | -6.6 | +| explained_variance | -0.0443 | +| learning_rate | 4.25e-05 | +| loss | -0.0315 | +| n_updates | 77156 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000106 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1401 | +| iterations | 15336 | +| time_elapsed | 22415 | +| total_timesteps | 31408128 | +| train/ | | +| approx_kl | 0.015553122 | +| clip_fraction | 0.366 | +| clip_range | 0.0671 | +| entropy_loss | -6.25 | +| explained_variance | 0.758 | +| learning_rate | 4.25e-05 | +| loss | -0.0327 | +| n_updates | 77160 | +| policy_gradient_loss | -0.0213 | +| value_loss | 5.35e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1401 | +| iterations | 15337 | +| time_elapsed | 22417 | +| total_timesteps | 31410176 | +| train/ | | +| approx_kl | 0.012954815 | +| clip_fraction | 0.315 | +| clip_range | 0.0671 | +| entropy_loss | -5.79 | +| explained_variance | 0.597 | +| learning_rate | 4.25e-05 | +| loss | -0.0253 | +| n_updates | 77164 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000148 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1401 | +| iterations | 15338 | +| time_elapsed | 22418 | +| total_timesteps | 31412224 | +| train/ | | +| approx_kl | 0.015059618 | +| clip_fraction | 0.35 | +| clip_range | 0.0671 | +| entropy_loss | -6.26 | +| explained_variance | 0.321 | +| learning_rate | 4.25e-05 | +| loss | -0.0273 | +| n_updates | 77168 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000149 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1401 | +| iterations | 15339 | +| time_elapsed | 22420 | +| total_timesteps | 31414272 | +| train/ | | +| approx_kl | 0.011704384 | +| clip_fraction | 0.31 | +| clip_range | 0.0671 | +| entropy_loss | -6.43 | +| explained_variance | 0.567 | +| learning_rate | 4.25e-05 | +| loss | -0.0275 | +| n_updates | 77172 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000105 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1401 | +| iterations | 15340 | +| time_elapsed | 22421 | +| total_timesteps | 31416320 | +| train/ | | +| approx_kl | 0.0152330445 | +| clip_fraction | 0.344 | +| clip_range | 0.0671 | +| entropy_loss | -5.74 | +| explained_variance | 0.39 | +| learning_rate | 4.25e-05 | +| loss | -0.0248 | +| n_updates | 77176 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.00019 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1401 | +| iterations | 15341 | +| time_elapsed | 22423 | +| total_timesteps | 31418368 | +| train/ | | +| approx_kl | 0.014199782 | +| clip_fraction | 0.351 | +| clip_range | 0.0671 | +| entropy_loss | -6.41 | +| explained_variance | 0.364 | +| learning_rate | 4.25e-05 | +| loss | -0.0302 | +| n_updates | 77180 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000113 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1401 | +| iterations | 15342 | +| time_elapsed | 22424 | +| total_timesteps | 31420416 | +| train/ | | +| approx_kl | 0.011340596 | +| clip_fraction | 0.309 | +| clip_range | 0.0671 | +| entropy_loss | -6.38 | +| explained_variance | 0.582 | +| learning_rate | 4.25e-05 | +| loss | -0.0273 | +| n_updates | 77184 | +| policy_gradient_loss | -0.017 | +| value_loss | 9.4e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1401 | +| iterations | 15343 | +| time_elapsed | 22426 | +| total_timesteps | 31422464 | +| train/ | | +| approx_kl | 0.012682132 | +| clip_fraction | 0.337 | +| clip_range | 0.0671 | +| entropy_loss | -6.25 | +| explained_variance | 0.334 | +| learning_rate | 4.25e-05 | +| loss | -0.0296 | +| n_updates | 77188 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.00013 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1401 | +| iterations | 15344 | +| time_elapsed | 22427 | +| total_timesteps | 31424512 | +| train/ | | +| approx_kl | 0.011430764 | +| clip_fraction | 0.302 | +| clip_range | 0.0671 | +| entropy_loss | -5.99 | +| explained_variance | 0.296 | +| learning_rate | 4.25e-05 | +| loss | -0.0199 | +| n_updates | 77192 | +| policy_gradient_loss | -0.0143 | +| value_loss | 0.000272 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1401 | +| iterations | 15345 | +| time_elapsed | 22429 | +| total_timesteps | 31426560 | +| train/ | | +| approx_kl | 0.01330632 | +| clip_fraction | 0.368 | +| clip_range | 0.0671 | +| entropy_loss | -5.78 | +| explained_variance | 0.667 | +| learning_rate | 4.25e-05 | +| loss | -0.0355 | +| n_updates | 77196 | +| policy_gradient_loss | -0.0215 | +| value_loss | 7.51e-05 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1401 | +| iterations | 15346 | +| time_elapsed | 22431 | +| total_timesteps | 31428608 | +| train/ | | +| approx_kl | 0.0136251785 | +| clip_fraction | 0.351 | +| clip_range | 0.0671 | +| entropy_loss | -6.45 | +| explained_variance | 0.272 | +| learning_rate | 4.25e-05 | +| loss | -0.0306 | +| n_updates | 77200 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.00015 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1401 | +| iterations | 15347 | +| time_elapsed | 22432 | +| total_timesteps | 31430656 | +| train/ | | +| approx_kl | 0.014156951 | +| clip_fraction | 0.34 | +| clip_range | 0.0671 | +| entropy_loss | -6.39 | +| explained_variance | -0.208 | +| learning_rate | 4.25e-05 | +| loss | -0.034 | +| n_updates | 77204 | +| policy_gradient_loss | -0.0179 | +| value_loss | 9.75e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1401 | +| iterations | 15348 | +| time_elapsed | 22434 | +| total_timesteps | 31432704 | +| train/ | | +| approx_kl | 0.011840823 | +| clip_fraction | 0.335 | +| clip_range | 0.0671 | +| entropy_loss | -6.13 | +| explained_variance | 0.468 | +| learning_rate | 4.25e-05 | +| loss | -0.0249 | +| n_updates | 77208 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000231 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 1401 | +| iterations | 15349 | +| time_elapsed | 22435 | +| total_timesteps | 31434752 | +| train/ | | +| approx_kl | 0.010747147 | +| clip_fraction | 0.302 | +| clip_range | 0.0671 | +| entropy_loss | -5.53 | +| explained_variance | 0.396 | +| learning_rate | 4.25e-05 | +| loss | -0.0296 | +| n_updates | 77212 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000398 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.304 | +| time/ | | +| fps | 1401 | +| iterations | 15350 | +| time_elapsed | 22437 | +| total_timesteps | 31436800 | +| train/ | | +| approx_kl | 0.010558389 | +| clip_fraction | 0.335 | +| clip_range | 0.0671 | +| entropy_loss | -5.57 | +| explained_variance | 0.617 | +| learning_rate | 4.25e-05 | +| loss | -0.0361 | +| n_updates | 77216 | +| policy_gradient_loss | -0.0199 | +| value_loss | 8.85e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1401 | +| iterations | 15351 | +| time_elapsed | 22438 | +| total_timesteps | 31438848 | +| train/ | | +| approx_kl | 0.011645825 | +| clip_fraction | 0.365 | +| clip_range | 0.0671 | +| entropy_loss | -6.03 | +| explained_variance | 0.569 | +| learning_rate | 4.25e-05 | +| loss | -0.035 | +| n_updates | 77220 | +| policy_gradient_loss | -0.0209 | +| value_loss | 8.83e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1401 | +| iterations | 15352 | +| time_elapsed | 22440 | +| total_timesteps | 31440896 | +| train/ | | +| approx_kl | 0.012964312 | +| clip_fraction | 0.313 | +| clip_range | 0.0671 | +| entropy_loss | -5.88 | +| explained_variance | 0.398 | +| learning_rate | 4.25e-05 | +| loss | -0.0217 | +| n_updates | 77224 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000301 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1401 | +| iterations | 15353 | +| time_elapsed | 22442 | +| total_timesteps | 31442944 | +| train/ | | +| approx_kl | 0.012632439 | +| clip_fraction | 0.338 | +| clip_range | 0.0671 | +| entropy_loss | -5.78 | +| explained_variance | 0.463 | +| learning_rate | 4.25e-05 | +| loss | -0.028 | +| n_updates | 77228 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000199 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1401 | +| iterations | 15354 | +| time_elapsed | 22443 | +| total_timesteps | 31444992 | +| train/ | | +| approx_kl | 0.014967915 | +| clip_fraction | 0.33 | +| clip_range | 0.0671 | +| entropy_loss | -6.39 | +| explained_variance | 0.138 | +| learning_rate | 4.25e-05 | +| loss | -0.0269 | +| n_updates | 77232 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000188 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1401 | +| iterations | 15355 | +| time_elapsed | 22445 | +| total_timesteps | 31447040 | +| train/ | | +| approx_kl | 0.011628134 | +| clip_fraction | 0.328 | +| clip_range | 0.0671 | +| entropy_loss | -6.7 | +| explained_variance | -0.107 | +| learning_rate | 4.25e-05 | +| loss | -0.0331 | +| n_updates | 77236 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000197 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1401 | +| iterations | 15356 | +| time_elapsed | 22446 | +| total_timesteps | 31449088 | +| train/ | | +| approx_kl | 0.011383459 | +| clip_fraction | 0.336 | +| clip_range | 0.0671 | +| entropy_loss | -6.86 | +| explained_variance | -0.0764 | +| learning_rate | 4.25e-05 | +| loss | -0.0227 | +| n_updates | 77240 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000249 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1401 | +| iterations | 15357 | +| time_elapsed | 22448 | +| total_timesteps | 31451136 | +| train/ | | +| approx_kl | 0.012210779 | +| clip_fraction | 0.311 | +| clip_range | 0.0671 | +| entropy_loss | -6.2 | +| explained_variance | 0.469 | +| learning_rate | 4.25e-05 | +| loss | -0.0251 | +| n_updates | 77244 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.00025 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1401 | +| iterations | 15358 | +| time_elapsed | 22449 | +| total_timesteps | 31453184 | +| train/ | | +| approx_kl | 0.011636741 | +| clip_fraction | 0.285 | +| clip_range | 0.0671 | +| entropy_loss | -6.42 | +| explained_variance | 0.161 | +| learning_rate | 4.25e-05 | +| loss | -0.0266 | +| n_updates | 77248 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000458 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1401 | +| iterations | 15359 | +| time_elapsed | 22451 | +| total_timesteps | 31455232 | +| train/ | | +| approx_kl | 0.010610394 | +| clip_fraction | 0.318 | +| clip_range | 0.0671 | +| entropy_loss | -5.14 | +| explained_variance | 0.575 | +| learning_rate | 4.25e-05 | +| loss | -0.0221 | +| n_updates | 77252 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000284 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1401 | +| iterations | 15360 | +| time_elapsed | 22452 | +| total_timesteps | 31457280 | +| train/ | | +| approx_kl | 0.013540967 | +| clip_fraction | 0.363 | +| clip_range | 0.0671 | +| entropy_loss | -5.7 | +| explained_variance | 0.422 | +| learning_rate | 4.25e-05 | +| loss | -0.0322 | +| n_updates | 77256 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000213 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1401 | +| iterations | 15361 | +| time_elapsed | 22454 | +| total_timesteps | 31459328 | +| train/ | | +| approx_kl | 0.012739945 | +| clip_fraction | 0.375 | +| clip_range | 0.0671 | +| entropy_loss | -6.56 | +| explained_variance | -0.151 | +| learning_rate | 4.25e-05 | +| loss | -0.0397 | +| n_updates | 77260 | +| policy_gradient_loss | -0.0234 | +| value_loss | 7.7e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1401 | +| iterations | 15362 | +| time_elapsed | 22455 | +| total_timesteps | 31461376 | +| train/ | | +| approx_kl | 0.014253263 | +| clip_fraction | 0.353 | +| clip_range | 0.0671 | +| entropy_loss | -6.42 | +| explained_variance | 0.336 | +| learning_rate | 4.25e-05 | +| loss | -0.0321 | +| n_updates | 77264 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000177 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1401 | +| iterations | 15363 | +| time_elapsed | 22457 | +| total_timesteps | 31463424 | +| train/ | | +| approx_kl | 0.011788657 | +| clip_fraction | 0.341 | +| clip_range | 0.0671 | +| entropy_loss | -6.11 | +| explained_variance | 0.585 | +| learning_rate | 4.25e-05 | +| loss | -0.0302 | +| n_updates | 77268 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.00014 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1401 | +| iterations | 15364 | +| time_elapsed | 22458 | +| total_timesteps | 31465472 | +| train/ | | +| approx_kl | 0.014485416 | +| clip_fraction | 0.332 | +| clip_range | 0.0671 | +| entropy_loss | -5.82 | +| explained_variance | 0.36 | +| learning_rate | 4.25e-05 | +| loss | -0.0268 | +| n_updates | 77272 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000119 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1401 | +| iterations | 15365 | +| time_elapsed | 22460 | +| total_timesteps | 31467520 | +| train/ | | +| approx_kl | 0.015409143 | +| clip_fraction | 0.337 | +| clip_range | 0.0671 | +| entropy_loss | -6.47 | +| explained_variance | -0.213 | +| learning_rate | 4.25e-05 | +| loss | -0.0237 | +| n_updates | 77276 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.00012 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1401 | +| iterations | 15366 | +| time_elapsed | 22461 | +| total_timesteps | 31469568 | +| train/ | | +| approx_kl | 0.014359979 | +| clip_fraction | 0.352 | +| clip_range | 0.0671 | +| entropy_loss | -6.59 | +| explained_variance | 0.386 | +| learning_rate | 4.25e-05 | +| loss | -0.027 | +| n_updates | 77280 | +| policy_gradient_loss | -0.0204 | +| value_loss | 8.12e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 1401 | +| iterations | 15367 | +| time_elapsed | 22463 | +| total_timesteps | 31471616 | +| train/ | | +| approx_kl | 0.01176974 | +| clip_fraction | 0.309 | +| clip_range | 0.0671 | +| entropy_loss | -6.44 | +| explained_variance | 0.291 | +| learning_rate | 4.25e-05 | +| loss | -0.0267 | +| n_updates | 77284 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.000209 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1401 | +| iterations | 15368 | +| time_elapsed | 22464 | +| total_timesteps | 31473664 | +| train/ | | +| approx_kl | 0.017567892 | +| clip_fraction | 0.344 | +| clip_range | 0.0671 | +| entropy_loss | -5.83 | +| explained_variance | 0.656 | +| learning_rate | 4.25e-05 | +| loss | -0.0327 | +| n_updates | 77288 | +| policy_gradient_loss | -0.0183 | +| value_loss | 7.23e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1401 | +| iterations | 15369 | +| time_elapsed | 22466 | +| total_timesteps | 31475712 | +| train/ | | +| approx_kl | 0.012475966 | +| clip_fraction | 0.335 | +| clip_range | 0.0671 | +| entropy_loss | -6.18 | +| explained_variance | 0.525 | +| learning_rate | 4.25e-05 | +| loss | -0.0291 | +| n_updates | 77292 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000148 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1401 | +| iterations | 15370 | +| time_elapsed | 22467 | +| total_timesteps | 31477760 | +| train/ | | +| approx_kl | 0.011244919 | +| clip_fraction | 0.315 | +| clip_range | 0.0671 | +| entropy_loss | -6.02 | +| explained_variance | 0.618 | +| learning_rate | 4.25e-05 | +| loss | -0.0263 | +| n_updates | 77296 | +| policy_gradient_loss | -0.0177 | +| value_loss | 8.97e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1401 | +| iterations | 15371 | +| time_elapsed | 22469 | +| total_timesteps | 31479808 | +| train/ | | +| approx_kl | 0.011845669 | +| clip_fraction | 0.338 | +| clip_range | 0.0671 | +| entropy_loss | -5.55 | +| explained_variance | 0.786 | +| learning_rate | 4.25e-05 | +| loss | -0.0296 | +| n_updates | 77300 | +| policy_gradient_loss | -0.0181 | +| value_loss | 5.93e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1401 | +| iterations | 15372 | +| time_elapsed | 22470 | +| total_timesteps | 31481856 | +| train/ | | +| approx_kl | 0.014821429 | +| clip_fraction | 0.326 | +| clip_range | 0.0671 | +| entropy_loss | -6.29 | +| explained_variance | 0.317 | +| learning_rate | 4.25e-05 | +| loss | -0.0278 | +| n_updates | 77304 | +| policy_gradient_loss | -0.0177 | +| value_loss | 9.35e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1400 | +| iterations | 15373 | +| time_elapsed | 22472 | +| total_timesteps | 31483904 | +| train/ | | +| approx_kl | 0.01220954 | +| clip_fraction | 0.329 | +| clip_range | 0.0671 | +| entropy_loss | -6.99 | +| explained_variance | -0.0548 | +| learning_rate | 4.25e-05 | +| loss | -0.0245 | +| n_updates | 77308 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000169 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1400 | +| iterations | 15374 | +| time_elapsed | 22474 | +| total_timesteps | 31485952 | +| train/ | | +| approx_kl | 0.009086333 | +| clip_fraction | 0.306 | +| clip_range | 0.0671 | +| entropy_loss | -6.71 | +| explained_variance | 0.351 | +| learning_rate | 4.25e-05 | +| loss | -0.0235 | +| n_updates | 77312 | +| policy_gradient_loss | -0.0136 | +| value_loss | 0.000273 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1400 | +| iterations | 15375 | +| time_elapsed | 22475 | +| total_timesteps | 31488000 | +| train/ | | +| approx_kl | 0.011223712 | +| clip_fraction | 0.336 | +| clip_range | 0.0671 | +| entropy_loss | -6.25 | +| explained_variance | 0.328 | +| learning_rate | 4.25e-05 | +| loss | -0.0302 | +| n_updates | 77316 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000152 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1400 | +| iterations | 15376 | +| time_elapsed | 22477 | +| total_timesteps | 31490048 | +| train/ | | +| approx_kl | 0.012410643 | +| clip_fraction | 0.313 | +| clip_range | 0.0671 | +| entropy_loss | -6.35 | +| explained_variance | 0.322 | +| learning_rate | 4.25e-05 | +| loss | -0.0238 | +| n_updates | 77320 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000136 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1400 | +| iterations | 15377 | +| time_elapsed | 22478 | +| total_timesteps | 31492096 | +| train/ | | +| approx_kl | 0.013196676 | +| clip_fraction | 0.329 | +| clip_range | 0.0671 | +| entropy_loss | -5.63 | +| explained_variance | 0.58 | +| learning_rate | 4.25e-05 | +| loss | -0.0201 | +| n_updates | 77324 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000191 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1400 | +| iterations | 15378 | +| time_elapsed | 22480 | +| total_timesteps | 31494144 | +| train/ | | +| approx_kl | 0.015096371 | +| clip_fraction | 0.326 | +| clip_range | 0.0671 | +| entropy_loss | -6.18 | +| explained_variance | 0.312 | +| learning_rate | 4.25e-05 | +| loss | -0.0276 | +| n_updates | 77328 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000116 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1400 | +| iterations | 15379 | +| time_elapsed | 22481 | +| total_timesteps | 31496192 | +| train/ | | +| approx_kl | 0.017130796 | +| clip_fraction | 0.334 | +| clip_range | 0.0671 | +| entropy_loss | -6.04 | +| explained_variance | 0.62 | +| learning_rate | 4.25e-05 | +| loss | -0.0215 | +| n_updates | 77332 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000101 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1400 | +| iterations | 15380 | +| time_elapsed | 22483 | +| total_timesteps | 31498240 | +| train/ | | +| approx_kl | 0.01437949 | +| clip_fraction | 0.34 | +| clip_range | 0.0671 | +| entropy_loss | -6.39 | +| explained_variance | 0.308 | +| learning_rate | 4.25e-05 | +| loss | -0.03 | +| n_updates | 77336 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000148 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1400 | +| iterations | 15381 | +| time_elapsed | 22484 | +| total_timesteps | 31500288 | +| train/ | | +| approx_kl | 0.010249207 | +| clip_fraction | 0.311 | +| clip_range | 0.0671 | +| entropy_loss | -6.36 | +| explained_variance | 0.301 | +| learning_rate | 4.25e-05 | +| loss | -0.0254 | +| n_updates | 77340 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000143 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1400 | +| iterations | 15382 | +| time_elapsed | 22486 | +| total_timesteps | 31502336 | +| train/ | | +| approx_kl | 0.011284066 | +| clip_fraction | 0.312 | +| clip_range | 0.0671 | +| entropy_loss | -6.16 | +| explained_variance | 0.608 | +| learning_rate | 4.25e-05 | +| loss | -0.0322 | +| n_updates | 77344 | +| policy_gradient_loss | -0.0174 | +| value_loss | 9.85e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1400 | +| iterations | 15383 | +| time_elapsed | 22487 | +| total_timesteps | 31504384 | +| train/ | | +| approx_kl | 0.01266147 | +| clip_fraction | 0.335 | +| clip_range | 0.0671 | +| entropy_loss | -5.99 | +| explained_variance | 0.469 | +| learning_rate | 4.25e-05 | +| loss | -0.0311 | +| n_updates | 77348 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000108 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1400 | +| iterations | 15384 | +| time_elapsed | 22489 | +| total_timesteps | 31506432 | +| train/ | | +| approx_kl | 0.013032271 | +| clip_fraction | 0.368 | +| clip_range | 0.0671 | +| entropy_loss | -6.14 | +| explained_variance | 0.595 | +| learning_rate | 4.25e-05 | +| loss | -0.0323 | +| n_updates | 77352 | +| policy_gradient_loss | -0.0209 | +| value_loss | 9.57e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1400 | +| iterations | 15385 | +| time_elapsed | 22490 | +| total_timesteps | 31508480 | +| train/ | | +| approx_kl | 0.018923387 | +| clip_fraction | 0.318 | +| clip_range | 0.0671 | +| entropy_loss | -6.28 | +| explained_variance | 0.346 | +| learning_rate | 4.25e-05 | +| loss | -0.0237 | +| n_updates | 77356 | +| policy_gradient_loss | -0.0153 | +| value_loss | 8.91e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1400 | +| iterations | 15386 | +| time_elapsed | 22492 | +| total_timesteps | 31510528 | +| train/ | | +| approx_kl | 0.014348367 | +| clip_fraction | 0.329 | +| clip_range | 0.0671 | +| entropy_loss | -5.66 | +| explained_variance | 0.778 | +| learning_rate | 4.25e-05 | +| loss | -0.0256 | +| n_updates | 77360 | +| policy_gradient_loss | -0.0165 | +| value_loss | 9.02e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1400 | +| iterations | 15387 | +| time_elapsed | 22493 | +| total_timesteps | 31512576 | +| train/ | | +| approx_kl | 0.01311741 | +| clip_fraction | 0.36 | +| clip_range | 0.0671 | +| entropy_loss | -6.05 | +| explained_variance | -0.0374 | +| learning_rate | 4.25e-05 | +| loss | -0.0358 | +| n_updates | 77364 | +| policy_gradient_loss | -0.0219 | +| value_loss | 4.12e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1400 | +| iterations | 15388 | +| time_elapsed | 22495 | +| total_timesteps | 31514624 | +| train/ | | +| approx_kl | 0.012633368 | +| clip_fraction | 0.328 | +| clip_range | 0.0671 | +| entropy_loss | -6.1 | +| explained_variance | 0.42 | +| learning_rate | 4.25e-05 | +| loss | -0.0263 | +| n_updates | 77368 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000292 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1400 | +| iterations | 15389 | +| time_elapsed | 22497 | +| total_timesteps | 31516672 | +| train/ | | +| approx_kl | 0.013917197 | +| clip_fraction | 0.337 | +| clip_range | 0.0671 | +| entropy_loss | -5.74 | +| explained_variance | 0.526 | +| learning_rate | 4.25e-05 | +| loss | -0.0253 | +| n_updates | 77372 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000164 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1400 | +| iterations | 15390 | +| time_elapsed | 22498 | +| total_timesteps | 31518720 | +| train/ | | +| approx_kl | 0.017451556 | +| clip_fraction | 0.339 | +| clip_range | 0.0671 | +| entropy_loss | -6.04 | +| explained_variance | 0.0355 | +| learning_rate | 4.25e-05 | +| loss | -0.0239 | +| n_updates | 77376 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000335 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1400 | +| iterations | 15391 | +| time_elapsed | 22500 | +| total_timesteps | 31520768 | +| train/ | | +| approx_kl | 0.014885121 | +| clip_fraction | 0.338 | +| clip_range | 0.0671 | +| entropy_loss | -6.73 | +| explained_variance | 0.15 | +| learning_rate | 4.25e-05 | +| loss | -0.0279 | +| n_updates | 77380 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000122 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1400 | +| iterations | 15392 | +| time_elapsed | 22501 | +| total_timesteps | 31522816 | +| train/ | | +| approx_kl | 0.01631318 | +| clip_fraction | 0.325 | +| clip_range | 0.0671 | +| entropy_loss | -6.71 | +| explained_variance | 0.28 | +| learning_rate | 4.25e-05 | +| loss | -0.0304 | +| n_updates | 77384 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.00016 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1400 | +| iterations | 15393 | +| time_elapsed | 22503 | +| total_timesteps | 31524864 | +| train/ | | +| approx_kl | 0.0124274455 | +| clip_fraction | 0.326 | +| clip_range | 0.0671 | +| entropy_loss | -6.16 | +| explained_variance | 0.563 | +| learning_rate | 4.25e-05 | +| loss | -0.0312 | +| n_updates | 77388 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000114 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1400 | +| iterations | 15394 | +| time_elapsed | 22504 | +| total_timesteps | 31526912 | +| train/ | | +| approx_kl | 0.011923576 | +| clip_fraction | 0.315 | +| clip_range | 0.0671 | +| entropy_loss | -5.95 | +| explained_variance | 0.434 | +| learning_rate | 4.25e-05 | +| loss | -0.031 | +| n_updates | 77392 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000125 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1400 | +| iterations | 15395 | +| time_elapsed | 22506 | +| total_timesteps | 31528960 | +| train/ | | +| approx_kl | 0.01033324 | +| clip_fraction | 0.312 | +| clip_range | 0.0671 | +| entropy_loss | -5.59 | +| explained_variance | 0.714 | +| learning_rate | 4.25e-05 | +| loss | -0.0275 | +| n_updates | 77396 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.0001 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1400 | +| iterations | 15396 | +| time_elapsed | 22507 | +| total_timesteps | 31531008 | +| train/ | | +| approx_kl | 0.010195084 | +| clip_fraction | 0.312 | +| clip_range | 0.0671 | +| entropy_loss | -6.25 | +| explained_variance | 0.207 | +| learning_rate | 4.25e-05 | +| loss | -0.0213 | +| n_updates | 77400 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000404 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1400 | +| iterations | 15397 | +| time_elapsed | 22509 | +| total_timesteps | 31533056 | +| train/ | | +| approx_kl | 0.012022393 | +| clip_fraction | 0.303 | +| clip_range | 0.0671 | +| entropy_loss | -6.28 | +| explained_variance | 0.384 | +| learning_rate | 4.25e-05 | +| loss | -0.0257 | +| n_updates | 77404 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000251 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1400 | +| iterations | 15398 | +| time_elapsed | 22510 | +| total_timesteps | 31535104 | +| train/ | | +| approx_kl | 0.013301097 | +| clip_fraction | 0.356 | +| clip_range | 0.0671 | +| entropy_loss | -6.45 | +| explained_variance | 0.294 | +| learning_rate | 4.25e-05 | +| loss | -0.0323 | +| n_updates | 77408 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000145 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1400 | +| iterations | 15399 | +| time_elapsed | 22512 | +| total_timesteps | 31537152 | +| train/ | | +| approx_kl | 0.012037418 | +| clip_fraction | 0.318 | +| clip_range | 0.0671 | +| entropy_loss | -6.11 | +| explained_variance | 0.468 | +| learning_rate | 4.25e-05 | +| loss | -0.0175 | +| n_updates | 77412 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000183 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1400 | +| iterations | 15400 | +| time_elapsed | 22513 | +| total_timesteps | 31539200 | +| train/ | | +| approx_kl | 0.012854021 | +| clip_fraction | 0.36 | +| clip_range | 0.0671 | +| entropy_loss | -6.11 | +| explained_variance | 0.318 | +| learning_rate | 4.25e-05 | +| loss | -0.0334 | +| n_updates | 77416 | +| policy_gradient_loss | -0.0213 | +| value_loss | 9.59e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1400 | +| iterations | 15401 | +| time_elapsed | 22515 | +| total_timesteps | 31541248 | +| train/ | | +| approx_kl | 0.012508656 | +| clip_fraction | 0.311 | +| clip_range | 0.0671 | +| entropy_loss | -6.57 | +| explained_variance | 0.245 | +| learning_rate | 4.25e-05 | +| loss | -0.0297 | +| n_updates | 77420 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000165 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1400 | +| iterations | 15402 | +| time_elapsed | 22516 | +| total_timesteps | 31543296 | +| train/ | | +| approx_kl | 0.011218581 | +| clip_fraction | 0.316 | +| clip_range | 0.0671 | +| entropy_loss | -6.23 | +| explained_variance | 0.602 | +| learning_rate | 4.25e-05 | +| loss | -0.0255 | +| n_updates | 77424 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000143 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1400 | +| iterations | 15403 | +| time_elapsed | 22518 | +| total_timesteps | 31545344 | +| train/ | | +| approx_kl | 0.009236339 | +| clip_fraction | 0.297 | +| clip_range | 0.0671 | +| entropy_loss | -6.43 | +| explained_variance | 0.309 | +| learning_rate | 4.25e-05 | +| loss | -0.0285 | +| n_updates | 77428 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000364 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1400 | +| iterations | 15404 | +| time_elapsed | 22519 | +| total_timesteps | 31547392 | +| train/ | | +| approx_kl | 0.0100041125 | +| clip_fraction | 0.305 | +| clip_range | 0.0671 | +| entropy_loss | -6.07 | +| explained_variance | 0.53 | +| learning_rate | 4.25e-05 | +| loss | -0.0311 | +| n_updates | 77432 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000131 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1400 | +| iterations | 15405 | +| time_elapsed | 22521 | +| total_timesteps | 31549440 | +| train/ | | +| approx_kl | 0.010540314 | +| clip_fraction | 0.329 | +| clip_range | 0.0671 | +| entropy_loss | -6 | +| explained_variance | 0.508 | +| learning_rate | 4.25e-05 | +| loss | -0.0289 | +| n_updates | 77436 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.0002 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1400 | +| iterations | 15406 | +| time_elapsed | 22522 | +| total_timesteps | 31551488 | +| train/ | | +| approx_kl | 0.015111197 | +| clip_fraction | 0.353 | +| clip_range | 0.0671 | +| entropy_loss | -6.5 | +| explained_variance | -0.407 | +| learning_rate | 4.25e-05 | +| loss | -0.033 | +| n_updates | 77440 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000104 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1400 | +| iterations | 15407 | +| time_elapsed | 22524 | +| total_timesteps | 31553536 | +| train/ | | +| approx_kl | 0.012278213 | +| clip_fraction | 0.328 | +| clip_range | 0.0671 | +| entropy_loss | -6.25 | +| explained_variance | 0.585 | +| learning_rate | 4.25e-05 | +| loss | -0.0295 | +| n_updates | 77444 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000106 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1400 | +| iterations | 15408 | +| time_elapsed | 22525 | +| total_timesteps | 31555584 | +| train/ | | +| approx_kl | 0.011129385 | +| clip_fraction | 0.331 | +| clip_range | 0.0671 | +| entropy_loss | -6.37 | +| explained_variance | 0.275 | +| learning_rate | 4.25e-05 | +| loss | -0.0293 | +| n_updates | 77448 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000252 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1400 | +| iterations | 15409 | +| time_elapsed | 22527 | +| total_timesteps | 31557632 | +| train/ | | +| approx_kl | 0.0078807045 | +| clip_fraction | 0.311 | +| clip_range | 0.0671 | +| entropy_loss | -6.61 | +| explained_variance | 0.245 | +| learning_rate | 4.25e-05 | +| loss | -0.0231 | +| n_updates | 77452 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000401 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1400 | +| iterations | 15410 | +| time_elapsed | 22528 | +| total_timesteps | 31559680 | +| train/ | | +| approx_kl | 0.012801288 | +| clip_fraction | 0.361 | +| clip_range | 0.0671 | +| entropy_loss | -6.29 | +| explained_variance | 0.389 | +| learning_rate | 4.25e-05 | +| loss | -0.0296 | +| n_updates | 77456 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000214 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1400 | +| iterations | 15411 | +| time_elapsed | 22530 | +| total_timesteps | 31561728 | +| train/ | | +| approx_kl | 0.011814663 | +| clip_fraction | 0.331 | +| clip_range | 0.0671 | +| entropy_loss | -5.55 | +| explained_variance | 0.759 | +| learning_rate | 4.25e-05 | +| loss | -0.031 | +| n_updates | 77460 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000112 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1400 | +| iterations | 15412 | +| time_elapsed | 22532 | +| total_timesteps | 31563776 | +| train/ | | +| approx_kl | 0.015370529 | +| clip_fraction | 0.337 | +| clip_range | 0.0671 | +| entropy_loss | -5.72 | +| explained_variance | 0.663 | +| learning_rate | 4.25e-05 | +| loss | -0.0332 | +| n_updates | 77464 | +| policy_gradient_loss | -0.0197 | +| value_loss | 8.18e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1400 | +| iterations | 15413 | +| time_elapsed | 22533 | +| total_timesteps | 31565824 | +| train/ | | +| approx_kl | 0.01114561 | +| clip_fraction | 0.365 | +| clip_range | 0.0671 | +| entropy_loss | -6.39 | +| explained_variance | 0.278 | +| learning_rate | 4.25e-05 | +| loss | -0.031 | +| n_updates | 77468 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000221 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1400 | +| iterations | 15414 | +| time_elapsed | 22535 | +| total_timesteps | 31567872 | +| train/ | | +| approx_kl | 0.010436006 | +| clip_fraction | 0.338 | +| clip_range | 0.0671 | +| entropy_loss | -6.63 | +| explained_variance | 0.244 | +| learning_rate | 4.25e-05 | +| loss | -0.0255 | +| n_updates | 77472 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.00024 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1400 | +| iterations | 15415 | +| time_elapsed | 22536 | +| total_timesteps | 31569920 | +| train/ | | +| approx_kl | 0.009289233 | +| clip_fraction | 0.306 | +| clip_range | 0.0671 | +| entropy_loss | -6.15 | +| explained_variance | 0.272 | +| learning_rate | 4.25e-05 | +| loss | -0.0196 | +| n_updates | 77476 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.000417 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1400 | +| iterations | 15416 | +| time_elapsed | 22538 | +| total_timesteps | 31571968 | +| train/ | | +| approx_kl | 0.009877855 | +| clip_fraction | 0.294 | +| clip_range | 0.0671 | +| entropy_loss | -5.45 | +| explained_variance | 0.531 | +| learning_rate | 4.25e-05 | +| loss | -0.0284 | +| n_updates | 77480 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000275 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1400 | +| iterations | 15417 | +| time_elapsed | 22539 | +| total_timesteps | 31574016 | +| train/ | | +| approx_kl | 0.010847034 | +| clip_fraction | 0.325 | +| clip_range | 0.0671 | +| entropy_loss | -6.16 | +| explained_variance | -0.0726 | +| learning_rate | 4.25e-05 | +| loss | -0.0299 | +| n_updates | 77484 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000171 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1400 | +| iterations | 15418 | +| time_elapsed | 22541 | +| total_timesteps | 31576064 | +| train/ | | +| approx_kl | 0.0133246705 | +| clip_fraction | 0.345 | +| clip_range | 0.0671 | +| entropy_loss | -6.57 | +| explained_variance | 0.42 | +| learning_rate | 4.25e-05 | +| loss | -0.0361 | +| n_updates | 77488 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000116 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1400 | +| iterations | 15419 | +| time_elapsed | 22542 | +| total_timesteps | 31578112 | +| train/ | | +| approx_kl | 0.011420336 | +| clip_fraction | 0.332 | +| clip_range | 0.0671 | +| entropy_loss | -6.31 | +| explained_variance | 0.559 | +| learning_rate | 4.25e-05 | +| loss | -0.0348 | +| n_updates | 77492 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000112 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1400 | +| iterations | 15420 | +| time_elapsed | 22544 | +| total_timesteps | 31580160 | +| train/ | | +| approx_kl | 0.009855853 | +| clip_fraction | 0.317 | +| clip_range | 0.0671 | +| entropy_loss | -7.01 | +| explained_variance | 0.214 | +| learning_rate | 4.25e-05 | +| loss | -0.0292 | +| n_updates | 77496 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000164 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1400 | +| iterations | 15421 | +| time_elapsed | 22545 | +| total_timesteps | 31582208 | +| train/ | | +| approx_kl | 0.013562851 | +| clip_fraction | 0.327 | +| clip_range | 0.0671 | +| entropy_loss | -6.95 | +| explained_variance | 0.131 | +| learning_rate | 4.25e-05 | +| loss | -0.0286 | +| n_updates | 77500 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000134 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1400 | +| iterations | 15422 | +| time_elapsed | 22547 | +| total_timesteps | 31584256 | +| train/ | | +| approx_kl | 0.015361948 | +| clip_fraction | 0.302 | +| clip_range | 0.0671 | +| entropy_loss | -6.21 | +| explained_variance | 0.373 | +| learning_rate | 4.25e-05 | +| loss | -0.0276 | +| n_updates | 77504 | +| policy_gradient_loss | -0.0146 | +| value_loss | 0.00042 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1400 | +| iterations | 15423 | +| time_elapsed | 22549 | +| total_timesteps | 31586304 | +| train/ | | +| approx_kl | 0.010169624 | +| clip_fraction | 0.297 | +| clip_range | 0.0671 | +| entropy_loss | -4.72 | +| explained_variance | 0.604 | +| learning_rate | 4.25e-05 | +| loss | -0.0181 | +| n_updates | 77508 | +| policy_gradient_loss | -0.0128 | +| value_loss | 0.000257 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1400 | +| iterations | 15424 | +| time_elapsed | 22550 | +| total_timesteps | 31588352 | +| train/ | | +| approx_kl | 0.011815012 | +| clip_fraction | 0.334 | +| clip_range | 0.0671 | +| entropy_loss | -5.16 | +| explained_variance | 0.356 | +| learning_rate | 4.25e-05 | +| loss | -0.0245 | +| n_updates | 77512 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.00028 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1400 | +| iterations | 15425 | +| time_elapsed | 22552 | +| total_timesteps | 31590400 | +| train/ | | +| approx_kl | 0.01141876 | +| clip_fraction | 0.327 | +| clip_range | 0.0671 | +| entropy_loss | -6.04 | +| explained_variance | 0.329 | +| learning_rate | 4.25e-05 | +| loss | -0.0295 | +| n_updates | 77516 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000314 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1400 | +| iterations | 15426 | +| time_elapsed | 22553 | +| total_timesteps | 31592448 | +| train/ | | +| approx_kl | 0.013604695 | +| clip_fraction | 0.374 | +| clip_range | 0.0671 | +| entropy_loss | -6.4 | +| explained_variance | -0.299 | +| learning_rate | 4.25e-05 | +| loss | -0.0383 | +| n_updates | 77520 | +| policy_gradient_loss | -0.0235 | +| value_loss | 0.00011 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1400 | +| iterations | 15427 | +| time_elapsed | 22555 | +| total_timesteps | 31594496 | +| train/ | | +| approx_kl | 0.011809766 | +| clip_fraction | 0.348 | +| clip_range | 0.0671 | +| entropy_loss | -6.75 | +| explained_variance | -0.0218 | +| learning_rate | 4.25e-05 | +| loss | -0.0321 | +| n_updates | 77524 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.00022 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1400 | +| iterations | 15428 | +| time_elapsed | 22556 | +| total_timesteps | 31596544 | +| train/ | | +| approx_kl | 0.013030751 | +| clip_fraction | 0.373 | +| clip_range | 0.0671 | +| entropy_loss | -6.7 | +| explained_variance | -0.193 | +| learning_rate | 4.25e-05 | +| loss | -0.0388 | +| n_updates | 77528 | +| policy_gradient_loss | -0.0223 | +| value_loss | 0.00012 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1400 | +| iterations | 15429 | +| time_elapsed | 22558 | +| total_timesteps | 31598592 | +| train/ | | +| approx_kl | 0.013062934 | +| clip_fraction | 0.374 | +| clip_range | 0.0671 | +| entropy_loss | -6.92 | +| explained_variance | -0.123 | +| learning_rate | 4.25e-05 | +| loss | -0.0375 | +| n_updates | 77532 | +| policy_gradient_loss | -0.0231 | +| value_loss | 9.51e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1400 | +| iterations | 15430 | +| time_elapsed | 22559 | +| total_timesteps | 31600640 | +| train/ | | +| approx_kl | 0.012132734 | +| clip_fraction | 0.318 | +| clip_range | 0.0671 | +| entropy_loss | -6.01 | +| explained_variance | 0.463 | +| learning_rate | 4.25e-05 | +| loss | -0.0273 | +| n_updates | 77536 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000191 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1400 | +| iterations | 15431 | +| time_elapsed | 22561 | +| total_timesteps | 31602688 | +| train/ | | +| approx_kl | 0.012016102 | +| clip_fraction | 0.315 | +| clip_range | 0.0671 | +| entropy_loss | -5.29 | +| explained_variance | 0.395 | +| learning_rate | 4.25e-05 | +| loss | -0.0275 | +| n_updates | 77540 | +| policy_gradient_loss | -0.0142 | +| value_loss | 0.000184 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1400 | +| iterations | 15432 | +| time_elapsed | 22562 | +| total_timesteps | 31604736 | +| train/ | | +| approx_kl | 0.015576505 | +| clip_fraction | 0.359 | +| clip_range | 0.0671 | +| entropy_loss | -5.91 | +| explained_variance | 0.498 | +| learning_rate | 4.25e-05 | +| loss | -0.0292 | +| n_updates | 77544 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000144 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1400 | +| iterations | 15433 | +| time_elapsed | 22564 | +| total_timesteps | 31606784 | +| train/ | | +| approx_kl | 0.012479816 | +| clip_fraction | 0.34 | +| clip_range | 0.0671 | +| entropy_loss | -6.3 | +| explained_variance | 0.631 | +| learning_rate | 4.25e-05 | +| loss | -0.0357 | +| n_updates | 77548 | +| policy_gradient_loss | -0.0207 | +| value_loss | 9.15e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1400 | +| iterations | 15434 | +| time_elapsed | 22565 | +| total_timesteps | 31608832 | +| train/ | | +| approx_kl | 0.013814384 | +| clip_fraction | 0.363 | +| clip_range | 0.0671 | +| entropy_loss | -6.14 | +| explained_variance | 0.124 | +| learning_rate | 4.25e-05 | +| loss | -0.0296 | +| n_updates | 77552 | +| policy_gradient_loss | -0.0194 | +| value_loss | 8.83e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1400 | +| iterations | 15435 | +| time_elapsed | 22567 | +| total_timesteps | 31610880 | +| train/ | | +| approx_kl | 0.013083879 | +| clip_fraction | 0.344 | +| clip_range | 0.0671 | +| entropy_loss | -5.35 | +| explained_variance | 0.709 | +| learning_rate | 4.25e-05 | +| loss | -0.0291 | +| n_updates | 77556 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000132 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1400 | +| iterations | 15436 | +| time_elapsed | 22569 | +| total_timesteps | 31612928 | +| train/ | | +| approx_kl | 0.018351361 | +| clip_fraction | 0.366 | +| clip_range | 0.0671 | +| entropy_loss | -5.74 | +| explained_variance | 0.379 | +| learning_rate | 4.25e-05 | +| loss | -0.0345 | +| n_updates | 77560 | +| policy_gradient_loss | -0.0207 | +| value_loss | 9.86e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1400 | +| iterations | 15437 | +| time_elapsed | 22570 | +| total_timesteps | 31614976 | +| train/ | | +| approx_kl | 0.01684776 | +| clip_fraction | 0.365 | +| clip_range | 0.0671 | +| entropy_loss | -6.14 | +| explained_variance | 0.349 | +| learning_rate | 4.25e-05 | +| loss | -0.0292 | +| n_updates | 77564 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000121 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1400 | +| iterations | 15438 | +| time_elapsed | 22572 | +| total_timesteps | 31617024 | +| train/ | | +| approx_kl | 0.013983766 | +| clip_fraction | 0.365 | +| clip_range | 0.0671 | +| entropy_loss | -6.83 | +| explained_variance | -0.0485 | +| learning_rate | 4.25e-05 | +| loss | -0.0285 | +| n_updates | 77568 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000158 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1400 | +| iterations | 15439 | +| time_elapsed | 22573 | +| total_timesteps | 31619072 | +| train/ | | +| approx_kl | 0.012023672 | +| clip_fraction | 0.311 | +| clip_range | 0.0671 | +| entropy_loss | -6.45 | +| explained_variance | 0.46 | +| learning_rate | 4.25e-05 | +| loss | -0.0255 | +| n_updates | 77572 | +| policy_gradient_loss | -0.0147 | +| value_loss | 0.000236 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1400 | +| iterations | 15440 | +| time_elapsed | 22575 | +| total_timesteps | 31621120 | +| train/ | | +| approx_kl | 0.014336199 | +| clip_fraction | 0.341 | +| clip_range | 0.0671 | +| entropy_loss | -6.57 | +| explained_variance | -0.055 | +| learning_rate | 4.25e-05 | +| loss | -0.025 | +| n_updates | 77576 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000131 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1400 | +| iterations | 15441 | +| time_elapsed | 22576 | +| total_timesteps | 31623168 | +| train/ | | +| approx_kl | 0.010378313 | +| clip_fraction | 0.308 | +| clip_range | 0.0671 | +| entropy_loss | -5.52 | +| explained_variance | 0.46 | +| learning_rate | 4.25e-05 | +| loss | -0.0183 | +| n_updates | 77580 | +| policy_gradient_loss | -0.0128 | +| value_loss | 0.000331 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1400 | +| iterations | 15442 | +| time_elapsed | 22578 | +| total_timesteps | 31625216 | +| train/ | | +| approx_kl | 0.011698712 | +| clip_fraction | 0.309 | +| clip_range | 0.0671 | +| entropy_loss | -5.57 | +| explained_variance | 0.562 | +| learning_rate | 4.25e-05 | +| loss | -0.0285 | +| n_updates | 77584 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000112 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1400 | +| iterations | 15443 | +| time_elapsed | 22579 | +| total_timesteps | 31627264 | +| train/ | | +| approx_kl | 0.013280725 | +| clip_fraction | 0.339 | +| clip_range | 0.0671 | +| entropy_loss | -6.25 | +| explained_variance | 0.375 | +| learning_rate | 4.25e-05 | +| loss | -0.0326 | +| n_updates | 77588 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000183 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1400 | +| iterations | 15444 | +| time_elapsed | 22581 | +| total_timesteps | 31629312 | +| train/ | | +| approx_kl | 0.012820977 | +| clip_fraction | 0.331 | +| clip_range | 0.0671 | +| entropy_loss | -6.27 | +| explained_variance | 0.38 | +| learning_rate | 4.25e-05 | +| loss | -0.0293 | +| n_updates | 77592 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000178 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1400 | +| iterations | 15445 | +| time_elapsed | 22583 | +| total_timesteps | 31631360 | +| train/ | | +| approx_kl | 0.013028271 | +| clip_fraction | 0.358 | +| clip_range | 0.0671 | +| entropy_loss | -6.24 | +| explained_variance | 0.173 | +| learning_rate | 4.25e-05 | +| loss | -0.0303 | +| n_updates | 77596 | +| policy_gradient_loss | -0.0198 | +| value_loss | 9.55e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1400 | +| iterations | 15446 | +| time_elapsed | 22584 | +| total_timesteps | 31633408 | +| train/ | | +| approx_kl | 0.015700128 | +| clip_fraction | 0.385 | +| clip_range | 0.0671 | +| entropy_loss | -5.99 | +| explained_variance | 0.628 | +| learning_rate | 4.25e-05 | +| loss | -0.0336 | +| n_updates | 77600 | +| policy_gradient_loss | -0.0205 | +| value_loss | 9.31e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1400 | +| iterations | 15447 | +| time_elapsed | 22586 | +| total_timesteps | 31635456 | +| train/ | | +| approx_kl | 0.013066413 | +| clip_fraction | 0.341 | +| clip_range | 0.0671 | +| entropy_loss | -6.2 | +| explained_variance | 0.584 | +| learning_rate | 4.25e-05 | +| loss | -0.016 | +| n_updates | 77604 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000111 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1400 | +| iterations | 15448 | +| time_elapsed | 22587 | +| total_timesteps | 31637504 | +| train/ | | +| approx_kl | 0.013892211 | +| clip_fraction | 0.288 | +| clip_range | 0.0671 | +| entropy_loss | -5.9 | +| explained_variance | 0.375 | +| learning_rate | 4.25e-05 | +| loss | -0.0225 | +| n_updates | 77608 | +| policy_gradient_loss | -0.0141 | +| value_loss | 0.000268 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1400 | +| iterations | 15449 | +| time_elapsed | 22589 | +| total_timesteps | 31639552 | +| train/ | | +| approx_kl | 0.010619472 | +| clip_fraction | 0.316 | +| clip_range | 0.0671 | +| entropy_loss | -5.83 | +| explained_variance | 0.558 | +| learning_rate | 4.25e-05 | +| loss | -0.0336 | +| n_updates | 77612 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000167 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1400 | +| iterations | 15450 | +| time_elapsed | 22590 | +| total_timesteps | 31641600 | +| train/ | | +| approx_kl | 0.011442581 | +| clip_fraction | 0.33 | +| clip_range | 0.0671 | +| entropy_loss | -5.93 | +| explained_variance | 0.51 | +| learning_rate | 4.25e-05 | +| loss | -0.0207 | +| n_updates | 77616 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000172 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1400 | +| iterations | 15451 | +| time_elapsed | 22592 | +| total_timesteps | 31643648 | +| train/ | | +| approx_kl | 0.015613358 | +| clip_fraction | 0.361 | +| clip_range | 0.0671 | +| entropy_loss | -6.02 | +| explained_variance | 0.175 | +| learning_rate | 4.25e-05 | +| loss | -0.0291 | +| n_updates | 77620 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000168 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1400 | +| iterations | 15452 | +| time_elapsed | 22593 | +| total_timesteps | 31645696 | +| train/ | | +| approx_kl | 0.01267755 | +| clip_fraction | 0.373 | +| clip_range | 0.0671 | +| entropy_loss | -6.37 | +| explained_variance | 0.377 | +| learning_rate | 4.25e-05 | +| loss | -0.0361 | +| n_updates | 77624 | +| policy_gradient_loss | -0.022 | +| value_loss | 0.000118 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1400 | +| iterations | 15453 | +| time_elapsed | 22595 | +| total_timesteps | 31647744 | +| train/ | | +| approx_kl | 0.010424582 | +| clip_fraction | 0.331 | +| clip_range | 0.0671 | +| entropy_loss | -5.94 | +| explained_variance | 0.414 | +| learning_rate | 4.25e-05 | +| loss | -0.0253 | +| n_updates | 77628 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000224 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1400 | +| iterations | 15454 | +| time_elapsed | 22596 | +| total_timesteps | 31649792 | +| train/ | | +| approx_kl | 0.01322826 | +| clip_fraction | 0.372 | +| clip_range | 0.0671 | +| entropy_loss | -6.62 | +| explained_variance | -0.294 | +| learning_rate | 4.25e-05 | +| loss | -0.0335 | +| n_updates | 77632 | +| policy_gradient_loss | -0.0222 | +| value_loss | 7.77e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1400 | +| iterations | 15455 | +| time_elapsed | 22598 | +| total_timesteps | 31651840 | +| train/ | | +| approx_kl | 0.010182881 | +| clip_fraction | 0.312 | +| clip_range | 0.0671 | +| entropy_loss | -6.22 | +| explained_variance | 0.345 | +| learning_rate | 4.25e-05 | +| loss | -0.0284 | +| n_updates | 77636 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.00025 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1400 | +| iterations | 15456 | +| time_elapsed | 22599 | +| total_timesteps | 31653888 | +| train/ | | +| approx_kl | 0.012859134 | +| clip_fraction | 0.33 | +| clip_range | 0.0671 | +| entropy_loss | -6.37 | +| explained_variance | 0.46 | +| learning_rate | 4.25e-05 | +| loss | -0.0307 | +| n_updates | 77640 | +| policy_gradient_loss | -0.0202 | +| value_loss | 7.49e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1400 | +| iterations | 15457 | +| time_elapsed | 22601 | +| total_timesteps | 31655936 | +| train/ | | +| approx_kl | 0.0128880795 | +| clip_fraction | 0.333 | +| clip_range | 0.0671 | +| entropy_loss | -5.9 | +| explained_variance | 0.564 | +| learning_rate | 4.25e-05 | +| loss | -0.0266 | +| n_updates | 77644 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000106 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1400 | +| iterations | 15458 | +| time_elapsed | 22603 | +| total_timesteps | 31657984 | +| train/ | | +| approx_kl | 0.010280581 | +| clip_fraction | 0.314 | +| clip_range | 0.0671 | +| entropy_loss | -6.04 | +| explained_variance | 0.519 | +| learning_rate | 4.25e-05 | +| loss | -0.0283 | +| n_updates | 77648 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.000169 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1400 | +| iterations | 15459 | +| time_elapsed | 22604 | +| total_timesteps | 31660032 | +| train/ | | +| approx_kl | 0.013208494 | +| clip_fraction | 0.317 | +| clip_range | 0.0671 | +| entropy_loss | -5.42 | +| explained_variance | 0.531 | +| learning_rate | 4.25e-05 | +| loss | -0.024 | +| n_updates | 77652 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000198 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1400 | +| iterations | 15460 | +| time_elapsed | 22606 | +| total_timesteps | 31662080 | +| train/ | | +| approx_kl | 0.014509506 | +| clip_fraction | 0.345 | +| clip_range | 0.0671 | +| entropy_loss | -5.54 | +| explained_variance | 0.593 | +| learning_rate | 4.25e-05 | +| loss | -0.0304 | +| n_updates | 77656 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000117 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1400 | +| iterations | 15461 | +| time_elapsed | 22607 | +| total_timesteps | 31664128 | +| train/ | | +| approx_kl | 0.011947102 | +| clip_fraction | 0.313 | +| clip_range | 0.0671 | +| entropy_loss | -5.64 | +| explained_variance | 0.506 | +| learning_rate | 4.25e-05 | +| loss | -0.0239 | +| n_updates | 77660 | +| policy_gradient_loss | -0.0141 | +| value_loss | 0.000232 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1400 | +| iterations | 15462 | +| time_elapsed | 22609 | +| total_timesteps | 31666176 | +| train/ | | +| approx_kl | 0.012882489 | +| clip_fraction | 0.347 | +| clip_range | 0.0671 | +| entropy_loss | -6.05 | +| explained_variance | 0.575 | +| learning_rate | 4.25e-05 | +| loss | -0.0336 | +| n_updates | 77664 | +| policy_gradient_loss | -0.018 | +| value_loss | 9.65e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1400 | +| iterations | 15463 | +| time_elapsed | 22610 | +| total_timesteps | 31668224 | +| train/ | | +| approx_kl | 0.014037233 | +| clip_fraction | 0.367 | +| clip_range | 0.0671 | +| entropy_loss | -6.73 | +| explained_variance | -0.124 | +| learning_rate | 4.25e-05 | +| loss | -0.0353 | +| n_updates | 77668 | +| policy_gradient_loss | -0.0198 | +| value_loss | 9.97e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1400 | +| iterations | 15464 | +| time_elapsed | 22612 | +| total_timesteps | 31670272 | +| train/ | | +| approx_kl | 0.013917101 | +| clip_fraction | 0.312 | +| clip_range | 0.0671 | +| entropy_loss | -6.72 | +| explained_variance | 0.157 | +| learning_rate | 4.25e-05 | +| loss | -0.0217 | +| n_updates | 77672 | +| policy_gradient_loss | -0.0145 | +| value_loss | 0.000238 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1400 | +| iterations | 15465 | +| time_elapsed | 22613 | +| total_timesteps | 31672320 | +| train/ | | +| approx_kl | 0.013625522 | +| clip_fraction | 0.342 | +| clip_range | 0.0671 | +| entropy_loss | -6.25 | +| explained_variance | 0.151 | +| learning_rate | 4.25e-05 | +| loss | -0.0291 | +| n_updates | 77676 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.00029 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1400 | +| iterations | 15466 | +| time_elapsed | 22615 | +| total_timesteps | 31674368 | +| train/ | | +| approx_kl | 0.01235361 | +| clip_fraction | 0.319 | +| clip_range | 0.0671 | +| entropy_loss | -5.81 | +| explained_variance | 0.336 | +| learning_rate | 4.25e-05 | +| loss | -0.0279 | +| n_updates | 77680 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000353 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1400 | +| iterations | 15467 | +| time_elapsed | 22616 | +| total_timesteps | 31676416 | +| train/ | | +| approx_kl | 0.013046392 | +| clip_fraction | 0.341 | +| clip_range | 0.0671 | +| entropy_loss | -6.2 | +| explained_variance | 0.186 | +| learning_rate | 4.25e-05 | +| loss | -0.0326 | +| n_updates | 77684 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000136 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1400 | +| iterations | 15468 | +| time_elapsed | 22618 | +| total_timesteps | 31678464 | +| train/ | | +| approx_kl | 0.014113253 | +| clip_fraction | 0.309 | +| clip_range | 0.0671 | +| entropy_loss | -5.81 | +| explained_variance | 0.657 | +| learning_rate | 4.25e-05 | +| loss | -0.0289 | +| n_updates | 77688 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000124 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1400 | +| iterations | 15469 | +| time_elapsed | 22620 | +| total_timesteps | 31680512 | +| train/ | | +| approx_kl | 0.01433125 | +| clip_fraction | 0.372 | +| clip_range | 0.0671 | +| entropy_loss | -5.74 | +| explained_variance | 0.648 | +| learning_rate | 4.25e-05 | +| loss | -0.0359 | +| n_updates | 77692 | +| policy_gradient_loss | -0.0222 | +| value_loss | 5.53e-05 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1400 | +| iterations | 15470 | +| time_elapsed | 22621 | +| total_timesteps | 31682560 | +| train/ | | +| approx_kl | 0.01189716 | +| clip_fraction | 0.297 | +| clip_range | 0.0671 | +| entropy_loss | -5.65 | +| explained_variance | 0.473 | +| learning_rate | 4.25e-05 | +| loss | -0.0206 | +| n_updates | 77696 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.000301 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1400 | +| iterations | 15471 | +| time_elapsed | 22623 | +| total_timesteps | 31684608 | +| train/ | | +| approx_kl | 0.013805467 | +| clip_fraction | 0.327 | +| clip_range | 0.0671 | +| entropy_loss | -6.13 | +| explained_variance | 0.383 | +| learning_rate | 4.25e-05 | +| loss | -0.0339 | +| n_updates | 77700 | +| policy_gradient_loss | -0.0198 | +| value_loss | 8.9e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1400 | +| iterations | 15472 | +| time_elapsed | 22624 | +| total_timesteps | 31686656 | +| train/ | | +| approx_kl | 0.011845251 | +| clip_fraction | 0.346 | +| clip_range | 0.0671 | +| entropy_loss | -6.2 | +| explained_variance | 0.245 | +| learning_rate | 4.25e-05 | +| loss | -0.0356 | +| n_updates | 77704 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000201 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1400 | +| iterations | 15473 | +| time_elapsed | 22626 | +| total_timesteps | 31688704 | +| train/ | | +| approx_kl | 0.0125199035 | +| clip_fraction | 0.323 | +| clip_range | 0.0671 | +| entropy_loss | -6.25 | +| explained_variance | 0.243 | +| learning_rate | 4.25e-05 | +| loss | -0.0234 | +| n_updates | 77708 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000182 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1400 | +| iterations | 15474 | +| time_elapsed | 22627 | +| total_timesteps | 31690752 | +| train/ | | +| approx_kl | 0.013841241 | +| clip_fraction | 0.34 | +| clip_range | 0.0671 | +| entropy_loss | -5.89 | +| explained_variance | 0.455 | +| learning_rate | 4.25e-05 | +| loss | -0.0342 | +| n_updates | 77712 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000145 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1400 | +| iterations | 15475 | +| time_elapsed | 22629 | +| total_timesteps | 31692800 | +| train/ | | +| approx_kl | 0.015341117 | +| clip_fraction | 0.342 | +| clip_range | 0.0671 | +| entropy_loss | -6.07 | +| explained_variance | 0.103 | +| learning_rate | 4.25e-05 | +| loss | -0.0286 | +| n_updates | 77716 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000206 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1400 | +| iterations | 15476 | +| time_elapsed | 22630 | +| total_timesteps | 31694848 | +| train/ | | +| approx_kl | 0.011012888 | +| clip_fraction | 0.322 | +| clip_range | 0.0671 | +| entropy_loss | -6.14 | +| explained_variance | 0.451 | +| learning_rate | 4.25e-05 | +| loss | -0.0195 | +| n_updates | 77720 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000166 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1400 | +| iterations | 15477 | +| time_elapsed | 22632 | +| total_timesteps | 31696896 | +| train/ | | +| approx_kl | 0.01153881 | +| clip_fraction | 0.339 | +| clip_range | 0.0671 | +| entropy_loss | -6.29 | +| explained_variance | 0.457 | +| learning_rate | 4.25e-05 | +| loss | -0.0262 | +| n_updates | 77724 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000179 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1400 | +| iterations | 15478 | +| time_elapsed | 22633 | +| total_timesteps | 31698944 | +| train/ | | +| approx_kl | 0.01292335 | +| clip_fraction | 0.353 | +| clip_range | 0.0671 | +| entropy_loss | -5.53 | +| explained_variance | 0.803 | +| learning_rate | 4.25e-05 | +| loss | -0.0327 | +| n_updates | 77728 | +| policy_gradient_loss | -0.0209 | +| value_loss | 6.6e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1400 | +| iterations | 15479 | +| time_elapsed | 22635 | +| total_timesteps | 31700992 | +| train/ | | +| approx_kl | 0.014632465 | +| clip_fraction | 0.353 | +| clip_range | 0.0671 | +| entropy_loss | -5.96 | +| explained_variance | -0.32 | +| learning_rate | 4.25e-05 | +| loss | -0.0331 | +| n_updates | 77732 | +| policy_gradient_loss | -0.0217 | +| value_loss | 6.6e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1400 | +| iterations | 15480 | +| time_elapsed | 22637 | +| total_timesteps | 31703040 | +| train/ | | +| approx_kl | 0.013426805 | +| clip_fraction | 0.356 | +| clip_range | 0.0671 | +| entropy_loss | -6.54 | +| explained_variance | -0.227 | +| learning_rate | 4.25e-05 | +| loss | -0.0295 | +| n_updates | 77736 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000117 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1400 | +| iterations | 15481 | +| time_elapsed | 22638 | +| total_timesteps | 31705088 | +| train/ | | +| approx_kl | 0.0132537875 | +| clip_fraction | 0.329 | +| clip_range | 0.0671 | +| entropy_loss | -6.44 | +| explained_variance | 0.305 | +| learning_rate | 4.25e-05 | +| loss | -0.028 | +| n_updates | 77740 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000104 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1400 | +| iterations | 15482 | +| time_elapsed | 22640 | +| total_timesteps | 31707136 | +| train/ | | +| approx_kl | 0.013179669 | +| clip_fraction | 0.347 | +| clip_range | 0.0671 | +| entropy_loss | -6.47 | +| explained_variance | 0.00446 | +| learning_rate | 4.25e-05 | +| loss | -0.0276 | +| n_updates | 77744 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000244 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1400 | +| iterations | 15483 | +| time_elapsed | 22641 | +| total_timesteps | 31709184 | +| train/ | | +| approx_kl | 0.015940057 | +| clip_fraction | 0.312 | +| clip_range | 0.0671 | +| entropy_loss | -5.65 | +| explained_variance | 0.343 | +| learning_rate | 4.25e-05 | +| loss | -0.027 | +| n_updates | 77748 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000482 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1400 | +| iterations | 15484 | +| time_elapsed | 22643 | +| total_timesteps | 31711232 | +| train/ | | +| approx_kl | 0.01350145 | +| clip_fraction | 0.332 | +| clip_range | 0.0671 | +| entropy_loss | -5.42 | +| explained_variance | 0.52 | +| learning_rate | 4.25e-05 | +| loss | -0.0279 | +| n_updates | 77752 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000166 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1400 | +| iterations | 15485 | +| time_elapsed | 22644 | +| total_timesteps | 31713280 | +| train/ | | +| approx_kl | 0.013278867 | +| clip_fraction | 0.346 | +| clip_range | 0.0671 | +| entropy_loss | -5.44 | +| explained_variance | 0.515 | +| learning_rate | 4.25e-05 | +| loss | -0.0271 | +| n_updates | 77756 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000235 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1400 | +| iterations | 15486 | +| time_elapsed | 22646 | +| total_timesteps | 31715328 | +| train/ | | +| approx_kl | 0.012355935 | +| clip_fraction | 0.331 | +| clip_range | 0.0671 | +| entropy_loss | -6.29 | +| explained_variance | 0.146 | +| learning_rate | 4.25e-05 | +| loss | -0.0249 | +| n_updates | 77760 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000147 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1400 | +| iterations | 15487 | +| time_elapsed | 22647 | +| total_timesteps | 31717376 | +| train/ | | +| approx_kl | 0.012401183 | +| clip_fraction | 0.332 | +| clip_range | 0.0671 | +| entropy_loss | -6.13 | +| explained_variance | 0.594 | +| learning_rate | 4.25e-05 | +| loss | -0.0254 | +| n_updates | 77764 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000133 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1400 | +| iterations | 15488 | +| time_elapsed | 22649 | +| total_timesteps | 31719424 | +| train/ | | +| approx_kl | 0.012279361 | +| clip_fraction | 0.331 | +| clip_range | 0.0671 | +| entropy_loss | -6.55 | +| explained_variance | -0.158 | +| learning_rate | 4.25e-05 | +| loss | -0.028 | +| n_updates | 77768 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000141 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1400 | +| iterations | 15489 | +| time_elapsed | 22650 | +| total_timesteps | 31721472 | +| train/ | | +| approx_kl | 0.013218695 | +| clip_fraction | 0.361 | +| clip_range | 0.0671 | +| entropy_loss | -6.98 | +| explained_variance | 0.421 | +| learning_rate | 4.25e-05 | +| loss | -0.0304 | +| n_updates | 77772 | +| policy_gradient_loss | -0.022 | +| value_loss | 7.46e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1400 | +| iterations | 15490 | +| time_elapsed | 22652 | +| total_timesteps | 31723520 | +| train/ | | +| approx_kl | 0.010313772 | +| clip_fraction | 0.315 | +| clip_range | 0.0671 | +| entropy_loss | -6.64 | +| explained_variance | 0.234 | +| learning_rate | 4.25e-05 | +| loss | -0.027 | +| n_updates | 77776 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.00022 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.315 | +| time/ | | +| fps | 1400 | +| iterations | 15491 | +| time_elapsed | 22653 | +| total_timesteps | 31725568 | +| train/ | | +| approx_kl | 0.012648752 | +| clip_fraction | 0.305 | +| clip_range | 0.0671 | +| entropy_loss | -6.19 | +| explained_variance | 0.432 | +| learning_rate | 4.25e-05 | +| loss | -0.0232 | +| n_updates | 77780 | +| policy_gradient_loss | -0.0147 | +| value_loss | 0.000184 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1400 | +| iterations | 15492 | +| time_elapsed | 22655 | +| total_timesteps | 31727616 | +| train/ | | +| approx_kl | 0.013017189 | +| clip_fraction | 0.338 | +| clip_range | 0.0671 | +| entropy_loss | -5.92 | +| explained_variance | 0.258 | +| learning_rate | 4.25e-05 | +| loss | -0.0283 | +| n_updates | 77784 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.00017 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1400 | +| iterations | 15493 | +| time_elapsed | 22656 | +| total_timesteps | 31729664 | +| train/ | | +| approx_kl | 0.013323452 | +| clip_fraction | 0.35 | +| clip_range | 0.0671 | +| entropy_loss | -5.88 | +| explained_variance | 0.407 | +| learning_rate | 4.25e-05 | +| loss | -0.0269 | +| n_updates | 77788 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000282 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1400 | +| iterations | 15494 | +| time_elapsed | 22658 | +| total_timesteps | 31731712 | +| train/ | | +| approx_kl | 0.015499735 | +| clip_fraction | 0.381 | +| clip_range | 0.0671 | +| entropy_loss | -5.63 | +| explained_variance | 0.511 | +| learning_rate | 4.25e-05 | +| loss | -0.0217 | +| n_updates | 77792 | +| policy_gradient_loss | -0.0217 | +| value_loss | 7.15e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1400 | +| iterations | 15495 | +| time_elapsed | 22660 | +| total_timesteps | 31733760 | +| train/ | | +| approx_kl | 0.014416367 | +| clip_fraction | 0.353 | +| clip_range | 0.0671 | +| entropy_loss | -6.37 | +| explained_variance | 0.251 | +| learning_rate | 4.25e-05 | +| loss | -0.0338 | +| n_updates | 77796 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000167 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1400 | +| iterations | 15496 | +| time_elapsed | 22661 | +| total_timesteps | 31735808 | +| train/ | | +| approx_kl | 0.010329289 | +| clip_fraction | 0.317 | +| clip_range | 0.0671 | +| entropy_loss | -5.94 | +| explained_variance | 0.398 | +| learning_rate | 4.25e-05 | +| loss | -0.0284 | +| n_updates | 77800 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.0003 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1400 | +| iterations | 15497 | +| time_elapsed | 22663 | +| total_timesteps | 31737856 | +| train/ | | +| approx_kl | 0.01290729 | +| clip_fraction | 0.361 | +| clip_range | 0.0671 | +| entropy_loss | -5.88 | +| explained_variance | 0.338 | +| learning_rate | 4.25e-05 | +| loss | -0.0326 | +| n_updates | 77804 | +| policy_gradient_loss | -0.0208 | +| value_loss | 8.78e-05 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1400 | +| iterations | 15498 | +| time_elapsed | 22664 | +| total_timesteps | 31739904 | +| train/ | | +| approx_kl | 0.01843642 | +| clip_fraction | 0.353 | +| clip_range | 0.0671 | +| entropy_loss | -5.68 | +| explained_variance | 0.502 | +| learning_rate | 4.25e-05 | +| loss | -0.0306 | +| n_updates | 77808 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000137 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1400 | +| iterations | 15499 | +| time_elapsed | 22666 | +| total_timesteps | 31741952 | +| train/ | | +| approx_kl | 0.012335298 | +| clip_fraction | 0.324 | +| clip_range | 0.0671 | +| entropy_loss | -5.59 | +| explained_variance | 0.425 | +| learning_rate | 4.25e-05 | +| loss | -0.0281 | +| n_updates | 77812 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000358 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1400 | +| iterations | 15500 | +| time_elapsed | 22667 | +| total_timesteps | 31744000 | +| train/ | | +| approx_kl | 0.012701182 | +| clip_fraction | 0.368 | +| clip_range | 0.0671 | +| entropy_loss | -5.9 | +| explained_variance | 0.292 | +| learning_rate | 4.25e-05 | +| loss | -0.0391 | +| n_updates | 77816 | +| policy_gradient_loss | -0.0237 | +| value_loss | 9.1e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1400 | +| iterations | 15501 | +| time_elapsed | 22669 | +| total_timesteps | 31746048 | +| train/ | | +| approx_kl | 0.008407231 | +| clip_fraction | 0.281 | +| clip_range | 0.0671 | +| entropy_loss | -6.27 | +| explained_variance | 0.402 | +| learning_rate | 4.25e-05 | +| loss | -0.0264 | +| n_updates | 77820 | +| policy_gradient_loss | -0.0147 | +| value_loss | 0.00036 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1400 | +| iterations | 15502 | +| time_elapsed | 22670 | +| total_timesteps | 31748096 | +| train/ | | +| approx_kl | 0.010387482 | +| clip_fraction | 0.33 | +| clip_range | 0.0671 | +| entropy_loss | -6.4 | +| explained_variance | 0.311 | +| learning_rate | 4.25e-05 | +| loss | -0.0339 | +| n_updates | 77824 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000125 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1400 | +| iterations | 15503 | +| time_elapsed | 22672 | +| total_timesteps | 31750144 | +| train/ | | +| approx_kl | 0.010775501 | +| clip_fraction | 0.299 | +| clip_range | 0.0671 | +| entropy_loss | -6.22 | +| explained_variance | 0.356 | +| learning_rate | 4.25e-05 | +| loss | -0.0273 | +| n_updates | 77828 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000318 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1400 | +| iterations | 15504 | +| time_elapsed | 22673 | +| total_timesteps | 31752192 | +| train/ | | +| approx_kl | 0.0122758765 | +| clip_fraction | 0.329 | +| clip_range | 0.0671 | +| entropy_loss | -6.13 | +| explained_variance | 0.338 | +| learning_rate | 4.25e-05 | +| loss | -0.0321 | +| n_updates | 77832 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000124 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1400 | +| iterations | 15505 | +| time_elapsed | 22675 | +| total_timesteps | 31754240 | +| train/ | | +| approx_kl | 0.012099253 | +| clip_fraction | 0.333 | +| clip_range | 0.0671 | +| entropy_loss | -5.77 | +| explained_variance | 0.59 | +| learning_rate | 4.25e-05 | +| loss | -0.029 | +| n_updates | 77836 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000164 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1400 | +| iterations | 15506 | +| time_elapsed | 22676 | +| total_timesteps | 31756288 | +| train/ | | +| approx_kl | 0.011676746 | +| clip_fraction | 0.329 | +| clip_range | 0.0671 | +| entropy_loss | -6.13 | +| explained_variance | 0.484 | +| learning_rate | 4.25e-05 | +| loss | -0.036 | +| n_updates | 77840 | +| policy_gradient_loss | -0.0206 | +| value_loss | 7.84e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1400 | +| iterations | 15507 | +| time_elapsed | 22678 | +| total_timesteps | 31758336 | +| train/ | | +| approx_kl | 0.010537691 | +| clip_fraction | 0.31 | +| clip_range | 0.0671 | +| entropy_loss | -6.7 | +| explained_variance | 0.271 | +| learning_rate | 4.25e-05 | +| loss | -0.0276 | +| n_updates | 77844 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.00017 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1400 | +| iterations | 15508 | +| time_elapsed | 22679 | +| total_timesteps | 31760384 | +| train/ | | +| approx_kl | 0.012243506 | +| clip_fraction | 0.314 | +| clip_range | 0.0671 | +| entropy_loss | -6.13 | +| explained_variance | 0.316 | +| learning_rate | 4.25e-05 | +| loss | -0.0252 | +| n_updates | 77848 | +| policy_gradient_loss | -0.0137 | +| value_loss | 0.000317 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1400 | +| iterations | 15509 | +| time_elapsed | 22681 | +| total_timesteps | 31762432 | +| train/ | | +| approx_kl | 0.013175415 | +| clip_fraction | 0.36 | +| clip_range | 0.0671 | +| entropy_loss | -5.9 | +| explained_variance | 0.524 | +| learning_rate | 4.25e-05 | +| loss | -0.0254 | +| n_updates | 77852 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000148 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1400 | +| iterations | 15510 | +| time_elapsed | 22682 | +| total_timesteps | 31764480 | +| train/ | | +| approx_kl | 0.012048839 | +| clip_fraction | 0.309 | +| clip_range | 0.0671 | +| entropy_loss | -5.66 | +| explained_variance | 0.365 | +| learning_rate | 4.25e-05 | +| loss | -0.0233 | +| n_updates | 77856 | +| policy_gradient_loss | -0.0144 | +| value_loss | 0.000423 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1400 | +| iterations | 15511 | +| time_elapsed | 22684 | +| total_timesteps | 31766528 | +| train/ | | +| approx_kl | 0.0135835335 | +| clip_fraction | 0.338 | +| clip_range | 0.0671 | +| entropy_loss | -5.95 | +| explained_variance | 0.269 | +| learning_rate | 4.25e-05 | +| loss | -0.0319 | +| n_updates | 77860 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000205 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1400 | +| iterations | 15512 | +| time_elapsed | 22685 | +| total_timesteps | 31768576 | +| train/ | | +| approx_kl | 0.011816323 | +| clip_fraction | 0.342 | +| clip_range | 0.0671 | +| entropy_loss | -6.17 | +| explained_variance | 0.386 | +| learning_rate | 4.25e-05 | +| loss | -0.0284 | +| n_updates | 77864 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000191 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1400 | +| iterations | 15513 | +| time_elapsed | 22687 | +| total_timesteps | 31770624 | +| train/ | | +| approx_kl | 0.012711119 | +| clip_fraction | 0.359 | +| clip_range | 0.0671 | +| entropy_loss | -6.34 | +| explained_variance | 0.33 | +| learning_rate | 4.25e-05 | +| loss | -0.0333 | +| n_updates | 77868 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000131 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1400 | +| iterations | 15514 | +| time_elapsed | 22688 | +| total_timesteps | 31772672 | +| train/ | | +| approx_kl | 0.0124056665 | +| clip_fraction | 0.339 | +| clip_range | 0.0671 | +| entropy_loss | -6.15 | +| explained_variance | 0.241 | +| learning_rate | 4.25e-05 | +| loss | -0.0264 | +| n_updates | 77872 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000437 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1400 | +| iterations | 15515 | +| time_elapsed | 22690 | +| total_timesteps | 31774720 | +| train/ | | +| approx_kl | 0.012151627 | +| clip_fraction | 0.341 | +| clip_range | 0.0671 | +| entropy_loss | -6.04 | +| explained_variance | 0.525 | +| learning_rate | 4.25e-05 | +| loss | -0.0248 | +| n_updates | 77876 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000215 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1400 | +| iterations | 15516 | +| time_elapsed | 22691 | +| total_timesteps | 31776768 | +| train/ | | +| approx_kl | 0.012165986 | +| clip_fraction | 0.347 | +| clip_range | 0.0671 | +| entropy_loss | -5.48 | +| explained_variance | 0.594 | +| learning_rate | 4.25e-05 | +| loss | -0.0303 | +| n_updates | 77880 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000138 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1400 | +| iterations | 15517 | +| time_elapsed | 22693 | +| total_timesteps | 31778816 | +| train/ | | +| approx_kl | 0.01301099 | +| clip_fraction | 0.333 | +| clip_range | 0.0671 | +| entropy_loss | -6.05 | +| explained_variance | 0.411 | +| learning_rate | 4.25e-05 | +| loss | -0.0241 | +| n_updates | 77884 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000174 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1400 | +| iterations | 15518 | +| time_elapsed | 22695 | +| total_timesteps | 31780864 | +| train/ | | +| approx_kl | 0.013039611 | +| clip_fraction | 0.34 | +| clip_range | 0.0671 | +| entropy_loss | -6.02 | +| explained_variance | 0.236 | +| learning_rate | 4.25e-05 | +| loss | -0.0233 | +| n_updates | 77888 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.00022 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1400 | +| iterations | 15519 | +| time_elapsed | 22696 | +| total_timesteps | 31782912 | +| train/ | | +| approx_kl | 0.012078177 | +| clip_fraction | 0.346 | +| clip_range | 0.0671 | +| entropy_loss | -6.51 | +| explained_variance | 0.0924 | +| learning_rate | 4.25e-05 | +| loss | -0.0307 | +| n_updates | 77892 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000141 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1400 | +| iterations | 15520 | +| time_elapsed | 22698 | +| total_timesteps | 31784960 | +| train/ | | +| approx_kl | 0.015147246 | +| clip_fraction | 0.353 | +| clip_range | 0.0671 | +| entropy_loss | -6.81 | +| explained_variance | -0.242 | +| learning_rate | 4.25e-05 | +| loss | -0.0337 | +| n_updates | 77896 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000104 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1400 | +| iterations | 15521 | +| time_elapsed | 22699 | +| total_timesteps | 31787008 | +| train/ | | +| approx_kl | 0.009645725 | +| clip_fraction | 0.303 | +| clip_range | 0.0671 | +| entropy_loss | -6.24 | +| explained_variance | 0.427 | +| learning_rate | 4.25e-05 | +| loss | -0.0297 | +| n_updates | 77900 | +| policy_gradient_loss | -0.0135 | +| value_loss | 0.000199 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1400 | +| iterations | 15522 | +| time_elapsed | 22701 | +| total_timesteps | 31789056 | +| train/ | | +| approx_kl | 0.010782336 | +| clip_fraction | 0.323 | +| clip_range | 0.0671 | +| entropy_loss | -5.64 | +| explained_variance | 0.689 | +| learning_rate | 4.25e-05 | +| loss | -0.0197 | +| n_updates | 77904 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000134 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1400 | +| iterations | 15523 | +| time_elapsed | 22702 | +| total_timesteps | 31791104 | +| train/ | | +| approx_kl | 0.013701088 | +| clip_fraction | 0.364 | +| clip_range | 0.0671 | +| entropy_loss | -5.97 | +| explained_variance | 0.568 | +| learning_rate | 4.25e-05 | +| loss | -0.0356 | +| n_updates | 77908 | +| policy_gradient_loss | -0.0197 | +| value_loss | 8.59e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1400 | +| iterations | 15524 | +| time_elapsed | 22704 | +| total_timesteps | 31793152 | +| train/ | | +| approx_kl | 0.012785001 | +| clip_fraction | 0.337 | +| clip_range | 0.0671 | +| entropy_loss | -6.51 | +| explained_variance | 0.413 | +| learning_rate | 4.24e-05 | +| loss | -0.0283 | +| n_updates | 77912 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000107 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1400 | +| iterations | 15525 | +| time_elapsed | 22705 | +| total_timesteps | 31795200 | +| train/ | | +| approx_kl | 0.012065593 | +| clip_fraction | 0.341 | +| clip_range | 0.0671 | +| entropy_loss | -6.59 | +| explained_variance | -0.0753 | +| learning_rate | 4.24e-05 | +| loss | -0.0266 | +| n_updates | 77916 | +| policy_gradient_loss | -0.0196 | +| value_loss | 7.38e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1400 | +| iterations | 15526 | +| time_elapsed | 22707 | +| total_timesteps | 31797248 | +| train/ | | +| approx_kl | 0.012256889 | +| clip_fraction | 0.357 | +| clip_range | 0.0671 | +| entropy_loss | -5.62 | +| explained_variance | 0.702 | +| learning_rate | 4.24e-05 | +| loss | -0.0258 | +| n_updates | 77920 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000139 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1400 | +| iterations | 15527 | +| time_elapsed | 22708 | +| total_timesteps | 31799296 | +| train/ | | +| approx_kl | 0.009902639 | +| clip_fraction | 0.306 | +| clip_range | 0.0671 | +| entropy_loss | -5.71 | +| explained_variance | 0.303 | +| learning_rate | 4.24e-05 | +| loss | -0.0216 | +| n_updates | 77924 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000179 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1400 | +| iterations | 15528 | +| time_elapsed | 22710 | +| total_timesteps | 31801344 | +| train/ | | +| approx_kl | 0.012191578 | +| clip_fraction | 0.319 | +| clip_range | 0.0671 | +| entropy_loss | -5.12 | +| explained_variance | 0.716 | +| learning_rate | 4.24e-05 | +| loss | -0.0252 | +| n_updates | 77928 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000126 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1400 | +| iterations | 15529 | +| time_elapsed | 22712 | +| total_timesteps | 31803392 | +| train/ | | +| approx_kl | 0.014171214 | +| clip_fraction | 0.334 | +| clip_range | 0.067 | +| entropy_loss | -6.02 | +| explained_variance | 0.165 | +| learning_rate | 4.24e-05 | +| loss | -0.0287 | +| n_updates | 77932 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000241 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1400 | +| iterations | 15530 | +| time_elapsed | 22713 | +| total_timesteps | 31805440 | +| train/ | | +| approx_kl | 0.014600303 | +| clip_fraction | 0.342 | +| clip_range | 0.067 | +| entropy_loss | -6.19 | +| explained_variance | 0.494 | +| learning_rate | 4.24e-05 | +| loss | -0.0317 | +| n_updates | 77936 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000148 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1400 | +| iterations | 15531 | +| time_elapsed | 22715 | +| total_timesteps | 31807488 | +| train/ | | +| approx_kl | 0.012445984 | +| clip_fraction | 0.356 | +| clip_range | 0.067 | +| entropy_loss | -6.48 | +| explained_variance | -0.214 | +| learning_rate | 4.24e-05 | +| loss | -0.031 | +| n_updates | 77940 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000111 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1400 | +| iterations | 15532 | +| time_elapsed | 22716 | +| total_timesteps | 31809536 | +| train/ | | +| approx_kl | 0.014550818 | +| clip_fraction | 0.347 | +| clip_range | 0.067 | +| entropy_loss | -6.41 | +| explained_variance | 0.337 | +| learning_rate | 4.24e-05 | +| loss | -0.0324 | +| n_updates | 77944 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000169 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1400 | +| iterations | 15533 | +| time_elapsed | 22718 | +| total_timesteps | 31811584 | +| train/ | | +| approx_kl | 0.015261324 | +| clip_fraction | 0.379 | +| clip_range | 0.067 | +| entropy_loss | -6.51 | +| explained_variance | -0.0402 | +| learning_rate | 4.24e-05 | +| loss | -0.0288 | +| n_updates | 77948 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000244 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1400 | +| iterations | 15534 | +| time_elapsed | 22719 | +| total_timesteps | 31813632 | +| train/ | | +| approx_kl | 0.014007033 | +| clip_fraction | 0.325 | +| clip_range | 0.067 | +| entropy_loss | -5.99 | +| explained_variance | 0.488 | +| learning_rate | 4.24e-05 | +| loss | -0.0309 | +| n_updates | 77952 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000146 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1400 | +| iterations | 15535 | +| time_elapsed | 22721 | +| total_timesteps | 31815680 | +| train/ | | +| approx_kl | 0.015174492 | +| clip_fraction | 0.324 | +| clip_range | 0.067 | +| entropy_loss | -5.45 | +| explained_variance | 0.513 | +| learning_rate | 4.24e-05 | +| loss | -0.0261 | +| n_updates | 77956 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000195 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1400 | +| iterations | 15536 | +| time_elapsed | 22722 | +| total_timesteps | 31817728 | +| train/ | | +| approx_kl | 0.012980245 | +| clip_fraction | 0.338 | +| clip_range | 0.067 | +| entropy_loss | -5.94 | +| explained_variance | 0.703 | +| learning_rate | 4.24e-05 | +| loss | -0.0284 | +| n_updates | 77960 | +| policy_gradient_loss | -0.018 | +| value_loss | 9.07e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1400 | +| iterations | 15537 | +| time_elapsed | 22724 | +| total_timesteps | 31819776 | +| train/ | | +| approx_kl | 0.01383231 | +| clip_fraction | 0.332 | +| clip_range | 0.067 | +| entropy_loss | -5.45 | +| explained_variance | 0.525 | +| learning_rate | 4.24e-05 | +| loss | -0.028 | +| n_updates | 77964 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000132 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1400 | +| iterations | 15538 | +| time_elapsed | 22726 | +| total_timesteps | 31821824 | +| train/ | | +| approx_kl | 0.013075642 | +| clip_fraction | 0.359 | +| clip_range | 0.067 | +| entropy_loss | -5.7 | +| explained_variance | 0.305 | +| learning_rate | 4.24e-05 | +| loss | -0.0298 | +| n_updates | 77968 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000168 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1400 | +| iterations | 15539 | +| time_elapsed | 22727 | +| total_timesteps | 31823872 | +| train/ | | +| approx_kl | 0.013569444 | +| clip_fraction | 0.369 | +| clip_range | 0.067 | +| entropy_loss | -5.71 | +| explained_variance | 0.422 | +| learning_rate | 4.24e-05 | +| loss | -0.0274 | +| n_updates | 77972 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000156 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1400 | +| iterations | 15540 | +| time_elapsed | 22729 | +| total_timesteps | 31825920 | +| train/ | | +| approx_kl | 0.014077119 | +| clip_fraction | 0.357 | +| clip_range | 0.067 | +| entropy_loss | -6.42 | +| explained_variance | 0.444 | +| learning_rate | 4.24e-05 | +| loss | -0.0316 | +| n_updates | 77976 | +| policy_gradient_loss | -0.0204 | +| value_loss | 9.81e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1400 | +| iterations | 15541 | +| time_elapsed | 22730 | +| total_timesteps | 31827968 | +| train/ | | +| approx_kl | 0.011772459 | +| clip_fraction | 0.342 | +| clip_range | 0.067 | +| entropy_loss | -6.23 | +| explained_variance | 0.676 | +| learning_rate | 4.24e-05 | +| loss | -0.0292 | +| n_updates | 77980 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000105 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1400 | +| iterations | 15542 | +| time_elapsed | 22732 | +| total_timesteps | 31830016 | +| train/ | | +| approx_kl | 0.010112497 | +| clip_fraction | 0.296 | +| clip_range | 0.067 | +| entropy_loss | -6.5 | +| explained_variance | 0.218 | +| learning_rate | 4.24e-05 | +| loss | -0.0219 | +| n_updates | 77984 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000164 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1400 | +| iterations | 15543 | +| time_elapsed | 22733 | +| total_timesteps | 31832064 | +| train/ | | +| approx_kl | 0.011208676 | +| clip_fraction | 0.353 | +| clip_range | 0.067 | +| entropy_loss | -6.25 | +| explained_variance | 0.602 | +| learning_rate | 4.24e-05 | +| loss | -0.0233 | +| n_updates | 77988 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000137 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1400 | +| iterations | 15544 | +| time_elapsed | 22735 | +| total_timesteps | 31834112 | +| train/ | | +| approx_kl | 0.01244569 | +| clip_fraction | 0.362 | +| clip_range | 0.067 | +| entropy_loss | -6.87 | +| explained_variance | -0.17 | +| learning_rate | 4.24e-05 | +| loss | -0.0274 | +| n_updates | 77992 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000131 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1400 | +| iterations | 15545 | +| time_elapsed | 22736 | +| total_timesteps | 31836160 | +| train/ | | +| approx_kl | 0.015440373 | +| clip_fraction | 0.334 | +| clip_range | 0.067 | +| entropy_loss | -6.81 | +| explained_variance | 0.314 | +| learning_rate | 4.24e-05 | +| loss | -0.0307 | +| n_updates | 77996 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000141 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1400 | +| iterations | 15546 | +| time_elapsed | 22738 | +| total_timesteps | 31838208 | +| train/ | | +| approx_kl | 0.0138057545 | +| clip_fraction | 0.347 | +| clip_range | 0.067 | +| entropy_loss | -6.02 | +| explained_variance | 0.509 | +| learning_rate | 4.24e-05 | +| loss | -0.0257 | +| n_updates | 78000 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000124 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1400 | +| iterations | 15547 | +| time_elapsed | 22739 | +| total_timesteps | 31840256 | +| train/ | | +| approx_kl | 0.01399059 | +| clip_fraction | 0.317 | +| clip_range | 0.067 | +| entropy_loss | -5.84 | +| explained_variance | 0.563 | +| learning_rate | 4.24e-05 | +| loss | -0.0303 | +| n_updates | 78004 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000112 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1400 | +| iterations | 15548 | +| time_elapsed | 22741 | +| total_timesteps | 31842304 | +| train/ | | +| approx_kl | 0.009784538 | +| clip_fraction | 0.31 | +| clip_range | 0.067 | +| entropy_loss | -6.56 | +| explained_variance | -0.024 | +| learning_rate | 4.24e-05 | +| loss | -0.0271 | +| n_updates | 78008 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.000214 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1400 | +| iterations | 15549 | +| time_elapsed | 22743 | +| total_timesteps | 31844352 | +| train/ | | +| approx_kl | 0.010434651 | +| clip_fraction | 0.314 | +| clip_range | 0.067 | +| entropy_loss | -5.4 | +| explained_variance | 0.662 | +| learning_rate | 4.24e-05 | +| loss | -0.0244 | +| n_updates | 78012 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000178 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1400 | +| iterations | 15550 | +| time_elapsed | 22744 | +| total_timesteps | 31846400 | +| train/ | | +| approx_kl | 0.013170755 | +| clip_fraction | 0.362 | +| clip_range | 0.067 | +| entropy_loss | -5.53 | +| explained_variance | 0.556 | +| learning_rate | 4.24e-05 | +| loss | -0.0292 | +| n_updates | 78016 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000131 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1400 | +| iterations | 15551 | +| time_elapsed | 22746 | +| total_timesteps | 31848448 | +| train/ | | +| approx_kl | 0.01326357 | +| clip_fraction | 0.329 | +| clip_range | 0.067 | +| entropy_loss | -5.26 | +| explained_variance | 0.478 | +| learning_rate | 4.24e-05 | +| loss | -0.0238 | +| n_updates | 78020 | +| policy_gradient_loss | -0.0147 | +| value_loss | 0.000259 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1400 | +| iterations | 15552 | +| time_elapsed | 22747 | +| total_timesteps | 31850496 | +| train/ | | +| approx_kl | 0.014402869 | +| clip_fraction | 0.351 | +| clip_range | 0.067 | +| entropy_loss | -6.26 | +| explained_variance | -0.15 | +| learning_rate | 4.24e-05 | +| loss | -0.0286 | +| n_updates | 78024 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.0002 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1400 | +| iterations | 15553 | +| time_elapsed | 22749 | +| total_timesteps | 31852544 | +| train/ | | +| approx_kl | 0.017787084 | +| clip_fraction | 0.368 | +| clip_range | 0.067 | +| entropy_loss | -6.24 | +| explained_variance | -0.0376 | +| learning_rate | 4.24e-05 | +| loss | -0.0333 | +| n_updates | 78028 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000144 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1400 | +| iterations | 15554 | +| time_elapsed | 22750 | +| total_timesteps | 31854592 | +| train/ | | +| approx_kl | 0.014328757 | +| clip_fraction | 0.372 | +| clip_range | 0.067 | +| entropy_loss | -6.27 | +| explained_variance | 0.373 | +| learning_rate | 4.24e-05 | +| loss | -0.0347 | +| n_updates | 78032 | +| policy_gradient_loss | -0.0202 | +| value_loss | 8.61e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1400 | +| iterations | 15555 | +| time_elapsed | 22752 | +| total_timesteps | 31856640 | +| train/ | | +| approx_kl | 0.015353806 | +| clip_fraction | 0.337 | +| clip_range | 0.067 | +| entropy_loss | -6.38 | +| explained_variance | 0.343 | +| learning_rate | 4.24e-05 | +| loss | -0.0249 | +| n_updates | 78036 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000156 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1400 | +| iterations | 15556 | +| time_elapsed | 22753 | +| total_timesteps | 31858688 | +| train/ | | +| approx_kl | 0.0150742605 | +| clip_fraction | 0.351 | +| clip_range | 0.067 | +| entropy_loss | -6.28 | +| explained_variance | 0.376 | +| learning_rate | 4.24e-05 | +| loss | -0.0298 | +| n_updates | 78040 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000132 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1400 | +| iterations | 15557 | +| time_elapsed | 22755 | +| total_timesteps | 31860736 | +| train/ | | +| approx_kl | 0.01232728 | +| clip_fraction | 0.336 | +| clip_range | 0.067 | +| entropy_loss | -6.1 | +| explained_variance | 0.403 | +| learning_rate | 4.24e-05 | +| loss | -0.0237 | +| n_updates | 78044 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000222 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1400 | +| iterations | 15558 | +| time_elapsed | 22757 | +| total_timesteps | 31862784 | +| train/ | | +| approx_kl | 0.011282685 | +| clip_fraction | 0.324 | +| clip_range | 0.067 | +| entropy_loss | -6.07 | +| explained_variance | 0.442 | +| learning_rate | 4.24e-05 | +| loss | -0.034 | +| n_updates | 78048 | +| policy_gradient_loss | -0.0148 | +| value_loss | 0.000179 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1400 | +| iterations | 15559 | +| time_elapsed | 22758 | +| total_timesteps | 31864832 | +| train/ | | +| approx_kl | 0.013088903 | +| clip_fraction | 0.375 | +| clip_range | 0.067 | +| entropy_loss | -6.18 | +| explained_variance | 0.529 | +| learning_rate | 4.24e-05 | +| loss | -0.0353 | +| n_updates | 78052 | +| policy_gradient_loss | -0.023 | +| value_loss | 8.65e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1400 | +| iterations | 15560 | +| time_elapsed | 22760 | +| total_timesteps | 31866880 | +| train/ | | +| approx_kl | 0.013987504 | +| clip_fraction | 0.319 | +| clip_range | 0.067 | +| entropy_loss | -6 | +| explained_variance | 0.522 | +| learning_rate | 4.24e-05 | +| loss | -0.026 | +| n_updates | 78056 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000207 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1400 | +| iterations | 15561 | +| time_elapsed | 22761 | +| total_timesteps | 31868928 | +| train/ | | +| approx_kl | 0.014349116 | +| clip_fraction | 0.369 | +| clip_range | 0.067 | +| entropy_loss | -6.07 | +| explained_variance | 0.11 | +| learning_rate | 4.24e-05 | +| loss | -0.0308 | +| n_updates | 78060 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000134 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1400 | +| iterations | 15562 | +| time_elapsed | 22763 | +| total_timesteps | 31870976 | +| train/ | | +| approx_kl | 0.0131302085 | +| clip_fraction | 0.324 | +| clip_range | 0.067 | +| entropy_loss | -5.81 | +| explained_variance | 0.579 | +| learning_rate | 4.24e-05 | +| loss | -0.0313 | +| n_updates | 78064 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000146 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1400 | +| iterations | 15563 | +| time_elapsed | 22764 | +| total_timesteps | 31873024 | +| train/ | | +| approx_kl | 0.0122761335 | +| clip_fraction | 0.346 | +| clip_range | 0.067 | +| entropy_loss | -6.22 | +| explained_variance | 0.494 | +| learning_rate | 4.24e-05 | +| loss | -0.0292 | +| n_updates | 78068 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000109 | +------------------------------------------ +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1400 | +| iterations | 15564 | +| time_elapsed | 22766 | +| total_timesteps | 31875072 | +| train/ | | +| approx_kl | 0.0191744 | +| clip_fraction | 0.328 | +| clip_range | 0.067 | +| entropy_loss | -6.31 | +| explained_variance | 0.437 | +| learning_rate | 4.24e-05 | +| loss | -0.03 | +| n_updates | 78072 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000166 | +--------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1400 | +| iterations | 15565 | +| time_elapsed | 22767 | +| total_timesteps | 31877120 | +| train/ | | +| approx_kl | 0.01494605 | +| clip_fraction | 0.345 | +| clip_range | 0.067 | +| entropy_loss | -5.95 | +| explained_variance | 0.557 | +| learning_rate | 4.24e-05 | +| loss | -0.0322 | +| n_updates | 78076 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000119 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1400 | +| iterations | 15566 | +| time_elapsed | 22769 | +| total_timesteps | 31879168 | +| train/ | | +| approx_kl | 0.015801778 | +| clip_fraction | 0.369 | +| clip_range | 0.067 | +| entropy_loss | -6.38 | +| explained_variance | 0.224 | +| learning_rate | 4.24e-05 | +| loss | -0.0297 | +| n_updates | 78080 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000162 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1400 | +| iterations | 15567 | +| time_elapsed | 22770 | +| total_timesteps | 31881216 | +| train/ | | +| approx_kl | 0.013272875 | +| clip_fraction | 0.339 | +| clip_range | 0.067 | +| entropy_loss | -6.58 | +| explained_variance | 0.264 | +| learning_rate | 4.24e-05 | +| loss | -0.0271 | +| n_updates | 78084 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000169 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1400 | +| iterations | 15568 | +| time_elapsed | 22772 | +| total_timesteps | 31883264 | +| train/ | | +| approx_kl | 0.012832403 | +| clip_fraction | 0.333 | +| clip_range | 0.067 | +| entropy_loss | -5.94 | +| explained_variance | 0.379 | +| learning_rate | 4.24e-05 | +| loss | -0.0253 | +| n_updates | 78088 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.00022 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1400 | +| iterations | 15569 | +| time_elapsed | 22774 | +| total_timesteps | 31885312 | +| train/ | | +| approx_kl | 0.014346747 | +| clip_fraction | 0.378 | +| clip_range | 0.067 | +| entropy_loss | -6.34 | +| explained_variance | 0.286 | +| learning_rate | 4.24e-05 | +| loss | -0.0346 | +| n_updates | 78092 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000119 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1400 | +| iterations | 15570 | +| time_elapsed | 22775 | +| total_timesteps | 31887360 | +| train/ | | +| approx_kl | 0.01602291 | +| clip_fraction | 0.38 | +| clip_range | 0.067 | +| entropy_loss | -6.34 | +| explained_variance | -0.223 | +| learning_rate | 4.24e-05 | +| loss | -0.0343 | +| n_updates | 78096 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000113 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1400 | +| iterations | 15571 | +| time_elapsed | 22777 | +| total_timesteps | 31889408 | +| train/ | | +| approx_kl | 0.011046762 | +| clip_fraction | 0.301 | +| clip_range | 0.067 | +| entropy_loss | -6.84 | +| explained_variance | -0.0742 | +| learning_rate | 4.24e-05 | +| loss | -0.0305 | +| n_updates | 78100 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000164 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1400 | +| iterations | 15572 | +| time_elapsed | 22778 | +| total_timesteps | 31891456 | +| train/ | | +| approx_kl | 0.012635331 | +| clip_fraction | 0.318 | +| clip_range | 0.067 | +| entropy_loss | -5.89 | +| explained_variance | 0.505 | +| learning_rate | 4.24e-05 | +| loss | -0.0271 | +| n_updates | 78104 | +| policy_gradient_loss | -0.014 | +| value_loss | 0.00024 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1400 | +| iterations | 15573 | +| time_elapsed | 22780 | +| total_timesteps | 31893504 | +| train/ | | +| approx_kl | 0.015997458 | +| clip_fraction | 0.351 | +| clip_range | 0.067 | +| entropy_loss | -4.94 | +| explained_variance | 0.701 | +| learning_rate | 4.24e-05 | +| loss | -0.0322 | +| n_updates | 78108 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000116 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1400 | +| iterations | 15574 | +| time_elapsed | 22781 | +| total_timesteps | 31895552 | +| train/ | | +| approx_kl | 0.0119296685 | +| clip_fraction | 0.312 | +| clip_range | 0.067 | +| entropy_loss | -5.84 | +| explained_variance | 0.476 | +| learning_rate | 4.24e-05 | +| loss | -0.0246 | +| n_updates | 78112 | +| policy_gradient_loss | -0.0146 | +| value_loss | 0.000247 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1400 | +| iterations | 15575 | +| time_elapsed | 22783 | +| total_timesteps | 31897600 | +| train/ | | +| approx_kl | 0.009739046 | +| clip_fraction | 0.324 | +| clip_range | 0.067 | +| entropy_loss | -6.36 | +| explained_variance | 0.199 | +| learning_rate | 4.24e-05 | +| loss | -0.0238 | +| n_updates | 78116 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000289 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1400 | +| iterations | 15576 | +| time_elapsed | 22784 | +| total_timesteps | 31899648 | +| train/ | | +| approx_kl | 0.012667308 | +| clip_fraction | 0.333 | +| clip_range | 0.067 | +| entropy_loss | -6.33 | +| explained_variance | 0.205 | +| learning_rate | 4.24e-05 | +| loss | -0.0306 | +| n_updates | 78120 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000234 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1400 | +| iterations | 15577 | +| time_elapsed | 22786 | +| total_timesteps | 31901696 | +| train/ | | +| approx_kl | 0.016292382 | +| clip_fraction | 0.37 | +| clip_range | 0.067 | +| entropy_loss | -6.15 | +| explained_variance | 0.578 | +| learning_rate | 4.24e-05 | +| loss | -0.0332 | +| n_updates | 78124 | +| policy_gradient_loss | -0.0216 | +| value_loss | 7.98e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1400 | +| iterations | 15578 | +| time_elapsed | 22787 | +| total_timesteps | 31903744 | +| train/ | | +| approx_kl | 0.016237916 | +| clip_fraction | 0.373 | +| clip_range | 0.067 | +| entropy_loss | -6.36 | +| explained_variance | 0.167 | +| learning_rate | 4.24e-05 | +| loss | -0.0332 | +| n_updates | 78128 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000187 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1400 | +| iterations | 15579 | +| time_elapsed | 22789 | +| total_timesteps | 31905792 | +| train/ | | +| approx_kl | 0.01382749 | +| clip_fraction | 0.307 | +| clip_range | 0.067 | +| entropy_loss | -6.12 | +| explained_variance | 0.405 | +| learning_rate | 4.24e-05 | +| loss | -0.0273 | +| n_updates | 78132 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.000343 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1400 | +| iterations | 15580 | +| time_elapsed | 22790 | +| total_timesteps | 31907840 | +| train/ | | +| approx_kl | 0.014445214 | +| clip_fraction | 0.337 | +| clip_range | 0.067 | +| entropy_loss | -5.66 | +| explained_variance | 0.371 | +| learning_rate | 4.24e-05 | +| loss | -0.0315 | +| n_updates | 78136 | +| policy_gradient_loss | -0.0214 | +| value_loss | 8.25e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1400 | +| iterations | 15581 | +| time_elapsed | 22792 | +| total_timesteps | 31909888 | +| train/ | | +| approx_kl | 0.013239204 | +| clip_fraction | 0.324 | +| clip_range | 0.067 | +| entropy_loss | -5.64 | +| explained_variance | 0.538 | +| learning_rate | 4.24e-05 | +| loss | -0.0233 | +| n_updates | 78140 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000208 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1400 | +| iterations | 15582 | +| time_elapsed | 22793 | +| total_timesteps | 31911936 | +| train/ | | +| approx_kl | 0.01573306 | +| clip_fraction | 0.361 | +| clip_range | 0.067 | +| entropy_loss | -5.89 | +| explained_variance | 0.326 | +| learning_rate | 4.24e-05 | +| loss | -0.0331 | +| n_updates | 78144 | +| policy_gradient_loss | -0.0218 | +| value_loss | 8.48e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1400 | +| iterations | 15583 | +| time_elapsed | 22795 | +| total_timesteps | 31913984 | +| train/ | | +| approx_kl | 0.012367735 | +| clip_fraction | 0.334 | +| clip_range | 0.067 | +| entropy_loss | -6.38 | +| explained_variance | 0.221 | +| learning_rate | 4.24e-05 | +| loss | -0.0303 | +| n_updates | 78148 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000193 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1400 | +| iterations | 15584 | +| time_elapsed | 22797 | +| total_timesteps | 31916032 | +| train/ | | +| approx_kl | 0.014225883 | +| clip_fraction | 0.345 | +| clip_range | 0.067 | +| entropy_loss | -6.42 | +| explained_variance | 0.372 | +| learning_rate | 4.24e-05 | +| loss | -0.0268 | +| n_updates | 78152 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000139 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1400 | +| iterations | 15585 | +| time_elapsed | 22798 | +| total_timesteps | 31918080 | +| train/ | | +| approx_kl | 0.011031846 | +| clip_fraction | 0.332 | +| clip_range | 0.067 | +| entropy_loss | -6.25 | +| explained_variance | 0.245 | +| learning_rate | 4.24e-05 | +| loss | -0.0278 | +| n_updates | 78156 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000215 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1399 | +| iterations | 15586 | +| time_elapsed | 22800 | +| total_timesteps | 31920128 | +| train/ | | +| approx_kl | 0.012579647 | +| clip_fraction | 0.342 | +| clip_range | 0.067 | +| entropy_loss | -6 | +| explained_variance | 0.515 | +| learning_rate | 4.24e-05 | +| loss | -0.0235 | +| n_updates | 78160 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000192 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1399 | +| iterations | 15587 | +| time_elapsed | 22801 | +| total_timesteps | 31922176 | +| train/ | | +| approx_kl | 0.010289814 | +| clip_fraction | 0.327 | +| clip_range | 0.067 | +| entropy_loss | -6.13 | +| explained_variance | 0.3 | +| learning_rate | 4.24e-05 | +| loss | -0.0257 | +| n_updates | 78164 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000322 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1399 | +| iterations | 15588 | +| time_elapsed | 22803 | +| total_timesteps | 31924224 | +| train/ | | +| approx_kl | 0.01180443 | +| clip_fraction | 0.331 | +| clip_range | 0.067 | +| entropy_loss | -5.75 | +| explained_variance | 0.536 | +| learning_rate | 4.24e-05 | +| loss | -0.0315 | +| n_updates | 78168 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000199 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1399 | +| iterations | 15589 | +| time_elapsed | 22804 | +| total_timesteps | 31926272 | +| train/ | | +| approx_kl | 0.013872875 | +| clip_fraction | 0.326 | +| clip_range | 0.067 | +| entropy_loss | -5.83 | +| explained_variance | 0.475 | +| learning_rate | 4.24e-05 | +| loss | -0.0298 | +| n_updates | 78172 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000142 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1399 | +| iterations | 15590 | +| time_elapsed | 22806 | +| total_timesteps | 31928320 | +| train/ | | +| approx_kl | 0.013569188 | +| clip_fraction | 0.358 | +| clip_range | 0.067 | +| entropy_loss | -5.85 | +| explained_variance | 0.624 | +| learning_rate | 4.24e-05 | +| loss | -0.0276 | +| n_updates | 78176 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000128 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1399 | +| iterations | 15591 | +| time_elapsed | 22807 | +| total_timesteps | 31930368 | +| train/ | | +| approx_kl | 0.013779307 | +| clip_fraction | 0.32 | +| clip_range | 0.067 | +| entropy_loss | -6.03 | +| explained_variance | 0.0833 | +| learning_rate | 4.24e-05 | +| loss | -0.0236 | +| n_updates | 78180 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000182 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1399 | +| iterations | 15592 | +| time_elapsed | 22809 | +| total_timesteps | 31932416 | +| train/ | | +| approx_kl | 0.011833485 | +| clip_fraction | 0.332 | +| clip_range | 0.067 | +| entropy_loss | -6.89 | +| explained_variance | -0.0188 | +| learning_rate | 4.24e-05 | +| loss | -0.0248 | +| n_updates | 78184 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000166 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1399 | +| iterations | 15593 | +| time_elapsed | 22810 | +| total_timesteps | 31934464 | +| train/ | | +| approx_kl | 0.018172283 | +| clip_fraction | 0.35 | +| clip_range | 0.067 | +| entropy_loss | -6.79 | +| explained_variance | 0.0123 | +| learning_rate | 4.24e-05 | +| loss | -0.031 | +| n_updates | 78188 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.00012 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1399 | +| iterations | 15594 | +| time_elapsed | 22812 | +| total_timesteps | 31936512 | +| train/ | | +| approx_kl | 0.011952854 | +| clip_fraction | 0.326 | +| clip_range | 0.067 | +| entropy_loss | -6.54 | +| explained_variance | 0.271 | +| learning_rate | 4.24e-05 | +| loss | -0.0225 | +| n_updates | 78192 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000271 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1399 | +| iterations | 15595 | +| time_elapsed | 22813 | +| total_timesteps | 31938560 | +| train/ | | +| approx_kl | 0.015154859 | +| clip_fraction | 0.358 | +| clip_range | 0.067 | +| entropy_loss | -6.4 | +| explained_variance | -0.112 | +| learning_rate | 4.24e-05 | +| loss | -0.0358 | +| n_updates | 78196 | +| policy_gradient_loss | -0.0224 | +| value_loss | 0.000114 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1399 | +| iterations | 15596 | +| time_elapsed | 22815 | +| total_timesteps | 31940608 | +| train/ | | +| approx_kl | 0.012865534 | +| clip_fraction | 0.33 | +| clip_range | 0.067 | +| entropy_loss | -6.44 | +| explained_variance | 0.467 | +| learning_rate | 4.24e-05 | +| loss | -0.0272 | +| n_updates | 78200 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000192 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1399 | +| iterations | 15597 | +| time_elapsed | 22816 | +| total_timesteps | 31942656 | +| train/ | | +| approx_kl | 0.011680257 | +| clip_fraction | 0.309 | +| clip_range | 0.067 | +| entropy_loss | -6.18 | +| explained_variance | 0.512 | +| learning_rate | 4.24e-05 | +| loss | -0.0244 | +| n_updates | 78204 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000157 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1399 | +| iterations | 15598 | +| time_elapsed | 22818 | +| total_timesteps | 31944704 | +| train/ | | +| approx_kl | 0.013728432 | +| clip_fraction | 0.332 | +| clip_range | 0.067 | +| entropy_loss | -6.19 | +| explained_variance | 0.207 | +| learning_rate | 4.24e-05 | +| loss | -0.0277 | +| n_updates | 78208 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000203 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1399 | +| iterations | 15599 | +| time_elapsed | 22820 | +| total_timesteps | 31946752 | +| train/ | | +| approx_kl | 0.013977522 | +| clip_fraction | 0.347 | +| clip_range | 0.067 | +| entropy_loss | -6.3 | +| explained_variance | 0.0167 | +| learning_rate | 4.24e-05 | +| loss | -0.026 | +| n_updates | 78212 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000147 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1399 | +| iterations | 15600 | +| time_elapsed | 22821 | +| total_timesteps | 31948800 | +| train/ | | +| approx_kl | 0.013189766 | +| clip_fraction | 0.316 | +| clip_range | 0.067 | +| entropy_loss | -6.5 | +| explained_variance | 0.343 | +| learning_rate | 4.24e-05 | +| loss | -0.0297 | +| n_updates | 78216 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000101 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1399 | +| iterations | 15601 | +| time_elapsed | 22823 | +| total_timesteps | 31950848 | +| train/ | | +| approx_kl | 0.015943017 | +| clip_fraction | 0.323 | +| clip_range | 0.067 | +| entropy_loss | -5.65 | +| explained_variance | 0.696 | +| learning_rate | 4.24e-05 | +| loss | -0.0227 | +| n_updates | 78220 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000133 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1399 | +| iterations | 15602 | +| time_elapsed | 22824 | +| total_timesteps | 31952896 | +| train/ | | +| approx_kl | 0.013453568 | +| clip_fraction | 0.356 | +| clip_range | 0.067 | +| entropy_loss | -6.27 | +| explained_variance | -0.438 | +| learning_rate | 4.24e-05 | +| loss | -0.0401 | +| n_updates | 78224 | +| policy_gradient_loss | -0.0196 | +| value_loss | 4.88e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1399 | +| iterations | 15603 | +| time_elapsed | 22826 | +| total_timesteps | 31954944 | +| train/ | | +| approx_kl | 0.011334076 | +| clip_fraction | 0.342 | +| clip_range | 0.067 | +| entropy_loss | -6.79 | +| explained_variance | 0.233 | +| learning_rate | 4.24e-05 | +| loss | -0.0311 | +| n_updates | 78228 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000131 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1399 | +| iterations | 15604 | +| time_elapsed | 22827 | +| total_timesteps | 31956992 | +| train/ | | +| approx_kl | 0.010544117 | +| clip_fraction | 0.308 | +| clip_range | 0.067 | +| entropy_loss | -6.11 | +| explained_variance | 0.48 | +| learning_rate | 4.24e-05 | +| loss | -0.021 | +| n_updates | 78232 | +| policy_gradient_loss | -0.0135 | +| value_loss | 0.000227 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1399 | +| iterations | 15605 | +| time_elapsed | 22829 | +| total_timesteps | 31959040 | +| train/ | | +| approx_kl | 0.013762863 | +| clip_fraction | 0.347 | +| clip_range | 0.067 | +| entropy_loss | -6.22 | +| explained_variance | 0.509 | +| learning_rate | 4.24e-05 | +| loss | -0.0385 | +| n_updates | 78236 | +| policy_gradient_loss | -0.0214 | +| value_loss | 8.42e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1399 | +| iterations | 15606 | +| time_elapsed | 22830 | +| total_timesteps | 31961088 | +| train/ | | +| approx_kl | 0.013964286 | +| clip_fraction | 0.357 | +| clip_range | 0.067 | +| entropy_loss | -5.83 | +| explained_variance | 0.345 | +| learning_rate | 4.24e-05 | +| loss | -0.0301 | +| n_updates | 78240 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000246 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1399 | +| iterations | 15607 | +| time_elapsed | 22832 | +| total_timesteps | 31963136 | +| train/ | | +| approx_kl | 0.012106197 | +| clip_fraction | 0.345 | +| clip_range | 0.067 | +| entropy_loss | -6.03 | +| explained_variance | 0.479 | +| learning_rate | 4.24e-05 | +| loss | -0.0271 | +| n_updates | 78244 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.00014 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1399 | +| iterations | 15608 | +| time_elapsed | 22833 | +| total_timesteps | 31965184 | +| train/ | | +| approx_kl | 0.0113386065 | +| clip_fraction | 0.321 | +| clip_range | 0.067 | +| entropy_loss | -5.88 | +| explained_variance | 0.622 | +| learning_rate | 4.24e-05 | +| loss | -0.0267 | +| n_updates | 78248 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000168 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1399 | +| iterations | 15609 | +| time_elapsed | 22835 | +| total_timesteps | 31967232 | +| train/ | | +| approx_kl | 0.01191123 | +| clip_fraction | 0.332 | +| clip_range | 0.067 | +| entropy_loss | -5.96 | +| explained_variance | 0.449 | +| learning_rate | 4.24e-05 | +| loss | -0.0221 | +| n_updates | 78252 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000228 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1399 | +| iterations | 15610 | +| time_elapsed | 22836 | +| total_timesteps | 31969280 | +| train/ | | +| approx_kl | 0.013667961 | +| clip_fraction | 0.361 | +| clip_range | 0.067 | +| entropy_loss | -6.44 | +| explained_variance | 0.198 | +| learning_rate | 4.24e-05 | +| loss | -0.0323 | +| n_updates | 78256 | +| policy_gradient_loss | -0.0209 | +| value_loss | 9.26e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1399 | +| iterations | 15611 | +| time_elapsed | 22838 | +| total_timesteps | 31971328 | +| train/ | | +| approx_kl | 0.009504842 | +| clip_fraction | 0.316 | +| clip_range | 0.067 | +| entropy_loss | -6.21 | +| explained_variance | 0.326 | +| learning_rate | 4.24e-05 | +| loss | -0.0157 | +| n_updates | 78260 | +| policy_gradient_loss | -0.0141 | +| value_loss | 0.000412 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1399 | +| iterations | 15612 | +| time_elapsed | 22840 | +| total_timesteps | 31973376 | +| train/ | | +| approx_kl | 0.013037247 | +| clip_fraction | 0.36 | +| clip_range | 0.067 | +| entropy_loss | -5.91 | +| explained_variance | 0.479 | +| learning_rate | 4.24e-05 | +| loss | -0.0324 | +| n_updates | 78264 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000153 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1399 | +| iterations | 15613 | +| time_elapsed | 22841 | +| total_timesteps | 31975424 | +| train/ | | +| approx_kl | 0.012781421 | +| clip_fraction | 0.367 | +| clip_range | 0.067 | +| entropy_loss | -6.41 | +| explained_variance | 0.301 | +| learning_rate | 4.24e-05 | +| loss | -0.0294 | +| n_updates | 78268 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000136 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1399 | +| iterations | 15614 | +| time_elapsed | 22843 | +| total_timesteps | 31977472 | +| train/ | | +| approx_kl | 0.013874708 | +| clip_fraction | 0.327 | +| clip_range | 0.067 | +| entropy_loss | -6.32 | +| explained_variance | 0.152 | +| learning_rate | 4.24e-05 | +| loss | -0.0313 | +| n_updates | 78272 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.00012 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1399 | +| iterations | 15615 | +| time_elapsed | 22844 | +| total_timesteps | 31979520 | +| train/ | | +| approx_kl | 0.0129613 | +| clip_fraction | 0.328 | +| clip_range | 0.067 | +| entropy_loss | -6.65 | +| explained_variance | 0.212 | +| learning_rate | 4.24e-05 | +| loss | -0.0334 | +| n_updates | 78276 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000204 | +--------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1399 | +| iterations | 15616 | +| time_elapsed | 22846 | +| total_timesteps | 31981568 | +| train/ | | +| approx_kl | 0.0155383125 | +| clip_fraction | 0.318 | +| clip_range | 0.067 | +| entropy_loss | -6.02 | +| explained_variance | 0.456 | +| learning_rate | 4.24e-05 | +| loss | -0.0228 | +| n_updates | 78280 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000215 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1399 | +| iterations | 15617 | +| time_elapsed | 22847 | +| total_timesteps | 31983616 | +| train/ | | +| approx_kl | 0.012488555 | +| clip_fraction | 0.337 | +| clip_range | 0.067 | +| entropy_loss | -6 | +| explained_variance | 0.325 | +| learning_rate | 4.24e-05 | +| loss | -0.035 | +| n_updates | 78284 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.00012 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1399 | +| iterations | 15618 | +| time_elapsed | 22849 | +| total_timesteps | 31985664 | +| train/ | | +| approx_kl | 0.013462184 | +| clip_fraction | 0.364 | +| clip_range | 0.067 | +| entropy_loss | -6.35 | +| explained_variance | 0.483 | +| learning_rate | 4.24e-05 | +| loss | -0.0285 | +| n_updates | 78288 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000126 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1399 | +| iterations | 15619 | +| time_elapsed | 22850 | +| total_timesteps | 31987712 | +| train/ | | +| approx_kl | 0.013353694 | +| clip_fraction | 0.339 | +| clip_range | 0.067 | +| entropy_loss | -6.33 | +| explained_variance | 0.551 | +| learning_rate | 4.24e-05 | +| loss | -0.0344 | +| n_updates | 78292 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000122 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1399 | +| iterations | 15620 | +| time_elapsed | 22852 | +| total_timesteps | 31989760 | +| train/ | | +| approx_kl | 0.015312548 | +| clip_fraction | 0.352 | +| clip_range | 0.067 | +| entropy_loss | -6.39 | +| explained_variance | 0.43 | +| learning_rate | 4.24e-05 | +| loss | -0.0337 | +| n_updates | 78296 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000116 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1399 | +| iterations | 15621 | +| time_elapsed | 22853 | +| total_timesteps | 31991808 | +| train/ | | +| approx_kl | 0.015500881 | +| clip_fraction | 0.318 | +| clip_range | 0.067 | +| entropy_loss | -5.95 | +| explained_variance | 0.556 | +| learning_rate | 4.24e-05 | +| loss | -0.025 | +| n_updates | 78300 | +| policy_gradient_loss | -0.0145 | +| value_loss | 0.000237 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1399 | +| iterations | 15622 | +| time_elapsed | 22855 | +| total_timesteps | 31993856 | +| train/ | | +| approx_kl | 0.012511069 | +| clip_fraction | 0.357 | +| clip_range | 0.067 | +| entropy_loss | -5.78 | +| explained_variance | 0.524 | +| learning_rate | 4.24e-05 | +| loss | -0.0271 | +| n_updates | 78304 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000137 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1399 | +| iterations | 15623 | +| time_elapsed | 22856 | +| total_timesteps | 31995904 | +| train/ | | +| approx_kl | 0.013310472 | +| clip_fraction | 0.346 | +| clip_range | 0.067 | +| entropy_loss | -6.27 | +| explained_variance | 0.0901 | +| learning_rate | 4.24e-05 | +| loss | -0.0339 | +| n_updates | 78308 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000151 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1399 | +| iterations | 15624 | +| time_elapsed | 22858 | +| total_timesteps | 31997952 | +| train/ | | +| approx_kl | 0.015518362 | +| clip_fraction | 0.35 | +| clip_range | 0.067 | +| entropy_loss | -6.62 | +| explained_variance | 0.174 | +| learning_rate | 4.24e-05 | +| loss | -0.0292 | +| n_updates | 78312 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000121 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1399 | +| iterations | 15625 | +| time_elapsed | 22859 | +| total_timesteps | 32000000 | +| train/ | | +| approx_kl | 0.010523421 | +| clip_fraction | 0.321 | +| clip_range | 0.067 | +| entropy_loss | -6.47 | +| explained_variance | 0.181 | +| learning_rate | 4.24e-05 | +| loss | -0.022 | +| n_updates | 78316 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000296 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1399 | +| iterations | 15626 | +| time_elapsed | 22861 | +| total_timesteps | 32002048 | +| train/ | | +| approx_kl | 0.0136882495 | +| clip_fraction | 0.345 | +| clip_range | 0.067 | +| entropy_loss | -6.18 | +| explained_variance | 0.518 | +| learning_rate | 4.24e-05 | +| loss | -0.0302 | +| n_updates | 78320 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000121 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1399 | +| iterations | 15627 | +| time_elapsed | 22862 | +| total_timesteps | 32004096 | +| train/ | | +| approx_kl | 0.0116879195 | +| clip_fraction | 0.31 | +| clip_range | 0.067 | +| entropy_loss | -5.69 | +| explained_variance | 0.626 | +| learning_rate | 4.24e-05 | +| loss | -0.0291 | +| n_updates | 78324 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000183 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1399 | +| iterations | 15628 | +| time_elapsed | 22864 | +| total_timesteps | 32006144 | +| train/ | | +| approx_kl | 0.0112473145 | +| clip_fraction | 0.325 | +| clip_range | 0.067 | +| entropy_loss | -6.04 | +| explained_variance | 0.367 | +| learning_rate | 4.24e-05 | +| loss | -0.0288 | +| n_updates | 78328 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000144 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1399 | +| iterations | 15629 | +| time_elapsed | 22866 | +| total_timesteps | 32008192 | +| train/ | | +| approx_kl | 0.012107583 | +| clip_fraction | 0.334 | +| clip_range | 0.067 | +| entropy_loss | -6.18 | +| explained_variance | 0.483 | +| learning_rate | 4.24e-05 | +| loss | -0.0304 | +| n_updates | 78332 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000181 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1399 | +| iterations | 15630 | +| time_elapsed | 22867 | +| total_timesteps | 32010240 | +| train/ | | +| approx_kl | 0.012072183 | +| clip_fraction | 0.339 | +| clip_range | 0.067 | +| entropy_loss | -5.94 | +| explained_variance | 0.364 | +| learning_rate | 4.24e-05 | +| loss | -0.0246 | +| n_updates | 78336 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000129 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1399 | +| iterations | 15631 | +| time_elapsed | 22869 | +| total_timesteps | 32012288 | +| train/ | | +| approx_kl | 0.014654804 | +| clip_fraction | 0.337 | +| clip_range | 0.067 | +| entropy_loss | -5.94 | +| explained_variance | 0.571 | +| learning_rate | 4.24e-05 | +| loss | -0.0281 | +| n_updates | 78340 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000173 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1399 | +| iterations | 15632 | +| time_elapsed | 22870 | +| total_timesteps | 32014336 | +| train/ | | +| approx_kl | 0.01141198 | +| clip_fraction | 0.339 | +| clip_range | 0.067 | +| entropy_loss | -6.71 | +| explained_variance | -0.128 | +| learning_rate | 4.24e-05 | +| loss | -0.028 | +| n_updates | 78344 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000135 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1399 | +| iterations | 15633 | +| time_elapsed | 22872 | +| total_timesteps | 32016384 | +| train/ | | +| approx_kl | 0.01247352 | +| clip_fraction | 0.332 | +| clip_range | 0.067 | +| entropy_loss | -6.52 | +| explained_variance | 0.272 | +| learning_rate | 4.24e-05 | +| loss | -0.0208 | +| n_updates | 78348 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000278 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1399 | +| iterations | 15634 | +| time_elapsed | 22873 | +| total_timesteps | 32018432 | +| train/ | | +| approx_kl | 0.0122455945 | +| clip_fraction | 0.329 | +| clip_range | 0.067 | +| entropy_loss | -6.18 | +| explained_variance | 0.331 | +| learning_rate | 4.24e-05 | +| loss | -0.0313 | +| n_updates | 78352 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000161 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1399 | +| iterations | 15635 | +| time_elapsed | 22875 | +| total_timesteps | 32020480 | +| train/ | | +| approx_kl | 0.011699224 | +| clip_fraction | 0.334 | +| clip_range | 0.067 | +| entropy_loss | -6.73 | +| explained_variance | 0.156 | +| learning_rate | 4.24e-05 | +| loss | -0.0285 | +| n_updates | 78356 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000233 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1399 | +| iterations | 15636 | +| time_elapsed | 22876 | +| total_timesteps | 32022528 | +| train/ | | +| approx_kl | 0.0126139615 | +| clip_fraction | 0.325 | +| clip_range | 0.067 | +| entropy_loss | -6.55 | +| explained_variance | 0.327 | +| learning_rate | 4.24e-05 | +| loss | -0.0266 | +| n_updates | 78360 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000165 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1399 | +| iterations | 15637 | +| time_elapsed | 22878 | +| total_timesteps | 32024576 | +| train/ | | +| approx_kl | 0.014946785 | +| clip_fraction | 0.358 | +| clip_range | 0.067 | +| entropy_loss | -6.2 | +| explained_variance | 0.325 | +| learning_rate | 4.24e-05 | +| loss | -0.0345 | +| n_updates | 78364 | +| policy_gradient_loss | -0.0223 | +| value_loss | 0.00012 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1399 | +| iterations | 15638 | +| time_elapsed | 22879 | +| total_timesteps | 32026624 | +| train/ | | +| approx_kl | 0.010342419 | +| clip_fraction | 0.319 | +| clip_range | 0.067 | +| entropy_loss | -6.72 | +| explained_variance | 0.279 | +| learning_rate | 4.24e-05 | +| loss | -0.0239 | +| n_updates | 78368 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000174 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1399 | +| iterations | 15639 | +| time_elapsed | 22881 | +| total_timesteps | 32028672 | +| train/ | | +| approx_kl | 0.009771151 | +| clip_fraction | 0.33 | +| clip_range | 0.067 | +| entropy_loss | -6.68 | +| explained_variance | 0.517 | +| learning_rate | 4.24e-05 | +| loss | -0.0232 | +| n_updates | 78372 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000149 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1399 | +| iterations | 15640 | +| time_elapsed | 22882 | +| total_timesteps | 32030720 | +| train/ | | +| approx_kl | 0.0118612 | +| clip_fraction | 0.328 | +| clip_range | 0.067 | +| entropy_loss | -6.17 | +| explained_variance | 0.348 | +| learning_rate | 4.24e-05 | +| loss | -0.0305 | +| n_updates | 78376 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000152 | +--------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1399 | +| iterations | 15641 | +| time_elapsed | 22884 | +| total_timesteps | 32032768 | +| train/ | | +| approx_kl | 0.0120252855 | +| clip_fraction | 0.309 | +| clip_range | 0.067 | +| entropy_loss | -5.81 | +| explained_variance | 0.673 | +| learning_rate | 4.24e-05 | +| loss | -0.0247 | +| n_updates | 78380 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.00014 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1399 | +| iterations | 15642 | +| time_elapsed | 22885 | +| total_timesteps | 32034816 | +| train/ | | +| approx_kl | 0.009992536 | +| clip_fraction | 0.311 | +| clip_range | 0.067 | +| entropy_loss | -6.4 | +| explained_variance | 0.325 | +| learning_rate | 4.24e-05 | +| loss | -0.0242 | +| n_updates | 78384 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000164 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1399 | +| iterations | 15643 | +| time_elapsed | 22887 | +| total_timesteps | 32036864 | +| train/ | | +| approx_kl | 0.011235176 | +| clip_fraction | 0.337 | +| clip_range | 0.067 | +| entropy_loss | -6.48 | +| explained_variance | 0.267 | +| learning_rate | 4.24e-05 | +| loss | -0.0231 | +| n_updates | 78388 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.00023 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1399 | +| iterations | 15644 | +| time_elapsed | 22888 | +| total_timesteps | 32038912 | +| train/ | | +| approx_kl | 0.013289556 | +| clip_fraction | 0.318 | +| clip_range | 0.067 | +| entropy_loss | -5.82 | +| explained_variance | 0.428 | +| learning_rate | 4.24e-05 | +| loss | -0.0204 | +| n_updates | 78392 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000317 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1399 | +| iterations | 15645 | +| time_elapsed | 22890 | +| total_timesteps | 32040960 | +| train/ | | +| approx_kl | 0.01362565 | +| clip_fraction | 0.363 | +| clip_range | 0.067 | +| entropy_loss | -5.94 | +| explained_variance | 0.601 | +| learning_rate | 4.24e-05 | +| loss | -0.0304 | +| n_updates | 78396 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000114 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1399 | +| iterations | 15646 | +| time_elapsed | 22891 | +| total_timesteps | 32043008 | +| train/ | | +| approx_kl | 0.013459457 | +| clip_fraction | 0.3 | +| clip_range | 0.067 | +| entropy_loss | -6.17 | +| explained_variance | 0.28 | +| learning_rate | 4.24e-05 | +| loss | -0.0187 | +| n_updates | 78400 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000251 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1399 | +| iterations | 15647 | +| time_elapsed | 22893 | +| total_timesteps | 32045056 | +| train/ | | +| approx_kl | 0.011556937 | +| clip_fraction | 0.321 | +| clip_range | 0.067 | +| entropy_loss | -6.16 | +| explained_variance | 0.427 | +| learning_rate | 4.24e-05 | +| loss | -0.0282 | +| n_updates | 78404 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000267 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1399 | +| iterations | 15648 | +| time_elapsed | 22894 | +| total_timesteps | 32047104 | +| train/ | | +| approx_kl | 0.011404722 | +| clip_fraction | 0.307 | +| clip_range | 0.067 | +| entropy_loss | -5.85 | +| explained_variance | 0.217 | +| learning_rate | 4.24e-05 | +| loss | -0.0237 | +| n_updates | 78408 | +| policy_gradient_loss | -0.0141 | +| value_loss | 0.000507 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1399 | +| iterations | 15649 | +| time_elapsed | 22896 | +| total_timesteps | 32049152 | +| train/ | | +| approx_kl | 0.0103290565 | +| clip_fraction | 0.305 | +| clip_range | 0.067 | +| entropy_loss | -5.72 | +| explained_variance | 0.338 | +| learning_rate | 4.24e-05 | +| loss | -0.026 | +| n_updates | 78412 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000384 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1399 | +| iterations | 15650 | +| time_elapsed | 22897 | +| total_timesteps | 32051200 | +| train/ | | +| approx_kl | 0.009684756 | +| clip_fraction | 0.327 | +| clip_range | 0.067 | +| entropy_loss | -6.8 | +| explained_variance | 0.0631 | +| learning_rate | 4.24e-05 | +| loss | -0.0275 | +| n_updates | 78416 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000232 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1399 | +| iterations | 15651 | +| time_elapsed | 22899 | +| total_timesteps | 32053248 | +| train/ | | +| approx_kl | 0.009371785 | +| clip_fraction | 0.331 | +| clip_range | 0.067 | +| entropy_loss | -6.84 | +| explained_variance | 0.237 | +| learning_rate | 4.24e-05 | +| loss | -0.0301 | +| n_updates | 78420 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000272 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1399 | +| iterations | 15652 | +| time_elapsed | 22900 | +| total_timesteps | 32055296 | +| train/ | | +| approx_kl | 0.014125595 | +| clip_fraction | 0.345 | +| clip_range | 0.067 | +| entropy_loss | -6.27 | +| explained_variance | 0.249 | +| learning_rate | 4.24e-05 | +| loss | -0.0229 | +| n_updates | 78424 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000371 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1399 | +| iterations | 15653 | +| time_elapsed | 22902 | +| total_timesteps | 32057344 | +| train/ | | +| approx_kl | 0.010708101 | +| clip_fraction | 0.331 | +| clip_range | 0.067 | +| entropy_loss | -6.21 | +| explained_variance | 0.18 | +| learning_rate | 4.24e-05 | +| loss | -0.0349 | +| n_updates | 78428 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000424 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1399 | +| iterations | 15654 | +| time_elapsed | 22903 | +| total_timesteps | 32059392 | +| train/ | | +| approx_kl | 0.010161404 | +| clip_fraction | 0.305 | +| clip_range | 0.067 | +| entropy_loss | -5.48 | +| explained_variance | 0.472 | +| learning_rate | 4.24e-05 | +| loss | -0.0256 | +| n_updates | 78432 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000346 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1399 | +| iterations | 15655 | +| time_elapsed | 22905 | +| total_timesteps | 32061440 | +| train/ | | +| approx_kl | 0.014551105 | +| clip_fraction | 0.381 | +| clip_range | 0.067 | +| entropy_loss | -5.69 | +| explained_variance | 0.629 | +| learning_rate | 4.24e-05 | +| loss | -0.0393 | +| n_updates | 78436 | +| policy_gradient_loss | -0.0232 | +| value_loss | 9.04e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1399 | +| iterations | 15656 | +| time_elapsed | 22907 | +| total_timesteps | 32063488 | +| train/ | | +| approx_kl | 0.012486233 | +| clip_fraction | 0.351 | +| clip_range | 0.067 | +| entropy_loss | -6.99 | +| explained_variance | -0.213 | +| learning_rate | 4.24e-05 | +| loss | -0.0336 | +| n_updates | 78440 | +| policy_gradient_loss | -0.0213 | +| value_loss | 9.27e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1399 | +| iterations | 15657 | +| time_elapsed | 22908 | +| total_timesteps | 32065536 | +| train/ | | +| approx_kl | 0.010721608 | +| clip_fraction | 0.325 | +| clip_range | 0.067 | +| entropy_loss | -5.96 | +| explained_variance | 0.534 | +| learning_rate | 4.24e-05 | +| loss | -0.0273 | +| n_updates | 78444 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000178 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1399 | +| iterations | 15658 | +| time_elapsed | 22910 | +| total_timesteps | 32067584 | +| train/ | | +| approx_kl | 0.01491713 | +| clip_fraction | 0.35 | +| clip_range | 0.067 | +| entropy_loss | -5.76 | +| explained_variance | 0.293 | +| learning_rate | 4.24e-05 | +| loss | -0.0348 | +| n_updates | 78448 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000137 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1399 | +| iterations | 15659 | +| time_elapsed | 22911 | +| total_timesteps | 32069632 | +| train/ | | +| approx_kl | 0.014915105 | +| clip_fraction | 0.345 | +| clip_range | 0.067 | +| entropy_loss | -6.3 | +| explained_variance | 0.459 | +| learning_rate | 4.24e-05 | +| loss | -0.0296 | +| n_updates | 78452 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000117 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1399 | +| iterations | 15660 | +| time_elapsed | 22913 | +| total_timesteps | 32071680 | +| train/ | | +| approx_kl | 0.013846874 | +| clip_fraction | 0.348 | +| clip_range | 0.067 | +| entropy_loss | -6.85 | +| explained_variance | -0.0519 | +| learning_rate | 4.24e-05 | +| loss | -0.0296 | +| n_updates | 78456 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000148 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1399 | +| iterations | 15661 | +| time_elapsed | 22914 | +| total_timesteps | 32073728 | +| train/ | | +| approx_kl | 0.0133222565 | +| clip_fraction | 0.329 | +| clip_range | 0.067 | +| entropy_loss | -6.63 | +| explained_variance | 0.23 | +| learning_rate | 4.24e-05 | +| loss | -0.0248 | +| n_updates | 78460 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.0002 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1399 | +| iterations | 15662 | +| time_elapsed | 22916 | +| total_timesteps | 32075776 | +| train/ | | +| approx_kl | 0.01802181 | +| clip_fraction | 0.307 | +| clip_range | 0.067 | +| entropy_loss | -5.83 | +| explained_variance | 0.534 | +| learning_rate | 4.24e-05 | +| loss | -0.0267 | +| n_updates | 78464 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000159 | +---------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1399 | +| iterations | 15663 | +| time_elapsed | 22917 | +| total_timesteps | 32077824 | +| train/ | | +| approx_kl | 0.0130897 | +| clip_fraction | 0.339 | +| clip_range | 0.067 | +| entropy_loss | -5.43 | +| explained_variance | 0.618 | +| learning_rate | 4.24e-05 | +| loss | -0.028 | +| n_updates | 78468 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000145 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1399 | +| iterations | 15664 | +| time_elapsed | 22919 | +| total_timesteps | 32079872 | +| train/ | | +| approx_kl | 0.011929639 | +| clip_fraction | 0.326 | +| clip_range | 0.067 | +| entropy_loss | -5.69 | +| explained_variance | 0.145 | +| learning_rate | 4.24e-05 | +| loss | -0.022 | +| n_updates | 78472 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.00046 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1399 | +| iterations | 15665 | +| time_elapsed | 22921 | +| total_timesteps | 32081920 | +| train/ | | +| approx_kl | 0.012939706 | +| clip_fraction | 0.349 | +| clip_range | 0.067 | +| entropy_loss | -6 | +| explained_variance | 0.387 | +| learning_rate | 4.24e-05 | +| loss | -0.0318 | +| n_updates | 78476 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000203 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1399 | +| iterations | 15666 | +| time_elapsed | 22922 | +| total_timesteps | 32083968 | +| train/ | | +| approx_kl | 0.01426114 | +| clip_fraction | 0.337 | +| clip_range | 0.067 | +| entropy_loss | -5.78 | +| explained_variance | 0.483 | +| learning_rate | 4.24e-05 | +| loss | -0.0266 | +| n_updates | 78480 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000234 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1399 | +| iterations | 15667 | +| time_elapsed | 22924 | +| total_timesteps | 32086016 | +| train/ | | +| approx_kl | 0.012503717 | +| clip_fraction | 0.335 | +| clip_range | 0.067 | +| entropy_loss | -6.65 | +| explained_variance | 0.0596 | +| learning_rate | 4.24e-05 | +| loss | -0.0282 | +| n_updates | 78484 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000203 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1399 | +| iterations | 15668 | +| time_elapsed | 22925 | +| total_timesteps | 32088064 | +| train/ | | +| approx_kl | 0.010439854 | +| clip_fraction | 0.319 | +| clip_range | 0.067 | +| entropy_loss | -5.97 | +| explained_variance | 0.466 | +| learning_rate | 4.24e-05 | +| loss | -0.0172 | +| n_updates | 78488 | +| policy_gradient_loss | -0.0143 | +| value_loss | 0.000335 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1399 | +| iterations | 15669 | +| time_elapsed | 22927 | +| total_timesteps | 32090112 | +| train/ | | +| approx_kl | 0.012706161 | +| clip_fraction | 0.353 | +| clip_range | 0.067 | +| entropy_loss | -6.2 | +| explained_variance | 0.342 | +| learning_rate | 4.24e-05 | +| loss | -0.0296 | +| n_updates | 78492 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000151 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1399 | +| iterations | 15670 | +| time_elapsed | 22928 | +| total_timesteps | 32092160 | +| train/ | | +| approx_kl | 0.009883535 | +| clip_fraction | 0.313 | +| clip_range | 0.067 | +| entropy_loss | -6.06 | +| explained_variance | 0.363 | +| learning_rate | 4.24e-05 | +| loss | -0.0315 | +| n_updates | 78496 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000191 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1399 | +| iterations | 15671 | +| time_elapsed | 22930 | +| total_timesteps | 32094208 | +| train/ | | +| approx_kl | 0.013032362 | +| clip_fraction | 0.328 | +| clip_range | 0.067 | +| entropy_loss | -6.81 | +| explained_variance | 0.235 | +| learning_rate | 4.24e-05 | +| loss | -0.0334 | +| n_updates | 78500 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000122 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1399 | +| iterations | 15672 | +| time_elapsed | 22931 | +| total_timesteps | 32096256 | +| train/ | | +| approx_kl | 0.0113695515 | +| clip_fraction | 0.323 | +| clip_range | 0.067 | +| entropy_loss | -6.61 | +| explained_variance | 0.335 | +| learning_rate | 4.24e-05 | +| loss | -0.0254 | +| n_updates | 78504 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000303 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1399 | +| iterations | 15673 | +| time_elapsed | 22933 | +| total_timesteps | 32098304 | +| train/ | | +| approx_kl | 0.011579504 | +| clip_fraction | 0.34 | +| clip_range | 0.067 | +| entropy_loss | -6.37 | +| explained_variance | 0.389 | +| learning_rate | 4.24e-05 | +| loss | -0.03 | +| n_updates | 78508 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000128 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1399 | +| iterations | 15674 | +| time_elapsed | 22934 | +| total_timesteps | 32100352 | +| train/ | | +| approx_kl | 0.008658803 | +| clip_fraction | 0.311 | +| clip_range | 0.067 | +| entropy_loss | -6.03 | +| explained_variance | 0.543 | +| learning_rate | 4.24e-05 | +| loss | -0.0244 | +| n_updates | 78512 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.000187 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1399 | +| iterations | 15675 | +| time_elapsed | 22936 | +| total_timesteps | 32102400 | +| train/ | | +| approx_kl | 0.013016766 | +| clip_fraction | 0.328 | +| clip_range | 0.067 | +| entropy_loss | -5.5 | +| explained_variance | 0.518 | +| learning_rate | 4.24e-05 | +| loss | -0.0228 | +| n_updates | 78516 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000235 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.389 | +| time/ | | +| fps | 1399 | +| iterations | 15676 | +| time_elapsed | 22937 | +| total_timesteps | 32104448 | +| train/ | | +| approx_kl | 0.011863722 | +| clip_fraction | 0.348 | +| clip_range | 0.067 | +| entropy_loss | -5.73 | +| explained_variance | 0.605 | +| learning_rate | 4.24e-05 | +| loss | -0.0296 | +| n_updates | 78520 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000135 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.389 | +| time/ | | +| fps | 1399 | +| iterations | 15677 | +| time_elapsed | 22939 | +| total_timesteps | 32106496 | +| train/ | | +| approx_kl | 0.013815861 | +| clip_fraction | 0.34 | +| clip_range | 0.067 | +| entropy_loss | -6.19 | +| explained_variance | 0.263 | +| learning_rate | 4.24e-05 | +| loss | -0.0305 | +| n_updates | 78524 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000215 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.389 | +| time/ | | +| fps | 1399 | +| iterations | 15678 | +| time_elapsed | 22941 | +| total_timesteps | 32108544 | +| train/ | | +| approx_kl | 0.015002356 | +| clip_fraction | 0.357 | +| clip_range | 0.067 | +| entropy_loss | -6.71 | +| explained_variance | -0.154 | +| learning_rate | 4.24e-05 | +| loss | -0.0308 | +| n_updates | 78528 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000135 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.388 | +| time/ | | +| fps | 1399 | +| iterations | 15679 | +| time_elapsed | 22942 | +| total_timesteps | 32110592 | +| train/ | | +| approx_kl | 0.014032524 | +| clip_fraction | 0.351 | +| clip_range | 0.067 | +| entropy_loss | -6.76 | +| explained_variance | -0.217 | +| learning_rate | 4.24e-05 | +| loss | -0.033 | +| n_updates | 78532 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.00011 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.394 | +| time/ | | +| fps | 1399 | +| iterations | 15680 | +| time_elapsed | 22944 | +| total_timesteps | 32112640 | +| train/ | | +| approx_kl | 0.014278657 | +| clip_fraction | 0.32 | +| clip_range | 0.067 | +| entropy_loss | -6.65 | +| explained_variance | 0.0722 | +| learning_rate | 4.24e-05 | +| loss | -0.0288 | +| n_updates | 78536 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000157 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.39 | +| time/ | | +| fps | 1399 | +| iterations | 15681 | +| time_elapsed | 22945 | +| total_timesteps | 32114688 | +| train/ | | +| approx_kl | 0.015211572 | +| clip_fraction | 0.326 | +| clip_range | 0.067 | +| entropy_loss | -5.85 | +| explained_variance | 0.591 | +| learning_rate | 4.24e-05 | +| loss | -0.0256 | +| n_updates | 78540 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000164 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.39 | +| time/ | | +| fps | 1399 | +| iterations | 15682 | +| time_elapsed | 22947 | +| total_timesteps | 32116736 | +| train/ | | +| approx_kl | 0.011408068 | +| clip_fraction | 0.312 | +| clip_range | 0.067 | +| entropy_loss | -5.35 | +| explained_variance | 0.492 | +| learning_rate | 4.24e-05 | +| loss | -0.0266 | +| n_updates | 78544 | +| policy_gradient_loss | -0.0138 | +| value_loss | 8.22e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.389 | +| time/ | | +| fps | 1399 | +| iterations | 15683 | +| time_elapsed | 22948 | +| total_timesteps | 32118784 | +| train/ | | +| approx_kl | 0.012501185 | +| clip_fraction | 0.325 | +| clip_range | 0.067 | +| entropy_loss | -6 | +| explained_variance | 0.702 | +| learning_rate | 4.24e-05 | +| loss | -0.0284 | +| n_updates | 78548 | +| policy_gradient_loss | -0.0161 | +| value_loss | 7.79e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.384 | +| time/ | | +| fps | 1399 | +| iterations | 15684 | +| time_elapsed | 22950 | +| total_timesteps | 32120832 | +| train/ | | +| approx_kl | 0.014883973 | +| clip_fraction | 0.354 | +| clip_range | 0.067 | +| entropy_loss | -5.94 | +| explained_variance | 0.717 | +| learning_rate | 4.24e-05 | +| loss | -0.0284 | +| n_updates | 78552 | +| policy_gradient_loss | -0.0182 | +| value_loss | 9.21e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.387 | +| time/ | | +| fps | 1399 | +| iterations | 15685 | +| time_elapsed | 22952 | +| total_timesteps | 32122880 | +| train/ | | +| approx_kl | 0.013129645 | +| clip_fraction | 0.315 | +| clip_range | 0.067 | +| entropy_loss | -5.54 | +| explained_variance | 0.551 | +| learning_rate | 4.24e-05 | +| loss | -0.0283 | +| n_updates | 78556 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000124 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.391 | +| time/ | | +| fps | 1399 | +| iterations | 15686 | +| time_elapsed | 22953 | +| total_timesteps | 32124928 | +| train/ | | +| approx_kl | 0.013258727 | +| clip_fraction | 0.317 | +| clip_range | 0.067 | +| entropy_loss | -5.45 | +| explained_variance | 0.698 | +| learning_rate | 4.24e-05 | +| loss | -0.0277 | +| n_updates | 78560 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000104 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.388 | +| time/ | | +| fps | 1399 | +| iterations | 15687 | +| time_elapsed | 22955 | +| total_timesteps | 32126976 | +| train/ | | +| approx_kl | 0.014033484 | +| clip_fraction | 0.326 | +| clip_range | 0.067 | +| entropy_loss | -6.29 | +| explained_variance | 0.33 | +| learning_rate | 4.24e-05 | +| loss | -0.0291 | +| n_updates | 78564 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000161 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.385 | +| time/ | | +| fps | 1399 | +| iterations | 15688 | +| time_elapsed | 22956 | +| total_timesteps | 32129024 | +| train/ | | +| approx_kl | 0.019055318 | +| clip_fraction | 0.377 | +| clip_range | 0.067 | +| entropy_loss | -6.18 | +| explained_variance | 0.498 | +| learning_rate | 4.24e-05 | +| loss | -0.0315 | +| n_updates | 78568 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000112 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.387 | +| time/ | | +| fps | 1399 | +| iterations | 15689 | +| time_elapsed | 22958 | +| total_timesteps | 32131072 | +| train/ | | +| approx_kl | 0.018970188 | +| clip_fraction | 0.359 | +| clip_range | 0.067 | +| entropy_loss | -6.2 | +| explained_variance | 0.244 | +| learning_rate | 4.24e-05 | +| loss | -0.0332 | +| n_updates | 78572 | +| policy_gradient_loss | -0.02 | +| value_loss | 8.02e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.387 | +| time/ | | +| fps | 1399 | +| iterations | 15690 | +| time_elapsed | 22959 | +| total_timesteps | 32133120 | +| train/ | | +| approx_kl | 0.01474112 | +| clip_fraction | 0.355 | +| clip_range | 0.067 | +| entropy_loss | -6.17 | +| explained_variance | 0.374 | +| learning_rate | 4.24e-05 | +| loss | -0.0225 | +| n_updates | 78576 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000234 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.392 | +| time/ | | +| fps | 1399 | +| iterations | 15691 | +| time_elapsed | 22961 | +| total_timesteps | 32135168 | +| train/ | | +| approx_kl | 0.018156253 | +| clip_fraction | 0.382 | +| clip_range | 0.067 | +| entropy_loss | -6.11 | +| explained_variance | 0.453 | +| learning_rate | 4.24e-05 | +| loss | -0.0391 | +| n_updates | 78580 | +| policy_gradient_loss | -0.0225 | +| value_loss | 9.07e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.384 | +| time/ | | +| fps | 1399 | +| iterations | 15692 | +| time_elapsed | 22962 | +| total_timesteps | 32137216 | +| train/ | | +| approx_kl | 0.01286211 | +| clip_fraction | 0.314 | +| clip_range | 0.067 | +| entropy_loss | -5.46 | +| explained_variance | 0.465 | +| learning_rate | 4.24e-05 | +| loss | -0.022 | +| n_updates | 78584 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000264 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.384 | +| time/ | | +| fps | 1399 | +| iterations | 15693 | +| time_elapsed | 22964 | +| total_timesteps | 32139264 | +| train/ | | +| approx_kl | 0.013607209 | +| clip_fraction | 0.347 | +| clip_range | 0.067 | +| entropy_loss | -5.91 | +| explained_variance | 0.397 | +| learning_rate | 4.24e-05 | +| loss | -0.0331 | +| n_updates | 78588 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.00013 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1399 | +| iterations | 15694 | +| time_elapsed | 22965 | +| total_timesteps | 32141312 | +| train/ | | +| approx_kl | 0.015408767 | +| clip_fraction | 0.371 | +| clip_range | 0.067 | +| entropy_loss | -6.05 | +| explained_variance | 0.219 | +| learning_rate | 4.24e-05 | +| loss | -0.0343 | +| n_updates | 78592 | +| policy_gradient_loss | -0.0204 | +| value_loss | 8.8e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1399 | +| iterations | 15695 | +| time_elapsed | 22967 | +| total_timesteps | 32143360 | +| train/ | | +| approx_kl | 0.012962654 | +| clip_fraction | 0.344 | +| clip_range | 0.067 | +| entropy_loss | -6.33 | +| explained_variance | 0.399 | +| learning_rate | 4.24e-05 | +| loss | -0.0276 | +| n_updates | 78596 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.00022 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1399 | +| iterations | 15696 | +| time_elapsed | 22968 | +| total_timesteps | 32145408 | +| train/ | | +| approx_kl | 0.012583016 | +| clip_fraction | 0.317 | +| clip_range | 0.067 | +| entropy_loss | -5.84 | +| explained_variance | 0.527 | +| learning_rate | 4.24e-05 | +| loss | -0.0264 | +| n_updates | 78600 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000111 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1399 | +| iterations | 15697 | +| time_elapsed | 22970 | +| total_timesteps | 32147456 | +| train/ | | +| approx_kl | 0.014378652 | +| clip_fraction | 0.367 | +| clip_range | 0.067 | +| entropy_loss | -6.08 | +| explained_variance | 0.507 | +| learning_rate | 4.24e-05 | +| loss | -0.0376 | +| n_updates | 78604 | +| policy_gradient_loss | -0.0213 | +| value_loss | 9.2e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1399 | +| iterations | 15698 | +| time_elapsed | 22971 | +| total_timesteps | 32149504 | +| train/ | | +| approx_kl | 0.01452636 | +| clip_fraction | 0.372 | +| clip_range | 0.067 | +| entropy_loss | -6.2 | +| explained_variance | 0.296 | +| learning_rate | 4.24e-05 | +| loss | -0.0259 | +| n_updates | 78608 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.00016 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1399 | +| iterations | 15699 | +| time_elapsed | 22973 | +| total_timesteps | 32151552 | +| train/ | | +| approx_kl | 0.01169979 | +| clip_fraction | 0.32 | +| clip_range | 0.067 | +| entropy_loss | -5.94 | +| explained_variance | 0.351 | +| learning_rate | 4.24e-05 | +| loss | -0.0191 | +| n_updates | 78612 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000277 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1399 | +| iterations | 15700 | +| time_elapsed | 22975 | +| total_timesteps | 32153600 | +| train/ | | +| approx_kl | 0.013072651 | +| clip_fraction | 0.329 | +| clip_range | 0.067 | +| entropy_loss | -5.67 | +| explained_variance | 0.438 | +| learning_rate | 4.24e-05 | +| loss | -0.0243 | +| n_updates | 78616 | +| policy_gradient_loss | -0.0148 | +| value_loss | 0.000263 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1399 | +| iterations | 15701 | +| time_elapsed | 22976 | +| total_timesteps | 32155648 | +| train/ | | +| approx_kl | 0.01145863 | +| clip_fraction | 0.332 | +| clip_range | 0.067 | +| entropy_loss | -5.62 | +| explained_variance | 0.507 | +| learning_rate | 4.24e-05 | +| loss | -0.0293 | +| n_updates | 78620 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000172 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1399 | +| iterations | 15702 | +| time_elapsed | 22978 | +| total_timesteps | 32157696 | +| train/ | | +| approx_kl | 0.01243867 | +| clip_fraction | 0.342 | +| clip_range | 0.067 | +| entropy_loss | -6.12 | +| explained_variance | 0.224 | +| learning_rate | 4.24e-05 | +| loss | -0.0343 | +| n_updates | 78624 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.00013 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1399 | +| iterations | 15703 | +| time_elapsed | 22979 | +| total_timesteps | 32159744 | +| train/ | | +| approx_kl | 0.011457609 | +| clip_fraction | 0.333 | +| clip_range | 0.067 | +| entropy_loss | -6.62 | +| explained_variance | 0.309 | +| learning_rate | 4.24e-05 | +| loss | -0.0297 | +| n_updates | 78628 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.00014 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1399 | +| iterations | 15704 | +| time_elapsed | 22981 | +| total_timesteps | 32161792 | +| train/ | | +| approx_kl | 0.011060756 | +| clip_fraction | 0.327 | +| clip_range | 0.067 | +| entropy_loss | -6.52 | +| explained_variance | 0.531 | +| learning_rate | 4.24e-05 | +| loss | -0.0239 | +| n_updates | 78632 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1399 | +| iterations | 15705 | +| time_elapsed | 22982 | +| total_timesteps | 32163840 | +| train/ | | +| approx_kl | 0.013540002 | +| clip_fraction | 0.35 | +| clip_range | 0.067 | +| entropy_loss | -5.77 | +| explained_variance | 0.817 | +| learning_rate | 4.24e-05 | +| loss | -0.0352 | +| n_updates | 78636 | +| policy_gradient_loss | -0.0226 | +| value_loss | 3.26e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1399 | +| iterations | 15706 | +| time_elapsed | 22984 | +| total_timesteps | 32165888 | +| train/ | | +| approx_kl | 0.011531729 | +| clip_fraction | 0.332 | +| clip_range | 0.067 | +| entropy_loss | -5.98 | +| explained_variance | 0.42 | +| learning_rate | 4.24e-05 | +| loss | -0.0296 | +| n_updates | 78640 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000129 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1399 | +| iterations | 15707 | +| time_elapsed | 22985 | +| total_timesteps | 32167936 | +| train/ | | +| approx_kl | 0.012201689 | +| clip_fraction | 0.313 | +| clip_range | 0.067 | +| entropy_loss | -6.26 | +| explained_variance | 0.324 | +| learning_rate | 4.24e-05 | +| loss | -0.0252 | +| n_updates | 78644 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000145 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1399 | +| iterations | 15708 | +| time_elapsed | 22987 | +| total_timesteps | 32169984 | +| train/ | | +| approx_kl | 0.012221505 | +| clip_fraction | 0.347 | +| clip_range | 0.067 | +| entropy_loss | -6.06 | +| explained_variance | 0.49 | +| learning_rate | 4.24e-05 | +| loss | -0.0248 | +| n_updates | 78648 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000174 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1399 | +| iterations | 15709 | +| time_elapsed | 22989 | +| total_timesteps | 32172032 | +| train/ | | +| approx_kl | 0.013033379 | +| clip_fraction | 0.31 | +| clip_range | 0.067 | +| entropy_loss | -6.06 | +| explained_variance | 0.39 | +| learning_rate | 4.24e-05 | +| loss | -0.024 | +| n_updates | 78652 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000221 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1399 | +| iterations | 15710 | +| time_elapsed | 22990 | +| total_timesteps | 32174080 | +| train/ | | +| approx_kl | 0.010157778 | +| clip_fraction | 0.316 | +| clip_range | 0.067 | +| entropy_loss | -6.31 | +| explained_variance | 0.452 | +| learning_rate | 4.24e-05 | +| loss | -0.029 | +| n_updates | 78656 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000117 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1399 | +| iterations | 15711 | +| time_elapsed | 22992 | +| total_timesteps | 32176128 | +| train/ | | +| approx_kl | 0.014762348 | +| clip_fraction | 0.383 | +| clip_range | 0.067 | +| entropy_loss | -6.36 | +| explained_variance | 0.547 | +| learning_rate | 4.24e-05 | +| loss | -0.0394 | +| n_updates | 78660 | +| policy_gradient_loss | -0.0239 | +| value_loss | 6.28e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1399 | +| iterations | 15712 | +| time_elapsed | 22993 | +| total_timesteps | 32178176 | +| train/ | | +| approx_kl | 0.013687778 | +| clip_fraction | 0.329 | +| clip_range | 0.067 | +| entropy_loss | -6.29 | +| explained_variance | 0.442 | +| learning_rate | 4.24e-05 | +| loss | -0.0271 | +| n_updates | 78664 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.00022 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1399 | +| iterations | 15713 | +| time_elapsed | 22995 | +| total_timesteps | 32180224 | +| train/ | | +| approx_kl | 0.010357294 | +| clip_fraction | 0.297 | +| clip_range | 0.067 | +| entropy_loss | -5.98 | +| explained_variance | 0.444 | +| learning_rate | 4.24e-05 | +| loss | -0.0169 | +| n_updates | 78668 | +| policy_gradient_loss | -0.0142 | +| value_loss | 0.000191 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1399 | +| iterations | 15714 | +| time_elapsed | 22996 | +| total_timesteps | 32182272 | +| train/ | | +| approx_kl | 0.012581658 | +| clip_fraction | 0.322 | +| clip_range | 0.067 | +| entropy_loss | -5.94 | +| explained_variance | 0.58 | +| learning_rate | 4.24e-05 | +| loss | -0.0266 | +| n_updates | 78672 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000105 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1399 | +| iterations | 15715 | +| time_elapsed | 22998 | +| total_timesteps | 32184320 | +| train/ | | +| approx_kl | 0.01057203 | +| clip_fraction | 0.318 | +| clip_range | 0.067 | +| entropy_loss | -6.51 | +| explained_variance | 0.381 | +| learning_rate | 4.24e-05 | +| loss | -0.0284 | +| n_updates | 78676 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000128 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1399 | +| iterations | 15716 | +| time_elapsed | 22999 | +| total_timesteps | 32186368 | +| train/ | | +| approx_kl | 0.014861291 | +| clip_fraction | 0.374 | +| clip_range | 0.067 | +| entropy_loss | -6.5 | +| explained_variance | 0.266 | +| learning_rate | 4.24e-05 | +| loss | -0.0378 | +| n_updates | 78680 | +| policy_gradient_loss | -0.0239 | +| value_loss | 5.3e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1399 | +| iterations | 15717 | +| time_elapsed | 23001 | +| total_timesteps | 32188416 | +| train/ | | +| approx_kl | 0.012583498 | +| clip_fraction | 0.349 | +| clip_range | 0.067 | +| entropy_loss | -6.26 | +| explained_variance | 0.383 | +| learning_rate | 4.24e-05 | +| loss | -0.0333 | +| n_updates | 78684 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.00011 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1399 | +| iterations | 15718 | +| time_elapsed | 23002 | +| total_timesteps | 32190464 | +| train/ | | +| approx_kl | 0.016898524 | +| clip_fraction | 0.384 | +| clip_range | 0.067 | +| entropy_loss | -6.01 | +| explained_variance | 0.762 | +| learning_rate | 4.24e-05 | +| loss | -0.0333 | +| n_updates | 78688 | +| policy_gradient_loss | -0.0214 | +| value_loss | 6.46e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1399 | +| iterations | 15719 | +| time_elapsed | 23004 | +| total_timesteps | 32192512 | +| train/ | | +| approx_kl | 0.01419588 | +| clip_fraction | 0.334 | +| clip_range | 0.067 | +| entropy_loss | -5.67 | +| explained_variance | 0.469 | +| learning_rate | 4.24e-05 | +| loss | -0.0292 | +| n_updates | 78692 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000175 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1399 | +| iterations | 15720 | +| time_elapsed | 23005 | +| total_timesteps | 32194560 | +| train/ | | +| approx_kl | 0.010404029 | +| clip_fraction | 0.339 | +| clip_range | 0.067 | +| entropy_loss | -6.74 | +| explained_variance | -0.0247 | +| learning_rate | 4.24e-05 | +| loss | -0.0292 | +| n_updates | 78696 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000129 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1399 | +| iterations | 15721 | +| time_elapsed | 23007 | +| total_timesteps | 32196608 | +| train/ | | +| approx_kl | 0.010866263 | +| clip_fraction | 0.31 | +| clip_range | 0.067 | +| entropy_loss | -7.01 | +| explained_variance | -0.0415 | +| learning_rate | 4.24e-05 | +| loss | -0.0239 | +| n_updates | 78700 | +| policy_gradient_loss | -0.0146 | +| value_loss | 0.000319 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1399 | +| iterations | 15722 | +| time_elapsed | 23008 | +| total_timesteps | 32198656 | +| train/ | | +| approx_kl | 0.0145427715 | +| clip_fraction | 0.339 | +| clip_range | 0.067 | +| entropy_loss | -5.75 | +| explained_variance | 0.586 | +| learning_rate | 4.24e-05 | +| loss | -0.0283 | +| n_updates | 78704 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000153 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1399 | +| iterations | 15723 | +| time_elapsed | 23010 | +| total_timesteps | 32200704 | +| train/ | | +| approx_kl | 0.012097217 | +| clip_fraction | 0.327 | +| clip_range | 0.067 | +| entropy_loss | -5.49 | +| explained_variance | 0.497 | +| learning_rate | 4.24e-05 | +| loss | -0.026 | +| n_updates | 78708 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000232 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1399 | +| iterations | 15724 | +| time_elapsed | 23012 | +| total_timesteps | 32202752 | +| train/ | | +| approx_kl | 0.013222021 | +| clip_fraction | 0.342 | +| clip_range | 0.0669 | +| entropy_loss | -6.38 | +| explained_variance | 0.488 | +| learning_rate | 4.24e-05 | +| loss | -0.0302 | +| n_updates | 78712 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000112 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1399 | +| iterations | 15725 | +| time_elapsed | 23013 | +| total_timesteps | 32204800 | +| train/ | | +| approx_kl | 0.017081782 | +| clip_fraction | 0.347 | +| clip_range | 0.0669 | +| entropy_loss | -6.61 | +| explained_variance | 0.363 | +| learning_rate | 4.24e-05 | +| loss | -0.0296 | +| n_updates | 78716 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000106 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1399 | +| iterations | 15726 | +| time_elapsed | 23015 | +| total_timesteps | 32206848 | +| train/ | | +| approx_kl | 0.016025525 | +| clip_fraction | 0.332 | +| clip_range | 0.0669 | +| entropy_loss | -5.69 | +| explained_variance | 0.597 | +| learning_rate | 4.24e-05 | +| loss | -0.0189 | +| n_updates | 78720 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000162 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1399 | +| iterations | 15727 | +| time_elapsed | 23016 | +| total_timesteps | 32208896 | +| train/ | | +| approx_kl | 0.013237087 | +| clip_fraction | 0.355 | +| clip_range | 0.0669 | +| entropy_loss | -5.61 | +| explained_variance | 0.66 | +| learning_rate | 4.24e-05 | +| loss | -0.0344 | +| n_updates | 78724 | +| policy_gradient_loss | -0.0202 | +| value_loss | 9.97e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1399 | +| iterations | 15728 | +| time_elapsed | 23018 | +| total_timesteps | 32210944 | +| train/ | | +| approx_kl | 0.013841874 | +| clip_fraction | 0.337 | +| clip_range | 0.0669 | +| entropy_loss | -6.09 | +| explained_variance | 0.369 | +| learning_rate | 4.24e-05 | +| loss | -0.0332 | +| n_updates | 78728 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000174 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1399 | +| iterations | 15729 | +| time_elapsed | 23019 | +| total_timesteps | 32212992 | +| train/ | | +| approx_kl | 0.012402745 | +| clip_fraction | 0.311 | +| clip_range | 0.0669 | +| entropy_loss | -5.93 | +| explained_variance | 0.604 | +| learning_rate | 4.23e-05 | +| loss | -0.0239 | +| n_updates | 78732 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000158 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1399 | +| iterations | 15730 | +| time_elapsed | 23021 | +| total_timesteps | 32215040 | +| train/ | | +| approx_kl | 0.014441895 | +| clip_fraction | 0.387 | +| clip_range | 0.0669 | +| entropy_loss | -6.33 | +| explained_variance | -0.155 | +| learning_rate | 4.23e-05 | +| loss | -0.0351 | +| n_updates | 78736 | +| policy_gradient_loss | -0.0231 | +| value_loss | 5.92e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1399 | +| iterations | 15731 | +| time_elapsed | 23022 | +| total_timesteps | 32217088 | +| train/ | | +| approx_kl | 0.009616961 | +| clip_fraction | 0.313 | +| clip_range | 0.0669 | +| entropy_loss | -6.38 | +| explained_variance | 0.531 | +| learning_rate | 4.23e-05 | +| loss | -0.0273 | +| n_updates | 78740 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000134 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1399 | +| iterations | 15732 | +| time_elapsed | 23024 | +| total_timesteps | 32219136 | +| train/ | | +| approx_kl | 0.011251557 | +| clip_fraction | 0.318 | +| clip_range | 0.0669 | +| entropy_loss | -6.31 | +| explained_variance | 0.68 | +| learning_rate | 4.23e-05 | +| loss | -0.0242 | +| n_updates | 78744 | +| policy_gradient_loss | -0.0175 | +| value_loss | 9.97e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1399 | +| iterations | 15733 | +| time_elapsed | 23025 | +| total_timesteps | 32221184 | +| train/ | | +| approx_kl | 0.010266478 | +| clip_fraction | 0.308 | +| clip_range | 0.0669 | +| entropy_loss | -5.87 | +| explained_variance | 0.54 | +| learning_rate | 4.23e-05 | +| loss | -0.0278 | +| n_updates | 78748 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000119 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1399 | +| iterations | 15734 | +| time_elapsed | 23027 | +| total_timesteps | 32223232 | +| train/ | | +| approx_kl | 0.012568139 | +| clip_fraction | 0.355 | +| clip_range | 0.0669 | +| entropy_loss | -6.39 | +| explained_variance | 0.198 | +| learning_rate | 4.23e-05 | +| loss | -0.0326 | +| n_updates | 78752 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000107 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1399 | +| iterations | 15735 | +| time_elapsed | 23029 | +| total_timesteps | 32225280 | +| train/ | | +| approx_kl | 0.010101665 | +| clip_fraction | 0.355 | +| clip_range | 0.0669 | +| entropy_loss | -6.62 | +| explained_variance | 0.522 | +| learning_rate | 4.23e-05 | +| loss | -0.0334 | +| n_updates | 78756 | +| policy_gradient_loss | -0.0206 | +| value_loss | 8.97e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1399 | +| iterations | 15736 | +| time_elapsed | 23030 | +| total_timesteps | 32227328 | +| train/ | | +| approx_kl | 0.013471285 | +| clip_fraction | 0.323 | +| clip_range | 0.0669 | +| entropy_loss | -6.24 | +| explained_variance | 0.639 | +| learning_rate | 4.23e-05 | +| loss | -0.0282 | +| n_updates | 78760 | +| policy_gradient_loss | -0.0175 | +| value_loss | 8.77e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1399 | +| iterations | 15737 | +| time_elapsed | 23032 | +| total_timesteps | 32229376 | +| train/ | | +| approx_kl | 0.010498434 | +| clip_fraction | 0.324 | +| clip_range | 0.0669 | +| entropy_loss | -6.34 | +| explained_variance | 0.441 | +| learning_rate | 4.23e-05 | +| loss | -0.0212 | +| n_updates | 78764 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000202 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1399 | +| iterations | 15738 | +| time_elapsed | 23033 | +| total_timesteps | 32231424 | +| train/ | | +| approx_kl | 0.01451288 | +| clip_fraction | 0.358 | +| clip_range | 0.0669 | +| entropy_loss | -6.31 | +| explained_variance | 0.568 | +| learning_rate | 4.23e-05 | +| loss | -0.0404 | +| n_updates | 78768 | +| policy_gradient_loss | -0.022 | +| value_loss | 8.23e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1399 | +| iterations | 15739 | +| time_elapsed | 23035 | +| total_timesteps | 32233472 | +| train/ | | +| approx_kl | 0.016617296 | +| clip_fraction | 0.357 | +| clip_range | 0.0669 | +| entropy_loss | -6.28 | +| explained_variance | 0.27 | +| learning_rate | 4.23e-05 | +| loss | -0.032 | +| n_updates | 78772 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000169 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.315 | +| time/ | | +| fps | 1399 | +| iterations | 15740 | +| time_elapsed | 23036 | +| total_timesteps | 32235520 | +| train/ | | +| approx_kl | 0.012366941 | +| clip_fraction | 0.323 | +| clip_range | 0.0669 | +| entropy_loss | -6.26 | +| explained_variance | 0.519 | +| learning_rate | 4.23e-05 | +| loss | -0.0228 | +| n_updates | 78776 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000164 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1399 | +| iterations | 15741 | +| time_elapsed | 23038 | +| total_timesteps | 32237568 | +| train/ | | +| approx_kl | 0.012533985 | +| clip_fraction | 0.328 | +| clip_range | 0.0669 | +| entropy_loss | -6.1 | +| explained_variance | 0.478 | +| learning_rate | 4.23e-05 | +| loss | -0.0264 | +| n_updates | 78780 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000147 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1399 | +| iterations | 15742 | +| time_elapsed | 23039 | +| total_timesteps | 32239616 | +| train/ | | +| approx_kl | 0.013065544 | +| clip_fraction | 0.341 | +| clip_range | 0.0669 | +| entropy_loss | -6.24 | +| explained_variance | 0.349 | +| learning_rate | 4.23e-05 | +| loss | -0.0333 | +| n_updates | 78784 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000129 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1399 | +| iterations | 15743 | +| time_elapsed | 23041 | +| total_timesteps | 32241664 | +| train/ | | +| approx_kl | 0.012540719 | +| clip_fraction | 0.317 | +| clip_range | 0.0669 | +| entropy_loss | -6.43 | +| explained_variance | 0.365 | +| learning_rate | 4.23e-05 | +| loss | -0.0249 | +| n_updates | 78788 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000246 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1399 | +| iterations | 15744 | +| time_elapsed | 23042 | +| total_timesteps | 32243712 | +| train/ | | +| approx_kl | 0.011387669 | +| clip_fraction | 0.306 | +| clip_range | 0.0669 | +| entropy_loss | -6.12 | +| explained_variance | 0.381 | +| learning_rate | 4.23e-05 | +| loss | -0.0302 | +| n_updates | 78792 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000238 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1399 | +| iterations | 15745 | +| time_elapsed | 23044 | +| total_timesteps | 32245760 | +| train/ | | +| approx_kl | 0.011368399 | +| clip_fraction | 0.293 | +| clip_range | 0.0669 | +| entropy_loss | -5.33 | +| explained_variance | 0.461 | +| learning_rate | 4.23e-05 | +| loss | -0.0223 | +| n_updates | 78796 | +| policy_gradient_loss | -0.0136 | +| value_loss | 0.000263 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1399 | +| iterations | 15746 | +| time_elapsed | 23045 | +| total_timesteps | 32247808 | +| train/ | | +| approx_kl | 0.012281945 | +| clip_fraction | 0.334 | +| clip_range | 0.0669 | +| entropy_loss | -5.83 | +| explained_variance | 0.67 | +| learning_rate | 4.23e-05 | +| loss | -0.0282 | +| n_updates | 78800 | +| policy_gradient_loss | -0.0195 | +| value_loss | 8.22e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1399 | +| iterations | 15747 | +| time_elapsed | 23047 | +| total_timesteps | 32249856 | +| train/ | | +| approx_kl | 0.014403336 | +| clip_fraction | 0.346 | +| clip_range | 0.0669 | +| entropy_loss | -6.34 | +| explained_variance | 0.346 | +| learning_rate | 4.23e-05 | +| loss | -0.0306 | +| n_updates | 78804 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000157 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1399 | +| iterations | 15748 | +| time_elapsed | 23048 | +| total_timesteps | 32251904 | +| train/ | | +| approx_kl | 0.014254482 | +| clip_fraction | 0.359 | +| clip_range | 0.0669 | +| entropy_loss | -6.32 | +| explained_variance | 0.67 | +| learning_rate | 4.23e-05 | +| loss | -0.0303 | +| n_updates | 78808 | +| policy_gradient_loss | -0.0212 | +| value_loss | 5.09e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1399 | +| iterations | 15749 | +| time_elapsed | 23050 | +| total_timesteps | 32253952 | +| train/ | | +| approx_kl | 0.014982754 | +| clip_fraction | 0.336 | +| clip_range | 0.0669 | +| entropy_loss | -6.02 | +| explained_variance | 0.453 | +| learning_rate | 4.23e-05 | +| loss | -0.0318 | +| n_updates | 78812 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000133 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1399 | +| iterations | 15750 | +| time_elapsed | 23051 | +| total_timesteps | 32256000 | +| train/ | | +| approx_kl | 0.01458648 | +| clip_fraction | 0.337 | +| clip_range | 0.0669 | +| entropy_loss | -5.91 | +| explained_variance | 0.456 | +| learning_rate | 4.23e-05 | +| loss | -0.028 | +| n_updates | 78816 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000162 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1399 | +| iterations | 15751 | +| time_elapsed | 23053 | +| total_timesteps | 32258048 | +| train/ | | +| approx_kl | 0.01431335 | +| clip_fraction | 0.36 | +| clip_range | 0.0669 | +| entropy_loss | -5.54 | +| explained_variance | 0.708 | +| learning_rate | 4.23e-05 | +| loss | -0.0261 | +| n_updates | 78820 | +| policy_gradient_loss | -0.0194 | +| value_loss | 8.28e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1399 | +| iterations | 15752 | +| time_elapsed | 23054 | +| total_timesteps | 32260096 | +| train/ | | +| approx_kl | 0.012566616 | +| clip_fraction | 0.323 | +| clip_range | 0.0669 | +| entropy_loss | -6.08 | +| explained_variance | 0.321 | +| learning_rate | 4.23e-05 | +| loss | -0.0277 | +| n_updates | 78824 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000165 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1399 | +| iterations | 15753 | +| time_elapsed | 23056 | +| total_timesteps | 32262144 | +| train/ | | +| approx_kl | 0.013302511 | +| clip_fraction | 0.342 | +| clip_range | 0.0669 | +| entropy_loss | -6.42 | +| explained_variance | -0.0504 | +| learning_rate | 4.23e-05 | +| loss | -0.0251 | +| n_updates | 78828 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000147 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1399 | +| iterations | 15754 | +| time_elapsed | 23057 | +| total_timesteps | 32264192 | +| train/ | | +| approx_kl | 0.01156248 | +| clip_fraction | 0.319 | +| clip_range | 0.0669 | +| entropy_loss | -6.54 | +| explained_variance | 0.436 | +| learning_rate | 4.23e-05 | +| loss | -0.0295 | +| n_updates | 78832 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000167 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1399 | +| iterations | 15755 | +| time_elapsed | 23059 | +| total_timesteps | 32266240 | +| train/ | | +| approx_kl | 0.011656264 | +| clip_fraction | 0.329 | +| clip_range | 0.0669 | +| entropy_loss | -6.62 | +| explained_variance | 0.18 | +| learning_rate | 4.23e-05 | +| loss | -0.0308 | +| n_updates | 78836 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000288 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1399 | +| iterations | 15756 | +| time_elapsed | 23060 | +| total_timesteps | 32268288 | +| train/ | | +| approx_kl | 0.010219278 | +| clip_fraction | 0.362 | +| clip_range | 0.0669 | +| entropy_loss | -6.55 | +| explained_variance | 0.361 | +| learning_rate | 4.23e-05 | +| loss | -0.0317 | +| n_updates | 78840 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000106 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1399 | +| iterations | 15757 | +| time_elapsed | 23062 | +| total_timesteps | 32270336 | +| train/ | | +| approx_kl | 0.011690589 | +| clip_fraction | 0.303 | +| clip_range | 0.0669 | +| entropy_loss | -5.41 | +| explained_variance | 0.606 | +| learning_rate | 4.23e-05 | +| loss | -0.02 | +| n_updates | 78844 | +| policy_gradient_loss | -0.0147 | +| value_loss | 0.000223 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.315 | +| time/ | | +| fps | 1399 | +| iterations | 15758 | +| time_elapsed | 23063 | +| total_timesteps | 32272384 | +| train/ | | +| approx_kl | 0.013779889 | +| clip_fraction | 0.336 | +| clip_range | 0.0669 | +| entropy_loss | -5.37 | +| explained_variance | 0.655 | +| learning_rate | 4.23e-05 | +| loss | -0.0298 | +| n_updates | 78848 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000115 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1399 | +| iterations | 15759 | +| time_elapsed | 23065 | +| total_timesteps | 32274432 | +| train/ | | +| approx_kl | 0.014133915 | +| clip_fraction | 0.334 | +| clip_range | 0.0669 | +| entropy_loss | -5.88 | +| explained_variance | 0.735 | +| learning_rate | 4.23e-05 | +| loss | -0.0299 | +| n_updates | 78852 | +| policy_gradient_loss | -0.0179 | +| value_loss | 9.82e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1399 | +| iterations | 15760 | +| time_elapsed | 23067 | +| total_timesteps | 32276480 | +| train/ | | +| approx_kl | 0.017202185 | +| clip_fraction | 0.317 | +| clip_range | 0.0669 | +| entropy_loss | -5.66 | +| explained_variance | 0.555 | +| learning_rate | 4.23e-05 | +| loss | -0.0287 | +| n_updates | 78856 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000108 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1399 | +| iterations | 15761 | +| time_elapsed | 23068 | +| total_timesteps | 32278528 | +| train/ | | +| approx_kl | 0.012601791 | +| clip_fraction | 0.328 | +| clip_range | 0.0669 | +| entropy_loss | -6.02 | +| explained_variance | 0.296 | +| learning_rate | 4.23e-05 | +| loss | -0.0293 | +| n_updates | 78860 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000115 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1399 | +| iterations | 15762 | +| time_elapsed | 23070 | +| total_timesteps | 32280576 | +| train/ | | +| approx_kl | 0.011973374 | +| clip_fraction | 0.328 | +| clip_range | 0.0669 | +| entropy_loss | -6.3 | +| explained_variance | -0.12 | +| learning_rate | 4.23e-05 | +| loss | -0.0267 | +| n_updates | 78864 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000182 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1399 | +| iterations | 15763 | +| time_elapsed | 23071 | +| total_timesteps | 32282624 | +| train/ | | +| approx_kl | 0.015380699 | +| clip_fraction | 0.346 | +| clip_range | 0.0669 | +| entropy_loss | -6.25 | +| explained_variance | 0.458 | +| learning_rate | 4.23e-05 | +| loss | -0.0276 | +| n_updates | 78868 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000165 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1399 | +| iterations | 15764 | +| time_elapsed | 23073 | +| total_timesteps | 32284672 | +| train/ | | +| approx_kl | 0.013036083 | +| clip_fraction | 0.362 | +| clip_range | 0.0669 | +| entropy_loss | -6.61 | +| explained_variance | -0.267 | +| learning_rate | 4.23e-05 | +| loss | -0.0304 | +| n_updates | 78872 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000115 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1399 | +| iterations | 15765 | +| time_elapsed | 23074 | +| total_timesteps | 32286720 | +| train/ | | +| approx_kl | 0.012079774 | +| clip_fraction | 0.315 | +| clip_range | 0.0669 | +| entropy_loss | -6.77 | +| explained_variance | 0.1 | +| learning_rate | 4.23e-05 | +| loss | -0.0247 | +| n_updates | 78876 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000284 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1399 | +| iterations | 15766 | +| time_elapsed | 23076 | +| total_timesteps | 32288768 | +| train/ | | +| approx_kl | 0.008625772 | +| clip_fraction | 0.288 | +| clip_range | 0.0669 | +| entropy_loss | -5.38 | +| explained_variance | 0.593 | +| learning_rate | 4.23e-05 | +| loss | -0.0182 | +| n_updates | 78880 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.000146 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1399 | +| iterations | 15767 | +| time_elapsed | 23077 | +| total_timesteps | 32290816 | +| train/ | | +| approx_kl | 0.0143371355 | +| clip_fraction | 0.33 | +| clip_range | 0.0669 | +| entropy_loss | -5.45 | +| explained_variance | 0.724 | +| learning_rate | 4.23e-05 | +| loss | -0.0324 | +| n_updates | 78884 | +| policy_gradient_loss | -0.0191 | +| value_loss | 9.23e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 1399 | +| iterations | 15768 | +| time_elapsed | 23079 | +| total_timesteps | 32292864 | +| train/ | | +| approx_kl | 0.013190118 | +| clip_fraction | 0.344 | +| clip_range | 0.0669 | +| entropy_loss | -6.08 | +| explained_variance | 0.577 | +| learning_rate | 4.23e-05 | +| loss | -0.0264 | +| n_updates | 78888 | +| policy_gradient_loss | -0.0192 | +| value_loss | 9.67e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 1399 | +| iterations | 15769 | +| time_elapsed | 23080 | +| total_timesteps | 32294912 | +| train/ | | +| approx_kl | 0.012906748 | +| clip_fraction | 0.341 | +| clip_range | 0.0669 | +| entropy_loss | -6.26 | +| explained_variance | 0.587 | +| learning_rate | 4.23e-05 | +| loss | -0.031 | +| n_updates | 78892 | +| policy_gradient_loss | -0.0174 | +| value_loss | 9.62e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1399 | +| iterations | 15770 | +| time_elapsed | 23082 | +| total_timesteps | 32296960 | +| train/ | | +| approx_kl | 0.0140416995 | +| clip_fraction | 0.329 | +| clip_range | 0.0669 | +| entropy_loss | -5.83 | +| explained_variance | 0.35 | +| learning_rate | 4.23e-05 | +| loss | -0.0249 | +| n_updates | 78896 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000284 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1399 | +| iterations | 15771 | +| time_elapsed | 23083 | +| total_timesteps | 32299008 | +| train/ | | +| approx_kl | 0.01227928 | +| clip_fraction | 0.334 | +| clip_range | 0.0669 | +| entropy_loss | -6.48 | +| explained_variance | -0.0665 | +| learning_rate | 4.23e-05 | +| loss | -0.0313 | +| n_updates | 78900 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000182 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1399 | +| iterations | 15772 | +| time_elapsed | 23085 | +| total_timesteps | 32301056 | +| train/ | | +| approx_kl | 0.01075867 | +| clip_fraction | 0.328 | +| clip_range | 0.0669 | +| entropy_loss | -6.67 | +| explained_variance | 0.253 | +| learning_rate | 4.23e-05 | +| loss | -0.0273 | +| n_updates | 78904 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000171 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1399 | +| iterations | 15773 | +| time_elapsed | 23087 | +| total_timesteps | 32303104 | +| train/ | | +| approx_kl | 0.012299538 | +| clip_fraction | 0.333 | +| clip_range | 0.0669 | +| entropy_loss | -5.9 | +| explained_variance | 0.577 | +| learning_rate | 4.23e-05 | +| loss | -0.0312 | +| n_updates | 78908 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.00016 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1399 | +| iterations | 15774 | +| time_elapsed | 23088 | +| total_timesteps | 32305152 | +| train/ | | +| approx_kl | 0.0122451745 | +| clip_fraction | 0.332 | +| clip_range | 0.0669 | +| entropy_loss | -5.37 | +| explained_variance | 0.702 | +| learning_rate | 4.23e-05 | +| loss | -0.0301 | +| n_updates | 78912 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000102 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 1399 | +| iterations | 15775 | +| time_elapsed | 23090 | +| total_timesteps | 32307200 | +| train/ | | +| approx_kl | 0.012509781 | +| clip_fraction | 0.339 | +| clip_range | 0.0669 | +| entropy_loss | -6.3 | +| explained_variance | 0.209 | +| learning_rate | 4.23e-05 | +| loss | -0.028 | +| n_updates | 78916 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000108 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1399 | +| iterations | 15776 | +| time_elapsed | 23091 | +| total_timesteps | 32309248 | +| train/ | | +| approx_kl | 0.010069828 | +| clip_fraction | 0.33 | +| clip_range | 0.0669 | +| entropy_loss | -6.46 | +| explained_variance | 0.466 | +| learning_rate | 4.23e-05 | +| loss | -0.0298 | +| n_updates | 78920 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000152 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1399 | +| iterations | 15777 | +| time_elapsed | 23093 | +| total_timesteps | 32311296 | +| train/ | | +| approx_kl | 0.010242202 | +| clip_fraction | 0.315 | +| clip_range | 0.0669 | +| entropy_loss | -6.37 | +| explained_variance | 0.295 | +| learning_rate | 4.23e-05 | +| loss | -0.0261 | +| n_updates | 78924 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000196 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 1399 | +| iterations | 15778 | +| time_elapsed | 23094 | +| total_timesteps | 32313344 | +| train/ | | +| approx_kl | 0.009957415 | +| clip_fraction | 0.327 | +| clip_range | 0.0669 | +| entropy_loss | -6.62 | +| explained_variance | 0.319 | +| learning_rate | 4.23e-05 | +| loss | -0.027 | +| n_updates | 78928 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000143 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.306 | +| time/ | | +| fps | 1399 | +| iterations | 15779 | +| time_elapsed | 23096 | +| total_timesteps | 32315392 | +| train/ | | +| approx_kl | 0.0112860575 | +| clip_fraction | 0.305 | +| clip_range | 0.0669 | +| entropy_loss | -6.63 | +| explained_variance | 0.519 | +| learning_rate | 4.23e-05 | +| loss | -0.0267 | +| n_updates | 78932 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000139 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 1399 | +| iterations | 15780 | +| time_elapsed | 23098 | +| total_timesteps | 32317440 | +| train/ | | +| approx_kl | 0.013668282 | +| clip_fraction | 0.322 | +| clip_range | 0.0669 | +| entropy_loss | -5.78 | +| explained_variance | 0.569 | +| learning_rate | 4.23e-05 | +| loss | -0.0258 | +| n_updates | 78936 | +| policy_gradient_loss | -0.0147 | +| value_loss | 0.000174 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.304 | +| time/ | | +| fps | 1399 | +| iterations | 15781 | +| time_elapsed | 23099 | +| total_timesteps | 32319488 | +| train/ | | +| approx_kl | 0.012288332 | +| clip_fraction | 0.322 | +| clip_range | 0.0669 | +| entropy_loss | -5.85 | +| explained_variance | 0.575 | +| learning_rate | 4.23e-05 | +| loss | -0.0342 | +| n_updates | 78940 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000102 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.302 | +| time/ | | +| fps | 1399 | +| iterations | 15782 | +| time_elapsed | 23101 | +| total_timesteps | 32321536 | +| train/ | | +| approx_kl | 0.013114108 | +| clip_fraction | 0.316 | +| clip_range | 0.0669 | +| entropy_loss | -6.17 | +| explained_variance | 0.232 | +| learning_rate | 4.23e-05 | +| loss | -0.0255 | +| n_updates | 78944 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000326 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1399 | +| iterations | 15783 | +| time_elapsed | 23102 | +| total_timesteps | 32323584 | +| train/ | | +| approx_kl | 0.01012185 | +| clip_fraction | 0.322 | +| clip_range | 0.0669 | +| entropy_loss | -6.06 | +| explained_variance | 0.5 | +| learning_rate | 4.23e-05 | +| loss | -0.0283 | +| n_updates | 78948 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000215 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.306 | +| time/ | | +| fps | 1399 | +| iterations | 15784 | +| time_elapsed | 23104 | +| total_timesteps | 32325632 | +| train/ | | +| approx_kl | 0.010063395 | +| clip_fraction | 0.311 | +| clip_range | 0.0669 | +| entropy_loss | -5.95 | +| explained_variance | 0.59 | +| learning_rate | 4.23e-05 | +| loss | -0.0309 | +| n_updates | 78952 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000123 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.304 | +| time/ | | +| fps | 1399 | +| iterations | 15785 | +| time_elapsed | 23105 | +| total_timesteps | 32327680 | +| train/ | | +| approx_kl | 0.010866824 | +| clip_fraction | 0.291 | +| clip_range | 0.0669 | +| entropy_loss | -5.94 | +| explained_variance | 0.327 | +| learning_rate | 4.23e-05 | +| loss | -0.0239 | +| n_updates | 78956 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000269 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.306 | +| time/ | | +| fps | 1399 | +| iterations | 15786 | +| time_elapsed | 23107 | +| total_timesteps | 32329728 | +| train/ | | +| approx_kl | 0.013275019 | +| clip_fraction | 0.356 | +| clip_range | 0.0669 | +| entropy_loss | -6.14 | +| explained_variance | 0.321 | +| learning_rate | 4.23e-05 | +| loss | -0.0262 | +| n_updates | 78960 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1399 | +| iterations | 15787 | +| time_elapsed | 23108 | +| total_timesteps | 32331776 | +| train/ | | +| approx_kl | 0.014928011 | +| clip_fraction | 0.342 | +| clip_range | 0.0669 | +| entropy_loss | -6.39 | +| explained_variance | 0.347 | +| learning_rate | 4.23e-05 | +| loss | -0.0326 | +| n_updates | 78964 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000123 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1399 | +| iterations | 15788 | +| time_elapsed | 23110 | +| total_timesteps | 32333824 | +| train/ | | +| approx_kl | 0.010314641 | +| clip_fraction | 0.33 | +| clip_range | 0.0669 | +| entropy_loss | -6.75 | +| explained_variance | 0.152 | +| learning_rate | 4.23e-05 | +| loss | -0.0259 | +| n_updates | 78968 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000281 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1399 | +| iterations | 15789 | +| time_elapsed | 23111 | +| total_timesteps | 32335872 | +| train/ | | +| approx_kl | 0.010810931 | +| clip_fraction | 0.301 | +| clip_range | 0.0669 | +| entropy_loss | -6.41 | +| explained_variance | 0.428 | +| learning_rate | 4.23e-05 | +| loss | -0.0328 | +| n_updates | 78972 | +| policy_gradient_loss | -0.0145 | +| value_loss | 0.000217 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1399 | +| iterations | 15790 | +| time_elapsed | 23113 | +| total_timesteps | 32337920 | +| train/ | | +| approx_kl | 0.0114349965 | +| clip_fraction | 0.315 | +| clip_range | 0.0669 | +| entropy_loss | -6.21 | +| explained_variance | 0.185 | +| learning_rate | 4.23e-05 | +| loss | -0.0305 | +| n_updates | 78976 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.00034 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1399 | +| iterations | 15791 | +| time_elapsed | 23114 | +| total_timesteps | 32339968 | +| train/ | | +| approx_kl | 0.013309097 | +| clip_fraction | 0.339 | +| clip_range | 0.0669 | +| entropy_loss | -6.48 | +| explained_variance | 0.589 | +| learning_rate | 4.23e-05 | +| loss | -0.0321 | +| n_updates | 78980 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000104 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1399 | +| iterations | 15792 | +| time_elapsed | 23116 | +| total_timesteps | 32342016 | +| train/ | | +| approx_kl | 0.011759867 | +| clip_fraction | 0.334 | +| clip_range | 0.0669 | +| entropy_loss | -6.14 | +| explained_variance | 0.499 | +| learning_rate | 4.23e-05 | +| loss | -0.0284 | +| n_updates | 78984 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000144 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1399 | +| iterations | 15793 | +| time_elapsed | 23118 | +| total_timesteps | 32344064 | +| train/ | | +| approx_kl | 0.012285614 | +| clip_fraction | 0.366 | +| clip_range | 0.0669 | +| entropy_loss | -5.65 | +| explained_variance | 0.824 | +| learning_rate | 4.23e-05 | +| loss | -0.0341 | +| n_updates | 78988 | +| policy_gradient_loss | -0.0235 | +| value_loss | 5.07e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1399 | +| iterations | 15794 | +| time_elapsed | 23119 | +| total_timesteps | 32346112 | +| train/ | | +| approx_kl | 0.012272302 | +| clip_fraction | 0.333 | +| clip_range | 0.0669 | +| entropy_loss | -6.42 | +| explained_variance | 0.22 | +| learning_rate | 4.23e-05 | +| loss | -0.033 | +| n_updates | 78992 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000179 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1399 | +| iterations | 15795 | +| time_elapsed | 23121 | +| total_timesteps | 32348160 | +| train/ | | +| approx_kl | 0.010645121 | +| clip_fraction | 0.338 | +| clip_range | 0.0669 | +| entropy_loss | -6.2 | +| explained_variance | 0.417 | +| learning_rate | 4.23e-05 | +| loss | -0.0276 | +| n_updates | 78996 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000193 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1399 | +| iterations | 15796 | +| time_elapsed | 23122 | +| total_timesteps | 32350208 | +| train/ | | +| approx_kl | 0.010951767 | +| clip_fraction | 0.311 | +| clip_range | 0.0669 | +| entropy_loss | -5.79 | +| explained_variance | 0.421 | +| learning_rate | 4.23e-05 | +| loss | -0.0315 | +| n_updates | 79000 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.00035 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1399 | +| iterations | 15797 | +| time_elapsed | 23124 | +| total_timesteps | 32352256 | +| train/ | | +| approx_kl | 0.013793535 | +| clip_fraction | 0.327 | +| clip_range | 0.0669 | +| entropy_loss | -5.49 | +| explained_variance | 0.592 | +| learning_rate | 4.23e-05 | +| loss | -0.0354 | +| n_updates | 79004 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000176 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1399 | +| iterations | 15798 | +| time_elapsed | 23125 | +| total_timesteps | 32354304 | +| train/ | | +| approx_kl | 0.013158586 | +| clip_fraction | 0.339 | +| clip_range | 0.0669 | +| entropy_loss | -5.97 | +| explained_variance | 0.408 | +| learning_rate | 4.23e-05 | +| loss | -0.0308 | +| n_updates | 79008 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000151 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1399 | +| iterations | 15799 | +| time_elapsed | 23127 | +| total_timesteps | 32356352 | +| train/ | | +| approx_kl | 0.011412909 | +| clip_fraction | 0.333 | +| clip_range | 0.0669 | +| entropy_loss | -6.66 | +| explained_variance | 0.0819 | +| learning_rate | 4.23e-05 | +| loss | -0.0352 | +| n_updates | 79012 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000129 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1399 | +| iterations | 15800 | +| time_elapsed | 23128 | +| total_timesteps | 32358400 | +| train/ | | +| approx_kl | 0.01352447 | +| clip_fraction | 0.327 | +| clip_range | 0.0669 | +| entropy_loss | -6.24 | +| explained_variance | 0.388 | +| learning_rate | 4.23e-05 | +| loss | -0.028 | +| n_updates | 79016 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000157 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1399 | +| iterations | 15801 | +| time_elapsed | 23130 | +| total_timesteps | 32360448 | +| train/ | | +| approx_kl | 0.012171372 | +| clip_fraction | 0.329 | +| clip_range | 0.0669 | +| entropy_loss | -5.81 | +| explained_variance | 0.5 | +| learning_rate | 4.23e-05 | +| loss | -0.027 | +| n_updates | 79020 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.00027 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1399 | +| iterations | 15802 | +| time_elapsed | 23132 | +| total_timesteps | 32362496 | +| train/ | | +| approx_kl | 0.01127672 | +| clip_fraction | 0.322 | +| clip_range | 0.0669 | +| entropy_loss | -5.98 | +| explained_variance | 0.0474 | +| learning_rate | 4.23e-05 | +| loss | -0.0272 | +| n_updates | 79024 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000318 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1399 | +| iterations | 15803 | +| time_elapsed | 23133 | +| total_timesteps | 32364544 | +| train/ | | +| approx_kl | 0.012216873 | +| clip_fraction | 0.333 | +| clip_range | 0.0669 | +| entropy_loss | -5.83 | +| explained_variance | 0.482 | +| learning_rate | 4.23e-05 | +| loss | -0.0287 | +| n_updates | 79028 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000313 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1399 | +| iterations | 15804 | +| time_elapsed | 23135 | +| total_timesteps | 32366592 | +| train/ | | +| approx_kl | 0.010241384 | +| clip_fraction | 0.334 | +| clip_range | 0.0669 | +| entropy_loss | -6.39 | +| explained_variance | -0.0788 | +| learning_rate | 4.23e-05 | +| loss | -0.0304 | +| n_updates | 79032 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000133 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1399 | +| iterations | 15805 | +| time_elapsed | 23136 | +| total_timesteps | 32368640 | +| train/ | | +| approx_kl | 0.010243226 | +| clip_fraction | 0.337 | +| clip_range | 0.0669 | +| entropy_loss | -6.55 | +| explained_variance | 0.426 | +| learning_rate | 4.23e-05 | +| loss | -0.029 | +| n_updates | 79036 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000261 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1399 | +| iterations | 15806 | +| time_elapsed | 23138 | +| total_timesteps | 32370688 | +| train/ | | +| approx_kl | 0.014500014 | +| clip_fraction | 0.352 | +| clip_range | 0.0669 | +| entropy_loss | -5.91 | +| explained_variance | 0.534 | +| learning_rate | 4.23e-05 | +| loss | -0.0346 | +| n_updates | 79040 | +| policy_gradient_loss | -0.0205 | +| value_loss | 9.75e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1399 | +| iterations | 15807 | +| time_elapsed | 23139 | +| total_timesteps | 32372736 | +| train/ | | +| approx_kl | 0.010633335 | +| clip_fraction | 0.329 | +| clip_range | 0.0669 | +| entropy_loss | -6.19 | +| explained_variance | 0.362 | +| learning_rate | 4.23e-05 | +| loss | -0.0296 | +| n_updates | 79044 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.00013 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1398 | +| iterations | 15808 | +| time_elapsed | 23141 | +| total_timesteps | 32374784 | +| train/ | | +| approx_kl | 0.009009784 | +| clip_fraction | 0.273 | +| clip_range | 0.0669 | +| entropy_loss | -6.94 | +| explained_variance | 0.105 | +| learning_rate | 4.23e-05 | +| loss | -0.0251 | +| n_updates | 79048 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000243 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1398 | +| iterations | 15809 | +| time_elapsed | 23142 | +| total_timesteps | 32376832 | +| train/ | | +| approx_kl | 0.015167342 | +| clip_fraction | 0.337 | +| clip_range | 0.0669 | +| entropy_loss | -5.96 | +| explained_variance | 0.665 | +| learning_rate | 4.23e-05 | +| loss | -0.0281 | +| n_updates | 79052 | +| policy_gradient_loss | -0.0196 | +| value_loss | 9.63e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1398 | +| iterations | 15810 | +| time_elapsed | 23144 | +| total_timesteps | 32378880 | +| train/ | | +| approx_kl | 0.014494145 | +| clip_fraction | 0.36 | +| clip_range | 0.0669 | +| entropy_loss | -6.18 | +| explained_variance | 0.525 | +| learning_rate | 4.23e-05 | +| loss | -0.0347 | +| n_updates | 79056 | +| policy_gradient_loss | -0.021 | +| value_loss | 6.14e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1398 | +| iterations | 15811 | +| time_elapsed | 23146 | +| total_timesteps | 32380928 | +| train/ | | +| approx_kl | 0.013133732 | +| clip_fraction | 0.305 | +| clip_range | 0.0669 | +| entropy_loss | -6.36 | +| explained_variance | 0.493 | +| learning_rate | 4.23e-05 | +| loss | -0.0246 | +| n_updates | 79060 | +| policy_gradient_loss | -0.0148 | +| value_loss | 0.000149 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1398 | +| iterations | 15812 | +| time_elapsed | 23147 | +| total_timesteps | 32382976 | +| train/ | | +| approx_kl | 0.014097318 | +| clip_fraction | 0.334 | +| clip_range | 0.0669 | +| entropy_loss | -5.79 | +| explained_variance | 0.6 | +| learning_rate | 4.23e-05 | +| loss | -0.0266 | +| n_updates | 79064 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000138 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1398 | +| iterations | 15813 | +| time_elapsed | 23149 | +| total_timesteps | 32385024 | +| train/ | | +| approx_kl | 0.01687727 | +| clip_fraction | 0.34 | +| clip_range | 0.0669 | +| entropy_loss | -5.89 | +| explained_variance | 0.193 | +| learning_rate | 4.23e-05 | +| loss | -0.0314 | +| n_updates | 79068 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000289 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1398 | +| iterations | 15814 | +| time_elapsed | 23150 | +| total_timesteps | 32387072 | +| train/ | | +| approx_kl | 0.017163213 | +| clip_fraction | 0.354 | +| clip_range | 0.0669 | +| entropy_loss | -5.74 | +| explained_variance | 0.506 | +| learning_rate | 4.23e-05 | +| loss | -0.0279 | +| n_updates | 79072 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000205 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1398 | +| iterations | 15815 | +| time_elapsed | 23152 | +| total_timesteps | 32389120 | +| train/ | | +| approx_kl | 0.010218863 | +| clip_fraction | 0.344 | +| clip_range | 0.0669 | +| entropy_loss | -6.4 | +| explained_variance | 0.291 | +| learning_rate | 4.23e-05 | +| loss | -0.0332 | +| n_updates | 79076 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000228 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1398 | +| iterations | 15816 | +| time_elapsed | 23153 | +| total_timesteps | 32391168 | +| train/ | | +| approx_kl | 0.01267601 | +| clip_fraction | 0.315 | +| clip_range | 0.0669 | +| entropy_loss | -6.41 | +| explained_variance | 0.348 | +| learning_rate | 4.23e-05 | +| loss | -0.0307 | +| n_updates | 79080 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000198 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1398 | +| iterations | 15817 | +| time_elapsed | 23155 | +| total_timesteps | 32393216 | +| train/ | | +| approx_kl | 0.014875502 | +| clip_fraction | 0.286 | +| clip_range | 0.0669 | +| entropy_loss | -5.53 | +| explained_variance | 0.349 | +| learning_rate | 4.23e-05 | +| loss | -0.0244 | +| n_updates | 79084 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000262 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1398 | +| iterations | 15818 | +| time_elapsed | 23156 | +| total_timesteps | 32395264 | +| train/ | | +| approx_kl | 0.016419386 | +| clip_fraction | 0.366 | +| clip_range | 0.0669 | +| entropy_loss | -6.17 | +| explained_variance | 0.519 | +| learning_rate | 4.23e-05 | +| loss | -0.0369 | +| n_updates | 79088 | +| policy_gradient_loss | -0.0229 | +| value_loss | 0.000111 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1398 | +| iterations | 15819 | +| time_elapsed | 23158 | +| total_timesteps | 32397312 | +| train/ | | +| approx_kl | 0.011921407 | +| clip_fraction | 0.353 | +| clip_range | 0.0669 | +| entropy_loss | -6.76 | +| explained_variance | -0.132 | +| learning_rate | 4.23e-05 | +| loss | -0.0263 | +| n_updates | 79092 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000246 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1398 | +| iterations | 15820 | +| time_elapsed | 23159 | +| total_timesteps | 32399360 | +| train/ | | +| approx_kl | 0.013065635 | +| clip_fraction | 0.308 | +| clip_range | 0.0669 | +| entropy_loss | -6.18 | +| explained_variance | 0.485 | +| learning_rate | 4.23e-05 | +| loss | -0.0235 | +| n_updates | 79096 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000266 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1398 | +| iterations | 15821 | +| time_elapsed | 23161 | +| total_timesteps | 32401408 | +| train/ | | +| approx_kl | 0.0153764505 | +| clip_fraction | 0.353 | +| clip_range | 0.0669 | +| entropy_loss | -6.34 | +| explained_variance | 0.357 | +| learning_rate | 4.23e-05 | +| loss | -0.0361 | +| n_updates | 79100 | +| policy_gradient_loss | -0.0225 | +| value_loss | 9.87e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1398 | +| iterations | 15822 | +| time_elapsed | 23163 | +| total_timesteps | 32403456 | +| train/ | | +| approx_kl | 0.013166241 | +| clip_fraction | 0.358 | +| clip_range | 0.0669 | +| entropy_loss | -6.35 | +| explained_variance | 0.527 | +| learning_rate | 4.23e-05 | +| loss | -0.0313 | +| n_updates | 79104 | +| policy_gradient_loss | -0.0212 | +| value_loss | 6.11e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1398 | +| iterations | 15823 | +| time_elapsed | 23164 | +| total_timesteps | 32405504 | +| train/ | | +| approx_kl | 0.00985161 | +| clip_fraction | 0.297 | +| clip_range | 0.0669 | +| entropy_loss | -5.71 | +| explained_variance | 0.546 | +| learning_rate | 4.23e-05 | +| loss | -0.0265 | +| n_updates | 79108 | +| policy_gradient_loss | -0.0145 | +| value_loss | 0.000273 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1398 | +| iterations | 15824 | +| time_elapsed | 23166 | +| total_timesteps | 32407552 | +| train/ | | +| approx_kl | 0.011999066 | +| clip_fraction | 0.327 | +| clip_range | 0.0669 | +| entropy_loss | -6.2 | +| explained_variance | 0.335 | +| learning_rate | 4.23e-05 | +| loss | -0.0314 | +| n_updates | 79112 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000189 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1398 | +| iterations | 15825 | +| time_elapsed | 23167 | +| total_timesteps | 32409600 | +| train/ | | +| approx_kl | 0.010432457 | +| clip_fraction | 0.319 | +| clip_range | 0.0669 | +| entropy_loss | -5.74 | +| explained_variance | 0.571 | +| learning_rate | 4.23e-05 | +| loss | -0.0225 | +| n_updates | 79116 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000206 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1398 | +| iterations | 15826 | +| time_elapsed | 23169 | +| total_timesteps | 32411648 | +| train/ | | +| approx_kl | 0.012542892 | +| clip_fraction | 0.323 | +| clip_range | 0.0669 | +| entropy_loss | -6.11 | +| explained_variance | 0.279 | +| learning_rate | 4.23e-05 | +| loss | -0.0233 | +| n_updates | 79120 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.00023 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1398 | +| iterations | 15827 | +| time_elapsed | 23170 | +| total_timesteps | 32413696 | +| train/ | | +| approx_kl | 0.011555041 | +| clip_fraction | 0.344 | +| clip_range | 0.0669 | +| entropy_loss | -6.74 | +| explained_variance | 0.00263 | +| learning_rate | 4.23e-05 | +| loss | -0.0306 | +| n_updates | 79124 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000158 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1398 | +| iterations | 15828 | +| time_elapsed | 23172 | +| total_timesteps | 32415744 | +| train/ | | +| approx_kl | 0.010663299 | +| clip_fraction | 0.333 | +| clip_range | 0.0669 | +| entropy_loss | -6.26 | +| explained_variance | 0.559 | +| learning_rate | 4.23e-05 | +| loss | -0.0309 | +| n_updates | 79128 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000129 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1398 | +| iterations | 15829 | +| time_elapsed | 23173 | +| total_timesteps | 32417792 | +| train/ | | +| approx_kl | 0.013893647 | +| clip_fraction | 0.34 | +| clip_range | 0.0669 | +| entropy_loss | -5.86 | +| explained_variance | 0.371 | +| learning_rate | 4.23e-05 | +| loss | -0.0276 | +| n_updates | 79132 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000252 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1398 | +| iterations | 15830 | +| time_elapsed | 23175 | +| total_timesteps | 32419840 | +| train/ | | +| approx_kl | 0.015406614 | +| clip_fraction | 0.343 | +| clip_range | 0.0669 | +| entropy_loss | -6.68 | +| explained_variance | 0.105 | +| learning_rate | 4.23e-05 | +| loss | -0.0275 | +| n_updates | 79136 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000156 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1398 | +| iterations | 15831 | +| time_elapsed | 23176 | +| total_timesteps | 32421888 | +| train/ | | +| approx_kl | 0.011379313 | +| clip_fraction | 0.315 | +| clip_range | 0.0669 | +| entropy_loss | -5.68 | +| explained_variance | 0.676 | +| learning_rate | 4.23e-05 | +| loss | -0.0268 | +| n_updates | 79140 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000156 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1398 | +| iterations | 15832 | +| time_elapsed | 23178 | +| total_timesteps | 32423936 | +| train/ | | +| approx_kl | 0.012575856 | +| clip_fraction | 0.337 | +| clip_range | 0.0669 | +| entropy_loss | -5.33 | +| explained_variance | 0.631 | +| learning_rate | 4.23e-05 | +| loss | -0.0302 | +| n_updates | 79144 | +| policy_gradient_loss | -0.0192 | +| value_loss | 9.22e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1398 | +| iterations | 15833 | +| time_elapsed | 23179 | +| total_timesteps | 32425984 | +| train/ | | +| approx_kl | 0.0106733255 | +| clip_fraction | 0.325 | +| clip_range | 0.0669 | +| entropy_loss | -6.31 | +| explained_variance | 0.563 | +| learning_rate | 4.23e-05 | +| loss | -0.0251 | +| n_updates | 79148 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000117 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1398 | +| iterations | 15834 | +| time_elapsed | 23181 | +| total_timesteps | 32428032 | +| train/ | | +| approx_kl | 0.009793324 | +| clip_fraction | 0.31 | +| clip_range | 0.0669 | +| entropy_loss | -6.29 | +| explained_variance | 0.351 | +| learning_rate | 4.23e-05 | +| loss | -0.0194 | +| n_updates | 79152 | +| policy_gradient_loss | -0.0143 | +| value_loss | 0.000301 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1398 | +| iterations | 15835 | +| time_elapsed | 23182 | +| total_timesteps | 32430080 | +| train/ | | +| approx_kl | 0.010704038 | +| clip_fraction | 0.31 | +| clip_range | 0.0669 | +| entropy_loss | -6.53 | +| explained_variance | 0.312 | +| learning_rate | 4.23e-05 | +| loss | -0.0282 | +| n_updates | 79156 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000214 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1398 | +| iterations | 15836 | +| time_elapsed | 23184 | +| total_timesteps | 32432128 | +| train/ | | +| approx_kl | 0.012693714 | +| clip_fraction | 0.351 | +| clip_range | 0.0669 | +| entropy_loss | -6.31 | +| explained_variance | 0.567 | +| learning_rate | 4.23e-05 | +| loss | -0.0344 | +| n_updates | 79160 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000109 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1398 | +| iterations | 15837 | +| time_elapsed | 23185 | +| total_timesteps | 32434176 | +| train/ | | +| approx_kl | 0.009392042 | +| clip_fraction | 0.329 | +| clip_range | 0.0669 | +| entropy_loss | -6.55 | +| explained_variance | 0.343 | +| learning_rate | 4.23e-05 | +| loss | -0.0265 | +| n_updates | 79164 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000167 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1398 | +| iterations | 15838 | +| time_elapsed | 23187 | +| total_timesteps | 32436224 | +| train/ | | +| approx_kl | 0.01150141 | +| clip_fraction | 0.335 | +| clip_range | 0.0669 | +| entropy_loss | -6.7 | +| explained_variance | 0.227 | +| learning_rate | 4.23e-05 | +| loss | -0.0315 | +| n_updates | 79168 | +| policy_gradient_loss | -0.0193 | +| value_loss | 7.71e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1398 | +| iterations | 15839 | +| time_elapsed | 23188 | +| total_timesteps | 32438272 | +| train/ | | +| approx_kl | 0.010485621 | +| clip_fraction | 0.313 | +| clip_range | 0.0669 | +| entropy_loss | -6.49 | +| explained_variance | 0.3 | +| learning_rate | 4.23e-05 | +| loss | -0.015 | +| n_updates | 79172 | +| policy_gradient_loss | -0.0146 | +| value_loss | 0.000179 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1398 | +| iterations | 15840 | +| time_elapsed | 23190 | +| total_timesteps | 32440320 | +| train/ | | +| approx_kl | 0.015923096 | +| clip_fraction | 0.357 | +| clip_range | 0.0669 | +| entropy_loss | -6.15 | +| explained_variance | 0.563 | +| learning_rate | 4.23e-05 | +| loss | -0.0296 | +| n_updates | 79176 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.00011 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1398 | +| iterations | 15841 | +| time_elapsed | 23191 | +| total_timesteps | 32442368 | +| train/ | | +| approx_kl | 0.014216314 | +| clip_fraction | 0.351 | +| clip_range | 0.0669 | +| entropy_loss | -6.33 | +| explained_variance | 0.275 | +| learning_rate | 4.23e-05 | +| loss | -0.028 | +| n_updates | 79180 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000159 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1398 | +| iterations | 15842 | +| time_elapsed | 23193 | +| total_timesteps | 32444416 | +| train/ | | +| approx_kl | 0.011464797 | +| clip_fraction | 0.308 | +| clip_range | 0.0669 | +| entropy_loss | -5.82 | +| explained_variance | 0.617 | +| learning_rate | 4.23e-05 | +| loss | -0.0305 | +| n_updates | 79184 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000116 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1398 | +| iterations | 15843 | +| time_elapsed | 23195 | +| total_timesteps | 32446464 | +| train/ | | +| approx_kl | 0.008381512 | +| clip_fraction | 0.289 | +| clip_range | 0.0669 | +| entropy_loss | -5.08 | +| explained_variance | 0.698 | +| learning_rate | 4.23e-05 | +| loss | -0.0219 | +| n_updates | 79188 | +| policy_gradient_loss | -0.0148 | +| value_loss | 0.000147 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1398 | +| iterations | 15844 | +| time_elapsed | 23196 | +| total_timesteps | 32448512 | +| train/ | | +| approx_kl | 0.0115604615 | +| clip_fraction | 0.329 | +| clip_range | 0.0669 | +| entropy_loss | -6.3 | +| explained_variance | 0.319 | +| learning_rate | 4.23e-05 | +| loss | -0.0277 | +| n_updates | 79192 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000158 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1398 | +| iterations | 15845 | +| time_elapsed | 23198 | +| total_timesteps | 32450560 | +| train/ | | +| approx_kl | 0.012478792 | +| clip_fraction | 0.341 | +| clip_range | 0.0669 | +| entropy_loss | -6.29 | +| explained_variance | 0.28 | +| learning_rate | 4.23e-05 | +| loss | -0.0256 | +| n_updates | 79196 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000143 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1398 | +| iterations | 15846 | +| time_elapsed | 23199 | +| total_timesteps | 32452608 | +| train/ | | +| approx_kl | 0.014927741 | +| clip_fraction | 0.36 | +| clip_range | 0.0669 | +| entropy_loss | -6.34 | +| explained_variance | 0.315 | +| learning_rate | 4.23e-05 | +| loss | -0.0293 | +| n_updates | 79200 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.00014 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1398 | +| iterations | 15847 | +| time_elapsed | 23201 | +| total_timesteps | 32454656 | +| train/ | | +| approx_kl | 0.0121371895 | +| clip_fraction | 0.312 | +| clip_range | 0.0669 | +| entropy_loss | -6.16 | +| explained_variance | 0.373 | +| learning_rate | 4.23e-05 | +| loss | -0.0268 | +| n_updates | 79204 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000238 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1398 | +| iterations | 15848 | +| time_elapsed | 23202 | +| total_timesteps | 32456704 | +| train/ | | +| approx_kl | 0.015696686 | +| clip_fraction | 0.349 | +| clip_range | 0.0669 | +| entropy_loss | -6.3 | +| explained_variance | 0.213 | +| learning_rate | 4.23e-05 | +| loss | -0.0339 | +| n_updates | 79208 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000194 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1398 | +| iterations | 15849 | +| time_elapsed | 23204 | +| total_timesteps | 32458752 | +| train/ | | +| approx_kl | 0.012734521 | +| clip_fraction | 0.345 | +| clip_range | 0.0669 | +| entropy_loss | -6.87 | +| explained_variance | -0.19 | +| learning_rate | 4.23e-05 | +| loss | -0.0349 | +| n_updates | 79212 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000158 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1398 | +| iterations | 15850 | +| time_elapsed | 23205 | +| total_timesteps | 32460800 | +| train/ | | +| approx_kl | 0.010367034 | +| clip_fraction | 0.308 | +| clip_range | 0.0669 | +| entropy_loss | -5.83 | +| explained_variance | 0.426 | +| learning_rate | 4.23e-05 | +| loss | -0.0217 | +| n_updates | 79216 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000348 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1398 | +| iterations | 15851 | +| time_elapsed | 23207 | +| total_timesteps | 32462848 | +| train/ | | +| approx_kl | 0.013384437 | +| clip_fraction | 0.351 | +| clip_range | 0.0669 | +| entropy_loss | -5.68 | +| explained_variance | 0.567 | +| learning_rate | 4.23e-05 | +| loss | -0.035 | +| n_updates | 79220 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1398 | +| iterations | 15852 | +| time_elapsed | 23208 | +| total_timesteps | 32464896 | +| train/ | | +| approx_kl | 0.014641922 | +| clip_fraction | 0.363 | +| clip_range | 0.0669 | +| entropy_loss | -6.35 | +| explained_variance | -0.135 | +| learning_rate | 4.23e-05 | +| loss | -0.0358 | +| n_updates | 79224 | +| policy_gradient_loss | -0.0218 | +| value_loss | 9.34e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1398 | +| iterations | 15853 | +| time_elapsed | 23210 | +| total_timesteps | 32466944 | +| train/ | | +| approx_kl | 0.01045946 | +| clip_fraction | 0.323 | +| clip_range | 0.0669 | +| entropy_loss | -6.42 | +| explained_variance | 0.329 | +| learning_rate | 4.23e-05 | +| loss | -0.0271 | +| n_updates | 79228 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000279 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1398 | +| iterations | 15854 | +| time_elapsed | 23211 | +| total_timesteps | 32468992 | +| train/ | | +| approx_kl | 0.01310306 | +| clip_fraction | 0.346 | +| clip_range | 0.0669 | +| entropy_loss | -5.8 | +| explained_variance | 0.466 | +| learning_rate | 4.23e-05 | +| loss | -0.0303 | +| n_updates | 79232 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000182 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1398 | +| iterations | 15855 | +| time_elapsed | 23213 | +| total_timesteps | 32471040 | +| train/ | | +| approx_kl | 0.011131672 | +| clip_fraction | 0.328 | +| clip_range | 0.0669 | +| entropy_loss | -6.02 | +| explained_variance | 0.559 | +| learning_rate | 4.23e-05 | +| loss | -0.0314 | +| n_updates | 79236 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1398 | +| iterations | 15856 | +| time_elapsed | 23214 | +| total_timesteps | 32473088 | +| train/ | | +| approx_kl | 0.009200849 | +| clip_fraction | 0.285 | +| clip_range | 0.0669 | +| entropy_loss | -6.14 | +| explained_variance | 0.543 | +| learning_rate | 4.23e-05 | +| loss | -0.0247 | +| n_updates | 79240 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.000194 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1398 | +| iterations | 15857 | +| time_elapsed | 23216 | +| total_timesteps | 32475136 | +| train/ | | +| approx_kl | 0.008535731 | +| clip_fraction | 0.295 | +| clip_range | 0.0669 | +| entropy_loss | -6.52 | +| explained_variance | 0.302 | +| learning_rate | 4.23e-05 | +| loss | -0.0321 | +| n_updates | 79244 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000168 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1398 | +| iterations | 15858 | +| time_elapsed | 23217 | +| total_timesteps | 32477184 | +| train/ | | +| approx_kl | 0.008918298 | +| clip_fraction | 0.313 | +| clip_range | 0.0669 | +| entropy_loss | -6.89 | +| explained_variance | 0.393 | +| learning_rate | 4.23e-05 | +| loss | -0.0249 | +| n_updates | 79248 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000169 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1398 | +| iterations | 15859 | +| time_elapsed | 23219 | +| total_timesteps | 32479232 | +| train/ | | +| approx_kl | 0.010338774 | +| clip_fraction | 0.284 | +| clip_range | 0.0669 | +| entropy_loss | -5.69 | +| explained_variance | 0.711 | +| learning_rate | 4.23e-05 | +| loss | -0.0314 | +| n_updates | 79252 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000151 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1398 | +| iterations | 15860 | +| time_elapsed | 23220 | +| total_timesteps | 32481280 | +| train/ | | +| approx_kl | 0.012506819 | +| clip_fraction | 0.336 | +| clip_range | 0.0669 | +| entropy_loss | -6.02 | +| explained_variance | -0.125 | +| learning_rate | 4.23e-05 | +| loss | -0.0325 | +| n_updates | 79256 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000128 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1398 | +| iterations | 15861 | +| time_elapsed | 23222 | +| total_timesteps | 32483328 | +| train/ | | +| approx_kl | 0.013829796 | +| clip_fraction | 0.369 | +| clip_range | 0.0669 | +| entropy_loss | -6.53 | +| explained_variance | -0.339 | +| learning_rate | 4.23e-05 | +| loss | -0.0312 | +| n_updates | 79260 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000121 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1398 | +| iterations | 15862 | +| time_elapsed | 23223 | +| total_timesteps | 32485376 | +| train/ | | +| approx_kl | 0.0124024525 | +| clip_fraction | 0.367 | +| clip_range | 0.0669 | +| entropy_loss | -6.74 | +| explained_variance | -0.0417 | +| learning_rate | 4.23e-05 | +| loss | -0.0304 | +| n_updates | 79264 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000244 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1398 | +| iterations | 15863 | +| time_elapsed | 23225 | +| total_timesteps | 32487424 | +| train/ | | +| approx_kl | 0.013056058 | +| clip_fraction | 0.314 | +| clip_range | 0.0669 | +| entropy_loss | -6.03 | +| explained_variance | 0.37 | +| learning_rate | 4.23e-05 | +| loss | -0.0249 | +| n_updates | 79268 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000341 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1398 | +| iterations | 15864 | +| time_elapsed | 23226 | +| total_timesteps | 32489472 | +| train/ | | +| approx_kl | 0.011225911 | +| clip_fraction | 0.324 | +| clip_range | 0.0669 | +| entropy_loss | -5.29 | +| explained_variance | 0.589 | +| learning_rate | 4.23e-05 | +| loss | -0.0252 | +| n_updates | 79272 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000217 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1398 | +| iterations | 15865 | +| time_elapsed | 23228 | +| total_timesteps | 32491520 | +| train/ | | +| approx_kl | 0.011073332 | +| clip_fraction | 0.339 | +| clip_range | 0.0669 | +| entropy_loss | -5.89 | +| explained_variance | 0.384 | +| learning_rate | 4.23e-05 | +| loss | -0.0303 | +| n_updates | 79276 | +| policy_gradient_loss | -0.0191 | +| value_loss | 9.94e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1398 | +| iterations | 15866 | +| time_elapsed | 23230 | +| total_timesteps | 32493568 | +| train/ | | +| approx_kl | 0.00980293 | +| clip_fraction | 0.299 | +| clip_range | 0.0669 | +| entropy_loss | -5.68 | +| explained_variance | 0.467 | +| learning_rate | 4.23e-05 | +| loss | -0.0242 | +| n_updates | 79280 | +| policy_gradient_loss | -0.0137 | +| value_loss | 0.00027 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1398 | +| iterations | 15867 | +| time_elapsed | 23231 | +| total_timesteps | 32495616 | +| train/ | | +| approx_kl | 0.014043985 | +| clip_fraction | 0.359 | +| clip_range | 0.0669 | +| entropy_loss | -5.66 | +| explained_variance | 0.711 | +| learning_rate | 4.23e-05 | +| loss | -0.0347 | +| n_updates | 79284 | +| policy_gradient_loss | -0.0217 | +| value_loss | 5.52e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1398 | +| iterations | 15868 | +| time_elapsed | 23233 | +| total_timesteps | 32497664 | +| train/ | | +| approx_kl | 0.0142972935 | +| clip_fraction | 0.328 | +| clip_range | 0.0669 | +| entropy_loss | -6.1 | +| explained_variance | 0.306 | +| learning_rate | 4.23e-05 | +| loss | -0.0248 | +| n_updates | 79288 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000181 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1398 | +| iterations | 15869 | +| time_elapsed | 23234 | +| total_timesteps | 32499712 | +| train/ | | +| approx_kl | 0.014038185 | +| clip_fraction | 0.358 | +| clip_range | 0.0669 | +| entropy_loss | -6.48 | +| explained_variance | -0.0258 | +| learning_rate | 4.23e-05 | +| loss | -0.0348 | +| n_updates | 79292 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000124 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1398 | +| iterations | 15870 | +| time_elapsed | 23236 | +| total_timesteps | 32501760 | +| train/ | | +| approx_kl | 0.014702087 | +| clip_fraction | 0.368 | +| clip_range | 0.0669 | +| entropy_loss | -6.58 | +| explained_variance | 0.0787 | +| learning_rate | 4.23e-05 | +| loss | -0.0263 | +| n_updates | 79296 | +| policy_gradient_loss | -0.02 | +| value_loss | 9.66e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1398 | +| iterations | 15871 | +| time_elapsed | 23237 | +| total_timesteps | 32503808 | +| train/ | | +| approx_kl | 0.0117466925 | +| clip_fraction | 0.307 | +| clip_range | 0.0669 | +| entropy_loss | -6.19 | +| explained_variance | 0.483 | +| learning_rate | 4.23e-05 | +| loss | -0.0275 | +| n_updates | 79300 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000218 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1398 | +| iterations | 15872 | +| time_elapsed | 23239 | +| total_timesteps | 32505856 | +| train/ | | +| approx_kl | 0.011529235 | +| clip_fraction | 0.323 | +| clip_range | 0.0669 | +| entropy_loss | -5.73 | +| explained_variance | 0.415 | +| learning_rate | 4.23e-05 | +| loss | -0.0227 | +| n_updates | 79304 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000231 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1398 | +| iterations | 15873 | +| time_elapsed | 23240 | +| total_timesteps | 32507904 | +| train/ | | +| approx_kl | 0.013583871 | +| clip_fraction | 0.358 | +| clip_range | 0.0669 | +| entropy_loss | -6.09 | +| explained_variance | 0.317 | +| learning_rate | 4.23e-05 | +| loss | -0.0293 | +| n_updates | 79308 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1398 | +| iterations | 15874 | +| time_elapsed | 23242 | +| total_timesteps | 32509952 | +| train/ | | +| approx_kl | 0.010623915 | +| clip_fraction | 0.289 | +| clip_range | 0.0669 | +| entropy_loss | -5.89 | +| explained_variance | 0.512 | +| learning_rate | 4.23e-05 | +| loss | -0.0204 | +| n_updates | 79312 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000263 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1398 | +| iterations | 15875 | +| time_elapsed | 23243 | +| total_timesteps | 32512000 | +| train/ | | +| approx_kl | 0.011903016 | +| clip_fraction | 0.324 | +| clip_range | 0.0669 | +| entropy_loss | -5.99 | +| explained_variance | 0.288 | +| learning_rate | 4.23e-05 | +| loss | -0.0235 | +| n_updates | 79316 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000211 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1398 | +| iterations | 15876 | +| time_elapsed | 23245 | +| total_timesteps | 32514048 | +| train/ | | +| approx_kl | 0.014520258 | +| clip_fraction | 0.342 | +| clip_range | 0.0669 | +| entropy_loss | -6.41 | +| explained_variance | 0.219 | +| learning_rate | 4.23e-05 | +| loss | -0.0334 | +| n_updates | 79320 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000218 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1398 | +| iterations | 15877 | +| time_elapsed | 23246 | +| total_timesteps | 32516096 | +| train/ | | +| approx_kl | 0.014367256 | +| clip_fraction | 0.38 | +| clip_range | 0.0669 | +| entropy_loss | -6.27 | +| explained_variance | -0.443 | +| learning_rate | 4.23e-05 | +| loss | -0.0339 | +| n_updates | 79324 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000108 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1398 | +| iterations | 15878 | +| time_elapsed | 23248 | +| total_timesteps | 32518144 | +| train/ | | +| approx_kl | 0.013089901 | +| clip_fraction | 0.367 | +| clip_range | 0.0669 | +| entropy_loss | -6.02 | +| explained_variance | 0.27 | +| learning_rate | 4.23e-05 | +| loss | -0.0254 | +| n_updates | 79328 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000172 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1398 | +| iterations | 15879 | +| time_elapsed | 23250 | +| total_timesteps | 32520192 | +| train/ | | +| approx_kl | 0.014780207 | +| clip_fraction | 0.343 | +| clip_range | 0.0669 | +| entropy_loss | -6.49 | +| explained_variance | 0.25 | +| learning_rate | 4.23e-05 | +| loss | -0.0281 | +| n_updates | 79332 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000226 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1398 | +| iterations | 15880 | +| time_elapsed | 23251 | +| total_timesteps | 32522240 | +| train/ | | +| approx_kl | 0.012536179 | +| clip_fraction | 0.343 | +| clip_range | 0.0669 | +| entropy_loss | -6.03 | +| explained_variance | 0.263 | +| learning_rate | 4.23e-05 | +| loss | -0.0191 | +| n_updates | 79336 | +| policy_gradient_loss | -0.0144 | +| value_loss | 0.000355 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1398 | +| iterations | 15881 | +| time_elapsed | 23253 | +| total_timesteps | 32524288 | +| train/ | | +| approx_kl | 0.014213879 | +| clip_fraction | 0.351 | +| clip_range | 0.0669 | +| entropy_loss | -5.72 | +| explained_variance | 0.579 | +| learning_rate | 4.23e-05 | +| loss | -0.0275 | +| n_updates | 79340 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000148 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1398 | +| iterations | 15882 | +| time_elapsed | 23254 | +| total_timesteps | 32526336 | +| train/ | | +| approx_kl | 0.015264239 | +| clip_fraction | 0.372 | +| clip_range | 0.0669 | +| entropy_loss | -6.1 | +| explained_variance | 0.504 | +| learning_rate | 4.23e-05 | +| loss | -0.0363 | +| n_updates | 79344 | +| policy_gradient_loss | -0.0232 | +| value_loss | 8.52e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1398 | +| iterations | 15883 | +| time_elapsed | 23256 | +| total_timesteps | 32528384 | +| train/ | | +| approx_kl | 0.012981015 | +| clip_fraction | 0.366 | +| clip_range | 0.0669 | +| entropy_loss | -6.38 | +| explained_variance | 0.54 | +| learning_rate | 4.23e-05 | +| loss | -0.0361 | +| n_updates | 79348 | +| policy_gradient_loss | -0.0203 | +| value_loss | 7.67e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1398 | +| iterations | 15884 | +| time_elapsed | 23257 | +| total_timesteps | 32530432 | +| train/ | | +| approx_kl | 0.015019252 | +| clip_fraction | 0.301 | +| clip_range | 0.0669 | +| entropy_loss | -6.28 | +| explained_variance | 0.226 | +| learning_rate | 4.23e-05 | +| loss | -0.026 | +| n_updates | 79352 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000187 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1398 | +| iterations | 15885 | +| time_elapsed | 23259 | +| total_timesteps | 32532480 | +| train/ | | +| approx_kl | 0.01178628 | +| clip_fraction | 0.317 | +| clip_range | 0.0669 | +| entropy_loss | -5.75 | +| explained_variance | 0.49 | +| learning_rate | 4.23e-05 | +| loss | -0.0241 | +| n_updates | 79356 | +| policy_gradient_loss | -0.0144 | +| value_loss | 0.000211 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1398 | +| iterations | 15886 | +| time_elapsed | 23260 | +| total_timesteps | 32534528 | +| train/ | | +| approx_kl | 0.01456143 | +| clip_fraction | 0.316 | +| clip_range | 0.0669 | +| entropy_loss | -6.17 | +| explained_variance | 0.192 | +| learning_rate | 4.23e-05 | +| loss | -0.0248 | +| n_updates | 79360 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000187 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1398 | +| iterations | 15887 | +| time_elapsed | 23262 | +| total_timesteps | 32536576 | +| train/ | | +| approx_kl | 0.011937867 | +| clip_fraction | 0.333 | +| clip_range | 0.0669 | +| entropy_loss | -6.2 | +| explained_variance | 0.337 | +| learning_rate | 4.23e-05 | +| loss | -0.029 | +| n_updates | 79364 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000145 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1398 | +| iterations | 15888 | +| time_elapsed | 23263 | +| total_timesteps | 32538624 | +| train/ | | +| approx_kl | 0.012898112 | +| clip_fraction | 0.34 | +| clip_range | 0.0669 | +| entropy_loss | -6.58 | +| explained_variance | 0.289 | +| learning_rate | 4.23e-05 | +| loss | -0.032 | +| n_updates | 79368 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000211 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1398 | +| iterations | 15889 | +| time_elapsed | 23265 | +| total_timesteps | 32540672 | +| train/ | | +| approx_kl | 0.011207411 | +| clip_fraction | 0.335 | +| clip_range | 0.0669 | +| entropy_loss | -6.52 | +| explained_variance | 0.346 | +| learning_rate | 4.23e-05 | +| loss | -0.0354 | +| n_updates | 79372 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000145 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1398 | +| iterations | 15890 | +| time_elapsed | 23267 | +| total_timesteps | 32542720 | +| train/ | | +| approx_kl | 0.010663309 | +| clip_fraction | 0.321 | +| clip_range | 0.0669 | +| entropy_loss | -6.64 | +| explained_variance | 0.1 | +| learning_rate | 4.23e-05 | +| loss | -0.0311 | +| n_updates | 79376 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000163 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1398 | +| iterations | 15891 | +| time_elapsed | 23268 | +| total_timesteps | 32544768 | +| train/ | | +| approx_kl | 0.011312105 | +| clip_fraction | 0.32 | +| clip_range | 0.0669 | +| entropy_loss | -6.28 | +| explained_variance | 0.652 | +| learning_rate | 4.23e-05 | +| loss | -0.0289 | +| n_updates | 79380 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000126 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1398 | +| iterations | 15892 | +| time_elapsed | 23270 | +| total_timesteps | 32546816 | +| train/ | | +| approx_kl | 0.011677177 | +| clip_fraction | 0.336 | +| clip_range | 0.0669 | +| entropy_loss | -6.03 | +| explained_variance | 0.602 | +| learning_rate | 4.23e-05 | +| loss | -0.0312 | +| n_updates | 79384 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000103 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1398 | +| iterations | 15893 | +| time_elapsed | 23271 | +| total_timesteps | 32548864 | +| train/ | | +| approx_kl | 0.0130908415 | +| clip_fraction | 0.331 | +| clip_range | 0.0669 | +| entropy_loss | -6.26 | +| explained_variance | 0.524 | +| learning_rate | 4.23e-05 | +| loss | -0.0346 | +| n_updates | 79388 | +| policy_gradient_loss | -0.0197 | +| value_loss | 6.07e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1398 | +| iterations | 15894 | +| time_elapsed | 23273 | +| total_timesteps | 32550912 | +| train/ | | +| approx_kl | 0.009387765 | +| clip_fraction | 0.302 | +| clip_range | 0.0669 | +| entropy_loss | -5.22 | +| explained_variance | 0.588 | +| learning_rate | 4.23e-05 | +| loss | -0.0202 | +| n_updates | 79392 | +| policy_gradient_loss | -0.0132 | +| value_loss | 0.000257 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1398 | +| iterations | 15895 | +| time_elapsed | 23274 | +| total_timesteps | 32552960 | +| train/ | | +| approx_kl | 0.011131304 | +| clip_fraction | 0.31 | +| clip_range | 0.0669 | +| entropy_loss | -6.03 | +| explained_variance | 0.0219 | +| learning_rate | 4.23e-05 | +| loss | -0.0228 | +| n_updates | 79396 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000194 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1398 | +| iterations | 15896 | +| time_elapsed | 23276 | +| total_timesteps | 32555008 | +| train/ | | +| approx_kl | 0.010546625 | +| clip_fraction | 0.319 | +| clip_range | 0.0669 | +| entropy_loss | -5.71 | +| explained_variance | 0.604 | +| learning_rate | 4.23e-05 | +| loss | -0.0309 | +| n_updates | 79400 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000177 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1398 | +| iterations | 15897 | +| time_elapsed | 23277 | +| total_timesteps | 32557056 | +| train/ | | +| approx_kl | 0.01165344 | +| clip_fraction | 0.346 | +| clip_range | 0.0669 | +| entropy_loss | -6.47 | +| explained_variance | -0.104 | +| learning_rate | 4.23e-05 | +| loss | -0.0339 | +| n_updates | 79404 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000156 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1398 | +| iterations | 15898 | +| time_elapsed | 23279 | +| total_timesteps | 32559104 | +| train/ | | +| approx_kl | 0.014378676 | +| clip_fraction | 0.341 | +| clip_range | 0.0669 | +| entropy_loss | -6.52 | +| explained_variance | 0.0403 | +| learning_rate | 4.23e-05 | +| loss | -0.0321 | +| n_updates | 79408 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.00013 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1398 | +| iterations | 15899 | +| time_elapsed | 23281 | +| total_timesteps | 32561152 | +| train/ | | +| approx_kl | 0.013219272 | +| clip_fraction | 0.325 | +| clip_range | 0.0669 | +| entropy_loss | -6.73 | +| explained_variance | 0.248 | +| learning_rate | 4.23e-05 | +| loss | -0.0236 | +| n_updates | 79412 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000142 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1398 | +| iterations | 15900 | +| time_elapsed | 23282 | +| total_timesteps | 32563200 | +| train/ | | +| approx_kl | 0.014261773 | +| clip_fraction | 0.384 | +| clip_range | 0.0669 | +| entropy_loss | -6.7 | +| explained_variance | -0.731 | +| learning_rate | 4.23e-05 | +| loss | -0.0413 | +| n_updates | 79416 | +| policy_gradient_loss | -0.0254 | +| value_loss | 4.16e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1398 | +| iterations | 15901 | +| time_elapsed | 23284 | +| total_timesteps | 32565248 | +| train/ | | +| approx_kl | 0.013825858 | +| clip_fraction | 0.329 | +| clip_range | 0.0669 | +| entropy_loss | -6.42 | +| explained_variance | -0.138 | +| learning_rate | 4.23e-05 | +| loss | -0.0244 | +| n_updates | 79420 | +| policy_gradient_loss | -0.0177 | +| value_loss | 9.03e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1398 | +| iterations | 15902 | +| time_elapsed | 23285 | +| total_timesteps | 32567296 | +| train/ | | +| approx_kl | 0.012488544 | +| clip_fraction | 0.315 | +| clip_range | 0.0669 | +| entropy_loss | -5.69 | +| explained_variance | 0.404 | +| learning_rate | 4.23e-05 | +| loss | -0.0241 | +| n_updates | 79424 | +| policy_gradient_loss | -0.0139 | +| value_loss | 0.000225 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1398 | +| iterations | 15903 | +| time_elapsed | 23287 | +| total_timesteps | 32569344 | +| train/ | | +| approx_kl | 0.013444245 | +| clip_fraction | 0.346 | +| clip_range | 0.0669 | +| entropy_loss | -5.97 | +| explained_variance | -0.0272 | +| learning_rate | 4.23e-05 | +| loss | -0.0333 | +| n_updates | 79428 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000258 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1398 | +| iterations | 15904 | +| time_elapsed | 23288 | +| total_timesteps | 32571392 | +| train/ | | +| approx_kl | 0.012011138 | +| clip_fraction | 0.328 | +| clip_range | 0.0669 | +| entropy_loss | -5.99 | +| explained_variance | 0.436 | +| learning_rate | 4.23e-05 | +| loss | -0.0322 | +| n_updates | 79432 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000159 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1398 | +| iterations | 15905 | +| time_elapsed | 23290 | +| total_timesteps | 32573440 | +| train/ | | +| approx_kl | 0.014213109 | +| clip_fraction | 0.336 | +| clip_range | 0.0669 | +| entropy_loss | -5.37 | +| explained_variance | 0.282 | +| learning_rate | 4.23e-05 | +| loss | -0.0199 | +| n_updates | 79436 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000345 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1398 | +| iterations | 15906 | +| time_elapsed | 23291 | +| total_timesteps | 32575488 | +| train/ | | +| approx_kl | 0.01517559 | +| clip_fraction | 0.394 | +| clip_range | 0.0669 | +| entropy_loss | -6.05 | +| explained_variance | -0.64 | +| learning_rate | 4.23e-05 | +| loss | -0.0366 | +| n_updates | 79440 | +| policy_gradient_loss | -0.0239 | +| value_loss | 0.000106 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1398 | +| iterations | 15907 | +| time_elapsed | 23293 | +| total_timesteps | 32577536 | +| train/ | | +| approx_kl | 0.013680145 | +| clip_fraction | 0.342 | +| clip_range | 0.0669 | +| entropy_loss | -6.51 | +| explained_variance | 0.141 | +| learning_rate | 4.23e-05 | +| loss | -0.0294 | +| n_updates | 79444 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000239 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1398 | +| iterations | 15908 | +| time_elapsed | 23295 | +| total_timesteps | 32579584 | +| train/ | | +| approx_kl | 0.010632742 | +| clip_fraction | 0.325 | +| clip_range | 0.0669 | +| entropy_loss | -6.67 | +| explained_variance | 0.0265 | +| learning_rate | 4.23e-05 | +| loss | -0.0246 | +| n_updates | 79448 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000357 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1398 | +| iterations | 15909 | +| time_elapsed | 23296 | +| total_timesteps | 32581632 | +| train/ | | +| approx_kl | 0.013016932 | +| clip_fraction | 0.305 | +| clip_range | 0.0669 | +| entropy_loss | -5.83 | +| explained_variance | 0.493 | +| learning_rate | 4.23e-05 | +| loss | -0.0247 | +| n_updates | 79452 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000184 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1398 | +| iterations | 15910 | +| time_elapsed | 23298 | +| total_timesteps | 32583680 | +| train/ | | +| approx_kl | 0.012311795 | +| clip_fraction | 0.37 | +| clip_range | 0.0669 | +| entropy_loss | -5.97 | +| explained_variance | 0.504 | +| learning_rate | 4.23e-05 | +| loss | -0.0264 | +| n_updates | 79456 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000165 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1398 | +| iterations | 15911 | +| time_elapsed | 23299 | +| total_timesteps | 32585728 | +| train/ | | +| approx_kl | 0.01007776 | +| clip_fraction | 0.313 | +| clip_range | 0.0669 | +| entropy_loss | -6.69 | +| explained_variance | 0.115 | +| learning_rate | 4.23e-05 | +| loss | -0.0284 | +| n_updates | 79460 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000225 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1398 | +| iterations | 15912 | +| time_elapsed | 23301 | +| total_timesteps | 32587776 | +| train/ | | +| approx_kl | 0.010432451 | +| clip_fraction | 0.333 | +| clip_range | 0.0669 | +| entropy_loss | -6.52 | +| explained_variance | 0.246 | +| learning_rate | 4.23e-05 | +| loss | -0.0282 | +| n_updates | 79464 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000131 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1398 | +| iterations | 15913 | +| time_elapsed | 23302 | +| total_timesteps | 32589824 | +| train/ | | +| approx_kl | 0.011677983 | +| clip_fraction | 0.282 | +| clip_range | 0.0669 | +| entropy_loss | -6.15 | +| explained_variance | 0.254 | +| learning_rate | 4.23e-05 | +| loss | -0.0177 | +| n_updates | 79468 | +| policy_gradient_loss | -0.0131 | +| value_loss | 0.000422 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1398 | +| iterations | 15914 | +| time_elapsed | 23304 | +| total_timesteps | 32591872 | +| train/ | | +| approx_kl | 0.012377445 | +| clip_fraction | 0.312 | +| clip_range | 0.0669 | +| entropy_loss | -5.84 | +| explained_variance | 0.485 | +| learning_rate | 4.23e-05 | +| loss | -0.0227 | +| n_updates | 79472 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000195 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1398 | +| iterations | 15915 | +| time_elapsed | 23305 | +| total_timesteps | 32593920 | +| train/ | | +| approx_kl | 0.012197806 | +| clip_fraction | 0.351 | +| clip_range | 0.0669 | +| entropy_loss | -6.07 | +| explained_variance | 0.164 | +| learning_rate | 4.23e-05 | +| loss | -0.0278 | +| n_updates | 79476 | +| policy_gradient_loss | -0.0197 | +| value_loss | 9.75e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1398 | +| iterations | 15916 | +| time_elapsed | 23307 | +| total_timesteps | 32595968 | +| train/ | | +| approx_kl | 0.010183135 | +| clip_fraction | 0.309 | +| clip_range | 0.0669 | +| entropy_loss | -5.55 | +| explained_variance | 0.718 | +| learning_rate | 4.23e-05 | +| loss | -0.0237 | +| n_updates | 79480 | +| policy_gradient_loss | -0.0138 | +| value_loss | 8.94e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1398 | +| iterations | 15917 | +| time_elapsed | 23309 | +| total_timesteps | 32598016 | +| train/ | | +| approx_kl | 0.008961583 | +| clip_fraction | 0.308 | +| clip_range | 0.0669 | +| entropy_loss | -5.86 | +| explained_variance | 0.44 | +| learning_rate | 4.23e-05 | +| loss | -0.0325 | +| n_updates | 79484 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000122 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1398 | +| iterations | 15918 | +| time_elapsed | 23310 | +| total_timesteps | 32600064 | +| train/ | | +| approx_kl | 0.0149166845 | +| clip_fraction | 0.366 | +| clip_range | 0.0669 | +| entropy_loss | -5.99 | +| explained_variance | 0.495 | +| learning_rate | 4.23e-05 | +| loss | -0.0296 | +| n_updates | 79488 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.0001 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1398 | +| iterations | 15919 | +| time_elapsed | 23312 | +| total_timesteps | 32602112 | +| train/ | | +| approx_kl | 0.018277407 | +| clip_fraction | 0.357 | +| clip_range | 0.0668 | +| entropy_loss | -6.11 | +| explained_variance | 0.415 | +| learning_rate | 4.23e-05 | +| loss | -0.0344 | +| n_updates | 79492 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.0001 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1398 | +| iterations | 15920 | +| time_elapsed | 23313 | +| total_timesteps | 32604160 | +| train/ | | +| approx_kl | 0.016135177 | +| clip_fraction | 0.317 | +| clip_range | 0.0668 | +| entropy_loss | -5.65 | +| explained_variance | 0.51 | +| learning_rate | 4.23e-05 | +| loss | -0.0263 | +| n_updates | 79496 | +| policy_gradient_loss | -0.014 | +| value_loss | 0.000223 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1398 | +| iterations | 15921 | +| time_elapsed | 23315 | +| total_timesteps | 32606208 | +| train/ | | +| approx_kl | 0.015225601 | +| clip_fraction | 0.377 | +| clip_range | 0.0668 | +| entropy_loss | -5.91 | +| explained_variance | 0.399 | +| learning_rate | 4.23e-05 | +| loss | -0.0343 | +| n_updates | 79500 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000139 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1398 | +| iterations | 15922 | +| time_elapsed | 23316 | +| total_timesteps | 32608256 | +| train/ | | +| approx_kl | 0.0130437305 | +| clip_fraction | 0.334 | +| clip_range | 0.0668 | +| entropy_loss | -6.3 | +| explained_variance | 0.281 | +| learning_rate | 4.23e-05 | +| loss | -0.0274 | +| n_updates | 79504 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000207 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1398 | +| iterations | 15923 | +| time_elapsed | 23318 | +| total_timesteps | 32610304 | +| train/ | | +| approx_kl | 0.014428284 | +| clip_fraction | 0.323 | +| clip_range | 0.0668 | +| entropy_loss | -6.25 | +| explained_variance | 0.431 | +| learning_rate | 4.23e-05 | +| loss | -0.0246 | +| n_updates | 79508 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000184 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1398 | +| iterations | 15924 | +| time_elapsed | 23319 | +| total_timesteps | 32612352 | +| train/ | | +| approx_kl | 0.010473644 | +| clip_fraction | 0.32 | +| clip_range | 0.0668 | +| entropy_loss | -6.03 | +| explained_variance | 0.454 | +| learning_rate | 4.23e-05 | +| loss | -0.0284 | +| n_updates | 79512 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000159 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1398 | +| iterations | 15925 | +| time_elapsed | 23321 | +| total_timesteps | 32614400 | +| train/ | | +| approx_kl | 0.010779006 | +| clip_fraction | 0.303 | +| clip_range | 0.0668 | +| entropy_loss | -5.96 | +| explained_variance | 0.444 | +| learning_rate | 4.23e-05 | +| loss | -0.0253 | +| n_updates | 79516 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.00021 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1398 | +| iterations | 15926 | +| time_elapsed | 23322 | +| total_timesteps | 32616448 | +| train/ | | +| approx_kl | 0.013404779 | +| clip_fraction | 0.336 | +| clip_range | 0.0668 | +| entropy_loss | -6.07 | +| explained_variance | 0.416 | +| learning_rate | 4.23e-05 | +| loss | -0.031 | +| n_updates | 79520 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000109 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1398 | +| iterations | 15927 | +| time_elapsed | 23324 | +| total_timesteps | 32618496 | +| train/ | | +| approx_kl | 0.015906466 | +| clip_fraction | 0.332 | +| clip_range | 0.0668 | +| entropy_loss | -6.27 | +| explained_variance | 0.443 | +| learning_rate | 4.23e-05 | +| loss | -0.022 | +| n_updates | 79524 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000114 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1398 | +| iterations | 15928 | +| time_elapsed | 23325 | +| total_timesteps | 32620544 | +| train/ | | +| approx_kl | 0.012438676 | +| clip_fraction | 0.355 | +| clip_range | 0.0668 | +| entropy_loss | -6.06 | +| explained_variance | 0.699 | +| learning_rate | 4.23e-05 | +| loss | -0.0286 | +| n_updates | 79528 | +| policy_gradient_loss | -0.0191 | +| value_loss | 5.94e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1398 | +| iterations | 15929 | +| time_elapsed | 23327 | +| total_timesteps | 32622592 | +| train/ | | +| approx_kl | 0.010725068 | +| clip_fraction | 0.317 | +| clip_range | 0.0668 | +| entropy_loss | -6.35 | +| explained_variance | 0.19 | +| learning_rate | 4.23e-05 | +| loss | -0.0276 | +| n_updates | 79532 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000131 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1398 | +| iterations | 15930 | +| time_elapsed | 23328 | +| total_timesteps | 32624640 | +| train/ | | +| approx_kl | 0.011482028 | +| clip_fraction | 0.294 | +| clip_range | 0.0668 | +| entropy_loss | -5.92 | +| explained_variance | 0.405 | +| learning_rate | 4.23e-05 | +| loss | -0.0197 | +| n_updates | 79536 | +| policy_gradient_loss | -0.0134 | +| value_loss | 0.000205 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1398 | +| iterations | 15931 | +| time_elapsed | 23330 | +| total_timesteps | 32626688 | +| train/ | | +| approx_kl | 0.011858475 | +| clip_fraction | 0.293 | +| clip_range | 0.0668 | +| entropy_loss | -5.98 | +| explained_variance | 0.449 | +| learning_rate | 4.23e-05 | +| loss | -0.0212 | +| n_updates | 79540 | +| policy_gradient_loss | -0.0148 | +| value_loss | 0.000212 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1398 | +| iterations | 15932 | +| time_elapsed | 23331 | +| total_timesteps | 32628736 | +| train/ | | +| approx_kl | 0.01380139 | +| clip_fraction | 0.323 | +| clip_range | 0.0668 | +| entropy_loss | -6.28 | +| explained_variance | 0.0516 | +| learning_rate | 4.23e-05 | +| loss | -0.026 | +| n_updates | 79544 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000223 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1398 | +| iterations | 15933 | +| time_elapsed | 23333 | +| total_timesteps | 32630784 | +| train/ | | +| approx_kl | 0.015340791 | +| clip_fraction | 0.386 | +| clip_range | 0.0668 | +| entropy_loss | -6.41 | +| explained_variance | 0.0794 | +| learning_rate | 4.23e-05 | +| loss | -0.035 | +| n_updates | 79548 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000144 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1398 | +| iterations | 15934 | +| time_elapsed | 23335 | +| total_timesteps | 32632832 | +| train/ | | +| approx_kl | 0.01300605 | +| clip_fraction | 0.345 | +| clip_range | 0.0668 | +| entropy_loss | -5.91 | +| explained_variance | 0.48 | +| learning_rate | 4.23e-05 | +| loss | -0.0205 | +| n_updates | 79552 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.00018 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1398 | +| iterations | 15935 | +| time_elapsed | 23336 | +| total_timesteps | 32634880 | +| train/ | | +| approx_kl | 0.013264853 | +| clip_fraction | 0.328 | +| clip_range | 0.0668 | +| entropy_loss | -6.35 | +| explained_variance | 0.365 | +| learning_rate | 4.22e-05 | +| loss | -0.0303 | +| n_updates | 79556 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.00013 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1398 | +| iterations | 15936 | +| time_elapsed | 23337 | +| total_timesteps | 32636928 | +| train/ | | +| approx_kl | 0.0143989995 | +| clip_fraction | 0.34 | +| clip_range | 0.0668 | +| entropy_loss | -6.09 | +| explained_variance | 0.329 | +| learning_rate | 4.22e-05 | +| loss | -0.0289 | +| n_updates | 79560 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000343 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1398 | +| iterations | 15937 | +| time_elapsed | 23339 | +| total_timesteps | 32638976 | +| train/ | | +| approx_kl | 0.010919476 | +| clip_fraction | 0.33 | +| clip_range | 0.0668 | +| entropy_loss | -5.64 | +| explained_variance | 0.396 | +| learning_rate | 4.22e-05 | +| loss | -0.0253 | +| n_updates | 79564 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000226 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1398 | +| iterations | 15938 | +| time_elapsed | 23341 | +| total_timesteps | 32641024 | +| train/ | | +| approx_kl | 0.013579371 | +| clip_fraction | 0.329 | +| clip_range | 0.0668 | +| entropy_loss | -6.18 | +| explained_variance | 0.37 | +| learning_rate | 4.22e-05 | +| loss | -0.0253 | +| n_updates | 79568 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000232 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1398 | +| iterations | 15939 | +| time_elapsed | 23342 | +| total_timesteps | 32643072 | +| train/ | | +| approx_kl | 0.013579819 | +| clip_fraction | 0.368 | +| clip_range | 0.0668 | +| entropy_loss | -6.72 | +| explained_variance | -0.0882 | +| learning_rate | 4.22e-05 | +| loss | -0.0353 | +| n_updates | 79572 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000193 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1398 | +| iterations | 15940 | +| time_elapsed | 23344 | +| total_timesteps | 32645120 | +| train/ | | +| approx_kl | 0.015440134 | +| clip_fraction | 0.34 | +| clip_range | 0.0668 | +| entropy_loss | -6.21 | +| explained_variance | 0.369 | +| learning_rate | 4.22e-05 | +| loss | -0.0293 | +| n_updates | 79576 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000196 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1398 | +| iterations | 15941 | +| time_elapsed | 23345 | +| total_timesteps | 32647168 | +| train/ | | +| approx_kl | 0.0131273195 | +| clip_fraction | 0.332 | +| clip_range | 0.0668 | +| entropy_loss | -6.28 | +| explained_variance | 0.283 | +| learning_rate | 4.22e-05 | +| loss | -0.0343 | +| n_updates | 79580 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000146 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1398 | +| iterations | 15942 | +| time_elapsed | 23347 | +| total_timesteps | 32649216 | +| train/ | | +| approx_kl | 0.013655974 | +| clip_fraction | 0.356 | +| clip_range | 0.0668 | +| entropy_loss | -6.08 | +| explained_variance | 0.435 | +| learning_rate | 4.22e-05 | +| loss | -0.0339 | +| n_updates | 79584 | +| policy_gradient_loss | -0.0196 | +| value_loss | 9.95e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1398 | +| iterations | 15943 | +| time_elapsed | 23348 | +| total_timesteps | 32651264 | +| train/ | | +| approx_kl | 0.015866097 | +| clip_fraction | 0.343 | +| clip_range | 0.0668 | +| entropy_loss | -5.68 | +| explained_variance | 0.606 | +| learning_rate | 4.22e-05 | +| loss | -0.0297 | +| n_updates | 79588 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000132 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1398 | +| iterations | 15944 | +| time_elapsed | 23350 | +| total_timesteps | 32653312 | +| train/ | | +| approx_kl | 0.013571387 | +| clip_fraction | 0.318 | +| clip_range | 0.0668 | +| entropy_loss | -6.54 | +| explained_variance | -0.106 | +| learning_rate | 4.22e-05 | +| loss | -0.0281 | +| n_updates | 79592 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000119 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1398 | +| iterations | 15945 | +| time_elapsed | 23351 | +| total_timesteps | 32655360 | +| train/ | | +| approx_kl | 0.015796095 | +| clip_fraction | 0.372 | +| clip_range | 0.0668 | +| entropy_loss | -6.67 | +| explained_variance | 0.172 | +| learning_rate | 4.22e-05 | +| loss | -0.0286 | +| n_updates | 79596 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000105 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1398 | +| iterations | 15946 | +| time_elapsed | 23353 | +| total_timesteps | 32657408 | +| train/ | | +| approx_kl | 0.015157663 | +| clip_fraction | 0.34 | +| clip_range | 0.0668 | +| entropy_loss | -6.07 | +| explained_variance | 0.436 | +| learning_rate | 4.22e-05 | +| loss | -0.0273 | +| n_updates | 79600 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000153 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1398 | +| iterations | 15947 | +| time_elapsed | 23354 | +| total_timesteps | 32659456 | +| train/ | | +| approx_kl | 0.018008158 | +| clip_fraction | 0.369 | +| clip_range | 0.0668 | +| entropy_loss | -5.84 | +| explained_variance | 0.645 | +| learning_rate | 4.22e-05 | +| loss | -0.0273 | +| n_updates | 79604 | +| policy_gradient_loss | -0.0199 | +| value_loss | 8.65e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1398 | +| iterations | 15948 | +| time_elapsed | 23356 | +| total_timesteps | 32661504 | +| train/ | | +| approx_kl | 0.011197035 | +| clip_fraction | 0.335 | +| clip_range | 0.0668 | +| entropy_loss | -6.33 | +| explained_variance | 0.455 | +| learning_rate | 4.22e-05 | +| loss | -0.0283 | +| n_updates | 79608 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000156 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1398 | +| iterations | 15949 | +| time_elapsed | 23357 | +| total_timesteps | 32663552 | +| train/ | | +| approx_kl | 0.012812404 | +| clip_fraction | 0.31 | +| clip_range | 0.0668 | +| entropy_loss | -6.44 | +| explained_variance | 0.209 | +| learning_rate | 4.22e-05 | +| loss | -0.0203 | +| n_updates | 79612 | +| policy_gradient_loss | -0.0148 | +| value_loss | 0.000307 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1398 | +| iterations | 15950 | +| time_elapsed | 23359 | +| total_timesteps | 32665600 | +| train/ | | +| approx_kl | 0.011453217 | +| clip_fraction | 0.316 | +| clip_range | 0.0668 | +| entropy_loss | -5.62 | +| explained_variance | 0.798 | +| learning_rate | 4.22e-05 | +| loss | -0.0258 | +| n_updates | 79616 | +| policy_gradient_loss | -0.0179 | +| value_loss | 8.35e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1398 | +| iterations | 15951 | +| time_elapsed | 23360 | +| total_timesteps | 32667648 | +| train/ | | +| approx_kl | 0.016085526 | +| clip_fraction | 0.349 | +| clip_range | 0.0668 | +| entropy_loss | -5.99 | +| explained_variance | 0.372 | +| learning_rate | 4.22e-05 | +| loss | -0.0291 | +| n_updates | 79620 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000145 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1398 | +| iterations | 15952 | +| time_elapsed | 23362 | +| total_timesteps | 32669696 | +| train/ | | +| approx_kl | 0.013013378 | +| clip_fraction | 0.322 | +| clip_range | 0.0668 | +| entropy_loss | -6.46 | +| explained_variance | 0.258 | +| learning_rate | 4.22e-05 | +| loss | -0.0294 | +| n_updates | 79624 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000198 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1398 | +| iterations | 15953 | +| time_elapsed | 23363 | +| total_timesteps | 32671744 | +| train/ | | +| approx_kl | 0.01741465 | +| clip_fraction | 0.345 | +| clip_range | 0.0668 | +| entropy_loss | -6.46 | +| explained_variance | -0.319 | +| learning_rate | 4.22e-05 | +| loss | -0.0292 | +| n_updates | 79628 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000131 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1398 | +| iterations | 15954 | +| time_elapsed | 23365 | +| total_timesteps | 32673792 | +| train/ | | +| approx_kl | 0.013564292 | +| clip_fraction | 0.337 | +| clip_range | 0.0668 | +| entropy_loss | -6.61 | +| explained_variance | 0.361 | +| learning_rate | 4.22e-05 | +| loss | -0.0304 | +| n_updates | 79632 | +| policy_gradient_loss | -0.0198 | +| value_loss | 9.4e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1398 | +| iterations | 15955 | +| time_elapsed | 23367 | +| total_timesteps | 32675840 | +| train/ | | +| approx_kl | 0.010185752 | +| clip_fraction | 0.317 | +| clip_range | 0.0668 | +| entropy_loss | -6.47 | +| explained_variance | 0.229 | +| learning_rate | 4.22e-05 | +| loss | -0.0292 | +| n_updates | 79636 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000167 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1398 | +| iterations | 15956 | +| time_elapsed | 23368 | +| total_timesteps | 32677888 | +| train/ | | +| approx_kl | 0.01124429 | +| clip_fraction | 0.322 | +| clip_range | 0.0668 | +| entropy_loss | -6.44 | +| explained_variance | 0.205 | +| learning_rate | 4.22e-05 | +| loss | -0.0285 | +| n_updates | 79640 | +| policy_gradient_loss | -0.0145 | +| value_loss | 0.000308 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1398 | +| iterations | 15957 | +| time_elapsed | 23370 | +| total_timesteps | 32679936 | +| train/ | | +| approx_kl | 0.013405547 | +| clip_fraction | 0.351 | +| clip_range | 0.0668 | +| entropy_loss | -6.2 | +| explained_variance | 0.517 | +| learning_rate | 4.22e-05 | +| loss | -0.027 | +| n_updates | 79644 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.00013 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1398 | +| iterations | 15958 | +| time_elapsed | 23371 | +| total_timesteps | 32681984 | +| train/ | | +| approx_kl | 0.010754311 | +| clip_fraction | 0.325 | +| clip_range | 0.0668 | +| entropy_loss | -5.92 | +| explained_variance | 0.42 | +| learning_rate | 4.22e-05 | +| loss | -0.0192 | +| n_updates | 79648 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000221 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1398 | +| iterations | 15959 | +| time_elapsed | 23373 | +| total_timesteps | 32684032 | +| train/ | | +| approx_kl | 0.010271676 | +| clip_fraction | 0.328 | +| clip_range | 0.0668 | +| entropy_loss | -5.42 | +| explained_variance | 0.632 | +| learning_rate | 4.22e-05 | +| loss | -0.0282 | +| n_updates | 79652 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000152 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1398 | +| iterations | 15960 | +| time_elapsed | 23374 | +| total_timesteps | 32686080 | +| train/ | | +| approx_kl | 0.016821053 | +| clip_fraction | 0.325 | +| clip_range | 0.0668 | +| entropy_loss | -6.05 | +| explained_variance | 0.387 | +| learning_rate | 4.22e-05 | +| loss | -0.0284 | +| n_updates | 79656 | +| policy_gradient_loss | -0.0198 | +| value_loss | 9.99e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1398 | +| iterations | 15961 | +| time_elapsed | 23376 | +| total_timesteps | 32688128 | +| train/ | | +| approx_kl | 0.013486177 | +| clip_fraction | 0.33 | +| clip_range | 0.0668 | +| entropy_loss | -6.22 | +| explained_variance | 0.484 | +| learning_rate | 4.22e-05 | +| loss | -0.0318 | +| n_updates | 79660 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000146 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1398 | +| iterations | 15962 | +| time_elapsed | 23377 | +| total_timesteps | 32690176 | +| train/ | | +| approx_kl | 0.015562679 | +| clip_fraction | 0.359 | +| clip_range | 0.0668 | +| entropy_loss | -6.15 | +| explained_variance | 0.267 | +| learning_rate | 4.22e-05 | +| loss | -0.0321 | +| n_updates | 79664 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000142 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1398 | +| iterations | 15963 | +| time_elapsed | 23379 | +| total_timesteps | 32692224 | +| train/ | | +| approx_kl | 0.013879202 | +| clip_fraction | 0.317 | +| clip_range | 0.0668 | +| entropy_loss | -6.41 | +| explained_variance | 0.251 | +| learning_rate | 4.22e-05 | +| loss | -0.0245 | +| n_updates | 79668 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000264 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1398 | +| iterations | 15964 | +| time_elapsed | 23380 | +| total_timesteps | 32694272 | +| train/ | | +| approx_kl | 0.010433404 | +| clip_fraction | 0.337 | +| clip_range | 0.0668 | +| entropy_loss | -6.33 | +| explained_variance | 0.465 | +| learning_rate | 4.22e-05 | +| loss | -0.0339 | +| n_updates | 79672 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000101 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1398 | +| iterations | 15965 | +| time_elapsed | 23382 | +| total_timesteps | 32696320 | +| train/ | | +| approx_kl | 0.012519557 | +| clip_fraction | 0.37 | +| clip_range | 0.0668 | +| entropy_loss | -6.49 | +| explained_variance | 0.596 | +| learning_rate | 4.22e-05 | +| loss | -0.0402 | +| n_updates | 79676 | +| policy_gradient_loss | -0.0228 | +| value_loss | 6.65e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1398 | +| iterations | 15966 | +| time_elapsed | 23383 | +| total_timesteps | 32698368 | +| train/ | | +| approx_kl | 0.013561614 | +| clip_fraction | 0.327 | +| clip_range | 0.0668 | +| entropy_loss | -6.3 | +| explained_variance | -0.0749 | +| learning_rate | 4.22e-05 | +| loss | -0.0259 | +| n_updates | 79680 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000136 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1398 | +| iterations | 15967 | +| time_elapsed | 23385 | +| total_timesteps | 32700416 | +| train/ | | +| approx_kl | 0.017699964 | +| clip_fraction | 0.295 | +| clip_range | 0.0668 | +| entropy_loss | -5.92 | +| explained_variance | 0.588 | +| learning_rate | 4.22e-05 | +| loss | -0.0249 | +| n_updates | 79684 | +| policy_gradient_loss | -0.014 | +| value_loss | 0.000166 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1398 | +| iterations | 15968 | +| time_elapsed | 23386 | +| total_timesteps | 32702464 | +| train/ | | +| approx_kl | 0.01037658 | +| clip_fraction | 0.302 | +| clip_range | 0.0668 | +| entropy_loss | -5.48 | +| explained_variance | 0.562 | +| learning_rate | 4.22e-05 | +| loss | -0.0247 | +| n_updates | 79688 | +| policy_gradient_loss | -0.0145 | +| value_loss | 0.000287 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1398 | +| iterations | 15969 | +| time_elapsed | 23388 | +| total_timesteps | 32704512 | +| train/ | | +| approx_kl | 0.014101487 | +| clip_fraction | 0.319 | +| clip_range | 0.0668 | +| entropy_loss | -6.05 | +| explained_variance | 0.324 | +| learning_rate | 4.22e-05 | +| loss | -0.0237 | +| n_updates | 79692 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000185 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1398 | +| iterations | 15970 | +| time_elapsed | 23389 | +| total_timesteps | 32706560 | +| train/ | | +| approx_kl | 0.010751988 | +| clip_fraction | 0.335 | +| clip_range | 0.0668 | +| entropy_loss | -5.93 | +| explained_variance | 0.433 | +| learning_rate | 4.22e-05 | +| loss | -0.0287 | +| n_updates | 79696 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.00018 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1398 | +| iterations | 15971 | +| time_elapsed | 23391 | +| total_timesteps | 32708608 | +| train/ | | +| approx_kl | 0.011407954 | +| clip_fraction | 0.344 | +| clip_range | 0.0668 | +| entropy_loss | -6.6 | +| explained_variance | -0.16 | +| learning_rate | 4.22e-05 | +| loss | -0.0301 | +| n_updates | 79700 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000103 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1398 | +| iterations | 15972 | +| time_elapsed | 23392 | +| total_timesteps | 32710656 | +| train/ | | +| approx_kl | 0.012279762 | +| clip_fraction | 0.345 | +| clip_range | 0.0668 | +| entropy_loss | -6.05 | +| explained_variance | 0.424 | +| learning_rate | 4.22e-05 | +| loss | -0.0281 | +| n_updates | 79704 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000244 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1398 | +| iterations | 15973 | +| time_elapsed | 23394 | +| total_timesteps | 32712704 | +| train/ | | +| approx_kl | 0.012516009 | +| clip_fraction | 0.353 | +| clip_range | 0.0668 | +| entropy_loss | -6.41 | +| explained_variance | 0.229 | +| learning_rate | 4.22e-05 | +| loss | -0.0292 | +| n_updates | 79708 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000139 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1398 | +| iterations | 15974 | +| time_elapsed | 23395 | +| total_timesteps | 32714752 | +| train/ | | +| approx_kl | 0.010552944 | +| clip_fraction | 0.317 | +| clip_range | 0.0668 | +| entropy_loss | -6.53 | +| explained_variance | 0.374 | +| learning_rate | 4.22e-05 | +| loss | -0.0283 | +| n_updates | 79712 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000184 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1398 | +| iterations | 15975 | +| time_elapsed | 23397 | +| total_timesteps | 32716800 | +| train/ | | +| approx_kl | 0.008933466 | +| clip_fraction | 0.296 | +| clip_range | 0.0668 | +| entropy_loss | -5.87 | +| explained_variance | 0.459 | +| learning_rate | 4.22e-05 | +| loss | -0.0202 | +| n_updates | 79716 | +| policy_gradient_loss | -0.0141 | +| value_loss | 0.000356 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1398 | +| iterations | 15976 | +| time_elapsed | 23399 | +| total_timesteps | 32718848 | +| train/ | | +| approx_kl | 0.011589479 | +| clip_fraction | 0.327 | +| clip_range | 0.0668 | +| entropy_loss | -5.9 | +| explained_variance | 0.389 | +| learning_rate | 4.22e-05 | +| loss | -0.0291 | +| n_updates | 79720 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000173 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1398 | +| iterations | 15977 | +| time_elapsed | 23400 | +| total_timesteps | 32720896 | +| train/ | | +| approx_kl | 0.01075908 | +| clip_fraction | 0.329 | +| clip_range | 0.0668 | +| entropy_loss | -6.86 | +| explained_variance | -0.0586 | +| learning_rate | 4.22e-05 | +| loss | -0.0317 | +| n_updates | 79724 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000204 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1398 | +| iterations | 15978 | +| time_elapsed | 23402 | +| total_timesteps | 32722944 | +| train/ | | +| approx_kl | 0.013555765 | +| clip_fraction | 0.362 | +| clip_range | 0.0668 | +| entropy_loss | -6.12 | +| explained_variance | 0.816 | +| learning_rate | 4.22e-05 | +| loss | -0.0288 | +| n_updates | 79728 | +| policy_gradient_loss | -0.0222 | +| value_loss | 5.5e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1398 | +| iterations | 15979 | +| time_elapsed | 23403 | +| total_timesteps | 32724992 | +| train/ | | +| approx_kl | 0.012459174 | +| clip_fraction | 0.344 | +| clip_range | 0.0668 | +| entropy_loss | -5.76 | +| explained_variance | 0.406 | +| learning_rate | 4.22e-05 | +| loss | -0.0312 | +| n_updates | 79732 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000221 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1398 | +| iterations | 15980 | +| time_elapsed | 23405 | +| total_timesteps | 32727040 | +| train/ | | +| approx_kl | 0.012132513 | +| clip_fraction | 0.317 | +| clip_range | 0.0668 | +| entropy_loss | -5.57 | +| explained_variance | 0.431 | +| learning_rate | 4.22e-05 | +| loss | -0.0335 | +| n_updates | 79736 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.00032 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1398 | +| iterations | 15981 | +| time_elapsed | 23406 | +| total_timesteps | 32729088 | +| train/ | | +| approx_kl | 0.012452163 | +| clip_fraction | 0.347 | +| clip_range | 0.0668 | +| entropy_loss | -5.58 | +| explained_variance | 0.677 | +| learning_rate | 4.22e-05 | +| loss | -0.0266 | +| n_updates | 79740 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000116 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1398 | +| iterations | 15982 | +| time_elapsed | 23408 | +| total_timesteps | 32731136 | +| train/ | | +| approx_kl | 0.012113615 | +| clip_fraction | 0.356 | +| clip_range | 0.0668 | +| entropy_loss | -5.65 | +| explained_variance | 0.651 | +| learning_rate | 4.22e-05 | +| loss | -0.0311 | +| n_updates | 79744 | +| policy_gradient_loss | -0.0213 | +| value_loss | 7.73e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1398 | +| iterations | 15983 | +| time_elapsed | 23409 | +| total_timesteps | 32733184 | +| train/ | | +| approx_kl | 0.011953922 | +| clip_fraction | 0.318 | +| clip_range | 0.0668 | +| entropy_loss | -6.74 | +| explained_variance | 0.152 | +| learning_rate | 4.22e-05 | +| loss | -0.0285 | +| n_updates | 79748 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000161 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1398 | +| iterations | 15984 | +| time_elapsed | 23411 | +| total_timesteps | 32735232 | +| train/ | | +| approx_kl | 0.011630146 | +| clip_fraction | 0.333 | +| clip_range | 0.0668 | +| entropy_loss | -6.42 | +| explained_variance | 0.376 | +| learning_rate | 4.22e-05 | +| loss | -0.0259 | +| n_updates | 79752 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000147 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1398 | +| iterations | 15985 | +| time_elapsed | 23412 | +| total_timesteps | 32737280 | +| train/ | | +| approx_kl | 0.009949624 | +| clip_fraction | 0.294 | +| clip_range | 0.0668 | +| entropy_loss | -6.71 | +| explained_variance | 0.288 | +| learning_rate | 4.22e-05 | +| loss | -0.0219 | +| n_updates | 79756 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000186 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1398 | +| iterations | 15986 | +| time_elapsed | 23414 | +| total_timesteps | 32739328 | +| train/ | | +| approx_kl | 0.009199163 | +| clip_fraction | 0.29 | +| clip_range | 0.0668 | +| entropy_loss | -5.83 | +| explained_variance | 0.465 | +| learning_rate | 4.22e-05 | +| loss | -0.0221 | +| n_updates | 79760 | +| policy_gradient_loss | -0.0145 | +| value_loss | 0.000285 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1398 | +| iterations | 15987 | +| time_elapsed | 23415 | +| total_timesteps | 32741376 | +| train/ | | +| approx_kl | 0.0109664565 | +| clip_fraction | 0.324 | +| clip_range | 0.0668 | +| entropy_loss | -5.65 | +| explained_variance | 0.498 | +| learning_rate | 4.22e-05 | +| loss | -0.0277 | +| n_updates | 79764 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000197 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1398 | +| iterations | 15988 | +| time_elapsed | 23417 | +| total_timesteps | 32743424 | +| train/ | | +| approx_kl | 0.011441508 | +| clip_fraction | 0.347 | +| clip_range | 0.0668 | +| entropy_loss | -6.2 | +| explained_variance | 0.401 | +| learning_rate | 4.22e-05 | +| loss | -0.0269 | +| n_updates | 79768 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.00017 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1398 | +| iterations | 15989 | +| time_elapsed | 23418 | +| total_timesteps | 32745472 | +| train/ | | +| approx_kl | 0.008766751 | +| clip_fraction | 0.301 | +| clip_range | 0.0668 | +| entropy_loss | -6.42 | +| explained_variance | 0.33 | +| learning_rate | 4.22e-05 | +| loss | -0.0133 | +| n_updates | 79772 | +| policy_gradient_loss | -0.0142 | +| value_loss | 0.000245 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1398 | +| iterations | 15990 | +| time_elapsed | 23420 | +| total_timesteps | 32747520 | +| train/ | | +| approx_kl | 0.012747711 | +| clip_fraction | 0.352 | +| clip_range | 0.0668 | +| entropy_loss | -6.04 | +| explained_variance | 0.582 | +| learning_rate | 4.22e-05 | +| loss | -0.0331 | +| n_updates | 79776 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000142 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1398 | +| iterations | 15991 | +| time_elapsed | 23421 | +| total_timesteps | 32749568 | +| train/ | | +| approx_kl | 0.011943962 | +| clip_fraction | 0.355 | +| clip_range | 0.0668 | +| entropy_loss | -6.11 | +| explained_variance | 0.178 | +| learning_rate | 4.22e-05 | +| loss | -0.0266 | +| n_updates | 79780 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000246 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1398 | +| iterations | 15992 | +| time_elapsed | 23423 | +| total_timesteps | 32751616 | +| train/ | | +| approx_kl | 0.015504837 | +| clip_fraction | 0.327 | +| clip_range | 0.0668 | +| entropy_loss | -5.7 | +| explained_variance | 0.592 | +| learning_rate | 4.22e-05 | +| loss | -0.0246 | +| n_updates | 79784 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000162 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1398 | +| iterations | 15993 | +| time_elapsed | 23425 | +| total_timesteps | 32753664 | +| train/ | | +| approx_kl | 0.010794342 | +| clip_fraction | 0.303 | +| clip_range | 0.0668 | +| entropy_loss | -5.39 | +| explained_variance | 0.408 | +| learning_rate | 4.22e-05 | +| loss | -0.023 | +| n_updates | 79788 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000305 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1398 | +| iterations | 15994 | +| time_elapsed | 23426 | +| total_timesteps | 32755712 | +| train/ | | +| approx_kl | 0.014668737 | +| clip_fraction | 0.368 | +| clip_range | 0.0668 | +| entropy_loss | -5.5 | +| explained_variance | 0.509 | +| learning_rate | 4.22e-05 | +| loss | -0.0329 | +| n_updates | 79792 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000174 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1398 | +| iterations | 15995 | +| time_elapsed | 23428 | +| total_timesteps | 32757760 | +| train/ | | +| approx_kl | 0.0102296285 | +| clip_fraction | 0.354 | +| clip_range | 0.0668 | +| entropy_loss | -6.62 | +| explained_variance | 0.0897 | +| learning_rate | 4.22e-05 | +| loss | -0.0316 | +| n_updates | 79796 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000175 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1398 | +| iterations | 15996 | +| time_elapsed | 23429 | +| total_timesteps | 32759808 | +| train/ | | +| approx_kl | 0.0105726905 | +| clip_fraction | 0.353 | +| clip_range | 0.0668 | +| entropy_loss | -7.07 | +| explained_variance | -0.148 | +| learning_rate | 4.22e-05 | +| loss | -0.0303 | +| n_updates | 79800 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000141 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1398 | +| iterations | 15997 | +| time_elapsed | 23430 | +| total_timesteps | 32761856 | +| train/ | | +| approx_kl | 0.009988607 | +| clip_fraction | 0.343 | +| clip_range | 0.0668 | +| entropy_loss | -6.81 | +| explained_variance | 0.01 | +| learning_rate | 4.22e-05 | +| loss | -0.0313 | +| n_updates | 79804 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000239 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1398 | +| iterations | 15998 | +| time_elapsed | 23432 | +| total_timesteps | 32763904 | +| train/ | | +| approx_kl | 0.015542014 | +| clip_fraction | 0.353 | +| clip_range | 0.0668 | +| entropy_loss | -6.3 | +| explained_variance | 0.559 | +| learning_rate | 4.22e-05 | +| loss | -0.0329 | +| n_updates | 79808 | +| policy_gradient_loss | -0.0197 | +| value_loss | 9.12e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1398 | +| iterations | 15999 | +| time_elapsed | 23434 | +| total_timesteps | 32765952 | +| train/ | | +| approx_kl | 0.0117278695 | +| clip_fraction | 0.299 | +| clip_range | 0.0668 | +| entropy_loss | -6.25 | +| explained_variance | 0.401 | +| learning_rate | 4.22e-05 | +| loss | -0.029 | +| n_updates | 79812 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000382 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1398 | +| iterations | 16000 | +| time_elapsed | 23435 | +| total_timesteps | 32768000 | +| train/ | | +| approx_kl | 0.012182575 | +| clip_fraction | 0.376 | +| clip_range | 0.0668 | +| entropy_loss | -5.98 | +| explained_variance | 0.505 | +| learning_rate | 4.22e-05 | +| loss | -0.0346 | +| n_updates | 79816 | +| policy_gradient_loss | -0.023 | +| value_loss | 7.92e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1398 | +| iterations | 16001 | +| time_elapsed | 23437 | +| total_timesteps | 32770048 | +| train/ | | +| approx_kl | 0.013465583 | +| clip_fraction | 0.355 | +| clip_range | 0.0668 | +| entropy_loss | -6.44 | +| explained_variance | 0.615 | +| learning_rate | 4.22e-05 | +| loss | -0.0345 | +| n_updates | 79820 | +| policy_gradient_loss | -0.0217 | +| value_loss | 5.58e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1398 | +| iterations | 16002 | +| time_elapsed | 23438 | +| total_timesteps | 32772096 | +| train/ | | +| approx_kl | 0.014121978 | +| clip_fraction | 0.362 | +| clip_range | 0.0668 | +| entropy_loss | -6.41 | +| explained_variance | 0.36 | +| learning_rate | 4.22e-05 | +| loss | -0.0267 | +| n_updates | 79824 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000174 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1398 | +| iterations | 16003 | +| time_elapsed | 23440 | +| total_timesteps | 32774144 | +| train/ | | +| approx_kl | 0.015040793 | +| clip_fraction | 0.306 | +| clip_range | 0.0668 | +| entropy_loss | -6.04 | +| explained_variance | 0.421 | +| learning_rate | 4.22e-05 | +| loss | -0.0253 | +| n_updates | 79828 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000194 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1398 | +| iterations | 16004 | +| time_elapsed | 23441 | +| total_timesteps | 32776192 | +| train/ | | +| approx_kl | 0.010429526 | +| clip_fraction | 0.324 | +| clip_range | 0.0668 | +| entropy_loss | -5.54 | +| explained_variance | 0.517 | +| learning_rate | 4.22e-05 | +| loss | -0.0209 | +| n_updates | 79832 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000219 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1398 | +| iterations | 16005 | +| time_elapsed | 23443 | +| total_timesteps | 32778240 | +| train/ | | +| approx_kl | 0.011495257 | +| clip_fraction | 0.325 | +| clip_range | 0.0668 | +| entropy_loss | -5.48 | +| explained_variance | 0.47 | +| learning_rate | 4.22e-05 | +| loss | -0.0269 | +| n_updates | 79836 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000248 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1398 | +| iterations | 16006 | +| time_elapsed | 23444 | +| total_timesteps | 32780288 | +| train/ | | +| approx_kl | 0.012881523 | +| clip_fraction | 0.348 | +| clip_range | 0.0668 | +| entropy_loss | -5.67 | +| explained_variance | 0.388 | +| learning_rate | 4.22e-05 | +| loss | -0.0312 | +| n_updates | 79840 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000232 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1398 | +| iterations | 16007 | +| time_elapsed | 23446 | +| total_timesteps | 32782336 | +| train/ | | +| approx_kl | 0.015538639 | +| clip_fraction | 0.368 | +| clip_range | 0.0668 | +| entropy_loss | -5.84 | +| explained_variance | 0.455 | +| learning_rate | 4.22e-05 | +| loss | -0.0283 | +| n_updates | 79844 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000174 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1398 | +| iterations | 16008 | +| time_elapsed | 23447 | +| total_timesteps | 32784384 | +| train/ | | +| approx_kl | 0.012496555 | +| clip_fraction | 0.365 | +| clip_range | 0.0668 | +| entropy_loss | -6.68 | +| explained_variance | 0.151 | +| learning_rate | 4.22e-05 | +| loss | -0.0338 | +| n_updates | 79848 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000115 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1398 | +| iterations | 16009 | +| time_elapsed | 23449 | +| total_timesteps | 32786432 | +| train/ | | +| approx_kl | 0.015037691 | +| clip_fraction | 0.359 | +| clip_range | 0.0668 | +| entropy_loss | -6.28 | +| explained_variance | 0.292 | +| learning_rate | 4.22e-05 | +| loss | -0.0251 | +| n_updates | 79852 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000188 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1398 | +| iterations | 16010 | +| time_elapsed | 23450 | +| total_timesteps | 32788480 | +| train/ | | +| approx_kl | 0.014820964 | +| clip_fraction | 0.35 | +| clip_range | 0.0668 | +| entropy_loss | -5.99 | +| explained_variance | 0.624 | +| learning_rate | 4.22e-05 | +| loss | -0.0325 | +| n_updates | 79856 | +| policy_gradient_loss | -0.0215 | +| value_loss | 6.01e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1398 | +| iterations | 16011 | +| time_elapsed | 23452 | +| total_timesteps | 32790528 | +| train/ | | +| approx_kl | 0.009990475 | +| clip_fraction | 0.339 | +| clip_range | 0.0668 | +| entropy_loss | -6.42 | +| explained_variance | 0.213 | +| learning_rate | 4.22e-05 | +| loss | -0.0284 | +| n_updates | 79860 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000146 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1398 | +| iterations | 16012 | +| time_elapsed | 23453 | +| total_timesteps | 32792576 | +| train/ | | +| approx_kl | 0.0122233275 | +| clip_fraction | 0.351 | +| clip_range | 0.0668 | +| entropy_loss | -6.46 | +| explained_variance | 0.581 | +| learning_rate | 4.22e-05 | +| loss | -0.0344 | +| n_updates | 79864 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000105 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1398 | +| iterations | 16013 | +| time_elapsed | 23455 | +| total_timesteps | 32794624 | +| train/ | | +| approx_kl | 0.013259592 | +| clip_fraction | 0.334 | +| clip_range | 0.0668 | +| entropy_loss | -5.49 | +| explained_variance | 0.726 | +| learning_rate | 4.22e-05 | +| loss | -0.0302 | +| n_updates | 79868 | +| policy_gradient_loss | -0.0172 | +| value_loss | 6.77e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1398 | +| iterations | 16014 | +| time_elapsed | 23457 | +| total_timesteps | 32796672 | +| train/ | | +| approx_kl | 0.012857445 | +| clip_fraction | 0.321 | +| clip_range | 0.0668 | +| entropy_loss | -5.43 | +| explained_variance | 0.545 | +| learning_rate | 4.22e-05 | +| loss | -0.0246 | +| n_updates | 79872 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.00012 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1398 | +| iterations | 16015 | +| time_elapsed | 23458 | +| total_timesteps | 32798720 | +| train/ | | +| approx_kl | 0.011438228 | +| clip_fraction | 0.311 | +| clip_range | 0.0668 | +| entropy_loss | -6.11 | +| explained_variance | 0.472 | +| learning_rate | 4.22e-05 | +| loss | -0.0266 | +| n_updates | 79876 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000203 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1398 | +| iterations | 16016 | +| time_elapsed | 23460 | +| total_timesteps | 32800768 | +| train/ | | +| approx_kl | 0.013997927 | +| clip_fraction | 0.332 | +| clip_range | 0.0668 | +| entropy_loss | -6.06 | +| explained_variance | 0.33 | +| learning_rate | 4.22e-05 | +| loss | -0.0294 | +| n_updates | 79880 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000156 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1398 | +| iterations | 16017 | +| time_elapsed | 23461 | +| total_timesteps | 32802816 | +| train/ | | +| approx_kl | 0.012962101 | +| clip_fraction | 0.307 | +| clip_range | 0.0668 | +| entropy_loss | -6.1 | +| explained_variance | 0.617 | +| learning_rate | 4.22e-05 | +| loss | -0.026 | +| n_updates | 79884 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000129 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1398 | +| iterations | 16018 | +| time_elapsed | 23463 | +| total_timesteps | 32804864 | +| train/ | | +| approx_kl | 0.012801367 | +| clip_fraction | 0.354 | +| clip_range | 0.0668 | +| entropy_loss | -5.84 | +| explained_variance | 0.414 | +| learning_rate | 4.22e-05 | +| loss | -0.0271 | +| n_updates | 79888 | +| policy_gradient_loss | -0.0193 | +| value_loss | 9.99e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1398 | +| iterations | 16019 | +| time_elapsed | 23464 | +| total_timesteps | 32806912 | +| train/ | | +| approx_kl | 0.014255211 | +| clip_fraction | 0.349 | +| clip_range | 0.0668 | +| entropy_loss | -5.46 | +| explained_variance | 0.441 | +| learning_rate | 4.22e-05 | +| loss | -0.024 | +| n_updates | 79892 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000308 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1398 | +| iterations | 16020 | +| time_elapsed | 23466 | +| total_timesteps | 32808960 | +| train/ | | +| approx_kl | 0.015933074 | +| clip_fraction | 0.377 | +| clip_range | 0.0668 | +| entropy_loss | -5.79 | +| explained_variance | 0.664 | +| learning_rate | 4.22e-05 | +| loss | -0.0326 | +| n_updates | 79896 | +| policy_gradient_loss | -0.0227 | +| value_loss | 7.3e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1398 | +| iterations | 16021 | +| time_elapsed | 23467 | +| total_timesteps | 32811008 | +| train/ | | +| approx_kl | 0.011141847 | +| clip_fraction | 0.345 | +| clip_range | 0.0668 | +| entropy_loss | -6.35 | +| explained_variance | 0.129 | +| learning_rate | 4.22e-05 | +| loss | -0.0302 | +| n_updates | 79900 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000195 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1398 | +| iterations | 16022 | +| time_elapsed | 23469 | +| total_timesteps | 32813056 | +| train/ | | +| approx_kl | 0.012707524 | +| clip_fraction | 0.336 | +| clip_range | 0.0668 | +| entropy_loss | -6.34 | +| explained_variance | 0.603 | +| learning_rate | 4.22e-05 | +| loss | -0.0291 | +| n_updates | 79904 | +| policy_gradient_loss | -0.0186 | +| value_loss | 8.96e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1398 | +| iterations | 16023 | +| time_elapsed | 23470 | +| total_timesteps | 32815104 | +| train/ | | +| approx_kl | 0.012340274 | +| clip_fraction | 0.337 | +| clip_range | 0.0668 | +| entropy_loss | -6.46 | +| explained_variance | 0.436 | +| learning_rate | 4.22e-05 | +| loss | -0.0272 | +| n_updates | 79908 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000141 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1398 | +| iterations | 16024 | +| time_elapsed | 23472 | +| total_timesteps | 32817152 | +| train/ | | +| approx_kl | 0.008175794 | +| clip_fraction | 0.285 | +| clip_range | 0.0668 | +| entropy_loss | -5.54 | +| explained_variance | 0.564 | +| learning_rate | 4.22e-05 | +| loss | -0.0237 | +| n_updates | 79912 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.00024 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1398 | +| iterations | 16025 | +| time_elapsed | 23473 | +| total_timesteps | 32819200 | +| train/ | | +| approx_kl | 0.010755908 | +| clip_fraction | 0.305 | +| clip_range | 0.0668 | +| entropy_loss | -5.82 | +| explained_variance | 0.473 | +| learning_rate | 4.22e-05 | +| loss | -0.0264 | +| n_updates | 79916 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000199 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1398 | +| iterations | 16026 | +| time_elapsed | 23475 | +| total_timesteps | 32821248 | +| train/ | | +| approx_kl | 0.012759234 | +| clip_fraction | 0.35 | +| clip_range | 0.0668 | +| entropy_loss | -5.97 | +| explained_variance | 0.285 | +| learning_rate | 4.22e-05 | +| loss | -0.0212 | +| n_updates | 79920 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000366 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1398 | +| iterations | 16027 | +| time_elapsed | 23476 | +| total_timesteps | 32823296 | +| train/ | | +| approx_kl | 0.01185149 | +| clip_fraction | 0.297 | +| clip_range | 0.0668 | +| entropy_loss | -6.07 | +| explained_variance | 0.264 | +| learning_rate | 4.22e-05 | +| loss | -0.0228 | +| n_updates | 79924 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000428 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1398 | +| iterations | 16028 | +| time_elapsed | 23478 | +| total_timesteps | 32825344 | +| train/ | | +| approx_kl | 0.009421251 | +| clip_fraction | 0.311 | +| clip_range | 0.0668 | +| entropy_loss | -5.88 | +| explained_variance | 0.392 | +| learning_rate | 4.22e-05 | +| loss | -0.0306 | +| n_updates | 79928 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000184 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1398 | +| iterations | 16029 | +| time_elapsed | 23480 | +| total_timesteps | 32827392 | +| train/ | | +| approx_kl | 0.010305544 | +| clip_fraction | 0.32 | +| clip_range | 0.0668 | +| entropy_loss | -5.72 | +| explained_variance | 0.431 | +| learning_rate | 4.22e-05 | +| loss | -0.0285 | +| n_updates | 79932 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000131 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1398 | +| iterations | 16030 | +| time_elapsed | 23481 | +| total_timesteps | 32829440 | +| train/ | | +| approx_kl | 0.012469176 | +| clip_fraction | 0.311 | +| clip_range | 0.0668 | +| entropy_loss | -6.15 | +| explained_variance | 0.276 | +| learning_rate | 4.22e-05 | +| loss | -0.0263 | +| n_updates | 79936 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000289 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1398 | +| iterations | 16031 | +| time_elapsed | 23483 | +| total_timesteps | 32831488 | +| train/ | | +| approx_kl | 0.01313962 | +| clip_fraction | 0.37 | +| clip_range | 0.0668 | +| entropy_loss | -6.5 | +| explained_variance | 0.22 | +| learning_rate | 4.22e-05 | +| loss | -0.0358 | +| n_updates | 79940 | +| policy_gradient_loss | -0.0231 | +| value_loss | 7.56e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1398 | +| iterations | 16032 | +| time_elapsed | 23484 | +| total_timesteps | 32833536 | +| train/ | | +| approx_kl | 0.013561869 | +| clip_fraction | 0.36 | +| clip_range | 0.0668 | +| entropy_loss | -6.44 | +| explained_variance | 0.131 | +| learning_rate | 4.22e-05 | +| loss | -0.0262 | +| n_updates | 79944 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000349 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1398 | +| iterations | 16033 | +| time_elapsed | 23486 | +| total_timesteps | 32835584 | +| train/ | | +| approx_kl | 0.014055839 | +| clip_fraction | 0.348 | +| clip_range | 0.0668 | +| entropy_loss | -6.26 | +| explained_variance | 0.402 | +| learning_rate | 4.22e-05 | +| loss | -0.0297 | +| n_updates | 79948 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000121 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1398 | +| iterations | 16034 | +| time_elapsed | 23487 | +| total_timesteps | 32837632 | +| train/ | | +| approx_kl | 0.010985563 | +| clip_fraction | 0.342 | +| clip_range | 0.0668 | +| entropy_loss | -6.53 | +| explained_variance | 0.325 | +| learning_rate | 4.22e-05 | +| loss | -0.0331 | +| n_updates | 79952 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000108 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1398 | +| iterations | 16035 | +| time_elapsed | 23489 | +| total_timesteps | 32839680 | +| train/ | | +| approx_kl | 0.013433909 | +| clip_fraction | 0.353 | +| clip_range | 0.0668 | +| entropy_loss | -6.23 | +| explained_variance | 0.353 | +| learning_rate | 4.22e-05 | +| loss | -0.0307 | +| n_updates | 79956 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000264 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1398 | +| iterations | 16036 | +| time_elapsed | 23490 | +| total_timesteps | 32841728 | +| train/ | | +| approx_kl | 0.014180139 | +| clip_fraction | 0.329 | +| clip_range | 0.0668 | +| entropy_loss | -5.18 | +| explained_variance | 0.551 | +| learning_rate | 4.22e-05 | +| loss | -0.0223 | +| n_updates | 79960 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000231 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1398 | +| iterations | 16037 | +| time_elapsed | 23492 | +| total_timesteps | 32843776 | +| train/ | | +| approx_kl | 0.015024246 | +| clip_fraction | 0.36 | +| clip_range | 0.0668 | +| entropy_loss | -5.35 | +| explained_variance | 0.369 | +| learning_rate | 4.22e-05 | +| loss | -0.0266 | +| n_updates | 79964 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000179 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1398 | +| iterations | 16038 | +| time_elapsed | 23493 | +| total_timesteps | 32845824 | +| train/ | | +| approx_kl | 0.014067572 | +| clip_fraction | 0.343 | +| clip_range | 0.0668 | +| entropy_loss | -5.92 | +| explained_variance | 0.338 | +| learning_rate | 4.22e-05 | +| loss | -0.0295 | +| n_updates | 79968 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000283 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1398 | +| iterations | 16039 | +| time_elapsed | 23495 | +| total_timesteps | 32847872 | +| train/ | | +| approx_kl | 0.014316108 | +| clip_fraction | 0.35 | +| clip_range | 0.0668 | +| entropy_loss | -5.67 | +| explained_variance | 0.427 | +| learning_rate | 4.22e-05 | +| loss | -0.0346 | +| n_updates | 79972 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000194 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1398 | +| iterations | 16040 | +| time_elapsed | 23497 | +| total_timesteps | 32849920 | +| train/ | | +| approx_kl | 0.013545236 | +| clip_fraction | 0.376 | +| clip_range | 0.0668 | +| entropy_loss | -6.02 | +| explained_variance | 0.354 | +| learning_rate | 4.22e-05 | +| loss | -0.0307 | +| n_updates | 79976 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000115 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1398 | +| iterations | 16041 | +| time_elapsed | 23498 | +| total_timesteps | 32851968 | +| train/ | | +| approx_kl | 0.00971123 | +| clip_fraction | 0.339 | +| clip_range | 0.0668 | +| entropy_loss | -6.54 | +| explained_variance | 0.111 | +| learning_rate | 4.22e-05 | +| loss | -0.0335 | +| n_updates | 79980 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000179 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1398 | +| iterations | 16042 | +| time_elapsed | 23500 | +| total_timesteps | 32854016 | +| train/ | | +| approx_kl | 0.0117361685 | +| clip_fraction | 0.328 | +| clip_range | 0.0668 | +| entropy_loss | -6.66 | +| explained_variance | 0.258 | +| learning_rate | 4.22e-05 | +| loss | -0.03 | +| n_updates | 79984 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000178 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1398 | +| iterations | 16043 | +| time_elapsed | 23501 | +| total_timesteps | 32856064 | +| train/ | | +| approx_kl | 0.011589732 | +| clip_fraction | 0.33 | +| clip_range | 0.0668 | +| entropy_loss | -6.84 | +| explained_variance | -0.0499 | +| learning_rate | 4.22e-05 | +| loss | -0.0266 | +| n_updates | 79988 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000178 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.387 | +| time/ | | +| fps | 1398 | +| iterations | 16044 | +| time_elapsed | 23503 | +| total_timesteps | 32858112 | +| train/ | | +| approx_kl | 0.01055355 | +| clip_fraction | 0.318 | +| clip_range | 0.0668 | +| entropy_loss | -6.14 | +| explained_variance | 0.501 | +| learning_rate | 4.22e-05 | +| loss | -0.0274 | +| n_updates | 79992 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.00017 | +---------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.384 | +| time/ | | +| fps | 1398 | +| iterations | 16045 | +| time_elapsed | 23504 | +| total_timesteps | 32860160 | +| train/ | | +| approx_kl | 0.0095942 | +| clip_fraction | 0.338 | +| clip_range | 0.0668 | +| entropy_loss | -6 | +| explained_variance | 0.398 | +| learning_rate | 4.22e-05 | +| loss | -0.0261 | +| n_updates | 79996 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.000235 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1398 | +| iterations | 16046 | +| time_elapsed | 23506 | +| total_timesteps | 32862208 | +| train/ | | +| approx_kl | 0.012269084 | +| clip_fraction | 0.319 | +| clip_range | 0.0668 | +| entropy_loss | -5.48 | +| explained_variance | 0.605 | +| learning_rate | 4.22e-05 | +| loss | -0.0259 | +| n_updates | 80000 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000224 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.385 | +| time/ | | +| fps | 1398 | +| iterations | 16047 | +| time_elapsed | 23507 | +| total_timesteps | 32864256 | +| train/ | | +| approx_kl | 0.009883295 | +| clip_fraction | 0.312 | +| clip_range | 0.0668 | +| entropy_loss | -6.23 | +| explained_variance | 0.246 | +| learning_rate | 4.22e-05 | +| loss | -0.0307 | +| n_updates | 80004 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000187 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.385 | +| time/ | | +| fps | 1398 | +| iterations | 16048 | +| time_elapsed | 23509 | +| total_timesteps | 32866304 | +| train/ | | +| approx_kl | 0.010766184 | +| clip_fraction | 0.319 | +| clip_range | 0.0668 | +| entropy_loss | -6.01 | +| explained_variance | 0.433 | +| learning_rate | 4.22e-05 | +| loss | -0.0255 | +| n_updates | 80008 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000244 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.385 | +| time/ | | +| fps | 1398 | +| iterations | 16049 | +| time_elapsed | 23510 | +| total_timesteps | 32868352 | +| train/ | | +| approx_kl | 0.0115249595 | +| clip_fraction | 0.329 | +| clip_range | 0.0668 | +| entropy_loss | -6.01 | +| explained_variance | 0.569 | +| learning_rate | 4.22e-05 | +| loss | -0.0314 | +| n_updates | 80012 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000103 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1398 | +| iterations | 16050 | +| time_elapsed | 23512 | +| total_timesteps | 32870400 | +| train/ | | +| approx_kl | 0.017483072 | +| clip_fraction | 0.37 | +| clip_range | 0.0668 | +| entropy_loss | -6.45 | +| explained_variance | -0.151 | +| learning_rate | 4.22e-05 | +| loss | -0.0337 | +| n_updates | 80016 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000181 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1397 | +| iterations | 16051 | +| time_elapsed | 23513 | +| total_timesteps | 32872448 | +| train/ | | +| approx_kl | 0.017075527 | +| clip_fraction | 0.346 | +| clip_range | 0.0668 | +| entropy_loss | -6.34 | +| explained_variance | 0.561 | +| learning_rate | 4.22e-05 | +| loss | -0.0341 | +| n_updates | 80020 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000125 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1397 | +| iterations | 16052 | +| time_elapsed | 23515 | +| total_timesteps | 32874496 | +| train/ | | +| approx_kl | 0.013555341 | +| clip_fraction | 0.348 | +| clip_range | 0.0668 | +| entropy_loss | -6.22 | +| explained_variance | 0.189 | +| learning_rate | 4.22e-05 | +| loss | -0.0294 | +| n_updates | 80024 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000202 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1397 | +| iterations | 16053 | +| time_elapsed | 23517 | +| total_timesteps | 32876544 | +| train/ | | +| approx_kl | 0.016838165 | +| clip_fraction | 0.364 | +| clip_range | 0.0668 | +| entropy_loss | -6.1 | +| explained_variance | 0.42 | +| learning_rate | 4.22e-05 | +| loss | -0.0305 | +| n_updates | 80028 | +| policy_gradient_loss | -0.0212 | +| value_loss | 8.64e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1397 | +| iterations | 16054 | +| time_elapsed | 23518 | +| total_timesteps | 32878592 | +| train/ | | +| approx_kl | 0.013507668 | +| clip_fraction | 0.321 | +| clip_range | 0.0668 | +| entropy_loss | -5.56 | +| explained_variance | 0.49 | +| learning_rate | 4.22e-05 | +| loss | -0.0223 | +| n_updates | 80032 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000233 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1397 | +| iterations | 16055 | +| time_elapsed | 23520 | +| total_timesteps | 32880640 | +| train/ | | +| approx_kl | 0.012789324 | +| clip_fraction | 0.335 | +| clip_range | 0.0668 | +| entropy_loss | -5.86 | +| explained_variance | 0.406 | +| learning_rate | 4.22e-05 | +| loss | -0.0269 | +| n_updates | 80036 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000202 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1397 | +| iterations | 16056 | +| time_elapsed | 23521 | +| total_timesteps | 32882688 | +| train/ | | +| approx_kl | 0.012685111 | +| clip_fraction | 0.346 | +| clip_range | 0.0668 | +| entropy_loss | -6.56 | +| explained_variance | 0.236 | +| learning_rate | 4.22e-05 | +| loss | -0.027 | +| n_updates | 80040 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000117 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1397 | +| iterations | 16057 | +| time_elapsed | 23523 | +| total_timesteps | 32884736 | +| train/ | | +| approx_kl | 0.014741619 | +| clip_fraction | 0.311 | +| clip_range | 0.0668 | +| entropy_loss | -5.76 | +| explained_variance | 0.509 | +| learning_rate | 4.22e-05 | +| loss | -0.0277 | +| n_updates | 80044 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000226 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1397 | +| iterations | 16058 | +| time_elapsed | 23524 | +| total_timesteps | 32886784 | +| train/ | | +| approx_kl | 0.01267658 | +| clip_fraction | 0.342 | +| clip_range | 0.0668 | +| entropy_loss | -5.71 | +| explained_variance | 0.555 | +| learning_rate | 4.22e-05 | +| loss | -0.03 | +| n_updates | 80048 | +| policy_gradient_loss | -0.0202 | +| value_loss | 9.21e-05 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1397 | +| iterations | 16059 | +| time_elapsed | 23526 | +| total_timesteps | 32888832 | +| train/ | | +| approx_kl | 0.01334518 | +| clip_fraction | 0.32 | +| clip_range | 0.0668 | +| entropy_loss | -6.02 | +| explained_variance | 0.284 | +| learning_rate | 4.22e-05 | +| loss | -0.0207 | +| n_updates | 80052 | +| policy_gradient_loss | -0.0147 | +| value_loss | 0.000331 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1397 | +| iterations | 16060 | +| time_elapsed | 23527 | +| total_timesteps | 32890880 | +| train/ | | +| approx_kl | 0.012101143 | +| clip_fraction | 0.349 | +| clip_range | 0.0668 | +| entropy_loss | -5.98 | +| explained_variance | 0.326 | +| learning_rate | 4.22e-05 | +| loss | -0.0295 | +| n_updates | 80056 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000217 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1397 | +| iterations | 16061 | +| time_elapsed | 23529 | +| total_timesteps | 32892928 | +| train/ | | +| approx_kl | 0.012071218 | +| clip_fraction | 0.356 | +| clip_range | 0.0668 | +| entropy_loss | -6.71 | +| explained_variance | -0.0678 | +| learning_rate | 4.22e-05 | +| loss | -0.0346 | +| n_updates | 80060 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000112 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1397 | +| iterations | 16062 | +| time_elapsed | 23530 | +| total_timesteps | 32894976 | +| train/ | | +| approx_kl | 0.011326926 | +| clip_fraction | 0.339 | +| clip_range | 0.0668 | +| entropy_loss | -6.45 | +| explained_variance | 0.315 | +| learning_rate | 4.22e-05 | +| loss | -0.0324 | +| n_updates | 80064 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000298 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1397 | +| iterations | 16063 | +| time_elapsed | 23532 | +| total_timesteps | 32897024 | +| train/ | | +| approx_kl | 0.011155862 | +| clip_fraction | 0.33 | +| clip_range | 0.0668 | +| entropy_loss | -6.07 | +| explained_variance | 0.297 | +| learning_rate | 4.22e-05 | +| loss | -0.0261 | +| n_updates | 80068 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000152 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1397 | +| iterations | 16064 | +| time_elapsed | 23533 | +| total_timesteps | 32899072 | +| train/ | | +| approx_kl | 0.012778388 | +| clip_fraction | 0.34 | +| clip_range | 0.0668 | +| entropy_loss | -6.59 | +| explained_variance | 0.231 | +| learning_rate | 4.22e-05 | +| loss | -0.0305 | +| n_updates | 80072 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000208 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1397 | +| iterations | 16065 | +| time_elapsed | 23535 | +| total_timesteps | 32901120 | +| train/ | | +| approx_kl | 0.016134588 | +| clip_fraction | 0.325 | +| clip_range | 0.0668 | +| entropy_loss | -5.53 | +| explained_variance | 0.591 | +| learning_rate | 4.22e-05 | +| loss | -0.0333 | +| n_updates | 80076 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000151 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1397 | +| iterations | 16066 | +| time_elapsed | 23536 | +| total_timesteps | 32903168 | +| train/ | | +| approx_kl | 0.011783641 | +| clip_fraction | 0.319 | +| clip_range | 0.0668 | +| entropy_loss | -5.86 | +| explained_variance | 0.509 | +| learning_rate | 4.22e-05 | +| loss | -0.0265 | +| n_updates | 80080 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000146 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1397 | +| iterations | 16067 | +| time_elapsed | 23538 | +| total_timesteps | 32905216 | +| train/ | | +| approx_kl | 0.016130002 | +| clip_fraction | 0.362 | +| clip_range | 0.0668 | +| entropy_loss | -6.21 | +| explained_variance | 0.277 | +| learning_rate | 4.22e-05 | +| loss | -0.0314 | +| n_updates | 80084 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000136 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1397 | +| iterations | 16068 | +| time_elapsed | 23540 | +| total_timesteps | 32907264 | +| train/ | | +| approx_kl | 0.01613014 | +| clip_fraction | 0.336 | +| clip_range | 0.0668 | +| entropy_loss | -6.39 | +| explained_variance | -0.259 | +| learning_rate | 4.22e-05 | +| loss | -0.0393 | +| n_updates | 80088 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000108 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1397 | +| iterations | 16069 | +| time_elapsed | 23541 | +| total_timesteps | 32909312 | +| train/ | | +| approx_kl | 0.014723539 | +| clip_fraction | 0.348 | +| clip_range | 0.0668 | +| entropy_loss | -6.37 | +| explained_variance | 0.473 | +| learning_rate | 4.22e-05 | +| loss | -0.0313 | +| n_updates | 80092 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000106 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1397 | +| iterations | 16070 | +| time_elapsed | 23543 | +| total_timesteps | 32911360 | +| train/ | | +| approx_kl | 0.013856333 | +| clip_fraction | 0.31 | +| clip_range | 0.0668 | +| entropy_loss | -5.64 | +| explained_variance | 0.509 | +| learning_rate | 4.22e-05 | +| loss | -0.0262 | +| n_updates | 80096 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000232 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1397 | +| iterations | 16071 | +| time_elapsed | 23544 | +| total_timesteps | 32913408 | +| train/ | | +| approx_kl | 0.01123813 | +| clip_fraction | 0.293 | +| clip_range | 0.0668 | +| entropy_loss | -5.9 | +| explained_variance | 0.216 | +| learning_rate | 4.22e-05 | +| loss | -0.0235 | +| n_updates | 80100 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.000426 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1397 | +| iterations | 16072 | +| time_elapsed | 23546 | +| total_timesteps | 32915456 | +| train/ | | +| approx_kl | 0.01456305 | +| clip_fraction | 0.368 | +| clip_range | 0.0668 | +| entropy_loss | -5.68 | +| explained_variance | 0.573 | +| learning_rate | 4.22e-05 | +| loss | -0.0318 | +| n_updates | 80104 | +| policy_gradient_loss | -0.0214 | +| value_loss | 9.79e-05 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1397 | +| iterations | 16073 | +| time_elapsed | 23547 | +| total_timesteps | 32917504 | +| train/ | | +| approx_kl | 0.01717095 | +| clip_fraction | 0.376 | +| clip_range | 0.0668 | +| entropy_loss | -5.63 | +| explained_variance | 0.403 | +| learning_rate | 4.22e-05 | +| loss | -0.0306 | +| n_updates | 80108 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000119 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1397 | +| iterations | 16074 | +| time_elapsed | 23549 | +| total_timesteps | 32919552 | +| train/ | | +| approx_kl | 0.013204943 | +| clip_fraction | 0.37 | +| clip_range | 0.0668 | +| entropy_loss | -6.59 | +| explained_variance | -0.0849 | +| learning_rate | 4.22e-05 | +| loss | -0.0308 | +| n_updates | 80112 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000163 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1397 | +| iterations | 16075 | +| time_elapsed | 23550 | +| total_timesteps | 32921600 | +| train/ | | +| approx_kl | 0.012522014 | +| clip_fraction | 0.323 | +| clip_range | 0.0668 | +| entropy_loss | -5.9 | +| explained_variance | 0.576 | +| learning_rate | 4.22e-05 | +| loss | -0.0292 | +| n_updates | 80116 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000206 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.386 | +| time/ | | +| fps | 1397 | +| iterations | 16076 | +| time_elapsed | 23552 | +| total_timesteps | 32923648 | +| train/ | | +| approx_kl | 0.015161652 | +| clip_fraction | 0.3 | +| clip_range | 0.0668 | +| entropy_loss | -5.43 | +| explained_variance | 0.435 | +| learning_rate | 4.22e-05 | +| loss | -0.0226 | +| n_updates | 80120 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000247 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.386 | +| time/ | | +| fps | 1397 | +| iterations | 16077 | +| time_elapsed | 23553 | +| total_timesteps | 32925696 | +| train/ | | +| approx_kl | 0.010442244 | +| clip_fraction | 0.325 | +| clip_range | 0.0668 | +| entropy_loss | -6.16 | +| explained_variance | 0.424 | +| learning_rate | 4.22e-05 | +| loss | -0.0278 | +| n_updates | 80124 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000185 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.387 | +| time/ | | +| fps | 1397 | +| iterations | 16078 | +| time_elapsed | 23555 | +| total_timesteps | 32927744 | +| train/ | | +| approx_kl | 0.014936932 | +| clip_fraction | 0.339 | +| clip_range | 0.0668 | +| entropy_loss | -6.12 | +| explained_variance | 0.318 | +| learning_rate | 4.22e-05 | +| loss | -0.0324 | +| n_updates | 80128 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000139 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.388 | +| time/ | | +| fps | 1397 | +| iterations | 16079 | +| time_elapsed | 23556 | +| total_timesteps | 32929792 | +| train/ | | +| approx_kl | 0.014411417 | +| clip_fraction | 0.379 | +| clip_range | 0.0668 | +| entropy_loss | -6.39 | +| explained_variance | -0.172 | +| learning_rate | 4.22e-05 | +| loss | -0.0328 | +| n_updates | 80132 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.00012 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1397 | +| iterations | 16080 | +| time_elapsed | 23558 | +| total_timesteps | 32931840 | +| train/ | | +| approx_kl | 0.014938953 | +| clip_fraction | 0.341 | +| clip_range | 0.0668 | +| entropy_loss | -6.24 | +| explained_variance | 0.326 | +| learning_rate | 4.22e-05 | +| loss | -0.0308 | +| n_updates | 80136 | +| policy_gradient_loss | -0.0191 | +| value_loss | 9.64e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1397 | +| iterations | 16081 | +| time_elapsed | 23559 | +| total_timesteps | 32933888 | +| train/ | | +| approx_kl | 0.012906897 | +| clip_fraction | 0.321 | +| clip_range | 0.0668 | +| entropy_loss | -6.44 | +| explained_variance | 0.525 | +| learning_rate | 4.22e-05 | +| loss | -0.0287 | +| n_updates | 80140 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000122 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.384 | +| time/ | | +| fps | 1397 | +| iterations | 16082 | +| time_elapsed | 23561 | +| total_timesteps | 32935936 | +| train/ | | +| approx_kl | 0.020167062 | +| clip_fraction | 0.328 | +| clip_range | 0.0668 | +| entropy_loss | -6.17 | +| explained_variance | -0.147 | +| learning_rate | 4.22e-05 | +| loss | -0.0225 | +| n_updates | 80144 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000147 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.384 | +| time/ | | +| fps | 1397 | +| iterations | 16083 | +| time_elapsed | 23562 | +| total_timesteps | 32937984 | +| train/ | | +| approx_kl | 0.0137212 | +| clip_fraction | 0.31 | +| clip_range | 0.0668 | +| entropy_loss | -5.87 | +| explained_variance | 0.547 | +| learning_rate | 4.22e-05 | +| loss | -0.0265 | +| n_updates | 80148 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000229 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1397 | +| iterations | 16084 | +| time_elapsed | 23564 | +| total_timesteps | 32940032 | +| train/ | | +| approx_kl | 0.012442453 | +| clip_fraction | 0.327 | +| clip_range | 0.0668 | +| entropy_loss | -5.65 | +| explained_variance | 0.0787 | +| learning_rate | 4.22e-05 | +| loss | -0.0365 | +| n_updates | 80152 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000139 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.388 | +| time/ | | +| fps | 1397 | +| iterations | 16085 | +| time_elapsed | 23566 | +| total_timesteps | 32942080 | +| train/ | | +| approx_kl | 0.009567775 | +| clip_fraction | 0.321 | +| clip_range | 0.0668 | +| entropy_loss | -5.93 | +| explained_variance | 0.462 | +| learning_rate | 4.22e-05 | +| loss | -0.0258 | +| n_updates | 80156 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000183 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.386 | +| time/ | | +| fps | 1397 | +| iterations | 16086 | +| time_elapsed | 23567 | +| total_timesteps | 32944128 | +| train/ | | +| approx_kl | 0.0138261765 | +| clip_fraction | 0.313 | +| clip_range | 0.0668 | +| entropy_loss | -6.33 | +| explained_variance | -0.0456 | +| learning_rate | 4.22e-05 | +| loss | -0.025 | +| n_updates | 80160 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000316 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.387 | +| time/ | | +| fps | 1397 | +| iterations | 16087 | +| time_elapsed | 23569 | +| total_timesteps | 32946176 | +| train/ | | +| approx_kl | 0.011659922 | +| clip_fraction | 0.359 | +| clip_range | 0.0668 | +| entropy_loss | -6.27 | +| explained_variance | 0.237 | +| learning_rate | 4.22e-05 | +| loss | -0.0283 | +| n_updates | 80164 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000269 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1397 | +| iterations | 16088 | +| time_elapsed | 23570 | +| total_timesteps | 32948224 | +| train/ | | +| approx_kl | 0.013482656 | +| clip_fraction | 0.363 | +| clip_range | 0.0668 | +| entropy_loss | -5.92 | +| explained_variance | 0.403 | +| learning_rate | 4.22e-05 | +| loss | -0.0361 | +| n_updates | 80168 | +| policy_gradient_loss | -0.0206 | +| value_loss | 9.59e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.386 | +| time/ | | +| fps | 1397 | +| iterations | 16089 | +| time_elapsed | 23572 | +| total_timesteps | 32950272 | +| train/ | | +| approx_kl | 0.014555468 | +| clip_fraction | 0.351 | +| clip_range | 0.0668 | +| entropy_loss | -5.81 | +| explained_variance | 0.457 | +| learning_rate | 4.22e-05 | +| loss | -0.0237 | +| n_updates | 80172 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.00024 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.393 | +| time/ | | +| fps | 1397 | +| iterations | 16090 | +| time_elapsed | 23573 | +| total_timesteps | 32952320 | +| train/ | | +| approx_kl | 0.013995176 | +| clip_fraction | 0.327 | +| clip_range | 0.0668 | +| entropy_loss | -5.88 | +| explained_variance | 0.49 | +| learning_rate | 4.22e-05 | +| loss | -0.0317 | +| n_updates | 80176 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000214 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.393 | +| time/ | | +| fps | 1397 | +| iterations | 16091 | +| time_elapsed | 23575 | +| total_timesteps | 32954368 | +| train/ | | +| approx_kl | 0.011895999 | +| clip_fraction | 0.348 | +| clip_range | 0.0668 | +| entropy_loss | -6.57 | +| explained_variance | 0.157 | +| learning_rate | 4.22e-05 | +| loss | -0.0276 | +| n_updates | 80180 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000235 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.392 | +| time/ | | +| fps | 1397 | +| iterations | 16092 | +| time_elapsed | 23576 | +| total_timesteps | 32956416 | +| train/ | | +| approx_kl | 0.008964226 | +| clip_fraction | 0.284 | +| clip_range | 0.0668 | +| entropy_loss | -6.61 | +| explained_variance | -0.125 | +| learning_rate | 4.22e-05 | +| loss | -0.0253 | +| n_updates | 80184 | +| policy_gradient_loss | -0.0141 | +| value_loss | 0.000265 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.387 | +| time/ | | +| fps | 1397 | +| iterations | 16093 | +| time_elapsed | 23578 | +| total_timesteps | 32958464 | +| train/ | | +| approx_kl | 0.012101206 | +| clip_fraction | 0.324 | +| clip_range | 0.0668 | +| entropy_loss | -6.75 | +| explained_variance | 0.15 | +| learning_rate | 4.22e-05 | +| loss | -0.0281 | +| n_updates | 80188 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.00022 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.384 | +| time/ | | +| fps | 1397 | +| iterations | 16094 | +| time_elapsed | 23579 | +| total_timesteps | 32960512 | +| train/ | | +| approx_kl | 0.012293446 | +| clip_fraction | 0.324 | +| clip_range | 0.0668 | +| entropy_loss | -6.48 | +| explained_variance | 0.285 | +| learning_rate | 4.22e-05 | +| loss | -0.0361 | +| n_updates | 80192 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000109 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1397 | +| iterations | 16095 | +| time_elapsed | 23581 | +| total_timesteps | 32962560 | +| train/ | | +| approx_kl | 0.012447132 | +| clip_fraction | 0.342 | +| clip_range | 0.0668 | +| entropy_loss | -6.26 | +| explained_variance | 0.565 | +| learning_rate | 4.22e-05 | +| loss | -0.0304 | +| n_updates | 80196 | +| policy_gradient_loss | -0.0199 | +| value_loss | 9.53e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1397 | +| iterations | 16096 | +| time_elapsed | 23582 | +| total_timesteps | 32964608 | +| train/ | | +| approx_kl | 0.009923381 | +| clip_fraction | 0.325 | +| clip_range | 0.0668 | +| entropy_loss | -6.33 | +| explained_variance | 0.521 | +| learning_rate | 4.22e-05 | +| loss | -0.0296 | +| n_updates | 80200 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000103 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1397 | +| iterations | 16097 | +| time_elapsed | 23584 | +| total_timesteps | 32966656 | +| train/ | | +| approx_kl | 0.010953398 | +| clip_fraction | 0.332 | +| clip_range | 0.0668 | +| entropy_loss | -5.91 | +| explained_variance | 0.724 | +| learning_rate | 4.22e-05 | +| loss | -0.0286 | +| n_updates | 80204 | +| policy_gradient_loss | -0.0184 | +| value_loss | 8.41e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1397 | +| iterations | 16098 | +| time_elapsed | 23585 | +| total_timesteps | 32968704 | +| train/ | | +| approx_kl | 0.011958168 | +| clip_fraction | 0.3 | +| clip_range | 0.0668 | +| entropy_loss | -6.32 | +| explained_variance | 0.458 | +| learning_rate | 4.22e-05 | +| loss | -0.0243 | +| n_updates | 80208 | +| policy_gradient_loss | -0.0161 | +| value_loss | 9.86e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1397 | +| iterations | 16099 | +| time_elapsed | 23587 | +| total_timesteps | 32970752 | +| train/ | | +| approx_kl | 0.01101773 | +| clip_fraction | 0.302 | +| clip_range | 0.0668 | +| entropy_loss | -6.41 | +| explained_variance | 0.274 | +| learning_rate | 4.22e-05 | +| loss | -0.0207 | +| n_updates | 80212 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.000245 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1397 | +| iterations | 16100 | +| time_elapsed | 23588 | +| total_timesteps | 32972800 | +| train/ | | +| approx_kl | 0.012123114 | +| clip_fraction | 0.313 | +| clip_range | 0.0668 | +| entropy_loss | -5.61 | +| explained_variance | 0.574 | +| learning_rate | 4.22e-05 | +| loss | -0.0256 | +| n_updates | 80216 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000147 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1397 | +| iterations | 16101 | +| time_elapsed | 23590 | +| total_timesteps | 32974848 | +| train/ | | +| approx_kl | 0.010513094 | +| clip_fraction | 0.326 | +| clip_range | 0.0668 | +| entropy_loss | -6.19 | +| explained_variance | 0.295 | +| learning_rate | 4.22e-05 | +| loss | -0.0281 | +| n_updates | 80220 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000177 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1397 | +| iterations | 16102 | +| time_elapsed | 23591 | +| total_timesteps | 32976896 | +| train/ | | +| approx_kl | 0.011788148 | +| clip_fraction | 0.302 | +| clip_range | 0.0668 | +| entropy_loss | -6.77 | +| explained_variance | 0.279 | +| learning_rate | 4.22e-05 | +| loss | -0.022 | +| n_updates | 80224 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000298 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1397 | +| iterations | 16103 | +| time_elapsed | 23593 | +| total_timesteps | 32978944 | +| train/ | | +| approx_kl | 0.013674127 | +| clip_fraction | 0.344 | +| clip_range | 0.0668 | +| entropy_loss | -6.48 | +| explained_variance | 0.356 | +| learning_rate | 4.22e-05 | +| loss | -0.0334 | +| n_updates | 80228 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000113 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1397 | +| iterations | 16104 | +| time_elapsed | 23595 | +| total_timesteps | 32980992 | +| train/ | | +| approx_kl | 0.012127668 | +| clip_fraction | 0.371 | +| clip_range | 0.0668 | +| entropy_loss | -6.5 | +| explained_variance | 0.449 | +| learning_rate | 4.22e-05 | +| loss | -0.0341 | +| n_updates | 80232 | +| policy_gradient_loss | -0.0214 | +| value_loss | 6.57e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1397 | +| iterations | 16105 | +| time_elapsed | 23596 | +| total_timesteps | 32983040 | +| train/ | | +| approx_kl | 0.009418989 | +| clip_fraction | 0.307 | +| clip_range | 0.0668 | +| entropy_loss | -6.08 | +| explained_variance | 0.52 | +| learning_rate | 4.22e-05 | +| loss | -0.0302 | +| n_updates | 80236 | +| policy_gradient_loss | -0.0134 | +| value_loss | 0.00026 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1397 | +| iterations | 16106 | +| time_elapsed | 23598 | +| total_timesteps | 32985088 | +| train/ | | +| approx_kl | 0.0103885075 | +| clip_fraction | 0.318 | +| clip_range | 0.0668 | +| entropy_loss | -5.87 | +| explained_variance | 0.432 | +| learning_rate | 4.22e-05 | +| loss | -0.0299 | +| n_updates | 80240 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000203 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1397 | +| iterations | 16107 | +| time_elapsed | 23599 | +| total_timesteps | 32987136 | +| train/ | | +| approx_kl | 0.011218232 | +| clip_fraction | 0.315 | +| clip_range | 0.0668 | +| entropy_loss | -6.12 | +| explained_variance | 0.522 | +| learning_rate | 4.22e-05 | +| loss | -0.0337 | +| n_updates | 80244 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000145 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1397 | +| iterations | 16108 | +| time_elapsed | 23601 | +| total_timesteps | 32989184 | +| train/ | | +| approx_kl | 0.0119261425 | +| clip_fraction | 0.33 | +| clip_range | 0.0668 | +| entropy_loss | -5.59 | +| explained_variance | 0.759 | +| learning_rate | 4.22e-05 | +| loss | -0.0244 | +| n_updates | 80248 | +| policy_gradient_loss | -0.0186 | +| value_loss | 9.42e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1397 | +| iterations | 16109 | +| time_elapsed | 23602 | +| total_timesteps | 32991232 | +| train/ | | +| approx_kl | 0.010789314 | +| clip_fraction | 0.337 | +| clip_range | 0.0668 | +| entropy_loss | -6.44 | +| explained_variance | 0.193 | +| learning_rate | 4.22e-05 | +| loss | -0.0284 | +| n_updates | 80252 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000137 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1397 | +| iterations | 16110 | +| time_elapsed | 23604 | +| total_timesteps | 32993280 | +| train/ | | +| approx_kl | 0.0090366 | +| clip_fraction | 0.303 | +| clip_range | 0.0668 | +| entropy_loss | -6.42 | +| explained_variance | 0.397 | +| learning_rate | 4.22e-05 | +| loss | -0.0292 | +| n_updates | 80256 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000273 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1397 | +| iterations | 16111 | +| time_elapsed | 23605 | +| total_timesteps | 32995328 | +| train/ | | +| approx_kl | 0.011833357 | +| clip_fraction | 0.349 | +| clip_range | 0.0668 | +| entropy_loss | -6.74 | +| explained_variance | -0.15 | +| learning_rate | 4.22e-05 | +| loss | -0.0369 | +| n_updates | 80260 | +| policy_gradient_loss | -0.0203 | +| value_loss | 9.07e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1397 | +| iterations | 16112 | +| time_elapsed | 23607 | +| total_timesteps | 32997376 | +| train/ | | +| approx_kl | 0.01278417 | +| clip_fraction | 0.356 | +| clip_range | 0.0668 | +| entropy_loss | -6.69 | +| explained_variance | 0.599 | +| learning_rate | 4.22e-05 | +| loss | -0.0368 | +| n_updates | 80264 | +| policy_gradient_loss | -0.0211 | +| value_loss | 6.63e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1397 | +| iterations | 16113 | +| time_elapsed | 23608 | +| total_timesteps | 32999424 | +| train/ | | +| approx_kl | 0.012416646 | +| clip_fraction | 0.336 | +| clip_range | 0.0668 | +| entropy_loss | -6.12 | +| explained_variance | 0.525 | +| learning_rate | 4.22e-05 | +| loss | -0.0277 | +| n_updates | 80268 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.00012 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1397 | +| iterations | 16114 | +| time_elapsed | 23610 | +| total_timesteps | 33001472 | +| train/ | | +| approx_kl | 0.011455294 | +| clip_fraction | 0.326 | +| clip_range | 0.0668 | +| entropy_loss | -6.01 | +| explained_variance | 0.541 | +| learning_rate | 4.22e-05 | +| loss | -0.0266 | +| n_updates | 80272 | +| policy_gradient_loss | -0.0184 | +| value_loss | 7.82e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1397 | +| iterations | 16115 | +| time_elapsed | 23611 | +| total_timesteps | 33003520 | +| train/ | | +| approx_kl | 0.011253204 | +| clip_fraction | 0.298 | +| clip_range | 0.0667 | +| entropy_loss | -6.13 | +| explained_variance | 0.435 | +| learning_rate | 4.22e-05 | +| loss | -0.0196 | +| n_updates | 80276 | +| policy_gradient_loss | -0.0129 | +| value_loss | 0.000206 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1397 | +| iterations | 16116 | +| time_elapsed | 23613 | +| total_timesteps | 33005568 | +| train/ | | +| approx_kl | 0.011954969 | +| clip_fraction | 0.317 | +| clip_range | 0.0667 | +| entropy_loss | -6.07 | +| explained_variance | 0.445 | +| learning_rate | 4.22e-05 | +| loss | -0.0275 | +| n_updates | 80280 | +| policy_gradient_loss | -0.0176 | +| value_loss | 9.86e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1397 | +| iterations | 16117 | +| time_elapsed | 23614 | +| total_timesteps | 33007616 | +| train/ | | +| approx_kl | 0.009894289 | +| clip_fraction | 0.288 | +| clip_range | 0.0667 | +| entropy_loss | -6.01 | +| explained_variance | 0.449 | +| learning_rate | 4.22e-05 | +| loss | -0.0261 | +| n_updates | 80284 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000271 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1397 | +| iterations | 16118 | +| time_elapsed | 23616 | +| total_timesteps | 33009664 | +| train/ | | +| approx_kl | 0.008953732 | +| clip_fraction | 0.289 | +| clip_range | 0.0667 | +| entropy_loss | -5.4 | +| explained_variance | 0.547 | +| learning_rate | 4.22e-05 | +| loss | -0.0211 | +| n_updates | 80288 | +| policy_gradient_loss | -0.0146 | +| value_loss | 0.00026 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1397 | +| iterations | 16119 | +| time_elapsed | 23618 | +| total_timesteps | 33011712 | +| train/ | | +| approx_kl | 0.01582626 | +| clip_fraction | 0.361 | +| clip_range | 0.0667 | +| entropy_loss | -6.1 | +| explained_variance | 0.341 | +| learning_rate | 4.22e-05 | +| loss | -0.0399 | +| n_updates | 80292 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.00014 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1397 | +| iterations | 16120 | +| time_elapsed | 23619 | +| total_timesteps | 33013760 | +| train/ | | +| approx_kl | 0.020504113 | +| clip_fraction | 0.349 | +| clip_range | 0.0667 | +| entropy_loss | -6.1 | +| explained_variance | 0.407 | +| learning_rate | 4.22e-05 | +| loss | -0.0278 | +| n_updates | 80296 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.00022 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1397 | +| iterations | 16121 | +| time_elapsed | 23621 | +| total_timesteps | 33015808 | +| train/ | | +| approx_kl | 0.013380939 | +| clip_fraction | 0.335 | +| clip_range | 0.0667 | +| entropy_loss | -6.15 | +| explained_variance | 0.299 | +| learning_rate | 4.22e-05 | +| loss | -0.0348 | +| n_updates | 80300 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000187 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1397 | +| iterations | 16122 | +| time_elapsed | 23622 | +| total_timesteps | 33017856 | +| train/ | | +| approx_kl | 0.011623422 | +| clip_fraction | 0.306 | +| clip_range | 0.0667 | +| entropy_loss | -6.57 | +| explained_variance | 0.129 | +| learning_rate | 4.22e-05 | +| loss | -0.0242 | +| n_updates | 80304 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000329 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1397 | +| iterations | 16123 | +| time_elapsed | 23624 | +| total_timesteps | 33019904 | +| train/ | | +| approx_kl | 0.013368025 | +| clip_fraction | 0.343 | +| clip_range | 0.0667 | +| entropy_loss | -5.87 | +| explained_variance | 0.41 | +| learning_rate | 4.22e-05 | +| loss | -0.0274 | +| n_updates | 80308 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000302 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1397 | +| iterations | 16124 | +| time_elapsed | 23625 | +| total_timesteps | 33021952 | +| train/ | | +| approx_kl | 0.014121491 | +| clip_fraction | 0.333 | +| clip_range | 0.0667 | +| entropy_loss | -5.76 | +| explained_variance | 0.262 | +| learning_rate | 4.22e-05 | +| loss | -0.0295 | +| n_updates | 80312 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000203 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1397 | +| iterations | 16125 | +| time_elapsed | 23627 | +| total_timesteps | 33024000 | +| train/ | | +| approx_kl | 0.012208665 | +| clip_fraction | 0.339 | +| clip_range | 0.0667 | +| entropy_loss | -6.43 | +| explained_variance | 0.214 | +| learning_rate | 4.22e-05 | +| loss | -0.0239 | +| n_updates | 80316 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000207 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1397 | +| iterations | 16126 | +| time_elapsed | 23628 | +| total_timesteps | 33026048 | +| train/ | | +| approx_kl | 0.013352233 | +| clip_fraction | 0.358 | +| clip_range | 0.0667 | +| entropy_loss | -6.54 | +| explained_variance | 0.0768 | +| learning_rate | 4.22e-05 | +| loss | -0.0322 | +| n_updates | 80320 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000139 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1397 | +| iterations | 16127 | +| time_elapsed | 23630 | +| total_timesteps | 33028096 | +| train/ | | +| approx_kl | 0.014682792 | +| clip_fraction | 0.318 | +| clip_range | 0.0667 | +| entropy_loss | -6.42 | +| explained_variance | 0.452 | +| learning_rate | 4.22e-05 | +| loss | -0.0288 | +| n_updates | 80324 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000132 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1397 | +| iterations | 16128 | +| time_elapsed | 23632 | +| total_timesteps | 33030144 | +| train/ | | +| approx_kl | 0.013226204 | +| clip_fraction | 0.359 | +| clip_range | 0.0667 | +| entropy_loss | -6.39 | +| explained_variance | 0.44 | +| learning_rate | 4.22e-05 | +| loss | -0.0329 | +| n_updates | 80328 | +| policy_gradient_loss | -0.0198 | +| value_loss | 8.42e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1397 | +| iterations | 16129 | +| time_elapsed | 23633 | +| total_timesteps | 33032192 | +| train/ | | +| approx_kl | 0.012008494 | +| clip_fraction | 0.312 | +| clip_range | 0.0667 | +| entropy_loss | -6.09 | +| explained_variance | 0.531 | +| learning_rate | 4.22e-05 | +| loss | -0.0285 | +| n_updates | 80332 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000144 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1397 | +| iterations | 16130 | +| time_elapsed | 23635 | +| total_timesteps | 33034240 | +| train/ | | +| approx_kl | 0.01090835 | +| clip_fraction | 0.33 | +| clip_range | 0.0667 | +| entropy_loss | -6.5 | +| explained_variance | -0.00382 | +| learning_rate | 4.22e-05 | +| loss | -0.0239 | +| n_updates | 80336 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000195 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1397 | +| iterations | 16131 | +| time_elapsed | 23636 | +| total_timesteps | 33036288 | +| train/ | | +| approx_kl | 0.011878459 | +| clip_fraction | 0.318 | +| clip_range | 0.0667 | +| entropy_loss | -6 | +| explained_variance | 0.592 | +| learning_rate | 4.22e-05 | +| loss | -0.0293 | +| n_updates | 80340 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000139 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1397 | +| iterations | 16132 | +| time_elapsed | 23638 | +| total_timesteps | 33038336 | +| train/ | | +| approx_kl | 0.01134265 | +| clip_fraction | 0.314 | +| clip_range | 0.0667 | +| entropy_loss | -6.18 | +| explained_variance | 0.413 | +| learning_rate | 4.22e-05 | +| loss | -0.0259 | +| n_updates | 80344 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000236 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1397 | +| iterations | 16133 | +| time_elapsed | 23639 | +| total_timesteps | 33040384 | +| train/ | | +| approx_kl | 0.012356286 | +| clip_fraction | 0.333 | +| clip_range | 0.0667 | +| entropy_loss | -5.92 | +| explained_variance | 0.689 | +| learning_rate | 4.22e-05 | +| loss | -0.0347 | +| n_updates | 80348 | +| policy_gradient_loss | -0.0202 | +| value_loss | 6.67e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1397 | +| iterations | 16134 | +| time_elapsed | 23641 | +| total_timesteps | 33042432 | +| train/ | | +| approx_kl | 0.010679675 | +| clip_fraction | 0.312 | +| clip_range | 0.0667 | +| entropy_loss | -6.7 | +| explained_variance | 0.202 | +| learning_rate | 4.22e-05 | +| loss | -0.0259 | +| n_updates | 80352 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.00027 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1397 | +| iterations | 16135 | +| time_elapsed | 23642 | +| total_timesteps | 33044480 | +| train/ | | +| approx_kl | 0.0114795305 | +| clip_fraction | 0.358 | +| clip_range | 0.0667 | +| entropy_loss | -6.51 | +| explained_variance | 0.443 | +| learning_rate | 4.22e-05 | +| loss | -0.0298 | +| n_updates | 80356 | +| policy_gradient_loss | -0.0211 | +| value_loss | 8.89e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1397 | +| iterations | 16136 | +| time_elapsed | 23644 | +| total_timesteps | 33046528 | +| train/ | | +| approx_kl | 0.015356032 | +| clip_fraction | 0.37 | +| clip_range | 0.0667 | +| entropy_loss | -6.01 | +| explained_variance | 0.62 | +| learning_rate | 4.22e-05 | +| loss | -0.0343 | +| n_updates | 80360 | +| policy_gradient_loss | -0.0222 | +| value_loss | 7.21e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1397 | +| iterations | 16137 | +| time_elapsed | 23645 | +| total_timesteps | 33048576 | +| train/ | | +| approx_kl | 0.014983479 | +| clip_fraction | 0.35 | +| clip_range | 0.0667 | +| entropy_loss | -6.2 | +| explained_variance | 0.349 | +| learning_rate | 4.22e-05 | +| loss | -0.0313 | +| n_updates | 80364 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000192 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1397 | +| iterations | 16138 | +| time_elapsed | 23647 | +| total_timesteps | 33050624 | +| train/ | | +| approx_kl | 0.016700886 | +| clip_fraction | 0.34 | +| clip_range | 0.0667 | +| entropy_loss | -5.5 | +| explained_variance | 0.761 | +| learning_rate | 4.22e-05 | +| loss | -0.0302 | +| n_updates | 80368 | +| policy_gradient_loss | -0.0192 | +| value_loss | 8.92e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1397 | +| iterations | 16139 | +| time_elapsed | 23648 | +| total_timesteps | 33052672 | +| train/ | | +| approx_kl | 0.013097085 | +| clip_fraction | 0.315 | +| clip_range | 0.0667 | +| entropy_loss | -5.34 | +| explained_variance | 0.555 | +| learning_rate | 4.22e-05 | +| loss | -0.0329 | +| n_updates | 80372 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000112 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1397 | +| iterations | 16140 | +| time_elapsed | 23650 | +| total_timesteps | 33054720 | +| train/ | | +| approx_kl | 0.010633046 | +| clip_fraction | 0.33 | +| clip_range | 0.0667 | +| entropy_loss | -6.19 | +| explained_variance | 0.367 | +| learning_rate | 4.21e-05 | +| loss | -0.031 | +| n_updates | 80376 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000154 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1397 | +| iterations | 16141 | +| time_elapsed | 23651 | +| total_timesteps | 33056768 | +| train/ | | +| approx_kl | 0.014134007 | +| clip_fraction | 0.316 | +| clip_range | 0.0667 | +| entropy_loss | -6.11 | +| explained_variance | 0.296 | +| learning_rate | 4.21e-05 | +| loss | -0.0241 | +| n_updates | 80380 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000319 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1397 | +| iterations | 16142 | +| time_elapsed | 23653 | +| total_timesteps | 33058816 | +| train/ | | +| approx_kl | 0.008123498 | +| clip_fraction | 0.292 | +| clip_range | 0.0667 | +| entropy_loss | -5.83 | +| explained_variance | 0.656 | +| learning_rate | 4.21e-05 | +| loss | -0.0256 | +| n_updates | 80384 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000125 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1397 | +| iterations | 16143 | +| time_elapsed | 23654 | +| total_timesteps | 33060864 | +| train/ | | +| approx_kl | 0.01059747 | +| clip_fraction | 0.305 | +| clip_range | 0.0667 | +| entropy_loss | -6.5 | +| explained_variance | 0.247 | +| learning_rate | 4.21e-05 | +| loss | -0.0286 | +| n_updates | 80388 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000197 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1397 | +| iterations | 16144 | +| time_elapsed | 23656 | +| total_timesteps | 33062912 | +| train/ | | +| approx_kl | 0.010603882 | +| clip_fraction | 0.334 | +| clip_range | 0.0667 | +| entropy_loss | -6.61 | +| explained_variance | 0.304 | +| learning_rate | 4.21e-05 | +| loss | -0.0289 | +| n_updates | 80392 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000117 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1397 | +| iterations | 16145 | +| time_elapsed | 23658 | +| total_timesteps | 33064960 | +| train/ | | +| approx_kl | 0.012623267 | +| clip_fraction | 0.341 | +| clip_range | 0.0667 | +| entropy_loss | -6.42 | +| explained_variance | 0.31 | +| learning_rate | 4.21e-05 | +| loss | -0.0314 | +| n_updates | 80396 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000126 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1397 | +| iterations | 16146 | +| time_elapsed | 23659 | +| total_timesteps | 33067008 | +| train/ | | +| approx_kl | 0.009851567 | +| clip_fraction | 0.33 | +| clip_range | 0.0667 | +| entropy_loss | -6.67 | +| explained_variance | 0.0808 | +| learning_rate | 4.21e-05 | +| loss | -0.0206 | +| n_updates | 80400 | +| policy_gradient_loss | -0.0146 | +| value_loss | 0.000206 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1397 | +| iterations | 16147 | +| time_elapsed | 23661 | +| total_timesteps | 33069056 | +| train/ | | +| approx_kl | 0.016610835 | +| clip_fraction | 0.349 | +| clip_range | 0.0667 | +| entropy_loss | -6.09 | +| explained_variance | 0.555 | +| learning_rate | 4.21e-05 | +| loss | -0.0319 | +| n_updates | 80404 | +| policy_gradient_loss | -0.0185 | +| value_loss | 8.82e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1397 | +| iterations | 16148 | +| time_elapsed | 23662 | +| total_timesteps | 33071104 | +| train/ | | +| approx_kl | 0.014138635 | +| clip_fraction | 0.32 | +| clip_range | 0.0667 | +| entropy_loss | -6.12 | +| explained_variance | 0.57 | +| learning_rate | 4.21e-05 | +| loss | -0.0229 | +| n_updates | 80408 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000107 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1397 | +| iterations | 16149 | +| time_elapsed | 23664 | +| total_timesteps | 33073152 | +| train/ | | +| approx_kl | 0.013249639 | +| clip_fraction | 0.292 | +| clip_range | 0.0667 | +| entropy_loss | -5.91 | +| explained_variance | 0.498 | +| learning_rate | 4.21e-05 | +| loss | -0.0221 | +| n_updates | 80412 | +| policy_gradient_loss | -0.0132 | +| value_loss | 0.000232 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1397 | +| iterations | 16150 | +| time_elapsed | 23665 | +| total_timesteps | 33075200 | +| train/ | | +| approx_kl | 0.012737827 | +| clip_fraction | 0.327 | +| clip_range | 0.0667 | +| entropy_loss | -5.04 | +| explained_variance | 0.58 | +| learning_rate | 4.21e-05 | +| loss | -0.0227 | +| n_updates | 80416 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.00015 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1397 | +| iterations | 16151 | +| time_elapsed | 23667 | +| total_timesteps | 33077248 | +| train/ | | +| approx_kl | 0.009980469 | +| clip_fraction | 0.319 | +| clip_range | 0.0667 | +| entropy_loss | -6.44 | +| explained_variance | 0.247 | +| learning_rate | 4.21e-05 | +| loss | -0.0321 | +| n_updates | 80420 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000129 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1397 | +| iterations | 16152 | +| time_elapsed | 23669 | +| total_timesteps | 33079296 | +| train/ | | +| approx_kl | 0.013304809 | +| clip_fraction | 0.341 | +| clip_range | 0.0667 | +| entropy_loss | -6.52 | +| explained_variance | 0.373 | +| learning_rate | 4.21e-05 | +| loss | -0.0313 | +| n_updates | 80424 | +| policy_gradient_loss | -0.0196 | +| value_loss | 7.12e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1397 | +| iterations | 16153 | +| time_elapsed | 23670 | +| total_timesteps | 33081344 | +| train/ | | +| approx_kl | 0.012894582 | +| clip_fraction | 0.346 | +| clip_range | 0.0667 | +| entropy_loss | -6.45 | +| explained_variance | 0.305 | +| learning_rate | 4.21e-05 | +| loss | -0.0269 | +| n_updates | 80428 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000156 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1397 | +| iterations | 16154 | +| time_elapsed | 23672 | +| total_timesteps | 33083392 | +| train/ | | +| approx_kl | 0.011550814 | +| clip_fraction | 0.308 | +| clip_range | 0.0667 | +| entropy_loss | -6.79 | +| explained_variance | 0.269 | +| learning_rate | 4.21e-05 | +| loss | -0.0291 | +| n_updates | 80432 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000162 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1397 | +| iterations | 16155 | +| time_elapsed | 23673 | +| total_timesteps | 33085440 | +| train/ | | +| approx_kl | 0.012385141 | +| clip_fraction | 0.338 | +| clip_range | 0.0667 | +| entropy_loss | -6.34 | +| explained_variance | 0.538 | +| learning_rate | 4.21e-05 | +| loss | -0.032 | +| n_updates | 80436 | +| policy_gradient_loss | -0.0197 | +| value_loss | 8.42e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1397 | +| iterations | 16156 | +| time_elapsed | 23674 | +| total_timesteps | 33087488 | +| train/ | | +| approx_kl | 0.013470059 | +| clip_fraction | 0.32 | +| clip_range | 0.0667 | +| entropy_loss | -5.7 | +| explained_variance | 0.72 | +| learning_rate | 4.21e-05 | +| loss | -0.0271 | +| n_updates | 80440 | +| policy_gradient_loss | -0.0159 | +| value_loss | 8.86e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1397 | +| iterations | 16157 | +| time_elapsed | 23676 | +| total_timesteps | 33089536 | +| train/ | | +| approx_kl | 0.012370726 | +| clip_fraction | 0.324 | +| clip_range | 0.0667 | +| entropy_loss | -5.99 | +| explained_variance | 0.56 | +| learning_rate | 4.21e-05 | +| loss | -0.0304 | +| n_updates | 80444 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.00015 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1397 | +| iterations | 16158 | +| time_elapsed | 23678 | +| total_timesteps | 33091584 | +| train/ | | +| approx_kl | 0.014629773 | +| clip_fraction | 0.339 | +| clip_range | 0.0667 | +| entropy_loss | -5.72 | +| explained_variance | 0.768 | +| learning_rate | 4.21e-05 | +| loss | -0.0284 | +| n_updates | 80448 | +| policy_gradient_loss | -0.0198 | +| value_loss | 4.82e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1397 | +| iterations | 16159 | +| time_elapsed | 23679 | +| total_timesteps | 33093632 | +| train/ | | +| approx_kl | 0.010260504 | +| clip_fraction | 0.315 | +| clip_range | 0.0667 | +| entropy_loss | -6.43 | +| explained_variance | 0.163 | +| learning_rate | 4.21e-05 | +| loss | -0.0261 | +| n_updates | 80452 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000209 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1397 | +| iterations | 16160 | +| time_elapsed | 23681 | +| total_timesteps | 33095680 | +| train/ | | +| approx_kl | 0.012599546 | +| clip_fraction | 0.312 | +| clip_range | 0.0667 | +| entropy_loss | -6.34 | +| explained_variance | 0.454 | +| learning_rate | 4.21e-05 | +| loss | -0.0281 | +| n_updates | 80456 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000179 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1397 | +| iterations | 16161 | +| time_elapsed | 23682 | +| total_timesteps | 33097728 | +| train/ | | +| approx_kl | 0.010253023 | +| clip_fraction | 0.315 | +| clip_range | 0.0667 | +| entropy_loss | -6.48 | +| explained_variance | 0.328 | +| learning_rate | 4.21e-05 | +| loss | -0.0224 | +| n_updates | 80460 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000133 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1397 | +| iterations | 16162 | +| time_elapsed | 23684 | +| total_timesteps | 33099776 | +| train/ | | +| approx_kl | 0.008809524 | +| clip_fraction | 0.317 | +| clip_range | 0.0667 | +| entropy_loss | -6.53 | +| explained_variance | 0.307 | +| learning_rate | 4.21e-05 | +| loss | -0.0217 | +| n_updates | 80464 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.000332 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1397 | +| iterations | 16163 | +| time_elapsed | 23685 | +| total_timesteps | 33101824 | +| train/ | | +| approx_kl | 0.010261598 | +| clip_fraction | 0.327 | +| clip_range | 0.0667 | +| entropy_loss | -6.33 | +| explained_variance | 0.333 | +| learning_rate | 4.21e-05 | +| loss | -0.0246 | +| n_updates | 80468 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.00015 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1397 | +| iterations | 16164 | +| time_elapsed | 23687 | +| total_timesteps | 33103872 | +| train/ | | +| approx_kl | 0.015044961 | +| clip_fraction | 0.329 | +| clip_range | 0.0667 | +| entropy_loss | -5.92 | +| explained_variance | 0.504 | +| learning_rate | 4.21e-05 | +| loss | -0.0321 | +| n_updates | 80472 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.00013 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1397 | +| iterations | 16165 | +| time_elapsed | 23688 | +| total_timesteps | 33105920 | +| train/ | | +| approx_kl | 0.013868289 | +| clip_fraction | 0.321 | +| clip_range | 0.0667 | +| entropy_loss | -6.04 | +| explained_variance | 0.582 | +| learning_rate | 4.21e-05 | +| loss | -0.0263 | +| n_updates | 80476 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000142 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1397 | +| iterations | 16166 | +| time_elapsed | 23690 | +| total_timesteps | 33107968 | +| train/ | | +| approx_kl | 0.011553156 | +| clip_fraction | 0.326 | +| clip_range | 0.0667 | +| entropy_loss | -6.02 | +| explained_variance | 0.51 | +| learning_rate | 4.21e-05 | +| loss | -0.0221 | +| n_updates | 80480 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000152 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1397 | +| iterations | 16167 | +| time_elapsed | 23691 | +| total_timesteps | 33110016 | +| train/ | | +| approx_kl | 0.01354376 | +| clip_fraction | 0.347 | +| clip_range | 0.0667 | +| entropy_loss | -5.51 | +| explained_variance | 0.825 | +| learning_rate | 4.21e-05 | +| loss | -0.0314 | +| n_updates | 80484 | +| policy_gradient_loss | -0.0203 | +| value_loss | 5.15e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1397 | +| iterations | 16168 | +| time_elapsed | 23693 | +| total_timesteps | 33112064 | +| train/ | | +| approx_kl | 0.011409845 | +| clip_fraction | 0.313 | +| clip_range | 0.0667 | +| entropy_loss | -6.1 | +| explained_variance | 0.664 | +| learning_rate | 4.21e-05 | +| loss | -0.0331 | +| n_updates | 80488 | +| policy_gradient_loss | -0.0184 | +| value_loss | 7.63e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1397 | +| iterations | 16169 | +| time_elapsed | 23694 | +| total_timesteps | 33114112 | +| train/ | | +| approx_kl | 0.012201489 | +| clip_fraction | 0.328 | +| clip_range | 0.0667 | +| entropy_loss | -6.82 | +| explained_variance | 0.22 | +| learning_rate | 4.21e-05 | +| loss | -0.026 | +| n_updates | 80492 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000131 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1397 | +| iterations | 16170 | +| time_elapsed | 23696 | +| total_timesteps | 33116160 | +| train/ | | +| approx_kl | 0.0118278265 | +| clip_fraction | 0.32 | +| clip_range | 0.0667 | +| entropy_loss | -6.58 | +| explained_variance | 0.18 | +| learning_rate | 4.21e-05 | +| loss | -0.0301 | +| n_updates | 80496 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000269 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1397 | +| iterations | 16171 | +| time_elapsed | 23698 | +| total_timesteps | 33118208 | +| train/ | | +| approx_kl | 0.015867475 | +| clip_fraction | 0.369 | +| clip_range | 0.0667 | +| entropy_loss | -6.03 | +| explained_variance | 0.557 | +| learning_rate | 4.21e-05 | +| loss | -0.0275 | +| n_updates | 80500 | +| policy_gradient_loss | -0.0209 | +| value_loss | 8.14e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1397 | +| iterations | 16172 | +| time_elapsed | 23699 | +| total_timesteps | 33120256 | +| train/ | | +| approx_kl | 0.017108895 | +| clip_fraction | 0.332 | +| clip_range | 0.0667 | +| entropy_loss | -5.28 | +| explained_variance | 0.549 | +| learning_rate | 4.21e-05 | +| loss | -0.0205 | +| n_updates | 80504 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.000302 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1397 | +| iterations | 16173 | +| time_elapsed | 23701 | +| total_timesteps | 33122304 | +| train/ | | +| approx_kl | 0.014326673 | +| clip_fraction | 0.358 | +| clip_range | 0.0667 | +| entropy_loss | -5.36 | +| explained_variance | 0.674 | +| learning_rate | 4.21e-05 | +| loss | -0.0349 | +| n_updates | 80508 | +| policy_gradient_loss | -0.0211 | +| value_loss | 7.71e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1397 | +| iterations | 16174 | +| time_elapsed | 23702 | +| total_timesteps | 33124352 | +| train/ | | +| approx_kl | 0.013292839 | +| clip_fraction | 0.333 | +| clip_range | 0.0667 | +| entropy_loss | -6.02 | +| explained_variance | 0.383 | +| learning_rate | 4.21e-05 | +| loss | -0.0336 | +| n_updates | 80512 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000194 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1397 | +| iterations | 16175 | +| time_elapsed | 23704 | +| total_timesteps | 33126400 | +| train/ | | +| approx_kl | 0.011588067 | +| clip_fraction | 0.318 | +| clip_range | 0.0667 | +| entropy_loss | -5.93 | +| explained_variance | 0.394 | +| learning_rate | 4.21e-05 | +| loss | -0.0253 | +| n_updates | 80516 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000392 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1397 | +| iterations | 16176 | +| time_elapsed | 23705 | +| total_timesteps | 33128448 | +| train/ | | +| approx_kl | 0.011684058 | +| clip_fraction | 0.35 | +| clip_range | 0.0667 | +| entropy_loss | -6.21 | +| explained_variance | 0.326 | +| learning_rate | 4.21e-05 | +| loss | -0.036 | +| n_updates | 80520 | +| policy_gradient_loss | -0.0219 | +| value_loss | 8.49e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1397 | +| iterations | 16177 | +| time_elapsed | 23707 | +| total_timesteps | 33130496 | +| train/ | | +| approx_kl | 0.012467071 | +| clip_fraction | 0.333 | +| clip_range | 0.0667 | +| entropy_loss | -6.58 | +| explained_variance | 0.264 | +| learning_rate | 4.21e-05 | +| loss | -0.03 | +| n_updates | 80524 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000177 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1397 | +| iterations | 16178 | +| time_elapsed | 23708 | +| total_timesteps | 33132544 | +| train/ | | +| approx_kl | 0.012557423 | +| clip_fraction | 0.321 | +| clip_range | 0.0667 | +| entropy_loss | -6.34 | +| explained_variance | 0.44 | +| learning_rate | 4.21e-05 | +| loss | -0.028 | +| n_updates | 80528 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000176 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1397 | +| iterations | 16179 | +| time_elapsed | 23710 | +| total_timesteps | 33134592 | +| train/ | | +| approx_kl | 0.013590727 | +| clip_fraction | 0.374 | +| clip_range | 0.0667 | +| entropy_loss | -6.29 | +| explained_variance | -0.268 | +| learning_rate | 4.21e-05 | +| loss | -0.0341 | +| n_updates | 80532 | +| policy_gradient_loss | -0.0205 | +| value_loss | 9.95e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1397 | +| iterations | 16180 | +| time_elapsed | 23711 | +| total_timesteps | 33136640 | +| train/ | | +| approx_kl | 0.014968261 | +| clip_fraction | 0.352 | +| clip_range | 0.0667 | +| entropy_loss | -6.48 | +| explained_variance | 0.512 | +| learning_rate | 4.21e-05 | +| loss | -0.0335 | +| n_updates | 80536 | +| policy_gradient_loss | -0.0183 | +| value_loss | 9.34e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1397 | +| iterations | 16181 | +| time_elapsed | 23713 | +| total_timesteps | 33138688 | +| train/ | | +| approx_kl | 0.012262621 | +| clip_fraction | 0.302 | +| clip_range | 0.0667 | +| entropy_loss | -6.31 | +| explained_variance | 0.369 | +| learning_rate | 4.21e-05 | +| loss | -0.023 | +| n_updates | 80540 | +| policy_gradient_loss | -0.0147 | +| value_loss | 0.000221 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1397 | +| iterations | 16182 | +| time_elapsed | 23714 | +| total_timesteps | 33140736 | +| train/ | | +| approx_kl | 0.013190858 | +| clip_fraction | 0.334 | +| clip_range | 0.0667 | +| entropy_loss | -6.24 | +| explained_variance | 0.475 | +| learning_rate | 4.21e-05 | +| loss | -0.0257 | +| n_updates | 80544 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000155 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1397 | +| iterations | 16183 | +| time_elapsed | 23716 | +| total_timesteps | 33142784 | +| train/ | | +| approx_kl | 0.012861194 | +| clip_fraction | 0.323 | +| clip_range | 0.0667 | +| entropy_loss | -5.99 | +| explained_variance | 0.412 | +| learning_rate | 4.21e-05 | +| loss | -0.0248 | +| n_updates | 80548 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000196 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1397 | +| iterations | 16184 | +| time_elapsed | 23718 | +| total_timesteps | 33144832 | +| train/ | | +| approx_kl | 0.010218414 | +| clip_fraction | 0.306 | +| clip_range | 0.0667 | +| entropy_loss | -5.2 | +| explained_variance | 0.507 | +| learning_rate | 4.21e-05 | +| loss | -0.0199 | +| n_updates | 80552 | +| policy_gradient_loss | -0.0125 | +| value_loss | 0.000258 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1397 | +| iterations | 16185 | +| time_elapsed | 23719 | +| total_timesteps | 33146880 | +| train/ | | +| approx_kl | 0.012992161 | +| clip_fraction | 0.332 | +| clip_range | 0.0667 | +| entropy_loss | -5.89 | +| explained_variance | 0.499 | +| learning_rate | 4.21e-05 | +| loss | -0.0298 | +| n_updates | 80556 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000196 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1397 | +| iterations | 16186 | +| time_elapsed | 23721 | +| total_timesteps | 33148928 | +| train/ | | +| approx_kl | 0.01611747 | +| clip_fraction | 0.337 | +| clip_range | 0.0667 | +| entropy_loss | -6.2 | +| explained_variance | -0.132 | +| learning_rate | 4.21e-05 | +| loss | -0.0289 | +| n_updates | 80560 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000151 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1397 | +| iterations | 16187 | +| time_elapsed | 23722 | +| total_timesteps | 33150976 | +| train/ | | +| approx_kl | 0.012452211 | +| clip_fraction | 0.349 | +| clip_range | 0.0667 | +| entropy_loss | -6.74 | +| explained_variance | 0.158 | +| learning_rate | 4.21e-05 | +| loss | -0.0303 | +| n_updates | 80564 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000248 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1397 | +| iterations | 16188 | +| time_elapsed | 23724 | +| total_timesteps | 33153024 | +| train/ | | +| approx_kl | 0.014003862 | +| clip_fraction | 0.314 | +| clip_range | 0.0667 | +| entropy_loss | -6.25 | +| explained_variance | 0.377 | +| learning_rate | 4.21e-05 | +| loss | -0.023 | +| n_updates | 80568 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000247 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1397 | +| iterations | 16189 | +| time_elapsed | 23725 | +| total_timesteps | 33155072 | +| train/ | | +| approx_kl | 0.013227805 | +| clip_fraction | 0.343 | +| clip_range | 0.0667 | +| entropy_loss | -5.71 | +| explained_variance | 0.345 | +| learning_rate | 4.21e-05 | +| loss | -0.0282 | +| n_updates | 80572 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000262 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1397 | +| iterations | 16190 | +| time_elapsed | 23727 | +| total_timesteps | 33157120 | +| train/ | | +| approx_kl | 0.014108954 | +| clip_fraction | 0.349 | +| clip_range | 0.0667 | +| entropy_loss | -5.79 | +| explained_variance | 0.429 | +| learning_rate | 4.21e-05 | +| loss | -0.0271 | +| n_updates | 80576 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000212 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1397 | +| iterations | 16191 | +| time_elapsed | 23728 | +| total_timesteps | 33159168 | +| train/ | | +| approx_kl | 0.014464198 | +| clip_fraction | 0.35 | +| clip_range | 0.0667 | +| entropy_loss | -6.25 | +| explained_variance | 0.451 | +| learning_rate | 4.21e-05 | +| loss | -0.033 | +| n_updates | 80580 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000176 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1397 | +| iterations | 16192 | +| time_elapsed | 23730 | +| total_timesteps | 33161216 | +| train/ | | +| approx_kl | 0.011329146 | +| clip_fraction | 0.313 | +| clip_range | 0.0667 | +| entropy_loss | -5.65 | +| explained_variance | 0.434 | +| learning_rate | 4.21e-05 | +| loss | -0.031 | +| n_updates | 80584 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000211 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1397 | +| iterations | 16193 | +| time_elapsed | 23731 | +| total_timesteps | 33163264 | +| train/ | | +| approx_kl | 0.015473086 | +| clip_fraction | 0.325 | +| clip_range | 0.0667 | +| entropy_loss | -5.85 | +| explained_variance | 0.456 | +| learning_rate | 4.21e-05 | +| loss | -0.0298 | +| n_updates | 80588 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000185 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1397 | +| iterations | 16194 | +| time_elapsed | 23733 | +| total_timesteps | 33165312 | +| train/ | | +| approx_kl | 0.0089940615 | +| clip_fraction | 0.301 | +| clip_range | 0.0667 | +| entropy_loss | -6 | +| explained_variance | 0.534 | +| learning_rate | 4.21e-05 | +| loss | -0.0182 | +| n_updates | 80592 | +| policy_gradient_loss | -0.0128 | +| value_loss | 0.000235 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1397 | +| iterations | 16195 | +| time_elapsed | 23734 | +| total_timesteps | 33167360 | +| train/ | | +| approx_kl | 0.017082296 | +| clip_fraction | 0.34 | +| clip_range | 0.0667 | +| entropy_loss | -5.58 | +| explained_variance | 0.389 | +| learning_rate | 4.21e-05 | +| loss | -0.0295 | +| n_updates | 80596 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000229 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1397 | +| iterations | 16196 | +| time_elapsed | 23736 | +| total_timesteps | 33169408 | +| train/ | | +| approx_kl | 0.013172882 | +| clip_fraction | 0.341 | +| clip_range | 0.0667 | +| entropy_loss | -5.79 | +| explained_variance | 0.454 | +| learning_rate | 4.21e-05 | +| loss | -0.034 | +| n_updates | 80600 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000108 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1397 | +| iterations | 16197 | +| time_elapsed | 23738 | +| total_timesteps | 33171456 | +| train/ | | +| approx_kl | 0.014561743 | +| clip_fraction | 0.356 | +| clip_range | 0.0667 | +| entropy_loss | -6.15 | +| explained_variance | 0.578 | +| learning_rate | 4.21e-05 | +| loss | -0.0315 | +| n_updates | 80604 | +| policy_gradient_loss | -0.021 | +| value_loss | 8.64e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1397 | +| iterations | 16198 | +| time_elapsed | 23739 | +| total_timesteps | 33173504 | +| train/ | | +| approx_kl | 0.013669897 | +| clip_fraction | 0.359 | +| clip_range | 0.0667 | +| entropy_loss | -6.36 | +| explained_variance | 0.34 | +| learning_rate | 4.21e-05 | +| loss | -0.0295 | +| n_updates | 80608 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000134 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1397 | +| iterations | 16199 | +| time_elapsed | 23741 | +| total_timesteps | 33175552 | +| train/ | | +| approx_kl | 0.01336154 | +| clip_fraction | 0.352 | +| clip_range | 0.0667 | +| entropy_loss | -6.77 | +| explained_variance | -0.122 | +| learning_rate | 4.21e-05 | +| loss | -0.0315 | +| n_updates | 80612 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000113 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1397 | +| iterations | 16200 | +| time_elapsed | 23742 | +| total_timesteps | 33177600 | +| train/ | | +| approx_kl | 0.01599495 | +| clip_fraction | 0.339 | +| clip_range | 0.0667 | +| entropy_loss | -6.63 | +| explained_variance | -0.101 | +| learning_rate | 4.21e-05 | +| loss | -0.0282 | +| n_updates | 80616 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000133 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1397 | +| iterations | 16201 | +| time_elapsed | 23744 | +| total_timesteps | 33179648 | +| train/ | | +| approx_kl | 0.014659651 | +| clip_fraction | 0.334 | +| clip_range | 0.0667 | +| entropy_loss | -6.27 | +| explained_variance | 0.282 | +| learning_rate | 4.21e-05 | +| loss | -0.0303 | +| n_updates | 80620 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000289 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1397 | +| iterations | 16202 | +| time_elapsed | 23745 | +| total_timesteps | 33181696 | +| train/ | | +| approx_kl | 0.010895499 | +| clip_fraction | 0.303 | +| clip_range | 0.0667 | +| entropy_loss | -5.37 | +| explained_variance | 0.662 | +| learning_rate | 4.21e-05 | +| loss | -0.0267 | +| n_updates | 80624 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000134 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1397 | +| iterations | 16203 | +| time_elapsed | 23747 | +| total_timesteps | 33183744 | +| train/ | | +| approx_kl | 0.010596747 | +| clip_fraction | 0.321 | +| clip_range | 0.0667 | +| entropy_loss | -6.37 | +| explained_variance | 0.676 | +| learning_rate | 4.21e-05 | +| loss | -0.0295 | +| n_updates | 80628 | +| policy_gradient_loss | -0.0196 | +| value_loss | 7.2e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1397 | +| iterations | 16204 | +| time_elapsed | 23748 | +| total_timesteps | 33185792 | +| train/ | | +| approx_kl | 0.011814214 | +| clip_fraction | 0.303 | +| clip_range | 0.0667 | +| entropy_loss | -6.09 | +| explained_variance | 0.467 | +| learning_rate | 4.21e-05 | +| loss | -0.0277 | +| n_updates | 80632 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000243 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1397 | +| iterations | 16205 | +| time_elapsed | 23750 | +| total_timesteps | 33187840 | +| train/ | | +| approx_kl | 0.012976192 | +| clip_fraction | 0.315 | +| clip_range | 0.0667 | +| entropy_loss | -6.02 | +| explained_variance | 0.0246 | +| learning_rate | 4.21e-05 | +| loss | -0.0291 | +| n_updates | 80636 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000197 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1397 | +| iterations | 16206 | +| time_elapsed | 23751 | +| total_timesteps | 33189888 | +| train/ | | +| approx_kl | 0.010165066 | +| clip_fraction | 0.302 | +| clip_range | 0.0667 | +| entropy_loss | -5.79 | +| explained_variance | 0.541 | +| learning_rate | 4.21e-05 | +| loss | -0.0157 | +| n_updates | 80640 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000135 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1397 | +| iterations | 16207 | +| time_elapsed | 23753 | +| total_timesteps | 33191936 | +| train/ | | +| approx_kl | 0.01240744 | +| clip_fraction | 0.327 | +| clip_range | 0.0667 | +| entropy_loss | -5.78 | +| explained_variance | 0.59 | +| learning_rate | 4.21e-05 | +| loss | -0.0327 | +| n_updates | 80644 | +| policy_gradient_loss | -0.0192 | +| value_loss | 9.19e-05 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1397 | +| iterations | 16208 | +| time_elapsed | 23754 | +| total_timesteps | 33193984 | +| train/ | | +| approx_kl | 0.01274008 | +| clip_fraction | 0.375 | +| clip_range | 0.0667 | +| entropy_loss | -6.3 | +| explained_variance | 0.446 | +| learning_rate | 4.21e-05 | +| loss | -0.0297 | +| n_updates | 80648 | +| policy_gradient_loss | -0.0196 | +| value_loss | 7.28e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1397 | +| iterations | 16209 | +| time_elapsed | 23756 | +| total_timesteps | 33196032 | +| train/ | | +| approx_kl | 0.014199605 | +| clip_fraction | 0.356 | +| clip_range | 0.0667 | +| entropy_loss | -6.45 | +| explained_variance | 0.405 | +| learning_rate | 4.21e-05 | +| loss | -0.0391 | +| n_updates | 80652 | +| policy_gradient_loss | -0.0225 | +| value_loss | 5.96e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1397 | +| iterations | 16210 | +| time_elapsed | 23757 | +| total_timesteps | 33198080 | +| train/ | | +| approx_kl | 0.014898317 | +| clip_fraction | 0.341 | +| clip_range | 0.0667 | +| entropy_loss | -6.4 | +| explained_variance | 0.0888 | +| learning_rate | 4.21e-05 | +| loss | -0.023 | +| n_updates | 80656 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000243 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1397 | +| iterations | 16211 | +| time_elapsed | 23759 | +| total_timesteps | 33200128 | +| train/ | | +| approx_kl | 0.011948819 | +| clip_fraction | 0.35 | +| clip_range | 0.0667 | +| entropy_loss | -6.83 | +| explained_variance | 0.0299 | +| learning_rate | 4.21e-05 | +| loss | -0.0258 | +| n_updates | 80660 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000155 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1397 | +| iterations | 16212 | +| time_elapsed | 23760 | +| total_timesteps | 33202176 | +| train/ | | +| approx_kl | 0.017426793 | +| clip_fraction | 0.317 | +| clip_range | 0.0667 | +| entropy_loss | -5.73 | +| explained_variance | 0.557 | +| learning_rate | 4.21e-05 | +| loss | -0.0244 | +| n_updates | 80664 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000191 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1397 | +| iterations | 16213 | +| time_elapsed | 23762 | +| total_timesteps | 33204224 | +| train/ | | +| approx_kl | 0.0148105305 | +| clip_fraction | 0.362 | +| clip_range | 0.0667 | +| entropy_loss | -5.19 | +| explained_variance | 0.824 | +| learning_rate | 4.21e-05 | +| loss | -0.0378 | +| n_updates | 80668 | +| policy_gradient_loss | -0.0209 | +| value_loss | 5.57e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1397 | +| iterations | 16214 | +| time_elapsed | 23763 | +| total_timesteps | 33206272 | +| train/ | | +| approx_kl | 0.013702525 | +| clip_fraction | 0.308 | +| clip_range | 0.0667 | +| entropy_loss | -5.14 | +| explained_variance | 0.483 | +| learning_rate | 4.21e-05 | +| loss | -0.0262 | +| n_updates | 80672 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000232 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1397 | +| iterations | 16215 | +| time_elapsed | 23765 | +| total_timesteps | 33208320 | +| train/ | | +| approx_kl | 0.017664865 | +| clip_fraction | 0.287 | +| clip_range | 0.0667 | +| entropy_loss | -5.48 | +| explained_variance | 0.638 | +| learning_rate | 4.21e-05 | +| loss | -0.0263 | +| n_updates | 80676 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000157 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1397 | +| iterations | 16216 | +| time_elapsed | 23766 | +| total_timesteps | 33210368 | +| train/ | | +| approx_kl | 0.012374571 | +| clip_fraction | 0.323 | +| clip_range | 0.0667 | +| entropy_loss | -6.32 | +| explained_variance | -0.0959 | +| learning_rate | 4.21e-05 | +| loss | -0.0285 | +| n_updates | 80680 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000146 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1397 | +| iterations | 16217 | +| time_elapsed | 23768 | +| total_timesteps | 33212416 | +| train/ | | +| approx_kl | 0.012338929 | +| clip_fraction | 0.351 | +| clip_range | 0.0667 | +| entropy_loss | -6.65 | +| explained_variance | -0.0713 | +| learning_rate | 4.21e-05 | +| loss | -0.0298 | +| n_updates | 80684 | +| policy_gradient_loss | -0.0202 | +| value_loss | 9.83e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1397 | +| iterations | 16218 | +| time_elapsed | 23769 | +| total_timesteps | 33214464 | +| train/ | | +| approx_kl | 0.013205051 | +| clip_fraction | 0.357 | +| clip_range | 0.0667 | +| entropy_loss | -6.72 | +| explained_variance | -0.0497 | +| learning_rate | 4.21e-05 | +| loss | -0.0341 | +| n_updates | 80688 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.00013 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1397 | +| iterations | 16219 | +| time_elapsed | 23771 | +| total_timesteps | 33216512 | +| train/ | | +| approx_kl | 0.011216143 | +| clip_fraction | 0.329 | +| clip_range | 0.0667 | +| entropy_loss | -6.77 | +| explained_variance | -0.0577 | +| learning_rate | 4.21e-05 | +| loss | -0.0235 | +| n_updates | 80692 | +| policy_gradient_loss | -0.0148 | +| value_loss | 0.000241 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1397 | +| iterations | 16220 | +| time_elapsed | 23772 | +| total_timesteps | 33218560 | +| train/ | | +| approx_kl | 0.010855555 | +| clip_fraction | 0.301 | +| clip_range | 0.0667 | +| entropy_loss | -6.49 | +| explained_variance | 0.354 | +| learning_rate | 4.21e-05 | +| loss | -0.0323 | +| n_updates | 80696 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000217 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1397 | +| iterations | 16221 | +| time_elapsed | 23774 | +| total_timesteps | 33220608 | +| train/ | | +| approx_kl | 0.012453307 | +| clip_fraction | 0.302 | +| clip_range | 0.0667 | +| entropy_loss | -5.98 | +| explained_variance | 0.534 | +| learning_rate | 4.21e-05 | +| loss | -0.0236 | +| n_updates | 80700 | +| policy_gradient_loss | -0.0142 | +| value_loss | 0.000182 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1397 | +| iterations | 16222 | +| time_elapsed | 23775 | +| total_timesteps | 33222656 | +| train/ | | +| approx_kl | 0.0102711655 | +| clip_fraction | 0.305 | +| clip_range | 0.0667 | +| entropy_loss | -5.88 | +| explained_variance | 0.517 | +| learning_rate | 4.21e-05 | +| loss | -0.0319 | +| n_updates | 80704 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000112 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1397 | +| iterations | 16223 | +| time_elapsed | 23777 | +| total_timesteps | 33224704 | +| train/ | | +| approx_kl | 0.01109549 | +| clip_fraction | 0.277 | +| clip_range | 0.0667 | +| entropy_loss | -5.8 | +| explained_variance | 0.456 | +| learning_rate | 4.21e-05 | +| loss | -0.0237 | +| n_updates | 80708 | +| policy_gradient_loss | -0.0143 | +| value_loss | 0.000285 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1397 | +| iterations | 16224 | +| time_elapsed | 23779 | +| total_timesteps | 33226752 | +| train/ | | +| approx_kl | 0.011017367 | +| clip_fraction | 0.327 | +| clip_range | 0.0667 | +| entropy_loss | -6.03 | +| explained_variance | 0.639 | +| learning_rate | 4.21e-05 | +| loss | -0.0325 | +| n_updates | 80712 | +| policy_gradient_loss | -0.0195 | +| value_loss | 8.54e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1397 | +| iterations | 16225 | +| time_elapsed | 23780 | +| total_timesteps | 33228800 | +| train/ | | +| approx_kl | 0.012895478 | +| clip_fraction | 0.335 | +| clip_range | 0.0667 | +| entropy_loss | -6.36 | +| explained_variance | 0.255 | +| learning_rate | 4.21e-05 | +| loss | -0.0266 | +| n_updates | 80716 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000144 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1397 | +| iterations | 16226 | +| time_elapsed | 23782 | +| total_timesteps | 33230848 | +| train/ | | +| approx_kl | 0.011778677 | +| clip_fraction | 0.304 | +| clip_range | 0.0667 | +| entropy_loss | -6.15 | +| explained_variance | 0.533 | +| learning_rate | 4.21e-05 | +| loss | -0.0273 | +| n_updates | 80720 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000136 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1397 | +| iterations | 16227 | +| time_elapsed | 23783 | +| total_timesteps | 33232896 | +| train/ | | +| approx_kl | 0.010754932 | +| clip_fraction | 0.314 | +| clip_range | 0.0667 | +| entropy_loss | -6.5 | +| explained_variance | 0.134 | +| learning_rate | 4.21e-05 | +| loss | -0.0256 | +| n_updates | 80724 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000237 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1397 | +| iterations | 16228 | +| time_elapsed | 23785 | +| total_timesteps | 33234944 | +| train/ | | +| approx_kl | 0.012339159 | +| clip_fraction | 0.344 | +| clip_range | 0.0667 | +| entropy_loss | -6.09 | +| explained_variance | 0.677 | +| learning_rate | 4.21e-05 | +| loss | -0.0285 | +| n_updates | 80728 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000103 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1397 | +| iterations | 16229 | +| time_elapsed | 23786 | +| total_timesteps | 33236992 | +| train/ | | +| approx_kl | 0.013686464 | +| clip_fraction | 0.343 | +| clip_range | 0.0667 | +| entropy_loss | -5.73 | +| explained_variance | 0.302 | +| learning_rate | 4.21e-05 | +| loss | -0.0249 | +| n_updates | 80732 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000153 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1397 | +| iterations | 16230 | +| time_elapsed | 23788 | +| total_timesteps | 33239040 | +| train/ | | +| approx_kl | 0.014466645 | +| clip_fraction | 0.346 | +| clip_range | 0.0667 | +| entropy_loss | -6.03 | +| explained_variance | 0.589 | +| learning_rate | 4.21e-05 | +| loss | -0.0319 | +| n_updates | 80736 | +| policy_gradient_loss | -0.0195 | +| value_loss | 9.77e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1397 | +| iterations | 16231 | +| time_elapsed | 23789 | +| total_timesteps | 33241088 | +| train/ | | +| approx_kl | 0.014164997 | +| clip_fraction | 0.37 | +| clip_range | 0.0667 | +| entropy_loss | -6.2 | +| explained_variance | 0.432 | +| learning_rate | 4.21e-05 | +| loss | -0.034 | +| n_updates | 80740 | +| policy_gradient_loss | -0.0209 | +| value_loss | 8.92e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1397 | +| iterations | 16232 | +| time_elapsed | 23791 | +| total_timesteps | 33243136 | +| train/ | | +| approx_kl | 0.015423479 | +| clip_fraction | 0.339 | +| clip_range | 0.0667 | +| entropy_loss | -5.11 | +| explained_variance | 0.776 | +| learning_rate | 4.21e-05 | +| loss | -0.0275 | +| n_updates | 80744 | +| policy_gradient_loss | -0.0192 | +| value_loss | 8.74e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1397 | +| iterations | 16233 | +| time_elapsed | 23792 | +| total_timesteps | 33245184 | +| train/ | | +| approx_kl | 0.01188799 | +| clip_fraction | 0.348 | +| clip_range | 0.0667 | +| entropy_loss | -5.66 | +| explained_variance | 0.387 | +| learning_rate | 4.21e-05 | +| loss | -0.0251 | +| n_updates | 80748 | +| policy_gradient_loss | -0.0151 | +| value_loss | 9.57e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1397 | +| iterations | 16234 | +| time_elapsed | 23794 | +| total_timesteps | 33247232 | +| train/ | | +| approx_kl | 0.011303367 | +| clip_fraction | 0.333 | +| clip_range | 0.0667 | +| entropy_loss | -6.07 | +| explained_variance | 0.419 | +| learning_rate | 4.21e-05 | +| loss | -0.0246 | +| n_updates | 80752 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000215 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1397 | +| iterations | 16235 | +| time_elapsed | 23795 | +| total_timesteps | 33249280 | +| train/ | | +| approx_kl | 0.016696472 | +| clip_fraction | 0.307 | +| clip_range | 0.0667 | +| entropy_loss | -5.88 | +| explained_variance | 0.249 | +| learning_rate | 4.21e-05 | +| loss | -0.0211 | +| n_updates | 80756 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000269 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1397 | +| iterations | 16236 | +| time_elapsed | 23797 | +| total_timesteps | 33251328 | +| train/ | | +| approx_kl | 0.0124544855 | +| clip_fraction | 0.35 | +| clip_range | 0.0667 | +| entropy_loss | -6.41 | +| explained_variance | -0.121 | +| learning_rate | 4.21e-05 | +| loss | -0.0318 | +| n_updates | 80760 | +| policy_gradient_loss | -0.0216 | +| value_loss | 6.95e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1397 | +| iterations | 16237 | +| time_elapsed | 23798 | +| total_timesteps | 33253376 | +| train/ | | +| approx_kl | 0.010978147 | +| clip_fraction | 0.327 | +| clip_range | 0.0667 | +| entropy_loss | -6.55 | +| explained_variance | 0.151 | +| learning_rate | 4.21e-05 | +| loss | -0.0303 | +| n_updates | 80764 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000265 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1397 | +| iterations | 16238 | +| time_elapsed | 23800 | +| total_timesteps | 33255424 | +| train/ | | +| approx_kl | 0.0128688775 | +| clip_fraction | 0.332 | +| clip_range | 0.0667 | +| entropy_loss | -6.15 | +| explained_variance | 0.501 | +| learning_rate | 4.21e-05 | +| loss | -0.0335 | +| n_updates | 80768 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000109 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1397 | +| iterations | 16239 | +| time_elapsed | 23802 | +| total_timesteps | 33257472 | +| train/ | | +| approx_kl | 0.016519444 | +| clip_fraction | 0.319 | +| clip_range | 0.0667 | +| entropy_loss | -5.6 | +| explained_variance | 0.572 | +| learning_rate | 4.21e-05 | +| loss | -0.0322 | +| n_updates | 80772 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000185 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1397 | +| iterations | 16240 | +| time_elapsed | 23803 | +| total_timesteps | 33259520 | +| train/ | | +| approx_kl | 0.017087802 | +| clip_fraction | 0.328 | +| clip_range | 0.0667 | +| entropy_loss | -6.05 | +| explained_variance | 0.0137 | +| learning_rate | 4.21e-05 | +| loss | -0.0292 | +| n_updates | 80776 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000252 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1397 | +| iterations | 16241 | +| time_elapsed | 23805 | +| total_timesteps | 33261568 | +| train/ | | +| approx_kl | 0.015780814 | +| clip_fraction | 0.354 | +| clip_range | 0.0667 | +| entropy_loss | -5.65 | +| explained_variance | 0.233 | +| learning_rate | 4.21e-05 | +| loss | -0.0278 | +| n_updates | 80780 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000385 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1397 | +| iterations | 16242 | +| time_elapsed | 23806 | +| total_timesteps | 33263616 | +| train/ | | +| approx_kl | 0.013767274 | +| clip_fraction | 0.371 | +| clip_range | 0.0667 | +| entropy_loss | -4.84 | +| explained_variance | 0.755 | +| learning_rate | 4.21e-05 | +| loss | -0.0383 | +| n_updates | 80784 | +| policy_gradient_loss | -0.0209 | +| value_loss | 7.58e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1397 | +| iterations | 16243 | +| time_elapsed | 23808 | +| total_timesteps | 33265664 | +| train/ | | +| approx_kl | 0.013832826 | +| clip_fraction | 0.36 | +| clip_range | 0.0667 | +| entropy_loss | -5.96 | +| explained_variance | 0.477 | +| learning_rate | 4.21e-05 | +| loss | -0.034 | +| n_updates | 80788 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000125 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1397 | +| iterations | 16244 | +| time_elapsed | 23809 | +| total_timesteps | 33267712 | +| train/ | | +| approx_kl | 0.011828234 | +| clip_fraction | 0.327 | +| clip_range | 0.0667 | +| entropy_loss | -6.2 | +| explained_variance | 0.202 | +| learning_rate | 4.21e-05 | +| loss | -0.025 | +| n_updates | 80792 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000184 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1397 | +| iterations | 16245 | +| time_elapsed | 23811 | +| total_timesteps | 33269760 | +| train/ | | +| approx_kl | 0.013457373 | +| clip_fraction | 0.37 | +| clip_range | 0.0667 | +| entropy_loss | -6.44 | +| explained_variance | 0.314 | +| learning_rate | 4.21e-05 | +| loss | -0.032 | +| n_updates | 80796 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.00011 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1397 | +| iterations | 16246 | +| time_elapsed | 23812 | +| total_timesteps | 33271808 | +| train/ | | +| approx_kl | 0.011386847 | +| clip_fraction | 0.318 | +| clip_range | 0.0667 | +| entropy_loss | -6.31 | +| explained_variance | 0.376 | +| learning_rate | 4.21e-05 | +| loss | -0.0292 | +| n_updates | 80800 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000167 | +----------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1397 | +| iterations | 16247 | +| time_elapsed | 23814 | +| total_timesteps | 33273856 | +| train/ | | +| approx_kl | 0.011001 | +| clip_fraction | 0.318 | +| clip_range | 0.0667 | +| entropy_loss | -5.84 | +| explained_variance | 0.529 | +| learning_rate | 4.21e-05 | +| loss | -0.0272 | +| n_updates | 80804 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000188 | +-------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1397 | +| iterations | 16248 | +| time_elapsed | 23816 | +| total_timesteps | 33275904 | +| train/ | | +| approx_kl | 0.009802783 | +| clip_fraction | 0.303 | +| clip_range | 0.0667 | +| entropy_loss | -5.74 | +| explained_variance | 0.357 | +| learning_rate | 4.21e-05 | +| loss | -0.0249 | +| n_updates | 80808 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000329 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1397 | +| iterations | 16249 | +| time_elapsed | 23817 | +| total_timesteps | 33277952 | +| train/ | | +| approx_kl | 0.0118515715 | +| clip_fraction | 0.332 | +| clip_range | 0.0667 | +| entropy_loss | -5.44 | +| explained_variance | 0.748 | +| learning_rate | 4.21e-05 | +| loss | -0.0313 | +| n_updates | 80812 | +| policy_gradient_loss | -0.0188 | +| value_loss | 7.89e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1397 | +| iterations | 16250 | +| time_elapsed | 23819 | +| total_timesteps | 33280000 | +| train/ | | +| approx_kl | 0.012340163 | +| clip_fraction | 0.33 | +| clip_range | 0.0667 | +| entropy_loss | -6.04 | +| explained_variance | 0.269 | +| learning_rate | 4.21e-05 | +| loss | -0.0235 | +| n_updates | 80816 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000143 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1397 | +| iterations | 16251 | +| time_elapsed | 23820 | +| total_timesteps | 33282048 | +| train/ | | +| approx_kl | 0.011957206 | +| clip_fraction | 0.333 | +| clip_range | 0.0667 | +| entropy_loss | -6.18 | +| explained_variance | 0.522 | +| learning_rate | 4.21e-05 | +| loss | -0.0301 | +| n_updates | 80820 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000173 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1397 | +| iterations | 16252 | +| time_elapsed | 23822 | +| total_timesteps | 33284096 | +| train/ | | +| approx_kl | 0.011760179 | +| clip_fraction | 0.329 | +| clip_range | 0.0667 | +| entropy_loss | -6.63 | +| explained_variance | -0.0361 | +| learning_rate | 4.21e-05 | +| loss | -0.029 | +| n_updates | 80824 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000135 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1397 | +| iterations | 16253 | +| time_elapsed | 23823 | +| total_timesteps | 33286144 | +| train/ | | +| approx_kl | 0.012304319 | +| clip_fraction | 0.318 | +| clip_range | 0.0667 | +| entropy_loss | -6.23 | +| explained_variance | 0.543 | +| learning_rate | 4.21e-05 | +| loss | -0.0267 | +| n_updates | 80828 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000129 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1397 | +| iterations | 16254 | +| time_elapsed | 23825 | +| total_timesteps | 33288192 | +| train/ | | +| approx_kl | 0.013610882 | +| clip_fraction | 0.343 | +| clip_range | 0.0667 | +| entropy_loss | -5.9 | +| explained_variance | 0.465 | +| learning_rate | 4.21e-05 | +| loss | -0.0242 | +| n_updates | 80832 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000173 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1397 | +| iterations | 16255 | +| time_elapsed | 23826 | +| total_timesteps | 33290240 | +| train/ | | +| approx_kl | 0.010692294 | +| clip_fraction | 0.32 | +| clip_range | 0.0667 | +| entropy_loss | -5.85 | +| explained_variance | 0.353 | +| learning_rate | 4.21e-05 | +| loss | -0.0275 | +| n_updates | 80836 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.0004 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1397 | +| iterations | 16256 | +| time_elapsed | 23828 | +| total_timesteps | 33292288 | +| train/ | | +| approx_kl | 0.014413139 | +| clip_fraction | 0.381 | +| clip_range | 0.0667 | +| entropy_loss | -5.71 | +| explained_variance | 0.486 | +| learning_rate | 4.21e-05 | +| loss | -0.0354 | +| n_updates | 80840 | +| policy_gradient_loss | -0.0224 | +| value_loss | 0.000116 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1397 | +| iterations | 16257 | +| time_elapsed | 23829 | +| total_timesteps | 33294336 | +| train/ | | +| approx_kl | 0.012068378 | +| clip_fraction | 0.343 | +| clip_range | 0.0667 | +| entropy_loss | -6.21 | +| explained_variance | 0.457 | +| learning_rate | 4.21e-05 | +| loss | -0.0313 | +| n_updates | 80844 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000175 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1397 | +| iterations | 16258 | +| time_elapsed | 23831 | +| total_timesteps | 33296384 | +| train/ | | +| approx_kl | 0.013980014 | +| clip_fraction | 0.333 | +| clip_range | 0.0667 | +| entropy_loss | -5.9 | +| explained_variance | 0.503 | +| learning_rate | 4.21e-05 | +| loss | -0.0228 | +| n_updates | 80848 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000172 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1397 | +| iterations | 16259 | +| time_elapsed | 23832 | +| total_timesteps | 33298432 | +| train/ | | +| approx_kl | 0.013226708 | +| clip_fraction | 0.356 | +| clip_range | 0.0667 | +| entropy_loss | -6.14 | +| explained_variance | 0.189 | +| learning_rate | 4.21e-05 | +| loss | -0.0255 | +| n_updates | 80852 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000219 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1397 | +| iterations | 16260 | +| time_elapsed | 23834 | +| total_timesteps | 33300480 | +| train/ | | +| approx_kl | 0.013338938 | +| clip_fraction | 0.33 | +| clip_range | 0.0667 | +| entropy_loss | -6.42 | +| explained_variance | 0.259 | +| learning_rate | 4.21e-05 | +| loss | -0.0263 | +| n_updates | 80856 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000182 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1397 | +| iterations | 16261 | +| time_elapsed | 23836 | +| total_timesteps | 33302528 | +| train/ | | +| approx_kl | 0.013326978 | +| clip_fraction | 0.341 | +| clip_range | 0.0667 | +| entropy_loss | -5.57 | +| explained_variance | 0.522 | +| learning_rate | 4.21e-05 | +| loss | -0.0257 | +| n_updates | 80860 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000133 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1397 | +| iterations | 16262 | +| time_elapsed | 23837 | +| total_timesteps | 33304576 | +| train/ | | +| approx_kl | 0.015070133 | +| clip_fraction | 0.339 | +| clip_range | 0.0667 | +| entropy_loss | -6.04 | +| explained_variance | 0.426 | +| learning_rate | 4.21e-05 | +| loss | -0.0293 | +| n_updates | 80864 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.00013 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1397 | +| iterations | 16263 | +| time_elapsed | 23839 | +| total_timesteps | 33306624 | +| train/ | | +| approx_kl | 0.013688739 | +| clip_fraction | 0.345 | +| clip_range | 0.0667 | +| entropy_loss | -5.62 | +| explained_variance | 0.7 | +| learning_rate | 4.21e-05 | +| loss | -0.0249 | +| n_updates | 80868 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000117 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1397 | +| iterations | 16264 | +| time_elapsed | 23840 | +| total_timesteps | 33308672 | +| train/ | | +| approx_kl | 0.013206648 | +| clip_fraction | 0.366 | +| clip_range | 0.0667 | +| entropy_loss | -6.27 | +| explained_variance | -0.14 | +| learning_rate | 4.21e-05 | +| loss | -0.0295 | +| n_updates | 80872 | +| policy_gradient_loss | -0.0212 | +| value_loss | 5.45e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1397 | +| iterations | 16265 | +| time_elapsed | 23842 | +| total_timesteps | 33310720 | +| train/ | | +| approx_kl | 0.012961581 | +| clip_fraction | 0.356 | +| clip_range | 0.0667 | +| entropy_loss | -6.33 | +| explained_variance | 0.436 | +| learning_rate | 4.21e-05 | +| loss | -0.0304 | +| n_updates | 80876 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000161 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1397 | +| iterations | 16266 | +| time_elapsed | 23843 | +| total_timesteps | 33312768 | +| train/ | | +| approx_kl | 0.012774799 | +| clip_fraction | 0.354 | +| clip_range | 0.0667 | +| entropy_loss | -6.56 | +| explained_variance | 0.598 | +| learning_rate | 4.21e-05 | +| loss | -0.0335 | +| n_updates | 80880 | +| policy_gradient_loss | -0.02 | +| value_loss | 5.17e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1397 | +| iterations | 16267 | +| time_elapsed | 23845 | +| total_timesteps | 33314816 | +| train/ | | +| approx_kl | 0.011772819 | +| clip_fraction | 0.297 | +| clip_range | 0.0667 | +| entropy_loss | -5.93 | +| explained_variance | 0.587 | +| learning_rate | 4.21e-05 | +| loss | -0.0269 | +| n_updates | 80884 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000151 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1397 | +| iterations | 16268 | +| time_elapsed | 23846 | +| total_timesteps | 33316864 | +| train/ | | +| approx_kl | 0.012747057 | +| clip_fraction | 0.335 | +| clip_range | 0.0667 | +| entropy_loss | -5.97 | +| explained_variance | 0.429 | +| learning_rate | 4.21e-05 | +| loss | -0.0324 | +| n_updates | 80888 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000106 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1397 | +| iterations | 16269 | +| time_elapsed | 23848 | +| total_timesteps | 33318912 | +| train/ | | +| approx_kl | 0.010550926 | +| clip_fraction | 0.317 | +| clip_range | 0.0667 | +| entropy_loss | -5.95 | +| explained_variance | 0.158 | +| learning_rate | 4.21e-05 | +| loss | -0.0233 | +| n_updates | 80892 | +| policy_gradient_loss | -0.0143 | +| value_loss | 0.000567 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1397 | +| iterations | 16270 | +| time_elapsed | 23849 | +| total_timesteps | 33320960 | +| train/ | | +| approx_kl | 0.012631819 | +| clip_fraction | 0.307 | +| clip_range | 0.0667 | +| entropy_loss | -4.74 | +| explained_variance | 0.484 | +| learning_rate | 4.21e-05 | +| loss | -0.0239 | +| n_updates | 80896 | +| policy_gradient_loss | -0.0143 | +| value_loss | 0.000353 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1397 | +| iterations | 16271 | +| time_elapsed | 23851 | +| total_timesteps | 33323008 | +| train/ | | +| approx_kl | 0.012471918 | +| clip_fraction | 0.346 | +| clip_range | 0.0667 | +| entropy_loss | -5.65 | +| explained_variance | 0.216 | +| learning_rate | 4.21e-05 | +| loss | -0.0321 | +| n_updates | 80900 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000188 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1397 | +| iterations | 16272 | +| time_elapsed | 23853 | +| total_timesteps | 33325056 | +| train/ | | +| approx_kl | 0.011918876 | +| clip_fraction | 0.357 | +| clip_range | 0.0667 | +| entropy_loss | -6.49 | +| explained_variance | 0.33 | +| learning_rate | 4.21e-05 | +| loss | -0.0351 | +| n_updates | 80904 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000165 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1397 | +| iterations | 16273 | +| time_elapsed | 23854 | +| total_timesteps | 33327104 | +| train/ | | +| approx_kl | 0.013382656 | +| clip_fraction | 0.355 | +| clip_range | 0.0667 | +| entropy_loss | -6.33 | +| explained_variance | 0.458 | +| learning_rate | 4.21e-05 | +| loss | -0.0317 | +| n_updates | 80908 | +| policy_gradient_loss | -0.021 | +| value_loss | 7.69e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1397 | +| iterations | 16274 | +| time_elapsed | 23856 | +| total_timesteps | 33329152 | +| train/ | | +| approx_kl | 0.011053441 | +| clip_fraction | 0.344 | +| clip_range | 0.0667 | +| entropy_loss | -6.5 | +| explained_variance | 0.147 | +| learning_rate | 4.21e-05 | +| loss | -0.0295 | +| n_updates | 80912 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000102 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1397 | +| iterations | 16275 | +| time_elapsed | 23857 | +| total_timesteps | 33331200 | +| train/ | | +| approx_kl | 0.0096997805 | +| clip_fraction | 0.335 | +| clip_range | 0.0667 | +| entropy_loss | -6.59 | +| explained_variance | 0.449 | +| learning_rate | 4.21e-05 | +| loss | -0.0316 | +| n_updates | 80916 | +| policy_gradient_loss | -0.0195 | +| value_loss | 6.81e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1397 | +| iterations | 16276 | +| time_elapsed | 23859 | +| total_timesteps | 33333248 | +| train/ | | +| approx_kl | 0.011165136 | +| clip_fraction | 0.328 | +| clip_range | 0.0667 | +| entropy_loss | -6.5 | +| explained_variance | 0.583 | +| learning_rate | 4.21e-05 | +| loss | -0.0354 | +| n_updates | 80920 | +| policy_gradient_loss | -0.0177 | +| value_loss | 5.66e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1397 | +| iterations | 16277 | +| time_elapsed | 23860 | +| total_timesteps | 33335296 | +| train/ | | +| approx_kl | 0.012885987 | +| clip_fraction | 0.339 | +| clip_range | 0.0667 | +| entropy_loss | -6.03 | +| explained_variance | 0.464 | +| learning_rate | 4.21e-05 | +| loss | -0.0268 | +| n_updates | 80924 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000169 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1397 | +| iterations | 16278 | +| time_elapsed | 23862 | +| total_timesteps | 33337344 | +| train/ | | +| approx_kl | 0.013800294 | +| clip_fraction | 0.317 | +| clip_range | 0.0667 | +| entropy_loss | -5.26 | +| explained_variance | 0.698 | +| learning_rate | 4.21e-05 | +| loss | -0.0226 | +| n_updates | 80928 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000153 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1397 | +| iterations | 16279 | +| time_elapsed | 23863 | +| total_timesteps | 33339392 | +| train/ | | +| approx_kl | 0.013554648 | +| clip_fraction | 0.318 | +| clip_range | 0.0667 | +| entropy_loss | -5.43 | +| explained_variance | 0.505 | +| learning_rate | 4.21e-05 | +| loss | -0.0243 | +| n_updates | 80932 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000107 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1397 | +| iterations | 16280 | +| time_elapsed | 23865 | +| total_timesteps | 33341440 | +| train/ | | +| approx_kl | 0.012886062 | +| clip_fraction | 0.331 | +| clip_range | 0.0667 | +| entropy_loss | -5.94 | +| explained_variance | 0.519 | +| learning_rate | 4.21e-05 | +| loss | -0.0302 | +| n_updates | 80936 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000169 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1397 | +| iterations | 16281 | +| time_elapsed | 23866 | +| total_timesteps | 33343488 | +| train/ | | +| approx_kl | 0.012652231 | +| clip_fraction | 0.342 | +| clip_range | 0.0667 | +| entropy_loss | -6.24 | +| explained_variance | -0.0222 | +| learning_rate | 4.21e-05 | +| loss | -0.0209 | +| n_updates | 80940 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000176 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1397 | +| iterations | 16282 | +| time_elapsed | 23868 | +| total_timesteps | 33345536 | +| train/ | | +| approx_kl | 0.018518474 | +| clip_fraction | 0.344 | +| clip_range | 0.0667 | +| entropy_loss | -6.12 | +| explained_variance | 0.244 | +| learning_rate | 4.21e-05 | +| loss | -0.0298 | +| n_updates | 80944 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000204 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1397 | +| iterations | 16283 | +| time_elapsed | 23869 | +| total_timesteps | 33347584 | +| train/ | | +| approx_kl | 0.020296719 | +| clip_fraction | 0.344 | +| clip_range | 0.0667 | +| entropy_loss | -6.34 | +| explained_variance | -0.145 | +| learning_rate | 4.21e-05 | +| loss | -0.0304 | +| n_updates | 80948 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000163 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1397 | +| iterations | 16284 | +| time_elapsed | 23871 | +| total_timesteps | 33349632 | +| train/ | | +| approx_kl | 0.013658473 | +| clip_fraction | 0.345 | +| clip_range | 0.0667 | +| entropy_loss | -6.46 | +| explained_variance | 0.0501 | +| learning_rate | 4.21e-05 | +| loss | -0.0295 | +| n_updates | 80952 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000186 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1397 | +| iterations | 16285 | +| time_elapsed | 23872 | +| total_timesteps | 33351680 | +| train/ | | +| approx_kl | 0.009047696 | +| clip_fraction | 0.292 | +| clip_range | 0.0667 | +| entropy_loss | -5.77 | +| explained_variance | 0.657 | +| learning_rate | 4.21e-05 | +| loss | -0.0272 | +| n_updates | 80956 | +| policy_gradient_loss | -0.0126 | +| value_loss | 0.000122 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1397 | +| iterations | 16286 | +| time_elapsed | 23874 | +| total_timesteps | 33353728 | +| train/ | | +| approx_kl | 0.012482906 | +| clip_fraction | 0.345 | +| clip_range | 0.0667 | +| entropy_loss | -6.18 | +| explained_variance | 0.606 | +| learning_rate | 4.21e-05 | +| loss | -0.0355 | +| n_updates | 80960 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000117 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1397 | +| iterations | 16287 | +| time_elapsed | 23876 | +| total_timesteps | 33355776 | +| train/ | | +| approx_kl | 0.010698056 | +| clip_fraction | 0.329 | +| clip_range | 0.0667 | +| entropy_loss | -6.32 | +| explained_variance | 0.346 | +| learning_rate | 4.21e-05 | +| loss | -0.0287 | +| n_updates | 80964 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000163 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1397 | +| iterations | 16288 | +| time_elapsed | 23877 | +| total_timesteps | 33357824 | +| train/ | | +| approx_kl | 0.016295329 | +| clip_fraction | 0.37 | +| clip_range | 0.0667 | +| entropy_loss | -6.12 | +| explained_variance | 0.715 | +| learning_rate | 4.21e-05 | +| loss | -0.0366 | +| n_updates | 80968 | +| policy_gradient_loss | -0.0219 | +| value_loss | 5.14e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1397 | +| iterations | 16289 | +| time_elapsed | 23879 | +| total_timesteps | 33359872 | +| train/ | | +| approx_kl | 0.013191474 | +| clip_fraction | 0.334 | +| clip_range | 0.0667 | +| entropy_loss | -6.6 | +| explained_variance | -0.175 | +| learning_rate | 4.21e-05 | +| loss | -0.033 | +| n_updates | 80972 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000103 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1397 | +| iterations | 16290 | +| time_elapsed | 23880 | +| total_timesteps | 33361920 | +| train/ | | +| approx_kl | 0.00984662 | +| clip_fraction | 0.296 | +| clip_range | 0.0667 | +| entropy_loss | -6.46 | +| explained_variance | 0.349 | +| learning_rate | 4.21e-05 | +| loss | -0.0277 | +| n_updates | 80976 | +| policy_gradient_loss | -0.0146 | +| value_loss | 0.000134 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1397 | +| iterations | 16291 | +| time_elapsed | 23882 | +| total_timesteps | 33363968 | +| train/ | | +| approx_kl | 0.011667455 | +| clip_fraction | 0.321 | +| clip_range | 0.0667 | +| entropy_loss | -6.22 | +| explained_variance | 0.561 | +| learning_rate | 4.21e-05 | +| loss | -0.0296 | +| n_updates | 80980 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000118 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1397 | +| iterations | 16292 | +| time_elapsed | 23883 | +| total_timesteps | 33366016 | +| train/ | | +| approx_kl | 0.011990104 | +| clip_fraction | 0.312 | +| clip_range | 0.0667 | +| entropy_loss | -5.59 | +| explained_variance | 0.699 | +| learning_rate | 4.21e-05 | +| loss | -0.0186 | +| n_updates | 80984 | +| policy_gradient_loss | -0.0137 | +| value_loss | 0.000171 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1397 | +| iterations | 16293 | +| time_elapsed | 23885 | +| total_timesteps | 33368064 | +| train/ | | +| approx_kl | 0.012994202 | +| clip_fraction | 0.344 | +| clip_range | 0.0667 | +| entropy_loss | -6.15 | +| explained_variance | -0.0334 | +| learning_rate | 4.21e-05 | +| loss | -0.0288 | +| n_updates | 80988 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000188 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1397 | +| iterations | 16294 | +| time_elapsed | 23886 | +| total_timesteps | 33370112 | +| train/ | | +| approx_kl | 0.011459777 | +| clip_fraction | 0.335 | +| clip_range | 0.0667 | +| entropy_loss | -6.56 | +| explained_variance | 0.169 | +| learning_rate | 4.21e-05 | +| loss | -0.0257 | +| n_updates | 80992 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000178 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.315 | +| time/ | | +| fps | 1397 | +| iterations | 16295 | +| time_elapsed | 23888 | +| total_timesteps | 33372160 | +| train/ | | +| approx_kl | 0.008483883 | +| clip_fraction | 0.307 | +| clip_range | 0.0667 | +| entropy_loss | -5.82 | +| explained_variance | 0.639 | +| learning_rate | 4.21e-05 | +| loss | -0.0227 | +| n_updates | 80996 | +| policy_gradient_loss | -0.0132 | +| value_loss | 0.000102 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1397 | +| iterations | 16296 | +| time_elapsed | 23889 | +| total_timesteps | 33374208 | +| train/ | | +| approx_kl | 0.013709398 | +| clip_fraction | 0.346 | +| clip_range | 0.0667 | +| entropy_loss | -5.65 | +| explained_variance | 0.551 | +| learning_rate | 4.21e-05 | +| loss | -0.0289 | +| n_updates | 81000 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000104 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1396 | +| iterations | 16297 | +| time_elapsed | 23891 | +| total_timesteps | 33376256 | +| train/ | | +| approx_kl | 0.009221066 | +| clip_fraction | 0.33 | +| clip_range | 0.0667 | +| entropy_loss | -6.46 | +| explained_variance | 0.217 | +| learning_rate | 4.21e-05 | +| loss | -0.0284 | +| n_updates | 81004 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000409 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1396 | +| iterations | 16298 | +| time_elapsed | 23892 | +| total_timesteps | 33378304 | +| train/ | | +| approx_kl | 0.01147146 | +| clip_fraction | 0.322 | +| clip_range | 0.0667 | +| entropy_loss | -6.37 | +| explained_variance | -0.086 | +| learning_rate | 4.21e-05 | +| loss | -0.0334 | +| n_updates | 81008 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000109 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1396 | +| iterations | 16299 | +| time_elapsed | 23894 | +| total_timesteps | 33380352 | +| train/ | | +| approx_kl | 0.010108136 | +| clip_fraction | 0.341 | +| clip_range | 0.0667 | +| entropy_loss | -6.25 | +| explained_variance | 0.114 | +| learning_rate | 4.21e-05 | +| loss | -0.0386 | +| n_updates | 81012 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000182 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1396 | +| iterations | 16300 | +| time_elapsed | 23895 | +| total_timesteps | 33382400 | +| train/ | | +| approx_kl | 0.012135446 | +| clip_fraction | 0.329 | +| clip_range | 0.0667 | +| entropy_loss | -6.41 | +| explained_variance | 0.4 | +| learning_rate | 4.21e-05 | +| loss | -0.0213 | +| n_updates | 81016 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000165 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1396 | +| iterations | 16301 | +| time_elapsed | 23897 | +| total_timesteps | 33384448 | +| train/ | | +| approx_kl | 0.013655176 | +| clip_fraction | 0.339 | +| clip_range | 0.0667 | +| entropy_loss | -7 | +| explained_variance | -0.0712 | +| learning_rate | 4.21e-05 | +| loss | -0.0298 | +| n_updates | 81020 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000168 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1396 | +| iterations | 16302 | +| time_elapsed | 23898 | +| total_timesteps | 33386496 | +| train/ | | +| approx_kl | 0.010155944 | +| clip_fraction | 0.294 | +| clip_range | 0.0667 | +| entropy_loss | -6.2 | +| explained_variance | 0.486 | +| learning_rate | 4.21e-05 | +| loss | -0.0179 | +| n_updates | 81024 | +| policy_gradient_loss | -0.014 | +| value_loss | 0.000266 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1396 | +| iterations | 16303 | +| time_elapsed | 23900 | +| total_timesteps | 33388544 | +| train/ | | +| approx_kl | 0.012614723 | +| clip_fraction | 0.352 | +| clip_range | 0.0667 | +| entropy_loss | -6.26 | +| explained_variance | 0.454 | +| learning_rate | 4.21e-05 | +| loss | -0.025 | +| n_updates | 81028 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000236 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1396 | +| iterations | 16304 | +| time_elapsed | 23902 | +| total_timesteps | 33390592 | +| train/ | | +| approx_kl | 0.012571531 | +| clip_fraction | 0.342 | +| clip_range | 0.0667 | +| entropy_loss | -6.45 | +| explained_variance | 0.155 | +| learning_rate | 4.21e-05 | +| loss | -0.0346 | +| n_updates | 81032 | +| policy_gradient_loss | -0.0214 | +| value_loss | 8.31e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1396 | +| iterations | 16305 | +| time_elapsed | 23903 | +| total_timesteps | 33392640 | +| train/ | | +| approx_kl | 0.012561331 | +| clip_fraction | 0.311 | +| clip_range | 0.0667 | +| entropy_loss | -5.88 | +| explained_variance | 0.576 | +| learning_rate | 4.21e-05 | +| loss | -0.0259 | +| n_updates | 81036 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000222 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1396 | +| iterations | 16306 | +| time_elapsed | 23905 | +| total_timesteps | 33394688 | +| train/ | | +| approx_kl | 0.011929726 | +| clip_fraction | 0.331 | +| clip_range | 0.0667 | +| entropy_loss | -5.79 | +| explained_variance | 0.284 | +| learning_rate | 4.21e-05 | +| loss | -0.0333 | +| n_updates | 81040 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000195 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1396 | +| iterations | 16307 | +| time_elapsed | 23906 | +| total_timesteps | 33396736 | +| train/ | | +| approx_kl | 0.01641279 | +| clip_fraction | 0.363 | +| clip_range | 0.0667 | +| entropy_loss | -6.23 | +| explained_variance | 0.398 | +| learning_rate | 4.21e-05 | +| loss | -0.034 | +| n_updates | 81044 | +| policy_gradient_loss | -0.0208 | +| value_loss | 7.95e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1396 | +| iterations | 16308 | +| time_elapsed | 23908 | +| total_timesteps | 33398784 | +| train/ | | +| approx_kl | 0.015019944 | +| clip_fraction | 0.361 | +| clip_range | 0.0667 | +| entropy_loss | -6.14 | +| explained_variance | 0.689 | +| learning_rate | 4.21e-05 | +| loss | -0.0323 | +| n_updates | 81048 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000109 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1396 | +| iterations | 16309 | +| time_elapsed | 23909 | +| total_timesteps | 33400832 | +| train/ | | +| approx_kl | 0.01185573 | +| clip_fraction | 0.349 | +| clip_range | 0.0667 | +| entropy_loss | -5.88 | +| explained_variance | 0.418 | +| learning_rate | 4.21e-05 | +| loss | -0.0193 | +| n_updates | 81052 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000175 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1396 | +| iterations | 16310 | +| time_elapsed | 23911 | +| total_timesteps | 33402880 | +| train/ | | +| approx_kl | 0.012503464 | +| clip_fraction | 0.309 | +| clip_range | 0.0666 | +| entropy_loss | -6.69 | +| explained_variance | -0.113 | +| learning_rate | 4.21e-05 | +| loss | -0.0256 | +| n_updates | 81056 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000129 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1396 | +| iterations | 16311 | +| time_elapsed | 23912 | +| total_timesteps | 33404928 | +| train/ | | +| approx_kl | 0.010431599 | +| clip_fraction | 0.284 | +| clip_range | 0.0666 | +| entropy_loss | -5.75 | +| explained_variance | 0.384 | +| learning_rate | 4.21e-05 | +| loss | -0.0231 | +| n_updates | 81060 | +| policy_gradient_loss | -0.0141 | +| value_loss | 0.000264 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1396 | +| iterations | 16312 | +| time_elapsed | 23914 | +| total_timesteps | 33406976 | +| train/ | | +| approx_kl | 0.014623348 | +| clip_fraction | 0.357 | +| clip_range | 0.0666 | +| entropy_loss | -6.38 | +| explained_variance | -0.00376 | +| learning_rate | 4.21e-05 | +| loss | -0.0323 | +| n_updates | 81064 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000116 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1396 | +| iterations | 16313 | +| time_elapsed | 23915 | +| total_timesteps | 33409024 | +| train/ | | +| approx_kl | 0.015463538 | +| clip_fraction | 0.367 | +| clip_range | 0.0666 | +| entropy_loss | -6.57 | +| explained_variance | 0.181 | +| learning_rate | 4.21e-05 | +| loss | -0.0238 | +| n_updates | 81068 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000161 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1396 | +| iterations | 16314 | +| time_elapsed | 23917 | +| total_timesteps | 33411072 | +| train/ | | +| approx_kl | 0.012074016 | +| clip_fraction | 0.333 | +| clip_range | 0.0666 | +| entropy_loss | -6.06 | +| explained_variance | 0.373 | +| learning_rate | 4.21e-05 | +| loss | -0.0276 | +| n_updates | 81072 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000196 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1396 | +| iterations | 16315 | +| time_elapsed | 23918 | +| total_timesteps | 33413120 | +| train/ | | +| approx_kl | 0.014523542 | +| clip_fraction | 0.33 | +| clip_range | 0.0666 | +| entropy_loss | -6 | +| explained_variance | 0.602 | +| learning_rate | 4.21e-05 | +| loss | -0.0291 | +| n_updates | 81076 | +| policy_gradient_loss | -0.0191 | +| value_loss | 8.9e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1396 | +| iterations | 16316 | +| time_elapsed | 23920 | +| total_timesteps | 33415168 | +| train/ | | +| approx_kl | 0.0098988395 | +| clip_fraction | 0.31 | +| clip_range | 0.0666 | +| entropy_loss | -6.46 | +| explained_variance | 0.296 | +| learning_rate | 4.21e-05 | +| loss | -0.0242 | +| n_updates | 81080 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.00017 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1396 | +| iterations | 16317 | +| time_elapsed | 23922 | +| total_timesteps | 33417216 | +| train/ | | +| approx_kl | 0.01318067 | +| clip_fraction | 0.331 | +| clip_range | 0.0666 | +| entropy_loss | -6.96 | +| explained_variance | 0.282 | +| learning_rate | 4.21e-05 | +| loss | -0.027 | +| n_updates | 81084 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000157 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1396 | +| iterations | 16318 | +| time_elapsed | 23923 | +| total_timesteps | 33419264 | +| train/ | | +| approx_kl | 0.009172385 | +| clip_fraction | 0.25 | +| clip_range | 0.0666 | +| entropy_loss | -6.03 | +| explained_variance | 0.411 | +| learning_rate | 4.21e-05 | +| loss | -0.0191 | +| n_updates | 81088 | +| policy_gradient_loss | -0.0116 | +| value_loss | 0.000372 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1396 | +| iterations | 16319 | +| time_elapsed | 23925 | +| total_timesteps | 33421312 | +| train/ | | +| approx_kl | 0.010338316 | +| clip_fraction | 0.313 | +| clip_range | 0.0666 | +| entropy_loss | -5.95 | +| explained_variance | 0.283 | +| learning_rate | 4.21e-05 | +| loss | -0.0262 | +| n_updates | 81092 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000179 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1396 | +| iterations | 16320 | +| time_elapsed | 23926 | +| total_timesteps | 33423360 | +| train/ | | +| approx_kl | 0.013865218 | +| clip_fraction | 0.349 | +| clip_range | 0.0666 | +| entropy_loss | -6.33 | +| explained_variance | 0.0381 | +| learning_rate | 4.21e-05 | +| loss | -0.0261 | +| n_updates | 81096 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000156 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1396 | +| iterations | 16321 | +| time_elapsed | 23928 | +| total_timesteps | 33425408 | +| train/ | | +| approx_kl | 0.013381215 | +| clip_fraction | 0.334 | +| clip_range | 0.0666 | +| entropy_loss | -6.24 | +| explained_variance | 0.283 | +| learning_rate | 4.21e-05 | +| loss | -0.027 | +| n_updates | 81100 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000304 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1396 | +| iterations | 16322 | +| time_elapsed | 23929 | +| total_timesteps | 33427456 | +| train/ | | +| approx_kl | 0.015570069 | +| clip_fraction | 0.359 | +| clip_range | 0.0666 | +| entropy_loss | -6.23 | +| explained_variance | 0.397 | +| learning_rate | 4.21e-05 | +| loss | -0.033 | +| n_updates | 81104 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000196 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1396 | +| iterations | 16323 | +| time_elapsed | 23931 | +| total_timesteps | 33429504 | +| train/ | | +| approx_kl | 0.011745636 | +| clip_fraction | 0.343 | +| clip_range | 0.0666 | +| entropy_loss | -5.53 | +| explained_variance | 0.638 | +| learning_rate | 4.21e-05 | +| loss | -0.0348 | +| n_updates | 81108 | +| policy_gradient_loss | -0.0181 | +| value_loss | 9.78e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1396 | +| iterations | 16324 | +| time_elapsed | 23932 | +| total_timesteps | 33431552 | +| train/ | | +| approx_kl | 0.013828183 | +| clip_fraction | 0.37 | +| clip_range | 0.0666 | +| entropy_loss | -5.81 | +| explained_variance | 0.746 | +| learning_rate | 4.21e-05 | +| loss | -0.0285 | +| n_updates | 81112 | +| policy_gradient_loss | -0.0213 | +| value_loss | 7.49e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1396 | +| iterations | 16325 | +| time_elapsed | 23934 | +| total_timesteps | 33433600 | +| train/ | | +| approx_kl | 0.011208741 | +| clip_fraction | 0.322 | +| clip_range | 0.0666 | +| entropy_loss | -5.56 | +| explained_variance | 0.386 | +| learning_rate | 4.21e-05 | +| loss | -0.0243 | +| n_updates | 81116 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000255 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1396 | +| iterations | 16326 | +| time_elapsed | 23935 | +| total_timesteps | 33435648 | +| train/ | | +| approx_kl | 0.0141867 | +| clip_fraction | 0.34 | +| clip_range | 0.0666 | +| entropy_loss | -5.92 | +| explained_variance | 0.331 | +| learning_rate | 4.21e-05 | +| loss | -0.0289 | +| n_updates | 81120 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000132 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1396 | +| iterations | 16327 | +| time_elapsed | 23937 | +| total_timesteps | 33437696 | +| train/ | | +| approx_kl | 0.014760273 | +| clip_fraction | 0.339 | +| clip_range | 0.0666 | +| entropy_loss | -6.18 | +| explained_variance | 0.219 | +| learning_rate | 4.21e-05 | +| loss | -0.0259 | +| n_updates | 81124 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000232 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1396 | +| iterations | 16328 | +| time_elapsed | 23938 | +| total_timesteps | 33439744 | +| train/ | | +| approx_kl | 0.009628031 | +| clip_fraction | 0.32 | +| clip_range | 0.0666 | +| entropy_loss | -6.81 | +| explained_variance | 0.155 | +| learning_rate | 4.21e-05 | +| loss | -0.0275 | +| n_updates | 81128 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000174 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1396 | +| iterations | 16329 | +| time_elapsed | 23940 | +| total_timesteps | 33441792 | +| train/ | | +| approx_kl | 0.011858606 | +| clip_fraction | 0.335 | +| clip_range | 0.0666 | +| entropy_loss | -6.58 | +| explained_variance | 0.167 | +| learning_rate | 4.21e-05 | +| loss | -0.0351 | +| n_updates | 81132 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000161 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1396 | +| iterations | 16330 | +| time_elapsed | 23941 | +| total_timesteps | 33443840 | +| train/ | | +| approx_kl | 0.009308351 | +| clip_fraction | 0.326 | +| clip_range | 0.0666 | +| entropy_loss | -5.85 | +| explained_variance | 0.412 | +| learning_rate | 4.21e-05 | +| loss | -0.0297 | +| n_updates | 81136 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000442 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1396 | +| iterations | 16331 | +| time_elapsed | 23943 | +| total_timesteps | 33445888 | +| train/ | | +| approx_kl | 0.013902128 | +| clip_fraction | 0.301 | +| clip_range | 0.0666 | +| entropy_loss | -5.47 | +| explained_variance | 0.382 | +| learning_rate | 4.21e-05 | +| loss | -0.0293 | +| n_updates | 81140 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000295 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1396 | +| iterations | 16332 | +| time_elapsed | 23944 | +| total_timesteps | 33447936 | +| train/ | | +| approx_kl | 0.015385572 | +| clip_fraction | 0.326 | +| clip_range | 0.0666 | +| entropy_loss | -6.03 | +| explained_variance | 0.142 | +| learning_rate | 4.21e-05 | +| loss | -0.0231 | +| n_updates | 81144 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000322 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1396 | +| iterations | 16333 | +| time_elapsed | 23946 | +| total_timesteps | 33449984 | +| train/ | | +| approx_kl | 0.0133024715 | +| clip_fraction | 0.369 | +| clip_range | 0.0666 | +| entropy_loss | -6.34 | +| explained_variance | 0.205 | +| learning_rate | 4.21e-05 | +| loss | -0.0353 | +| n_updates | 81148 | +| policy_gradient_loss | -0.0221 | +| value_loss | 0.000113 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1396 | +| iterations | 16334 | +| time_elapsed | 23947 | +| total_timesteps | 33452032 | +| train/ | | +| approx_kl | 0.013798725 | +| clip_fraction | 0.334 | +| clip_range | 0.0666 | +| entropy_loss | -6.32 | +| explained_variance | 0.294 | +| learning_rate | 4.21e-05 | +| loss | -0.0276 | +| n_updates | 81152 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000146 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1396 | +| iterations | 16335 | +| time_elapsed | 23949 | +| total_timesteps | 33454080 | +| train/ | | +| approx_kl | 0.014426864 | +| clip_fraction | 0.349 | +| clip_range | 0.0666 | +| entropy_loss | -6.12 | +| explained_variance | 0.57 | +| learning_rate | 4.21e-05 | +| loss | -0.0299 | +| n_updates | 81156 | +| policy_gradient_loss | -0.0195 | +| value_loss | 9.92e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1396 | +| iterations | 16336 | +| time_elapsed | 23950 | +| total_timesteps | 33456128 | +| train/ | | +| approx_kl | 0.016682034 | +| clip_fraction | 0.381 | +| clip_range | 0.0666 | +| entropy_loss | -5.78 | +| explained_variance | 0.674 | +| learning_rate | 4.21e-05 | +| loss | -0.0357 | +| n_updates | 81160 | +| policy_gradient_loss | -0.0224 | +| value_loss | 6.3e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1396 | +| iterations | 16337 | +| time_elapsed | 23952 | +| total_timesteps | 33458176 | +| train/ | | +| approx_kl | 0.014135281 | +| clip_fraction | 0.324 | +| clip_range | 0.0666 | +| entropy_loss | -5.86 | +| explained_variance | 0.342 | +| learning_rate | 4.21e-05 | +| loss | -0.0237 | +| n_updates | 81164 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000278 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1396 | +| iterations | 16338 | +| time_elapsed | 23954 | +| total_timesteps | 33460224 | +| train/ | | +| approx_kl | 0.016320836 | +| clip_fraction | 0.344 | +| clip_range | 0.0666 | +| entropy_loss | -5.86 | +| explained_variance | 0.465 | +| learning_rate | 4.21e-05 | +| loss | -0.0277 | +| n_updates | 81168 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000166 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1396 | +| iterations | 16339 | +| time_elapsed | 23955 | +| total_timesteps | 33462272 | +| train/ | | +| approx_kl | 0.017342094 | +| clip_fraction | 0.336 | +| clip_range | 0.0666 | +| entropy_loss | -5.99 | +| explained_variance | 0.314 | +| learning_rate | 4.21e-05 | +| loss | -0.0251 | +| n_updates | 81172 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000178 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1396 | +| iterations | 16340 | +| time_elapsed | 23957 | +| total_timesteps | 33464320 | +| train/ | | +| approx_kl | 0.01876209 | +| clip_fraction | 0.383 | +| clip_range | 0.0666 | +| entropy_loss | -6.25 | +| explained_variance | 0.371 | +| learning_rate | 4.21e-05 | +| loss | -0.0345 | +| n_updates | 81176 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000113 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1396 | +| iterations | 16341 | +| time_elapsed | 23958 | +| total_timesteps | 33466368 | +| train/ | | +| approx_kl | 0.015228389 | +| clip_fraction | 0.376 | +| clip_range | 0.0666 | +| entropy_loss | -5.89 | +| explained_variance | 0.575 | +| learning_rate | 4.21e-05 | +| loss | -0.0303 | +| n_updates | 81180 | +| policy_gradient_loss | -0.0198 | +| value_loss | 9.67e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1396 | +| iterations | 16342 | +| time_elapsed | 23960 | +| total_timesteps | 33468416 | +| train/ | | +| approx_kl | 0.013412718 | +| clip_fraction | 0.325 | +| clip_range | 0.0666 | +| entropy_loss | -6.34 | +| explained_variance | 0.17 | +| learning_rate | 4.21e-05 | +| loss | -0.0282 | +| n_updates | 81184 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000291 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1396 | +| iterations | 16343 | +| time_elapsed | 23961 | +| total_timesteps | 33470464 | +| train/ | | +| approx_kl | 0.010494028 | +| clip_fraction | 0.364 | +| clip_range | 0.0666 | +| entropy_loss | -6.28 | +| explained_variance | 0.153 | +| learning_rate | 4.21e-05 | +| loss | -0.0219 | +| n_updates | 81188 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000284 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1396 | +| iterations | 16344 | +| time_elapsed | 23963 | +| total_timesteps | 33472512 | +| train/ | | +| approx_kl | 0.011928899 | +| clip_fraction | 0.34 | +| clip_range | 0.0666 | +| entropy_loss | -6 | +| explained_variance | 0.507 | +| learning_rate | 4.21e-05 | +| loss | -0.0292 | +| n_updates | 81192 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000163 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1396 | +| iterations | 16345 | +| time_elapsed | 23964 | +| total_timesteps | 33474560 | +| train/ | | +| approx_kl | 0.012157485 | +| clip_fraction | 0.337 | +| clip_range | 0.0666 | +| entropy_loss | -5.71 | +| explained_variance | 0.425 | +| learning_rate | 4.21e-05 | +| loss | -0.0267 | +| n_updates | 81196 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000265 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1396 | +| iterations | 16346 | +| time_elapsed | 23966 | +| total_timesteps | 33476608 | +| train/ | | +| approx_kl | 0.012316786 | +| clip_fraction | 0.364 | +| clip_range | 0.0666 | +| entropy_loss | -5.79 | +| explained_variance | 0.627 | +| learning_rate | 4.2e-05 | +| loss | -0.0311 | +| n_updates | 81200 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000104 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1396 | +| iterations | 16347 | +| time_elapsed | 23967 | +| total_timesteps | 33478656 | +| train/ | | +| approx_kl | 0.014031699 | +| clip_fraction | 0.347 | +| clip_range | 0.0666 | +| entropy_loss | -6.17 | +| explained_variance | 0.298 | +| learning_rate | 4.2e-05 | +| loss | -0.0298 | +| n_updates | 81204 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000114 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1396 | +| iterations | 16348 | +| time_elapsed | 23969 | +| total_timesteps | 33480704 | +| train/ | | +| approx_kl | 0.01462796 | +| clip_fraction | 0.341 | +| clip_range | 0.0666 | +| entropy_loss | -6.17 | +| explained_variance | 0.683 | +| learning_rate | 4.2e-05 | +| loss | -0.0346 | +| n_updates | 81208 | +| policy_gradient_loss | -0.0199 | +| value_loss | 5.25e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1396 | +| iterations | 16349 | +| time_elapsed | 23970 | +| total_timesteps | 33482752 | +| train/ | | +| approx_kl | 0.013394061 | +| clip_fraction | 0.351 | +| clip_range | 0.0666 | +| entropy_loss | -5.71 | +| explained_variance | 0.618 | +| learning_rate | 4.2e-05 | +| loss | -0.0275 | +| n_updates | 81212 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000121 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1396 | +| iterations | 16350 | +| time_elapsed | 23972 | +| total_timesteps | 33484800 | +| train/ | | +| approx_kl | 0.012935648 | +| clip_fraction | 0.358 | +| clip_range | 0.0666 | +| entropy_loss | -6.28 | +| explained_variance | 0.21 | +| learning_rate | 4.2e-05 | +| loss | -0.0303 | +| n_updates | 81216 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000199 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1396 | +| iterations | 16351 | +| time_elapsed | 23973 | +| total_timesteps | 33486848 | +| train/ | | +| approx_kl | 0.012689191 | +| clip_fraction | 0.367 | +| clip_range | 0.0666 | +| entropy_loss | -6.22 | +| explained_variance | 0.436 | +| learning_rate | 4.2e-05 | +| loss | -0.0229 | +| n_updates | 81220 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000124 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1396 | +| iterations | 16352 | +| time_elapsed | 23975 | +| total_timesteps | 33488896 | +| train/ | | +| approx_kl | 0.011989075 | +| clip_fraction | 0.298 | +| clip_range | 0.0666 | +| entropy_loss | -5.79 | +| explained_variance | 0.425 | +| learning_rate | 4.2e-05 | +| loss | -0.0181 | +| n_updates | 81224 | +| policy_gradient_loss | -0.0133 | +| value_loss | 0.000233 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1396 | +| iterations | 16353 | +| time_elapsed | 23977 | +| total_timesteps | 33490944 | +| train/ | | +| approx_kl | 0.012750165 | +| clip_fraction | 0.364 | +| clip_range | 0.0666 | +| entropy_loss | -6.31 | +| explained_variance | 0.296 | +| learning_rate | 4.2e-05 | +| loss | -0.038 | +| n_updates | 81228 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000207 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1396 | +| iterations | 16354 | +| time_elapsed | 23978 | +| total_timesteps | 33492992 | +| train/ | | +| approx_kl | 0.009883196 | +| clip_fraction | 0.319 | +| clip_range | 0.0666 | +| entropy_loss | -6 | +| explained_variance | 0.319 | +| learning_rate | 4.2e-05 | +| loss | -0.0221 | +| n_updates | 81232 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000268 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1396 | +| iterations | 16355 | +| time_elapsed | 23980 | +| total_timesteps | 33495040 | +| train/ | | +| approx_kl | 0.013256529 | +| clip_fraction | 0.361 | +| clip_range | 0.0666 | +| entropy_loss | -5.99 | +| explained_variance | 0.594 | +| learning_rate | 4.2e-05 | +| loss | -0.0344 | +| n_updates | 81236 | +| policy_gradient_loss | -0.0219 | +| value_loss | 9.13e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1396 | +| iterations | 16356 | +| time_elapsed | 23981 | +| total_timesteps | 33497088 | +| train/ | | +| approx_kl | 0.011817172 | +| clip_fraction | 0.315 | +| clip_range | 0.0666 | +| entropy_loss | -6.43 | +| explained_variance | 0.392 | +| learning_rate | 4.2e-05 | +| loss | -0.0343 | +| n_updates | 81240 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000162 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1396 | +| iterations | 16357 | +| time_elapsed | 23983 | +| total_timesteps | 33499136 | +| train/ | | +| approx_kl | 0.012321222 | +| clip_fraction | 0.299 | +| clip_range | 0.0666 | +| entropy_loss | -6.73 | +| explained_variance | 0.213 | +| learning_rate | 4.2e-05 | +| loss | -0.0211 | +| n_updates | 81244 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000247 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1396 | +| iterations | 16358 | +| time_elapsed | 23984 | +| total_timesteps | 33501184 | +| train/ | | +| approx_kl | 0.010477297 | +| clip_fraction | 0.289 | +| clip_range | 0.0666 | +| entropy_loss | -5.65 | +| explained_variance | 0.527 | +| learning_rate | 4.2e-05 | +| loss | -0.0263 | +| n_updates | 81248 | +| policy_gradient_loss | -0.0148 | +| value_loss | 0.000311 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1396 | +| iterations | 16359 | +| time_elapsed | 23986 | +| total_timesteps | 33503232 | +| train/ | | +| approx_kl | 0.01340192 | +| clip_fraction | 0.328 | +| clip_range | 0.0666 | +| entropy_loss | -6.21 | +| explained_variance | -0.122 | +| learning_rate | 4.2e-05 | +| loss | -0.027 | +| n_updates | 81252 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000227 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1396 | +| iterations | 16360 | +| time_elapsed | 23987 | +| total_timesteps | 33505280 | +| train/ | | +| approx_kl | 0.0147497505 | +| clip_fraction | 0.328 | +| clip_range | 0.0666 | +| entropy_loss | -5.73 | +| explained_variance | 0.438 | +| learning_rate | 4.2e-05 | +| loss | -0.0309 | +| n_updates | 81256 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000224 | +------------------------------------------ +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1396 | +| iterations | 16361 | +| time_elapsed | 23989 | +| total_timesteps | 33507328 | +| train/ | | +| approx_kl | 0.0149336 | +| clip_fraction | 0.369 | +| clip_range | 0.0666 | +| entropy_loss | -6.27 | +| explained_variance | 0.314 | +| learning_rate | 4.2e-05 | +| loss | -0.031 | +| n_updates | 81260 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.0001 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1396 | +| iterations | 16362 | +| time_elapsed | 23991 | +| total_timesteps | 33509376 | +| train/ | | +| approx_kl | 0.013533512 | +| clip_fraction | 0.353 | +| clip_range | 0.0666 | +| entropy_loss | -6 | +| explained_variance | 0.494 | +| learning_rate | 4.2e-05 | +| loss | -0.0289 | +| n_updates | 81264 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000228 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1396 | +| iterations | 16363 | +| time_elapsed | 23992 | +| total_timesteps | 33511424 | +| train/ | | +| approx_kl | 0.012563046 | +| clip_fraction | 0.364 | +| clip_range | 0.0666 | +| entropy_loss | -6.25 | +| explained_variance | 0.319 | +| learning_rate | 4.2e-05 | +| loss | -0.0252 | +| n_updates | 81268 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000126 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1396 | +| iterations | 16364 | +| time_elapsed | 23994 | +| total_timesteps | 33513472 | +| train/ | | +| approx_kl | 0.010548899 | +| clip_fraction | 0.339 | +| clip_range | 0.0666 | +| entropy_loss | -6.01 | +| explained_variance | 0.55 | +| learning_rate | 4.2e-05 | +| loss | -0.0291 | +| n_updates | 81272 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000106 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1396 | +| iterations | 16365 | +| time_elapsed | 23995 | +| total_timesteps | 33515520 | +| train/ | | +| approx_kl | 0.011907447 | +| clip_fraction | 0.355 | +| clip_range | 0.0666 | +| entropy_loss | -6.02 | +| explained_variance | 0.681 | +| learning_rate | 4.2e-05 | +| loss | -0.0266 | +| n_updates | 81276 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000107 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1396 | +| iterations | 16366 | +| time_elapsed | 23997 | +| total_timesteps | 33517568 | +| train/ | | +| approx_kl | 0.013693125 | +| clip_fraction | 0.331 | +| clip_range | 0.0666 | +| entropy_loss | -5.64 | +| explained_variance | 0.383 | +| learning_rate | 4.2e-05 | +| loss | -0.0231 | +| n_updates | 81280 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.000352 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1396 | +| iterations | 16367 | +| time_elapsed | 23998 | +| total_timesteps | 33519616 | +| train/ | | +| approx_kl | 0.01579391 | +| clip_fraction | 0.364 | +| clip_range | 0.0666 | +| entropy_loss | -6.04 | +| explained_variance | 0.287 | +| learning_rate | 4.2e-05 | +| loss | -0.0346 | +| n_updates | 81284 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000101 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1396 | +| iterations | 16368 | +| time_elapsed | 24000 | +| total_timesteps | 33521664 | +| train/ | | +| approx_kl | 0.01212042 | +| clip_fraction | 0.345 | +| clip_range | 0.0666 | +| entropy_loss | -6.52 | +| explained_variance | 0.305 | +| learning_rate | 4.2e-05 | +| loss | -0.0295 | +| n_updates | 81288 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000123 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1396 | +| iterations | 16369 | +| time_elapsed | 24001 | +| total_timesteps | 33523712 | +| train/ | | +| approx_kl | 0.014866106 | +| clip_fraction | 0.325 | +| clip_range | 0.0666 | +| entropy_loss | -6.68 | +| explained_variance | 0.232 | +| learning_rate | 4.2e-05 | +| loss | -0.0292 | +| n_updates | 81292 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000164 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1396 | +| iterations | 16370 | +| time_elapsed | 24003 | +| total_timesteps | 33525760 | +| train/ | | +| approx_kl | 0.009990798 | +| clip_fraction | 0.318 | +| clip_range | 0.0666 | +| entropy_loss | -6.71 | +| explained_variance | 0.227 | +| learning_rate | 4.2e-05 | +| loss | -0.0275 | +| n_updates | 81296 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000249 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1396 | +| iterations | 16371 | +| time_elapsed | 24004 | +| total_timesteps | 33527808 | +| train/ | | +| approx_kl | 0.010684313 | +| clip_fraction | 0.308 | +| clip_range | 0.0666 | +| entropy_loss | -6.04 | +| explained_variance | 0.611 | +| learning_rate | 4.2e-05 | +| loss | -0.0278 | +| n_updates | 81300 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000124 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1396 | +| iterations | 16372 | +| time_elapsed | 24006 | +| total_timesteps | 33529856 | +| train/ | | +| approx_kl | 0.010935372 | +| clip_fraction | 0.305 | +| clip_range | 0.0666 | +| entropy_loss | -5.65 | +| explained_variance | 0.586 | +| learning_rate | 4.2e-05 | +| loss | -0.0255 | +| n_updates | 81304 | +| policy_gradient_loss | -0.0143 | +| value_loss | 0.000214 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1396 | +| iterations | 16373 | +| time_elapsed | 24008 | +| total_timesteps | 33531904 | +| train/ | | +| approx_kl | 0.0126121305 | +| clip_fraction | 0.328 | +| clip_range | 0.0666 | +| entropy_loss | -5.95 | +| explained_variance | 0.365 | +| learning_rate | 4.2e-05 | +| loss | -0.0289 | +| n_updates | 81308 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000145 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1396 | +| iterations | 16374 | +| time_elapsed | 24009 | +| total_timesteps | 33533952 | +| train/ | | +| approx_kl | 0.009724371 | +| clip_fraction | 0.338 | +| clip_range | 0.0666 | +| entropy_loss | -6.83 | +| explained_variance | -0.177 | +| learning_rate | 4.2e-05 | +| loss | -0.0303 | +| n_updates | 81312 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000148 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1396 | +| iterations | 16375 | +| time_elapsed | 24011 | +| total_timesteps | 33536000 | +| train/ | | +| approx_kl | 0.012858488 | +| clip_fraction | 0.337 | +| clip_range | 0.0666 | +| entropy_loss | -6.61 | +| explained_variance | 0.318 | +| learning_rate | 4.2e-05 | +| loss | -0.0286 | +| n_updates | 81316 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000136 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1396 | +| iterations | 16376 | +| time_elapsed | 24012 | +| total_timesteps | 33538048 | +| train/ | | +| approx_kl | 0.012327287 | +| clip_fraction | 0.325 | +| clip_range | 0.0666 | +| entropy_loss | -6.6 | +| explained_variance | 0.364 | +| learning_rate | 4.2e-05 | +| loss | -0.0282 | +| n_updates | 81320 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000142 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1396 | +| iterations | 16377 | +| time_elapsed | 24014 | +| total_timesteps | 33540096 | +| train/ | | +| approx_kl | 0.013864607 | +| clip_fraction | 0.339 | +| clip_range | 0.0666 | +| entropy_loss | -6.38 | +| explained_variance | 0.461 | +| learning_rate | 4.2e-05 | +| loss | -0.0363 | +| n_updates | 81324 | +| policy_gradient_loss | -0.0203 | +| value_loss | 7.96e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1396 | +| iterations | 16378 | +| time_elapsed | 24015 | +| total_timesteps | 33542144 | +| train/ | | +| approx_kl | 0.012104974 | +| clip_fraction | 0.325 | +| clip_range | 0.0666 | +| entropy_loss | -6.34 | +| explained_variance | 0.598 | +| learning_rate | 4.2e-05 | +| loss | -0.0223 | +| n_updates | 81328 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000128 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1396 | +| iterations | 16379 | +| time_elapsed | 24017 | +| total_timesteps | 33544192 | +| train/ | | +| approx_kl | 0.011192262 | +| clip_fraction | 0.314 | +| clip_range | 0.0666 | +| entropy_loss | -6.42 | +| explained_variance | 0.437 | +| learning_rate | 4.2e-05 | +| loss | -0.0273 | +| n_updates | 81332 | +| policy_gradient_loss | -0.0178 | +| value_loss | 7.56e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1396 | +| iterations | 16380 | +| time_elapsed | 24018 | +| total_timesteps | 33546240 | +| train/ | | +| approx_kl | 0.0114802215 | +| clip_fraction | 0.288 | +| clip_range | 0.0666 | +| entropy_loss | -5.42 | +| explained_variance | 0.58 | +| learning_rate | 4.2e-05 | +| loss | -0.0213 | +| n_updates | 81336 | +| policy_gradient_loss | -0.0133 | +| value_loss | 0.000256 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1396 | +| iterations | 16381 | +| time_elapsed | 24020 | +| total_timesteps | 33548288 | +| train/ | | +| approx_kl | 0.012260066 | +| clip_fraction | 0.347 | +| clip_range | 0.0666 | +| entropy_loss | -5.65 | +| explained_variance | -0.394 | +| learning_rate | 4.2e-05 | +| loss | -0.0395 | +| n_updates | 81340 | +| policy_gradient_loss | -0.0196 | +| value_loss | 6.9e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1396 | +| iterations | 16382 | +| time_elapsed | 24021 | +| total_timesteps | 33550336 | +| train/ | | +| approx_kl | 0.0152314305 | +| clip_fraction | 0.329 | +| clip_range | 0.0666 | +| entropy_loss | -6.19 | +| explained_variance | 0.523 | +| learning_rate | 4.2e-05 | +| loss | -0.0287 | +| n_updates | 81344 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000128 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1396 | +| iterations | 16383 | +| time_elapsed | 24023 | +| total_timesteps | 33552384 | +| train/ | | +| approx_kl | 0.010021625 | +| clip_fraction | 0.326 | +| clip_range | 0.0666 | +| entropy_loss | -6.04 | +| explained_variance | 0.388 | +| learning_rate | 4.2e-05 | +| loss | -0.0241 | +| n_updates | 81348 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000239 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1396 | +| iterations | 16384 | +| time_elapsed | 24025 | +| total_timesteps | 33554432 | +| train/ | | +| approx_kl | 0.013952823 | +| clip_fraction | 0.371 | +| clip_range | 0.0666 | +| entropy_loss | -6.06 | +| explained_variance | 0.448 | +| learning_rate | 4.2e-05 | +| loss | -0.0341 | +| n_updates | 81352 | +| policy_gradient_loss | -0.0212 | +| value_loss | 9.23e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1396 | +| iterations | 16385 | +| time_elapsed | 24026 | +| total_timesteps | 33556480 | +| train/ | | +| approx_kl | 0.015366869 | +| clip_fraction | 0.354 | +| clip_range | 0.0666 | +| entropy_loss | -6.14 | +| explained_variance | 0.389 | +| learning_rate | 4.2e-05 | +| loss | -0.0316 | +| n_updates | 81356 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000172 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1396 | +| iterations | 16386 | +| time_elapsed | 24028 | +| total_timesteps | 33558528 | +| train/ | | +| approx_kl | 0.010357806 | +| clip_fraction | 0.311 | +| clip_range | 0.0666 | +| entropy_loss | -6.66 | +| explained_variance | 0.0512 | +| learning_rate | 4.2e-05 | +| loss | -0.0248 | +| n_updates | 81360 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1396 | +| iterations | 16387 | +| time_elapsed | 24029 | +| total_timesteps | 33560576 | +| train/ | | +| approx_kl | 0.011582842 | +| clip_fraction | 0.312 | +| clip_range | 0.0666 | +| entropy_loss | -6.06 | +| explained_variance | 0.623 | +| learning_rate | 4.2e-05 | +| loss | -0.0244 | +| n_updates | 81364 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000132 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1396 | +| iterations | 16388 | +| time_elapsed | 24031 | +| total_timesteps | 33562624 | +| train/ | | +| approx_kl | 0.0119771045 | +| clip_fraction | 0.323 | +| clip_range | 0.0666 | +| entropy_loss | -5.8 | +| explained_variance | 0.393 | +| learning_rate | 4.2e-05 | +| loss | -0.0276 | +| n_updates | 81368 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000239 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1396 | +| iterations | 16389 | +| time_elapsed | 24032 | +| total_timesteps | 33564672 | +| train/ | | +| approx_kl | 0.013810642 | +| clip_fraction | 0.321 | +| clip_range | 0.0666 | +| entropy_loss | -6 | +| explained_variance | 0.64 | +| learning_rate | 4.2e-05 | +| loss | -0.0297 | +| n_updates | 81372 | +| policy_gradient_loss | -0.0185 | +| value_loss | 9.01e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1396 | +| iterations | 16390 | +| time_elapsed | 24034 | +| total_timesteps | 33566720 | +| train/ | | +| approx_kl | 0.012874186 | +| clip_fraction | 0.313 | +| clip_range | 0.0666 | +| entropy_loss | -6.32 | +| explained_variance | 0.401 | +| learning_rate | 4.2e-05 | +| loss | -0.0266 | +| n_updates | 81376 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.0002 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1396 | +| iterations | 16391 | +| time_elapsed | 24035 | +| total_timesteps | 33568768 | +| train/ | | +| approx_kl | 0.014801487 | +| clip_fraction | 0.339 | +| clip_range | 0.0666 | +| entropy_loss | -5.63 | +| explained_variance | 0.599 | +| learning_rate | 4.2e-05 | +| loss | -0.0322 | +| n_updates | 81380 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000148 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1396 | +| iterations | 16392 | +| time_elapsed | 24037 | +| total_timesteps | 33570816 | +| train/ | | +| approx_kl | 0.0147567205 | +| clip_fraction | 0.359 | +| clip_range | 0.0666 | +| entropy_loss | -6.42 | +| explained_variance | -0.00167 | +| learning_rate | 4.2e-05 | +| loss | -0.0288 | +| n_updates | 81384 | +| policy_gradient_loss | -0.0201 | +| value_loss | 9.77e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1396 | +| iterations | 16393 | +| time_elapsed | 24038 | +| total_timesteps | 33572864 | +| train/ | | +| approx_kl | 0.012555836 | +| clip_fraction | 0.334 | +| clip_range | 0.0666 | +| entropy_loss | -6.23 | +| explained_variance | 0.475 | +| learning_rate | 4.2e-05 | +| loss | -0.0316 | +| n_updates | 81388 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000213 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1396 | +| iterations | 16394 | +| time_elapsed | 24040 | +| total_timesteps | 33574912 | +| train/ | | +| approx_kl | 0.011354957 | +| clip_fraction | 0.313 | +| clip_range | 0.0666 | +| entropy_loss | -6.25 | +| explained_variance | 0.41 | +| learning_rate | 4.2e-05 | +| loss | -0.0329 | +| n_updates | 81392 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000173 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1396 | +| iterations | 16395 | +| time_elapsed | 24042 | +| total_timesteps | 33576960 | +| train/ | | +| approx_kl | 0.012605285 | +| clip_fraction | 0.367 | +| clip_range | 0.0666 | +| entropy_loss | -6.65 | +| explained_variance | -0.216 | +| learning_rate | 4.2e-05 | +| loss | -0.0267 | +| n_updates | 81396 | +| policy_gradient_loss | -0.0205 | +| value_loss | 8.52e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1396 | +| iterations | 16396 | +| time_elapsed | 24043 | +| total_timesteps | 33579008 | +| train/ | | +| approx_kl | 0.01178822 | +| clip_fraction | 0.332 | +| clip_range | 0.0666 | +| entropy_loss | -6.46 | +| explained_variance | 0.358 | +| learning_rate | 4.2e-05 | +| loss | -0.0308 | +| n_updates | 81400 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000136 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1396 | +| iterations | 16397 | +| time_elapsed | 24045 | +| total_timesteps | 33581056 | +| train/ | | +| approx_kl | 0.014502144 | +| clip_fraction | 0.316 | +| clip_range | 0.0666 | +| entropy_loss | -6.03 | +| explained_variance | 0.452 | +| learning_rate | 4.2e-05 | +| loss | -0.0233 | +| n_updates | 81404 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000258 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1396 | +| iterations | 16398 | +| time_elapsed | 24046 | +| total_timesteps | 33583104 | +| train/ | | +| approx_kl | 0.010977427 | +| clip_fraction | 0.306 | +| clip_range | 0.0666 | +| entropy_loss | -6.51 | +| explained_variance | -0.0571 | +| learning_rate | 4.2e-05 | +| loss | -0.0228 | +| n_updates | 81408 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000223 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1396 | +| iterations | 16399 | +| time_elapsed | 24048 | +| total_timesteps | 33585152 | +| train/ | | +| approx_kl | 0.0125574125 | +| clip_fraction | 0.342 | +| clip_range | 0.0666 | +| entropy_loss | -5.7 | +| explained_variance | 0.851 | +| learning_rate | 4.2e-05 | +| loss | -0.0371 | +| n_updates | 81412 | +| policy_gradient_loss | -0.0223 | +| value_loss | 5.46e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1396 | +| iterations | 16400 | +| time_elapsed | 24049 | +| total_timesteps | 33587200 | +| train/ | | +| approx_kl | 0.014580178 | +| clip_fraction | 0.34 | +| clip_range | 0.0666 | +| entropy_loss | -5.66 | +| explained_variance | 0.428 | +| learning_rate | 4.2e-05 | +| loss | -0.0277 | +| n_updates | 81416 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000211 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1396 | +| iterations | 16401 | +| time_elapsed | 24051 | +| total_timesteps | 33589248 | +| train/ | | +| approx_kl | 0.01379987 | +| clip_fraction | 0.33 | +| clip_range | 0.0666 | +| entropy_loss | -5.42 | +| explained_variance | 0.695 | +| learning_rate | 4.2e-05 | +| loss | -0.0287 | +| n_updates | 81420 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000105 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1396 | +| iterations | 16402 | +| time_elapsed | 24052 | +| total_timesteps | 33591296 | +| train/ | | +| approx_kl | 0.012292424 | +| clip_fraction | 0.35 | +| clip_range | 0.0666 | +| entropy_loss | -6.45 | +| explained_variance | 0.418 | +| learning_rate | 4.2e-05 | +| loss | -0.0325 | +| n_updates | 81424 | +| policy_gradient_loss | -0.0183 | +| value_loss | 7.14e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1396 | +| iterations | 16403 | +| time_elapsed | 24054 | +| total_timesteps | 33593344 | +| train/ | | +| approx_kl | 0.011991865 | +| clip_fraction | 0.341 | +| clip_range | 0.0666 | +| entropy_loss | -6.46 | +| explained_variance | 0.499 | +| learning_rate | 4.2e-05 | +| loss | -0.0263 | +| n_updates | 81428 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000113 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1396 | +| iterations | 16404 | +| time_elapsed | 24055 | +| total_timesteps | 33595392 | +| train/ | | +| approx_kl | 0.011488641 | +| clip_fraction | 0.324 | +| clip_range | 0.0666 | +| entropy_loss | -6.15 | +| explained_variance | 0.604 | +| learning_rate | 4.2e-05 | +| loss | -0.0309 | +| n_updates | 81432 | +| policy_gradient_loss | -0.0182 | +| value_loss | 7.75e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1396 | +| iterations | 16405 | +| time_elapsed | 24057 | +| total_timesteps | 33597440 | +| train/ | | +| approx_kl | 0.011571998 | +| clip_fraction | 0.293 | +| clip_range | 0.0666 | +| entropy_loss | -6.25 | +| explained_variance | 0.588 | +| learning_rate | 4.2e-05 | +| loss | -0.0258 | +| n_updates | 81436 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000113 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1396 | +| iterations | 16406 | +| time_elapsed | 24058 | +| total_timesteps | 33599488 | +| train/ | | +| approx_kl | 0.012067448 | +| clip_fraction | 0.332 | +| clip_range | 0.0666 | +| entropy_loss | -6.32 | +| explained_variance | 0.461 | +| learning_rate | 4.2e-05 | +| loss | -0.026 | +| n_updates | 81440 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.00013 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1396 | +| iterations | 16407 | +| time_elapsed | 24060 | +| total_timesteps | 33601536 | +| train/ | | +| approx_kl | 0.009083901 | +| clip_fraction | 0.288 | +| clip_range | 0.0666 | +| entropy_loss | -5.73 | +| explained_variance | 0.53 | +| learning_rate | 4.2e-05 | +| loss | -0.019 | +| n_updates | 81444 | +| policy_gradient_loss | -0.0137 | +| value_loss | 0.000194 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1396 | +| iterations | 16408 | +| time_elapsed | 24061 | +| total_timesteps | 33603584 | +| train/ | | +| approx_kl | 0.012886848 | +| clip_fraction | 0.32 | +| clip_range | 0.0666 | +| entropy_loss | -5.58 | +| explained_variance | 0.503 | +| learning_rate | 4.2e-05 | +| loss | -0.0261 | +| n_updates | 81448 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000154 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1396 | +| iterations | 16409 | +| time_elapsed | 24063 | +| total_timesteps | 33605632 | +| train/ | | +| approx_kl | 0.01623789 | +| clip_fraction | 0.363 | +| clip_range | 0.0666 | +| entropy_loss | -6.12 | +| explained_variance | 0.424 | +| learning_rate | 4.2e-05 | +| loss | -0.0295 | +| n_updates | 81452 | +| policy_gradient_loss | -0.0184 | +| value_loss | 8.08e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1396 | +| iterations | 16410 | +| time_elapsed | 24064 | +| total_timesteps | 33607680 | +| train/ | | +| approx_kl | 0.016335495 | +| clip_fraction | 0.34 | +| clip_range | 0.0666 | +| entropy_loss | -6.22 | +| explained_variance | -0.136 | +| learning_rate | 4.2e-05 | +| loss | -0.0273 | +| n_updates | 81456 | +| policy_gradient_loss | -0.0192 | +| value_loss | 7.66e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1396 | +| iterations | 16411 | +| time_elapsed | 24066 | +| total_timesteps | 33609728 | +| train/ | | +| approx_kl | 0.01403315 | +| clip_fraction | 0.309 | +| clip_range | 0.0666 | +| entropy_loss | -6.34 | +| explained_variance | 0.276 | +| learning_rate | 4.2e-05 | +| loss | -0.0226 | +| n_updates | 81460 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.00023 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1396 | +| iterations | 16412 | +| time_elapsed | 24068 | +| total_timesteps | 33611776 | +| train/ | | +| approx_kl | 0.014584559 | +| clip_fraction | 0.347 | +| clip_range | 0.0666 | +| entropy_loss | -5.75 | +| explained_variance | 0.653 | +| learning_rate | 4.2e-05 | +| loss | -0.026 | +| n_updates | 81464 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000113 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1396 | +| iterations | 16413 | +| time_elapsed | 24069 | +| total_timesteps | 33613824 | +| train/ | | +| approx_kl | 0.010064206 | +| clip_fraction | 0.306 | +| clip_range | 0.0666 | +| entropy_loss | -6.26 | +| explained_variance | 0.439 | +| learning_rate | 4.2e-05 | +| loss | -0.0236 | +| n_updates | 81468 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000177 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.315 | +| time/ | | +| fps | 1396 | +| iterations | 16414 | +| time_elapsed | 24071 | +| total_timesteps | 33615872 | +| train/ | | +| approx_kl | 0.009548401 | +| clip_fraction | 0.314 | +| clip_range | 0.0666 | +| entropy_loss | -6.59 | +| explained_variance | 0.124 | +| learning_rate | 4.2e-05 | +| loss | -0.0264 | +| n_updates | 81472 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000293 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1396 | +| iterations | 16415 | +| time_elapsed | 24072 | +| total_timesteps | 33617920 | +| train/ | | +| approx_kl | 0.011777222 | +| clip_fraction | 0.33 | +| clip_range | 0.0666 | +| entropy_loss | -5.97 | +| explained_variance | 0.721 | +| learning_rate | 4.2e-05 | +| loss | -0.0307 | +| n_updates | 81476 | +| policy_gradient_loss | -0.0186 | +| value_loss | 9.45e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1396 | +| iterations | 16416 | +| time_elapsed | 24074 | +| total_timesteps | 33619968 | +| train/ | | +| approx_kl | 0.010888742 | +| clip_fraction | 0.296 | +| clip_range | 0.0666 | +| entropy_loss | -5.61 | +| explained_variance | 0.637 | +| learning_rate | 4.2e-05 | +| loss | -0.0247 | +| n_updates | 81480 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.00012 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1396 | +| iterations | 16417 | +| time_elapsed | 24075 | +| total_timesteps | 33622016 | +| train/ | | +| approx_kl | 0.010338714 | +| clip_fraction | 0.312 | +| clip_range | 0.0666 | +| entropy_loss | -5.5 | +| explained_variance | 0.424 | +| learning_rate | 4.2e-05 | +| loss | -0.0248 | +| n_updates | 81484 | +| policy_gradient_loss | -0.0141 | +| value_loss | 0.000324 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1396 | +| iterations | 16418 | +| time_elapsed | 24077 | +| total_timesteps | 33624064 | +| train/ | | +| approx_kl | 0.015180536 | +| clip_fraction | 0.358 | +| clip_range | 0.0666 | +| entropy_loss | -5.26 | +| explained_variance | 0.62 | +| learning_rate | 4.2e-05 | +| loss | -0.0311 | +| n_updates | 81488 | +| policy_gradient_loss | -0.0195 | +| value_loss | 7.23e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1396 | +| iterations | 16419 | +| time_elapsed | 24078 | +| total_timesteps | 33626112 | +| train/ | | +| approx_kl | 0.015841361 | +| clip_fraction | 0.377 | +| clip_range | 0.0666 | +| entropy_loss | -6.32 | +| explained_variance | -0.207 | +| learning_rate | 4.2e-05 | +| loss | -0.0371 | +| n_updates | 81492 | +| policy_gradient_loss | -0.0218 | +| value_loss | 7.96e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1396 | +| iterations | 16420 | +| time_elapsed | 24080 | +| total_timesteps | 33628160 | +| train/ | | +| approx_kl | 0.015534231 | +| clip_fraction | 0.35 | +| clip_range | 0.0666 | +| entropy_loss | -6.49 | +| explained_variance | 0.291 | +| learning_rate | 4.2e-05 | +| loss | -0.0301 | +| n_updates | 81496 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000209 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1396 | +| iterations | 16421 | +| time_elapsed | 24081 | +| total_timesteps | 33630208 | +| train/ | | +| approx_kl | 0.017354812 | +| clip_fraction | 0.383 | +| clip_range | 0.0666 | +| entropy_loss | -5.7 | +| explained_variance | 0.489 | +| learning_rate | 4.2e-05 | +| loss | -0.0287 | +| n_updates | 81500 | +| policy_gradient_loss | -0.0214 | +| value_loss | 7.11e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1396 | +| iterations | 16422 | +| time_elapsed | 24083 | +| total_timesteps | 33632256 | +| train/ | | +| approx_kl | 0.01406467 | +| clip_fraction | 0.361 | +| clip_range | 0.0666 | +| entropy_loss | -5.89 | +| explained_variance | 0.532 | +| learning_rate | 4.2e-05 | +| loss | -0.0326 | +| n_updates | 81504 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000124 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 1396 | +| iterations | 16423 | +| time_elapsed | 24084 | +| total_timesteps | 33634304 | +| train/ | | +| approx_kl | 0.01355885 | +| clip_fraction | 0.338 | +| clip_range | 0.0666 | +| entropy_loss | -5.77 | +| explained_variance | 0.559 | +| learning_rate | 4.2e-05 | +| loss | -0.0314 | +| n_updates | 81508 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000108 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1396 | +| iterations | 16424 | +| time_elapsed | 24086 | +| total_timesteps | 33636352 | +| train/ | | +| approx_kl | 0.013407014 | +| clip_fraction | 0.353 | +| clip_range | 0.0666 | +| entropy_loss | -5.74 | +| explained_variance | 0.51 | +| learning_rate | 4.2e-05 | +| loss | -0.0295 | +| n_updates | 81512 | +| policy_gradient_loss | -0.0185 | +| value_loss | 8.5e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1396 | +| iterations | 16425 | +| time_elapsed | 24087 | +| total_timesteps | 33638400 | +| train/ | | +| approx_kl | 0.011645114 | +| clip_fraction | 0.304 | +| clip_range | 0.0666 | +| entropy_loss | -6.22 | +| explained_variance | 0.321 | +| learning_rate | 4.2e-05 | +| loss | -0.0234 | +| n_updates | 81516 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000259 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1396 | +| iterations | 16426 | +| time_elapsed | 24089 | +| total_timesteps | 33640448 | +| train/ | | +| approx_kl | 0.011454207 | +| clip_fraction | 0.324 | +| clip_range | 0.0666 | +| entropy_loss | -6.03 | +| explained_variance | 0.506 | +| learning_rate | 4.2e-05 | +| loss | -0.0288 | +| n_updates | 81520 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000197 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1396 | +| iterations | 16427 | +| time_elapsed | 24090 | +| total_timesteps | 33642496 | +| train/ | | +| approx_kl | 0.014539374 | +| clip_fraction | 0.38 | +| clip_range | 0.0666 | +| entropy_loss | -6.18 | +| explained_variance | -0.271 | +| learning_rate | 4.2e-05 | +| loss | -0.0361 | +| n_updates | 81524 | +| policy_gradient_loss | -0.0222 | +| value_loss | 8.55e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1396 | +| iterations | 16428 | +| time_elapsed | 24092 | +| total_timesteps | 33644544 | +| train/ | | +| approx_kl | 0.012081724 | +| clip_fraction | 0.361 | +| clip_range | 0.0666 | +| entropy_loss | -6.62 | +| explained_variance | 0.316 | +| learning_rate | 4.2e-05 | +| loss | -0.0321 | +| n_updates | 81528 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000121 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1396 | +| iterations | 16429 | +| time_elapsed | 24094 | +| total_timesteps | 33646592 | +| train/ | | +| approx_kl | 0.012105152 | +| clip_fraction | 0.333 | +| clip_range | 0.0666 | +| entropy_loss | -6.61 | +| explained_variance | -0.0131 | +| learning_rate | 4.2e-05 | +| loss | -0.028 | +| n_updates | 81532 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000151 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 1396 | +| iterations | 16430 | +| time_elapsed | 24095 | +| total_timesteps | 33648640 | +| train/ | | +| approx_kl | 0.010365013 | +| clip_fraction | 0.332 | +| clip_range | 0.0666 | +| entropy_loss | -6.48 | +| explained_variance | 0.296 | +| learning_rate | 4.2e-05 | +| loss | -0.0271 | +| n_updates | 81536 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000109 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 1396 | +| iterations | 16431 | +| time_elapsed | 24097 | +| total_timesteps | 33650688 | +| train/ | | +| approx_kl | 0.010829929 | +| clip_fraction | 0.335 | +| clip_range | 0.0666 | +| entropy_loss | -6.22 | +| explained_variance | 0.66 | +| learning_rate | 4.2e-05 | +| loss | -0.0304 | +| n_updates | 81540 | +| policy_gradient_loss | -0.0182 | +| value_loss | 7.98e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 1396 | +| iterations | 16432 | +| time_elapsed | 24098 | +| total_timesteps | 33652736 | +| train/ | | +| approx_kl | 0.0123967435 | +| clip_fraction | 0.303 | +| clip_range | 0.0666 | +| entropy_loss | -5.91 | +| explained_variance | 0.517 | +| learning_rate | 4.2e-05 | +| loss | -0.0217 | +| n_updates | 81544 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.000142 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.3 | +| time/ | | +| fps | 1396 | +| iterations | 16433 | +| time_elapsed | 24100 | +| total_timesteps | 33654784 | +| train/ | | +| approx_kl | 0.010749791 | +| clip_fraction | 0.316 | +| clip_range | 0.0666 | +| entropy_loss | -6.01 | +| explained_variance | 0.609 | +| learning_rate | 4.2e-05 | +| loss | -0.0273 | +| n_updates | 81548 | +| policy_gradient_loss | -0.0156 | +| value_loss | 9e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.3 | +| time/ | | +| fps | 1396 | +| iterations | 16434 | +| time_elapsed | 24101 | +| total_timesteps | 33656832 | +| train/ | | +| approx_kl | 0.010858139 | +| clip_fraction | 0.295 | +| clip_range | 0.0666 | +| entropy_loss | -5.76 | +| explained_variance | 0.518 | +| learning_rate | 4.2e-05 | +| loss | -0.0236 | +| n_updates | 81552 | +| policy_gradient_loss | -0.0146 | +| value_loss | 0.000223 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 1396 | +| iterations | 16435 | +| time_elapsed | 24103 | +| total_timesteps | 33658880 | +| train/ | | +| approx_kl | 0.010914199 | +| clip_fraction | 0.336 | +| clip_range | 0.0666 | +| entropy_loss | -6.28 | +| explained_variance | 0.153 | +| learning_rate | 4.2e-05 | +| loss | -0.0254 | +| n_updates | 81556 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000186 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1396 | +| iterations | 16436 | +| time_elapsed | 24104 | +| total_timesteps | 33660928 | +| train/ | | +| approx_kl | 0.011276129 | +| clip_fraction | 0.33 | +| clip_range | 0.0666 | +| entropy_loss | -6.46 | +| explained_variance | 0.216 | +| learning_rate | 4.2e-05 | +| loss | -0.031 | +| n_updates | 81560 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000298 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1396 | +| iterations | 16437 | +| time_elapsed | 24106 | +| total_timesteps | 33662976 | +| train/ | | +| approx_kl | 0.012068673 | +| clip_fraction | 0.341 | +| clip_range | 0.0666 | +| entropy_loss | -6.09 | +| explained_variance | 0.271 | +| learning_rate | 4.2e-05 | +| loss | -0.0312 | +| n_updates | 81564 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000212 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1396 | +| iterations | 16438 | +| time_elapsed | 24107 | +| total_timesteps | 33665024 | +| train/ | | +| approx_kl | 0.012144584 | +| clip_fraction | 0.32 | +| clip_range | 0.0666 | +| entropy_loss | -5.24 | +| explained_variance | 0.562 | +| learning_rate | 4.2e-05 | +| loss | -0.0248 | +| n_updates | 81568 | +| policy_gradient_loss | -0.0145 | +| value_loss | 0.000261 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1396 | +| iterations | 16439 | +| time_elapsed | 24109 | +| total_timesteps | 33667072 | +| train/ | | +| approx_kl | 0.013832582 | +| clip_fraction | 0.353 | +| clip_range | 0.0666 | +| entropy_loss | -5.72 | +| explained_variance | 0.54 | +| learning_rate | 4.2e-05 | +| loss | -0.031 | +| n_updates | 81572 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000122 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1396 | +| iterations | 16440 | +| time_elapsed | 24110 | +| total_timesteps | 33669120 | +| train/ | | +| approx_kl | 0.013066288 | +| clip_fraction | 0.33 | +| clip_range | 0.0666 | +| entropy_loss | -6.18 | +| explained_variance | 0.377 | +| learning_rate | 4.2e-05 | +| loss | -0.0235 | +| n_updates | 81576 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000279 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1396 | +| iterations | 16441 | +| time_elapsed | 24112 | +| total_timesteps | 33671168 | +| train/ | | +| approx_kl | 0.0157592 | +| clip_fraction | 0.36 | +| clip_range | 0.0666 | +| entropy_loss | -6.35 | +| explained_variance | -0.351 | +| learning_rate | 4.2e-05 | +| loss | -0.0288 | +| n_updates | 81580 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000126 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1396 | +| iterations | 16442 | +| time_elapsed | 24113 | +| total_timesteps | 33673216 | +| train/ | | +| approx_kl | 0.014522882 | +| clip_fraction | 0.365 | +| clip_range | 0.0666 | +| entropy_loss | -6.47 | +| explained_variance | 0.148 | +| learning_rate | 4.2e-05 | +| loss | -0.0325 | +| n_updates | 81584 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000102 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1396 | +| iterations | 16443 | +| time_elapsed | 24115 | +| total_timesteps | 33675264 | +| train/ | | +| approx_kl | 0.012149323 | +| clip_fraction | 0.334 | +| clip_range | 0.0666 | +| entropy_loss | -6.5 | +| explained_variance | 0.322 | +| learning_rate | 4.2e-05 | +| loss | -0.027 | +| n_updates | 81588 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000167 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1396 | +| iterations | 16444 | +| time_elapsed | 24116 | +| total_timesteps | 33677312 | +| train/ | | +| approx_kl | 0.012472209 | +| clip_fraction | 0.332 | +| clip_range | 0.0666 | +| entropy_loss | -6.15 | +| explained_variance | 0.677 | +| learning_rate | 4.2e-05 | +| loss | -0.0237 | +| n_updates | 81592 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.00011 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1396 | +| iterations | 16445 | +| time_elapsed | 24118 | +| total_timesteps | 33679360 | +| train/ | | +| approx_kl | 0.013534785 | +| clip_fraction | 0.326 | +| clip_range | 0.0666 | +| entropy_loss | -5.24 | +| explained_variance | 0.477 | +| learning_rate | 4.2e-05 | +| loss | -0.0294 | +| n_updates | 81596 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.000203 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1396 | +| iterations | 16446 | +| time_elapsed | 24119 | +| total_timesteps | 33681408 | +| train/ | | +| approx_kl | 0.011937002 | +| clip_fraction | 0.308 | +| clip_range | 0.0666 | +| entropy_loss | -5.63 | +| explained_variance | 0.451 | +| learning_rate | 4.2e-05 | +| loss | -0.0287 | +| n_updates | 81600 | +| policy_gradient_loss | -0.0142 | +| value_loss | 0.000246 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1396 | +| iterations | 16447 | +| time_elapsed | 24121 | +| total_timesteps | 33683456 | +| train/ | | +| approx_kl | 0.012141426 | +| clip_fraction | 0.32 | +| clip_range | 0.0666 | +| entropy_loss | -5 | +| explained_variance | 0.706 | +| learning_rate | 4.2e-05 | +| loss | -0.0234 | +| n_updates | 81604 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000158 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1396 | +| iterations | 16448 | +| time_elapsed | 24122 | +| total_timesteps | 33685504 | +| train/ | | +| approx_kl | 0.0118471375 | +| clip_fraction | 0.334 | +| clip_range | 0.0666 | +| entropy_loss | -5.39 | +| explained_variance | 0.499 | +| learning_rate | 4.2e-05 | +| loss | -0.0294 | +| n_updates | 81608 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000179 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1396 | +| iterations | 16449 | +| time_elapsed | 24124 | +| total_timesteps | 33687552 | +| train/ | | +| approx_kl | 0.014778125 | +| clip_fraction | 0.358 | +| clip_range | 0.0666 | +| entropy_loss | -6.22 | +| explained_variance | 0.391 | +| learning_rate | 4.2e-05 | +| loss | -0.029 | +| n_updates | 81612 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000168 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1396 | +| iterations | 16450 | +| time_elapsed | 24126 | +| total_timesteps | 33689600 | +| train/ | | +| approx_kl | 0.012793528 | +| clip_fraction | 0.354 | +| clip_range | 0.0666 | +| entropy_loss | -6.45 | +| explained_variance | -0.0295 | +| learning_rate | 4.2e-05 | +| loss | -0.031 | +| n_updates | 81616 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000142 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1396 | +| iterations | 16451 | +| time_elapsed | 24127 | +| total_timesteps | 33691648 | +| train/ | | +| approx_kl | 0.012256088 | +| clip_fraction | 0.337 | +| clip_range | 0.0666 | +| entropy_loss | -6.42 | +| explained_variance | 0.157 | +| learning_rate | 4.2e-05 | +| loss | -0.0205 | +| n_updates | 81620 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000269 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1396 | +| iterations | 16452 | +| time_elapsed | 24129 | +| total_timesteps | 33693696 | +| train/ | | +| approx_kl | 0.013380485 | +| clip_fraction | 0.356 | +| clip_range | 0.0666 | +| entropy_loss | -6.33 | +| explained_variance | 0.0435 | +| learning_rate | 4.2e-05 | +| loss | -0.0341 | +| n_updates | 81624 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000169 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1396 | +| iterations | 16453 | +| time_elapsed | 24130 | +| total_timesteps | 33695744 | +| train/ | | +| approx_kl | 0.014829552 | +| clip_fraction | 0.369 | +| clip_range | 0.0666 | +| entropy_loss | -6.04 | +| explained_variance | 0.319 | +| learning_rate | 4.2e-05 | +| loss | -0.0334 | +| n_updates | 81628 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000134 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1396 | +| iterations | 16454 | +| time_elapsed | 24132 | +| total_timesteps | 33697792 | +| train/ | | +| approx_kl | 0.016852345 | +| clip_fraction | 0.332 | +| clip_range | 0.0666 | +| entropy_loss | -5.58 | +| explained_variance | 0.37 | +| learning_rate | 4.2e-05 | +| loss | -0.0263 | +| n_updates | 81632 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.00031 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1396 | +| iterations | 16455 | +| time_elapsed | 24133 | +| total_timesteps | 33699840 | +| train/ | | +| approx_kl | 0.01423853 | +| clip_fraction | 0.352 | +| clip_range | 0.0666 | +| entropy_loss | -5.03 | +| explained_variance | 0.682 | +| learning_rate | 4.2e-05 | +| loss | -0.0322 | +| n_updates | 81636 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.00015 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1396 | +| iterations | 16456 | +| time_elapsed | 24135 | +| total_timesteps | 33701888 | +| train/ | | +| approx_kl | 0.013244523 | +| clip_fraction | 0.367 | +| clip_range | 0.0666 | +| entropy_loss | -5.13 | +| explained_variance | 0.688 | +| learning_rate | 4.2e-05 | +| loss | -0.0295 | +| n_updates | 81640 | +| policy_gradient_loss | -0.0201 | +| value_loss | 8.05e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1396 | +| iterations | 16457 | +| time_elapsed | 24136 | +| total_timesteps | 33703936 | +| train/ | | +| approx_kl | 0.014697506 | +| clip_fraction | 0.362 | +| clip_range | 0.0666 | +| entropy_loss | -5.74 | +| explained_variance | 0.472 | +| learning_rate | 4.2e-05 | +| loss | -0.0296 | +| n_updates | 81644 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000106 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1396 | +| iterations | 16458 | +| time_elapsed | 24138 | +| total_timesteps | 33705984 | +| train/ | | +| approx_kl | 0.013225967 | +| clip_fraction | 0.344 | +| clip_range | 0.0666 | +| entropy_loss | -5.69 | +| explained_variance | 0.474 | +| learning_rate | 4.2e-05 | +| loss | -0.0333 | +| n_updates | 81648 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000123 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1396 | +| iterations | 16459 | +| time_elapsed | 24139 | +| total_timesteps | 33708032 | +| train/ | | +| approx_kl | 0.01710319 | +| clip_fraction | 0.361 | +| clip_range | 0.0666 | +| entropy_loss | -6.05 | +| explained_variance | 0.328 | +| learning_rate | 4.2e-05 | +| loss | -0.0343 | +| n_updates | 81652 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000146 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1396 | +| iterations | 16460 | +| time_elapsed | 24141 | +| total_timesteps | 33710080 | +| train/ | | +| approx_kl | 0.015210937 | +| clip_fraction | 0.347 | +| clip_range | 0.0666 | +| entropy_loss | -5.94 | +| explained_variance | -0.0204 | +| learning_rate | 4.2e-05 | +| loss | -0.0303 | +| n_updates | 81656 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000129 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1396 | +| iterations | 16461 | +| time_elapsed | 24142 | +| total_timesteps | 33712128 | +| train/ | | +| approx_kl | 0.017579902 | +| clip_fraction | 0.34 | +| clip_range | 0.0666 | +| entropy_loss | -5.64 | +| explained_variance | 0.49 | +| learning_rate | 4.2e-05 | +| loss | -0.0275 | +| n_updates | 81660 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000185 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1396 | +| iterations | 16462 | +| time_elapsed | 24144 | +| total_timesteps | 33714176 | +| train/ | | +| approx_kl | 0.012933405 | +| clip_fraction | 0.357 | +| clip_range | 0.0666 | +| entropy_loss | -6.03 | +| explained_variance | 0.496 | +| learning_rate | 4.2e-05 | +| loss | -0.0365 | +| n_updates | 81664 | +| policy_gradient_loss | -0.0204 | +| value_loss | 7.26e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1396 | +| iterations | 16463 | +| time_elapsed | 24145 | +| total_timesteps | 33716224 | +| train/ | | +| approx_kl | 0.012278318 | +| clip_fraction | 0.328 | +| clip_range | 0.0666 | +| entropy_loss | -6.76 | +| explained_variance | -0.00163 | +| learning_rate | 4.2e-05 | +| loss | -0.0265 | +| n_updates | 81668 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000166 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1396 | +| iterations | 16464 | +| time_elapsed | 24147 | +| total_timesteps | 33718272 | +| train/ | | +| approx_kl | 0.010473017 | +| clip_fraction | 0.303 | +| clip_range | 0.0666 | +| entropy_loss | -6.2 | +| explained_variance | 0.506 | +| learning_rate | 4.2e-05 | +| loss | -0.0238 | +| n_updates | 81672 | +| policy_gradient_loss | -0.0142 | +| value_loss | 0.000218 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1396 | +| iterations | 16465 | +| time_elapsed | 24148 | +| total_timesteps | 33720320 | +| train/ | | +| approx_kl | 0.01195232 | +| clip_fraction | 0.328 | +| clip_range | 0.0666 | +| entropy_loss | -5.69 | +| explained_variance | 0.544 | +| learning_rate | 4.2e-05 | +| loss | -0.0303 | +| n_updates | 81676 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000146 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1396 | +| iterations | 16466 | +| time_elapsed | 24150 | +| total_timesteps | 33722368 | +| train/ | | +| approx_kl | 0.011349989 | +| clip_fraction | 0.331 | +| clip_range | 0.0666 | +| entropy_loss | -6.34 | +| explained_variance | 0.421 | +| learning_rate | 4.2e-05 | +| loss | -0.0302 | +| n_updates | 81680 | +| policy_gradient_loss | -0.0186 | +| value_loss | 8.49e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1396 | +| iterations | 16467 | +| time_elapsed | 24152 | +| total_timesteps | 33724416 | +| train/ | | +| approx_kl | 0.011789484 | +| clip_fraction | 0.324 | +| clip_range | 0.0666 | +| entropy_loss | -6.41 | +| explained_variance | 0.271 | +| learning_rate | 4.2e-05 | +| loss | -0.018 | +| n_updates | 81684 | +| policy_gradient_loss | -0.0146 | +| value_loss | 0.00021 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1396 | +| iterations | 16468 | +| time_elapsed | 24153 | +| total_timesteps | 33726464 | +| train/ | | +| approx_kl | 0.016171498 | +| clip_fraction | 0.37 | +| clip_range | 0.0666 | +| entropy_loss | -5.65 | +| explained_variance | 0.808 | +| learning_rate | 4.2e-05 | +| loss | -0.0388 | +| n_updates | 81688 | +| policy_gradient_loss | -0.0225 | +| value_loss | 6.63e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1396 | +| iterations | 16469 | +| time_elapsed | 24155 | +| total_timesteps | 33728512 | +| train/ | | +| approx_kl | 0.01482391 | +| clip_fraction | 0.35 | +| clip_range | 0.0666 | +| entropy_loss | -5.67 | +| explained_variance | 0.328 | +| learning_rate | 4.2e-05 | +| loss | -0.0296 | +| n_updates | 81692 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000126 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1396 | +| iterations | 16470 | +| time_elapsed | 24156 | +| total_timesteps | 33730560 | +| train/ | | +| approx_kl | 0.013648342 | +| clip_fraction | 0.344 | +| clip_range | 0.0666 | +| entropy_loss | -6.41 | +| explained_variance | 0.372 | +| learning_rate | 4.2e-05 | +| loss | -0.0324 | +| n_updates | 81696 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.00011 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1396 | +| iterations | 16471 | +| time_elapsed | 24158 | +| total_timesteps | 33732608 | +| train/ | | +| approx_kl | 0.014944535 | +| clip_fraction | 0.34 | +| clip_range | 0.0666 | +| entropy_loss | -5.83 | +| explained_variance | 0.392 | +| learning_rate | 4.2e-05 | +| loss | -0.0267 | +| n_updates | 81700 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000233 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1396 | +| iterations | 16472 | +| time_elapsed | 24159 | +| total_timesteps | 33734656 | +| train/ | | +| approx_kl | 0.015003977 | +| clip_fraction | 0.361 | +| clip_range | 0.0666 | +| entropy_loss | -5.57 | +| explained_variance | 0.606 | +| learning_rate | 4.2e-05 | +| loss | -0.0291 | +| n_updates | 81704 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000145 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1396 | +| iterations | 16473 | +| time_elapsed | 24161 | +| total_timesteps | 33736704 | +| train/ | | +| approx_kl | 0.013349325 | +| clip_fraction | 0.326 | +| clip_range | 0.0666 | +| entropy_loss | -5.43 | +| explained_variance | 0.554 | +| learning_rate | 4.2e-05 | +| loss | -0.0262 | +| n_updates | 81708 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000142 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1396 | +| iterations | 16474 | +| time_elapsed | 24162 | +| total_timesteps | 33738752 | +| train/ | | +| approx_kl | 0.01278266 | +| clip_fraction | 0.363 | +| clip_range | 0.0666 | +| entropy_loss | -5.98 | +| explained_variance | 0.126 | +| learning_rate | 4.2e-05 | +| loss | -0.0324 | +| n_updates | 81712 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000122 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1396 | +| iterations | 16475 | +| time_elapsed | 24164 | +| total_timesteps | 33740800 | +| train/ | | +| approx_kl | 0.0135698365 | +| clip_fraction | 0.371 | +| clip_range | 0.0666 | +| entropy_loss | -6.15 | +| explained_variance | 0.41 | +| learning_rate | 4.2e-05 | +| loss | -0.0306 | +| n_updates | 81716 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000141 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1396 | +| iterations | 16476 | +| time_elapsed | 24165 | +| total_timesteps | 33742848 | +| train/ | | +| approx_kl | 0.013170857 | +| clip_fraction | 0.358 | +| clip_range | 0.0666 | +| entropy_loss | -6.41 | +| explained_variance | 0.0596 | +| learning_rate | 4.2e-05 | +| loss | -0.0301 | +| n_updates | 81720 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000136 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1396 | +| iterations | 16477 | +| time_elapsed | 24167 | +| total_timesteps | 33744896 | +| train/ | | +| approx_kl | 0.0137839 | +| clip_fraction | 0.323 | +| clip_range | 0.0666 | +| entropy_loss | -5.89 | +| explained_variance | 0.258 | +| learning_rate | 4.2e-05 | +| loss | -0.024 | +| n_updates | 81724 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.000281 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1396 | +| iterations | 16478 | +| time_elapsed | 24168 | +| total_timesteps | 33746944 | +| train/ | | +| approx_kl | 0.019909471 | +| clip_fraction | 0.347 | +| clip_range | 0.0666 | +| entropy_loss | -5.98 | +| explained_variance | 0.294 | +| learning_rate | 4.2e-05 | +| loss | -0.0321 | +| n_updates | 81728 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000135 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1396 | +| iterations | 16479 | +| time_elapsed | 24170 | +| total_timesteps | 33748992 | +| train/ | | +| approx_kl | 0.0150412675 | +| clip_fraction | 0.336 | +| clip_range | 0.0666 | +| entropy_loss | -6.04 | +| explained_variance | 0.527 | +| learning_rate | 4.2e-05 | +| loss | -0.032 | +| n_updates | 81732 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000124 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1396 | +| iterations | 16480 | +| time_elapsed | 24171 | +| total_timesteps | 33751040 | +| train/ | | +| approx_kl | 0.013358865 | +| clip_fraction | 0.345 | +| clip_range | 0.0666 | +| entropy_loss | -5.99 | +| explained_variance | 0.63 | +| learning_rate | 4.2e-05 | +| loss | -0.0246 | +| n_updates | 81736 | +| policy_gradient_loss | -0.0177 | +| value_loss | 9.98e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1396 | +| iterations | 16481 | +| time_elapsed | 24173 | +| total_timesteps | 33753088 | +| train/ | | +| approx_kl | 0.012956535 | +| clip_fraction | 0.33 | +| clip_range | 0.0666 | +| entropy_loss | -5.82 | +| explained_variance | 0.376 | +| learning_rate | 4.2e-05 | +| loss | -0.0231 | +| n_updates | 81740 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.00016 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1396 | +| iterations | 16482 | +| time_elapsed | 24175 | +| total_timesteps | 33755136 | +| train/ | | +| approx_kl | 0.013370403 | +| clip_fraction | 0.313 | +| clip_range | 0.0666 | +| entropy_loss | -5.8 | +| explained_variance | 0.433 | +| learning_rate | 4.2e-05 | +| loss | -0.025 | +| n_updates | 81744 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.000154 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1396 | +| iterations | 16483 | +| time_elapsed | 24176 | +| total_timesteps | 33757184 | +| train/ | | +| approx_kl | 0.012951136 | +| clip_fraction | 0.315 | +| clip_range | 0.0666 | +| entropy_loss | -6.33 | +| explained_variance | 0.425 | +| learning_rate | 4.2e-05 | +| loss | -0.0257 | +| n_updates | 81748 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000195 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1396 | +| iterations | 16484 | +| time_elapsed | 24178 | +| total_timesteps | 33759232 | +| train/ | | +| approx_kl | 0.019009607 | +| clip_fraction | 0.325 | +| clip_range | 0.0666 | +| entropy_loss | -6.01 | +| explained_variance | 0.585 | +| learning_rate | 4.2e-05 | +| loss | -0.024 | +| n_updates | 81752 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000164 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1396 | +| iterations | 16485 | +| time_elapsed | 24179 | +| total_timesteps | 33761280 | +| train/ | | +| approx_kl | 0.013676122 | +| clip_fraction | 0.349 | +| clip_range | 0.0666 | +| entropy_loss | -5.91 | +| explained_variance | 0.441 | +| learning_rate | 4.2e-05 | +| loss | -0.0242 | +| n_updates | 81756 | +| policy_gradient_loss | -0.019 | +| value_loss | 8.72e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1396 | +| iterations | 16486 | +| time_elapsed | 24180 | +| total_timesteps | 33763328 | +| train/ | | +| approx_kl | 0.0125186015 | +| clip_fraction | 0.332 | +| clip_range | 0.0666 | +| entropy_loss | -6.12 | +| explained_variance | 0.181 | +| learning_rate | 4.2e-05 | +| loss | -0.0281 | +| n_updates | 81760 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.00022 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1396 | +| iterations | 16487 | +| time_elapsed | 24182 | +| total_timesteps | 33765376 | +| train/ | | +| approx_kl | 0.011566062 | +| clip_fraction | 0.336 | +| clip_range | 0.0666 | +| entropy_loss | -5.53 | +| explained_variance | 0.552 | +| learning_rate | 4.2e-05 | +| loss | -0.0315 | +| n_updates | 81764 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000252 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1396 | +| iterations | 16488 | +| time_elapsed | 24183 | +| total_timesteps | 33767424 | +| train/ | | +| approx_kl | 0.010717194 | +| clip_fraction | 0.332 | +| clip_range | 0.0666 | +| entropy_loss | -5.95 | +| explained_variance | 0.363 | +| learning_rate | 4.2e-05 | +| loss | -0.0331 | +| n_updates | 81768 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000162 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1396 | +| iterations | 16489 | +| time_elapsed | 24185 | +| total_timesteps | 33769472 | +| train/ | | +| approx_kl | 0.010858893 | +| clip_fraction | 0.333 | +| clip_range | 0.0666 | +| entropy_loss | -6.09 | +| explained_variance | 0.409 | +| learning_rate | 4.2e-05 | +| loss | -0.0254 | +| n_updates | 81772 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000231 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1396 | +| iterations | 16490 | +| time_elapsed | 24187 | +| total_timesteps | 33771520 | +| train/ | | +| approx_kl | 0.011876769 | +| clip_fraction | 0.353 | +| clip_range | 0.0666 | +| entropy_loss | -6.54 | +| explained_variance | 0.143 | +| learning_rate | 4.2e-05 | +| loss | -0.0259 | +| n_updates | 81776 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000166 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1396 | +| iterations | 16491 | +| time_elapsed | 24188 | +| total_timesteps | 33773568 | +| train/ | | +| approx_kl | 0.012327265 | +| clip_fraction | 0.337 | +| clip_range | 0.0666 | +| entropy_loss | -6.48 | +| explained_variance | 0.296 | +| learning_rate | 4.2e-05 | +| loss | -0.0285 | +| n_updates | 81780 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000153 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1396 | +| iterations | 16492 | +| time_elapsed | 24190 | +| total_timesteps | 33775616 | +| train/ | | +| approx_kl | 0.0108297765 | +| clip_fraction | 0.344 | +| clip_range | 0.0666 | +| entropy_loss | -6.75 | +| explained_variance | 0.426 | +| learning_rate | 4.2e-05 | +| loss | -0.0166 | +| n_updates | 81784 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000125 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1396 | +| iterations | 16493 | +| time_elapsed | 24191 | +| total_timesteps | 33777664 | +| train/ | | +| approx_kl | 0.012348229 | +| clip_fraction | 0.329 | +| clip_range | 0.0666 | +| entropy_loss | -6.4 | +| explained_variance | 0.185 | +| learning_rate | 4.2e-05 | +| loss | -0.0274 | +| n_updates | 81788 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000145 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1396 | +| iterations | 16494 | +| time_elapsed | 24193 | +| total_timesteps | 33779712 | +| train/ | | +| approx_kl | 0.010282557 | +| clip_fraction | 0.336 | +| clip_range | 0.0666 | +| entropy_loss | -5.96 | +| explained_variance | 0.589 | +| learning_rate | 4.2e-05 | +| loss | -0.022 | +| n_updates | 81792 | +| policy_gradient_loss | -0.0147 | +| value_loss | 0.000114 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1396 | +| iterations | 16495 | +| time_elapsed | 24194 | +| total_timesteps | 33781760 | +| train/ | | +| approx_kl | 0.011449279 | +| clip_fraction | 0.33 | +| clip_range | 0.0666 | +| entropy_loss | -5.61 | +| explained_variance | 0.42 | +| learning_rate | 4.2e-05 | +| loss | -0.0259 | +| n_updates | 81796 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000263 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1396 | +| iterations | 16496 | +| time_elapsed | 24196 | +| total_timesteps | 33783808 | +| train/ | | +| approx_kl | 0.013472428 | +| clip_fraction | 0.343 | +| clip_range | 0.0666 | +| entropy_loss | -5.43 | +| explained_variance | 0.419 | +| learning_rate | 4.2e-05 | +| loss | -0.0258 | +| n_updates | 81800 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000264 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1396 | +| iterations | 16497 | +| time_elapsed | 24197 | +| total_timesteps | 33785856 | +| train/ | | +| approx_kl | 0.013822831 | +| clip_fraction | 0.33 | +| clip_range | 0.0666 | +| entropy_loss | -5.71 | +| explained_variance | 0.684 | +| learning_rate | 4.2e-05 | +| loss | -0.0245 | +| n_updates | 81804 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000124 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1396 | +| iterations | 16498 | +| time_elapsed | 24199 | +| total_timesteps | 33787904 | +| train/ | | +| approx_kl | 0.014190715 | +| clip_fraction | 0.341 | +| clip_range | 0.0666 | +| entropy_loss | -6.13 | +| explained_variance | 0.459 | +| learning_rate | 4.2e-05 | +| loss | -0.0258 | +| n_updates | 81808 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.00018 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1396 | +| iterations | 16499 | +| time_elapsed | 24200 | +| total_timesteps | 33789952 | +| train/ | | +| approx_kl | 0.01314149 | +| clip_fraction | 0.349 | +| clip_range | 0.0666 | +| entropy_loss | -6.21 | +| explained_variance | 0.633 | +| learning_rate | 4.2e-05 | +| loss | -0.0269 | +| n_updates | 81812 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.00011 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1396 | +| iterations | 16500 | +| time_elapsed | 24202 | +| total_timesteps | 33792000 | +| train/ | | +| approx_kl | 0.012276521 | +| clip_fraction | 0.321 | +| clip_range | 0.0666 | +| entropy_loss | -6.34 | +| explained_variance | 0.186 | +| learning_rate | 4.2e-05 | +| loss | -0.0248 | +| n_updates | 81816 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000134 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1396 | +| iterations | 16501 | +| time_elapsed | 24204 | +| total_timesteps | 33794048 | +| train/ | | +| approx_kl | 0.013878579 | +| clip_fraction | 0.352 | +| clip_range | 0.0666 | +| entropy_loss | -6.08 | +| explained_variance | 0.384 | +| learning_rate | 4.2e-05 | +| loss | -0.0216 | +| n_updates | 81820 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000175 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1396 | +| iterations | 16502 | +| time_elapsed | 24205 | +| total_timesteps | 33796096 | +| train/ | | +| approx_kl | 0.012145033 | +| clip_fraction | 0.333 | +| clip_range | 0.0666 | +| entropy_loss | -5.74 | +| explained_variance | 0.378 | +| learning_rate | 4.2e-05 | +| loss | -0.0244 | +| n_updates | 81824 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.00022 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1396 | +| iterations | 16503 | +| time_elapsed | 24207 | +| total_timesteps | 33798144 | +| train/ | | +| approx_kl | 0.009538888 | +| clip_fraction | 0.328 | +| clip_range | 0.0666 | +| entropy_loss | -6.75 | +| explained_variance | -0.0151 | +| learning_rate | 4.2e-05 | +| loss | -0.0286 | +| n_updates | 81828 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000127 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1396 | +| iterations | 16504 | +| time_elapsed | 24208 | +| total_timesteps | 33800192 | +| train/ | | +| approx_kl | 0.0108733345 | +| clip_fraction | 0.301 | +| clip_range | 0.0666 | +| entropy_loss | -6.49 | +| explained_variance | 0.379 | +| learning_rate | 4.2e-05 | +| loss | -0.0257 | +| n_updates | 81832 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000183 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1396 | +| iterations | 16505 | +| time_elapsed | 24210 | +| total_timesteps | 33802240 | +| train/ | | +| approx_kl | 0.01534768 | +| clip_fraction | 0.297 | +| clip_range | 0.0665 | +| entropy_loss | -5.72 | +| explained_variance | 0.407 | +| learning_rate | 4.2e-05 | +| loss | -0.0305 | +| n_updates | 81836 | +| policy_gradient_loss | -0.0146 | +| value_loss | 0.0003 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1396 | +| iterations | 16506 | +| time_elapsed | 24211 | +| total_timesteps | 33804288 | +| train/ | | +| approx_kl | 0.012076221 | +| clip_fraction | 0.316 | +| clip_range | 0.0665 | +| entropy_loss | -5.43 | +| explained_variance | 0.701 | +| learning_rate | 4.2e-05 | +| loss | -0.0309 | +| n_updates | 81840 | +| policy_gradient_loss | -0.0192 | +| value_loss | 8.49e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1396 | +| iterations | 16507 | +| time_elapsed | 24213 | +| total_timesteps | 33806336 | +| train/ | | +| approx_kl | 0.013184506 | +| clip_fraction | 0.368 | +| clip_range | 0.0665 | +| entropy_loss | -5.71 | +| explained_variance | 0.456 | +| learning_rate | 4.2e-05 | +| loss | -0.0238 | +| n_updates | 81844 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000154 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1396 | +| iterations | 16508 | +| time_elapsed | 24214 | +| total_timesteps | 33808384 | +| train/ | | +| approx_kl | 0.01694318 | +| clip_fraction | 0.355 | +| clip_range | 0.0665 | +| entropy_loss | -5.93 | +| explained_variance | 0.475 | +| learning_rate | 4.2e-05 | +| loss | -0.0315 | +| n_updates | 81848 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000171 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1396 | +| iterations | 16509 | +| time_elapsed | 24216 | +| total_timesteps | 33810432 | +| train/ | | +| approx_kl | 0.012286569 | +| clip_fraction | 0.36 | +| clip_range | 0.0665 | +| entropy_loss | -6.66 | +| explained_variance | -0.0075 | +| learning_rate | 4.2e-05 | +| loss | -0.0274 | +| n_updates | 81852 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000183 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1396 | +| iterations | 16510 | +| time_elapsed | 24218 | +| total_timesteps | 33812480 | +| train/ | | +| approx_kl | 0.010628993 | +| clip_fraction | 0.302 | +| clip_range | 0.0665 | +| entropy_loss | -6.16 | +| explained_variance | 0.419 | +| learning_rate | 4.2e-05 | +| loss | -0.0298 | +| n_updates | 81856 | +| policy_gradient_loss | -0.0139 | +| value_loss | 0.000295 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1396 | +| iterations | 16511 | +| time_elapsed | 24219 | +| total_timesteps | 33814528 | +| train/ | | +| approx_kl | 0.016166296 | +| clip_fraction | 0.364 | +| clip_range | 0.0665 | +| entropy_loss | -6 | +| explained_variance | 0.0897 | +| learning_rate | 4.2e-05 | +| loss | -0.0316 | +| n_updates | 81860 | +| policy_gradient_loss | -0.0205 | +| value_loss | 7.04e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1396 | +| iterations | 16512 | +| time_elapsed | 24221 | +| total_timesteps | 33816576 | +| train/ | | +| approx_kl | 0.015978543 | +| clip_fraction | 0.369 | +| clip_range | 0.0665 | +| entropy_loss | -6.4 | +| explained_variance | 0.332 | +| learning_rate | 4.2e-05 | +| loss | -0.0241 | +| n_updates | 81864 | +| policy_gradient_loss | -0.0185 | +| value_loss | 7.46e-05 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1396 | +| iterations | 16513 | +| time_elapsed | 24222 | +| total_timesteps | 33818624 | +| train/ | | +| approx_kl | 0.0167045 | +| clip_fraction | 0.289 | +| clip_range | 0.0665 | +| entropy_loss | -6.7 | +| explained_variance | 0.218 | +| learning_rate | 4.2e-05 | +| loss | -0.0242 | +| n_updates | 81868 | +| policy_gradient_loss | -0.0141 | +| value_loss | 0.000255 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.315 | +| time/ | | +| fps | 1396 | +| iterations | 16514 | +| time_elapsed | 24224 | +| total_timesteps | 33820672 | +| train/ | | +| approx_kl | 0.013741648 | +| clip_fraction | 0.339 | +| clip_range | 0.0665 | +| entropy_loss | -5.88 | +| explained_variance | 0.502 | +| learning_rate | 4.2e-05 | +| loss | -0.0314 | +| n_updates | 81872 | +| policy_gradient_loss | -0.0178 | +| value_loss | 9.06e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.315 | +| time/ | | +| fps | 1396 | +| iterations | 16515 | +| time_elapsed | 24225 | +| total_timesteps | 33822720 | +| train/ | | +| approx_kl | 0.0127150435 | +| clip_fraction | 0.336 | +| clip_range | 0.0665 | +| entropy_loss | -5.87 | +| explained_variance | 0.656 | +| learning_rate | 4.2e-05 | +| loss | -0.0264 | +| n_updates | 81876 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000125 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1396 | +| iterations | 16516 | +| time_elapsed | 24227 | +| total_timesteps | 33824768 | +| train/ | | +| approx_kl | 0.013744694 | +| clip_fraction | 0.323 | +| clip_range | 0.0665 | +| entropy_loss | -5.33 | +| explained_variance | 0.714 | +| learning_rate | 4.2e-05 | +| loss | -0.0279 | +| n_updates | 81880 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000119 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1396 | +| iterations | 16517 | +| time_elapsed | 24228 | +| total_timesteps | 33826816 | +| train/ | | +| approx_kl | 0.010051536 | +| clip_fraction | 0.329 | +| clip_range | 0.0665 | +| entropy_loss | -5.54 | +| explained_variance | 0.689 | +| learning_rate | 4.2e-05 | +| loss | -0.0278 | +| n_updates | 81884 | +| policy_gradient_loss | -0.0173 | +| value_loss | 9.56e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.315 | +| time/ | | +| fps | 1396 | +| iterations | 16518 | +| time_elapsed | 24230 | +| total_timesteps | 33828864 | +| train/ | | +| approx_kl | 0.014950953 | +| clip_fraction | 0.329 | +| clip_range | 0.0665 | +| entropy_loss | -5.99 | +| explained_variance | 0.347 | +| learning_rate | 4.2e-05 | +| loss | -0.027 | +| n_updates | 81888 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000179 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.315 | +| time/ | | +| fps | 1396 | +| iterations | 16519 | +| time_elapsed | 24231 | +| total_timesteps | 33830912 | +| train/ | | +| approx_kl | 0.015425935 | +| clip_fraction | 0.363 | +| clip_range | 0.0665 | +| entropy_loss | -6.09 | +| explained_variance | 0.416 | +| learning_rate | 4.2e-05 | +| loss | -0.0322 | +| n_updates | 81892 | +| policy_gradient_loss | -0.0201 | +| value_loss | 9.63e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.315 | +| time/ | | +| fps | 1396 | +| iterations | 16520 | +| time_elapsed | 24233 | +| total_timesteps | 33832960 | +| train/ | | +| approx_kl | 0.01401069 | +| clip_fraction | 0.328 | +| clip_range | 0.0665 | +| entropy_loss | -6.55 | +| explained_variance | -0.202 | +| learning_rate | 4.2e-05 | +| loss | -0.0296 | +| n_updates | 81896 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000139 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1396 | +| iterations | 16521 | +| time_elapsed | 24234 | +| total_timesteps | 33835008 | +| train/ | | +| approx_kl | 0.012732554 | +| clip_fraction | 0.339 | +| clip_range | 0.0665 | +| entropy_loss | -6.87 | +| explained_variance | 0.131 | +| learning_rate | 4.2e-05 | +| loss | -0.0257 | +| n_updates | 81900 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000122 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1396 | +| iterations | 16522 | +| time_elapsed | 24236 | +| total_timesteps | 33837056 | +| train/ | | +| approx_kl | 0.011137633 | +| clip_fraction | 0.32 | +| clip_range | 0.0665 | +| entropy_loss | -5.99 | +| explained_variance | 0.336 | +| learning_rate | 4.2e-05 | +| loss | -0.0247 | +| n_updates | 81904 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000365 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1396 | +| iterations | 16523 | +| time_elapsed | 24237 | +| total_timesteps | 33839104 | +| train/ | | +| approx_kl | 0.013647153 | +| clip_fraction | 0.338 | +| clip_range | 0.0665 | +| entropy_loss | -5.78 | +| explained_variance | 0.312 | +| learning_rate | 4.2e-05 | +| loss | -0.0323 | +| n_updates | 81908 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000116 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1396 | +| iterations | 16524 | +| time_elapsed | 24239 | +| total_timesteps | 33841152 | +| train/ | | +| approx_kl | 0.014802049 | +| clip_fraction | 0.361 | +| clip_range | 0.0665 | +| entropy_loss | -5.99 | +| explained_variance | 0.361 | +| learning_rate | 4.2e-05 | +| loss | -0.0253 | +| n_updates | 81912 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000237 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1396 | +| iterations | 16525 | +| time_elapsed | 24241 | +| total_timesteps | 33843200 | +| train/ | | +| approx_kl | 0.014146211 | +| clip_fraction | 0.354 | +| clip_range | 0.0665 | +| entropy_loss | -6.34 | +| explained_variance | -0.202 | +| learning_rate | 4.2e-05 | +| loss | -0.0353 | +| n_updates | 81916 | +| policy_gradient_loss | -0.0188 | +| value_loss | 8.87e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1396 | +| iterations | 16526 | +| time_elapsed | 24242 | +| total_timesteps | 33845248 | +| train/ | | +| approx_kl | 0.013487695 | +| clip_fraction | 0.31 | +| clip_range | 0.0665 | +| entropy_loss | -6.09 | +| explained_variance | 0.292 | +| learning_rate | 4.2e-05 | +| loss | -0.0297 | +| n_updates | 81920 | +| policy_gradient_loss | -0.0138 | +| value_loss | 0.000313 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1396 | +| iterations | 16527 | +| time_elapsed | 24244 | +| total_timesteps | 33847296 | +| train/ | | +| approx_kl | 0.0129886605 | +| clip_fraction | 0.344 | +| clip_range | 0.0665 | +| entropy_loss | -5.77 | +| explained_variance | 0.511 | +| learning_rate | 4.2e-05 | +| loss | -0.0309 | +| n_updates | 81924 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000143 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1396 | +| iterations | 16528 | +| time_elapsed | 24245 | +| total_timesteps | 33849344 | +| train/ | | +| approx_kl | 0.015339533 | +| clip_fraction | 0.32 | +| clip_range | 0.0665 | +| entropy_loss | -6.2 | +| explained_variance | -0.0788 | +| learning_rate | 4.2e-05 | +| loss | -0.025 | +| n_updates | 81928 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000312 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1396 | +| iterations | 16529 | +| time_elapsed | 24247 | +| total_timesteps | 33851392 | +| train/ | | +| approx_kl | 0.016890988 | +| clip_fraction | 0.388 | +| clip_range | 0.0665 | +| entropy_loss | -5.7 | +| explained_variance | 0.523 | +| learning_rate | 4.2e-05 | +| loss | -0.0373 | +| n_updates | 81932 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000123 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1396 | +| iterations | 16530 | +| time_elapsed | 24248 | +| total_timesteps | 33853440 | +| train/ | | +| approx_kl | 0.019916393 | +| clip_fraction | 0.351 | +| clip_range | 0.0665 | +| entropy_loss | -6.15 | +| explained_variance | 0.334 | +| learning_rate | 4.2e-05 | +| loss | -0.0304 | +| n_updates | 81936 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000123 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1396 | +| iterations | 16531 | +| time_elapsed | 24250 | +| total_timesteps | 33855488 | +| train/ | | +| approx_kl | 0.015177787 | +| clip_fraction | 0.325 | +| clip_range | 0.0665 | +| entropy_loss | -6.49 | +| explained_variance | 0.12 | +| learning_rate | 4.2e-05 | +| loss | -0.0289 | +| n_updates | 81940 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000151 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1396 | +| iterations | 16532 | +| time_elapsed | 24251 | +| total_timesteps | 33857536 | +| train/ | | +| approx_kl | 0.014591623 | +| clip_fraction | 0.385 | +| clip_range | 0.0665 | +| entropy_loss | -6.65 | +| explained_variance | -0.209 | +| learning_rate | 4.2e-05 | +| loss | -0.0334 | +| n_updates | 81944 | +| policy_gradient_loss | -0.0224 | +| value_loss | 0.000108 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1396 | +| iterations | 16533 | +| time_elapsed | 24253 | +| total_timesteps | 33859584 | +| train/ | | +| approx_kl | 0.010777573 | +| clip_fraction | 0.322 | +| clip_range | 0.0665 | +| entropy_loss | -6.51 | +| explained_variance | 0.439 | +| learning_rate | 4.2e-05 | +| loss | -0.0219 | +| n_updates | 81948 | +| policy_gradient_loss | -0.0146 | +| value_loss | 0.000149 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1396 | +| iterations | 16534 | +| time_elapsed | 24254 | +| total_timesteps | 33861632 | +| train/ | | +| approx_kl | 0.013201861 | +| clip_fraction | 0.356 | +| clip_range | 0.0665 | +| entropy_loss | -5.78 | +| explained_variance | 0.631 | +| learning_rate | 4.2e-05 | +| loss | -0.0238 | +| n_updates | 81952 | +| policy_gradient_loss | -0.0176 | +| value_loss | 8.22e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1396 | +| iterations | 16535 | +| time_elapsed | 24256 | +| total_timesteps | 33863680 | +| train/ | | +| approx_kl | 0.013581969 | +| clip_fraction | 0.323 | +| clip_range | 0.0665 | +| entropy_loss | -6.32 | +| explained_variance | 0.0155 | +| learning_rate | 4.2e-05 | +| loss | -0.0285 | +| n_updates | 81956 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.0002 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1396 | +| iterations | 16536 | +| time_elapsed | 24257 | +| total_timesteps | 33865728 | +| train/ | | +| approx_kl | 0.013304359 | +| clip_fraction | 0.334 | +| clip_range | 0.0665 | +| entropy_loss | -6.37 | +| explained_variance | 0.275 | +| learning_rate | 4.2e-05 | +| loss | -0.0192 | +| n_updates | 81960 | +| policy_gradient_loss | -0.0141 | +| value_loss | 0.000161 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1396 | +| iterations | 16537 | +| time_elapsed | 24259 | +| total_timesteps | 33867776 | +| train/ | | +| approx_kl | 0.0141543485 | +| clip_fraction | 0.341 | +| clip_range | 0.0665 | +| entropy_loss | -6.04 | +| explained_variance | -0.048 | +| learning_rate | 4.2e-05 | +| loss | -0.0324 | +| n_updates | 81964 | +| policy_gradient_loss | -0.0178 | +| value_loss | 9.29e-05 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1396 | +| iterations | 16538 | +| time_elapsed | 24260 | +| total_timesteps | 33869824 | +| train/ | | +| approx_kl | 0.0142023135 | +| clip_fraction | 0.34 | +| clip_range | 0.0665 | +| entropy_loss | -5.7 | +| explained_variance | 0.478 | +| learning_rate | 4.2e-05 | +| loss | -0.0232 | +| n_updates | 81968 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000156 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1396 | +| iterations | 16539 | +| time_elapsed | 24262 | +| total_timesteps | 33871872 | +| train/ | | +| approx_kl | 0.011622991 | +| clip_fraction | 0.332 | +| clip_range | 0.0665 | +| entropy_loss | -5.64 | +| explained_variance | 0.594 | +| learning_rate | 4.2e-05 | +| loss | -0.0232 | +| n_updates | 81972 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000132 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1396 | +| iterations | 16540 | +| time_elapsed | 24263 | +| total_timesteps | 33873920 | +| train/ | | +| approx_kl | 0.014099218 | +| clip_fraction | 0.351 | +| clip_range | 0.0665 | +| entropy_loss | -5.95 | +| explained_variance | 0.652 | +| learning_rate | 4.2e-05 | +| loss | -0.0349 | +| n_updates | 81976 | +| policy_gradient_loss | -0.0201 | +| value_loss | 6.66e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1396 | +| iterations | 16541 | +| time_elapsed | 24265 | +| total_timesteps | 33875968 | +| train/ | | +| approx_kl | 0.014187805 | +| clip_fraction | 0.342 | +| clip_range | 0.0665 | +| entropy_loss | -6.45 | +| explained_variance | 0.211 | +| learning_rate | 4.2e-05 | +| loss | -0.0315 | +| n_updates | 81980 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.00011 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1396 | +| iterations | 16542 | +| time_elapsed | 24266 | +| total_timesteps | 33878016 | +| train/ | | +| approx_kl | 0.01040745 | +| clip_fraction | 0.346 | +| clip_range | 0.0665 | +| entropy_loss | -6.55 | +| explained_variance | 0.264 | +| learning_rate | 4.2e-05 | +| loss | -0.0275 | +| n_updates | 81984 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000179 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1396 | +| iterations | 16543 | +| time_elapsed | 24268 | +| total_timesteps | 33880064 | +| train/ | | +| approx_kl | 0.009453923 | +| clip_fraction | 0.316 | +| clip_range | 0.0665 | +| entropy_loss | -6.27 | +| explained_variance | 0.518 | +| learning_rate | 4.2e-05 | +| loss | -0.0283 | +| n_updates | 81988 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000131 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1396 | +| iterations | 16544 | +| time_elapsed | 24269 | +| total_timesteps | 33882112 | +| train/ | | +| approx_kl | 0.013683512 | +| clip_fraction | 0.382 | +| clip_range | 0.0665 | +| entropy_loss | -6.47 | +| explained_variance | 0.000605 | +| learning_rate | 4.2e-05 | +| loss | -0.0296 | +| n_updates | 81992 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000124 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1396 | +| iterations | 16545 | +| time_elapsed | 24271 | +| total_timesteps | 33884160 | +| train/ | | +| approx_kl | 0.011046117 | +| clip_fraction | 0.344 | +| clip_range | 0.0665 | +| entropy_loss | -6.19 | +| explained_variance | 0.482 | +| learning_rate | 4.2e-05 | +| loss | -0.0273 | +| n_updates | 81996 | +| policy_gradient_loss | -0.0169 | +| value_loss | 9.34e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1396 | +| iterations | 16546 | +| time_elapsed | 24272 | +| total_timesteps | 33886208 | +| train/ | | +| approx_kl | 0.013407518 | +| clip_fraction | 0.329 | +| clip_range | 0.0665 | +| entropy_loss | -6.24 | +| explained_variance | 0.312 | +| learning_rate | 4.2e-05 | +| loss | -0.027 | +| n_updates | 82000 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000145 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1396 | +| iterations | 16547 | +| time_elapsed | 24274 | +| total_timesteps | 33888256 | +| train/ | | +| approx_kl | 0.012203863 | +| clip_fraction | 0.328 | +| clip_range | 0.0665 | +| entropy_loss | -6.03 | +| explained_variance | 0.382 | +| learning_rate | 4.2e-05 | +| loss | -0.0236 | +| n_updates | 82004 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000259 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1396 | +| iterations | 16548 | +| time_elapsed | 24276 | +| total_timesteps | 33890304 | +| train/ | | +| approx_kl | 0.015666027 | +| clip_fraction | 0.33 | +| clip_range | 0.0665 | +| entropy_loss | -5.01 | +| explained_variance | 0.534 | +| learning_rate | 4.2e-05 | +| loss | -0.0228 | +| n_updates | 82008 | +| policy_gradient_loss | -0.0144 | +| value_loss | 0.000251 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1396 | +| iterations | 16549 | +| time_elapsed | 24277 | +| total_timesteps | 33892352 | +| train/ | | +| approx_kl | 0.014915789 | +| clip_fraction | 0.374 | +| clip_range | 0.0665 | +| entropy_loss | -5.67 | +| explained_variance | 0.174 | +| learning_rate | 4.2e-05 | +| loss | -0.028 | +| n_updates | 82012 | +| policy_gradient_loss | -0.0208 | +| value_loss | 9.94e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1396 | +| iterations | 16550 | +| time_elapsed | 24279 | +| total_timesteps | 33894400 | +| train/ | | +| approx_kl | 0.01362207 | +| clip_fraction | 0.32 | +| clip_range | 0.0665 | +| entropy_loss | -5.93 | +| explained_variance | 0.127 | +| learning_rate | 4.2e-05 | +| loss | -0.027 | +| n_updates | 82016 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000186 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1396 | +| iterations | 16551 | +| time_elapsed | 24280 | +| total_timesteps | 33896448 | +| train/ | | +| approx_kl | 0.014638498 | +| clip_fraction | 0.352 | +| clip_range | 0.0665 | +| entropy_loss | -5.13 | +| explained_variance | 0.735 | +| learning_rate | 4.2e-05 | +| loss | -0.0254 | +| n_updates | 82020 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000109 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1396 | +| iterations | 16552 | +| time_elapsed | 24282 | +| total_timesteps | 33898496 | +| train/ | | +| approx_kl | 0.014825652 | +| clip_fraction | 0.369 | +| clip_range | 0.0665 | +| entropy_loss | -5.84 | +| explained_variance | -0.209 | +| learning_rate | 4.19e-05 | +| loss | -0.0289 | +| n_updates | 82024 | +| policy_gradient_loss | -0.0204 | +| value_loss | 9.86e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1396 | +| iterations | 16553 | +| time_elapsed | 24283 | +| total_timesteps | 33900544 | +| train/ | | +| approx_kl | 0.017585903 | +| clip_fraction | 0.341 | +| clip_range | 0.0665 | +| entropy_loss | -6.09 | +| explained_variance | 0.387 | +| learning_rate | 4.19e-05 | +| loss | -0.0276 | +| n_updates | 82028 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000216 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1396 | +| iterations | 16554 | +| time_elapsed | 24285 | +| total_timesteps | 33902592 | +| train/ | | +| approx_kl | 0.013954944 | +| clip_fraction | 0.36 | +| clip_range | 0.0665 | +| entropy_loss | -6.01 | +| explained_variance | 0.305 | +| learning_rate | 4.19e-05 | +| loss | -0.0271 | +| n_updates | 82032 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000128 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1396 | +| iterations | 16555 | +| time_elapsed | 24286 | +| total_timesteps | 33904640 | +| train/ | | +| approx_kl | 0.014015341 | +| clip_fraction | 0.352 | +| clip_range | 0.0665 | +| entropy_loss | -6.81 | +| explained_variance | -0.129 | +| learning_rate | 4.19e-05 | +| loss | -0.0341 | +| n_updates | 82036 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.00013 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1396 | +| iterations | 16556 | +| time_elapsed | 24288 | +| total_timesteps | 33906688 | +| train/ | | +| approx_kl | 0.015399318 | +| clip_fraction | 0.347 | +| clip_range | 0.0665 | +| entropy_loss | -6.61 | +| explained_variance | -0.111 | +| learning_rate | 4.19e-05 | +| loss | -0.0286 | +| n_updates | 82040 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000143 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1396 | +| iterations | 16557 | +| time_elapsed | 24289 | +| total_timesteps | 33908736 | +| train/ | | +| approx_kl | 0.01196792 | +| clip_fraction | 0.353 | +| clip_range | 0.0665 | +| entropy_loss | -6.7 | +| explained_variance | -0.22 | +| learning_rate | 4.19e-05 | +| loss | -0.0325 | +| n_updates | 82044 | +| policy_gradient_loss | -0.0187 | +| value_loss | 7.91e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1396 | +| iterations | 16558 | +| time_elapsed | 24291 | +| total_timesteps | 33910784 | +| train/ | | +| approx_kl | 0.013344694 | +| clip_fraction | 0.325 | +| clip_range | 0.0665 | +| entropy_loss | -5.78 | +| explained_variance | 0.701 | +| learning_rate | 4.19e-05 | +| loss | -0.0212 | +| n_updates | 82048 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000115 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1395 | +| iterations | 16559 | +| time_elapsed | 24292 | +| total_timesteps | 33912832 | +| train/ | | +| approx_kl | 0.01269264 | +| clip_fraction | 0.319 | +| clip_range | 0.0665 | +| entropy_loss | -5.91 | +| explained_variance | 0.296 | +| learning_rate | 4.19e-05 | +| loss | -0.0211 | +| n_updates | 82052 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.000177 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1395 | +| iterations | 16560 | +| time_elapsed | 24294 | +| total_timesteps | 33914880 | +| train/ | | +| approx_kl | 0.013783684 | +| clip_fraction | 0.341 | +| clip_range | 0.0665 | +| entropy_loss | -5.87 | +| explained_variance | 0.575 | +| learning_rate | 4.19e-05 | +| loss | -0.0336 | +| n_updates | 82056 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000107 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1395 | +| iterations | 16561 | +| time_elapsed | 24295 | +| total_timesteps | 33916928 | +| train/ | | +| approx_kl | 0.012412071 | +| clip_fraction | 0.325 | +| clip_range | 0.0665 | +| entropy_loss | -5.89 | +| explained_variance | 0.552 | +| learning_rate | 4.19e-05 | +| loss | -0.034 | +| n_updates | 82060 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000144 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1395 | +| iterations | 16562 | +| time_elapsed | 24297 | +| total_timesteps | 33918976 | +| train/ | | +| approx_kl | 0.013286313 | +| clip_fraction | 0.315 | +| clip_range | 0.0665 | +| entropy_loss | -6.01 | +| explained_variance | 0.584 | +| learning_rate | 4.19e-05 | +| loss | -0.0309 | +| n_updates | 82064 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000111 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1395 | +| iterations | 16563 | +| time_elapsed | 24298 | +| total_timesteps | 33921024 | +| train/ | | +| approx_kl | 0.014015192 | +| clip_fraction | 0.358 | +| clip_range | 0.0665 | +| entropy_loss | -6.09 | +| explained_variance | 0.406 | +| learning_rate | 4.19e-05 | +| loss | -0.032 | +| n_updates | 82068 | +| policy_gradient_loss | -0.0218 | +| value_loss | 5.97e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1395 | +| iterations | 16564 | +| time_elapsed | 24300 | +| total_timesteps | 33923072 | +| train/ | | +| approx_kl | 0.010118257 | +| clip_fraction | 0.305 | +| clip_range | 0.0665 | +| entropy_loss | -6.67 | +| explained_variance | 0.362 | +| learning_rate | 4.19e-05 | +| loss | -0.0266 | +| n_updates | 82072 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.00013 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1395 | +| iterations | 16565 | +| time_elapsed | 24301 | +| total_timesteps | 33925120 | +| train/ | | +| approx_kl | 0.009798854 | +| clip_fraction | 0.315 | +| clip_range | 0.0665 | +| entropy_loss | -6.24 | +| explained_variance | 0.349 | +| learning_rate | 4.19e-05 | +| loss | -0.0298 | +| n_updates | 82076 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000274 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1395 | +| iterations | 16566 | +| time_elapsed | 24303 | +| total_timesteps | 33927168 | +| train/ | | +| approx_kl | 0.013528525 | +| clip_fraction | 0.371 | +| clip_range | 0.0665 | +| entropy_loss | -5.86 | +| explained_variance | 0.7 | +| learning_rate | 4.19e-05 | +| loss | -0.036 | +| n_updates | 82080 | +| policy_gradient_loss | -0.0229 | +| value_loss | 5.97e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1395 | +| iterations | 16567 | +| time_elapsed | 24304 | +| total_timesteps | 33929216 | +| train/ | | +| approx_kl | 0.015983663 | +| clip_fraction | 0.349 | +| clip_range | 0.0665 | +| entropy_loss | -5.75 | +| explained_variance | 0.429 | +| learning_rate | 4.19e-05 | +| loss | -0.0241 | +| n_updates | 82084 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000172 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1395 | +| iterations | 16568 | +| time_elapsed | 24306 | +| total_timesteps | 33931264 | +| train/ | | +| approx_kl | 0.013255984 | +| clip_fraction | 0.346 | +| clip_range | 0.0665 | +| entropy_loss | -6.34 | +| explained_variance | 0.439 | +| learning_rate | 4.19e-05 | +| loss | -0.0292 | +| n_updates | 82088 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000123 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1395 | +| iterations | 16569 | +| time_elapsed | 24307 | +| total_timesteps | 33933312 | +| train/ | | +| approx_kl | 0.017998552 | +| clip_fraction | 0.33 | +| clip_range | 0.0665 | +| entropy_loss | -5.94 | +| explained_variance | 0.359 | +| learning_rate | 4.19e-05 | +| loss | -0.0265 | +| n_updates | 82092 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000302 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1395 | +| iterations | 16570 | +| time_elapsed | 24309 | +| total_timesteps | 33935360 | +| train/ | | +| approx_kl | 0.015062485 | +| clip_fraction | 0.348 | +| clip_range | 0.0665 | +| entropy_loss | -5.42 | +| explained_variance | 0.612 | +| learning_rate | 4.19e-05 | +| loss | -0.0298 | +| n_updates | 82096 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000114 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1395 | +| iterations | 16571 | +| time_elapsed | 24310 | +| total_timesteps | 33937408 | +| train/ | | +| approx_kl | 0.010865055 | +| clip_fraction | 0.343 | +| clip_range | 0.0665 | +| entropy_loss | -6.57 | +| explained_variance | 0.291 | +| learning_rate | 4.19e-05 | +| loss | -0.0285 | +| n_updates | 82100 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000125 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1395 | +| iterations | 16572 | +| time_elapsed | 24312 | +| total_timesteps | 33939456 | +| train/ | | +| approx_kl | 0.016853098 | +| clip_fraction | 0.337 | +| clip_range | 0.0665 | +| entropy_loss | -6.35 | +| explained_variance | 0.453 | +| learning_rate | 4.19e-05 | +| loss | -0.0344 | +| n_updates | 82104 | +| policy_gradient_loss | -0.0195 | +| value_loss | 7.16e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1395 | +| iterations | 16573 | +| time_elapsed | 24314 | +| total_timesteps | 33941504 | +| train/ | | +| approx_kl | 0.011200456 | +| clip_fraction | 0.316 | +| clip_range | 0.0665 | +| entropy_loss | -5.6 | +| explained_variance | 0.739 | +| learning_rate | 4.19e-05 | +| loss | -0.0226 | +| n_updates | 82108 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000101 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1395 | +| iterations | 16574 | +| time_elapsed | 24315 | +| total_timesteps | 33943552 | +| train/ | | +| approx_kl | 0.011953792 | +| clip_fraction | 0.328 | +| clip_range | 0.0665 | +| entropy_loss | -6.36 | +| explained_variance | 0.417 | +| learning_rate | 4.19e-05 | +| loss | -0.0259 | +| n_updates | 82112 | +| policy_gradient_loss | -0.0178 | +| value_loss | 9.8e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 1395 | +| iterations | 16575 | +| time_elapsed | 24317 | +| total_timesteps | 33945600 | +| train/ | | +| approx_kl | 0.013746185 | +| clip_fraction | 0.327 | +| clip_range | 0.0665 | +| entropy_loss | -6.77 | +| explained_variance | 0.295 | +| learning_rate | 4.19e-05 | +| loss | -0.029 | +| n_updates | 82116 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000145 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1395 | +| iterations | 16576 | +| time_elapsed | 24318 | +| total_timesteps | 33947648 | +| train/ | | +| approx_kl | 0.013554303 | +| clip_fraction | 0.35 | +| clip_range | 0.0665 | +| entropy_loss | -6.44 | +| explained_variance | 0.37 | +| learning_rate | 4.19e-05 | +| loss | -0.0257 | +| n_updates | 82120 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000115 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1395 | +| iterations | 16577 | +| time_elapsed | 24320 | +| total_timesteps | 33949696 | +| train/ | | +| approx_kl | 0.013984113 | +| clip_fraction | 0.348 | +| clip_range | 0.0665 | +| entropy_loss | -6.5 | +| explained_variance | -0.113 | +| learning_rate | 4.19e-05 | +| loss | -0.0251 | +| n_updates | 82124 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000141 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1395 | +| iterations | 16578 | +| time_elapsed | 24321 | +| total_timesteps | 33951744 | +| train/ | | +| approx_kl | 0.010573388 | +| clip_fraction | 0.347 | +| clip_range | 0.0665 | +| entropy_loss | -6.15 | +| explained_variance | 0.158 | +| learning_rate | 4.19e-05 | +| loss | -0.0203 | +| n_updates | 82128 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000421 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1395 | +| iterations | 16579 | +| time_elapsed | 24323 | +| total_timesteps | 33953792 | +| train/ | | +| approx_kl | 0.012487085 | +| clip_fraction | 0.332 | +| clip_range | 0.0665 | +| entropy_loss | -5.45 | +| explained_variance | 0.624 | +| learning_rate | 4.19e-05 | +| loss | -0.0304 | +| n_updates | 82132 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000122 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1395 | +| iterations | 16580 | +| time_elapsed | 24324 | +| total_timesteps | 33955840 | +| train/ | | +| approx_kl | 0.012091307 | +| clip_fraction | 0.328 | +| clip_range | 0.0665 | +| entropy_loss | -6.41 | +| explained_variance | 0.285 | +| learning_rate | 4.19e-05 | +| loss | -0.0273 | +| n_updates | 82136 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000163 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1395 | +| iterations | 16581 | +| time_elapsed | 24326 | +| total_timesteps | 33957888 | +| train/ | | +| approx_kl | 0.015671927 | +| clip_fraction | 0.356 | +| clip_range | 0.0665 | +| entropy_loss | -5.53 | +| explained_variance | 0.743 | +| learning_rate | 4.19e-05 | +| loss | -0.0294 | +| n_updates | 82140 | +| policy_gradient_loss | -0.0196 | +| value_loss | 7.79e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1395 | +| iterations | 16582 | +| time_elapsed | 24327 | +| total_timesteps | 33959936 | +| train/ | | +| approx_kl | 0.013553618 | +| clip_fraction | 0.313 | +| clip_range | 0.0665 | +| entropy_loss | -5.86 | +| explained_variance | 0.263 | +| learning_rate | 4.19e-05 | +| loss | -0.0237 | +| n_updates | 82144 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000201 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1395 | +| iterations | 16583 | +| time_elapsed | 24329 | +| total_timesteps | 33961984 | +| train/ | | +| approx_kl | 0.012568361 | +| clip_fraction | 0.341 | +| clip_range | 0.0665 | +| entropy_loss | -6.65 | +| explained_variance | -0.0877 | +| learning_rate | 4.19e-05 | +| loss | -0.0316 | +| n_updates | 82148 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000168 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1395 | +| iterations | 16584 | +| time_elapsed | 24330 | +| total_timesteps | 33964032 | +| train/ | | +| approx_kl | 0.016917966 | +| clip_fraction | 0.353 | +| clip_range | 0.0665 | +| entropy_loss | -6.22 | +| explained_variance | -0.196 | +| learning_rate | 4.19e-05 | +| loss | -0.0329 | +| n_updates | 82152 | +| policy_gradient_loss | -0.0212 | +| value_loss | 9.04e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1395 | +| iterations | 16585 | +| time_elapsed | 24332 | +| total_timesteps | 33966080 | +| train/ | | +| approx_kl | 0.01677375 | +| clip_fraction | 0.374 | +| clip_range | 0.0665 | +| entropy_loss | -5.92 | +| explained_variance | 0.253 | +| learning_rate | 4.19e-05 | +| loss | -0.0326 | +| n_updates | 82156 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000103 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1395 | +| iterations | 16586 | +| time_elapsed | 24334 | +| total_timesteps | 33968128 | +| train/ | | +| approx_kl | 0.01395852 | +| clip_fraction | 0.331 | +| clip_range | 0.0665 | +| entropy_loss | -5.86 | +| explained_variance | 0.653 | +| learning_rate | 4.19e-05 | +| loss | -0.0279 | +| n_updates | 82160 | +| policy_gradient_loss | -0.0164 | +| value_loss | 7.67e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 1395 | +| iterations | 16587 | +| time_elapsed | 24335 | +| total_timesteps | 33970176 | +| train/ | | +| approx_kl | 0.014105167 | +| clip_fraction | 0.315 | +| clip_range | 0.0665 | +| entropy_loss | -5.09 | +| explained_variance | 0.39 | +| learning_rate | 4.19e-05 | +| loss | -0.0227 | +| n_updates | 82164 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000292 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.306 | +| time/ | | +| fps | 1395 | +| iterations | 16588 | +| time_elapsed | 24337 | +| total_timesteps | 33972224 | +| train/ | | +| approx_kl | 0.011842381 | +| clip_fraction | 0.341 | +| clip_range | 0.0665 | +| entropy_loss | -5.36 | +| explained_variance | 0.637 | +| learning_rate | 4.19e-05 | +| loss | -0.0325 | +| n_updates | 82168 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000121 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 1395 | +| iterations | 16589 | +| time_elapsed | 24338 | +| total_timesteps | 33974272 | +| train/ | | +| approx_kl | 0.015410701 | +| clip_fraction | 0.374 | +| clip_range | 0.0665 | +| entropy_loss | -5.81 | +| explained_variance | 0.62 | +| learning_rate | 4.19e-05 | +| loss | -0.0345 | +| n_updates | 82172 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000112 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 1395 | +| iterations | 16590 | +| time_elapsed | 24340 | +| total_timesteps | 33976320 | +| train/ | | +| approx_kl | 0.016509475 | +| clip_fraction | 0.339 | +| clip_range | 0.0665 | +| entropy_loss | -6.17 | +| explained_variance | 0.42 | +| learning_rate | 4.19e-05 | +| loss | -0.0288 | +| n_updates | 82176 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000118 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.292 | +| time/ | | +| fps | 1395 | +| iterations | 16591 | +| time_elapsed | 24341 | +| total_timesteps | 33978368 | +| train/ | | +| approx_kl | 0.016299618 | +| clip_fraction | 0.367 | +| clip_range | 0.0665 | +| entropy_loss | -6.07 | +| explained_variance | 0.367 | +| learning_rate | 4.19e-05 | +| loss | -0.0241 | +| n_updates | 82180 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000121 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.294 | +| time/ | | +| fps | 1395 | +| iterations | 16592 | +| time_elapsed | 24343 | +| total_timesteps | 33980416 | +| train/ | | +| approx_kl | 0.014235465 | +| clip_fraction | 0.357 | +| clip_range | 0.0665 | +| entropy_loss | -6.43 | +| explained_variance | 0.437 | +| learning_rate | 4.19e-05 | +| loss | -0.0277 | +| n_updates | 82184 | +| policy_gradient_loss | -0.0192 | +| value_loss | 8.29e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 1395 | +| iterations | 16593 | +| time_elapsed | 24344 | +| total_timesteps | 33982464 | +| train/ | | +| approx_kl | 0.014460053 | +| clip_fraction | 0.347 | +| clip_range | 0.0665 | +| entropy_loss | -5.8 | +| explained_variance | 0.49 | +| learning_rate | 4.19e-05 | +| loss | -0.0356 | +| n_updates | 82188 | +| policy_gradient_loss | -0.0184 | +| value_loss | 9.49e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.292 | +| time/ | | +| fps | 1395 | +| iterations | 16594 | +| time_elapsed | 24346 | +| total_timesteps | 33984512 | +| train/ | | +| approx_kl | 0.015687592 | +| clip_fraction | 0.356 | +| clip_range | 0.0665 | +| entropy_loss | -5.86 | +| explained_variance | 0.475 | +| learning_rate | 4.19e-05 | +| loss | -0.0237 | +| n_updates | 82192 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000152 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.297 | +| time/ | | +| fps | 1395 | +| iterations | 16595 | +| time_elapsed | 24347 | +| total_timesteps | 33986560 | +| train/ | | +| approx_kl | 0.013937098 | +| clip_fraction | 0.361 | +| clip_range | 0.0665 | +| entropy_loss | -6.08 | +| explained_variance | 0.317 | +| learning_rate | 4.19e-05 | +| loss | -0.0341 | +| n_updates | 82196 | +| policy_gradient_loss | -0.0196 | +| value_loss | 7.79e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 1395 | +| iterations | 16596 | +| time_elapsed | 24349 | +| total_timesteps | 33988608 | +| train/ | | +| approx_kl | 0.012474535 | +| clip_fraction | 0.353 | +| clip_range | 0.0665 | +| entropy_loss | -6.03 | +| explained_variance | 0.35 | +| learning_rate | 4.19e-05 | +| loss | -0.0301 | +| n_updates | 82200 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000173 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 1395 | +| iterations | 16597 | +| time_elapsed | 24351 | +| total_timesteps | 33990656 | +| train/ | | +| approx_kl | 0.0122867655 | +| clip_fraction | 0.344 | +| clip_range | 0.0665 | +| entropy_loss | -5.53 | +| explained_variance | 0.566 | +| learning_rate | 4.19e-05 | +| loss | -0.0239 | +| n_updates | 82204 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000204 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 1395 | +| iterations | 16598 | +| time_elapsed | 24352 | +| total_timesteps | 33992704 | +| train/ | | +| approx_kl | 0.012413846 | +| clip_fraction | 0.358 | +| clip_range | 0.0665 | +| entropy_loss | -6.11 | +| explained_variance | 0.0915 | +| learning_rate | 4.19e-05 | +| loss | -0.0311 | +| n_updates | 82208 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.00012 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 1395 | +| iterations | 16599 | +| time_elapsed | 24354 | +| total_timesteps | 33994752 | +| train/ | | +| approx_kl | 0.011766806 | +| clip_fraction | 0.323 | +| clip_range | 0.0665 | +| entropy_loss | -6.4 | +| explained_variance | 0.412 | +| learning_rate | 4.19e-05 | +| loss | -0.0275 | +| n_updates | 82212 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000165 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 1395 | +| iterations | 16600 | +| time_elapsed | 24355 | +| total_timesteps | 33996800 | +| train/ | | +| approx_kl | 0.012691689 | +| clip_fraction | 0.324 | +| clip_range | 0.0665 | +| entropy_loss | -6.63 | +| explained_variance | 0.301 | +| learning_rate | 4.19e-05 | +| loss | -0.0286 | +| n_updates | 82216 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000131 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.297 | +| time/ | | +| fps | 1395 | +| iterations | 16601 | +| time_elapsed | 24357 | +| total_timesteps | 33998848 | +| train/ | | +| approx_kl | 0.011401918 | +| clip_fraction | 0.318 | +| clip_range | 0.0665 | +| entropy_loss | -6.3 | +| explained_variance | 0.513 | +| learning_rate | 4.19e-05 | +| loss | -0.029 | +| n_updates | 82220 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000107 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.297 | +| time/ | | +| fps | 1395 | +| iterations | 16602 | +| time_elapsed | 24358 | +| total_timesteps | 34000896 | +| train/ | | +| approx_kl | 0.01009999 | +| clip_fraction | 0.329 | +| clip_range | 0.0665 | +| entropy_loss | -6.09 | +| explained_variance | 0.338 | +| learning_rate | 4.19e-05 | +| loss | -0.033 | +| n_updates | 82224 | +| policy_gradient_loss | -0.0131 | +| value_loss | 0.000225 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.302 | +| time/ | | +| fps | 1395 | +| iterations | 16603 | +| time_elapsed | 24360 | +| total_timesteps | 34002944 | +| train/ | | +| approx_kl | 0.013404787 | +| clip_fraction | 0.339 | +| clip_range | 0.0665 | +| entropy_loss | -6 | +| explained_variance | 0.616 | +| learning_rate | 4.19e-05 | +| loss | -0.0282 | +| n_updates | 82228 | +| policy_gradient_loss | -0.0199 | +| value_loss | 9.26e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.304 | +| time/ | | +| fps | 1395 | +| iterations | 16604 | +| time_elapsed | 24361 | +| total_timesteps | 34004992 | +| train/ | | +| approx_kl | 0.013428709 | +| clip_fraction | 0.329 | +| clip_range | 0.0665 | +| entropy_loss | -5.9 | +| explained_variance | 0.315 | +| learning_rate | 4.19e-05 | +| loss | -0.0242 | +| n_updates | 82232 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000225 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 1395 | +| iterations | 16605 | +| time_elapsed | 24363 | +| total_timesteps | 34007040 | +| train/ | | +| approx_kl | 0.014820758 | +| clip_fraction | 0.341 | +| clip_range | 0.0665 | +| entropy_loss | -5.47 | +| explained_variance | 0.493 | +| learning_rate | 4.19e-05 | +| loss | -0.0308 | +| n_updates | 82236 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000112 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 1395 | +| iterations | 16606 | +| time_elapsed | 24365 | +| total_timesteps | 34009088 | +| train/ | | +| approx_kl | 0.013174047 | +| clip_fraction | 0.358 | +| clip_range | 0.0665 | +| entropy_loss | -5.88 | +| explained_variance | 0.278 | +| learning_rate | 4.19e-05 | +| loss | -0.0267 | +| n_updates | 82240 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000172 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 1395 | +| iterations | 16607 | +| time_elapsed | 24366 | +| total_timesteps | 34011136 | +| train/ | | +| approx_kl | 0.012113331 | +| clip_fraction | 0.341 | +| clip_range | 0.0665 | +| entropy_loss | -6.06 | +| explained_variance | 0.192 | +| learning_rate | 4.19e-05 | +| loss | -0.0318 | +| n_updates | 82244 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000219 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1395 | +| iterations | 16608 | +| time_elapsed | 24368 | +| total_timesteps | 34013184 | +| train/ | | +| approx_kl | 0.014247166 | +| clip_fraction | 0.374 | +| clip_range | 0.0665 | +| entropy_loss | -5.61 | +| explained_variance | 0.726 | +| learning_rate | 4.19e-05 | +| loss | -0.036 | +| n_updates | 82248 | +| policy_gradient_loss | -0.0217 | +| value_loss | 6.97e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.306 | +| time/ | | +| fps | 1395 | +| iterations | 16609 | +| time_elapsed | 24369 | +| total_timesteps | 34015232 | +| train/ | | +| approx_kl | 0.012894616 | +| clip_fraction | 0.331 | +| clip_range | 0.0665 | +| entropy_loss | -6.04 | +| explained_variance | 0.361 | +| learning_rate | 4.19e-05 | +| loss | -0.0289 | +| n_updates | 82252 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000244 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.298 | +| time/ | | +| fps | 1395 | +| iterations | 16610 | +| time_elapsed | 24371 | +| total_timesteps | 34017280 | +| train/ | | +| approx_kl | 0.011868563 | +| clip_fraction | 0.349 | +| clip_range | 0.0665 | +| entropy_loss | -6.46 | +| explained_variance | 0.365 | +| learning_rate | 4.19e-05 | +| loss | -0.0306 | +| n_updates | 82256 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000113 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.287 | +| time/ | | +| fps | 1395 | +| iterations | 16611 | +| time_elapsed | 24372 | +| total_timesteps | 34019328 | +| train/ | | +| approx_kl | 0.009867318 | +| clip_fraction | 0.309 | +| clip_range | 0.0665 | +| entropy_loss | -6.43 | +| explained_variance | 0.474 | +| learning_rate | 4.19e-05 | +| loss | -0.0268 | +| n_updates | 82260 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000162 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.29 | +| time/ | | +| fps | 1395 | +| iterations | 16612 | +| time_elapsed | 24374 | +| total_timesteps | 34021376 | +| train/ | | +| approx_kl | 0.013600719 | +| clip_fraction | 0.365 | +| clip_range | 0.0665 | +| entropy_loss | -5.54 | +| explained_variance | 0.773 | +| learning_rate | 4.19e-05 | +| loss | -0.0298 | +| n_updates | 82264 | +| policy_gradient_loss | -0.0195 | +| value_loss | 8.1e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.293 | +| time/ | | +| fps | 1395 | +| iterations | 16613 | +| time_elapsed | 24375 | +| total_timesteps | 34023424 | +| train/ | | +| approx_kl | 0.012113487 | +| clip_fraction | 0.32 | +| clip_range | 0.0665 | +| entropy_loss | -5.92 | +| explained_variance | 0.52 | +| learning_rate | 4.19e-05 | +| loss | -0.0255 | +| n_updates | 82268 | +| policy_gradient_loss | -0.0144 | +| value_loss | 0.00012 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.297 | +| time/ | | +| fps | 1395 | +| iterations | 16614 | +| time_elapsed | 24377 | +| total_timesteps | 34025472 | +| train/ | | +| approx_kl | 0.0142613575 | +| clip_fraction | 0.348 | +| clip_range | 0.0665 | +| entropy_loss | -5.73 | +| explained_variance | 0.318 | +| learning_rate | 4.19e-05 | +| loss | -0.0308 | +| n_updates | 82272 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000112 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.297 | +| time/ | | +| fps | 1395 | +| iterations | 16615 | +| time_elapsed | 24378 | +| total_timesteps | 34027520 | +| train/ | | +| approx_kl | 0.015087866 | +| clip_fraction | 0.348 | +| clip_range | 0.0665 | +| entropy_loss | -5.99 | +| explained_variance | 0.507 | +| learning_rate | 4.19e-05 | +| loss | -0.031 | +| n_updates | 82276 | +| policy_gradient_loss | -0.0179 | +| value_loss | 9.59e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.292 | +| time/ | | +| fps | 1395 | +| iterations | 16616 | +| time_elapsed | 24380 | +| total_timesteps | 34029568 | +| train/ | | +| approx_kl | 0.014338868 | +| clip_fraction | 0.323 | +| clip_range | 0.0665 | +| entropy_loss | -6.26 | +| explained_variance | 0.0176 | +| learning_rate | 4.19e-05 | +| loss | -0.0377 | +| n_updates | 82280 | +| policy_gradient_loss | -0.0191 | +| value_loss | 6.12e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.288 | +| time/ | | +| fps | 1395 | +| iterations | 16617 | +| time_elapsed | 24382 | +| total_timesteps | 34031616 | +| train/ | | +| approx_kl | 0.01351718 | +| clip_fraction | 0.352 | +| clip_range | 0.0665 | +| entropy_loss | -6.05 | +| explained_variance | 0.597 | +| learning_rate | 4.19e-05 | +| loss | -0.0254 | +| n_updates | 82284 | +| policy_gradient_loss | -0.0177 | +| value_loss | 8.58e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.284 | +| time/ | | +| fps | 1395 | +| iterations | 16618 | +| time_elapsed | 24383 | +| total_timesteps | 34033664 | +| train/ | | +| approx_kl | 0.015468339 | +| clip_fraction | 0.348 | +| clip_range | 0.0665 | +| entropy_loss | -5.57 | +| explained_variance | 0.776 | +| learning_rate | 4.19e-05 | +| loss | -0.0314 | +| n_updates | 82288 | +| policy_gradient_loss | -0.0177 | +| value_loss | 6.8e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.286 | +| time/ | | +| fps | 1395 | +| iterations | 16619 | +| time_elapsed | 24385 | +| total_timesteps | 34035712 | +| train/ | | +| approx_kl | 0.015012687 | +| clip_fraction | 0.323 | +| clip_range | 0.0665 | +| entropy_loss | -5.66 | +| explained_variance | 0.242 | +| learning_rate | 4.19e-05 | +| loss | -0.0239 | +| n_updates | 82292 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.00019 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.285 | +| time/ | | +| fps | 1395 | +| iterations | 16620 | +| time_elapsed | 24386 | +| total_timesteps | 34037760 | +| train/ | | +| approx_kl | 0.012021698 | +| clip_fraction | 0.313 | +| clip_range | 0.0665 | +| entropy_loss | -6.22 | +| explained_variance | 0.374 | +| learning_rate | 4.19e-05 | +| loss | -0.0278 | +| n_updates | 82296 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000211 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.287 | +| time/ | | +| fps | 1395 | +| iterations | 16621 | +| time_elapsed | 24388 | +| total_timesteps | 34039808 | +| train/ | | +| approx_kl | 0.018808283 | +| clip_fraction | 0.329 | +| clip_range | 0.0665 | +| entropy_loss | -6.03 | +| explained_variance | 0.484 | +| learning_rate | 4.19e-05 | +| loss | -0.0259 | +| n_updates | 82300 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000124 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.288 | +| time/ | | +| fps | 1395 | +| iterations | 16622 | +| time_elapsed | 24389 | +| total_timesteps | 34041856 | +| train/ | | +| approx_kl | 0.014830271 | +| clip_fraction | 0.333 | +| clip_range | 0.0665 | +| entropy_loss | -5.81 | +| explained_variance | 0.105 | +| learning_rate | 4.19e-05 | +| loss | -0.0227 | +| n_updates | 82304 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000332 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.291 | +| time/ | | +| fps | 1395 | +| iterations | 16623 | +| time_elapsed | 24391 | +| total_timesteps | 34043904 | +| train/ | | +| approx_kl | 0.016238019 | +| clip_fraction | 0.371 | +| clip_range | 0.0665 | +| entropy_loss | -5.69 | +| explained_variance | 0.559 | +| learning_rate | 4.19e-05 | +| loss | -0.0309 | +| n_updates | 82308 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000147 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.292 | +| time/ | | +| fps | 1395 | +| iterations | 16624 | +| time_elapsed | 24392 | +| total_timesteps | 34045952 | +| train/ | | +| approx_kl | 0.0158901 | +| clip_fraction | 0.356 | +| clip_range | 0.0665 | +| entropy_loss | -5.95 | +| explained_variance | 0.267 | +| learning_rate | 4.19e-05 | +| loss | -0.0303 | +| n_updates | 82312 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000155 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.292 | +| time/ | | +| fps | 1395 | +| iterations | 16625 | +| time_elapsed | 24394 | +| total_timesteps | 34048000 | +| train/ | | +| approx_kl | 0.012027958 | +| clip_fraction | 0.347 | +| clip_range | 0.0665 | +| entropy_loss | -6.23 | +| explained_variance | 0.368 | +| learning_rate | 4.19e-05 | +| loss | -0.0232 | +| n_updates | 82316 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000124 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.29 | +| time/ | | +| fps | 1395 | +| iterations | 16626 | +| time_elapsed | 24395 | +| total_timesteps | 34050048 | +| train/ | | +| approx_kl | 0.018417338 | +| clip_fraction | 0.38 | +| clip_range | 0.0665 | +| entropy_loss | -6.06 | +| explained_variance | -0.0815 | +| learning_rate | 4.19e-05 | +| loss | -0.0307 | +| n_updates | 82320 | +| policy_gradient_loss | -0.0193 | +| value_loss | 9.67e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.289 | +| time/ | | +| fps | 1395 | +| iterations | 16627 | +| time_elapsed | 24397 | +| total_timesteps | 34052096 | +| train/ | | +| approx_kl | 0.014392455 | +| clip_fraction | 0.346 | +| clip_range | 0.0665 | +| entropy_loss | -6.35 | +| explained_variance | 0.303 | +| learning_rate | 4.19e-05 | +| loss | -0.0255 | +| n_updates | 82324 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000152 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.292 | +| time/ | | +| fps | 1395 | +| iterations | 16628 | +| time_elapsed | 24399 | +| total_timesteps | 34054144 | +| train/ | | +| approx_kl | 0.013429154 | +| clip_fraction | 0.344 | +| clip_range | 0.0665 | +| entropy_loss | -5.53 | +| explained_variance | 0.502 | +| learning_rate | 4.19e-05 | +| loss | -0.0278 | +| n_updates | 82328 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000187 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.292 | +| time/ | | +| fps | 1395 | +| iterations | 16629 | +| time_elapsed | 24400 | +| total_timesteps | 34056192 | +| train/ | | +| approx_kl | 0.015194921 | +| clip_fraction | 0.347 | +| clip_range | 0.0665 | +| entropy_loss | -5.5 | +| explained_variance | 0.369 | +| learning_rate | 4.19e-05 | +| loss | -0.0238 | +| n_updates | 82332 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000184 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.286 | +| time/ | | +| fps | 1395 | +| iterations | 16630 | +| time_elapsed | 24402 | +| total_timesteps | 34058240 | +| train/ | | +| approx_kl | 0.0162336 | +| clip_fraction | 0.384 | +| clip_range | 0.0665 | +| entropy_loss | -5.84 | +| explained_variance | 0.634 | +| learning_rate | 4.19e-05 | +| loss | -0.0353 | +| n_updates | 82336 | +| policy_gradient_loss | -0.0232 | +| value_loss | 5.33e-05 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.286 | +| time/ | | +| fps | 1395 | +| iterations | 16631 | +| time_elapsed | 24403 | +| total_timesteps | 34060288 | +| train/ | | +| approx_kl | 0.013518698 | +| clip_fraction | 0.348 | +| clip_range | 0.0665 | +| entropy_loss | -6.33 | +| explained_variance | 0.122 | +| learning_rate | 4.19e-05 | +| loss | -0.0299 | +| n_updates | 82340 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000121 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.293 | +| time/ | | +| fps | 1395 | +| iterations | 16632 | +| time_elapsed | 24405 | +| total_timesteps | 34062336 | +| train/ | | +| approx_kl | 0.0134322755 | +| clip_fraction | 0.312 | +| clip_range | 0.0665 | +| entropy_loss | -5.9 | +| explained_variance | 0.613 | +| learning_rate | 4.19e-05 | +| loss | -0.0292 | +| n_updates | 82344 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000114 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.293 | +| time/ | | +| fps | 1395 | +| iterations | 16633 | +| time_elapsed | 24406 | +| total_timesteps | 34064384 | +| train/ | | +| approx_kl | 0.01170706 | +| clip_fraction | 0.313 | +| clip_range | 0.0665 | +| entropy_loss | -5.98 | +| explained_variance | 0.233 | +| learning_rate | 4.19e-05 | +| loss | -0.0241 | +| n_updates | 82348 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000274 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.291 | +| time/ | | +| fps | 1395 | +| iterations | 16634 | +| time_elapsed | 24408 | +| total_timesteps | 34066432 | +| train/ | | +| approx_kl | 0.011751524 | +| clip_fraction | 0.345 | +| clip_range | 0.0665 | +| entropy_loss | -6.5 | +| explained_variance | -0.081 | +| learning_rate | 4.19e-05 | +| loss | -0.0325 | +| n_updates | 82352 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.00021 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.29 | +| time/ | | +| fps | 1395 | +| iterations | 16635 | +| time_elapsed | 24409 | +| total_timesteps | 34068480 | +| train/ | | +| approx_kl | 0.016076138 | +| clip_fraction | 0.392 | +| clip_range | 0.0665 | +| entropy_loss | -6.66 | +| explained_variance | -0.339 | +| learning_rate | 4.19e-05 | +| loss | -0.0352 | +| n_updates | 82356 | +| policy_gradient_loss | -0.0231 | +| value_loss | 7.59e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.295 | +| time/ | | +| fps | 1395 | +| iterations | 16636 | +| time_elapsed | 24411 | +| total_timesteps | 34070528 | +| train/ | | +| approx_kl | 0.011163448 | +| clip_fraction | 0.338 | +| clip_range | 0.0665 | +| entropy_loss | -6.2 | +| explained_variance | 0.342 | +| learning_rate | 4.19e-05 | +| loss | -0.0308 | +| n_updates | 82360 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000146 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.288 | +| time/ | | +| fps | 1395 | +| iterations | 16637 | +| time_elapsed | 24412 | +| total_timesteps | 34072576 | +| train/ | | +| approx_kl | 0.011883631 | +| clip_fraction | 0.346 | +| clip_range | 0.0665 | +| entropy_loss | -5.56 | +| explained_variance | 0.532 | +| learning_rate | 4.19e-05 | +| loss | -0.0251 | +| n_updates | 82364 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000171 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.293 | +| time/ | | +| fps | 1395 | +| iterations | 16638 | +| time_elapsed | 24414 | +| total_timesteps | 34074624 | +| train/ | | +| approx_kl | 0.011941183 | +| clip_fraction | 0.336 | +| clip_range | 0.0665 | +| entropy_loss | -5.76 | +| explained_variance | 0.565 | +| learning_rate | 4.19e-05 | +| loss | -0.0324 | +| n_updates | 82368 | +| policy_gradient_loss | -0.0177 | +| value_loss | 9.07e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.294 | +| time/ | | +| fps | 1395 | +| iterations | 16639 | +| time_elapsed | 24415 | +| total_timesteps | 34076672 | +| train/ | | +| approx_kl | 0.014393875 | +| clip_fraction | 0.354 | +| clip_range | 0.0665 | +| entropy_loss | -5.38 | +| explained_variance | 0.373 | +| learning_rate | 4.19e-05 | +| loss | -0.0289 | +| n_updates | 82372 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000226 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.294 | +| time/ | | +| fps | 1395 | +| iterations | 16640 | +| time_elapsed | 24417 | +| total_timesteps | 34078720 | +| train/ | | +| approx_kl | 0.0120744 | +| clip_fraction | 0.354 | +| clip_range | 0.0665 | +| entropy_loss | -5.35 | +| explained_variance | 0.549 | +| learning_rate | 4.19e-05 | +| loss | -0.0198 | +| n_updates | 82376 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000166 | +--------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.289 | +| time/ | | +| fps | 1395 | +| iterations | 16641 | +| time_elapsed | 24419 | +| total_timesteps | 34080768 | +| train/ | | +| approx_kl | 0.0111412285 | +| clip_fraction | 0.363 | +| clip_range | 0.0665 | +| entropy_loss | -6.45 | +| explained_variance | 0.157 | +| learning_rate | 4.19e-05 | +| loss | -0.0306 | +| n_updates | 82380 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000246 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.286 | +| time/ | | +| fps | 1395 | +| iterations | 16642 | +| time_elapsed | 24420 | +| total_timesteps | 34082816 | +| train/ | | +| approx_kl | 0.014409247 | +| clip_fraction | 0.33 | +| clip_range | 0.0665 | +| entropy_loss | -6.15 | +| explained_variance | 0.325 | +| learning_rate | 4.19e-05 | +| loss | -0.0269 | +| n_updates | 82384 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000236 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.291 | +| time/ | | +| fps | 1395 | +| iterations | 16643 | +| time_elapsed | 24422 | +| total_timesteps | 34084864 | +| train/ | | +| approx_kl | 0.012763865 | +| clip_fraction | 0.346 | +| clip_range | 0.0665 | +| entropy_loss | -6.23 | +| explained_variance | 0.541 | +| learning_rate | 4.19e-05 | +| loss | -0.027 | +| n_updates | 82388 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000116 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.291 | +| time/ | | +| fps | 1395 | +| iterations | 16644 | +| time_elapsed | 24423 | +| total_timesteps | 34086912 | +| train/ | | +| approx_kl | 0.01429839 | +| clip_fraction | 0.315 | +| clip_range | 0.0665 | +| entropy_loss | -6.16 | +| explained_variance | 0.327 | +| learning_rate | 4.19e-05 | +| loss | -0.0221 | +| n_updates | 82392 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000211 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.295 | +| time/ | | +| fps | 1395 | +| iterations | 16645 | +| time_elapsed | 24425 | +| total_timesteps | 34088960 | +| train/ | | +| approx_kl | 0.013668977 | +| clip_fraction | 0.356 | +| clip_range | 0.0665 | +| entropy_loss | -5.67 | +| explained_variance | 0.555 | +| learning_rate | 4.19e-05 | +| loss | -0.0291 | +| n_updates | 82396 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000101 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.297 | +| time/ | | +| fps | 1395 | +| iterations | 16646 | +| time_elapsed | 24426 | +| total_timesteps | 34091008 | +| train/ | | +| approx_kl | 0.014893347 | +| clip_fraction | 0.362 | +| clip_range | 0.0665 | +| entropy_loss | -6.05 | +| explained_variance | 0.528 | +| learning_rate | 4.19e-05 | +| loss | -0.0311 | +| n_updates | 82400 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000124 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 1395 | +| iterations | 16647 | +| time_elapsed | 24428 | +| total_timesteps | 34093056 | +| train/ | | +| approx_kl | 0.016860988 | +| clip_fraction | 0.37 | +| clip_range | 0.0665 | +| entropy_loss | -6.11 | +| explained_variance | 0.414 | +| learning_rate | 4.19e-05 | +| loss | -0.034 | +| n_updates | 82404 | +| policy_gradient_loss | -0.0207 | +| value_loss | 9.21e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 1395 | +| iterations | 16648 | +| time_elapsed | 24429 | +| total_timesteps | 34095104 | +| train/ | | +| approx_kl | 0.013411607 | +| clip_fraction | 0.356 | +| clip_range | 0.0665 | +| entropy_loss | -6.19 | +| explained_variance | 0.248 | +| learning_rate | 4.19e-05 | +| loss | -0.0228 | +| n_updates | 82408 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000221 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.304 | +| time/ | | +| fps | 1395 | +| iterations | 16649 | +| time_elapsed | 24431 | +| total_timesteps | 34097152 | +| train/ | | +| approx_kl | 0.015476065 | +| clip_fraction | 0.381 | +| clip_range | 0.0665 | +| entropy_loss | -6.25 | +| explained_variance | 0.69 | +| learning_rate | 4.19e-05 | +| loss | -0.0408 | +| n_updates | 82412 | +| policy_gradient_loss | -0.0241 | +| value_loss | 3.38e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1395 | +| iterations | 16650 | +| time_elapsed | 24432 | +| total_timesteps | 34099200 | +| train/ | | +| approx_kl | 0.013505673 | +| clip_fraction | 0.335 | +| clip_range | 0.0665 | +| entropy_loss | -5.88 | +| explained_variance | 0.509 | +| learning_rate | 4.19e-05 | +| loss | -0.0248 | +| n_updates | 82416 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000197 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1395 | +| iterations | 16651 | +| time_elapsed | 24434 | +| total_timesteps | 34101248 | +| train/ | | +| approx_kl | 0.012915835 | +| clip_fraction | 0.356 | +| clip_range | 0.0665 | +| entropy_loss | -5.64 | +| explained_variance | 0.484 | +| learning_rate | 4.19e-05 | +| loss | -0.0325 | +| n_updates | 82420 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000184 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1395 | +| iterations | 16652 | +| time_elapsed | 24436 | +| total_timesteps | 34103296 | +| train/ | | +| approx_kl | 0.010914579 | +| clip_fraction | 0.345 | +| clip_range | 0.0665 | +| entropy_loss | -5.97 | +| explained_variance | 0.566 | +| learning_rate | 4.19e-05 | +| loss | -0.0317 | +| n_updates | 82424 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000148 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1395 | +| iterations | 16653 | +| time_elapsed | 24437 | +| total_timesteps | 34105344 | +| train/ | | +| approx_kl | 0.013502446 | +| clip_fraction | 0.338 | +| clip_range | 0.0665 | +| entropy_loss | -5.87 | +| explained_variance | 0.407 | +| learning_rate | 4.19e-05 | +| loss | -0.0311 | +| n_updates | 82428 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000174 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1395 | +| iterations | 16654 | +| time_elapsed | 24439 | +| total_timesteps | 34107392 | +| train/ | | +| approx_kl | 0.014576803 | +| clip_fraction | 0.345 | +| clip_range | 0.0665 | +| entropy_loss | -5.66 | +| explained_variance | 0.683 | +| learning_rate | 4.19e-05 | +| loss | -0.0318 | +| n_updates | 82432 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000102 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 1395 | +| iterations | 16655 | +| time_elapsed | 24440 | +| total_timesteps | 34109440 | +| train/ | | +| approx_kl | 0.019192446 | +| clip_fraction | 0.338 | +| clip_range | 0.0665 | +| entropy_loss | -5.27 | +| explained_variance | 0.514 | +| learning_rate | 4.19e-05 | +| loss | -0.0253 | +| n_updates | 82436 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000136 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1395 | +| iterations | 16656 | +| time_elapsed | 24442 | +| total_timesteps | 34111488 | +| train/ | | +| approx_kl | 0.012800084 | +| clip_fraction | 0.326 | +| clip_range | 0.0665 | +| entropy_loss | -5.89 | +| explained_variance | 0.533 | +| learning_rate | 4.19e-05 | +| loss | -0.0282 | +| n_updates | 82440 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000175 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1395 | +| iterations | 16657 | +| time_elapsed | 24443 | +| total_timesteps | 34113536 | +| train/ | | +| approx_kl | 0.0138594825 | +| clip_fraction | 0.346 | +| clip_range | 0.0665 | +| entropy_loss | -6.07 | +| explained_variance | 0.26 | +| learning_rate | 4.19e-05 | +| loss | -0.0273 | +| n_updates | 82444 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000209 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1395 | +| iterations | 16658 | +| time_elapsed | 24445 | +| total_timesteps | 34115584 | +| train/ | | +| approx_kl | 0.01432587 | +| clip_fraction | 0.376 | +| clip_range | 0.0665 | +| entropy_loss | -5.92 | +| explained_variance | 0.26 | +| learning_rate | 4.19e-05 | +| loss | -0.03 | +| n_updates | 82448 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000151 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1395 | +| iterations | 16659 | +| time_elapsed | 24446 | +| total_timesteps | 34117632 | +| train/ | | +| approx_kl | 0.016913775 | +| clip_fraction | 0.388 | +| clip_range | 0.0665 | +| entropy_loss | -5.73 | +| explained_variance | 0.194 | +| learning_rate | 4.19e-05 | +| loss | -0.0333 | +| n_updates | 82452 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000118 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.306 | +| time/ | | +| fps | 1395 | +| iterations | 16660 | +| time_elapsed | 24448 | +| total_timesteps | 34119680 | +| train/ | | +| approx_kl | 0.017977675 | +| clip_fraction | 0.399 | +| clip_range | 0.0665 | +| entropy_loss | -5.21 | +| explained_variance | 0.738 | +| learning_rate | 4.19e-05 | +| loss | -0.0325 | +| n_updates | 82456 | +| policy_gradient_loss | -0.0199 | +| value_loss | 7.3e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.306 | +| time/ | | +| fps | 1395 | +| iterations | 16661 | +| time_elapsed | 24449 | +| total_timesteps | 34121728 | +| train/ | | +| approx_kl | 0.016649712 | +| clip_fraction | 0.385 | +| clip_range | 0.0665 | +| entropy_loss | -5.2 | +| explained_variance | 0.725 | +| learning_rate | 4.19e-05 | +| loss | -0.0322 | +| n_updates | 82460 | +| policy_gradient_loss | -0.0211 | +| value_loss | 5.32e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 1395 | +| iterations | 16662 | +| time_elapsed | 24451 | +| total_timesteps | 34123776 | +| train/ | | +| approx_kl | 0.013365718 | +| clip_fraction | 0.334 | +| clip_range | 0.0665 | +| entropy_loss | -5.86 | +| explained_variance | 0.356 | +| learning_rate | 4.19e-05 | +| loss | -0.0268 | +| n_updates | 82464 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000105 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 1395 | +| iterations | 16663 | +| time_elapsed | 24452 | +| total_timesteps | 34125824 | +| train/ | | +| approx_kl | 0.015305625 | +| clip_fraction | 0.371 | +| clip_range | 0.0665 | +| entropy_loss | -6.4 | +| explained_variance | 0.0715 | +| learning_rate | 4.19e-05 | +| loss | -0.0278 | +| n_updates | 82468 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.304 | +| time/ | | +| fps | 1395 | +| iterations | 16664 | +| time_elapsed | 24454 | +| total_timesteps | 34127872 | +| train/ | | +| approx_kl | 0.011664585 | +| clip_fraction | 0.343 | +| clip_range | 0.0665 | +| entropy_loss | -6.26 | +| explained_variance | 0.408 | +| learning_rate | 4.19e-05 | +| loss | -0.0321 | +| n_updates | 82472 | +| policy_gradient_loss | -0.0195 | +| value_loss | 9.49e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 1395 | +| iterations | 16665 | +| time_elapsed | 24455 | +| total_timesteps | 34129920 | +| train/ | | +| approx_kl | 0.013588069 | +| clip_fraction | 0.346 | +| clip_range | 0.0665 | +| entropy_loss | -6.3 | +| explained_variance | 0.359 | +| learning_rate | 4.19e-05 | +| loss | -0.0286 | +| n_updates | 82476 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000118 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 1395 | +| iterations | 16666 | +| time_elapsed | 24457 | +| total_timesteps | 34131968 | +| train/ | | +| approx_kl | 0.011770387 | +| clip_fraction | 0.324 | +| clip_range | 0.0665 | +| entropy_loss | -6.04 | +| explained_variance | 0.483 | +| learning_rate | 4.19e-05 | +| loss | -0.0233 | +| n_updates | 82480 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000212 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 1395 | +| iterations | 16667 | +| time_elapsed | 24458 | +| total_timesteps | 34134016 | +| train/ | | +| approx_kl | 0.015299885 | +| clip_fraction | 0.334 | +| clip_range | 0.0665 | +| entropy_loss | -6.03 | +| explained_variance | 0.367 | +| learning_rate | 4.19e-05 | +| loss | -0.0282 | +| n_updates | 82484 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000116 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 1395 | +| iterations | 16668 | +| time_elapsed | 24460 | +| total_timesteps | 34136064 | +| train/ | | +| approx_kl | 0.01184154 | +| clip_fraction | 0.339 | +| clip_range | 0.0665 | +| entropy_loss | -6.41 | +| explained_variance | 0.21 | +| learning_rate | 4.19e-05 | +| loss | -0.023 | +| n_updates | 82488 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000297 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.302 | +| time/ | | +| fps | 1395 | +| iterations | 16669 | +| time_elapsed | 24461 | +| total_timesteps | 34138112 | +| train/ | | +| approx_kl | 0.010902789 | +| clip_fraction | 0.313 | +| clip_range | 0.0665 | +| entropy_loss | -5.86 | +| explained_variance | 0.481 | +| learning_rate | 4.19e-05 | +| loss | -0.0134 | +| n_updates | 82492 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000161 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.3 | +| time/ | | +| fps | 1395 | +| iterations | 16670 | +| time_elapsed | 24463 | +| total_timesteps | 34140160 | +| train/ | | +| approx_kl | 0.018357258 | +| clip_fraction | 0.359 | +| clip_range | 0.0665 | +| entropy_loss | -5.97 | +| explained_variance | 0.494 | +| learning_rate | 4.19e-05 | +| loss | -0.0323 | +| n_updates | 82496 | +| policy_gradient_loss | -0.0208 | +| value_loss | 7.08e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.298 | +| time/ | | +| fps | 1395 | +| iterations | 16671 | +| time_elapsed | 24464 | +| total_timesteps | 34142208 | +| train/ | | +| approx_kl | 0.014869412 | +| clip_fraction | 0.374 | +| clip_range | 0.0665 | +| entropy_loss | -5.27 | +| explained_variance | 0.853 | +| learning_rate | 4.19e-05 | +| loss | -0.0346 | +| n_updates | 82500 | +| policy_gradient_loss | -0.0222 | +| value_loss | 3.76e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.298 | +| time/ | | +| fps | 1395 | +| iterations | 16672 | +| time_elapsed | 24466 | +| total_timesteps | 34144256 | +| train/ | | +| approx_kl | 0.015587873 | +| clip_fraction | 0.346 | +| clip_range | 0.0665 | +| entropy_loss | -5.42 | +| explained_variance | 0.281 | +| learning_rate | 4.19e-05 | +| loss | -0.0227 | +| n_updates | 82504 | +| policy_gradient_loss | -0.0156 | +| value_loss | 8.41e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 1395 | +| iterations | 16673 | +| time_elapsed | 24467 | +| total_timesteps | 34146304 | +| train/ | | +| approx_kl | 0.013902553 | +| clip_fraction | 0.334 | +| clip_range | 0.0665 | +| entropy_loss | -5.66 | +| explained_variance | 0.604 | +| learning_rate | 4.19e-05 | +| loss | -0.024 | +| n_updates | 82508 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000117 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.304 | +| time/ | | +| fps | 1395 | +| iterations | 16674 | +| time_elapsed | 24469 | +| total_timesteps | 34148352 | +| train/ | | +| approx_kl | 0.011203538 | +| clip_fraction | 0.294 | +| clip_range | 0.0665 | +| entropy_loss | -6.2 | +| explained_variance | 0.525 | +| learning_rate | 4.19e-05 | +| loss | -0.0257 | +| n_updates | 82512 | +| policy_gradient_loss | -0.0162 | +| value_loss | 7.9e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.304 | +| time/ | | +| fps | 1395 | +| iterations | 16675 | +| time_elapsed | 24471 | +| total_timesteps | 34150400 | +| train/ | | +| approx_kl | 0.014020313 | +| clip_fraction | 0.306 | +| clip_range | 0.0665 | +| entropy_loss | -5.67 | +| explained_variance | 0.491 | +| learning_rate | 4.19e-05 | +| loss | -0.0272 | +| n_updates | 82516 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000244 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.304 | +| time/ | | +| fps | 1395 | +| iterations | 16676 | +| time_elapsed | 24472 | +| total_timesteps | 34152448 | +| train/ | | +| approx_kl | 0.015323469 | +| clip_fraction | 0.377 | +| clip_range | 0.0665 | +| entropy_loss | -6.07 | +| explained_variance | 0.00909 | +| learning_rate | 4.19e-05 | +| loss | -0.0344 | +| n_updates | 82520 | +| policy_gradient_loss | -0.0209 | +| value_loss | 9.35e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 1395 | +| iterations | 16677 | +| time_elapsed | 24474 | +| total_timesteps | 34154496 | +| train/ | | +| approx_kl | 0.0137979835 | +| clip_fraction | 0.367 | +| clip_range | 0.0665 | +| entropy_loss | -6.48 | +| explained_variance | 0.314 | +| learning_rate | 4.19e-05 | +| loss | -0.0277 | +| n_updates | 82524 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000166 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 1395 | +| iterations | 16678 | +| time_elapsed | 24475 | +| total_timesteps | 34156544 | +| train/ | | +| approx_kl | 0.011974383 | +| clip_fraction | 0.345 | +| clip_range | 0.0665 | +| entropy_loss | -6.69 | +| explained_variance | -0.0386 | +| learning_rate | 4.19e-05 | +| loss | -0.0236 | +| n_updates | 82528 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000151 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 1395 | +| iterations | 16679 | +| time_elapsed | 24477 | +| total_timesteps | 34158592 | +| train/ | | +| approx_kl | 0.016513608 | +| clip_fraction | 0.328 | +| clip_range | 0.0665 | +| entropy_loss | -6.32 | +| explained_variance | 0.418 | +| learning_rate | 4.19e-05 | +| loss | -0.0282 | +| n_updates | 82532 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000178 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1395 | +| iterations | 16680 | +| time_elapsed | 24478 | +| total_timesteps | 34160640 | +| train/ | | +| approx_kl | 0.0141188195 | +| clip_fraction | 0.351 | +| clip_range | 0.0665 | +| entropy_loss | -5.82 | +| explained_variance | 0.725 | +| learning_rate | 4.19e-05 | +| loss | -0.0282 | +| n_updates | 82536 | +| policy_gradient_loss | -0.0206 | +| value_loss | 7.77e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1395 | +| iterations | 16681 | +| time_elapsed | 24480 | +| total_timesteps | 34162688 | +| train/ | | +| approx_kl | 0.011480594 | +| clip_fraction | 0.319 | +| clip_range | 0.0665 | +| entropy_loss | -5.73 | +| explained_variance | 0.371 | +| learning_rate | 4.19e-05 | +| loss | -0.0258 | +| n_updates | 82540 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000224 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1395 | +| iterations | 16682 | +| time_elapsed | 24481 | +| total_timesteps | 34164736 | +| train/ | | +| approx_kl | 0.012985417 | +| clip_fraction | 0.362 | +| clip_range | 0.0665 | +| entropy_loss | -5.61 | +| explained_variance | 0.318 | +| learning_rate | 4.19e-05 | +| loss | -0.0309 | +| n_updates | 82544 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000153 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1395 | +| iterations | 16683 | +| time_elapsed | 24483 | +| total_timesteps | 34166784 | +| train/ | | +| approx_kl | 0.015047224 | +| clip_fraction | 0.322 | +| clip_range | 0.0665 | +| entropy_loss | -6.04 | +| explained_variance | 0.603 | +| learning_rate | 4.19e-05 | +| loss | -0.0279 | +| n_updates | 82548 | +| policy_gradient_loss | -0.0184 | +| value_loss | 7.21e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1395 | +| iterations | 16684 | +| time_elapsed | 24484 | +| total_timesteps | 34168832 | +| train/ | | +| approx_kl | 0.01428036 | +| clip_fraction | 0.3 | +| clip_range | 0.0665 | +| entropy_loss | -5.81 | +| explained_variance | 0.528 | +| learning_rate | 4.19e-05 | +| loss | -0.0207 | +| n_updates | 82552 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.000169 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1395 | +| iterations | 16685 | +| time_elapsed | 24486 | +| total_timesteps | 34170880 | +| train/ | | +| approx_kl | 0.01343652 | +| clip_fraction | 0.322 | +| clip_range | 0.0665 | +| entropy_loss | -5.59 | +| explained_variance | 0.586 | +| learning_rate | 4.19e-05 | +| loss | -0.0253 | +| n_updates | 82556 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.00014 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1395 | +| iterations | 16686 | +| time_elapsed | 24487 | +| total_timesteps | 34172928 | +| train/ | | +| approx_kl | 0.016207196 | +| clip_fraction | 0.361 | +| clip_range | 0.0665 | +| entropy_loss | -5.75 | +| explained_variance | 0.395 | +| learning_rate | 4.19e-05 | +| loss | -0.0287 | +| n_updates | 82560 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000157 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1395 | +| iterations | 16687 | +| time_elapsed | 24489 | +| total_timesteps | 34174976 | +| train/ | | +| approx_kl | 0.014366694 | +| clip_fraction | 0.356 | +| clip_range | 0.0665 | +| entropy_loss | -6.24 | +| explained_variance | 0.292 | +| learning_rate | 4.19e-05 | +| loss | -0.0308 | +| n_updates | 82564 | +| policy_gradient_loss | -0.0207 | +| value_loss | 9.85e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1395 | +| iterations | 16688 | +| time_elapsed | 24490 | +| total_timesteps | 34177024 | +| train/ | | +| approx_kl | 0.014497034 | +| clip_fraction | 0.322 | +| clip_range | 0.0665 | +| entropy_loss | -5.45 | +| explained_variance | 0.51 | +| learning_rate | 4.19e-05 | +| loss | -0.0209 | +| n_updates | 82568 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000172 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1395 | +| iterations | 16689 | +| time_elapsed | 24492 | +| total_timesteps | 34179072 | +| train/ | | +| approx_kl | 0.012869734 | +| clip_fraction | 0.355 | +| clip_range | 0.0665 | +| entropy_loss | -5.69 | +| explained_variance | 0.237 | +| learning_rate | 4.19e-05 | +| loss | -0.0312 | +| n_updates | 82572 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000246 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1395 | +| iterations | 16690 | +| time_elapsed | 24493 | +| total_timesteps | 34181120 | +| train/ | | +| approx_kl | 0.0145135615 | +| clip_fraction | 0.365 | +| clip_range | 0.0665 | +| entropy_loss | -6 | +| explained_variance | 0.687 | +| learning_rate | 4.19e-05 | +| loss | -0.0393 | +| n_updates | 82576 | +| policy_gradient_loss | -0.0226 | +| value_loss | 6.56e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 1395 | +| iterations | 16691 | +| time_elapsed | 24495 | +| total_timesteps | 34183168 | +| train/ | | +| approx_kl | 0.011472087 | +| clip_fraction | 0.348 | +| clip_range | 0.0665 | +| entropy_loss | -6.56 | +| explained_variance | -0.0927 | +| learning_rate | 4.19e-05 | +| loss | -0.0301 | +| n_updates | 82580 | +| policy_gradient_loss | -0.0186 | +| value_loss | 8.12e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.304 | +| time/ | | +| fps | 1395 | +| iterations | 16692 | +| time_elapsed | 24497 | +| total_timesteps | 34185216 | +| train/ | | +| approx_kl | 0.010129876 | +| clip_fraction | 0.316 | +| clip_range | 0.0665 | +| entropy_loss | -6.31 | +| explained_variance | 0.372 | +| learning_rate | 4.19e-05 | +| loss | -0.0255 | +| n_updates | 82584 | +| policy_gradient_loss | -0.0143 | +| value_loss | 0.000206 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.302 | +| time/ | | +| fps | 1395 | +| iterations | 16693 | +| time_elapsed | 24498 | +| total_timesteps | 34187264 | +| train/ | | +| approx_kl | 0.01215407 | +| clip_fraction | 0.322 | +| clip_range | 0.0665 | +| entropy_loss | -4.66 | +| explained_variance | 0.7 | +| learning_rate | 4.19e-05 | +| loss | -0.0265 | +| n_updates | 82588 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000132 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 1395 | +| iterations | 16694 | +| time_elapsed | 24500 | +| total_timesteps | 34189312 | +| train/ | | +| approx_kl | 0.012737064 | +| clip_fraction | 0.337 | +| clip_range | 0.0665 | +| entropy_loss | -5.41 | +| explained_variance | 0.516 | +| learning_rate | 4.19e-05 | +| loss | -0.0223 | +| n_updates | 82592 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000235 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 1395 | +| iterations | 16695 | +| time_elapsed | 24501 | +| total_timesteps | 34191360 | +| train/ | | +| approx_kl | 0.015177261 | +| clip_fraction | 0.365 | +| clip_range | 0.0665 | +| entropy_loss | -5.22 | +| explained_variance | 0.462 | +| learning_rate | 4.19e-05 | +| loss | -0.0286 | +| n_updates | 82596 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000151 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 1395 | +| iterations | 16696 | +| time_elapsed | 24503 | +| total_timesteps | 34193408 | +| train/ | | +| approx_kl | 0.013477368 | +| clip_fraction | 0.372 | +| clip_range | 0.0665 | +| entropy_loss | -5.89 | +| explained_variance | -0.398 | +| learning_rate | 4.19e-05 | +| loss | -0.0265 | +| n_updates | 82600 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000111 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.304 | +| time/ | | +| fps | 1395 | +| iterations | 16697 | +| time_elapsed | 24504 | +| total_timesteps | 34195456 | +| train/ | | +| approx_kl | 0.0141028315 | +| clip_fraction | 0.345 | +| clip_range | 0.0665 | +| entropy_loss | -6.78 | +| explained_variance | 0.0353 | +| learning_rate | 4.19e-05 | +| loss | -0.0325 | +| n_updates | 82604 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000139 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 1395 | +| iterations | 16698 | +| time_elapsed | 24506 | +| total_timesteps | 34197504 | +| train/ | | +| approx_kl | 0.012470807 | +| clip_fraction | 0.31 | +| clip_range | 0.0665 | +| entropy_loss | -6.47 | +| explained_variance | 0.389 | +| learning_rate | 4.19e-05 | +| loss | -0.024 | +| n_updates | 82608 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000191 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1395 | +| iterations | 16699 | +| time_elapsed | 24507 | +| total_timesteps | 34199552 | +| train/ | | +| approx_kl | 0.010165593 | +| clip_fraction | 0.295 | +| clip_range | 0.0665 | +| entropy_loss | -5.89 | +| explained_variance | 0.414 | +| learning_rate | 4.19e-05 | +| loss | -0.0255 | +| n_updates | 82612 | +| policy_gradient_loss | -0.0145 | +| value_loss | 0.000299 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1395 | +| iterations | 16700 | +| time_elapsed | 24509 | +| total_timesteps | 34201600 | +| train/ | | +| approx_kl | 0.012182312 | +| clip_fraction | 0.355 | +| clip_range | 0.0665 | +| entropy_loss | -6.27 | +| explained_variance | 0.00252 | +| learning_rate | 4.19e-05 | +| loss | -0.0313 | +| n_updates | 82616 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000226 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1395 | +| iterations | 16701 | +| time_elapsed | 24510 | +| total_timesteps | 34203648 | +| train/ | | +| approx_kl | 0.012879083 | +| clip_fraction | 0.365 | +| clip_range | 0.0664 | +| entropy_loss | -6.01 | +| explained_variance | 0.369 | +| learning_rate | 4.19e-05 | +| loss | -0.0368 | +| n_updates | 82620 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000114 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 1395 | +| iterations | 16702 | +| time_elapsed | 24512 | +| total_timesteps | 34205696 | +| train/ | | +| approx_kl | 0.013074577 | +| clip_fraction | 0.33 | +| clip_range | 0.0664 | +| entropy_loss | -5.72 | +| explained_variance | 0.72 | +| learning_rate | 4.19e-05 | +| loss | -0.0228 | +| n_updates | 82624 | +| policy_gradient_loss | -0.0173 | +| value_loss | 8.68e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 1395 | +| iterations | 16703 | +| time_elapsed | 24513 | +| total_timesteps | 34207744 | +| train/ | | +| approx_kl | 0.00903474 | +| clip_fraction | 0.332 | +| clip_range | 0.0664 | +| entropy_loss | -6.31 | +| explained_variance | 0.324 | +| learning_rate | 4.19e-05 | +| loss | -0.0258 | +| n_updates | 82628 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000144 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.304 | +| time/ | | +| fps | 1395 | +| iterations | 16704 | +| time_elapsed | 24515 | +| total_timesteps | 34209792 | +| train/ | | +| approx_kl | 0.0125933895 | +| clip_fraction | 0.323 | +| clip_range | 0.0664 | +| entropy_loss | -6 | +| explained_variance | 0.65 | +| learning_rate | 4.19e-05 | +| loss | -0.0275 | +| n_updates | 82632 | +| policy_gradient_loss | -0.0178 | +| value_loss | 9.08e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 1395 | +| iterations | 16705 | +| time_elapsed | 24517 | +| total_timesteps | 34211840 | +| train/ | | +| approx_kl | 0.014710018 | +| clip_fraction | 0.346 | +| clip_range | 0.0664 | +| entropy_loss | -5.62 | +| explained_variance | 0.695 | +| learning_rate | 4.19e-05 | +| loss | -0.0284 | +| n_updates | 82636 | +| policy_gradient_loss | -0.0189 | +| value_loss | 7.1e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 1395 | +| iterations | 16706 | +| time_elapsed | 24518 | +| total_timesteps | 34213888 | +| train/ | | +| approx_kl | 0.011881944 | +| clip_fraction | 0.327 | +| clip_range | 0.0664 | +| entropy_loss | -6.07 | +| explained_variance | 0.538 | +| learning_rate | 4.19e-05 | +| loss | -0.0222 | +| n_updates | 82640 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000107 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.306 | +| time/ | | +| fps | 1395 | +| iterations | 16707 | +| time_elapsed | 24520 | +| total_timesteps | 34215936 | +| train/ | | +| approx_kl | 0.020970311 | +| clip_fraction | 0.346 | +| clip_range | 0.0664 | +| entropy_loss | -6.1 | +| explained_variance | 0.532 | +| learning_rate | 4.19e-05 | +| loss | -0.0323 | +| n_updates | 82644 | +| policy_gradient_loss | -0.0207 | +| value_loss | 5.33e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.304 | +| time/ | | +| fps | 1395 | +| iterations | 16708 | +| time_elapsed | 24521 | +| total_timesteps | 34217984 | +| train/ | | +| approx_kl | 0.016419854 | +| clip_fraction | 0.343 | +| clip_range | 0.0664 | +| entropy_loss | -6.47 | +| explained_variance | 0.316 | +| learning_rate | 4.19e-05 | +| loss | -0.0299 | +| n_updates | 82648 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000136 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.304 | +| time/ | | +| fps | 1395 | +| iterations | 16709 | +| time_elapsed | 24523 | +| total_timesteps | 34220032 | +| train/ | | +| approx_kl | 0.012537522 | +| clip_fraction | 0.334 | +| clip_range | 0.0664 | +| entropy_loss | -6.41 | +| explained_variance | 0.422 | +| learning_rate | 4.19e-05 | +| loss | -0.032 | +| n_updates | 82652 | +| policy_gradient_loss | -0.0183 | +| value_loss | 8.91e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 1395 | +| iterations | 16710 | +| time_elapsed | 24524 | +| total_timesteps | 34222080 | +| train/ | | +| approx_kl | 0.010853024 | +| clip_fraction | 0.322 | +| clip_range | 0.0664 | +| entropy_loss | -6.14 | +| explained_variance | 0.411 | +| learning_rate | 4.19e-05 | +| loss | -0.0246 | +| n_updates | 82656 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000201 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 1395 | +| iterations | 16711 | +| time_elapsed | 24526 | +| total_timesteps | 34224128 | +| train/ | | +| approx_kl | 0.0117925685 | +| clip_fraction | 0.314 | +| clip_range | 0.0664 | +| entropy_loss | -5.08 | +| explained_variance | 0.509 | +| learning_rate | 4.19e-05 | +| loss | -0.0253 | +| n_updates | 82660 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000256 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.302 | +| time/ | | +| fps | 1395 | +| iterations | 16712 | +| time_elapsed | 24527 | +| total_timesteps | 34226176 | +| train/ | | +| approx_kl | 0.011846375 | +| clip_fraction | 0.342 | +| clip_range | 0.0664 | +| entropy_loss | -5.33 | +| explained_variance | 0.554 | +| learning_rate | 4.19e-05 | +| loss | -0.0311 | +| n_updates | 82664 | +| policy_gradient_loss | -0.0201 | +| value_loss | 9.45e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.302 | +| time/ | | +| fps | 1395 | +| iterations | 16713 | +| time_elapsed | 24529 | +| total_timesteps | 34228224 | +| train/ | | +| approx_kl | 0.016381133 | +| clip_fraction | 0.345 | +| clip_range | 0.0664 | +| entropy_loss | -6.11 | +| explained_variance | 0.224 | +| learning_rate | 4.19e-05 | +| loss | -0.0298 | +| n_updates | 82668 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.00018 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 1395 | +| iterations | 16714 | +| time_elapsed | 24531 | +| total_timesteps | 34230272 | +| train/ | | +| approx_kl | 0.013549408 | +| clip_fraction | 0.372 | +| clip_range | 0.0664 | +| entropy_loss | -6.27 | +| explained_variance | 0.432 | +| learning_rate | 4.19e-05 | +| loss | -0.0362 | +| n_updates | 82672 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000101 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 1395 | +| iterations | 16715 | +| time_elapsed | 24532 | +| total_timesteps | 34232320 | +| train/ | | +| approx_kl | 0.013566654 | +| clip_fraction | 0.342 | +| clip_range | 0.0664 | +| entropy_loss | -6.54 | +| explained_variance | 0.444 | +| learning_rate | 4.19e-05 | +| loss | -0.0281 | +| n_updates | 82676 | +| policy_gradient_loss | -0.018 | +| value_loss | 9.5e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.297 | +| time/ | | +| fps | 1395 | +| iterations | 16716 | +| time_elapsed | 24533 | +| total_timesteps | 34234368 | +| train/ | | +| approx_kl | 0.011226245 | +| clip_fraction | 0.309 | +| clip_range | 0.0664 | +| entropy_loss | -5.99 | +| explained_variance | 0.494 | +| learning_rate | 4.19e-05 | +| loss | -0.0195 | +| n_updates | 82680 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.000204 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.297 | +| time/ | | +| fps | 1395 | +| iterations | 16717 | +| time_elapsed | 24535 | +| total_timesteps | 34236416 | +| train/ | | +| approx_kl | 0.015449249 | +| clip_fraction | 0.342 | +| clip_range | 0.0664 | +| entropy_loss | -5.71 | +| explained_variance | 0.592 | +| learning_rate | 4.19e-05 | +| loss | -0.0258 | +| n_updates | 82684 | +| policy_gradient_loss | -0.0179 | +| value_loss | 9.97e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.3 | +| time/ | | +| fps | 1395 | +| iterations | 16718 | +| time_elapsed | 24536 | +| total_timesteps | 34238464 | +| train/ | | +| approx_kl | 0.015231447 | +| clip_fraction | 0.372 | +| clip_range | 0.0664 | +| entropy_loss | -5.9 | +| explained_variance | -0.0663 | +| learning_rate | 4.19e-05 | +| loss | -0.03 | +| n_updates | 82688 | +| policy_gradient_loss | -0.0208 | +| value_loss | 8.37e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 1395 | +| iterations | 16719 | +| time_elapsed | 24538 | +| total_timesteps | 34240512 | +| train/ | | +| approx_kl | 0.01388533 | +| clip_fraction | 0.371 | +| clip_range | 0.0664 | +| entropy_loss | -6.74 | +| explained_variance | -0.0343 | +| learning_rate | 4.19e-05 | +| loss | -0.0259 | +| n_updates | 82692 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.00014 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 1395 | +| iterations | 16720 | +| time_elapsed | 24540 | +| total_timesteps | 34242560 | +| train/ | | +| approx_kl | 0.011952466 | +| clip_fraction | 0.31 | +| clip_range | 0.0664 | +| entropy_loss | -6.15 | +| explained_variance | 0.469 | +| learning_rate | 4.19e-05 | +| loss | -0.0229 | +| n_updates | 82696 | +| policy_gradient_loss | -0.0145 | +| value_loss | 0.000255 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 1395 | +| iterations | 16721 | +| time_elapsed | 24541 | +| total_timesteps | 34244608 | +| train/ | | +| approx_kl | 0.011700386 | +| clip_fraction | 0.343 | +| clip_range | 0.0664 | +| entropy_loss | -4.78 | +| explained_variance | 0.796 | +| learning_rate | 4.19e-05 | +| loss | -0.028 | +| n_updates | 82700 | +| policy_gradient_loss | -0.0179 | +| value_loss | 8.89e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 1395 | +| iterations | 16722 | +| time_elapsed | 24543 | +| total_timesteps | 34246656 | +| train/ | | +| approx_kl | 0.011925754 | +| clip_fraction | 0.364 | +| clip_range | 0.0664 | +| entropy_loss | -6.51 | +| explained_variance | -0.185 | +| learning_rate | 4.19e-05 | +| loss | -0.0306 | +| n_updates | 82704 | +| policy_gradient_loss | -0.0203 | +| value_loss | 7.23e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 1395 | +| iterations | 16723 | +| time_elapsed | 24544 | +| total_timesteps | 34248704 | +| train/ | | +| approx_kl | 0.010888372 | +| clip_fraction | 0.331 | +| clip_range | 0.0664 | +| entropy_loss | -6.31 | +| explained_variance | 0.392 | +| learning_rate | 4.19e-05 | +| loss | -0.0233 | +| n_updates | 82708 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000182 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.306 | +| time/ | | +| fps | 1395 | +| iterations | 16724 | +| time_elapsed | 24546 | +| total_timesteps | 34250752 | +| train/ | | +| approx_kl | 0.014287464 | +| clip_fraction | 0.351 | +| clip_range | 0.0664 | +| entropy_loss | -5.84 | +| explained_variance | 0.484 | +| learning_rate | 4.19e-05 | +| loss | -0.0285 | +| n_updates | 82712 | +| policy_gradient_loss | -0.0185 | +| value_loss | 8.29e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.306 | +| time/ | | +| fps | 1395 | +| iterations | 16725 | +| time_elapsed | 24547 | +| total_timesteps | 34252800 | +| train/ | | +| approx_kl | 0.012274091 | +| clip_fraction | 0.327 | +| clip_range | 0.0664 | +| entropy_loss | -6.12 | +| explained_variance | 0.361 | +| learning_rate | 4.19e-05 | +| loss | -0.0297 | +| n_updates | 82716 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000144 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.302 | +| time/ | | +| fps | 1395 | +| iterations | 16726 | +| time_elapsed | 24549 | +| total_timesteps | 34254848 | +| train/ | | +| approx_kl | 0.011211021 | +| clip_fraction | 0.35 | +| clip_range | 0.0664 | +| entropy_loss | -6.84 | +| explained_variance | -0.0145 | +| learning_rate | 4.19e-05 | +| loss | -0.034 | +| n_updates | 82720 | +| policy_gradient_loss | -0.0219 | +| value_loss | 5.77e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 1395 | +| iterations | 16727 | +| time_elapsed | 24550 | +| total_timesteps | 34256896 | +| train/ | | +| approx_kl | 0.012746341 | +| clip_fraction | 0.32 | +| clip_range | 0.0664 | +| entropy_loss | -6.94 | +| explained_variance | 0.0209 | +| learning_rate | 4.19e-05 | +| loss | -0.0246 | +| n_updates | 82724 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000101 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.3 | +| time/ | | +| fps | 1395 | +| iterations | 16728 | +| time_elapsed | 24552 | +| total_timesteps | 34258944 | +| train/ | | +| approx_kl | 0.013394726 | +| clip_fraction | 0.307 | +| clip_range | 0.0664 | +| entropy_loss | -5.87 | +| explained_variance | 0.64 | +| learning_rate | 4.19e-05 | +| loss | -0.0233 | +| n_updates | 82728 | +| policy_gradient_loss | -0.0147 | +| value_loss | 0.000131 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.294 | +| time/ | | +| fps | 1395 | +| iterations | 16729 | +| time_elapsed | 24553 | +| total_timesteps | 34260992 | +| train/ | | +| approx_kl | 0.015250897 | +| clip_fraction | 0.343 | +| clip_range | 0.0664 | +| entropy_loss | -5.24 | +| explained_variance | 0.763 | +| learning_rate | 4.19e-05 | +| loss | -0.0281 | +| n_updates | 82732 | +| policy_gradient_loss | -0.017 | +| value_loss | 9.35e-05 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 1395 | +| iterations | 16730 | +| time_elapsed | 24555 | +| total_timesteps | 34263040 | +| train/ | | +| approx_kl | 0.0121804 | +| clip_fraction | 0.338 | +| clip_range | 0.0664 | +| entropy_loss | -5.64 | +| explained_variance | 0.466 | +| learning_rate | 4.19e-05 | +| loss | -0.0319 | +| n_updates | 82736 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000145 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.295 | +| time/ | | +| fps | 1395 | +| iterations | 16731 | +| time_elapsed | 24556 | +| total_timesteps | 34265088 | +| train/ | | +| approx_kl | 0.015277186 | +| clip_fraction | 0.34 | +| clip_range | 0.0664 | +| entropy_loss | -6.08 | +| explained_variance | 0.485 | +| learning_rate | 4.19e-05 | +| loss | -0.0295 | +| n_updates | 82740 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000103 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.295 | +| time/ | | +| fps | 1395 | +| iterations | 16732 | +| time_elapsed | 24558 | +| total_timesteps | 34267136 | +| train/ | | +| approx_kl | 0.015151842 | +| clip_fraction | 0.343 | +| clip_range | 0.0664 | +| entropy_loss | -5.99 | +| explained_variance | 0.498 | +| learning_rate | 4.19e-05 | +| loss | -0.0272 | +| n_updates | 82744 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000139 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 1395 | +| iterations | 16733 | +| time_elapsed | 24559 | +| total_timesteps | 34269184 | +| train/ | | +| approx_kl | 0.016040107 | +| clip_fraction | 0.37 | +| clip_range | 0.0664 | +| entropy_loss | -6.34 | +| explained_variance | 0.529 | +| learning_rate | 4.19e-05 | +| loss | -0.0257 | +| n_updates | 82748 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000107 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 1395 | +| iterations | 16734 | +| time_elapsed | 24561 | +| total_timesteps | 34271232 | +| train/ | | +| approx_kl | 0.012467065 | +| clip_fraction | 0.346 | +| clip_range | 0.0664 | +| entropy_loss | -6.37 | +| explained_variance | 0.367 | +| learning_rate | 4.19e-05 | +| loss | -0.0272 | +| n_updates | 82752 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000142 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1395 | +| iterations | 16735 | +| time_elapsed | 24562 | +| total_timesteps | 34273280 | +| train/ | | +| approx_kl | 0.016573552 | +| clip_fraction | 0.353 | +| clip_range | 0.0664 | +| entropy_loss | -6.24 | +| explained_variance | 0.507 | +| learning_rate | 4.19e-05 | +| loss | -0.0292 | +| n_updates | 82756 | +| policy_gradient_loss | -0.019 | +| value_loss | 7.89e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1395 | +| iterations | 16736 | +| time_elapsed | 24564 | +| total_timesteps | 34275328 | +| train/ | | +| approx_kl | 0.013467887 | +| clip_fraction | 0.295 | +| clip_range | 0.0664 | +| entropy_loss | -6.04 | +| explained_variance | 0.349 | +| learning_rate | 4.19e-05 | +| loss | -0.0274 | +| n_updates | 82760 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000332 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 1395 | +| iterations | 16737 | +| time_elapsed | 24566 | +| total_timesteps | 34277376 | +| train/ | | +| approx_kl | 0.011158338 | +| clip_fraction | 0.306 | +| clip_range | 0.0664 | +| entropy_loss | -5.69 | +| explained_variance | 0.545 | +| learning_rate | 4.19e-05 | +| loss | -0.028 | +| n_updates | 82764 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000129 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 1395 | +| iterations | 16738 | +| time_elapsed | 24567 | +| total_timesteps | 34279424 | +| train/ | | +| approx_kl | 0.013147155 | +| clip_fraction | 0.32 | +| clip_range | 0.0664 | +| entropy_loss | -5.53 | +| explained_variance | 0.668 | +| learning_rate | 4.19e-05 | +| loss | -0.0279 | +| n_updates | 82768 | +| policy_gradient_loss | -0.0186 | +| value_loss | 9.05e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1395 | +| iterations | 16739 | +| time_elapsed | 24569 | +| total_timesteps | 34281472 | +| train/ | | +| approx_kl | 0.0133181345 | +| clip_fraction | 0.332 | +| clip_range | 0.0664 | +| entropy_loss | -6.16 | +| explained_variance | 0.219 | +| learning_rate | 4.19e-05 | +| loss | -0.0345 | +| n_updates | 82772 | +| policy_gradient_loss | -0.0194 | +| value_loss | 9.13e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1395 | +| iterations | 16740 | +| time_elapsed | 24570 | +| total_timesteps | 34283520 | +| train/ | | +| approx_kl | 0.017196584 | +| clip_fraction | 0.31 | +| clip_range | 0.0664 | +| entropy_loss | -5.24 | +| explained_variance | 0.454 | +| learning_rate | 4.19e-05 | +| loss | -0.0232 | +| n_updates | 82776 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.00032 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1395 | +| iterations | 16741 | +| time_elapsed | 24572 | +| total_timesteps | 34285568 | +| train/ | | +| approx_kl | 0.014533593 | +| clip_fraction | 0.344 | +| clip_range | 0.0664 | +| entropy_loss | -6.11 | +| explained_variance | -0.239 | +| learning_rate | 4.19e-05 | +| loss | -0.0367 | +| n_updates | 82780 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000139 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1395 | +| iterations | 16742 | +| time_elapsed | 24573 | +| total_timesteps | 34287616 | +| train/ | | +| approx_kl | 0.012702982 | +| clip_fraction | 0.31 | +| clip_range | 0.0664 | +| entropy_loss | -6.36 | +| explained_variance | 0.143 | +| learning_rate | 4.19e-05 | +| loss | -0.0295 | +| n_updates | 82784 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000291 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1395 | +| iterations | 16743 | +| time_elapsed | 24575 | +| total_timesteps | 34289664 | +| train/ | | +| approx_kl | 0.010471685 | +| clip_fraction | 0.299 | +| clip_range | 0.0664 | +| entropy_loss | -6.15 | +| explained_variance | 0.347 | +| learning_rate | 4.19e-05 | +| loss | -0.0201 | +| n_updates | 82788 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.000368 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1395 | +| iterations | 16744 | +| time_elapsed | 24576 | +| total_timesteps | 34291712 | +| train/ | | +| approx_kl | 0.010675734 | +| clip_fraction | 0.318 | +| clip_range | 0.0664 | +| entropy_loss | -6.29 | +| explained_variance | 0.323 | +| learning_rate | 4.19e-05 | +| loss | -0.029 | +| n_updates | 82792 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000213 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1395 | +| iterations | 16745 | +| time_elapsed | 24578 | +| total_timesteps | 34293760 | +| train/ | | +| approx_kl | 0.011797955 | +| clip_fraction | 0.304 | +| clip_range | 0.0664 | +| entropy_loss | -5.91 | +| explained_variance | 0.436 | +| learning_rate | 4.19e-05 | +| loss | -0.0286 | +| n_updates | 82796 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000214 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1395 | +| iterations | 16746 | +| time_elapsed | 24580 | +| total_timesteps | 34295808 | +| train/ | | +| approx_kl | 0.012742832 | +| clip_fraction | 0.313 | +| clip_range | 0.0664 | +| entropy_loss | -5.77 | +| explained_variance | 0.329 | +| learning_rate | 4.19e-05 | +| loss | -0.0264 | +| n_updates | 82800 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000197 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1395 | +| iterations | 16747 | +| time_elapsed | 24581 | +| total_timesteps | 34297856 | +| train/ | | +| approx_kl | 0.014960258 | +| clip_fraction | 0.291 | +| clip_range | 0.0664 | +| entropy_loss | -5.6 | +| explained_variance | 0.457 | +| learning_rate | 4.19e-05 | +| loss | -0.0272 | +| n_updates | 82804 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.000253 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1395 | +| iterations | 16748 | +| time_elapsed | 24583 | +| total_timesteps | 34299904 | +| train/ | | +| approx_kl | 0.0128760245 | +| clip_fraction | 0.325 | +| clip_range | 0.0664 | +| entropy_loss | -5.81 | +| explained_variance | 0.389 | +| learning_rate | 4.19e-05 | +| loss | -0.0231 | +| n_updates | 82808 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000125 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1395 | +| iterations | 16749 | +| time_elapsed | 24584 | +| total_timesteps | 34301952 | +| train/ | | +| approx_kl | 0.009808609 | +| clip_fraction | 0.326 | +| clip_range | 0.0664 | +| entropy_loss | -6.79 | +| explained_variance | 7.42e-05 | +| learning_rate | 4.19e-05 | +| loss | -0.031 | +| n_updates | 82812 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000166 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1395 | +| iterations | 16750 | +| time_elapsed | 24586 | +| total_timesteps | 34304000 | +| train/ | | +| approx_kl | 0.009484975 | +| clip_fraction | 0.33 | +| clip_range | 0.0664 | +| entropy_loss | -6.61 | +| explained_variance | 0.264 | +| learning_rate | 4.19e-05 | +| loss | -0.0305 | +| n_updates | 82816 | +| policy_gradient_loss | -0.0144 | +| value_loss | 0.000386 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1395 | +| iterations | 16751 | +| time_elapsed | 24587 | +| total_timesteps | 34306048 | +| train/ | | +| approx_kl | 0.0142491255 | +| clip_fraction | 0.319 | +| clip_range | 0.0664 | +| entropy_loss | -5.73 | +| explained_variance | 0.499 | +| learning_rate | 4.19e-05 | +| loss | -0.0328 | +| n_updates | 82820 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000123 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1395 | +| iterations | 16752 | +| time_elapsed | 24589 | +| total_timesteps | 34308096 | +| train/ | | +| approx_kl | 0.014426198 | +| clip_fraction | 0.333 | +| clip_range | 0.0664 | +| entropy_loss | -6.07 | +| explained_variance | 0.0278 | +| learning_rate | 4.19e-05 | +| loss | -0.0331 | +| n_updates | 82824 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000128 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1395 | +| iterations | 16753 | +| time_elapsed | 24590 | +| total_timesteps | 34310144 | +| train/ | | +| approx_kl | 0.014463719 | +| clip_fraction | 0.338 | +| clip_range | 0.0664 | +| entropy_loss | -5.8 | +| explained_variance | 0.349 | +| learning_rate | 4.19e-05 | +| loss | -0.0284 | +| n_updates | 82828 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000243 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1395 | +| iterations | 16754 | +| time_elapsed | 24592 | +| total_timesteps | 34312192 | +| train/ | | +| approx_kl | 0.0098979585 | +| clip_fraction | 0.324 | +| clip_range | 0.0664 | +| entropy_loss | -6.09 | +| explained_variance | 0.342 | +| learning_rate | 4.19e-05 | +| loss | -0.0242 | +| n_updates | 82832 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000142 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1395 | +| iterations | 16755 | +| time_elapsed | 24593 | +| total_timesteps | 34314240 | +| train/ | | +| approx_kl | 0.013970384 | +| clip_fraction | 0.326 | +| clip_range | 0.0664 | +| entropy_loss | -5.75 | +| explained_variance | 0.467 | +| learning_rate | 4.19e-05 | +| loss | -0.0299 | +| n_updates | 82836 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000203 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1395 | +| iterations | 16756 | +| time_elapsed | 24595 | +| total_timesteps | 34316288 | +| train/ | | +| approx_kl | 0.016569559 | +| clip_fraction | 0.315 | +| clip_range | 0.0664 | +| entropy_loss | -5.21 | +| explained_variance | 0.56 | +| learning_rate | 4.19e-05 | +| loss | -0.032 | +| n_updates | 82840 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000173 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1395 | +| iterations | 16757 | +| time_elapsed | 24596 | +| total_timesteps | 34318336 | +| train/ | | +| approx_kl | 0.014325556 | +| clip_fraction | 0.364 | +| clip_range | 0.0664 | +| entropy_loss | -5.99 | +| explained_variance | -0.254 | +| learning_rate | 4.18e-05 | +| loss | -0.0353 | +| n_updates | 82844 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000152 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1395 | +| iterations | 16758 | +| time_elapsed | 24598 | +| total_timesteps | 34320384 | +| train/ | | +| approx_kl | 0.015467128 | +| clip_fraction | 0.345 | +| clip_range | 0.0664 | +| entropy_loss | -6.5 | +| explained_variance | -0.0525 | +| learning_rate | 4.18e-05 | +| loss | -0.0305 | +| n_updates | 82848 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000205 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1395 | +| iterations | 16759 | +| time_elapsed | 24599 | +| total_timesteps | 34322432 | +| train/ | | +| approx_kl | 0.012199732 | +| clip_fraction | 0.344 | +| clip_range | 0.0664 | +| entropy_loss | -5.76 | +| explained_variance | 0.567 | +| learning_rate | 4.18e-05 | +| loss | -0.0278 | +| n_updates | 82852 | +| policy_gradient_loss | -0.0171 | +| value_loss | 7.92e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1395 | +| iterations | 16760 | +| time_elapsed | 24601 | +| total_timesteps | 34324480 | +| train/ | | +| approx_kl | 0.011002935 | +| clip_fraction | 0.331 | +| clip_range | 0.0664 | +| entropy_loss | -6.05 | +| explained_variance | -0.123 | +| learning_rate | 4.18e-05 | +| loss | -0.0332 | +| n_updates | 82856 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000129 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1395 | +| iterations | 16761 | +| time_elapsed | 24603 | +| total_timesteps | 34326528 | +| train/ | | +| approx_kl | 0.012455769 | +| clip_fraction | 0.324 | +| clip_range | 0.0664 | +| entropy_loss | -5.68 | +| explained_variance | 0.482 | +| learning_rate | 4.18e-05 | +| loss | -0.0236 | +| n_updates | 82860 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000131 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1395 | +| iterations | 16762 | +| time_elapsed | 24604 | +| total_timesteps | 34328576 | +| train/ | | +| approx_kl | 0.012892811 | +| clip_fraction | 0.335 | +| clip_range | 0.0664 | +| entropy_loss | -5.92 | +| explained_variance | 0.381 | +| learning_rate | 4.18e-05 | +| loss | -0.0291 | +| n_updates | 82864 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000145 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1395 | +| iterations | 16763 | +| time_elapsed | 24606 | +| total_timesteps | 34330624 | +| train/ | | +| approx_kl | 0.012746007 | +| clip_fraction | 0.333 | +| clip_range | 0.0664 | +| entropy_loss | -6.11 | +| explained_variance | 0.606 | +| learning_rate | 4.18e-05 | +| loss | -0.0302 | +| n_updates | 82868 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000113 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1395 | +| iterations | 16764 | +| time_elapsed | 24607 | +| total_timesteps | 34332672 | +| train/ | | +| approx_kl | 0.012101029 | +| clip_fraction | 0.314 | +| clip_range | 0.0664 | +| entropy_loss | -5.65 | +| explained_variance | 0.572 | +| learning_rate | 4.18e-05 | +| loss | -0.0257 | +| n_updates | 82872 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000207 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1395 | +| iterations | 16765 | +| time_elapsed | 24609 | +| total_timesteps | 34334720 | +| train/ | | +| approx_kl | 0.012672171 | +| clip_fraction | 0.331 | +| clip_range | 0.0664 | +| entropy_loss | -5.84 | +| explained_variance | 0.383 | +| learning_rate | 4.18e-05 | +| loss | -0.0281 | +| n_updates | 82876 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000122 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1395 | +| iterations | 16766 | +| time_elapsed | 24610 | +| total_timesteps | 34336768 | +| train/ | | +| approx_kl | 0.0154022295 | +| clip_fraction | 0.323 | +| clip_range | 0.0664 | +| entropy_loss | -6 | +| explained_variance | 0.538 | +| learning_rate | 4.18e-05 | +| loss | -0.0333 | +| n_updates | 82880 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000113 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1395 | +| iterations | 16767 | +| time_elapsed | 24612 | +| total_timesteps | 34338816 | +| train/ | | +| approx_kl | 0.011249699 | +| clip_fraction | 0.328 | +| clip_range | 0.0664 | +| entropy_loss | -6.08 | +| explained_variance | 0.433 | +| learning_rate | 4.18e-05 | +| loss | -0.032 | +| n_updates | 82884 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000103 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1395 | +| iterations | 16768 | +| time_elapsed | 24613 | +| total_timesteps | 34340864 | +| train/ | | +| approx_kl | 0.010636031 | +| clip_fraction | 0.335 | +| clip_range | 0.0664 | +| entropy_loss | -5.83 | +| explained_variance | 0.628 | +| learning_rate | 4.18e-05 | +| loss | -0.0327 | +| n_updates | 82888 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000101 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1395 | +| iterations | 16769 | +| time_elapsed | 24615 | +| total_timesteps | 34342912 | +| train/ | | +| approx_kl | 0.009338373 | +| clip_fraction | 0.302 | +| clip_range | 0.0664 | +| entropy_loss | -6.43 | +| explained_variance | 0.637 | +| learning_rate | 4.18e-05 | +| loss | -0.0293 | +| n_updates | 82892 | +| policy_gradient_loss | -0.0171 | +| value_loss | 9.08e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1395 | +| iterations | 16770 | +| time_elapsed | 24616 | +| total_timesteps | 34344960 | +| train/ | | +| approx_kl | 0.010897122 | +| clip_fraction | 0.312 | +| clip_range | 0.0664 | +| entropy_loss | -5.8 | +| explained_variance | 0.465 | +| learning_rate | 4.18e-05 | +| loss | -0.0187 | +| n_updates | 82896 | +| policy_gradient_loss | -0.0131 | +| value_loss | 0.000232 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1395 | +| iterations | 16771 | +| time_elapsed | 24618 | +| total_timesteps | 34347008 | +| train/ | | +| approx_kl | 0.012175094 | +| clip_fraction | 0.323 | +| clip_range | 0.0664 | +| entropy_loss | -5.89 | +| explained_variance | 0.396 | +| learning_rate | 4.18e-05 | +| loss | -0.0322 | +| n_updates | 82900 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000139 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1395 | +| iterations | 16772 | +| time_elapsed | 24619 | +| total_timesteps | 34349056 | +| train/ | | +| approx_kl | 0.010974865 | +| clip_fraction | 0.351 | +| clip_range | 0.0664 | +| entropy_loss | -6.41 | +| explained_variance | 0.59 | +| learning_rate | 4.18e-05 | +| loss | -0.0325 | +| n_updates | 82904 | +| policy_gradient_loss | -0.019 | +| value_loss | 5.74e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1395 | +| iterations | 16773 | +| time_elapsed | 24621 | +| total_timesteps | 34351104 | +| train/ | | +| approx_kl | 0.013386205 | +| clip_fraction | 0.332 | +| clip_range | 0.0664 | +| entropy_loss | -5.87 | +| explained_variance | 0.666 | +| learning_rate | 4.18e-05 | +| loss | -0.0261 | +| n_updates | 82908 | +| policy_gradient_loss | -0.0185 | +| value_loss | 8.7e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1395 | +| iterations | 16774 | +| time_elapsed | 24622 | +| total_timesteps | 34353152 | +| train/ | | +| approx_kl | 0.013837703 | +| clip_fraction | 0.371 | +| clip_range | 0.0664 | +| entropy_loss | -5.84 | +| explained_variance | 0.594 | +| learning_rate | 4.18e-05 | +| loss | -0.0388 | +| n_updates | 82912 | +| policy_gradient_loss | -0.0207 | +| value_loss | 5.88e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1395 | +| iterations | 16775 | +| time_elapsed | 24624 | +| total_timesteps | 34355200 | +| train/ | | +| approx_kl | 0.013609802 | +| clip_fraction | 0.347 | +| clip_range | 0.0664 | +| entropy_loss | -5.78 | +| explained_variance | 0.73 | +| learning_rate | 4.18e-05 | +| loss | -0.025 | +| n_updates | 82916 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000111 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1395 | +| iterations | 16776 | +| time_elapsed | 24625 | +| total_timesteps | 34357248 | +| train/ | | +| approx_kl | 0.0129608605 | +| clip_fraction | 0.321 | +| clip_range | 0.0664 | +| entropy_loss | -5.81 | +| explained_variance | 0.305 | +| learning_rate | 4.18e-05 | +| loss | -0.0283 | +| n_updates | 82920 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000144 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1395 | +| iterations | 16777 | +| time_elapsed | 24627 | +| total_timesteps | 34359296 | +| train/ | | +| approx_kl | 0.010940029 | +| clip_fraction | 0.294 | +| clip_range | 0.0664 | +| entropy_loss | -5.95 | +| explained_variance | 0.461 | +| learning_rate | 4.18e-05 | +| loss | -0.0247 | +| n_updates | 82924 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000255 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1395 | +| iterations | 16778 | +| time_elapsed | 24628 | +| total_timesteps | 34361344 | +| train/ | | +| approx_kl | 0.015088648 | +| clip_fraction | 0.337 | +| clip_range | 0.0664 | +| entropy_loss | -6.18 | +| explained_variance | 0.435 | +| learning_rate | 4.18e-05 | +| loss | -0.027 | +| n_updates | 82928 | +| policy_gradient_loss | -0.0191 | +| value_loss | 9.88e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1395 | +| iterations | 16779 | +| time_elapsed | 24630 | +| total_timesteps | 34363392 | +| train/ | | +| approx_kl | 0.01577621 | +| clip_fraction | 0.344 | +| clip_range | 0.0664 | +| entropy_loss | -6.16 | +| explained_variance | 0.293 | +| learning_rate | 4.18e-05 | +| loss | -0.0279 | +| n_updates | 82932 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000138 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1395 | +| iterations | 16780 | +| time_elapsed | 24632 | +| total_timesteps | 34365440 | +| train/ | | +| approx_kl | 0.011511181 | +| clip_fraction | 0.31 | +| clip_range | 0.0664 | +| entropy_loss | -6.02 | +| explained_variance | 0.35 | +| learning_rate | 4.18e-05 | +| loss | -0.0199 | +| n_updates | 82936 | +| policy_gradient_loss | -0.0143 | +| value_loss | 0.000467 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1395 | +| iterations | 16781 | +| time_elapsed | 24633 | +| total_timesteps | 34367488 | +| train/ | | +| approx_kl | 0.013958058 | +| clip_fraction | 0.298 | +| clip_range | 0.0664 | +| entropy_loss | -5.68 | +| explained_variance | 0.232 | +| learning_rate | 4.18e-05 | +| loss | -0.0205 | +| n_updates | 82940 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000313 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1395 | +| iterations | 16782 | +| time_elapsed | 24635 | +| total_timesteps | 34369536 | +| train/ | | +| approx_kl | 0.014966741 | +| clip_fraction | 0.387 | +| clip_range | 0.0664 | +| entropy_loss | -5.76 | +| explained_variance | -0.673 | +| learning_rate | 4.18e-05 | +| loss | -0.0365 | +| n_updates | 82944 | +| policy_gradient_loss | -0.0247 | +| value_loss | 8.73e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1395 | +| iterations | 16783 | +| time_elapsed | 24636 | +| total_timesteps | 34371584 | +| train/ | | +| approx_kl | 0.015148716 | +| clip_fraction | 0.389 | +| clip_range | 0.0664 | +| entropy_loss | -5.79 | +| explained_variance | 0.505 | +| learning_rate | 4.18e-05 | +| loss | -0.027 | +| n_updates | 82948 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000128 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1395 | +| iterations | 16784 | +| time_elapsed | 24638 | +| total_timesteps | 34373632 | +| train/ | | +| approx_kl | 0.012364555 | +| clip_fraction | 0.366 | +| clip_range | 0.0664 | +| entropy_loss | -6.19 | +| explained_variance | 0.312 | +| learning_rate | 4.18e-05 | +| loss | -0.0321 | +| n_updates | 82952 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000107 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1395 | +| iterations | 16785 | +| time_elapsed | 24639 | +| total_timesteps | 34375680 | +| train/ | | +| approx_kl | 0.012802679 | +| clip_fraction | 0.335 | +| clip_range | 0.0664 | +| entropy_loss | -6.13 | +| explained_variance | 0.306 | +| learning_rate | 4.18e-05 | +| loss | -0.0283 | +| n_updates | 82956 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000168 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1395 | +| iterations | 16786 | +| time_elapsed | 24641 | +| total_timesteps | 34377728 | +| train/ | | +| approx_kl | 0.013884287 | +| clip_fraction | 0.32 | +| clip_range | 0.0664 | +| entropy_loss | -5.78 | +| explained_variance | 0.39 | +| learning_rate | 4.18e-05 | +| loss | -0.0225 | +| n_updates | 82960 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000246 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1395 | +| iterations | 16787 | +| time_elapsed | 24642 | +| total_timesteps | 34379776 | +| train/ | | +| approx_kl | 0.014242377 | +| clip_fraction | 0.355 | +| clip_range | 0.0664 | +| entropy_loss | -5.76 | +| explained_variance | 0.603 | +| learning_rate | 4.18e-05 | +| loss | -0.0334 | +| n_updates | 82964 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000129 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1395 | +| iterations | 16788 | +| time_elapsed | 24644 | +| total_timesteps | 34381824 | +| train/ | | +| approx_kl | 0.014221365 | +| clip_fraction | 0.372 | +| clip_range | 0.0664 | +| entropy_loss | -6.02 | +| explained_variance | 0.566 | +| learning_rate | 4.18e-05 | +| loss | -0.0305 | +| n_updates | 82968 | +| policy_gradient_loss | -0.0206 | +| value_loss | 9.79e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1395 | +| iterations | 16789 | +| time_elapsed | 24645 | +| total_timesteps | 34383872 | +| train/ | | +| approx_kl | 0.016359657 | +| clip_fraction | 0.353 | +| clip_range | 0.0664 | +| entropy_loss | -5.57 | +| explained_variance | 0.516 | +| learning_rate | 4.18e-05 | +| loss | -0.03 | +| n_updates | 82972 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000143 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1395 | +| iterations | 16790 | +| time_elapsed | 24647 | +| total_timesteps | 34385920 | +| train/ | | +| approx_kl | 0.0127736945 | +| clip_fraction | 0.307 | +| clip_range | 0.0664 | +| entropy_loss | -5.46 | +| explained_variance | 0.653 | +| learning_rate | 4.18e-05 | +| loss | -0.0337 | +| n_updates | 82976 | +| policy_gradient_loss | -0.0175 | +| value_loss | 7.18e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1395 | +| iterations | 16791 | +| time_elapsed | 24648 | +| total_timesteps | 34387968 | +| train/ | | +| approx_kl | 0.013921742 | +| clip_fraction | 0.299 | +| clip_range | 0.0664 | +| entropy_loss | -6.42 | +| explained_variance | -0.0277 | +| learning_rate | 4.18e-05 | +| loss | -0.0238 | +| n_updates | 82980 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000172 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1395 | +| iterations | 16792 | +| time_elapsed | 24650 | +| total_timesteps | 34390016 | +| train/ | | +| approx_kl | 0.0134709915 | +| clip_fraction | 0.305 | +| clip_range | 0.0664 | +| entropy_loss | -5.92 | +| explained_variance | 0.437 | +| learning_rate | 4.18e-05 | +| loss | -0.0199 | +| n_updates | 82984 | +| policy_gradient_loss | -0.0146 | +| value_loss | 0.000264 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1395 | +| iterations | 16793 | +| time_elapsed | 24651 | +| total_timesteps | 34392064 | +| train/ | | +| approx_kl | 0.014788173 | +| clip_fraction | 0.351 | +| clip_range | 0.0664 | +| entropy_loss | -5.74 | +| explained_variance | 0.526 | +| learning_rate | 4.18e-05 | +| loss | -0.0316 | +| n_updates | 82988 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1395 | +| iterations | 16794 | +| time_elapsed | 24653 | +| total_timesteps | 34394112 | +| train/ | | +| approx_kl | 0.016062053 | +| clip_fraction | 0.362 | +| clip_range | 0.0664 | +| entropy_loss | -6.24 | +| explained_variance | -0.0917 | +| learning_rate | 4.18e-05 | +| loss | -0.0344 | +| n_updates | 82992 | +| policy_gradient_loss | -0.0209 | +| value_loss | 8.14e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1395 | +| iterations | 16795 | +| time_elapsed | 24654 | +| total_timesteps | 34396160 | +| train/ | | +| approx_kl | 0.016795803 | +| clip_fraction | 0.36 | +| clip_range | 0.0664 | +| entropy_loss | -5.8 | +| explained_variance | 0.589 | +| learning_rate | 4.18e-05 | +| loss | -0.036 | +| n_updates | 82996 | +| policy_gradient_loss | -0.02 | +| value_loss | 8.2e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1395 | +| iterations | 16796 | +| time_elapsed | 24656 | +| total_timesteps | 34398208 | +| train/ | | +| approx_kl | 0.01494745 | +| clip_fraction | 0.348 | +| clip_range | 0.0664 | +| entropy_loss | -5.91 | +| explained_variance | 0.553 | +| learning_rate | 4.18e-05 | +| loss | -0.026 | +| n_updates | 83000 | +| policy_gradient_loss | -0.0172 | +| value_loss | 8.59e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1395 | +| iterations | 16797 | +| time_elapsed | 24657 | +| total_timesteps | 34400256 | +| train/ | | +| approx_kl | 0.012881065 | +| clip_fraction | 0.328 | +| clip_range | 0.0664 | +| entropy_loss | -5.78 | +| explained_variance | 0.347 | +| learning_rate | 4.18e-05 | +| loss | -0.0258 | +| n_updates | 83004 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000193 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1395 | +| iterations | 16798 | +| time_elapsed | 24659 | +| total_timesteps | 34402304 | +| train/ | | +| approx_kl | 0.012352785 | +| clip_fraction | 0.338 | +| clip_range | 0.0664 | +| entropy_loss | -6.02 | +| explained_variance | 0.405 | +| learning_rate | 4.18e-05 | +| loss | -0.0313 | +| n_updates | 83008 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000116 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1395 | +| iterations | 16799 | +| time_elapsed | 24660 | +| total_timesteps | 34404352 | +| train/ | | +| approx_kl | 0.012662651 | +| clip_fraction | 0.339 | +| clip_range | 0.0664 | +| entropy_loss | -5.28 | +| explained_variance | 0.634 | +| learning_rate | 4.18e-05 | +| loss | -0.0297 | +| n_updates | 83012 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000214 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1395 | +| iterations | 16800 | +| time_elapsed | 24662 | +| total_timesteps | 34406400 | +| train/ | | +| approx_kl | 0.011877736 | +| clip_fraction | 0.335 | +| clip_range | 0.0664 | +| entropy_loss | -5.33 | +| explained_variance | 0.478 | +| learning_rate | 4.18e-05 | +| loss | -0.0221 | +| n_updates | 83016 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000167 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1395 | +| iterations | 16801 | +| time_elapsed | 24663 | +| total_timesteps | 34408448 | +| train/ | | +| approx_kl | 0.0142431045 | +| clip_fraction | 0.365 | +| clip_range | 0.0664 | +| entropy_loss | -6.05 | +| explained_variance | -0.228 | +| learning_rate | 4.18e-05 | +| loss | -0.0324 | +| n_updates | 83020 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000112 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1395 | +| iterations | 16802 | +| time_elapsed | 24665 | +| total_timesteps | 34410496 | +| train/ | | +| approx_kl | 0.013906582 | +| clip_fraction | 0.325 | +| clip_range | 0.0664 | +| entropy_loss | -6.48 | +| explained_variance | 0.267 | +| learning_rate | 4.18e-05 | +| loss | -0.0266 | +| n_updates | 83024 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000145 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1395 | +| iterations | 16803 | +| time_elapsed | 24667 | +| total_timesteps | 34412544 | +| train/ | | +| approx_kl | 0.011952493 | +| clip_fraction | 0.314 | +| clip_range | 0.0664 | +| entropy_loss | -6.12 | +| explained_variance | 0.422 | +| learning_rate | 4.18e-05 | +| loss | -0.023 | +| n_updates | 83028 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000205 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1395 | +| iterations | 16804 | +| time_elapsed | 24668 | +| total_timesteps | 34414592 | +| train/ | | +| approx_kl | 0.011847205 | +| clip_fraction | 0.348 | +| clip_range | 0.0664 | +| entropy_loss | -6.33 | +| explained_variance | 0.384 | +| learning_rate | 4.18e-05 | +| loss | -0.0289 | +| n_updates | 83032 | +| policy_gradient_loss | -0.0188 | +| value_loss | 9.09e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1395 | +| iterations | 16805 | +| time_elapsed | 24670 | +| total_timesteps | 34416640 | +| train/ | | +| approx_kl | 0.0133873215 | +| clip_fraction | 0.332 | +| clip_range | 0.0664 | +| entropy_loss | -6.15 | +| explained_variance | 0.307 | +| learning_rate | 4.18e-05 | +| loss | -0.0201 | +| n_updates | 83036 | +| policy_gradient_loss | -0.014 | +| value_loss | 0.000268 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1395 | +| iterations | 16806 | +| time_elapsed | 24671 | +| total_timesteps | 34418688 | +| train/ | | +| approx_kl | 0.016266849 | +| clip_fraction | 0.337 | +| clip_range | 0.0664 | +| entropy_loss | -6.17 | +| explained_variance | -0.0812 | +| learning_rate | 4.18e-05 | +| loss | -0.032 | +| n_updates | 83040 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000125 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1395 | +| iterations | 16807 | +| time_elapsed | 24673 | +| total_timesteps | 34420736 | +| train/ | | +| approx_kl | 0.012550846 | +| clip_fraction | 0.334 | +| clip_range | 0.0664 | +| entropy_loss | -6.14 | +| explained_variance | 0.474 | +| learning_rate | 4.18e-05 | +| loss | -0.0274 | +| n_updates | 83044 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.00018 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1395 | +| iterations | 16808 | +| time_elapsed | 24674 | +| total_timesteps | 34422784 | +| train/ | | +| approx_kl | 0.01203893 | +| clip_fraction | 0.344 | +| clip_range | 0.0664 | +| entropy_loss | -5.57 | +| explained_variance | 0.587 | +| learning_rate | 4.18e-05 | +| loss | -0.027 | +| n_updates | 83048 | +| policy_gradient_loss | -0.0176 | +| value_loss | 9.95e-05 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1395 | +| iterations | 16809 | +| time_elapsed | 24676 | +| total_timesteps | 34424832 | +| train/ | | +| approx_kl | 0.00790073 | +| clip_fraction | 0.302 | +| clip_range | 0.0664 | +| entropy_loss | -6.43 | +| explained_variance | 0.208 | +| learning_rate | 4.18e-05 | +| loss | -0.0264 | +| n_updates | 83052 | +| policy_gradient_loss | -0.0148 | +| value_loss | 0.000278 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 1395 | +| iterations | 16810 | +| time_elapsed | 24677 | +| total_timesteps | 34426880 | +| train/ | | +| approx_kl | 0.01105623 | +| clip_fraction | 0.337 | +| clip_range | 0.0664 | +| entropy_loss | -5.76 | +| explained_variance | 0.602 | +| learning_rate | 4.18e-05 | +| loss | -0.0249 | +| n_updates | 83056 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000159 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1395 | +| iterations | 16811 | +| time_elapsed | 24679 | +| total_timesteps | 34428928 | +| train/ | | +| approx_kl | 0.010714427 | +| clip_fraction | 0.316 | +| clip_range | 0.0664 | +| entropy_loss | -5.93 | +| explained_variance | 0.549 | +| learning_rate | 4.18e-05 | +| loss | -0.0287 | +| n_updates | 83060 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000107 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.302 | +| time/ | | +| fps | 1395 | +| iterations | 16812 | +| time_elapsed | 24681 | +| total_timesteps | 34430976 | +| train/ | | +| approx_kl | 0.013237251 | +| clip_fraction | 0.316 | +| clip_range | 0.0664 | +| entropy_loss | -6.35 | +| explained_variance | 0.354 | +| learning_rate | 4.18e-05 | +| loss | -0.0266 | +| n_updates | 83064 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000266 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 1395 | +| iterations | 16813 | +| time_elapsed | 24682 | +| total_timesteps | 34433024 | +| train/ | | +| approx_kl | 0.013014232 | +| clip_fraction | 0.335 | +| clip_range | 0.0664 | +| entropy_loss | -5.99 | +| explained_variance | 0.547 | +| learning_rate | 4.18e-05 | +| loss | -0.0294 | +| n_updates | 83068 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000145 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 1395 | +| iterations | 16814 | +| time_elapsed | 24684 | +| total_timesteps | 34435072 | +| train/ | | +| approx_kl | 0.008844826 | +| clip_fraction | 0.303 | +| clip_range | 0.0664 | +| entropy_loss | -5.85 | +| explained_variance | 0.396 | +| learning_rate | 4.18e-05 | +| loss | -0.0251 | +| n_updates | 83072 | +| policy_gradient_loss | -0.0148 | +| value_loss | 0.000196 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1395 | +| iterations | 16815 | +| time_elapsed | 24685 | +| total_timesteps | 34437120 | +| train/ | | +| approx_kl | 0.011672934 | +| clip_fraction | 0.339 | +| clip_range | 0.0664 | +| entropy_loss | -6.28 | +| explained_variance | 0.356 | +| learning_rate | 4.18e-05 | +| loss | -0.0291 | +| n_updates | 83076 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000124 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1395 | +| iterations | 16816 | +| time_elapsed | 24687 | +| total_timesteps | 34439168 | +| train/ | | +| approx_kl | 0.011694897 | +| clip_fraction | 0.293 | +| clip_range | 0.0664 | +| entropy_loss | -6.26 | +| explained_variance | 0.153 | +| learning_rate | 4.18e-05 | +| loss | -0.0181 | +| n_updates | 83080 | +| policy_gradient_loss | -0.0134 | +| value_loss | 0.000363 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1395 | +| iterations | 16817 | +| time_elapsed | 24688 | +| total_timesteps | 34441216 | +| train/ | | +| approx_kl | 0.01443029 | +| clip_fraction | 0.339 | +| clip_range | 0.0664 | +| entropy_loss | -5.24 | +| explained_variance | 0.556 | +| learning_rate | 4.18e-05 | +| loss | -0.0235 | +| n_updates | 83084 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000193 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1395 | +| iterations | 16818 | +| time_elapsed | 24690 | +| total_timesteps | 34443264 | +| train/ | | +| approx_kl | 0.013278416 | +| clip_fraction | 0.34 | +| clip_range | 0.0664 | +| entropy_loss | -5.36 | +| explained_variance | 0.344 | +| learning_rate | 4.18e-05 | +| loss | -0.0295 | +| n_updates | 83088 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000361 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1395 | +| iterations | 16819 | +| time_elapsed | 24691 | +| total_timesteps | 34445312 | +| train/ | | +| approx_kl | 0.015156108 | +| clip_fraction | 0.395 | +| clip_range | 0.0664 | +| entropy_loss | -5.98 | +| explained_variance | -0.717 | +| learning_rate | 4.18e-05 | +| loss | -0.0395 | +| n_updates | 83092 | +| policy_gradient_loss | -0.0271 | +| value_loss | 7.59e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1395 | +| iterations | 16820 | +| time_elapsed | 24693 | +| total_timesteps | 34447360 | +| train/ | | +| approx_kl | 0.012289971 | +| clip_fraction | 0.322 | +| clip_range | 0.0664 | +| entropy_loss | -6.82 | +| explained_variance | 0.0681 | +| learning_rate | 4.18e-05 | +| loss | -0.0286 | +| n_updates | 83096 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000185 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1395 | +| iterations | 16821 | +| time_elapsed | 24694 | +| total_timesteps | 34449408 | +| train/ | | +| approx_kl | 0.00967595 | +| clip_fraction | 0.313 | +| clip_range | 0.0664 | +| entropy_loss | -6.95 | +| explained_variance | 0.0942 | +| learning_rate | 4.18e-05 | +| loss | -0.0297 | +| n_updates | 83100 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000281 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1395 | +| iterations | 16822 | +| time_elapsed | 24696 | +| total_timesteps | 34451456 | +| train/ | | +| approx_kl | 0.010870218 | +| clip_fraction | 0.318 | +| clip_range | 0.0664 | +| entropy_loss | -6.31 | +| explained_variance | 0.216 | +| learning_rate | 4.18e-05 | +| loss | -0.0282 | +| n_updates | 83104 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000239 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1395 | +| iterations | 16823 | +| time_elapsed | 24697 | +| total_timesteps | 34453504 | +| train/ | | +| approx_kl | 0.009355417 | +| clip_fraction | 0.333 | +| clip_range | 0.0664 | +| entropy_loss | -6.05 | +| explained_variance | 0.377 | +| learning_rate | 4.18e-05 | +| loss | -0.0278 | +| n_updates | 83108 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000202 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1395 | +| iterations | 16824 | +| time_elapsed | 24699 | +| total_timesteps | 34455552 | +| train/ | | +| approx_kl | 0.010043704 | +| clip_fraction | 0.309 | +| clip_range | 0.0664 | +| entropy_loss | -6.08 | +| explained_variance | 0.346 | +| learning_rate | 4.18e-05 | +| loss | -0.022 | +| n_updates | 83112 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.000263 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1394 | +| iterations | 16825 | +| time_elapsed | 24700 | +| total_timesteps | 34457600 | +| train/ | | +| approx_kl | 0.010284549 | +| clip_fraction | 0.309 | +| clip_range | 0.0664 | +| entropy_loss | -5.91 | +| explained_variance | 0.447 | +| learning_rate | 4.18e-05 | +| loss | -0.0255 | +| n_updates | 83116 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000297 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1394 | +| iterations | 16826 | +| time_elapsed | 24702 | +| total_timesteps | 34459648 | +| train/ | | +| approx_kl | 0.010036056 | +| clip_fraction | 0.304 | +| clip_range | 0.0664 | +| entropy_loss | -5.68 | +| explained_variance | 0.401 | +| learning_rate | 4.18e-05 | +| loss | -0.0255 | +| n_updates | 83120 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.000196 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1394 | +| iterations | 16827 | +| time_elapsed | 24703 | +| total_timesteps | 34461696 | +| train/ | | +| approx_kl | 0.012475729 | +| clip_fraction | 0.358 | +| clip_range | 0.0664 | +| entropy_loss | -5.25 | +| explained_variance | 0.77 | +| learning_rate | 4.18e-05 | +| loss | -0.0305 | +| n_updates | 83124 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000106 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1394 | +| iterations | 16828 | +| time_elapsed | 24705 | +| total_timesteps | 34463744 | +| train/ | | +| approx_kl | 0.011616984 | +| clip_fraction | 0.32 | +| clip_range | 0.0664 | +| entropy_loss | -6.07 | +| explained_variance | 0.532 | +| learning_rate | 4.18e-05 | +| loss | -0.0285 | +| n_updates | 83128 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000132 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1394 | +| iterations | 16829 | +| time_elapsed | 24706 | +| total_timesteps | 34465792 | +| train/ | | +| approx_kl | 0.0123647805 | +| clip_fraction | 0.33 | +| clip_range | 0.0664 | +| entropy_loss | -6.16 | +| explained_variance | 0.00192 | +| learning_rate | 4.18e-05 | +| loss | -0.032 | +| n_updates | 83132 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000154 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1394 | +| iterations | 16830 | +| time_elapsed | 24708 | +| total_timesteps | 34467840 | +| train/ | | +| approx_kl | 0.018656874 | +| clip_fraction | 0.365 | +| clip_range | 0.0664 | +| entropy_loss | -6.08 | +| explained_variance | 0.295 | +| learning_rate | 4.18e-05 | +| loss | -0.0304 | +| n_updates | 83136 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000108 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1394 | +| iterations | 16831 | +| time_elapsed | 24710 | +| total_timesteps | 34469888 | +| train/ | | +| approx_kl | 0.009630233 | +| clip_fraction | 0.321 | +| clip_range | 0.0664 | +| entropy_loss | -6.71 | +| explained_variance | 0.245 | +| learning_rate | 4.18e-05 | +| loss | -0.0286 | +| n_updates | 83140 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000229 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1394 | +| iterations | 16832 | +| time_elapsed | 24711 | +| total_timesteps | 34471936 | +| train/ | | +| approx_kl | 0.013192801 | +| clip_fraction | 0.293 | +| clip_range | 0.0664 | +| entropy_loss | -6.82 | +| explained_variance | -0.000988 | +| learning_rate | 4.18e-05 | +| loss | -0.029 | +| n_updates | 83144 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000158 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1394 | +| iterations | 16833 | +| time_elapsed | 24713 | +| total_timesteps | 34473984 | +| train/ | | +| approx_kl | 0.013291908 | +| clip_fraction | 0.288 | +| clip_range | 0.0664 | +| entropy_loss | -6 | +| explained_variance | 0.545 | +| learning_rate | 4.18e-05 | +| loss | -0.0237 | +| n_updates | 83148 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000184 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1394 | +| iterations | 16834 | +| time_elapsed | 24714 | +| total_timesteps | 34476032 | +| train/ | | +| approx_kl | 0.013201843 | +| clip_fraction | 0.33 | +| clip_range | 0.0664 | +| entropy_loss | -5.63 | +| explained_variance | 0.421 | +| learning_rate | 4.18e-05 | +| loss | -0.0202 | +| n_updates | 83152 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000174 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1394 | +| iterations | 16835 | +| time_elapsed | 24716 | +| total_timesteps | 34478080 | +| train/ | | +| approx_kl | 0.014683315 | +| clip_fraction | 0.354 | +| clip_range | 0.0664 | +| entropy_loss | -6.36 | +| explained_variance | -0.373 | +| learning_rate | 4.18e-05 | +| loss | -0.0325 | +| n_updates | 83156 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.00011 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1394 | +| iterations | 16836 | +| time_elapsed | 24717 | +| total_timesteps | 34480128 | +| train/ | | +| approx_kl | 0.016307447 | +| clip_fraction | 0.346 | +| clip_range | 0.0664 | +| entropy_loss | -6.1 | +| explained_variance | 0.159 | +| learning_rate | 4.18e-05 | +| loss | -0.0242 | +| n_updates | 83160 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000169 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1394 | +| iterations | 16837 | +| time_elapsed | 24719 | +| total_timesteps | 34482176 | +| train/ | | +| approx_kl | 0.013502998 | +| clip_fraction | 0.343 | +| clip_range | 0.0664 | +| entropy_loss | -5.72 | +| explained_variance | 0.293 | +| learning_rate | 4.18e-05 | +| loss | -0.0262 | +| n_updates | 83164 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000188 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1394 | +| iterations | 16838 | +| time_elapsed | 24720 | +| total_timesteps | 34484224 | +| train/ | | +| approx_kl | 0.015893942 | +| clip_fraction | 0.342 | +| clip_range | 0.0664 | +| entropy_loss | -6.24 | +| explained_variance | 0.287 | +| learning_rate | 4.18e-05 | +| loss | -0.0345 | +| n_updates | 83168 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000121 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1394 | +| iterations | 16839 | +| time_elapsed | 24722 | +| total_timesteps | 34486272 | +| train/ | | +| approx_kl | 0.01597262 | +| clip_fraction | 0.299 | +| clip_range | 0.0664 | +| entropy_loss | -5.98 | +| explained_variance | 0.227 | +| learning_rate | 4.18e-05 | +| loss | -0.0272 | +| n_updates | 83172 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000213 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1394 | +| iterations | 16840 | +| time_elapsed | 24723 | +| total_timesteps | 34488320 | +| train/ | | +| approx_kl | 0.014259085 | +| clip_fraction | 0.325 | +| clip_range | 0.0664 | +| entropy_loss | -4.91 | +| explained_variance | 0.623 | +| learning_rate | 4.18e-05 | +| loss | -0.0233 | +| n_updates | 83176 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.000251 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1394 | +| iterations | 16841 | +| time_elapsed | 24725 | +| total_timesteps | 34490368 | +| train/ | | +| approx_kl | 0.016204368 | +| clip_fraction | 0.356 | +| clip_range | 0.0664 | +| entropy_loss | -5.41 | +| explained_variance | 0.533 | +| learning_rate | 4.18e-05 | +| loss | -0.0364 | +| n_updates | 83180 | +| policy_gradient_loss | -0.0207 | +| value_loss | 5.99e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1394 | +| iterations | 16842 | +| time_elapsed | 24727 | +| total_timesteps | 34492416 | +| train/ | | +| approx_kl | 0.01628042 | +| clip_fraction | 0.348 | +| clip_range | 0.0664 | +| entropy_loss | -6.33 | +| explained_variance | 0.121 | +| learning_rate | 4.18e-05 | +| loss | -0.0286 | +| n_updates | 83184 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000146 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1394 | +| iterations | 16843 | +| time_elapsed | 24728 | +| total_timesteps | 34494464 | +| train/ | | +| approx_kl | 0.012153387 | +| clip_fraction | 0.309 | +| clip_range | 0.0664 | +| entropy_loss | -6.46 | +| explained_variance | 0.388 | +| learning_rate | 4.18e-05 | +| loss | -0.0329 | +| n_updates | 83188 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000193 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1394 | +| iterations | 16844 | +| time_elapsed | 24730 | +| total_timesteps | 34496512 | +| train/ | | +| approx_kl | 0.011853604 | +| clip_fraction | 0.327 | +| clip_range | 0.0664 | +| entropy_loss | -6.36 | +| explained_variance | -0.0642 | +| learning_rate | 4.18e-05 | +| loss | -0.0281 | +| n_updates | 83192 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000127 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1394 | +| iterations | 16845 | +| time_elapsed | 24731 | +| total_timesteps | 34498560 | +| train/ | | +| approx_kl | 0.0115218405 | +| clip_fraction | 0.332 | +| clip_range | 0.0664 | +| entropy_loss | -6.63 | +| explained_variance | 0.363 | +| learning_rate | 4.18e-05 | +| loss | -0.0241 | +| n_updates | 83196 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000153 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1394 | +| iterations | 16846 | +| time_elapsed | 24733 | +| total_timesteps | 34500608 | +| train/ | | +| approx_kl | 0.011783106 | +| clip_fraction | 0.284 | +| clip_range | 0.0664 | +| entropy_loss | -5.95 | +| explained_variance | 0.351 | +| learning_rate | 4.18e-05 | +| loss | -0.0258 | +| n_updates | 83200 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000433 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1394 | +| iterations | 16847 | +| time_elapsed | 24734 | +| total_timesteps | 34502656 | +| train/ | | +| approx_kl | 0.013764901 | +| clip_fraction | 0.377 | +| clip_range | 0.0664 | +| entropy_loss | -5.92 | +| explained_variance | 0.235 | +| learning_rate | 4.18e-05 | +| loss | -0.0344 | +| n_updates | 83204 | +| policy_gradient_loss | -0.0219 | +| value_loss | 0.000143 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1394 | +| iterations | 16848 | +| time_elapsed | 24736 | +| total_timesteps | 34504704 | +| train/ | | +| approx_kl | 0.014311752 | +| clip_fraction | 0.36 | +| clip_range | 0.0664 | +| entropy_loss | -6.2 | +| explained_variance | 0.416 | +| learning_rate | 4.18e-05 | +| loss | -0.0326 | +| n_updates | 83208 | +| policy_gradient_loss | -0.0214 | +| value_loss | 8.53e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1394 | +| iterations | 16849 | +| time_elapsed | 24737 | +| total_timesteps | 34506752 | +| train/ | | +| approx_kl | 0.010597916 | +| clip_fraction | 0.323 | +| clip_range | 0.0664 | +| entropy_loss | -5.61 | +| explained_variance | 0.597 | +| learning_rate | 4.18e-05 | +| loss | -0.0258 | +| n_updates | 83212 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.00018 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1394 | +| iterations | 16850 | +| time_elapsed | 24739 | +| total_timesteps | 34508800 | +| train/ | | +| approx_kl | 0.0101231355 | +| clip_fraction | 0.288 | +| clip_range | 0.0664 | +| entropy_loss | -5 | +| explained_variance | 0.577 | +| learning_rate | 4.18e-05 | +| loss | -0.0264 | +| n_updates | 83216 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000242 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1394 | +| iterations | 16851 | +| time_elapsed | 24741 | +| total_timesteps | 34510848 | +| train/ | | +| approx_kl | 0.010324353 | +| clip_fraction | 0.333 | +| clip_range | 0.0664 | +| entropy_loss | -6.4 | +| explained_variance | -0.106 | +| learning_rate | 4.18e-05 | +| loss | -0.0271 | +| n_updates | 83220 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000196 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1394 | +| iterations | 16852 | +| time_elapsed | 24742 | +| total_timesteps | 34512896 | +| train/ | | +| approx_kl | 0.012573926 | +| clip_fraction | 0.361 | +| clip_range | 0.0664 | +| entropy_loss | -6.5 | +| explained_variance | 0.405 | +| learning_rate | 4.18e-05 | +| loss | -0.036 | +| n_updates | 83224 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1394 | +| iterations | 16853 | +| time_elapsed | 24744 | +| total_timesteps | 34514944 | +| train/ | | +| approx_kl | 0.010957299 | +| clip_fraction | 0.301 | +| clip_range | 0.0664 | +| entropy_loss | -6.06 | +| explained_variance | 0.379 | +| learning_rate | 4.18e-05 | +| loss | -0.0224 | +| n_updates | 83228 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000376 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1394 | +| iterations | 16854 | +| time_elapsed | 24745 | +| total_timesteps | 34516992 | +| train/ | | +| approx_kl | 0.012623759 | +| clip_fraction | 0.34 | +| clip_range | 0.0664 | +| entropy_loss | -5.87 | +| explained_variance | 0.394 | +| learning_rate | 4.18e-05 | +| loss | -0.0319 | +| n_updates | 83232 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000146 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1394 | +| iterations | 16855 | +| time_elapsed | 24747 | +| total_timesteps | 34519040 | +| train/ | | +| approx_kl | 0.010683759 | +| clip_fraction | 0.343 | +| clip_range | 0.0664 | +| entropy_loss | -6.61 | +| explained_variance | -0.0535 | +| learning_rate | 4.18e-05 | +| loss | -0.0356 | +| n_updates | 83236 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.00013 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1394 | +| iterations | 16856 | +| time_elapsed | 24748 | +| total_timesteps | 34521088 | +| train/ | | +| approx_kl | 0.010749634 | +| clip_fraction | 0.329 | +| clip_range | 0.0664 | +| entropy_loss | -5.89 | +| explained_variance | 0.755 | +| learning_rate | 4.18e-05 | +| loss | -0.0319 | +| n_updates | 83240 | +| policy_gradient_loss | -0.019 | +| value_loss | 7.13e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1394 | +| iterations | 16857 | +| time_elapsed | 24750 | +| total_timesteps | 34523136 | +| train/ | | +| approx_kl | 0.013733377 | +| clip_fraction | 0.306 | +| clip_range | 0.0664 | +| entropy_loss | -6.37 | +| explained_variance | 0.233 | +| learning_rate | 4.18e-05 | +| loss | -0.0218 | +| n_updates | 83244 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000223 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1394 | +| iterations | 16858 | +| time_elapsed | 24752 | +| total_timesteps | 34525184 | +| train/ | | +| approx_kl | 0.012432106 | +| clip_fraction | 0.352 | +| clip_range | 0.0664 | +| entropy_loss | -6.06 | +| explained_variance | 0.574 | +| learning_rate | 4.18e-05 | +| loss | -0.031 | +| n_updates | 83248 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000107 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1394 | +| iterations | 16859 | +| time_elapsed | 24753 | +| total_timesteps | 34527232 | +| train/ | | +| approx_kl | 0.013688415 | +| clip_fraction | 0.339 | +| clip_range | 0.0664 | +| entropy_loss | -5.91 | +| explained_variance | 0.378 | +| learning_rate | 4.18e-05 | +| loss | -0.0245 | +| n_updates | 83252 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000148 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1394 | +| iterations | 16860 | +| time_elapsed | 24755 | +| total_timesteps | 34529280 | +| train/ | | +| approx_kl | 0.015323775 | +| clip_fraction | 0.352 | +| clip_range | 0.0664 | +| entropy_loss | -5.69 | +| explained_variance | 0.669 | +| learning_rate | 4.18e-05 | +| loss | -0.0303 | +| n_updates | 83256 | +| policy_gradient_loss | -0.0194 | +| value_loss | 8.54e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1394 | +| iterations | 16861 | +| time_elapsed | 24756 | +| total_timesteps | 34531328 | +| train/ | | +| approx_kl | 0.013804953 | +| clip_fraction | 0.366 | +| clip_range | 0.0664 | +| entropy_loss | -6.16 | +| explained_variance | 0.225 | +| learning_rate | 4.18e-05 | +| loss | -0.0337 | +| n_updates | 83260 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.00011 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1394 | +| iterations | 16862 | +| time_elapsed | 24758 | +| total_timesteps | 34533376 | +| train/ | | +| approx_kl | 0.013444221 | +| clip_fraction | 0.352 | +| clip_range | 0.0664 | +| entropy_loss | -5.76 | +| explained_variance | 0.593 | +| learning_rate | 4.18e-05 | +| loss | -0.034 | +| n_updates | 83264 | +| policy_gradient_loss | -0.019 | +| value_loss | 9.2e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1394 | +| iterations | 16863 | +| time_elapsed | 24759 | +| total_timesteps | 34535424 | +| train/ | | +| approx_kl | 0.013927146 | +| clip_fraction | 0.332 | +| clip_range | 0.0664 | +| entropy_loss | -5.76 | +| explained_variance | 0.36 | +| learning_rate | 4.18e-05 | +| loss | -0.0272 | +| n_updates | 83268 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.00012 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1394 | +| iterations | 16864 | +| time_elapsed | 24761 | +| total_timesteps | 34537472 | +| train/ | | +| approx_kl | 0.015041183 | +| clip_fraction | 0.343 | +| clip_range | 0.0664 | +| entropy_loss | -6.37 | +| explained_variance | 0.194 | +| learning_rate | 4.18e-05 | +| loss | -0.0281 | +| n_updates | 83272 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000286 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1394 | +| iterations | 16865 | +| time_elapsed | 24762 | +| total_timesteps | 34539520 | +| train/ | | +| approx_kl | 0.013102574 | +| clip_fraction | 0.345 | +| clip_range | 0.0664 | +| entropy_loss | -6.18 | +| explained_variance | 0.586 | +| learning_rate | 4.18e-05 | +| loss | -0.0295 | +| n_updates | 83276 | +| policy_gradient_loss | -0.0197 | +| value_loss | 8.76e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1394 | +| iterations | 16866 | +| time_elapsed | 24764 | +| total_timesteps | 34541568 | +| train/ | | +| approx_kl | 0.012849847 | +| clip_fraction | 0.324 | +| clip_range | 0.0664 | +| entropy_loss | -6.36 | +| explained_variance | 0.318 | +| learning_rate | 4.18e-05 | +| loss | -0.028 | +| n_updates | 83280 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000137 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1394 | +| iterations | 16867 | +| time_elapsed | 24765 | +| total_timesteps | 34543616 | +| train/ | | +| approx_kl | 0.011231138 | +| clip_fraction | 0.307 | +| clip_range | 0.0664 | +| entropy_loss | -5.99 | +| explained_variance | 0.36 | +| learning_rate | 4.18e-05 | +| loss | -0.0272 | +| n_updates | 83284 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000329 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1394 | +| iterations | 16868 | +| time_elapsed | 24767 | +| total_timesteps | 34545664 | +| train/ | | +| approx_kl | 0.012249556 | +| clip_fraction | 0.327 | +| clip_range | 0.0664 | +| entropy_loss | -6.18 | +| explained_variance | -0.00328 | +| learning_rate | 4.18e-05 | +| loss | -0.0308 | +| n_updates | 83288 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000116 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1394 | +| iterations | 16869 | +| time_elapsed | 24768 | +| total_timesteps | 34547712 | +| train/ | | +| approx_kl | 0.014126568 | +| clip_fraction | 0.339 | +| clip_range | 0.0664 | +| entropy_loss | -5.05 | +| explained_variance | 0.606 | +| learning_rate | 4.18e-05 | +| loss | -0.0262 | +| n_updates | 83292 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000191 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1394 | +| iterations | 16870 | +| time_elapsed | 24770 | +| total_timesteps | 34549760 | +| train/ | | +| approx_kl | 0.014240575 | +| clip_fraction | 0.335 | +| clip_range | 0.0664 | +| entropy_loss | -5.32 | +| explained_variance | 0.566 | +| learning_rate | 4.18e-05 | +| loss | -0.0266 | +| n_updates | 83296 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000119 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1394 | +| iterations | 16871 | +| time_elapsed | 24771 | +| total_timesteps | 34551808 | +| train/ | | +| approx_kl | 0.013752266 | +| clip_fraction | 0.341 | +| clip_range | 0.0664 | +| entropy_loss | -5.9 | +| explained_variance | 0.347 | +| learning_rate | 4.18e-05 | +| loss | -0.0216 | +| n_updates | 83300 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.00018 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1394 | +| iterations | 16872 | +| time_elapsed | 24773 | +| total_timesteps | 34553856 | +| train/ | | +| approx_kl | 0.016021509 | +| clip_fraction | 0.359 | +| clip_range | 0.0664 | +| entropy_loss | -5.81 | +| explained_variance | 0.29 | +| learning_rate | 4.18e-05 | +| loss | -0.0309 | +| n_updates | 83304 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000105 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1394 | +| iterations | 16873 | +| time_elapsed | 24774 | +| total_timesteps | 34555904 | +| train/ | | +| approx_kl | 0.011661908 | +| clip_fraction | 0.329 | +| clip_range | 0.0664 | +| entropy_loss | -6.71 | +| explained_variance | -0.12 | +| learning_rate | 4.18e-05 | +| loss | -0.027 | +| n_updates | 83308 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000144 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1394 | +| iterations | 16874 | +| time_elapsed | 24776 | +| total_timesteps | 34557952 | +| train/ | | +| approx_kl | 0.013345605 | +| clip_fraction | 0.329 | +| clip_range | 0.0664 | +| entropy_loss | -6.12 | +| explained_variance | 0.51 | +| learning_rate | 4.18e-05 | +| loss | -0.03 | +| n_updates | 83312 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1394 | +| iterations | 16875 | +| time_elapsed | 24777 | +| total_timesteps | 34560000 | +| train/ | | +| approx_kl | 0.012120608 | +| clip_fraction | 0.329 | +| clip_range | 0.0664 | +| entropy_loss | -6.05 | +| explained_variance | 0.477 | +| learning_rate | 4.18e-05 | +| loss | -0.0304 | +| n_updates | 83316 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000121 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1394 | +| iterations | 16876 | +| time_elapsed | 24779 | +| total_timesteps | 34562048 | +| train/ | | +| approx_kl | 0.012406327 | +| clip_fraction | 0.339 | +| clip_range | 0.0664 | +| entropy_loss | -6.25 | +| explained_variance | 0.34 | +| learning_rate | 4.18e-05 | +| loss | -0.0308 | +| n_updates | 83320 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000134 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1394 | +| iterations | 16877 | +| time_elapsed | 24781 | +| total_timesteps | 34564096 | +| train/ | | +| approx_kl | 0.012359927 | +| clip_fraction | 0.332 | +| clip_range | 0.0664 | +| entropy_loss | -6.48 | +| explained_variance | 0.351 | +| learning_rate | 4.18e-05 | +| loss | -0.0243 | +| n_updates | 83324 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000175 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1394 | +| iterations | 16878 | +| time_elapsed | 24782 | +| total_timesteps | 34566144 | +| train/ | | +| approx_kl | 0.011474403 | +| clip_fraction | 0.335 | +| clip_range | 0.0664 | +| entropy_loss | -6.15 | +| explained_variance | 0.337 | +| learning_rate | 4.18e-05 | +| loss | -0.0324 | +| n_updates | 83328 | +| policy_gradient_loss | -0.0199 | +| value_loss | 8.5e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1394 | +| iterations | 16879 | +| time_elapsed | 24784 | +| total_timesteps | 34568192 | +| train/ | | +| approx_kl | 0.013222587 | +| clip_fraction | 0.31 | +| clip_range | 0.0664 | +| entropy_loss | -5.43 | +| explained_variance | 0.545 | +| learning_rate | 4.18e-05 | +| loss | -0.0236 | +| n_updates | 83332 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000235 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1394 | +| iterations | 16880 | +| time_elapsed | 24785 | +| total_timesteps | 34570240 | +| train/ | | +| approx_kl | 0.012755986 | +| clip_fraction | 0.342 | +| clip_range | 0.0664 | +| entropy_loss | -5.96 | +| explained_variance | 0.421 | +| learning_rate | 4.18e-05 | +| loss | -0.0323 | +| n_updates | 83336 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000112 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1394 | +| iterations | 16881 | +| time_elapsed | 24787 | +| total_timesteps | 34572288 | +| train/ | | +| approx_kl | 0.013980949 | +| clip_fraction | 0.333 | +| clip_range | 0.0664 | +| entropy_loss | -5.88 | +| explained_variance | 0.515 | +| learning_rate | 4.18e-05 | +| loss | -0.0296 | +| n_updates | 83340 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000175 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1394 | +| iterations | 16882 | +| time_elapsed | 24788 | +| total_timesteps | 34574336 | +| train/ | | +| approx_kl | 0.010218557 | +| clip_fraction | 0.286 | +| clip_range | 0.0664 | +| entropy_loss | -5.69 | +| explained_variance | 0.541 | +| learning_rate | 4.18e-05 | +| loss | -0.021 | +| n_updates | 83344 | +| policy_gradient_loss | -0.0133 | +| value_loss | 0.000267 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1394 | +| iterations | 16883 | +| time_elapsed | 24790 | +| total_timesteps | 34576384 | +| train/ | | +| approx_kl | 0.012939801 | +| clip_fraction | 0.344 | +| clip_range | 0.0664 | +| entropy_loss | -5.34 | +| explained_variance | 0.532 | +| learning_rate | 4.18e-05 | +| loss | -0.0312 | +| n_updates | 83348 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000106 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1394 | +| iterations | 16884 | +| time_elapsed | 24791 | +| total_timesteps | 34578432 | +| train/ | | +| approx_kl | 0.014793264 | +| clip_fraction | 0.346 | +| clip_range | 0.0664 | +| entropy_loss | -5.79 | +| explained_variance | 0.52 | +| learning_rate | 4.18e-05 | +| loss | -0.0338 | +| n_updates | 83352 | +| policy_gradient_loss | -0.0199 | +| value_loss | 7.17e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1394 | +| iterations | 16885 | +| time_elapsed | 24793 | +| total_timesteps | 34580480 | +| train/ | | +| approx_kl | 0.0082153585 | +| clip_fraction | 0.325 | +| clip_range | 0.0664 | +| entropy_loss | -6.31 | +| explained_variance | 0.476 | +| learning_rate | 4.18e-05 | +| loss | -0.0306 | +| n_updates | 83356 | +| policy_gradient_loss | -0.0144 | +| value_loss | 0.000234 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1394 | +| iterations | 16886 | +| time_elapsed | 24794 | +| total_timesteps | 34582528 | +| train/ | | +| approx_kl | 0.0106267175 | +| clip_fraction | 0.326 | +| clip_range | 0.0664 | +| entropy_loss | -6.13 | +| explained_variance | 0.397 | +| learning_rate | 4.18e-05 | +| loss | -0.0275 | +| n_updates | 83360 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000164 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1394 | +| iterations | 16887 | +| time_elapsed | 24796 | +| total_timesteps | 34584576 | +| train/ | | +| approx_kl | 0.011208693 | +| clip_fraction | 0.36 | +| clip_range | 0.0664 | +| entropy_loss | -6.2 | +| explained_variance | 0.386 | +| learning_rate | 4.18e-05 | +| loss | -0.0327 | +| n_updates | 83364 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000113 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1394 | +| iterations | 16888 | +| time_elapsed | 24797 | +| total_timesteps | 34586624 | +| train/ | | +| approx_kl | 0.01293617 | +| clip_fraction | 0.316 | +| clip_range | 0.0664 | +| entropy_loss | -6.37 | +| explained_variance | 0.151 | +| learning_rate | 4.18e-05 | +| loss | -0.0241 | +| n_updates | 83368 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.00028 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1394 | +| iterations | 16889 | +| time_elapsed | 24799 | +| total_timesteps | 34588672 | +| train/ | | +| approx_kl | 0.013282999 | +| clip_fraction | 0.338 | +| clip_range | 0.0664 | +| entropy_loss | -6.26 | +| explained_variance | 0.571 | +| learning_rate | 4.18e-05 | +| loss | -0.0311 | +| n_updates | 83372 | +| policy_gradient_loss | -0.0191 | +| value_loss | 8.62e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1394 | +| iterations | 16890 | +| time_elapsed | 24800 | +| total_timesteps | 34590720 | +| train/ | | +| approx_kl | 0.015003031 | +| clip_fraction | 0.347 | +| clip_range | 0.0664 | +| entropy_loss | -6.32 | +| explained_variance | -0.16 | +| learning_rate | 4.18e-05 | +| loss | -0.0288 | +| n_updates | 83376 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000102 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1394 | +| iterations | 16891 | +| time_elapsed | 24802 | +| total_timesteps | 34592768 | +| train/ | | +| approx_kl | 0.013336156 | +| clip_fraction | 0.326 | +| clip_range | 0.0664 | +| entropy_loss | -6.56 | +| explained_variance | 0.391 | +| learning_rate | 4.18e-05 | +| loss | -0.0302 | +| n_updates | 83380 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000205 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1394 | +| iterations | 16892 | +| time_elapsed | 24803 | +| total_timesteps | 34594816 | +| train/ | | +| approx_kl | 0.012585747 | +| clip_fraction | 0.337 | +| clip_range | 0.0664 | +| entropy_loss | -6.17 | +| explained_variance | 0.317 | +| learning_rate | 4.18e-05 | +| loss | -0.0292 | +| n_updates | 83384 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000153 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1394 | +| iterations | 16893 | +| time_elapsed | 24805 | +| total_timesteps | 34596864 | +| train/ | | +| approx_kl | 0.010223994 | +| clip_fraction | 0.305 | +| clip_range | 0.0664 | +| entropy_loss | -5.45 | +| explained_variance | 0.507 | +| learning_rate | 4.18e-05 | +| loss | -0.0295 | +| n_updates | 83388 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000196 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1394 | +| iterations | 16894 | +| time_elapsed | 24806 | +| total_timesteps | 34598912 | +| train/ | | +| approx_kl | 0.013717311 | +| clip_fraction | 0.325 | +| clip_range | 0.0664 | +| entropy_loss | -5.14 | +| explained_variance | 0.657 | +| learning_rate | 4.18e-05 | +| loss | -0.0251 | +| n_updates | 83392 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000152 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1394 | +| iterations | 16895 | +| time_elapsed | 24808 | +| total_timesteps | 34600960 | +| train/ | | +| approx_kl | 0.012525384 | +| clip_fraction | 0.326 | +| clip_range | 0.0664 | +| entropy_loss | -5.89 | +| explained_variance | 0.245 | +| learning_rate | 4.18e-05 | +| loss | -0.0297 | +| n_updates | 83396 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000287 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1394 | +| iterations | 16896 | +| time_elapsed | 24809 | +| total_timesteps | 34603008 | +| train/ | | +| approx_kl | 0.0136076845 | +| clip_fraction | 0.339 | +| clip_range | 0.0663 | +| entropy_loss | -6.13 | +| explained_variance | 0.389 | +| learning_rate | 4.18e-05 | +| loss | -0.0375 | +| n_updates | 83400 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000115 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1394 | +| iterations | 16897 | +| time_elapsed | 24811 | +| total_timesteps | 34605056 | +| train/ | | +| approx_kl | 0.012577881 | +| clip_fraction | 0.324 | +| clip_range | 0.0663 | +| entropy_loss | -6.4 | +| explained_variance | -0.0709 | +| learning_rate | 4.18e-05 | +| loss | -0.03 | +| n_updates | 83404 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.00015 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1394 | +| iterations | 16898 | +| time_elapsed | 24813 | +| total_timesteps | 34607104 | +| train/ | | +| approx_kl | 0.013396857 | +| clip_fraction | 0.325 | +| clip_range | 0.0663 | +| entropy_loss | -5.95 | +| explained_variance | 0.508 | +| learning_rate | 4.18e-05 | +| loss | -0.0284 | +| n_updates | 83408 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000171 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1394 | +| iterations | 16899 | +| time_elapsed | 24814 | +| total_timesteps | 34609152 | +| train/ | | +| approx_kl | 0.01269648 | +| clip_fraction | 0.318 | +| clip_range | 0.0663 | +| entropy_loss | -5.59 | +| explained_variance | 0.552 | +| learning_rate | 4.18e-05 | +| loss | -0.0253 | +| n_updates | 83412 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000152 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1394 | +| iterations | 16900 | +| time_elapsed | 24816 | +| total_timesteps | 34611200 | +| train/ | | +| approx_kl | 0.014065919 | +| clip_fraction | 0.335 | +| clip_range | 0.0663 | +| entropy_loss | -6.23 | +| explained_variance | 0.356 | +| learning_rate | 4.18e-05 | +| loss | -0.0279 | +| n_updates | 83416 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000133 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1394 | +| iterations | 16901 | +| time_elapsed | 24817 | +| total_timesteps | 34613248 | +| train/ | | +| approx_kl | 0.011386172 | +| clip_fraction | 0.329 | +| clip_range | 0.0663 | +| entropy_loss | -6.51 | +| explained_variance | 0.231 | +| learning_rate | 4.18e-05 | +| loss | -0.0246 | +| n_updates | 83420 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.00022 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1394 | +| iterations | 16902 | +| time_elapsed | 24819 | +| total_timesteps | 34615296 | +| train/ | | +| approx_kl | 0.009009628 | +| clip_fraction | 0.265 | +| clip_range | 0.0663 | +| entropy_loss | -5.86 | +| explained_variance | 0.459 | +| learning_rate | 4.18e-05 | +| loss | -0.0214 | +| n_updates | 83424 | +| policy_gradient_loss | -0.0137 | +| value_loss | 0.000312 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1394 | +| iterations | 16903 | +| time_elapsed | 24820 | +| total_timesteps | 34617344 | +| train/ | | +| approx_kl | 0.013020573 | +| clip_fraction | 0.319 | +| clip_range | 0.0663 | +| entropy_loss | -5.29 | +| explained_variance | 0.435 | +| learning_rate | 4.18e-05 | +| loss | -0.028 | +| n_updates | 83428 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000247 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1394 | +| iterations | 16904 | +| time_elapsed | 24822 | +| total_timesteps | 34619392 | +| train/ | | +| approx_kl | 0.013958219 | +| clip_fraction | 0.341 | +| clip_range | 0.0663 | +| entropy_loss | -5.41 | +| explained_variance | 0.495 | +| learning_rate | 4.18e-05 | +| loss | -0.0297 | +| n_updates | 83432 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000166 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1394 | +| iterations | 16905 | +| time_elapsed | 24823 | +| total_timesteps | 34621440 | +| train/ | | +| approx_kl | 0.013502899 | +| clip_fraction | 0.324 | +| clip_range | 0.0663 | +| entropy_loss | -5.61 | +| explained_variance | 0.615 | +| learning_rate | 4.18e-05 | +| loss | -0.0343 | +| n_updates | 83436 | +| policy_gradient_loss | -0.0185 | +| value_loss | 8.55e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1394 | +| iterations | 16906 | +| time_elapsed | 24825 | +| total_timesteps | 34623488 | +| train/ | | +| approx_kl | 0.018883035 | +| clip_fraction | 0.354 | +| clip_range | 0.0663 | +| entropy_loss | -6.04 | +| explained_variance | 0.519 | +| learning_rate | 4.18e-05 | +| loss | -0.0262 | +| n_updates | 83440 | +| policy_gradient_loss | -0.02 | +| value_loss | 7.83e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1394 | +| iterations | 16907 | +| time_elapsed | 24826 | +| total_timesteps | 34625536 | +| train/ | | +| approx_kl | 0.013336513 | +| clip_fraction | 0.353 | +| clip_range | 0.0663 | +| entropy_loss | -6.5 | +| explained_variance | -0.102 | +| learning_rate | 4.18e-05 | +| loss | -0.0322 | +| n_updates | 83444 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000218 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1394 | +| iterations | 16908 | +| time_elapsed | 24828 | +| total_timesteps | 34627584 | +| train/ | | +| approx_kl | 0.012159802 | +| clip_fraction | 0.34 | +| clip_range | 0.0663 | +| entropy_loss | -6.12 | +| explained_variance | 0.443 | +| learning_rate | 4.18e-05 | +| loss | -0.0314 | +| n_updates | 83448 | +| policy_gradient_loss | -0.0186 | +| value_loss | 9.15e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1394 | +| iterations | 16909 | +| time_elapsed | 24829 | +| total_timesteps | 34629632 | +| train/ | | +| approx_kl | 0.013136137 | +| clip_fraction | 0.326 | +| clip_range | 0.0663 | +| entropy_loss | -6.28 | +| explained_variance | 0.385 | +| learning_rate | 4.18e-05 | +| loss | -0.0306 | +| n_updates | 83452 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1394 | +| iterations | 16910 | +| time_elapsed | 24831 | +| total_timesteps | 34631680 | +| train/ | | +| approx_kl | 0.011397562 | +| clip_fraction | 0.322 | +| clip_range | 0.0663 | +| entropy_loss | -6.34 | +| explained_variance | 0.364 | +| learning_rate | 4.18e-05 | +| loss | -0.0305 | +| n_updates | 83456 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.00016 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1394 | +| iterations | 16911 | +| time_elapsed | 24832 | +| total_timesteps | 34633728 | +| train/ | | +| approx_kl | 0.012984912 | +| clip_fraction | 0.306 | +| clip_range | 0.0663 | +| entropy_loss | -6.18 | +| explained_variance | 0.205 | +| learning_rate | 4.18e-05 | +| loss | -0.0254 | +| n_updates | 83460 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.00016 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1394 | +| iterations | 16912 | +| time_elapsed | 24834 | +| total_timesteps | 34635776 | +| train/ | | +| approx_kl | 0.010606716 | +| clip_fraction | 0.277 | +| clip_range | 0.0663 | +| entropy_loss | -4.93 | +| explained_variance | 0.492 | +| learning_rate | 4.18e-05 | +| loss | -0.0194 | +| n_updates | 83464 | +| policy_gradient_loss | -0.014 | +| value_loss | 0.000446 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1394 | +| iterations | 16913 | +| time_elapsed | 24835 | +| total_timesteps | 34637824 | +| train/ | | +| approx_kl | 0.01239997 | +| clip_fraction | 0.33 | +| clip_range | 0.0663 | +| entropy_loss | -5.21 | +| explained_variance | 0.303 | +| learning_rate | 4.18e-05 | +| loss | -0.026 | +| n_updates | 83468 | +| policy_gradient_loss | -0.0188 | +| value_loss | 9.86e-05 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1394 | +| iterations | 16914 | +| time_elapsed | 24837 | +| total_timesteps | 34639872 | +| train/ | | +| approx_kl | 0.0126675805 | +| clip_fraction | 0.35 | +| clip_range | 0.0663 | +| entropy_loss | -6.02 | +| explained_variance | 0.258 | +| learning_rate | 4.18e-05 | +| loss | -0.0308 | +| n_updates | 83472 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000193 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1394 | +| iterations | 16915 | +| time_elapsed | 24838 | +| total_timesteps | 34641920 | +| train/ | | +| approx_kl | 0.009300466 | +| clip_fraction | 0.306 | +| clip_range | 0.0663 | +| entropy_loss | -6.24 | +| explained_variance | 0.518 | +| learning_rate | 4.18e-05 | +| loss | -0.0273 | +| n_updates | 83476 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000138 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1394 | +| iterations | 16916 | +| time_elapsed | 24840 | +| total_timesteps | 34643968 | +| train/ | | +| approx_kl | 0.0067476016 | +| clip_fraction | 0.285 | +| clip_range | 0.0663 | +| entropy_loss | -5.93 | +| explained_variance | 0.571 | +| learning_rate | 4.18e-05 | +| loss | -0.0221 | +| n_updates | 83480 | +| policy_gradient_loss | -0.0138 | +| value_loss | 0.000188 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1394 | +| iterations | 16917 | +| time_elapsed | 24841 | +| total_timesteps | 34646016 | +| train/ | | +| approx_kl | 0.0077732736 | +| clip_fraction | 0.268 | +| clip_range | 0.0663 | +| entropy_loss | -6.47 | +| explained_variance | 0.158 | +| learning_rate | 4.18e-05 | +| loss | -0.0202 | +| n_updates | 83484 | +| policy_gradient_loss | -0.0145 | +| value_loss | 0.000409 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1394 | +| iterations | 16918 | +| time_elapsed | 24843 | +| total_timesteps | 34648064 | +| train/ | | +| approx_kl | 0.010090189 | +| clip_fraction | 0.328 | +| clip_range | 0.0663 | +| entropy_loss | -6.81 | +| explained_variance | 0.365 | +| learning_rate | 4.18e-05 | +| loss | -0.0339 | +| n_updates | 83488 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000121 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1394 | +| iterations | 16919 | +| time_elapsed | 24844 | +| total_timesteps | 34650112 | +| train/ | | +| approx_kl | 0.010587991 | +| clip_fraction | 0.3 | +| clip_range | 0.0663 | +| entropy_loss | -6.38 | +| explained_variance | 0.332 | +| learning_rate | 4.18e-05 | +| loss | -0.0276 | +| n_updates | 83492 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000151 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1394 | +| iterations | 16920 | +| time_elapsed | 24846 | +| total_timesteps | 34652160 | +| train/ | | +| approx_kl | 0.013450844 | +| clip_fraction | 0.354 | +| clip_range | 0.0663 | +| entropy_loss | -5.82 | +| explained_variance | 0.486 | +| learning_rate | 4.18e-05 | +| loss | -0.0273 | +| n_updates | 83496 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000151 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1394 | +| iterations | 16921 | +| time_elapsed | 24847 | +| total_timesteps | 34654208 | +| train/ | | +| approx_kl | 0.0151427 | +| clip_fraction | 0.329 | +| clip_range | 0.0663 | +| entropy_loss | -5.39 | +| explained_variance | 0.318 | +| learning_rate | 4.18e-05 | +| loss | -0.0256 | +| n_updates | 83500 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000326 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1394 | +| iterations | 16922 | +| time_elapsed | 24849 | +| total_timesteps | 34656256 | +| train/ | | +| approx_kl | 0.015686765 | +| clip_fraction | 0.368 | +| clip_range | 0.0663 | +| entropy_loss | -5.95 | +| explained_variance | 0.265 | +| learning_rate | 4.18e-05 | +| loss | -0.0299 | +| n_updates | 83504 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000194 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1394 | +| iterations | 16923 | +| time_elapsed | 24850 | +| total_timesteps | 34658304 | +| train/ | | +| approx_kl | 0.014747439 | +| clip_fraction | 0.348 | +| clip_range | 0.0663 | +| entropy_loss | -5.67 | +| explained_variance | 0.415 | +| learning_rate | 4.18e-05 | +| loss | -0.0348 | +| n_updates | 83508 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000195 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1394 | +| iterations | 16924 | +| time_elapsed | 24852 | +| total_timesteps | 34660352 | +| train/ | | +| approx_kl | 0.013729321 | +| clip_fraction | 0.348 | +| clip_range | 0.0663 | +| entropy_loss | -5.18 | +| explained_variance | 0.487 | +| learning_rate | 4.18e-05 | +| loss | -0.036 | +| n_updates | 83512 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000179 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1394 | +| iterations | 16925 | +| time_elapsed | 24853 | +| total_timesteps | 34662400 | +| train/ | | +| approx_kl | 0.012999946 | +| clip_fraction | 0.362 | +| clip_range | 0.0663 | +| entropy_loss | -5.83 | +| explained_variance | 0.393 | +| learning_rate | 4.18e-05 | +| loss | -0.0252 | +| n_updates | 83516 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000107 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1394 | +| iterations | 16926 | +| time_elapsed | 24855 | +| total_timesteps | 34664448 | +| train/ | | +| approx_kl | 0.013355481 | +| clip_fraction | 0.32 | +| clip_range | 0.0663 | +| entropy_loss | -6.25 | +| explained_variance | 0.364 | +| learning_rate | 4.18e-05 | +| loss | -0.0331 | +| n_updates | 83520 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000188 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1394 | +| iterations | 16927 | +| time_elapsed | 24856 | +| total_timesteps | 34666496 | +| train/ | | +| approx_kl | 0.011530733 | +| clip_fraction | 0.329 | +| clip_range | 0.0663 | +| entropy_loss | -5.93 | +| explained_variance | 0.468 | +| learning_rate | 4.18e-05 | +| loss | -0.0263 | +| n_updates | 83524 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.00013 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1394 | +| iterations | 16928 | +| time_elapsed | 24858 | +| total_timesteps | 34668544 | +| train/ | | +| approx_kl | 0.008574229 | +| clip_fraction | 0.329 | +| clip_range | 0.0663 | +| entropy_loss | -6.76 | +| explained_variance | -0.0594 | +| learning_rate | 4.18e-05 | +| loss | -0.0282 | +| n_updates | 83528 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000198 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1394 | +| iterations | 16929 | +| time_elapsed | 24859 | +| total_timesteps | 34670592 | +| train/ | | +| approx_kl | 0.009790673 | +| clip_fraction | 0.265 | +| clip_range | 0.0663 | +| entropy_loss | -5.53 | +| explained_variance | 0.576 | +| learning_rate | 4.18e-05 | +| loss | -0.0241 | +| n_updates | 83532 | +| policy_gradient_loss | -0.0119 | +| value_loss | 0.000283 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1394 | +| iterations | 16930 | +| time_elapsed | 24861 | +| total_timesteps | 34672640 | +| train/ | | +| approx_kl | 0.010862535 | +| clip_fraction | 0.335 | +| clip_range | 0.0663 | +| entropy_loss | -5.12 | +| explained_variance | 0.438 | +| learning_rate | 4.18e-05 | +| loss | -0.0318 | +| n_updates | 83536 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000227 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1394 | +| iterations | 16931 | +| time_elapsed | 24863 | +| total_timesteps | 34674688 | +| train/ | | +| approx_kl | 0.012968154 | +| clip_fraction | 0.331 | +| clip_range | 0.0663 | +| entropy_loss | -5.89 | +| explained_variance | 0.29 | +| learning_rate | 4.18e-05 | +| loss | -0.0243 | +| n_updates | 83540 | +| policy_gradient_loss | -0.0144 | +| value_loss | 0.00036 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1394 | +| iterations | 16932 | +| time_elapsed | 24864 | +| total_timesteps | 34676736 | +| train/ | | +| approx_kl | 0.013010964 | +| clip_fraction | 0.336 | +| clip_range | 0.0663 | +| entropy_loss | -6.38 | +| explained_variance | 0.0185 | +| learning_rate | 4.18e-05 | +| loss | -0.033 | +| n_updates | 83544 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000134 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1394 | +| iterations | 16933 | +| time_elapsed | 24866 | +| total_timesteps | 34678784 | +| train/ | | +| approx_kl | 0.012480944 | +| clip_fraction | 0.331 | +| clip_range | 0.0663 | +| entropy_loss | -5.83 | +| explained_variance | 0.482 | +| learning_rate | 4.18e-05 | +| loss | -0.0319 | +| n_updates | 83548 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000152 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1394 | +| iterations | 16934 | +| time_elapsed | 24867 | +| total_timesteps | 34680832 | +| train/ | | +| approx_kl | 0.013077479 | +| clip_fraction | 0.339 | +| clip_range | 0.0663 | +| entropy_loss | -6.19 | +| explained_variance | 0.315 | +| learning_rate | 4.18e-05 | +| loss | -0.0273 | +| n_updates | 83552 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000171 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1394 | +| iterations | 16935 | +| time_elapsed | 24869 | +| total_timesteps | 34682880 | +| train/ | | +| approx_kl | 0.0150029985 | +| clip_fraction | 0.353 | +| clip_range | 0.0663 | +| entropy_loss | -6.69 | +| explained_variance | -0.249 | +| learning_rate | 4.18e-05 | +| loss | -0.0356 | +| n_updates | 83556 | +| policy_gradient_loss | -0.0208 | +| value_loss | 8.84e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1394 | +| iterations | 16936 | +| time_elapsed | 24870 | +| total_timesteps | 34684928 | +| train/ | | +| approx_kl | 0.013108384 | +| clip_fraction | 0.334 | +| clip_range | 0.0663 | +| entropy_loss | -6.41 | +| explained_variance | 0.336 | +| learning_rate | 4.18e-05 | +| loss | -0.0268 | +| n_updates | 83560 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000188 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1394 | +| iterations | 16937 | +| time_elapsed | 24872 | +| total_timesteps | 34686976 | +| train/ | | +| approx_kl | 0.010228615 | +| clip_fraction | 0.312 | +| clip_range | 0.0663 | +| entropy_loss | -5.7 | +| explained_variance | 0.444 | +| learning_rate | 4.18e-05 | +| loss | -0.0232 | +| n_updates | 83564 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.000273 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1394 | +| iterations | 16938 | +| time_elapsed | 24873 | +| total_timesteps | 34689024 | +| train/ | | +| approx_kl | 0.014827313 | +| clip_fraction | 0.336 | +| clip_range | 0.0663 | +| entropy_loss | -5.7 | +| explained_variance | 0.666 | +| learning_rate | 4.18e-05 | +| loss | -0.027 | +| n_updates | 83568 | +| policy_gradient_loss | -0.018 | +| value_loss | 9.77e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1394 | +| iterations | 16939 | +| time_elapsed | 24875 | +| total_timesteps | 34691072 | +| train/ | | +| approx_kl | 0.013353071 | +| clip_fraction | 0.353 | +| clip_range | 0.0663 | +| entropy_loss | -6 | +| explained_variance | 0.233 | +| learning_rate | 4.18e-05 | +| loss | -0.0344 | +| n_updates | 83572 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000199 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1394 | +| iterations | 16940 | +| time_elapsed | 24876 | +| total_timesteps | 34693120 | +| train/ | | +| approx_kl | 0.0129852425 | +| clip_fraction | 0.347 | +| clip_range | 0.0663 | +| entropy_loss | -6.08 | +| explained_variance | 0.437 | +| learning_rate | 4.18e-05 | +| loss | -0.0202 | +| n_updates | 83576 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000168 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1394 | +| iterations | 16941 | +| time_elapsed | 24878 | +| total_timesteps | 34695168 | +| train/ | | +| approx_kl | 0.0105379205 | +| clip_fraction | 0.323 | +| clip_range | 0.0663 | +| entropy_loss | -5.65 | +| explained_variance | 0.749 | +| learning_rate | 4.18e-05 | +| loss | -0.0262 | +| n_updates | 83580 | +| policy_gradient_loss | -0.0178 | +| value_loss | 9.01e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1394 | +| iterations | 16942 | +| time_elapsed | 24879 | +| total_timesteps | 34697216 | +| train/ | | +| approx_kl | 0.012238551 | +| clip_fraction | 0.324 | +| clip_range | 0.0663 | +| entropy_loss | -5.7 | +| explained_variance | 0.418 | +| learning_rate | 4.18e-05 | +| loss | -0.0255 | +| n_updates | 83584 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.00011 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1394 | +| iterations | 16943 | +| time_elapsed | 24881 | +| total_timesteps | 34699264 | +| train/ | | +| approx_kl | 0.012517106 | +| clip_fraction | 0.353 | +| clip_range | 0.0663 | +| entropy_loss | -6.05 | +| explained_variance | 0.492 | +| learning_rate | 4.18e-05 | +| loss | -0.0291 | +| n_updates | 83588 | +| policy_gradient_loss | -0.0182 | +| value_loss | 9.73e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1394 | +| iterations | 16944 | +| time_elapsed | 24883 | +| total_timesteps | 34701312 | +| train/ | | +| approx_kl | 0.01307159 | +| clip_fraction | 0.334 | +| clip_range | 0.0663 | +| entropy_loss | -6.64 | +| explained_variance | -0.0254 | +| learning_rate | 4.18e-05 | +| loss | -0.0242 | +| n_updates | 83592 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000134 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1394 | +| iterations | 16945 | +| time_elapsed | 24884 | +| total_timesteps | 34703360 | +| train/ | | +| approx_kl | 0.013666084 | +| clip_fraction | 0.318 | +| clip_range | 0.0663 | +| entropy_loss | -6.05 | +| explained_variance | 0.447 | +| learning_rate | 4.18e-05 | +| loss | -0.0219 | +| n_updates | 83596 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000169 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1394 | +| iterations | 16946 | +| time_elapsed | 24886 | +| total_timesteps | 34705408 | +| train/ | | +| approx_kl | 0.012926463 | +| clip_fraction | 0.326 | +| clip_range | 0.0663 | +| entropy_loss | -6.21 | +| explained_variance | 0.267 | +| learning_rate | 4.18e-05 | +| loss | -0.0291 | +| n_updates | 83600 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.00017 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1394 | +| iterations | 16947 | +| time_elapsed | 24887 | +| total_timesteps | 34707456 | +| train/ | | +| approx_kl | 0.012516623 | +| clip_fraction | 0.382 | +| clip_range | 0.0663 | +| entropy_loss | -6.2 | +| explained_variance | 0.439 | +| learning_rate | 4.18e-05 | +| loss | -0.03 | +| n_updates | 83604 | +| policy_gradient_loss | -0.0206 | +| value_loss | 7.6e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1394 | +| iterations | 16948 | +| time_elapsed | 24889 | +| total_timesteps | 34709504 | +| train/ | | +| approx_kl | 0.012339363 | +| clip_fraction | 0.318 | +| clip_range | 0.0663 | +| entropy_loss | -5.85 | +| explained_variance | 0.687 | +| learning_rate | 4.18e-05 | +| loss | -0.0268 | +| n_updates | 83608 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000114 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1394 | +| iterations | 16949 | +| time_elapsed | 24890 | +| total_timesteps | 34711552 | +| train/ | | +| approx_kl | 0.012468182 | +| clip_fraction | 0.321 | +| clip_range | 0.0663 | +| entropy_loss | -6.22 | +| explained_variance | -0.222 | +| learning_rate | 4.18e-05 | +| loss | -0.0316 | +| n_updates | 83612 | +| policy_gradient_loss | -0.0177 | +| value_loss | 8.73e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1394 | +| iterations | 16950 | +| time_elapsed | 24892 | +| total_timesteps | 34713600 | +| train/ | | +| approx_kl | 0.010760678 | +| clip_fraction | 0.321 | +| clip_range | 0.0663 | +| entropy_loss | -6.19 | +| explained_variance | 0.612 | +| learning_rate | 4.18e-05 | +| loss | -0.0254 | +| n_updates | 83616 | +| policy_gradient_loss | -0.0158 | +| value_loss | 9.64e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1394 | +| iterations | 16951 | +| time_elapsed | 24893 | +| total_timesteps | 34715648 | +| train/ | | +| approx_kl | 0.012374386 | +| clip_fraction | 0.316 | +| clip_range | 0.0663 | +| entropy_loss | -6.16 | +| explained_variance | 0.378 | +| learning_rate | 4.18e-05 | +| loss | -0.0231 | +| n_updates | 83620 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.00026 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1394 | +| iterations | 16952 | +| time_elapsed | 24895 | +| total_timesteps | 34717696 | +| train/ | | +| approx_kl | 0.012829415 | +| clip_fraction | 0.328 | +| clip_range | 0.0663 | +| entropy_loss | -5.08 | +| explained_variance | 0.749 | +| learning_rate | 4.18e-05 | +| loss | -0.0288 | +| n_updates | 83624 | +| policy_gradient_loss | -0.0155 | +| value_loss | 7.16e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1394 | +| iterations | 16953 | +| time_elapsed | 24896 | +| total_timesteps | 34719744 | +| train/ | | +| approx_kl | 0.01876064 | +| clip_fraction | 0.338 | +| clip_range | 0.0663 | +| entropy_loss | -5.14 | +| explained_variance | 0.368 | +| learning_rate | 4.18e-05 | +| loss | -0.0258 | +| n_updates | 83628 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000129 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1394 | +| iterations | 16954 | +| time_elapsed | 24898 | +| total_timesteps | 34721792 | +| train/ | | +| approx_kl | 0.012905774 | +| clip_fraction | 0.344 | +| clip_range | 0.0663 | +| entropy_loss | -5.85 | +| explained_variance | 0.33 | +| learning_rate | 4.18e-05 | +| loss | -0.0313 | +| n_updates | 83632 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000139 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1394 | +| iterations | 16955 | +| time_elapsed | 24899 | +| total_timesteps | 34723840 | +| train/ | | +| approx_kl | 0.014251526 | +| clip_fraction | 0.313 | +| clip_range | 0.0663 | +| entropy_loss | -6.44 | +| explained_variance | 0.586 | +| learning_rate | 4.18e-05 | +| loss | -0.0237 | +| n_updates | 83636 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000104 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1394 | +| iterations | 16956 | +| time_elapsed | 24901 | +| total_timesteps | 34725888 | +| train/ | | +| approx_kl | 0.010448458 | +| clip_fraction | 0.323 | +| clip_range | 0.0663 | +| entropy_loss | -5.94 | +| explained_variance | 0.504 | +| learning_rate | 4.18e-05 | +| loss | -0.0268 | +| n_updates | 83640 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000153 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1394 | +| iterations | 16957 | +| time_elapsed | 24903 | +| total_timesteps | 34727936 | +| train/ | | +| approx_kl | 0.013483212 | +| clip_fraction | 0.315 | +| clip_range | 0.0663 | +| entropy_loss | -5.59 | +| explained_variance | 0.32 | +| learning_rate | 4.18e-05 | +| loss | -0.0263 | +| n_updates | 83644 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000342 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1394 | +| iterations | 16958 | +| time_elapsed | 24904 | +| total_timesteps | 34729984 | +| train/ | | +| approx_kl | 0.01676331 | +| clip_fraction | 0.38 | +| clip_range | 0.0663 | +| entropy_loss | -5.65 | +| explained_variance | 0.393 | +| learning_rate | 4.18e-05 | +| loss | -0.0388 | +| n_updates | 83648 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000118 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1394 | +| iterations | 16959 | +| time_elapsed | 24906 | +| total_timesteps | 34732032 | +| train/ | | +| approx_kl | 0.014295073 | +| clip_fraction | 0.331 | +| clip_range | 0.0663 | +| entropy_loss | -5.59 | +| explained_variance | 0.559 | +| learning_rate | 4.18e-05 | +| loss | -0.0248 | +| n_updates | 83652 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000153 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1394 | +| iterations | 16960 | +| time_elapsed | 24907 | +| total_timesteps | 34734080 | +| train/ | | +| approx_kl | 0.012318443 | +| clip_fraction | 0.319 | +| clip_range | 0.0663 | +| entropy_loss | -5.52 | +| explained_variance | 0.519 | +| learning_rate | 4.18e-05 | +| loss | -0.0253 | +| n_updates | 83656 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.000144 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1394 | +| iterations | 16961 | +| time_elapsed | 24909 | +| total_timesteps | 34736128 | +| train/ | | +| approx_kl | 0.01605347 | +| clip_fraction | 0.353 | +| clip_range | 0.0663 | +| entropy_loss | -5.6 | +| explained_variance | 0.339 | +| learning_rate | 4.18e-05 | +| loss | -0.0253 | +| n_updates | 83660 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000127 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1394 | +| iterations | 16962 | +| time_elapsed | 24910 | +| total_timesteps | 34738176 | +| train/ | | +| approx_kl | 0.019008618 | +| clip_fraction | 0.319 | +| clip_range | 0.0663 | +| entropy_loss | -6.07 | +| explained_variance | 0.29 | +| learning_rate | 4.18e-05 | +| loss | -0.0215 | +| n_updates | 83664 | +| policy_gradient_loss | -0.0146 | +| value_loss | 0.000189 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1394 | +| iterations | 16963 | +| time_elapsed | 24912 | +| total_timesteps | 34740224 | +| train/ | | +| approx_kl | 0.018425293 | +| clip_fraction | 0.337 | +| clip_range | 0.0663 | +| entropy_loss | -5.89 | +| explained_variance | 0.3 | +| learning_rate | 4.17e-05 | +| loss | -0.0296 | +| n_updates | 83668 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000155 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1394 | +| iterations | 16964 | +| time_elapsed | 24913 | +| total_timesteps | 34742272 | +| train/ | | +| approx_kl | 0.013324265 | +| clip_fraction | 0.341 | +| clip_range | 0.0663 | +| entropy_loss | -6.04 | +| explained_variance | 0.259 | +| learning_rate | 4.17e-05 | +| loss | -0.0286 | +| n_updates | 83672 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000201 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1394 | +| iterations | 16965 | +| time_elapsed | 24915 | +| total_timesteps | 34744320 | +| train/ | | +| approx_kl | 0.014132482 | +| clip_fraction | 0.356 | +| clip_range | 0.0663 | +| entropy_loss | -5.58 | +| explained_variance | 0.709 | +| learning_rate | 4.17e-05 | +| loss | -0.0293 | +| n_updates | 83676 | +| policy_gradient_loss | -0.0205 | +| value_loss | 9.84e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1394 | +| iterations | 16966 | +| time_elapsed | 24916 | +| total_timesteps | 34746368 | +| train/ | | +| approx_kl | 0.013472399 | +| clip_fraction | 0.361 | +| clip_range | 0.0663 | +| entropy_loss | -5.93 | +| explained_variance | 0.514 | +| learning_rate | 4.17e-05 | +| loss | -0.0271 | +| n_updates | 83680 | +| policy_gradient_loss | -0.0189 | +| value_loss | 8.22e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1394 | +| iterations | 16967 | +| time_elapsed | 24918 | +| total_timesteps | 34748416 | +| train/ | | +| approx_kl | 0.011114115 | +| clip_fraction | 0.313 | +| clip_range | 0.0663 | +| entropy_loss | -5.98 | +| explained_variance | 0.603 | +| learning_rate | 4.17e-05 | +| loss | -0.0233 | +| n_updates | 83684 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000135 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1394 | +| iterations | 16968 | +| time_elapsed | 24919 | +| total_timesteps | 34750464 | +| train/ | | +| approx_kl | 0.015748268 | +| clip_fraction | 0.351 | +| clip_range | 0.0663 | +| entropy_loss | -5.48 | +| explained_variance | 0.719 | +| learning_rate | 4.17e-05 | +| loss | -0.0343 | +| n_updates | 83688 | +| policy_gradient_loss | -0.0203 | +| value_loss | 6.14e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1394 | +| iterations | 16969 | +| time_elapsed | 24921 | +| total_timesteps | 34752512 | +| train/ | | +| approx_kl | 0.01409512 | +| clip_fraction | 0.344 | +| clip_range | 0.0663 | +| entropy_loss | -5.53 | +| explained_variance | 0.423 | +| learning_rate | 4.17e-05 | +| loss | -0.0265 | +| n_updates | 83692 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000235 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1394 | +| iterations | 16970 | +| time_elapsed | 24923 | +| total_timesteps | 34754560 | +| train/ | | +| approx_kl | 0.015067932 | +| clip_fraction | 0.349 | +| clip_range | 0.0663 | +| entropy_loss | -5.74 | +| explained_variance | 0.557 | +| learning_rate | 4.17e-05 | +| loss | -0.0288 | +| n_updates | 83696 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000111 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1394 | +| iterations | 16971 | +| time_elapsed | 24924 | +| total_timesteps | 34756608 | +| train/ | | +| approx_kl | 0.010090984 | +| clip_fraction | 0.297 | +| clip_range | 0.0663 | +| entropy_loss | -5.77 | +| explained_variance | 0.264 | +| learning_rate | 4.17e-05 | +| loss | -0.0259 | +| n_updates | 83700 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000143 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1394 | +| iterations | 16972 | +| time_elapsed | 24926 | +| total_timesteps | 34758656 | +| train/ | | +| approx_kl | 0.014183755 | +| clip_fraction | 0.365 | +| clip_range | 0.0663 | +| entropy_loss | -5.99 | +| explained_variance | 0.535 | +| learning_rate | 4.17e-05 | +| loss | -0.0319 | +| n_updates | 83704 | +| policy_gradient_loss | -0.0204 | +| value_loss | 7.11e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1394 | +| iterations | 16973 | +| time_elapsed | 24927 | +| total_timesteps | 34760704 | +| train/ | | +| approx_kl | 0.013882371 | +| clip_fraction | 0.36 | +| clip_range | 0.0663 | +| entropy_loss | -6.04 | +| explained_variance | -0.0601 | +| learning_rate | 4.17e-05 | +| loss | -0.0277 | +| n_updates | 83708 | +| policy_gradient_loss | -0.0189 | +| value_loss | 9.61e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1394 | +| iterations | 16974 | +| time_elapsed | 24929 | +| total_timesteps | 34762752 | +| train/ | | +| approx_kl | 0.011817237 | +| clip_fraction | 0.309 | +| clip_range | 0.0663 | +| entropy_loss | -6.31 | +| explained_variance | 0.465 | +| learning_rate | 4.17e-05 | +| loss | -0.0285 | +| n_updates | 83712 | +| policy_gradient_loss | -0.0167 | +| value_loss | 8.44e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1394 | +| iterations | 16975 | +| time_elapsed | 24930 | +| total_timesteps | 34764800 | +| train/ | | +| approx_kl | 0.010649439 | +| clip_fraction | 0.309 | +| clip_range | 0.0663 | +| entropy_loss | -5.53 | +| explained_variance | 0.696 | +| learning_rate | 4.17e-05 | +| loss | -0.0301 | +| n_updates | 83716 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000126 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1394 | +| iterations | 16976 | +| time_elapsed | 24932 | +| total_timesteps | 34766848 | +| train/ | | +| approx_kl | 0.008182469 | +| clip_fraction | 0.288 | +| clip_range | 0.0663 | +| entropy_loss | -6.13 | +| explained_variance | 0.22 | +| learning_rate | 4.17e-05 | +| loss | -0.0165 | +| n_updates | 83720 | +| policy_gradient_loss | -0.0137 | +| value_loss | 0.000318 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1394 | +| iterations | 16977 | +| time_elapsed | 24933 | +| total_timesteps | 34768896 | +| train/ | | +| approx_kl | 0.0091389865 | +| clip_fraction | 0.316 | +| clip_range | 0.0663 | +| entropy_loss | -6.1 | +| explained_variance | 0.409 | +| learning_rate | 4.17e-05 | +| loss | -0.028 | +| n_updates | 83724 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000144 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1394 | +| iterations | 16978 | +| time_elapsed | 24935 | +| total_timesteps | 34770944 | +| train/ | | +| approx_kl | 0.010813581 | +| clip_fraction | 0.328 | +| clip_range | 0.0663 | +| entropy_loss | -5.2 | +| explained_variance | 0.647 | +| learning_rate | 4.17e-05 | +| loss | -0.0273 | +| n_updates | 83728 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.00014 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1394 | +| iterations | 16979 | +| time_elapsed | 24936 | +| total_timesteps | 34772992 | +| train/ | | +| approx_kl | 0.01950454 | +| clip_fraction | 0.293 | +| clip_range | 0.0663 | +| entropy_loss | -4.51 | +| explained_variance | 0.7 | +| learning_rate | 4.17e-05 | +| loss | -0.0261 | +| n_updates | 83732 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000106 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1394 | +| iterations | 16980 | +| time_elapsed | 24938 | +| total_timesteps | 34775040 | +| train/ | | +| approx_kl | 0.012709988 | +| clip_fraction | 0.361 | +| clip_range | 0.0663 | +| entropy_loss | -5.68 | +| explained_variance | 0.384 | +| learning_rate | 4.17e-05 | +| loss | -0.0305 | +| n_updates | 83736 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000133 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1394 | +| iterations | 16981 | +| time_elapsed | 24940 | +| total_timesteps | 34777088 | +| train/ | | +| approx_kl | 0.011978529 | +| clip_fraction | 0.348 | +| clip_range | 0.0663 | +| entropy_loss | -6.37 | +| explained_variance | 0.121 | +| learning_rate | 4.17e-05 | +| loss | -0.0262 | +| n_updates | 83740 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.00016 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1394 | +| iterations | 16982 | +| time_elapsed | 24941 | +| total_timesteps | 34779136 | +| train/ | | +| approx_kl | 0.014423962 | +| clip_fraction | 0.335 | +| clip_range | 0.0663 | +| entropy_loss | -6.29 | +| explained_variance | 0.385 | +| learning_rate | 4.17e-05 | +| loss | -0.0316 | +| n_updates | 83744 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000108 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1394 | +| iterations | 16983 | +| time_elapsed | 24943 | +| total_timesteps | 34781184 | +| train/ | | +| approx_kl | 0.00988386 | +| clip_fraction | 0.288 | +| clip_range | 0.0663 | +| entropy_loss | -5.91 | +| explained_variance | 0.444 | +| learning_rate | 4.17e-05 | +| loss | -0.0204 | +| n_updates | 83748 | +| policy_gradient_loss | -0.0139 | +| value_loss | 0.000169 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1394 | +| iterations | 16984 | +| time_elapsed | 24944 | +| total_timesteps | 34783232 | +| train/ | | +| approx_kl | 0.009043524 | +| clip_fraction | 0.306 | +| clip_range | 0.0663 | +| entropy_loss | -6.26 | +| explained_variance | -0.131 | +| learning_rate | 4.17e-05 | +| loss | -0.0186 | +| n_updates | 83752 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000182 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1394 | +| iterations | 16985 | +| time_elapsed | 24946 | +| total_timesteps | 34785280 | +| train/ | | +| approx_kl | 0.012648178 | +| clip_fraction | 0.359 | +| clip_range | 0.0663 | +| entropy_loss | -5.95 | +| explained_variance | 0.231 | +| learning_rate | 4.17e-05 | +| loss | -0.031 | +| n_updates | 83756 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000166 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1394 | +| iterations | 16986 | +| time_elapsed | 24947 | +| total_timesteps | 34787328 | +| train/ | | +| approx_kl | 0.010666417 | +| clip_fraction | 0.314 | +| clip_range | 0.0663 | +| entropy_loss | -6.11 | +| explained_variance | 0.372 | +| learning_rate | 4.17e-05 | +| loss | -0.0277 | +| n_updates | 83760 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000268 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1394 | +| iterations | 16987 | +| time_elapsed | 24949 | +| total_timesteps | 34789376 | +| train/ | | +| approx_kl | 0.010505583 | +| clip_fraction | 0.315 | +| clip_range | 0.0663 | +| entropy_loss | -5.22 | +| explained_variance | 0.626 | +| learning_rate | 4.17e-05 | +| loss | -0.0258 | +| n_updates | 83764 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000209 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1394 | +| iterations | 16988 | +| time_elapsed | 24950 | +| total_timesteps | 34791424 | +| train/ | | +| approx_kl | 0.0134762935 | +| clip_fraction | 0.319 | +| clip_range | 0.0663 | +| entropy_loss | -4.94 | +| explained_variance | 0.569 | +| learning_rate | 4.17e-05 | +| loss | -0.0289 | +| n_updates | 83768 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000103 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1394 | +| iterations | 16989 | +| time_elapsed | 24952 | +| total_timesteps | 34793472 | +| train/ | | +| approx_kl | 0.01371094 | +| clip_fraction | 0.317 | +| clip_range | 0.0663 | +| entropy_loss | -5.74 | +| explained_variance | 0.278 | +| learning_rate | 4.17e-05 | +| loss | -0.0288 | +| n_updates | 83772 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000158 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1394 | +| iterations | 16990 | +| time_elapsed | 24953 | +| total_timesteps | 34795520 | +| train/ | | +| approx_kl | 0.014391503 | +| clip_fraction | 0.364 | +| clip_range | 0.0663 | +| entropy_loss | -6.38 | +| explained_variance | -0.243 | +| learning_rate | 4.17e-05 | +| loss | -0.0368 | +| n_updates | 83776 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.0001 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1394 | +| iterations | 16991 | +| time_elapsed | 24955 | +| total_timesteps | 34797568 | +| train/ | | +| approx_kl | 0.013215382 | +| clip_fraction | 0.344 | +| clip_range | 0.0663 | +| entropy_loss | -6.2 | +| explained_variance | 0.225 | +| learning_rate | 4.17e-05 | +| loss | -0.0283 | +| n_updates | 83780 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.00023 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1394 | +| iterations | 16992 | +| time_elapsed | 24956 | +| total_timesteps | 34799616 | +| train/ | | +| approx_kl | 0.016766984 | +| clip_fraction | 0.36 | +| clip_range | 0.0663 | +| entropy_loss | -5.54 | +| explained_variance | 0.673 | +| learning_rate | 4.17e-05 | +| loss | -0.0335 | +| n_updates | 83784 | +| policy_gradient_loss | -0.0209 | +| value_loss | 7.39e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1394 | +| iterations | 16993 | +| time_elapsed | 24958 | +| total_timesteps | 34801664 | +| train/ | | +| approx_kl | 0.016631946 | +| clip_fraction | 0.365 | +| clip_range | 0.0663 | +| entropy_loss | -5.62 | +| explained_variance | 0.22 | +| learning_rate | 4.17e-05 | +| loss | -0.0307 | +| n_updates | 83788 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000114 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1394 | +| iterations | 16994 | +| time_elapsed | 24960 | +| total_timesteps | 34803712 | +| train/ | | +| approx_kl | 0.011437079 | +| clip_fraction | 0.3 | +| clip_range | 0.0663 | +| entropy_loss | -5.72 | +| explained_variance | 0.39 | +| learning_rate | 4.17e-05 | +| loss | -0.0215 | +| n_updates | 83792 | +| policy_gradient_loss | -0.0132 | +| value_loss | 0.00031 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1394 | +| iterations | 16995 | +| time_elapsed | 24961 | +| total_timesteps | 34805760 | +| train/ | | +| approx_kl | 0.012261866 | +| clip_fraction | 0.302 | +| clip_range | 0.0663 | +| entropy_loss | -5.73 | +| explained_variance | 0.258 | +| learning_rate | 4.17e-05 | +| loss | -0.0257 | +| n_updates | 83796 | +| policy_gradient_loss | -0.0141 | +| value_loss | 0.000197 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1394 | +| iterations | 16996 | +| time_elapsed | 24963 | +| total_timesteps | 34807808 | +| train/ | | +| approx_kl | 0.010180829 | +| clip_fraction | 0.347 | +| clip_range | 0.0663 | +| entropy_loss | -5.66 | +| explained_variance | 0.524 | +| learning_rate | 4.17e-05 | +| loss | -0.0262 | +| n_updates | 83800 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000102 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1394 | +| iterations | 16997 | +| time_elapsed | 24964 | +| total_timesteps | 34809856 | +| train/ | | +| approx_kl | 0.013713336 | +| clip_fraction | 0.322 | +| clip_range | 0.0663 | +| entropy_loss | -5.84 | +| explained_variance | 0.402 | +| learning_rate | 4.17e-05 | +| loss | -0.0293 | +| n_updates | 83804 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000201 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 1394 | +| iterations | 16998 | +| time_elapsed | 24966 | +| total_timesteps | 34811904 | +| train/ | | +| approx_kl | 0.009136482 | +| clip_fraction | 0.311 | +| clip_range | 0.0663 | +| entropy_loss | -6.05 | +| explained_variance | 0.448 | +| learning_rate | 4.17e-05 | +| loss | -0.023 | +| n_updates | 83808 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000186 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 1394 | +| iterations | 16999 | +| time_elapsed | 24967 | +| total_timesteps | 34813952 | +| train/ | | +| approx_kl | 0.013016817 | +| clip_fraction | 0.294 | +| clip_range | 0.0663 | +| entropy_loss | -5.67 | +| explained_variance | 0.471 | +| learning_rate | 4.17e-05 | +| loss | -0.025 | +| n_updates | 83812 | +| policy_gradient_loss | -0.0142 | +| value_loss | 0.000249 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 1394 | +| iterations | 17000 | +| time_elapsed | 24969 | +| total_timesteps | 34816000 | +| train/ | | +| approx_kl | 0.012684718 | +| clip_fraction | 0.34 | +| clip_range | 0.0663 | +| entropy_loss | -6.12 | +| explained_variance | 0.0515 | +| learning_rate | 4.17e-05 | +| loss | -0.0268 | +| n_updates | 83816 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000167 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 1394 | +| iterations | 17001 | +| time_elapsed | 24970 | +| total_timesteps | 34818048 | +| train/ | | +| approx_kl | 0.013739469 | +| clip_fraction | 0.358 | +| clip_range | 0.0663 | +| entropy_loss | -6.16 | +| explained_variance | 0.029 | +| learning_rate | 4.17e-05 | +| loss | -0.0271 | +| n_updates | 83820 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000118 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 1394 | +| iterations | 17002 | +| time_elapsed | 24972 | +| total_timesteps | 34820096 | +| train/ | | +| approx_kl | 0.011442864 | +| clip_fraction | 0.339 | +| clip_range | 0.0663 | +| entropy_loss | -6.07 | +| explained_variance | 0.486 | +| learning_rate | 4.17e-05 | +| loss | -0.0298 | +| n_updates | 83824 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000169 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 1394 | +| iterations | 17003 | +| time_elapsed | 24973 | +| total_timesteps | 34822144 | +| train/ | | +| approx_kl | 0.014804469 | +| clip_fraction | 0.366 | +| clip_range | 0.0663 | +| entropy_loss | -5.72 | +| explained_variance | -0.00647 | +| learning_rate | 4.17e-05 | +| loss | -0.0283 | +| n_updates | 83828 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000131 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 1394 | +| iterations | 17004 | +| time_elapsed | 24975 | +| total_timesteps | 34824192 | +| train/ | | +| approx_kl | 0.015646454 | +| clip_fraction | 0.35 | +| clip_range | 0.0663 | +| entropy_loss | -6.06 | +| explained_variance | 0.367 | +| learning_rate | 4.17e-05 | +| loss | -0.0309 | +| n_updates | 83832 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000152 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.306 | +| time/ | | +| fps | 1394 | +| iterations | 17005 | +| time_elapsed | 24976 | +| total_timesteps | 34826240 | +| train/ | | +| approx_kl | 0.01415769 | +| clip_fraction | 0.365 | +| clip_range | 0.0663 | +| entropy_loss | -5.48 | +| explained_variance | 0.609 | +| learning_rate | 4.17e-05 | +| loss | -0.03 | +| n_updates | 83836 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000112 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1394 | +| iterations | 17006 | +| time_elapsed | 24978 | +| total_timesteps | 34828288 | +| train/ | | +| approx_kl | 0.014683489 | +| clip_fraction | 0.334 | +| clip_range | 0.0663 | +| entropy_loss | -5.8 | +| explained_variance | 0.305 | +| learning_rate | 4.17e-05 | +| loss | -0.0248 | +| n_updates | 83840 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000188 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.315 | +| time/ | | +| fps | 1394 | +| iterations | 17007 | +| time_elapsed | 24979 | +| total_timesteps | 34830336 | +| train/ | | +| approx_kl | 0.010483456 | +| clip_fraction | 0.329 | +| clip_range | 0.0663 | +| entropy_loss | -6.05 | +| explained_variance | 0.509 | +| learning_rate | 4.17e-05 | +| loss | -0.0232 | +| n_updates | 83844 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000164 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1394 | +| iterations | 17008 | +| time_elapsed | 24981 | +| total_timesteps | 34832384 | +| train/ | | +| approx_kl | 0.008816345 | +| clip_fraction | 0.309 | +| clip_range | 0.0663 | +| entropy_loss | -6.21 | +| explained_variance | 0.356 | +| learning_rate | 4.17e-05 | +| loss | -0.03 | +| n_updates | 83848 | +| policy_gradient_loss | -0.0148 | +| value_loss | 0.000258 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1394 | +| iterations | 17009 | +| time_elapsed | 24982 | +| total_timesteps | 34834432 | +| train/ | | +| approx_kl | 0.011537313 | +| clip_fraction | 0.296 | +| clip_range | 0.0663 | +| entropy_loss | -6.14 | +| explained_variance | 0.405 | +| learning_rate | 4.17e-05 | +| loss | -0.0274 | +| n_updates | 83852 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000191 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1394 | +| iterations | 17010 | +| time_elapsed | 24984 | +| total_timesteps | 34836480 | +| train/ | | +| approx_kl | 0.012714838 | +| clip_fraction | 0.323 | +| clip_range | 0.0663 | +| entropy_loss | -5.58 | +| explained_variance | 0.547 | +| learning_rate | 4.17e-05 | +| loss | -0.029 | +| n_updates | 83856 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000164 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1394 | +| iterations | 17011 | +| time_elapsed | 24986 | +| total_timesteps | 34838528 | +| train/ | | +| approx_kl | 0.012095522 | +| clip_fraction | 0.347 | +| clip_range | 0.0663 | +| entropy_loss | -6.43 | +| explained_variance | 0.0719 | +| learning_rate | 4.17e-05 | +| loss | -0.0337 | +| n_updates | 83860 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000104 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1394 | +| iterations | 17012 | +| time_elapsed | 24987 | +| total_timesteps | 34840576 | +| train/ | | +| approx_kl | 0.012076607 | +| clip_fraction | 0.322 | +| clip_range | 0.0663 | +| entropy_loss | -6.06 | +| explained_variance | 0.225 | +| learning_rate | 4.17e-05 | +| loss | -0.0255 | +| n_updates | 83864 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000374 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1394 | +| iterations | 17013 | +| time_elapsed | 24989 | +| total_timesteps | 34842624 | +| train/ | | +| approx_kl | 0.016269237 | +| clip_fraction | 0.329 | +| clip_range | 0.0663 | +| entropy_loss | -5.58 | +| explained_variance | 0.538 | +| learning_rate | 4.17e-05 | +| loss | -0.0281 | +| n_updates | 83868 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.00015 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1394 | +| iterations | 17014 | +| time_elapsed | 24990 | +| total_timesteps | 34844672 | +| train/ | | +| approx_kl | 0.01215495 | +| clip_fraction | 0.344 | +| clip_range | 0.0663 | +| entropy_loss | -6.18 | +| explained_variance | 0.243 | +| learning_rate | 4.17e-05 | +| loss | -0.0265 | +| n_updates | 83872 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000198 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1394 | +| iterations | 17015 | +| time_elapsed | 24992 | +| total_timesteps | 34846720 | +| train/ | | +| approx_kl | 0.011863988 | +| clip_fraction | 0.344 | +| clip_range | 0.0663 | +| entropy_loss | -5.8 | +| explained_variance | 0.522 | +| learning_rate | 4.17e-05 | +| loss | -0.0337 | +| n_updates | 83876 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1394 | +| iterations | 17016 | +| time_elapsed | 24993 | +| total_timesteps | 34848768 | +| train/ | | +| approx_kl | 0.009120828 | +| clip_fraction | 0.298 | +| clip_range | 0.0663 | +| entropy_loss | -6.34 | +| explained_variance | 0.523 | +| learning_rate | 4.17e-05 | +| loss | -0.0243 | +| n_updates | 83880 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000161 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1394 | +| iterations | 17017 | +| time_elapsed | 24995 | +| total_timesteps | 34850816 | +| train/ | | +| approx_kl | 0.009561557 | +| clip_fraction | 0.317 | +| clip_range | 0.0663 | +| entropy_loss | -6.1 | +| explained_variance | 0.459 | +| learning_rate | 4.17e-05 | +| loss | -0.0333 | +| n_updates | 83884 | +| policy_gradient_loss | -0.0178 | +| value_loss | 8.97e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1394 | +| iterations | 17018 | +| time_elapsed | 24996 | +| total_timesteps | 34852864 | +| train/ | | +| approx_kl | 0.0114294635 | +| clip_fraction | 0.301 | +| clip_range | 0.0663 | +| entropy_loss | -6.49 | +| explained_variance | 0.332 | +| learning_rate | 4.17e-05 | +| loss | -0.0271 | +| n_updates | 83888 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000111 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1394 | +| iterations | 17019 | +| time_elapsed | 24998 | +| total_timesteps | 34854912 | +| train/ | | +| approx_kl | 0.00938614 | +| clip_fraction | 0.318 | +| clip_range | 0.0663 | +| entropy_loss | -6.58 | +| explained_variance | -0.0613 | +| learning_rate | 4.17e-05 | +| loss | -0.028 | +| n_updates | 83892 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000184 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1394 | +| iterations | 17020 | +| time_elapsed | 24999 | +| total_timesteps | 34856960 | +| train/ | | +| approx_kl | 0.014941682 | +| clip_fraction | 0.362 | +| clip_range | 0.0663 | +| entropy_loss | -6.3 | +| explained_variance | 0.525 | +| learning_rate | 4.17e-05 | +| loss | -0.0287 | +| n_updates | 83896 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000132 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1394 | +| iterations | 17021 | +| time_elapsed | 25001 | +| total_timesteps | 34859008 | +| train/ | | +| approx_kl | 0.014188418 | +| clip_fraction | 0.328 | +| clip_range | 0.0663 | +| entropy_loss | -5.84 | +| explained_variance | 0.213 | +| learning_rate | 4.17e-05 | +| loss | -0.0264 | +| n_updates | 83900 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000115 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1394 | +| iterations | 17022 | +| time_elapsed | 25003 | +| total_timesteps | 34861056 | +| train/ | | +| approx_kl | 0.012188517 | +| clip_fraction | 0.332 | +| clip_range | 0.0663 | +| entropy_loss | -5.64 | +| explained_variance | 0.845 | +| learning_rate | 4.17e-05 | +| loss | -0.0298 | +| n_updates | 83904 | +| policy_gradient_loss | -0.0202 | +| value_loss | 4.85e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1394 | +| iterations | 17023 | +| time_elapsed | 25004 | +| total_timesteps | 34863104 | +| train/ | | +| approx_kl | 0.016568948 | +| clip_fraction | 0.346 | +| clip_range | 0.0663 | +| entropy_loss | -5.33 | +| explained_variance | 0.724 | +| learning_rate | 4.17e-05 | +| loss | -0.0267 | +| n_updates | 83908 | +| policy_gradient_loss | -0.019 | +| value_loss | 6.38e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1394 | +| iterations | 17024 | +| time_elapsed | 25006 | +| total_timesteps | 34865152 | +| train/ | | +| approx_kl | 0.016460424 | +| clip_fraction | 0.334 | +| clip_range | 0.0663 | +| entropy_loss | -5.75 | +| explained_variance | 0.458 | +| learning_rate | 4.17e-05 | +| loss | -0.0308 | +| n_updates | 83912 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000183 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1394 | +| iterations | 17025 | +| time_elapsed | 25007 | +| total_timesteps | 34867200 | +| train/ | | +| approx_kl | 0.014159406 | +| clip_fraction | 0.321 | +| clip_range | 0.0663 | +| entropy_loss | -5.37 | +| explained_variance | 0.451 | +| learning_rate | 4.17e-05 | +| loss | -0.0262 | +| n_updates | 83916 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000164 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1394 | +| iterations | 17026 | +| time_elapsed | 25009 | +| total_timesteps | 34869248 | +| train/ | | +| approx_kl | 0.0155539755 | +| clip_fraction | 0.334 | +| clip_range | 0.0663 | +| entropy_loss | -5.79 | +| explained_variance | 0.261 | +| learning_rate | 4.17e-05 | +| loss | -0.0236 | +| n_updates | 83920 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.00034 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1394 | +| iterations | 17027 | +| time_elapsed | 25010 | +| total_timesteps | 34871296 | +| train/ | | +| approx_kl | 0.013639649 | +| clip_fraction | 0.363 | +| clip_range | 0.0663 | +| entropy_loss | -6.09 | +| explained_variance | -0.178 | +| learning_rate | 4.17e-05 | +| loss | -0.0268 | +| n_updates | 83924 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000113 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1394 | +| iterations | 17028 | +| time_elapsed | 25012 | +| total_timesteps | 34873344 | +| train/ | | +| approx_kl | 0.014378162 | +| clip_fraction | 0.359 | +| clip_range | 0.0663 | +| entropy_loss | -5.86 | +| explained_variance | 0.517 | +| learning_rate | 4.17e-05 | +| loss | -0.0334 | +| n_updates | 83928 | +| policy_gradient_loss | -0.02 | +| value_loss | 9.92e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1394 | +| iterations | 17029 | +| time_elapsed | 25013 | +| total_timesteps | 34875392 | +| train/ | | +| approx_kl | 0.015114358 | +| clip_fraction | 0.36 | +| clip_range | 0.0663 | +| entropy_loss | -6.11 | +| explained_variance | 0.426 | +| learning_rate | 4.17e-05 | +| loss | -0.0338 | +| n_updates | 83932 | +| policy_gradient_loss | -0.0199 | +| value_loss | 8.97e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1394 | +| iterations | 17030 | +| time_elapsed | 25015 | +| total_timesteps | 34877440 | +| train/ | | +| approx_kl | 0.01632072 | +| clip_fraction | 0.341 | +| clip_range | 0.0663 | +| entropy_loss | -5.89 | +| explained_variance | 0.588 | +| learning_rate | 4.17e-05 | +| loss | -0.0256 | +| n_updates | 83936 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000128 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1394 | +| iterations | 17031 | +| time_elapsed | 25016 | +| total_timesteps | 34879488 | +| train/ | | +| approx_kl | 0.010719897 | +| clip_fraction | 0.343 | +| clip_range | 0.0663 | +| entropy_loss | -5.51 | +| explained_variance | 0.383 | +| learning_rate | 4.17e-05 | +| loss | -0.0284 | +| n_updates | 83940 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000115 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1394 | +| iterations | 17032 | +| time_elapsed | 25018 | +| total_timesteps | 34881536 | +| train/ | | +| approx_kl | 0.012939695 | +| clip_fraction | 0.362 | +| clip_range | 0.0663 | +| entropy_loss | -6.25 | +| explained_variance | 0.353 | +| learning_rate | 4.17e-05 | +| loss | -0.0286 | +| n_updates | 83944 | +| policy_gradient_loss | -0.0195 | +| value_loss | 8.73e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1394 | +| iterations | 17033 | +| time_elapsed | 25019 | +| total_timesteps | 34883584 | +| train/ | | +| approx_kl | 0.00867906 | +| clip_fraction | 0.3 | +| clip_range | 0.0663 | +| entropy_loss | -6.31 | +| explained_variance | 0.35 | +| learning_rate | 4.17e-05 | +| loss | -0.0208 | +| n_updates | 83948 | +| policy_gradient_loss | -0.0148 | +| value_loss | 0.000189 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1394 | +| iterations | 17034 | +| time_elapsed | 25021 | +| total_timesteps | 34885632 | +| train/ | | +| approx_kl | 0.012899895 | +| clip_fraction | 0.305 | +| clip_range | 0.0663 | +| entropy_loss | -6.16 | +| explained_variance | 0.471 | +| learning_rate | 4.17e-05 | +| loss | -0.0269 | +| n_updates | 83952 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000126 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1394 | +| iterations | 17035 | +| time_elapsed | 25022 | +| total_timesteps | 34887680 | +| train/ | | +| approx_kl | 0.009649295 | +| clip_fraction | 0.324 | +| clip_range | 0.0663 | +| entropy_loss | -5.88 | +| explained_variance | 0.681 | +| learning_rate | 4.17e-05 | +| loss | -0.0279 | +| n_updates | 83956 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000144 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1394 | +| iterations | 17036 | +| time_elapsed | 25024 | +| total_timesteps | 34889728 | +| train/ | | +| approx_kl | 0.012079125 | +| clip_fraction | 0.312 | +| clip_range | 0.0663 | +| entropy_loss | -5.45 | +| explained_variance | 0.207 | +| learning_rate | 4.17e-05 | +| loss | -0.024 | +| n_updates | 83960 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000187 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1394 | +| iterations | 17037 | +| time_elapsed | 25025 | +| total_timesteps | 34891776 | +| train/ | | +| approx_kl | 0.01254449 | +| clip_fraction | 0.324 | +| clip_range | 0.0663 | +| entropy_loss | -5.19 | +| explained_variance | 0.537 | +| learning_rate | 4.17e-05 | +| loss | -0.0226 | +| n_updates | 83964 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000226 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1394 | +| iterations | 17038 | +| time_elapsed | 25027 | +| total_timesteps | 34893824 | +| train/ | | +| approx_kl | 0.012148298 | +| clip_fraction | 0.323 | +| clip_range | 0.0663 | +| entropy_loss | -5.88 | +| explained_variance | 0.323 | +| learning_rate | 4.17e-05 | +| loss | -0.0334 | +| n_updates | 83968 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000161 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1394 | +| iterations | 17039 | +| time_elapsed | 25028 | +| total_timesteps | 34895872 | +| train/ | | +| approx_kl | 0.011880778 | +| clip_fraction | 0.332 | +| clip_range | 0.0663 | +| entropy_loss | -6.17 | +| explained_variance | 0.374 | +| learning_rate | 4.17e-05 | +| loss | -0.0314 | +| n_updates | 83972 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000181 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1394 | +| iterations | 17040 | +| time_elapsed | 25030 | +| total_timesteps | 34897920 | +| train/ | | +| approx_kl | 0.012990325 | +| clip_fraction | 0.353 | +| clip_range | 0.0663 | +| entropy_loss | -5.89 | +| explained_variance | 0.404 | +| learning_rate | 4.17e-05 | +| loss | -0.0326 | +| n_updates | 83976 | +| policy_gradient_loss | -0.0197 | +| value_loss | 9.44e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1394 | +| iterations | 17041 | +| time_elapsed | 25031 | +| total_timesteps | 34899968 | +| train/ | | +| approx_kl | 0.013457637 | +| clip_fraction | 0.327 | +| clip_range | 0.0663 | +| entropy_loss | -5.86 | +| explained_variance | 0.442 | +| learning_rate | 4.17e-05 | +| loss | -0.0262 | +| n_updates | 83980 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000188 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1394 | +| iterations | 17042 | +| time_elapsed | 25033 | +| total_timesteps | 34902016 | +| train/ | | +| approx_kl | 0.013419073 | +| clip_fraction | 0.3 | +| clip_range | 0.0663 | +| entropy_loss | -6.02 | +| explained_variance | 0.232 | +| learning_rate | 4.17e-05 | +| loss | -0.0294 | +| n_updates | 83984 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000293 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1394 | +| iterations | 17043 | +| time_elapsed | 25034 | +| total_timesteps | 34904064 | +| train/ | | +| approx_kl | 0.0144295 | +| clip_fraction | 0.331 | +| clip_range | 0.0663 | +| entropy_loss | -5.66 | +| explained_variance | 0.535 | +| learning_rate | 4.17e-05 | +| loss | -0.0338 | +| n_updates | 83988 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000111 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1394 | +| iterations | 17044 | +| time_elapsed | 25036 | +| total_timesteps | 34906112 | +| train/ | | +| approx_kl | 0.015605143 | +| clip_fraction | 0.35 | +| clip_range | 0.0663 | +| entropy_loss | -5.84 | +| explained_variance | 0.29 | +| learning_rate | 4.17e-05 | +| loss | -0.0289 | +| n_updates | 83992 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000133 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1394 | +| iterations | 17045 | +| time_elapsed | 25037 | +| total_timesteps | 34908160 | +| train/ | | +| approx_kl | 0.013045653 | +| clip_fraction | 0.343 | +| clip_range | 0.0663 | +| entropy_loss | -6.21 | +| explained_variance | 0.66 | +| learning_rate | 4.17e-05 | +| loss | -0.0281 | +| n_updates | 83996 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000104 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1394 | +| iterations | 17046 | +| time_elapsed | 25039 | +| total_timesteps | 34910208 | +| train/ | | +| approx_kl | 0.012346377 | +| clip_fraction | 0.341 | +| clip_range | 0.0663 | +| entropy_loss | -5.95 | +| explained_variance | 0.13 | +| learning_rate | 4.17e-05 | +| loss | -0.0244 | +| n_updates | 84000 | +| policy_gradient_loss | -0.0166 | +| value_loss | 8.06e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1394 | +| iterations | 17047 | +| time_elapsed | 25040 | +| total_timesteps | 34912256 | +| train/ | | +| approx_kl | 0.011893204 | +| clip_fraction | 0.333 | +| clip_range | 0.0663 | +| entropy_loss | -6.2 | +| explained_variance | -0.13 | +| learning_rate | 4.17e-05 | +| loss | -0.0292 | +| n_updates | 84004 | +| policy_gradient_loss | -0.0179 | +| value_loss | 7.73e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1394 | +| iterations | 17048 | +| time_elapsed | 25042 | +| total_timesteps | 34914304 | +| train/ | | +| approx_kl | 0.016362194 | +| clip_fraction | 0.369 | +| clip_range | 0.0663 | +| entropy_loss | -6.16 | +| explained_variance | 0.517 | +| learning_rate | 4.17e-05 | +| loss | -0.0221 | +| n_updates | 84008 | +| policy_gradient_loss | -0.02 | +| value_loss | 6.15e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1394 | +| iterations | 17049 | +| time_elapsed | 25043 | +| total_timesteps | 34916352 | +| train/ | | +| approx_kl | 0.01420516 | +| clip_fraction | 0.339 | +| clip_range | 0.0663 | +| entropy_loss | -5.79 | +| explained_variance | 0.633 | +| learning_rate | 4.17e-05 | +| loss | -0.0244 | +| n_updates | 84012 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000133 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1394 | +| iterations | 17050 | +| time_elapsed | 25045 | +| total_timesteps | 34918400 | +| train/ | | +| approx_kl | 0.014244415 | +| clip_fraction | 0.312 | +| clip_range | 0.0663 | +| entropy_loss | -5.23 | +| explained_variance | 0.53 | +| learning_rate | 4.17e-05 | +| loss | -0.027 | +| n_updates | 84016 | +| policy_gradient_loss | -0.0148 | +| value_loss | 0.000189 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1394 | +| iterations | 17051 | +| time_elapsed | 25047 | +| total_timesteps | 34920448 | +| train/ | | +| approx_kl | 0.014778964 | +| clip_fraction | 0.347 | +| clip_range | 0.0663 | +| entropy_loss | -5.08 | +| explained_variance | 0.737 | +| learning_rate | 4.17e-05 | +| loss | -0.0297 | +| n_updates | 84020 | +| policy_gradient_loss | -0.0182 | +| value_loss | 8.79e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1394 | +| iterations | 17052 | +| time_elapsed | 25048 | +| total_timesteps | 34922496 | +| train/ | | +| approx_kl | 0.013697496 | +| clip_fraction | 0.329 | +| clip_range | 0.0663 | +| entropy_loss | -5.3 | +| explained_variance | 0.634 | +| learning_rate | 4.17e-05 | +| loss | -0.0281 | +| n_updates | 84024 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000125 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.315 | +| time/ | | +| fps | 1394 | +| iterations | 17053 | +| time_elapsed | 25050 | +| total_timesteps | 34924544 | +| train/ | | +| approx_kl | 0.013668995 | +| clip_fraction | 0.332 | +| clip_range | 0.0663 | +| entropy_loss | -5.42 | +| explained_variance | 0.636 | +| learning_rate | 4.17e-05 | +| loss | -0.0327 | +| n_updates | 84028 | +| policy_gradient_loss | -0.0185 | +| value_loss | 6.97e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1394 | +| iterations | 17054 | +| time_elapsed | 25051 | +| total_timesteps | 34926592 | +| train/ | | +| approx_kl | 0.013879502 | +| clip_fraction | 0.339 | +| clip_range | 0.0663 | +| entropy_loss | -6 | +| explained_variance | 0.383 | +| learning_rate | 4.17e-05 | +| loss | -0.0278 | +| n_updates | 84032 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000147 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1394 | +| iterations | 17055 | +| time_elapsed | 25053 | +| total_timesteps | 34928640 | +| train/ | | +| approx_kl | 0.014413616 | +| clip_fraction | 0.35 | +| clip_range | 0.0663 | +| entropy_loss | -5.54 | +| explained_variance | 0.602 | +| learning_rate | 4.17e-05 | +| loss | -0.0264 | +| n_updates | 84036 | +| policy_gradient_loss | -0.0193 | +| value_loss | 9.21e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1394 | +| iterations | 17056 | +| time_elapsed | 25054 | +| total_timesteps | 34930688 | +| train/ | | +| approx_kl | 0.012547333 | +| clip_fraction | 0.327 | +| clip_range | 0.0663 | +| entropy_loss | -5.78 | +| explained_variance | 0.543 | +| learning_rate | 4.17e-05 | +| loss | -0.0294 | +| n_updates | 84040 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000102 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1394 | +| iterations | 17057 | +| time_elapsed | 25056 | +| total_timesteps | 34932736 | +| train/ | | +| approx_kl | 0.015689723 | +| clip_fraction | 0.315 | +| clip_range | 0.0663 | +| entropy_loss | -6.11 | +| explained_variance | 0.241 | +| learning_rate | 4.17e-05 | +| loss | -0.0303 | +| n_updates | 84044 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000164 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.315 | +| time/ | | +| fps | 1394 | +| iterations | 17058 | +| time_elapsed | 25057 | +| total_timesteps | 34934784 | +| train/ | | +| approx_kl | 0.0136850905 | +| clip_fraction | 0.34 | +| clip_range | 0.0663 | +| entropy_loss | -6.45 | +| explained_variance | -0.104 | +| learning_rate | 4.17e-05 | +| loss | -0.0305 | +| n_updates | 84048 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000139 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1394 | +| iterations | 17059 | +| time_elapsed | 25059 | +| total_timesteps | 34936832 | +| train/ | | +| approx_kl | 0.011055563 | +| clip_fraction | 0.32 | +| clip_range | 0.0663 | +| entropy_loss | -6.38 | +| explained_variance | 0.373 | +| learning_rate | 4.17e-05 | +| loss | -0.0259 | +| n_updates | 84052 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000188 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1394 | +| iterations | 17060 | +| time_elapsed | 25060 | +| total_timesteps | 34938880 | +| train/ | | +| approx_kl | 0.011897238 | +| clip_fraction | 0.325 | +| clip_range | 0.0663 | +| entropy_loss | -6.18 | +| explained_variance | -0.0746 | +| learning_rate | 4.17e-05 | +| loss | -0.0254 | +| n_updates | 84056 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000153 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1394 | +| iterations | 17061 | +| time_elapsed | 25062 | +| total_timesteps | 34940928 | +| train/ | | +| approx_kl | 0.010296637 | +| clip_fraction | 0.318 | +| clip_range | 0.0663 | +| entropy_loss | -6.47 | +| explained_variance | 0.226 | +| learning_rate | 4.17e-05 | +| loss | -0.0247 | +| n_updates | 84060 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000185 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1394 | +| iterations | 17062 | +| time_elapsed | 25063 | +| total_timesteps | 34942976 | +| train/ | | +| approx_kl | 0.011198452 | +| clip_fraction | 0.306 | +| clip_range | 0.0663 | +| entropy_loss | -5.75 | +| explained_variance | 0.603 | +| learning_rate | 4.17e-05 | +| loss | -0.026 | +| n_updates | 84064 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000208 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1394 | +| iterations | 17063 | +| time_elapsed | 25065 | +| total_timesteps | 34945024 | +| train/ | | +| approx_kl | 0.010067752 | +| clip_fraction | 0.303 | +| clip_range | 0.0663 | +| entropy_loss | -5.23 | +| explained_variance | 0.576 | +| learning_rate | 4.17e-05 | +| loss | -0.0246 | +| n_updates | 84068 | +| policy_gradient_loss | -0.0136 | +| value_loss | 0.000152 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1394 | +| iterations | 17064 | +| time_elapsed | 25066 | +| total_timesteps | 34947072 | +| train/ | | +| approx_kl | 0.011628309 | +| clip_fraction | 0.348 | +| clip_range | 0.0663 | +| entropy_loss | -6.2 | +| explained_variance | 0.0714 | +| learning_rate | 4.17e-05 | +| loss | -0.0301 | +| n_updates | 84072 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1394 | +| iterations | 17065 | +| time_elapsed | 25068 | +| total_timesteps | 34949120 | +| train/ | | +| approx_kl | 0.010643465 | +| clip_fraction | 0.338 | +| clip_range | 0.0663 | +| entropy_loss | -6.24 | +| explained_variance | 0.42 | +| learning_rate | 4.17e-05 | +| loss | -0.0177 | +| n_updates | 84076 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000176 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1394 | +| iterations | 17066 | +| time_elapsed | 25070 | +| total_timesteps | 34951168 | +| train/ | | +| approx_kl | 0.013819968 | +| clip_fraction | 0.319 | +| clip_range | 0.0663 | +| entropy_loss | -5.96 | +| explained_variance | 0.321 | +| learning_rate | 4.17e-05 | +| loss | -0.0244 | +| n_updates | 84080 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000301 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1394 | +| iterations | 17067 | +| time_elapsed | 25071 | +| total_timesteps | 34953216 | +| train/ | | +| approx_kl | 0.011257391 | +| clip_fraction | 0.346 | +| clip_range | 0.0663 | +| entropy_loss | -5.9 | +| explained_variance | 0.541 | +| learning_rate | 4.17e-05 | +| loss | -0.0355 | +| n_updates | 84084 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000118 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1394 | +| iterations | 17068 | +| time_elapsed | 25073 | +| total_timesteps | 34955264 | +| train/ | | +| approx_kl | 0.010037303 | +| clip_fraction | 0.331 | +| clip_range | 0.0663 | +| entropy_loss | -6.34 | +| explained_variance | -0.0164 | +| learning_rate | 4.17e-05 | +| loss | -0.0274 | +| n_updates | 84088 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000124 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1394 | +| iterations | 17069 | +| time_elapsed | 25074 | +| total_timesteps | 34957312 | +| train/ | | +| approx_kl | 0.011369003 | +| clip_fraction | 0.31 | +| clip_range | 0.0663 | +| entropy_loss | -5.85 | +| explained_variance | 0.487 | +| learning_rate | 4.17e-05 | +| loss | -0.0286 | +| n_updates | 84092 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000237 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1394 | +| iterations | 17070 | +| time_elapsed | 25076 | +| total_timesteps | 34959360 | +| train/ | | +| approx_kl | 0.014824563 | +| clip_fraction | 0.345 | +| clip_range | 0.0663 | +| entropy_loss | -6.03 | +| explained_variance | -0.244 | +| learning_rate | 4.17e-05 | +| loss | -0.031 | +| n_updates | 84096 | +| policy_gradient_loss | -0.0202 | +| value_loss | 9.42e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1394 | +| iterations | 17071 | +| time_elapsed | 25077 | +| total_timesteps | 34961408 | +| train/ | | +| approx_kl | 0.010867089 | +| clip_fraction | 0.34 | +| clip_range | 0.0663 | +| entropy_loss | -6.71 | +| explained_variance | 0.419 | +| learning_rate | 4.17e-05 | +| loss | -0.0299 | +| n_updates | 84100 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000131 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.315 | +| time/ | | +| fps | 1394 | +| iterations | 17072 | +| time_elapsed | 25079 | +| total_timesteps | 34963456 | +| train/ | | +| approx_kl | 0.013367118 | +| clip_fraction | 0.348 | +| clip_range | 0.0663 | +| entropy_loss | -6.25 | +| explained_variance | 0.421 | +| learning_rate | 4.17e-05 | +| loss | -0.0289 | +| n_updates | 84104 | +| policy_gradient_loss | -0.0195 | +| value_loss | 8.15e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1394 | +| iterations | 17073 | +| time_elapsed | 25081 | +| total_timesteps | 34965504 | +| train/ | | +| approx_kl | 0.016503397 | +| clip_fraction | 0.339 | +| clip_range | 0.0663 | +| entropy_loss | -5.21 | +| explained_variance | 0.71 | +| learning_rate | 4.17e-05 | +| loss | -0.026 | +| n_updates | 84108 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000106 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 1394 | +| iterations | 17074 | +| time_elapsed | 25082 | +| total_timesteps | 34967552 | +| train/ | | +| approx_kl | 0.016181005 | +| clip_fraction | 0.35 | +| clip_range | 0.0663 | +| entropy_loss | -5.22 | +| explained_variance | 0.458 | +| learning_rate | 4.17e-05 | +| loss | -0.0301 | +| n_updates | 84112 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000205 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 1394 | +| iterations | 17075 | +| time_elapsed | 25084 | +| total_timesteps | 34969600 | +| train/ | | +| approx_kl | 0.014350972 | +| clip_fraction | 0.336 | +| clip_range | 0.0663 | +| entropy_loss | -5.44 | +| explained_variance | 0.551 | +| learning_rate | 4.17e-05 | +| loss | -0.0281 | +| n_updates | 84116 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000105 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 1394 | +| iterations | 17076 | +| time_elapsed | 25085 | +| total_timesteps | 34971648 | +| train/ | | +| approx_kl | 0.010837124 | +| clip_fraction | 0.312 | +| clip_range | 0.0663 | +| entropy_loss | -5.51 | +| explained_variance | 0.533 | +| learning_rate | 4.17e-05 | +| loss | -0.0328 | +| n_updates | 84120 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000142 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1394 | +| iterations | 17077 | +| time_elapsed | 25087 | +| total_timesteps | 34973696 | +| train/ | | +| approx_kl | 0.0153993685 | +| clip_fraction | 0.35 | +| clip_range | 0.0663 | +| entropy_loss | -6.16 | +| explained_variance | 0.128 | +| learning_rate | 4.17e-05 | +| loss | -0.0318 | +| n_updates | 84124 | +| policy_gradient_loss | -0.0199 | +| value_loss | 9.69e-05 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1394 | +| iterations | 17078 | +| time_elapsed | 25088 | +| total_timesteps | 34975744 | +| train/ | | +| approx_kl | 0.01352023 | +| clip_fraction | 0.305 | +| clip_range | 0.0663 | +| entropy_loss | -6.32 | +| explained_variance | 0.192 | +| learning_rate | 4.17e-05 | +| loss | -0.0252 | +| n_updates | 84128 | +| policy_gradient_loss | -0.0148 | +| value_loss | 0.000193 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1394 | +| iterations | 17079 | +| time_elapsed | 25090 | +| total_timesteps | 34977792 | +| train/ | | +| approx_kl | 0.015425161 | +| clip_fraction | 0.359 | +| clip_range | 0.0663 | +| entropy_loss | -6.58 | +| explained_variance | -0.229 | +| learning_rate | 4.17e-05 | +| loss | -0.0335 | +| n_updates | 84132 | +| policy_gradient_loss | -0.0205 | +| value_loss | 9.27e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1394 | +| iterations | 17080 | +| time_elapsed | 25091 | +| total_timesteps | 34979840 | +| train/ | | +| approx_kl | 0.013456415 | +| clip_fraction | 0.314 | +| clip_range | 0.0663 | +| entropy_loss | -6.19 | +| explained_variance | 0.458 | +| learning_rate | 4.17e-05 | +| loss | -0.0265 | +| n_updates | 84136 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000223 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.315 | +| time/ | | +| fps | 1394 | +| iterations | 17081 | +| time_elapsed | 25093 | +| total_timesteps | 34981888 | +| train/ | | +| approx_kl | 0.0104963565 | +| clip_fraction | 0.323 | +| clip_range | 0.0663 | +| entropy_loss | -5.91 | +| explained_variance | 0.331 | +| learning_rate | 4.17e-05 | +| loss | -0.0244 | +| n_updates | 84140 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000311 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.315 | +| time/ | | +| fps | 1394 | +| iterations | 17082 | +| time_elapsed | 25094 | +| total_timesteps | 34983936 | +| train/ | | +| approx_kl | 0.012104164 | +| clip_fraction | 0.321 | +| clip_range | 0.0663 | +| entropy_loss | -5.27 | +| explained_variance | 0.542 | +| learning_rate | 4.17e-05 | +| loss | -0.0268 | +| n_updates | 84144 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000158 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1394 | +| iterations | 17083 | +| time_elapsed | 25096 | +| total_timesteps | 34985984 | +| train/ | | +| approx_kl | 0.011997837 | +| clip_fraction | 0.34 | +| clip_range | 0.0663 | +| entropy_loss | -5.56 | +| explained_variance | 0.45 | +| learning_rate | 4.17e-05 | +| loss | -0.0324 | +| n_updates | 84148 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000143 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1394 | +| iterations | 17084 | +| time_elapsed | 25097 | +| total_timesteps | 34988032 | +| train/ | | +| approx_kl | 0.011286084 | +| clip_fraction | 0.333 | +| clip_range | 0.0663 | +| entropy_loss | -5.82 | +| explained_variance | 0.351 | +| learning_rate | 4.17e-05 | +| loss | -0.0186 | +| n_updates | 84152 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.000293 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1394 | +| iterations | 17085 | +| time_elapsed | 25099 | +| total_timesteps | 34990080 | +| train/ | | +| approx_kl | 0.011406094 | +| clip_fraction | 0.316 | +| clip_range | 0.0663 | +| entropy_loss | -6.34 | +| explained_variance | 0.262 | +| learning_rate | 4.17e-05 | +| loss | -0.0226 | +| n_updates | 84156 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000218 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1394 | +| iterations | 17086 | +| time_elapsed | 25100 | +| total_timesteps | 34992128 | +| train/ | | +| approx_kl | 0.010460113 | +| clip_fraction | 0.309 | +| clip_range | 0.0663 | +| entropy_loss | -5.61 | +| explained_variance | 0.466 | +| learning_rate | 4.17e-05 | +| loss | -0.0263 | +| n_updates | 84160 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.000241 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1394 | +| iterations | 17087 | +| time_elapsed | 25102 | +| total_timesteps | 34994176 | +| train/ | | +| approx_kl | 0.012858715 | +| clip_fraction | 0.336 | +| clip_range | 0.0663 | +| entropy_loss | -5.47 | +| explained_variance | 0.282 | +| learning_rate | 4.17e-05 | +| loss | -0.0276 | +| n_updates | 84164 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000188 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1394 | +| iterations | 17088 | +| time_elapsed | 25104 | +| total_timesteps | 34996224 | +| train/ | | +| approx_kl | 0.012944617 | +| clip_fraction | 0.334 | +| clip_range | 0.0663 | +| entropy_loss | -5.89 | +| explained_variance | 0.621 | +| learning_rate | 4.17e-05 | +| loss | -0.0304 | +| n_updates | 84168 | +| policy_gradient_loss | -0.0186 | +| value_loss | 9.91e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1394 | +| iterations | 17089 | +| time_elapsed | 25105 | +| total_timesteps | 34998272 | +| train/ | | +| approx_kl | 0.015065815 | +| clip_fraction | 0.352 | +| clip_range | 0.0663 | +| entropy_loss | -6.08 | +| explained_variance | 0.448 | +| learning_rate | 4.17e-05 | +| loss | -0.0289 | +| n_updates | 84172 | +| policy_gradient_loss | -0.018 | +| value_loss | 9.64e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1394 | +| iterations | 17090 | +| time_elapsed | 25107 | +| total_timesteps | 35000320 | +| train/ | | +| approx_kl | 0.011391915 | +| clip_fraction | 0.309 | +| clip_range | 0.0663 | +| entropy_loss | -5.5 | +| explained_variance | 0.504 | +| learning_rate | 4.17e-05 | +| loss | -0.0185 | +| n_updates | 84176 | +| policy_gradient_loss | -0.0144 | +| value_loss | 0.000228 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1394 | +| iterations | 17091 | +| time_elapsed | 25108 | +| total_timesteps | 35002368 | +| train/ | | +| approx_kl | 0.0142737515 | +| clip_fraction | 0.354 | +| clip_range | 0.0662 | +| entropy_loss | -6.05 | +| explained_variance | 0.0366 | +| learning_rate | 4.17e-05 | +| loss | -0.0336 | +| n_updates | 84180 | +| policy_gradient_loss | -0.0186 | +| value_loss | 9.99e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1394 | +| iterations | 17092 | +| time_elapsed | 25110 | +| total_timesteps | 35004416 | +| train/ | | +| approx_kl | 0.013458069 | +| clip_fraction | 0.351 | +| clip_range | 0.0662 | +| entropy_loss | -6.1 | +| explained_variance | 0.426 | +| learning_rate | 4.17e-05 | +| loss | -0.0292 | +| n_updates | 84184 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000101 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1394 | +| iterations | 17093 | +| time_elapsed | 25111 | +| total_timesteps | 35006464 | +| train/ | | +| approx_kl | 0.01262627 | +| clip_fraction | 0.346 | +| clip_range | 0.0662 | +| entropy_loss | -6.23 | +| explained_variance | 0.342 | +| learning_rate | 4.17e-05 | +| loss | -0.0297 | +| n_updates | 84188 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000141 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1394 | +| iterations | 17094 | +| time_elapsed | 25113 | +| total_timesteps | 35008512 | +| train/ | | +| approx_kl | 0.011121309 | +| clip_fraction | 0.316 | +| clip_range | 0.0662 | +| entropy_loss | -6.49 | +| explained_variance | 0.0726 | +| learning_rate | 4.17e-05 | +| loss | -0.0278 | +| n_updates | 84192 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000166 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1394 | +| iterations | 17095 | +| time_elapsed | 25115 | +| total_timesteps | 35010560 | +| train/ | | +| approx_kl | 0.008931838 | +| clip_fraction | 0.297 | +| clip_range | 0.0662 | +| entropy_loss | -6.61 | +| explained_variance | 0.164 | +| learning_rate | 4.17e-05 | +| loss | -0.0251 | +| n_updates | 84196 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.000337 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1394 | +| iterations | 17096 | +| time_elapsed | 25116 | +| total_timesteps | 35012608 | +| train/ | | +| approx_kl | 0.009244351 | +| clip_fraction | 0.312 | +| clip_range | 0.0662 | +| entropy_loss | -6.05 | +| explained_variance | 0.524 | +| learning_rate | 4.17e-05 | +| loss | -0.0242 | +| n_updates | 84200 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000203 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1394 | +| iterations | 17097 | +| time_elapsed | 25118 | +| total_timesteps | 35014656 | +| train/ | | +| approx_kl | 0.010573623 | +| clip_fraction | 0.302 | +| clip_range | 0.0662 | +| entropy_loss | -4.94 | +| explained_variance | 0.637 | +| learning_rate | 4.17e-05 | +| loss | -0.0221 | +| n_updates | 84204 | +| policy_gradient_loss | -0.013 | +| value_loss | 0.000217 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1393 | +| iterations | 17098 | +| time_elapsed | 25119 | +| total_timesteps | 35016704 | +| train/ | | +| approx_kl | 0.012398066 | +| clip_fraction | 0.325 | +| clip_range | 0.0662 | +| entropy_loss | -5.28 | +| explained_variance | 0.669 | +| learning_rate | 4.17e-05 | +| loss | -0.0293 | +| n_updates | 84208 | +| policy_gradient_loss | -0.0186 | +| value_loss | 7.33e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1393 | +| iterations | 17099 | +| time_elapsed | 25121 | +| total_timesteps | 35018752 | +| train/ | | +| approx_kl | 0.017593922 | +| clip_fraction | 0.356 | +| clip_range | 0.0662 | +| entropy_loss | -5.51 | +| explained_variance | 0.489 | +| learning_rate | 4.17e-05 | +| loss | -0.0288 | +| n_updates | 84212 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000108 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1393 | +| iterations | 17100 | +| time_elapsed | 25122 | +| total_timesteps | 35020800 | +| train/ | | +| approx_kl | 0.012481825 | +| clip_fraction | 0.313 | +| clip_range | 0.0662 | +| entropy_loss | -6.47 | +| explained_variance | -0.0466 | +| learning_rate | 4.17e-05 | +| loss | -0.0283 | +| n_updates | 84216 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000214 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1393 | +| iterations | 17101 | +| time_elapsed | 25124 | +| total_timesteps | 35022848 | +| train/ | | +| approx_kl | 0.015785428 | +| clip_fraction | 0.361 | +| clip_range | 0.0662 | +| entropy_loss | -6.28 | +| explained_variance | 0.362 | +| learning_rate | 4.17e-05 | +| loss | -0.0296 | +| n_updates | 84220 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000119 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1393 | +| iterations | 17102 | +| time_elapsed | 25125 | +| total_timesteps | 35024896 | +| train/ | | +| approx_kl | 0.011625525 | +| clip_fraction | 0.322 | +| clip_range | 0.0662 | +| entropy_loss | -6.21 | +| explained_variance | 0.351 | +| learning_rate | 4.17e-05 | +| loss | -0.0295 | +| n_updates | 84224 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.00014 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1393 | +| iterations | 17103 | +| time_elapsed | 25127 | +| total_timesteps | 35026944 | +| train/ | | +| approx_kl | 0.012478128 | +| clip_fraction | 0.332 | +| clip_range | 0.0662 | +| entropy_loss | -5.63 | +| explained_variance | 0.811 | +| learning_rate | 4.17e-05 | +| loss | -0.0212 | +| n_updates | 84228 | +| policy_gradient_loss | -0.0189 | +| value_loss | 5.12e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1393 | +| iterations | 17104 | +| time_elapsed | 25128 | +| total_timesteps | 35028992 | +| train/ | | +| approx_kl | 0.010551268 | +| clip_fraction | 0.335 | +| clip_range | 0.0662 | +| entropy_loss | -6.09 | +| explained_variance | 0.219 | +| learning_rate | 4.17e-05 | +| loss | -0.0281 | +| n_updates | 84232 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000261 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1393 | +| iterations | 17105 | +| time_elapsed | 25130 | +| total_timesteps | 35031040 | +| train/ | | +| approx_kl | 0.011867207 | +| clip_fraction | 0.344 | +| clip_range | 0.0662 | +| entropy_loss | -6.39 | +| explained_variance | 0.45 | +| learning_rate | 4.17e-05 | +| loss | -0.0302 | +| n_updates | 84236 | +| policy_gradient_loss | -0.0186 | +| value_loss | 9.24e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1393 | +| iterations | 17106 | +| time_elapsed | 25131 | +| total_timesteps | 35033088 | +| train/ | | +| approx_kl | 0.0120484745 | +| clip_fraction | 0.324 | +| clip_range | 0.0662 | +| entropy_loss | -5.59 | +| explained_variance | 0.435 | +| learning_rate | 4.17e-05 | +| loss | -0.027 | +| n_updates | 84240 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000186 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1393 | +| iterations | 17107 | +| time_elapsed | 25133 | +| total_timesteps | 35035136 | +| train/ | | +| approx_kl | 0.010462079 | +| clip_fraction | 0.318 | +| clip_range | 0.0662 | +| entropy_loss | -6 | +| explained_variance | 0.274 | +| learning_rate | 4.17e-05 | +| loss | -0.0272 | +| n_updates | 84244 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000174 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1393 | +| iterations | 17108 | +| time_elapsed | 25134 | +| total_timesteps | 35037184 | +| train/ | | +| approx_kl | 0.013829658 | +| clip_fraction | 0.322 | +| clip_range | 0.0662 | +| entropy_loss | -6.14 | +| explained_variance | 0.398 | +| learning_rate | 4.17e-05 | +| loss | -0.0285 | +| n_updates | 84248 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000105 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1393 | +| iterations | 17109 | +| time_elapsed | 25136 | +| total_timesteps | 35039232 | +| train/ | | +| approx_kl | 0.010026032 | +| clip_fraction | 0.329 | +| clip_range | 0.0662 | +| entropy_loss | -5.92 | +| explained_variance | 0.508 | +| learning_rate | 4.17e-05 | +| loss | -0.0241 | +| n_updates | 84252 | +| policy_gradient_loss | -0.0144 | +| value_loss | 0.000212 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1393 | +| iterations | 17110 | +| time_elapsed | 25137 | +| total_timesteps | 35041280 | +| train/ | | +| approx_kl | 0.012273128 | +| clip_fraction | 0.33 | +| clip_range | 0.0662 | +| entropy_loss | -6.14 | +| explained_variance | 0.479 | +| learning_rate | 4.17e-05 | +| loss | -0.0288 | +| n_updates | 84256 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000112 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1393 | +| iterations | 17111 | +| time_elapsed | 25139 | +| total_timesteps | 35043328 | +| train/ | | +| approx_kl | 0.01353493 | +| clip_fraction | 0.344 | +| clip_range | 0.0662 | +| entropy_loss | -5.69 | +| explained_variance | 0.56 | +| learning_rate | 4.17e-05 | +| loss | -0.0257 | +| n_updates | 84260 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000125 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1393 | +| iterations | 17112 | +| time_elapsed | 25140 | +| total_timesteps | 35045376 | +| train/ | | +| approx_kl | 0.014633194 | +| clip_fraction | 0.311 | +| clip_range | 0.0662 | +| entropy_loss | -6.15 | +| explained_variance | 0.218 | +| learning_rate | 4.17e-05 | +| loss | -0.029 | +| n_updates | 84264 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000183 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1393 | +| iterations | 17113 | +| time_elapsed | 25142 | +| total_timesteps | 35047424 | +| train/ | | +| approx_kl | 0.012457926 | +| clip_fraction | 0.338 | +| clip_range | 0.0662 | +| entropy_loss | -6.28 | +| explained_variance | -0.0609 | +| learning_rate | 4.17e-05 | +| loss | -0.0283 | +| n_updates | 84268 | +| policy_gradient_loss | -0.0184 | +| value_loss | 8.93e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1393 | +| iterations | 17114 | +| time_elapsed | 25143 | +| total_timesteps | 35049472 | +| train/ | | +| approx_kl | 0.0111793075 | +| clip_fraction | 0.326 | +| clip_range | 0.0662 | +| entropy_loss | -6.39 | +| explained_variance | 0.411 | +| learning_rate | 4.17e-05 | +| loss | -0.032 | +| n_updates | 84272 | +| policy_gradient_loss | -0.0173 | +| value_loss | 9.41e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1393 | +| iterations | 17115 | +| time_elapsed | 25145 | +| total_timesteps | 35051520 | +| train/ | | +| approx_kl | 0.013276772 | +| clip_fraction | 0.337 | +| clip_range | 0.0662 | +| entropy_loss | -5.73 | +| explained_variance | 0.689 | +| learning_rate | 4.17e-05 | +| loss | -0.0278 | +| n_updates | 84276 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000137 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1393 | +| iterations | 17116 | +| time_elapsed | 25146 | +| total_timesteps | 35053568 | +| train/ | | +| approx_kl | 0.011919488 | +| clip_fraction | 0.336 | +| clip_range | 0.0662 | +| entropy_loss | -6.39 | +| explained_variance | 0.0101 | +| learning_rate | 4.17e-05 | +| loss | -0.0328 | +| n_updates | 84280 | +| policy_gradient_loss | -0.0171 | +| value_loss | 6.96e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1393 | +| iterations | 17117 | +| time_elapsed | 25148 | +| total_timesteps | 35055616 | +| train/ | | +| approx_kl | 0.012307435 | +| clip_fraction | 0.319 | +| clip_range | 0.0662 | +| entropy_loss | -6.67 | +| explained_variance | -0.218 | +| learning_rate | 4.17e-05 | +| loss | -0.0292 | +| n_updates | 84284 | +| policy_gradient_loss | -0.0169 | +| value_loss | 9.52e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1393 | +| iterations | 17118 | +| time_elapsed | 25149 | +| total_timesteps | 35057664 | +| train/ | | +| approx_kl | 0.010198884 | +| clip_fraction | 0.303 | +| clip_range | 0.0662 | +| entropy_loss | -6.08 | +| explained_variance | 0.498 | +| learning_rate | 4.17e-05 | +| loss | -0.0233 | +| n_updates | 84288 | +| policy_gradient_loss | -0.0148 | +| value_loss | 0.000246 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1393 | +| iterations | 17119 | +| time_elapsed | 25151 | +| total_timesteps | 35059712 | +| train/ | | +| approx_kl | 0.009957992 | +| clip_fraction | 0.298 | +| clip_range | 0.0662 | +| entropy_loss | -5.18 | +| explained_variance | 0.47 | +| learning_rate | 4.17e-05 | +| loss | -0.0161 | +| n_updates | 84292 | +| policy_gradient_loss | -0.0136 | +| value_loss | 0.000252 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1393 | +| iterations | 17120 | +| time_elapsed | 25153 | +| total_timesteps | 35061760 | +| train/ | | +| approx_kl | 0.013870767 | +| clip_fraction | 0.337 | +| clip_range | 0.0662 | +| entropy_loss | -5.57 | +| explained_variance | 0.338 | +| learning_rate | 4.17e-05 | +| loss | -0.0338 | +| n_updates | 84296 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000174 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1393 | +| iterations | 17121 | +| time_elapsed | 25154 | +| total_timesteps | 35063808 | +| train/ | | +| approx_kl | 0.013639662 | +| clip_fraction | 0.365 | +| clip_range | 0.0662 | +| entropy_loss | -6.14 | +| explained_variance | 0.457 | +| learning_rate | 4.17e-05 | +| loss | -0.0347 | +| n_updates | 84300 | +| policy_gradient_loss | -0.0218 | +| value_loss | 7.93e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1393 | +| iterations | 17122 | +| time_elapsed | 25156 | +| total_timesteps | 35065856 | +| train/ | | +| approx_kl | 0.008990275 | +| clip_fraction | 0.303 | +| clip_range | 0.0662 | +| entropy_loss | -6.89 | +| explained_variance | 0.029 | +| learning_rate | 4.17e-05 | +| loss | -0.0266 | +| n_updates | 84304 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000144 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1393 | +| iterations | 17123 | +| time_elapsed | 25157 | +| total_timesteps | 35067904 | +| train/ | | +| approx_kl | 0.008696202 | +| clip_fraction | 0.283 | +| clip_range | 0.0662 | +| entropy_loss | -6.25 | +| explained_variance | 0.557 | +| learning_rate | 4.17e-05 | +| loss | -0.0229 | +| n_updates | 84308 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000134 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1393 | +| iterations | 17124 | +| time_elapsed | 25159 | +| total_timesteps | 35069952 | +| train/ | | +| approx_kl | 0.008328625 | +| clip_fraction | 0.293 | +| clip_range | 0.0662 | +| entropy_loss | -6.08 | +| explained_variance | 0.394 | +| learning_rate | 4.17e-05 | +| loss | -0.0241 | +| n_updates | 84312 | +| policy_gradient_loss | -0.0145 | +| value_loss | 0.000339 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1393 | +| iterations | 17125 | +| time_elapsed | 25160 | +| total_timesteps | 35072000 | +| train/ | | +| approx_kl | 0.010973728 | +| clip_fraction | 0.299 | +| clip_range | 0.0662 | +| entropy_loss | -5.89 | +| explained_variance | 0.355 | +| learning_rate | 4.17e-05 | +| loss | -0.0207 | +| n_updates | 84316 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000285 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1393 | +| iterations | 17126 | +| time_elapsed | 25162 | +| total_timesteps | 35074048 | +| train/ | | +| approx_kl | 0.014194534 | +| clip_fraction | 0.365 | +| clip_range | 0.0662 | +| entropy_loss | -5.28 | +| explained_variance | 0.61 | +| learning_rate | 4.17e-05 | +| loss | -0.0327 | +| n_updates | 84320 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000153 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1393 | +| iterations | 17127 | +| time_elapsed | 25163 | +| total_timesteps | 35076096 | +| train/ | | +| approx_kl | 0.015356443 | +| clip_fraction | 0.37 | +| clip_range | 0.0662 | +| entropy_loss | -5.89 | +| explained_variance | -0.227 | +| learning_rate | 4.17e-05 | +| loss | -0.0309 | +| n_updates | 84324 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000128 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1393 | +| iterations | 17128 | +| time_elapsed | 25165 | +| total_timesteps | 35078144 | +| train/ | | +| approx_kl | 0.013769366 | +| clip_fraction | 0.341 | +| clip_range | 0.0662 | +| entropy_loss | -6.12 | +| explained_variance | 0.218 | +| learning_rate | 4.17e-05 | +| loss | -0.0283 | +| n_updates | 84328 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.00021 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1393 | +| iterations | 17129 | +| time_elapsed | 25166 | +| total_timesteps | 35080192 | +| train/ | | +| approx_kl | 0.012607768 | +| clip_fraction | 0.344 | +| clip_range | 0.0662 | +| entropy_loss | -5.88 | +| explained_variance | 0.194 | +| learning_rate | 4.17e-05 | +| loss | -0.0286 | +| n_updates | 84332 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000168 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1393 | +| iterations | 17130 | +| time_elapsed | 25168 | +| total_timesteps | 35082240 | +| train/ | | +| approx_kl | 0.012117747 | +| clip_fraction | 0.34 | +| clip_range | 0.0662 | +| entropy_loss | -5.99 | +| explained_variance | 0.244 | +| learning_rate | 4.17e-05 | +| loss | -0.0248 | +| n_updates | 84336 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000182 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1393 | +| iterations | 17131 | +| time_elapsed | 25169 | +| total_timesteps | 35084288 | +| train/ | | +| approx_kl | 0.0133161275 | +| clip_fraction | 0.344 | +| clip_range | 0.0662 | +| entropy_loss | -5.78 | +| explained_variance | 0.725 | +| learning_rate | 4.17e-05 | +| loss | -0.0227 | +| n_updates | 84340 | +| policy_gradient_loss | -0.0187 | +| value_loss | 8.81e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1393 | +| iterations | 17132 | +| time_elapsed | 25171 | +| total_timesteps | 35086336 | +| train/ | | +| approx_kl | 0.013069082 | +| clip_fraction | 0.317 | +| clip_range | 0.0662 | +| entropy_loss | -5.8 | +| explained_variance | 0.254 | +| learning_rate | 4.17e-05 | +| loss | -0.0223 | +| n_updates | 84344 | +| policy_gradient_loss | -0.0141 | +| value_loss | 0.000314 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1393 | +| iterations | 17133 | +| time_elapsed | 25172 | +| total_timesteps | 35088384 | +| train/ | | +| approx_kl | 0.010483608 | +| clip_fraction | 0.319 | +| clip_range | 0.0662 | +| entropy_loss | -5.53 | +| explained_variance | 0.539 | +| learning_rate | 4.17e-05 | +| loss | -0.0292 | +| n_updates | 84348 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000216 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1393 | +| iterations | 17134 | +| time_elapsed | 25174 | +| total_timesteps | 35090432 | +| train/ | | +| approx_kl | 0.012684372 | +| clip_fraction | 0.326 | +| clip_range | 0.0662 | +| entropy_loss | -6.18 | +| explained_variance | 0.262 | +| learning_rate | 4.17e-05 | +| loss | -0.0272 | +| n_updates | 84352 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000162 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1393 | +| iterations | 17135 | +| time_elapsed | 25175 | +| total_timesteps | 35092480 | +| train/ | | +| approx_kl | 0.0120612085 | +| clip_fraction | 0.339 | +| clip_range | 0.0662 | +| entropy_loss | -6.1 | +| explained_variance | 0.464 | +| learning_rate | 4.17e-05 | +| loss | -0.0259 | +| n_updates | 84356 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.0002 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1393 | +| iterations | 17136 | +| time_elapsed | 25177 | +| total_timesteps | 35094528 | +| train/ | | +| approx_kl | 0.010856655 | +| clip_fraction | 0.294 | +| clip_range | 0.0662 | +| entropy_loss | -5.93 | +| explained_variance | 0.484 | +| learning_rate | 4.17e-05 | +| loss | -0.0264 | +| n_updates | 84360 | +| policy_gradient_loss | -0.0135 | +| value_loss | 0.000156 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1393 | +| iterations | 17137 | +| time_elapsed | 25178 | +| total_timesteps | 35096576 | +| train/ | | +| approx_kl | 0.010296505 | +| clip_fraction | 0.318 | +| clip_range | 0.0662 | +| entropy_loss | -5.76 | +| explained_variance | 0.342 | +| learning_rate | 4.17e-05 | +| loss | -0.0207 | +| n_updates | 84364 | +| policy_gradient_loss | -0.0134 | +| value_loss | 0.000432 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1393 | +| iterations | 17138 | +| time_elapsed | 25180 | +| total_timesteps | 35098624 | +| train/ | | +| approx_kl | 0.011979744 | +| clip_fraction | 0.356 | +| clip_range | 0.0662 | +| entropy_loss | -6.05 | +| explained_variance | 0.296 | +| learning_rate | 4.17e-05 | +| loss | -0.0329 | +| n_updates | 84368 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000137 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1393 | +| iterations | 17139 | +| time_elapsed | 25182 | +| total_timesteps | 35100672 | +| train/ | | +| approx_kl | 0.012616716 | +| clip_fraction | 0.33 | +| clip_range | 0.0662 | +| entropy_loss | -6.65 | +| explained_variance | -0.204 | +| learning_rate | 4.17e-05 | +| loss | -0.0307 | +| n_updates | 84372 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000133 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1393 | +| iterations | 17140 | +| time_elapsed | 25183 | +| total_timesteps | 35102720 | +| train/ | | +| approx_kl | 0.011769758 | +| clip_fraction | 0.281 | +| clip_range | 0.0662 | +| entropy_loss | -6.83 | +| explained_variance | 0.209 | +| learning_rate | 4.17e-05 | +| loss | -0.0168 | +| n_updates | 84376 | +| policy_gradient_loss | -0.0133 | +| value_loss | 0.000223 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1393 | +| iterations | 17141 | +| time_elapsed | 25185 | +| total_timesteps | 35104768 | +| train/ | | +| approx_kl | 0.016068036 | +| clip_fraction | 0.381 | +| clip_range | 0.0662 | +| entropy_loss | -6.22 | +| explained_variance | 0.294 | +| learning_rate | 4.17e-05 | +| loss | -0.027 | +| n_updates | 84380 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000117 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1393 | +| iterations | 17142 | +| time_elapsed | 25186 | +| total_timesteps | 35106816 | +| train/ | | +| approx_kl | 0.013069983 | +| clip_fraction | 0.342 | +| clip_range | 0.0662 | +| entropy_loss | -6.28 | +| explained_variance | 0.222 | +| learning_rate | 4.17e-05 | +| loss | -0.0311 | +| n_updates | 84384 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000219 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1393 | +| iterations | 17143 | +| time_elapsed | 25188 | +| total_timesteps | 35108864 | +| train/ | | +| approx_kl | 0.01600211 | +| clip_fraction | 0.296 | +| clip_range | 0.0662 | +| entropy_loss | -5.35 | +| explained_variance | 0.441 | +| learning_rate | 4.17e-05 | +| loss | -0.0232 | +| n_updates | 84388 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000237 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1393 | +| iterations | 17144 | +| time_elapsed | 25189 | +| total_timesteps | 35110912 | +| train/ | | +| approx_kl | 0.013020517 | +| clip_fraction | 0.35 | +| clip_range | 0.0662 | +| entropy_loss | -5.11 | +| explained_variance | 0.771 | +| learning_rate | 4.17e-05 | +| loss | -0.031 | +| n_updates | 84392 | +| policy_gradient_loss | -0.0197 | +| value_loss | 9.09e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1393 | +| iterations | 17145 | +| time_elapsed | 25191 | +| total_timesteps | 35112960 | +| train/ | | +| approx_kl | 0.014700996 | +| clip_fraction | 0.379 | +| clip_range | 0.0662 | +| entropy_loss | -5.81 | +| explained_variance | 0.0867 | +| learning_rate | 4.17e-05 | +| loss | -0.029 | +| n_updates | 84396 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000171 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1393 | +| iterations | 17146 | +| time_elapsed | 25192 | +| total_timesteps | 35115008 | +| train/ | | +| approx_kl | 0.014000661 | +| clip_fraction | 0.36 | +| clip_range | 0.0662 | +| entropy_loss | -6.19 | +| explained_variance | 0.0289 | +| learning_rate | 4.17e-05 | +| loss | -0.028 | +| n_updates | 84400 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000155 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1393 | +| iterations | 17147 | +| time_elapsed | 25194 | +| total_timesteps | 35117056 | +| train/ | | +| approx_kl | 0.013364237 | +| clip_fraction | 0.335 | +| clip_range | 0.0662 | +| entropy_loss | -5.86 | +| explained_variance | 0.475 | +| learning_rate | 4.17e-05 | +| loss | -0.0291 | +| n_updates | 84404 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000167 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1393 | +| iterations | 17148 | +| time_elapsed | 25195 | +| total_timesteps | 35119104 | +| train/ | | +| approx_kl | 0.015342666 | +| clip_fraction | 0.331 | +| clip_range | 0.0662 | +| entropy_loss | -6.25 | +| explained_variance | 0.32 | +| learning_rate | 4.17e-05 | +| loss | -0.027 | +| n_updates | 84408 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1393 | +| iterations | 17149 | +| time_elapsed | 25197 | +| total_timesteps | 35121152 | +| train/ | | +| approx_kl | 0.016386911 | +| clip_fraction | 0.341 | +| clip_range | 0.0662 | +| entropy_loss | -6.39 | +| explained_variance | 0.344 | +| learning_rate | 4.17e-05 | +| loss | -0.0249 | +| n_updates | 84412 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000144 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1393 | +| iterations | 17150 | +| time_elapsed | 25198 | +| total_timesteps | 35123200 | +| train/ | | +| approx_kl | 0.017200582 | +| clip_fraction | 0.341 | +| clip_range | 0.0662 | +| entropy_loss | -6.24 | +| explained_variance | 0.62 | +| learning_rate | 4.17e-05 | +| loss | -0.0319 | +| n_updates | 84416 | +| policy_gradient_loss | -0.0198 | +| value_loss | 6.15e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1393 | +| iterations | 17151 | +| time_elapsed | 25200 | +| total_timesteps | 35125248 | +| train/ | | +| approx_kl | 0.014416701 | +| clip_fraction | 0.327 | +| clip_range | 0.0662 | +| entropy_loss | -6.07 | +| explained_variance | 0.416 | +| learning_rate | 4.17e-05 | +| loss | -0.0273 | +| n_updates | 84420 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000147 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1393 | +| iterations | 17152 | +| time_elapsed | 25201 | +| total_timesteps | 35127296 | +| train/ | | +| approx_kl | 0.012421722 | +| clip_fraction | 0.303 | +| clip_range | 0.0662 | +| entropy_loss | -5.95 | +| explained_variance | 0.448 | +| learning_rate | 4.17e-05 | +| loss | -0.0249 | +| n_updates | 84424 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000209 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1393 | +| iterations | 17153 | +| time_elapsed | 25203 | +| total_timesteps | 35129344 | +| train/ | | +| approx_kl | 0.013514198 | +| clip_fraction | 0.345 | +| clip_range | 0.0662 | +| entropy_loss | -5.69 | +| explained_variance | 0.539 | +| learning_rate | 4.17e-05 | +| loss | -0.0235 | +| n_updates | 84428 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000119 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1393 | +| iterations | 17154 | +| time_elapsed | 25204 | +| total_timesteps | 35131392 | +| train/ | | +| approx_kl | 0.014809573 | +| clip_fraction | 0.349 | +| clip_range | 0.0662 | +| entropy_loss | -5.95 | +| explained_variance | -0.0116 | +| learning_rate | 4.17e-05 | +| loss | -0.0299 | +| n_updates | 84432 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000168 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1393 | +| iterations | 17155 | +| time_elapsed | 25206 | +| total_timesteps | 35133440 | +| train/ | | +| approx_kl | 0.013624414 | +| clip_fraction | 0.366 | +| clip_range | 0.0662 | +| entropy_loss | -5.72 | +| explained_variance | 0.506 | +| learning_rate | 4.17e-05 | +| loss | -0.0263 | +| n_updates | 84436 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000153 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1393 | +| iterations | 17156 | +| time_elapsed | 25207 | +| total_timesteps | 35135488 | +| train/ | | +| approx_kl | 0.012926208 | +| clip_fraction | 0.326 | +| clip_range | 0.0662 | +| entropy_loss | -5.39 | +| explained_variance | 0.588 | +| learning_rate | 4.17e-05 | +| loss | -0.0246 | +| n_updates | 84440 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000203 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1393 | +| iterations | 17157 | +| time_elapsed | 25209 | +| total_timesteps | 35137536 | +| train/ | | +| approx_kl | 0.013057297 | +| clip_fraction | 0.35 | +| clip_range | 0.0662 | +| entropy_loss | -5.92 | +| explained_variance | 0.508 | +| learning_rate | 4.17e-05 | +| loss | -0.0321 | +| n_updates | 84444 | +| policy_gradient_loss | -0.0208 | +| value_loss | 8.28e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1393 | +| iterations | 17158 | +| time_elapsed | 25210 | +| total_timesteps | 35139584 | +| train/ | | +| approx_kl | 0.013670914 | +| clip_fraction | 0.356 | +| clip_range | 0.0662 | +| entropy_loss | -6.03 | +| explained_variance | 0.308 | +| learning_rate | 4.17e-05 | +| loss | -0.029 | +| n_updates | 84448 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000139 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1393 | +| iterations | 17159 | +| time_elapsed | 25212 | +| total_timesteps | 35141632 | +| train/ | | +| approx_kl | 0.012824563 | +| clip_fraction | 0.319 | +| clip_range | 0.0662 | +| entropy_loss | -6.06 | +| explained_variance | 0.509 | +| learning_rate | 4.17e-05 | +| loss | -0.0293 | +| n_updates | 84452 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000148 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1393 | +| iterations | 17160 | +| time_elapsed | 25213 | +| total_timesteps | 35143680 | +| train/ | | +| approx_kl | 0.0142516745 | +| clip_fraction | 0.324 | +| clip_range | 0.0662 | +| entropy_loss | -5.89 | +| explained_variance | 0.616 | +| learning_rate | 4.17e-05 | +| loss | -0.0244 | +| n_updates | 84456 | +| policy_gradient_loss | -0.0182 | +| value_loss | 8.58e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1393 | +| iterations | 17161 | +| time_elapsed | 25215 | +| total_timesteps | 35145728 | +| train/ | | +| approx_kl | 0.012760228 | +| clip_fraction | 0.364 | +| clip_range | 0.0662 | +| entropy_loss | -6.39 | +| explained_variance | 0.367 | +| learning_rate | 4.17e-05 | +| loss | -0.0248 | +| n_updates | 84460 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000102 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1393 | +| iterations | 17162 | +| time_elapsed | 25216 | +| total_timesteps | 35147776 | +| train/ | | +| approx_kl | 0.013634544 | +| clip_fraction | 0.326 | +| clip_range | 0.0662 | +| entropy_loss | -6.14 | +| explained_variance | 0.447 | +| learning_rate | 4.17e-05 | +| loss | -0.0307 | +| n_updates | 84464 | +| policy_gradient_loss | -0.0169 | +| value_loss | 9.54e-05 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1393 | +| iterations | 17163 | +| time_elapsed | 25218 | +| total_timesteps | 35149824 | +| train/ | | +| approx_kl | 0.0122999 | +| clip_fraction | 0.337 | +| clip_range | 0.0662 | +| entropy_loss | -5.69 | +| explained_variance | 0.542 | +| learning_rate | 4.17e-05 | +| loss | -0.0279 | +| n_updates | 84468 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000132 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1393 | +| iterations | 17164 | +| time_elapsed | 25219 | +| total_timesteps | 35151872 | +| train/ | | +| approx_kl | 0.011816556 | +| clip_fraction | 0.314 | +| clip_range | 0.0662 | +| entropy_loss | -5.76 | +| explained_variance | 0.517 | +| learning_rate | 4.17e-05 | +| loss | -0.0235 | +| n_updates | 84472 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000149 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1393 | +| iterations | 17165 | +| time_elapsed | 25221 | +| total_timesteps | 35153920 | +| train/ | | +| approx_kl | 0.0115665905 | +| clip_fraction | 0.3 | +| clip_range | 0.0662 | +| entropy_loss | -5.55 | +| explained_variance | 0.745 | +| learning_rate | 4.17e-05 | +| loss | -0.0206 | +| n_updates | 84476 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000107 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1393 | +| iterations | 17166 | +| time_elapsed | 25222 | +| total_timesteps | 35155968 | +| train/ | | +| approx_kl | 0.012968071 | +| clip_fraction | 0.346 | +| clip_range | 0.0662 | +| entropy_loss | -5.68 | +| explained_variance | -0.173 | +| learning_rate | 4.17e-05 | +| loss | -0.0302 | +| n_updates | 84480 | +| policy_gradient_loss | -0.0188 | +| value_loss | 8.89e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1393 | +| iterations | 17167 | +| time_elapsed | 25224 | +| total_timesteps | 35158016 | +| train/ | | +| approx_kl | 0.012090245 | +| clip_fraction | 0.348 | +| clip_range | 0.0662 | +| entropy_loss | -6.18 | +| explained_variance | 0.228 | +| learning_rate | 4.17e-05 | +| loss | -0.0216 | +| n_updates | 84484 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000303 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1393 | +| iterations | 17168 | +| time_elapsed | 25225 | +| total_timesteps | 35160064 | +| train/ | | +| approx_kl | 0.01095096 | +| clip_fraction | 0.288 | +| clip_range | 0.0662 | +| entropy_loss | -5.66 | +| explained_variance | 0.5 | +| learning_rate | 4.16e-05 | +| loss | -0.0239 | +| n_updates | 84488 | +| policy_gradient_loss | -0.0138 | +| value_loss | 0.000274 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1393 | +| iterations | 17169 | +| time_elapsed | 25227 | +| total_timesteps | 35162112 | +| train/ | | +| approx_kl | 0.01151811 | +| clip_fraction | 0.306 | +| clip_range | 0.0662 | +| entropy_loss | -6.12 | +| explained_variance | -0.0718 | +| learning_rate | 4.16e-05 | +| loss | -0.0304 | +| n_updates | 84492 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000123 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1393 | +| iterations | 17170 | +| time_elapsed | 25229 | +| total_timesteps | 35164160 | +| train/ | | +| approx_kl | 0.014124674 | +| clip_fraction | 0.336 | +| clip_range | 0.0662 | +| entropy_loss | -5.77 | +| explained_variance | 0.466 | +| learning_rate | 4.16e-05 | +| loss | -0.0311 | +| n_updates | 84496 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000214 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1393 | +| iterations | 17171 | +| time_elapsed | 25230 | +| total_timesteps | 35166208 | +| train/ | | +| approx_kl | 0.013496258 | +| clip_fraction | 0.331 | +| clip_range | 0.0662 | +| entropy_loss | -5.84 | +| explained_variance | 0.106 | +| learning_rate | 4.16e-05 | +| loss | -0.0294 | +| n_updates | 84500 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000175 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1393 | +| iterations | 17172 | +| time_elapsed | 25232 | +| total_timesteps | 35168256 | +| train/ | | +| approx_kl | 0.012726221 | +| clip_fraction | 0.341 | +| clip_range | 0.0662 | +| entropy_loss | -6.06 | +| explained_variance | 0.328 | +| learning_rate | 4.16e-05 | +| loss | -0.0242 | +| n_updates | 84504 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000169 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1393 | +| iterations | 17173 | +| time_elapsed | 25233 | +| total_timesteps | 35170304 | +| train/ | | +| approx_kl | 0.013098003 | +| clip_fraction | 0.334 | +| clip_range | 0.0662 | +| entropy_loss | -6.08 | +| explained_variance | 0.297 | +| learning_rate | 4.16e-05 | +| loss | -0.0274 | +| n_updates | 84508 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000306 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1393 | +| iterations | 17174 | +| time_elapsed | 25235 | +| total_timesteps | 35172352 | +| train/ | | +| approx_kl | 0.015664939 | +| clip_fraction | 0.331 | +| clip_range | 0.0662 | +| entropy_loss | -5.79 | +| explained_variance | 0.475 | +| learning_rate | 4.16e-05 | +| loss | -0.0264 | +| n_updates | 84512 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000116 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1393 | +| iterations | 17175 | +| time_elapsed | 25236 | +| total_timesteps | 35174400 | +| train/ | | +| approx_kl | 0.012787558 | +| clip_fraction | 0.349 | +| clip_range | 0.0662 | +| entropy_loss | -6.41 | +| explained_variance | 0.125 | +| learning_rate | 4.16e-05 | +| loss | -0.0306 | +| n_updates | 84516 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000164 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1393 | +| iterations | 17176 | +| time_elapsed | 25238 | +| total_timesteps | 35176448 | +| train/ | | +| approx_kl | 0.011064188 | +| clip_fraction | 0.319 | +| clip_range | 0.0662 | +| entropy_loss | -6.1 | +| explained_variance | 0.405 | +| learning_rate | 4.16e-05 | +| loss | -0.0254 | +| n_updates | 84520 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000191 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1393 | +| iterations | 17177 | +| time_elapsed | 25239 | +| total_timesteps | 35178496 | +| train/ | | +| approx_kl | 0.011469478 | +| clip_fraction | 0.324 | +| clip_range | 0.0662 | +| entropy_loss | -5.19 | +| explained_variance | 0.596 | +| learning_rate | 4.16e-05 | +| loss | -0.022 | +| n_updates | 84524 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000158 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1393 | +| iterations | 17178 | +| time_elapsed | 25241 | +| total_timesteps | 35180544 | +| train/ | | +| approx_kl | 0.012238145 | +| clip_fraction | 0.331 | +| clip_range | 0.0662 | +| entropy_loss | -5.78 | +| explained_variance | 0.57 | +| learning_rate | 4.16e-05 | +| loss | -0.0292 | +| n_updates | 84528 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000117 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1393 | +| iterations | 17179 | +| time_elapsed | 25242 | +| total_timesteps | 35182592 | +| train/ | | +| approx_kl | 0.012668634 | +| clip_fraction | 0.351 | +| clip_range | 0.0662 | +| entropy_loss | -6.51 | +| explained_variance | 0.21 | +| learning_rate | 4.16e-05 | +| loss | -0.0302 | +| n_updates | 84532 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000104 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1393 | +| iterations | 17180 | +| time_elapsed | 25244 | +| total_timesteps | 35184640 | +| train/ | | +| approx_kl | 0.0125328675 | +| clip_fraction | 0.345 | +| clip_range | 0.0662 | +| entropy_loss | -6.49 | +| explained_variance | 0.086 | +| learning_rate | 4.16e-05 | +| loss | -0.0283 | +| n_updates | 84536 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000186 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1393 | +| iterations | 17181 | +| time_elapsed | 25245 | +| total_timesteps | 35186688 | +| train/ | | +| approx_kl | 0.015547644 | +| clip_fraction | 0.338 | +| clip_range | 0.0662 | +| entropy_loss | -6.01 | +| explained_variance | 0.584 | +| learning_rate | 4.16e-05 | +| loss | -0.0278 | +| n_updates | 84540 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000115 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1393 | +| iterations | 17182 | +| time_elapsed | 25247 | +| total_timesteps | 35188736 | +| train/ | | +| approx_kl | 0.0121147465 | +| clip_fraction | 0.286 | +| clip_range | 0.0662 | +| entropy_loss | -6.21 | +| explained_variance | 0.384 | +| learning_rate | 4.16e-05 | +| loss | -0.0228 | +| n_updates | 84544 | +| policy_gradient_loss | -0.0147 | +| value_loss | 0.000185 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1393 | +| iterations | 17183 | +| time_elapsed | 25249 | +| total_timesteps | 35190784 | +| train/ | | +| approx_kl | 0.009694491 | +| clip_fraction | 0.301 | +| clip_range | 0.0662 | +| entropy_loss | -6.31 | +| explained_variance | 0.299 | +| learning_rate | 4.16e-05 | +| loss | -0.0317 | +| n_updates | 84548 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000341 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1393 | +| iterations | 17184 | +| time_elapsed | 25250 | +| total_timesteps | 35192832 | +| train/ | | +| approx_kl | 0.013927652 | +| clip_fraction | 0.355 | +| clip_range | 0.0662 | +| entropy_loss | -6.61 | +| explained_variance | -0.325 | +| learning_rate | 4.16e-05 | +| loss | -0.0317 | +| n_updates | 84552 | +| policy_gradient_loss | -0.0217 | +| value_loss | 7.37e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1393 | +| iterations | 17185 | +| time_elapsed | 25252 | +| total_timesteps | 35194880 | +| train/ | | +| approx_kl | 0.008985754 | +| clip_fraction | 0.307 | +| clip_range | 0.0662 | +| entropy_loss | -5.92 | +| explained_variance | 0.484 | +| learning_rate | 4.16e-05 | +| loss | -0.0251 | +| n_updates | 84556 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.00023 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1393 | +| iterations | 17186 | +| time_elapsed | 25253 | +| total_timesteps | 35196928 | +| train/ | | +| approx_kl | 0.012537271 | +| clip_fraction | 0.335 | +| clip_range | 0.0662 | +| entropy_loss | -5.75 | +| explained_variance | 0.0558 | +| learning_rate | 4.16e-05 | +| loss | -0.0319 | +| n_updates | 84560 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000145 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1393 | +| iterations | 17187 | +| time_elapsed | 25255 | +| total_timesteps | 35198976 | +| train/ | | +| approx_kl | 0.014141791 | +| clip_fraction | 0.322 | +| clip_range | 0.0662 | +| entropy_loss | -5.5 | +| explained_variance | 0.572 | +| learning_rate | 4.16e-05 | +| loss | -0.024 | +| n_updates | 84564 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000151 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1393 | +| iterations | 17188 | +| time_elapsed | 25256 | +| total_timesteps | 35201024 | +| train/ | | +| approx_kl | 0.013255371 | +| clip_fraction | 0.362 | +| clip_range | 0.0662 | +| entropy_loss | -5.65 | +| explained_variance | 0.595 | +| learning_rate | 4.16e-05 | +| loss | -0.0346 | +| n_updates | 84568 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.00011 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1393 | +| iterations | 17189 | +| time_elapsed | 25258 | +| total_timesteps | 35203072 | +| train/ | | +| approx_kl | 0.010486381 | +| clip_fraction | 0.325 | +| clip_range | 0.0662 | +| entropy_loss | -6.81 | +| explained_variance | 0.0218 | +| learning_rate | 4.16e-05 | +| loss | -0.0353 | +| n_updates | 84572 | +| policy_gradient_loss | -0.0184 | +| value_loss | 9.38e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1393 | +| iterations | 17190 | +| time_elapsed | 25259 | +| total_timesteps | 35205120 | +| train/ | | +| approx_kl | 0.012523111 | +| clip_fraction | 0.333 | +| clip_range | 0.0662 | +| entropy_loss | -6.68 | +| explained_variance | 0.182 | +| learning_rate | 4.16e-05 | +| loss | -0.0246 | +| n_updates | 84576 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000258 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1393 | +| iterations | 17191 | +| time_elapsed | 25261 | +| total_timesteps | 35207168 | +| train/ | | +| approx_kl | 0.013025124 | +| clip_fraction | 0.363 | +| clip_range | 0.0662 | +| entropy_loss | -5.93 | +| explained_variance | 0.431 | +| learning_rate | 4.16e-05 | +| loss | -0.0305 | +| n_updates | 84580 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000106 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1393 | +| iterations | 17192 | +| time_elapsed | 25262 | +| total_timesteps | 35209216 | +| train/ | | +| approx_kl | 0.012674646 | +| clip_fraction | 0.31 | +| clip_range | 0.0662 | +| entropy_loss | -6.45 | +| explained_variance | 0.284 | +| learning_rate | 4.16e-05 | +| loss | -0.0295 | +| n_updates | 84584 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000192 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1393 | +| iterations | 17193 | +| time_elapsed | 25264 | +| total_timesteps | 35211264 | +| train/ | | +| approx_kl | 0.01038735 | +| clip_fraction | 0.297 | +| clip_range | 0.0662 | +| entropy_loss | -6.48 | +| explained_variance | 0.251 | +| learning_rate | 4.16e-05 | +| loss | -0.0308 | +| n_updates | 84588 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000169 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1393 | +| iterations | 17194 | +| time_elapsed | 25265 | +| total_timesteps | 35213312 | +| train/ | | +| approx_kl | 0.010782366 | +| clip_fraction | 0.317 | +| clip_range | 0.0662 | +| entropy_loss | -6.66 | +| explained_variance | -0.123 | +| learning_rate | 4.16e-05 | +| loss | -0.0266 | +| n_updates | 84592 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000112 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1393 | +| iterations | 17195 | +| time_elapsed | 25267 | +| total_timesteps | 35215360 | +| train/ | | +| approx_kl | 0.0096926745 | +| clip_fraction | 0.329 | +| clip_range | 0.0662 | +| entropy_loss | -6.33 | +| explained_variance | 0.355 | +| learning_rate | 4.16e-05 | +| loss | -0.0274 | +| n_updates | 84596 | +| policy_gradient_loss | -0.0146 | +| value_loss | 0.000251 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1393 | +| iterations | 17196 | +| time_elapsed | 25268 | +| total_timesteps | 35217408 | +| train/ | | +| approx_kl | 0.018986683 | +| clip_fraction | 0.337 | +| clip_range | 0.0662 | +| entropy_loss | -5.94 | +| explained_variance | 0.614 | +| learning_rate | 4.16e-05 | +| loss | -0.0289 | +| n_updates | 84600 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000124 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1393 | +| iterations | 17197 | +| time_elapsed | 25270 | +| total_timesteps | 35219456 | +| train/ | | +| approx_kl | 0.011804804 | +| clip_fraction | 0.326 | +| clip_range | 0.0662 | +| entropy_loss | -5.42 | +| explained_variance | 0.364 | +| learning_rate | 4.16e-05 | +| loss | -0.0268 | +| n_updates | 84604 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000196 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1393 | +| iterations | 17198 | +| time_elapsed | 25271 | +| total_timesteps | 35221504 | +| train/ | | +| approx_kl | 0.012554146 | +| clip_fraction | 0.337 | +| clip_range | 0.0662 | +| entropy_loss | -5.5 | +| explained_variance | 0.562 | +| learning_rate | 4.16e-05 | +| loss | -0.023 | +| n_updates | 84608 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000211 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1393 | +| iterations | 17199 | +| time_elapsed | 25273 | +| total_timesteps | 35223552 | +| train/ | | +| approx_kl | 0.010959428 | +| clip_fraction | 0.329 | +| clip_range | 0.0662 | +| entropy_loss | -5.98 | +| explained_variance | 0.344 | +| learning_rate | 4.16e-05 | +| loss | -0.0318 | +| n_updates | 84612 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000195 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1393 | +| iterations | 17200 | +| time_elapsed | 25274 | +| total_timesteps | 35225600 | +| train/ | | +| approx_kl | 0.0128383655 | +| clip_fraction | 0.332 | +| clip_range | 0.0662 | +| entropy_loss | -5.91 | +| explained_variance | 0.613 | +| learning_rate | 4.16e-05 | +| loss | -0.0332 | +| n_updates | 84616 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000136 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1393 | +| iterations | 17201 | +| time_elapsed | 25276 | +| total_timesteps | 35227648 | +| train/ | | +| approx_kl | 0.015296545 | +| clip_fraction | 0.351 | +| clip_range | 0.0662 | +| entropy_loss | -6.2 | +| explained_variance | -0.0722 | +| learning_rate | 4.16e-05 | +| loss | -0.035 | +| n_updates | 84620 | +| policy_gradient_loss | -0.0204 | +| value_loss | 8.69e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1393 | +| iterations | 17202 | +| time_elapsed | 25278 | +| total_timesteps | 35229696 | +| train/ | | +| approx_kl | 0.013768008 | +| clip_fraction | 0.322 | +| clip_range | 0.0662 | +| entropy_loss | -6.11 | +| explained_variance | 0.291 | +| learning_rate | 4.16e-05 | +| loss | -0.0297 | +| n_updates | 84624 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000164 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1393 | +| iterations | 17203 | +| time_elapsed | 25279 | +| total_timesteps | 35231744 | +| train/ | | +| approx_kl | 0.0127184605 | +| clip_fraction | 0.339 | +| clip_range | 0.0662 | +| entropy_loss | -6.48 | +| explained_variance | 0.0227 | +| learning_rate | 4.16e-05 | +| loss | -0.027 | +| n_updates | 84628 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000138 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1393 | +| iterations | 17204 | +| time_elapsed | 25281 | +| total_timesteps | 35233792 | +| train/ | | +| approx_kl | 0.014491368 | +| clip_fraction | 0.332 | +| clip_range | 0.0662 | +| entropy_loss | -5.83 | +| explained_variance | 0.445 | +| learning_rate | 4.16e-05 | +| loss | -0.029 | +| n_updates | 84632 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000123 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1393 | +| iterations | 17205 | +| time_elapsed | 25282 | +| total_timesteps | 35235840 | +| train/ | | +| approx_kl | 0.013049694 | +| clip_fraction | 0.333 | +| clip_range | 0.0662 | +| entropy_loss | -6.03 | +| explained_variance | 0.215 | +| learning_rate | 4.16e-05 | +| loss | -0.0274 | +| n_updates | 84636 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000272 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1393 | +| iterations | 17206 | +| time_elapsed | 25284 | +| total_timesteps | 35237888 | +| train/ | | +| approx_kl | 0.013167705 | +| clip_fraction | 0.313 | +| clip_range | 0.0662 | +| entropy_loss | -5.42 | +| explained_variance | 0.621 | +| learning_rate | 4.16e-05 | +| loss | -0.0248 | +| n_updates | 84640 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000169 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1393 | +| iterations | 17207 | +| time_elapsed | 25285 | +| total_timesteps | 35239936 | +| train/ | | +| approx_kl | 0.010680601 | +| clip_fraction | 0.3 | +| clip_range | 0.0662 | +| entropy_loss | -5.7 | +| explained_variance | 0.37 | +| learning_rate | 4.16e-05 | +| loss | -0.0264 | +| n_updates | 84644 | +| policy_gradient_loss | -0.0143 | +| value_loss | 0.000203 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1393 | +| iterations | 17208 | +| time_elapsed | 25287 | +| total_timesteps | 35241984 | +| train/ | | +| approx_kl | 0.011269191 | +| clip_fraction | 0.349 | +| clip_range | 0.0662 | +| entropy_loss | -6.08 | +| explained_variance | 0.322 | +| learning_rate | 4.16e-05 | +| loss | -0.0273 | +| n_updates | 84648 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000128 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1393 | +| iterations | 17209 | +| time_elapsed | 25288 | +| total_timesteps | 35244032 | +| train/ | | +| approx_kl | 0.010811711 | +| clip_fraction | 0.302 | +| clip_range | 0.0662 | +| entropy_loss | -6.02 | +| explained_variance | 0.428 | +| learning_rate | 4.16e-05 | +| loss | -0.0208 | +| n_updates | 84652 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000189 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1393 | +| iterations | 17210 | +| time_elapsed | 25290 | +| total_timesteps | 35246080 | +| train/ | | +| approx_kl | 0.0102107115 | +| clip_fraction | 0.304 | +| clip_range | 0.0662 | +| entropy_loss | -6.16 | +| explained_variance | 0.498 | +| learning_rate | 4.16e-05 | +| loss | -0.025 | +| n_updates | 84656 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.00023 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1393 | +| iterations | 17211 | +| time_elapsed | 25291 | +| total_timesteps | 35248128 | +| train/ | | +| approx_kl | 0.009900499 | +| clip_fraction | 0.285 | +| clip_range | 0.0662 | +| entropy_loss | -6.39 | +| explained_variance | 0.523 | +| learning_rate | 4.16e-05 | +| loss | -0.0245 | +| n_updates | 84660 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000123 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1393 | +| iterations | 17212 | +| time_elapsed | 25293 | +| total_timesteps | 35250176 | +| train/ | | +| approx_kl | 0.007370639 | +| clip_fraction | 0.288 | +| clip_range | 0.0662 | +| entropy_loss | -6.07 | +| explained_variance | 0.291 | +| learning_rate | 4.16e-05 | +| loss | -0.0202 | +| n_updates | 84664 | +| policy_gradient_loss | -0.0129 | +| value_loss | 0.000409 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1393 | +| iterations | 17213 | +| time_elapsed | 25294 | +| total_timesteps | 35252224 | +| train/ | | +| approx_kl | 0.013024089 | +| clip_fraction | 0.333 | +| clip_range | 0.0662 | +| entropy_loss | -6.03 | +| explained_variance | 0.449 | +| learning_rate | 4.16e-05 | +| loss | -0.0282 | +| n_updates | 84668 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000158 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1393 | +| iterations | 17214 | +| time_elapsed | 25296 | +| total_timesteps | 35254272 | +| train/ | | +| approx_kl | 0.010350607 | +| clip_fraction | 0.318 | +| clip_range | 0.0662 | +| entropy_loss | -6.34 | +| explained_variance | 0.139 | +| learning_rate | 4.16e-05 | +| loss | -0.0263 | +| n_updates | 84672 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000269 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1393 | +| iterations | 17215 | +| time_elapsed | 25298 | +| total_timesteps | 35256320 | +| train/ | | +| approx_kl | 0.013365566 | +| clip_fraction | 0.311 | +| clip_range | 0.0662 | +| entropy_loss | -5.75 | +| explained_variance | 0.534 | +| learning_rate | 4.16e-05 | +| loss | -0.0263 | +| n_updates | 84676 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000224 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1393 | +| iterations | 17216 | +| time_elapsed | 25299 | +| total_timesteps | 35258368 | +| train/ | | +| approx_kl | 0.010465072 | +| clip_fraction | 0.319 | +| clip_range | 0.0662 | +| entropy_loss | -5.99 | +| explained_variance | 0.214 | +| learning_rate | 4.16e-05 | +| loss | -0.0263 | +| n_updates | 84680 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000231 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1393 | +| iterations | 17217 | +| time_elapsed | 25301 | +| total_timesteps | 35260416 | +| train/ | | +| approx_kl | 0.015136217 | +| clip_fraction | 0.347 | +| clip_range | 0.0662 | +| entropy_loss | -5.73 | +| explained_variance | 0.382 | +| learning_rate | 4.16e-05 | +| loss | -0.0304 | +| n_updates | 84684 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000124 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1393 | +| iterations | 17218 | +| time_elapsed | 25302 | +| total_timesteps | 35262464 | +| train/ | | +| approx_kl | 0.013969013 | +| clip_fraction | 0.362 | +| clip_range | 0.0662 | +| entropy_loss | -6.39 | +| explained_variance | -0.0336 | +| learning_rate | 4.16e-05 | +| loss | -0.0323 | +| n_updates | 84688 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000135 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1393 | +| iterations | 17219 | +| time_elapsed | 25304 | +| total_timesteps | 35264512 | +| train/ | | +| approx_kl | 0.012354879 | +| clip_fraction | 0.305 | +| clip_range | 0.0662 | +| entropy_loss | -5.64 | +| explained_variance | 0.361 | +| learning_rate | 4.16e-05 | +| loss | -0.0228 | +| n_updates | 84692 | +| policy_gradient_loss | -0.0145 | +| value_loss | 0.00031 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1393 | +| iterations | 17220 | +| time_elapsed | 25305 | +| total_timesteps | 35266560 | +| train/ | | +| approx_kl | 0.016741931 | +| clip_fraction | 0.356 | +| clip_range | 0.0662 | +| entropy_loss | -5.11 | +| explained_variance | 0.689 | +| learning_rate | 4.16e-05 | +| loss | -0.0335 | +| n_updates | 84696 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000116 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1393 | +| iterations | 17221 | +| time_elapsed | 25307 | +| total_timesteps | 35268608 | +| train/ | | +| approx_kl | 0.014850417 | +| clip_fraction | 0.349 | +| clip_range | 0.0662 | +| entropy_loss | -5.91 | +| explained_variance | 0.268 | +| learning_rate | 4.16e-05 | +| loss | -0.0304 | +| n_updates | 84700 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000159 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1393 | +| iterations | 17222 | +| time_elapsed | 25308 | +| total_timesteps | 35270656 | +| train/ | | +| approx_kl | 0.013986688 | +| clip_fraction | 0.345 | +| clip_range | 0.0662 | +| entropy_loss | -5.96 | +| explained_variance | 0.519 | +| learning_rate | 4.16e-05 | +| loss | -0.0273 | +| n_updates | 84704 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000135 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1393 | +| iterations | 17223 | +| time_elapsed | 25310 | +| total_timesteps | 35272704 | +| train/ | | +| approx_kl | 0.016604722 | +| clip_fraction | 0.337 | +| clip_range | 0.0662 | +| entropy_loss | -6.12 | +| explained_variance | -0.0771 | +| learning_rate | 4.16e-05 | +| loss | -0.0267 | +| n_updates | 84708 | +| policy_gradient_loss | -0.0171 | +| value_loss | 9.72e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1393 | +| iterations | 17224 | +| time_elapsed | 25311 | +| total_timesteps | 35274752 | +| train/ | | +| approx_kl | 0.015677337 | +| clip_fraction | 0.365 | +| clip_range | 0.0662 | +| entropy_loss | -6.61 | +| explained_variance | -0.0218 | +| learning_rate | 4.16e-05 | +| loss | -0.0291 | +| n_updates | 84712 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000184 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1393 | +| iterations | 17225 | +| time_elapsed | 25313 | +| total_timesteps | 35276800 | +| train/ | | +| approx_kl | 0.01484609 | +| clip_fraction | 0.321 | +| clip_range | 0.0662 | +| entropy_loss | -5.98 | +| explained_variance | 0.548 | +| learning_rate | 4.16e-05 | +| loss | -0.0219 | +| n_updates | 84716 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000198 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1393 | +| iterations | 17226 | +| time_elapsed | 25314 | +| total_timesteps | 35278848 | +| train/ | | +| approx_kl | 0.009697344 | +| clip_fraction | 0.276 | +| clip_range | 0.0662 | +| entropy_loss | -5.7 | +| explained_variance | 0.219 | +| learning_rate | 4.16e-05 | +| loss | -0.0274 | +| n_updates | 84720 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.00029 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1393 | +| iterations | 17227 | +| time_elapsed | 25316 | +| total_timesteps | 35280896 | +| train/ | | +| approx_kl | 0.01130577 | +| clip_fraction | 0.3 | +| clip_range | 0.0662 | +| entropy_loss | -5.69 | +| explained_variance | 0.556 | +| learning_rate | 4.16e-05 | +| loss | -0.0223 | +| n_updates | 84724 | +| policy_gradient_loss | -0.0147 | +| value_loss | 0.000172 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1393 | +| iterations | 17228 | +| time_elapsed | 25317 | +| total_timesteps | 35282944 | +| train/ | | +| approx_kl | 0.01719924 | +| clip_fraction | 0.308 | +| clip_range | 0.0662 | +| entropy_loss | -6.04 | +| explained_variance | 0.114 | +| learning_rate | 4.16e-05 | +| loss | -0.0318 | +| n_updates | 84728 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000202 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1393 | +| iterations | 17229 | +| time_elapsed | 25319 | +| total_timesteps | 35284992 | +| train/ | | +| approx_kl | 0.012098936 | +| clip_fraction | 0.328 | +| clip_range | 0.0662 | +| entropy_loss | -6.5 | +| explained_variance | -0.0476 | +| learning_rate | 4.16e-05 | +| loss | -0.0376 | +| n_updates | 84732 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000144 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1393 | +| iterations | 17230 | +| time_elapsed | 25320 | +| total_timesteps | 35287040 | +| train/ | | +| approx_kl | 0.013139214 | +| clip_fraction | 0.334 | +| clip_range | 0.0662 | +| entropy_loss | -6.16 | +| explained_variance | 0.318 | +| learning_rate | 4.16e-05 | +| loss | -0.0283 | +| n_updates | 84736 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000158 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1393 | +| iterations | 17231 | +| time_elapsed | 25322 | +| total_timesteps | 35289088 | +| train/ | | +| approx_kl | 0.008826014 | +| clip_fraction | 0.296 | +| clip_range | 0.0662 | +| entropy_loss | -6.17 | +| explained_variance | 0.326 | +| learning_rate | 4.16e-05 | +| loss | -0.0197 | +| n_updates | 84740 | +| policy_gradient_loss | -0.0137 | +| value_loss | 0.00032 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1393 | +| iterations | 17232 | +| time_elapsed | 25324 | +| total_timesteps | 35291136 | +| train/ | | +| approx_kl | 0.011294103 | +| clip_fraction | 0.313 | +| clip_range | 0.0662 | +| entropy_loss | -6.31 | +| explained_variance | 0.314 | +| learning_rate | 4.16e-05 | +| loss | -0.0297 | +| n_updates | 84744 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000156 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1393 | +| iterations | 17233 | +| time_elapsed | 25325 | +| total_timesteps | 35293184 | +| train/ | | +| approx_kl | 0.009945306 | +| clip_fraction | 0.33 | +| clip_range | 0.0662 | +| entropy_loss | -6.15 | +| explained_variance | 0.538 | +| learning_rate | 4.16e-05 | +| loss | -0.0305 | +| n_updates | 84748 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000157 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1393 | +| iterations | 17234 | +| time_elapsed | 25327 | +| total_timesteps | 35295232 | +| train/ | | +| approx_kl | 0.013025347 | +| clip_fraction | 0.346 | +| clip_range | 0.0662 | +| entropy_loss | -5.75 | +| explained_variance | 0.622 | +| learning_rate | 4.16e-05 | +| loss | -0.0309 | +| n_updates | 84752 | +| policy_gradient_loss | -0.0202 | +| value_loss | 8.91e-05 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1393 | +| iterations | 17235 | +| time_elapsed | 25328 | +| total_timesteps | 35297280 | +| train/ | | +| approx_kl | 0.0105386 | +| clip_fraction | 0.31 | +| clip_range | 0.0662 | +| entropy_loss | -5.92 | +| explained_variance | 0.678 | +| learning_rate | 4.16e-05 | +| loss | -0.0241 | +| n_updates | 84756 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000124 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1393 | +| iterations | 17236 | +| time_elapsed | 25330 | +| total_timesteps | 35299328 | +| train/ | | +| approx_kl | 0.009643397 | +| clip_fraction | 0.284 | +| clip_range | 0.0662 | +| entropy_loss | -6.11 | +| explained_variance | 0.321 | +| learning_rate | 4.16e-05 | +| loss | -0.0263 | +| n_updates | 84760 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.000168 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1393 | +| iterations | 17237 | +| time_elapsed | 25331 | +| total_timesteps | 35301376 | +| train/ | | +| approx_kl | 0.010716227 | +| clip_fraction | 0.287 | +| clip_range | 0.0662 | +| entropy_loss | -6.63 | +| explained_variance | 0.3 | +| learning_rate | 4.16e-05 | +| loss | -0.0274 | +| n_updates | 84764 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000161 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1393 | +| iterations | 17238 | +| time_elapsed | 25333 | +| total_timesteps | 35303424 | +| train/ | | +| approx_kl | 0.008675784 | +| clip_fraction | 0.269 | +| clip_range | 0.0662 | +| entropy_loss | -5.32 | +| explained_variance | 0.505 | +| learning_rate | 4.16e-05 | +| loss | -0.0172 | +| n_updates | 84768 | +| policy_gradient_loss | -0.0128 | +| value_loss | 0.00031 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1393 | +| iterations | 17239 | +| time_elapsed | 25334 | +| total_timesteps | 35305472 | +| train/ | | +| approx_kl | 0.012978345 | +| clip_fraction | 0.337 | +| clip_range | 0.0662 | +| entropy_loss | -6.08 | +| explained_variance | 0.0643 | +| learning_rate | 4.16e-05 | +| loss | -0.0357 | +| n_updates | 84772 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000119 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1393 | +| iterations | 17240 | +| time_elapsed | 25336 | +| total_timesteps | 35307520 | +| train/ | | +| approx_kl | 0.0118072545 | +| clip_fraction | 0.311 | +| clip_range | 0.0662 | +| entropy_loss | -6.24 | +| explained_variance | 0.338 | +| learning_rate | 4.16e-05 | +| loss | -0.0261 | +| n_updates | 84776 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000358 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1393 | +| iterations | 17241 | +| time_elapsed | 25337 | +| total_timesteps | 35309568 | +| train/ | | +| approx_kl | 0.016025249 | +| clip_fraction | 0.344 | +| clip_range | 0.0662 | +| entropy_loss | -5.77 | +| explained_variance | 0.376 | +| learning_rate | 4.16e-05 | +| loss | -0.0332 | +| n_updates | 84780 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000111 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1393 | +| iterations | 17242 | +| time_elapsed | 25339 | +| total_timesteps | 35311616 | +| train/ | | +| approx_kl | 0.0129431635 | +| clip_fraction | 0.352 | +| clip_range | 0.0662 | +| entropy_loss | -5.83 | +| explained_variance | 0.198 | +| learning_rate | 4.16e-05 | +| loss | -0.0334 | +| n_updates | 84784 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000142 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1393 | +| iterations | 17243 | +| time_elapsed | 25340 | +| total_timesteps | 35313664 | +| train/ | | +| approx_kl | 0.011211833 | +| clip_fraction | 0.316 | +| clip_range | 0.0662 | +| entropy_loss | -6.43 | +| explained_variance | 0.416 | +| learning_rate | 4.16e-05 | +| loss | -0.0276 | +| n_updates | 84788 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000171 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1393 | +| iterations | 17244 | +| time_elapsed | 25342 | +| total_timesteps | 35315712 | +| train/ | | +| approx_kl | 0.011919118 | +| clip_fraction | 0.31 | +| clip_range | 0.0662 | +| entropy_loss | -6.4 | +| explained_variance | -0.0596 | +| learning_rate | 4.16e-05 | +| loss | -0.027 | +| n_updates | 84792 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000152 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1393 | +| iterations | 17245 | +| time_elapsed | 25343 | +| total_timesteps | 35317760 | +| train/ | | +| approx_kl | 0.010841588 | +| clip_fraction | 0.335 | +| clip_range | 0.0662 | +| entropy_loss | -6.27 | +| explained_variance | 0.603 | +| learning_rate | 4.16e-05 | +| loss | -0.0281 | +| n_updates | 84796 | +| policy_gradient_loss | -0.0185 | +| value_loss | 9.11e-05 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1393 | +| iterations | 17246 | +| time_elapsed | 25345 | +| total_timesteps | 35319808 | +| train/ | | +| approx_kl | 0.0103729 | +| clip_fraction | 0.322 | +| clip_range | 0.0662 | +| entropy_loss | -6.04 | +| explained_variance | 0.464 | +| learning_rate | 4.16e-05 | +| loss | -0.027 | +| n_updates | 84800 | +| policy_gradient_loss | -0.0175 | +| value_loss | 8.69e-05 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1393 | +| iterations | 17247 | +| time_elapsed | 25346 | +| total_timesteps | 35321856 | +| train/ | | +| approx_kl | 0.011992861 | +| clip_fraction | 0.321 | +| clip_range | 0.0662 | +| entropy_loss | -5.5 | +| explained_variance | 0.771 | +| learning_rate | 4.16e-05 | +| loss | -0.0316 | +| n_updates | 84804 | +| policy_gradient_loss | -0.0173 | +| value_loss | 9.97e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1393 | +| iterations | 17248 | +| time_elapsed | 25348 | +| total_timesteps | 35323904 | +| train/ | | +| approx_kl | 0.012934705 | +| clip_fraction | 0.34 | +| clip_range | 0.0662 | +| entropy_loss | -5.45 | +| explained_variance | 0.175 | +| learning_rate | 4.16e-05 | +| loss | -0.0335 | +| n_updates | 84808 | +| policy_gradient_loss | -0.0205 | +| value_loss | 6.17e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1393 | +| iterations | 17249 | +| time_elapsed | 25350 | +| total_timesteps | 35325952 | +| train/ | | +| approx_kl | 0.01345736 | +| clip_fraction | 0.319 | +| clip_range | 0.0662 | +| entropy_loss | -5.99 | +| explained_variance | 0.492 | +| learning_rate | 4.16e-05 | +| loss | -0.0252 | +| n_updates | 84812 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.00015 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1393 | +| iterations | 17250 | +| time_elapsed | 25351 | +| total_timesteps | 35328000 | +| train/ | | +| approx_kl | 0.010025838 | +| clip_fraction | 0.31 | +| clip_range | 0.0662 | +| entropy_loss | -6.23 | +| explained_variance | 0.534 | +| learning_rate | 4.16e-05 | +| loss | -0.026 | +| n_updates | 84816 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000163 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1393 | +| iterations | 17251 | +| time_elapsed | 25353 | +| total_timesteps | 35330048 | +| train/ | | +| approx_kl | 0.013225384 | +| clip_fraction | 0.323 | +| clip_range | 0.0662 | +| entropy_loss | -6.31 | +| explained_variance | 0.392 | +| learning_rate | 4.16e-05 | +| loss | -0.0296 | +| n_updates | 84820 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1393 | +| iterations | 17252 | +| time_elapsed | 25354 | +| total_timesteps | 35332096 | +| train/ | | +| approx_kl | 0.015112668 | +| clip_fraction | 0.362 | +| clip_range | 0.0662 | +| entropy_loss | -5.74 | +| explained_variance | 0.412 | +| learning_rate | 4.16e-05 | +| loss | -0.0293 | +| n_updates | 84824 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000175 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1393 | +| iterations | 17253 | +| time_elapsed | 25356 | +| total_timesteps | 35334144 | +| train/ | | +| approx_kl | 0.011773868 | +| clip_fraction | 0.32 | +| clip_range | 0.0662 | +| entropy_loss | -5.84 | +| explained_variance | 0.335 | +| learning_rate | 4.16e-05 | +| loss | -0.0271 | +| n_updates | 84828 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000364 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1393 | +| iterations | 17254 | +| time_elapsed | 25357 | +| total_timesteps | 35336192 | +| train/ | | +| approx_kl | 0.014450861 | +| clip_fraction | 0.344 | +| clip_range | 0.0662 | +| entropy_loss | -5.97 | +| explained_variance | 0.415 | +| learning_rate | 4.16e-05 | +| loss | -0.0249 | +| n_updates | 84832 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000174 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1393 | +| iterations | 17255 | +| time_elapsed | 25359 | +| total_timesteps | 35338240 | +| train/ | | +| approx_kl | 0.01243846 | +| clip_fraction | 0.343 | +| clip_range | 0.0662 | +| entropy_loss | -5.98 | +| explained_variance | 0.641 | +| learning_rate | 4.16e-05 | +| loss | -0.0298 | +| n_updates | 84836 | +| policy_gradient_loss | -0.0209 | +| value_loss | 7.75e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1393 | +| iterations | 17256 | +| time_elapsed | 25360 | +| total_timesteps | 35340288 | +| train/ | | +| approx_kl | 0.009596405 | +| clip_fraction | 0.31 | +| clip_range | 0.0662 | +| entropy_loss | -5.89 | +| explained_variance | 0.294 | +| learning_rate | 4.16e-05 | +| loss | -0.0231 | +| n_updates | 84840 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000199 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1393 | +| iterations | 17257 | +| time_elapsed | 25362 | +| total_timesteps | 35342336 | +| train/ | | +| approx_kl | 0.009913281 | +| clip_fraction | 0.295 | +| clip_range | 0.0662 | +| entropy_loss | -5.36 | +| explained_variance | 0.592 | +| learning_rate | 4.16e-05 | +| loss | -0.0248 | +| n_updates | 84844 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000238 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1393 | +| iterations | 17258 | +| time_elapsed | 25363 | +| total_timesteps | 35344384 | +| train/ | | +| approx_kl | 0.012859812 | +| clip_fraction | 0.329 | +| clip_range | 0.0662 | +| entropy_loss | -5.96 | +| explained_variance | 0.132 | +| learning_rate | 4.16e-05 | +| loss | -0.0314 | +| n_updates | 84848 | +| policy_gradient_loss | -0.0198 | +| value_loss | 8.59e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1393 | +| iterations | 17259 | +| time_elapsed | 25365 | +| total_timesteps | 35346432 | +| train/ | | +| approx_kl | 0.011082223 | +| clip_fraction | 0.329 | +| clip_range | 0.0662 | +| entropy_loss | -6.49 | +| explained_variance | -0.0438 | +| learning_rate | 4.16e-05 | +| loss | -0.025 | +| n_updates | 84852 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000238 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1393 | +| iterations | 17260 | +| time_elapsed | 25366 | +| total_timesteps | 35348480 | +| train/ | | +| approx_kl | 0.01408891 | +| clip_fraction | 0.331 | +| clip_range | 0.0662 | +| entropy_loss | -6.37 | +| explained_variance | 0.276 | +| learning_rate | 4.16e-05 | +| loss | -0.0313 | +| n_updates | 84856 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000138 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1393 | +| iterations | 17261 | +| time_elapsed | 25368 | +| total_timesteps | 35350528 | +| train/ | | +| approx_kl | 0.010917701 | +| clip_fraction | 0.314 | +| clip_range | 0.0662 | +| entropy_loss | -6.26 | +| explained_variance | 0.405 | +| learning_rate | 4.16e-05 | +| loss | -0.0199 | +| n_updates | 84860 | +| policy_gradient_loss | -0.0142 | +| value_loss | 0.00025 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1393 | +| iterations | 17262 | +| time_elapsed | 25369 | +| total_timesteps | 35352576 | +| train/ | | +| approx_kl | 0.01473374 | +| clip_fraction | 0.313 | +| clip_range | 0.0662 | +| entropy_loss | -5.9 | +| explained_variance | 0.697 | +| learning_rate | 4.16e-05 | +| loss | -0.0243 | +| n_updates | 84864 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.00011 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1393 | +| iterations | 17263 | +| time_elapsed | 25371 | +| total_timesteps | 35354624 | +| train/ | | +| approx_kl | 0.01146665 | +| clip_fraction | 0.341 | +| clip_range | 0.0662 | +| entropy_loss | -5.66 | +| explained_variance | 0.648 | +| learning_rate | 4.16e-05 | +| loss | -0.03 | +| n_updates | 84868 | +| policy_gradient_loss | -0.0223 | +| value_loss | 7.96e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1393 | +| iterations | 17264 | +| time_elapsed | 25372 | +| total_timesteps | 35356672 | +| train/ | | +| approx_kl | 0.013774753 | +| clip_fraction | 0.337 | +| clip_range | 0.0662 | +| entropy_loss | -6.17 | +| explained_variance | -0.0847 | +| learning_rate | 4.16e-05 | +| loss | -0.0313 | +| n_updates | 84872 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000159 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1393 | +| iterations | 17265 | +| time_elapsed | 25374 | +| total_timesteps | 35358720 | +| train/ | | +| approx_kl | 0.012185121 | +| clip_fraction | 0.291 | +| clip_range | 0.0662 | +| entropy_loss | -6.35 | +| explained_variance | 0.307 | +| learning_rate | 4.16e-05 | +| loss | -0.0272 | +| n_updates | 84876 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000157 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1393 | +| iterations | 17266 | +| time_elapsed | 25375 | +| total_timesteps | 35360768 | +| train/ | | +| approx_kl | 0.01241731 | +| clip_fraction | 0.285 | +| clip_range | 0.0662 | +| entropy_loss | -5.6 | +| explained_variance | 0.456 | +| learning_rate | 4.16e-05 | +| loss | -0.0245 | +| n_updates | 84880 | +| policy_gradient_loss | -0.0147 | +| value_loss | 0.000308 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1393 | +| iterations | 17267 | +| time_elapsed | 25377 | +| total_timesteps | 35362816 | +| train/ | | +| approx_kl | 0.01285669 | +| clip_fraction | 0.303 | +| clip_range | 0.0662 | +| entropy_loss | -5.82 | +| explained_variance | 0.282 | +| learning_rate | 4.16e-05 | +| loss | -0.0225 | +| n_updates | 84884 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000325 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1393 | +| iterations | 17268 | +| time_elapsed | 25378 | +| total_timesteps | 35364864 | +| train/ | | +| approx_kl | 0.01102479 | +| clip_fraction | 0.317 | +| clip_range | 0.0662 | +| entropy_loss | -5.56 | +| explained_variance | 0.691 | +| learning_rate | 4.16e-05 | +| loss | -0.0321 | +| n_updates | 84888 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000146 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1393 | +| iterations | 17269 | +| time_elapsed | 25380 | +| total_timesteps | 35366912 | +| train/ | | +| approx_kl | 0.012403685 | +| clip_fraction | 0.312 | +| clip_range | 0.0662 | +| entropy_loss | -5.89 | +| explained_variance | 0.304 | +| learning_rate | 4.16e-05 | +| loss | -0.0283 | +| n_updates | 84892 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000137 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1393 | +| iterations | 17270 | +| time_elapsed | 25381 | +| total_timesteps | 35368960 | +| train/ | | +| approx_kl | 0.011546962 | +| clip_fraction | 0.34 | +| clip_range | 0.0662 | +| entropy_loss | -6.76 | +| explained_variance | 0.112 | +| learning_rate | 4.16e-05 | +| loss | -0.0313 | +| n_updates | 84896 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000149 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1393 | +| iterations | 17271 | +| time_elapsed | 25383 | +| total_timesteps | 35371008 | +| train/ | | +| approx_kl | 0.010176749 | +| clip_fraction | 0.312 | +| clip_range | 0.0662 | +| entropy_loss | -6.66 | +| explained_variance | 0.258 | +| learning_rate | 4.16e-05 | +| loss | -0.0285 | +| n_updates | 84900 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000177 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1393 | +| iterations | 17272 | +| time_elapsed | 25384 | +| total_timesteps | 35373056 | +| train/ | | +| approx_kl | 0.0144021325 | +| clip_fraction | 0.326 | +| clip_range | 0.0662 | +| entropy_loss | -5.47 | +| explained_variance | 0.705 | +| learning_rate | 4.16e-05 | +| loss | -0.0314 | +| n_updates | 84904 | +| policy_gradient_loss | -0.0179 | +| value_loss | 8.63e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1393 | +| iterations | 17273 | +| time_elapsed | 25386 | +| total_timesteps | 35375104 | +| train/ | | +| approx_kl | 0.012107782 | +| clip_fraction | 0.334 | +| clip_range | 0.0662 | +| entropy_loss | -6.24 | +| explained_variance | 0.432 | +| learning_rate | 4.16e-05 | +| loss | -0.0309 | +| n_updates | 84908 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000137 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1393 | +| iterations | 17274 | +| time_elapsed | 25387 | +| total_timesteps | 35377152 | +| train/ | | +| approx_kl | 0.014482527 | +| clip_fraction | 0.331 | +| clip_range | 0.0662 | +| entropy_loss | -5.87 | +| explained_variance | 0.216 | +| learning_rate | 4.16e-05 | +| loss | -0.0224 | +| n_updates | 84912 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000265 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1393 | +| iterations | 17275 | +| time_elapsed | 25389 | +| total_timesteps | 35379200 | +| train/ | | +| approx_kl | 0.014161001 | +| clip_fraction | 0.353 | +| clip_range | 0.0662 | +| entropy_loss | -5.95 | +| explained_variance | -0.0374 | +| learning_rate | 4.16e-05 | +| loss | -0.0302 | +| n_updates | 84916 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000205 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1393 | +| iterations | 17276 | +| time_elapsed | 25390 | +| total_timesteps | 35381248 | +| train/ | | +| approx_kl | 0.009665493 | +| clip_fraction | 0.29 | +| clip_range | 0.0662 | +| entropy_loss | -5.62 | +| explained_variance | 0.367 | +| learning_rate | 4.16e-05 | +| loss | -0.0225 | +| n_updates | 84920 | +| policy_gradient_loss | -0.0144 | +| value_loss | 0.000253 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1393 | +| iterations | 17277 | +| time_elapsed | 25392 | +| total_timesteps | 35383296 | +| train/ | | +| approx_kl | 0.016211342 | +| clip_fraction | 0.315 | +| clip_range | 0.0662 | +| entropy_loss | -5.62 | +| explained_variance | 0.242 | +| learning_rate | 4.16e-05 | +| loss | -0.0257 | +| n_updates | 84924 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000309 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1393 | +| iterations | 17278 | +| time_elapsed | 25394 | +| total_timesteps | 35385344 | +| train/ | | +| approx_kl | 0.011772465 | +| clip_fraction | 0.324 | +| clip_range | 0.0662 | +| entropy_loss | -5.29 | +| explained_variance | 0.471 | +| learning_rate | 4.16e-05 | +| loss | -0.0229 | +| n_updates | 84928 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000296 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1393 | +| iterations | 17279 | +| time_elapsed | 25395 | +| total_timesteps | 35387392 | +| train/ | | +| approx_kl | 0.013495766 | +| clip_fraction | 0.36 | +| clip_range | 0.0662 | +| entropy_loss | -6.01 | +| explained_variance | 0.284 | +| learning_rate | 4.16e-05 | +| loss | -0.0349 | +| n_updates | 84932 | +| policy_gradient_loss | -0.0212 | +| value_loss | 9.6e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1393 | +| iterations | 17280 | +| time_elapsed | 25397 | +| total_timesteps | 35389440 | +| train/ | | +| approx_kl | 0.010173719 | +| clip_fraction | 0.324 | +| clip_range | 0.0662 | +| entropy_loss | -6.84 | +| explained_variance | -0.109 | +| learning_rate | 4.16e-05 | +| loss | -0.0274 | +| n_updates | 84936 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000201 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1393 | +| iterations | 17281 | +| time_elapsed | 25398 | +| total_timesteps | 35391488 | +| train/ | | +| approx_kl | 0.009993166 | +| clip_fraction | 0.305 | +| clip_range | 0.0662 | +| entropy_loss | -6.07 | +| explained_variance | 0.481 | +| learning_rate | 4.16e-05 | +| loss | -0.0276 | +| n_updates | 84940 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000188 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1393 | +| iterations | 17282 | +| time_elapsed | 25400 | +| total_timesteps | 35393536 | +| train/ | | +| approx_kl | 0.013519876 | +| clip_fraction | 0.325 | +| clip_range | 0.0662 | +| entropy_loss | -5.65 | +| explained_variance | 0.747 | +| learning_rate | 4.16e-05 | +| loss | -0.0353 | +| n_updates | 84944 | +| policy_gradient_loss | -0.0208 | +| value_loss | 6.89e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1393 | +| iterations | 17283 | +| time_elapsed | 25401 | +| total_timesteps | 35395584 | +| train/ | | +| approx_kl | 0.013860179 | +| clip_fraction | 0.336 | +| clip_range | 0.0662 | +| entropy_loss | -5.75 | +| explained_variance | 0.582 | +| learning_rate | 4.16e-05 | +| loss | -0.0359 | +| n_updates | 84948 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.0001 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1393 | +| iterations | 17284 | +| time_elapsed | 25403 | +| total_timesteps | 35397632 | +| train/ | | +| approx_kl | 0.011676968 | +| clip_fraction | 0.325 | +| clip_range | 0.0662 | +| entropy_loss | -6.07 | +| explained_variance | 0.23 | +| learning_rate | 4.16e-05 | +| loss | -0.0218 | +| n_updates | 84952 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000276 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1393 | +| iterations | 17285 | +| time_elapsed | 25404 | +| total_timesteps | 35399680 | +| train/ | | +| approx_kl | 0.017190449 | +| clip_fraction | 0.314 | +| clip_range | 0.0662 | +| entropy_loss | -6.25 | +| explained_variance | -0.206 | +| learning_rate | 4.16e-05 | +| loss | -0.029 | +| n_updates | 84956 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000149 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1393 | +| iterations | 17286 | +| time_elapsed | 25406 | +| total_timesteps | 35401728 | +| train/ | | +| approx_kl | 0.01112851 | +| clip_fraction | 0.372 | +| clip_range | 0.0662 | +| entropy_loss | -5.68 | +| explained_variance | 0.825 | +| learning_rate | 4.16e-05 | +| loss | -0.0366 | +| n_updates | 84960 | +| policy_gradient_loss | -0.021 | +| value_loss | 6.85e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1393 | +| iterations | 17287 | +| time_elapsed | 25407 | +| total_timesteps | 35403776 | +| train/ | | +| approx_kl | 0.015140254 | +| clip_fraction | 0.358 | +| clip_range | 0.0661 | +| entropy_loss | -5.73 | +| explained_variance | 0.369 | +| learning_rate | 4.16e-05 | +| loss | -0.0283 | +| n_updates | 84964 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000111 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1393 | +| iterations | 17288 | +| time_elapsed | 25409 | +| total_timesteps | 35405824 | +| train/ | | +| approx_kl | 0.009824583 | +| clip_fraction | 0.315 | +| clip_range | 0.0661 | +| entropy_loss | -5.95 | +| explained_variance | 0.209 | +| learning_rate | 4.16e-05 | +| loss | -0.0252 | +| n_updates | 84968 | +| policy_gradient_loss | -0.0131 | +| value_loss | 0.000305 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1393 | +| iterations | 17289 | +| time_elapsed | 25410 | +| total_timesteps | 35407872 | +| train/ | | +| approx_kl | 0.011439596 | +| clip_fraction | 0.337 | +| clip_range | 0.0661 | +| entropy_loss | -6.49 | +| explained_variance | 0.339 | +| learning_rate | 4.16e-05 | +| loss | -0.0344 | +| n_updates | 84972 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000103 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1393 | +| iterations | 17290 | +| time_elapsed | 25412 | +| total_timesteps | 35409920 | +| train/ | | +| approx_kl | 0.011674182 | +| clip_fraction | 0.335 | +| clip_range | 0.0661 | +| entropy_loss | -6.1 | +| explained_variance | 0.376 | +| learning_rate | 4.16e-05 | +| loss | -0.0271 | +| n_updates | 84976 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000228 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1393 | +| iterations | 17291 | +| time_elapsed | 25413 | +| total_timesteps | 35411968 | +| train/ | | +| approx_kl | 0.013560912 | +| clip_fraction | 0.328 | +| clip_range | 0.0661 | +| entropy_loss | -5.43 | +| explained_variance | 0.545 | +| learning_rate | 4.16e-05 | +| loss | -0.0251 | +| n_updates | 84980 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000183 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1393 | +| iterations | 17292 | +| time_elapsed | 25415 | +| total_timesteps | 35414016 | +| train/ | | +| approx_kl | 0.013021175 | +| clip_fraction | 0.332 | +| clip_range | 0.0661 | +| entropy_loss | -5.49 | +| explained_variance | 0.425 | +| learning_rate | 4.16e-05 | +| loss | -0.0362 | +| n_updates | 84984 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000115 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1393 | +| iterations | 17293 | +| time_elapsed | 25416 | +| total_timesteps | 35416064 | +| train/ | | +| approx_kl | 0.013905099 | +| clip_fraction | 0.326 | +| clip_range | 0.0661 | +| entropy_loss | -5.84 | +| explained_variance | 0.508 | +| learning_rate | 4.16e-05 | +| loss | -0.0257 | +| n_updates | 84988 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000211 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1393 | +| iterations | 17294 | +| time_elapsed | 25418 | +| total_timesteps | 35418112 | +| train/ | | +| approx_kl | 0.01090658 | +| clip_fraction | 0.333 | +| clip_range | 0.0661 | +| entropy_loss | -6.4 | +| explained_variance | -0.196 | +| learning_rate | 4.16e-05 | +| loss | -0.0339 | +| n_updates | 84992 | +| policy_gradient_loss | -0.0197 | +| value_loss | 9.38e-05 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1393 | +| iterations | 17295 | +| time_elapsed | 25419 | +| total_timesteps | 35420160 | +| train/ | | +| approx_kl | 0.01237051 | +| clip_fraction | 0.32 | +| clip_range | 0.0661 | +| entropy_loss | -6.84 | +| explained_variance | 0.195 | +| learning_rate | 4.16e-05 | +| loss | -0.0303 | +| n_updates | 84996 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000201 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1393 | +| iterations | 17296 | +| time_elapsed | 25421 | +| total_timesteps | 35422208 | +| train/ | | +| approx_kl | 0.0130383875 | +| clip_fraction | 0.322 | +| clip_range | 0.0661 | +| entropy_loss | -5.78 | +| explained_variance | 0.53 | +| learning_rate | 4.16e-05 | +| loss | -0.0268 | +| n_updates | 85000 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000185 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1393 | +| iterations | 17297 | +| time_elapsed | 25422 | +| total_timesteps | 35424256 | +| train/ | | +| approx_kl | 0.016537786 | +| clip_fraction | 0.373 | +| clip_range | 0.0661 | +| entropy_loss | -5.33 | +| explained_variance | 0.615 | +| learning_rate | 4.16e-05 | +| loss | -0.0278 | +| n_updates | 85004 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000139 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1393 | +| iterations | 17298 | +| time_elapsed | 25424 | +| total_timesteps | 35426304 | +| train/ | | +| approx_kl | 0.011935106 | +| clip_fraction | 0.32 | +| clip_range | 0.0661 | +| entropy_loss | -5.55 | +| explained_variance | 0.306 | +| learning_rate | 4.16e-05 | +| loss | -0.0291 | +| n_updates | 85008 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000223 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1393 | +| iterations | 17299 | +| time_elapsed | 25426 | +| total_timesteps | 35428352 | +| train/ | | +| approx_kl | 0.011224032 | +| clip_fraction | 0.328 | +| clip_range | 0.0661 | +| entropy_loss | -5.46 | +| explained_variance | 0.471 | +| learning_rate | 4.16e-05 | +| loss | -0.0209 | +| n_updates | 85012 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000281 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1393 | +| iterations | 17300 | +| time_elapsed | 25427 | +| total_timesteps | 35430400 | +| train/ | | +| approx_kl | 0.0135432845 | +| clip_fraction | 0.33 | +| clip_range | 0.0661 | +| entropy_loss | -5.74 | +| explained_variance | 0.337 | +| learning_rate | 4.16e-05 | +| loss | -0.028 | +| n_updates | 85016 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000154 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1393 | +| iterations | 17301 | +| time_elapsed | 25429 | +| total_timesteps | 35432448 | +| train/ | | +| approx_kl | 0.01373288 | +| clip_fraction | 0.321 | +| clip_range | 0.0661 | +| entropy_loss | -6.26 | +| explained_variance | 0.202 | +| learning_rate | 4.16e-05 | +| loss | -0.0289 | +| n_updates | 85020 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000212 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1393 | +| iterations | 17302 | +| time_elapsed | 25430 | +| total_timesteps | 35434496 | +| train/ | | +| approx_kl | 0.01094725 | +| clip_fraction | 0.329 | +| clip_range | 0.0661 | +| entropy_loss | -6.69 | +| explained_variance | 0.216 | +| learning_rate | 4.16e-05 | +| loss | -0.0289 | +| n_updates | 85024 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000221 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1393 | +| iterations | 17303 | +| time_elapsed | 25432 | +| total_timesteps | 35436544 | +| train/ | | +| approx_kl | 0.010668719 | +| clip_fraction | 0.333 | +| clip_range | 0.0661 | +| entropy_loss | -6.76 | +| explained_variance | 0.0527 | +| learning_rate | 4.16e-05 | +| loss | -0.0286 | +| n_updates | 85028 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000177 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1393 | +| iterations | 17304 | +| time_elapsed | 25433 | +| total_timesteps | 35438592 | +| train/ | | +| approx_kl | 0.012014119 | +| clip_fraction | 0.305 | +| clip_range | 0.0661 | +| entropy_loss | -5.58 | +| explained_variance | 0.397 | +| learning_rate | 4.16e-05 | +| loss | -0.0294 | +| n_updates | 85032 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000442 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1393 | +| iterations | 17305 | +| time_elapsed | 25435 | +| total_timesteps | 35440640 | +| train/ | | +| approx_kl | 0.01019477 | +| clip_fraction | 0.319 | +| clip_range | 0.0661 | +| entropy_loss | -6.22 | +| explained_variance | -0.181 | +| learning_rate | 4.16e-05 | +| loss | -0.0301 | +| n_updates | 85036 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000165 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1393 | +| iterations | 17306 | +| time_elapsed | 25436 | +| total_timesteps | 35442688 | +| train/ | | +| approx_kl | 0.010693768 | +| clip_fraction | 0.258 | +| clip_range | 0.0661 | +| entropy_loss | -6.56 | +| explained_variance | 0.232 | +| learning_rate | 4.16e-05 | +| loss | -0.0242 | +| n_updates | 85040 | +| policy_gradient_loss | -0.014 | +| value_loss | 0.000434 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1393 | +| iterations | 17307 | +| time_elapsed | 25438 | +| total_timesteps | 35444736 | +| train/ | | +| approx_kl | 0.015098773 | +| clip_fraction | 0.332 | +| clip_range | 0.0661 | +| entropy_loss | -5.45 | +| explained_variance | 0.424 | +| learning_rate | 4.16e-05 | +| loss | -0.0234 | +| n_updates | 85044 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000258 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1393 | +| iterations | 17308 | +| time_elapsed | 25440 | +| total_timesteps | 35446784 | +| train/ | | +| approx_kl | 0.013072869 | +| clip_fraction | 0.327 | +| clip_range | 0.0661 | +| entropy_loss | -5.67 | +| explained_variance | 0.453 | +| learning_rate | 4.16e-05 | +| loss | -0.0241 | +| n_updates | 85048 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000239 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1393 | +| iterations | 17309 | +| time_elapsed | 25441 | +| total_timesteps | 35448832 | +| train/ | | +| approx_kl | 0.012425425 | +| clip_fraction | 0.329 | +| clip_range | 0.0661 | +| entropy_loss | -5.87 | +| explained_variance | 0.517 | +| learning_rate | 4.16e-05 | +| loss | -0.0355 | +| n_updates | 85052 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.00012 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1393 | +| iterations | 17310 | +| time_elapsed | 25443 | +| total_timesteps | 35450880 | +| train/ | | +| approx_kl | 0.01215063 | +| clip_fraction | 0.349 | +| clip_range | 0.0661 | +| entropy_loss | -6.2 | +| explained_variance | 0.0329 | +| learning_rate | 4.16e-05 | +| loss | -0.0316 | +| n_updates | 85056 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000233 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1393 | +| iterations | 17311 | +| time_elapsed | 25444 | +| total_timesteps | 35452928 | +| train/ | | +| approx_kl | 0.010252197 | +| clip_fraction | 0.352 | +| clip_range | 0.0661 | +| entropy_loss | -6.38 | +| explained_variance | 0.297 | +| learning_rate | 4.16e-05 | +| loss | -0.0328 | +| n_updates | 85060 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000145 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1393 | +| iterations | 17312 | +| time_elapsed | 25446 | +| total_timesteps | 35454976 | +| train/ | | +| approx_kl | 0.011690816 | +| clip_fraction | 0.347 | +| clip_range | 0.0661 | +| entropy_loss | -6.52 | +| explained_variance | -0.0819 | +| learning_rate | 4.16e-05 | +| loss | -0.0337 | +| n_updates | 85064 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.00013 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1393 | +| iterations | 17313 | +| time_elapsed | 25447 | +| total_timesteps | 35457024 | +| train/ | | +| approx_kl | 0.008916579 | +| clip_fraction | 0.32 | +| clip_range | 0.0661 | +| entropy_loss | -6.67 | +| explained_variance | 0.245 | +| learning_rate | 4.16e-05 | +| loss | -0.0293 | +| n_updates | 85068 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000301 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1393 | +| iterations | 17314 | +| time_elapsed | 25449 | +| total_timesteps | 35459072 | +| train/ | | +| approx_kl | 0.009925069 | +| clip_fraction | 0.332 | +| clip_range | 0.0661 | +| entropy_loss | -5.95 | +| explained_variance | 0.505 | +| learning_rate | 4.16e-05 | +| loss | -0.0268 | +| n_updates | 85072 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000214 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1393 | +| iterations | 17315 | +| time_elapsed | 25450 | +| total_timesteps | 35461120 | +| train/ | | +| approx_kl | 0.013179169 | +| clip_fraction | 0.366 | +| clip_range | 0.0661 | +| entropy_loss | -5.4 | +| explained_variance | 0.649 | +| learning_rate | 4.16e-05 | +| loss | -0.0358 | +| n_updates | 85076 | +| policy_gradient_loss | -0.0224 | +| value_loss | 7.42e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1393 | +| iterations | 17316 | +| time_elapsed | 25452 | +| total_timesteps | 35463168 | +| train/ | | +| approx_kl | 0.012464061 | +| clip_fraction | 0.323 | +| clip_range | 0.0661 | +| entropy_loss | -5.6 | +| explained_variance | 0.631 | +| learning_rate | 4.16e-05 | +| loss | -0.0302 | +| n_updates | 85080 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000101 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1393 | +| iterations | 17317 | +| time_elapsed | 25453 | +| total_timesteps | 35465216 | +| train/ | | +| approx_kl | 0.014719554 | +| clip_fraction | 0.354 | +| clip_range | 0.0661 | +| entropy_loss | -5.77 | +| explained_variance | 0.429 | +| learning_rate | 4.16e-05 | +| loss | -0.0333 | +| n_updates | 85084 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000115 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1393 | +| iterations | 17318 | +| time_elapsed | 25455 | +| total_timesteps | 35467264 | +| train/ | | +| approx_kl | 0.020076634 | +| clip_fraction | 0.306 | +| clip_range | 0.0661 | +| entropy_loss | -5.93 | +| explained_variance | 0.415 | +| learning_rate | 4.16e-05 | +| loss | -0.0233 | +| n_updates | 85088 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.000195 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1393 | +| iterations | 17319 | +| time_elapsed | 25456 | +| total_timesteps | 35469312 | +| train/ | | +| approx_kl | 0.01257089 | +| clip_fraction | 0.355 | +| clip_range | 0.0661 | +| entropy_loss | -5.97 | +| explained_variance | 0.364 | +| learning_rate | 4.16e-05 | +| loss | -0.0331 | +| n_updates | 85092 | +| policy_gradient_loss | -0.0196 | +| value_loss | 9.82e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1393 | +| iterations | 17320 | +| time_elapsed | 25458 | +| total_timesteps | 35471360 | +| train/ | | +| approx_kl | 0.011789994 | +| clip_fraction | 0.332 | +| clip_range | 0.0661 | +| entropy_loss | -5.44 | +| explained_variance | 0.682 | +| learning_rate | 4.16e-05 | +| loss | -0.0249 | +| n_updates | 85096 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.00014 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1393 | +| iterations | 17321 | +| time_elapsed | 25460 | +| total_timesteps | 35473408 | +| train/ | | +| approx_kl | 0.012875836 | +| clip_fraction | 0.357 | +| clip_range | 0.0661 | +| entropy_loss | -5.91 | +| explained_variance | -0.0807 | +| learning_rate | 4.16e-05 | +| loss | -0.0326 | +| n_updates | 85100 | +| policy_gradient_loss | -0.021 | +| value_loss | 5.23e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1393 | +| iterations | 17322 | +| time_elapsed | 25461 | +| total_timesteps | 35475456 | +| train/ | | +| approx_kl | 0.013397396 | +| clip_fraction | 0.34 | +| clip_range | 0.0661 | +| entropy_loss | -6.4 | +| explained_variance | 0.231 | +| learning_rate | 4.16e-05 | +| loss | -0.0281 | +| n_updates | 85104 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000206 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1393 | +| iterations | 17323 | +| time_elapsed | 25463 | +| total_timesteps | 35477504 | +| train/ | | +| approx_kl | 0.014394426 | +| clip_fraction | 0.336 | +| clip_range | 0.0661 | +| entropy_loss | -6.43 | +| explained_variance | 0.0131 | +| learning_rate | 4.16e-05 | +| loss | -0.031 | +| n_updates | 85108 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.00019 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1393 | +| iterations | 17324 | +| time_elapsed | 25464 | +| total_timesteps | 35479552 | +| train/ | | +| approx_kl | 0.0142377 | +| clip_fraction | 0.323 | +| clip_range | 0.0661 | +| entropy_loss | -5.72 | +| explained_variance | 0.542 | +| learning_rate | 4.16e-05 | +| loss | -0.0281 | +| n_updates | 85112 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000147 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1393 | +| iterations | 17325 | +| time_elapsed | 25466 | +| total_timesteps | 35481600 | +| train/ | | +| approx_kl | 0.015373329 | +| clip_fraction | 0.37 | +| clip_range | 0.0661 | +| entropy_loss | -5.82 | +| explained_variance | 0.378 | +| learning_rate | 4.16e-05 | +| loss | -0.0303 | +| n_updates | 85116 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000117 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1393 | +| iterations | 17326 | +| time_elapsed | 25467 | +| total_timesteps | 35483648 | +| train/ | | +| approx_kl | 0.010699025 | +| clip_fraction | 0.309 | +| clip_range | 0.0661 | +| entropy_loss | -6.07 | +| explained_variance | 0.339 | +| learning_rate | 4.16e-05 | +| loss | -0.0242 | +| n_updates | 85120 | +| policy_gradient_loss | -0.0146 | +| value_loss | 0.000187 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1393 | +| iterations | 17327 | +| time_elapsed | 25469 | +| total_timesteps | 35485696 | +| train/ | | +| approx_kl | 0.013621228 | +| clip_fraction | 0.335 | +| clip_range | 0.0661 | +| entropy_loss | -5.72 | +| explained_variance | 0.659 | +| learning_rate | 4.16e-05 | +| loss | -0.0331 | +| n_updates | 85124 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000109 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1393 | +| iterations | 17328 | +| time_elapsed | 25470 | +| total_timesteps | 35487744 | +| train/ | | +| approx_kl | 0.0126753105 | +| clip_fraction | 0.342 | +| clip_range | 0.0661 | +| entropy_loss | -5.41 | +| explained_variance | 0.631 | +| learning_rate | 4.16e-05 | +| loss | -0.0271 | +| n_updates | 85128 | +| policy_gradient_loss | -0.0191 | +| value_loss | 8.26e-05 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1393 | +| iterations | 17329 | +| time_elapsed | 25472 | +| total_timesteps | 35489792 | +| train/ | | +| approx_kl | 0.01116179 | +| clip_fraction | 0.323 | +| clip_range | 0.0661 | +| entropy_loss | -5.69 | +| explained_variance | 0.573 | +| learning_rate | 4.16e-05 | +| loss | -0.0273 | +| n_updates | 85132 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000148 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1393 | +| iterations | 17330 | +| time_elapsed | 25474 | +| total_timesteps | 35491840 | +| train/ | | +| approx_kl | 0.013917092 | +| clip_fraction | 0.332 | +| clip_range | 0.0661 | +| entropy_loss | -6.55 | +| explained_variance | 0.00761 | +| learning_rate | 4.16e-05 | +| loss | -0.0274 | +| n_updates | 85136 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000103 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1393 | +| iterations | 17331 | +| time_elapsed | 25475 | +| total_timesteps | 35493888 | +| train/ | | +| approx_kl | 0.011867745 | +| clip_fraction | 0.362 | +| clip_range | 0.0661 | +| entropy_loss | -6.4 | +| explained_variance | 0.393 | +| learning_rate | 4.16e-05 | +| loss | -0.0305 | +| n_updates | 85140 | +| policy_gradient_loss | -0.0192 | +| value_loss | 9.72e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1393 | +| iterations | 17332 | +| time_elapsed | 25477 | +| total_timesteps | 35495936 | +| train/ | | +| approx_kl | 0.012260663 | +| clip_fraction | 0.335 | +| clip_range | 0.0661 | +| entropy_loss | -6.64 | +| explained_variance | 0.0576 | +| learning_rate | 4.16e-05 | +| loss | -0.0312 | +| n_updates | 85144 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000112 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1393 | +| iterations | 17333 | +| time_elapsed | 25478 | +| total_timesteps | 35497984 | +| train/ | | +| approx_kl | 0.011702901 | +| clip_fraction | 0.339 | +| clip_range | 0.0661 | +| entropy_loss | -6.58 | +| explained_variance | 0.563 | +| learning_rate | 4.16e-05 | +| loss | -0.0297 | +| n_updates | 85148 | +| policy_gradient_loss | -0.0211 | +| value_loss | 5.84e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1393 | +| iterations | 17334 | +| time_elapsed | 25480 | +| total_timesteps | 35500032 | +| train/ | | +| approx_kl | 0.010932084 | +| clip_fraction | 0.285 | +| clip_range | 0.0661 | +| entropy_loss | -5.78 | +| explained_variance | 0.645 | +| learning_rate | 4.16e-05 | +| loss | -0.017 | +| n_updates | 85152 | +| policy_gradient_loss | -0.0128 | +| value_loss | 0.000166 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1393 | +| iterations | 17335 | +| time_elapsed | 25481 | +| total_timesteps | 35502080 | +| train/ | | +| approx_kl | 0.010580022 | +| clip_fraction | 0.323 | +| clip_range | 0.0661 | +| entropy_loss | -5.19 | +| explained_variance | 0.7 | +| learning_rate | 4.16e-05 | +| loss | -0.0235 | +| n_updates | 85156 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000102 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1393 | +| iterations | 17336 | +| time_elapsed | 25483 | +| total_timesteps | 35504128 | +| train/ | | +| approx_kl | 0.012798082 | +| clip_fraction | 0.323 | +| clip_range | 0.0661 | +| entropy_loss | -6.21 | +| explained_variance | -0.0612 | +| learning_rate | 4.16e-05 | +| loss | -0.0292 | +| n_updates | 85160 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000107 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1393 | +| iterations | 17337 | +| time_elapsed | 25484 | +| total_timesteps | 35506176 | +| train/ | | +| approx_kl | 0.011686549 | +| clip_fraction | 0.353 | +| clip_range | 0.0661 | +| entropy_loss | -6.13 | +| explained_variance | 0.668 | +| learning_rate | 4.16e-05 | +| loss | -0.0336 | +| n_updates | 85164 | +| policy_gradient_loss | -0.0188 | +| value_loss | 6.8e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1393 | +| iterations | 17338 | +| time_elapsed | 25486 | +| total_timesteps | 35508224 | +| train/ | | +| approx_kl | 0.009964374 | +| clip_fraction | 0.308 | +| clip_range | 0.0661 | +| entropy_loss | -6.33 | +| explained_variance | 0.448 | +| learning_rate | 4.16e-05 | +| loss | -0.0269 | +| n_updates | 85168 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000104 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1393 | +| iterations | 17339 | +| time_elapsed | 25487 | +| total_timesteps | 35510272 | +| train/ | | +| approx_kl | 0.009216106 | +| clip_fraction | 0.301 | +| clip_range | 0.0661 | +| entropy_loss | -5.91 | +| explained_variance | 0.708 | +| learning_rate | 4.16e-05 | +| loss | -0.0304 | +| n_updates | 85172 | +| policy_gradient_loss | -0.0161 | +| value_loss | 9.44e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1393 | +| iterations | 17340 | +| time_elapsed | 25489 | +| total_timesteps | 35512320 | +| train/ | | +| approx_kl | 0.0091307545 | +| clip_fraction | 0.283 | +| clip_range | 0.0661 | +| entropy_loss | -5.49 | +| explained_variance | 0.515 | +| learning_rate | 4.16e-05 | +| loss | -0.0212 | +| n_updates | 85176 | +| policy_gradient_loss | -0.0135 | +| value_loss | 0.000297 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1393 | +| iterations | 17341 | +| time_elapsed | 25491 | +| total_timesteps | 35514368 | +| train/ | | +| approx_kl | 0.012201127 | +| clip_fraction | 0.304 | +| clip_range | 0.0661 | +| entropy_loss | -5.86 | +| explained_variance | 0.429 | +| learning_rate | 4.16e-05 | +| loss | -0.028 | +| n_updates | 85180 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000217 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1393 | +| iterations | 17342 | +| time_elapsed | 25492 | +| total_timesteps | 35516416 | +| train/ | | +| approx_kl | 0.009079577 | +| clip_fraction | 0.335 | +| clip_range | 0.0661 | +| entropy_loss | -6.5 | +| explained_variance | 0.243 | +| learning_rate | 4.16e-05 | +| loss | -0.0286 | +| n_updates | 85184 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000117 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1393 | +| iterations | 17343 | +| time_elapsed | 25494 | +| total_timesteps | 35518464 | +| train/ | | +| approx_kl | 0.010053367 | +| clip_fraction | 0.316 | +| clip_range | 0.0661 | +| entropy_loss | -6.82 | +| explained_variance | 0.0307 | +| learning_rate | 4.16e-05 | +| loss | -0.0268 | +| n_updates | 85188 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000171 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1393 | +| iterations | 17344 | +| time_elapsed | 25495 | +| total_timesteps | 35520512 | +| train/ | | +| approx_kl | 0.010355474 | +| clip_fraction | 0.318 | +| clip_range | 0.0661 | +| entropy_loss | -6.66 | +| explained_variance | 0.263 | +| learning_rate | 4.16e-05 | +| loss | -0.0281 | +| n_updates | 85192 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000178 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1393 | +| iterations | 17345 | +| time_elapsed | 25497 | +| total_timesteps | 35522560 | +| train/ | | +| approx_kl | 0.009161444 | +| clip_fraction | 0.286 | +| clip_range | 0.0661 | +| entropy_loss | -6.2 | +| explained_variance | 0.561 | +| learning_rate | 4.16e-05 | +| loss | -0.0232 | +| n_updates | 85196 | +| policy_gradient_loss | -0.0131 | +| value_loss | 0.000185 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1393 | +| iterations | 17346 | +| time_elapsed | 25498 | +| total_timesteps | 35524608 | +| train/ | | +| approx_kl | 0.012259317 | +| clip_fraction | 0.311 | +| clip_range | 0.0661 | +| entropy_loss | -5.36 | +| explained_variance | 0.382 | +| learning_rate | 4.16e-05 | +| loss | -0.0234 | +| n_updates | 85200 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000303 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1393 | +| iterations | 17347 | +| time_elapsed | 25500 | +| total_timesteps | 35526656 | +| train/ | | +| approx_kl | 0.011040604 | +| clip_fraction | 0.335 | +| clip_range | 0.0661 | +| entropy_loss | -5.38 | +| explained_variance | 0.367 | +| learning_rate | 4.16e-05 | +| loss | -0.0277 | +| n_updates | 85204 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000404 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1393 | +| iterations | 17348 | +| time_elapsed | 25501 | +| total_timesteps | 35528704 | +| train/ | | +| approx_kl | 0.012589485 | +| clip_fraction | 0.329 | +| clip_range | 0.0661 | +| entropy_loss | -5.8 | +| explained_variance | 0.136 | +| learning_rate | 4.16e-05 | +| loss | -0.0225 | +| n_updates | 85208 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000217 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1393 | +| iterations | 17349 | +| time_elapsed | 25503 | +| total_timesteps | 35530752 | +| train/ | | +| approx_kl | 0.011815716 | +| clip_fraction | 0.343 | +| clip_range | 0.0661 | +| entropy_loss | -5.55 | +| explained_variance | 0.617 | +| learning_rate | 4.16e-05 | +| loss | -0.0294 | +| n_updates | 85212 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000157 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1393 | +| iterations | 17350 | +| time_elapsed | 25505 | +| total_timesteps | 35532800 | +| train/ | | +| approx_kl | 0.012604596 | +| clip_fraction | 0.344 | +| clip_range | 0.0661 | +| entropy_loss | -6.07 | +| explained_variance | 0.347 | +| learning_rate | 4.16e-05 | +| loss | -0.027 | +| n_updates | 85216 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000154 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1393 | +| iterations | 17351 | +| time_elapsed | 25506 | +| total_timesteps | 35534848 | +| train/ | | +| approx_kl | 0.010937614 | +| clip_fraction | 0.321 | +| clip_range | 0.0661 | +| entropy_loss | -6.18 | +| explained_variance | 0.425 | +| learning_rate | 4.16e-05 | +| loss | -0.0264 | +| n_updates | 85220 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.00021 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1393 | +| iterations | 17352 | +| time_elapsed | 25508 | +| total_timesteps | 35536896 | +| train/ | | +| approx_kl | 0.011411578 | +| clip_fraction | 0.333 | +| clip_range | 0.0661 | +| entropy_loss | -6.3 | +| explained_variance | 0.298 | +| learning_rate | 4.16e-05 | +| loss | -0.0269 | +| n_updates | 85224 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000179 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1393 | +| iterations | 17353 | +| time_elapsed | 25509 | +| total_timesteps | 35538944 | +| train/ | | +| approx_kl | 0.013709266 | +| clip_fraction | 0.331 | +| clip_range | 0.0661 | +| entropy_loss | -6.01 | +| explained_variance | 0.216 | +| learning_rate | 4.16e-05 | +| loss | -0.0313 | +| n_updates | 85228 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000196 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1393 | +| iterations | 17354 | +| time_elapsed | 25511 | +| total_timesteps | 35540992 | +| train/ | | +| approx_kl | 0.014697776 | +| clip_fraction | 0.387 | +| clip_range | 0.0661 | +| entropy_loss | -6.11 | +| explained_variance | -0.155 | +| learning_rate | 4.16e-05 | +| loss | -0.0287 | +| n_updates | 85232 | +| policy_gradient_loss | -0.0229 | +| value_loss | 6.99e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1393 | +| iterations | 17355 | +| time_elapsed | 25512 | +| total_timesteps | 35543040 | +| train/ | | +| approx_kl | 0.014509765 | +| clip_fraction | 0.348 | +| clip_range | 0.0661 | +| entropy_loss | -5.9 | +| explained_variance | 0.364 | +| learning_rate | 4.16e-05 | +| loss | -0.0315 | +| n_updates | 85236 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000163 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1393 | +| iterations | 17356 | +| time_elapsed | 25514 | +| total_timesteps | 35545088 | +| train/ | | +| approx_kl | 0.011125011 | +| clip_fraction | 0.304 | +| clip_range | 0.0661 | +| entropy_loss | -5.96 | +| explained_variance | 0.419 | +| learning_rate | 4.16e-05 | +| loss | -0.0297 | +| n_updates | 85240 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000236 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1393 | +| iterations | 17357 | +| time_elapsed | 25515 | +| total_timesteps | 35547136 | +| train/ | | +| approx_kl | 0.01052502 | +| clip_fraction | 0.291 | +| clip_range | 0.0661 | +| entropy_loss | -5.94 | +| explained_variance | 0.46 | +| learning_rate | 4.16e-05 | +| loss | -0.0253 | +| n_updates | 85244 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000213 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1393 | +| iterations | 17358 | +| time_elapsed | 25517 | +| total_timesteps | 35549184 | +| train/ | | +| approx_kl | 0.014142141 | +| clip_fraction | 0.33 | +| clip_range | 0.0661 | +| entropy_loss | -6.03 | +| explained_variance | 0.547 | +| learning_rate | 4.16e-05 | +| loss | -0.0316 | +| n_updates | 85248 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.00011 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1393 | +| iterations | 17359 | +| time_elapsed | 25518 | +| total_timesteps | 35551232 | +| train/ | | +| approx_kl | 0.013509741 | +| clip_fraction | 0.344 | +| clip_range | 0.0661 | +| entropy_loss | -6.35 | +| explained_variance | 0.223 | +| learning_rate | 4.16e-05 | +| loss | -0.0334 | +| n_updates | 85252 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000218 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1393 | +| iterations | 17360 | +| time_elapsed | 25520 | +| total_timesteps | 35553280 | +| train/ | | +| approx_kl | 0.012871876 | +| clip_fraction | 0.34 | +| clip_range | 0.0661 | +| entropy_loss | -6.34 | +| explained_variance | 0.0359 | +| learning_rate | 4.16e-05 | +| loss | -0.0299 | +| n_updates | 85256 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000134 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1393 | +| iterations | 17361 | +| time_elapsed | 25521 | +| total_timesteps | 35555328 | +| train/ | | +| approx_kl | 0.012676547 | +| clip_fraction | 0.329 | +| clip_range | 0.0661 | +| entropy_loss | -5.59 | +| explained_variance | 0.581 | +| learning_rate | 4.16e-05 | +| loss | -0.0208 | +| n_updates | 85260 | +| policy_gradient_loss | -0.0156 | +| value_loss | 8.87e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1393 | +| iterations | 17362 | +| time_elapsed | 25523 | +| total_timesteps | 35557376 | +| train/ | | +| approx_kl | 0.00940231 | +| clip_fraction | 0.319 | +| clip_range | 0.0661 | +| entropy_loss | -5.46 | +| explained_variance | 0.489 | +| learning_rate | 4.16e-05 | +| loss | -0.0243 | +| n_updates | 85264 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000191 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1393 | +| iterations | 17363 | +| time_elapsed | 25524 | +| total_timesteps | 35559424 | +| train/ | | +| approx_kl | 0.007813487 | +| clip_fraction | 0.286 | +| clip_range | 0.0661 | +| entropy_loss | -5.99 | +| explained_variance | 0.545 | +| learning_rate | 4.16e-05 | +| loss | -0.0191 | +| n_updates | 85268 | +| policy_gradient_loss | -0.0145 | +| value_loss | 0.000156 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1393 | +| iterations | 17364 | +| time_elapsed | 25526 | +| total_timesteps | 35561472 | +| train/ | | +| approx_kl | 0.016298067 | +| clip_fraction | 0.32 | +| clip_range | 0.0661 | +| entropy_loss | -6.07 | +| explained_variance | 0.553 | +| learning_rate | 4.16e-05 | +| loss | -0.0338 | +| n_updates | 85272 | +| policy_gradient_loss | -0.0198 | +| value_loss | 5.88e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1393 | +| iterations | 17365 | +| time_elapsed | 25528 | +| total_timesteps | 35563520 | +| train/ | | +| approx_kl | 0.011559399 | +| clip_fraction | 0.328 | +| clip_range | 0.0661 | +| entropy_loss | -5.79 | +| explained_variance | 0.442 | +| learning_rate | 4.16e-05 | +| loss | -0.0258 | +| n_updates | 85276 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000238 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1393 | +| iterations | 17366 | +| time_elapsed | 25529 | +| total_timesteps | 35565568 | +| train/ | | +| approx_kl | 0.012622192 | +| clip_fraction | 0.334 | +| clip_range | 0.0661 | +| entropy_loss | -5.98 | +| explained_variance | 0.52 | +| learning_rate | 4.16e-05 | +| loss | -0.0308 | +| n_updates | 85280 | +| policy_gradient_loss | -0.0198 | +| value_loss | 7.61e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1393 | +| iterations | 17367 | +| time_elapsed | 25531 | +| total_timesteps | 35567616 | +| train/ | | +| approx_kl | 0.014833048 | +| clip_fraction | 0.333 | +| clip_range | 0.0661 | +| entropy_loss | -5.97 | +| explained_variance | 0.595 | +| learning_rate | 4.16e-05 | +| loss | -0.024 | +| n_updates | 85284 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000171 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1393 | +| iterations | 17368 | +| time_elapsed | 25532 | +| total_timesteps | 35569664 | +| train/ | | +| approx_kl | 0.013315241 | +| clip_fraction | 0.321 | +| clip_range | 0.0661 | +| entropy_loss | -6.63 | +| explained_variance | 0.419 | +| learning_rate | 4.16e-05 | +| loss | -0.0256 | +| n_updates | 85288 | +| policy_gradient_loss | -0.017 | +| value_loss | 9.31e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1393 | +| iterations | 17369 | +| time_elapsed | 25534 | +| total_timesteps | 35571712 | +| train/ | | +| approx_kl | 0.010725695 | +| clip_fraction | 0.308 | +| clip_range | 0.0661 | +| entropy_loss | -6.1 | +| explained_variance | 0.389 | +| learning_rate | 4.16e-05 | +| loss | -0.0276 | +| n_updates | 85292 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000335 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1393 | +| iterations | 17370 | +| time_elapsed | 25535 | +| total_timesteps | 35573760 | +| train/ | | +| approx_kl | 0.011183215 | +| clip_fraction | 0.329 | +| clip_range | 0.0661 | +| entropy_loss | -6.45 | +| explained_variance | 0.237 | +| learning_rate | 4.16e-05 | +| loss | -0.0293 | +| n_updates | 85296 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000111 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1393 | +| iterations | 17371 | +| time_elapsed | 25537 | +| total_timesteps | 35575808 | +| train/ | | +| approx_kl | 0.011502967 | +| clip_fraction | 0.323 | +| clip_range | 0.0661 | +| entropy_loss | -6.38 | +| explained_variance | 0.195 | +| learning_rate | 4.16e-05 | +| loss | -0.0269 | +| n_updates | 85300 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000124 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1393 | +| iterations | 17372 | +| time_elapsed | 25538 | +| total_timesteps | 35577856 | +| train/ | | +| approx_kl | 0.012751833 | +| clip_fraction | 0.332 | +| clip_range | 0.0661 | +| entropy_loss | -5.85 | +| explained_variance | 0.779 | +| learning_rate | 4.16e-05 | +| loss | -0.0262 | +| n_updates | 85304 | +| policy_gradient_loss | -0.0186 | +| value_loss | 8.15e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1393 | +| iterations | 17373 | +| time_elapsed | 25540 | +| total_timesteps | 35579904 | +| train/ | | +| approx_kl | 0.011539627 | +| clip_fraction | 0.31 | +| clip_range | 0.0661 | +| entropy_loss | -5.71 | +| explained_variance | 0.484 | +| learning_rate | 4.16e-05 | +| loss | -0.0184 | +| n_updates | 85308 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.000162 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1393 | +| iterations | 17374 | +| time_elapsed | 25541 | +| total_timesteps | 35581952 | +| train/ | | +| approx_kl | 0.009818685 | +| clip_fraction | 0.317 | +| clip_range | 0.0661 | +| entropy_loss | -6.15 | +| explained_variance | 0.177 | +| learning_rate | 4.15e-05 | +| loss | -0.0235 | +| n_updates | 85312 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000397 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1393 | +| iterations | 17375 | +| time_elapsed | 25543 | +| total_timesteps | 35584000 | +| train/ | | +| approx_kl | 0.012100974 | +| clip_fraction | 0.323 | +| clip_range | 0.0661 | +| entropy_loss | -6.15 | +| explained_variance | 0.523 | +| learning_rate | 4.15e-05 | +| loss | -0.0294 | +| n_updates | 85316 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000122 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1393 | +| iterations | 17376 | +| time_elapsed | 25545 | +| total_timesteps | 35586048 | +| train/ | | +| approx_kl | 0.010197566 | +| clip_fraction | 0.325 | +| clip_range | 0.0661 | +| entropy_loss | -6.18 | +| explained_variance | 0.367 | +| learning_rate | 4.15e-05 | +| loss | -0.0244 | +| n_updates | 85320 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.0002 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1393 | +| iterations | 17377 | +| time_elapsed | 25546 | +| total_timesteps | 35588096 | +| train/ | | +| approx_kl | 0.01214557 | +| clip_fraction | 0.34 | +| clip_range | 0.0661 | +| entropy_loss | -5.91 | +| explained_variance | 0.263 | +| learning_rate | 4.15e-05 | +| loss | -0.0214 | +| n_updates | 85324 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000259 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1393 | +| iterations | 17378 | +| time_elapsed | 25548 | +| total_timesteps | 35590144 | +| train/ | | +| approx_kl | 0.012805183 | +| clip_fraction | 0.335 | +| clip_range | 0.0661 | +| entropy_loss | -5.29 | +| explained_variance | 0.794 | +| learning_rate | 4.15e-05 | +| loss | -0.0294 | +| n_updates | 85328 | +| policy_gradient_loss | -0.0194 | +| value_loss | 9.03e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1393 | +| iterations | 17379 | +| time_elapsed | 25549 | +| total_timesteps | 35592192 | +| train/ | | +| approx_kl | 0.012735677 | +| clip_fraction | 0.346 | +| clip_range | 0.0661 | +| entropy_loss | -5.86 | +| explained_variance | 0.424 | +| learning_rate | 4.15e-05 | +| loss | -0.0311 | +| n_updates | 85332 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000112 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1393 | +| iterations | 17380 | +| time_elapsed | 25551 | +| total_timesteps | 35594240 | +| train/ | | +| approx_kl | 0.016237654 | +| clip_fraction | 0.348 | +| clip_range | 0.0661 | +| entropy_loss | -6.14 | +| explained_variance | 0.227 | +| learning_rate | 4.15e-05 | +| loss | -0.0273 | +| n_updates | 85336 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000121 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1393 | +| iterations | 17381 | +| time_elapsed | 25552 | +| total_timesteps | 35596288 | +| train/ | | +| approx_kl | 0.015253292 | +| clip_fraction | 0.367 | +| clip_range | 0.0661 | +| entropy_loss | -5.74 | +| explained_variance | 0.533 | +| learning_rate | 4.15e-05 | +| loss | -0.0307 | +| n_updates | 85340 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000124 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1393 | +| iterations | 17382 | +| time_elapsed | 25554 | +| total_timesteps | 35598336 | +| train/ | | +| approx_kl | 0.012891197 | +| clip_fraction | 0.345 | +| clip_range | 0.0661 | +| entropy_loss | -5.94 | +| explained_variance | 0.308 | +| learning_rate | 4.15e-05 | +| loss | -0.0234 | +| n_updates | 85344 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.00028 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1393 | +| iterations | 17383 | +| time_elapsed | 25555 | +| total_timesteps | 35600384 | +| train/ | | +| approx_kl | 0.011587301 | +| clip_fraction | 0.363 | +| clip_range | 0.0661 | +| entropy_loss | -6.03 | +| explained_variance | 0.247 | +| learning_rate | 4.15e-05 | +| loss | -0.0293 | +| n_updates | 85348 | +| policy_gradient_loss | -0.0186 | +| value_loss | 9.57e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1393 | +| iterations | 17384 | +| time_elapsed | 25557 | +| total_timesteps | 35602432 | +| train/ | | +| approx_kl | 0.009907139 | +| clip_fraction | 0.316 | +| clip_range | 0.0661 | +| entropy_loss | -5.71 | +| explained_variance | 0.39 | +| learning_rate | 4.15e-05 | +| loss | -0.0256 | +| n_updates | 85352 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000322 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1393 | +| iterations | 17385 | +| time_elapsed | 25558 | +| total_timesteps | 35604480 | +| train/ | | +| approx_kl | 0.012165232 | +| clip_fraction | 0.33 | +| clip_range | 0.0661 | +| entropy_loss | -5.49 | +| explained_variance | 0.417 | +| learning_rate | 4.15e-05 | +| loss | -0.0218 | +| n_updates | 85356 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000265 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1393 | +| iterations | 17386 | +| time_elapsed | 25560 | +| total_timesteps | 35606528 | +| train/ | | +| approx_kl | 0.010710714 | +| clip_fraction | 0.36 | +| clip_range | 0.0661 | +| entropy_loss | -6.26 | +| explained_variance | 0.264 | +| learning_rate | 4.15e-05 | +| loss | -0.0317 | +| n_updates | 85360 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000187 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1393 | +| iterations | 17387 | +| time_elapsed | 25561 | +| total_timesteps | 35608576 | +| train/ | | +| approx_kl | 0.010582339 | +| clip_fraction | 0.313 | +| clip_range | 0.0661 | +| entropy_loss | -6.51 | +| explained_variance | 0.188 | +| learning_rate | 4.15e-05 | +| loss | -0.0308 | +| n_updates | 85364 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000168 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1393 | +| iterations | 17388 | +| time_elapsed | 25563 | +| total_timesteps | 35610624 | +| train/ | | +| approx_kl | 0.010186398 | +| clip_fraction | 0.345 | +| clip_range | 0.0661 | +| entropy_loss | -6 | +| explained_variance | 0.197 | +| learning_rate | 4.15e-05 | +| loss | -0.0248 | +| n_updates | 85368 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000133 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1393 | +| iterations | 17389 | +| time_elapsed | 25564 | +| total_timesteps | 35612672 | +| train/ | | +| approx_kl | 0.01092119 | +| clip_fraction | 0.312 | +| clip_range | 0.0661 | +| entropy_loss | -6.19 | +| explained_variance | 0.214 | +| learning_rate | 4.15e-05 | +| loss | -0.0276 | +| n_updates | 85372 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000235 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1393 | +| iterations | 17390 | +| time_elapsed | 25566 | +| total_timesteps | 35614720 | +| train/ | | +| approx_kl | 0.015214038 | +| clip_fraction | 0.331 | +| clip_range | 0.0661 | +| entropy_loss | -5.46 | +| explained_variance | 0.566 | +| learning_rate | 4.15e-05 | +| loss | -0.0308 | +| n_updates | 85376 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000155 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1393 | +| iterations | 17391 | +| time_elapsed | 25567 | +| total_timesteps | 35616768 | +| train/ | | +| approx_kl | 0.010293862 | +| clip_fraction | 0.323 | +| clip_range | 0.0661 | +| entropy_loss | -4.94 | +| explained_variance | 0.588 | +| learning_rate | 4.15e-05 | +| loss | -0.0201 | +| n_updates | 85380 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.000217 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1393 | +| iterations | 17392 | +| time_elapsed | 25569 | +| total_timesteps | 35618816 | +| train/ | | +| approx_kl | 0.010541076 | +| clip_fraction | 0.309 | +| clip_range | 0.0661 | +| entropy_loss | -5.51 | +| explained_variance | 0.455 | +| learning_rate | 4.15e-05 | +| loss | -0.0271 | +| n_updates | 85384 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.000259 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1393 | +| iterations | 17393 | +| time_elapsed | 25570 | +| total_timesteps | 35620864 | +| train/ | | +| approx_kl | 0.012408538 | +| clip_fraction | 0.331 | +| clip_range | 0.0661 | +| entropy_loss | -5.57 | +| explained_variance | 0.373 | +| learning_rate | 4.15e-05 | +| loss | -0.0267 | +| n_updates | 85388 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000269 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1393 | +| iterations | 17394 | +| time_elapsed | 25572 | +| total_timesteps | 35622912 | +| train/ | | +| approx_kl | 0.011806615 | +| clip_fraction | 0.338 | +| clip_range | 0.0661 | +| entropy_loss | -5.99 | +| explained_variance | 0.301 | +| learning_rate | 4.15e-05 | +| loss | -0.0276 | +| n_updates | 85392 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000206 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1393 | +| iterations | 17395 | +| time_elapsed | 25574 | +| total_timesteps | 35624960 | +| train/ | | +| approx_kl | 0.009129261 | +| clip_fraction | 0.3 | +| clip_range | 0.0661 | +| entropy_loss | -6.46 | +| explained_variance | 0.234 | +| learning_rate | 4.15e-05 | +| loss | -0.027 | +| n_updates | 85396 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000102 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1393 | +| iterations | 17396 | +| time_elapsed | 25575 | +| total_timesteps | 35627008 | +| train/ | | +| approx_kl | 0.009348938 | +| clip_fraction | 0.328 | +| clip_range | 0.0661 | +| entropy_loss | -6.22 | +| explained_variance | 0.424 | +| learning_rate | 4.15e-05 | +| loss | -0.0293 | +| n_updates | 85400 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.0003 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1393 | +| iterations | 17397 | +| time_elapsed | 25577 | +| total_timesteps | 35629056 | +| train/ | | +| approx_kl | 0.008440373 | +| clip_fraction | 0.294 | +| clip_range | 0.0661 | +| entropy_loss | -5.93 | +| explained_variance | 0.218 | +| learning_rate | 4.15e-05 | +| loss | -0.0228 | +| n_updates | 85404 | +| policy_gradient_loss | -0.0145 | +| value_loss | 0.000355 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1392 | +| iterations | 17398 | +| time_elapsed | 25578 | +| total_timesteps | 35631104 | +| train/ | | +| approx_kl | 0.010124551 | +| clip_fraction | 0.312 | +| clip_range | 0.0661 | +| entropy_loss | -5.98 | +| explained_variance | 0.388 | +| learning_rate | 4.15e-05 | +| loss | -0.0285 | +| n_updates | 85408 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000335 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1392 | +| iterations | 17399 | +| time_elapsed | 25580 | +| total_timesteps | 35633152 | +| train/ | | +| approx_kl | 0.008221259 | +| clip_fraction | 0.293 | +| clip_range | 0.0661 | +| entropy_loss | -6.09 | +| explained_variance | 0.352 | +| learning_rate | 4.15e-05 | +| loss | -0.0334 | +| n_updates | 85412 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.000286 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1392 | +| iterations | 17400 | +| time_elapsed | 25581 | +| total_timesteps | 35635200 | +| train/ | | +| approx_kl | 0.009123831 | +| clip_fraction | 0.334 | +| clip_range | 0.0661 | +| entropy_loss | -6.16 | +| explained_variance | 0.461 | +| learning_rate | 4.15e-05 | +| loss | -0.0262 | +| n_updates | 85416 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.00019 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1392 | +| iterations | 17401 | +| time_elapsed | 25583 | +| total_timesteps | 35637248 | +| train/ | | +| approx_kl | 0.013013606 | +| clip_fraction | 0.364 | +| clip_range | 0.0661 | +| entropy_loss | -6.41 | +| explained_variance | 0.389 | +| learning_rate | 4.15e-05 | +| loss | -0.0262 | +| n_updates | 85420 | +| policy_gradient_loss | -0.021 | +| value_loss | 9.72e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.385 | +| time/ | | +| fps | 1392 | +| iterations | 17402 | +| time_elapsed | 25584 | +| total_timesteps | 35639296 | +| train/ | | +| approx_kl | 0.010724062 | +| clip_fraction | 0.329 | +| clip_range | 0.0661 | +| entropy_loss | -6.64 | +| explained_variance | -0.00916 | +| learning_rate | 4.15e-05 | +| loss | -0.0288 | +| n_updates | 85424 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000229 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1392 | +| iterations | 17403 | +| time_elapsed | 25586 | +| total_timesteps | 35641344 | +| train/ | | +| approx_kl | 0.011334333 | +| clip_fraction | 0.334 | +| clip_range | 0.0661 | +| entropy_loss | -6.96 | +| explained_variance | -0.047 | +| learning_rate | 4.15e-05 | +| loss | -0.031 | +| n_updates | 85428 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.00023 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1392 | +| iterations | 17404 | +| time_elapsed | 25587 | +| total_timesteps | 35643392 | +| train/ | | +| approx_kl | 0.010876995 | +| clip_fraction | 0.301 | +| clip_range | 0.0661 | +| entropy_loss | -5.93 | +| explained_variance | 0.61 | +| learning_rate | 4.15e-05 | +| loss | -0.0273 | +| n_updates | 85432 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000169 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1392 | +| iterations | 17405 | +| time_elapsed | 25589 | +| total_timesteps | 35645440 | +| train/ | | +| approx_kl | 0.010780046 | +| clip_fraction | 0.289 | +| clip_range | 0.0661 | +| entropy_loss | -5.77 | +| explained_variance | 0.276 | +| learning_rate | 4.15e-05 | +| loss | -0.0222 | +| n_updates | 85436 | +| policy_gradient_loss | -0.0137 | +| value_loss | 0.000313 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1392 | +| iterations | 17406 | +| time_elapsed | 25590 | +| total_timesteps | 35647488 | +| train/ | | +| approx_kl | 0.009723164 | +| clip_fraction | 0.314 | +| clip_range | 0.0661 | +| entropy_loss | -5.04 | +| explained_variance | 0.613 | +| learning_rate | 4.15e-05 | +| loss | -0.0253 | +| n_updates | 85440 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000209 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1392 | +| iterations | 17407 | +| time_elapsed | 25592 | +| total_timesteps | 35649536 | +| train/ | | +| approx_kl | 0.013188255 | +| clip_fraction | 0.348 | +| clip_range | 0.0661 | +| entropy_loss | -5.73 | +| explained_variance | 0.332 | +| learning_rate | 4.15e-05 | +| loss | -0.0275 | +| n_updates | 85444 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000323 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1392 | +| iterations | 17408 | +| time_elapsed | 25593 | +| total_timesteps | 35651584 | +| train/ | | +| approx_kl | 0.012215827 | +| clip_fraction | 0.349 | +| clip_range | 0.0661 | +| entropy_loss | -6.13 | +| explained_variance | 0.461 | +| learning_rate | 4.15e-05 | +| loss | -0.0363 | +| n_updates | 85448 | +| policy_gradient_loss | -0.0205 | +| value_loss | 8.25e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1392 | +| iterations | 17409 | +| time_elapsed | 25595 | +| total_timesteps | 35653632 | +| train/ | | +| approx_kl | 0.012953188 | +| clip_fraction | 0.353 | +| clip_range | 0.0661 | +| entropy_loss | -6.51 | +| explained_variance | 0.104 | +| learning_rate | 4.15e-05 | +| loss | -0.0333 | +| n_updates | 85452 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000141 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1392 | +| iterations | 17410 | +| time_elapsed | 25597 | +| total_timesteps | 35655680 | +| train/ | | +| approx_kl | 0.013032065 | +| clip_fraction | 0.335 | +| clip_range | 0.0661 | +| entropy_loss | -6.51 | +| explained_variance | 0.351 | +| learning_rate | 4.15e-05 | +| loss | -0.0295 | +| n_updates | 85456 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000133 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1392 | +| iterations | 17411 | +| time_elapsed | 25598 | +| total_timesteps | 35657728 | +| train/ | | +| approx_kl | 0.014115261 | +| clip_fraction | 0.336 | +| clip_range | 0.0661 | +| entropy_loss | -6.24 | +| explained_variance | 0.334 | +| learning_rate | 4.15e-05 | +| loss | -0.03 | +| n_updates | 85460 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000131 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1392 | +| iterations | 17412 | +| time_elapsed | 25600 | +| total_timesteps | 35659776 | +| train/ | | +| approx_kl | 0.010872596 | +| clip_fraction | 0.352 | +| clip_range | 0.0661 | +| entropy_loss | -6.1 | +| explained_variance | 0.243 | +| learning_rate | 4.15e-05 | +| loss | -0.0253 | +| n_updates | 85464 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000248 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1392 | +| iterations | 17413 | +| time_elapsed | 25601 | +| total_timesteps | 35661824 | +| train/ | | +| approx_kl | 0.023288408 | +| clip_fraction | 0.325 | +| clip_range | 0.0661 | +| entropy_loss | -6.16 | +| explained_variance | 0.182 | +| learning_rate | 4.15e-05 | +| loss | -0.0286 | +| n_updates | 85468 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000189 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1392 | +| iterations | 17414 | +| time_elapsed | 25603 | +| total_timesteps | 35663872 | +| train/ | | +| approx_kl | 0.01393656 | +| clip_fraction | 0.348 | +| clip_range | 0.0661 | +| entropy_loss | -6.03 | +| explained_variance | 0.481 | +| learning_rate | 4.15e-05 | +| loss | -0.0274 | +| n_updates | 85472 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000139 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1392 | +| iterations | 17415 | +| time_elapsed | 25604 | +| total_timesteps | 35665920 | +| train/ | | +| approx_kl | 0.013950156 | +| clip_fraction | 0.349 | +| clip_range | 0.0661 | +| entropy_loss | -5.98 | +| explained_variance | 0.524 | +| learning_rate | 4.15e-05 | +| loss | -0.0282 | +| n_updates | 85476 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000145 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1392 | +| iterations | 17416 | +| time_elapsed | 25606 | +| total_timesteps | 35667968 | +| train/ | | +| approx_kl | 0.013274719 | +| clip_fraction | 0.357 | +| clip_range | 0.0661 | +| entropy_loss | -5.89 | +| explained_variance | 0.322 | +| learning_rate | 4.15e-05 | +| loss | -0.0301 | +| n_updates | 85480 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000119 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1392 | +| iterations | 17417 | +| time_elapsed | 25607 | +| total_timesteps | 35670016 | +| train/ | | +| approx_kl | 0.015158372 | +| clip_fraction | 0.357 | +| clip_range | 0.0661 | +| entropy_loss | -6.14 | +| explained_variance | 0.49 | +| learning_rate | 4.15e-05 | +| loss | -0.0297 | +| n_updates | 85484 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000115 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1392 | +| iterations | 17418 | +| time_elapsed | 25609 | +| total_timesteps | 35672064 | +| train/ | | +| approx_kl | 0.014791992 | +| clip_fraction | 0.32 | +| clip_range | 0.0661 | +| entropy_loss | -5.66 | +| explained_variance | 0.705 | +| learning_rate | 4.15e-05 | +| loss | -0.0289 | +| n_updates | 85488 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000113 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1392 | +| iterations | 17419 | +| time_elapsed | 25610 | +| total_timesteps | 35674112 | +| train/ | | +| approx_kl | 0.009189474 | +| clip_fraction | 0.314 | +| clip_range | 0.0661 | +| entropy_loss | -5.82 | +| explained_variance | 0.284 | +| learning_rate | 4.15e-05 | +| loss | -0.026 | +| n_updates | 85492 | +| policy_gradient_loss | -0.0123 | +| value_loss | 0.000332 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1392 | +| iterations | 17420 | +| time_elapsed | 25612 | +| total_timesteps | 35676160 | +| train/ | | +| approx_kl | 0.01191479 | +| clip_fraction | 0.34 | +| clip_range | 0.0661 | +| entropy_loss | -6.19 | +| explained_variance | 0.177 | +| learning_rate | 4.15e-05 | +| loss | -0.0332 | +| n_updates | 85496 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000147 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1392 | +| iterations | 17421 | +| time_elapsed | 25614 | +| total_timesteps | 35678208 | +| train/ | | +| approx_kl | 0.0142294895 | +| clip_fraction | 0.339 | +| clip_range | 0.0661 | +| entropy_loss | -5.76 | +| explained_variance | 0.645 | +| learning_rate | 4.15e-05 | +| loss | -0.0303 | +| n_updates | 85500 | +| policy_gradient_loss | -0.0188 | +| value_loss | 8.88e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1392 | +| iterations | 17422 | +| time_elapsed | 25615 | +| total_timesteps | 35680256 | +| train/ | | +| approx_kl | 0.012926418 | +| clip_fraction | 0.321 | +| clip_range | 0.0661 | +| entropy_loss | -5.75 | +| explained_variance | 0.512 | +| learning_rate | 4.15e-05 | +| loss | -0.0218 | +| n_updates | 85504 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000215 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1392 | +| iterations | 17423 | +| time_elapsed | 25617 | +| total_timesteps | 35682304 | +| train/ | | +| approx_kl | 0.017248675 | +| clip_fraction | 0.358 | +| clip_range | 0.0661 | +| entropy_loss | -5.41 | +| explained_variance | 0.377 | +| learning_rate | 4.15e-05 | +| loss | -0.0313 | +| n_updates | 85508 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000143 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1392 | +| iterations | 17424 | +| time_elapsed | 25618 | +| total_timesteps | 35684352 | +| train/ | | +| approx_kl | 0.014823152 | +| clip_fraction | 0.346 | +| clip_range | 0.0661 | +| entropy_loss | -6.18 | +| explained_variance | 0.414 | +| learning_rate | 4.15e-05 | +| loss | -0.03 | +| n_updates | 85512 | +| policy_gradient_loss | -0.0192 | +| value_loss | 8.84e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.385 | +| time/ | | +| fps | 1392 | +| iterations | 17425 | +| time_elapsed | 25620 | +| total_timesteps | 35686400 | +| train/ | | +| approx_kl | 0.011647446 | +| clip_fraction | 0.301 | +| clip_range | 0.0661 | +| entropy_loss | -6.62 | +| explained_variance | 0.228 | +| learning_rate | 4.15e-05 | +| loss | -0.0305 | +| n_updates | 85516 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000185 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.385 | +| time/ | | +| fps | 1392 | +| iterations | 17426 | +| time_elapsed | 25621 | +| total_timesteps | 35688448 | +| train/ | | +| approx_kl | 0.012251051 | +| clip_fraction | 0.328 | +| clip_range | 0.0661 | +| entropy_loss | -6.04 | +| explained_variance | 0.283 | +| learning_rate | 4.15e-05 | +| loss | -0.0316 | +| n_updates | 85520 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000158 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1392 | +| iterations | 17427 | +| time_elapsed | 25623 | +| total_timesteps | 35690496 | +| train/ | | +| approx_kl | 0.014601721 | +| clip_fraction | 0.337 | +| clip_range | 0.0661 | +| entropy_loss | -6.15 | +| explained_variance | 0.0861 | +| learning_rate | 4.15e-05 | +| loss | -0.0269 | +| n_updates | 85524 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000189 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1392 | +| iterations | 17428 | +| time_elapsed | 25624 | +| total_timesteps | 35692544 | +| train/ | | +| approx_kl | 0.009953931 | +| clip_fraction | 0.314 | +| clip_range | 0.0661 | +| entropy_loss | -6.33 | +| explained_variance | 0.394 | +| learning_rate | 4.15e-05 | +| loss | -0.0133 | +| n_updates | 85528 | +| policy_gradient_loss | -0.0139 | +| value_loss | 0.000101 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.384 | +| time/ | | +| fps | 1392 | +| iterations | 17429 | +| time_elapsed | 25626 | +| total_timesteps | 35694592 | +| train/ | | +| approx_kl | 0.016342485 | +| clip_fraction | 0.312 | +| clip_range | 0.0661 | +| entropy_loss | -5.45 | +| explained_variance | 0.705 | +| learning_rate | 4.15e-05 | +| loss | -0.0244 | +| n_updates | 85532 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000112 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1392 | +| iterations | 17430 | +| time_elapsed | 25627 | +| total_timesteps | 35696640 | +| train/ | | +| approx_kl | 0.012642719 | +| clip_fraction | 0.311 | +| clip_range | 0.0661 | +| entropy_loss | -5.36 | +| explained_variance | 0.437 | +| learning_rate | 4.15e-05 | +| loss | -0.0268 | +| n_updates | 85536 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000342 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1392 | +| iterations | 17431 | +| time_elapsed | 25629 | +| total_timesteps | 35698688 | +| train/ | | +| approx_kl | 0.0129422825 | +| clip_fraction | 0.324 | +| clip_range | 0.0661 | +| entropy_loss | -5.1 | +| explained_variance | 0.444 | +| learning_rate | 4.15e-05 | +| loss | -0.0245 | +| n_updates | 85540 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000255 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1392 | +| iterations | 17432 | +| time_elapsed | 25631 | +| total_timesteps | 35700736 | +| train/ | | +| approx_kl | 0.011871986 | +| clip_fraction | 0.318 | +| clip_range | 0.0661 | +| entropy_loss | -5.28 | +| explained_variance | 0.457 | +| learning_rate | 4.15e-05 | +| loss | -0.0296 | +| n_updates | 85544 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000246 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1392 | +| iterations | 17433 | +| time_elapsed | 25632 | +| total_timesteps | 35702784 | +| train/ | | +| approx_kl | 0.01199889 | +| clip_fraction | 0.35 | +| clip_range | 0.0661 | +| entropy_loss | -6.36 | +| explained_variance | 0.264 | +| learning_rate | 4.15e-05 | +| loss | -0.0333 | +| n_updates | 85548 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000132 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1392 | +| iterations | 17434 | +| time_elapsed | 25634 | +| total_timesteps | 35704832 | +| train/ | | +| approx_kl | 0.011173665 | +| clip_fraction | 0.356 | +| clip_range | 0.0661 | +| entropy_loss | -6.66 | +| explained_variance | 0.302 | +| learning_rate | 4.15e-05 | +| loss | -0.0304 | +| n_updates | 85552 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000126 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.386 | +| time/ | | +| fps | 1392 | +| iterations | 17435 | +| time_elapsed | 25635 | +| total_timesteps | 35706880 | +| train/ | | +| approx_kl | 0.01142868 | +| clip_fraction | 0.326 | +| clip_range | 0.0661 | +| entropy_loss | -6.19 | +| explained_variance | 0.482 | +| learning_rate | 4.15e-05 | +| loss | -0.0257 | +| n_updates | 85556 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000135 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.384 | +| time/ | | +| fps | 1392 | +| iterations | 17436 | +| time_elapsed | 25637 | +| total_timesteps | 35708928 | +| train/ | | +| approx_kl | 0.012505889 | +| clip_fraction | 0.336 | +| clip_range | 0.0661 | +| entropy_loss | -6.09 | +| explained_variance | 0.239 | +| learning_rate | 4.15e-05 | +| loss | -0.0262 | +| n_updates | 85560 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000156 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.385 | +| time/ | | +| fps | 1392 | +| iterations | 17437 | +| time_elapsed | 25638 | +| total_timesteps | 35710976 | +| train/ | | +| approx_kl | 0.012365155 | +| clip_fraction | 0.342 | +| clip_range | 0.0661 | +| entropy_loss | -6.4 | +| explained_variance | 0.266 | +| learning_rate | 4.15e-05 | +| loss | -0.0232 | +| n_updates | 85564 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000205 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.384 | +| time/ | | +| fps | 1392 | +| iterations | 17438 | +| time_elapsed | 25640 | +| total_timesteps | 35713024 | +| train/ | | +| approx_kl | 0.012957755 | +| clip_fraction | 0.322 | +| clip_range | 0.0661 | +| entropy_loss | -6.18 | +| explained_variance | 0.572 | +| learning_rate | 4.15e-05 | +| loss | -0.0277 | +| n_updates | 85568 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000112 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.388 | +| time/ | | +| fps | 1392 | +| iterations | 17439 | +| time_elapsed | 25641 | +| total_timesteps | 35715072 | +| train/ | | +| approx_kl | 0.014798103 | +| clip_fraction | 0.356 | +| clip_range | 0.0661 | +| entropy_loss | -6.08 | +| explained_variance | -0.195 | +| learning_rate | 4.15e-05 | +| loss | -0.0321 | +| n_updates | 85572 | +| policy_gradient_loss | -0.0208 | +| value_loss | 8.07e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.389 | +| time/ | | +| fps | 1392 | +| iterations | 17440 | +| time_elapsed | 25643 | +| total_timesteps | 35717120 | +| train/ | | +| approx_kl | 0.014047761 | +| clip_fraction | 0.372 | +| clip_range | 0.0661 | +| entropy_loss | -5.64 | +| explained_variance | 0.698 | +| learning_rate | 4.15e-05 | +| loss | -0.0344 | +| n_updates | 85576 | +| policy_gradient_loss | -0.0202 | +| value_loss | 9.24e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.393 | +| time/ | | +| fps | 1392 | +| iterations | 17441 | +| time_elapsed | 25644 | +| total_timesteps | 35719168 | +| train/ | | +| approx_kl | 0.014223495 | +| clip_fraction | 0.368 | +| clip_range | 0.0661 | +| entropy_loss | -5.63 | +| explained_variance | 0.503 | +| learning_rate | 4.15e-05 | +| loss | -0.0326 | +| n_updates | 85580 | +| policy_gradient_loss | -0.019 | +| value_loss | 8.26e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.396 | +| time/ | | +| fps | 1392 | +| iterations | 17442 | +| time_elapsed | 25646 | +| total_timesteps | 35721216 | +| train/ | | +| approx_kl | 0.010177693 | +| clip_fraction | 0.334 | +| clip_range | 0.0661 | +| entropy_loss | -6 | +| explained_variance | 0.589 | +| learning_rate | 4.15e-05 | +| loss | -0.0222 | +| n_updates | 85584 | +| policy_gradient_loss | -0.0164 | +| value_loss | 9.76e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.393 | +| time/ | | +| fps | 1392 | +| iterations | 17443 | +| time_elapsed | 25647 | +| total_timesteps | 35723264 | +| train/ | | +| approx_kl | 0.011005046 | +| clip_fraction | 0.305 | +| clip_range | 0.0661 | +| entropy_loss | -5.42 | +| explained_variance | 0.601 | +| learning_rate | 4.15e-05 | +| loss | -0.0262 | +| n_updates | 85588 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000169 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.387 | +| time/ | | +| fps | 1392 | +| iterations | 17444 | +| time_elapsed | 25649 | +| total_timesteps | 35725312 | +| train/ | | +| approx_kl | 0.015919361 | +| clip_fraction | 0.354 | +| clip_range | 0.0661 | +| entropy_loss | -5.7 | +| explained_variance | 0.494 | +| learning_rate | 4.15e-05 | +| loss | -0.0288 | +| n_updates | 85592 | +| policy_gradient_loss | -0.0211 | +| value_loss | 6.87e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1392 | +| iterations | 17445 | +| time_elapsed | 25651 | +| total_timesteps | 35727360 | +| train/ | | +| approx_kl | 0.012782009 | +| clip_fraction | 0.339 | +| clip_range | 0.0661 | +| entropy_loss | -5.84 | +| explained_variance | 0.423 | +| learning_rate | 4.15e-05 | +| loss | -0.0286 | +| n_updates | 85596 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000138 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1392 | +| iterations | 17446 | +| time_elapsed | 25652 | +| total_timesteps | 35729408 | +| train/ | | +| approx_kl | 0.0113709 | +| clip_fraction | 0.341 | +| clip_range | 0.0661 | +| entropy_loss | -5.53 | +| explained_variance | 0.839 | +| learning_rate | 4.15e-05 | +| loss | -0.0325 | +| n_updates | 85600 | +| policy_gradient_loss | -0.021 | +| value_loss | 6.33e-05 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1392 | +| iterations | 17447 | +| time_elapsed | 25654 | +| total_timesteps | 35731456 | +| train/ | | +| approx_kl | 0.012797617 | +| clip_fraction | 0.338 | +| clip_range | 0.0661 | +| entropy_loss | -5.75 | +| explained_variance | 0.487 | +| learning_rate | 4.15e-05 | +| loss | -0.0346 | +| n_updates | 85604 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000118 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1392 | +| iterations | 17448 | +| time_elapsed | 25655 | +| total_timesteps | 35733504 | +| train/ | | +| approx_kl | 0.010764967 | +| clip_fraction | 0.333 | +| clip_range | 0.0661 | +| entropy_loss | -6.47 | +| explained_variance | 0.273 | +| learning_rate | 4.15e-05 | +| loss | -0.0304 | +| n_updates | 85608 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000249 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1392 | +| iterations | 17449 | +| time_elapsed | 25657 | +| total_timesteps | 35735552 | +| train/ | | +| approx_kl | 0.012193518 | +| clip_fraction | 0.347 | +| clip_range | 0.0661 | +| entropy_loss | -6.34 | +| explained_variance | 0.545 | +| learning_rate | 4.15e-05 | +| loss | -0.0296 | +| n_updates | 85612 | +| policy_gradient_loss | -0.019 | +| value_loss | 7.85e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1392 | +| iterations | 17450 | +| time_elapsed | 25658 | +| total_timesteps | 35737600 | +| train/ | | +| approx_kl | 0.010086706 | +| clip_fraction | 0.313 | +| clip_range | 0.0661 | +| entropy_loss | -6.04 | +| explained_variance | 0.578 | +| learning_rate | 4.15e-05 | +| loss | -0.0221 | +| n_updates | 85616 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.00016 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1392 | +| iterations | 17451 | +| time_elapsed | 25660 | +| total_timesteps | 35739648 | +| train/ | | +| approx_kl | 0.010035204 | +| clip_fraction | 0.311 | +| clip_range | 0.0661 | +| entropy_loss | -6.14 | +| explained_variance | 0.196 | +| learning_rate | 4.15e-05 | +| loss | -0.0229 | +| n_updates | 85620 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000209 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1392 | +| iterations | 17452 | +| time_elapsed | 25661 | +| total_timesteps | 35741696 | +| train/ | | +| approx_kl | 0.010962075 | +| clip_fraction | 0.331 | +| clip_range | 0.0661 | +| entropy_loss | -6.55 | +| explained_variance | 0.517 | +| learning_rate | 4.15e-05 | +| loss | -0.0329 | +| n_updates | 85624 | +| policy_gradient_loss | -0.0188 | +| value_loss | 7.82e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1392 | +| iterations | 17453 | +| time_elapsed | 25663 | +| total_timesteps | 35743744 | +| train/ | | +| approx_kl | 0.01284905 | +| clip_fraction | 0.323 | +| clip_range | 0.0661 | +| entropy_loss | -5.9 | +| explained_variance | 0.201 | +| learning_rate | 4.15e-05 | +| loss | -0.0237 | +| n_updates | 85628 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000399 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1392 | +| iterations | 17454 | +| time_elapsed | 25664 | +| total_timesteps | 35745792 | +| train/ | | +| approx_kl | 0.01494537 | +| clip_fraction | 0.38 | +| clip_range | 0.0661 | +| entropy_loss | -5.76 | +| explained_variance | 0.306 | +| learning_rate | 4.15e-05 | +| loss | -0.0304 | +| n_updates | 85632 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000123 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1392 | +| iterations | 17455 | +| time_elapsed | 25666 | +| total_timesteps | 35747840 | +| train/ | | +| approx_kl | 0.014044235 | +| clip_fraction | 0.37 | +| clip_range | 0.0661 | +| entropy_loss | -5.97 | +| explained_variance | 0.7 | +| learning_rate | 4.15e-05 | +| loss | -0.0396 | +| n_updates | 85636 | +| policy_gradient_loss | -0.023 | +| value_loss | 5.2e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1392 | +| iterations | 17456 | +| time_elapsed | 25667 | +| total_timesteps | 35749888 | +| train/ | | +| approx_kl | 0.014791437 | +| clip_fraction | 0.364 | +| clip_range | 0.0661 | +| entropy_loss | -5.56 | +| explained_variance | 0.75 | +| learning_rate | 4.15e-05 | +| loss | -0.0285 | +| n_updates | 85640 | +| policy_gradient_loss | -0.0209 | +| value_loss | 4.63e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1392 | +| iterations | 17457 | +| time_elapsed | 25669 | +| total_timesteps | 35751936 | +| train/ | | +| approx_kl | 0.016204229 | +| clip_fraction | 0.316 | +| clip_range | 0.0661 | +| entropy_loss | -4.83 | +| explained_variance | 0.543 | +| learning_rate | 4.15e-05 | +| loss | -0.0218 | +| n_updates | 85644 | +| policy_gradient_loss | -0.0137 | +| value_loss | 0.000188 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1392 | +| iterations | 17458 | +| time_elapsed | 25671 | +| total_timesteps | 35753984 | +| train/ | | +| approx_kl | 0.014767323 | +| clip_fraction | 0.359 | +| clip_range | 0.0661 | +| entropy_loss | -5.4 | +| explained_variance | 0.693 | +| learning_rate | 4.15e-05 | +| loss | -0.0296 | +| n_updates | 85648 | +| policy_gradient_loss | -0.0194 | +| value_loss | 6.95e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1392 | +| iterations | 17459 | +| time_elapsed | 25672 | +| total_timesteps | 35756032 | +| train/ | | +| approx_kl | 0.011361245 | +| clip_fraction | 0.314 | +| clip_range | 0.0661 | +| entropy_loss | -6.7 | +| explained_variance | -0.0372 | +| learning_rate | 4.15e-05 | +| loss | -0.0268 | +| n_updates | 85652 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000173 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1392 | +| iterations | 17460 | +| time_elapsed | 25674 | +| total_timesteps | 35758080 | +| train/ | | +| approx_kl | 0.009455586 | +| clip_fraction | 0.322 | +| clip_range | 0.0661 | +| entropy_loss | -6.6 | +| explained_variance | 0.23 | +| learning_rate | 4.15e-05 | +| loss | -0.0258 | +| n_updates | 85656 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000202 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1392 | +| iterations | 17461 | +| time_elapsed | 25675 | +| total_timesteps | 35760128 | +| train/ | | +| approx_kl | 0.014298857 | +| clip_fraction | 0.314 | +| clip_range | 0.0661 | +| entropy_loss | -6.02 | +| explained_variance | 0.35 | +| learning_rate | 4.15e-05 | +| loss | -0.0267 | +| n_updates | 85660 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000109 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1392 | +| iterations | 17462 | +| time_elapsed | 25677 | +| total_timesteps | 35762176 | +| train/ | | +| approx_kl | 0.011561732 | +| clip_fraction | 0.327 | +| clip_range | 0.0661 | +| entropy_loss | -5.66 | +| explained_variance | 0.244 | +| learning_rate | 4.15e-05 | +| loss | -0.0226 | +| n_updates | 85664 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000387 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1392 | +| iterations | 17463 | +| time_elapsed | 25678 | +| total_timesteps | 35764224 | +| train/ | | +| approx_kl | 0.016420897 | +| clip_fraction | 0.393 | +| clip_range | 0.0661 | +| entropy_loss | -6.04 | +| explained_variance | -0.206 | +| learning_rate | 4.15e-05 | +| loss | -0.0404 | +| n_updates | 85668 | +| policy_gradient_loss | -0.0222 | +| value_loss | 7.88e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1392 | +| iterations | 17464 | +| time_elapsed | 25680 | +| total_timesteps | 35766272 | +| train/ | | +| approx_kl | 0.012958925 | +| clip_fraction | 0.331 | +| clip_range | 0.0661 | +| entropy_loss | -6.24 | +| explained_variance | 0.491 | +| learning_rate | 4.15e-05 | +| loss | -0.0283 | +| n_updates | 85672 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000179 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1392 | +| iterations | 17465 | +| time_elapsed | 25681 | +| total_timesteps | 35768320 | +| train/ | | +| approx_kl | 0.013541544 | +| clip_fraction | 0.329 | +| clip_range | 0.0661 | +| entropy_loss | -5.12 | +| explained_variance | 0.649 | +| learning_rate | 4.15e-05 | +| loss | -0.0276 | +| n_updates | 85676 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000117 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1392 | +| iterations | 17466 | +| time_elapsed | 25683 | +| total_timesteps | 35770368 | +| train/ | | +| approx_kl | 0.0117102 | +| clip_fraction | 0.301 | +| clip_range | 0.0661 | +| entropy_loss | -5.85 | +| explained_variance | 0.344 | +| learning_rate | 4.15e-05 | +| loss | -0.0269 | +| n_updates | 85680 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000258 | +--------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1392 | +| iterations | 17467 | +| time_elapsed | 25684 | +| total_timesteps | 35772416 | +| train/ | | +| approx_kl | 0.0132164685 | +| clip_fraction | 0.342 | +| clip_range | 0.0661 | +| entropy_loss | -6.14 | +| explained_variance | 0.386 | +| learning_rate | 4.15e-05 | +| loss | -0.0339 | +| n_updates | 85684 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000129 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1392 | +| iterations | 17468 | +| time_elapsed | 25686 | +| total_timesteps | 35774464 | +| train/ | | +| approx_kl | 0.013759159 | +| clip_fraction | 0.33 | +| clip_range | 0.0661 | +| entropy_loss | -5.35 | +| explained_variance | 0.6 | +| learning_rate | 4.15e-05 | +| loss | -0.0274 | +| n_updates | 85688 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000201 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1392 | +| iterations | 17469 | +| time_elapsed | 25687 | +| total_timesteps | 35776512 | +| train/ | | +| approx_kl | 0.0130616445 | +| clip_fraction | 0.317 | +| clip_range | 0.0661 | +| entropy_loss | -5.42 | +| explained_variance | 0.389 | +| learning_rate | 4.15e-05 | +| loss | -0.0226 | +| n_updates | 85692 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000179 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1392 | +| iterations | 17470 | +| time_elapsed | 25689 | +| total_timesteps | 35778560 | +| train/ | | +| approx_kl | 0.014625035 | +| clip_fraction | 0.341 | +| clip_range | 0.0661 | +| entropy_loss | -5.36 | +| explained_variance | 0.639 | +| learning_rate | 4.15e-05 | +| loss | -0.0344 | +| n_updates | 85696 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000134 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1392 | +| iterations | 17471 | +| time_elapsed | 25691 | +| total_timesteps | 35780608 | +| train/ | | +| approx_kl | 0.015635218 | +| clip_fraction | 0.364 | +| clip_range | 0.0661 | +| entropy_loss | -5.67 | +| explained_variance | 0.473 | +| learning_rate | 4.15e-05 | +| loss | -0.0351 | +| n_updates | 85700 | +| policy_gradient_loss | -0.022 | +| value_loss | 9.46e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1392 | +| iterations | 17472 | +| time_elapsed | 25692 | +| total_timesteps | 35782656 | +| train/ | | +| approx_kl | 0.013582984 | +| clip_fraction | 0.335 | +| clip_range | 0.0661 | +| entropy_loss | -6.23 | +| explained_variance | -0.041 | +| learning_rate | 4.15e-05 | +| loss | -0.0263 | +| n_updates | 85704 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000121 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1392 | +| iterations | 17473 | +| time_elapsed | 25694 | +| total_timesteps | 35784704 | +| train/ | | +| approx_kl | 0.009734746 | +| clip_fraction | 0.301 | +| clip_range | 0.0661 | +| entropy_loss | -6.01 | +| explained_variance | 0.527 | +| learning_rate | 4.15e-05 | +| loss | -0.0219 | +| n_updates | 85708 | +| policy_gradient_loss | -0.0148 | +| value_loss | 0.000191 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1392 | +| iterations | 17474 | +| time_elapsed | 25695 | +| total_timesteps | 35786752 | +| train/ | | +| approx_kl | 0.014845526 | +| clip_fraction | 0.359 | +| clip_range | 0.0661 | +| entropy_loss | -5.41 | +| explained_variance | 0.634 | +| learning_rate | 4.15e-05 | +| loss | -0.0271 | +| n_updates | 85712 | +| policy_gradient_loss | -0.0195 | +| value_loss | 7.06e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1392 | +| iterations | 17475 | +| time_elapsed | 25697 | +| total_timesteps | 35788800 | +| train/ | | +| approx_kl | 0.013760686 | +| clip_fraction | 0.289 | +| clip_range | 0.0661 | +| entropy_loss | -6.05 | +| explained_variance | 0.255 | +| learning_rate | 4.15e-05 | +| loss | -0.0264 | +| n_updates | 85716 | +| policy_gradient_loss | -0.0148 | +| value_loss | 0.000271 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1392 | +| iterations | 17476 | +| time_elapsed | 25698 | +| total_timesteps | 35790848 | +| train/ | | +| approx_kl | 0.011778658 | +| clip_fraction | 0.325 | +| clip_range | 0.0661 | +| entropy_loss | -5.68 | +| explained_variance | 0.454 | +| learning_rate | 4.15e-05 | +| loss | -0.0299 | +| n_updates | 85720 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000132 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1392 | +| iterations | 17477 | +| time_elapsed | 25700 | +| total_timesteps | 35792896 | +| train/ | | +| approx_kl | 0.013205023 | +| clip_fraction | 0.328 | +| clip_range | 0.0661 | +| entropy_loss | -5.98 | +| explained_variance | 0.3 | +| learning_rate | 4.15e-05 | +| loss | -0.0372 | +| n_updates | 85724 | +| policy_gradient_loss | -0.021 | +| value_loss | 9.03e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1392 | +| iterations | 17478 | +| time_elapsed | 25701 | +| total_timesteps | 35794944 | +| train/ | | +| approx_kl | 0.011057012 | +| clip_fraction | 0.314 | +| clip_range | 0.0661 | +| entropy_loss | -6.44 | +| explained_variance | 0.2 | +| learning_rate | 4.15e-05 | +| loss | -0.0291 | +| n_updates | 85728 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000294 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1392 | +| iterations | 17479 | +| time_elapsed | 25703 | +| total_timesteps | 35796992 | +| train/ | | +| approx_kl | 0.012553621 | +| clip_fraction | 0.337 | +| clip_range | 0.0661 | +| entropy_loss | -5.64 | +| explained_variance | 0.728 | +| learning_rate | 4.15e-05 | +| loss | -0.0341 | +| n_updates | 85732 | +| policy_gradient_loss | -0.021 | +| value_loss | 7.66e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1392 | +| iterations | 17480 | +| time_elapsed | 25704 | +| total_timesteps | 35799040 | +| train/ | | +| approx_kl | 0.013106875 | +| clip_fraction | 0.366 | +| clip_range | 0.0661 | +| entropy_loss | -6.06 | +| explained_variance | 0.477 | +| learning_rate | 4.15e-05 | +| loss | -0.0349 | +| n_updates | 85736 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000101 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1392 | +| iterations | 17481 | +| time_elapsed | 25706 | +| total_timesteps | 35801088 | +| train/ | | +| approx_kl | 0.012393031 | +| clip_fraction | 0.342 | +| clip_range | 0.0661 | +| entropy_loss | -6.22 | +| explained_variance | 0.257 | +| learning_rate | 4.15e-05 | +| loss | -0.0232 | +| n_updates | 85740 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000185 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1392 | +| iterations | 17482 | +| time_elapsed | 25707 | +| total_timesteps | 35803136 | +| train/ | | +| approx_kl | 0.009992495 | +| clip_fraction | 0.301 | +| clip_range | 0.066 | +| entropy_loss | -5.97 | +| explained_variance | 0.589 | +| learning_rate | 4.15e-05 | +| loss | -0.0245 | +| n_updates | 85744 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000219 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1392 | +| iterations | 17483 | +| time_elapsed | 25709 | +| total_timesteps | 35805184 | +| train/ | | +| approx_kl | 0.010062856 | +| clip_fraction | 0.298 | +| clip_range | 0.066 | +| entropy_loss | -5.15 | +| explained_variance | 0.215 | +| learning_rate | 4.15e-05 | +| loss | -0.0197 | +| n_updates | 85748 | +| policy_gradient_loss | -0.0148 | +| value_loss | 0.000345 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1392 | +| iterations | 17484 | +| time_elapsed | 25710 | +| total_timesteps | 35807232 | +| train/ | | +| approx_kl | 0.014857406 | +| clip_fraction | 0.355 | +| clip_range | 0.066 | +| entropy_loss | -5.32 | +| explained_variance | 0.476 | +| learning_rate | 4.15e-05 | +| loss | -0.0286 | +| n_updates | 85752 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000163 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1392 | +| iterations | 17485 | +| time_elapsed | 25712 | +| total_timesteps | 35809280 | +| train/ | | +| approx_kl | 0.013166144 | +| clip_fraction | 0.348 | +| clip_range | 0.066 | +| entropy_loss | -6.45 | +| explained_variance | 0.094 | +| learning_rate | 4.15e-05 | +| loss | -0.031 | +| n_updates | 85756 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000157 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1392 | +| iterations | 17486 | +| time_elapsed | 25713 | +| total_timesteps | 35811328 | +| train/ | | +| approx_kl | 0.011825345 | +| clip_fraction | 0.326 | +| clip_range | 0.066 | +| entropy_loss | -6.31 | +| explained_variance | 0.353 | +| learning_rate | 4.15e-05 | +| loss | -0.0256 | +| n_updates | 85760 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000307 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1392 | +| iterations | 17487 | +| time_elapsed | 25715 | +| total_timesteps | 35813376 | +| train/ | | +| approx_kl | 0.012457401 | +| clip_fraction | 0.33 | +| clip_range | 0.066 | +| entropy_loss | -5.82 | +| explained_variance | 0.647 | +| learning_rate | 4.15e-05 | +| loss | -0.0311 | +| n_updates | 85764 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000105 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1392 | +| iterations | 17488 | +| time_elapsed | 25716 | +| total_timesteps | 35815424 | +| train/ | | +| approx_kl | 0.013398687 | +| clip_fraction | 0.338 | +| clip_range | 0.066 | +| entropy_loss | -6.13 | +| explained_variance | 0.122 | +| learning_rate | 4.15e-05 | +| loss | -0.0328 | +| n_updates | 85768 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000122 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1392 | +| iterations | 17489 | +| time_elapsed | 25718 | +| total_timesteps | 35817472 | +| train/ | | +| approx_kl | 0.013835885 | +| clip_fraction | 0.327 | +| clip_range | 0.066 | +| entropy_loss | -5.62 | +| explained_variance | 0.531 | +| learning_rate | 4.15e-05 | +| loss | -0.0268 | +| n_updates | 85772 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.00014 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1392 | +| iterations | 17490 | +| time_elapsed | 25719 | +| total_timesteps | 35819520 | +| train/ | | +| approx_kl | 0.011981776 | +| clip_fraction | 0.32 | +| clip_range | 0.066 | +| entropy_loss | -5.58 | +| explained_variance | 0.54 | +| learning_rate | 4.15e-05 | +| loss | -0.0232 | +| n_updates | 85776 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000126 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1392 | +| iterations | 17491 | +| time_elapsed | 25721 | +| total_timesteps | 35821568 | +| train/ | | +| approx_kl | 0.0112325335 | +| clip_fraction | 0.323 | +| clip_range | 0.066 | +| entropy_loss | -5.87 | +| explained_variance | 0.315 | +| learning_rate | 4.15e-05 | +| loss | -0.0245 | +| n_updates | 85780 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000173 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1392 | +| iterations | 17492 | +| time_elapsed | 25722 | +| total_timesteps | 35823616 | +| train/ | | +| approx_kl | 0.0131348595 | +| clip_fraction | 0.34 | +| clip_range | 0.066 | +| entropy_loss | -5.37 | +| explained_variance | 0.664 | +| learning_rate | 4.15e-05 | +| loss | -0.0248 | +| n_updates | 85784 | +| policy_gradient_loss | -0.0187 | +| value_loss | 9.81e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1392 | +| iterations | 17493 | +| time_elapsed | 25724 | +| total_timesteps | 35825664 | +| train/ | | +| approx_kl | 0.012660969 | +| clip_fraction | 0.327 | +| clip_range | 0.066 | +| entropy_loss | -5.25 | +| explained_variance | 0.521 | +| learning_rate | 4.15e-05 | +| loss | -0.0227 | +| n_updates | 85788 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000192 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1392 | +| iterations | 17494 | +| time_elapsed | 25725 | +| total_timesteps | 35827712 | +| train/ | | +| approx_kl | 0.0142533025 | +| clip_fraction | 0.349 | +| clip_range | 0.066 | +| entropy_loss | -5.69 | +| explained_variance | 0.202 | +| learning_rate | 4.15e-05 | +| loss | -0.031 | +| n_updates | 85792 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000109 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.315 | +| time/ | | +| fps | 1392 | +| iterations | 17495 | +| time_elapsed | 25727 | +| total_timesteps | 35829760 | +| train/ | | +| approx_kl | 0.016972937 | +| clip_fraction | 0.357 | +| clip_range | 0.066 | +| entropy_loss | -6.33 | +| explained_variance | 0.0361 | +| learning_rate | 4.15e-05 | +| loss | -0.0319 | +| n_updates | 85796 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000114 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.315 | +| time/ | | +| fps | 1392 | +| iterations | 17496 | +| time_elapsed | 25728 | +| total_timesteps | 35831808 | +| train/ | | +| approx_kl | 0.012269443 | +| clip_fraction | 0.352 | +| clip_range | 0.066 | +| entropy_loss | -6.34 | +| explained_variance | 0.331 | +| learning_rate | 4.15e-05 | +| loss | -0.03 | +| n_updates | 85800 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000125 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1392 | +| iterations | 17497 | +| time_elapsed | 25730 | +| total_timesteps | 35833856 | +| train/ | | +| approx_kl | 0.011954133 | +| clip_fraction | 0.319 | +| clip_range | 0.066 | +| entropy_loss | -6.59 | +| explained_variance | -0.0211 | +| learning_rate | 4.15e-05 | +| loss | -0.0279 | +| n_updates | 85804 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.00014 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1392 | +| iterations | 17498 | +| time_elapsed | 25731 | +| total_timesteps | 35835904 | +| train/ | | +| approx_kl | 0.010692556 | +| clip_fraction | 0.316 | +| clip_range | 0.066 | +| entropy_loss | -6.16 | +| explained_variance | 0.568 | +| learning_rate | 4.15e-05 | +| loss | -0.031 | +| n_updates | 85808 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000153 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1392 | +| iterations | 17499 | +| time_elapsed | 25733 | +| total_timesteps | 35837952 | +| train/ | | +| approx_kl | 0.011513514 | +| clip_fraction | 0.327 | +| clip_range | 0.066 | +| entropy_loss | -5.59 | +| explained_variance | 0.511 | +| learning_rate | 4.15e-05 | +| loss | -0.0231 | +| n_updates | 85812 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000239 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1392 | +| iterations | 17500 | +| time_elapsed | 25734 | +| total_timesteps | 35840000 | +| train/ | | +| approx_kl | 0.011277204 | +| clip_fraction | 0.336 | +| clip_range | 0.066 | +| entropy_loss | -5.11 | +| explained_variance | 0.718 | +| learning_rate | 4.15e-05 | +| loss | -0.0277 | +| n_updates | 85816 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000108 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1392 | +| iterations | 17501 | +| time_elapsed | 25736 | +| total_timesteps | 35842048 | +| train/ | | +| approx_kl | 0.014292342 | +| clip_fraction | 0.354 | +| clip_range | 0.066 | +| entropy_loss | -5.36 | +| explained_variance | 0.478 | +| learning_rate | 4.15e-05 | +| loss | -0.0287 | +| n_updates | 85820 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000112 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1392 | +| iterations | 17502 | +| time_elapsed | 25738 | +| total_timesteps | 35844096 | +| train/ | | +| approx_kl | 0.015679508 | +| clip_fraction | 0.382 | +| clip_range | 0.066 | +| entropy_loss | -5.65 | +| explained_variance | 0.507 | +| learning_rate | 4.15e-05 | +| loss | -0.0295 | +| n_updates | 85824 | +| policy_gradient_loss | -0.0221 | +| value_loss | 6.7e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1392 | +| iterations | 17503 | +| time_elapsed | 25739 | +| total_timesteps | 35846144 | +| train/ | | +| approx_kl | 0.018205717 | +| clip_fraction | 0.369 | +| clip_range | 0.066 | +| entropy_loss | -5.99 | +| explained_variance | 0.523 | +| learning_rate | 4.15e-05 | +| loss | -0.0293 | +| n_updates | 85828 | +| policy_gradient_loss | -0.0202 | +| value_loss | 6.27e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1392 | +| iterations | 17504 | +| time_elapsed | 25741 | +| total_timesteps | 35848192 | +| train/ | | +| approx_kl | 0.017629148 | +| clip_fraction | 0.343 | +| clip_range | 0.066 | +| entropy_loss | -6.05 | +| explained_variance | 0.134 | +| learning_rate | 4.15e-05 | +| loss | -0.0271 | +| n_updates | 85832 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000139 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1392 | +| iterations | 17505 | +| time_elapsed | 25742 | +| total_timesteps | 35850240 | +| train/ | | +| approx_kl | 0.0138078015 | +| clip_fraction | 0.36 | +| clip_range | 0.066 | +| entropy_loss | -5.74 | +| explained_variance | 0.637 | +| learning_rate | 4.15e-05 | +| loss | -0.0308 | +| n_updates | 85836 | +| policy_gradient_loss | -0.0191 | +| value_loss | 6.39e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1392 | +| iterations | 17506 | +| time_elapsed | 25744 | +| total_timesteps | 35852288 | +| train/ | | +| approx_kl | 0.010351328 | +| clip_fraction | 0.307 | +| clip_range | 0.066 | +| entropy_loss | -6.27 | +| explained_variance | 0.353 | +| learning_rate | 4.15e-05 | +| loss | -0.0279 | +| n_updates | 85840 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000155 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1392 | +| iterations | 17507 | +| time_elapsed | 25745 | +| total_timesteps | 35854336 | +| train/ | | +| approx_kl | 0.014349226 | +| clip_fraction | 0.354 | +| clip_range | 0.066 | +| entropy_loss | -5.66 | +| explained_variance | 0.837 | +| learning_rate | 4.15e-05 | +| loss | -0.0223 | +| n_updates | 85844 | +| policy_gradient_loss | -0.0188 | +| value_loss | 6.71e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1392 | +| iterations | 17508 | +| time_elapsed | 25747 | +| total_timesteps | 35856384 | +| train/ | | +| approx_kl | 0.011054547 | +| clip_fraction | 0.313 | +| clip_range | 0.066 | +| entropy_loss | -5.36 | +| explained_variance | 0.373 | +| learning_rate | 4.15e-05 | +| loss | -0.0224 | +| n_updates | 85848 | +| policy_gradient_loss | -0.0165 | +| value_loss | 6.69e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1392 | +| iterations | 17509 | +| time_elapsed | 25748 | +| total_timesteps | 35858432 | +| train/ | | +| approx_kl | 0.013468862 | +| clip_fraction | 0.333 | +| clip_range | 0.066 | +| entropy_loss | -5.4 | +| explained_variance | 0.593 | +| learning_rate | 4.15e-05 | +| loss | -0.027 | +| n_updates | 85852 | +| policy_gradient_loss | -0.0157 | +| value_loss | 7.45e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1392 | +| iterations | 17510 | +| time_elapsed | 25749 | +| total_timesteps | 35860480 | +| train/ | | +| approx_kl | 0.012906561 | +| clip_fraction | 0.327 | +| clip_range | 0.066 | +| entropy_loss | -5.99 | +| explained_variance | 0.312 | +| learning_rate | 4.15e-05 | +| loss | -0.0262 | +| n_updates | 85856 | +| policy_gradient_loss | -0.0179 | +| value_loss | 8.61e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1392 | +| iterations | 17511 | +| time_elapsed | 25751 | +| total_timesteps | 35862528 | +| train/ | | +| approx_kl | 0.012792806 | +| clip_fraction | 0.334 | +| clip_range | 0.066 | +| entropy_loss | -5.92 | +| explained_variance | 0.387 | +| learning_rate | 4.15e-05 | +| loss | -0.0271 | +| n_updates | 85860 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.00019 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.304 | +| time/ | | +| fps | 1392 | +| iterations | 17512 | +| time_elapsed | 25753 | +| total_timesteps | 35864576 | +| train/ | | +| approx_kl | 0.011586413 | +| clip_fraction | 0.333 | +| clip_range | 0.066 | +| entropy_loss | -5.57 | +| explained_variance | 0.687 | +| learning_rate | 4.15e-05 | +| loss | -0.0253 | +| n_updates | 85864 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000113 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 1392 | +| iterations | 17513 | +| time_elapsed | 25754 | +| total_timesteps | 35866624 | +| train/ | | +| approx_kl | 0.008420443 | +| clip_fraction | 0.317 | +| clip_range | 0.066 | +| entropy_loss | -6.09 | +| explained_variance | 0.276 | +| learning_rate | 4.15e-05 | +| loss | -0.0264 | +| n_updates | 85868 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000183 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1392 | +| iterations | 17514 | +| time_elapsed | 25756 | +| total_timesteps | 35868672 | +| train/ | | +| approx_kl | 0.012968341 | +| clip_fraction | 0.321 | +| clip_range | 0.066 | +| entropy_loss | -5.9 | +| explained_variance | 0.482 | +| learning_rate | 4.15e-05 | +| loss | -0.0261 | +| n_updates | 85872 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000153 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1392 | +| iterations | 17515 | +| time_elapsed | 25757 | +| total_timesteps | 35870720 | +| train/ | | +| approx_kl | 0.0089760525 | +| clip_fraction | 0.297 | +| clip_range | 0.066 | +| entropy_loss | -5.73 | +| explained_variance | 0.246 | +| learning_rate | 4.15e-05 | +| loss | -0.024 | +| n_updates | 85876 | +| policy_gradient_loss | -0.0141 | +| value_loss | 0.000382 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1392 | +| iterations | 17516 | +| time_elapsed | 25759 | +| total_timesteps | 35872768 | +| train/ | | +| approx_kl | 0.012935272 | +| clip_fraction | 0.308 | +| clip_range | 0.066 | +| entropy_loss | -4.58 | +| explained_variance | 0.743 | +| learning_rate | 4.15e-05 | +| loss | -0.0291 | +| n_updates | 85880 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000128 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1392 | +| iterations | 17517 | +| time_elapsed | 25760 | +| total_timesteps | 35874816 | +| train/ | | +| approx_kl | 0.012816971 | +| clip_fraction | 0.336 | +| clip_range | 0.066 | +| entropy_loss | -5.71 | +| explained_variance | 0.328 | +| learning_rate | 4.15e-05 | +| loss | -0.0374 | +| n_updates | 85884 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000105 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1392 | +| iterations | 17518 | +| time_elapsed | 25762 | +| total_timesteps | 35876864 | +| train/ | | +| approx_kl | 0.011838343 | +| clip_fraction | 0.375 | +| clip_range | 0.066 | +| entropy_loss | -6.41 | +| explained_variance | -0.0223 | +| learning_rate | 4.15e-05 | +| loss | -0.0329 | +| n_updates | 85888 | +| policy_gradient_loss | -0.0203 | +| value_loss | 7.4e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1392 | +| iterations | 17519 | +| time_elapsed | 25763 | +| total_timesteps | 35878912 | +| train/ | | +| approx_kl | 0.012040008 | +| clip_fraction | 0.345 | +| clip_range | 0.066 | +| entropy_loss | -6.26 | +| explained_variance | 0.301 | +| learning_rate | 4.15e-05 | +| loss | -0.0307 | +| n_updates | 85892 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000212 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1392 | +| iterations | 17520 | +| time_elapsed | 25765 | +| total_timesteps | 35880960 | +| train/ | | +| approx_kl | 0.013586648 | +| clip_fraction | 0.377 | +| clip_range | 0.066 | +| entropy_loss | -6.39 | +| explained_variance | -0.257 | +| learning_rate | 4.15e-05 | +| loss | -0.0304 | +| n_updates | 85896 | +| policy_gradient_loss | -0.0205 | +| value_loss | 9.82e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 1392 | +| iterations | 17521 | +| time_elapsed | 25766 | +| total_timesteps | 35883008 | +| train/ | | +| approx_kl | 0.011428772 | +| clip_fraction | 0.298 | +| clip_range | 0.066 | +| entropy_loss | -6.1 | +| explained_variance | 0.372 | +| learning_rate | 4.15e-05 | +| loss | -0.025 | +| n_updates | 85900 | +| policy_gradient_loss | -0.0146 | +| value_loss | 0.000296 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.306 | +| time/ | | +| fps | 1392 | +| iterations | 17522 | +| time_elapsed | 25768 | +| total_timesteps | 35885056 | +| train/ | | +| approx_kl | 0.011487628 | +| clip_fraction | 0.335 | +| clip_range | 0.066 | +| entropy_loss | -6.13 | +| explained_variance | 0.591 | +| learning_rate | 4.15e-05 | +| loss | -0.0292 | +| n_updates | 85904 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000102 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1392 | +| iterations | 17523 | +| time_elapsed | 25770 | +| total_timesteps | 35887104 | +| train/ | | +| approx_kl | 0.0128508415 | +| clip_fraction | 0.325 | +| clip_range | 0.066 | +| entropy_loss | -5.68 | +| explained_variance | 0.475 | +| learning_rate | 4.15e-05 | +| loss | -0.0266 | +| n_updates | 85908 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000158 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1392 | +| iterations | 17524 | +| time_elapsed | 25771 | +| total_timesteps | 35889152 | +| train/ | | +| approx_kl | 0.012559823 | +| clip_fraction | 0.334 | +| clip_range | 0.066 | +| entropy_loss | -5.41 | +| explained_variance | 0.627 | +| learning_rate | 4.15e-05 | +| loss | -0.0298 | +| n_updates | 85912 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000131 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 1392 | +| iterations | 17525 | +| time_elapsed | 25773 | +| total_timesteps | 35891200 | +| train/ | | +| approx_kl | 0.0117691215 | +| clip_fraction | 0.32 | +| clip_range | 0.066 | +| entropy_loss | -5.7 | +| explained_variance | 0.794 | +| learning_rate | 4.15e-05 | +| loss | -0.0318 | +| n_updates | 85916 | +| policy_gradient_loss | -0.0198 | +| value_loss | 4.6e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 1392 | +| iterations | 17526 | +| time_elapsed | 25774 | +| total_timesteps | 35893248 | +| train/ | | +| approx_kl | 0.008175963 | +| clip_fraction | 0.303 | +| clip_range | 0.066 | +| entropy_loss | -5.78 | +| explained_variance | 0.396 | +| learning_rate | 4.15e-05 | +| loss | -0.0241 | +| n_updates | 85920 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000166 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.304 | +| time/ | | +| fps | 1392 | +| iterations | 17527 | +| time_elapsed | 25776 | +| total_timesteps | 35895296 | +| train/ | | +| approx_kl | 0.012353398 | +| clip_fraction | 0.372 | +| clip_range | 0.066 | +| entropy_loss | -6.11 | +| explained_variance | 0.63 | +| learning_rate | 4.15e-05 | +| loss | -0.0339 | +| n_updates | 85924 | +| policy_gradient_loss | -0.0229 | +| value_loss | 4.14e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 1392 | +| iterations | 17528 | +| time_elapsed | 25777 | +| total_timesteps | 35897344 | +| train/ | | +| approx_kl | 0.01258382 | +| clip_fraction | 0.314 | +| clip_range | 0.066 | +| entropy_loss | -6.43 | +| explained_variance | 0.319 | +| learning_rate | 4.15e-05 | +| loss | -0.0278 | +| n_updates | 85928 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000168 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 1392 | +| iterations | 17529 | +| time_elapsed | 25779 | +| total_timesteps | 35899392 | +| train/ | | +| approx_kl | 0.014891431 | +| clip_fraction | 0.333 | +| clip_range | 0.066 | +| entropy_loss | -5.51 | +| explained_variance | 0.469 | +| learning_rate | 4.15e-05 | +| loss | -0.0262 | +| n_updates | 85932 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000227 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1392 | +| iterations | 17530 | +| time_elapsed | 25780 | +| total_timesteps | 35901440 | +| train/ | | +| approx_kl | 0.015887009 | +| clip_fraction | 0.382 | +| clip_range | 0.066 | +| entropy_loss | -6.09 | +| explained_variance | -0.0463 | +| learning_rate | 4.15e-05 | +| loss | -0.0341 | +| n_updates | 85936 | +| policy_gradient_loss | -0.0234 | +| value_loss | 7.42e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 1392 | +| iterations | 17531 | +| time_elapsed | 25782 | +| total_timesteps | 35903488 | +| train/ | | +| approx_kl | 0.009992171 | +| clip_fraction | 0.302 | +| clip_range | 0.066 | +| entropy_loss | -6.38 | +| explained_variance | 0.136 | +| learning_rate | 4.15e-05 | +| loss | -0.0255 | +| n_updates | 85940 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000255 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1392 | +| iterations | 17532 | +| time_elapsed | 25783 | +| total_timesteps | 35905536 | +| train/ | | +| approx_kl | 0.011043921 | +| clip_fraction | 0.337 | +| clip_range | 0.066 | +| entropy_loss | -5.98 | +| explained_variance | 0.512 | +| learning_rate | 4.15e-05 | +| loss | -0.0253 | +| n_updates | 85944 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000151 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1392 | +| iterations | 17533 | +| time_elapsed | 25785 | +| total_timesteps | 35907584 | +| train/ | | +| approx_kl | 0.016354274 | +| clip_fraction | 0.304 | +| clip_range | 0.066 | +| entropy_loss | -6.05 | +| explained_variance | 0.342 | +| learning_rate | 4.15e-05 | +| loss | -0.0319 | +| n_updates | 85948 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000224 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1392 | +| iterations | 17534 | +| time_elapsed | 25786 | +| total_timesteps | 35909632 | +| train/ | | +| approx_kl | 0.013210079 | +| clip_fraction | 0.345 | +| clip_range | 0.066 | +| entropy_loss | -5.51 | +| explained_variance | 0.817 | +| learning_rate | 4.15e-05 | +| loss | -0.0328 | +| n_updates | 85952 | +| policy_gradient_loss | -0.0196 | +| value_loss | 6.39e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.306 | +| time/ | | +| fps | 1392 | +| iterations | 17535 | +| time_elapsed | 25788 | +| total_timesteps | 35911680 | +| train/ | | +| approx_kl | 0.013238819 | +| clip_fraction | 0.327 | +| clip_range | 0.066 | +| entropy_loss | -5.19 | +| explained_variance | 0.398 | +| learning_rate | 4.15e-05 | +| loss | -0.0232 | +| n_updates | 85956 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000191 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.306 | +| time/ | | +| fps | 1392 | +| iterations | 17536 | +| time_elapsed | 25789 | +| total_timesteps | 35913728 | +| train/ | | +| approx_kl | 0.013100289 | +| clip_fraction | 0.337 | +| clip_range | 0.066 | +| entropy_loss | -5.62 | +| explained_variance | 0.453 | +| learning_rate | 4.15e-05 | +| loss | -0.0159 | +| n_updates | 85960 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000155 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.302 | +| time/ | | +| fps | 1392 | +| iterations | 17537 | +| time_elapsed | 25791 | +| total_timesteps | 35915776 | +| train/ | | +| approx_kl | 0.013982667 | +| clip_fraction | 0.363 | +| clip_range | 0.066 | +| entropy_loss | -6.1 | +| explained_variance | -0.155 | +| learning_rate | 4.15e-05 | +| loss | -0.028 | +| n_updates | 85964 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000144 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 1392 | +| iterations | 17538 | +| time_elapsed | 25793 | +| total_timesteps | 35917824 | +| train/ | | +| approx_kl | 0.0132345725 | +| clip_fraction | 0.357 | +| clip_range | 0.066 | +| entropy_loss | -5.88 | +| explained_variance | 0.255 | +| learning_rate | 4.15e-05 | +| loss | -0.0244 | +| n_updates | 85968 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000111 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 1392 | +| iterations | 17539 | +| time_elapsed | 25794 | +| total_timesteps | 35919872 | +| train/ | | +| approx_kl | 0.013685497 | +| clip_fraction | 0.321 | +| clip_range | 0.066 | +| entropy_loss | -5.09 | +| explained_variance | 0.584 | +| learning_rate | 4.15e-05 | +| loss | -0.0242 | +| n_updates | 85972 | +| policy_gradient_loss | -0.0146 | +| value_loss | 0.000141 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.3 | +| time/ | | +| fps | 1392 | +| iterations | 17540 | +| time_elapsed | 25796 | +| total_timesteps | 35921920 | +| train/ | | +| approx_kl | 0.011922152 | +| clip_fraction | 0.331 | +| clip_range | 0.066 | +| entropy_loss | -5.48 | +| explained_variance | 0.395 | +| learning_rate | 4.15e-05 | +| loss | -0.0292 | +| n_updates | 85976 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000123 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.3 | +| time/ | | +| fps | 1392 | +| iterations | 17541 | +| time_elapsed | 25797 | +| total_timesteps | 35923968 | +| train/ | | +| approx_kl | 0.010083962 | +| clip_fraction | 0.318 | +| clip_range | 0.066 | +| entropy_loss | -5.61 | +| explained_variance | 0.623 | +| learning_rate | 4.15e-05 | +| loss | -0.0268 | +| n_updates | 85980 | +| policy_gradient_loss | -0.0161 | +| value_loss | 8.36e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.298 | +| time/ | | +| fps | 1392 | +| iterations | 17542 | +| time_elapsed | 25799 | +| total_timesteps | 35926016 | +| train/ | | +| approx_kl | 0.011867588 | +| clip_fraction | 0.328 | +| clip_range | 0.066 | +| entropy_loss | -6.27 | +| explained_variance | 0.13 | +| learning_rate | 4.15e-05 | +| loss | -0.0257 | +| n_updates | 85984 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000176 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 1392 | +| iterations | 17543 | +| time_elapsed | 25800 | +| total_timesteps | 35928064 | +| train/ | | +| approx_kl | 0.014062259 | +| clip_fraction | 0.324 | +| clip_range | 0.066 | +| entropy_loss | -5.94 | +| explained_variance | 0.498 | +| learning_rate | 4.15e-05 | +| loss | -0.0253 | +| n_updates | 85988 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000183 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 1392 | +| iterations | 17544 | +| time_elapsed | 25802 | +| total_timesteps | 35930112 | +| train/ | | +| approx_kl | 0.00861367 | +| clip_fraction | 0.303 | +| clip_range | 0.066 | +| entropy_loss | -6 | +| explained_variance | 0.41 | +| learning_rate | 4.15e-05 | +| loss | -0.0221 | +| n_updates | 85992 | +| policy_gradient_loss | -0.0138 | +| value_loss | 0.000153 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 1392 | +| iterations | 17545 | +| time_elapsed | 25803 | +| total_timesteps | 35932160 | +| train/ | | +| approx_kl | 0.011674756 | +| clip_fraction | 0.356 | +| clip_range | 0.066 | +| entropy_loss | -6.17 | +| explained_variance | 0.611 | +| learning_rate | 4.15e-05 | +| loss | -0.0324 | +| n_updates | 85996 | +| policy_gradient_loss | -0.022 | +| value_loss | 4.94e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.3 | +| time/ | | +| fps | 1392 | +| iterations | 17546 | +| time_elapsed | 25805 | +| total_timesteps | 35934208 | +| train/ | | +| approx_kl | 0.011176536 | +| clip_fraction | 0.325 | +| clip_range | 0.066 | +| entropy_loss | -6.14 | +| explained_variance | 0.202 | +| learning_rate | 4.15e-05 | +| loss | -0.0245 | +| n_updates | 86000 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.00025 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 1392 | +| iterations | 17547 | +| time_elapsed | 25807 | +| total_timesteps | 35936256 | +| train/ | | +| approx_kl | 0.00821839 | +| clip_fraction | 0.287 | +| clip_range | 0.066 | +| entropy_loss | -5.17 | +| explained_variance | 0.544 | +| learning_rate | 4.15e-05 | +| loss | -0.022 | +| n_updates | 86004 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.00025 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 1392 | +| iterations | 17548 | +| time_elapsed | 25808 | +| total_timesteps | 35938304 | +| train/ | | +| approx_kl | 0.014017548 | +| clip_fraction | 0.344 | +| clip_range | 0.066 | +| entropy_loss | -5.08 | +| explained_variance | 0.457 | +| learning_rate | 4.15e-05 | +| loss | -0.0304 | +| n_updates | 86008 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000191 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 1392 | +| iterations | 17549 | +| time_elapsed | 25810 | +| total_timesteps | 35940352 | +| train/ | | +| approx_kl | 0.017165652 | +| clip_fraction | 0.366 | +| clip_range | 0.066 | +| entropy_loss | -5.32 | +| explained_variance | 0.471 | +| learning_rate | 4.15e-05 | +| loss | -0.0305 | +| n_updates | 86012 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.00016 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 1392 | +| iterations | 17550 | +| time_elapsed | 25811 | +| total_timesteps | 35942400 | +| train/ | | +| approx_kl | 0.01194666 | +| clip_fraction | 0.35 | +| clip_range | 0.066 | +| entropy_loss | -5.9 | +| explained_variance | 0.141 | +| learning_rate | 4.15e-05 | +| loss | -0.0335 | +| n_updates | 86016 | +| policy_gradient_loss | -0.0199 | +| value_loss | 8.83e-05 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 1392 | +| iterations | 17551 | +| time_elapsed | 25813 | +| total_timesteps | 35944448 | +| train/ | | +| approx_kl | 0.01915981 | +| clip_fraction | 0.39 | +| clip_range | 0.066 | +| entropy_loss | -5.94 | +| explained_variance | 0.645 | +| learning_rate | 4.15e-05 | +| loss | -0.0285 | +| n_updates | 86020 | +| policy_gradient_loss | -0.0216 | +| value_loss | 5.02e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.304 | +| time/ | | +| fps | 1392 | +| iterations | 17552 | +| time_elapsed | 25814 | +| total_timesteps | 35946496 | +| train/ | | +| approx_kl | 0.018900316 | +| clip_fraction | 0.346 | +| clip_range | 0.066 | +| entropy_loss | -6.25 | +| explained_variance | -0.0831 | +| learning_rate | 4.15e-05 | +| loss | -0.028 | +| n_updates | 86024 | +| policy_gradient_loss | -0.0178 | +| value_loss | 9.88e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1392 | +| iterations | 17553 | +| time_elapsed | 25816 | +| total_timesteps | 35948544 | +| train/ | | +| approx_kl | 0.0101838475 | +| clip_fraction | 0.338 | +| clip_range | 0.066 | +| entropy_loss | -6.54 | +| explained_variance | 0.101 | +| learning_rate | 4.15e-05 | +| loss | -0.0234 | +| n_updates | 86028 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000441 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1392 | +| iterations | 17554 | +| time_elapsed | 25817 | +| total_timesteps | 35950592 | +| train/ | | +| approx_kl | 0.012602894 | +| clip_fraction | 0.335 | +| clip_range | 0.066 | +| entropy_loss | -5.57 | +| explained_variance | 0.437 | +| learning_rate | 4.15e-05 | +| loss | -0.0251 | +| n_updates | 86032 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000252 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.306 | +| time/ | | +| fps | 1392 | +| iterations | 17555 | +| time_elapsed | 25819 | +| total_timesteps | 35952640 | +| train/ | | +| approx_kl | 0.015614715 | +| clip_fraction | 0.328 | +| clip_range | 0.066 | +| entropy_loss | -4.78 | +| explained_variance | 0.535 | +| learning_rate | 4.15e-05 | +| loss | -0.028 | +| n_updates | 86036 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000269 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1392 | +| iterations | 17556 | +| time_elapsed | 25820 | +| total_timesteps | 35954688 | +| train/ | | +| approx_kl | 0.015709877 | +| clip_fraction | 0.391 | +| clip_range | 0.066 | +| entropy_loss | -5.21 | +| explained_variance | 0.738 | +| learning_rate | 4.15e-05 | +| loss | -0.0334 | +| n_updates | 86040 | +| policy_gradient_loss | -0.0214 | +| value_loss | 8.05e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 1392 | +| iterations | 17557 | +| time_elapsed | 25822 | +| total_timesteps | 35956736 | +| train/ | | +| approx_kl | 0.011847867 | +| clip_fraction | 0.353 | +| clip_range | 0.066 | +| entropy_loss | -5.59 | +| explained_variance | 0.165 | +| learning_rate | 4.15e-05 | +| loss | -0.0283 | +| n_updates | 86044 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000306 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 1392 | +| iterations | 17558 | +| time_elapsed | 25823 | +| total_timesteps | 35958784 | +| train/ | | +| approx_kl | 0.015986318 | +| clip_fraction | 0.327 | +| clip_range | 0.066 | +| entropy_loss | -4.92 | +| explained_variance | 0.7 | +| learning_rate | 4.15e-05 | +| loss | -0.0301 | +| n_updates | 86048 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000143 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.302 | +| time/ | | +| fps | 1392 | +| iterations | 17559 | +| time_elapsed | 25825 | +| total_timesteps | 35960832 | +| train/ | | +| approx_kl | 0.0137586 | +| clip_fraction | 0.365 | +| clip_range | 0.066 | +| entropy_loss | -5.55 | +| explained_variance | -0.166 | +| learning_rate | 4.15e-05 | +| loss | -0.0369 | +| n_updates | 86052 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000143 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 1392 | +| iterations | 17560 | +| time_elapsed | 25826 | +| total_timesteps | 35962880 | +| train/ | | +| approx_kl | 0.013952102 | +| clip_fraction | 0.382 | +| clip_range | 0.066 | +| entropy_loss | -5.79 | +| explained_variance | -0.0601 | +| learning_rate | 4.15e-05 | +| loss | -0.0391 | +| n_updates | 86056 | +| policy_gradient_loss | -0.0232 | +| value_loss | 7.51e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 1392 | +| iterations | 17561 | +| time_elapsed | 25828 | +| total_timesteps | 35964928 | +| train/ | | +| approx_kl | 0.011144415 | +| clip_fraction | 0.313 | +| clip_range | 0.066 | +| entropy_loss | -6.17 | +| explained_variance | 0.361 | +| learning_rate | 4.15e-05 | +| loss | -0.0218 | +| n_updates | 86060 | +| policy_gradient_loss | -0.0146 | +| value_loss | 0.000257 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1392 | +| iterations | 17562 | +| time_elapsed | 25830 | +| total_timesteps | 35966976 | +| train/ | | +| approx_kl | 0.013580287 | +| clip_fraction | 0.331 | +| clip_range | 0.066 | +| entropy_loss | -6.27 | +| explained_variance | 0.196 | +| learning_rate | 4.15e-05 | +| loss | -0.0269 | +| n_updates | 86064 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000162 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1392 | +| iterations | 17563 | +| time_elapsed | 25831 | +| total_timesteps | 35969024 | +| train/ | | +| approx_kl | 0.015926238 | +| clip_fraction | 0.352 | +| clip_range | 0.066 | +| entropy_loss | -6.18 | +| explained_variance | 0.493 | +| learning_rate | 4.15e-05 | +| loss | -0.0288 | +| n_updates | 86068 | +| policy_gradient_loss | -0.0192 | +| value_loss | 9.49e-05 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1392 | +| iterations | 17564 | +| time_elapsed | 25833 | +| total_timesteps | 35971072 | +| train/ | | +| approx_kl | 0.0159954 | +| clip_fraction | 0.367 | +| clip_range | 0.066 | +| entropy_loss | -5.86 | +| explained_variance | 0.125 | +| learning_rate | 4.15e-05 | +| loss | -0.0291 | +| n_updates | 86072 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000142 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1392 | +| iterations | 17565 | +| time_elapsed | 25834 | +| total_timesteps | 35973120 | +| train/ | | +| approx_kl | 0.011834331 | +| clip_fraction | 0.35 | +| clip_range | 0.066 | +| entropy_loss | -5.44 | +| explained_variance | 0.453 | +| learning_rate | 4.15e-05 | +| loss | -0.0243 | +| n_updates | 86076 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000263 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1392 | +| iterations | 17566 | +| time_elapsed | 25836 | +| total_timesteps | 35975168 | +| train/ | | +| approx_kl | 0.013347292 | +| clip_fraction | 0.337 | +| clip_range | 0.066 | +| entropy_loss | -5.35 | +| explained_variance | 0.559 | +| learning_rate | 4.15e-05 | +| loss | -0.0265 | +| n_updates | 86080 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000172 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1392 | +| iterations | 17567 | +| time_elapsed | 25837 | +| total_timesteps | 35977216 | +| train/ | | +| approx_kl | 0.01341594 | +| clip_fraction | 0.352 | +| clip_range | 0.066 | +| entropy_loss | -5.15 | +| explained_variance | 0.673 | +| learning_rate | 4.15e-05 | +| loss | -0.03 | +| n_updates | 86084 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000118 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1392 | +| iterations | 17568 | +| time_elapsed | 25839 | +| total_timesteps | 35979264 | +| train/ | | +| approx_kl | 0.012479598 | +| clip_fraction | 0.365 | +| clip_range | 0.066 | +| entropy_loss | -5.65 | +| explained_variance | 0.16 | +| learning_rate | 4.15e-05 | +| loss | -0.0372 | +| n_updates | 86088 | +| policy_gradient_loss | -0.0194 | +| value_loss | 8.27e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1392 | +| iterations | 17569 | +| time_elapsed | 25840 | +| total_timesteps | 35981312 | +| train/ | | +| approx_kl | 0.015545825 | +| clip_fraction | 0.339 | +| clip_range | 0.066 | +| entropy_loss | -6.38 | +| explained_variance | 0.102 | +| learning_rate | 4.15e-05 | +| loss | -0.0292 | +| n_updates | 86092 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000151 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1392 | +| iterations | 17570 | +| time_elapsed | 25842 | +| total_timesteps | 35983360 | +| train/ | | +| approx_kl | 0.013952877 | +| clip_fraction | 0.35 | +| clip_range | 0.066 | +| entropy_loss | -6 | +| explained_variance | 0.435 | +| learning_rate | 4.15e-05 | +| loss | -0.0259 | +| n_updates | 86096 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.00016 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1392 | +| iterations | 17571 | +| time_elapsed | 25843 | +| total_timesteps | 35985408 | +| train/ | | +| approx_kl | 0.013539391 | +| clip_fraction | 0.342 | +| clip_range | 0.066 | +| entropy_loss | -5.99 | +| explained_variance | 0.25 | +| learning_rate | 4.15e-05 | +| loss | -0.0281 | +| n_updates | 86100 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000184 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1392 | +| iterations | 17572 | +| time_elapsed | 25845 | +| total_timesteps | 35987456 | +| train/ | | +| approx_kl | 0.014534968 | +| clip_fraction | 0.355 | +| clip_range | 0.066 | +| entropy_loss | -5.47 | +| explained_variance | 0.347 | +| learning_rate | 4.15e-05 | +| loss | -0.0248 | +| n_updates | 86104 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000151 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1392 | +| iterations | 17573 | +| time_elapsed | 25847 | +| total_timesteps | 35989504 | +| train/ | | +| approx_kl | 0.013176109 | +| clip_fraction | 0.362 | +| clip_range | 0.066 | +| entropy_loss | -6.07 | +| explained_variance | -0.096 | +| learning_rate | 4.15e-05 | +| loss | -0.0306 | +| n_updates | 86108 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000121 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1392 | +| iterations | 17574 | +| time_elapsed | 25848 | +| total_timesteps | 35991552 | +| train/ | | +| approx_kl | 0.009859837 | +| clip_fraction | 0.32 | +| clip_range | 0.066 | +| entropy_loss | -5.94 | +| explained_variance | 0.566 | +| learning_rate | 4.15e-05 | +| loss | -0.0239 | +| n_updates | 86112 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000127 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1392 | +| iterations | 17575 | +| time_elapsed | 25850 | +| total_timesteps | 35993600 | +| train/ | | +| approx_kl | 0.01240412 | +| clip_fraction | 0.318 | +| clip_range | 0.066 | +| entropy_loss | -5.55 | +| explained_variance | 0.62 | +| learning_rate | 4.15e-05 | +| loss | -0.0257 | +| n_updates | 86116 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000119 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1392 | +| iterations | 17576 | +| time_elapsed | 25851 | +| total_timesteps | 35995648 | +| train/ | | +| approx_kl | 0.011576891 | +| clip_fraction | 0.301 | +| clip_range | 0.066 | +| entropy_loss | -5.36 | +| explained_variance | 0.507 | +| learning_rate | 4.15e-05 | +| loss | -0.0223 | +| n_updates | 86120 | +| policy_gradient_loss | -0.0132 | +| value_loss | 0.000238 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1392 | +| iterations | 17577 | +| time_elapsed | 25853 | +| total_timesteps | 35997696 | +| train/ | | +| approx_kl | 0.015175659 | +| clip_fraction | 0.366 | +| clip_range | 0.066 | +| entropy_loss | -5.62 | +| explained_variance | 0.257 | +| learning_rate | 4.15e-05 | +| loss | -0.0324 | +| n_updates | 86124 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000202 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1392 | +| iterations | 17578 | +| time_elapsed | 25854 | +| total_timesteps | 35999744 | +| train/ | | +| approx_kl | 0.011859531 | +| clip_fraction | 0.346 | +| clip_range | 0.066 | +| entropy_loss | -5.71 | +| explained_variance | 0.233 | +| learning_rate | 4.15e-05 | +| loss | -0.0304 | +| n_updates | 86128 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000175 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1392 | +| iterations | 17579 | +| time_elapsed | 25856 | +| total_timesteps | 36001792 | +| train/ | | +| approx_kl | 0.016218856 | +| clip_fraction | 0.34 | +| clip_range | 0.066 | +| entropy_loss | -5.41 | +| explained_variance | 0.506 | +| learning_rate | 4.15e-05 | +| loss | -0.0322 | +| n_updates | 86132 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000172 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1392 | +| iterations | 17580 | +| time_elapsed | 25857 | +| total_timesteps | 36003840 | +| train/ | | +| approx_kl | 0.014742523 | +| clip_fraction | 0.357 | +| clip_range | 0.066 | +| entropy_loss | -5.8 | +| explained_variance | 0.427 | +| learning_rate | 4.14e-05 | +| loss | -0.0319 | +| n_updates | 86136 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000109 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1392 | +| iterations | 17581 | +| time_elapsed | 25859 | +| total_timesteps | 36005888 | +| train/ | | +| approx_kl | 0.0114436885 | +| clip_fraction | 0.312 | +| clip_range | 0.066 | +| entropy_loss | -5.51 | +| explained_variance | 0.624 | +| learning_rate | 4.14e-05 | +| loss | -0.0235 | +| n_updates | 86140 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000171 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1392 | +| iterations | 17582 | +| time_elapsed | 25860 | +| total_timesteps | 36007936 | +| train/ | | +| approx_kl | 0.014190321 | +| clip_fraction | 0.32 | +| clip_range | 0.066 | +| entropy_loss | -5.39 | +| explained_variance | 0.469 | +| learning_rate | 4.14e-05 | +| loss | -0.0305 | +| n_updates | 86144 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000129 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1392 | +| iterations | 17583 | +| time_elapsed | 25862 | +| total_timesteps | 36009984 | +| train/ | | +| approx_kl | 0.013040276 | +| clip_fraction | 0.335 | +| clip_range | 0.066 | +| entropy_loss | -5.9 | +| explained_variance | 0.451 | +| learning_rate | 4.14e-05 | +| loss | -0.0318 | +| n_updates | 86148 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000106 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1392 | +| iterations | 17584 | +| time_elapsed | 25864 | +| total_timesteps | 36012032 | +| train/ | | +| approx_kl | 0.0136964135 | +| clip_fraction | 0.328 | +| clip_range | 0.066 | +| entropy_loss | -6.65 | +| explained_variance | -0.132 | +| learning_rate | 4.14e-05 | +| loss | -0.032 | +| n_updates | 86152 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000158 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1392 | +| iterations | 17585 | +| time_elapsed | 25865 | +| total_timesteps | 36014080 | +| train/ | | +| approx_kl | 0.012328271 | +| clip_fraction | 0.319 | +| clip_range | 0.066 | +| entropy_loss | -6.13 | +| explained_variance | 0.36 | +| learning_rate | 4.14e-05 | +| loss | -0.0299 | +| n_updates | 86156 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000165 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1392 | +| iterations | 17586 | +| time_elapsed | 25867 | +| total_timesteps | 36016128 | +| train/ | | +| approx_kl | 0.010256976 | +| clip_fraction | 0.305 | +| clip_range | 0.066 | +| entropy_loss | -5.33 | +| explained_variance | 0.534 | +| learning_rate | 4.14e-05 | +| loss | -0.0196 | +| n_updates | 86160 | +| policy_gradient_loss | -0.0139 | +| value_loss | 0.000202 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1392 | +| iterations | 17587 | +| time_elapsed | 25868 | +| total_timesteps | 36018176 | +| train/ | | +| approx_kl | 0.01546224 | +| clip_fraction | 0.377 | +| clip_range | 0.066 | +| entropy_loss | -5.83 | +| explained_variance | -0.089 | +| learning_rate | 4.14e-05 | +| loss | -0.0391 | +| n_updates | 86164 | +| policy_gradient_loss | -0.0217 | +| value_loss | 9e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1392 | +| iterations | 17588 | +| time_elapsed | 25870 | +| total_timesteps | 36020224 | +| train/ | | +| approx_kl | 0.016215941 | +| clip_fraction | 0.347 | +| clip_range | 0.066 | +| entropy_loss | -6 | +| explained_variance | 0.486 | +| learning_rate | 4.14e-05 | +| loss | -0.0315 | +| n_updates | 86168 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000108 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1392 | +| iterations | 17589 | +| time_elapsed | 25871 | +| total_timesteps | 36022272 | +| train/ | | +| approx_kl | 0.01222475 | +| clip_fraction | 0.34 | +| clip_range | 0.066 | +| entropy_loss | -5.03 | +| explained_variance | 0.646 | +| learning_rate | 4.14e-05 | +| loss | -0.0247 | +| n_updates | 86172 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000194 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1392 | +| iterations | 17590 | +| time_elapsed | 25873 | +| total_timesteps | 36024320 | +| train/ | | +| approx_kl | 0.012579248 | +| clip_fraction | 0.3 | +| clip_range | 0.066 | +| entropy_loss | -5.11 | +| explained_variance | 0.375 | +| learning_rate | 4.14e-05 | +| loss | -0.0192 | +| n_updates | 86176 | +| policy_gradient_loss | -0.012 | +| value_loss | 0.000347 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1392 | +| iterations | 17591 | +| time_elapsed | 25874 | +| total_timesteps | 36026368 | +| train/ | | +| approx_kl | 0.014160866 | +| clip_fraction | 0.353 | +| clip_range | 0.066 | +| entropy_loss | -5.5 | +| explained_variance | 0.385 | +| learning_rate | 4.14e-05 | +| loss | -0.0281 | +| n_updates | 86180 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000216 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1392 | +| iterations | 17592 | +| time_elapsed | 25876 | +| total_timesteps | 36028416 | +| train/ | | +| approx_kl | 0.016008833 | +| clip_fraction | 0.336 | +| clip_range | 0.066 | +| entropy_loss | -6.01 | +| explained_variance | 0.178 | +| learning_rate | 4.14e-05 | +| loss | -0.0315 | +| n_updates | 86184 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000204 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1392 | +| iterations | 17593 | +| time_elapsed | 25877 | +| total_timesteps | 36030464 | +| train/ | | +| approx_kl | 0.010268113 | +| clip_fraction | 0.355 | +| clip_range | 0.066 | +| entropy_loss | -6.44 | +| explained_variance | -0.0761 | +| learning_rate | 4.14e-05 | +| loss | -0.0323 | +| n_updates | 86188 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000209 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1392 | +| iterations | 17594 | +| time_elapsed | 25879 | +| total_timesteps | 36032512 | +| train/ | | +| approx_kl | 0.012227772 | +| clip_fraction | 0.329 | +| clip_range | 0.066 | +| entropy_loss | -6.42 | +| explained_variance | 0.149 | +| learning_rate | 4.14e-05 | +| loss | -0.0305 | +| n_updates | 86192 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000207 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1392 | +| iterations | 17595 | +| time_elapsed | 25880 | +| total_timesteps | 36034560 | +| train/ | | +| approx_kl | 0.012391865 | +| clip_fraction | 0.324 | +| clip_range | 0.066 | +| entropy_loss | -5.84 | +| explained_variance | 0.695 | +| learning_rate | 4.14e-05 | +| loss | -0.0229 | +| n_updates | 86196 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000124 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1392 | +| iterations | 17596 | +| time_elapsed | 25882 | +| total_timesteps | 36036608 | +| train/ | | +| approx_kl | 0.01407004 | +| clip_fraction | 0.341 | +| clip_range | 0.066 | +| entropy_loss | -5.5 | +| explained_variance | 0.535 | +| learning_rate | 4.14e-05 | +| loss | -0.0315 | +| n_updates | 86200 | +| policy_gradient_loss | -0.0201 | +| value_loss | 6.7e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1392 | +| iterations | 17597 | +| time_elapsed | 25883 | +| total_timesteps | 36038656 | +| train/ | | +| approx_kl | 0.012322294 | +| clip_fraction | 0.358 | +| clip_range | 0.066 | +| entropy_loss | -5.5 | +| explained_variance | 0.579 | +| learning_rate | 4.14e-05 | +| loss | -0.0296 | +| n_updates | 86204 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000117 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1392 | +| iterations | 17598 | +| time_elapsed | 25885 | +| total_timesteps | 36040704 | +| train/ | | +| approx_kl | 0.0152251255 | +| clip_fraction | 0.315 | +| clip_range | 0.066 | +| entropy_loss | -5.5 | +| explained_variance | 0.407 | +| learning_rate | 4.14e-05 | +| loss | -0.0269 | +| n_updates | 86208 | +| policy_gradient_loss | -0.0144 | +| value_loss | 0.000377 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1392 | +| iterations | 17599 | +| time_elapsed | 25886 | +| total_timesteps | 36042752 | +| train/ | | +| approx_kl | 0.011693225 | +| clip_fraction | 0.327 | +| clip_range | 0.066 | +| entropy_loss | -5.57 | +| explained_variance | 0.438 | +| learning_rate | 4.14e-05 | +| loss | -0.0225 | +| n_updates | 86212 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000133 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1392 | +| iterations | 17600 | +| time_elapsed | 25888 | +| total_timesteps | 36044800 | +| train/ | | +| approx_kl | 0.0119809285 | +| clip_fraction | 0.338 | +| clip_range | 0.066 | +| entropy_loss | -6.53 | +| explained_variance | 0.338 | +| learning_rate | 4.14e-05 | +| loss | -0.0304 | +| n_updates | 86216 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000122 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1392 | +| iterations | 17601 | +| time_elapsed | 25889 | +| total_timesteps | 36046848 | +| train/ | | +| approx_kl | 0.012820789 | +| clip_fraction | 0.331 | +| clip_range | 0.066 | +| entropy_loss | -6.46 | +| explained_variance | 0.218 | +| learning_rate | 4.14e-05 | +| loss | -0.0264 | +| n_updates | 86220 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000227 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1392 | +| iterations | 17602 | +| time_elapsed | 25891 | +| total_timesteps | 36048896 | +| train/ | | +| approx_kl | 0.009408286 | +| clip_fraction | 0.313 | +| clip_range | 0.066 | +| entropy_loss | -5.81 | +| explained_variance | 0.412 | +| learning_rate | 4.14e-05 | +| loss | -0.0251 | +| n_updates | 86224 | +| policy_gradient_loss | -0.0146 | +| value_loss | 0.00021 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1392 | +| iterations | 17603 | +| time_elapsed | 25892 | +| total_timesteps | 36050944 | +| train/ | | +| approx_kl | 0.011788214 | +| clip_fraction | 0.323 | +| clip_range | 0.066 | +| entropy_loss | -5.96 | +| explained_variance | 0.33 | +| learning_rate | 4.14e-05 | +| loss | -0.0211 | +| n_updates | 86228 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.00021 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1392 | +| iterations | 17604 | +| time_elapsed | 25894 | +| total_timesteps | 36052992 | +| train/ | | +| approx_kl | 0.010304589 | +| clip_fraction | 0.327 | +| clip_range | 0.066 | +| entropy_loss | -5.95 | +| explained_variance | 0.465 | +| learning_rate | 4.14e-05 | +| loss | -0.03 | +| n_updates | 86232 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000215 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1392 | +| iterations | 17605 | +| time_elapsed | 25895 | +| total_timesteps | 36055040 | +| train/ | | +| approx_kl | 0.012470985 | +| clip_fraction | 0.355 | +| clip_range | 0.066 | +| entropy_loss | -5.68 | +| explained_variance | 0.772 | +| learning_rate | 4.14e-05 | +| loss | -0.0335 | +| n_updates | 86236 | +| policy_gradient_loss | -0.0205 | +| value_loss | 5.17e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1392 | +| iterations | 17606 | +| time_elapsed | 25897 | +| total_timesteps | 36057088 | +| train/ | | +| approx_kl | 0.011112509 | +| clip_fraction | 0.344 | +| clip_range | 0.066 | +| entropy_loss | -6.36 | +| explained_variance | 0.115 | +| learning_rate | 4.14e-05 | +| loss | -0.033 | +| n_updates | 86240 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000112 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1392 | +| iterations | 17607 | +| time_elapsed | 25899 | +| total_timesteps | 36059136 | +| train/ | | +| approx_kl | 0.014180153 | +| clip_fraction | 0.342 | +| clip_range | 0.066 | +| entropy_loss | -5.4 | +| explained_variance | 0.796 | +| learning_rate | 4.14e-05 | +| loss | -0.0257 | +| n_updates | 86244 | +| policy_gradient_loss | -0.0169 | +| value_loss | 7.01e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1392 | +| iterations | 17608 | +| time_elapsed | 25900 | +| total_timesteps | 36061184 | +| train/ | | +| approx_kl | 0.013865555 | +| clip_fraction | 0.328 | +| clip_range | 0.066 | +| entropy_loss | -5.74 | +| explained_variance | 0.48 | +| learning_rate | 4.14e-05 | +| loss | -0.0325 | +| n_updates | 86248 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000114 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1392 | +| iterations | 17609 | +| time_elapsed | 25902 | +| total_timesteps | 36063232 | +| train/ | | +| approx_kl | 0.012354156 | +| clip_fraction | 0.324 | +| clip_range | 0.066 | +| entropy_loss | -5.35 | +| explained_variance | 0.49 | +| learning_rate | 4.14e-05 | +| loss | -0.0287 | +| n_updates | 86252 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000268 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1392 | +| iterations | 17610 | +| time_elapsed | 25903 | +| total_timesteps | 36065280 | +| train/ | | +| approx_kl | 0.011649534 | +| clip_fraction | 0.319 | +| clip_range | 0.066 | +| entropy_loss | -5.63 | +| explained_variance | 0.631 | +| learning_rate | 4.14e-05 | +| loss | -0.0249 | +| n_updates | 86256 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000151 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1392 | +| iterations | 17611 | +| time_elapsed | 25905 | +| total_timesteps | 36067328 | +| train/ | | +| approx_kl | 0.011449323 | +| clip_fraction | 0.34 | +| clip_range | 0.066 | +| entropy_loss | -5.39 | +| explained_variance | 0.24 | +| learning_rate | 4.14e-05 | +| loss | -0.0277 | +| n_updates | 86260 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000494 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1392 | +| iterations | 17612 | +| time_elapsed | 25906 | +| total_timesteps | 36069376 | +| train/ | | +| approx_kl | 0.011042736 | +| clip_fraction | 0.344 | +| clip_range | 0.066 | +| entropy_loss | -5.87 | +| explained_variance | 0.147 | +| learning_rate | 4.14e-05 | +| loss | -0.0347 | +| n_updates | 86264 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000122 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1392 | +| iterations | 17613 | +| time_elapsed | 25908 | +| total_timesteps | 36071424 | +| train/ | | +| approx_kl | 0.01079778 | +| clip_fraction | 0.326 | +| clip_range | 0.066 | +| entropy_loss | -6.25 | +| explained_variance | 0.226 | +| learning_rate | 4.14e-05 | +| loss | -0.0208 | +| n_updates | 86268 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000273 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1392 | +| iterations | 17614 | +| time_elapsed | 25909 | +| total_timesteps | 36073472 | +| train/ | | +| approx_kl | 0.012249091 | +| clip_fraction | 0.342 | +| clip_range | 0.066 | +| entropy_loss | -6.28 | +| explained_variance | 0.141 | +| learning_rate | 4.14e-05 | +| loss | -0.0263 | +| n_updates | 86272 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000239 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1392 | +| iterations | 17615 | +| time_elapsed | 25911 | +| total_timesteps | 36075520 | +| train/ | | +| approx_kl | 0.012001108 | +| clip_fraction | 0.34 | +| clip_range | 0.066 | +| entropy_loss | -5.95 | +| explained_variance | 0.173 | +| learning_rate | 4.14e-05 | +| loss | -0.0313 | +| n_updates | 86276 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.00015 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1392 | +| iterations | 17616 | +| time_elapsed | 25912 | +| total_timesteps | 36077568 | +| train/ | | +| approx_kl | 0.012213079 | +| clip_fraction | 0.334 | +| clip_range | 0.066 | +| entropy_loss | -5.97 | +| explained_variance | 0.475 | +| learning_rate | 4.14e-05 | +| loss | -0.0263 | +| n_updates | 86280 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000164 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1392 | +| iterations | 17617 | +| time_elapsed | 25914 | +| total_timesteps | 36079616 | +| train/ | | +| approx_kl | 0.0146619165 | +| clip_fraction | 0.336 | +| clip_range | 0.066 | +| entropy_loss | -5.95 | +| explained_variance | -0.119 | +| learning_rate | 4.14e-05 | +| loss | -0.0281 | +| n_updates | 86284 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000176 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1392 | +| iterations | 17618 | +| time_elapsed | 25915 | +| total_timesteps | 36081664 | +| train/ | | +| approx_kl | 0.018632801 | +| clip_fraction | 0.338 | +| clip_range | 0.066 | +| entropy_loss | -5.49 | +| explained_variance | 0.646 | +| learning_rate | 4.14e-05 | +| loss | -0.0309 | +| n_updates | 86288 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000151 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1392 | +| iterations | 17619 | +| time_elapsed | 25917 | +| total_timesteps | 36083712 | +| train/ | | +| approx_kl | 0.015709063 | +| clip_fraction | 0.372 | +| clip_range | 0.066 | +| entropy_loss | -5.46 | +| explained_variance | 0.624 | +| learning_rate | 4.14e-05 | +| loss | -0.0338 | +| n_updates | 86292 | +| policy_gradient_loss | -0.0201 | +| value_loss | 8.75e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1392 | +| iterations | 17620 | +| time_elapsed | 25918 | +| total_timesteps | 36085760 | +| train/ | | +| approx_kl | 0.015523729 | +| clip_fraction | 0.333 | +| clip_range | 0.066 | +| entropy_loss | -5.98 | +| explained_variance | 0.538 | +| learning_rate | 4.14e-05 | +| loss | -0.0246 | +| n_updates | 86296 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.000142 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1392 | +| iterations | 17621 | +| time_elapsed | 25920 | +| total_timesteps | 36087808 | +| train/ | | +| approx_kl | 0.012276623 | +| clip_fraction | 0.317 | +| clip_range | 0.066 | +| entropy_loss | -5.85 | +| explained_variance | 0.357 | +| learning_rate | 4.14e-05 | +| loss | -0.0283 | +| n_updates | 86300 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000153 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1392 | +| iterations | 17622 | +| time_elapsed | 25921 | +| total_timesteps | 36089856 | +| train/ | | +| approx_kl | 0.013215806 | +| clip_fraction | 0.368 | +| clip_range | 0.066 | +| entropy_loss | -5.64 | +| explained_variance | 0.71 | +| learning_rate | 4.14e-05 | +| loss | -0.0383 | +| n_updates | 86304 | +| policy_gradient_loss | -0.0214 | +| value_loss | 6.27e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1392 | +| iterations | 17623 | +| time_elapsed | 25923 | +| total_timesteps | 36091904 | +| train/ | | +| approx_kl | 0.013150694 | +| clip_fraction | 0.346 | +| clip_range | 0.066 | +| entropy_loss | -5.64 | +| explained_variance | 0.485 | +| learning_rate | 4.14e-05 | +| loss | -0.0268 | +| n_updates | 86308 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000241 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1392 | +| iterations | 17624 | +| time_elapsed | 25924 | +| total_timesteps | 36093952 | +| train/ | | +| approx_kl | 0.015918933 | +| clip_fraction | 0.328 | +| clip_range | 0.066 | +| entropy_loss | -5.5 | +| explained_variance | 0.347 | +| learning_rate | 4.14e-05 | +| loss | -0.0283 | +| n_updates | 86312 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.00016 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1392 | +| iterations | 17625 | +| time_elapsed | 25926 | +| total_timesteps | 36096000 | +| train/ | | +| approx_kl | 0.0134452535 | +| clip_fraction | 0.352 | +| clip_range | 0.066 | +| entropy_loss | -5.82 | +| explained_variance | 0.442 | +| learning_rate | 4.14e-05 | +| loss | -0.0265 | +| n_updates | 86316 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.00014 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1392 | +| iterations | 17626 | +| time_elapsed | 25927 | +| total_timesteps | 36098048 | +| train/ | | +| approx_kl | 0.013851546 | +| clip_fraction | 0.336 | +| clip_range | 0.066 | +| entropy_loss | -5.82 | +| explained_variance | 0.357 | +| learning_rate | 4.14e-05 | +| loss | -0.0319 | +| n_updates | 86320 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000121 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1392 | +| iterations | 17627 | +| time_elapsed | 25929 | +| total_timesteps | 36100096 | +| train/ | | +| approx_kl | 0.017495763 | +| clip_fraction | 0.349 | +| clip_range | 0.066 | +| entropy_loss | -6.13 | +| explained_variance | -0.261 | +| learning_rate | 4.14e-05 | +| loss | -0.0271 | +| n_updates | 86324 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.00014 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1392 | +| iterations | 17628 | +| time_elapsed | 25931 | +| total_timesteps | 36102144 | +| train/ | | +| approx_kl | 0.014729882 | +| clip_fraction | 0.336 | +| clip_range | 0.066 | +| entropy_loss | -5.8 | +| explained_variance | 0.523 | +| learning_rate | 4.14e-05 | +| loss | -0.0286 | +| n_updates | 86328 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000133 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1392 | +| iterations | 17629 | +| time_elapsed | 25932 | +| total_timesteps | 36104192 | +| train/ | | +| approx_kl | 0.013073951 | +| clip_fraction | 0.323 | +| clip_range | 0.066 | +| entropy_loss | -5.77 | +| explained_variance | 0.148 | +| learning_rate | 4.14e-05 | +| loss | -0.022 | +| n_updates | 86332 | +| policy_gradient_loss | -0.0132 | +| value_loss | 0.000233 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1392 | +| iterations | 17630 | +| time_elapsed | 25934 | +| total_timesteps | 36106240 | +| train/ | | +| approx_kl | 0.010770205 | +| clip_fraction | 0.33 | +| clip_range | 0.066 | +| entropy_loss | -5.57 | +| explained_variance | 0.436 | +| learning_rate | 4.14e-05 | +| loss | -0.0252 | +| n_updates | 86336 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000285 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1392 | +| iterations | 17631 | +| time_elapsed | 25935 | +| total_timesteps | 36108288 | +| train/ | | +| approx_kl | 0.0114932135 | +| clip_fraction | 0.32 | +| clip_range | 0.066 | +| entropy_loss | -5.56 | +| explained_variance | 0.485 | +| learning_rate | 4.14e-05 | +| loss | -0.0287 | +| n_updates | 86340 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000222 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1392 | +| iterations | 17632 | +| time_elapsed | 25937 | +| total_timesteps | 36110336 | +| train/ | | +| approx_kl | 0.012853695 | +| clip_fraction | 0.338 | +| clip_range | 0.066 | +| entropy_loss | -5.68 | +| explained_variance | 0.398 | +| learning_rate | 4.14e-05 | +| loss | -0.0263 | +| n_updates | 86344 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000162 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1392 | +| iterations | 17633 | +| time_elapsed | 25938 | +| total_timesteps | 36112384 | +| train/ | | +| approx_kl | 0.012158422 | +| clip_fraction | 0.356 | +| clip_range | 0.066 | +| entropy_loss | -5.81 | +| explained_variance | -0.071 | +| learning_rate | 4.14e-05 | +| loss | -0.0309 | +| n_updates | 86348 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000171 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1392 | +| iterations | 17634 | +| time_elapsed | 25940 | +| total_timesteps | 36114432 | +| train/ | | +| approx_kl | 0.012619619 | +| clip_fraction | 0.335 | +| clip_range | 0.066 | +| entropy_loss | -5.9 | +| explained_variance | 0.392 | +| learning_rate | 4.14e-05 | +| loss | -0.0202 | +| n_updates | 86352 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000245 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1392 | +| iterations | 17635 | +| time_elapsed | 25941 | +| total_timesteps | 36116480 | +| train/ | | +| approx_kl | 0.0111754965 | +| clip_fraction | 0.337 | +| clip_range | 0.066 | +| entropy_loss | -6.59 | +| explained_variance | -0.171 | +| learning_rate | 4.14e-05 | +| loss | -0.0275 | +| n_updates | 86356 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000148 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1392 | +| iterations | 17636 | +| time_elapsed | 25943 | +| total_timesteps | 36118528 | +| train/ | | +| approx_kl | 0.012239644 | +| clip_fraction | 0.325 | +| clip_range | 0.066 | +| entropy_loss | -6.08 | +| explained_variance | 0.551 | +| learning_rate | 4.14e-05 | +| loss | -0.0307 | +| n_updates | 86360 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000155 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1392 | +| iterations | 17637 | +| time_elapsed | 25944 | +| total_timesteps | 36120576 | +| train/ | | +| approx_kl | 0.01554428 | +| clip_fraction | 0.376 | +| clip_range | 0.066 | +| entropy_loss | -5.92 | +| explained_variance | -0.266 | +| learning_rate | 4.14e-05 | +| loss | -0.0336 | +| n_updates | 86364 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000109 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1392 | +| iterations | 17638 | +| time_elapsed | 25946 | +| total_timesteps | 36122624 | +| train/ | | +| approx_kl | 0.0097857565 | +| clip_fraction | 0.306 | +| clip_range | 0.066 | +| entropy_loss | -5.73 | +| explained_variance | 0.491 | +| learning_rate | 4.14e-05 | +| loss | -0.0226 | +| n_updates | 86368 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.000201 | +------------------------------------------ +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1392 | +| iterations | 17639 | +| time_elapsed | 25947 | +| total_timesteps | 36124672 | +| train/ | | +| approx_kl | 0.0114417 | +| clip_fraction | 0.31 | +| clip_range | 0.066 | +| entropy_loss | -6.01 | +| explained_variance | 0.364 | +| learning_rate | 4.14e-05 | +| loss | -0.0253 | +| n_updates | 86372 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000192 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1392 | +| iterations | 17640 | +| time_elapsed | 25949 | +| total_timesteps | 36126720 | +| train/ | | +| approx_kl | 0.010144204 | +| clip_fraction | 0.324 | +| clip_range | 0.066 | +| entropy_loss | -6.01 | +| explained_variance | 0.262 | +| learning_rate | 4.14e-05 | +| loss | -0.023 | +| n_updates | 86376 | +| policy_gradient_loss | -0.018 | +| value_loss | 7.99e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1392 | +| iterations | 17641 | +| time_elapsed | 25950 | +| total_timesteps | 36128768 | +| train/ | | +| approx_kl | 0.0115159685 | +| clip_fraction | 0.361 | +| clip_range | 0.066 | +| entropy_loss | -5.47 | +| explained_variance | 0.557 | +| learning_rate | 4.14e-05 | +| loss | -0.0325 | +| n_updates | 86380 | +| policy_gradient_loss | -0.0175 | +| value_loss | 9.27e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1392 | +| iterations | 17642 | +| time_elapsed | 25952 | +| total_timesteps | 36130816 | +| train/ | | +| approx_kl | 0.015838362 | +| clip_fraction | 0.338 | +| clip_range | 0.066 | +| entropy_loss | -6.29 | +| explained_variance | -0.123 | +| learning_rate | 4.14e-05 | +| loss | -0.0306 | +| n_updates | 86384 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000117 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1392 | +| iterations | 17643 | +| time_elapsed | 25953 | +| total_timesteps | 36132864 | +| train/ | | +| approx_kl | 0.010969197 | +| clip_fraction | 0.306 | +| clip_range | 0.066 | +| entropy_loss | -6.04 | +| explained_variance | 0.263 | +| learning_rate | 4.14e-05 | +| loss | -0.0278 | +| n_updates | 86388 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000249 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1392 | +| iterations | 17644 | +| time_elapsed | 25955 | +| total_timesteps | 36134912 | +| train/ | | +| approx_kl | 0.011469549 | +| clip_fraction | 0.342 | +| clip_range | 0.066 | +| entropy_loss | -5.81 | +| explained_variance | 0.507 | +| learning_rate | 4.14e-05 | +| loss | -0.0288 | +| n_updates | 86392 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.00012 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1392 | +| iterations | 17645 | +| time_elapsed | 25957 | +| total_timesteps | 36136960 | +| train/ | | +| approx_kl | 0.012400746 | +| clip_fraction | 0.339 | +| clip_range | 0.066 | +| entropy_loss | -5.94 | +| explained_variance | 0.0199 | +| learning_rate | 4.14e-05 | +| loss | -0.0281 | +| n_updates | 86396 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000184 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1392 | +| iterations | 17646 | +| time_elapsed | 25958 | +| total_timesteps | 36139008 | +| train/ | | +| approx_kl | 0.016925942 | +| clip_fraction | 0.333 | +| clip_range | 0.066 | +| entropy_loss | -5.94 | +| explained_variance | 0.325 | +| learning_rate | 4.14e-05 | +| loss | -0.0272 | +| n_updates | 86400 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000252 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1392 | +| iterations | 17647 | +| time_elapsed | 25960 | +| total_timesteps | 36141056 | +| train/ | | +| approx_kl | 0.012185197 | +| clip_fraction | 0.342 | +| clip_range | 0.066 | +| entropy_loss | -5.61 | +| explained_variance | 0.61 | +| learning_rate | 4.14e-05 | +| loss | -0.0337 | +| n_updates | 86404 | +| policy_gradient_loss | -0.0194 | +| value_loss | 7.6e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1392 | +| iterations | 17648 | +| time_elapsed | 25961 | +| total_timesteps | 36143104 | +| train/ | | +| approx_kl | 0.011829678 | +| clip_fraction | 0.328 | +| clip_range | 0.066 | +| entropy_loss | -5.83 | +| explained_variance | 0.331 | +| learning_rate | 4.14e-05 | +| loss | -0.0301 | +| n_updates | 86408 | +| policy_gradient_loss | -0.0146 | +| value_loss | 0.000217 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1392 | +| iterations | 17649 | +| time_elapsed | 25963 | +| total_timesteps | 36145152 | +| train/ | | +| approx_kl | 0.01032954 | +| clip_fraction | 0.319 | +| clip_range | 0.066 | +| entropy_loss | -6.13 | +| explained_variance | 0.328 | +| learning_rate | 4.14e-05 | +| loss | -0.028 | +| n_updates | 86412 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.00021 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1392 | +| iterations | 17650 | +| time_elapsed | 25964 | +| total_timesteps | 36147200 | +| train/ | | +| approx_kl | 0.0119924005 | +| clip_fraction | 0.308 | +| clip_range | 0.066 | +| entropy_loss | -6.21 | +| explained_variance | 0.185 | +| learning_rate | 4.14e-05 | +| loss | -0.0255 | +| n_updates | 86416 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000326 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1392 | +| iterations | 17651 | +| time_elapsed | 25966 | +| total_timesteps | 36149248 | +| train/ | | +| approx_kl | 0.010922868 | +| clip_fraction | 0.316 | +| clip_range | 0.066 | +| entropy_loss | -5.66 | +| explained_variance | 0.572 | +| learning_rate | 4.14e-05 | +| loss | -0.0318 | +| n_updates | 86420 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000151 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1392 | +| iterations | 17652 | +| time_elapsed | 25967 | +| total_timesteps | 36151296 | +| train/ | | +| approx_kl | 0.01653533 | +| clip_fraction | 0.347 | +| clip_range | 0.066 | +| entropy_loss | -6.05 | +| explained_variance | -0.139 | +| learning_rate | 4.14e-05 | +| loss | -0.0291 | +| n_updates | 86424 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000163 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1392 | +| iterations | 17653 | +| time_elapsed | 25969 | +| total_timesteps | 36153344 | +| train/ | | +| approx_kl | 0.013916745 | +| clip_fraction | 0.321 | +| clip_range | 0.066 | +| entropy_loss | -6.29 | +| explained_variance | 0.237 | +| learning_rate | 4.14e-05 | +| loss | -0.022 | +| n_updates | 86428 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000226 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1392 | +| iterations | 17654 | +| time_elapsed | 25970 | +| total_timesteps | 36155392 | +| train/ | | +| approx_kl | 0.01382079 | +| clip_fraction | 0.331 | +| clip_range | 0.066 | +| entropy_loss | -5.81 | +| explained_variance | 0.463 | +| learning_rate | 4.14e-05 | +| loss | -0.0351 | +| n_updates | 86432 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000129 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1392 | +| iterations | 17655 | +| time_elapsed | 25972 | +| total_timesteps | 36157440 | +| train/ | | +| approx_kl | 0.009062451 | +| clip_fraction | 0.294 | +| clip_range | 0.066 | +| entropy_loss | -5.93 | +| explained_variance | 0.538 | +| learning_rate | 4.14e-05 | +| loss | -0.0226 | +| n_updates | 86436 | +| policy_gradient_loss | -0.0145 | +| value_loss | 0.000218 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1392 | +| iterations | 17656 | +| time_elapsed | 25973 | +| total_timesteps | 36159488 | +| train/ | | +| approx_kl | 0.009496169 | +| clip_fraction | 0.294 | +| clip_range | 0.066 | +| entropy_loss | -5.96 | +| explained_variance | 0.462 | +| learning_rate | 4.14e-05 | +| loss | -0.0222 | +| n_updates | 86440 | +| policy_gradient_loss | -0.0147 | +| value_loss | 0.000181 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1392 | +| iterations | 17657 | +| time_elapsed | 25975 | +| total_timesteps | 36161536 | +| train/ | | +| approx_kl | 0.011389782 | +| clip_fraction | 0.333 | +| clip_range | 0.066 | +| entropy_loss | -5.85 | +| explained_variance | 0.574 | +| learning_rate | 4.14e-05 | +| loss | -0.0353 | +| n_updates | 86444 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.00011 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1392 | +| iterations | 17658 | +| time_elapsed | 25976 | +| total_timesteps | 36163584 | +| train/ | | +| approx_kl | 0.016507166 | +| clip_fraction | 0.342 | +| clip_range | 0.066 | +| entropy_loss | -6.4 | +| explained_variance | 0.22 | +| learning_rate | 4.14e-05 | +| loss | -0.0281 | +| n_updates | 86448 | +| policy_gradient_loss | -0.0183 | +| value_loss | 9.62e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1392 | +| iterations | 17659 | +| time_elapsed | 25978 | +| total_timesteps | 36165632 | +| train/ | | +| approx_kl | 0.012495708 | +| clip_fraction | 0.359 | +| clip_range | 0.066 | +| entropy_loss | -6.14 | +| explained_variance | 0.247 | +| learning_rate | 4.14e-05 | +| loss | -0.0341 | +| n_updates | 86452 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000176 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1392 | +| iterations | 17660 | +| time_elapsed | 25979 | +| total_timesteps | 36167680 | +| train/ | | +| approx_kl | 0.012634188 | +| clip_fraction | 0.331 | +| clip_range | 0.066 | +| entropy_loss | -6.29 | +| explained_variance | 0.204 | +| learning_rate | 4.14e-05 | +| loss | -0.0283 | +| n_updates | 86456 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000178 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1392 | +| iterations | 17661 | +| time_elapsed | 25981 | +| total_timesteps | 36169728 | +| train/ | | +| approx_kl | 0.011636252 | +| clip_fraction | 0.324 | +| clip_range | 0.066 | +| entropy_loss | -5.55 | +| explained_variance | 0.558 | +| learning_rate | 4.14e-05 | +| loss | -0.0235 | +| n_updates | 86460 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.00019 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1392 | +| iterations | 17662 | +| time_elapsed | 25983 | +| total_timesteps | 36171776 | +| train/ | | +| approx_kl | 0.010826359 | +| clip_fraction | 0.338 | +| clip_range | 0.066 | +| entropy_loss | -6.14 | +| explained_variance | 0.515 | +| learning_rate | 4.14e-05 | +| loss | -0.0253 | +| n_updates | 86464 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000174 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1392 | +| iterations | 17663 | +| time_elapsed | 25984 | +| total_timesteps | 36173824 | +| train/ | | +| approx_kl | 0.014690284 | +| clip_fraction | 0.283 | +| clip_range | 0.066 | +| entropy_loss | -6.09 | +| explained_variance | 0.407 | +| learning_rate | 4.14e-05 | +| loss | -0.0223 | +| n_updates | 86468 | +| policy_gradient_loss | -0.0143 | +| value_loss | 0.000303 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1392 | +| iterations | 17664 | +| time_elapsed | 25986 | +| total_timesteps | 36175872 | +| train/ | | +| approx_kl | 0.013082202 | +| clip_fraction | 0.373 | +| clip_range | 0.066 | +| entropy_loss | -6.23 | +| explained_variance | 0.347 | +| learning_rate | 4.14e-05 | +| loss | -0.0287 | +| n_updates | 86472 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000107 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1392 | +| iterations | 17665 | +| time_elapsed | 25987 | +| total_timesteps | 36177920 | +| train/ | | +| approx_kl | 0.0137028005 | +| clip_fraction | 0.34 | +| clip_range | 0.066 | +| entropy_loss | -5.83 | +| explained_variance | 0.259 | +| learning_rate | 4.14e-05 | +| loss | -0.0257 | +| n_updates | 86476 | +| policy_gradient_loss | -0.0148 | +| value_loss | 0.000373 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1392 | +| iterations | 17666 | +| time_elapsed | 25989 | +| total_timesteps | 36179968 | +| train/ | | +| approx_kl | 0.011770198 | +| clip_fraction | 0.313 | +| clip_range | 0.066 | +| entropy_loss | -5.34 | +| explained_variance | 0.496 | +| learning_rate | 4.14e-05 | +| loss | -0.0293 | +| n_updates | 86480 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000201 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1392 | +| iterations | 17667 | +| time_elapsed | 25990 | +| total_timesteps | 36182016 | +| train/ | | +| approx_kl | 0.013008374 | +| clip_fraction | 0.323 | +| clip_range | 0.066 | +| entropy_loss | -5.43 | +| explained_variance | 0.586 | +| learning_rate | 4.14e-05 | +| loss | -0.0241 | +| n_updates | 86484 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000144 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1392 | +| iterations | 17668 | +| time_elapsed | 25992 | +| total_timesteps | 36184064 | +| train/ | | +| approx_kl | 0.009917585 | +| clip_fraction | 0.323 | +| clip_range | 0.066 | +| entropy_loss | -6.45 | +| explained_variance | 0.332 | +| learning_rate | 4.14e-05 | +| loss | -0.0246 | +| n_updates | 86488 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000116 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1392 | +| iterations | 17669 | +| time_elapsed | 25993 | +| total_timesteps | 36186112 | +| train/ | | +| approx_kl | 0.011969113 | +| clip_fraction | 0.326 | +| clip_range | 0.066 | +| entropy_loss | -6.28 | +| explained_variance | 0.262 | +| learning_rate | 4.14e-05 | +| loss | -0.0289 | +| n_updates | 86492 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000408 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1392 | +| iterations | 17670 | +| time_elapsed | 25995 | +| total_timesteps | 36188160 | +| train/ | | +| approx_kl | 0.010771401 | +| clip_fraction | 0.293 | +| clip_range | 0.066 | +| entropy_loss | -6.17 | +| explained_variance | 0.172 | +| learning_rate | 4.14e-05 | +| loss | -0.0242 | +| n_updates | 86496 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.000471 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1392 | +| iterations | 17671 | +| time_elapsed | 25997 | +| total_timesteps | 36190208 | +| train/ | | +| approx_kl | 0.010433275 | +| clip_fraction | 0.324 | +| clip_range | 0.066 | +| entropy_loss | -6.13 | +| explained_variance | 0.188 | +| learning_rate | 4.14e-05 | +| loss | -0.028 | +| n_updates | 86500 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000329 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1392 | +| iterations | 17672 | +| time_elapsed | 25998 | +| total_timesteps | 36192256 | +| train/ | | +| approx_kl | 0.011434425 | +| clip_fraction | 0.353 | +| clip_range | 0.066 | +| entropy_loss | -6.16 | +| explained_variance | 0.268 | +| learning_rate | 4.14e-05 | +| loss | -0.0304 | +| n_updates | 86504 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000144 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1392 | +| iterations | 17673 | +| time_elapsed | 26000 | +| total_timesteps | 36194304 | +| train/ | | +| approx_kl | 0.007842403 | +| clip_fraction | 0.309 | +| clip_range | 0.066 | +| entropy_loss | -5.95 | +| explained_variance | 0.355 | +| learning_rate | 4.14e-05 | +| loss | -0.0222 | +| n_updates | 86508 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000265 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1392 | +| iterations | 17674 | +| time_elapsed | 26001 | +| total_timesteps | 36196352 | +| train/ | | +| approx_kl | 0.011569272 | +| clip_fraction | 0.318 | +| clip_range | 0.066 | +| entropy_loss | -5.52 | +| explained_variance | 0.422 | +| learning_rate | 4.14e-05 | +| loss | -0.0278 | +| n_updates | 86512 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000222 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1392 | +| iterations | 17675 | +| time_elapsed | 26003 | +| total_timesteps | 36198400 | +| train/ | | +| approx_kl | 0.009740956 | +| clip_fraction | 0.313 | +| clip_range | 0.066 | +| entropy_loss | -5.16 | +| explained_variance | 0.586 | +| learning_rate | 4.14e-05 | +| loss | -0.0225 | +| n_updates | 86516 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000191 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1392 | +| iterations | 17676 | +| time_elapsed | 26004 | +| total_timesteps | 36200448 | +| train/ | | +| approx_kl | 0.012323191 | +| clip_fraction | 0.321 | +| clip_range | 0.066 | +| entropy_loss | -5.4 | +| explained_variance | 0.562 | +| learning_rate | 4.14e-05 | +| loss | -0.0297 | +| n_updates | 86520 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000124 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1392 | +| iterations | 17677 | +| time_elapsed | 26006 | +| total_timesteps | 36202496 | +| train/ | | +| approx_kl | 0.011704264 | +| clip_fraction | 0.31 | +| clip_range | 0.0659 | +| entropy_loss | -6.02 | +| explained_variance | 0.508 | +| learning_rate | 4.14e-05 | +| loss | -0.0291 | +| n_updates | 86524 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000158 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1392 | +| iterations | 17678 | +| time_elapsed | 26007 | +| total_timesteps | 36204544 | +| train/ | | +| approx_kl | 0.0117686745 | +| clip_fraction | 0.339 | +| clip_range | 0.0659 | +| entropy_loss | -6.42 | +| explained_variance | 0.0661 | +| learning_rate | 4.14e-05 | +| loss | -0.0263 | +| n_updates | 86528 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000119 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1392 | +| iterations | 17679 | +| time_elapsed | 26009 | +| total_timesteps | 36206592 | +| train/ | | +| approx_kl | 0.010826396 | +| clip_fraction | 0.32 | +| clip_range | 0.0659 | +| entropy_loss | -6.76 | +| explained_variance | 0.232 | +| learning_rate | 4.14e-05 | +| loss | -0.0254 | +| n_updates | 86532 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000216 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1392 | +| iterations | 17680 | +| time_elapsed | 26010 | +| total_timesteps | 36208640 | +| train/ | | +| approx_kl | 0.013360053 | +| clip_fraction | 0.301 | +| clip_range | 0.0659 | +| entropy_loss | -6.65 | +| explained_variance | -0.11 | +| learning_rate | 4.14e-05 | +| loss | -0.026 | +| n_updates | 86536 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000156 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1392 | +| iterations | 17681 | +| time_elapsed | 26012 | +| total_timesteps | 36210688 | +| train/ | | +| approx_kl | 0.012063706 | +| clip_fraction | 0.331 | +| clip_range | 0.0659 | +| entropy_loss | -6.55 | +| explained_variance | 0.0571 | +| learning_rate | 4.14e-05 | +| loss | -0.0264 | +| n_updates | 86540 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000242 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1392 | +| iterations | 17682 | +| time_elapsed | 26013 | +| total_timesteps | 36212736 | +| train/ | | +| approx_kl | 0.011689772 | +| clip_fraction | 0.353 | +| clip_range | 0.0659 | +| entropy_loss | -5.98 | +| explained_variance | 0.594 | +| learning_rate | 4.14e-05 | +| loss | -0.0307 | +| n_updates | 86544 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000135 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1392 | +| iterations | 17683 | +| time_elapsed | 26015 | +| total_timesteps | 36214784 | +| train/ | | +| approx_kl | 0.008883273 | +| clip_fraction | 0.3 | +| clip_range | 0.0659 | +| entropy_loss | -5.88 | +| explained_variance | 0.137 | +| learning_rate | 4.14e-05 | +| loss | -0.0214 | +| n_updates | 86548 | +| policy_gradient_loss | -0.0129 | +| value_loss | 0.000493 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1392 | +| iterations | 17684 | +| time_elapsed | 26017 | +| total_timesteps | 36216832 | +| train/ | | +| approx_kl | 0.012559721 | +| clip_fraction | 0.354 | +| clip_range | 0.0659 | +| entropy_loss | -5.33 | +| explained_variance | 0.633 | +| learning_rate | 4.14e-05 | +| loss | -0.0275 | +| n_updates | 86552 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000109 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1392 | +| iterations | 17685 | +| time_elapsed | 26018 | +| total_timesteps | 36218880 | +| train/ | | +| approx_kl | 0.012338496 | +| clip_fraction | 0.339 | +| clip_range | 0.0659 | +| entropy_loss | -5.39 | +| explained_variance | 0.623 | +| learning_rate | 4.14e-05 | +| loss | -0.0265 | +| n_updates | 86556 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000188 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1392 | +| iterations | 17686 | +| time_elapsed | 26020 | +| total_timesteps | 36220928 | +| train/ | | +| approx_kl | 0.010475577 | +| clip_fraction | 0.323 | +| clip_range | 0.0659 | +| entropy_loss | -4.89 | +| explained_variance | 0.665 | +| learning_rate | 4.14e-05 | +| loss | -0.027 | +| n_updates | 86560 | +| policy_gradient_loss | -0.0181 | +| value_loss | 8.95e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1392 | +| iterations | 17687 | +| time_elapsed | 26021 | +| total_timesteps | 36222976 | +| train/ | | +| approx_kl | 0.012197373 | +| clip_fraction | 0.339 | +| clip_range | 0.0659 | +| entropy_loss | -5.83 | +| explained_variance | 0.337 | +| learning_rate | 4.14e-05 | +| loss | -0.0299 | +| n_updates | 86564 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000191 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1392 | +| iterations | 17688 | +| time_elapsed | 26023 | +| total_timesteps | 36225024 | +| train/ | | +| approx_kl | 0.016699795 | +| clip_fraction | 0.393 | +| clip_range | 0.0659 | +| entropy_loss | -5.74 | +| explained_variance | 0.567 | +| learning_rate | 4.14e-05 | +| loss | -0.0313 | +| n_updates | 86568 | +| policy_gradient_loss | -0.0215 | +| value_loss | 9.83e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1392 | +| iterations | 17689 | +| time_elapsed | 26024 | +| total_timesteps | 36227072 | +| train/ | | +| approx_kl | 0.011673263 | +| clip_fraction | 0.338 | +| clip_range | 0.0659 | +| entropy_loss | -5.85 | +| explained_variance | 0.437 | +| learning_rate | 4.14e-05 | +| loss | -0.0285 | +| n_updates | 86572 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000155 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1392 | +| iterations | 17690 | +| time_elapsed | 26026 | +| total_timesteps | 36229120 | +| train/ | | +| approx_kl | 0.012159595 | +| clip_fraction | 0.345 | +| clip_range | 0.0659 | +| entropy_loss | -6.47 | +| explained_variance | -0.039 | +| learning_rate | 4.14e-05 | +| loss | -0.0269 | +| n_updates | 86576 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000121 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1392 | +| iterations | 17691 | +| time_elapsed | 26027 | +| total_timesteps | 36231168 | +| train/ | | +| approx_kl | 0.012100896 | +| clip_fraction | 0.359 | +| clip_range | 0.0659 | +| entropy_loss | -6.47 | +| explained_variance | -0.0944 | +| learning_rate | 4.14e-05 | +| loss | -0.0295 | +| n_updates | 86580 | +| policy_gradient_loss | -0.0191 | +| value_loss | 7.12e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1392 | +| iterations | 17692 | +| time_elapsed | 26029 | +| total_timesteps | 36233216 | +| train/ | | +| approx_kl | 0.015069545 | +| clip_fraction | 0.323 | +| clip_range | 0.0659 | +| entropy_loss | -5.99 | +| explained_variance | 0.426 | +| learning_rate | 4.14e-05 | +| loss | -0.0274 | +| n_updates | 86584 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.000183 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1392 | +| iterations | 17693 | +| time_elapsed | 26030 | +| total_timesteps | 36235264 | +| train/ | | +| approx_kl | 0.013144715 | +| clip_fraction | 0.325 | +| clip_range | 0.0659 | +| entropy_loss | -5.87 | +| explained_variance | 0.365 | +| learning_rate | 4.14e-05 | +| loss | -0.0275 | +| n_updates | 86588 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000182 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1392 | +| iterations | 17694 | +| time_elapsed | 26032 | +| total_timesteps | 36237312 | +| train/ | | +| approx_kl | 0.011818264 | +| clip_fraction | 0.338 | +| clip_range | 0.0659 | +| entropy_loss | -6 | +| explained_variance | 0.331 | +| learning_rate | 4.14e-05 | +| loss | -0.0264 | +| n_updates | 86592 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000133 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1392 | +| iterations | 17695 | +| time_elapsed | 26033 | +| total_timesteps | 36239360 | +| train/ | | +| approx_kl | 0.012255759 | +| clip_fraction | 0.31 | +| clip_range | 0.0659 | +| entropy_loss | -5.46 | +| explained_variance | 0.504 | +| learning_rate | 4.14e-05 | +| loss | -0.022 | +| n_updates | 86596 | +| policy_gradient_loss | -0.0148 | +| value_loss | 0.0002 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1392 | +| iterations | 17696 | +| time_elapsed | 26035 | +| total_timesteps | 36241408 | +| train/ | | +| approx_kl | 0.01282785 | +| clip_fraction | 0.319 | +| clip_range | 0.0659 | +| entropy_loss | -5.72 | +| explained_variance | 0.333 | +| learning_rate | 4.14e-05 | +| loss | -0.0256 | +| n_updates | 86600 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000141 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1392 | +| iterations | 17697 | +| time_elapsed | 26036 | +| total_timesteps | 36243456 | +| train/ | | +| approx_kl | 0.011806112 | +| clip_fraction | 0.314 | +| clip_range | 0.0659 | +| entropy_loss | -5.95 | +| explained_variance | 0.485 | +| learning_rate | 4.14e-05 | +| loss | -0.0229 | +| n_updates | 86604 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000185 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1392 | +| iterations | 17698 | +| time_elapsed | 26038 | +| total_timesteps | 36245504 | +| train/ | | +| approx_kl | 0.014498441 | +| clip_fraction | 0.331 | +| clip_range | 0.0659 | +| entropy_loss | -5.8 | +| explained_variance | 0.267 | +| learning_rate | 4.14e-05 | +| loss | -0.031 | +| n_updates | 86608 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000184 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1392 | +| iterations | 17699 | +| time_elapsed | 26039 | +| total_timesteps | 36247552 | +| train/ | | +| approx_kl | 0.011528977 | +| clip_fraction | 0.315 | +| clip_range | 0.0659 | +| entropy_loss | -5.8 | +| explained_variance | 0.367 | +| learning_rate | 4.14e-05 | +| loss | -0.0273 | +| n_updates | 86612 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000312 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1392 | +| iterations | 17700 | +| time_elapsed | 26041 | +| total_timesteps | 36249600 | +| train/ | | +| approx_kl | 0.009929577 | +| clip_fraction | 0.302 | +| clip_range | 0.0659 | +| entropy_loss | -5.71 | +| explained_variance | 0.452 | +| learning_rate | 4.14e-05 | +| loss | -0.0181 | +| n_updates | 86616 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000255 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1391 | +| iterations | 17701 | +| time_elapsed | 26042 | +| total_timesteps | 36251648 | +| train/ | | +| approx_kl | 0.013234175 | +| clip_fraction | 0.343 | +| clip_range | 0.0659 | +| entropy_loss | -5.22 | +| explained_variance | 0.439 | +| learning_rate | 4.14e-05 | +| loss | -0.0317 | +| n_updates | 86620 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000172 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1391 | +| iterations | 17702 | +| time_elapsed | 26044 | +| total_timesteps | 36253696 | +| train/ | | +| approx_kl | 0.01305451 | +| clip_fraction | 0.339 | +| clip_range | 0.0659 | +| entropy_loss | -5.38 | +| explained_variance | 0.535 | +| learning_rate | 4.14e-05 | +| loss | -0.0342 | +| n_updates | 86624 | +| policy_gradient_loss | -0.0185 | +| value_loss | 9.54e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1391 | +| iterations | 17703 | +| time_elapsed | 26046 | +| total_timesteps | 36255744 | +| train/ | | +| approx_kl | 0.010218356 | +| clip_fraction | 0.316 | +| clip_range | 0.0659 | +| entropy_loss | -5.59 | +| explained_variance | 0.426 | +| learning_rate | 4.14e-05 | +| loss | -0.0227 | +| n_updates | 86628 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000261 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1391 | +| iterations | 17704 | +| time_elapsed | 26047 | +| total_timesteps | 36257792 | +| train/ | | +| approx_kl | 0.011465368 | +| clip_fraction | 0.322 | +| clip_range | 0.0659 | +| entropy_loss | -5.95 | +| explained_variance | 0.34 | +| learning_rate | 4.14e-05 | +| loss | -0.0244 | +| n_updates | 86632 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000241 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1391 | +| iterations | 17705 | +| time_elapsed | 26049 | +| total_timesteps | 36259840 | +| train/ | | +| approx_kl | 0.009647841 | +| clip_fraction | 0.323 | +| clip_range | 0.0659 | +| entropy_loss | -5.82 | +| explained_variance | 0.344 | +| learning_rate | 4.14e-05 | +| loss | -0.0197 | +| n_updates | 86636 | +| policy_gradient_loss | -0.0147 | +| value_loss | 0.000364 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.385 | +| time/ | | +| fps | 1391 | +| iterations | 17706 | +| time_elapsed | 26050 | +| total_timesteps | 36261888 | +| train/ | | +| approx_kl | 0.010851558 | +| clip_fraction | 0.364 | +| clip_range | 0.0659 | +| entropy_loss | -6.17 | +| explained_variance | 0.455 | +| learning_rate | 4.14e-05 | +| loss | -0.0324 | +| n_updates | 86640 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000119 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1391 | +| iterations | 17707 | +| time_elapsed | 26052 | +| total_timesteps | 36263936 | +| train/ | | +| approx_kl | 0.01597177 | +| clip_fraction | 0.314 | +| clip_range | 0.0659 | +| entropy_loss | -6.09 | +| explained_variance | 0.273 | +| learning_rate | 4.14e-05 | +| loss | -0.0255 | +| n_updates | 86644 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.000233 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1391 | +| iterations | 17708 | +| time_elapsed | 26053 | +| total_timesteps | 36265984 | +| train/ | | +| approx_kl | 0.017473958 | +| clip_fraction | 0.353 | +| clip_range | 0.0659 | +| entropy_loss | -5.92 | +| explained_variance | 0.178 | +| learning_rate | 4.14e-05 | +| loss | -0.0321 | +| n_updates | 86648 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000134 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1391 | +| iterations | 17709 | +| time_elapsed | 26055 | +| total_timesteps | 36268032 | +| train/ | | +| approx_kl | 0.016471814 | +| clip_fraction | 0.3 | +| clip_range | 0.0659 | +| entropy_loss | -5.4 | +| explained_variance | 0.554 | +| learning_rate | 4.14e-05 | +| loss | -0.0251 | +| n_updates | 86652 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.000174 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1391 | +| iterations | 17710 | +| time_elapsed | 26056 | +| total_timesteps | 36270080 | +| train/ | | +| approx_kl | 0.0108010005 | +| clip_fraction | 0.312 | +| clip_range | 0.0659 | +| entropy_loss | -5.63 | +| explained_variance | 0.402 | +| learning_rate | 4.14e-05 | +| loss | -0.0261 | +| n_updates | 86656 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.00028 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1391 | +| iterations | 17711 | +| time_elapsed | 26058 | +| total_timesteps | 36272128 | +| train/ | | +| approx_kl | 0.014042718 | +| clip_fraction | 0.368 | +| clip_range | 0.0659 | +| entropy_loss | -6.29 | +| explained_variance | -0.513 | +| learning_rate | 4.14e-05 | +| loss | -0.0433 | +| n_updates | 86660 | +| policy_gradient_loss | -0.0239 | +| value_loss | 9.49e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1391 | +| iterations | 17712 | +| time_elapsed | 26059 | +| total_timesteps | 36274176 | +| train/ | | +| approx_kl | 0.009957218 | +| clip_fraction | 0.332 | +| clip_range | 0.0659 | +| entropy_loss | -6.27 | +| explained_variance | 0.575 | +| learning_rate | 4.14e-05 | +| loss | -0.0309 | +| n_updates | 86664 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000123 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1391 | +| iterations | 17713 | +| time_elapsed | 26061 | +| total_timesteps | 36276224 | +| train/ | | +| approx_kl | 0.013147845 | +| clip_fraction | 0.338 | +| clip_range | 0.0659 | +| entropy_loss | -6.04 | +| explained_variance | -0.163 | +| learning_rate | 4.14e-05 | +| loss | -0.0236 | +| n_updates | 86668 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000174 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1391 | +| iterations | 17714 | +| time_elapsed | 26062 | +| total_timesteps | 36278272 | +| train/ | | +| approx_kl | 0.011972636 | +| clip_fraction | 0.332 | +| clip_range | 0.0659 | +| entropy_loss | -6.13 | +| explained_variance | 0.167 | +| learning_rate | 4.14e-05 | +| loss | -0.027 | +| n_updates | 86672 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000251 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1391 | +| iterations | 17715 | +| time_elapsed | 26064 | +| total_timesteps | 36280320 | +| train/ | | +| approx_kl | 0.012676571 | +| clip_fraction | 0.308 | +| clip_range | 0.0659 | +| entropy_loss | -5.53 | +| explained_variance | 0.561 | +| learning_rate | 4.14e-05 | +| loss | -0.0286 | +| n_updates | 86676 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000104 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1391 | +| iterations | 17716 | +| time_elapsed | 26065 | +| total_timesteps | 36282368 | +| train/ | | +| approx_kl | 0.015193363 | +| clip_fraction | 0.359 | +| clip_range | 0.0659 | +| entropy_loss | -5.74 | +| explained_variance | 0.621 | +| learning_rate | 4.14e-05 | +| loss | -0.0281 | +| n_updates | 86680 | +| policy_gradient_loss | -0.0181 | +| value_loss | 7.95e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1391 | +| iterations | 17717 | +| time_elapsed | 26067 | +| total_timesteps | 36284416 | +| train/ | | +| approx_kl | 0.010333205 | +| clip_fraction | 0.315 | +| clip_range | 0.0659 | +| entropy_loss | -6.22 | +| explained_variance | 0.225 | +| learning_rate | 4.14e-05 | +| loss | -0.0234 | +| n_updates | 86684 | +| policy_gradient_loss | -0.0146 | +| value_loss | 0.000258 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1391 | +| iterations | 17718 | +| time_elapsed | 26068 | +| total_timesteps | 36286464 | +| train/ | | +| approx_kl | 0.009874607 | +| clip_fraction | 0.3 | +| clip_range | 0.0659 | +| entropy_loss | -6.26 | +| explained_variance | 0.267 | +| learning_rate | 4.14e-05 | +| loss | -0.0257 | +| n_updates | 86688 | +| policy_gradient_loss | -0.0124 | +| value_loss | 0.00026 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1391 | +| iterations | 17719 | +| time_elapsed | 26070 | +| total_timesteps | 36288512 | +| train/ | | +| approx_kl | 0.012764414 | +| clip_fraction | 0.364 | +| clip_range | 0.0659 | +| entropy_loss | -6.22 | +| explained_variance | -0.126 | +| learning_rate | 4.14e-05 | +| loss | -0.0259 | +| n_updates | 86692 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000226 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1391 | +| iterations | 17720 | +| time_elapsed | 26071 | +| total_timesteps | 36290560 | +| train/ | | +| approx_kl | 0.013035057 | +| clip_fraction | 0.337 | +| clip_range | 0.0659 | +| entropy_loss | -5.71 | +| explained_variance | 0.754 | +| learning_rate | 4.14e-05 | +| loss | -0.0295 | +| n_updates | 86696 | +| policy_gradient_loss | -0.0191 | +| value_loss | 9.48e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1391 | +| iterations | 17721 | +| time_elapsed | 26073 | +| total_timesteps | 36292608 | +| train/ | | +| approx_kl | 0.011980501 | +| clip_fraction | 0.322 | +| clip_range | 0.0659 | +| entropy_loss | -5.49 | +| explained_variance | 0.208 | +| learning_rate | 4.14e-05 | +| loss | -0.0166 | +| n_updates | 86700 | +| policy_gradient_loss | -0.0133 | +| value_loss | 0.000249 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1391 | +| iterations | 17722 | +| time_elapsed | 26074 | +| total_timesteps | 36294656 | +| train/ | | +| approx_kl | 0.014380928 | +| clip_fraction | 0.374 | +| clip_range | 0.0659 | +| entropy_loss | -6.01 | +| explained_variance | 0.433 | +| learning_rate | 4.14e-05 | +| loss | -0.0354 | +| n_updates | 86704 | +| policy_gradient_loss | -0.0221 | +| value_loss | 0.0001 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1391 | +| iterations | 17723 | +| time_elapsed | 26076 | +| total_timesteps | 36296704 | +| train/ | | +| approx_kl | 0.013086582 | +| clip_fraction | 0.333 | +| clip_range | 0.0659 | +| entropy_loss | -6.14 | +| explained_variance | 0.239 | +| learning_rate | 4.14e-05 | +| loss | -0.0268 | +| n_updates | 86708 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000145 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1391 | +| iterations | 17724 | +| time_elapsed | 26077 | +| total_timesteps | 36298752 | +| train/ | | +| approx_kl | 0.0083154915 | +| clip_fraction | 0.292 | +| clip_range | 0.0659 | +| entropy_loss | -6.24 | +| explained_variance | 0.407 | +| learning_rate | 4.14e-05 | +| loss | -0.0242 | +| n_updates | 86712 | +| policy_gradient_loss | -0.0141 | +| value_loss | 0.000243 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1391 | +| iterations | 17725 | +| time_elapsed | 26079 | +| total_timesteps | 36300800 | +| train/ | | +| approx_kl | 0.009840369 | +| clip_fraction | 0.323 | +| clip_range | 0.0659 | +| entropy_loss | -6.22 | +| explained_variance | 0.138 | +| learning_rate | 4.14e-05 | +| loss | -0.0264 | +| n_updates | 86716 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000163 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1391 | +| iterations | 17726 | +| time_elapsed | 26080 | +| total_timesteps | 36302848 | +| train/ | | +| approx_kl | 0.011971714 | +| clip_fraction | 0.338 | +| clip_range | 0.0659 | +| entropy_loss | -6.06 | +| explained_variance | 0.126 | +| learning_rate | 4.14e-05 | +| loss | -0.0258 | +| n_updates | 86720 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.00028 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1391 | +| iterations | 17727 | +| time_elapsed | 26082 | +| total_timesteps | 36304896 | +| train/ | | +| approx_kl | 0.014212959 | +| clip_fraction | 0.34 | +| clip_range | 0.0659 | +| entropy_loss | -5.92 | +| explained_variance | 0.501 | +| learning_rate | 4.14e-05 | +| loss | -0.0283 | +| n_updates | 86724 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000154 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1391 | +| iterations | 17728 | +| time_elapsed | 26084 | +| total_timesteps | 36306944 | +| train/ | | +| approx_kl | 0.014002795 | +| clip_fraction | 0.338 | +| clip_range | 0.0659 | +| entropy_loss | -6.02 | +| explained_variance | 0.302 | +| learning_rate | 4.14e-05 | +| loss | -0.031 | +| n_updates | 86728 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000143 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1391 | +| iterations | 17729 | +| time_elapsed | 26085 | +| total_timesteps | 36308992 | +| train/ | | +| approx_kl | 0.014699129 | +| clip_fraction | 0.353 | +| clip_range | 0.0659 | +| entropy_loss | -6.58 | +| explained_variance | -0.237 | +| learning_rate | 4.14e-05 | +| loss | -0.0382 | +| n_updates | 86732 | +| policy_gradient_loss | -0.0205 | +| value_loss | 9.04e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1391 | +| iterations | 17730 | +| time_elapsed | 26087 | +| total_timesteps | 36311040 | +| train/ | | +| approx_kl | 0.013943279 | +| clip_fraction | 0.34 | +| clip_range | 0.0659 | +| entropy_loss | -5.96 | +| explained_variance | 0.557 | +| learning_rate | 4.14e-05 | +| loss | -0.0244 | +| n_updates | 86736 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000114 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1391 | +| iterations | 17731 | +| time_elapsed | 26088 | +| total_timesteps | 36313088 | +| train/ | | +| approx_kl | 0.014080305 | +| clip_fraction | 0.33 | +| clip_range | 0.0659 | +| entropy_loss | -5.28 | +| explained_variance | 0.652 | +| learning_rate | 4.14e-05 | +| loss | -0.0239 | +| n_updates | 86740 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.00011 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1391 | +| iterations | 17732 | +| time_elapsed | 26090 | +| total_timesteps | 36315136 | +| train/ | | +| approx_kl | 0.013744304 | +| clip_fraction | 0.361 | +| clip_range | 0.0659 | +| entropy_loss | -5.44 | +| explained_variance | 0.63 | +| learning_rate | 4.14e-05 | +| loss | -0.0304 | +| n_updates | 86744 | +| policy_gradient_loss | -0.0183 | +| value_loss | 9.52e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1391 | +| iterations | 17733 | +| time_elapsed | 26091 | +| total_timesteps | 36317184 | +| train/ | | +| approx_kl | 0.009471248 | +| clip_fraction | 0.325 | +| clip_range | 0.0659 | +| entropy_loss | -6.21 | +| explained_variance | 0.557 | +| learning_rate | 4.14e-05 | +| loss | -0.0272 | +| n_updates | 86748 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000118 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1391 | +| iterations | 17734 | +| time_elapsed | 26093 | +| total_timesteps | 36319232 | +| train/ | | +| approx_kl | 0.010770559 | +| clip_fraction | 0.303 | +| clip_range | 0.0659 | +| entropy_loss | -6.62 | +| explained_variance | 0.424 | +| learning_rate | 4.14e-05 | +| loss | -0.027 | +| n_updates | 86752 | +| policy_gradient_loss | -0.0168 | +| value_loss | 9.63e-05 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1391 | +| iterations | 17735 | +| time_elapsed | 26094 | +| total_timesteps | 36321280 | +| train/ | | +| approx_kl | 0.0132963 | +| clip_fraction | 0.329 | +| clip_range | 0.0659 | +| entropy_loss | -6.59 | +| explained_variance | 0.442 | +| learning_rate | 4.14e-05 | +| loss | -0.0296 | +| n_updates | 86756 | +| policy_gradient_loss | -0.0182 | +| value_loss | 9.85e-05 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1391 | +| iterations | 17736 | +| time_elapsed | 26096 | +| total_timesteps | 36323328 | +| train/ | | +| approx_kl | 0.010453587 | +| clip_fraction | 0.319 | +| clip_range | 0.0659 | +| entropy_loss | -6.28 | +| explained_variance | 0.296 | +| learning_rate | 4.14e-05 | +| loss | -0.0227 | +| n_updates | 86760 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000194 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1391 | +| iterations | 17737 | +| time_elapsed | 26097 | +| total_timesteps | 36325376 | +| train/ | | +| approx_kl | 0.01463411 | +| clip_fraction | 0.354 | +| clip_range | 0.0659 | +| entropy_loss | -5.84 | +| explained_variance | 0.688 | +| learning_rate | 4.14e-05 | +| loss | -0.0342 | +| n_updates | 86764 | +| policy_gradient_loss | -0.0192 | +| value_loss | 6.63e-05 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1391 | +| iterations | 17738 | +| time_elapsed | 26099 | +| total_timesteps | 36327424 | +| train/ | | +| approx_kl | 0.0123233935 | +| clip_fraction | 0.322 | +| clip_range | 0.0659 | +| entropy_loss | -6.08 | +| explained_variance | 0.444 | +| learning_rate | 4.14e-05 | +| loss | -0.0271 | +| n_updates | 86768 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000212 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1391 | +| iterations | 17739 | +| time_elapsed | 26100 | +| total_timesteps | 36329472 | +| train/ | | +| approx_kl | 0.010470192 | +| clip_fraction | 0.292 | +| clip_range | 0.0659 | +| entropy_loss | -5.4 | +| explained_variance | 0.536 | +| learning_rate | 4.14e-05 | +| loss | -0.0205 | +| n_updates | 86772 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.000216 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1391 | +| iterations | 17740 | +| time_elapsed | 26102 | +| total_timesteps | 36331520 | +| train/ | | +| approx_kl | 0.011211619 | +| clip_fraction | 0.314 | +| clip_range | 0.0659 | +| entropy_loss | -5.42 | +| explained_variance | 0.35 | +| learning_rate | 4.14e-05 | +| loss | -0.0206 | +| n_updates | 86776 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000221 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1391 | +| iterations | 17741 | +| time_elapsed | 26103 | +| total_timesteps | 36333568 | +| train/ | | +| approx_kl | 0.010873446 | +| clip_fraction | 0.325 | +| clip_range | 0.0659 | +| entropy_loss | -6.08 | +| explained_variance | 0.303 | +| learning_rate | 4.14e-05 | +| loss | -0.0309 | +| n_updates | 86780 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000143 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1391 | +| iterations | 17742 | +| time_elapsed | 26105 | +| total_timesteps | 36335616 | +| train/ | | +| approx_kl | 0.011403799 | +| clip_fraction | 0.327 | +| clip_range | 0.0659 | +| entropy_loss | -5.69 | +| explained_variance | 0.342 | +| learning_rate | 4.14e-05 | +| loss | -0.0267 | +| n_updates | 86784 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000296 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1391 | +| iterations | 17743 | +| time_elapsed | 26106 | +| total_timesteps | 36337664 | +| train/ | | +| approx_kl | 0.014172727 | +| clip_fraction | 0.35 | +| clip_range | 0.0659 | +| entropy_loss | -5.93 | +| explained_variance | 0.0146 | +| learning_rate | 4.14e-05 | +| loss | -0.0335 | +| n_updates | 86788 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000151 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1391 | +| iterations | 17744 | +| time_elapsed | 26108 | +| total_timesteps | 36339712 | +| train/ | | +| approx_kl | 0.015333495 | +| clip_fraction | 0.359 | +| clip_range | 0.0659 | +| entropy_loss | -6.04 | +| explained_variance | 0.202 | +| learning_rate | 4.14e-05 | +| loss | -0.027 | +| n_updates | 86792 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000191 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1391 | +| iterations | 17745 | +| time_elapsed | 26109 | +| total_timesteps | 36341760 | +| train/ | | +| approx_kl | 0.010702584 | +| clip_fraction | 0.303 | +| clip_range | 0.0659 | +| entropy_loss | -5.92 | +| explained_variance | 0.433 | +| learning_rate | 4.14e-05 | +| loss | -0.0282 | +| n_updates | 86796 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000224 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1391 | +| iterations | 17746 | +| time_elapsed | 26111 | +| total_timesteps | 36343808 | +| train/ | | +| approx_kl | 0.014470207 | +| clip_fraction | 0.38 | +| clip_range | 0.0659 | +| entropy_loss | -5.45 | +| explained_variance | 0.776 | +| learning_rate | 4.14e-05 | +| loss | -0.0325 | +| n_updates | 86800 | +| policy_gradient_loss | -0.0235 | +| value_loss | 6.66e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1391 | +| iterations | 17747 | +| time_elapsed | 26113 | +| total_timesteps | 36345856 | +| train/ | | +| approx_kl | 0.010645717 | +| clip_fraction | 0.32 | +| clip_range | 0.0659 | +| entropy_loss | -5.92 | +| explained_variance | 0.339 | +| learning_rate | 4.14e-05 | +| loss | -0.0277 | +| n_updates | 86804 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.000177 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1391 | +| iterations | 17748 | +| time_elapsed | 26114 | +| total_timesteps | 36347904 | +| train/ | | +| approx_kl | 0.015299382 | +| clip_fraction | 0.349 | +| clip_range | 0.0659 | +| entropy_loss | -6.2 | +| explained_variance | 0.306 | +| learning_rate | 4.14e-05 | +| loss | -0.0322 | +| n_updates | 86808 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000172 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1391 | +| iterations | 17749 | +| time_elapsed | 26116 | +| total_timesteps | 36349952 | +| train/ | | +| approx_kl | 0.013449011 | +| clip_fraction | 0.351 | +| clip_range | 0.0659 | +| entropy_loss | -6.41 | +| explained_variance | 0.39 | +| learning_rate | 4.14e-05 | +| loss | -0.0243 | +| n_updates | 86812 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000114 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1391 | +| iterations | 17750 | +| time_elapsed | 26117 | +| total_timesteps | 36352000 | +| train/ | | +| approx_kl | 0.01619172 | +| clip_fraction | 0.35 | +| clip_range | 0.0659 | +| entropy_loss | -6.03 | +| explained_variance | 0.456 | +| learning_rate | 4.14e-05 | +| loss | -0.0329 | +| n_updates | 86816 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000157 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1391 | +| iterations | 17751 | +| time_elapsed | 26119 | +| total_timesteps | 36354048 | +| train/ | | +| approx_kl | 0.015067361 | +| clip_fraction | 0.344 | +| clip_range | 0.0659 | +| entropy_loss | -5.67 | +| explained_variance | 0.328 | +| learning_rate | 4.14e-05 | +| loss | -0.0255 | +| n_updates | 86820 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000165 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1391 | +| iterations | 17752 | +| time_elapsed | 26120 | +| total_timesteps | 36356096 | +| train/ | | +| approx_kl | 0.014656773 | +| clip_fraction | 0.347 | +| clip_range | 0.0659 | +| entropy_loss | -5.81 | +| explained_variance | 0.453 | +| learning_rate | 4.14e-05 | +| loss | -0.0313 | +| n_updates | 86824 | +| policy_gradient_loss | -0.0199 | +| value_loss | 7.88e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1391 | +| iterations | 17753 | +| time_elapsed | 26122 | +| total_timesteps | 36358144 | +| train/ | | +| approx_kl | 0.014704553 | +| clip_fraction | 0.323 | +| clip_range | 0.0659 | +| entropy_loss | -5.91 | +| explained_variance | 0.336 | +| learning_rate | 4.14e-05 | +| loss | -0.0237 | +| n_updates | 86828 | +| policy_gradient_loss | -0.0139 | +| value_loss | 0.000266 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1391 | +| iterations | 17754 | +| time_elapsed | 26123 | +| total_timesteps | 36360192 | +| train/ | | +| approx_kl | 0.01240859 | +| clip_fraction | 0.317 | +| clip_range | 0.0659 | +| entropy_loss | -5.37 | +| explained_variance | 0.518 | +| learning_rate | 4.14e-05 | +| loss | -0.0259 | +| n_updates | 86832 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000267 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1391 | +| iterations | 17755 | +| time_elapsed | 26125 | +| total_timesteps | 36362240 | +| train/ | | +| approx_kl | 0.01480976 | +| clip_fraction | 0.332 | +| clip_range | 0.0659 | +| entropy_loss | -6.09 | +| explained_variance | -0.149 | +| learning_rate | 4.14e-05 | +| loss | -0.0313 | +| n_updates | 86836 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000154 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1391 | +| iterations | 17756 | +| time_elapsed | 26126 | +| total_timesteps | 36364288 | +| train/ | | +| approx_kl | 0.013202915 | +| clip_fraction | 0.361 | +| clip_range | 0.0659 | +| entropy_loss | -6.49 | +| explained_variance | -0.0935 | +| learning_rate | 4.14e-05 | +| loss | -0.0251 | +| n_updates | 86840 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000122 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1391 | +| iterations | 17757 | +| time_elapsed | 26128 | +| total_timesteps | 36366336 | +| train/ | | +| approx_kl | 0.011975754 | +| clip_fraction | 0.311 | +| clip_range | 0.0659 | +| entropy_loss | -6.34 | +| explained_variance | 0.343 | +| learning_rate | 4.14e-05 | +| loss | -0.0236 | +| n_updates | 86844 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000234 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1391 | +| iterations | 17758 | +| time_elapsed | 26129 | +| total_timesteps | 36368384 | +| train/ | | +| approx_kl | 0.010576021 | +| clip_fraction | 0.283 | +| clip_range | 0.0659 | +| entropy_loss | -5.65 | +| explained_variance | 0.436 | +| learning_rate | 4.14e-05 | +| loss | -0.0233 | +| n_updates | 86848 | +| policy_gradient_loss | -0.0145 | +| value_loss | 0.000168 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1391 | +| iterations | 17759 | +| time_elapsed | 26131 | +| total_timesteps | 36370432 | +| train/ | | +| approx_kl | 0.012764065 | +| clip_fraction | 0.306 | +| clip_range | 0.0659 | +| entropy_loss | -5.81 | +| explained_variance | 0.345 | +| learning_rate | 4.14e-05 | +| loss | -0.0181 | +| n_updates | 86852 | +| policy_gradient_loss | -0.014 | +| value_loss | 0.000197 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1391 | +| iterations | 17760 | +| time_elapsed | 26132 | +| total_timesteps | 36372480 | +| train/ | | +| approx_kl | 0.012569409 | +| clip_fraction | 0.338 | +| clip_range | 0.0659 | +| entropy_loss | -5.13 | +| explained_variance | 0.754 | +| learning_rate | 4.14e-05 | +| loss | -0.0242 | +| n_updates | 86856 | +| policy_gradient_loss | -0.0179 | +| value_loss | 7.75e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1391 | +| iterations | 17761 | +| time_elapsed | 26134 | +| total_timesteps | 36374528 | +| train/ | | +| approx_kl | 0.009810509 | +| clip_fraction | 0.319 | +| clip_range | 0.0659 | +| entropy_loss | -5.97 | +| explained_variance | 0.184 | +| learning_rate | 4.14e-05 | +| loss | -0.0291 | +| n_updates | 86860 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000271 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1391 | +| iterations | 17762 | +| time_elapsed | 26136 | +| total_timesteps | 36376576 | +| train/ | | +| approx_kl | 0.0120455045 | +| clip_fraction | 0.346 | +| clip_range | 0.0659 | +| entropy_loss | -5.74 | +| explained_variance | 0.459 | +| learning_rate | 4.14e-05 | +| loss | -0.0318 | +| n_updates | 86864 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000147 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1391 | +| iterations | 17763 | +| time_elapsed | 26137 | +| total_timesteps | 36378624 | +| train/ | | +| approx_kl | 0.011921358 | +| clip_fraction | 0.335 | +| clip_range | 0.0659 | +| entropy_loss | -6.2 | +| explained_variance | 0.339 | +| learning_rate | 4.14e-05 | +| loss | -0.022 | +| n_updates | 86868 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1391 | +| iterations | 17764 | +| time_elapsed | 26139 | +| total_timesteps | 36380672 | +| train/ | | +| approx_kl | 0.012464921 | +| clip_fraction | 0.305 | +| clip_range | 0.0659 | +| entropy_loss | -6.27 | +| explained_variance | 0.539 | +| learning_rate | 4.14e-05 | +| loss | -0.0288 | +| n_updates | 86872 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000145 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1391 | +| iterations | 17765 | +| time_elapsed | 26140 | +| total_timesteps | 36382720 | +| train/ | | +| approx_kl | 0.010858483 | +| clip_fraction | 0.312 | +| clip_range | 0.0659 | +| entropy_loss | -6.1 | +| explained_variance | 0.351 | +| learning_rate | 4.14e-05 | +| loss | -0.0294 | +| n_updates | 86876 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000128 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1391 | +| iterations | 17766 | +| time_elapsed | 26142 | +| total_timesteps | 36384768 | +| train/ | | +| approx_kl | 0.010382066 | +| clip_fraction | 0.338 | +| clip_range | 0.0659 | +| entropy_loss | -6.6 | +| explained_variance | 0.111 | +| learning_rate | 4.14e-05 | +| loss | -0.0287 | +| n_updates | 86880 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000181 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1391 | +| iterations | 17767 | +| time_elapsed | 26143 | +| total_timesteps | 36386816 | +| train/ | | +| approx_kl | 0.011672411 | +| clip_fraction | 0.364 | +| clip_range | 0.0659 | +| entropy_loss | -6.63 | +| explained_variance | 0.471 | +| learning_rate | 4.14e-05 | +| loss | -0.0303 | +| n_updates | 86884 | +| policy_gradient_loss | -0.0196 | +| value_loss | 7.36e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1391 | +| iterations | 17768 | +| time_elapsed | 26145 | +| total_timesteps | 36388864 | +| train/ | | +| approx_kl | 0.010897084 | +| clip_fraction | 0.316 | +| clip_range | 0.0659 | +| entropy_loss | -6.09 | +| explained_variance | 0.659 | +| learning_rate | 4.14e-05 | +| loss | -0.0207 | +| n_updates | 86888 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000121 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1391 | +| iterations | 17769 | +| time_elapsed | 26146 | +| total_timesteps | 36390912 | +| train/ | | +| approx_kl | 0.009318799 | +| clip_fraction | 0.296 | +| clip_range | 0.0659 | +| entropy_loss | -5.69 | +| explained_variance | 0.517 | +| learning_rate | 4.14e-05 | +| loss | -0.0238 | +| n_updates | 86892 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000159 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1391 | +| iterations | 17770 | +| time_elapsed | 26148 | +| total_timesteps | 36392960 | +| train/ | | +| approx_kl | 0.008950081 | +| clip_fraction | 0.311 | +| clip_range | 0.0659 | +| entropy_loss | -5.84 | +| explained_variance | 0.298 | +| learning_rate | 4.14e-05 | +| loss | -0.0274 | +| n_updates | 86896 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000321 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1391 | +| iterations | 17771 | +| time_elapsed | 26149 | +| total_timesteps | 36395008 | +| train/ | | +| approx_kl | 0.013651842 | +| clip_fraction | 0.331 | +| clip_range | 0.0659 | +| entropy_loss | -5 | +| explained_variance | 0.515 | +| learning_rate | 4.14e-05 | +| loss | -0.0298 | +| n_updates | 86900 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000129 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1391 | +| iterations | 17772 | +| time_elapsed | 26151 | +| total_timesteps | 36397056 | +| train/ | | +| approx_kl | 0.013603689 | +| clip_fraction | 0.35 | +| clip_range | 0.0659 | +| entropy_loss | -5.44 | +| explained_variance | 0.297 | +| learning_rate | 4.14e-05 | +| loss | -0.0326 | +| n_updates | 86904 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000163 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1391 | +| iterations | 17773 | +| time_elapsed | 26152 | +| total_timesteps | 36399104 | +| train/ | | +| approx_kl | 0.016727572 | +| clip_fraction | 0.359 | +| clip_range | 0.0659 | +| entropy_loss | -5.44 | +| explained_variance | 0.533 | +| learning_rate | 4.14e-05 | +| loss | -0.0258 | +| n_updates | 86908 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000134 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1391 | +| iterations | 17774 | +| time_elapsed | 26154 | +| total_timesteps | 36401152 | +| train/ | | +| approx_kl | 0.015123711 | +| clip_fraction | 0.339 | +| clip_range | 0.0659 | +| entropy_loss | -5.77 | +| explained_variance | 0.314 | +| learning_rate | 4.14e-05 | +| loss | -0.0293 | +| n_updates | 86912 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.00012 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1391 | +| iterations | 17775 | +| time_elapsed | 26155 | +| total_timesteps | 36403200 | +| train/ | | +| approx_kl | 0.01972223 | +| clip_fraction | 0.324 | +| clip_range | 0.0659 | +| entropy_loss | -5.84 | +| explained_variance | 0.188 | +| learning_rate | 4.14e-05 | +| loss | -0.0263 | +| n_updates | 86916 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000196 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1391 | +| iterations | 17776 | +| time_elapsed | 26157 | +| total_timesteps | 36405248 | +| train/ | | +| approx_kl | 0.012353889 | +| clip_fraction | 0.354 | +| clip_range | 0.0659 | +| entropy_loss | -6.25 | +| explained_variance | 0.6 | +| learning_rate | 4.14e-05 | +| loss | -0.0308 | +| n_updates | 86920 | +| policy_gradient_loss | -0.0199 | +| value_loss | 5.31e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1391 | +| iterations | 17777 | +| time_elapsed | 26159 | +| total_timesteps | 36407296 | +| train/ | | +| approx_kl | 0.013256425 | +| clip_fraction | 0.363 | +| clip_range | 0.0659 | +| entropy_loss | -5.88 | +| explained_variance | 0.61 | +| learning_rate | 4.14e-05 | +| loss | -0.0334 | +| n_updates | 86924 | +| policy_gradient_loss | -0.0192 | +| value_loss | 8.06e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1391 | +| iterations | 17778 | +| time_elapsed | 26160 | +| total_timesteps | 36409344 | +| train/ | | +| approx_kl | 0.018342126 | +| clip_fraction | 0.341 | +| clip_range | 0.0659 | +| entropy_loss | -5.71 | +| explained_variance | 0.681 | +| learning_rate | 4.14e-05 | +| loss | -0.0306 | +| n_updates | 86928 | +| policy_gradient_loss | -0.0183 | +| value_loss | 6.99e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1391 | +| iterations | 17779 | +| time_elapsed | 26162 | +| total_timesteps | 36411392 | +| train/ | | +| approx_kl | 0.0120172845 | +| clip_fraction | 0.333 | +| clip_range | 0.0659 | +| entropy_loss | -5.9 | +| explained_variance | 0.648 | +| learning_rate | 4.14e-05 | +| loss | -0.0271 | +| n_updates | 86932 | +| policy_gradient_loss | -0.0154 | +| value_loss | 9.96e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1391 | +| iterations | 17780 | +| time_elapsed | 26163 | +| total_timesteps | 36413440 | +| train/ | | +| approx_kl | 0.013244554 | +| clip_fraction | 0.322 | +| clip_range | 0.0659 | +| entropy_loss | -6.15 | +| explained_variance | 0.545 | +| learning_rate | 4.14e-05 | +| loss | -0.0247 | +| n_updates | 86936 | +| policy_gradient_loss | -0.0165 | +| value_loss | 7.88e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1391 | +| iterations | 17781 | +| time_elapsed | 26165 | +| total_timesteps | 36415488 | +| train/ | | +| approx_kl | 0.012029423 | +| clip_fraction | 0.293 | +| clip_range | 0.0659 | +| entropy_loss | -5.62 | +| explained_variance | 0.659 | +| learning_rate | 4.14e-05 | +| loss | -0.0199 | +| n_updates | 86940 | +| policy_gradient_loss | -0.0148 | +| value_loss | 0.000122 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1391 | +| iterations | 17782 | +| time_elapsed | 26166 | +| total_timesteps | 36417536 | +| train/ | | +| approx_kl | 0.009235951 | +| clip_fraction | 0.296 | +| clip_range | 0.0659 | +| entropy_loss | -6.12 | +| explained_variance | 0.275 | +| learning_rate | 4.14e-05 | +| loss | -0.0237 | +| n_updates | 86944 | +| policy_gradient_loss | -0.0145 | +| value_loss | 0.000299 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1391 | +| iterations | 17783 | +| time_elapsed | 26168 | +| total_timesteps | 36419584 | +| train/ | | +| approx_kl | 0.012290831 | +| clip_fraction | 0.308 | +| clip_range | 0.0659 | +| entropy_loss | -5.4 | +| explained_variance | 0.346 | +| learning_rate | 4.14e-05 | +| loss | -0.0187 | +| n_updates | 86948 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000276 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1391 | +| iterations | 17784 | +| time_elapsed | 26169 | +| total_timesteps | 36421632 | +| train/ | | +| approx_kl | 0.011635893 | +| clip_fraction | 0.314 | +| clip_range | 0.0659 | +| entropy_loss | -5.17 | +| explained_variance | 0.532 | +| learning_rate | 4.14e-05 | +| loss | -0.0193 | +| n_updates | 86952 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.000173 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1391 | +| iterations | 17785 | +| time_elapsed | 26171 | +| total_timesteps | 36423680 | +| train/ | | +| approx_kl | 0.010403482 | +| clip_fraction | 0.336 | +| clip_range | 0.0659 | +| entropy_loss | -5.91 | +| explained_variance | 0.127 | +| learning_rate | 4.13e-05 | +| loss | -0.0237 | +| n_updates | 86956 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000228 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1391 | +| iterations | 17786 | +| time_elapsed | 26172 | +| total_timesteps | 36425728 | +| train/ | | +| approx_kl | 0.010070268 | +| clip_fraction | 0.309 | +| clip_range | 0.0659 | +| entropy_loss | -6.35 | +| explained_variance | 0.237 | +| learning_rate | 4.13e-05 | +| loss | -0.0246 | +| n_updates | 86960 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000227 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1391 | +| iterations | 17787 | +| time_elapsed | 26174 | +| total_timesteps | 36427776 | +| train/ | | +| approx_kl | 0.0104408525 | +| clip_fraction | 0.309 | +| clip_range | 0.0659 | +| entropy_loss | -6.09 | +| explained_variance | 0.366 | +| learning_rate | 4.13e-05 | +| loss | -0.0284 | +| n_updates | 86964 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000186 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1391 | +| iterations | 17788 | +| time_elapsed | 26175 | +| total_timesteps | 36429824 | +| train/ | | +| approx_kl | 0.0107895825 | +| clip_fraction | 0.32 | +| clip_range | 0.0659 | +| entropy_loss | -6.1 | +| explained_variance | 0.268 | +| learning_rate | 4.13e-05 | +| loss | -0.0303 | +| n_updates | 86968 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000158 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1391 | +| iterations | 17789 | +| time_elapsed | 26177 | +| total_timesteps | 36431872 | +| train/ | | +| approx_kl | 0.008896859 | +| clip_fraction | 0.317 | +| clip_range | 0.0659 | +| entropy_loss | -6.21 | +| explained_variance | 0.432 | +| learning_rate | 4.13e-05 | +| loss | -0.0211 | +| n_updates | 86972 | +| policy_gradient_loss | -0.0145 | +| value_loss | 0.000223 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1391 | +| iterations | 17790 | +| time_elapsed | 26178 | +| total_timesteps | 36433920 | +| train/ | | +| approx_kl | 0.010418262 | +| clip_fraction | 0.31 | +| clip_range | 0.0659 | +| entropy_loss | -5.79 | +| explained_variance | 0.405 | +| learning_rate | 4.13e-05 | +| loss | -0.0255 | +| n_updates | 86976 | +| policy_gradient_loss | -0.0135 | +| value_loss | 0.000213 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1391 | +| iterations | 17791 | +| time_elapsed | 26180 | +| total_timesteps | 36435968 | +| train/ | | +| approx_kl | 0.011575419 | +| clip_fraction | 0.311 | +| clip_range | 0.0659 | +| entropy_loss | -5.53 | +| explained_variance | 0.673 | +| learning_rate | 4.13e-05 | +| loss | -0.0295 | +| n_updates | 86980 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000126 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1391 | +| iterations | 17792 | +| time_elapsed | 26182 | +| total_timesteps | 36438016 | +| train/ | | +| approx_kl | 0.010175604 | +| clip_fraction | 0.339 | +| clip_range | 0.0659 | +| entropy_loss | -6.02 | +| explained_variance | 0.495 | +| learning_rate | 4.13e-05 | +| loss | -0.0253 | +| n_updates | 86984 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000149 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1391 | +| iterations | 17793 | +| time_elapsed | 26183 | +| total_timesteps | 36440064 | +| train/ | | +| approx_kl | 0.011534411 | +| clip_fraction | 0.327 | +| clip_range | 0.0659 | +| entropy_loss | -5.95 | +| explained_variance | 0.618 | +| learning_rate | 4.13e-05 | +| loss | -0.0255 | +| n_updates | 86988 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000109 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1391 | +| iterations | 17794 | +| time_elapsed | 26185 | +| total_timesteps | 36442112 | +| train/ | | +| approx_kl | 0.012288138 | +| clip_fraction | 0.325 | +| clip_range | 0.0659 | +| entropy_loss | -5.68 | +| explained_variance | 0.493 | +| learning_rate | 4.13e-05 | +| loss | -0.0249 | +| n_updates | 86992 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000123 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1391 | +| iterations | 17795 | +| time_elapsed | 26186 | +| total_timesteps | 36444160 | +| train/ | | +| approx_kl | 0.014017064 | +| clip_fraction | 0.351 | +| clip_range | 0.0659 | +| entropy_loss | -6.2 | +| explained_variance | -0.0782 | +| learning_rate | 4.13e-05 | +| loss | -0.0348 | +| n_updates | 86996 | +| policy_gradient_loss | -0.0186 | +| value_loss | 7.36e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1391 | +| iterations | 17796 | +| time_elapsed | 26188 | +| total_timesteps | 36446208 | +| train/ | | +| approx_kl | 0.017109439 | +| clip_fraction | 0.334 | +| clip_range | 0.0659 | +| entropy_loss | -6.8 | +| explained_variance | 0.113 | +| learning_rate | 4.13e-05 | +| loss | -0.029 | +| n_updates | 87000 | +| policy_gradient_loss | -0.0191 | +| value_loss | 6.06e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1391 | +| iterations | 17797 | +| time_elapsed | 26189 | +| total_timesteps | 36448256 | +| train/ | | +| approx_kl | 0.010556936 | +| clip_fraction | 0.312 | +| clip_range | 0.0659 | +| entropy_loss | -6.34 | +| explained_variance | 0.284 | +| learning_rate | 4.13e-05 | +| loss | -0.0251 | +| n_updates | 87004 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000279 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1391 | +| iterations | 17798 | +| time_elapsed | 26191 | +| total_timesteps | 36450304 | +| train/ | | +| approx_kl | 0.019393334 | +| clip_fraction | 0.346 | +| clip_range | 0.0659 | +| entropy_loss | -5.3 | +| explained_variance | 0.559 | +| learning_rate | 4.13e-05 | +| loss | -0.0259 | +| n_updates | 87008 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000172 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1391 | +| iterations | 17799 | +| time_elapsed | 26192 | +| total_timesteps | 36452352 | +| train/ | | +| approx_kl | 0.01237515 | +| clip_fraction | 0.347 | +| clip_range | 0.0659 | +| entropy_loss | -5.62 | +| explained_variance | 0.677 | +| learning_rate | 4.13e-05 | +| loss | -0.0276 | +| n_updates | 87012 | +| policy_gradient_loss | -0.0184 | +| value_loss | 8.26e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1391 | +| iterations | 17800 | +| time_elapsed | 26194 | +| total_timesteps | 36454400 | +| train/ | | +| approx_kl | 0.010997849 | +| clip_fraction | 0.302 | +| clip_range | 0.0659 | +| entropy_loss | -5.37 | +| explained_variance | 0.732 | +| learning_rate | 4.13e-05 | +| loss | -0.0258 | +| n_updates | 87016 | +| policy_gradient_loss | -0.0158 | +| value_loss | 9.37e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1391 | +| iterations | 17801 | +| time_elapsed | 26196 | +| total_timesteps | 36456448 | +| train/ | | +| approx_kl | 0.011346562 | +| clip_fraction | 0.328 | +| clip_range | 0.0659 | +| entropy_loss | -5.21 | +| explained_variance | 0.62 | +| learning_rate | 4.13e-05 | +| loss | -0.023 | +| n_updates | 87020 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1391 | +| iterations | 17802 | +| time_elapsed | 26197 | +| total_timesteps | 36458496 | +| train/ | | +| approx_kl | 0.015163306 | +| clip_fraction | 0.343 | +| clip_range | 0.0659 | +| entropy_loss | -5.98 | +| explained_variance | 0.395 | +| learning_rate | 4.13e-05 | +| loss | -0.0256 | +| n_updates | 87024 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000113 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1391 | +| iterations | 17803 | +| time_elapsed | 26199 | +| total_timesteps | 36460544 | +| train/ | | +| approx_kl | 0.013051959 | +| clip_fraction | 0.346 | +| clip_range | 0.0659 | +| entropy_loss | -6.43 | +| explained_variance | 0.252 | +| learning_rate | 4.13e-05 | +| loss | -0.0281 | +| n_updates | 87028 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000129 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1391 | +| iterations | 17804 | +| time_elapsed | 26200 | +| total_timesteps | 36462592 | +| train/ | | +| approx_kl | 0.0100633595 | +| clip_fraction | 0.312 | +| clip_range | 0.0659 | +| entropy_loss | -6.4 | +| explained_variance | 0.229 | +| learning_rate | 4.13e-05 | +| loss | -0.0248 | +| n_updates | 87032 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000351 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1391 | +| iterations | 17805 | +| time_elapsed | 26202 | +| total_timesteps | 36464640 | +| train/ | | +| approx_kl | 0.0121594835 | +| clip_fraction | 0.298 | +| clip_range | 0.0659 | +| entropy_loss | -5.95 | +| explained_variance | 0.249 | +| learning_rate | 4.13e-05 | +| loss | -0.017 | +| n_updates | 87036 | +| policy_gradient_loss | -0.0139 | +| value_loss | 0.000365 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1391 | +| iterations | 17806 | +| time_elapsed | 26203 | +| total_timesteps | 36466688 | +| train/ | | +| approx_kl | 0.011120706 | +| clip_fraction | 0.315 | +| clip_range | 0.0659 | +| entropy_loss | -5.66 | +| explained_variance | 0.289 | +| learning_rate | 4.13e-05 | +| loss | -0.0234 | +| n_updates | 87040 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.00034 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1391 | +| iterations | 17807 | +| time_elapsed | 26205 | +| total_timesteps | 36468736 | +| train/ | | +| approx_kl | 0.015363203 | +| clip_fraction | 0.37 | +| clip_range | 0.0659 | +| entropy_loss | -5.73 | +| explained_variance | 0.522 | +| learning_rate | 4.13e-05 | +| loss | -0.0279 | +| n_updates | 87044 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000144 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1391 | +| iterations | 17808 | +| time_elapsed | 26206 | +| total_timesteps | 36470784 | +| train/ | | +| approx_kl | 0.012659155 | +| clip_fraction | 0.364 | +| clip_range | 0.0659 | +| entropy_loss | -6.11 | +| explained_variance | -0.055 | +| learning_rate | 4.13e-05 | +| loss | -0.0357 | +| n_updates | 87048 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000128 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1391 | +| iterations | 17809 | +| time_elapsed | 26208 | +| total_timesteps | 36472832 | +| train/ | | +| approx_kl | 0.011299083 | +| clip_fraction | 0.334 | +| clip_range | 0.0659 | +| entropy_loss | -6.16 | +| explained_variance | 0.304 | +| learning_rate | 4.13e-05 | +| loss | -0.027 | +| n_updates | 87052 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.00025 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1391 | +| iterations | 17810 | +| time_elapsed | 26209 | +| total_timesteps | 36474880 | +| train/ | | +| approx_kl | 0.014291681 | +| clip_fraction | 0.352 | +| clip_range | 0.0659 | +| entropy_loss | -5.36 | +| explained_variance | 0.639 | +| learning_rate | 4.13e-05 | +| loss | -0.0272 | +| n_updates | 87056 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000138 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1391 | +| iterations | 17811 | +| time_elapsed | 26211 | +| total_timesteps | 36476928 | +| train/ | | +| approx_kl | 0.01582202 | +| clip_fraction | 0.329 | +| clip_range | 0.0659 | +| entropy_loss | -5.49 | +| explained_variance | 0.243 | +| learning_rate | 4.13e-05 | +| loss | -0.0221 | +| n_updates | 87060 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.000392 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1391 | +| iterations | 17812 | +| time_elapsed | 26212 | +| total_timesteps | 36478976 | +| train/ | | +| approx_kl | 0.011723658 | +| clip_fraction | 0.314 | +| clip_range | 0.0659 | +| entropy_loss | -5.15 | +| explained_variance | 0.272 | +| learning_rate | 4.13e-05 | +| loss | -0.0285 | +| n_updates | 87064 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000159 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1391 | +| iterations | 17813 | +| time_elapsed | 26214 | +| total_timesteps | 36481024 | +| train/ | | +| approx_kl | 0.015324326 | +| clip_fraction | 0.359 | +| clip_range | 0.0659 | +| entropy_loss | -5.7 | +| explained_variance | 0.375 | +| learning_rate | 4.13e-05 | +| loss | -0.0333 | +| n_updates | 87068 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000148 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1391 | +| iterations | 17814 | +| time_elapsed | 26215 | +| total_timesteps | 36483072 | +| train/ | | +| approx_kl | 0.01604481 | +| clip_fraction | 0.342 | +| clip_range | 0.0659 | +| entropy_loss | -5.61 | +| explained_variance | 0.592 | +| learning_rate | 4.13e-05 | +| loss | -0.0283 | +| n_updates | 87072 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000121 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1391 | +| iterations | 17815 | +| time_elapsed | 26217 | +| total_timesteps | 36485120 | +| train/ | | +| approx_kl | 0.012972325 | +| clip_fraction | 0.335 | +| clip_range | 0.0659 | +| entropy_loss | -5.47 | +| explained_variance | 0.6 | +| learning_rate | 4.13e-05 | +| loss | -0.0288 | +| n_updates | 87076 | +| policy_gradient_loss | -0.0181 | +| value_loss | 9.02e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1391 | +| iterations | 17816 | +| time_elapsed | 26219 | +| total_timesteps | 36487168 | +| train/ | | +| approx_kl | 0.011446139 | +| clip_fraction | 0.315 | +| clip_range | 0.0659 | +| entropy_loss | -5.81 | +| explained_variance | 0.482 | +| learning_rate | 4.13e-05 | +| loss | -0.0213 | +| n_updates | 87080 | +| policy_gradient_loss | -0.0141 | +| value_loss | 0.000234 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1391 | +| iterations | 17817 | +| time_elapsed | 26220 | +| total_timesteps | 36489216 | +| train/ | | +| approx_kl | 0.012696622 | +| clip_fraction | 0.317 | +| clip_range | 0.0659 | +| entropy_loss | -5.62 | +| explained_variance | 0.236 | +| learning_rate | 4.13e-05 | +| loss | -0.0268 | +| n_updates | 87084 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000215 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1391 | +| iterations | 17818 | +| time_elapsed | 26222 | +| total_timesteps | 36491264 | +| train/ | | +| approx_kl | 0.011806183 | +| clip_fraction | 0.333 | +| clip_range | 0.0659 | +| entropy_loss | -6.04 | +| explained_variance | 0.302 | +| learning_rate | 4.13e-05 | +| loss | -0.0298 | +| n_updates | 87088 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000101 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1391 | +| iterations | 17819 | +| time_elapsed | 26223 | +| total_timesteps | 36493312 | +| train/ | | +| approx_kl | 0.012049132 | +| clip_fraction | 0.338 | +| clip_range | 0.0659 | +| entropy_loss | -5.77 | +| explained_variance | 0.643 | +| learning_rate | 4.13e-05 | +| loss | -0.0244 | +| n_updates | 87092 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000119 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1391 | +| iterations | 17820 | +| time_elapsed | 26225 | +| total_timesteps | 36495360 | +| train/ | | +| approx_kl | 0.011521701 | +| clip_fraction | 0.317 | +| clip_range | 0.0659 | +| entropy_loss | -6.29 | +| explained_variance | 0.0873 | +| learning_rate | 4.13e-05 | +| loss | -0.0275 | +| n_updates | 87096 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000213 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1391 | +| iterations | 17821 | +| time_elapsed | 26226 | +| total_timesteps | 36497408 | +| train/ | | +| approx_kl | 0.013155299 | +| clip_fraction | 0.358 | +| clip_range | 0.0659 | +| entropy_loss | -6.33 | +| explained_variance | 0.474 | +| learning_rate | 4.13e-05 | +| loss | -0.0333 | +| n_updates | 87100 | +| policy_gradient_loss | -0.0237 | +| value_loss | 5.12e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1391 | +| iterations | 17822 | +| time_elapsed | 26228 | +| total_timesteps | 36499456 | +| train/ | | +| approx_kl | 0.013448041 | +| clip_fraction | 0.339 | +| clip_range | 0.0659 | +| entropy_loss | -6.25 | +| explained_variance | 0.218 | +| learning_rate | 4.13e-05 | +| loss | -0.0327 | +| n_updates | 87104 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000216 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1391 | +| iterations | 17823 | +| time_elapsed | 26229 | +| total_timesteps | 36501504 | +| train/ | | +| approx_kl | 0.011318688 | +| clip_fraction | 0.333 | +| clip_range | 0.0659 | +| entropy_loss | -5.69 | +| explained_variance | 0.421 | +| learning_rate | 4.13e-05 | +| loss | -0.0273 | +| n_updates | 87108 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000246 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1391 | +| iterations | 17824 | +| time_elapsed | 26231 | +| total_timesteps | 36503552 | +| train/ | | +| approx_kl | 0.012762897 | +| clip_fraction | 0.349 | +| clip_range | 0.0659 | +| entropy_loss | -5.4 | +| explained_variance | 0.463 | +| learning_rate | 4.13e-05 | +| loss | -0.0234 | +| n_updates | 87112 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000171 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1391 | +| iterations | 17825 | +| time_elapsed | 26232 | +| total_timesteps | 36505600 | +| train/ | | +| approx_kl | 0.013188202 | +| clip_fraction | 0.356 | +| clip_range | 0.0659 | +| entropy_loss | -5.82 | +| explained_variance | 0.345 | +| learning_rate | 4.13e-05 | +| loss | -0.0307 | +| n_updates | 87116 | +| policy_gradient_loss | -0.02 | +| value_loss | 9.63e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1391 | +| iterations | 17826 | +| time_elapsed | 26234 | +| total_timesteps | 36507648 | +| train/ | | +| approx_kl | 0.014261209 | +| clip_fraction | 0.31 | +| clip_range | 0.0659 | +| entropy_loss | -6.24 | +| explained_variance | 0.275 | +| learning_rate | 4.13e-05 | +| loss | -0.0258 | +| n_updates | 87120 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000172 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1391 | +| iterations | 17827 | +| time_elapsed | 26235 | +| total_timesteps | 36509696 | +| train/ | | +| approx_kl | 0.011977686 | +| clip_fraction | 0.343 | +| clip_range | 0.0659 | +| entropy_loss | -6.43 | +| explained_variance | 0.359 | +| learning_rate | 4.13e-05 | +| loss | -0.0274 | +| n_updates | 87124 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000132 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1391 | +| iterations | 17828 | +| time_elapsed | 26237 | +| total_timesteps | 36511744 | +| train/ | | +| approx_kl | 0.011768693 | +| clip_fraction | 0.319 | +| clip_range | 0.0659 | +| entropy_loss | -6.59 | +| explained_variance | -0.0323 | +| learning_rate | 4.13e-05 | +| loss | -0.0311 | +| n_updates | 87128 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000184 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1391 | +| iterations | 17829 | +| time_elapsed | 26238 | +| total_timesteps | 36513792 | +| train/ | | +| approx_kl | 0.0134628285 | +| clip_fraction | 0.318 | +| clip_range | 0.0659 | +| entropy_loss | -6.03 | +| explained_variance | 0.679 | +| learning_rate | 4.13e-05 | +| loss | -0.033 | +| n_updates | 87132 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000141 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1391 | +| iterations | 17830 | +| time_elapsed | 26240 | +| total_timesteps | 36515840 | +| train/ | | +| approx_kl | 0.014996084 | +| clip_fraction | 0.336 | +| clip_range | 0.0659 | +| entropy_loss | -5.54 | +| explained_variance | -0.0312 | +| learning_rate | 4.13e-05 | +| loss | -0.0301 | +| n_updates | 87136 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000132 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1391 | +| iterations | 17831 | +| time_elapsed | 26241 | +| total_timesteps | 36517888 | +| train/ | | +| approx_kl | 0.011949381 | +| clip_fraction | 0.319 | +| clip_range | 0.0659 | +| entropy_loss | -5.88 | +| explained_variance | 0.625 | +| learning_rate | 4.13e-05 | +| loss | -0.0255 | +| n_updates | 87140 | +| policy_gradient_loss | -0.0172 | +| value_loss | 6.24e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1391 | +| iterations | 17832 | +| time_elapsed | 26243 | +| total_timesteps | 36519936 | +| train/ | | +| approx_kl | 0.010503936 | +| clip_fraction | 0.318 | +| clip_range | 0.0659 | +| entropy_loss | -5.89 | +| explained_variance | 0.128 | +| learning_rate | 4.13e-05 | +| loss | -0.0255 | +| n_updates | 87144 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000175 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1391 | +| iterations | 17833 | +| time_elapsed | 26244 | +| total_timesteps | 36521984 | +| train/ | | +| approx_kl | 0.017099395 | +| clip_fraction | 0.344 | +| clip_range | 0.0659 | +| entropy_loss | -5.64 | +| explained_variance | 0.618 | +| learning_rate | 4.13e-05 | +| loss | -0.0254 | +| n_updates | 87148 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.00013 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1391 | +| iterations | 17834 | +| time_elapsed | 26246 | +| total_timesteps | 36524032 | +| train/ | | +| approx_kl | 0.012748482 | +| clip_fraction | 0.334 | +| clip_range | 0.0659 | +| entropy_loss | -5.94 | +| explained_variance | 0.546 | +| learning_rate | 4.13e-05 | +| loss | -0.025 | +| n_updates | 87152 | +| policy_gradient_loss | -0.0168 | +| value_loss | 8.09e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1391 | +| iterations | 17835 | +| time_elapsed | 26248 | +| total_timesteps | 36526080 | +| train/ | | +| approx_kl | 0.012909079 | +| clip_fraction | 0.329 | +| clip_range | 0.0659 | +| entropy_loss | -5.95 | +| explained_variance | 0.31 | +| learning_rate | 4.13e-05 | +| loss | -0.0291 | +| n_updates | 87156 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000171 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1391 | +| iterations | 17836 | +| time_elapsed | 26249 | +| total_timesteps | 36528128 | +| train/ | | +| approx_kl | 0.010109361 | +| clip_fraction | 0.319 | +| clip_range | 0.0659 | +| entropy_loss | -6.22 | +| explained_variance | 0.53 | +| learning_rate | 4.13e-05 | +| loss | -0.0278 | +| n_updates | 87160 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1391 | +| iterations | 17837 | +| time_elapsed | 26251 | +| total_timesteps | 36530176 | +| train/ | | +| approx_kl | 0.007494162 | +| clip_fraction | 0.292 | +| clip_range | 0.0659 | +| entropy_loss | -6.66 | +| explained_variance | 0.227 | +| learning_rate | 4.13e-05 | +| loss | -0.0175 | +| n_updates | 87164 | +| policy_gradient_loss | -0.0138 | +| value_loss | 0.000221 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1391 | +| iterations | 17838 | +| time_elapsed | 26252 | +| total_timesteps | 36532224 | +| train/ | | +| approx_kl | 0.010248281 | +| clip_fraction | 0.312 | +| clip_range | 0.0659 | +| entropy_loss | -5.71 | +| explained_variance | 0.438 | +| learning_rate | 4.13e-05 | +| loss | -0.0219 | +| n_updates | 87168 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000209 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1391 | +| iterations | 17839 | +| time_elapsed | 26254 | +| total_timesteps | 36534272 | +| train/ | | +| approx_kl | 0.011081355 | +| clip_fraction | 0.338 | +| clip_range | 0.0659 | +| entropy_loss | -6.17 | +| explained_variance | 0.457 | +| learning_rate | 4.13e-05 | +| loss | -0.0284 | +| n_updates | 87172 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000177 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1391 | +| iterations | 17840 | +| time_elapsed | 26255 | +| total_timesteps | 36536320 | +| train/ | | +| approx_kl | 0.014565556 | +| clip_fraction | 0.309 | +| clip_range | 0.0659 | +| entropy_loss | -5.12 | +| explained_variance | 0.555 | +| learning_rate | 4.13e-05 | +| loss | -0.0277 | +| n_updates | 87176 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000176 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1391 | +| iterations | 17841 | +| time_elapsed | 26257 | +| total_timesteps | 36538368 | +| train/ | | +| approx_kl | 0.01226843 | +| clip_fraction | 0.365 | +| clip_range | 0.0659 | +| entropy_loss | -5.69 | +| explained_variance | 0.321 | +| learning_rate | 4.13e-05 | +| loss | -0.0328 | +| n_updates | 87180 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000112 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1391 | +| iterations | 17842 | +| time_elapsed | 26258 | +| total_timesteps | 36540416 | +| train/ | | +| approx_kl | 0.0147494525 | +| clip_fraction | 0.372 | +| clip_range | 0.0659 | +| entropy_loss | -5.99 | +| explained_variance | 0.169 | +| learning_rate | 4.13e-05 | +| loss | -0.0301 | +| n_updates | 87184 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.0001 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1391 | +| iterations | 17843 | +| time_elapsed | 26260 | +| total_timesteps | 36542464 | +| train/ | | +| approx_kl | 0.015250076 | +| clip_fraction | 0.334 | +| clip_range | 0.0659 | +| entropy_loss | -6.11 | +| explained_variance | 0.418 | +| learning_rate | 4.13e-05 | +| loss | -0.0272 | +| n_updates | 87188 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000227 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1391 | +| iterations | 17844 | +| time_elapsed | 26261 | +| total_timesteps | 36544512 | +| train/ | | +| approx_kl | 0.014871955 | +| clip_fraction | 0.35 | +| clip_range | 0.0659 | +| entropy_loss | -6.1 | +| explained_variance | -0.0772 | +| learning_rate | 4.13e-05 | +| loss | -0.028 | +| n_updates | 87192 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000141 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1391 | +| iterations | 17845 | +| time_elapsed | 26263 | +| total_timesteps | 36546560 | +| train/ | | +| approx_kl | 0.014540805 | +| clip_fraction | 0.359 | +| clip_range | 0.0659 | +| entropy_loss | -6.12 | +| explained_variance | 0.311 | +| learning_rate | 4.13e-05 | +| loss | -0.0367 | +| n_updates | 87196 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000101 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1391 | +| iterations | 17846 | +| time_elapsed | 26264 | +| total_timesteps | 36548608 | +| train/ | | +| approx_kl | 0.011428682 | +| clip_fraction | 0.309 | +| clip_range | 0.0659 | +| entropy_loss | -6.33 | +| explained_variance | 0.364 | +| learning_rate | 4.13e-05 | +| loss | -0.0239 | +| n_updates | 87200 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000137 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1391 | +| iterations | 17847 | +| time_elapsed | 26266 | +| total_timesteps | 36550656 | +| train/ | | +| approx_kl | 0.012620936 | +| clip_fraction | 0.289 | +| clip_range | 0.0659 | +| entropy_loss | -5.04 | +| explained_variance | 0.619 | +| learning_rate | 4.13e-05 | +| loss | -0.0251 | +| n_updates | 87204 | +| policy_gradient_loss | -0.0143 | +| value_loss | 0.000226 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1391 | +| iterations | 17848 | +| time_elapsed | 26267 | +| total_timesteps | 36552704 | +| train/ | | +| approx_kl | 0.0129987765 | +| clip_fraction | 0.319 | +| clip_range | 0.0659 | +| entropy_loss | -5.13 | +| explained_variance | 0.226 | +| learning_rate | 4.13e-05 | +| loss | -0.0236 | +| n_updates | 87208 | +| policy_gradient_loss | -0.0143 | +| value_loss | 0.000402 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1391 | +| iterations | 17849 | +| time_elapsed | 26269 | +| total_timesteps | 36554752 | +| train/ | | +| approx_kl | 0.015406301 | +| clip_fraction | 0.378 | +| clip_range | 0.0659 | +| entropy_loss | -5.3 | +| explained_variance | 0.58 | +| learning_rate | 4.13e-05 | +| loss | -0.0338 | +| n_updates | 87212 | +| policy_gradient_loss | -0.0223 | +| value_loss | 7.88e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1391 | +| iterations | 17850 | +| time_elapsed | 26270 | +| total_timesteps | 36556800 | +| train/ | | +| approx_kl | 0.014403895 | +| clip_fraction | 0.403 | +| clip_range | 0.0659 | +| entropy_loss | -5.73 | +| explained_variance | 0.68 | +| learning_rate | 4.13e-05 | +| loss | -0.0408 | +| n_updates | 87216 | +| policy_gradient_loss | -0.0253 | +| value_loss | 4.67e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1391 | +| iterations | 17851 | +| time_elapsed | 26272 | +| total_timesteps | 36558848 | +| train/ | | +| approx_kl | 0.013088433 | +| clip_fraction | 0.36 | +| clip_range | 0.0659 | +| entropy_loss | -6.19 | +| explained_variance | 0.118 | +| learning_rate | 4.13e-05 | +| loss | -0.0272 | +| n_updates | 87220 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000141 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1391 | +| iterations | 17852 | +| time_elapsed | 26273 | +| total_timesteps | 36560896 | +| train/ | | +| approx_kl | 0.013077198 | +| clip_fraction | 0.341 | +| clip_range | 0.0659 | +| entropy_loss | -6.33 | +| explained_variance | 0.312 | +| learning_rate | 4.13e-05 | +| loss | -0.0259 | +| n_updates | 87224 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000132 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1391 | +| iterations | 17853 | +| time_elapsed | 26275 | +| total_timesteps | 36562944 | +| train/ | | +| approx_kl | 0.017926395 | +| clip_fraction | 0.329 | +| clip_range | 0.0659 | +| entropy_loss | -5.55 | +| explained_variance | 0.404 | +| learning_rate | 4.13e-05 | +| loss | -0.028 | +| n_updates | 87228 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000154 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1391 | +| iterations | 17854 | +| time_elapsed | 26277 | +| total_timesteps | 36564992 | +| train/ | | +| approx_kl | 0.013577185 | +| clip_fraction | 0.388 | +| clip_range | 0.0659 | +| entropy_loss | -6.12 | +| explained_variance | 0.575 | +| learning_rate | 4.13e-05 | +| loss | -0.0279 | +| n_updates | 87232 | +| policy_gradient_loss | -0.0217 | +| value_loss | 4.32e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1391 | +| iterations | 17855 | +| time_elapsed | 26278 | +| total_timesteps | 36567040 | +| train/ | | +| approx_kl | 0.013263769 | +| clip_fraction | 0.354 | +| clip_range | 0.0659 | +| entropy_loss | -6.38 | +| explained_variance | 0.0796 | +| learning_rate | 4.13e-05 | +| loss | -0.029 | +| n_updates | 87236 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000128 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1391 | +| iterations | 17856 | +| time_elapsed | 26280 | +| total_timesteps | 36569088 | +| train/ | | +| approx_kl | 0.011777609 | +| clip_fraction | 0.302 | +| clip_range | 0.0659 | +| entropy_loss | -5.6 | +| explained_variance | 0.464 | +| learning_rate | 4.13e-05 | +| loss | -0.0265 | +| n_updates | 87240 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.00031 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1391 | +| iterations | 17857 | +| time_elapsed | 26281 | +| total_timesteps | 36571136 | +| train/ | | +| approx_kl | 0.015603045 | +| clip_fraction | 0.376 | +| clip_range | 0.0659 | +| entropy_loss | -5.12 | +| explained_variance | 0.829 | +| learning_rate | 4.13e-05 | +| loss | -0.0331 | +| n_updates | 87244 | +| policy_gradient_loss | -0.0224 | +| value_loss | 5.83e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1391 | +| iterations | 17858 | +| time_elapsed | 26283 | +| total_timesteps | 36573184 | +| train/ | | +| approx_kl | 0.013278386 | +| clip_fraction | 0.359 | +| clip_range | 0.0659 | +| entropy_loss | -5.59 | +| explained_variance | 0.592 | +| learning_rate | 4.13e-05 | +| loss | -0.0296 | +| n_updates | 87248 | +| policy_gradient_loss | -0.0197 | +| value_loss | 6.7e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1391 | +| iterations | 17859 | +| time_elapsed | 26284 | +| total_timesteps | 36575232 | +| train/ | | +| approx_kl | 0.010665104 | +| clip_fraction | 0.333 | +| clip_range | 0.0659 | +| entropy_loss | -6.41 | +| explained_variance | 0.225 | +| learning_rate | 4.13e-05 | +| loss | -0.027 | +| n_updates | 87252 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000177 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1391 | +| iterations | 17860 | +| time_elapsed | 26286 | +| total_timesteps | 36577280 | +| train/ | | +| approx_kl | 0.010173721 | +| clip_fraction | 0.284 | +| clip_range | 0.0659 | +| entropy_loss | -6.31 | +| explained_variance | 0.166 | +| learning_rate | 4.13e-05 | +| loss | -0.0213 | +| n_updates | 87256 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000246 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1391 | +| iterations | 17861 | +| time_elapsed | 26287 | +| total_timesteps | 36579328 | +| train/ | | +| approx_kl | 0.014423532 | +| clip_fraction | 0.344 | +| clip_range | 0.0659 | +| entropy_loss | -6.4 | +| explained_variance | -0.105 | +| learning_rate | 4.13e-05 | +| loss | -0.026 | +| n_updates | 87260 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000165 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1391 | +| iterations | 17862 | +| time_elapsed | 26289 | +| total_timesteps | 36581376 | +| train/ | | +| approx_kl | 0.012729145 | +| clip_fraction | 0.374 | +| clip_range | 0.0659 | +| entropy_loss | -5.93 | +| explained_variance | 0.272 | +| learning_rate | 4.13e-05 | +| loss | -0.02 | +| n_updates | 87264 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000326 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1391 | +| iterations | 17863 | +| time_elapsed | 26290 | +| total_timesteps | 36583424 | +| train/ | | +| approx_kl | 0.015421036 | +| clip_fraction | 0.329 | +| clip_range | 0.0659 | +| entropy_loss | -5.13 | +| explained_variance | 0.525 | +| learning_rate | 4.13e-05 | +| loss | -0.0295 | +| n_updates | 87268 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000202 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1391 | +| iterations | 17864 | +| time_elapsed | 26292 | +| total_timesteps | 36585472 | +| train/ | | +| approx_kl | 0.01511311 | +| clip_fraction | 0.373 | +| clip_range | 0.0659 | +| entropy_loss | -5.36 | +| explained_variance | 0.534 | +| learning_rate | 4.13e-05 | +| loss | -0.0317 | +| n_updates | 87272 | +| policy_gradient_loss | -0.021 | +| value_loss | 8.58e-05 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1391 | +| iterations | 17865 | +| time_elapsed | 26293 | +| total_timesteps | 36587520 | +| train/ | | +| approx_kl | 0.01287001 | +| clip_fraction | 0.355 | +| clip_range | 0.0659 | +| entropy_loss | -5.63 | +| explained_variance | 0.516 | +| learning_rate | 4.13e-05 | +| loss | -0.0244 | +| n_updates | 87276 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000122 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1391 | +| iterations | 17866 | +| time_elapsed | 26295 | +| total_timesteps | 36589568 | +| train/ | | +| approx_kl | 0.016014917 | +| clip_fraction | 0.35 | +| clip_range | 0.0659 | +| entropy_loss | -5.87 | +| explained_variance | -0.00858 | +| learning_rate | 4.13e-05 | +| loss | -0.0333 | +| n_updates | 87280 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000169 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1391 | +| iterations | 17867 | +| time_elapsed | 26296 | +| total_timesteps | 36591616 | +| train/ | | +| approx_kl | 0.0138371475 | +| clip_fraction | 0.346 | +| clip_range | 0.0659 | +| entropy_loss | -5.73 | +| explained_variance | 0.187 | +| learning_rate | 4.13e-05 | +| loss | -0.0276 | +| n_updates | 87284 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000194 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1391 | +| iterations | 17868 | +| time_elapsed | 26298 | +| total_timesteps | 36593664 | +| train/ | | +| approx_kl | 0.01334134 | +| clip_fraction | 0.353 | +| clip_range | 0.0659 | +| entropy_loss | -6.07 | +| explained_variance | 0.355 | +| learning_rate | 4.13e-05 | +| loss | -0.0287 | +| n_updates | 87288 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000138 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1391 | +| iterations | 17869 | +| time_elapsed | 26299 | +| total_timesteps | 36595712 | +| train/ | | +| approx_kl | 0.014822216 | +| clip_fraction | 0.37 | +| clip_range | 0.0659 | +| entropy_loss | -6.33 | +| explained_variance | 0.00654 | +| learning_rate | 4.13e-05 | +| loss | -0.0287 | +| n_updates | 87292 | +| policy_gradient_loss | -0.0201 | +| value_loss | 8.63e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1391 | +| iterations | 17870 | +| time_elapsed | 26301 | +| total_timesteps | 36597760 | +| train/ | | +| approx_kl | 0.012469901 | +| clip_fraction | 0.349 | +| clip_range | 0.0659 | +| entropy_loss | -5.02 | +| explained_variance | 0.857 | +| learning_rate | 4.13e-05 | +| loss | -0.0313 | +| n_updates | 87296 | +| policy_gradient_loss | -0.0185 | +| value_loss | 5.78e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1391 | +| iterations | 17871 | +| time_elapsed | 26302 | +| total_timesteps | 36599808 | +| train/ | | +| approx_kl | 0.01452725 | +| clip_fraction | 0.29 | +| clip_range | 0.0659 | +| entropy_loss | -5.54 | +| explained_variance | 0.523 | +| learning_rate | 4.13e-05 | +| loss | -0.019 | +| n_updates | 87300 | +| policy_gradient_loss | -0.0129 | +| value_loss | 0.000216 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1391 | +| iterations | 17872 | +| time_elapsed | 26304 | +| total_timesteps | 36601856 | +| train/ | | +| approx_kl | 0.009512188 | +| clip_fraction | 0.296 | +| clip_range | 0.0659 | +| entropy_loss | -5.06 | +| explained_variance | 0.561 | +| learning_rate | 4.13e-05 | +| loss | -0.0219 | +| n_updates | 87304 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000203 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1391 | +| iterations | 17873 | +| time_elapsed | 26306 | +| total_timesteps | 36603904 | +| train/ | | +| approx_kl | 0.0139149 | +| clip_fraction | 0.326 | +| clip_range | 0.0658 | +| entropy_loss | -5.63 | +| explained_variance | 0.25 | +| learning_rate | 4.13e-05 | +| loss | -0.0247 | +| n_updates | 87308 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000126 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1391 | +| iterations | 17874 | +| time_elapsed | 26307 | +| total_timesteps | 36605952 | +| train/ | | +| approx_kl | 0.018645234 | +| clip_fraction | 0.389 | +| clip_range | 0.0658 | +| entropy_loss | -6.02 | +| explained_variance | -0.28 | +| learning_rate | 4.13e-05 | +| loss | -0.0298 | +| n_updates | 87312 | +| policy_gradient_loss | -0.0208 | +| value_loss | 7.04e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1391 | +| iterations | 17875 | +| time_elapsed | 26309 | +| total_timesteps | 36608000 | +| train/ | | +| approx_kl | 0.012914037 | +| clip_fraction | 0.354 | +| clip_range | 0.0658 | +| entropy_loss | -6.03 | +| explained_variance | 0.463 | +| learning_rate | 4.13e-05 | +| loss | -0.0315 | +| n_updates | 87316 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000161 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1391 | +| iterations | 17876 | +| time_elapsed | 26310 | +| total_timesteps | 36610048 | +| train/ | | +| approx_kl | 0.013475041 | +| clip_fraction | 0.34 | +| clip_range | 0.0658 | +| entropy_loss | -5.46 | +| explained_variance | 0.687 | +| learning_rate | 4.13e-05 | +| loss | -0.0277 | +| n_updates | 87320 | +| policy_gradient_loss | -0.017 | +| value_loss | 9.47e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1391 | +| iterations | 17877 | +| time_elapsed | 26312 | +| total_timesteps | 36612096 | +| train/ | | +| approx_kl | 0.014759477 | +| clip_fraction | 0.369 | +| clip_range | 0.0658 | +| entropy_loss | -5.57 | +| explained_variance | 0.4 | +| learning_rate | 4.13e-05 | +| loss | -0.0287 | +| n_updates | 87324 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000104 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1391 | +| iterations | 17878 | +| time_elapsed | 26313 | +| total_timesteps | 36614144 | +| train/ | | +| approx_kl | 0.014245764 | +| clip_fraction | 0.354 | +| clip_range | 0.0658 | +| entropy_loss | -6.16 | +| explained_variance | 0.498 | +| learning_rate | 4.13e-05 | +| loss | -0.024 | +| n_updates | 87328 | +| policy_gradient_loss | -0.0182 | +| value_loss | 7.29e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1391 | +| iterations | 17879 | +| time_elapsed | 26315 | +| total_timesteps | 36616192 | +| train/ | | +| approx_kl | 0.014873061 | +| clip_fraction | 0.336 | +| clip_range | 0.0658 | +| entropy_loss | -5.64 | +| explained_variance | 0.445 | +| learning_rate | 4.13e-05 | +| loss | -0.0258 | +| n_updates | 87332 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000179 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1391 | +| iterations | 17880 | +| time_elapsed | 26316 | +| total_timesteps | 36618240 | +| train/ | | +| approx_kl | 0.011619265 | +| clip_fraction | 0.325 | +| clip_range | 0.0658 | +| entropy_loss | -6.14 | +| explained_variance | -0.0889 | +| learning_rate | 4.13e-05 | +| loss | -0.0285 | +| n_updates | 87336 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000141 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1391 | +| iterations | 17881 | +| time_elapsed | 26318 | +| total_timesteps | 36620288 | +| train/ | | +| approx_kl | 0.013384223 | +| clip_fraction | 0.358 | +| clip_range | 0.0658 | +| entropy_loss | -5.99 | +| explained_variance | 0.525 | +| learning_rate | 4.13e-05 | +| loss | -0.03 | +| n_updates | 87340 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000126 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1391 | +| iterations | 17882 | +| time_elapsed | 26319 | +| total_timesteps | 36622336 | +| train/ | | +| approx_kl | 0.01597188 | +| clip_fraction | 0.329 | +| clip_range | 0.0658 | +| entropy_loss | -5.71 | +| explained_variance | 0.575 | +| learning_rate | 4.13e-05 | +| loss | -0.019 | +| n_updates | 87344 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000119 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1391 | +| iterations | 17883 | +| time_elapsed | 26321 | +| total_timesteps | 36624384 | +| train/ | | +| approx_kl | 0.012555292 | +| clip_fraction | 0.316 | +| clip_range | 0.0658 | +| entropy_loss | -5.06 | +| explained_variance | 0.532 | +| learning_rate | 4.13e-05 | +| loss | -0.021 | +| n_updates | 87348 | +| policy_gradient_loss | -0.0141 | +| value_loss | 0.000262 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1391 | +| iterations | 17884 | +| time_elapsed | 26322 | +| total_timesteps | 36626432 | +| train/ | | +| approx_kl | 0.013237245 | +| clip_fraction | 0.362 | +| clip_range | 0.0658 | +| entropy_loss | -5.93 | +| explained_variance | -0.127 | +| learning_rate | 4.13e-05 | +| loss | -0.0375 | +| n_updates | 87352 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000115 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1391 | +| iterations | 17885 | +| time_elapsed | 26324 | +| total_timesteps | 36628480 | +| train/ | | +| approx_kl | 0.014477285 | +| clip_fraction | 0.359 | +| clip_range | 0.0658 | +| entropy_loss | -5.82 | +| explained_variance | 0.56 | +| learning_rate | 4.13e-05 | +| loss | -0.0343 | +| n_updates | 87356 | +| policy_gradient_loss | -0.0201 | +| value_loss | 8.57e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1391 | +| iterations | 17886 | +| time_elapsed | 26325 | +| total_timesteps | 36630528 | +| train/ | | +| approx_kl | 0.012682583 | +| clip_fraction | 0.332 | +| clip_range | 0.0658 | +| entropy_loss | -5.95 | +| explained_variance | 0.315 | +| learning_rate | 4.13e-05 | +| loss | -0.0299 | +| n_updates | 87360 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000135 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1391 | +| iterations | 17887 | +| time_elapsed | 26327 | +| total_timesteps | 36632576 | +| train/ | | +| approx_kl | 0.01347966 | +| clip_fraction | 0.323 | +| clip_range | 0.0658 | +| entropy_loss | -6.33 | +| explained_variance | 0.189 | +| learning_rate | 4.13e-05 | +| loss | -0.0264 | +| n_updates | 87364 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000328 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1391 | +| iterations | 17888 | +| time_elapsed | 26328 | +| total_timesteps | 36634624 | +| train/ | | +| approx_kl | 0.012386605 | +| clip_fraction | 0.325 | +| clip_range | 0.0658 | +| entropy_loss | -6.16 | +| explained_variance | 0.348 | +| learning_rate | 4.13e-05 | +| loss | -0.0247 | +| n_updates | 87368 | +| policy_gradient_loss | -0.0184 | +| value_loss | 9.01e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1391 | +| iterations | 17889 | +| time_elapsed | 26330 | +| total_timesteps | 36636672 | +| train/ | | +| approx_kl | 0.011298861 | +| clip_fraction | 0.333 | +| clip_range | 0.0658 | +| entropy_loss | -5.8 | +| explained_variance | 0.435 | +| learning_rate | 4.13e-05 | +| loss | -0.0301 | +| n_updates | 87372 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000165 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1391 | +| iterations | 17890 | +| time_elapsed | 26332 | +| total_timesteps | 36638720 | +| train/ | | +| approx_kl | 0.013877895 | +| clip_fraction | 0.345 | +| clip_range | 0.0658 | +| entropy_loss | -6.22 | +| explained_variance | 0.687 | +| learning_rate | 4.13e-05 | +| loss | -0.0341 | +| n_updates | 87376 | +| policy_gradient_loss | -0.0198 | +| value_loss | 5.53e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1391 | +| iterations | 17891 | +| time_elapsed | 26333 | +| total_timesteps | 36640768 | +| train/ | | +| approx_kl | 0.012682879 | +| clip_fraction | 0.323 | +| clip_range | 0.0658 | +| entropy_loss | -5.73 | +| explained_variance | 0.516 | +| learning_rate | 4.13e-05 | +| loss | -0.0226 | +| n_updates | 87380 | +| policy_gradient_loss | -0.0147 | +| value_loss | 0.000147 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1391 | +| iterations | 17892 | +| time_elapsed | 26335 | +| total_timesteps | 36642816 | +| train/ | | +| approx_kl | 0.011819088 | +| clip_fraction | 0.318 | +| clip_range | 0.0658 | +| entropy_loss | -5.2 | +| explained_variance | 0.477 | +| learning_rate | 4.13e-05 | +| loss | -0.0183 | +| n_updates | 87384 | +| policy_gradient_loss | -0.0132 | +| value_loss | 0.000248 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1391 | +| iterations | 17893 | +| time_elapsed | 26336 | +| total_timesteps | 36644864 | +| train/ | | +| approx_kl | 0.012192626 | +| clip_fraction | 0.347 | +| clip_range | 0.0658 | +| entropy_loss | -6.04 | +| explained_variance | 0.162 | +| learning_rate | 4.13e-05 | +| loss | -0.0284 | +| n_updates | 87388 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000126 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1391 | +| iterations | 17894 | +| time_elapsed | 26338 | +| total_timesteps | 36646912 | +| train/ | | +| approx_kl | 0.013268109 | +| clip_fraction | 0.347 | +| clip_range | 0.0658 | +| entropy_loss | -5.88 | +| explained_variance | 0.318 | +| learning_rate | 4.13e-05 | +| loss | -0.0239 | +| n_updates | 87392 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000125 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1391 | +| iterations | 17895 | +| time_elapsed | 26339 | +| total_timesteps | 36648960 | +| train/ | | +| approx_kl | 0.013394881 | +| clip_fraction | 0.34 | +| clip_range | 0.0658 | +| entropy_loss | -5.25 | +| explained_variance | 0.52 | +| learning_rate | 4.13e-05 | +| loss | -0.031 | +| n_updates | 87396 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000112 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1391 | +| iterations | 17896 | +| time_elapsed | 26341 | +| total_timesteps | 36651008 | +| train/ | | +| approx_kl | 0.012891324 | +| clip_fraction | 0.351 | +| clip_range | 0.0658 | +| entropy_loss | -5.98 | +| explained_variance | 0.00149 | +| learning_rate | 4.13e-05 | +| loss | -0.0339 | +| n_updates | 87400 | +| policy_gradient_loss | -0.0192 | +| value_loss | 9.52e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1391 | +| iterations | 17897 | +| time_elapsed | 26343 | +| total_timesteps | 36653056 | +| train/ | | +| approx_kl | 0.013230456 | +| clip_fraction | 0.319 | +| clip_range | 0.0658 | +| entropy_loss | -6.15 | +| explained_variance | 0.288 | +| learning_rate | 4.13e-05 | +| loss | -0.0219 | +| n_updates | 87404 | +| policy_gradient_loss | -0.014 | +| value_loss | 0.000233 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1391 | +| iterations | 17898 | +| time_elapsed | 26344 | +| total_timesteps | 36655104 | +| train/ | | +| approx_kl | 0.01589302 | +| clip_fraction | 0.334 | +| clip_range | 0.0658 | +| entropy_loss | -6.31 | +| explained_variance | -0.0384 | +| learning_rate | 4.13e-05 | +| loss | -0.03 | +| n_updates | 87408 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000194 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1391 | +| iterations | 17899 | +| time_elapsed | 26346 | +| total_timesteps | 36657152 | +| train/ | | +| approx_kl | 0.014072883 | +| clip_fraction | 0.337 | +| clip_range | 0.0658 | +| entropy_loss | -6.36 | +| explained_variance | 0.232 | +| learning_rate | 4.13e-05 | +| loss | -0.0275 | +| n_updates | 87412 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000173 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1391 | +| iterations | 17900 | +| time_elapsed | 26347 | +| total_timesteps | 36659200 | +| train/ | | +| approx_kl | 0.0142416 | +| clip_fraction | 0.392 | +| clip_range | 0.0658 | +| entropy_loss | -5.37 | +| explained_variance | 0.614 | +| learning_rate | 4.13e-05 | +| loss | -0.0285 | +| n_updates | 87416 | +| policy_gradient_loss | -0.02 | +| value_loss | 6.79e-05 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1391 | +| iterations | 17901 | +| time_elapsed | 26349 | +| total_timesteps | 36661248 | +| train/ | | +| approx_kl | 0.015280452 | +| clip_fraction | 0.325 | +| clip_range | 0.0658 | +| entropy_loss | -5.62 | +| explained_variance | 0.178 | +| learning_rate | 4.13e-05 | +| loss | -0.0269 | +| n_updates | 87420 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000204 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 1391 | +| iterations | 17902 | +| time_elapsed | 26350 | +| total_timesteps | 36663296 | +| train/ | | +| approx_kl | 0.015121134 | +| clip_fraction | 0.334 | +| clip_range | 0.0658 | +| entropy_loss | -5.55 | +| explained_variance | 0.517 | +| learning_rate | 4.13e-05 | +| loss | -0.0294 | +| n_updates | 87424 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000141 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.302 | +| time/ | | +| fps | 1391 | +| iterations | 17903 | +| time_elapsed | 26352 | +| total_timesteps | 36665344 | +| train/ | | +| approx_kl | 0.012374019 | +| clip_fraction | 0.32 | +| clip_range | 0.0658 | +| entropy_loss | -5.08 | +| explained_variance | 0.687 | +| learning_rate | 4.13e-05 | +| loss | -0.0267 | +| n_updates | 87428 | +| policy_gradient_loss | -0.0167 | +| value_loss | 8.74e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1391 | +| iterations | 17904 | +| time_elapsed | 26353 | +| total_timesteps | 36667392 | +| train/ | | +| approx_kl | 0.011786673 | +| clip_fraction | 0.34 | +| clip_range | 0.0658 | +| entropy_loss | -5.45 | +| explained_variance | 0.543 | +| learning_rate | 4.13e-05 | +| loss | -0.026 | +| n_updates | 87432 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000128 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1391 | +| iterations | 17905 | +| time_elapsed | 26355 | +| total_timesteps | 36669440 | +| train/ | | +| approx_kl | 0.011624405 | +| clip_fraction | 0.314 | +| clip_range | 0.0658 | +| entropy_loss | -6.12 | +| explained_variance | 0.371 | +| learning_rate | 4.13e-05 | +| loss | -0.0272 | +| n_updates | 87436 | +| policy_gradient_loss | -0.0142 | +| value_loss | 0.000223 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1391 | +| iterations | 17906 | +| time_elapsed | 26356 | +| total_timesteps | 36671488 | +| train/ | | +| approx_kl | 0.010396035 | +| clip_fraction | 0.326 | +| clip_range | 0.0658 | +| entropy_loss | -5.89 | +| explained_variance | 0.368 | +| learning_rate | 4.13e-05 | +| loss | -0.032 | +| n_updates | 87440 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000222 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1391 | +| iterations | 17907 | +| time_elapsed | 26358 | +| total_timesteps | 36673536 | +| train/ | | +| approx_kl | 0.009860822 | +| clip_fraction | 0.357 | +| clip_range | 0.0658 | +| entropy_loss | -6.52 | +| explained_variance | -0.376 | +| learning_rate | 4.13e-05 | +| loss | -0.0299 | +| n_updates | 87444 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000117 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1391 | +| iterations | 17908 | +| time_elapsed | 26359 | +| total_timesteps | 36675584 | +| train/ | | +| approx_kl | 0.010375749 | +| clip_fraction | 0.357 | +| clip_range | 0.0658 | +| entropy_loss | -6.74 | +| explained_variance | -0.0744 | +| learning_rate | 4.13e-05 | +| loss | -0.0294 | +| n_updates | 87448 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000115 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 1391 | +| iterations | 17909 | +| time_elapsed | 26361 | +| total_timesteps | 36677632 | +| train/ | | +| approx_kl | 0.008730477 | +| clip_fraction | 0.306 | +| clip_range | 0.0658 | +| entropy_loss | -6.41 | +| explained_variance | 0.527 | +| learning_rate | 4.13e-05 | +| loss | -0.0221 | +| n_updates | 87452 | +| policy_gradient_loss | -0.0138 | +| value_loss | 0.000133 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.298 | +| time/ | | +| fps | 1391 | +| iterations | 17910 | +| time_elapsed | 26362 | +| total_timesteps | 36679680 | +| train/ | | +| approx_kl | 0.010734903 | +| clip_fraction | 0.291 | +| clip_range | 0.0658 | +| entropy_loss | -5.36 | +| explained_variance | 0.613 | +| learning_rate | 4.13e-05 | +| loss | -0.0242 | +| n_updates | 87456 | +| policy_gradient_loss | -0.0114 | +| value_loss | 0.000213 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.3 | +| time/ | | +| fps | 1391 | +| iterations | 17911 | +| time_elapsed | 26364 | +| total_timesteps | 36681728 | +| train/ | | +| approx_kl | 0.014670614 | +| clip_fraction | 0.323 | +| clip_range | 0.0658 | +| entropy_loss | -4.7 | +| explained_variance | 0.592 | +| learning_rate | 4.13e-05 | +| loss | -0.0251 | +| n_updates | 87460 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000149 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.3 | +| time/ | | +| fps | 1391 | +| iterations | 17912 | +| time_elapsed | 26366 | +| total_timesteps | 36683776 | +| train/ | | +| approx_kl | 0.013999719 | +| clip_fraction | 0.364 | +| clip_range | 0.0658 | +| entropy_loss | -5.83 | +| explained_variance | -0.0928 | +| learning_rate | 4.13e-05 | +| loss | -0.0338 | +| n_updates | 87464 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000161 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.302 | +| time/ | | +| fps | 1391 | +| iterations | 17913 | +| time_elapsed | 26367 | +| total_timesteps | 36685824 | +| train/ | | +| approx_kl | 0.015106953 | +| clip_fraction | 0.349 | +| clip_range | 0.0658 | +| entropy_loss | -6.51 | +| explained_variance | 0.239 | +| learning_rate | 4.13e-05 | +| loss | -0.0288 | +| n_updates | 87468 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000151 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 1391 | +| iterations | 17914 | +| time_elapsed | 26369 | +| total_timesteps | 36687872 | +| train/ | | +| approx_kl | 0.012126759 | +| clip_fraction | 0.355 | +| clip_range | 0.0658 | +| entropy_loss | -6.19 | +| explained_variance | 0.629 | +| learning_rate | 4.13e-05 | +| loss | -0.0239 | +| n_updates | 87472 | +| policy_gradient_loss | -0.0193 | +| value_loss | 9.04e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 1391 | +| iterations | 17915 | +| time_elapsed | 26370 | +| total_timesteps | 36689920 | +| train/ | | +| approx_kl | 0.011957549 | +| clip_fraction | 0.349 | +| clip_range | 0.0658 | +| entropy_loss | -5.9 | +| explained_variance | 0.397 | +| learning_rate | 4.13e-05 | +| loss | -0.0275 | +| n_updates | 87476 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000113 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 1391 | +| iterations | 17916 | +| time_elapsed | 26372 | +| total_timesteps | 36691968 | +| train/ | | +| approx_kl | 0.013733626 | +| clip_fraction | 0.332 | +| clip_range | 0.0658 | +| entropy_loss | -5.75 | +| explained_variance | 0.447 | +| learning_rate | 4.13e-05 | +| loss | -0.0268 | +| n_updates | 87480 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000223 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 1391 | +| iterations | 17917 | +| time_elapsed | 26373 | +| total_timesteps | 36694016 | +| train/ | | +| approx_kl | 0.0169204 | +| clip_fraction | 0.326 | +| clip_range | 0.0658 | +| entropy_loss | -5.53 | +| explained_variance | 0.556 | +| learning_rate | 4.13e-05 | +| loss | -0.032 | +| n_updates | 87484 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000109 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1391 | +| iterations | 17918 | +| time_elapsed | 26375 | +| total_timesteps | 36696064 | +| train/ | | +| approx_kl | 0.012283623 | +| clip_fraction | 0.312 | +| clip_range | 0.0658 | +| entropy_loss | -5.96 | +| explained_variance | 0.167 | +| learning_rate | 4.13e-05 | +| loss | -0.0252 | +| n_updates | 87488 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000257 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1391 | +| iterations | 17919 | +| time_elapsed | 26376 | +| total_timesteps | 36698112 | +| train/ | | +| approx_kl | 0.012674616 | +| clip_fraction | 0.317 | +| clip_range | 0.0658 | +| entropy_loss | -5.59 | +| explained_variance | 0.462 | +| learning_rate | 4.13e-05 | +| loss | -0.0227 | +| n_updates | 87492 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000196 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1391 | +| iterations | 17920 | +| time_elapsed | 26378 | +| total_timesteps | 36700160 | +| train/ | | +| approx_kl | 0.015135317 | +| clip_fraction | 0.346 | +| clip_range | 0.0658 | +| entropy_loss | -5.41 | +| explained_variance | 0.47 | +| learning_rate | 4.13e-05 | +| loss | -0.0278 | +| n_updates | 87496 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000237 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.298 | +| time/ | | +| fps | 1391 | +| iterations | 17921 | +| time_elapsed | 26379 | +| total_timesteps | 36702208 | +| train/ | | +| approx_kl | 0.013340246 | +| clip_fraction | 0.34 | +| clip_range | 0.0658 | +| entropy_loss | -5.23 | +| explained_variance | 0.329 | +| learning_rate | 4.13e-05 | +| loss | -0.0222 | +| n_updates | 87500 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000186 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.298 | +| time/ | | +| fps | 1391 | +| iterations | 17922 | +| time_elapsed | 26381 | +| total_timesteps | 36704256 | +| train/ | | +| approx_kl | 0.013147086 | +| clip_fraction | 0.365 | +| clip_range | 0.0658 | +| entropy_loss | -5.23 | +| explained_variance | 0.638 | +| learning_rate | 4.13e-05 | +| loss | -0.0365 | +| n_updates | 87504 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000115 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.298 | +| time/ | | +| fps | 1391 | +| iterations | 17923 | +| time_elapsed | 26382 | +| total_timesteps | 36706304 | +| train/ | | +| approx_kl | 0.013518333 | +| clip_fraction | 0.364 | +| clip_range | 0.0658 | +| entropy_loss | -5.23 | +| explained_variance | 0.329 | +| learning_rate | 4.13e-05 | +| loss | -0.0291 | +| n_updates | 87508 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000187 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 1391 | +| iterations | 17924 | +| time_elapsed | 26384 | +| total_timesteps | 36708352 | +| train/ | | +| approx_kl | 0.014391034 | +| clip_fraction | 0.367 | +| clip_range | 0.0658 | +| entropy_loss | -5.69 | +| explained_variance | 0.118 | +| learning_rate | 4.13e-05 | +| loss | -0.0283 | +| n_updates | 87512 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.0002 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1391 | +| iterations | 17925 | +| time_elapsed | 26385 | +| total_timesteps | 36710400 | +| train/ | | +| approx_kl | 0.010826841 | +| clip_fraction | 0.342 | +| clip_range | 0.0658 | +| entropy_loss | -5.99 | +| explained_variance | 0.485 | +| learning_rate | 4.13e-05 | +| loss | -0.028 | +| n_updates | 87516 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000157 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1391 | +| iterations | 17926 | +| time_elapsed | 26387 | +| total_timesteps | 36712448 | +| train/ | | +| approx_kl | 0.012353732 | +| clip_fraction | 0.354 | +| clip_range | 0.0658 | +| entropy_loss | -5.96 | +| explained_variance | 0.388 | +| learning_rate | 4.13e-05 | +| loss | -0.0209 | +| n_updates | 87520 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000247 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1391 | +| iterations | 17927 | +| time_elapsed | 26389 | +| total_timesteps | 36714496 | +| train/ | | +| approx_kl | 0.01640154 | +| clip_fraction | 0.325 | +| clip_range | 0.0658 | +| entropy_loss | -5.83 | +| explained_variance | 0.151 | +| learning_rate | 4.13e-05 | +| loss | -0.0331 | +| n_updates | 87524 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000206 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1391 | +| iterations | 17928 | +| time_elapsed | 26390 | +| total_timesteps | 36716544 | +| train/ | | +| approx_kl | 0.014752643 | +| clip_fraction | 0.38 | +| clip_range | 0.0658 | +| entropy_loss | -6.16 | +| explained_variance | 0.361 | +| learning_rate | 4.13e-05 | +| loss | -0.0336 | +| n_updates | 87528 | +| policy_gradient_loss | -0.0218 | +| value_loss | 8.42e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1391 | +| iterations | 17929 | +| time_elapsed | 26392 | +| total_timesteps | 36718592 | +| train/ | | +| approx_kl | 0.012291663 | +| clip_fraction | 0.34 | +| clip_range | 0.0658 | +| entropy_loss | -5.64 | +| explained_variance | 0.488 | +| learning_rate | 4.13e-05 | +| loss | -0.0251 | +| n_updates | 87532 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000165 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1391 | +| iterations | 17930 | +| time_elapsed | 26393 | +| total_timesteps | 36720640 | +| train/ | | +| approx_kl | 0.011548845 | +| clip_fraction | 0.301 | +| clip_range | 0.0658 | +| entropy_loss | -6.2 | +| explained_variance | 0.23 | +| learning_rate | 4.13e-05 | +| loss | -0.0223 | +| n_updates | 87536 | +| policy_gradient_loss | -0.0135 | +| value_loss | 0.000252 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1391 | +| iterations | 17931 | +| time_elapsed | 26395 | +| total_timesteps | 36722688 | +| train/ | | +| approx_kl | 0.012152952 | +| clip_fraction | 0.333 | +| clip_range | 0.0658 | +| entropy_loss | -5.96 | +| explained_variance | 0.535 | +| learning_rate | 4.13e-05 | +| loss | -0.028 | +| n_updates | 87540 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.00013 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1391 | +| iterations | 17932 | +| time_elapsed | 26396 | +| total_timesteps | 36724736 | +| train/ | | +| approx_kl | 0.009657878 | +| clip_fraction | 0.292 | +| clip_range | 0.0658 | +| entropy_loss | -5.8 | +| explained_variance | 0.424 | +| learning_rate | 4.13e-05 | +| loss | -0.0179 | +| n_updates | 87544 | +| policy_gradient_loss | -0.013 | +| value_loss | 0.000295 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1391 | +| iterations | 17933 | +| time_elapsed | 26398 | +| total_timesteps | 36726784 | +| train/ | | +| approx_kl | 0.010157246 | +| clip_fraction | 0.29 | +| clip_range | 0.0658 | +| entropy_loss | -5.76 | +| explained_variance | 0.48 | +| learning_rate | 4.13e-05 | +| loss | -0.0208 | +| n_updates | 87548 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000192 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1391 | +| iterations | 17934 | +| time_elapsed | 26399 | +| total_timesteps | 36728832 | +| train/ | | +| approx_kl | 0.010350821 | +| clip_fraction | 0.32 | +| clip_range | 0.0658 | +| entropy_loss | -5.56 | +| explained_variance | 0.675 | +| learning_rate | 4.13e-05 | +| loss | -0.0324 | +| n_updates | 87552 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000126 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1391 | +| iterations | 17935 | +| time_elapsed | 26401 | +| total_timesteps | 36730880 | +| train/ | | +| approx_kl | 0.016532125 | +| clip_fraction | 0.35 | +| clip_range | 0.0658 | +| entropy_loss | -5.75 | +| explained_variance | -0.252 | +| learning_rate | 4.13e-05 | +| loss | -0.0337 | +| n_updates | 87556 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000103 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.315 | +| time/ | | +| fps | 1391 | +| iterations | 17936 | +| time_elapsed | 26402 | +| total_timesteps | 36732928 | +| train/ | | +| approx_kl | 0.014815406 | +| clip_fraction | 0.34 | +| clip_range | 0.0658 | +| entropy_loss | -5.81 | +| explained_variance | 0.492 | +| learning_rate | 4.13e-05 | +| loss | -0.0253 | +| n_updates | 87560 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000222 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1391 | +| iterations | 17937 | +| time_elapsed | 26404 | +| total_timesteps | 36734976 | +| train/ | | +| approx_kl | 0.012032577 | +| clip_fraction | 0.336 | +| clip_range | 0.0658 | +| entropy_loss | -5.82 | +| explained_variance | 0.548 | +| learning_rate | 4.13e-05 | +| loss | -0.0315 | +| n_updates | 87564 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000107 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1391 | +| iterations | 17938 | +| time_elapsed | 26405 | +| total_timesteps | 36737024 | +| train/ | | +| approx_kl | 0.009979956 | +| clip_fraction | 0.311 | +| clip_range | 0.0658 | +| entropy_loss | -6.31 | +| explained_variance | 0.235 | +| learning_rate | 4.13e-05 | +| loss | -0.0278 | +| n_updates | 87568 | +| policy_gradient_loss | -0.0141 | +| value_loss | 0.000416 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1391 | +| iterations | 17939 | +| time_elapsed | 26407 | +| total_timesteps | 36739072 | +| train/ | | +| approx_kl | 0.012262933 | +| clip_fraction | 0.311 | +| clip_range | 0.0658 | +| entropy_loss | -5.09 | +| explained_variance | 0.606 | +| learning_rate | 4.13e-05 | +| loss | -0.0208 | +| n_updates | 87572 | +| policy_gradient_loss | -0.0145 | +| value_loss | 0.000173 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1391 | +| iterations | 17940 | +| time_elapsed | 26409 | +| total_timesteps | 36741120 | +| train/ | | +| approx_kl | 0.012532359 | +| clip_fraction | 0.325 | +| clip_range | 0.0658 | +| entropy_loss | -5.85 | +| explained_variance | -0.0344 | +| learning_rate | 4.13e-05 | +| loss | -0.0208 | +| n_updates | 87576 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.00018 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1391 | +| iterations | 17941 | +| time_elapsed | 26410 | +| total_timesteps | 36743168 | +| train/ | | +| approx_kl | 0.0129315285 | +| clip_fraction | 0.337 | +| clip_range | 0.0658 | +| entropy_loss | -6 | +| explained_variance | 0.185 | +| learning_rate | 4.13e-05 | +| loss | -0.0325 | +| n_updates | 87580 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000137 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1391 | +| iterations | 17942 | +| time_elapsed | 26412 | +| total_timesteps | 36745216 | +| train/ | | +| approx_kl | 0.012079208 | +| clip_fraction | 0.319 | +| clip_range | 0.0658 | +| entropy_loss | -6.1 | +| explained_variance | 0.443 | +| learning_rate | 4.13e-05 | +| loss | -0.0262 | +| n_updates | 87584 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000139 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1391 | +| iterations | 17943 | +| time_elapsed | 26413 | +| total_timesteps | 36747264 | +| train/ | | +| approx_kl | 0.0132859545 | +| clip_fraction | 0.348 | +| clip_range | 0.0658 | +| entropy_loss | -6.26 | +| explained_variance | 0.347 | +| learning_rate | 4.13e-05 | +| loss | -0.0279 | +| n_updates | 87588 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000115 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1391 | +| iterations | 17944 | +| time_elapsed | 26415 | +| total_timesteps | 36749312 | +| train/ | | +| approx_kl | 0.011786562 | +| clip_fraction | 0.338 | +| clip_range | 0.0658 | +| entropy_loss | -6.33 | +| explained_variance | 0.265 | +| learning_rate | 4.13e-05 | +| loss | -0.0278 | +| n_updates | 87592 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.000245 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.315 | +| time/ | | +| fps | 1391 | +| iterations | 17945 | +| time_elapsed | 26416 | +| total_timesteps | 36751360 | +| train/ | | +| approx_kl | 0.010504743 | +| clip_fraction | 0.335 | +| clip_range | 0.0658 | +| entropy_loss | -5.91 | +| explained_variance | 0.431 | +| learning_rate | 4.13e-05 | +| loss | -0.0244 | +| n_updates | 87596 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000231 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1391 | +| iterations | 17946 | +| time_elapsed | 26418 | +| total_timesteps | 36753408 | +| train/ | | +| approx_kl | 0.013461572 | +| clip_fraction | 0.338 | +| clip_range | 0.0658 | +| entropy_loss | -5.85 | +| explained_variance | 0.264 | +| learning_rate | 4.13e-05 | +| loss | -0.0232 | +| n_updates | 87600 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.00028 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1391 | +| iterations | 17947 | +| time_elapsed | 26419 | +| total_timesteps | 36755456 | +| train/ | | +| approx_kl | 0.0071772896 | +| clip_fraction | 0.315 | +| clip_range | 0.0658 | +| entropy_loss | -5.97 | +| explained_variance | 0.489 | +| learning_rate | 4.13e-05 | +| loss | -0.0171 | +| n_updates | 87604 | +| policy_gradient_loss | -0.0131 | +| value_loss | 0.000254 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1391 | +| iterations | 17948 | +| time_elapsed | 26421 | +| total_timesteps | 36757504 | +| train/ | | +| approx_kl | 0.008667281 | +| clip_fraction | 0.291 | +| clip_range | 0.0658 | +| entropy_loss | -5.89 | +| explained_variance | 0.496 | +| learning_rate | 4.13e-05 | +| loss | -0.0246 | +| n_updates | 87608 | +| policy_gradient_loss | -0.0145 | +| value_loss | 0.000265 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1391 | +| iterations | 17949 | +| time_elapsed | 26422 | +| total_timesteps | 36759552 | +| train/ | | +| approx_kl | 0.008936306 | +| clip_fraction | 0.306 | +| clip_range | 0.0658 | +| entropy_loss | -5.68 | +| explained_variance | 0.366 | +| learning_rate | 4.13e-05 | +| loss | -0.021 | +| n_updates | 87612 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.00019 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1391 | +| iterations | 17950 | +| time_elapsed | 26424 | +| total_timesteps | 36761600 | +| train/ | | +| approx_kl | 0.012296362 | +| clip_fraction | 0.354 | +| clip_range | 0.0658 | +| entropy_loss | -5.56 | +| explained_variance | 0.341 | +| learning_rate | 4.13e-05 | +| loss | -0.0298 | +| n_updates | 87616 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000336 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1391 | +| iterations | 17951 | +| time_elapsed | 26425 | +| total_timesteps | 36763648 | +| train/ | | +| approx_kl | 0.015058035 | +| clip_fraction | 0.367 | +| clip_range | 0.0658 | +| entropy_loss | -6.02 | +| explained_variance | 0.125 | +| learning_rate | 4.13e-05 | +| loss | -0.0339 | +| n_updates | 87620 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000139 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1391 | +| iterations | 17952 | +| time_elapsed | 26427 | +| total_timesteps | 36765696 | +| train/ | | +| approx_kl | 0.012919437 | +| clip_fraction | 0.351 | +| clip_range | 0.0658 | +| entropy_loss | -6.13 | +| explained_variance | 0.424 | +| learning_rate | 4.13e-05 | +| loss | -0.0327 | +| n_updates | 87624 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000171 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1391 | +| iterations | 17953 | +| time_elapsed | 26428 | +| total_timesteps | 36767744 | +| train/ | | +| approx_kl | 0.014505958 | +| clip_fraction | 0.372 | +| clip_range | 0.0658 | +| entropy_loss | -6.08 | +| explained_variance | -0.354 | +| learning_rate | 4.13e-05 | +| loss | -0.0355 | +| n_updates | 87628 | +| policy_gradient_loss | -0.022 | +| value_loss | 7.94e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1391 | +| iterations | 17954 | +| time_elapsed | 26430 | +| total_timesteps | 36769792 | +| train/ | | +| approx_kl | 0.01160853 | +| clip_fraction | 0.358 | +| clip_range | 0.0658 | +| entropy_loss | -5.77 | +| explained_variance | 0.443 | +| learning_rate | 4.13e-05 | +| loss | -0.0287 | +| n_updates | 87632 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000211 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1391 | +| iterations | 17955 | +| time_elapsed | 26431 | +| total_timesteps | 36771840 | +| train/ | | +| approx_kl | 0.012371591 | +| clip_fraction | 0.355 | +| clip_range | 0.0658 | +| entropy_loss | -5.39 | +| explained_variance | 0.752 | +| learning_rate | 4.13e-05 | +| loss | -0.0346 | +| n_updates | 87636 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.00011 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1391 | +| iterations | 17956 | +| time_elapsed | 26433 | +| total_timesteps | 36773888 | +| train/ | | +| approx_kl | 0.012946522 | +| clip_fraction | 0.355 | +| clip_range | 0.0658 | +| entropy_loss | -5.52 | +| explained_variance | 0.815 | +| learning_rate | 4.13e-05 | +| loss | -0.0265 | +| n_updates | 87640 | +| policy_gradient_loss | -0.0185 | +| value_loss | 5.75e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1391 | +| iterations | 17957 | +| time_elapsed | 26434 | +| total_timesteps | 36775936 | +| train/ | | +| approx_kl | 0.00957741 | +| clip_fraction | 0.32 | +| clip_range | 0.0658 | +| entropy_loss | -5.55 | +| explained_variance | 0.525 | +| learning_rate | 4.13e-05 | +| loss | -0.0232 | +| n_updates | 87644 | +| policy_gradient_loss | -0.0141 | +| value_loss | 0.000192 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1391 | +| iterations | 17958 | +| time_elapsed | 26436 | +| total_timesteps | 36777984 | +| train/ | | +| approx_kl | 0.013411791 | +| clip_fraction | 0.358 | +| clip_range | 0.0658 | +| entropy_loss | -5.88 | +| explained_variance | 0.611 | +| learning_rate | 4.13e-05 | +| loss | -0.0253 | +| n_updates | 87648 | +| policy_gradient_loss | -0.0176 | +| value_loss | 8.61e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1391 | +| iterations | 17959 | +| time_elapsed | 26437 | +| total_timesteps | 36780032 | +| train/ | | +| approx_kl | 0.014586272 | +| clip_fraction | 0.349 | +| clip_range | 0.0658 | +| entropy_loss | -5.99 | +| explained_variance | 0.283 | +| learning_rate | 4.13e-05 | +| loss | -0.0296 | +| n_updates | 87652 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.00017 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1391 | +| iterations | 17960 | +| time_elapsed | 26439 | +| total_timesteps | 36782080 | +| train/ | | +| approx_kl | 0.015881265 | +| clip_fraction | 0.36 | +| clip_range | 0.0658 | +| entropy_loss | -6.42 | +| explained_variance | -0.00543 | +| learning_rate | 4.13e-05 | +| loss | -0.0314 | +| n_updates | 87656 | +| policy_gradient_loss | -0.0191 | +| value_loss | 8.61e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1391 | +| iterations | 17961 | +| time_elapsed | 26440 | +| total_timesteps | 36784128 | +| train/ | | +| approx_kl | 0.016054105 | +| clip_fraction | 0.358 | +| clip_range | 0.0658 | +| entropy_loss | -6 | +| explained_variance | 0.495 | +| learning_rate | 4.13e-05 | +| loss | -0.0292 | +| n_updates | 87660 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000157 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1391 | +| iterations | 17962 | +| time_elapsed | 26442 | +| total_timesteps | 36786176 | +| train/ | | +| approx_kl | 0.012877824 | +| clip_fraction | 0.32 | +| clip_range | 0.0658 | +| entropy_loss | -5.08 | +| explained_variance | 0.433 | +| learning_rate | 4.13e-05 | +| loss | -0.021 | +| n_updates | 87664 | +| policy_gradient_loss | -0.0127 | +| value_loss | 0.000264 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1391 | +| iterations | 17963 | +| time_elapsed | 26444 | +| total_timesteps | 36788224 | +| train/ | | +| approx_kl | 0.01447192 | +| clip_fraction | 0.355 | +| clip_range | 0.0658 | +| entropy_loss | -5.47 | +| explained_variance | 0.179 | +| learning_rate | 4.13e-05 | +| loss | -0.0312 | +| n_updates | 87668 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.00024 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1391 | +| iterations | 17964 | +| time_elapsed | 26445 | +| total_timesteps | 36790272 | +| train/ | | +| approx_kl | 0.012516858 | +| clip_fraction | 0.331 | +| clip_range | 0.0658 | +| entropy_loss | -5.84 | +| explained_variance | 0.282 | +| learning_rate | 4.13e-05 | +| loss | -0.0245 | +| n_updates | 87672 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000174 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1391 | +| iterations | 17965 | +| time_elapsed | 26447 | +| total_timesteps | 36792320 | +| train/ | | +| approx_kl | 0.012237624 | +| clip_fraction | 0.351 | +| clip_range | 0.0658 | +| entropy_loss | -6.6 | +| explained_variance | 0.303 | +| learning_rate | 4.13e-05 | +| loss | -0.0358 | +| n_updates | 87676 | +| policy_gradient_loss | -0.0205 | +| value_loss | 7.72e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1391 | +| iterations | 17966 | +| time_elapsed | 26448 | +| total_timesteps | 36794368 | +| train/ | | +| approx_kl | 0.014443186 | +| clip_fraction | 0.368 | +| clip_range | 0.0658 | +| entropy_loss | -6.1 | +| explained_variance | 0.302 | +| learning_rate | 4.13e-05 | +| loss | -0.0297 | +| n_updates | 87680 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000159 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1391 | +| iterations | 17967 | +| time_elapsed | 26450 | +| total_timesteps | 36796416 | +| train/ | | +| approx_kl | 0.013443092 | +| clip_fraction | 0.343 | +| clip_range | 0.0658 | +| entropy_loss | -5.84 | +| explained_variance | 0.685 | +| learning_rate | 4.13e-05 | +| loss | -0.0285 | +| n_updates | 87684 | +| policy_gradient_loss | -0.0182 | +| value_loss | 9.24e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1391 | +| iterations | 17968 | +| time_elapsed | 26451 | +| total_timesteps | 36798464 | +| train/ | | +| approx_kl | 0.013311667 | +| clip_fraction | 0.358 | +| clip_range | 0.0658 | +| entropy_loss | -5.93 | +| explained_variance | -0.0832 | +| learning_rate | 4.13e-05 | +| loss | -0.0238 | +| n_updates | 87688 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000196 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1391 | +| iterations | 17969 | +| time_elapsed | 26453 | +| total_timesteps | 36800512 | +| train/ | | +| approx_kl | 0.013086246 | +| clip_fraction | 0.327 | +| clip_range | 0.0658 | +| entropy_loss | -5.45 | +| explained_variance | 0.602 | +| learning_rate | 4.13e-05 | +| loss | -0.0163 | +| n_updates | 87692 | +| policy_gradient_loss | -0.0141 | +| value_loss | 0.00022 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1391 | +| iterations | 17970 | +| time_elapsed | 26454 | +| total_timesteps | 36802560 | +| train/ | | +| approx_kl | 0.016944218 | +| clip_fraction | 0.384 | +| clip_range | 0.0658 | +| entropy_loss | -5.72 | +| explained_variance | 0.292 | +| learning_rate | 4.13e-05 | +| loss | -0.0279 | +| n_updates | 87696 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000155 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1391 | +| iterations | 17971 | +| time_elapsed | 26456 | +| total_timesteps | 36804608 | +| train/ | | +| approx_kl | 0.01242296 | +| clip_fraction | 0.357 | +| clip_range | 0.0658 | +| entropy_loss | -5.72 | +| explained_variance | 0.554 | +| learning_rate | 4.13e-05 | +| loss | -0.0278 | +| n_updates | 87700 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000165 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1391 | +| iterations | 17972 | +| time_elapsed | 26457 | +| total_timesteps | 36806656 | +| train/ | | +| approx_kl | 0.013688816 | +| clip_fraction | 0.342 | +| clip_range | 0.0658 | +| entropy_loss | -5.87 | +| explained_variance | 0.449 | +| learning_rate | 4.13e-05 | +| loss | -0.03 | +| n_updates | 87704 | +| policy_gradient_loss | -0.018 | +| value_loss | 8.11e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1391 | +| iterations | 17973 | +| time_elapsed | 26459 | +| total_timesteps | 36808704 | +| train/ | | +| approx_kl | 0.014429092 | +| clip_fraction | 0.346 | +| clip_range | 0.0658 | +| entropy_loss | -5.79 | +| explained_variance | 0.547 | +| learning_rate | 4.13e-05 | +| loss | -0.0275 | +| n_updates | 87708 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000128 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1391 | +| iterations | 17974 | +| time_elapsed | 26460 | +| total_timesteps | 36810752 | +| train/ | | +| approx_kl | 0.0118859 | +| clip_fraction | 0.328 | +| clip_range | 0.0658 | +| entropy_loss | -6.15 | +| explained_variance | 0.038 | +| learning_rate | 4.13e-05 | +| loss | -0.0281 | +| n_updates | 87712 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000365 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1391 | +| iterations | 17975 | +| time_elapsed | 26462 | +| total_timesteps | 36812800 | +| train/ | | +| approx_kl | 0.011473762 | +| clip_fraction | 0.323 | +| clip_range | 0.0658 | +| entropy_loss | -5.19 | +| explained_variance | 0.497 | +| learning_rate | 4.13e-05 | +| loss | -0.0216 | +| n_updates | 87716 | +| policy_gradient_loss | -0.0148 | +| value_loss | 0.000273 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1391 | +| iterations | 17976 | +| time_elapsed | 26463 | +| total_timesteps | 36814848 | +| train/ | | +| approx_kl | 0.011253959 | +| clip_fraction | 0.344 | +| clip_range | 0.0658 | +| entropy_loss | -6.43 | +| explained_variance | -0.0644 | +| learning_rate | 4.13e-05 | +| loss | -0.0317 | +| n_updates | 87720 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000137 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1391 | +| iterations | 17977 | +| time_elapsed | 26465 | +| total_timesteps | 36816896 | +| train/ | | +| approx_kl | 0.012921068 | +| clip_fraction | 0.343 | +| clip_range | 0.0658 | +| entropy_loss | -5.79 | +| explained_variance | 0.702 | +| learning_rate | 4.13e-05 | +| loss | -0.0233 | +| n_updates | 87724 | +| policy_gradient_loss | -0.0172 | +| value_loss | 9.73e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1391 | +| iterations | 17978 | +| time_elapsed | 26466 | +| total_timesteps | 36818944 | +| train/ | | +| approx_kl | 0.014980799 | +| clip_fraction | 0.328 | +| clip_range | 0.0658 | +| entropy_loss | -5.27 | +| explained_variance | 0.385 | +| learning_rate | 4.13e-05 | +| loss | -0.0254 | +| n_updates | 87728 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000262 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1391 | +| iterations | 17979 | +| time_elapsed | 26468 | +| total_timesteps | 36820992 | +| train/ | | +| approx_kl | 0.012826535 | +| clip_fraction | 0.348 | +| clip_range | 0.0658 | +| entropy_loss | -5.73 | +| explained_variance | 0.0363 | +| learning_rate | 4.13e-05 | +| loss | -0.0253 | +| n_updates | 87732 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1391 | +| iterations | 17980 | +| time_elapsed | 26469 | +| total_timesteps | 36823040 | +| train/ | | +| approx_kl | 0.018942803 | +| clip_fraction | 0.35 | +| clip_range | 0.0658 | +| entropy_loss | -5.79 | +| explained_variance | 0.506 | +| learning_rate | 4.13e-05 | +| loss | -0.0299 | +| n_updates | 87736 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.00011 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1391 | +| iterations | 17981 | +| time_elapsed | 26471 | +| total_timesteps | 36825088 | +| train/ | | +| approx_kl | 0.013450019 | +| clip_fraction | 0.375 | +| clip_range | 0.0658 | +| entropy_loss | -6.22 | +| explained_variance | -0.148 | +| learning_rate | 4.13e-05 | +| loss | -0.028 | +| n_updates | 87740 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000281 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1391 | +| iterations | 17982 | +| time_elapsed | 26472 | +| total_timesteps | 36827136 | +| train/ | | +| approx_kl | 0.016034678 | +| clip_fraction | 0.363 | +| clip_range | 0.0658 | +| entropy_loss | -5.78 | +| explained_variance | 0.303 | +| learning_rate | 4.13e-05 | +| loss | -0.0302 | +| n_updates | 87744 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000139 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1391 | +| iterations | 17983 | +| time_elapsed | 26474 | +| total_timesteps | 36829184 | +| train/ | | +| approx_kl | 0.01631422 | +| clip_fraction | 0.356 | +| clip_range | 0.0658 | +| entropy_loss | -5.26 | +| explained_variance | 0.684 | +| learning_rate | 4.13e-05 | +| loss | -0.0176 | +| n_updates | 87748 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000111 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1391 | +| iterations | 17984 | +| time_elapsed | 26475 | +| total_timesteps | 36831232 | +| train/ | | +| approx_kl | 0.016429836 | +| clip_fraction | 0.297 | +| clip_range | 0.0658 | +| entropy_loss | -5.01 | +| explained_variance | 0.702 | +| learning_rate | 4.13e-05 | +| loss | -0.0233 | +| n_updates | 87752 | +| policy_gradient_loss | -0.0139 | +| value_loss | 0.000115 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1391 | +| iterations | 17985 | +| time_elapsed | 26477 | +| total_timesteps | 36833280 | +| train/ | | +| approx_kl | 0.013035066 | +| clip_fraction | 0.339 | +| clip_range | 0.0658 | +| entropy_loss | -6.4 | +| explained_variance | -0.0203 | +| learning_rate | 4.13e-05 | +| loss | -0.0289 | +| n_updates | 87756 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000139 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1391 | +| iterations | 17986 | +| time_elapsed | 26479 | +| total_timesteps | 36835328 | +| train/ | | +| approx_kl | 0.011611057 | +| clip_fraction | 0.337 | +| clip_range | 0.0658 | +| entropy_loss | -6.23 | +| explained_variance | 0.28 | +| learning_rate | 4.13e-05 | +| loss | -0.0239 | +| n_updates | 87760 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000206 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1391 | +| iterations | 17987 | +| time_elapsed | 26480 | +| total_timesteps | 36837376 | +| train/ | | +| approx_kl | 0.010408079 | +| clip_fraction | 0.32 | +| clip_range | 0.0658 | +| entropy_loss | -5.99 | +| explained_variance | 0.503 | +| learning_rate | 4.13e-05 | +| loss | -0.0173 | +| n_updates | 87764 | +| policy_gradient_loss | -0.0132 | +| value_loss | 0.000243 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1391 | +| iterations | 17988 | +| time_elapsed | 26482 | +| total_timesteps | 36839424 | +| train/ | | +| approx_kl | 0.012828434 | +| clip_fraction | 0.303 | +| clip_range | 0.0658 | +| entropy_loss | -5.48 | +| explained_variance | 0.433 | +| learning_rate | 4.13e-05 | +| loss | -0.0193 | +| n_updates | 87768 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000183 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1391 | +| iterations | 17989 | +| time_elapsed | 26483 | +| total_timesteps | 36841472 | +| train/ | | +| approx_kl | 0.012079848 | +| clip_fraction | 0.33 | +| clip_range | 0.0658 | +| entropy_loss | -6.35 | +| explained_variance | 0.223 | +| learning_rate | 4.13e-05 | +| loss | -0.0305 | +| n_updates | 87772 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1391 | +| iterations | 17990 | +| time_elapsed | 26485 | +| total_timesteps | 36843520 | +| train/ | | +| approx_kl | 0.009949303 | +| clip_fraction | 0.32 | +| clip_range | 0.0658 | +| entropy_loss | -5.66 | +| explained_variance | 0.423 | +| learning_rate | 4.13e-05 | +| loss | -0.0185 | +| n_updates | 87776 | +| policy_gradient_loss | -0.0145 | +| value_loss | 0.000246 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1391 | +| iterations | 17991 | +| time_elapsed | 26486 | +| total_timesteps | 36845568 | +| train/ | | +| approx_kl | 0.015212348 | +| clip_fraction | 0.37 | +| clip_range | 0.0658 | +| entropy_loss | -5.8 | +| explained_variance | 0.28 | +| learning_rate | 4.12e-05 | +| loss | -0.0323 | +| n_updates | 87780 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000109 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1391 | +| iterations | 17992 | +| time_elapsed | 26488 | +| total_timesteps | 36847616 | +| train/ | | +| approx_kl | 0.014259734 | +| clip_fraction | 0.365 | +| clip_range | 0.0658 | +| entropy_loss | -5.94 | +| explained_variance | 0.3 | +| learning_rate | 4.12e-05 | +| loss | -0.0258 | +| n_updates | 87784 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000219 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1391 | +| iterations | 17993 | +| time_elapsed | 26489 | +| total_timesteps | 36849664 | +| train/ | | +| approx_kl | 0.012668544 | +| clip_fraction | 0.341 | +| clip_range | 0.0658 | +| entropy_loss | -6.19 | +| explained_variance | 0.319 | +| learning_rate | 4.12e-05 | +| loss | -0.0263 | +| n_updates | 87788 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000237 | +----------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1391 | +| iterations | 17994 | +| time_elapsed | 26491 | +| total_timesteps | 36851712 | +| train/ | | +| approx_kl | 0.014347 | +| clip_fraction | 0.315 | +| clip_range | 0.0658 | +| entropy_loss | -5.66 | +| explained_variance | 0.214 | +| learning_rate | 4.12e-05 | +| loss | -0.0243 | +| n_updates | 87792 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000154 | +-------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1391 | +| iterations | 17995 | +| time_elapsed | 26492 | +| total_timesteps | 36853760 | +| train/ | | +| approx_kl | 0.012850283 | +| clip_fraction | 0.357 | +| clip_range | 0.0658 | +| entropy_loss | -6.21 | +| explained_variance | 0.384 | +| learning_rate | 4.12e-05 | +| loss | -0.0325 | +| n_updates | 87796 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000115 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1391 | +| iterations | 17996 | +| time_elapsed | 26494 | +| total_timesteps | 36855808 | +| train/ | | +| approx_kl | 0.013337864 | +| clip_fraction | 0.334 | +| clip_range | 0.0658 | +| entropy_loss | -6.74 | +| explained_variance | -0.296 | +| learning_rate | 4.12e-05 | +| loss | -0.0296 | +| n_updates | 87800 | +| policy_gradient_loss | -0.0184 | +| value_loss | 8.63e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1391 | +| iterations | 17997 | +| time_elapsed | 26495 | +| total_timesteps | 36857856 | +| train/ | | +| approx_kl | 0.012909122 | +| clip_fraction | 0.328 | +| clip_range | 0.0658 | +| entropy_loss | -5.61 | +| explained_variance | 0.594 | +| learning_rate | 4.12e-05 | +| loss | -0.0292 | +| n_updates | 87804 | +| policy_gradient_loss | -0.0147 | +| value_loss | 0.000145 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1391 | +| iterations | 17998 | +| time_elapsed | 26497 | +| total_timesteps | 36859904 | +| train/ | | +| approx_kl | 0.014820296 | +| clip_fraction | 0.333 | +| clip_range | 0.0658 | +| entropy_loss | -5.24 | +| explained_variance | 0.658 | +| learning_rate | 4.12e-05 | +| loss | -0.0232 | +| n_updates | 87808 | +| policy_gradient_loss | -0.0167 | +| value_loss | 8.29e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1391 | +| iterations | 17999 | +| time_elapsed | 26499 | +| total_timesteps | 36861952 | +| train/ | | +| approx_kl | 0.012347963 | +| clip_fraction | 0.32 | +| clip_range | 0.0658 | +| entropy_loss | -6.1 | +| explained_variance | 0.335 | +| learning_rate | 4.12e-05 | +| loss | -0.0264 | +| n_updates | 87812 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000114 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1391 | +| iterations | 18000 | +| time_elapsed | 26500 | +| total_timesteps | 36864000 | +| train/ | | +| approx_kl | 0.011866469 | +| clip_fraction | 0.336 | +| clip_range | 0.0658 | +| entropy_loss | -6.11 | +| explained_variance | 0.418 | +| learning_rate | 4.12e-05 | +| loss | -0.0252 | +| n_updates | 87816 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000202 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1391 | +| iterations | 18001 | +| time_elapsed | 26502 | +| total_timesteps | 36866048 | +| train/ | | +| approx_kl | 0.009657726 | +| clip_fraction | 0.31 | +| clip_range | 0.0658 | +| entropy_loss | -5.76 | +| explained_variance | 0.552 | +| learning_rate | 4.12e-05 | +| loss | -0.0274 | +| n_updates | 87820 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000201 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1391 | +| iterations | 18002 | +| time_elapsed | 26503 | +| total_timesteps | 36868096 | +| train/ | | +| approx_kl | 0.013088722 | +| clip_fraction | 0.328 | +| clip_range | 0.0658 | +| entropy_loss | -5.43 | +| explained_variance | 0.329 | +| learning_rate | 4.12e-05 | +| loss | -0.0165 | +| n_updates | 87824 | +| policy_gradient_loss | -0.0143 | +| value_loss | 0.000319 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1391 | +| iterations | 18003 | +| time_elapsed | 26505 | +| total_timesteps | 36870144 | +| train/ | | +| approx_kl | 0.013524789 | +| clip_fraction | 0.37 | +| clip_range | 0.0658 | +| entropy_loss | -5.55 | +| explained_variance | 0.451 | +| learning_rate | 4.12e-05 | +| loss | -0.0335 | +| n_updates | 87828 | +| policy_gradient_loss | -0.0194 | +| value_loss | 9.64e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1391 | +| iterations | 18004 | +| time_elapsed | 26506 | +| total_timesteps | 36872192 | +| train/ | | +| approx_kl | 0.010217683 | +| clip_fraction | 0.325 | +| clip_range | 0.0658 | +| entropy_loss | -5.87 | +| explained_variance | 0.473 | +| learning_rate | 4.12e-05 | +| loss | -0.0214 | +| n_updates | 87832 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000163 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1391 | +| iterations | 18005 | +| time_elapsed | 26508 | +| total_timesteps | 36874240 | +| train/ | | +| approx_kl | 0.010654554 | +| clip_fraction | 0.326 | +| clip_range | 0.0658 | +| entropy_loss | -6.52 | +| explained_variance | 0.0783 | +| learning_rate | 4.12e-05 | +| loss | -0.0294 | +| n_updates | 87836 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000214 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1391 | +| iterations | 18006 | +| time_elapsed | 26509 | +| total_timesteps | 36876288 | +| train/ | | +| approx_kl | 0.0090848915 | +| clip_fraction | 0.309 | +| clip_range | 0.0658 | +| entropy_loss | -6.87 | +| explained_variance | -0.151 | +| learning_rate | 4.12e-05 | +| loss | -0.0263 | +| n_updates | 87840 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.000224 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1391 | +| iterations | 18007 | +| time_elapsed | 26511 | +| total_timesteps | 36878336 | +| train/ | | +| approx_kl | 0.009811821 | +| clip_fraction | 0.292 | +| clip_range | 0.0658 | +| entropy_loss | -6.07 | +| explained_variance | 0.428 | +| learning_rate | 4.12e-05 | +| loss | -0.0261 | +| n_updates | 87844 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000234 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1391 | +| iterations | 18008 | +| time_elapsed | 26512 | +| total_timesteps | 36880384 | +| train/ | | +| approx_kl | 0.013637201 | +| clip_fraction | 0.347 | +| clip_range | 0.0658 | +| entropy_loss | -5.98 | +| explained_variance | 0.244 | +| learning_rate | 4.12e-05 | +| loss | -0.0235 | +| n_updates | 87848 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.00022 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1391 | +| iterations | 18009 | +| time_elapsed | 26514 | +| total_timesteps | 36882432 | +| train/ | | +| approx_kl | 0.015871234 | +| clip_fraction | 0.361 | +| clip_range | 0.0658 | +| entropy_loss | -5.86 | +| explained_variance | 0.704 | +| learning_rate | 4.12e-05 | +| loss | -0.0322 | +| n_updates | 87852 | +| policy_gradient_loss | -0.0193 | +| value_loss | 7.17e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1391 | +| iterations | 18010 | +| time_elapsed | 26515 | +| total_timesteps | 36884480 | +| train/ | | +| approx_kl | 0.012837082 | +| clip_fraction | 0.34 | +| clip_range | 0.0658 | +| entropy_loss | -5.56 | +| explained_variance | 0.427 | +| learning_rate | 4.12e-05 | +| loss | -0.0263 | +| n_updates | 87856 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000158 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1391 | +| iterations | 18011 | +| time_elapsed | 26517 | +| total_timesteps | 36886528 | +| train/ | | +| approx_kl | 0.011716408 | +| clip_fraction | 0.312 | +| clip_range | 0.0658 | +| entropy_loss | -5.17 | +| explained_variance | 0.589 | +| learning_rate | 4.12e-05 | +| loss | -0.0266 | +| n_updates | 87860 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000156 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1391 | +| iterations | 18012 | +| time_elapsed | 26519 | +| total_timesteps | 36888576 | +| train/ | | +| approx_kl | 0.012741159 | +| clip_fraction | 0.312 | +| clip_range | 0.0658 | +| entropy_loss | -5.84 | +| explained_variance | 0.515 | +| learning_rate | 4.12e-05 | +| loss | -0.0251 | +| n_updates | 87864 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000157 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1391 | +| iterations | 18013 | +| time_elapsed | 26520 | +| total_timesteps | 36890624 | +| train/ | | +| approx_kl | 0.012919115 | +| clip_fraction | 0.326 | +| clip_range | 0.0658 | +| entropy_loss | -5.67 | +| explained_variance | 0.417 | +| learning_rate | 4.12e-05 | +| loss | -0.0256 | +| n_updates | 87868 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000171 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1391 | +| iterations | 18014 | +| time_elapsed | 26522 | +| total_timesteps | 36892672 | +| train/ | | +| approx_kl | 0.013784779 | +| clip_fraction | 0.357 | +| clip_range | 0.0658 | +| entropy_loss | -6.05 | +| explained_variance | 0.178 | +| learning_rate | 4.12e-05 | +| loss | -0.034 | +| n_updates | 87872 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000176 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1391 | +| iterations | 18015 | +| time_elapsed | 26523 | +| total_timesteps | 36894720 | +| train/ | | +| approx_kl | 0.014675342 | +| clip_fraction | 0.377 | +| clip_range | 0.0658 | +| entropy_loss | -6.02 | +| explained_variance | 0.243 | +| learning_rate | 4.12e-05 | +| loss | -0.0265 | +| n_updates | 87876 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000228 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1391 | +| iterations | 18016 | +| time_elapsed | 26525 | +| total_timesteps | 36896768 | +| train/ | | +| approx_kl | 0.014306114 | +| clip_fraction | 0.365 | +| clip_range | 0.0658 | +| entropy_loss | -6.44 | +| explained_variance | -0.177 | +| learning_rate | 4.12e-05 | +| loss | -0.0348 | +| n_updates | 87880 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.0002 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1391 | +| iterations | 18017 | +| time_elapsed | 26526 | +| total_timesteps | 36898816 | +| train/ | | +| approx_kl | 0.011154383 | +| clip_fraction | 0.317 | +| clip_range | 0.0658 | +| entropy_loss | -6.7 | +| explained_variance | 0.304 | +| learning_rate | 4.12e-05 | +| loss | -0.032 | +| n_updates | 87884 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000118 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1391 | +| iterations | 18018 | +| time_elapsed | 26528 | +| total_timesteps | 36900864 | +| train/ | | +| approx_kl | 0.015234334 | +| clip_fraction | 0.372 | +| clip_range | 0.0658 | +| entropy_loss | -6.2 | +| explained_variance | 0.633 | +| learning_rate | 4.12e-05 | +| loss | -0.0359 | +| n_updates | 87888 | +| policy_gradient_loss | -0.023 | +| value_loss | 4.43e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1390 | +| iterations | 18019 | +| time_elapsed | 26529 | +| total_timesteps | 36902912 | +| train/ | | +| approx_kl | 0.01062892 | +| clip_fraction | 0.325 | +| clip_range | 0.0658 | +| entropy_loss | -5.83 | +| explained_variance | 0.543 | +| learning_rate | 4.12e-05 | +| loss | -0.0238 | +| n_updates | 87892 | +| policy_gradient_loss | -0.0156 | +| value_loss | 9.94e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1390 | +| iterations | 18020 | +| time_elapsed | 26531 | +| total_timesteps | 36904960 | +| train/ | | +| approx_kl | 0.008460538 | +| clip_fraction | 0.296 | +| clip_range | 0.0658 | +| entropy_loss | -5.82 | +| explained_variance | 0.526 | +| learning_rate | 4.12e-05 | +| loss | -0.0252 | +| n_updates | 87896 | +| policy_gradient_loss | -0.0132 | +| value_loss | 0.000217 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1390 | +| iterations | 18021 | +| time_elapsed | 26532 | +| total_timesteps | 36907008 | +| train/ | | +| approx_kl | 0.0099192895 | +| clip_fraction | 0.317 | +| clip_range | 0.0658 | +| entropy_loss | -5.92 | +| explained_variance | 0.479 | +| learning_rate | 4.12e-05 | +| loss | -0.0292 | +| n_updates | 87900 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000176 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1390 | +| iterations | 18022 | +| time_elapsed | 26534 | +| total_timesteps | 36909056 | +| train/ | | +| approx_kl | 0.014880256 | +| clip_fraction | 0.313 | +| clip_range | 0.0658 | +| entropy_loss | -5.82 | +| explained_variance | 0.534 | +| learning_rate | 4.12e-05 | +| loss | -0.0288 | +| n_updates | 87904 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.00017 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1390 | +| iterations | 18023 | +| time_elapsed | 26535 | +| total_timesteps | 36911104 | +| train/ | | +| approx_kl | 0.014130729 | +| clip_fraction | 0.315 | +| clip_range | 0.0658 | +| entropy_loss | -5.63 | +| explained_variance | 0.22 | +| learning_rate | 4.12e-05 | +| loss | -0.0201 | +| n_updates | 87908 | +| policy_gradient_loss | -0.0137 | +| value_loss | 0.00024 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1390 | +| iterations | 18024 | +| time_elapsed | 26537 | +| total_timesteps | 36913152 | +| train/ | | +| approx_kl | 0.010783641 | +| clip_fraction | 0.335 | +| clip_range | 0.0658 | +| entropy_loss | -6.58 | +| explained_variance | -0.128 | +| learning_rate | 4.12e-05 | +| loss | -0.0288 | +| n_updates | 87912 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000177 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1390 | +| iterations | 18025 | +| time_elapsed | 26538 | +| total_timesteps | 36915200 | +| train/ | | +| approx_kl | 0.014003161 | +| clip_fraction | 0.304 | +| clip_range | 0.0658 | +| entropy_loss | -6.04 | +| explained_variance | 0.387 | +| learning_rate | 4.12e-05 | +| loss | -0.0227 | +| n_updates | 87916 | +| policy_gradient_loss | -0.0141 | +| value_loss | 0.000323 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1390 | +| iterations | 18026 | +| time_elapsed | 26540 | +| total_timesteps | 36917248 | +| train/ | | +| approx_kl | 0.014355504 | +| clip_fraction | 0.359 | +| clip_range | 0.0658 | +| entropy_loss | -5.58 | +| explained_variance | 0.258 | +| learning_rate | 4.12e-05 | +| loss | -0.0242 | +| n_updates | 87920 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000145 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1390 | +| iterations | 18027 | +| time_elapsed | 26542 | +| total_timesteps | 36919296 | +| train/ | | +| approx_kl | 0.015779745 | +| clip_fraction | 0.391 | +| clip_range | 0.0658 | +| entropy_loss | -5.59 | +| explained_variance | 0.188 | +| learning_rate | 4.12e-05 | +| loss | -0.0319 | +| n_updates | 87924 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000135 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1390 | +| iterations | 18028 | +| time_elapsed | 26543 | +| total_timesteps | 36921344 | +| train/ | | +| approx_kl | 0.012543139 | +| clip_fraction | 0.348 | +| clip_range | 0.0658 | +| entropy_loss | -6.46 | +| explained_variance | 0.283 | +| learning_rate | 4.12e-05 | +| loss | -0.0311 | +| n_updates | 87928 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000156 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1390 | +| iterations | 18029 | +| time_elapsed | 26545 | +| total_timesteps | 36923392 | +| train/ | | +| approx_kl | 0.010753853 | +| clip_fraction | 0.339 | +| clip_range | 0.0658 | +| entropy_loss | -6.39 | +| explained_variance | 0.0307 | +| learning_rate | 4.12e-05 | +| loss | -0.0246 | +| n_updates | 87932 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000204 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1390 | +| iterations | 18030 | +| time_elapsed | 26546 | +| total_timesteps | 36925440 | +| train/ | | +| approx_kl | 0.009719772 | +| clip_fraction | 0.3 | +| clip_range | 0.0658 | +| entropy_loss | -6.11 | +| explained_variance | 0.467 | +| learning_rate | 4.12e-05 | +| loss | -0.0184 | +| n_updates | 87936 | +| policy_gradient_loss | -0.013 | +| value_loss | 0.000276 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1390 | +| iterations | 18031 | +| time_elapsed | 26548 | +| total_timesteps | 36927488 | +| train/ | | +| approx_kl | 0.010177435 | +| clip_fraction | 0.318 | +| clip_range | 0.0658 | +| entropy_loss | -4.96 | +| explained_variance | 0.57 | +| learning_rate | 4.12e-05 | +| loss | -0.0173 | +| n_updates | 87940 | +| policy_gradient_loss | -0.0141 | +| value_loss | 0.00017 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1390 | +| iterations | 18032 | +| time_elapsed | 26549 | +| total_timesteps | 36929536 | +| train/ | | +| approx_kl | 0.011866973 | +| clip_fraction | 0.342 | +| clip_range | 0.0658 | +| entropy_loss | -5.26 | +| explained_variance | 0.565 | +| learning_rate | 4.12e-05 | +| loss | -0.0272 | +| n_updates | 87944 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.00023 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1390 | +| iterations | 18033 | +| time_elapsed | 26551 | +| total_timesteps | 36931584 | +| train/ | | +| approx_kl | 0.012864605 | +| clip_fraction | 0.37 | +| clip_range | 0.0658 | +| entropy_loss | -5.97 | +| explained_variance | 0.267 | +| learning_rate | 4.12e-05 | +| loss | -0.0322 | +| n_updates | 87948 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.00011 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1390 | +| iterations | 18034 | +| time_elapsed | 26552 | +| total_timesteps | 36933632 | +| train/ | | +| approx_kl | 0.011430286 | +| clip_fraction | 0.331 | +| clip_range | 0.0658 | +| entropy_loss | -6.14 | +| explained_variance | 0.479 | +| learning_rate | 4.12e-05 | +| loss | -0.0303 | +| n_updates | 87952 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000197 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1390 | +| iterations | 18035 | +| time_elapsed | 26554 | +| total_timesteps | 36935680 | +| train/ | | +| approx_kl | 0.01331895 | +| clip_fraction | 0.353 | +| clip_range | 0.0658 | +| entropy_loss | -5.97 | +| explained_variance | 0.165 | +| learning_rate | 4.12e-05 | +| loss | -0.0268 | +| n_updates | 87956 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000172 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1390 | +| iterations | 18036 | +| time_elapsed | 26556 | +| total_timesteps | 36937728 | +| train/ | | +| approx_kl | 0.013279237 | +| clip_fraction | 0.363 | +| clip_range | 0.0658 | +| entropy_loss | -5.34 | +| explained_variance | 0.706 | +| learning_rate | 4.12e-05 | +| loss | -0.032 | +| n_updates | 87960 | +| policy_gradient_loss | -0.0204 | +| value_loss | 8.43e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1390 | +| iterations | 18037 | +| time_elapsed | 26557 | +| total_timesteps | 36939776 | +| train/ | | +| approx_kl | 0.011515193 | +| clip_fraction | 0.329 | +| clip_range | 0.0658 | +| entropy_loss | -5.85 | +| explained_variance | 0.413 | +| learning_rate | 4.12e-05 | +| loss | -0.0296 | +| n_updates | 87964 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000101 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1390 | +| iterations | 18038 | +| time_elapsed | 26559 | +| total_timesteps | 36941824 | +| train/ | | +| approx_kl | 0.01593794 | +| clip_fraction | 0.327 | +| clip_range | 0.0658 | +| entropy_loss | -4.96 | +| explained_variance | 0.401 | +| learning_rate | 4.12e-05 | +| loss | -0.0203 | +| n_updates | 87968 | +| policy_gradient_loss | -0.0145 | +| value_loss | 0.000428 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1390 | +| iterations | 18039 | +| time_elapsed | 26560 | +| total_timesteps | 36943872 | +| train/ | | +| approx_kl | 0.012987947 | +| clip_fraction | 0.357 | +| clip_range | 0.0658 | +| entropy_loss | -6.08 | +| explained_variance | -0.214 | +| learning_rate | 4.12e-05 | +| loss | -0.0302 | +| n_updates | 87972 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.00012 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1390 | +| iterations | 18040 | +| time_elapsed | 26562 | +| total_timesteps | 36945920 | +| train/ | | +| approx_kl | 0.013482629 | +| clip_fraction | 0.318 | +| clip_range | 0.0658 | +| entropy_loss | -6.34 | +| explained_variance | 0.274 | +| learning_rate | 4.12e-05 | +| loss | -0.0228 | +| n_updates | 87976 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000256 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1390 | +| iterations | 18041 | +| time_elapsed | 26563 | +| total_timesteps | 36947968 | +| train/ | | +| approx_kl | 0.01436029 | +| clip_fraction | 0.352 | +| clip_range | 0.0658 | +| entropy_loss | -5.82 | +| explained_variance | 0.631 | +| learning_rate | 4.12e-05 | +| loss | -0.0301 | +| n_updates | 87980 | +| policy_gradient_loss | -0.019 | +| value_loss | 8.75e-05 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1390 | +| iterations | 18042 | +| time_elapsed | 26565 | +| total_timesteps | 36950016 | +| train/ | | +| approx_kl | 0.01406549 | +| clip_fraction | 0.309 | +| clip_range | 0.0658 | +| entropy_loss | -5.93 | +| explained_variance | 0.348 | +| learning_rate | 4.12e-05 | +| loss | -0.0246 | +| n_updates | 87984 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000221 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1390 | +| iterations | 18043 | +| time_elapsed | 26566 | +| total_timesteps | 36952064 | +| train/ | | +| approx_kl | 0.014191577 | +| clip_fraction | 0.341 | +| clip_range | 0.0658 | +| entropy_loss | -5.91 | +| explained_variance | 0.286 | +| learning_rate | 4.12e-05 | +| loss | -0.0265 | +| n_updates | 87988 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000175 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1390 | +| iterations | 18044 | +| time_elapsed | 26568 | +| total_timesteps | 36954112 | +| train/ | | +| approx_kl | 0.012332553 | +| clip_fraction | 0.355 | +| clip_range | 0.0658 | +| entropy_loss | -6.31 | +| explained_variance | 0.369 | +| learning_rate | 4.12e-05 | +| loss | -0.0279 | +| n_updates | 87992 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000146 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1390 | +| iterations | 18045 | +| time_elapsed | 26569 | +| total_timesteps | 36956160 | +| train/ | | +| approx_kl | 0.01399444 | +| clip_fraction | 0.351 | +| clip_range | 0.0658 | +| entropy_loss | -6.15 | +| explained_variance | 0.378 | +| learning_rate | 4.12e-05 | +| loss | -0.028 | +| n_updates | 87996 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000113 | +---------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1390 | +| iterations | 18046 | +| time_elapsed | 26571 | +| total_timesteps | 36958208 | +| train/ | | +| approx_kl | 0.0085985 | +| clip_fraction | 0.309 | +| clip_range | 0.0658 | +| entropy_loss | -6.09 | +| explained_variance | 0.262 | +| learning_rate | 4.12e-05 | +| loss | -0.0242 | +| n_updates | 88000 | +| policy_gradient_loss | -0.0143 | +| value_loss | 0.000479 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1390 | +| iterations | 18047 | +| time_elapsed | 26572 | +| total_timesteps | 36960256 | +| train/ | | +| approx_kl | 0.011383147 | +| clip_fraction | 0.34 | +| clip_range | 0.0658 | +| entropy_loss | -6.1 | +| explained_variance | 0.437 | +| learning_rate | 4.12e-05 | +| loss | -0.0326 | +| n_updates | 88004 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000134 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1390 | +| iterations | 18048 | +| time_elapsed | 26574 | +| total_timesteps | 36962304 | +| train/ | | +| approx_kl | 0.0124835055 | +| clip_fraction | 0.345 | +| clip_range | 0.0658 | +| entropy_loss | -6.12 | +| explained_variance | 0.423 | +| learning_rate | 4.12e-05 | +| loss | -0.0326 | +| n_updates | 88008 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000118 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1390 | +| iterations | 18049 | +| time_elapsed | 26575 | +| total_timesteps | 36964352 | +| train/ | | +| approx_kl | 0.009484785 | +| clip_fraction | 0.315 | +| clip_range | 0.0658 | +| entropy_loss | -5.8 | +| explained_variance | 0.431 | +| learning_rate | 4.12e-05 | +| loss | -0.0225 | +| n_updates | 88012 | +| policy_gradient_loss | -0.0133 | +| value_loss | 0.000236 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1390 | +| iterations | 18050 | +| time_elapsed | 26577 | +| total_timesteps | 36966400 | +| train/ | | +| approx_kl | 0.013744801 | +| clip_fraction | 0.342 | +| clip_range | 0.0658 | +| entropy_loss | -5.91 | +| explained_variance | 0.341 | +| learning_rate | 4.12e-05 | +| loss | -0.0271 | +| n_updates | 88016 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.00024 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1390 | +| iterations | 18051 | +| time_elapsed | 26579 | +| total_timesteps | 36968448 | +| train/ | | +| approx_kl | 0.014248651 | +| clip_fraction | 0.358 | +| clip_range | 0.0658 | +| entropy_loss | -5.8 | +| explained_variance | 0.424 | +| learning_rate | 4.12e-05 | +| loss | -0.0354 | +| n_updates | 88020 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000187 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1390 | +| iterations | 18052 | +| time_elapsed | 26580 | +| total_timesteps | 36970496 | +| train/ | | +| approx_kl | 0.013496498 | +| clip_fraction | 0.356 | +| clip_range | 0.0658 | +| entropy_loss | -6.02 | +| explained_variance | 0.374 | +| learning_rate | 4.12e-05 | +| loss | -0.031 | +| n_updates | 88024 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.00013 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1390 | +| iterations | 18053 | +| time_elapsed | 26582 | +| total_timesteps | 36972544 | +| train/ | | +| approx_kl | 0.014590794 | +| clip_fraction | 0.324 | +| clip_range | 0.0658 | +| entropy_loss | -5.68 | +| explained_variance | 0.618 | +| learning_rate | 4.12e-05 | +| loss | -0.0276 | +| n_updates | 88028 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000131 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1390 | +| iterations | 18054 | +| time_elapsed | 26583 | +| total_timesteps | 36974592 | +| train/ | | +| approx_kl | 0.015087366 | +| clip_fraction | 0.352 | +| clip_range | 0.0658 | +| entropy_loss | -6.51 | +| explained_variance | -0.273 | +| learning_rate | 4.12e-05 | +| loss | -0.0399 | +| n_updates | 88032 | +| policy_gradient_loss | -0.0218 | +| value_loss | 6.7e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1390 | +| iterations | 18055 | +| time_elapsed | 26585 | +| total_timesteps | 36976640 | +| train/ | | +| approx_kl | 0.012109108 | +| clip_fraction | 0.347 | +| clip_range | 0.0658 | +| entropy_loss | -6.51 | +| explained_variance | -0.182 | +| learning_rate | 4.12e-05 | +| loss | -0.0311 | +| n_updates | 88036 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000147 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1390 | +| iterations | 18056 | +| time_elapsed | 26586 | +| total_timesteps | 36978688 | +| train/ | | +| approx_kl | 0.010783818 | +| clip_fraction | 0.339 | +| clip_range | 0.0658 | +| entropy_loss | -6.02 | +| explained_variance | 0.479 | +| learning_rate | 4.12e-05 | +| loss | -0.0239 | +| n_updates | 88040 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.00016 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1390 | +| iterations | 18057 | +| time_elapsed | 26588 | +| total_timesteps | 36980736 | +| train/ | | +| approx_kl | 0.01188262 | +| clip_fraction | 0.323 | +| clip_range | 0.0658 | +| entropy_loss | -5.76 | +| explained_variance | 0.527 | +| learning_rate | 4.12e-05 | +| loss | -0.0275 | +| n_updates | 88044 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.00012 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1390 | +| iterations | 18058 | +| time_elapsed | 26589 | +| total_timesteps | 36982784 | +| train/ | | +| approx_kl | 0.014064292 | +| clip_fraction | 0.349 | +| clip_range | 0.0658 | +| entropy_loss | -5.72 | +| explained_variance | 0.282 | +| learning_rate | 4.12e-05 | +| loss | -0.0297 | +| n_updates | 88048 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000183 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1390 | +| iterations | 18059 | +| time_elapsed | 26591 | +| total_timesteps | 36984832 | +| train/ | | +| approx_kl | 0.013517513 | +| clip_fraction | 0.314 | +| clip_range | 0.0658 | +| entropy_loss | -6.01 | +| explained_variance | 0.566 | +| learning_rate | 4.12e-05 | +| loss | -0.0301 | +| n_updates | 88052 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000144 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1390 | +| iterations | 18060 | +| time_elapsed | 26592 | +| total_timesteps | 36986880 | +| train/ | | +| approx_kl | 0.013854598 | +| clip_fraction | 0.328 | +| clip_range | 0.0658 | +| entropy_loss | -5.3 | +| explained_variance | 0.804 | +| learning_rate | 4.12e-05 | +| loss | -0.0253 | +| n_updates | 88056 | +| policy_gradient_loss | -0.0173 | +| value_loss | 9.31e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1390 | +| iterations | 18061 | +| time_elapsed | 26594 | +| total_timesteps | 36988928 | +| train/ | | +| approx_kl | 0.014670813 | +| clip_fraction | 0.386 | +| clip_range | 0.0658 | +| entropy_loss | -5.74 | +| explained_variance | 0.554 | +| learning_rate | 4.12e-05 | +| loss | -0.0305 | +| n_updates | 88060 | +| policy_gradient_loss | -0.018 | +| value_loss | 8.99e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1390 | +| iterations | 18062 | +| time_elapsed | 26596 | +| total_timesteps | 36990976 | +| train/ | | +| approx_kl | 0.018417504 | +| clip_fraction | 0.346 | +| clip_range | 0.0658 | +| entropy_loss | -5.37 | +| explained_variance | 0.653 | +| learning_rate | 4.12e-05 | +| loss | -0.03 | +| n_updates | 88064 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000128 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1390 | +| iterations | 18063 | +| time_elapsed | 26597 | +| total_timesteps | 36993024 | +| train/ | | +| approx_kl | 0.017040456 | +| clip_fraction | 0.365 | +| clip_range | 0.0658 | +| entropy_loss | -5.7 | +| explained_variance | 0.504 | +| learning_rate | 4.12e-05 | +| loss | -0.036 | +| n_updates | 88068 | +| policy_gradient_loss | -0.0215 | +| value_loss | 7.1e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1390 | +| iterations | 18064 | +| time_elapsed | 26599 | +| total_timesteps | 36995072 | +| train/ | | +| approx_kl | 0.0133945355 | +| clip_fraction | 0.316 | +| clip_range | 0.0658 | +| entropy_loss | -5.94 | +| explained_variance | 0.182 | +| learning_rate | 4.12e-05 | +| loss | -0.0189 | +| n_updates | 88072 | +| policy_gradient_loss | -0.0136 | +| value_loss | 0.000276 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1390 | +| iterations | 18065 | +| time_elapsed | 26600 | +| total_timesteps | 36997120 | +| train/ | | +| approx_kl | 0.01306233 | +| clip_fraction | 0.358 | +| clip_range | 0.0658 | +| entropy_loss | -5.77 | +| explained_variance | 0.375 | +| learning_rate | 4.12e-05 | +| loss | -0.0251 | +| n_updates | 88076 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.00032 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1390 | +| iterations | 18066 | +| time_elapsed | 26602 | +| total_timesteps | 36999168 | +| train/ | | +| approx_kl | 0.015566013 | +| clip_fraction | 0.401 | +| clip_range | 0.0658 | +| entropy_loss | -5.17 | +| explained_variance | 0.59 | +| learning_rate | 4.12e-05 | +| loss | -0.0332 | +| n_updates | 88080 | +| policy_gradient_loss | -0.0227 | +| value_loss | 8.19e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1390 | +| iterations | 18067 | +| time_elapsed | 26603 | +| total_timesteps | 37001216 | +| train/ | | +| approx_kl | 0.017893355 | +| clip_fraction | 0.337 | +| clip_range | 0.0658 | +| entropy_loss | -5.67 | +| explained_variance | 0.653 | +| learning_rate | 4.12e-05 | +| loss | -0.0313 | +| n_updates | 88084 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.00012 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1390 | +| iterations | 18068 | +| time_elapsed | 26605 | +| total_timesteps | 37003264 | +| train/ | | +| approx_kl | 0.010106571 | +| clip_fraction | 0.338 | +| clip_range | 0.0657 | +| entropy_loss | -6.45 | +| explained_variance | -0.122 | +| learning_rate | 4.12e-05 | +| loss | -0.0294 | +| n_updates | 88088 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000204 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1390 | +| iterations | 18069 | +| time_elapsed | 26606 | +| total_timesteps | 37005312 | +| train/ | | +| approx_kl | 0.013191557 | +| clip_fraction | 0.342 | +| clip_range | 0.0657 | +| entropy_loss | -6.08 | +| explained_variance | 0.121 | +| learning_rate | 4.12e-05 | +| loss | -0.0286 | +| n_updates | 88092 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000279 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1390 | +| iterations | 18070 | +| time_elapsed | 26608 | +| total_timesteps | 37007360 | +| train/ | | +| approx_kl | 0.01654059 | +| clip_fraction | 0.344 | +| clip_range | 0.0657 | +| entropy_loss | -5.13 | +| explained_variance | 0.522 | +| learning_rate | 4.12e-05 | +| loss | -0.0193 | +| n_updates | 88096 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000172 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1390 | +| iterations | 18071 | +| time_elapsed | 26609 | +| total_timesteps | 37009408 | +| train/ | | +| approx_kl | 0.015391954 | +| clip_fraction | 0.33 | +| clip_range | 0.0657 | +| entropy_loss | -5.82 | +| explained_variance | 0.35 | +| learning_rate | 4.12e-05 | +| loss | -0.0328 | +| n_updates | 88100 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000139 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1390 | +| iterations | 18072 | +| time_elapsed | 26611 | +| total_timesteps | 37011456 | +| train/ | | +| approx_kl | 0.014630449 | +| clip_fraction | 0.342 | +| clip_range | 0.0657 | +| entropy_loss | -5.95 | +| explained_variance | 0.383 | +| learning_rate | 4.12e-05 | +| loss | -0.0275 | +| n_updates | 88104 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000152 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1390 | +| iterations | 18073 | +| time_elapsed | 26612 | +| total_timesteps | 37013504 | +| train/ | | +| approx_kl | 0.010124147 | +| clip_fraction | 0.322 | +| clip_range | 0.0657 | +| entropy_loss | -6.25 | +| explained_variance | 0.326 | +| learning_rate | 4.12e-05 | +| loss | -0.02 | +| n_updates | 88108 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000289 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1390 | +| iterations | 18074 | +| time_elapsed | 26614 | +| total_timesteps | 37015552 | +| train/ | | +| approx_kl | 0.011064654 | +| clip_fraction | 0.339 | +| clip_range | 0.0657 | +| entropy_loss | -6.78 | +| explained_variance | -0.178 | +| learning_rate | 4.12e-05 | +| loss | -0.0269 | +| n_updates | 88112 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000115 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1390 | +| iterations | 18075 | +| time_elapsed | 26616 | +| total_timesteps | 37017600 | +| train/ | | +| approx_kl | 0.011206815 | +| clip_fraction | 0.321 | +| clip_range | 0.0657 | +| entropy_loss | -6.35 | +| explained_variance | 0.166 | +| learning_rate | 4.12e-05 | +| loss | -0.0303 | +| n_updates | 88116 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000246 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1390 | +| iterations | 18076 | +| time_elapsed | 26617 | +| total_timesteps | 37019648 | +| train/ | | +| approx_kl | 0.0086321 | +| clip_fraction | 0.307 | +| clip_range | 0.0657 | +| entropy_loss | -5.38 | +| explained_variance | 0.445 | +| learning_rate | 4.12e-05 | +| loss | -0.0223 | +| n_updates | 88120 | +| policy_gradient_loss | -0.0119 | +| value_loss | 0.000338 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1390 | +| iterations | 18077 | +| time_elapsed | 26619 | +| total_timesteps | 37021696 | +| train/ | | +| approx_kl | 0.014504457 | +| clip_fraction | 0.322 | +| clip_range | 0.0657 | +| entropy_loss | -4.9 | +| explained_variance | 0.511 | +| learning_rate | 4.12e-05 | +| loss | -0.0227 | +| n_updates | 88124 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000219 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1390 | +| iterations | 18078 | +| time_elapsed | 26620 | +| total_timesteps | 37023744 | +| train/ | | +| approx_kl | 0.0152703095 | +| clip_fraction | 0.379 | +| clip_range | 0.0657 | +| entropy_loss | -5.38 | +| explained_variance | 0.698 | +| learning_rate | 4.12e-05 | +| loss | -0.0329 | +| n_updates | 88128 | +| policy_gradient_loss | -0.0217 | +| value_loss | 7.22e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1390 | +| iterations | 18079 | +| time_elapsed | 26622 | +| total_timesteps | 37025792 | +| train/ | | +| approx_kl | 0.012378946 | +| clip_fraction | 0.334 | +| clip_range | 0.0657 | +| entropy_loss | -6.04 | +| explained_variance | 0.065 | +| learning_rate | 4.12e-05 | +| loss | -0.0291 | +| n_updates | 88132 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000174 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1390 | +| iterations | 18080 | +| time_elapsed | 26623 | +| total_timesteps | 37027840 | +| train/ | | +| approx_kl | 0.017393753 | +| clip_fraction | 0.343 | +| clip_range | 0.0657 | +| entropy_loss | -6.13 | +| explained_variance | 0.581 | +| learning_rate | 4.12e-05 | +| loss | -0.0287 | +| n_updates | 88136 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000104 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1390 | +| iterations | 18081 | +| time_elapsed | 26625 | +| total_timesteps | 37029888 | +| train/ | | +| approx_kl | 0.011751716 | +| clip_fraction | 0.322 | +| clip_range | 0.0657 | +| entropy_loss | -6.07 | +| explained_variance | 0.303 | +| learning_rate | 4.12e-05 | +| loss | -0.0225 | +| n_updates | 88140 | +| policy_gradient_loss | -0.0146 | +| value_loss | 0.000225 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1390 | +| iterations | 18082 | +| time_elapsed | 26626 | +| total_timesteps | 37031936 | +| train/ | | +| approx_kl | 0.011697189 | +| clip_fraction | 0.327 | +| clip_range | 0.0657 | +| entropy_loss | -5.67 | +| explained_variance | 0.595 | +| learning_rate | 4.12e-05 | +| loss | -0.0253 | +| n_updates | 88144 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000124 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1390 | +| iterations | 18083 | +| time_elapsed | 26628 | +| total_timesteps | 37033984 | +| train/ | | +| approx_kl | 0.013975719 | +| clip_fraction | 0.366 | +| clip_range | 0.0657 | +| entropy_loss | -5.73 | +| explained_variance | -0.0529 | +| learning_rate | 4.12e-05 | +| loss | -0.0309 | +| n_updates | 88148 | +| policy_gradient_loss | -0.019 | +| value_loss | 9.68e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1390 | +| iterations | 18084 | +| time_elapsed | 26629 | +| total_timesteps | 37036032 | +| train/ | | +| approx_kl | 0.012010604 | +| clip_fraction | 0.327 | +| clip_range | 0.0657 | +| entropy_loss | -6.08 | +| explained_variance | 0.399 | +| learning_rate | 4.12e-05 | +| loss | -0.0267 | +| n_updates | 88152 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000108 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1390 | +| iterations | 18085 | +| time_elapsed | 26631 | +| total_timesteps | 37038080 | +| train/ | | +| approx_kl | 0.011586603 | +| clip_fraction | 0.34 | +| clip_range | 0.0657 | +| entropy_loss | -5.6 | +| explained_variance | 0.496 | +| learning_rate | 4.12e-05 | +| loss | -0.0243 | +| n_updates | 88156 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000123 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1390 | +| iterations | 18086 | +| time_elapsed | 26632 | +| total_timesteps | 37040128 | +| train/ | | +| approx_kl | 0.016425882 | +| clip_fraction | 0.345 | +| clip_range | 0.0657 | +| entropy_loss | -5.88 | +| explained_variance | -0.0537 | +| learning_rate | 4.12e-05 | +| loss | -0.0346 | +| n_updates | 88160 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000104 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1390 | +| iterations | 18087 | +| time_elapsed | 26634 | +| total_timesteps | 37042176 | +| train/ | | +| approx_kl | 0.01349717 | +| clip_fraction | 0.361 | +| clip_range | 0.0657 | +| entropy_loss | -5.6 | +| explained_variance | 0.633 | +| learning_rate | 4.12e-05 | +| loss | -0.0253 | +| n_updates | 88164 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000124 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1390 | +| iterations | 18088 | +| time_elapsed | 26635 | +| total_timesteps | 37044224 | +| train/ | | +| approx_kl | 0.01268889 | +| clip_fraction | 0.276 | +| clip_range | 0.0657 | +| entropy_loss | -4.97 | +| explained_variance | 0.45 | +| learning_rate | 4.12e-05 | +| loss | -0.0217 | +| n_updates | 88168 | +| policy_gradient_loss | -0.0136 | +| value_loss | 0.000327 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1390 | +| iterations | 18089 | +| time_elapsed | 26637 | +| total_timesteps | 37046272 | +| train/ | | +| approx_kl | 0.012248616 | +| clip_fraction | 0.332 | +| clip_range | 0.0657 | +| entropy_loss | -5.24 | +| explained_variance | 0.661 | +| learning_rate | 4.12e-05 | +| loss | -0.028 | +| n_updates | 88172 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000154 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1390 | +| iterations | 18090 | +| time_elapsed | 26638 | +| total_timesteps | 37048320 | +| train/ | | +| approx_kl | 0.013463179 | +| clip_fraction | 0.334 | +| clip_range | 0.0657 | +| entropy_loss | -5.64 | +| explained_variance | 0.232 | +| learning_rate | 4.12e-05 | +| loss | -0.0291 | +| n_updates | 88176 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000158 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1390 | +| iterations | 18091 | +| time_elapsed | 26640 | +| total_timesteps | 37050368 | +| train/ | | +| approx_kl | 0.015237937 | +| clip_fraction | 0.366 | +| clip_range | 0.0657 | +| entropy_loss | -6.41 | +| explained_variance | -0.0852 | +| learning_rate | 4.12e-05 | +| loss | -0.0261 | +| n_updates | 88180 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000186 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1390 | +| iterations | 18092 | +| time_elapsed | 26641 | +| total_timesteps | 37052416 | +| train/ | | +| approx_kl | 0.014934986 | +| clip_fraction | 0.364 | +| clip_range | 0.0657 | +| entropy_loss | -6.1 | +| explained_variance | 0.468 | +| learning_rate | 4.12e-05 | +| loss | -0.0324 | +| n_updates | 88184 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000111 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1390 | +| iterations | 18093 | +| time_elapsed | 26643 | +| total_timesteps | 37054464 | +| train/ | | +| approx_kl | 0.01559523 | +| clip_fraction | 0.35 | +| clip_range | 0.0657 | +| entropy_loss | -5.64 | +| explained_variance | 0.369 | +| learning_rate | 4.12e-05 | +| loss | -0.0286 | +| n_updates | 88188 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000239 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1390 | +| iterations | 18094 | +| time_elapsed | 26645 | +| total_timesteps | 37056512 | +| train/ | | +| approx_kl | 0.014182579 | +| clip_fraction | 0.345 | +| clip_range | 0.0657 | +| entropy_loss | -5.65 | +| explained_variance | 0.538 | +| learning_rate | 4.12e-05 | +| loss | -0.0312 | +| n_updates | 88192 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000108 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1390 | +| iterations | 18095 | +| time_elapsed | 26646 | +| total_timesteps | 37058560 | +| train/ | | +| approx_kl | 0.013544679 | +| clip_fraction | 0.332 | +| clip_range | 0.0657 | +| entropy_loss | -5.85 | +| explained_variance | 0.354 | +| learning_rate | 4.12e-05 | +| loss | -0.0254 | +| n_updates | 88196 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000195 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1390 | +| iterations | 18096 | +| time_elapsed | 26648 | +| total_timesteps | 37060608 | +| train/ | | +| approx_kl | 0.009571057 | +| clip_fraction | 0.306 | +| clip_range | 0.0657 | +| entropy_loss | -6.16 | +| explained_variance | 0.372 | +| learning_rate | 4.12e-05 | +| loss | -0.0191 | +| n_updates | 88200 | +| policy_gradient_loss | -0.0136 | +| value_loss | 0.000291 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1390 | +| iterations | 18097 | +| time_elapsed | 26649 | +| total_timesteps | 37062656 | +| train/ | | +| approx_kl | 0.009817878 | +| clip_fraction | 0.297 | +| clip_range | 0.0657 | +| entropy_loss | -5.45 | +| explained_variance | 0.504 | +| learning_rate | 4.12e-05 | +| loss | -0.0262 | +| n_updates | 88204 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000245 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1390 | +| iterations | 18098 | +| time_elapsed | 26651 | +| total_timesteps | 37064704 | +| train/ | | +| approx_kl | 0.010974926 | +| clip_fraction | 0.32 | +| clip_range | 0.0657 | +| entropy_loss | -5.7 | +| explained_variance | 0.273 | +| learning_rate | 4.12e-05 | +| loss | -0.0259 | +| n_updates | 88208 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000173 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1390 | +| iterations | 18099 | +| time_elapsed | 26652 | +| total_timesteps | 37066752 | +| train/ | | +| approx_kl | 0.01323878 | +| clip_fraction | 0.35 | +| clip_range | 0.0657 | +| entropy_loss | -5.73 | +| explained_variance | 0.258 | +| learning_rate | 4.12e-05 | +| loss | -0.0327 | +| n_updates | 88212 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000317 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1390 | +| iterations | 18100 | +| time_elapsed | 26654 | +| total_timesteps | 37068800 | +| train/ | | +| approx_kl | 0.016046941 | +| clip_fraction | 0.368 | +| clip_range | 0.0657 | +| entropy_loss | -5.51 | +| explained_variance | 0.526 | +| learning_rate | 4.12e-05 | +| loss | -0.0299 | +| n_updates | 88216 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000114 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1390 | +| iterations | 18101 | +| time_elapsed | 26655 | +| total_timesteps | 37070848 | +| train/ | | +| approx_kl | 0.009642135 | +| clip_fraction | 0.341 | +| clip_range | 0.0657 | +| entropy_loss | -5.77 | +| explained_variance | 0.536 | +| learning_rate | 4.12e-05 | +| loss | -0.0255 | +| n_updates | 88220 | +| policy_gradient_loss | -0.0146 | +| value_loss | 0.000166 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1390 | +| iterations | 18102 | +| time_elapsed | 26657 | +| total_timesteps | 37072896 | +| train/ | | +| approx_kl | 0.008849453 | +| clip_fraction | 0.306 | +| clip_range | 0.0657 | +| entropy_loss | -5.84 | +| explained_variance | 0.544 | +| learning_rate | 4.12e-05 | +| loss | -0.0249 | +| n_updates | 88224 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000158 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1390 | +| iterations | 18103 | +| time_elapsed | 26658 | +| total_timesteps | 37074944 | +| train/ | | +| approx_kl | 0.008395438 | +| clip_fraction | 0.317 | +| clip_range | 0.0657 | +| entropy_loss | -5.78 | +| explained_variance | 0.559 | +| learning_rate | 4.12e-05 | +| loss | -0.0251 | +| n_updates | 88228 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000177 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1390 | +| iterations | 18104 | +| time_elapsed | 26660 | +| total_timesteps | 37076992 | +| train/ | | +| approx_kl | 0.010603044 | +| clip_fraction | 0.303 | +| clip_range | 0.0657 | +| entropy_loss | -5.19 | +| explained_variance | 0.345 | +| learning_rate | 4.12e-05 | +| loss | -0.0219 | +| n_updates | 88232 | +| policy_gradient_loss | -0.0132 | +| value_loss | 0.000428 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1390 | +| iterations | 18105 | +| time_elapsed | 26661 | +| total_timesteps | 37079040 | +| train/ | | +| approx_kl | 0.014425187 | +| clip_fraction | 0.351 | +| clip_range | 0.0657 | +| entropy_loss | -5.59 | +| explained_variance | 0.294 | +| learning_rate | 4.12e-05 | +| loss | -0.0344 | +| n_updates | 88236 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000307 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1390 | +| iterations | 18106 | +| time_elapsed | 26663 | +| total_timesteps | 37081088 | +| train/ | | +| approx_kl | 0.011333977 | +| clip_fraction | 0.388 | +| clip_range | 0.0657 | +| entropy_loss | -5.71 | +| explained_variance | 0.137 | +| learning_rate | 4.12e-05 | +| loss | -0.0238 | +| n_updates | 88240 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000182 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1390 | +| iterations | 18107 | +| time_elapsed | 26665 | +| total_timesteps | 37083136 | +| train/ | | +| approx_kl | 0.015752546 | +| clip_fraction | 0.368 | +| clip_range | 0.0657 | +| entropy_loss | -6.13 | +| explained_variance | -0.239 | +| learning_rate | 4.12e-05 | +| loss | -0.0295 | +| n_updates | 88244 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000111 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1390 | +| iterations | 18108 | +| time_elapsed | 26666 | +| total_timesteps | 37085184 | +| train/ | | +| approx_kl | 0.014895591 | +| clip_fraction | 0.342 | +| clip_range | 0.0657 | +| entropy_loss | -5.72 | +| explained_variance | 0.532 | +| learning_rate | 4.12e-05 | +| loss | -0.0268 | +| n_updates | 88248 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000164 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1390 | +| iterations | 18109 | +| time_elapsed | 26668 | +| total_timesteps | 37087232 | +| train/ | | +| approx_kl | 0.016463788 | +| clip_fraction | 0.339 | +| clip_range | 0.0657 | +| entropy_loss | -5.37 | +| explained_variance | 0.408 | +| learning_rate | 4.12e-05 | +| loss | -0.0224 | +| n_updates | 88252 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000235 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1390 | +| iterations | 18110 | +| time_elapsed | 26669 | +| total_timesteps | 37089280 | +| train/ | | +| approx_kl | 0.01650555 | +| clip_fraction | 0.38 | +| clip_range | 0.0657 | +| entropy_loss | -5.31 | +| explained_variance | 0.385 | +| learning_rate | 4.12e-05 | +| loss | -0.0307 | +| n_updates | 88256 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000135 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1390 | +| iterations | 18111 | +| time_elapsed | 26671 | +| total_timesteps | 37091328 | +| train/ | | +| approx_kl | 0.014183605 | +| clip_fraction | 0.379 | +| clip_range | 0.0657 | +| entropy_loss | -5.95 | +| explained_variance | 0.188 | +| learning_rate | 4.12e-05 | +| loss | -0.0266 | +| n_updates | 88260 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000107 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1390 | +| iterations | 18112 | +| time_elapsed | 26672 | +| total_timesteps | 37093376 | +| train/ | | +| approx_kl | 0.013114087 | +| clip_fraction | 0.338 | +| clip_range | 0.0657 | +| entropy_loss | -6.01 | +| explained_variance | 0.231 | +| learning_rate | 4.12e-05 | +| loss | -0.025 | +| n_updates | 88264 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000194 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1390 | +| iterations | 18113 | +| time_elapsed | 26674 | +| total_timesteps | 37095424 | +| train/ | | +| approx_kl | 0.012956317 | +| clip_fraction | 0.35 | +| clip_range | 0.0657 | +| entropy_loss | -6.01 | +| explained_variance | 0.511 | +| learning_rate | 4.12e-05 | +| loss | -0.0241 | +| n_updates | 88268 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000131 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1390 | +| iterations | 18114 | +| time_elapsed | 26675 | +| total_timesteps | 37097472 | +| train/ | | +| approx_kl | 0.010996944 | +| clip_fraction | 0.346 | +| clip_range | 0.0657 | +| entropy_loss | -6.23 | +| explained_variance | -0.08 | +| learning_rate | 4.12e-05 | +| loss | -0.0273 | +| n_updates | 88272 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000163 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1390 | +| iterations | 18115 | +| time_elapsed | 26677 | +| total_timesteps | 37099520 | +| train/ | | +| approx_kl | 0.013013653 | +| clip_fraction | 0.334 | +| clip_range | 0.0657 | +| entropy_loss | -6.02 | +| explained_variance | 0.615 | +| learning_rate | 4.12e-05 | +| loss | -0.0298 | +| n_updates | 88276 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000102 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1390 | +| iterations | 18116 | +| time_elapsed | 26678 | +| total_timesteps | 37101568 | +| train/ | | +| approx_kl | 0.0119048655 | +| clip_fraction | 0.333 | +| clip_range | 0.0657 | +| entropy_loss | -5.76 | +| explained_variance | 0.489 | +| learning_rate | 4.12e-05 | +| loss | -0.0229 | +| n_updates | 88280 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000178 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1390 | +| iterations | 18117 | +| time_elapsed | 26680 | +| total_timesteps | 37103616 | +| train/ | | +| approx_kl | 0.0114721935 | +| clip_fraction | 0.323 | +| clip_range | 0.0657 | +| entropy_loss | -5.29 | +| explained_variance | 0.448 | +| learning_rate | 4.12e-05 | +| loss | -0.0273 | +| n_updates | 88284 | +| policy_gradient_loss | -0.0132 | +| value_loss | 0.000344 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1390 | +| iterations | 18118 | +| time_elapsed | 26681 | +| total_timesteps | 37105664 | +| train/ | | +| approx_kl | 0.015429946 | +| clip_fraction | 0.351 | +| clip_range | 0.0657 | +| entropy_loss | -4.95 | +| explained_variance | 0.634 | +| learning_rate | 4.12e-05 | +| loss | -0.0299 | +| n_updates | 88288 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000128 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1390 | +| iterations | 18119 | +| time_elapsed | 26683 | +| total_timesteps | 37107712 | +| train/ | | +| approx_kl | 0.013693974 | +| clip_fraction | 0.361 | +| clip_range | 0.0657 | +| entropy_loss | -5.45 | +| explained_variance | 0.343 | +| learning_rate | 4.12e-05 | +| loss | -0.0308 | +| n_updates | 88292 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000116 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1390 | +| iterations | 18120 | +| time_elapsed | 26684 | +| total_timesteps | 37109760 | +| train/ | | +| approx_kl | 0.013492247 | +| clip_fraction | 0.347 | +| clip_range | 0.0657 | +| entropy_loss | -5.98 | +| explained_variance | 0.363 | +| learning_rate | 4.12e-05 | +| loss | -0.0248 | +| n_updates | 88296 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000141 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1390 | +| iterations | 18121 | +| time_elapsed | 26686 | +| total_timesteps | 37111808 | +| train/ | | +| approx_kl | 0.012581453 | +| clip_fraction | 0.359 | +| clip_range | 0.0657 | +| entropy_loss | -5.98 | +| explained_variance | 0.0724 | +| learning_rate | 4.12e-05 | +| loss | -0.0252 | +| n_updates | 88300 | +| policy_gradient_loss | -0.017 | +| value_loss | 9.61e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1390 | +| iterations | 18122 | +| time_elapsed | 26687 | +| total_timesteps | 37113856 | +| train/ | | +| approx_kl | 0.018193012 | +| clip_fraction | 0.319 | +| clip_range | 0.0657 | +| entropy_loss | -5.35 | +| explained_variance | 0.634 | +| learning_rate | 4.12e-05 | +| loss | -0.0261 | +| n_updates | 88304 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000139 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1390 | +| iterations | 18123 | +| time_elapsed | 26689 | +| total_timesteps | 37115904 | +| train/ | | +| approx_kl | 0.010761564 | +| clip_fraction | 0.308 | +| clip_range | 0.0657 | +| entropy_loss | -5.42 | +| explained_variance | 0.351 | +| learning_rate | 4.12e-05 | +| loss | -0.0272 | +| n_updates | 88308 | +| policy_gradient_loss | -0.0145 | +| value_loss | 0.000231 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1390 | +| iterations | 18124 | +| time_elapsed | 26691 | +| total_timesteps | 37117952 | +| train/ | | +| approx_kl | 0.011799973 | +| clip_fraction | 0.317 | +| clip_range | 0.0657 | +| entropy_loss | -5.41 | +| explained_variance | 0.514 | +| learning_rate | 4.12e-05 | +| loss | -0.0233 | +| n_updates | 88312 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000157 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1390 | +| iterations | 18125 | +| time_elapsed | 26692 | +| total_timesteps | 37120000 | +| train/ | | +| approx_kl | 0.013957785 | +| clip_fraction | 0.368 | +| clip_range | 0.0657 | +| entropy_loss | -5.34 | +| explained_variance | 0.497 | +| learning_rate | 4.12e-05 | +| loss | -0.0379 | +| n_updates | 88316 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000121 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1390 | +| iterations | 18126 | +| time_elapsed | 26694 | +| total_timesteps | 37122048 | +| train/ | | +| approx_kl | 0.014417092 | +| clip_fraction | 0.352 | +| clip_range | 0.0657 | +| entropy_loss | -6.16 | +| explained_variance | 0.482 | +| learning_rate | 4.12e-05 | +| loss | -0.0353 | +| n_updates | 88320 | +| policy_gradient_loss | -0.0177 | +| value_loss | 8.7e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1390 | +| iterations | 18127 | +| time_elapsed | 26695 | +| total_timesteps | 37124096 | +| train/ | | +| approx_kl | 0.0124601945 | +| clip_fraction | 0.326 | +| clip_range | 0.0657 | +| entropy_loss | -6.28 | +| explained_variance | 0.504 | +| learning_rate | 4.12e-05 | +| loss | -0.0322 | +| n_updates | 88324 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000127 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1390 | +| iterations | 18128 | +| time_elapsed | 26697 | +| total_timesteps | 37126144 | +| train/ | | +| approx_kl | 0.01413185 | +| clip_fraction | 0.328 | +| clip_range | 0.0657 | +| entropy_loss | -5.5 | +| explained_variance | 0.623 | +| learning_rate | 4.12e-05 | +| loss | -0.0254 | +| n_updates | 88328 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.00015 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1390 | +| iterations | 18129 | +| time_elapsed | 26698 | +| total_timesteps | 37128192 | +| train/ | | +| approx_kl | 0.012759306 | +| clip_fraction | 0.318 | +| clip_range | 0.0657 | +| entropy_loss | -4.86 | +| explained_variance | 0.554 | +| learning_rate | 4.12e-05 | +| loss | -0.0163 | +| n_updates | 88332 | +| policy_gradient_loss | -0.0136 | +| value_loss | 0.00021 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1390 | +| iterations | 18130 | +| time_elapsed | 26700 | +| total_timesteps | 37130240 | +| train/ | | +| approx_kl | 0.018312842 | +| clip_fraction | 0.367 | +| clip_range | 0.0657 | +| entropy_loss | -4.62 | +| explained_variance | 0.549 | +| learning_rate | 4.12e-05 | +| loss | -0.0258 | +| n_updates | 88336 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.00011 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1390 | +| iterations | 18131 | +| time_elapsed | 26701 | +| total_timesteps | 37132288 | +| train/ | | +| approx_kl | 0.014101681 | +| clip_fraction | 0.371 | +| clip_range | 0.0657 | +| entropy_loss | -5.69 | +| explained_variance | 0.381 | +| learning_rate | 4.12e-05 | +| loss | -0.0278 | +| n_updates | 88340 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000175 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1390 | +| iterations | 18132 | +| time_elapsed | 26703 | +| total_timesteps | 37134336 | +| train/ | | +| approx_kl | 0.014870012 | +| clip_fraction | 0.361 | +| clip_range | 0.0657 | +| entropy_loss | -5.39 | +| explained_variance | 0.643 | +| learning_rate | 4.12e-05 | +| loss | -0.0282 | +| n_updates | 88344 | +| policy_gradient_loss | -0.0194 | +| value_loss | 8.86e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1390 | +| iterations | 18133 | +| time_elapsed | 26704 | +| total_timesteps | 37136384 | +| train/ | | +| approx_kl | 0.010853541 | +| clip_fraction | 0.345 | +| clip_range | 0.0657 | +| entropy_loss | -6.24 | +| explained_variance | -0.0066 | +| learning_rate | 4.12e-05 | +| loss | -0.0311 | +| n_updates | 88348 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.00013 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1390 | +| iterations | 18134 | +| time_elapsed | 26706 | +| total_timesteps | 37138432 | +| train/ | | +| approx_kl | 0.010368505 | +| clip_fraction | 0.326 | +| clip_range | 0.0657 | +| entropy_loss | -5.99 | +| explained_variance | 0.51 | +| learning_rate | 4.12e-05 | +| loss | -0.0256 | +| n_updates | 88352 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000155 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1390 | +| iterations | 18135 | +| time_elapsed | 26708 | +| total_timesteps | 37140480 | +| train/ | | +| approx_kl | 0.008167572 | +| clip_fraction | 0.292 | +| clip_range | 0.0657 | +| entropy_loss | -6.2 | +| explained_variance | 0.351 | +| learning_rate | 4.12e-05 | +| loss | -0.0197 | +| n_updates | 88356 | +| policy_gradient_loss | -0.0125 | +| value_loss | 0.000339 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1390 | +| iterations | 18136 | +| time_elapsed | 26709 | +| total_timesteps | 37142528 | +| train/ | | +| approx_kl | 0.011791687 | +| clip_fraction | 0.32 | +| clip_range | 0.0657 | +| entropy_loss | -5.63 | +| explained_variance | 0.552 | +| learning_rate | 4.12e-05 | +| loss | -0.0294 | +| n_updates | 88360 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.00015 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1390 | +| iterations | 18137 | +| time_elapsed | 26711 | +| total_timesteps | 37144576 | +| train/ | | +| approx_kl | 0.010057567 | +| clip_fraction | 0.312 | +| clip_range | 0.0657 | +| entropy_loss | -5.59 | +| explained_variance | 0.194 | +| learning_rate | 4.12e-05 | +| loss | -0.0208 | +| n_updates | 88364 | +| policy_gradient_loss | -0.0147 | +| value_loss | 0.000488 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1390 | +| iterations | 18138 | +| time_elapsed | 26712 | +| total_timesteps | 37146624 | +| train/ | | +| approx_kl | 0.01240178 | +| clip_fraction | 0.334 | +| clip_range | 0.0657 | +| entropy_loss | -5.63 | +| explained_variance | 0.626 | +| learning_rate | 4.12e-05 | +| loss | -0.0304 | +| n_updates | 88368 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000163 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1390 | +| iterations | 18139 | +| time_elapsed | 26714 | +| total_timesteps | 37148672 | +| train/ | | +| approx_kl | 0.011928232 | +| clip_fraction | 0.355 | +| clip_range | 0.0657 | +| entropy_loss | -5.38 | +| explained_variance | 0.476 | +| learning_rate | 4.12e-05 | +| loss | -0.0193 | +| n_updates | 88372 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000298 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1390 | +| iterations | 18140 | +| time_elapsed | 26715 | +| total_timesteps | 37150720 | +| train/ | | +| approx_kl | 0.011262137 | +| clip_fraction | 0.338 | +| clip_range | 0.0657 | +| entropy_loss | -5.88 | +| explained_variance | 0.209 | +| learning_rate | 4.12e-05 | +| loss | -0.019 | +| n_updates | 88376 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000402 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1390 | +| iterations | 18141 | +| time_elapsed | 26717 | +| total_timesteps | 37152768 | +| train/ | | +| approx_kl | 0.014406977 | +| clip_fraction | 0.374 | +| clip_range | 0.0657 | +| entropy_loss | -6 | +| explained_variance | 0.453 | +| learning_rate | 4.12e-05 | +| loss | -0.0295 | +| n_updates | 88380 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000131 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1390 | +| iterations | 18142 | +| time_elapsed | 26718 | +| total_timesteps | 37154816 | +| train/ | | +| approx_kl | 0.014033563 | +| clip_fraction | 0.37 | +| clip_range | 0.0657 | +| entropy_loss | -6.56 | +| explained_variance | 0.141 | +| learning_rate | 4.12e-05 | +| loss | -0.033 | +| n_updates | 88384 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000134 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1390 | +| iterations | 18143 | +| time_elapsed | 26720 | +| total_timesteps | 37156864 | +| train/ | | +| approx_kl | 0.012871942 | +| clip_fraction | 0.348 | +| clip_range | 0.0657 | +| entropy_loss | -6.11 | +| explained_variance | 0.388 | +| learning_rate | 4.12e-05 | +| loss | -0.0291 | +| n_updates | 88388 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.00021 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1390 | +| iterations | 18144 | +| time_elapsed | 26721 | +| total_timesteps | 37158912 | +| train/ | | +| approx_kl | 0.01300876 | +| clip_fraction | 0.35 | +| clip_range | 0.0657 | +| entropy_loss | -5.98 | +| explained_variance | 0.517 | +| learning_rate | 4.12e-05 | +| loss | -0.0336 | +| n_updates | 88392 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000204 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1390 | +| iterations | 18145 | +| time_elapsed | 26723 | +| total_timesteps | 37160960 | +| train/ | | +| approx_kl | 0.012114653 | +| clip_fraction | 0.325 | +| clip_range | 0.0657 | +| entropy_loss | -5.42 | +| explained_variance | 0.562 | +| learning_rate | 4.12e-05 | +| loss | -0.0208 | +| n_updates | 88396 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000107 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1390 | +| iterations | 18146 | +| time_elapsed | 26725 | +| total_timesteps | 37163008 | +| train/ | | +| approx_kl | 0.011503344 | +| clip_fraction | 0.303 | +| clip_range | 0.0657 | +| entropy_loss | -5.27 | +| explained_variance | 0.485 | +| learning_rate | 4.12e-05 | +| loss | -0.0248 | +| n_updates | 88400 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000241 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1390 | +| iterations | 18147 | +| time_elapsed | 26726 | +| total_timesteps | 37165056 | +| train/ | | +| approx_kl | 0.010997878 | +| clip_fraction | 0.332 | +| clip_range | 0.0657 | +| entropy_loss | -5.75 | +| explained_variance | 0.251 | +| learning_rate | 4.12e-05 | +| loss | -0.03 | +| n_updates | 88404 | +| policy_gradient_loss | -0.0147 | +| value_loss | 0.000285 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1390 | +| iterations | 18148 | +| time_elapsed | 26728 | +| total_timesteps | 37167104 | +| train/ | | +| approx_kl | 0.013624763 | +| clip_fraction | 0.34 | +| clip_range | 0.0657 | +| entropy_loss | -5.83 | +| explained_variance | 0.484 | +| learning_rate | 4.12e-05 | +| loss | -0.0287 | +| n_updates | 88408 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1390 | +| iterations | 18149 | +| time_elapsed | 26729 | +| total_timesteps | 37169152 | +| train/ | | +| approx_kl | 0.014321746 | +| clip_fraction | 0.323 | +| clip_range | 0.0657 | +| entropy_loss | -5.57 | +| explained_variance | 0.421 | +| learning_rate | 4.12e-05 | +| loss | -0.0233 | +| n_updates | 88412 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000203 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1390 | +| iterations | 18150 | +| time_elapsed | 26731 | +| total_timesteps | 37171200 | +| train/ | | +| approx_kl | 0.011187337 | +| clip_fraction | 0.307 | +| clip_range | 0.0657 | +| entropy_loss | -5.32 | +| explained_variance | 0.525 | +| learning_rate | 4.12e-05 | +| loss | -0.0253 | +| n_updates | 88416 | +| policy_gradient_loss | -0.0147 | +| value_loss | 0.000208 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1390 | +| iterations | 18151 | +| time_elapsed | 26732 | +| total_timesteps | 37173248 | +| train/ | | +| approx_kl | 0.015556166 | +| clip_fraction | 0.361 | +| clip_range | 0.0657 | +| entropy_loss | -5.78 | +| explained_variance | 0.0671 | +| learning_rate | 4.12e-05 | +| loss | -0.0341 | +| n_updates | 88420 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1390 | +| iterations | 18152 | +| time_elapsed | 26734 | +| total_timesteps | 37175296 | +| train/ | | +| approx_kl | 0.015804317 | +| clip_fraction | 0.327 | +| clip_range | 0.0657 | +| entropy_loss | -5.91 | +| explained_variance | 0.503 | +| learning_rate | 4.12e-05 | +| loss | -0.0287 | +| n_updates | 88424 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000169 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1390 | +| iterations | 18153 | +| time_elapsed | 26735 | +| total_timesteps | 37177344 | +| train/ | | +| approx_kl | 0.016030665 | +| clip_fraction | 0.355 | +| clip_range | 0.0657 | +| entropy_loss | -6.03 | +| explained_variance | -0.225 | +| learning_rate | 4.12e-05 | +| loss | -0.0278 | +| n_updates | 88428 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000128 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1390 | +| iterations | 18154 | +| time_elapsed | 26737 | +| total_timesteps | 37179392 | +| train/ | | +| approx_kl | 0.013373317 | +| clip_fraction | 0.369 | +| clip_range | 0.0657 | +| entropy_loss | -6.55 | +| explained_variance | -0.24 | +| learning_rate | 4.12e-05 | +| loss | -0.0292 | +| n_updates | 88432 | +| policy_gradient_loss | -0.0196 | +| value_loss | 9.32e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1390 | +| iterations | 18155 | +| time_elapsed | 26738 | +| total_timesteps | 37181440 | +| train/ | | +| approx_kl | 0.013521055 | +| clip_fraction | 0.344 | +| clip_range | 0.0657 | +| entropy_loss | -6.29 | +| explained_variance | 0.356 | +| learning_rate | 4.12e-05 | +| loss | -0.0285 | +| n_updates | 88436 | +| policy_gradient_loss | -0.0178 | +| value_loss | 8.48e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1390 | +| iterations | 18156 | +| time_elapsed | 26740 | +| total_timesteps | 37183488 | +| train/ | | +| approx_kl | 0.013939818 | +| clip_fraction | 0.325 | +| clip_range | 0.0657 | +| entropy_loss | -5.65 | +| explained_variance | 0.413 | +| learning_rate | 4.12e-05 | +| loss | -0.0302 | +| n_updates | 88440 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.000168 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1390 | +| iterations | 18157 | +| time_elapsed | 26742 | +| total_timesteps | 37185536 | +| train/ | | +| approx_kl | 0.016325776 | +| clip_fraction | 0.322 | +| clip_range | 0.0657 | +| entropy_loss | -4.72 | +| explained_variance | 0.634 | +| learning_rate | 4.12e-05 | +| loss | -0.0269 | +| n_updates | 88444 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000167 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1390 | +| iterations | 18158 | +| time_elapsed | 26743 | +| total_timesteps | 37187584 | +| train/ | | +| approx_kl | 0.0122616235 | +| clip_fraction | 0.323 | +| clip_range | 0.0657 | +| entropy_loss | -5.38 | +| explained_variance | 0.4 | +| learning_rate | 4.12e-05 | +| loss | -0.0285 | +| n_updates | 88448 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.00014 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1390 | +| iterations | 18159 | +| time_elapsed | 26745 | +| total_timesteps | 37189632 | +| train/ | | +| approx_kl | 0.014601427 | +| clip_fraction | 0.331 | +| clip_range | 0.0657 | +| entropy_loss | -5.3 | +| explained_variance | 0.527 | +| learning_rate | 4.12e-05 | +| loss | -0.0217 | +| n_updates | 88452 | +| policy_gradient_loss | -0.0141 | +| value_loss | 0.000168 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1390 | +| iterations | 18160 | +| time_elapsed | 26746 | +| total_timesteps | 37191680 | +| train/ | | +| approx_kl | 0.01698772 | +| clip_fraction | 0.339 | +| clip_range | 0.0657 | +| entropy_loss | -5.68 | +| explained_variance | 0.303 | +| learning_rate | 4.12e-05 | +| loss | -0.0254 | +| n_updates | 88456 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000222 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1390 | +| iterations | 18161 | +| time_elapsed | 26748 | +| total_timesteps | 37193728 | +| train/ | | +| approx_kl | 0.013054722 | +| clip_fraction | 0.345 | +| clip_range | 0.0657 | +| entropy_loss | -6.15 | +| explained_variance | 0.131 | +| learning_rate | 4.12e-05 | +| loss | -0.0197 | +| n_updates | 88460 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000198 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1390 | +| iterations | 18162 | +| time_elapsed | 26749 | +| total_timesteps | 37195776 | +| train/ | | +| approx_kl | 0.011961583 | +| clip_fraction | 0.338 | +| clip_range | 0.0657 | +| entropy_loss | -6.12 | +| explained_variance | 0.448 | +| learning_rate | 4.12e-05 | +| loss | -0.0263 | +| n_updates | 88464 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000166 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1390 | +| iterations | 18163 | +| time_elapsed | 26751 | +| total_timesteps | 37197824 | +| train/ | | +| approx_kl | 0.012848616 | +| clip_fraction | 0.309 | +| clip_range | 0.0657 | +| entropy_loss | -5.33 | +| explained_variance | 0.288 | +| learning_rate | 4.12e-05 | +| loss | -0.0161 | +| n_updates | 88468 | +| policy_gradient_loss | -0.0122 | +| value_loss | 0.000537 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1390 | +| iterations | 18164 | +| time_elapsed | 26752 | +| total_timesteps | 37199872 | +| train/ | | +| approx_kl | 0.013753788 | +| clip_fraction | 0.405 | +| clip_range | 0.0657 | +| entropy_loss | -5.81 | +| explained_variance | 0.362 | +| learning_rate | 4.12e-05 | +| loss | -0.0365 | +| n_updates | 88472 | +| policy_gradient_loss | -0.0223 | +| value_loss | 0.000124 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1390 | +| iterations | 18165 | +| time_elapsed | 26754 | +| total_timesteps | 37201920 | +| train/ | | +| approx_kl | 0.017066222 | +| clip_fraction | 0.391 | +| clip_range | 0.0657 | +| entropy_loss | -5.65 | +| explained_variance | 0.669 | +| learning_rate | 4.12e-05 | +| loss | -0.0376 | +| n_updates | 88476 | +| policy_gradient_loss | -0.0224 | +| value_loss | 6.28e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1390 | +| iterations | 18166 | +| time_elapsed | 26755 | +| total_timesteps | 37203968 | +| train/ | | +| approx_kl | 0.013796782 | +| clip_fraction | 0.362 | +| clip_range | 0.0657 | +| entropy_loss | -5.85 | +| explained_variance | 0.343 | +| learning_rate | 4.12e-05 | +| loss | -0.0303 | +| n_updates | 88480 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000153 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1390 | +| iterations | 18167 | +| time_elapsed | 26757 | +| total_timesteps | 37206016 | +| train/ | | +| approx_kl | 0.016118234 | +| clip_fraction | 0.356 | +| clip_range | 0.0657 | +| entropy_loss | -6.07 | +| explained_variance | 0.258 | +| learning_rate | 4.12e-05 | +| loss | -0.0269 | +| n_updates | 88484 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000219 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1390 | +| iterations | 18168 | +| time_elapsed | 26758 | +| total_timesteps | 37208064 | +| train/ | | +| approx_kl | 0.009921674 | +| clip_fraction | 0.322 | +| clip_range | 0.0657 | +| entropy_loss | -5.52 | +| explained_variance | 0.527 | +| learning_rate | 4.12e-05 | +| loss | -0.0259 | +| n_updates | 88488 | +| policy_gradient_loss | -0.014 | +| value_loss | 0.000211 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1390 | +| iterations | 18169 | +| time_elapsed | 26760 | +| total_timesteps | 37210112 | +| train/ | | +| approx_kl | 0.013166603 | +| clip_fraction | 0.338 | +| clip_range | 0.0657 | +| entropy_loss | -5.55 | +| explained_variance | 0.297 | +| learning_rate | 4.12e-05 | +| loss | -0.0283 | +| n_updates | 88492 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000148 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1390 | +| iterations | 18170 | +| time_elapsed | 26761 | +| total_timesteps | 37212160 | +| train/ | | +| approx_kl | 0.013745021 | +| clip_fraction | 0.3 | +| clip_range | 0.0657 | +| entropy_loss | -4.89 | +| explained_variance | 0.594 | +| learning_rate | 4.12e-05 | +| loss | -0.0283 | +| n_updates | 88496 | +| policy_gradient_loss | -0.0143 | +| value_loss | 0.000146 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1390 | +| iterations | 18171 | +| time_elapsed | 26763 | +| total_timesteps | 37214208 | +| train/ | | +| approx_kl | 0.012247571 | +| clip_fraction | 0.333 | +| clip_range | 0.0657 | +| entropy_loss | -5.44 | +| explained_variance | 0.379 | +| learning_rate | 4.12e-05 | +| loss | -0.0227 | +| n_updates | 88500 | +| policy_gradient_loss | -0.0147 | +| value_loss | 0.000233 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1390 | +| iterations | 18172 | +| time_elapsed | 26764 | +| total_timesteps | 37216256 | +| train/ | | +| approx_kl | 0.0130592175 | +| clip_fraction | 0.346 | +| clip_range | 0.0657 | +| entropy_loss | -6.1 | +| explained_variance | 0.172 | +| learning_rate | 4.12e-05 | +| loss | -0.0304 | +| n_updates | 88504 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000182 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1390 | +| iterations | 18173 | +| time_elapsed | 26766 | +| total_timesteps | 37218304 | +| train/ | | +| approx_kl | 0.019748539 | +| clip_fraction | 0.372 | +| clip_range | 0.0657 | +| entropy_loss | -6.08 | +| explained_variance | 0.232 | +| learning_rate | 4.12e-05 | +| loss | -0.0302 | +| n_updates | 88508 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.0001 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1390 | +| iterations | 18174 | +| time_elapsed | 26768 | +| total_timesteps | 37220352 | +| train/ | | +| approx_kl | 0.01243496 | +| clip_fraction | 0.35 | +| clip_range | 0.0657 | +| entropy_loss | -5.84 | +| explained_variance | 0.377 | +| learning_rate | 4.12e-05 | +| loss | -0.0259 | +| n_updates | 88512 | +| policy_gradient_loss | -0.0184 | +| value_loss | 9.2e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1390 | +| iterations | 18175 | +| time_elapsed | 26769 | +| total_timesteps | 37222400 | +| train/ | | +| approx_kl | 0.013867132 | +| clip_fraction | 0.381 | +| clip_range | 0.0657 | +| entropy_loss | -6.06 | +| explained_variance | -0.0456 | +| learning_rate | 4.12e-05 | +| loss | -0.0341 | +| n_updates | 88516 | +| policy_gradient_loss | -0.0188 | +| value_loss | 9.73e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1390 | +| iterations | 18176 | +| time_elapsed | 26771 | +| total_timesteps | 37224448 | +| train/ | | +| approx_kl | 0.016114816 | +| clip_fraction | 0.334 | +| clip_range | 0.0657 | +| entropy_loss | -6.46 | +| explained_variance | 0.226 | +| learning_rate | 4.12e-05 | +| loss | -0.0284 | +| n_updates | 88520 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000228 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1390 | +| iterations | 18177 | +| time_elapsed | 26772 | +| total_timesteps | 37226496 | +| train/ | | +| approx_kl | 0.013710496 | +| clip_fraction | 0.35 | +| clip_range | 0.0657 | +| entropy_loss | -5.25 | +| explained_variance | 0.454 | +| learning_rate | 4.12e-05 | +| loss | -0.0262 | +| n_updates | 88524 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000203 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1390 | +| iterations | 18178 | +| time_elapsed | 26774 | +| total_timesteps | 37228544 | +| train/ | | +| approx_kl | 0.011160238 | +| clip_fraction | 0.319 | +| clip_range | 0.0657 | +| entropy_loss | -5.59 | +| explained_variance | 0.602 | +| learning_rate | 4.12e-05 | +| loss | -0.0225 | +| n_updates | 88528 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000137 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1390 | +| iterations | 18179 | +| time_elapsed | 26775 | +| total_timesteps | 37230592 | +| train/ | | +| approx_kl | 0.010444998 | +| clip_fraction | 0.299 | +| clip_range | 0.0657 | +| entropy_loss | -5.35 | +| explained_variance | 0.587 | +| learning_rate | 4.12e-05 | +| loss | -0.0304 | +| n_updates | 88532 | +| policy_gradient_loss | -0.0145 | +| value_loss | 0.000167 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1390 | +| iterations | 18180 | +| time_elapsed | 26777 | +| total_timesteps | 37232640 | +| train/ | | +| approx_kl | 0.009948812 | +| clip_fraction | 0.318 | +| clip_range | 0.0657 | +| entropy_loss | -6.18 | +| explained_variance | 0.306 | +| learning_rate | 4.12e-05 | +| loss | -0.0268 | +| n_updates | 88536 | +| policy_gradient_loss | -0.0142 | +| value_loss | 0.00015 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1390 | +| iterations | 18181 | +| time_elapsed | 26778 | +| total_timesteps | 37234688 | +| train/ | | +| approx_kl | 0.014971228 | +| clip_fraction | 0.35 | +| clip_range | 0.0657 | +| entropy_loss | -5.07 | +| explained_variance | 0.693 | +| learning_rate | 4.12e-05 | +| loss | -0.0284 | +| n_updates | 88540 | +| policy_gradient_loss | -0.0176 | +| value_loss | 9.31e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1390 | +| iterations | 18182 | +| time_elapsed | 26780 | +| total_timesteps | 37236736 | +| train/ | | +| approx_kl | 0.011771461 | +| clip_fraction | 0.328 | +| clip_range | 0.0657 | +| entropy_loss | -5.82 | +| explained_variance | -0.0649 | +| learning_rate | 4.12e-05 | +| loss | -0.027 | +| n_updates | 88544 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000204 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1390 | +| iterations | 18183 | +| time_elapsed | 26781 | +| total_timesteps | 37238784 | +| train/ | | +| approx_kl | 0.011506379 | +| clip_fraction | 0.322 | +| clip_range | 0.0657 | +| entropy_loss | -5.97 | +| explained_variance | 0.462 | +| learning_rate | 4.12e-05 | +| loss | -0.0259 | +| n_updates | 88548 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000193 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1390 | +| iterations | 18184 | +| time_elapsed | 26783 | +| total_timesteps | 37240832 | +| train/ | | +| approx_kl | 0.013527823 | +| clip_fraction | 0.368 | +| clip_range | 0.0657 | +| entropy_loss | -5.73 | +| explained_variance | 0.616 | +| learning_rate | 4.12e-05 | +| loss | -0.0346 | +| n_updates | 88552 | +| policy_gradient_loss | -0.0191 | +| value_loss | 8.84e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1390 | +| iterations | 18185 | +| time_elapsed | 26784 | +| total_timesteps | 37242880 | +| train/ | | +| approx_kl | 0.014495455 | +| clip_fraction | 0.348 | +| clip_range | 0.0657 | +| entropy_loss | -5.35 | +| explained_variance | 0.554 | +| learning_rate | 4.12e-05 | +| loss | -0.0265 | +| n_updates | 88556 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000118 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1390 | +| iterations | 18186 | +| time_elapsed | 26786 | +| total_timesteps | 37244928 | +| train/ | | +| approx_kl | 0.013974602 | +| clip_fraction | 0.317 | +| clip_range | 0.0657 | +| entropy_loss | -5.9 | +| explained_variance | 0.371 | +| learning_rate | 4.12e-05 | +| loss | -0.0231 | +| n_updates | 88560 | +| policy_gradient_loss | -0.0136 | +| value_loss | 0.000201 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1390 | +| iterations | 18187 | +| time_elapsed | 26787 | +| total_timesteps | 37246976 | +| train/ | | +| approx_kl | 0.010567223 | +| clip_fraction | 0.322 | +| clip_range | 0.0657 | +| entropy_loss | -6.23 | +| explained_variance | 0.145 | +| learning_rate | 4.12e-05 | +| loss | -0.0282 | +| n_updates | 88564 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.0003 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1390 | +| iterations | 18188 | +| time_elapsed | 26789 | +| total_timesteps | 37249024 | +| train/ | | +| approx_kl | 0.012768192 | +| clip_fraction | 0.36 | +| clip_range | 0.0657 | +| entropy_loss | -5.58 | +| explained_variance | 0.544 | +| learning_rate | 4.12e-05 | +| loss | -0.0371 | +| n_updates | 88568 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000123 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1390 | +| iterations | 18189 | +| time_elapsed | 26790 | +| total_timesteps | 37251072 | +| train/ | | +| approx_kl | 0.013875559 | +| clip_fraction | 0.372 | +| clip_range | 0.0657 | +| entropy_loss | -5.48 | +| explained_variance | 0.59 | +| learning_rate | 4.12e-05 | +| loss | -0.032 | +| n_updates | 88572 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000139 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1390 | +| iterations | 18190 | +| time_elapsed | 26792 | +| total_timesteps | 37253120 | +| train/ | | +| approx_kl | 0.013163098 | +| clip_fraction | 0.316 | +| clip_range | 0.0657 | +| entropy_loss | -5.31 | +| explained_variance | 0.504 | +| learning_rate | 4.12e-05 | +| loss | -0.023 | +| n_updates | 88576 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000162 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1390 | +| iterations | 18191 | +| time_elapsed | 26794 | +| total_timesteps | 37255168 | +| train/ | | +| approx_kl | 0.013836794 | +| clip_fraction | 0.351 | +| clip_range | 0.0657 | +| entropy_loss | -5.32 | +| explained_variance | 0.169 | +| learning_rate | 4.12e-05 | +| loss | -0.0306 | +| n_updates | 88580 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000136 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1390 | +| iterations | 18192 | +| time_elapsed | 26795 | +| total_timesteps | 37257216 | +| train/ | | +| approx_kl | 0.01673399 | +| clip_fraction | 0.34 | +| clip_range | 0.0657 | +| entropy_loss | -5.66 | +| explained_variance | 0.376 | +| learning_rate | 4.12e-05 | +| loss | -0.0275 | +| n_updates | 88584 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000263 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1390 | +| iterations | 18193 | +| time_elapsed | 26797 | +| total_timesteps | 37259264 | +| train/ | | +| approx_kl | 0.014158037 | +| clip_fraction | 0.36 | +| clip_range | 0.0657 | +| entropy_loss | -5.39 | +| explained_variance | 0.649 | +| learning_rate | 4.12e-05 | +| loss | -0.0246 | +| n_updates | 88588 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000147 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1390 | +| iterations | 18194 | +| time_elapsed | 26798 | +| total_timesteps | 37261312 | +| train/ | | +| approx_kl | 0.015686642 | +| clip_fraction | 0.359 | +| clip_range | 0.0657 | +| entropy_loss | -5.19 | +| explained_variance | 0.407 | +| learning_rate | 4.12e-05 | +| loss | -0.027 | +| n_updates | 88592 | +| policy_gradient_loss | -0.019 | +| value_loss | 8.3e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1390 | +| iterations | 18195 | +| time_elapsed | 26800 | +| total_timesteps | 37263360 | +| train/ | | +| approx_kl | 0.015003509 | +| clip_fraction | 0.334 | +| clip_range | 0.0657 | +| entropy_loss | -5.99 | +| explained_variance | 0.243 | +| learning_rate | 4.12e-05 | +| loss | -0.0311 | +| n_updates | 88596 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000234 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1390 | +| iterations | 18196 | +| time_elapsed | 26801 | +| total_timesteps | 37265408 | +| train/ | | +| approx_kl | 0.013314524 | +| clip_fraction | 0.328 | +| clip_range | 0.0657 | +| entropy_loss | -6.36 | +| explained_variance | -0.106 | +| learning_rate | 4.11e-05 | +| loss | -0.0263 | +| n_updates | 88600 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000116 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1390 | +| iterations | 18197 | +| time_elapsed | 26803 | +| total_timesteps | 37267456 | +| train/ | | +| approx_kl | 0.016641228 | +| clip_fraction | 0.342 | +| clip_range | 0.0657 | +| entropy_loss | -5.74 | +| explained_variance | 0.419 | +| learning_rate | 4.11e-05 | +| loss | -0.0337 | +| n_updates | 88604 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000106 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1390 | +| iterations | 18198 | +| time_elapsed | 26804 | +| total_timesteps | 37269504 | +| train/ | | +| approx_kl | 0.013327015 | +| clip_fraction | 0.336 | +| clip_range | 0.0657 | +| entropy_loss | -5.68 | +| explained_variance | 0.371 | +| learning_rate | 4.11e-05 | +| loss | -0.0239 | +| n_updates | 88608 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000237 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1390 | +| iterations | 18199 | +| time_elapsed | 26806 | +| total_timesteps | 37271552 | +| train/ | | +| approx_kl | 0.01183315 | +| clip_fraction | 0.341 | +| clip_range | 0.0657 | +| entropy_loss | -5.26 | +| explained_variance | 0.547 | +| learning_rate | 4.11e-05 | +| loss | -0.0292 | +| n_updates | 88612 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000222 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1390 | +| iterations | 18200 | +| time_elapsed | 26807 | +| total_timesteps | 37273600 | +| train/ | | +| approx_kl | 0.010165226 | +| clip_fraction | 0.328 | +| clip_range | 0.0657 | +| entropy_loss | -5.68 | +| explained_variance | 0.604 | +| learning_rate | 4.11e-05 | +| loss | -0.0285 | +| n_updates | 88616 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000101 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1390 | +| iterations | 18201 | +| time_elapsed | 26809 | +| total_timesteps | 37275648 | +| train/ | | +| approx_kl | 0.012139887 | +| clip_fraction | 0.345 | +| clip_range | 0.0657 | +| entropy_loss | -6.15 | +| explained_variance | -0.0854 | +| learning_rate | 4.11e-05 | +| loss | -0.028 | +| n_updates | 88620 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.00017 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1390 | +| iterations | 18202 | +| time_elapsed | 26810 | +| total_timesteps | 37277696 | +| train/ | | +| approx_kl | 0.012280179 | +| clip_fraction | 0.34 | +| clip_range | 0.0657 | +| entropy_loss | -6.44 | +| explained_variance | 0.35 | +| learning_rate | 4.11e-05 | +| loss | -0.029 | +| n_updates | 88624 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000147 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1390 | +| iterations | 18203 | +| time_elapsed | 26812 | +| total_timesteps | 37279744 | +| train/ | | +| approx_kl | 0.015524536 | +| clip_fraction | 0.369 | +| clip_range | 0.0657 | +| entropy_loss | -5.56 | +| explained_variance | 0.306 | +| learning_rate | 4.11e-05 | +| loss | -0.0247 | +| n_updates | 88628 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.00014 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1390 | +| iterations | 18204 | +| time_elapsed | 26813 | +| total_timesteps | 37281792 | +| train/ | | +| approx_kl | 0.009460421 | +| clip_fraction | 0.327 | +| clip_range | 0.0657 | +| entropy_loss | -6.09 | +| explained_variance | 0.412 | +| learning_rate | 4.11e-05 | +| loss | -0.0246 | +| n_updates | 88632 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000213 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1390 | +| iterations | 18205 | +| time_elapsed | 26815 | +| total_timesteps | 37283840 | +| train/ | | +| approx_kl | 0.011160514 | +| clip_fraction | 0.317 | +| clip_range | 0.0657 | +| entropy_loss | -4.72 | +| explained_variance | 0.562 | +| learning_rate | 4.11e-05 | +| loss | -0.0174 | +| n_updates | 88636 | +| policy_gradient_loss | -0.0133 | +| value_loss | 0.000302 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1390 | +| iterations | 18206 | +| time_elapsed | 26817 | +| total_timesteps | 37285888 | +| train/ | | +| approx_kl | 0.010475727 | +| clip_fraction | 0.332 | +| clip_range | 0.0657 | +| entropy_loss | -5.42 | +| explained_variance | 0.311 | +| learning_rate | 4.11e-05 | +| loss | -0.023 | +| n_updates | 88640 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000212 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1390 | +| iterations | 18207 | +| time_elapsed | 26818 | +| total_timesteps | 37287936 | +| train/ | | +| approx_kl | 0.012336222 | +| clip_fraction | 0.354 | +| clip_range | 0.0657 | +| entropy_loss | -5.16 | +| explained_variance | 0.592 | +| learning_rate | 4.11e-05 | +| loss | -0.0315 | +| n_updates | 88644 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000155 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1390 | +| iterations | 18208 | +| time_elapsed | 26820 | +| total_timesteps | 37289984 | +| train/ | | +| approx_kl | 0.012421459 | +| clip_fraction | 0.345 | +| clip_range | 0.0657 | +| entropy_loss | -5.42 | +| explained_variance | 0.539 | +| learning_rate | 4.11e-05 | +| loss | -0.0269 | +| n_updates | 88648 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000227 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1390 | +| iterations | 18209 | +| time_elapsed | 26821 | +| total_timesteps | 37292032 | +| train/ | | +| approx_kl | 0.013999129 | +| clip_fraction | 0.361 | +| clip_range | 0.0657 | +| entropy_loss | -6.19 | +| explained_variance | -0.0553 | +| learning_rate | 4.11e-05 | +| loss | -0.0318 | +| n_updates | 88652 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000163 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1390 | +| iterations | 18210 | +| time_elapsed | 26823 | +| total_timesteps | 37294080 | +| train/ | | +| approx_kl | 0.010809811 | +| clip_fraction | 0.337 | +| clip_range | 0.0657 | +| entropy_loss | -6.2 | +| explained_variance | 0.27 | +| learning_rate | 4.11e-05 | +| loss | -0.0354 | +| n_updates | 88656 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000139 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1390 | +| iterations | 18211 | +| time_elapsed | 26824 | +| total_timesteps | 37296128 | +| train/ | | +| approx_kl | 0.015443696 | +| clip_fraction | 0.368 | +| clip_range | 0.0657 | +| entropy_loss | -5.62 | +| explained_variance | 0.565 | +| learning_rate | 4.11e-05 | +| loss | -0.0316 | +| n_updates | 88660 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000104 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1390 | +| iterations | 18212 | +| time_elapsed | 26826 | +| total_timesteps | 37298176 | +| train/ | | +| approx_kl | 0.016529515 | +| clip_fraction | 0.348 | +| clip_range | 0.0657 | +| entropy_loss | -6.11 | +| explained_variance | 0.000213 | +| learning_rate | 4.11e-05 | +| loss | -0.0291 | +| n_updates | 88664 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000205 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1390 | +| iterations | 18213 | +| time_elapsed | 26827 | +| total_timesteps | 37300224 | +| train/ | | +| approx_kl | 0.0177771 | +| clip_fraction | 0.34 | +| clip_range | 0.0657 | +| entropy_loss | -5.55 | +| explained_variance | 0.494 | +| learning_rate | 4.11e-05 | +| loss | -0.0214 | +| n_updates | 88668 | +| policy_gradient_loss | -0.014 | +| value_loss | 0.000236 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1390 | +| iterations | 18214 | +| time_elapsed | 26829 | +| total_timesteps | 37302272 | +| train/ | | +| approx_kl | 0.016269011 | +| clip_fraction | 0.377 | +| clip_range | 0.0657 | +| entropy_loss | -5.06 | +| explained_variance | 0.365 | +| learning_rate | 4.11e-05 | +| loss | -0.0322 | +| n_updates | 88672 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.00021 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1390 | +| iterations | 18215 | +| time_elapsed | 26830 | +| total_timesteps | 37304320 | +| train/ | | +| approx_kl | 0.015687887 | +| clip_fraction | 0.365 | +| clip_range | 0.0657 | +| entropy_loss | -6.02 | +| explained_variance | -0.0774 | +| learning_rate | 4.11e-05 | +| loss | -0.0334 | +| n_updates | 88676 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000261 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1390 | +| iterations | 18216 | +| time_elapsed | 26832 | +| total_timesteps | 37306368 | +| train/ | | +| approx_kl | 0.012813181 | +| clip_fraction | 0.338 | +| clip_range | 0.0657 | +| entropy_loss | -5.43 | +| explained_variance | 0.396 | +| learning_rate | 4.11e-05 | +| loss | -0.028 | +| n_updates | 88680 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000272 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1390 | +| iterations | 18217 | +| time_elapsed | 26833 | +| total_timesteps | 37308416 | +| train/ | | +| approx_kl | 0.01339603 | +| clip_fraction | 0.338 | +| clip_range | 0.0657 | +| entropy_loss | -5.51 | +| explained_variance | 0.597 | +| learning_rate | 4.11e-05 | +| loss | -0.0226 | +| n_updates | 88684 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000153 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1390 | +| iterations | 18218 | +| time_elapsed | 26835 | +| total_timesteps | 37310464 | +| train/ | | +| approx_kl | 0.015008682 | +| clip_fraction | 0.381 | +| clip_range | 0.0657 | +| entropy_loss | -5.63 | +| explained_variance | 0.605 | +| learning_rate | 4.11e-05 | +| loss | -0.0299 | +| n_updates | 88688 | +| policy_gradient_loss | -0.0208 | +| value_loss | 8.2e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1390 | +| iterations | 18219 | +| time_elapsed | 26836 | +| total_timesteps | 37312512 | +| train/ | | +| approx_kl | 0.014287538 | +| clip_fraction | 0.361 | +| clip_range | 0.0657 | +| entropy_loss | -6.39 | +| explained_variance | -0.622 | +| learning_rate | 4.11e-05 | +| loss | -0.0344 | +| n_updates | 88692 | +| policy_gradient_loss | -0.021 | +| value_loss | 5.01e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1390 | +| iterations | 18220 | +| time_elapsed | 26838 | +| total_timesteps | 37314560 | +| train/ | | +| approx_kl | 0.010644209 | +| clip_fraction | 0.339 | +| clip_range | 0.0657 | +| entropy_loss | -6.55 | +| explained_variance | 0.022 | +| learning_rate | 4.11e-05 | +| loss | -0.031 | +| n_updates | 88696 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1390 | +| iterations | 18221 | +| time_elapsed | 26840 | +| total_timesteps | 37316608 | +| train/ | | +| approx_kl | 0.011355918 | +| clip_fraction | 0.319 | +| clip_range | 0.0657 | +| entropy_loss | -6.01 | +| explained_variance | 0.423 | +| learning_rate | 4.11e-05 | +| loss | -0.026 | +| n_updates | 88700 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.0002 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1390 | +| iterations | 18222 | +| time_elapsed | 26841 | +| total_timesteps | 37318656 | +| train/ | | +| approx_kl | 0.013383012 | +| clip_fraction | 0.311 | +| clip_range | 0.0657 | +| entropy_loss | -5.84 | +| explained_variance | 0.403 | +| learning_rate | 4.11e-05 | +| loss | -0.0265 | +| n_updates | 88704 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000205 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1390 | +| iterations | 18223 | +| time_elapsed | 26843 | +| total_timesteps | 37320704 | +| train/ | | +| approx_kl | 0.013180772 | +| clip_fraction | 0.325 | +| clip_range | 0.0657 | +| entropy_loss | -5.1 | +| explained_variance | 0.489 | +| learning_rate | 4.11e-05 | +| loss | -0.0219 | +| n_updates | 88708 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.00037 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1390 | +| iterations | 18224 | +| time_elapsed | 26844 | +| total_timesteps | 37322752 | +| train/ | | +| approx_kl | 0.014446293 | +| clip_fraction | 0.331 | +| clip_range | 0.0657 | +| entropy_loss | -4.96 | +| explained_variance | 0.492 | +| learning_rate | 4.11e-05 | +| loss | -0.0288 | +| n_updates | 88712 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000156 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1390 | +| iterations | 18225 | +| time_elapsed | 26846 | +| total_timesteps | 37324800 | +| train/ | | +| approx_kl | 0.011176944 | +| clip_fraction | 0.334 | +| clip_range | 0.0657 | +| entropy_loss | -6.25 | +| explained_variance | 0.289 | +| learning_rate | 4.11e-05 | +| loss | -0.0295 | +| n_updates | 88716 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000177 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1390 | +| iterations | 18226 | +| time_elapsed | 26847 | +| total_timesteps | 37326848 | +| train/ | | +| approx_kl | 0.014473853 | +| clip_fraction | 0.337 | +| clip_range | 0.0657 | +| entropy_loss | -6.08 | +| explained_variance | 0.31 | +| learning_rate | 4.11e-05 | +| loss | -0.0276 | +| n_updates | 88720 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.00018 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1390 | +| iterations | 18227 | +| time_elapsed | 26849 | +| total_timesteps | 37328896 | +| train/ | | +| approx_kl | 0.012292268 | +| clip_fraction | 0.344 | +| clip_range | 0.0657 | +| entropy_loss | -6.48 | +| explained_variance | -0.174 | +| learning_rate | 4.11e-05 | +| loss | -0.0334 | +| n_updates | 88724 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000158 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1390 | +| iterations | 18228 | +| time_elapsed | 26850 | +| total_timesteps | 37330944 | +| train/ | | +| approx_kl | 0.011265799 | +| clip_fraction | 0.326 | +| clip_range | 0.0657 | +| entropy_loss | -6.05 | +| explained_variance | 0.377 | +| learning_rate | 4.11e-05 | +| loss | -0.0294 | +| n_updates | 88728 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000335 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1390 | +| iterations | 18229 | +| time_elapsed | 26852 | +| total_timesteps | 37332992 | +| train/ | | +| approx_kl | 0.013074652 | +| clip_fraction | 0.352 | +| clip_range | 0.0657 | +| entropy_loss | -5.41 | +| explained_variance | 0.246 | +| learning_rate | 4.11e-05 | +| loss | -0.0272 | +| n_updates | 88732 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000207 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1390 | +| iterations | 18230 | +| time_elapsed | 26853 | +| total_timesteps | 37335040 | +| train/ | | +| approx_kl | 0.012507876 | +| clip_fraction | 0.342 | +| clip_range | 0.0657 | +| entropy_loss | -5.81 | +| explained_variance | 0.41 | +| learning_rate | 4.11e-05 | +| loss | -0.028 | +| n_updates | 88736 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000152 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1390 | +| iterations | 18231 | +| time_elapsed | 26855 | +| total_timesteps | 37337088 | +| train/ | | +| approx_kl | 0.011525461 | +| clip_fraction | 0.332 | +| clip_range | 0.0657 | +| entropy_loss | -5.55 | +| explained_variance | 0.247 | +| learning_rate | 4.11e-05 | +| loss | -0.0264 | +| n_updates | 88740 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000217 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1390 | +| iterations | 18232 | +| time_elapsed | 26856 | +| total_timesteps | 37339136 | +| train/ | | +| approx_kl | 0.01428654 | +| clip_fraction | 0.378 | +| clip_range | 0.0657 | +| entropy_loss | -5.72 | +| explained_variance | 0.519 | +| learning_rate | 4.11e-05 | +| loss | -0.0312 | +| n_updates | 88744 | +| policy_gradient_loss | -0.0199 | +| value_loss | 5.33e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1390 | +| iterations | 18233 | +| time_elapsed | 26858 | +| total_timesteps | 37341184 | +| train/ | | +| approx_kl | 0.015005076 | +| clip_fraction | 0.378 | +| clip_range | 0.0657 | +| entropy_loss | -6.17 | +| explained_variance | 0.476 | +| learning_rate | 4.11e-05 | +| loss | -0.031 | +| n_updates | 88748 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000123 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1390 | +| iterations | 18234 | +| time_elapsed | 26859 | +| total_timesteps | 37343232 | +| train/ | | +| approx_kl | 0.011979114 | +| clip_fraction | 0.333 | +| clip_range | 0.0657 | +| entropy_loss | -5.21 | +| explained_variance | 0.782 | +| learning_rate | 4.11e-05 | +| loss | -0.023 | +| n_updates | 88752 | +| policy_gradient_loss | -0.0161 | +| value_loss | 8.53e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1390 | +| iterations | 18235 | +| time_elapsed | 26861 | +| total_timesteps | 37345280 | +| train/ | | +| approx_kl | 0.014033094 | +| clip_fraction | 0.33 | +| clip_range | 0.0657 | +| entropy_loss | -5.56 | +| explained_variance | 0.465 | +| learning_rate | 4.11e-05 | +| loss | -0.0284 | +| n_updates | 88756 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000108 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1390 | +| iterations | 18236 | +| time_elapsed | 26863 | +| total_timesteps | 37347328 | +| train/ | | +| approx_kl | 0.011220547 | +| clip_fraction | 0.338 | +| clip_range | 0.0657 | +| entropy_loss | -6.04 | +| explained_variance | 0.546 | +| learning_rate | 4.11e-05 | +| loss | -0.0283 | +| n_updates | 88760 | +| policy_gradient_loss | -0.0182 | +| value_loss | 9.53e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1390 | +| iterations | 18237 | +| time_elapsed | 26864 | +| total_timesteps | 37349376 | +| train/ | | +| approx_kl | 0.011886802 | +| clip_fraction | 0.309 | +| clip_range | 0.0657 | +| entropy_loss | -6.06 | +| explained_variance | 0.459 | +| learning_rate | 4.11e-05 | +| loss | -0.0231 | +| n_updates | 88764 | +| policy_gradient_loss | -0.0146 | +| value_loss | 0.000196 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1390 | +| iterations | 18238 | +| time_elapsed | 26866 | +| total_timesteps | 37351424 | +| train/ | | +| approx_kl | 0.012853947 | +| clip_fraction | 0.314 | +| clip_range | 0.0657 | +| entropy_loss | -5.59 | +| explained_variance | 0.25 | +| learning_rate | 4.11e-05 | +| loss | -0.0273 | +| n_updates | 88768 | +| policy_gradient_loss | -0.0145 | +| value_loss | 0.000219 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1390 | +| iterations | 18239 | +| time_elapsed | 26867 | +| total_timesteps | 37353472 | +| train/ | | +| approx_kl | 0.012145892 | +| clip_fraction | 0.349 | +| clip_range | 0.0657 | +| entropy_loss | -6.01 | +| explained_variance | 0.286 | +| learning_rate | 4.11e-05 | +| loss | -0.0246 | +| n_updates | 88772 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000181 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1390 | +| iterations | 18240 | +| time_elapsed | 26869 | +| total_timesteps | 37355520 | +| train/ | | +| approx_kl | 0.014510505 | +| clip_fraction | 0.353 | +| clip_range | 0.0657 | +| entropy_loss | -6.17 | +| explained_variance | 0.247 | +| learning_rate | 4.11e-05 | +| loss | -0.0304 | +| n_updates | 88776 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000136 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1390 | +| iterations | 18241 | +| time_elapsed | 26870 | +| total_timesteps | 37357568 | +| train/ | | +| approx_kl | 0.012230836 | +| clip_fraction | 0.342 | +| clip_range | 0.0657 | +| entropy_loss | -5.89 | +| explained_variance | 0.204 | +| learning_rate | 4.11e-05 | +| loss | -0.0276 | +| n_updates | 88780 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000128 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1390 | +| iterations | 18242 | +| time_elapsed | 26872 | +| total_timesteps | 37359616 | +| train/ | | +| approx_kl | 0.013866723 | +| clip_fraction | 0.339 | +| clip_range | 0.0657 | +| entropy_loss | -5.23 | +| explained_variance | 0.383 | +| learning_rate | 4.11e-05 | +| loss | -0.0224 | +| n_updates | 88784 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000215 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.386 | +| time/ | | +| fps | 1390 | +| iterations | 18243 | +| time_elapsed | 26873 | +| total_timesteps | 37361664 | +| train/ | | +| approx_kl | 0.011961594 | +| clip_fraction | 0.343 | +| clip_range | 0.0657 | +| entropy_loss | -5.42 | +| explained_variance | 0.51 | +| learning_rate | 4.11e-05 | +| loss | -0.0218 | +| n_updates | 88788 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000154 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.384 | +| time/ | | +| fps | 1390 | +| iterations | 18244 | +| time_elapsed | 26875 | +| total_timesteps | 37363712 | +| train/ | | +| approx_kl | 0.014685513 | +| clip_fraction | 0.288 | +| clip_range | 0.0657 | +| entropy_loss | -4.74 | +| explained_variance | 0.521 | +| learning_rate | 4.11e-05 | +| loss | -0.0206 | +| n_updates | 88792 | +| policy_gradient_loss | -0.0139 | +| value_loss | 0.00042 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.384 | +| time/ | | +| fps | 1390 | +| iterations | 18245 | +| time_elapsed | 26876 | +| total_timesteps | 37365760 | +| train/ | | +| approx_kl | 0.010952052 | +| clip_fraction | 0.349 | +| clip_range | 0.0657 | +| entropy_loss | -5.1 | +| explained_variance | 0.529 | +| learning_rate | 4.11e-05 | +| loss | -0.026 | +| n_updates | 88796 | +| policy_gradient_loss | -0.0187 | +| value_loss | 9.5e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.385 | +| time/ | | +| fps | 1390 | +| iterations | 18246 | +| time_elapsed | 26878 | +| total_timesteps | 37367808 | +| train/ | | +| approx_kl | 0.014307855 | +| clip_fraction | 0.333 | +| clip_range | 0.0657 | +| entropy_loss | -6.06 | +| explained_variance | 0.193 | +| learning_rate | 4.11e-05 | +| loss | -0.0255 | +| n_updates | 88800 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000171 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.386 | +| time/ | | +| fps | 1390 | +| iterations | 18247 | +| time_elapsed | 26880 | +| total_timesteps | 37369856 | +| train/ | | +| approx_kl | 0.014243754 | +| clip_fraction | 0.337 | +| clip_range | 0.0657 | +| entropy_loss | -6.12 | +| explained_variance | 0.386 | +| learning_rate | 4.11e-05 | +| loss | -0.0264 | +| n_updates | 88804 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000111 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.387 | +| time/ | | +| fps | 1390 | +| iterations | 18248 | +| time_elapsed | 26881 | +| total_timesteps | 37371904 | +| train/ | | +| approx_kl | 0.013342664 | +| clip_fraction | 0.352 | +| clip_range | 0.0657 | +| entropy_loss | -6.21 | +| explained_variance | 0.199 | +| learning_rate | 4.11e-05 | +| loss | -0.0334 | +| n_updates | 88808 | +| policy_gradient_loss | -0.0191 | +| value_loss | 7.34e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.387 | +| time/ | | +| fps | 1390 | +| iterations | 18249 | +| time_elapsed | 26883 | +| total_timesteps | 37373952 | +| train/ | | +| approx_kl | 0.012370996 | +| clip_fraction | 0.328 | +| clip_range | 0.0657 | +| entropy_loss | -5.54 | +| explained_variance | 0.482 | +| learning_rate | 4.11e-05 | +| loss | -0.0275 | +| n_updates | 88812 | +| policy_gradient_loss | -0.014 | +| value_loss | 0.000223 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1390 | +| iterations | 18250 | +| time_elapsed | 26884 | +| total_timesteps | 37376000 | +| train/ | | +| approx_kl | 0.011689301 | +| clip_fraction | 0.334 | +| clip_range | 0.0657 | +| entropy_loss | -5.72 | +| explained_variance | 0.288 | +| learning_rate | 4.11e-05 | +| loss | -0.0295 | +| n_updates | 88816 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000149 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1390 | +| iterations | 18251 | +| time_elapsed | 26886 | +| total_timesteps | 37378048 | +| train/ | | +| approx_kl | 0.014037755 | +| clip_fraction | 0.357 | +| clip_range | 0.0657 | +| entropy_loss | -5.97 | +| explained_variance | 0.105 | +| learning_rate | 4.11e-05 | +| loss | -0.0284 | +| n_updates | 88820 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1390 | +| iterations | 18252 | +| time_elapsed | 26887 | +| total_timesteps | 37380096 | +| train/ | | +| approx_kl | 0.010103278 | +| clip_fraction | 0.288 | +| clip_range | 0.0657 | +| entropy_loss | -5.41 | +| explained_variance | 0.618 | +| learning_rate | 4.11e-05 | +| loss | -0.02 | +| n_updates | 88824 | +| policy_gradient_loss | -0.0148 | +| value_loss | 0.00023 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1390 | +| iterations | 18253 | +| time_elapsed | 26889 | +| total_timesteps | 37382144 | +| train/ | | +| approx_kl | 0.0100410925 | +| clip_fraction | 0.326 | +| clip_range | 0.0657 | +| entropy_loss | -4.98 | +| explained_variance | 0.759 | +| learning_rate | 4.11e-05 | +| loss | -0.0233 | +| n_updates | 88828 | +| policy_gradient_loss | -0.0174 | +| value_loss | 9.81e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1390 | +| iterations | 18254 | +| time_elapsed | 26890 | +| total_timesteps | 37384192 | +| train/ | | +| approx_kl | 0.011343114 | +| clip_fraction | 0.327 | +| clip_range | 0.0657 | +| entropy_loss | -5.95 | +| explained_variance | 0.224 | +| learning_rate | 4.11e-05 | +| loss | -0.023 | +| n_updates | 88832 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000146 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1390 | +| iterations | 18255 | +| time_elapsed | 26892 | +| total_timesteps | 37386240 | +| train/ | | +| approx_kl | 0.013790316 | +| clip_fraction | 0.34 | +| clip_range | 0.0657 | +| entropy_loss | -5.99 | +| explained_variance | 0.303 | +| learning_rate | 4.11e-05 | +| loss | -0.03 | +| n_updates | 88836 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000181 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1390 | +| iterations | 18256 | +| time_elapsed | 26893 | +| total_timesteps | 37388288 | +| train/ | | +| approx_kl | 0.017904866 | +| clip_fraction | 0.387 | +| clip_range | 0.0657 | +| entropy_loss | -6.04 | +| explained_variance | -0.233 | +| learning_rate | 4.11e-05 | +| loss | -0.0433 | +| n_updates | 88840 | +| policy_gradient_loss | -0.0228 | +| value_loss | 4.99e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1390 | +| iterations | 18257 | +| time_elapsed | 26895 | +| total_timesteps | 37390336 | +| train/ | | +| approx_kl | 0.012603782 | +| clip_fraction | 0.345 | +| clip_range | 0.0657 | +| entropy_loss | -6.62 | +| explained_variance | 0.175 | +| learning_rate | 4.11e-05 | +| loss | -0.0251 | +| n_updates | 88844 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000306 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1390 | +| iterations | 18258 | +| time_elapsed | 26896 | +| total_timesteps | 37392384 | +| train/ | | +| approx_kl | 0.011518274 | +| clip_fraction | 0.348 | +| clip_range | 0.0657 | +| entropy_loss | -5.78 | +| explained_variance | 0.701 | +| learning_rate | 4.11e-05 | +| loss | -0.0299 | +| n_updates | 88848 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000107 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1390 | +| iterations | 18259 | +| time_elapsed | 26898 | +| total_timesteps | 37394432 | +| train/ | | +| approx_kl | 0.014304809 | +| clip_fraction | 0.347 | +| clip_range | 0.0657 | +| entropy_loss | -5.48 | +| explained_variance | 0.469 | +| learning_rate | 4.11e-05 | +| loss | -0.0233 | +| n_updates | 88852 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000113 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1390 | +| iterations | 18260 | +| time_elapsed | 26899 | +| total_timesteps | 37396480 | +| train/ | | +| approx_kl | 0.014741267 | +| clip_fraction | 0.317 | +| clip_range | 0.0657 | +| entropy_loss | -5.18 | +| explained_variance | 0.643 | +| learning_rate | 4.11e-05 | +| loss | -0.0214 | +| n_updates | 88856 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000177 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1390 | +| iterations | 18261 | +| time_elapsed | 26901 | +| total_timesteps | 37398528 | +| train/ | | +| approx_kl | 0.013130596 | +| clip_fraction | 0.303 | +| clip_range | 0.0657 | +| entropy_loss | -5.67 | +| explained_variance | 0.405 | +| learning_rate | 4.11e-05 | +| loss | -0.0271 | +| n_updates | 88860 | +| policy_gradient_loss | -0.0176 | +| value_loss | 7.34e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1390 | +| iterations | 18262 | +| time_elapsed | 26902 | +| total_timesteps | 37400576 | +| train/ | | +| approx_kl | 0.013259817 | +| clip_fraction | 0.35 | +| clip_range | 0.0657 | +| entropy_loss | -5.77 | +| explained_variance | 0.451 | +| learning_rate | 4.11e-05 | +| loss | -0.0283 | +| n_updates | 88864 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000115 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1390 | +| iterations | 18263 | +| time_elapsed | 26904 | +| total_timesteps | 37402624 | +| train/ | | +| approx_kl | 0.012800571 | +| clip_fraction | 0.316 | +| clip_range | 0.0656 | +| entropy_loss | -6.66 | +| explained_variance | 0.0258 | +| learning_rate | 4.11e-05 | +| loss | -0.0236 | +| n_updates | 88868 | +| policy_gradient_loss | -0.0137 | +| value_loss | 0.000179 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1390 | +| iterations | 18264 | +| time_elapsed | 26906 | +| total_timesteps | 37404672 | +| train/ | | +| approx_kl | 0.014405807 | +| clip_fraction | 0.335 | +| clip_range | 0.0656 | +| entropy_loss | -5.56 | +| explained_variance | 0.607 | +| learning_rate | 4.11e-05 | +| loss | -0.0294 | +| n_updates | 88872 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000117 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1390 | +| iterations | 18265 | +| time_elapsed | 26907 | +| total_timesteps | 37406720 | +| train/ | | +| approx_kl | 0.013315575 | +| clip_fraction | 0.328 | +| clip_range | 0.0656 | +| entropy_loss | -5.64 | +| explained_variance | 0.562 | +| learning_rate | 4.11e-05 | +| loss | -0.0283 | +| n_updates | 88876 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000116 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1390 | +| iterations | 18266 | +| time_elapsed | 26909 | +| total_timesteps | 37408768 | +| train/ | | +| approx_kl | 0.015298276 | +| clip_fraction | 0.353 | +| clip_range | 0.0656 | +| entropy_loss | -5.85 | +| explained_variance | 0.00532 | +| learning_rate | 4.11e-05 | +| loss | -0.0235 | +| n_updates | 88880 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000282 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1390 | +| iterations | 18267 | +| time_elapsed | 26910 | +| total_timesteps | 37410816 | +| train/ | | +| approx_kl | 0.011610595 | +| clip_fraction | 0.324 | +| clip_range | 0.0656 | +| entropy_loss | -5.82 | +| explained_variance | 0.462 | +| learning_rate | 4.11e-05 | +| loss | -0.0339 | +| n_updates | 88884 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000225 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1390 | +| iterations | 18268 | +| time_elapsed | 26912 | +| total_timesteps | 37412864 | +| train/ | | +| approx_kl | 0.012769249 | +| clip_fraction | 0.338 | +| clip_range | 0.0656 | +| entropy_loss | -5.37 | +| explained_variance | 0.559 | +| learning_rate | 4.11e-05 | +| loss | -0.0305 | +| n_updates | 88888 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.00013 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1390 | +| iterations | 18269 | +| time_elapsed | 26914 | +| total_timesteps | 37414912 | +| train/ | | +| approx_kl | 0.012126217 | +| clip_fraction | 0.344 | +| clip_range | 0.0656 | +| entropy_loss | -5.76 | +| explained_variance | 0.38 | +| learning_rate | 4.11e-05 | +| loss | -0.0263 | +| n_updates | 88892 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000145 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1390 | +| iterations | 18270 | +| time_elapsed | 26915 | +| total_timesteps | 37416960 | +| train/ | | +| approx_kl | 0.015467481 | +| clip_fraction | 0.354 | +| clip_range | 0.0656 | +| entropy_loss | -5.94 | +| explained_variance | 0.216 | +| learning_rate | 4.11e-05 | +| loss | -0.0264 | +| n_updates | 88896 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000245 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1390 | +| iterations | 18271 | +| time_elapsed | 26917 | +| total_timesteps | 37419008 | +| train/ | | +| approx_kl | 0.0154296225 | +| clip_fraction | 0.376 | +| clip_range | 0.0656 | +| entropy_loss | -5.65 | +| explained_variance | 0.315 | +| learning_rate | 4.11e-05 | +| loss | -0.0289 | +| n_updates | 88900 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000105 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1390 | +| iterations | 18272 | +| time_elapsed | 26918 | +| total_timesteps | 37421056 | +| train/ | | +| approx_kl | 0.014302544 | +| clip_fraction | 0.36 | +| clip_range | 0.0656 | +| entropy_loss | -6.11 | +| explained_variance | -0.0252 | +| learning_rate | 4.11e-05 | +| loss | -0.0217 | +| n_updates | 88904 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000203 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1390 | +| iterations | 18273 | +| time_elapsed | 26920 | +| total_timesteps | 37423104 | +| train/ | | +| approx_kl | 0.012047456 | +| clip_fraction | 0.327 | +| clip_range | 0.0656 | +| entropy_loss | -5.28 | +| explained_variance | 0.555 | +| learning_rate | 4.11e-05 | +| loss | -0.0217 | +| n_updates | 88908 | +| policy_gradient_loss | -0.0144 | +| value_loss | 0.000155 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1390 | +| iterations | 18274 | +| time_elapsed | 26921 | +| total_timesteps | 37425152 | +| train/ | | +| approx_kl | 0.015502462 | +| clip_fraction | 0.337 | +| clip_range | 0.0656 | +| entropy_loss | -5.18 | +| explained_variance | 0.18 | +| learning_rate | 4.11e-05 | +| loss | -0.0285 | +| n_updates | 88912 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000127 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1390 | +| iterations | 18275 | +| time_elapsed | 26923 | +| total_timesteps | 37427200 | +| train/ | | +| approx_kl | 0.01332311 | +| clip_fraction | 0.34 | +| clip_range | 0.0656 | +| entropy_loss | -6.08 | +| explained_variance | 0.23 | +| learning_rate | 4.11e-05 | +| loss | -0.0267 | +| n_updates | 88916 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000159 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1390 | +| iterations | 18276 | +| time_elapsed | 26924 | +| total_timesteps | 37429248 | +| train/ | | +| approx_kl | 0.014376157 | +| clip_fraction | 0.312 | +| clip_range | 0.0656 | +| entropy_loss | -5.79 | +| explained_variance | 0.485 | +| learning_rate | 4.11e-05 | +| loss | -0.0254 | +| n_updates | 88920 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000136 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1390 | +| iterations | 18277 | +| time_elapsed | 26926 | +| total_timesteps | 37431296 | +| train/ | | +| approx_kl | 0.013470076 | +| clip_fraction | 0.318 | +| clip_range | 0.0656 | +| entropy_loss | -5.71 | +| explained_variance | 0.273 | +| learning_rate | 4.11e-05 | +| loss | -0.0243 | +| n_updates | 88924 | +| policy_gradient_loss | -0.0143 | +| value_loss | 0.000367 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1390 | +| iterations | 18278 | +| time_elapsed | 26927 | +| total_timesteps | 37433344 | +| train/ | | +| approx_kl | 0.0112600615 | +| clip_fraction | 0.292 | +| clip_range | 0.0656 | +| entropy_loss | -6.01 | +| explained_variance | 0.467 | +| learning_rate | 4.11e-05 | +| loss | -0.0253 | +| n_updates | 88928 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000175 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1390 | +| iterations | 18279 | +| time_elapsed | 26929 | +| total_timesteps | 37435392 | +| train/ | | +| approx_kl | 0.008731129 | +| clip_fraction | 0.311 | +| clip_range | 0.0656 | +| entropy_loss | -5.73 | +| explained_variance | 0.307 | +| learning_rate | 4.11e-05 | +| loss | -0.0263 | +| n_updates | 88932 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.00038 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1390 | +| iterations | 18280 | +| time_elapsed | 26930 | +| total_timesteps | 37437440 | +| train/ | | +| approx_kl | 0.013378931 | +| clip_fraction | 0.335 | +| clip_range | 0.0656 | +| entropy_loss | -4.76 | +| explained_variance | 0.445 | +| learning_rate | 4.11e-05 | +| loss | -0.0236 | +| n_updates | 88936 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.000251 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1390 | +| iterations | 18281 | +| time_elapsed | 26932 | +| total_timesteps | 37439488 | +| train/ | | +| approx_kl | 0.014117714 | +| clip_fraction | 0.371 | +| clip_range | 0.0656 | +| entropy_loss | -4.82 | +| explained_variance | 0.602 | +| learning_rate | 4.11e-05 | +| loss | -0.0298 | +| n_updates | 88940 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000133 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1390 | +| iterations | 18282 | +| time_elapsed | 26933 | +| total_timesteps | 37441536 | +| train/ | | +| approx_kl | 0.015346077 | +| clip_fraction | 0.374 | +| clip_range | 0.0656 | +| entropy_loss | -5.5 | +| explained_variance | 0.505 | +| learning_rate | 4.11e-05 | +| loss | -0.0345 | +| n_updates | 88944 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000114 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1390 | +| iterations | 18283 | +| time_elapsed | 26935 | +| total_timesteps | 37443584 | +| train/ | | +| approx_kl | 0.011911747 | +| clip_fraction | 0.367 | +| clip_range | 0.0656 | +| entropy_loss | -5.95 | +| explained_variance | 0.341 | +| learning_rate | 4.11e-05 | +| loss | -0.0349 | +| n_updates | 88948 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000162 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1390 | +| iterations | 18284 | +| time_elapsed | 26936 | +| total_timesteps | 37445632 | +| train/ | | +| approx_kl | 0.013684183 | +| clip_fraction | 0.348 | +| clip_range | 0.0656 | +| entropy_loss | -6.01 | +| explained_variance | 0.449 | +| learning_rate | 4.11e-05 | +| loss | -0.0287 | +| n_updates | 88952 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000149 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1390 | +| iterations | 18285 | +| time_elapsed | 26938 | +| total_timesteps | 37447680 | +| train/ | | +| approx_kl | 0.011786006 | +| clip_fraction | 0.309 | +| clip_range | 0.0656 | +| entropy_loss | -5.63 | +| explained_variance | 0.282 | +| learning_rate | 4.11e-05 | +| loss | -0.0258 | +| n_updates | 88956 | +| policy_gradient_loss | -0.0143 | +| value_loss | 0.000216 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1390 | +| iterations | 18286 | +| time_elapsed | 26939 | +| total_timesteps | 37449728 | +| train/ | | +| approx_kl | 0.013760127 | +| clip_fraction | 0.37 | +| clip_range | 0.0656 | +| entropy_loss | -5.94 | +| explained_variance | -0.0192 | +| learning_rate | 4.11e-05 | +| loss | -0.0272 | +| n_updates | 88960 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.0001 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1390 | +| iterations | 18287 | +| time_elapsed | 26941 | +| total_timesteps | 37451776 | +| train/ | | +| approx_kl | 0.016015291 | +| clip_fraction | 0.373 | +| clip_range | 0.0656 | +| entropy_loss | -5.9 | +| explained_variance | -0.0404 | +| learning_rate | 4.11e-05 | +| loss | -0.0347 | +| n_updates | 88964 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000102 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1390 | +| iterations | 18288 | +| time_elapsed | 26942 | +| total_timesteps | 37453824 | +| train/ | | +| approx_kl | 0.014614139 | +| clip_fraction | 0.315 | +| clip_range | 0.0656 | +| entropy_loss | -5.36 | +| explained_variance | 0.301 | +| learning_rate | 4.11e-05 | +| loss | -0.0235 | +| n_updates | 88968 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000384 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1390 | +| iterations | 18289 | +| time_elapsed | 26944 | +| total_timesteps | 37455872 | +| train/ | | +| approx_kl | 0.012231559 | +| clip_fraction | 0.341 | +| clip_range | 0.0656 | +| entropy_loss | -5.78 | +| explained_variance | 0.0924 | +| learning_rate | 4.11e-05 | +| loss | -0.0275 | +| n_updates | 88972 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000217 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1390 | +| iterations | 18290 | +| time_elapsed | 26946 | +| total_timesteps | 37457920 | +| train/ | | +| approx_kl | 0.012688822 | +| clip_fraction | 0.342 | +| clip_range | 0.0656 | +| entropy_loss | -6.38 | +| explained_variance | 0.276 | +| learning_rate | 4.11e-05 | +| loss | -0.0314 | +| n_updates | 88976 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000157 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1390 | +| iterations | 18291 | +| time_elapsed | 26947 | +| total_timesteps | 37459968 | +| train/ | | +| approx_kl | 0.013967606 | +| clip_fraction | 0.334 | +| clip_range | 0.0656 | +| entropy_loss | -6.06 | +| explained_variance | 0.588 | +| learning_rate | 4.11e-05 | +| loss | -0.0315 | +| n_updates | 88980 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000134 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1390 | +| iterations | 18292 | +| time_elapsed | 26949 | +| total_timesteps | 37462016 | +| train/ | | +| approx_kl | 0.015536456 | +| clip_fraction | 0.371 | +| clip_range | 0.0656 | +| entropy_loss | -5.7 | +| explained_variance | 0.476 | +| learning_rate | 4.11e-05 | +| loss | -0.0382 | +| n_updates | 88984 | +| policy_gradient_loss | -0.0217 | +| value_loss | 6.33e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1390 | +| iterations | 18293 | +| time_elapsed | 26950 | +| total_timesteps | 37464064 | +| train/ | | +| approx_kl | 0.01616533 | +| clip_fraction | 0.363 | +| clip_range | 0.0656 | +| entropy_loss | -5.22 | +| explained_variance | 0.622 | +| learning_rate | 4.11e-05 | +| loss | -0.0293 | +| n_updates | 88988 | +| policy_gradient_loss | -0.0191 | +| value_loss | 9.34e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1390 | +| iterations | 18294 | +| time_elapsed | 26952 | +| total_timesteps | 37466112 | +| train/ | | +| approx_kl | 0.013667151 | +| clip_fraction | 0.359 | +| clip_range | 0.0656 | +| entropy_loss | -5.21 | +| explained_variance | 0.414 | +| learning_rate | 4.11e-05 | +| loss | -0.0216 | +| n_updates | 88992 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000238 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1390 | +| iterations | 18295 | +| time_elapsed | 26953 | +| total_timesteps | 37468160 | +| train/ | | +| approx_kl | 0.01649961 | +| clip_fraction | 0.374 | +| clip_range | 0.0656 | +| entropy_loss | -5.39 | +| explained_variance | 0.679 | +| learning_rate | 4.11e-05 | +| loss | -0.0258 | +| n_updates | 88996 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000125 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1390 | +| iterations | 18296 | +| time_elapsed | 26955 | +| total_timesteps | 37470208 | +| train/ | | +| approx_kl | 0.015646469 | +| clip_fraction | 0.337 | +| clip_range | 0.0656 | +| entropy_loss | -5.51 | +| explained_variance | 0.41 | +| learning_rate | 4.11e-05 | +| loss | -0.0294 | +| n_updates | 89000 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000152 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1390 | +| iterations | 18297 | +| time_elapsed | 26956 | +| total_timesteps | 37472256 | +| train/ | | +| approx_kl | 0.012690533 | +| clip_fraction | 0.365 | +| clip_range | 0.0656 | +| entropy_loss | -5.87 | +| explained_variance | 0.468 | +| learning_rate | 4.11e-05 | +| loss | -0.0329 | +| n_updates | 89004 | +| policy_gradient_loss | -0.0204 | +| value_loss | 8.81e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1390 | +| iterations | 18298 | +| time_elapsed | 26958 | +| total_timesteps | 37474304 | +| train/ | | +| approx_kl | 0.0118665695 | +| clip_fraction | 0.338 | +| clip_range | 0.0656 | +| entropy_loss | -5.97 | +| explained_variance | 0.3 | +| learning_rate | 4.11e-05 | +| loss | -0.0252 | +| n_updates | 89008 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000186 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1390 | +| iterations | 18299 | +| time_elapsed | 26959 | +| total_timesteps | 37476352 | +| train/ | | +| approx_kl | 0.015593384 | +| clip_fraction | 0.344 | +| clip_range | 0.0656 | +| entropy_loss | -5.4 | +| explained_variance | 0.341 | +| learning_rate | 4.11e-05 | +| loss | -0.0284 | +| n_updates | 89012 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000146 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1390 | +| iterations | 18300 | +| time_elapsed | 26961 | +| total_timesteps | 37478400 | +| train/ | | +| approx_kl | 0.013497254 | +| clip_fraction | 0.344 | +| clip_range | 0.0656 | +| entropy_loss | -5.75 | +| explained_variance | 0.404 | +| learning_rate | 4.11e-05 | +| loss | -0.0272 | +| n_updates | 89016 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000125 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1390 | +| iterations | 18301 | +| time_elapsed | 26962 | +| total_timesteps | 37480448 | +| train/ | | +| approx_kl | 0.012463099 | +| clip_fraction | 0.365 | +| clip_range | 0.0656 | +| entropy_loss | -6.01 | +| explained_variance | 0.335 | +| learning_rate | 4.11e-05 | +| loss | -0.0378 | +| n_updates | 89020 | +| policy_gradient_loss | -0.0193 | +| value_loss | 8.27e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1390 | +| iterations | 18302 | +| time_elapsed | 26964 | +| total_timesteps | 37482496 | +| train/ | | +| approx_kl | 0.015316449 | +| clip_fraction | 0.359 | +| clip_range | 0.0656 | +| entropy_loss | -5.96 | +| explained_variance | -0.159 | +| learning_rate | 4.11e-05 | +| loss | -0.0317 | +| n_updates | 89024 | +| policy_gradient_loss | -0.0194 | +| value_loss | 6.13e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1390 | +| iterations | 18303 | +| time_elapsed | 26966 | +| total_timesteps | 37484544 | +| train/ | | +| approx_kl | 0.015184607 | +| clip_fraction | 0.343 | +| clip_range | 0.0656 | +| entropy_loss | -5.02 | +| explained_variance | 0.525 | +| learning_rate | 4.11e-05 | +| loss | -0.0261 | +| n_updates | 89028 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.00031 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1390 | +| iterations | 18304 | +| time_elapsed | 26967 | +| total_timesteps | 37486592 | +| train/ | | +| approx_kl | 0.011419591 | +| clip_fraction | 0.308 | +| clip_range | 0.0656 | +| entropy_loss | -4.82 | +| explained_variance | 0.663 | +| learning_rate | 4.11e-05 | +| loss | -0.0297 | +| n_updates | 89032 | +| policy_gradient_loss | -0.0169 | +| value_loss | 9.2e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1390 | +| iterations | 18305 | +| time_elapsed | 26969 | +| total_timesteps | 37488640 | +| train/ | | +| approx_kl | 0.011726051 | +| clip_fraction | 0.325 | +| clip_range | 0.0656 | +| entropy_loss | -5.63 | +| explained_variance | 0.464 | +| learning_rate | 4.11e-05 | +| loss | -0.0234 | +| n_updates | 89036 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000149 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1390 | +| iterations | 18306 | +| time_elapsed | 26970 | +| total_timesteps | 37490688 | +| train/ | | +| approx_kl | 0.015016184 | +| clip_fraction | 0.327 | +| clip_range | 0.0656 | +| entropy_loss | -4.95 | +| explained_variance | 0.626 | +| learning_rate | 4.11e-05 | +| loss | -0.0249 | +| n_updates | 89040 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000134 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1390 | +| iterations | 18307 | +| time_elapsed | 26972 | +| total_timesteps | 37492736 | +| train/ | | +| approx_kl | 0.013698613 | +| clip_fraction | 0.34 | +| clip_range | 0.0656 | +| entropy_loss | -5.5 | +| explained_variance | 0.445 | +| learning_rate | 4.11e-05 | +| loss | -0.0286 | +| n_updates | 89044 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000136 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1390 | +| iterations | 18308 | +| time_elapsed | 26973 | +| total_timesteps | 37494784 | +| train/ | | +| approx_kl | 0.012959138 | +| clip_fraction | 0.338 | +| clip_range | 0.0656 | +| entropy_loss | -6.12 | +| explained_variance | 0.193 | +| learning_rate | 4.11e-05 | +| loss | -0.0275 | +| n_updates | 89048 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000181 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1390 | +| iterations | 18309 | +| time_elapsed | 26975 | +| total_timesteps | 37496832 | +| train/ | | +| approx_kl | 0.010663429 | +| clip_fraction | 0.323 | +| clip_range | 0.0656 | +| entropy_loss | -5.67 | +| explained_variance | 0.494 | +| learning_rate | 4.11e-05 | +| loss | -0.0268 | +| n_updates | 89052 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000204 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1390 | +| iterations | 18310 | +| time_elapsed | 26976 | +| total_timesteps | 37498880 | +| train/ | | +| approx_kl | 0.009477926 | +| clip_fraction | 0.345 | +| clip_range | 0.0656 | +| entropy_loss | -6.01 | +| explained_variance | 0.132 | +| learning_rate | 4.11e-05 | +| loss | -0.0264 | +| n_updates | 89056 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000211 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1390 | +| iterations | 18311 | +| time_elapsed | 26978 | +| total_timesteps | 37500928 | +| train/ | | +| approx_kl | 0.014020359 | +| clip_fraction | 0.336 | +| clip_range | 0.0656 | +| entropy_loss | -5.88 | +| explained_variance | 0.32 | +| learning_rate | 4.11e-05 | +| loss | -0.0293 | +| n_updates | 89060 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.00028 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1390 | +| iterations | 18312 | +| time_elapsed | 26979 | +| total_timesteps | 37502976 | +| train/ | | +| approx_kl | 0.0131338835 | +| clip_fraction | 0.337 | +| clip_range | 0.0656 | +| entropy_loss | -5.32 | +| explained_variance | 0.429 | +| learning_rate | 4.11e-05 | +| loss | -0.0185 | +| n_updates | 89064 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000208 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1390 | +| iterations | 18313 | +| time_elapsed | 26981 | +| total_timesteps | 37505024 | +| train/ | | +| approx_kl | 0.012833528 | +| clip_fraction | 0.334 | +| clip_range | 0.0656 | +| entropy_loss | -5.53 | +| explained_variance | 0.487 | +| learning_rate | 4.11e-05 | +| loss | -0.0223 | +| n_updates | 89068 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000181 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1390 | +| iterations | 18314 | +| time_elapsed | 26983 | +| total_timesteps | 37507072 | +| train/ | | +| approx_kl | 0.013017614 | +| clip_fraction | 0.337 | +| clip_range | 0.0656 | +| entropy_loss | -5.52 | +| explained_variance | 0.476 | +| learning_rate | 4.11e-05 | +| loss | -0.0271 | +| n_updates | 89072 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000151 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1390 | +| iterations | 18315 | +| time_elapsed | 26984 | +| total_timesteps | 37509120 | +| train/ | | +| approx_kl | 0.014231571 | +| clip_fraction | 0.351 | +| clip_range | 0.0656 | +| entropy_loss | -5.76 | +| explained_variance | 0.666 | +| learning_rate | 4.11e-05 | +| loss | -0.0301 | +| n_updates | 89076 | +| policy_gradient_loss | -0.0181 | +| value_loss | 9.52e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1390 | +| iterations | 18316 | +| time_elapsed | 26986 | +| total_timesteps | 37511168 | +| train/ | | +| approx_kl | 0.014608087 | +| clip_fraction | 0.362 | +| clip_range | 0.0656 | +| entropy_loss | -5.75 | +| explained_variance | 0.391 | +| learning_rate | 4.11e-05 | +| loss | -0.0261 | +| n_updates | 89080 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000126 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1390 | +| iterations | 18317 | +| time_elapsed | 26987 | +| total_timesteps | 37513216 | +| train/ | | +| approx_kl | 0.011209124 | +| clip_fraction | 0.326 | +| clip_range | 0.0656 | +| entropy_loss | -5.34 | +| explained_variance | 0.523 | +| learning_rate | 4.11e-05 | +| loss | -0.0235 | +| n_updates | 89084 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000245 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1390 | +| iterations | 18318 | +| time_elapsed | 26989 | +| total_timesteps | 37515264 | +| train/ | | +| approx_kl | 0.013291467 | +| clip_fraction | 0.34 | +| clip_range | 0.0656 | +| entropy_loss | -5.37 | +| explained_variance | 0.499 | +| learning_rate | 4.11e-05 | +| loss | -0.0323 | +| n_updates | 89088 | +| policy_gradient_loss | -0.0192 | +| value_loss | 9.99e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1390 | +| iterations | 18319 | +| time_elapsed | 26990 | +| total_timesteps | 37517312 | +| train/ | | +| approx_kl | 0.016075402 | +| clip_fraction | 0.313 | +| clip_range | 0.0656 | +| entropy_loss | -5.67 | +| explained_variance | 0.481 | +| learning_rate | 4.11e-05 | +| loss | -0.0279 | +| n_updates | 89092 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000157 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1390 | +| iterations | 18320 | +| time_elapsed | 26992 | +| total_timesteps | 37519360 | +| train/ | | +| approx_kl | 0.013413904 | +| clip_fraction | 0.333 | +| clip_range | 0.0656 | +| entropy_loss | -6.29 | +| explained_variance | 0.457 | +| learning_rate | 4.11e-05 | +| loss | -0.0302 | +| n_updates | 89096 | +| policy_gradient_loss | -0.0188 | +| value_loss | 7.93e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1390 | +| iterations | 18321 | +| time_elapsed | 26993 | +| total_timesteps | 37521408 | +| train/ | | +| approx_kl | 0.010416912 | +| clip_fraction | 0.309 | +| clip_range | 0.0656 | +| entropy_loss | -5.1 | +| explained_variance | 0.533 | +| learning_rate | 4.11e-05 | +| loss | -0.0223 | +| n_updates | 89100 | +| policy_gradient_loss | -0.0147 | +| value_loss | 0.000255 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1390 | +| iterations | 18322 | +| time_elapsed | 26995 | +| total_timesteps | 37523456 | +| train/ | | +| approx_kl | 0.011303406 | +| clip_fraction | 0.335 | +| clip_range | 0.0656 | +| entropy_loss | -5.91 | +| explained_variance | -0.0885 | +| learning_rate | 4.11e-05 | +| loss | -0.0335 | +| n_updates | 89104 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000103 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1390 | +| iterations | 18323 | +| time_elapsed | 26996 | +| total_timesteps | 37525504 | +| train/ | | +| approx_kl | 0.01341704 | +| clip_fraction | 0.333 | +| clip_range | 0.0656 | +| entropy_loss | -5.87 | +| explained_variance | 0.328 | +| learning_rate | 4.11e-05 | +| loss | -0.0276 | +| n_updates | 89108 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.00028 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1389 | +| iterations | 18324 | +| time_elapsed | 26998 | +| total_timesteps | 37527552 | +| train/ | | +| approx_kl | 0.01340281 | +| clip_fraction | 0.347 | +| clip_range | 0.0656 | +| entropy_loss | -6.04 | +| explained_variance | 0.13 | +| learning_rate | 4.11e-05 | +| loss | -0.0298 | +| n_updates | 89112 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000136 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1389 | +| iterations | 18325 | +| time_elapsed | 26999 | +| total_timesteps | 37529600 | +| train/ | | +| approx_kl | 0.011047455 | +| clip_fraction | 0.313 | +| clip_range | 0.0656 | +| entropy_loss | -5.71 | +| explained_variance | 0.434 | +| learning_rate | 4.11e-05 | +| loss | -0.025 | +| n_updates | 89116 | +| policy_gradient_loss | -0.0137 | +| value_loss | 0.000181 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1389 | +| iterations | 18326 | +| time_elapsed | 27001 | +| total_timesteps | 37531648 | +| train/ | | +| approx_kl | 0.014461863 | +| clip_fraction | 0.342 | +| clip_range | 0.0656 | +| entropy_loss | -5.72 | +| explained_variance | 0.701 | +| learning_rate | 4.11e-05 | +| loss | -0.0348 | +| n_updates | 89120 | +| policy_gradient_loss | -0.0211 | +| value_loss | 5.61e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1389 | +| iterations | 18327 | +| time_elapsed | 27002 | +| total_timesteps | 37533696 | +| train/ | | +| approx_kl | 0.013962065 | +| clip_fraction | 0.349 | +| clip_range | 0.0656 | +| entropy_loss | -5.41 | +| explained_variance | 0.673 | +| learning_rate | 4.11e-05 | +| loss | -0.0254 | +| n_updates | 89124 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000114 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1389 | +| iterations | 18328 | +| time_elapsed | 27004 | +| total_timesteps | 37535744 | +| train/ | | +| approx_kl | 0.015452511 | +| clip_fraction | 0.344 | +| clip_range | 0.0656 | +| entropy_loss | -5.92 | +| explained_variance | 0.31 | +| learning_rate | 4.11e-05 | +| loss | -0.0275 | +| n_updates | 89128 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000144 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1389 | +| iterations | 18329 | +| time_elapsed | 27005 | +| total_timesteps | 37537792 | +| train/ | | +| approx_kl | 0.017363194 | +| clip_fraction | 0.357 | +| clip_range | 0.0656 | +| entropy_loss | -6.25 | +| explained_variance | -0.144 | +| learning_rate | 4.11e-05 | +| loss | -0.0266 | +| n_updates | 89132 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000147 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1389 | +| iterations | 18330 | +| time_elapsed | 27007 | +| total_timesteps | 37539840 | +| train/ | | +| approx_kl | 0.013823574 | +| clip_fraction | 0.345 | +| clip_range | 0.0656 | +| entropy_loss | -5.85 | +| explained_variance | 0.417 | +| learning_rate | 4.11e-05 | +| loss | -0.0303 | +| n_updates | 89136 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000202 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1389 | +| iterations | 18331 | +| time_elapsed | 27008 | +| total_timesteps | 37541888 | +| train/ | | +| approx_kl | 0.012481797 | +| clip_fraction | 0.365 | +| clip_range | 0.0656 | +| entropy_loss | -5.16 | +| explained_variance | 0.695 | +| learning_rate | 4.11e-05 | +| loss | -0.0262 | +| n_updates | 89140 | +| policy_gradient_loss | -0.0183 | +| value_loss | 7.66e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1389 | +| iterations | 18332 | +| time_elapsed | 27010 | +| total_timesteps | 37543936 | +| train/ | | +| approx_kl | 0.011128487 | +| clip_fraction | 0.331 | +| clip_range | 0.0656 | +| entropy_loss | -5.73 | +| explained_variance | 0.233 | +| learning_rate | 4.11e-05 | +| loss | -0.0293 | +| n_updates | 89144 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000257 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1389 | +| iterations | 18333 | +| time_elapsed | 27012 | +| total_timesteps | 37545984 | +| train/ | | +| approx_kl | 0.013748102 | +| clip_fraction | 0.338 | +| clip_range | 0.0656 | +| entropy_loss | -5.65 | +| explained_variance | 0.385 | +| learning_rate | 4.11e-05 | +| loss | -0.0247 | +| n_updates | 89148 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000187 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1389 | +| iterations | 18334 | +| time_elapsed | 27013 | +| total_timesteps | 37548032 | +| train/ | | +| approx_kl | 0.01235774 | +| clip_fraction | 0.293 | +| clip_range | 0.0656 | +| entropy_loss | -5.44 | +| explained_variance | 0.428 | +| learning_rate | 4.11e-05 | +| loss | -0.0225 | +| n_updates | 89152 | +| policy_gradient_loss | -0.0134 | +| value_loss | 0.000327 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1389 | +| iterations | 18335 | +| time_elapsed | 27015 | +| total_timesteps | 37550080 | +| train/ | | +| approx_kl | 0.01524224 | +| clip_fraction | 0.341 | +| clip_range | 0.0656 | +| entropy_loss | -5.64 | +| explained_variance | 0.315 | +| learning_rate | 4.11e-05 | +| loss | -0.032 | +| n_updates | 89156 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000148 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1389 | +| iterations | 18336 | +| time_elapsed | 27016 | +| total_timesteps | 37552128 | +| train/ | | +| approx_kl | 0.01389936 | +| clip_fraction | 0.364 | +| clip_range | 0.0656 | +| entropy_loss | -5.76 | +| explained_variance | 0.366 | +| learning_rate | 4.11e-05 | +| loss | -0.0362 | +| n_updates | 89160 | +| policy_gradient_loss | -0.0222 | +| value_loss | 0.000104 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1389 | +| iterations | 18337 | +| time_elapsed | 27018 | +| total_timesteps | 37554176 | +| train/ | | +| approx_kl | 0.0094266655 | +| clip_fraction | 0.31 | +| clip_range | 0.0656 | +| entropy_loss | -6.6 | +| explained_variance | 0.204 | +| learning_rate | 4.11e-05 | +| loss | -0.0256 | +| n_updates | 89164 | +| policy_gradient_loss | -0.0145 | +| value_loss | 0.000253 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1389 | +| iterations | 18338 | +| time_elapsed | 27019 | +| total_timesteps | 37556224 | +| train/ | | +| approx_kl | 0.010634187 | +| clip_fraction | 0.33 | +| clip_range | 0.0656 | +| entropy_loss | -6.35 | +| explained_variance | -0.15 | +| learning_rate | 4.11e-05 | +| loss | -0.0222 | +| n_updates | 89168 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000154 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1389 | +| iterations | 18339 | +| time_elapsed | 27021 | +| total_timesteps | 37558272 | +| train/ | | +| approx_kl | 0.012419651 | +| clip_fraction | 0.327 | +| clip_range | 0.0656 | +| entropy_loss | -6.05 | +| explained_variance | 0.33 | +| learning_rate | 4.11e-05 | +| loss | -0.024 | +| n_updates | 89172 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000221 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1389 | +| iterations | 18340 | +| time_elapsed | 27022 | +| total_timesteps | 37560320 | +| train/ | | +| approx_kl | 0.012927707 | +| clip_fraction | 0.344 | +| clip_range | 0.0656 | +| entropy_loss | -5.72 | +| explained_variance | 0.731 | +| learning_rate | 4.11e-05 | +| loss | -0.0247 | +| n_updates | 89176 | +| policy_gradient_loss | -0.0174 | +| value_loss | 7.44e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1389 | +| iterations | 18341 | +| time_elapsed | 27024 | +| total_timesteps | 37562368 | +| train/ | | +| approx_kl | 0.0121693015 | +| clip_fraction | 0.334 | +| clip_range | 0.0656 | +| entropy_loss | -5.06 | +| explained_variance | 0.788 | +| learning_rate | 4.11e-05 | +| loss | -0.0314 | +| n_updates | 89180 | +| policy_gradient_loss | -0.0162 | +| value_loss | 8.42e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1389 | +| iterations | 18342 | +| time_elapsed | 27026 | +| total_timesteps | 37564416 | +| train/ | | +| approx_kl | 0.014118746 | +| clip_fraction | 0.349 | +| clip_range | 0.0656 | +| entropy_loss | -5.33 | +| explained_variance | 0.436 | +| learning_rate | 4.11e-05 | +| loss | -0.0304 | +| n_updates | 89184 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000191 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1389 | +| iterations | 18343 | +| time_elapsed | 27027 | +| total_timesteps | 37566464 | +| train/ | | +| approx_kl | 0.0136261955 | +| clip_fraction | 0.358 | +| clip_range | 0.0656 | +| entropy_loss | -6.08 | +| explained_variance | 0.279 | +| learning_rate | 4.11e-05 | +| loss | -0.0282 | +| n_updates | 89188 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000113 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1389 | +| iterations | 18344 | +| time_elapsed | 27029 | +| total_timesteps | 37568512 | +| train/ | | +| approx_kl | 0.009425605 | +| clip_fraction | 0.296 | +| clip_range | 0.0656 | +| entropy_loss | -5.24 | +| explained_variance | 0.35 | +| learning_rate | 4.11e-05 | +| loss | -0.0215 | +| n_updates | 89192 | +| policy_gradient_loss | -0.0143 | +| value_loss | 0.000516 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1389 | +| iterations | 18345 | +| time_elapsed | 27030 | +| total_timesteps | 37570560 | +| train/ | | +| approx_kl | 0.013898604 | +| clip_fraction | 0.352 | +| clip_range | 0.0656 | +| entropy_loss | -6.07 | +| explained_variance | 0.297 | +| learning_rate | 4.11e-05 | +| loss | -0.0366 | +| n_updates | 89196 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000147 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1389 | +| iterations | 18346 | +| time_elapsed | 27032 | +| total_timesteps | 37572608 | +| train/ | | +| approx_kl | 0.010472565 | +| clip_fraction | 0.334 | +| clip_range | 0.0656 | +| entropy_loss | -6.23 | +| explained_variance | 0.189 | +| learning_rate | 4.11e-05 | +| loss | -0.021 | +| n_updates | 89200 | +| policy_gradient_loss | -0.0143 | +| value_loss | 0.000198 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1389 | +| iterations | 18347 | +| time_elapsed | 27033 | +| total_timesteps | 37574656 | +| train/ | | +| approx_kl | 0.009318816 | +| clip_fraction | 0.311 | +| clip_range | 0.0656 | +| entropy_loss | -5.46 | +| explained_variance | 0.521 | +| learning_rate | 4.11e-05 | +| loss | -0.016 | +| n_updates | 89204 | +| policy_gradient_loss | -0.0136 | +| value_loss | 0.000318 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1389 | +| iterations | 18348 | +| time_elapsed | 27035 | +| total_timesteps | 37576704 | +| train/ | | +| approx_kl | 0.010068384 | +| clip_fraction | 0.319 | +| clip_range | 0.0656 | +| entropy_loss | -5.69 | +| explained_variance | 0.262 | +| learning_rate | 4.11e-05 | +| loss | -0.0278 | +| n_updates | 89208 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.00017 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1389 | +| iterations | 18349 | +| time_elapsed | 27036 | +| total_timesteps | 37578752 | +| train/ | | +| approx_kl | 0.00853082 | +| clip_fraction | 0.32 | +| clip_range | 0.0656 | +| entropy_loss | -6.43 | +| explained_variance | 0.0807 | +| learning_rate | 4.11e-05 | +| loss | -0.0275 | +| n_updates | 89212 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000308 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1389 | +| iterations | 18350 | +| time_elapsed | 27038 | +| total_timesteps | 37580800 | +| train/ | | +| approx_kl | 0.011926805 | +| clip_fraction | 0.354 | +| clip_range | 0.0656 | +| entropy_loss | -5.3 | +| explained_variance | 0.786 | +| learning_rate | 4.11e-05 | +| loss | -0.0315 | +| n_updates | 89216 | +| policy_gradient_loss | -0.0199 | +| value_loss | 6.79e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1389 | +| iterations | 18351 | +| time_elapsed | 27039 | +| total_timesteps | 37582848 | +| train/ | | +| approx_kl | 0.014451572 | +| clip_fraction | 0.347 | +| clip_range | 0.0656 | +| entropy_loss | -6 | +| explained_variance | 0.206 | +| learning_rate | 4.11e-05 | +| loss | -0.0196 | +| n_updates | 89220 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000196 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1389 | +| iterations | 18352 | +| time_elapsed | 27041 | +| total_timesteps | 37584896 | +| train/ | | +| approx_kl | 0.01496416 | +| clip_fraction | 0.343 | +| clip_range | 0.0656 | +| entropy_loss | -5.66 | +| explained_variance | 0.574 | +| learning_rate | 4.11e-05 | +| loss | -0.0345 | +| n_updates | 89224 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000103 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1389 | +| iterations | 18353 | +| time_elapsed | 27042 | +| total_timesteps | 37586944 | +| train/ | | +| approx_kl | 0.014138846 | +| clip_fraction | 0.359 | +| clip_range | 0.0656 | +| entropy_loss | -5.92 | +| explained_variance | 0.475 | +| learning_rate | 4.11e-05 | +| loss | -0.0312 | +| n_updates | 89228 | +| policy_gradient_loss | -0.0206 | +| value_loss | 7.2e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1389 | +| iterations | 18354 | +| time_elapsed | 27044 | +| total_timesteps | 37588992 | +| train/ | | +| approx_kl | 0.013603644 | +| clip_fraction | 0.342 | +| clip_range | 0.0656 | +| entropy_loss | -5.88 | +| explained_variance | 0.546 | +| learning_rate | 4.11e-05 | +| loss | -0.0222 | +| n_updates | 89232 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000119 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1389 | +| iterations | 18355 | +| time_elapsed | 27045 | +| total_timesteps | 37591040 | +| train/ | | +| approx_kl | 0.013312946 | +| clip_fraction | 0.322 | +| clip_range | 0.0656 | +| entropy_loss | -6.14 | +| explained_variance | -0.188 | +| learning_rate | 4.11e-05 | +| loss | -0.0273 | +| n_updates | 89236 | +| policy_gradient_loss | -0.0176 | +| value_loss | 8.35e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1389 | +| iterations | 18356 | +| time_elapsed | 27047 | +| total_timesteps | 37593088 | +| train/ | | +| approx_kl | 0.009563923 | +| clip_fraction | 0.295 | +| clip_range | 0.0656 | +| entropy_loss | -6.39 | +| explained_variance | 0.18 | +| learning_rate | 4.11e-05 | +| loss | -0.0237 | +| n_updates | 89240 | +| policy_gradient_loss | -0.0136 | +| value_loss | 0.0003 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1389 | +| iterations | 18357 | +| time_elapsed | 27048 | +| total_timesteps | 37595136 | +| train/ | | +| approx_kl | 0.01304356 | +| clip_fraction | 0.337 | +| clip_range | 0.0656 | +| entropy_loss | -5.64 | +| explained_variance | 0.543 | +| learning_rate | 4.11e-05 | +| loss | -0.0271 | +| n_updates | 89244 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000153 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1389 | +| iterations | 18358 | +| time_elapsed | 27050 | +| total_timesteps | 37597184 | +| train/ | | +| approx_kl | 0.011848209 | +| clip_fraction | 0.318 | +| clip_range | 0.0656 | +| entropy_loss | -5.43 | +| explained_variance | 0.559 | +| learning_rate | 4.11e-05 | +| loss | -0.0209 | +| n_updates | 89248 | +| policy_gradient_loss | -0.0147 | +| value_loss | 0.000153 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1389 | +| iterations | 18359 | +| time_elapsed | 27051 | +| total_timesteps | 37599232 | +| train/ | | +| approx_kl | 0.009443664 | +| clip_fraction | 0.316 | +| clip_range | 0.0656 | +| entropy_loss | -5.6 | +| explained_variance | 0.347 | +| learning_rate | 4.11e-05 | +| loss | -0.0303 | +| n_updates | 89252 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000227 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1389 | +| iterations | 18360 | +| time_elapsed | 27053 | +| total_timesteps | 37601280 | +| train/ | | +| approx_kl | 0.013859754 | +| clip_fraction | 0.338 | +| clip_range | 0.0656 | +| entropy_loss | -5.44 | +| explained_variance | 0.582 | +| learning_rate | 4.11e-05 | +| loss | -0.0284 | +| n_updates | 89256 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000121 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1389 | +| iterations | 18361 | +| time_elapsed | 27055 | +| total_timesteps | 37603328 | +| train/ | | +| approx_kl | 0.009276515 | +| clip_fraction | 0.305 | +| clip_range | 0.0656 | +| entropy_loss | -5.4 | +| explained_variance | 0.565 | +| learning_rate | 4.11e-05 | +| loss | -0.0263 | +| n_updates | 89260 | +| policy_gradient_loss | -0.0141 | +| value_loss | 0.000293 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1389 | +| iterations | 18362 | +| time_elapsed | 27056 | +| total_timesteps | 37605376 | +| train/ | | +| approx_kl | 0.013461405 | +| clip_fraction | 0.335 | +| clip_range | 0.0656 | +| entropy_loss | -5.63 | +| explained_variance | 0.0896 | +| learning_rate | 4.11e-05 | +| loss | -0.0286 | +| n_updates | 89264 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000222 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1389 | +| iterations | 18363 | +| time_elapsed | 27058 | +| total_timesteps | 37607424 | +| train/ | | +| approx_kl | 0.0127342 | +| clip_fraction | 0.343 | +| clip_range | 0.0656 | +| entropy_loss | -5.78 | +| explained_variance | 0.239 | +| learning_rate | 4.11e-05 | +| loss | -0.0355 | +| n_updates | 89268 | +| policy_gradient_loss | -0.022 | +| value_loss | 8.81e-05 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1389 | +| iterations | 18364 | +| time_elapsed | 27059 | +| total_timesteps | 37609472 | +| train/ | | +| approx_kl | 0.014074689 | +| clip_fraction | 0.343 | +| clip_range | 0.0656 | +| entropy_loss | -6.23 | +| explained_variance | -0.216 | +| learning_rate | 4.11e-05 | +| loss | -0.0348 | +| n_updates | 89272 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.00014 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1389 | +| iterations | 18365 | +| time_elapsed | 27061 | +| total_timesteps | 37611520 | +| train/ | | +| approx_kl | 0.01182257 | +| clip_fraction | 0.349 | +| clip_range | 0.0656 | +| entropy_loss | -6.3 | +| explained_variance | 0.118 | +| learning_rate | 4.11e-05 | +| loss | -0.0294 | +| n_updates | 89276 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000218 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1389 | +| iterations | 18366 | +| time_elapsed | 27062 | +| total_timesteps | 37613568 | +| train/ | | +| approx_kl | 0.011357788 | +| clip_fraction | 0.313 | +| clip_range | 0.0656 | +| entropy_loss | -5.52 | +| explained_variance | 0.462 | +| learning_rate | 4.11e-05 | +| loss | -0.0247 | +| n_updates | 89280 | +| policy_gradient_loss | -0.0139 | +| value_loss | 0.000238 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1389 | +| iterations | 18367 | +| time_elapsed | 27064 | +| total_timesteps | 37615616 | +| train/ | | +| approx_kl | 0.011944244 | +| clip_fraction | 0.35 | +| clip_range | 0.0656 | +| entropy_loss | -5.38 | +| explained_variance | 0.514 | +| learning_rate | 4.11e-05 | +| loss | -0.0257 | +| n_updates | 89284 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000133 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1389 | +| iterations | 18368 | +| time_elapsed | 27065 | +| total_timesteps | 37617664 | +| train/ | | +| approx_kl | 0.015153302 | +| clip_fraction | 0.347 | +| clip_range | 0.0656 | +| entropy_loss | -5.6 | +| explained_variance | 0.584 | +| learning_rate | 4.11e-05 | +| loss | -0.0334 | +| n_updates | 89288 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000112 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1389 | +| iterations | 18369 | +| time_elapsed | 27067 | +| total_timesteps | 37619712 | +| train/ | | +| approx_kl | 0.010104414 | +| clip_fraction | 0.316 | +| clip_range | 0.0656 | +| entropy_loss | -5.54 | +| explained_variance | 0.568 | +| learning_rate | 4.11e-05 | +| loss | -0.0248 | +| n_updates | 89292 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000193 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1389 | +| iterations | 18370 | +| time_elapsed | 27068 | +| total_timesteps | 37621760 | +| train/ | | +| approx_kl | 0.010791238 | +| clip_fraction | 0.322 | +| clip_range | 0.0656 | +| entropy_loss | -5.5 | +| explained_variance | 0.639 | +| learning_rate | 4.11e-05 | +| loss | -0.0264 | +| n_updates | 89296 | +| policy_gradient_loss | -0.0177 | +| value_loss | 6.45e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1389 | +| iterations | 18371 | +| time_elapsed | 27070 | +| total_timesteps | 37623808 | +| train/ | | +| approx_kl | 0.011545501 | +| clip_fraction | 0.33 | +| clip_range | 0.0656 | +| entropy_loss | -5.03 | +| explained_variance | 0.402 | +| learning_rate | 4.11e-05 | +| loss | -0.0237 | +| n_updates | 89300 | +| policy_gradient_loss | -0.0142 | +| value_loss | 0.000282 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1389 | +| iterations | 18372 | +| time_elapsed | 27072 | +| total_timesteps | 37625856 | +| train/ | | +| approx_kl | 0.014268024 | +| clip_fraction | 0.363 | +| clip_range | 0.0656 | +| entropy_loss | -5.48 | +| explained_variance | 0.447 | +| learning_rate | 4.11e-05 | +| loss | -0.0322 | +| n_updates | 89304 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000116 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1389 | +| iterations | 18373 | +| time_elapsed | 27073 | +| total_timesteps | 37627904 | +| train/ | | +| approx_kl | 0.0138161555 | +| clip_fraction | 0.341 | +| clip_range | 0.0656 | +| entropy_loss | -5.87 | +| explained_variance | 0.52 | +| learning_rate | 4.11e-05 | +| loss | -0.0294 | +| n_updates | 89308 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.00013 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1389 | +| iterations | 18374 | +| time_elapsed | 27075 | +| total_timesteps | 37629952 | +| train/ | | +| approx_kl | 0.014425742 | +| clip_fraction | 0.338 | +| clip_range | 0.0656 | +| entropy_loss | -5.62 | +| explained_variance | 0.506 | +| learning_rate | 4.11e-05 | +| loss | -0.0312 | +| n_updates | 89312 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000144 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1389 | +| iterations | 18375 | +| time_elapsed | 27076 | +| total_timesteps | 37632000 | +| train/ | | +| approx_kl | 0.015671732 | +| clip_fraction | 0.37 | +| clip_range | 0.0656 | +| entropy_loss | -5.83 | +| explained_variance | 0.425 | +| learning_rate | 4.11e-05 | +| loss | -0.0309 | +| n_updates | 89316 | +| policy_gradient_loss | -0.0197 | +| value_loss | 9.58e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1389 | +| iterations | 18376 | +| time_elapsed | 27078 | +| total_timesteps | 37634048 | +| train/ | | +| approx_kl | 0.012161296 | +| clip_fraction | 0.354 | +| clip_range | 0.0656 | +| entropy_loss | -5.79 | +| explained_variance | 0.463 | +| learning_rate | 4.11e-05 | +| loss | -0.0279 | +| n_updates | 89320 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000178 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1389 | +| iterations | 18377 | +| time_elapsed | 27079 | +| total_timesteps | 37636096 | +| train/ | | +| approx_kl | 0.017703533 | +| clip_fraction | 0.368 | +| clip_range | 0.0656 | +| entropy_loss | -4.91 | +| explained_variance | 0.751 | +| learning_rate | 4.11e-05 | +| loss | -0.0309 | +| n_updates | 89324 | +| policy_gradient_loss | -0.0162 | +| value_loss | 7.84e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1389 | +| iterations | 18378 | +| time_elapsed | 27081 | +| total_timesteps | 37638144 | +| train/ | | +| approx_kl | 0.014169206 | +| clip_fraction | 0.36 | +| clip_range | 0.0656 | +| entropy_loss | -5.72 | +| explained_variance | 0.522 | +| learning_rate | 4.11e-05 | +| loss | -0.0278 | +| n_updates | 89328 | +| policy_gradient_loss | -0.0191 | +| value_loss | 5.29e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1389 | +| iterations | 18379 | +| time_elapsed | 27082 | +| total_timesteps | 37640192 | +| train/ | | +| approx_kl | 0.012056936 | +| clip_fraction | 0.338 | +| clip_range | 0.0656 | +| entropy_loss | -5.7 | +| explained_variance | 0.3 | +| learning_rate | 4.11e-05 | +| loss | -0.0256 | +| n_updates | 89332 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000167 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1389 | +| iterations | 18380 | +| time_elapsed | 27084 | +| total_timesteps | 37642240 | +| train/ | | +| approx_kl | 0.012286043 | +| clip_fraction | 0.369 | +| clip_range | 0.0656 | +| entropy_loss | -6.36 | +| explained_variance | -0.185 | +| learning_rate | 4.11e-05 | +| loss | -0.0297 | +| n_updates | 89336 | +| policy_gradient_loss | -0.0196 | +| value_loss | 6.99e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1389 | +| iterations | 18381 | +| time_elapsed | 27085 | +| total_timesteps | 37644288 | +| train/ | | +| approx_kl | 0.014942789 | +| clip_fraction | 0.322 | +| clip_range | 0.0656 | +| entropy_loss | -5.7 | +| explained_variance | 0.482 | +| learning_rate | 4.11e-05 | +| loss | -0.0268 | +| n_updates | 89340 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.00025 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1389 | +| iterations | 18382 | +| time_elapsed | 27087 | +| total_timesteps | 37646336 | +| train/ | | +| approx_kl | 0.012951854 | +| clip_fraction | 0.329 | +| clip_range | 0.0656 | +| entropy_loss | -5.71 | +| explained_variance | 0.462 | +| learning_rate | 4.11e-05 | +| loss | -0.0268 | +| n_updates | 89344 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1389 | +| iterations | 18383 | +| time_elapsed | 27088 | +| total_timesteps | 37648384 | +| train/ | | +| approx_kl | 0.012488634 | +| clip_fraction | 0.322 | +| clip_range | 0.0656 | +| entropy_loss | -5.75 | +| explained_variance | 0.588 | +| learning_rate | 4.11e-05 | +| loss | -0.0294 | +| n_updates | 89348 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000113 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1389 | +| iterations | 18384 | +| time_elapsed | 27090 | +| total_timesteps | 37650432 | +| train/ | | +| approx_kl | 0.009395216 | +| clip_fraction | 0.305 | +| clip_range | 0.0656 | +| entropy_loss | -6.13 | +| explained_variance | 0.612 | +| learning_rate | 4.11e-05 | +| loss | -0.0259 | +| n_updates | 89352 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.000119 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1389 | +| iterations | 18385 | +| time_elapsed | 27092 | +| total_timesteps | 37652480 | +| train/ | | +| approx_kl | 0.012168344 | +| clip_fraction | 0.339 | +| clip_range | 0.0656 | +| entropy_loss | -5.7 | +| explained_variance | 0.477 | +| learning_rate | 4.11e-05 | +| loss | -0.0331 | +| n_updates | 89356 | +| policy_gradient_loss | -0.0183 | +| value_loss | 8.35e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1389 | +| iterations | 18386 | +| time_elapsed | 27093 | +| total_timesteps | 37654528 | +| train/ | | +| approx_kl | 0.017199717 | +| clip_fraction | 0.338 | +| clip_range | 0.0656 | +| entropy_loss | -5.3 | +| explained_variance | 0.336 | +| learning_rate | 4.11e-05 | +| loss | -0.0316 | +| n_updates | 89360 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000146 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1389 | +| iterations | 18387 | +| time_elapsed | 27095 | +| total_timesteps | 37656576 | +| train/ | | +| approx_kl | 0.014616113 | +| clip_fraction | 0.349 | +| clip_range | 0.0656 | +| entropy_loss | -5.57 | +| explained_variance | 0.587 | +| learning_rate | 4.11e-05 | +| loss | -0.0343 | +| n_updates | 89364 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000103 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1389 | +| iterations | 18388 | +| time_elapsed | 27096 | +| total_timesteps | 37658624 | +| train/ | | +| approx_kl | 0.014620468 | +| clip_fraction | 0.349 | +| clip_range | 0.0656 | +| entropy_loss | -5.68 | +| explained_variance | 0.408 | +| learning_rate | 4.11e-05 | +| loss | -0.0248 | +| n_updates | 89368 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000219 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1389 | +| iterations | 18389 | +| time_elapsed | 27098 | +| total_timesteps | 37660672 | +| train/ | | +| approx_kl | 0.013923392 | +| clip_fraction | 0.334 | +| clip_range | 0.0656 | +| entropy_loss | -5.49 | +| explained_variance | 0.43 | +| learning_rate | 4.11e-05 | +| loss | -0.0256 | +| n_updates | 89372 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000205 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1389 | +| iterations | 18390 | +| time_elapsed | 27099 | +| total_timesteps | 37662720 | +| train/ | | +| approx_kl | 0.011058573 | +| clip_fraction | 0.355 | +| clip_range | 0.0656 | +| entropy_loss | -5.77 | +| explained_variance | 0.452 | +| learning_rate | 4.11e-05 | +| loss | -0.0305 | +| n_updates | 89376 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000142 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1389 | +| iterations | 18391 | +| time_elapsed | 27101 | +| total_timesteps | 37664768 | +| train/ | | +| approx_kl | 0.009920644 | +| clip_fraction | 0.314 | +| clip_range | 0.0656 | +| entropy_loss | -5.71 | +| explained_variance | 0.417 | +| learning_rate | 4.11e-05 | +| loss | -0.0192 | +| n_updates | 89380 | +| policy_gradient_loss | -0.0143 | +| value_loss | 0.000344 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1389 | +| iterations | 18392 | +| time_elapsed | 27102 | +| total_timesteps | 37666816 | +| train/ | | +| approx_kl | 0.011781001 | +| clip_fraction | 0.328 | +| clip_range | 0.0656 | +| entropy_loss | -5.37 | +| explained_variance | 0.518 | +| learning_rate | 4.11e-05 | +| loss | -0.0355 | +| n_updates | 89384 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000174 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1389 | +| iterations | 18393 | +| time_elapsed | 27104 | +| total_timesteps | 37668864 | +| train/ | | +| approx_kl | 0.011633802 | +| clip_fraction | 0.338 | +| clip_range | 0.0656 | +| entropy_loss | -5.65 | +| explained_variance | 0.287 | +| learning_rate | 4.11e-05 | +| loss | -0.0226 | +| n_updates | 89388 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000135 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1389 | +| iterations | 18394 | +| time_elapsed | 27105 | +| total_timesteps | 37670912 | +| train/ | | +| approx_kl | 0.014083875 | +| clip_fraction | 0.356 | +| clip_range | 0.0656 | +| entropy_loss | -5.87 | +| explained_variance | -0.217 | +| learning_rate | 4.11e-05 | +| loss | -0.0329 | +| n_updates | 89392 | +| policy_gradient_loss | -0.0189 | +| value_loss | 8.55e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1389 | +| iterations | 18395 | +| time_elapsed | 27107 | +| total_timesteps | 37672960 | +| train/ | | +| approx_kl | 0.012146101 | +| clip_fraction | 0.316 | +| clip_range | 0.0656 | +| entropy_loss | -5.8 | +| explained_variance | 0.452 | +| learning_rate | 4.11e-05 | +| loss | -0.022 | +| n_updates | 89396 | +| policy_gradient_loss | -0.0142 | +| value_loss | 0.000199 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1389 | +| iterations | 18396 | +| time_elapsed | 27108 | +| total_timesteps | 37675008 | +| train/ | | +| approx_kl | 0.009011744 | +| clip_fraction | 0.306 | +| clip_range | 0.0656 | +| entropy_loss | -5.8 | +| explained_variance | 0.205 | +| learning_rate | 4.11e-05 | +| loss | -0.0212 | +| n_updates | 89400 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.00027 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1389 | +| iterations | 18397 | +| time_elapsed | 27110 | +| total_timesteps | 37677056 | +| train/ | | +| approx_kl | 0.013918724 | +| clip_fraction | 0.328 | +| clip_range | 0.0656 | +| entropy_loss | -5.14 | +| explained_variance | 0.588 | +| learning_rate | 4.11e-05 | +| loss | -0.0247 | +| n_updates | 89404 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000205 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1389 | +| iterations | 18398 | +| time_elapsed | 27111 | +| total_timesteps | 37679104 | +| train/ | | +| approx_kl | 0.014271257 | +| clip_fraction | 0.349 | +| clip_range | 0.0656 | +| entropy_loss | -5.7 | +| explained_variance | 0.172 | +| learning_rate | 4.11e-05 | +| loss | -0.0193 | +| n_updates | 89408 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000282 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1389 | +| iterations | 18399 | +| time_elapsed | 27113 | +| total_timesteps | 37681152 | +| train/ | | +| approx_kl | 0.010908316 | +| clip_fraction | 0.314 | +| clip_range | 0.0656 | +| entropy_loss | -5.29 | +| explained_variance | 0.476 | +| learning_rate | 4.11e-05 | +| loss | -0.0245 | +| n_updates | 89412 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000237 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1389 | +| iterations | 18400 | +| time_elapsed | 27115 | +| total_timesteps | 37683200 | +| train/ | | +| approx_kl | 0.014869016 | +| clip_fraction | 0.35 | +| clip_range | 0.0656 | +| entropy_loss | -4.98 | +| explained_variance | 0.633 | +| learning_rate | 4.11e-05 | +| loss | -0.0269 | +| n_updates | 89416 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000107 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1389 | +| iterations | 18401 | +| time_elapsed | 27116 | +| total_timesteps | 37685248 | +| train/ | | +| approx_kl | 0.014546569 | +| clip_fraction | 0.357 | +| clip_range | 0.0656 | +| entropy_loss | -5.83 | +| explained_variance | 0.359 | +| learning_rate | 4.11e-05 | +| loss | -0.0301 | +| n_updates | 89420 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.00021 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1389 | +| iterations | 18402 | +| time_elapsed | 27118 | +| total_timesteps | 37687296 | +| train/ | | +| approx_kl | 0.009928374 | +| clip_fraction | 0.34 | +| clip_range | 0.0656 | +| entropy_loss | -6.15 | +| explained_variance | 0.276 | +| learning_rate | 4.1e-05 | +| loss | -0.0259 | +| n_updates | 89424 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000287 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1389 | +| iterations | 18403 | +| time_elapsed | 27119 | +| total_timesteps | 37689344 | +| train/ | | +| approx_kl | 0.018176526 | +| clip_fraction | 0.352 | +| clip_range | 0.0656 | +| entropy_loss | -6.15 | +| explained_variance | 0.0297 | +| learning_rate | 4.1e-05 | +| loss | -0.0307 | +| n_updates | 89428 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000227 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1389 | +| iterations | 18404 | +| time_elapsed | 27121 | +| total_timesteps | 37691392 | +| train/ | | +| approx_kl | 0.013783347 | +| clip_fraction | 0.386 | +| clip_range | 0.0656 | +| entropy_loss | -5.72 | +| explained_variance | 0.419 | +| learning_rate | 4.1e-05 | +| loss | -0.0295 | +| n_updates | 89432 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000113 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1389 | +| iterations | 18405 | +| time_elapsed | 27122 | +| total_timesteps | 37693440 | +| train/ | | +| approx_kl | 0.0115782 | +| clip_fraction | 0.315 | +| clip_range | 0.0656 | +| entropy_loss | -5 | +| explained_variance | 0.372 | +| learning_rate | 4.1e-05 | +| loss | -0.0217 | +| n_updates | 89436 | +| policy_gradient_loss | -0.0134 | +| value_loss | 0.000455 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1389 | +| iterations | 18406 | +| time_elapsed | 27124 | +| total_timesteps | 37695488 | +| train/ | | +| approx_kl | 0.014575323 | +| clip_fraction | 0.323 | +| clip_range | 0.0656 | +| entropy_loss | -4.35 | +| explained_variance | 0.496 | +| learning_rate | 4.1e-05 | +| loss | -0.0241 | +| n_updates | 89440 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000159 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1389 | +| iterations | 18407 | +| time_elapsed | 27125 | +| total_timesteps | 37697536 | +| train/ | | +| approx_kl | 0.014618664 | +| clip_fraction | 0.362 | +| clip_range | 0.0656 | +| entropy_loss | -5.28 | +| explained_variance | 0.505 | +| learning_rate | 4.1e-05 | +| loss | -0.0352 | +| n_updates | 89444 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.00013 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1389 | +| iterations | 18408 | +| time_elapsed | 27127 | +| total_timesteps | 37699584 | +| train/ | | +| approx_kl | 0.016074292 | +| clip_fraction | 0.37 | +| clip_range | 0.0656 | +| entropy_loss | -5.52 | +| explained_variance | 0.43 | +| learning_rate | 4.1e-05 | +| loss | -0.0317 | +| n_updates | 89448 | +| policy_gradient_loss | -0.0193 | +| value_loss | 9.19e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1389 | +| iterations | 18409 | +| time_elapsed | 27128 | +| total_timesteps | 37701632 | +| train/ | | +| approx_kl | 0.015020199 | +| clip_fraction | 0.388 | +| clip_range | 0.0656 | +| entropy_loss | -4.93 | +| explained_variance | 0.761 | +| learning_rate | 4.1e-05 | +| loss | -0.0314 | +| n_updates | 89452 | +| policy_gradient_loss | -0.0213 | +| value_loss | 5e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1389 | +| iterations | 18410 | +| time_elapsed | 27130 | +| total_timesteps | 37703680 | +| train/ | | +| approx_kl | 0.014936039 | +| clip_fraction | 0.307 | +| clip_range | 0.0656 | +| entropy_loss | -5.76 | +| explained_variance | 0.414 | +| learning_rate | 4.1e-05 | +| loss | -0.0279 | +| n_updates | 89456 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000111 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1389 | +| iterations | 18411 | +| time_elapsed | 27131 | +| total_timesteps | 37705728 | +| train/ | | +| approx_kl | 0.013996868 | +| clip_fraction | 0.333 | +| clip_range | 0.0656 | +| entropy_loss | -5.5 | +| explained_variance | 0.685 | +| learning_rate | 4.1e-05 | +| loss | -0.028 | +| n_updates | 89460 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000136 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1389 | +| iterations | 18412 | +| time_elapsed | 27133 | +| total_timesteps | 37707776 | +| train/ | | +| approx_kl | 0.014217073 | +| clip_fraction | 0.327 | +| clip_range | 0.0656 | +| entropy_loss | -5.37 | +| explained_variance | -0.0824 | +| learning_rate | 4.1e-05 | +| loss | -0.0243 | +| n_updates | 89464 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000119 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1389 | +| iterations | 18413 | +| time_elapsed | 27135 | +| total_timesteps | 37709824 | +| train/ | | +| approx_kl | 0.011686364 | +| clip_fraction | 0.326 | +| clip_range | 0.0656 | +| entropy_loss | -5.66 | +| explained_variance | 0.513 | +| learning_rate | 4.1e-05 | +| loss | -0.0262 | +| n_updates | 89468 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000233 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1389 | +| iterations | 18414 | +| time_elapsed | 27136 | +| total_timesteps | 37711872 | +| train/ | | +| approx_kl | 0.011647431 | +| clip_fraction | 0.317 | +| clip_range | 0.0656 | +| entropy_loss | -5.43 | +| explained_variance | 0.204 | +| learning_rate | 4.1e-05 | +| loss | -0.0213 | +| n_updates | 89472 | +| policy_gradient_loss | -0.0139 | +| value_loss | 0.000278 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1389 | +| iterations | 18415 | +| time_elapsed | 27138 | +| total_timesteps | 37713920 | +| train/ | | +| approx_kl | 0.012934923 | +| clip_fraction | 0.346 | +| clip_range | 0.0656 | +| entropy_loss | -5.07 | +| explained_variance | 0.404 | +| learning_rate | 4.1e-05 | +| loss | -0.0233 | +| n_updates | 89476 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000288 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1389 | +| iterations | 18416 | +| time_elapsed | 27139 | +| total_timesteps | 37715968 | +| train/ | | +| approx_kl | 0.014203764 | +| clip_fraction | 0.34 | +| clip_range | 0.0656 | +| entropy_loss | -5.27 | +| explained_variance | 0.53 | +| learning_rate | 4.1e-05 | +| loss | -0.0294 | +| n_updates | 89480 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.00018 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1389 | +| iterations | 18417 | +| time_elapsed | 27141 | +| total_timesteps | 37718016 | +| train/ | | +| approx_kl | 0.017027678 | +| clip_fraction | 0.362 | +| clip_range | 0.0656 | +| entropy_loss | -5.47 | +| explained_variance | 0.062 | +| learning_rate | 4.1e-05 | +| loss | -0.0296 | +| n_updates | 89484 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000162 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1389 | +| iterations | 18418 | +| time_elapsed | 27142 | +| total_timesteps | 37720064 | +| train/ | | +| approx_kl | 0.013765287 | +| clip_fraction | 0.365 | +| clip_range | 0.0656 | +| entropy_loss | -5.76 | +| explained_variance | 0.321 | +| learning_rate | 4.1e-05 | +| loss | -0.0299 | +| n_updates | 89488 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000248 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1389 | +| iterations | 18419 | +| time_elapsed | 27144 | +| total_timesteps | 37722112 | +| train/ | | +| approx_kl | 0.013679846 | +| clip_fraction | 0.337 | +| clip_range | 0.0656 | +| entropy_loss | -5.24 | +| explained_variance | 0.375 | +| learning_rate | 4.1e-05 | +| loss | -0.0184 | +| n_updates | 89492 | +| policy_gradient_loss | -0.0148 | +| value_loss | 0.000273 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1389 | +| iterations | 18420 | +| time_elapsed | 27145 | +| total_timesteps | 37724160 | +| train/ | | +| approx_kl | 0.014937893 | +| clip_fraction | 0.353 | +| clip_range | 0.0656 | +| entropy_loss | -5.7 | +| explained_variance | 0.338 | +| learning_rate | 4.1e-05 | +| loss | -0.0321 | +| n_updates | 89496 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000141 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1389 | +| iterations | 18421 | +| time_elapsed | 27147 | +| total_timesteps | 37726208 | +| train/ | | +| approx_kl | 0.010787047 | +| clip_fraction | 0.348 | +| clip_range | 0.0656 | +| entropy_loss | -5.68 | +| explained_variance | 0.533 | +| learning_rate | 4.1e-05 | +| loss | -0.0251 | +| n_updates | 89500 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000124 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1389 | +| iterations | 18422 | +| time_elapsed | 27148 | +| total_timesteps | 37728256 | +| train/ | | +| approx_kl | 0.0112409135 | +| clip_fraction | 0.324 | +| clip_range | 0.0656 | +| entropy_loss | -5.12 | +| explained_variance | 0.412 | +| learning_rate | 4.1e-05 | +| loss | -0.0234 | +| n_updates | 89504 | +| policy_gradient_loss | -0.0148 | +| value_loss | 0.000397 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1389 | +| iterations | 18423 | +| time_elapsed | 27150 | +| total_timesteps | 37730304 | +| train/ | | +| approx_kl | 0.011721628 | +| clip_fraction | 0.347 | +| clip_range | 0.0656 | +| entropy_loss | -5.23 | +| explained_variance | 0.364 | +| learning_rate | 4.1e-05 | +| loss | -0.0342 | +| n_updates | 89508 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000172 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1389 | +| iterations | 18424 | +| time_elapsed | 27151 | +| total_timesteps | 37732352 | +| train/ | | +| approx_kl | 0.01282893 | +| clip_fraction | 0.346 | +| clip_range | 0.0656 | +| entropy_loss | -5.34 | +| explained_variance | 0.467 | +| learning_rate | 4.1e-05 | +| loss | -0.027 | +| n_updates | 89512 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000296 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1389 | +| iterations | 18425 | +| time_elapsed | 27153 | +| total_timesteps | 37734400 | +| train/ | | +| approx_kl | 0.013524596 | +| clip_fraction | 0.35 | +| clip_range | 0.0656 | +| entropy_loss | -5.27 | +| explained_variance | 0.412 | +| learning_rate | 4.1e-05 | +| loss | -0.0269 | +| n_updates | 89516 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000165 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1389 | +| iterations | 18426 | +| time_elapsed | 27154 | +| total_timesteps | 37736448 | +| train/ | | +| approx_kl | 0.010859355 | +| clip_fraction | 0.348 | +| clip_range | 0.0656 | +| entropy_loss | -4.98 | +| explained_variance | 0.461 | +| learning_rate | 4.1e-05 | +| loss | -0.0237 | +| n_updates | 89520 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000149 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1389 | +| iterations | 18427 | +| time_elapsed | 27156 | +| total_timesteps | 37738496 | +| train/ | | +| approx_kl | 0.011266656 | +| clip_fraction | 0.32 | +| clip_range | 0.0656 | +| entropy_loss | -5.88 | +| explained_variance | -0.0615 | +| learning_rate | 4.1e-05 | +| loss | -0.0257 | +| n_updates | 89524 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000185 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1389 | +| iterations | 18428 | +| time_elapsed | 27157 | +| total_timesteps | 37740544 | +| train/ | | +| approx_kl | 0.014918808 | +| clip_fraction | 0.317 | +| clip_range | 0.0656 | +| entropy_loss | -6.3 | +| explained_variance | 0.157 | +| learning_rate | 4.1e-05 | +| loss | -0.0307 | +| n_updates | 89528 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000204 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1389 | +| iterations | 18429 | +| time_elapsed | 27159 | +| total_timesteps | 37742592 | +| train/ | | +| approx_kl | 0.019733693 | +| clip_fraction | 0.295 | +| clip_range | 0.0656 | +| entropy_loss | -5.59 | +| explained_variance | 0.569 | +| learning_rate | 4.1e-05 | +| loss | -0.0202 | +| n_updates | 89532 | +| policy_gradient_loss | -0.0134 | +| value_loss | 0.000244 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1389 | +| iterations | 18430 | +| time_elapsed | 27160 | +| total_timesteps | 37744640 | +| train/ | | +| approx_kl | 0.010938068 | +| clip_fraction | 0.284 | +| clip_range | 0.0656 | +| entropy_loss | -5.22 | +| explained_variance | 0.47 | +| learning_rate | 4.1e-05 | +| loss | -0.0231 | +| n_updates | 89536 | +| policy_gradient_loss | -0.0139 | +| value_loss | 0.000461 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1389 | +| iterations | 18431 | +| time_elapsed | 27162 | +| total_timesteps | 37746688 | +| train/ | | +| approx_kl | 0.011010514 | +| clip_fraction | 0.317 | +| clip_range | 0.0656 | +| entropy_loss | -5.12 | +| explained_variance | 0.405 | +| learning_rate | 4.1e-05 | +| loss | -0.0201 | +| n_updates | 89540 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000184 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1389 | +| iterations | 18432 | +| time_elapsed | 27163 | +| total_timesteps | 37748736 | +| train/ | | +| approx_kl | 0.014968298 | +| clip_fraction | 0.381 | +| clip_range | 0.0656 | +| entropy_loss | -4.89 | +| explained_variance | 0.587 | +| learning_rate | 4.1e-05 | +| loss | -0.0311 | +| n_updates | 89544 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000122 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1389 | +| iterations | 18433 | +| time_elapsed | 27165 | +| total_timesteps | 37750784 | +| train/ | | +| approx_kl | 0.017412005 | +| clip_fraction | 0.352 | +| clip_range | 0.0656 | +| entropy_loss | -5.59 | +| explained_variance | 0.128 | +| learning_rate | 4.1e-05 | +| loss | -0.034 | +| n_updates | 89548 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000126 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1389 | +| iterations | 18434 | +| time_elapsed | 27167 | +| total_timesteps | 37752832 | +| train/ | | +| approx_kl | 0.015743036 | +| clip_fraction | 0.352 | +| clip_range | 0.0656 | +| entropy_loss | -6.15 | +| explained_variance | 0.245 | +| learning_rate | 4.1e-05 | +| loss | -0.0296 | +| n_updates | 89552 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000137 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1389 | +| iterations | 18435 | +| time_elapsed | 27168 | +| total_timesteps | 37754880 | +| train/ | | +| approx_kl | 0.014329297 | +| clip_fraction | 0.351 | +| clip_range | 0.0656 | +| entropy_loss | -5.36 | +| explained_variance | 0.226 | +| learning_rate | 4.1e-05 | +| loss | -0.0271 | +| n_updates | 89556 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000226 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1389 | +| iterations | 18436 | +| time_elapsed | 27170 | +| total_timesteps | 37756928 | +| train/ | | +| approx_kl | 0.0149272205 | +| clip_fraction | 0.348 | +| clip_range | 0.0656 | +| entropy_loss | -5.98 | +| explained_variance | 0.0166 | +| learning_rate | 4.1e-05 | +| loss | -0.0294 | +| n_updates | 89560 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000151 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1389 | +| iterations | 18437 | +| time_elapsed | 27171 | +| total_timesteps | 37758976 | +| train/ | | +| approx_kl | 0.007811569 | +| clip_fraction | 0.308 | +| clip_range | 0.0656 | +| entropy_loss | -6.54 | +| explained_variance | 0.0623 | +| learning_rate | 4.1e-05 | +| loss | -0.0224 | +| n_updates | 89564 | +| policy_gradient_loss | -0.0124 | +| value_loss | 0.000352 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1389 | +| iterations | 18438 | +| time_elapsed | 27173 | +| total_timesteps | 37761024 | +| train/ | | +| approx_kl | 0.0077668144 | +| clip_fraction | 0.284 | +| clip_range | 0.0656 | +| entropy_loss | -5.06 | +| explained_variance | 0.641 | +| learning_rate | 4.1e-05 | +| loss | -0.0152 | +| n_updates | 89568 | +| policy_gradient_loss | -0.011 | +| value_loss | 0.000242 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1389 | +| iterations | 18439 | +| time_elapsed | 27174 | +| total_timesteps | 37763072 | +| train/ | | +| approx_kl | 0.012635946 | +| clip_fraction | 0.334 | +| clip_range | 0.0656 | +| entropy_loss | -4.24 | +| explained_variance | 0.723 | +| learning_rate | 4.1e-05 | +| loss | -0.0264 | +| n_updates | 89572 | +| policy_gradient_loss | -0.0175 | +| value_loss | 9.47e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1389 | +| iterations | 18440 | +| time_elapsed | 27176 | +| total_timesteps | 37765120 | +| train/ | | +| approx_kl | 0.01474965 | +| clip_fraction | 0.363 | +| clip_range | 0.0656 | +| entropy_loss | -4.78 | +| explained_variance | 0.53 | +| learning_rate | 4.1e-05 | +| loss | -0.0287 | +| n_updates | 89576 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000146 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1389 | +| iterations | 18441 | +| time_elapsed | 27177 | +| total_timesteps | 37767168 | +| train/ | | +| approx_kl | 0.016523164 | +| clip_fraction | 0.371 | +| clip_range | 0.0656 | +| entropy_loss | -5.91 | +| explained_variance | -0.334 | +| learning_rate | 4.1e-05 | +| loss | -0.0312 | +| n_updates | 89580 | +| policy_gradient_loss | -0.019 | +| value_loss | 6.92e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1389 | +| iterations | 18442 | +| time_elapsed | 27179 | +| total_timesteps | 37769216 | +| train/ | | +| approx_kl | 0.015049877 | +| clip_fraction | 0.312 | +| clip_range | 0.0656 | +| entropy_loss | -6.65 | +| explained_variance | 0.00714 | +| learning_rate | 4.1e-05 | +| loss | -0.0265 | +| n_updates | 89584 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000234 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1389 | +| iterations | 18443 | +| time_elapsed | 27180 | +| total_timesteps | 37771264 | +| train/ | | +| approx_kl | 0.012596119 | +| clip_fraction | 0.306 | +| clip_range | 0.0656 | +| entropy_loss | -6.07 | +| explained_variance | 0.414 | +| learning_rate | 4.1e-05 | +| loss | -0.0215 | +| n_updates | 89588 | +| policy_gradient_loss | -0.0144 | +| value_loss | 0.000222 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1389 | +| iterations | 18444 | +| time_elapsed | 27182 | +| total_timesteps | 37773312 | +| train/ | | +| approx_kl | 0.013033181 | +| clip_fraction | 0.306 | +| clip_range | 0.0656 | +| entropy_loss | -5.84 | +| explained_variance | 0.113 | +| learning_rate | 4.1e-05 | +| loss | -0.0294 | +| n_updates | 89592 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000327 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1389 | +| iterations | 18445 | +| time_elapsed | 27183 | +| total_timesteps | 37775360 | +| train/ | | +| approx_kl | 0.015171257 | +| clip_fraction | 0.333 | +| clip_range | 0.0656 | +| entropy_loss | -5.23 | +| explained_variance | 0.573 | +| learning_rate | 4.1e-05 | +| loss | -0.0333 | +| n_updates | 89596 | +| policy_gradient_loss | -0.0196 | +| value_loss | 9.38e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1389 | +| iterations | 18446 | +| time_elapsed | 27185 | +| total_timesteps | 37777408 | +| train/ | | +| approx_kl | 0.01268633 | +| clip_fraction | 0.34 | +| clip_range | 0.0656 | +| entropy_loss | -5.89 | +| explained_variance | 0.114 | +| learning_rate | 4.1e-05 | +| loss | -0.0238 | +| n_updates | 89600 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000177 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1389 | +| iterations | 18447 | +| time_elapsed | 27186 | +| total_timesteps | 37779456 | +| train/ | | +| approx_kl | 0.013612489 | +| clip_fraction | 0.352 | +| clip_range | 0.0656 | +| entropy_loss | -5.53 | +| explained_variance | 0.607 | +| learning_rate | 4.1e-05 | +| loss | -0.0242 | +| n_updates | 89604 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000117 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1389 | +| iterations | 18448 | +| time_elapsed | 27188 | +| total_timesteps | 37781504 | +| train/ | | +| approx_kl | 0.011703453 | +| clip_fraction | 0.335 | +| clip_range | 0.0656 | +| entropy_loss | -5.41 | +| explained_variance | 0.477 | +| learning_rate | 4.1e-05 | +| loss | -0.0225 | +| n_updates | 89608 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.000248 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1389 | +| iterations | 18449 | +| time_elapsed | 27190 | +| total_timesteps | 37783552 | +| train/ | | +| approx_kl | 0.015509826 | +| clip_fraction | 0.318 | +| clip_range | 0.0656 | +| entropy_loss | -5.21 | +| explained_variance | 0.65 | +| learning_rate | 4.1e-05 | +| loss | -0.0339 | +| n_updates | 89612 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000154 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1389 | +| iterations | 18450 | +| time_elapsed | 27191 | +| total_timesteps | 37785600 | +| train/ | | +| approx_kl | 0.013506596 | +| clip_fraction | 0.313 | +| clip_range | 0.0656 | +| entropy_loss | -4.69 | +| explained_variance | 0.479 | +| learning_rate | 4.1e-05 | +| loss | -0.0248 | +| n_updates | 89616 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000244 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1389 | +| iterations | 18451 | +| time_elapsed | 27193 | +| total_timesteps | 37787648 | +| train/ | | +| approx_kl | 0.012551154 | +| clip_fraction | 0.374 | +| clip_range | 0.0656 | +| entropy_loss | -5.49 | +| explained_variance | 0.407 | +| learning_rate | 4.1e-05 | +| loss | -0.0334 | +| n_updates | 89620 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000128 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1389 | +| iterations | 18452 | +| time_elapsed | 27194 | +| total_timesteps | 37789696 | +| train/ | | +| approx_kl | 0.009006108 | +| clip_fraction | 0.327 | +| clip_range | 0.0656 | +| entropy_loss | -6.74 | +| explained_variance | -0.0191 | +| learning_rate | 4.1e-05 | +| loss | -0.0246 | +| n_updates | 89624 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000256 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1389 | +| iterations | 18453 | +| time_elapsed | 27196 | +| total_timesteps | 37791744 | +| train/ | | +| approx_kl | 0.012726059 | +| clip_fraction | 0.308 | +| clip_range | 0.0656 | +| entropy_loss | -5.86 | +| explained_variance | 0.444 | +| learning_rate | 4.1e-05 | +| loss | -0.025 | +| n_updates | 89628 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000222 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1389 | +| iterations | 18454 | +| time_elapsed | 27197 | +| total_timesteps | 37793792 | +| train/ | | +| approx_kl | 0.016111923 | +| clip_fraction | 0.339 | +| clip_range | 0.0656 | +| entropy_loss | -5.72 | +| explained_variance | 0.283 | +| learning_rate | 4.1e-05 | +| loss | -0.0285 | +| n_updates | 89632 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000184 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1389 | +| iterations | 18455 | +| time_elapsed | 27199 | +| total_timesteps | 37795840 | +| train/ | | +| approx_kl | 0.012966315 | +| clip_fraction | 0.318 | +| clip_range | 0.0656 | +| entropy_loss | -5.96 | +| explained_variance | 0.366 | +| learning_rate | 4.1e-05 | +| loss | -0.0224 | +| n_updates | 89636 | +| policy_gradient_loss | -0.0141 | +| value_loss | 0.000238 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1389 | +| iterations | 18456 | +| time_elapsed | 27200 | +| total_timesteps | 37797888 | +| train/ | | +| approx_kl | 0.015850153 | +| clip_fraction | 0.326 | +| clip_range | 0.0656 | +| entropy_loss | -5.48 | +| explained_variance | 0.389 | +| learning_rate | 4.1e-05 | +| loss | -0.0223 | +| n_updates | 89640 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000146 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1389 | +| iterations | 18457 | +| time_elapsed | 27202 | +| total_timesteps | 37799936 | +| train/ | | +| approx_kl | 0.015034145 | +| clip_fraction | 0.359 | +| clip_range | 0.0656 | +| entropy_loss | -5.6 | +| explained_variance | 0.469 | +| learning_rate | 4.1e-05 | +| loss | -0.0299 | +| n_updates | 89644 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000173 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1389 | +| iterations | 18458 | +| time_elapsed | 27203 | +| total_timesteps | 37801984 | +| train/ | | +| approx_kl | 0.017649204 | +| clip_fraction | 0.337 | +| clip_range | 0.0656 | +| entropy_loss | -5.75 | +| explained_variance | -0.0747 | +| learning_rate | 4.1e-05 | +| loss | -0.0256 | +| n_updates | 89648 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000194 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1389 | +| iterations | 18459 | +| time_elapsed | 27205 | +| total_timesteps | 37804032 | +| train/ | | +| approx_kl | 0.017417993 | +| clip_fraction | 0.399 | +| clip_range | 0.0655 | +| entropy_loss | -5.75 | +| explained_variance | 0.336 | +| learning_rate | 4.1e-05 | +| loss | -0.0345 | +| n_updates | 89652 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000128 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1389 | +| iterations | 18460 | +| time_elapsed | 27206 | +| total_timesteps | 37806080 | +| train/ | | +| approx_kl | 0.01543309 | +| clip_fraction | 0.363 | +| clip_range | 0.0655 | +| entropy_loss | -5.69 | +| explained_variance | 0.423 | +| learning_rate | 4.1e-05 | +| loss | -0.0284 | +| n_updates | 89656 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000171 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1389 | +| iterations | 18461 | +| time_elapsed | 27208 | +| total_timesteps | 37808128 | +| train/ | | +| approx_kl | 0.01343341 | +| clip_fraction | 0.351 | +| clip_range | 0.0655 | +| entropy_loss | -5.71 | +| explained_variance | -0.122 | +| learning_rate | 4.1e-05 | +| loss | -0.0273 | +| n_updates | 89660 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000192 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1389 | +| iterations | 18462 | +| time_elapsed | 27210 | +| total_timesteps | 37810176 | +| train/ | | +| approx_kl | 0.016619638 | +| clip_fraction | 0.333 | +| clip_range | 0.0655 | +| entropy_loss | -4.85 | +| explained_variance | 0.713 | +| learning_rate | 4.1e-05 | +| loss | -0.0263 | +| n_updates | 89664 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000106 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1389 | +| iterations | 18463 | +| time_elapsed | 27211 | +| total_timesteps | 37812224 | +| train/ | | +| approx_kl | 0.014846487 | +| clip_fraction | 0.341 | +| clip_range | 0.0655 | +| entropy_loss | -4.99 | +| explained_variance | 0.346 | +| learning_rate | 4.1e-05 | +| loss | -0.031 | +| n_updates | 89668 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000146 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1389 | +| iterations | 18464 | +| time_elapsed | 27213 | +| total_timesteps | 37814272 | +| train/ | | +| approx_kl | 0.012666285 | +| clip_fraction | 0.317 | +| clip_range | 0.0655 | +| entropy_loss | -5.76 | +| explained_variance | 0.527 | +| learning_rate | 4.1e-05 | +| loss | -0.0289 | +| n_updates | 89672 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000126 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1389 | +| iterations | 18465 | +| time_elapsed | 27214 | +| total_timesteps | 37816320 | +| train/ | | +| approx_kl | 0.012693599 | +| clip_fraction | 0.352 | +| clip_range | 0.0655 | +| entropy_loss | -6.09 | +| explained_variance | -0.0148 | +| learning_rate | 4.1e-05 | +| loss | -0.0229 | +| n_updates | 89676 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000185 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1389 | +| iterations | 18466 | +| time_elapsed | 27216 | +| total_timesteps | 37818368 | +| train/ | | +| approx_kl | 0.011282131 | +| clip_fraction | 0.304 | +| clip_range | 0.0655 | +| entropy_loss | -5.85 | +| explained_variance | 0.62 | +| learning_rate | 4.1e-05 | +| loss | -0.0272 | +| n_updates | 89680 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000142 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1389 | +| iterations | 18467 | +| time_elapsed | 27217 | +| total_timesteps | 37820416 | +| train/ | | +| approx_kl | 0.013415612 | +| clip_fraction | 0.351 | +| clip_range | 0.0655 | +| entropy_loss | -6.38 | +| explained_variance | -0.00749 | +| learning_rate | 4.1e-05 | +| loss | -0.0271 | +| n_updates | 89684 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000142 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1389 | +| iterations | 18468 | +| time_elapsed | 27219 | +| total_timesteps | 37822464 | +| train/ | | +| approx_kl | 0.013490301 | +| clip_fraction | 0.341 | +| clip_range | 0.0655 | +| entropy_loss | -5.99 | +| explained_variance | 0.409 | +| learning_rate | 4.1e-05 | +| loss | -0.024 | +| n_updates | 89688 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000168 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1389 | +| iterations | 18469 | +| time_elapsed | 27220 | +| total_timesteps | 37824512 | +| train/ | | +| approx_kl | 0.015543523 | +| clip_fraction | 0.351 | +| clip_range | 0.0655 | +| entropy_loss | -5.24 | +| explained_variance | 0.622 | +| learning_rate | 4.1e-05 | +| loss | -0.0269 | +| n_updates | 89692 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000112 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1389 | +| iterations | 18470 | +| time_elapsed | 27222 | +| total_timesteps | 37826560 | +| train/ | | +| approx_kl | 0.01193684 | +| clip_fraction | 0.337 | +| clip_range | 0.0655 | +| entropy_loss | -5 | +| explained_variance | 0.155 | +| learning_rate | 4.1e-05 | +| loss | -0.0214 | +| n_updates | 89696 | +| policy_gradient_loss | -0.0146 | +| value_loss | 0.000475 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1389 | +| iterations | 18471 | +| time_elapsed | 27223 | +| total_timesteps | 37828608 | +| train/ | | +| approx_kl | 0.014235612 | +| clip_fraction | 0.362 | +| clip_range | 0.0655 | +| entropy_loss | -5.46 | +| explained_variance | 0.611 | +| learning_rate | 4.1e-05 | +| loss | -0.0303 | +| n_updates | 89700 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000117 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.384 | +| time/ | | +| fps | 1389 | +| iterations | 18472 | +| time_elapsed | 27225 | +| total_timesteps | 37830656 | +| train/ | | +| approx_kl | 0.014784602 | +| clip_fraction | 0.368 | +| clip_range | 0.0655 | +| entropy_loss | -5.87 | +| explained_variance | 0.593 | +| learning_rate | 4.1e-05 | +| loss | -0.0286 | +| n_updates | 89704 | +| policy_gradient_loss | -0.0194 | +| value_loss | 9.91e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1389 | +| iterations | 18473 | +| time_elapsed | 27226 | +| total_timesteps | 37832704 | +| train/ | | +| approx_kl | 0.011668559 | +| clip_fraction | 0.329 | +| clip_range | 0.0655 | +| entropy_loss | -6.13 | +| explained_variance | 0.332 | +| learning_rate | 4.1e-05 | +| loss | -0.0239 | +| n_updates | 89708 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000248 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1389 | +| iterations | 18474 | +| time_elapsed | 27228 | +| total_timesteps | 37834752 | +| train/ | | +| approx_kl | 0.01241212 | +| clip_fraction | 0.336 | +| clip_range | 0.0655 | +| entropy_loss | -5.98 | +| explained_variance | 0.486 | +| learning_rate | 4.1e-05 | +| loss | -0.0255 | +| n_updates | 89712 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.0002 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1389 | +| iterations | 18475 | +| time_elapsed | 27229 | +| total_timesteps | 37836800 | +| train/ | | +| approx_kl | 0.015750926 | +| clip_fraction | 0.365 | +| clip_range | 0.0655 | +| entropy_loss | -5.71 | +| explained_variance | 0.35 | +| learning_rate | 4.1e-05 | +| loss | -0.0341 | +| n_updates | 89716 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000137 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.386 | +| time/ | | +| fps | 1389 | +| iterations | 18476 | +| time_elapsed | 27231 | +| total_timesteps | 37838848 | +| train/ | | +| approx_kl | 0.012161399 | +| clip_fraction | 0.341 | +| clip_range | 0.0655 | +| entropy_loss | -6.34 | +| explained_variance | 0.386 | +| learning_rate | 4.1e-05 | +| loss | -0.0217 | +| n_updates | 89720 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000235 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1389 | +| iterations | 18477 | +| time_elapsed | 27233 | +| total_timesteps | 37840896 | +| train/ | | +| approx_kl | 0.012859235 | +| clip_fraction | 0.314 | +| clip_range | 0.0655 | +| entropy_loss | -6.16 | +| explained_variance | 0.377 | +| learning_rate | 4.1e-05 | +| loss | -0.0205 | +| n_updates | 89724 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000237 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1389 | +| iterations | 18478 | +| time_elapsed | 27234 | +| total_timesteps | 37842944 | +| train/ | | +| approx_kl | 0.011381886 | +| clip_fraction | 0.334 | +| clip_range | 0.0655 | +| entropy_loss | -5.8 | +| explained_variance | 0.596 | +| learning_rate | 4.1e-05 | +| loss | -0.00855 | +| n_updates | 89728 | +| policy_gradient_loss | -0.0168 | +| value_loss | 7.33e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1389 | +| iterations | 18479 | +| time_elapsed | 27236 | +| total_timesteps | 37844992 | +| train/ | | +| approx_kl | 0.018921908 | +| clip_fraction | 0.347 | +| clip_range | 0.0655 | +| entropy_loss | -5.38 | +| explained_variance | 0.453 | +| learning_rate | 4.1e-05 | +| loss | -0.0262 | +| n_updates | 89732 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000152 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1389 | +| iterations | 18480 | +| time_elapsed | 27237 | +| total_timesteps | 37847040 | +| train/ | | +| approx_kl | 0.014619492 | +| clip_fraction | 0.364 | +| clip_range | 0.0655 | +| entropy_loss | -5.84 | +| explained_variance | 0.419 | +| learning_rate | 4.1e-05 | +| loss | -0.037 | +| n_updates | 89736 | +| policy_gradient_loss | -0.0207 | +| value_loss | 8.57e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1389 | +| iterations | 18481 | +| time_elapsed | 27239 | +| total_timesteps | 37849088 | +| train/ | | +| approx_kl | 0.012150355 | +| clip_fraction | 0.347 | +| clip_range | 0.0655 | +| entropy_loss | -5.8 | +| explained_variance | 0.562 | +| learning_rate | 4.1e-05 | +| loss | -0.0265 | +| n_updates | 89740 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000132 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1389 | +| iterations | 18482 | +| time_elapsed | 27240 | +| total_timesteps | 37851136 | +| train/ | | +| approx_kl | 0.011402849 | +| clip_fraction | 0.31 | +| clip_range | 0.0655 | +| entropy_loss | -5.1 | +| explained_variance | 0.742 | +| learning_rate | 4.1e-05 | +| loss | -0.0232 | +| n_updates | 89744 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.000101 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1389 | +| iterations | 18483 | +| time_elapsed | 27242 | +| total_timesteps | 37853184 | +| train/ | | +| approx_kl | 0.010662391 | +| clip_fraction | 0.306 | +| clip_range | 0.0655 | +| entropy_loss | -5.27 | +| explained_variance | 0.527 | +| learning_rate | 4.1e-05 | +| loss | -0.0207 | +| n_updates | 89748 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.000228 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1389 | +| iterations | 18484 | +| time_elapsed | 27243 | +| total_timesteps | 37855232 | +| train/ | | +| approx_kl | 0.01905518 | +| clip_fraction | 0.362 | +| clip_range | 0.0655 | +| entropy_loss | -6.04 | +| explained_variance | -0.214 | +| learning_rate | 4.1e-05 | +| loss | -0.0318 | +| n_updates | 89752 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000131 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1389 | +| iterations | 18485 | +| time_elapsed | 27245 | +| total_timesteps | 37857280 | +| train/ | | +| approx_kl | 0.013629251 | +| clip_fraction | 0.345 | +| clip_range | 0.0655 | +| entropy_loss | -5.55 | +| explained_variance | 0.226 | +| learning_rate | 4.1e-05 | +| loss | -0.0272 | +| n_updates | 89756 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000208 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1389 | +| iterations | 18486 | +| time_elapsed | 27247 | +| total_timesteps | 37859328 | +| train/ | | +| approx_kl | 0.014307054 | +| clip_fraction | 0.347 | +| clip_range | 0.0655 | +| entropy_loss | -5.71 | +| explained_variance | 0.415 | +| learning_rate | 4.1e-05 | +| loss | -0.0298 | +| n_updates | 89760 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000203 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1389 | +| iterations | 18487 | +| time_elapsed | 27248 | +| total_timesteps | 37861376 | +| train/ | | +| approx_kl | 0.012410682 | +| clip_fraction | 0.339 | +| clip_range | 0.0655 | +| entropy_loss | -5.88 | +| explained_variance | 0.21 | +| learning_rate | 4.1e-05 | +| loss | -0.0291 | +| n_updates | 89764 | +| policy_gradient_loss | -0.0138 | +| value_loss | 0.000364 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1389 | +| iterations | 18488 | +| time_elapsed | 27250 | +| total_timesteps | 37863424 | +| train/ | | +| approx_kl | 0.01207559 | +| clip_fraction | 0.362 | +| clip_range | 0.0655 | +| entropy_loss | -5.31 | +| explained_variance | 0.628 | +| learning_rate | 4.1e-05 | +| loss | -0.0332 | +| n_updates | 89768 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000102 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1389 | +| iterations | 18489 | +| time_elapsed | 27251 | +| total_timesteps | 37865472 | +| train/ | | +| approx_kl | 0.012640227 | +| clip_fraction | 0.339 | +| clip_range | 0.0655 | +| entropy_loss | -5.23 | +| explained_variance | 0.459 | +| learning_rate | 4.1e-05 | +| loss | -0.0268 | +| n_updates | 89772 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000213 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1389 | +| iterations | 18490 | +| time_elapsed | 27253 | +| total_timesteps | 37867520 | +| train/ | | +| approx_kl | 0.0128046535 | +| clip_fraction | 0.356 | +| clip_range | 0.0655 | +| entropy_loss | -6.08 | +| explained_variance | 0.461 | +| learning_rate | 4.1e-05 | +| loss | -0.027 | +| n_updates | 89776 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000154 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1389 | +| iterations | 18491 | +| time_elapsed | 27254 | +| total_timesteps | 37869568 | +| train/ | | +| approx_kl | 0.011485327 | +| clip_fraction | 0.317 | +| clip_range | 0.0655 | +| entropy_loss | -5.94 | +| explained_variance | 0.481 | +| learning_rate | 4.1e-05 | +| loss | -0.0314 | +| n_updates | 89780 | +| policy_gradient_loss | -0.0179 | +| value_loss | 8.6e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1389 | +| iterations | 18492 | +| time_elapsed | 27256 | +| total_timesteps | 37871616 | +| train/ | | +| approx_kl | 0.012422476 | +| clip_fraction | 0.344 | +| clip_range | 0.0655 | +| entropy_loss | -5.99 | +| explained_variance | 0.0896 | +| learning_rate | 4.1e-05 | +| loss | -0.0196 | +| n_updates | 89784 | +| policy_gradient_loss | -0.0141 | +| value_loss | 0.000186 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1389 | +| iterations | 18493 | +| time_elapsed | 27257 | +| total_timesteps | 37873664 | +| train/ | | +| approx_kl | 0.014970136 | +| clip_fraction | 0.327 | +| clip_range | 0.0655 | +| entropy_loss | -4.86 | +| explained_variance | 0.668 | +| learning_rate | 4.1e-05 | +| loss | -0.0206 | +| n_updates | 89788 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.000118 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1389 | +| iterations | 18494 | +| time_elapsed | 27259 | +| total_timesteps | 37875712 | +| train/ | | +| approx_kl | 0.016225504 | +| clip_fraction | 0.365 | +| clip_range | 0.0655 | +| entropy_loss | -5.33 | +| explained_variance | 0.474 | +| learning_rate | 4.1e-05 | +| loss | -0.0296 | +| n_updates | 89792 | +| policy_gradient_loss | -0.0185 | +| value_loss | 9.28e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1389 | +| iterations | 18495 | +| time_elapsed | 27260 | +| total_timesteps | 37877760 | +| train/ | | +| approx_kl | 0.015967606 | +| clip_fraction | 0.361 | +| clip_range | 0.0655 | +| entropy_loss | -5.6 | +| explained_variance | 0.478 | +| learning_rate | 4.1e-05 | +| loss | -0.0282 | +| n_updates | 89796 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000143 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1389 | +| iterations | 18496 | +| time_elapsed | 27262 | +| total_timesteps | 37879808 | +| train/ | | +| approx_kl | 0.013615198 | +| clip_fraction | 0.318 | +| clip_range | 0.0655 | +| entropy_loss | -5.17 | +| explained_variance | 0.485 | +| learning_rate | 4.1e-05 | +| loss | -0.025 | +| n_updates | 89800 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000159 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1389 | +| iterations | 18497 | +| time_elapsed | 27263 | +| total_timesteps | 37881856 | +| train/ | | +| approx_kl | 0.014359993 | +| clip_fraction | 0.356 | +| clip_range | 0.0655 | +| entropy_loss | -5.51 | +| explained_variance | 0.593 | +| learning_rate | 4.1e-05 | +| loss | -0.0253 | +| n_updates | 89804 | +| policy_gradient_loss | -0.016 | +| value_loss | 9.02e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1389 | +| iterations | 18498 | +| time_elapsed | 27265 | +| total_timesteps | 37883904 | +| train/ | | +| approx_kl | 0.014166117 | +| clip_fraction | 0.375 | +| clip_range | 0.0655 | +| entropy_loss | -5.92 | +| explained_variance | 0.117 | +| learning_rate | 4.1e-05 | +| loss | -0.0324 | +| n_updates | 89808 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000129 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1389 | +| iterations | 18499 | +| time_elapsed | 27266 | +| total_timesteps | 37885952 | +| train/ | | +| approx_kl | 0.013847434 | +| clip_fraction | 0.335 | +| clip_range | 0.0655 | +| entropy_loss | -6.31 | +| explained_variance | -0.0626 | +| learning_rate | 4.1e-05 | +| loss | -0.0259 | +| n_updates | 89812 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000133 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1389 | +| iterations | 18500 | +| time_elapsed | 27268 | +| total_timesteps | 37888000 | +| train/ | | +| approx_kl | 0.011696938 | +| clip_fraction | 0.307 | +| clip_range | 0.0655 | +| entropy_loss | -5.81 | +| explained_variance | 0.518 | +| learning_rate | 4.1e-05 | +| loss | -0.0241 | +| n_updates | 89816 | +| policy_gradient_loss | -0.0146 | +| value_loss | 0.000217 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1389 | +| iterations | 18501 | +| time_elapsed | 27269 | +| total_timesteps | 37890048 | +| train/ | | +| approx_kl | 0.008947924 | +| clip_fraction | 0.289 | +| clip_range | 0.0655 | +| entropy_loss | -5.36 | +| explained_variance | 0.171 | +| learning_rate | 4.1e-05 | +| loss | -0.0235 | +| n_updates | 89820 | +| policy_gradient_loss | -0.013 | +| value_loss | 0.000365 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1389 | +| iterations | 18502 | +| time_elapsed | 27271 | +| total_timesteps | 37892096 | +| train/ | | +| approx_kl | 0.014122543 | +| clip_fraction | 0.366 | +| clip_range | 0.0655 | +| entropy_loss | -5.44 | +| explained_variance | 0.729 | +| learning_rate | 4.1e-05 | +| loss | -0.0315 | +| n_updates | 89824 | +| policy_gradient_loss | -0.0223 | +| value_loss | 7.85e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1389 | +| iterations | 18503 | +| time_elapsed | 27273 | +| total_timesteps | 37894144 | +| train/ | | +| approx_kl | 0.01134029 | +| clip_fraction | 0.343 | +| clip_range | 0.0655 | +| entropy_loss | -5.89 | +| explained_variance | 0.388 | +| learning_rate | 4.1e-05 | +| loss | -0.0257 | +| n_updates | 89828 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000145 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1389 | +| iterations | 18504 | +| time_elapsed | 27274 | +| total_timesteps | 37896192 | +| train/ | | +| approx_kl | 0.015739188 | +| clip_fraction | 0.323 | +| clip_range | 0.0655 | +| entropy_loss | -5.79 | +| explained_variance | 0.631 | +| learning_rate | 4.1e-05 | +| loss | -0.0255 | +| n_updates | 89832 | +| policy_gradient_loss | -0.0165 | +| value_loss | 6.15e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1389 | +| iterations | 18505 | +| time_elapsed | 27276 | +| total_timesteps | 37898240 | +| train/ | | +| approx_kl | 0.01387829 | +| clip_fraction | 0.321 | +| clip_range | 0.0655 | +| entropy_loss | -6.14 | +| explained_variance | 0.373 | +| learning_rate | 4.1e-05 | +| loss | -0.0258 | +| n_updates | 89836 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000121 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1389 | +| iterations | 18506 | +| time_elapsed | 27277 | +| total_timesteps | 37900288 | +| train/ | | +| approx_kl | 0.010558617 | +| clip_fraction | 0.312 | +| clip_range | 0.0655 | +| entropy_loss | -5.84 | +| explained_variance | 0.382 | +| learning_rate | 4.1e-05 | +| loss | -0.0188 | +| n_updates | 89840 | +| policy_gradient_loss | -0.0139 | +| value_loss | 0.000221 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1389 | +| iterations | 18507 | +| time_elapsed | 27279 | +| total_timesteps | 37902336 | +| train/ | | +| approx_kl | 0.01366943 | +| clip_fraction | 0.346 | +| clip_range | 0.0655 | +| entropy_loss | -4.95 | +| explained_variance | 0.605 | +| learning_rate | 4.1e-05 | +| loss | -0.0223 | +| n_updates | 89844 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000127 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1389 | +| iterations | 18508 | +| time_elapsed | 27280 | +| total_timesteps | 37904384 | +| train/ | | +| approx_kl | 0.018246753 | +| clip_fraction | 0.375 | +| clip_range | 0.0655 | +| entropy_loss | -5.09 | +| explained_variance | 0.157 | +| learning_rate | 4.1e-05 | +| loss | -0.0305 | +| n_updates | 89848 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000103 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1389 | +| iterations | 18509 | +| time_elapsed | 27282 | +| total_timesteps | 37906432 | +| train/ | | +| approx_kl | 0.015026181 | +| clip_fraction | 0.339 | +| clip_range | 0.0655 | +| entropy_loss | -5.7 | +| explained_variance | 0.418 | +| learning_rate | 4.1e-05 | +| loss | -0.0236 | +| n_updates | 89852 | +| policy_gradient_loss | -0.0167 | +| value_loss | 9.91e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1389 | +| iterations | 18510 | +| time_elapsed | 27283 | +| total_timesteps | 37908480 | +| train/ | | +| approx_kl | 0.01505626 | +| clip_fraction | 0.343 | +| clip_range | 0.0655 | +| entropy_loss | -5.6 | +| explained_variance | 0.455 | +| learning_rate | 4.1e-05 | +| loss | -0.0282 | +| n_updates | 89856 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.00015 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1389 | +| iterations | 18511 | +| time_elapsed | 27285 | +| total_timesteps | 37910528 | +| train/ | | +| approx_kl | 0.012194876 | +| clip_fraction | 0.327 | +| clip_range | 0.0655 | +| entropy_loss | -5.52 | +| explained_variance | 0.553 | +| learning_rate | 4.1e-05 | +| loss | -0.0225 | +| n_updates | 89860 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000191 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1389 | +| iterations | 18512 | +| time_elapsed | 27286 | +| total_timesteps | 37912576 | +| train/ | | +| approx_kl | 0.01530659 | +| clip_fraction | 0.37 | +| clip_range | 0.0655 | +| entropy_loss | -5.65 | +| explained_variance | -0.118 | +| learning_rate | 4.1e-05 | +| loss | -0.037 | +| n_updates | 89864 | +| policy_gradient_loss | -0.02 | +| value_loss | 6.98e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1389 | +| iterations | 18513 | +| time_elapsed | 27288 | +| total_timesteps | 37914624 | +| train/ | | +| approx_kl | 0.015891053 | +| clip_fraction | 0.334 | +| clip_range | 0.0655 | +| entropy_loss | -5.91 | +| explained_variance | 0.431 | +| learning_rate | 4.1e-05 | +| loss | -0.0269 | +| n_updates | 89868 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000183 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1389 | +| iterations | 18514 | +| time_elapsed | 27290 | +| total_timesteps | 37916672 | +| train/ | | +| approx_kl | 0.012182148 | +| clip_fraction | 0.312 | +| clip_range | 0.0655 | +| entropy_loss | -6.25 | +| explained_variance | -0.221 | +| learning_rate | 4.1e-05 | +| loss | -0.0208 | +| n_updates | 89872 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000117 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1389 | +| iterations | 18515 | +| time_elapsed | 27291 | +| total_timesteps | 37918720 | +| train/ | | +| approx_kl | 0.010846622 | +| clip_fraction | 0.333 | +| clip_range | 0.0655 | +| entropy_loss | -6.16 | +| explained_variance | 0.0426 | +| learning_rate | 4.1e-05 | +| loss | -0.0231 | +| n_updates | 89876 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000276 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1389 | +| iterations | 18516 | +| time_elapsed | 27293 | +| total_timesteps | 37920768 | +| train/ | | +| approx_kl | 0.010715489 | +| clip_fraction | 0.288 | +| clip_range | 0.0655 | +| entropy_loss | -5.19 | +| explained_variance | 0.475 | +| learning_rate | 4.1e-05 | +| loss | -0.0219 | +| n_updates | 89880 | +| policy_gradient_loss | -0.0138 | +| value_loss | 0.00031 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1389 | +| iterations | 18517 | +| time_elapsed | 27294 | +| total_timesteps | 37922816 | +| train/ | | +| approx_kl | 0.011239479 | +| clip_fraction | 0.317 | +| clip_range | 0.0655 | +| entropy_loss | -5.31 | +| explained_variance | 0.52 | +| learning_rate | 4.1e-05 | +| loss | -0.0304 | +| n_updates | 89884 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000188 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1389 | +| iterations | 18518 | +| time_elapsed | 27296 | +| total_timesteps | 37924864 | +| train/ | | +| approx_kl | 0.015082173 | +| clip_fraction | 0.344 | +| clip_range | 0.0655 | +| entropy_loss | -5.53 | +| explained_variance | 0.332 | +| learning_rate | 4.1e-05 | +| loss | -0.0278 | +| n_updates | 89888 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000124 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1389 | +| iterations | 18519 | +| time_elapsed | 27297 | +| total_timesteps | 37926912 | +| train/ | | +| approx_kl | 0.01195579 | +| clip_fraction | 0.346 | +| clip_range | 0.0655 | +| entropy_loss | -6.07 | +| explained_variance | 0.334 | +| learning_rate | 4.1e-05 | +| loss | -0.031 | +| n_updates | 89892 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000111 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1389 | +| iterations | 18520 | +| time_elapsed | 27299 | +| total_timesteps | 37928960 | +| train/ | | +| approx_kl | 0.014792417 | +| clip_fraction | 0.323 | +| clip_range | 0.0655 | +| entropy_loss | -5.16 | +| explained_variance | 0.589 | +| learning_rate | 4.1e-05 | +| loss | -0.0225 | +| n_updates | 89896 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000206 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1389 | +| iterations | 18521 | +| time_elapsed | 27300 | +| total_timesteps | 37931008 | +| train/ | | +| approx_kl | 0.016844884 | +| clip_fraction | 0.348 | +| clip_range | 0.0655 | +| entropy_loss | -5.25 | +| explained_variance | 0.123 | +| learning_rate | 4.1e-05 | +| loss | -0.029 | +| n_updates | 89900 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000115 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1389 | +| iterations | 18522 | +| time_elapsed | 27302 | +| total_timesteps | 37933056 | +| train/ | | +| approx_kl | 0.015899181 | +| clip_fraction | 0.379 | +| clip_range | 0.0655 | +| entropy_loss | -5.77 | +| explained_variance | 0.135 | +| learning_rate | 4.1e-05 | +| loss | -0.0316 | +| n_updates | 89904 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.00018 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1389 | +| iterations | 18523 | +| time_elapsed | 27303 | +| total_timesteps | 37935104 | +| train/ | | +| approx_kl | 0.015640242 | +| clip_fraction | 0.36 | +| clip_range | 0.0655 | +| entropy_loss | -6.08 | +| explained_variance | 0.377 | +| learning_rate | 4.1e-05 | +| loss | -0.0334 | +| n_updates | 89908 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000104 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1389 | +| iterations | 18524 | +| time_elapsed | 27305 | +| total_timesteps | 37937152 | +| train/ | | +| approx_kl | 0.014052491 | +| clip_fraction | 0.337 | +| clip_range | 0.0655 | +| entropy_loss | -6.16 | +| explained_variance | 0.355 | +| learning_rate | 4.1e-05 | +| loss | -0.0317 | +| n_updates | 89912 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000119 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1389 | +| iterations | 18525 | +| time_elapsed | 27306 | +| total_timesteps | 37939200 | +| train/ | | +| approx_kl | 0.012515262 | +| clip_fraction | 0.36 | +| clip_range | 0.0655 | +| entropy_loss | -6.19 | +| explained_variance | -0.00754 | +| learning_rate | 4.1e-05 | +| loss | -0.0288 | +| n_updates | 89916 | +| policy_gradient_loss | -0.0191 | +| value_loss | 9.73e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1389 | +| iterations | 18526 | +| time_elapsed | 27308 | +| total_timesteps | 37941248 | +| train/ | | +| approx_kl | 0.0120814815 | +| clip_fraction | 0.33 | +| clip_range | 0.0655 | +| entropy_loss | -6.19 | +| explained_variance | 0.411 | +| learning_rate | 4.1e-05 | +| loss | -0.0245 | +| n_updates | 89920 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000109 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1389 | +| iterations | 18527 | +| time_elapsed | 27309 | +| total_timesteps | 37943296 | +| train/ | | +| approx_kl | 0.014239602 | +| clip_fraction | 0.295 | +| clip_range | 0.0655 | +| entropy_loss | -5.07 | +| explained_variance | 0.662 | +| learning_rate | 4.1e-05 | +| loss | -0.0226 | +| n_updates | 89924 | +| policy_gradient_loss | -0.0145 | +| value_loss | 0.000192 | +----------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1389 | +| iterations | 18528 | +| time_elapsed | 27311 | +| total_timesteps | 37945344 | +| train/ | | +| approx_kl | 0.016266 | +| clip_fraction | 0.371 | +| clip_range | 0.0655 | +| entropy_loss | -5.42 | +| explained_variance | -0.345 | +| learning_rate | 4.1e-05 | +| loss | -0.0297 | +| n_updates | 89928 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000101 | +-------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1389 | +| iterations | 18529 | +| time_elapsed | 27313 | +| total_timesteps | 37947392 | +| train/ | | +| approx_kl | 0.013209054 | +| clip_fraction | 0.336 | +| clip_range | 0.0655 | +| entropy_loss | -5.15 | +| explained_variance | 0.483 | +| learning_rate | 4.1e-05 | +| loss | -0.0233 | +| n_updates | 89932 | +| policy_gradient_loss | -0.0148 | +| value_loss | 0.000199 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1389 | +| iterations | 18530 | +| time_elapsed | 27314 | +| total_timesteps | 37949440 | +| train/ | | +| approx_kl | 0.015580045 | +| clip_fraction | 0.351 | +| clip_range | 0.0655 | +| entropy_loss | -4.44 | +| explained_variance | 0.777 | +| learning_rate | 4.1e-05 | +| loss | -0.0295 | +| n_updates | 89936 | +| policy_gradient_loss | -0.0176 | +| value_loss | 8.23e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1389 | +| iterations | 18531 | +| time_elapsed | 27316 | +| total_timesteps | 37951488 | +| train/ | | +| approx_kl | 0.014939308 | +| clip_fraction | 0.362 | +| clip_range | 0.0655 | +| entropy_loss | -4.87 | +| explained_variance | 0.267 | +| learning_rate | 4.1e-05 | +| loss | -0.0283 | +| n_updates | 89940 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000124 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1389 | +| iterations | 18532 | +| time_elapsed | 27317 | +| total_timesteps | 37953536 | +| train/ | | +| approx_kl | 0.015088333 | +| clip_fraction | 0.359 | +| clip_range | 0.0655 | +| entropy_loss | -6.16 | +| explained_variance | 0.0591 | +| learning_rate | 4.1e-05 | +| loss | -0.0331 | +| n_updates | 89944 | +| policy_gradient_loss | -0.017 | +| value_loss | 7.8e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1389 | +| iterations | 18533 | +| time_elapsed | 27319 | +| total_timesteps | 37955584 | +| train/ | | +| approx_kl | 0.013435173 | +| clip_fraction | 0.352 | +| clip_range | 0.0655 | +| entropy_loss | -6.03 | +| explained_variance | 0.465 | +| learning_rate | 4.1e-05 | +| loss | -0.0291 | +| n_updates | 89948 | +| policy_gradient_loss | -0.0186 | +| value_loss | 9.35e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1389 | +| iterations | 18534 | +| time_elapsed | 27320 | +| total_timesteps | 37957632 | +| train/ | | +| approx_kl | 0.017149713 | +| clip_fraction | 0.37 | +| clip_range | 0.0655 | +| entropy_loss | -6.09 | +| explained_variance | -0.0227 | +| learning_rate | 4.1e-05 | +| loss | -0.0284 | +| n_updates | 89952 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000141 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1389 | +| iterations | 18535 | +| time_elapsed | 27322 | +| total_timesteps | 37959680 | +| train/ | | +| approx_kl | 0.01435801 | +| clip_fraction | 0.367 | +| clip_range | 0.0655 | +| entropy_loss | -6.44 | +| explained_variance | -0.167 | +| learning_rate | 4.1e-05 | +| loss | -0.034 | +| n_updates | 89956 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000105 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1389 | +| iterations | 18536 | +| time_elapsed | 27323 | +| total_timesteps | 37961728 | +| train/ | | +| approx_kl | 0.014768345 | +| clip_fraction | 0.343 | +| clip_range | 0.0655 | +| entropy_loss | -6.29 | +| explained_variance | 0.0155 | +| learning_rate | 4.1e-05 | +| loss | -0.0302 | +| n_updates | 89960 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000134 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1389 | +| iterations | 18537 | +| time_elapsed | 27325 | +| total_timesteps | 37963776 | +| train/ | | +| approx_kl | 0.013639138 | +| clip_fraction | 0.3 | +| clip_range | 0.0655 | +| entropy_loss | -4.23 | +| explained_variance | 0.918 | +| learning_rate | 4.1e-05 | +| loss | -0.0265 | +| n_updates | 89964 | +| policy_gradient_loss | -0.0137 | +| value_loss | 4.85e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1389 | +| iterations | 18538 | +| time_elapsed | 27326 | +| total_timesteps | 37965824 | +| train/ | | +| approx_kl | 0.011797688 | +| clip_fraction | 0.334 | +| clip_range | 0.0655 | +| entropy_loss | -5 | +| explained_variance | 0.619 | +| learning_rate | 4.1e-05 | +| loss | -0.0211 | +| n_updates | 89968 | +| policy_gradient_loss | -0.015 | +| value_loss | 6.6e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1389 | +| iterations | 18539 | +| time_elapsed | 27328 | +| total_timesteps | 37967872 | +| train/ | | +| approx_kl | 0.012879792 | +| clip_fraction | 0.336 | +| clip_range | 0.0655 | +| entropy_loss | -5.7 | +| explained_variance | 0.515 | +| learning_rate | 4.1e-05 | +| loss | -0.0255 | +| n_updates | 89972 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000121 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1389 | +| iterations | 18540 | +| time_elapsed | 27329 | +| total_timesteps | 37969920 | +| train/ | | +| approx_kl | 0.012713391 | +| clip_fraction | 0.342 | +| clip_range | 0.0655 | +| entropy_loss | -5.5 | +| explained_variance | 0.685 | +| learning_rate | 4.1e-05 | +| loss | -0.0303 | +| n_updates | 89976 | +| policy_gradient_loss | -0.0166 | +| value_loss | 7.4e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 1389 | +| iterations | 18541 | +| time_elapsed | 27331 | +| total_timesteps | 37971968 | +| train/ | | +| approx_kl | 0.01650887 | +| clip_fraction | 0.374 | +| clip_range | 0.0655 | +| entropy_loss | -5.65 | +| explained_variance | -0.0553 | +| learning_rate | 4.1e-05 | +| loss | -0.0261 | +| n_updates | 89980 | +| policy_gradient_loss | -0.0187 | +| value_loss | 5.88e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1389 | +| iterations | 18542 | +| time_elapsed | 27332 | +| total_timesteps | 37974016 | +| train/ | | +| approx_kl | 0.012873862 | +| clip_fraction | 0.33 | +| clip_range | 0.0655 | +| entropy_loss | -5.86 | +| explained_variance | 0.576 | +| learning_rate | 4.1e-05 | +| loss | -0.0206 | +| n_updates | 89984 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.00016 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 1389 | +| iterations | 18543 | +| time_elapsed | 27334 | +| total_timesteps | 37976064 | +| train/ | | +| approx_kl | 0.010123158 | +| clip_fraction | 0.313 | +| clip_range | 0.0655 | +| entropy_loss | -5.46 | +| explained_variance | 0.392 | +| learning_rate | 4.1e-05 | +| loss | -0.0228 | +| n_updates | 89988 | +| policy_gradient_loss | -0.0142 | +| value_loss | 0.000223 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1389 | +| iterations | 18544 | +| time_elapsed | 27335 | +| total_timesteps | 37978112 | +| train/ | | +| approx_kl | 0.010882283 | +| clip_fraction | 0.327 | +| clip_range | 0.0655 | +| entropy_loss | -6.08 | +| explained_variance | 0.286 | +| learning_rate | 4.1e-05 | +| loss | -0.0293 | +| n_updates | 89992 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000181 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1389 | +| iterations | 18545 | +| time_elapsed | 27337 | +| total_timesteps | 37980160 | +| train/ | | +| approx_kl | 0.0111704245 | +| clip_fraction | 0.344 | +| clip_range | 0.0655 | +| entropy_loss | -6.31 | +| explained_variance | 0.276 | +| learning_rate | 4.1e-05 | +| loss | -0.0246 | +| n_updates | 89996 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000187 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.304 | +| time/ | | +| fps | 1389 | +| iterations | 18546 | +| time_elapsed | 27339 | +| total_timesteps | 37982208 | +| train/ | | +| approx_kl | 0.010848481 | +| clip_fraction | 0.339 | +| clip_range | 0.0655 | +| entropy_loss | -5.81 | +| explained_variance | 0.252 | +| learning_rate | 4.1e-05 | +| loss | -0.019 | +| n_updates | 90000 | +| policy_gradient_loss | -0.0136 | +| value_loss | 0.000233 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 1389 | +| iterations | 18547 | +| time_elapsed | 27340 | +| total_timesteps | 37984256 | +| train/ | | +| approx_kl | 0.012918685 | +| clip_fraction | 0.331 | +| clip_range | 0.0655 | +| entropy_loss | -4.75 | +| explained_variance | 0.631 | +| learning_rate | 4.1e-05 | +| loss | -0.0222 | +| n_updates | 90004 | +| policy_gradient_loss | -0.0146 | +| value_loss | 0.000161 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.297 | +| time/ | | +| fps | 1389 | +| iterations | 18548 | +| time_elapsed | 27342 | +| total_timesteps | 37986304 | +| train/ | | +| approx_kl | 0.015821807 | +| clip_fraction | 0.367 | +| clip_range | 0.0655 | +| entropy_loss | -5.26 | +| explained_variance | 0.579 | +| learning_rate | 4.1e-05 | +| loss | -0.0307 | +| n_updates | 90008 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000101 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.3 | +| time/ | | +| fps | 1389 | +| iterations | 18549 | +| time_elapsed | 27343 | +| total_timesteps | 37988352 | +| train/ | | +| approx_kl | 0.0142631885 | +| clip_fraction | 0.357 | +| clip_range | 0.0655 | +| entropy_loss | -5.32 | +| explained_variance | 0.645 | +| learning_rate | 4.1e-05 | +| loss | -0.0276 | +| n_updates | 90012 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000108 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.297 | +| time/ | | +| fps | 1389 | +| iterations | 18550 | +| time_elapsed | 27345 | +| total_timesteps | 37990400 | +| train/ | | +| approx_kl | 0.01163538 | +| clip_fraction | 0.334 | +| clip_range | 0.0655 | +| entropy_loss | -5.77 | +| explained_variance | 0.471 | +| learning_rate | 4.1e-05 | +| loss | -0.0273 | +| n_updates | 90016 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000123 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.3 | +| time/ | | +| fps | 1389 | +| iterations | 18551 | +| time_elapsed | 27346 | +| total_timesteps | 37992448 | +| train/ | | +| approx_kl | 0.010349955 | +| clip_fraction | 0.307 | +| clip_range | 0.0655 | +| entropy_loss | -5.81 | +| explained_variance | 0.456 | +| learning_rate | 4.1e-05 | +| loss | -0.0259 | +| n_updates | 90020 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.00023 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.3 | +| time/ | | +| fps | 1389 | +| iterations | 18552 | +| time_elapsed | 27348 | +| total_timesteps | 37994496 | +| train/ | | +| approx_kl | 0.010268325 | +| clip_fraction | 0.32 | +| clip_range | 0.0655 | +| entropy_loss | -5.24 | +| explained_variance | 0.284 | +| learning_rate | 4.1e-05 | +| loss | -0.0315 | +| n_updates | 90024 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000226 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.304 | +| time/ | | +| fps | 1389 | +| iterations | 18553 | +| time_elapsed | 27349 | +| total_timesteps | 37996544 | +| train/ | | +| approx_kl | 0.012776978 | +| clip_fraction | 0.345 | +| clip_range | 0.0655 | +| entropy_loss | -5.64 | +| explained_variance | -0.485 | +| learning_rate | 4.1e-05 | +| loss | -0.03 | +| n_updates | 90028 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000124 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1389 | +| iterations | 18554 | +| time_elapsed | 27351 | +| total_timesteps | 37998592 | +| train/ | | +| approx_kl | 0.01419005 | +| clip_fraction | 0.35 | +| clip_range | 0.0655 | +| entropy_loss | -5.72 | +| explained_variance | 0.301 | +| learning_rate | 4.1e-05 | +| loss | -0.0266 | +| n_updates | 90032 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000251 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1389 | +| iterations | 18555 | +| time_elapsed | 27352 | +| total_timesteps | 38000640 | +| train/ | | +| approx_kl | 0.014924154 | +| clip_fraction | 0.333 | +| clip_range | 0.0655 | +| entropy_loss | -4.87 | +| explained_variance | 0.365 | +| learning_rate | 4.1e-05 | +| loss | -0.0219 | +| n_updates | 90036 | +| policy_gradient_loss | -0.0142 | +| value_loss | 0.000403 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1389 | +| iterations | 18556 | +| time_elapsed | 27354 | +| total_timesteps | 38002688 | +| train/ | | +| approx_kl | 0.0123431645 | +| clip_fraction | 0.34 | +| clip_range | 0.0655 | +| entropy_loss | -5.41 | +| explained_variance | 0.308 | +| learning_rate | 4.1e-05 | +| loss | -0.0295 | +| n_updates | 90040 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000294 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1389 | +| iterations | 18557 | +| time_elapsed | 27355 | +| total_timesteps | 38004736 | +| train/ | | +| approx_kl | 0.013404198 | +| clip_fraction | 0.332 | +| clip_range | 0.0655 | +| entropy_loss | -5.55 | +| explained_variance | 0.264 | +| learning_rate | 4.1e-05 | +| loss | -0.024 | +| n_updates | 90044 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.0002 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1389 | +| iterations | 18558 | +| time_elapsed | 27357 | +| total_timesteps | 38006784 | +| train/ | | +| approx_kl | 0.014579556 | +| clip_fraction | 0.335 | +| clip_range | 0.0655 | +| entropy_loss | -5.67 | +| explained_variance | 0.29 | +| learning_rate | 4.1e-05 | +| loss | -0.0241 | +| n_updates | 90048 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000157 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 1389 | +| iterations | 18559 | +| time_elapsed | 27358 | +| total_timesteps | 38008832 | +| train/ | | +| approx_kl | 0.016742188 | +| clip_fraction | 0.354 | +| clip_range | 0.0655 | +| entropy_loss | -5.93 | +| explained_variance | 0.239 | +| learning_rate | 4.1e-05 | +| loss | -0.0303 | +| n_updates | 90052 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000183 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 1389 | +| iterations | 18560 | +| time_elapsed | 27360 | +| total_timesteps | 38010880 | +| train/ | | +| approx_kl | 0.011993237 | +| clip_fraction | 0.329 | +| clip_range | 0.0655 | +| entropy_loss | -5.88 | +| explained_variance | 0.617 | +| learning_rate | 4.1e-05 | +| loss | -0.0285 | +| n_updates | 90056 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000102 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1389 | +| iterations | 18561 | +| time_elapsed | 27361 | +| total_timesteps | 38012928 | +| train/ | | +| approx_kl | 0.013482865 | +| clip_fraction | 0.325 | +| clip_range | 0.0655 | +| entropy_loss | -5.9 | +| explained_variance | 0.282 | +| learning_rate | 4.1e-05 | +| loss | -0.0268 | +| n_updates | 90060 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000151 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1389 | +| iterations | 18562 | +| time_elapsed | 27363 | +| total_timesteps | 38014976 | +| train/ | | +| approx_kl | 0.012552907 | +| clip_fraction | 0.33 | +| clip_range | 0.0655 | +| entropy_loss | -6.33 | +| explained_variance | 0.187 | +| learning_rate | 4.1e-05 | +| loss | -0.0295 | +| n_updates | 90064 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000427 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 1389 | +| iterations | 18563 | +| time_elapsed | 27364 | +| total_timesteps | 38017024 | +| train/ | | +| approx_kl | 0.014402462 | +| clip_fraction | 0.339 | +| clip_range | 0.0655 | +| entropy_loss | -5.74 | +| explained_variance | 0.407 | +| learning_rate | 4.1e-05 | +| loss | -0.0188 | +| n_updates | 90068 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000206 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1389 | +| iterations | 18564 | +| time_elapsed | 27366 | +| total_timesteps | 38019072 | +| train/ | | +| approx_kl | 0.011843676 | +| clip_fraction | 0.347 | +| clip_range | 0.0655 | +| entropy_loss | -5.43 | +| explained_variance | 0.694 | +| learning_rate | 4.1e-05 | +| loss | -0.0346 | +| n_updates | 90072 | +| policy_gradient_loss | -0.0203 | +| value_loss | 7.6e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1389 | +| iterations | 18565 | +| time_elapsed | 27367 | +| total_timesteps | 38021120 | +| train/ | | +| approx_kl | 0.012728959 | +| clip_fraction | 0.35 | +| clip_range | 0.0655 | +| entropy_loss | -5.64 | +| explained_variance | 0.562 | +| learning_rate | 4.1e-05 | +| loss | -0.0292 | +| n_updates | 90076 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.00016 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1389 | +| iterations | 18566 | +| time_elapsed | 27369 | +| total_timesteps | 38023168 | +| train/ | | +| approx_kl | 0.011382209 | +| clip_fraction | 0.348 | +| clip_range | 0.0655 | +| entropy_loss | -6.02 | +| explained_variance | -0.0496 | +| learning_rate | 4.1e-05 | +| loss | -0.026 | +| n_updates | 90080 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.00016 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1389 | +| iterations | 18567 | +| time_elapsed | 27370 | +| total_timesteps | 38025216 | +| train/ | | +| approx_kl | 0.011331307 | +| clip_fraction | 0.298 | +| clip_range | 0.0655 | +| entropy_loss | -6.22 | +| explained_variance | 0.459 | +| learning_rate | 4.1e-05 | +| loss | -0.0259 | +| n_updates | 90084 | +| policy_gradient_loss | -0.0144 | +| value_loss | 0.000162 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.315 | +| time/ | | +| fps | 1389 | +| iterations | 18568 | +| time_elapsed | 27372 | +| total_timesteps | 38027264 | +| train/ | | +| approx_kl | 0.015816588 | +| clip_fraction | 0.347 | +| clip_range | 0.0655 | +| entropy_loss | -4.97 | +| explained_variance | 0.565 | +| learning_rate | 4.1e-05 | +| loss | -0.0271 | +| n_updates | 90088 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.00016 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.315 | +| time/ | | +| fps | 1389 | +| iterations | 18569 | +| time_elapsed | 27373 | +| total_timesteps | 38029312 | +| train/ | | +| approx_kl | 0.016318057 | +| clip_fraction | 0.385 | +| clip_range | 0.0655 | +| entropy_loss | -4.92 | +| explained_variance | 0.452 | +| learning_rate | 4.1e-05 | +| loss | -0.0239 | +| n_updates | 90092 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000182 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1389 | +| iterations | 18570 | +| time_elapsed | 27375 | +| total_timesteps | 38031360 | +| train/ | | +| approx_kl | 0.015056824 | +| clip_fraction | 0.382 | +| clip_range | 0.0655 | +| entropy_loss | -5.59 | +| explained_variance | 0.56 | +| learning_rate | 4.1e-05 | +| loss | -0.0339 | +| n_updates | 90096 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000105 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1389 | +| iterations | 18571 | +| time_elapsed | 27376 | +| total_timesteps | 38033408 | +| train/ | | +| approx_kl | 0.014470462 | +| clip_fraction | 0.375 | +| clip_range | 0.0655 | +| entropy_loss | -6.09 | +| explained_variance | 0.566 | +| learning_rate | 4.1e-05 | +| loss | -0.0273 | +| n_updates | 90100 | +| policy_gradient_loss | -0.0206 | +| value_loss | 6.17e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1389 | +| iterations | 18572 | +| time_elapsed | 27378 | +| total_timesteps | 38035456 | +| train/ | | +| approx_kl | 0.012387162 | +| clip_fraction | 0.347 | +| clip_range | 0.0655 | +| entropy_loss | -6.19 | +| explained_variance | 0.26 | +| learning_rate | 4.1e-05 | +| loss | -0.0256 | +| n_updates | 90104 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000164 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1389 | +| iterations | 18573 | +| time_elapsed | 27380 | +| total_timesteps | 38037504 | +| train/ | | +| approx_kl | 0.012500043 | +| clip_fraction | 0.351 | +| clip_range | 0.0655 | +| entropy_loss | -6.03 | +| explained_variance | 0.612 | +| learning_rate | 4.1e-05 | +| loss | -0.0288 | +| n_updates | 90108 | +| policy_gradient_loss | -0.0181 | +| value_loss | 7.41e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1389 | +| iterations | 18574 | +| time_elapsed | 27381 | +| total_timesteps | 38039552 | +| train/ | | +| approx_kl | 0.011512121 | +| clip_fraction | 0.32 | +| clip_range | 0.0655 | +| entropy_loss | -5.54 | +| explained_variance | 0.367 | +| learning_rate | 4.1e-05 | +| loss | -0.0264 | +| n_updates | 90112 | +| policy_gradient_loss | -0.014 | +| value_loss | 0.00025 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1389 | +| iterations | 18575 | +| time_elapsed | 27383 | +| total_timesteps | 38041600 | +| train/ | | +| approx_kl | 0.013183071 | +| clip_fraction | 0.333 | +| clip_range | 0.0655 | +| entropy_loss | -5.5 | +| explained_variance | 0.293 | +| learning_rate | 4.1e-05 | +| loss | -0.0275 | +| n_updates | 90116 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000208 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1389 | +| iterations | 18576 | +| time_elapsed | 27384 | +| total_timesteps | 38043648 | +| train/ | | +| approx_kl | 0.014412389 | +| clip_fraction | 0.335 | +| clip_range | 0.0655 | +| entropy_loss | -5.02 | +| explained_variance | 0.476 | +| learning_rate | 4.1e-05 | +| loss | -0.0252 | +| n_updates | 90120 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000252 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1389 | +| iterations | 18577 | +| time_elapsed | 27386 | +| total_timesteps | 38045696 | +| train/ | | +| approx_kl | 0.01290055 | +| clip_fraction | 0.359 | +| clip_range | 0.0655 | +| entropy_loss | -5.25 | +| explained_variance | 0.487 | +| learning_rate | 4.1e-05 | +| loss | -0.0306 | +| n_updates | 90124 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000118 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1389 | +| iterations | 18578 | +| time_elapsed | 27387 | +| total_timesteps | 38047744 | +| train/ | | +| approx_kl | 0.013342711 | +| clip_fraction | 0.344 | +| clip_range | 0.0655 | +| entropy_loss | -5.82 | +| explained_variance | 0.369 | +| learning_rate | 4.1e-05 | +| loss | -0.0304 | +| n_updates | 90128 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000187 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1389 | +| iterations | 18579 | +| time_elapsed | 27389 | +| total_timesteps | 38049792 | +| train/ | | +| approx_kl | 0.00972422 | +| clip_fraction | 0.303 | +| clip_range | 0.0655 | +| entropy_loss | -6.01 | +| explained_variance | 0.493 | +| learning_rate | 4.1e-05 | +| loss | -0.0226 | +| n_updates | 90132 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000161 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1389 | +| iterations | 18580 | +| time_elapsed | 27390 | +| total_timesteps | 38051840 | +| train/ | | +| approx_kl | 0.011562034 | +| clip_fraction | 0.313 | +| clip_range | 0.0655 | +| entropy_loss | -5.55 | +| explained_variance | 0.474 | +| learning_rate | 4.1e-05 | +| loss | -0.0283 | +| n_updates | 90136 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000134 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1389 | +| iterations | 18581 | +| time_elapsed | 27392 | +| total_timesteps | 38053888 | +| train/ | | +| approx_kl | 0.01280652 | +| clip_fraction | 0.348 | +| clip_range | 0.0655 | +| entropy_loss | -5.53 | +| explained_variance | 0.436 | +| learning_rate | 4.1e-05 | +| loss | -0.0292 | +| n_updates | 90140 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000135 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1389 | +| iterations | 18582 | +| time_elapsed | 27393 | +| total_timesteps | 38055936 | +| train/ | | +| approx_kl | 0.012265017 | +| clip_fraction | 0.323 | +| clip_range | 0.0655 | +| entropy_loss | -6.08 | +| explained_variance | 0.412 | +| learning_rate | 4.1e-05 | +| loss | -0.0284 | +| n_updates | 90144 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.00017 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1389 | +| iterations | 18583 | +| time_elapsed | 27395 | +| total_timesteps | 38057984 | +| train/ | | +| approx_kl | 0.014069363 | +| clip_fraction | 0.325 | +| clip_range | 0.0655 | +| entropy_loss | -6.04 | +| explained_variance | 0.237 | +| learning_rate | 4.1e-05 | +| loss | -0.0277 | +| n_updates | 90148 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000226 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1389 | +| iterations | 18584 | +| time_elapsed | 27396 | +| total_timesteps | 38060032 | +| train/ | | +| approx_kl | 0.010151057 | +| clip_fraction | 0.295 | +| clip_range | 0.0655 | +| entropy_loss | -5.8 | +| explained_variance | 0.306 | +| learning_rate | 4.1e-05 | +| loss | -0.0249 | +| n_updates | 90152 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000549 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1389 | +| iterations | 18585 | +| time_elapsed | 27398 | +| total_timesteps | 38062080 | +| train/ | | +| approx_kl | 0.012355935 | +| clip_fraction | 0.331 | +| clip_range | 0.0655 | +| entropy_loss | -5.07 | +| explained_variance | 0.473 | +| learning_rate | 4.1e-05 | +| loss | -0.0341 | +| n_updates | 90156 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000114 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1389 | +| iterations | 18586 | +| time_elapsed | 27399 | +| total_timesteps | 38064128 | +| train/ | | +| approx_kl | 0.016015224 | +| clip_fraction | 0.356 | +| clip_range | 0.0655 | +| entropy_loss | -5.18 | +| explained_variance | 0.137 | +| learning_rate | 4.1e-05 | +| loss | -0.0275 | +| n_updates | 90160 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000147 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1389 | +| iterations | 18587 | +| time_elapsed | 27401 | +| total_timesteps | 38066176 | +| train/ | | +| approx_kl | 0.012812395 | +| clip_fraction | 0.334 | +| clip_range | 0.0655 | +| entropy_loss | -5.51 | +| explained_variance | 0.405 | +| learning_rate | 4.1e-05 | +| loss | -0.0285 | +| n_updates | 90164 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.0002 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1389 | +| iterations | 18588 | +| time_elapsed | 27402 | +| total_timesteps | 38068224 | +| train/ | | +| approx_kl | 0.013075912 | +| clip_fraction | 0.355 | +| clip_range | 0.0655 | +| entropy_loss | -5.77 | +| explained_variance | 0.417 | +| learning_rate | 4.1e-05 | +| loss | -0.0265 | +| n_updates | 90168 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000113 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1389 | +| iterations | 18589 | +| time_elapsed | 27404 | +| total_timesteps | 38070272 | +| train/ | | +| approx_kl | 0.012660441 | +| clip_fraction | 0.346 | +| clip_range | 0.0655 | +| entropy_loss | -6.39 | +| explained_variance | 0.216 | +| learning_rate | 4.1e-05 | +| loss | -0.0306 | +| n_updates | 90172 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000157 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1389 | +| iterations | 18590 | +| time_elapsed | 27405 | +| total_timesteps | 38072320 | +| train/ | | +| approx_kl | 0.012999998 | +| clip_fraction | 0.331 | +| clip_range | 0.0655 | +| entropy_loss | -4.85 | +| explained_variance | 0.555 | +| learning_rate | 4.1e-05 | +| loss | -0.0149 | +| n_updates | 90176 | +| policy_gradient_loss | -0.0129 | +| value_loss | 0.000244 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1389 | +| iterations | 18591 | +| time_elapsed | 27407 | +| total_timesteps | 38074368 | +| train/ | | +| approx_kl | 0.014885324 | +| clip_fraction | 0.321 | +| clip_range | 0.0655 | +| entropy_loss | -5.05 | +| explained_variance | 0.58 | +| learning_rate | 4.1e-05 | +| loss | -0.0283 | +| n_updates | 90180 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000143 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1389 | +| iterations | 18592 | +| time_elapsed | 27408 | +| total_timesteps | 38076416 | +| train/ | | +| approx_kl | 0.012614872 | +| clip_fraction | 0.347 | +| clip_range | 0.0655 | +| entropy_loss | -5.35 | +| explained_variance | 0.498 | +| learning_rate | 4.1e-05 | +| loss | -0.0229 | +| n_updates | 90184 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000158 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1389 | +| iterations | 18593 | +| time_elapsed | 27410 | +| total_timesteps | 38078464 | +| train/ | | +| approx_kl | 0.013987258 | +| clip_fraction | 0.345 | +| clip_range | 0.0655 | +| entropy_loss | -5.69 | +| explained_variance | 0.317 | +| learning_rate | 4.1e-05 | +| loss | -0.0296 | +| n_updates | 90188 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000124 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1389 | +| iterations | 18594 | +| time_elapsed | 27412 | +| total_timesteps | 38080512 | +| train/ | | +| approx_kl | 0.011842901 | +| clip_fraction | 0.329 | +| clip_range | 0.0655 | +| entropy_loss | -5.8 | +| explained_variance | 0.46 | +| learning_rate | 4.1e-05 | +| loss | -0.0236 | +| n_updates | 90192 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000146 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1389 | +| iterations | 18595 | +| time_elapsed | 27413 | +| total_timesteps | 38082560 | +| train/ | | +| approx_kl | 0.009292118 | +| clip_fraction | 0.333 | +| clip_range | 0.0655 | +| entropy_loss | -5.61 | +| explained_variance | 0.358 | +| learning_rate | 4.1e-05 | +| loss | -0.0225 | +| n_updates | 90196 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.00027 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1389 | +| iterations | 18596 | +| time_elapsed | 27415 | +| total_timesteps | 38084608 | +| train/ | | +| approx_kl | 0.010298999 | +| clip_fraction | 0.332 | +| clip_range | 0.0655 | +| entropy_loss | -5.22 | +| explained_variance | 0.425 | +| learning_rate | 4.1e-05 | +| loss | -0.0196 | +| n_updates | 90200 | +| policy_gradient_loss | -0.0136 | +| value_loss | 0.000361 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1389 | +| iterations | 18597 | +| time_elapsed | 27416 | +| total_timesteps | 38086656 | +| train/ | | +| approx_kl | 0.015422559 | +| clip_fraction | 0.406 | +| clip_range | 0.0655 | +| entropy_loss | -5.39 | +| explained_variance | 0.564 | +| learning_rate | 4.1e-05 | +| loss | -0.0337 | +| n_updates | 90204 | +| policy_gradient_loss | -0.0224 | +| value_loss | 8.48e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1389 | +| iterations | 18598 | +| time_elapsed | 27418 | +| total_timesteps | 38088704 | +| train/ | | +| approx_kl | 0.013527816 | +| clip_fraction | 0.362 | +| clip_range | 0.0655 | +| entropy_loss | -5.19 | +| explained_variance | 0.497 | +| learning_rate | 4.1e-05 | +| loss | -0.0222 | +| n_updates | 90208 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000132 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1389 | +| iterations | 18599 | +| time_elapsed | 27419 | +| total_timesteps | 38090752 | +| train/ | | +| approx_kl | 0.015655208 | +| clip_fraction | 0.374 | +| clip_range | 0.0655 | +| entropy_loss | -5.55 | +| explained_variance | 0.306 | +| learning_rate | 4.1e-05 | +| loss | -0.025 | +| n_updates | 90212 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000166 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1389 | +| iterations | 18600 | +| time_elapsed | 27421 | +| total_timesteps | 38092800 | +| train/ | | +| approx_kl | 0.012637369 | +| clip_fraction | 0.328 | +| clip_range | 0.0655 | +| entropy_loss | -5.22 | +| explained_variance | 0.472 | +| learning_rate | 4.1e-05 | +| loss | -0.0291 | +| n_updates | 90216 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.000218 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1389 | +| iterations | 18601 | +| time_elapsed | 27422 | +| total_timesteps | 38094848 | +| train/ | | +| approx_kl | 0.01107147 | +| clip_fraction | 0.313 | +| clip_range | 0.0655 | +| entropy_loss | -5.9 | +| explained_variance | 0.248 | +| learning_rate | 4.1e-05 | +| loss | -0.0242 | +| n_updates | 90220 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000192 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1389 | +| iterations | 18602 | +| time_elapsed | 27424 | +| total_timesteps | 38096896 | +| train/ | | +| approx_kl | 0.013054644 | +| clip_fraction | 0.347 | +| clip_range | 0.0655 | +| entropy_loss | -5.48 | +| explained_variance | 0.69 | +| learning_rate | 4.1e-05 | +| loss | -0.0288 | +| n_updates | 90224 | +| policy_gradient_loss | -0.0187 | +| value_loss | 6.15e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1389 | +| iterations | 18603 | +| time_elapsed | 27426 | +| total_timesteps | 38098944 | +| train/ | | +| approx_kl | 0.014330961 | +| clip_fraction | 0.327 | +| clip_range | 0.0655 | +| entropy_loss | -5.38 | +| explained_variance | 0.525 | +| learning_rate | 4.1e-05 | +| loss | -0.0175 | +| n_updates | 90228 | +| policy_gradient_loss | -0.0138 | +| value_loss | 0.000223 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1389 | +| iterations | 18604 | +| time_elapsed | 27427 | +| total_timesteps | 38100992 | +| train/ | | +| approx_kl | 0.0152735505 | +| clip_fraction | 0.374 | +| clip_range | 0.0655 | +| entropy_loss | -5.97 | +| explained_variance | 0.189 | +| learning_rate | 4.1e-05 | +| loss | -0.0296 | +| n_updates | 90232 | +| policy_gradient_loss | -0.0177 | +| value_loss | 8.31e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1389 | +| iterations | 18605 | +| time_elapsed | 27429 | +| total_timesteps | 38103040 | +| train/ | | +| approx_kl | 0.012808016 | +| clip_fraction | 0.375 | +| clip_range | 0.0655 | +| entropy_loss | -6.41 | +| explained_variance | -0.00252 | +| learning_rate | 4.1e-05 | +| loss | -0.0306 | +| n_updates | 90236 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000147 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1389 | +| iterations | 18606 | +| time_elapsed | 27430 | +| total_timesteps | 38105088 | +| train/ | | +| approx_kl | 0.012236785 | +| clip_fraction | 0.347 | +| clip_range | 0.0655 | +| entropy_loss | -5.92 | +| explained_variance | 0.161 | +| learning_rate | 4.1e-05 | +| loss | -0.0224 | +| n_updates | 90240 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000347 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1389 | +| iterations | 18607 | +| time_elapsed | 27432 | +| total_timesteps | 38107136 | +| train/ | | +| approx_kl | 0.016096054 | +| clip_fraction | 0.352 | +| clip_range | 0.0655 | +| entropy_loss | -5.34 | +| explained_variance | 0.281 | +| learning_rate | 4.1e-05 | +| loss | -0.028 | +| n_updates | 90244 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000154 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1389 | +| iterations | 18608 | +| time_elapsed | 27433 | +| total_timesteps | 38109184 | +| train/ | | +| approx_kl | 0.013355853 | +| clip_fraction | 0.322 | +| clip_range | 0.0655 | +| entropy_loss | -5.28 | +| explained_variance | 0.466 | +| learning_rate | 4.09e-05 | +| loss | -0.0202 | +| n_updates | 90248 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000205 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1389 | +| iterations | 18609 | +| time_elapsed | 27435 | +| total_timesteps | 38111232 | +| train/ | | +| approx_kl | 0.01160885 | +| clip_fraction | 0.327 | +| clip_range | 0.0655 | +| entropy_loss | -5.19 | +| explained_variance | 0.422 | +| learning_rate | 4.09e-05 | +| loss | -0.0263 | +| n_updates | 90252 | +| policy_gradient_loss | -0.0135 | +| value_loss | 0.00019 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1389 | +| iterations | 18610 | +| time_elapsed | 27436 | +| total_timesteps | 38113280 | +| train/ | | +| approx_kl | 0.017371234 | +| clip_fraction | 0.358 | +| clip_range | 0.0655 | +| entropy_loss | -4.99 | +| explained_variance | 0.683 | +| learning_rate | 4.09e-05 | +| loss | -0.0303 | +| n_updates | 90256 | +| policy_gradient_loss | -0.0184 | +| value_loss | 9.9e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1389 | +| iterations | 18611 | +| time_elapsed | 27438 | +| total_timesteps | 38115328 | +| train/ | | +| approx_kl | 0.013559039 | +| clip_fraction | 0.332 | +| clip_range | 0.0655 | +| entropy_loss | -5.93 | +| explained_variance | 0.278 | +| learning_rate | 4.09e-05 | +| loss | -0.0251 | +| n_updates | 90260 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000209 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1389 | +| iterations | 18612 | +| time_elapsed | 27439 | +| total_timesteps | 38117376 | +| train/ | | +| approx_kl | 0.015101186 | +| clip_fraction | 0.367 | +| clip_range | 0.0655 | +| entropy_loss | -5.45 | +| explained_variance | 0.48 | +| learning_rate | 4.09e-05 | +| loss | -0.0335 | +| n_updates | 90264 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000153 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1389 | +| iterations | 18613 | +| time_elapsed | 27441 | +| total_timesteps | 38119424 | +| train/ | | +| approx_kl | 0.013990907 | +| clip_fraction | 0.353 | +| clip_range | 0.0655 | +| entropy_loss | -5.62 | +| explained_variance | 0.314 | +| learning_rate | 4.09e-05 | +| loss | -0.0289 | +| n_updates | 90268 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000136 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1389 | +| iterations | 18614 | +| time_elapsed | 27442 | +| total_timesteps | 38121472 | +| train/ | | +| approx_kl | 0.013295485 | +| clip_fraction | 0.36 | +| clip_range | 0.0655 | +| entropy_loss | -5.94 | +| explained_variance | 0.312 | +| learning_rate | 4.09e-05 | +| loss | -0.0287 | +| n_updates | 90272 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000172 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1389 | +| iterations | 18615 | +| time_elapsed | 27444 | +| total_timesteps | 38123520 | +| train/ | | +| approx_kl | 0.0142128635 | +| clip_fraction | 0.353 | +| clip_range | 0.0655 | +| entropy_loss | -5.93 | +| explained_variance | 0.323 | +| learning_rate | 4.09e-05 | +| loss | -0.0344 | +| n_updates | 90276 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000105 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1389 | +| iterations | 18616 | +| time_elapsed | 27445 | +| total_timesteps | 38125568 | +| train/ | | +| approx_kl | 0.01249355 | +| clip_fraction | 0.358 | +| clip_range | 0.0655 | +| entropy_loss | -5.92 | +| explained_variance | 0.307 | +| learning_rate | 4.09e-05 | +| loss | -0.0333 | +| n_updates | 90280 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000158 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1389 | +| iterations | 18617 | +| time_elapsed | 27447 | +| total_timesteps | 38127616 | +| train/ | | +| approx_kl | 0.012672585 | +| clip_fraction | 0.32 | +| clip_range | 0.0655 | +| entropy_loss | -5.43 | +| explained_variance | 0.293 | +| learning_rate | 4.09e-05 | +| loss | -0.0207 | +| n_updates | 90284 | +| policy_gradient_loss | -0.0141 | +| value_loss | 0.000198 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1389 | +| iterations | 18618 | +| time_elapsed | 27448 | +| total_timesteps | 38129664 | +| train/ | | +| approx_kl | 0.013044033 | +| clip_fraction | 0.335 | +| clip_range | 0.0655 | +| entropy_loss | -5.27 | +| explained_variance | 0.492 | +| learning_rate | 4.09e-05 | +| loss | -0.0221 | +| n_updates | 90288 | +| policy_gradient_loss | -0.0141 | +| value_loss | 0.000202 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1389 | +| iterations | 18619 | +| time_elapsed | 27450 | +| total_timesteps | 38131712 | +| train/ | | +| approx_kl | 0.011361128 | +| clip_fraction | 0.356 | +| clip_range | 0.0655 | +| entropy_loss | -5.89 | +| explained_variance | 0.0889 | +| learning_rate | 4.09e-05 | +| loss | -0.0264 | +| n_updates | 90292 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000136 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1389 | +| iterations | 18620 | +| time_elapsed | 27452 | +| total_timesteps | 38133760 | +| train/ | | +| approx_kl | 0.013312156 | +| clip_fraction | 0.34 | +| clip_range | 0.0655 | +| entropy_loss | -5.6 | +| explained_variance | 0.515 | +| learning_rate | 4.09e-05 | +| loss | -0.0297 | +| n_updates | 90296 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000122 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1389 | +| iterations | 18621 | +| time_elapsed | 27453 | +| total_timesteps | 38135808 | +| train/ | | +| approx_kl | 0.012405999 | +| clip_fraction | 0.351 | +| clip_range | 0.0655 | +| entropy_loss | -6.29 | +| explained_variance | 0.44 | +| learning_rate | 4.09e-05 | +| loss | -0.0296 | +| n_updates | 90300 | +| policy_gradient_loss | -0.0175 | +| value_loss | 9.09e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1389 | +| iterations | 18622 | +| time_elapsed | 27455 | +| total_timesteps | 38137856 | +| train/ | | +| approx_kl | 0.013725273 | +| clip_fraction | 0.347 | +| clip_range | 0.0655 | +| entropy_loss | -5.33 | +| explained_variance | 0.609 | +| learning_rate | 4.09e-05 | +| loss | -0.027 | +| n_updates | 90304 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.00014 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1389 | +| iterations | 18623 | +| time_elapsed | 27456 | +| total_timesteps | 38139904 | +| train/ | | +| approx_kl | 0.015428618 | +| clip_fraction | 0.361 | +| clip_range | 0.0655 | +| entropy_loss | -5.65 | +| explained_variance | 0.61 | +| learning_rate | 4.09e-05 | +| loss | -0.0271 | +| n_updates | 90308 | +| policy_gradient_loss | -0.0195 | +| value_loss | 4.57e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1389 | +| iterations | 18624 | +| time_elapsed | 27458 | +| total_timesteps | 38141952 | +| train/ | | +| approx_kl | 0.014379978 | +| clip_fraction | 0.379 | +| clip_range | 0.0655 | +| entropy_loss | -5.98 | +| explained_variance | 0.106 | +| learning_rate | 4.09e-05 | +| loss | -0.03 | +| n_updates | 90312 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000146 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1389 | +| iterations | 18625 | +| time_elapsed | 27459 | +| total_timesteps | 38144000 | +| train/ | | +| approx_kl | 0.010916853 | +| clip_fraction | 0.331 | +| clip_range | 0.0655 | +| entropy_loss | -5.91 | +| explained_variance | 0.517 | +| learning_rate | 4.09e-05 | +| loss | -0.0222 | +| n_updates | 90316 | +| policy_gradient_loss | -0.0142 | +| value_loss | 0.000195 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1389 | +| iterations | 18626 | +| time_elapsed | 27461 | +| total_timesteps | 38146048 | +| train/ | | +| approx_kl | 0.014725563 | +| clip_fraction | 0.329 | +| clip_range | 0.0655 | +| entropy_loss | -5.75 | +| explained_variance | 0.49 | +| learning_rate | 4.09e-05 | +| loss | -0.0285 | +| n_updates | 90320 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.00014 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1389 | +| iterations | 18627 | +| time_elapsed | 27462 | +| total_timesteps | 38148096 | +| train/ | | +| approx_kl | 0.016475499 | +| clip_fraction | 0.385 | +| clip_range | 0.0655 | +| entropy_loss | -5.52 | +| explained_variance | 0.494 | +| learning_rate | 4.09e-05 | +| loss | -0.0281 | +| n_updates | 90324 | +| policy_gradient_loss | -0.0192 | +| value_loss | 9.45e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1389 | +| iterations | 18628 | +| time_elapsed | 27464 | +| total_timesteps | 38150144 | +| train/ | | +| approx_kl | 0.015235165 | +| clip_fraction | 0.372 | +| clip_range | 0.0655 | +| entropy_loss | -5.06 | +| explained_variance | 0.555 | +| learning_rate | 4.09e-05 | +| loss | -0.0326 | +| n_updates | 90328 | +| policy_gradient_loss | -0.0188 | +| value_loss | 7.58e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1389 | +| iterations | 18629 | +| time_elapsed | 27465 | +| total_timesteps | 38152192 | +| train/ | | +| approx_kl | 0.015582795 | +| clip_fraction | 0.332 | +| clip_range | 0.0655 | +| entropy_loss | -5.16 | +| explained_variance | 0.722 | +| learning_rate | 4.09e-05 | +| loss | -0.0257 | +| n_updates | 90332 | +| policy_gradient_loss | -0.0183 | +| value_loss | 5.84e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1389 | +| iterations | 18630 | +| time_elapsed | 27467 | +| total_timesteps | 38154240 | +| train/ | | +| approx_kl | 0.015558195 | +| clip_fraction | 0.347 | +| clip_range | 0.0655 | +| entropy_loss | -5.41 | +| explained_variance | 0.395 | +| learning_rate | 4.09e-05 | +| loss | -0.0303 | +| n_updates | 90336 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000112 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1389 | +| iterations | 18631 | +| time_elapsed | 27469 | +| total_timesteps | 38156288 | +| train/ | | +| approx_kl | 0.019579925 | +| clip_fraction | 0.359 | +| clip_range | 0.0655 | +| entropy_loss | -5.31 | +| explained_variance | 0.375 | +| learning_rate | 4.09e-05 | +| loss | -0.0287 | +| n_updates | 90340 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000132 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1389 | +| iterations | 18632 | +| time_elapsed | 27470 | +| total_timesteps | 38158336 | +| train/ | | +| approx_kl | 0.01660915 | +| clip_fraction | 0.349 | +| clip_range | 0.0655 | +| entropy_loss | -5.76 | +| explained_variance | 0.43 | +| learning_rate | 4.09e-05 | +| loss | -0.0272 | +| n_updates | 90344 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000106 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1389 | +| iterations | 18633 | +| time_elapsed | 27472 | +| total_timesteps | 38160384 | +| train/ | | +| approx_kl | 0.022152474 | +| clip_fraction | 0.326 | +| clip_range | 0.0655 | +| entropy_loss | -5.22 | +| explained_variance | 0.496 | +| learning_rate | 4.09e-05 | +| loss | -0.0237 | +| n_updates | 90348 | +| policy_gradient_loss | -0.0144 | +| value_loss | 0.000209 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1389 | +| iterations | 18634 | +| time_elapsed | 27473 | +| total_timesteps | 38162432 | +| train/ | | +| approx_kl | 0.014197946 | +| clip_fraction | 0.364 | +| clip_range | 0.0655 | +| entropy_loss | -5.26 | +| explained_variance | 0.7 | +| learning_rate | 4.09e-05 | +| loss | -0.0289 | +| n_updates | 90352 | +| policy_gradient_loss | -0.0192 | +| value_loss | 9.17e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1389 | +| iterations | 18635 | +| time_elapsed | 27475 | +| total_timesteps | 38164480 | +| train/ | | +| approx_kl | 0.011119809 | +| clip_fraction | 0.343 | +| clip_range | 0.0655 | +| entropy_loss | -5.85 | +| explained_variance | 0.271 | +| learning_rate | 4.09e-05 | +| loss | -0.0265 | +| n_updates | 90356 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000133 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1389 | +| iterations | 18636 | +| time_elapsed | 27476 | +| total_timesteps | 38166528 | +| train/ | | +| approx_kl | 0.016133916 | +| clip_fraction | 0.336 | +| clip_range | 0.0655 | +| entropy_loss | -4.8 | +| explained_variance | 0.68 | +| learning_rate | 4.09e-05 | +| loss | -0.0256 | +| n_updates | 90360 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000113 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1389 | +| iterations | 18637 | +| time_elapsed | 27478 | +| total_timesteps | 38168576 | +| train/ | | +| approx_kl | 0.017794866 | +| clip_fraction | 0.358 | +| clip_range | 0.0655 | +| entropy_loss | -5.21 | +| explained_variance | 0.467 | +| learning_rate | 4.09e-05 | +| loss | -0.0239 | +| n_updates | 90364 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1389 | +| iterations | 18638 | +| time_elapsed | 27479 | +| total_timesteps | 38170624 | +| train/ | | +| approx_kl | 0.014292337 | +| clip_fraction | 0.362 | +| clip_range | 0.0655 | +| entropy_loss | -5.51 | +| explained_variance | 0.277 | +| learning_rate | 4.09e-05 | +| loss | -0.0281 | +| n_updates | 90368 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000278 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1389 | +| iterations | 18639 | +| time_elapsed | 27481 | +| total_timesteps | 38172672 | +| train/ | | +| approx_kl | 0.016233012 | +| clip_fraction | 0.373 | +| clip_range | 0.0655 | +| entropy_loss | -5.36 | +| explained_variance | 0.499 | +| learning_rate | 4.09e-05 | +| loss | -0.0347 | +| n_updates | 90372 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000101 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1389 | +| iterations | 18640 | +| time_elapsed | 27482 | +| total_timesteps | 38174720 | +| train/ | | +| approx_kl | 0.015032022 | +| clip_fraction | 0.369 | +| clip_range | 0.0655 | +| entropy_loss | -5.7 | +| explained_variance | 0.692 | +| learning_rate | 4.09e-05 | +| loss | -0.0289 | +| n_updates | 90376 | +| policy_gradient_loss | -0.0189 | +| value_loss | 8.47e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1389 | +| iterations | 18641 | +| time_elapsed | 27484 | +| total_timesteps | 38176768 | +| train/ | | +| approx_kl | 0.019057607 | +| clip_fraction | 0.316 | +| clip_range | 0.0655 | +| entropy_loss | -5.58 | +| explained_variance | 0.251 | +| learning_rate | 4.09e-05 | +| loss | -0.028 | +| n_updates | 90380 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000172 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1389 | +| iterations | 18642 | +| time_elapsed | 27485 | +| total_timesteps | 38178816 | +| train/ | | +| approx_kl | 0.015661322 | +| clip_fraction | 0.331 | +| clip_range | 0.0655 | +| entropy_loss | -5.34 | +| explained_variance | 0.426 | +| learning_rate | 4.09e-05 | +| loss | -0.0299 | +| n_updates | 90384 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000195 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1389 | +| iterations | 18643 | +| time_elapsed | 27487 | +| total_timesteps | 38180864 | +| train/ | | +| approx_kl | 0.016878296 | +| clip_fraction | 0.368 | +| clip_range | 0.0655 | +| entropy_loss | -5.92 | +| explained_variance | 0.29 | +| learning_rate | 4.09e-05 | +| loss | -0.0282 | +| n_updates | 90388 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.00013 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1389 | +| iterations | 18644 | +| time_elapsed | 27489 | +| total_timesteps | 38182912 | +| train/ | | +| approx_kl | 0.016840117 | +| clip_fraction | 0.336 | +| clip_range | 0.0655 | +| entropy_loss | -6.12 | +| explained_variance | 0.41 | +| learning_rate | 4.09e-05 | +| loss | -0.0282 | +| n_updates | 90392 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000129 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 1389 | +| iterations | 18645 | +| time_elapsed | 27490 | +| total_timesteps | 38184960 | +| train/ | | +| approx_kl | 0.017604733 | +| clip_fraction | 0.342 | +| clip_range | 0.0655 | +| entropy_loss | -6.21 | +| explained_variance | -0.319 | +| learning_rate | 4.09e-05 | +| loss | -0.0307 | +| n_updates | 90396 | +| policy_gradient_loss | -0.0199 | +| value_loss | 7.71e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.306 | +| time/ | | +| fps | 1389 | +| iterations | 18646 | +| time_elapsed | 27492 | +| total_timesteps | 38187008 | +| train/ | | +| approx_kl | 0.012681248 | +| clip_fraction | 0.339 | +| clip_range | 0.0655 | +| entropy_loss | -5.54 | +| explained_variance | 0.727 | +| learning_rate | 4.09e-05 | +| loss | -0.0267 | +| n_updates | 90400 | +| policy_gradient_loss | -0.017 | +| value_loss | 8e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1389 | +| iterations | 18647 | +| time_elapsed | 27493 | +| total_timesteps | 38189056 | +| train/ | | +| approx_kl | 0.012294818 | +| clip_fraction | 0.352 | +| clip_range | 0.0655 | +| entropy_loss | -5.42 | +| explained_variance | 0.726 | +| learning_rate | 4.09e-05 | +| loss | -0.0279 | +| n_updates | 90404 | +| policy_gradient_loss | -0.0173 | +| value_loss | 8.3e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.302 | +| time/ | | +| fps | 1389 | +| iterations | 18648 | +| time_elapsed | 27495 | +| total_timesteps | 38191104 | +| train/ | | +| approx_kl | 0.011069121 | +| clip_fraction | 0.318 | +| clip_range | 0.0655 | +| entropy_loss | -5.38 | +| explained_variance | 0.562 | +| learning_rate | 4.09e-05 | +| loss | -0.021 | +| n_updates | 90408 | +| policy_gradient_loss | -0.014 | +| value_loss | 0.000133 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.304 | +| time/ | | +| fps | 1389 | +| iterations | 18649 | +| time_elapsed | 27496 | +| total_timesteps | 38193152 | +| train/ | | +| approx_kl | 0.014602359 | +| clip_fraction | 0.362 | +| clip_range | 0.0655 | +| entropy_loss | -5.13 | +| explained_variance | 0.587 | +| learning_rate | 4.09e-05 | +| loss | -0.032 | +| n_updates | 90412 | +| policy_gradient_loss | -0.0191 | +| value_loss | 9.56e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1389 | +| iterations | 18650 | +| time_elapsed | 27498 | +| total_timesteps | 38195200 | +| train/ | | +| approx_kl | 0.014696125 | +| clip_fraction | 0.335 | +| clip_range | 0.0655 | +| entropy_loss | -5.39 | +| explained_variance | 0.599 | +| learning_rate | 4.09e-05 | +| loss | -0.0237 | +| n_updates | 90416 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000106 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.302 | +| time/ | | +| fps | 1389 | +| iterations | 18651 | +| time_elapsed | 27499 | +| total_timesteps | 38197248 | +| train/ | | +| approx_kl | 0.014797514 | +| clip_fraction | 0.345 | +| clip_range | 0.0655 | +| entropy_loss | -5.15 | +| explained_variance | 0.635 | +| learning_rate | 4.09e-05 | +| loss | -0.026 | +| n_updates | 90420 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000138 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.306 | +| time/ | | +| fps | 1389 | +| iterations | 18652 | +| time_elapsed | 27501 | +| total_timesteps | 38199296 | +| train/ | | +| approx_kl | 0.01582406 | +| clip_fraction | 0.338 | +| clip_range | 0.0655 | +| entropy_loss | -5.03 | +| explained_variance | 0.401 | +| learning_rate | 4.09e-05 | +| loss | -0.0255 | +| n_updates | 90424 | +| policy_gradient_loss | -0.0145 | +| value_loss | 0.000163 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1388 | +| iterations | 18653 | +| time_elapsed | 27502 | +| total_timesteps | 38201344 | +| train/ | | +| approx_kl | 0.018516168 | +| clip_fraction | 0.34 | +| clip_range | 0.0655 | +| entropy_loss | -5.21 | +| explained_variance | 0.452 | +| learning_rate | 4.09e-05 | +| loss | -0.023 | +| n_updates | 90428 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000167 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1388 | +| iterations | 18654 | +| time_elapsed | 27504 | +| total_timesteps | 38203392 | +| train/ | | +| approx_kl | 0.01772974 | +| clip_fraction | 0.316 | +| clip_range | 0.0654 | +| entropy_loss | -5.41 | +| explained_variance | 0.316 | +| learning_rate | 4.09e-05 | +| loss | -0.0291 | +| n_updates | 90432 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.00022 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1388 | +| iterations | 18655 | +| time_elapsed | 27505 | +| total_timesteps | 38205440 | +| train/ | | +| approx_kl | 0.0147258695 | +| clip_fraction | 0.376 | +| clip_range | 0.0654 | +| entropy_loss | -5.48 | +| explained_variance | 0.352 | +| learning_rate | 4.09e-05 | +| loss | -0.0284 | +| n_updates | 90436 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000142 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.306 | +| time/ | | +| fps | 1388 | +| iterations | 18656 | +| time_elapsed | 27507 | +| total_timesteps | 38207488 | +| train/ | | +| approx_kl | 0.01272518 | +| clip_fraction | 0.355 | +| clip_range | 0.0654 | +| entropy_loss | -6.32 | +| explained_variance | 0.172 | +| learning_rate | 4.09e-05 | +| loss | -0.032 | +| n_updates | 90440 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000144 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.297 | +| time/ | | +| fps | 1388 | +| iterations | 18657 | +| time_elapsed | 27508 | +| total_timesteps | 38209536 | +| train/ | | +| approx_kl | 0.01263801 | +| clip_fraction | 0.335 | +| clip_range | 0.0654 | +| entropy_loss | -6.33 | +| explained_variance | 0.528 | +| learning_rate | 4.09e-05 | +| loss | -0.0316 | +| n_updates | 90444 | +| policy_gradient_loss | -0.0179 | +| value_loss | 7.5e-05 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 1388 | +| iterations | 18658 | +| time_elapsed | 27510 | +| total_timesteps | 38211584 | +| train/ | | +| approx_kl | 0.01625678 | +| clip_fraction | 0.327 | +| clip_range | 0.0654 | +| entropy_loss | -5.72 | +| explained_variance | 0.627 | +| learning_rate | 4.09e-05 | +| loss | -0.0269 | +| n_updates | 90448 | +| policy_gradient_loss | -0.016 | +| value_loss | 9.66e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 1388 | +| iterations | 18659 | +| time_elapsed | 27511 | +| total_timesteps | 38213632 | +| train/ | | +| approx_kl | 0.013714286 | +| clip_fraction | 0.341 | +| clip_range | 0.0654 | +| entropy_loss | -5.68 | +| explained_variance | 0.24 | +| learning_rate | 4.09e-05 | +| loss | -0.0261 | +| n_updates | 90452 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000191 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.293 | +| time/ | | +| fps | 1388 | +| iterations | 18660 | +| time_elapsed | 27513 | +| total_timesteps | 38215680 | +| train/ | | +| approx_kl | 0.015820114 | +| clip_fraction | 0.338 | +| clip_range | 0.0654 | +| entropy_loss | -5.31 | +| explained_variance | 0.274 | +| learning_rate | 4.09e-05 | +| loss | -0.0247 | +| n_updates | 90456 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000156 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.3 | +| time/ | | +| fps | 1388 | +| iterations | 18661 | +| time_elapsed | 27515 | +| total_timesteps | 38217728 | +| train/ | | +| approx_kl | 0.016213784 | +| clip_fraction | 0.364 | +| clip_range | 0.0654 | +| entropy_loss | -5.42 | +| explained_variance | 0.457 | +| learning_rate | 4.09e-05 | +| loss | -0.0313 | +| n_updates | 90460 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000165 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.302 | +| time/ | | +| fps | 1388 | +| iterations | 18662 | +| time_elapsed | 27516 | +| total_timesteps | 38219776 | +| train/ | | +| approx_kl | 0.016332176 | +| clip_fraction | 0.372 | +| clip_range | 0.0654 | +| entropy_loss | -5.27 | +| explained_variance | 0.548 | +| learning_rate | 4.09e-05 | +| loss | -0.0283 | +| n_updates | 90464 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000135 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.302 | +| time/ | | +| fps | 1388 | +| iterations | 18663 | +| time_elapsed | 27518 | +| total_timesteps | 38221824 | +| train/ | | +| approx_kl | 0.018587315 | +| clip_fraction | 0.356 | +| clip_range | 0.0654 | +| entropy_loss | -5.53 | +| explained_variance | 0.104 | +| learning_rate | 4.09e-05 | +| loss | -0.0261 | +| n_updates | 90468 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000161 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 1388 | +| iterations | 18664 | +| time_elapsed | 27519 | +| total_timesteps | 38223872 | +| train/ | | +| approx_kl | 0.014637896 | +| clip_fraction | 0.382 | +| clip_range | 0.0654 | +| entropy_loss | -6.06 | +| explained_variance | 0.289 | +| learning_rate | 4.09e-05 | +| loss | -0.0299 | +| n_updates | 90472 | +| policy_gradient_loss | -0.0194 | +| value_loss | 8.58e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.3 | +| time/ | | +| fps | 1388 | +| iterations | 18665 | +| time_elapsed | 27521 | +| total_timesteps | 38225920 | +| train/ | | +| approx_kl | 0.015211976 | +| clip_fraction | 0.296 | +| clip_range | 0.0654 | +| entropy_loss | -6.13 | +| explained_variance | 0.232 | +| learning_rate | 4.09e-05 | +| loss | -0.0241 | +| n_updates | 90476 | +| policy_gradient_loss | -0.0147 | +| value_loss | 0.000248 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.3 | +| time/ | | +| fps | 1388 | +| iterations | 18666 | +| time_elapsed | 27522 | +| total_timesteps | 38227968 | +| train/ | | +| approx_kl | 0.01811496 | +| clip_fraction | 0.365 | +| clip_range | 0.0654 | +| entropy_loss | -5.39 | +| explained_variance | 0.535 | +| learning_rate | 4.09e-05 | +| loss | -0.0242 | +| n_updates | 90480 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000144 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.3 | +| time/ | | +| fps | 1388 | +| iterations | 18667 | +| time_elapsed | 27524 | +| total_timesteps | 38230016 | +| train/ | | +| approx_kl | 0.015207813 | +| clip_fraction | 0.361 | +| clip_range | 0.0654 | +| entropy_loss | -5.48 | +| explained_variance | 0.387 | +| learning_rate | 4.09e-05 | +| loss | -0.0266 | +| n_updates | 90484 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000133 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.3 | +| time/ | | +| fps | 1388 | +| iterations | 18668 | +| time_elapsed | 27525 | +| total_timesteps | 38232064 | +| train/ | | +| approx_kl | 0.012713153 | +| clip_fraction | 0.349 | +| clip_range | 0.0654 | +| entropy_loss | -5.3 | +| explained_variance | 0.468 | +| learning_rate | 4.09e-05 | +| loss | -0.0216 | +| n_updates | 90488 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.000223 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.297 | +| time/ | | +| fps | 1388 | +| iterations | 18669 | +| time_elapsed | 27527 | +| total_timesteps | 38234112 | +| train/ | | +| approx_kl | 0.014026256 | +| clip_fraction | 0.36 | +| clip_range | 0.0654 | +| entropy_loss | -5.73 | +| explained_variance | 0.39 | +| learning_rate | 4.09e-05 | +| loss | -0.0299 | +| n_updates | 90492 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000108 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.293 | +| time/ | | +| fps | 1388 | +| iterations | 18670 | +| time_elapsed | 27528 | +| total_timesteps | 38236160 | +| train/ | | +| approx_kl | 0.015473111 | +| clip_fraction | 0.319 | +| clip_range | 0.0654 | +| entropy_loss | -6.34 | +| explained_variance | 0.444 | +| learning_rate | 4.09e-05 | +| loss | -0.027 | +| n_updates | 90496 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000176 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.292 | +| time/ | | +| fps | 1388 | +| iterations | 18671 | +| time_elapsed | 27530 | +| total_timesteps | 38238208 | +| train/ | | +| approx_kl | 0.013893514 | +| clip_fraction | 0.337 | +| clip_range | 0.0654 | +| entropy_loss | -5.56 | +| explained_variance | 0.495 | +| learning_rate | 4.09e-05 | +| loss | -0.0254 | +| n_updates | 90500 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.00013 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.3 | +| time/ | | +| fps | 1388 | +| iterations | 18672 | +| time_elapsed | 27531 | +| total_timesteps | 38240256 | +| train/ | | +| approx_kl | 0.017201276 | +| clip_fraction | 0.368 | +| clip_range | 0.0654 | +| entropy_loss | -5.67 | +| explained_variance | 0.465 | +| learning_rate | 4.09e-05 | +| loss | -0.0299 | +| n_updates | 90504 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000128 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.3 | +| time/ | | +| fps | 1388 | +| iterations | 18673 | +| time_elapsed | 27533 | +| total_timesteps | 38242304 | +| train/ | | +| approx_kl | 0.012408261 | +| clip_fraction | 0.307 | +| clip_range | 0.0654 | +| entropy_loss | -5.96 | +| explained_variance | 0.171 | +| learning_rate | 4.09e-05 | +| loss | -0.0246 | +| n_updates | 90508 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000441 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.297 | +| time/ | | +| fps | 1388 | +| iterations | 18674 | +| time_elapsed | 27534 | +| total_timesteps | 38244352 | +| train/ | | +| approx_kl | 0.014731426 | +| clip_fraction | 0.354 | +| clip_range | 0.0654 | +| entropy_loss | -5.58 | +| explained_variance | 0.54 | +| learning_rate | 4.09e-05 | +| loss | -0.0313 | +| n_updates | 90512 | +| policy_gradient_loss | -0.0211 | +| value_loss | 8.43e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.297 | +| time/ | | +| fps | 1388 | +| iterations | 18675 | +| time_elapsed | 27536 | +| total_timesteps | 38246400 | +| train/ | | +| approx_kl | 0.01542717 | +| clip_fraction | 0.37 | +| clip_range | 0.0654 | +| entropy_loss | -5.6 | +| explained_variance | 0.243 | +| learning_rate | 4.09e-05 | +| loss | -0.0274 | +| n_updates | 90516 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000141 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.298 | +| time/ | | +| fps | 1388 | +| iterations | 18676 | +| time_elapsed | 27537 | +| total_timesteps | 38248448 | +| train/ | | +| approx_kl | 0.0139563475 | +| clip_fraction | 0.355 | +| clip_range | 0.0654 | +| entropy_loss | -5.91 | +| explained_variance | 0.423 | +| learning_rate | 4.09e-05 | +| loss | -0.0239 | +| n_updates | 90520 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000182 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.298 | +| time/ | | +| fps | 1388 | +| iterations | 18677 | +| time_elapsed | 27539 | +| total_timesteps | 38250496 | +| train/ | | +| approx_kl | 0.013145662 | +| clip_fraction | 0.351 | +| clip_range | 0.0654 | +| entropy_loss | -5.82 | +| explained_variance | 0.599 | +| learning_rate | 4.09e-05 | +| loss | -0.0248 | +| n_updates | 90524 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000102 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1388 | +| iterations | 18678 | +| time_elapsed | 27540 | +| total_timesteps | 38252544 | +| train/ | | +| approx_kl | 0.013733045 | +| clip_fraction | 0.37 | +| clip_range | 0.0654 | +| entropy_loss | -6.14 | +| explained_variance | -0.371 | +| learning_rate | 4.09e-05 | +| loss | -0.0354 | +| n_updates | 90528 | +| policy_gradient_loss | -0.0209 | +| value_loss | 4.66e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 1388 | +| iterations | 18679 | +| time_elapsed | 27542 | +| total_timesteps | 38254592 | +| train/ | | +| approx_kl | 0.012802454 | +| clip_fraction | 0.337 | +| clip_range | 0.0654 | +| entropy_loss | -6.17 | +| explained_variance | 0.323 | +| learning_rate | 4.09e-05 | +| loss | -0.0238 | +| n_updates | 90532 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.000278 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 1388 | +| iterations | 18680 | +| time_elapsed | 27543 | +| total_timesteps | 38256640 | +| train/ | | +| approx_kl | 0.018704504 | +| clip_fraction | 0.369 | +| clip_range | 0.0654 | +| entropy_loss | -5.53 | +| explained_variance | 0.586 | +| learning_rate | 4.09e-05 | +| loss | -0.0322 | +| n_updates | 90536 | +| policy_gradient_loss | -0.0213 | +| value_loss | 7.82e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.302 | +| time/ | | +| fps | 1388 | +| iterations | 18681 | +| time_elapsed | 27545 | +| total_timesteps | 38258688 | +| train/ | | +| approx_kl | 0.013091038 | +| clip_fraction | 0.343 | +| clip_range | 0.0654 | +| entropy_loss | -5.17 | +| explained_variance | 0.683 | +| learning_rate | 4.09e-05 | +| loss | -0.0235 | +| n_updates | 90540 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 1388 | +| iterations | 18682 | +| time_elapsed | 27546 | +| total_timesteps | 38260736 | +| train/ | | +| approx_kl | 0.011398123 | +| clip_fraction | 0.305 | +| clip_range | 0.0654 | +| entropy_loss | -5.64 | +| explained_variance | 0.38 | +| learning_rate | 4.09e-05 | +| loss | -0.0221 | +| n_updates | 90544 | +| policy_gradient_loss | -0.0144 | +| value_loss | 0.00019 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1388 | +| iterations | 18683 | +| time_elapsed | 27548 | +| total_timesteps | 38262784 | +| train/ | | +| approx_kl | 0.0134965805 | +| clip_fraction | 0.344 | +| clip_range | 0.0654 | +| entropy_loss | -5.86 | +| explained_variance | 0.28 | +| learning_rate | 4.09e-05 | +| loss | -0.0268 | +| n_updates | 90548 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000232 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1388 | +| iterations | 18684 | +| time_elapsed | 27549 | +| total_timesteps | 38264832 | +| train/ | | +| approx_kl | 0.010436603 | +| clip_fraction | 0.343 | +| clip_range | 0.0654 | +| entropy_loss | -6.11 | +| explained_variance | 0.253 | +| learning_rate | 4.09e-05 | +| loss | -0.0274 | +| n_updates | 90552 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000249 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1388 | +| iterations | 18685 | +| time_elapsed | 27551 | +| total_timesteps | 38266880 | +| train/ | | +| approx_kl | 0.018943131 | +| clip_fraction | 0.314 | +| clip_range | 0.0654 | +| entropy_loss | -5.78 | +| explained_variance | 0.525 | +| learning_rate | 4.09e-05 | +| loss | -0.028 | +| n_updates | 90556 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000181 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1388 | +| iterations | 18686 | +| time_elapsed | 27552 | +| total_timesteps | 38268928 | +| train/ | | +| approx_kl | 0.016108913 | +| clip_fraction | 0.362 | +| clip_range | 0.0654 | +| entropy_loss | -5.72 | +| explained_variance | -0.166 | +| learning_rate | 4.09e-05 | +| loss | -0.0322 | +| n_updates | 90560 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000144 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.315 | +| time/ | | +| fps | 1388 | +| iterations | 18687 | +| time_elapsed | 27554 | +| total_timesteps | 38270976 | +| train/ | | +| approx_kl | 0.013007548 | +| clip_fraction | 0.331 | +| clip_range | 0.0654 | +| entropy_loss | -6.44 | +| explained_variance | 0.479 | +| learning_rate | 4.09e-05 | +| loss | -0.0303 | +| n_updates | 90564 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.00011 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1388 | +| iterations | 18688 | +| time_elapsed | 27555 | +| total_timesteps | 38273024 | +| train/ | | +| approx_kl | 0.01325225 | +| clip_fraction | 0.342 | +| clip_range | 0.0654 | +| entropy_loss | -5.47 | +| explained_variance | 0.367 | +| learning_rate | 4.09e-05 | +| loss | -0.0194 | +| n_updates | 90568 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000257 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1388 | +| iterations | 18689 | +| time_elapsed | 27557 | +| total_timesteps | 38275072 | +| train/ | | +| approx_kl | 0.019215927 | +| clip_fraction | 0.355 | +| clip_range | 0.0654 | +| entropy_loss | -5.07 | +| explained_variance | 0.363 | +| learning_rate | 4.09e-05 | +| loss | -0.0231 | +| n_updates | 90572 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000288 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1388 | +| iterations | 18690 | +| time_elapsed | 27558 | +| total_timesteps | 38277120 | +| train/ | | +| approx_kl | 0.017925806 | +| clip_fraction | 0.357 | +| clip_range | 0.0654 | +| entropy_loss | -4.96 | +| explained_variance | 0.488 | +| learning_rate | 4.09e-05 | +| loss | -0.0302 | +| n_updates | 90576 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000152 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1388 | +| iterations | 18691 | +| time_elapsed | 27560 | +| total_timesteps | 38279168 | +| train/ | | +| approx_kl | 0.01369182 | +| clip_fraction | 0.333 | +| clip_range | 0.0654 | +| entropy_loss | -4.99 | +| explained_variance | 0.481 | +| learning_rate | 4.09e-05 | +| loss | -0.0294 | +| n_updates | 90580 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000195 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1388 | +| iterations | 18692 | +| time_elapsed | 27562 | +| total_timesteps | 38281216 | +| train/ | | +| approx_kl | 0.016968304 | +| clip_fraction | 0.382 | +| clip_range | 0.0654 | +| entropy_loss | -5.26 | +| explained_variance | 0.539 | +| learning_rate | 4.09e-05 | +| loss | -0.0348 | +| n_updates | 90584 | +| policy_gradient_loss | -0.0234 | +| value_loss | 5.69e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1388 | +| iterations | 18693 | +| time_elapsed | 27563 | +| total_timesteps | 38283264 | +| train/ | | +| approx_kl | 0.013350083 | +| clip_fraction | 0.328 | +| clip_range | 0.0654 | +| entropy_loss | -5.19 | +| explained_variance | 0.705 | +| learning_rate | 4.09e-05 | +| loss | -0.0267 | +| n_updates | 90588 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000105 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1388 | +| iterations | 18694 | +| time_elapsed | 27565 | +| total_timesteps | 38285312 | +| train/ | | +| approx_kl | 0.018316798 | +| clip_fraction | 0.366 | +| clip_range | 0.0654 | +| entropy_loss | -5.26 | +| explained_variance | 0.0548 | +| learning_rate | 4.09e-05 | +| loss | -0.0276 | +| n_updates | 90592 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000169 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1388 | +| iterations | 18695 | +| time_elapsed | 27566 | +| total_timesteps | 38287360 | +| train/ | | +| approx_kl | 0.018749047 | +| clip_fraction | 0.376 | +| clip_range | 0.0654 | +| entropy_loss | -5.21 | +| explained_variance | 0.769 | +| learning_rate | 4.09e-05 | +| loss | -0.0314 | +| n_updates | 90596 | +| policy_gradient_loss | -0.0188 | +| value_loss | 6.4e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1388 | +| iterations | 18696 | +| time_elapsed | 27568 | +| total_timesteps | 38289408 | +| train/ | | +| approx_kl | 0.018219758 | +| clip_fraction | 0.339 | +| clip_range | 0.0654 | +| entropy_loss | -5.64 | +| explained_variance | -0.19 | +| learning_rate | 4.09e-05 | +| loss | -0.0253 | +| n_updates | 90600 | +| policy_gradient_loss | -0.016 | +| value_loss | 9.1e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1388 | +| iterations | 18697 | +| time_elapsed | 27569 | +| total_timesteps | 38291456 | +| train/ | | +| approx_kl | 0.015127668 | +| clip_fraction | 0.335 | +| clip_range | 0.0654 | +| entropy_loss | -6.22 | +| explained_variance | 0.346 | +| learning_rate | 4.09e-05 | +| loss | -0.0234 | +| n_updates | 90604 | +| policy_gradient_loss | -0.0147 | +| value_loss | 0.000237 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1388 | +| iterations | 18698 | +| time_elapsed | 27571 | +| total_timesteps | 38293504 | +| train/ | | +| approx_kl | 0.016064238 | +| clip_fraction | 0.354 | +| clip_range | 0.0654 | +| entropy_loss | -5.61 | +| explained_variance | 0.356 | +| learning_rate | 4.09e-05 | +| loss | -0.0268 | +| n_updates | 90608 | +| policy_gradient_loss | -0.016 | +| value_loss | 9.36e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1388 | +| iterations | 18699 | +| time_elapsed | 27572 | +| total_timesteps | 38295552 | +| train/ | | +| approx_kl | 0.016591841 | +| clip_fraction | 0.374 | +| clip_range | 0.0654 | +| entropy_loss | -5.76 | +| explained_variance | 0.479 | +| learning_rate | 4.09e-05 | +| loss | -0.0283 | +| n_updates | 90612 | +| policy_gradient_loss | -0.0218 | +| value_loss | 7.43e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1388 | +| iterations | 18700 | +| time_elapsed | 27574 | +| total_timesteps | 38297600 | +| train/ | | +| approx_kl | 0.015180069 | +| clip_fraction | 0.357 | +| clip_range | 0.0654 | +| entropy_loss | -6.2 | +| explained_variance | -0.0891 | +| learning_rate | 4.09e-05 | +| loss | -0.0235 | +| n_updates | 90616 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000127 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1388 | +| iterations | 18701 | +| time_elapsed | 27575 | +| total_timesteps | 38299648 | +| train/ | | +| approx_kl | 0.01135761 | +| clip_fraction | 0.332 | +| clip_range | 0.0654 | +| entropy_loss | -5.84 | +| explained_variance | 0.448 | +| learning_rate | 4.09e-05 | +| loss | -0.0257 | +| n_updates | 90620 | +| policy_gradient_loss | -0.0142 | +| value_loss | 0.000175 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1388 | +| iterations | 18702 | +| time_elapsed | 27577 | +| total_timesteps | 38301696 | +| train/ | | +| approx_kl | 0.015129294 | +| clip_fraction | 0.333 | +| clip_range | 0.0654 | +| entropy_loss | -5.16 | +| explained_variance | 0.452 | +| learning_rate | 4.09e-05 | +| loss | -0.0273 | +| n_updates | 90624 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000242 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1388 | +| iterations | 18703 | +| time_elapsed | 27578 | +| total_timesteps | 38303744 | +| train/ | | +| approx_kl | 0.023094123 | +| clip_fraction | 0.324 | +| clip_range | 0.0654 | +| entropy_loss | -5.33 | +| explained_variance | 0.555 | +| learning_rate | 4.09e-05 | +| loss | -0.0263 | +| n_updates | 90628 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000157 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1388 | +| iterations | 18704 | +| time_elapsed | 27580 | +| total_timesteps | 38305792 | +| train/ | | +| approx_kl | 0.015464228 | +| clip_fraction | 0.334 | +| clip_range | 0.0654 | +| entropy_loss | -5.04 | +| explained_variance | 0.431 | +| learning_rate | 4.09e-05 | +| loss | -0.0229 | +| n_updates | 90632 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000157 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1388 | +| iterations | 18705 | +| time_elapsed | 27582 | +| total_timesteps | 38307840 | +| train/ | | +| approx_kl | 0.014497746 | +| clip_fraction | 0.358 | +| clip_range | 0.0654 | +| entropy_loss | -5.51 | +| explained_variance | 0.536 | +| learning_rate | 4.09e-05 | +| loss | -0.0273 | +| n_updates | 90636 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.00014 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1388 | +| iterations | 18706 | +| time_elapsed | 27583 | +| total_timesteps | 38309888 | +| train/ | | +| approx_kl | 0.011059865 | +| clip_fraction | 0.336 | +| clip_range | 0.0654 | +| entropy_loss | -5.71 | +| explained_variance | 0.317 | +| learning_rate | 4.09e-05 | +| loss | -0.021 | +| n_updates | 90640 | +| policy_gradient_loss | -0.0144 | +| value_loss | 0.000455 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1388 | +| iterations | 18707 | +| time_elapsed | 27585 | +| total_timesteps | 38311936 | +| train/ | | +| approx_kl | 0.011953933 | +| clip_fraction | 0.348 | +| clip_range | 0.0654 | +| entropy_loss | -5.97 | +| explained_variance | -0.044 | +| learning_rate | 4.09e-05 | +| loss | -0.0336 | +| n_updates | 90644 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000137 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1388 | +| iterations | 18708 | +| time_elapsed | 27586 | +| total_timesteps | 38313984 | +| train/ | | +| approx_kl | 0.011933253 | +| clip_fraction | 0.359 | +| clip_range | 0.0654 | +| entropy_loss | -5.72 | +| explained_variance | 0.558 | +| learning_rate | 4.09e-05 | +| loss | -0.0271 | +| n_updates | 90648 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1388 | +| iterations | 18709 | +| time_elapsed | 27588 | +| total_timesteps | 38316032 | +| train/ | | +| approx_kl | 0.012371558 | +| clip_fraction | 0.325 | +| clip_range | 0.0654 | +| entropy_loss | -5.53 | +| explained_variance | -0.0839 | +| learning_rate | 4.09e-05 | +| loss | -0.0291 | +| n_updates | 90652 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000123 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1388 | +| iterations | 18710 | +| time_elapsed | 27589 | +| total_timesteps | 38318080 | +| train/ | | +| approx_kl | 0.012148662 | +| clip_fraction | 0.349 | +| clip_range | 0.0654 | +| entropy_loss | -5.73 | +| explained_variance | 0.525 | +| learning_rate | 4.09e-05 | +| loss | -0.0335 | +| n_updates | 90656 | +| policy_gradient_loss | -0.0184 | +| value_loss | 6.99e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1388 | +| iterations | 18711 | +| time_elapsed | 27591 | +| total_timesteps | 38320128 | +| train/ | | +| approx_kl | 0.0130696725 | +| clip_fraction | 0.344 | +| clip_range | 0.0654 | +| entropy_loss | -5.82 | +| explained_variance | 0.619 | +| learning_rate | 4.09e-05 | +| loss | -0.0289 | +| n_updates | 90660 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000111 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1388 | +| iterations | 18712 | +| time_elapsed | 27592 | +| total_timesteps | 38322176 | +| train/ | | +| approx_kl | 0.011964856 | +| clip_fraction | 0.323 | +| clip_range | 0.0654 | +| entropy_loss | -5.99 | +| explained_variance | 0.349 | +| learning_rate | 4.09e-05 | +| loss | -0.0302 | +| n_updates | 90664 | +| policy_gradient_loss | -0.0143 | +| value_loss | 0.000171 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1388 | +| iterations | 18713 | +| time_elapsed | 27594 | +| total_timesteps | 38324224 | +| train/ | | +| approx_kl | 0.016250167 | +| clip_fraction | 0.35 | +| clip_range | 0.0654 | +| entropy_loss | -5.64 | +| explained_variance | 0.478 | +| learning_rate | 4.09e-05 | +| loss | -0.0206 | +| n_updates | 90668 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000217 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1388 | +| iterations | 18714 | +| time_elapsed | 27595 | +| total_timesteps | 38326272 | +| train/ | | +| approx_kl | 0.013889293 | +| clip_fraction | 0.355 | +| clip_range | 0.0654 | +| entropy_loss | -6.01 | +| explained_variance | 0.41 | +| learning_rate | 4.09e-05 | +| loss | -0.0343 | +| n_updates | 90672 | +| policy_gradient_loss | -0.0203 | +| value_loss | 8.87e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1388 | +| iterations | 18715 | +| time_elapsed | 27597 | +| total_timesteps | 38328320 | +| train/ | | +| approx_kl | 0.010952408 | +| clip_fraction | 0.324 | +| clip_range | 0.0654 | +| entropy_loss | -5.87 | +| explained_variance | 0.285 | +| learning_rate | 4.09e-05 | +| loss | -0.0234 | +| n_updates | 90676 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000366 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1388 | +| iterations | 18716 | +| time_elapsed | 27599 | +| total_timesteps | 38330368 | +| train/ | | +| approx_kl | 0.014547838 | +| clip_fraction | 0.322 | +| clip_range | 0.0654 | +| entropy_loss | -5.17 | +| explained_variance | 0.619 | +| learning_rate | 4.09e-05 | +| loss | -0.0289 | +| n_updates | 90680 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000131 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1388 | +| iterations | 18717 | +| time_elapsed | 27600 | +| total_timesteps | 38332416 | +| train/ | | +| approx_kl | 0.014818152 | +| clip_fraction | 0.352 | +| clip_range | 0.0654 | +| entropy_loss | -5.76 | +| explained_variance | -0.101 | +| learning_rate | 4.09e-05 | +| loss | -0.029 | +| n_updates | 90684 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000194 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1388 | +| iterations | 18718 | +| time_elapsed | 27602 | +| total_timesteps | 38334464 | +| train/ | | +| approx_kl | 0.013309065 | +| clip_fraction | 0.34 | +| clip_range | 0.0654 | +| entropy_loss | -6.21 | +| explained_variance | 0.035 | +| learning_rate | 4.09e-05 | +| loss | -0.0232 | +| n_updates | 90688 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000331 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1388 | +| iterations | 18719 | +| time_elapsed | 27603 | +| total_timesteps | 38336512 | +| train/ | | +| approx_kl | 0.016368886 | +| clip_fraction | 0.351 | +| clip_range | 0.0654 | +| entropy_loss | -5.27 | +| explained_variance | 0.369 | +| learning_rate | 4.09e-05 | +| loss | -0.0333 | +| n_updates | 90692 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000105 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1388 | +| iterations | 18720 | +| time_elapsed | 27605 | +| total_timesteps | 38338560 | +| train/ | | +| approx_kl | 0.013874708 | +| clip_fraction | 0.346 | +| clip_range | 0.0654 | +| entropy_loss | -5.58 | +| explained_variance | 0.406 | +| learning_rate | 4.09e-05 | +| loss | -0.0237 | +| n_updates | 90696 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000154 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1388 | +| iterations | 18721 | +| time_elapsed | 27606 | +| total_timesteps | 38340608 | +| train/ | | +| approx_kl | 0.01712764 | +| clip_fraction | 0.393 | +| clip_range | 0.0654 | +| entropy_loss | -4.74 | +| explained_variance | 0.701 | +| learning_rate | 4.09e-05 | +| loss | -0.0339 | +| n_updates | 90700 | +| policy_gradient_loss | -0.021 | +| value_loss | 5.86e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1388 | +| iterations | 18722 | +| time_elapsed | 27608 | +| total_timesteps | 38342656 | +| train/ | | +| approx_kl | 0.016718294 | +| clip_fraction | 0.341 | +| clip_range | 0.0654 | +| entropy_loss | -5.29 | +| explained_variance | 0.648 | +| learning_rate | 4.09e-05 | +| loss | -0.0235 | +| n_updates | 90704 | +| policy_gradient_loss | -0.0163 | +| value_loss | 7.63e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1388 | +| iterations | 18723 | +| time_elapsed | 27609 | +| total_timesteps | 38344704 | +| train/ | | +| approx_kl | 0.014305493 | +| clip_fraction | 0.32 | +| clip_range | 0.0654 | +| entropy_loss | -5.93 | +| explained_variance | 0.375 | +| learning_rate | 4.09e-05 | +| loss | -0.0318 | +| n_updates | 90708 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000119 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1388 | +| iterations | 18724 | +| time_elapsed | 27611 | +| total_timesteps | 38346752 | +| train/ | | +| approx_kl | 0.011828927 | +| clip_fraction | 0.357 | +| clip_range | 0.0654 | +| entropy_loss | -6.08 | +| explained_variance | 0.431 | +| learning_rate | 4.09e-05 | +| loss | -0.0255 | +| n_updates | 90712 | +| policy_gradient_loss | -0.0167 | +| value_loss | 8.94e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1388 | +| iterations | 18725 | +| time_elapsed | 27613 | +| total_timesteps | 38348800 | +| train/ | | +| approx_kl | 0.014133796 | +| clip_fraction | 0.32 | +| clip_range | 0.0654 | +| entropy_loss | -5.35 | +| explained_variance | 0.633 | +| learning_rate | 4.09e-05 | +| loss | -0.0291 | +| n_updates | 90716 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000138 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1388 | +| iterations | 18726 | +| time_elapsed | 27614 | +| total_timesteps | 38350848 | +| train/ | | +| approx_kl | 0.01533484 | +| clip_fraction | 0.322 | +| clip_range | 0.0654 | +| entropy_loss | -4.81 | +| explained_variance | 0.437 | +| learning_rate | 4.09e-05 | +| loss | -0.0222 | +| n_updates | 90720 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000206 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1388 | +| iterations | 18727 | +| time_elapsed | 27616 | +| total_timesteps | 38352896 | +| train/ | | +| approx_kl | 0.014422245 | +| clip_fraction | 0.343 | +| clip_range | 0.0654 | +| entropy_loss | -4.61 | +| explained_variance | 0.77 | +| learning_rate | 4.09e-05 | +| loss | -0.0259 | +| n_updates | 90724 | +| policy_gradient_loss | -0.0185 | +| value_loss | 7.68e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1388 | +| iterations | 18728 | +| time_elapsed | 27617 | +| total_timesteps | 38354944 | +| train/ | | +| approx_kl | 0.01576876 | +| clip_fraction | 0.375 | +| clip_range | 0.0654 | +| entropy_loss | -5.45 | +| explained_variance | 0.17 | +| learning_rate | 4.09e-05 | +| loss | -0.0237 | +| n_updates | 90728 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000133 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1388 | +| iterations | 18729 | +| time_elapsed | 27619 | +| total_timesteps | 38356992 | +| train/ | | +| approx_kl | 0.016343068 | +| clip_fraction | 0.347 | +| clip_range | 0.0654 | +| entropy_loss | -5.28 | +| explained_variance | 0.648 | +| learning_rate | 4.09e-05 | +| loss | -0.0285 | +| n_updates | 90732 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000134 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1388 | +| iterations | 18730 | +| time_elapsed | 27620 | +| total_timesteps | 38359040 | +| train/ | | +| approx_kl | 0.014719461 | +| clip_fraction | 0.349 | +| clip_range | 0.0654 | +| entropy_loss | -5.38 | +| explained_variance | 0.292 | +| learning_rate | 4.09e-05 | +| loss | -0.026 | +| n_updates | 90736 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000141 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1388 | +| iterations | 18731 | +| time_elapsed | 27622 | +| total_timesteps | 38361088 | +| train/ | | +| approx_kl | 0.011105871 | +| clip_fraction | 0.327 | +| clip_range | 0.0654 | +| entropy_loss | -6.49 | +| explained_variance | -0.193 | +| learning_rate | 4.09e-05 | +| loss | -0.024 | +| n_updates | 90740 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000177 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1388 | +| iterations | 18732 | +| time_elapsed | 27623 | +| total_timesteps | 38363136 | +| train/ | | +| approx_kl | 0.01233448 | +| clip_fraction | 0.323 | +| clip_range | 0.0654 | +| entropy_loss | -6.06 | +| explained_variance | 0.211 | +| learning_rate | 4.09e-05 | +| loss | -0.0254 | +| n_updates | 90744 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000285 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1388 | +| iterations | 18733 | +| time_elapsed | 27625 | +| total_timesteps | 38365184 | +| train/ | | +| approx_kl | 0.012845874 | +| clip_fraction | 0.338 | +| clip_range | 0.0654 | +| entropy_loss | -5.48 | +| explained_variance | 0.368 | +| learning_rate | 4.09e-05 | +| loss | -0.0204 | +| n_updates | 90748 | +| policy_gradient_loss | -0.014 | +| value_loss | 0.000363 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1388 | +| iterations | 18734 | +| time_elapsed | 27626 | +| total_timesteps | 38367232 | +| train/ | | +| approx_kl | 0.015318814 | +| clip_fraction | 0.344 | +| clip_range | 0.0654 | +| entropy_loss | -5.4 | +| explained_variance | 0.43 | +| learning_rate | 4.09e-05 | +| loss | -0.0325 | +| n_updates | 90752 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000172 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1388 | +| iterations | 18735 | +| time_elapsed | 27628 | +| total_timesteps | 38369280 | +| train/ | | +| approx_kl | 0.013625916 | +| clip_fraction | 0.375 | +| clip_range | 0.0654 | +| entropy_loss | -5.54 | +| explained_variance | 0.552 | +| learning_rate | 4.09e-05 | +| loss | -0.0236 | +| n_updates | 90756 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000142 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1388 | +| iterations | 18736 | +| time_elapsed | 27630 | +| total_timesteps | 38371328 | +| train/ | | +| approx_kl | 0.017765123 | +| clip_fraction | 0.341 | +| clip_range | 0.0654 | +| entropy_loss | -5.07 | +| explained_variance | 0.432 | +| learning_rate | 4.09e-05 | +| loss | -0.0303 | +| n_updates | 90760 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000129 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1388 | +| iterations | 18737 | +| time_elapsed | 27631 | +| total_timesteps | 38373376 | +| train/ | | +| approx_kl | 0.013265045 | +| clip_fraction | 0.327 | +| clip_range | 0.0654 | +| entropy_loss | -5.11 | +| explained_variance | 0.659 | +| learning_rate | 4.09e-05 | +| loss | -0.0261 | +| n_updates | 90764 | +| policy_gradient_loss | -0.0176 | +| value_loss | 9.35e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1388 | +| iterations | 18738 | +| time_elapsed | 27633 | +| total_timesteps | 38375424 | +| train/ | | +| approx_kl | 0.011731979 | +| clip_fraction | 0.33 | +| clip_range | 0.0654 | +| entropy_loss | -5.49 | +| explained_variance | 0.557 | +| learning_rate | 4.09e-05 | +| loss | -0.0264 | +| n_updates | 90768 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000164 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1388 | +| iterations | 18739 | +| time_elapsed | 27634 | +| total_timesteps | 38377472 | +| train/ | | +| approx_kl | 0.014021341 | +| clip_fraction | 0.32 | +| clip_range | 0.0654 | +| entropy_loss | -4.98 | +| explained_variance | 0.203 | +| learning_rate | 4.09e-05 | +| loss | -0.0249 | +| n_updates | 90772 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.000173 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1388 | +| iterations | 18740 | +| time_elapsed | 27636 | +| total_timesteps | 38379520 | +| train/ | | +| approx_kl | 0.012703752 | +| clip_fraction | 0.346 | +| clip_range | 0.0654 | +| entropy_loss | -5.85 | +| explained_variance | 0.0812 | +| learning_rate | 4.09e-05 | +| loss | -0.0267 | +| n_updates | 90776 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000124 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1388 | +| iterations | 18741 | +| time_elapsed | 27637 | +| total_timesteps | 38381568 | +| train/ | | +| approx_kl | 0.012331982 | +| clip_fraction | 0.313 | +| clip_range | 0.0654 | +| entropy_loss | -6.79 | +| explained_variance | -0.0968 | +| learning_rate | 4.09e-05 | +| loss | -0.0291 | +| n_updates | 90780 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000189 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1388 | +| iterations | 18742 | +| time_elapsed | 27639 | +| total_timesteps | 38383616 | +| train/ | | +| approx_kl | 0.009662947 | +| clip_fraction | 0.3 | +| clip_range | 0.0654 | +| entropy_loss | -6.04 | +| explained_variance | 0.361 | +| learning_rate | 4.09e-05 | +| loss | -0.0225 | +| n_updates | 90784 | +| policy_gradient_loss | -0.0127 | +| value_loss | 0.000282 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1388 | +| iterations | 18743 | +| time_elapsed | 27641 | +| total_timesteps | 38385664 | +| train/ | | +| approx_kl | 0.014519136 | +| clip_fraction | 0.339 | +| clip_range | 0.0654 | +| entropy_loss | -5.26 | +| explained_variance | 0.459 | +| learning_rate | 4.09e-05 | +| loss | -0.0288 | +| n_updates | 90788 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000153 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1388 | +| iterations | 18744 | +| time_elapsed | 27642 | +| total_timesteps | 38387712 | +| train/ | | +| approx_kl | 0.015275537 | +| clip_fraction | 0.368 | +| clip_range | 0.0654 | +| entropy_loss | -5.3 | +| explained_variance | 0.309 | +| learning_rate | 4.09e-05 | +| loss | -0.0285 | +| n_updates | 90792 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000241 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1388 | +| iterations | 18745 | +| time_elapsed | 27644 | +| total_timesteps | 38389760 | +| train/ | | +| approx_kl | 0.013679474 | +| clip_fraction | 0.335 | +| clip_range | 0.0654 | +| entropy_loss | -4.58 | +| explained_variance | 0.625 | +| learning_rate | 4.09e-05 | +| loss | -0.0266 | +| n_updates | 90796 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000137 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1388 | +| iterations | 18746 | +| time_elapsed | 27645 | +| total_timesteps | 38391808 | +| train/ | | +| approx_kl | 0.015890753 | +| clip_fraction | 0.323 | +| clip_range | 0.0654 | +| entropy_loss | -5.52 | +| explained_variance | 0.336 | +| learning_rate | 4.09e-05 | +| loss | -0.0261 | +| n_updates | 90800 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000212 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1388 | +| iterations | 18747 | +| time_elapsed | 27647 | +| total_timesteps | 38393856 | +| train/ | | +| approx_kl | 0.014822807 | +| clip_fraction | 0.348 | +| clip_range | 0.0654 | +| entropy_loss | -5.15 | +| explained_variance | 0.393 | +| learning_rate | 4.09e-05 | +| loss | -0.0263 | +| n_updates | 90804 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000165 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1388 | +| iterations | 18748 | +| time_elapsed | 27648 | +| total_timesteps | 38395904 | +| train/ | | +| approx_kl | 0.016240478 | +| clip_fraction | 0.376 | +| clip_range | 0.0654 | +| entropy_loss | -5.76 | +| explained_variance | -0.0652 | +| learning_rate | 4.09e-05 | +| loss | -0.0324 | +| n_updates | 90808 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000102 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1388 | +| iterations | 18749 | +| time_elapsed | 27650 | +| total_timesteps | 38397952 | +| train/ | | +| approx_kl | 0.013404869 | +| clip_fraction | 0.367 | +| clip_range | 0.0654 | +| entropy_loss | -6.07 | +| explained_variance | 0.367 | +| learning_rate | 4.09e-05 | +| loss | -0.0369 | +| n_updates | 90812 | +| policy_gradient_loss | -0.0204 | +| value_loss | 8.18e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1388 | +| iterations | 18750 | +| time_elapsed | 27651 | +| total_timesteps | 38400000 | +| train/ | | +| approx_kl | 0.012891708 | +| clip_fraction | 0.354 | +| clip_range | 0.0654 | +| entropy_loss | -6.04 | +| explained_variance | 0.383 | +| learning_rate | 4.09e-05 | +| loss | -0.0186 | +| n_updates | 90816 | +| policy_gradient_loss | -0.0141 | +| value_loss | 0.000118 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1388 | +| iterations | 18751 | +| time_elapsed | 27653 | +| total_timesteps | 38402048 | +| train/ | | +| approx_kl | 0.014215042 | +| clip_fraction | 0.369 | +| clip_range | 0.0654 | +| entropy_loss | -5.71 | +| explained_variance | 0.343 | +| learning_rate | 4.09e-05 | +| loss | -0.0329 | +| n_updates | 90820 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000129 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1388 | +| iterations | 18752 | +| time_elapsed | 27654 | +| total_timesteps | 38404096 | +| train/ | | +| approx_kl | 0.012675676 | +| clip_fraction | 0.323 | +| clip_range | 0.0654 | +| entropy_loss | -6.03 | +| explained_variance | 0.151 | +| learning_rate | 4.09e-05 | +| loss | -0.0271 | +| n_updates | 90824 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000133 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1388 | +| iterations | 18753 | +| time_elapsed | 27656 | +| total_timesteps | 38406144 | +| train/ | | +| approx_kl | 0.0122023355 | +| clip_fraction | 0.336 | +| clip_range | 0.0654 | +| entropy_loss | -5.32 | +| explained_variance | 0.497 | +| learning_rate | 4.09e-05 | +| loss | -0.0229 | +| n_updates | 90828 | +| policy_gradient_loss | -0.0148 | +| value_loss | 0.000244 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1388 | +| iterations | 18754 | +| time_elapsed | 27657 | +| total_timesteps | 38408192 | +| train/ | | +| approx_kl | 0.01307302 | +| clip_fraction | 0.36 | +| clip_range | 0.0654 | +| entropy_loss | -5.63 | +| explained_variance | -0.0815 | +| learning_rate | 4.09e-05 | +| loss | -0.0274 | +| n_updates | 90832 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000125 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1388 | +| iterations | 18755 | +| time_elapsed | 27659 | +| total_timesteps | 38410240 | +| train/ | | +| approx_kl | 0.014246303 | +| clip_fraction | 0.347 | +| clip_range | 0.0654 | +| entropy_loss | -5.23 | +| explained_variance | 0.675 | +| learning_rate | 4.09e-05 | +| loss | -0.0277 | +| n_updates | 90836 | +| policy_gradient_loss | -0.0181 | +| value_loss | 9.93e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1388 | +| iterations | 18756 | +| time_elapsed | 27660 | +| total_timesteps | 38412288 | +| train/ | | +| approx_kl | 0.014966543 | +| clip_fraction | 0.343 | +| clip_range | 0.0654 | +| entropy_loss | -4.91 | +| explained_variance | 0.775 | +| learning_rate | 4.09e-05 | +| loss | -0.031 | +| n_updates | 90840 | +| policy_gradient_loss | -0.0197 | +| value_loss | 6.53e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1388 | +| iterations | 18757 | +| time_elapsed | 27662 | +| total_timesteps | 38414336 | +| train/ | | +| approx_kl | 0.015140561 | +| clip_fraction | 0.341 | +| clip_range | 0.0654 | +| entropy_loss | -5.95 | +| explained_variance | 0.578 | +| learning_rate | 4.09e-05 | +| loss | -0.0257 | +| n_updates | 90844 | +| policy_gradient_loss | -0.0163 | +| value_loss | 7.9e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1388 | +| iterations | 18758 | +| time_elapsed | 27663 | +| total_timesteps | 38416384 | +| train/ | | +| approx_kl | 0.01567858 | +| clip_fraction | 0.325 | +| clip_range | 0.0654 | +| entropy_loss | -5.76 | +| explained_variance | 0.361 | +| learning_rate | 4.09e-05 | +| loss | -0.0197 | +| n_updates | 90848 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.000159 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1388 | +| iterations | 18759 | +| time_elapsed | 27665 | +| total_timesteps | 38418432 | +| train/ | | +| approx_kl | 0.0144722145 | +| clip_fraction | 0.346 | +| clip_range | 0.0654 | +| entropy_loss | -5.36 | +| explained_variance | 0.697 | +| learning_rate | 4.09e-05 | +| loss | -0.0284 | +| n_updates | 90852 | +| policy_gradient_loss | -0.0174 | +| value_loss | 8.07e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1388 | +| iterations | 18760 | +| time_elapsed | 27666 | +| total_timesteps | 38420480 | +| train/ | | +| approx_kl | 0.015828466 | +| clip_fraction | 0.362 | +| clip_range | 0.0654 | +| entropy_loss | -5.54 | +| explained_variance | 0.331 | +| learning_rate | 4.09e-05 | +| loss | -0.0294 | +| n_updates | 90856 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000137 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1388 | +| iterations | 18761 | +| time_elapsed | 27668 | +| total_timesteps | 38422528 | +| train/ | | +| approx_kl | 0.015502168 | +| clip_fraction | 0.354 | +| clip_range | 0.0654 | +| entropy_loss | -5.61 | +| explained_variance | 0.392 | +| learning_rate | 4.09e-05 | +| loss | -0.0262 | +| n_updates | 90860 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000104 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1388 | +| iterations | 18762 | +| time_elapsed | 27670 | +| total_timesteps | 38424576 | +| train/ | | +| approx_kl | 0.013418598 | +| clip_fraction | 0.363 | +| clip_range | 0.0654 | +| entropy_loss | -5.81 | +| explained_variance | 0.294 | +| learning_rate | 4.09e-05 | +| loss | -0.0318 | +| n_updates | 90864 | +| policy_gradient_loss | -0.0198 | +| value_loss | 4.63e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1388 | +| iterations | 18763 | +| time_elapsed | 27671 | +| total_timesteps | 38426624 | +| train/ | | +| approx_kl | 0.015474426 | +| clip_fraction | 0.354 | +| clip_range | 0.0654 | +| entropy_loss | -5.79 | +| explained_variance | 0.398 | +| learning_rate | 4.09e-05 | +| loss | -0.0265 | +| n_updates | 90868 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.00012 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1388 | +| iterations | 18764 | +| time_elapsed | 27673 | +| total_timesteps | 38428672 | +| train/ | | +| approx_kl | 0.015086772 | +| clip_fraction | 0.314 | +| clip_range | 0.0654 | +| entropy_loss | -4.86 | +| explained_variance | 0.774 | +| learning_rate | 4.09e-05 | +| loss | -0.0188 | +| n_updates | 90872 | +| policy_gradient_loss | -0.0143 | +| value_loss | 0.000101 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1388 | +| iterations | 18765 | +| time_elapsed | 27674 | +| total_timesteps | 38430720 | +| train/ | | +| approx_kl | 0.015931387 | +| clip_fraction | 0.355 | +| clip_range | 0.0654 | +| entropy_loss | -4.73 | +| explained_variance | 0.351 | +| learning_rate | 4.09e-05 | +| loss | -0.0274 | +| n_updates | 90876 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000134 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1388 | +| iterations | 18766 | +| time_elapsed | 27676 | +| total_timesteps | 38432768 | +| train/ | | +| approx_kl | 0.012175493 | +| clip_fraction | 0.343 | +| clip_range | 0.0654 | +| entropy_loss | -6.08 | +| explained_variance | 0.192 | +| learning_rate | 4.09e-05 | +| loss | -0.0245 | +| n_updates | 90880 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000166 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1388 | +| iterations | 18767 | +| time_elapsed | 27677 | +| total_timesteps | 38434816 | +| train/ | | +| approx_kl | 0.016752666 | +| clip_fraction | 0.377 | +| clip_range | 0.0654 | +| entropy_loss | -5.48 | +| explained_variance | 0.649 | +| learning_rate | 4.09e-05 | +| loss | -0.0304 | +| n_updates | 90884 | +| policy_gradient_loss | -0.0184 | +| value_loss | 7.95e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1388 | +| iterations | 18768 | +| time_elapsed | 27679 | +| total_timesteps | 38436864 | +| train/ | | +| approx_kl | 0.01690636 | +| clip_fraction | 0.325 | +| clip_range | 0.0654 | +| entropy_loss | -4.6 | +| explained_variance | 0.792 | +| learning_rate | 4.09e-05 | +| loss | -0.0237 | +| n_updates | 90888 | +| policy_gradient_loss | -0.0159 | +| value_loss | 6.32e-05 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1388 | +| iterations | 18769 | +| time_elapsed | 27680 | +| total_timesteps | 38438912 | +| train/ | | +| approx_kl | 0.0147075085 | +| clip_fraction | 0.342 | +| clip_range | 0.0654 | +| entropy_loss | -5.03 | +| explained_variance | 0.59 | +| learning_rate | 4.09e-05 | +| loss | -0.0264 | +| n_updates | 90892 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000113 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1388 | +| iterations | 18770 | +| time_elapsed | 27682 | +| total_timesteps | 38440960 | +| train/ | | +| approx_kl | 0.012853638 | +| clip_fraction | 0.353 | +| clip_range | 0.0654 | +| entropy_loss | -6.08 | +| explained_variance | -0.0239 | +| learning_rate | 4.09e-05 | +| loss | -0.0338 | +| n_updates | 90896 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000101 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1388 | +| iterations | 18771 | +| time_elapsed | 27683 | +| total_timesteps | 38443008 | +| train/ | | +| approx_kl | 0.013324355 | +| clip_fraction | 0.338 | +| clip_range | 0.0654 | +| entropy_loss | -5.93 | +| explained_variance | 0.462 | +| learning_rate | 4.09e-05 | +| loss | -0.0268 | +| n_updates | 90900 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000129 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1388 | +| iterations | 18772 | +| time_elapsed | 27685 | +| total_timesteps | 38445056 | +| train/ | | +| approx_kl | 0.01361585 | +| clip_fraction | 0.357 | +| clip_range | 0.0654 | +| entropy_loss | -5.92 | +| explained_variance | 0.477 | +| learning_rate | 4.09e-05 | +| loss | -0.0312 | +| n_updates | 90904 | +| policy_gradient_loss | -0.019 | +| value_loss | 9.22e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1388 | +| iterations | 18773 | +| time_elapsed | 27686 | +| total_timesteps | 38447104 | +| train/ | | +| approx_kl | 0.013140066 | +| clip_fraction | 0.327 | +| clip_range | 0.0654 | +| entropy_loss | -5.79 | +| explained_variance | 0.385 | +| learning_rate | 4.09e-05 | +| loss | -0.0206 | +| n_updates | 90908 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000112 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1388 | +| iterations | 18774 | +| time_elapsed | 27688 | +| total_timesteps | 38449152 | +| train/ | | +| approx_kl | 0.014695787 | +| clip_fraction | 0.31 | +| clip_range | 0.0654 | +| entropy_loss | -5.35 | +| explained_variance | 0.671 | +| learning_rate | 4.09e-05 | +| loss | -0.0239 | +| n_updates | 90912 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000146 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1388 | +| iterations | 18775 | +| time_elapsed | 27689 | +| total_timesteps | 38451200 | +| train/ | | +| approx_kl | 0.012863664 | +| clip_fraction | 0.317 | +| clip_range | 0.0654 | +| entropy_loss | -5.37 | +| explained_variance | 0.148 | +| learning_rate | 4.09e-05 | +| loss | -0.0259 | +| n_updates | 90916 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000163 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.302 | +| time/ | | +| fps | 1388 | +| iterations | 18776 | +| time_elapsed | 27691 | +| total_timesteps | 38453248 | +| train/ | | +| approx_kl | 0.014022269 | +| clip_fraction | 0.355 | +| clip_range | 0.0654 | +| entropy_loss | -5.34 | +| explained_variance | 0.431 | +| learning_rate | 4.09e-05 | +| loss | -0.0223 | +| n_updates | 90920 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.00016 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.297 | +| time/ | | +| fps | 1388 | +| iterations | 18777 | +| time_elapsed | 27693 | +| total_timesteps | 38455296 | +| train/ | | +| approx_kl | 0.01444288 | +| clip_fraction | 0.343 | +| clip_range | 0.0654 | +| entropy_loss | -5.48 | +| explained_variance | 0.821 | +| learning_rate | 4.09e-05 | +| loss | -0.032 | +| n_updates | 90924 | +| policy_gradient_loss | -0.0197 | +| value_loss | 6.2e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.295 | +| time/ | | +| fps | 1388 | +| iterations | 18778 | +| time_elapsed | 27694 | +| total_timesteps | 38457344 | +| train/ | | +| approx_kl | 0.010736676 | +| clip_fraction | 0.327 | +| clip_range | 0.0654 | +| entropy_loss | -5.44 | +| explained_variance | 0.657 | +| learning_rate | 4.09e-05 | +| loss | -0.0266 | +| n_updates | 90928 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000109 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 1388 | +| iterations | 18779 | +| time_elapsed | 27696 | +| total_timesteps | 38459392 | +| train/ | | +| approx_kl | 0.010066292 | +| clip_fraction | 0.337 | +| clip_range | 0.0654 | +| entropy_loss | -5.59 | +| explained_variance | 0.364 | +| learning_rate | 4.09e-05 | +| loss | -0.0204 | +| n_updates | 90932 | +| policy_gradient_loss | -0.0129 | +| value_loss | 0.000251 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 1388 | +| iterations | 18780 | +| time_elapsed | 27697 | +| total_timesteps | 38461440 | +| train/ | | +| approx_kl | 0.008086918 | +| clip_fraction | 0.28 | +| clip_range | 0.0654 | +| entropy_loss | -5.15 | +| explained_variance | 0.472 | +| learning_rate | 4.09e-05 | +| loss | -0.0207 | +| n_updates | 90936 | +| policy_gradient_loss | -0.0095 | +| value_loss | 0.000273 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 1388 | +| iterations | 18781 | +| time_elapsed | 27699 | +| total_timesteps | 38463488 | +| train/ | | +| approx_kl | 0.016719762 | +| clip_fraction | 0.328 | +| clip_range | 0.0654 | +| entropy_loss | -4.84 | +| explained_variance | 0.595 | +| learning_rate | 4.09e-05 | +| loss | -0.0254 | +| n_updates | 90940 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 1388 | +| iterations | 18782 | +| time_elapsed | 27700 | +| total_timesteps | 38465536 | +| train/ | | +| approx_kl | 0.017490169 | +| clip_fraction | 0.366 | +| clip_range | 0.0654 | +| entropy_loss | -5.23 | +| explained_variance | 0.539 | +| learning_rate | 4.09e-05 | +| loss | -0.0236 | +| n_updates | 90944 | +| policy_gradient_loss | -0.0185 | +| value_loss | 9.11e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 1388 | +| iterations | 18783 | +| time_elapsed | 27702 | +| total_timesteps | 38467584 | +| train/ | | +| approx_kl | 0.017433139 | +| clip_fraction | 0.366 | +| clip_range | 0.0654 | +| entropy_loss | -5.73 | +| explained_variance | -0.254 | +| learning_rate | 4.09e-05 | +| loss | -0.031 | +| n_updates | 90948 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000137 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 1388 | +| iterations | 18784 | +| time_elapsed | 27703 | +| total_timesteps | 38469632 | +| train/ | | +| approx_kl | 0.016776878 | +| clip_fraction | 0.337 | +| clip_range | 0.0654 | +| entropy_loss | -5.26 | +| explained_variance | 0.562 | +| learning_rate | 4.09e-05 | +| loss | -0.0297 | +| n_updates | 90952 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000169 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1388 | +| iterations | 18785 | +| time_elapsed | 27705 | +| total_timesteps | 38471680 | +| train/ | | +| approx_kl | 0.014427407 | +| clip_fraction | 0.335 | +| clip_range | 0.0654 | +| entropy_loss | -5.85 | +| explained_variance | -0.124 | +| learning_rate | 4.09e-05 | +| loss | -0.0259 | +| n_updates | 90956 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000106 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1388 | +| iterations | 18786 | +| time_elapsed | 27706 | +| total_timesteps | 38473728 | +| train/ | | +| approx_kl | 0.012453558 | +| clip_fraction | 0.359 | +| clip_range | 0.0654 | +| entropy_loss | -5.67 | +| explained_variance | 0.234 | +| learning_rate | 4.09e-05 | +| loss | -0.0248 | +| n_updates | 90960 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000415 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1388 | +| iterations | 18787 | +| time_elapsed | 27708 | +| total_timesteps | 38475776 | +| train/ | | +| approx_kl | 0.015050061 | +| clip_fraction | 0.371 | +| clip_range | 0.0654 | +| entropy_loss | -5.19 | +| explained_variance | 0.295 | +| learning_rate | 4.09e-05 | +| loss | -0.0288 | +| n_updates | 90964 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.00015 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1388 | +| iterations | 18788 | +| time_elapsed | 27709 | +| total_timesteps | 38477824 | +| train/ | | +| approx_kl | 0.012830875 | +| clip_fraction | 0.37 | +| clip_range | 0.0654 | +| entropy_loss | -6.06 | +| explained_variance | 0.0546 | +| learning_rate | 4.09e-05 | +| loss | -0.0332 | +| n_updates | 90968 | +| policy_gradient_loss | -0.0174 | +| value_loss | 9.87e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1388 | +| iterations | 18789 | +| time_elapsed | 27711 | +| total_timesteps | 38479872 | +| train/ | | +| approx_kl | 0.014423091 | +| clip_fraction | 0.321 | +| clip_range | 0.0654 | +| entropy_loss | -4.68 | +| explained_variance | 0.434 | +| learning_rate | 4.09e-05 | +| loss | -0.0209 | +| n_updates | 90972 | +| policy_gradient_loss | -0.0141 | +| value_loss | 0.000315 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1388 | +| iterations | 18790 | +| time_elapsed | 27712 | +| total_timesteps | 38481920 | +| train/ | | +| approx_kl | 0.014477435 | +| clip_fraction | 0.335 | +| clip_range | 0.0654 | +| entropy_loss | -4.68 | +| explained_variance | 0.691 | +| learning_rate | 4.09e-05 | +| loss | -0.028 | +| n_updates | 90976 | +| policy_gradient_loss | -0.0192 | +| value_loss | 8.68e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1388 | +| iterations | 18791 | +| time_elapsed | 27714 | +| total_timesteps | 38483968 | +| train/ | | +| approx_kl | 0.013671453 | +| clip_fraction | 0.351 | +| clip_range | 0.0654 | +| entropy_loss | -5.3 | +| explained_variance | 0.283 | +| learning_rate | 4.09e-05 | +| loss | -0.0193 | +| n_updates | 90980 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000179 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.315 | +| time/ | | +| fps | 1388 | +| iterations | 18792 | +| time_elapsed | 27715 | +| total_timesteps | 38486016 | +| train/ | | +| approx_kl | 0.020304602 | +| clip_fraction | 0.361 | +| clip_range | 0.0654 | +| entropy_loss | -4.84 | +| explained_variance | 0.324 | +| learning_rate | 4.09e-05 | +| loss | -0.0268 | +| n_updates | 90984 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000122 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1388 | +| iterations | 18793 | +| time_elapsed | 27717 | +| total_timesteps | 38488064 | +| train/ | | +| approx_kl | 0.020271469 | +| clip_fraction | 0.35 | +| clip_range | 0.0654 | +| entropy_loss | -5.65 | +| explained_variance | -0.0746 | +| learning_rate | 4.09e-05 | +| loss | -0.0247 | +| n_updates | 90988 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000123 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 1388 | +| iterations | 18794 | +| time_elapsed | 27718 | +| total_timesteps | 38490112 | +| train/ | | +| approx_kl | 0.015420485 | +| clip_fraction | 0.34 | +| clip_range | 0.0654 | +| entropy_loss | -5.56 | +| explained_variance | 0.589 | +| learning_rate | 4.09e-05 | +| loss | -0.0305 | +| n_updates | 90992 | +| policy_gradient_loss | -0.0176 | +| value_loss | 8.44e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1388 | +| iterations | 18795 | +| time_elapsed | 27720 | +| total_timesteps | 38492160 | +| train/ | | +| approx_kl | 0.015730402 | +| clip_fraction | 0.365 | +| clip_range | 0.0654 | +| entropy_loss | -5.73 | +| explained_variance | -0.0863 | +| learning_rate | 4.09e-05 | +| loss | -0.027 | +| n_updates | 90996 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000127 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1388 | +| iterations | 18796 | +| time_elapsed | 27721 | +| total_timesteps | 38494208 | +| train/ | | +| approx_kl | 0.01339062 | +| clip_fraction | 0.323 | +| clip_range | 0.0654 | +| entropy_loss | -5.35 | +| explained_variance | 0.544 | +| learning_rate | 4.09e-05 | +| loss | -0.0226 | +| n_updates | 91000 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000174 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1388 | +| iterations | 18797 | +| time_elapsed | 27723 | +| total_timesteps | 38496256 | +| train/ | | +| approx_kl | 0.01224279 | +| clip_fraction | 0.334 | +| clip_range | 0.0654 | +| entropy_loss | -6.04 | +| explained_variance | 0.419 | +| learning_rate | 4.09e-05 | +| loss | -0.0249 | +| n_updates | 91004 | +| policy_gradient_loss | -0.0143 | +| value_loss | 0.000164 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 1388 | +| iterations | 18798 | +| time_elapsed | 27724 | +| total_timesteps | 38498304 | +| train/ | | +| approx_kl | 0.010508785 | +| clip_fraction | 0.329 | +| clip_range | 0.0654 | +| entropy_loss | -6.25 | +| explained_variance | 0.358 | +| learning_rate | 4.09e-05 | +| loss | -0.0262 | +| n_updates | 91008 | +| policy_gradient_loss | -0.014 | +| value_loss | 0.000154 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 1388 | +| iterations | 18799 | +| time_elapsed | 27726 | +| total_timesteps | 38500352 | +| train/ | | +| approx_kl | 0.016674824 | +| clip_fraction | 0.332 | +| clip_range | 0.0654 | +| entropy_loss | -5.61 | +| explained_variance | 0.463 | +| learning_rate | 4.09e-05 | +| loss | -0.0241 | +| n_updates | 91012 | +| policy_gradient_loss | -0.0168 | +| value_loss | 8.01e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 1388 | +| iterations | 18800 | +| time_elapsed | 27727 | +| total_timesteps | 38502400 | +| train/ | | +| approx_kl | 0.013402926 | +| clip_fraction | 0.327 | +| clip_range | 0.0654 | +| entropy_loss | -4.74 | +| explained_variance | 0.619 | +| learning_rate | 4.09e-05 | +| loss | -0.0257 | +| n_updates | 91016 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000172 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 1388 | +| iterations | 18801 | +| time_elapsed | 27729 | +| total_timesteps | 38504448 | +| train/ | | +| approx_kl | 0.014380792 | +| clip_fraction | 0.309 | +| clip_range | 0.0654 | +| entropy_loss | -4.8 | +| explained_variance | 0.665 | +| learning_rate | 4.09e-05 | +| loss | -0.0226 | +| n_updates | 91020 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000121 | +----------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 1388 | +| iterations | 18802 | +| time_elapsed | 27730 | +| total_timesteps | 38506496 | +| train/ | | +| approx_kl | 0.013249 | +| clip_fraction | 0.33 | +| clip_range | 0.0654 | +| entropy_loss | -5.75 | +| explained_variance | 0.31 | +| learning_rate | 4.09e-05 | +| loss | -0.0235 | +| n_updates | 91024 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000189 | +-------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.302 | +| time/ | | +| fps | 1388 | +| iterations | 18803 | +| time_elapsed | 27732 | +| total_timesteps | 38508544 | +| train/ | | +| approx_kl | 0.016950302 | +| clip_fraction | 0.373 | +| clip_range | 0.0654 | +| entropy_loss | -5.96 | +| explained_variance | -0.172 | +| learning_rate | 4.09e-05 | +| loss | -0.031 | +| n_updates | 91028 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000128 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.302 | +| time/ | | +| fps | 1388 | +| iterations | 18804 | +| time_elapsed | 27733 | +| total_timesteps | 38510592 | +| train/ | | +| approx_kl | 0.011496127 | +| clip_fraction | 0.341 | +| clip_range | 0.0654 | +| entropy_loss | -5.67 | +| explained_variance | 0.328 | +| learning_rate | 4.09e-05 | +| loss | -0.0258 | +| n_updates | 91032 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000201 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.306 | +| time/ | | +| fps | 1388 | +| iterations | 18805 | +| time_elapsed | 27735 | +| total_timesteps | 38512640 | +| train/ | | +| approx_kl | 0.011338286 | +| clip_fraction | 0.343 | +| clip_range | 0.0654 | +| entropy_loss | -6.29 | +| explained_variance | -0.332 | +| learning_rate | 4.09e-05 | +| loss | -0.0306 | +| n_updates | 91036 | +| policy_gradient_loss | -0.0188 | +| value_loss | 9.41e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 1388 | +| iterations | 18806 | +| time_elapsed | 27737 | +| total_timesteps | 38514688 | +| train/ | | +| approx_kl | 0.014998897 | +| clip_fraction | 0.305 | +| clip_range | 0.0654 | +| entropy_loss | -6.3 | +| explained_variance | 0.274 | +| learning_rate | 4.09e-05 | +| loss | -0.023 | +| n_updates | 91040 | +| policy_gradient_loss | -0.0144 | +| value_loss | 0.000271 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.298 | +| time/ | | +| fps | 1388 | +| iterations | 18807 | +| time_elapsed | 27738 | +| total_timesteps | 38516736 | +| train/ | | +| approx_kl | 0.016981045 | +| clip_fraction | 0.331 | +| clip_range | 0.0654 | +| entropy_loss | -5.59 | +| explained_variance | 0.0605 | +| learning_rate | 4.09e-05 | +| loss | -0.0234 | +| n_updates | 91044 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000183 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.298 | +| time/ | | +| fps | 1388 | +| iterations | 18808 | +| time_elapsed | 27740 | +| total_timesteps | 38518784 | +| train/ | | +| approx_kl | 0.015062968 | +| clip_fraction | 0.347 | +| clip_range | 0.0654 | +| entropy_loss | -5.19 | +| explained_variance | 0.45 | +| learning_rate | 4.09e-05 | +| loss | -0.0291 | +| n_updates | 91048 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000152 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 1388 | +| iterations | 18809 | +| time_elapsed | 27741 | +| total_timesteps | 38520832 | +| train/ | | +| approx_kl | 0.015042493 | +| clip_fraction | 0.346 | +| clip_range | 0.0654 | +| entropy_loss | -5.09 | +| explained_variance | 0.732 | +| learning_rate | 4.09e-05 | +| loss | -0.0284 | +| n_updates | 91052 | +| policy_gradient_loss | -0.0198 | +| value_loss | 6.34e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.297 | +| time/ | | +| fps | 1388 | +| iterations | 18810 | +| time_elapsed | 27743 | +| total_timesteps | 38522880 | +| train/ | | +| approx_kl | 0.01155426 | +| clip_fraction | 0.321 | +| clip_range | 0.0654 | +| entropy_loss | -5.59 | +| explained_variance | 0.277 | +| learning_rate | 4.09e-05 | +| loss | -0.0272 | +| n_updates | 91056 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000142 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.293 | +| time/ | | +| fps | 1388 | +| iterations | 18811 | +| time_elapsed | 27744 | +| total_timesteps | 38524928 | +| train/ | | +| approx_kl | 0.011740563 | +| clip_fraction | 0.302 | +| clip_range | 0.0654 | +| entropy_loss | -5.57 | +| explained_variance | 0.516 | +| learning_rate | 4.09e-05 | +| loss | -0.0246 | +| n_updates | 91060 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000225 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 1388 | +| iterations | 18812 | +| time_elapsed | 27746 | +| total_timesteps | 38526976 | +| train/ | | +| approx_kl | 0.014354684 | +| clip_fraction | 0.344 | +| clip_range | 0.0654 | +| entropy_loss | -5.13 | +| explained_variance | 0.622 | +| learning_rate | 4.09e-05 | +| loss | -0.0274 | +| n_updates | 91064 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000134 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.293 | +| time/ | | +| fps | 1388 | +| iterations | 18813 | +| time_elapsed | 27747 | +| total_timesteps | 38529024 | +| train/ | | +| approx_kl | 0.014073149 | +| clip_fraction | 0.345 | +| clip_range | 0.0654 | +| entropy_loss | -5.1 | +| explained_variance | 0.22 | +| learning_rate | 4.08e-05 | +| loss | -0.0172 | +| n_updates | 91068 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.000291 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.293 | +| time/ | | +| fps | 1388 | +| iterations | 18814 | +| time_elapsed | 27749 | +| total_timesteps | 38531072 | +| train/ | | +| approx_kl | 0.013494581 | +| clip_fraction | 0.339 | +| clip_range | 0.0654 | +| entropy_loss | -5.26 | +| explained_variance | 0.589 | +| learning_rate | 4.08e-05 | +| loss | -0.0293 | +| n_updates | 91072 | +| policy_gradient_loss | -0.0178 | +| value_loss | 8.6e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.29 | +| time/ | | +| fps | 1388 | +| iterations | 18815 | +| time_elapsed | 27750 | +| total_timesteps | 38533120 | +| train/ | | +| approx_kl | 0.012436591 | +| clip_fraction | 0.38 | +| clip_range | 0.0654 | +| entropy_loss | -5.87 | +| explained_variance | -0.0739 | +| learning_rate | 4.08e-05 | +| loss | -0.0278 | +| n_updates | 91076 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000101 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.292 | +| time/ | | +| fps | 1388 | +| iterations | 18816 | +| time_elapsed | 27752 | +| total_timesteps | 38535168 | +| train/ | | +| approx_kl | 0.014920317 | +| clip_fraction | 0.354 | +| clip_range | 0.0654 | +| entropy_loss | -5.71 | +| explained_variance | 0.308 | +| learning_rate | 4.08e-05 | +| loss | -0.0262 | +| n_updates | 91080 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.00017 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.292 | +| time/ | | +| fps | 1388 | +| iterations | 18817 | +| time_elapsed | 27753 | +| total_timesteps | 38537216 | +| train/ | | +| approx_kl | 0.014185829 | +| clip_fraction | 0.333 | +| clip_range | 0.0654 | +| entropy_loss | -5.54 | +| explained_variance | 0.257 | +| learning_rate | 4.08e-05 | +| loss | -0.0238 | +| n_updates | 91084 | +| policy_gradient_loss | -0.0147 | +| value_loss | 0.000226 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.294 | +| time/ | | +| fps | 1388 | +| iterations | 18818 | +| time_elapsed | 27755 | +| total_timesteps | 38539264 | +| train/ | | +| approx_kl | 0.017868247 | +| clip_fraction | 0.362 | +| clip_range | 0.0654 | +| entropy_loss | -5.36 | +| explained_variance | 0.504 | +| learning_rate | 4.08e-05 | +| loss | -0.0252 | +| n_updates | 91088 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000128 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.302 | +| time/ | | +| fps | 1388 | +| iterations | 18819 | +| time_elapsed | 27756 | +| total_timesteps | 38541312 | +| train/ | | +| approx_kl | 0.0134006515 | +| clip_fraction | 0.364 | +| clip_range | 0.0654 | +| entropy_loss | -5.86 | +| explained_variance | 0.299 | +| learning_rate | 4.08e-05 | +| loss | -0.0271 | +| n_updates | 91092 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000163 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.304 | +| time/ | | +| fps | 1388 | +| iterations | 18820 | +| time_elapsed | 27758 | +| total_timesteps | 38543360 | +| train/ | | +| approx_kl | 0.011998106 | +| clip_fraction | 0.318 | +| clip_range | 0.0654 | +| entropy_loss | -5.15 | +| explained_variance | 0.491 | +| learning_rate | 4.08e-05 | +| loss | -0.0236 | +| n_updates | 91096 | +| policy_gradient_loss | -0.0142 | +| value_loss | 0.00032 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1388 | +| iterations | 18821 | +| time_elapsed | 27760 | +| total_timesteps | 38545408 | +| train/ | | +| approx_kl | 0.011279866 | +| clip_fraction | 0.35 | +| clip_range | 0.0654 | +| entropy_loss | -5.36 | +| explained_variance | 0.506 | +| learning_rate | 4.08e-05 | +| loss | -0.0308 | +| n_updates | 91100 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000174 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 1388 | +| iterations | 18822 | +| time_elapsed | 27761 | +| total_timesteps | 38547456 | +| train/ | | +| approx_kl | 0.012393919 | +| clip_fraction | 0.339 | +| clip_range | 0.0654 | +| entropy_loss | -5.47 | +| explained_variance | 0.274 | +| learning_rate | 4.08e-05 | +| loss | -0.0307 | +| n_updates | 91104 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000155 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.304 | +| time/ | | +| fps | 1388 | +| iterations | 18823 | +| time_elapsed | 27763 | +| total_timesteps | 38549504 | +| train/ | | +| approx_kl | 0.014257187 | +| clip_fraction | 0.328 | +| clip_range | 0.0654 | +| entropy_loss | -5.55 | +| explained_variance | 0.652 | +| learning_rate | 4.08e-05 | +| loss | -0.0276 | +| n_updates | 91108 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000107 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1388 | +| iterations | 18824 | +| time_elapsed | 27764 | +| total_timesteps | 38551552 | +| train/ | | +| approx_kl | 0.0116210915 | +| clip_fraction | 0.34 | +| clip_range | 0.0654 | +| entropy_loss | -5.64 | +| explained_variance | 0.355 | +| learning_rate | 4.08e-05 | +| loss | -0.024 | +| n_updates | 91112 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000203 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1388 | +| iterations | 18825 | +| time_elapsed | 27766 | +| total_timesteps | 38553600 | +| train/ | | +| approx_kl | 0.012989233 | +| clip_fraction | 0.302 | +| clip_range | 0.0654 | +| entropy_loss | -5.69 | +| explained_variance | 0.321 | +| learning_rate | 4.08e-05 | +| loss | -0.023 | +| n_updates | 91116 | +| policy_gradient_loss | -0.013 | +| value_loss | 0.000315 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1388 | +| iterations | 18826 | +| time_elapsed | 27767 | +| total_timesteps | 38555648 | +| train/ | | +| approx_kl | 0.012228946 | +| clip_fraction | 0.36 | +| clip_range | 0.0654 | +| entropy_loss | -5.91 | +| explained_variance | 0.27 | +| learning_rate | 4.08e-05 | +| loss | -0.0261 | +| n_updates | 91120 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000187 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1388 | +| iterations | 18827 | +| time_elapsed | 27769 | +| total_timesteps | 38557696 | +| train/ | | +| approx_kl | 0.016126137 | +| clip_fraction | 0.36 | +| clip_range | 0.0654 | +| entropy_loss | -5.83 | +| explained_variance | 0.18 | +| learning_rate | 4.08e-05 | +| loss | -0.021 | +| n_updates | 91124 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000162 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1388 | +| iterations | 18828 | +| time_elapsed | 27770 | +| total_timesteps | 38559744 | +| train/ | | +| approx_kl | 0.013961787 | +| clip_fraction | 0.336 | +| clip_range | 0.0654 | +| entropy_loss | -5.73 | +| explained_variance | 0.256 | +| learning_rate | 4.08e-05 | +| loss | -0.025 | +| n_updates | 91128 | +| policy_gradient_loss | -0.0148 | +| value_loss | 0.000239 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1388 | +| iterations | 18829 | +| time_elapsed | 27772 | +| total_timesteps | 38561792 | +| train/ | | +| approx_kl | 0.014115423 | +| clip_fraction | 0.333 | +| clip_range | 0.0654 | +| entropy_loss | -5.17 | +| explained_variance | 0.372 | +| learning_rate | 4.08e-05 | +| loss | -0.0266 | +| n_updates | 91132 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000393 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1388 | +| iterations | 18830 | +| time_elapsed | 27773 | +| total_timesteps | 38563840 | +| train/ | | +| approx_kl | 0.017316159 | +| clip_fraction | 0.382 | +| clip_range | 0.0654 | +| entropy_loss | -5.06 | +| explained_variance | 0.246 | +| learning_rate | 4.08e-05 | +| loss | -0.0277 | +| n_updates | 91136 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000137 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1388 | +| iterations | 18831 | +| time_elapsed | 27775 | +| total_timesteps | 38565888 | +| train/ | | +| approx_kl | 0.018984873 | +| clip_fraction | 0.417 | +| clip_range | 0.0654 | +| entropy_loss | -5.37 | +| explained_variance | 0.286 | +| learning_rate | 4.08e-05 | +| loss | -0.0385 | +| n_updates | 91140 | +| policy_gradient_loss | -0.0218 | +| value_loss | 8.09e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1388 | +| iterations | 18832 | +| time_elapsed | 27776 | +| total_timesteps | 38567936 | +| train/ | | +| approx_kl | 0.013940221 | +| clip_fraction | 0.364 | +| clip_range | 0.0654 | +| entropy_loss | -5.88 | +| explained_variance | -0.231 | +| learning_rate | 4.08e-05 | +| loss | -0.0286 | +| n_updates | 91144 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000122 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1388 | +| iterations | 18833 | +| time_elapsed | 27778 | +| total_timesteps | 38569984 | +| train/ | | +| approx_kl | 0.010204277 | +| clip_fraction | 0.337 | +| clip_range | 0.0654 | +| entropy_loss | -6.46 | +| explained_variance | 0.286 | +| learning_rate | 4.08e-05 | +| loss | -0.0268 | +| n_updates | 91148 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000199 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1388 | +| iterations | 18834 | +| time_elapsed | 27780 | +| total_timesteps | 38572032 | +| train/ | | +| approx_kl | 0.012828987 | +| clip_fraction | 0.348 | +| clip_range | 0.0654 | +| entropy_loss | -5.72 | +| explained_variance | 0.675 | +| learning_rate | 4.08e-05 | +| loss | -0.0228 | +| n_updates | 91152 | +| policy_gradient_loss | -0.017 | +| value_loss | 7.15e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1388 | +| iterations | 18835 | +| time_elapsed | 27781 | +| total_timesteps | 38574080 | +| train/ | | +| approx_kl | 0.011297802 | +| clip_fraction | 0.34 | +| clip_range | 0.0654 | +| entropy_loss | -5.42 | +| explained_variance | 0.741 | +| learning_rate | 4.08e-05 | +| loss | -0.0249 | +| n_updates | 91156 | +| policy_gradient_loss | -0.0168 | +| value_loss | 7.89e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1388 | +| iterations | 18836 | +| time_elapsed | 27783 | +| total_timesteps | 38576128 | +| train/ | | +| approx_kl | 0.023825867 | +| clip_fraction | 0.317 | +| clip_range | 0.0654 | +| entropy_loss | -5.2 | +| explained_variance | 0.493 | +| learning_rate | 4.08e-05 | +| loss | -0.0229 | +| n_updates | 91160 | +| policy_gradient_loss | -0.0125 | +| value_loss | 0.00017 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1388 | +| iterations | 18837 | +| time_elapsed | 27784 | +| total_timesteps | 38578176 | +| train/ | | +| approx_kl | 0.01764204 | +| clip_fraction | 0.362 | +| clip_range | 0.0654 | +| entropy_loss | -4.94 | +| explained_variance | 0.437 | +| learning_rate | 4.08e-05 | +| loss | -0.0303 | +| n_updates | 91164 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000177 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1388 | +| iterations | 18838 | +| time_elapsed | 27786 | +| total_timesteps | 38580224 | +| train/ | | +| approx_kl | 0.015689995 | +| clip_fraction | 0.358 | +| clip_range | 0.0654 | +| entropy_loss | -5.46 | +| explained_variance | 0.454 | +| learning_rate | 4.08e-05 | +| loss | -0.0267 | +| n_updates | 91168 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000129 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1388 | +| iterations | 18839 | +| time_elapsed | 27787 | +| total_timesteps | 38582272 | +| train/ | | +| approx_kl | 0.013562428 | +| clip_fraction | 0.323 | +| clip_range | 0.0654 | +| entropy_loss | -5.76 | +| explained_variance | -0.143 | +| learning_rate | 4.08e-05 | +| loss | -0.0246 | +| n_updates | 91172 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000288 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1388 | +| iterations | 18840 | +| time_elapsed | 27789 | +| total_timesteps | 38584320 | +| train/ | | +| approx_kl | 0.012329681 | +| clip_fraction | 0.331 | +| clip_range | 0.0654 | +| entropy_loss | -5.93 | +| explained_variance | 0.51 | +| learning_rate | 4.08e-05 | +| loss | -0.0291 | +| n_updates | 91176 | +| policy_gradient_loss | -0.0184 | +| value_loss | 9.25e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1388 | +| iterations | 18841 | +| time_elapsed | 27790 | +| total_timesteps | 38586368 | +| train/ | | +| approx_kl | 0.013487131 | +| clip_fraction | 0.373 | +| clip_range | 0.0654 | +| entropy_loss | -5.61 | +| explained_variance | 0.356 | +| learning_rate | 4.08e-05 | +| loss | -0.0327 | +| n_updates | 91180 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000133 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1388 | +| iterations | 18842 | +| time_elapsed | 27792 | +| total_timesteps | 38588416 | +| train/ | | +| approx_kl | 0.011490811 | +| clip_fraction | 0.335 | +| clip_range | 0.0654 | +| entropy_loss | -5.52 | +| explained_variance | 0.599 | +| learning_rate | 4.08e-05 | +| loss | -0.0254 | +| n_updates | 91184 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000146 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1388 | +| iterations | 18843 | +| time_elapsed | 27793 | +| total_timesteps | 38590464 | +| train/ | | +| approx_kl | 0.01565161 | +| clip_fraction | 0.365 | +| clip_range | 0.0654 | +| entropy_loss | -5.56 | +| explained_variance | 0.0346 | +| learning_rate | 4.08e-05 | +| loss | -0.0303 | +| n_updates | 91188 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000129 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1388 | +| iterations | 18844 | +| time_elapsed | 27795 | +| total_timesteps | 38592512 | +| train/ | | +| approx_kl | 0.016338613 | +| clip_fraction | 0.333 | +| clip_range | 0.0654 | +| entropy_loss | -5.86 | +| explained_variance | 0.524 | +| learning_rate | 4.08e-05 | +| loss | -0.0254 | +| n_updates | 91192 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000108 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1388 | +| iterations | 18845 | +| time_elapsed | 27797 | +| total_timesteps | 38594560 | +| train/ | | +| approx_kl | 0.01844619 | +| clip_fraction | 0.328 | +| clip_range | 0.0654 | +| entropy_loss | -4.72 | +| explained_variance | 0.732 | +| learning_rate | 4.08e-05 | +| loss | -0.0277 | +| n_updates | 91196 | +| policy_gradient_loss | -0.0173 | +| value_loss | 8.76e-05 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1388 | +| iterations | 18846 | +| time_elapsed | 27798 | +| total_timesteps | 38596608 | +| train/ | | +| approx_kl | 0.0150366975 | +| clip_fraction | 0.325 | +| clip_range | 0.0654 | +| entropy_loss | -4.84 | +| explained_variance | 0.294 | +| learning_rate | 4.08e-05 | +| loss | -0.0221 | +| n_updates | 91200 | +| policy_gradient_loss | -0.0142 | +| value_loss | 0.000275 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1388 | +| iterations | 18847 | +| time_elapsed | 27800 | +| total_timesteps | 38598656 | +| train/ | | +| approx_kl | 0.015240934 | +| clip_fraction | 0.347 | +| clip_range | 0.0654 | +| entropy_loss | -4.76 | +| explained_variance | 0.557 | +| learning_rate | 4.08e-05 | +| loss | -0.0286 | +| n_updates | 91204 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000146 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1388 | +| iterations | 18848 | +| time_elapsed | 27801 | +| total_timesteps | 38600704 | +| train/ | | +| approx_kl | 0.011022308 | +| clip_fraction | 0.331 | +| clip_range | 0.0654 | +| entropy_loss | -5.57 | +| explained_variance | 0.49 | +| learning_rate | 4.08e-05 | +| loss | -0.0261 | +| n_updates | 91208 | +| policy_gradient_loss | -0.0147 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1388 | +| iterations | 18849 | +| time_elapsed | 27803 | +| total_timesteps | 38602752 | +| train/ | | +| approx_kl | 0.013345453 | +| clip_fraction | 0.337 | +| clip_range | 0.0653 | +| entropy_loss | -6.08 | +| explained_variance | 0.00431 | +| learning_rate | 4.08e-05 | +| loss | -0.0268 | +| n_updates | 91212 | +| policy_gradient_loss | -0.0181 | +| value_loss | 9.49e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1388 | +| iterations | 18850 | +| time_elapsed | 27804 | +| total_timesteps | 38604800 | +| train/ | | +| approx_kl | 0.01493273 | +| clip_fraction | 0.344 | +| clip_range | 0.0653 | +| entropy_loss | -6.06 | +| explained_variance | 0.195 | +| learning_rate | 4.08e-05 | +| loss | -0.0253 | +| n_updates | 91216 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000148 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1388 | +| iterations | 18851 | +| time_elapsed | 27806 | +| total_timesteps | 38606848 | +| train/ | | +| approx_kl | 0.019393377 | +| clip_fraction | 0.329 | +| clip_range | 0.0653 | +| entropy_loss | -5.68 | +| explained_variance | 0.266 | +| learning_rate | 4.08e-05 | +| loss | -0.0224 | +| n_updates | 91220 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.000109 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1388 | +| iterations | 18852 | +| time_elapsed | 27807 | +| total_timesteps | 38608896 | +| train/ | | +| approx_kl | 0.013254179 | +| clip_fraction | 0.328 | +| clip_range | 0.0653 | +| entropy_loss | -5.34 | +| explained_variance | 0.47 | +| learning_rate | 4.08e-05 | +| loss | -0.0208 | +| n_updates | 91224 | +| policy_gradient_loss | -0.0139 | +| value_loss | 0.000236 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1388 | +| iterations | 18853 | +| time_elapsed | 27809 | +| total_timesteps | 38610944 | +| train/ | | +| approx_kl | 0.012890153 | +| clip_fraction | 0.345 | +| clip_range | 0.0653 | +| entropy_loss | -5.72 | +| explained_variance | 0.343 | +| learning_rate | 4.08e-05 | +| loss | -0.0266 | +| n_updates | 91228 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000155 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1388 | +| iterations | 18854 | +| time_elapsed | 27810 | +| total_timesteps | 38612992 | +| train/ | | +| approx_kl | 0.0103942435 | +| clip_fraction | 0.309 | +| clip_range | 0.0653 | +| entropy_loss | -5.64 | +| explained_variance | 0.503 | +| learning_rate | 4.08e-05 | +| loss | -0.024 | +| n_updates | 91232 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.00021 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1388 | +| iterations | 18855 | +| time_elapsed | 27812 | +| total_timesteps | 38615040 | +| train/ | | +| approx_kl | 0.011915553 | +| clip_fraction | 0.342 | +| clip_range | 0.0653 | +| entropy_loss | -5.7 | +| explained_variance | 0.613 | +| learning_rate | 4.08e-05 | +| loss | -0.0267 | +| n_updates | 91236 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000147 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1388 | +| iterations | 18856 | +| time_elapsed | 27814 | +| total_timesteps | 38617088 | +| train/ | | +| approx_kl | 0.012243318 | +| clip_fraction | 0.363 | +| clip_range | 0.0653 | +| entropy_loss | -6.4 | +| explained_variance | 0.101 | +| learning_rate | 4.08e-05 | +| loss | -0.0273 | +| n_updates | 91240 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000159 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1388 | +| iterations | 18857 | +| time_elapsed | 27815 | +| total_timesteps | 38619136 | +| train/ | | +| approx_kl | 0.014090044 | +| clip_fraction | 0.319 | +| clip_range | 0.0653 | +| entropy_loss | -6.03 | +| explained_variance | 0.423 | +| learning_rate | 4.08e-05 | +| loss | -0.0261 | +| n_updates | 91244 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000193 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1388 | +| iterations | 18858 | +| time_elapsed | 27817 | +| total_timesteps | 38621184 | +| train/ | | +| approx_kl | 0.011734121 | +| clip_fraction | 0.326 | +| clip_range | 0.0653 | +| entropy_loss | -5.94 | +| explained_variance | 0.295 | +| learning_rate | 4.08e-05 | +| loss | -0.0234 | +| n_updates | 91248 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000248 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1388 | +| iterations | 18859 | +| time_elapsed | 27818 | +| total_timesteps | 38623232 | +| train/ | | +| approx_kl | 0.013551691 | +| clip_fraction | 0.345 | +| clip_range | 0.0653 | +| entropy_loss | -5.44 | +| explained_variance | 0.555 | +| learning_rate | 4.08e-05 | +| loss | -0.0279 | +| n_updates | 91252 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.00013 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1388 | +| iterations | 18860 | +| time_elapsed | 27820 | +| total_timesteps | 38625280 | +| train/ | | +| approx_kl | 0.015404858 | +| clip_fraction | 0.377 | +| clip_range | 0.0653 | +| entropy_loss | -5.44 | +| explained_variance | 0.568 | +| learning_rate | 4.08e-05 | +| loss | -0.0251 | +| n_updates | 91256 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000174 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1388 | +| iterations | 18861 | +| time_elapsed | 27821 | +| total_timesteps | 38627328 | +| train/ | | +| approx_kl | 0.01587744 | +| clip_fraction | 0.336 | +| clip_range | 0.0653 | +| entropy_loss | -5.59 | +| explained_variance | 0.525 | +| learning_rate | 4.08e-05 | +| loss | -0.0236 | +| n_updates | 91260 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.00013 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1388 | +| iterations | 18862 | +| time_elapsed | 27823 | +| total_timesteps | 38629376 | +| train/ | | +| approx_kl | 0.013950175 | +| clip_fraction | 0.299 | +| clip_range | 0.0653 | +| entropy_loss | -5.94 | +| explained_variance | 0.371 | +| learning_rate | 4.08e-05 | +| loss | -0.0231 | +| n_updates | 91264 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000132 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1388 | +| iterations | 18863 | +| time_elapsed | 27824 | +| total_timesteps | 38631424 | +| train/ | | +| approx_kl | 0.012002416 | +| clip_fraction | 0.346 | +| clip_range | 0.0653 | +| entropy_loss | -5.83 | +| explained_variance | 0.389 | +| learning_rate | 4.08e-05 | +| loss | -0.0288 | +| n_updates | 91268 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000162 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1388 | +| iterations | 18864 | +| time_elapsed | 27826 | +| total_timesteps | 38633472 | +| train/ | | +| approx_kl | 0.012947509 | +| clip_fraction | 0.332 | +| clip_range | 0.0653 | +| entropy_loss | -6.34 | +| explained_variance | 0.197 | +| learning_rate | 4.08e-05 | +| loss | -0.0316 | +| n_updates | 91272 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000107 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1388 | +| iterations | 18865 | +| time_elapsed | 27827 | +| total_timesteps | 38635520 | +| train/ | | +| approx_kl | 0.010857023 | +| clip_fraction | 0.33 | +| clip_range | 0.0653 | +| entropy_loss | -6.04 | +| explained_variance | 0.191 | +| learning_rate | 4.08e-05 | +| loss | -0.0223 | +| n_updates | 91276 | +| policy_gradient_loss | -0.0143 | +| value_loss | 0.000405 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1388 | +| iterations | 18866 | +| time_elapsed | 27829 | +| total_timesteps | 38637568 | +| train/ | | +| approx_kl | 0.015685087 | +| clip_fraction | 0.345 | +| clip_range | 0.0653 | +| entropy_loss | -4.8 | +| explained_variance | 0.575 | +| learning_rate | 4.08e-05 | +| loss | -0.0291 | +| n_updates | 91280 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.00018 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1388 | +| iterations | 18867 | +| time_elapsed | 27830 | +| total_timesteps | 38639616 | +| train/ | | +| approx_kl | 0.012306618 | +| clip_fraction | 0.321 | +| clip_range | 0.0653 | +| entropy_loss | -3.99 | +| explained_variance | 0.673 | +| learning_rate | 4.08e-05 | +| loss | -0.0272 | +| n_updates | 91284 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000225 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1388 | +| iterations | 18868 | +| time_elapsed | 27832 | +| total_timesteps | 38641664 | +| train/ | | +| approx_kl | 0.01716345 | +| clip_fraction | 0.375 | +| clip_range | 0.0653 | +| entropy_loss | -4.84 | +| explained_variance | -0.501 | +| learning_rate | 4.08e-05 | +| loss | -0.0367 | +| n_updates | 91288 | +| policy_gradient_loss | -0.0222 | +| value_loss | 7.17e-05 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1388 | +| iterations | 18869 | +| time_elapsed | 27833 | +| total_timesteps | 38643712 | +| train/ | | +| approx_kl | 0.01359662 | +| clip_fraction | 0.367 | +| clip_range | 0.0653 | +| entropy_loss | -6.32 | +| explained_variance | -0.098 | +| learning_rate | 4.08e-05 | +| loss | -0.0273 | +| n_updates | 91292 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000131 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1388 | +| iterations | 18870 | +| time_elapsed | 27835 | +| total_timesteps | 38645760 | +| train/ | | +| approx_kl | 0.012920835 | +| clip_fraction | 0.339 | +| clip_range | 0.0653 | +| entropy_loss | -6.21 | +| explained_variance | 0.258 | +| learning_rate | 4.08e-05 | +| loss | -0.0302 | +| n_updates | 91296 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000175 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1388 | +| iterations | 18871 | +| time_elapsed | 27836 | +| total_timesteps | 38647808 | +| train/ | | +| approx_kl | 0.015945144 | +| clip_fraction | 0.337 | +| clip_range | 0.0653 | +| entropy_loss | -5.64 | +| explained_variance | 0.473 | +| learning_rate | 4.08e-05 | +| loss | -0.0247 | +| n_updates | 91300 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000178 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1388 | +| iterations | 18872 | +| time_elapsed | 27838 | +| total_timesteps | 38649856 | +| train/ | | +| approx_kl | 0.01545364 | +| clip_fraction | 0.355 | +| clip_range | 0.0653 | +| entropy_loss | -5.67 | +| explained_variance | 0.436 | +| learning_rate | 4.08e-05 | +| loss | -0.0253 | +| n_updates | 91304 | +| policy_gradient_loss | -0.019 | +| value_loss | 9.33e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1388 | +| iterations | 18873 | +| time_elapsed | 27839 | +| total_timesteps | 38651904 | +| train/ | | +| approx_kl | 0.013579651 | +| clip_fraction | 0.358 | +| clip_range | 0.0653 | +| entropy_loss | -5.95 | +| explained_variance | 0.552 | +| learning_rate | 4.08e-05 | +| loss | -0.029 | +| n_updates | 91308 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000135 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1388 | +| iterations | 18874 | +| time_elapsed | 27841 | +| total_timesteps | 38653952 | +| train/ | | +| approx_kl | 0.011170159 | +| clip_fraction | 0.331 | +| clip_range | 0.0653 | +| entropy_loss | -6.1 | +| explained_variance | -0.0394 | +| learning_rate | 4.08e-05 | +| loss | -0.0263 | +| n_updates | 91312 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.00017 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1388 | +| iterations | 18875 | +| time_elapsed | 27842 | +| total_timesteps | 38656000 | +| train/ | | +| approx_kl | 0.01247919 | +| clip_fraction | 0.327 | +| clip_range | 0.0653 | +| entropy_loss | -6.21 | +| explained_variance | 0.299 | +| learning_rate | 4.08e-05 | +| loss | -0.0256 | +| n_updates | 91316 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000169 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1388 | +| iterations | 18876 | +| time_elapsed | 27844 | +| total_timesteps | 38658048 | +| train/ | | +| approx_kl | 0.014335197 | +| clip_fraction | 0.306 | +| clip_range | 0.0653 | +| entropy_loss | -5.61 | +| explained_variance | 0.271 | +| learning_rate | 4.08e-05 | +| loss | -0.024 | +| n_updates | 91320 | +| policy_gradient_loss | -0.0128 | +| value_loss | 0.000313 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1388 | +| iterations | 18877 | +| time_elapsed | 27845 | +| total_timesteps | 38660096 | +| train/ | | +| approx_kl | 0.018257698 | +| clip_fraction | 0.399 | +| clip_range | 0.0653 | +| entropy_loss | -5.04 | +| explained_variance | 0.618 | +| learning_rate | 4.08e-05 | +| loss | -0.0343 | +| n_updates | 91324 | +| policy_gradient_loss | -0.0224 | +| value_loss | 9.96e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1388 | +| iterations | 18878 | +| time_elapsed | 27847 | +| total_timesteps | 38662144 | +| train/ | | +| approx_kl | 0.015731797 | +| clip_fraction | 0.354 | +| clip_range | 0.0653 | +| entropy_loss | -5.58 | +| explained_variance | 0.178 | +| learning_rate | 4.08e-05 | +| loss | -0.0319 | +| n_updates | 91328 | +| policy_gradient_loss | -0.0183 | +| value_loss | 9.71e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1388 | +| iterations | 18879 | +| time_elapsed | 27848 | +| total_timesteps | 38664192 | +| train/ | | +| approx_kl | 0.0121055525 | +| clip_fraction | 0.289 | +| clip_range | 0.0653 | +| entropy_loss | -5.67 | +| explained_variance | 0.651 | +| learning_rate | 4.08e-05 | +| loss | -0.0203 | +| n_updates | 91332 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.000126 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1388 | +| iterations | 18880 | +| time_elapsed | 27850 | +| total_timesteps | 38666240 | +| train/ | | +| approx_kl | 0.015045433 | +| clip_fraction | 0.335 | +| clip_range | 0.0653 | +| entropy_loss | -5.99 | +| explained_variance | 0.135 | +| learning_rate | 4.08e-05 | +| loss | -0.0267 | +| n_updates | 91336 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000194 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1388 | +| iterations | 18881 | +| time_elapsed | 27851 | +| total_timesteps | 38668288 | +| train/ | | +| approx_kl | 0.010725211 | +| clip_fraction | 0.314 | +| clip_range | 0.0653 | +| entropy_loss | -5.82 | +| explained_variance | 0.341 | +| learning_rate | 4.08e-05 | +| loss | -0.0284 | +| n_updates | 91340 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000233 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1388 | +| iterations | 18882 | +| time_elapsed | 27853 | +| total_timesteps | 38670336 | +| train/ | | +| approx_kl | 0.012408648 | +| clip_fraction | 0.357 | +| clip_range | 0.0653 | +| entropy_loss | -5.79 | +| explained_variance | 0.581 | +| learning_rate | 4.08e-05 | +| loss | -0.0273 | +| n_updates | 91344 | +| policy_gradient_loss | -0.0181 | +| value_loss | 7.9e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1388 | +| iterations | 18883 | +| time_elapsed | 27855 | +| total_timesteps | 38672384 | +| train/ | | +| approx_kl | 0.010751152 | +| clip_fraction | 0.328 | +| clip_range | 0.0653 | +| entropy_loss | -6.22 | +| explained_variance | 0.309 | +| learning_rate | 4.08e-05 | +| loss | -0.0236 | +| n_updates | 91348 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000142 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1388 | +| iterations | 18884 | +| time_elapsed | 27856 | +| total_timesteps | 38674432 | +| train/ | | +| approx_kl | 0.01204573 | +| clip_fraction | 0.315 | +| clip_range | 0.0653 | +| entropy_loss | -5.61 | +| explained_variance | 0.437 | +| learning_rate | 4.08e-05 | +| loss | -0.018 | +| n_updates | 91352 | +| policy_gradient_loss | -0.0124 | +| value_loss | 0.000481 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1388 | +| iterations | 18885 | +| time_elapsed | 27858 | +| total_timesteps | 38676480 | +| train/ | | +| approx_kl | 0.013198858 | +| clip_fraction | 0.353 | +| clip_range | 0.0653 | +| entropy_loss | -4.82 | +| explained_variance | 0.619 | +| learning_rate | 4.08e-05 | +| loss | -0.0218 | +| n_updates | 91356 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000123 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1388 | +| iterations | 18886 | +| time_elapsed | 27859 | +| total_timesteps | 38678528 | +| train/ | | +| approx_kl | 0.014538683 | +| clip_fraction | 0.343 | +| clip_range | 0.0653 | +| entropy_loss | -5.35 | +| explained_variance | -0.0245 | +| learning_rate | 4.08e-05 | +| loss | -0.0305 | +| n_updates | 91360 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000124 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1388 | +| iterations | 18887 | +| time_elapsed | 27861 | +| total_timesteps | 38680576 | +| train/ | | +| approx_kl | 0.020839062 | +| clip_fraction | 0.348 | +| clip_range | 0.0653 | +| entropy_loss | -5.58 | +| explained_variance | 0.55 | +| learning_rate | 4.08e-05 | +| loss | -0.0265 | +| n_updates | 91364 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000143 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1388 | +| iterations | 18888 | +| time_elapsed | 27862 | +| total_timesteps | 38682624 | +| train/ | | +| approx_kl | 0.015088556 | +| clip_fraction | 0.326 | +| clip_range | 0.0653 | +| entropy_loss | -5.8 | +| explained_variance | 0.166 | +| learning_rate | 4.08e-05 | +| loss | -0.0259 | +| n_updates | 91368 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000179 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1388 | +| iterations | 18889 | +| time_elapsed | 27864 | +| total_timesteps | 38684672 | +| train/ | | +| approx_kl | 0.016088052 | +| clip_fraction | 0.352 | +| clip_range | 0.0653 | +| entropy_loss | -5.92 | +| explained_variance | 0.457 | +| learning_rate | 4.08e-05 | +| loss | -0.0289 | +| n_updates | 91372 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000179 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1388 | +| iterations | 18890 | +| time_elapsed | 27865 | +| total_timesteps | 38686720 | +| train/ | | +| approx_kl | 0.015324479 | +| clip_fraction | 0.36 | +| clip_range | 0.0653 | +| entropy_loss | -5.24 | +| explained_variance | 0.242 | +| learning_rate | 4.08e-05 | +| loss | -0.032 | +| n_updates | 91376 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1388 | +| iterations | 18891 | +| time_elapsed | 27867 | +| total_timesteps | 38688768 | +| train/ | | +| approx_kl | 0.013586467 | +| clip_fraction | 0.337 | +| clip_range | 0.0653 | +| entropy_loss | -5.67 | +| explained_variance | 0.251 | +| learning_rate | 4.08e-05 | +| loss | -0.0258 | +| n_updates | 91380 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000266 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1388 | +| iterations | 18892 | +| time_elapsed | 27868 | +| total_timesteps | 38690816 | +| train/ | | +| approx_kl | 0.008912938 | +| clip_fraction | 0.293 | +| clip_range | 0.0653 | +| entropy_loss | -6.14 | +| explained_variance | -0.128 | +| learning_rate | 4.08e-05 | +| loss | -0.0216 | +| n_updates | 91384 | +| policy_gradient_loss | -0.0142 | +| value_loss | 0.000225 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1388 | +| iterations | 18893 | +| time_elapsed | 27870 | +| total_timesteps | 38692864 | +| train/ | | +| approx_kl | 0.014779711 | +| clip_fraction | 0.323 | +| clip_range | 0.0653 | +| entropy_loss | -4.9 | +| explained_variance | 0.643 | +| learning_rate | 4.08e-05 | +| loss | -0.0266 | +| n_updates | 91388 | +| policy_gradient_loss | -0.0146 | +| value_loss | 0.000178 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1388 | +| iterations | 18894 | +| time_elapsed | 27871 | +| total_timesteps | 38694912 | +| train/ | | +| approx_kl | 0.013437426 | +| clip_fraction | 0.323 | +| clip_range | 0.0653 | +| entropy_loss | -5.13 | +| explained_variance | 0.497 | +| learning_rate | 4.08e-05 | +| loss | -0.025 | +| n_updates | 91392 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000204 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1388 | +| iterations | 18895 | +| time_elapsed | 27873 | +| total_timesteps | 38696960 | +| train/ | | +| approx_kl | 0.01342232 | +| clip_fraction | 0.335 | +| clip_range | 0.0653 | +| entropy_loss | -5.31 | +| explained_variance | 0.5 | +| learning_rate | 4.08e-05 | +| loss | -0.0241 | +| n_updates | 91396 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000138 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1388 | +| iterations | 18896 | +| time_elapsed | 27874 | +| total_timesteps | 38699008 | +| train/ | | +| approx_kl | 0.015722124 | +| clip_fraction | 0.343 | +| clip_range | 0.0653 | +| entropy_loss | -5.58 | +| explained_variance | -0.0787 | +| learning_rate | 4.08e-05 | +| loss | -0.0294 | +| n_updates | 91400 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000135 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1388 | +| iterations | 18897 | +| time_elapsed | 27876 | +| total_timesteps | 38701056 | +| train/ | | +| approx_kl | 0.014205694 | +| clip_fraction | 0.344 | +| clip_range | 0.0653 | +| entropy_loss | -5.5 | +| explained_variance | 0.402 | +| learning_rate | 4.08e-05 | +| loss | -0.0218 | +| n_updates | 91404 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000207 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1388 | +| iterations | 18898 | +| time_elapsed | 27877 | +| total_timesteps | 38703104 | +| train/ | | +| approx_kl | 0.014946391 | +| clip_fraction | 0.347 | +| clip_range | 0.0653 | +| entropy_loss | -5.2 | +| explained_variance | 0.805 | +| learning_rate | 4.08e-05 | +| loss | -0.0281 | +| n_updates | 91408 | +| policy_gradient_loss | -0.0186 | +| value_loss | 5.76e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1388 | +| iterations | 18899 | +| time_elapsed | 27879 | +| total_timesteps | 38705152 | +| train/ | | +| approx_kl | 0.014731875 | +| clip_fraction | 0.35 | +| clip_range | 0.0653 | +| entropy_loss | -5.48 | +| explained_variance | 0.131 | +| learning_rate | 4.08e-05 | +| loss | -0.0294 | +| n_updates | 91412 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000143 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1388 | +| iterations | 18900 | +| time_elapsed | 27880 | +| total_timesteps | 38707200 | +| train/ | | +| approx_kl | 0.013900582 | +| clip_fraction | 0.341 | +| clip_range | 0.0653 | +| entropy_loss | -5.25 | +| explained_variance | 0.558 | +| learning_rate | 4.08e-05 | +| loss | -0.0231 | +| n_updates | 91416 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000182 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1388 | +| iterations | 18901 | +| time_elapsed | 27882 | +| total_timesteps | 38709248 | +| train/ | | +| approx_kl | 0.015274512 | +| clip_fraction | 0.354 | +| clip_range | 0.0653 | +| entropy_loss | -5.64 | +| explained_variance | 0.269 | +| learning_rate | 4.08e-05 | +| loss | -0.0278 | +| n_updates | 91420 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000163 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1388 | +| iterations | 18902 | +| time_elapsed | 27883 | +| total_timesteps | 38711296 | +| train/ | | +| approx_kl | 0.015486388 | +| clip_fraction | 0.357 | +| clip_range | 0.0653 | +| entropy_loss | -5.63 | +| explained_variance | 0.712 | +| learning_rate | 4.08e-05 | +| loss | -0.0333 | +| n_updates | 91424 | +| policy_gradient_loss | -0.0207 | +| value_loss | 8.69e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1388 | +| iterations | 18903 | +| time_elapsed | 27885 | +| total_timesteps | 38713344 | +| train/ | | +| approx_kl | 0.011843797 | +| clip_fraction | 0.345 | +| clip_range | 0.0653 | +| entropy_loss | -6.05 | +| explained_variance | -0.173 | +| learning_rate | 4.08e-05 | +| loss | -0.0272 | +| n_updates | 91428 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000105 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1388 | +| iterations | 18904 | +| time_elapsed | 27886 | +| total_timesteps | 38715392 | +| train/ | | +| approx_kl | 0.015096038 | +| clip_fraction | 0.325 | +| clip_range | 0.0653 | +| entropy_loss | -6.05 | +| explained_variance | 0.585 | +| learning_rate | 4.08e-05 | +| loss | -0.0215 | +| n_updates | 91432 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.000154 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1388 | +| iterations | 18905 | +| time_elapsed | 27888 | +| total_timesteps | 38717440 | +| train/ | | +| approx_kl | 0.011658468 | +| clip_fraction | 0.302 | +| clip_range | 0.0653 | +| entropy_loss | -5.74 | +| explained_variance | 0.371 | +| learning_rate | 4.08e-05 | +| loss | -0.0204 | +| n_updates | 91436 | +| policy_gradient_loss | -0.0128 | +| value_loss | 0.000285 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1388 | +| iterations | 18906 | +| time_elapsed | 27889 | +| total_timesteps | 38719488 | +| train/ | | +| approx_kl | 0.009148521 | +| clip_fraction | 0.321 | +| clip_range | 0.0653 | +| entropy_loss | -5.57 | +| explained_variance | 0.324 | +| learning_rate | 4.08e-05 | +| loss | -0.0155 | +| n_updates | 91440 | +| policy_gradient_loss | -0.0119 | +| value_loss | 0.000444 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1388 | +| iterations | 18907 | +| time_elapsed | 27891 | +| total_timesteps | 38721536 | +| train/ | | +| approx_kl | 0.018565897 | +| clip_fraction | 0.372 | +| clip_range | 0.0653 | +| entropy_loss | -4.94 | +| explained_variance | 0.746 | +| learning_rate | 4.08e-05 | +| loss | -0.0322 | +| n_updates | 91444 | +| policy_gradient_loss | -0.0207 | +| value_loss | 6.95e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1388 | +| iterations | 18908 | +| time_elapsed | 27893 | +| total_timesteps | 38723584 | +| train/ | | +| approx_kl | 0.012706883 | +| clip_fraction | 0.343 | +| clip_range | 0.0653 | +| entropy_loss | -5.35 | +| explained_variance | 0.617 | +| learning_rate | 4.08e-05 | +| loss | -0.0299 | +| n_updates | 91448 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000121 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1388 | +| iterations | 18909 | +| time_elapsed | 27894 | +| total_timesteps | 38725632 | +| train/ | | +| approx_kl | 0.016677894 | +| clip_fraction | 0.361 | +| clip_range | 0.0653 | +| entropy_loss | -5.06 | +| explained_variance | 0.546 | +| learning_rate | 4.08e-05 | +| loss | -0.0215 | +| n_updates | 91452 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000162 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1388 | +| iterations | 18910 | +| time_elapsed | 27896 | +| total_timesteps | 38727680 | +| train/ | | +| approx_kl | 0.015075802 | +| clip_fraction | 0.353 | +| clip_range | 0.0653 | +| entropy_loss | -5.61 | +| explained_variance | 0.369 | +| learning_rate | 4.08e-05 | +| loss | -0.0213 | +| n_updates | 91456 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000251 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1388 | +| iterations | 18911 | +| time_elapsed | 27897 | +| total_timesteps | 38729728 | +| train/ | | +| approx_kl | 0.014444191 | +| clip_fraction | 0.367 | +| clip_range | 0.0653 | +| entropy_loss | -5.49 | +| explained_variance | 0.44 | +| learning_rate | 4.08e-05 | +| loss | -0.0261 | +| n_updates | 91460 | +| policy_gradient_loss | -0.0191 | +| value_loss | 9.15e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1388 | +| iterations | 18912 | +| time_elapsed | 27898 | +| total_timesteps | 38731776 | +| train/ | | +| approx_kl | 0.014553202 | +| clip_fraction | 0.332 | +| clip_range | 0.0653 | +| entropy_loss | -5.78 | +| explained_variance | 0.563 | +| learning_rate | 4.08e-05 | +| loss | -0.0315 | +| n_updates | 91464 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000117 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1388 | +| iterations | 18913 | +| time_elapsed | 27900 | +| total_timesteps | 38733824 | +| train/ | | +| approx_kl | 0.014263649 | +| clip_fraction | 0.342 | +| clip_range | 0.0653 | +| entropy_loss | -5.53 | +| explained_variance | 0.551 | +| learning_rate | 4.08e-05 | +| loss | -0.0248 | +| n_updates | 91468 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000158 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1388 | +| iterations | 18914 | +| time_elapsed | 27901 | +| total_timesteps | 38735872 | +| train/ | | +| approx_kl | 0.012904029 | +| clip_fraction | 0.353 | +| clip_range | 0.0653 | +| entropy_loss | -5.74 | +| explained_variance | 0.511 | +| learning_rate | 4.08e-05 | +| loss | -0.0263 | +| n_updates | 91472 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000136 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1388 | +| iterations | 18915 | +| time_elapsed | 27903 | +| total_timesteps | 38737920 | +| train/ | | +| approx_kl | 0.013272785 | +| clip_fraction | 0.346 | +| clip_range | 0.0653 | +| entropy_loss | -5.77 | +| explained_variance | -0.0271 | +| learning_rate | 4.08e-05 | +| loss | -0.0278 | +| n_updates | 91476 | +| policy_gradient_loss | -0.0142 | +| value_loss | 0.000245 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1388 | +| iterations | 18916 | +| time_elapsed | 27904 | +| total_timesteps | 38739968 | +| train/ | | +| approx_kl | 0.020420877 | +| clip_fraction | 0.397 | +| clip_range | 0.0653 | +| entropy_loss | -5.1 | +| explained_variance | 0.74 | +| learning_rate | 4.08e-05 | +| loss | -0.0369 | +| n_updates | 91480 | +| policy_gradient_loss | -0.0231 | +| value_loss | 5.01e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1388 | +| iterations | 18917 | +| time_elapsed | 27906 | +| total_timesteps | 38742016 | +| train/ | | +| approx_kl | 0.01705078 | +| clip_fraction | 0.368 | +| clip_range | 0.0653 | +| entropy_loss | -5.08 | +| explained_variance | 0.773 | +| learning_rate | 4.08e-05 | +| loss | -0.0246 | +| n_updates | 91484 | +| policy_gradient_loss | -0.0167 | +| value_loss | 6.27e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1388 | +| iterations | 18918 | +| time_elapsed | 27907 | +| total_timesteps | 38744064 | +| train/ | | +| approx_kl | 0.019044463 | +| clip_fraction | 0.326 | +| clip_range | 0.0653 | +| entropy_loss | -5.35 | +| explained_variance | 0.395 | +| learning_rate | 4.08e-05 | +| loss | -0.0301 | +| n_updates | 91488 | +| policy_gradient_loss | -0.0168 | +| value_loss | 9.85e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1388 | +| iterations | 18919 | +| time_elapsed | 27909 | +| total_timesteps | 38746112 | +| train/ | | +| approx_kl | 0.017358258 | +| clip_fraction | 0.35 | +| clip_range | 0.0653 | +| entropy_loss | -5.7 | +| explained_variance | 0.581 | +| learning_rate | 4.08e-05 | +| loss | -0.0279 | +| n_updates | 91492 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000105 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1388 | +| iterations | 18920 | +| time_elapsed | 27911 | +| total_timesteps | 38748160 | +| train/ | | +| approx_kl | 0.015941823 | +| clip_fraction | 0.323 | +| clip_range | 0.0653 | +| entropy_loss | -5.71 | +| explained_variance | 0.424 | +| learning_rate | 4.08e-05 | +| loss | -0.0206 | +| n_updates | 91496 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000232 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1388 | +| iterations | 18921 | +| time_elapsed | 27912 | +| total_timesteps | 38750208 | +| train/ | | +| approx_kl | 0.01631629 | +| clip_fraction | 0.383 | +| clip_range | 0.0653 | +| entropy_loss | -5.72 | +| explained_variance | -0.162 | +| learning_rate | 4.08e-05 | +| loss | -0.0284 | +| n_updates | 91500 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000145 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1388 | +| iterations | 18922 | +| time_elapsed | 27914 | +| total_timesteps | 38752256 | +| train/ | | +| approx_kl | 0.015016458 | +| clip_fraction | 0.367 | +| clip_range | 0.0653 | +| entropy_loss | -5.39 | +| explained_variance | 0.298 | +| learning_rate | 4.08e-05 | +| loss | -0.0304 | +| n_updates | 91504 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000298 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1388 | +| iterations | 18923 | +| time_elapsed | 27915 | +| total_timesteps | 38754304 | +| train/ | | +| approx_kl | 0.016950253 | +| clip_fraction | 0.371 | +| clip_range | 0.0653 | +| entropy_loss | -6 | +| explained_variance | -0.376 | +| learning_rate | 4.08e-05 | +| loss | -0.032 | +| n_updates | 91508 | +| policy_gradient_loss | -0.0198 | +| value_loss | 9.62e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1388 | +| iterations | 18924 | +| time_elapsed | 27917 | +| total_timesteps | 38756352 | +| train/ | | +| approx_kl | 0.01564805 | +| clip_fraction | 0.329 | +| clip_range | 0.0653 | +| entropy_loss | -6.21 | +| explained_variance | 0.533 | +| learning_rate | 4.08e-05 | +| loss | -0.0282 | +| n_updates | 91512 | +| policy_gradient_loss | -0.0186 | +| value_loss | 9.76e-05 | +---------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1388 | +| iterations | 18925 | +| time_elapsed | 27918 | +| total_timesteps | 38758400 | +| train/ | | +| approx_kl | 0.0158946 | +| clip_fraction | 0.32 | +| clip_range | 0.0653 | +| entropy_loss | -5.7 | +| explained_variance | 0.35 | +| learning_rate | 4.08e-05 | +| loss | -0.0229 | +| n_updates | 91516 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000115 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1388 | +| iterations | 18926 | +| time_elapsed | 27920 | +| total_timesteps | 38760448 | +| train/ | | +| approx_kl | 0.015585009 | +| clip_fraction | 0.368 | +| clip_range | 0.0653 | +| entropy_loss | -5.33 | +| explained_variance | 0.552 | +| learning_rate | 4.08e-05 | +| loss | -0.0262 | +| n_updates | 91520 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000176 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1388 | +| iterations | 18927 | +| time_elapsed | 27921 | +| total_timesteps | 38762496 | +| train/ | | +| approx_kl | 0.013864288 | +| clip_fraction | 0.335 | +| clip_range | 0.0653 | +| entropy_loss | -5.26 | +| explained_variance | 0.554 | +| learning_rate | 4.08e-05 | +| loss | -0.0254 | +| n_updates | 91524 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000135 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1388 | +| iterations | 18928 | +| time_elapsed | 27923 | +| total_timesteps | 38764544 | +| train/ | | +| approx_kl | 0.01635813 | +| clip_fraction | 0.344 | +| clip_range | 0.0653 | +| entropy_loss | -5.29 | +| explained_variance | 0.514 | +| learning_rate | 4.08e-05 | +| loss | -0.0245 | +| n_updates | 91528 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000115 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1388 | +| iterations | 18929 | +| time_elapsed | 27924 | +| total_timesteps | 38766592 | +| train/ | | +| approx_kl | 0.016429719 | +| clip_fraction | 0.351 | +| clip_range | 0.0653 | +| entropy_loss | -5.44 | +| explained_variance | 0.281 | +| learning_rate | 4.08e-05 | +| loss | -0.0264 | +| n_updates | 91532 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000149 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1388 | +| iterations | 18930 | +| time_elapsed | 27926 | +| total_timesteps | 38768640 | +| train/ | | +| approx_kl | 0.012712235 | +| clip_fraction | 0.339 | +| clip_range | 0.0653 | +| entropy_loss | -5.79 | +| explained_variance | 0.482 | +| learning_rate | 4.08e-05 | +| loss | -0.0274 | +| n_updates | 91536 | +| policy_gradient_loss | -0.0161 | +| value_loss | 9.46e-05 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1388 | +| iterations | 18931 | +| time_elapsed | 27927 | +| total_timesteps | 38770688 | +| train/ | | +| approx_kl | 0.0103111 | +| clip_fraction | 0.332 | +| clip_range | 0.0653 | +| entropy_loss | -6.12 | +| explained_variance | -0.0293 | +| learning_rate | 4.08e-05 | +| loss | -0.0243 | +| n_updates | 91540 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.0002 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1388 | +| iterations | 18932 | +| time_elapsed | 27929 | +| total_timesteps | 38772736 | +| train/ | | +| approx_kl | 0.016256955 | +| clip_fraction | 0.318 | +| clip_range | 0.0653 | +| entropy_loss | -5.35 | +| explained_variance | 0.389 | +| learning_rate | 4.08e-05 | +| loss | -0.0313 | +| n_updates | 91544 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000277 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1388 | +| iterations | 18933 | +| time_elapsed | 27930 | +| total_timesteps | 38774784 | +| train/ | | +| approx_kl | 0.012847608 | +| clip_fraction | 0.36 | +| clip_range | 0.0653 | +| entropy_loss | -5.56 | +| explained_variance | 0.191 | +| learning_rate | 4.08e-05 | +| loss | -0.0275 | +| n_updates | 91548 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000239 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1388 | +| iterations | 18934 | +| time_elapsed | 27932 | +| total_timesteps | 38776832 | +| train/ | | +| approx_kl | 0.014829068 | +| clip_fraction | 0.365 | +| clip_range | 0.0653 | +| entropy_loss | -5.52 | +| explained_variance | 0.504 | +| learning_rate | 4.08e-05 | +| loss | -0.0277 | +| n_updates | 91552 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000116 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1388 | +| iterations | 18935 | +| time_elapsed | 27933 | +| total_timesteps | 38778880 | +| train/ | | +| approx_kl | 0.014774681 | +| clip_fraction | 0.326 | +| clip_range | 0.0653 | +| entropy_loss | -5.34 | +| explained_variance | 0.36 | +| learning_rate | 4.08e-05 | +| loss | -0.0234 | +| n_updates | 91556 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000245 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1388 | +| iterations | 18936 | +| time_elapsed | 27935 | +| total_timesteps | 38780928 | +| train/ | | +| approx_kl | 0.01432343 | +| clip_fraction | 0.331 | +| clip_range | 0.0653 | +| entropy_loss | -4.93 | +| explained_variance | 0.451 | +| learning_rate | 4.08e-05 | +| loss | -0.0164 | +| n_updates | 91560 | +| policy_gradient_loss | -0.0142 | +| value_loss | 0.000305 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1388 | +| iterations | 18937 | +| time_elapsed | 27936 | +| total_timesteps | 38782976 | +| train/ | | +| approx_kl | 0.018236015 | +| clip_fraction | 0.364 | +| clip_range | 0.0653 | +| entropy_loss | -5.68 | +| explained_variance | 0.26 | +| learning_rate | 4.08e-05 | +| loss | -0.0286 | +| n_updates | 91564 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000216 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1388 | +| iterations | 18938 | +| time_elapsed | 27938 | +| total_timesteps | 38785024 | +| train/ | | +| approx_kl | 0.012700569 | +| clip_fraction | 0.347 | +| clip_range | 0.0653 | +| entropy_loss | -5.56 | +| explained_variance | 0.534 | +| learning_rate | 4.08e-05 | +| loss | -0.0305 | +| n_updates | 91568 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000124 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1388 | +| iterations | 18939 | +| time_elapsed | 27940 | +| total_timesteps | 38787072 | +| train/ | | +| approx_kl | 0.01672526 | +| clip_fraction | 0.371 | +| clip_range | 0.0653 | +| entropy_loss | -6.08 | +| explained_variance | 0.486 | +| learning_rate | 4.08e-05 | +| loss | -0.0332 | +| n_updates | 91572 | +| policy_gradient_loss | -0.0188 | +| value_loss | 8.22e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1388 | +| iterations | 18940 | +| time_elapsed | 27941 | +| total_timesteps | 38789120 | +| train/ | | +| approx_kl | 0.014772534 | +| clip_fraction | 0.364 | +| clip_range | 0.0653 | +| entropy_loss | -5.59 | +| explained_variance | -0.135 | +| learning_rate | 4.08e-05 | +| loss | -0.0248 | +| n_updates | 91576 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.00021 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1388 | +| iterations | 18941 | +| time_elapsed | 27943 | +| total_timesteps | 38791168 | +| train/ | | +| approx_kl | 0.017504923 | +| clip_fraction | 0.376 | +| clip_range | 0.0653 | +| entropy_loss | -5.55 | +| explained_variance | 0.39 | +| learning_rate | 4.08e-05 | +| loss | -0.0208 | +| n_updates | 91580 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000103 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1388 | +| iterations | 18942 | +| time_elapsed | 27944 | +| total_timesteps | 38793216 | +| train/ | | +| approx_kl | 0.012459411 | +| clip_fraction | 0.362 | +| clip_range | 0.0653 | +| entropy_loss | -5.93 | +| explained_variance | -0.173 | +| learning_rate | 4.08e-05 | +| loss | -0.0259 | +| n_updates | 91584 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000106 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1388 | +| iterations | 18943 | +| time_elapsed | 27946 | +| total_timesteps | 38795264 | +| train/ | | +| approx_kl | 0.015858136 | +| clip_fraction | 0.365 | +| clip_range | 0.0653 | +| entropy_loss | -5.55 | +| explained_variance | 0.581 | +| learning_rate | 4.08e-05 | +| loss | -0.0225 | +| n_updates | 91588 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000103 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.315 | +| time/ | | +| fps | 1388 | +| iterations | 18944 | +| time_elapsed | 27947 | +| total_timesteps | 38797312 | +| train/ | | +| approx_kl | 0.018274104 | +| clip_fraction | 0.344 | +| clip_range | 0.0653 | +| entropy_loss | -5.3 | +| explained_variance | 0.362 | +| learning_rate | 4.08e-05 | +| loss | -0.0207 | +| n_updates | 91592 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000312 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1388 | +| iterations | 18945 | +| time_elapsed | 27949 | +| total_timesteps | 38799360 | +| train/ | | +| approx_kl | 0.015179874 | +| clip_fraction | 0.351 | +| clip_range | 0.0653 | +| entropy_loss | -5.25 | +| explained_variance | 0.355 | +| learning_rate | 4.08e-05 | +| loss | -0.028 | +| n_updates | 91596 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000158 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1388 | +| iterations | 18946 | +| time_elapsed | 27950 | +| total_timesteps | 38801408 | +| train/ | | +| approx_kl | 0.014608491 | +| clip_fraction | 0.357 | +| clip_range | 0.0653 | +| entropy_loss | -5.58 | +| explained_variance | 0.241 | +| learning_rate | 4.08e-05 | +| loss | -0.0243 | +| n_updates | 91600 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000163 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1388 | +| iterations | 18947 | +| time_elapsed | 27952 | +| total_timesteps | 38803456 | +| train/ | | +| approx_kl | 0.012693831 | +| clip_fraction | 0.32 | +| clip_range | 0.0653 | +| entropy_loss | -4.91 | +| explained_variance | 0.539 | +| learning_rate | 4.08e-05 | +| loss | -0.0245 | +| n_updates | 91604 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000179 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1388 | +| iterations | 18948 | +| time_elapsed | 27953 | +| total_timesteps | 38805504 | +| train/ | | +| approx_kl | 0.013600853 | +| clip_fraction | 0.329 | +| clip_range | 0.0653 | +| entropy_loss | -5.68 | +| explained_variance | 0.42 | +| learning_rate | 4.08e-05 | +| loss | -0.0316 | +| n_updates | 91608 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000124 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1388 | +| iterations | 18949 | +| time_elapsed | 27955 | +| total_timesteps | 38807552 | +| train/ | | +| approx_kl | 0.014182436 | +| clip_fraction | 0.359 | +| clip_range | 0.0653 | +| entropy_loss | -5.84 | +| explained_variance | 0.313 | +| learning_rate | 4.08e-05 | +| loss | -0.0309 | +| n_updates | 91612 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000143 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1388 | +| iterations | 18950 | +| time_elapsed | 27956 | +| total_timesteps | 38809600 | +| train/ | | +| approx_kl | 0.010392208 | +| clip_fraction | 0.319 | +| clip_range | 0.0653 | +| entropy_loss | -6.03 | +| explained_variance | 0.315 | +| learning_rate | 4.08e-05 | +| loss | -0.0311 | +| n_updates | 91616 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.00013 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.315 | +| time/ | | +| fps | 1388 | +| iterations | 18951 | +| time_elapsed | 27958 | +| total_timesteps | 38811648 | +| train/ | | +| approx_kl | 0.014902222 | +| clip_fraction | 0.353 | +| clip_range | 0.0653 | +| entropy_loss | -5.5 | +| explained_variance | 0.443 | +| learning_rate | 4.08e-05 | +| loss | -0.0228 | +| n_updates | 91620 | +| policy_gradient_loss | -0.0147 | +| value_loss | 0.000278 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1388 | +| iterations | 18952 | +| time_elapsed | 27960 | +| total_timesteps | 38813696 | +| train/ | | +| approx_kl | 0.015287169 | +| clip_fraction | 0.359 | +| clip_range | 0.0653 | +| entropy_loss | -5.38 | +| explained_variance | 0.254 | +| learning_rate | 4.08e-05 | +| loss | -0.0244 | +| n_updates | 91624 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000131 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.315 | +| time/ | | +| fps | 1388 | +| iterations | 18953 | +| time_elapsed | 27961 | +| total_timesteps | 38815744 | +| train/ | | +| approx_kl | 0.01205808 | +| clip_fraction | 0.361 | +| clip_range | 0.0653 | +| entropy_loss | -6.16 | +| explained_variance | 0.253 | +| learning_rate | 4.08e-05 | +| loss | -0.0259 | +| n_updates | 91628 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000219 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 1388 | +| iterations | 18954 | +| time_elapsed | 27963 | +| total_timesteps | 38817792 | +| train/ | | +| approx_kl | 0.015028521 | +| clip_fraction | 0.349 | +| clip_range | 0.0653 | +| entropy_loss | -5.81 | +| explained_variance | 0.561 | +| learning_rate | 4.08e-05 | +| loss | -0.0358 | +| n_updates | 91632 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000117 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 1388 | +| iterations | 18955 | +| time_elapsed | 27964 | +| total_timesteps | 38819840 | +| train/ | | +| approx_kl | 0.013494836 | +| clip_fraction | 0.333 | +| clip_range | 0.0653 | +| entropy_loss | -5.24 | +| explained_variance | 0.705 | +| learning_rate | 4.08e-05 | +| loss | -0.0236 | +| n_updates | 91636 | +| policy_gradient_loss | -0.017 | +| value_loss | 9.03e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 1388 | +| iterations | 18956 | +| time_elapsed | 27966 | +| total_timesteps | 38821888 | +| train/ | | +| approx_kl | 0.011805401 | +| clip_fraction | 0.334 | +| clip_range | 0.0653 | +| entropy_loss | -5.7 | +| explained_variance | 0.412 | +| learning_rate | 4.08e-05 | +| loss | -0.0245 | +| n_updates | 91640 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000111 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 1388 | +| iterations | 18957 | +| time_elapsed | 27967 | +| total_timesteps | 38823936 | +| train/ | | +| approx_kl | 0.014764054 | +| clip_fraction | 0.35 | +| clip_range | 0.0653 | +| entropy_loss | -5.64 | +| explained_variance | 0.526 | +| learning_rate | 4.08e-05 | +| loss | -0.0308 | +| n_updates | 91644 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.00011 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.306 | +| time/ | | +| fps | 1388 | +| iterations | 18958 | +| time_elapsed | 27969 | +| total_timesteps | 38825984 | +| train/ | | +| approx_kl | 0.018601626 | +| clip_fraction | 0.367 | +| clip_range | 0.0653 | +| entropy_loss | -5.2 | +| explained_variance | -0.0939 | +| learning_rate | 4.08e-05 | +| loss | -0.0274 | +| n_updates | 91648 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000192 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1388 | +| iterations | 18959 | +| time_elapsed | 27970 | +| total_timesteps | 38828032 | +| train/ | | +| approx_kl | 0.016929124 | +| clip_fraction | 0.359 | +| clip_range | 0.0653 | +| entropy_loss | -5.46 | +| explained_variance | 0.0102 | +| learning_rate | 4.08e-05 | +| loss | -0.0237 | +| n_updates | 91652 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000246 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1388 | +| iterations | 18960 | +| time_elapsed | 27972 | +| total_timesteps | 38830080 | +| train/ | | +| approx_kl | 0.013250367 | +| clip_fraction | 0.357 | +| clip_range | 0.0653 | +| entropy_loss | -5.47 | +| explained_variance | 0.375 | +| learning_rate | 4.08e-05 | +| loss | -0.0204 | +| n_updates | 91656 | +| policy_gradient_loss | -0.0146 | +| value_loss | 0.000302 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1388 | +| iterations | 18961 | +| time_elapsed | 27973 | +| total_timesteps | 38832128 | +| train/ | | +| approx_kl | 0.013729434 | +| clip_fraction | 0.362 | +| clip_range | 0.0653 | +| entropy_loss | -5.23 | +| explained_variance | 0.0618 | +| learning_rate | 4.08e-05 | +| loss | -0.0318 | +| n_updates | 91660 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000123 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1388 | +| iterations | 18962 | +| time_elapsed | 27975 | +| total_timesteps | 38834176 | +| train/ | | +| approx_kl | 0.015275856 | +| clip_fraction | 0.366 | +| clip_range | 0.0653 | +| entropy_loss | -5.57 | +| explained_variance | 0.373 | +| learning_rate | 4.08e-05 | +| loss | -0.0272 | +| n_updates | 91664 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.00013 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1388 | +| iterations | 18963 | +| time_elapsed | 27976 | +| total_timesteps | 38836224 | +| train/ | | +| approx_kl | 0.011588389 | +| clip_fraction | 0.327 | +| clip_range | 0.0653 | +| entropy_loss | -5.51 | +| explained_variance | 0.361 | +| learning_rate | 4.08e-05 | +| loss | -0.0189 | +| n_updates | 91668 | +| policy_gradient_loss | -0.0143 | +| value_loss | 0.00027 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1388 | +| iterations | 18964 | +| time_elapsed | 27978 | +| total_timesteps | 38838272 | +| train/ | | +| approx_kl | 0.010064968 | +| clip_fraction | 0.335 | +| clip_range | 0.0653 | +| entropy_loss | -5.82 | +| explained_variance | 0.339 | +| learning_rate | 4.08e-05 | +| loss | -0.0242 | +| n_updates | 91672 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000235 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1388 | +| iterations | 18965 | +| time_elapsed | 27980 | +| total_timesteps | 38840320 | +| train/ | | +| approx_kl | 0.008714856 | +| clip_fraction | 0.308 | +| clip_range | 0.0653 | +| entropy_loss | -5.93 | +| explained_variance | 0.341 | +| learning_rate | 4.08e-05 | +| loss | -0.0254 | +| n_updates | 91676 | +| policy_gradient_loss | -0.0145 | +| value_loss | 0.000287 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1388 | +| iterations | 18966 | +| time_elapsed | 27981 | +| total_timesteps | 38842368 | +| train/ | | +| approx_kl | 0.011380356 | +| clip_fraction | 0.316 | +| clip_range | 0.0653 | +| entropy_loss | -5.62 | +| explained_variance | 0.495 | +| learning_rate | 4.08e-05 | +| loss | -0.0246 | +| n_updates | 91680 | +| policy_gradient_loss | -0.0146 | +| value_loss | 0.000253 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.306 | +| time/ | | +| fps | 1388 | +| iterations | 18967 | +| time_elapsed | 27983 | +| total_timesteps | 38844416 | +| train/ | | +| approx_kl | 0.014069272 | +| clip_fraction | 0.362 | +| clip_range | 0.0653 | +| entropy_loss | -6.09 | +| explained_variance | 0.345 | +| learning_rate | 4.08e-05 | +| loss | -0.0352 | +| n_updates | 91684 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000137 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1388 | +| iterations | 18968 | +| time_elapsed | 27984 | +| total_timesteps | 38846464 | +| train/ | | +| approx_kl | 0.014585011 | +| clip_fraction | 0.37 | +| clip_range | 0.0653 | +| entropy_loss | -6.18 | +| explained_variance | 0.403 | +| learning_rate | 4.08e-05 | +| loss | -0.029 | +| n_updates | 91688 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000183 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1388 | +| iterations | 18969 | +| time_elapsed | 27986 | +| total_timesteps | 38848512 | +| train/ | | +| approx_kl | 0.01455735 | +| clip_fraction | 0.321 | +| clip_range | 0.0653 | +| entropy_loss | -5.3 | +| explained_variance | 0.317 | +| learning_rate | 4.08e-05 | +| loss | -0.0256 | +| n_updates | 91692 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.000383 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1388 | +| iterations | 18970 | +| time_elapsed | 27987 | +| total_timesteps | 38850560 | +| train/ | | +| approx_kl | 0.021833703 | +| clip_fraction | 0.383 | +| clip_range | 0.0653 | +| entropy_loss | -5.23 | +| explained_variance | 0.058 | +| learning_rate | 4.08e-05 | +| loss | -0.0265 | +| n_updates | 91696 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000202 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1388 | +| iterations | 18971 | +| time_elapsed | 27989 | +| total_timesteps | 38852608 | +| train/ | | +| approx_kl | 0.01526935 | +| clip_fraction | 0.326 | +| clip_range | 0.0653 | +| entropy_loss | -5.91 | +| explained_variance | 0.268 | +| learning_rate | 4.08e-05 | +| loss | -0.0277 | +| n_updates | 91700 | +| policy_gradient_loss | -0.0147 | +| value_loss | 0.000306 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1388 | +| iterations | 18972 | +| time_elapsed | 27990 | +| total_timesteps | 38854656 | +| train/ | | +| approx_kl | 0.016650166 | +| clip_fraction | 0.364 | +| clip_range | 0.0653 | +| entropy_loss | -6.2 | +| explained_variance | 0.299 | +| learning_rate | 4.08e-05 | +| loss | -0.0349 | +| n_updates | 91704 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000106 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1388 | +| iterations | 18973 | +| time_elapsed | 27992 | +| total_timesteps | 38856704 | +| train/ | | +| approx_kl | 0.011075297 | +| clip_fraction | 0.311 | +| clip_range | 0.0653 | +| entropy_loss | -6.29 | +| explained_variance | 0.378 | +| learning_rate | 4.08e-05 | +| loss | -0.0295 | +| n_updates | 91708 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000214 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1388 | +| iterations | 18974 | +| time_elapsed | 27994 | +| total_timesteps | 38858752 | +| train/ | | +| approx_kl | 0.014191693 | +| clip_fraction | 0.348 | +| clip_range | 0.0653 | +| entropy_loss | -6.02 | +| explained_variance | -0.094 | +| learning_rate | 4.08e-05 | +| loss | -0.0302 | +| n_updates | 91712 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000152 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1388 | +| iterations | 18975 | +| time_elapsed | 27995 | +| total_timesteps | 38860800 | +| train/ | | +| approx_kl | 0.01653916 | +| clip_fraction | 0.349 | +| clip_range | 0.0653 | +| entropy_loss | -5.81 | +| explained_variance | 0.294 | +| learning_rate | 4.08e-05 | +| loss | -0.0275 | +| n_updates | 91716 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000265 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1388 | +| iterations | 18976 | +| time_elapsed | 27997 | +| total_timesteps | 38862848 | +| train/ | | +| approx_kl | 0.015422982 | +| clip_fraction | 0.349 | +| clip_range | 0.0653 | +| entropy_loss | -5.72 | +| explained_variance | 0.473 | +| learning_rate | 4.08e-05 | +| loss | -0.0363 | +| n_updates | 91720 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000147 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1388 | +| iterations | 18977 | +| time_elapsed | 27998 | +| total_timesteps | 38864896 | +| train/ | | +| approx_kl | 0.020422515 | +| clip_fraction | 0.339 | +| clip_range | 0.0653 | +| entropy_loss | -5.93 | +| explained_variance | 0.209 | +| learning_rate | 4.08e-05 | +| loss | -0.0229 | +| n_updates | 91724 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000299 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1388 | +| iterations | 18978 | +| time_elapsed | 28000 | +| total_timesteps | 38866944 | +| train/ | | +| approx_kl | 0.0127892075 | +| clip_fraction | 0.342 | +| clip_range | 0.0653 | +| entropy_loss | -5.76 | +| explained_variance | 0.302 | +| learning_rate | 4.08e-05 | +| loss | -0.0218 | +| n_updates | 91728 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000257 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1388 | +| iterations | 18979 | +| time_elapsed | 28001 | +| total_timesteps | 38868992 | +| train/ | | +| approx_kl | 0.012190768 | +| clip_fraction | 0.33 | +| clip_range | 0.0653 | +| entropy_loss | -6.47 | +| explained_variance | -0.13 | +| learning_rate | 4.08e-05 | +| loss | -0.0277 | +| n_updates | 91732 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000179 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1388 | +| iterations | 18980 | +| time_elapsed | 28003 | +| total_timesteps | 38871040 | +| train/ | | +| approx_kl | 0.013463306 | +| clip_fraction | 0.348 | +| clip_range | 0.0653 | +| entropy_loss | -5.92 | +| explained_variance | 0.207 | +| learning_rate | 4.08e-05 | +| loss | -0.0266 | +| n_updates | 91736 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000119 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1388 | +| iterations | 18981 | +| time_elapsed | 28004 | +| total_timesteps | 38873088 | +| train/ | | +| approx_kl | 0.0126950145 | +| clip_fraction | 0.354 | +| clip_range | 0.0653 | +| entropy_loss | -6.18 | +| explained_variance | 0.0689 | +| learning_rate | 4.08e-05 | +| loss | -0.0259 | +| n_updates | 91740 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.00014 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1388 | +| iterations | 18982 | +| time_elapsed | 28006 | +| total_timesteps | 38875136 | +| train/ | | +| approx_kl | 0.014528743 | +| clip_fraction | 0.315 | +| clip_range | 0.0653 | +| entropy_loss | -4.58 | +| explained_variance | 0.441 | +| learning_rate | 4.08e-05 | +| loss | -0.0223 | +| n_updates | 91744 | +| policy_gradient_loss | -0.0114 | +| value_loss | 0.000352 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1388 | +| iterations | 18983 | +| time_elapsed | 28007 | +| total_timesteps | 38877184 | +| train/ | | +| approx_kl | 0.016707964 | +| clip_fraction | 0.394 | +| clip_range | 0.0653 | +| entropy_loss | -4.29 | +| explained_variance | 0.411 | +| learning_rate | 4.08e-05 | +| loss | -0.0292 | +| n_updates | 91748 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000168 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1388 | +| iterations | 18984 | +| time_elapsed | 28009 | +| total_timesteps | 38879232 | +| train/ | | +| approx_kl | 0.017078336 | +| clip_fraction | 0.394 | +| clip_range | 0.0653 | +| entropy_loss | -5.82 | +| explained_variance | 0.229 | +| learning_rate | 4.08e-05 | +| loss | -0.0345 | +| n_updates | 91752 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000159 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1388 | +| iterations | 18985 | +| time_elapsed | 28010 | +| total_timesteps | 38881280 | +| train/ | | +| approx_kl | 0.011150737 | +| clip_fraction | 0.324 | +| clip_range | 0.0653 | +| entropy_loss | -5.66 | +| explained_variance | 0.4 | +| learning_rate | 4.08e-05 | +| loss | -0.0286 | +| n_updates | 91756 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000128 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1388 | +| iterations | 18986 | +| time_elapsed | 28012 | +| total_timesteps | 38883328 | +| train/ | | +| approx_kl | 0.011160949 | +| clip_fraction | 0.32 | +| clip_range | 0.0653 | +| entropy_loss | -6.48 | +| explained_variance | 0.313 | +| learning_rate | 4.08e-05 | +| loss | -0.0241 | +| n_updates | 91760 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000158 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1388 | +| iterations | 18987 | +| time_elapsed | 28013 | +| total_timesteps | 38885376 | +| train/ | | +| approx_kl | 0.012283465 | +| clip_fraction | 0.355 | +| clip_range | 0.0653 | +| entropy_loss | -6.41 | +| explained_variance | -0.538 | +| learning_rate | 4.08e-05 | +| loss | -0.0371 | +| n_updates | 91764 | +| policy_gradient_loss | -0.0215 | +| value_loss | 5.28e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1388 | +| iterations | 18988 | +| time_elapsed | 28015 | +| total_timesteps | 38887424 | +| train/ | | +| approx_kl | 0.0104329735 | +| clip_fraction | 0.326 | +| clip_range | 0.0653 | +| entropy_loss | -5.38 | +| explained_variance | 0.34 | +| learning_rate | 4.08e-05 | +| loss | -0.0234 | +| n_updates | 91768 | +| policy_gradient_loss | -0.0147 | +| value_loss | 0.000273 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1388 | +| iterations | 18989 | +| time_elapsed | 28016 | +| total_timesteps | 38889472 | +| train/ | | +| approx_kl | 0.01041971 | +| clip_fraction | 0.312 | +| clip_range | 0.0653 | +| entropy_loss | -5.45 | +| explained_variance | 0.545 | +| learning_rate | 4.08e-05 | +| loss | -0.0233 | +| n_updates | 91772 | +| policy_gradient_loss | -0.0148 | +| value_loss | 0.000164 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1388 | +| iterations | 18990 | +| time_elapsed | 28018 | +| total_timesteps | 38891520 | +| train/ | | +| approx_kl | 0.017519342 | +| clip_fraction | 0.401 | +| clip_range | 0.0653 | +| entropy_loss | -5.7 | +| explained_variance | 0.707 | +| learning_rate | 4.08e-05 | +| loss | -0.0354 | +| n_updates | 91776 | +| policy_gradient_loss | -0.0225 | +| value_loss | 5.27e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1388 | +| iterations | 18991 | +| time_elapsed | 28019 | +| total_timesteps | 38893568 | +| train/ | | +| approx_kl | 0.0146621335 | +| clip_fraction | 0.33 | +| clip_range | 0.0653 | +| entropy_loss | -5.47 | +| explained_variance | 0.569 | +| learning_rate | 4.08e-05 | +| loss | -0.0227 | +| n_updates | 91780 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000128 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1388 | +| iterations | 18992 | +| time_elapsed | 28021 | +| total_timesteps | 38895616 | +| train/ | | +| approx_kl | 0.0139861675 | +| clip_fraction | 0.279 | +| clip_range | 0.0653 | +| entropy_loss | -5.42 | +| explained_variance | 0.335 | +| learning_rate | 4.08e-05 | +| loss | -0.0211 | +| n_updates | 91784 | +| policy_gradient_loss | -0.0127 | +| value_loss | 0.000128 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1388 | +| iterations | 18993 | +| time_elapsed | 28022 | +| total_timesteps | 38897664 | +| train/ | | +| approx_kl | 0.019731998 | +| clip_fraction | 0.335 | +| clip_range | 0.0653 | +| entropy_loss | -5.64 | +| explained_variance | -0.00921 | +| learning_rate | 4.08e-05 | +| loss | -0.0221 | +| n_updates | 91788 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000215 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1388 | +| iterations | 18994 | +| time_elapsed | 28024 | +| total_timesteps | 38899712 | +| train/ | | +| approx_kl | 0.016358273 | +| clip_fraction | 0.333 | +| clip_range | 0.0653 | +| entropy_loss | -4.73 | +| explained_variance | 0.723 | +| learning_rate | 4.08e-05 | +| loss | -0.026 | +| n_updates | 91792 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000126 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1388 | +| iterations | 18995 | +| time_elapsed | 28026 | +| total_timesteps | 38901760 | +| train/ | | +| approx_kl | 0.016950889 | +| clip_fraction | 0.335 | +| clip_range | 0.0653 | +| entropy_loss | -4.98 | +| explained_variance | 0.232 | +| learning_rate | 4.08e-05 | +| loss | -0.024 | +| n_updates | 91796 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000124 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1388 | +| iterations | 18996 | +| time_elapsed | 28027 | +| total_timesteps | 38903808 | +| train/ | | +| approx_kl | 0.0137357265 | +| clip_fraction | 0.325 | +| clip_range | 0.0653 | +| entropy_loss | -6.18 | +| explained_variance | 0.218 | +| learning_rate | 4.08e-05 | +| loss | -0.0282 | +| n_updates | 91800 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000185 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1388 | +| iterations | 18997 | +| time_elapsed | 28029 | +| total_timesteps | 38905856 | +| train/ | | +| approx_kl | 0.012642952 | +| clip_fraction | 0.36 | +| clip_range | 0.0653 | +| entropy_loss | -6.64 | +| explained_variance | -0.188 | +| learning_rate | 4.08e-05 | +| loss | -0.0358 | +| n_updates | 91804 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000125 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1388 | +| iterations | 18998 | +| time_elapsed | 28030 | +| total_timesteps | 38907904 | +| train/ | | +| approx_kl | 0.013485681 | +| clip_fraction | 0.302 | +| clip_range | 0.0653 | +| entropy_loss | -6.62 | +| explained_variance | -0.0653 | +| learning_rate | 4.08e-05 | +| loss | -0.0208 | +| n_updates | 91808 | +| policy_gradient_loss | -0.0147 | +| value_loss | 0.000239 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1388 | +| iterations | 18999 | +| time_elapsed | 28032 | +| total_timesteps | 38909952 | +| train/ | | +| approx_kl | 0.015502853 | +| clip_fraction | 0.383 | +| clip_range | 0.0653 | +| entropy_loss | -5.22 | +| explained_variance | 0.41 | +| learning_rate | 4.08e-05 | +| loss | -0.0289 | +| n_updates | 91812 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000231 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1388 | +| iterations | 19000 | +| time_elapsed | 28033 | +| total_timesteps | 38912000 | +| train/ | | +| approx_kl | 0.017227098 | +| clip_fraction | 0.347 | +| clip_range | 0.0653 | +| entropy_loss | -5.36 | +| explained_variance | -0.0051 | +| learning_rate | 4.08e-05 | +| loss | -0.0309 | +| n_updates | 91816 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000258 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1388 | +| iterations | 19001 | +| time_elapsed | 28035 | +| total_timesteps | 38914048 | +| train/ | | +| approx_kl | 0.01639685 | +| clip_fraction | 0.352 | +| clip_range | 0.0653 | +| entropy_loss | -5.46 | +| explained_variance | 0.536 | +| learning_rate | 4.08e-05 | +| loss | -0.0284 | +| n_updates | 91820 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000117 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1388 | +| iterations | 19002 | +| time_elapsed | 28036 | +| total_timesteps | 38916096 | +| train/ | | +| approx_kl | 0.017471762 | +| clip_fraction | 0.38 | +| clip_range | 0.0653 | +| entropy_loss | -5.35 | +| explained_variance | 0.406 | +| learning_rate | 4.08e-05 | +| loss | -0.0348 | +| n_updates | 91824 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000107 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1388 | +| iterations | 19003 | +| time_elapsed | 28038 | +| total_timesteps | 38918144 | +| train/ | | +| approx_kl | 0.015255698 | +| clip_fraction | 0.348 | +| clip_range | 0.0653 | +| entropy_loss | -5.28 | +| explained_variance | 0.604 | +| learning_rate | 4.08e-05 | +| loss | -0.0248 | +| n_updates | 91828 | +| policy_gradient_loss | -0.0177 | +| value_loss | 9.66e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1388 | +| iterations | 19004 | +| time_elapsed | 28039 | +| total_timesteps | 38920192 | +| train/ | | +| approx_kl | 0.016551394 | +| clip_fraction | 0.34 | +| clip_range | 0.0653 | +| entropy_loss | -5.55 | +| explained_variance | 0.469 | +| learning_rate | 4.08e-05 | +| loss | -0.0262 | +| n_updates | 91832 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000155 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1388 | +| iterations | 19005 | +| time_elapsed | 28041 | +| total_timesteps | 38922240 | +| train/ | | +| approx_kl | 0.013006043 | +| clip_fraction | 0.312 | +| clip_range | 0.0653 | +| entropy_loss | -5.52 | +| explained_variance | 0.367 | +| learning_rate | 4.08e-05 | +| loss | -0.0185 | +| n_updates | 91836 | +| policy_gradient_loss | -0.012 | +| value_loss | 0.000271 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1388 | +| iterations | 19006 | +| time_elapsed | 28042 | +| total_timesteps | 38924288 | +| train/ | | +| approx_kl | 0.015673582 | +| clip_fraction | 0.341 | +| clip_range | 0.0653 | +| entropy_loss | -5.44 | +| explained_variance | 0.568 | +| learning_rate | 4.08e-05 | +| loss | -0.0292 | +| n_updates | 91840 | +| policy_gradient_loss | -0.0173 | +| value_loss | 9.54e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1388 | +| iterations | 19007 | +| time_elapsed | 28044 | +| total_timesteps | 38926336 | +| train/ | | +| approx_kl | 0.014890688 | +| clip_fraction | 0.374 | +| clip_range | 0.0653 | +| entropy_loss | -5.83 | +| explained_variance | 0.161 | +| learning_rate | 4.08e-05 | +| loss | -0.0305 | +| n_updates | 91844 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000322 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1388 | +| iterations | 19008 | +| time_elapsed | 28045 | +| total_timesteps | 38928384 | +| train/ | | +| approx_kl | 0.020382643 | +| clip_fraction | 0.394 | +| clip_range | 0.0653 | +| entropy_loss | -5.22 | +| explained_variance | 0.473 | +| learning_rate | 4.08e-05 | +| loss | -0.033 | +| n_updates | 91848 | +| policy_gradient_loss | -0.0212 | +| value_loss | 7.14e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1388 | +| iterations | 19009 | +| time_elapsed | 28047 | +| total_timesteps | 38930432 | +| train/ | | +| approx_kl | 0.014378261 | +| clip_fraction | 0.348 | +| clip_range | 0.0653 | +| entropy_loss | -5.84 | +| explained_variance | 0.369 | +| learning_rate | 4.08e-05 | +| loss | -0.0281 | +| n_updates | 91852 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.00015 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1388 | +| iterations | 19010 | +| time_elapsed | 28048 | +| total_timesteps | 38932480 | +| train/ | | +| approx_kl | 0.013419735 | +| clip_fraction | 0.389 | +| clip_range | 0.0653 | +| entropy_loss | -5.67 | +| explained_variance | -0.0863 | +| learning_rate | 4.08e-05 | +| loss | -0.0279 | +| n_updates | 91856 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000113 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1388 | +| iterations | 19011 | +| time_elapsed | 28050 | +| total_timesteps | 38934528 | +| train/ | | +| approx_kl | 0.012868546 | +| clip_fraction | 0.359 | +| clip_range | 0.0653 | +| entropy_loss | -6.51 | +| explained_variance | 0.0486 | +| learning_rate | 4.08e-05 | +| loss | -0.0264 | +| n_updates | 91860 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000186 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1388 | +| iterations | 19012 | +| time_elapsed | 28052 | +| total_timesteps | 38936576 | +| train/ | | +| approx_kl | 0.012375382 | +| clip_fraction | 0.319 | +| clip_range | 0.0653 | +| entropy_loss | -5.45 | +| explained_variance | 0.622 | +| learning_rate | 4.08e-05 | +| loss | -0.0244 | +| n_updates | 91864 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000182 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1388 | +| iterations | 19013 | +| time_elapsed | 28053 | +| total_timesteps | 38938624 | +| train/ | | +| approx_kl | 0.013691891 | +| clip_fraction | 0.333 | +| clip_range | 0.0653 | +| entropy_loss | -4.69 | +| explained_variance | 0.772 | +| learning_rate | 4.08e-05 | +| loss | -0.025 | +| n_updates | 91868 | +| policy_gradient_loss | -0.0163 | +| value_loss | 6.4e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1388 | +| iterations | 19014 | +| time_elapsed | 28055 | +| total_timesteps | 38940672 | +| train/ | | +| approx_kl | 0.012349955 | +| clip_fraction | 0.349 | +| clip_range | 0.0653 | +| entropy_loss | -5.11 | +| explained_variance | 0.297 | +| learning_rate | 4.08e-05 | +| loss | -0.0242 | +| n_updates | 91872 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.000154 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1388 | +| iterations | 19015 | +| time_elapsed | 28056 | +| total_timesteps | 38942720 | +| train/ | | +| approx_kl | 0.01619773 | +| clip_fraction | 0.319 | +| clip_range | 0.0653 | +| entropy_loss | -4.7 | +| explained_variance | 0.396 | +| learning_rate | 4.08e-05 | +| loss | -0.0225 | +| n_updates | 91876 | +| policy_gradient_loss | -0.0137 | +| value_loss | 0.000349 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1388 | +| iterations | 19016 | +| time_elapsed | 28058 | +| total_timesteps | 38944768 | +| train/ | | +| approx_kl | 0.014284892 | +| clip_fraction | 0.368 | +| clip_range | 0.0653 | +| entropy_loss | -5.63 | +| explained_variance | 0.238 | +| learning_rate | 4.08e-05 | +| loss | -0.027 | +| n_updates | 91880 | +| policy_gradient_loss | -0.0177 | +| value_loss | 9.83e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1387 | +| iterations | 19017 | +| time_elapsed | 28059 | +| total_timesteps | 38946816 | +| train/ | | +| approx_kl | 0.012342894 | +| clip_fraction | 0.337 | +| clip_range | 0.0653 | +| entropy_loss | -6.07 | +| explained_variance | 0.358 | +| learning_rate | 4.08e-05 | +| loss | -0.0293 | +| n_updates | 91884 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000111 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1387 | +| iterations | 19018 | +| time_elapsed | 28061 | +| total_timesteps | 38948864 | +| train/ | | +| approx_kl | 0.013487458 | +| clip_fraction | 0.316 | +| clip_range | 0.0653 | +| entropy_loss | -5.96 | +| explained_variance | 0.264 | +| learning_rate | 4.08e-05 | +| loss | -0.0232 | +| n_updates | 91888 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.000169 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1387 | +| iterations | 19019 | +| time_elapsed | 28062 | +| total_timesteps | 38950912 | +| train/ | | +| approx_kl | 0.014029542 | +| clip_fraction | 0.341 | +| clip_range | 0.0653 | +| entropy_loss | -5.65 | +| explained_variance | 0.27 | +| learning_rate | 4.07e-05 | +| loss | -0.0337 | +| n_updates | 91892 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000151 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1387 | +| iterations | 19020 | +| time_elapsed | 28064 | +| total_timesteps | 38952960 | +| train/ | | +| approx_kl | 0.014834927 | +| clip_fraction | 0.344 | +| clip_range | 0.0653 | +| entropy_loss | -5.89 | +| explained_variance | 0.189 | +| learning_rate | 4.07e-05 | +| loss | -0.0309 | +| n_updates | 91896 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000163 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1387 | +| iterations | 19021 | +| time_elapsed | 28065 | +| total_timesteps | 38955008 | +| train/ | | +| approx_kl | 0.01367251 | +| clip_fraction | 0.337 | +| clip_range | 0.0653 | +| entropy_loss | -6.34 | +| explained_variance | 0.0903 | +| learning_rate | 4.07e-05 | +| loss | -0.0311 | +| n_updates | 91900 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000145 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1387 | +| iterations | 19022 | +| time_elapsed | 28067 | +| total_timesteps | 38957056 | +| train/ | | +| approx_kl | 0.017438281 | +| clip_fraction | 0.337 | +| clip_range | 0.0653 | +| entropy_loss | -5.89 | +| explained_variance | 0.189 | +| learning_rate | 4.07e-05 | +| loss | -0.0239 | +| n_updates | 91904 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000198 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1387 | +| iterations | 19023 | +| time_elapsed | 28068 | +| total_timesteps | 38959104 | +| train/ | | +| approx_kl | 0.013928588 | +| clip_fraction | 0.354 | +| clip_range | 0.0653 | +| entropy_loss | -5.87 | +| explained_variance | 0.385 | +| learning_rate | 4.07e-05 | +| loss | -0.0273 | +| n_updates | 91908 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000129 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1387 | +| iterations | 19024 | +| time_elapsed | 28070 | +| total_timesteps | 38961152 | +| train/ | | +| approx_kl | 0.013754176 | +| clip_fraction | 0.36 | +| clip_range | 0.0653 | +| entropy_loss | -5.35 | +| explained_variance | 0.41 | +| learning_rate | 4.07e-05 | +| loss | -0.0257 | +| n_updates | 91912 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000234 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1387 | +| iterations | 19025 | +| time_elapsed | 28071 | +| total_timesteps | 38963200 | +| train/ | | +| approx_kl | 0.015730858 | +| clip_fraction | 0.339 | +| clip_range | 0.0653 | +| entropy_loss | -4.98 | +| explained_variance | 0.339 | +| learning_rate | 4.07e-05 | +| loss | -0.0262 | +| n_updates | 91916 | +| policy_gradient_loss | -0.0147 | +| value_loss | 0.000194 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1387 | +| iterations | 19026 | +| time_elapsed | 28073 | +| total_timesteps | 38965248 | +| train/ | | +| approx_kl | 0.0147576 | +| clip_fraction | 0.322 | +| clip_range | 0.0653 | +| entropy_loss | -4.76 | +| explained_variance | 0.576 | +| learning_rate | 4.07e-05 | +| loss | -0.0314 | +| n_updates | 91920 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000177 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1387 | +| iterations | 19027 | +| time_elapsed | 28074 | +| total_timesteps | 38967296 | +| train/ | | +| approx_kl | 0.012035108 | +| clip_fraction | 0.328 | +| clip_range | 0.0653 | +| entropy_loss | -4.86 | +| explained_variance | 0.516 | +| learning_rate | 4.07e-05 | +| loss | -0.0217 | +| n_updates | 91924 | +| policy_gradient_loss | -0.0148 | +| value_loss | 0.000244 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1387 | +| iterations | 19028 | +| time_elapsed | 28076 | +| total_timesteps | 38969344 | +| train/ | | +| approx_kl | 0.0137875695 | +| clip_fraction | 0.358 | +| clip_range | 0.0653 | +| entropy_loss | -5.33 | +| explained_variance | 0.438 | +| learning_rate | 4.07e-05 | +| loss | -0.0299 | +| n_updates | 91928 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000192 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1387 | +| iterations | 19029 | +| time_elapsed | 28078 | +| total_timesteps | 38971392 | +| train/ | | +| approx_kl | 0.014092632 | +| clip_fraction | 0.352 | +| clip_range | 0.0653 | +| entropy_loss | -5.74 | +| explained_variance | -0.138 | +| learning_rate | 4.07e-05 | +| loss | -0.0322 | +| n_updates | 91932 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000104 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1387 | +| iterations | 19030 | +| time_elapsed | 28079 | +| total_timesteps | 38973440 | +| train/ | | +| approx_kl | 0.012948932 | +| clip_fraction | 0.351 | +| clip_range | 0.0653 | +| entropy_loss | -5.82 | +| explained_variance | 0.207 | +| learning_rate | 4.07e-05 | +| loss | -0.0256 | +| n_updates | 91936 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000215 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1387 | +| iterations | 19031 | +| time_elapsed | 28080 | +| total_timesteps | 38975488 | +| train/ | | +| approx_kl | 0.017726308 | +| clip_fraction | 0.347 | +| clip_range | 0.0653 | +| entropy_loss | -5.84 | +| explained_variance | 0.166 | +| learning_rate | 4.07e-05 | +| loss | -0.0249 | +| n_updates | 91940 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000265 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1387 | +| iterations | 19032 | +| time_elapsed | 28082 | +| total_timesteps | 38977536 | +| train/ | | +| approx_kl | 0.012490454 | +| clip_fraction | 0.355 | +| clip_range | 0.0653 | +| entropy_loss | -5.84 | +| explained_variance | 0.396 | +| learning_rate | 4.07e-05 | +| loss | -0.0335 | +| n_updates | 91944 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000109 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1387 | +| iterations | 19033 | +| time_elapsed | 28083 | +| total_timesteps | 38979584 | +| train/ | | +| approx_kl | 0.012999478 | +| clip_fraction | 0.342 | +| clip_range | 0.0653 | +| entropy_loss | -5.22 | +| explained_variance | 0.518 | +| learning_rate | 4.07e-05 | +| loss | -0.0239 | +| n_updates | 91948 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000104 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1387 | +| iterations | 19034 | +| time_elapsed | 28085 | +| total_timesteps | 38981632 | +| train/ | | +| approx_kl | 0.012877682 | +| clip_fraction | 0.293 | +| clip_range | 0.0653 | +| entropy_loss | -5.94 | +| explained_variance | 0.217 | +| learning_rate | 4.07e-05 | +| loss | -0.0224 | +| n_updates | 91952 | +| policy_gradient_loss | -0.0133 | +| value_loss | 0.000223 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1387 | +| iterations | 19035 | +| time_elapsed | 28086 | +| total_timesteps | 38983680 | +| train/ | | +| approx_kl | 0.017052013 | +| clip_fraction | 0.348 | +| clip_range | 0.0653 | +| entropy_loss | -5.62 | +| explained_variance | 0.739 | +| learning_rate | 4.07e-05 | +| loss | -0.0295 | +| n_updates | 91956 | +| policy_gradient_loss | -0.0176 | +| value_loss | 7.95e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1387 | +| iterations | 19036 | +| time_elapsed | 28088 | +| total_timesteps | 38985728 | +| train/ | | +| approx_kl | 0.017306883 | +| clip_fraction | 0.356 | +| clip_range | 0.0653 | +| entropy_loss | -5.25 | +| explained_variance | -0.311 | +| learning_rate | 4.07e-05 | +| loss | -0.0296 | +| n_updates | 91960 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000136 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1387 | +| iterations | 19037 | +| time_elapsed | 28090 | +| total_timesteps | 38987776 | +| train/ | | +| approx_kl | 0.012636541 | +| clip_fraction | 0.336 | +| clip_range | 0.0653 | +| entropy_loss | -6.05 | +| explained_variance | 0.31 | +| learning_rate | 4.07e-05 | +| loss | -0.0264 | +| n_updates | 91964 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000162 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1387 | +| iterations | 19038 | +| time_elapsed | 28091 | +| total_timesteps | 38989824 | +| train/ | | +| approx_kl | 0.014059694 | +| clip_fraction | 0.361 | +| clip_range | 0.0653 | +| entropy_loss | -5.88 | +| explained_variance | 0.401 | +| learning_rate | 4.07e-05 | +| loss | -0.023 | +| n_updates | 91968 | +| policy_gradient_loss | -0.0168 | +| value_loss | 9.02e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1387 | +| iterations | 19039 | +| time_elapsed | 28093 | +| total_timesteps | 38991872 | +| train/ | | +| approx_kl | 0.015152919 | +| clip_fraction | 0.327 | +| clip_range | 0.0653 | +| entropy_loss | -5.92 | +| explained_variance | 0.313 | +| learning_rate | 4.07e-05 | +| loss | -0.0259 | +| n_updates | 91972 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.000165 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1387 | +| iterations | 19040 | +| time_elapsed | 28094 | +| total_timesteps | 38993920 | +| train/ | | +| approx_kl | 0.011552713 | +| clip_fraction | 0.314 | +| clip_range | 0.0653 | +| entropy_loss | -5.22 | +| explained_variance | 0.537 | +| learning_rate | 4.07e-05 | +| loss | -0.0242 | +| n_updates | 91976 | +| policy_gradient_loss | -0.0138 | +| value_loss | 0.000153 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1387 | +| iterations | 19041 | +| time_elapsed | 28096 | +| total_timesteps | 38995968 | +| train/ | | +| approx_kl | 0.013991078 | +| clip_fraction | 0.336 | +| clip_range | 0.0653 | +| entropy_loss | -5.32 | +| explained_variance | 0.692 | +| learning_rate | 4.07e-05 | +| loss | -0.0252 | +| n_updates | 91980 | +| policy_gradient_loss | -0.017 | +| value_loss | 6.38e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1387 | +| iterations | 19042 | +| time_elapsed | 28097 | +| total_timesteps | 38998016 | +| train/ | | +| approx_kl | 0.014128923 | +| clip_fraction | 0.349 | +| clip_range | 0.0653 | +| entropy_loss | -5.7 | +| explained_variance | 0.416 | +| learning_rate | 4.07e-05 | +| loss | -0.0267 | +| n_updates | 91984 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.00012 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1387 | +| iterations | 19043 | +| time_elapsed | 28099 | +| total_timesteps | 39000064 | +| train/ | | +| approx_kl | 0.0148004275 | +| clip_fraction | 0.319 | +| clip_range | 0.0653 | +| entropy_loss | -5.77 | +| explained_variance | 0.447 | +| learning_rate | 4.07e-05 | +| loss | -0.0253 | +| n_updates | 91988 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.00017 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1387 | +| iterations | 19044 | +| time_elapsed | 28101 | +| total_timesteps | 39002112 | +| train/ | | +| approx_kl | 0.013635144 | +| clip_fraction | 0.303 | +| clip_range | 0.0652 | +| entropy_loss | -5.41 | +| explained_variance | 0.324 | +| learning_rate | 4.07e-05 | +| loss | -0.0239 | +| n_updates | 91992 | +| policy_gradient_loss | -0.0134 | +| value_loss | 0.000304 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1387 | +| iterations | 19045 | +| time_elapsed | 28102 | +| total_timesteps | 39004160 | +| train/ | | +| approx_kl | 0.01578041 | +| clip_fraction | 0.353 | +| clip_range | 0.0652 | +| entropy_loss | -5.25 | +| explained_variance | 0.285 | +| learning_rate | 4.07e-05 | +| loss | -0.0344 | +| n_updates | 91996 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000167 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1387 | +| iterations | 19046 | +| time_elapsed | 28104 | +| total_timesteps | 39006208 | +| train/ | | +| approx_kl | 0.014185656 | +| clip_fraction | 0.336 | +| clip_range | 0.0652 | +| entropy_loss | -6.05 | +| explained_variance | 0.342 | +| learning_rate | 4.07e-05 | +| loss | -0.03 | +| n_updates | 92000 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000143 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1387 | +| iterations | 19047 | +| time_elapsed | 28105 | +| total_timesteps | 39008256 | +| train/ | | +| approx_kl | 0.012248114 | +| clip_fraction | 0.328 | +| clip_range | 0.0652 | +| entropy_loss | -5.89 | +| explained_variance | 0.303 | +| learning_rate | 4.07e-05 | +| loss | -0.0246 | +| n_updates | 92004 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000135 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1387 | +| iterations | 19048 | +| time_elapsed | 28107 | +| total_timesteps | 39010304 | +| train/ | | +| approx_kl | 0.01372315 | +| clip_fraction | 0.336 | +| clip_range | 0.0652 | +| entropy_loss | -5.87 | +| explained_variance | -0.0309 | +| learning_rate | 4.07e-05 | +| loss | -0.026 | +| n_updates | 92008 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000158 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1387 | +| iterations | 19049 | +| time_elapsed | 28108 | +| total_timesteps | 39012352 | +| train/ | | +| approx_kl | 0.012064604 | +| clip_fraction | 0.323 | +| clip_range | 0.0652 | +| entropy_loss | -6.03 | +| explained_variance | 0.257 | +| learning_rate | 4.07e-05 | +| loss | -0.0215 | +| n_updates | 92012 | +| policy_gradient_loss | -0.0141 | +| value_loss | 0.000221 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1387 | +| iterations | 19050 | +| time_elapsed | 28110 | +| total_timesteps | 39014400 | +| train/ | | +| approx_kl | 0.017145112 | +| clip_fraction | 0.365 | +| clip_range | 0.0652 | +| entropy_loss | -5.6 | +| explained_variance | 0.31 | +| learning_rate | 4.07e-05 | +| loss | -0.0247 | +| n_updates | 92016 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000174 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1387 | +| iterations | 19051 | +| time_elapsed | 28111 | +| total_timesteps | 39016448 | +| train/ | | +| approx_kl | 0.011529045 | +| clip_fraction | 0.343 | +| clip_range | 0.0652 | +| entropy_loss | -5.59 | +| explained_variance | 0.435 | +| learning_rate | 4.07e-05 | +| loss | -0.0246 | +| n_updates | 92020 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000234 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1387 | +| iterations | 19052 | +| time_elapsed | 28113 | +| total_timesteps | 39018496 | +| train/ | | +| approx_kl | 0.01334553 | +| clip_fraction | 0.343 | +| clip_range | 0.0652 | +| entropy_loss | -5.86 | +| explained_variance | 0.0748 | +| learning_rate | 4.07e-05 | +| loss | -0.028 | +| n_updates | 92024 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000124 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1387 | +| iterations | 19053 | +| time_elapsed | 28115 | +| total_timesteps | 39020544 | +| train/ | | +| approx_kl | 0.013240283 | +| clip_fraction | 0.315 | +| clip_range | 0.0652 | +| entropy_loss | -5.14 | +| explained_variance | 0.59 | +| learning_rate | 4.07e-05 | +| loss | -0.0231 | +| n_updates | 92028 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000144 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1387 | +| iterations | 19054 | +| time_elapsed | 28116 | +| total_timesteps | 39022592 | +| train/ | | +| approx_kl | 0.014317023 | +| clip_fraction | 0.353 | +| clip_range | 0.0652 | +| entropy_loss | -5.94 | +| explained_variance | 0.504 | +| learning_rate | 4.07e-05 | +| loss | -0.0278 | +| n_updates | 92032 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000121 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1387 | +| iterations | 19055 | +| time_elapsed | 28118 | +| total_timesteps | 39024640 | +| train/ | | +| approx_kl | 0.011638117 | +| clip_fraction | 0.339 | +| clip_range | 0.0652 | +| entropy_loss | -5.75 | +| explained_variance | 0.637 | +| learning_rate | 4.07e-05 | +| loss | -0.0239 | +| n_updates | 92036 | +| policy_gradient_loss | -0.0145 | +| value_loss | 0.000172 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1387 | +| iterations | 19056 | +| time_elapsed | 28119 | +| total_timesteps | 39026688 | +| train/ | | +| approx_kl | 0.014043996 | +| clip_fraction | 0.384 | +| clip_range | 0.0652 | +| entropy_loss | -5.48 | +| explained_variance | 0.3 | +| learning_rate | 4.07e-05 | +| loss | -0.0337 | +| n_updates | 92040 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000148 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1387 | +| iterations | 19057 | +| time_elapsed | 28121 | +| total_timesteps | 39028736 | +| train/ | | +| approx_kl | 0.015456228 | +| clip_fraction | 0.339 | +| clip_range | 0.0652 | +| entropy_loss | -5.67 | +| explained_variance | 0.132 | +| learning_rate | 4.07e-05 | +| loss | -0.0269 | +| n_updates | 92044 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000407 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1387 | +| iterations | 19058 | +| time_elapsed | 28122 | +| total_timesteps | 39030784 | +| train/ | | +| approx_kl | 0.01520321 | +| clip_fraction | 0.35 | +| clip_range | 0.0652 | +| entropy_loss | -5.83 | +| explained_variance | 0.496 | +| learning_rate | 4.07e-05 | +| loss | -0.0301 | +| n_updates | 92048 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000163 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1387 | +| iterations | 19059 | +| time_elapsed | 28124 | +| total_timesteps | 39032832 | +| train/ | | +| approx_kl | 0.010839522 | +| clip_fraction | 0.318 | +| clip_range | 0.0652 | +| entropy_loss | -6.61 | +| explained_variance | -0.23 | +| learning_rate | 4.07e-05 | +| loss | -0.0272 | +| n_updates | 92052 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000201 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1387 | +| iterations | 19060 | +| time_elapsed | 28125 | +| total_timesteps | 39034880 | +| train/ | | +| approx_kl | 0.009154618 | +| clip_fraction | 0.315 | +| clip_range | 0.0652 | +| entropy_loss | -6.7 | +| explained_variance | -0.102 | +| learning_rate | 4.07e-05 | +| loss | -0.0255 | +| n_updates | 92056 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000177 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1387 | +| iterations | 19061 | +| time_elapsed | 28127 | +| total_timesteps | 39036928 | +| train/ | | +| approx_kl | 0.012778984 | +| clip_fraction | 0.338 | +| clip_range | 0.0652 | +| entropy_loss | -4.87 | +| explained_variance | 0.521 | +| learning_rate | 4.07e-05 | +| loss | -0.02 | +| n_updates | 92060 | +| policy_gradient_loss | -0.0138 | +| value_loss | 0.000254 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1387 | +| iterations | 19062 | +| time_elapsed | 28128 | +| total_timesteps | 39038976 | +| train/ | | +| approx_kl | 0.016712252 | +| clip_fraction | 0.37 | +| clip_range | 0.0652 | +| entropy_loss | -5.16 | +| explained_variance | 0.22 | +| learning_rate | 4.07e-05 | +| loss | -0.0321 | +| n_updates | 92064 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.00014 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1387 | +| iterations | 19063 | +| time_elapsed | 28130 | +| total_timesteps | 39041024 | +| train/ | | +| approx_kl | 0.014834378 | +| clip_fraction | 0.356 | +| clip_range | 0.0652 | +| entropy_loss | -5.65 | +| explained_variance | 0.27 | +| learning_rate | 4.07e-05 | +| loss | -0.032 | +| n_updates | 92068 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000146 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1387 | +| iterations | 19064 | +| time_elapsed | 28132 | +| total_timesteps | 39043072 | +| train/ | | +| approx_kl | 0.017655022 | +| clip_fraction | 0.324 | +| clip_range | 0.0652 | +| entropy_loss | -5.48 | +| explained_variance | 0.36 | +| learning_rate | 4.07e-05 | +| loss | -0.0249 | +| n_updates | 92072 | +| policy_gradient_loss | -0.0142 | +| value_loss | 0.00017 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1387 | +| iterations | 19065 | +| time_elapsed | 28133 | +| total_timesteps | 39045120 | +| train/ | | +| approx_kl | 0.013227886 | +| clip_fraction | 0.316 | +| clip_range | 0.0652 | +| entropy_loss | -4.77 | +| explained_variance | 0.549 | +| learning_rate | 4.07e-05 | +| loss | -0.0211 | +| n_updates | 92076 | +| policy_gradient_loss | -0.0145 | +| value_loss | 0.000209 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1387 | +| iterations | 19066 | +| time_elapsed | 28135 | +| total_timesteps | 39047168 | +| train/ | | +| approx_kl | 0.01187635 | +| clip_fraction | 0.302 | +| clip_range | 0.0652 | +| entropy_loss | -5.4 | +| explained_variance | 0.46 | +| learning_rate | 4.07e-05 | +| loss | -0.0229 | +| n_updates | 92080 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000216 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1387 | +| iterations | 19067 | +| time_elapsed | 28136 | +| total_timesteps | 39049216 | +| train/ | | +| approx_kl | 0.015913012 | +| clip_fraction | 0.339 | +| clip_range | 0.0652 | +| entropy_loss | -6.01 | +| explained_variance | 0.369 | +| learning_rate | 4.07e-05 | +| loss | -0.0266 | +| n_updates | 92084 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000128 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1387 | +| iterations | 19068 | +| time_elapsed | 28138 | +| total_timesteps | 39051264 | +| train/ | | +| approx_kl | 0.015515909 | +| clip_fraction | 0.293 | +| clip_range | 0.0652 | +| entropy_loss | -5.3 | +| explained_variance | 0.239 | +| learning_rate | 4.07e-05 | +| loss | -0.02 | +| n_updates | 92088 | +| policy_gradient_loss | -0.0125 | +| value_loss | 0.000426 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1387 | +| iterations | 19069 | +| time_elapsed | 28139 | +| total_timesteps | 39053312 | +| train/ | | +| approx_kl | 0.012564359 | +| clip_fraction | 0.339 | +| clip_range | 0.0652 | +| entropy_loss | -5.13 | +| explained_variance | 0.501 | +| learning_rate | 4.07e-05 | +| loss | -0.0284 | +| n_updates | 92092 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000218 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1387 | +| iterations | 19070 | +| time_elapsed | 28141 | +| total_timesteps | 39055360 | +| train/ | | +| approx_kl | 0.011947982 | +| clip_fraction | 0.332 | +| clip_range | 0.0652 | +| entropy_loss | -5.76 | +| explained_variance | 0.0531 | +| learning_rate | 4.07e-05 | +| loss | -0.032 | +| n_updates | 92096 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000268 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1387 | +| iterations | 19071 | +| time_elapsed | 28142 | +| total_timesteps | 39057408 | +| train/ | | +| approx_kl | 0.014263629 | +| clip_fraction | 0.345 | +| clip_range | 0.0652 | +| entropy_loss | -6.08 | +| explained_variance | 0.294 | +| learning_rate | 4.07e-05 | +| loss | -0.0269 | +| n_updates | 92100 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000159 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1387 | +| iterations | 19072 | +| time_elapsed | 28144 | +| total_timesteps | 39059456 | +| train/ | | +| approx_kl | 0.012401059 | +| clip_fraction | 0.32 | +| clip_range | 0.0652 | +| entropy_loss | -6.03 | +| explained_variance | 0.535 | +| learning_rate | 4.07e-05 | +| loss | -0.0221 | +| n_updates | 92104 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000186 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1387 | +| iterations | 19073 | +| time_elapsed | 28145 | +| total_timesteps | 39061504 | +| train/ | | +| approx_kl | 0.0124859195 | +| clip_fraction | 0.328 | +| clip_range | 0.0652 | +| entropy_loss | -5.79 | +| explained_variance | 0.13 | +| learning_rate | 4.07e-05 | +| loss | -0.0229 | +| n_updates | 92108 | +| policy_gradient_loss | -0.0146 | +| value_loss | 0.000165 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1387 | +| iterations | 19074 | +| time_elapsed | 28147 | +| total_timesteps | 39063552 | +| train/ | | +| approx_kl | 0.012143819 | +| clip_fraction | 0.354 | +| clip_range | 0.0652 | +| entropy_loss | -5.47 | +| explained_variance | 0.42 | +| learning_rate | 4.07e-05 | +| loss | -0.0258 | +| n_updates | 92112 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000193 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1387 | +| iterations | 19075 | +| time_elapsed | 28149 | +| total_timesteps | 39065600 | +| train/ | | +| approx_kl | 0.015024086 | +| clip_fraction | 0.371 | +| clip_range | 0.0652 | +| entropy_loss | -5.59 | +| explained_variance | -0.0711 | +| learning_rate | 4.07e-05 | +| loss | -0.0226 | +| n_updates | 92116 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000113 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1387 | +| iterations | 19076 | +| time_elapsed | 28150 | +| total_timesteps | 39067648 | +| train/ | | +| approx_kl | 0.015135536 | +| clip_fraction | 0.328 | +| clip_range | 0.0652 | +| entropy_loss | -5.96 | +| explained_variance | -0.0816 | +| learning_rate | 4.07e-05 | +| loss | -0.0281 | +| n_updates | 92120 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000218 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1387 | +| iterations | 19077 | +| time_elapsed | 28152 | +| total_timesteps | 39069696 | +| train/ | | +| approx_kl | 0.012568085 | +| clip_fraction | 0.314 | +| clip_range | 0.0652 | +| entropy_loss | -5.29 | +| explained_variance | 0.635 | +| learning_rate | 4.07e-05 | +| loss | -0.0286 | +| n_updates | 92124 | +| policy_gradient_loss | -0.0148 | +| value_loss | 7.83e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1387 | +| iterations | 19078 | +| time_elapsed | 28153 | +| total_timesteps | 39071744 | +| train/ | | +| approx_kl | 0.013296467 | +| clip_fraction | 0.32 | +| clip_range | 0.0652 | +| entropy_loss | -5.56 | +| explained_variance | 0.219 | +| learning_rate | 4.07e-05 | +| loss | -0.0284 | +| n_updates | 92128 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000235 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1387 | +| iterations | 19079 | +| time_elapsed | 28155 | +| total_timesteps | 39073792 | +| train/ | | +| approx_kl | 0.013922922 | +| clip_fraction | 0.347 | +| clip_range | 0.0652 | +| entropy_loss | -5.56 | +| explained_variance | 0.532 | +| learning_rate | 4.07e-05 | +| loss | -0.0258 | +| n_updates | 92132 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000108 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1387 | +| iterations | 19080 | +| time_elapsed | 28156 | +| total_timesteps | 39075840 | +| train/ | | +| approx_kl | 0.013707571 | +| clip_fraction | 0.335 | +| clip_range | 0.0652 | +| entropy_loss | -5.36 | +| explained_variance | 0.28 | +| learning_rate | 4.07e-05 | +| loss | -0.0241 | +| n_updates | 92136 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000212 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1387 | +| iterations | 19081 | +| time_elapsed | 28158 | +| total_timesteps | 39077888 | +| train/ | | +| approx_kl | 0.015076744 | +| clip_fraction | 0.359 | +| clip_range | 0.0652 | +| entropy_loss | -6.01 | +| explained_variance | 0.289 | +| learning_rate | 4.07e-05 | +| loss | -0.0238 | +| n_updates | 92140 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000114 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1387 | +| iterations | 19082 | +| time_elapsed | 28159 | +| total_timesteps | 39079936 | +| train/ | | +| approx_kl | 0.020023275 | +| clip_fraction | 0.319 | +| clip_range | 0.0652 | +| entropy_loss | -5.74 | +| explained_variance | 0.032 | +| learning_rate | 4.07e-05 | +| loss | -0.027 | +| n_updates | 92144 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000224 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1387 | +| iterations | 19083 | +| time_elapsed | 28161 | +| total_timesteps | 39081984 | +| train/ | | +| approx_kl | 0.011700567 | +| clip_fraction | 0.323 | +| clip_range | 0.0652 | +| entropy_loss | -5.84 | +| explained_variance | 0.496 | +| learning_rate | 4.07e-05 | +| loss | -0.0242 | +| n_updates | 92148 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000149 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1387 | +| iterations | 19084 | +| time_elapsed | 28163 | +| total_timesteps | 39084032 | +| train/ | | +| approx_kl | 0.013077926 | +| clip_fraction | 0.301 | +| clip_range | 0.0652 | +| entropy_loss | -5.3 | +| explained_variance | 0.71 | +| learning_rate | 4.07e-05 | +| loss | -0.0308 | +| n_updates | 92152 | +| policy_gradient_loss | -0.0173 | +| value_loss | 7.07e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1387 | +| iterations | 19085 | +| time_elapsed | 28164 | +| total_timesteps | 39086080 | +| train/ | | +| approx_kl | 0.015756037 | +| clip_fraction | 0.363 | +| clip_range | 0.0652 | +| entropy_loss | -5.38 | +| explained_variance | 0.476 | +| learning_rate | 4.07e-05 | +| loss | -0.0276 | +| n_updates | 92156 | +| policy_gradient_loss | -0.0182 | +| value_loss | 6.83e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1387 | +| iterations | 19086 | +| time_elapsed | 28166 | +| total_timesteps | 39088128 | +| train/ | | +| approx_kl | 0.012252869 | +| clip_fraction | 0.312 | +| clip_range | 0.0652 | +| entropy_loss | -5.75 | +| explained_variance | 0.55 | +| learning_rate | 4.07e-05 | +| loss | -0.0229 | +| n_updates | 92160 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000223 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1387 | +| iterations | 19087 | +| time_elapsed | 28167 | +| total_timesteps | 39090176 | +| train/ | | +| approx_kl | 0.015886806 | +| clip_fraction | 0.318 | +| clip_range | 0.0652 | +| entropy_loss | -5.45 | +| explained_variance | 0.257 | +| learning_rate | 4.07e-05 | +| loss | -0.0262 | +| n_updates | 92164 | +| policy_gradient_loss | -0.0142 | +| value_loss | 0.000356 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1387 | +| iterations | 19088 | +| time_elapsed | 28169 | +| total_timesteps | 39092224 | +| train/ | | +| approx_kl | 0.016209088 | +| clip_fraction | 0.379 | +| clip_range | 0.0652 | +| entropy_loss | -5.18 | +| explained_variance | 0.337 | +| learning_rate | 4.07e-05 | +| loss | -0.0309 | +| n_updates | 92168 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000114 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1387 | +| iterations | 19089 | +| time_elapsed | 28170 | +| total_timesteps | 39094272 | +| train/ | | +| approx_kl | 0.015740491 | +| clip_fraction | 0.352 | +| clip_range | 0.0652 | +| entropy_loss | -5.33 | +| explained_variance | 0.22 | +| learning_rate | 4.07e-05 | +| loss | -0.0217 | +| n_updates | 92172 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000199 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1387 | +| iterations | 19090 | +| time_elapsed | 28172 | +| total_timesteps | 39096320 | +| train/ | | +| approx_kl | 0.011002352 | +| clip_fraction | 0.334 | +| clip_range | 0.0652 | +| entropy_loss | -5.86 | +| explained_variance | 0.372 | +| learning_rate | 4.07e-05 | +| loss | -0.0255 | +| n_updates | 92176 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000243 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1387 | +| iterations | 19091 | +| time_elapsed | 28173 | +| total_timesteps | 39098368 | +| train/ | | +| approx_kl | 0.014120565 | +| clip_fraction | 0.366 | +| clip_range | 0.0652 | +| entropy_loss | -6.07 | +| explained_variance | -0.0863 | +| learning_rate | 4.07e-05 | +| loss | -0.0279 | +| n_updates | 92180 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000117 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1387 | +| iterations | 19092 | +| time_elapsed | 28175 | +| total_timesteps | 39100416 | +| train/ | | +| approx_kl | 0.011235574 | +| clip_fraction | 0.315 | +| clip_range | 0.0652 | +| entropy_loss | -6 | +| explained_variance | 0.379 | +| learning_rate | 4.07e-05 | +| loss | -0.0216 | +| n_updates | 92184 | +| policy_gradient_loss | -0.0139 | +| value_loss | 0.000209 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1387 | +| iterations | 19093 | +| time_elapsed | 28176 | +| total_timesteps | 39102464 | +| train/ | | +| approx_kl | 0.013891382 | +| clip_fraction | 0.336 | +| clip_range | 0.0652 | +| entropy_loss | -6.25 | +| explained_variance | -0.395 | +| learning_rate | 4.07e-05 | +| loss | -0.0247 | +| n_updates | 92188 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000122 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1387 | +| iterations | 19094 | +| time_elapsed | 28178 | +| total_timesteps | 39104512 | +| train/ | | +| approx_kl | 0.0139091015 | +| clip_fraction | 0.312 | +| clip_range | 0.0652 | +| entropy_loss | -5.19 | +| explained_variance | 0.734 | +| learning_rate | 4.07e-05 | +| loss | -0.0288 | +| n_updates | 92192 | +| policy_gradient_loss | -0.0143 | +| value_loss | 0.000112 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1387 | +| iterations | 19095 | +| time_elapsed | 28180 | +| total_timesteps | 39106560 | +| train/ | | +| approx_kl | 0.011584828 | +| clip_fraction | 0.286 | +| clip_range | 0.0652 | +| entropy_loss | -4.38 | +| explained_variance | 0.405 | +| learning_rate | 4.07e-05 | +| loss | -0.0178 | +| n_updates | 92196 | +| policy_gradient_loss | -0.0118 | +| value_loss | 0.000403 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1387 | +| iterations | 19096 | +| time_elapsed | 28181 | +| total_timesteps | 39108608 | +| train/ | | +| approx_kl | 0.015319018 | +| clip_fraction | 0.369 | +| clip_range | 0.0652 | +| entropy_loss | -5.32 | +| explained_variance | 0.23 | +| learning_rate | 4.07e-05 | +| loss | -0.028 | +| n_updates | 92200 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000117 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1387 | +| iterations | 19097 | +| time_elapsed | 28183 | +| total_timesteps | 39110656 | +| train/ | | +| approx_kl | 0.014433343 | +| clip_fraction | 0.346 | +| clip_range | 0.0652 | +| entropy_loss | -5.32 | +| explained_variance | 0.374 | +| learning_rate | 4.07e-05 | +| loss | -0.0231 | +| n_updates | 92204 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000261 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1387 | +| iterations | 19098 | +| time_elapsed | 28184 | +| total_timesteps | 39112704 | +| train/ | | +| approx_kl | 0.015319057 | +| clip_fraction | 0.368 | +| clip_range | 0.0652 | +| entropy_loss | -6.13 | +| explained_variance | -0.238 | +| learning_rate | 4.07e-05 | +| loss | -0.0309 | +| n_updates | 92208 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000128 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1387 | +| iterations | 19099 | +| time_elapsed | 28186 | +| total_timesteps | 39114752 | +| train/ | | +| approx_kl | 0.018236026 | +| clip_fraction | 0.327 | +| clip_range | 0.0652 | +| entropy_loss | -5.97 | +| explained_variance | 0.386 | +| learning_rate | 4.07e-05 | +| loss | -0.0297 | +| n_updates | 92212 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000137 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1387 | +| iterations | 19100 | +| time_elapsed | 28187 | +| total_timesteps | 39116800 | +| train/ | | +| approx_kl | 0.010750283 | +| clip_fraction | 0.321 | +| clip_range | 0.0652 | +| entropy_loss | -6.28 | +| explained_variance | 0.0571 | +| learning_rate | 4.07e-05 | +| loss | -0.0238 | +| n_updates | 92216 | +| policy_gradient_loss | -0.0146 | +| value_loss | 0.000189 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1387 | +| iterations | 19101 | +| time_elapsed | 28189 | +| total_timesteps | 39118848 | +| train/ | | +| approx_kl | 0.009769011 | +| clip_fraction | 0.329 | +| clip_range | 0.0652 | +| entropy_loss | -6.21 | +| explained_variance | 0.0841 | +| learning_rate | 4.07e-05 | +| loss | -0.018 | +| n_updates | 92220 | +| policy_gradient_loss | -0.0138 | +| value_loss | 0.000335 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1387 | +| iterations | 19102 | +| time_elapsed | 28190 | +| total_timesteps | 39120896 | +| train/ | | +| approx_kl | 0.012062038 | +| clip_fraction | 0.329 | +| clip_range | 0.0652 | +| entropy_loss | -5.86 | +| explained_variance | 0.541 | +| learning_rate | 4.07e-05 | +| loss | -0.0258 | +| n_updates | 92224 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000155 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1387 | +| iterations | 19103 | +| time_elapsed | 28192 | +| total_timesteps | 39122944 | +| train/ | | +| approx_kl | 0.01160883 | +| clip_fraction | 0.33 | +| clip_range | 0.0652 | +| entropy_loss | -5.59 | +| explained_variance | 0.251 | +| learning_rate | 4.07e-05 | +| loss | -0.023 | +| n_updates | 92228 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.00035 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1387 | +| iterations | 19104 | +| time_elapsed | 28193 | +| total_timesteps | 39124992 | +| train/ | | +| approx_kl | 0.016567606 | +| clip_fraction | 0.355 | +| clip_range | 0.0652 | +| entropy_loss | -5.21 | +| explained_variance | 0.53 | +| learning_rate | 4.07e-05 | +| loss | -0.0295 | +| n_updates | 92232 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000146 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1387 | +| iterations | 19105 | +| time_elapsed | 28195 | +| total_timesteps | 39127040 | +| train/ | | +| approx_kl | 0.011085562 | +| clip_fraction | 0.35 | +| clip_range | 0.0652 | +| entropy_loss | -6 | +| explained_variance | 0.359 | +| learning_rate | 4.07e-05 | +| loss | -0.0309 | +| n_updates | 92236 | +| policy_gradient_loss | -0.018 | +| value_loss | 9.74e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1387 | +| iterations | 19106 | +| time_elapsed | 28196 | +| total_timesteps | 39129088 | +| train/ | | +| approx_kl | 0.012964498 | +| clip_fraction | 0.351 | +| clip_range | 0.0652 | +| entropy_loss | -5.82 | +| explained_variance | 0.425 | +| learning_rate | 4.07e-05 | +| loss | -0.029 | +| n_updates | 92240 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000137 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1387 | +| iterations | 19107 | +| time_elapsed | 28198 | +| total_timesteps | 39131136 | +| train/ | | +| approx_kl | 0.014265059 | +| clip_fraction | 0.306 | +| clip_range | 0.0652 | +| entropy_loss | -6.23 | +| explained_variance | 0.22 | +| learning_rate | 4.07e-05 | +| loss | -0.0221 | +| n_updates | 92244 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.000223 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1387 | +| iterations | 19108 | +| time_elapsed | 28199 | +| total_timesteps | 39133184 | +| train/ | | +| approx_kl | 0.018692147 | +| clip_fraction | 0.333 | +| clip_range | 0.0652 | +| entropy_loss | -5.46 | +| explained_variance | 0.456 | +| learning_rate | 4.07e-05 | +| loss | -0.0336 | +| n_updates | 92248 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000158 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1387 | +| iterations | 19109 | +| time_elapsed | 28201 | +| total_timesteps | 39135232 | +| train/ | | +| approx_kl | 0.012542019 | +| clip_fraction | 0.344 | +| clip_range | 0.0652 | +| entropy_loss | -5.97 | +| explained_variance | 0.492 | +| learning_rate | 4.07e-05 | +| loss | -0.0337 | +| n_updates | 92252 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000105 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1387 | +| iterations | 19110 | +| time_elapsed | 28202 | +| total_timesteps | 39137280 | +| train/ | | +| approx_kl | 0.015241044 | +| clip_fraction | 0.327 | +| clip_range | 0.0652 | +| entropy_loss | -6.32 | +| explained_variance | 0.337 | +| learning_rate | 4.07e-05 | +| loss | -0.0262 | +| n_updates | 92256 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000124 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1387 | +| iterations | 19111 | +| time_elapsed | 28204 | +| total_timesteps | 39139328 | +| train/ | | +| approx_kl | 0.010379895 | +| clip_fraction | 0.287 | +| clip_range | 0.0652 | +| entropy_loss | -5.56 | +| explained_variance | 0.399 | +| learning_rate | 4.07e-05 | +| loss | -0.0189 | +| n_updates | 92260 | +| policy_gradient_loss | -0.0119 | +| value_loss | 0.000287 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1387 | +| iterations | 19112 | +| time_elapsed | 28205 | +| total_timesteps | 39141376 | +| train/ | | +| approx_kl | 0.01347501 | +| clip_fraction | 0.352 | +| clip_range | 0.0652 | +| entropy_loss | -5.06 | +| explained_variance | 0.452 | +| learning_rate | 4.07e-05 | +| loss | -0.0304 | +| n_updates | 92264 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000132 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1387 | +| iterations | 19113 | +| time_elapsed | 28207 | +| total_timesteps | 39143424 | +| train/ | | +| approx_kl | 0.015609973 | +| clip_fraction | 0.351 | +| clip_range | 0.0652 | +| entropy_loss | -5.97 | +| explained_variance | 0.305 | +| learning_rate | 4.07e-05 | +| loss | -0.0268 | +| n_updates | 92268 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000164 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1387 | +| iterations | 19114 | +| time_elapsed | 28208 | +| total_timesteps | 39145472 | +| train/ | | +| approx_kl | 0.0133518465 | +| clip_fraction | 0.32 | +| clip_range | 0.0652 | +| entropy_loss | -5.87 | +| explained_variance | 0.444 | +| learning_rate | 4.07e-05 | +| loss | -0.0235 | +| n_updates | 92272 | +| policy_gradient_loss | -0.0147 | +| value_loss | 0.000161 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1387 | +| iterations | 19115 | +| time_elapsed | 28210 | +| total_timesteps | 39147520 | +| train/ | | +| approx_kl | 0.011170421 | +| clip_fraction | 0.324 | +| clip_range | 0.0652 | +| entropy_loss | -6.08 | +| explained_variance | 0.469 | +| learning_rate | 4.07e-05 | +| loss | -0.0332 | +| n_updates | 92276 | +| policy_gradient_loss | -0.0161 | +| value_loss | 7.44e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1387 | +| iterations | 19116 | +| time_elapsed | 28211 | +| total_timesteps | 39149568 | +| train/ | | +| approx_kl | 0.011790717 | +| clip_fraction | 0.296 | +| clip_range | 0.0652 | +| entropy_loss | -5.18 | +| explained_variance | 0.733 | +| learning_rate | 4.07e-05 | +| loss | -0.0218 | +| n_updates | 92280 | +| policy_gradient_loss | -0.0143 | +| value_loss | 0.000143 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1387 | +| iterations | 19117 | +| time_elapsed | 28213 | +| total_timesteps | 39151616 | +| train/ | | +| approx_kl | 0.019558458 | +| clip_fraction | 0.339 | +| clip_range | 0.0652 | +| entropy_loss | -4.39 | +| explained_variance | 0.725 | +| learning_rate | 4.07e-05 | +| loss | -0.0226 | +| n_updates | 92284 | +| policy_gradient_loss | -0.0162 | +| value_loss | 9.67e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1387 | +| iterations | 19118 | +| time_elapsed | 28215 | +| total_timesteps | 39153664 | +| train/ | | +| approx_kl | 0.015461529 | +| clip_fraction | 0.33 | +| clip_range | 0.0652 | +| entropy_loss | -5.16 | +| explained_variance | 0.0653 | +| learning_rate | 4.07e-05 | +| loss | -0.0281 | +| n_updates | 92288 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000137 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1387 | +| iterations | 19119 | +| time_elapsed | 28216 | +| total_timesteps | 39155712 | +| train/ | | +| approx_kl | 0.016432684 | +| clip_fraction | 0.366 | +| clip_range | 0.0652 | +| entropy_loss | -5.69 | +| explained_variance | 0.169 | +| learning_rate | 4.07e-05 | +| loss | -0.0293 | +| n_updates | 92292 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000116 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1387 | +| iterations | 19120 | +| time_elapsed | 28218 | +| total_timesteps | 39157760 | +| train/ | | +| approx_kl | 0.012525855 | +| clip_fraction | 0.334 | +| clip_range | 0.0652 | +| entropy_loss | -5.99 | +| explained_variance | 0.446 | +| learning_rate | 4.07e-05 | +| loss | -0.0239 | +| n_updates | 92296 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000108 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1387 | +| iterations | 19121 | +| time_elapsed | 28219 | +| total_timesteps | 39159808 | +| train/ | | +| approx_kl | 0.013833787 | +| clip_fraction | 0.345 | +| clip_range | 0.0652 | +| entropy_loss | -5.92 | +| explained_variance | 0.207 | +| learning_rate | 4.07e-05 | +| loss | -0.023 | +| n_updates | 92300 | +| policy_gradient_loss | -0.0146 | +| value_loss | 0.000316 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1387 | +| iterations | 19122 | +| time_elapsed | 28221 | +| total_timesteps | 39161856 | +| train/ | | +| approx_kl | 0.011430664 | +| clip_fraction | 0.348 | +| clip_range | 0.0652 | +| entropy_loss | -6.07 | +| explained_variance | 0.358 | +| learning_rate | 4.07e-05 | +| loss | -0.0254 | +| n_updates | 92304 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.00013 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1387 | +| iterations | 19123 | +| time_elapsed | 28222 | +| total_timesteps | 39163904 | +| train/ | | +| approx_kl | 0.01663273 | +| clip_fraction | 0.323 | +| clip_range | 0.0652 | +| entropy_loss | -5.35 | +| explained_variance | 0.336 | +| learning_rate | 4.07e-05 | +| loss | -0.0265 | +| n_updates | 92308 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000237 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1387 | +| iterations | 19124 | +| time_elapsed | 28224 | +| total_timesteps | 39165952 | +| train/ | | +| approx_kl | 0.017134486 | +| clip_fraction | 0.312 | +| clip_range | 0.0652 | +| entropy_loss | -4.98 | +| explained_variance | 0.378 | +| learning_rate | 4.07e-05 | +| loss | -0.0297 | +| n_updates | 92312 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000274 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1387 | +| iterations | 19125 | +| time_elapsed | 28225 | +| total_timesteps | 39168000 | +| train/ | | +| approx_kl | 0.012667457 | +| clip_fraction | 0.352 | +| clip_range | 0.0652 | +| entropy_loss | -5.6 | +| explained_variance | 0.286 | +| learning_rate | 4.07e-05 | +| loss | -0.0297 | +| n_updates | 92316 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000155 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1387 | +| iterations | 19126 | +| time_elapsed | 28227 | +| total_timesteps | 39170048 | +| train/ | | +| approx_kl | 0.016696697 | +| clip_fraction | 0.368 | +| clip_range | 0.0652 | +| entropy_loss | -6.09 | +| explained_variance | -0.0416 | +| learning_rate | 4.07e-05 | +| loss | -0.0331 | +| n_updates | 92320 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000104 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1387 | +| iterations | 19127 | +| time_elapsed | 28228 | +| total_timesteps | 39172096 | +| train/ | | +| approx_kl | 0.014553877 | +| clip_fraction | 0.32 | +| clip_range | 0.0652 | +| entropy_loss | -6.25 | +| explained_variance | 0.299 | +| learning_rate | 4.07e-05 | +| loss | -0.0261 | +| n_updates | 92324 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1387 | +| iterations | 19128 | +| time_elapsed | 28230 | +| total_timesteps | 39174144 | +| train/ | | +| approx_kl | 0.013277419 | +| clip_fraction | 0.37 | +| clip_range | 0.0652 | +| entropy_loss | -6.08 | +| explained_variance | 0.38 | +| learning_rate | 4.07e-05 | +| loss | -0.0283 | +| n_updates | 92328 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000105 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1387 | +| iterations | 19129 | +| time_elapsed | 28231 | +| total_timesteps | 39176192 | +| train/ | | +| approx_kl | 0.009033491 | +| clip_fraction | 0.31 | +| clip_range | 0.0652 | +| entropy_loss | -6.05 | +| explained_variance | 0.414 | +| learning_rate | 4.07e-05 | +| loss | -0.0197 | +| n_updates | 92332 | +| policy_gradient_loss | -0.0127 | +| value_loss | 0.000202 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1387 | +| iterations | 19130 | +| time_elapsed | 28233 | +| total_timesteps | 39178240 | +| train/ | | +| approx_kl | 0.011426023 | +| clip_fraction | 0.317 | +| clip_range | 0.0652 | +| entropy_loss | -5.75 | +| explained_variance | 0.55 | +| learning_rate | 4.07e-05 | +| loss | -0.0226 | +| n_updates | 92336 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000122 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1387 | +| iterations | 19131 | +| time_elapsed | 28234 | +| total_timesteps | 39180288 | +| train/ | | +| approx_kl | 0.01991247 | +| clip_fraction | 0.374 | +| clip_range | 0.0652 | +| entropy_loss | -4.98 | +| explained_variance | 0.503 | +| learning_rate | 4.07e-05 | +| loss | -0.0294 | +| n_updates | 92340 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000149 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1387 | +| iterations | 19132 | +| time_elapsed | 28236 | +| total_timesteps | 39182336 | +| train/ | | +| approx_kl | 0.013938855 | +| clip_fraction | 0.342 | +| clip_range | 0.0652 | +| entropy_loss | -5.36 | +| explained_variance | 0.592 | +| learning_rate | 4.07e-05 | +| loss | -0.0281 | +| n_updates | 92344 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000103 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1387 | +| iterations | 19133 | +| time_elapsed | 28237 | +| total_timesteps | 39184384 | +| train/ | | +| approx_kl | 0.013718451 | +| clip_fraction | 0.367 | +| clip_range | 0.0652 | +| entropy_loss | -5.1 | +| explained_variance | 0.57 | +| learning_rate | 4.07e-05 | +| loss | -0.0285 | +| n_updates | 92348 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000158 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1387 | +| iterations | 19134 | +| time_elapsed | 28239 | +| total_timesteps | 39186432 | +| train/ | | +| approx_kl | 0.013055623 | +| clip_fraction | 0.336 | +| clip_range | 0.0652 | +| entropy_loss | -5.44 | +| explained_variance | 0.43 | +| learning_rate | 4.07e-05 | +| loss | -0.0238 | +| n_updates | 92352 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000266 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1387 | +| iterations | 19135 | +| time_elapsed | 28240 | +| total_timesteps | 39188480 | +| train/ | | +| approx_kl | 0.013448926 | +| clip_fraction | 0.335 | +| clip_range | 0.0652 | +| entropy_loss | -5.59 | +| explained_variance | -0.142 | +| learning_rate | 4.07e-05 | +| loss | -0.0243 | +| n_updates | 92356 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000106 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1387 | +| iterations | 19136 | +| time_elapsed | 28242 | +| total_timesteps | 39190528 | +| train/ | | +| approx_kl | 0.016499551 | +| clip_fraction | 0.353 | +| clip_range | 0.0652 | +| entropy_loss | -6.24 | +| explained_variance | -0.11 | +| learning_rate | 4.07e-05 | +| loss | -0.0319 | +| n_updates | 92360 | +| policy_gradient_loss | -0.0179 | +| value_loss | 9.08e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1387 | +| iterations | 19137 | +| time_elapsed | 28243 | +| total_timesteps | 39192576 | +| train/ | | +| approx_kl | 0.012807951 | +| clip_fraction | 0.318 | +| clip_range | 0.0652 | +| entropy_loss | -5.74 | +| explained_variance | 0.357 | +| learning_rate | 4.07e-05 | +| loss | -0.021 | +| n_updates | 92364 | +| policy_gradient_loss | -0.0147 | +| value_loss | 0.00033 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1387 | +| iterations | 19138 | +| time_elapsed | 28245 | +| total_timesteps | 39194624 | +| train/ | | +| approx_kl | 0.014497526 | +| clip_fraction | 0.366 | +| clip_range | 0.0652 | +| entropy_loss | -5.42 | +| explained_variance | 0.351 | +| learning_rate | 4.07e-05 | +| loss | -0.0345 | +| n_updates | 92368 | +| policy_gradient_loss | -0.0208 | +| value_loss | 8.11e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1387 | +| iterations | 19139 | +| time_elapsed | 28246 | +| total_timesteps | 39196672 | +| train/ | | +| approx_kl | 0.015561019 | +| clip_fraction | 0.343 | +| clip_range | 0.0652 | +| entropy_loss | -6.33 | +| explained_variance | -0.0992 | +| learning_rate | 4.07e-05 | +| loss | -0.0359 | +| n_updates | 92372 | +| policy_gradient_loss | -0.0185 | +| value_loss | 8.23e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1387 | +| iterations | 19140 | +| time_elapsed | 28248 | +| total_timesteps | 39198720 | +| train/ | | +| approx_kl | 0.013297081 | +| clip_fraction | 0.322 | +| clip_range | 0.0652 | +| entropy_loss | -6.04 | +| explained_variance | 0.32 | +| learning_rate | 4.07e-05 | +| loss | -0.0185 | +| n_updates | 92376 | +| policy_gradient_loss | -0.0144 | +| value_loss | 0.000175 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1387 | +| iterations | 19141 | +| time_elapsed | 28249 | +| total_timesteps | 39200768 | +| train/ | | +| approx_kl | 0.012398364 | +| clip_fraction | 0.324 | +| clip_range | 0.0652 | +| entropy_loss | -4.78 | +| explained_variance | 0.715 | +| learning_rate | 4.07e-05 | +| loss | -0.0263 | +| n_updates | 92380 | +| policy_gradient_loss | -0.0166 | +| value_loss | 8.4e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1387 | +| iterations | 19142 | +| time_elapsed | 28251 | +| total_timesteps | 39202816 | +| train/ | | +| approx_kl | 0.009869505 | +| clip_fraction | 0.298 | +| clip_range | 0.0652 | +| entropy_loss | -4.79 | +| explained_variance | 0.679 | +| learning_rate | 4.07e-05 | +| loss | -0.0206 | +| n_updates | 92384 | +| policy_gradient_loss | -0.0133 | +| value_loss | 0.000125 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1387 | +| iterations | 19143 | +| time_elapsed | 28252 | +| total_timesteps | 39204864 | +| train/ | | +| approx_kl | 0.014873094 | +| clip_fraction | 0.354 | +| clip_range | 0.0652 | +| entropy_loss | -4.82 | +| explained_variance | 0.386 | +| learning_rate | 4.07e-05 | +| loss | -0.0281 | +| n_updates | 92388 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000133 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1387 | +| iterations | 19144 | +| time_elapsed | 28254 | +| total_timesteps | 39206912 | +| train/ | | +| approx_kl | 0.011750078 | +| clip_fraction | 0.339 | +| clip_range | 0.0652 | +| entropy_loss | -5.48 | +| explained_variance | 0.517 | +| learning_rate | 4.07e-05 | +| loss | -0.028 | +| n_updates | 92392 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000127 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1387 | +| iterations | 19145 | +| time_elapsed | 28255 | +| total_timesteps | 39208960 | +| train/ | | +| approx_kl | 0.01062156 | +| clip_fraction | 0.329 | +| clip_range | 0.0652 | +| entropy_loss | -6.04 | +| explained_variance | 0.126 | +| learning_rate | 4.07e-05 | +| loss | -0.0221 | +| n_updates | 92396 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000168 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1387 | +| iterations | 19146 | +| time_elapsed | 28257 | +| total_timesteps | 39211008 | +| train/ | | +| approx_kl | 0.015781265 | +| clip_fraction | 0.358 | +| clip_range | 0.0652 | +| entropy_loss | -6.29 | +| explained_variance | -0.0327 | +| learning_rate | 4.07e-05 | +| loss | -0.0279 | +| n_updates | 92400 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000177 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1387 | +| iterations | 19147 | +| time_elapsed | 28259 | +| total_timesteps | 39213056 | +| train/ | | +| approx_kl | 0.009044217 | +| clip_fraction | 0.326 | +| clip_range | 0.0652 | +| entropy_loss | -6.06 | +| explained_variance | 0.177 | +| learning_rate | 4.07e-05 | +| loss | -0.0237 | +| n_updates | 92404 | +| policy_gradient_loss | -0.0143 | +| value_loss | 0.000513 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1387 | +| iterations | 19148 | +| time_elapsed | 28260 | +| total_timesteps | 39215104 | +| train/ | | +| approx_kl | 0.017153794 | +| clip_fraction | 0.327 | +| clip_range | 0.0652 | +| entropy_loss | -5.05 | +| explained_variance | 0.438 | +| learning_rate | 4.07e-05 | +| loss | -0.0266 | +| n_updates | 92408 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.00015 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1387 | +| iterations | 19149 | +| time_elapsed | 28262 | +| total_timesteps | 39217152 | +| train/ | | +| approx_kl | 0.015664395 | +| clip_fraction | 0.349 | +| clip_range | 0.0652 | +| entropy_loss | -5.15 | +| explained_variance | 0.391 | +| learning_rate | 4.07e-05 | +| loss | -0.0247 | +| n_updates | 92412 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000229 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1387 | +| iterations | 19150 | +| time_elapsed | 28263 | +| total_timesteps | 39219200 | +| train/ | | +| approx_kl | 0.01288259 | +| clip_fraction | 0.348 | +| clip_range | 0.0652 | +| entropy_loss | -5.91 | +| explained_variance | 0.27 | +| learning_rate | 4.07e-05 | +| loss | -0.0312 | +| n_updates | 92416 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.00021 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1387 | +| iterations | 19151 | +| time_elapsed | 28265 | +| total_timesteps | 39221248 | +| train/ | | +| approx_kl | 0.014300383 | +| clip_fraction | 0.305 | +| clip_range | 0.0652 | +| entropy_loss | -5.18 | +| explained_variance | 0.369 | +| learning_rate | 4.07e-05 | +| loss | -0.0229 | +| n_updates | 92420 | +| policy_gradient_loss | -0.0146 | +| value_loss | 0.000222 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1387 | +| iterations | 19152 | +| time_elapsed | 28266 | +| total_timesteps | 39223296 | +| train/ | | +| approx_kl | 0.013850022 | +| clip_fraction | 0.302 | +| clip_range | 0.0652 | +| entropy_loss | -4.82 | +| explained_variance | 0.547 | +| learning_rate | 4.07e-05 | +| loss | -0.0255 | +| n_updates | 92424 | +| policy_gradient_loss | -0.014 | +| value_loss | 0.000181 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1387 | +| iterations | 19153 | +| time_elapsed | 28268 | +| total_timesteps | 39225344 | +| train/ | | +| approx_kl | 0.015134721 | +| clip_fraction | 0.34 | +| clip_range | 0.0652 | +| entropy_loss | -5.58 | +| explained_variance | 0.157 | +| learning_rate | 4.07e-05 | +| loss | -0.0295 | +| n_updates | 92428 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.00022 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1387 | +| iterations | 19154 | +| time_elapsed | 28269 | +| total_timesteps | 39227392 | +| train/ | | +| approx_kl | 0.012946857 | +| clip_fraction | 0.353 | +| clip_range | 0.0652 | +| entropy_loss | -6.3 | +| explained_variance | -0.115 | +| learning_rate | 4.07e-05 | +| loss | -0.0281 | +| n_updates | 92432 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.00023 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1387 | +| iterations | 19155 | +| time_elapsed | 28271 | +| total_timesteps | 39229440 | +| train/ | | +| approx_kl | 0.010158123 | +| clip_fraction | 0.328 | +| clip_range | 0.0652 | +| entropy_loss | -6.06 | +| explained_variance | 0.239 | +| learning_rate | 4.07e-05 | +| loss | -0.0219 | +| n_updates | 92436 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000266 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1387 | +| iterations | 19156 | +| time_elapsed | 28272 | +| total_timesteps | 39231488 | +| train/ | | +| approx_kl | 0.013943851 | +| clip_fraction | 0.38 | +| clip_range | 0.0652 | +| entropy_loss | -5.75 | +| explained_variance | 0.423 | +| learning_rate | 4.07e-05 | +| loss | -0.0306 | +| n_updates | 92440 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000181 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1387 | +| iterations | 19157 | +| time_elapsed | 28274 | +| total_timesteps | 39233536 | +| train/ | | +| approx_kl | 0.011298863 | +| clip_fraction | 0.344 | +| clip_range | 0.0652 | +| entropy_loss | -6.31 | +| explained_variance | 0.233 | +| learning_rate | 4.07e-05 | +| loss | -0.0248 | +| n_updates | 92444 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.000247 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1387 | +| iterations | 19158 | +| time_elapsed | 28275 | +| total_timesteps | 39235584 | +| train/ | | +| approx_kl | 0.011031231 | +| clip_fraction | 0.343 | +| clip_range | 0.0652 | +| entropy_loss | -6.34 | +| explained_variance | 0.331 | +| learning_rate | 4.07e-05 | +| loss | -0.0326 | +| n_updates | 92448 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000171 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1387 | +| iterations | 19159 | +| time_elapsed | 28277 | +| total_timesteps | 39237632 | +| train/ | | +| approx_kl | 0.011586811 | +| clip_fraction | 0.342 | +| clip_range | 0.0652 | +| entropy_loss | -6.02 | +| explained_variance | 0.398 | +| learning_rate | 4.07e-05 | +| loss | -0.0249 | +| n_updates | 92452 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.00019 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1387 | +| iterations | 19160 | +| time_elapsed | 28278 | +| total_timesteps | 39239680 | +| train/ | | +| approx_kl | 0.010930144 | +| clip_fraction | 0.272 | +| clip_range | 0.0652 | +| entropy_loss | -5.49 | +| explained_variance | 0.37 | +| learning_rate | 4.07e-05 | +| loss | -0.0223 | +| n_updates | 92456 | +| policy_gradient_loss | -0.0131 | +| value_loss | 0.000253 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1387 | +| iterations | 19161 | +| time_elapsed | 28280 | +| total_timesteps | 39241728 | +| train/ | | +| approx_kl | 0.010366214 | +| clip_fraction | 0.307 | +| clip_range | 0.0652 | +| entropy_loss | -5.27 | +| explained_variance | 0.249 | +| learning_rate | 4.07e-05 | +| loss | -0.0248 | +| n_updates | 92460 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.000517 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1387 | +| iterations | 19162 | +| time_elapsed | 28281 | +| total_timesteps | 39243776 | +| train/ | | +| approx_kl | 0.014891509 | +| clip_fraction | 0.33 | +| clip_range | 0.0652 | +| entropy_loss | -5.18 | +| explained_variance | 0.478 | +| learning_rate | 4.07e-05 | +| loss | -0.0285 | +| n_updates | 92464 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000151 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1387 | +| iterations | 19163 | +| time_elapsed | 28283 | +| total_timesteps | 39245824 | +| train/ | | +| approx_kl | 0.013404722 | +| clip_fraction | 0.323 | +| clip_range | 0.0652 | +| entropy_loss | -5.6 | +| explained_variance | 0.337 | +| learning_rate | 4.07e-05 | +| loss | -0.0298 | +| n_updates | 92468 | +| policy_gradient_loss | -0.0147 | +| value_loss | 0.000251 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1387 | +| iterations | 19164 | +| time_elapsed | 28285 | +| total_timesteps | 39247872 | +| train/ | | +| approx_kl | 0.015933387 | +| clip_fraction | 0.363 | +| clip_range | 0.0652 | +| entropy_loss | -5.03 | +| explained_variance | 0.477 | +| learning_rate | 4.07e-05 | +| loss | -0.0311 | +| n_updates | 92472 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000143 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1387 | +| iterations | 19165 | +| time_elapsed | 28286 | +| total_timesteps | 39249920 | +| train/ | | +| approx_kl | 0.013825348 | +| clip_fraction | 0.368 | +| clip_range | 0.0652 | +| entropy_loss | -5.7 | +| explained_variance | 0.512 | +| learning_rate | 4.07e-05 | +| loss | -0.0275 | +| n_updates | 92476 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1387 | +| iterations | 19166 | +| time_elapsed | 28288 | +| total_timesteps | 39251968 | +| train/ | | +| approx_kl | 0.016123135 | +| clip_fraction | 0.343 | +| clip_range | 0.0652 | +| entropy_loss | -5.74 | +| explained_variance | 0.434 | +| learning_rate | 4.07e-05 | +| loss | -0.035 | +| n_updates | 92480 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000103 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1387 | +| iterations | 19167 | +| time_elapsed | 28289 | +| total_timesteps | 39254016 | +| train/ | | +| approx_kl | 0.014201611 | +| clip_fraction | 0.321 | +| clip_range | 0.0652 | +| entropy_loss | -5.72 | +| explained_variance | 0.3 | +| learning_rate | 4.07e-05 | +| loss | -0.022 | +| n_updates | 92484 | +| policy_gradient_loss | -0.013 | +| value_loss | 0.000219 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1387 | +| iterations | 19168 | +| time_elapsed | 28291 | +| total_timesteps | 39256064 | +| train/ | | +| approx_kl | 0.012088895 | +| clip_fraction | 0.319 | +| clip_range | 0.0652 | +| entropy_loss | -5.86 | +| explained_variance | 0.575 | +| learning_rate | 4.07e-05 | +| loss | -0.0219 | +| n_updates | 92488 | +| policy_gradient_loss | -0.0166 | +| value_loss | 9.58e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1387 | +| iterations | 19169 | +| time_elapsed | 28292 | +| total_timesteps | 39258112 | +| train/ | | +| approx_kl | 0.014726413 | +| clip_fraction | 0.364 | +| clip_range | 0.0652 | +| entropy_loss | -5.51 | +| explained_variance | 0.676 | +| learning_rate | 4.07e-05 | +| loss | -0.0335 | +| n_updates | 92492 | +| policy_gradient_loss | -0.0194 | +| value_loss | 7.05e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1387 | +| iterations | 19170 | +| time_elapsed | 28294 | +| total_timesteps | 39260160 | +| train/ | | +| approx_kl | 0.010037543 | +| clip_fraction | 0.305 | +| clip_range | 0.0652 | +| entropy_loss | -5.9 | +| explained_variance | 0.439 | +| learning_rate | 4.07e-05 | +| loss | -0.0256 | +| n_updates | 92496 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000178 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1387 | +| iterations | 19171 | +| time_elapsed | 28295 | +| total_timesteps | 39262208 | +| train/ | | +| approx_kl | 0.01521088 | +| clip_fraction | 0.314 | +| clip_range | 0.0652 | +| entropy_loss | -5.66 | +| explained_variance | 0.607 | +| learning_rate | 4.07e-05 | +| loss | -0.025 | +| n_updates | 92500 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000115 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1387 | +| iterations | 19172 | +| time_elapsed | 28297 | +| total_timesteps | 39264256 | +| train/ | | +| approx_kl | 0.010361558 | +| clip_fraction | 0.313 | +| clip_range | 0.0652 | +| entropy_loss | -6.42 | +| explained_variance | 0.409 | +| learning_rate | 4.07e-05 | +| loss | -0.0244 | +| n_updates | 92504 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000102 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1387 | +| iterations | 19173 | +| time_elapsed | 28298 | +| total_timesteps | 39266304 | +| train/ | | +| approx_kl | 0.012765838 | +| clip_fraction | 0.301 | +| clip_range | 0.0652 | +| entropy_loss | -6.01 | +| explained_variance | 0.0559 | +| learning_rate | 4.07e-05 | +| loss | -0.0216 | +| n_updates | 92508 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000229 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1387 | +| iterations | 19174 | +| time_elapsed | 28300 | +| total_timesteps | 39268352 | +| train/ | | +| approx_kl | 0.013246394 | +| clip_fraction | 0.329 | +| clip_range | 0.0652 | +| entropy_loss | -5.91 | +| explained_variance | 0.555 | +| learning_rate | 4.07e-05 | +| loss | -0.033 | +| n_updates | 92512 | +| policy_gradient_loss | -0.0186 | +| value_loss | 8.46e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1387 | +| iterations | 19175 | +| time_elapsed | 28301 | +| total_timesteps | 39270400 | +| train/ | | +| approx_kl | 0.013534777 | +| clip_fraction | 0.34 | +| clip_range | 0.0652 | +| entropy_loss | -6.07 | +| explained_variance | -0.127 | +| learning_rate | 4.07e-05 | +| loss | -0.0311 | +| n_updates | 92516 | +| policy_gradient_loss | -0.0192 | +| value_loss | 8.97e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1387 | +| iterations | 19176 | +| time_elapsed | 28303 | +| total_timesteps | 39272448 | +| train/ | | +| approx_kl | 0.012869764 | +| clip_fraction | 0.326 | +| clip_range | 0.0652 | +| entropy_loss | -6.1 | +| explained_variance | -0.177 | +| learning_rate | 4.07e-05 | +| loss | -0.0314 | +| n_updates | 92520 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000116 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1387 | +| iterations | 19177 | +| time_elapsed | 28304 | +| total_timesteps | 39274496 | +| train/ | | +| approx_kl | 0.011699678 | +| clip_fraction | 0.278 | +| clip_range | 0.0652 | +| entropy_loss | -6.04 | +| explained_variance | 0.357 | +| learning_rate | 4.07e-05 | +| loss | -0.0263 | +| n_updates | 92524 | +| policy_gradient_loss | -0.0142 | +| value_loss | 0.000222 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1387 | +| iterations | 19178 | +| time_elapsed | 28306 | +| total_timesteps | 39276544 | +| train/ | | +| approx_kl | 0.01406876 | +| clip_fraction | 0.318 | +| clip_range | 0.0652 | +| entropy_loss | -5.63 | +| explained_variance | 0.603 | +| learning_rate | 4.07e-05 | +| loss | -0.028 | +| n_updates | 92528 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000125 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1387 | +| iterations | 19179 | +| time_elapsed | 28308 | +| total_timesteps | 39278592 | +| train/ | | +| approx_kl | 0.015636269 | +| clip_fraction | 0.335 | +| clip_range | 0.0652 | +| entropy_loss | -5.5 | +| explained_variance | 0.487 | +| learning_rate | 4.07e-05 | +| loss | -0.0268 | +| n_updates | 92532 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000114 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1387 | +| iterations | 19180 | +| time_elapsed | 28309 | +| total_timesteps | 39280640 | +| train/ | | +| approx_kl | 0.016897727 | +| clip_fraction | 0.317 | +| clip_range | 0.0652 | +| entropy_loss | -5.14 | +| explained_variance | 0.426 | +| learning_rate | 4.07e-05 | +| loss | -0.0221 | +| n_updates | 92536 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000288 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1387 | +| iterations | 19181 | +| time_elapsed | 28311 | +| total_timesteps | 39282688 | +| train/ | | +| approx_kl | 0.013888915 | +| clip_fraction | 0.337 | +| clip_range | 0.0652 | +| entropy_loss | -5.54 | +| explained_variance | 0.473 | +| learning_rate | 4.07e-05 | +| loss | -0.0293 | +| n_updates | 92540 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.00014 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.384 | +| time/ | | +| fps | 1387 | +| iterations | 19182 | +| time_elapsed | 28312 | +| total_timesteps | 39284736 | +| train/ | | +| approx_kl | 0.011573033 | +| clip_fraction | 0.32 | +| clip_range | 0.0652 | +| entropy_loss | -5.75 | +| explained_variance | -0.129 | +| learning_rate | 4.07e-05 | +| loss | -0.0249 | +| n_updates | 92544 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000144 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.384 | +| time/ | | +| fps | 1387 | +| iterations | 19183 | +| time_elapsed | 28314 | +| total_timesteps | 39286784 | +| train/ | | +| approx_kl | 0.010711722 | +| clip_fraction | 0.305 | +| clip_range | 0.0652 | +| entropy_loss | -5.95 | +| explained_variance | 0.496 | +| learning_rate | 4.07e-05 | +| loss | -0.0247 | +| n_updates | 92548 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000154 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.387 | +| time/ | | +| fps | 1387 | +| iterations | 19184 | +| time_elapsed | 28315 | +| total_timesteps | 39288832 | +| train/ | | +| approx_kl | 0.010711693 | +| clip_fraction | 0.308 | +| clip_range | 0.0652 | +| entropy_loss | -6.24 | +| explained_variance | 0.107 | +| learning_rate | 4.07e-05 | +| loss | -0.0256 | +| n_updates | 92552 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000207 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.387 | +| time/ | | +| fps | 1387 | +| iterations | 19185 | +| time_elapsed | 28317 | +| total_timesteps | 39290880 | +| train/ | | +| approx_kl | 0.009108969 | +| clip_fraction | 0.285 | +| clip_range | 0.0652 | +| entropy_loss | -5.83 | +| explained_variance | 0.415 | +| learning_rate | 4.07e-05 | +| loss | -0.0218 | +| n_updates | 92556 | +| policy_gradient_loss | -0.0135 | +| value_loss | 0.000392 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1387 | +| iterations | 19186 | +| time_elapsed | 28318 | +| total_timesteps | 39292928 | +| train/ | | +| approx_kl | 0.011203574 | +| clip_fraction | 0.322 | +| clip_range | 0.0652 | +| entropy_loss | -5.44 | +| explained_variance | 0.311 | +| learning_rate | 4.07e-05 | +| loss | -0.0201 | +| n_updates | 92560 | +| policy_gradient_loss | -0.0146 | +| value_loss | 0.000284 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.386 | +| time/ | | +| fps | 1387 | +| iterations | 19187 | +| time_elapsed | 28320 | +| total_timesteps | 39294976 | +| train/ | | +| approx_kl | 0.013781238 | +| clip_fraction | 0.331 | +| clip_range | 0.0652 | +| entropy_loss | -5.56 | +| explained_variance | 0.417 | +| learning_rate | 4.07e-05 | +| loss | -0.026 | +| n_updates | 92564 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000104 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.384 | +| time/ | | +| fps | 1387 | +| iterations | 19188 | +| time_elapsed | 28321 | +| total_timesteps | 39297024 | +| train/ | | +| approx_kl | 0.014898016 | +| clip_fraction | 0.358 | +| clip_range | 0.0652 | +| entropy_loss | -5.39 | +| explained_variance | 0.509 | +| learning_rate | 4.07e-05 | +| loss | -0.0278 | +| n_updates | 92568 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000145 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1387 | +| iterations | 19189 | +| time_elapsed | 28323 | +| total_timesteps | 39299072 | +| train/ | | +| approx_kl | 0.015433854 | +| clip_fraction | 0.346 | +| clip_range | 0.0652 | +| entropy_loss | -5.42 | +| explained_variance | 0.334 | +| learning_rate | 4.07e-05 | +| loss | -0.0331 | +| n_updates | 92572 | +| policy_gradient_loss | -0.0192 | +| value_loss | 9.88e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1387 | +| iterations | 19190 | +| time_elapsed | 28325 | +| total_timesteps | 39301120 | +| train/ | | +| approx_kl | 0.01674752 | +| clip_fraction | 0.343 | +| clip_range | 0.0652 | +| entropy_loss | -5.54 | +| explained_variance | 0.635 | +| learning_rate | 4.07e-05 | +| loss | -0.0285 | +| n_updates | 92576 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000111 | +---------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1387 | +| iterations | 19191 | +| time_elapsed | 28326 | +| total_timesteps | 39303168 | +| train/ | | +| approx_kl | 0.0154383 | +| clip_fraction | 0.321 | +| clip_range | 0.0652 | +| entropy_loss | -5.42 | +| explained_variance | 0.256 | +| learning_rate | 4.07e-05 | +| loss | -0.0246 | +| n_updates | 92580 | +| policy_gradient_loss | -0.0146 | +| value_loss | 0.000195 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1387 | +| iterations | 19192 | +| time_elapsed | 28328 | +| total_timesteps | 39305216 | +| train/ | | +| approx_kl | 0.015094615 | +| clip_fraction | 0.314 | +| clip_range | 0.0652 | +| entropy_loss | -5.89 | +| explained_variance | 0.515 | +| learning_rate | 4.07e-05 | +| loss | -0.0245 | +| n_updates | 92584 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000129 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1387 | +| iterations | 19193 | +| time_elapsed | 28329 | +| total_timesteps | 39307264 | +| train/ | | +| approx_kl | 0.013976349 | +| clip_fraction | 0.327 | +| clip_range | 0.0652 | +| entropy_loss | -5.66 | +| explained_variance | 0.554 | +| learning_rate | 4.07e-05 | +| loss | -0.0256 | +| n_updates | 92588 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000118 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1387 | +| iterations | 19194 | +| time_elapsed | 28331 | +| total_timesteps | 39309312 | +| train/ | | +| approx_kl | 0.017879725 | +| clip_fraction | 0.32 | +| clip_range | 0.0652 | +| entropy_loss | -5.63 | +| explained_variance | -0.0792 | +| learning_rate | 4.07e-05 | +| loss | -0.0253 | +| n_updates | 92592 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000132 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1387 | +| iterations | 19195 | +| time_elapsed | 28332 | +| total_timesteps | 39311360 | +| train/ | | +| approx_kl | 0.012667853 | +| clip_fraction | 0.295 | +| clip_range | 0.0652 | +| entropy_loss | -6.04 | +| explained_variance | 0.346 | +| learning_rate | 4.07e-05 | +| loss | -0.0281 | +| n_updates | 92596 | +| policy_gradient_loss | -0.0145 | +| value_loss | 0.000188 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1387 | +| iterations | 19196 | +| time_elapsed | 28334 | +| total_timesteps | 39313408 | +| train/ | | +| approx_kl | 0.01386256 | +| clip_fraction | 0.31 | +| clip_range | 0.0652 | +| entropy_loss | -5.87 | +| explained_variance | 0.47 | +| learning_rate | 4.07e-05 | +| loss | -0.0258 | +| n_updates | 92600 | +| policy_gradient_loss | -0.0148 | +| value_loss | 0.000159 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1387 | +| iterations | 19197 | +| time_elapsed | 28335 | +| total_timesteps | 39315456 | +| train/ | | +| approx_kl | 0.014395798 | +| clip_fraction | 0.347 | +| clip_range | 0.0652 | +| entropy_loss | -5.79 | +| explained_variance | 0.386 | +| learning_rate | 4.07e-05 | +| loss | -0.0299 | +| n_updates | 92604 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000102 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1387 | +| iterations | 19198 | +| time_elapsed | 28337 | +| total_timesteps | 39317504 | +| train/ | | +| approx_kl | 0.014797565 | +| clip_fraction | 0.316 | +| clip_range | 0.0652 | +| entropy_loss | -5.11 | +| explained_variance | 0.665 | +| learning_rate | 4.07e-05 | +| loss | -0.0328 | +| n_updates | 92608 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000118 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1387 | +| iterations | 19199 | +| time_elapsed | 28338 | +| total_timesteps | 39319552 | +| train/ | | +| approx_kl | 0.014548056 | +| clip_fraction | 0.332 | +| clip_range | 0.0652 | +| entropy_loss | -5.13 | +| explained_variance | 0.357 | +| learning_rate | 4.07e-05 | +| loss | -0.0247 | +| n_updates | 92612 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000275 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1387 | +| iterations | 19200 | +| time_elapsed | 28340 | +| total_timesteps | 39321600 | +| train/ | | +| approx_kl | 0.014666444 | +| clip_fraction | 0.345 | +| clip_range | 0.0652 | +| entropy_loss | -5.64 | +| explained_variance | 0.454 | +| learning_rate | 4.07e-05 | +| loss | -0.0287 | +| n_updates | 92616 | +| policy_gradient_loss | -0.0186 | +| value_loss | 9.28e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1387 | +| iterations | 19201 | +| time_elapsed | 28341 | +| total_timesteps | 39323648 | +| train/ | | +| approx_kl | 0.012396038 | +| clip_fraction | 0.327 | +| clip_range | 0.0652 | +| entropy_loss | -5.48 | +| explained_variance | 0.631 | +| learning_rate | 4.07e-05 | +| loss | -0.0267 | +| n_updates | 92620 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000136 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1387 | +| iterations | 19202 | +| time_elapsed | 28343 | +| total_timesteps | 39325696 | +| train/ | | +| approx_kl | 0.014250206 | +| clip_fraction | 0.332 | +| clip_range | 0.0652 | +| entropy_loss | -5.58 | +| explained_variance | -0.0423 | +| learning_rate | 4.07e-05 | +| loss | -0.0241 | +| n_updates | 92624 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000115 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1387 | +| iterations | 19203 | +| time_elapsed | 28344 | +| total_timesteps | 39327744 | +| train/ | | +| approx_kl | 0.010436207 | +| clip_fraction | 0.329 | +| clip_range | 0.0652 | +| entropy_loss | -6.41 | +| explained_variance | 0.301 | +| learning_rate | 4.07e-05 | +| loss | -0.0275 | +| n_updates | 92628 | +| policy_gradient_loss | -0.0131 | +| value_loss | 0.000266 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1387 | +| iterations | 19204 | +| time_elapsed | 28346 | +| total_timesteps | 39329792 | +| train/ | | +| approx_kl | 0.01699472 | +| clip_fraction | 0.32 | +| clip_range | 0.0652 | +| entropy_loss | -5.71 | +| explained_variance | 0.367 | +| learning_rate | 4.07e-05 | +| loss | -0.0265 | +| n_updates | 92632 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.00024 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1387 | +| iterations | 19205 | +| time_elapsed | 28348 | +| total_timesteps | 39331840 | +| train/ | | +| approx_kl | 0.011575609 | +| clip_fraction | 0.333 | +| clip_range | 0.0652 | +| entropy_loss | -5.42 | +| explained_variance | 0.611 | +| learning_rate | 4.07e-05 | +| loss | -0.0271 | +| n_updates | 92636 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1387 | +| iterations | 19206 | +| time_elapsed | 28349 | +| total_timesteps | 39333888 | +| train/ | | +| approx_kl | 0.012810765 | +| clip_fraction | 0.355 | +| clip_range | 0.0652 | +| entropy_loss | -5.68 | +| explained_variance | 0.412 | +| learning_rate | 4.07e-05 | +| loss | -0.0361 | +| n_updates | 92640 | +| policy_gradient_loss | -0.0192 | +| value_loss | 9.25e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1387 | +| iterations | 19207 | +| time_elapsed | 28351 | +| total_timesteps | 39335936 | +| train/ | | +| approx_kl | 0.013283543 | +| clip_fraction | 0.341 | +| clip_range | 0.0652 | +| entropy_loss | -5.78 | +| explained_variance | 0.342 | +| learning_rate | 4.07e-05 | +| loss | -0.0275 | +| n_updates | 92644 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000154 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1387 | +| iterations | 19208 | +| time_elapsed | 28352 | +| total_timesteps | 39337984 | +| train/ | | +| approx_kl | 0.0140587045 | +| clip_fraction | 0.321 | +| clip_range | 0.0652 | +| entropy_loss | -5.64 | +| explained_variance | 0.413 | +| learning_rate | 4.07e-05 | +| loss | -0.0276 | +| n_updates | 92648 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000114 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1387 | +| iterations | 19209 | +| time_elapsed | 28354 | +| total_timesteps | 39340032 | +| train/ | | +| approx_kl | 0.0130956825 | +| clip_fraction | 0.345 | +| clip_range | 0.0652 | +| entropy_loss | -5.58 | +| explained_variance | 0.409 | +| learning_rate | 4.07e-05 | +| loss | -0.0198 | +| n_updates | 92652 | +| policy_gradient_loss | -0.0163 | +| value_loss | 9.9e-05 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1387 | +| iterations | 19210 | +| time_elapsed | 28355 | +| total_timesteps | 39342080 | +| train/ | | +| approx_kl | 0.01843011 | +| clip_fraction | 0.35 | +| clip_range | 0.0652 | +| entropy_loss | -5.78 | +| explained_variance | -0.0574 | +| learning_rate | 4.07e-05 | +| loss | -0.0296 | +| n_updates | 92656 | +| policy_gradient_loss | -0.0175 | +| value_loss | 9.05e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1387 | +| iterations | 19211 | +| time_elapsed | 28357 | +| total_timesteps | 39344128 | +| train/ | | +| approx_kl | 0.017061729 | +| clip_fraction | 0.36 | +| clip_range | 0.0652 | +| entropy_loss | -5.76 | +| explained_variance | 0.737 | +| learning_rate | 4.07e-05 | +| loss | -0.0317 | +| n_updates | 92660 | +| policy_gradient_loss | -0.019 | +| value_loss | 5.87e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1387 | +| iterations | 19212 | +| time_elapsed | 28358 | +| total_timesteps | 39346176 | +| train/ | | +| approx_kl | 0.011367502 | +| clip_fraction | 0.317 | +| clip_range | 0.0652 | +| entropy_loss | -5.63 | +| explained_variance | 0.204 | +| learning_rate | 4.07e-05 | +| loss | -0.0249 | +| n_updates | 92664 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000152 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1387 | +| iterations | 19213 | +| time_elapsed | 28360 | +| total_timesteps | 39348224 | +| train/ | | +| approx_kl | 0.010413334 | +| clip_fraction | 0.302 | +| clip_range | 0.0652 | +| entropy_loss | -5.84 | +| explained_variance | 0.497 | +| learning_rate | 4.07e-05 | +| loss | -0.0214 | +| n_updates | 92668 | +| policy_gradient_loss | -0.0141 | +| value_loss | 0.000214 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1387 | +| iterations | 19214 | +| time_elapsed | 28362 | +| total_timesteps | 39350272 | +| train/ | | +| approx_kl | 0.012072837 | +| clip_fraction | 0.356 | +| clip_range | 0.0652 | +| entropy_loss | -6 | +| explained_variance | 0.396 | +| learning_rate | 4.07e-05 | +| loss | -0.0307 | +| n_updates | 92672 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000119 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1387 | +| iterations | 19215 | +| time_elapsed | 28363 | +| total_timesteps | 39352320 | +| train/ | | +| approx_kl | 0.009707079 | +| clip_fraction | 0.298 | +| clip_range | 0.0652 | +| entropy_loss | -5.66 | +| explained_variance | 0.606 | +| learning_rate | 4.07e-05 | +| loss | -0.021 | +| n_updates | 92676 | +| policy_gradient_loss | -0.0131 | +| value_loss | 0.000216 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1387 | +| iterations | 19216 | +| time_elapsed | 28365 | +| total_timesteps | 39354368 | +| train/ | | +| approx_kl | 0.012668128 | +| clip_fraction | 0.311 | +| clip_range | 0.0652 | +| entropy_loss | -5.2 | +| explained_variance | 0.442 | +| learning_rate | 4.07e-05 | +| loss | -0.0213 | +| n_updates | 92680 | +| policy_gradient_loss | -0.0139 | +| value_loss | 0.000172 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1387 | +| iterations | 19217 | +| time_elapsed | 28366 | +| total_timesteps | 39356416 | +| train/ | | +| approx_kl | 0.016028255 | +| clip_fraction | 0.33 | +| clip_range | 0.0652 | +| entropy_loss | -5.59 | +| explained_variance | 0.056 | +| learning_rate | 4.07e-05 | +| loss | -0.025 | +| n_updates | 92684 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.0002 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1387 | +| iterations | 19218 | +| time_elapsed | 28368 | +| total_timesteps | 39358464 | +| train/ | | +| approx_kl | 0.011498541 | +| clip_fraction | 0.336 | +| clip_range | 0.0652 | +| entropy_loss | -5.76 | +| explained_variance | 0.311 | +| learning_rate | 4.07e-05 | +| loss | -0.0252 | +| n_updates | 92688 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.000275 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1387 | +| iterations | 19219 | +| time_elapsed | 28369 | +| total_timesteps | 39360512 | +| train/ | | +| approx_kl | 0.013651718 | +| clip_fraction | 0.316 | +| clip_range | 0.0652 | +| entropy_loss | -5.65 | +| explained_variance | 0.313 | +| learning_rate | 4.07e-05 | +| loss | -0.0334 | +| n_updates | 92692 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000126 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1387 | +| iterations | 19220 | +| time_elapsed | 28371 | +| total_timesteps | 39362560 | +| train/ | | +| approx_kl | 0.010874936 | +| clip_fraction | 0.32 | +| clip_range | 0.0652 | +| entropy_loss | -6.35 | +| explained_variance | 0.563 | +| learning_rate | 4.07e-05 | +| loss | -0.0211 | +| n_updates | 92696 | +| policy_gradient_loss | -0.0159 | +| value_loss | 6.54e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1387 | +| iterations | 19221 | +| time_elapsed | 28372 | +| total_timesteps | 39364608 | +| train/ | | +| approx_kl | 0.010144239 | +| clip_fraction | 0.318 | +| clip_range | 0.0652 | +| entropy_loss | -6.2 | +| explained_variance | 0.356 | +| learning_rate | 4.07e-05 | +| loss | -0.0235 | +| n_updates | 92700 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000139 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1387 | +| iterations | 19222 | +| time_elapsed | 28374 | +| total_timesteps | 39366656 | +| train/ | | +| approx_kl | 0.011170374 | +| clip_fraction | 0.284 | +| clip_range | 0.0652 | +| entropy_loss | -5.71 | +| explained_variance | 0.46 | +| learning_rate | 4.07e-05 | +| loss | -0.0223 | +| n_updates | 92704 | +| policy_gradient_loss | -0.0123 | +| value_loss | 0.000269 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1387 | +| iterations | 19223 | +| time_elapsed | 28375 | +| total_timesteps | 39368704 | +| train/ | | +| approx_kl | 0.013709502 | +| clip_fraction | 0.342 | +| clip_range | 0.0652 | +| entropy_loss | -5.39 | +| explained_variance | 0.483 | +| learning_rate | 4.07e-05 | +| loss | -0.027 | +| n_updates | 92708 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000148 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1387 | +| iterations | 19224 | +| time_elapsed | 28377 | +| total_timesteps | 39370752 | +| train/ | | +| approx_kl | 0.015482188 | +| clip_fraction | 0.329 | +| clip_range | 0.0652 | +| entropy_loss | -5.54 | +| explained_variance | 0.351 | +| learning_rate | 4.06e-05 | +| loss | -0.0313 | +| n_updates | 92712 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000158 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1387 | +| iterations | 19225 | +| time_elapsed | 28378 | +| total_timesteps | 39372800 | +| train/ | | +| approx_kl | 0.015050687 | +| clip_fraction | 0.36 | +| clip_range | 0.0652 | +| entropy_loss | -6.23 | +| explained_variance | 0.363 | +| learning_rate | 4.06e-05 | +| loss | -0.0313 | +| n_updates | 92716 | +| policy_gradient_loss | -0.021 | +| value_loss | 5.28e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1387 | +| iterations | 19226 | +| time_elapsed | 28380 | +| total_timesteps | 39374848 | +| train/ | | +| approx_kl | 0.012606222 | +| clip_fraction | 0.319 | +| clip_range | 0.0652 | +| entropy_loss | -6.41 | +| explained_variance | 0.253 | +| learning_rate | 4.06e-05 | +| loss | -0.0212 | +| n_updates | 92720 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000186 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1387 | +| iterations | 19227 | +| time_elapsed | 28381 | +| total_timesteps | 39376896 | +| train/ | | +| approx_kl | 0.010163806 | +| clip_fraction | 0.303 | +| clip_range | 0.0652 | +| entropy_loss | -6.25 | +| explained_variance | 0.385 | +| learning_rate | 4.06e-05 | +| loss | -0.0248 | +| n_updates | 92724 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000148 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1387 | +| iterations | 19228 | +| time_elapsed | 28383 | +| total_timesteps | 39378944 | +| train/ | | +| approx_kl | 0.009360061 | +| clip_fraction | 0.278 | +| clip_range | 0.0652 | +| entropy_loss | -5.14 | +| explained_variance | 0.542 | +| learning_rate | 4.06e-05 | +| loss | -0.0217 | +| n_updates | 92728 | +| policy_gradient_loss | -0.0118 | +| value_loss | 0.000263 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1387 | +| iterations | 19229 | +| time_elapsed | 28384 | +| total_timesteps | 39380992 | +| train/ | | +| approx_kl | 0.015670234 | +| clip_fraction | 0.355 | +| clip_range | 0.0652 | +| entropy_loss | -4.75 | +| explained_variance | 0.665 | +| learning_rate | 4.06e-05 | +| loss | -0.0302 | +| n_updates | 92732 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000101 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1387 | +| iterations | 19230 | +| time_elapsed | 28386 | +| total_timesteps | 39383040 | +| train/ | | +| approx_kl | 0.016848383 | +| clip_fraction | 0.343 | +| clip_range | 0.0652 | +| entropy_loss | -5.84 | +| explained_variance | 0.28 | +| learning_rate | 4.06e-05 | +| loss | -0.0317 | +| n_updates | 92736 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000174 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1387 | +| iterations | 19231 | +| time_elapsed | 28388 | +| total_timesteps | 39385088 | +| train/ | | +| approx_kl | 0.015181936 | +| clip_fraction | 0.345 | +| clip_range | 0.0652 | +| entropy_loss | -6.08 | +| explained_variance | -0.216 | +| learning_rate | 4.06e-05 | +| loss | -0.03 | +| n_updates | 92740 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000107 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1387 | +| iterations | 19232 | +| time_elapsed | 28389 | +| total_timesteps | 39387136 | +| train/ | | +| approx_kl | 0.01249871 | +| clip_fraction | 0.306 | +| clip_range | 0.0652 | +| entropy_loss | -6.09 | +| explained_variance | 0.279 | +| learning_rate | 4.06e-05 | +| loss | -0.0249 | +| n_updates | 92744 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.000152 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1387 | +| iterations | 19233 | +| time_elapsed | 28391 | +| total_timesteps | 39389184 | +| train/ | | +| approx_kl | 0.012695734 | +| clip_fraction | 0.327 | +| clip_range | 0.0652 | +| entropy_loss | -5.23 | +| explained_variance | 0.512 | +| learning_rate | 4.06e-05 | +| loss | -0.0273 | +| n_updates | 92748 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000192 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1387 | +| iterations | 19234 | +| time_elapsed | 28392 | +| total_timesteps | 39391232 | +| train/ | | +| approx_kl | 0.013137776 | +| clip_fraction | 0.349 | +| clip_range | 0.0652 | +| entropy_loss | -5.59 | +| explained_variance | 0.463 | +| learning_rate | 4.06e-05 | +| loss | -0.0275 | +| n_updates | 92752 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000101 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1387 | +| iterations | 19235 | +| time_elapsed | 28394 | +| total_timesteps | 39393280 | +| train/ | | +| approx_kl | 0.017836772 | +| clip_fraction | 0.334 | +| clip_range | 0.0652 | +| entropy_loss | -6.16 | +| explained_variance | 0.394 | +| learning_rate | 4.06e-05 | +| loss | -0.0264 | +| n_updates | 92756 | +| policy_gradient_loss | -0.0168 | +| value_loss | 9.97e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1387 | +| iterations | 19236 | +| time_elapsed | 28395 | +| total_timesteps | 39395328 | +| train/ | | +| approx_kl | 0.011913113 | +| clip_fraction | 0.315 | +| clip_range | 0.0652 | +| entropy_loss | -6.01 | +| explained_variance | 0.414 | +| learning_rate | 4.06e-05 | +| loss | -0.0235 | +| n_updates | 92760 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000325 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1387 | +| iterations | 19237 | +| time_elapsed | 28397 | +| total_timesteps | 39397376 | +| train/ | | +| approx_kl | 0.0148113305 | +| clip_fraction | 0.308 | +| clip_range | 0.0652 | +| entropy_loss | -5.64 | +| explained_variance | 0.429 | +| learning_rate | 4.06e-05 | +| loss | -0.0252 | +| n_updates | 92764 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000173 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1387 | +| iterations | 19238 | +| time_elapsed | 28398 | +| total_timesteps | 39399424 | +| train/ | | +| approx_kl | 0.0139754135 | +| clip_fraction | 0.361 | +| clip_range | 0.0652 | +| entropy_loss | -5.51 | +| explained_variance | 0.412 | +| learning_rate | 4.06e-05 | +| loss | -0.0324 | +| n_updates | 92768 | +| policy_gradient_loss | -0.0194 | +| value_loss | 8.45e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1387 | +| iterations | 19239 | +| time_elapsed | 28400 | +| total_timesteps | 39401472 | +| train/ | | +| approx_kl | 0.013136567 | +| clip_fraction | 0.34 | +| clip_range | 0.0652 | +| entropy_loss | -6.2 | +| explained_variance | 0.00562 | +| learning_rate | 4.06e-05 | +| loss | -0.031 | +| n_updates | 92772 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000169 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1387 | +| iterations | 19240 | +| time_elapsed | 28401 | +| total_timesteps | 39403520 | +| train/ | | +| approx_kl | 0.013933593 | +| clip_fraction | 0.337 | +| clip_range | 0.0651 | +| entropy_loss | -5.94 | +| explained_variance | 0.547 | +| learning_rate | 4.06e-05 | +| loss | -0.03 | +| n_updates | 92776 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000126 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1387 | +| iterations | 19241 | +| time_elapsed | 28403 | +| total_timesteps | 39405568 | +| train/ | | +| approx_kl | 0.012968777 | +| clip_fraction | 0.324 | +| clip_range | 0.0651 | +| entropy_loss | -5.94 | +| explained_variance | 0.46 | +| learning_rate | 4.06e-05 | +| loss | -0.025 | +| n_updates | 92780 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000173 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1387 | +| iterations | 19242 | +| time_elapsed | 28404 | +| total_timesteps | 39407616 | +| train/ | | +| approx_kl | 0.012801589 | +| clip_fraction | 0.3 | +| clip_range | 0.0651 | +| entropy_loss | -5.6 | +| explained_variance | 0.297 | +| learning_rate | 4.06e-05 | +| loss | -0.0249 | +| n_updates | 92784 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000197 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1387 | +| iterations | 19243 | +| time_elapsed | 28406 | +| total_timesteps | 39409664 | +| train/ | | +| approx_kl | 0.0135780815 | +| clip_fraction | 0.337 | +| clip_range | 0.0651 | +| entropy_loss | -5.89 | +| explained_variance | 0.69 | +| learning_rate | 4.06e-05 | +| loss | -0.0332 | +| n_updates | 92788 | +| policy_gradient_loss | -0.0195 | +| value_loss | 7.24e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1387 | +| iterations | 19244 | +| time_elapsed | 28407 | +| total_timesteps | 39411712 | +| train/ | | +| approx_kl | 0.018989056 | +| clip_fraction | 0.328 | +| clip_range | 0.0651 | +| entropy_loss | -5.64 | +| explained_variance | 0.63 | +| learning_rate | 4.06e-05 | +| loss | -0.0257 | +| n_updates | 92792 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000124 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1387 | +| iterations | 19245 | +| time_elapsed | 28409 | +| total_timesteps | 39413760 | +| train/ | | +| approx_kl | 0.012807558 | +| clip_fraction | 0.302 | +| clip_range | 0.0651 | +| entropy_loss | -5.67 | +| explained_variance | 0.461 | +| learning_rate | 4.06e-05 | +| loss | -0.0225 | +| n_updates | 92796 | +| policy_gradient_loss | -0.0146 | +| value_loss | 0.000155 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1387 | +| iterations | 19246 | +| time_elapsed | 28410 | +| total_timesteps | 39415808 | +| train/ | | +| approx_kl | 0.016449448 | +| clip_fraction | 0.354 | +| clip_range | 0.0651 | +| entropy_loss | -6.26 | +| explained_variance | -0.186 | +| learning_rate | 4.06e-05 | +| loss | -0.0292 | +| n_updates | 92800 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000104 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1387 | +| iterations | 19247 | +| time_elapsed | 28412 | +| total_timesteps | 39417856 | +| train/ | | +| approx_kl | 0.0127756335 | +| clip_fraction | 0.334 | +| clip_range | 0.0651 | +| entropy_loss | -6.12 | +| explained_variance | 0.37 | +| learning_rate | 4.06e-05 | +| loss | -0.0259 | +| n_updates | 92804 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000224 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1387 | +| iterations | 19248 | +| time_elapsed | 28414 | +| total_timesteps | 39419904 | +| train/ | | +| approx_kl | 0.019638803 | +| clip_fraction | 0.319 | +| clip_range | 0.0651 | +| entropy_loss | -6.54 | +| explained_variance | -0.307 | +| learning_rate | 4.06e-05 | +| loss | -0.0325 | +| n_updates | 92808 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000114 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1387 | +| iterations | 19249 | +| time_elapsed | 28415 | +| total_timesteps | 39421952 | +| train/ | | +| approx_kl | 0.009716642 | +| clip_fraction | 0.266 | +| clip_range | 0.0651 | +| entropy_loss | -6.31 | +| explained_variance | 0.22 | +| learning_rate | 4.06e-05 | +| loss | -0.022 | +| n_updates | 92812 | +| policy_gradient_loss | -0.0116 | +| value_loss | 0.000285 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1387 | +| iterations | 19250 | +| time_elapsed | 28417 | +| total_timesteps | 39424000 | +| train/ | | +| approx_kl | 0.016931172 | +| clip_fraction | 0.341 | +| clip_range | 0.0651 | +| entropy_loss | -6.02 | +| explained_variance | 0.275 | +| learning_rate | 4.06e-05 | +| loss | -0.0248 | +| n_updates | 92816 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.00012 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1387 | +| iterations | 19251 | +| time_elapsed | 28418 | +| total_timesteps | 39426048 | +| train/ | | +| approx_kl | 0.015630499 | +| clip_fraction | 0.334 | +| clip_range | 0.0651 | +| entropy_loss | -5.94 | +| explained_variance | 0.38 | +| learning_rate | 4.06e-05 | +| loss | -0.0247 | +| n_updates | 92820 | +| policy_gradient_loss | -0.0148 | +| value_loss | 0.000195 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1387 | +| iterations | 19252 | +| time_elapsed | 28420 | +| total_timesteps | 39428096 | +| train/ | | +| approx_kl | 0.015878756 | +| clip_fraction | 0.355 | +| clip_range | 0.0651 | +| entropy_loss | -5.8 | +| explained_variance | 0.268 | +| learning_rate | 4.06e-05 | +| loss | -0.0309 | +| n_updates | 92824 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000139 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1387 | +| iterations | 19253 | +| time_elapsed | 28421 | +| total_timesteps | 39430144 | +| train/ | | +| approx_kl | 0.013242459 | +| clip_fraction | 0.346 | +| clip_range | 0.0651 | +| entropy_loss | -5.76 | +| explained_variance | 0.482 | +| learning_rate | 4.06e-05 | +| loss | -0.0252 | +| n_updates | 92828 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.00021 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1387 | +| iterations | 19254 | +| time_elapsed | 28423 | +| total_timesteps | 39432192 | +| train/ | | +| approx_kl | 0.014425382 | +| clip_fraction | 0.368 | +| clip_range | 0.0651 | +| entropy_loss | -5.73 | +| explained_variance | 0.365 | +| learning_rate | 4.06e-05 | +| loss | -0.0276 | +| n_updates | 92832 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000122 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1387 | +| iterations | 19255 | +| time_elapsed | 28424 | +| total_timesteps | 39434240 | +| train/ | | +| approx_kl | 0.011044227 | +| clip_fraction | 0.338 | +| clip_range | 0.0651 | +| entropy_loss | -5.48 | +| explained_variance | 0.573 | +| learning_rate | 4.06e-05 | +| loss | -0.0221 | +| n_updates | 92836 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000143 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1387 | +| iterations | 19256 | +| time_elapsed | 28426 | +| total_timesteps | 39436288 | +| train/ | | +| approx_kl | 0.010658678 | +| clip_fraction | 0.327 | +| clip_range | 0.0651 | +| entropy_loss | -5.71 | +| explained_variance | 0.683 | +| learning_rate | 4.06e-05 | +| loss | -0.028 | +| n_updates | 92840 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000111 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1387 | +| iterations | 19257 | +| time_elapsed | 28427 | +| total_timesteps | 39438336 | +| train/ | | +| approx_kl | 0.011829313 | +| clip_fraction | 0.351 | +| clip_range | 0.0651 | +| entropy_loss | -5.48 | +| explained_variance | 0.511 | +| learning_rate | 4.06e-05 | +| loss | -0.0321 | +| n_updates | 92844 | +| policy_gradient_loss | -0.0168 | +| value_loss | 9.22e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1387 | +| iterations | 19258 | +| time_elapsed | 28429 | +| total_timesteps | 39440384 | +| train/ | | +| approx_kl | 0.012374615 | +| clip_fraction | 0.326 | +| clip_range | 0.0651 | +| entropy_loss | -5.79 | +| explained_variance | 0.335 | +| learning_rate | 4.06e-05 | +| loss | -0.0244 | +| n_updates | 92848 | +| policy_gradient_loss | -0.0146 | +| value_loss | 0.000163 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1387 | +| iterations | 19259 | +| time_elapsed | 28430 | +| total_timesteps | 39442432 | +| train/ | | +| approx_kl | 0.011855181 | +| clip_fraction | 0.32 | +| clip_range | 0.0651 | +| entropy_loss | -5.84 | +| explained_variance | 0.448 | +| learning_rate | 4.06e-05 | +| loss | -0.0266 | +| n_updates | 92852 | +| policy_gradient_loss | -0.0146 | +| value_loss | 0.000186 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1387 | +| iterations | 19260 | +| time_elapsed | 28432 | +| total_timesteps | 39444480 | +| train/ | | +| approx_kl | 0.013600634 | +| clip_fraction | 0.307 | +| clip_range | 0.0651 | +| entropy_loss | -5.71 | +| explained_variance | 0.275 | +| learning_rate | 4.06e-05 | +| loss | -0.023 | +| n_updates | 92856 | +| policy_gradient_loss | -0.0144 | +| value_loss | 0.000302 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1387 | +| iterations | 19261 | +| time_elapsed | 28433 | +| total_timesteps | 39446528 | +| train/ | | +| approx_kl | 0.015958788 | +| clip_fraction | 0.374 | +| clip_range | 0.0651 | +| entropy_loss | -5.51 | +| explained_variance | 0.604 | +| learning_rate | 4.06e-05 | +| loss | -0.0339 | +| n_updates | 92860 | +| policy_gradient_loss | -0.0213 | +| value_loss | 8.4e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1387 | +| iterations | 19262 | +| time_elapsed | 28435 | +| total_timesteps | 39448576 | +| train/ | | +| approx_kl | 0.013404012 | +| clip_fraction | 0.344 | +| clip_range | 0.0651 | +| entropy_loss | -5.83 | +| explained_variance | 0.66 | +| learning_rate | 4.06e-05 | +| loss | -0.0343 | +| n_updates | 92864 | +| policy_gradient_loss | -0.0188 | +| value_loss | 6.3e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1387 | +| iterations | 19263 | +| time_elapsed | 28437 | +| total_timesteps | 39450624 | +| train/ | | +| approx_kl | 0.014800122 | +| clip_fraction | 0.318 | +| clip_range | 0.0651 | +| entropy_loss | -6.02 | +| explained_variance | 0.285 | +| learning_rate | 4.06e-05 | +| loss | -0.03 | +| n_updates | 92868 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000299 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1387 | +| iterations | 19264 | +| time_elapsed | 28438 | +| total_timesteps | 39452672 | +| train/ | | +| approx_kl | 0.016533263 | +| clip_fraction | 0.325 | +| clip_range | 0.0651 | +| entropy_loss | -5.59 | +| explained_variance | 0.311 | +| learning_rate | 4.06e-05 | +| loss | -0.0235 | +| n_updates | 92872 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000133 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1387 | +| iterations | 19265 | +| time_elapsed | 28440 | +| total_timesteps | 39454720 | +| train/ | | +| approx_kl | 0.020356026 | +| clip_fraction | 0.366 | +| clip_range | 0.0651 | +| entropy_loss | -5.35 | +| explained_variance | -0.0461 | +| learning_rate | 4.06e-05 | +| loss | -0.024 | +| n_updates | 92876 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000197 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1387 | +| iterations | 19266 | +| time_elapsed | 28441 | +| total_timesteps | 39456768 | +| train/ | | +| approx_kl | 0.016148869 | +| clip_fraction | 0.395 | +| clip_range | 0.0651 | +| entropy_loss | -5.41 | +| explained_variance | 0.746 | +| learning_rate | 4.06e-05 | +| loss | -0.0382 | +| n_updates | 92880 | +| policy_gradient_loss | -0.0213 | +| value_loss | 6.54e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1387 | +| iterations | 19267 | +| time_elapsed | 28443 | +| total_timesteps | 39458816 | +| train/ | | +| approx_kl | 0.0136915175 | +| clip_fraction | 0.332 | +| clip_range | 0.0651 | +| entropy_loss | -5.12 | +| explained_variance | 0.532 | +| learning_rate | 4.06e-05 | +| loss | -0.0256 | +| n_updates | 92884 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000234 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1387 | +| iterations | 19268 | +| time_elapsed | 28444 | +| total_timesteps | 39460864 | +| train/ | | +| approx_kl | 0.013179962 | +| clip_fraction | 0.368 | +| clip_range | 0.0651 | +| entropy_loss | -5.32 | +| explained_variance | 0.514 | +| learning_rate | 4.06e-05 | +| loss | -0.0232 | +| n_updates | 92888 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000123 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1387 | +| iterations | 19269 | +| time_elapsed | 28446 | +| total_timesteps | 39462912 | +| train/ | | +| approx_kl | 0.015044166 | +| clip_fraction | 0.376 | +| clip_range | 0.0651 | +| entropy_loss | -6.14 | +| explained_variance | 0.0637 | +| learning_rate | 4.06e-05 | +| loss | -0.0306 | +| n_updates | 92892 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000139 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1387 | +| iterations | 19270 | +| time_elapsed | 28447 | +| total_timesteps | 39464960 | +| train/ | | +| approx_kl | 0.012896437 | +| clip_fraction | 0.367 | +| clip_range | 0.0651 | +| entropy_loss | -5.92 | +| explained_variance | 0.539 | +| learning_rate | 4.06e-05 | +| loss | -0.0241 | +| n_updates | 92896 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000109 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1387 | +| iterations | 19271 | +| time_elapsed | 28449 | +| total_timesteps | 39467008 | +| train/ | | +| approx_kl | 0.010880811 | +| clip_fraction | 0.327 | +| clip_range | 0.0651 | +| entropy_loss | -5.78 | +| explained_variance | 0.0192 | +| learning_rate | 4.06e-05 | +| loss | -0.0243 | +| n_updates | 92900 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000163 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1387 | +| iterations | 19272 | +| time_elapsed | 28450 | +| total_timesteps | 39469056 | +| train/ | | +| approx_kl | 0.011742054 | +| clip_fraction | 0.292 | +| clip_range | 0.0651 | +| entropy_loss | -5.12 | +| explained_variance | 0.675 | +| learning_rate | 4.06e-05 | +| loss | -0.0217 | +| n_updates | 92904 | +| policy_gradient_loss | -0.0147 | +| value_loss | 0.000139 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1387 | +| iterations | 19273 | +| time_elapsed | 28452 | +| total_timesteps | 39471104 | +| train/ | | +| approx_kl | 0.014381763 | +| clip_fraction | 0.334 | +| clip_range | 0.0651 | +| entropy_loss | -5.68 | +| explained_variance | 0.0267 | +| learning_rate | 4.06e-05 | +| loss | -0.0326 | +| n_updates | 92908 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000121 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1387 | +| iterations | 19274 | +| time_elapsed | 28453 | +| total_timesteps | 39473152 | +| train/ | | +| approx_kl | 0.01409671 | +| clip_fraction | 0.339 | +| clip_range | 0.0651 | +| entropy_loss | -5.51 | +| explained_variance | 0.483 | +| learning_rate | 4.06e-05 | +| loss | -0.0213 | +| n_updates | 92912 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.00025 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1387 | +| iterations | 19275 | +| time_elapsed | 28455 | +| total_timesteps | 39475200 | +| train/ | | +| approx_kl | 0.014995009 | +| clip_fraction | 0.348 | +| clip_range | 0.0651 | +| entropy_loss | -5.74 | +| explained_variance | 0.208 | +| learning_rate | 4.06e-05 | +| loss | -0.0335 | +| n_updates | 92916 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.00019 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1387 | +| iterations | 19276 | +| time_elapsed | 28457 | +| total_timesteps | 39477248 | +| train/ | | +| approx_kl | 0.015155158 | +| clip_fraction | 0.366 | +| clip_range | 0.0651 | +| entropy_loss | -5.64 | +| explained_variance | 0.106 | +| learning_rate | 4.06e-05 | +| loss | -0.0279 | +| n_updates | 92920 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000143 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1387 | +| iterations | 19277 | +| time_elapsed | 28458 | +| total_timesteps | 39479296 | +| train/ | | +| approx_kl | 0.011665683 | +| clip_fraction | 0.343 | +| clip_range | 0.0651 | +| entropy_loss | -5.68 | +| explained_variance | 0.42 | +| learning_rate | 4.06e-05 | +| loss | -0.0278 | +| n_updates | 92924 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000105 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1387 | +| iterations | 19278 | +| time_elapsed | 28460 | +| total_timesteps | 39481344 | +| train/ | | +| approx_kl | 0.014795517 | +| clip_fraction | 0.353 | +| clip_range | 0.0651 | +| entropy_loss | -6.08 | +| explained_variance | 0.634 | +| learning_rate | 4.06e-05 | +| loss | -0.0293 | +| n_updates | 92928 | +| policy_gradient_loss | -0.0194 | +| value_loss | 5.08e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1387 | +| iterations | 19279 | +| time_elapsed | 28461 | +| total_timesteps | 39483392 | +| train/ | | +| approx_kl | 0.012921863 | +| clip_fraction | 0.272 | +| clip_range | 0.0651 | +| entropy_loss | -5.08 | +| explained_variance | 0.576 | +| learning_rate | 4.06e-05 | +| loss | -0.022 | +| n_updates | 92932 | +| policy_gradient_loss | -0.0127 | +| value_loss | 0.000219 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1387 | +| iterations | 19280 | +| time_elapsed | 28463 | +| total_timesteps | 39485440 | +| train/ | | +| approx_kl | 0.013516368 | +| clip_fraction | 0.312 | +| clip_range | 0.0651 | +| entropy_loss | -5.21 | +| explained_variance | 0.42 | +| learning_rate | 4.06e-05 | +| loss | -0.0231 | +| n_updates | 92936 | +| policy_gradient_loss | -0.0148 | +| value_loss | 0.000155 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1387 | +| iterations | 19281 | +| time_elapsed | 28464 | +| total_timesteps | 39487488 | +| train/ | | +| approx_kl | 0.015633509 | +| clip_fraction | 0.375 | +| clip_range | 0.0651 | +| entropy_loss | -5.44 | +| explained_variance | 0.411 | +| learning_rate | 4.06e-05 | +| loss | -0.0345 | +| n_updates | 92940 | +| policy_gradient_loss | -0.0196 | +| value_loss | 9.27e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1387 | +| iterations | 19282 | +| time_elapsed | 28466 | +| total_timesteps | 39489536 | +| train/ | | +| approx_kl | 0.014405942 | +| clip_fraction | 0.361 | +| clip_range | 0.0651 | +| entropy_loss | -5.73 | +| explained_variance | 0.415 | +| learning_rate | 4.06e-05 | +| loss | -0.0259 | +| n_updates | 92944 | +| policy_gradient_loss | -0.018 | +| value_loss | 8.47e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1387 | +| iterations | 19283 | +| time_elapsed | 28467 | +| total_timesteps | 39491584 | +| train/ | | +| approx_kl | 0.010207493 | +| clip_fraction | 0.298 | +| clip_range | 0.0651 | +| entropy_loss | -5.91 | +| explained_variance | 0.142 | +| learning_rate | 4.06e-05 | +| loss | -0.021 | +| n_updates | 92948 | +| policy_gradient_loss | -0.0126 | +| value_loss | 0.000367 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1387 | +| iterations | 19284 | +| time_elapsed | 28469 | +| total_timesteps | 39493632 | +| train/ | | +| approx_kl | 0.01132334 | +| clip_fraction | 0.32 | +| clip_range | 0.0651 | +| entropy_loss | -5.53 | +| explained_variance | 0.511 | +| learning_rate | 4.06e-05 | +| loss | -0.0287 | +| n_updates | 92952 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000229 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1387 | +| iterations | 19285 | +| time_elapsed | 28470 | +| total_timesteps | 39495680 | +| train/ | | +| approx_kl | 0.01181564 | +| clip_fraction | 0.331 | +| clip_range | 0.0651 | +| entropy_loss | -5.33 | +| explained_variance | 0.475 | +| learning_rate | 4.06e-05 | +| loss | -0.0266 | +| n_updates | 92956 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000226 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1387 | +| iterations | 19286 | +| time_elapsed | 28472 | +| total_timesteps | 39497728 | +| train/ | | +| approx_kl | 0.013460215 | +| clip_fraction | 0.334 | +| clip_range | 0.0651 | +| entropy_loss | -5.85 | +| explained_variance | 0.00441 | +| learning_rate | 4.06e-05 | +| loss | -0.0319 | +| n_updates | 92960 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000142 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1387 | +| iterations | 19287 | +| time_elapsed | 28474 | +| total_timesteps | 39499776 | +| train/ | | +| approx_kl | 0.011786891 | +| clip_fraction | 0.358 | +| clip_range | 0.0651 | +| entropy_loss | -6.59 | +| explained_variance | -0.185 | +| learning_rate | 4.06e-05 | +| loss | -0.0269 | +| n_updates | 92964 | +| policy_gradient_loss | -0.0189 | +| value_loss | 8.06e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1387 | +| iterations | 19288 | +| time_elapsed | 28475 | +| total_timesteps | 39501824 | +| train/ | | +| approx_kl | 0.013608366 | +| clip_fraction | 0.318 | +| clip_range | 0.0651 | +| entropy_loss | -6.06 | +| explained_variance | 0.213 | +| learning_rate | 4.06e-05 | +| loss | -0.0287 | +| n_updates | 92968 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.000175 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1387 | +| iterations | 19289 | +| time_elapsed | 28477 | +| total_timesteps | 39503872 | +| train/ | | +| approx_kl | 0.011702785 | +| clip_fraction | 0.324 | +| clip_range | 0.0651 | +| entropy_loss | -5.38 | +| explained_variance | 0.494 | +| learning_rate | 4.06e-05 | +| loss | -0.0227 | +| n_updates | 92972 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000156 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1387 | +| iterations | 19290 | +| time_elapsed | 28478 | +| total_timesteps | 39505920 | +| train/ | | +| approx_kl | 0.014605093 | +| clip_fraction | 0.339 | +| clip_range | 0.0651 | +| entropy_loss | -5.81 | +| explained_variance | 0.00735 | +| learning_rate | 4.06e-05 | +| loss | -0.0266 | +| n_updates | 92976 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.00019 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1387 | +| iterations | 19291 | +| time_elapsed | 28480 | +| total_timesteps | 39507968 | +| train/ | | +| approx_kl | 0.013282304 | +| clip_fraction | 0.322 | +| clip_range | 0.0651 | +| entropy_loss | -6.21 | +| explained_variance | 0.247 | +| learning_rate | 4.06e-05 | +| loss | -0.0232 | +| n_updates | 92980 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000152 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1387 | +| iterations | 19292 | +| time_elapsed | 28481 | +| total_timesteps | 39510016 | +| train/ | | +| approx_kl | 0.010121653 | +| clip_fraction | 0.306 | +| clip_range | 0.0651 | +| entropy_loss | -6.28 | +| explained_variance | 0.198 | +| learning_rate | 4.06e-05 | +| loss | -0.0262 | +| n_updates | 92984 | +| policy_gradient_loss | -0.0148 | +| value_loss | 0.000226 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1387 | +| iterations | 19293 | +| time_elapsed | 28483 | +| total_timesteps | 39512064 | +| train/ | | +| approx_kl | 0.014539938 | +| clip_fraction | 0.335 | +| clip_range | 0.0651 | +| entropy_loss | -5.72 | +| explained_variance | 0.31 | +| learning_rate | 4.06e-05 | +| loss | -0.0264 | +| n_updates | 92988 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1387 | +| iterations | 19294 | +| time_elapsed | 28485 | +| total_timesteps | 39514112 | +| train/ | | +| approx_kl | 0.011973331 | +| clip_fraction | 0.312 | +| clip_range | 0.0651 | +| entropy_loss | -5.89 | +| explained_variance | 0.348 | +| learning_rate | 4.06e-05 | +| loss | -0.0204 | +| n_updates | 92992 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000206 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1387 | +| iterations | 19295 | +| time_elapsed | 28486 | +| total_timesteps | 39516160 | +| train/ | | +| approx_kl | 0.014548482 | +| clip_fraction | 0.321 | +| clip_range | 0.0651 | +| entropy_loss | -4.91 | +| explained_variance | 0.608 | +| learning_rate | 4.06e-05 | +| loss | -0.0285 | +| n_updates | 92996 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000141 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1387 | +| iterations | 19296 | +| time_elapsed | 28488 | +| total_timesteps | 39518208 | +| train/ | | +| approx_kl | 0.013840654 | +| clip_fraction | 0.352 | +| clip_range | 0.0651 | +| entropy_loss | -5.47 | +| explained_variance | 0.524 | +| learning_rate | 4.06e-05 | +| loss | -0.0309 | +| n_updates | 93000 | +| policy_gradient_loss | -0.0198 | +| value_loss | 6.24e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1387 | +| iterations | 19297 | +| time_elapsed | 28489 | +| total_timesteps | 39520256 | +| train/ | | +| approx_kl | 0.01586831 | +| clip_fraction | 0.328 | +| clip_range | 0.0651 | +| entropy_loss | -6.24 | +| explained_variance | 0.128 | +| learning_rate | 4.06e-05 | +| loss | -0.0322 | +| n_updates | 93004 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000131 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1387 | +| iterations | 19298 | +| time_elapsed | 28491 | +| total_timesteps | 39522304 | +| train/ | | +| approx_kl | 0.012705665 | +| clip_fraction | 0.307 | +| clip_range | 0.0651 | +| entropy_loss | -5.48 | +| explained_variance | 0.535 | +| learning_rate | 4.06e-05 | +| loss | -0.0245 | +| n_updates | 93008 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.00014 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1387 | +| iterations | 19299 | +| time_elapsed | 28492 | +| total_timesteps | 39524352 | +| train/ | | +| approx_kl | 0.012685709 | +| clip_fraction | 0.353 | +| clip_range | 0.0651 | +| entropy_loss | -5.49 | +| explained_variance | 0.377 | +| learning_rate | 4.06e-05 | +| loss | -0.0258 | +| n_updates | 93012 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000271 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1387 | +| iterations | 19300 | +| time_elapsed | 28494 | +| total_timesteps | 39526400 | +| train/ | | +| approx_kl | 0.01184679 | +| clip_fraction | 0.325 | +| clip_range | 0.0651 | +| entropy_loss | -5.78 | +| explained_variance | 0.0187 | +| learning_rate | 4.06e-05 | +| loss | -0.0251 | +| n_updates | 93016 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.00015 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1387 | +| iterations | 19301 | +| time_elapsed | 28495 | +| total_timesteps | 39528448 | +| train/ | | +| approx_kl | 0.012656406 | +| clip_fraction | 0.343 | +| clip_range | 0.0651 | +| entropy_loss | -6.06 | +| explained_variance | 0.247 | +| learning_rate | 4.06e-05 | +| loss | -0.0242 | +| n_updates | 93020 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000227 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1387 | +| iterations | 19302 | +| time_elapsed | 28497 | +| total_timesteps | 39530496 | +| train/ | | +| approx_kl | 0.009663634 | +| clip_fraction | 0.326 | +| clip_range | 0.0651 | +| entropy_loss | -6 | +| explained_variance | 0.0576 | +| learning_rate | 4.06e-05 | +| loss | -0.0267 | +| n_updates | 93024 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000271 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1387 | +| iterations | 19303 | +| time_elapsed | 28498 | +| total_timesteps | 39532544 | +| train/ | | +| approx_kl | 0.012596036 | +| clip_fraction | 0.303 | +| clip_range | 0.0651 | +| entropy_loss | -5.61 | +| explained_variance | 0.491 | +| learning_rate | 4.06e-05 | +| loss | -0.028 | +| n_updates | 93028 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.0002 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1387 | +| iterations | 19304 | +| time_elapsed | 28500 | +| total_timesteps | 39534592 | +| train/ | | +| approx_kl | 0.010508474 | +| clip_fraction | 0.311 | +| clip_range | 0.0651 | +| entropy_loss | -5.07 | +| explained_variance | 0.614 | +| learning_rate | 4.06e-05 | +| loss | -0.022 | +| n_updates | 93032 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000164 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1387 | +| iterations | 19305 | +| time_elapsed | 28502 | +| total_timesteps | 39536640 | +| train/ | | +| approx_kl | 0.012542031 | +| clip_fraction | 0.35 | +| clip_range | 0.0651 | +| entropy_loss | -5.11 | +| explained_variance | 0.637 | +| learning_rate | 4.06e-05 | +| loss | -0.0288 | +| n_updates | 93036 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000106 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1387 | +| iterations | 19306 | +| time_elapsed | 28503 | +| total_timesteps | 39538688 | +| train/ | | +| approx_kl | 0.012800511 | +| clip_fraction | 0.325 | +| clip_range | 0.0651 | +| entropy_loss | -5.58 | +| explained_variance | 0.574 | +| learning_rate | 4.06e-05 | +| loss | -0.0259 | +| n_updates | 93040 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000122 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1387 | +| iterations | 19307 | +| time_elapsed | 28505 | +| total_timesteps | 39540736 | +| train/ | | +| approx_kl | 0.01102937 | +| clip_fraction | 0.305 | +| clip_range | 0.0651 | +| entropy_loss | -5.83 | +| explained_variance | 0.551 | +| learning_rate | 4.06e-05 | +| loss | -0.0262 | +| n_updates | 93044 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000128 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1387 | +| iterations | 19308 | +| time_elapsed | 28506 | +| total_timesteps | 39542784 | +| train/ | | +| approx_kl | 0.012017893 | +| clip_fraction | 0.317 | +| clip_range | 0.0651 | +| entropy_loss | -5.53 | +| explained_variance | 0.539 | +| learning_rate | 4.06e-05 | +| loss | -0.0295 | +| n_updates | 93048 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000102 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1387 | +| iterations | 19309 | +| time_elapsed | 28508 | +| total_timesteps | 39544832 | +| train/ | | +| approx_kl | 0.011538669 | +| clip_fraction | 0.349 | +| clip_range | 0.0651 | +| entropy_loss | -5.99 | +| explained_variance | -0.0401 | +| learning_rate | 4.06e-05 | +| loss | -0.0308 | +| n_updates | 93052 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000173 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1387 | +| iterations | 19310 | +| time_elapsed | 28509 | +| total_timesteps | 39546880 | +| train/ | | +| approx_kl | 0.013789151 | +| clip_fraction | 0.313 | +| clip_range | 0.0651 | +| entropy_loss | -6.3 | +| explained_variance | 0.222 | +| learning_rate | 4.06e-05 | +| loss | -0.0243 | +| n_updates | 93056 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000149 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1387 | +| iterations | 19311 | +| time_elapsed | 28511 | +| total_timesteps | 39548928 | +| train/ | | +| approx_kl | 0.013815362 | +| clip_fraction | 0.37 | +| clip_range | 0.0651 | +| entropy_loss | -5.78 | +| explained_variance | 0.267 | +| learning_rate | 4.06e-05 | +| loss | -0.0257 | +| n_updates | 93060 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000157 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1387 | +| iterations | 19312 | +| time_elapsed | 28512 | +| total_timesteps | 39550976 | +| train/ | | +| approx_kl | 0.012649966 | +| clip_fraction | 0.328 | +| clip_range | 0.0651 | +| entropy_loss | -5.93 | +| explained_variance | 0.57 | +| learning_rate | 4.06e-05 | +| loss | -0.0322 | +| n_updates | 93064 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000141 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1387 | +| iterations | 19313 | +| time_elapsed | 28514 | +| total_timesteps | 39553024 | +| train/ | | +| approx_kl | 0.014016291 | +| clip_fraction | 0.337 | +| clip_range | 0.0651 | +| entropy_loss | -5.41 | +| explained_variance | 0.663 | +| learning_rate | 4.06e-05 | +| loss | -0.0279 | +| n_updates | 93068 | +| policy_gradient_loss | -0.0163 | +| value_loss | 7.37e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1387 | +| iterations | 19314 | +| time_elapsed | 28516 | +| total_timesteps | 39555072 | +| train/ | | +| approx_kl | 0.015098863 | +| clip_fraction | 0.337 | +| clip_range | 0.0651 | +| entropy_loss | -5.73 | +| explained_variance | 0.505 | +| learning_rate | 4.06e-05 | +| loss | -0.0297 | +| n_updates | 93072 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000102 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1387 | +| iterations | 19315 | +| time_elapsed | 28517 | +| total_timesteps | 39557120 | +| train/ | | +| approx_kl | 0.013767684 | +| clip_fraction | 0.335 | +| clip_range | 0.0651 | +| entropy_loss | -5.76 | +| explained_variance | -0.0829 | +| learning_rate | 4.06e-05 | +| loss | -0.0287 | +| n_updates | 93076 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000191 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1387 | +| iterations | 19316 | +| time_elapsed | 28519 | +| total_timesteps | 39559168 | +| train/ | | +| approx_kl | 0.0150806755 | +| clip_fraction | 0.351 | +| clip_range | 0.0651 | +| entropy_loss | -5.58 | +| explained_variance | 0.419 | +| learning_rate | 4.06e-05 | +| loss | -0.0255 | +| n_updates | 93080 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000187 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1387 | +| iterations | 19317 | +| time_elapsed | 28520 | +| total_timesteps | 39561216 | +| train/ | | +| approx_kl | 0.01061691 | +| clip_fraction | 0.32 | +| clip_range | 0.0651 | +| entropy_loss | -5.64 | +| explained_variance | 0.636 | +| learning_rate | 4.06e-05 | +| loss | -0.0292 | +| n_updates | 93084 | +| policy_gradient_loss | -0.0177 | +| value_loss | 8.66e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1387 | +| iterations | 19318 | +| time_elapsed | 28522 | +| total_timesteps | 39563264 | +| train/ | | +| approx_kl | 0.012112559 | +| clip_fraction | 0.31 | +| clip_range | 0.0651 | +| entropy_loss | -5.74 | +| explained_variance | 0.705 | +| learning_rate | 4.06e-05 | +| loss | -0.0221 | +| n_updates | 93088 | +| policy_gradient_loss | -0.0143 | +| value_loss | 0.000106 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1387 | +| iterations | 19319 | +| time_elapsed | 28523 | +| total_timesteps | 39565312 | +| train/ | | +| approx_kl | 0.010208257 | +| clip_fraction | 0.328 | +| clip_range | 0.0651 | +| entropy_loss | -6.08 | +| explained_variance | -0.0433 | +| learning_rate | 4.06e-05 | +| loss | -0.0268 | +| n_updates | 93092 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.00012 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1387 | +| iterations | 19320 | +| time_elapsed | 28525 | +| total_timesteps | 39567360 | +| train/ | | +| approx_kl | 0.0129609555 | +| clip_fraction | 0.328 | +| clip_range | 0.0651 | +| entropy_loss | -5.96 | +| explained_variance | 0.559 | +| learning_rate | 4.06e-05 | +| loss | -0.0296 | +| n_updates | 93096 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.00011 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1387 | +| iterations | 19321 | +| time_elapsed | 28526 | +| total_timesteps | 39569408 | +| train/ | | +| approx_kl | 0.011221118 | +| clip_fraction | 0.307 | +| clip_range | 0.0651 | +| entropy_loss | -5.16 | +| explained_variance | 0.594 | +| learning_rate | 4.06e-05 | +| loss | -0.03 | +| n_updates | 93100 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.000204 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1387 | +| iterations | 19322 | +| time_elapsed | 28528 | +| total_timesteps | 39571456 | +| train/ | | +| approx_kl | 0.011087496 | +| clip_fraction | 0.341 | +| clip_range | 0.0651 | +| entropy_loss | -5.27 | +| explained_variance | 0.505 | +| learning_rate | 4.06e-05 | +| loss | -0.0268 | +| n_updates | 93104 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000224 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1387 | +| iterations | 19323 | +| time_elapsed | 28529 | +| total_timesteps | 39573504 | +| train/ | | +| approx_kl | 0.015315683 | +| clip_fraction | 0.356 | +| clip_range | 0.0651 | +| entropy_loss | -4.91 | +| explained_variance | 0.393 | +| learning_rate | 4.06e-05 | +| loss | -0.0266 | +| n_updates | 93108 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000119 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1387 | +| iterations | 19324 | +| time_elapsed | 28531 | +| total_timesteps | 39575552 | +| train/ | | +| approx_kl | 0.01070951 | +| clip_fraction | 0.329 | +| clip_range | 0.0651 | +| entropy_loss | -6.47 | +| explained_variance | 0.0312 | +| learning_rate | 4.06e-05 | +| loss | -0.0296 | +| n_updates | 93112 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000174 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1387 | +| iterations | 19325 | +| time_elapsed | 28533 | +| total_timesteps | 39577600 | +| train/ | | +| approx_kl | 0.013461985 | +| clip_fraction | 0.343 | +| clip_range | 0.0651 | +| entropy_loss | -6.63 | +| explained_variance | 0.0626 | +| learning_rate | 4.06e-05 | +| loss | -0.0293 | +| n_updates | 93116 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.00014 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1387 | +| iterations | 19326 | +| time_elapsed | 28534 | +| total_timesteps | 39579648 | +| train/ | | +| approx_kl | 0.011265026 | +| clip_fraction | 0.333 | +| clip_range | 0.0651 | +| entropy_loss | -6.45 | +| explained_variance | 0.427 | +| learning_rate | 4.06e-05 | +| loss | -0.0331 | +| n_updates | 93120 | +| policy_gradient_loss | -0.0177 | +| value_loss | 9.33e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1387 | +| iterations | 19327 | +| time_elapsed | 28536 | +| total_timesteps | 39581696 | +| train/ | | +| approx_kl | 0.0124280825 | +| clip_fraction | 0.304 | +| clip_range | 0.0651 | +| entropy_loss | -5.58 | +| explained_variance | 0.671 | +| learning_rate | 4.06e-05 | +| loss | -0.0225 | +| n_updates | 93124 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000125 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1387 | +| iterations | 19328 | +| time_elapsed | 28537 | +| total_timesteps | 39583744 | +| train/ | | +| approx_kl | 0.014775207 | +| clip_fraction | 0.312 | +| clip_range | 0.0651 | +| entropy_loss | -5.14 | +| explained_variance | 0.118 | +| learning_rate | 4.06e-05 | +| loss | -0.0218 | +| n_updates | 93128 | +| policy_gradient_loss | -0.0127 | +| value_loss | 0.000123 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1387 | +| iterations | 19329 | +| time_elapsed | 28539 | +| total_timesteps | 39585792 | +| train/ | | +| approx_kl | 0.012967254 | +| clip_fraction | 0.34 | +| clip_range | 0.0651 | +| entropy_loss | -5.39 | +| explained_variance | 0.57 | +| learning_rate | 4.06e-05 | +| loss | -0.0257 | +| n_updates | 93132 | +| policy_gradient_loss | -0.0162 | +| value_loss | 7.31e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1387 | +| iterations | 19330 | +| time_elapsed | 28540 | +| total_timesteps | 39587840 | +| train/ | | +| approx_kl | 0.01607375 | +| clip_fraction | 0.331 | +| clip_range | 0.0651 | +| entropy_loss | -5.91 | +| explained_variance | 0.419 | +| learning_rate | 4.06e-05 | +| loss | -0.0201 | +| n_updates | 93136 | +| policy_gradient_loss | -0.0145 | +| value_loss | 0.0002 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1387 | +| iterations | 19331 | +| time_elapsed | 28542 | +| total_timesteps | 39589888 | +| train/ | | +| approx_kl | 0.014560005 | +| clip_fraction | 0.348 | +| clip_range | 0.0651 | +| entropy_loss | -5.29 | +| explained_variance | 0.639 | +| learning_rate | 4.06e-05 | +| loss | -0.0281 | +| n_updates | 93140 | +| policy_gradient_loss | -0.0177 | +| value_loss | 8.13e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1387 | +| iterations | 19332 | +| time_elapsed | 28543 | +| total_timesteps | 39591936 | +| train/ | | +| approx_kl | 0.0106068915 | +| clip_fraction | 0.311 | +| clip_range | 0.0651 | +| entropy_loss | -5.22 | +| explained_variance | 0.54 | +| learning_rate | 4.06e-05 | +| loss | -0.0248 | +| n_updates | 93144 | +| policy_gradient_loss | -0.0146 | +| value_loss | 0.000257 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1387 | +| iterations | 19333 | +| time_elapsed | 28545 | +| total_timesteps | 39593984 | +| train/ | | +| approx_kl | 0.012380898 | +| clip_fraction | 0.354 | +| clip_range | 0.0651 | +| entropy_loss | -5.65 | +| explained_variance | 0.0412 | +| learning_rate | 4.06e-05 | +| loss | -0.0359 | +| n_updates | 93148 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000143 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1387 | +| iterations | 19334 | +| time_elapsed | 28546 | +| total_timesteps | 39596032 | +| train/ | | +| approx_kl | 0.008749922 | +| clip_fraction | 0.288 | +| clip_range | 0.0651 | +| entropy_loss | -6.63 | +| explained_variance | 0.231 | +| learning_rate | 4.06e-05 | +| loss | -0.0236 | +| n_updates | 93152 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000141 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 1387 | +| iterations | 19335 | +| time_elapsed | 28548 | +| total_timesteps | 39598080 | +| train/ | | +| approx_kl | 0.008852358 | +| clip_fraction | 0.312 | +| clip_range | 0.0651 | +| entropy_loss | -6.78 | +| explained_variance | -0.0185 | +| learning_rate | 4.06e-05 | +| loss | -0.0232 | +| n_updates | 93156 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000176 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1387 | +| iterations | 19336 | +| time_elapsed | 28550 | +| total_timesteps | 39600128 | +| train/ | | +| approx_kl | 0.010085421 | +| clip_fraction | 0.285 | +| clip_range | 0.0651 | +| entropy_loss | -5.98 | +| explained_variance | 0.448 | +| learning_rate | 4.06e-05 | +| loss | -0.024 | +| n_updates | 93160 | +| policy_gradient_loss | -0.0128 | +| value_loss | 0.000217 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1387 | +| iterations | 19337 | +| time_elapsed | 28551 | +| total_timesteps | 39602176 | +| train/ | | +| approx_kl | 0.011982091 | +| clip_fraction | 0.325 | +| clip_range | 0.0651 | +| entropy_loss | -6.13 | +| explained_variance | 0.1 | +| learning_rate | 4.06e-05 | +| loss | -0.0231 | +| n_updates | 93164 | +| policy_gradient_loss | -0.0144 | +| value_loss | 0.000435 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1387 | +| iterations | 19338 | +| time_elapsed | 28553 | +| total_timesteps | 39604224 | +| train/ | | +| approx_kl | 0.014849573 | +| clip_fraction | 0.355 | +| clip_range | 0.0651 | +| entropy_loss | -5.91 | +| explained_variance | 0.437 | +| learning_rate | 4.06e-05 | +| loss | -0.0331 | +| n_updates | 93168 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000131 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1387 | +| iterations | 19339 | +| time_elapsed | 28554 | +| total_timesteps | 39606272 | +| train/ | | +| approx_kl | 0.011082575 | +| clip_fraction | 0.338 | +| clip_range | 0.0651 | +| entropy_loss | -6.08 | +| explained_variance | 0.462 | +| learning_rate | 4.06e-05 | +| loss | -0.0347 | +| n_updates | 93172 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000126 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1387 | +| iterations | 19340 | +| time_elapsed | 28556 | +| total_timesteps | 39608320 | +| train/ | | +| approx_kl | 0.013496736 | +| clip_fraction | 0.317 | +| clip_range | 0.0651 | +| entropy_loss | -5.54 | +| explained_variance | 0.547 | +| learning_rate | 4.06e-05 | +| loss | -0.023 | +| n_updates | 93176 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000179 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1387 | +| iterations | 19341 | +| time_elapsed | 28557 | +| total_timesteps | 39610368 | +| train/ | | +| approx_kl | 0.013654941 | +| clip_fraction | 0.351 | +| clip_range | 0.0651 | +| entropy_loss | -5.3 | +| explained_variance | 0.22 | +| learning_rate | 4.06e-05 | +| loss | -0.0266 | +| n_updates | 93180 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000189 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1387 | +| iterations | 19342 | +| time_elapsed | 28559 | +| total_timesteps | 39612416 | +| train/ | | +| approx_kl | 0.013106963 | +| clip_fraction | 0.342 | +| clip_range | 0.0651 | +| entropy_loss | -5.19 | +| explained_variance | 0.446 | +| learning_rate | 4.06e-05 | +| loss | -0.0262 | +| n_updates | 93184 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.000171 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1387 | +| iterations | 19343 | +| time_elapsed | 28560 | +| total_timesteps | 39614464 | +| train/ | | +| approx_kl | 0.017425055 | +| clip_fraction | 0.357 | +| clip_range | 0.0651 | +| entropy_loss | -6.29 | +| explained_variance | -0.14 | +| learning_rate | 4.06e-05 | +| loss | -0.032 | +| n_updates | 93188 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000114 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1387 | +| iterations | 19344 | +| time_elapsed | 28562 | +| total_timesteps | 39616512 | +| train/ | | +| approx_kl | 0.015858937 | +| clip_fraction | 0.376 | +| clip_range | 0.0651 | +| entropy_loss | -6.23 | +| explained_variance | -0.0668 | +| learning_rate | 4.06e-05 | +| loss | -0.0281 | +| n_updates | 93192 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000159 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1387 | +| iterations | 19345 | +| time_elapsed | 28563 | +| total_timesteps | 39618560 | +| train/ | | +| approx_kl | 0.016633658 | +| clip_fraction | 0.322 | +| clip_range | 0.0651 | +| entropy_loss | -5.72 | +| explained_variance | 0.339 | +| learning_rate | 4.06e-05 | +| loss | -0.0205 | +| n_updates | 93196 | +| policy_gradient_loss | -0.0143 | +| value_loss | 0.000241 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1387 | +| iterations | 19346 | +| time_elapsed | 28565 | +| total_timesteps | 39620608 | +| train/ | | +| approx_kl | 0.01628138 | +| clip_fraction | 0.357 | +| clip_range | 0.0651 | +| entropy_loss | -5.03 | +| explained_variance | 0.401 | +| learning_rate | 4.06e-05 | +| loss | -0.0336 | +| n_updates | 93200 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000149 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1387 | +| iterations | 19347 | +| time_elapsed | 28566 | +| total_timesteps | 39622656 | +| train/ | | +| approx_kl | 0.015549375 | +| clip_fraction | 0.342 | +| clip_range | 0.0651 | +| entropy_loss | -5.31 | +| explained_variance | 0.518 | +| learning_rate | 4.06e-05 | +| loss | -0.024 | +| n_updates | 93204 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000182 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1387 | +| iterations | 19348 | +| time_elapsed | 28568 | +| total_timesteps | 39624704 | +| train/ | | +| approx_kl | 0.013448493 | +| clip_fraction | 0.349 | +| clip_range | 0.0651 | +| entropy_loss | -5.94 | +| explained_variance | 0.27 | +| learning_rate | 4.06e-05 | +| loss | -0.02 | +| n_updates | 93208 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000222 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1387 | +| iterations | 19349 | +| time_elapsed | 28569 | +| total_timesteps | 39626752 | +| train/ | | +| approx_kl | 0.013751151 | +| clip_fraction | 0.334 | +| clip_range | 0.0651 | +| entropy_loss | -5.61 | +| explained_variance | 0.338 | +| learning_rate | 4.06e-05 | +| loss | -0.0249 | +| n_updates | 93212 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000213 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1387 | +| iterations | 19350 | +| time_elapsed | 28571 | +| total_timesteps | 39628800 | +| train/ | | +| approx_kl | 0.014867973 | +| clip_fraction | 0.337 | +| clip_range | 0.0651 | +| entropy_loss | -5.16 | +| explained_variance | 0.675 | +| learning_rate | 4.06e-05 | +| loss | -0.0305 | +| n_updates | 93216 | +| policy_gradient_loss | -0.0192 | +| value_loss | 9.93e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1387 | +| iterations | 19351 | +| time_elapsed | 28572 | +| total_timesteps | 39630848 | +| train/ | | +| approx_kl | 0.013046099 | +| clip_fraction | 0.319 | +| clip_range | 0.0651 | +| entropy_loss | -5.49 | +| explained_variance | 0.421 | +| learning_rate | 4.06e-05 | +| loss | -0.0206 | +| n_updates | 93220 | +| policy_gradient_loss | -0.0147 | +| value_loss | 0.000294 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1387 | +| iterations | 19352 | +| time_elapsed | 28574 | +| total_timesteps | 39632896 | +| train/ | | +| approx_kl | 0.013958204 | +| clip_fraction | 0.287 | +| clip_range | 0.0651 | +| entropy_loss | -5.33 | +| explained_variance | 0.467 | +| learning_rate | 4.06e-05 | +| loss | -0.0221 | +| n_updates | 93224 | +| policy_gradient_loss | -0.0148 | +| value_loss | 0.000287 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1386 | +| iterations | 19353 | +| time_elapsed | 28576 | +| total_timesteps | 39634944 | +| train/ | | +| approx_kl | 0.017802265 | +| clip_fraction | 0.366 | +| clip_range | 0.0651 | +| entropy_loss | -5.38 | +| explained_variance | 0.498 | +| learning_rate | 4.06e-05 | +| loss | -0.0378 | +| n_updates | 93228 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000122 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1386 | +| iterations | 19354 | +| time_elapsed | 28577 | +| total_timesteps | 39636992 | +| train/ | | +| approx_kl | 0.013528649 | +| clip_fraction | 0.339 | +| clip_range | 0.0651 | +| entropy_loss | -5.65 | +| explained_variance | 0.589 | +| learning_rate | 4.06e-05 | +| loss | -0.0298 | +| n_updates | 93232 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000118 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1386 | +| iterations | 19355 | +| time_elapsed | 28579 | +| total_timesteps | 39639040 | +| train/ | | +| approx_kl | 0.015847098 | +| clip_fraction | 0.384 | +| clip_range | 0.0651 | +| entropy_loss | -5.85 | +| explained_variance | -0.0328 | +| learning_rate | 4.06e-05 | +| loss | -0.0271 | +| n_updates | 93236 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000189 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1386 | +| iterations | 19356 | +| time_elapsed | 28580 | +| total_timesteps | 39641088 | +| train/ | | +| approx_kl | 0.011000799 | +| clip_fraction | 0.337 | +| clip_range | 0.0651 | +| entropy_loss | -6.57 | +| explained_variance | -0.0785 | +| learning_rate | 4.06e-05 | +| loss | -0.0296 | +| n_updates | 93240 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000122 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1386 | +| iterations | 19357 | +| time_elapsed | 28582 | +| total_timesteps | 39643136 | +| train/ | | +| approx_kl | 0.011772387 | +| clip_fraction | 0.324 | +| clip_range | 0.0651 | +| entropy_loss | -6.67 | +| explained_variance | 0.232 | +| learning_rate | 4.06e-05 | +| loss | -0.0288 | +| n_updates | 93244 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000309 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1386 | +| iterations | 19358 | +| time_elapsed | 28583 | +| total_timesteps | 39645184 | +| train/ | | +| approx_kl | 0.012266161 | +| clip_fraction | 0.348 | +| clip_range | 0.0651 | +| entropy_loss | -6.06 | +| explained_variance | 0.205 | +| learning_rate | 4.06e-05 | +| loss | -0.0292 | +| n_updates | 93248 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000156 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1386 | +| iterations | 19359 | +| time_elapsed | 28585 | +| total_timesteps | 39647232 | +| train/ | | +| approx_kl | 0.010526048 | +| clip_fraction | 0.312 | +| clip_range | 0.0651 | +| entropy_loss | -5.64 | +| explained_variance | 0.521 | +| learning_rate | 4.06e-05 | +| loss | -0.0229 | +| n_updates | 93252 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000181 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1386 | +| iterations | 19360 | +| time_elapsed | 28586 | +| total_timesteps | 39649280 | +| train/ | | +| approx_kl | 0.012785906 | +| clip_fraction | 0.331 | +| clip_range | 0.0651 | +| entropy_loss | -4.24 | +| explained_variance | 0.679 | +| learning_rate | 4.06e-05 | +| loss | -0.0221 | +| n_updates | 93256 | +| policy_gradient_loss | -0.0146 | +| value_loss | 0.000197 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1386 | +| iterations | 19361 | +| time_elapsed | 28588 | +| total_timesteps | 39651328 | +| train/ | | +| approx_kl | 0.011988773 | +| clip_fraction | 0.352 | +| clip_range | 0.0651 | +| entropy_loss | -6.07 | +| explained_variance | -0.125 | +| learning_rate | 4.06e-05 | +| loss | -0.0306 | +| n_updates | 93260 | +| policy_gradient_loss | -0.0211 | +| value_loss | 9.13e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1386 | +| iterations | 19362 | +| time_elapsed | 28589 | +| total_timesteps | 39653376 | +| train/ | | +| approx_kl | 0.011937925 | +| clip_fraction | 0.334 | +| clip_range | 0.0651 | +| entropy_loss | -6.72 | +| explained_variance | -0.155 | +| learning_rate | 4.06e-05 | +| loss | -0.0282 | +| n_updates | 93264 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000144 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1386 | +| iterations | 19363 | +| time_elapsed | 28591 | +| total_timesteps | 39655424 | +| train/ | | +| approx_kl | 0.013530577 | +| clip_fraction | 0.313 | +| clip_range | 0.0651 | +| entropy_loss | -6.66 | +| explained_variance | 0.265 | +| learning_rate | 4.06e-05 | +| loss | -0.0282 | +| n_updates | 93268 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.00013 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1386 | +| iterations | 19364 | +| time_elapsed | 28592 | +| total_timesteps | 39657472 | +| train/ | | +| approx_kl | 0.013463248 | +| clip_fraction | 0.343 | +| clip_range | 0.0651 | +| entropy_loss | -5.88 | +| explained_variance | 0.163 | +| learning_rate | 4.06e-05 | +| loss | -0.0251 | +| n_updates | 93272 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000386 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1386 | +| iterations | 19365 | +| time_elapsed | 28594 | +| total_timesteps | 39659520 | +| train/ | | +| approx_kl | 0.016522545 | +| clip_fraction | 0.354 | +| clip_range | 0.0651 | +| entropy_loss | -5.38 | +| explained_variance | 0.141 | +| learning_rate | 4.06e-05 | +| loss | -0.0286 | +| n_updates | 93276 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000281 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1386 | +| iterations | 19366 | +| time_elapsed | 28595 | +| total_timesteps | 39661568 | +| train/ | | +| approx_kl | 0.013366831 | +| clip_fraction | 0.34 | +| clip_range | 0.0651 | +| entropy_loss | -5.04 | +| explained_variance | 0.302 | +| learning_rate | 4.06e-05 | +| loss | -0.0294 | +| n_updates | 93280 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000303 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1386 | +| iterations | 19367 | +| time_elapsed | 28597 | +| total_timesteps | 39663616 | +| train/ | | +| approx_kl | 0.013795974 | +| clip_fraction | 0.334 | +| clip_range | 0.0651 | +| entropy_loss | -5.6 | +| explained_variance | 0.417 | +| learning_rate | 4.06e-05 | +| loss | -0.0313 | +| n_updates | 93284 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000206 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1386 | +| iterations | 19368 | +| time_elapsed | 28598 | +| total_timesteps | 39665664 | +| train/ | | +| approx_kl | 0.0135902865 | +| clip_fraction | 0.358 | +| clip_range | 0.0651 | +| entropy_loss | -6.13 | +| explained_variance | 0.258 | +| learning_rate | 4.06e-05 | +| loss | -0.0311 | +| n_updates | 93288 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000153 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1386 | +| iterations | 19369 | +| time_elapsed | 28600 | +| total_timesteps | 39667712 | +| train/ | | +| approx_kl | 0.01340737 | +| clip_fraction | 0.316 | +| clip_range | 0.0651 | +| entropy_loss | -6.27 | +| explained_variance | 0.391 | +| learning_rate | 4.06e-05 | +| loss | -0.0279 | +| n_updates | 93292 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000252 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1386 | +| iterations | 19370 | +| time_elapsed | 28602 | +| total_timesteps | 39669760 | +| train/ | | +| approx_kl | 0.01063186 | +| clip_fraction | 0.317 | +| clip_range | 0.0651 | +| entropy_loss | -5.7 | +| explained_variance | 0.396 | +| learning_rate | 4.06e-05 | +| loss | -0.0243 | +| n_updates | 93296 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000264 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1386 | +| iterations | 19371 | +| time_elapsed | 28603 | +| total_timesteps | 39671808 | +| train/ | | +| approx_kl | 0.0145610105 | +| clip_fraction | 0.344 | +| clip_range | 0.0651 | +| entropy_loss | -5.35 | +| explained_variance | 0.358 | +| learning_rate | 4.06e-05 | +| loss | -0.0269 | +| n_updates | 93300 | +| policy_gradient_loss | -0.0196 | +| value_loss | 9e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1386 | +| iterations | 19372 | +| time_elapsed | 28605 | +| total_timesteps | 39673856 | +| train/ | | +| approx_kl | 0.016873974 | +| clip_fraction | 0.346 | +| clip_range | 0.0651 | +| entropy_loss | -4.36 | +| explained_variance | 0.796 | +| learning_rate | 4.06e-05 | +| loss | -0.029 | +| n_updates | 93304 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000105 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1386 | +| iterations | 19373 | +| time_elapsed | 28606 | +| total_timesteps | 39675904 | +| train/ | | +| approx_kl | 0.017995123 | +| clip_fraction | 0.332 | +| clip_range | 0.0651 | +| entropy_loss | -5.05 | +| explained_variance | 0.469 | +| learning_rate | 4.06e-05 | +| loss | -0.0352 | +| n_updates | 93308 | +| policy_gradient_loss | -0.0187 | +| value_loss | 8.4e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1386 | +| iterations | 19374 | +| time_elapsed | 28608 | +| total_timesteps | 39677952 | +| train/ | | +| approx_kl | 0.015447944 | +| clip_fraction | 0.334 | +| clip_range | 0.0651 | +| entropy_loss | -6.16 | +| explained_variance | 0.329 | +| learning_rate | 4.06e-05 | +| loss | -0.0282 | +| n_updates | 93312 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1386 | +| iterations | 19375 | +| time_elapsed | 28609 | +| total_timesteps | 39680000 | +| train/ | | +| approx_kl | 0.015113903 | +| clip_fraction | 0.339 | +| clip_range | 0.0651 | +| entropy_loss | -5.72 | +| explained_variance | 0.541 | +| learning_rate | 4.06e-05 | +| loss | -0.0241 | +| n_updates | 93316 | +| policy_gradient_loss | -0.0165 | +| value_loss | 9.64e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1386 | +| iterations | 19376 | +| time_elapsed | 28611 | +| total_timesteps | 39682048 | +| train/ | | +| approx_kl | 0.014121294 | +| clip_fraction | 0.331 | +| clip_range | 0.0651 | +| entropy_loss | -5.72 | +| explained_variance | 0.505 | +| learning_rate | 4.06e-05 | +| loss | -0.0287 | +| n_updates | 93320 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1386 | +| iterations | 19377 | +| time_elapsed | 28612 | +| total_timesteps | 39684096 | +| train/ | | +| approx_kl | 0.013911951 | +| clip_fraction | 0.317 | +| clip_range | 0.0651 | +| entropy_loss | -6.27 | +| explained_variance | -0.0688 | +| learning_rate | 4.06e-05 | +| loss | -0.0282 | +| n_updates | 93324 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000168 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1386 | +| iterations | 19378 | +| time_elapsed | 28614 | +| total_timesteps | 39686144 | +| train/ | | +| approx_kl | 0.0144407945 | +| clip_fraction | 0.35 | +| clip_range | 0.0651 | +| entropy_loss | -6 | +| explained_variance | 0.292 | +| learning_rate | 4.06e-05 | +| loss | -0.031 | +| n_updates | 93328 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000158 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1386 | +| iterations | 19379 | +| time_elapsed | 28615 | +| total_timesteps | 39688192 | +| train/ | | +| approx_kl | 0.011477403 | +| clip_fraction | 0.315 | +| clip_range | 0.0651 | +| entropy_loss | -5.78 | +| explained_variance | 0.454 | +| learning_rate | 4.06e-05 | +| loss | -0.0246 | +| n_updates | 93332 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000259 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1386 | +| iterations | 19380 | +| time_elapsed | 28617 | +| total_timesteps | 39690240 | +| train/ | | +| approx_kl | 0.012416223 | +| clip_fraction | 0.321 | +| clip_range | 0.0651 | +| entropy_loss | -5.4 | +| explained_variance | 0.328 | +| learning_rate | 4.06e-05 | +| loss | -0.0263 | +| n_updates | 93336 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000123 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1386 | +| iterations | 19381 | +| time_elapsed | 28618 | +| total_timesteps | 39692288 | +| train/ | | +| approx_kl | 0.013662527 | +| clip_fraction | 0.328 | +| clip_range | 0.0651 | +| entropy_loss | -5.52 | +| explained_variance | 0.406 | +| learning_rate | 4.06e-05 | +| loss | -0.0201 | +| n_updates | 93340 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.0002 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1386 | +| iterations | 19382 | +| time_elapsed | 28620 | +| total_timesteps | 39694336 | +| train/ | | +| approx_kl | 0.011622943 | +| clip_fraction | 0.317 | +| clip_range | 0.0651 | +| entropy_loss | -5.14 | +| explained_variance | 0.538 | +| learning_rate | 4.06e-05 | +| loss | -0.0202 | +| n_updates | 93344 | +| policy_gradient_loss | -0.014 | +| value_loss | 0.000184 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1386 | +| iterations | 19383 | +| time_elapsed | 28621 | +| total_timesteps | 39696384 | +| train/ | | +| approx_kl | 0.016800258 | +| clip_fraction | 0.328 | +| clip_range | 0.0651 | +| entropy_loss | -5.6 | +| explained_variance | 0.6 | +| learning_rate | 4.06e-05 | +| loss | -0.0265 | +| n_updates | 93348 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000104 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1386 | +| iterations | 19384 | +| time_elapsed | 28623 | +| total_timesteps | 39698432 | +| train/ | | +| approx_kl | 0.015890645 | +| clip_fraction | 0.379 | +| clip_range | 0.0651 | +| entropy_loss | -5.83 | +| explained_variance | 0.413 | +| learning_rate | 4.06e-05 | +| loss | -0.0287 | +| n_updates | 93352 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000106 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1386 | +| iterations | 19385 | +| time_elapsed | 28624 | +| total_timesteps | 39700480 | +| train/ | | +| approx_kl | 0.016716827 | +| clip_fraction | 0.354 | +| clip_range | 0.0651 | +| entropy_loss | -6.13 | +| explained_variance | -0.0915 | +| learning_rate | 4.06e-05 | +| loss | -0.0284 | +| n_updates | 93356 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000117 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1386 | +| iterations | 19386 | +| time_elapsed | 28626 | +| total_timesteps | 39702528 | +| train/ | | +| approx_kl | 0.01358247 | +| clip_fraction | 0.339 | +| clip_range | 0.0651 | +| entropy_loss | -6.32 | +| explained_variance | -0.0485 | +| learning_rate | 4.06e-05 | +| loss | -0.0293 | +| n_updates | 93360 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000137 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1386 | +| iterations | 19387 | +| time_elapsed | 28627 | +| total_timesteps | 39704576 | +| train/ | | +| approx_kl | 0.012446921 | +| clip_fraction | 0.334 | +| clip_range | 0.0651 | +| entropy_loss | -6.25 | +| explained_variance | 0.349 | +| learning_rate | 4.06e-05 | +| loss | -0.0268 | +| n_updates | 93364 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000141 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1386 | +| iterations | 19388 | +| time_elapsed | 28629 | +| total_timesteps | 39706624 | +| train/ | | +| approx_kl | 0.0150229195 | +| clip_fraction | 0.336 | +| clip_range | 0.0651 | +| entropy_loss | -6.31 | +| explained_variance | -0.0304 | +| learning_rate | 4.06e-05 | +| loss | -0.0247 | +| n_updates | 93368 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000171 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1386 | +| iterations | 19389 | +| time_elapsed | 28630 | +| total_timesteps | 39708672 | +| train/ | | +| approx_kl | 0.012440668 | +| clip_fraction | 0.312 | +| clip_range | 0.0651 | +| entropy_loss | -5.79 | +| explained_variance | 0.564 | +| learning_rate | 4.06e-05 | +| loss | -0.0288 | +| n_updates | 93372 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000211 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1386 | +| iterations | 19390 | +| time_elapsed | 28632 | +| total_timesteps | 39710720 | +| train/ | | +| approx_kl | 0.021675853 | +| clip_fraction | 0.328 | +| clip_range | 0.0651 | +| entropy_loss | -5.25 | +| explained_variance | 0.649 | +| learning_rate | 4.06e-05 | +| loss | -0.0281 | +| n_updates | 93376 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000109 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1386 | +| iterations | 19391 | +| time_elapsed | 28633 | +| total_timesteps | 39712768 | +| train/ | | +| approx_kl | 0.012269963 | +| clip_fraction | 0.353 | +| clip_range | 0.0651 | +| entropy_loss | -5.67 | +| explained_variance | 0.478 | +| learning_rate | 4.06e-05 | +| loss | -0.03 | +| n_updates | 93380 | +| policy_gradient_loss | -0.0191 | +| value_loss | 6.28e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1386 | +| iterations | 19392 | +| time_elapsed | 28635 | +| total_timesteps | 39714816 | +| train/ | | +| approx_kl | 0.012765124 | +| clip_fraction | 0.356 | +| clip_range | 0.0651 | +| entropy_loss | -5.65 | +| explained_variance | 0.756 | +| learning_rate | 4.06e-05 | +| loss | -0.03 | +| n_updates | 93384 | +| policy_gradient_loss | -0.0205 | +| value_loss | 4.78e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1386 | +| iterations | 19393 | +| time_elapsed | 28636 | +| total_timesteps | 39716864 | +| train/ | | +| approx_kl | 0.0113837235 | +| clip_fraction | 0.291 | +| clip_range | 0.0651 | +| entropy_loss | -6.12 | +| explained_variance | 0.332 | +| learning_rate | 4.06e-05 | +| loss | -0.0231 | +| n_updates | 93388 | +| policy_gradient_loss | -0.0135 | +| value_loss | 0.000144 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1386 | +| iterations | 19394 | +| time_elapsed | 28638 | +| total_timesteps | 39718912 | +| train/ | | +| approx_kl | 0.012677922 | +| clip_fraction | 0.319 | +| clip_range | 0.0651 | +| entropy_loss | -6.02 | +| explained_variance | 0.208 | +| learning_rate | 4.06e-05 | +| loss | -0.0263 | +| n_updates | 93392 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000232 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1386 | +| iterations | 19395 | +| time_elapsed | 28639 | +| total_timesteps | 39720960 | +| train/ | | +| approx_kl | 0.013401603 | +| clip_fraction | 0.32 | +| clip_range | 0.0651 | +| entropy_loss | -5.83 | +| explained_variance | 0.382 | +| learning_rate | 4.06e-05 | +| loss | -0.0254 | +| n_updates | 93396 | +| policy_gradient_loss | -0.0129 | +| value_loss | 0.00023 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1386 | +| iterations | 19396 | +| time_elapsed | 28641 | +| total_timesteps | 39723008 | +| train/ | | +| approx_kl | 0.011907445 | +| clip_fraction | 0.333 | +| clip_range | 0.0651 | +| entropy_loss | -6.17 | +| explained_variance | 0.407 | +| learning_rate | 4.06e-05 | +| loss | -0.0311 | +| n_updates | 93400 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000125 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1386 | +| iterations | 19397 | +| time_elapsed | 28642 | +| total_timesteps | 39725056 | +| train/ | | +| approx_kl | 0.011070054 | +| clip_fraction | 0.315 | +| clip_range | 0.0651 | +| entropy_loss | -6.23 | +| explained_variance | 0.175 | +| learning_rate | 4.06e-05 | +| loss | -0.0242 | +| n_updates | 93404 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000162 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1386 | +| iterations | 19398 | +| time_elapsed | 28644 | +| total_timesteps | 39727104 | +| train/ | | +| approx_kl | 0.016695552 | +| clip_fraction | 0.34 | +| clip_range | 0.0651 | +| entropy_loss | -5.84 | +| explained_variance | 0.515 | +| learning_rate | 4.06e-05 | +| loss | -0.0256 | +| n_updates | 93408 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000134 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1386 | +| iterations | 19399 | +| time_elapsed | 28645 | +| total_timesteps | 39729152 | +| train/ | | +| approx_kl | 0.017094139 | +| clip_fraction | 0.364 | +| clip_range | 0.0651 | +| entropy_loss | -6.34 | +| explained_variance | -0.415 | +| learning_rate | 4.06e-05 | +| loss | -0.0303 | +| n_updates | 93412 | +| policy_gradient_loss | -0.0204 | +| value_loss | 4.61e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1386 | +| iterations | 19400 | +| time_elapsed | 28647 | +| total_timesteps | 39731200 | +| train/ | | +| approx_kl | 0.011027794 | +| clip_fraction | 0.32 | +| clip_range | 0.0651 | +| entropy_loss | -5.9 | +| explained_variance | 0.621 | +| learning_rate | 4.06e-05 | +| loss | -0.0288 | +| n_updates | 93416 | +| policy_gradient_loss | -0.0156 | +| value_loss | 9.62e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1386 | +| iterations | 19401 | +| time_elapsed | 28648 | +| total_timesteps | 39733248 | +| train/ | | +| approx_kl | 0.012162345 | +| clip_fraction | 0.312 | +| clip_range | 0.0651 | +| entropy_loss | -5.57 | +| explained_variance | 0.528 | +| learning_rate | 4.06e-05 | +| loss | -0.0244 | +| n_updates | 93420 | +| policy_gradient_loss | -0.0142 | +| value_loss | 0.000245 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1386 | +| iterations | 19402 | +| time_elapsed | 28650 | +| total_timesteps | 39735296 | +| train/ | | +| approx_kl | 0.012459021 | +| clip_fraction | 0.34 | +| clip_range | 0.0651 | +| entropy_loss | -5.76 | +| explained_variance | 0.649 | +| learning_rate | 4.06e-05 | +| loss | -0.0287 | +| n_updates | 93424 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000122 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1386 | +| iterations | 19403 | +| time_elapsed | 28651 | +| total_timesteps | 39737344 | +| train/ | | +| approx_kl | 0.012088565 | +| clip_fraction | 0.329 | +| clip_range | 0.0651 | +| entropy_loss | -6.38 | +| explained_variance | 0.019 | +| learning_rate | 4.06e-05 | +| loss | -0.0303 | +| n_updates | 93428 | +| policy_gradient_loss | -0.0193 | +| value_loss | 8.69e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1386 | +| iterations | 19404 | +| time_elapsed | 28653 | +| total_timesteps | 39739392 | +| train/ | | +| approx_kl | 0.011834567 | +| clip_fraction | 0.345 | +| clip_range | 0.0651 | +| entropy_loss | -5.87 | +| explained_variance | 0.584 | +| learning_rate | 4.06e-05 | +| loss | -0.0292 | +| n_updates | 93432 | +| policy_gradient_loss | -0.0191 | +| value_loss | 9.91e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1386 | +| iterations | 19405 | +| time_elapsed | 28654 | +| total_timesteps | 39741440 | +| train/ | | +| approx_kl | 0.010514779 | +| clip_fraction | 0.328 | +| clip_range | 0.0651 | +| entropy_loss | -6.25 | +| explained_variance | 0.459 | +| learning_rate | 4.06e-05 | +| loss | -0.0319 | +| n_updates | 93436 | +| policy_gradient_loss | -0.0182 | +| value_loss | 8.3e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1386 | +| iterations | 19406 | +| time_elapsed | 28656 | +| total_timesteps | 39743488 | +| train/ | | +| approx_kl | 0.010133487 | +| clip_fraction | 0.323 | +| clip_range | 0.0651 | +| entropy_loss | -6.09 | +| explained_variance | 0.649 | +| learning_rate | 4.06e-05 | +| loss | -0.0236 | +| n_updates | 93440 | +| policy_gradient_loss | -0.0155 | +| value_loss | 8.95e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1386 | +| iterations | 19407 | +| time_elapsed | 28657 | +| total_timesteps | 39745536 | +| train/ | | +| approx_kl | 0.018710723 | +| clip_fraction | 0.336 | +| clip_range | 0.0651 | +| entropy_loss | -5.72 | +| explained_variance | 0.497 | +| learning_rate | 4.06e-05 | +| loss | -0.03 | +| n_updates | 93444 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000151 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1386 | +| iterations | 19408 | +| time_elapsed | 28659 | +| total_timesteps | 39747584 | +| train/ | | +| approx_kl | 0.013976043 | +| clip_fraction | 0.327 | +| clip_range | 0.0651 | +| entropy_loss | -6.34 | +| explained_variance | 0.122 | +| learning_rate | 4.06e-05 | +| loss | -0.0262 | +| n_updates | 93448 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000166 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1386 | +| iterations | 19409 | +| time_elapsed | 28661 | +| total_timesteps | 39749632 | +| train/ | | +| approx_kl | 0.013521289 | +| clip_fraction | 0.329 | +| clip_range | 0.0651 | +| entropy_loss | -5.45 | +| explained_variance | 0.44 | +| learning_rate | 4.06e-05 | +| loss | -0.0253 | +| n_updates | 93452 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.000201 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1386 | +| iterations | 19410 | +| time_elapsed | 28662 | +| total_timesteps | 39751680 | +| train/ | | +| approx_kl | 0.013184475 | +| clip_fraction | 0.329 | +| clip_range | 0.0651 | +| entropy_loss | -5.7 | +| explained_variance | 0.384 | +| learning_rate | 4.06e-05 | +| loss | -0.0218 | +| n_updates | 93456 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.00022 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1386 | +| iterations | 19411 | +| time_elapsed | 28664 | +| total_timesteps | 39753728 | +| train/ | | +| approx_kl | 0.01191335 | +| clip_fraction | 0.335 | +| clip_range | 0.0651 | +| entropy_loss | -6.21 | +| explained_variance | 0.273 | +| learning_rate | 4.06e-05 | +| loss | -0.0252 | +| n_updates | 93460 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000179 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1386 | +| iterations | 19412 | +| time_elapsed | 28665 | +| total_timesteps | 39755776 | +| train/ | | +| approx_kl | 0.01156758 | +| clip_fraction | 0.331 | +| clip_range | 0.0651 | +| entropy_loss | -6.24 | +| explained_variance | 0.213 | +| learning_rate | 4.06e-05 | +| loss | -0.0294 | +| n_updates | 93464 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000254 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1386 | +| iterations | 19413 | +| time_elapsed | 28667 | +| total_timesteps | 39757824 | +| train/ | | +| approx_kl | 0.012538484 | +| clip_fraction | 0.33 | +| clip_range | 0.0651 | +| entropy_loss | -6.74 | +| explained_variance | -0.135 | +| learning_rate | 4.06e-05 | +| loss | -0.0297 | +| n_updates | 93468 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000155 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1386 | +| iterations | 19414 | +| time_elapsed | 28668 | +| total_timesteps | 39759872 | +| train/ | | +| approx_kl | 0.010919223 | +| clip_fraction | 0.34 | +| clip_range | 0.0651 | +| entropy_loss | -6.03 | +| explained_variance | 0.203 | +| learning_rate | 4.06e-05 | +| loss | -0.028 | +| n_updates | 93472 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000332 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1386 | +| iterations | 19415 | +| time_elapsed | 28670 | +| total_timesteps | 39761920 | +| train/ | | +| approx_kl | 0.013720246 | +| clip_fraction | 0.333 | +| clip_range | 0.0651 | +| entropy_loss | -5.48 | +| explained_variance | 0.649 | +| learning_rate | 4.06e-05 | +| loss | -0.0267 | +| n_updates | 93476 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000131 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1386 | +| iterations | 19416 | +| time_elapsed | 28671 | +| total_timesteps | 39763968 | +| train/ | | +| approx_kl | 0.015746808 | +| clip_fraction | 0.354 | +| clip_range | 0.0651 | +| entropy_loss | -5.37 | +| explained_variance | 0.263 | +| learning_rate | 4.06e-05 | +| loss | -0.0305 | +| n_updates | 93480 | +| policy_gradient_loss | -0.0148 | +| value_loss | 0.000236 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1386 | +| iterations | 19417 | +| time_elapsed | 28673 | +| total_timesteps | 39766016 | +| train/ | | +| approx_kl | 0.01498552 | +| clip_fraction | 0.36 | +| clip_range | 0.0651 | +| entropy_loss | -5.18 | +| explained_variance | 0.617 | +| learning_rate | 4.06e-05 | +| loss | -0.0331 | +| n_updates | 93484 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.00015 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1386 | +| iterations | 19418 | +| time_elapsed | 28674 | +| total_timesteps | 39768064 | +| train/ | | +| approx_kl | 0.016928753 | +| clip_fraction | 0.38 | +| clip_range | 0.0651 | +| entropy_loss | -5.68 | +| explained_variance | 0.704 | +| learning_rate | 4.06e-05 | +| loss | -0.028 | +| n_updates | 93488 | +| policy_gradient_loss | -0.0194 | +| value_loss | 6.71e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1386 | +| iterations | 19419 | +| time_elapsed | 28676 | +| total_timesteps | 39770112 | +| train/ | | +| approx_kl | 0.012165761 | +| clip_fraction | 0.344 | +| clip_range | 0.0651 | +| entropy_loss | -6.19 | +| explained_variance | -0.0504 | +| learning_rate | 4.06e-05 | +| loss | -0.0242 | +| n_updates | 93492 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.00015 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1386 | +| iterations | 19420 | +| time_elapsed | 28677 | +| total_timesteps | 39772160 | +| train/ | | +| approx_kl | 0.009591849 | +| clip_fraction | 0.318 | +| clip_range | 0.0651 | +| entropy_loss | -6.08 | +| explained_variance | 0.26 | +| learning_rate | 4.06e-05 | +| loss | -0.0294 | +| n_updates | 93496 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000391 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1386 | +| iterations | 19421 | +| time_elapsed | 28679 | +| total_timesteps | 39774208 | +| train/ | | +| approx_kl | 0.01248182 | +| clip_fraction | 0.345 | +| clip_range | 0.0651 | +| entropy_loss | -5.81 | +| explained_variance | 0.23 | +| learning_rate | 4.06e-05 | +| loss | -0.0268 | +| n_updates | 93500 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.00039 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1386 | +| iterations | 19422 | +| time_elapsed | 28681 | +| total_timesteps | 39776256 | +| train/ | | +| approx_kl | 0.015198943 | +| clip_fraction | 0.37 | +| clip_range | 0.0651 | +| entropy_loss | -6 | +| explained_variance | 0.282 | +| learning_rate | 4.06e-05 | +| loss | -0.0359 | +| n_updates | 93504 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000118 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1386 | +| iterations | 19423 | +| time_elapsed | 28682 | +| total_timesteps | 39778304 | +| train/ | | +| approx_kl | 0.011216101 | +| clip_fraction | 0.326 | +| clip_range | 0.0651 | +| entropy_loss | -6.31 | +| explained_variance | 0.278 | +| learning_rate | 4.06e-05 | +| loss | -0.033 | +| n_updates | 93508 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000142 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1386 | +| iterations | 19424 | +| time_elapsed | 28684 | +| total_timesteps | 39780352 | +| train/ | | +| approx_kl | 0.013856255 | +| clip_fraction | 0.313 | +| clip_range | 0.0651 | +| entropy_loss | -5.85 | +| explained_variance | 0.251 | +| learning_rate | 4.06e-05 | +| loss | -0.0271 | +| n_updates | 93512 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000221 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1386 | +| iterations | 19425 | +| time_elapsed | 28685 | +| total_timesteps | 39782400 | +| train/ | | +| approx_kl | 0.014901215 | +| clip_fraction | 0.332 | +| clip_range | 0.0651 | +| entropy_loss | -5.67 | +| explained_variance | 0.591 | +| learning_rate | 4.06e-05 | +| loss | -0.0278 | +| n_updates | 93516 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.00011 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1386 | +| iterations | 19426 | +| time_elapsed | 28687 | +| total_timesteps | 39784448 | +| train/ | | +| approx_kl | 0.016253315 | +| clip_fraction | 0.328 | +| clip_range | 0.0651 | +| entropy_loss | -6.33 | +| explained_variance | -0.122 | +| learning_rate | 4.06e-05 | +| loss | -0.0248 | +| n_updates | 93520 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.00019 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1386 | +| iterations | 19427 | +| time_elapsed | 28688 | +| total_timesteps | 39786496 | +| train/ | | +| approx_kl | 0.013995198 | +| clip_fraction | 0.289 | +| clip_range | 0.0651 | +| entropy_loss | -5.94 | +| explained_variance | 0.562 | +| learning_rate | 4.06e-05 | +| loss | -0.0166 | +| n_updates | 93524 | +| policy_gradient_loss | -0.0133 | +| value_loss | 0.000165 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1386 | +| iterations | 19428 | +| time_elapsed | 28690 | +| total_timesteps | 39788544 | +| train/ | | +| approx_kl | 0.016423438 | +| clip_fraction | 0.338 | +| clip_range | 0.0651 | +| entropy_loss | -5.76 | +| explained_variance | 0.182 | +| learning_rate | 4.06e-05 | +| loss | -0.0254 | +| n_updates | 93528 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000236 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1386 | +| iterations | 19429 | +| time_elapsed | 28691 | +| total_timesteps | 39790592 | +| train/ | | +| approx_kl | 0.013515988 | +| clip_fraction | 0.349 | +| clip_range | 0.0651 | +| entropy_loss | -5.8 | +| explained_variance | 0.476 | +| learning_rate | 4.06e-05 | +| loss | -0.0271 | +| n_updates | 93532 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000164 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1386 | +| iterations | 19430 | +| time_elapsed | 28693 | +| total_timesteps | 39792640 | +| train/ | | +| approx_kl | 0.015656501 | +| clip_fraction | 0.321 | +| clip_range | 0.0651 | +| entropy_loss | -5.75 | +| explained_variance | 0.311 | +| learning_rate | 4.05e-05 | +| loss | -0.0219 | +| n_updates | 93536 | +| policy_gradient_loss | -0.0146 | +| value_loss | 0.00026 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1386 | +| iterations | 19431 | +| time_elapsed | 28694 | +| total_timesteps | 39794688 | +| train/ | | +| approx_kl | 0.01035141 | +| clip_fraction | 0.316 | +| clip_range | 0.0651 | +| entropy_loss | -5.58 | +| explained_variance | 0.297 | +| learning_rate | 4.05e-05 | +| loss | -0.0273 | +| n_updates | 93540 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000309 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1386 | +| iterations | 19432 | +| time_elapsed | 28696 | +| total_timesteps | 39796736 | +| train/ | | +| approx_kl | 0.014334985 | +| clip_fraction | 0.355 | +| clip_range | 0.0651 | +| entropy_loss | -5.96 | +| explained_variance | -0.0415 | +| learning_rate | 4.05e-05 | +| loss | -0.0328 | +| n_updates | 93544 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.00012 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1386 | +| iterations | 19433 | +| time_elapsed | 28698 | +| total_timesteps | 39798784 | +| train/ | | +| approx_kl | 0.013830598 | +| clip_fraction | 0.346 | +| clip_range | 0.0651 | +| entropy_loss | -6.24 | +| explained_variance | 0.304 | +| learning_rate | 4.05e-05 | +| loss | -0.0246 | +| n_updates | 93548 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000173 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1386 | +| iterations | 19434 | +| time_elapsed | 28699 | +| total_timesteps | 39800832 | +| train/ | | +| approx_kl | 0.013233354 | +| clip_fraction | 0.337 | +| clip_range | 0.0651 | +| entropy_loss | -5.61 | +| explained_variance | 0.609 | +| learning_rate | 4.05e-05 | +| loss | -0.0309 | +| n_updates | 93552 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000102 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1386 | +| iterations | 19435 | +| time_elapsed | 28701 | +| total_timesteps | 39802880 | +| train/ | | +| approx_kl | 0.015231242 | +| clip_fraction | 0.328 | +| clip_range | 0.065 | +| entropy_loss | -5.58 | +| explained_variance | 0.263 | +| learning_rate | 4.05e-05 | +| loss | -0.026 | +| n_updates | 93556 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000163 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1386 | +| iterations | 19436 | +| time_elapsed | 28702 | +| total_timesteps | 39804928 | +| train/ | | +| approx_kl | 0.011697357 | +| clip_fraction | 0.329 | +| clip_range | 0.065 | +| entropy_loss | -6.39 | +| explained_variance | 0.0948 | +| learning_rate | 4.05e-05 | +| loss | -0.0192 | +| n_updates | 93560 | +| policy_gradient_loss | -0.0136 | +| value_loss | 0.000166 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1386 | +| iterations | 19437 | +| time_elapsed | 28704 | +| total_timesteps | 39806976 | +| train/ | | +| approx_kl | 0.014324054 | +| clip_fraction | 0.335 | +| clip_range | 0.065 | +| entropy_loss | -5.76 | +| explained_variance | 0.301 | +| learning_rate | 4.05e-05 | +| loss | -0.0232 | +| n_updates | 93564 | +| policy_gradient_loss | -0.0145 | +| value_loss | 0.000195 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1386 | +| iterations | 19438 | +| time_elapsed | 28705 | +| total_timesteps | 39809024 | +| train/ | | +| approx_kl | 0.013667412 | +| clip_fraction | 0.333 | +| clip_range | 0.065 | +| entropy_loss | -5.67 | +| explained_variance | 0.469 | +| learning_rate | 4.05e-05 | +| loss | -0.0272 | +| n_updates | 93568 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000206 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1386 | +| iterations | 19439 | +| time_elapsed | 28707 | +| total_timesteps | 39811072 | +| train/ | | +| approx_kl | 0.01375098 | +| clip_fraction | 0.32 | +| clip_range | 0.065 | +| entropy_loss | -5.32 | +| explained_variance | 0.487 | +| learning_rate | 4.05e-05 | +| loss | -0.0298 | +| n_updates | 93572 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000239 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1386 | +| iterations | 19440 | +| time_elapsed | 28708 | +| total_timesteps | 39813120 | +| train/ | | +| approx_kl | 0.017209027 | +| clip_fraction | 0.342 | +| clip_range | 0.065 | +| entropy_loss | -5.05 | +| explained_variance | 0.484 | +| learning_rate | 4.05e-05 | +| loss | -0.0293 | +| n_updates | 93576 | +| policy_gradient_loss | -0.0202 | +| value_loss | 8.81e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1386 | +| iterations | 19441 | +| time_elapsed | 28710 | +| total_timesteps | 39815168 | +| train/ | | +| approx_kl | 0.018530022 | +| clip_fraction | 0.377 | +| clip_range | 0.065 | +| entropy_loss | -5.59 | +| explained_variance | 0.289 | +| learning_rate | 4.05e-05 | +| loss | -0.0301 | +| n_updates | 93580 | +| policy_gradient_loss | -0.0206 | +| value_loss | 9.57e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1386 | +| iterations | 19442 | +| time_elapsed | 28711 | +| total_timesteps | 39817216 | +| train/ | | +| approx_kl | 0.016267225 | +| clip_fraction | 0.365 | +| clip_range | 0.065 | +| entropy_loss | -6.15 | +| explained_variance | -0.129 | +| learning_rate | 4.05e-05 | +| loss | -0.0296 | +| n_updates | 93584 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000135 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1386 | +| iterations | 19443 | +| time_elapsed | 28713 | +| total_timesteps | 39819264 | +| train/ | | +| approx_kl | 0.014316586 | +| clip_fraction | 0.345 | +| clip_range | 0.065 | +| entropy_loss | -6.29 | +| explained_variance | 0.464 | +| learning_rate | 4.05e-05 | +| loss | -0.0174 | +| n_updates | 93588 | +| policy_gradient_loss | -0.0178 | +| value_loss | 9.38e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1386 | +| iterations | 19444 | +| time_elapsed | 28714 | +| total_timesteps | 39821312 | +| train/ | | +| approx_kl | 0.015542397 | +| clip_fraction | 0.3 | +| clip_range | 0.065 | +| entropy_loss | -5.79 | +| explained_variance | 0.462 | +| learning_rate | 4.05e-05 | +| loss | -0.021 | +| n_updates | 93592 | +| policy_gradient_loss | -0.0145 | +| value_loss | 0.000186 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1386 | +| iterations | 19445 | +| time_elapsed | 28716 | +| total_timesteps | 39823360 | +| train/ | | +| approx_kl | 0.014083819 | +| clip_fraction | 0.342 | +| clip_range | 0.065 | +| entropy_loss | -5.35 | +| explained_variance | 0.497 | +| learning_rate | 4.05e-05 | +| loss | -0.0284 | +| n_updates | 93596 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000122 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1386 | +| iterations | 19446 | +| time_elapsed | 28718 | +| total_timesteps | 39825408 | +| train/ | | +| approx_kl | 0.011196759 | +| clip_fraction | 0.3 | +| clip_range | 0.065 | +| entropy_loss | -5.41 | +| explained_variance | 0.658 | +| learning_rate | 4.05e-05 | +| loss | -0.0236 | +| n_updates | 93600 | +| policy_gradient_loss | -0.0141 | +| value_loss | 8.08e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1386 | +| iterations | 19447 | +| time_elapsed | 28719 | +| total_timesteps | 39827456 | +| train/ | | +| approx_kl | 0.015688494 | +| clip_fraction | 0.343 | +| clip_range | 0.065 | +| entropy_loss | -5.72 | +| explained_variance | 0.334 | +| learning_rate | 4.05e-05 | +| loss | -0.0269 | +| n_updates | 93604 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000146 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1386 | +| iterations | 19448 | +| time_elapsed | 28721 | +| total_timesteps | 39829504 | +| train/ | | +| approx_kl | 0.023768336 | +| clip_fraction | 0.346 | +| clip_range | 0.065 | +| entropy_loss | -5.44 | +| explained_variance | -0.0829 | +| learning_rate | 4.05e-05 | +| loss | -0.0286 | +| n_updates | 93608 | +| policy_gradient_loss | -0.0154 | +| value_loss | 8.62e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1386 | +| iterations | 19449 | +| time_elapsed | 28722 | +| total_timesteps | 39831552 | +| train/ | | +| approx_kl | 0.017000437 | +| clip_fraction | 0.401 | +| clip_range | 0.065 | +| entropy_loss | -5.75 | +| explained_variance | 0.53 | +| learning_rate | 4.05e-05 | +| loss | -0.0387 | +| n_updates | 93612 | +| policy_gradient_loss | -0.0211 | +| value_loss | 5.42e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1386 | +| iterations | 19450 | +| time_elapsed | 28724 | +| total_timesteps | 39833600 | +| train/ | | +| approx_kl | 0.013807645 | +| clip_fraction | 0.347 | +| clip_range | 0.065 | +| entropy_loss | -6.24 | +| explained_variance | 0.343 | +| learning_rate | 4.05e-05 | +| loss | -0.0291 | +| n_updates | 93616 | +| policy_gradient_loss | -0.018 | +| value_loss | 7.76e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1386 | +| iterations | 19451 | +| time_elapsed | 28725 | +| total_timesteps | 39835648 | +| train/ | | +| approx_kl | 0.010664202 | +| clip_fraction | 0.307 | +| clip_range | 0.065 | +| entropy_loss | -6.14 | +| explained_variance | 0.551 | +| learning_rate | 4.05e-05 | +| loss | -0.0285 | +| n_updates | 93620 | +| policy_gradient_loss | -0.0141 | +| value_loss | 0.000123 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1386 | +| iterations | 19452 | +| time_elapsed | 28727 | +| total_timesteps | 39837696 | +| train/ | | +| approx_kl | 0.011385506 | +| clip_fraction | 0.317 | +| clip_range | 0.065 | +| entropy_loss | -6.25 | +| explained_variance | 0.251 | +| learning_rate | 4.05e-05 | +| loss | -0.0226 | +| n_updates | 93624 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.00032 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1386 | +| iterations | 19453 | +| time_elapsed | 28728 | +| total_timesteps | 39839744 | +| train/ | | +| approx_kl | 0.009919561 | +| clip_fraction | 0.296 | +| clip_range | 0.065 | +| entropy_loss | -5.79 | +| explained_variance | 0.498 | +| learning_rate | 4.05e-05 | +| loss | -0.0249 | +| n_updates | 93628 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000175 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1386 | +| iterations | 19454 | +| time_elapsed | 28730 | +| total_timesteps | 39841792 | +| train/ | | +| approx_kl | 0.010911213 | +| clip_fraction | 0.309 | +| clip_range | 0.065 | +| entropy_loss | -5.83 | +| explained_variance | 0.44 | +| learning_rate | 4.05e-05 | +| loss | -0.024 | +| n_updates | 93632 | +| policy_gradient_loss | -0.0144 | +| value_loss | 0.000241 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1386 | +| iterations | 19455 | +| time_elapsed | 28731 | +| total_timesteps | 39843840 | +| train/ | | +| approx_kl | 0.01171805 | +| clip_fraction | 0.329 | +| clip_range | 0.065 | +| entropy_loss | -5.67 | +| explained_variance | 0.35 | +| learning_rate | 4.05e-05 | +| loss | -0.0277 | +| n_updates | 93636 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000229 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1386 | +| iterations | 19456 | +| time_elapsed | 28733 | +| total_timesteps | 39845888 | +| train/ | | +| approx_kl | 0.013655415 | +| clip_fraction | 0.371 | +| clip_range | 0.065 | +| entropy_loss | -5.06 | +| explained_variance | 0.489 | +| learning_rate | 4.05e-05 | +| loss | -0.0328 | +| n_updates | 93640 | +| policy_gradient_loss | -0.0203 | +| value_loss | 6.36e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1386 | +| iterations | 19457 | +| time_elapsed | 28734 | +| total_timesteps | 39847936 | +| train/ | | +| approx_kl | 0.014301948 | +| clip_fraction | 0.349 | +| clip_range | 0.065 | +| entropy_loss | -5.72 | +| explained_variance | 0.291 | +| learning_rate | 4.05e-05 | +| loss | -0.0274 | +| n_updates | 93644 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000179 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1386 | +| iterations | 19458 | +| time_elapsed | 28736 | +| total_timesteps | 39849984 | +| train/ | | +| approx_kl | 0.012257744 | +| clip_fraction | 0.334 | +| clip_range | 0.065 | +| entropy_loss | -6.07 | +| explained_variance | 0.289 | +| learning_rate | 4.05e-05 | +| loss | -0.0248 | +| n_updates | 93648 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000183 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1386 | +| iterations | 19459 | +| time_elapsed | 28738 | +| total_timesteps | 39852032 | +| train/ | | +| approx_kl | 0.012647442 | +| clip_fraction | 0.336 | +| clip_range | 0.065 | +| entropy_loss | -5.78 | +| explained_variance | 0.344 | +| learning_rate | 4.05e-05 | +| loss | -0.02 | +| n_updates | 93652 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000239 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1386 | +| iterations | 19460 | +| time_elapsed | 28739 | +| total_timesteps | 39854080 | +| train/ | | +| approx_kl | 0.019785203 | +| clip_fraction | 0.333 | +| clip_range | 0.065 | +| entropy_loss | -5.04 | +| explained_variance | 0.535 | +| learning_rate | 4.05e-05 | +| loss | -0.0282 | +| n_updates | 93656 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000254 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1386 | +| iterations | 19461 | +| time_elapsed | 28741 | +| total_timesteps | 39856128 | +| train/ | | +| approx_kl | 0.013849564 | +| clip_fraction | 0.353 | +| clip_range | 0.065 | +| entropy_loss | -5.26 | +| explained_variance | 0.23 | +| learning_rate | 4.05e-05 | +| loss | -0.0268 | +| n_updates | 93660 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000249 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1386 | +| iterations | 19462 | +| time_elapsed | 28742 | +| total_timesteps | 39858176 | +| train/ | | +| approx_kl | 0.012481645 | +| clip_fraction | 0.33 | +| clip_range | 0.065 | +| entropy_loss | -5.7 | +| explained_variance | 0.323 | +| learning_rate | 4.05e-05 | +| loss | -0.0211 | +| n_updates | 93664 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000285 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1386 | +| iterations | 19463 | +| time_elapsed | 28744 | +| total_timesteps | 39860224 | +| train/ | | +| approx_kl | 0.014504172 | +| clip_fraction | 0.363 | +| clip_range | 0.065 | +| entropy_loss | -5.47 | +| explained_variance | 0.427 | +| learning_rate | 4.05e-05 | +| loss | -0.034 | +| n_updates | 93668 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000132 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1386 | +| iterations | 19464 | +| time_elapsed | 28745 | +| total_timesteps | 39862272 | +| train/ | | +| approx_kl | 0.01498875 | +| clip_fraction | 0.329 | +| clip_range | 0.065 | +| entropy_loss | -6.1 | +| explained_variance | 0.389 | +| learning_rate | 4.05e-05 | +| loss | -0.0305 | +| n_updates | 93672 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000186 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1386 | +| iterations | 19465 | +| time_elapsed | 28747 | +| total_timesteps | 39864320 | +| train/ | | +| approx_kl | 0.013544375 | +| clip_fraction | 0.341 | +| clip_range | 0.065 | +| entropy_loss | -6.49 | +| explained_variance | -0.0921 | +| learning_rate | 4.05e-05 | +| loss | -0.0281 | +| n_updates | 93676 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000175 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1386 | +| iterations | 19466 | +| time_elapsed | 28748 | +| total_timesteps | 39866368 | +| train/ | | +| approx_kl | 0.012704998 | +| clip_fraction | 0.333 | +| clip_range | 0.065 | +| entropy_loss | -6.23 | +| explained_variance | 0.462 | +| learning_rate | 4.05e-05 | +| loss | -0.028 | +| n_updates | 93680 | +| policy_gradient_loss | -0.0191 | +| value_loss | 7.83e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1386 | +| iterations | 19467 | +| time_elapsed | 28750 | +| total_timesteps | 39868416 | +| train/ | | +| approx_kl | 0.012620562 | +| clip_fraction | 0.325 | +| clip_range | 0.065 | +| entropy_loss | -5.28 | +| explained_variance | 0.743 | +| learning_rate | 4.05e-05 | +| loss | -0.0275 | +| n_updates | 93684 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000107 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1386 | +| iterations | 19468 | +| time_elapsed | 28751 | +| total_timesteps | 39870464 | +| train/ | | +| approx_kl | 0.018778913 | +| clip_fraction | 0.363 | +| clip_range | 0.065 | +| entropy_loss | -5.5 | +| explained_variance | -0.164 | +| learning_rate | 4.05e-05 | +| loss | -0.0296 | +| n_updates | 93688 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000108 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1386 | +| iterations | 19469 | +| time_elapsed | 28753 | +| total_timesteps | 39872512 | +| train/ | | +| approx_kl | 0.01426744 | +| clip_fraction | 0.391 | +| clip_range | 0.065 | +| entropy_loss | -5.91 | +| explained_variance | 0.168 | +| learning_rate | 4.05e-05 | +| loss | -0.0249 | +| n_updates | 93692 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000103 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1386 | +| iterations | 19470 | +| time_elapsed | 28754 | +| total_timesteps | 39874560 | +| train/ | | +| approx_kl | 0.013928462 | +| clip_fraction | 0.303 | +| clip_range | 0.065 | +| entropy_loss | -5.88 | +| explained_variance | 0.386 | +| learning_rate | 4.05e-05 | +| loss | -0.0227 | +| n_updates | 93696 | +| policy_gradient_loss | -0.0145 | +| value_loss | 0.000242 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1386 | +| iterations | 19471 | +| time_elapsed | 28756 | +| total_timesteps | 39876608 | +| train/ | | +| approx_kl | 0.014778938 | +| clip_fraction | 0.357 | +| clip_range | 0.065 | +| entropy_loss | -5.57 | +| explained_variance | 0.643 | +| learning_rate | 4.05e-05 | +| loss | -0.0265 | +| n_updates | 93700 | +| policy_gradient_loss | -0.0203 | +| value_loss | 7.11e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1386 | +| iterations | 19472 | +| time_elapsed | 28758 | +| total_timesteps | 39878656 | +| train/ | | +| approx_kl | 0.014262989 | +| clip_fraction | 0.316 | +| clip_range | 0.065 | +| entropy_loss | -5.03 | +| explained_variance | 0.49 | +| learning_rate | 4.05e-05 | +| loss | -0.0261 | +| n_updates | 93704 | +| policy_gradient_loss | -0.0144 | +| value_loss | 0.000226 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1386 | +| iterations | 19473 | +| time_elapsed | 28759 | +| total_timesteps | 39880704 | +| train/ | | +| approx_kl | 0.013961192 | +| clip_fraction | 0.339 | +| clip_range | 0.065 | +| entropy_loss | -6.11 | +| explained_variance | 0.272 | +| learning_rate | 4.05e-05 | +| loss | -0.0308 | +| n_updates | 93708 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.00017 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1386 | +| iterations | 19474 | +| time_elapsed | 28761 | +| total_timesteps | 39882752 | +| train/ | | +| approx_kl | 0.014962463 | +| clip_fraction | 0.326 | +| clip_range | 0.065 | +| entropy_loss | -6.35 | +| explained_variance | 0.422 | +| learning_rate | 4.05e-05 | +| loss | -0.0282 | +| n_updates | 93712 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000203 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1386 | +| iterations | 19475 | +| time_elapsed | 28762 | +| total_timesteps | 39884800 | +| train/ | | +| approx_kl | 0.015362119 | +| clip_fraction | 0.356 | +| clip_range | 0.065 | +| entropy_loss | -5.39 | +| explained_variance | 0.601 | +| learning_rate | 4.05e-05 | +| loss | -0.0341 | +| n_updates | 93716 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000108 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1386 | +| iterations | 19476 | +| time_elapsed | 28764 | +| total_timesteps | 39886848 | +| train/ | | +| approx_kl | 0.0114399465 | +| clip_fraction | 0.344 | +| clip_range | 0.065 | +| entropy_loss | -5.7 | +| explained_variance | 0.29 | +| learning_rate | 4.05e-05 | +| loss | -0.0247 | +| n_updates | 93720 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000147 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1386 | +| iterations | 19477 | +| time_elapsed | 28765 | +| total_timesteps | 39888896 | +| train/ | | +| approx_kl | 0.009709617 | +| clip_fraction | 0.32 | +| clip_range | 0.065 | +| entropy_loss | -6.54 | +| explained_variance | 0.0401 | +| learning_rate | 4.05e-05 | +| loss | -0.0256 | +| n_updates | 93724 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000115 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1386 | +| iterations | 19478 | +| time_elapsed | 28767 | +| total_timesteps | 39890944 | +| train/ | | +| approx_kl | 0.013732446 | +| clip_fraction | 0.284 | +| clip_range | 0.065 | +| entropy_loss | -6 | +| explained_variance | 0.53 | +| learning_rate | 4.05e-05 | +| loss | -0.0235 | +| n_updates | 93728 | +| policy_gradient_loss | -0.0127 | +| value_loss | 0.000213 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1386 | +| iterations | 19479 | +| time_elapsed | 28768 | +| total_timesteps | 39892992 | +| train/ | | +| approx_kl | 0.013389107 | +| clip_fraction | 0.358 | +| clip_range | 0.065 | +| entropy_loss | -6.06 | +| explained_variance | 0.117 | +| learning_rate | 4.05e-05 | +| loss | -0.0271 | +| n_updates | 93732 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000153 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1386 | +| iterations | 19480 | +| time_elapsed | 28770 | +| total_timesteps | 39895040 | +| train/ | | +| approx_kl | 0.012859188 | +| clip_fraction | 0.341 | +| clip_range | 0.065 | +| entropy_loss | -6.04 | +| explained_variance | 0.418 | +| learning_rate | 4.05e-05 | +| loss | -0.0273 | +| n_updates | 93736 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000125 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1386 | +| iterations | 19481 | +| time_elapsed | 28771 | +| total_timesteps | 39897088 | +| train/ | | +| approx_kl | 0.011933759 | +| clip_fraction | 0.321 | +| clip_range | 0.065 | +| entropy_loss | -4.28 | +| explained_variance | 0.497 | +| learning_rate | 4.05e-05 | +| loss | -0.0182 | +| n_updates | 93740 | +| policy_gradient_loss | -0.0133 | +| value_loss | 0.000507 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1386 | +| iterations | 19482 | +| time_elapsed | 28773 | +| total_timesteps | 39899136 | +| train/ | | +| approx_kl | 0.017358225 | +| clip_fraction | 0.333 | +| clip_range | 0.065 | +| entropy_loss | -4.93 | +| explained_variance | 0.385 | +| learning_rate | 4.05e-05 | +| loss | -0.0272 | +| n_updates | 93744 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000203 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1386 | +| iterations | 19483 | +| time_elapsed | 28774 | +| total_timesteps | 39901184 | +| train/ | | +| approx_kl | 0.015852127 | +| clip_fraction | 0.371 | +| clip_range | 0.065 | +| entropy_loss | -5.8 | +| explained_variance | -0.344 | +| learning_rate | 4.05e-05 | +| loss | -0.0312 | +| n_updates | 93748 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000121 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1386 | +| iterations | 19484 | +| time_elapsed | 28776 | +| total_timesteps | 39903232 | +| train/ | | +| approx_kl | 0.012060782 | +| clip_fraction | 0.362 | +| clip_range | 0.065 | +| entropy_loss | -6.36 | +| explained_variance | -0.158 | +| learning_rate | 4.05e-05 | +| loss | -0.0318 | +| n_updates | 93752 | +| policy_gradient_loss | -0.0183 | +| value_loss | 9.74e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1386 | +| iterations | 19485 | +| time_elapsed | 28777 | +| total_timesteps | 39905280 | +| train/ | | +| approx_kl | 0.012013365 | +| clip_fraction | 0.323 | +| clip_range | 0.065 | +| entropy_loss | -6.45 | +| explained_variance | 0.288 | +| learning_rate | 4.05e-05 | +| loss | -0.0255 | +| n_updates | 93756 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000136 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1386 | +| iterations | 19486 | +| time_elapsed | 28779 | +| total_timesteps | 39907328 | +| train/ | | +| approx_kl | 0.01305824 | +| clip_fraction | 0.348 | +| clip_range | 0.065 | +| entropy_loss | -5.49 | +| explained_variance | 0.722 | +| learning_rate | 4.05e-05 | +| loss | -0.0263 | +| n_updates | 93760 | +| policy_gradient_loss | -0.0176 | +| value_loss | 9e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1386 | +| iterations | 19487 | +| time_elapsed | 28780 | +| total_timesteps | 39909376 | +| train/ | | +| approx_kl | 0.015439097 | +| clip_fraction | 0.345 | +| clip_range | 0.065 | +| entropy_loss | -5.78 | +| explained_variance | 0.402 | +| learning_rate | 4.05e-05 | +| loss | -0.0279 | +| n_updates | 93764 | +| policy_gradient_loss | -0.0177 | +| value_loss | 8.59e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1386 | +| iterations | 19488 | +| time_elapsed | 28782 | +| total_timesteps | 39911424 | +| train/ | | +| approx_kl | 0.01929485 | +| clip_fraction | 0.345 | +| clip_range | 0.065 | +| entropy_loss | -5.39 | +| explained_variance | 0.529 | +| learning_rate | 4.05e-05 | +| loss | -0.0275 | +| n_updates | 93768 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.00014 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1386 | +| iterations | 19489 | +| time_elapsed | 28783 | +| total_timesteps | 39913472 | +| train/ | | +| approx_kl | 0.012410486 | +| clip_fraction | 0.339 | +| clip_range | 0.065 | +| entropy_loss | -6.19 | +| explained_variance | 0.583 | +| learning_rate | 4.05e-05 | +| loss | -0.0261 | +| n_updates | 93772 | +| policy_gradient_loss | -0.016 | +| value_loss | 9.48e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1386 | +| iterations | 19490 | +| time_elapsed | 28785 | +| total_timesteps | 39915520 | +| train/ | | +| approx_kl | 0.01594877 | +| clip_fraction | 0.317 | +| clip_range | 0.065 | +| entropy_loss | -6.2 | +| explained_variance | 0.266 | +| learning_rate | 4.05e-05 | +| loss | -0.0206 | +| n_updates | 93776 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000228 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1386 | +| iterations | 19491 | +| time_elapsed | 28786 | +| total_timesteps | 39917568 | +| train/ | | +| approx_kl | 0.013349637 | +| clip_fraction | 0.322 | +| clip_range | 0.065 | +| entropy_loss | -5.51 | +| explained_variance | 0.605 | +| learning_rate | 4.05e-05 | +| loss | -0.0231 | +| n_updates | 93780 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000139 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1386 | +| iterations | 19492 | +| time_elapsed | 28788 | +| total_timesteps | 39919616 | +| train/ | | +| approx_kl | 0.018006265 | +| clip_fraction | 0.319 | +| clip_range | 0.065 | +| entropy_loss | -6.14 | +| explained_variance | -0.108 | +| learning_rate | 4.05e-05 | +| loss | -0.0305 | +| n_updates | 93784 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000149 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1386 | +| iterations | 19493 | +| time_elapsed | 28790 | +| total_timesteps | 39921664 | +| train/ | | +| approx_kl | 0.014004547 | +| clip_fraction | 0.325 | +| clip_range | 0.065 | +| entropy_loss | -5.87 | +| explained_variance | 0.504 | +| learning_rate | 4.05e-05 | +| loss | -0.0195 | +| n_updates | 93788 | +| policy_gradient_loss | -0.0143 | +| value_loss | 0.000175 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1386 | +| iterations | 19494 | +| time_elapsed | 28791 | +| total_timesteps | 39923712 | +| train/ | | +| approx_kl | 0.014559904 | +| clip_fraction | 0.338 | +| clip_range | 0.065 | +| entropy_loss | -5.63 | +| explained_variance | 0.246 | +| learning_rate | 4.05e-05 | +| loss | -0.0273 | +| n_updates | 93792 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000149 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1386 | +| iterations | 19495 | +| time_elapsed | 28793 | +| total_timesteps | 39925760 | +| train/ | | +| approx_kl | 0.012657649 | +| clip_fraction | 0.321 | +| clip_range | 0.065 | +| entropy_loss | -5.41 | +| explained_variance | 0.381 | +| learning_rate | 4.05e-05 | +| loss | -0.0214 | +| n_updates | 93796 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000347 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1386 | +| iterations | 19496 | +| time_elapsed | 28794 | +| total_timesteps | 39927808 | +| train/ | | +| approx_kl | 0.013212258 | +| clip_fraction | 0.336 | +| clip_range | 0.065 | +| entropy_loss | -5.72 | +| explained_variance | 0.21 | +| learning_rate | 4.05e-05 | +| loss | -0.0295 | +| n_updates | 93800 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000254 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1386 | +| iterations | 19497 | +| time_elapsed | 28796 | +| total_timesteps | 39929856 | +| train/ | | +| approx_kl | 0.016867034 | +| clip_fraction | 0.357 | +| clip_range | 0.065 | +| entropy_loss | -5.92 | +| explained_variance | 0.457 | +| learning_rate | 4.05e-05 | +| loss | -0.0316 | +| n_updates | 93804 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1386 | +| iterations | 19498 | +| time_elapsed | 28797 | +| total_timesteps | 39931904 | +| train/ | | +| approx_kl | 0.014184985 | +| clip_fraction | 0.335 | +| clip_range | 0.065 | +| entropy_loss | -5.74 | +| explained_variance | 0.489 | +| learning_rate | 4.05e-05 | +| loss | -0.0301 | +| n_updates | 93808 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000182 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1386 | +| iterations | 19499 | +| time_elapsed | 28799 | +| total_timesteps | 39933952 | +| train/ | | +| approx_kl | 0.012743763 | +| clip_fraction | 0.32 | +| clip_range | 0.065 | +| entropy_loss | -6.11 | +| explained_variance | 0.37 | +| learning_rate | 4.05e-05 | +| loss | -0.0333 | +| n_updates | 93812 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.00011 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1386 | +| iterations | 19500 | +| time_elapsed | 28800 | +| total_timesteps | 39936000 | +| train/ | | +| approx_kl | 0.015012737 | +| clip_fraction | 0.354 | +| clip_range | 0.065 | +| entropy_loss | -6.31 | +| explained_variance | -0.342 | +| learning_rate | 4.05e-05 | +| loss | -0.031 | +| n_updates | 93816 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000124 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1386 | +| iterations | 19501 | +| time_elapsed | 28802 | +| total_timesteps | 39938048 | +| train/ | | +| approx_kl | 0.010822415 | +| clip_fraction | 0.329 | +| clip_range | 0.065 | +| entropy_loss | -5.99 | +| explained_variance | 0.491 | +| learning_rate | 4.05e-05 | +| loss | -0.0235 | +| n_updates | 93820 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.000208 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1386 | +| iterations | 19502 | +| time_elapsed | 28803 | +| total_timesteps | 39940096 | +| train/ | | +| approx_kl | 0.012331116 | +| clip_fraction | 0.287 | +| clip_range | 0.065 | +| entropy_loss | -5.72 | +| explained_variance | 0.492 | +| learning_rate | 4.05e-05 | +| loss | -0.0297 | +| n_updates | 93824 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000119 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1386 | +| iterations | 19503 | +| time_elapsed | 28805 | +| total_timesteps | 39942144 | +| train/ | | +| approx_kl | 0.010903178 | +| clip_fraction | 0.308 | +| clip_range | 0.065 | +| entropy_loss | -6.09 | +| explained_variance | 0.276 | +| learning_rate | 4.05e-05 | +| loss | -0.0171 | +| n_updates | 93828 | +| policy_gradient_loss | -0.0127 | +| value_loss | 0.000348 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1386 | +| iterations | 19504 | +| time_elapsed | 28806 | +| total_timesteps | 39944192 | +| train/ | | +| approx_kl | 0.015338987 | +| clip_fraction | 0.314 | +| clip_range | 0.065 | +| entropy_loss | -6.09 | +| explained_variance | 0.669 | +| learning_rate | 4.05e-05 | +| loss | -0.0303 | +| n_updates | 93832 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.00011 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1386 | +| iterations | 19505 | +| time_elapsed | 28808 | +| total_timesteps | 39946240 | +| train/ | | +| approx_kl | 0.013547936 | +| clip_fraction | 0.327 | +| clip_range | 0.065 | +| entropy_loss | -6.09 | +| explained_variance | 0.505 | +| learning_rate | 4.05e-05 | +| loss | -0.03 | +| n_updates | 93836 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000142 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1386 | +| iterations | 19506 | +| time_elapsed | 28810 | +| total_timesteps | 39948288 | +| train/ | | +| approx_kl | 0.014180763 | +| clip_fraction | 0.321 | +| clip_range | 0.065 | +| entropy_loss | -6 | +| explained_variance | 0.289 | +| learning_rate | 4.05e-05 | +| loss | -0.024 | +| n_updates | 93840 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000157 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1386 | +| iterations | 19507 | +| time_elapsed | 28811 | +| total_timesteps | 39950336 | +| train/ | | +| approx_kl | 0.015291087 | +| clip_fraction | 0.326 | +| clip_range | 0.065 | +| entropy_loss | -6.57 | +| explained_variance | -0.168 | +| learning_rate | 4.05e-05 | +| loss | -0.0304 | +| n_updates | 93844 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000137 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1386 | +| iterations | 19508 | +| time_elapsed | 28813 | +| total_timesteps | 39952384 | +| train/ | | +| approx_kl | 0.009870324 | +| clip_fraction | 0.325 | +| clip_range | 0.065 | +| entropy_loss | -6.86 | +| explained_variance | 0.0439 | +| learning_rate | 4.05e-05 | +| loss | -0.0253 | +| n_updates | 93848 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000211 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1386 | +| iterations | 19509 | +| time_elapsed | 28814 | +| total_timesteps | 39954432 | +| train/ | | +| approx_kl | 0.009659547 | +| clip_fraction | 0.306 | +| clip_range | 0.065 | +| entropy_loss | -6.46 | +| explained_variance | 0.312 | +| learning_rate | 4.05e-05 | +| loss | -0.027 | +| n_updates | 93852 | +| policy_gradient_loss | -0.0146 | +| value_loss | 0.000284 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1386 | +| iterations | 19510 | +| time_elapsed | 28816 | +| total_timesteps | 39956480 | +| train/ | | +| approx_kl | 0.013111111 | +| clip_fraction | 0.297 | +| clip_range | 0.065 | +| entropy_loss | -5.93 | +| explained_variance | 0.419 | +| learning_rate | 4.05e-05 | +| loss | -0.0256 | +| n_updates | 93856 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000205 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1386 | +| iterations | 19511 | +| time_elapsed | 28817 | +| total_timesteps | 39958528 | +| train/ | | +| approx_kl | 0.0109852385 | +| clip_fraction | 0.342 | +| clip_range | 0.065 | +| entropy_loss | -6.07 | +| explained_variance | 0.476 | +| learning_rate | 4.05e-05 | +| loss | -0.027 | +| n_updates | 93860 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000107 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1386 | +| iterations | 19512 | +| time_elapsed | 28819 | +| total_timesteps | 39960576 | +| train/ | | +| approx_kl | 0.0110540185 | +| clip_fraction | 0.298 | +| clip_range | 0.065 | +| entropy_loss | -5.91 | +| explained_variance | 0.564 | +| learning_rate | 4.05e-05 | +| loss | -0.0244 | +| n_updates | 93864 | +| policy_gradient_loss | -0.013 | +| value_loss | 0.000179 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1386 | +| iterations | 19513 | +| time_elapsed | 28820 | +| total_timesteps | 39962624 | +| train/ | | +| approx_kl | 0.017546874 | +| clip_fraction | 0.347 | +| clip_range | 0.065 | +| entropy_loss | -5.24 | +| explained_variance | 0.585 | +| learning_rate | 4.05e-05 | +| loss | -0.0223 | +| n_updates | 93868 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000109 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1386 | +| iterations | 19514 | +| time_elapsed | 28822 | +| total_timesteps | 39964672 | +| train/ | | +| approx_kl | 0.015565912 | +| clip_fraction | 0.353 | +| clip_range | 0.065 | +| entropy_loss | -5.59 | +| explained_variance | 0.344 | +| learning_rate | 4.05e-05 | +| loss | -0.028 | +| n_updates | 93872 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000188 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1386 | +| iterations | 19515 | +| time_elapsed | 28823 | +| total_timesteps | 39966720 | +| train/ | | +| approx_kl | 0.015585514 | +| clip_fraction | 0.379 | +| clip_range | 0.065 | +| entropy_loss | -5.66 | +| explained_variance | 0.303 | +| learning_rate | 4.05e-05 | +| loss | -0.0289 | +| n_updates | 93876 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1386 | +| iterations | 19516 | +| time_elapsed | 28825 | +| total_timesteps | 39968768 | +| train/ | | +| approx_kl | 0.011084002 | +| clip_fraction | 0.331 | +| clip_range | 0.065 | +| entropy_loss | -6.65 | +| explained_variance | -0.0649 | +| learning_rate | 4.05e-05 | +| loss | -0.0232 | +| n_updates | 93880 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.00017 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1386 | +| iterations | 19517 | +| time_elapsed | 28827 | +| total_timesteps | 39970816 | +| train/ | | +| approx_kl | 0.012139362 | +| clip_fraction | 0.307 | +| clip_range | 0.065 | +| entropy_loss | -6.26 | +| explained_variance | 0.455 | +| learning_rate | 4.05e-05 | +| loss | -0.024 | +| n_updates | 93884 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000196 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1386 | +| iterations | 19518 | +| time_elapsed | 28828 | +| total_timesteps | 39972864 | +| train/ | | +| approx_kl | 0.012226447 | +| clip_fraction | 0.347 | +| clip_range | 0.065 | +| entropy_loss | -6.49 | +| explained_variance | 0.135 | +| learning_rate | 4.05e-05 | +| loss | -0.0275 | +| n_updates | 93888 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000162 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1386 | +| iterations | 19519 | +| time_elapsed | 28830 | +| total_timesteps | 39974912 | +| train/ | | +| approx_kl | 0.009890959 | +| clip_fraction | 0.286 | +| clip_range | 0.065 | +| entropy_loss | -6.36 | +| explained_variance | 0.298 | +| learning_rate | 4.05e-05 | +| loss | -0.0302 | +| n_updates | 93892 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000174 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1386 | +| iterations | 19520 | +| time_elapsed | 28831 | +| total_timesteps | 39976960 | +| train/ | | +| approx_kl | 0.01246024 | +| clip_fraction | 0.351 | +| clip_range | 0.065 | +| entropy_loss | -6.49 | +| explained_variance | -0.156 | +| learning_rate | 4.05e-05 | +| loss | -0.0331 | +| n_updates | 93896 | +| policy_gradient_loss | -0.0224 | +| value_loss | 5.53e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1386 | +| iterations | 19521 | +| time_elapsed | 28833 | +| total_timesteps | 39979008 | +| train/ | | +| approx_kl | 0.010527135 | +| clip_fraction | 0.3 | +| clip_range | 0.065 | +| entropy_loss | -5.3 | +| explained_variance | 0.501 | +| learning_rate | 4.05e-05 | +| loss | -0.0211 | +| n_updates | 93900 | +| policy_gradient_loss | -0.0132 | +| value_loss | 0.000403 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1386 | +| iterations | 19522 | +| time_elapsed | 28834 | +| total_timesteps | 39981056 | +| train/ | | +| approx_kl | 0.016229166 | +| clip_fraction | 0.334 | +| clip_range | 0.065 | +| entropy_loss | -5.34 | +| explained_variance | 0.385 | +| learning_rate | 4.05e-05 | +| loss | -0.0289 | +| n_updates | 93904 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000161 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1386 | +| iterations | 19523 | +| time_elapsed | 28836 | +| total_timesteps | 39983104 | +| train/ | | +| approx_kl | 0.013446298 | +| clip_fraction | 0.336 | +| clip_range | 0.065 | +| entropy_loss | -5.14 | +| explained_variance | 0.497 | +| learning_rate | 4.05e-05 | +| loss | -0.0232 | +| n_updates | 93908 | +| policy_gradient_loss | -0.014 | +| value_loss | 0.000282 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1386 | +| iterations | 19524 | +| time_elapsed | 28837 | +| total_timesteps | 39985152 | +| train/ | | +| approx_kl | 0.012979682 | +| clip_fraction | 0.335 | +| clip_range | 0.065 | +| entropy_loss | -5.77 | +| explained_variance | 0.536 | +| learning_rate | 4.05e-05 | +| loss | -0.0281 | +| n_updates | 93912 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000137 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1386 | +| iterations | 19525 | +| time_elapsed | 28839 | +| total_timesteps | 39987200 | +| train/ | | +| approx_kl | 0.017022274 | +| clip_fraction | 0.338 | +| clip_range | 0.065 | +| entropy_loss | -5.34 | +| explained_variance | 0.351 | +| learning_rate | 4.05e-05 | +| loss | -0.0297 | +| n_updates | 93916 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000252 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1386 | +| iterations | 19526 | +| time_elapsed | 28840 | +| total_timesteps | 39989248 | +| train/ | | +| approx_kl | 0.016740005 | +| clip_fraction | 0.35 | +| clip_range | 0.065 | +| entropy_loss | -6.17 | +| explained_variance | -0.146 | +| learning_rate | 4.05e-05 | +| loss | -0.0308 | +| n_updates | 93920 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000111 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1386 | +| iterations | 19527 | +| time_elapsed | 28842 | +| total_timesteps | 39991296 | +| train/ | | +| approx_kl | 0.0123826675 | +| clip_fraction | 0.364 | +| clip_range | 0.065 | +| entropy_loss | -6.46 | +| explained_variance | -0.51 | +| learning_rate | 4.05e-05 | +| loss | -0.0248 | +| n_updates | 93924 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.00013 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1386 | +| iterations | 19528 | +| time_elapsed | 28843 | +| total_timesteps | 39993344 | +| train/ | | +| approx_kl | 0.01437477 | +| clip_fraction | 0.354 | +| clip_range | 0.065 | +| entropy_loss | -5.82 | +| explained_variance | 0.4 | +| learning_rate | 4.05e-05 | +| loss | -0.0257 | +| n_updates | 93928 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000199 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1386 | +| iterations | 19529 | +| time_elapsed | 28845 | +| total_timesteps | 39995392 | +| train/ | | +| approx_kl | 0.01150612 | +| clip_fraction | 0.343 | +| clip_range | 0.065 | +| entropy_loss | -5.78 | +| explained_variance | 0.319 | +| learning_rate | 4.05e-05 | +| loss | -0.0222 | +| n_updates | 93932 | +| policy_gradient_loss | -0.0134 | +| value_loss | 0.000295 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1386 | +| iterations | 19530 | +| time_elapsed | 28846 | +| total_timesteps | 39997440 | +| train/ | | +| approx_kl | 0.012050698 | +| clip_fraction | 0.36 | +| clip_range | 0.065 | +| entropy_loss | -6.28 | +| explained_variance | 0.0651 | +| learning_rate | 4.05e-05 | +| loss | -0.027 | +| n_updates | 93936 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000135 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1386 | +| iterations | 19531 | +| time_elapsed | 28848 | +| total_timesteps | 39999488 | +| train/ | | +| approx_kl | 0.011846465 | +| clip_fraction | 0.344 | +| clip_range | 0.065 | +| entropy_loss | -5.77 | +| explained_variance | 0.512 | +| learning_rate | 4.05e-05 | +| loss | -0.0299 | +| n_updates | 93940 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000136 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1386 | +| iterations | 19532 | +| time_elapsed | 28849 | +| total_timesteps | 40001536 | +| train/ | | +| approx_kl | 0.012133168 | +| clip_fraction | 0.356 | +| clip_range | 0.065 | +| entropy_loss | -5.84 | +| explained_variance | -0.383 | +| learning_rate | 4.05e-05 | +| loss | -0.0342 | +| n_updates | 93944 | +| policy_gradient_loss | -0.0187 | +| value_loss | 5.8e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1386 | +| iterations | 19533 | +| time_elapsed | 28851 | +| total_timesteps | 40003584 | +| train/ | | +| approx_kl | 0.012012841 | +| clip_fraction | 0.321 | +| clip_range | 0.065 | +| entropy_loss | -5.74 | +| explained_variance | 0.716 | +| learning_rate | 4.05e-05 | +| loss | -0.0261 | +| n_updates | 93948 | +| policy_gradient_loss | -0.0164 | +| value_loss | 7.26e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1386 | +| iterations | 19534 | +| time_elapsed | 28853 | +| total_timesteps | 40005632 | +| train/ | | +| approx_kl | 0.014423126 | +| clip_fraction | 0.357 | +| clip_range | 0.065 | +| entropy_loss | -5.87 | +| explained_variance | -0.139 | +| learning_rate | 4.05e-05 | +| loss | -0.0339 | +| n_updates | 93952 | +| policy_gradient_loss | -0.0199 | +| value_loss | 6.33e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1386 | +| iterations | 19535 | +| time_elapsed | 28854 | +| total_timesteps | 40007680 | +| train/ | | +| approx_kl | 0.012918147 | +| clip_fraction | 0.31 | +| clip_range | 0.065 | +| entropy_loss | -6.13 | +| explained_variance | 0.426 | +| learning_rate | 4.05e-05 | +| loss | -0.0275 | +| n_updates | 93956 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000129 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1386 | +| iterations | 19536 | +| time_elapsed | 28856 | +| total_timesteps | 40009728 | +| train/ | | +| approx_kl | 0.008171609 | +| clip_fraction | 0.274 | +| clip_range | 0.065 | +| entropy_loss | -5.77 | +| explained_variance | 0.47 | +| learning_rate | 4.05e-05 | +| loss | -0.017 | +| n_updates | 93960 | +| policy_gradient_loss | -0.0124 | +| value_loss | 0.0003 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1386 | +| iterations | 19537 | +| time_elapsed | 28857 | +| total_timesteps | 40011776 | +| train/ | | +| approx_kl | 0.012748852 | +| clip_fraction | 0.305 | +| clip_range | 0.065 | +| entropy_loss | -5.56 | +| explained_variance | 0.518 | +| learning_rate | 4.05e-05 | +| loss | -0.0272 | +| n_updates | 93964 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000199 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1386 | +| iterations | 19538 | +| time_elapsed | 28859 | +| total_timesteps | 40013824 | +| train/ | | +| approx_kl | 0.012856178 | +| clip_fraction | 0.33 | +| clip_range | 0.065 | +| entropy_loss | -5.53 | +| explained_variance | 0.772 | +| learning_rate | 4.05e-05 | +| loss | -0.0301 | +| n_updates | 93968 | +| policy_gradient_loss | -0.0179 | +| value_loss | 7.63e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1386 | +| iterations | 19539 | +| time_elapsed | 28860 | +| total_timesteps | 40015872 | +| train/ | | +| approx_kl | 0.011919828 | +| clip_fraction | 0.314 | +| clip_range | 0.065 | +| entropy_loss | -5.75 | +| explained_variance | 0.494 | +| learning_rate | 4.05e-05 | +| loss | -0.0275 | +| n_updates | 93972 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000155 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1386 | +| iterations | 19540 | +| time_elapsed | 28862 | +| total_timesteps | 40017920 | +| train/ | | +| approx_kl | 0.011967718 | +| clip_fraction | 0.314 | +| clip_range | 0.065 | +| entropy_loss | -5.39 | +| explained_variance | 0.514 | +| learning_rate | 4.05e-05 | +| loss | -0.0257 | +| n_updates | 93976 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000163 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1386 | +| iterations | 19541 | +| time_elapsed | 28864 | +| total_timesteps | 40019968 | +| train/ | | +| approx_kl | 0.014993066 | +| clip_fraction | 0.358 | +| clip_range | 0.065 | +| entropy_loss | -6.34 | +| explained_variance | -0.148 | +| learning_rate | 4.05e-05 | +| loss | -0.035 | +| n_updates | 93980 | +| policy_gradient_loss | -0.0215 | +| value_loss | 8.44e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1386 | +| iterations | 19542 | +| time_elapsed | 28865 | +| total_timesteps | 40022016 | +| train/ | | +| approx_kl | 0.010523044 | +| clip_fraction | 0.342 | +| clip_range | 0.065 | +| entropy_loss | -6.39 | +| explained_variance | 0.191 | +| learning_rate | 4.05e-05 | +| loss | -0.0281 | +| n_updates | 93984 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000199 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1386 | +| iterations | 19543 | +| time_elapsed | 28867 | +| total_timesteps | 40024064 | +| train/ | | +| approx_kl | 0.010812999 | +| clip_fraction | 0.319 | +| clip_range | 0.065 | +| entropy_loss | -5.63 | +| explained_variance | 0.188 | +| learning_rate | 4.05e-05 | +| loss | -0.0256 | +| n_updates | 93988 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.00032 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1386 | +| iterations | 19544 | +| time_elapsed | 28868 | +| total_timesteps | 40026112 | +| train/ | | +| approx_kl | 0.009406926 | +| clip_fraction | 0.317 | +| clip_range | 0.065 | +| entropy_loss | -4.92 | +| explained_variance | 0.435 | +| learning_rate | 4.05e-05 | +| loss | -0.0195 | +| n_updates | 93992 | +| policy_gradient_loss | -0.0125 | +| value_loss | 0.000414 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1386 | +| iterations | 19545 | +| time_elapsed | 28870 | +| total_timesteps | 40028160 | +| train/ | | +| approx_kl | 0.012388234 | +| clip_fraction | 0.363 | +| clip_range | 0.065 | +| entropy_loss | -5.5 | +| explained_variance | 0.603 | +| learning_rate | 4.05e-05 | +| loss | -0.0323 | +| n_updates | 93996 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000135 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1386 | +| iterations | 19546 | +| time_elapsed | 28871 | +| total_timesteps | 40030208 | +| train/ | | +| approx_kl | 0.011143792 | +| clip_fraction | 0.331 | +| clip_range | 0.065 | +| entropy_loss | -6.11 | +| explained_variance | 0.218 | +| learning_rate | 4.05e-05 | +| loss | -0.0294 | +| n_updates | 94000 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000275 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1386 | +| iterations | 19547 | +| time_elapsed | 28873 | +| total_timesteps | 40032256 | +| train/ | | +| approx_kl | 0.013991769 | +| clip_fraction | 0.328 | +| clip_range | 0.065 | +| entropy_loss | -5.52 | +| explained_variance | 0.44 | +| learning_rate | 4.05e-05 | +| loss | -0.0288 | +| n_updates | 94004 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000158 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1386 | +| iterations | 19548 | +| time_elapsed | 28874 | +| total_timesteps | 40034304 | +| train/ | | +| approx_kl | 0.012207443 | +| clip_fraction | 0.348 | +| clip_range | 0.065 | +| entropy_loss | -5.95 | +| explained_variance | 0.0431 | +| learning_rate | 4.05e-05 | +| loss | -0.0311 | +| n_updates | 94008 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000332 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1386 | +| iterations | 19549 | +| time_elapsed | 28876 | +| total_timesteps | 40036352 | +| train/ | | +| approx_kl | 0.017058015 | +| clip_fraction | 0.369 | +| clip_range | 0.065 | +| entropy_loss | -6.05 | +| explained_variance | 0.317 | +| learning_rate | 4.05e-05 | +| loss | -0.0289 | +| n_updates | 94012 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000107 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1386 | +| iterations | 19550 | +| time_elapsed | 28877 | +| total_timesteps | 40038400 | +| train/ | | +| approx_kl | 0.01406635 | +| clip_fraction | 0.346 | +| clip_range | 0.065 | +| entropy_loss | -6.1 | +| explained_variance | 0.387 | +| learning_rate | 4.05e-05 | +| loss | -0.0258 | +| n_updates | 94016 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000129 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1386 | +| iterations | 19551 | +| time_elapsed | 28879 | +| total_timesteps | 40040448 | +| train/ | | +| approx_kl | 0.014005209 | +| clip_fraction | 0.345 | +| clip_range | 0.065 | +| entropy_loss | -5.6 | +| explained_variance | 0.576 | +| learning_rate | 4.05e-05 | +| loss | -0.0321 | +| n_updates | 94020 | +| policy_gradient_loss | -0.0181 | +| value_loss | 9.84e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1386 | +| iterations | 19552 | +| time_elapsed | 28881 | +| total_timesteps | 40042496 | +| train/ | | +| approx_kl | 0.012073876 | +| clip_fraction | 0.318 | +| clip_range | 0.065 | +| entropy_loss | -5.56 | +| explained_variance | 0.497 | +| learning_rate | 4.05e-05 | +| loss | -0.0229 | +| n_updates | 94024 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000224 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1386 | +| iterations | 19553 | +| time_elapsed | 28882 | +| total_timesteps | 40044544 | +| train/ | | +| approx_kl | 0.01121228 | +| clip_fraction | 0.322 | +| clip_range | 0.065 | +| entropy_loss | -5.81 | +| explained_variance | 0.567 | +| learning_rate | 4.05e-05 | +| loss | -0.0341 | +| n_updates | 94028 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000155 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1386 | +| iterations | 19554 | +| time_elapsed | 28884 | +| total_timesteps | 40046592 | +| train/ | | +| approx_kl | 0.0120436475 | +| clip_fraction | 0.341 | +| clip_range | 0.065 | +| entropy_loss | -5.88 | +| explained_variance | 0.299 | +| learning_rate | 4.05e-05 | +| loss | -0.0273 | +| n_updates | 94032 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000186 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1386 | +| iterations | 19555 | +| time_elapsed | 28885 | +| total_timesteps | 40048640 | +| train/ | | +| approx_kl | 0.011160474 | +| clip_fraction | 0.34 | +| clip_range | 0.065 | +| entropy_loss | -6.36 | +| explained_variance | 0.354 | +| learning_rate | 4.05e-05 | +| loss | -0.0346 | +| n_updates | 94036 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000115 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1386 | +| iterations | 19556 | +| time_elapsed | 28887 | +| total_timesteps | 40050688 | +| train/ | | +| approx_kl | 0.01134784 | +| clip_fraction | 0.303 | +| clip_range | 0.065 | +| entropy_loss | -5.97 | +| explained_variance | 0.502 | +| learning_rate | 4.05e-05 | +| loss | -0.0238 | +| n_updates | 94040 | +| policy_gradient_loss | -0.0143 | +| value_loss | 0.000193 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1386 | +| iterations | 19557 | +| time_elapsed | 28888 | +| total_timesteps | 40052736 | +| train/ | | +| approx_kl | 0.012595509 | +| clip_fraction | 0.354 | +| clip_range | 0.065 | +| entropy_loss | -6.17 | +| explained_variance | 0.516 | +| learning_rate | 4.05e-05 | +| loss | -0.0328 | +| n_updates | 94044 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000107 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1386 | +| iterations | 19558 | +| time_elapsed | 28890 | +| total_timesteps | 40054784 | +| train/ | | +| approx_kl | 0.011395263 | +| clip_fraction | 0.327 | +| clip_range | 0.065 | +| entropy_loss | -5.77 | +| explained_variance | 0.537 | +| learning_rate | 4.05e-05 | +| loss | -0.0274 | +| n_updates | 94048 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.00012 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1386 | +| iterations | 19559 | +| time_elapsed | 28891 | +| total_timesteps | 40056832 | +| train/ | | +| approx_kl | 0.011468933 | +| clip_fraction | 0.348 | +| clip_range | 0.065 | +| entropy_loss | -6.19 | +| explained_variance | 0.409 | +| learning_rate | 4.05e-05 | +| loss | -0.0318 | +| n_updates | 94052 | +| policy_gradient_loss | -0.0194 | +| value_loss | 7.33e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1386 | +| iterations | 19560 | +| time_elapsed | 28893 | +| total_timesteps | 40058880 | +| train/ | | +| approx_kl | 0.013401689 | +| clip_fraction | 0.329 | +| clip_range | 0.065 | +| entropy_loss | -6.22 | +| explained_variance | 0.28 | +| learning_rate | 4.05e-05 | +| loss | -0.0324 | +| n_updates | 94056 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.00012 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1386 | +| iterations | 19561 | +| time_elapsed | 28894 | +| total_timesteps | 40060928 | +| train/ | | +| approx_kl | 0.008756271 | +| clip_fraction | 0.296 | +| clip_range | 0.065 | +| entropy_loss | -6.09 | +| explained_variance | 0.37 | +| learning_rate | 4.05e-05 | +| loss | -0.0258 | +| n_updates | 94060 | +| policy_gradient_loss | -0.0144 | +| value_loss | 0.00021 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1386 | +| iterations | 19562 | +| time_elapsed | 28896 | +| total_timesteps | 40062976 | +| train/ | | +| approx_kl | 0.013355754 | +| clip_fraction | 0.291 | +| clip_range | 0.065 | +| entropy_loss | -5.9 | +| explained_variance | 0.565 | +| learning_rate | 4.05e-05 | +| loss | -0.0234 | +| n_updates | 94064 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000111 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1386 | +| iterations | 19563 | +| time_elapsed | 28897 | +| total_timesteps | 40065024 | +| train/ | | +| approx_kl | 0.013701843 | +| clip_fraction | 0.344 | +| clip_range | 0.065 | +| entropy_loss | -5.53 | +| explained_variance | 0.571 | +| learning_rate | 4.05e-05 | +| loss | -0.025 | +| n_updates | 94068 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000103 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1386 | +| iterations | 19564 | +| time_elapsed | 28899 | +| total_timesteps | 40067072 | +| train/ | | +| approx_kl | 0.014118513 | +| clip_fraction | 0.381 | +| clip_range | 0.065 | +| entropy_loss | -5.16 | +| explained_variance | 0.79 | +| learning_rate | 4.05e-05 | +| loss | -0.0337 | +| n_updates | 94072 | +| policy_gradient_loss | -0.0198 | +| value_loss | 4.84e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1386 | +| iterations | 19565 | +| time_elapsed | 28900 | +| total_timesteps | 40069120 | +| train/ | | +| approx_kl | 0.011704052 | +| clip_fraction | 0.313 | +| clip_range | 0.065 | +| entropy_loss | -6.27 | +| explained_variance | 0.312 | +| learning_rate | 4.05e-05 | +| loss | -0.0257 | +| n_updates | 94076 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000143 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1386 | +| iterations | 19566 | +| time_elapsed | 28902 | +| total_timesteps | 40071168 | +| train/ | | +| approx_kl | 0.010757956 | +| clip_fraction | 0.323 | +| clip_range | 0.065 | +| entropy_loss | -6.45 | +| explained_variance | 0.0923 | +| learning_rate | 4.05e-05 | +| loss | -0.0271 | +| n_updates | 94080 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1386 | +| iterations | 19567 | +| time_elapsed | 28904 | +| total_timesteps | 40073216 | +| train/ | | +| approx_kl | 0.014732736 | +| clip_fraction | 0.31 | +| clip_range | 0.065 | +| entropy_loss | -6.32 | +| explained_variance | 0.27 | +| learning_rate | 4.05e-05 | +| loss | -0.0262 | +| n_updates | 94084 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000152 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1386 | +| iterations | 19568 | +| time_elapsed | 28905 | +| total_timesteps | 40075264 | +| train/ | | +| approx_kl | 0.009978792 | +| clip_fraction | 0.322 | +| clip_range | 0.065 | +| entropy_loss | -6.06 | +| explained_variance | 0.117 | +| learning_rate | 4.05e-05 | +| loss | -0.0287 | +| n_updates | 94088 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000338 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1386 | +| iterations | 19569 | +| time_elapsed | 28907 | +| total_timesteps | 40077312 | +| train/ | | +| approx_kl | 0.012455617 | +| clip_fraction | 0.311 | +| clip_range | 0.065 | +| entropy_loss | -5.87 | +| explained_variance | 0.243 | +| learning_rate | 4.05e-05 | +| loss | -0.0183 | +| n_updates | 94092 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.000431 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1386 | +| iterations | 19570 | +| time_elapsed | 28908 | +| total_timesteps | 40079360 | +| train/ | | +| approx_kl | 0.013523123 | +| clip_fraction | 0.361 | +| clip_range | 0.065 | +| entropy_loss | -5.01 | +| explained_variance | 0.554 | +| learning_rate | 4.05e-05 | +| loss | -0.0247 | +| n_updates | 94096 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000167 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1386 | +| iterations | 19571 | +| time_elapsed | 28910 | +| total_timesteps | 40081408 | +| train/ | | +| approx_kl | 0.014901873 | +| clip_fraction | 0.354 | +| clip_range | 0.065 | +| entropy_loss | -5.25 | +| explained_variance | 0.541 | +| learning_rate | 4.05e-05 | +| loss | -0.0276 | +| n_updates | 94100 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000173 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1386 | +| iterations | 19572 | +| time_elapsed | 28911 | +| total_timesteps | 40083456 | +| train/ | | +| approx_kl | 0.013753759 | +| clip_fraction | 0.345 | +| clip_range | 0.065 | +| entropy_loss | -5.59 | +| explained_variance | 0.252 | +| learning_rate | 4.05e-05 | +| loss | -0.0264 | +| n_updates | 94104 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000146 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1386 | +| iterations | 19573 | +| time_elapsed | 28913 | +| total_timesteps | 40085504 | +| train/ | | +| approx_kl | 0.012749087 | +| clip_fraction | 0.36 | +| clip_range | 0.065 | +| entropy_loss | -6.26 | +| explained_variance | -0.0953 | +| learning_rate | 4.05e-05 | +| loss | -0.0325 | +| n_updates | 94108 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000102 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1386 | +| iterations | 19574 | +| time_elapsed | 28914 | +| total_timesteps | 40087552 | +| train/ | | +| approx_kl | 0.013157319 | +| clip_fraction | 0.342 | +| clip_range | 0.065 | +| entropy_loss | -6.13 | +| explained_variance | 0.448 | +| learning_rate | 4.05e-05 | +| loss | -0.0275 | +| n_updates | 94112 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000121 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1386 | +| iterations | 19575 | +| time_elapsed | 28916 | +| total_timesteps | 40089600 | +| train/ | | +| approx_kl | 0.01684907 | +| clip_fraction | 0.351 | +| clip_range | 0.065 | +| entropy_loss | -5.6 | +| explained_variance | 0.531 | +| learning_rate | 4.05e-05 | +| loss | -0.0274 | +| n_updates | 94116 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000134 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1386 | +| iterations | 19576 | +| time_elapsed | 28917 | +| total_timesteps | 40091648 | +| train/ | | +| approx_kl | 0.013590879 | +| clip_fraction | 0.34 | +| clip_range | 0.065 | +| entropy_loss | -5.41 | +| explained_variance | 0.359 | +| learning_rate | 4.05e-05 | +| loss | -0.021 | +| n_updates | 94120 | +| policy_gradient_loss | -0.014 | +| value_loss | 0.000228 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1386 | +| iterations | 19577 | +| time_elapsed | 28919 | +| total_timesteps | 40093696 | +| train/ | | +| approx_kl | 0.012194924 | +| clip_fraction | 0.292 | +| clip_range | 0.065 | +| entropy_loss | -5.94 | +| explained_variance | 0.272 | +| learning_rate | 4.05e-05 | +| loss | -0.0247 | +| n_updates | 94124 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000243 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1386 | +| iterations | 19578 | +| time_elapsed | 28920 | +| total_timesteps | 40095744 | +| train/ | | +| approx_kl | 0.01393353 | +| clip_fraction | 0.337 | +| clip_range | 0.065 | +| entropy_loss | -5.73 | +| explained_variance | 0.348 | +| learning_rate | 4.05e-05 | +| loss | -0.0329 | +| n_updates | 94128 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.00015 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1386 | +| iterations | 19579 | +| time_elapsed | 28922 | +| total_timesteps | 40097792 | +| train/ | | +| approx_kl | 0.012124674 | +| clip_fraction | 0.341 | +| clip_range | 0.065 | +| entropy_loss | -5.74 | +| explained_variance | -0.0589 | +| learning_rate | 4.05e-05 | +| loss | -0.0214 | +| n_updates | 94132 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000194 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1386 | +| iterations | 19580 | +| time_elapsed | 28924 | +| total_timesteps | 40099840 | +| train/ | | +| approx_kl | 0.013415849 | +| clip_fraction | 0.344 | +| clip_range | 0.065 | +| entropy_loss | -6.02 | +| explained_variance | 0.549 | +| learning_rate | 4.05e-05 | +| loss | -0.0211 | +| n_updates | 94136 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000141 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1386 | +| iterations | 19581 | +| time_elapsed | 28925 | +| total_timesteps | 40101888 | +| train/ | | +| approx_kl | 0.009617332 | +| clip_fraction | 0.298 | +| clip_range | 0.065 | +| entropy_loss | -4.88 | +| explained_variance | 0.449 | +| learning_rate | 4.05e-05 | +| loss | -0.0203 | +| n_updates | 94140 | +| policy_gradient_loss | -0.0119 | +| value_loss | 0.000421 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1386 | +| iterations | 19582 | +| time_elapsed | 28927 | +| total_timesteps | 40103936 | +| train/ | | +| approx_kl | 0.014747789 | +| clip_fraction | 0.331 | +| clip_range | 0.065 | +| entropy_loss | -4.92 | +| explained_variance | 0.384 | +| learning_rate | 4.05e-05 | +| loss | -0.0293 | +| n_updates | 94144 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000184 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1386 | +| iterations | 19583 | +| time_elapsed | 28928 | +| total_timesteps | 40105984 | +| train/ | | +| approx_kl | 0.0112286005 | +| clip_fraction | 0.349 | +| clip_range | 0.065 | +| entropy_loss | -5.93 | +| explained_variance | 0.222 | +| learning_rate | 4.05e-05 | +| loss | -0.0281 | +| n_updates | 94148 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000114 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1386 | +| iterations | 19584 | +| time_elapsed | 28930 | +| total_timesteps | 40108032 | +| train/ | | +| approx_kl | 0.014472093 | +| clip_fraction | 0.328 | +| clip_range | 0.065 | +| entropy_loss | -5.93 | +| explained_variance | 0.315 | +| learning_rate | 4.05e-05 | +| loss | -0.0279 | +| n_updates | 94152 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000278 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1386 | +| iterations | 19585 | +| time_elapsed | 28931 | +| total_timesteps | 40110080 | +| train/ | | +| approx_kl | 0.013848921 | +| clip_fraction | 0.351 | +| clip_range | 0.065 | +| entropy_loss | -5.64 | +| explained_variance | 0.244 | +| learning_rate | 4.05e-05 | +| loss | -0.0287 | +| n_updates | 94156 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000157 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1386 | +| iterations | 19586 | +| time_elapsed | 28933 | +| total_timesteps | 40112128 | +| train/ | | +| approx_kl | 0.012166271 | +| clip_fraction | 0.331 | +| clip_range | 0.065 | +| entropy_loss | -5.78 | +| explained_variance | 0.191 | +| learning_rate | 4.05e-05 | +| loss | -0.0225 | +| n_updates | 94160 | +| policy_gradient_loss | -0.0142 | +| value_loss | 0.000441 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1386 | +| iterations | 19587 | +| time_elapsed | 28934 | +| total_timesteps | 40114176 | +| train/ | | +| approx_kl | 0.012482982 | +| clip_fraction | 0.349 | +| clip_range | 0.065 | +| entropy_loss | -5.69 | +| explained_variance | 0.235 | +| learning_rate | 4.05e-05 | +| loss | -0.029 | +| n_updates | 94164 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000212 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1386 | +| iterations | 19588 | +| time_elapsed | 28936 | +| total_timesteps | 40116224 | +| train/ | | +| approx_kl | 0.014160529 | +| clip_fraction | 0.377 | +| clip_range | 0.065 | +| entropy_loss | -5.54 | +| explained_variance | 0.627 | +| learning_rate | 4.05e-05 | +| loss | -0.0393 | +| n_updates | 94168 | +| policy_gradient_loss | -0.0219 | +| value_loss | 7.51e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1386 | +| iterations | 19589 | +| time_elapsed | 28937 | +| total_timesteps | 40118272 | +| train/ | | +| approx_kl | 0.016936451 | +| clip_fraction | 0.325 | +| clip_range | 0.065 | +| entropy_loss | -5.73 | +| explained_variance | 0.259 | +| learning_rate | 4.05e-05 | +| loss | -0.0235 | +| n_updates | 94172 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000253 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1386 | +| iterations | 19590 | +| time_elapsed | 28939 | +| total_timesteps | 40120320 | +| train/ | | +| approx_kl | 0.012169031 | +| clip_fraction | 0.344 | +| clip_range | 0.065 | +| entropy_loss | -5.68 | +| explained_variance | 0.258 | +| learning_rate | 4.05e-05 | +| loss | -0.0267 | +| n_updates | 94176 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1386 | +| iterations | 19591 | +| time_elapsed | 28940 | +| total_timesteps | 40122368 | +| train/ | | +| approx_kl | 0.011692911 | +| clip_fraction | 0.33 | +| clip_range | 0.065 | +| entropy_loss | -5.72 | +| explained_variance | 0.343 | +| learning_rate | 4.05e-05 | +| loss | -0.0313 | +| n_updates | 94180 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.00014 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1386 | +| iterations | 19592 | +| time_elapsed | 28942 | +| total_timesteps | 40124416 | +| train/ | | +| approx_kl | 0.014852378 | +| clip_fraction | 0.331 | +| clip_range | 0.065 | +| entropy_loss | -6.27 | +| explained_variance | 0.0908 | +| learning_rate | 4.05e-05 | +| loss | -0.0291 | +| n_updates | 94184 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000202 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1386 | +| iterations | 19593 | +| time_elapsed | 28943 | +| total_timesteps | 40126464 | +| train/ | | +| approx_kl | 0.013425879 | +| clip_fraction | 0.355 | +| clip_range | 0.065 | +| entropy_loss | -6.37 | +| explained_variance | -0.0733 | +| learning_rate | 4.05e-05 | +| loss | -0.0255 | +| n_updates | 94188 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000106 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1386 | +| iterations | 19594 | +| time_elapsed | 28945 | +| total_timesteps | 40128512 | +| train/ | | +| approx_kl | 0.011203377 | +| clip_fraction | 0.351 | +| clip_range | 0.065 | +| entropy_loss | -6.35 | +| explained_variance | -0.102 | +| learning_rate | 4.05e-05 | +| loss | -0.029 | +| n_updates | 94192 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000105 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1386 | +| iterations | 19595 | +| time_elapsed | 28946 | +| total_timesteps | 40130560 | +| train/ | | +| approx_kl | 0.00999378 | +| clip_fraction | 0.329 | +| clip_range | 0.065 | +| entropy_loss | -5.85 | +| explained_variance | 0.483 | +| learning_rate | 4.05e-05 | +| loss | -0.0222 | +| n_updates | 94196 | +| policy_gradient_loss | -0.0141 | +| value_loss | 0.000207 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1386 | +| iterations | 19596 | +| time_elapsed | 28948 | +| total_timesteps | 40132608 | +| train/ | | +| approx_kl | 0.014023596 | +| clip_fraction | 0.323 | +| clip_range | 0.065 | +| entropy_loss | -5.08 | +| explained_variance | 0.685 | +| learning_rate | 4.05e-05 | +| loss | -0.0304 | +| n_updates | 94200 | +| policy_gradient_loss | -0.0175 | +| value_loss | 8.02e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1386 | +| iterations | 19597 | +| time_elapsed | 28949 | +| total_timesteps | 40134656 | +| train/ | | +| approx_kl | 0.013964316 | +| clip_fraction | 0.358 | +| clip_range | 0.065 | +| entropy_loss | -5.33 | +| explained_variance | 0.571 | +| learning_rate | 4.05e-05 | +| loss | -0.0284 | +| n_updates | 94204 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.00012 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1386 | +| iterations | 19598 | +| time_elapsed | 28951 | +| total_timesteps | 40136704 | +| train/ | | +| approx_kl | 0.016742896 | +| clip_fraction | 0.358 | +| clip_range | 0.065 | +| entropy_loss | -5.56 | +| explained_variance | 0.227 | +| learning_rate | 4.05e-05 | +| loss | -0.0247 | +| n_updates | 94208 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000454 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1386 | +| iterations | 19599 | +| time_elapsed | 28952 | +| total_timesteps | 40138752 | +| train/ | | +| approx_kl | 0.01579174 | +| clip_fraction | 0.377 | +| clip_range | 0.065 | +| entropy_loss | -5.29 | +| explained_variance | 0.318 | +| learning_rate | 4.05e-05 | +| loss | -0.0315 | +| n_updates | 94212 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000154 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1386 | +| iterations | 19600 | +| time_elapsed | 28954 | +| total_timesteps | 40140800 | +| train/ | | +| approx_kl | 0.016280409 | +| clip_fraction | 0.359 | +| clip_range | 0.065 | +| entropy_loss | -5.9 | +| explained_variance | 0.22 | +| learning_rate | 4.05e-05 | +| loss | -0.0338 | +| n_updates | 94216 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000182 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1386 | +| iterations | 19601 | +| time_elapsed | 28956 | +| total_timesteps | 40142848 | +| train/ | | +| approx_kl | 0.012242528 | +| clip_fraction | 0.331 | +| clip_range | 0.065 | +| entropy_loss | -5.88 | +| explained_variance | 0.331 | +| learning_rate | 4.05e-05 | +| loss | -0.0271 | +| n_updates | 94220 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000123 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1386 | +| iterations | 19602 | +| time_elapsed | 28957 | +| total_timesteps | 40144896 | +| train/ | | +| approx_kl | 0.012934165 | +| clip_fraction | 0.365 | +| clip_range | 0.065 | +| entropy_loss | -5.9 | +| explained_variance | 0.205 | +| learning_rate | 4.05e-05 | +| loss | -0.0266 | +| n_updates | 94224 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000102 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1386 | +| iterations | 19603 | +| time_elapsed | 28959 | +| total_timesteps | 40146944 | +| train/ | | +| approx_kl | 0.01522262 | +| clip_fraction | 0.369 | +| clip_range | 0.065 | +| entropy_loss | -5.25 | +| explained_variance | 0.783 | +| learning_rate | 4.05e-05 | +| loss | -0.0291 | +| n_updates | 94228 | +| policy_gradient_loss | -0.0197 | +| value_loss | 6.52e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1386 | +| iterations | 19604 | +| time_elapsed | 28960 | +| total_timesteps | 40148992 | +| train/ | | +| approx_kl | 0.012862876 | +| clip_fraction | 0.307 | +| clip_range | 0.065 | +| entropy_loss | -5.51 | +| explained_variance | 0.39 | +| learning_rate | 4.05e-05 | +| loss | -0.0217 | +| n_updates | 94232 | +| policy_gradient_loss | -0.0147 | +| value_loss | 0.000254 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1386 | +| iterations | 19605 | +| time_elapsed | 28962 | +| total_timesteps | 40151040 | +| train/ | | +| approx_kl | 0.011325536 | +| clip_fraction | 0.316 | +| clip_range | 0.065 | +| entropy_loss | -5.25 | +| explained_variance | 0.548 | +| learning_rate | 4.05e-05 | +| loss | -0.0266 | +| n_updates | 94236 | +| policy_gradient_loss | -0.0145 | +| value_loss | 0.000236 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1386 | +| iterations | 19606 | +| time_elapsed | 28963 | +| total_timesteps | 40153088 | +| train/ | | +| approx_kl | 0.013625413 | +| clip_fraction | 0.361 | +| clip_range | 0.065 | +| entropy_loss | -5.1 | +| explained_variance | 0.287 | +| learning_rate | 4.05e-05 | +| loss | -0.0275 | +| n_updates | 94240 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000154 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1386 | +| iterations | 19607 | +| time_elapsed | 28965 | +| total_timesteps | 40155136 | +| train/ | | +| approx_kl | 0.016204294 | +| clip_fraction | 0.377 | +| clip_range | 0.065 | +| entropy_loss | -5.95 | +| explained_variance | -0.213 | +| learning_rate | 4.05e-05 | +| loss | -0.0309 | +| n_updates | 94244 | +| policy_gradient_loss | -0.0199 | +| value_loss | 9.49e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1386 | +| iterations | 19608 | +| time_elapsed | 28966 | +| total_timesteps | 40157184 | +| train/ | | +| approx_kl | 0.010487471 | +| clip_fraction | 0.328 | +| clip_range | 0.065 | +| entropy_loss | -6.05 | +| explained_variance | 0.46 | +| learning_rate | 4.05e-05 | +| loss | -0.0272 | +| n_updates | 94248 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.000175 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1386 | +| iterations | 19609 | +| time_elapsed | 28968 | +| total_timesteps | 40159232 | +| train/ | | +| approx_kl | 0.013667818 | +| clip_fraction | 0.365 | +| clip_range | 0.065 | +| entropy_loss | -6.22 | +| explained_variance | -0.331 | +| learning_rate | 4.05e-05 | +| loss | -0.0314 | +| n_updates | 94252 | +| policy_gradient_loss | -0.0199 | +| value_loss | 7.25e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1386 | +| iterations | 19610 | +| time_elapsed | 28969 | +| total_timesteps | 40161280 | +| train/ | | +| approx_kl | 0.011704953 | +| clip_fraction | 0.316 | +| clip_range | 0.065 | +| entropy_loss | -6 | +| explained_variance | 0.278 | +| learning_rate | 4.05e-05 | +| loss | -0.022 | +| n_updates | 94256 | +| policy_gradient_loss | -0.0145 | +| value_loss | 0.000197 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1386 | +| iterations | 19611 | +| time_elapsed | 28971 | +| total_timesteps | 40163328 | +| train/ | | +| approx_kl | 0.013604855 | +| clip_fraction | 0.346 | +| clip_range | 0.065 | +| entropy_loss | -5.98 | +| explained_variance | 0.57 | +| learning_rate | 4.05e-05 | +| loss | -0.0324 | +| n_updates | 94260 | +| policy_gradient_loss | -0.0187 | +| value_loss | 5.87e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1386 | +| iterations | 19612 | +| time_elapsed | 28972 | +| total_timesteps | 40165376 | +| train/ | | +| approx_kl | 0.013038883 | +| clip_fraction | 0.323 | +| clip_range | 0.065 | +| entropy_loss | -6.05 | +| explained_variance | 0.292 | +| learning_rate | 4.05e-05 | +| loss | -0.0246 | +| n_updates | 94264 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000164 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1386 | +| iterations | 19613 | +| time_elapsed | 28974 | +| total_timesteps | 40167424 | +| train/ | | +| approx_kl | 0.010898402 | +| clip_fraction | 0.328 | +| clip_range | 0.065 | +| entropy_loss | -6.13 | +| explained_variance | -0.0702 | +| learning_rate | 4.05e-05 | +| loss | -0.0276 | +| n_updates | 94268 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1386 | +| iterations | 19614 | +| time_elapsed | 28975 | +| total_timesteps | 40169472 | +| train/ | | +| approx_kl | 0.012680314 | +| clip_fraction | 0.34 | +| clip_range | 0.065 | +| entropy_loss | -5.11 | +| explained_variance | 0.7 | +| learning_rate | 4.05e-05 | +| loss | -0.0212 | +| n_updates | 94272 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000125 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1386 | +| iterations | 19615 | +| time_elapsed | 28977 | +| total_timesteps | 40171520 | +| train/ | | +| approx_kl | 0.014319196 | +| clip_fraction | 0.325 | +| clip_range | 0.065 | +| entropy_loss | -4.85 | +| explained_variance | 0.682 | +| learning_rate | 4.05e-05 | +| loss | -0.0227 | +| n_updates | 94276 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000117 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1386 | +| iterations | 19616 | +| time_elapsed | 28978 | +| total_timesteps | 40173568 | +| train/ | | +| approx_kl | 0.0102079045 | +| clip_fraction | 0.325 | +| clip_range | 0.065 | +| entropy_loss | -5.4 | +| explained_variance | 0.299 | +| learning_rate | 4.05e-05 | +| loss | -0.0209 | +| n_updates | 94280 | +| policy_gradient_loss | -0.0146 | +| value_loss | 0.000212 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1386 | +| iterations | 19617 | +| time_elapsed | 28980 | +| total_timesteps | 40175616 | +| train/ | | +| approx_kl | 0.012481704 | +| clip_fraction | 0.334 | +| clip_range | 0.065 | +| entropy_loss | -5.61 | +| explained_variance | 0.272 | +| learning_rate | 4.05e-05 | +| loss | -0.0249 | +| n_updates | 94284 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000265 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1386 | +| iterations | 19618 | +| time_elapsed | 28981 | +| total_timesteps | 40177664 | +| train/ | | +| approx_kl | 0.013619169 | +| clip_fraction | 0.328 | +| clip_range | 0.065 | +| entropy_loss | -5.58 | +| explained_variance | 0.466 | +| learning_rate | 4.05e-05 | +| loss | -0.0285 | +| n_updates | 94288 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000136 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1386 | +| iterations | 19619 | +| time_elapsed | 28983 | +| total_timesteps | 40179712 | +| train/ | | +| approx_kl | 0.011563646 | +| clip_fraction | 0.328 | +| clip_range | 0.065 | +| entropy_loss | -6.09 | +| explained_variance | 0.218 | +| learning_rate | 4.05e-05 | +| loss | -0.0351 | +| n_updates | 94292 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000128 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1386 | +| iterations | 19620 | +| time_elapsed | 28984 | +| total_timesteps | 40181760 | +| train/ | | +| approx_kl | 0.0115180705 | +| clip_fraction | 0.336 | +| clip_range | 0.065 | +| entropy_loss | -6.43 | +| explained_variance | -0.024 | +| learning_rate | 4.05e-05 | +| loss | -0.0254 | +| n_updates | 94296 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000133 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1386 | +| iterations | 19621 | +| time_elapsed | 28986 | +| total_timesteps | 40183808 | +| train/ | | +| approx_kl | 0.007905034 | +| clip_fraction | 0.302 | +| clip_range | 0.065 | +| entropy_loss | -6.96 | +| explained_variance | -0.0874 | +| learning_rate | 4.05e-05 | +| loss | -0.0242 | +| n_updates | 94300 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000132 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1386 | +| iterations | 19622 | +| time_elapsed | 28987 | +| total_timesteps | 40185856 | +| train/ | | +| approx_kl | 0.009607469 | +| clip_fraction | 0.3 | +| clip_range | 0.065 | +| entropy_loss | -6.74 | +| explained_variance | 0.269 | +| learning_rate | 4.05e-05 | +| loss | -0.0213 | +| n_updates | 94304 | +| policy_gradient_loss | -0.0138 | +| value_loss | 0.000175 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1386 | +| iterations | 19623 | +| time_elapsed | 28989 | +| total_timesteps | 40187904 | +| train/ | | +| approx_kl | 0.011601398 | +| clip_fraction | 0.328 | +| clip_range | 0.065 | +| entropy_loss | -6.2 | +| explained_variance | 0.46 | +| learning_rate | 4.05e-05 | +| loss | -0.0308 | +| n_updates | 94308 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000113 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1386 | +| iterations | 19624 | +| time_elapsed | 28990 | +| total_timesteps | 40189952 | +| train/ | | +| approx_kl | 0.008630523 | +| clip_fraction | 0.294 | +| clip_range | 0.065 | +| entropy_loss | -6.07 | +| explained_variance | 0.452 | +| learning_rate | 4.05e-05 | +| loss | -0.0279 | +| n_updates | 94312 | +| policy_gradient_loss | -0.0131 | +| value_loss | 0.000217 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1386 | +| iterations | 19625 | +| time_elapsed | 28992 | +| total_timesteps | 40192000 | +| train/ | | +| approx_kl | 0.012425929 | +| clip_fraction | 0.335 | +| clip_range | 0.065 | +| entropy_loss | -5.61 | +| explained_variance | 0.588 | +| learning_rate | 4.05e-05 | +| loss | -0.0309 | +| n_updates | 94316 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000106 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1386 | +| iterations | 19626 | +| time_elapsed | 28993 | +| total_timesteps | 40194048 | +| train/ | | +| approx_kl | 0.013844398 | +| clip_fraction | 0.35 | +| clip_range | 0.065 | +| entropy_loss | -5.26 | +| explained_variance | 0.682 | +| learning_rate | 4.05e-05 | +| loss | -0.0263 | +| n_updates | 94320 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000161 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1386 | +| iterations | 19627 | +| time_elapsed | 28995 | +| total_timesteps | 40196096 | +| train/ | | +| approx_kl | 0.013678086 | +| clip_fraction | 0.367 | +| clip_range | 0.065 | +| entropy_loss | -5.47 | +| explained_variance | 0.472 | +| learning_rate | 4.05e-05 | +| loss | -0.0318 | +| n_updates | 94324 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000217 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1386 | +| iterations | 19628 | +| time_elapsed | 28996 | +| total_timesteps | 40198144 | +| train/ | | +| approx_kl | 0.013603298 | +| clip_fraction | 0.33 | +| clip_range | 0.065 | +| entropy_loss | -5.79 | +| explained_variance | 0.557 | +| learning_rate | 4.05e-05 | +| loss | -0.0302 | +| n_updates | 94328 | +| policy_gradient_loss | -0.0182 | +| value_loss | 7.34e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1386 | +| iterations | 19629 | +| time_elapsed | 28998 | +| total_timesteps | 40200192 | +| train/ | | +| approx_kl | 0.016854007 | +| clip_fraction | 0.34 | +| clip_range | 0.065 | +| entropy_loss | -5.8 | +| explained_variance | 0.236 | +| learning_rate | 4.05e-05 | +| loss | -0.0284 | +| n_updates | 94332 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000172 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1386 | +| iterations | 19630 | +| time_elapsed | 29000 | +| total_timesteps | 40202240 | +| train/ | | +| approx_kl | 0.016042132 | +| clip_fraction | 0.362 | +| clip_range | 0.0649 | +| entropy_loss | -5.95 | +| explained_variance | 0.213 | +| learning_rate | 4.05e-05 | +| loss | -0.0279 | +| n_updates | 94336 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000153 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1386 | +| iterations | 19631 | +| time_elapsed | 29001 | +| total_timesteps | 40204288 | +| train/ | | +| approx_kl | 0.015386034 | +| clip_fraction | 0.315 | +| clip_range | 0.0649 | +| entropy_loss | -6.29 | +| explained_variance | 0.0777 | +| learning_rate | 4.05e-05 | +| loss | -0.0268 | +| n_updates | 94340 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000241 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1386 | +| iterations | 19632 | +| time_elapsed | 29003 | +| total_timesteps | 40206336 | +| train/ | | +| approx_kl | 0.014007461 | +| clip_fraction | 0.375 | +| clip_range | 0.0649 | +| entropy_loss | -5.52 | +| explained_variance | 0.607 | +| learning_rate | 4.05e-05 | +| loss | -0.0266 | +| n_updates | 94344 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000107 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1386 | +| iterations | 19633 | +| time_elapsed | 29004 | +| total_timesteps | 40208384 | +| train/ | | +| approx_kl | 0.01546773 | +| clip_fraction | 0.348 | +| clip_range | 0.0649 | +| entropy_loss | -5.45 | +| explained_variance | 0.495 | +| learning_rate | 4.05e-05 | +| loss | -0.0272 | +| n_updates | 94348 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000139 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1386 | +| iterations | 19634 | +| time_elapsed | 29006 | +| total_timesteps | 40210432 | +| train/ | | +| approx_kl | 0.013170893 | +| clip_fraction | 0.335 | +| clip_range | 0.0649 | +| entropy_loss | -5.41 | +| explained_variance | 0.313 | +| learning_rate | 4.05e-05 | +| loss | -0.0241 | +| n_updates | 94352 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.00021 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1386 | +| iterations | 19635 | +| time_elapsed | 29007 | +| total_timesteps | 40212480 | +| train/ | | +| approx_kl | 0.013069542 | +| clip_fraction | 0.331 | +| clip_range | 0.0649 | +| entropy_loss | -5.9 | +| explained_variance | 0.184 | +| learning_rate | 4.05e-05 | +| loss | -0.0252 | +| n_updates | 94356 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000161 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1386 | +| iterations | 19636 | +| time_elapsed | 29009 | +| total_timesteps | 40214528 | +| train/ | | +| approx_kl | 0.010886159 | +| clip_fraction | 0.323 | +| clip_range | 0.0649 | +| entropy_loss | -6.65 | +| explained_variance | 0.0646 | +| learning_rate | 4.04e-05 | +| loss | -0.03 | +| n_updates | 94360 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000121 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1386 | +| iterations | 19637 | +| time_elapsed | 29010 | +| total_timesteps | 40216576 | +| train/ | | +| approx_kl | 0.013238223 | +| clip_fraction | 0.308 | +| clip_range | 0.0649 | +| entropy_loss | -6.13 | +| explained_variance | 0.493 | +| learning_rate | 4.04e-05 | +| loss | -0.0257 | +| n_updates | 94364 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000118 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1386 | +| iterations | 19638 | +| time_elapsed | 29012 | +| total_timesteps | 40218624 | +| train/ | | +| approx_kl | 0.012189059 | +| clip_fraction | 0.325 | +| clip_range | 0.0649 | +| entropy_loss | -5.84 | +| explained_variance | 0.48 | +| learning_rate | 4.04e-05 | +| loss | -0.0272 | +| n_updates | 94368 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000177 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1386 | +| iterations | 19639 | +| time_elapsed | 29013 | +| total_timesteps | 40220672 | +| train/ | | +| approx_kl | 0.013988227 | +| clip_fraction | 0.321 | +| clip_range | 0.0649 | +| entropy_loss | -6 | +| explained_variance | 0.237 | +| learning_rate | 4.04e-05 | +| loss | -0.0292 | +| n_updates | 94372 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.00012 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1386 | +| iterations | 19640 | +| time_elapsed | 29015 | +| total_timesteps | 40222720 | +| train/ | | +| approx_kl | 0.012455436 | +| clip_fraction | 0.333 | +| clip_range | 0.0649 | +| entropy_loss | -5.51 | +| explained_variance | 0.381 | +| learning_rate | 4.04e-05 | +| loss | -0.0275 | +| n_updates | 94376 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000125 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1386 | +| iterations | 19641 | +| time_elapsed | 29016 | +| total_timesteps | 40224768 | +| train/ | | +| approx_kl | 0.01738023 | +| clip_fraction | 0.321 | +| clip_range | 0.0649 | +| entropy_loss | -5.34 | +| explained_variance | 0.431 | +| learning_rate | 4.04e-05 | +| loss | -0.0254 | +| n_updates | 94380 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000172 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1386 | +| iterations | 19642 | +| time_elapsed | 29018 | +| total_timesteps | 40226816 | +| train/ | | +| approx_kl | 0.01521979 | +| clip_fraction | 0.365 | +| clip_range | 0.0649 | +| entropy_loss | -5.38 | +| explained_variance | 0.393 | +| learning_rate | 4.04e-05 | +| loss | -0.0254 | +| n_updates | 94384 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000173 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1386 | +| iterations | 19643 | +| time_elapsed | 29019 | +| total_timesteps | 40228864 | +| train/ | | +| approx_kl | 0.012999362 | +| clip_fraction | 0.331 | +| clip_range | 0.0649 | +| entropy_loss | -5 | +| explained_variance | 0.515 | +| learning_rate | 4.04e-05 | +| loss | -0.0212 | +| n_updates | 94388 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000236 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1386 | +| iterations | 19644 | +| time_elapsed | 29021 | +| total_timesteps | 40230912 | +| train/ | | +| approx_kl | 0.015791781 | +| clip_fraction | 0.36 | +| clip_range | 0.0649 | +| entropy_loss | -5.31 | +| explained_variance | 0.165 | +| learning_rate | 4.04e-05 | +| loss | -0.0308 | +| n_updates | 94392 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000113 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1386 | +| iterations | 19645 | +| time_elapsed | 29022 | +| total_timesteps | 40232960 | +| train/ | | +| approx_kl | 0.01344887 | +| clip_fraction | 0.341 | +| clip_range | 0.0649 | +| entropy_loss | -5.72 | +| explained_variance | 0.0942 | +| learning_rate | 4.04e-05 | +| loss | -0.0245 | +| n_updates | 94396 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000164 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1386 | +| iterations | 19646 | +| time_elapsed | 29024 | +| total_timesteps | 40235008 | +| train/ | | +| approx_kl | 0.012672321 | +| clip_fraction | 0.355 | +| clip_range | 0.0649 | +| entropy_loss | -5.94 | +| explained_variance | 0.299 | +| learning_rate | 4.04e-05 | +| loss | -0.0311 | +| n_updates | 94400 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000113 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1386 | +| iterations | 19647 | +| time_elapsed | 29025 | +| total_timesteps | 40237056 | +| train/ | | +| approx_kl | 0.012680275 | +| clip_fraction | 0.343 | +| clip_range | 0.0649 | +| entropy_loss | -6.14 | +| explained_variance | 0.479 | +| learning_rate | 4.04e-05 | +| loss | -0.0272 | +| n_updates | 94404 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000166 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1386 | +| iterations | 19648 | +| time_elapsed | 29027 | +| total_timesteps | 40239104 | +| train/ | | +| approx_kl | 0.00960474 | +| clip_fraction | 0.321 | +| clip_range | 0.0649 | +| entropy_loss | -5.99 | +| explained_variance | 0.61 | +| learning_rate | 4.04e-05 | +| loss | -0.0287 | +| n_updates | 94408 | +| policy_gradient_loss | -0.0145 | +| value_loss | 0.000153 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1386 | +| iterations | 19649 | +| time_elapsed | 29029 | +| total_timesteps | 40241152 | +| train/ | | +| approx_kl | 0.014039086 | +| clip_fraction | 0.341 | +| clip_range | 0.0649 | +| entropy_loss | -5.77 | +| explained_variance | 0.01 | +| learning_rate | 4.04e-05 | +| loss | -0.0271 | +| n_updates | 94412 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000111 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1386 | +| iterations | 19650 | +| time_elapsed | 29030 | +| total_timesteps | 40243200 | +| train/ | | +| approx_kl | 0.013938466 | +| clip_fraction | 0.356 | +| clip_range | 0.0649 | +| entropy_loss | -6.02 | +| explained_variance | 0.341 | +| learning_rate | 4.04e-05 | +| loss | -0.0309 | +| n_updates | 94416 | +| policy_gradient_loss | -0.0176 | +| value_loss | 7.34e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1386 | +| iterations | 19651 | +| time_elapsed | 29032 | +| total_timesteps | 40245248 | +| train/ | | +| approx_kl | 0.012506889 | +| clip_fraction | 0.343 | +| clip_range | 0.0649 | +| entropy_loss | -6.55 | +| explained_variance | -0.0397 | +| learning_rate | 4.04e-05 | +| loss | -0.0223 | +| n_updates | 94420 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.00022 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1386 | +| iterations | 19652 | +| time_elapsed | 29033 | +| total_timesteps | 40247296 | +| train/ | | +| approx_kl | 0.011898609 | +| clip_fraction | 0.3 | +| clip_range | 0.0649 | +| entropy_loss | -5.81 | +| explained_variance | 0.465 | +| learning_rate | 4.04e-05 | +| loss | -0.0209 | +| n_updates | 94424 | +| policy_gradient_loss | -0.0146 | +| value_loss | 0.000244 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1386 | +| iterations | 19653 | +| time_elapsed | 29035 | +| total_timesteps | 40249344 | +| train/ | | +| approx_kl | 0.014800118 | +| clip_fraction | 0.314 | +| clip_range | 0.0649 | +| entropy_loss | -5.41 | +| explained_variance | 0.368 | +| learning_rate | 4.04e-05 | +| loss | -0.0272 | +| n_updates | 94428 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000191 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1386 | +| iterations | 19654 | +| time_elapsed | 29036 | +| total_timesteps | 40251392 | +| train/ | | +| approx_kl | 0.013202323 | +| clip_fraction | 0.307 | +| clip_range | 0.0649 | +| entropy_loss | -4.52 | +| explained_variance | 0.6 | +| learning_rate | 4.04e-05 | +| loss | -0.0203 | +| n_updates | 94432 | +| policy_gradient_loss | -0.0146 | +| value_loss | 0.000227 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1386 | +| iterations | 19655 | +| time_elapsed | 29038 | +| total_timesteps | 40253440 | +| train/ | | +| approx_kl | 0.015875734 | +| clip_fraction | 0.336 | +| clip_range | 0.0649 | +| entropy_loss | -5.35 | +| explained_variance | -0.135 | +| learning_rate | 4.04e-05 | +| loss | -0.029 | +| n_updates | 94436 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000192 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1386 | +| iterations | 19656 | +| time_elapsed | 29039 | +| total_timesteps | 40255488 | +| train/ | | +| approx_kl | 0.008375829 | +| clip_fraction | 0.303 | +| clip_range | 0.0649 | +| entropy_loss | -6.04 | +| explained_variance | 0.0619 | +| learning_rate | 4.04e-05 | +| loss | -0.0192 | +| n_updates | 94440 | +| policy_gradient_loss | -0.0129 | +| value_loss | 0.000375 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1386 | +| iterations | 19657 | +| time_elapsed | 29041 | +| total_timesteps | 40257536 | +| train/ | | +| approx_kl | 0.012025682 | +| clip_fraction | 0.348 | +| clip_range | 0.0649 | +| entropy_loss | -5.93 | +| explained_variance | 0.218 | +| learning_rate | 4.04e-05 | +| loss | -0.0251 | +| n_updates | 94444 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000318 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1386 | +| iterations | 19658 | +| time_elapsed | 29042 | +| total_timesteps | 40259584 | +| train/ | | +| approx_kl | 0.013111439 | +| clip_fraction | 0.341 | +| clip_range | 0.0649 | +| entropy_loss | -6.46 | +| explained_variance | 0.358 | +| learning_rate | 4.04e-05 | +| loss | -0.0303 | +| n_updates | 94448 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000144 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1386 | +| iterations | 19659 | +| time_elapsed | 29044 | +| total_timesteps | 40261632 | +| train/ | | +| approx_kl | 0.007933296 | +| clip_fraction | 0.286 | +| clip_range | 0.0649 | +| entropy_loss | -6.17 | +| explained_variance | 0.193 | +| learning_rate | 4.04e-05 | +| loss | -0.0244 | +| n_updates | 94452 | +| policy_gradient_loss | -0.0137 | +| value_loss | 0.000347 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1386 | +| iterations | 19660 | +| time_elapsed | 29046 | +| total_timesteps | 40263680 | +| train/ | | +| approx_kl | 0.012658668 | +| clip_fraction | 0.339 | +| clip_range | 0.0649 | +| entropy_loss | -5.81 | +| explained_variance | 0.56 | +| learning_rate | 4.04e-05 | +| loss | -0.0257 | +| n_updates | 94456 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.00015 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1386 | +| iterations | 19661 | +| time_elapsed | 29047 | +| total_timesteps | 40265728 | +| train/ | | +| approx_kl | 0.01454149 | +| clip_fraction | 0.365 | +| clip_range | 0.0649 | +| entropy_loss | -5.31 | +| explained_variance | 0.718 | +| learning_rate | 4.04e-05 | +| loss | -0.039 | +| n_updates | 94460 | +| policy_gradient_loss | -0.0216 | +| value_loss | 6.38e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1386 | +| iterations | 19662 | +| time_elapsed | 29049 | +| total_timesteps | 40267776 | +| train/ | | +| approx_kl | 0.011110494 | +| clip_fraction | 0.32 | +| clip_range | 0.0649 | +| entropy_loss | -6.45 | +| explained_variance | 0.376 | +| learning_rate | 4.04e-05 | +| loss | -0.0243 | +| n_updates | 94464 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000207 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1386 | +| iterations | 19663 | +| time_elapsed | 29050 | +| total_timesteps | 40269824 | +| train/ | | +| approx_kl | 0.011156404 | +| clip_fraction | 0.316 | +| clip_range | 0.0649 | +| entropy_loss | -5.53 | +| explained_variance | 0.467 | +| learning_rate | 4.04e-05 | +| loss | -0.0205 | +| n_updates | 94468 | +| policy_gradient_loss | -0.0139 | +| value_loss | 0.000292 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1386 | +| iterations | 19664 | +| time_elapsed | 29052 | +| total_timesteps | 40271872 | +| train/ | | +| approx_kl | 0.014584679 | +| clip_fraction | 0.335 | +| clip_range | 0.0649 | +| entropy_loss | -5.63 | +| explained_variance | 0.494 | +| learning_rate | 4.04e-05 | +| loss | -0.0272 | +| n_updates | 94472 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000144 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1386 | +| iterations | 19665 | +| time_elapsed | 29053 | +| total_timesteps | 40273920 | +| train/ | | +| approx_kl | 0.012620108 | +| clip_fraction | 0.334 | +| clip_range | 0.0649 | +| entropy_loss | -6.12 | +| explained_variance | -0.0276 | +| learning_rate | 4.04e-05 | +| loss | -0.03 | +| n_updates | 94476 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000151 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1386 | +| iterations | 19666 | +| time_elapsed | 29055 | +| total_timesteps | 40275968 | +| train/ | | +| approx_kl | 0.010828663 | +| clip_fraction | 0.319 | +| clip_range | 0.0649 | +| entropy_loss | -6.12 | +| explained_variance | 0.355 | +| learning_rate | 4.04e-05 | +| loss | -0.025 | +| n_updates | 94480 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000215 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1386 | +| iterations | 19667 | +| time_elapsed | 29056 | +| total_timesteps | 40278016 | +| train/ | | +| approx_kl | 0.013561044 | +| clip_fraction | 0.332 | +| clip_range | 0.0649 | +| entropy_loss | -5.66 | +| explained_variance | 0.386 | +| learning_rate | 4.04e-05 | +| loss | -0.0275 | +| n_updates | 94484 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000187 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1386 | +| iterations | 19668 | +| time_elapsed | 29058 | +| total_timesteps | 40280064 | +| train/ | | +| approx_kl | 0.012878289 | +| clip_fraction | 0.348 | +| clip_range | 0.0649 | +| entropy_loss | -6.18 | +| explained_variance | 0.185 | +| learning_rate | 4.04e-05 | +| loss | -0.0262 | +| n_updates | 94488 | +| policy_gradient_loss | -0.0181 | +| value_loss | 9.57e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1386 | +| iterations | 19669 | +| time_elapsed | 29059 | +| total_timesteps | 40282112 | +| train/ | | +| approx_kl | 0.010488547 | +| clip_fraction | 0.355 | +| clip_range | 0.0649 | +| entropy_loss | -6.71 | +| explained_variance | -0.161 | +| learning_rate | 4.04e-05 | +| loss | -0.0248 | +| n_updates | 94492 | +| policy_gradient_loss | -0.0188 | +| value_loss | 9.65e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1386 | +| iterations | 19670 | +| time_elapsed | 29061 | +| total_timesteps | 40284160 | +| train/ | | +| approx_kl | 0.011796301 | +| clip_fraction | 0.349 | +| clip_range | 0.0649 | +| entropy_loss | -6.67 | +| explained_variance | -0.0517 | +| learning_rate | 4.04e-05 | +| loss | -0.0233 | +| n_updates | 94496 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000106 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1386 | +| iterations | 19671 | +| time_elapsed | 29062 | +| total_timesteps | 40286208 | +| train/ | | +| approx_kl | 0.01033753 | +| clip_fraction | 0.298 | +| clip_range | 0.0649 | +| entropy_loss | -6.59 | +| explained_variance | 0.301 | +| learning_rate | 4.04e-05 | +| loss | -0.0227 | +| n_updates | 94500 | +| policy_gradient_loss | -0.0137 | +| value_loss | 0.000165 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1386 | +| iterations | 19672 | +| time_elapsed | 29064 | +| total_timesteps | 40288256 | +| train/ | | +| approx_kl | 0.011860699 | +| clip_fraction | 0.318 | +| clip_range | 0.0649 | +| entropy_loss | -5.53 | +| explained_variance | 0.625 | +| learning_rate | 4.04e-05 | +| loss | -0.0227 | +| n_updates | 94504 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000121 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1386 | +| iterations | 19673 | +| time_elapsed | 29065 | +| total_timesteps | 40290304 | +| train/ | | +| approx_kl | 0.0140647 | +| clip_fraction | 0.318 | +| clip_range | 0.0649 | +| entropy_loss | -5.4 | +| explained_variance | 0.78 | +| learning_rate | 4.04e-05 | +| loss | -0.0294 | +| n_updates | 94508 | +| policy_gradient_loss | -0.018 | +| value_loss | 6.59e-05 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1386 | +| iterations | 19674 | +| time_elapsed | 29067 | +| total_timesteps | 40292352 | +| train/ | | +| approx_kl | 0.014273245 | +| clip_fraction | 0.31 | +| clip_range | 0.0649 | +| entropy_loss | -4.39 | +| explained_variance | 0.668 | +| learning_rate | 4.04e-05 | +| loss | -0.0243 | +| n_updates | 94512 | +| policy_gradient_loss | -0.014 | +| value_loss | 0.000223 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1386 | +| iterations | 19675 | +| time_elapsed | 29068 | +| total_timesteps | 40294400 | +| train/ | | +| approx_kl | 0.013062776 | +| clip_fraction | 0.323 | +| clip_range | 0.0649 | +| entropy_loss | -5.58 | +| explained_variance | -0.159 | +| learning_rate | 4.04e-05 | +| loss | -0.0224 | +| n_updates | 94516 | +| policy_gradient_loss | -0.0148 | +| value_loss | 0.000135 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1386 | +| iterations | 19676 | +| time_elapsed | 29070 | +| total_timesteps | 40296448 | +| train/ | | +| approx_kl | 0.013242122 | +| clip_fraction | 0.353 | +| clip_range | 0.0649 | +| entropy_loss | -6.61 | +| explained_variance | -0.0884 | +| learning_rate | 4.04e-05 | +| loss | -0.0312 | +| n_updates | 94520 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000101 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1386 | +| iterations | 19677 | +| time_elapsed | 29072 | +| total_timesteps | 40298496 | +| train/ | | +| approx_kl | 0.0131627 | +| clip_fraction | 0.315 | +| clip_range | 0.0649 | +| entropy_loss | -6.71 | +| explained_variance | -0.0991 | +| learning_rate | 4.04e-05 | +| loss | -0.0221 | +| n_updates | 94524 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.0002 | +--------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1386 | +| iterations | 19678 | +| time_elapsed | 29073 | +| total_timesteps | 40300544 | +| train/ | | +| approx_kl | 0.0104223145 | +| clip_fraction | 0.334 | +| clip_range | 0.0649 | +| entropy_loss | -6.74 | +| explained_variance | -0.0631 | +| learning_rate | 4.04e-05 | +| loss | -0.0287 | +| n_updates | 94528 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000194 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1386 | +| iterations | 19679 | +| time_elapsed | 29075 | +| total_timesteps | 40302592 | +| train/ | | +| approx_kl | 0.01297168 | +| clip_fraction | 0.315 | +| clip_range | 0.0649 | +| entropy_loss | -6.24 | +| explained_variance | 0.13 | +| learning_rate | 4.04e-05 | +| loss | -0.0241 | +| n_updates | 94532 | +| policy_gradient_loss | -0.0138 | +| value_loss | 0.00023 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1386 | +| iterations | 19680 | +| time_elapsed | 29076 | +| total_timesteps | 40304640 | +| train/ | | +| approx_kl | 0.013280306 | +| clip_fraction | 0.333 | +| clip_range | 0.0649 | +| entropy_loss | -5.93 | +| explained_variance | 0.521 | +| learning_rate | 4.04e-05 | +| loss | -0.0289 | +| n_updates | 94536 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000113 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1386 | +| iterations | 19681 | +| time_elapsed | 29078 | +| total_timesteps | 40306688 | +| train/ | | +| approx_kl | 0.015407691 | +| clip_fraction | 0.275 | +| clip_range | 0.0649 | +| entropy_loss | -5.71 | +| explained_variance | 0.431 | +| learning_rate | 4.04e-05 | +| loss | -0.0225 | +| n_updates | 94540 | +| policy_gradient_loss | -0.0135 | +| value_loss | 0.000278 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1386 | +| iterations | 19682 | +| time_elapsed | 29079 | +| total_timesteps | 40308736 | +| train/ | | +| approx_kl | 0.0140605625 | +| clip_fraction | 0.297 | +| clip_range | 0.0649 | +| entropy_loss | -5.4 | +| explained_variance | 0.487 | +| learning_rate | 4.04e-05 | +| loss | -0.025 | +| n_updates | 94544 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000168 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1386 | +| iterations | 19683 | +| time_elapsed | 29081 | +| total_timesteps | 40310784 | +| train/ | | +| approx_kl | 0.016521681 | +| clip_fraction | 0.339 | +| clip_range | 0.0649 | +| entropy_loss | -5.52 | +| explained_variance | 0.521 | +| learning_rate | 4.04e-05 | +| loss | -0.0327 | +| n_updates | 94548 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000122 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1386 | +| iterations | 19684 | +| time_elapsed | 29082 | +| total_timesteps | 40312832 | +| train/ | | +| approx_kl | 0.016200101 | +| clip_fraction | 0.338 | +| clip_range | 0.0649 | +| entropy_loss | -5.3 | +| explained_variance | 0.302 | +| learning_rate | 4.04e-05 | +| loss | -0.0292 | +| n_updates | 94552 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000112 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1386 | +| iterations | 19685 | +| time_elapsed | 29084 | +| total_timesteps | 40314880 | +| train/ | | +| approx_kl | 0.015463099 | +| clip_fraction | 0.374 | +| clip_range | 0.0649 | +| entropy_loss | -5.81 | +| explained_variance | 0.707 | +| learning_rate | 4.04e-05 | +| loss | -0.0349 | +| n_updates | 94556 | +| policy_gradient_loss | -0.0211 | +| value_loss | 5.51e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1386 | +| iterations | 19686 | +| time_elapsed | 29086 | +| total_timesteps | 40316928 | +| train/ | | +| approx_kl | 0.01301433 | +| clip_fraction | 0.341 | +| clip_range | 0.0649 | +| entropy_loss | -5.53 | +| explained_variance | 0.463 | +| learning_rate | 4.04e-05 | +| loss | -0.0234 | +| n_updates | 94560 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.000171 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1386 | +| iterations | 19687 | +| time_elapsed | 29087 | +| total_timesteps | 40318976 | +| train/ | | +| approx_kl | 0.011911433 | +| clip_fraction | 0.315 | +| clip_range | 0.0649 | +| entropy_loss | -4.95 | +| explained_variance | 0.552 | +| learning_rate | 4.04e-05 | +| loss | -0.0275 | +| n_updates | 94564 | +| policy_gradient_loss | -0.014 | +| value_loss | 0.000228 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1386 | +| iterations | 19688 | +| time_elapsed | 29089 | +| total_timesteps | 40321024 | +| train/ | | +| approx_kl | 0.013958715 | +| clip_fraction | 0.335 | +| clip_range | 0.0649 | +| entropy_loss | -5.97 | +| explained_variance | -0.219 | +| learning_rate | 4.04e-05 | +| loss | -0.0261 | +| n_updates | 94568 | +| policy_gradient_loss | -0.0189 | +| value_loss | 7.12e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1386 | +| iterations | 19689 | +| time_elapsed | 29090 | +| total_timesteps | 40323072 | +| train/ | | +| approx_kl | 0.011472903 | +| clip_fraction | 0.325 | +| clip_range | 0.0649 | +| entropy_loss | -5.95 | +| explained_variance | 0.284 | +| learning_rate | 4.04e-05 | +| loss | -0.0286 | +| n_updates | 94572 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000188 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1386 | +| iterations | 19690 | +| time_elapsed | 29092 | +| total_timesteps | 40325120 | +| train/ | | +| approx_kl | 0.01060218 | +| clip_fraction | 0.326 | +| clip_range | 0.0649 | +| entropy_loss | -6.24 | +| explained_variance | 0.315 | +| learning_rate | 4.04e-05 | +| loss | -0.0253 | +| n_updates | 94576 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000128 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1386 | +| iterations | 19691 | +| time_elapsed | 29093 | +| total_timesteps | 40327168 | +| train/ | | +| approx_kl | 0.015438257 | +| clip_fraction | 0.302 | +| clip_range | 0.0649 | +| entropy_loss | -6.23 | +| explained_variance | 0.239 | +| learning_rate | 4.04e-05 | +| loss | -0.0262 | +| n_updates | 94580 | +| policy_gradient_loss | -0.0133 | +| value_loss | 0.000337 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1386 | +| iterations | 19692 | +| time_elapsed | 29095 | +| total_timesteps | 40329216 | +| train/ | | +| approx_kl | 0.01323735 | +| clip_fraction | 0.359 | +| clip_range | 0.0649 | +| entropy_loss | -5.53 | +| explained_variance | 0.47 | +| learning_rate | 4.04e-05 | +| loss | -0.0328 | +| n_updates | 94584 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000155 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1386 | +| iterations | 19693 | +| time_elapsed | 29096 | +| total_timesteps | 40331264 | +| train/ | | +| approx_kl | 0.014567179 | +| clip_fraction | 0.345 | +| clip_range | 0.0649 | +| entropy_loss | -5.58 | +| explained_variance | 0.61 | +| learning_rate | 4.04e-05 | +| loss | -0.0272 | +| n_updates | 94588 | +| policy_gradient_loss | -0.0188 | +| value_loss | 7.92e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1386 | +| iterations | 19694 | +| time_elapsed | 29098 | +| total_timesteps | 40333312 | +| train/ | | +| approx_kl | 0.011848069 | +| clip_fraction | 0.339 | +| clip_range | 0.0649 | +| entropy_loss | -6.1 | +| explained_variance | 0.503 | +| learning_rate | 4.04e-05 | +| loss | -0.0315 | +| n_updates | 94592 | +| policy_gradient_loss | -0.0185 | +| value_loss | 8.33e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1386 | +| iterations | 19695 | +| time_elapsed | 29099 | +| total_timesteps | 40335360 | +| train/ | | +| approx_kl | 0.013816422 | +| clip_fraction | 0.292 | +| clip_range | 0.0649 | +| entropy_loss | -6.01 | +| explained_variance | 0.287 | +| learning_rate | 4.04e-05 | +| loss | -0.0236 | +| n_updates | 94596 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000157 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1386 | +| iterations | 19696 | +| time_elapsed | 29101 | +| total_timesteps | 40337408 | +| train/ | | +| approx_kl | 0.010290628 | +| clip_fraction | 0.327 | +| clip_range | 0.0649 | +| entropy_loss | -6.36 | +| explained_variance | 0.00738 | +| learning_rate | 4.04e-05 | +| loss | -0.0211 | +| n_updates | 94600 | +| policy_gradient_loss | -0.0138 | +| value_loss | 0.000233 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1386 | +| iterations | 19697 | +| time_elapsed | 29102 | +| total_timesteps | 40339456 | +| train/ | | +| approx_kl | 0.015627991 | +| clip_fraction | 0.319 | +| clip_range | 0.0649 | +| entropy_loss | -5.14 | +| explained_variance | 0.508 | +| learning_rate | 4.04e-05 | +| loss | -0.0296 | +| n_updates | 94604 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000234 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1386 | +| iterations | 19698 | +| time_elapsed | 29104 | +| total_timesteps | 40341504 | +| train/ | | +| approx_kl | 0.012367317 | +| clip_fraction | 0.34 | +| clip_range | 0.0649 | +| entropy_loss | -5.75 | +| explained_variance | 0.579 | +| learning_rate | 4.04e-05 | +| loss | -0.0295 | +| n_updates | 94608 | +| policy_gradient_loss | -0.0183 | +| value_loss | 8.21e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1386 | +| iterations | 19699 | +| time_elapsed | 29105 | +| total_timesteps | 40343552 | +| train/ | | +| approx_kl | 0.012105552 | +| clip_fraction | 0.35 | +| clip_range | 0.0649 | +| entropy_loss | -5.64 | +| explained_variance | 0.417 | +| learning_rate | 4.04e-05 | +| loss | -0.0293 | +| n_updates | 94612 | +| policy_gradient_loss | -0.0185 | +| value_loss | 9.41e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1386 | +| iterations | 19700 | +| time_elapsed | 29107 | +| total_timesteps | 40345600 | +| train/ | | +| approx_kl | 0.014422445 | +| clip_fraction | 0.321 | +| clip_range | 0.0649 | +| entropy_loss | -5.39 | +| explained_variance | 0.777 | +| learning_rate | 4.04e-05 | +| loss | -0.0247 | +| n_updates | 94616 | +| policy_gradient_loss | -0.0167 | +| value_loss | 7.81e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1386 | +| iterations | 19701 | +| time_elapsed | 29108 | +| total_timesteps | 40347648 | +| train/ | | +| approx_kl | 0.0139961075 | +| clip_fraction | 0.29 | +| clip_range | 0.0649 | +| entropy_loss | -5.8 | +| explained_variance | 0.0641 | +| learning_rate | 4.04e-05 | +| loss | -0.0183 | +| n_updates | 94620 | +| policy_gradient_loss | -0.0137 | +| value_loss | 0.000236 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1386 | +| iterations | 19702 | +| time_elapsed | 29110 | +| total_timesteps | 40349696 | +| train/ | | +| approx_kl | 0.01428633 | +| clip_fraction | 0.323 | +| clip_range | 0.0649 | +| entropy_loss | -5.46 | +| explained_variance | 0.527 | +| learning_rate | 4.04e-05 | +| loss | -0.0236 | +| n_updates | 94624 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000143 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1386 | +| iterations | 19703 | +| time_elapsed | 29112 | +| total_timesteps | 40351744 | +| train/ | | +| approx_kl | 0.013245934 | +| clip_fraction | 0.303 | +| clip_range | 0.0649 | +| entropy_loss | -5.99 | +| explained_variance | 0.269 | +| learning_rate | 4.04e-05 | +| loss | -0.0254 | +| n_updates | 94628 | +| policy_gradient_loss | -0.0145 | +| value_loss | 0.000179 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1386 | +| iterations | 19704 | +| time_elapsed | 29113 | +| total_timesteps | 40353792 | +| train/ | | +| approx_kl | 0.015519104 | +| clip_fraction | 0.327 | +| clip_range | 0.0649 | +| entropy_loss | -6.38 | +| explained_variance | 0.401 | +| learning_rate | 4.04e-05 | +| loss | -0.0273 | +| n_updates | 94632 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000121 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1386 | +| iterations | 19705 | +| time_elapsed | 29115 | +| total_timesteps | 40355840 | +| train/ | | +| approx_kl | 0.013098149 | +| clip_fraction | 0.364 | +| clip_range | 0.0649 | +| entropy_loss | -5.85 | +| explained_variance | 0.373 | +| learning_rate | 4.04e-05 | +| loss | -0.0293 | +| n_updates | 94636 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1386 | +| iterations | 19706 | +| time_elapsed | 29116 | +| total_timesteps | 40357888 | +| train/ | | +| approx_kl | 0.012441003 | +| clip_fraction | 0.336 | +| clip_range | 0.0649 | +| entropy_loss | -6.52 | +| explained_variance | -0.188 | +| learning_rate | 4.04e-05 | +| loss | -0.0275 | +| n_updates | 94640 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000118 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1386 | +| iterations | 19707 | +| time_elapsed | 29118 | +| total_timesteps | 40359936 | +| train/ | | +| approx_kl | 0.014127838 | +| clip_fraction | 0.332 | +| clip_range | 0.0649 | +| entropy_loss | -5.43 | +| explained_variance | 0.415 | +| learning_rate | 4.04e-05 | +| loss | -0.0225 | +| n_updates | 94644 | +| policy_gradient_loss | -0.0138 | +| value_loss | 0.000174 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1386 | +| iterations | 19708 | +| time_elapsed | 29119 | +| total_timesteps | 40361984 | +| train/ | | +| approx_kl | 0.013297584 | +| clip_fraction | 0.35 | +| clip_range | 0.0649 | +| entropy_loss | -5.32 | +| explained_variance | 0.519 | +| learning_rate | 4.04e-05 | +| loss | -0.0263 | +| n_updates | 94648 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000163 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1386 | +| iterations | 19709 | +| time_elapsed | 29121 | +| total_timesteps | 40364032 | +| train/ | | +| approx_kl | 0.013046271 | +| clip_fraction | 0.299 | +| clip_range | 0.0649 | +| entropy_loss | -5.75 | +| explained_variance | 0.477 | +| learning_rate | 4.04e-05 | +| loss | -0.021 | +| n_updates | 94652 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000289 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1386 | +| iterations | 19710 | +| time_elapsed | 29122 | +| total_timesteps | 40366080 | +| train/ | | +| approx_kl | 0.014266629 | +| clip_fraction | 0.312 | +| clip_range | 0.0649 | +| entropy_loss | -5.27 | +| explained_variance | 0.468 | +| learning_rate | 4.04e-05 | +| loss | -0.024 | +| n_updates | 94656 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000199 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1386 | +| iterations | 19711 | +| time_elapsed | 29124 | +| total_timesteps | 40368128 | +| train/ | | +| approx_kl | 0.013275215 | +| clip_fraction | 0.358 | +| clip_range | 0.0649 | +| entropy_loss | -5.71 | +| explained_variance | 0.358 | +| learning_rate | 4.04e-05 | +| loss | -0.0311 | +| n_updates | 94660 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000171 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1386 | +| iterations | 19712 | +| time_elapsed | 29125 | +| total_timesteps | 40370176 | +| train/ | | +| approx_kl | 0.013429649 | +| clip_fraction | 0.356 | +| clip_range | 0.0649 | +| entropy_loss | -5.78 | +| explained_variance | -0.0701 | +| learning_rate | 4.04e-05 | +| loss | -0.0321 | +| n_updates | 94664 | +| policy_gradient_loss | -0.0189 | +| value_loss | 8.76e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1386 | +| iterations | 19713 | +| time_elapsed | 29127 | +| total_timesteps | 40372224 | +| train/ | | +| approx_kl | 0.011692272 | +| clip_fraction | 0.334 | +| clip_range | 0.0649 | +| entropy_loss | -5.45 | +| explained_variance | 0.255 | +| learning_rate | 4.04e-05 | +| loss | -0.0222 | +| n_updates | 94668 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000254 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1386 | +| iterations | 19714 | +| time_elapsed | 29128 | +| total_timesteps | 40374272 | +| train/ | | +| approx_kl | 0.013809416 | +| clip_fraction | 0.344 | +| clip_range | 0.0649 | +| entropy_loss | -5.96 | +| explained_variance | 0.318 | +| learning_rate | 4.04e-05 | +| loss | -0.0287 | +| n_updates | 94672 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000171 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1386 | +| iterations | 19715 | +| time_elapsed | 29130 | +| total_timesteps | 40376320 | +| train/ | | +| approx_kl | 0.013955185 | +| clip_fraction | 0.361 | +| clip_range | 0.0649 | +| entropy_loss | -5.45 | +| explained_variance | 0.454 | +| learning_rate | 4.04e-05 | +| loss | -0.0261 | +| n_updates | 94676 | +| policy_gradient_loss | -0.0177 | +| value_loss | 8.47e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1386 | +| iterations | 19716 | +| time_elapsed | 29131 | +| total_timesteps | 40378368 | +| train/ | | +| approx_kl | 0.014351349 | +| clip_fraction | 0.343 | +| clip_range | 0.0649 | +| entropy_loss | -5.71 | +| explained_variance | 0.393 | +| learning_rate | 4.04e-05 | +| loss | -0.0269 | +| n_updates | 94680 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000168 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1386 | +| iterations | 19717 | +| time_elapsed | 29133 | +| total_timesteps | 40380416 | +| train/ | | +| approx_kl | 0.014910841 | +| clip_fraction | 0.311 | +| clip_range | 0.0649 | +| entropy_loss | -5.37 | +| explained_variance | 0.406 | +| learning_rate | 4.04e-05 | +| loss | -0.0249 | +| n_updates | 94684 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000221 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1386 | +| iterations | 19718 | +| time_elapsed | 29135 | +| total_timesteps | 40382464 | +| train/ | | +| approx_kl | 0.010983675 | +| clip_fraction | 0.308 | +| clip_range | 0.0649 | +| entropy_loss | -5.38 | +| explained_variance | 0.777 | +| learning_rate | 4.04e-05 | +| loss | -0.032 | +| n_updates | 94688 | +| policy_gradient_loss | -0.018 | +| value_loss | 8.61e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1386 | +| iterations | 19719 | +| time_elapsed | 29136 | +| total_timesteps | 40384512 | +| train/ | | +| approx_kl | 0.01134325 | +| clip_fraction | 0.347 | +| clip_range | 0.0649 | +| entropy_loss | -5.97 | +| explained_variance | 0.363 | +| learning_rate | 4.04e-05 | +| loss | -0.035 | +| n_updates | 94692 | +| policy_gradient_loss | -0.0209 | +| value_loss | 4.5e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1386 | +| iterations | 19720 | +| time_elapsed | 29138 | +| total_timesteps | 40386560 | +| train/ | | +| approx_kl | 0.014016857 | +| clip_fraction | 0.339 | +| clip_range | 0.0649 | +| entropy_loss | -5.96 | +| explained_variance | 0.469 | +| learning_rate | 4.04e-05 | +| loss | -0.0202 | +| n_updates | 94696 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000147 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1386 | +| iterations | 19721 | +| time_elapsed | 29139 | +| total_timesteps | 40388608 | +| train/ | | +| approx_kl | 0.012178933 | +| clip_fraction | 0.363 | +| clip_range | 0.0649 | +| entropy_loss | -5.82 | +| explained_variance | 0.16 | +| learning_rate | 4.04e-05 | +| loss | -0.0239 | +| n_updates | 94700 | +| policy_gradient_loss | -0.0171 | +| value_loss | 8.21e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1386 | +| iterations | 19722 | +| time_elapsed | 29141 | +| total_timesteps | 40390656 | +| train/ | | +| approx_kl | 0.014989053 | +| clip_fraction | 0.344 | +| clip_range | 0.0649 | +| entropy_loss | -5.76 | +| explained_variance | 0.632 | +| learning_rate | 4.04e-05 | +| loss | -0.0236 | +| n_updates | 94704 | +| policy_gradient_loss | -0.0172 | +| value_loss | 6.94e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1386 | +| iterations | 19723 | +| time_elapsed | 29142 | +| total_timesteps | 40392704 | +| train/ | | +| approx_kl | 0.011602715 | +| clip_fraction | 0.342 | +| clip_range | 0.0649 | +| entropy_loss | -5.44 | +| explained_variance | 0.476 | +| learning_rate | 4.04e-05 | +| loss | -0.0218 | +| n_updates | 94708 | +| policy_gradient_loss | -0.0155 | +| value_loss | 9.22e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1386 | +| iterations | 19724 | +| time_elapsed | 29144 | +| total_timesteps | 40394752 | +| train/ | | +| approx_kl | 0.011781307 | +| clip_fraction | 0.3 | +| clip_range | 0.0649 | +| entropy_loss | -5.97 | +| explained_variance | 0.53 | +| learning_rate | 4.04e-05 | +| loss | -0.0244 | +| n_updates | 94712 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1386 | +| iterations | 19725 | +| time_elapsed | 29145 | +| total_timesteps | 40396800 | +| train/ | | +| approx_kl | 0.013677003 | +| clip_fraction | 0.338 | +| clip_range | 0.0649 | +| entropy_loss | -5.41 | +| explained_variance | 0.583 | +| learning_rate | 4.04e-05 | +| loss | -0.0245 | +| n_updates | 94716 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000115 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1386 | +| iterations | 19726 | +| time_elapsed | 29146 | +| total_timesteps | 40398848 | +| train/ | | +| approx_kl | 0.014107405 | +| clip_fraction | 0.313 | +| clip_range | 0.0649 | +| entropy_loss | -5.81 | +| explained_variance | 0.0325 | +| learning_rate | 4.04e-05 | +| loss | -0.0269 | +| n_updates | 94720 | +| policy_gradient_loss | -0.0132 | +| value_loss | 0.000185 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1386 | +| iterations | 19727 | +| time_elapsed | 29148 | +| total_timesteps | 40400896 | +| train/ | | +| approx_kl | 0.01280679 | +| clip_fraction | 0.351 | +| clip_range | 0.0649 | +| entropy_loss | -5.9 | +| explained_variance | 0.449 | +| learning_rate | 4.04e-05 | +| loss | -0.0327 | +| n_updates | 94724 | +| policy_gradient_loss | -0.0194 | +| value_loss | 9.52e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1386 | +| iterations | 19728 | +| time_elapsed | 29150 | +| total_timesteps | 40402944 | +| train/ | | +| approx_kl | 0.012659209 | +| clip_fraction | 0.316 | +| clip_range | 0.0649 | +| entropy_loss | -5.69 | +| explained_variance | 0.648 | +| learning_rate | 4.04e-05 | +| loss | -0.0221 | +| n_updates | 94728 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000121 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1386 | +| iterations | 19729 | +| time_elapsed | 29151 | +| total_timesteps | 40404992 | +| train/ | | +| approx_kl | 0.014354534 | +| clip_fraction | 0.334 | +| clip_range | 0.0649 | +| entropy_loss | -5.7 | +| explained_variance | 0.636 | +| learning_rate | 4.04e-05 | +| loss | -0.0279 | +| n_updates | 94732 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000122 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1386 | +| iterations | 19730 | +| time_elapsed | 29153 | +| total_timesteps | 40407040 | +| train/ | | +| approx_kl | 0.014870798 | +| clip_fraction | 0.35 | +| clip_range | 0.0649 | +| entropy_loss | -5.77 | +| explained_variance | 0.307 | +| learning_rate | 4.04e-05 | +| loss | -0.0279 | +| n_updates | 94736 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000198 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1386 | +| iterations | 19731 | +| time_elapsed | 29154 | +| total_timesteps | 40409088 | +| train/ | | +| approx_kl | 0.015096106 | +| clip_fraction | 0.352 | +| clip_range | 0.0649 | +| entropy_loss | -5.91 | +| explained_variance | 0.194 | +| learning_rate | 4.04e-05 | +| loss | -0.0327 | +| n_updates | 94740 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000156 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1386 | +| iterations | 19732 | +| time_elapsed | 29156 | +| total_timesteps | 40411136 | +| train/ | | +| approx_kl | 0.016238265 | +| clip_fraction | 0.357 | +| clip_range | 0.0649 | +| entropy_loss | -5.52 | +| explained_variance | 0.232 | +| learning_rate | 4.04e-05 | +| loss | -0.0298 | +| n_updates | 94744 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000169 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1386 | +| iterations | 19733 | +| time_elapsed | 29157 | +| total_timesteps | 40413184 | +| train/ | | +| approx_kl | 0.01158854 | +| clip_fraction | 0.33 | +| clip_range | 0.0649 | +| entropy_loss | -6.25 | +| explained_variance | 0.226 | +| learning_rate | 4.04e-05 | +| loss | -0.0212 | +| n_updates | 94748 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000233 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1386 | +| iterations | 19734 | +| time_elapsed | 29159 | +| total_timesteps | 40415232 | +| train/ | | +| approx_kl | 0.014574123 | +| clip_fraction | 0.362 | +| clip_range | 0.0649 | +| entropy_loss | -6.17 | +| explained_variance | -0.431 | +| learning_rate | 4.04e-05 | +| loss | -0.037 | +| n_updates | 94752 | +| policy_gradient_loss | -0.0202 | +| value_loss | 6.41e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1386 | +| iterations | 19735 | +| time_elapsed | 29160 | +| total_timesteps | 40417280 | +| train/ | | +| approx_kl | 0.010456439 | +| clip_fraction | 0.319 | +| clip_range | 0.0649 | +| entropy_loss | -5.63 | +| explained_variance | 0.406 | +| learning_rate | 4.04e-05 | +| loss | -0.0262 | +| n_updates | 94756 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.000206 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1386 | +| iterations | 19736 | +| time_elapsed | 29162 | +| total_timesteps | 40419328 | +| train/ | | +| approx_kl | 0.0131237395 | +| clip_fraction | 0.349 | +| clip_range | 0.0649 | +| entropy_loss | -5.94 | +| explained_variance | 0.653 | +| learning_rate | 4.04e-05 | +| loss | -0.0258 | +| n_updates | 94760 | +| policy_gradient_loss | -0.0173 | +| value_loss | 9.37e-05 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1386 | +| iterations | 19737 | +| time_elapsed | 29163 | +| total_timesteps | 40421376 | +| train/ | | +| approx_kl | 0.01280106 | +| clip_fraction | 0.326 | +| clip_range | 0.0649 | +| entropy_loss | -5.64 | +| explained_variance | 0.235 | +| learning_rate | 4.04e-05 | +| loss | -0.0221 | +| n_updates | 94764 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000283 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1386 | +| iterations | 19738 | +| time_elapsed | 29165 | +| total_timesteps | 40423424 | +| train/ | | +| approx_kl | 0.0119284475 | +| clip_fraction | 0.344 | +| clip_range | 0.0649 | +| entropy_loss | -5.89 | +| explained_variance | 0.575 | +| learning_rate | 4.04e-05 | +| loss | -0.0318 | +| n_updates | 94768 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000126 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1386 | +| iterations | 19739 | +| time_elapsed | 29166 | +| total_timesteps | 40425472 | +| train/ | | +| approx_kl | 0.012748665 | +| clip_fraction | 0.323 | +| clip_range | 0.0649 | +| entropy_loss | -4.93 | +| explained_variance | 0.256 | +| learning_rate | 4.04e-05 | +| loss | -0.0304 | +| n_updates | 94772 | +| policy_gradient_loss | -0.017 | +| value_loss | 9.83e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1386 | +| iterations | 19740 | +| time_elapsed | 29168 | +| total_timesteps | 40427520 | +| train/ | | +| approx_kl | 0.012971403 | +| clip_fraction | 0.324 | +| clip_range | 0.0649 | +| entropy_loss | -5.25 | +| explained_variance | 0.452 | +| learning_rate | 4.04e-05 | +| loss | -0.0247 | +| n_updates | 94776 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000229 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1386 | +| iterations | 19741 | +| time_elapsed | 29169 | +| total_timesteps | 40429568 | +| train/ | | +| approx_kl | 0.013848828 | +| clip_fraction | 0.342 | +| clip_range | 0.0649 | +| entropy_loss | -5.59 | +| explained_variance | 0.532 | +| learning_rate | 4.04e-05 | +| loss | -0.0263 | +| n_updates | 94780 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000147 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1385 | +| iterations | 19742 | +| time_elapsed | 29171 | +| total_timesteps | 40431616 | +| train/ | | +| approx_kl | 0.011289161 | +| clip_fraction | 0.33 | +| clip_range | 0.0649 | +| entropy_loss | -6.22 | +| explained_variance | -0.0453 | +| learning_rate | 4.04e-05 | +| loss | -0.0315 | +| n_updates | 94784 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000182 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1385 | +| iterations | 19743 | +| time_elapsed | 29173 | +| total_timesteps | 40433664 | +| train/ | | +| approx_kl | 0.014658629 | +| clip_fraction | 0.369 | +| clip_range | 0.0649 | +| entropy_loss | -5.99 | +| explained_variance | 0.00236 | +| learning_rate | 4.04e-05 | +| loss | -0.0265 | +| n_updates | 94788 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000268 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1385 | +| iterations | 19744 | +| time_elapsed | 29174 | +| total_timesteps | 40435712 | +| train/ | | +| approx_kl | 0.012430906 | +| clip_fraction | 0.35 | +| clip_range | 0.0649 | +| entropy_loss | -5.58 | +| explained_variance | 0.46 | +| learning_rate | 4.04e-05 | +| loss | -0.026 | +| n_updates | 94792 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000198 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1385 | +| iterations | 19745 | +| time_elapsed | 29176 | +| total_timesteps | 40437760 | +| train/ | | +| approx_kl | 0.015659299 | +| clip_fraction | 0.345 | +| clip_range | 0.0649 | +| entropy_loss | -6.25 | +| explained_variance | -0.376 | +| learning_rate | 4.04e-05 | +| loss | -0.0316 | +| n_updates | 94796 | +| policy_gradient_loss | -0.0208 | +| value_loss | 7.61e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1385 | +| iterations | 19746 | +| time_elapsed | 29177 | +| total_timesteps | 40439808 | +| train/ | | +| approx_kl | 0.0111376755 | +| clip_fraction | 0.307 | +| clip_range | 0.0649 | +| entropy_loss | -5.97 | +| explained_variance | 0.462 | +| learning_rate | 4.04e-05 | +| loss | -0.0237 | +| n_updates | 94800 | +| policy_gradient_loss | -0.0147 | +| value_loss | 0.000157 | +------------------------------------------ +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1385 | +| iterations | 19747 | +| time_elapsed | 29179 | +| total_timesteps | 40441856 | +| train/ | | +| approx_kl | 0.0122688 | +| clip_fraction | 0.32 | +| clip_range | 0.0649 | +| entropy_loss | -5.81 | +| explained_variance | 0.719 | +| learning_rate | 4.04e-05 | +| loss | -0.0264 | +| n_updates | 94804 | +| policy_gradient_loss | -0.0178 | +| value_loss | 5.85e-05 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1385 | +| iterations | 19748 | +| time_elapsed | 29180 | +| total_timesteps | 40443904 | +| train/ | | +| approx_kl | 0.013478678 | +| clip_fraction | 0.326 | +| clip_range | 0.0649 | +| entropy_loss | -5.68 | +| explained_variance | 0.673 | +| learning_rate | 4.04e-05 | +| loss | -0.0308 | +| n_updates | 94808 | +| policy_gradient_loss | -0.0182 | +| value_loss | 7.45e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1385 | +| iterations | 19749 | +| time_elapsed | 29182 | +| total_timesteps | 40445952 | +| train/ | | +| approx_kl | 0.010583662 | +| clip_fraction | 0.308 | +| clip_range | 0.0649 | +| entropy_loss | -5.51 | +| explained_variance | 0.512 | +| learning_rate | 4.04e-05 | +| loss | -0.022 | +| n_updates | 94812 | +| policy_gradient_loss | -0.014 | +| value_loss | 0.000293 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1385 | +| iterations | 19750 | +| time_elapsed | 29183 | +| total_timesteps | 40448000 | +| train/ | | +| approx_kl | 0.011867885 | +| clip_fraction | 0.338 | +| clip_range | 0.0649 | +| entropy_loss | -5.5 | +| explained_variance | 0.446 | +| learning_rate | 4.04e-05 | +| loss | -0.028 | +| n_updates | 94816 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000208 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1385 | +| iterations | 19751 | +| time_elapsed | 29185 | +| total_timesteps | 40450048 | +| train/ | | +| approx_kl | 0.010402659 | +| clip_fraction | 0.323 | +| clip_range | 0.0649 | +| entropy_loss | -6.2 | +| explained_variance | 0.211 | +| learning_rate | 4.04e-05 | +| loss | -0.0177 | +| n_updates | 94820 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000275 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1385 | +| iterations | 19752 | +| time_elapsed | 29186 | +| total_timesteps | 40452096 | +| train/ | | +| approx_kl | 0.011762815 | +| clip_fraction | 0.339 | +| clip_range | 0.0649 | +| entropy_loss | -5.52 | +| explained_variance | 0.512 | +| learning_rate | 4.04e-05 | +| loss | -0.0266 | +| n_updates | 94824 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.00021 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1385 | +| iterations | 19753 | +| time_elapsed | 29188 | +| total_timesteps | 40454144 | +| train/ | | +| approx_kl | 0.014509033 | +| clip_fraction | 0.352 | +| clip_range | 0.0649 | +| entropy_loss | -6.21 | +| explained_variance | -0.191 | +| learning_rate | 4.04e-05 | +| loss | -0.0355 | +| n_updates | 94828 | +| policy_gradient_loss | -0.0196 | +| value_loss | 8.67e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1385 | +| iterations | 19754 | +| time_elapsed | 29190 | +| total_timesteps | 40456192 | +| train/ | | +| approx_kl | 0.012714683 | +| clip_fraction | 0.342 | +| clip_range | 0.0649 | +| entropy_loss | -6.56 | +| explained_variance | -0.178 | +| learning_rate | 4.04e-05 | +| loss | -0.0277 | +| n_updates | 94832 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000177 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1385 | +| iterations | 19755 | +| time_elapsed | 29191 | +| total_timesteps | 40458240 | +| train/ | | +| approx_kl | 0.012793771 | +| clip_fraction | 0.364 | +| clip_range | 0.0649 | +| entropy_loss | -6.61 | +| explained_variance | -0.109 | +| learning_rate | 4.04e-05 | +| loss | -0.0285 | +| n_updates | 94836 | +| policy_gradient_loss | -0.0178 | +| value_loss | 8.91e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1385 | +| iterations | 19756 | +| time_elapsed | 29193 | +| total_timesteps | 40460288 | +| train/ | | +| approx_kl | 0.01337852 | +| clip_fraction | 0.325 | +| clip_range | 0.0649 | +| entropy_loss | -6.45 | +| explained_variance | 0.318 | +| learning_rate | 4.04e-05 | +| loss | -0.0245 | +| n_updates | 94840 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000106 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1385 | +| iterations | 19757 | +| time_elapsed | 29194 | +| total_timesteps | 40462336 | +| train/ | | +| approx_kl | 0.01265654 | +| clip_fraction | 0.315 | +| clip_range | 0.0649 | +| entropy_loss | -6.23 | +| explained_variance | 0.429 | +| learning_rate | 4.04e-05 | +| loss | -0.025 | +| n_updates | 94844 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000192 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1385 | +| iterations | 19758 | +| time_elapsed | 29196 | +| total_timesteps | 40464384 | +| train/ | | +| approx_kl | 0.0129101295 | +| clip_fraction | 0.304 | +| clip_range | 0.0649 | +| entropy_loss | -6.18 | +| explained_variance | 0.209 | +| learning_rate | 4.04e-05 | +| loss | -0.0244 | +| n_updates | 94848 | +| policy_gradient_loss | -0.0147 | +| value_loss | 0.000221 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1385 | +| iterations | 19759 | +| time_elapsed | 29197 | +| total_timesteps | 40466432 | +| train/ | | +| approx_kl | 0.014287683 | +| clip_fraction | 0.364 | +| clip_range | 0.0649 | +| entropy_loss | -5.5 | +| explained_variance | 0.479 | +| learning_rate | 4.04e-05 | +| loss | -0.0273 | +| n_updates | 94852 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000153 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1385 | +| iterations | 19760 | +| time_elapsed | 29199 | +| total_timesteps | 40468480 | +| train/ | | +| approx_kl | 0.011969056 | +| clip_fraction | 0.331 | +| clip_range | 0.0649 | +| entropy_loss | -5.76 | +| explained_variance | 0.615 | +| learning_rate | 4.04e-05 | +| loss | -0.0314 | +| n_updates | 94856 | +| policy_gradient_loss | -0.0184 | +| value_loss | 9.47e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1385 | +| iterations | 19761 | +| time_elapsed | 29200 | +| total_timesteps | 40470528 | +| train/ | | +| approx_kl | 0.016953155 | +| clip_fraction | 0.343 | +| clip_range | 0.0649 | +| entropy_loss | -5.36 | +| explained_variance | 0.78 | +| learning_rate | 4.04e-05 | +| loss | -0.0288 | +| n_updates | 94860 | +| policy_gradient_loss | -0.0182 | +| value_loss | 8.44e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1385 | +| iterations | 19762 | +| time_elapsed | 29202 | +| total_timesteps | 40472576 | +| train/ | | +| approx_kl | 0.010793458 | +| clip_fraction | 0.299 | +| clip_range | 0.0649 | +| entropy_loss | -5.39 | +| explained_variance | 0.295 | +| learning_rate | 4.04e-05 | +| loss | -0.0224 | +| n_updates | 94864 | +| policy_gradient_loss | -0.0145 | +| value_loss | 0.000228 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1385 | +| iterations | 19763 | +| time_elapsed | 29203 | +| total_timesteps | 40474624 | +| train/ | | +| approx_kl | 0.012938339 | +| clip_fraction | 0.315 | +| clip_range | 0.0649 | +| entropy_loss | -5.8 | +| explained_variance | 0.324 | +| learning_rate | 4.04e-05 | +| loss | -0.0265 | +| n_updates | 94868 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.000249 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1385 | +| iterations | 19764 | +| time_elapsed | 29205 | +| total_timesteps | 40476672 | +| train/ | | +| approx_kl | 0.012411149 | +| clip_fraction | 0.355 | +| clip_range | 0.0649 | +| entropy_loss | -5.94 | +| explained_variance | -0.407 | +| learning_rate | 4.04e-05 | +| loss | -0.0339 | +| n_updates | 94872 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000113 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1385 | +| iterations | 19765 | +| time_elapsed | 29206 | +| total_timesteps | 40478720 | +| train/ | | +| approx_kl | 0.011721954 | +| clip_fraction | 0.342 | +| clip_range | 0.0649 | +| entropy_loss | -5.94 | +| explained_variance | -0.112 | +| learning_rate | 4.04e-05 | +| loss | -0.0236 | +| n_updates | 94876 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.000185 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1385 | +| iterations | 19766 | +| time_elapsed | 29208 | +| total_timesteps | 40480768 | +| train/ | | +| approx_kl | 0.009757632 | +| clip_fraction | 0.319 | +| clip_range | 0.0649 | +| entropy_loss | -6.57 | +| explained_variance | -0.184 | +| learning_rate | 4.04e-05 | +| loss | -0.0291 | +| n_updates | 94880 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000166 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1385 | +| iterations | 19767 | +| time_elapsed | 29209 | +| total_timesteps | 40482816 | +| train/ | | +| approx_kl | 0.011325851 | +| clip_fraction | 0.311 | +| clip_range | 0.0649 | +| entropy_loss | -5.75 | +| explained_variance | 0.537 | +| learning_rate | 4.04e-05 | +| loss | -0.0312 | +| n_updates | 94884 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000149 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1385 | +| iterations | 19768 | +| time_elapsed | 29211 | +| total_timesteps | 40484864 | +| train/ | | +| approx_kl | 0.013460726 | +| clip_fraction | 0.365 | +| clip_range | 0.0649 | +| entropy_loss | -5.79 | +| explained_variance | -0.0627 | +| learning_rate | 4.04e-05 | +| loss | -0.0278 | +| n_updates | 94888 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000119 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1385 | +| iterations | 19769 | +| time_elapsed | 29212 | +| total_timesteps | 40486912 | +| train/ | | +| approx_kl | 0.0140178995 | +| clip_fraction | 0.317 | +| clip_range | 0.0649 | +| entropy_loss | -5.44 | +| explained_variance | 0.718 | +| learning_rate | 4.04e-05 | +| loss | -0.0296 | +| n_updates | 94892 | +| policy_gradient_loss | -0.0163 | +| value_loss | 8.46e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1385 | +| iterations | 19770 | +| time_elapsed | 29214 | +| total_timesteps | 40488960 | +| train/ | | +| approx_kl | 0.015271107 | +| clip_fraction | 0.355 | +| clip_range | 0.0649 | +| entropy_loss | -6.29 | +| explained_variance | -0.0599 | +| learning_rate | 4.04e-05 | +| loss | -0.0251 | +| n_updates | 94896 | +| policy_gradient_loss | -0.0172 | +| value_loss | 9.31e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1385 | +| iterations | 19771 | +| time_elapsed | 29215 | +| total_timesteps | 40491008 | +| train/ | | +| approx_kl | 0.011817537 | +| clip_fraction | 0.312 | +| clip_range | 0.0649 | +| entropy_loss | -6.06 | +| explained_variance | 0.422 | +| learning_rate | 4.04e-05 | +| loss | -0.0275 | +| n_updates | 94900 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000126 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1385 | +| iterations | 19772 | +| time_elapsed | 29217 | +| total_timesteps | 40493056 | +| train/ | | +| approx_kl | 0.010770805 | +| clip_fraction | 0.297 | +| clip_range | 0.0649 | +| entropy_loss | -5.8 | +| explained_variance | 0.63 | +| learning_rate | 4.04e-05 | +| loss | -0.024 | +| n_updates | 94904 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.000119 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1385 | +| iterations | 19773 | +| time_elapsed | 29218 | +| total_timesteps | 40495104 | +| train/ | | +| approx_kl | 0.009475861 | +| clip_fraction | 0.287 | +| clip_range | 0.0649 | +| entropy_loss | -5.94 | +| explained_variance | 0.203 | +| learning_rate | 4.04e-05 | +| loss | -0.0206 | +| n_updates | 94908 | +| policy_gradient_loss | -0.0113 | +| value_loss | 0.000362 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1385 | +| iterations | 19774 | +| time_elapsed | 29220 | +| total_timesteps | 40497152 | +| train/ | | +| approx_kl | 0.013964855 | +| clip_fraction | 0.333 | +| clip_range | 0.0649 | +| entropy_loss | -6.37 | +| explained_variance | 0.533 | +| learning_rate | 4.04e-05 | +| loss | -0.0283 | +| n_updates | 94912 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000103 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1385 | +| iterations | 19775 | +| time_elapsed | 29221 | +| total_timesteps | 40499200 | +| train/ | | +| approx_kl | 0.014676325 | +| clip_fraction | 0.303 | +| clip_range | 0.0649 | +| entropy_loss | -6.07 | +| explained_variance | 0.177 | +| learning_rate | 4.04e-05 | +| loss | -0.0243 | +| n_updates | 94916 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000136 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1385 | +| iterations | 19776 | +| time_elapsed | 29223 | +| total_timesteps | 40501248 | +| train/ | | +| approx_kl | 0.017530058 | +| clip_fraction | 0.338 | +| clip_range | 0.0649 | +| entropy_loss | -5.64 | +| explained_variance | 0.707 | +| learning_rate | 4.04e-05 | +| loss | -0.03 | +| n_updates | 94920 | +| policy_gradient_loss | -0.0176 | +| value_loss | 8.16e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1385 | +| iterations | 19777 | +| time_elapsed | 29225 | +| total_timesteps | 40503296 | +| train/ | | +| approx_kl | 0.014093443 | +| clip_fraction | 0.364 | +| clip_range | 0.0649 | +| entropy_loss | -5.17 | +| explained_variance | 0.677 | +| learning_rate | 4.04e-05 | +| loss | -0.0324 | +| n_updates | 94924 | +| policy_gradient_loss | -0.0201 | +| value_loss | 6.59e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1385 | +| iterations | 19778 | +| time_elapsed | 29226 | +| total_timesteps | 40505344 | +| train/ | | +| approx_kl | 0.014448579 | +| clip_fraction | 0.341 | +| clip_range | 0.0649 | +| entropy_loss | -6.11 | +| explained_variance | 0.362 | +| learning_rate | 4.04e-05 | +| loss | -0.0269 | +| n_updates | 94928 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000136 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1385 | +| iterations | 19779 | +| time_elapsed | 29228 | +| total_timesteps | 40507392 | +| train/ | | +| approx_kl | 0.012577329 | +| clip_fraction | 0.326 | +| clip_range | 0.0649 | +| entropy_loss | -5.52 | +| explained_variance | 0.516 | +| learning_rate | 4.04e-05 | +| loss | -0.0284 | +| n_updates | 94932 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.00019 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1385 | +| iterations | 19780 | +| time_elapsed | 29229 | +| total_timesteps | 40509440 | +| train/ | | +| approx_kl | 0.013439824 | +| clip_fraction | 0.34 | +| clip_range | 0.0649 | +| entropy_loss | -5.88 | +| explained_variance | 0.284 | +| learning_rate | 4.04e-05 | +| loss | -0.0246 | +| n_updates | 94936 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000158 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1385 | +| iterations | 19781 | +| time_elapsed | 29231 | +| total_timesteps | 40511488 | +| train/ | | +| approx_kl | 0.012418684 | +| clip_fraction | 0.308 | +| clip_range | 0.0649 | +| entropy_loss | -5.76 | +| explained_variance | 0.508 | +| learning_rate | 4.04e-05 | +| loss | -0.0241 | +| n_updates | 94940 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.000249 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1385 | +| iterations | 19782 | +| time_elapsed | 29232 | +| total_timesteps | 40513536 | +| train/ | | +| approx_kl | 0.011465933 | +| clip_fraction | 0.296 | +| clip_range | 0.0649 | +| entropy_loss | -5.47 | +| explained_variance | 0.411 | +| learning_rate | 4.04e-05 | +| loss | -0.0213 | +| n_updates | 94944 | +| policy_gradient_loss | -0.0137 | +| value_loss | 0.000217 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1385 | +| iterations | 19783 | +| time_elapsed | 29234 | +| total_timesteps | 40515584 | +| train/ | | +| approx_kl | 0.013810504 | +| clip_fraction | 0.359 | +| clip_range | 0.0649 | +| entropy_loss | -6.03 | +| explained_variance | -0.114 | +| learning_rate | 4.04e-05 | +| loss | -0.0344 | +| n_updates | 94948 | +| policy_gradient_loss | -0.0207 | +| value_loss | 9.79e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1385 | +| iterations | 19784 | +| time_elapsed | 29235 | +| total_timesteps | 40517632 | +| train/ | | +| approx_kl | 0.010112874 | +| clip_fraction | 0.302 | +| clip_range | 0.0649 | +| entropy_loss | -5.61 | +| explained_variance | 0.63 | +| learning_rate | 4.04e-05 | +| loss | -0.0241 | +| n_updates | 94952 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.000205 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1385 | +| iterations | 19785 | +| time_elapsed | 29237 | +| total_timesteps | 40519680 | +| train/ | | +| approx_kl | 0.014375074 | +| clip_fraction | 0.312 | +| clip_range | 0.0649 | +| entropy_loss | -5.66 | +| explained_variance | 0.463 | +| learning_rate | 4.04e-05 | +| loss | -0.0213 | +| n_updates | 94956 | +| policy_gradient_loss | -0.0137 | +| value_loss | 0.000254 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1385 | +| iterations | 19786 | +| time_elapsed | 29239 | +| total_timesteps | 40521728 | +| train/ | | +| approx_kl | 0.013741638 | +| clip_fraction | 0.355 | +| clip_range | 0.0649 | +| entropy_loss | -5.13 | +| explained_variance | 0.57 | +| learning_rate | 4.04e-05 | +| loss | -0.0342 | +| n_updates | 94960 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000117 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1385 | +| iterations | 19787 | +| time_elapsed | 29240 | +| total_timesteps | 40523776 | +| train/ | | +| approx_kl | 0.014404406 | +| clip_fraction | 0.348 | +| clip_range | 0.0649 | +| entropy_loss | -6.15 | +| explained_variance | -0.185 | +| learning_rate | 4.04e-05 | +| loss | -0.0364 | +| n_updates | 94964 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000119 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1385 | +| iterations | 19788 | +| time_elapsed | 29242 | +| total_timesteps | 40525824 | +| train/ | | +| approx_kl | 0.010730277 | +| clip_fraction | 0.311 | +| clip_range | 0.0649 | +| entropy_loss | -6.71 | +| explained_variance | 0.393 | +| learning_rate | 4.04e-05 | +| loss | -0.0278 | +| n_updates | 94968 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000128 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1385 | +| iterations | 19789 | +| time_elapsed | 29243 | +| total_timesteps | 40527872 | +| train/ | | +| approx_kl | 0.009026626 | +| clip_fraction | 0.319 | +| clip_range | 0.0649 | +| entropy_loss | -6.56 | +| explained_variance | 0.0225 | +| learning_rate | 4.04e-05 | +| loss | -0.0272 | +| n_updates | 94972 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000186 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1385 | +| iterations | 19790 | +| time_elapsed | 29245 | +| total_timesteps | 40529920 | +| train/ | | +| approx_kl | 0.007821217 | +| clip_fraction | 0.304 | +| clip_range | 0.0649 | +| entropy_loss | -5.88 | +| explained_variance | 0.381 | +| learning_rate | 4.04e-05 | +| loss | -0.0229 | +| n_updates | 94976 | +| policy_gradient_loss | -0.0126 | +| value_loss | 0.00042 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1385 | +| iterations | 19791 | +| time_elapsed | 29246 | +| total_timesteps | 40531968 | +| train/ | | +| approx_kl | 0.010345731 | +| clip_fraction | 0.306 | +| clip_range | 0.0649 | +| entropy_loss | -5.83 | +| explained_variance | 0.543 | +| learning_rate | 4.04e-05 | +| loss | -0.0295 | +| n_updates | 94980 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000178 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1385 | +| iterations | 19792 | +| time_elapsed | 29248 | +| total_timesteps | 40534016 | +| train/ | | +| approx_kl | 0.013093168 | +| clip_fraction | 0.368 | +| clip_range | 0.0649 | +| entropy_loss | -5.71 | +| explained_variance | 0.0263 | +| learning_rate | 4.04e-05 | +| loss | -0.0333 | +| n_updates | 94984 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000104 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1385 | +| iterations | 19793 | +| time_elapsed | 29249 | +| total_timesteps | 40536064 | +| train/ | | +| approx_kl | 0.014792461 | +| clip_fraction | 0.337 | +| clip_range | 0.0649 | +| entropy_loss | -5.45 | +| explained_variance | 0.63 | +| learning_rate | 4.04e-05 | +| loss | -0.0338 | +| n_updates | 94988 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000109 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1385 | +| iterations | 19794 | +| time_elapsed | 29251 | +| total_timesteps | 40538112 | +| train/ | | +| approx_kl | 0.011817614 | +| clip_fraction | 0.35 | +| clip_range | 0.0649 | +| entropy_loss | -5.68 | +| explained_variance | 0.417 | +| learning_rate | 4.04e-05 | +| loss | -0.0212 | +| n_updates | 94992 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000136 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1385 | +| iterations | 19795 | +| time_elapsed | 29252 | +| total_timesteps | 40540160 | +| train/ | | +| approx_kl | 0.018610936 | +| clip_fraction | 0.357 | +| clip_range | 0.0649 | +| entropy_loss | -5.58 | +| explained_variance | 0.476 | +| learning_rate | 4.04e-05 | +| loss | -0.029 | +| n_updates | 94996 | +| policy_gradient_loss | -0.0174 | +| value_loss | 9.04e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1385 | +| iterations | 19796 | +| time_elapsed | 29254 | +| total_timesteps | 40542208 | +| train/ | | +| approx_kl | 0.013071929 | +| clip_fraction | 0.307 | +| clip_range | 0.0649 | +| entropy_loss | -5.3 | +| explained_variance | 0.607 | +| learning_rate | 4.04e-05 | +| loss | -0.024 | +| n_updates | 95000 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.000211 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1385 | +| iterations | 19797 | +| time_elapsed | 29255 | +| total_timesteps | 40544256 | +| train/ | | +| approx_kl | 0.01107798 | +| clip_fraction | 0.296 | +| clip_range | 0.0649 | +| entropy_loss | -5.05 | +| explained_variance | 0.307 | +| learning_rate | 4.04e-05 | +| loss | -0.0218 | +| n_updates | 95004 | +| policy_gradient_loss | -0.0145 | +| value_loss | 0.000301 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1385 | +| iterations | 19798 | +| time_elapsed | 29257 | +| total_timesteps | 40546304 | +| train/ | | +| approx_kl | 0.015348556 | +| clip_fraction | 0.33 | +| clip_range | 0.0649 | +| entropy_loss | -5.45 | +| explained_variance | 0.678 | +| learning_rate | 4.04e-05 | +| loss | -0.0299 | +| n_updates | 95008 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000109 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1385 | +| iterations | 19799 | +| time_elapsed | 29259 | +| total_timesteps | 40548352 | +| train/ | | +| approx_kl | 0.013758396 | +| clip_fraction | 0.344 | +| clip_range | 0.0649 | +| entropy_loss | -6.49 | +| explained_variance | -0.128 | +| learning_rate | 4.04e-05 | +| loss | -0.0256 | +| n_updates | 95012 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000179 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1385 | +| iterations | 19800 | +| time_elapsed | 29260 | +| total_timesteps | 40550400 | +| train/ | | +| approx_kl | 0.01576496 | +| clip_fraction | 0.347 | +| clip_range | 0.0649 | +| entropy_loss | -5.66 | +| explained_variance | 0.547 | +| learning_rate | 4.04e-05 | +| loss | -0.0342 | +| n_updates | 95016 | +| policy_gradient_loss | -0.0205 | +| value_loss | 6.8e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1385 | +| iterations | 19801 | +| time_elapsed | 29262 | +| total_timesteps | 40552448 | +| train/ | | +| approx_kl | 0.016170735 | +| clip_fraction | 0.349 | +| clip_range | 0.0649 | +| entropy_loss | -5.93 | +| explained_variance | 0.35 | +| learning_rate | 4.04e-05 | +| loss | -0.0211 | +| n_updates | 95020 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000164 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1385 | +| iterations | 19802 | +| time_elapsed | 29263 | +| total_timesteps | 40554496 | +| train/ | | +| approx_kl | 0.01531444 | +| clip_fraction | 0.363 | +| clip_range | 0.0649 | +| entropy_loss | -5.95 | +| explained_variance | 0.456 | +| learning_rate | 4.04e-05 | +| loss | -0.0267 | +| n_updates | 95024 | +| policy_gradient_loss | -0.019 | +| value_loss | 8.86e-05 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1385 | +| iterations | 19803 | +| time_elapsed | 29265 | +| total_timesteps | 40556544 | +| train/ | | +| approx_kl | 0.01371622 | +| clip_fraction | 0.338 | +| clip_range | 0.0649 | +| entropy_loss | -5.77 | +| explained_variance | 0.301 | +| learning_rate | 4.04e-05 | +| loss | -0.0178 | +| n_updates | 95028 | +| policy_gradient_loss | -0.0147 | +| value_loss | 0.000181 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1385 | +| iterations | 19804 | +| time_elapsed | 29266 | +| total_timesteps | 40558592 | +| train/ | | +| approx_kl | 0.016354138 | +| clip_fraction | 0.338 | +| clip_range | 0.0649 | +| entropy_loss | -5.53 | +| explained_variance | 0.563 | +| learning_rate | 4.04e-05 | +| loss | -0.0368 | +| n_updates | 95032 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000108 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1385 | +| iterations | 19805 | +| time_elapsed | 29268 | +| total_timesteps | 40560640 | +| train/ | | +| approx_kl | 0.012185566 | +| clip_fraction | 0.342 | +| clip_range | 0.0649 | +| entropy_loss | -5.73 | +| explained_variance | 0.611 | +| learning_rate | 4.04e-05 | +| loss | -0.0289 | +| n_updates | 95036 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000113 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1385 | +| iterations | 19806 | +| time_elapsed | 29269 | +| total_timesteps | 40562688 | +| train/ | | +| approx_kl | 0.011805294 | +| clip_fraction | 0.312 | +| clip_range | 0.0649 | +| entropy_loss | -5.75 | +| explained_variance | 0.279 | +| learning_rate | 4.04e-05 | +| loss | -0.0264 | +| n_updates | 95040 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000186 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1385 | +| iterations | 19807 | +| time_elapsed | 29271 | +| total_timesteps | 40564736 | +| train/ | | +| approx_kl | 0.011012914 | +| clip_fraction | 0.3 | +| clip_range | 0.0649 | +| entropy_loss | -5.8 | +| explained_variance | 0.435 | +| learning_rate | 4.04e-05 | +| loss | -0.0252 | +| n_updates | 95044 | +| policy_gradient_loss | -0.0148 | +| value_loss | 0.000191 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1385 | +| iterations | 19808 | +| time_elapsed | 29272 | +| total_timesteps | 40566784 | +| train/ | | +| approx_kl | 0.010423299 | +| clip_fraction | 0.325 | +| clip_range | 0.0649 | +| entropy_loss | -5.69 | +| explained_variance | 0.507 | +| learning_rate | 4.04e-05 | +| loss | -0.028 | +| n_updates | 95048 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.00014 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1385 | +| iterations | 19809 | +| time_elapsed | 29274 | +| total_timesteps | 40568832 | +| train/ | | +| approx_kl | 0.015325039 | +| clip_fraction | 0.369 | +| clip_range | 0.0649 | +| entropy_loss | -6.07 | +| explained_variance | -0.536 | +| learning_rate | 4.04e-05 | +| loss | -0.0288 | +| n_updates | 95052 | +| policy_gradient_loss | -0.02 | +| value_loss | 4.98e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1385 | +| iterations | 19810 | +| time_elapsed | 29276 | +| total_timesteps | 40570880 | +| train/ | | +| approx_kl | 0.014134468 | +| clip_fraction | 0.338 | +| clip_range | 0.0649 | +| entropy_loss | -5.95 | +| explained_variance | 0.276 | +| learning_rate | 4.04e-05 | +| loss | -0.0294 | +| n_updates | 95056 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1385 | +| iterations | 19811 | +| time_elapsed | 29277 | +| total_timesteps | 40572928 | +| train/ | | +| approx_kl | 0.013697078 | +| clip_fraction | 0.295 | +| clip_range | 0.0649 | +| entropy_loss | -5.6 | +| explained_variance | 0.511 | +| learning_rate | 4.04e-05 | +| loss | -0.0257 | +| n_updates | 95060 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000126 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1385 | +| iterations | 19812 | +| time_elapsed | 29279 | +| total_timesteps | 40574976 | +| train/ | | +| approx_kl | 0.013731617 | +| clip_fraction | 0.306 | +| clip_range | 0.0649 | +| entropy_loss | -5.97 | +| explained_variance | 0.46 | +| learning_rate | 4.04e-05 | +| loss | -0.0257 | +| n_updates | 95064 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000155 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1385 | +| iterations | 19813 | +| time_elapsed | 29280 | +| total_timesteps | 40577024 | +| train/ | | +| approx_kl | 0.010791919 | +| clip_fraction | 0.334 | +| clip_range | 0.0649 | +| entropy_loss | -5.91 | +| explained_variance | 0.179 | +| learning_rate | 4.04e-05 | +| loss | -0.0248 | +| n_updates | 95068 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000223 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1385 | +| iterations | 19814 | +| time_elapsed | 29282 | +| total_timesteps | 40579072 | +| train/ | | +| approx_kl | 0.013974419 | +| clip_fraction | 0.366 | +| clip_range | 0.0649 | +| entropy_loss | -6.33 | +| explained_variance | 0.164 | +| learning_rate | 4.04e-05 | +| loss | -0.0307 | +| n_updates | 95072 | +| policy_gradient_loss | -0.0196 | +| value_loss | 7.26e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1385 | +| iterations | 19815 | +| time_elapsed | 29283 | +| total_timesteps | 40581120 | +| train/ | | +| approx_kl | 0.012515878 | +| clip_fraction | 0.325 | +| clip_range | 0.0649 | +| entropy_loss | -5.57 | +| explained_variance | 0.524 | +| learning_rate | 4.04e-05 | +| loss | -0.0223 | +| n_updates | 95076 | +| policy_gradient_loss | -0.0146 | +| value_loss | 0.000155 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1385 | +| iterations | 19816 | +| time_elapsed | 29285 | +| total_timesteps | 40583168 | +| train/ | | +| approx_kl | 0.011819249 | +| clip_fraction | 0.301 | +| clip_range | 0.0649 | +| entropy_loss | -5.07 | +| explained_variance | 0.571 | +| learning_rate | 4.04e-05 | +| loss | -0.0227 | +| n_updates | 95080 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000162 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1385 | +| iterations | 19817 | +| time_elapsed | 29286 | +| total_timesteps | 40585216 | +| train/ | | +| approx_kl | 0.0149872545 | +| clip_fraction | 0.352 | +| clip_range | 0.0649 | +| entropy_loss | -5.15 | +| explained_variance | 0.679 | +| learning_rate | 4.04e-05 | +| loss | -0.0264 | +| n_updates | 95084 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000112 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1385 | +| iterations | 19818 | +| time_elapsed | 29288 | +| total_timesteps | 40587264 | +| train/ | | +| approx_kl | 0.014305587 | +| clip_fraction | 0.341 | +| clip_range | 0.0649 | +| entropy_loss | -5.3 | +| explained_variance | 0.409 | +| learning_rate | 4.04e-05 | +| loss | -0.0249 | +| n_updates | 95088 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000136 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1385 | +| iterations | 19819 | +| time_elapsed | 29289 | +| total_timesteps | 40589312 | +| train/ | | +| approx_kl | 0.012667542 | +| clip_fraction | 0.327 | +| clip_range | 0.0649 | +| entropy_loss | -5.7 | +| explained_variance | 0.456 | +| learning_rate | 4.04e-05 | +| loss | -0.028 | +| n_updates | 95092 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.00015 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1385 | +| iterations | 19820 | +| time_elapsed | 29291 | +| total_timesteps | 40591360 | +| train/ | | +| approx_kl | 0.015403521 | +| clip_fraction | 0.351 | +| clip_range | 0.0649 | +| entropy_loss | -5.86 | +| explained_variance | 0.73 | +| learning_rate | 4.04e-05 | +| loss | -0.0324 | +| n_updates | 95096 | +| policy_gradient_loss | -0.0196 | +| value_loss | 5.34e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.315 | +| time/ | | +| fps | 1385 | +| iterations | 19821 | +| time_elapsed | 29292 | +| total_timesteps | 40593408 | +| train/ | | +| approx_kl | 0.013778361 | +| clip_fraction | 0.32 | +| clip_range | 0.0649 | +| entropy_loss | -5.57 | +| explained_variance | -0.0116 | +| learning_rate | 4.04e-05 | +| loss | -0.027 | +| n_updates | 95100 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000154 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1385 | +| iterations | 19822 | +| time_elapsed | 29294 | +| total_timesteps | 40595456 | +| train/ | | +| approx_kl | 0.012820119 | +| clip_fraction | 0.367 | +| clip_range | 0.0649 | +| entropy_loss | -5.55 | +| explained_variance | 0.431 | +| learning_rate | 4.04e-05 | +| loss | -0.0339 | +| n_updates | 95104 | +| policy_gradient_loss | -0.0186 | +| value_loss | 8.49e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1385 | +| iterations | 19823 | +| time_elapsed | 29296 | +| total_timesteps | 40597504 | +| train/ | | +| approx_kl | 0.015796077 | +| clip_fraction | 0.335 | +| clip_range | 0.0649 | +| entropy_loss | -5.88 | +| explained_variance | 0.449 | +| learning_rate | 4.04e-05 | +| loss | -0.0241 | +| n_updates | 95108 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000176 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1385 | +| iterations | 19824 | +| time_elapsed | 29297 | +| total_timesteps | 40599552 | +| train/ | | +| approx_kl | 0.012015256 | +| clip_fraction | 0.324 | +| clip_range | 0.0649 | +| entropy_loss | -5.96 | +| explained_variance | 0.273 | +| learning_rate | 4.04e-05 | +| loss | -0.0254 | +| n_updates | 95112 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000164 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1385 | +| iterations | 19825 | +| time_elapsed | 29299 | +| total_timesteps | 40601600 | +| train/ | | +| approx_kl | 0.010446034 | +| clip_fraction | 0.319 | +| clip_range | 0.0649 | +| entropy_loss | -6.17 | +| explained_variance | 0.279 | +| learning_rate | 4.04e-05 | +| loss | -0.0259 | +| n_updates | 95116 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000114 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1385 | +| iterations | 19826 | +| time_elapsed | 29300 | +| total_timesteps | 40603648 | +| train/ | | +| approx_kl | 0.012366869 | +| clip_fraction | 0.264 | +| clip_range | 0.0648 | +| entropy_loss | -5.88 | +| explained_variance | 0.464 | +| learning_rate | 4.04e-05 | +| loss | -0.0245 | +| n_updates | 95120 | +| policy_gradient_loss | -0.0128 | +| value_loss | 0.000335 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1385 | +| iterations | 19827 | +| time_elapsed | 29302 | +| total_timesteps | 40605696 | +| train/ | | +| approx_kl | 0.013771803 | +| clip_fraction | 0.319 | +| clip_range | 0.0648 | +| entropy_loss | -4.84 | +| explained_variance | 0.772 | +| learning_rate | 4.04e-05 | +| loss | -0.0288 | +| n_updates | 95124 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000129 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1385 | +| iterations | 19828 | +| time_elapsed | 29303 | +| total_timesteps | 40607744 | +| train/ | | +| approx_kl | 0.0129172 | +| clip_fraction | 0.342 | +| clip_range | 0.0648 | +| entropy_loss | -5.61 | +| explained_variance | 0.542 | +| learning_rate | 4.04e-05 | +| loss | -0.0261 | +| n_updates | 95128 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000108 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1385 | +| iterations | 19829 | +| time_elapsed | 29305 | +| total_timesteps | 40609792 | +| train/ | | +| approx_kl | 0.013501486 | +| clip_fraction | 0.337 | +| clip_range | 0.0648 | +| entropy_loss | -6.3 | +| explained_variance | 0.232 | +| learning_rate | 4.04e-05 | +| loss | -0.0305 | +| n_updates | 95132 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000175 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1385 | +| iterations | 19830 | +| time_elapsed | 29306 | +| total_timesteps | 40611840 | +| train/ | | +| approx_kl | 0.014278449 | +| clip_fraction | 0.356 | +| clip_range | 0.0648 | +| entropy_loss | -6.06 | +| explained_variance | -0.0398 | +| learning_rate | 4.04e-05 | +| loss | -0.0274 | +| n_updates | 95136 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000142 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1385 | +| iterations | 19831 | +| time_elapsed | 29308 | +| total_timesteps | 40613888 | +| train/ | | +| approx_kl | 0.012531778 | +| clip_fraction | 0.35 | +| clip_range | 0.0648 | +| entropy_loss | -6.29 | +| explained_variance | 0.447 | +| learning_rate | 4.04e-05 | +| loss | -0.0311 | +| n_updates | 95140 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000101 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1385 | +| iterations | 19832 | +| time_elapsed | 29309 | +| total_timesteps | 40615936 | +| train/ | | +| approx_kl | 0.013714986 | +| clip_fraction | 0.307 | +| clip_range | 0.0648 | +| entropy_loss | -5.7 | +| explained_variance | 0.392 | +| learning_rate | 4.04e-05 | +| loss | -0.0252 | +| n_updates | 95144 | +| policy_gradient_loss | -0.0146 | +| value_loss | 0.000189 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1385 | +| iterations | 19833 | +| time_elapsed | 29311 | +| total_timesteps | 40617984 | +| train/ | | +| approx_kl | 0.01147877 | +| clip_fraction | 0.361 | +| clip_range | 0.0648 | +| entropy_loss | -5.73 | +| explained_variance | 0.298 | +| learning_rate | 4.04e-05 | +| loss | -0.026 | +| n_updates | 95148 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000126 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1385 | +| iterations | 19834 | +| time_elapsed | 29312 | +| total_timesteps | 40620032 | +| train/ | | +| approx_kl | 0.01259766 | +| clip_fraction | 0.365 | +| clip_range | 0.0648 | +| entropy_loss | -5.6 | +| explained_variance | 0.6 | +| learning_rate | 4.04e-05 | +| loss | -0.0331 | +| n_updates | 95152 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000107 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1385 | +| iterations | 19835 | +| time_elapsed | 29314 | +| total_timesteps | 40622080 | +| train/ | | +| approx_kl | 0.009369651 | +| clip_fraction | 0.332 | +| clip_range | 0.0648 | +| entropy_loss | -5.83 | +| explained_variance | 0.0602 | +| learning_rate | 4.04e-05 | +| loss | -0.0271 | +| n_updates | 95156 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000111 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1385 | +| iterations | 19836 | +| time_elapsed | 29315 | +| total_timesteps | 40624128 | +| train/ | | +| approx_kl | 0.009330068 | +| clip_fraction | 0.307 | +| clip_range | 0.0648 | +| entropy_loss | -5.68 | +| explained_variance | 0.339 | +| learning_rate | 4.04e-05 | +| loss | -0.0218 | +| n_updates | 95160 | +| policy_gradient_loss | -0.0138 | +| value_loss | 0.000272 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1385 | +| iterations | 19837 | +| time_elapsed | 29317 | +| total_timesteps | 40626176 | +| train/ | | +| approx_kl | 0.010668529 | +| clip_fraction | 0.315 | +| clip_range | 0.0648 | +| entropy_loss | -5.41 | +| explained_variance | 0.505 | +| learning_rate | 4.04e-05 | +| loss | -0.0255 | +| n_updates | 95164 | +| policy_gradient_loss | -0.0147 | +| value_loss | 0.000152 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1385 | +| iterations | 19838 | +| time_elapsed | 29318 | +| total_timesteps | 40628224 | +| train/ | | +| approx_kl | 0.014611092 | +| clip_fraction | 0.329 | +| clip_range | 0.0648 | +| entropy_loss | -4.83 | +| explained_variance | 0.723 | +| learning_rate | 4.04e-05 | +| loss | -0.0231 | +| n_updates | 95168 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000106 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1385 | +| iterations | 19839 | +| time_elapsed | 29320 | +| total_timesteps | 40630272 | +| train/ | | +| approx_kl | 0.013654051 | +| clip_fraction | 0.333 | +| clip_range | 0.0648 | +| entropy_loss | -5.53 | +| explained_variance | 0.67 | +| learning_rate | 4.04e-05 | +| loss | -0.0298 | +| n_updates | 95172 | +| policy_gradient_loss | -0.0177 | +| value_loss | 9.61e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1385 | +| iterations | 19840 | +| time_elapsed | 29321 | +| total_timesteps | 40632320 | +| train/ | | +| approx_kl | 0.013917148 | +| clip_fraction | 0.348 | +| clip_range | 0.0648 | +| entropy_loss | -5.6 | +| explained_variance | 0.728 | +| learning_rate | 4.04e-05 | +| loss | -0.0308 | +| n_updates | 95176 | +| policy_gradient_loss | -0.0193 | +| value_loss | 7.19e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1385 | +| iterations | 19841 | +| time_elapsed | 29323 | +| total_timesteps | 40634368 | +| train/ | | +| approx_kl | 0.011366923 | +| clip_fraction | 0.33 | +| clip_range | 0.0648 | +| entropy_loss | -5.71 | +| explained_variance | 0.516 | +| learning_rate | 4.03e-05 | +| loss | -0.0284 | +| n_updates | 95180 | +| policy_gradient_loss | -0.0165 | +| value_loss | 9.46e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1385 | +| iterations | 19842 | +| time_elapsed | 29324 | +| total_timesteps | 40636416 | +| train/ | | +| approx_kl | 0.016686143 | +| clip_fraction | 0.322 | +| clip_range | 0.0648 | +| entropy_loss | -6.26 | +| explained_variance | -0.0636 | +| learning_rate | 4.03e-05 | +| loss | -0.0237 | +| n_updates | 95184 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1385 | +| iterations | 19843 | +| time_elapsed | 29326 | +| total_timesteps | 40638464 | +| train/ | | +| approx_kl | 0.013472376 | +| clip_fraction | 0.343 | +| clip_range | 0.0648 | +| entropy_loss | -6.43 | +| explained_variance | -0.224 | +| learning_rate | 4.03e-05 | +| loss | -0.0276 | +| n_updates | 95188 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000105 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1385 | +| iterations | 19844 | +| time_elapsed | 29327 | +| total_timesteps | 40640512 | +| train/ | | +| approx_kl | 0.012565916 | +| clip_fraction | 0.306 | +| clip_range | 0.0648 | +| entropy_loss | -6.29 | +| explained_variance | 0.343 | +| learning_rate | 4.03e-05 | +| loss | -0.0226 | +| n_updates | 95192 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.00015 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.306 | +| time/ | | +| fps | 1385 | +| iterations | 19845 | +| time_elapsed | 29329 | +| total_timesteps | 40642560 | +| train/ | | +| approx_kl | 0.011665399 | +| clip_fraction | 0.347 | +| clip_range | 0.0648 | +| entropy_loss | -5.58 | +| explained_variance | 0.413 | +| learning_rate | 4.03e-05 | +| loss | -0.0297 | +| n_updates | 95196 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000196 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 1385 | +| iterations | 19846 | +| time_elapsed | 29330 | +| total_timesteps | 40644608 | +| train/ | | +| approx_kl | 0.015869034 | +| clip_fraction | 0.403 | +| clip_range | 0.0648 | +| entropy_loss | -5.6 | +| explained_variance | -0.143 | +| learning_rate | 4.03e-05 | +| loss | -0.0356 | +| n_updates | 95200 | +| policy_gradient_loss | -0.0226 | +| value_loss | 5.79e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 1385 | +| iterations | 19847 | +| time_elapsed | 29332 | +| total_timesteps | 40646656 | +| train/ | | +| approx_kl | 0.013583851 | +| clip_fraction | 0.332 | +| clip_range | 0.0648 | +| entropy_loss | -5.62 | +| explained_variance | 0.846 | +| learning_rate | 4.03e-05 | +| loss | -0.0245 | +| n_updates | 95204 | +| policy_gradient_loss | -0.017 | +| value_loss | 4.6e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1385 | +| iterations | 19848 | +| time_elapsed | 29333 | +| total_timesteps | 40648704 | +| train/ | | +| approx_kl | 0.01401083 | +| clip_fraction | 0.328 | +| clip_range | 0.0648 | +| entropy_loss | -5.46 | +| explained_variance | 0.547 | +| learning_rate | 4.03e-05 | +| loss | -0.0256 | +| n_updates | 95208 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000134 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.306 | +| time/ | | +| fps | 1385 | +| iterations | 19849 | +| time_elapsed | 29335 | +| total_timesteps | 40650752 | +| train/ | | +| approx_kl | 0.013494168 | +| clip_fraction | 0.364 | +| clip_range | 0.0648 | +| entropy_loss | -5.86 | +| explained_variance | 0.408 | +| learning_rate | 4.03e-05 | +| loss | -0.0309 | +| n_updates | 95212 | +| policy_gradient_loss | -0.0189 | +| value_loss | 8.42e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1385 | +| iterations | 19850 | +| time_elapsed | 29337 | +| total_timesteps | 40652800 | +| train/ | | +| approx_kl | 0.013730515 | +| clip_fraction | 0.346 | +| clip_range | 0.0648 | +| entropy_loss | -5.69 | +| explained_variance | 0.795 | +| learning_rate | 4.03e-05 | +| loss | -0.0264 | +| n_updates | 95216 | +| policy_gradient_loss | -0.018 | +| value_loss | 5.88e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.315 | +| time/ | | +| fps | 1385 | +| iterations | 19851 | +| time_elapsed | 29338 | +| total_timesteps | 40654848 | +| train/ | | +| approx_kl | 0.012503552 | +| clip_fraction | 0.32 | +| clip_range | 0.0648 | +| entropy_loss | -5.49 | +| explained_variance | 0.558 | +| learning_rate | 4.03e-05 | +| loss | -0.0287 | +| n_updates | 95220 | +| policy_gradient_loss | -0.017 | +| value_loss | 7.29e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1385 | +| iterations | 19852 | +| time_elapsed | 29340 | +| total_timesteps | 40656896 | +| train/ | | +| approx_kl | 0.00893571 | +| clip_fraction | 0.295 | +| clip_range | 0.0648 | +| entropy_loss | -5.65 | +| explained_variance | 0.182 | +| learning_rate | 4.03e-05 | +| loss | -0.0234 | +| n_updates | 95224 | +| policy_gradient_loss | -0.0128 | +| value_loss | 0.000473 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1385 | +| iterations | 19853 | +| time_elapsed | 29341 | +| total_timesteps | 40658944 | +| train/ | | +| approx_kl | 0.014519262 | +| clip_fraction | 0.335 | +| clip_range | 0.0648 | +| entropy_loss | -5.48 | +| explained_variance | 0.31 | +| learning_rate | 4.03e-05 | +| loss | -0.0228 | +| n_updates | 95228 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.000312 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1385 | +| iterations | 19854 | +| time_elapsed | 29343 | +| total_timesteps | 40660992 | +| train/ | | +| approx_kl | 0.012781501 | +| clip_fraction | 0.376 | +| clip_range | 0.0648 | +| entropy_loss | -5.13 | +| explained_variance | 0.652 | +| learning_rate | 4.03e-05 | +| loss | -0.0332 | +| n_updates | 95232 | +| policy_gradient_loss | -0.0204 | +| value_loss | 7.29e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1385 | +| iterations | 19855 | +| time_elapsed | 29344 | +| total_timesteps | 40663040 | +| train/ | | +| approx_kl | 0.012416357 | +| clip_fraction | 0.335 | +| clip_range | 0.0648 | +| entropy_loss | -5.41 | +| explained_variance | 0.381 | +| learning_rate | 4.03e-05 | +| loss | -0.0322 | +| n_updates | 95236 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000151 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1385 | +| iterations | 19856 | +| time_elapsed | 29346 | +| total_timesteps | 40665088 | +| train/ | | +| approx_kl | 0.010573925 | +| clip_fraction | 0.334 | +| clip_range | 0.0648 | +| entropy_loss | -5.57 | +| explained_variance | 0.481 | +| learning_rate | 4.03e-05 | +| loss | -0.0261 | +| n_updates | 95240 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000152 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1385 | +| iterations | 19857 | +| time_elapsed | 29347 | +| total_timesteps | 40667136 | +| train/ | | +| approx_kl | 0.015471229 | +| clip_fraction | 0.356 | +| clip_range | 0.0648 | +| entropy_loss | -6.24 | +| explained_variance | -0.282 | +| learning_rate | 4.03e-05 | +| loss | -0.0285 | +| n_updates | 95244 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000114 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1385 | +| iterations | 19858 | +| time_elapsed | 29349 | +| total_timesteps | 40669184 | +| train/ | | +| approx_kl | 0.013387812 | +| clip_fraction | 0.342 | +| clip_range | 0.0648 | +| entropy_loss | -6.01 | +| explained_variance | 0.362 | +| learning_rate | 4.03e-05 | +| loss | -0.0253 | +| n_updates | 95248 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000128 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 1385 | +| iterations | 19859 | +| time_elapsed | 29350 | +| total_timesteps | 40671232 | +| train/ | | +| approx_kl | 0.011961922 | +| clip_fraction | 0.28 | +| clip_range | 0.0648 | +| entropy_loss | -5.04 | +| explained_variance | 0.672 | +| learning_rate | 4.03e-05 | +| loss | -0.0234 | +| n_updates | 95252 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.000119 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1385 | +| iterations | 19860 | +| time_elapsed | 29352 | +| total_timesteps | 40673280 | +| train/ | | +| approx_kl | 0.014029762 | +| clip_fraction | 0.294 | +| clip_range | 0.0648 | +| entropy_loss | -5.38 | +| explained_variance | 0.574 | +| learning_rate | 4.03e-05 | +| loss | -0.025 | +| n_updates | 95256 | +| policy_gradient_loss | -0.0148 | +| value_loss | 0.000165 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1385 | +| iterations | 19861 | +| time_elapsed | 29353 | +| total_timesteps | 40675328 | +| train/ | | +| approx_kl | 0.013062548 | +| clip_fraction | 0.324 | +| clip_range | 0.0648 | +| entropy_loss | -5.44 | +| explained_variance | 0.488 | +| learning_rate | 4.03e-05 | +| loss | -0.0265 | +| n_updates | 95260 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.000145 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1385 | +| iterations | 19862 | +| time_elapsed | 29355 | +| total_timesteps | 40677376 | +| train/ | | +| approx_kl | 0.010732627 | +| clip_fraction | 0.32 | +| clip_range | 0.0648 | +| entropy_loss | -5.53 | +| explained_variance | 0.3 | +| learning_rate | 4.03e-05 | +| loss | -0.0267 | +| n_updates | 95264 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000229 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1385 | +| iterations | 19863 | +| time_elapsed | 29356 | +| total_timesteps | 40679424 | +| train/ | | +| approx_kl | 0.013086149 | +| clip_fraction | 0.335 | +| clip_range | 0.0648 | +| entropy_loss | -5.61 | +| explained_variance | 0.569 | +| learning_rate | 4.03e-05 | +| loss | -0.0315 | +| n_updates | 95268 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.00012 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1385 | +| iterations | 19864 | +| time_elapsed | 29358 | +| total_timesteps | 40681472 | +| train/ | | +| approx_kl | 0.013043562 | +| clip_fraction | 0.328 | +| clip_range | 0.0648 | +| entropy_loss | -5.74 | +| explained_variance | 0.463 | +| learning_rate | 4.03e-05 | +| loss | -0.0314 | +| n_updates | 95272 | +| policy_gradient_loss | -0.0168 | +| value_loss | 7.89e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1385 | +| iterations | 19865 | +| time_elapsed | 29359 | +| total_timesteps | 40683520 | +| train/ | | +| approx_kl | 0.010079433 | +| clip_fraction | 0.326 | +| clip_range | 0.0648 | +| entropy_loss | -6.31 | +| explained_variance | -0.105 | +| learning_rate | 4.03e-05 | +| loss | -0.0292 | +| n_updates | 95276 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000108 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1385 | +| iterations | 19866 | +| time_elapsed | 29361 | +| total_timesteps | 40685568 | +| train/ | | +| approx_kl | 0.013959994 | +| clip_fraction | 0.346 | +| clip_range | 0.0648 | +| entropy_loss | -6.08 | +| explained_variance | 0.583 | +| learning_rate | 4.03e-05 | +| loss | -0.0294 | +| n_updates | 95280 | +| policy_gradient_loss | -0.0175 | +| value_loss | 8.51e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1385 | +| iterations | 19867 | +| time_elapsed | 29362 | +| total_timesteps | 40687616 | +| train/ | | +| approx_kl | 0.014630139 | +| clip_fraction | 0.308 | +| clip_range | 0.0648 | +| entropy_loss | -5.69 | +| explained_variance | 0.424 | +| learning_rate | 4.03e-05 | +| loss | -0.027 | +| n_updates | 95284 | +| policy_gradient_loss | -0.0145 | +| value_loss | 0.000247 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1385 | +| iterations | 19868 | +| time_elapsed | 29364 | +| total_timesteps | 40689664 | +| train/ | | +| approx_kl | 0.011746425 | +| clip_fraction | 0.323 | +| clip_range | 0.0648 | +| entropy_loss | -5.56 | +| explained_variance | 0.559 | +| learning_rate | 4.03e-05 | +| loss | -0.0264 | +| n_updates | 95288 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000118 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1385 | +| iterations | 19869 | +| time_elapsed | 29365 | +| total_timesteps | 40691712 | +| train/ | | +| approx_kl | 0.01284828 | +| clip_fraction | 0.33 | +| clip_range | 0.0648 | +| entropy_loss | -6.37 | +| explained_variance | -0.102 | +| learning_rate | 4.03e-05 | +| loss | -0.0285 | +| n_updates | 95292 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000135 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1385 | +| iterations | 19870 | +| time_elapsed | 29367 | +| total_timesteps | 40693760 | +| train/ | | +| approx_kl | 0.014064968 | +| clip_fraction | 0.35 | +| clip_range | 0.0648 | +| entropy_loss | -6.6 | +| explained_variance | -0.34 | +| learning_rate | 4.03e-05 | +| loss | -0.0324 | +| n_updates | 95296 | +| policy_gradient_loss | -0.0193 | +| value_loss | 4.52e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1385 | +| iterations | 19871 | +| time_elapsed | 29369 | +| total_timesteps | 40695808 | +| train/ | | +| approx_kl | 0.011291316 | +| clip_fraction | 0.339 | +| clip_range | 0.0648 | +| entropy_loss | -5.36 | +| explained_variance | 0.763 | +| learning_rate | 4.03e-05 | +| loss | -0.0229 | +| n_updates | 95300 | +| policy_gradient_loss | -0.0146 | +| value_loss | 0.000113 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1385 | +| iterations | 19872 | +| time_elapsed | 29370 | +| total_timesteps | 40697856 | +| train/ | | +| approx_kl | 0.015566385 | +| clip_fraction | 0.347 | +| clip_range | 0.0648 | +| entropy_loss | -4.85 | +| explained_variance | 0.173 | +| learning_rate | 4.03e-05 | +| loss | -0.0266 | +| n_updates | 95304 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000242 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1385 | +| iterations | 19873 | +| time_elapsed | 29372 | +| total_timesteps | 40699904 | +| train/ | | +| approx_kl | 0.01192813 | +| clip_fraction | 0.341 | +| clip_range | 0.0648 | +| entropy_loss | -5.3 | +| explained_variance | 0.62 | +| learning_rate | 4.03e-05 | +| loss | -0.0233 | +| n_updates | 95308 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000127 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1385 | +| iterations | 19874 | +| time_elapsed | 29373 | +| total_timesteps | 40701952 | +| train/ | | +| approx_kl | 0.015573676 | +| clip_fraction | 0.34 | +| clip_range | 0.0648 | +| entropy_loss | -5.84 | +| explained_variance | 0.311 | +| learning_rate | 4.03e-05 | +| loss | -0.0285 | +| n_updates | 95312 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000114 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1385 | +| iterations | 19875 | +| time_elapsed | 29375 | +| total_timesteps | 40704000 | +| train/ | | +| approx_kl | 0.014831463 | +| clip_fraction | 0.348 | +| clip_range | 0.0648 | +| entropy_loss | -5.61 | +| explained_variance | 0.586 | +| learning_rate | 4.03e-05 | +| loss | -0.0268 | +| n_updates | 95316 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.00011 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1385 | +| iterations | 19876 | +| time_elapsed | 29376 | +| total_timesteps | 40706048 | +| train/ | | +| approx_kl | 0.013850617 | +| clip_fraction | 0.365 | +| clip_range | 0.0648 | +| entropy_loss | -5.79 | +| explained_variance | -0.0811 | +| learning_rate | 4.03e-05 | +| loss | -0.0238 | +| n_updates | 95320 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000148 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1385 | +| iterations | 19877 | +| time_elapsed | 29378 | +| total_timesteps | 40708096 | +| train/ | | +| approx_kl | 0.013058919 | +| clip_fraction | 0.344 | +| clip_range | 0.0648 | +| entropy_loss | -6.12 | +| explained_variance | 0.267 | +| learning_rate | 4.03e-05 | +| loss | -0.0291 | +| n_updates | 95324 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000174 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.315 | +| time/ | | +| fps | 1385 | +| iterations | 19878 | +| time_elapsed | 29379 | +| total_timesteps | 40710144 | +| train/ | | +| approx_kl | 0.012432186 | +| clip_fraction | 0.312 | +| clip_range | 0.0648 | +| entropy_loss | -5.94 | +| explained_variance | 0.296 | +| learning_rate | 4.03e-05 | +| loss | -0.0254 | +| n_updates | 95328 | +| policy_gradient_loss | -0.0138 | +| value_loss | 0.000225 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1385 | +| iterations | 19879 | +| time_elapsed | 29381 | +| total_timesteps | 40712192 | +| train/ | | +| approx_kl | 0.011310101 | +| clip_fraction | 0.318 | +| clip_range | 0.0648 | +| entropy_loss | -5.79 | +| explained_variance | 0.403 | +| learning_rate | 4.03e-05 | +| loss | -0.0193 | +| n_updates | 95332 | +| policy_gradient_loss | -0.0148 | +| value_loss | 0.000231 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1385 | +| iterations | 19880 | +| time_elapsed | 29382 | +| total_timesteps | 40714240 | +| train/ | | +| approx_kl | 0.009348091 | +| clip_fraction | 0.315 | +| clip_range | 0.0648 | +| entropy_loss | -5.36 | +| explained_variance | 0.449 | +| learning_rate | 4.03e-05 | +| loss | -0.0216 | +| n_updates | 95336 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000225 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1385 | +| iterations | 19881 | +| time_elapsed | 29384 | +| total_timesteps | 40716288 | +| train/ | | +| approx_kl | 0.012741929 | +| clip_fraction | 0.335 | +| clip_range | 0.0648 | +| entropy_loss | -5.36 | +| explained_variance | 0.458 | +| learning_rate | 4.03e-05 | +| loss | -0.0301 | +| n_updates | 95340 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000141 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1385 | +| iterations | 19882 | +| time_elapsed | 29385 | +| total_timesteps | 40718336 | +| train/ | | +| approx_kl | 0.013965163 | +| clip_fraction | 0.346 | +| clip_range | 0.0648 | +| entropy_loss | -5.43 | +| explained_variance | 0.477 | +| learning_rate | 4.03e-05 | +| loss | -0.0254 | +| n_updates | 95344 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000159 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1385 | +| iterations | 19883 | +| time_elapsed | 29387 | +| total_timesteps | 40720384 | +| train/ | | +| approx_kl | 0.01415251 | +| clip_fraction | 0.348 | +| clip_range | 0.0648 | +| entropy_loss | -5.65 | +| explained_variance | 0.458 | +| learning_rate | 4.03e-05 | +| loss | -0.0235 | +| n_updates | 95348 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000167 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1385 | +| iterations | 19884 | +| time_elapsed | 29388 | +| total_timesteps | 40722432 | +| train/ | | +| approx_kl | 0.015327029 | +| clip_fraction | 0.345 | +| clip_range | 0.0648 | +| entropy_loss | -5.57 | +| explained_variance | 0.561 | +| learning_rate | 4.03e-05 | +| loss | -0.0298 | +| n_updates | 95352 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.00011 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1385 | +| iterations | 19885 | +| time_elapsed | 29390 | +| total_timesteps | 40724480 | +| train/ | | +| approx_kl | 0.010280193 | +| clip_fraction | 0.291 | +| clip_range | 0.0648 | +| entropy_loss | -5.89 | +| explained_variance | 0.197 | +| learning_rate | 4.03e-05 | +| loss | -0.0188 | +| n_updates | 95356 | +| policy_gradient_loss | -0.014 | +| value_loss | 0.000293 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1385 | +| iterations | 19886 | +| time_elapsed | 29391 | +| total_timesteps | 40726528 | +| train/ | | +| approx_kl | 0.013285406 | +| clip_fraction | 0.362 | +| clip_range | 0.0648 | +| entropy_loss | -5.72 | +| explained_variance | 0.383 | +| learning_rate | 4.03e-05 | +| loss | -0.026 | +| n_updates | 95360 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000246 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1385 | +| iterations | 19887 | +| time_elapsed | 29393 | +| total_timesteps | 40728576 | +| train/ | | +| approx_kl | 0.011585888 | +| clip_fraction | 0.347 | +| clip_range | 0.0648 | +| entropy_loss | -6.15 | +| explained_variance | -0.0704 | +| learning_rate | 4.03e-05 | +| loss | -0.0356 | +| n_updates | 95364 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000139 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1385 | +| iterations | 19888 | +| time_elapsed | 29394 | +| total_timesteps | 40730624 | +| train/ | | +| approx_kl | 0.008337425 | +| clip_fraction | 0.299 | +| clip_range | 0.0648 | +| entropy_loss | -5.67 | +| explained_variance | 0.472 | +| learning_rate | 4.03e-05 | +| loss | -0.02 | +| n_updates | 95368 | +| policy_gradient_loss | -0.0126 | +| value_loss | 0.000394 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1385 | +| iterations | 19889 | +| time_elapsed | 29396 | +| total_timesteps | 40732672 | +| train/ | | +| approx_kl | 0.012624345 | +| clip_fraction | 0.346 | +| clip_range | 0.0648 | +| entropy_loss | -5.55 | +| explained_variance | 0.306 | +| learning_rate | 4.03e-05 | +| loss | -0.0285 | +| n_updates | 95372 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000179 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1385 | +| iterations | 19890 | +| time_elapsed | 29397 | +| total_timesteps | 40734720 | +| train/ | | +| approx_kl | 0.013859063 | +| clip_fraction | 0.335 | +| clip_range | 0.0648 | +| entropy_loss | -6.57 | +| explained_variance | 0.158 | +| learning_rate | 4.03e-05 | +| loss | -0.0248 | +| n_updates | 95376 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000196 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1385 | +| iterations | 19891 | +| time_elapsed | 29399 | +| total_timesteps | 40736768 | +| train/ | | +| approx_kl | 0.011349661 | +| clip_fraction | 0.323 | +| clip_range | 0.0648 | +| entropy_loss | -6.14 | +| explained_variance | 0.217 | +| learning_rate | 4.03e-05 | +| loss | -0.029 | +| n_updates | 95380 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000239 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1385 | +| iterations | 19892 | +| time_elapsed | 29400 | +| total_timesteps | 40738816 | +| train/ | | +| approx_kl | 0.015233355 | +| clip_fraction | 0.327 | +| clip_range | 0.0648 | +| entropy_loss | -6.05 | +| explained_variance | 0.669 | +| learning_rate | 4.03e-05 | +| loss | -0.0303 | +| n_updates | 95384 | +| policy_gradient_loss | -0.0181 | +| value_loss | 7.52e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1385 | +| iterations | 19893 | +| time_elapsed | 29402 | +| total_timesteps | 40740864 | +| train/ | | +| approx_kl | 0.01060381 | +| clip_fraction | 0.323 | +| clip_range | 0.0648 | +| entropy_loss | -5.58 | +| explained_variance | 0.385 | +| learning_rate | 4.03e-05 | +| loss | -0.0246 | +| n_updates | 95388 | +| policy_gradient_loss | -0.0143 | +| value_loss | 0.000222 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1385 | +| iterations | 19894 | +| time_elapsed | 29404 | +| total_timesteps | 40742912 | +| train/ | | +| approx_kl | 0.012191234 | +| clip_fraction | 0.344 | +| clip_range | 0.0648 | +| entropy_loss | -5.83 | +| explained_variance | 0.5 | +| learning_rate | 4.03e-05 | +| loss | -0.0272 | +| n_updates | 95392 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000114 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1385 | +| iterations | 19895 | +| time_elapsed | 29405 | +| total_timesteps | 40744960 | +| train/ | | +| approx_kl | 0.016465653 | +| clip_fraction | 0.334 | +| clip_range | 0.0648 | +| entropy_loss | -5.91 | +| explained_variance | 0.381 | +| learning_rate | 4.03e-05 | +| loss | -0.0283 | +| n_updates | 95396 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000234 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1385 | +| iterations | 19896 | +| time_elapsed | 29407 | +| total_timesteps | 40747008 | +| train/ | | +| approx_kl | 0.014617212 | +| clip_fraction | 0.354 | +| clip_range | 0.0648 | +| entropy_loss | -5.94 | +| explained_variance | -0.292 | +| learning_rate | 4.03e-05 | +| loss | -0.0342 | +| n_updates | 95400 | +| policy_gradient_loss | -0.0202 | +| value_loss | 8.72e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1385 | +| iterations | 19897 | +| time_elapsed | 29408 | +| total_timesteps | 40749056 | +| train/ | | +| approx_kl | 0.011114722 | +| clip_fraction | 0.336 | +| clip_range | 0.0648 | +| entropy_loss | -6.17 | +| explained_variance | 0.2 | +| learning_rate | 4.03e-05 | +| loss | -0.0263 | +| n_updates | 95404 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000264 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1385 | +| iterations | 19898 | +| time_elapsed | 29410 | +| total_timesteps | 40751104 | +| train/ | | +| approx_kl | 0.01383058 | +| clip_fraction | 0.318 | +| clip_range | 0.0648 | +| entropy_loss | -4.95 | +| explained_variance | 0.647 | +| learning_rate | 4.03e-05 | +| loss | -0.0245 | +| n_updates | 95408 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.000142 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1385 | +| iterations | 19899 | +| time_elapsed | 29411 | +| total_timesteps | 40753152 | +| train/ | | +| approx_kl | 0.015131344 | +| clip_fraction | 0.369 | +| clip_range | 0.0648 | +| entropy_loss | -5.52 | +| explained_variance | 0.177 | +| learning_rate | 4.03e-05 | +| loss | -0.0336 | +| n_updates | 95412 | +| policy_gradient_loss | -0.022 | +| value_loss | 0.000114 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1385 | +| iterations | 19900 | +| time_elapsed | 29413 | +| total_timesteps | 40755200 | +| train/ | | +| approx_kl | 0.018858073 | +| clip_fraction | 0.333 | +| clip_range | 0.0648 | +| entropy_loss | -5.85 | +| explained_variance | 0.144 | +| learning_rate | 4.03e-05 | +| loss | -0.0227 | +| n_updates | 95416 | +| policy_gradient_loss | -0.0146 | +| value_loss | 0.000388 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1385 | +| iterations | 19901 | +| time_elapsed | 29414 | +| total_timesteps | 40757248 | +| train/ | | +| approx_kl | 0.012704454 | +| clip_fraction | 0.344 | +| clip_range | 0.0648 | +| entropy_loss | -4.56 | +| explained_variance | 0.753 | +| learning_rate | 4.03e-05 | +| loss | -0.029 | +| n_updates | 95420 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000129 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1385 | +| iterations | 19902 | +| time_elapsed | 29416 | +| total_timesteps | 40759296 | +| train/ | | +| approx_kl | 0.014952177 | +| clip_fraction | 0.348 | +| clip_range | 0.0648 | +| entropy_loss | -5.29 | +| explained_variance | 0.448 | +| learning_rate | 4.03e-05 | +| loss | -0.0305 | +| n_updates | 95424 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000172 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1385 | +| iterations | 19903 | +| time_elapsed | 29417 | +| total_timesteps | 40761344 | +| train/ | | +| approx_kl | 0.014318714 | +| clip_fraction | 0.362 | +| clip_range | 0.0648 | +| entropy_loss | -6.05 | +| explained_variance | 0.0576 | +| learning_rate | 4.03e-05 | +| loss | -0.0306 | +| n_updates | 95428 | +| policy_gradient_loss | -0.019 | +| value_loss | 6.34e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1385 | +| iterations | 19904 | +| time_elapsed | 29419 | +| total_timesteps | 40763392 | +| train/ | | +| approx_kl | 0.01434718 | +| clip_fraction | 0.34 | +| clip_range | 0.0648 | +| entropy_loss | -6.22 | +| explained_variance | 0.415 | +| learning_rate | 4.03e-05 | +| loss | -0.0249 | +| n_updates | 95432 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000148 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1385 | +| iterations | 19905 | +| time_elapsed | 29421 | +| total_timesteps | 40765440 | +| train/ | | +| approx_kl | 0.0115594845 | +| clip_fraction | 0.339 | +| clip_range | 0.0648 | +| entropy_loss | -5.79 | +| explained_variance | 0.627 | +| learning_rate | 4.03e-05 | +| loss | -0.0228 | +| n_updates | 95436 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000122 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1385 | +| iterations | 19906 | +| time_elapsed | 29422 | +| total_timesteps | 40767488 | +| train/ | | +| approx_kl | 0.009363182 | +| clip_fraction | 0.317 | +| clip_range | 0.0648 | +| entropy_loss | -6.41 | +| explained_variance | -0.0301 | +| learning_rate | 4.03e-05 | +| loss | -0.0222 | +| n_updates | 95440 | +| policy_gradient_loss | -0.0147 | +| value_loss | 0.000254 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1385 | +| iterations | 19907 | +| time_elapsed | 29424 | +| total_timesteps | 40769536 | +| train/ | | +| approx_kl | 0.014506255 | +| clip_fraction | 0.318 | +| clip_range | 0.0648 | +| entropy_loss | -6.05 | +| explained_variance | 0.354 | +| learning_rate | 4.03e-05 | +| loss | -0.0274 | +| n_updates | 95444 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000119 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1385 | +| iterations | 19908 | +| time_elapsed | 29425 | +| total_timesteps | 40771584 | +| train/ | | +| approx_kl | 0.0130222 | +| clip_fraction | 0.318 | +| clip_range | 0.0648 | +| entropy_loss | -5.23 | +| explained_variance | 0.457 | +| learning_rate | 4.03e-05 | +| loss | -0.0256 | +| n_updates | 95448 | +| policy_gradient_loss | -0.0135 | +| value_loss | 0.000281 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1385 | +| iterations | 19909 | +| time_elapsed | 29427 | +| total_timesteps | 40773632 | +| train/ | | +| approx_kl | 0.016084744 | +| clip_fraction | 0.35 | +| clip_range | 0.0648 | +| entropy_loss | -5.3 | +| explained_variance | 0.521 | +| learning_rate | 4.03e-05 | +| loss | -0.024 | +| n_updates | 95452 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000138 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1385 | +| iterations | 19910 | +| time_elapsed | 29428 | +| total_timesteps | 40775680 | +| train/ | | +| approx_kl | 0.01048602 | +| clip_fraction | 0.332 | +| clip_range | 0.0648 | +| entropy_loss | -6.14 | +| explained_variance | 0.217 | +| learning_rate | 4.03e-05 | +| loss | -0.0302 | +| n_updates | 95456 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000213 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1385 | +| iterations | 19911 | +| time_elapsed | 29430 | +| total_timesteps | 40777728 | +| train/ | | +| approx_kl | 0.00929555 | +| clip_fraction | 0.297 | +| clip_range | 0.0648 | +| entropy_loss | -5.84 | +| explained_variance | 0.29 | +| learning_rate | 4.03e-05 | +| loss | -0.0239 | +| n_updates | 95460 | +| policy_gradient_loss | -0.0145 | +| value_loss | 0.000329 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1385 | +| iterations | 19912 | +| time_elapsed | 29431 | +| total_timesteps | 40779776 | +| train/ | | +| approx_kl | 0.013968684 | +| clip_fraction | 0.355 | +| clip_range | 0.0648 | +| entropy_loss | -5.61 | +| explained_variance | 0.486 | +| learning_rate | 4.03e-05 | +| loss | -0.0342 | +| n_updates | 95464 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000144 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1385 | +| iterations | 19913 | +| time_elapsed | 29433 | +| total_timesteps | 40781824 | +| train/ | | +| approx_kl | 0.010649616 | +| clip_fraction | 0.317 | +| clip_range | 0.0648 | +| entropy_loss | -5.74 | +| explained_variance | 0.373 | +| learning_rate | 4.03e-05 | +| loss | -0.0256 | +| n_updates | 95468 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000209 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1385 | +| iterations | 19914 | +| time_elapsed | 29434 | +| total_timesteps | 40783872 | +| train/ | | +| approx_kl | 0.009857405 | +| clip_fraction | 0.325 | +| clip_range | 0.0648 | +| entropy_loss | -5.15 | +| explained_variance | 0.425 | +| learning_rate | 4.03e-05 | +| loss | -0.026 | +| n_updates | 95472 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000317 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1385 | +| iterations | 19915 | +| time_elapsed | 29436 | +| total_timesteps | 40785920 | +| train/ | | +| approx_kl | 0.011383163 | +| clip_fraction | 0.285 | +| clip_range | 0.0648 | +| entropy_loss | -5.66 | +| explained_variance | 0.473 | +| learning_rate | 4.03e-05 | +| loss | -0.0279 | +| n_updates | 95476 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000219 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1385 | +| iterations | 19916 | +| time_elapsed | 29437 | +| total_timesteps | 40787968 | +| train/ | | +| approx_kl | 0.014131889 | +| clip_fraction | 0.363 | +| clip_range | 0.0648 | +| entropy_loss | -5.67 | +| explained_variance | -0.775 | +| learning_rate | 4.03e-05 | +| loss | -0.0355 | +| n_updates | 95480 | +| policy_gradient_loss | -0.022 | +| value_loss | 9.89e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1385 | +| iterations | 19917 | +| time_elapsed | 29439 | +| total_timesteps | 40790016 | +| train/ | | +| approx_kl | 0.014481133 | +| clip_fraction | 0.334 | +| clip_range | 0.0648 | +| entropy_loss | -5.65 | +| explained_variance | 0.352 | +| learning_rate | 4.03e-05 | +| loss | -0.0198 | +| n_updates | 95484 | +| policy_gradient_loss | -0.014 | +| value_loss | 0.000178 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1385 | +| iterations | 19918 | +| time_elapsed | 29441 | +| total_timesteps | 40792064 | +| train/ | | +| approx_kl | 0.012560647 | +| clip_fraction | 0.324 | +| clip_range | 0.0648 | +| entropy_loss | -5.25 | +| explained_variance | 0.508 | +| learning_rate | 4.03e-05 | +| loss | -0.0204 | +| n_updates | 95488 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000142 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1385 | +| iterations | 19919 | +| time_elapsed | 29442 | +| total_timesteps | 40794112 | +| train/ | | +| approx_kl | 0.009641662 | +| clip_fraction | 0.34 | +| clip_range | 0.0648 | +| entropy_loss | -6.41 | +| explained_variance | -0.0999 | +| learning_rate | 4.03e-05 | +| loss | -0.0317 | +| n_updates | 95492 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000123 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1385 | +| iterations | 19920 | +| time_elapsed | 29444 | +| total_timesteps | 40796160 | +| train/ | | +| approx_kl | 0.012996754 | +| clip_fraction | 0.335 | +| clip_range | 0.0648 | +| entropy_loss | -6.27 | +| explained_variance | 0.294 | +| learning_rate | 4.03e-05 | +| loss | -0.0299 | +| n_updates | 95496 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000128 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1385 | +| iterations | 19921 | +| time_elapsed | 29445 | +| total_timesteps | 40798208 | +| train/ | | +| approx_kl | 0.013901206 | +| clip_fraction | 0.338 | +| clip_range | 0.0648 | +| entropy_loss | -5.93 | +| explained_variance | 0.28 | +| learning_rate | 4.03e-05 | +| loss | -0.0263 | +| n_updates | 95500 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000198 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1385 | +| iterations | 19922 | +| time_elapsed | 29447 | +| total_timesteps | 40800256 | +| train/ | | +| approx_kl | 0.011742393 | +| clip_fraction | 0.346 | +| clip_range | 0.0648 | +| entropy_loss | -6.17 | +| explained_variance | 0.331 | +| learning_rate | 4.03e-05 | +| loss | -0.0298 | +| n_updates | 95504 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1385 | +| iterations | 19923 | +| time_elapsed | 29448 | +| total_timesteps | 40802304 | +| train/ | | +| approx_kl | 0.010211801 | +| clip_fraction | 0.319 | +| clip_range | 0.0648 | +| entropy_loss | -5.67 | +| explained_variance | 0.449 | +| learning_rate | 4.03e-05 | +| loss | -0.0281 | +| n_updates | 95508 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000233 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1385 | +| iterations | 19924 | +| time_elapsed | 29450 | +| total_timesteps | 40804352 | +| train/ | | +| approx_kl | 0.010239042 | +| clip_fraction | 0.318 | +| clip_range | 0.0648 | +| entropy_loss | -5.05 | +| explained_variance | 0.508 | +| learning_rate | 4.03e-05 | +| loss | -0.0209 | +| n_updates | 95512 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000223 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1385 | +| iterations | 19925 | +| time_elapsed | 29451 | +| total_timesteps | 40806400 | +| train/ | | +| approx_kl | 0.010807047 | +| clip_fraction | 0.343 | +| clip_range | 0.0648 | +| entropy_loss | -5.22 | +| explained_variance | 0.46 | +| learning_rate | 4.03e-05 | +| loss | -0.0262 | +| n_updates | 95516 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.000186 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1385 | +| iterations | 19926 | +| time_elapsed | 29453 | +| total_timesteps | 40808448 | +| train/ | | +| approx_kl | 0.013756002 | +| clip_fraction | 0.35 | +| clip_range | 0.0648 | +| entropy_loss | -5.05 | +| explained_variance | 0.538 | +| learning_rate | 4.03e-05 | +| loss | -0.0274 | +| n_updates | 95520 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1385 | +| iterations | 19927 | +| time_elapsed | 29454 | +| total_timesteps | 40810496 | +| train/ | | +| approx_kl | 0.013432926 | +| clip_fraction | 0.352 | +| clip_range | 0.0648 | +| entropy_loss | -5.73 | +| explained_variance | 0.557 | +| learning_rate | 4.03e-05 | +| loss | -0.0264 | +| n_updates | 95524 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000133 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1385 | +| iterations | 19928 | +| time_elapsed | 29456 | +| total_timesteps | 40812544 | +| train/ | | +| approx_kl | 0.015185883 | +| clip_fraction | 0.318 | +| clip_range | 0.0648 | +| entropy_loss | -5.63 | +| explained_variance | 0.106 | +| learning_rate | 4.03e-05 | +| loss | -0.0259 | +| n_updates | 95528 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000177 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1385 | +| iterations | 19929 | +| time_elapsed | 29457 | +| total_timesteps | 40814592 | +| train/ | | +| approx_kl | 0.011798046 | +| clip_fraction | 0.324 | +| clip_range | 0.0648 | +| entropy_loss | -5.57 | +| explained_variance | 0.436 | +| learning_rate | 4.03e-05 | +| loss | -0.0229 | +| n_updates | 95532 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000133 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1385 | +| iterations | 19930 | +| time_elapsed | 29459 | +| total_timesteps | 40816640 | +| train/ | | +| approx_kl | 0.017496288 | +| clip_fraction | 0.365 | +| clip_range | 0.0648 | +| entropy_loss | -5.47 | +| explained_variance | 0.708 | +| learning_rate | 4.03e-05 | +| loss | -0.0373 | +| n_updates | 95536 | +| policy_gradient_loss | -0.0211 | +| value_loss | 5.63e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1385 | +| iterations | 19931 | +| time_elapsed | 29460 | +| total_timesteps | 40818688 | +| train/ | | +| approx_kl | 0.012491164 | +| clip_fraction | 0.354 | +| clip_range | 0.0648 | +| entropy_loss | -5.96 | +| explained_variance | 0.412 | +| learning_rate | 4.03e-05 | +| loss | -0.0312 | +| n_updates | 95540 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000111 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1385 | +| iterations | 19932 | +| time_elapsed | 29462 | +| total_timesteps | 40820736 | +| train/ | | +| approx_kl | 0.013924584 | +| clip_fraction | 0.354 | +| clip_range | 0.0648 | +| entropy_loss | -5.82 | +| explained_variance | 0.424 | +| learning_rate | 4.03e-05 | +| loss | -0.0267 | +| n_updates | 95544 | +| policy_gradient_loss | -0.0185 | +| value_loss | 7.63e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1385 | +| iterations | 19933 | +| time_elapsed | 29463 | +| total_timesteps | 40822784 | +| train/ | | +| approx_kl | 0.012758927 | +| clip_fraction | 0.351 | +| clip_range | 0.0648 | +| entropy_loss | -5.22 | +| explained_variance | 0.738 | +| learning_rate | 4.03e-05 | +| loss | -0.0276 | +| n_updates | 95548 | +| policy_gradient_loss | -0.0168 | +| value_loss | 6.48e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1385 | +| iterations | 19934 | +| time_elapsed | 29465 | +| total_timesteps | 40824832 | +| train/ | | +| approx_kl | 0.013899537 | +| clip_fraction | 0.357 | +| clip_range | 0.0648 | +| entropy_loss | -5.77 | +| explained_variance | -0.113 | +| learning_rate | 4.03e-05 | +| loss | -0.0338 | +| n_updates | 95552 | +| policy_gradient_loss | -0.0175 | +| value_loss | 6.16e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1385 | +| iterations | 19935 | +| time_elapsed | 29466 | +| total_timesteps | 40826880 | +| train/ | | +| approx_kl | 0.01275067 | +| clip_fraction | 0.299 | +| clip_range | 0.0648 | +| entropy_loss | -5.37 | +| explained_variance | 0.675 | +| learning_rate | 4.03e-05 | +| loss | -0.0189 | +| n_updates | 95556 | +| policy_gradient_loss | -0.0125 | +| value_loss | 0.000133 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1385 | +| iterations | 19936 | +| time_elapsed | 29468 | +| total_timesteps | 40828928 | +| train/ | | +| approx_kl | 0.014776274 | +| clip_fraction | 0.333 | +| clip_range | 0.0648 | +| entropy_loss | -4.93 | +| explained_variance | 0.697 | +| learning_rate | 4.03e-05 | +| loss | -0.029 | +| n_updates | 95560 | +| policy_gradient_loss | -0.0171 | +| value_loss | 8.45e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1385 | +| iterations | 19937 | +| time_elapsed | 29469 | +| total_timesteps | 40830976 | +| train/ | | +| approx_kl | 0.013035016 | +| clip_fraction | 0.313 | +| clip_range | 0.0648 | +| entropy_loss | -5.36 | +| explained_variance | 0.439 | +| learning_rate | 4.03e-05 | +| loss | -0.0246 | +| n_updates | 95564 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.00016 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1385 | +| iterations | 19938 | +| time_elapsed | 29471 | +| total_timesteps | 40833024 | +| train/ | | +| approx_kl | 0.013130425 | +| clip_fraction | 0.326 | +| clip_range | 0.0648 | +| entropy_loss | -5.74 | +| explained_variance | 0.394 | +| learning_rate | 4.03e-05 | +| loss | -0.0242 | +| n_updates | 95568 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1385 | +| iterations | 19939 | +| time_elapsed | 29472 | +| total_timesteps | 40835072 | +| train/ | | +| approx_kl | 0.012828067 | +| clip_fraction | 0.315 | +| clip_range | 0.0648 | +| entropy_loss | -5.41 | +| explained_variance | 0.483 | +| learning_rate | 4.03e-05 | +| loss | -0.0224 | +| n_updates | 95572 | +| policy_gradient_loss | -0.0137 | +| value_loss | 0.000186 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1385 | +| iterations | 19940 | +| time_elapsed | 29474 | +| total_timesteps | 40837120 | +| train/ | | +| approx_kl | 0.014650334 | +| clip_fraction | 0.338 | +| clip_range | 0.0648 | +| entropy_loss | -5.89 | +| explained_variance | 0.247 | +| learning_rate | 4.03e-05 | +| loss | -0.0246 | +| n_updates | 95576 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000187 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1385 | +| iterations | 19941 | +| time_elapsed | 29476 | +| total_timesteps | 40839168 | +| train/ | | +| approx_kl | 0.013957696 | +| clip_fraction | 0.318 | +| clip_range | 0.0648 | +| entropy_loss | -5.55 | +| explained_variance | 0.356 | +| learning_rate | 4.03e-05 | +| loss | -0.0196 | +| n_updates | 95580 | +| policy_gradient_loss | -0.0146 | +| value_loss | 0.000264 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1385 | +| iterations | 19942 | +| time_elapsed | 29477 | +| total_timesteps | 40841216 | +| train/ | | +| approx_kl | 0.016342238 | +| clip_fraction | 0.373 | +| clip_range | 0.0648 | +| entropy_loss | -5.33 | +| explained_variance | 0.409 | +| learning_rate | 4.03e-05 | +| loss | -0.0285 | +| n_updates | 95584 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000107 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1385 | +| iterations | 19943 | +| time_elapsed | 29479 | +| total_timesteps | 40843264 | +| train/ | | +| approx_kl | 0.012455285 | +| clip_fraction | 0.369 | +| clip_range | 0.0648 | +| entropy_loss | -5.86 | +| explained_variance | 0.385 | +| learning_rate | 4.03e-05 | +| loss | -0.0285 | +| n_updates | 95588 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000106 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1385 | +| iterations | 19944 | +| time_elapsed | 29480 | +| total_timesteps | 40845312 | +| train/ | | +| approx_kl | 0.012123538 | +| clip_fraction | 0.34 | +| clip_range | 0.0648 | +| entropy_loss | -5.52 | +| explained_variance | 0.349 | +| learning_rate | 4.03e-05 | +| loss | -0.0255 | +| n_updates | 95592 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000212 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1385 | +| iterations | 19945 | +| time_elapsed | 29482 | +| total_timesteps | 40847360 | +| train/ | | +| approx_kl | 0.014498329 | +| clip_fraction | 0.375 | +| clip_range | 0.0648 | +| entropy_loss | -5.39 | +| explained_variance | 0.535 | +| learning_rate | 4.03e-05 | +| loss | -0.0313 | +| n_updates | 95596 | +| policy_gradient_loss | -0.0196 | +| value_loss | 5.47e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1385 | +| iterations | 19946 | +| time_elapsed | 29483 | +| total_timesteps | 40849408 | +| train/ | | +| approx_kl | 0.014131999 | +| clip_fraction | 0.35 | +| clip_range | 0.0648 | +| entropy_loss | -5.23 | +| explained_variance | 0.465 | +| learning_rate | 4.03e-05 | +| loss | -0.0162 | +| n_updates | 95600 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.00017 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1385 | +| iterations | 19947 | +| time_elapsed | 29485 | +| total_timesteps | 40851456 | +| train/ | | +| approx_kl | 0.011998797 | +| clip_fraction | 0.332 | +| clip_range | 0.0648 | +| entropy_loss | -5.24 | +| explained_variance | 0.381 | +| learning_rate | 4.03e-05 | +| loss | -0.0343 | +| n_updates | 95604 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000116 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1385 | +| iterations | 19948 | +| time_elapsed | 29486 | +| total_timesteps | 40853504 | +| train/ | | +| approx_kl | 0.011801587 | +| clip_fraction | 0.342 | +| clip_range | 0.0648 | +| entropy_loss | -5.87 | +| explained_variance | 0.0651 | +| learning_rate | 4.03e-05 | +| loss | -0.0239 | +| n_updates | 95608 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.00014 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1385 | +| iterations | 19949 | +| time_elapsed | 29488 | +| total_timesteps | 40855552 | +| train/ | | +| approx_kl | 0.013192123 | +| clip_fraction | 0.326 | +| clip_range | 0.0648 | +| entropy_loss | -5.38 | +| explained_variance | 0.437 | +| learning_rate | 4.03e-05 | +| loss | -0.0217 | +| n_updates | 95612 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000268 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1385 | +| iterations | 19950 | +| time_elapsed | 29489 | +| total_timesteps | 40857600 | +| train/ | | +| approx_kl | 0.013443195 | +| clip_fraction | 0.316 | +| clip_range | 0.0648 | +| entropy_loss | -5.09 | +| explained_variance | 0.408 | +| learning_rate | 4.03e-05 | +| loss | -0.0332 | +| n_updates | 95616 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000156 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1385 | +| iterations | 19951 | +| time_elapsed | 29491 | +| total_timesteps | 40859648 | +| train/ | | +| approx_kl | 0.013169298 | +| clip_fraction | 0.326 | +| clip_range | 0.0648 | +| entropy_loss | -5.64 | +| explained_variance | 0.353 | +| learning_rate | 4.03e-05 | +| loss | -0.0212 | +| n_updates | 95620 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.000143 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1385 | +| iterations | 19952 | +| time_elapsed | 29493 | +| total_timesteps | 40861696 | +| train/ | | +| approx_kl | 0.014432294 | +| clip_fraction | 0.349 | +| clip_range | 0.0648 | +| entropy_loss | -5.79 | +| explained_variance | 0.113 | +| learning_rate | 4.03e-05 | +| loss | -0.0333 | +| n_updates | 95624 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000164 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1385 | +| iterations | 19953 | +| time_elapsed | 29494 | +| total_timesteps | 40863744 | +| train/ | | +| approx_kl | 0.01195834 | +| clip_fraction | 0.352 | +| clip_range | 0.0648 | +| entropy_loss | -5.78 | +| explained_variance | 0.351 | +| learning_rate | 4.03e-05 | +| loss | -0.0249 | +| n_updates | 95628 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000202 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1385 | +| iterations | 19954 | +| time_elapsed | 29496 | +| total_timesteps | 40865792 | +| train/ | | +| approx_kl | 0.011784568 | +| clip_fraction | 0.321 | +| clip_range | 0.0648 | +| entropy_loss | -6.1 | +| explained_variance | 0.17 | +| learning_rate | 4.03e-05 | +| loss | -0.0242 | +| n_updates | 95632 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000216 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1385 | +| iterations | 19955 | +| time_elapsed | 29497 | +| total_timesteps | 40867840 | +| train/ | | +| approx_kl | 0.011696273 | +| clip_fraction | 0.314 | +| clip_range | 0.0648 | +| entropy_loss | -4.97 | +| explained_variance | 0.596 | +| learning_rate | 4.03e-05 | +| loss | -0.0245 | +| n_updates | 95636 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.0002 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1385 | +| iterations | 19956 | +| time_elapsed | 29499 | +| total_timesteps | 40869888 | +| train/ | | +| approx_kl | 0.012625704 | +| clip_fraction | 0.377 | +| clip_range | 0.0648 | +| entropy_loss | -5.67 | +| explained_variance | -0.199 | +| learning_rate | 4.03e-05 | +| loss | -0.0354 | +| n_updates | 95640 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000107 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1385 | +| iterations | 19957 | +| time_elapsed | 29500 | +| total_timesteps | 40871936 | +| train/ | | +| approx_kl | 0.012649478 | +| clip_fraction | 0.373 | +| clip_range | 0.0648 | +| entropy_loss | -5.94 | +| explained_variance | 0.14 | +| learning_rate | 4.03e-05 | +| loss | -0.0343 | +| n_updates | 95644 | +| policy_gradient_loss | -0.0206 | +| value_loss | 6.3e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1385 | +| iterations | 19958 | +| time_elapsed | 29502 | +| total_timesteps | 40873984 | +| train/ | | +| approx_kl | 0.0127897905 | +| clip_fraction | 0.324 | +| clip_range | 0.0648 | +| entropy_loss | -5.65 | +| explained_variance | 0.433 | +| learning_rate | 4.03e-05 | +| loss | -0.00894 | +| n_updates | 95648 | +| policy_gradient_loss | -0.0141 | +| value_loss | 0.000198 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1385 | +| iterations | 19959 | +| time_elapsed | 29503 | +| total_timesteps | 40876032 | +| train/ | | +| approx_kl | 0.014281144 | +| clip_fraction | 0.336 | +| clip_range | 0.0648 | +| entropy_loss | -5.17 | +| explained_variance | 0.473 | +| learning_rate | 4.03e-05 | +| loss | -0.0285 | +| n_updates | 95652 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000155 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1385 | +| iterations | 19960 | +| time_elapsed | 29505 | +| total_timesteps | 40878080 | +| train/ | | +| approx_kl | 0.013696777 | +| clip_fraction | 0.354 | +| clip_range | 0.0648 | +| entropy_loss | -5.51 | +| explained_variance | 0.377 | +| learning_rate | 4.03e-05 | +| loss | -0.03 | +| n_updates | 95656 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000119 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1385 | +| iterations | 19961 | +| time_elapsed | 29506 | +| total_timesteps | 40880128 | +| train/ | | +| approx_kl | 0.012444811 | +| clip_fraction | 0.298 | +| clip_range | 0.0648 | +| entropy_loss | -6.19 | +| explained_variance | 0.347 | +| learning_rate | 4.03e-05 | +| loss | -0.023 | +| n_updates | 95660 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000208 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1385 | +| iterations | 19962 | +| time_elapsed | 29508 | +| total_timesteps | 40882176 | +| train/ | | +| approx_kl | 0.009554399 | +| clip_fraction | 0.303 | +| clip_range | 0.0648 | +| entropy_loss | -5.84 | +| explained_variance | 0.57 | +| learning_rate | 4.03e-05 | +| loss | -0.024 | +| n_updates | 95664 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000193 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1385 | +| iterations | 19963 | +| time_elapsed | 29509 | +| total_timesteps | 40884224 | +| train/ | | +| approx_kl | 0.009878634 | +| clip_fraction | 0.312 | +| clip_range | 0.0648 | +| entropy_loss | -5.82 | +| explained_variance | 0.489 | +| learning_rate | 4.03e-05 | +| loss | -0.0237 | +| n_updates | 95668 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000154 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1385 | +| iterations | 19964 | +| time_elapsed | 29511 | +| total_timesteps | 40886272 | +| train/ | | +| approx_kl | 0.011220051 | +| clip_fraction | 0.343 | +| clip_range | 0.0648 | +| entropy_loss | -5.95 | +| explained_variance | 0.357 | +| learning_rate | 4.03e-05 | +| loss | -0.0302 | +| n_updates | 95672 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000125 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1385 | +| iterations | 19965 | +| time_elapsed | 29512 | +| total_timesteps | 40888320 | +| train/ | | +| approx_kl | 0.014851503 | +| clip_fraction | 0.333 | +| clip_range | 0.0648 | +| entropy_loss | -6.01 | +| explained_variance | -0.0235 | +| learning_rate | 4.03e-05 | +| loss | -0.0274 | +| n_updates | 95676 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000118 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1385 | +| iterations | 19966 | +| time_elapsed | 29514 | +| total_timesteps | 40890368 | +| train/ | | +| approx_kl | 0.011807816 | +| clip_fraction | 0.329 | +| clip_range | 0.0648 | +| entropy_loss | -5.79 | +| explained_variance | 0.249 | +| learning_rate | 4.03e-05 | +| loss | -0.0338 | +| n_updates | 95680 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000149 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1385 | +| iterations | 19967 | +| time_elapsed | 29515 | +| total_timesteps | 40892416 | +| train/ | | +| approx_kl | 0.013649255 | +| clip_fraction | 0.342 | +| clip_range | 0.0648 | +| entropy_loss | -5.26 | +| explained_variance | 0.716 | +| learning_rate | 4.03e-05 | +| loss | -0.0329 | +| n_updates | 95684 | +| policy_gradient_loss | -0.0176 | +| value_loss | 7.63e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1385 | +| iterations | 19968 | +| time_elapsed | 29517 | +| total_timesteps | 40894464 | +| train/ | | +| approx_kl | 0.011457147 | +| clip_fraction | 0.319 | +| clip_range | 0.0648 | +| entropy_loss | -5.58 | +| explained_variance | 0.36 | +| learning_rate | 4.03e-05 | +| loss | -0.0269 | +| n_updates | 95688 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000334 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1385 | +| iterations | 19969 | +| time_elapsed | 29518 | +| total_timesteps | 40896512 | +| train/ | | +| approx_kl | 0.012875572 | +| clip_fraction | 0.333 | +| clip_range | 0.0648 | +| entropy_loss | -5.45 | +| explained_variance | 0.554 | +| learning_rate | 4.03e-05 | +| loss | -0.0309 | +| n_updates | 95692 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000108 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1385 | +| iterations | 19970 | +| time_elapsed | 29520 | +| total_timesteps | 40898560 | +| train/ | | +| approx_kl | 0.01305736 | +| clip_fraction | 0.36 | +| clip_range | 0.0648 | +| entropy_loss | -5.69 | +| explained_variance | 0.2 | +| learning_rate | 4.03e-05 | +| loss | -0.0273 | +| n_updates | 95696 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000219 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1385 | +| iterations | 19971 | +| time_elapsed | 29521 | +| total_timesteps | 40900608 | +| train/ | | +| approx_kl | 0.013821045 | +| clip_fraction | 0.353 | +| clip_range | 0.0648 | +| entropy_loss | -5.58 | +| explained_variance | 0.654 | +| learning_rate | 4.03e-05 | +| loss | -0.0282 | +| n_updates | 95700 | +| policy_gradient_loss | -0.0188 | +| value_loss | 8.35e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1385 | +| iterations | 19972 | +| time_elapsed | 29523 | +| total_timesteps | 40902656 | +| train/ | | +| approx_kl | 0.012766337 | +| clip_fraction | 0.337 | +| clip_range | 0.0648 | +| entropy_loss | -5.67 | +| explained_variance | 0.444 | +| learning_rate | 4.03e-05 | +| loss | -0.0256 | +| n_updates | 95704 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000146 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1385 | +| iterations | 19973 | +| time_elapsed | 29524 | +| total_timesteps | 40904704 | +| train/ | | +| approx_kl | 0.009084739 | +| clip_fraction | 0.301 | +| clip_range | 0.0648 | +| entropy_loss | -5.78 | +| explained_variance | 0.279 | +| learning_rate | 4.03e-05 | +| loss | -0.0224 | +| n_updates | 95708 | +| policy_gradient_loss | -0.0111 | +| value_loss | 0.000352 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1385 | +| iterations | 19974 | +| time_elapsed | 29526 | +| total_timesteps | 40906752 | +| train/ | | +| approx_kl | 0.0094536375 | +| clip_fraction | 0.31 | +| clip_range | 0.0648 | +| entropy_loss | -5.33 | +| explained_variance | 0.615 | +| learning_rate | 4.03e-05 | +| loss | -0.0286 | +| n_updates | 95712 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000113 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1385 | +| iterations | 19975 | +| time_elapsed | 29528 | +| total_timesteps | 40908800 | +| train/ | | +| approx_kl | 0.011884648 | +| clip_fraction | 0.307 | +| clip_range | 0.0648 | +| entropy_loss | -6.04 | +| explained_variance | 0.29 | +| learning_rate | 4.03e-05 | +| loss | -0.0236 | +| n_updates | 95716 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000148 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1385 | +| iterations | 19976 | +| time_elapsed | 29529 | +| total_timesteps | 40910848 | +| train/ | | +| approx_kl | 0.010361956 | +| clip_fraction | 0.336 | +| clip_range | 0.0648 | +| entropy_loss | -6.1 | +| explained_variance | 0.384 | +| learning_rate | 4.03e-05 | +| loss | -0.025 | +| n_updates | 95720 | +| policy_gradient_loss | -0.0134 | +| value_loss | 0.00024 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1385 | +| iterations | 19977 | +| time_elapsed | 29531 | +| total_timesteps | 40912896 | +| train/ | | +| approx_kl | 0.011304037 | +| clip_fraction | 0.351 | +| clip_range | 0.0648 | +| entropy_loss | -5.86 | +| explained_variance | 0.447 | +| learning_rate | 4.03e-05 | +| loss | -0.0273 | +| n_updates | 95724 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000144 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1385 | +| iterations | 19978 | +| time_elapsed | 29532 | +| total_timesteps | 40914944 | +| train/ | | +| approx_kl | 0.01047565 | +| clip_fraction | 0.348 | +| clip_range | 0.0648 | +| entropy_loss | -5.4 | +| explained_variance | 0.514 | +| learning_rate | 4.03e-05 | +| loss | -0.0321 | +| n_updates | 95728 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000108 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1385 | +| iterations | 19979 | +| time_elapsed | 29534 | +| total_timesteps | 40916992 | +| train/ | | +| approx_kl | 0.0142528685 | +| clip_fraction | 0.329 | +| clip_range | 0.0648 | +| entropy_loss | -5.72 | +| explained_variance | 0.704 | +| learning_rate | 4.03e-05 | +| loss | -0.0308 | +| n_updates | 95732 | +| policy_gradient_loss | -0.0191 | +| value_loss | 6.23e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1385 | +| iterations | 19980 | +| time_elapsed | 29535 | +| total_timesteps | 40919040 | +| train/ | | +| approx_kl | 0.012471488 | +| clip_fraction | 0.321 | +| clip_range | 0.0648 | +| entropy_loss | -5.92 | +| explained_variance | -0.0518 | +| learning_rate | 4.03e-05 | +| loss | -0.0287 | +| n_updates | 95736 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000163 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1385 | +| iterations | 19981 | +| time_elapsed | 29537 | +| total_timesteps | 40921088 | +| train/ | | +| approx_kl | 0.012782324 | +| clip_fraction | 0.315 | +| clip_range | 0.0648 | +| entropy_loss | -5.26 | +| explained_variance | 0.632 | +| learning_rate | 4.03e-05 | +| loss | -0.0218 | +| n_updates | 95740 | +| policy_gradient_loss | -0.0146 | +| value_loss | 0.000133 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1385 | +| iterations | 19982 | +| time_elapsed | 29538 | +| total_timesteps | 40923136 | +| train/ | | +| approx_kl | 0.010299716 | +| clip_fraction | 0.314 | +| clip_range | 0.0648 | +| entropy_loss | -5.2 | +| explained_variance | 0.407 | +| learning_rate | 4.03e-05 | +| loss | -0.0234 | +| n_updates | 95744 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.00011 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1385 | +| iterations | 19983 | +| time_elapsed | 29540 | +| total_timesteps | 40925184 | +| train/ | | +| approx_kl | 0.0153176 | +| clip_fraction | 0.327 | +| clip_range | 0.0648 | +| entropy_loss | -5.25 | +| explained_variance | 0.59 | +| learning_rate | 4.03e-05 | +| loss | -0.0271 | +| n_updates | 95748 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000122 | +--------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1385 | +| iterations | 19984 | +| time_elapsed | 29541 | +| total_timesteps | 40927232 | +| train/ | | +| approx_kl | 0.0144093465 | +| clip_fraction | 0.32 | +| clip_range | 0.0648 | +| entropy_loss | -5.72 | +| explained_variance | 0.606 | +| learning_rate | 4.03e-05 | +| loss | -0.026 | +| n_updates | 95752 | +| policy_gradient_loss | -0.0172 | +| value_loss | 8e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1385 | +| iterations | 19985 | +| time_elapsed | 29543 | +| total_timesteps | 40929280 | +| train/ | | +| approx_kl | 0.014071466 | +| clip_fraction | 0.347 | +| clip_range | 0.0648 | +| entropy_loss | -6.24 | +| explained_variance | 0.0232 | +| learning_rate | 4.03e-05 | +| loss | -0.0301 | +| n_updates | 95756 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.00014 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1385 | +| iterations | 19986 | +| time_elapsed | 29545 | +| total_timesteps | 40931328 | +| train/ | | +| approx_kl | 0.016577933 | +| clip_fraction | 0.301 | +| clip_range | 0.0648 | +| entropy_loss | -6.06 | +| explained_variance | 0.578 | +| learning_rate | 4.03e-05 | +| loss | -0.021 | +| n_updates | 95760 | +| policy_gradient_loss | -0.0149 | +| value_loss | 9.6e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1385 | +| iterations | 19987 | +| time_elapsed | 29546 | +| total_timesteps | 40933376 | +| train/ | | +| approx_kl | 0.01325232 | +| clip_fraction | 0.341 | +| clip_range | 0.0648 | +| entropy_loss | -6.1 | +| explained_variance | -0.0378 | +| learning_rate | 4.03e-05 | +| loss | -0.0264 | +| n_updates | 95764 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000231 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1385 | +| iterations | 19988 | +| time_elapsed | 29548 | +| total_timesteps | 40935424 | +| train/ | | +| approx_kl | 0.012040583 | +| clip_fraction | 0.317 | +| clip_range | 0.0648 | +| entropy_loss | -5.38 | +| explained_variance | 0.357 | +| learning_rate | 4.03e-05 | +| loss | -0.0215 | +| n_updates | 95768 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000266 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1385 | +| iterations | 19989 | +| time_elapsed | 29549 | +| total_timesteps | 40937472 | +| train/ | | +| approx_kl | 0.013890717 | +| clip_fraction | 0.318 | +| clip_range | 0.0648 | +| entropy_loss | -5.07 | +| explained_variance | 0.541 | +| learning_rate | 4.03e-05 | +| loss | -0.0277 | +| n_updates | 95772 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000319 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1385 | +| iterations | 19990 | +| time_elapsed | 29551 | +| total_timesteps | 40939520 | +| train/ | | +| approx_kl | 0.01349717 | +| clip_fraction | 0.364 | +| clip_range | 0.0648 | +| entropy_loss | -5.42 | +| explained_variance | 0.285 | +| learning_rate | 4.03e-05 | +| loss | -0.0237 | +| n_updates | 95776 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000103 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1385 | +| iterations | 19991 | +| time_elapsed | 29552 | +| total_timesteps | 40941568 | +| train/ | | +| approx_kl | 0.012971761 | +| clip_fraction | 0.353 | +| clip_range | 0.0648 | +| entropy_loss | -5.37 | +| explained_variance | 0.275 | +| learning_rate | 4.03e-05 | +| loss | -0.0231 | +| n_updates | 95780 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000359 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1385 | +| iterations | 19992 | +| time_elapsed | 29554 | +| total_timesteps | 40943616 | +| train/ | | +| approx_kl | 0.014391048 | +| clip_fraction | 0.344 | +| clip_range | 0.0648 | +| entropy_loss | -5.26 | +| explained_variance | 0.677 | +| learning_rate | 4.03e-05 | +| loss | -0.0338 | +| n_updates | 95784 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000103 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1385 | +| iterations | 19993 | +| time_elapsed | 29555 | +| total_timesteps | 40945664 | +| train/ | | +| approx_kl | 0.011044774 | +| clip_fraction | 0.328 | +| clip_range | 0.0648 | +| entropy_loss | -5.78 | +| explained_variance | 0.267 | +| learning_rate | 4.03e-05 | +| loss | -0.0258 | +| n_updates | 95788 | +| policy_gradient_loss | -0.0134 | +| value_loss | 0.0004 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1385 | +| iterations | 19994 | +| time_elapsed | 29557 | +| total_timesteps | 40947712 | +| train/ | | +| approx_kl | 0.011960909 | +| clip_fraction | 0.338 | +| clip_range | 0.0648 | +| entropy_loss | -5.94 | +| explained_variance | 0.146 | +| learning_rate | 4.03e-05 | +| loss | -0.0269 | +| n_updates | 95792 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000203 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1385 | +| iterations | 19995 | +| time_elapsed | 29558 | +| total_timesteps | 40949760 | +| train/ | | +| approx_kl | 0.011442315 | +| clip_fraction | 0.328 | +| clip_range | 0.0648 | +| entropy_loss | -6.53 | +| explained_variance | -0.102 | +| learning_rate | 4.03e-05 | +| loss | -0.0231 | +| n_updates | 95796 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000317 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1385 | +| iterations | 19996 | +| time_elapsed | 29560 | +| total_timesteps | 40951808 | +| train/ | | +| approx_kl | 0.011224806 | +| clip_fraction | 0.333 | +| clip_range | 0.0648 | +| entropy_loss | -5.84 | +| explained_variance | 0.143 | +| learning_rate | 4.03e-05 | +| loss | -0.0249 | +| n_updates | 95800 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000337 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1385 | +| iterations | 19997 | +| time_elapsed | 29561 | +| total_timesteps | 40953856 | +| train/ | | +| approx_kl | 0.01219799 | +| clip_fraction | 0.328 | +| clip_range | 0.0648 | +| entropy_loss | -5.82 | +| explained_variance | 0.45 | +| learning_rate | 4.03e-05 | +| loss | -0.0287 | +| n_updates | 95804 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000263 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1385 | +| iterations | 19998 | +| time_elapsed | 29563 | +| total_timesteps | 40955904 | +| train/ | | +| approx_kl | 0.014421178 | +| clip_fraction | 0.353 | +| clip_range | 0.0648 | +| entropy_loss | -5.2 | +| explained_variance | 0.785 | +| learning_rate | 4.03e-05 | +| loss | -0.0349 | +| n_updates | 95808 | +| policy_gradient_loss | -0.021 | +| value_loss | 6.71e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1385 | +| iterations | 19999 | +| time_elapsed | 29564 | +| total_timesteps | 40957952 | +| train/ | | +| approx_kl | 0.014139977 | +| clip_fraction | 0.383 | +| clip_range | 0.0648 | +| entropy_loss | -5.63 | +| explained_variance | 0.0776 | +| learning_rate | 4.03e-05 | +| loss | -0.0338 | +| n_updates | 95812 | +| policy_gradient_loss | -0.0201 | +| value_loss | 8.44e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1385 | +| iterations | 20000 | +| time_elapsed | 29566 | +| total_timesteps | 40960000 | +| train/ | | +| approx_kl | 0.013995618 | +| clip_fraction | 0.329 | +| clip_range | 0.0648 | +| entropy_loss | -5.88 | +| explained_variance | 0.545 | +| learning_rate | 4.03e-05 | +| loss | -0.0163 | +| n_updates | 95816 | +| policy_gradient_loss | -0.0146 | +| value_loss | 0.00013 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1385 | +| iterations | 20001 | +| time_elapsed | 29568 | +| total_timesteps | 40962048 | +| train/ | | +| approx_kl | 0.012032799 | +| clip_fraction | 0.352 | +| clip_range | 0.0648 | +| entropy_loss | -6.18 | +| explained_variance | -0.0164 | +| learning_rate | 4.03e-05 | +| loss | -0.0268 | +| n_updates | 95820 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000245 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1385 | +| iterations | 20002 | +| time_elapsed | 29569 | +| total_timesteps | 40964096 | +| train/ | | +| approx_kl | 0.011531331 | +| clip_fraction | 0.333 | +| clip_range | 0.0648 | +| entropy_loss | -6.13 | +| explained_variance | 0.576 | +| learning_rate | 4.03e-05 | +| loss | -0.0307 | +| n_updates | 95824 | +| policy_gradient_loss | -0.0166 | +| value_loss | 9.78e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1385 | +| iterations | 20003 | +| time_elapsed | 29571 | +| total_timesteps | 40966144 | +| train/ | | +| approx_kl | 0.014284864 | +| clip_fraction | 0.337 | +| clip_range | 0.0648 | +| entropy_loss | -6.21 | +| explained_variance | 0.217 | +| learning_rate | 4.03e-05 | +| loss | -0.0302 | +| n_updates | 95828 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000117 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1385 | +| iterations | 20004 | +| time_elapsed | 29572 | +| total_timesteps | 40968192 | +| train/ | | +| approx_kl | 0.014340007 | +| clip_fraction | 0.343 | +| clip_range | 0.0648 | +| entropy_loss | -6.07 | +| explained_variance | 0.146 | +| learning_rate | 4.03e-05 | +| loss | -0.0247 | +| n_updates | 95832 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000206 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1385 | +| iterations | 20005 | +| time_elapsed | 29574 | +| total_timesteps | 40970240 | +| train/ | | +| approx_kl | 0.013235636 | +| clip_fraction | 0.325 | +| clip_range | 0.0648 | +| entropy_loss | -4.44 | +| explained_variance | 0.735 | +| learning_rate | 4.03e-05 | +| loss | -0.0219 | +| n_updates | 95836 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.000143 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1385 | +| iterations | 20006 | +| time_elapsed | 29575 | +| total_timesteps | 40972288 | +| train/ | | +| approx_kl | 0.0149408905 | +| clip_fraction | 0.344 | +| clip_range | 0.0648 | +| entropy_loss | -5.72 | +| explained_variance | 0.325 | +| learning_rate | 4.03e-05 | +| loss | -0.0284 | +| n_updates | 95840 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000108 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1385 | +| iterations | 20007 | +| time_elapsed | 29577 | +| total_timesteps | 40974336 | +| train/ | | +| approx_kl | 0.009738812 | +| clip_fraction | 0.327 | +| clip_range | 0.0648 | +| entropy_loss | -6.15 | +| explained_variance | 0.478 | +| learning_rate | 4.03e-05 | +| loss | -0.0216 | +| n_updates | 95844 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.000179 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1385 | +| iterations | 20008 | +| time_elapsed | 29578 | +| total_timesteps | 40976384 | +| train/ | | +| approx_kl | 0.009178627 | +| clip_fraction | 0.313 | +| clip_range | 0.0648 | +| entropy_loss | -5.95 | +| explained_variance | 0.278 | +| learning_rate | 4.03e-05 | +| loss | -0.0196 | +| n_updates | 95848 | +| policy_gradient_loss | -0.0132 | +| value_loss | 0.000331 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1385 | +| iterations | 20009 | +| time_elapsed | 29580 | +| total_timesteps | 40978432 | +| train/ | | +| approx_kl | 0.011553125 | +| clip_fraction | 0.34 | +| clip_range | 0.0648 | +| entropy_loss | -5.39 | +| explained_variance | 0.62 | +| learning_rate | 4.03e-05 | +| loss | -0.027 | +| n_updates | 95852 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000121 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1385 | +| iterations | 20010 | +| time_elapsed | 29581 | +| total_timesteps | 40980480 | +| train/ | | +| approx_kl | 0.010343529 | +| clip_fraction | 0.322 | +| clip_range | 0.0648 | +| entropy_loss | -5.58 | +| explained_variance | 0.161 | +| learning_rate | 4.03e-05 | +| loss | -0.0187 | +| n_updates | 95856 | +| policy_gradient_loss | -0.0138 | +| value_loss | 0.000353 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1385 | +| iterations | 20011 | +| time_elapsed | 29583 | +| total_timesteps | 40982528 | +| train/ | | +| approx_kl | 0.014529927 | +| clip_fraction | 0.386 | +| clip_range | 0.0648 | +| entropy_loss | -5.66 | +| explained_variance | 0.316 | +| learning_rate | 4.03e-05 | +| loss | -0.0268 | +| n_updates | 95860 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000149 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1385 | +| iterations | 20012 | +| time_elapsed | 29584 | +| total_timesteps | 40984576 | +| train/ | | +| approx_kl | 0.014658731 | +| clip_fraction | 0.358 | +| clip_range | 0.0648 | +| entropy_loss | -5.12 | +| explained_variance | 0.257 | +| learning_rate | 4.03e-05 | +| loss | -0.0271 | +| n_updates | 95864 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000357 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1385 | +| iterations | 20013 | +| time_elapsed | 29586 | +| total_timesteps | 40986624 | +| train/ | | +| approx_kl | 0.014050787 | +| clip_fraction | 0.354 | +| clip_range | 0.0648 | +| entropy_loss | -6.2 | +| explained_variance | -0.279 | +| learning_rate | 4.03e-05 | +| loss | -0.0336 | +| n_updates | 95868 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000146 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1385 | +| iterations | 20014 | +| time_elapsed | 29588 | +| total_timesteps | 40988672 | +| train/ | | +| approx_kl | 0.01356545 | +| clip_fraction | 0.361 | +| clip_range | 0.0648 | +| entropy_loss | -6.17 | +| explained_variance | 0.532 | +| learning_rate | 4.03e-05 | +| loss | -0.0289 | +| n_updates | 95872 | +| policy_gradient_loss | -0.0195 | +| value_loss | 6.93e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1385 | +| iterations | 20015 | +| time_elapsed | 29589 | +| total_timesteps | 40990720 | +| train/ | | +| approx_kl | 0.013485894 | +| clip_fraction | 0.362 | +| clip_range | 0.0648 | +| entropy_loss | -5.66 | +| explained_variance | 0.378 | +| learning_rate | 4.03e-05 | +| loss | -0.0348 | +| n_updates | 95876 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000115 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1385 | +| iterations | 20016 | +| time_elapsed | 29591 | +| total_timesteps | 40992768 | +| train/ | | +| approx_kl | 0.014516504 | +| clip_fraction | 0.376 | +| clip_range | 0.0648 | +| entropy_loss | -6.18 | +| explained_variance | -0.224 | +| learning_rate | 4.03e-05 | +| loss | -0.0297 | +| n_updates | 95880 | +| policy_gradient_loss | -0.0195 | +| value_loss | 5.72e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1385 | +| iterations | 20017 | +| time_elapsed | 29592 | +| total_timesteps | 40994816 | +| train/ | | +| approx_kl | 0.013611037 | +| clip_fraction | 0.314 | +| clip_range | 0.0648 | +| entropy_loss | -6.34 | +| explained_variance | 0.229 | +| learning_rate | 4.03e-05 | +| loss | -0.024 | +| n_updates | 95884 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000245 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1385 | +| iterations | 20018 | +| time_elapsed | 29594 | +| total_timesteps | 40996864 | +| train/ | | +| approx_kl | 0.01152744 | +| clip_fraction | 0.295 | +| clip_range | 0.0648 | +| entropy_loss | -5.6 | +| explained_variance | 0.497 | +| learning_rate | 4.03e-05 | +| loss | -0.02 | +| n_updates | 95888 | +| policy_gradient_loss | -0.0141 | +| value_loss | 0.00025 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1385 | +| iterations | 20019 | +| time_elapsed | 29595 | +| total_timesteps | 40998912 | +| train/ | | +| approx_kl | 0.010662302 | +| clip_fraction | 0.312 | +| clip_range | 0.0648 | +| entropy_loss | -5.17 | +| explained_variance | 0.487 | +| learning_rate | 4.03e-05 | +| loss | -0.0232 | +| n_updates | 95892 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.000157 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1385 | +| iterations | 20020 | +| time_elapsed | 29597 | +| total_timesteps | 41000960 | +| train/ | | +| approx_kl | 0.014543344 | +| clip_fraction | 0.341 | +| clip_range | 0.0648 | +| entropy_loss | -5.72 | +| explained_variance | 0.381 | +| learning_rate | 4.03e-05 | +| loss | -0.0263 | +| n_updates | 95896 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000155 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1385 | +| iterations | 20021 | +| time_elapsed | 29599 | +| total_timesteps | 41003008 | +| train/ | | +| approx_kl | 0.015129051 | +| clip_fraction | 0.359 | +| clip_range | 0.0647 | +| entropy_loss | -5.85 | +| explained_variance | 0.49 | +| learning_rate | 4.03e-05 | +| loss | -0.0347 | +| n_updates | 95900 | +| policy_gradient_loss | -0.0203 | +| value_loss | 8.39e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1385 | +| iterations | 20022 | +| time_elapsed | 29600 | +| total_timesteps | 41005056 | +| train/ | | +| approx_kl | 0.014310961 | +| clip_fraction | 0.302 | +| clip_range | 0.0647 | +| entropy_loss | -5.53 | +| explained_variance | 0.679 | +| learning_rate | 4.03e-05 | +| loss | -0.028 | +| n_updates | 95904 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000139 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1385 | +| iterations | 20023 | +| time_elapsed | 29602 | +| total_timesteps | 41007104 | +| train/ | | +| approx_kl | 0.017360378 | +| clip_fraction | 0.331 | +| clip_range | 0.0647 | +| entropy_loss | -5.11 | +| explained_variance | 0.687 | +| learning_rate | 4.03e-05 | +| loss | -0.0308 | +| n_updates | 95908 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000112 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1385 | +| iterations | 20024 | +| time_elapsed | 29603 | +| total_timesteps | 41009152 | +| train/ | | +| approx_kl | 0.01467174 | +| clip_fraction | 0.357 | +| clip_range | 0.0647 | +| entropy_loss | -5.82 | +| explained_variance | 0.271 | +| learning_rate | 4.03e-05 | +| loss | -0.0303 | +| n_updates | 95912 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000193 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1385 | +| iterations | 20025 | +| time_elapsed | 29605 | +| total_timesteps | 41011200 | +| train/ | | +| approx_kl | 0.010992877 | +| clip_fraction | 0.334 | +| clip_range | 0.0647 | +| entropy_loss | -5.93 | +| explained_variance | 0.583 | +| learning_rate | 4.03e-05 | +| loss | -0.0338 | +| n_updates | 95916 | +| policy_gradient_loss | -0.0162 | +| value_loss | 8.6e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1385 | +| iterations | 20026 | +| time_elapsed | 29606 | +| total_timesteps | 41013248 | +| train/ | | +| approx_kl | 0.013619482 | +| clip_fraction | 0.37 | +| clip_range | 0.0647 | +| entropy_loss | -6.06 | +| explained_variance | -0.195 | +| learning_rate | 4.03e-05 | +| loss | -0.0334 | +| n_updates | 95920 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000149 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1385 | +| iterations | 20027 | +| time_elapsed | 29608 | +| total_timesteps | 41015296 | +| train/ | | +| approx_kl | 0.012103248 | +| clip_fraction | 0.344 | +| clip_range | 0.0647 | +| entropy_loss | -5.56 | +| explained_variance | 0.451 | +| learning_rate | 4.03e-05 | +| loss | -0.0302 | +| n_updates | 95924 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000161 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1385 | +| iterations | 20028 | +| time_elapsed | 29609 | +| total_timesteps | 41017344 | +| train/ | | +| approx_kl | 0.009377136 | +| clip_fraction | 0.307 | +| clip_range | 0.0647 | +| entropy_loss | -5.49 | +| explained_variance | 0.271 | +| learning_rate | 4.03e-05 | +| loss | -0.0279 | +| n_updates | 95928 | +| policy_gradient_loss | -0.0133 | +| value_loss | 0.000331 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1385 | +| iterations | 20029 | +| time_elapsed | 29611 | +| total_timesteps | 41019392 | +| train/ | | +| approx_kl | 0.0141951665 | +| clip_fraction | 0.362 | +| clip_range | 0.0647 | +| entropy_loss | -5.66 | +| explained_variance | 0.625 | +| learning_rate | 4.03e-05 | +| loss | -0.0273 | +| n_updates | 95932 | +| policy_gradient_loss | -0.0204 | +| value_loss | 9.13e-05 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1385 | +| iterations | 20030 | +| time_elapsed | 29612 | +| total_timesteps | 41021440 | +| train/ | | +| approx_kl | 0.01477191 | +| clip_fraction | 0.342 | +| clip_range | 0.0647 | +| entropy_loss | -6.21 | +| explained_variance | 0.442 | +| learning_rate | 4.03e-05 | +| loss | -0.0294 | +| n_updates | 95936 | +| policy_gradient_loss | -0.0192 | +| value_loss | 7.06e-05 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1385 | +| iterations | 20031 | +| time_elapsed | 29614 | +| total_timesteps | 41023488 | +| train/ | | +| approx_kl | 0.01303033 | +| clip_fraction | 0.354 | +| clip_range | 0.0647 | +| entropy_loss | -5.64 | +| explained_variance | 0.671 | +| learning_rate | 4.03e-05 | +| loss | -0.0247 | +| n_updates | 95940 | +| policy_gradient_loss | -0.0192 | +| value_loss | 4.19e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1385 | +| iterations | 20032 | +| time_elapsed | 29616 | +| total_timesteps | 41025536 | +| train/ | | +| approx_kl | 0.012098745 | +| clip_fraction | 0.318 | +| clip_range | 0.0647 | +| entropy_loss | -5.23 | +| explained_variance | 0.681 | +| learning_rate | 4.03e-05 | +| loss | -0.0248 | +| n_updates | 95944 | +| policy_gradient_loss | -0.0147 | +| value_loss | 0.000103 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1385 | +| iterations | 20033 | +| time_elapsed | 29617 | +| total_timesteps | 41027584 | +| train/ | | +| approx_kl | 0.013602879 | +| clip_fraction | 0.346 | +| clip_range | 0.0647 | +| entropy_loss | -5.13 | +| explained_variance | 0.479 | +| learning_rate | 4.03e-05 | +| loss | -0.0251 | +| n_updates | 95948 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000324 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1385 | +| iterations | 20034 | +| time_elapsed | 29619 | +| total_timesteps | 41029632 | +| train/ | | +| approx_kl | 0.017912056 | +| clip_fraction | 0.313 | +| clip_range | 0.0647 | +| entropy_loss | -5.52 | +| explained_variance | -0.311 | +| learning_rate | 4.03e-05 | +| loss | -0.0244 | +| n_updates | 95952 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000162 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1385 | +| iterations | 20035 | +| time_elapsed | 29620 | +| total_timesteps | 41031680 | +| train/ | | +| approx_kl | 0.015983876 | +| clip_fraction | 0.365 | +| clip_range | 0.0647 | +| entropy_loss | -6.03 | +| explained_variance | 0.277 | +| learning_rate | 4.03e-05 | +| loss | -0.0294 | +| n_updates | 95956 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000116 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1385 | +| iterations | 20036 | +| time_elapsed | 29622 | +| total_timesteps | 41033728 | +| train/ | | +| approx_kl | 0.013095272 | +| clip_fraction | 0.353 | +| clip_range | 0.0647 | +| entropy_loss | -5.49 | +| explained_variance | 0.384 | +| learning_rate | 4.03e-05 | +| loss | -0.0257 | +| n_updates | 95960 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000126 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1385 | +| iterations | 20037 | +| time_elapsed | 29623 | +| total_timesteps | 41035776 | +| train/ | | +| approx_kl | 0.009458581 | +| clip_fraction | 0.306 | +| clip_range | 0.0647 | +| entropy_loss | -6.47 | +| explained_variance | 0.276 | +| learning_rate | 4.03e-05 | +| loss | -0.0218 | +| n_updates | 95964 | +| policy_gradient_loss | -0.0148 | +| value_loss | 0.00021 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1385 | +| iterations | 20038 | +| time_elapsed | 29625 | +| total_timesteps | 41037824 | +| train/ | | +| approx_kl | 0.0121201165 | +| clip_fraction | 0.31 | +| clip_range | 0.0647 | +| entropy_loss | -5.67 | +| explained_variance | 0.615 | +| learning_rate | 4.03e-05 | +| loss | -0.0219 | +| n_updates | 95968 | +| policy_gradient_loss | -0.0142 | +| value_loss | 0.000137 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1385 | +| iterations | 20039 | +| time_elapsed | 29626 | +| total_timesteps | 41039872 | +| train/ | | +| approx_kl | 0.013008331 | +| clip_fraction | 0.328 | +| clip_range | 0.0647 | +| entropy_loss | -5.29 | +| explained_variance | 0.677 | +| learning_rate | 4.03e-05 | +| loss | -0.0328 | +| n_updates | 95972 | +| policy_gradient_loss | -0.0182 | +| value_loss | 7.37e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1385 | +| iterations | 20040 | +| time_elapsed | 29628 | +| total_timesteps | 41041920 | +| train/ | | +| approx_kl | 0.014705356 | +| clip_fraction | 0.34 | +| clip_range | 0.0647 | +| entropy_loss | -5.41 | +| explained_variance | 0.307 | +| learning_rate | 4.03e-05 | +| loss | -0.0242 | +| n_updates | 95976 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000149 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1385 | +| iterations | 20041 | +| time_elapsed | 29629 | +| total_timesteps | 41043968 | +| train/ | | +| approx_kl | 0.012932375 | +| clip_fraction | 0.317 | +| clip_range | 0.0647 | +| entropy_loss | -5.88 | +| explained_variance | 0.334 | +| learning_rate | 4.03e-05 | +| loss | -0.0235 | +| n_updates | 95980 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000267 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1385 | +| iterations | 20042 | +| time_elapsed | 29631 | +| total_timesteps | 41046016 | +| train/ | | +| approx_kl | 0.011194006 | +| clip_fraction | 0.297 | +| clip_range | 0.0647 | +| entropy_loss | -6.26 | +| explained_variance | 0.292 | +| learning_rate | 4.03e-05 | +| loss | -0.0282 | +| n_updates | 95984 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000182 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1385 | +| iterations | 20043 | +| time_elapsed | 29632 | +| total_timesteps | 41048064 | +| train/ | | +| approx_kl | 0.011510953 | +| clip_fraction | 0.321 | +| clip_range | 0.0647 | +| entropy_loss | -6.25 | +| explained_variance | 0.32 | +| learning_rate | 4.03e-05 | +| loss | -0.0252 | +| n_updates | 95988 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000153 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1385 | +| iterations | 20044 | +| time_elapsed | 29634 | +| total_timesteps | 41050112 | +| train/ | | +| approx_kl | 0.011148404 | +| clip_fraction | 0.324 | +| clip_range | 0.0647 | +| entropy_loss | -6.17 | +| explained_variance | 0.406 | +| learning_rate | 4.03e-05 | +| loss | -0.0286 | +| n_updates | 95992 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000223 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1385 | +| iterations | 20045 | +| time_elapsed | 29635 | +| total_timesteps | 41052160 | +| train/ | | +| approx_kl | 0.012864355 | +| clip_fraction | 0.364 | +| clip_range | 0.0647 | +| entropy_loss | -5.71 | +| explained_variance | 0.54 | +| learning_rate | 4.03e-05 | +| loss | -0.0333 | +| n_updates | 95996 | +| policy_gradient_loss | -0.0219 | +| value_loss | 5.1e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1385 | +| iterations | 20046 | +| time_elapsed | 29637 | +| total_timesteps | 41054208 | +| train/ | | +| approx_kl | 0.011402311 | +| clip_fraction | 0.333 | +| clip_range | 0.0647 | +| entropy_loss | -5.46 | +| explained_variance | 0.451 | +| learning_rate | 4.03e-05 | +| loss | -0.0291 | +| n_updates | 96000 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000183 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1385 | +| iterations | 20047 | +| time_elapsed | 29638 | +| total_timesteps | 41056256 | +| train/ | | +| approx_kl | 0.010626508 | +| clip_fraction | 0.311 | +| clip_range | 0.0647 | +| entropy_loss | -5.43 | +| explained_variance | 0.301 | +| learning_rate | 4.02e-05 | +| loss | -0.0261 | +| n_updates | 96004 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000218 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1385 | +| iterations | 20048 | +| time_elapsed | 29640 | +| total_timesteps | 41058304 | +| train/ | | +| approx_kl | 0.0110928975 | +| clip_fraction | 0.284 | +| clip_range | 0.0647 | +| entropy_loss | -5.67 | +| explained_variance | 0.517 | +| learning_rate | 4.02e-05 | +| loss | -0.0219 | +| n_updates | 96008 | +| policy_gradient_loss | -0.0148 | +| value_loss | 0.000194 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1385 | +| iterations | 20049 | +| time_elapsed | 29642 | +| total_timesteps | 41060352 | +| train/ | | +| approx_kl | 0.0127481315 | +| clip_fraction | 0.3 | +| clip_range | 0.0647 | +| entropy_loss | -6.34 | +| explained_variance | 0.256 | +| learning_rate | 4.02e-05 | +| loss | -0.0245 | +| n_updates | 96012 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000181 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1385 | +| iterations | 20050 | +| time_elapsed | 29643 | +| total_timesteps | 41062400 | +| train/ | | +| approx_kl | 0.014698302 | +| clip_fraction | 0.333 | +| clip_range | 0.0647 | +| entropy_loss | -6.52 | +| explained_variance | -0.101 | +| learning_rate | 4.02e-05 | +| loss | -0.0255 | +| n_updates | 96016 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000124 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1385 | +| iterations | 20051 | +| time_elapsed | 29645 | +| total_timesteps | 41064448 | +| train/ | | +| approx_kl | 0.011608234 | +| clip_fraction | 0.328 | +| clip_range | 0.0647 | +| entropy_loss | -6.56 | +| explained_variance | 0.248 | +| learning_rate | 4.02e-05 | +| loss | -0.0281 | +| n_updates | 96020 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000235 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1385 | +| iterations | 20052 | +| time_elapsed | 29646 | +| total_timesteps | 41066496 | +| train/ | | +| approx_kl | 0.011620153 | +| clip_fraction | 0.314 | +| clip_range | 0.0647 | +| entropy_loss | -6.47 | +| explained_variance | 0.277 | +| learning_rate | 4.02e-05 | +| loss | -0.0212 | +| n_updates | 96024 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000216 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1385 | +| iterations | 20053 | +| time_elapsed | 29648 | +| total_timesteps | 41068544 | +| train/ | | +| approx_kl | 0.009468215 | +| clip_fraction | 0.281 | +| clip_range | 0.0647 | +| entropy_loss | -5.26 | +| explained_variance | 0.424 | +| learning_rate | 4.02e-05 | +| loss | -0.0227 | +| n_updates | 96028 | +| policy_gradient_loss | -0.014 | +| value_loss | 0.000483 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1385 | +| iterations | 20054 | +| time_elapsed | 29649 | +| total_timesteps | 41070592 | +| train/ | | +| approx_kl | 0.015213028 | +| clip_fraction | 0.337 | +| clip_range | 0.0647 | +| entropy_loss | -5.11 | +| explained_variance | 0.297 | +| learning_rate | 4.02e-05 | +| loss | -0.0316 | +| n_updates | 96032 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000125 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1385 | +| iterations | 20055 | +| time_elapsed | 29651 | +| total_timesteps | 41072640 | +| train/ | | +| approx_kl | 0.014593594 | +| clip_fraction | 0.321 | +| clip_range | 0.0647 | +| entropy_loss | -5.16 | +| explained_variance | 0.549 | +| learning_rate | 4.02e-05 | +| loss | -0.0246 | +| n_updates | 96036 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000125 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1385 | +| iterations | 20056 | +| time_elapsed | 29652 | +| total_timesteps | 41074688 | +| train/ | | +| approx_kl | 0.013541617 | +| clip_fraction | 0.344 | +| clip_range | 0.0647 | +| entropy_loss | -5.52 | +| explained_variance | 0.385 | +| learning_rate | 4.02e-05 | +| loss | -0.0242 | +| n_updates | 96040 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000219 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1385 | +| iterations | 20057 | +| time_elapsed | 29654 | +| total_timesteps | 41076736 | +| train/ | | +| approx_kl | 0.016429305 | +| clip_fraction | 0.335 | +| clip_range | 0.0647 | +| entropy_loss | -5.75 | +| explained_variance | 0.102 | +| learning_rate | 4.02e-05 | +| loss | -0.0217 | +| n_updates | 96044 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000183 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1385 | +| iterations | 20058 | +| time_elapsed | 29655 | +| total_timesteps | 41078784 | +| train/ | | +| approx_kl | 0.014838451 | +| clip_fraction | 0.356 | +| clip_range | 0.0647 | +| entropy_loss | -5.69 | +| explained_variance | 0.621 | +| learning_rate | 4.02e-05 | +| loss | -0.0342 | +| n_updates | 96048 | +| policy_gradient_loss | -0.019 | +| value_loss | 8.05e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1385 | +| iterations | 20059 | +| time_elapsed | 29657 | +| total_timesteps | 41080832 | +| train/ | | +| approx_kl | 0.012840216 | +| clip_fraction | 0.334 | +| clip_range | 0.0647 | +| entropy_loss | -5.85 | +| explained_variance | 0.308 | +| learning_rate | 4.02e-05 | +| loss | -0.0269 | +| n_updates | 96052 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000173 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1385 | +| iterations | 20060 | +| time_elapsed | 29658 | +| total_timesteps | 41082880 | +| train/ | | +| approx_kl | 0.011145464 | +| clip_fraction | 0.323 | +| clip_range | 0.0647 | +| entropy_loss | -6.02 | +| explained_variance | 0.00389 | +| learning_rate | 4.02e-05 | +| loss | -0.0279 | +| n_updates | 96056 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000141 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1385 | +| iterations | 20061 | +| time_elapsed | 29660 | +| total_timesteps | 41084928 | +| train/ | | +| approx_kl | 0.01294636 | +| clip_fraction | 0.346 | +| clip_range | 0.0647 | +| entropy_loss | -6.29 | +| explained_variance | -0.0653 | +| learning_rate | 4.02e-05 | +| loss | -0.0247 | +| n_updates | 96060 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000127 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1385 | +| iterations | 20062 | +| time_elapsed | 29661 | +| total_timesteps | 41086976 | +| train/ | | +| approx_kl | 0.011324596 | +| clip_fraction | 0.327 | +| clip_range | 0.0647 | +| entropy_loss | -6 | +| explained_variance | 0.582 | +| learning_rate | 4.02e-05 | +| loss | -0.0248 | +| n_updates | 96064 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000162 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1385 | +| iterations | 20063 | +| time_elapsed | 29663 | +| total_timesteps | 41089024 | +| train/ | | +| approx_kl | 0.013013719 | +| clip_fraction | 0.325 | +| clip_range | 0.0647 | +| entropy_loss | -4.83 | +| explained_variance | 0.732 | +| learning_rate | 4.02e-05 | +| loss | -0.0222 | +| n_updates | 96068 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000134 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1385 | +| iterations | 20064 | +| time_elapsed | 29665 | +| total_timesteps | 41091072 | +| train/ | | +| approx_kl | 0.015210195 | +| clip_fraction | 0.338 | +| clip_range | 0.0647 | +| entropy_loss | -4.6 | +| explained_variance | 0.448 | +| learning_rate | 4.02e-05 | +| loss | -0.0279 | +| n_updates | 96072 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.00012 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1385 | +| iterations | 20065 | +| time_elapsed | 29666 | +| total_timesteps | 41093120 | +| train/ | | +| approx_kl | 0.013682857 | +| clip_fraction | 0.344 | +| clip_range | 0.0647 | +| entropy_loss | -5.74 | +| explained_variance | 0.56 | +| learning_rate | 4.02e-05 | +| loss | -0.0293 | +| n_updates | 96076 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000134 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1385 | +| iterations | 20066 | +| time_elapsed | 29668 | +| total_timesteps | 41095168 | +| train/ | | +| approx_kl | 0.013222858 | +| clip_fraction | 0.348 | +| clip_range | 0.0647 | +| entropy_loss | -5.97 | +| explained_variance | 0.175 | +| learning_rate | 4.02e-05 | +| loss | -0.0249 | +| n_updates | 96080 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000124 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1385 | +| iterations | 20067 | +| time_elapsed | 29669 | +| total_timesteps | 41097216 | +| train/ | | +| approx_kl | 0.0107926745 | +| clip_fraction | 0.354 | +| clip_range | 0.0647 | +| entropy_loss | -6.11 | +| explained_variance | 0.28 | +| learning_rate | 4.02e-05 | +| loss | -0.0236 | +| n_updates | 96084 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000116 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1385 | +| iterations | 20068 | +| time_elapsed | 29671 | +| total_timesteps | 41099264 | +| train/ | | +| approx_kl | 0.011178626 | +| clip_fraction | 0.317 | +| clip_range | 0.0647 | +| entropy_loss | -6.04 | +| explained_variance | 0.521 | +| learning_rate | 4.02e-05 | +| loss | -0.0244 | +| n_updates | 96088 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000129 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1385 | +| iterations | 20069 | +| time_elapsed | 29672 | +| total_timesteps | 41101312 | +| train/ | | +| approx_kl | 0.009517614 | +| clip_fraction | 0.306 | +| clip_range | 0.0647 | +| entropy_loss | -6.57 | +| explained_variance | 0.238 | +| learning_rate | 4.02e-05 | +| loss | -0.0292 | +| n_updates | 96092 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000164 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1385 | +| iterations | 20070 | +| time_elapsed | 29674 | +| total_timesteps | 41103360 | +| train/ | | +| approx_kl | 0.009489187 | +| clip_fraction | 0.306 | +| clip_range | 0.0647 | +| entropy_loss | -6.32 | +| explained_variance | 0.229 | +| learning_rate | 4.02e-05 | +| loss | -0.0268 | +| n_updates | 96096 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000251 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1385 | +| iterations | 20071 | +| time_elapsed | 29675 | +| total_timesteps | 41105408 | +| train/ | | +| approx_kl | 0.014644457 | +| clip_fraction | 0.339 | +| clip_range | 0.0647 | +| entropy_loss | -5.92 | +| explained_variance | 0.341 | +| learning_rate | 4.02e-05 | +| loss | -0.0207 | +| n_updates | 96100 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000293 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1385 | +| iterations | 20072 | +| time_elapsed | 29677 | +| total_timesteps | 41107456 | +| train/ | | +| approx_kl | 0.013211824 | +| clip_fraction | 0.33 | +| clip_range | 0.0647 | +| entropy_loss | -5.47 | +| explained_variance | 0.556 | +| learning_rate | 4.02e-05 | +| loss | -0.029 | +| n_updates | 96104 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000131 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1385 | +| iterations | 20073 | +| time_elapsed | 29678 | +| total_timesteps | 41109504 | +| train/ | | +| approx_kl | 0.0132614635 | +| clip_fraction | 0.321 | +| clip_range | 0.0647 | +| entropy_loss | -5.65 | +| explained_variance | 0.594 | +| learning_rate | 4.02e-05 | +| loss | -0.0304 | +| n_updates | 96108 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000107 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1385 | +| iterations | 20074 | +| time_elapsed | 29680 | +| total_timesteps | 41111552 | +| train/ | | +| approx_kl | 0.013552355 | +| clip_fraction | 0.333 | +| clip_range | 0.0647 | +| entropy_loss | -5.5 | +| explained_variance | 0.59 | +| learning_rate | 4.02e-05 | +| loss | -0.0292 | +| n_updates | 96112 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000148 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1385 | +| iterations | 20075 | +| time_elapsed | 29681 | +| total_timesteps | 41113600 | +| train/ | | +| approx_kl | 0.017149549 | +| clip_fraction | 0.324 | +| clip_range | 0.0647 | +| entropy_loss | -5.93 | +| explained_variance | 0.341 | +| learning_rate | 4.02e-05 | +| loss | -0.029 | +| n_updates | 96116 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000154 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1385 | +| iterations | 20076 | +| time_elapsed | 29683 | +| total_timesteps | 41115648 | +| train/ | | +| approx_kl | 0.010353127 | +| clip_fraction | 0.318 | +| clip_range | 0.0647 | +| entropy_loss | -6.04 | +| explained_variance | 0.548 | +| learning_rate | 4.02e-05 | +| loss | -0.0257 | +| n_updates | 96120 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000108 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1385 | +| iterations | 20077 | +| time_elapsed | 29684 | +| total_timesteps | 41117696 | +| train/ | | +| approx_kl | 0.012286721 | +| clip_fraction | 0.304 | +| clip_range | 0.0647 | +| entropy_loss | -5.8 | +| explained_variance | 0.466 | +| learning_rate | 4.02e-05 | +| loss | -0.0271 | +| n_updates | 96124 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000188 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1385 | +| iterations | 20078 | +| time_elapsed | 29686 | +| total_timesteps | 41119744 | +| train/ | | +| approx_kl | 0.012430922 | +| clip_fraction | 0.328 | +| clip_range | 0.0647 | +| entropy_loss | -6.26 | +| explained_variance | 0.23 | +| learning_rate | 4.02e-05 | +| loss | -0.0264 | +| n_updates | 96128 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000215 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1385 | +| iterations | 20079 | +| time_elapsed | 29687 | +| total_timesteps | 41121792 | +| train/ | | +| approx_kl | 0.01361746 | +| clip_fraction | 0.339 | +| clip_range | 0.0647 | +| entropy_loss | -6.29 | +| explained_variance | 0.343 | +| learning_rate | 4.02e-05 | +| loss | -0.0269 | +| n_updates | 96132 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000174 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1385 | +| iterations | 20080 | +| time_elapsed | 29689 | +| total_timesteps | 41123840 | +| train/ | | +| approx_kl | 0.012583457 | +| clip_fraction | 0.319 | +| clip_range | 0.0647 | +| entropy_loss | -5.75 | +| explained_variance | 0.451 | +| learning_rate | 4.02e-05 | +| loss | -0.0308 | +| n_updates | 96136 | +| policy_gradient_loss | -0.0175 | +| value_loss | 7.96e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1385 | +| iterations | 20081 | +| time_elapsed | 29691 | +| total_timesteps | 41125888 | +| train/ | | +| approx_kl | 0.012341775 | +| clip_fraction | 0.326 | +| clip_range | 0.0647 | +| entropy_loss | -6.29 | +| explained_variance | 0.0851 | +| learning_rate | 4.02e-05 | +| loss | -0.0273 | +| n_updates | 96140 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000128 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1385 | +| iterations | 20082 | +| time_elapsed | 29692 | +| total_timesteps | 41127936 | +| train/ | | +| approx_kl | 0.01436335 | +| clip_fraction | 0.293 | +| clip_range | 0.0647 | +| entropy_loss | -5.76 | +| explained_variance | 0.459 | +| learning_rate | 4.02e-05 | +| loss | -0.0223 | +| n_updates | 96144 | +| policy_gradient_loss | -0.0139 | +| value_loss | 0.000248 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1385 | +| iterations | 20083 | +| time_elapsed | 29694 | +| total_timesteps | 41129984 | +| train/ | | +| approx_kl | 0.011627929 | +| clip_fraction | 0.321 | +| clip_range | 0.0647 | +| entropy_loss | -6.09 | +| explained_variance | 0.226 | +| learning_rate | 4.02e-05 | +| loss | -0.0244 | +| n_updates | 96148 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000185 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1385 | +| iterations | 20084 | +| time_elapsed | 29695 | +| total_timesteps | 41132032 | +| train/ | | +| approx_kl | 0.012070732 | +| clip_fraction | 0.321 | +| clip_range | 0.0647 | +| entropy_loss | -5.61 | +| explained_variance | 0.449 | +| learning_rate | 4.02e-05 | +| loss | -0.0235 | +| n_updates | 96152 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000257 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1385 | +| iterations | 20085 | +| time_elapsed | 29697 | +| total_timesteps | 41134080 | +| train/ | | +| approx_kl | 0.013221178 | +| clip_fraction | 0.332 | +| clip_range | 0.0647 | +| entropy_loss | -6.21 | +| explained_variance | 0.53 | +| learning_rate | 4.02e-05 | +| loss | -0.0269 | +| n_updates | 96156 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000114 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1385 | +| iterations | 20086 | +| time_elapsed | 29698 | +| total_timesteps | 41136128 | +| train/ | | +| approx_kl | 0.010012037 | +| clip_fraction | 0.304 | +| clip_range | 0.0647 | +| entropy_loss | -5.4 | +| explained_variance | 0.419 | +| learning_rate | 4.02e-05 | +| loss | -0.0253 | +| n_updates | 96160 | +| policy_gradient_loss | -0.0121 | +| value_loss | 0.000355 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1385 | +| iterations | 20087 | +| time_elapsed | 29700 | +| total_timesteps | 41138176 | +| train/ | | +| approx_kl | 0.013695322 | +| clip_fraction | 0.325 | +| clip_range | 0.0647 | +| entropy_loss | -5.68 | +| explained_variance | 0.385 | +| learning_rate | 4.02e-05 | +| loss | -0.026 | +| n_updates | 96164 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000177 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1385 | +| iterations | 20088 | +| time_elapsed | 29701 | +| total_timesteps | 41140224 | +| train/ | | +| approx_kl | 0.012036378 | +| clip_fraction | 0.347 | +| clip_range | 0.0647 | +| entropy_loss | -5.17 | +| explained_variance | 0.612 | +| learning_rate | 4.02e-05 | +| loss | -0.0281 | +| n_updates | 96168 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000143 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1385 | +| iterations | 20089 | +| time_elapsed | 29703 | +| total_timesteps | 41142272 | +| train/ | | +| approx_kl | 0.011521079 | +| clip_fraction | 0.311 | +| clip_range | 0.0647 | +| entropy_loss | -5.93 | +| explained_variance | 0.166 | +| learning_rate | 4.02e-05 | +| loss | -0.031 | +| n_updates | 96172 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000216 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1385 | +| iterations | 20090 | +| time_elapsed | 29704 | +| total_timesteps | 41144320 | +| train/ | | +| approx_kl | 0.013057953 | +| clip_fraction | 0.385 | +| clip_range | 0.0647 | +| entropy_loss | -5.79 | +| explained_variance | 0.361 | +| learning_rate | 4.02e-05 | +| loss | -0.033 | +| n_updates | 96176 | +| policy_gradient_loss | -0.0213 | +| value_loss | 8.27e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1385 | +| iterations | 20091 | +| time_elapsed | 29706 | +| total_timesteps | 41146368 | +| train/ | | +| approx_kl | 0.013432258 | +| clip_fraction | 0.324 | +| clip_range | 0.0647 | +| entropy_loss | -6.05 | +| explained_variance | 0.343 | +| learning_rate | 4.02e-05 | +| loss | -0.0259 | +| n_updates | 96180 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1385 | +| iterations | 20092 | +| time_elapsed | 29707 | +| total_timesteps | 41148416 | +| train/ | | +| approx_kl | 0.011066271 | +| clip_fraction | 0.311 | +| clip_range | 0.0647 | +| entropy_loss | -5 | +| explained_variance | 0.755 | +| learning_rate | 4.02e-05 | +| loss | -0.0265 | +| n_updates | 96184 | +| policy_gradient_loss | -0.0148 | +| value_loss | 7.72e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1385 | +| iterations | 20093 | +| time_elapsed | 29709 | +| total_timesteps | 41150464 | +| train/ | | +| approx_kl | 0.012468699 | +| clip_fraction | 0.355 | +| clip_range | 0.0647 | +| entropy_loss | -6.04 | +| explained_variance | -0.208 | +| learning_rate | 4.02e-05 | +| loss | -0.0347 | +| n_updates | 96188 | +| policy_gradient_loss | -0.0186 | +| value_loss | 6.15e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1385 | +| iterations | 20094 | +| time_elapsed | 29710 | +| total_timesteps | 41152512 | +| train/ | | +| approx_kl | 0.01111366 | +| clip_fraction | 0.299 | +| clip_range | 0.0647 | +| entropy_loss | -5.4 | +| explained_variance | 0.259 | +| learning_rate | 4.02e-05 | +| loss | -0.0176 | +| n_updates | 96192 | +| policy_gradient_loss | -0.0131 | +| value_loss | 0.000176 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1385 | +| iterations | 20095 | +| time_elapsed | 29712 | +| total_timesteps | 41154560 | +| train/ | | +| approx_kl | 0.014763792 | +| clip_fraction | 0.33 | +| clip_range | 0.0647 | +| entropy_loss | -5.9 | +| explained_variance | -0.131 | +| learning_rate | 4.02e-05 | +| loss | -0.0259 | +| n_updates | 96196 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000107 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1385 | +| iterations | 20096 | +| time_elapsed | 29713 | +| total_timesteps | 41156608 | +| train/ | | +| approx_kl | 0.014039574 | +| clip_fraction | 0.352 | +| clip_range | 0.0647 | +| entropy_loss | -5.86 | +| explained_variance | 0.365 | +| learning_rate | 4.02e-05 | +| loss | -0.0274 | +| n_updates | 96200 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000202 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1385 | +| iterations | 20097 | +| time_elapsed | 29715 | +| total_timesteps | 41158656 | +| train/ | | +| approx_kl | 0.011395892 | +| clip_fraction | 0.309 | +| clip_range | 0.0647 | +| entropy_loss | -4.75 | +| explained_variance | 0.627 | +| learning_rate | 4.02e-05 | +| loss | -0.0186 | +| n_updates | 96204 | +| policy_gradient_loss | -0.0126 | +| value_loss | 0.000225 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1385 | +| iterations | 20098 | +| time_elapsed | 29716 | +| total_timesteps | 41160704 | +| train/ | | +| approx_kl | 0.012681099 | +| clip_fraction | 0.336 | +| clip_range | 0.0647 | +| entropy_loss | -4.81 | +| explained_variance | 0.526 | +| learning_rate | 4.02e-05 | +| loss | -0.0247 | +| n_updates | 96208 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000202 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1385 | +| iterations | 20099 | +| time_elapsed | 29718 | +| total_timesteps | 41162752 | +| train/ | | +| approx_kl | 0.012702631 | +| clip_fraction | 0.367 | +| clip_range | 0.0647 | +| entropy_loss | -6.01 | +| explained_variance | -0.0981 | +| learning_rate | 4.02e-05 | +| loss | -0.0368 | +| n_updates | 96212 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000134 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1385 | +| iterations | 20100 | +| time_elapsed | 29719 | +| total_timesteps | 41164800 | +| train/ | | +| approx_kl | 0.013998779 | +| clip_fraction | 0.328 | +| clip_range | 0.0647 | +| entropy_loss | -6.14 | +| explained_variance | -0.0805 | +| learning_rate | 4.02e-05 | +| loss | -0.0276 | +| n_updates | 96216 | +| policy_gradient_loss | -0.0182 | +| value_loss | 9.83e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1385 | +| iterations | 20101 | +| time_elapsed | 29721 | +| total_timesteps | 41166848 | +| train/ | | +| approx_kl | 0.012665784 | +| clip_fraction | 0.324 | +| clip_range | 0.0647 | +| entropy_loss | -5.94 | +| explained_variance | 0.612 | +| learning_rate | 4.02e-05 | +| loss | -0.0242 | +| n_updates | 96220 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000104 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1385 | +| iterations | 20102 | +| time_elapsed | 29722 | +| total_timesteps | 41168896 | +| train/ | | +| approx_kl | 0.014585138 | +| clip_fraction | 0.326 | +| clip_range | 0.0647 | +| entropy_loss | -5.64 | +| explained_variance | 0.473 | +| learning_rate | 4.02e-05 | +| loss | -0.0243 | +| n_updates | 96224 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000192 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1385 | +| iterations | 20103 | +| time_elapsed | 29724 | +| total_timesteps | 41170944 | +| train/ | | +| approx_kl | 0.011863882 | +| clip_fraction | 0.35 | +| clip_range | 0.0647 | +| entropy_loss | -5.53 | +| explained_variance | 0.401 | +| learning_rate | 4.02e-05 | +| loss | -0.0292 | +| n_updates | 96228 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000173 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1385 | +| iterations | 20104 | +| time_elapsed | 29725 | +| total_timesteps | 41172992 | +| train/ | | +| approx_kl | 0.013477328 | +| clip_fraction | 0.33 | +| clip_range | 0.0647 | +| entropy_loss | -5.66 | +| explained_variance | 0.391 | +| learning_rate | 4.02e-05 | +| loss | -0.0291 | +| n_updates | 96232 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000116 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1385 | +| iterations | 20105 | +| time_elapsed | 29727 | +| total_timesteps | 41175040 | +| train/ | | +| approx_kl | 0.012504218 | +| clip_fraction | 0.292 | +| clip_range | 0.0647 | +| entropy_loss | -5.75 | +| explained_variance | 0.441 | +| learning_rate | 4.02e-05 | +| loss | -0.0229 | +| n_updates | 96236 | +| policy_gradient_loss | -0.0123 | +| value_loss | 0.000199 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1385 | +| iterations | 20106 | +| time_elapsed | 29729 | +| total_timesteps | 41177088 | +| train/ | | +| approx_kl | 0.0112319775 | +| clip_fraction | 0.327 | +| clip_range | 0.0647 | +| entropy_loss | -5.83 | +| explained_variance | 0.23 | +| learning_rate | 4.02e-05 | +| loss | -0.0193 | +| n_updates | 96240 | +| policy_gradient_loss | -0.0147 | +| value_loss | 0.000326 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1385 | +| iterations | 20107 | +| time_elapsed | 29730 | +| total_timesteps | 41179136 | +| train/ | | +| approx_kl | 0.014946026 | +| clip_fraction | 0.353 | +| clip_range | 0.0647 | +| entropy_loss | -5.47 | +| explained_variance | 0.614 | +| learning_rate | 4.02e-05 | +| loss | -0.0308 | +| n_updates | 96244 | +| policy_gradient_loss | -0.0193 | +| value_loss | 9.34e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1385 | +| iterations | 20108 | +| time_elapsed | 29732 | +| total_timesteps | 41181184 | +| train/ | | +| approx_kl | 0.011948866 | +| clip_fraction | 0.317 | +| clip_range | 0.0647 | +| entropy_loss | -6.11 | +| explained_variance | -0.00439 | +| learning_rate | 4.02e-05 | +| loss | -0.0287 | +| n_updates | 96248 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000197 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1385 | +| iterations | 20109 | +| time_elapsed | 29733 | +| total_timesteps | 41183232 | +| train/ | | +| approx_kl | 0.016012724 | +| clip_fraction | 0.31 | +| clip_range | 0.0647 | +| entropy_loss | -5.74 | +| explained_variance | 0.568 | +| learning_rate | 4.02e-05 | +| loss | -0.0278 | +| n_updates | 96252 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000124 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1385 | +| iterations | 20110 | +| time_elapsed | 29735 | +| total_timesteps | 41185280 | +| train/ | | +| approx_kl | 0.010892428 | +| clip_fraction | 0.304 | +| clip_range | 0.0647 | +| entropy_loss | -5.35 | +| explained_variance | 0.606 | +| learning_rate | 4.02e-05 | +| loss | -0.0239 | +| n_updates | 96256 | +| policy_gradient_loss | -0.0141 | +| value_loss | 0.000201 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1385 | +| iterations | 20111 | +| time_elapsed | 29736 | +| total_timesteps | 41187328 | +| train/ | | +| approx_kl | 0.017202713 | +| clip_fraction | 0.369 | +| clip_range | 0.0647 | +| entropy_loss | -5.38 | +| explained_variance | -0.0193 | +| learning_rate | 4.02e-05 | +| loss | -0.0307 | +| n_updates | 96260 | +| policy_gradient_loss | -0.02 | +| value_loss | 6.98e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1385 | +| iterations | 20112 | +| time_elapsed | 29738 | +| total_timesteps | 41189376 | +| train/ | | +| approx_kl | 0.011655706 | +| clip_fraction | 0.334 | +| clip_range | 0.0647 | +| entropy_loss | -5.71 | +| explained_variance | 0.0602 | +| learning_rate | 4.02e-05 | +| loss | -0.026 | +| n_updates | 96264 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000311 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1385 | +| iterations | 20113 | +| time_elapsed | 29739 | +| total_timesteps | 41191424 | +| train/ | | +| approx_kl | 0.014672642 | +| clip_fraction | 0.363 | +| clip_range | 0.0647 | +| entropy_loss | -6.22 | +| explained_variance | -0.178 | +| learning_rate | 4.02e-05 | +| loss | -0.0315 | +| n_updates | 96268 | +| policy_gradient_loss | -0.0202 | +| value_loss | 9.47e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1385 | +| iterations | 20114 | +| time_elapsed | 29741 | +| total_timesteps | 41193472 | +| train/ | | +| approx_kl | 0.013086581 | +| clip_fraction | 0.319 | +| clip_range | 0.0647 | +| entropy_loss | -6.32 | +| explained_variance | 0.536 | +| learning_rate | 4.02e-05 | +| loss | -0.0307 | +| n_updates | 96272 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000142 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1385 | +| iterations | 20115 | +| time_elapsed | 29743 | +| total_timesteps | 41195520 | +| train/ | | +| approx_kl | 0.012567788 | +| clip_fraction | 0.315 | +| clip_range | 0.0647 | +| entropy_loss | -6.06 | +| explained_variance | 0.3 | +| learning_rate | 4.02e-05 | +| loss | -0.0261 | +| n_updates | 96276 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000137 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1385 | +| iterations | 20116 | +| time_elapsed | 29744 | +| total_timesteps | 41197568 | +| train/ | | +| approx_kl | 0.013894804 | +| clip_fraction | 0.342 | +| clip_range | 0.0647 | +| entropy_loss | -6 | +| explained_variance | -0.243 | +| learning_rate | 4.02e-05 | +| loss | -0.0329 | +| n_updates | 96280 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000109 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1385 | +| iterations | 20117 | +| time_elapsed | 29746 | +| total_timesteps | 41199616 | +| train/ | | +| approx_kl | 0.012522064 | +| clip_fraction | 0.365 | +| clip_range | 0.0647 | +| entropy_loss | -5.98 | +| explained_variance | 0.345 | +| learning_rate | 4.02e-05 | +| loss | -0.0256 | +| n_updates | 96284 | +| policy_gradient_loss | -0.018 | +| value_loss | 9.29e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1385 | +| iterations | 20118 | +| time_elapsed | 29747 | +| total_timesteps | 41201664 | +| train/ | | +| approx_kl | 0.01119682 | +| clip_fraction | 0.311 | +| clip_range | 0.0647 | +| entropy_loss | -5.48 | +| explained_variance | 0.605 | +| learning_rate | 4.02e-05 | +| loss | -0.0244 | +| n_updates | 96288 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.000238 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1385 | +| iterations | 20119 | +| time_elapsed | 29749 | +| total_timesteps | 41203712 | +| train/ | | +| approx_kl | 0.014283745 | +| clip_fraction | 0.327 | +| clip_range | 0.0647 | +| entropy_loss | -5.89 | +| explained_variance | -0.0597 | +| learning_rate | 4.02e-05 | +| loss | -0.0237 | +| n_updates | 96292 | +| policy_gradient_loss | -0.0146 | +| value_loss | 0.000312 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1385 | +| iterations | 20120 | +| time_elapsed | 29750 | +| total_timesteps | 41205760 | +| train/ | | +| approx_kl | 0.012386377 | +| clip_fraction | 0.355 | +| clip_range | 0.0647 | +| entropy_loss | -5.56 | +| explained_variance | 0.633 | +| learning_rate | 4.02e-05 | +| loss | -0.0274 | +| n_updates | 96296 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000104 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1385 | +| iterations | 20121 | +| time_elapsed | 29752 | +| total_timesteps | 41207808 | +| train/ | | +| approx_kl | 0.014357985 | +| clip_fraction | 0.325 | +| clip_range | 0.0647 | +| entropy_loss | -5.71 | +| explained_variance | 0.232 | +| learning_rate | 4.02e-05 | +| loss | -0.029 | +| n_updates | 96300 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000167 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1385 | +| iterations | 20122 | +| time_elapsed | 29753 | +| total_timesteps | 41209856 | +| train/ | | +| approx_kl | 0.0139746405 | +| clip_fraction | 0.312 | +| clip_range | 0.0647 | +| entropy_loss | -6.32 | +| explained_variance | -0.236 | +| learning_rate | 4.02e-05 | +| loss | -0.0283 | +| n_updates | 96304 | +| policy_gradient_loss | -0.0178 | +| value_loss | 7.72e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1385 | +| iterations | 20123 | +| time_elapsed | 29755 | +| total_timesteps | 41211904 | +| train/ | | +| approx_kl | 0.010852063 | +| clip_fraction | 0.313 | +| clip_range | 0.0647 | +| entropy_loss | -6.01 | +| explained_variance | 0.413 | +| learning_rate | 4.02e-05 | +| loss | -0.0222 | +| n_updates | 96308 | +| policy_gradient_loss | -0.0165 | +| value_loss | 7.97e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1385 | +| iterations | 20124 | +| time_elapsed | 29756 | +| total_timesteps | 41213952 | +| train/ | | +| approx_kl | 0.012986852 | +| clip_fraction | 0.353 | +| clip_range | 0.0647 | +| entropy_loss | -5.84 | +| explained_variance | -0.0765 | +| learning_rate | 4.02e-05 | +| loss | -0.0286 | +| n_updates | 96312 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000104 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1385 | +| iterations | 20125 | +| time_elapsed | 29758 | +| total_timesteps | 41216000 | +| train/ | | +| approx_kl | 0.013070042 | +| clip_fraction | 0.291 | +| clip_range | 0.0647 | +| entropy_loss | -6.07 | +| explained_variance | -0.0591 | +| learning_rate | 4.02e-05 | +| loss | -0.026 | +| n_updates | 96316 | +| policy_gradient_loss | -0.0132 | +| value_loss | 0.000204 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1385 | +| iterations | 20126 | +| time_elapsed | 29759 | +| total_timesteps | 41218048 | +| train/ | | +| approx_kl | 0.012906992 | +| clip_fraction | 0.345 | +| clip_range | 0.0647 | +| entropy_loss | -5.55 | +| explained_variance | 0.591 | +| learning_rate | 4.02e-05 | +| loss | -0.0291 | +| n_updates | 96320 | +| policy_gradient_loss | -0.0166 | +| value_loss | 8.8e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1385 | +| iterations | 20127 | +| time_elapsed | 29761 | +| total_timesteps | 41220096 | +| train/ | | +| approx_kl | 0.01688069 | +| clip_fraction | 0.341 | +| clip_range | 0.0647 | +| entropy_loss | -5.77 | +| explained_variance | -0.151 | +| learning_rate | 4.02e-05 | +| loss | -0.026 | +| n_updates | 96324 | +| policy_gradient_loss | -0.0161 | +| value_loss | 9.95e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1385 | +| iterations | 20128 | +| time_elapsed | 29763 | +| total_timesteps | 41222144 | +| train/ | | +| approx_kl | 0.011882987 | +| clip_fraction | 0.315 | +| clip_range | 0.0647 | +| entropy_loss | -5.64 | +| explained_variance | 0.419 | +| learning_rate | 4.02e-05 | +| loss | -0.026 | +| n_updates | 96328 | +| policy_gradient_loss | -0.0129 | +| value_loss | 0.000228 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1385 | +| iterations | 20129 | +| time_elapsed | 29764 | +| total_timesteps | 41224192 | +| train/ | | +| approx_kl | 0.014711322 | +| clip_fraction | 0.358 | +| clip_range | 0.0647 | +| entropy_loss | -5.34 | +| explained_variance | 0.507 | +| learning_rate | 4.02e-05 | +| loss | -0.0367 | +| n_updates | 96332 | +| policy_gradient_loss | -0.019 | +| value_loss | 8.56e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1384 | +| iterations | 20130 | +| time_elapsed | 29766 | +| total_timesteps | 41226240 | +| train/ | | +| approx_kl | 0.01149511 | +| clip_fraction | 0.331 | +| clip_range | 0.0647 | +| entropy_loss | -5.45 | +| explained_variance | 0.418 | +| learning_rate | 4.02e-05 | +| loss | -0.024 | +| n_updates | 96336 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000224 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1384 | +| iterations | 20131 | +| time_elapsed | 29767 | +| total_timesteps | 41228288 | +| train/ | | +| approx_kl | 0.012759436 | +| clip_fraction | 0.338 | +| clip_range | 0.0647 | +| entropy_loss | -5.71 | +| explained_variance | 0.258 | +| learning_rate | 4.02e-05 | +| loss | -0.0356 | +| n_updates | 96340 | +| policy_gradient_loss | -0.0189 | +| value_loss | 7.99e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1384 | +| iterations | 20132 | +| time_elapsed | 29769 | +| total_timesteps | 41230336 | +| train/ | | +| approx_kl | 0.010571718 | +| clip_fraction | 0.332 | +| clip_range | 0.0647 | +| entropy_loss | -6.5 | +| explained_variance | 0.121 | +| learning_rate | 4.02e-05 | +| loss | -0.0251 | +| n_updates | 96344 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.00023 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1384 | +| iterations | 20133 | +| time_elapsed | 29770 | +| total_timesteps | 41232384 | +| train/ | | +| approx_kl | 0.01239096 | +| clip_fraction | 0.338 | +| clip_range | 0.0647 | +| entropy_loss | -6.15 | +| explained_variance | 0.148 | +| learning_rate | 4.02e-05 | +| loss | -0.0331 | +| n_updates | 96348 | +| policy_gradient_loss | -0.0193 | +| value_loss | 7.93e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1384 | +| iterations | 20134 | +| time_elapsed | 29772 | +| total_timesteps | 41234432 | +| train/ | | +| approx_kl | 0.011007414 | +| clip_fraction | 0.313 | +| clip_range | 0.0647 | +| entropy_loss | -5.56 | +| explained_variance | 0.195 | +| learning_rate | 4.02e-05 | +| loss | -0.0208 | +| n_updates | 96352 | +| policy_gradient_loss | -0.0142 | +| value_loss | 0.000409 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1384 | +| iterations | 20135 | +| time_elapsed | 29774 | +| total_timesteps | 41236480 | +| train/ | | +| approx_kl | 0.009487596 | +| clip_fraction | 0.326 | +| clip_range | 0.0647 | +| entropy_loss | -6.4 | +| explained_variance | 0.285 | +| learning_rate | 4.02e-05 | +| loss | -0.0257 | +| n_updates | 96356 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000245 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1384 | +| iterations | 20136 | +| time_elapsed | 29775 | +| total_timesteps | 41238528 | +| train/ | | +| approx_kl | 0.009480175 | +| clip_fraction | 0.318 | +| clip_range | 0.0647 | +| entropy_loss | -6.01 | +| explained_variance | 0.478 | +| learning_rate | 4.02e-05 | +| loss | -0.0301 | +| n_updates | 96360 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000235 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1384 | +| iterations | 20137 | +| time_elapsed | 29777 | +| total_timesteps | 41240576 | +| train/ | | +| approx_kl | 0.014642144 | +| clip_fraction | 0.341 | +| clip_range | 0.0647 | +| entropy_loss | -5.88 | +| explained_variance | 0.292 | +| learning_rate | 4.02e-05 | +| loss | -0.0274 | +| n_updates | 96364 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000153 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1384 | +| iterations | 20138 | +| time_elapsed | 29778 | +| total_timesteps | 41242624 | +| train/ | | +| approx_kl | 0.010569165 | +| clip_fraction | 0.337 | +| clip_range | 0.0647 | +| entropy_loss | -6.46 | +| explained_variance | -0.211 | +| learning_rate | 4.02e-05 | +| loss | -0.0306 | +| n_updates | 96368 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000118 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1384 | +| iterations | 20139 | +| time_elapsed | 29780 | +| total_timesteps | 41244672 | +| train/ | | +| approx_kl | 0.014049033 | +| clip_fraction | 0.359 | +| clip_range | 0.0647 | +| entropy_loss | -5.65 | +| explained_variance | 0.543 | +| learning_rate | 4.02e-05 | +| loss | -0.0276 | +| n_updates | 96372 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000133 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1384 | +| iterations | 20140 | +| time_elapsed | 29781 | +| total_timesteps | 41246720 | +| train/ | | +| approx_kl | 0.011621572 | +| clip_fraction | 0.328 | +| clip_range | 0.0647 | +| entropy_loss | -6.13 | +| explained_variance | 0.248 | +| learning_rate | 4.02e-05 | +| loss | -0.0218 | +| n_updates | 96376 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000248 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1384 | +| iterations | 20141 | +| time_elapsed | 29783 | +| total_timesteps | 41248768 | +| train/ | | +| approx_kl | 0.017040372 | +| clip_fraction | 0.34 | +| clip_range | 0.0647 | +| entropy_loss | -5.47 | +| explained_variance | 0.505 | +| learning_rate | 4.02e-05 | +| loss | -0.0211 | +| n_updates | 96380 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000133 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1384 | +| iterations | 20142 | +| time_elapsed | 29784 | +| total_timesteps | 41250816 | +| train/ | | +| approx_kl | 0.014747692 | +| clip_fraction | 0.349 | +| clip_range | 0.0647 | +| entropy_loss | -5.02 | +| explained_variance | 0.727 | +| learning_rate | 4.02e-05 | +| loss | -0.0267 | +| n_updates | 96384 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000119 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1384 | +| iterations | 20143 | +| time_elapsed | 29786 | +| total_timesteps | 41252864 | +| train/ | | +| approx_kl | 0.010801692 | +| clip_fraction | 0.328 | +| clip_range | 0.0647 | +| entropy_loss | -6.16 | +| explained_variance | 0.193 | +| learning_rate | 4.02e-05 | +| loss | -0.0265 | +| n_updates | 96388 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000192 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1384 | +| iterations | 20144 | +| time_elapsed | 29787 | +| total_timesteps | 41254912 | +| train/ | | +| approx_kl | 0.012913586 | +| clip_fraction | 0.349 | +| clip_range | 0.0647 | +| entropy_loss | -6.75 | +| explained_variance | -0.267 | +| learning_rate | 4.02e-05 | +| loss | -0.0363 | +| n_updates | 96392 | +| policy_gradient_loss | -0.0213 | +| value_loss | 7.5e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1384 | +| iterations | 20145 | +| time_elapsed | 29789 | +| total_timesteps | 41256960 | +| train/ | | +| approx_kl | 0.0112873325 | +| clip_fraction | 0.338 | +| clip_range | 0.0647 | +| entropy_loss | -6.03 | +| explained_variance | 0.285 | +| learning_rate | 4.02e-05 | +| loss | -0.0315 | +| n_updates | 96396 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000181 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1384 | +| iterations | 20146 | +| time_elapsed | 29790 | +| total_timesteps | 41259008 | +| train/ | | +| approx_kl | 0.0110252295 | +| clip_fraction | 0.33 | +| clip_range | 0.0647 | +| entropy_loss | -5.82 | +| explained_variance | 0.563 | +| learning_rate | 4.02e-05 | +| loss | -0.0271 | +| n_updates | 96400 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000129 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1384 | +| iterations | 20147 | +| time_elapsed | 29792 | +| total_timesteps | 41261056 | +| train/ | | +| approx_kl | 0.01158077 | +| clip_fraction | 0.328 | +| clip_range | 0.0647 | +| entropy_loss | -5.65 | +| explained_variance | 0.615 | +| learning_rate | 4.02e-05 | +| loss | -0.0312 | +| n_updates | 96404 | +| policy_gradient_loss | -0.0194 | +| value_loss | 9.05e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1384 | +| iterations | 20148 | +| time_elapsed | 29793 | +| total_timesteps | 41263104 | +| train/ | | +| approx_kl | 0.008805351 | +| clip_fraction | 0.278 | +| clip_range | 0.0647 | +| entropy_loss | -6.28 | +| explained_variance | 0.423 | +| learning_rate | 4.02e-05 | +| loss | -0.0221 | +| n_updates | 96408 | +| policy_gradient_loss | -0.013 | +| value_loss | 0.000194 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1384 | +| iterations | 20149 | +| time_elapsed | 29795 | +| total_timesteps | 41265152 | +| train/ | | +| approx_kl | 0.008434626 | +| clip_fraction | 0.308 | +| clip_range | 0.0647 | +| entropy_loss | -5.91 | +| explained_variance | 0.38 | +| learning_rate | 4.02e-05 | +| loss | -0.0266 | +| n_updates | 96412 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000263 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1384 | +| iterations | 20150 | +| time_elapsed | 29796 | +| total_timesteps | 41267200 | +| train/ | | +| approx_kl | 0.008914094 | +| clip_fraction | 0.328 | +| clip_range | 0.0647 | +| entropy_loss | -6.48 | +| explained_variance | 0.0641 | +| learning_rate | 4.02e-05 | +| loss | -0.0314 | +| n_updates | 96416 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000128 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1384 | +| iterations | 20151 | +| time_elapsed | 29798 | +| total_timesteps | 41269248 | +| train/ | | +| approx_kl | 0.011807222 | +| clip_fraction | 0.302 | +| clip_range | 0.0647 | +| entropy_loss | -6.41 | +| explained_variance | 0.144 | +| learning_rate | 4.02e-05 | +| loss | -0.0238 | +| n_updates | 96420 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.000243 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1384 | +| iterations | 20152 | +| time_elapsed | 29800 | +| total_timesteps | 41271296 | +| train/ | | +| approx_kl | 0.011848081 | +| clip_fraction | 0.288 | +| clip_range | 0.0647 | +| entropy_loss | -4.37 | +| explained_variance | 0.764 | +| learning_rate | 4.02e-05 | +| loss | -0.0168 | +| n_updates | 96424 | +| policy_gradient_loss | -0.0124 | +| value_loss | 0.000179 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1384 | +| iterations | 20153 | +| time_elapsed | 29801 | +| total_timesteps | 41273344 | +| train/ | | +| approx_kl | 0.014066701 | +| clip_fraction | 0.355 | +| clip_range | 0.0647 | +| entropy_loss | -5.42 | +| explained_variance | -0.284 | +| learning_rate | 4.02e-05 | +| loss | -0.0288 | +| n_updates | 96428 | +| policy_gradient_loss | -0.0199 | +| value_loss | 9.19e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1384 | +| iterations | 20154 | +| time_elapsed | 29803 | +| total_timesteps | 41275392 | +| train/ | | +| approx_kl | 0.012536993 | +| clip_fraction | 0.311 | +| clip_range | 0.0647 | +| entropy_loss | -5.72 | +| explained_variance | 0.474 | +| learning_rate | 4.02e-05 | +| loss | -0.0322 | +| n_updates | 96432 | +| policy_gradient_loss | -0.0178 | +| value_loss | 9.05e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1384 | +| iterations | 20155 | +| time_elapsed | 29804 | +| total_timesteps | 41277440 | +| train/ | | +| approx_kl | 0.009442368 | +| clip_fraction | 0.305 | +| clip_range | 0.0647 | +| entropy_loss | -5.94 | +| explained_variance | -0.0856 | +| learning_rate | 4.02e-05 | +| loss | -0.0234 | +| n_updates | 96436 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000168 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1384 | +| iterations | 20156 | +| time_elapsed | 29806 | +| total_timesteps | 41279488 | +| train/ | | +| approx_kl | 0.0107562365 | +| clip_fraction | 0.306 | +| clip_range | 0.0647 | +| entropy_loss | -5.27 | +| explained_variance | 0.384 | +| learning_rate | 4.02e-05 | +| loss | -0.0176 | +| n_updates | 96440 | +| policy_gradient_loss | -0.0135 | +| value_loss | 0.000268 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1384 | +| iterations | 20157 | +| time_elapsed | 29807 | +| total_timesteps | 41281536 | +| train/ | | +| approx_kl | 0.012113391 | +| clip_fraction | 0.331 | +| clip_range | 0.0647 | +| entropy_loss | -5.83 | +| explained_variance | 0.402 | +| learning_rate | 4.02e-05 | +| loss | -0.0319 | +| n_updates | 96444 | +| policy_gradient_loss | -0.0193 | +| value_loss | 7.73e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1384 | +| iterations | 20158 | +| time_elapsed | 29809 | +| total_timesteps | 41283584 | +| train/ | | +| approx_kl | 0.012184806 | +| clip_fraction | 0.335 | +| clip_range | 0.0647 | +| entropy_loss | -6.3 | +| explained_variance | -0.246 | +| learning_rate | 4.02e-05 | +| loss | -0.0316 | +| n_updates | 96448 | +| policy_gradient_loss | -0.0189 | +| value_loss | 9.92e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1384 | +| iterations | 20159 | +| time_elapsed | 29810 | +| total_timesteps | 41285632 | +| train/ | | +| approx_kl | 0.009364955 | +| clip_fraction | 0.299 | +| clip_range | 0.0647 | +| entropy_loss | -6.08 | +| explained_variance | 0.44 | +| learning_rate | 4.02e-05 | +| loss | -0.0256 | +| n_updates | 96452 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000145 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1384 | +| iterations | 20160 | +| time_elapsed | 29812 | +| total_timesteps | 41287680 | +| train/ | | +| approx_kl | 0.010070826 | +| clip_fraction | 0.305 | +| clip_range | 0.0647 | +| entropy_loss | -6.14 | +| explained_variance | 0.296 | +| learning_rate | 4.02e-05 | +| loss | -0.0234 | +| n_updates | 96456 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000303 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1384 | +| iterations | 20161 | +| time_elapsed | 29813 | +| total_timesteps | 41289728 | +| train/ | | +| approx_kl | 0.009616038 | +| clip_fraction | 0.33 | +| clip_range | 0.0647 | +| entropy_loss | -5.52 | +| explained_variance | 0.527 | +| learning_rate | 4.02e-05 | +| loss | -0.0258 | +| n_updates | 96460 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000185 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1384 | +| iterations | 20162 | +| time_elapsed | 29815 | +| total_timesteps | 41291776 | +| train/ | | +| approx_kl | 0.013254581 | +| clip_fraction | 0.331 | +| clip_range | 0.0647 | +| entropy_loss | -5.8 | +| explained_variance | 0.277 | +| learning_rate | 4.02e-05 | +| loss | -0.0326 | +| n_updates | 96464 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000195 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1384 | +| iterations | 20163 | +| time_elapsed | 29816 | +| total_timesteps | 41293824 | +| train/ | | +| approx_kl | 0.014463024 | +| clip_fraction | 0.351 | +| clip_range | 0.0647 | +| entropy_loss | -6.03 | +| explained_variance | 0.467 | +| learning_rate | 4.02e-05 | +| loss | -0.0285 | +| n_updates | 96468 | +| policy_gradient_loss | -0.0203 | +| value_loss | 8.16e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1384 | +| iterations | 20164 | +| time_elapsed | 29818 | +| total_timesteps | 41295872 | +| train/ | | +| approx_kl | 0.01057861 | +| clip_fraction | 0.312 | +| clip_range | 0.0647 | +| entropy_loss | -5.75 | +| explained_variance | 0.525 | +| learning_rate | 4.02e-05 | +| loss | -0.0249 | +| n_updates | 96472 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000287 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1384 | +| iterations | 20165 | +| time_elapsed | 29819 | +| total_timesteps | 41297920 | +| train/ | | +| approx_kl | 0.01170294 | +| clip_fraction | 0.353 | +| clip_range | 0.0647 | +| entropy_loss | -6.16 | +| explained_variance | 0.455 | +| learning_rate | 4.02e-05 | +| loss | -0.0314 | +| n_updates | 96476 | +| policy_gradient_loss | -0.0182 | +| value_loss | 9.26e-05 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1384 | +| iterations | 20166 | +| time_elapsed | 29821 | +| total_timesteps | 41299968 | +| train/ | | +| approx_kl | 0.01065296 | +| clip_fraction | 0.302 | +| clip_range | 0.0647 | +| entropy_loss | -5.69 | +| explained_variance | 0.672 | +| learning_rate | 4.02e-05 | +| loss | -0.0175 | +| n_updates | 96480 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.00013 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1384 | +| iterations | 20167 | +| time_elapsed | 29822 | +| total_timesteps | 41302016 | +| train/ | | +| approx_kl | 0.009644595 | +| clip_fraction | 0.32 | +| clip_range | 0.0647 | +| entropy_loss | -5.82 | +| explained_variance | 0.219 | +| learning_rate | 4.02e-05 | +| loss | -0.0289 | +| n_updates | 96484 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000113 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1384 | +| iterations | 20168 | +| time_elapsed | 29824 | +| total_timesteps | 41304064 | +| train/ | | +| approx_kl | 0.012811162 | +| clip_fraction | 0.307 | +| clip_range | 0.0647 | +| entropy_loss | -6.01 | +| explained_variance | 0.474 | +| learning_rate | 4.02e-05 | +| loss | -0.0252 | +| n_updates | 96488 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.000143 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1384 | +| iterations | 20169 | +| time_elapsed | 29825 | +| total_timesteps | 41306112 | +| train/ | | +| approx_kl | 0.012522677 | +| clip_fraction | 0.317 | +| clip_range | 0.0647 | +| entropy_loss | -5.78 | +| explained_variance | 0.443 | +| learning_rate | 4.02e-05 | +| loss | -0.0276 | +| n_updates | 96492 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.000193 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1384 | +| iterations | 20170 | +| time_elapsed | 29827 | +| total_timesteps | 41308160 | +| train/ | | +| approx_kl | 0.015133066 | +| clip_fraction | 0.326 | +| clip_range | 0.0647 | +| entropy_loss | -6.34 | +| explained_variance | 0.498 | +| learning_rate | 4.02e-05 | +| loss | -0.0308 | +| n_updates | 96496 | +| policy_gradient_loss | -0.0179 | +| value_loss | 8.33e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1384 | +| iterations | 20171 | +| time_elapsed | 29829 | +| total_timesteps | 41310208 | +| train/ | | +| approx_kl | 0.010939973 | +| clip_fraction | 0.334 | +| clip_range | 0.0647 | +| entropy_loss | -6.52 | +| explained_variance | -0.0536 | +| learning_rate | 4.02e-05 | +| loss | -0.0251 | +| n_updates | 96500 | +| policy_gradient_loss | -0.0161 | +| value_loss | 7.8e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1384 | +| iterations | 20172 | +| time_elapsed | 29830 | +| total_timesteps | 41312256 | +| train/ | | +| approx_kl | 0.010003265 | +| clip_fraction | 0.289 | +| clip_range | 0.0647 | +| entropy_loss | -6.22 | +| explained_variance | 0.43 | +| learning_rate | 4.02e-05 | +| loss | -0.0197 | +| n_updates | 96504 | +| policy_gradient_loss | -0.0145 | +| value_loss | 0.000202 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1384 | +| iterations | 20173 | +| time_elapsed | 29832 | +| total_timesteps | 41314304 | +| train/ | | +| approx_kl | 0.01139771 | +| clip_fraction | 0.306 | +| clip_range | 0.0647 | +| entropy_loss | -6.13 | +| explained_variance | -0.0332 | +| learning_rate | 4.02e-05 | +| loss | -0.0251 | +| n_updates | 96508 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000128 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1384 | +| iterations | 20174 | +| time_elapsed | 29833 | +| total_timesteps | 41316352 | +| train/ | | +| approx_kl | 0.012548219 | +| clip_fraction | 0.311 | +| clip_range | 0.0647 | +| entropy_loss | -5.91 | +| explained_variance | 0.411 | +| learning_rate | 4.02e-05 | +| loss | -0.0229 | +| n_updates | 96512 | +| policy_gradient_loss | -0.0141 | +| value_loss | 0.000193 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1384 | +| iterations | 20175 | +| time_elapsed | 29835 | +| total_timesteps | 41318400 | +| train/ | | +| approx_kl | 0.012311062 | +| clip_fraction | 0.331 | +| clip_range | 0.0647 | +| entropy_loss | -6.56 | +| explained_variance | -0.0852 | +| learning_rate | 4.02e-05 | +| loss | -0.024 | +| n_updates | 96516 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000127 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1384 | +| iterations | 20176 | +| time_elapsed | 29836 | +| total_timesteps | 41320448 | +| train/ | | +| approx_kl | 0.0127483625 | +| clip_fraction | 0.306 | +| clip_range | 0.0647 | +| entropy_loss | -5.54 | +| explained_variance | 0.65 | +| learning_rate | 4.02e-05 | +| loss | -0.0265 | +| n_updates | 96520 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000121 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1384 | +| iterations | 20177 | +| time_elapsed | 29838 | +| total_timesteps | 41322496 | +| train/ | | +| approx_kl | 0.011332919 | +| clip_fraction | 0.345 | +| clip_range | 0.0647 | +| entropy_loss | -5.32 | +| explained_variance | 0.494 | +| learning_rate | 4.02e-05 | +| loss | -0.0244 | +| n_updates | 96524 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000174 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1384 | +| iterations | 20178 | +| time_elapsed | 29839 | +| total_timesteps | 41324544 | +| train/ | | +| approx_kl | 0.015217446 | +| clip_fraction | 0.373 | +| clip_range | 0.0647 | +| entropy_loss | -5.02 | +| explained_variance | 0.749 | +| learning_rate | 4.02e-05 | +| loss | -0.0282 | +| n_updates | 96528 | +| policy_gradient_loss | -0.0189 | +| value_loss | 9.18e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1384 | +| iterations | 20179 | +| time_elapsed | 29841 | +| total_timesteps | 41326592 | +| train/ | | +| approx_kl | 0.012494948 | +| clip_fraction | 0.352 | +| clip_range | 0.0647 | +| entropy_loss | -5.73 | +| explained_variance | 0.477 | +| learning_rate | 4.02e-05 | +| loss | -0.0294 | +| n_updates | 96532 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000155 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1384 | +| iterations | 20180 | +| time_elapsed | 29842 | +| total_timesteps | 41328640 | +| train/ | | +| approx_kl | 0.012930706 | +| clip_fraction | 0.326 | +| clip_range | 0.0647 | +| entropy_loss | -5.8 | +| explained_variance | 0.298 | +| learning_rate | 4.02e-05 | +| loss | -0.0288 | +| n_updates | 96536 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000169 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1384 | +| iterations | 20181 | +| time_elapsed | 29844 | +| total_timesteps | 41330688 | +| train/ | | +| approx_kl | 0.010337185 | +| clip_fraction | 0.331 | +| clip_range | 0.0647 | +| entropy_loss | -5.91 | +| explained_variance | 0.236 | +| learning_rate | 4.02e-05 | +| loss | -0.0306 | +| n_updates | 96540 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000242 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1384 | +| iterations | 20182 | +| time_elapsed | 29845 | +| total_timesteps | 41332736 | +| train/ | | +| approx_kl | 0.012812597 | +| clip_fraction | 0.346 | +| clip_range | 0.0647 | +| entropy_loss | -5.78 | +| explained_variance | 0.497 | +| learning_rate | 4.02e-05 | +| loss | -0.0366 | +| n_updates | 96544 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000159 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1384 | +| iterations | 20183 | +| time_elapsed | 29847 | +| total_timesteps | 41334784 | +| train/ | | +| approx_kl | 0.010732623 | +| clip_fraction | 0.343 | +| clip_range | 0.0647 | +| entropy_loss | -6.21 | +| explained_variance | 0.261 | +| learning_rate | 4.02e-05 | +| loss | -0.0303 | +| n_updates | 96548 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000117 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1384 | +| iterations | 20184 | +| time_elapsed | 29848 | +| total_timesteps | 41336832 | +| train/ | | +| approx_kl | 0.010837444 | +| clip_fraction | 0.318 | +| clip_range | 0.0647 | +| entropy_loss | -6.23 | +| explained_variance | -0.3 | +| learning_rate | 4.02e-05 | +| loss | -0.0307 | +| n_updates | 96552 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000136 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1384 | +| iterations | 20185 | +| time_elapsed | 29850 | +| total_timesteps | 41338880 | +| train/ | | +| approx_kl | 0.010672818 | +| clip_fraction | 0.311 | +| clip_range | 0.0647 | +| entropy_loss | -5.54 | +| explained_variance | 0.65 | +| learning_rate | 4.02e-05 | +| loss | -0.0199 | +| n_updates | 96556 | +| policy_gradient_loss | -0.0137 | +| value_loss | 0.000189 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1384 | +| iterations | 20186 | +| time_elapsed | 29852 | +| total_timesteps | 41340928 | +| train/ | | +| approx_kl | 0.015108225 | +| clip_fraction | 0.326 | +| clip_range | 0.0647 | +| entropy_loss | -5.04 | +| explained_variance | 0.643 | +| learning_rate | 4.02e-05 | +| loss | -0.0214 | +| n_updates | 96560 | +| policy_gradient_loss | -0.014 | +| value_loss | 0.000186 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1384 | +| iterations | 20187 | +| time_elapsed | 29853 | +| total_timesteps | 41342976 | +| train/ | | +| approx_kl | 0.009648108 | +| clip_fraction | 0.318 | +| clip_range | 0.0647 | +| entropy_loss | -6.18 | +| explained_variance | 0.279 | +| learning_rate | 4.02e-05 | +| loss | -0.0188 | +| n_updates | 96564 | +| policy_gradient_loss | -0.0145 | +| value_loss | 0.000277 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1384 | +| iterations | 20188 | +| time_elapsed | 29855 | +| total_timesteps | 41345024 | +| train/ | | +| approx_kl | 0.010457793 | +| clip_fraction | 0.314 | +| clip_range | 0.0647 | +| entropy_loss | -6.7 | +| explained_variance | 0.0537 | +| learning_rate | 4.02e-05 | +| loss | -0.029 | +| n_updates | 96568 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000233 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1384 | +| iterations | 20189 | +| time_elapsed | 29856 | +| total_timesteps | 41347072 | +| train/ | | +| approx_kl | 0.010550382 | +| clip_fraction | 0.313 | +| clip_range | 0.0647 | +| entropy_loss | -5.98 | +| explained_variance | 0.535 | +| learning_rate | 4.02e-05 | +| loss | -0.0264 | +| n_updates | 96572 | +| policy_gradient_loss | -0.0144 | +| value_loss | 0.000259 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1384 | +| iterations | 20190 | +| time_elapsed | 29858 | +| total_timesteps | 41349120 | +| train/ | | +| approx_kl | 0.014235669 | +| clip_fraction | 0.375 | +| clip_range | 0.0647 | +| entropy_loss | -4.63 | +| explained_variance | 0.8 | +| learning_rate | 4.02e-05 | +| loss | -0.0331 | +| n_updates | 96576 | +| policy_gradient_loss | -0.0213 | +| value_loss | 5.91e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1384 | +| iterations | 20191 | +| time_elapsed | 29859 | +| total_timesteps | 41351168 | +| train/ | | +| approx_kl | 0.014995426 | +| clip_fraction | 0.347 | +| clip_range | 0.0647 | +| entropy_loss | -5.22 | +| explained_variance | 0.514 | +| learning_rate | 4.02e-05 | +| loss | -0.0277 | +| n_updates | 96580 | +| policy_gradient_loss | -0.0179 | +| value_loss | 9.28e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1384 | +| iterations | 20192 | +| time_elapsed | 29861 | +| total_timesteps | 41353216 | +| train/ | | +| approx_kl | 0.014017763 | +| clip_fraction | 0.331 | +| clip_range | 0.0647 | +| entropy_loss | -5.88 | +| explained_variance | 0.348 | +| learning_rate | 4.02e-05 | +| loss | -0.0315 | +| n_updates | 96584 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000131 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1384 | +| iterations | 20193 | +| time_elapsed | 29862 | +| total_timesteps | 41355264 | +| train/ | | +| approx_kl | 0.009827896 | +| clip_fraction | 0.298 | +| clip_range | 0.0647 | +| entropy_loss | -6.78 | +| explained_variance | -0.0293 | +| learning_rate | 4.02e-05 | +| loss | -0.0264 | +| n_updates | 96588 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000166 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1384 | +| iterations | 20194 | +| time_elapsed | 29864 | +| total_timesteps | 41357312 | +| train/ | | +| approx_kl | 0.007860505 | +| clip_fraction | 0.268 | +| clip_range | 0.0647 | +| entropy_loss | -6.34 | +| explained_variance | 0.392 | +| learning_rate | 4.02e-05 | +| loss | -0.0182 | +| n_updates | 96592 | +| policy_gradient_loss | -0.0122 | +| value_loss | 0.000329 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1384 | +| iterations | 20195 | +| time_elapsed | 29865 | +| total_timesteps | 41359360 | +| train/ | | +| approx_kl | 0.010479018 | +| clip_fraction | 0.319 | +| clip_range | 0.0647 | +| entropy_loss | -6.19 | +| explained_variance | 0.233 | +| learning_rate | 4.02e-05 | +| loss | -0.0276 | +| n_updates | 96596 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000265 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1384 | +| iterations | 20196 | +| time_elapsed | 29867 | +| total_timesteps | 41361408 | +| train/ | | +| approx_kl | 0.014352599 | +| clip_fraction | 0.324 | +| clip_range | 0.0647 | +| entropy_loss | -5.94 | +| explained_variance | 0.327 | +| learning_rate | 4.02e-05 | +| loss | -0.0272 | +| n_updates | 96600 | +| policy_gradient_loss | -0.0147 | +| value_loss | 0.000219 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1384 | +| iterations | 20197 | +| time_elapsed | 29868 | +| total_timesteps | 41363456 | +| train/ | | +| approx_kl | 0.011223994 | +| clip_fraction | 0.317 | +| clip_range | 0.0647 | +| entropy_loss | -6.04 | +| explained_variance | 0.381 | +| learning_rate | 4.02e-05 | +| loss | -0.0221 | +| n_updates | 96604 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.000215 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1384 | +| iterations | 20198 | +| time_elapsed | 29870 | +| total_timesteps | 41365504 | +| train/ | | +| approx_kl | 0.0155017935 | +| clip_fraction | 0.323 | +| clip_range | 0.0647 | +| entropy_loss | -5.78 | +| explained_variance | 0.292 | +| learning_rate | 4.02e-05 | +| loss | -0.0308 | +| n_updates | 96608 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.00011 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1384 | +| iterations | 20199 | +| time_elapsed | 29871 | +| total_timesteps | 41367552 | +| train/ | | +| approx_kl | 0.013456482 | +| clip_fraction | 0.34 | +| clip_range | 0.0647 | +| entropy_loss | -5.55 | +| explained_variance | 0.54 | +| learning_rate | 4.02e-05 | +| loss | -0.0289 | +| n_updates | 96612 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000116 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1384 | +| iterations | 20200 | +| time_elapsed | 29873 | +| total_timesteps | 41369600 | +| train/ | | +| approx_kl | 0.012561703 | +| clip_fraction | 0.319 | +| clip_range | 0.0647 | +| entropy_loss | -5.54 | +| explained_variance | 0.4 | +| learning_rate | 4.02e-05 | +| loss | -0.0229 | +| n_updates | 96616 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000204 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1384 | +| iterations | 20201 | +| time_elapsed | 29874 | +| total_timesteps | 41371648 | +| train/ | | +| approx_kl | 0.010310436 | +| clip_fraction | 0.321 | +| clip_range | 0.0647 | +| entropy_loss | -5.77 | +| explained_variance | 0.295 | +| learning_rate | 4.02e-05 | +| loss | -0.0228 | +| n_updates | 96620 | +| policy_gradient_loss | -0.0142 | +| value_loss | 0.000342 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1384 | +| iterations | 20202 | +| time_elapsed | 29876 | +| total_timesteps | 41373696 | +| train/ | | +| approx_kl | 0.012751079 | +| clip_fraction | 0.327 | +| clip_range | 0.0647 | +| entropy_loss | -5.61 | +| explained_variance | 0.507 | +| learning_rate | 4.02e-05 | +| loss | -0.0299 | +| n_updates | 96624 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000116 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1384 | +| iterations | 20203 | +| time_elapsed | 29878 | +| total_timesteps | 41375744 | +| train/ | | +| approx_kl | 0.013752135 | +| clip_fraction | 0.331 | +| clip_range | 0.0647 | +| entropy_loss | -5.91 | +| explained_variance | 0.543 | +| learning_rate | 4.02e-05 | +| loss | -0.0268 | +| n_updates | 96628 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000141 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1384 | +| iterations | 20204 | +| time_elapsed | 29879 | +| total_timesteps | 41377792 | +| train/ | | +| approx_kl | 0.014433331 | +| clip_fraction | 0.301 | +| clip_range | 0.0647 | +| entropy_loss | -6.19 | +| explained_variance | 0.33 | +| learning_rate | 4.02e-05 | +| loss | -0.0264 | +| n_updates | 96632 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000252 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1384 | +| iterations | 20205 | +| time_elapsed | 29881 | +| total_timesteps | 41379840 | +| train/ | | +| approx_kl | 0.013923805 | +| clip_fraction | 0.359 | +| clip_range | 0.0647 | +| entropy_loss | -5.99 | +| explained_variance | -0.224 | +| learning_rate | 4.02e-05 | +| loss | -0.0296 | +| n_updates | 96636 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000196 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1384 | +| iterations | 20206 | +| time_elapsed | 29882 | +| total_timesteps | 41381888 | +| train/ | | +| approx_kl | 0.013629656 | +| clip_fraction | 0.346 | +| clip_range | 0.0647 | +| entropy_loss | -6.21 | +| explained_variance | -0.389 | +| learning_rate | 4.02e-05 | +| loss | -0.0349 | +| n_updates | 96640 | +| policy_gradient_loss | -0.0206 | +| value_loss | 7.62e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1384 | +| iterations | 20207 | +| time_elapsed | 29884 | +| total_timesteps | 41383936 | +| train/ | | +| approx_kl | 0.012247029 | +| clip_fraction | 0.282 | +| clip_range | 0.0647 | +| entropy_loss | -5.78 | +| explained_variance | 0.535 | +| learning_rate | 4.02e-05 | +| loss | -0.0205 | +| n_updates | 96644 | +| policy_gradient_loss | -0.0141 | +| value_loss | 0.000201 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1384 | +| iterations | 20208 | +| time_elapsed | 29885 | +| total_timesteps | 41385984 | +| train/ | | +| approx_kl | 0.015156463 | +| clip_fraction | 0.354 | +| clip_range | 0.0647 | +| entropy_loss | -5.62 | +| explained_variance | 0.416 | +| learning_rate | 4.02e-05 | +| loss | -0.0301 | +| n_updates | 96648 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000119 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1384 | +| iterations | 20209 | +| time_elapsed | 29887 | +| total_timesteps | 41388032 | +| train/ | | +| approx_kl | 0.014504427 | +| clip_fraction | 0.331 | +| clip_range | 0.0647 | +| entropy_loss | -5.66 | +| explained_variance | 0.455 | +| learning_rate | 4.02e-05 | +| loss | -0.0271 | +| n_updates | 96652 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000155 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1384 | +| iterations | 20210 | +| time_elapsed | 29888 | +| total_timesteps | 41390080 | +| train/ | | +| approx_kl | 0.011886518 | +| clip_fraction | 0.318 | +| clip_range | 0.0647 | +| entropy_loss | -6.21 | +| explained_variance | 0.446 | +| learning_rate | 4.02e-05 | +| loss | -0.0276 | +| n_updates | 96656 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000101 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1384 | +| iterations | 20211 | +| time_elapsed | 29890 | +| total_timesteps | 41392128 | +| train/ | | +| approx_kl | 0.008310754 | +| clip_fraction | 0.309 | +| clip_range | 0.0647 | +| entropy_loss | -6.49 | +| explained_variance | 0.233 | +| learning_rate | 4.02e-05 | +| loss | -0.0273 | +| n_updates | 96660 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000251 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1384 | +| iterations | 20212 | +| time_elapsed | 29891 | +| total_timesteps | 41394176 | +| train/ | | +| approx_kl | 0.009844648 | +| clip_fraction | 0.311 | +| clip_range | 0.0647 | +| entropy_loss | -6.01 | +| explained_variance | 0.483 | +| learning_rate | 4.02e-05 | +| loss | -0.0278 | +| n_updates | 96664 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000175 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1384 | +| iterations | 20213 | +| time_elapsed | 29893 | +| total_timesteps | 41396224 | +| train/ | | +| approx_kl | 0.012086071 | +| clip_fraction | 0.275 | +| clip_range | 0.0647 | +| entropy_loss | -5.31 | +| explained_variance | 0.444 | +| learning_rate | 4.02e-05 | +| loss | -0.0298 | +| n_updates | 96668 | +| policy_gradient_loss | -0.0126 | +| value_loss | 0.000335 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1384 | +| iterations | 20214 | +| time_elapsed | 29894 | +| total_timesteps | 41398272 | +| train/ | | +| approx_kl | 0.014308799 | +| clip_fraction | 0.35 | +| clip_range | 0.0647 | +| entropy_loss | -5.46 | +| explained_variance | 0.319 | +| learning_rate | 4.02e-05 | +| loss | -0.0262 | +| n_updates | 96672 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000117 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1384 | +| iterations | 20215 | +| time_elapsed | 29896 | +| total_timesteps | 41400320 | +| train/ | | +| approx_kl | 0.0069103623 | +| clip_fraction | 0.302 | +| clip_range | 0.0647 | +| entropy_loss | -6.36 | +| explained_variance | 0.44 | +| learning_rate | 4.02e-05 | +| loss | -0.0207 | +| n_updates | 96676 | +| policy_gradient_loss | -0.0146 | +| value_loss | 0.000221 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1384 | +| iterations | 20216 | +| time_elapsed | 29897 | +| total_timesteps | 41402368 | +| train/ | | +| approx_kl | 0.010669397 | +| clip_fraction | 0.295 | +| clip_range | 0.0646 | +| entropy_loss | -6.03 | +| explained_variance | 0.233 | +| learning_rate | 4.02e-05 | +| loss | -0.0266 | +| n_updates | 96680 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000142 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1384 | +| iterations | 20217 | +| time_elapsed | 29899 | +| total_timesteps | 41404416 | +| train/ | | +| approx_kl | 0.012358844 | +| clip_fraction | 0.314 | +| clip_range | 0.0646 | +| entropy_loss | -5.79 | +| explained_variance | 0.453 | +| learning_rate | 4.02e-05 | +| loss | -0.0229 | +| n_updates | 96684 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000178 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1384 | +| iterations | 20218 | +| time_elapsed | 29900 | +| total_timesteps | 41406464 | +| train/ | | +| approx_kl | 0.012275113 | +| clip_fraction | 0.327 | +| clip_range | 0.0646 | +| entropy_loss | -6.32 | +| explained_variance | 0.107 | +| learning_rate | 4.02e-05 | +| loss | -0.0291 | +| n_updates | 96688 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000137 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1384 | +| iterations | 20219 | +| time_elapsed | 29902 | +| total_timesteps | 41408512 | +| train/ | | +| approx_kl | 0.010804642 | +| clip_fraction | 0.325 | +| clip_range | 0.0646 | +| entropy_loss | -5.81 | +| explained_variance | 0.701 | +| learning_rate | 4.02e-05 | +| loss | -0.0261 | +| n_updates | 96692 | +| policy_gradient_loss | -0.017 | +| value_loss | 9.18e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1384 | +| iterations | 20220 | +| time_elapsed | 29904 | +| total_timesteps | 41410560 | +| train/ | | +| approx_kl | 0.013412046 | +| clip_fraction | 0.304 | +| clip_range | 0.0646 | +| entropy_loss | -5.85 | +| explained_variance | 0.268 | +| learning_rate | 4.02e-05 | +| loss | -0.0202 | +| n_updates | 96696 | +| policy_gradient_loss | -0.0141 | +| value_loss | 0.00036 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1384 | +| iterations | 20221 | +| time_elapsed | 29905 | +| total_timesteps | 41412608 | +| train/ | | +| approx_kl | 0.011374318 | +| clip_fraction | 0.311 | +| clip_range | 0.0646 | +| entropy_loss | -5.71 | +| explained_variance | 0.438 | +| learning_rate | 4.02e-05 | +| loss | -0.025 | +| n_updates | 96700 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000193 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1384 | +| iterations | 20222 | +| time_elapsed | 29907 | +| total_timesteps | 41414656 | +| train/ | | +| approx_kl | 0.009657189 | +| clip_fraction | 0.306 | +| clip_range | 0.0646 | +| entropy_loss | -5.29 | +| explained_variance | 0.317 | +| learning_rate | 4.02e-05 | +| loss | -0.0201 | +| n_updates | 96704 | +| policy_gradient_loss | -0.0141 | +| value_loss | 0.000321 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1384 | +| iterations | 20223 | +| time_elapsed | 29908 | +| total_timesteps | 41416704 | +| train/ | | +| approx_kl | 0.013007076 | +| clip_fraction | 0.335 | +| clip_range | 0.0646 | +| entropy_loss | -5.91 | +| explained_variance | 0.428 | +| learning_rate | 4.02e-05 | +| loss | -0.0348 | +| n_updates | 96708 | +| policy_gradient_loss | -0.0203 | +| value_loss | 8.12e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1384 | +| iterations | 20224 | +| time_elapsed | 29910 | +| total_timesteps | 41418752 | +| train/ | | +| approx_kl | 0.013814079 | +| clip_fraction | 0.314 | +| clip_range | 0.0646 | +| entropy_loss | -6.15 | +| explained_variance | 0.345 | +| learning_rate | 4.02e-05 | +| loss | -0.0283 | +| n_updates | 96712 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000119 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1384 | +| iterations | 20225 | +| time_elapsed | 29911 | +| total_timesteps | 41420800 | +| train/ | | +| approx_kl | 0.009998084 | +| clip_fraction | 0.3 | +| clip_range | 0.0646 | +| entropy_loss | -6.23 | +| explained_variance | 0.502 | +| learning_rate | 4.02e-05 | +| loss | -0.0223 | +| n_updates | 96716 | +| policy_gradient_loss | -0.014 | +| value_loss | 0.000184 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1384 | +| iterations | 20226 | +| time_elapsed | 29913 | +| total_timesteps | 41422848 | +| train/ | | +| approx_kl | 0.010407085 | +| clip_fraction | 0.282 | +| clip_range | 0.0646 | +| entropy_loss | -6.11 | +| explained_variance | 0.362 | +| learning_rate | 4.02e-05 | +| loss | -0.0251 | +| n_updates | 96720 | +| policy_gradient_loss | -0.0142 | +| value_loss | 0.000133 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1384 | +| iterations | 20227 | +| time_elapsed | 29914 | +| total_timesteps | 41424896 | +| train/ | | +| approx_kl | 0.014362216 | +| clip_fraction | 0.307 | +| clip_range | 0.0646 | +| entropy_loss | -5.87 | +| explained_variance | 0.283 | +| learning_rate | 4.02e-05 | +| loss | -0.0267 | +| n_updates | 96724 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000248 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1384 | +| iterations | 20228 | +| time_elapsed | 29916 | +| total_timesteps | 41426944 | +| train/ | | +| approx_kl | 0.010876158 | +| clip_fraction | 0.317 | +| clip_range | 0.0646 | +| entropy_loss | -5.67 | +| explained_variance | 0.528 | +| learning_rate | 4.02e-05 | +| loss | -0.0299 | +| n_updates | 96728 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000135 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1384 | +| iterations | 20229 | +| time_elapsed | 29917 | +| total_timesteps | 41428992 | +| train/ | | +| approx_kl | 0.014065703 | +| clip_fraction | 0.345 | +| clip_range | 0.0646 | +| entropy_loss | -5.79 | +| explained_variance | 0.494 | +| learning_rate | 4.02e-05 | +| loss | -0.0268 | +| n_updates | 96732 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000133 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1384 | +| iterations | 20230 | +| time_elapsed | 29919 | +| total_timesteps | 41431040 | +| train/ | | +| approx_kl | 0.009756856 | +| clip_fraction | 0.285 | +| clip_range | 0.0646 | +| entropy_loss | -6.16 | +| explained_variance | 0.323 | +| learning_rate | 4.02e-05 | +| loss | -0.0257 | +| n_updates | 96736 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000137 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1384 | +| iterations | 20231 | +| time_elapsed | 29920 | +| total_timesteps | 41433088 | +| train/ | | +| approx_kl | 0.0153696 | +| clip_fraction | 0.342 | +| clip_range | 0.0646 | +| entropy_loss | -5.94 | +| explained_variance | -0.172 | +| learning_rate | 4.02e-05 | +| loss | -0.0278 | +| n_updates | 96740 | +| policy_gradient_loss | -0.0196 | +| value_loss | 5.14e-05 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1384 | +| iterations | 20232 | +| time_elapsed | 29922 | +| total_timesteps | 41435136 | +| train/ | | +| approx_kl | 0.014506321 | +| clip_fraction | 0.325 | +| clip_range | 0.0646 | +| entropy_loss | -5.74 | +| explained_variance | 0.575 | +| learning_rate | 4.02e-05 | +| loss | -0.0214 | +| n_updates | 96744 | +| policy_gradient_loss | -0.0163 | +| value_loss | 9.73e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1384 | +| iterations | 20233 | +| time_elapsed | 29924 | +| total_timesteps | 41437184 | +| train/ | | +| approx_kl | 0.014213119 | +| clip_fraction | 0.332 | +| clip_range | 0.0646 | +| entropy_loss | -5.26 | +| explained_variance | 0.739 | +| learning_rate | 4.02e-05 | +| loss | -0.0278 | +| n_updates | 96748 | +| policy_gradient_loss | -0.0173 | +| value_loss | 9.06e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1384 | +| iterations | 20234 | +| time_elapsed | 29925 | +| total_timesteps | 41439232 | +| train/ | | +| approx_kl | 0.016567683 | +| clip_fraction | 0.319 | +| clip_range | 0.0646 | +| entropy_loss | -5.6 | +| explained_variance | 0.481 | +| learning_rate | 4.02e-05 | +| loss | -0.0274 | +| n_updates | 96752 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000175 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1384 | +| iterations | 20235 | +| time_elapsed | 29927 | +| total_timesteps | 41441280 | +| train/ | | +| approx_kl | 0.013625916 | +| clip_fraction | 0.316 | +| clip_range | 0.0646 | +| entropy_loss | -5.88 | +| explained_variance | -0.0997 | +| learning_rate | 4.02e-05 | +| loss | -0.0252 | +| n_updates | 96756 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000106 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1384 | +| iterations | 20236 | +| time_elapsed | 29928 | +| total_timesteps | 41443328 | +| train/ | | +| approx_kl | 0.013264891 | +| clip_fraction | 0.324 | +| clip_range | 0.0646 | +| entropy_loss | -5.82 | +| explained_variance | 0.507 | +| learning_rate | 4.02e-05 | +| loss | -0.0311 | +| n_updates | 96760 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000143 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1384 | +| iterations | 20237 | +| time_elapsed | 29930 | +| total_timesteps | 41445376 | +| train/ | | +| approx_kl | 0.01253055 | +| clip_fraction | 0.277 | +| clip_range | 0.0646 | +| entropy_loss | -5.81 | +| explained_variance | 0.312 | +| learning_rate | 4.02e-05 | +| loss | -0.025 | +| n_updates | 96764 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000203 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1384 | +| iterations | 20238 | +| time_elapsed | 29931 | +| total_timesteps | 41447424 | +| train/ | | +| approx_kl | 0.011647937 | +| clip_fraction | 0.338 | +| clip_range | 0.0646 | +| entropy_loss | -6.11 | +| explained_variance | -0.0472 | +| learning_rate | 4.02e-05 | +| loss | -0.0277 | +| n_updates | 96768 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000226 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1384 | +| iterations | 20239 | +| time_elapsed | 29933 | +| total_timesteps | 41449472 | +| train/ | | +| approx_kl | 0.011034504 | +| clip_fraction | 0.319 | +| clip_range | 0.0646 | +| entropy_loss | -5.58 | +| explained_variance | 0.242 | +| learning_rate | 4.02e-05 | +| loss | -0.0235 | +| n_updates | 96772 | +| policy_gradient_loss | -0.0148 | +| value_loss | 0.000248 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1384 | +| iterations | 20240 | +| time_elapsed | 29934 | +| total_timesteps | 41451520 | +| train/ | | +| approx_kl | 0.013658492 | +| clip_fraction | 0.304 | +| clip_range | 0.0646 | +| entropy_loss | -5.13 | +| explained_variance | 0.629 | +| learning_rate | 4.02e-05 | +| loss | -0.0225 | +| n_updates | 96776 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.000174 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1384 | +| iterations | 20241 | +| time_elapsed | 29936 | +| total_timesteps | 41453568 | +| train/ | | +| approx_kl | 0.011098381 | +| clip_fraction | 0.331 | +| clip_range | 0.0646 | +| entropy_loss | -6.12 | +| explained_variance | -0.214 | +| learning_rate | 4.02e-05 | +| loss | -0.0306 | +| n_updates | 96780 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000179 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1384 | +| iterations | 20242 | +| time_elapsed | 29937 | +| total_timesteps | 41455616 | +| train/ | | +| approx_kl | 0.012281988 | +| clip_fraction | 0.333 | +| clip_range | 0.0646 | +| entropy_loss | -6.08 | +| explained_variance | 0.382 | +| learning_rate | 4.02e-05 | +| loss | -0.0217 | +| n_updates | 96784 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000257 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1384 | +| iterations | 20243 | +| time_elapsed | 29939 | +| total_timesteps | 41457664 | +| train/ | | +| approx_kl | 0.011353747 | +| clip_fraction | 0.301 | +| clip_range | 0.0646 | +| entropy_loss | -6.36 | +| explained_variance | 0.116 | +| learning_rate | 4.02e-05 | +| loss | -0.0295 | +| n_updates | 96788 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000182 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1384 | +| iterations | 20244 | +| time_elapsed | 29940 | +| total_timesteps | 41459712 | +| train/ | | +| approx_kl | 0.013681302 | +| clip_fraction | 0.361 | +| clip_range | 0.0646 | +| entropy_loss | -6.23 | +| explained_variance | 0.438 | +| learning_rate | 4.02e-05 | +| loss | -0.0342 | +| n_updates | 96792 | +| policy_gradient_loss | -0.0193 | +| value_loss | 8.24e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1384 | +| iterations | 20245 | +| time_elapsed | 29942 | +| total_timesteps | 41461760 | +| train/ | | +| approx_kl | 0.010894453 | +| clip_fraction | 0.303 | +| clip_range | 0.0646 | +| entropy_loss | -5.48 | +| explained_variance | 0.365 | +| learning_rate | 4.02e-05 | +| loss | -0.0259 | +| n_updates | 96796 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000198 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1384 | +| iterations | 20246 | +| time_elapsed | 29944 | +| total_timesteps | 41463808 | +| train/ | | +| approx_kl | 0.010256441 | +| clip_fraction | 0.277 | +| clip_range | 0.0646 | +| entropy_loss | -6.05 | +| explained_variance | 0.31 | +| learning_rate | 4.02e-05 | +| loss | -0.0189 | +| n_updates | 96800 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.000217 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1384 | +| iterations | 20247 | +| time_elapsed | 29945 | +| total_timesteps | 41465856 | +| train/ | | +| approx_kl | 0.013221048 | +| clip_fraction | 0.359 | +| clip_range | 0.0646 | +| entropy_loss | -5.74 | +| explained_variance | 0.344 | +| learning_rate | 4.02e-05 | +| loss | -0.0305 | +| n_updates | 96804 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000144 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1384 | +| iterations | 20248 | +| time_elapsed | 29947 | +| total_timesteps | 41467904 | +| train/ | | +| approx_kl | 0.012270557 | +| clip_fraction | 0.302 | +| clip_range | 0.0646 | +| entropy_loss | -5.42 | +| explained_variance | 0.554 | +| learning_rate | 4.02e-05 | +| loss | -0.0235 | +| n_updates | 96808 | +| policy_gradient_loss | -0.0147 | +| value_loss | 0.000206 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1384 | +| iterations | 20249 | +| time_elapsed | 29948 | +| total_timesteps | 41469952 | +| train/ | | +| approx_kl | 0.012485885 | +| clip_fraction | 0.349 | +| clip_range | 0.0646 | +| entropy_loss | -5.66 | +| explained_variance | 0.426 | +| learning_rate | 4.02e-05 | +| loss | -0.0276 | +| n_updates | 96812 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000216 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1384 | +| iterations | 20250 | +| time_elapsed | 29950 | +| total_timesteps | 41472000 | +| train/ | | +| approx_kl | 0.013167559 | +| clip_fraction | 0.312 | +| clip_range | 0.0646 | +| entropy_loss | -5.91 | +| explained_variance | 0.482 | +| learning_rate | 4.02e-05 | +| loss | -0.0294 | +| n_updates | 96816 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000154 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1384 | +| iterations | 20251 | +| time_elapsed | 29951 | +| total_timesteps | 41474048 | +| train/ | | +| approx_kl | 0.011344955 | +| clip_fraction | 0.313 | +| clip_range | 0.0646 | +| entropy_loss | -6.27 | +| explained_variance | 0.355 | +| learning_rate | 4.02e-05 | +| loss | -0.0303 | +| n_updates | 96820 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000144 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1384 | +| iterations | 20252 | +| time_elapsed | 29953 | +| total_timesteps | 41476096 | +| train/ | | +| approx_kl | 0.013046644 | +| clip_fraction | 0.325 | +| clip_range | 0.0646 | +| entropy_loss | -5.91 | +| explained_variance | 0.399 | +| learning_rate | 4.01e-05 | +| loss | -0.0263 | +| n_updates | 96824 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000109 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1384 | +| iterations | 20253 | +| time_elapsed | 29954 | +| total_timesteps | 41478144 | +| train/ | | +| approx_kl | 0.009393821 | +| clip_fraction | 0.31 | +| clip_range | 0.0646 | +| entropy_loss | -6.53 | +| explained_variance | -0.13 | +| learning_rate | 4.01e-05 | +| loss | -0.0253 | +| n_updates | 96828 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000158 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1384 | +| iterations | 20254 | +| time_elapsed | 29956 | +| total_timesteps | 41480192 | +| train/ | | +| approx_kl | 0.008325102 | +| clip_fraction | 0.285 | +| clip_range | 0.0646 | +| entropy_loss | -6.29 | +| explained_variance | 0.274 | +| learning_rate | 4.01e-05 | +| loss | -0.0206 | +| n_updates | 96832 | +| policy_gradient_loss | -0.0128 | +| value_loss | 0.000329 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1384 | +| iterations | 20255 | +| time_elapsed | 29957 | +| total_timesteps | 41482240 | +| train/ | | +| approx_kl | 0.010083456 | +| clip_fraction | 0.313 | +| clip_range | 0.0646 | +| entropy_loss | -5.01 | +| explained_variance | 0.683 | +| learning_rate | 4.01e-05 | +| loss | -0.0264 | +| n_updates | 96836 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.0002 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1384 | +| iterations | 20256 | +| time_elapsed | 29959 | +| total_timesteps | 41484288 | +| train/ | | +| approx_kl | 0.013964375 | +| clip_fraction | 0.327 | +| clip_range | 0.0646 | +| entropy_loss | -5.66 | +| explained_variance | -0.427 | +| learning_rate | 4.01e-05 | +| loss | -0.0341 | +| n_updates | 96840 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000145 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1384 | +| iterations | 20257 | +| time_elapsed | 29961 | +| total_timesteps | 41486336 | +| train/ | | +| approx_kl | 0.0094462 | +| clip_fraction | 0.328 | +| clip_range | 0.0646 | +| entropy_loss | -6.41 | +| explained_variance | 0.377 | +| learning_rate | 4.01e-05 | +| loss | -0.024 | +| n_updates | 96844 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.00016 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1384 | +| iterations | 20258 | +| time_elapsed | 29962 | +| total_timesteps | 41488384 | +| train/ | | +| approx_kl | 0.009668994 | +| clip_fraction | 0.316 | +| clip_range | 0.0646 | +| entropy_loss | -6.36 | +| explained_variance | 0.638 | +| learning_rate | 4.01e-05 | +| loss | -0.0211 | +| n_updates | 96848 | +| policy_gradient_loss | -0.0173 | +| value_loss | 9.9e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1384 | +| iterations | 20259 | +| time_elapsed | 29964 | +| total_timesteps | 41490432 | +| train/ | | +| approx_kl | 0.014869364 | +| clip_fraction | 0.331 | +| clip_range | 0.0646 | +| entropy_loss | -5.48 | +| explained_variance | 0.37 | +| learning_rate | 4.01e-05 | +| loss | -0.0254 | +| n_updates | 96852 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000223 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1384 | +| iterations | 20260 | +| time_elapsed | 29965 | +| total_timesteps | 41492480 | +| train/ | | +| approx_kl | 0.012575521 | +| clip_fraction | 0.327 | +| clip_range | 0.0646 | +| entropy_loss | -5.67 | +| explained_variance | 0.0161 | +| learning_rate | 4.01e-05 | +| loss | -0.0282 | +| n_updates | 96856 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000151 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1384 | +| iterations | 20261 | +| time_elapsed | 29967 | +| total_timesteps | 41494528 | +| train/ | | +| approx_kl | 0.018596482 | +| clip_fraction | 0.343 | +| clip_range | 0.0646 | +| entropy_loss | -6.04 | +| explained_variance | -0.174 | +| learning_rate | 4.01e-05 | +| loss | -0.0261 | +| n_updates | 96860 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000147 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1384 | +| iterations | 20262 | +| time_elapsed | 29968 | +| total_timesteps | 41496576 | +| train/ | | +| approx_kl | 0.0137337 | +| clip_fraction | 0.353 | +| clip_range | 0.0646 | +| entropy_loss | -5.97 | +| explained_variance | -0.204 | +| learning_rate | 4.01e-05 | +| loss | -0.0337 | +| n_updates | 96864 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000117 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1384 | +| iterations | 20263 | +| time_elapsed | 29970 | +| total_timesteps | 41498624 | +| train/ | | +| approx_kl | 0.012789671 | +| clip_fraction | 0.315 | +| clip_range | 0.0646 | +| entropy_loss | -6.03 | +| explained_variance | 0.257 | +| learning_rate | 4.01e-05 | +| loss | -0.0234 | +| n_updates | 96868 | +| policy_gradient_loss | -0.0145 | +| value_loss | 0.000229 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1384 | +| iterations | 20264 | +| time_elapsed | 29971 | +| total_timesteps | 41500672 | +| train/ | | +| approx_kl | 0.011868128 | +| clip_fraction | 0.31 | +| clip_range | 0.0646 | +| entropy_loss | -5.55 | +| explained_variance | 0.646 | +| learning_rate | 4.01e-05 | +| loss | -0.0246 | +| n_updates | 96872 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000101 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1384 | +| iterations | 20265 | +| time_elapsed | 29973 | +| total_timesteps | 41502720 | +| train/ | | +| approx_kl | 0.012682996 | +| clip_fraction | 0.319 | +| clip_range | 0.0646 | +| entropy_loss | -5.2 | +| explained_variance | 0.734 | +| learning_rate | 4.01e-05 | +| loss | -0.0288 | +| n_updates | 96876 | +| policy_gradient_loss | -0.0168 | +| value_loss | 9e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1384 | +| iterations | 20266 | +| time_elapsed | 29975 | +| total_timesteps | 41504768 | +| train/ | | +| approx_kl | 0.013597025 | +| clip_fraction | 0.313 | +| clip_range | 0.0646 | +| entropy_loss | -5.16 | +| explained_variance | 0.601 | +| learning_rate | 4.01e-05 | +| loss | -0.0248 | +| n_updates | 96880 | +| policy_gradient_loss | -0.0148 | +| value_loss | 0.000146 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1384 | +| iterations | 20267 | +| time_elapsed | 29976 | +| total_timesteps | 41506816 | +| train/ | | +| approx_kl | 0.013462908 | +| clip_fraction | 0.32 | +| clip_range | 0.0646 | +| entropy_loss | -5.86 | +| explained_variance | -0.209 | +| learning_rate | 4.01e-05 | +| loss | -0.0268 | +| n_updates | 96884 | +| policy_gradient_loss | -0.0163 | +| value_loss | 7.11e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1384 | +| iterations | 20268 | +| time_elapsed | 29978 | +| total_timesteps | 41508864 | +| train/ | | +| approx_kl | 0.011597406 | +| clip_fraction | 0.314 | +| clip_range | 0.0646 | +| entropy_loss | -6.35 | +| explained_variance | -0.0669 | +| learning_rate | 4.01e-05 | +| loss | -0.0308 | +| n_updates | 96888 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000122 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1384 | +| iterations | 20269 | +| time_elapsed | 29979 | +| total_timesteps | 41510912 | +| train/ | | +| approx_kl | 0.009106716 | +| clip_fraction | 0.32 | +| clip_range | 0.0646 | +| entropy_loss | -6.16 | +| explained_variance | -0.016 | +| learning_rate | 4.01e-05 | +| loss | -0.0246 | +| n_updates | 96892 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.00019 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1384 | +| iterations | 20270 | +| time_elapsed | 29981 | +| total_timesteps | 41512960 | +| train/ | | +| approx_kl | 0.009046189 | +| clip_fraction | 0.315 | +| clip_range | 0.0646 | +| entropy_loss | -6.01 | +| explained_variance | 0.213 | +| learning_rate | 4.01e-05 | +| loss | -0.0235 | +| n_updates | 96896 | +| policy_gradient_loss | -0.0142 | +| value_loss | 0.000321 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1384 | +| iterations | 20271 | +| time_elapsed | 29982 | +| total_timesteps | 41515008 | +| train/ | | +| approx_kl | 0.012584352 | +| clip_fraction | 0.314 | +| clip_range | 0.0646 | +| entropy_loss | -5.13 | +| explained_variance | 0.55 | +| learning_rate | 4.01e-05 | +| loss | -0.0236 | +| n_updates | 96900 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000119 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1384 | +| iterations | 20272 | +| time_elapsed | 29984 | +| total_timesteps | 41517056 | +| train/ | | +| approx_kl | 0.011519916 | +| clip_fraction | 0.326 | +| clip_range | 0.0646 | +| entropy_loss | -5.05 | +| explained_variance | 0.428 | +| learning_rate | 4.01e-05 | +| loss | -0.0297 | +| n_updates | 96904 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.00016 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1384 | +| iterations | 20273 | +| time_elapsed | 29985 | +| total_timesteps | 41519104 | +| train/ | | +| approx_kl | 0.010752078 | +| clip_fraction | 0.315 | +| clip_range | 0.0646 | +| entropy_loss | -5.64 | +| explained_variance | 0.383 | +| learning_rate | 4.01e-05 | +| loss | -0.0269 | +| n_updates | 96908 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000234 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1384 | +| iterations | 20274 | +| time_elapsed | 29987 | +| total_timesteps | 41521152 | +| train/ | | +| approx_kl | 0.010716226 | +| clip_fraction | 0.323 | +| clip_range | 0.0646 | +| entropy_loss | -5.55 | +| explained_variance | 0.224 | +| learning_rate | 4.01e-05 | +| loss | -0.0259 | +| n_updates | 96912 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000237 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1384 | +| iterations | 20275 | +| time_elapsed | 29988 | +| total_timesteps | 41523200 | +| train/ | | +| approx_kl | 0.014045561 | +| clip_fraction | 0.367 | +| clip_range | 0.0646 | +| entropy_loss | -5.7 | +| explained_variance | -0.279 | +| learning_rate | 4.01e-05 | +| loss | -0.0358 | +| n_updates | 96916 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000103 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1384 | +| iterations | 20276 | +| time_elapsed | 29990 | +| total_timesteps | 41525248 | +| train/ | | +| approx_kl | 0.011465593 | +| clip_fraction | 0.324 | +| clip_range | 0.0646 | +| entropy_loss | -5.88 | +| explained_variance | 0.496 | +| learning_rate | 4.01e-05 | +| loss | -0.0259 | +| n_updates | 96920 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000132 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1384 | +| iterations | 20277 | +| time_elapsed | 29991 | +| total_timesteps | 41527296 | +| train/ | | +| approx_kl | 0.011270398 | +| clip_fraction | 0.315 | +| clip_range | 0.0646 | +| entropy_loss | -5.32 | +| explained_variance | 0.508 | +| learning_rate | 4.01e-05 | +| loss | -0.0236 | +| n_updates | 96924 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000164 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1384 | +| iterations | 20278 | +| time_elapsed | 29993 | +| total_timesteps | 41529344 | +| train/ | | +| approx_kl | 0.013877104 | +| clip_fraction | 0.355 | +| clip_range | 0.0646 | +| entropy_loss | -5.77 | +| explained_variance | -0.167 | +| learning_rate | 4.01e-05 | +| loss | -0.0287 | +| n_updates | 96928 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000196 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1384 | +| iterations | 20279 | +| time_elapsed | 29995 | +| total_timesteps | 41531392 | +| train/ | | +| approx_kl | 0.013308608 | +| clip_fraction | 0.35 | +| clip_range | 0.0646 | +| entropy_loss | -5.53 | +| explained_variance | 0.639 | +| learning_rate | 4.01e-05 | +| loss | -0.0307 | +| n_updates | 96932 | +| policy_gradient_loss | -0.0197 | +| value_loss | 8.01e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1384 | +| iterations | 20280 | +| time_elapsed | 29996 | +| total_timesteps | 41533440 | +| train/ | | +| approx_kl | 0.012139923 | +| clip_fraction | 0.302 | +| clip_range | 0.0646 | +| entropy_loss | -5.36 | +| explained_variance | 0.463 | +| learning_rate | 4.01e-05 | +| loss | -0.0262 | +| n_updates | 96936 | +| policy_gradient_loss | -0.0148 | +| value_loss | 0.000269 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1384 | +| iterations | 20281 | +| time_elapsed | 29998 | +| total_timesteps | 41535488 | +| train/ | | +| approx_kl | 0.012078868 | +| clip_fraction | 0.359 | +| clip_range | 0.0646 | +| entropy_loss | -5.52 | +| explained_variance | 0.0246 | +| learning_rate | 4.01e-05 | +| loss | -0.0253 | +| n_updates | 96940 | +| policy_gradient_loss | -0.0191 | +| value_loss | 6.64e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1384 | +| iterations | 20282 | +| time_elapsed | 29999 | +| total_timesteps | 41537536 | +| train/ | | +| approx_kl | 0.0131281875 | +| clip_fraction | 0.309 | +| clip_range | 0.0646 | +| entropy_loss | -5.06 | +| explained_variance | 0.368 | +| learning_rate | 4.01e-05 | +| loss | -0.0221 | +| n_updates | 96944 | +| policy_gradient_loss | -0.0139 | +| value_loss | 0.00025 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1384 | +| iterations | 20283 | +| time_elapsed | 30001 | +| total_timesteps | 41539584 | +| train/ | | +| approx_kl | 0.011324021 | +| clip_fraction | 0.331 | +| clip_range | 0.0646 | +| entropy_loss | -5.46 | +| explained_variance | 0.575 | +| learning_rate | 4.01e-05 | +| loss | -0.0254 | +| n_updates | 96948 | +| policy_gradient_loss | -0.0184 | +| value_loss | 8.74e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1384 | +| iterations | 20284 | +| time_elapsed | 30002 | +| total_timesteps | 41541632 | +| train/ | | +| approx_kl | 0.011998579 | +| clip_fraction | 0.338 | +| clip_range | 0.0646 | +| entropy_loss | -6.06 | +| explained_variance | -0.0229 | +| learning_rate | 4.01e-05 | +| loss | -0.0311 | +| n_updates | 96952 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000187 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1384 | +| iterations | 20285 | +| time_elapsed | 30004 | +| total_timesteps | 41543680 | +| train/ | | +| approx_kl | 0.00952963 | +| clip_fraction | 0.31 | +| clip_range | 0.0646 | +| entropy_loss | -6.35 | +| explained_variance | 0.322 | +| learning_rate | 4.01e-05 | +| loss | -0.0216 | +| n_updates | 96956 | +| policy_gradient_loss | -0.0123 | +| value_loss | 0.000332 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1384 | +| iterations | 20286 | +| time_elapsed | 30005 | +| total_timesteps | 41545728 | +| train/ | | +| approx_kl | 0.008725967 | +| clip_fraction | 0.333 | +| clip_range | 0.0646 | +| entropy_loss | -6.43 | +| explained_variance | 0.367 | +| learning_rate | 4.01e-05 | +| loss | -0.0344 | +| n_updates | 96960 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000146 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1384 | +| iterations | 20287 | +| time_elapsed | 30007 | +| total_timesteps | 41547776 | +| train/ | | +| approx_kl | 0.010834755 | +| clip_fraction | 0.314 | +| clip_range | 0.0646 | +| entropy_loss | -6.41 | +| explained_variance | 0.0917 | +| learning_rate | 4.01e-05 | +| loss | -0.0313 | +| n_updates | 96964 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000143 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1384 | +| iterations | 20288 | +| time_elapsed | 30008 | +| total_timesteps | 41549824 | +| train/ | | +| approx_kl | 0.01013058 | +| clip_fraction | 0.32 | +| clip_range | 0.0646 | +| entropy_loss | -6.02 | +| explained_variance | 0.388 | +| learning_rate | 4.01e-05 | +| loss | -0.0182 | +| n_updates | 96968 | +| policy_gradient_loss | -0.0148 | +| value_loss | 0.000288 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1384 | +| iterations | 20289 | +| time_elapsed | 30010 | +| total_timesteps | 41551872 | +| train/ | | +| approx_kl | 0.014318787 | +| clip_fraction | 0.33 | +| clip_range | 0.0646 | +| entropy_loss | -5.08 | +| explained_variance | 0.641 | +| learning_rate | 4.01e-05 | +| loss | -0.0279 | +| n_updates | 96972 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1384 | +| iterations | 20290 | +| time_elapsed | 30011 | +| total_timesteps | 41553920 | +| train/ | | +| approx_kl | 0.014577841 | +| clip_fraction | 0.375 | +| clip_range | 0.0646 | +| entropy_loss | -5.78 | +| explained_variance | 0.37 | +| learning_rate | 4.01e-05 | +| loss | -0.0356 | +| n_updates | 96976 | +| policy_gradient_loss | -0.0206 | +| value_loss | 7.13e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1384 | +| iterations | 20291 | +| time_elapsed | 30013 | +| total_timesteps | 41555968 | +| train/ | | +| approx_kl | 0.013233609 | +| clip_fraction | 0.339 | +| clip_range | 0.0646 | +| entropy_loss | -6.11 | +| explained_variance | -0.041 | +| learning_rate | 4.01e-05 | +| loss | -0.0276 | +| n_updates | 96980 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000125 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1384 | +| iterations | 20292 | +| time_elapsed | 30014 | +| total_timesteps | 41558016 | +| train/ | | +| approx_kl | 0.011342277 | +| clip_fraction | 0.291 | +| clip_range | 0.0646 | +| entropy_loss | -6.14 | +| explained_variance | 0.257 | +| learning_rate | 4.01e-05 | +| loss | -0.0229 | +| n_updates | 96984 | +| policy_gradient_loss | -0.0145 | +| value_loss | 0.00019 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1384 | +| iterations | 20293 | +| time_elapsed | 30016 | +| total_timesteps | 41560064 | +| train/ | | +| approx_kl | 0.010529684 | +| clip_fraction | 0.322 | +| clip_range | 0.0646 | +| entropy_loss | -6.28 | +| explained_variance | 0.345 | +| learning_rate | 4.01e-05 | +| loss | -0.0246 | +| n_updates | 96988 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.00015 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1384 | +| iterations | 20294 | +| time_elapsed | 30018 | +| total_timesteps | 41562112 | +| train/ | | +| approx_kl | 0.0104394015 | +| clip_fraction | 0.307 | +| clip_range | 0.0646 | +| entropy_loss | -5.9 | +| explained_variance | 0.485 | +| learning_rate | 4.01e-05 | +| loss | -0.0264 | +| n_updates | 96992 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.00013 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1384 | +| iterations | 20295 | +| time_elapsed | 30019 | +| total_timesteps | 41564160 | +| train/ | | +| approx_kl | 0.010703235 | +| clip_fraction | 0.302 | +| clip_range | 0.0646 | +| entropy_loss | -5.63 | +| explained_variance | 0.583 | +| learning_rate | 4.01e-05 | +| loss | -0.0276 | +| n_updates | 96996 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000136 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1384 | +| iterations | 20296 | +| time_elapsed | 30021 | +| total_timesteps | 41566208 | +| train/ | | +| approx_kl | 0.010685861 | +| clip_fraction | 0.293 | +| clip_range | 0.0646 | +| entropy_loss | -5.36 | +| explained_variance | 0.546 | +| learning_rate | 4.01e-05 | +| loss | -0.0187 | +| n_updates | 97000 | +| policy_gradient_loss | -0.0131 | +| value_loss | 0.000198 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1384 | +| iterations | 20297 | +| time_elapsed | 30022 | +| total_timesteps | 41568256 | +| train/ | | +| approx_kl | 0.014360331 | +| clip_fraction | 0.332 | +| clip_range | 0.0646 | +| entropy_loss | -5.31 | +| explained_variance | 0.302 | +| learning_rate | 4.01e-05 | +| loss | -0.029 | +| n_updates | 97004 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000121 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1384 | +| iterations | 20298 | +| time_elapsed | 30024 | +| total_timesteps | 41570304 | +| train/ | | +| approx_kl | 0.011763588 | +| clip_fraction | 0.332 | +| clip_range | 0.0646 | +| entropy_loss | -6.52 | +| explained_variance | -0.2 | +| learning_rate | 4.01e-05 | +| loss | -0.0314 | +| n_updates | 97008 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000129 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1384 | +| iterations | 20299 | +| time_elapsed | 30025 | +| total_timesteps | 41572352 | +| train/ | | +| approx_kl | 0.012864483 | +| clip_fraction | 0.324 | +| clip_range | 0.0646 | +| entropy_loss | -5.41 | +| explained_variance | 0.544 | +| learning_rate | 4.01e-05 | +| loss | -0.0291 | +| n_updates | 97012 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000115 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1384 | +| iterations | 20300 | +| time_elapsed | 30027 | +| total_timesteps | 41574400 | +| train/ | | +| approx_kl | 0.011377873 | +| clip_fraction | 0.289 | +| clip_range | 0.0646 | +| entropy_loss | -6.22 | +| explained_variance | 0.0435 | +| learning_rate | 4.01e-05 | +| loss | -0.0223 | +| n_updates | 97016 | +| policy_gradient_loss | -0.0141 | +| value_loss | 0.000225 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1384 | +| iterations | 20301 | +| time_elapsed | 30028 | +| total_timesteps | 41576448 | +| train/ | | +| approx_kl | 0.015610447 | +| clip_fraction | 0.309 | +| clip_range | 0.0646 | +| entropy_loss | -5.76 | +| explained_variance | 0.16 | +| learning_rate | 4.01e-05 | +| loss | -0.02 | +| n_updates | 97020 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000213 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1384 | +| iterations | 20302 | +| time_elapsed | 30030 | +| total_timesteps | 41578496 | +| train/ | | +| approx_kl | 0.013581814 | +| clip_fraction | 0.357 | +| clip_range | 0.0646 | +| entropy_loss | -5.39 | +| explained_variance | 0.494 | +| learning_rate | 4.01e-05 | +| loss | -0.0329 | +| n_updates | 97024 | +| policy_gradient_loss | -0.0183 | +| value_loss | 9.56e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1384 | +| iterations | 20303 | +| time_elapsed | 30031 | +| total_timesteps | 41580544 | +| train/ | | +| approx_kl | 0.015383475 | +| clip_fraction | 0.318 | +| clip_range | 0.0646 | +| entropy_loss | -5.58 | +| explained_variance | 0.626 | +| learning_rate | 4.01e-05 | +| loss | -0.0282 | +| n_updates | 97028 | +| policy_gradient_loss | -0.0181 | +| value_loss | 8.44e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1384 | +| iterations | 20304 | +| time_elapsed | 30033 | +| total_timesteps | 41582592 | +| train/ | | +| approx_kl | 0.015025223 | +| clip_fraction | 0.339 | +| clip_range | 0.0646 | +| entropy_loss | -5.63 | +| explained_variance | -0.0285 | +| learning_rate | 4.01e-05 | +| loss | -0.0282 | +| n_updates | 97032 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000114 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1384 | +| iterations | 20305 | +| time_elapsed | 30034 | +| total_timesteps | 41584640 | +| train/ | | +| approx_kl | 0.014631682 | +| clip_fraction | 0.324 | +| clip_range | 0.0646 | +| entropy_loss | -5.86 | +| explained_variance | 0.555 | +| learning_rate | 4.01e-05 | +| loss | -0.0259 | +| n_updates | 97036 | +| policy_gradient_loss | -0.0167 | +| value_loss | 9.23e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1384 | +| iterations | 20306 | +| time_elapsed | 30036 | +| total_timesteps | 41586688 | +| train/ | | +| approx_kl | 0.01171907 | +| clip_fraction | 0.313 | +| clip_range | 0.0646 | +| entropy_loss | -5.54 | +| explained_variance | 0.593 | +| learning_rate | 4.01e-05 | +| loss | -0.0238 | +| n_updates | 97040 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.000147 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1384 | +| iterations | 20307 | +| time_elapsed | 30037 | +| total_timesteps | 41588736 | +| train/ | | +| approx_kl | 0.01293228 | +| clip_fraction | 0.316 | +| clip_range | 0.0646 | +| entropy_loss | -5.36 | +| explained_variance | 0.221 | +| learning_rate | 4.01e-05 | +| loss | -0.0253 | +| n_updates | 97044 | +| policy_gradient_loss | -0.0145 | +| value_loss | 0.000189 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1384 | +| iterations | 20308 | +| time_elapsed | 30039 | +| total_timesteps | 41590784 | +| train/ | | +| approx_kl | 0.010609608 | +| clip_fraction | 0.325 | +| clip_range | 0.0646 | +| entropy_loss | -5.41 | +| explained_variance | 0.444 | +| learning_rate | 4.01e-05 | +| loss | -0.0279 | +| n_updates | 97048 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.00021 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1384 | +| iterations | 20309 | +| time_elapsed | 30040 | +| total_timesteps | 41592832 | +| train/ | | +| approx_kl | 0.01404917 | +| clip_fraction | 0.331 | +| clip_range | 0.0646 | +| entropy_loss | -6.05 | +| explained_variance | 0.0637 | +| learning_rate | 4.01e-05 | +| loss | -0.0275 | +| n_updates | 97052 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000124 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1384 | +| iterations | 20310 | +| time_elapsed | 30042 | +| total_timesteps | 41594880 | +| train/ | | +| approx_kl | 0.009830123 | +| clip_fraction | 0.292 | +| clip_range | 0.0646 | +| entropy_loss | -6.51 | +| explained_variance | 0.094 | +| learning_rate | 4.01e-05 | +| loss | -0.0194 | +| n_updates | 97056 | +| policy_gradient_loss | -0.014 | +| value_loss | 0.000258 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1384 | +| iterations | 20311 | +| time_elapsed | 30043 | +| total_timesteps | 41596928 | +| train/ | | +| approx_kl | 0.011259399 | +| clip_fraction | 0.322 | +| clip_range | 0.0646 | +| entropy_loss | -5.96 | +| explained_variance | 0.604 | +| learning_rate | 4.01e-05 | +| loss | -0.0305 | +| n_updates | 97060 | +| policy_gradient_loss | -0.0176 | +| value_loss | 9.8e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1384 | +| iterations | 20312 | +| time_elapsed | 30045 | +| total_timesteps | 41598976 | +| train/ | | +| approx_kl | 0.010859184 | +| clip_fraction | 0.3 | +| clip_range | 0.0646 | +| entropy_loss | -5.7 | +| explained_variance | 0.615 | +| learning_rate | 4.01e-05 | +| loss | -0.0213 | +| n_updates | 97064 | +| policy_gradient_loss | -0.0143 | +| value_loss | 0.000203 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1384 | +| iterations | 20313 | +| time_elapsed | 30046 | +| total_timesteps | 41601024 | +| train/ | | +| approx_kl | 0.010867971 | +| clip_fraction | 0.311 | +| clip_range | 0.0646 | +| entropy_loss | -5.68 | +| explained_variance | 0.316 | +| learning_rate | 4.01e-05 | +| loss | -0.0226 | +| n_updates | 97068 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000199 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1384 | +| iterations | 20314 | +| time_elapsed | 30048 | +| total_timesteps | 41603072 | +| train/ | | +| approx_kl | 0.013995959 | +| clip_fraction | 0.316 | +| clip_range | 0.0646 | +| entropy_loss | -5.69 | +| explained_variance | 0.436 | +| learning_rate | 4.01e-05 | +| loss | -0.028 | +| n_updates | 97072 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000136 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1384 | +| iterations | 20315 | +| time_elapsed | 30049 | +| total_timesteps | 41605120 | +| train/ | | +| approx_kl | 0.011631502 | +| clip_fraction | 0.342 | +| clip_range | 0.0646 | +| entropy_loss | -5.97 | +| explained_variance | -0.062 | +| learning_rate | 4.01e-05 | +| loss | -0.0314 | +| n_updates | 97076 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000203 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1384 | +| iterations | 20316 | +| time_elapsed | 30051 | +| total_timesteps | 41607168 | +| train/ | | +| approx_kl | 0.01183652 | +| clip_fraction | 0.327 | +| clip_range | 0.0646 | +| entropy_loss | -5.73 | +| explained_variance | 0.395 | +| learning_rate | 4.01e-05 | +| loss | -0.0245 | +| n_updates | 97080 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.000186 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1384 | +| iterations | 20317 | +| time_elapsed | 30053 | +| total_timesteps | 41609216 | +| train/ | | +| approx_kl | 0.010082331 | +| clip_fraction | 0.323 | +| clip_range | 0.0646 | +| entropy_loss | -5.93 | +| explained_variance | 0.416 | +| learning_rate | 4.01e-05 | +| loss | -0.0262 | +| n_updates | 97084 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000223 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1384 | +| iterations | 20318 | +| time_elapsed | 30054 | +| total_timesteps | 41611264 | +| train/ | | +| approx_kl | 0.012496104 | +| clip_fraction | 0.303 | +| clip_range | 0.0646 | +| entropy_loss | -6.02 | +| explained_variance | -0.0898 | +| learning_rate | 4.01e-05 | +| loss | -0.027 | +| n_updates | 97088 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000149 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1384 | +| iterations | 20319 | +| time_elapsed | 30056 | +| total_timesteps | 41613312 | +| train/ | | +| approx_kl | 0.011556136 | +| clip_fraction | 0.298 | +| clip_range | 0.0646 | +| entropy_loss | -6.19 | +| explained_variance | 0.464 | +| learning_rate | 4.01e-05 | +| loss | -0.0266 | +| n_updates | 97092 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000162 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1384 | +| iterations | 20320 | +| time_elapsed | 30057 | +| total_timesteps | 41615360 | +| train/ | | +| approx_kl | 0.0070100008 | +| clip_fraction | 0.273 | +| clip_range | 0.0646 | +| entropy_loss | -6.41 | +| explained_variance | 0.465 | +| learning_rate | 4.01e-05 | +| loss | -0.0228 | +| n_updates | 97096 | +| policy_gradient_loss | -0.014 | +| value_loss | 0.000113 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1384 | +| iterations | 20321 | +| time_elapsed | 30059 | +| total_timesteps | 41617408 | +| train/ | | +| approx_kl | 0.010677374 | +| clip_fraction | 0.292 | +| clip_range | 0.0646 | +| entropy_loss | -6.53 | +| explained_variance | 0.421 | +| learning_rate | 4.01e-05 | +| loss | -0.0257 | +| n_updates | 97100 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000107 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1384 | +| iterations | 20322 | +| time_elapsed | 30060 | +| total_timesteps | 41619456 | +| train/ | | +| approx_kl | 0.009689551 | +| clip_fraction | 0.306 | +| clip_range | 0.0646 | +| entropy_loss | -5.04 | +| explained_variance | 0.535 | +| learning_rate | 4.01e-05 | +| loss | -0.0205 | +| n_updates | 97104 | +| policy_gradient_loss | -0.0136 | +| value_loss | 0.000193 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1384 | +| iterations | 20323 | +| time_elapsed | 30062 | +| total_timesteps | 41621504 | +| train/ | | +| approx_kl | 0.011691488 | +| clip_fraction | 0.296 | +| clip_range | 0.0646 | +| entropy_loss | -5.41 | +| explained_variance | 0.353 | +| learning_rate | 4.01e-05 | +| loss | -0.0216 | +| n_updates | 97108 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.000318 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1384 | +| iterations | 20324 | +| time_elapsed | 30063 | +| total_timesteps | 41623552 | +| train/ | | +| approx_kl | 0.012003738 | +| clip_fraction | 0.318 | +| clip_range | 0.0646 | +| entropy_loss | -6.05 | +| explained_variance | 0.401 | +| learning_rate | 4.01e-05 | +| loss | -0.0287 | +| n_updates | 97112 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000184 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1384 | +| iterations | 20325 | +| time_elapsed | 30065 | +| total_timesteps | 41625600 | +| train/ | | +| approx_kl | 0.010823773 | +| clip_fraction | 0.324 | +| clip_range | 0.0646 | +| entropy_loss | -6.39 | +| explained_variance | 0.176 | +| learning_rate | 4.01e-05 | +| loss | -0.0265 | +| n_updates | 97116 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000243 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1384 | +| iterations | 20326 | +| time_elapsed | 30066 | +| total_timesteps | 41627648 | +| train/ | | +| approx_kl | 0.010060746 | +| clip_fraction | 0.264 | +| clip_range | 0.0646 | +| entropy_loss | -5.97 | +| explained_variance | 0.379 | +| learning_rate | 4.01e-05 | +| loss | -0.0243 | +| n_updates | 97120 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.000321 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1384 | +| iterations | 20327 | +| time_elapsed | 30068 | +| total_timesteps | 41629696 | +| train/ | | +| approx_kl | 0.009776831 | +| clip_fraction | 0.315 | +| clip_range | 0.0646 | +| entropy_loss | -5.73 | +| explained_variance | 0.337 | +| learning_rate | 4.01e-05 | +| loss | -0.0274 | +| n_updates | 97124 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000243 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1384 | +| iterations | 20328 | +| time_elapsed | 30069 | +| total_timesteps | 41631744 | +| train/ | | +| approx_kl | 0.01024068 | +| clip_fraction | 0.314 | +| clip_range | 0.0646 | +| entropy_loss | -5.15 | +| explained_variance | 0.478 | +| learning_rate | 4.01e-05 | +| loss | -0.0256 | +| n_updates | 97128 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000204 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1384 | +| iterations | 20329 | +| time_elapsed | 30071 | +| total_timesteps | 41633792 | +| train/ | | +| approx_kl | 0.013927525 | +| clip_fraction | 0.304 | +| clip_range | 0.0646 | +| entropy_loss | -5.76 | +| explained_variance | 0.381 | +| learning_rate | 4.01e-05 | +| loss | -0.0251 | +| n_updates | 97132 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000122 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1384 | +| iterations | 20330 | +| time_elapsed | 30072 | +| total_timesteps | 41635840 | +| train/ | | +| approx_kl | 0.012473947 | +| clip_fraction | 0.322 | +| clip_range | 0.0646 | +| entropy_loss | -6.2 | +| explained_variance | 0.0607 | +| learning_rate | 4.01e-05 | +| loss | -0.0333 | +| n_updates | 97136 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000141 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1384 | +| iterations | 20331 | +| time_elapsed | 30074 | +| total_timesteps | 41637888 | +| train/ | | +| approx_kl | 0.012276528 | +| clip_fraction | 0.305 | +| clip_range | 0.0646 | +| entropy_loss | -5.87 | +| explained_variance | 0.267 | +| learning_rate | 4.01e-05 | +| loss | -0.0218 | +| n_updates | 97140 | +| policy_gradient_loss | -0.0144 | +| value_loss | 0.000286 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1384 | +| iterations | 20332 | +| time_elapsed | 30075 | +| total_timesteps | 41639936 | +| train/ | | +| approx_kl | 0.014302334 | +| clip_fraction | 0.316 | +| clip_range | 0.0646 | +| entropy_loss | -5.68 | +| explained_variance | 0.258 | +| learning_rate | 4.01e-05 | +| loss | -0.034 | +| n_updates | 97144 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000125 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1384 | +| iterations | 20333 | +| time_elapsed | 30077 | +| total_timesteps | 41641984 | +| train/ | | +| approx_kl | 0.012952464 | +| clip_fraction | 0.326 | +| clip_range | 0.0646 | +| entropy_loss | -5.83 | +| explained_variance | 0.461 | +| learning_rate | 4.01e-05 | +| loss | -0.0354 | +| n_updates | 97148 | +| policy_gradient_loss | -0.0198 | +| value_loss | 8.91e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1384 | +| iterations | 20334 | +| time_elapsed | 30078 | +| total_timesteps | 41644032 | +| train/ | | +| approx_kl | 0.011225909 | +| clip_fraction | 0.304 | +| clip_range | 0.0646 | +| entropy_loss | -5.63 | +| explained_variance | 0.602 | +| learning_rate | 4.01e-05 | +| loss | -0.0255 | +| n_updates | 97152 | +| policy_gradient_loss | -0.0134 | +| value_loss | 0.000179 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1384 | +| iterations | 20335 | +| time_elapsed | 30080 | +| total_timesteps | 41646080 | +| train/ | | +| approx_kl | 0.012591176 | +| clip_fraction | 0.332 | +| clip_range | 0.0646 | +| entropy_loss | -4.75 | +| explained_variance | 0.543 | +| learning_rate | 4.01e-05 | +| loss | -0.0282 | +| n_updates | 97156 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.0002 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.367 | +| time/ | | +| fps | 1384 | +| iterations | 20336 | +| time_elapsed | 30081 | +| total_timesteps | 41648128 | +| train/ | | +| approx_kl | 0.0135328015 | +| clip_fraction | 0.351 | +| clip_range | 0.0646 | +| entropy_loss | -5.6 | +| explained_variance | 0.758 | +| learning_rate | 4.01e-05 | +| loss | -0.0363 | +| n_updates | 97160 | +| policy_gradient_loss | -0.0211 | +| value_loss | 7.6e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1384 | +| iterations | 20337 | +| time_elapsed | 30083 | +| total_timesteps | 41650176 | +| train/ | | +| approx_kl | 0.011523592 | +| clip_fraction | 0.333 | +| clip_range | 0.0646 | +| entropy_loss | -5.55 | +| explained_variance | -0.142 | +| learning_rate | 4.01e-05 | +| loss | -0.0248 | +| n_updates | 97164 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000195 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1384 | +| iterations | 20338 | +| time_elapsed | 30084 | +| total_timesteps | 41652224 | +| train/ | | +| approx_kl | 0.013270757 | +| clip_fraction | 0.34 | +| clip_range | 0.0646 | +| entropy_loss | -6.27 | +| explained_variance | 0.122 | +| learning_rate | 4.01e-05 | +| loss | -0.0282 | +| n_updates | 97168 | +| policy_gradient_loss | -0.0189 | +| value_loss | 9.11e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1384 | +| iterations | 20339 | +| time_elapsed | 30086 | +| total_timesteps | 41654272 | +| train/ | | +| approx_kl | 0.010783033 | +| clip_fraction | 0.307 | +| clip_range | 0.0646 | +| entropy_loss | -6.05 | +| explained_variance | 0.343 | +| learning_rate | 4.01e-05 | +| loss | -0.028 | +| n_updates | 97172 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000369 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1384 | +| iterations | 20340 | +| time_elapsed | 30088 | +| total_timesteps | 41656320 | +| train/ | | +| approx_kl | 0.011581233 | +| clip_fraction | 0.298 | +| clip_range | 0.0646 | +| entropy_loss | -5.67 | +| explained_variance | 0.231 | +| learning_rate | 4.01e-05 | +| loss | -0.0198 | +| n_updates | 97176 | +| policy_gradient_loss | -0.0133 | +| value_loss | 0.000508 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1384 | +| iterations | 20341 | +| time_elapsed | 30089 | +| total_timesteps | 41658368 | +| train/ | | +| approx_kl | 0.011059105 | +| clip_fraction | 0.329 | +| clip_range | 0.0646 | +| entropy_loss | -5.92 | +| explained_variance | 0.154 | +| learning_rate | 4.01e-05 | +| loss | -0.0312 | +| n_updates | 97180 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000144 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1384 | +| iterations | 20342 | +| time_elapsed | 30091 | +| total_timesteps | 41660416 | +| train/ | | +| approx_kl | 0.0090015195 | +| clip_fraction | 0.316 | +| clip_range | 0.0646 | +| entropy_loss | -6.7 | +| explained_variance | -0.23 | +| learning_rate | 4.01e-05 | +| loss | -0.0226 | +| n_updates | 97184 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000211 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1384 | +| iterations | 20343 | +| time_elapsed | 30092 | +| total_timesteps | 41662464 | +| train/ | | +| approx_kl | 0.010629519 | +| clip_fraction | 0.296 | +| clip_range | 0.0646 | +| entropy_loss | -5.49 | +| explained_variance | 0.584 | +| learning_rate | 4.01e-05 | +| loss | -0.0233 | +| n_updates | 97188 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000149 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1384 | +| iterations | 20344 | +| time_elapsed | 30094 | +| total_timesteps | 41664512 | +| train/ | | +| approx_kl | 0.010866058 | +| clip_fraction | 0.324 | +| clip_range | 0.0646 | +| entropy_loss | -5.61 | +| explained_variance | 0.481 | +| learning_rate | 4.01e-05 | +| loss | -0.028 | +| n_updates | 97192 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000183 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1384 | +| iterations | 20345 | +| time_elapsed | 30095 | +| total_timesteps | 41666560 | +| train/ | | +| approx_kl | 0.009657497 | +| clip_fraction | 0.312 | +| clip_range | 0.0646 | +| entropy_loss | -6.08 | +| explained_variance | 0.207 | +| learning_rate | 4.01e-05 | +| loss | -0.0319 | +| n_updates | 97196 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.00019 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1384 | +| iterations | 20346 | +| time_elapsed | 30097 | +| total_timesteps | 41668608 | +| train/ | | +| approx_kl | 0.01315886 | +| clip_fraction | 0.335 | +| clip_range | 0.0646 | +| entropy_loss | -5.42 | +| explained_variance | 0.605 | +| learning_rate | 4.01e-05 | +| loss | -0.0328 | +| n_updates | 97200 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000114 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1384 | +| iterations | 20347 | +| time_elapsed | 30098 | +| total_timesteps | 41670656 | +| train/ | | +| approx_kl | 0.01243581 | +| clip_fraction | 0.313 | +| clip_range | 0.0646 | +| entropy_loss | -5.58 | +| explained_variance | 0.561 | +| learning_rate | 4.01e-05 | +| loss | -0.0282 | +| n_updates | 97204 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000106 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1384 | +| iterations | 20348 | +| time_elapsed | 30100 | +| total_timesteps | 41672704 | +| train/ | | +| approx_kl | 0.011615911 | +| clip_fraction | 0.305 | +| clip_range | 0.0646 | +| entropy_loss | -5.93 | +| explained_variance | 0.329 | +| learning_rate | 4.01e-05 | +| loss | -0.0272 | +| n_updates | 97208 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000164 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1384 | +| iterations | 20349 | +| time_elapsed | 30101 | +| total_timesteps | 41674752 | +| train/ | | +| approx_kl | 0.010987546 | +| clip_fraction | 0.301 | +| clip_range | 0.0646 | +| entropy_loss | -6.68 | +| explained_variance | 0.239 | +| learning_rate | 4.01e-05 | +| loss | -0.0304 | +| n_updates | 97212 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000113 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1384 | +| iterations | 20350 | +| time_elapsed | 30103 | +| total_timesteps | 41676800 | +| train/ | | +| approx_kl | 0.012535078 | +| clip_fraction | 0.311 | +| clip_range | 0.0646 | +| entropy_loss | -5.74 | +| explained_variance | 0.345 | +| learning_rate | 4.01e-05 | +| loss | -0.0217 | +| n_updates | 97216 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.000313 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1384 | +| iterations | 20351 | +| time_elapsed | 30104 | +| total_timesteps | 41678848 | +| train/ | | +| approx_kl | 0.01177117 | +| clip_fraction | 0.341 | +| clip_range | 0.0646 | +| entropy_loss | -5.06 | +| explained_variance | 0.488 | +| learning_rate | 4.01e-05 | +| loss | -0.0267 | +| n_updates | 97220 | +| policy_gradient_loss | -0.0145 | +| value_loss | 0.000264 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1384 | +| iterations | 20352 | +| time_elapsed | 30106 | +| total_timesteps | 41680896 | +| train/ | | +| approx_kl | 0.015782539 | +| clip_fraction | 0.322 | +| clip_range | 0.0646 | +| entropy_loss | -5.07 | +| explained_variance | 0.401 | +| learning_rate | 4.01e-05 | +| loss | -0.0307 | +| n_updates | 97224 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000324 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1384 | +| iterations | 20353 | +| time_elapsed | 30108 | +| total_timesteps | 41682944 | +| train/ | | +| approx_kl | 0.010136981 | +| clip_fraction | 0.288 | +| clip_range | 0.0646 | +| entropy_loss | -5.84 | +| explained_variance | 0.272 | +| learning_rate | 4.01e-05 | +| loss | -0.029 | +| n_updates | 97228 | +| policy_gradient_loss | -0.0141 | +| value_loss | 0.000263 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1384 | +| iterations | 20354 | +| time_elapsed | 30109 | +| total_timesteps | 41684992 | +| train/ | | +| approx_kl | 0.012064201 | +| clip_fraction | 0.33 | +| clip_range | 0.0646 | +| entropy_loss | -5.69 | +| explained_variance | 0.406 | +| learning_rate | 4.01e-05 | +| loss | -0.0293 | +| n_updates | 97232 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000152 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1384 | +| iterations | 20355 | +| time_elapsed | 30111 | +| total_timesteps | 41687040 | +| train/ | | +| approx_kl | 0.010905651 | +| clip_fraction | 0.303 | +| clip_range | 0.0646 | +| entropy_loss | -5.77 | +| explained_variance | 0.477 | +| learning_rate | 4.01e-05 | +| loss | -0.0276 | +| n_updates | 97236 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.00015 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.374 | +| time/ | | +| fps | 1384 | +| iterations | 20356 | +| time_elapsed | 30112 | +| total_timesteps | 41689088 | +| train/ | | +| approx_kl | 0.01105947 | +| clip_fraction | 0.318 | +| clip_range | 0.0646 | +| entropy_loss | -6.13 | +| explained_variance | -0.0897 | +| learning_rate | 4.01e-05 | +| loss | -0.0307 | +| n_updates | 97240 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000114 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1384 | +| iterations | 20357 | +| time_elapsed | 30114 | +| total_timesteps | 41691136 | +| train/ | | +| approx_kl | 0.013537741 | +| clip_fraction | 0.331 | +| clip_range | 0.0646 | +| entropy_loss | -6.39 | +| explained_variance | 0.191 | +| learning_rate | 4.01e-05 | +| loss | -0.0309 | +| n_updates | 97244 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000107 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1384 | +| iterations | 20358 | +| time_elapsed | 30115 | +| total_timesteps | 41693184 | +| train/ | | +| approx_kl | 0.01155616 | +| clip_fraction | 0.317 | +| clip_range | 0.0646 | +| entropy_loss | -6.52 | +| explained_variance | -0.0274 | +| learning_rate | 4.01e-05 | +| loss | -0.025 | +| n_updates | 97248 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000272 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1384 | +| iterations | 20359 | +| time_elapsed | 30117 | +| total_timesteps | 41695232 | +| train/ | | +| approx_kl | 0.009557154 | +| clip_fraction | 0.303 | +| clip_range | 0.0646 | +| entropy_loss | -5.95 | +| explained_variance | 0.457 | +| learning_rate | 4.01e-05 | +| loss | -0.0224 | +| n_updates | 97252 | +| policy_gradient_loss | -0.0134 | +| value_loss | 0.000174 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1384 | +| iterations | 20360 | +| time_elapsed | 30118 | +| total_timesteps | 41697280 | +| train/ | | +| approx_kl | 0.011584783 | +| clip_fraction | 0.337 | +| clip_range | 0.0646 | +| entropy_loss | -5.84 | +| explained_variance | 0.464 | +| learning_rate | 4.01e-05 | +| loss | -0.0293 | +| n_updates | 97256 | +| policy_gradient_loss | -0.0188 | +| value_loss | 8.42e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1384 | +| iterations | 20361 | +| time_elapsed | 30120 | +| total_timesteps | 41699328 | +| train/ | | +| approx_kl | 0.009396413 | +| clip_fraction | 0.291 | +| clip_range | 0.0646 | +| entropy_loss | -6.1 | +| explained_variance | 0.504 | +| learning_rate | 4.01e-05 | +| loss | -0.0251 | +| n_updates | 97260 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000143 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1384 | +| iterations | 20362 | +| time_elapsed | 30121 | +| total_timesteps | 41701376 | +| train/ | | +| approx_kl | 0.010812665 | +| clip_fraction | 0.311 | +| clip_range | 0.0646 | +| entropy_loss | -5.87 | +| explained_variance | 0.407 | +| learning_rate | 4.01e-05 | +| loss | -0.0258 | +| n_updates | 97264 | +| policy_gradient_loss | -0.0169 | +| value_loss | 9.99e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1384 | +| iterations | 20363 | +| time_elapsed | 30123 | +| total_timesteps | 41703424 | +| train/ | | +| approx_kl | 0.0119026145 | +| clip_fraction | 0.294 | +| clip_range | 0.0646 | +| entropy_loss | -5.93 | +| explained_variance | 0.508 | +| learning_rate | 4.01e-05 | +| loss | -0.0299 | +| n_updates | 97268 | +| policy_gradient_loss | -0.0167 | +| value_loss | 9.69e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1384 | +| iterations | 20364 | +| time_elapsed | 30124 | +| total_timesteps | 41705472 | +| train/ | | +| approx_kl | 0.013196465 | +| clip_fraction | 0.301 | +| clip_range | 0.0646 | +| entropy_loss | -5.82 | +| explained_variance | 0.466 | +| learning_rate | 4.01e-05 | +| loss | -0.018 | +| n_updates | 97272 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000281 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1384 | +| iterations | 20365 | +| time_elapsed | 30126 | +| total_timesteps | 41707520 | +| train/ | | +| approx_kl | 0.012338731 | +| clip_fraction | 0.309 | +| clip_range | 0.0646 | +| entropy_loss | -5.26 | +| explained_variance | 0.368 | +| learning_rate | 4.01e-05 | +| loss | -0.0302 | +| n_updates | 97276 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000163 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.387 | +| time/ | | +| fps | 1384 | +| iterations | 20366 | +| time_elapsed | 30128 | +| total_timesteps | 41709568 | +| train/ | | +| approx_kl | 0.013465503 | +| clip_fraction | 0.293 | +| clip_range | 0.0646 | +| entropy_loss | -5.54 | +| explained_variance | 0.377 | +| learning_rate | 4.01e-05 | +| loss | -0.0203 | +| n_updates | 97280 | +| policy_gradient_loss | -0.0146 | +| value_loss | 0.000256 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.393 | +| time/ | | +| fps | 1384 | +| iterations | 20367 | +| time_elapsed | 30129 | +| total_timesteps | 41711616 | +| train/ | | +| approx_kl | 0.012292665 | +| clip_fraction | 0.325 | +| clip_range | 0.0646 | +| entropy_loss | -5.64 | +| explained_variance | 0.152 | +| learning_rate | 4.01e-05 | +| loss | -0.0253 | +| n_updates | 97284 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000329 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.393 | +| time/ | | +| fps | 1384 | +| iterations | 20368 | +| time_elapsed | 30131 | +| total_timesteps | 41713664 | +| train/ | | +| approx_kl | 0.013499259 | +| clip_fraction | 0.357 | +| clip_range | 0.0646 | +| entropy_loss | -5.48 | +| explained_variance | -0.12 | +| learning_rate | 4.01e-05 | +| loss | -0.0316 | +| n_updates | 97288 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000109 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.393 | +| time/ | | +| fps | 1384 | +| iterations | 20369 | +| time_elapsed | 30132 | +| total_timesteps | 41715712 | +| train/ | | +| approx_kl | 0.012986652 | +| clip_fraction | 0.348 | +| clip_range | 0.0646 | +| entropy_loss | -5.74 | +| explained_variance | 0.579 | +| learning_rate | 4.01e-05 | +| loss | -0.0314 | +| n_updates | 97292 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000125 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.389 | +| time/ | | +| fps | 1384 | +| iterations | 20370 | +| time_elapsed | 30134 | +| total_timesteps | 41717760 | +| train/ | | +| approx_kl | 0.012828942 | +| clip_fraction | 0.348 | +| clip_range | 0.0646 | +| entropy_loss | -6.53 | +| explained_variance | -0.0879 | +| learning_rate | 4.01e-05 | +| loss | -0.0278 | +| n_updates | 97296 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000201 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.388 | +| time/ | | +| fps | 1384 | +| iterations | 20371 | +| time_elapsed | 30135 | +| total_timesteps | 41719808 | +| train/ | | +| approx_kl | 0.011411736 | +| clip_fraction | 0.338 | +| clip_range | 0.0646 | +| entropy_loss | -6.15 | +| explained_variance | 0.0831 | +| learning_rate | 4.01e-05 | +| loss | -0.0225 | +| n_updates | 97300 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000134 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.385 | +| time/ | | +| fps | 1384 | +| iterations | 20372 | +| time_elapsed | 30137 | +| total_timesteps | 41721856 | +| train/ | | +| approx_kl | 0.010662669 | +| clip_fraction | 0.286 | +| clip_range | 0.0646 | +| entropy_loss | -5.51 | +| explained_variance | 0.486 | +| learning_rate | 4.01e-05 | +| loss | -0.0191 | +| n_updates | 97304 | +| policy_gradient_loss | -0.0134 | +| value_loss | 0.000122 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1384 | +| iterations | 20373 | +| time_elapsed | 30138 | +| total_timesteps | 41723904 | +| train/ | | +| approx_kl | 0.01123677 | +| clip_fraction | 0.279 | +| clip_range | 0.0646 | +| entropy_loss | -5.09 | +| explained_variance | 0.458 | +| learning_rate | 4.01e-05 | +| loss | -0.0187 | +| n_updates | 97308 | +| policy_gradient_loss | -0.013 | +| value_loss | 0.000239 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1384 | +| iterations | 20374 | +| time_elapsed | 30140 | +| total_timesteps | 41725952 | +| train/ | | +| approx_kl | 0.014288957 | +| clip_fraction | 0.31 | +| clip_range | 0.0646 | +| entropy_loss | -5.09 | +| explained_variance | 0.492 | +| learning_rate | 4.01e-05 | +| loss | -0.027 | +| n_updates | 97312 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000127 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1384 | +| iterations | 20375 | +| time_elapsed | 30142 | +| total_timesteps | 41728000 | +| train/ | | +| approx_kl | 0.0146630965 | +| clip_fraction | 0.348 | +| clip_range | 0.0646 | +| entropy_loss | -5.28 | +| explained_variance | 0.386 | +| learning_rate | 4.01e-05 | +| loss | -0.0257 | +| n_updates | 97316 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000175 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1384 | +| iterations | 20376 | +| time_elapsed | 30143 | +| total_timesteps | 41730048 | +| train/ | | +| approx_kl | 0.009710914 | +| clip_fraction | 0.306 | +| clip_range | 0.0646 | +| entropy_loss | -6.15 | +| explained_variance | 0.296 | +| learning_rate | 4.01e-05 | +| loss | -0.0261 | +| n_updates | 97320 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000101 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1384 | +| iterations | 20377 | +| time_elapsed | 30145 | +| total_timesteps | 41732096 | +| train/ | | +| approx_kl | 0.010924194 | +| clip_fraction | 0.288 | +| clip_range | 0.0646 | +| entropy_loss | -6.27 | +| explained_variance | 0.444 | +| learning_rate | 4.01e-05 | +| loss | -0.0261 | +| n_updates | 97324 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000242 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1384 | +| iterations | 20378 | +| time_elapsed | 30146 | +| total_timesteps | 41734144 | +| train/ | | +| approx_kl | 0.009257447 | +| clip_fraction | 0.285 | +| clip_range | 0.0646 | +| entropy_loss | -5.62 | +| explained_variance | 0.185 | +| learning_rate | 4.01e-05 | +| loss | -0.0213 | +| n_updates | 97328 | +| policy_gradient_loss | -0.0138 | +| value_loss | 0.00029 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1384 | +| iterations | 20379 | +| time_elapsed | 30148 | +| total_timesteps | 41736192 | +| train/ | | +| approx_kl | 0.009522714 | +| clip_fraction | 0.296 | +| clip_range | 0.0646 | +| entropy_loss | -5.79 | +| explained_variance | 0.388 | +| learning_rate | 4.01e-05 | +| loss | -0.022 | +| n_updates | 97332 | +| policy_gradient_loss | -0.0147 | +| value_loss | 0.000231 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1384 | +| iterations | 20380 | +| time_elapsed | 30149 | +| total_timesteps | 41738240 | +| train/ | | +| approx_kl | 0.010388719 | +| clip_fraction | 0.281 | +| clip_range | 0.0646 | +| entropy_loss | -6.46 | +| explained_variance | 0.239 | +| learning_rate | 4.01e-05 | +| loss | -0.026 | +| n_updates | 97336 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000283 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1384 | +| iterations | 20381 | +| time_elapsed | 30151 | +| total_timesteps | 41740288 | +| train/ | | +| approx_kl | 0.00862721 | +| clip_fraction | 0.293 | +| clip_range | 0.0646 | +| entropy_loss | -6.56 | +| explained_variance | 0.409 | +| learning_rate | 4.01e-05 | +| loss | -0.0213 | +| n_updates | 97340 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000274 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.387 | +| time/ | | +| fps | 1384 | +| iterations | 20382 | +| time_elapsed | 30152 | +| total_timesteps | 41742336 | +| train/ | | +| approx_kl | 0.009393329 | +| clip_fraction | 0.31 | +| clip_range | 0.0646 | +| entropy_loss | -5.58 | +| explained_variance | 0.191 | +| learning_rate | 4.01e-05 | +| loss | -0.0317 | +| n_updates | 97344 | +| policy_gradient_loss | -0.0176 | +| value_loss | 9.42e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1384 | +| iterations | 20383 | +| time_elapsed | 30154 | +| total_timesteps | 41744384 | +| train/ | | +| approx_kl | 0.008742478 | +| clip_fraction | 0.313 | +| clip_range | 0.0646 | +| entropy_loss | -6.08 | +| explained_variance | 0.339 | +| learning_rate | 4.01e-05 | +| loss | -0.026 | +| n_updates | 97348 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000143 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1384 | +| iterations | 20384 | +| time_elapsed | 30155 | +| total_timesteps | 41746432 | +| train/ | | +| approx_kl | 0.01190658 | +| clip_fraction | 0.344 | +| clip_range | 0.0646 | +| entropy_loss | -5.97 | +| explained_variance | 0.707 | +| learning_rate | 4.01e-05 | +| loss | -0.0385 | +| n_updates | 97352 | +| policy_gradient_loss | -0.0202 | +| value_loss | 5.14e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1384 | +| iterations | 20385 | +| time_elapsed | 30157 | +| total_timesteps | 41748480 | +| train/ | | +| approx_kl | 0.012023676 | +| clip_fraction | 0.224 | +| clip_range | 0.0646 | +| entropy_loss | -5.27 | +| explained_variance | 0.283 | +| learning_rate | 4.01e-05 | +| loss | -0.0164 | +| n_updates | 97356 | +| policy_gradient_loss | -0.0111 | +| value_loss | 0.00025 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1384 | +| iterations | 20386 | +| time_elapsed | 30158 | +| total_timesteps | 41750528 | +| train/ | | +| approx_kl | 0.010853523 | +| clip_fraction | 0.299 | +| clip_range | 0.0646 | +| entropy_loss | -5.63 | +| explained_variance | 0.346 | +| learning_rate | 4.01e-05 | +| loss | -0.0257 | +| n_updates | 97360 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000283 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1384 | +| iterations | 20387 | +| time_elapsed | 30160 | +| total_timesteps | 41752576 | +| train/ | | +| approx_kl | 0.012009141 | +| clip_fraction | 0.332 | +| clip_range | 0.0646 | +| entropy_loss | -5.56 | +| explained_variance | 0.556 | +| learning_rate | 4.01e-05 | +| loss | -0.0298 | +| n_updates | 97364 | +| policy_gradient_loss | -0.0192 | +| value_loss | 8.48e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1384 | +| iterations | 20388 | +| time_elapsed | 30162 | +| total_timesteps | 41754624 | +| train/ | | +| approx_kl | 0.012372612 | +| clip_fraction | 0.337 | +| clip_range | 0.0646 | +| entropy_loss | -5.65 | +| explained_variance | 0.703 | +| learning_rate | 4.01e-05 | +| loss | -0.0335 | +| n_updates | 97368 | +| policy_gradient_loss | -0.0192 | +| value_loss | 9.31e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1384 | +| iterations | 20389 | +| time_elapsed | 30163 | +| total_timesteps | 41756672 | +| train/ | | +| approx_kl | 0.014587371 | +| clip_fraction | 0.309 | +| clip_range | 0.0646 | +| entropy_loss | -5.68 | +| explained_variance | 0.301 | +| learning_rate | 4.01e-05 | +| loss | -0.0261 | +| n_updates | 97372 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.00015 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1384 | +| iterations | 20390 | +| time_elapsed | 30165 | +| total_timesteps | 41758720 | +| train/ | | +| approx_kl | 0.011551775 | +| clip_fraction | 0.295 | +| clip_range | 0.0646 | +| entropy_loss | -6.05 | +| explained_variance | 0.426 | +| learning_rate | 4.01e-05 | +| loss | -0.0258 | +| n_updates | 97376 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000156 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1384 | +| iterations | 20391 | +| time_elapsed | 30166 | +| total_timesteps | 41760768 | +| train/ | | +| approx_kl | 0.00957696 | +| clip_fraction | 0.3 | +| clip_range | 0.0646 | +| entropy_loss | -6.19 | +| explained_variance | 0.357 | +| learning_rate | 4.01e-05 | +| loss | -0.0254 | +| n_updates | 97380 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000106 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1384 | +| iterations | 20392 | +| time_elapsed | 30168 | +| total_timesteps | 41762816 | +| train/ | | +| approx_kl | 0.012977954 | +| clip_fraction | 0.298 | +| clip_range | 0.0646 | +| entropy_loss | -5.55 | +| explained_variance | 0.478 | +| learning_rate | 4.01e-05 | +| loss | -0.0225 | +| n_updates | 97384 | +| policy_gradient_loss | -0.0143 | +| value_loss | 0.00021 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1384 | +| iterations | 20393 | +| time_elapsed | 30169 | +| total_timesteps | 41764864 | +| train/ | | +| approx_kl | 0.013221972 | +| clip_fraction | 0.322 | +| clip_range | 0.0646 | +| entropy_loss | -6.32 | +| explained_variance | -0.166 | +| learning_rate | 4.01e-05 | +| loss | -0.0252 | +| n_updates | 97388 | +| policy_gradient_loss | -0.018 | +| value_loss | 7.2e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1384 | +| iterations | 20394 | +| time_elapsed | 30171 | +| total_timesteps | 41766912 | +| train/ | | +| approx_kl | 0.010264354 | +| clip_fraction | 0.31 | +| clip_range | 0.0646 | +| entropy_loss | -6.19 | +| explained_variance | 0.528 | +| learning_rate | 4.01e-05 | +| loss | -0.0255 | +| n_updates | 97392 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000172 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1384 | +| iterations | 20395 | +| time_elapsed | 30173 | +| total_timesteps | 41768960 | +| train/ | | +| approx_kl | 0.012025464 | +| clip_fraction | 0.299 | +| clip_range | 0.0646 | +| entropy_loss | -5.89 | +| explained_variance | 0.373 | +| learning_rate | 4.01e-05 | +| loss | -0.0295 | +| n_updates | 97396 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000271 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1384 | +| iterations | 20396 | +| time_elapsed | 30174 | +| total_timesteps | 41771008 | +| train/ | | +| approx_kl | 0.011175277 | +| clip_fraction | 0.316 | +| clip_range | 0.0646 | +| entropy_loss | -6.13 | +| explained_variance | 0.283 | +| learning_rate | 4.01e-05 | +| loss | -0.0278 | +| n_updates | 97400 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000194 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1384 | +| iterations | 20397 | +| time_elapsed | 30176 | +| total_timesteps | 41773056 | +| train/ | | +| approx_kl | 0.008282896 | +| clip_fraction | 0.263 | +| clip_range | 0.0646 | +| entropy_loss | -5.67 | +| explained_variance | 0.255 | +| learning_rate | 4.01e-05 | +| loss | -0.0247 | +| n_updates | 97404 | +| policy_gradient_loss | -0.0134 | +| value_loss | 0.0002 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1384 | +| iterations | 20398 | +| time_elapsed | 30177 | +| total_timesteps | 41775104 | +| train/ | | +| approx_kl | 0.012038179 | +| clip_fraction | 0.328 | +| clip_range | 0.0646 | +| entropy_loss | -5.29 | +| explained_variance | 0.595 | +| learning_rate | 4.01e-05 | +| loss | -0.0304 | +| n_updates | 97408 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000142 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1384 | +| iterations | 20399 | +| time_elapsed | 30179 | +| total_timesteps | 41777152 | +| train/ | | +| approx_kl | 0.011535201 | +| clip_fraction | 0.312 | +| clip_range | 0.0646 | +| entropy_loss | -5.72 | +| explained_variance | 0.439 | +| learning_rate | 4.01e-05 | +| loss | -0.0191 | +| n_updates | 97412 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000224 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1384 | +| iterations | 20400 | +| time_elapsed | 30180 | +| total_timesteps | 41779200 | +| train/ | | +| approx_kl | 0.011250887 | +| clip_fraction | 0.341 | +| clip_range | 0.0646 | +| entropy_loss | -6.56 | +| explained_variance | -0.146 | +| learning_rate | 4.01e-05 | +| loss | -0.0275 | +| n_updates | 97416 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000113 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1384 | +| iterations | 20401 | +| time_elapsed | 30182 | +| total_timesteps | 41781248 | +| train/ | | +| approx_kl | 0.014362073 | +| clip_fraction | 0.371 | +| clip_range | 0.0646 | +| entropy_loss | -6.13 | +| explained_variance | 0.546 | +| learning_rate | 4.01e-05 | +| loss | -0.0352 | +| n_updates | 97420 | +| policy_gradient_loss | -0.022 | +| value_loss | 4e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1384 | +| iterations | 20402 | +| time_elapsed | 30183 | +| total_timesteps | 41783296 | +| train/ | | +| approx_kl | 0.01009857 | +| clip_fraction | 0.331 | +| clip_range | 0.0646 | +| entropy_loss | -6.11 | +| explained_variance | 0.294 | +| learning_rate | 4.01e-05 | +| loss | -0.0245 | +| n_updates | 97424 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000188 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1384 | +| iterations | 20403 | +| time_elapsed | 30185 | +| total_timesteps | 41785344 | +| train/ | | +| approx_kl | 0.011406514 | +| clip_fraction | 0.313 | +| clip_range | 0.0646 | +| entropy_loss | -5.91 | +| explained_variance | 0.0355 | +| learning_rate | 4.01e-05 | +| loss | -0.0201 | +| n_updates | 97428 | +| policy_gradient_loss | -0.0139 | +| value_loss | 0.000291 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1384 | +| iterations | 20404 | +| time_elapsed | 30186 | +| total_timesteps | 41787392 | +| train/ | | +| approx_kl | 0.010250498 | +| clip_fraction | 0.297 | +| clip_range | 0.0646 | +| entropy_loss | -5.63 | +| explained_variance | 0.467 | +| learning_rate | 4.01e-05 | +| loss | -0.025 | +| n_updates | 97432 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000254 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1384 | +| iterations | 20405 | +| time_elapsed | 30188 | +| total_timesteps | 41789440 | +| train/ | | +| approx_kl | 0.011666637 | +| clip_fraction | 0.315 | +| clip_range | 0.0646 | +| entropy_loss | -5.29 | +| explained_variance | 0.653 | +| learning_rate | 4.01e-05 | +| loss | -0.0208 | +| n_updates | 97436 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000106 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1384 | +| iterations | 20406 | +| time_elapsed | 30189 | +| total_timesteps | 41791488 | +| train/ | | +| approx_kl | 0.013855144 | +| clip_fraction | 0.341 | +| clip_range | 0.0646 | +| entropy_loss | -5.46 | +| explained_variance | 0.555 | +| learning_rate | 4.01e-05 | +| loss | -0.0338 | +| n_updates | 97440 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000111 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1384 | +| iterations | 20407 | +| time_elapsed | 30191 | +| total_timesteps | 41793536 | +| train/ | | +| approx_kl | 0.015620476 | +| clip_fraction | 0.323 | +| clip_range | 0.0646 | +| entropy_loss | -5.48 | +| explained_variance | 0.604 | +| learning_rate | 4.01e-05 | +| loss | -0.028 | +| n_updates | 97444 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1384 | +| iterations | 20408 | +| time_elapsed | 30192 | +| total_timesteps | 41795584 | +| train/ | | +| approx_kl | 0.014415231 | +| clip_fraction | 0.315 | +| clip_range | 0.0646 | +| entropy_loss | -6.41 | +| explained_variance | -0.206 | +| learning_rate | 4.01e-05 | +| loss | -0.0276 | +| n_updates | 97448 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000117 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1384 | +| iterations | 20409 | +| time_elapsed | 30194 | +| total_timesteps | 41797632 | +| train/ | | +| approx_kl | 0.0116300685 | +| clip_fraction | 0.311 | +| clip_range | 0.0646 | +| entropy_loss | -6.46 | +| explained_variance | -0.736 | +| learning_rate | 4.01e-05 | +| loss | -0.0248 | +| n_updates | 97452 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000157 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1384 | +| iterations | 20410 | +| time_elapsed | 30195 | +| total_timesteps | 41799680 | +| train/ | | +| approx_kl | 0.009982171 | +| clip_fraction | 0.294 | +| clip_range | 0.0646 | +| entropy_loss | -6.3 | +| explained_variance | 0.0204 | +| learning_rate | 4.01e-05 | +| loss | -0.0261 | +| n_updates | 97456 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000216 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1384 | +| iterations | 20411 | +| time_elapsed | 30197 | +| total_timesteps | 41801728 | +| train/ | | +| approx_kl | 0.008163239 | +| clip_fraction | 0.306 | +| clip_range | 0.0646 | +| entropy_loss | -6.1 | +| explained_variance | 0.11 | +| learning_rate | 4.01e-05 | +| loss | -0.0248 | +| n_updates | 97460 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000165 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1384 | +| iterations | 20412 | +| time_elapsed | 30199 | +| total_timesteps | 41803776 | +| train/ | | +| approx_kl | 0.008546911 | +| clip_fraction | 0.307 | +| clip_range | 0.0645 | +| entropy_loss | -6.19 | +| explained_variance | 0.337 | +| learning_rate | 4.01e-05 | +| loss | -0.029 | +| n_updates | 97464 | +| policy_gradient_loss | -0.0141 | +| value_loss | 0.000132 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1384 | +| iterations | 20413 | +| time_elapsed | 30200 | +| total_timesteps | 41805824 | +| train/ | | +| approx_kl | 0.01107434 | +| clip_fraction | 0.304 | +| clip_range | 0.0645 | +| entropy_loss | -6.17 | +| explained_variance | 0.606 | +| learning_rate | 4.01e-05 | +| loss | -0.0292 | +| n_updates | 97468 | +| policy_gradient_loss | -0.0171 | +| value_loss | 7.53e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1384 | +| iterations | 20414 | +| time_elapsed | 30202 | +| total_timesteps | 41807872 | +| train/ | | +| approx_kl | 0.009415467 | +| clip_fraction | 0.301 | +| clip_range | 0.0645 | +| entropy_loss | -5.38 | +| explained_variance | 0.554 | +| learning_rate | 4.01e-05 | +| loss | -0.0263 | +| n_updates | 97472 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000199 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1384 | +| iterations | 20415 | +| time_elapsed | 30203 | +| total_timesteps | 41809920 | +| train/ | | +| approx_kl | 0.009451998 | +| clip_fraction | 0.29 | +| clip_range | 0.0645 | +| entropy_loss | -5.2 | +| explained_variance | 0.541 | +| learning_rate | 4.01e-05 | +| loss | -0.0278 | +| n_updates | 97476 | +| policy_gradient_loss | -0.0139 | +| value_loss | 0.000163 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1384 | +| iterations | 20416 | +| time_elapsed | 30205 | +| total_timesteps | 41811968 | +| train/ | | +| approx_kl | 0.013054984 | +| clip_fraction | 0.328 | +| clip_range | 0.0645 | +| entropy_loss | -5.18 | +| explained_variance | 0.675 | +| learning_rate | 4.01e-05 | +| loss | -0.0323 | +| n_updates | 97480 | +| policy_gradient_loss | -0.0189 | +| value_loss | 8.99e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1384 | +| iterations | 20417 | +| time_elapsed | 30206 | +| total_timesteps | 41814016 | +| train/ | | +| approx_kl | 0.011618334 | +| clip_fraction | 0.303 | +| clip_range | 0.0645 | +| entropy_loss | -5.56 | +| explained_variance | 0.358 | +| learning_rate | 4.01e-05 | +| loss | -0.0289 | +| n_updates | 97484 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000107 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1384 | +| iterations | 20418 | +| time_elapsed | 30208 | +| total_timesteps | 41816064 | +| train/ | | +| approx_kl | 0.011522666 | +| clip_fraction | 0.309 | +| clip_range | 0.0645 | +| entropy_loss | -6.72 | +| explained_variance | 0.119 | +| learning_rate | 4.01e-05 | +| loss | -0.026 | +| n_updates | 97488 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.00011 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1384 | +| iterations | 20419 | +| time_elapsed | 30209 | +| total_timesteps | 41818112 | +| train/ | | +| approx_kl | 0.009836934 | +| clip_fraction | 0.321 | +| clip_range | 0.0645 | +| entropy_loss | -6.59 | +| explained_variance | 0.283 | +| learning_rate | 4.01e-05 | +| loss | -0.0287 | +| n_updates | 97492 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000156 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1384 | +| iterations | 20420 | +| time_elapsed | 30211 | +| total_timesteps | 41820160 | +| train/ | | +| approx_kl | 0.014300006 | +| clip_fraction | 0.291 | +| clip_range | 0.0645 | +| entropy_loss | -6.07 | +| explained_variance | 0.551 | +| learning_rate | 4.01e-05 | +| loss | -0.0289 | +| n_updates | 97496 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000103 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1384 | +| iterations | 20421 | +| time_elapsed | 30212 | +| total_timesteps | 41822208 | +| train/ | | +| approx_kl | 0.012702442 | +| clip_fraction | 0.298 | +| clip_range | 0.0645 | +| entropy_loss | -6.02 | +| explained_variance | 0.198 | +| learning_rate | 4.01e-05 | +| loss | -0.0231 | +| n_updates | 97500 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000325 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1384 | +| iterations | 20422 | +| time_elapsed | 30214 | +| total_timesteps | 41824256 | +| train/ | | +| approx_kl | 0.01244051 | +| clip_fraction | 0.317 | +| clip_range | 0.0645 | +| entropy_loss | -5.82 | +| explained_variance | 0.612 | +| learning_rate | 4.01e-05 | +| loss | -0.0294 | +| n_updates | 97504 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000151 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1384 | +| iterations | 20423 | +| time_elapsed | 30215 | +| total_timesteps | 41826304 | +| train/ | | +| approx_kl | 0.0095911855 | +| clip_fraction | 0.303 | +| clip_range | 0.0645 | +| entropy_loss | -5.06 | +| explained_variance | 0.493 | +| learning_rate | 4.01e-05 | +| loss | -0.0291 | +| n_updates | 97508 | +| policy_gradient_loss | -0.0141 | +| value_loss | 0.000282 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1384 | +| iterations | 20424 | +| time_elapsed | 30217 | +| total_timesteps | 41828352 | +| train/ | | +| approx_kl | 0.01076638 | +| clip_fraction | 0.323 | +| clip_range | 0.0645 | +| entropy_loss | -5.21 | +| explained_variance | 0.348 | +| learning_rate | 4.01e-05 | +| loss | -0.0325 | +| n_updates | 97512 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000133 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1384 | +| iterations | 20425 | +| time_elapsed | 30219 | +| total_timesteps | 41830400 | +| train/ | | +| approx_kl | 0.010450404 | +| clip_fraction | 0.329 | +| clip_range | 0.0645 | +| entropy_loss | -6 | +| explained_variance | 0.187 | +| learning_rate | 4.01e-05 | +| loss | -0.0291 | +| n_updates | 97516 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.00014 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1384 | +| iterations | 20426 | +| time_elapsed | 30220 | +| total_timesteps | 41832448 | +| train/ | | +| approx_kl | 0.009286409 | +| clip_fraction | 0.305 | +| clip_range | 0.0645 | +| entropy_loss | -6.38 | +| explained_variance | 0.244 | +| learning_rate | 4.01e-05 | +| loss | -0.0237 | +| n_updates | 97520 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000221 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1384 | +| iterations | 20427 | +| time_elapsed | 30222 | +| total_timesteps | 41834496 | +| train/ | | +| approx_kl | 0.013202658 | +| clip_fraction | 0.324 | +| clip_range | 0.0645 | +| entropy_loss | -5.61 | +| explained_variance | 0.51 | +| learning_rate | 4.01e-05 | +| loss | -0.029 | +| n_updates | 97524 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000144 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1384 | +| iterations | 20428 | +| time_elapsed | 30223 | +| total_timesteps | 41836544 | +| train/ | | +| approx_kl | 0.0101525 | +| clip_fraction | 0.315 | +| clip_range | 0.0645 | +| entropy_loss | -5.57 | +| explained_variance | 0.285 | +| learning_rate | 4.01e-05 | +| loss | -0.0237 | +| n_updates | 97528 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000555 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1384 | +| iterations | 20429 | +| time_elapsed | 30225 | +| total_timesteps | 41838592 | +| train/ | | +| approx_kl | 0.010329761 | +| clip_fraction | 0.312 | +| clip_range | 0.0645 | +| entropy_loss | -5.62 | +| explained_variance | 0.305 | +| learning_rate | 4.01e-05 | +| loss | -0.0319 | +| n_updates | 97532 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000239 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1384 | +| iterations | 20430 | +| time_elapsed | 30226 | +| total_timesteps | 41840640 | +| train/ | | +| approx_kl | 0.013238288 | +| clip_fraction | 0.318 | +| clip_range | 0.0645 | +| entropy_loss | -5.88 | +| explained_variance | 0.339 | +| learning_rate | 4.01e-05 | +| loss | -0.0261 | +| n_updates | 97536 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.00028 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1384 | +| iterations | 20431 | +| time_elapsed | 30228 | +| total_timesteps | 41842688 | +| train/ | | +| approx_kl | 0.008491331 | +| clip_fraction | 0.316 | +| clip_range | 0.0645 | +| entropy_loss | -5.84 | +| explained_variance | 0.319 | +| learning_rate | 4.01e-05 | +| loss | -0.0236 | +| n_updates | 97540 | +| policy_gradient_loss | -0.0147 | +| value_loss | 0.000315 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1384 | +| iterations | 20432 | +| time_elapsed | 30229 | +| total_timesteps | 41844736 | +| train/ | | +| approx_kl | 0.011509763 | +| clip_fraction | 0.328 | +| clip_range | 0.0645 | +| entropy_loss | -4.97 | +| explained_variance | 0.708 | +| learning_rate | 4.01e-05 | +| loss | -0.0324 | +| n_updates | 97544 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000121 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1384 | +| iterations | 20433 | +| time_elapsed | 30231 | +| total_timesteps | 41846784 | +| train/ | | +| approx_kl | 0.015010105 | +| clip_fraction | 0.323 | +| clip_range | 0.0645 | +| entropy_loss | -5.7 | +| explained_variance | 0.27 | +| learning_rate | 4.01e-05 | +| loss | -0.026 | +| n_updates | 97548 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000207 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1384 | +| iterations | 20434 | +| time_elapsed | 30232 | +| total_timesteps | 41848832 | +| train/ | | +| approx_kl | 0.012138421 | +| clip_fraction | 0.36 | +| clip_range | 0.0645 | +| entropy_loss | -5.98 | +| explained_variance | 0.228 | +| learning_rate | 4.01e-05 | +| loss | -0.0304 | +| n_updates | 97552 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000181 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1384 | +| iterations | 20435 | +| time_elapsed | 30234 | +| total_timesteps | 41850880 | +| train/ | | +| approx_kl | 0.013811152 | +| clip_fraction | 0.336 | +| clip_range | 0.0645 | +| entropy_loss | -6.02 | +| explained_variance | 0.338 | +| learning_rate | 4.01e-05 | +| loss | -0.0349 | +| n_updates | 97556 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000131 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1384 | +| iterations | 20436 | +| time_elapsed | 30236 | +| total_timesteps | 41852928 | +| train/ | | +| approx_kl | 0.013875777 | +| clip_fraction | 0.315 | +| clip_range | 0.0645 | +| entropy_loss | -6.48 | +| explained_variance | 0.0219 | +| learning_rate | 4.01e-05 | +| loss | -0.0289 | +| n_updates | 97560 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000131 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1384 | +| iterations | 20437 | +| time_elapsed | 30238 | +| total_timesteps | 41854976 | +| train/ | | +| approx_kl | 0.013166159 | +| clip_fraction | 0.333 | +| clip_range | 0.0645 | +| entropy_loss | -5.97 | +| explained_variance | 0.319 | +| learning_rate | 4.01e-05 | +| loss | -0.0235 | +| n_updates | 97564 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000318 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1384 | +| iterations | 20438 | +| time_elapsed | 30239 | +| total_timesteps | 41857024 | +| train/ | | +| approx_kl | 0.016180525 | +| clip_fraction | 0.286 | +| clip_range | 0.0645 | +| entropy_loss | -5.63 | +| explained_variance | 0.602 | +| learning_rate | 4.01e-05 | +| loss | -0.026 | +| n_updates | 97568 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.000207 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1384 | +| iterations | 20439 | +| time_elapsed | 30241 | +| total_timesteps | 41859072 | +| train/ | | +| approx_kl | 0.01369318 | +| clip_fraction | 0.336 | +| clip_range | 0.0645 | +| entropy_loss | -5.52 | +| explained_variance | 0.254 | +| learning_rate | 4.01e-05 | +| loss | -0.0335 | +| n_updates | 97572 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000135 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1384 | +| iterations | 20440 | +| time_elapsed | 30242 | +| total_timesteps | 41861120 | +| train/ | | +| approx_kl | 0.011697328 | +| clip_fraction | 0.34 | +| clip_range | 0.0645 | +| entropy_loss | -6.19 | +| explained_variance | 0.69 | +| learning_rate | 4.01e-05 | +| loss | -0.0281 | +| n_updates | 97576 | +| policy_gradient_loss | -0.0192 | +| value_loss | 8.93e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1384 | +| iterations | 20441 | +| time_elapsed | 30244 | +| total_timesteps | 41863168 | +| train/ | | +| approx_kl | 0.011147891 | +| clip_fraction | 0.309 | +| clip_range | 0.0645 | +| entropy_loss | -6.08 | +| explained_variance | 0.121 | +| learning_rate | 4.01e-05 | +| loss | -0.0206 | +| n_updates | 97580 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.00015 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1384 | +| iterations | 20442 | +| time_elapsed | 30245 | +| total_timesteps | 41865216 | +| train/ | | +| approx_kl | 0.012367929 | +| clip_fraction | 0.314 | +| clip_range | 0.0645 | +| entropy_loss | -6.18 | +| explained_variance | 0.537 | +| learning_rate | 4.01e-05 | +| loss | -0.0284 | +| n_updates | 97584 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000113 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1384 | +| iterations | 20443 | +| time_elapsed | 30247 | +| total_timesteps | 41867264 | +| train/ | | +| approx_kl | 0.01066046 | +| clip_fraction | 0.295 | +| clip_range | 0.0645 | +| entropy_loss | -6.48 | +| explained_variance | 0.0246 | +| learning_rate | 4.01e-05 | +| loss | -0.0219 | +| n_updates | 97588 | +| policy_gradient_loss | -0.014 | +| value_loss | 0.000195 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1384 | +| iterations | 20444 | +| time_elapsed | 30248 | +| total_timesteps | 41869312 | +| train/ | | +| approx_kl | 0.010733042 | +| clip_fraction | 0.341 | +| clip_range | 0.0645 | +| entropy_loss | -5.52 | +| explained_variance | 0.461 | +| learning_rate | 4.01e-05 | +| loss | -0.0307 | +| n_updates | 97592 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000149 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1384 | +| iterations | 20445 | +| time_elapsed | 30250 | +| total_timesteps | 41871360 | +| train/ | | +| approx_kl | 0.011950608 | +| clip_fraction | 0.3 | +| clip_range | 0.0645 | +| entropy_loss | -4.99 | +| explained_variance | 0.508 | +| learning_rate | 4.01e-05 | +| loss | -0.0198 | +| n_updates | 97596 | +| policy_gradient_loss | -0.0138 | +| value_loss | 0.000335 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1384 | +| iterations | 20446 | +| time_elapsed | 30251 | +| total_timesteps | 41873408 | +| train/ | | +| approx_kl | 0.012586946 | +| clip_fraction | 0.328 | +| clip_range | 0.0645 | +| entropy_loss | -6.16 | +| explained_variance | -0.222 | +| learning_rate | 4.01e-05 | +| loss | -0.0309 | +| n_updates | 97600 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000126 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1384 | +| iterations | 20447 | +| time_elapsed | 30253 | +| total_timesteps | 41875456 | +| train/ | | +| approx_kl | 0.014354126 | +| clip_fraction | 0.314 | +| clip_range | 0.0645 | +| entropy_loss | -6.42 | +| explained_variance | 0.0997 | +| learning_rate | 4.01e-05 | +| loss | -0.0217 | +| n_updates | 97604 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000144 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1384 | +| iterations | 20448 | +| time_elapsed | 30255 | +| total_timesteps | 41877504 | +| train/ | | +| approx_kl | 0.012579292 | +| clip_fraction | 0.314 | +| clip_range | 0.0645 | +| entropy_loss | -5.96 | +| explained_variance | 0.353 | +| learning_rate | 4.01e-05 | +| loss | -0.0227 | +| n_updates | 97608 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000251 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1384 | +| iterations | 20449 | +| time_elapsed | 30256 | +| total_timesteps | 41879552 | +| train/ | | +| approx_kl | 0.012887489 | +| clip_fraction | 0.329 | +| clip_range | 0.0645 | +| entropy_loss | -4.98 | +| explained_variance | 0.798 | +| learning_rate | 4.01e-05 | +| loss | -0.0313 | +| n_updates | 97612 | +| policy_gradient_loss | -0.0181 | +| value_loss | 6.57e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1384 | +| iterations | 20450 | +| time_elapsed | 30258 | +| total_timesteps | 41881600 | +| train/ | | +| approx_kl | 0.012496131 | +| clip_fraction | 0.3 | +| clip_range | 0.0645 | +| entropy_loss | -4.73 | +| explained_variance | 0.647 | +| learning_rate | 4.01e-05 | +| loss | -0.0236 | +| n_updates | 97616 | +| policy_gradient_loss | -0.0146 | +| value_loss | 0.000124 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1384 | +| iterations | 20451 | +| time_elapsed | 30259 | +| total_timesteps | 41883648 | +| train/ | | +| approx_kl | 0.011879966 | +| clip_fraction | 0.304 | +| clip_range | 0.0645 | +| entropy_loss | -5.28 | +| explained_variance | 0.513 | +| learning_rate | 4.01e-05 | +| loss | -0.0278 | +| n_updates | 97620 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000102 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1384 | +| iterations | 20452 | +| time_elapsed | 30261 | +| total_timesteps | 41885696 | +| train/ | | +| approx_kl | 0.015128307 | +| clip_fraction | 0.312 | +| clip_range | 0.0645 | +| entropy_loss | -6.06 | +| explained_variance | 0.325 | +| learning_rate | 4.01e-05 | +| loss | -0.0238 | +| n_updates | 97624 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000158 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1384 | +| iterations | 20453 | +| time_elapsed | 30262 | +| total_timesteps | 41887744 | +| train/ | | +| approx_kl | 0.012103789 | +| clip_fraction | 0.301 | +| clip_range | 0.0645 | +| entropy_loss | -5.78 | +| explained_variance | 0.356 | +| learning_rate | 4.01e-05 | +| loss | -0.0289 | +| n_updates | 97628 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000232 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1384 | +| iterations | 20454 | +| time_elapsed | 30264 | +| total_timesteps | 41889792 | +| train/ | | +| approx_kl | 0.010327571 | +| clip_fraction | 0.321 | +| clip_range | 0.0645 | +| entropy_loss | -6.63 | +| explained_variance | -0.112 | +| learning_rate | 4.01e-05 | +| loss | -0.0322 | +| n_updates | 97632 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000119 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1384 | +| iterations | 20455 | +| time_elapsed | 30265 | +| total_timesteps | 41891840 | +| train/ | | +| approx_kl | 0.009178396 | +| clip_fraction | 0.276 | +| clip_range | 0.0645 | +| entropy_loss | -6.8 | +| explained_variance | 0.144 | +| learning_rate | 4.01e-05 | +| loss | -0.0293 | +| n_updates | 97636 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000149 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1384 | +| iterations | 20456 | +| time_elapsed | 30267 | +| total_timesteps | 41893888 | +| train/ | | +| approx_kl | 0.009919361 | +| clip_fraction | 0.323 | +| clip_range | 0.0645 | +| entropy_loss | -6.43 | +| explained_variance | 0.378 | +| learning_rate | 4.01e-05 | +| loss | -0.02 | +| n_updates | 97640 | +| policy_gradient_loss | -0.0143 | +| value_loss | 0.000223 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1384 | +| iterations | 20457 | +| time_elapsed | 30269 | +| total_timesteps | 41895936 | +| train/ | | +| approx_kl | 0.01034262 | +| clip_fraction | 0.322 | +| clip_range | 0.0645 | +| entropy_loss | -5.57 | +| explained_variance | 0.46 | +| learning_rate | 4.01e-05 | +| loss | -0.0348 | +| n_updates | 97644 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000146 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1384 | +| iterations | 20458 | +| time_elapsed | 30270 | +| total_timesteps | 41897984 | +| train/ | | +| approx_kl | 0.00874188 | +| clip_fraction | 0.302 | +| clip_range | 0.0645 | +| entropy_loss | -5.15 | +| explained_variance | 0.566 | +| learning_rate | 4e-05 | +| loss | -0.0214 | +| n_updates | 97648 | +| policy_gradient_loss | -0.0145 | +| value_loss | 0.000205 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1384 | +| iterations | 20459 | +| time_elapsed | 30272 | +| total_timesteps | 41900032 | +| train/ | | +| approx_kl | 0.013116143 | +| clip_fraction | 0.352 | +| clip_range | 0.0645 | +| entropy_loss | -4.58 | +| explained_variance | 0.857 | +| learning_rate | 4e-05 | +| loss | -0.031 | +| n_updates | 97652 | +| policy_gradient_loss | -0.0202 | +| value_loss | 6.01e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1384 | +| iterations | 20460 | +| time_elapsed | 30273 | +| total_timesteps | 41902080 | +| train/ | | +| approx_kl | 0.012484546 | +| clip_fraction | 0.312 | +| clip_range | 0.0645 | +| entropy_loss | -5.75 | +| explained_variance | 0.288 | +| learning_rate | 4e-05 | +| loss | -0.0317 | +| n_updates | 97656 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000137 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1384 | +| iterations | 20461 | +| time_elapsed | 30275 | +| total_timesteps | 41904128 | +| train/ | | +| approx_kl | 0.010717003 | +| clip_fraction | 0.315 | +| clip_range | 0.0645 | +| entropy_loss | -6.23 | +| explained_variance | 0.488 | +| learning_rate | 4e-05 | +| loss | -0.0247 | +| n_updates | 97660 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000187 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1384 | +| iterations | 20462 | +| time_elapsed | 30276 | +| total_timesteps | 41906176 | +| train/ | | +| approx_kl | 0.012266668 | +| clip_fraction | 0.334 | +| clip_range | 0.0645 | +| entropy_loss | -5.84 | +| explained_variance | -0.199 | +| learning_rate | 4e-05 | +| loss | -0.0347 | +| n_updates | 97664 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.00013 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1384 | +| iterations | 20463 | +| time_elapsed | 30278 | +| total_timesteps | 41908224 | +| train/ | | +| approx_kl | 0.012947992 | +| clip_fraction | 0.344 | +| clip_range | 0.0645 | +| entropy_loss | -6.36 | +| explained_variance | 0.0209 | +| learning_rate | 4e-05 | +| loss | -0.0297 | +| n_updates | 97668 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000173 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1384 | +| iterations | 20464 | +| time_elapsed | 30280 | +| total_timesteps | 41910272 | +| train/ | | +| approx_kl | 0.009635095 | +| clip_fraction | 0.296 | +| clip_range | 0.0645 | +| entropy_loss | -6.06 | +| explained_variance | 0.261 | +| learning_rate | 4e-05 | +| loss | -0.0266 | +| n_updates | 97672 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000215 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1384 | +| iterations | 20465 | +| time_elapsed | 30281 | +| total_timesteps | 41912320 | +| train/ | | +| approx_kl | 0.010927272 | +| clip_fraction | 0.296 | +| clip_range | 0.0645 | +| entropy_loss | -5.8 | +| explained_variance | 0.484 | +| learning_rate | 4e-05 | +| loss | -0.0261 | +| n_updates | 97676 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.000256 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1384 | +| iterations | 20466 | +| time_elapsed | 30283 | +| total_timesteps | 41914368 | +| train/ | | +| approx_kl | 0.011465613 | +| clip_fraction | 0.326 | +| clip_range | 0.0645 | +| entropy_loss | -6.01 | +| explained_variance | 0.544 | +| learning_rate | 4e-05 | +| loss | -0.0306 | +| n_updates | 97680 | +| policy_gradient_loss | -0.0207 | +| value_loss | 9.36e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1384 | +| iterations | 20467 | +| time_elapsed | 30284 | +| total_timesteps | 41916416 | +| train/ | | +| approx_kl | 0.010687851 | +| clip_fraction | 0.324 | +| clip_range | 0.0645 | +| entropy_loss | -5.71 | +| explained_variance | 0.389 | +| learning_rate | 4e-05 | +| loss | -0.0246 | +| n_updates | 97684 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000149 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1384 | +| iterations | 20468 | +| time_elapsed | 30286 | +| total_timesteps | 41918464 | +| train/ | | +| approx_kl | 0.014083646 | +| clip_fraction | 0.343 | +| clip_range | 0.0645 | +| entropy_loss | -4.78 | +| explained_variance | 0.767 | +| learning_rate | 4e-05 | +| loss | -0.0289 | +| n_updates | 97688 | +| policy_gradient_loss | -0.0193 | +| value_loss | 8.2e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1384 | +| iterations | 20469 | +| time_elapsed | 30287 | +| total_timesteps | 41920512 | +| train/ | | +| approx_kl | 0.010903864 | +| clip_fraction | 0.299 | +| clip_range | 0.0645 | +| entropy_loss | -5.31 | +| explained_variance | 0.635 | +| learning_rate | 4e-05 | +| loss | -0.0251 | +| n_updates | 97692 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000142 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1384 | +| iterations | 20470 | +| time_elapsed | 30289 | +| total_timesteps | 41922560 | +| train/ | | +| approx_kl | 0.0113940425 | +| clip_fraction | 0.305 | +| clip_range | 0.0645 | +| entropy_loss | -5.56 | +| explained_variance | 0.549 | +| learning_rate | 4e-05 | +| loss | -0.0261 | +| n_updates | 97696 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000156 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1384 | +| iterations | 20471 | +| time_elapsed | 30290 | +| total_timesteps | 41924608 | +| train/ | | +| approx_kl | 0.010455536 | +| clip_fraction | 0.31 | +| clip_range | 0.0645 | +| entropy_loss | -5.9 | +| explained_variance | 0.537 | +| learning_rate | 4e-05 | +| loss | -0.0317 | +| n_updates | 97700 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000118 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1384 | +| iterations | 20472 | +| time_elapsed | 30292 | +| total_timesteps | 41926656 | +| train/ | | +| approx_kl | 0.010476461 | +| clip_fraction | 0.305 | +| clip_range | 0.0645 | +| entropy_loss | -5.68 | +| explained_variance | 0.348 | +| learning_rate | 4e-05 | +| loss | -0.0208 | +| n_updates | 97704 | +| policy_gradient_loss | -0.0143 | +| value_loss | 0.000423 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1384 | +| iterations | 20473 | +| time_elapsed | 30294 | +| total_timesteps | 41928704 | +| train/ | | +| approx_kl | 0.011826474 | +| clip_fraction | 0.328 | +| clip_range | 0.0645 | +| entropy_loss | -5.86 | +| explained_variance | 0.0035 | +| learning_rate | 4e-05 | +| loss | -0.0307 | +| n_updates | 97708 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000168 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1384 | +| iterations | 20474 | +| time_elapsed | 30295 | +| total_timesteps | 41930752 | +| train/ | | +| approx_kl | 0.009798334 | +| clip_fraction | 0.329 | +| clip_range | 0.0645 | +| entropy_loss | -5.9 | +| explained_variance | 0.186 | +| learning_rate | 4e-05 | +| loss | -0.0283 | +| n_updates | 97712 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000147 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1384 | +| iterations | 20475 | +| time_elapsed | 30297 | +| total_timesteps | 41932800 | +| train/ | | +| approx_kl | 0.01106865 | +| clip_fraction | 0.313 | +| clip_range | 0.0645 | +| entropy_loss | -6.45 | +| explained_variance | 0.209 | +| learning_rate | 4e-05 | +| loss | -0.0222 | +| n_updates | 97716 | +| policy_gradient_loss | -0.0136 | +| value_loss | 0.000421 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.17e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1384 | +| iterations | 20476 | +| time_elapsed | 30298 | +| total_timesteps | 41934848 | +| train/ | | +| approx_kl | 0.013650514 | +| clip_fraction | 0.314 | +| clip_range | 0.0645 | +| entropy_loss | -5.69 | +| explained_variance | 0.706 | +| learning_rate | 4e-05 | +| loss | -0.0258 | +| n_updates | 97720 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000115 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1384 | +| iterations | 20477 | +| time_elapsed | 30300 | +| total_timesteps | 41936896 | +| train/ | | +| approx_kl | 0.0106873475 | +| clip_fraction | 0.34 | +| clip_range | 0.0645 | +| entropy_loss | -6.27 | +| explained_variance | -0.135 | +| learning_rate | 4e-05 | +| loss | -0.0373 | +| n_updates | 97724 | +| policy_gradient_loss | -0.0203 | +| value_loss | 7.04e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1384 | +| iterations | 20478 | +| time_elapsed | 30301 | +| total_timesteps | 41938944 | +| train/ | | +| approx_kl | 0.012623791 | +| clip_fraction | 0.338 | +| clip_range | 0.0645 | +| entropy_loss | -5.57 | +| explained_variance | 0.477 | +| learning_rate | 4e-05 | +| loss | -0.0278 | +| n_updates | 97728 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000155 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1384 | +| iterations | 20479 | +| time_elapsed | 30303 | +| total_timesteps | 41940992 | +| train/ | | +| approx_kl | 0.010610068 | +| clip_fraction | 0.332 | +| clip_range | 0.0645 | +| entropy_loss | -5.97 | +| explained_variance | 0.103 | +| learning_rate | 4e-05 | +| loss | -0.0197 | +| n_updates | 97732 | +| policy_gradient_loss | -0.0145 | +| value_loss | 0.000227 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1384 | +| iterations | 20480 | +| time_elapsed | 30304 | +| total_timesteps | 41943040 | +| train/ | | +| approx_kl | 0.01403659 | +| clip_fraction | 0.332 | +| clip_range | 0.0645 | +| entropy_loss | -5.67 | +| explained_variance | 0.52 | +| learning_rate | 4e-05 | +| loss | -0.0276 | +| n_updates | 97736 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000158 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1384 | +| iterations | 20481 | +| time_elapsed | 30306 | +| total_timesteps | 41945088 | +| train/ | | +| approx_kl | 0.013254193 | +| clip_fraction | 0.336 | +| clip_range | 0.0645 | +| entropy_loss | -6.01 | +| explained_variance | 0.209 | +| learning_rate | 4e-05 | +| loss | -0.0281 | +| n_updates | 97740 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000218 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1384 | +| iterations | 20482 | +| time_elapsed | 30308 | +| total_timesteps | 41947136 | +| train/ | | +| approx_kl | 0.011705622 | +| clip_fraction | 0.323 | +| clip_range | 0.0645 | +| entropy_loss | -6.53 | +| explained_variance | 0.435 | +| learning_rate | 4e-05 | +| loss | -0.0309 | +| n_updates | 97744 | +| policy_gradient_loss | -0.0183 | +| value_loss | 7.64e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1384 | +| iterations | 20483 | +| time_elapsed | 30309 | +| total_timesteps | 41949184 | +| train/ | | +| approx_kl | 0.010333832 | +| clip_fraction | 0.299 | +| clip_range | 0.0645 | +| entropy_loss | -6.04 | +| explained_variance | 0.202 | +| learning_rate | 4e-05 | +| loss | -0.0221 | +| n_updates | 97748 | +| policy_gradient_loss | -0.0148 | +| value_loss | 0.000227 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1384 | +| iterations | 20484 | +| time_elapsed | 30311 | +| total_timesteps | 41951232 | +| train/ | | +| approx_kl | 0.013283756 | +| clip_fraction | 0.315 | +| clip_range | 0.0645 | +| entropy_loss | -5.43 | +| explained_variance | 0.613 | +| learning_rate | 4e-05 | +| loss | -0.023 | +| n_updates | 97752 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000133 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1384 | +| iterations | 20485 | +| time_elapsed | 30312 | +| total_timesteps | 41953280 | +| train/ | | +| approx_kl | 0.011112734 | +| clip_fraction | 0.305 | +| clip_range | 0.0645 | +| entropy_loss | -6.03 | +| explained_variance | 0.349 | +| learning_rate | 4e-05 | +| loss | -0.0248 | +| n_updates | 97756 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1384 | +| iterations | 20486 | +| time_elapsed | 30314 | +| total_timesteps | 41955328 | +| train/ | | +| approx_kl | 0.008722488 | +| clip_fraction | 0.283 | +| clip_range | 0.0645 | +| entropy_loss | -6.64 | +| explained_variance | -0.252 | +| learning_rate | 4e-05 | +| loss | -0.0269 | +| n_updates | 97760 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000191 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1384 | +| iterations | 20487 | +| time_elapsed | 30315 | +| total_timesteps | 41957376 | +| train/ | | +| approx_kl | 0.009466445 | +| clip_fraction | 0.289 | +| clip_range | 0.0645 | +| entropy_loss | -5.92 | +| explained_variance | 0.598 | +| learning_rate | 4e-05 | +| loss | -0.0217 | +| n_updates | 97764 | +| policy_gradient_loss | -0.0142 | +| value_loss | 0.000183 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1384 | +| iterations | 20488 | +| time_elapsed | 30317 | +| total_timesteps | 41959424 | +| train/ | | +| approx_kl | 0.013750175 | +| clip_fraction | 0.33 | +| clip_range | 0.0645 | +| entropy_loss | -5.41 | +| explained_variance | 0.724 | +| learning_rate | 4e-05 | +| loss | -0.0293 | +| n_updates | 97768 | +| policy_gradient_loss | -0.0185 | +| value_loss | 9.8e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1383 | +| iterations | 20489 | +| time_elapsed | 30319 | +| total_timesteps | 41961472 | +| train/ | | +| approx_kl | 0.010667473 | +| clip_fraction | 0.327 | +| clip_range | 0.0645 | +| entropy_loss | -6.31 | +| explained_variance | -0.0611 | +| learning_rate | 4e-05 | +| loss | -0.0244 | +| n_updates | 97772 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000184 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1383 | +| iterations | 20490 | +| time_elapsed | 30320 | +| total_timesteps | 41963520 | +| train/ | | +| approx_kl | 0.009613048 | +| clip_fraction | 0.299 | +| clip_range | 0.0645 | +| entropy_loss | -6.2 | +| explained_variance | 0.338 | +| learning_rate | 4e-05 | +| loss | -0.0296 | +| n_updates | 97776 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000149 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1383 | +| iterations | 20491 | +| time_elapsed | 30322 | +| total_timesteps | 41965568 | +| train/ | | +| approx_kl | 0.009164156 | +| clip_fraction | 0.3 | +| clip_range | 0.0645 | +| entropy_loss | -5.94 | +| explained_variance | 0.578 | +| learning_rate | 4e-05 | +| loss | -0.0279 | +| n_updates | 97780 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.00015 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1383 | +| iterations | 20492 | +| time_elapsed | 30323 | +| total_timesteps | 41967616 | +| train/ | | +| approx_kl | 0.011974078 | +| clip_fraction | 0.289 | +| clip_range | 0.0645 | +| entropy_loss | -5.25 | +| explained_variance | 0.588 | +| learning_rate | 4e-05 | +| loss | -0.027 | +| n_updates | 97784 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000116 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1383 | +| iterations | 20493 | +| time_elapsed | 30325 | +| total_timesteps | 41969664 | +| train/ | | +| approx_kl | 0.0151234865 | +| clip_fraction | 0.335 | +| clip_range | 0.0645 | +| entropy_loss | -6.27 | +| explained_variance | 0.0311 | +| learning_rate | 4e-05 | +| loss | -0.0239 | +| n_updates | 97788 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000193 | +------------------------------------------ +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1383 | +| iterations | 20494 | +| time_elapsed | 30326 | +| total_timesteps | 41971712 | +| train/ | | +| approx_kl | 0.0117029 | +| clip_fraction | 0.322 | +| clip_range | 0.0645 | +| entropy_loss | -6.42 | +| explained_variance | 0.448 | +| learning_rate | 4e-05 | +| loss | -0.0279 | +| n_updates | 97792 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000164 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1383 | +| iterations | 20495 | +| time_elapsed | 30328 | +| total_timesteps | 41973760 | +| train/ | | +| approx_kl | 0.0081196 | +| clip_fraction | 0.29 | +| clip_range | 0.0645 | +| entropy_loss | -6.65 | +| explained_variance | 0.403 | +| learning_rate | 4e-05 | +| loss | -0.0233 | +| n_updates | 97796 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000258 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1383 | +| iterations | 20496 | +| time_elapsed | 30330 | +| total_timesteps | 41975808 | +| train/ | | +| approx_kl | 0.009509276 | +| clip_fraction | 0.297 | +| clip_range | 0.0645 | +| entropy_loss | -6.34 | +| explained_variance | 0.275 | +| learning_rate | 4e-05 | +| loss | -0.0279 | +| n_updates | 97800 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000171 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1383 | +| iterations | 20497 | +| time_elapsed | 30331 | +| total_timesteps | 41977856 | +| train/ | | +| approx_kl | 0.01244831 | +| clip_fraction | 0.297 | +| clip_range | 0.0645 | +| entropy_loss | -5.74 | +| explained_variance | 0.611 | +| learning_rate | 4e-05 | +| loss | -0.0198 | +| n_updates | 97804 | +| policy_gradient_loss | -0.0144 | +| value_loss | 0.000139 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1383 | +| iterations | 20498 | +| time_elapsed | 30333 | +| total_timesteps | 41979904 | +| train/ | | +| approx_kl | 0.011294169 | +| clip_fraction | 0.306 | +| clip_range | 0.0645 | +| entropy_loss | -6.29 | +| explained_variance | 0.312 | +| learning_rate | 4e-05 | +| loss | -0.0303 | +| n_updates | 97808 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000135 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1383 | +| iterations | 20499 | +| time_elapsed | 30334 | +| total_timesteps | 41981952 | +| train/ | | +| approx_kl | 0.009305871 | +| clip_fraction | 0.294 | +| clip_range | 0.0645 | +| entropy_loss | -6.08 | +| explained_variance | 0.402 | +| learning_rate | 4e-05 | +| loss | -0.0235 | +| n_updates | 97812 | +| policy_gradient_loss | -0.0147 | +| value_loss | 0.000265 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1383 | +| iterations | 20500 | +| time_elapsed | 30336 | +| total_timesteps | 41984000 | +| train/ | | +| approx_kl | 0.012974504 | +| clip_fraction | 0.302 | +| clip_range | 0.0645 | +| entropy_loss | -6.56 | +| explained_variance | 0.0783 | +| learning_rate | 4e-05 | +| loss | -0.0306 | +| n_updates | 97816 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.00012 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1383 | +| iterations | 20501 | +| time_elapsed | 30337 | +| total_timesteps | 41986048 | +| train/ | | +| approx_kl | 0.008971498 | +| clip_fraction | 0.289 | +| clip_range | 0.0645 | +| entropy_loss | -6.72 | +| explained_variance | 0.339 | +| learning_rate | 4e-05 | +| loss | -0.0286 | +| n_updates | 97820 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000101 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1383 | +| iterations | 20502 | +| time_elapsed | 30339 | +| total_timesteps | 41988096 | +| train/ | | +| approx_kl | 0.010008478 | +| clip_fraction | 0.3 | +| clip_range | 0.0645 | +| entropy_loss | -5.89 | +| explained_variance | 0.38 | +| learning_rate | 4e-05 | +| loss | -0.0186 | +| n_updates | 97824 | +| policy_gradient_loss | -0.0138 | +| value_loss | 0.000422 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1383 | +| iterations | 20503 | +| time_elapsed | 30341 | +| total_timesteps | 41990144 | +| train/ | | +| approx_kl | 0.013640237 | +| clip_fraction | 0.349 | +| clip_range | 0.0645 | +| entropy_loss | -5.98 | +| explained_variance | 0.307 | +| learning_rate | 4e-05 | +| loss | -0.0308 | +| n_updates | 97828 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000101 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1383 | +| iterations | 20504 | +| time_elapsed | 30342 | +| total_timesteps | 41992192 | +| train/ | | +| approx_kl | 0.012251662 | +| clip_fraction | 0.311 | +| clip_range | 0.0645 | +| entropy_loss | -5.68 | +| explained_variance | 0.582 | +| learning_rate | 4e-05 | +| loss | -0.0254 | +| n_updates | 97832 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000164 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1383 | +| iterations | 20505 | +| time_elapsed | 30344 | +| total_timesteps | 41994240 | +| train/ | | +| approx_kl | 0.014386775 | +| clip_fraction | 0.339 | +| clip_range | 0.0645 | +| entropy_loss | -5.45 | +| explained_variance | -0.171 | +| learning_rate | 4e-05 | +| loss | -0.0324 | +| n_updates | 97836 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000139 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1383 | +| iterations | 20506 | +| time_elapsed | 30345 | +| total_timesteps | 41996288 | +| train/ | | +| approx_kl | 0.0103859985 | +| clip_fraction | 0.333 | +| clip_range | 0.0645 | +| entropy_loss | -6.34 | +| explained_variance | 0.124 | +| learning_rate | 4e-05 | +| loss | -0.0258 | +| n_updates | 97840 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000121 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1383 | +| iterations | 20507 | +| time_elapsed | 30347 | +| total_timesteps | 41998336 | +| train/ | | +| approx_kl | 0.011241428 | +| clip_fraction | 0.315 | +| clip_range | 0.0645 | +| entropy_loss | -6.38 | +| explained_variance | 0.419 | +| learning_rate | 4e-05 | +| loss | -0.0295 | +| n_updates | 97844 | +| policy_gradient_loss | -0.017 | +| value_loss | 9.77e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1383 | +| iterations | 20508 | +| time_elapsed | 30348 | +| total_timesteps | 42000384 | +| train/ | | +| approx_kl | 0.010976605 | +| clip_fraction | 0.303 | +| clip_range | 0.0645 | +| entropy_loss | -5.93 | +| explained_variance | 0.556 | +| learning_rate | 4e-05 | +| loss | -0.0272 | +| n_updates | 97848 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000158 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1383 | +| iterations | 20509 | +| time_elapsed | 30350 | +| total_timesteps | 42002432 | +| train/ | | +| approx_kl | 0.009641816 | +| clip_fraction | 0.289 | +| clip_range | 0.0645 | +| entropy_loss | -6.31 | +| explained_variance | -0.00527 | +| learning_rate | 4e-05 | +| loss | -0.0228 | +| n_updates | 97852 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000198 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1383 | +| iterations | 20510 | +| time_elapsed | 30351 | +| total_timesteps | 42004480 | +| train/ | | +| approx_kl | 0.010698415 | +| clip_fraction | 0.305 | +| clip_range | 0.0645 | +| entropy_loss | -6.07 | +| explained_variance | 0.438 | +| learning_rate | 4e-05 | +| loss | -0.0248 | +| n_updates | 97856 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000119 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1383 | +| iterations | 20511 | +| time_elapsed | 30353 | +| total_timesteps | 42006528 | +| train/ | | +| approx_kl | 0.00965724 | +| clip_fraction | 0.328 | +| clip_range | 0.0645 | +| entropy_loss | -6.02 | +| explained_variance | 0.404 | +| learning_rate | 4e-05 | +| loss | -0.0257 | +| n_updates | 97860 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000123 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1383 | +| iterations | 20512 | +| time_elapsed | 30355 | +| total_timesteps | 42008576 | +| train/ | | +| approx_kl | 0.0084410235 | +| clip_fraction | 0.287 | +| clip_range | 0.0645 | +| entropy_loss | -6.34 | +| explained_variance | 0.346 | +| learning_rate | 4e-05 | +| loss | -0.0263 | +| n_updates | 97864 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000156 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1383 | +| iterations | 20513 | +| time_elapsed | 30356 | +| total_timesteps | 42010624 | +| train/ | | +| approx_kl | 0.011842659 | +| clip_fraction | 0.306 | +| clip_range | 0.0645 | +| entropy_loss | -5.99 | +| explained_variance | 0.742 | +| learning_rate | 4e-05 | +| loss | -0.025 | +| n_updates | 97868 | +| policy_gradient_loss | -0.0168 | +| value_loss | 8.15e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1383 | +| iterations | 20514 | +| time_elapsed | 30358 | +| total_timesteps | 42012672 | +| train/ | | +| approx_kl | 0.012457554 | +| clip_fraction | 0.315 | +| clip_range | 0.0645 | +| entropy_loss | -6.09 | +| explained_variance | 0.78 | +| learning_rate | 4e-05 | +| loss | -0.0313 | +| n_updates | 97872 | +| policy_gradient_loss | -0.0213 | +| value_loss | 4.8e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1383 | +| iterations | 20515 | +| time_elapsed | 30359 | +| total_timesteps | 42014720 | +| train/ | | +| approx_kl | 0.0076313964 | +| clip_fraction | 0.302 | +| clip_range | 0.0645 | +| entropy_loss | -5.77 | +| explained_variance | 0.485 | +| learning_rate | 4e-05 | +| loss | -0.0191 | +| n_updates | 97876 | +| policy_gradient_loss | -0.0132 | +| value_loss | 0.00023 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1383 | +| iterations | 20516 | +| time_elapsed | 30361 | +| total_timesteps | 42016768 | +| train/ | | +| approx_kl | 0.0151504185 | +| clip_fraction | 0.33 | +| clip_range | 0.0645 | +| entropy_loss | -5.03 | +| explained_variance | 0.786 | +| learning_rate | 4e-05 | +| loss | -0.0298 | +| n_updates | 97880 | +| policy_gradient_loss | -0.0182 | +| value_loss | 9.54e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1383 | +| iterations | 20517 | +| time_elapsed | 30362 | +| total_timesteps | 42018816 | +| train/ | | +| approx_kl | 0.017339699 | +| clip_fraction | 0.312 | +| clip_range | 0.0645 | +| entropy_loss | -5.95 | +| explained_variance | -0.213 | +| learning_rate | 4e-05 | +| loss | -0.0298 | +| n_updates | 97884 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000121 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1383 | +| iterations | 20518 | +| time_elapsed | 30364 | +| total_timesteps | 42020864 | +| train/ | | +| approx_kl | 0.014759917 | +| clip_fraction | 0.319 | +| clip_range | 0.0645 | +| entropy_loss | -5.96 | +| explained_variance | 0.45 | +| learning_rate | 4e-05 | +| loss | -0.028 | +| n_updates | 97888 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000166 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1383 | +| iterations | 20519 | +| time_elapsed | 30365 | +| total_timesteps | 42022912 | +| train/ | | +| approx_kl | 0.013187384 | +| clip_fraction | 0.338 | +| clip_range | 0.0645 | +| entropy_loss | -6.3 | +| explained_variance | -0.0768 | +| learning_rate | 4e-05 | +| loss | -0.0298 | +| n_updates | 97892 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000149 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1383 | +| iterations | 20520 | +| time_elapsed | 30367 | +| total_timesteps | 42024960 | +| train/ | | +| approx_kl | 0.0119145885 | +| clip_fraction | 0.358 | +| clip_range | 0.0645 | +| entropy_loss | -6.38 | +| explained_variance | 0.518 | +| learning_rate | 4e-05 | +| loss | -0.0342 | +| n_updates | 97896 | +| policy_gradient_loss | -0.0207 | +| value_loss | 4.65e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1383 | +| iterations | 20521 | +| time_elapsed | 30368 | +| total_timesteps | 42027008 | +| train/ | | +| approx_kl | 0.012337292 | +| clip_fraction | 0.293 | +| clip_range | 0.0645 | +| entropy_loss | -6.34 | +| explained_variance | 0.401 | +| learning_rate | 4e-05 | +| loss | -0.029 | +| n_updates | 97900 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000193 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1383 | +| iterations | 20522 | +| time_elapsed | 30370 | +| total_timesteps | 42029056 | +| train/ | | +| approx_kl | 0.011635786 | +| clip_fraction | 0.345 | +| clip_range | 0.0645 | +| entropy_loss | -5.82 | +| explained_variance | 0.339 | +| learning_rate | 4e-05 | +| loss | -0.0298 | +| n_updates | 97904 | +| policy_gradient_loss | -0.0189 | +| value_loss | 8.15e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1383 | +| iterations | 20523 | +| time_elapsed | 30372 | +| total_timesteps | 42031104 | +| train/ | | +| approx_kl | 0.011288369 | +| clip_fraction | 0.271 | +| clip_range | 0.0645 | +| entropy_loss | -5.11 | +| explained_variance | 0.781 | +| learning_rate | 4e-05 | +| loss | -0.0238 | +| n_updates | 97908 | +| policy_gradient_loss | -0.0142 | +| value_loss | 9.72e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1383 | +| iterations | 20524 | +| time_elapsed | 30373 | +| total_timesteps | 42033152 | +| train/ | | +| approx_kl | 0.011036819 | +| clip_fraction | 0.329 | +| clip_range | 0.0645 | +| entropy_loss | -4.65 | +| explained_variance | 0.669 | +| learning_rate | 4e-05 | +| loss | -0.0278 | +| n_updates | 97912 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000131 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1383 | +| iterations | 20525 | +| time_elapsed | 30375 | +| total_timesteps | 42035200 | +| train/ | | +| approx_kl | 0.012338092 | +| clip_fraction | 0.323 | +| clip_range | 0.0645 | +| entropy_loss | -5.52 | +| explained_variance | 0.593 | +| learning_rate | 4e-05 | +| loss | -0.0232 | +| n_updates | 97916 | +| policy_gradient_loss | -0.0145 | +| value_loss | 0.000179 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1383 | +| iterations | 20526 | +| time_elapsed | 30376 | +| total_timesteps | 42037248 | +| train/ | | +| approx_kl | 0.010885306 | +| clip_fraction | 0.322 | +| clip_range | 0.0645 | +| entropy_loss | -6.42 | +| explained_variance | 0.292 | +| learning_rate | 4e-05 | +| loss | -0.0288 | +| n_updates | 97920 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.00015 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1383 | +| iterations | 20527 | +| time_elapsed | 30378 | +| total_timesteps | 42039296 | +| train/ | | +| approx_kl | 0.011713311 | +| clip_fraction | 0.359 | +| clip_range | 0.0645 | +| entropy_loss | -6.65 | +| explained_variance | -0.475 | +| learning_rate | 4e-05 | +| loss | -0.0368 | +| n_updates | 97924 | +| policy_gradient_loss | -0.0222 | +| value_loss | 7.49e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1383 | +| iterations | 20528 | +| time_elapsed | 30379 | +| total_timesteps | 42041344 | +| train/ | | +| approx_kl | 0.009976743 | +| clip_fraction | 0.275 | +| clip_range | 0.0645 | +| entropy_loss | -5.38 | +| explained_variance | 0.302 | +| learning_rate | 4e-05 | +| loss | -0.0231 | +| n_updates | 97928 | +| policy_gradient_loss | -0.012 | +| value_loss | 0.00033 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1383 | +| iterations | 20529 | +| time_elapsed | 30381 | +| total_timesteps | 42043392 | +| train/ | | +| approx_kl | 0.013970772 | +| clip_fraction | 0.339 | +| clip_range | 0.0645 | +| entropy_loss | -5.59 | +| explained_variance | 0.293 | +| learning_rate | 4e-05 | +| loss | -0.0325 | +| n_updates | 97932 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000152 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1383 | +| iterations | 20530 | +| time_elapsed | 30383 | +| total_timesteps | 42045440 | +| train/ | | +| approx_kl | 0.011479809 | +| clip_fraction | 0.307 | +| clip_range | 0.0645 | +| entropy_loss | -5.95 | +| explained_variance | 0.343 | +| learning_rate | 4e-05 | +| loss | -0.0263 | +| n_updates | 97936 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.000221 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1383 | +| iterations | 20531 | +| time_elapsed | 30384 | +| total_timesteps | 42047488 | +| train/ | | +| approx_kl | 0.012064037 | +| clip_fraction | 0.318 | +| clip_range | 0.0645 | +| entropy_loss | -5.09 | +| explained_variance | 0.601 | +| learning_rate | 4e-05 | +| loss | -0.0276 | +| n_updates | 97940 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000234 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1383 | +| iterations | 20532 | +| time_elapsed | 30386 | +| total_timesteps | 42049536 | +| train/ | | +| approx_kl | 0.014186438 | +| clip_fraction | 0.364 | +| clip_range | 0.0645 | +| entropy_loss | -5.87 | +| explained_variance | 0.366 | +| learning_rate | 4e-05 | +| loss | -0.0327 | +| n_updates | 97944 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000116 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1383 | +| iterations | 20533 | +| time_elapsed | 30387 | +| total_timesteps | 42051584 | +| train/ | | +| approx_kl | 0.015693448 | +| clip_fraction | 0.356 | +| clip_range | 0.0645 | +| entropy_loss | -5.99 | +| explained_variance | 0.406 | +| learning_rate | 4e-05 | +| loss | -0.0356 | +| n_updates | 97948 | +| policy_gradient_loss | -0.0216 | +| value_loss | 6.65e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1383 | +| iterations | 20534 | +| time_elapsed | 30389 | +| total_timesteps | 42053632 | +| train/ | | +| approx_kl | 0.012816437 | +| clip_fraction | 0.379 | +| clip_range | 0.0645 | +| entropy_loss | -6.01 | +| explained_variance | 0.583 | +| learning_rate | 4e-05 | +| loss | -0.0381 | +| n_updates | 97952 | +| policy_gradient_loss | -0.0229 | +| value_loss | 5.16e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1383 | +| iterations | 20535 | +| time_elapsed | 30390 | +| total_timesteps | 42055680 | +| train/ | | +| approx_kl | 0.0133789405 | +| clip_fraction | 0.295 | +| clip_range | 0.0645 | +| entropy_loss | -6.44 | +| explained_variance | 0.306 | +| learning_rate | 4e-05 | +| loss | -0.0287 | +| n_updates | 97956 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000142 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1383 | +| iterations | 20536 | +| time_elapsed | 30392 | +| total_timesteps | 42057728 | +| train/ | | +| approx_kl | 0.01247106 | +| clip_fraction | 0.304 | +| clip_range | 0.0645 | +| entropy_loss | -6.23 | +| explained_variance | 0.467 | +| learning_rate | 4e-05 | +| loss | -0.0274 | +| n_updates | 97960 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000179 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1383 | +| iterations | 20537 | +| time_elapsed | 30393 | +| total_timesteps | 42059776 | +| train/ | | +| approx_kl | 0.015701601 | +| clip_fraction | 0.338 | +| clip_range | 0.0645 | +| entropy_loss | -5.64 | +| explained_variance | 0.526 | +| learning_rate | 4e-05 | +| loss | -0.0201 | +| n_updates | 97964 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000134 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1383 | +| iterations | 20538 | +| time_elapsed | 30395 | +| total_timesteps | 42061824 | +| train/ | | +| approx_kl | 0.012574952 | +| clip_fraction | 0.326 | +| clip_range | 0.0645 | +| entropy_loss | -5.77 | +| explained_variance | 0.47 | +| learning_rate | 4e-05 | +| loss | -0.0227 | +| n_updates | 97968 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000137 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1383 | +| iterations | 20539 | +| time_elapsed | 30397 | +| total_timesteps | 42063872 | +| train/ | | +| approx_kl | 0.012551663 | +| clip_fraction | 0.332 | +| clip_range | 0.0645 | +| entropy_loss | -5.9 | +| explained_variance | 0.611 | +| learning_rate | 4e-05 | +| loss | -0.0278 | +| n_updates | 97972 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000126 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.302 | +| time/ | | +| fps | 1383 | +| iterations | 20540 | +| time_elapsed | 30398 | +| total_timesteps | 42065920 | +| train/ | | +| approx_kl | 0.016435543 | +| clip_fraction | 0.353 | +| clip_range | 0.0645 | +| entropy_loss | -5.31 | +| explained_variance | 0.592 | +| learning_rate | 4e-05 | +| loss | -0.0253 | +| n_updates | 97976 | +| policy_gradient_loss | -0.0169 | +| value_loss | 7.66e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.304 | +| time/ | | +| fps | 1383 | +| iterations | 20541 | +| time_elapsed | 30399 | +| total_timesteps | 42067968 | +| train/ | | +| approx_kl | 0.013406059 | +| clip_fraction | 0.315 | +| clip_range | 0.0645 | +| entropy_loss | -5.47 | +| explained_variance | 0.429 | +| learning_rate | 4e-05 | +| loss | -0.0231 | +| n_updates | 97980 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000207 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 1383 | +| iterations | 20542 | +| time_elapsed | 30401 | +| total_timesteps | 42070016 | +| train/ | | +| approx_kl | 0.013320683 | +| clip_fraction | 0.319 | +| clip_range | 0.0645 | +| entropy_loss | -5.73 | +| explained_variance | 0.228 | +| learning_rate | 4e-05 | +| loss | -0.021 | +| n_updates | 97984 | +| policy_gradient_loss | -0.0136 | +| value_loss | 0.000274 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 1383 | +| iterations | 20543 | +| time_elapsed | 30402 | +| total_timesteps | 42072064 | +| train/ | | +| approx_kl | 0.011706976 | +| clip_fraction | 0.349 | +| clip_range | 0.0645 | +| entropy_loss | -5.76 | +| explained_variance | 0.0902 | +| learning_rate | 4e-05 | +| loss | -0.0329 | +| n_updates | 97988 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000287 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 1383 | +| iterations | 20544 | +| time_elapsed | 30404 | +| total_timesteps | 42074112 | +| train/ | | +| approx_kl | 0.0121429805 | +| clip_fraction | 0.297 | +| clip_range | 0.0645 | +| entropy_loss | -5.49 | +| explained_variance | 0.497 | +| learning_rate | 4e-05 | +| loss | -0.0242 | +| n_updates | 97992 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.000342 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 1383 | +| iterations | 20545 | +| time_elapsed | 30405 | +| total_timesteps | 42076160 | +| train/ | | +| approx_kl | 0.016723325 | +| clip_fraction | 0.324 | +| clip_range | 0.0645 | +| entropy_loss | -5.62 | +| explained_variance | 0.0112 | +| learning_rate | 4e-05 | +| loss | -0.0268 | +| n_updates | 97996 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000162 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 1383 | +| iterations | 20546 | +| time_elapsed | 30407 | +| total_timesteps | 42078208 | +| train/ | | +| approx_kl | 0.013335454 | +| clip_fraction | 0.351 | +| clip_range | 0.0645 | +| entropy_loss | -6.25 | +| explained_variance | -1.33 | +| learning_rate | 4e-05 | +| loss | -0.0347 | +| n_updates | 98000 | +| policy_gradient_loss | -0.0209 | +| value_loss | 6.57e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.3 | +| time/ | | +| fps | 1383 | +| iterations | 20547 | +| time_elapsed | 30408 | +| total_timesteps | 42080256 | +| train/ | | +| approx_kl | 0.009680574 | +| clip_fraction | 0.329 | +| clip_range | 0.0645 | +| entropy_loss | -6.52 | +| explained_variance | -0.103 | +| learning_rate | 4e-05 | +| loss | -0.0289 | +| n_updates | 98004 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000101 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.3 | +| time/ | | +| fps | 1383 | +| iterations | 20548 | +| time_elapsed | 30410 | +| total_timesteps | 42082304 | +| train/ | | +| approx_kl | 0.01005098 | +| clip_fraction | 0.285 | +| clip_range | 0.0645 | +| entropy_loss | -6.52 | +| explained_variance | 0.168 | +| learning_rate | 4e-05 | +| loss | -0.0237 | +| n_updates | 98008 | +| policy_gradient_loss | -0.0134 | +| value_loss | 0.000229 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.304 | +| time/ | | +| fps | 1383 | +| iterations | 20549 | +| time_elapsed | 30411 | +| total_timesteps | 42084352 | +| train/ | | +| approx_kl | 0.009753474 | +| clip_fraction | 0.315 | +| clip_range | 0.0645 | +| entropy_loss | -6.29 | +| explained_variance | 0.513 | +| learning_rate | 4e-05 | +| loss | -0.0259 | +| n_updates | 98012 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.00012 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.304 | +| time/ | | +| fps | 1383 | +| iterations | 20550 | +| time_elapsed | 30413 | +| total_timesteps | 42086400 | +| train/ | | +| approx_kl | 0.010579625 | +| clip_fraction | 0.33 | +| clip_range | 0.0645 | +| entropy_loss | -6.41 | +| explained_variance | -0.181 | +| learning_rate | 4e-05 | +| loss | -0.0348 | +| n_updates | 98016 | +| policy_gradient_loss | -0.018 | +| value_loss | 9.32e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1383 | +| iterations | 20551 | +| time_elapsed | 30414 | +| total_timesteps | 42088448 | +| train/ | | +| approx_kl | 0.0122680925 | +| clip_fraction | 0.31 | +| clip_range | 0.0645 | +| entropy_loss | -5.72 | +| explained_variance | 0.767 | +| learning_rate | 4e-05 | +| loss | -0.0286 | +| n_updates | 98020 | +| policy_gradient_loss | -0.0162 | +| value_loss | 9.72e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1383 | +| iterations | 20552 | +| time_elapsed | 30416 | +| total_timesteps | 42090496 | +| train/ | | +| approx_kl | 0.009564345 | +| clip_fraction | 0.291 | +| clip_range | 0.0645 | +| entropy_loss | -4.86 | +| explained_variance | 0.556 | +| learning_rate | 4e-05 | +| loss | -0.0234 | +| n_updates | 98024 | +| policy_gradient_loss | -0.0136 | +| value_loss | 0.000244 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1383 | +| iterations | 20553 | +| time_elapsed | 30418 | +| total_timesteps | 42092544 | +| train/ | | +| approx_kl | 0.013286363 | +| clip_fraction | 0.351 | +| clip_range | 0.0645 | +| entropy_loss | -5.15 | +| explained_variance | 0.702 | +| learning_rate | 4e-05 | +| loss | -0.0314 | +| n_updates | 98028 | +| policy_gradient_loss | -0.0198 | +| value_loss | 8.93e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1383 | +| iterations | 20554 | +| time_elapsed | 30419 | +| total_timesteps | 42094592 | +| train/ | | +| approx_kl | 0.01280256 | +| clip_fraction | 0.335 | +| clip_range | 0.0645 | +| entropy_loss | -5.97 | +| explained_variance | 0.431 | +| learning_rate | 4e-05 | +| loss | -0.0315 | +| n_updates | 98032 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000106 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.306 | +| time/ | | +| fps | 1383 | +| iterations | 20555 | +| time_elapsed | 30421 | +| total_timesteps | 42096640 | +| train/ | | +| approx_kl | 0.014248438 | +| clip_fraction | 0.342 | +| clip_range | 0.0645 | +| entropy_loss | -6.41 | +| explained_variance | -0.0687 | +| learning_rate | 4e-05 | +| loss | -0.0301 | +| n_updates | 98036 | +| policy_gradient_loss | -0.0187 | +| value_loss | 6.87e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1383 | +| iterations | 20556 | +| time_elapsed | 30422 | +| total_timesteps | 42098688 | +| train/ | | +| approx_kl | 0.009759057 | +| clip_fraction | 0.326 | +| clip_range | 0.0645 | +| entropy_loss | -6.82 | +| explained_variance | 0.402 | +| learning_rate | 4e-05 | +| loss | -0.0242 | +| n_updates | 98040 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000132 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1383 | +| iterations | 20557 | +| time_elapsed | 30424 | +| total_timesteps | 42100736 | +| train/ | | +| approx_kl | 0.007873375 | +| clip_fraction | 0.278 | +| clip_range | 0.0645 | +| entropy_loss | -6.45 | +| explained_variance | 0.0961 | +| learning_rate | 4e-05 | +| loss | -0.0186 | +| n_updates | 98044 | +| policy_gradient_loss | -0.0109 | +| value_loss | 0.000375 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 1383 | +| iterations | 20558 | +| time_elapsed | 30425 | +| total_timesteps | 42102784 | +| train/ | | +| approx_kl | 0.009248002 | +| clip_fraction | 0.296 | +| clip_range | 0.0645 | +| entropy_loss | -5.5 | +| explained_variance | 0.646 | +| learning_rate | 4e-05 | +| loss | -0.0282 | +| n_updates | 98048 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000146 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.301 | +| time/ | | +| fps | 1383 | +| iterations | 20559 | +| time_elapsed | 30427 | +| total_timesteps | 42104832 | +| train/ | | +| approx_kl | 0.009097625 | +| clip_fraction | 0.314 | +| clip_range | 0.0645 | +| entropy_loss | -5.79 | +| explained_variance | 0.408 | +| learning_rate | 4e-05 | +| loss | -0.0265 | +| n_updates | 98052 | +| policy_gradient_loss | -0.0144 | +| value_loss | 0.000249 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 1383 | +| iterations | 20560 | +| time_elapsed | 30428 | +| total_timesteps | 42106880 | +| train/ | | +| approx_kl | 0.012425569 | +| clip_fraction | 0.334 | +| clip_range | 0.0645 | +| entropy_loss | -5.09 | +| explained_variance | 0.63 | +| learning_rate | 4e-05 | +| loss | -0.0309 | +| n_updates | 98056 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000134 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 1383 | +| iterations | 20561 | +| time_elapsed | 30430 | +| total_timesteps | 42108928 | +| train/ | | +| approx_kl | 0.011064462 | +| clip_fraction | 0.341 | +| clip_range | 0.0645 | +| entropy_loss | -5.79 | +| explained_variance | 0.439 | +| learning_rate | 4e-05 | +| loss | -0.0306 | +| n_updates | 98060 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000106 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 1383 | +| iterations | 20562 | +| time_elapsed | 30432 | +| total_timesteps | 42110976 | +| train/ | | +| approx_kl | 0.016219024 | +| clip_fraction | 0.303 | +| clip_range | 0.0645 | +| entropy_loss | -6.52 | +| explained_variance | -0.171 | +| learning_rate | 4e-05 | +| loss | -0.023 | +| n_updates | 98064 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000107 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.293 | +| time/ | | +| fps | 1383 | +| iterations | 20563 | +| time_elapsed | 30433 | +| total_timesteps | 42113024 | +| train/ | | +| approx_kl | 0.014036833 | +| clip_fraction | 0.33 | +| clip_range | 0.0645 | +| entropy_loss | -5.69 | +| explained_variance | 0.293 | +| learning_rate | 4e-05 | +| loss | -0.0241 | +| n_updates | 98068 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.000202 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 1383 | +| iterations | 20564 | +| time_elapsed | 30435 | +| total_timesteps | 42115072 | +| train/ | | +| approx_kl | 0.0133713875 | +| clip_fraction | 0.339 | +| clip_range | 0.0645 | +| entropy_loss | -5.63 | +| explained_variance | 0.577 | +| learning_rate | 4e-05 | +| loss | -0.0291 | +| n_updates | 98072 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000158 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 1383 | +| iterations | 20565 | +| time_elapsed | 30436 | +| total_timesteps | 42117120 | +| train/ | | +| approx_kl | 0.012476223 | +| clip_fraction | 0.334 | +| clip_range | 0.0645 | +| entropy_loss | -4.92 | +| explained_variance | 0.468 | +| learning_rate | 4e-05 | +| loss | -0.025 | +| n_updates | 98076 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000312 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.295 | +| time/ | | +| fps | 1383 | +| iterations | 20566 | +| time_elapsed | 30438 | +| total_timesteps | 42119168 | +| train/ | | +| approx_kl | 0.016246445 | +| clip_fraction | 0.322 | +| clip_range | 0.0645 | +| entropy_loss | -5.75 | +| explained_variance | -0.206 | +| learning_rate | 4e-05 | +| loss | -0.0362 | +| n_updates | 98080 | +| policy_gradient_loss | -0.0195 | +| value_loss | 9.86e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.296 | +| time/ | | +| fps | 1383 | +| iterations | 20567 | +| time_elapsed | 30439 | +| total_timesteps | 42121216 | +| train/ | | +| approx_kl | 0.013899071 | +| clip_fraction | 0.355 | +| clip_range | 0.0645 | +| entropy_loss | -6.03 | +| explained_variance | 0.164 | +| learning_rate | 4e-05 | +| loss | -0.029 | +| n_updates | 98084 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000188 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.295 | +| time/ | | +| fps | 1383 | +| iterations | 20568 | +| time_elapsed | 30441 | +| total_timesteps | 42123264 | +| train/ | | +| approx_kl | 0.012554854 | +| clip_fraction | 0.347 | +| clip_range | 0.0645 | +| entropy_loss | -5.61 | +| explained_variance | 0.446 | +| learning_rate | 4e-05 | +| loss | -0.023 | +| n_updates | 98088 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.000263 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 1383 | +| iterations | 20569 | +| time_elapsed | 30442 | +| total_timesteps | 42125312 | +| train/ | | +| approx_kl | 0.019164342 | +| clip_fraction | 0.35 | +| clip_range | 0.0645 | +| entropy_loss | -6.09 | +| explained_variance | -0.0266 | +| learning_rate | 4e-05 | +| loss | -0.0371 | +| n_updates | 98092 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000112 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 1383 | +| iterations | 20570 | +| time_elapsed | 30444 | +| total_timesteps | 42127360 | +| train/ | | +| approx_kl | 0.009630453 | +| clip_fraction | 0.285 | +| clip_range | 0.0645 | +| entropy_loss | -5.74 | +| explained_variance | 0.463 | +| learning_rate | 4e-05 | +| loss | -0.0235 | +| n_updates | 98096 | +| policy_gradient_loss | -0.0138 | +| value_loss | 0.000275 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 1383 | +| iterations | 20571 | +| time_elapsed | 30445 | +| total_timesteps | 42129408 | +| train/ | | +| approx_kl | 0.0118450355 | +| clip_fraction | 0.317 | +| clip_range | 0.0645 | +| entropy_loss | -5.89 | +| explained_variance | 0.25 | +| learning_rate | 4e-05 | +| loss | -0.0299 | +| n_updates | 98100 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000162 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 1383 | +| iterations | 20572 | +| time_elapsed | 30447 | +| total_timesteps | 42131456 | +| train/ | | +| approx_kl | 0.014398275 | +| clip_fraction | 0.355 | +| clip_range | 0.0645 | +| entropy_loss | -5.82 | +| explained_variance | -0.0613 | +| learning_rate | 4e-05 | +| loss | -0.0295 | +| n_updates | 98104 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000154 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 1383 | +| iterations | 20573 | +| time_elapsed | 30448 | +| total_timesteps | 42133504 | +| train/ | | +| approx_kl | 0.012907565 | +| clip_fraction | 0.335 | +| clip_range | 0.0645 | +| entropy_loss | -5.93 | +| explained_variance | 0.305 | +| learning_rate | 4e-05 | +| loss | -0.031 | +| n_updates | 98108 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.00017 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.295 | +| time/ | | +| fps | 1383 | +| iterations | 20574 | +| time_elapsed | 30450 | +| total_timesteps | 42135552 | +| train/ | | +| approx_kl | 0.011041149 | +| clip_fraction | 0.335 | +| clip_range | 0.0645 | +| entropy_loss | -6.33 | +| explained_variance | 0.335 | +| learning_rate | 4e-05 | +| loss | -0.0271 | +| n_updates | 98112 | +| policy_gradient_loss | -0.0184 | +| value_loss | 9.66e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.29 | +| time/ | | +| fps | 1383 | +| iterations | 20575 | +| time_elapsed | 30452 | +| total_timesteps | 42137600 | +| train/ | | +| approx_kl | 0.01189358 | +| clip_fraction | 0.297 | +| clip_range | 0.0645 | +| entropy_loss | -5.39 | +| explained_variance | 0.72 | +| learning_rate | 4e-05 | +| loss | -0.0261 | +| n_updates | 98116 | +| policy_gradient_loss | -0.0165 | +| value_loss | 8.93e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.289 | +| time/ | | +| fps | 1383 | +| iterations | 20576 | +| time_elapsed | 30453 | +| total_timesteps | 42139648 | +| train/ | | +| approx_kl | 0.012598518 | +| clip_fraction | 0.331 | +| clip_range | 0.0645 | +| entropy_loss | -5.35 | +| explained_variance | 0.815 | +| learning_rate | 4e-05 | +| loss | -0.0303 | +| n_updates | 98120 | +| policy_gradient_loss | -0.0191 | +| value_loss | 5.13e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.287 | +| time/ | | +| fps | 1383 | +| iterations | 20577 | +| time_elapsed | 30455 | +| total_timesteps | 42141696 | +| train/ | | +| approx_kl | 0.009285441 | +| clip_fraction | 0.292 | +| clip_range | 0.0645 | +| entropy_loss | -6.55 | +| explained_variance | 0.35 | +| learning_rate | 4e-05 | +| loss | -0.0202 | +| n_updates | 98124 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.00011 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.288 | +| time/ | | +| fps | 1383 | +| iterations | 20578 | +| time_elapsed | 30456 | +| total_timesteps | 42143744 | +| train/ | | +| approx_kl | 0.01159413 | +| clip_fraction | 0.282 | +| clip_range | 0.0645 | +| entropy_loss | -5.99 | +| explained_variance | 0.63 | +| learning_rate | 4e-05 | +| loss | -0.0249 | +| n_updates | 98128 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000149 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.294 | +| time/ | | +| fps | 1383 | +| iterations | 20579 | +| time_elapsed | 30458 | +| total_timesteps | 42145792 | +| train/ | | +| approx_kl | 0.012099223 | +| clip_fraction | 0.304 | +| clip_range | 0.0645 | +| entropy_loss | -5.88 | +| explained_variance | 0.545 | +| learning_rate | 4e-05 | +| loss | -0.0269 | +| n_updates | 98132 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000132 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.294 | +| time/ | | +| fps | 1383 | +| iterations | 20580 | +| time_elapsed | 30460 | +| total_timesteps | 42147840 | +| train/ | | +| approx_kl | 0.011854751 | +| clip_fraction | 0.302 | +| clip_range | 0.0645 | +| entropy_loss | -6.31 | +| explained_variance | 0.326 | +| learning_rate | 4e-05 | +| loss | -0.0203 | +| n_updates | 98136 | +| policy_gradient_loss | -0.0141 | +| value_loss | 0.000371 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.299 | +| time/ | | +| fps | 1383 | +| iterations | 20581 | +| time_elapsed | 30461 | +| total_timesteps | 42149888 | +| train/ | | +| approx_kl | 0.01361496 | +| clip_fraction | 0.315 | +| clip_range | 0.0645 | +| entropy_loss | -5.86 | +| explained_variance | 0.469 | +| learning_rate | 4e-05 | +| loss | -0.0333 | +| n_updates | 98140 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000149 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1383 | +| iterations | 20582 | +| time_elapsed | 30463 | +| total_timesteps | 42151936 | +| train/ | | +| approx_kl | 0.0129381195 | +| clip_fraction | 0.334 | +| clip_range | 0.0645 | +| entropy_loss | -5.84 | +| explained_variance | -0.14 | +| learning_rate | 4e-05 | +| loss | -0.0253 | +| n_updates | 98144 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000241 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.304 | +| time/ | | +| fps | 1383 | +| iterations | 20583 | +| time_elapsed | 30464 | +| total_timesteps | 42153984 | +| train/ | | +| approx_kl | 0.012975412 | +| clip_fraction | 0.305 | +| clip_range | 0.0645 | +| entropy_loss | -5.32 | +| explained_variance | 0.472 | +| learning_rate | 4e-05 | +| loss | -0.0187 | +| n_updates | 98148 | +| policy_gradient_loss | -0.0121 | +| value_loss | 0.000311 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.304 | +| time/ | | +| fps | 1383 | +| iterations | 20584 | +| time_elapsed | 30466 | +| total_timesteps | 42156032 | +| train/ | | +| approx_kl | 0.013726927 | +| clip_fraction | 0.356 | +| clip_range | 0.0645 | +| entropy_loss | -5.72 | +| explained_variance | 0.0845 | +| learning_rate | 4e-05 | +| loss | -0.0325 | +| n_updates | 98152 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000115 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.304 | +| time/ | | +| fps | 1383 | +| iterations | 20585 | +| time_elapsed | 30467 | +| total_timesteps | 42158080 | +| train/ | | +| approx_kl | 0.01329485 | +| clip_fraction | 0.325 | +| clip_range | 0.0645 | +| entropy_loss | -6.28 | +| explained_variance | 0.00435 | +| learning_rate | 4e-05 | +| loss | -0.0288 | +| n_updates | 98156 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000159 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 1383 | +| iterations | 20586 | +| time_elapsed | 30469 | +| total_timesteps | 42160128 | +| train/ | | +| approx_kl | 0.009842542 | +| clip_fraction | 0.311 | +| clip_range | 0.0645 | +| entropy_loss | -7 | +| explained_variance | 0.0139 | +| learning_rate | 4e-05 | +| loss | -0.0255 | +| n_updates | 98160 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000305 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1383 | +| iterations | 20587 | +| time_elapsed | 30471 | +| total_timesteps | 42162176 | +| train/ | | +| approx_kl | 0.008546095 | +| clip_fraction | 0.322 | +| clip_range | 0.0645 | +| entropy_loss | -6.67 | +| explained_variance | 0.19 | +| learning_rate | 4e-05 | +| loss | -0.0258 | +| n_updates | 98164 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000355 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1383 | +| iterations | 20588 | +| time_elapsed | 30472 | +| total_timesteps | 42164224 | +| train/ | | +| approx_kl | 0.009935733 | +| clip_fraction | 0.292 | +| clip_range | 0.0645 | +| entropy_loss | -5.52 | +| explained_variance | 0.636 | +| learning_rate | 4e-05 | +| loss | -0.0214 | +| n_updates | 98168 | +| policy_gradient_loss | -0.014 | +| value_loss | 0.000148 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1383 | +| iterations | 20589 | +| time_elapsed | 30474 | +| total_timesteps | 42166272 | +| train/ | | +| approx_kl | 0.012186763 | +| clip_fraction | 0.343 | +| clip_range | 0.0645 | +| entropy_loss | -5.13 | +| explained_variance | 0.369 | +| learning_rate | 4e-05 | +| loss | -0.019 | +| n_updates | 98172 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000241 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.315 | +| time/ | | +| fps | 1383 | +| iterations | 20590 | +| time_elapsed | 30475 | +| total_timesteps | 42168320 | +| train/ | | +| approx_kl | 0.012630929 | +| clip_fraction | 0.349 | +| clip_range | 0.0645 | +| entropy_loss | -5.41 | +| explained_variance | 0.193 | +| learning_rate | 4e-05 | +| loss | -0.0242 | +| n_updates | 98176 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1383 | +| iterations | 20591 | +| time_elapsed | 30477 | +| total_timesteps | 42170368 | +| train/ | | +| approx_kl | 0.012462583 | +| clip_fraction | 0.304 | +| clip_range | 0.0645 | +| entropy_loss | -5.75 | +| explained_variance | 0.62 | +| learning_rate | 4e-05 | +| loss | -0.0225 | +| n_updates | 98180 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000177 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1383 | +| iterations | 20592 | +| time_elapsed | 30478 | +| total_timesteps | 42172416 | +| train/ | | +| approx_kl | 0.015692892 | +| clip_fraction | 0.312 | +| clip_range | 0.0645 | +| entropy_loss | -5.79 | +| explained_variance | 0.531 | +| learning_rate | 4e-05 | +| loss | -0.0213 | +| n_updates | 98184 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000136 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1383 | +| iterations | 20593 | +| time_elapsed | 30480 | +| total_timesteps | 42174464 | +| train/ | | +| approx_kl | 0.0138209555 | +| clip_fraction | 0.315 | +| clip_range | 0.0645 | +| entropy_loss | -6.38 | +| explained_variance | -0.056 | +| learning_rate | 4e-05 | +| loss | -0.0315 | +| n_updates | 98188 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000121 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1383 | +| iterations | 20594 | +| time_elapsed | 30481 | +| total_timesteps | 42176512 | +| train/ | | +| approx_kl | 0.009261703 | +| clip_fraction | 0.317 | +| clip_range | 0.0645 | +| entropy_loss | -6.56 | +| explained_variance | 0.178 | +| learning_rate | 4e-05 | +| loss | -0.0279 | +| n_updates | 98192 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.000266 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1383 | +| iterations | 20595 | +| time_elapsed | 30483 | +| total_timesteps | 42178560 | +| train/ | | +| approx_kl | 0.012526093 | +| clip_fraction | 0.353 | +| clip_range | 0.0645 | +| entropy_loss | -5.89 | +| explained_variance | 0.651 | +| learning_rate | 4e-05 | +| loss | -0.0262 | +| n_updates | 98196 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000115 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1383 | +| iterations | 20596 | +| time_elapsed | 30485 | +| total_timesteps | 42180608 | +| train/ | | +| approx_kl | 0.0134114325 | +| clip_fraction | 0.358 | +| clip_range | 0.0645 | +| entropy_loss | -5.5 | +| explained_variance | 0.49 | +| learning_rate | 4e-05 | +| loss | -0.0289 | +| n_updates | 98200 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000103 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1383 | +| iterations | 20597 | +| time_elapsed | 30486 | +| total_timesteps | 42182656 | +| train/ | | +| approx_kl | 0.01046481 | +| clip_fraction | 0.32 | +| clip_range | 0.0645 | +| entropy_loss | -6.08 | +| explained_variance | 0.246 | +| learning_rate | 4e-05 | +| loss | -0.0285 | +| n_updates | 98204 | +| policy_gradient_loss | -0.0137 | +| value_loss | 0.000267 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1383 | +| iterations | 20598 | +| time_elapsed | 30488 | +| total_timesteps | 42184704 | +| train/ | | +| approx_kl | 0.0142194955 | +| clip_fraction | 0.359 | +| clip_range | 0.0645 | +| entropy_loss | -6.01 | +| explained_variance | 0.529 | +| learning_rate | 4e-05 | +| loss | -0.0287 | +| n_updates | 98208 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000144 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1383 | +| iterations | 20599 | +| time_elapsed | 30490 | +| total_timesteps | 42186752 | +| train/ | | +| approx_kl | 0.015937181 | +| clip_fraction | 0.321 | +| clip_range | 0.0645 | +| entropy_loss | -5.78 | +| explained_variance | 0.171 | +| learning_rate | 4e-05 | +| loss | -0.0274 | +| n_updates | 98212 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000184 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1383 | +| iterations | 20600 | +| time_elapsed | 30491 | +| total_timesteps | 42188800 | +| train/ | | +| approx_kl | 0.013561651 | +| clip_fraction | 0.327 | +| clip_range | 0.0645 | +| entropy_loss | -6.02 | +| explained_variance | 0.0136 | +| learning_rate | 4e-05 | +| loss | -0.0245 | +| n_updates | 98216 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000156 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1383 | +| iterations | 20601 | +| time_elapsed | 30493 | +| total_timesteps | 42190848 | +| train/ | | +| approx_kl | 0.012873851 | +| clip_fraction | 0.35 | +| clip_range | 0.0645 | +| entropy_loss | -5.96 | +| explained_variance | 0.122 | +| learning_rate | 4e-05 | +| loss | -0.0322 | +| n_updates | 98220 | +| policy_gradient_loss | -0.0192 | +| value_loss | 9.3e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1383 | +| iterations | 20602 | +| time_elapsed | 30494 | +| total_timesteps | 42192896 | +| train/ | | +| approx_kl | 0.01085099 | +| clip_fraction | 0.31 | +| clip_range | 0.0645 | +| entropy_loss | -6.04 | +| explained_variance | 0.286 | +| learning_rate | 4e-05 | +| loss | -0.0224 | +| n_updates | 98224 | +| policy_gradient_loss | -0.0136 | +| value_loss | 0.000344 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1383 | +| iterations | 20603 | +| time_elapsed | 30496 | +| total_timesteps | 42194944 | +| train/ | | +| approx_kl | 0.01389654 | +| clip_fraction | 0.328 | +| clip_range | 0.0645 | +| entropy_loss | -6.14 | +| explained_variance | 0.372 | +| learning_rate | 4e-05 | +| loss | -0.0298 | +| n_updates | 98228 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000114 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1383 | +| iterations | 20604 | +| time_elapsed | 30497 | +| total_timesteps | 42196992 | +| train/ | | +| approx_kl | 0.013067538 | +| clip_fraction | 0.323 | +| clip_range | 0.0645 | +| entropy_loss | -5.56 | +| explained_variance | 0.515 | +| learning_rate | 4e-05 | +| loss | -0.0245 | +| n_updates | 98232 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000213 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1383 | +| iterations | 20605 | +| time_elapsed | 30499 | +| total_timesteps | 42199040 | +| train/ | | +| approx_kl | 0.0140286395 | +| clip_fraction | 0.32 | +| clip_range | 0.0645 | +| entropy_loss | -5.99 | +| explained_variance | 0.315 | +| learning_rate | 4e-05 | +| loss | -0.0264 | +| n_updates | 98236 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000167 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1383 | +| iterations | 20606 | +| time_elapsed | 30500 | +| total_timesteps | 42201088 | +| train/ | | +| approx_kl | 0.0128390435 | +| clip_fraction | 0.346 | +| clip_range | 0.0645 | +| entropy_loss | -6.26 | +| explained_variance | -0.206 | +| learning_rate | 4e-05 | +| loss | -0.0319 | +| n_updates | 98240 | +| policy_gradient_loss | -0.0205 | +| value_loss | 8.81e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1383 | +| iterations | 20607 | +| time_elapsed | 30502 | +| total_timesteps | 42203136 | +| train/ | | +| approx_kl | 0.018165518 | +| clip_fraction | 0.334 | +| clip_range | 0.0644 | +| entropy_loss | -5.87 | +| explained_variance | 0.329 | +| learning_rate | 4e-05 | +| loss | -0.0291 | +| n_updates | 98244 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000137 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1383 | +| iterations | 20608 | +| time_elapsed | 30503 | +| total_timesteps | 42205184 | +| train/ | | +| approx_kl | 0.011645567 | +| clip_fraction | 0.352 | +| clip_range | 0.0644 | +| entropy_loss | -5.97 | +| explained_variance | 0.439 | +| learning_rate | 4e-05 | +| loss | -0.0231 | +| n_updates | 98248 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000174 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1383 | +| iterations | 20609 | +| time_elapsed | 30505 | +| total_timesteps | 42207232 | +| train/ | | +| approx_kl | 0.010759516 | +| clip_fraction | 0.342 | +| clip_range | 0.0644 | +| entropy_loss | -6.1 | +| explained_variance | 0.435 | +| learning_rate | 4e-05 | +| loss | -0.021 | +| n_updates | 98252 | +| policy_gradient_loss | -0.0146 | +| value_loss | 0.000192 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1383 | +| iterations | 20610 | +| time_elapsed | 30506 | +| total_timesteps | 42209280 | +| train/ | | +| approx_kl | 0.013189326 | +| clip_fraction | 0.34 | +| clip_range | 0.0644 | +| entropy_loss | -5.65 | +| explained_variance | 0.593 | +| learning_rate | 4e-05 | +| loss | -0.0286 | +| n_updates | 98256 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000176 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1383 | +| iterations | 20611 | +| time_elapsed | 30508 | +| total_timesteps | 42211328 | +| train/ | | +| approx_kl | 0.010889394 | +| clip_fraction | 0.32 | +| clip_range | 0.0644 | +| entropy_loss | -6.33 | +| explained_variance | -0.00549 | +| learning_rate | 4e-05 | +| loss | -0.0274 | +| n_updates | 98260 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000283 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1383 | +| iterations | 20612 | +| time_elapsed | 30510 | +| total_timesteps | 42213376 | +| train/ | | +| approx_kl | 0.011094585 | +| clip_fraction | 0.326 | +| clip_range | 0.0644 | +| entropy_loss | -6.07 | +| explained_variance | 0.292 | +| learning_rate | 4e-05 | +| loss | -0.0245 | +| n_updates | 98264 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000175 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1383 | +| iterations | 20613 | +| time_elapsed | 30511 | +| total_timesteps | 42215424 | +| train/ | | +| approx_kl | 0.0109623475 | +| clip_fraction | 0.362 | +| clip_range | 0.0644 | +| entropy_loss | -6.59 | +| explained_variance | 0.646 | +| learning_rate | 4e-05 | +| loss | -0.0364 | +| n_updates | 98268 | +| policy_gradient_loss | -0.0206 | +| value_loss | 6.43e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1383 | +| iterations | 20614 | +| time_elapsed | 30513 | +| total_timesteps | 42217472 | +| train/ | | +| approx_kl | 0.010217439 | +| clip_fraction | 0.288 | +| clip_range | 0.0644 | +| entropy_loss | -6.56 | +| explained_variance | 0.129 | +| learning_rate | 4e-05 | +| loss | -0.0243 | +| n_updates | 98272 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000112 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1383 | +| iterations | 20615 | +| time_elapsed | 30514 | +| total_timesteps | 42219520 | +| train/ | | +| approx_kl | 0.012315579 | +| clip_fraction | 0.299 | +| clip_range | 0.0644 | +| entropy_loss | -5.93 | +| explained_variance | 0.371 | +| learning_rate | 4e-05 | +| loss | -0.0287 | +| n_updates | 98276 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000247 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1383 | +| iterations | 20616 | +| time_elapsed | 30516 | +| total_timesteps | 42221568 | +| train/ | | +| approx_kl | 0.014555827 | +| clip_fraction | 0.328 | +| clip_range | 0.0644 | +| entropy_loss | -5.15 | +| explained_variance | 0.564 | +| learning_rate | 4e-05 | +| loss | -0.0208 | +| n_updates | 98280 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000183 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1383 | +| iterations | 20617 | +| time_elapsed | 30517 | +| total_timesteps | 42223616 | +| train/ | | +| approx_kl | 0.012371529 | +| clip_fraction | 0.307 | +| clip_range | 0.0644 | +| entropy_loss | -5.71 | +| explained_variance | 0.0373 | +| learning_rate | 4e-05 | +| loss | -0.0216 | +| n_updates | 98284 | +| policy_gradient_loss | -0.0147 | +| value_loss | 0.000223 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1383 | +| iterations | 20618 | +| time_elapsed | 30519 | +| total_timesteps | 42225664 | +| train/ | | +| approx_kl | 0.012427064 | +| clip_fraction | 0.313 | +| clip_range | 0.0644 | +| entropy_loss | -6.02 | +| explained_variance | 0.504 | +| learning_rate | 4e-05 | +| loss | -0.0248 | +| n_updates | 98288 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1383 | +| iterations | 20619 | +| time_elapsed | 30520 | +| total_timesteps | 42227712 | +| train/ | | +| approx_kl | 0.011965882 | +| clip_fraction | 0.312 | +| clip_range | 0.0644 | +| entropy_loss | -6.05 | +| explained_variance | 0.28 | +| learning_rate | 4e-05 | +| loss | -0.0253 | +| n_updates | 98292 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000178 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1383 | +| iterations | 20620 | +| time_elapsed | 30522 | +| total_timesteps | 42229760 | +| train/ | | +| approx_kl | 0.012570282 | +| clip_fraction | 0.34 | +| clip_range | 0.0644 | +| entropy_loss | -5.81 | +| explained_variance | 0.557 | +| learning_rate | 4e-05 | +| loss | -0.0299 | +| n_updates | 98296 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000129 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1383 | +| iterations | 20621 | +| time_elapsed | 30523 | +| total_timesteps | 42231808 | +| train/ | | +| approx_kl | 0.012774454 | +| clip_fraction | 0.312 | +| clip_range | 0.0644 | +| entropy_loss | -6.28 | +| explained_variance | -0.0171 | +| learning_rate | 4e-05 | +| loss | -0.0293 | +| n_updates | 98300 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000174 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1383 | +| iterations | 20622 | +| time_elapsed | 30525 | +| total_timesteps | 42233856 | +| train/ | | +| approx_kl | 0.013391807 | +| clip_fraction | 0.328 | +| clip_range | 0.0644 | +| entropy_loss | -6.24 | +| explained_variance | 0.292 | +| learning_rate | 4e-05 | +| loss | -0.0227 | +| n_updates | 98304 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.00017 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1383 | +| iterations | 20623 | +| time_elapsed | 30526 | +| total_timesteps | 42235904 | +| train/ | | +| approx_kl | 0.010381054 | +| clip_fraction | 0.315 | +| clip_range | 0.0644 | +| entropy_loss | -5.94 | +| explained_variance | 0.557 | +| learning_rate | 4e-05 | +| loss | -0.0267 | +| n_updates | 98308 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000124 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1383 | +| iterations | 20624 | +| time_elapsed | 30528 | +| total_timesteps | 42237952 | +| train/ | | +| approx_kl | 0.010564264 | +| clip_fraction | 0.303 | +| clip_range | 0.0644 | +| entropy_loss | -6.47 | +| explained_variance | -0.0976 | +| learning_rate | 4e-05 | +| loss | -0.0258 | +| n_updates | 98312 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.00022 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1383 | +| iterations | 20625 | +| time_elapsed | 30529 | +| total_timesteps | 42240000 | +| train/ | | +| approx_kl | 0.011163894 | +| clip_fraction | 0.326 | +| clip_range | 0.0644 | +| entropy_loss | -6.43 | +| explained_variance | 0.555 | +| learning_rate | 4e-05 | +| loss | -0.0321 | +| n_updates | 98316 | +| policy_gradient_loss | -0.0197 | +| value_loss | 9.05e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1383 | +| iterations | 20626 | +| time_elapsed | 30531 | +| total_timesteps | 42242048 | +| train/ | | +| approx_kl | 0.010266354 | +| clip_fraction | 0.315 | +| clip_range | 0.0644 | +| entropy_loss | -5.68 | +| explained_variance | 0.804 | +| learning_rate | 4e-05 | +| loss | -0.0212 | +| n_updates | 98320 | +| policy_gradient_loss | -0.0149 | +| value_loss | 8.11e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1383 | +| iterations | 20627 | +| time_elapsed | 30532 | +| total_timesteps | 42244096 | +| train/ | | +| approx_kl | 0.009745211 | +| clip_fraction | 0.294 | +| clip_range | 0.0644 | +| entropy_loss | -5.52 | +| explained_variance | 0.587 | +| learning_rate | 4e-05 | +| loss | -0.0219 | +| n_updates | 98324 | +| policy_gradient_loss | -0.0144 | +| value_loss | 0.000156 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1383 | +| iterations | 20628 | +| time_elapsed | 30534 | +| total_timesteps | 42246144 | +| train/ | | +| approx_kl | 0.010666024 | +| clip_fraction | 0.305 | +| clip_range | 0.0644 | +| entropy_loss | -6.28 | +| explained_variance | 0.654 | +| learning_rate | 4e-05 | +| loss | -0.0292 | +| n_updates | 98328 | +| policy_gradient_loss | -0.0154 | +| value_loss | 9.29e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1383 | +| iterations | 20629 | +| time_elapsed | 30536 | +| total_timesteps | 42248192 | +| train/ | | +| approx_kl | 0.01412362 | +| clip_fraction | 0.352 | +| clip_range | 0.0644 | +| entropy_loss | -5.5 | +| explained_variance | 0.668 | +| learning_rate | 4e-05 | +| loss | -0.0296 | +| n_updates | 98332 | +| policy_gradient_loss | -0.0184 | +| value_loss | 8.45e-05 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1383 | +| iterations | 20630 | +| time_elapsed | 30537 | +| total_timesteps | 42250240 | +| train/ | | +| approx_kl | 0.01155957 | +| clip_fraction | 0.311 | +| clip_range | 0.0644 | +| entropy_loss | -6.42 | +| explained_variance | -0.00998 | +| learning_rate | 4e-05 | +| loss | -0.0264 | +| n_updates | 98336 | +| policy_gradient_loss | -0.0148 | +| value_loss | 0.000181 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1383 | +| iterations | 20631 | +| time_elapsed | 30539 | +| total_timesteps | 42252288 | +| train/ | | +| approx_kl | 0.010645498 | +| clip_fraction | 0.33 | +| clip_range | 0.0644 | +| entropy_loss | -6.41 | +| explained_variance | 0.347 | +| learning_rate | 4e-05 | +| loss | -0.0313 | +| n_updates | 98340 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000154 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1383 | +| iterations | 20632 | +| time_elapsed | 30540 | +| total_timesteps | 42254336 | +| train/ | | +| approx_kl | 0.008021159 | +| clip_fraction | 0.299 | +| clip_range | 0.0644 | +| entropy_loss | -6.55 | +| explained_variance | 0.517 | +| learning_rate | 4e-05 | +| loss | -0.0258 | +| n_updates | 98344 | +| policy_gradient_loss | -0.0138 | +| value_loss | 0.000229 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1383 | +| iterations | 20633 | +| time_elapsed | 30542 | +| total_timesteps | 42256384 | +| train/ | | +| approx_kl | 0.011279367 | +| clip_fraction | 0.312 | +| clip_range | 0.0644 | +| entropy_loss | -6.41 | +| explained_variance | -0.137 | +| learning_rate | 4e-05 | +| loss | -0.0282 | +| n_updates | 98348 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000149 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1383 | +| iterations | 20634 | +| time_elapsed | 30543 | +| total_timesteps | 42258432 | +| train/ | | +| approx_kl | 0.009829835 | +| clip_fraction | 0.317 | +| clip_range | 0.0644 | +| entropy_loss | -5.63 | +| explained_variance | 0.269 | +| learning_rate | 4e-05 | +| loss | -0.0216 | +| n_updates | 98352 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.00024 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1383 | +| iterations | 20635 | +| time_elapsed | 30545 | +| total_timesteps | 42260480 | +| train/ | | +| approx_kl | 0.0141074965 | +| clip_fraction | 0.333 | +| clip_range | 0.0644 | +| entropy_loss | -6.04 | +| explained_variance | 0.372 | +| learning_rate | 4e-05 | +| loss | -0.0284 | +| n_updates | 98356 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000137 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1383 | +| iterations | 20636 | +| time_elapsed | 30546 | +| total_timesteps | 42262528 | +| train/ | | +| approx_kl | 0.010478325 | +| clip_fraction | 0.286 | +| clip_range | 0.0644 | +| entropy_loss | -6.65 | +| explained_variance | 0.375 | +| learning_rate | 4e-05 | +| loss | -0.0256 | +| n_updates | 98360 | +| policy_gradient_loss | -0.0159 | +| value_loss | 9.93e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1383 | +| iterations | 20637 | +| time_elapsed | 30548 | +| total_timesteps | 42264576 | +| train/ | | +| approx_kl | 0.00953575 | +| clip_fraction | 0.282 | +| clip_range | 0.0644 | +| entropy_loss | -5.43 | +| explained_variance | 0.418 | +| learning_rate | 4e-05 | +| loss | -0.0189 | +| n_updates | 98364 | +| policy_gradient_loss | -0.0132 | +| value_loss | 0.000387 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1383 | +| iterations | 20638 | +| time_elapsed | 30549 | +| total_timesteps | 42266624 | +| train/ | | +| approx_kl | 0.015180292 | +| clip_fraction | 0.331 | +| clip_range | 0.0644 | +| entropy_loss | -5.76 | +| explained_variance | 0.341 | +| learning_rate | 4e-05 | +| loss | -0.0318 | +| n_updates | 98368 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000124 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1383 | +| iterations | 20639 | +| time_elapsed | 30551 | +| total_timesteps | 42268672 | +| train/ | | +| approx_kl | 0.0152690755 | +| clip_fraction | 0.312 | +| clip_range | 0.0644 | +| entropy_loss | -5.62 | +| explained_variance | 0.579 | +| learning_rate | 4e-05 | +| loss | -0.0256 | +| n_updates | 98372 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000173 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1383 | +| iterations | 20640 | +| time_elapsed | 30552 | +| total_timesteps | 42270720 | +| train/ | | +| approx_kl | 0.013253798 | +| clip_fraction | 0.325 | +| clip_range | 0.0644 | +| entropy_loss | -5.9 | +| explained_variance | 0.556 | +| learning_rate | 4e-05 | +| loss | -0.0304 | +| n_updates | 98376 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000102 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1383 | +| iterations | 20641 | +| time_elapsed | 30554 | +| total_timesteps | 42272768 | +| train/ | | +| approx_kl | 0.012382831 | +| clip_fraction | 0.322 | +| clip_range | 0.0644 | +| entropy_loss | -6.17 | +| explained_variance | 0.14 | +| learning_rate | 4e-05 | +| loss | -0.0264 | +| n_updates | 98380 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000194 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1383 | +| iterations | 20642 | +| time_elapsed | 30555 | +| total_timesteps | 42274816 | +| train/ | | +| approx_kl | 0.010694817 | +| clip_fraction | 0.357 | +| clip_range | 0.0644 | +| entropy_loss | -6.83 | +| explained_variance | 0.338 | +| learning_rate | 4e-05 | +| loss | -0.03 | +| n_updates | 98384 | +| policy_gradient_loss | -0.0186 | +| value_loss | 9.68e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1383 | +| iterations | 20643 | +| time_elapsed | 30557 | +| total_timesteps | 42276864 | +| train/ | | +| approx_kl | 0.010701237 | +| clip_fraction | 0.292 | +| clip_range | 0.0644 | +| entropy_loss | -5.76 | +| explained_variance | 0.329 | +| learning_rate | 4e-05 | +| loss | -0.0195 | +| n_updates | 98388 | +| policy_gradient_loss | -0.0141 | +| value_loss | 0.000478 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1383 | +| iterations | 20644 | +| time_elapsed | 30559 | +| total_timesteps | 42278912 | +| train/ | | +| approx_kl | 0.012042312 | +| clip_fraction | 0.322 | +| clip_range | 0.0644 | +| entropy_loss | -6.64 | +| explained_variance | -0.199 | +| learning_rate | 4e-05 | +| loss | -0.0305 | +| n_updates | 98392 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000134 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1383 | +| iterations | 20645 | +| time_elapsed | 30560 | +| total_timesteps | 42280960 | +| train/ | | +| approx_kl | 0.010798739 | +| clip_fraction | 0.324 | +| clip_range | 0.0644 | +| entropy_loss | -6.67 | +| explained_variance | -0.118 | +| learning_rate | 4e-05 | +| loss | -0.0271 | +| n_updates | 98396 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000225 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1383 | +| iterations | 20646 | +| time_elapsed | 30562 | +| total_timesteps | 42283008 | +| train/ | | +| approx_kl | 0.01365061 | +| clip_fraction | 0.337 | +| clip_range | 0.0644 | +| entropy_loss | -5.61 | +| explained_variance | 0.48 | +| learning_rate | 4e-05 | +| loss | -0.027 | +| n_updates | 98400 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000146 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1383 | +| iterations | 20647 | +| time_elapsed | 30563 | +| total_timesteps | 42285056 | +| train/ | | +| approx_kl | 0.016518403 | +| clip_fraction | 0.349 | +| clip_range | 0.0644 | +| entropy_loss | -5.46 | +| explained_variance | 0.612 | +| learning_rate | 4e-05 | +| loss | -0.0316 | +| n_updates | 98404 | +| policy_gradient_loss | -0.0191 | +| value_loss | 8.93e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1383 | +| iterations | 20648 | +| time_elapsed | 30565 | +| total_timesteps | 42287104 | +| train/ | | +| approx_kl | 0.015033837 | +| clip_fraction | 0.339 | +| clip_range | 0.0644 | +| entropy_loss | -6.52 | +| explained_variance | -0.193 | +| learning_rate | 4e-05 | +| loss | -0.0273 | +| n_updates | 98408 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000115 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1383 | +| iterations | 20649 | +| time_elapsed | 30566 | +| total_timesteps | 42289152 | +| train/ | | +| approx_kl | 0.012303002 | +| clip_fraction | 0.328 | +| clip_range | 0.0644 | +| entropy_loss | -5.6 | +| explained_variance | 0.684 | +| learning_rate | 4e-05 | +| loss | -0.0245 | +| n_updates | 98412 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000155 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1383 | +| iterations | 20650 | +| time_elapsed | 30568 | +| total_timesteps | 42291200 | +| train/ | | +| approx_kl | 0.014579212 | +| clip_fraction | 0.324 | +| clip_range | 0.0644 | +| entropy_loss | -5.08 | +| explained_variance | 0.755 | +| learning_rate | 4e-05 | +| loss | -0.0262 | +| n_updates | 98416 | +| policy_gradient_loss | -0.0164 | +| value_loss | 8.89e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1383 | +| iterations | 20651 | +| time_elapsed | 30569 | +| total_timesteps | 42293248 | +| train/ | | +| approx_kl | 0.013190068 | +| clip_fraction | 0.346 | +| clip_range | 0.0644 | +| entropy_loss | -5.98 | +| explained_variance | 0.697 | +| learning_rate | 4e-05 | +| loss | -0.025 | +| n_updates | 98420 | +| policy_gradient_loss | -0.018 | +| value_loss | 5.98e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1383 | +| iterations | 20652 | +| time_elapsed | 30571 | +| total_timesteps | 42295296 | +| train/ | | +| approx_kl | 0.012076129 | +| clip_fraction | 0.309 | +| clip_range | 0.0644 | +| entropy_loss | -6.62 | +| explained_variance | 0.38 | +| learning_rate | 4e-05 | +| loss | -0.0281 | +| n_updates | 98424 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000104 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1383 | +| iterations | 20653 | +| time_elapsed | 30572 | +| total_timesteps | 42297344 | +| train/ | | +| approx_kl | 0.012460244 | +| clip_fraction | 0.313 | +| clip_range | 0.0644 | +| entropy_loss | -6.27 | +| explained_variance | 0.317 | +| learning_rate | 4e-05 | +| loss | -0.0307 | +| n_updates | 98428 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000152 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1383 | +| iterations | 20654 | +| time_elapsed | 30574 | +| total_timesteps | 42299392 | +| train/ | | +| approx_kl | 0.011848823 | +| clip_fraction | 0.339 | +| clip_range | 0.0644 | +| entropy_loss | -6.12 | +| explained_variance | 0.0254 | +| learning_rate | 4e-05 | +| loss | -0.0339 | +| n_updates | 98432 | +| policy_gradient_loss | -0.0187 | +| value_loss | 6.16e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1383 | +| iterations | 20655 | +| time_elapsed | 30575 | +| total_timesteps | 42301440 | +| train/ | | +| approx_kl | 0.013889853 | +| clip_fraction | 0.304 | +| clip_range | 0.0644 | +| entropy_loss | -6.4 | +| explained_variance | 0.0142 | +| learning_rate | 4e-05 | +| loss | -0.0252 | +| n_updates | 98436 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000163 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1383 | +| iterations | 20656 | +| time_elapsed | 30577 | +| total_timesteps | 42303488 | +| train/ | | +| approx_kl | 0.009383395 | +| clip_fraction | 0.307 | +| clip_range | 0.0644 | +| entropy_loss | -6.3 | +| explained_variance | 0.3 | +| learning_rate | 4e-05 | +| loss | -0.0311 | +| n_updates | 98440 | +| policy_gradient_loss | -0.0172 | +| value_loss | 8.72e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1383 | +| iterations | 20657 | +| time_elapsed | 30578 | +| total_timesteps | 42305536 | +| train/ | | +| approx_kl | 0.011127471 | +| clip_fraction | 0.306 | +| clip_range | 0.0644 | +| entropy_loss | -6.26 | +| explained_variance | 0.443 | +| learning_rate | 4e-05 | +| loss | -0.0333 | +| n_updates | 98444 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.000117 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1383 | +| iterations | 20658 | +| time_elapsed | 30580 | +| total_timesteps | 42307584 | +| train/ | | +| approx_kl | 0.01077874 | +| clip_fraction | 0.313 | +| clip_range | 0.0644 | +| entropy_loss | -5.72 | +| explained_variance | 0.735 | +| learning_rate | 4e-05 | +| loss | -0.0292 | +| n_updates | 98448 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.000126 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1383 | +| iterations | 20659 | +| time_elapsed | 30581 | +| total_timesteps | 42309632 | +| train/ | | +| approx_kl | 0.012128871 | +| clip_fraction | 0.313 | +| clip_range | 0.0644 | +| entropy_loss | -6.02 | +| explained_variance | 0.0478 | +| learning_rate | 4e-05 | +| loss | -0.0268 | +| n_updates | 98452 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000144 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1383 | +| iterations | 20660 | +| time_elapsed | 30583 | +| total_timesteps | 42311680 | +| train/ | | +| approx_kl | 0.011690275 | +| clip_fraction | 0.321 | +| clip_range | 0.0644 | +| entropy_loss | -5.96 | +| explained_variance | 0.448 | +| learning_rate | 4e-05 | +| loss | -0.0263 | +| n_updates | 98456 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000145 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1383 | +| iterations | 20661 | +| time_elapsed | 30584 | +| total_timesteps | 42313728 | +| train/ | | +| approx_kl | 0.011630453 | +| clip_fraction | 0.318 | +| clip_range | 0.0644 | +| entropy_loss | -5.38 | +| explained_variance | 0.675 | +| learning_rate | 4e-05 | +| loss | -0.0243 | +| n_updates | 98460 | +| policy_gradient_loss | -0.0147 | +| value_loss | 0.000122 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1383 | +| iterations | 20662 | +| time_elapsed | 30586 | +| total_timesteps | 42315776 | +| train/ | | +| approx_kl | 0.010373827 | +| clip_fraction | 0.306 | +| clip_range | 0.0644 | +| entropy_loss | -5.85 | +| explained_variance | 0.247 | +| learning_rate | 4e-05 | +| loss | -0.0236 | +| n_updates | 98464 | +| policy_gradient_loss | -0.0148 | +| value_loss | 0.000286 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1383 | +| iterations | 20663 | +| time_elapsed | 30587 | +| total_timesteps | 42317824 | +| train/ | | +| approx_kl | 0.013169805 | +| clip_fraction | 0.331 | +| clip_range | 0.0644 | +| entropy_loss | -5.89 | +| explained_variance | -0.12 | +| learning_rate | 4e-05 | +| loss | -0.0263 | +| n_updates | 98468 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000126 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1383 | +| iterations | 20664 | +| time_elapsed | 30589 | +| total_timesteps | 42319872 | +| train/ | | +| approx_kl | 0.014234765 | +| clip_fraction | 0.333 | +| clip_range | 0.0644 | +| entropy_loss | -5.99 | +| explained_variance | 0.533 | +| learning_rate | 3.99e-05 | +| loss | -0.0281 | +| n_updates | 98472 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000117 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1383 | +| iterations | 20665 | +| time_elapsed | 30590 | +| total_timesteps | 42321920 | +| train/ | | +| approx_kl | 0.012887405 | +| clip_fraction | 0.323 | +| clip_range | 0.0644 | +| entropy_loss | -5.59 | +| explained_variance | 0.328 | +| learning_rate | 3.99e-05 | +| loss | -0.0317 | +| n_updates | 98476 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000109 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1383 | +| iterations | 20666 | +| time_elapsed | 30592 | +| total_timesteps | 42323968 | +| train/ | | +| approx_kl | 0.01591026 | +| clip_fraction | 0.325 | +| clip_range | 0.0644 | +| entropy_loss | -6.13 | +| explained_variance | 0.529 | +| learning_rate | 3.99e-05 | +| loss | -0.0263 | +| n_updates | 98480 | +| policy_gradient_loss | -0.0188 | +| value_loss | 7.1e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1383 | +| iterations | 20667 | +| time_elapsed | 30593 | +| total_timesteps | 42326016 | +| train/ | | +| approx_kl | 0.014316196 | +| clip_fraction | 0.327 | +| clip_range | 0.0644 | +| entropy_loss | -5.92 | +| explained_variance | -0.0658 | +| learning_rate | 3.99e-05 | +| loss | -0.0223 | +| n_updates | 98484 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000146 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1383 | +| iterations | 20668 | +| time_elapsed | 30595 | +| total_timesteps | 42328064 | +| train/ | | +| approx_kl | 0.011525371 | +| clip_fraction | 0.324 | +| clip_range | 0.0644 | +| entropy_loss | -6.24 | +| explained_variance | 0.404 | +| learning_rate | 3.99e-05 | +| loss | -0.0253 | +| n_updates | 98488 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000123 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1383 | +| iterations | 20669 | +| time_elapsed | 30597 | +| total_timesteps | 42330112 | +| train/ | | +| approx_kl | 0.008924207 | +| clip_fraction | 0.284 | +| clip_range | 0.0644 | +| entropy_loss | -5.91 | +| explained_variance | 0.474 | +| learning_rate | 3.99e-05 | +| loss | -0.0274 | +| n_updates | 98492 | +| policy_gradient_loss | -0.0145 | +| value_loss | 0.000236 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1383 | +| iterations | 20670 | +| time_elapsed | 30598 | +| total_timesteps | 42332160 | +| train/ | | +| approx_kl | 0.011154139 | +| clip_fraction | 0.313 | +| clip_range | 0.0644 | +| entropy_loss | -6.14 | +| explained_variance | 0.367 | +| learning_rate | 3.99e-05 | +| loss | -0.0271 | +| n_updates | 98496 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000124 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1383 | +| iterations | 20671 | +| time_elapsed | 30600 | +| total_timesteps | 42334208 | +| train/ | | +| approx_kl | 0.011927322 | +| clip_fraction | 0.319 | +| clip_range | 0.0644 | +| entropy_loss | -6.18 | +| explained_variance | 0.6 | +| learning_rate | 3.99e-05 | +| loss | -0.0276 | +| n_updates | 98500 | +| policy_gradient_loss | -0.0169 | +| value_loss | 9.96e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1383 | +| iterations | 20672 | +| time_elapsed | 30601 | +| total_timesteps | 42336256 | +| train/ | | +| approx_kl | 0.012135919 | +| clip_fraction | 0.344 | +| clip_range | 0.0644 | +| entropy_loss | -6.13 | +| explained_variance | 0.519 | +| learning_rate | 3.99e-05 | +| loss | -0.0289 | +| n_updates | 98504 | +| policy_gradient_loss | -0.0183 | +| value_loss | 8.82e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1383 | +| iterations | 20673 | +| time_elapsed | 30603 | +| total_timesteps | 42338304 | +| train/ | | +| approx_kl | 0.013077337 | +| clip_fraction | 0.316 | +| clip_range | 0.0644 | +| entropy_loss | -6.12 | +| explained_variance | 0.276 | +| learning_rate | 3.99e-05 | +| loss | -0.0282 | +| n_updates | 98508 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000135 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1383 | +| iterations | 20674 | +| time_elapsed | 30604 | +| total_timesteps | 42340352 | +| train/ | | +| approx_kl | 0.0128581375 | +| clip_fraction | 0.294 | +| clip_range | 0.0644 | +| entropy_loss | -6.42 | +| explained_variance | 0.378 | +| learning_rate | 3.99e-05 | +| loss | -0.0241 | +| n_updates | 98512 | +| policy_gradient_loss | -0.0148 | +| value_loss | 0.000153 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1383 | +| iterations | 20675 | +| time_elapsed | 30606 | +| total_timesteps | 42342400 | +| train/ | | +| approx_kl | 0.010327939 | +| clip_fraction | 0.289 | +| clip_range | 0.0644 | +| entropy_loss | -6.02 | +| explained_variance | 0.315 | +| learning_rate | 3.99e-05 | +| loss | -0.0184 | +| n_updates | 98516 | +| policy_gradient_loss | -0.0128 | +| value_loss | 0.000388 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1383 | +| iterations | 20676 | +| time_elapsed | 30607 | +| total_timesteps | 42344448 | +| train/ | | +| approx_kl | 0.014114284 | +| clip_fraction | 0.319 | +| clip_range | 0.0644 | +| entropy_loss | -5.21 | +| explained_variance | 0.659 | +| learning_rate | 3.99e-05 | +| loss | -0.0296 | +| n_updates | 98520 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000151 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1383 | +| iterations | 20677 | +| time_elapsed | 30609 | +| total_timesteps | 42346496 | +| train/ | | +| approx_kl | 0.014370544 | +| clip_fraction | 0.34 | +| clip_range | 0.0644 | +| entropy_loss | -6.11 | +| explained_variance | 0.167 | +| learning_rate | 3.99e-05 | +| loss | -0.0295 | +| n_updates | 98524 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000171 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1383 | +| iterations | 20678 | +| time_elapsed | 30610 | +| total_timesteps | 42348544 | +| train/ | | +| approx_kl | 0.010365974 | +| clip_fraction | 0.323 | +| clip_range | 0.0644 | +| entropy_loss | -6.02 | +| explained_variance | 0.531 | +| learning_rate | 3.99e-05 | +| loss | -0.0295 | +| n_updates | 98528 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000135 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1383 | +| iterations | 20679 | +| time_elapsed | 30612 | +| total_timesteps | 42350592 | +| train/ | | +| approx_kl | 0.010363574 | +| clip_fraction | 0.32 | +| clip_range | 0.0644 | +| entropy_loss | -6.23 | +| explained_variance | -0.168 | +| learning_rate | 3.99e-05 | +| loss | -0.0301 | +| n_updates | 98532 | +| policy_gradient_loss | -0.0178 | +| value_loss | 9.34e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1383 | +| iterations | 20680 | +| time_elapsed | 30614 | +| total_timesteps | 42352640 | +| train/ | | +| approx_kl | 0.012131158 | +| clip_fraction | 0.313 | +| clip_range | 0.0644 | +| entropy_loss | -5.95 | +| explained_variance | -0.0829 | +| learning_rate | 3.99e-05 | +| loss | -0.0269 | +| n_updates | 98536 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000136 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1383 | +| iterations | 20681 | +| time_elapsed | 30615 | +| total_timesteps | 42354688 | +| train/ | | +| approx_kl | 0.0145056695 | +| clip_fraction | 0.326 | +| clip_range | 0.0644 | +| entropy_loss | -5.93 | +| explained_variance | 0.075 | +| learning_rate | 3.99e-05 | +| loss | -0.0241 | +| n_updates | 98540 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000334 | +------------------------------------------ +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1383 | +| iterations | 20682 | +| time_elapsed | 30617 | +| total_timesteps | 42356736 | +| train/ | | +| approx_kl | 0.0124192 | +| clip_fraction | 0.321 | +| clip_range | 0.0644 | +| entropy_loss | -5.79 | +| explained_variance | 0.365 | +| learning_rate | 3.99e-05 | +| loss | -0.0277 | +| n_updates | 98544 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000166 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1383 | +| iterations | 20683 | +| time_elapsed | 30618 | +| total_timesteps | 42358784 | +| train/ | | +| approx_kl | 0.011613587 | +| clip_fraction | 0.309 | +| clip_range | 0.0644 | +| entropy_loss | -5.89 | +| explained_variance | 0.644 | +| learning_rate | 3.99e-05 | +| loss | -0.0211 | +| n_updates | 98548 | +| policy_gradient_loss | -0.0172 | +| value_loss | 9.42e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1383 | +| iterations | 20684 | +| time_elapsed | 30620 | +| total_timesteps | 42360832 | +| train/ | | +| approx_kl | 0.012563432 | +| clip_fraction | 0.291 | +| clip_range | 0.0644 | +| entropy_loss | -5.92 | +| explained_variance | 0.0237 | +| learning_rate | 3.99e-05 | +| loss | -0.031 | +| n_updates | 98552 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000189 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1383 | +| iterations | 20685 | +| time_elapsed | 30621 | +| total_timesteps | 42362880 | +| train/ | | +| approx_kl | 0.010384091 | +| clip_fraction | 0.311 | +| clip_range | 0.0644 | +| entropy_loss | -5.91 | +| explained_variance | 0.343 | +| learning_rate | 3.99e-05 | +| loss | -0.0251 | +| n_updates | 98556 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.00026 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1383 | +| iterations | 20686 | +| time_elapsed | 30623 | +| total_timesteps | 42364928 | +| train/ | | +| approx_kl | 0.013439719 | +| clip_fraction | 0.349 | +| clip_range | 0.0644 | +| entropy_loss | -5.68 | +| explained_variance | 0.551 | +| learning_rate | 3.99e-05 | +| loss | -0.0223 | +| n_updates | 98560 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000146 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1383 | +| iterations | 20687 | +| time_elapsed | 30624 | +| total_timesteps | 42366976 | +| train/ | | +| approx_kl | 0.013472987 | +| clip_fraction | 0.331 | +| clip_range | 0.0644 | +| entropy_loss | -5.88 | +| explained_variance | 0.252 | +| learning_rate | 3.99e-05 | +| loss | -0.0239 | +| n_updates | 98564 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000171 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1383 | +| iterations | 20688 | +| time_elapsed | 30626 | +| total_timesteps | 42369024 | +| train/ | | +| approx_kl | 0.012182495 | +| clip_fraction | 0.299 | +| clip_range | 0.0644 | +| entropy_loss | -6.2 | +| explained_variance | 0.437 | +| learning_rate | 3.99e-05 | +| loss | -0.0266 | +| n_updates | 98568 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000168 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1383 | +| iterations | 20689 | +| time_elapsed | 30627 | +| total_timesteps | 42371072 | +| train/ | | +| approx_kl | 0.010602091 | +| clip_fraction | 0.302 | +| clip_range | 0.0644 | +| entropy_loss | -6.66 | +| explained_variance | 0.498 | +| learning_rate | 3.99e-05 | +| loss | -0.0274 | +| n_updates | 98572 | +| policy_gradient_loss | -0.0178 | +| value_loss | 9.31e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1383 | +| iterations | 20690 | +| time_elapsed | 30629 | +| total_timesteps | 42373120 | +| train/ | | +| approx_kl | 0.017527718 | +| clip_fraction | 0.311 | +| clip_range | 0.0644 | +| entropy_loss | -6.18 | +| explained_variance | 0.38 | +| learning_rate | 3.99e-05 | +| loss | -0.0328 | +| n_updates | 98576 | +| policy_gradient_loss | -0.0184 | +| value_loss | 7.8e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1383 | +| iterations | 20691 | +| time_elapsed | 30631 | +| total_timesteps | 42375168 | +| train/ | | +| approx_kl | 0.012059173 | +| clip_fraction | 0.325 | +| clip_range | 0.0644 | +| entropy_loss | -6.24 | +| explained_variance | -0.0618 | +| learning_rate | 3.99e-05 | +| loss | -0.0273 | +| n_updates | 98580 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000175 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1383 | +| iterations | 20692 | +| time_elapsed | 30632 | +| total_timesteps | 42377216 | +| train/ | | +| approx_kl | 0.014372678 | +| clip_fraction | 0.339 | +| clip_range | 0.0644 | +| entropy_loss | -5.55 | +| explained_variance | 0.758 | +| learning_rate | 3.99e-05 | +| loss | -0.0284 | +| n_updates | 98584 | +| policy_gradient_loss | -0.0187 | +| value_loss | 6.38e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1383 | +| iterations | 20693 | +| time_elapsed | 30634 | +| total_timesteps | 42379264 | +| train/ | | +| approx_kl | 0.011764216 | +| clip_fraction | 0.343 | +| clip_range | 0.0644 | +| entropy_loss | -5.49 | +| explained_variance | 0.537 | +| learning_rate | 3.99e-05 | +| loss | -0.03 | +| n_updates | 98588 | +| policy_gradient_loss | -0.0177 | +| value_loss | 6.27e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1383 | +| iterations | 20694 | +| time_elapsed | 30635 | +| total_timesteps | 42381312 | +| train/ | | +| approx_kl | 0.010316346 | +| clip_fraction | 0.299 | +| clip_range | 0.0644 | +| entropy_loss | -5.47 | +| explained_variance | 0.668 | +| learning_rate | 3.99e-05 | +| loss | -0.0185 | +| n_updates | 98592 | +| policy_gradient_loss | -0.0129 | +| value_loss | 0.000108 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1383 | +| iterations | 20695 | +| time_elapsed | 30637 | +| total_timesteps | 42383360 | +| train/ | | +| approx_kl | 0.01030261 | +| clip_fraction | 0.315 | +| clip_range | 0.0644 | +| entropy_loss | -5.84 | +| explained_variance | -0.113 | +| learning_rate | 3.99e-05 | +| loss | -0.0248 | +| n_updates | 98596 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.00019 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1383 | +| iterations | 20696 | +| time_elapsed | 30638 | +| total_timesteps | 42385408 | +| train/ | | +| approx_kl | 0.010510946 | +| clip_fraction | 0.322 | +| clip_range | 0.0644 | +| entropy_loss | -5.93 | +| explained_variance | 0.455 | +| learning_rate | 3.99e-05 | +| loss | -0.0239 | +| n_updates | 98600 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.00015 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1383 | +| iterations | 20697 | +| time_elapsed | 30640 | +| total_timesteps | 42387456 | +| train/ | | +| approx_kl | 0.012161545 | +| clip_fraction | 0.344 | +| clip_range | 0.0644 | +| entropy_loss | -5.77 | +| explained_variance | 0.529 | +| learning_rate | 3.99e-05 | +| loss | -0.0272 | +| n_updates | 98604 | +| policy_gradient_loss | -0.0176 | +| value_loss | 6.92e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1383 | +| iterations | 20698 | +| time_elapsed | 30641 | +| total_timesteps | 42389504 | +| train/ | | +| approx_kl | 0.012685876 | +| clip_fraction | 0.341 | +| clip_range | 0.0644 | +| entropy_loss | -5.8 | +| explained_variance | 0.556 | +| learning_rate | 3.99e-05 | +| loss | -0.0285 | +| n_updates | 98608 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000113 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1383 | +| iterations | 20699 | +| time_elapsed | 30643 | +| total_timesteps | 42391552 | +| train/ | | +| approx_kl | 0.010921103 | +| clip_fraction | 0.279 | +| clip_range | 0.0644 | +| entropy_loss | -5.65 | +| explained_variance | 0.314 | +| learning_rate | 3.99e-05 | +| loss | -0.0226 | +| n_updates | 98612 | +| policy_gradient_loss | -0.0143 | +| value_loss | 0.000261 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1383 | +| iterations | 20700 | +| time_elapsed | 30644 | +| total_timesteps | 42393600 | +| train/ | | +| approx_kl | 0.012766445 | +| clip_fraction | 0.325 | +| clip_range | 0.0644 | +| entropy_loss | -5.72 | +| explained_variance | 0.152 | +| learning_rate | 3.99e-05 | +| loss | -0.0284 | +| n_updates | 98616 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.0003 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1383 | +| iterations | 20701 | +| time_elapsed | 30646 | +| total_timesteps | 42395648 | +| train/ | | +| approx_kl | 0.010229146 | +| clip_fraction | 0.338 | +| clip_range | 0.0644 | +| entropy_loss | -6.38 | +| explained_variance | 0.251 | +| learning_rate | 3.99e-05 | +| loss | -0.0292 | +| n_updates | 98620 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.00019 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1383 | +| iterations | 20702 | +| time_elapsed | 30648 | +| total_timesteps | 42397696 | +| train/ | | +| approx_kl | 0.009074919 | +| clip_fraction | 0.314 | +| clip_range | 0.0644 | +| entropy_loss | -6.49 | +| explained_variance | 0.24 | +| learning_rate | 3.99e-05 | +| loss | -0.0235 | +| n_updates | 98624 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000145 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1383 | +| iterations | 20703 | +| time_elapsed | 30649 | +| total_timesteps | 42399744 | +| train/ | | +| approx_kl | 0.009393336 | +| clip_fraction | 0.327 | +| clip_range | 0.0644 | +| entropy_loss | -6.12 | +| explained_variance | 0.525 | +| learning_rate | 3.99e-05 | +| loss | -0.0205 | +| n_updates | 98628 | +| policy_gradient_loss | -0.0145 | +| value_loss | 0.000171 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1383 | +| iterations | 20704 | +| time_elapsed | 30651 | +| total_timesteps | 42401792 | +| train/ | | +| approx_kl | 0.012800675 | +| clip_fraction | 0.302 | +| clip_range | 0.0644 | +| entropy_loss | -6.04 | +| explained_variance | 0.611 | +| learning_rate | 3.99e-05 | +| loss | -0.0252 | +| n_updates | 98632 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000145 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1383 | +| iterations | 20705 | +| time_elapsed | 30652 | +| total_timesteps | 42403840 | +| train/ | | +| approx_kl | 0.011747548 | +| clip_fraction | 0.3 | +| clip_range | 0.0644 | +| entropy_loss | -5.85 | +| explained_variance | 0.0625 | +| learning_rate | 3.99e-05 | +| loss | -0.0284 | +| n_updates | 98636 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000233 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1383 | +| iterations | 20706 | +| time_elapsed | 30654 | +| total_timesteps | 42405888 | +| train/ | | +| approx_kl | 0.013278546 | +| clip_fraction | 0.315 | +| clip_range | 0.0644 | +| entropy_loss | -5.44 | +| explained_variance | 0.283 | +| learning_rate | 3.99e-05 | +| loss | -0.0228 | +| n_updates | 98640 | +| policy_gradient_loss | -0.0146 | +| value_loss | 0.000168 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1383 | +| iterations | 20707 | +| time_elapsed | 30655 | +| total_timesteps | 42407936 | +| train/ | | +| approx_kl | 0.011652214 | +| clip_fraction | 0.322 | +| clip_range | 0.0644 | +| entropy_loss | -5.37 | +| explained_variance | 0.454 | +| learning_rate | 3.99e-05 | +| loss | -0.0267 | +| n_updates | 98644 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000165 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1383 | +| iterations | 20708 | +| time_elapsed | 30657 | +| total_timesteps | 42409984 | +| train/ | | +| approx_kl | 0.012880869 | +| clip_fraction | 0.353 | +| clip_range | 0.0644 | +| entropy_loss | -6.25 | +| explained_variance | 0.521 | +| learning_rate | 3.99e-05 | +| loss | -0.0329 | +| n_updates | 98648 | +| policy_gradient_loss | -0.0213 | +| value_loss | 5.8e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1383 | +| iterations | 20709 | +| time_elapsed | 30658 | +| total_timesteps | 42412032 | +| train/ | | +| approx_kl | 0.009481767 | +| clip_fraction | 0.288 | +| clip_range | 0.0644 | +| entropy_loss | -6.44 | +| explained_variance | 0.493 | +| learning_rate | 3.99e-05 | +| loss | -0.0276 | +| n_updates | 98652 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000157 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1383 | +| iterations | 20710 | +| time_elapsed | 30660 | +| total_timesteps | 42414080 | +| train/ | | +| approx_kl | 0.011319498 | +| clip_fraction | 0.317 | +| clip_range | 0.0644 | +| entropy_loss | -6.15 | +| explained_variance | 0.0666 | +| learning_rate | 3.99e-05 | +| loss | -0.0264 | +| n_updates | 98656 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.000135 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1383 | +| iterations | 20711 | +| time_elapsed | 30661 | +| total_timesteps | 42416128 | +| train/ | | +| approx_kl | 0.008620952 | +| clip_fraction | 0.306 | +| clip_range | 0.0644 | +| entropy_loss | -6.28 | +| explained_variance | 0.515 | +| learning_rate | 3.99e-05 | +| loss | -0.0246 | +| n_updates | 98660 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.00014 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1383 | +| iterations | 20712 | +| time_elapsed | 30663 | +| total_timesteps | 42418176 | +| train/ | | +| approx_kl | 0.011623583 | +| clip_fraction | 0.326 | +| clip_range | 0.0644 | +| entropy_loss | -6.03 | +| explained_variance | 0.458 | +| learning_rate | 3.99e-05 | +| loss | -0.0249 | +| n_updates | 98664 | +| policy_gradient_loss | -0.0178 | +| value_loss | 9.33e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1383 | +| iterations | 20713 | +| time_elapsed | 30664 | +| total_timesteps | 42420224 | +| train/ | | +| approx_kl | 0.00983184 | +| clip_fraction | 0.321 | +| clip_range | 0.0644 | +| entropy_loss | -6.23 | +| explained_variance | 0.421 | +| learning_rate | 3.99e-05 | +| loss | -0.0239 | +| n_updates | 98668 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000156 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1383 | +| iterations | 20714 | +| time_elapsed | 30666 | +| total_timesteps | 42422272 | +| train/ | | +| approx_kl | 0.013901785 | +| clip_fraction | 0.336 | +| clip_range | 0.0644 | +| entropy_loss | -5.81 | +| explained_variance | 0.547 | +| learning_rate | 3.99e-05 | +| loss | -0.031 | +| n_updates | 98672 | +| policy_gradient_loss | -0.0197 | +| value_loss | 6.36e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1383 | +| iterations | 20715 | +| time_elapsed | 30667 | +| total_timesteps | 42424320 | +| train/ | | +| approx_kl | 0.010867998 | +| clip_fraction | 0.304 | +| clip_range | 0.0644 | +| entropy_loss | -5.59 | +| explained_variance | 0.683 | +| learning_rate | 3.99e-05 | +| loss | -0.0243 | +| n_updates | 98676 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000128 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1383 | +| iterations | 20716 | +| time_elapsed | 30669 | +| total_timesteps | 42426368 | +| train/ | | +| approx_kl | 0.013223479 | +| clip_fraction | 0.312 | +| clip_range | 0.0644 | +| entropy_loss | -5.46 | +| explained_variance | 0.67 | +| learning_rate | 3.99e-05 | +| loss | -0.0232 | +| n_updates | 98680 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000102 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1383 | +| iterations | 20717 | +| time_elapsed | 30671 | +| total_timesteps | 42428416 | +| train/ | | +| approx_kl | 0.012742275 | +| clip_fraction | 0.302 | +| clip_range | 0.0644 | +| entropy_loss | -6.35 | +| explained_variance | 0.116 | +| learning_rate | 3.99e-05 | +| loss | -0.026 | +| n_updates | 98684 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000151 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1383 | +| iterations | 20718 | +| time_elapsed | 30672 | +| total_timesteps | 42430464 | +| train/ | | +| approx_kl | 0.011047101 | +| clip_fraction | 0.32 | +| clip_range | 0.0644 | +| entropy_loss | -6.18 | +| explained_variance | 0.358 | +| learning_rate | 3.99e-05 | +| loss | -0.0247 | +| n_updates | 98688 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000136 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1383 | +| iterations | 20719 | +| time_elapsed | 30674 | +| total_timesteps | 42432512 | +| train/ | | +| approx_kl | 0.013256436 | +| clip_fraction | 0.324 | +| clip_range | 0.0644 | +| entropy_loss | -5.8 | +| explained_variance | 0.352 | +| learning_rate | 3.99e-05 | +| loss | -0.0271 | +| n_updates | 98692 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000191 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1383 | +| iterations | 20720 | +| time_elapsed | 30675 | +| total_timesteps | 42434560 | +| train/ | | +| approx_kl | 0.009870499 | +| clip_fraction | 0.297 | +| clip_range | 0.0644 | +| entropy_loss | -6.26 | +| explained_variance | 0.48 | +| learning_rate | 3.99e-05 | +| loss | -0.0261 | +| n_updates | 98696 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000152 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1383 | +| iterations | 20721 | +| time_elapsed | 30677 | +| total_timesteps | 42436608 | +| train/ | | +| approx_kl | 0.011650778 | +| clip_fraction | 0.279 | +| clip_range | 0.0644 | +| entropy_loss | -6.48 | +| explained_variance | 0.341 | +| learning_rate | 3.99e-05 | +| loss | -0.0205 | +| n_updates | 98700 | +| policy_gradient_loss | -0.0147 | +| value_loss | 0.000284 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1383 | +| iterations | 20722 | +| time_elapsed | 30678 | +| total_timesteps | 42438656 | +| train/ | | +| approx_kl | 0.009440824 | +| clip_fraction | 0.298 | +| clip_range | 0.0644 | +| entropy_loss | -6.3 | +| explained_variance | 0.426 | +| learning_rate | 3.99e-05 | +| loss | -0.0282 | +| n_updates | 98704 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000213 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1383 | +| iterations | 20723 | +| time_elapsed | 30680 | +| total_timesteps | 42440704 | +| train/ | | +| approx_kl | 0.01162857 | +| clip_fraction | 0.347 | +| clip_range | 0.0644 | +| entropy_loss | -5.59 | +| explained_variance | 0.67 | +| learning_rate | 3.99e-05 | +| loss | -0.0274 | +| n_updates | 98708 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000108 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1383 | +| iterations | 20724 | +| time_elapsed | 30681 | +| total_timesteps | 42442752 | +| train/ | | +| approx_kl | 0.010591945 | +| clip_fraction | 0.305 | +| clip_range | 0.0644 | +| entropy_loss | -6.26 | +| explained_variance | 0.37 | +| learning_rate | 3.99e-05 | +| loss | -0.027 | +| n_updates | 98712 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000104 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1383 | +| iterations | 20725 | +| time_elapsed | 30683 | +| total_timesteps | 42444800 | +| train/ | | +| approx_kl | 0.010115333 | +| clip_fraction | 0.298 | +| clip_range | 0.0644 | +| entropy_loss | -6.25 | +| explained_variance | 0.327 | +| learning_rate | 3.99e-05 | +| loss | -0.026 | +| n_updates | 98716 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000204 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1383 | +| iterations | 20726 | +| time_elapsed | 30684 | +| total_timesteps | 42446848 | +| train/ | | +| approx_kl | 0.0132479705 | +| clip_fraction | 0.328 | +| clip_range | 0.0644 | +| entropy_loss | -5.2 | +| explained_variance | 0.673 | +| learning_rate | 3.99e-05 | +| loss | -0.0286 | +| n_updates | 98720 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000118 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1383 | +| iterations | 20727 | +| time_elapsed | 30686 | +| total_timesteps | 42448896 | +| train/ | | +| approx_kl | 0.013822243 | +| clip_fraction | 0.312 | +| clip_range | 0.0644 | +| entropy_loss | -5.94 | +| explained_variance | -0.365 | +| learning_rate | 3.99e-05 | +| loss | -0.0235 | +| n_updates | 98724 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000129 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1383 | +| iterations | 20728 | +| time_elapsed | 30687 | +| total_timesteps | 42450944 | +| train/ | | +| approx_kl | 0.012725377 | +| clip_fraction | 0.345 | +| clip_range | 0.0644 | +| entropy_loss | -6.1 | +| explained_variance | -0.16 | +| learning_rate | 3.99e-05 | +| loss | -0.0266 | +| n_updates | 98728 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.0001 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1383 | +| iterations | 20729 | +| time_elapsed | 30689 | +| total_timesteps | 42452992 | +| train/ | | +| approx_kl | 0.011528685 | +| clip_fraction | 0.296 | +| clip_range | 0.0644 | +| entropy_loss | -5.75 | +| explained_variance | 0.464 | +| learning_rate | 3.99e-05 | +| loss | -0.0209 | +| n_updates | 98732 | +| policy_gradient_loss | -0.0136 | +| value_loss | 0.000244 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1383 | +| iterations | 20730 | +| time_elapsed | 30690 | +| total_timesteps | 42455040 | +| train/ | | +| approx_kl | 0.01193055 | +| clip_fraction | 0.322 | +| clip_range | 0.0644 | +| entropy_loss | -5.59 | +| explained_variance | 0.751 | +| learning_rate | 3.99e-05 | +| loss | -0.0263 | +| n_updates | 98736 | +| policy_gradient_loss | -0.018 | +| value_loss | 8.17e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1383 | +| iterations | 20731 | +| time_elapsed | 30692 | +| total_timesteps | 42457088 | +| train/ | | +| approx_kl | 0.012103226 | +| clip_fraction | 0.299 | +| clip_range | 0.0644 | +| entropy_loss | -5.87 | +| explained_variance | 0.355 | +| learning_rate | 3.99e-05 | +| loss | -0.0264 | +| n_updates | 98740 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000124 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1383 | +| iterations | 20732 | +| time_elapsed | 30694 | +| total_timesteps | 42459136 | +| train/ | | +| approx_kl | 0.011684015 | +| clip_fraction | 0.287 | +| clip_range | 0.0644 | +| entropy_loss | -6.4 | +| explained_variance | 0.241 | +| learning_rate | 3.99e-05 | +| loss | -0.0223 | +| n_updates | 98744 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.00018 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1383 | +| iterations | 20733 | +| time_elapsed | 30695 | +| total_timesteps | 42461184 | +| train/ | | +| approx_kl | 0.008767925 | +| clip_fraction | 0.327 | +| clip_range | 0.0644 | +| entropy_loss | -6.31 | +| explained_variance | 0.569 | +| learning_rate | 3.99e-05 | +| loss | -0.0329 | +| n_updates | 98748 | +| policy_gradient_loss | -0.0183 | +| value_loss | 8.64e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1383 | +| iterations | 20734 | +| time_elapsed | 30697 | +| total_timesteps | 42463232 | +| train/ | | +| approx_kl | 0.009705437 | +| clip_fraction | 0.291 | +| clip_range | 0.0644 | +| entropy_loss | -5.55 | +| explained_variance | 0.471 | +| learning_rate | 3.99e-05 | +| loss | -0.027 | +| n_updates | 98752 | +| policy_gradient_loss | -0.0141 | +| value_loss | 0.000257 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1383 | +| iterations | 20735 | +| time_elapsed | 30698 | +| total_timesteps | 42465280 | +| train/ | | +| approx_kl | 0.012075311 | +| clip_fraction | 0.343 | +| clip_range | 0.0644 | +| entropy_loss | -5.45 | +| explained_variance | 0.74 | +| learning_rate | 3.99e-05 | +| loss | -0.031 | +| n_updates | 98756 | +| policy_gradient_loss | -0.0191 | +| value_loss | 7.28e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1383 | +| iterations | 20736 | +| time_elapsed | 30700 | +| total_timesteps | 42467328 | +| train/ | | +| approx_kl | 0.010843792 | +| clip_fraction | 0.329 | +| clip_range | 0.0644 | +| entropy_loss | -5.25 | +| explained_variance | 0.604 | +| learning_rate | 3.99e-05 | +| loss | -0.0283 | +| n_updates | 98760 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000106 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1383 | +| iterations | 20737 | +| time_elapsed | 30701 | +| total_timesteps | 42469376 | +| train/ | | +| approx_kl | 0.012335759 | +| clip_fraction | 0.319 | +| clip_range | 0.0644 | +| entropy_loss | -5.73 | +| explained_variance | 0.522 | +| learning_rate | 3.99e-05 | +| loss | -0.0279 | +| n_updates | 98764 | +| policy_gradient_loss | -0.0171 | +| value_loss | 6.6e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1383 | +| iterations | 20738 | +| time_elapsed | 30703 | +| total_timesteps | 42471424 | +| train/ | | +| approx_kl | 0.012662709 | +| clip_fraction | 0.319 | +| clip_range | 0.0644 | +| entropy_loss | -4.84 | +| explained_variance | 0.433 | +| learning_rate | 3.99e-05 | +| loss | -0.0238 | +| n_updates | 98768 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000205 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1383 | +| iterations | 20739 | +| time_elapsed | 30704 | +| total_timesteps | 42473472 | +| train/ | | +| approx_kl | 0.012653885 | +| clip_fraction | 0.347 | +| clip_range | 0.0644 | +| entropy_loss | -4.8 | +| explained_variance | 0.252 | +| learning_rate | 3.99e-05 | +| loss | -0.0259 | +| n_updates | 98772 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000247 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1383 | +| iterations | 20740 | +| time_elapsed | 30706 | +| total_timesteps | 42475520 | +| train/ | | +| approx_kl | 0.013715785 | +| clip_fraction | 0.349 | +| clip_range | 0.0644 | +| entropy_loss | -5.87 | +| explained_variance | 0.233 | +| learning_rate | 3.99e-05 | +| loss | -0.0358 | +| n_updates | 98776 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000102 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1383 | +| iterations | 20741 | +| time_elapsed | 30707 | +| total_timesteps | 42477568 | +| train/ | | +| approx_kl | 0.0105759725 | +| clip_fraction | 0.305 | +| clip_range | 0.0644 | +| entropy_loss | -6.43 | +| explained_variance | 0.19 | +| learning_rate | 3.99e-05 | +| loss | -0.0221 | +| n_updates | 98780 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000319 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1383 | +| iterations | 20742 | +| time_elapsed | 30709 | +| total_timesteps | 42479616 | +| train/ | | +| approx_kl | 0.012416182 | +| clip_fraction | 0.315 | +| clip_range | 0.0644 | +| entropy_loss | -5.73 | +| explained_variance | 0.645 | +| learning_rate | 3.99e-05 | +| loss | -0.0278 | +| n_updates | 98784 | +| policy_gradient_loss | -0.0178 | +| value_loss | 6.93e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1383 | +| iterations | 20743 | +| time_elapsed | 30711 | +| total_timesteps | 42481664 | +| train/ | | +| approx_kl | 0.013381667 | +| clip_fraction | 0.274 | +| clip_range | 0.0644 | +| entropy_loss | -5.35 | +| explained_variance | 0.671 | +| learning_rate | 3.99e-05 | +| loss | -0.0219 | +| n_updates | 98788 | +| policy_gradient_loss | -0.014 | +| value_loss | 0.000118 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1383 | +| iterations | 20744 | +| time_elapsed | 30712 | +| total_timesteps | 42483712 | +| train/ | | +| approx_kl | 0.012510013 | +| clip_fraction | 0.324 | +| clip_range | 0.0644 | +| entropy_loss | -5.38 | +| explained_variance | 0.22 | +| learning_rate | 3.99e-05 | +| loss | -0.0257 | +| n_updates | 98792 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000312 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1383 | +| iterations | 20745 | +| time_elapsed | 30714 | +| total_timesteps | 42485760 | +| train/ | | +| approx_kl | 0.011417121 | +| clip_fraction | 0.344 | +| clip_range | 0.0644 | +| entropy_loss | -5.81 | +| explained_variance | 0.18 | +| learning_rate | 3.99e-05 | +| loss | -0.0344 | +| n_updates | 98796 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.00013 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1383 | +| iterations | 20746 | +| time_elapsed | 30715 | +| total_timesteps | 42487808 | +| train/ | | +| approx_kl | 0.013256084 | +| clip_fraction | 0.377 | +| clip_range | 0.0644 | +| entropy_loss | -6.45 | +| explained_variance | -0.0452 | +| learning_rate | 3.99e-05 | +| loss | -0.0298 | +| n_updates | 98800 | +| policy_gradient_loss | -0.0206 | +| value_loss | 6.94e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1383 | +| iterations | 20747 | +| time_elapsed | 30717 | +| total_timesteps | 42489856 | +| train/ | | +| approx_kl | 0.013653936 | +| clip_fraction | 0.3 | +| clip_range | 0.0644 | +| entropy_loss | -5.39 | +| explained_variance | 0.35 | +| learning_rate | 3.99e-05 | +| loss | -0.0241 | +| n_updates | 98804 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000144 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1383 | +| iterations | 20748 | +| time_elapsed | 30718 | +| total_timesteps | 42491904 | +| train/ | | +| approx_kl | 0.014056576 | +| clip_fraction | 0.328 | +| clip_range | 0.0644 | +| entropy_loss | -5.65 | +| explained_variance | 0.53 | +| learning_rate | 3.99e-05 | +| loss | -0.0287 | +| n_updates | 98808 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000117 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1383 | +| iterations | 20749 | +| time_elapsed | 30720 | +| total_timesteps | 42493952 | +| train/ | | +| approx_kl | 0.011545848 | +| clip_fraction | 0.315 | +| clip_range | 0.0644 | +| entropy_loss | -6.27 | +| explained_variance | 0.355 | +| learning_rate | 3.99e-05 | +| loss | -0.0281 | +| n_updates | 98812 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.00014 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1383 | +| iterations | 20750 | +| time_elapsed | 30721 | +| total_timesteps | 42496000 | +| train/ | | +| approx_kl | 0.0137817655 | +| clip_fraction | 0.354 | +| clip_range | 0.0644 | +| entropy_loss | -5.87 | +| explained_variance | -0.351 | +| learning_rate | 3.99e-05 | +| loss | -0.0317 | +| n_updates | 98816 | +| policy_gradient_loss | -0.0207 | +| value_loss | 5.49e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1383 | +| iterations | 20751 | +| time_elapsed | 30723 | +| total_timesteps | 42498048 | +| train/ | | +| approx_kl | 0.011224642 | +| clip_fraction | 0.318 | +| clip_range | 0.0644 | +| entropy_loss | -5.86 | +| explained_variance | 0.774 | +| learning_rate | 3.99e-05 | +| loss | -0.031 | +| n_updates | 98820 | +| policy_gradient_loss | -0.0183 | +| value_loss | 5.45e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1383 | +| iterations | 20752 | +| time_elapsed | 30725 | +| total_timesteps | 42500096 | +| train/ | | +| approx_kl | 0.01097855 | +| clip_fraction | 0.29 | +| clip_range | 0.0644 | +| entropy_loss | -6.19 | +| explained_variance | 0.388 | +| learning_rate | 3.99e-05 | +| loss | -0.0217 | +| n_updates | 98824 | +| policy_gradient_loss | -0.0147 | +| value_loss | 0.000133 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1383 | +| iterations | 20753 | +| time_elapsed | 30726 | +| total_timesteps | 42502144 | +| train/ | | +| approx_kl | 0.01264073 | +| clip_fraction | 0.316 | +| clip_range | 0.0644 | +| entropy_loss | -5.81 | +| explained_variance | 0.479 | +| learning_rate | 3.99e-05 | +| loss | -0.024 | +| n_updates | 98828 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000162 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1383 | +| iterations | 20754 | +| time_elapsed | 30728 | +| total_timesteps | 42504192 | +| train/ | | +| approx_kl | 0.0141177755 | +| clip_fraction | 0.313 | +| clip_range | 0.0644 | +| entropy_loss | -5.5 | +| explained_variance | 0.302 | +| learning_rate | 3.99e-05 | +| loss | -0.0233 | +| n_updates | 98832 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.00014 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1383 | +| iterations | 20755 | +| time_elapsed | 30729 | +| total_timesteps | 42506240 | +| train/ | | +| approx_kl | 0.013356766 | +| clip_fraction | 0.348 | +| clip_range | 0.0644 | +| entropy_loss | -5.98 | +| explained_variance | -0.0192 | +| learning_rate | 3.99e-05 | +| loss | -0.0255 | +| n_updates | 98836 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000121 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1383 | +| iterations | 20756 | +| time_elapsed | 30731 | +| total_timesteps | 42508288 | +| train/ | | +| approx_kl | 0.010786272 | +| clip_fraction | 0.31 | +| clip_range | 0.0644 | +| entropy_loss | -6.33 | +| explained_variance | 0.256 | +| learning_rate | 3.99e-05 | +| loss | -0.0257 | +| n_updates | 98840 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.00022 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1383 | +| iterations | 20757 | +| time_elapsed | 30732 | +| total_timesteps | 42510336 | +| train/ | | +| approx_kl | 0.010791684 | +| clip_fraction | 0.311 | +| clip_range | 0.0644 | +| entropy_loss | -6.46 | +| explained_variance | -0.14 | +| learning_rate | 3.99e-05 | +| loss | -0.0286 | +| n_updates | 98844 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000121 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1383 | +| iterations | 20758 | +| time_elapsed | 30734 | +| total_timesteps | 42512384 | +| train/ | | +| approx_kl | 0.011599828 | +| clip_fraction | 0.289 | +| clip_range | 0.0644 | +| entropy_loss | -5.92 | +| explained_variance | 0.571 | +| learning_rate | 3.99e-05 | +| loss | -0.0265 | +| n_updates | 98848 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000159 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1383 | +| iterations | 20759 | +| time_elapsed | 30735 | +| total_timesteps | 42514432 | +| train/ | | +| approx_kl | 0.012686024 | +| clip_fraction | 0.292 | +| clip_range | 0.0644 | +| entropy_loss | -6.12 | +| explained_variance | 0.323 | +| learning_rate | 3.99e-05 | +| loss | -0.0292 | +| n_updates | 98852 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000114 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1383 | +| iterations | 20760 | +| time_elapsed | 30737 | +| total_timesteps | 42516480 | +| train/ | | +| approx_kl | 0.013787864 | +| clip_fraction | 0.309 | +| clip_range | 0.0644 | +| entropy_loss | -5.68 | +| explained_variance | 0.687 | +| learning_rate | 3.99e-05 | +| loss | -0.0279 | +| n_updates | 98856 | +| policy_gradient_loss | -0.0164 | +| value_loss | 9.39e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1383 | +| iterations | 20761 | +| time_elapsed | 30739 | +| total_timesteps | 42518528 | +| train/ | | +| approx_kl | 0.0129944105 | +| clip_fraction | 0.309 | +| clip_range | 0.0644 | +| entropy_loss | -5.52 | +| explained_variance | 0.457 | +| learning_rate | 3.99e-05 | +| loss | -0.027 | +| n_updates | 98860 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000118 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1383 | +| iterations | 20762 | +| time_elapsed | 30740 | +| total_timesteps | 42520576 | +| train/ | | +| approx_kl | 0.009643963 | +| clip_fraction | 0.314 | +| clip_range | 0.0644 | +| entropy_loss | -5.74 | +| explained_variance | 0.335 | +| learning_rate | 3.99e-05 | +| loss | -0.0265 | +| n_updates | 98864 | +| policy_gradient_loss | -0.012 | +| value_loss | 0.000284 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1383 | +| iterations | 20763 | +| time_elapsed | 30742 | +| total_timesteps | 42522624 | +| train/ | | +| approx_kl | 0.011309036 | +| clip_fraction | 0.35 | +| clip_range | 0.0644 | +| entropy_loss | -5.19 | +| explained_variance | 0.543 | +| learning_rate | 3.99e-05 | +| loss | -0.0237 | +| n_updates | 98868 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.00012 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1383 | +| iterations | 20764 | +| time_elapsed | 30743 | +| total_timesteps | 42524672 | +| train/ | | +| approx_kl | 0.012069274 | +| clip_fraction | 0.32 | +| clip_range | 0.0644 | +| entropy_loss | -5.73 | +| explained_variance | 0.315 | +| learning_rate | 3.99e-05 | +| loss | -0.0272 | +| n_updates | 98872 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.00013 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1383 | +| iterations | 20765 | +| time_elapsed | 30745 | +| total_timesteps | 42526720 | +| train/ | | +| approx_kl | 0.010284647 | +| clip_fraction | 0.316 | +| clip_range | 0.0644 | +| entropy_loss | -6.34 | +| explained_variance | 0.334 | +| learning_rate | 3.99e-05 | +| loss | -0.0266 | +| n_updates | 98876 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000148 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1383 | +| iterations | 20766 | +| time_elapsed | 30746 | +| total_timesteps | 42528768 | +| train/ | | +| approx_kl | 0.01233468 | +| clip_fraction | 0.338 | +| clip_range | 0.0644 | +| entropy_loss | -5.68 | +| explained_variance | 0.675 | +| learning_rate | 3.99e-05 | +| loss | -0.0293 | +| n_updates | 98880 | +| policy_gradient_loss | -0.0174 | +| value_loss | 7.82e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1383 | +| iterations | 20767 | +| time_elapsed | 30748 | +| total_timesteps | 42530816 | +| train/ | | +| approx_kl | 0.014604531 | +| clip_fraction | 0.35 | +| clip_range | 0.0644 | +| entropy_loss | -6.06 | +| explained_variance | -0.0638 | +| learning_rate | 3.99e-05 | +| loss | -0.0337 | +| n_updates | 98884 | +| policy_gradient_loss | -0.0184 | +| value_loss | 7.41e-05 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1383 | +| iterations | 20768 | +| time_elapsed | 30749 | +| total_timesteps | 42532864 | +| train/ | | +| approx_kl | 0.0139718 | +| clip_fraction | 0.322 | +| clip_range | 0.0644 | +| entropy_loss | -5.72 | +| explained_variance | 0.51 | +| learning_rate | 3.99e-05 | +| loss | -0.0241 | +| n_updates | 98888 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000124 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1383 | +| iterations | 20769 | +| time_elapsed | 30751 | +| total_timesteps | 42534912 | +| train/ | | +| approx_kl | 0.013616795 | +| clip_fraction | 0.36 | +| clip_range | 0.0644 | +| entropy_loss | -5.78 | +| explained_variance | 0.422 | +| learning_rate | 3.99e-05 | +| loss | -0.0342 | +| n_updates | 98892 | +| policy_gradient_loss | -0.0205 | +| value_loss | 7.42e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1383 | +| iterations | 20770 | +| time_elapsed | 30752 | +| total_timesteps | 42536960 | +| train/ | | +| approx_kl | 0.011757124 | +| clip_fraction | 0.319 | +| clip_range | 0.0644 | +| entropy_loss | -5.81 | +| explained_variance | 0.415 | +| learning_rate | 3.99e-05 | +| loss | -0.029 | +| n_updates | 98896 | +| policy_gradient_loss | -0.017 | +| value_loss | 9.58e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1383 | +| iterations | 20771 | +| time_elapsed | 30754 | +| total_timesteps | 42539008 | +| train/ | | +| approx_kl | 0.012897237 | +| clip_fraction | 0.331 | +| clip_range | 0.0644 | +| entropy_loss | -5.35 | +| explained_variance | 0.513 | +| learning_rate | 3.99e-05 | +| loss | -0.024 | +| n_updates | 98900 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000146 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.315 | +| time/ | | +| fps | 1383 | +| iterations | 20772 | +| time_elapsed | 30756 | +| total_timesteps | 42541056 | +| train/ | | +| approx_kl | 0.01118891 | +| clip_fraction | 0.327 | +| clip_range | 0.0644 | +| entropy_loss | -6.03 | +| explained_variance | -0.16 | +| learning_rate | 3.99e-05 | +| loss | -0.0307 | +| n_updates | 98904 | +| policy_gradient_loss | -0.0186 | +| value_loss | 9.26e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1383 | +| iterations | 20773 | +| time_elapsed | 30757 | +| total_timesteps | 42543104 | +| train/ | | +| approx_kl | 0.011314213 | +| clip_fraction | 0.268 | +| clip_range | 0.0644 | +| entropy_loss | -5.87 | +| explained_variance | 0.433 | +| learning_rate | 3.99e-05 | +| loss | -0.0201 | +| n_updates | 98908 | +| policy_gradient_loss | -0.0123 | +| value_loss | 0.000201 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1383 | +| iterations | 20774 | +| time_elapsed | 30759 | +| total_timesteps | 42545152 | +| train/ | | +| approx_kl | 0.012953687 | +| clip_fraction | 0.318 | +| clip_range | 0.0644 | +| entropy_loss | -6.07 | +| explained_variance | 0.388 | +| learning_rate | 3.99e-05 | +| loss | -0.0242 | +| n_updates | 98912 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000214 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1383 | +| iterations | 20775 | +| time_elapsed | 30760 | +| total_timesteps | 42547200 | +| train/ | | +| approx_kl | 0.011994128 | +| clip_fraction | 0.34 | +| clip_range | 0.0644 | +| entropy_loss | -6.12 | +| explained_variance | 0.485 | +| learning_rate | 3.99e-05 | +| loss | -0.0311 | +| n_updates | 98916 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.00014 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1383 | +| iterations | 20776 | +| time_elapsed | 30762 | +| total_timesteps | 42549248 | +| train/ | | +| approx_kl | 0.01447543 | +| clip_fraction | 0.342 | +| clip_range | 0.0644 | +| entropy_loss | -5.83 | +| explained_variance | 0.743 | +| learning_rate | 3.99e-05 | +| loss | -0.0354 | +| n_updates | 98920 | +| policy_gradient_loss | -0.0213 | +| value_loss | 6.33e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1383 | +| iterations | 20777 | +| time_elapsed | 30763 | +| total_timesteps | 42551296 | +| train/ | | +| approx_kl | 0.013716845 | +| clip_fraction | 0.339 | +| clip_range | 0.0644 | +| entropy_loss | -5.89 | +| explained_variance | -0.135 | +| learning_rate | 3.99e-05 | +| loss | -0.0275 | +| n_updates | 98924 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000154 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1383 | +| iterations | 20778 | +| time_elapsed | 30765 | +| total_timesteps | 42553344 | +| train/ | | +| approx_kl | 0.014255296 | +| clip_fraction | 0.349 | +| clip_range | 0.0644 | +| entropy_loss | -5.9 | +| explained_variance | 0.225 | +| learning_rate | 3.99e-05 | +| loss | -0.0289 | +| n_updates | 98928 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000143 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1383 | +| iterations | 20779 | +| time_elapsed | 30766 | +| total_timesteps | 42555392 | +| train/ | | +| approx_kl | 0.012431545 | +| clip_fraction | 0.307 | +| clip_range | 0.0644 | +| entropy_loss | -5.95 | +| explained_variance | 0.305 | +| learning_rate | 3.99e-05 | +| loss | -0.0203 | +| n_updates | 98932 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000165 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1383 | +| iterations | 20780 | +| time_elapsed | 30768 | +| total_timesteps | 42557440 | +| train/ | | +| approx_kl | 0.011699491 | +| clip_fraction | 0.33 | +| clip_range | 0.0644 | +| entropy_loss | -5.99 | +| explained_variance | 0.343 | +| learning_rate | 3.99e-05 | +| loss | -0.0263 | +| n_updates | 98936 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000106 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1383 | +| iterations | 20781 | +| time_elapsed | 30769 | +| total_timesteps | 42559488 | +| train/ | | +| approx_kl | 0.010681836 | +| clip_fraction | 0.315 | +| clip_range | 0.0644 | +| entropy_loss | -6.05 | +| explained_variance | 0.592 | +| learning_rate | 3.99e-05 | +| loss | -0.0221 | +| n_updates | 98940 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000157 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1383 | +| iterations | 20782 | +| time_elapsed | 30771 | +| total_timesteps | 42561536 | +| train/ | | +| approx_kl | 0.008318529 | +| clip_fraction | 0.305 | +| clip_range | 0.0644 | +| entropy_loss | -6.36 | +| explained_variance | 0.451 | +| learning_rate | 3.99e-05 | +| loss | -0.0291 | +| n_updates | 98944 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000194 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1383 | +| iterations | 20783 | +| time_elapsed | 30772 | +| total_timesteps | 42563584 | +| train/ | | +| approx_kl | 0.009555515 | +| clip_fraction | 0.314 | +| clip_range | 0.0644 | +| entropy_loss | -6.12 | +| explained_variance | 0.417 | +| learning_rate | 3.99e-05 | +| loss | -0.0287 | +| n_updates | 98948 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000101 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1383 | +| iterations | 20784 | +| time_elapsed | 30774 | +| total_timesteps | 42565632 | +| train/ | | +| approx_kl | 0.012388274 | +| clip_fraction | 0.336 | +| clip_range | 0.0644 | +| entropy_loss | -5.98 | +| explained_variance | 0.36 | +| learning_rate | 3.99e-05 | +| loss | -0.0254 | +| n_updates | 98952 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1383 | +| iterations | 20785 | +| time_elapsed | 30775 | +| total_timesteps | 42567680 | +| train/ | | +| approx_kl | 0.010460553 | +| clip_fraction | 0.294 | +| clip_range | 0.0644 | +| entropy_loss | -6.06 | +| explained_variance | 0.427 | +| learning_rate | 3.99e-05 | +| loss | -0.0237 | +| n_updates | 98956 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000291 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1383 | +| iterations | 20786 | +| time_elapsed | 30777 | +| total_timesteps | 42569728 | +| train/ | | +| approx_kl | 0.010100048 | +| clip_fraction | 0.296 | +| clip_range | 0.0644 | +| entropy_loss | -5.79 | +| explained_variance | 0.36 | +| learning_rate | 3.99e-05 | +| loss | -0.0251 | +| n_updates | 98960 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000179 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1383 | +| iterations | 20787 | +| time_elapsed | 30779 | +| total_timesteps | 42571776 | +| train/ | | +| approx_kl | 0.0138820885 | +| clip_fraction | 0.322 | +| clip_range | 0.0644 | +| entropy_loss | -5.79 | +| explained_variance | 0.458 | +| learning_rate | 3.99e-05 | +| loss | -0.0226 | +| n_updates | 98964 | +| policy_gradient_loss | -0.0146 | +| value_loss | 0.000276 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1383 | +| iterations | 20788 | +| time_elapsed | 30780 | +| total_timesteps | 42573824 | +| train/ | | +| approx_kl | 0.01223815 | +| clip_fraction | 0.331 | +| clip_range | 0.0644 | +| entropy_loss | -6.02 | +| explained_variance | 0.315 | +| learning_rate | 3.99e-05 | +| loss | -0.0311 | +| n_updates | 98968 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000136 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1383 | +| iterations | 20789 | +| time_elapsed | 30782 | +| total_timesteps | 42575872 | +| train/ | | +| approx_kl | 0.011639863 | +| clip_fraction | 0.305 | +| clip_range | 0.0644 | +| entropy_loss | -6.07 | +| explained_variance | 0.334 | +| learning_rate | 3.99e-05 | +| loss | -0.0216 | +| n_updates | 98972 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000296 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1383 | +| iterations | 20790 | +| time_elapsed | 30783 | +| total_timesteps | 42577920 | +| train/ | | +| approx_kl | 0.012865398 | +| clip_fraction | 0.334 | +| clip_range | 0.0644 | +| entropy_loss | -5.97 | +| explained_variance | 0.453 | +| learning_rate | 3.99e-05 | +| loss | -0.0273 | +| n_updates | 98976 | +| policy_gradient_loss | -0.0183 | +| value_loss | 9.34e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1383 | +| iterations | 20791 | +| time_elapsed | 30785 | +| total_timesteps | 42579968 | +| train/ | | +| approx_kl | 0.012692319 | +| clip_fraction | 0.317 | +| clip_range | 0.0644 | +| entropy_loss | -6.52 | +| explained_variance | -0.312 | +| learning_rate | 3.99e-05 | +| loss | -0.0322 | +| n_updates | 98980 | +| policy_gradient_loss | -0.0185 | +| value_loss | 7.28e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1383 | +| iterations | 20792 | +| time_elapsed | 30786 | +| total_timesteps | 42582016 | +| train/ | | +| approx_kl | 0.0107462965 | +| clip_fraction | 0.292 | +| clip_range | 0.0644 | +| entropy_loss | -6.54 | +| explained_variance | 0.457 | +| learning_rate | 3.99e-05 | +| loss | -0.0282 | +| n_updates | 98984 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000107 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1383 | +| iterations | 20793 | +| time_elapsed | 30788 | +| total_timesteps | 42584064 | +| train/ | | +| approx_kl | 0.010992387 | +| clip_fraction | 0.317 | +| clip_range | 0.0644 | +| entropy_loss | -6.01 | +| explained_variance | 0.39 | +| learning_rate | 3.99e-05 | +| loss | -0.0186 | +| n_updates | 98988 | +| policy_gradient_loss | -0.0143 | +| value_loss | 0.000259 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1383 | +| iterations | 20794 | +| time_elapsed | 30789 | +| total_timesteps | 42586112 | +| train/ | | +| approx_kl | 0.00948422 | +| clip_fraction | 0.302 | +| clip_range | 0.0644 | +| entropy_loss | -5.98 | +| explained_variance | 0.546 | +| learning_rate | 3.99e-05 | +| loss | -0.025 | +| n_updates | 98992 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000141 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1383 | +| iterations | 20795 | +| time_elapsed | 30791 | +| total_timesteps | 42588160 | +| train/ | | +| approx_kl | 0.008052002 | +| clip_fraction | 0.285 | +| clip_range | 0.0644 | +| entropy_loss | -6.04 | +| explained_variance | 0.395 | +| learning_rate | 3.99e-05 | +| loss | -0.0224 | +| n_updates | 98996 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.000271 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1383 | +| iterations | 20796 | +| time_elapsed | 30792 | +| total_timesteps | 42590208 | +| train/ | | +| approx_kl | 0.0073696906 | +| clip_fraction | 0.304 | +| clip_range | 0.0644 | +| entropy_loss | -6.45 | +| explained_variance | 0.325 | +| learning_rate | 3.99e-05 | +| loss | -0.0266 | +| n_updates | 99000 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000165 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1383 | +| iterations | 20797 | +| time_elapsed | 30794 | +| total_timesteps | 42592256 | +| train/ | | +| approx_kl | 0.009829712 | +| clip_fraction | 0.315 | +| clip_range | 0.0644 | +| entropy_loss | -5.59 | +| explained_variance | 0.775 | +| learning_rate | 3.99e-05 | +| loss | -0.0299 | +| n_updates | 99004 | +| policy_gradient_loss | -0.0178 | +| value_loss | 8.37e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1383 | +| iterations | 20798 | +| time_elapsed | 30795 | +| total_timesteps | 42594304 | +| train/ | | +| approx_kl | 0.013556698 | +| clip_fraction | 0.313 | +| clip_range | 0.0644 | +| entropy_loss | -5.89 | +| explained_variance | -0.0526 | +| learning_rate | 3.99e-05 | +| loss | -0.0298 | +| n_updates | 99008 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000208 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1383 | +| iterations | 20799 | +| time_elapsed | 30797 | +| total_timesteps | 42596352 | +| train/ | | +| approx_kl | 0.010376626 | +| clip_fraction | 0.3 | +| clip_range | 0.0644 | +| entropy_loss | -5.96 | +| explained_variance | 0.631 | +| learning_rate | 3.99e-05 | +| loss | -0.0193 | +| n_updates | 99012 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000137 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1383 | +| iterations | 20800 | +| time_elapsed | 30798 | +| total_timesteps | 42598400 | +| train/ | | +| approx_kl | 0.012326872 | +| clip_fraction | 0.323 | +| clip_range | 0.0644 | +| entropy_loss | -6.05 | +| explained_variance | 0.198 | +| learning_rate | 3.99e-05 | +| loss | -0.0208 | +| n_updates | 99016 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000282 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1383 | +| iterations | 20801 | +| time_elapsed | 30800 | +| total_timesteps | 42600448 | +| train/ | | +| approx_kl | 0.013155409 | +| clip_fraction | 0.341 | +| clip_range | 0.0644 | +| entropy_loss | -5.98 | +| explained_variance | 0.396 | +| learning_rate | 3.99e-05 | +| loss | -0.0321 | +| n_updates | 99020 | +| policy_gradient_loss | -0.0198 | +| value_loss | 8.76e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1383 | +| iterations | 20802 | +| time_elapsed | 30801 | +| total_timesteps | 42602496 | +| train/ | | +| approx_kl | 0.0142936185 | +| clip_fraction | 0.344 | +| clip_range | 0.0643 | +| entropy_loss | -6.1 | +| explained_variance | 0.272 | +| learning_rate | 3.99e-05 | +| loss | -0.0317 | +| n_updates | 99024 | +| policy_gradient_loss | -0.0193 | +| value_loss | 7.55e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1383 | +| iterations | 20803 | +| time_elapsed | 30803 | +| total_timesteps | 42604544 | +| train/ | | +| approx_kl | 0.012862892 | +| clip_fraction | 0.337 | +| clip_range | 0.0643 | +| entropy_loss | -6.01 | +| explained_variance | 0.47 | +| learning_rate | 3.99e-05 | +| loss | -0.0282 | +| n_updates | 99028 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1383 | +| iterations | 20804 | +| time_elapsed | 30804 | +| total_timesteps | 42606592 | +| train/ | | +| approx_kl | 0.011957309 | +| clip_fraction | 0.324 | +| clip_range | 0.0643 | +| entropy_loss | -5.81 | +| explained_variance | 0.347 | +| learning_rate | 3.99e-05 | +| loss | -0.0291 | +| n_updates | 99032 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000314 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1383 | +| iterations | 20805 | +| time_elapsed | 30806 | +| total_timesteps | 42608640 | +| train/ | | +| approx_kl | 0.009692784 | +| clip_fraction | 0.317 | +| clip_range | 0.0643 | +| entropy_loss | -5.89 | +| explained_variance | 0.482 | +| learning_rate | 3.99e-05 | +| loss | -0.0211 | +| n_updates | 99036 | +| policy_gradient_loss | -0.0147 | +| value_loss | 0.000295 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1383 | +| iterations | 20806 | +| time_elapsed | 30807 | +| total_timesteps | 42610688 | +| train/ | | +| approx_kl | 0.011360982 | +| clip_fraction | 0.336 | +| clip_range | 0.0643 | +| entropy_loss | -5.33 | +| explained_variance | 0.733 | +| learning_rate | 3.99e-05 | +| loss | -0.0331 | +| n_updates | 99040 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000105 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1383 | +| iterations | 20807 | +| time_elapsed | 30809 | +| total_timesteps | 42612736 | +| train/ | | +| approx_kl | 0.012547017 | +| clip_fraction | 0.35 | +| clip_range | 0.0643 | +| entropy_loss | -5.59 | +| explained_variance | 0.711 | +| learning_rate | 3.99e-05 | +| loss | -0.0317 | +| n_updates | 99044 | +| policy_gradient_loss | -0.0203 | +| value_loss | 7.81e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1383 | +| iterations | 20808 | +| time_elapsed | 30811 | +| total_timesteps | 42614784 | +| train/ | | +| approx_kl | 0.013742212 | +| clip_fraction | 0.34 | +| clip_range | 0.0643 | +| entropy_loss | -6.03 | +| explained_variance | 0.348 | +| learning_rate | 3.99e-05 | +| loss | -0.0256 | +| n_updates | 99048 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000144 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1383 | +| iterations | 20809 | +| time_elapsed | 30812 | +| total_timesteps | 42616832 | +| train/ | | +| approx_kl | 0.013106076 | +| clip_fraction | 0.331 | +| clip_range | 0.0643 | +| entropy_loss | -6.27 | +| explained_variance | -0.0254 | +| learning_rate | 3.99e-05 | +| loss | -0.0325 | +| n_updates | 99052 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000114 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1383 | +| iterations | 20810 | +| time_elapsed | 30814 | +| total_timesteps | 42618880 | +| train/ | | +| approx_kl | 0.008102147 | +| clip_fraction | 0.283 | +| clip_range | 0.0643 | +| entropy_loss | -6.37 | +| explained_variance | 0.533 | +| learning_rate | 3.99e-05 | +| loss | -0.0267 | +| n_updates | 99056 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.000147 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1383 | +| iterations | 20811 | +| time_elapsed | 30815 | +| total_timesteps | 42620928 | +| train/ | | +| approx_kl | 0.011988077 | +| clip_fraction | 0.312 | +| clip_range | 0.0643 | +| entropy_loss | -6.17 | +| explained_variance | 0.505 | +| learning_rate | 3.99e-05 | +| loss | -0.0217 | +| n_updates | 99060 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000141 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1383 | +| iterations | 20812 | +| time_elapsed | 30817 | +| total_timesteps | 42622976 | +| train/ | | +| approx_kl | 0.011925226 | +| clip_fraction | 0.327 | +| clip_range | 0.0643 | +| entropy_loss | -5.95 | +| explained_variance | 0.212 | +| learning_rate | 3.99e-05 | +| loss | -0.0309 | +| n_updates | 99064 | +| policy_gradient_loss | -0.0181 | +| value_loss | 9.83e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1383 | +| iterations | 20813 | +| time_elapsed | 30818 | +| total_timesteps | 42625024 | +| train/ | | +| approx_kl | 0.009674818 | +| clip_fraction | 0.298 | +| clip_range | 0.0643 | +| entropy_loss | -5.73 | +| explained_variance | 0.519 | +| learning_rate | 3.99e-05 | +| loss | -0.0243 | +| n_updates | 99068 | +| policy_gradient_loss | -0.0135 | +| value_loss | 0.00026 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1383 | +| iterations | 20814 | +| time_elapsed | 30820 | +| total_timesteps | 42627072 | +| train/ | | +| approx_kl | 0.008295998 | +| clip_fraction | 0.296 | +| clip_range | 0.0643 | +| entropy_loss | -5.93 | +| explained_variance | 0.232 | +| learning_rate | 3.99e-05 | +| loss | -0.0255 | +| n_updates | 99072 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000274 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1383 | +| iterations | 20815 | +| time_elapsed | 30821 | +| total_timesteps | 42629120 | +| train/ | | +| approx_kl | 0.009866318 | +| clip_fraction | 0.315 | +| clip_range | 0.0643 | +| entropy_loss | -6.32 | +| explained_variance | 0.612 | +| learning_rate | 3.99e-05 | +| loss | -0.029 | +| n_updates | 99076 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000101 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1383 | +| iterations | 20816 | +| time_elapsed | 30823 | +| total_timesteps | 42631168 | +| train/ | | +| approx_kl | 0.011017675 | +| clip_fraction | 0.325 | +| clip_range | 0.0643 | +| entropy_loss | -6.26 | +| explained_variance | 0.419 | +| learning_rate | 3.99e-05 | +| loss | -0.0292 | +| n_updates | 99080 | +| policy_gradient_loss | -0.0187 | +| value_loss | 9.19e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1383 | +| iterations | 20817 | +| time_elapsed | 30825 | +| total_timesteps | 42633216 | +| train/ | | +| approx_kl | 0.009029224 | +| clip_fraction | 0.289 | +| clip_range | 0.0643 | +| entropy_loss | -6.53 | +| explained_variance | 0.469 | +| learning_rate | 3.99e-05 | +| loss | -0.0256 | +| n_updates | 99084 | +| policy_gradient_loss | -0.0155 | +| value_loss | 8.31e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1383 | +| iterations | 20818 | +| time_elapsed | 30826 | +| total_timesteps | 42635264 | +| train/ | | +| approx_kl | 0.009623721 | +| clip_fraction | 0.303 | +| clip_range | 0.0643 | +| entropy_loss | -5.94 | +| explained_variance | 0.43 | +| learning_rate | 3.99e-05 | +| loss | -0.0243 | +| n_updates | 99088 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000202 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1383 | +| iterations | 20819 | +| time_elapsed | 30828 | +| total_timesteps | 42637312 | +| train/ | | +| approx_kl | 0.01314828 | +| clip_fraction | 0.322 | +| clip_range | 0.0643 | +| entropy_loss | -5.56 | +| explained_variance | 0.729 | +| learning_rate | 3.99e-05 | +| loss | -0.0306 | +| n_updates | 99092 | +| policy_gradient_loss | -0.0174 | +| value_loss | 8.63e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1383 | +| iterations | 20820 | +| time_elapsed | 30829 | +| total_timesteps | 42639360 | +| train/ | | +| approx_kl | 0.010859561 | +| clip_fraction | 0.278 | +| clip_range | 0.0643 | +| entropy_loss | -5.86 | +| explained_variance | 0.287 | +| learning_rate | 3.99e-05 | +| loss | -0.0209 | +| n_updates | 99096 | +| policy_gradient_loss | -0.0141 | +| value_loss | 0.000354 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1383 | +| iterations | 20821 | +| time_elapsed | 30831 | +| total_timesteps | 42641408 | +| train/ | | +| approx_kl | 0.01307385 | +| clip_fraction | 0.304 | +| clip_range | 0.0643 | +| entropy_loss | -6.4 | +| explained_variance | 0.0495 | +| learning_rate | 3.99e-05 | +| loss | -0.0274 | +| n_updates | 99100 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000257 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1383 | +| iterations | 20822 | +| time_elapsed | 30832 | +| total_timesteps | 42643456 | +| train/ | | +| approx_kl | 0.010133654 | +| clip_fraction | 0.307 | +| clip_range | 0.0643 | +| entropy_loss | -5.66 | +| explained_variance | 0.544 | +| learning_rate | 3.99e-05 | +| loss | -0.0256 | +| n_updates | 99104 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000146 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1383 | +| iterations | 20823 | +| time_elapsed | 30834 | +| total_timesteps | 42645504 | +| train/ | | +| approx_kl | 0.011541415 | +| clip_fraction | 0.328 | +| clip_range | 0.0643 | +| entropy_loss | -5.86 | +| explained_variance | 0.253 | +| learning_rate | 3.99e-05 | +| loss | -0.0325 | +| n_updates | 99108 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000105 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1383 | +| iterations | 20824 | +| time_elapsed | 30835 | +| total_timesteps | 42647552 | +| train/ | | +| approx_kl | 0.010062226 | +| clip_fraction | 0.298 | +| clip_range | 0.0643 | +| entropy_loss | -6.43 | +| explained_variance | 0.183 | +| learning_rate | 3.99e-05 | +| loss | -0.0257 | +| n_updates | 99112 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000169 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1383 | +| iterations | 20825 | +| time_elapsed | 30837 | +| total_timesteps | 42649600 | +| train/ | | +| approx_kl | 0.010177823 | +| clip_fraction | 0.312 | +| clip_range | 0.0643 | +| entropy_loss | -6.29 | +| explained_variance | 0.00119 | +| learning_rate | 3.99e-05 | +| loss | -0.0207 | +| n_updates | 99116 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000173 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1383 | +| iterations | 20826 | +| time_elapsed | 30838 | +| total_timesteps | 42651648 | +| train/ | | +| approx_kl | 0.010955975 | +| clip_fraction | 0.308 | +| clip_range | 0.0643 | +| entropy_loss | -5.24 | +| explained_variance | 0.583 | +| learning_rate | 3.99e-05 | +| loss | -0.0279 | +| n_updates | 99120 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000142 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1383 | +| iterations | 20827 | +| time_elapsed | 30840 | +| total_timesteps | 42653696 | +| train/ | | +| approx_kl | 0.013021911 | +| clip_fraction | 0.346 | +| clip_range | 0.0643 | +| entropy_loss | -6.04 | +| explained_variance | 0.278 | +| learning_rate | 3.99e-05 | +| loss | -0.0283 | +| n_updates | 99124 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000143 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1383 | +| iterations | 20828 | +| time_elapsed | 30841 | +| total_timesteps | 42655744 | +| train/ | | +| approx_kl | 0.0110954065 | +| clip_fraction | 0.289 | +| clip_range | 0.0643 | +| entropy_loss | -6.16 | +| explained_variance | 0.13 | +| learning_rate | 3.99e-05 | +| loss | -0.0255 | +| n_updates | 99128 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.000234 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1383 | +| iterations | 20829 | +| time_elapsed | 30843 | +| total_timesteps | 42657792 | +| train/ | | +| approx_kl | 0.0119108055 | +| clip_fraction | 0.295 | +| clip_range | 0.0643 | +| entropy_loss | -6.05 | +| explained_variance | 0.206 | +| learning_rate | 3.99e-05 | +| loss | -0.0245 | +| n_updates | 99132 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000274 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1383 | +| iterations | 20830 | +| time_elapsed | 30844 | +| total_timesteps | 42659840 | +| train/ | | +| approx_kl | 0.013018607 | +| clip_fraction | 0.324 | +| clip_range | 0.0643 | +| entropy_loss | -5.79 | +| explained_variance | 0.489 | +| learning_rate | 3.99e-05 | +| loss | -0.0318 | +| n_updates | 99136 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000141 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1383 | +| iterations | 20831 | +| time_elapsed | 30846 | +| total_timesteps | 42661888 | +| train/ | | +| approx_kl | 0.014980022 | +| clip_fraction | 0.347 | +| clip_range | 0.0643 | +| entropy_loss | -5.42 | +| explained_variance | 0.767 | +| learning_rate | 3.99e-05 | +| loss | -0.0282 | +| n_updates | 99140 | +| policy_gradient_loss | -0.02 | +| value_loss | 7.04e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1383 | +| iterations | 20832 | +| time_elapsed | 30848 | +| total_timesteps | 42663936 | +| train/ | | +| approx_kl | 0.014141124 | +| clip_fraction | 0.357 | +| clip_range | 0.0643 | +| entropy_loss | -5.32 | +| explained_variance | 0.704 | +| learning_rate | 3.99e-05 | +| loss | -0.0332 | +| n_updates | 99144 | +| policy_gradient_loss | -0.0198 | +| value_loss | 5.55e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1383 | +| iterations | 20833 | +| time_elapsed | 30849 | +| total_timesteps | 42665984 | +| train/ | | +| approx_kl | 0.008995175 | +| clip_fraction | 0.31 | +| clip_range | 0.0643 | +| entropy_loss | -6.58 | +| explained_variance | 0.0239 | +| learning_rate | 3.99e-05 | +| loss | -0.0252 | +| n_updates | 99148 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000193 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1383 | +| iterations | 20834 | +| time_elapsed | 30851 | +| total_timesteps | 42668032 | +| train/ | | +| approx_kl | 0.012361154 | +| clip_fraction | 0.312 | +| clip_range | 0.0643 | +| entropy_loss | -6.43 | +| explained_variance | 0.371 | +| learning_rate | 3.99e-05 | +| loss | -0.029 | +| n_updates | 99152 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000118 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1383 | +| iterations | 20835 | +| time_elapsed | 30852 | +| total_timesteps | 42670080 | +| train/ | | +| approx_kl | 0.009841247 | +| clip_fraction | 0.31 | +| clip_range | 0.0643 | +| entropy_loss | -6.55 | +| explained_variance | 0.325 | +| learning_rate | 3.99e-05 | +| loss | -0.0269 | +| n_updates | 99156 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000149 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1383 | +| iterations | 20836 | +| time_elapsed | 30854 | +| total_timesteps | 42672128 | +| train/ | | +| approx_kl | 0.009850863 | +| clip_fraction | 0.316 | +| clip_range | 0.0643 | +| entropy_loss | -6.6 | +| explained_variance | 0.404 | +| learning_rate | 3.99e-05 | +| loss | -0.0331 | +| n_updates | 99160 | +| policy_gradient_loss | -0.0186 | +| value_loss | 9.65e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1383 | +| iterations | 20837 | +| time_elapsed | 30855 | +| total_timesteps | 42674176 | +| train/ | | +| approx_kl | 0.0083564855 | +| clip_fraction | 0.283 | +| clip_range | 0.0643 | +| entropy_loss | -6.87 | +| explained_variance | 0.079 | +| learning_rate | 3.99e-05 | +| loss | -0.0171 | +| n_updates | 99164 | +| policy_gradient_loss | -0.0139 | +| value_loss | 0.000211 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1383 | +| iterations | 20838 | +| time_elapsed | 30857 | +| total_timesteps | 42676224 | +| train/ | | +| approx_kl | 0.009577998 | +| clip_fraction | 0.276 | +| clip_range | 0.0643 | +| entropy_loss | -5.78 | +| explained_variance | 0.601 | +| learning_rate | 3.99e-05 | +| loss | -0.0229 | +| n_updates | 99168 | +| policy_gradient_loss | -0.0142 | +| value_loss | 0.000216 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1383 | +| iterations | 20839 | +| time_elapsed | 30858 | +| total_timesteps | 42678272 | +| train/ | | +| approx_kl | 0.014498892 | +| clip_fraction | 0.317 | +| clip_range | 0.0643 | +| entropy_loss | -4.75 | +| explained_variance | 0.443 | +| learning_rate | 3.99e-05 | +| loss | -0.0286 | +| n_updates | 99172 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000207 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1383 | +| iterations | 20840 | +| time_elapsed | 30860 | +| total_timesteps | 42680320 | +| train/ | | +| approx_kl | 0.0130053945 | +| clip_fraction | 0.375 | +| clip_range | 0.0643 | +| entropy_loss | -5.5 | +| explained_variance | 0.55 | +| learning_rate | 3.99e-05 | +| loss | -0.0321 | +| n_updates | 99176 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000116 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1383 | +| iterations | 20841 | +| time_elapsed | 30861 | +| total_timesteps | 42682368 | +| train/ | | +| approx_kl | 0.011997936 | +| clip_fraction | 0.331 | +| clip_range | 0.0643 | +| entropy_loss | -5.8 | +| explained_variance | 0.329 | +| learning_rate | 3.99e-05 | +| loss | -0.0239 | +| n_updates | 99180 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000122 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1383 | +| iterations | 20842 | +| time_elapsed | 30863 | +| total_timesteps | 42684416 | +| train/ | | +| approx_kl | 0.010988567 | +| clip_fraction | 0.295 | +| clip_range | 0.0643 | +| entropy_loss | -6.83 | +| explained_variance | 0.0133 | +| learning_rate | 3.99e-05 | +| loss | -0.0235 | +| n_updates | 99184 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000221 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1383 | +| iterations | 20843 | +| time_elapsed | 30864 | +| total_timesteps | 42686464 | +| train/ | | +| approx_kl | 0.010695614 | +| clip_fraction | 0.311 | +| clip_range | 0.0643 | +| entropy_loss | -5.85 | +| explained_variance | 0.499 | +| learning_rate | 3.99e-05 | +| loss | -0.0264 | +| n_updates | 99188 | +| policy_gradient_loss | -0.0135 | +| value_loss | 0.000288 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1383 | +| iterations | 20844 | +| time_elapsed | 30866 | +| total_timesteps | 42688512 | +| train/ | | +| approx_kl | 0.013848366 | +| clip_fraction | 0.307 | +| clip_range | 0.0643 | +| entropy_loss | -5.29 | +| explained_variance | 0.581 | +| learning_rate | 3.99e-05 | +| loss | -0.0266 | +| n_updates | 99192 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000235 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1383 | +| iterations | 20845 | +| time_elapsed | 30867 | +| total_timesteps | 42690560 | +| train/ | | +| approx_kl | 0.011583639 | +| clip_fraction | 0.329 | +| clip_range | 0.0643 | +| entropy_loss | -6.2 | +| explained_variance | 0.255 | +| learning_rate | 3.99e-05 | +| loss | -0.027 | +| n_updates | 99196 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000174 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1383 | +| iterations | 20846 | +| time_elapsed | 30869 | +| total_timesteps | 42692608 | +| train/ | | +| approx_kl | 0.009086666 | +| clip_fraction | 0.299 | +| clip_range | 0.0643 | +| entropy_loss | -5.81 | +| explained_variance | 0.519 | +| learning_rate | 3.99e-05 | +| loss | -0.0237 | +| n_updates | 99200 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.00022 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1383 | +| iterations | 20847 | +| time_elapsed | 30871 | +| total_timesteps | 42694656 | +| train/ | | +| approx_kl | 0.012611415 | +| clip_fraction | 0.302 | +| clip_range | 0.0643 | +| entropy_loss | -6.34 | +| explained_variance | -0.0747 | +| learning_rate | 3.99e-05 | +| loss | -0.0264 | +| n_updates | 99204 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.00014 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1382 | +| iterations | 20848 | +| time_elapsed | 30872 | +| total_timesteps | 42696704 | +| train/ | | +| approx_kl | 0.013104336 | +| clip_fraction | 0.356 | +| clip_range | 0.0643 | +| entropy_loss | -5.81 | +| explained_variance | 0.278 | +| learning_rate | 3.99e-05 | +| loss | -0.0279 | +| n_updates | 99208 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000255 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1382 | +| iterations | 20849 | +| time_elapsed | 30874 | +| total_timesteps | 42698752 | +| train/ | | +| approx_kl | 0.015088132 | +| clip_fraction | 0.343 | +| clip_range | 0.0643 | +| entropy_loss | -5.87 | +| explained_variance | -0.0395 | +| learning_rate | 3.99e-05 | +| loss | -0.0276 | +| n_updates | 99212 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000145 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1382 | +| iterations | 20850 | +| time_elapsed | 30875 | +| total_timesteps | 42700800 | +| train/ | | +| approx_kl | 0.014622441 | +| clip_fraction | 0.324 | +| clip_range | 0.0643 | +| entropy_loss | -5.86 | +| explained_variance | 0.165 | +| learning_rate | 3.99e-05 | +| loss | -0.0249 | +| n_updates | 99216 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000264 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1382 | +| iterations | 20851 | +| time_elapsed | 30877 | +| total_timesteps | 42702848 | +| train/ | | +| approx_kl | 0.009917252 | +| clip_fraction | 0.303 | +| clip_range | 0.0643 | +| entropy_loss | -6.13 | +| explained_variance | 0.509 | +| learning_rate | 3.99e-05 | +| loss | -0.0219 | +| n_updates | 99220 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000213 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1382 | +| iterations | 20852 | +| time_elapsed | 30878 | +| total_timesteps | 42704896 | +| train/ | | +| approx_kl | 0.012333886 | +| clip_fraction | 0.333 | +| clip_range | 0.0643 | +| entropy_loss | -5.88 | +| explained_variance | 0.547 | +| learning_rate | 3.99e-05 | +| loss | -0.0328 | +| n_updates | 99224 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000113 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1382 | +| iterations | 20853 | +| time_elapsed | 30880 | +| total_timesteps | 42706944 | +| train/ | | +| approx_kl | 0.0134005705 | +| clip_fraction | 0.363 | +| clip_range | 0.0643 | +| entropy_loss | -5.8 | +| explained_variance | 0.342 | +| learning_rate | 3.99e-05 | +| loss | -0.0276 | +| n_updates | 99228 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000113 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1382 | +| iterations | 20854 | +| time_elapsed | 30881 | +| total_timesteps | 42708992 | +| train/ | | +| approx_kl | 0.012101687 | +| clip_fraction | 0.322 | +| clip_range | 0.0643 | +| entropy_loss | -6.01 | +| explained_variance | 0.0708 | +| learning_rate | 3.99e-05 | +| loss | -0.025 | +| n_updates | 99232 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000261 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1382 | +| iterations | 20855 | +| time_elapsed | 30883 | +| total_timesteps | 42711040 | +| train/ | | +| approx_kl | 0.012149156 | +| clip_fraction | 0.35 | +| clip_range | 0.0643 | +| entropy_loss | -6.14 | +| explained_variance | 0.424 | +| learning_rate | 3.99e-05 | +| loss | -0.0317 | +| n_updates | 99236 | +| policy_gradient_loss | -0.0197 | +| value_loss | 6.87e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1382 | +| iterations | 20856 | +| time_elapsed | 30884 | +| total_timesteps | 42713088 | +| train/ | | +| approx_kl | 0.012685396 | +| clip_fraction | 0.32 | +| clip_range | 0.0643 | +| entropy_loss | -6.53 | +| explained_variance | 0.284 | +| learning_rate | 3.99e-05 | +| loss | -0.0261 | +| n_updates | 99240 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000167 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1382 | +| iterations | 20857 | +| time_elapsed | 30886 | +| total_timesteps | 42715136 | +| train/ | | +| approx_kl | 0.012591678 | +| clip_fraction | 0.327 | +| clip_range | 0.0643 | +| entropy_loss | -6.12 | +| explained_variance | 0.443 | +| learning_rate | 3.99e-05 | +| loss | -0.024 | +| n_updates | 99244 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000205 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1382 | +| iterations | 20858 | +| time_elapsed | 30887 | +| total_timesteps | 42717184 | +| train/ | | +| approx_kl | 0.014821555 | +| clip_fraction | 0.351 | +| clip_range | 0.0643 | +| entropy_loss | -5.39 | +| explained_variance | 0.452 | +| learning_rate | 3.99e-05 | +| loss | -0.03 | +| n_updates | 99248 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000183 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1382 | +| iterations | 20859 | +| time_elapsed | 30889 | +| total_timesteps | 42719232 | +| train/ | | +| approx_kl | 0.016581722 | +| clip_fraction | 0.414 | +| clip_range | 0.0643 | +| entropy_loss | -5.63 | +| explained_variance | -0.324 | +| learning_rate | 3.99e-05 | +| loss | -0.0365 | +| n_updates | 99252 | +| policy_gradient_loss | -0.0221 | +| value_loss | 0.000109 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1382 | +| iterations | 20860 | +| time_elapsed | 30891 | +| total_timesteps | 42721280 | +| train/ | | +| approx_kl | 0.013508637 | +| clip_fraction | 0.375 | +| clip_range | 0.0643 | +| entropy_loss | -6.19 | +| explained_variance | 0.491 | +| learning_rate | 3.99e-05 | +| loss | -0.0331 | +| n_updates | 99256 | +| policy_gradient_loss | -0.018 | +| value_loss | 6.72e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1382 | +| iterations | 20861 | +| time_elapsed | 30892 | +| total_timesteps | 42723328 | +| train/ | | +| approx_kl | 0.013644142 | +| clip_fraction | 0.347 | +| clip_range | 0.0643 | +| entropy_loss | -5.54 | +| explained_variance | 0.386 | +| learning_rate | 3.99e-05 | +| loss | -0.0292 | +| n_updates | 99260 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000133 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1382 | +| iterations | 20862 | +| time_elapsed | 30893 | +| total_timesteps | 42725376 | +| train/ | | +| approx_kl | 0.010900076 | +| clip_fraction | 0.328 | +| clip_range | 0.0643 | +| entropy_loss | -6.24 | +| explained_variance | -0.097 | +| learning_rate | 3.99e-05 | +| loss | -0.0304 | +| n_updates | 99264 | +| policy_gradient_loss | -0.0176 | +| value_loss | 5.89e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1382 | +| iterations | 20863 | +| time_elapsed | 30895 | +| total_timesteps | 42727424 | +| train/ | | +| approx_kl | 0.010052079 | +| clip_fraction | 0.339 | +| clip_range | 0.0643 | +| entropy_loss | -5.71 | +| explained_variance | 0.682 | +| learning_rate | 3.99e-05 | +| loss | -0.0266 | +| n_updates | 99268 | +| policy_gradient_loss | -0.0163 | +| value_loss | 6.18e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1382 | +| iterations | 20864 | +| time_elapsed | 30897 | +| total_timesteps | 42729472 | +| train/ | | +| approx_kl | 0.012987005 | +| clip_fraction | 0.346 | +| clip_range | 0.0643 | +| entropy_loss | -5.46 | +| explained_variance | 0.602 | +| learning_rate | 3.99e-05 | +| loss | -0.0309 | +| n_updates | 99272 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000105 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1382 | +| iterations | 20865 | +| time_elapsed | 30898 | +| total_timesteps | 42731520 | +| train/ | | +| approx_kl | 0.012203757 | +| clip_fraction | 0.335 | +| clip_range | 0.0643 | +| entropy_loss | -5.55 | +| explained_variance | 0.461 | +| learning_rate | 3.99e-05 | +| loss | -0.0247 | +| n_updates | 99276 | +| policy_gradient_loss | -0.0169 | +| value_loss | 8.86e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1382 | +| iterations | 20866 | +| time_elapsed | 30900 | +| total_timesteps | 42733568 | +| train/ | | +| approx_kl | 0.009290384 | +| clip_fraction | 0.288 | +| clip_range | 0.0643 | +| entropy_loss | -6.08 | +| explained_variance | 0.513 | +| learning_rate | 3.99e-05 | +| loss | -0.0222 | +| n_updates | 99280 | +| policy_gradient_loss | -0.0139 | +| value_loss | 0.000158 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1382 | +| iterations | 20867 | +| time_elapsed | 30901 | +| total_timesteps | 42735616 | +| train/ | | +| approx_kl | 0.010641899 | +| clip_fraction | 0.307 | +| clip_range | 0.0643 | +| entropy_loss | -5.85 | +| explained_variance | 0.418 | +| learning_rate | 3.99e-05 | +| loss | -0.0301 | +| n_updates | 99284 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000189 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1382 | +| iterations | 20868 | +| time_elapsed | 30903 | +| total_timesteps | 42737664 | +| train/ | | +| approx_kl | 0.010830068 | +| clip_fraction | 0.32 | +| clip_range | 0.0643 | +| entropy_loss | -6.22 | +| explained_variance | 0.473 | +| learning_rate | 3.99e-05 | +| loss | -0.0233 | +| n_updates | 99288 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000156 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1382 | +| iterations | 20869 | +| time_elapsed | 30904 | +| total_timesteps | 42739712 | +| train/ | | +| approx_kl | 0.010451413 | +| clip_fraction | 0.319 | +| clip_range | 0.0643 | +| entropy_loss | -6.5 | +| explained_variance | 0.498 | +| learning_rate | 3.98e-05 | +| loss | -0.0295 | +| n_updates | 99292 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000148 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1382 | +| iterations | 20870 | +| time_elapsed | 30906 | +| total_timesteps | 42741760 | +| train/ | | +| approx_kl | 0.011962583 | +| clip_fraction | 0.299 | +| clip_range | 0.0643 | +| entropy_loss | -6.29 | +| explained_variance | 0.212 | +| learning_rate | 3.98e-05 | +| loss | -0.022 | +| n_updates | 99296 | +| policy_gradient_loss | -0.0148 | +| value_loss | 0.000293 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1382 | +| iterations | 20871 | +| time_elapsed | 30907 | +| total_timesteps | 42743808 | +| train/ | | +| approx_kl | 0.010063829 | +| clip_fraction | 0.308 | +| clip_range | 0.0643 | +| entropy_loss | -6.12 | +| explained_variance | 0.398 | +| learning_rate | 3.98e-05 | +| loss | -0.0274 | +| n_updates | 99300 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000224 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1382 | +| iterations | 20872 | +| time_elapsed | 30909 | +| total_timesteps | 42745856 | +| train/ | | +| approx_kl | 0.01322582 | +| clip_fraction | 0.334 | +| clip_range | 0.0643 | +| entropy_loss | -5.84 | +| explained_variance | 0.401 | +| learning_rate | 3.98e-05 | +| loss | -0.0298 | +| n_updates | 99304 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000166 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1382 | +| iterations | 20873 | +| time_elapsed | 30910 | +| total_timesteps | 42747904 | +| train/ | | +| approx_kl | 0.011701204 | +| clip_fraction | 0.346 | +| clip_range | 0.0643 | +| entropy_loss | -6.19 | +| explained_variance | 0.535 | +| learning_rate | 3.98e-05 | +| loss | -0.0281 | +| n_updates | 99308 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000128 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1382 | +| iterations | 20874 | +| time_elapsed | 30912 | +| total_timesteps | 42749952 | +| train/ | | +| approx_kl | 0.0111481305 | +| clip_fraction | 0.298 | +| clip_range | 0.0643 | +| entropy_loss | -5.99 | +| explained_variance | 0.255 | +| learning_rate | 3.98e-05 | +| loss | -0.0223 | +| n_updates | 99312 | +| policy_gradient_loss | -0.0141 | +| value_loss | 0.00016 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1382 | +| iterations | 20875 | +| time_elapsed | 30913 | +| total_timesteps | 42752000 | +| train/ | | +| approx_kl | 0.012944766 | +| clip_fraction | 0.326 | +| clip_range | 0.0643 | +| entropy_loss | -6.22 | +| explained_variance | 0.328 | +| learning_rate | 3.98e-05 | +| loss | -0.026 | +| n_updates | 99316 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000135 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1382 | +| iterations | 20876 | +| time_elapsed | 30915 | +| total_timesteps | 42754048 | +| train/ | | +| approx_kl | 0.009801796 | +| clip_fraction | 0.272 | +| clip_range | 0.0643 | +| entropy_loss | -5.81 | +| explained_variance | 0.613 | +| learning_rate | 3.98e-05 | +| loss | -0.0237 | +| n_updates | 99320 | +| policy_gradient_loss | -0.0124 | +| value_loss | 0.000184 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1382 | +| iterations | 20877 | +| time_elapsed | 30916 | +| total_timesteps | 42756096 | +| train/ | | +| approx_kl | 0.009545041 | +| clip_fraction | 0.277 | +| clip_range | 0.0643 | +| entropy_loss | -5.56 | +| explained_variance | 0.389 | +| learning_rate | 3.98e-05 | +| loss | -0.0229 | +| n_updates | 99324 | +| policy_gradient_loss | -0.011 | +| value_loss | 0.000261 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1382 | +| iterations | 20878 | +| time_elapsed | 30918 | +| total_timesteps | 42758144 | +| train/ | | +| approx_kl | 0.00793949 | +| clip_fraction | 0.292 | +| clip_range | 0.0643 | +| entropy_loss | -4.99 | +| explained_variance | 0.468 | +| learning_rate | 3.98e-05 | +| loss | -0.0213 | +| n_updates | 99328 | +| policy_gradient_loss | -0.0117 | +| value_loss | 0.000311 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1382 | +| iterations | 20879 | +| time_elapsed | 30919 | +| total_timesteps | 42760192 | +| train/ | | +| approx_kl | 0.0110870935 | +| clip_fraction | 0.331 | +| clip_range | 0.0643 | +| entropy_loss | -5.67 | +| explained_variance | 0.259 | +| learning_rate | 3.98e-05 | +| loss | -0.0306 | +| n_updates | 99332 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000148 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1382 | +| iterations | 20880 | +| time_elapsed | 30921 | +| total_timesteps | 42762240 | +| train/ | | +| approx_kl | 0.010116182 | +| clip_fraction | 0.359 | +| clip_range | 0.0643 | +| entropy_loss | -6.56 | +| explained_variance | -0.142 | +| learning_rate | 3.98e-05 | +| loss | -0.0326 | +| n_updates | 99336 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.00015 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1382 | +| iterations | 20881 | +| time_elapsed | 30922 | +| total_timesteps | 42764288 | +| train/ | | +| approx_kl | 0.011127849 | +| clip_fraction | 0.326 | +| clip_range | 0.0643 | +| entropy_loss | -6.12 | +| explained_variance | 0.456 | +| learning_rate | 3.98e-05 | +| loss | -0.0276 | +| n_updates | 99340 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000116 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1382 | +| iterations | 20882 | +| time_elapsed | 30924 | +| total_timesteps | 42766336 | +| train/ | | +| approx_kl | 0.014052097 | +| clip_fraction | 0.3 | +| clip_range | 0.0643 | +| entropy_loss | -6.19 | +| explained_variance | 0.186 | +| learning_rate | 3.98e-05 | +| loss | -0.0295 | +| n_updates | 99344 | +| policy_gradient_loss | -0.0139 | +| value_loss | 0.000191 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1382 | +| iterations | 20883 | +| time_elapsed | 30926 | +| total_timesteps | 42768384 | +| train/ | | +| approx_kl | 0.0133210905 | +| clip_fraction | 0.333 | +| clip_range | 0.0643 | +| entropy_loss | -5.96 | +| explained_variance | 0.369 | +| learning_rate | 3.98e-05 | +| loss | -0.0267 | +| n_updates | 99348 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000135 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1382 | +| iterations | 20884 | +| time_elapsed | 30927 | +| total_timesteps | 42770432 | +| train/ | | +| approx_kl | 0.008671444 | +| clip_fraction | 0.309 | +| clip_range | 0.0643 | +| entropy_loss | -6.66 | +| explained_variance | 0.272 | +| learning_rate | 3.98e-05 | +| loss | -0.0213 | +| n_updates | 99352 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000158 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1382 | +| iterations | 20885 | +| time_elapsed | 30929 | +| total_timesteps | 42772480 | +| train/ | | +| approx_kl | 0.0111090625 | +| clip_fraction | 0.316 | +| clip_range | 0.0643 | +| entropy_loss | -6.01 | +| explained_variance | 0.261 | +| learning_rate | 3.98e-05 | +| loss | -0.0237 | +| n_updates | 99356 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000217 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1382 | +| iterations | 20886 | +| time_elapsed | 30930 | +| total_timesteps | 42774528 | +| train/ | | +| approx_kl | 0.014290616 | +| clip_fraction | 0.302 | +| clip_range | 0.0643 | +| entropy_loss | -5.73 | +| explained_variance | 0.55 | +| learning_rate | 3.98e-05 | +| loss | -0.0309 | +| n_updates | 99360 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000122 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1382 | +| iterations | 20887 | +| time_elapsed | 30932 | +| total_timesteps | 42776576 | +| train/ | | +| approx_kl | 0.0113765 | +| clip_fraction | 0.338 | +| clip_range | 0.0643 | +| entropy_loss | -5.85 | +| explained_variance | 0.576 | +| learning_rate | 3.98e-05 | +| loss | -0.0379 | +| n_updates | 99364 | +| policy_gradient_loss | -0.0204 | +| value_loss | 5.92e-05 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1382 | +| iterations | 20888 | +| time_elapsed | 30933 | +| total_timesteps | 42778624 | +| train/ | | +| approx_kl | 0.010649705 | +| clip_fraction | 0.307 | +| clip_range | 0.0643 | +| entropy_loss | -6.16 | +| explained_variance | 0.544 | +| learning_rate | 3.98e-05 | +| loss | -0.0263 | +| n_updates | 99368 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000117 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1382 | +| iterations | 20889 | +| time_elapsed | 30935 | +| total_timesteps | 42780672 | +| train/ | | +| approx_kl | 0.014016631 | +| clip_fraction | 0.313 | +| clip_range | 0.0643 | +| entropy_loss | -6.26 | +| explained_variance | 0.316 | +| learning_rate | 3.98e-05 | +| loss | -0.0284 | +| n_updates | 99372 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000144 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1382 | +| iterations | 20890 | +| time_elapsed | 30936 | +| total_timesteps | 42782720 | +| train/ | | +| approx_kl | 0.008810518 | +| clip_fraction | 0.306 | +| clip_range | 0.0643 | +| entropy_loss | -6.79 | +| explained_variance | 0.218 | +| learning_rate | 3.98e-05 | +| loss | -0.0273 | +| n_updates | 99376 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000244 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1382 | +| iterations | 20891 | +| time_elapsed | 30938 | +| total_timesteps | 42784768 | +| train/ | | +| approx_kl | 0.010617331 | +| clip_fraction | 0.287 | +| clip_range | 0.0643 | +| entropy_loss | -6.66 | +| explained_variance | 0.314 | +| learning_rate | 3.98e-05 | +| loss | -0.0214 | +| n_updates | 99380 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.00015 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1382 | +| iterations | 20892 | +| time_elapsed | 30939 | +| total_timesteps | 42786816 | +| train/ | | +| approx_kl | 0.011648266 | +| clip_fraction | 0.284 | +| clip_range | 0.0643 | +| entropy_loss | -6.09 | +| explained_variance | 0.494 | +| learning_rate | 3.98e-05 | +| loss | -0.026 | +| n_updates | 99384 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.00016 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1382 | +| iterations | 20893 | +| time_elapsed | 30941 | +| total_timesteps | 42788864 | +| train/ | | +| approx_kl | 0.0130178705 | +| clip_fraction | 0.314 | +| clip_range | 0.0643 | +| entropy_loss | -5.59 | +| explained_variance | 0.392 | +| learning_rate | 3.98e-05 | +| loss | -0.0298 | +| n_updates | 99388 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000202 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1382 | +| iterations | 20894 | +| time_elapsed | 30942 | +| total_timesteps | 42790912 | +| train/ | | +| approx_kl | 0.012494174 | +| clip_fraction | 0.35 | +| clip_range | 0.0643 | +| entropy_loss | -5.9 | +| explained_variance | -0.267 | +| learning_rate | 3.98e-05 | +| loss | -0.0377 | +| n_updates | 99392 | +| policy_gradient_loss | -0.0183 | +| value_loss | 8.81e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1382 | +| iterations | 20895 | +| time_elapsed | 30944 | +| total_timesteps | 42792960 | +| train/ | | +| approx_kl | 0.013352511 | +| clip_fraction | 0.31 | +| clip_range | 0.0643 | +| entropy_loss | -6.43 | +| explained_variance | 0.377 | +| learning_rate | 3.98e-05 | +| loss | -0.0253 | +| n_updates | 99396 | +| policy_gradient_loss | -0.0178 | +| value_loss | 8.3e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1382 | +| iterations | 20896 | +| time_elapsed | 30945 | +| total_timesteps | 42795008 | +| train/ | | +| approx_kl | 0.008563962 | +| clip_fraction | 0.289 | +| clip_range | 0.0643 | +| entropy_loss | -6.62 | +| explained_variance | 0.0532 | +| learning_rate | 3.98e-05 | +| loss | -0.0276 | +| n_updates | 99400 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.00023 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1382 | +| iterations | 20897 | +| time_elapsed | 30947 | +| total_timesteps | 42797056 | +| train/ | | +| approx_kl | 0.009667292 | +| clip_fraction | 0.312 | +| clip_range | 0.0643 | +| entropy_loss | -5.52 | +| explained_variance | 0.621 | +| learning_rate | 3.98e-05 | +| loss | -0.0222 | +| n_updates | 99404 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.000145 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1382 | +| iterations | 20898 | +| time_elapsed | 30948 | +| total_timesteps | 42799104 | +| train/ | | +| approx_kl | 0.013154094 | +| clip_fraction | 0.337 | +| clip_range | 0.0643 | +| entropy_loss | -6.11 | +| explained_variance | -0.183 | +| learning_rate | 3.98e-05 | +| loss | -0.0327 | +| n_updates | 99408 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000136 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1382 | +| iterations | 20899 | +| time_elapsed | 30950 | +| total_timesteps | 42801152 | +| train/ | | +| approx_kl | 0.013633912 | +| clip_fraction | 0.322 | +| clip_range | 0.0643 | +| entropy_loss | -5.6 | +| explained_variance | 0.421 | +| learning_rate | 3.98e-05 | +| loss | -0.0245 | +| n_updates | 99412 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000244 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1382 | +| iterations | 20900 | +| time_elapsed | 30951 | +| total_timesteps | 42803200 | +| train/ | | +| approx_kl | 0.012515612 | +| clip_fraction | 0.344 | +| clip_range | 0.0643 | +| entropy_loss | -5.25 | +| explained_variance | 0.523 | +| learning_rate | 3.98e-05 | +| loss | -0.0261 | +| n_updates | 99416 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000175 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1382 | +| iterations | 20901 | +| time_elapsed | 30953 | +| total_timesteps | 42805248 | +| train/ | | +| approx_kl | 0.012877233 | +| clip_fraction | 0.348 | +| clip_range | 0.0643 | +| entropy_loss | -5.34 | +| explained_variance | 0.391 | +| learning_rate | 3.98e-05 | +| loss | -0.0252 | +| n_updates | 99420 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000153 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1382 | +| iterations | 20902 | +| time_elapsed | 30954 | +| total_timesteps | 42807296 | +| train/ | | +| approx_kl | 0.010629075 | +| clip_fraction | 0.329 | +| clip_range | 0.0643 | +| entropy_loss | -5.94 | +| explained_variance | 0.505 | +| learning_rate | 3.98e-05 | +| loss | -0.0328 | +| n_updates | 99424 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000114 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1382 | +| iterations | 20903 | +| time_elapsed | 30956 | +| total_timesteps | 42809344 | +| train/ | | +| approx_kl | 0.011638723 | +| clip_fraction | 0.318 | +| clip_range | 0.0643 | +| entropy_loss | -6.59 | +| explained_variance | -0.132 | +| learning_rate | 3.98e-05 | +| loss | -0.0241 | +| n_updates | 99428 | +| policy_gradient_loss | -0.0172 | +| value_loss | 9.88e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1382 | +| iterations | 20904 | +| time_elapsed | 30957 | +| total_timesteps | 42811392 | +| train/ | | +| approx_kl | 0.009769842 | +| clip_fraction | 0.302 | +| clip_range | 0.0643 | +| entropy_loss | -6.08 | +| explained_variance | 0.537 | +| learning_rate | 3.98e-05 | +| loss | -0.0213 | +| n_updates | 99432 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000118 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1382 | +| iterations | 20905 | +| time_elapsed | 30959 | +| total_timesteps | 42813440 | +| train/ | | +| approx_kl | 0.011915912 | +| clip_fraction | 0.339 | +| clip_range | 0.0643 | +| entropy_loss | -6.05 | +| explained_variance | 0.301 | +| learning_rate | 3.98e-05 | +| loss | -0.0257 | +| n_updates | 99436 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000291 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1382 | +| iterations | 20906 | +| time_elapsed | 30961 | +| total_timesteps | 42815488 | +| train/ | | +| approx_kl | 0.012768402 | +| clip_fraction | 0.352 | +| clip_range | 0.0643 | +| entropy_loss | -5.44 | +| explained_variance | 0.414 | +| learning_rate | 3.98e-05 | +| loss | -0.0276 | +| n_updates | 99440 | +| policy_gradient_loss | -0.0184 | +| value_loss | 9.74e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1382 | +| iterations | 20907 | +| time_elapsed | 30962 | +| total_timesteps | 42817536 | +| train/ | | +| approx_kl | 0.014387748 | +| clip_fraction | 0.312 | +| clip_range | 0.0643 | +| entropy_loss | -5.65 | +| explained_variance | 0.649 | +| learning_rate | 3.98e-05 | +| loss | -0.0213 | +| n_updates | 99444 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000109 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1382 | +| iterations | 20908 | +| time_elapsed | 30964 | +| total_timesteps | 42819584 | +| train/ | | +| approx_kl | 0.014780438 | +| clip_fraction | 0.295 | +| clip_range | 0.0643 | +| entropy_loss | -5.47 | +| explained_variance | 0.58 | +| learning_rate | 3.98e-05 | +| loss | -0.0243 | +| n_updates | 99448 | +| policy_gradient_loss | -0.0147 | +| value_loss | 9.78e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1382 | +| iterations | 20909 | +| time_elapsed | 30965 | +| total_timesteps | 42821632 | +| train/ | | +| approx_kl | 0.012072805 | +| clip_fraction | 0.312 | +| clip_range | 0.0643 | +| entropy_loss | -6.08 | +| explained_variance | 0.422 | +| learning_rate | 3.98e-05 | +| loss | -0.0267 | +| n_updates | 99452 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000183 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1382 | +| iterations | 20910 | +| time_elapsed | 30967 | +| total_timesteps | 42823680 | +| train/ | | +| approx_kl | 0.011715349 | +| clip_fraction | 0.328 | +| clip_range | 0.0643 | +| entropy_loss | -6.06 | +| explained_variance | 0.359 | +| learning_rate | 3.98e-05 | +| loss | -0.0261 | +| n_updates | 99456 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000189 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1382 | +| iterations | 20911 | +| time_elapsed | 30968 | +| total_timesteps | 42825728 | +| train/ | | +| approx_kl | 0.014601013 | +| clip_fraction | 0.325 | +| clip_range | 0.0643 | +| entropy_loss | -5.81 | +| explained_variance | 0.42 | +| learning_rate | 3.98e-05 | +| loss | -0.0285 | +| n_updates | 99460 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000151 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1382 | +| iterations | 20912 | +| time_elapsed | 30970 | +| total_timesteps | 42827776 | +| train/ | | +| approx_kl | 0.009860273 | +| clip_fraction | 0.301 | +| clip_range | 0.0643 | +| entropy_loss | -5.84 | +| explained_variance | 0.325 | +| learning_rate | 3.98e-05 | +| loss | -0.017 | +| n_updates | 99464 | +| policy_gradient_loss | -0.0115 | +| value_loss | 0.000471 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1382 | +| iterations | 20913 | +| time_elapsed | 30971 | +| total_timesteps | 42829824 | +| train/ | | +| approx_kl | 0.013242205 | +| clip_fraction | 0.35 | +| clip_range | 0.0643 | +| entropy_loss | -5.81 | +| explained_variance | 0.317 | +| learning_rate | 3.98e-05 | +| loss | -0.0336 | +| n_updates | 99468 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000226 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1382 | +| iterations | 20914 | +| time_elapsed | 30973 | +| total_timesteps | 42831872 | +| train/ | | +| approx_kl | 0.010408724 | +| clip_fraction | 0.337 | +| clip_range | 0.0643 | +| entropy_loss | -6 | +| explained_variance | 0.306 | +| learning_rate | 3.98e-05 | +| loss | -0.0345 | +| n_updates | 99472 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000297 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1382 | +| iterations | 20915 | +| time_elapsed | 30974 | +| total_timesteps | 42833920 | +| train/ | | +| approx_kl | 0.012415482 | +| clip_fraction | 0.338 | +| clip_range | 0.0643 | +| entropy_loss | -6.01 | +| explained_variance | 0.278 | +| learning_rate | 3.98e-05 | +| loss | -0.0305 | +| n_updates | 99476 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000209 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1382 | +| iterations | 20916 | +| time_elapsed | 30976 | +| total_timesteps | 42835968 | +| train/ | | +| approx_kl | 0.013126133 | +| clip_fraction | 0.345 | +| clip_range | 0.0643 | +| entropy_loss | -6.22 | +| explained_variance | 0.249 | +| learning_rate | 3.98e-05 | +| loss | -0.0301 | +| n_updates | 99480 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000121 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1382 | +| iterations | 20917 | +| time_elapsed | 30977 | +| total_timesteps | 42838016 | +| train/ | | +| approx_kl | 0.0093862135 | +| clip_fraction | 0.318 | +| clip_range | 0.0643 | +| entropy_loss | -6.27 | +| explained_variance | 0.315 | +| learning_rate | 3.98e-05 | +| loss | -0.028 | +| n_updates | 99484 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000146 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1382 | +| iterations | 20918 | +| time_elapsed | 30979 | +| total_timesteps | 42840064 | +| train/ | | +| approx_kl | 0.007434296 | +| clip_fraction | 0.264 | +| clip_range | 0.0643 | +| entropy_loss | -6.2 | +| explained_variance | 0.65 | +| learning_rate | 3.98e-05 | +| loss | -0.0218 | +| n_updates | 99488 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000142 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1382 | +| iterations | 20919 | +| time_elapsed | 30980 | +| total_timesteps | 42842112 | +| train/ | | +| approx_kl | 0.010440193 | +| clip_fraction | 0.324 | +| clip_range | 0.0643 | +| entropy_loss | -6.19 | +| explained_variance | 0.231 | +| learning_rate | 3.98e-05 | +| loss | -0.0212 | +| n_updates | 99492 | +| policy_gradient_loss | -0.0131 | +| value_loss | 0.000307 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1382 | +| iterations | 20920 | +| time_elapsed | 30982 | +| total_timesteps | 42844160 | +| train/ | | +| approx_kl | 0.013836654 | +| clip_fraction | 0.304 | +| clip_range | 0.0643 | +| entropy_loss | -5.88 | +| explained_variance | 0.495 | +| learning_rate | 3.98e-05 | +| loss | -0.0268 | +| n_updates | 99496 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000167 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1382 | +| iterations | 20921 | +| time_elapsed | 30983 | +| total_timesteps | 42846208 | +| train/ | | +| approx_kl | 0.013496371 | +| clip_fraction | 0.317 | +| clip_range | 0.0643 | +| entropy_loss | -5.63 | +| explained_variance | 0.176 | +| learning_rate | 3.98e-05 | +| loss | -0.0284 | +| n_updates | 99500 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000178 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1382 | +| iterations | 20922 | +| time_elapsed | 30985 | +| total_timesteps | 42848256 | +| train/ | | +| approx_kl | 0.010969697 | +| clip_fraction | 0.313 | +| clip_range | 0.0643 | +| entropy_loss | -5.48 | +| explained_variance | 0.325 | +| learning_rate | 3.98e-05 | +| loss | -0.0256 | +| n_updates | 99504 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.00033 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1382 | +| iterations | 20923 | +| time_elapsed | 30986 | +| total_timesteps | 42850304 | +| train/ | | +| approx_kl | 0.014691487 | +| clip_fraction | 0.374 | +| clip_range | 0.0643 | +| entropy_loss | -5.4 | +| explained_variance | 0.716 | +| learning_rate | 3.98e-05 | +| loss | -0.0382 | +| n_updates | 99508 | +| policy_gradient_loss | -0.0218 | +| value_loss | 5.49e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1382 | +| iterations | 20924 | +| time_elapsed | 30988 | +| total_timesteps | 42852352 | +| train/ | | +| approx_kl | 0.014297748 | +| clip_fraction | 0.326 | +| clip_range | 0.0643 | +| entropy_loss | -5.46 | +| explained_variance | 0.332 | +| learning_rate | 3.98e-05 | +| loss | -0.0281 | +| n_updates | 99512 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000128 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1382 | +| iterations | 20925 | +| time_elapsed | 30989 | +| total_timesteps | 42854400 | +| train/ | | +| approx_kl | 0.010418994 | +| clip_fraction | 0.301 | +| clip_range | 0.0643 | +| entropy_loss | -5.81 | +| explained_variance | 0.423 | +| learning_rate | 3.98e-05 | +| loss | -0.0289 | +| n_updates | 99516 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000112 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1382 | +| iterations | 20926 | +| time_elapsed | 30991 | +| total_timesteps | 42856448 | +| train/ | | +| approx_kl | 0.011936542 | +| clip_fraction | 0.281 | +| clip_range | 0.0643 | +| entropy_loss | -6.34 | +| explained_variance | 0.175 | +| learning_rate | 3.98e-05 | +| loss | -0.0193 | +| n_updates | 99520 | +| policy_gradient_loss | -0.0133 | +| value_loss | 0.000307 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1382 | +| iterations | 20927 | +| time_elapsed | 30993 | +| total_timesteps | 42858496 | +| train/ | | +| approx_kl | 0.012827123 | +| clip_fraction | 0.309 | +| clip_range | 0.0643 | +| entropy_loss | -5.28 | +| explained_variance | 0.689 | +| learning_rate | 3.98e-05 | +| loss | -0.0241 | +| n_updates | 99524 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000135 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1382 | +| iterations | 20928 | +| time_elapsed | 30994 | +| total_timesteps | 42860544 | +| train/ | | +| approx_kl | 0.012327236 | +| clip_fraction | 0.312 | +| clip_range | 0.0643 | +| entropy_loss | -5.32 | +| explained_variance | 0.422 | +| learning_rate | 3.98e-05 | +| loss | -0.0269 | +| n_updates | 99528 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000165 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1382 | +| iterations | 20929 | +| time_elapsed | 30996 | +| total_timesteps | 42862592 | +| train/ | | +| approx_kl | 0.009332166 | +| clip_fraction | 0.29 | +| clip_range | 0.0643 | +| entropy_loss | -6.16 | +| explained_variance | 0.196 | +| learning_rate | 3.98e-05 | +| loss | -0.03 | +| n_updates | 99532 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000233 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1382 | +| iterations | 20930 | +| time_elapsed | 30997 | +| total_timesteps | 42864640 | +| train/ | | +| approx_kl | 0.00718576 | +| clip_fraction | 0.289 | +| clip_range | 0.0643 | +| entropy_loss | -6.41 | +| explained_variance | 0.2 | +| learning_rate | 3.98e-05 | +| loss | -0.0263 | +| n_updates | 99536 | +| policy_gradient_loss | -0.0127 | +| value_loss | 0.000306 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1382 | +| iterations | 20931 | +| time_elapsed | 30999 | +| total_timesteps | 42866688 | +| train/ | | +| approx_kl | 0.009010395 | +| clip_fraction | 0.294 | +| clip_range | 0.0643 | +| entropy_loss | -6.48 | +| explained_variance | 0.266 | +| learning_rate | 3.98e-05 | +| loss | -0.0301 | +| n_updates | 99540 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000161 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1382 | +| iterations | 20932 | +| time_elapsed | 31000 | +| total_timesteps | 42868736 | +| train/ | | +| approx_kl | 0.013369003 | +| clip_fraction | 0.311 | +| clip_range | 0.0643 | +| entropy_loss | -5.66 | +| explained_variance | 0.593 | +| learning_rate | 3.98e-05 | +| loss | -0.0254 | +| n_updates | 99544 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000143 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1382 | +| iterations | 20933 | +| time_elapsed | 31002 | +| total_timesteps | 42870784 | +| train/ | | +| approx_kl | 0.011874345 | +| clip_fraction | 0.31 | +| clip_range | 0.0643 | +| entropy_loss | -5.8 | +| explained_variance | 0.391 | +| learning_rate | 3.98e-05 | +| loss | -0.0221 | +| n_updates | 99548 | +| policy_gradient_loss | -0.0139 | +| value_loss | 0.000279 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1382 | +| iterations | 20934 | +| time_elapsed | 31003 | +| total_timesteps | 42872832 | +| train/ | | +| approx_kl | 0.011110787 | +| clip_fraction | 0.318 | +| clip_range | 0.0643 | +| entropy_loss | -5.51 | +| explained_variance | 0.408 | +| learning_rate | 3.98e-05 | +| loss | -0.0221 | +| n_updates | 99552 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000334 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1382 | +| iterations | 20935 | +| time_elapsed | 31005 | +| total_timesteps | 42874880 | +| train/ | | +| approx_kl | 0.012129346 | +| clip_fraction | 0.323 | +| clip_range | 0.0643 | +| entropy_loss | -5.44 | +| explained_variance | 0.177 | +| learning_rate | 3.98e-05 | +| loss | -0.0318 | +| n_updates | 99556 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.00015 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1382 | +| iterations | 20936 | +| time_elapsed | 31006 | +| total_timesteps | 42876928 | +| train/ | | +| approx_kl | 0.011905778 | +| clip_fraction | 0.338 | +| clip_range | 0.0643 | +| entropy_loss | -6.06 | +| explained_variance | 0.378 | +| learning_rate | 3.98e-05 | +| loss | -0.0297 | +| n_updates | 99560 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000175 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1382 | +| iterations | 20937 | +| time_elapsed | 31008 | +| total_timesteps | 42878976 | +| train/ | | +| approx_kl | 0.011388119 | +| clip_fraction | 0.335 | +| clip_range | 0.0643 | +| entropy_loss | -5.89 | +| explained_variance | -0.133 | +| learning_rate | 3.98e-05 | +| loss | -0.0289 | +| n_updates | 99564 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000115 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1382 | +| iterations | 20938 | +| time_elapsed | 31009 | +| total_timesteps | 42881024 | +| train/ | | +| approx_kl | 0.01051485 | +| clip_fraction | 0.306 | +| clip_range | 0.0643 | +| entropy_loss | -5.81 | +| explained_variance | 0.523 | +| learning_rate | 3.98e-05 | +| loss | -0.0212 | +| n_updates | 99568 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000176 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1382 | +| iterations | 20939 | +| time_elapsed | 31011 | +| total_timesteps | 42883072 | +| train/ | | +| approx_kl | 0.01223062 | +| clip_fraction | 0.325 | +| clip_range | 0.0643 | +| entropy_loss | -6.1 | +| explained_variance | 0.172 | +| learning_rate | 3.98e-05 | +| loss | -0.0302 | +| n_updates | 99572 | +| policy_gradient_loss | -0.0193 | +| value_loss | 8.03e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1382 | +| iterations | 20940 | +| time_elapsed | 31012 | +| total_timesteps | 42885120 | +| train/ | | +| approx_kl | 0.011879406 | +| clip_fraction | 0.298 | +| clip_range | 0.0643 | +| entropy_loss | -6.07 | +| explained_variance | 0.327 | +| learning_rate | 3.98e-05 | +| loss | -0.0257 | +| n_updates | 99576 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000215 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1382 | +| iterations | 20941 | +| time_elapsed | 31014 | +| total_timesteps | 42887168 | +| train/ | | +| approx_kl | 0.013747359 | +| clip_fraction | 0.325 | +| clip_range | 0.0643 | +| entropy_loss | -5.55 | +| explained_variance | 0.354 | +| learning_rate | 3.98e-05 | +| loss | -0.0152 | +| n_updates | 99580 | +| policy_gradient_loss | -0.0144 | +| value_loss | 0.000218 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1382 | +| iterations | 20942 | +| time_elapsed | 31015 | +| total_timesteps | 42889216 | +| train/ | | +| approx_kl | 0.010841186 | +| clip_fraction | 0.318 | +| clip_range | 0.0643 | +| entropy_loss | -5.7 | +| explained_variance | -0.133 | +| learning_rate | 3.98e-05 | +| loss | -0.0289 | +| n_updates | 99584 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000243 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1382 | +| iterations | 20943 | +| time_elapsed | 31017 | +| total_timesteps | 42891264 | +| train/ | | +| approx_kl | 0.013744725 | +| clip_fraction | 0.376 | +| clip_range | 0.0643 | +| entropy_loss | -5.72 | +| explained_variance | 0.397 | +| learning_rate | 3.98e-05 | +| loss | -0.0319 | +| n_updates | 99588 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000116 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1382 | +| iterations | 20944 | +| time_elapsed | 31018 | +| total_timesteps | 42893312 | +| train/ | | +| approx_kl | 0.013054298 | +| clip_fraction | 0.336 | +| clip_range | 0.0643 | +| entropy_loss | -5.73 | +| explained_variance | 0.698 | +| learning_rate | 3.98e-05 | +| loss | -0.0266 | +| n_updates | 99592 | +| policy_gradient_loss | -0.0173 | +| value_loss | 9.87e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1382 | +| iterations | 20945 | +| time_elapsed | 31020 | +| total_timesteps | 42895360 | +| train/ | | +| approx_kl | 0.013335969 | +| clip_fraction | 0.31 | +| clip_range | 0.0643 | +| entropy_loss | -5.83 | +| explained_variance | 0.478 | +| learning_rate | 3.98e-05 | +| loss | -0.0281 | +| n_updates | 99596 | +| policy_gradient_loss | -0.0177 | +| value_loss | 8.57e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1382 | +| iterations | 20946 | +| time_elapsed | 31021 | +| total_timesteps | 42897408 | +| train/ | | +| approx_kl | 0.011536469 | +| clip_fraction | 0.281 | +| clip_range | 0.0643 | +| entropy_loss | -6.53 | +| explained_variance | 0.329 | +| learning_rate | 3.98e-05 | +| loss | -0.0224 | +| n_updates | 99600 | +| policy_gradient_loss | -0.0136 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1382 | +| iterations | 20947 | +| time_elapsed | 31023 | +| total_timesteps | 42899456 | +| train/ | | +| approx_kl | 0.013001282 | +| clip_fraction | 0.328 | +| clip_range | 0.0643 | +| entropy_loss | -5.75 | +| explained_variance | 0.542 | +| learning_rate | 3.98e-05 | +| loss | -0.0317 | +| n_updates | 99604 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000191 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1382 | +| iterations | 20948 | +| time_elapsed | 31024 | +| total_timesteps | 42901504 | +| train/ | | +| approx_kl | 0.013648965 | +| clip_fraction | 0.326 | +| clip_range | 0.0643 | +| entropy_loss | -6.16 | +| explained_variance | -0.0497 | +| learning_rate | 3.98e-05 | +| loss | -0.0252 | +| n_updates | 99608 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.00028 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1382 | +| iterations | 20949 | +| time_elapsed | 31026 | +| total_timesteps | 42903552 | +| train/ | | +| approx_kl | 0.013274606 | +| clip_fraction | 0.326 | +| clip_range | 0.0643 | +| entropy_loss | -6.31 | +| explained_variance | 0.313 | +| learning_rate | 3.98e-05 | +| loss | -0.0275 | +| n_updates | 99612 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000133 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1382 | +| iterations | 20950 | +| time_elapsed | 31028 | +| total_timesteps | 42905600 | +| train/ | | +| approx_kl | 0.012628884 | +| clip_fraction | 0.318 | +| clip_range | 0.0643 | +| entropy_loss | -6.22 | +| explained_variance | 0.312 | +| learning_rate | 3.98e-05 | +| loss | -0.0275 | +| n_updates | 99616 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000172 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1382 | +| iterations | 20951 | +| time_elapsed | 31029 | +| total_timesteps | 42907648 | +| train/ | | +| approx_kl | 0.013775133 | +| clip_fraction | 0.343 | +| clip_range | 0.0643 | +| entropy_loss | -6.03 | +| explained_variance | 0.429 | +| learning_rate | 3.98e-05 | +| loss | -0.0311 | +| n_updates | 99620 | +| policy_gradient_loss | -0.0193 | +| value_loss | 9.05e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1382 | +| iterations | 20952 | +| time_elapsed | 31031 | +| total_timesteps | 42909696 | +| train/ | | +| approx_kl | 0.012451489 | +| clip_fraction | 0.306 | +| clip_range | 0.0643 | +| entropy_loss | -5.6 | +| explained_variance | 0.406 | +| learning_rate | 3.98e-05 | +| loss | -0.0221 | +| n_updates | 99624 | +| policy_gradient_loss | -0.0141 | +| value_loss | 0.000245 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1382 | +| iterations | 20953 | +| time_elapsed | 31032 | +| total_timesteps | 42911744 | +| train/ | | +| approx_kl | 0.011691322 | +| clip_fraction | 0.312 | +| clip_range | 0.0643 | +| entropy_loss | -5.73 | +| explained_variance | 0.128 | +| learning_rate | 3.98e-05 | +| loss | -0.0313 | +| n_updates | 99628 | +| policy_gradient_loss | -0.0182 | +| value_loss | 6.86e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1382 | +| iterations | 20954 | +| time_elapsed | 31034 | +| total_timesteps | 42913792 | +| train/ | | +| approx_kl | 0.013478698 | +| clip_fraction | 0.337 | +| clip_range | 0.0643 | +| entropy_loss | -5.86 | +| explained_variance | -0.0644 | +| learning_rate | 3.98e-05 | +| loss | -0.0282 | +| n_updates | 99632 | +| policy_gradient_loss | -0.0192 | +| value_loss | 7.95e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1382 | +| iterations | 20955 | +| time_elapsed | 31035 | +| total_timesteps | 42915840 | +| train/ | | +| approx_kl | 0.012416565 | +| clip_fraction | 0.304 | +| clip_range | 0.0643 | +| entropy_loss | -6.05 | +| explained_variance | 0.545 | +| learning_rate | 3.98e-05 | +| loss | -0.0272 | +| n_updates | 99636 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000118 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1382 | +| iterations | 20956 | +| time_elapsed | 31037 | +| total_timesteps | 42917888 | +| train/ | | +| approx_kl | 0.011222361 | +| clip_fraction | 0.32 | +| clip_range | 0.0643 | +| entropy_loss | -6.05 | +| explained_variance | 0.488 | +| learning_rate | 3.98e-05 | +| loss | -0.0205 | +| n_updates | 99640 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.00011 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1382 | +| iterations | 20957 | +| time_elapsed | 31038 | +| total_timesteps | 42919936 | +| train/ | | +| approx_kl | 0.009716541 | +| clip_fraction | 0.317 | +| clip_range | 0.0643 | +| entropy_loss | -4.87 | +| explained_variance | 0.752 | +| learning_rate | 3.98e-05 | +| loss | -0.0221 | +| n_updates | 99644 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000104 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1382 | +| iterations | 20958 | +| time_elapsed | 31040 | +| total_timesteps | 42921984 | +| train/ | | +| approx_kl | 0.012373599 | +| clip_fraction | 0.316 | +| clip_range | 0.0643 | +| entropy_loss | -5.46 | +| explained_variance | 0.64 | +| learning_rate | 3.98e-05 | +| loss | -0.0244 | +| n_updates | 99648 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.00012 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1382 | +| iterations | 20959 | +| time_elapsed | 31041 | +| total_timesteps | 42924032 | +| train/ | | +| approx_kl | 0.009379847 | +| clip_fraction | 0.297 | +| clip_range | 0.0643 | +| entropy_loss | -6.74 | +| explained_variance | -0.0772 | +| learning_rate | 3.98e-05 | +| loss | -0.026 | +| n_updates | 99652 | +| policy_gradient_loss | -0.0141 | +| value_loss | 0.000199 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1382 | +| iterations | 20960 | +| time_elapsed | 31043 | +| total_timesteps | 42926080 | +| train/ | | +| approx_kl | 0.011026718 | +| clip_fraction | 0.331 | +| clip_range | 0.0643 | +| entropy_loss | -6.49 | +| explained_variance | 0.387 | +| learning_rate | 3.98e-05 | +| loss | -0.0243 | +| n_updates | 99656 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000137 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1382 | +| iterations | 20961 | +| time_elapsed | 31044 | +| total_timesteps | 42928128 | +| train/ | | +| approx_kl | 0.013517327 | +| clip_fraction | 0.311 | +| clip_range | 0.0643 | +| entropy_loss | -5.77 | +| explained_variance | 0.589 | +| learning_rate | 3.98e-05 | +| loss | -0.0286 | +| n_updates | 99660 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000122 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1382 | +| iterations | 20962 | +| time_elapsed | 31046 | +| total_timesteps | 42930176 | +| train/ | | +| approx_kl | 0.01294754 | +| clip_fraction | 0.34 | +| clip_range | 0.0643 | +| entropy_loss | -5.62 | +| explained_variance | 0.424 | +| learning_rate | 3.98e-05 | +| loss | -0.0295 | +| n_updates | 99664 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000136 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1382 | +| iterations | 20963 | +| time_elapsed | 31047 | +| total_timesteps | 42932224 | +| train/ | | +| approx_kl | 0.012263862 | +| clip_fraction | 0.318 | +| clip_range | 0.0643 | +| entropy_loss | -5.61 | +| explained_variance | 0.416 | +| learning_rate | 3.98e-05 | +| loss | -0.0222 | +| n_updates | 99668 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000251 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.369 | +| time/ | | +| fps | 1382 | +| iterations | 20964 | +| time_elapsed | 31049 | +| total_timesteps | 42934272 | +| train/ | | +| approx_kl | 0.015375981 | +| clip_fraction | 0.315 | +| clip_range | 0.0643 | +| entropy_loss | -6.16 | +| explained_variance | 0.311 | +| learning_rate | 3.98e-05 | +| loss | -0.0273 | +| n_updates | 99672 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000133 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1382 | +| iterations | 20965 | +| time_elapsed | 31050 | +| total_timesteps | 42936320 | +| train/ | | +| approx_kl | 0.011499474 | +| clip_fraction | 0.341 | +| clip_range | 0.0643 | +| entropy_loss | -6.51 | +| explained_variance | -0.0381 | +| learning_rate | 3.98e-05 | +| loss | -0.0278 | +| n_updates | 99676 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000267 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.384 | +| time/ | | +| fps | 1382 | +| iterations | 20966 | +| time_elapsed | 31052 | +| total_timesteps | 42938368 | +| train/ | | +| approx_kl | 0.010607967 | +| clip_fraction | 0.329 | +| clip_range | 0.0643 | +| entropy_loss | -5.8 | +| explained_variance | 0.496 | +| learning_rate | 3.98e-05 | +| loss | -0.0257 | +| n_updates | 99680 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000158 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.386 | +| time/ | | +| fps | 1382 | +| iterations | 20967 | +| time_elapsed | 31053 | +| total_timesteps | 42940416 | +| train/ | | +| approx_kl | 0.009434918 | +| clip_fraction | 0.304 | +| clip_range | 0.0643 | +| entropy_loss | -5.89 | +| explained_variance | 0.232 | +| learning_rate | 3.98e-05 | +| loss | -0.0288 | +| n_updates | 99684 | +| policy_gradient_loss | -0.0137 | +| value_loss | 0.000534 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.391 | +| time/ | | +| fps | 1382 | +| iterations | 20968 | +| time_elapsed | 31055 | +| total_timesteps | 42942464 | +| train/ | | +| approx_kl | 0.012755819 | +| clip_fraction | 0.306 | +| clip_range | 0.0643 | +| entropy_loss | -5.3 | +| explained_variance | 0.456 | +| learning_rate | 3.98e-05 | +| loss | -0.021 | +| n_updates | 99688 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000269 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.394 | +| time/ | | +| fps | 1382 | +| iterations | 20969 | +| time_elapsed | 31057 | +| total_timesteps | 42944512 | +| train/ | | +| approx_kl | 0.0132008735 | +| clip_fraction | 0.336 | +| clip_range | 0.0643 | +| entropy_loss | -5.08 | +| explained_variance | 0.486 | +| learning_rate | 3.98e-05 | +| loss | -0.0321 | +| n_updates | 99692 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000188 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.398 | +| time/ | | +| fps | 1382 | +| iterations | 20970 | +| time_elapsed | 31058 | +| total_timesteps | 42946560 | +| train/ | | +| approx_kl | 0.01602535 | +| clip_fraction | 0.316 | +| clip_range | 0.0643 | +| entropy_loss | -5.33 | +| explained_variance | 0.178 | +| learning_rate | 3.98e-05 | +| loss | -0.0235 | +| n_updates | 99696 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.0002 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.401 | +| time/ | | +| fps | 1382 | +| iterations | 20971 | +| time_elapsed | 31060 | +| total_timesteps | 42948608 | +| train/ | | +| approx_kl | 0.012075979 | +| clip_fraction | 0.321 | +| clip_range | 0.0643 | +| entropy_loss | -6.28 | +| explained_variance | 0.406 | +| learning_rate | 3.98e-05 | +| loss | -0.0274 | +| n_updates | 99700 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000157 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.401 | +| time/ | | +| fps | 1382 | +| iterations | 20972 | +| time_elapsed | 31061 | +| total_timesteps | 42950656 | +| train/ | | +| approx_kl | 0.009648232 | +| clip_fraction | 0.27 | +| clip_range | 0.0643 | +| entropy_loss | -5.52 | +| explained_variance | 0.379 | +| learning_rate | 3.98e-05 | +| loss | -0.019 | +| n_updates | 99704 | +| policy_gradient_loss | -0.0128 | +| value_loss | 0.000324 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.401 | +| time/ | | +| fps | 1382 | +| iterations | 20973 | +| time_elapsed | 31063 | +| total_timesteps | 42952704 | +| train/ | | +| approx_kl | 0.013444323 | +| clip_fraction | 0.304 | +| clip_range | 0.0643 | +| entropy_loss | -6.27 | +| explained_variance | -0.231 | +| learning_rate | 3.98e-05 | +| loss | -0.0311 | +| n_updates | 99708 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.00011 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.401 | +| time/ | | +| fps | 1382 | +| iterations | 20974 | +| time_elapsed | 31064 | +| total_timesteps | 42954752 | +| train/ | | +| approx_kl | 0.01168599 | +| clip_fraction | 0.283 | +| clip_range | 0.0643 | +| entropy_loss | -5.63 | +| explained_variance | 0.577 | +| learning_rate | 3.98e-05 | +| loss | -0.0206 | +| n_updates | 99712 | +| policy_gradient_loss | -0.0144 | +| value_loss | 0.000168 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.391 | +| time/ | | +| fps | 1382 | +| iterations | 20975 | +| time_elapsed | 31066 | +| total_timesteps | 42956800 | +| train/ | | +| approx_kl | 0.011747341 | +| clip_fraction | 0.292 | +| clip_range | 0.0643 | +| entropy_loss | -6.13 | +| explained_variance | -0.25 | +| learning_rate | 3.98e-05 | +| loss | -0.0284 | +| n_updates | 99716 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.00011 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.391 | +| time/ | | +| fps | 1382 | +| iterations | 20976 | +| time_elapsed | 31067 | +| total_timesteps | 42958848 | +| train/ | | +| approx_kl | 0.010267833 | +| clip_fraction | 0.277 | +| clip_range | 0.0643 | +| entropy_loss | -6.27 | +| explained_variance | 0.463 | +| learning_rate | 3.98e-05 | +| loss | -0.0217 | +| n_updates | 99720 | +| policy_gradient_loss | -0.0141 | +| value_loss | 0.000186 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1382 | +| iterations | 20977 | +| time_elapsed | 31069 | +| total_timesteps | 42960896 | +| train/ | | +| approx_kl | 0.01254132 | +| clip_fraction | 0.325 | +| clip_range | 0.0643 | +| entropy_loss | -5.73 | +| explained_variance | 0.38 | +| learning_rate | 3.98e-05 | +| loss | -0.0256 | +| n_updates | 99724 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000121 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1382 | +| iterations | 20978 | +| time_elapsed | 31070 | +| total_timesteps | 42962944 | +| train/ | | +| approx_kl | 0.010627606 | +| clip_fraction | 0.329 | +| clip_range | 0.0643 | +| entropy_loss | -5.63 | +| explained_variance | 0.465 | +| learning_rate | 3.98e-05 | +| loss | -0.0294 | +| n_updates | 99728 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000121 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.38 | +| time/ | | +| fps | 1382 | +| iterations | 20979 | +| time_elapsed | 31072 | +| total_timesteps | 42964992 | +| train/ | | +| approx_kl | 0.010642675 | +| clip_fraction | 0.316 | +| clip_range | 0.0643 | +| entropy_loss | -5.63 | +| explained_variance | 0.281 | +| learning_rate | 3.98e-05 | +| loss | -0.0243 | +| n_updates | 99732 | +| policy_gradient_loss | -0.0142 | +| value_loss | 0.00018 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1382 | +| iterations | 20980 | +| time_elapsed | 31073 | +| total_timesteps | 42967040 | +| train/ | | +| approx_kl | 0.010538412 | +| clip_fraction | 0.28 | +| clip_range | 0.0643 | +| entropy_loss | -6.3 | +| explained_variance | 0.252 | +| learning_rate | 3.98e-05 | +| loss | -0.0242 | +| n_updates | 99736 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.000165 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1382 | +| iterations | 20981 | +| time_elapsed | 31075 | +| total_timesteps | 42969088 | +| train/ | | +| approx_kl | 0.00910164 | +| clip_fraction | 0.297 | +| clip_range | 0.0643 | +| entropy_loss | -5.87 | +| explained_variance | 0.319 | +| learning_rate | 3.98e-05 | +| loss | -0.0272 | +| n_updates | 99740 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.000276 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1382 | +| iterations | 20982 | +| time_elapsed | 31076 | +| total_timesteps | 42971136 | +| train/ | | +| approx_kl | 0.01122267 | +| clip_fraction | 0.336 | +| clip_range | 0.0643 | +| entropy_loss | -5.72 | +| explained_variance | 0.542 | +| learning_rate | 3.98e-05 | +| loss | -0.0221 | +| n_updates | 99744 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000149 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1382 | +| iterations | 20983 | +| time_elapsed | 31078 | +| total_timesteps | 42973184 | +| train/ | | +| approx_kl | 0.009453685 | +| clip_fraction | 0.349 | +| clip_range | 0.0643 | +| entropy_loss | -5.89 | +| explained_variance | 0.489 | +| learning_rate | 3.98e-05 | +| loss | -0.0268 | +| n_updates | 99748 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000163 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1382 | +| iterations | 20984 | +| time_elapsed | 31080 | +| total_timesteps | 42975232 | +| train/ | | +| approx_kl | 0.0122839175 | +| clip_fraction | 0.298 | +| clip_range | 0.0643 | +| entropy_loss | -6.31 | +| explained_variance | 0.338 | +| learning_rate | 3.98e-05 | +| loss | -0.026 | +| n_updates | 99752 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000137 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.383 | +| time/ | | +| fps | 1382 | +| iterations | 20985 | +| time_elapsed | 31081 | +| total_timesteps | 42977280 | +| train/ | | +| approx_kl | 0.009504859 | +| clip_fraction | 0.303 | +| clip_range | 0.0643 | +| entropy_loss | -6.46 | +| explained_variance | 0.28 | +| learning_rate | 3.98e-05 | +| loss | -0.0281 | +| n_updates | 99756 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000198 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.385 | +| time/ | | +| fps | 1382 | +| iterations | 20986 | +| time_elapsed | 31083 | +| total_timesteps | 42979328 | +| train/ | | +| approx_kl | 0.014033609 | +| clip_fraction | 0.343 | +| clip_range | 0.0643 | +| entropy_loss | -6.58 | +| explained_variance | -0.217 | +| learning_rate | 3.98e-05 | +| loss | -0.041 | +| n_updates | 99760 | +| policy_gradient_loss | -0.0228 | +| value_loss | 5.33e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.385 | +| time/ | | +| fps | 1382 | +| iterations | 20987 | +| time_elapsed | 31084 | +| total_timesteps | 42981376 | +| train/ | | +| approx_kl | 0.009620734 | +| clip_fraction | 0.293 | +| clip_range | 0.0643 | +| entropy_loss | -5.94 | +| explained_variance | 0.385 | +| learning_rate | 3.98e-05 | +| loss | -0.0154 | +| n_updates | 99764 | +| policy_gradient_loss | -0.0139 | +| value_loss | 0.000228 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.387 | +| time/ | | +| fps | 1382 | +| iterations | 20988 | +| time_elapsed | 31086 | +| total_timesteps | 42983424 | +| train/ | | +| approx_kl | 0.008879237 | +| clip_fraction | 0.303 | +| clip_range | 0.0643 | +| entropy_loss | -6.3 | +| explained_variance | 0.00246 | +| learning_rate | 3.98e-05 | +| loss | -0.0219 | +| n_updates | 99768 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000196 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.386 | +| time/ | | +| fps | 1382 | +| iterations | 20989 | +| time_elapsed | 31087 | +| total_timesteps | 42985472 | +| train/ | | +| approx_kl | 0.011224236 | +| clip_fraction | 0.322 | +| clip_range | 0.0643 | +| entropy_loss | -6.28 | +| explained_variance | 0.25 | +| learning_rate | 3.98e-05 | +| loss | -0.0266 | +| n_updates | 99772 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000224 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.385 | +| time/ | | +| fps | 1382 | +| iterations | 20990 | +| time_elapsed | 31089 | +| total_timesteps | 42987520 | +| train/ | | +| approx_kl | 0.01102256 | +| clip_fraction | 0.29 | +| clip_range | 0.0643 | +| entropy_loss | -5.01 | +| explained_variance | 0.703 | +| learning_rate | 3.98e-05 | +| loss | -0.0282 | +| n_updates | 99776 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.000132 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.385 | +| time/ | | +| fps | 1382 | +| iterations | 20991 | +| time_elapsed | 31090 | +| total_timesteps | 42989568 | +| train/ | | +| approx_kl | 0.011119692 | +| clip_fraction | 0.309 | +| clip_range | 0.0643 | +| entropy_loss | -5.75 | +| explained_variance | 0.272 | +| learning_rate | 3.98e-05 | +| loss | -0.0269 | +| n_updates | 99780 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000174 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.384 | +| time/ | | +| fps | 1382 | +| iterations | 20992 | +| time_elapsed | 31092 | +| total_timesteps | 42991616 | +| train/ | | +| approx_kl | 0.012530968 | +| clip_fraction | 0.343 | +| clip_range | 0.0643 | +| entropy_loss | -6.17 | +| explained_variance | -0.187 | +| learning_rate | 3.98e-05 | +| loss | -0.0314 | +| n_updates | 99784 | +| policy_gradient_loss | -0.0185 | +| value_loss | 9.21e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.378 | +| time/ | | +| fps | 1382 | +| iterations | 20993 | +| time_elapsed | 31093 | +| total_timesteps | 42993664 | +| train/ | | +| approx_kl | 0.012525404 | +| clip_fraction | 0.312 | +| clip_range | 0.0643 | +| entropy_loss | -6.17 | +| explained_variance | 0.598 | +| learning_rate | 3.98e-05 | +| loss | -0.026 | +| n_updates | 99788 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000103 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.376 | +| time/ | | +| fps | 1382 | +| iterations | 20994 | +| time_elapsed | 31095 | +| total_timesteps | 42995712 | +| train/ | | +| approx_kl | 0.011759969 | +| clip_fraction | 0.287 | +| clip_range | 0.0643 | +| entropy_loss | -5.81 | +| explained_variance | 0.653 | +| learning_rate | 3.98e-05 | +| loss | -0.0229 | +| n_updates | 99792 | +| policy_gradient_loss | -0.0148 | +| value_loss | 0.000113 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.382 | +| time/ | | +| fps | 1382 | +| iterations | 20995 | +| time_elapsed | 31096 | +| total_timesteps | 42997760 | +| train/ | | +| approx_kl | 0.009971737 | +| clip_fraction | 0.281 | +| clip_range | 0.0643 | +| entropy_loss | -5.9 | +| explained_variance | 0.484 | +| learning_rate | 3.98e-05 | +| loss | -0.0234 | +| n_updates | 99796 | +| policy_gradient_loss | -0.0148 | +| value_loss | 0.000203 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1382 | +| iterations | 20996 | +| time_elapsed | 31098 | +| total_timesteps | 42999808 | +| train/ | | +| approx_kl | 0.009297869 | +| clip_fraction | 0.307 | +| clip_range | 0.0643 | +| entropy_loss | -6.37 | +| explained_variance | 0.182 | +| learning_rate | 3.98e-05 | +| loss | -0.0237 | +| n_updates | 99800 | +| policy_gradient_loss | -0.0136 | +| value_loss | 0.000358 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.377 | +| time/ | | +| fps | 1382 | +| iterations | 20997 | +| time_elapsed | 31100 | +| total_timesteps | 43001856 | +| train/ | | +| approx_kl | 0.012673079 | +| clip_fraction | 0.323 | +| clip_range | 0.0643 | +| entropy_loss | -5.7 | +| explained_variance | 0.522 | +| learning_rate | 3.98e-05 | +| loss | -0.0248 | +| n_updates | 99804 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000139 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1382 | +| iterations | 20998 | +| time_elapsed | 31101 | +| total_timesteps | 43003904 | +| train/ | | +| approx_kl | 0.011072712 | +| clip_fraction | 0.335 | +| clip_range | 0.0642 | +| entropy_loss | -6.58 | +| explained_variance | 0.242 | +| learning_rate | 3.98e-05 | +| loss | -0.0326 | +| n_updates | 99808 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000218 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1382 | +| iterations | 20999 | +| time_elapsed | 31103 | +| total_timesteps | 43005952 | +| train/ | | +| approx_kl | 0.011663028 | +| clip_fraction | 0.298 | +| clip_range | 0.0642 | +| entropy_loss | -6.48 | +| explained_variance | 0.22 | +| learning_rate | 3.98e-05 | +| loss | -0.025 | +| n_updates | 99812 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000196 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.379 | +| time/ | | +| fps | 1382 | +| iterations | 21000 | +| time_elapsed | 31104 | +| total_timesteps | 43008000 | +| train/ | | +| approx_kl | 0.014376415 | +| clip_fraction | 0.344 | +| clip_range | 0.0642 | +| entropy_loss | -5.6 | +| explained_variance | 0.545 | +| learning_rate | 3.98e-05 | +| loss | -0.029 | +| n_updates | 99816 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1382 | +| iterations | 21001 | +| time_elapsed | 31106 | +| total_timesteps | 43010048 | +| train/ | | +| approx_kl | 0.012936307 | +| clip_fraction | 0.372 | +| clip_range | 0.0642 | +| entropy_loss | -5.94 | +| explained_variance | 0.228 | +| learning_rate | 3.98e-05 | +| loss | -0.0323 | +| n_updates | 99820 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000165 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.381 | +| time/ | | +| fps | 1382 | +| iterations | 21002 | +| time_elapsed | 31107 | +| total_timesteps | 43012096 | +| train/ | | +| approx_kl | 0.009713739 | +| clip_fraction | 0.327 | +| clip_range | 0.0642 | +| entropy_loss | -6.65 | +| explained_variance | 0.000856 | +| learning_rate | 3.98e-05 | +| loss | -0.0219 | +| n_updates | 99824 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000182 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1382 | +| iterations | 21003 | +| time_elapsed | 31109 | +| total_timesteps | 43014144 | +| train/ | | +| approx_kl | 0.010019717 | +| clip_fraction | 0.309 | +| clip_range | 0.0642 | +| entropy_loss | -6.05 | +| explained_variance | 0.526 | +| learning_rate | 3.98e-05 | +| loss | -0.0279 | +| n_updates | 99828 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000109 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.37 | +| time/ | | +| fps | 1382 | +| iterations | 21004 | +| time_elapsed | 31111 | +| total_timesteps | 43016192 | +| train/ | | +| approx_kl | 0.011927113 | +| clip_fraction | 0.305 | +| clip_range | 0.0642 | +| entropy_loss | -6.23 | +| explained_variance | 0.581 | +| learning_rate | 3.98e-05 | +| loss | -0.0348 | +| n_updates | 99832 | +| policy_gradient_loss | -0.0166 | +| value_loss | 9.14e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1382 | +| iterations | 21005 | +| time_elapsed | 31112 | +| total_timesteps | 43018240 | +| train/ | | +| approx_kl | 0.013242566 | +| clip_fraction | 0.325 | +| clip_range | 0.0642 | +| entropy_loss | -5.91 | +| explained_variance | 0.686 | +| learning_rate | 3.98e-05 | +| loss | -0.0242 | +| n_updates | 99836 | +| policy_gradient_loss | -0.0175 | +| value_loss | 8.3e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1382 | +| iterations | 21006 | +| time_elapsed | 31114 | +| total_timesteps | 43020288 | +| train/ | | +| approx_kl | 0.011976373 | +| clip_fraction | 0.3 | +| clip_range | 0.0642 | +| entropy_loss | -6.04 | +| explained_variance | 0.574 | +| learning_rate | 3.98e-05 | +| loss | -0.0225 | +| n_updates | 99840 | +| policy_gradient_loss | -0.0144 | +| value_loss | 0.000126 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.368 | +| time/ | | +| fps | 1382 | +| iterations | 21007 | +| time_elapsed | 31115 | +| total_timesteps | 43022336 | +| train/ | | +| approx_kl | 0.011822064 | +| clip_fraction | 0.318 | +| clip_range | 0.0642 | +| entropy_loss | -6.11 | +| explained_variance | 0.352 | +| learning_rate | 3.98e-05 | +| loss | -0.031 | +| n_updates | 99844 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000146 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1382 | +| iterations | 21008 | +| time_elapsed | 31117 | +| total_timesteps | 43024384 | +| train/ | | +| approx_kl | 0.013482749 | +| clip_fraction | 0.329 | +| clip_range | 0.0642 | +| entropy_loss | -5.65 | +| explained_variance | 0.691 | +| learning_rate | 3.98e-05 | +| loss | -0.0261 | +| n_updates | 99848 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000102 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1382 | +| iterations | 21009 | +| time_elapsed | 31118 | +| total_timesteps | 43026432 | +| train/ | | +| approx_kl | 0.015935747 | +| clip_fraction | 0.368 | +| clip_range | 0.0642 | +| entropy_loss | -5.58 | +| explained_variance | 0.737 | +| learning_rate | 3.98e-05 | +| loss | -0.0317 | +| n_updates | 99852 | +| policy_gradient_loss | -0.0176 | +| value_loss | 8.61e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1382 | +| iterations | 21010 | +| time_elapsed | 31120 | +| total_timesteps | 43028480 | +| train/ | | +| approx_kl | 0.011618763 | +| clip_fraction | 0.334 | +| clip_range | 0.0642 | +| entropy_loss | -6.04 | +| explained_variance | 0.377 | +| learning_rate | 3.98e-05 | +| loss | -0.0322 | +| n_updates | 99856 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000121 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1382 | +| iterations | 21011 | +| time_elapsed | 31121 | +| total_timesteps | 43030528 | +| train/ | | +| approx_kl | 0.012920071 | +| clip_fraction | 0.333 | +| clip_range | 0.0642 | +| entropy_loss | -6.39 | +| explained_variance | -0.169 | +| learning_rate | 3.98e-05 | +| loss | -0.0256 | +| n_updates | 99860 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000132 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1382 | +| iterations | 21012 | +| time_elapsed | 31123 | +| total_timesteps | 43032576 | +| train/ | | +| approx_kl | 0.012882814 | +| clip_fraction | 0.324 | +| clip_range | 0.0642 | +| entropy_loss | -6.15 | +| explained_variance | 0.517 | +| learning_rate | 3.98e-05 | +| loss | -0.0237 | +| n_updates | 99864 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000153 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1382 | +| iterations | 21013 | +| time_elapsed | 31124 | +| total_timesteps | 43034624 | +| train/ | | +| approx_kl | 0.010887513 | +| clip_fraction | 0.319 | +| clip_range | 0.0642 | +| entropy_loss | -6.09 | +| explained_variance | 0.334 | +| learning_rate | 3.98e-05 | +| loss | -0.0279 | +| n_updates | 99868 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000153 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1382 | +| iterations | 21014 | +| time_elapsed | 31126 | +| total_timesteps | 43036672 | +| train/ | | +| approx_kl | 0.012114911 | +| clip_fraction | 0.348 | +| clip_range | 0.0642 | +| entropy_loss | -6.02 | +| explained_variance | 0.408 | +| learning_rate | 3.98e-05 | +| loss | -0.0306 | +| n_updates | 99872 | +| policy_gradient_loss | -0.0181 | +| value_loss | 9.22e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1382 | +| iterations | 21015 | +| time_elapsed | 31127 | +| total_timesteps | 43038720 | +| train/ | | +| approx_kl | 0.013764994 | +| clip_fraction | 0.317 | +| clip_range | 0.0642 | +| entropy_loss | -6.01 | +| explained_variance | 0.65 | +| learning_rate | 3.98e-05 | +| loss | -0.0246 | +| n_updates | 99876 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000125 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1382 | +| iterations | 21016 | +| time_elapsed | 31129 | +| total_timesteps | 43040768 | +| train/ | | +| approx_kl | 0.009682596 | +| clip_fraction | 0.282 | +| clip_range | 0.0642 | +| entropy_loss | -5.56 | +| explained_variance | 0.385 | +| learning_rate | 3.98e-05 | +| loss | -0.0217 | +| n_updates | 99880 | +| policy_gradient_loss | -0.0139 | +| value_loss | 0.000252 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1382 | +| iterations | 21017 | +| time_elapsed | 31130 | +| total_timesteps | 43042816 | +| train/ | | +| approx_kl | 0.009338351 | +| clip_fraction | 0.309 | +| clip_range | 0.0642 | +| entropy_loss | -6.63 | +| explained_variance | 0.0668 | +| learning_rate | 3.98e-05 | +| loss | -0.0336 | +| n_updates | 99884 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000112 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1382 | +| iterations | 21018 | +| time_elapsed | 31132 | +| total_timesteps | 43044864 | +| train/ | | +| approx_kl | 0.007829718 | +| clip_fraction | 0.275 | +| clip_range | 0.0642 | +| entropy_loss | -5.78 | +| explained_variance | 0.613 | +| learning_rate | 3.98e-05 | +| loss | -0.0228 | +| n_updates | 99888 | +| policy_gradient_loss | -0.0136 | +| value_loss | 0.000188 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1382 | +| iterations | 21019 | +| time_elapsed | 31133 | +| total_timesteps | 43046912 | +| train/ | | +| approx_kl | 0.009389894 | +| clip_fraction | 0.326 | +| clip_range | 0.0642 | +| entropy_loss | -5.7 | +| explained_variance | 0.338 | +| learning_rate | 3.98e-05 | +| loss | -0.0274 | +| n_updates | 99892 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000129 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1382 | +| iterations | 21020 | +| time_elapsed | 31135 | +| total_timesteps | 43048960 | +| train/ | | +| approx_kl | 0.0102907885 | +| clip_fraction | 0.334 | +| clip_range | 0.0642 | +| entropy_loss | -6.02 | +| explained_variance | 0.292 | +| learning_rate | 3.98e-05 | +| loss | -0.0283 | +| n_updates | 99896 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000205 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.362 | +| time/ | | +| fps | 1382 | +| iterations | 21021 | +| time_elapsed | 31137 | +| total_timesteps | 43051008 | +| train/ | | +| approx_kl | 0.010484144 | +| clip_fraction | 0.332 | +| clip_range | 0.0642 | +| entropy_loss | -5.53 | +| explained_variance | 0.377 | +| learning_rate | 3.98e-05 | +| loss | -0.0206 | +| n_updates | 99900 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000406 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1382 | +| iterations | 21022 | +| time_elapsed | 31138 | +| total_timesteps | 43053056 | +| train/ | | +| approx_kl | 0.013411389 | +| clip_fraction | 0.362 | +| clip_range | 0.0642 | +| entropy_loss | -5.93 | +| explained_variance | 0.342 | +| learning_rate | 3.98e-05 | +| loss | -0.0345 | +| n_updates | 99904 | +| policy_gradient_loss | -0.0219 | +| value_loss | 0.000119 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1382 | +| iterations | 21023 | +| time_elapsed | 31140 | +| total_timesteps | 43055104 | +| train/ | | +| approx_kl | 0.014011547 | +| clip_fraction | 0.316 | +| clip_range | 0.0642 | +| entropy_loss | -6.47 | +| explained_variance | 0.174 | +| learning_rate | 3.98e-05 | +| loss | -0.0265 | +| n_updates | 99908 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000249 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1382 | +| iterations | 21024 | +| time_elapsed | 31141 | +| total_timesteps | 43057152 | +| train/ | | +| approx_kl | 0.011373916 | +| clip_fraction | 0.339 | +| clip_range | 0.0642 | +| entropy_loss | -5.58 | +| explained_variance | 0.357 | +| learning_rate | 3.98e-05 | +| loss | -0.0282 | +| n_updates | 99912 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000201 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.372 | +| time/ | | +| fps | 1382 | +| iterations | 21025 | +| time_elapsed | 31143 | +| total_timesteps | 43059200 | +| train/ | | +| approx_kl | 0.012026189 | +| clip_fraction | 0.358 | +| clip_range | 0.0642 | +| entropy_loss | -5.79 | +| explained_variance | 0.265 | +| learning_rate | 3.98e-05 | +| loss | -0.027 | +| n_updates | 99916 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000141 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.375 | +| time/ | | +| fps | 1382 | +| iterations | 21026 | +| time_elapsed | 31144 | +| total_timesteps | 43061248 | +| train/ | | +| approx_kl | 0.011519091 | +| clip_fraction | 0.329 | +| clip_range | 0.0642 | +| entropy_loss | -6.28 | +| explained_variance | 0.33 | +| learning_rate | 3.98e-05 | +| loss | -0.0327 | +| n_updates | 99920 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.00012 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.371 | +| time/ | | +| fps | 1382 | +| iterations | 21027 | +| time_elapsed | 31146 | +| total_timesteps | 43063296 | +| train/ | | +| approx_kl | 0.011361363 | +| clip_fraction | 0.319 | +| clip_range | 0.0642 | +| entropy_loss | -5.67 | +| explained_variance | 0.33 | +| learning_rate | 3.98e-05 | +| loss | -0.0205 | +| n_updates | 99924 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000158 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.373 | +| time/ | | +| fps | 1382 | +| iterations | 21028 | +| time_elapsed | 31147 | +| total_timesteps | 43065344 | +| train/ | | +| approx_kl | 0.01132789 | +| clip_fraction | 0.346 | +| clip_range | 0.0642 | +| entropy_loss | -6.05 | +| explained_variance | 0.698 | +| learning_rate | 3.98e-05 | +| loss | -0.035 | +| n_updates | 99928 | +| policy_gradient_loss | -0.0198 | +| value_loss | 6.64e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1382 | +| iterations | 21029 | +| time_elapsed | 31149 | +| total_timesteps | 43067392 | +| train/ | | +| approx_kl | 0.010393073 | +| clip_fraction | 0.294 | +| clip_range | 0.0642 | +| entropy_loss | -6.11 | +| explained_variance | 0.267 | +| learning_rate | 3.98e-05 | +| loss | -0.0225 | +| n_updates | 99932 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000218 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1382 | +| iterations | 21030 | +| time_elapsed | 31150 | +| total_timesteps | 43069440 | +| train/ | | +| approx_kl | 0.011633741 | +| clip_fraction | 0.318 | +| clip_range | 0.0642 | +| entropy_loss | -5.77 | +| explained_variance | 0.63 | +| learning_rate | 3.98e-05 | +| loss | -0.0292 | +| n_updates | 99936 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000102 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1382 | +| iterations | 21031 | +| time_elapsed | 31152 | +| total_timesteps | 43071488 | +| train/ | | +| approx_kl | 0.01235581 | +| clip_fraction | 0.315 | +| clip_range | 0.0642 | +| entropy_loss | -5.94 | +| explained_variance | 0.283 | +| learning_rate | 3.98e-05 | +| loss | -0.0268 | +| n_updates | 99940 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000185 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1382 | +| iterations | 21032 | +| time_elapsed | 31154 | +| total_timesteps | 43073536 | +| train/ | | +| approx_kl | 0.011790361 | +| clip_fraction | 0.33 | +| clip_range | 0.0642 | +| entropy_loss | -5.77 | +| explained_variance | 0.606 | +| learning_rate | 3.98e-05 | +| loss | -0.03 | +| n_updates | 99944 | +| policy_gradient_loss | -0.017 | +| value_loss | 9.51e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1382 | +| iterations | 21033 | +| time_elapsed | 31155 | +| total_timesteps | 43075584 | +| train/ | | +| approx_kl | 0.0111933015 | +| clip_fraction | 0.303 | +| clip_range | 0.0642 | +| entropy_loss | -5.53 | +| explained_variance | 0.56 | +| learning_rate | 3.98e-05 | +| loss | -0.0234 | +| n_updates | 99948 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000185 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1382 | +| iterations | 21034 | +| time_elapsed | 31157 | +| total_timesteps | 43077632 | +| train/ | | +| approx_kl | 0.011283807 | +| clip_fraction | 0.3 | +| clip_range | 0.0642 | +| entropy_loss | -5.41 | +| explained_variance | 0.645 | +| learning_rate | 3.98e-05 | +| loss | -0.0232 | +| n_updates | 99952 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000154 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1382 | +| iterations | 21035 | +| time_elapsed | 31158 | +| total_timesteps | 43079680 | +| train/ | | +| approx_kl | 0.015822697 | +| clip_fraction | 0.313 | +| clip_range | 0.0642 | +| entropy_loss | -5.32 | +| explained_variance | 0.258 | +| learning_rate | 3.98e-05 | +| loss | -0.0257 | +| n_updates | 99956 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000309 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1382 | +| iterations | 21036 | +| time_elapsed | 31160 | +| total_timesteps | 43081728 | +| train/ | | +| approx_kl | 0.012120232 | +| clip_fraction | 0.359 | +| clip_range | 0.0642 | +| entropy_loss | -6.25 | +| explained_variance | -0.133 | +| learning_rate | 3.98e-05 | +| loss | -0.0353 | +| n_updates | 99960 | +| policy_gradient_loss | -0.0214 | +| value_loss | 6.86e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1382 | +| iterations | 21037 | +| time_elapsed | 31161 | +| total_timesteps | 43083776 | +| train/ | | +| approx_kl | 0.010585595 | +| clip_fraction | 0.312 | +| clip_range | 0.0642 | +| entropy_loss | -6.26 | +| explained_variance | 0.277 | +| learning_rate | 3.98e-05 | +| loss | -0.0207 | +| n_updates | 99964 | +| policy_gradient_loss | -0.0145 | +| value_loss | 0.000375 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1382 | +| iterations | 21038 | +| time_elapsed | 31163 | +| total_timesteps | 43085824 | +| train/ | | +| approx_kl | 0.010984091 | +| clip_fraction | 0.332 | +| clip_range | 0.0642 | +| entropy_loss | -6.06 | +| explained_variance | 0.302 | +| learning_rate | 3.98e-05 | +| loss | -0.0315 | +| n_updates | 99968 | +| policy_gradient_loss | -0.0196 | +| value_loss | 9.05e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1382 | +| iterations | 21039 | +| time_elapsed | 31164 | +| total_timesteps | 43087872 | +| train/ | | +| approx_kl | 0.010758205 | +| clip_fraction | 0.315 | +| clip_range | 0.0642 | +| entropy_loss | -6.77 | +| explained_variance | -0.0389 | +| learning_rate | 3.98e-05 | +| loss | -0.0293 | +| n_updates | 99972 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000224 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1382 | +| iterations | 21040 | +| time_elapsed | 31166 | +| total_timesteps | 43089920 | +| train/ | | +| approx_kl | 0.011923686 | +| clip_fraction | 0.331 | +| clip_range | 0.0642 | +| entropy_loss | -6.73 | +| explained_variance | -0.0171 | +| learning_rate | 3.98e-05 | +| loss | -0.0318 | +| n_updates | 99976 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1382 | +| iterations | 21041 | +| time_elapsed | 31167 | +| total_timesteps | 43091968 | +| train/ | | +| approx_kl | 0.011006637 | +| clip_fraction | 0.317 | +| clip_range | 0.0642 | +| entropy_loss | -6.06 | +| explained_variance | 0.364 | +| learning_rate | 3.98e-05 | +| loss | -0.0272 | +| n_updates | 99980 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000129 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1382 | +| iterations | 21042 | +| time_elapsed | 31169 | +| total_timesteps | 43094016 | +| train/ | | +| approx_kl | 0.008235659 | +| clip_fraction | 0.289 | +| clip_range | 0.0642 | +| entropy_loss | -5.55 | +| explained_variance | 0.514 | +| learning_rate | 3.98e-05 | +| loss | -0.0257 | +| n_updates | 99984 | +| policy_gradient_loss | -0.014 | +| value_loss | 0.00021 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1382 | +| iterations | 21043 | +| time_elapsed | 31170 | +| total_timesteps | 43096064 | +| train/ | | +| approx_kl | 0.009205449 | +| clip_fraction | 0.29 | +| clip_range | 0.0642 | +| entropy_loss | -6.09 | +| explained_variance | 0.134 | +| learning_rate | 3.98e-05 | +| loss | -0.0249 | +| n_updates | 99988 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000199 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1382 | +| iterations | 21044 | +| time_elapsed | 31172 | +| total_timesteps | 43098112 | +| train/ | | +| approx_kl | 0.009784838 | +| clip_fraction | 0.305 | +| clip_range | 0.0642 | +| entropy_loss | -5.92 | +| explained_variance | 0.807 | +| learning_rate | 3.98e-05 | +| loss | -0.0213 | +| n_updates | 99992 | +| policy_gradient_loss | -0.0168 | +| value_loss | 6.95e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1382 | +| iterations | 21045 | +| time_elapsed | 31173 | +| total_timesteps | 43100160 | +| train/ | | +| approx_kl | 0.011544072 | +| clip_fraction | 0.31 | +| clip_range | 0.0642 | +| entropy_loss | -5.77 | +| explained_variance | 0.59 | +| learning_rate | 3.98e-05 | +| loss | -0.0254 | +| n_updates | 99996 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1382 | +| iterations | 21046 | +| time_elapsed | 31175 | +| total_timesteps | 43102208 | +| train/ | | +| approx_kl | 0.010862029 | +| clip_fraction | 0.305 | +| clip_range | 0.0642 | +| entropy_loss | -5.52 | +| explained_variance | 0.839 | +| learning_rate | 3.98e-05 | +| loss | -0.0193 | +| n_updates | 100000 | +| policy_gradient_loss | -0.0149 | +| value_loss | 6.39e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1382 | +| iterations | 21047 | +| time_elapsed | 31177 | +| total_timesteps | 43104256 | +| train/ | | +| approx_kl | 0.011513725 | +| clip_fraction | 0.262 | +| clip_range | 0.0642 | +| entropy_loss | -5.81 | +| explained_variance | 0.664 | +| learning_rate | 3.98e-05 | +| loss | -0.017 | +| n_updates | 100004 | +| policy_gradient_loss | -0.0123 | +| value_loss | 0.000148 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1382 | +| iterations | 21048 | +| time_elapsed | 31178 | +| total_timesteps | 43106304 | +| train/ | | +| approx_kl | 0.010710437 | +| clip_fraction | 0.288 | +| clip_range | 0.0642 | +| entropy_loss | -6.25 | +| explained_variance | 0.559 | +| learning_rate | 3.98e-05 | +| loss | -0.0265 | +| n_updates | 100008 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.000124 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1382 | +| iterations | 21049 | +| time_elapsed | 31180 | +| total_timesteps | 43108352 | +| train/ | | +| approx_kl | 0.010434461 | +| clip_fraction | 0.279 | +| clip_range | 0.0642 | +| entropy_loss | -6.15 | +| explained_variance | 0.216 | +| learning_rate | 3.98e-05 | +| loss | -0.0261 | +| n_updates | 100012 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000184 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1382 | +| iterations | 21050 | +| time_elapsed | 31181 | +| total_timesteps | 43110400 | +| train/ | | +| approx_kl | 0.01043094 | +| clip_fraction | 0.329 | +| clip_range | 0.0642 | +| entropy_loss | -6.28 | +| explained_variance | 0.0387 | +| learning_rate | 3.98e-05 | +| loss | -0.0305 | +| n_updates | 100016 | +| policy_gradient_loss | -0.0191 | +| value_loss | 7.78e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1382 | +| iterations | 21051 | +| time_elapsed | 31183 | +| total_timesteps | 43112448 | +| train/ | | +| approx_kl | 0.011940371 | +| clip_fraction | 0.312 | +| clip_range | 0.0642 | +| entropy_loss | -5.98 | +| explained_variance | 0.62 | +| learning_rate | 3.98e-05 | +| loss | -0.0241 | +| n_updates | 100020 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000134 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1382 | +| iterations | 21052 | +| time_elapsed | 31184 | +| total_timesteps | 43114496 | +| train/ | | +| approx_kl | 0.012207527 | +| clip_fraction | 0.276 | +| clip_range | 0.0642 | +| entropy_loss | -6.09 | +| explained_variance | 0.402 | +| learning_rate | 3.98e-05 | +| loss | -0.0267 | +| n_updates | 100024 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1382 | +| iterations | 21053 | +| time_elapsed | 31186 | +| total_timesteps | 43116544 | +| train/ | | +| approx_kl | 0.010252581 | +| clip_fraction | 0.309 | +| clip_range | 0.0642 | +| entropy_loss | -5.2 | +| explained_variance | 0.534 | +| learning_rate | 3.98e-05 | +| loss | -0.0242 | +| n_updates | 100028 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000126 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1382 | +| iterations | 21054 | +| time_elapsed | 31188 | +| total_timesteps | 43118592 | +| train/ | | +| approx_kl | 0.011840867 | +| clip_fraction | 0.343 | +| clip_range | 0.0642 | +| entropy_loss | -5.77 | +| explained_variance | 0.466 | +| learning_rate | 3.98e-05 | +| loss | -0.0262 | +| n_updates | 100032 | +| policy_gradient_loss | -0.019 | +| value_loss | 8.94e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1382 | +| iterations | 21055 | +| time_elapsed | 31189 | +| total_timesteps | 43120640 | +| train/ | | +| approx_kl | 0.0133405235 | +| clip_fraction | 0.292 | +| clip_range | 0.0642 | +| entropy_loss | -5.49 | +| explained_variance | 0.527 | +| learning_rate | 3.98e-05 | +| loss | -0.0243 | +| n_updates | 100036 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.000221 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1382 | +| iterations | 21056 | +| time_elapsed | 31191 | +| total_timesteps | 43122688 | +| train/ | | +| approx_kl | 0.013253328 | +| clip_fraction | 0.341 | +| clip_range | 0.0642 | +| entropy_loss | -4.56 | +| explained_variance | 0.747 | +| learning_rate | 3.98e-05 | +| loss | -0.0272 | +| n_updates | 100040 | +| policy_gradient_loss | -0.0173 | +| value_loss | 8.92e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1382 | +| iterations | 21057 | +| time_elapsed | 31192 | +| total_timesteps | 43124736 | +| train/ | | +| approx_kl | 0.009454433 | +| clip_fraction | 0.308 | +| clip_range | 0.0642 | +| entropy_loss | -6.05 | +| explained_variance | 0.142 | +| learning_rate | 3.98e-05 | +| loss | -0.0273 | +| n_updates | 100044 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000105 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1382 | +| iterations | 21058 | +| time_elapsed | 31194 | +| total_timesteps | 43126784 | +| train/ | | +| approx_kl | 0.013195563 | +| clip_fraction | 0.312 | +| clip_range | 0.0642 | +| entropy_loss | -6.54 | +| explained_variance | -0.125 | +| learning_rate | 3.98e-05 | +| loss | -0.0279 | +| n_updates | 100048 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000137 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1382 | +| iterations | 21059 | +| time_elapsed | 31195 | +| total_timesteps | 43128832 | +| train/ | | +| approx_kl | 0.011087238 | +| clip_fraction | 0.312 | +| clip_range | 0.0642 | +| entropy_loss | -6.31 | +| explained_variance | 0.371 | +| learning_rate | 3.98e-05 | +| loss | -0.0295 | +| n_updates | 100052 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.00013 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1382 | +| iterations | 21060 | +| time_elapsed | 31197 | +| total_timesteps | 43130880 | +| train/ | | +| approx_kl | 0.009627584 | +| clip_fraction | 0.332 | +| clip_range | 0.0642 | +| entropy_loss | -6.42 | +| explained_variance | -0.126 | +| learning_rate | 3.98e-05 | +| loss | -0.03 | +| n_updates | 100056 | +| policy_gradient_loss | -0.0191 | +| value_loss | 8.1e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1382 | +| iterations | 21061 | +| time_elapsed | 31198 | +| total_timesteps | 43132928 | +| train/ | | +| approx_kl | 0.009747677 | +| clip_fraction | 0.293 | +| clip_range | 0.0642 | +| entropy_loss | -5.77 | +| explained_variance | 0.693 | +| learning_rate | 3.98e-05 | +| loss | -0.0254 | +| n_updates | 100060 | +| policy_gradient_loss | -0.0146 | +| value_loss | 0.00016 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.315 | +| time/ | | +| fps | 1382 | +| iterations | 21062 | +| time_elapsed | 31200 | +| total_timesteps | 43134976 | +| train/ | | +| approx_kl | 0.010634238 | +| clip_fraction | 0.315 | +| clip_range | 0.0642 | +| entropy_loss | -5.74 | +| explained_variance | 0.363 | +| learning_rate | 3.98e-05 | +| loss | -0.0258 | +| n_updates | 100064 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000102 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.315 | +| time/ | | +| fps | 1382 | +| iterations | 21063 | +| time_elapsed | 31201 | +| total_timesteps | 43137024 | +| train/ | | +| approx_kl | 0.008239749 | +| clip_fraction | 0.275 | +| clip_range | 0.0642 | +| entropy_loss | -6.23 | +| explained_variance | 0.381 | +| learning_rate | 3.98e-05 | +| loss | -0.0227 | +| n_updates | 100068 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.000211 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1382 | +| iterations | 21064 | +| time_elapsed | 31203 | +| total_timesteps | 43139072 | +| train/ | | +| approx_kl | 0.010601954 | +| clip_fraction | 0.323 | +| clip_range | 0.0642 | +| entropy_loss | -6.46 | +| explained_variance | 0.46 | +| learning_rate | 3.98e-05 | +| loss | -0.0299 | +| n_updates | 100072 | +| policy_gradient_loss | -0.0182 | +| value_loss | 9.51e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1382 | +| iterations | 21065 | +| time_elapsed | 31205 | +| total_timesteps | 43141120 | +| train/ | | +| approx_kl | 0.011079322 | +| clip_fraction | 0.339 | +| clip_range | 0.0642 | +| entropy_loss | -6.36 | +| explained_variance | 0.657 | +| learning_rate | 3.98e-05 | +| loss | -0.0265 | +| n_updates | 100076 | +| policy_gradient_loss | -0.0177 | +| value_loss | 7.85e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1382 | +| iterations | 21066 | +| time_elapsed | 31206 | +| total_timesteps | 43143168 | +| train/ | | +| approx_kl | 0.012155293 | +| clip_fraction | 0.321 | +| clip_range | 0.0642 | +| entropy_loss | -5.94 | +| explained_variance | 0.63 | +| learning_rate | 3.98e-05 | +| loss | -0.0205 | +| n_updates | 100080 | +| policy_gradient_loss | -0.0165 | +| value_loss | 9.35e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1382 | +| iterations | 21067 | +| time_elapsed | 31208 | +| total_timesteps | 43145216 | +| train/ | | +| approx_kl | 0.01180559 | +| clip_fraction | 0.325 | +| clip_range | 0.0642 | +| entropy_loss | -5.64 | +| explained_variance | 0.232 | +| learning_rate | 3.98e-05 | +| loss | -0.0257 | +| n_updates | 100084 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.00023 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1382 | +| iterations | 21068 | +| time_elapsed | 31209 | +| total_timesteps | 43147264 | +| train/ | | +| approx_kl | 0.010271292 | +| clip_fraction | 0.298 | +| clip_range | 0.0642 | +| entropy_loss | -6.19 | +| explained_variance | 0.346 | +| learning_rate | 3.98e-05 | +| loss | -0.0204 | +| n_updates | 100088 | +| policy_gradient_loss | -0.0148 | +| value_loss | 0.000141 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1382 | +| iterations | 21069 | +| time_elapsed | 31211 | +| total_timesteps | 43149312 | +| train/ | | +| approx_kl | 0.014035002 | +| clip_fraction | 0.32 | +| clip_range | 0.0642 | +| entropy_loss | -5.69 | +| explained_variance | 0.378 | +| learning_rate | 3.98e-05 | +| loss | -0.0271 | +| n_updates | 100092 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000144 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1382 | +| iterations | 21070 | +| time_elapsed | 31212 | +| total_timesteps | 43151360 | +| train/ | | +| approx_kl | 0.0126290405 | +| clip_fraction | 0.332 | +| clip_range | 0.0642 | +| entropy_loss | -5.68 | +| explained_variance | 0.495 | +| learning_rate | 3.98e-05 | +| loss | -0.0295 | +| n_updates | 100096 | +| policy_gradient_loss | -0.0185 | +| value_loss | 7.15e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1382 | +| iterations | 21071 | +| time_elapsed | 31214 | +| total_timesteps | 43153408 | +| train/ | | +| approx_kl | 0.011648019 | +| clip_fraction | 0.307 | +| clip_range | 0.0642 | +| entropy_loss | -5.69 | +| explained_variance | 0.355 | +| learning_rate | 3.98e-05 | +| loss | -0.0221 | +| n_updates | 100100 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.000181 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1382 | +| iterations | 21072 | +| time_elapsed | 31215 | +| total_timesteps | 43155456 | +| train/ | | +| approx_kl | 0.012063745 | +| clip_fraction | 0.325 | +| clip_range | 0.0642 | +| entropy_loss | -6.33 | +| explained_variance | 0.396 | +| learning_rate | 3.98e-05 | +| loss | -0.0288 | +| n_updates | 100104 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000113 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1382 | +| iterations | 21073 | +| time_elapsed | 31217 | +| total_timesteps | 43157504 | +| train/ | | +| approx_kl | 0.013338201 | +| clip_fraction | 0.281 | +| clip_range | 0.0642 | +| entropy_loss | -6.01 | +| explained_variance | 0.441 | +| learning_rate | 3.98e-05 | +| loss | -0.0239 | +| n_updates | 100108 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000242 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1382 | +| iterations | 21074 | +| time_elapsed | 31218 | +| total_timesteps | 43159552 | +| train/ | | +| approx_kl | 0.011597222 | +| clip_fraction | 0.315 | +| clip_range | 0.0642 | +| entropy_loss | -5.84 | +| explained_variance | 0.562 | +| learning_rate | 3.98e-05 | +| loss | -0.0208 | +| n_updates | 100112 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000184 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1382 | +| iterations | 21075 | +| time_elapsed | 31220 | +| total_timesteps | 43161600 | +| train/ | | +| approx_kl | 0.013329705 | +| clip_fraction | 0.332 | +| clip_range | 0.0642 | +| entropy_loss | -6.31 | +| explained_variance | -0.173 | +| learning_rate | 3.97e-05 | +| loss | -0.0326 | +| n_updates | 100116 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000131 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1382 | +| iterations | 21076 | +| time_elapsed | 31222 | +| total_timesteps | 43163648 | +| train/ | | +| approx_kl | 0.009845328 | +| clip_fraction | 0.316 | +| clip_range | 0.0642 | +| entropy_loss | -6.71 | +| explained_variance | 0.0179 | +| learning_rate | 3.97e-05 | +| loss | -0.0278 | +| n_updates | 100120 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000168 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1382 | +| iterations | 21077 | +| time_elapsed | 31223 | +| total_timesteps | 43165696 | +| train/ | | +| approx_kl | 0.009610454 | +| clip_fraction | 0.31 | +| clip_range | 0.0642 | +| entropy_loss | -6.53 | +| explained_variance | 0.309 | +| learning_rate | 3.97e-05 | +| loss | -0.0311 | +| n_updates | 100124 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000174 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1382 | +| iterations | 21078 | +| time_elapsed | 31225 | +| total_timesteps | 43167744 | +| train/ | | +| approx_kl | 0.012703638 | +| clip_fraction | 0.333 | +| clip_range | 0.0642 | +| entropy_loss | -5.97 | +| explained_variance | 0.388 | +| learning_rate | 3.97e-05 | +| loss | -0.0272 | +| n_updates | 100128 | +| policy_gradient_loss | -0.0195 | +| value_loss | 9.33e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1382 | +| iterations | 21079 | +| time_elapsed | 31226 | +| total_timesteps | 43169792 | +| train/ | | +| approx_kl | 0.01399686 | +| clip_fraction | 0.337 | +| clip_range | 0.0642 | +| entropy_loss | -5.57 | +| explained_variance | 0.722 | +| learning_rate | 3.97e-05 | +| loss | -0.0238 | +| n_updates | 100132 | +| policy_gradient_loss | -0.0182 | +| value_loss | 7.29e-05 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1382 | +| iterations | 21080 | +| time_elapsed | 31228 | +| total_timesteps | 43171840 | +| train/ | | +| approx_kl | 0.01220374 | +| clip_fraction | 0.342 | +| clip_range | 0.0642 | +| entropy_loss | -5.79 | +| explained_variance | 0.384 | +| learning_rate | 3.97e-05 | +| loss | -0.0314 | +| n_updates | 100136 | +| policy_gradient_loss | -0.0171 | +| value_loss | 9.11e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1382 | +| iterations | 21081 | +| time_elapsed | 31229 | +| total_timesteps | 43173888 | +| train/ | | +| approx_kl | 0.009761455 | +| clip_fraction | 0.308 | +| clip_range | 0.0642 | +| entropy_loss | -5.57 | +| explained_variance | 0.679 | +| learning_rate | 3.97e-05 | +| loss | -0.03 | +| n_updates | 100140 | +| policy_gradient_loss | -0.0164 | +| value_loss | 9.88e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1382 | +| iterations | 21082 | +| time_elapsed | 31231 | +| total_timesteps | 43175936 | +| train/ | | +| approx_kl | 0.01344279 | +| clip_fraction | 0.342 | +| clip_range | 0.0642 | +| entropy_loss | -5.12 | +| explained_variance | 0.835 | +| learning_rate | 3.97e-05 | +| loss | -0.0322 | +| n_updates | 100144 | +| policy_gradient_loss | -0.0182 | +| value_loss | 5.2e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1382 | +| iterations | 21083 | +| time_elapsed | 31232 | +| total_timesteps | 43177984 | +| train/ | | +| approx_kl | 0.013637304 | +| clip_fraction | 0.306 | +| clip_range | 0.0642 | +| entropy_loss | -5.63 | +| explained_variance | 0.0735 | +| learning_rate | 3.97e-05 | +| loss | -0.025 | +| n_updates | 100148 | +| policy_gradient_loss | -0.015 | +| value_loss | 8.39e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1382 | +| iterations | 21084 | +| time_elapsed | 31234 | +| total_timesteps | 43180032 | +| train/ | | +| approx_kl | 0.011511313 | +| clip_fraction | 0.313 | +| clip_range | 0.0642 | +| entropy_loss | -5.85 | +| explained_variance | 0.262 | +| learning_rate | 3.97e-05 | +| loss | -0.0233 | +| n_updates | 100152 | +| policy_gradient_loss | -0.0141 | +| value_loss | 0.000103 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1382 | +| iterations | 21085 | +| time_elapsed | 31235 | +| total_timesteps | 43182080 | +| train/ | | +| approx_kl | 0.009885902 | +| clip_fraction | 0.302 | +| clip_range | 0.0642 | +| entropy_loss | -5.77 | +| explained_variance | 0.357 | +| learning_rate | 3.97e-05 | +| loss | -0.0246 | +| n_updates | 100156 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000177 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1382 | +| iterations | 21086 | +| time_elapsed | 31237 | +| total_timesteps | 43184128 | +| train/ | | +| approx_kl | 0.012490843 | +| clip_fraction | 0.349 | +| clip_range | 0.0642 | +| entropy_loss | -5.96 | +| explained_variance | -0.0476 | +| learning_rate | 3.97e-05 | +| loss | -0.0256 | +| n_updates | 100160 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000148 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1382 | +| iterations | 21087 | +| time_elapsed | 31238 | +| total_timesteps | 43186176 | +| train/ | | +| approx_kl | 0.013334623 | +| clip_fraction | 0.302 | +| clip_range | 0.0642 | +| entropy_loss | -5.37 | +| explained_variance | 0.403 | +| learning_rate | 3.97e-05 | +| loss | -0.0209 | +| n_updates | 100164 | +| policy_gradient_loss | -0.0141 | +| value_loss | 0.000382 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1382 | +| iterations | 21088 | +| time_elapsed | 31240 | +| total_timesteps | 43188224 | +| train/ | | +| approx_kl | 0.012092061 | +| clip_fraction | 0.343 | +| clip_range | 0.0642 | +| entropy_loss | -5.86 | +| explained_variance | -0.261 | +| learning_rate | 3.97e-05 | +| loss | -0.027 | +| n_updates | 100168 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000144 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1382 | +| iterations | 21089 | +| time_elapsed | 31241 | +| total_timesteps | 43190272 | +| train/ | | +| approx_kl | 0.009031544 | +| clip_fraction | 0.323 | +| clip_range | 0.0642 | +| entropy_loss | -5.81 | +| explained_variance | 0.604 | +| learning_rate | 3.97e-05 | +| loss | -0.0258 | +| n_updates | 100172 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1382 | +| iterations | 21090 | +| time_elapsed | 31243 | +| total_timesteps | 43192320 | +| train/ | | +| approx_kl | 0.007403392 | +| clip_fraction | 0.288 | +| clip_range | 0.0642 | +| entropy_loss | -6.03 | +| explained_variance | 0.499 | +| learning_rate | 3.97e-05 | +| loss | -0.0291 | +| n_updates | 100176 | +| policy_gradient_loss | -0.0145 | +| value_loss | 0.000175 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1382 | +| iterations | 21091 | +| time_elapsed | 31245 | +| total_timesteps | 43194368 | +| train/ | | +| approx_kl | 0.013903874 | +| clip_fraction | 0.336 | +| clip_range | 0.0642 | +| entropy_loss | -5.67 | +| explained_variance | 0.241 | +| learning_rate | 3.97e-05 | +| loss | -0.0259 | +| n_updates | 100180 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000163 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1382 | +| iterations | 21092 | +| time_elapsed | 31246 | +| total_timesteps | 43196416 | +| train/ | | +| approx_kl | 0.0097674355 | +| clip_fraction | 0.315 | +| clip_range | 0.0642 | +| entropy_loss | -5.21 | +| explained_variance | 0.44 | +| learning_rate | 3.97e-05 | +| loss | -0.0169 | +| n_updates | 100184 | +| policy_gradient_loss | -0.0139 | +| value_loss | 0.000334 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1382 | +| iterations | 21093 | +| time_elapsed | 31248 | +| total_timesteps | 43198464 | +| train/ | | +| approx_kl | 0.014393149 | +| clip_fraction | 0.359 | +| clip_range | 0.0642 | +| entropy_loss | -5.64 | +| explained_variance | 0.217 | +| learning_rate | 3.97e-05 | +| loss | -0.0309 | +| n_updates | 100188 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000261 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1382 | +| iterations | 21094 | +| time_elapsed | 31249 | +| total_timesteps | 43200512 | +| train/ | | +| approx_kl | 0.013168628 | +| clip_fraction | 0.348 | +| clip_range | 0.0642 | +| entropy_loss | -6.28 | +| explained_variance | 0.263 | +| learning_rate | 3.97e-05 | +| loss | -0.0287 | +| n_updates | 100192 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000203 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1382 | +| iterations | 21095 | +| time_elapsed | 31251 | +| total_timesteps | 43202560 | +| train/ | | +| approx_kl | 0.010798871 | +| clip_fraction | 0.326 | +| clip_range | 0.0642 | +| entropy_loss | -6.05 | +| explained_variance | 0.27 | +| learning_rate | 3.97e-05 | +| loss | -0.0346 | +| n_updates | 100196 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000139 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1382 | +| iterations | 21096 | +| time_elapsed | 31252 | +| total_timesteps | 43204608 | +| train/ | | +| approx_kl | 0.012999269 | +| clip_fraction | 0.361 | +| clip_range | 0.0642 | +| entropy_loss | -6.15 | +| explained_variance | 0.337 | +| learning_rate | 3.97e-05 | +| loss | -0.0311 | +| n_updates | 100200 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000104 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1382 | +| iterations | 21097 | +| time_elapsed | 31254 | +| total_timesteps | 43206656 | +| train/ | | +| approx_kl | 0.013715585 | +| clip_fraction | 0.325 | +| clip_range | 0.0642 | +| entropy_loss | -5.5 | +| explained_variance | 0.557 | +| learning_rate | 3.97e-05 | +| loss | -0.0217 | +| n_updates | 100204 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000124 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1382 | +| iterations | 21098 | +| time_elapsed | 31255 | +| total_timesteps | 43208704 | +| train/ | | +| approx_kl | 0.013302979 | +| clip_fraction | 0.322 | +| clip_range | 0.0642 | +| entropy_loss | -6.02 | +| explained_variance | -0.451 | +| learning_rate | 3.97e-05 | +| loss | -0.0369 | +| n_updates | 100208 | +| policy_gradient_loss | -0.0202 | +| value_loss | 6.12e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1382 | +| iterations | 21099 | +| time_elapsed | 31257 | +| total_timesteps | 43210752 | +| train/ | | +| approx_kl | 0.012424773 | +| clip_fraction | 0.318 | +| clip_range | 0.0642 | +| entropy_loss | -5.2 | +| explained_variance | 0.871 | +| learning_rate | 3.97e-05 | +| loss | -0.0255 | +| n_updates | 100212 | +| policy_gradient_loss | -0.0157 | +| value_loss | 4.19e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1382 | +| iterations | 21100 | +| time_elapsed | 31258 | +| total_timesteps | 43212800 | +| train/ | | +| approx_kl | 0.012415288 | +| clip_fraction | 0.298 | +| clip_range | 0.0642 | +| entropy_loss | -5.79 | +| explained_variance | 0.415 | +| learning_rate | 3.97e-05 | +| loss | -0.0202 | +| n_updates | 100216 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000116 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1382 | +| iterations | 21101 | +| time_elapsed | 31260 | +| total_timesteps | 43214848 | +| train/ | | +| approx_kl | 0.010618122 | +| clip_fraction | 0.307 | +| clip_range | 0.0642 | +| entropy_loss | -5.92 | +| explained_variance | 0.558 | +| learning_rate | 3.97e-05 | +| loss | -0.0239 | +| n_updates | 100220 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.000184 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1382 | +| iterations | 21102 | +| time_elapsed | 31261 | +| total_timesteps | 43216896 | +| train/ | | +| approx_kl | 0.010683793 | +| clip_fraction | 0.312 | +| clip_range | 0.0642 | +| entropy_loss | -6.56 | +| explained_variance | 0.349 | +| learning_rate | 3.97e-05 | +| loss | -0.0283 | +| n_updates | 100224 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000156 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1382 | +| iterations | 21103 | +| time_elapsed | 31263 | +| total_timesteps | 43218944 | +| train/ | | +| approx_kl | 0.010682268 | +| clip_fraction | 0.267 | +| clip_range | 0.0642 | +| entropy_loss | -5.65 | +| explained_variance | 0.397 | +| learning_rate | 3.97e-05 | +| loss | -0.0213 | +| n_updates | 100228 | +| policy_gradient_loss | -0.0134 | +| value_loss | 0.000405 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1382 | +| iterations | 21104 | +| time_elapsed | 31265 | +| total_timesteps | 43220992 | +| train/ | | +| approx_kl | 0.014042918 | +| clip_fraction | 0.335 | +| clip_range | 0.0642 | +| entropy_loss | -5.14 | +| explained_variance | 0.161 | +| learning_rate | 3.97e-05 | +| loss | -0.0155 | +| n_updates | 100232 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000237 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1382 | +| iterations | 21105 | +| time_elapsed | 31266 | +| total_timesteps | 43223040 | +| train/ | | +| approx_kl | 0.0125804525 | +| clip_fraction | 0.341 | +| clip_range | 0.0642 | +| entropy_loss | -5.36 | +| explained_variance | 0.474 | +| learning_rate | 3.97e-05 | +| loss | -0.0261 | +| n_updates | 100236 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000165 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1382 | +| iterations | 21106 | +| time_elapsed | 31268 | +| total_timesteps | 43225088 | +| train/ | | +| approx_kl | 0.013920256 | +| clip_fraction | 0.329 | +| clip_range | 0.0642 | +| entropy_loss | -5.43 | +| explained_variance | 0.494 | +| learning_rate | 3.97e-05 | +| loss | -0.0251 | +| n_updates | 100240 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000122 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1382 | +| iterations | 21107 | +| time_elapsed | 31269 | +| total_timesteps | 43227136 | +| train/ | | +| approx_kl | 0.014399745 | +| clip_fraction | 0.348 | +| clip_range | 0.0642 | +| entropy_loss | -5.97 | +| explained_variance | 0.467 | +| learning_rate | 3.97e-05 | +| loss | -0.025 | +| n_updates | 100244 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000104 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1382 | +| iterations | 21108 | +| time_elapsed | 31271 | +| total_timesteps | 43229184 | +| train/ | | +| approx_kl | 0.009662898 | +| clip_fraction | 0.311 | +| clip_range | 0.0642 | +| entropy_loss | -5.86 | +| explained_variance | -0.0548 | +| learning_rate | 3.97e-05 | +| loss | -0.0272 | +| n_updates | 100248 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000114 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1382 | +| iterations | 21109 | +| time_elapsed | 31272 | +| total_timesteps | 43231232 | +| train/ | | +| approx_kl | 0.0121539375 | +| clip_fraction | 0.311 | +| clip_range | 0.0642 | +| entropy_loss | -6.43 | +| explained_variance | 0.329 | +| learning_rate | 3.97e-05 | +| loss | -0.0256 | +| n_updates | 100252 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.00018 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.315 | +| time/ | | +| fps | 1382 | +| iterations | 21110 | +| time_elapsed | 31274 | +| total_timesteps | 43233280 | +| train/ | | +| approx_kl | 0.009983657 | +| clip_fraction | 0.295 | +| clip_range | 0.0642 | +| entropy_loss | -5.9 | +| explained_variance | 0.37 | +| learning_rate | 3.97e-05 | +| loss | -0.0222 | +| n_updates | 100256 | +| policy_gradient_loss | -0.0127 | +| value_loss | 0.000243 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1382 | +| iterations | 21111 | +| time_elapsed | 31275 | +| total_timesteps | 43235328 | +| train/ | | +| approx_kl | 0.011538714 | +| clip_fraction | 0.33 | +| clip_range | 0.0642 | +| entropy_loss | -5.93 | +| explained_variance | 0.308 | +| learning_rate | 3.97e-05 | +| loss | -0.0278 | +| n_updates | 100260 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1382 | +| iterations | 21112 | +| time_elapsed | 31277 | +| total_timesteps | 43237376 | +| train/ | | +| approx_kl | 0.013088476 | +| clip_fraction | 0.326 | +| clip_range | 0.0642 | +| entropy_loss | -5.91 | +| explained_variance | 0.383 | +| learning_rate | 3.97e-05 | +| loss | -0.0208 | +| n_updates | 100264 | +| policy_gradient_loss | -0.0144 | +| value_loss | 0.00025 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1382 | +| iterations | 21113 | +| time_elapsed | 31278 | +| total_timesteps | 43239424 | +| train/ | | +| approx_kl | 0.010342439 | +| clip_fraction | 0.313 | +| clip_range | 0.0642 | +| entropy_loss | -6.12 | +| explained_variance | 0.223 | +| learning_rate | 3.97e-05 | +| loss | -0.0244 | +| n_updates | 100268 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000263 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1382 | +| iterations | 21114 | +| time_elapsed | 31280 | +| total_timesteps | 43241472 | +| train/ | | +| approx_kl | 0.012434401 | +| clip_fraction | 0.364 | +| clip_range | 0.0642 | +| entropy_loss | -5.48 | +| explained_variance | 0.77 | +| learning_rate | 3.97e-05 | +| loss | -0.0346 | +| n_updates | 100272 | +| policy_gradient_loss | -0.0195 | +| value_loss | 6.81e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1382 | +| iterations | 21115 | +| time_elapsed | 31281 | +| total_timesteps | 43243520 | +| train/ | | +| approx_kl | 0.013392313 | +| clip_fraction | 0.317 | +| clip_range | 0.0642 | +| entropy_loss | -5.06 | +| explained_variance | 0.6 | +| learning_rate | 3.97e-05 | +| loss | -0.0298 | +| n_updates | 100276 | +| policy_gradient_loss | -0.0176 | +| value_loss | 9.42e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1382 | +| iterations | 21116 | +| time_elapsed | 31283 | +| total_timesteps | 43245568 | +| train/ | | +| approx_kl | 0.014693236 | +| clip_fraction | 0.337 | +| clip_range | 0.0642 | +| entropy_loss | -5.55 | +| explained_variance | 0.591 | +| learning_rate | 3.97e-05 | +| loss | -0.032 | +| n_updates | 100280 | +| policy_gradient_loss | -0.0171 | +| value_loss | 7.79e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1382 | +| iterations | 21117 | +| time_elapsed | 31284 | +| total_timesteps | 43247616 | +| train/ | | +| approx_kl | 0.009875264 | +| clip_fraction | 0.322 | +| clip_range | 0.0642 | +| entropy_loss | -6.07 | +| explained_variance | 0.341 | +| learning_rate | 3.97e-05 | +| loss | -0.0252 | +| n_updates | 100284 | +| policy_gradient_loss | -0.0154 | +| value_loss | 9.39e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1382 | +| iterations | 21118 | +| time_elapsed | 31286 | +| total_timesteps | 43249664 | +| train/ | | +| approx_kl | 0.014229901 | +| clip_fraction | 0.314 | +| clip_range | 0.0642 | +| entropy_loss | -6.12 | +| explained_variance | 0.371 | +| learning_rate | 3.97e-05 | +| loss | -0.0256 | +| n_updates | 100288 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000144 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1382 | +| iterations | 21119 | +| time_elapsed | 31288 | +| total_timesteps | 43251712 | +| train/ | | +| approx_kl | 0.0129101155 | +| clip_fraction | 0.327 | +| clip_range | 0.0642 | +| entropy_loss | -6.14 | +| explained_variance | -0.093 | +| learning_rate | 3.97e-05 | +| loss | -0.0273 | +| n_updates | 100292 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000151 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1382 | +| iterations | 21120 | +| time_elapsed | 31289 | +| total_timesteps | 43253760 | +| train/ | | +| approx_kl | 0.012266133 | +| clip_fraction | 0.337 | +| clip_range | 0.0642 | +| entropy_loss | -5.72 | +| explained_variance | 0.743 | +| learning_rate | 3.97e-05 | +| loss | -0.0308 | +| n_updates | 100296 | +| policy_gradient_loss | -0.0179 | +| value_loss | 7.1e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1382 | +| iterations | 21121 | +| time_elapsed | 31291 | +| total_timesteps | 43255808 | +| train/ | | +| approx_kl | 0.013356367 | +| clip_fraction | 0.337 | +| clip_range | 0.0642 | +| entropy_loss | -5.39 | +| explained_variance | 0.347 | +| learning_rate | 3.97e-05 | +| loss | -0.0317 | +| n_updates | 100300 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000122 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1382 | +| iterations | 21122 | +| time_elapsed | 31292 | +| total_timesteps | 43257856 | +| train/ | | +| approx_kl | 0.015952604 | +| clip_fraction | 0.317 | +| clip_range | 0.0642 | +| entropy_loss | -5.63 | +| explained_variance | 0.473 | +| learning_rate | 3.97e-05 | +| loss | -0.0197 | +| n_updates | 100304 | +| policy_gradient_loss | -0.0142 | +| value_loss | 0.000169 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1382 | +| iterations | 21123 | +| time_elapsed | 31294 | +| total_timesteps | 43259904 | +| train/ | | +| approx_kl | 0.01661881 | +| clip_fraction | 0.329 | +| clip_range | 0.0642 | +| entropy_loss | -6.1 | +| explained_variance | -0.16 | +| learning_rate | 3.97e-05 | +| loss | -0.0263 | +| n_updates | 100308 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000139 | +---------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1382 | +| iterations | 21124 | +| time_elapsed | 31295 | +| total_timesteps | 43261952 | +| train/ | | +| approx_kl | 0.0098442 | +| clip_fraction | 0.28 | +| clip_range | 0.0642 | +| entropy_loss | -6.03 | +| explained_variance | 0.464 | +| learning_rate | 3.97e-05 | +| loss | -0.0283 | +| n_updates | 100312 | +| policy_gradient_loss | -0.0138 | +| value_loss | 0.000192 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1382 | +| iterations | 21125 | +| time_elapsed | 31297 | +| total_timesteps | 43264000 | +| train/ | | +| approx_kl | 0.014783828 | +| clip_fraction | 0.331 | +| clip_range | 0.0642 | +| entropy_loss | -5.28 | +| explained_variance | 0.65 | +| learning_rate | 3.97e-05 | +| loss | -0.0262 | +| n_updates | 100316 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000118 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1382 | +| iterations | 21126 | +| time_elapsed | 31298 | +| total_timesteps | 43266048 | +| train/ | | +| approx_kl | 0.010203565 | +| clip_fraction | 0.311 | +| clip_range | 0.0642 | +| entropy_loss | -6.61 | +| explained_variance | 0.421 | +| learning_rate | 3.97e-05 | +| loss | -0.0306 | +| n_updates | 100320 | +| policy_gradient_loss | -0.018 | +| value_loss | 7.9e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1382 | +| iterations | 21127 | +| time_elapsed | 31300 | +| total_timesteps | 43268096 | +| train/ | | +| approx_kl | 0.00866848 | +| clip_fraction | 0.295 | +| clip_range | 0.0642 | +| entropy_loss | -6.4 | +| explained_variance | 0.367 | +| learning_rate | 3.97e-05 | +| loss | -0.0293 | +| n_updates | 100324 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000251 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1382 | +| iterations | 21128 | +| time_elapsed | 31301 | +| total_timesteps | 43270144 | +| train/ | | +| approx_kl | 0.0063270964 | +| clip_fraction | 0.28 | +| clip_range | 0.0642 | +| entropy_loss | -6.41 | +| explained_variance | 0.424 | +| learning_rate | 3.97e-05 | +| loss | -0.0274 | +| n_updates | 100328 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000143 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1382 | +| iterations | 21129 | +| time_elapsed | 31303 | +| total_timesteps | 43272192 | +| train/ | | +| approx_kl | 0.009256971 | +| clip_fraction | 0.284 | +| clip_range | 0.0642 | +| entropy_loss | -6.29 | +| explained_variance | 0.439 | +| learning_rate | 3.97e-05 | +| loss | -0.0299 | +| n_updates | 100332 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000122 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1382 | +| iterations | 21130 | +| time_elapsed | 31305 | +| total_timesteps | 43274240 | +| train/ | | +| approx_kl | 0.009598248 | +| clip_fraction | 0.302 | +| clip_range | 0.0642 | +| entropy_loss | -6.15 | +| explained_variance | 0.504 | +| learning_rate | 3.97e-05 | +| loss | -0.0243 | +| n_updates | 100336 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000126 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1382 | +| iterations | 21131 | +| time_elapsed | 31306 | +| total_timesteps | 43276288 | +| train/ | | +| approx_kl | 0.012715494 | +| clip_fraction | 0.333 | +| clip_range | 0.0642 | +| entropy_loss | -5.62 | +| explained_variance | 0.379 | +| learning_rate | 3.97e-05 | +| loss | -0.0303 | +| n_updates | 100340 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000132 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1382 | +| iterations | 21132 | +| time_elapsed | 31308 | +| total_timesteps | 43278336 | +| train/ | | +| approx_kl | 0.013263565 | +| clip_fraction | 0.328 | +| clip_range | 0.0642 | +| entropy_loss | -4.9 | +| explained_variance | 0.843 | +| learning_rate | 3.97e-05 | +| loss | -0.029 | +| n_updates | 100344 | +| policy_gradient_loss | -0.0176 | +| value_loss | 5.86e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1382 | +| iterations | 21133 | +| time_elapsed | 31309 | +| total_timesteps | 43280384 | +| train/ | | +| approx_kl | 0.011544121 | +| clip_fraction | 0.29 | +| clip_range | 0.0642 | +| entropy_loss | -5.82 | +| explained_variance | 0.499 | +| learning_rate | 3.97e-05 | +| loss | -0.0277 | +| n_updates | 100348 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000115 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1382 | +| iterations | 21134 | +| time_elapsed | 31311 | +| total_timesteps | 43282432 | +| train/ | | +| approx_kl | 0.009254487 | +| clip_fraction | 0.325 | +| clip_range | 0.0642 | +| entropy_loss | -6.07 | +| explained_variance | 0.249 | +| learning_rate | 3.97e-05 | +| loss | -0.0204 | +| n_updates | 100352 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.0002 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1382 | +| iterations | 21135 | +| time_elapsed | 31312 | +| total_timesteps | 43284480 | +| train/ | | +| approx_kl | 0.01148909 | +| clip_fraction | 0.324 | +| clip_range | 0.0642 | +| entropy_loss | -6.06 | +| explained_variance | 0.114 | +| learning_rate | 3.97e-05 | +| loss | -0.0295 | +| n_updates | 100356 | +| policy_gradient_loss | -0.0173 | +| value_loss | 7.17e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1382 | +| iterations | 21136 | +| time_elapsed | 31314 | +| total_timesteps | 43286528 | +| train/ | | +| approx_kl | 0.011305872 | +| clip_fraction | 0.342 | +| clip_range | 0.0642 | +| entropy_loss | -6.24 | +| explained_variance | 0.373 | +| learning_rate | 3.97e-05 | +| loss | -0.0257 | +| n_updates | 100360 | +| policy_gradient_loss | -0.0167 | +| value_loss | 8.45e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1382 | +| iterations | 21137 | +| time_elapsed | 31315 | +| total_timesteps | 43288576 | +| train/ | | +| approx_kl | 0.008731005 | +| clip_fraction | 0.313 | +| clip_range | 0.0642 | +| entropy_loss | -6.67 | +| explained_variance | -0.101 | +| learning_rate | 3.97e-05 | +| loss | -0.0241 | +| n_updates | 100364 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000114 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1382 | +| iterations | 21138 | +| time_elapsed | 31317 | +| total_timesteps | 43290624 | +| train/ | | +| approx_kl | 0.0090670455 | +| clip_fraction | 0.284 | +| clip_range | 0.0642 | +| entropy_loss | -6.11 | +| explained_variance | 0.712 | +| learning_rate | 3.97e-05 | +| loss | -0.0216 | +| n_updates | 100368 | +| policy_gradient_loss | -0.0154 | +| value_loss | 8.72e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1382 | +| iterations | 21139 | +| time_elapsed | 31318 | +| total_timesteps | 43292672 | +| train/ | | +| approx_kl | 0.012392456 | +| clip_fraction | 0.312 | +| clip_range | 0.0642 | +| entropy_loss | -5.7 | +| explained_variance | 0.623 | +| learning_rate | 3.97e-05 | +| loss | -0.0218 | +| n_updates | 100372 | +| policy_gradient_loss | -0.0155 | +| value_loss | 9.63e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1382 | +| iterations | 21140 | +| time_elapsed | 31320 | +| total_timesteps | 43294720 | +| train/ | | +| approx_kl | 0.01064941 | +| clip_fraction | 0.285 | +| clip_range | 0.0642 | +| entropy_loss | -5.49 | +| explained_variance | 0.582 | +| learning_rate | 3.97e-05 | +| loss | -0.0254 | +| n_updates | 100376 | +| policy_gradient_loss | -0.0145 | +| value_loss | 0.000138 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1382 | +| iterations | 21141 | +| time_elapsed | 31321 | +| total_timesteps | 43296768 | +| train/ | | +| approx_kl | 0.011774945 | +| clip_fraction | 0.311 | +| clip_range | 0.0642 | +| entropy_loss | -6.15 | +| explained_variance | 0.0803 | +| learning_rate | 3.97e-05 | +| loss | -0.0271 | +| n_updates | 100380 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1382 | +| iterations | 21142 | +| time_elapsed | 31323 | +| total_timesteps | 43298816 | +| train/ | | +| approx_kl | 0.010866544 | +| clip_fraction | 0.275 | +| clip_range | 0.0642 | +| entropy_loss | -6.08 | +| explained_variance | 0.545 | +| learning_rate | 3.97e-05 | +| loss | -0.0191 | +| n_updates | 100384 | +| policy_gradient_loss | -0.0129 | +| value_loss | 0.000215 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1382 | +| iterations | 21143 | +| time_elapsed | 31324 | +| total_timesteps | 43300864 | +| train/ | | +| approx_kl | 0.010997435 | +| clip_fraction | 0.326 | +| clip_range | 0.0642 | +| entropy_loss | -5.05 | +| explained_variance | 0.715 | +| learning_rate | 3.97e-05 | +| loss | -0.0299 | +| n_updates | 100388 | +| policy_gradient_loss | -0.0181 | +| value_loss | 8.73e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1382 | +| iterations | 21144 | +| time_elapsed | 31326 | +| total_timesteps | 43302912 | +| train/ | | +| approx_kl | 0.011698317 | +| clip_fraction | 0.334 | +| clip_range | 0.0642 | +| entropy_loss | -5.24 | +| explained_variance | 0.361 | +| learning_rate | 3.97e-05 | +| loss | -0.0203 | +| n_updates | 100392 | +| policy_gradient_loss | -0.0124 | +| value_loss | 0.000342 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1382 | +| iterations | 21145 | +| time_elapsed | 31328 | +| total_timesteps | 43304960 | +| train/ | | +| approx_kl | 0.015567882 | +| clip_fraction | 0.365 | +| clip_range | 0.0642 | +| entropy_loss | -6.28 | +| explained_variance | -0.0195 | +| learning_rate | 3.97e-05 | +| loss | -0.0331 | +| n_updates | 100396 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000153 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1382 | +| iterations | 21146 | +| time_elapsed | 31329 | +| total_timesteps | 43307008 | +| train/ | | +| approx_kl | 0.012566933 | +| clip_fraction | 0.351 | +| clip_range | 0.0642 | +| entropy_loss | -6.19 | +| explained_variance | -0.255 | +| learning_rate | 3.97e-05 | +| loss | -0.0307 | +| n_updates | 100400 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000166 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1382 | +| iterations | 21147 | +| time_elapsed | 31331 | +| total_timesteps | 43309056 | +| train/ | | +| approx_kl | 0.011691654 | +| clip_fraction | 0.333 | +| clip_range | 0.0642 | +| entropy_loss | -6.33 | +| explained_variance | 0.222 | +| learning_rate | 3.97e-05 | +| loss | -0.023 | +| n_updates | 100404 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000193 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1382 | +| iterations | 21148 | +| time_elapsed | 31332 | +| total_timesteps | 43311104 | +| train/ | | +| approx_kl | 0.011694945 | +| clip_fraction | 0.36 | +| clip_range | 0.0642 | +| entropy_loss | -6.31 | +| explained_variance | 0.0122 | +| learning_rate | 3.97e-05 | +| loss | -0.0232 | +| n_updates | 100408 | +| policy_gradient_loss | -0.0175 | +| value_loss | 9.7e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1382 | +| iterations | 21149 | +| time_elapsed | 31334 | +| total_timesteps | 43313152 | +| train/ | | +| approx_kl | 0.011431137 | +| clip_fraction | 0.321 | +| clip_range | 0.0642 | +| entropy_loss | -6 | +| explained_variance | 0.309 | +| learning_rate | 3.97e-05 | +| loss | -0.0291 | +| n_updates | 100412 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.000362 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1382 | +| iterations | 21150 | +| time_elapsed | 31335 | +| total_timesteps | 43315200 | +| train/ | | +| approx_kl | 0.010184293 | +| clip_fraction | 0.331 | +| clip_range | 0.0642 | +| entropy_loss | -5.17 | +| explained_variance | 0.39 | +| learning_rate | 3.97e-05 | +| loss | -0.0269 | +| n_updates | 100416 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000312 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1382 | +| iterations | 21151 | +| time_elapsed | 31337 | +| total_timesteps | 43317248 | +| train/ | | +| approx_kl | 0.012582998 | +| clip_fraction | 0.351 | +| clip_range | 0.0642 | +| entropy_loss | -5.09 | +| explained_variance | 0.554 | +| learning_rate | 3.97e-05 | +| loss | -0.0293 | +| n_updates | 100420 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000117 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1382 | +| iterations | 21152 | +| time_elapsed | 31338 | +| total_timesteps | 43319296 | +| train/ | | +| approx_kl | 0.01256487 | +| clip_fraction | 0.331 | +| clip_range | 0.0642 | +| entropy_loss | -5.51 | +| explained_variance | 0.547 | +| learning_rate | 3.97e-05 | +| loss | -0.0291 | +| n_updates | 100424 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000155 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1382 | +| iterations | 21153 | +| time_elapsed | 31340 | +| total_timesteps | 43321344 | +| train/ | | +| approx_kl | 0.012690897 | +| clip_fraction | 0.344 | +| clip_range | 0.0642 | +| entropy_loss | -5.82 | +| explained_variance | 0.501 | +| learning_rate | 3.97e-05 | +| loss | -0.027 | +| n_updates | 100428 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000154 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1382 | +| iterations | 21154 | +| time_elapsed | 31341 | +| total_timesteps | 43323392 | +| train/ | | +| approx_kl | 0.01563607 | +| clip_fraction | 0.36 | +| clip_range | 0.0642 | +| entropy_loss | -6.05 | +| explained_variance | -0.184 | +| learning_rate | 3.97e-05 | +| loss | -0.0316 | +| n_updates | 100432 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000147 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1382 | +| iterations | 21155 | +| time_elapsed | 31343 | +| total_timesteps | 43325440 | +| train/ | | +| approx_kl | 0.010369756 | +| clip_fraction | 0.345 | +| clip_range | 0.0642 | +| entropy_loss | -6.3 | +| explained_variance | 0.045 | +| learning_rate | 3.97e-05 | +| loss | -0.0296 | +| n_updates | 100436 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000236 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1382 | +| iterations | 21156 | +| time_elapsed | 31344 | +| total_timesteps | 43327488 | +| train/ | | +| approx_kl | 0.010822188 | +| clip_fraction | 0.262 | +| clip_range | 0.0642 | +| entropy_loss | -5.89 | +| explained_variance | 0.352 | +| learning_rate | 3.97e-05 | +| loss | -0.0203 | +| n_updates | 100440 | +| policy_gradient_loss | -0.0128 | +| value_loss | 0.00035 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1382 | +| iterations | 21157 | +| time_elapsed | 31346 | +| total_timesteps | 43329536 | +| train/ | | +| approx_kl | 0.011518886 | +| clip_fraction | 0.325 | +| clip_range | 0.0642 | +| entropy_loss | -5.19 | +| explained_variance | 0.416 | +| learning_rate | 3.97e-05 | +| loss | -0.0225 | +| n_updates | 100444 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000332 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1382 | +| iterations | 21158 | +| time_elapsed | 31347 | +| total_timesteps | 43331584 | +| train/ | | +| approx_kl | 0.012156745 | +| clip_fraction | 0.368 | +| clip_range | 0.0642 | +| entropy_loss | -5.69 | +| explained_variance | 0.519 | +| learning_rate | 3.97e-05 | +| loss | -0.0301 | +| n_updates | 100448 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000126 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1382 | +| iterations | 21159 | +| time_elapsed | 31349 | +| total_timesteps | 43333632 | +| train/ | | +| approx_kl | 0.0105992835 | +| clip_fraction | 0.327 | +| clip_range | 0.0642 | +| entropy_loss | -6.04 | +| explained_variance | 0.249 | +| learning_rate | 3.97e-05 | +| loss | -0.0257 | +| n_updates | 100452 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000275 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1382 | +| iterations | 21160 | +| time_elapsed | 31351 | +| total_timesteps | 43335680 | +| train/ | | +| approx_kl | 0.012949944 | +| clip_fraction | 0.373 | +| clip_range | 0.0642 | +| entropy_loss | -5.88 | +| explained_variance | 0.584 | +| learning_rate | 3.97e-05 | +| loss | -0.036 | +| n_updates | 100456 | +| policy_gradient_loss | -0.022 | +| value_loss | 0.000103 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1382 | +| iterations | 21161 | +| time_elapsed | 31352 | +| total_timesteps | 43337728 | +| train/ | | +| approx_kl | 0.011092681 | +| clip_fraction | 0.339 | +| clip_range | 0.0642 | +| entropy_loss | -6.08 | +| explained_variance | 0.377 | +| learning_rate | 3.97e-05 | +| loss | -0.0285 | +| n_updates | 100460 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000162 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1382 | +| iterations | 21162 | +| time_elapsed | 31354 | +| total_timesteps | 43339776 | +| train/ | | +| approx_kl | 0.01301677 | +| clip_fraction | 0.297 | +| clip_range | 0.0642 | +| entropy_loss | -6.14 | +| explained_variance | 0.55 | +| learning_rate | 3.97e-05 | +| loss | -0.0262 | +| n_updates | 100464 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.000114 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1382 | +| iterations | 21163 | +| time_elapsed | 31355 | +| total_timesteps | 43341824 | +| train/ | | +| approx_kl | 0.01224935 | +| clip_fraction | 0.317 | +| clip_range | 0.0642 | +| entropy_loss | -6.25 | +| explained_variance | -0.051 | +| learning_rate | 3.97e-05 | +| loss | -0.0287 | +| n_updates | 100468 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000166 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.336 | +| time/ | | +| fps | 1382 | +| iterations | 21164 | +| time_elapsed | 31357 | +| total_timesteps | 43343872 | +| train/ | | +| approx_kl | 0.008590555 | +| clip_fraction | 0.295 | +| clip_range | 0.0642 | +| entropy_loss | -6.57 | +| explained_variance | 0.147 | +| learning_rate | 3.97e-05 | +| loss | -0.0223 | +| n_updates | 100472 | +| policy_gradient_loss | -0.0126 | +| value_loss | 0.000516 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1382 | +| iterations | 21165 | +| time_elapsed | 31358 | +| total_timesteps | 43345920 | +| train/ | | +| approx_kl | 0.011496079 | +| clip_fraction | 0.333 | +| clip_range | 0.0642 | +| entropy_loss | -5.74 | +| explained_variance | 0.496 | +| learning_rate | 3.97e-05 | +| loss | -0.0323 | +| n_updates | 100476 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.00013 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1382 | +| iterations | 21166 | +| time_elapsed | 31360 | +| total_timesteps | 43347968 | +| train/ | | +| approx_kl | 0.011545073 | +| clip_fraction | 0.342 | +| clip_range | 0.0642 | +| entropy_loss | -6 | +| explained_variance | 0.527 | +| learning_rate | 3.97e-05 | +| loss | -0.0288 | +| n_updates | 100480 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000122 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1382 | +| iterations | 21167 | +| time_elapsed | 31361 | +| total_timesteps | 43350016 | +| train/ | | +| approx_kl | 0.011180509 | +| clip_fraction | 0.333 | +| clip_range | 0.0642 | +| entropy_loss | -5.68 | +| explained_variance | 0.65 | +| learning_rate | 3.97e-05 | +| loss | -0.0287 | +| n_updates | 100484 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000115 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1382 | +| iterations | 21168 | +| time_elapsed | 31363 | +| total_timesteps | 43352064 | +| train/ | | +| approx_kl | 0.013871242 | +| clip_fraction | 0.358 | +| clip_range | 0.0642 | +| entropy_loss | -5.65 | +| explained_variance | -0.724 | +| learning_rate | 3.97e-05 | +| loss | -0.0322 | +| n_updates | 100488 | +| policy_gradient_loss | -0.0214 | +| value_loss | 5.5e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1382 | +| iterations | 21169 | +| time_elapsed | 31365 | +| total_timesteps | 43354112 | +| train/ | | +| approx_kl | 0.008690735 | +| clip_fraction | 0.294 | +| clip_range | 0.0642 | +| entropy_loss | -6.35 | +| explained_variance | 0.28 | +| learning_rate | 3.97e-05 | +| loss | -0.0215 | +| n_updates | 100492 | +| policy_gradient_loss | -0.0146 | +| value_loss | 0.000144 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1382 | +| iterations | 21170 | +| time_elapsed | 31366 | +| total_timesteps | 43356160 | +| train/ | | +| approx_kl | 0.009518838 | +| clip_fraction | 0.301 | +| clip_range | 0.0642 | +| entropy_loss | -5.63 | +| explained_variance | 0.435 | +| learning_rate | 3.97e-05 | +| loss | -0.027 | +| n_updates | 100496 | +| policy_gradient_loss | -0.0145 | +| value_loss | 0.000354 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1382 | +| iterations | 21171 | +| time_elapsed | 31368 | +| total_timesteps | 43358208 | +| train/ | | +| approx_kl | 0.010081682 | +| clip_fraction | 0.297 | +| clip_range | 0.0642 | +| entropy_loss | -5.91 | +| explained_variance | 0.407 | +| learning_rate | 3.97e-05 | +| loss | -0.0188 | +| n_updates | 100500 | +| policy_gradient_loss | -0.0126 | +| value_loss | 0.000303 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1382 | +| iterations | 21172 | +| time_elapsed | 31369 | +| total_timesteps | 43360256 | +| train/ | | +| approx_kl | 0.010101506 | +| clip_fraction | 0.295 | +| clip_range | 0.0642 | +| entropy_loss | -6.01 | +| explained_variance | 0.533 | +| learning_rate | 3.97e-05 | +| loss | -0.0259 | +| n_updates | 100504 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.00023 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1382 | +| iterations | 21173 | +| time_elapsed | 31371 | +| total_timesteps | 43362304 | +| train/ | | +| approx_kl | 0.013326852 | +| clip_fraction | 0.348 | +| clip_range | 0.0642 | +| entropy_loss | -5.83 | +| explained_variance | -0.248 | +| learning_rate | 3.97e-05 | +| loss | -0.0313 | +| n_updates | 100508 | +| policy_gradient_loss | -0.0204 | +| value_loss | 9.12e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1382 | +| iterations | 21174 | +| time_elapsed | 31372 | +| total_timesteps | 43364352 | +| train/ | | +| approx_kl | 0.013262989 | +| clip_fraction | 0.371 | +| clip_range | 0.0642 | +| entropy_loss | -6.38 | +| explained_variance | -0.281 | +| learning_rate | 3.97e-05 | +| loss | -0.034 | +| n_updates | 100512 | +| policy_gradient_loss | -0.0212 | +| value_loss | 7.93e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1382 | +| iterations | 21175 | +| time_elapsed | 31374 | +| total_timesteps | 43366400 | +| train/ | | +| approx_kl | 0.009168221 | +| clip_fraction | 0.317 | +| clip_range | 0.0642 | +| entropy_loss | -5.94 | +| explained_variance | 0.303 | +| learning_rate | 3.97e-05 | +| loss | -0.025 | +| n_updates | 100516 | +| policy_gradient_loss | -0.0144 | +| value_loss | 0.000344 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1382 | +| iterations | 21176 | +| time_elapsed | 31375 | +| total_timesteps | 43368448 | +| train/ | | +| approx_kl | 0.011855513 | +| clip_fraction | 0.315 | +| clip_range | 0.0642 | +| entropy_loss | -5.41 | +| explained_variance | 0.592 | +| learning_rate | 3.97e-05 | +| loss | -0.0227 | +| n_updates | 100520 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000157 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1382 | +| iterations | 21177 | +| time_elapsed | 31377 | +| total_timesteps | 43370496 | +| train/ | | +| approx_kl | 0.012657052 | +| clip_fraction | 0.317 | +| clip_range | 0.0642 | +| entropy_loss | -5.99 | +| explained_variance | 0.402 | +| learning_rate | 3.97e-05 | +| loss | -0.0302 | +| n_updates | 100524 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000108 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1382 | +| iterations | 21178 | +| time_elapsed | 31378 | +| total_timesteps | 43372544 | +| train/ | | +| approx_kl | 0.015862651 | +| clip_fraction | 0.324 | +| clip_range | 0.0642 | +| entropy_loss | -5.82 | +| explained_variance | 0.518 | +| learning_rate | 3.97e-05 | +| loss | -0.0258 | +| n_updates | 100528 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000119 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1382 | +| iterations | 21179 | +| time_elapsed | 31380 | +| total_timesteps | 43374592 | +| train/ | | +| approx_kl | 0.014507814 | +| clip_fraction | 0.323 | +| clip_range | 0.0642 | +| entropy_loss | -6.13 | +| explained_variance | -0.107 | +| learning_rate | 3.97e-05 | +| loss | -0.0246 | +| n_updates | 100532 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000105 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1382 | +| iterations | 21180 | +| time_elapsed | 31381 | +| total_timesteps | 43376640 | +| train/ | | +| approx_kl | 0.011617206 | +| clip_fraction | 0.308 | +| clip_range | 0.0642 | +| entropy_loss | -6.07 | +| explained_variance | 0.331 | +| learning_rate | 3.97e-05 | +| loss | -0.0269 | +| n_updates | 100536 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000128 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1382 | +| iterations | 21181 | +| time_elapsed | 31383 | +| total_timesteps | 43378688 | +| train/ | | +| approx_kl | 0.010867995 | +| clip_fraction | 0.316 | +| clip_range | 0.0642 | +| entropy_loss | -5.51 | +| explained_variance | 0.559 | +| learning_rate | 3.97e-05 | +| loss | -0.0204 | +| n_updates | 100540 | +| policy_gradient_loss | -0.0143 | +| value_loss | 0.000171 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1382 | +| iterations | 21182 | +| time_elapsed | 31384 | +| total_timesteps | 43380736 | +| train/ | | +| approx_kl | 0.011906251 | +| clip_fraction | 0.31 | +| clip_range | 0.0642 | +| entropy_loss | -5.84 | +| explained_variance | 0.577 | +| learning_rate | 3.97e-05 | +| loss | -0.0285 | +| n_updates | 100544 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000141 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1382 | +| iterations | 21183 | +| time_elapsed | 31386 | +| total_timesteps | 43382784 | +| train/ | | +| approx_kl | 0.012702379 | +| clip_fraction | 0.342 | +| clip_range | 0.0642 | +| entropy_loss | -6.21 | +| explained_variance | -0.273 | +| learning_rate | 3.97e-05 | +| loss | -0.0282 | +| n_updates | 100548 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000102 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1382 | +| iterations | 21184 | +| time_elapsed | 31388 | +| total_timesteps | 43384832 | +| train/ | | +| approx_kl | 0.01299783 | +| clip_fraction | 0.324 | +| clip_range | 0.0642 | +| entropy_loss | -5.95 | +| explained_variance | 0.38 | +| learning_rate | 3.97e-05 | +| loss | -0.026 | +| n_updates | 100552 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000206 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1382 | +| iterations | 21185 | +| time_elapsed | 31389 | +| total_timesteps | 43386880 | +| train/ | | +| approx_kl | 0.0128928255 | +| clip_fraction | 0.322 | +| clip_range | 0.0642 | +| entropy_loss | -5.92 | +| explained_variance | 0.523 | +| learning_rate | 3.97e-05 | +| loss | -0.0207 | +| n_updates | 100556 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000163 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1382 | +| iterations | 21186 | +| time_elapsed | 31391 | +| total_timesteps | 43388928 | +| train/ | | +| approx_kl | 0.014357839 | +| clip_fraction | 0.364 | +| clip_range | 0.0642 | +| entropy_loss | -5.38 | +| explained_variance | 0.719 | +| learning_rate | 3.97e-05 | +| loss | -0.0414 | +| n_updates | 100560 | +| policy_gradient_loss | -0.0231 | +| value_loss | 4.63e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1382 | +| iterations | 21187 | +| time_elapsed | 31392 | +| total_timesteps | 43390976 | +| train/ | | +| approx_kl | 0.013570127 | +| clip_fraction | 0.311 | +| clip_range | 0.0642 | +| entropy_loss | -6.03 | +| explained_variance | 0.225 | +| learning_rate | 3.97e-05 | +| loss | -0.0266 | +| n_updates | 100564 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000146 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1382 | +| iterations | 21188 | +| time_elapsed | 31394 | +| total_timesteps | 43393024 | +| train/ | | +| approx_kl | 0.010475996 | +| clip_fraction | 0.306 | +| clip_range | 0.0642 | +| entropy_loss | -5.89 | +| explained_variance | 0.294 | +| learning_rate | 3.97e-05 | +| loss | -0.024 | +| n_updates | 100568 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.00029 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1382 | +| iterations | 21189 | +| time_elapsed | 31395 | +| total_timesteps | 43395072 | +| train/ | | +| approx_kl | 0.01340738 | +| clip_fraction | 0.321 | +| clip_range | 0.0642 | +| entropy_loss | -5.7 | +| explained_variance | 0.449 | +| learning_rate | 3.97e-05 | +| loss | -0.0293 | +| n_updates | 100572 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000124 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1382 | +| iterations | 21190 | +| time_elapsed | 31397 | +| total_timesteps | 43397120 | +| train/ | | +| approx_kl | 0.012147663 | +| clip_fraction | 0.303 | +| clip_range | 0.0642 | +| entropy_loss | -6.07 | +| explained_variance | 0.491 | +| learning_rate | 3.97e-05 | +| loss | -0.027 | +| n_updates | 100576 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000155 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1382 | +| iterations | 21191 | +| time_elapsed | 31398 | +| total_timesteps | 43399168 | +| train/ | | +| approx_kl | 0.011660599 | +| clip_fraction | 0.326 | +| clip_range | 0.0642 | +| entropy_loss | -5.89 | +| explained_variance | 0.136 | +| learning_rate | 3.97e-05 | +| loss | -0.0246 | +| n_updates | 100580 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000238 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1382 | +| iterations | 21192 | +| time_elapsed | 31400 | +| total_timesteps | 43401216 | +| train/ | | +| approx_kl | 0.012300314 | +| clip_fraction | 0.36 | +| clip_range | 0.0642 | +| entropy_loss | -5.72 | +| explained_variance | 0.404 | +| learning_rate | 3.97e-05 | +| loss | -0.0329 | +| n_updates | 100584 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000118 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1382 | +| iterations | 21193 | +| time_elapsed | 31402 | +| total_timesteps | 43403264 | +| train/ | | +| approx_kl | 0.014221842 | +| clip_fraction | 0.338 | +| clip_range | 0.0641 | +| entropy_loss | -5.48 | +| explained_variance | 0.671 | +| learning_rate | 3.97e-05 | +| loss | -0.0245 | +| n_updates | 100588 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000112 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1382 | +| iterations | 21194 | +| time_elapsed | 31403 | +| total_timesteps | 43405312 | +| train/ | | +| approx_kl | 0.011932998 | +| clip_fraction | 0.31 | +| clip_range | 0.0641 | +| entropy_loss | -6.09 | +| explained_variance | -0.245 | +| learning_rate | 3.97e-05 | +| loss | -0.0303 | +| n_updates | 100592 | +| policy_gradient_loss | -0.0186 | +| value_loss | 8.5e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1382 | +| iterations | 21195 | +| time_elapsed | 31405 | +| total_timesteps | 43407360 | +| train/ | | +| approx_kl | 0.009869877 | +| clip_fraction | 0.291 | +| clip_range | 0.0641 | +| entropy_loss | -6.42 | +| explained_variance | 0.491 | +| learning_rate | 3.97e-05 | +| loss | -0.0281 | +| n_updates | 100596 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000145 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1382 | +| iterations | 21196 | +| time_elapsed | 31406 | +| total_timesteps | 43409408 | +| train/ | | +| approx_kl | 0.010007381 | +| clip_fraction | 0.295 | +| clip_range | 0.0641 | +| entropy_loss | -5.76 | +| explained_variance | 0.588 | +| learning_rate | 3.97e-05 | +| loss | -0.0307 | +| n_updates | 100600 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000193 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1382 | +| iterations | 21197 | +| time_elapsed | 31408 | +| total_timesteps | 43411456 | +| train/ | | +| approx_kl | 0.008645516 | +| clip_fraction | 0.295 | +| clip_range | 0.0641 | +| entropy_loss | -6.53 | +| explained_variance | -0.233 | +| learning_rate | 3.97e-05 | +| loss | -0.026 | +| n_updates | 100604 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000118 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1382 | +| iterations | 21198 | +| time_elapsed | 31409 | +| total_timesteps | 43413504 | +| train/ | | +| approx_kl | 0.009894325 | +| clip_fraction | 0.325 | +| clip_range | 0.0641 | +| entropy_loss | -6.32 | +| explained_variance | 0.0916 | +| learning_rate | 3.97e-05 | +| loss | -0.0267 | +| n_updates | 100608 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000141 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1382 | +| iterations | 21199 | +| time_elapsed | 31411 | +| total_timesteps | 43415552 | +| train/ | | +| approx_kl | 0.010692454 | +| clip_fraction | 0.294 | +| clip_range | 0.0641 | +| entropy_loss | -5.43 | +| explained_variance | 0.548 | +| learning_rate | 3.97e-05 | +| loss | -0.0256 | +| n_updates | 100612 | +| policy_gradient_loss | -0.0131 | +| value_loss | 0.000114 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1382 | +| iterations | 21200 | +| time_elapsed | 31413 | +| total_timesteps | 43417600 | +| train/ | | +| approx_kl | 0.012898983 | +| clip_fraction | 0.318 | +| clip_range | 0.0641 | +| entropy_loss | -5.66 | +| explained_variance | 0.564 | +| learning_rate | 3.97e-05 | +| loss | -0.0274 | +| n_updates | 100616 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000117 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1382 | +| iterations | 21201 | +| time_elapsed | 31414 | +| total_timesteps | 43419648 | +| train/ | | +| approx_kl | 0.01591874 | +| clip_fraction | 0.295 | +| clip_range | 0.0641 | +| entropy_loss | -5.83 | +| explained_variance | -0.147 | +| learning_rate | 3.97e-05 | +| loss | -0.0297 | +| n_updates | 100620 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000118 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1382 | +| iterations | 21202 | +| time_elapsed | 31416 | +| total_timesteps | 43421696 | +| train/ | | +| approx_kl | 0.011524029 | +| clip_fraction | 0.311 | +| clip_range | 0.0641 | +| entropy_loss | -5.98 | +| explained_variance | 0.387 | +| learning_rate | 3.97e-05 | +| loss | -0.0262 | +| n_updates | 100624 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000111 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1382 | +| iterations | 21203 | +| time_elapsed | 31417 | +| total_timesteps | 43423744 | +| train/ | | +| approx_kl | 0.011230104 | +| clip_fraction | 0.315 | +| clip_range | 0.0641 | +| entropy_loss | -5.45 | +| explained_variance | 0.44 | +| learning_rate | 3.97e-05 | +| loss | -0.0212 | +| n_updates | 100628 | +| policy_gradient_loss | -0.0148 | +| value_loss | 0.000253 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1382 | +| iterations | 21204 | +| time_elapsed | 31419 | +| total_timesteps | 43425792 | +| train/ | | +| approx_kl | 0.012644513 | +| clip_fraction | 0.322 | +| clip_range | 0.0641 | +| entropy_loss | -5.14 | +| explained_variance | 0.565 | +| learning_rate | 3.97e-05 | +| loss | -0.0274 | +| n_updates | 100632 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000162 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1382 | +| iterations | 21205 | +| time_elapsed | 31420 | +| total_timesteps | 43427840 | +| train/ | | +| approx_kl | 0.012906624 | +| clip_fraction | 0.324 | +| clip_range | 0.0641 | +| entropy_loss | -5.77 | +| explained_variance | 0.138 | +| learning_rate | 3.97e-05 | +| loss | -0.0238 | +| n_updates | 100636 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000137 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1382 | +| iterations | 21206 | +| time_elapsed | 31422 | +| total_timesteps | 43429888 | +| train/ | | +| approx_kl | 0.012464227 | +| clip_fraction | 0.293 | +| clip_range | 0.0641 | +| entropy_loss | -6.1 | +| explained_variance | 0.357 | +| learning_rate | 3.97e-05 | +| loss | -0.0269 | +| n_updates | 100640 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000183 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1382 | +| iterations | 21207 | +| time_elapsed | 31423 | +| total_timesteps | 43431936 | +| train/ | | +| approx_kl | 0.014020558 | +| clip_fraction | 0.355 | +| clip_range | 0.0641 | +| entropy_loss | -5.61 | +| explained_variance | 0.627 | +| learning_rate | 3.97e-05 | +| loss | -0.0302 | +| n_updates | 100644 | +| policy_gradient_loss | -0.0194 | +| value_loss | 8.32e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1382 | +| iterations | 21208 | +| time_elapsed | 31425 | +| total_timesteps | 43433984 | +| train/ | | +| approx_kl | 0.013957836 | +| clip_fraction | 0.317 | +| clip_range | 0.0641 | +| entropy_loss | -6.13 | +| explained_variance | 0.305 | +| learning_rate | 3.97e-05 | +| loss | -0.0317 | +| n_updates | 100648 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000182 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1382 | +| iterations | 21209 | +| time_elapsed | 31426 | +| total_timesteps | 43436032 | +| train/ | | +| approx_kl | 0.013634745 | +| clip_fraction | 0.322 | +| clip_range | 0.0641 | +| entropy_loss | -6.28 | +| explained_variance | -0.0606 | +| learning_rate | 3.97e-05 | +| loss | -0.0242 | +| n_updates | 100652 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000178 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1382 | +| iterations | 21210 | +| time_elapsed | 31428 | +| total_timesteps | 43438080 | +| train/ | | +| approx_kl | 0.0105834585 | +| clip_fraction | 0.295 | +| clip_range | 0.0641 | +| entropy_loss | -5.59 | +| explained_variance | 0.366 | +| learning_rate | 3.97e-05 | +| loss | -0.0183 | +| n_updates | 100656 | +| policy_gradient_loss | -0.0135 | +| value_loss | 0.000403 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1382 | +| iterations | 21211 | +| time_elapsed | 31429 | +| total_timesteps | 43440128 | +| train/ | | +| approx_kl | 0.013444319 | +| clip_fraction | 0.304 | +| clip_range | 0.0641 | +| entropy_loss | -5.25 | +| explained_variance | 0.458 | +| learning_rate | 3.97e-05 | +| loss | -0.0235 | +| n_updates | 100660 | +| policy_gradient_loss | -0.0141 | +| value_loss | 0.000293 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1382 | +| iterations | 21212 | +| time_elapsed | 31431 | +| total_timesteps | 43442176 | +| train/ | | +| approx_kl | 0.0137092415 | +| clip_fraction | 0.344 | +| clip_range | 0.0641 | +| entropy_loss | -5.6 | +| explained_variance | 0.146 | +| learning_rate | 3.97e-05 | +| loss | -0.0313 | +| n_updates | 100664 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000177 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1382 | +| iterations | 21213 | +| time_elapsed | 31432 | +| total_timesteps | 43444224 | +| train/ | | +| approx_kl | 0.012229437 | +| clip_fraction | 0.367 | +| clip_range | 0.0641 | +| entropy_loss | -6.05 | +| explained_variance | 0.387 | +| learning_rate | 3.97e-05 | +| loss | -0.0301 | +| n_updates | 100668 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000108 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1382 | +| iterations | 21214 | +| time_elapsed | 31434 | +| total_timesteps | 43446272 | +| train/ | | +| approx_kl | 0.010582211 | +| clip_fraction | 0.341 | +| clip_range | 0.0641 | +| entropy_loss | -6.32 | +| explained_variance | 0.38 | +| learning_rate | 3.97e-05 | +| loss | -0.0283 | +| n_updates | 100672 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.0001 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1382 | +| iterations | 21215 | +| time_elapsed | 31436 | +| total_timesteps | 43448320 | +| train/ | | +| approx_kl | 0.01163776 | +| clip_fraction | 0.323 | +| clip_range | 0.0641 | +| entropy_loss | -6.1 | +| explained_variance | -0.183 | +| learning_rate | 3.97e-05 | +| loss | -0.0275 | +| n_updates | 100676 | +| policy_gradient_loss | -0.0176 | +| value_loss | 7.82e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1382 | +| iterations | 21216 | +| time_elapsed | 31437 | +| total_timesteps | 43450368 | +| train/ | | +| approx_kl | 0.010937551 | +| clip_fraction | 0.328 | +| clip_range | 0.0641 | +| entropy_loss | -6.28 | +| explained_variance | 0.0097 | +| learning_rate | 3.97e-05 | +| loss | -0.03 | +| n_updates | 100680 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000179 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1382 | +| iterations | 21217 | +| time_elapsed | 31439 | +| total_timesteps | 43452416 | +| train/ | | +| approx_kl | 0.014519618 | +| clip_fraction | 0.317 | +| clip_range | 0.0641 | +| entropy_loss | -6.21 | +| explained_variance | 0.309 | +| learning_rate | 3.97e-05 | +| loss | -0.0269 | +| n_updates | 100684 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000141 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1382 | +| iterations | 21218 | +| time_elapsed | 31440 | +| total_timesteps | 43454464 | +| train/ | | +| approx_kl | 0.010112904 | +| clip_fraction | 0.306 | +| clip_range | 0.0641 | +| entropy_loss | -5.4 | +| explained_variance | 0.496 | +| learning_rate | 3.97e-05 | +| loss | -0.0244 | +| n_updates | 100688 | +| policy_gradient_loss | -0.0133 | +| value_loss | 0.000276 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1382 | +| iterations | 21219 | +| time_elapsed | 31442 | +| total_timesteps | 43456512 | +| train/ | | +| approx_kl | 0.013008593 | +| clip_fraction | 0.327 | +| clip_range | 0.0641 | +| entropy_loss | -4.92 | +| explained_variance | 0.71 | +| learning_rate | 3.97e-05 | +| loss | -0.0218 | +| n_updates | 100692 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000129 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1382 | +| iterations | 21220 | +| time_elapsed | 31443 | +| total_timesteps | 43458560 | +| train/ | | +| approx_kl | 0.01290795 | +| clip_fraction | 0.337 | +| clip_range | 0.0641 | +| entropy_loss | -5.1 | +| explained_variance | 0.561 | +| learning_rate | 3.97e-05 | +| loss | -0.0295 | +| n_updates | 100696 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000138 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1382 | +| iterations | 21221 | +| time_elapsed | 31445 | +| total_timesteps | 43460608 | +| train/ | | +| approx_kl | 0.011812869 | +| clip_fraction | 0.357 | +| clip_range | 0.0641 | +| entropy_loss | -5.45 | +| explained_variance | 0.449 | +| learning_rate | 3.97e-05 | +| loss | -0.0304 | +| n_updates | 100700 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.00011 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1382 | +| iterations | 21222 | +| time_elapsed | 31446 | +| total_timesteps | 43462656 | +| train/ | | +| approx_kl | 0.015015065 | +| clip_fraction | 0.331 | +| clip_range | 0.0641 | +| entropy_loss | -5.32 | +| explained_variance | 0.308 | +| learning_rate | 3.97e-05 | +| loss | -0.0173 | +| n_updates | 100704 | +| policy_gradient_loss | -0.0134 | +| value_loss | 0.000367 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1382 | +| iterations | 21223 | +| time_elapsed | 31448 | +| total_timesteps | 43464704 | +| train/ | | +| approx_kl | 0.013208799 | +| clip_fraction | 0.357 | +| clip_range | 0.0641 | +| entropy_loss | -5.7 | +| explained_variance | 0.324 | +| learning_rate | 3.97e-05 | +| loss | -0.0289 | +| n_updates | 100708 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000119 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1382 | +| iterations | 21224 | +| time_elapsed | 31449 | +| total_timesteps | 43466752 | +| train/ | | +| approx_kl | 0.01323272 | +| clip_fraction | 0.323 | +| clip_range | 0.0641 | +| entropy_loss | -6.29 | +| explained_variance | 0.297 | +| learning_rate | 3.97e-05 | +| loss | -0.0284 | +| n_updates | 100712 | +| policy_gradient_loss | -0.0177 | +| value_loss | 9.56e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1382 | +| iterations | 21225 | +| time_elapsed | 31451 | +| total_timesteps | 43468800 | +| train/ | | +| approx_kl | 0.013277515 | +| clip_fraction | 0.359 | +| clip_range | 0.0641 | +| entropy_loss | -5.98 | +| explained_variance | 0.18 | +| learning_rate | 3.97e-05 | +| loss | -0.0291 | +| n_updates | 100716 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000373 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1382 | +| iterations | 21226 | +| time_elapsed | 31452 | +| total_timesteps | 43470848 | +| train/ | | +| approx_kl | 0.012790447 | +| clip_fraction | 0.309 | +| clip_range | 0.0641 | +| entropy_loss | -6.17 | +| explained_variance | 0.154 | +| learning_rate | 3.97e-05 | +| loss | -0.028 | +| n_updates | 100720 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000235 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1382 | +| iterations | 21227 | +| time_elapsed | 31454 | +| total_timesteps | 43472896 | +| train/ | | +| approx_kl | 0.012220349 | +| clip_fraction | 0.361 | +| clip_range | 0.0641 | +| entropy_loss | -6.35 | +| explained_variance | 0.0404 | +| learning_rate | 3.97e-05 | +| loss | -0.0314 | +| n_updates | 100724 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000119 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1382 | +| iterations | 21228 | +| time_elapsed | 31455 | +| total_timesteps | 43474944 | +| train/ | | +| approx_kl | 0.013975125 | +| clip_fraction | 0.344 | +| clip_range | 0.0641 | +| entropy_loss | -5.07 | +| explained_variance | 0.531 | +| learning_rate | 3.97e-05 | +| loss | -0.0235 | +| n_updates | 100728 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.00024 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1382 | +| iterations | 21229 | +| time_elapsed | 31457 | +| total_timesteps | 43476992 | +| train/ | | +| approx_kl | 0.014581593 | +| clip_fraction | 0.343 | +| clip_range | 0.0641 | +| entropy_loss | -5.35 | +| explained_variance | 0.452 | +| learning_rate | 3.97e-05 | +| loss | -0.0271 | +| n_updates | 100732 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000151 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1382 | +| iterations | 21230 | +| time_elapsed | 31458 | +| total_timesteps | 43479040 | +| train/ | | +| approx_kl | 0.015310705 | +| clip_fraction | 0.364 | +| clip_range | 0.0641 | +| entropy_loss | -6.31 | +| explained_variance | -0.518 | +| learning_rate | 3.97e-05 | +| loss | -0.0316 | +| n_updates | 100736 | +| policy_gradient_loss | -0.0204 | +| value_loss | 7.04e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1382 | +| iterations | 21231 | +| time_elapsed | 31460 | +| total_timesteps | 43481088 | +| train/ | | +| approx_kl | 0.0133817345 | +| clip_fraction | 0.367 | +| clip_range | 0.0641 | +| entropy_loss | -5.89 | +| explained_variance | -0.0177 | +| learning_rate | 3.97e-05 | +| loss | -0.0278 | +| n_updates | 100740 | +| policy_gradient_loss | -0.017 | +| value_loss | 9.94e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1382 | +| iterations | 21232 | +| time_elapsed | 31462 | +| total_timesteps | 43483136 | +| train/ | | +| approx_kl | 0.011161197 | +| clip_fraction | 0.329 | +| clip_range | 0.0641 | +| entropy_loss | -6.1 | +| explained_variance | 0.501 | +| learning_rate | 3.97e-05 | +| loss | -0.0202 | +| n_updates | 100744 | +| policy_gradient_loss | -0.0147 | +| value_loss | 0.000143 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1382 | +| iterations | 21233 | +| time_elapsed | 31463 | +| total_timesteps | 43485184 | +| train/ | | +| approx_kl | 0.012626558 | +| clip_fraction | 0.325 | +| clip_range | 0.0641 | +| entropy_loss | -5.91 | +| explained_variance | 0.347 | +| learning_rate | 3.97e-05 | +| loss | -0.0291 | +| n_updates | 100748 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000147 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1382 | +| iterations | 21234 | +| time_elapsed | 31465 | +| total_timesteps | 43487232 | +| train/ | | +| approx_kl | 0.011812134 | +| clip_fraction | 0.344 | +| clip_range | 0.0641 | +| entropy_loss | -6.53 | +| explained_variance | -0.0957 | +| learning_rate | 3.97e-05 | +| loss | -0.0325 | +| n_updates | 100752 | +| policy_gradient_loss | -0.0191 | +| value_loss | 7.35e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1382 | +| iterations | 21235 | +| time_elapsed | 31466 | +| total_timesteps | 43489280 | +| train/ | | +| approx_kl | 0.010876107 | +| clip_fraction | 0.3 | +| clip_range | 0.0641 | +| entropy_loss | -6.01 | +| explained_variance | 0.46 | +| learning_rate | 3.97e-05 | +| loss | -0.0254 | +| n_updates | 100756 | +| policy_gradient_loss | -0.0142 | +| value_loss | 0.000262 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1382 | +| iterations | 21236 | +| time_elapsed | 31468 | +| total_timesteps | 43491328 | +| train/ | | +| approx_kl | 0.0113608185 | +| clip_fraction | 0.328 | +| clip_range | 0.0641 | +| entropy_loss | -5.49 | +| explained_variance | 0.415 | +| learning_rate | 3.97e-05 | +| loss | -0.0279 | +| n_updates | 100760 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000197 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1382 | +| iterations | 21237 | +| time_elapsed | 31469 | +| total_timesteps | 43493376 | +| train/ | | +| approx_kl | 0.012984083 | +| clip_fraction | 0.333 | +| clip_range | 0.0641 | +| entropy_loss | -5.27 | +| explained_variance | 0.692 | +| learning_rate | 3.97e-05 | +| loss | -0.0276 | +| n_updates | 100764 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000106 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1382 | +| iterations | 21238 | +| time_elapsed | 31471 | +| total_timesteps | 43495424 | +| train/ | | +| approx_kl | 0.012554928 | +| clip_fraction | 0.354 | +| clip_range | 0.0641 | +| entropy_loss | -5.17 | +| explained_variance | 0.553 | +| learning_rate | 3.97e-05 | +| loss | -0.0269 | +| n_updates | 100768 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000119 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1382 | +| iterations | 21239 | +| time_elapsed | 31472 | +| total_timesteps | 43497472 | +| train/ | | +| approx_kl | 0.013809734 | +| clip_fraction | 0.32 | +| clip_range | 0.0641 | +| entropy_loss | -5.4 | +| explained_variance | 0.462 | +| learning_rate | 3.97e-05 | +| loss | -0.0283 | +| n_updates | 100772 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000266 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1382 | +| iterations | 21240 | +| time_elapsed | 31474 | +| total_timesteps | 43499520 | +| train/ | | +| approx_kl | 0.014569025 | +| clip_fraction | 0.349 | +| clip_range | 0.0641 | +| entropy_loss | -5.15 | +| explained_variance | 0.444 | +| learning_rate | 3.97e-05 | +| loss | -0.031 | +| n_updates | 100776 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.00014 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1382 | +| iterations | 21241 | +| time_elapsed | 31475 | +| total_timesteps | 43501568 | +| train/ | | +| approx_kl | 0.011851256 | +| clip_fraction | 0.356 | +| clip_range | 0.0641 | +| entropy_loss | -5.71 | +| explained_variance | 0.451 | +| learning_rate | 3.97e-05 | +| loss | -0.0305 | +| n_updates | 100780 | +| policy_gradient_loss | -0.0192 | +| value_loss | 9.69e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1382 | +| iterations | 21242 | +| time_elapsed | 31477 | +| total_timesteps | 43503616 | +| train/ | | +| approx_kl | 0.010561153 | +| clip_fraction | 0.307 | +| clip_range | 0.0641 | +| entropy_loss | -5.57 | +| explained_variance | 0.567 | +| learning_rate | 3.97e-05 | +| loss | -0.0284 | +| n_updates | 100784 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000139 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1382 | +| iterations | 21243 | +| time_elapsed | 31478 | +| total_timesteps | 43505664 | +| train/ | | +| approx_kl | 0.013696343 | +| clip_fraction | 0.322 | +| clip_range | 0.0641 | +| entropy_loss | -6.18 | +| explained_variance | -0.136 | +| learning_rate | 3.97e-05 | +| loss | -0.0309 | +| n_updates | 100788 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000102 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1382 | +| iterations | 21244 | +| time_elapsed | 31480 | +| total_timesteps | 43507712 | +| train/ | | +| approx_kl | 0.010090509 | +| clip_fraction | 0.314 | +| clip_range | 0.0641 | +| entropy_loss | -6.43 | +| explained_variance | 0.235 | +| learning_rate | 3.97e-05 | +| loss | -0.0267 | +| n_updates | 100792 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000158 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1382 | +| iterations | 21245 | +| time_elapsed | 31482 | +| total_timesteps | 43509760 | +| train/ | | +| approx_kl | 0.011596486 | +| clip_fraction | 0.319 | +| clip_range | 0.0641 | +| entropy_loss | -6.59 | +| explained_variance | 0.326 | +| learning_rate | 3.97e-05 | +| loss | -0.0243 | +| n_updates | 100796 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000129 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1382 | +| iterations | 21246 | +| time_elapsed | 31483 | +| total_timesteps | 43511808 | +| train/ | | +| approx_kl | 0.011194015 | +| clip_fraction | 0.297 | +| clip_range | 0.0641 | +| entropy_loss | -5.66 | +| explained_variance | 0.41 | +| learning_rate | 3.97e-05 | +| loss | -0.0224 | +| n_updates | 100800 | +| policy_gradient_loss | -0.0127 | +| value_loss | 0.000277 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.364 | +| time/ | | +| fps | 1382 | +| iterations | 21247 | +| time_elapsed | 31485 | +| total_timesteps | 43513856 | +| train/ | | +| approx_kl | 0.0135522345 | +| clip_fraction | 0.332 | +| clip_range | 0.0641 | +| entropy_loss | -5.39 | +| explained_variance | 0.25 | +| learning_rate | 3.97e-05 | +| loss | -0.0264 | +| n_updates | 100804 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000387 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1382 | +| iterations | 21248 | +| time_elapsed | 31486 | +| total_timesteps | 43515904 | +| train/ | | +| approx_kl | 0.013890139 | +| clip_fraction | 0.354 | +| clip_range | 0.0641 | +| entropy_loss | -5.83 | +| explained_variance | 0.367 | +| learning_rate | 3.97e-05 | +| loss | -0.0328 | +| n_updates | 100808 | +| policy_gradient_loss | -0.0212 | +| value_loss | 9.44e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.366 | +| time/ | | +| fps | 1382 | +| iterations | 21249 | +| time_elapsed | 31488 | +| total_timesteps | 43517952 | +| train/ | | +| approx_kl | 0.012051078 | +| clip_fraction | 0.355 | +| clip_range | 0.0641 | +| entropy_loss | -5.81 | +| explained_variance | 0.599 | +| learning_rate | 3.97e-05 | +| loss | -0.0365 | +| n_updates | 100812 | +| policy_gradient_loss | -0.0212 | +| value_loss | 8.23e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.365 | +| time/ | | +| fps | 1382 | +| iterations | 21250 | +| time_elapsed | 31489 | +| total_timesteps | 43520000 | +| train/ | | +| approx_kl | 0.010708101 | +| clip_fraction | 0.328 | +| clip_range | 0.0641 | +| entropy_loss | -6.48 | +| explained_variance | -0.137 | +| learning_rate | 3.97e-05 | +| loss | -0.0273 | +| n_updates | 100816 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000108 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1382 | +| iterations | 21251 | +| time_elapsed | 31491 | +| total_timesteps | 43522048 | +| train/ | | +| approx_kl | 0.012579464 | +| clip_fraction | 0.343 | +| clip_range | 0.0641 | +| entropy_loss | -6.01 | +| explained_variance | 0.434 | +| learning_rate | 3.97e-05 | +| loss | -0.0273 | +| n_updates | 100820 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000106 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.363 | +| time/ | | +| fps | 1382 | +| iterations | 21252 | +| time_elapsed | 31492 | +| total_timesteps | 43524096 | +| train/ | | +| approx_kl | 0.012479495 | +| clip_fraction | 0.319 | +| clip_range | 0.0641 | +| entropy_loss | -5.78 | +| explained_variance | 0.697 | +| learning_rate | 3.97e-05 | +| loss | -0.0265 | +| n_updates | 100824 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000117 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1382 | +| iterations | 21253 | +| time_elapsed | 31494 | +| total_timesteps | 43526144 | +| train/ | | +| approx_kl | 0.012129936 | +| clip_fraction | 0.317 | +| clip_range | 0.0641 | +| entropy_loss | -5.6 | +| explained_variance | 0.296 | +| learning_rate | 3.97e-05 | +| loss | -0.0242 | +| n_updates | 100828 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000161 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1382 | +| iterations | 21254 | +| time_elapsed | 31495 | +| total_timesteps | 43528192 | +| train/ | | +| approx_kl | 0.012004793 | +| clip_fraction | 0.346 | +| clip_range | 0.0641 | +| entropy_loss | -5.79 | +| explained_variance | 0.582 | +| learning_rate | 3.97e-05 | +| loss | -0.0268 | +| n_updates | 100832 | +| policy_gradient_loss | -0.018 | +| value_loss | 7.26e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1382 | +| iterations | 21255 | +| time_elapsed | 31497 | +| total_timesteps | 43530240 | +| train/ | | +| approx_kl | 0.012504833 | +| clip_fraction | 0.327 | +| clip_range | 0.0641 | +| entropy_loss | -5.9 | +| explained_variance | 0.13 | +| learning_rate | 3.97e-05 | +| loss | -0.0226 | +| n_updates | 100836 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.00016 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1382 | +| iterations | 21256 | +| time_elapsed | 31498 | +| total_timesteps | 43532288 | +| train/ | | +| approx_kl | 0.012406226 | +| clip_fraction | 0.305 | +| clip_range | 0.0641 | +| entropy_loss | -5.98 | +| explained_variance | 0.486 | +| learning_rate | 3.97e-05 | +| loss | -0.0286 | +| n_updates | 100840 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.00014 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1382 | +| iterations | 21257 | +| time_elapsed | 31500 | +| total_timesteps | 43534336 | +| train/ | | +| approx_kl | 0.010955732 | +| clip_fraction | 0.319 | +| clip_range | 0.0641 | +| entropy_loss | -6.15 | +| explained_variance | 0.553 | +| learning_rate | 3.97e-05 | +| loss | -0.0264 | +| n_updates | 100844 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000131 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1382 | +| iterations | 21258 | +| time_elapsed | 31501 | +| total_timesteps | 43536384 | +| train/ | | +| approx_kl | 0.010602369 | +| clip_fraction | 0.328 | +| clip_range | 0.0641 | +| entropy_loss | -6.16 | +| explained_variance | 0.301 | +| learning_rate | 3.97e-05 | +| loss | -0.0306 | +| n_updates | 100848 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000154 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1382 | +| iterations | 21259 | +| time_elapsed | 31503 | +| total_timesteps | 43538432 | +| train/ | | +| approx_kl | 0.013298488 | +| clip_fraction | 0.352 | +| clip_range | 0.0641 | +| entropy_loss | -6 | +| explained_variance | -0.266 | +| learning_rate | 3.97e-05 | +| loss | -0.0305 | +| n_updates | 100852 | +| policy_gradient_loss | -0.0189 | +| value_loss | 6.73e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.36 | +| time/ | | +| fps | 1382 | +| iterations | 21260 | +| time_elapsed | 31504 | +| total_timesteps | 43540480 | +| train/ | | +| approx_kl | 0.011554271 | +| clip_fraction | 0.308 | +| clip_range | 0.0641 | +| entropy_loss | -5.69 | +| explained_variance | 0.633 | +| learning_rate | 3.97e-05 | +| loss | -0.0294 | +| n_updates | 100856 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000116 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.358 | +| time/ | | +| fps | 1382 | +| iterations | 21261 | +| time_elapsed | 31506 | +| total_timesteps | 43542528 | +| train/ | | +| approx_kl | 0.012131284 | +| clip_fraction | 0.314 | +| clip_range | 0.0641 | +| entropy_loss | -5.52 | +| explained_variance | 0.358 | +| learning_rate | 3.97e-05 | +| loss | -0.0196 | +| n_updates | 100860 | +| policy_gradient_loss | -0.0145 | +| value_loss | 0.000153 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.359 | +| time/ | | +| fps | 1382 | +| iterations | 21262 | +| time_elapsed | 31508 | +| total_timesteps | 43544576 | +| train/ | | +| approx_kl | 0.013597633 | +| clip_fraction | 0.319 | +| clip_range | 0.0641 | +| entropy_loss | -5.83 | +| explained_variance | 0.168 | +| learning_rate | 3.97e-05 | +| loss | -0.0258 | +| n_updates | 100864 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000256 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.361 | +| time/ | | +| fps | 1382 | +| iterations | 21263 | +| time_elapsed | 31509 | +| total_timesteps | 43546624 | +| train/ | | +| approx_kl | 0.0133950515 | +| clip_fraction | 0.264 | +| clip_range | 0.0641 | +| entropy_loss | -5.72 | +| explained_variance | 0.572 | +| learning_rate | 3.97e-05 | +| loss | -0.0242 | +| n_updates | 100868 | +| policy_gradient_loss | -0.0141 | +| value_loss | 0.000273 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1382 | +| iterations | 21264 | +| time_elapsed | 31511 | +| total_timesteps | 43548672 | +| train/ | | +| approx_kl | 0.011783711 | +| clip_fraction | 0.335 | +| clip_range | 0.0641 | +| entropy_loss | -5.16 | +| explained_variance | 0.64 | +| learning_rate | 3.97e-05 | +| loss | -0.0295 | +| n_updates | 100872 | +| policy_gradient_loss | -0.0196 | +| value_loss | 9.77e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1382 | +| iterations | 21265 | +| time_elapsed | 31512 | +| total_timesteps | 43550720 | +| train/ | | +| approx_kl | 0.014522259 | +| clip_fraction | 0.323 | +| clip_range | 0.0641 | +| entropy_loss | -5.53 | +| explained_variance | 0.666 | +| learning_rate | 3.97e-05 | +| loss | -0.0285 | +| n_updates | 100876 | +| policy_gradient_loss | -0.0177 | +| value_loss | 7.36e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1382 | +| iterations | 21266 | +| time_elapsed | 31514 | +| total_timesteps | 43552768 | +| train/ | | +| approx_kl | 0.011909416 | +| clip_fraction | 0.307 | +| clip_range | 0.0641 | +| entropy_loss | -5.85 | +| explained_variance | 0.303 | +| learning_rate | 3.97e-05 | +| loss | -0.0319 | +| n_updates | 100880 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000163 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1382 | +| iterations | 21267 | +| time_elapsed | 31515 | +| total_timesteps | 43554816 | +| train/ | | +| approx_kl | 0.011461403 | +| clip_fraction | 0.331 | +| clip_range | 0.0641 | +| entropy_loss | -6.45 | +| explained_variance | -0.0449 | +| learning_rate | 3.97e-05 | +| loss | -0.0282 | +| n_updates | 100884 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000136 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1381 | +| iterations | 21268 | +| time_elapsed | 31517 | +| total_timesteps | 43556864 | +| train/ | | +| approx_kl | 0.01256804 | +| clip_fraction | 0.312 | +| clip_range | 0.0641 | +| entropy_loss | -6.2 | +| explained_variance | 0.444 | +| learning_rate | 3.97e-05 | +| loss | -0.0308 | +| n_updates | 100888 | +| policy_gradient_loss | -0.0166 | +| value_loss | 8.73e-05 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1381 | +| iterations | 21269 | +| time_elapsed | 31518 | +| total_timesteps | 43558912 | +| train/ | | +| approx_kl | 0.01258889 | +| clip_fraction | 0.316 | +| clip_range | 0.0641 | +| entropy_loss | -4.92 | +| explained_variance | 0.76 | +| learning_rate | 3.97e-05 | +| loss | -0.0238 | +| n_updates | 100892 | +| policy_gradient_loss | -0.0166 | +| value_loss | 9.7e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1381 | +| iterations | 21270 | +| time_elapsed | 31520 | +| total_timesteps | 43560960 | +| train/ | | +| approx_kl | 0.011256486 | +| clip_fraction | 0.307 | +| clip_range | 0.0641 | +| entropy_loss | -5.52 | +| explained_variance | 0.364 | +| learning_rate | 3.97e-05 | +| loss | -0.0212 | +| n_updates | 100896 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000147 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1381 | +| iterations | 21271 | +| time_elapsed | 31521 | +| total_timesteps | 43563008 | +| train/ | | +| approx_kl | 0.01114305 | +| clip_fraction | 0.335 | +| clip_range | 0.0641 | +| entropy_loss | -5.68 | +| explained_variance | 0.423 | +| learning_rate | 3.97e-05 | +| loss | -0.0274 | +| n_updates | 100900 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000166 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1381 | +| iterations | 21272 | +| time_elapsed | 31523 | +| total_timesteps | 43565056 | +| train/ | | +| approx_kl | 0.008236334 | +| clip_fraction | 0.3 | +| clip_range | 0.0641 | +| entropy_loss | -6.19 | +| explained_variance | 0.212 | +| learning_rate | 3.97e-05 | +| loss | -0.0197 | +| n_updates | 100904 | +| policy_gradient_loss | -0.0137 | +| value_loss | 0.000245 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1381 | +| iterations | 21273 | +| time_elapsed | 31524 | +| total_timesteps | 43567104 | +| train/ | | +| approx_kl | 0.012003849 | +| clip_fraction | 0.304 | +| clip_range | 0.0641 | +| entropy_loss | -5.54 | +| explained_variance | 0.572 | +| learning_rate | 3.97e-05 | +| loss | -0.0264 | +| n_updates | 100908 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000175 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1381 | +| iterations | 21274 | +| time_elapsed | 31526 | +| total_timesteps | 43569152 | +| train/ | | +| approx_kl | 0.012635697 | +| clip_fraction | 0.332 | +| clip_range | 0.0641 | +| entropy_loss | -5.69 | +| explained_variance | 0.358 | +| learning_rate | 3.97e-05 | +| loss | -0.0274 | +| n_updates | 100912 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000155 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1381 | +| iterations | 21275 | +| time_elapsed | 31528 | +| total_timesteps | 43571200 | +| train/ | | +| approx_kl | 0.012774115 | +| clip_fraction | 0.314 | +| clip_range | 0.0641 | +| entropy_loss | -6.12 | +| explained_variance | 0.334 | +| learning_rate | 3.97e-05 | +| loss | -0.0285 | +| n_updates | 100916 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000134 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.351 | +| time/ | | +| fps | 1381 | +| iterations | 21276 | +| time_elapsed | 31529 | +| total_timesteps | 43573248 | +| train/ | | +| approx_kl | 0.01191213 | +| clip_fraction | 0.345 | +| clip_range | 0.0641 | +| entropy_loss | -6.38 | +| explained_variance | -0.0418 | +| learning_rate | 3.97e-05 | +| loss | -0.0284 | +| n_updates | 100920 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000128 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1381 | +| iterations | 21277 | +| time_elapsed | 31531 | +| total_timesteps | 43575296 | +| train/ | | +| approx_kl | 0.009568591 | +| clip_fraction | 0.276 | +| clip_range | 0.0641 | +| entropy_loss | -5.57 | +| explained_variance | 0.42 | +| learning_rate | 3.97e-05 | +| loss | -0.0215 | +| n_updates | 100924 | +| policy_gradient_loss | -0.0128 | +| value_loss | 0.000315 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1381 | +| iterations | 21278 | +| time_elapsed | 31532 | +| total_timesteps | 43577344 | +| train/ | | +| approx_kl | 0.0098832995 | +| clip_fraction | 0.311 | +| clip_range | 0.0641 | +| entropy_loss | -5.43 | +| explained_variance | 0.365 | +| learning_rate | 3.97e-05 | +| loss | -0.0257 | +| n_updates | 100928 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000145 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1381 | +| iterations | 21279 | +| time_elapsed | 31534 | +| total_timesteps | 43579392 | +| train/ | | +| approx_kl | 0.0106201675 | +| clip_fraction | 0.323 | +| clip_range | 0.0641 | +| entropy_loss | -4.76 | +| explained_variance | 0.567 | +| learning_rate | 3.97e-05 | +| loss | -0.0257 | +| n_updates | 100932 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000148 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1381 | +| iterations | 21280 | +| time_elapsed | 31535 | +| total_timesteps | 43581440 | +| train/ | | +| approx_kl | 0.012494057 | +| clip_fraction | 0.344 | +| clip_range | 0.0641 | +| entropy_loss | -5.46 | +| explained_variance | 0.353 | +| learning_rate | 3.96e-05 | +| loss | -0.0278 | +| n_updates | 100936 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000266 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1381 | +| iterations | 21281 | +| time_elapsed | 31537 | +| total_timesteps | 43583488 | +| train/ | | +| approx_kl | 0.013552416 | +| clip_fraction | 0.378 | +| clip_range | 0.0641 | +| entropy_loss | -5.95 | +| explained_variance | -0.81 | +| learning_rate | 3.96e-05 | +| loss | -0.04 | +| n_updates | 100940 | +| policy_gradient_loss | -0.0238 | +| value_loss | 5.59e-05 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1381 | +| iterations | 21282 | +| time_elapsed | 31538 | +| total_timesteps | 43585536 | +| train/ | | +| approx_kl | 0.0114514 | +| clip_fraction | 0.323 | +| clip_range | 0.0641 | +| entropy_loss | -6.63 | +| explained_variance | -0.0565 | +| learning_rate | 3.96e-05 | +| loss | -0.0272 | +| n_updates | 100944 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000187 | +--------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1381 | +| iterations | 21283 | +| time_elapsed | 31540 | +| total_timesteps | 43587584 | +| train/ | | +| approx_kl | 0.01043971 | +| clip_fraction | 0.287 | +| clip_range | 0.0641 | +| entropy_loss | -6.11 | +| explained_variance | 0.267 | +| learning_rate | 3.96e-05 | +| loss | -0.0267 | +| n_updates | 100948 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.00038 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1381 | +| iterations | 21284 | +| time_elapsed | 31541 | +| total_timesteps | 43589632 | +| train/ | | +| approx_kl | 0.012515869 | +| clip_fraction | 0.327 | +| clip_range | 0.0641 | +| entropy_loss | -5.65 | +| explained_variance | 0.422 | +| learning_rate | 3.96e-05 | +| loss | -0.0252 | +| n_updates | 100952 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000284 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1381 | +| iterations | 21285 | +| time_elapsed | 31543 | +| total_timesteps | 43591680 | +| train/ | | +| approx_kl | 0.01448329 | +| clip_fraction | 0.314 | +| clip_range | 0.0641 | +| entropy_loss | -5.77 | +| explained_variance | 0.215 | +| learning_rate | 3.96e-05 | +| loss | -0.0286 | +| n_updates | 100956 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.00021 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1381 | +| iterations | 21286 | +| time_elapsed | 31544 | +| total_timesteps | 43593728 | +| train/ | | +| approx_kl | 0.012541297 | +| clip_fraction | 0.356 | +| clip_range | 0.0641 | +| entropy_loss | -5.74 | +| explained_variance | 0.276 | +| learning_rate | 3.96e-05 | +| loss | -0.0336 | +| n_updates | 100960 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000123 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1381 | +| iterations | 21287 | +| time_elapsed | 31546 | +| total_timesteps | 43595776 | +| train/ | | +| approx_kl | 0.012172679 | +| clip_fraction | 0.332 | +| clip_range | 0.0641 | +| entropy_loss | -5.06 | +| explained_variance | 0.228 | +| learning_rate | 3.96e-05 | +| loss | -0.0237 | +| n_updates | 100964 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000239 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1381 | +| iterations | 21288 | +| time_elapsed | 31547 | +| total_timesteps | 43597824 | +| train/ | | +| approx_kl | 0.012458345 | +| clip_fraction | 0.352 | +| clip_range | 0.0641 | +| entropy_loss | -5.47 | +| explained_variance | 0.532 | +| learning_rate | 3.96e-05 | +| loss | -0.028 | +| n_updates | 100968 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000119 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1381 | +| iterations | 21289 | +| time_elapsed | 31549 | +| total_timesteps | 43599872 | +| train/ | | +| approx_kl | 0.015881302 | +| clip_fraction | 0.341 | +| clip_range | 0.0641 | +| entropy_loss | -5.8 | +| explained_variance | 0.336 | +| learning_rate | 3.96e-05 | +| loss | -0.03 | +| n_updates | 100972 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000115 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1381 | +| iterations | 21290 | +| time_elapsed | 31550 | +| total_timesteps | 43601920 | +| train/ | | +| approx_kl | 0.012280809 | +| clip_fraction | 0.339 | +| clip_range | 0.0641 | +| entropy_loss | -5.14 | +| explained_variance | 0.413 | +| learning_rate | 3.96e-05 | +| loss | -0.021 | +| n_updates | 100976 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000256 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1381 | +| iterations | 21291 | +| time_elapsed | 31552 | +| total_timesteps | 43603968 | +| train/ | | +| approx_kl | 0.015087739 | +| clip_fraction | 0.362 | +| clip_range | 0.0641 | +| entropy_loss | -5.26 | +| explained_variance | -0.0355 | +| learning_rate | 3.96e-05 | +| loss | -0.0306 | +| n_updates | 100980 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000141 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1381 | +| iterations | 21292 | +| time_elapsed | 31553 | +| total_timesteps | 43606016 | +| train/ | | +| approx_kl | 0.01287761 | +| clip_fraction | 0.324 | +| clip_range | 0.0641 | +| entropy_loss | -6.11 | +| explained_variance | 0.214 | +| learning_rate | 3.96e-05 | +| loss | -0.0284 | +| n_updates | 100984 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000167 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1381 | +| iterations | 21293 | +| time_elapsed | 31555 | +| total_timesteps | 43608064 | +| train/ | | +| approx_kl | 0.013215803 | +| clip_fraction | 0.307 | +| clip_range | 0.0641 | +| entropy_loss | -5.98 | +| explained_variance | 0.334 | +| learning_rate | 3.96e-05 | +| loss | -0.0268 | +| n_updates | 100988 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1381 | +| iterations | 21294 | +| time_elapsed | 31557 | +| total_timesteps | 43610112 | +| train/ | | +| approx_kl | 0.015433943 | +| clip_fraction | 0.335 | +| clip_range | 0.0641 | +| entropy_loss | -4.99 | +| explained_variance | 0.629 | +| learning_rate | 3.96e-05 | +| loss | -0.0275 | +| n_updates | 100992 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000115 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1381 | +| iterations | 21295 | +| time_elapsed | 31558 | +| total_timesteps | 43612160 | +| train/ | | +| approx_kl | 0.012588105 | +| clip_fraction | 0.362 | +| clip_range | 0.0641 | +| entropy_loss | -5.58 | +| explained_variance | 0.557 | +| learning_rate | 3.96e-05 | +| loss | -0.0323 | +| n_updates | 100996 | +| policy_gradient_loss | -0.0212 | +| value_loss | 4.62e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1381 | +| iterations | 21296 | +| time_elapsed | 31560 | +| total_timesteps | 43614208 | +| train/ | | +| approx_kl | 0.009759767 | +| clip_fraction | 0.326 | +| clip_range | 0.0641 | +| entropy_loss | -6.53 | +| explained_variance | 0.0661 | +| learning_rate | 3.96e-05 | +| loss | -0.0243 | +| n_updates | 101000 | +| policy_gradient_loss | -0.0161 | +| value_loss | 9.94e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1381 | +| iterations | 21297 | +| time_elapsed | 31561 | +| total_timesteps | 43616256 | +| train/ | | +| approx_kl | 0.009977154 | +| clip_fraction | 0.301 | +| clip_range | 0.0641 | +| entropy_loss | -6.2 | +| explained_variance | 0.484 | +| learning_rate | 3.96e-05 | +| loss | -0.0242 | +| n_updates | 101004 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000176 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1381 | +| iterations | 21298 | +| time_elapsed | 31563 | +| total_timesteps | 43618304 | +| train/ | | +| approx_kl | 0.012472665 | +| clip_fraction | 0.331 | +| clip_range | 0.0641 | +| entropy_loss | -6.01 | +| explained_variance | 0.13 | +| learning_rate | 3.96e-05 | +| loss | -0.0217 | +| n_updates | 101008 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000212 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1381 | +| iterations | 21299 | +| time_elapsed | 31564 | +| total_timesteps | 43620352 | +| train/ | | +| approx_kl | 0.014021881 | +| clip_fraction | 0.353 | +| clip_range | 0.0641 | +| entropy_loss | -5.93 | +| explained_variance | 0.287 | +| learning_rate | 3.96e-05 | +| loss | -0.0295 | +| n_updates | 101012 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000143 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1381 | +| iterations | 21300 | +| time_elapsed | 31566 | +| total_timesteps | 43622400 | +| train/ | | +| approx_kl | 0.010522356 | +| clip_fraction | 0.344 | +| clip_range | 0.0641 | +| entropy_loss | -5.62 | +| explained_variance | 0.0793 | +| learning_rate | 3.96e-05 | +| loss | -0.0204 | +| n_updates | 101016 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.000134 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1381 | +| iterations | 21301 | +| time_elapsed | 31567 | +| total_timesteps | 43624448 | +| train/ | | +| approx_kl | 0.0121606225 | +| clip_fraction | 0.314 | +| clip_range | 0.0641 | +| entropy_loss | -5.81 | +| explained_variance | 0.586 | +| learning_rate | 3.96e-05 | +| loss | -0.0236 | +| n_updates | 101020 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.00013 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1381 | +| iterations | 21302 | +| time_elapsed | 31569 | +| total_timesteps | 43626496 | +| train/ | | +| approx_kl | 0.012961794 | +| clip_fraction | 0.322 | +| clip_range | 0.0641 | +| entropy_loss | -5.72 | +| explained_variance | 0.383 | +| learning_rate | 3.96e-05 | +| loss | -0.029 | +| n_updates | 101024 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000124 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1381 | +| iterations | 21303 | +| time_elapsed | 31570 | +| total_timesteps | 43628544 | +| train/ | | +| approx_kl | 0.011212664 | +| clip_fraction | 0.318 | +| clip_range | 0.0641 | +| entropy_loss | -5.91 | +| explained_variance | 0.744 | +| learning_rate | 3.96e-05 | +| loss | -0.0276 | +| n_updates | 101028 | +| policy_gradient_loss | -0.0175 | +| value_loss | 5.57e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1381 | +| iterations | 21304 | +| time_elapsed | 31572 | +| total_timesteps | 43630592 | +| train/ | | +| approx_kl | 0.009741576 | +| clip_fraction | 0.323 | +| clip_range | 0.0641 | +| entropy_loss | -6 | +| explained_variance | 0.28 | +| learning_rate | 3.96e-05 | +| loss | -0.0272 | +| n_updates | 101032 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000165 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1381 | +| iterations | 21305 | +| time_elapsed | 31573 | +| total_timesteps | 43632640 | +| train/ | | +| approx_kl | 0.013586378 | +| clip_fraction | 0.319 | +| clip_range | 0.0641 | +| entropy_loss | -5.93 | +| explained_variance | -0.075 | +| learning_rate | 3.96e-05 | +| loss | -0.0242 | +| n_updates | 101036 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.000147 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1381 | +| iterations | 21306 | +| time_elapsed | 31575 | +| total_timesteps | 43634688 | +| train/ | | +| approx_kl | 0.015022742 | +| clip_fraction | 0.335 | +| clip_range | 0.0641 | +| entropy_loss | -5.88 | +| explained_variance | 0.699 | +| learning_rate | 3.96e-05 | +| loss | -0.031 | +| n_updates | 101040 | +| policy_gradient_loss | -0.0185 | +| value_loss | 7.86e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1381 | +| iterations | 21307 | +| time_elapsed | 31577 | +| total_timesteps | 43636736 | +| train/ | | +| approx_kl | 0.013883845 | +| clip_fraction | 0.341 | +| clip_range | 0.0641 | +| entropy_loss | -5.05 | +| explained_variance | 0.807 | +| learning_rate | 3.96e-05 | +| loss | -0.033 | +| n_updates | 101044 | +| policy_gradient_loss | -0.0185 | +| value_loss | 5.52e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1381 | +| iterations | 21308 | +| time_elapsed | 31578 | +| total_timesteps | 43638784 | +| train/ | | +| approx_kl | 0.012269809 | +| clip_fraction | 0.329 | +| clip_range | 0.0641 | +| entropy_loss | -5.35 | +| explained_variance | 0.638 | +| learning_rate | 3.96e-05 | +| loss | -0.0251 | +| n_updates | 101048 | +| policy_gradient_loss | -0.0174 | +| value_loss | 9.4e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1381 | +| iterations | 21309 | +| time_elapsed | 31580 | +| total_timesteps | 43640832 | +| train/ | | +| approx_kl | 0.008484632 | +| clip_fraction | 0.296 | +| clip_range | 0.0641 | +| entropy_loss | -6.26 | +| explained_variance | -0.0174 | +| learning_rate | 3.96e-05 | +| loss | -0.0225 | +| n_updates | 101052 | +| policy_gradient_loss | -0.0148 | +| value_loss | 9.59e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1381 | +| iterations | 21310 | +| time_elapsed | 31581 | +| total_timesteps | 43642880 | +| train/ | | +| approx_kl | 0.012212617 | +| clip_fraction | 0.274 | +| clip_range | 0.0641 | +| entropy_loss | -6.38 | +| explained_variance | 0.239 | +| learning_rate | 3.96e-05 | +| loss | -0.0237 | +| n_updates | 101056 | +| policy_gradient_loss | -0.0136 | +| value_loss | 0.00023 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.331 | +| time/ | | +| fps | 1381 | +| iterations | 21311 | +| time_elapsed | 31583 | +| total_timesteps | 43644928 | +| train/ | | +| approx_kl | 0.00937793 | +| clip_fraction | 0.293 | +| clip_range | 0.0641 | +| entropy_loss | -6.57 | +| explained_variance | -0.0121 | +| learning_rate | 3.96e-05 | +| loss | -0.0267 | +| n_updates | 101060 | +| policy_gradient_loss | -0.0148 | +| value_loss | 0.000146 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1381 | +| iterations | 21312 | +| time_elapsed | 31584 | +| total_timesteps | 43646976 | +| train/ | | +| approx_kl | 0.009232809 | +| clip_fraction | 0.292 | +| clip_range | 0.0641 | +| entropy_loss | -6.45 | +| explained_variance | 0.396 | +| learning_rate | 3.96e-05 | +| loss | -0.0261 | +| n_updates | 101064 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000112 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1381 | +| iterations | 21313 | +| time_elapsed | 31586 | +| total_timesteps | 43649024 | +| train/ | | +| approx_kl | 0.010121523 | +| clip_fraction | 0.317 | +| clip_range | 0.0641 | +| entropy_loss | -6.17 | +| explained_variance | 0.234 | +| learning_rate | 3.96e-05 | +| loss | -0.0225 | +| n_updates | 101068 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000273 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.329 | +| time/ | | +| fps | 1381 | +| iterations | 21314 | +| time_elapsed | 31587 | +| total_timesteps | 43651072 | +| train/ | | +| approx_kl | 0.009872539 | +| clip_fraction | 0.302 | +| clip_range | 0.0641 | +| entropy_loss | -5.55 | +| explained_variance | 0.544 | +| learning_rate | 3.96e-05 | +| loss | -0.0247 | +| n_updates | 101072 | +| policy_gradient_loss | -0.0139 | +| value_loss | 0.00022 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1381 | +| iterations | 21315 | +| time_elapsed | 31589 | +| total_timesteps | 43653120 | +| train/ | | +| approx_kl | 0.012560789 | +| clip_fraction | 0.317 | +| clip_range | 0.0641 | +| entropy_loss | -5.42 | +| explained_variance | 0.674 | +| learning_rate | 3.96e-05 | +| loss | -0.0249 | +| n_updates | 101076 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000114 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1381 | +| iterations | 21316 | +| time_elapsed | 31591 | +| total_timesteps | 43655168 | +| train/ | | +| approx_kl | 0.01469833 | +| clip_fraction | 0.333 | +| clip_range | 0.0641 | +| entropy_loss | -5.91 | +| explained_variance | 0.128 | +| learning_rate | 3.96e-05 | +| loss | -0.0329 | +| n_updates | 101080 | +| policy_gradient_loss | -0.0188 | +| value_loss | 9.29e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1381 | +| iterations | 21317 | +| time_elapsed | 31592 | +| total_timesteps | 43657216 | +| train/ | | +| approx_kl | 0.011896012 | +| clip_fraction | 0.313 | +| clip_range | 0.0641 | +| entropy_loss | -5.65 | +| explained_variance | 0.543 | +| learning_rate | 3.96e-05 | +| loss | -0.0273 | +| n_updates | 101084 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.00014 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1381 | +| iterations | 21318 | +| time_elapsed | 31594 | +| total_timesteps | 43659264 | +| train/ | | +| approx_kl | 0.012025073 | +| clip_fraction | 0.305 | +| clip_range | 0.0641 | +| entropy_loss | -5.94 | +| explained_variance | 0.315 | +| learning_rate | 3.96e-05 | +| loss | -0.0214 | +| n_updates | 101088 | +| policy_gradient_loss | -0.0141 | +| value_loss | 0.000247 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1381 | +| iterations | 21319 | +| time_elapsed | 31595 | +| total_timesteps | 43661312 | +| train/ | | +| approx_kl | 0.01329526 | +| clip_fraction | 0.329 | +| clip_range | 0.0641 | +| entropy_loss | -4.69 | +| explained_variance | 0.594 | +| learning_rate | 3.96e-05 | +| loss | -0.0253 | +| n_updates | 101092 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000164 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1381 | +| iterations | 21320 | +| time_elapsed | 31597 | +| total_timesteps | 43663360 | +| train/ | | +| approx_kl | 0.01407499 | +| clip_fraction | 0.341 | +| clip_range | 0.0641 | +| entropy_loss | -5.74 | +| explained_variance | 0.299 | +| learning_rate | 3.96e-05 | +| loss | -0.0316 | +| n_updates | 101096 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000113 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1381 | +| iterations | 21321 | +| time_elapsed | 31598 | +| total_timesteps | 43665408 | +| train/ | | +| approx_kl | 0.013865985 | +| clip_fraction | 0.357 | +| clip_range | 0.0641 | +| entropy_loss | -6.11 | +| explained_variance | -0.281 | +| learning_rate | 3.96e-05 | +| loss | -0.0376 | +| n_updates | 101100 | +| policy_gradient_loss | -0.0211 | +| value_loss | 4.81e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1381 | +| iterations | 21322 | +| time_elapsed | 31600 | +| total_timesteps | 43667456 | +| train/ | | +| approx_kl | 0.014239262 | +| clip_fraction | 0.334 | +| clip_range | 0.0641 | +| entropy_loss | -6.41 | +| explained_variance | -0.0394 | +| learning_rate | 3.96e-05 | +| loss | -0.0248 | +| n_updates | 101104 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000162 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1381 | +| iterations | 21323 | +| time_elapsed | 31601 | +| total_timesteps | 43669504 | +| train/ | | +| approx_kl | 0.013290955 | +| clip_fraction | 0.296 | +| clip_range | 0.0641 | +| entropy_loss | -5.97 | +| explained_variance | 0.364 | +| learning_rate | 3.96e-05 | +| loss | -0.0209 | +| n_updates | 101108 | +| policy_gradient_loss | -0.0146 | +| value_loss | 0.000203 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1381 | +| iterations | 21324 | +| time_elapsed | 31603 | +| total_timesteps | 43671552 | +| train/ | | +| approx_kl | 0.011571772 | +| clip_fraction | 0.333 | +| clip_range | 0.0641 | +| entropy_loss | -5.61 | +| explained_variance | 0.378 | +| learning_rate | 3.96e-05 | +| loss | -0.0311 | +| n_updates | 101112 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000137 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1381 | +| iterations | 21325 | +| time_elapsed | 31604 | +| total_timesteps | 43673600 | +| train/ | | +| approx_kl | 0.01289533 | +| clip_fraction | 0.327 | +| clip_range | 0.0641 | +| entropy_loss | -5.37 | +| explained_variance | 0.715 | +| learning_rate | 3.96e-05 | +| loss | -0.0295 | +| n_updates | 101116 | +| policy_gradient_loss | -0.0175 | +| value_loss | 6.93e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1381 | +| iterations | 21326 | +| time_elapsed | 31606 | +| total_timesteps | 43675648 | +| train/ | | +| approx_kl | 0.015237916 | +| clip_fraction | 0.329 | +| clip_range | 0.0641 | +| entropy_loss | -6.21 | +| explained_variance | -0.0539 | +| learning_rate | 3.96e-05 | +| loss | -0.03 | +| n_updates | 101120 | +| policy_gradient_loss | -0.0173 | +| value_loss | 8.09e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.315 | +| time/ | | +| fps | 1381 | +| iterations | 21327 | +| time_elapsed | 31607 | +| total_timesteps | 43677696 | +| train/ | | +| approx_kl | 0.011019368 | +| clip_fraction | 0.31 | +| clip_range | 0.0641 | +| entropy_loss | -6.25 | +| explained_variance | 0.691 | +| learning_rate | 3.96e-05 | +| loss | -0.0257 | +| n_updates | 101124 | +| policy_gradient_loss | -0.0153 | +| value_loss | 8.62e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1381 | +| iterations | 21328 | +| time_elapsed | 31609 | +| total_timesteps | 43679744 | +| train/ | | +| approx_kl | 0.011276944 | +| clip_fraction | 0.288 | +| clip_range | 0.0641 | +| entropy_loss | -5.81 | +| explained_variance | 0.264 | +| learning_rate | 3.96e-05 | +| loss | -0.0237 | +| n_updates | 101128 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000248 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1381 | +| iterations | 21329 | +| time_elapsed | 31610 | +| total_timesteps | 43681792 | +| train/ | | +| approx_kl | 0.011747306 | +| clip_fraction | 0.315 | +| clip_range | 0.0641 | +| entropy_loss | -5.51 | +| explained_variance | 0.616 | +| learning_rate | 3.96e-05 | +| loss | -0.0259 | +| n_updates | 101132 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000144 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1381 | +| iterations | 21330 | +| time_elapsed | 31612 | +| total_timesteps | 43683840 | +| train/ | | +| approx_kl | 0.015178451 | +| clip_fraction | 0.327 | +| clip_range | 0.0641 | +| entropy_loss | -5.97 | +| explained_variance | 0.652 | +| learning_rate | 3.96e-05 | +| loss | -0.0242 | +| n_updates | 101136 | +| policy_gradient_loss | -0.0171 | +| value_loss | 9.27e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1381 | +| iterations | 21331 | +| time_elapsed | 31613 | +| total_timesteps | 43685888 | +| train/ | | +| approx_kl | 0.011157264 | +| clip_fraction | 0.339 | +| clip_range | 0.0641 | +| entropy_loss | -6.09 | +| explained_variance | 0.0895 | +| learning_rate | 3.96e-05 | +| loss | -0.0293 | +| n_updates | 101140 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000117 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1381 | +| iterations | 21332 | +| time_elapsed | 31615 | +| total_timesteps | 43687936 | +| train/ | | +| approx_kl | 0.012683127 | +| clip_fraction | 0.322 | +| clip_range | 0.0641 | +| entropy_loss | -5.79 | +| explained_variance | 0.565 | +| learning_rate | 3.96e-05 | +| loss | -0.0214 | +| n_updates | 101144 | +| policy_gradient_loss | -0.0148 | +| value_loss | 0.000116 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.327 | +| time/ | | +| fps | 1381 | +| iterations | 21333 | +| time_elapsed | 31616 | +| total_timesteps | 43689984 | +| train/ | | +| approx_kl | 0.010713392 | +| clip_fraction | 0.292 | +| clip_range | 0.0641 | +| entropy_loss | -6.24 | +| explained_variance | -0.0556 | +| learning_rate | 3.96e-05 | +| loss | -0.0281 | +| n_updates | 101148 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000299 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1381 | +| iterations | 21334 | +| time_elapsed | 31618 | +| total_timesteps | 43692032 | +| train/ | | +| approx_kl | 0.008436355 | +| clip_fraction | 0.318 | +| clip_range | 0.0641 | +| entropy_loss | -6.47 | +| explained_variance | 0.347 | +| learning_rate | 3.96e-05 | +| loss | -0.0231 | +| n_updates | 101152 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000169 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1381 | +| iterations | 21335 | +| time_elapsed | 31620 | +| total_timesteps | 43694080 | +| train/ | | +| approx_kl | 0.010010361 | +| clip_fraction | 0.302 | +| clip_range | 0.0641 | +| entropy_loss | -6.16 | +| explained_variance | 0.276 | +| learning_rate | 3.96e-05 | +| loss | -0.0183 | +| n_updates | 101156 | +| policy_gradient_loss | -0.0142 | +| value_loss | 0.000183 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1381 | +| iterations | 21336 | +| time_elapsed | 31621 | +| total_timesteps | 43696128 | +| train/ | | +| approx_kl | 0.010020045 | +| clip_fraction | 0.335 | +| clip_range | 0.0641 | +| entropy_loss | -5.95 | +| explained_variance | 0.335 | +| learning_rate | 3.96e-05 | +| loss | -0.0274 | +| n_updates | 101160 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000299 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.332 | +| time/ | | +| fps | 1381 | +| iterations | 21337 | +| time_elapsed | 31623 | +| total_timesteps | 43698176 | +| train/ | | +| approx_kl | 0.011463849 | +| clip_fraction | 0.342 | +| clip_range | 0.0641 | +| entropy_loss | -6.09 | +| explained_variance | 0.33 | +| learning_rate | 3.96e-05 | +| loss | -0.0323 | +| n_updates | 101164 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000136 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1381 | +| iterations | 21338 | +| time_elapsed | 31624 | +| total_timesteps | 43700224 | +| train/ | | +| approx_kl | 0.013060528 | +| clip_fraction | 0.354 | +| clip_range | 0.0641 | +| entropy_loss | -6.34 | +| explained_variance | -0.203 | +| learning_rate | 3.96e-05 | +| loss | -0.0304 | +| n_updates | 101168 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000115 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.333 | +| time/ | | +| fps | 1381 | +| iterations | 21339 | +| time_elapsed | 31626 | +| total_timesteps | 43702272 | +| train/ | | +| approx_kl | 0.009668947 | +| clip_fraction | 0.31 | +| clip_range | 0.0641 | +| entropy_loss | -5.91 | +| explained_variance | 0.449 | +| learning_rate | 3.96e-05 | +| loss | -0.0249 | +| n_updates | 101172 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000194 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.334 | +| time/ | | +| fps | 1381 | +| iterations | 21340 | +| time_elapsed | 31627 | +| total_timesteps | 43704320 | +| train/ | | +| approx_kl | 0.010397999 | +| clip_fraction | 0.329 | +| clip_range | 0.0641 | +| entropy_loss | -6.17 | +| explained_variance | 0.451 | +| learning_rate | 3.96e-05 | +| loss | -0.0297 | +| n_updates | 101176 | +| policy_gradient_loss | -0.0182 | +| value_loss | 9.71e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1381 | +| iterations | 21341 | +| time_elapsed | 31629 | +| total_timesteps | 43706368 | +| train/ | | +| approx_kl | 0.01329054 | +| clip_fraction | 0.325 | +| clip_range | 0.0641 | +| entropy_loss | -6.31 | +| explained_variance | 0.722 | +| learning_rate | 3.96e-05 | +| loss | -0.0307 | +| n_updates | 101180 | +| policy_gradient_loss | -0.0169 | +| value_loss | 8.94e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1381 | +| iterations | 21342 | +| time_elapsed | 31630 | +| total_timesteps | 43708416 | +| train/ | | +| approx_kl | 0.012353161 | +| clip_fraction | 0.317 | +| clip_range | 0.0641 | +| entropy_loss | -5.65 | +| explained_variance | 0.24 | +| learning_rate | 3.96e-05 | +| loss | -0.0264 | +| n_updates | 101184 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.000261 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1381 | +| iterations | 21343 | +| time_elapsed | 31632 | +| total_timesteps | 43710464 | +| train/ | | +| approx_kl | 0.014205798 | +| clip_fraction | 0.333 | +| clip_range | 0.0641 | +| entropy_loss | -5.5 | +| explained_variance | 0.594 | +| learning_rate | 3.96e-05 | +| loss | -0.0298 | +| n_updates | 101188 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000146 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1381 | +| iterations | 21344 | +| time_elapsed | 31633 | +| total_timesteps | 43712512 | +| train/ | | +| approx_kl | 0.014872837 | +| clip_fraction | 0.362 | +| clip_range | 0.0641 | +| entropy_loss | -5.87 | +| explained_variance | -0.144 | +| learning_rate | 3.96e-05 | +| loss | -0.0256 | +| n_updates | 101192 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000143 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1381 | +| iterations | 21345 | +| time_elapsed | 31635 | +| total_timesteps | 43714560 | +| train/ | | +| approx_kl | 0.009723446 | +| clip_fraction | 0.308 | +| clip_range | 0.0641 | +| entropy_loss | -5.77 | +| explained_variance | 0.408 | +| learning_rate | 3.96e-05 | +| loss | -0.0295 | +| n_updates | 101196 | +| policy_gradient_loss | -0.0145 | +| value_loss | 0.000262 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1381 | +| iterations | 21346 | +| time_elapsed | 31636 | +| total_timesteps | 43716608 | +| train/ | | +| approx_kl | 0.013085286 | +| clip_fraction | 0.34 | +| clip_range | 0.0641 | +| entropy_loss | -5.93 | +| explained_variance | 0.42 | +| learning_rate | 3.96e-05 | +| loss | -0.033 | +| n_updates | 101200 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.00012 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1381 | +| iterations | 21347 | +| time_elapsed | 31638 | +| total_timesteps | 43718656 | +| train/ | | +| approx_kl | 0.0128068775 | +| clip_fraction | 0.353 | +| clip_range | 0.0641 | +| entropy_loss | -6.33 | +| explained_variance | 0.408 | +| learning_rate | 3.96e-05 | +| loss | -0.0387 | +| n_updates | 101204 | +| policy_gradient_loss | -0.0209 | +| value_loss | 7.81e-05 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1381 | +| iterations | 21348 | +| time_elapsed | 31639 | +| total_timesteps | 43720704 | +| train/ | | +| approx_kl | 0.011161125 | +| clip_fraction | 0.349 | +| clip_range | 0.0641 | +| entropy_loss | -5.95 | +| explained_variance | -0.142 | +| learning_rate | 3.96e-05 | +| loss | -0.0343 | +| n_updates | 101208 | +| policy_gradient_loss | -0.0195 | +| value_loss | 9.94e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1381 | +| iterations | 21349 | +| time_elapsed | 31641 | +| total_timesteps | 43722752 | +| train/ | | +| approx_kl | 0.010268018 | +| clip_fraction | 0.305 | +| clip_range | 0.0641 | +| entropy_loss | -5.73 | +| explained_variance | 0.428 | +| learning_rate | 3.96e-05 | +| loss | -0.0256 | +| n_updates | 101212 | +| policy_gradient_loss | -0.0127 | +| value_loss | 0.00028 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1381 | +| iterations | 21350 | +| time_elapsed | 31642 | +| total_timesteps | 43724800 | +| train/ | | +| approx_kl | 0.0134302 | +| clip_fraction | 0.317 | +| clip_range | 0.0641 | +| entropy_loss | -5.69 | +| explained_variance | -0.163 | +| learning_rate | 3.96e-05 | +| loss | -0.0303 | +| n_updates | 101216 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000151 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1381 | +| iterations | 21351 | +| time_elapsed | 31644 | +| total_timesteps | 43726848 | +| train/ | | +| approx_kl | 0.012161979 | +| clip_fraction | 0.334 | +| clip_range | 0.0641 | +| entropy_loss | -5.32 | +| explained_variance | 0.527 | +| learning_rate | 3.96e-05 | +| loss | -0.0246 | +| n_updates | 101220 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.0002 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1381 | +| iterations | 21352 | +| time_elapsed | 31645 | +| total_timesteps | 43728896 | +| train/ | | +| approx_kl | 0.012465014 | +| clip_fraction | 0.329 | +| clip_range | 0.0641 | +| entropy_loss | -5.69 | +| explained_variance | 0.436 | +| learning_rate | 3.96e-05 | +| loss | -0.0276 | +| n_updates | 101224 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000159 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1381 | +| iterations | 21353 | +| time_elapsed | 31647 | +| total_timesteps | 43730944 | +| train/ | | +| approx_kl | 0.012121447 | +| clip_fraction | 0.341 | +| clip_range | 0.0641 | +| entropy_loss | -5.79 | +| explained_variance | -0.0235 | +| learning_rate | 3.96e-05 | +| loss | -0.0261 | +| n_updates | 101228 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000181 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1381 | +| iterations | 21354 | +| time_elapsed | 31648 | +| total_timesteps | 43732992 | +| train/ | | +| approx_kl | 0.015202235 | +| clip_fraction | 0.362 | +| clip_range | 0.0641 | +| entropy_loss | -4.88 | +| explained_variance | 0.705 | +| learning_rate | 3.96e-05 | +| loss | -0.0243 | +| n_updates | 101232 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000106 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1381 | +| iterations | 21355 | +| time_elapsed | 31649 | +| total_timesteps | 43735040 | +| train/ | | +| approx_kl | 0.01105173 | +| clip_fraction | 0.343 | +| clip_range | 0.0641 | +| entropy_loss | -5.45 | +| explained_variance | 0.376 | +| learning_rate | 3.96e-05 | +| loss | -0.0235 | +| n_updates | 101236 | +| policy_gradient_loss | -0.014 | +| value_loss | 0.000299 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1381 | +| iterations | 21356 | +| time_elapsed | 31651 | +| total_timesteps | 43737088 | +| train/ | | +| approx_kl | 0.014470326 | +| clip_fraction | 0.361 | +| clip_range | 0.0641 | +| entropy_loss | -5.21 | +| explained_variance | 0.585 | +| learning_rate | 3.96e-05 | +| loss | -0.0336 | +| n_updates | 101240 | +| policy_gradient_loss | -0.0199 | +| value_loss | 9.08e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1381 | +| iterations | 21357 | +| time_elapsed | 31653 | +| total_timesteps | 43739136 | +| train/ | | +| approx_kl | 0.015957765 | +| clip_fraction | 0.335 | +| clip_range | 0.0641 | +| entropy_loss | -5.78 | +| explained_variance | -0.261 | +| learning_rate | 3.96e-05 | +| loss | -0.0351 | +| n_updates | 101244 | +| policy_gradient_loss | -0.0197 | +| value_loss | 7.38e-05 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1381 | +| iterations | 21358 | +| time_elapsed | 31654 | +| total_timesteps | 43741184 | +| train/ | | +| approx_kl | 0.0145584 | +| clip_fraction | 0.357 | +| clip_range | 0.0641 | +| entropy_loss | -5.49 | +| explained_variance | 0.766 | +| learning_rate | 3.96e-05 | +| loss | -0.0371 | +| n_updates | 101248 | +| policy_gradient_loss | -0.0187 | +| value_loss | 6.66e-05 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1381 | +| iterations | 21359 | +| time_elapsed | 31656 | +| total_timesteps | 43743232 | +| train/ | | +| approx_kl | 0.009959552 | +| clip_fraction | 0.298 | +| clip_range | 0.0641 | +| entropy_loss | -5.9 | +| explained_variance | 0.358 | +| learning_rate | 3.96e-05 | +| loss | -0.0256 | +| n_updates | 101252 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000131 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.348 | +| time/ | | +| fps | 1381 | +| iterations | 21360 | +| time_elapsed | 31657 | +| total_timesteps | 43745280 | +| train/ | | +| approx_kl | 0.010364847 | +| clip_fraction | 0.321 | +| clip_range | 0.0641 | +| entropy_loss | -5.35 | +| explained_variance | 0.639 | +| learning_rate | 3.96e-05 | +| loss | -0.0249 | +| n_updates | 101256 | +| policy_gradient_loss | -0.0152 | +| value_loss | 9.71e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1381 | +| iterations | 21361 | +| time_elapsed | 31658 | +| total_timesteps | 43747328 | +| train/ | | +| approx_kl | 0.01250218 | +| clip_fraction | 0.357 | +| clip_range | 0.0641 | +| entropy_loss | -5.72 | +| explained_variance | 0.073 | +| learning_rate | 3.96e-05 | +| loss | -0.0279 | +| n_updates | 101260 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000225 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1381 | +| iterations | 21362 | +| time_elapsed | 31660 | +| total_timesteps | 43749376 | +| train/ | | +| approx_kl | 0.009617918 | +| clip_fraction | 0.322 | +| clip_range | 0.0641 | +| entropy_loss | -5.8 | +| explained_variance | 0.598 | +| learning_rate | 3.96e-05 | +| loss | -0.0255 | +| n_updates | 101264 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000111 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1381 | +| iterations | 21363 | +| time_elapsed | 31661 | +| total_timesteps | 43751424 | +| train/ | | +| approx_kl | 0.012567954 | +| clip_fraction | 0.306 | +| clip_range | 0.0641 | +| entropy_loss | -6.04 | +| explained_variance | -0.00176 | +| learning_rate | 3.96e-05 | +| loss | -0.0275 | +| n_updates | 101268 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000197 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1381 | +| iterations | 21364 | +| time_elapsed | 31663 | +| total_timesteps | 43753472 | +| train/ | | +| approx_kl | 0.010612863 | +| clip_fraction | 0.329 | +| clip_range | 0.0641 | +| entropy_loss | -6.05 | +| explained_variance | 0.151 | +| learning_rate | 3.96e-05 | +| loss | -0.0269 | +| n_updates | 101272 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000133 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1381 | +| iterations | 21365 | +| time_elapsed | 31664 | +| total_timesteps | 43755520 | +| train/ | | +| approx_kl | 0.012377722 | +| clip_fraction | 0.345 | +| clip_range | 0.0641 | +| entropy_loss | -5.61 | +| explained_variance | 0.54 | +| learning_rate | 3.96e-05 | +| loss | -0.0281 | +| n_updates | 101276 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000101 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1381 | +| iterations | 21366 | +| time_elapsed | 31666 | +| total_timesteps | 43757568 | +| train/ | | +| approx_kl | 0.015225904 | +| clip_fraction | 0.327 | +| clip_range | 0.0641 | +| entropy_loss | -5.39 | +| explained_variance | 0.263 | +| learning_rate | 3.96e-05 | +| loss | -0.0272 | +| n_updates | 101280 | +| policy_gradient_loss | -0.0148 | +| value_loss | 7.36e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1381 | +| iterations | 21367 | +| time_elapsed | 31667 | +| total_timesteps | 43759616 | +| train/ | | +| approx_kl | 0.0143917445 | +| clip_fraction | 0.343 | +| clip_range | 0.0641 | +| entropy_loss | -5.71 | +| explained_variance | 0.3 | +| learning_rate | 3.96e-05 | +| loss | -0.0284 | +| n_updates | 101284 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000197 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1381 | +| iterations | 21368 | +| time_elapsed | 31669 | +| total_timesteps | 43761664 | +| train/ | | +| approx_kl | 0.012890844 | +| clip_fraction | 0.32 | +| clip_range | 0.0641 | +| entropy_loss | -5.83 | +| explained_variance | -0.0142 | +| learning_rate | 3.96e-05 | +| loss | -0.0224 | +| n_updates | 101288 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000142 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1381 | +| iterations | 21369 | +| time_elapsed | 31670 | +| total_timesteps | 43763712 | +| train/ | | +| approx_kl | 0.011723292 | +| clip_fraction | 0.334 | +| clip_range | 0.0641 | +| entropy_loss | -6.09 | +| explained_variance | -0.183 | +| learning_rate | 3.96e-05 | +| loss | -0.0281 | +| n_updates | 101292 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.0001 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1381 | +| iterations | 21370 | +| time_elapsed | 31671 | +| total_timesteps | 43765760 | +| train/ | | +| approx_kl | 0.011994724 | +| clip_fraction | 0.294 | +| clip_range | 0.0641 | +| entropy_loss | -5.58 | +| explained_variance | 0.452 | +| learning_rate | 3.96e-05 | +| loss | -0.0244 | +| n_updates | 101296 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000215 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1381 | +| iterations | 21371 | +| time_elapsed | 31673 | +| total_timesteps | 43767808 | +| train/ | | +| approx_kl | 0.012706647 | +| clip_fraction | 0.327 | +| clip_range | 0.0641 | +| entropy_loss | -5.41 | +| explained_variance | 0.414 | +| learning_rate | 3.96e-05 | +| loss | -0.0307 | +| n_updates | 101300 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000145 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1381 | +| iterations | 21372 | +| time_elapsed | 31674 | +| total_timesteps | 43769856 | +| train/ | | +| approx_kl | 0.009865206 | +| clip_fraction | 0.326 | +| clip_range | 0.0641 | +| entropy_loss | -6.08 | +| explained_variance | 0.204 | +| learning_rate | 3.96e-05 | +| loss | -0.0226 | +| n_updates | 101304 | +| policy_gradient_loss | -0.0148 | +| value_loss | 0.000212 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1381 | +| iterations | 21373 | +| time_elapsed | 31676 | +| total_timesteps | 43771904 | +| train/ | | +| approx_kl | 0.01146044 | +| clip_fraction | 0.314 | +| clip_range | 0.0641 | +| entropy_loss | -5.62 | +| explained_variance | 0.711 | +| learning_rate | 3.96e-05 | +| loss | -0.0253 | +| n_updates | 101308 | +| policy_gradient_loss | -0.0175 | +| value_loss | 9.22e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1381 | +| iterations | 21374 | +| time_elapsed | 31677 | +| total_timesteps | 43773952 | +| train/ | | +| approx_kl | 0.010662014 | +| clip_fraction | 0.31 | +| clip_range | 0.0641 | +| entropy_loss | -6.06 | +| explained_variance | 0.41 | +| learning_rate | 3.96e-05 | +| loss | -0.0238 | +| n_updates | 101312 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.000233 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1381 | +| iterations | 21375 | +| time_elapsed | 31679 | +| total_timesteps | 43776000 | +| train/ | | +| approx_kl | 0.010400977 | +| clip_fraction | 0.356 | +| clip_range | 0.0641 | +| entropy_loss | -5.8 | +| explained_variance | -0.118 | +| learning_rate | 3.96e-05 | +| loss | -0.0333 | +| n_updates | 101316 | +| policy_gradient_loss | -0.0201 | +| value_loss | 9.41e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1381 | +| iterations | 21376 | +| time_elapsed | 31680 | +| total_timesteps | 43778048 | +| train/ | | +| approx_kl | 0.011466311 | +| clip_fraction | 0.332 | +| clip_range | 0.0641 | +| entropy_loss | -5.88 | +| explained_variance | 0.389 | +| learning_rate | 3.96e-05 | +| loss | -0.0286 | +| n_updates | 101320 | +| policy_gradient_loss | -0.0172 | +| value_loss | 9.2e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.347 | +| time/ | | +| fps | 1381 | +| iterations | 21377 | +| time_elapsed | 31682 | +| total_timesteps | 43780096 | +| train/ | | +| approx_kl | 0.0093369195 | +| clip_fraction | 0.278 | +| clip_range | 0.0641 | +| entropy_loss | -6.36 | +| explained_variance | 0.27 | +| learning_rate | 3.96e-05 | +| loss | -0.0223 | +| n_updates | 101324 | +| policy_gradient_loss | -0.0135 | +| value_loss | 0.000195 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1381 | +| iterations | 21378 | +| time_elapsed | 31683 | +| total_timesteps | 43782144 | +| train/ | | +| approx_kl | 0.00918944 | +| clip_fraction | 0.276 | +| clip_range | 0.0641 | +| entropy_loss | -6 | +| explained_variance | 0.327 | +| learning_rate | 3.96e-05 | +| loss | -0.0265 | +| n_updates | 101328 | +| policy_gradient_loss | -0.0142 | +| value_loss | 0.000302 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1381 | +| iterations | 21379 | +| time_elapsed | 31684 | +| total_timesteps | 43784192 | +| train/ | | +| approx_kl | 0.009533407 | +| clip_fraction | 0.33 | +| clip_range | 0.0641 | +| entropy_loss | -5.46 | +| explained_variance | 0.615 | +| learning_rate | 3.96e-05 | +| loss | -0.0251 | +| n_updates | 101332 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000137 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1381 | +| iterations | 21380 | +| time_elapsed | 31686 | +| total_timesteps | 43786240 | +| train/ | | +| approx_kl | 0.011782382 | +| clip_fraction | 0.321 | +| clip_range | 0.0641 | +| entropy_loss | -5.35 | +| explained_variance | 0.513 | +| learning_rate | 3.96e-05 | +| loss | -0.0275 | +| n_updates | 101336 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000113 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1381 | +| iterations | 21381 | +| time_elapsed | 31687 | +| total_timesteps | 43788288 | +| train/ | | +| approx_kl | 0.013387786 | +| clip_fraction | 0.358 | +| clip_range | 0.0641 | +| entropy_loss | -5.76 | +| explained_variance | -0.152 | +| learning_rate | 3.96e-05 | +| loss | -0.0294 | +| n_updates | 101340 | +| policy_gradient_loss | -0.019 | +| value_loss | 9.29e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1381 | +| iterations | 21382 | +| time_elapsed | 31689 | +| total_timesteps | 43790336 | +| train/ | | +| approx_kl | 0.014159728 | +| clip_fraction | 0.357 | +| clip_range | 0.0641 | +| entropy_loss | -5.28 | +| explained_variance | 0.604 | +| learning_rate | 3.96e-05 | +| loss | -0.0295 | +| n_updates | 101344 | +| policy_gradient_loss | -0.0171 | +| value_loss | 8.56e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1381 | +| iterations | 21383 | +| time_elapsed | 31690 | +| total_timesteps | 43792384 | +| train/ | | +| approx_kl | 0.012969609 | +| clip_fraction | 0.352 | +| clip_range | 0.0641 | +| entropy_loss | -4.7 | +| explained_variance | 0.361 | +| learning_rate | 3.96e-05 | +| loss | -0.0296 | +| n_updates | 101348 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000129 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1381 | +| iterations | 21384 | +| time_elapsed | 31692 | +| total_timesteps | 43794432 | +| train/ | | +| approx_kl | 0.013955696 | +| clip_fraction | 0.349 | +| clip_range | 0.0641 | +| entropy_loss | -5.46 | +| explained_variance | 0.556 | +| learning_rate | 3.96e-05 | +| loss | -0.0286 | +| n_updates | 101352 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000113 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.346 | +| time/ | | +| fps | 1381 | +| iterations | 21385 | +| time_elapsed | 31693 | +| total_timesteps | 43796480 | +| train/ | | +| approx_kl | 0.014306545 | +| clip_fraction | 0.351 | +| clip_range | 0.0641 | +| entropy_loss | -5.74 | +| explained_variance | 0.00684 | +| learning_rate | 3.96e-05 | +| loss | -0.0305 | +| n_updates | 101356 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000119 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1381 | +| iterations | 21386 | +| time_elapsed | 31695 | +| total_timesteps | 43798528 | +| train/ | | +| approx_kl | 0.011351037 | +| clip_fraction | 0.303 | +| clip_range | 0.0641 | +| entropy_loss | -6.16 | +| explained_variance | 0.278 | +| learning_rate | 3.96e-05 | +| loss | -0.021 | +| n_updates | 101360 | +| policy_gradient_loss | -0.0139 | +| value_loss | 0.00026 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.352 | +| time/ | | +| fps | 1381 | +| iterations | 21387 | +| time_elapsed | 31696 | +| total_timesteps | 43800576 | +| train/ | | +| approx_kl | 0.01128336 | +| clip_fraction | 0.324 | +| clip_range | 0.0641 | +| entropy_loss | -5.7 | +| explained_variance | 0.343 | +| learning_rate | 3.96e-05 | +| loss | -0.0271 | +| n_updates | 101364 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000252 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1381 | +| iterations | 21388 | +| time_elapsed | 31698 | +| total_timesteps | 43802624 | +| train/ | | +| approx_kl | 0.012822535 | +| clip_fraction | 0.332 | +| clip_range | 0.064 | +| entropy_loss | -5.44 | +| explained_variance | 0.538 | +| learning_rate | 3.96e-05 | +| loss | -0.0201 | +| n_updates | 101368 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000235 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.355 | +| time/ | | +| fps | 1381 | +| iterations | 21389 | +| time_elapsed | 31699 | +| total_timesteps | 43804672 | +| train/ | | +| approx_kl | 0.01893069 | +| clip_fraction | 0.379 | +| clip_range | 0.064 | +| entropy_loss | -5.59 | +| explained_variance | 0.32 | +| learning_rate | 3.96e-05 | +| loss | -0.0328 | +| n_updates | 101372 | +| policy_gradient_loss | -0.0216 | +| value_loss | 9.62e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1381 | +| iterations | 21390 | +| time_elapsed | 31701 | +| total_timesteps | 43806720 | +| train/ | | +| approx_kl | 0.013702518 | +| clip_fraction | 0.35 | +| clip_range | 0.064 | +| entropy_loss | -6 | +| explained_variance | -0.144 | +| learning_rate | 3.96e-05 | +| loss | -0.0314 | +| n_updates | 101376 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.00012 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.356 | +| time/ | | +| fps | 1381 | +| iterations | 21391 | +| time_elapsed | 31702 | +| total_timesteps | 43808768 | +| train/ | | +| approx_kl | 0.014512362 | +| clip_fraction | 0.341 | +| clip_range | 0.064 | +| entropy_loss | -6 | +| explained_variance | 0.294 | +| learning_rate | 3.96e-05 | +| loss | -0.0303 | +| n_updates | 101380 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.35 | +| time/ | | +| fps | 1381 | +| iterations | 21392 | +| time_elapsed | 31704 | +| total_timesteps | 43810816 | +| train/ | | +| approx_kl | 0.013392403 | +| clip_fraction | 0.319 | +| clip_range | 0.064 | +| entropy_loss | -5.25 | +| explained_variance | 0.374 | +| learning_rate | 3.96e-05 | +| loss | -0.0243 | +| n_updates | 101384 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000215 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.349 | +| time/ | | +| fps | 1381 | +| iterations | 21393 | +| time_elapsed | 31705 | +| total_timesteps | 43812864 | +| train/ | | +| approx_kl | 0.01043121 | +| clip_fraction | 0.318 | +| clip_range | 0.064 | +| entropy_loss | -5.36 | +| explained_variance | 0.474 | +| learning_rate | 3.96e-05 | +| loss | -0.0267 | +| n_updates | 101388 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.00014 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.353 | +| time/ | | +| fps | 1381 | +| iterations | 21394 | +| time_elapsed | 31707 | +| total_timesteps | 43814912 | +| train/ | | +| approx_kl | 0.010030077 | +| clip_fraction | 0.32 | +| clip_range | 0.064 | +| entropy_loss | -5.76 | +| explained_variance | 0.333 | +| learning_rate | 3.96e-05 | +| loss | -0.0251 | +| n_updates | 101392 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000154 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1381 | +| iterations | 21395 | +| time_elapsed | 31708 | +| total_timesteps | 43816960 | +| train/ | | +| approx_kl | 0.010760327 | +| clip_fraction | 0.311 | +| clip_range | 0.064 | +| entropy_loss | -5.08 | +| explained_variance | 0.353 | +| learning_rate | 3.96e-05 | +| loss | -0.0221 | +| n_updates | 101396 | +| policy_gradient_loss | -0.0128 | +| value_loss | 0.000252 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.357 | +| time/ | | +| fps | 1381 | +| iterations | 21396 | +| time_elapsed | 31709 | +| total_timesteps | 43819008 | +| train/ | | +| approx_kl | 0.00954995 | +| clip_fraction | 0.299 | +| clip_range | 0.064 | +| entropy_loss | -6.07 | +| explained_variance | 0.277 | +| learning_rate | 3.96e-05 | +| loss | -0.0244 | +| n_updates | 101400 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000169 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.354 | +| time/ | | +| fps | 1381 | +| iterations | 21397 | +| time_elapsed | 31711 | +| total_timesteps | 43821056 | +| train/ | | +| approx_kl | 0.010366131 | +| clip_fraction | 0.31 | +| clip_range | 0.064 | +| entropy_loss | -6.15 | +| explained_variance | -0.205 | +| learning_rate | 3.96e-05 | +| loss | -0.0279 | +| n_updates | 101404 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.00016 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1381 | +| iterations | 21398 | +| time_elapsed | 31712 | +| total_timesteps | 43823104 | +| train/ | | +| approx_kl | 0.01132006 | +| clip_fraction | 0.296 | +| clip_range | 0.064 | +| entropy_loss | -6.4 | +| explained_variance | 0.29 | +| learning_rate | 3.96e-05 | +| loss | -0.0226 | +| n_updates | 101408 | +| policy_gradient_loss | -0.0147 | +| value_loss | 0.000107 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.344 | +| time/ | | +| fps | 1381 | +| iterations | 21399 | +| time_elapsed | 31714 | +| total_timesteps | 43825152 | +| train/ | | +| approx_kl | 0.009358121 | +| clip_fraction | 0.306 | +| clip_range | 0.064 | +| entropy_loss | -5.65 | +| explained_variance | 0.324 | +| learning_rate | 3.96e-05 | +| loss | -0.0226 | +| n_updates | 101412 | +| policy_gradient_loss | -0.0142 | +| value_loss | 0.000262 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.345 | +| time/ | | +| fps | 1381 | +| iterations | 21400 | +| time_elapsed | 31715 | +| total_timesteps | 43827200 | +| train/ | | +| approx_kl | 0.008968454 | +| clip_fraction | 0.302 | +| clip_range | 0.064 | +| entropy_loss | -5.39 | +| explained_variance | 0.45 | +| learning_rate | 3.96e-05 | +| loss | -0.0182 | +| n_updates | 101416 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.000245 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.343 | +| time/ | | +| fps | 1381 | +| iterations | 21401 | +| time_elapsed | 31717 | +| total_timesteps | 43829248 | +| train/ | | +| approx_kl | 0.014051044 | +| clip_fraction | 0.323 | +| clip_range | 0.064 | +| entropy_loss | -5.72 | +| explained_variance | 0.186 | +| learning_rate | 3.96e-05 | +| loss | -0.0259 | +| n_updates | 101420 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000258 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.34 | +| time/ | | +| fps | 1381 | +| iterations | 21402 | +| time_elapsed | 31718 | +| total_timesteps | 43831296 | +| train/ | | +| approx_kl | 0.013893807 | +| clip_fraction | 0.348 | +| clip_range | 0.064 | +| entropy_loss | -4.74 | +| explained_variance | 0.381 | +| learning_rate | 3.96e-05 | +| loss | -0.0319 | +| n_updates | 101424 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000173 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.337 | +| time/ | | +| fps | 1381 | +| iterations | 21403 | +| time_elapsed | 31720 | +| total_timesteps | 43833344 | +| train/ | | +| approx_kl | 0.013941037 | +| clip_fraction | 0.34 | +| clip_range | 0.064 | +| entropy_loss | -5.35 | +| explained_variance | 0.627 | +| learning_rate | 3.96e-05 | +| loss | -0.0268 | +| n_updates | 101428 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000116 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.339 | +| time/ | | +| fps | 1381 | +| iterations | 21404 | +| time_elapsed | 31721 | +| total_timesteps | 43835392 | +| train/ | | +| approx_kl | 0.017691169 | +| clip_fraction | 0.363 | +| clip_range | 0.064 | +| entropy_loss | -5.18 | +| explained_variance | 0.518 | +| learning_rate | 3.96e-05 | +| loss | -0.0389 | +| n_updates | 101432 | +| policy_gradient_loss | -0.0212 | +| value_loss | 7.54e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1381 | +| iterations | 21405 | +| time_elapsed | 31723 | +| total_timesteps | 43837440 | +| train/ | | +| approx_kl | 0.011310459 | +| clip_fraction | 0.34 | +| clip_range | 0.064 | +| entropy_loss | -6.1 | +| explained_variance | 0.00603 | +| learning_rate | 3.96e-05 | +| loss | -0.0229 | +| n_updates | 101436 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000362 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.335 | +| time/ | | +| fps | 1381 | +| iterations | 21406 | +| time_elapsed | 31724 | +| total_timesteps | 43839488 | +| train/ | | +| approx_kl | 0.010941465 | +| clip_fraction | 0.346 | +| clip_range | 0.064 | +| entropy_loss | -5.81 | +| explained_variance | 0.6 | +| learning_rate | 3.96e-05 | +| loss | -0.0351 | +| n_updates | 101440 | +| policy_gradient_loss | -0.0196 | +| value_loss | 8.85e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1381 | +| iterations | 21407 | +| time_elapsed | 31726 | +| total_timesteps | 43841536 | +| train/ | | +| approx_kl | 0.00973906 | +| clip_fraction | 0.327 | +| clip_range | 0.064 | +| entropy_loss | -5.19 | +| explained_variance | 0.518 | +| learning_rate | 3.96e-05 | +| loss | -0.0248 | +| n_updates | 101444 | +| policy_gradient_loss | -0.0143 | +| value_loss | 0.000289 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1381 | +| iterations | 21408 | +| time_elapsed | 31727 | +| total_timesteps | 43843584 | +| train/ | | +| approx_kl | 0.012180215 | +| clip_fraction | 0.335 | +| clip_range | 0.064 | +| entropy_loss | -5.3 | +| explained_variance | 0.395 | +| learning_rate | 3.96e-05 | +| loss | -0.0263 | +| n_updates | 101448 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000224 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1381 | +| iterations | 21409 | +| time_elapsed | 31728 | +| total_timesteps | 43845632 | +| train/ | | +| approx_kl | 0.012570749 | +| clip_fraction | 0.339 | +| clip_range | 0.064 | +| entropy_loss | -5.14 | +| explained_variance | 0.408 | +| learning_rate | 3.96e-05 | +| loss | -0.029 | +| n_updates | 101452 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000207 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1381 | +| iterations | 21410 | +| time_elapsed | 31730 | +| total_timesteps | 43847680 | +| train/ | | +| approx_kl | 0.011386555 | +| clip_fraction | 0.348 | +| clip_range | 0.064 | +| entropy_loss | -6 | +| explained_variance | 0.228 | +| learning_rate | 3.96e-05 | +| loss | -0.0286 | +| n_updates | 101456 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000222 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1381 | +| iterations | 21411 | +| time_elapsed | 31731 | +| total_timesteps | 43849728 | +| train/ | | +| approx_kl | 0.013848698 | +| clip_fraction | 0.348 | +| clip_range | 0.064 | +| entropy_loss | -5.51 | +| explained_variance | 0.636 | +| learning_rate | 3.96e-05 | +| loss | -0.0304 | +| n_updates | 101460 | +| policy_gradient_loss | -0.019 | +| value_loss | 9.3e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1381 | +| iterations | 21412 | +| time_elapsed | 31733 | +| total_timesteps | 43851776 | +| train/ | | +| approx_kl | 0.012929449 | +| clip_fraction | 0.342 | +| clip_range | 0.064 | +| entropy_loss | -6.05 | +| explained_variance | -0.213 | +| learning_rate | 3.96e-05 | +| loss | -0.0315 | +| n_updates | 101464 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000115 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1381 | +| iterations | 21413 | +| time_elapsed | 31734 | +| total_timesteps | 43853824 | +| train/ | | +| approx_kl | 0.013511859 | +| clip_fraction | 0.325 | +| clip_range | 0.064 | +| entropy_loss | -6.17 | +| explained_variance | 0.376 | +| learning_rate | 3.96e-05 | +| loss | -0.0267 | +| n_updates | 101468 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000111 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.326 | +| time/ | | +| fps | 1381 | +| iterations | 21414 | +| time_elapsed | 31736 | +| total_timesteps | 43855872 | +| train/ | | +| approx_kl | 0.012953313 | +| clip_fraction | 0.334 | +| clip_range | 0.064 | +| entropy_loss | -5.82 | +| explained_variance | 0.402 | +| learning_rate | 3.96e-05 | +| loss | -0.0282 | +| n_updates | 101472 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000106 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1381 | +| iterations | 21415 | +| time_elapsed | 31737 | +| total_timesteps | 43857920 | +| train/ | | +| approx_kl | 0.008366829 | +| clip_fraction | 0.296 | +| clip_range | 0.064 | +| entropy_loss | -6.24 | +| explained_variance | 0.437 | +| learning_rate | 3.96e-05 | +| loss | -0.0276 | +| n_updates | 101476 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000133 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1381 | +| iterations | 21416 | +| time_elapsed | 31739 | +| total_timesteps | 43859968 | +| train/ | | +| approx_kl | 0.010206868 | +| clip_fraction | 0.303 | +| clip_range | 0.064 | +| entropy_loss | -5.91 | +| explained_variance | 0.569 | +| learning_rate | 3.96e-05 | +| loss | -0.0241 | +| n_updates | 101480 | +| policy_gradient_loss | -0.0146 | +| value_loss | 0.000136 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1381 | +| iterations | 21417 | +| time_elapsed | 31740 | +| total_timesteps | 43862016 | +| train/ | | +| approx_kl | 0.00913116 | +| clip_fraction | 0.304 | +| clip_range | 0.064 | +| entropy_loss | -5.57 | +| explained_variance | 0.546 | +| learning_rate | 3.96e-05 | +| loss | -0.03 | +| n_updates | 101484 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000274 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1381 | +| iterations | 21418 | +| time_elapsed | 31741 | +| total_timesteps | 43864064 | +| train/ | | +| approx_kl | 0.013085216 | +| clip_fraction | 0.367 | +| clip_range | 0.064 | +| entropy_loss | -5.3 | +| explained_variance | -0.276 | +| learning_rate | 3.96e-05 | +| loss | -0.0319 | +| n_updates | 101488 | +| policy_gradient_loss | -0.0212 | +| value_loss | 5.65e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1381 | +| iterations | 21419 | +| time_elapsed | 31743 | +| total_timesteps | 43866112 | +| train/ | | +| approx_kl | 0.012120335 | +| clip_fraction | 0.337 | +| clip_range | 0.064 | +| entropy_loss | -5.4 | +| explained_variance | 0.612 | +| learning_rate | 3.96e-05 | +| loss | -0.0257 | +| n_updates | 101492 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000118 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1381 | +| iterations | 21420 | +| time_elapsed | 31744 | +| total_timesteps | 43868160 | +| train/ | | +| approx_kl | 0.014081214 | +| clip_fraction | 0.381 | +| clip_range | 0.064 | +| entropy_loss | -5.68 | +| explained_variance | 0.23 | +| learning_rate | 3.96e-05 | +| loss | -0.0352 | +| n_updates | 101496 | +| policy_gradient_loss | -0.0228 | +| value_loss | 4.08e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1381 | +| iterations | 21421 | +| time_elapsed | 31746 | +| total_timesteps | 43870208 | +| train/ | | +| approx_kl | 0.009359846 | +| clip_fraction | 0.325 | +| clip_range | 0.064 | +| entropy_loss | -5.96 | +| explained_variance | 0.524 | +| learning_rate | 3.96e-05 | +| loss | -0.0233 | +| n_updates | 101500 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000151 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1381 | +| iterations | 21422 | +| time_elapsed | 31747 | +| total_timesteps | 43872256 | +| train/ | | +| approx_kl | 0.01124026 | +| clip_fraction | 0.292 | +| clip_range | 0.064 | +| entropy_loss | -6.04 | +| explained_variance | 0.344 | +| learning_rate | 3.96e-05 | +| loss | -0.0231 | +| n_updates | 101504 | +| policy_gradient_loss | -0.0138 | +| value_loss | 0.000118 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1381 | +| iterations | 21423 | +| time_elapsed | 31749 | +| total_timesteps | 43874304 | +| train/ | | +| approx_kl | 0.012465099 | +| clip_fraction | 0.337 | +| clip_range | 0.064 | +| entropy_loss | -6.05 | +| explained_variance | 0.569 | +| learning_rate | 3.96e-05 | +| loss | -0.036 | +| n_updates | 101508 | +| policy_gradient_loss | -0.0188 | +| value_loss | 5.24e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1381 | +| iterations | 21424 | +| time_elapsed | 31750 | +| total_timesteps | 43876352 | +| train/ | | +| approx_kl | 0.010721158 | +| clip_fraction | 0.337 | +| clip_range | 0.064 | +| entropy_loss | -6.2 | +| explained_variance | -0.23 | +| learning_rate | 3.96e-05 | +| loss | -0.0304 | +| n_updates | 101512 | +| policy_gradient_loss | -0.0181 | +| value_loss | 6.65e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1381 | +| iterations | 21425 | +| time_elapsed | 31752 | +| total_timesteps | 43878400 | +| train/ | | +| approx_kl | 0.009282928 | +| clip_fraction | 0.29 | +| clip_range | 0.064 | +| entropy_loss | -5.46 | +| explained_variance | 0.541 | +| learning_rate | 3.96e-05 | +| loss | -0.0158 | +| n_updates | 101516 | +| policy_gradient_loss | -0.0128 | +| value_loss | 0.00025 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1381 | +| iterations | 21426 | +| time_elapsed | 31753 | +| total_timesteps | 43880448 | +| train/ | | +| approx_kl | 0.016740754 | +| clip_fraction | 0.332 | +| clip_range | 0.064 | +| entropy_loss | -4.34 | +| explained_variance | 0.752 | +| learning_rate | 3.96e-05 | +| loss | -0.0245 | +| n_updates | 101520 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000102 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1381 | +| iterations | 21427 | +| time_elapsed | 31755 | +| total_timesteps | 43882496 | +| train/ | | +| approx_kl | 0.014615424 | +| clip_fraction | 0.347 | +| clip_range | 0.064 | +| entropy_loss | -5.15 | +| explained_variance | 0.58 | +| learning_rate | 3.96e-05 | +| loss | -0.0366 | +| n_updates | 101524 | +| policy_gradient_loss | -0.0209 | +| value_loss | 5.28e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.319 | +| time/ | | +| fps | 1381 | +| iterations | 21428 | +| time_elapsed | 31756 | +| total_timesteps | 43884544 | +| train/ | | +| approx_kl | 0.013818075 | +| clip_fraction | 0.325 | +| clip_range | 0.064 | +| entropy_loss | -6.11 | +| explained_variance | -0.0578 | +| learning_rate | 3.96e-05 | +| loss | -0.0296 | +| n_updates | 101528 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000103 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1381 | +| iterations | 21429 | +| time_elapsed | 31758 | +| total_timesteps | 43886592 | +| train/ | | +| approx_kl | 0.01639798 | +| clip_fraction | 0.343 | +| clip_range | 0.064 | +| entropy_loss | -5.84 | +| explained_variance | 0.395 | +| learning_rate | 3.96e-05 | +| loss | -0.0274 | +| n_updates | 101532 | +| policy_gradient_loss | -0.0176 | +| value_loss | 9.67e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1381 | +| iterations | 21430 | +| time_elapsed | 31759 | +| total_timesteps | 43888640 | +| train/ | | +| approx_kl | 0.013188658 | +| clip_fraction | 0.323 | +| clip_range | 0.064 | +| entropy_loss | -5.48 | +| explained_variance | 0.22 | +| learning_rate | 3.96e-05 | +| loss | -0.0264 | +| n_updates | 101536 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.000179 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1381 | +| iterations | 21431 | +| time_elapsed | 31761 | +| total_timesteps | 43890688 | +| train/ | | +| approx_kl | 0.010142174 | +| clip_fraction | 0.318 | +| clip_range | 0.064 | +| entropy_loss | -6.01 | +| explained_variance | 0.146 | +| learning_rate | 3.96e-05 | +| loss | -0.0304 | +| n_updates | 101540 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000103 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1381 | +| iterations | 21432 | +| time_elapsed | 31762 | +| total_timesteps | 43892736 | +| train/ | | +| approx_kl | 0.011631919 | +| clip_fraction | 0.328 | +| clip_range | 0.064 | +| entropy_loss | -5.69 | +| explained_variance | 0.53 | +| learning_rate | 3.96e-05 | +| loss | -0.0298 | +| n_updates | 101544 | +| policy_gradient_loss | -0.0165 | +| value_loss | 9.62e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1381 | +| iterations | 21433 | +| time_elapsed | 31763 | +| total_timesteps | 43894784 | +| train/ | | +| approx_kl | 0.012217966 | +| clip_fraction | 0.334 | +| clip_range | 0.064 | +| entropy_loss | -5.83 | +| explained_variance | 0.309 | +| learning_rate | 3.96e-05 | +| loss | -0.0255 | +| n_updates | 101548 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000114 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.308 | +| time/ | | +| fps | 1381 | +| iterations | 21434 | +| time_elapsed | 31765 | +| total_timesteps | 43896832 | +| train/ | | +| approx_kl | 0.013999306 | +| clip_fraction | 0.345 | +| clip_range | 0.064 | +| entropy_loss | -5.98 | +| explained_variance | 0.549 | +| learning_rate | 3.96e-05 | +| loss | -0.0271 | +| n_updates | 101552 | +| policy_gradient_loss | -0.0185 | +| value_loss | 6.7e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1381 | +| iterations | 21435 | +| time_elapsed | 31766 | +| total_timesteps | 43898880 | +| train/ | | +| approx_kl | 0.01104657 | +| clip_fraction | 0.269 | +| clip_range | 0.064 | +| entropy_loss | -5.27 | +| explained_variance | 0.667 | +| learning_rate | 3.96e-05 | +| loss | -0.0194 | +| n_updates | 101556 | +| policy_gradient_loss | -0.014 | +| value_loss | 0.000147 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1381 | +| iterations | 21436 | +| time_elapsed | 31768 | +| total_timesteps | 43900928 | +| train/ | | +| approx_kl | 0.014246669 | +| clip_fraction | 0.355 | +| clip_range | 0.064 | +| entropy_loss | -5.63 | +| explained_variance | 0.687 | +| learning_rate | 3.96e-05 | +| loss | -0.0296 | +| n_updates | 101560 | +| policy_gradient_loss | -0.0191 | +| value_loss | 5.73e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1381 | +| iterations | 21437 | +| time_elapsed | 31769 | +| total_timesteps | 43902976 | +| train/ | | +| approx_kl | 0.012770351 | +| clip_fraction | 0.332 | +| clip_range | 0.064 | +| entropy_loss | -5.65 | +| explained_variance | 0.363 | +| learning_rate | 3.96e-05 | +| loss | -0.0282 | +| n_updates | 101564 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000139 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.311 | +| time/ | | +| fps | 1381 | +| iterations | 21438 | +| time_elapsed | 31771 | +| total_timesteps | 43905024 | +| train/ | | +| approx_kl | 0.012534589 | +| clip_fraction | 0.318 | +| clip_range | 0.064 | +| entropy_loss | -5.92 | +| explained_variance | -0.0929 | +| learning_rate | 3.96e-05 | +| loss | -0.0267 | +| n_updates | 101568 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000121 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1381 | +| iterations | 21439 | +| time_elapsed | 31772 | +| total_timesteps | 43907072 | +| train/ | | +| approx_kl | 0.011832695 | +| clip_fraction | 0.338 | +| clip_range | 0.064 | +| entropy_loss | -6.49 | +| explained_variance | 0.357 | +| learning_rate | 3.96e-05 | +| loss | -0.027 | +| n_updates | 101572 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000196 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1381 | +| iterations | 21440 | +| time_elapsed | 31774 | +| total_timesteps | 43909120 | +| train/ | | +| approx_kl | 0.010414277 | +| clip_fraction | 0.323 | +| clip_range | 0.064 | +| entropy_loss | -5.71 | +| explained_variance | 0.683 | +| learning_rate | 3.96e-05 | +| loss | -0.0305 | +| n_updates | 101576 | +| policy_gradient_loss | -0.0166 | +| value_loss | 8.37e-05 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1381 | +| iterations | 21441 | +| time_elapsed | 31775 | +| total_timesteps | 43911168 | +| train/ | | +| approx_kl | 0.0136524215 | +| clip_fraction | 0.319 | +| clip_range | 0.064 | +| entropy_loss | -4.71 | +| explained_variance | 0.537 | +| learning_rate | 3.96e-05 | +| loss | -0.0179 | +| n_updates | 101580 | +| policy_gradient_loss | -0.0127 | +| value_loss | 0.000182 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1381 | +| iterations | 21442 | +| time_elapsed | 31777 | +| total_timesteps | 43913216 | +| train/ | | +| approx_kl | 0.012831211 | +| clip_fraction | 0.315 | +| clip_range | 0.064 | +| entropy_loss | -4.81 | +| explained_variance | 0.649 | +| learning_rate | 3.96e-05 | +| loss | -0.0251 | +| n_updates | 101584 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000136 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1381 | +| iterations | 21443 | +| time_elapsed | 31778 | +| total_timesteps | 43915264 | +| train/ | | +| approx_kl | 0.017076237 | +| clip_fraction | 0.306 | +| clip_range | 0.064 | +| entropy_loss | -5.44 | +| explained_variance | 0.508 | +| learning_rate | 3.96e-05 | +| loss | -0.0253 | +| n_updates | 101588 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000146 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.31 | +| time/ | | +| fps | 1381 | +| iterations | 21444 | +| time_elapsed | 31780 | +| total_timesteps | 43917312 | +| train/ | | +| approx_kl | 0.010598757 | +| clip_fraction | 0.32 | +| clip_range | 0.064 | +| entropy_loss | -5.95 | +| explained_variance | 0.265 | +| learning_rate | 3.96e-05 | +| loss | -0.0247 | +| n_updates | 101592 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000172 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1381 | +| iterations | 21445 | +| time_elapsed | 31781 | +| total_timesteps | 43919360 | +| train/ | | +| approx_kl | 0.009986394 | +| clip_fraction | 0.326 | +| clip_range | 0.064 | +| entropy_loss | -6.48 | +| explained_variance | -0.0816 | +| learning_rate | 3.96e-05 | +| loss | -0.0264 | +| n_updates | 101596 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000125 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1381 | +| iterations | 21446 | +| time_elapsed | 31783 | +| total_timesteps | 43921408 | +| train/ | | +| approx_kl | 0.0093152635 | +| clip_fraction | 0.315 | +| clip_range | 0.064 | +| entropy_loss | -6.18 | +| explained_variance | 0.406 | +| learning_rate | 3.96e-05 | +| loss | -0.0258 | +| n_updates | 101600 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000137 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1381 | +| iterations | 21447 | +| time_elapsed | 31784 | +| total_timesteps | 43923456 | +| train/ | | +| approx_kl | 0.008898761 | +| clip_fraction | 0.305 | +| clip_range | 0.064 | +| entropy_loss | -5.7 | +| explained_variance | 0.378 | +| learning_rate | 3.96e-05 | +| loss | -0.0223 | +| n_updates | 101604 | +| policy_gradient_loss | -0.0136 | +| value_loss | 0.000346 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1381 | +| iterations | 21448 | +| time_elapsed | 31786 | +| total_timesteps | 43925504 | +| train/ | | +| approx_kl | 0.009771613 | +| clip_fraction | 0.302 | +| clip_range | 0.064 | +| entropy_loss | -5.27 | +| explained_variance | 0.288 | +| learning_rate | 3.96e-05 | +| loss | -0.0186 | +| n_updates | 101608 | +| policy_gradient_loss | -0.013 | +| value_loss | 0.000431 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1381 | +| iterations | 21449 | +| time_elapsed | 31787 | +| total_timesteps | 43927552 | +| train/ | | +| approx_kl | 0.012326343 | +| clip_fraction | 0.334 | +| clip_range | 0.064 | +| entropy_loss | -4.84 | +| explained_variance | 0.53 | +| learning_rate | 3.96e-05 | +| loss | -0.0296 | +| n_updates | 101612 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000187 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1381 | +| iterations | 21450 | +| time_elapsed | 31789 | +| total_timesteps | 43929600 | +| train/ | | +| approx_kl | 0.0152305495 | +| clip_fraction | 0.338 | +| clip_range | 0.064 | +| entropy_loss | -5.35 | +| explained_variance | 0.501 | +| learning_rate | 3.96e-05 | +| loss | -0.0372 | +| n_updates | 101616 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000141 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.321 | +| time/ | | +| fps | 1381 | +| iterations | 21451 | +| time_elapsed | 31790 | +| total_timesteps | 43931648 | +| train/ | | +| approx_kl | 0.009026073 | +| clip_fraction | 0.318 | +| clip_range | 0.064 | +| entropy_loss | -6.27 | +| explained_variance | 0.269 | +| learning_rate | 3.96e-05 | +| loss | -0.0229 | +| n_updates | 101620 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000235 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1381 | +| iterations | 21452 | +| time_elapsed | 31792 | +| total_timesteps | 43933696 | +| train/ | | +| approx_kl | 0.013092721 | +| clip_fraction | 0.336 | +| clip_range | 0.064 | +| entropy_loss | -6.17 | +| explained_variance | 0.549 | +| learning_rate | 3.96e-05 | +| loss | -0.033 | +| n_updates | 101624 | +| policy_gradient_loss | -0.0192 | +| value_loss | 7.29e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1381 | +| iterations | 21453 | +| time_elapsed | 31793 | +| total_timesteps | 43935744 | +| train/ | | +| approx_kl | 0.010375496 | +| clip_fraction | 0.296 | +| clip_range | 0.064 | +| entropy_loss | -5.85 | +| explained_variance | 0.398 | +| learning_rate | 3.96e-05 | +| loss | -0.0229 | +| n_updates | 101628 | +| policy_gradient_loss | -0.0144 | +| value_loss | 0.000265 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1381 | +| iterations | 21454 | +| time_elapsed | 31795 | +| total_timesteps | 43937792 | +| train/ | | +| approx_kl | 0.015430182 | +| clip_fraction | 0.366 | +| clip_range | 0.064 | +| entropy_loss | -5.71 | +| explained_variance | 0.632 | +| learning_rate | 3.96e-05 | +| loss | -0.0368 | +| n_updates | 101632 | +| policy_gradient_loss | -0.0208 | +| value_loss | 8.91e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.324 | +| time/ | | +| fps | 1381 | +| iterations | 21455 | +| time_elapsed | 31796 | +| total_timesteps | 43939840 | +| train/ | | +| approx_kl | 0.015596481 | +| clip_fraction | 0.383 | +| clip_range | 0.064 | +| entropy_loss | -5.91 | +| explained_variance | -0.171 | +| learning_rate | 3.96e-05 | +| loss | -0.037 | +| n_updates | 101636 | +| policy_gradient_loss | -0.0222 | +| value_loss | 8.37e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.325 | +| time/ | | +| fps | 1381 | +| iterations | 21456 | +| time_elapsed | 31798 | +| total_timesteps | 43941888 | +| train/ | | +| approx_kl | 0.013380954 | +| clip_fraction | 0.342 | +| clip_range | 0.064 | +| entropy_loss | -6.14 | +| explained_variance | 0.482 | +| learning_rate | 3.96e-05 | +| loss | -0.0272 | +| n_updates | 101640 | +| policy_gradient_loss | -0.0189 | +| value_loss | 7.68e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.32 | +| time/ | | +| fps | 1381 | +| iterations | 21457 | +| time_elapsed | 31799 | +| total_timesteps | 43943936 | +| train/ | | +| approx_kl | 0.009529818 | +| clip_fraction | 0.311 | +| clip_range | 0.064 | +| entropy_loss | -6.05 | +| explained_variance | 0.63 | +| learning_rate | 3.96e-05 | +| loss | -0.028 | +| n_updates | 101644 | +| policy_gradient_loss | -0.0163 | +| value_loss | 9.81e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1381 | +| iterations | 21458 | +| time_elapsed | 31800 | +| total_timesteps | 43945984 | +| train/ | | +| approx_kl | 0.008739989 | +| clip_fraction | 0.286 | +| clip_range | 0.064 | +| entropy_loss | -5.44 | +| explained_variance | 0.608 | +| learning_rate | 3.96e-05 | +| loss | -0.0219 | +| n_updates | 101648 | +| policy_gradient_loss | -0.0135 | +| value_loss | 0.000192 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1381 | +| iterations | 21459 | +| time_elapsed | 31802 | +| total_timesteps | 43948032 | +| train/ | | +| approx_kl | 0.016853712 | +| clip_fraction | 0.315 | +| clip_range | 0.064 | +| entropy_loss | -5.14 | +| explained_variance | 0.538 | +| learning_rate | 3.96e-05 | +| loss | -0.0277 | +| n_updates | 101652 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000107 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1381 | +| iterations | 21460 | +| time_elapsed | 31803 | +| total_timesteps | 43950080 | +| train/ | | +| approx_kl | 0.015386505 | +| clip_fraction | 0.392 | +| clip_range | 0.064 | +| entropy_loss | -4.94 | +| explained_variance | 0.734 | +| learning_rate | 3.96e-05 | +| loss | -0.0336 | +| n_updates | 101656 | +| policy_gradient_loss | -0.0227 | +| value_loss | 4.75e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1381 | +| iterations | 21461 | +| time_elapsed | 31805 | +| total_timesteps | 43952128 | +| train/ | | +| approx_kl | 0.01624842 | +| clip_fraction | 0.349 | +| clip_range | 0.064 | +| entropy_loss | -5.66 | +| explained_variance | 0.331 | +| learning_rate | 3.96e-05 | +| loss | -0.025 | +| n_updates | 101660 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000163 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1381 | +| iterations | 21462 | +| time_elapsed | 31806 | +| total_timesteps | 43954176 | +| train/ | | +| approx_kl | 0.011946155 | +| clip_fraction | 0.333 | +| clip_range | 0.064 | +| entropy_loss | -5.88 | +| explained_variance | 0.388 | +| learning_rate | 3.96e-05 | +| loss | -0.0226 | +| n_updates | 101664 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.000118 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 1381 | +| iterations | 21463 | +| time_elapsed | 31808 | +| total_timesteps | 43956224 | +| train/ | | +| approx_kl | 0.011945242 | +| clip_fraction | 0.324 | +| clip_range | 0.064 | +| entropy_loss | -6.17 | +| explained_variance | 0.314 | +| learning_rate | 3.96e-05 | +| loss | -0.0214 | +| n_updates | 101668 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000147 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1381 | +| iterations | 21464 | +| time_elapsed | 31809 | +| total_timesteps | 43958272 | +| train/ | | +| approx_kl | 0.014423482 | +| clip_fraction | 0.334 | +| clip_range | 0.064 | +| entropy_loss | -5.52 | +| explained_variance | -0.0139 | +| learning_rate | 3.96e-05 | +| loss | -0.0286 | +| n_updates | 101672 | +| policy_gradient_loss | -0.0184 | +| value_loss | 5.22e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1381 | +| iterations | 21465 | +| time_elapsed | 31811 | +| total_timesteps | 43960320 | +| train/ | | +| approx_kl | 0.014669984 | +| clip_fraction | 0.311 | +| clip_range | 0.064 | +| entropy_loss | -5.36 | +| explained_variance | 0.381 | +| learning_rate | 3.96e-05 | +| loss | -0.0208 | +| n_updates | 101676 | +| policy_gradient_loss | -0.0143 | +| value_loss | 0.000231 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1381 | +| iterations | 21466 | +| time_elapsed | 31812 | +| total_timesteps | 43962368 | +| train/ | | +| approx_kl | 0.012709474 | +| clip_fraction | 0.34 | +| clip_range | 0.064 | +| entropy_loss | -5.93 | +| explained_variance | -0.133 | +| learning_rate | 3.96e-05 | +| loss | -0.0214 | +| n_updates | 101680 | +| policy_gradient_loss | -0.0172 | +| value_loss | 9.22e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.304 | +| time/ | | +| fps | 1381 | +| iterations | 21467 | +| time_elapsed | 31814 | +| total_timesteps | 43964416 | +| train/ | | +| approx_kl | 0.012975009 | +| clip_fraction | 0.295 | +| clip_range | 0.064 | +| entropy_loss | -6.05 | +| explained_variance | 0.288 | +| learning_rate | 3.96e-05 | +| loss | -0.0247 | +| n_updates | 101684 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.00013 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 1381 | +| iterations | 21468 | +| time_elapsed | 31815 | +| total_timesteps | 43966464 | +| train/ | | +| approx_kl | 0.013222967 | +| clip_fraction | 0.345 | +| clip_range | 0.064 | +| entropy_loss | -5.64 | +| explained_variance | 0.441 | +| learning_rate | 3.96e-05 | +| loss | -0.0318 | +| n_updates | 101688 | +| policy_gradient_loss | -0.0188 | +| value_loss | 9.32e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.305 | +| time/ | | +| fps | 1381 | +| iterations | 21469 | +| time_elapsed | 31817 | +| total_timesteps | 43968512 | +| train/ | | +| approx_kl | 0.013211912 | +| clip_fraction | 0.321 | +| clip_range | 0.064 | +| entropy_loss | -5.24 | +| explained_variance | 0.647 | +| learning_rate | 3.96e-05 | +| loss | -0.0226 | +| n_updates | 101692 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.000129 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.303 | +| time/ | | +| fps | 1381 | +| iterations | 21470 | +| time_elapsed | 31818 | +| total_timesteps | 43970560 | +| train/ | | +| approx_kl | 0.010870856 | +| clip_fraction | 0.306 | +| clip_range | 0.064 | +| entropy_loss | -5.84 | +| explained_variance | 0.358 | +| learning_rate | 3.96e-05 | +| loss | -0.025 | +| n_updates | 101696 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000113 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.307 | +| time/ | | +| fps | 1381 | +| iterations | 21471 | +| time_elapsed | 31819 | +| total_timesteps | 43972608 | +| train/ | | +| approx_kl | 0.0107910875 | +| clip_fraction | 0.321 | +| clip_range | 0.064 | +| entropy_loss | -6.38 | +| explained_variance | -0.0474 | +| learning_rate | 3.96e-05 | +| loss | -0.0259 | +| n_updates | 101700 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000208 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1381 | +| iterations | 21472 | +| time_elapsed | 31821 | +| total_timesteps | 43974656 | +| train/ | | +| approx_kl | 0.013890317 | +| clip_fraction | 0.321 | +| clip_range | 0.064 | +| entropy_loss | -6.07 | +| explained_variance | 0.428 | +| learning_rate | 3.96e-05 | +| loss | -0.0252 | +| n_updates | 101704 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000186 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1381 | +| iterations | 21473 | +| time_elapsed | 31822 | +| total_timesteps | 43976704 | +| train/ | | +| approx_kl | 0.01127538 | +| clip_fraction | 0.345 | +| clip_range | 0.064 | +| entropy_loss | -5.55 | +| explained_variance | 0.383 | +| learning_rate | 3.96e-05 | +| loss | -0.0262 | +| n_updates | 101708 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000268 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1381 | +| iterations | 21474 | +| time_elapsed | 31824 | +| total_timesteps | 43978752 | +| train/ | | +| approx_kl | 0.009822566 | +| clip_fraction | 0.33 | +| clip_range | 0.064 | +| entropy_loss | -5.94 | +| explained_variance | 0.201 | +| learning_rate | 3.96e-05 | +| loss | -0.0263 | +| n_updates | 101712 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000212 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.312 | +| time/ | | +| fps | 1381 | +| iterations | 21475 | +| time_elapsed | 31825 | +| total_timesteps | 43980800 | +| train/ | | +| approx_kl | 0.01264147 | +| clip_fraction | 0.371 | +| clip_range | 0.064 | +| entropy_loss | -5.77 | +| explained_variance | 0.672 | +| learning_rate | 3.96e-05 | +| loss | -0.0349 | +| n_updates | 101716 | +| policy_gradient_loss | -0.0221 | +| value_loss | 6.68e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.309 | +| time/ | | +| fps | 1381 | +| iterations | 21476 | +| time_elapsed | 31827 | +| total_timesteps | 43982848 | +| train/ | | +| approx_kl | 0.012317197 | +| clip_fraction | 0.32 | +| clip_range | 0.064 | +| entropy_loss | -5.9 | +| explained_variance | 0.559 | +| learning_rate | 3.96e-05 | +| loss | -0.027 | +| n_updates | 101720 | +| policy_gradient_loss | -0.0168 | +| value_loss | 9.72e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1381 | +| iterations | 21477 | +| time_elapsed | 31828 | +| total_timesteps | 43984896 | +| train/ | | +| approx_kl | 0.012495922 | +| clip_fraction | 0.329 | +| clip_range | 0.064 | +| entropy_loss | -5.38 | +| explained_variance | 0.652 | +| learning_rate | 3.96e-05 | +| loss | -0.0239 | +| n_updates | 101724 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000131 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.314 | +| time/ | | +| fps | 1381 | +| iterations | 21478 | +| time_elapsed | 31829 | +| total_timesteps | 43986944 | +| train/ | | +| approx_kl | 0.010987676 | +| clip_fraction | 0.323 | +| clip_range | 0.064 | +| entropy_loss | -5.19 | +| explained_variance | -0.0289 | +| learning_rate | 3.96e-05 | +| loss | -0.0281 | +| n_updates | 101728 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000158 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1381 | +| iterations | 21479 | +| time_elapsed | 31831 | +| total_timesteps | 43988992 | +| train/ | | +| approx_kl | 0.009909241 | +| clip_fraction | 0.31 | +| clip_range | 0.064 | +| entropy_loss | -6.15 | +| explained_variance | 0.238 | +| learning_rate | 3.96e-05 | +| loss | -0.0263 | +| n_updates | 101732 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000142 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1381 | +| iterations | 21480 | +| time_elapsed | 31832 | +| total_timesteps | 43991040 | +| train/ | | +| approx_kl | 0.011574214 | +| clip_fraction | 0.308 | +| clip_range | 0.064 | +| entropy_loss | -5.69 | +| explained_variance | 0.343 | +| learning_rate | 3.96e-05 | +| loss | -0.0217 | +| n_updates | 101736 | +| policy_gradient_loss | -0.0126 | +| value_loss | 0.000162 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.313 | +| time/ | | +| fps | 1381 | +| iterations | 21481 | +| time_elapsed | 31834 | +| total_timesteps | 43993088 | +| train/ | | +| approx_kl | 0.014492933 | +| clip_fraction | 0.323 | +| clip_range | 0.064 | +| entropy_loss | -5.57 | +| explained_variance | 0.521 | +| learning_rate | 3.96e-05 | +| loss | -0.026 | +| n_updates | 101740 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.000118 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.317 | +| time/ | | +| fps | 1381 | +| iterations | 21482 | +| time_elapsed | 31835 | +| total_timesteps | 43995136 | +| train/ | | +| approx_kl | 0.012434961 | +| clip_fraction | 0.304 | +| clip_range | 0.064 | +| entropy_loss | -5.46 | +| explained_variance | 0.617 | +| learning_rate | 3.96e-05 | +| loss | -0.0242 | +| n_updates | 101744 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1381 | +| iterations | 21483 | +| time_elapsed | 31837 | +| total_timesteps | 43997184 | +| train/ | | +| approx_kl | 0.012268098 | +| clip_fraction | 0.323 | +| clip_range | 0.064 | +| entropy_loss | -4.89 | +| explained_variance | 0.553 | +| learning_rate | 3.96e-05 | +| loss | -0.0236 | +| n_updates | 101748 | +| policy_gradient_loss | -0.0148 | +| value_loss | 0.000208 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1381 | +| iterations | 21484 | +| time_elapsed | 31838 | +| total_timesteps | 43999232 | +| train/ | | +| approx_kl | 0.018232351 | +| clip_fraction | 0.355 | +| clip_range | 0.064 | +| entropy_loss | -5.29 | +| explained_variance | 0.371 | +| learning_rate | 3.96e-05 | +| loss | -0.0283 | +| n_updates | 101752 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000114 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.316 | +| time/ | | +| fps | 1381 | +| iterations | 21485 | +| time_elapsed | 31840 | +| total_timesteps | 44001280 | +| train/ | | +| approx_kl | 0.011048408 | +| clip_fraction | 0.33 | +| clip_range | 0.064 | +| entropy_loss | -5.92 | +| explained_variance | -0.0378 | +| learning_rate | 3.96e-05 | +| loss | -0.0288 | +| n_updates | 101756 | +| policy_gradient_loss | -0.0152 | +| value_loss | 0.000175 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.318 | +| time/ | | +| fps | 1381 | +| iterations | 21486 | +| time_elapsed | 31841 | +| total_timesteps | 44003328 | +| train/ | | +| approx_kl | 0.011261177 | +| clip_fraction | 0.326 | +| clip_range | 0.064 | +| entropy_loss | -6.17 | +| explained_variance | -0.0225 | +| learning_rate | 3.95e-05 | +| loss | -0.0282 | +| n_updates | 101760 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000176 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.323 | +| time/ | | +| fps | 1381 | +| iterations | 21487 | +| time_elapsed | 31842 | +| total_timesteps | 44005376 | +| train/ | | +| approx_kl | 0.012491452 | +| clip_fraction | 0.3 | +| clip_range | 0.064 | +| entropy_loss | -5.34 | +| explained_variance | 0.447 | +| learning_rate | 3.95e-05 | +| loss | -0.0311 | +| n_updates | 101764 | +| policy_gradient_loss | -0.0144 | +| value_loss | 0.000157 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1381 | +| iterations | 21488 | +| time_elapsed | 31844 | +| total_timesteps | 44007424 | +| train/ | | +| approx_kl | 0.013945656 | +| clip_fraction | 0.355 | +| clip_range | 0.064 | +| entropy_loss | -5.74 | +| explained_variance | 0.212 | +| learning_rate | 3.95e-05 | +| loss | -0.0282 | +| n_updates | 101768 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000211 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1381 | +| iterations | 21489 | +| time_elapsed | 31845 | +| total_timesteps | 44009472 | +| train/ | | +| approx_kl | 0.010140875 | +| clip_fraction | 0.306 | +| clip_range | 0.064 | +| entropy_loss | -5.96 | +| explained_variance | 0.292 | +| learning_rate | 3.95e-05 | +| loss | -0.0274 | +| n_updates | 101772 | +| policy_gradient_loss | -0.0147 | +| value_loss | 0.000347 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.322 | +| time/ | | +| fps | 1381 | +| iterations | 21490 | +| time_elapsed | 31847 | +| total_timesteps | 44011520 | +| train/ | | +| approx_kl | 0.011367362 | +| clip_fraction | 0.317 | +| clip_range | 0.064 | +| entropy_loss | -6.45 | +| explained_variance | -0.0912 | +| learning_rate | 3.95e-05 | +| loss | -0.0267 | +| n_updates | 101776 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000158 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.328 | +| time/ | | +| fps | 1381 | +| iterations | 21491 | +| time_elapsed | 31848 | +| total_timesteps | 44013568 | +| train/ | | +| approx_kl | 0.009202281 | +| clip_fraction | 0.311 | +| clip_range | 0.064 | +| entropy_loss | -6.73 | +| explained_variance | 0.267 | +| learning_rate | 3.95e-05 | +| loss | -0.0284 | +| n_updates | 101780 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000146 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.33 | +| time/ | | +| fps | 1381 | +| iterations | 21492 | +| time_elapsed | 31850 | +| total_timesteps | 44015616 | +| train/ | | +| approx_kl | 0.01077048 | +| clip_fraction | 0.329 | +| clip_range | 0.064 | +| entropy_loss | -5.72 | +| explained_variance | 0.679 | +| learning_rate | 3.95e-05 | +| loss | -0.0267 | +| n_updates | 101784 | +| policy_gradient_loss | -0.0172 | +| value_loss | 8.7e-05 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.341 | +| time/ | | +| fps | 1381 | +| iterations | 21493 | +| time_elapsed | 31851 | +| total_timesteps | 44017664 | +| train/ | | +| approx_kl | 0.014131464 | +| clip_fraction | 0.326 | +| clip_range | 0.064 | +| entropy_loss | -5.41 | +| explained_variance | 0.642 | +| learning_rate | 3.95e-05 | +| loss | -0.0309 | +| n_updates | 101788 | +| policy_gradient_loss | -0.0164 | +| value_loss | 8.45e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.342 | +| time/ | | +| fps | 1381 | +| iterations | 21494 | +| time_elapsed | 31853 | +| total_timesteps | 44019712 | +| train/ | | +| approx_kl | 0.008228732 | +| clip_fraction | 0.295 | +| clip_range | 0.064 | +| entropy_loss | -4.88 | +| explained_variance | 0.424 | +| learning_rate | 3.95e-05 | +| loss | -0.0176 | +| n_updates | 101792 | +| policy_gradient_loss | -0.0113 | +| value_loss | 0.000402 | +----------------------------------------- diff --git a/006_rgb_stack_ram_based_reward_time_reward_final_round/trained_models_ryu_vs_bison_no_coef_no_time_reward/training_log.txt b/006_rgb_stack_ram_based_reward_time_reward_final_round/trained_models_ryu_vs_bison_no_coef_no_time_reward/training_log.txt new file mode 100644 index 0000000..24c64f1 --- /dev/null +++ b/006_rgb_stack_ram_based_reward_time_reward_final_round/trained_models_ryu_vs_bison_no_coef_no_time_reward/training_log.txt @@ -0,0 +1,12884 @@ +Logging to logs\PPO_4 +----------------------------- +| time/ | | +| fps | 1208 | +| iterations | 1 | +| time_elapsed | 1 | +| total_timesteps | 2048 | +----------------------------- +----------------------------------------- +| time/ | | +| fps | 1286 | +| iterations | 2 | +| time_elapsed | 3 | +| total_timesteps | 4096 | +| train/ | | +| approx_kl | 0.008637257 | +| clip_fraction | 0.263 | +| clip_range | 0.075 | +| entropy_loss | -3.48 | +| explained_variance | 0.828 | +| learning_rate | 5e-05 | +| loss | -0.0214 | +| n_updates | 35352 | +| policy_gradient_loss | -0.00886 | +| value_loss | 7.89e-05 | +----------------------------------------- +----------------------------------------- +| time/ | | +| fps | 1309 | +| iterations | 3 | +| time_elapsed | 4 | +| total_timesteps | 6144 | +| train/ | | +| approx_kl | 0.012750633 | +| clip_fraction | 0.297 | +| clip_range | 0.075 | +| entropy_loss | -7.24 | +| explained_variance | -0.133 | +| learning_rate | 5e-05 | +| loss | -0.0288 | +| n_updates | 35356 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000181 | +----------------------------------------- +----------------------------------------- +| time/ | | +| fps | 1313 | +| iterations | 4 | +| time_elapsed | 6 | +| total_timesteps | 8192 | +| train/ | | +| approx_kl | 0.012273455 | +| clip_fraction | 0.311 | +| clip_range | 0.075 | +| entropy_loss | -7.33 | +| explained_variance | -0.142 | +| learning_rate | 5e-05 | +| loss | -0.0308 | +| n_updates | 35360 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.0003 | +----------------------------------------- +---------------------------------------- +| time/ | | +| fps | 1301 | +| iterations | 5 | +| time_elapsed | 7 | +| total_timesteps | 10240 | +| train/ | | +| approx_kl | 0.01382168 | +| clip_fraction | 0.288 | +| clip_range | 0.075 | +| entropy_loss | -7.39 | +| explained_variance | -0.0349 | +| learning_rate | 5e-05 | +| loss | -0.0295 | +| n_updates | 35364 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000226 | +---------------------------------------- +----------------------------------------- +| time/ | | +| fps | 1307 | +| iterations | 6 | +| time_elapsed | 9 | +| total_timesteps | 12288 | +| train/ | | +| approx_kl | 0.011477925 | +| clip_fraction | 0.313 | +| clip_range | 0.075 | +| entropy_loss | -7.54 | +| explained_variance | -0.0444 | +| learning_rate | 5e-05 | +| loss | -0.0337 | +| n_updates | 35368 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000308 | +----------------------------------------- +----------------------------------------- +| time/ | | +| fps | 1298 | +| iterations | 7 | +| time_elapsed | 11 | +| total_timesteps | 14336 | +| train/ | | +| approx_kl | 0.012032962 | +| clip_fraction | 0.332 | +| clip_range | 0.075 | +| entropy_loss | -7.39 | +| explained_variance | -0.0174 | +| learning_rate | 5e-05 | +| loss | -0.0327 | +| n_updates | 35372 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000325 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 983 | +| ep_rew_mean | 0.0286 | +| time/ | | +| fps | 1298 | +| iterations | 8 | +| time_elapsed | 12 | +| total_timesteps | 16384 | +| train/ | | +| approx_kl | 0.0134359915 | +| clip_fraction | 0.312 | +| clip_range | 0.075 | +| entropy_loss | -7.43 | +| explained_variance | -0.127 | +| learning_rate | 5e-05 | +| loss | -0.0319 | +| n_updates | 35376 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000328 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.04e+03 | +| ep_rew_mean | 0.0537 | +| time/ | | +| fps | 1294 | +| iterations | 9 | +| time_elapsed | 14 | +| total_timesteps | 18432 | +| train/ | | +| approx_kl | 0.010892904 | +| clip_fraction | 0.324 | +| clip_range | 0.075 | +| entropy_loss | -7.26 | +| explained_variance | 0.0714 | +| learning_rate | 5e-05 | +| loss | -0.0326 | +| n_updates | 35380 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000207 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.07e+03 | +| ep_rew_mean | 0.000985 | +| time/ | | +| fps | 1291 | +| iterations | 10 | +| time_elapsed | 15 | +| total_timesteps | 20480 | +| train/ | | +| approx_kl | 0.012009218 | +| clip_fraction | 0.312 | +| clip_range | 0.075 | +| entropy_loss | -6.9 | +| explained_variance | 0.178 | +| learning_rate | 5e-05 | +| loss | -0.0329 | +| n_updates | 35384 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000239 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | 0.00577 | +| time/ | | +| fps | 1294 | +| iterations | 11 | +| time_elapsed | 17 | +| total_timesteps | 22528 | +| train/ | | +| approx_kl | 0.010798417 | +| clip_fraction | 0.294 | +| clip_range | 0.075 | +| entropy_loss | -7.1 | +| explained_variance | 0.394 | +| learning_rate | 5e-05 | +| loss | -0.0311 | +| n_updates | 35388 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000203 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | -0.0281 | +| time/ | | +| fps | 1294 | +| iterations | 12 | +| time_elapsed | 18 | +| total_timesteps | 24576 | +| train/ | | +| approx_kl | 0.009672813 | +| clip_fraction | 0.298 | +| clip_range | 0.075 | +| entropy_loss | -6.93 | +| explained_variance | 0.444 | +| learning_rate | 5e-05 | +| loss | -0.031 | +| n_updates | 35392 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000197 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | -0.0345 | +| time/ | | +| fps | 1296 | +| iterations | 13 | +| time_elapsed | 20 | +| total_timesteps | 26624 | +| train/ | | +| approx_kl | 0.011173179 | +| clip_fraction | 0.297 | +| clip_range | 0.075 | +| entropy_loss | -6.93 | +| explained_variance | 0.348 | +| learning_rate | 5e-05 | +| loss | -0.0239 | +| n_updates | 35396 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000244 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | -0.0361 | +| time/ | | +| fps | 1299 | +| iterations | 14 | +| time_elapsed | 22 | +| total_timesteps | 28672 | +| train/ | | +| approx_kl | 0.013024174 | +| clip_fraction | 0.31 | +| clip_range | 0.075 | +| entropy_loss | -6.58 | +| explained_variance | 0.676 | +| learning_rate | 5e-05 | +| loss | -0.0376 | +| n_updates | 35400 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000106 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | -0.0349 | +| time/ | | +| fps | 1303 | +| iterations | 15 | +| time_elapsed | 23 | +| total_timesteps | 30720 | +| train/ | | +| approx_kl | 0.011423709 | +| clip_fraction | 0.301 | +| clip_range | 0.075 | +| entropy_loss | -7.08 | +| explained_variance | 0.183 | +| learning_rate | 5e-05 | +| loss | -0.0288 | +| n_updates | 35404 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000239 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | -0.0349 | +| time/ | | +| fps | 1304 | +| iterations | 16 | +| time_elapsed | 25 | +| total_timesteps | 32768 | +| train/ | | +| approx_kl | 0.011740649 | +| clip_fraction | 0.304 | +| clip_range | 0.075 | +| entropy_loss | -7.04 | +| explained_variance | 0.259 | +| learning_rate | 5e-05 | +| loss | -0.0326 | +| n_updates | 35408 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.00035 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | -0.0349 | +| time/ | | +| fps | 1306 | +| iterations | 17 | +| time_elapsed | 26 | +| total_timesteps | 34816 | +| train/ | | +| approx_kl | 0.011826695 | +| clip_fraction | 0.316 | +| clip_range | 0.075 | +| entropy_loss | -7.33 | +| explained_variance | -0.0348 | +| learning_rate | 5e-05 | +| loss | -0.0348 | +| n_updates | 35412 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000216 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | -0.00746 | +| time/ | | +| fps | 1307 | +| iterations | 18 | +| time_elapsed | 28 | +| total_timesteps | 36864 | +| train/ | | +| approx_kl | 0.011875508 | +| clip_fraction | 0.316 | +| clip_range | 0.075 | +| entropy_loss | -7.52 | +| explained_variance | -0.173 | +| learning_rate | 5e-05 | +| loss | -0.0323 | +| n_updates | 35416 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000236 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | -0.00746 | +| time/ | | +| fps | 1308 | +| iterations | 19 | +| time_elapsed | 29 | +| total_timesteps | 38912 | +| train/ | | +| approx_kl | 0.010079924 | +| clip_fraction | 0.284 | +| clip_range | 0.075 | +| entropy_loss | -7.21 | +| explained_variance | 0.153 | +| learning_rate | 5e-05 | +| loss | -0.0315 | +| n_updates | 35420 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.00039 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | -0.00349 | +| time/ | | +| fps | 1310 | +| iterations | 20 | +| time_elapsed | 31 | +| total_timesteps | 40960 | +| train/ | | +| approx_kl | 0.011211742 | +| clip_fraction | 0.33 | +| clip_range | 0.075 | +| entropy_loss | -7.31 | +| explained_variance | 0.129 | +| learning_rate | 5e-05 | +| loss | -0.0347 | +| n_updates | 35424 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.00039 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.00856 | +| time/ | | +| fps | 1312 | +| iterations | 21 | +| time_elapsed | 32 | +| total_timesteps | 43008 | +| train/ | | +| approx_kl | 0.012231384 | +| clip_fraction | 0.315 | +| clip_range | 0.075 | +| entropy_loss | -6.82 | +| explained_variance | 0.586 | +| learning_rate | 5e-05 | +| loss | -0.0397 | +| n_updates | 35428 | +| policy_gradient_loss | -0.0229 | +| value_loss | 0.000116 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0115 | +| time/ | | +| fps | 1309 | +| iterations | 22 | +| time_elapsed | 34 | +| total_timesteps | 45056 | +| train/ | | +| approx_kl | 0.013433607 | +| clip_fraction | 0.321 | +| clip_range | 0.075 | +| entropy_loss | -6.61 | +| explained_variance | 0.462 | +| learning_rate | 5e-05 | +| loss | -0.0317 | +| n_updates | 35432 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000221 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0241 | +| time/ | | +| fps | 1310 | +| iterations | 23 | +| time_elapsed | 35 | +| total_timesteps | 47104 | +| train/ | | +| approx_kl | 0.013079792 | +| clip_fraction | 0.322 | +| clip_range | 0.075 | +| entropy_loss | -7.06 | +| explained_variance | 0.25 | +| learning_rate | 5e-05 | +| loss | -0.0329 | +| n_updates | 35436 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000226 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0341 | +| time/ | | +| fps | 1310 | +| iterations | 24 | +| time_elapsed | 37 | +| total_timesteps | 49152 | +| train/ | | +| approx_kl | 0.016626205 | +| clip_fraction | 0.33 | +| clip_range | 0.075 | +| entropy_loss | -6.72 | +| explained_variance | 0.479 | +| learning_rate | 5e-05 | +| loss | -0.0291 | +| n_updates | 35440 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000234 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0595 | +| time/ | | +| fps | 1312 | +| iterations | 25 | +| time_elapsed | 39 | +| total_timesteps | 51200 | +| train/ | | +| approx_kl | 0.010226171 | +| clip_fraction | 0.319 | +| clip_range | 0.075 | +| entropy_loss | -7.26 | +| explained_variance | -0.131 | +| learning_rate | 5e-05 | +| loss | -0.0292 | +| n_updates | 35444 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000233 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0595 | +| time/ | | +| fps | 1312 | +| iterations | 26 | +| time_elapsed | 40 | +| total_timesteps | 53248 | +| train/ | | +| approx_kl | 0.010784894 | +| clip_fraction | 0.307 | +| clip_range | 0.075 | +| entropy_loss | -6.76 | +| explained_variance | 0.337 | +| learning_rate | 5e-05 | +| loss | -0.0297 | +| n_updates | 35448 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000384 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0633 | +| time/ | | +| fps | 1311 | +| iterations | 27 | +| time_elapsed | 42 | +| total_timesteps | 55296 | +| train/ | | +| approx_kl | 0.01150302 | +| clip_fraction | 0.312 | +| clip_range | 0.075 | +| entropy_loss | -6.81 | +| explained_variance | 0.372 | +| learning_rate | 5e-05 | +| loss | -0.0341 | +| n_updates | 35452 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000249 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0633 | +| time/ | | +| fps | 1310 | +| iterations | 28 | +| time_elapsed | 43 | +| total_timesteps | 57344 | +| train/ | | +| approx_kl | 0.010914087 | +| clip_fraction | 0.332 | +| clip_range | 0.075 | +| entropy_loss | -7.31 | +| explained_variance | 0.228 | +| learning_rate | 5e-05 | +| loss | -0.0319 | +| n_updates | 35456 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000245 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0633 | +| time/ | | +| fps | 1310 | +| iterations | 29 | +| time_elapsed | 45 | +| total_timesteps | 59392 | +| train/ | | +| approx_kl | 0.012363162 | +| clip_fraction | 0.304 | +| clip_range | 0.075 | +| entropy_loss | -7.4 | +| explained_variance | -0.00526 | +| learning_rate | 5e-05 | +| loss | -0.0319 | +| n_updates | 35460 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000245 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.06 | +| time/ | | +| fps | 1310 | +| iterations | 30 | +| time_elapsed | 46 | +| total_timesteps | 61440 | +| train/ | | +| approx_kl | 0.014024986 | +| clip_fraction | 0.32 | +| clip_range | 0.075 | +| entropy_loss | -7.4 | +| explained_variance | -0.114 | +| learning_rate | 5e-05 | +| loss | -0.0379 | +| n_updates | 35464 | +| policy_gradient_loss | -0.022 | +| value_loss | 0.000246 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.059 | +| time/ | | +| fps | 1309 | +| iterations | 31 | +| time_elapsed | 48 | +| total_timesteps | 63488 | +| train/ | | +| approx_kl | 0.012914965 | +| clip_fraction | 0.342 | +| clip_range | 0.075 | +| entropy_loss | -7.14 | +| explained_variance | 0.182 | +| learning_rate | 5e-05 | +| loss | -0.0301 | +| n_updates | 35468 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000311 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0499 | +| time/ | | +| fps | 1309 | +| iterations | 32 | +| time_elapsed | 50 | +| total_timesteps | 65536 | +| train/ | | +| approx_kl | 0.012149816 | +| clip_fraction | 0.324 | +| clip_range | 0.075 | +| entropy_loss | -7.35 | +| explained_variance | 0.0773 | +| learning_rate | 5e-05 | +| loss | -0.034 | +| n_updates | 35472 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000278 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.0366 | +| time/ | | +| fps | 1308 | +| iterations | 33 | +| time_elapsed | 51 | +| total_timesteps | 67584 | +| train/ | | +| approx_kl | 0.010648668 | +| clip_fraction | 0.326 | +| clip_range | 0.075 | +| entropy_loss | -6.86 | +| explained_variance | 0.323 | +| learning_rate | 5e-05 | +| loss | -0.0313 | +| n_updates | 35476 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000342 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0351 | +| time/ | | +| fps | 1308 | +| iterations | 34 | +| time_elapsed | 53 | +| total_timesteps | 69632 | +| train/ | | +| approx_kl | 0.01272173 | +| clip_fraction | 0.317 | +| clip_range | 0.075 | +| entropy_loss | -6.44 | +| explained_variance | 0.564 | +| learning_rate | 5e-05 | +| loss | -0.0324 | +| n_updates | 35480 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000203 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0332 | +| time/ | | +| fps | 1309 | +| iterations | 35 | +| time_elapsed | 54 | +| total_timesteps | 71680 | +| train/ | | +| approx_kl | 0.012442693 | +| clip_fraction | 0.325 | +| clip_range | 0.075 | +| entropy_loss | -6.53 | +| explained_variance | 0.535 | +| learning_rate | 5e-05 | +| loss | -0.0288 | +| n_updates | 35484 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000228 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.0529 | +| time/ | | +| fps | 1308 | +| iterations | 36 | +| time_elapsed | 56 | +| total_timesteps | 73728 | +| train/ | | +| approx_kl | 0.010931101 | +| clip_fraction | 0.331 | +| clip_range | 0.075 | +| entropy_loss | -6.5 | +| explained_variance | 0.486 | +| learning_rate | 5e-05 | +| loss | -0.0309 | +| n_updates | 35488 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000175 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0501 | +| time/ | | +| fps | 1307 | +| iterations | 37 | +| time_elapsed | 57 | +| total_timesteps | 75776 | +| train/ | | +| approx_kl | 0.010283986 | +| clip_fraction | 0.295 | +| clip_range | 0.075 | +| entropy_loss | -6.93 | +| explained_variance | 0.15 | +| learning_rate | 5e-05 | +| loss | -0.0269 | +| n_updates | 35492 | +| policy_gradient_loss | -0.014 | +| value_loss | 0.000762 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0501 | +| time/ | | +| fps | 1309 | +| iterations | 38 | +| time_elapsed | 59 | +| total_timesteps | 77824 | +| train/ | | +| approx_kl | 0.012309639 | +| clip_fraction | 0.314 | +| clip_range | 0.075 | +| entropy_loss | -7.2 | +| explained_variance | 0.0581 | +| learning_rate | 5e-05 | +| loss | -0.0354 | +| n_updates | 35496 | +| policy_gradient_loss | -0.022 | +| value_loss | 0.000366 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0501 | +| time/ | | +| fps | 1310 | +| iterations | 39 | +| time_elapsed | 60 | +| total_timesteps | 79872 | +| train/ | | +| approx_kl | 0.012034239 | +| clip_fraction | 0.34 | +| clip_range | 0.075 | +| entropy_loss | -7.26 | +| explained_variance | -0.147 | +| learning_rate | 5e-05 | +| loss | -0.036 | +| n_updates | 35500 | +| policy_gradient_loss | -0.0229 | +| value_loss | 0.000249 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.0659 | +| time/ | | +| fps | 1311 | +| iterations | 40 | +| time_elapsed | 62 | +| total_timesteps | 81920 | +| train/ | | +| approx_kl | 0.013204134 | +| clip_fraction | 0.319 | +| clip_range | 0.075 | +| entropy_loss | -7.35 | +| explained_variance | -0.0863 | +| learning_rate | 5e-05 | +| loss | -0.0347 | +| n_updates | 35504 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000259 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.0905 | +| time/ | | +| fps | 1311 | +| iterations | 41 | +| time_elapsed | 64 | +| total_timesteps | 83968 | +| train/ | | +| approx_kl | 0.010557491 | +| clip_fraction | 0.292 | +| clip_range | 0.075 | +| entropy_loss | -7.11 | +| explained_variance | 0.122 | +| learning_rate | 5e-05 | +| loss | -0.0289 | +| n_updates | 35508 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000924 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.0905 | +| time/ | | +| fps | 1312 | +| iterations | 42 | +| time_elapsed | 65 | +| total_timesteps | 86016 | +| train/ | | +| approx_kl | 0.0103440285 | +| clip_fraction | 0.306 | +| clip_range | 0.075 | +| entropy_loss | -7.03 | +| explained_variance | -0.00227 | +| learning_rate | 5e-05 | +| loss | -0.0306 | +| n_updates | 35512 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000968 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.0849 | +| time/ | | +| fps | 1313 | +| iterations | 43 | +| time_elapsed | 67 | +| total_timesteps | 88064 | +| train/ | | +| approx_kl | 0.012921256 | +| clip_fraction | 0.362 | +| clip_range | 0.075 | +| entropy_loss | -6.92 | +| explained_variance | 0.136 | +| learning_rate | 5e-05 | +| loss | -0.0389 | +| n_updates | 35516 | +| policy_gradient_loss | -0.0251 | +| value_loss | 0.00024 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.0835 | +| time/ | | +| fps | 1314 | +| iterations | 44 | +| time_elapsed | 68 | +| total_timesteps | 90112 | +| train/ | | +| approx_kl | 0.013228323 | +| clip_fraction | 0.36 | +| clip_range | 0.075 | +| entropy_loss | -7.42 | +| explained_variance | -0.142 | +| learning_rate | 5e-05 | +| loss | -0.0437 | +| n_updates | 35520 | +| policy_gradient_loss | -0.025 | +| value_loss | 0.000239 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.0818 | +| time/ | | +| fps | 1314 | +| iterations | 45 | +| time_elapsed | 70 | +| total_timesteps | 92160 | +| train/ | | +| approx_kl | 0.012879809 | +| clip_fraction | 0.36 | +| clip_range | 0.075 | +| entropy_loss | -7.05 | +| explained_variance | 0.371 | +| learning_rate | 5e-05 | +| loss | -0.0416 | +| n_updates | 35524 | +| policy_gradient_loss | -0.024 | +| value_loss | 0.00022 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0807 | +| time/ | | +| fps | 1314 | +| iterations | 46 | +| time_elapsed | 71 | +| total_timesteps | 94208 | +| train/ | | +| approx_kl | 0.014805021 | +| clip_fraction | 0.365 | +| clip_range | 0.075 | +| entropy_loss | -6.92 | +| explained_variance | 0.472 | +| learning_rate | 5e-05 | +| loss | -0.0382 | +| n_updates | 35528 | +| policy_gradient_loss | -0.024 | +| value_loss | 0.000173 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0814 | +| time/ | | +| fps | 1314 | +| iterations | 47 | +| time_elapsed | 73 | +| total_timesteps | 96256 | +| train/ | | +| approx_kl | 0.013372215 | +| clip_fraction | 0.317 | +| clip_range | 0.075 | +| entropy_loss | -6.55 | +| explained_variance | 0.364 | +| learning_rate | 5e-05 | +| loss | -0.0283 | +| n_updates | 35532 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000211 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0813 | +| time/ | | +| fps | 1315 | +| iterations | 48 | +| time_elapsed | 74 | +| total_timesteps | 98304 | +| train/ | | +| approx_kl | 0.013345073 | +| clip_fraction | 0.329 | +| clip_range | 0.075 | +| entropy_loss | -7.12 | +| explained_variance | 0.178 | +| learning_rate | 5e-05 | +| loss | -0.0335 | +| n_updates | 35536 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000255 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0813 | +| time/ | | +| fps | 1316 | +| iterations | 49 | +| time_elapsed | 76 | +| total_timesteps | 100352 | +| train/ | | +| approx_kl | 0.01437229 | +| clip_fraction | 0.332 | +| clip_range | 0.075 | +| entropy_loss | -7.09 | +| explained_variance | 0.226 | +| learning_rate | 5e-05 | +| loss | -0.0296 | +| n_updates | 35540 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000222 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0797 | +| time/ | | +| fps | 1316 | +| iterations | 50 | +| time_elapsed | 77 | +| total_timesteps | 102400 | +| train/ | | +| approx_kl | 0.01304752 | +| clip_fraction | 0.335 | +| clip_range | 0.075 | +| entropy_loss | -7.35 | +| explained_variance | -0.0167 | +| learning_rate | 5e-05 | +| loss | -0.0336 | +| n_updates | 35544 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.00022 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.088 | +| time/ | | +| fps | 1317 | +| iterations | 51 | +| time_elapsed | 79 | +| total_timesteps | 104448 | +| train/ | | +| approx_kl | 0.012543377 | +| clip_fraction | 0.323 | +| clip_range | 0.075 | +| entropy_loss | -7.2 | +| explained_variance | 0.199 | +| learning_rate | 5e-05 | +| loss | -0.0353 | +| n_updates | 35548 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.00028 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0848 | +| time/ | | +| fps | 1318 | +| iterations | 52 | +| time_elapsed | 80 | +| total_timesteps | 106496 | +| train/ | | +| approx_kl | 0.012504156 | +| clip_fraction | 0.304 | +| clip_range | 0.075 | +| entropy_loss | -7.19 | +| explained_variance | 0.111 | +| learning_rate | 5e-05 | +| loss | -0.0323 | +| n_updates | 35552 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000351 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0831 | +| time/ | | +| fps | 1317 | +| iterations | 53 | +| time_elapsed | 82 | +| total_timesteps | 108544 | +| train/ | | +| approx_kl | 0.012536913 | +| clip_fraction | 0.33 | +| clip_range | 0.075 | +| entropy_loss | -6.71 | +| explained_variance | 0.336 | +| learning_rate | 5e-05 | +| loss | -0.0348 | +| n_updates | 35556 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000278 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0769 | +| time/ | | +| fps | 1317 | +| iterations | 54 | +| time_elapsed | 83 | +| total_timesteps | 110592 | +| train/ | | +| approx_kl | 0.015633954 | +| clip_fraction | 0.355 | +| clip_range | 0.075 | +| entropy_loss | -6.97 | +| explained_variance | 0.293 | +| learning_rate | 5e-05 | +| loss | -0.0438 | +| n_updates | 35560 | +| policy_gradient_loss | -0.0239 | +| value_loss | 8.17e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0766 | +| time/ | | +| fps | 1316 | +| iterations | 55 | +| time_elapsed | 85 | +| total_timesteps | 112640 | +| train/ | | +| approx_kl | 0.012614845 | +| clip_fraction | 0.306 | +| clip_range | 0.075 | +| entropy_loss | -6.23 | +| explained_variance | 0.65 | +| learning_rate | 5e-05 | +| loss | -0.0299 | +| n_updates | 35564 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000188 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0766 | +| time/ | | +| fps | 1316 | +| iterations | 56 | +| time_elapsed | 87 | +| total_timesteps | 114688 | +| train/ | | +| approx_kl | 0.014266961 | +| clip_fraction | 0.347 | +| clip_range | 0.075 | +| entropy_loss | -7.25 | +| explained_variance | -0.121 | +| learning_rate | 5e-05 | +| loss | -0.0375 | +| n_updates | 35568 | +| policy_gradient_loss | -0.023 | +| value_loss | 0.000297 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0747 | +| time/ | | +| fps | 1317 | +| iterations | 57 | +| time_elapsed | 88 | +| total_timesteps | 116736 | +| train/ | | +| approx_kl | 0.01375927 | +| clip_fraction | 0.343 | +| clip_range | 0.075 | +| entropy_loss | -7 | +| explained_variance | 0.341 | +| learning_rate | 5e-05 | +| loss | -0.0375 | +| n_updates | 35572 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000166 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0745 | +| time/ | | +| fps | 1317 | +| iterations | 58 | +| time_elapsed | 90 | +| total_timesteps | 118784 | +| train/ | | +| approx_kl | 0.012048656 | +| clip_fraction | 0.311 | +| clip_range | 0.075 | +| entropy_loss | -7.28 | +| explained_variance | 0.302 | +| learning_rate | 5e-05 | +| loss | -0.0323 | +| n_updates | 35576 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000226 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0639 | +| time/ | | +| fps | 1317 | +| iterations | 59 | +| time_elapsed | 91 | +| total_timesteps | 120832 | +| train/ | | +| approx_kl | 0.012043912 | +| clip_fraction | 0.336 | +| clip_range | 0.075 | +| entropy_loss | -6.79 | +| explained_variance | 0.474 | +| learning_rate | 5e-05 | +| loss | -0.0334 | +| n_updates | 35580 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000105 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0686 | +| time/ | | +| fps | 1317 | +| iterations | 60 | +| time_elapsed | 93 | +| total_timesteps | 122880 | +| train/ | | +| approx_kl | 0.01412118 | +| clip_fraction | 0.315 | +| clip_range | 0.075 | +| entropy_loss | -6.94 | +| explained_variance | 0.162 | +| learning_rate | 5e-05 | +| loss | -0.0326 | +| n_updates | 35584 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000314 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0706 | +| time/ | | +| fps | 1317 | +| iterations | 61 | +| time_elapsed | 94 | +| total_timesteps | 124928 | +| train/ | | +| approx_kl | 0.01534212 | +| clip_fraction | 0.313 | +| clip_range | 0.075 | +| entropy_loss | -7.2 | +| explained_variance | -0.0946 | +| learning_rate | 5e-05 | +| loss | -0.0279 | +| n_updates | 35588 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.00025 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0708 | +| time/ | | +| fps | 1318 | +| iterations | 62 | +| time_elapsed | 96 | +| total_timesteps | 126976 | +| train/ | | +| approx_kl | 0.012977337 | +| clip_fraction | 0.338 | +| clip_range | 0.075 | +| entropy_loss | -7.42 | +| explained_variance | -0.0764 | +| learning_rate | 5e-05 | +| loss | -0.0383 | +| n_updates | 35592 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000292 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0689 | +| time/ | | +| fps | 1319 | +| iterations | 63 | +| time_elapsed | 97 | +| total_timesteps | 129024 | +| train/ | | +| approx_kl | 0.01416301 | +| clip_fraction | 0.324 | +| clip_range | 0.075 | +| entropy_loss | -6.9 | +| explained_variance | 0.284 | +| learning_rate | 5e-05 | +| loss | -0.0316 | +| n_updates | 35596 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000294 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0681 | +| time/ | | +| fps | 1319 | +| iterations | 64 | +| time_elapsed | 99 | +| total_timesteps | 131072 | +| train/ | | +| approx_kl | 0.012443513 | +| clip_fraction | 0.344 | +| clip_range | 0.075 | +| entropy_loss | -7.06 | +| explained_variance | -0.248 | +| learning_rate | 5e-05 | +| loss | -0.0371 | +| n_updates | 35600 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000244 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.066 | +| time/ | | +| fps | 1319 | +| iterations | 65 | +| time_elapsed | 100 | +| total_timesteps | 133120 | +| train/ | | +| approx_kl | 0.013524729 | +| clip_fraction | 0.361 | +| clip_range | 0.075 | +| entropy_loss | -6.81 | +| explained_variance | 0.146 | +| learning_rate | 5e-05 | +| loss | -0.0327 | +| n_updates | 35604 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000268 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0654 | +| time/ | | +| fps | 1319 | +| iterations | 66 | +| time_elapsed | 102 | +| total_timesteps | 135168 | +| train/ | | +| approx_kl | 0.014209322 | +| clip_fraction | 0.351 | +| clip_range | 0.075 | +| entropy_loss | -7.09 | +| explained_variance | -0.172 | +| learning_rate | 5e-05 | +| loss | -0.0334 | +| n_updates | 35608 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000322 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0654 | +| time/ | | +| fps | 1320 | +| iterations | 67 | +| time_elapsed | 103 | +| total_timesteps | 137216 | +| train/ | | +| approx_kl | 0.012665633 | +| clip_fraction | 0.329 | +| clip_range | 0.075 | +| entropy_loss | -7.06 | +| explained_variance | 0.151 | +| learning_rate | 5e-05 | +| loss | -0.0289 | +| n_updates | 35612 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000243 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0684 | +| time/ | | +| fps | 1320 | +| iterations | 68 | +| time_elapsed | 105 | +| total_timesteps | 139264 | +| train/ | | +| approx_kl | 0.014103389 | +| clip_fraction | 0.325 | +| clip_range | 0.075 | +| entropy_loss | -6.97 | +| explained_variance | 0.0632 | +| learning_rate | 5e-05 | +| loss | -0.0316 | +| n_updates | 35616 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000225 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0714 | +| time/ | | +| fps | 1320 | +| iterations | 69 | +| time_elapsed | 106 | +| total_timesteps | 141312 | +| train/ | | +| approx_kl | 0.0117412135 | +| clip_fraction | 0.342 | +| clip_range | 0.075 | +| entropy_loss | -6.88 | +| explained_variance | 0.255 | +| learning_rate | 5e-05 | +| loss | -0.0286 | +| n_updates | 35620 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000234 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0708 | +| time/ | | +| fps | 1321 | +| iterations | 70 | +| time_elapsed | 108 | +| total_timesteps | 143360 | +| train/ | | +| approx_kl | 0.015339334 | +| clip_fraction | 0.344 | +| clip_range | 0.075 | +| entropy_loss | -6.4 | +| explained_variance | 0.499 | +| learning_rate | 5e-05 | +| loss | -0.0303 | +| n_updates | 35624 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000175 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0708 | +| time/ | | +| fps | 1321 | +| iterations | 71 | +| time_elapsed | 110 | +| total_timesteps | 145408 | +| train/ | | +| approx_kl | 0.014043204 | +| clip_fraction | 0.329 | +| clip_range | 0.075 | +| entropy_loss | -6.96 | +| explained_variance | -0.107 | +| learning_rate | 5e-05 | +| loss | -0.0296 | +| n_updates | 35628 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000244 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0715 | +| time/ | | +| fps | 1321 | +| iterations | 72 | +| time_elapsed | 111 | +| total_timesteps | 147456 | +| train/ | | +| approx_kl | 0.014039282 | +| clip_fraction | 0.35 | +| clip_range | 0.075 | +| entropy_loss | -7.36 | +| explained_variance | -0.22 | +| learning_rate | 5e-05 | +| loss | -0.0353 | +| n_updates | 35632 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.00018 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0715 | +| time/ | | +| fps | 1321 | +| iterations | 73 | +| time_elapsed | 113 | +| total_timesteps | 149504 | +| train/ | | +| approx_kl | 0.015912663 | +| clip_fraction | 0.324 | +| clip_range | 0.075 | +| entropy_loss | -7.08 | +| explained_variance | 0.196 | +| learning_rate | 5e-05 | +| loss | -0.0298 | +| n_updates | 35636 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000205 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0696 | +| time/ | | +| fps | 1321 | +| iterations | 74 | +| time_elapsed | 114 | +| total_timesteps | 151552 | +| train/ | | +| approx_kl | 0.01390294 | +| clip_fraction | 0.321 | +| clip_range | 0.075 | +| entropy_loss | -7.2 | +| explained_variance | -0.139 | +| learning_rate | 5e-05 | +| loss | -0.0305 | +| n_updates | 35640 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000242 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0606 | +| time/ | | +| fps | 1321 | +| iterations | 75 | +| time_elapsed | 116 | +| total_timesteps | 153600 | +| train/ | | +| approx_kl | 0.013544986 | +| clip_fraction | 0.329 | +| clip_range | 0.075 | +| entropy_loss | -6.94 | +| explained_variance | 0.447 | +| learning_rate | 5e-05 | +| loss | -0.0313 | +| n_updates | 35644 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000164 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0629 | +| time/ | | +| fps | 1321 | +| iterations | 76 | +| time_elapsed | 117 | +| total_timesteps | 155648 | +| train/ | | +| approx_kl | 0.011588755 | +| clip_fraction | 0.305 | +| clip_range | 0.075 | +| entropy_loss | -7.13 | +| explained_variance | 0.0979 | +| learning_rate | 5e-05 | +| loss | -0.0294 | +| n_updates | 35648 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000802 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.0624 | +| time/ | | +| fps | 1321 | +| iterations | 77 | +| time_elapsed | 119 | +| total_timesteps | 157696 | +| train/ | | +| approx_kl | 0.014191719 | +| clip_fraction | 0.321 | +| clip_range | 0.075 | +| entropy_loss | -6.77 | +| explained_variance | -0.131 | +| learning_rate | 5e-05 | +| loss | -0.0347 | +| n_updates | 35652 | +| policy_gradient_loss | -0.0221 | +| value_loss | 0.000435 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.063 | +| time/ | | +| fps | 1321 | +| iterations | 78 | +| time_elapsed | 120 | +| total_timesteps | 159744 | +| train/ | | +| approx_kl | 0.012890504 | +| clip_fraction | 0.338 | +| clip_range | 0.075 | +| entropy_loss | -6.86 | +| explained_variance | 0.0278 | +| learning_rate | 5e-05 | +| loss | -0.0353 | +| n_updates | 35656 | +| policy_gradient_loss | -0.0227 | +| value_loss | 0.000297 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0696 | +| time/ | | +| fps | 1320 | +| iterations | 79 | +| time_elapsed | 122 | +| total_timesteps | 161792 | +| train/ | | +| approx_kl | 0.01349571 | +| clip_fraction | 0.344 | +| clip_range | 0.075 | +| entropy_loss | -6.83 | +| explained_variance | 0.168 | +| learning_rate | 5e-05 | +| loss | -0.0308 | +| n_updates | 35660 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000261 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0664 | +| time/ | | +| fps | 1320 | +| iterations | 80 | +| time_elapsed | 124 | +| total_timesteps | 163840 | +| train/ | | +| approx_kl | 0.011604542 | +| clip_fraction | 0.311 | +| clip_range | 0.075 | +| entropy_loss | -7 | +| explained_variance | 0.129 | +| learning_rate | 5e-05 | +| loss | -0.0298 | +| n_updates | 35664 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000425 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0664 | +| time/ | | +| fps | 1320 | +| iterations | 81 | +| time_elapsed | 125 | +| total_timesteps | 165888 | +| train/ | | +| approx_kl | 0.013106018 | +| clip_fraction | 0.337 | +| clip_range | 0.075 | +| entropy_loss | -6.76 | +| explained_variance | 0.0999 | +| learning_rate | 5e-05 | +| loss | -0.0339 | +| n_updates | 35668 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000332 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0698 | +| time/ | | +| fps | 1320 | +| iterations | 82 | +| time_elapsed | 127 | +| total_timesteps | 167936 | +| train/ | | +| approx_kl | 0.0117604975 | +| clip_fraction | 0.34 | +| clip_range | 0.075 | +| entropy_loss | -7.27 | +| explained_variance | -0.0717 | +| learning_rate | 5e-05 | +| loss | -0.0336 | +| n_updates | 35672 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000382 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0717 | +| time/ | | +| fps | 1320 | +| iterations | 83 | +| time_elapsed | 128 | +| total_timesteps | 169984 | +| train/ | | +| approx_kl | 0.012271982 | +| clip_fraction | 0.309 | +| clip_range | 0.075 | +| entropy_loss | -7.17 | +| explained_variance | -0.0162 | +| learning_rate | 5e-05 | +| loss | -0.0299 | +| n_updates | 35676 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000296 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0705 | +| time/ | | +| fps | 1320 | +| iterations | 84 | +| time_elapsed | 130 | +| total_timesteps | 172032 | +| train/ | | +| approx_kl | 0.014861429 | +| clip_fraction | 0.343 | +| clip_range | 0.075 | +| entropy_loss | -6.86 | +| explained_variance | 0.111 | +| learning_rate | 5e-05 | +| loss | -0.0373 | +| n_updates | 35680 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000206 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.074 | +| time/ | | +| fps | 1320 | +| iterations | 85 | +| time_elapsed | 131 | +| total_timesteps | 174080 | +| train/ | | +| approx_kl | 0.01284519 | +| clip_fraction | 0.354 | +| clip_range | 0.075 | +| entropy_loss | -6.93 | +| explained_variance | 0.112 | +| learning_rate | 5e-05 | +| loss | -0.0356 | +| n_updates | 35684 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000289 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0568 | +| time/ | | +| fps | 1320 | +| iterations | 86 | +| time_elapsed | 133 | +| total_timesteps | 176128 | +| train/ | | +| approx_kl | 0.014099643 | +| clip_fraction | 0.322 | +| clip_range | 0.075 | +| entropy_loss | -6.7 | +| explained_variance | 0.211 | +| learning_rate | 5e-05 | +| loss | -0.0283 | +| n_updates | 35688 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000281 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0591 | +| time/ | | +| fps | 1319 | +| iterations | 87 | +| time_elapsed | 135 | +| total_timesteps | 178176 | +| train/ | | +| approx_kl | 0.013397336 | +| clip_fraction | 0.312 | +| clip_range | 0.075 | +| entropy_loss | -7.02 | +| explained_variance | -0.0317 | +| learning_rate | 5e-05 | +| loss | -0.0291 | +| n_updates | 35692 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000917 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.057 | +| time/ | | +| fps | 1319 | +| iterations | 88 | +| time_elapsed | 136 | +| total_timesteps | 180224 | +| train/ | | +| approx_kl | 0.013055215 | +| clip_fraction | 0.342 | +| clip_range | 0.075 | +| entropy_loss | -6.51 | +| explained_variance | 0.498 | +| learning_rate | 5e-05 | +| loss | -0.0336 | +| n_updates | 35696 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000174 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.0558 | +| time/ | | +| fps | 1319 | +| iterations | 89 | +| time_elapsed | 138 | +| total_timesteps | 182272 | +| train/ | | +| approx_kl | 0.014684988 | +| clip_fraction | 0.348 | +| clip_range | 0.075 | +| entropy_loss | -7.03 | +| explained_variance | -0.152 | +| learning_rate | 5e-05 | +| loss | -0.0381 | +| n_updates | 35700 | +| policy_gradient_loss | -0.0242 | +| value_loss | 0.000284 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0462 | +| time/ | | +| fps | 1319 | +| iterations | 90 | +| time_elapsed | 139 | +| total_timesteps | 184320 | +| train/ | | +| approx_kl | 0.014585439 | +| clip_fraction | 0.339 | +| clip_range | 0.075 | +| entropy_loss | -6.67 | +| explained_variance | 0.35 | +| learning_rate | 5e-05 | +| loss | -0.0356 | +| n_updates | 35704 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000209 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0419 | +| time/ | | +| fps | 1319 | +| iterations | 91 | +| time_elapsed | 141 | +| total_timesteps | 186368 | +| train/ | | +| approx_kl | 0.013656527 | +| clip_fraction | 0.352 | +| clip_range | 0.075 | +| entropy_loss | -7.01 | +| explained_variance | -0.0291 | +| learning_rate | 5e-05 | +| loss | -0.0362 | +| n_updates | 35708 | +| policy_gradient_loss | -0.0221 | +| value_loss | 0.000338 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0378 | +| time/ | | +| fps | 1319 | +| iterations | 92 | +| time_elapsed | 142 | +| total_timesteps | 188416 | +| train/ | | +| approx_kl | 0.015473574 | +| clip_fraction | 0.36 | +| clip_range | 0.075 | +| entropy_loss | -6.54 | +| explained_variance | 0.272 | +| learning_rate | 5e-05 | +| loss | -0.0324 | +| n_updates | 35712 | +| policy_gradient_loss | -0.0223 | +| value_loss | 0.000272 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0378 | +| time/ | | +| fps | 1319 | +| iterations | 93 | +| time_elapsed | 144 | +| total_timesteps | 190464 | +| train/ | | +| approx_kl | 0.0150451 | +| clip_fraction | 0.364 | +| clip_range | 0.075 | +| entropy_loss | -6.89 | +| explained_variance | 0.311 | +| learning_rate | 5e-05 | +| loss | -0.0357 | +| n_updates | 35716 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000162 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0286 | +| time/ | | +| fps | 1320 | +| iterations | 94 | +| time_elapsed | 145 | +| total_timesteps | 192512 | +| train/ | | +| approx_kl | 0.014108069 | +| clip_fraction | 0.353 | +| clip_range | 0.075 | +| entropy_loss | -6.85 | +| explained_variance | 0.164 | +| learning_rate | 5e-05 | +| loss | -0.0347 | +| n_updates | 35720 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000301 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.034 | +| time/ | | +| fps | 1320 | +| iterations | 95 | +| time_elapsed | 147 | +| total_timesteps | 194560 | +| train/ | | +| approx_kl | 0.01340856 | +| clip_fraction | 0.331 | +| clip_range | 0.075 | +| entropy_loss | -6.67 | +| explained_variance | 0.253 | +| learning_rate | 5e-05 | +| loss | -0.0295 | +| n_updates | 35724 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000203 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.034 | +| time/ | | +| fps | 1320 | +| iterations | 96 | +| time_elapsed | 148 | +| total_timesteps | 196608 | +| train/ | | +| approx_kl | 0.012587531 | +| clip_fraction | 0.343 | +| clip_range | 0.075 | +| entropy_loss | -7 | +| explained_variance | 0.155 | +| learning_rate | 5e-05 | +| loss | -0.0328 | +| n_updates | 35728 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000352 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0333 | +| time/ | | +| fps | 1320 | +| iterations | 97 | +| time_elapsed | 150 | +| total_timesteps | 198656 | +| train/ | | +| approx_kl | 0.013431055 | +| clip_fraction | 0.339 | +| clip_range | 0.075 | +| entropy_loss | -7.12 | +| explained_variance | -0.177 | +| learning_rate | 5e-05 | +| loss | -0.0324 | +| n_updates | 35732 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000245 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.0343 | +| time/ | | +| fps | 1320 | +| iterations | 98 | +| time_elapsed | 152 | +| total_timesteps | 200704 | +| train/ | | +| approx_kl | 0.013490648 | +| clip_fraction | 0.326 | +| clip_range | 0.075 | +| entropy_loss | -7.07 | +| explained_variance | 0.249 | +| learning_rate | 5e-05 | +| loss | -0.0319 | +| n_updates | 35736 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.00026 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.0394 | +| time/ | | +| fps | 1320 | +| iterations | 99 | +| time_elapsed | 153 | +| total_timesteps | 202752 | +| train/ | | +| approx_kl | 0.012452628 | +| clip_fraction | 0.328 | +| clip_range | 0.0749 | +| entropy_loss | -6.89 | +| explained_variance | 0.116 | +| learning_rate | 5e-05 | +| loss | -0.0323 | +| n_updates | 35740 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000328 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0388 | +| time/ | | +| fps | 1320 | +| iterations | 100 | +| time_elapsed | 155 | +| total_timesteps | 204800 | +| train/ | | +| approx_kl | 0.013811487 | +| clip_fraction | 0.335 | +| clip_range | 0.0749 | +| entropy_loss | -6.49 | +| explained_variance | 0.398 | +| learning_rate | 5e-05 | +| loss | -0.0302 | +| n_updates | 35744 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000198 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0403 | +| time/ | | +| fps | 1320 | +| iterations | 101 | +| time_elapsed | 156 | +| total_timesteps | 206848 | +| train/ | | +| approx_kl | 0.016587477 | +| clip_fraction | 0.362 | +| clip_range | 0.0749 | +| entropy_loss | -6.3 | +| explained_variance | 0.557 | +| learning_rate | 5e-05 | +| loss | -0.0331 | +| n_updates | 35748 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.00021 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.0424 | +| time/ | | +| fps | 1320 | +| iterations | 102 | +| time_elapsed | 158 | +| total_timesteps | 208896 | +| train/ | | +| approx_kl | 0.015243406 | +| clip_fraction | 0.341 | +| clip_range | 0.0749 | +| entropy_loss | -6.61 | +| explained_variance | 0.333 | +| learning_rate | 5e-05 | +| loss | -0.0372 | +| n_updates | 35752 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.00016 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.0457 | +| time/ | | +| fps | 1320 | +| iterations | 103 | +| time_elapsed | 159 | +| total_timesteps | 210944 | +| train/ | | +| approx_kl | 0.015284476 | +| clip_fraction | 0.358 | +| clip_range | 0.0749 | +| entropy_loss | -6.92 | +| explained_variance | 0.191 | +| learning_rate | 5e-05 | +| loss | -0.0358 | +| n_updates | 35756 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.0003 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.0474 | +| time/ | | +| fps | 1320 | +| iterations | 104 | +| time_elapsed | 161 | +| total_timesteps | 212992 | +| train/ | | +| approx_kl | 0.01618735 | +| clip_fraction | 0.388 | +| clip_range | 0.0749 | +| entropy_loss | -6.88 | +| explained_variance | -0.0233 | +| learning_rate | 4.99e-05 | +| loss | -0.0408 | +| n_updates | 35760 | +| policy_gradient_loss | -0.023 | +| value_loss | 0.000282 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.0505 | +| time/ | | +| fps | 1319 | +| iterations | 105 | +| time_elapsed | 162 | +| total_timesteps | 215040 | +| train/ | | +| approx_kl | 0.0135713965 | +| clip_fraction | 0.33 | +| clip_range | 0.0749 | +| entropy_loss | -6.89 | +| explained_variance | 0.0875 | +| learning_rate | 4.99e-05 | +| loss | -0.0296 | +| n_updates | 35764 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000874 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.0426 | +| time/ | | +| fps | 1319 | +| iterations | 106 | +| time_elapsed | 164 | +| total_timesteps | 217088 | +| train/ | | +| approx_kl | 0.018174453 | +| clip_fraction | 0.369 | +| clip_range | 0.0749 | +| entropy_loss | -6.79 | +| explained_variance | 0.261 | +| learning_rate | 4.99e-05 | +| loss | -0.0433 | +| n_updates | 35768 | +| policy_gradient_loss | -0.0242 | +| value_loss | 0.000258 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.0429 | +| time/ | | +| fps | 1319 | +| iterations | 107 | +| time_elapsed | 166 | +| total_timesteps | 219136 | +| train/ | | +| approx_kl | 0.014504006 | +| clip_fraction | 0.396 | +| clip_range | 0.0749 | +| entropy_loss | -7 | +| explained_variance | -0.165 | +| learning_rate | 4.99e-05 | +| loss | -0.0392 | +| n_updates | 35772 | +| policy_gradient_loss | -0.0246 | +| value_loss | 0.000196 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.0323 | +| time/ | | +| fps | 1318 | +| iterations | 108 | +| time_elapsed | 167 | +| total_timesteps | 221184 | +| train/ | | +| approx_kl | 0.015819645 | +| clip_fraction | 0.35 | +| clip_range | 0.0749 | +| entropy_loss | -6.7 | +| explained_variance | 0.281 | +| learning_rate | 4.99e-05 | +| loss | -0.0333 | +| n_updates | 35776 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000311 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.0292 | +| time/ | | +| fps | 1319 | +| iterations | 109 | +| time_elapsed | 169 | +| total_timesteps | 223232 | +| train/ | | +| approx_kl | 0.013331752 | +| clip_fraction | 0.32 | +| clip_range | 0.0749 | +| entropy_loss | -6.96 | +| explained_variance | 0.169 | +| learning_rate | 4.99e-05 | +| loss | -0.0342 | +| n_updates | 35780 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000282 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.0302 | +| time/ | | +| fps | 1319 | +| iterations | 110 | +| time_elapsed | 170 | +| total_timesteps | 225280 | +| train/ | | +| approx_kl | 0.012601452 | +| clip_fraction | 0.336 | +| clip_range | 0.0749 | +| entropy_loss | -6.91 | +| explained_variance | 0.355 | +| learning_rate | 4.99e-05 | +| loss | -0.0321 | +| n_updates | 35784 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000282 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.0299 | +| time/ | | +| fps | 1319 | +| iterations | 111 | +| time_elapsed | 172 | +| total_timesteps | 227328 | +| train/ | | +| approx_kl | 0.012599109 | +| clip_fraction | 0.35 | +| clip_range | 0.0749 | +| entropy_loss | -6.42 | +| explained_variance | 0.464 | +| learning_rate | 4.99e-05 | +| loss | -0.0323 | +| n_updates | 35788 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000232 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.0282 | +| time/ | | +| fps | 1318 | +| iterations | 112 | +| time_elapsed | 173 | +| total_timesteps | 229376 | +| train/ | | +| approx_kl | 0.015380288 | +| clip_fraction | 0.355 | +| clip_range | 0.0749 | +| entropy_loss | -6.74 | +| explained_variance | 0.413 | +| learning_rate | 4.99e-05 | +| loss | -0.034 | +| n_updates | 35792 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000198 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.0287 | +| time/ | | +| fps | 1319 | +| iterations | 113 | +| time_elapsed | 175 | +| total_timesteps | 231424 | +| train/ | | +| approx_kl | 0.014044922 | +| clip_fraction | 0.34 | +| clip_range | 0.0749 | +| entropy_loss | -6.87 | +| explained_variance | -0.0218 | +| learning_rate | 4.99e-05 | +| loss | -0.0297 | +| n_updates | 35796 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000339 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0357 | +| time/ | | +| fps | 1319 | +| iterations | 114 | +| time_elapsed | 177 | +| total_timesteps | 233472 | +| train/ | | +| approx_kl | 0.01476652 | +| clip_fraction | 0.359 | +| clip_range | 0.0749 | +| entropy_loss | -6.75 | +| explained_variance | 0.0975 | +| learning_rate | 4.99e-05 | +| loss | -0.0342 | +| n_updates | 35800 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000213 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0442 | +| time/ | | +| fps | 1319 | +| iterations | 115 | +| time_elapsed | 178 | +| total_timesteps | 235520 | +| train/ | | +| approx_kl | 0.010685507 | +| clip_fraction | 0.304 | +| clip_range | 0.0749 | +| entropy_loss | -6.36 | +| explained_variance | 0.183 | +| learning_rate | 4.99e-05 | +| loss | -0.0189 | +| n_updates | 35804 | +| policy_gradient_loss | -0.0135 | +| value_loss | 0.00081 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0442 | +| time/ | | +| fps | 1319 | +| iterations | 116 | +| time_elapsed | 180 | +| total_timesteps | 237568 | +| train/ | | +| approx_kl | 0.0124621615 | +| clip_fraction | 0.336 | +| clip_range | 0.0749 | +| entropy_loss | -6.29 | +| explained_variance | 0.252 | +| learning_rate | 4.99e-05 | +| loss | -0.0209 | +| n_updates | 35808 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000713 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.041 | +| time/ | | +| fps | 1319 | +| iterations | 117 | +| time_elapsed | 181 | +| total_timesteps | 239616 | +| train/ | | +| approx_kl | 0.013588825 | +| clip_fraction | 0.348 | +| clip_range | 0.0749 | +| entropy_loss | -7.03 | +| explained_variance | -0.096 | +| learning_rate | 4.99e-05 | +| loss | -0.037 | +| n_updates | 35812 | +| policy_gradient_loss | -0.0221 | +| value_loss | 0.00036 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0449 | +| time/ | | +| fps | 1319 | +| iterations | 118 | +| time_elapsed | 183 | +| total_timesteps | 241664 | +| train/ | | +| approx_kl | 0.013100532 | +| clip_fraction | 0.357 | +| clip_range | 0.0749 | +| entropy_loss | -7.12 | +| explained_variance | -0.054 | +| learning_rate | 4.99e-05 | +| loss | -0.0361 | +| n_updates | 35816 | +| policy_gradient_loss | -0.0226 | +| value_loss | 0.000231 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0479 | +| time/ | | +| fps | 1320 | +| iterations | 119 | +| time_elapsed | 184 | +| total_timesteps | 243712 | +| train/ | | +| approx_kl | 0.00946822 | +| clip_fraction | 0.31 | +| clip_range | 0.0749 | +| entropy_loss | -6.44 | +| explained_variance | 0.22 | +| learning_rate | 4.99e-05 | +| loss | -0.0189 | +| n_updates | 35820 | +| policy_gradient_loss | -0.0139 | +| value_loss | 0.000825 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0535 | +| time/ | | +| fps | 1320 | +| iterations | 120 | +| time_elapsed | 186 | +| total_timesteps | 245760 | +| train/ | | +| approx_kl | 0.012132201 | +| clip_fraction | 0.343 | +| clip_range | 0.0749 | +| entropy_loss | -6.92 | +| explained_variance | -0.0301 | +| learning_rate | 4.99e-05 | +| loss | -0.035 | +| n_updates | 35824 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000314 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0499 | +| time/ | | +| fps | 1320 | +| iterations | 121 | +| time_elapsed | 187 | +| total_timesteps | 247808 | +| train/ | | +| approx_kl | 0.014676698 | +| clip_fraction | 0.325 | +| clip_range | 0.0749 | +| entropy_loss | -6.69 | +| explained_variance | 0.243 | +| learning_rate | 4.99e-05 | +| loss | -0.0354 | +| n_updates | 35828 | +| policy_gradient_loss | -0.0219 | +| value_loss | 0.000342 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0499 | +| time/ | | +| fps | 1320 | +| iterations | 122 | +| time_elapsed | 189 | +| total_timesteps | 249856 | +| train/ | | +| approx_kl | 0.015328223 | +| clip_fraction | 0.362 | +| clip_range | 0.0749 | +| entropy_loss | -6.55 | +| explained_variance | 0.359 | +| learning_rate | 4.99e-05 | +| loss | -0.0398 | +| n_updates | 35832 | +| policy_gradient_loss | -0.023 | +| value_loss | 0.000233 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0499 | +| time/ | | +| fps | 1320 | +| iterations | 123 | +| time_elapsed | 190 | +| total_timesteps | 251904 | +| train/ | | +| approx_kl | 0.013638202 | +| clip_fraction | 0.331 | +| clip_range | 0.0749 | +| entropy_loss | -7.03 | +| explained_variance | -0.0396 | +| learning_rate | 4.99e-05 | +| loss | -0.0329 | +| n_updates | 35836 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.00033 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0523 | +| time/ | | +| fps | 1320 | +| iterations | 124 | +| time_elapsed | 192 | +| total_timesteps | 253952 | +| train/ | | +| approx_kl | 0.013951329 | +| clip_fraction | 0.354 | +| clip_range | 0.0749 | +| entropy_loss | -7.05 | +| explained_variance | -0.126 | +| learning_rate | 4.99e-05 | +| loss | -0.0323 | +| n_updates | 35840 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.00034 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0561 | +| time/ | | +| fps | 1320 | +| iterations | 125 | +| time_elapsed | 193 | +| total_timesteps | 256000 | +| train/ | | +| approx_kl | 0.010811456 | +| clip_fraction | 0.3 | +| clip_range | 0.0749 | +| entropy_loss | -6.54 | +| explained_variance | 0.0613 | +| learning_rate | 4.99e-05 | +| loss | -0.0235 | +| n_updates | 35844 | +| policy_gradient_loss | -0.0145 | +| value_loss | 0.000408 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.052 | +| time/ | | +| fps | 1320 | +| iterations | 126 | +| time_elapsed | 195 | +| total_timesteps | 258048 | +| train/ | | +| approx_kl | 0.012576152 | +| clip_fraction | 0.339 | +| clip_range | 0.0749 | +| entropy_loss | -6.67 | +| explained_variance | 0.233 | +| learning_rate | 4.99e-05 | +| loss | -0.0318 | +| n_updates | 35848 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000365 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0542 | +| time/ | | +| fps | 1320 | +| iterations | 127 | +| time_elapsed | 196 | +| total_timesteps | 260096 | +| train/ | | +| approx_kl | 0.014787132 | +| clip_fraction | 0.342 | +| clip_range | 0.0749 | +| entropy_loss | -6.51 | +| explained_variance | 0.387 | +| learning_rate | 4.99e-05 | +| loss | -0.0373 | +| n_updates | 35852 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000153 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0562 | +| time/ | | +| fps | 1321 | +| iterations | 128 | +| time_elapsed | 198 | +| total_timesteps | 262144 | +| train/ | | +| approx_kl | 0.01753102 | +| clip_fraction | 0.37 | +| clip_range | 0.0749 | +| entropy_loss | -6.26 | +| explained_variance | 0.39 | +| learning_rate | 4.99e-05 | +| loss | -0.0316 | +| n_updates | 35856 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000172 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0562 | +| time/ | | +| fps | 1321 | +| iterations | 129 | +| time_elapsed | 199 | +| total_timesteps | 264192 | +| train/ | | +| approx_kl | 0.01597916 | +| clip_fraction | 0.347 | +| clip_range | 0.0749 | +| entropy_loss | -6.8 | +| explained_variance | -0.0461 | +| learning_rate | 4.99e-05 | +| loss | -0.0309 | +| n_updates | 35860 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000224 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.0513 | +| time/ | | +| fps | 1321 | +| iterations | 130 | +| time_elapsed | 201 | +| total_timesteps | 266240 | +| train/ | | +| approx_kl | 0.014052269 | +| clip_fraction | 0.348 | +| clip_range | 0.0749 | +| entropy_loss | -7.04 | +| explained_variance | -0.0966 | +| learning_rate | 4.99e-05 | +| loss | -0.0372 | +| n_updates | 35864 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000347 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.0513 | +| time/ | | +| fps | 1321 | +| iterations | 131 | +| time_elapsed | 203 | +| total_timesteps | 268288 | +| train/ | | +| approx_kl | 0.0156091 | +| clip_fraction | 0.347 | +| clip_range | 0.0749 | +| entropy_loss | -6.98 | +| explained_variance | 0.00468 | +| learning_rate | 4.99e-05 | +| loss | -0.0349 | +| n_updates | 35868 | +| policy_gradient_loss | -0.0227 | +| value_loss | 0.000293 | +--------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.0419 | +| time/ | | +| fps | 1321 | +| iterations | 132 | +| time_elapsed | 204 | +| total_timesteps | 270336 | +| train/ | | +| approx_kl | 0.01569521 | +| clip_fraction | 0.344 | +| clip_range | 0.0749 | +| entropy_loss | -6.86 | +| explained_variance | -0.099 | +| learning_rate | 4.99e-05 | +| loss | -0.0383 | +| n_updates | 35872 | +| policy_gradient_loss | -0.0236 | +| value_loss | 0.000247 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.0441 | +| time/ | | +| fps | 1321 | +| iterations | 133 | +| time_elapsed | 206 | +| total_timesteps | 272384 | +| train/ | | +| approx_kl | 0.015812699 | +| clip_fraction | 0.37 | +| clip_range | 0.0749 | +| entropy_loss | -6.6 | +| explained_variance | 0.172 | +| learning_rate | 4.99e-05 | +| loss | -0.0379 | +| n_updates | 35876 | +| policy_gradient_loss | -0.0226 | +| value_loss | 0.0003 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.0441 | +| time/ | | +| fps | 1322 | +| iterations | 134 | +| time_elapsed | 207 | +| total_timesteps | 274432 | +| train/ | | +| approx_kl | 0.012479443 | +| clip_fraction | 0.322 | +| clip_range | 0.0749 | +| entropy_loss | -6.48 | +| explained_variance | 0.373 | +| learning_rate | 4.99e-05 | +| loss | -0.0263 | +| n_updates | 35880 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000241 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.0441 | +| time/ | | +| fps | 1322 | +| iterations | 135 | +| time_elapsed | 209 | +| total_timesteps | 276480 | +| train/ | | +| approx_kl | 0.015970888 | +| clip_fraction | 0.367 | +| clip_range | 0.0749 | +| entropy_loss | -6.81 | +| explained_variance | -0.0492 | +| learning_rate | 4.99e-05 | +| loss | -0.0309 | +| n_updates | 35884 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000177 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.0441 | +| time/ | | +| fps | 1322 | +| iterations | 136 | +| time_elapsed | 210 | +| total_timesteps | 278528 | +| train/ | | +| approx_kl | 0.01721241 | +| clip_fraction | 0.361 | +| clip_range | 0.0749 | +| entropy_loss | -6.93 | +| explained_variance | -0.0407 | +| learning_rate | 4.99e-05 | +| loss | -0.0343 | +| n_updates | 35888 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000321 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.0452 | +| time/ | | +| fps | 1322 | +| iterations | 137 | +| time_elapsed | 212 | +| total_timesteps | 280576 | +| train/ | | +| approx_kl | 0.016277855 | +| clip_fraction | 0.365 | +| clip_range | 0.0749 | +| entropy_loss | -7.1 | +| explained_variance | -0.0332 | +| learning_rate | 4.99e-05 | +| loss | -0.0347 | +| n_updates | 35892 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000235 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.0619 | +| time/ | | +| fps | 1322 | +| iterations | 138 | +| time_elapsed | 213 | +| total_timesteps | 282624 | +| train/ | | +| approx_kl | 0.016387088 | +| clip_fraction | 0.376 | +| clip_range | 0.0749 | +| entropy_loss | -7.04 | +| explained_variance | -0.0763 | +| learning_rate | 4.99e-05 | +| loss | -0.0333 | +| n_updates | 35896 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000245 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.0643 | +| time/ | | +| fps | 1322 | +| iterations | 139 | +| time_elapsed | 215 | +| total_timesteps | 284672 | +| train/ | | +| approx_kl | 0.012709313 | +| clip_fraction | 0.325 | +| clip_range | 0.0749 | +| entropy_loss | -6.41 | +| explained_variance | 0.133 | +| learning_rate | 4.99e-05 | +| loss | -0.0238 | +| n_updates | 35900 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000779 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.0661 | +| time/ | | +| fps | 1322 | +| iterations | 140 | +| time_elapsed | 216 | +| total_timesteps | 286720 | +| train/ | | +| approx_kl | 0.018560883 | +| clip_fraction | 0.381 | +| clip_range | 0.0749 | +| entropy_loss | -6.86 | +| explained_variance | 0.0628 | +| learning_rate | 4.99e-05 | +| loss | -0.0397 | +| n_updates | 35904 | +| policy_gradient_loss | -0.0253 | +| value_loss | 0.000276 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.0651 | +| time/ | | +| fps | 1322 | +| iterations | 141 | +| time_elapsed | 218 | +| total_timesteps | 288768 | +| train/ | | +| approx_kl | 0.01625771 | +| clip_fraction | 0.407 | +| clip_range | 0.0749 | +| entropy_loss | -6.87 | +| explained_variance | -0.0906 | +| learning_rate | 4.99e-05 | +| loss | -0.042 | +| n_updates | 35908 | +| policy_gradient_loss | -0.0243 | +| value_loss | 0.000259 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.0651 | +| time/ | | +| fps | 1322 | +| iterations | 142 | +| time_elapsed | 219 | +| total_timesteps | 290816 | +| train/ | | +| approx_kl | 0.014470022 | +| clip_fraction | 0.357 | +| clip_range | 0.0749 | +| entropy_loss | -6.79 | +| explained_variance | 0.219 | +| learning_rate | 4.99e-05 | +| loss | -0.0352 | +| n_updates | 35912 | +| policy_gradient_loss | -0.0221 | +| value_loss | 0.000159 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.0654 | +| time/ | | +| fps | 1322 | +| iterations | 143 | +| time_elapsed | 221 | +| total_timesteps | 292864 | +| train/ | | +| approx_kl | 0.014116779 | +| clip_fraction | 0.339 | +| clip_range | 0.0749 | +| entropy_loss | -6.88 | +| explained_variance | 0.154 | +| learning_rate | 4.99e-05 | +| loss | -0.0339 | +| n_updates | 35916 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000252 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.0648 | +| time/ | | +| fps | 1322 | +| iterations | 144 | +| time_elapsed | 222 | +| total_timesteps | 294912 | +| train/ | | +| approx_kl | 0.013995226 | +| clip_fraction | 0.366 | +| clip_range | 0.0749 | +| entropy_loss | -6.76 | +| explained_variance | 0.325 | +| learning_rate | 4.99e-05 | +| loss | -0.0303 | +| n_updates | 35920 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000345 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.0562 | +| time/ | | +| fps | 1322 | +| iterations | 145 | +| time_elapsed | 224 | +| total_timesteps | 296960 | +| train/ | | +| approx_kl | 0.01690873 | +| clip_fraction | 0.339 | +| clip_range | 0.0749 | +| entropy_loss | -6.5 | +| explained_variance | 0.35 | +| learning_rate | 4.99e-05 | +| loss | -0.0314 | +| n_updates | 35924 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000245 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.0562 | +| time/ | | +| fps | 1322 | +| iterations | 146 | +| time_elapsed | 226 | +| total_timesteps | 299008 | +| train/ | | +| approx_kl | 0.015197494 | +| clip_fraction | 0.341 | +| clip_range | 0.0749 | +| entropy_loss | -6.65 | +| explained_variance | 0.154 | +| learning_rate | 4.99e-05 | +| loss | -0.0306 | +| n_updates | 35928 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000302 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.0567 | +| time/ | | +| fps | 1322 | +| iterations | 147 | +| time_elapsed | 227 | +| total_timesteps | 301056 | +| train/ | | +| approx_kl | 0.015539947 | +| clip_fraction | 0.375 | +| clip_range | 0.0749 | +| entropy_loss | -6.92 | +| explained_variance | -0.286 | +| learning_rate | 4.99e-05 | +| loss | -0.0378 | +| n_updates | 35932 | +| policy_gradient_loss | -0.023 | +| value_loss | 0.000188 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.0502 | +| time/ | | +| fps | 1322 | +| iterations | 148 | +| time_elapsed | 229 | +| total_timesteps | 303104 | +| train/ | | +| approx_kl | 0.017454272 | +| clip_fraction | 0.357 | +| clip_range | 0.0749 | +| entropy_loss | -6.79 | +| explained_variance | 0.0673 | +| learning_rate | 4.99e-05 | +| loss | -0.0339 | +| n_updates | 35936 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000307 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.053 | +| time/ | | +| fps | 1322 | +| iterations | 149 | +| time_elapsed | 230 | +| total_timesteps | 305152 | +| train/ | | +| approx_kl | 0.013709943 | +| clip_fraction | 0.332 | +| clip_range | 0.0749 | +| entropy_loss | -6.61 | +| explained_variance | 0.34 | +| learning_rate | 4.99e-05 | +| loss | -0.0258 | +| n_updates | 35940 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000282 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.0634 | +| time/ | | +| fps | 1321 | +| iterations | 150 | +| time_elapsed | 232 | +| total_timesteps | 307200 | +| train/ | | +| approx_kl | 0.015982304 | +| clip_fraction | 0.336 | +| clip_range | 0.0749 | +| entropy_loss | -6.79 | +| explained_variance | -0.0213 | +| learning_rate | 4.99e-05 | +| loss | -0.0291 | +| n_updates | 35944 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000507 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.0634 | +| time/ | | +| fps | 1322 | +| iterations | 151 | +| time_elapsed | 233 | +| total_timesteps | 309248 | +| train/ | | +| approx_kl | 0.015972883 | +| clip_fraction | 0.363 | +| clip_range | 0.0749 | +| entropy_loss | -6.87 | +| explained_variance | -0.105 | +| learning_rate | 4.99e-05 | +| loss | -0.0415 | +| n_updates | 35948 | +| policy_gradient_loss | -0.0242 | +| value_loss | 0.000307 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.0615 | +| time/ | | +| fps | 1322 | +| iterations | 152 | +| time_elapsed | 235 | +| total_timesteps | 311296 | +| train/ | | +| approx_kl | 0.01574542 | +| clip_fraction | 0.381 | +| clip_range | 0.0749 | +| entropy_loss | -6.95 | +| explained_variance | -0.28 | +| learning_rate | 4.99e-05 | +| loss | -0.0366 | +| n_updates | 35952 | +| policy_gradient_loss | -0.0236 | +| value_loss | 0.000157 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.066 | +| time/ | | +| fps | 1322 | +| iterations | 153 | +| time_elapsed | 236 | +| total_timesteps | 313344 | +| train/ | | +| approx_kl | 0.016249144 | +| clip_fraction | 0.367 | +| clip_range | 0.0749 | +| entropy_loss | -6.73 | +| explained_variance | 0.0839 | +| learning_rate | 4.99e-05 | +| loss | -0.0358 | +| n_updates | 35956 | +| policy_gradient_loss | -0.0219 | +| value_loss | 0.000237 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.066 | +| time/ | | +| fps | 1322 | +| iterations | 154 | +| time_elapsed | 238 | +| total_timesteps | 315392 | +| train/ | | +| approx_kl | 0.012670524 | +| clip_fraction | 0.336 | +| clip_range | 0.0749 | +| entropy_loss | -6.05 | +| explained_variance | 0.502 | +| learning_rate | 4.99e-05 | +| loss | -0.0315 | +| n_updates | 35960 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000295 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0709 | +| time/ | | +| fps | 1322 | +| iterations | 155 | +| time_elapsed | 240 | +| total_timesteps | 317440 | +| train/ | | +| approx_kl | 0.017762633 | +| clip_fraction | 0.367 | +| clip_range | 0.0749 | +| entropy_loss | -6.78 | +| explained_variance | 0.0154 | +| learning_rate | 4.99e-05 | +| loss | -0.0358 | +| n_updates | 35964 | +| policy_gradient_loss | -0.023 | +| value_loss | 0.000221 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0709 | +| time/ | | +| fps | 1322 | +| iterations | 156 | +| time_elapsed | 241 | +| total_timesteps | 319488 | +| train/ | | +| approx_kl | 0.015252376 | +| clip_fraction | 0.351 | +| clip_range | 0.0749 | +| entropy_loss | -6.74 | +| explained_variance | 0.171 | +| learning_rate | 4.99e-05 | +| loss | -0.0341 | +| n_updates | 35968 | +| policy_gradient_loss | -0.0221 | +| value_loss | 0.000383 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0712 | +| time/ | | +| fps | 1322 | +| iterations | 157 | +| time_elapsed | 243 | +| total_timesteps | 321536 | +| train/ | | +| approx_kl | 0.01470149 | +| clip_fraction | 0.347 | +| clip_range | 0.0749 | +| entropy_loss | -6.8 | +| explained_variance | 0.249 | +| learning_rate | 4.99e-05 | +| loss | -0.036 | +| n_updates | 35972 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000236 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.0713 | +| time/ | | +| fps | 1323 | +| iterations | 158 | +| time_elapsed | 244 | +| total_timesteps | 323584 | +| train/ | | +| approx_kl | 0.015488522 | +| clip_fraction | 0.381 | +| clip_range | 0.0749 | +| entropy_loss | -6.96 | +| explained_variance | -0.0125 | +| learning_rate | 4.99e-05 | +| loss | -0.036 | +| n_updates | 35976 | +| policy_gradient_loss | -0.0228 | +| value_loss | 0.000307 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0639 | +| time/ | | +| fps | 1323 | +| iterations | 159 | +| time_elapsed | 246 | +| total_timesteps | 325632 | +| train/ | | +| approx_kl | 0.014249876 | +| clip_fraction | 0.342 | +| clip_range | 0.0749 | +| entropy_loss | -6.86 | +| explained_variance | 0.25 | +| learning_rate | 4.99e-05 | +| loss | -0.0324 | +| n_updates | 35980 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000288 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.0604 | +| time/ | | +| fps | 1323 | +| iterations | 160 | +| time_elapsed | 247 | +| total_timesteps | 327680 | +| train/ | | +| approx_kl | 0.01548392 | +| clip_fraction | 0.377 | +| clip_range | 0.0749 | +| entropy_loss | -6.35 | +| explained_variance | 0.245 | +| learning_rate | 4.99e-05 | +| loss | -0.0347 | +| n_updates | 35984 | +| policy_gradient_loss | -0.0228 | +| value_loss | 0.000178 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.0604 | +| time/ | | +| fps | 1323 | +| iterations | 161 | +| time_elapsed | 249 | +| total_timesteps | 329728 | +| train/ | | +| approx_kl | 0.01425706 | +| clip_fraction | 0.353 | +| clip_range | 0.0749 | +| entropy_loss | -6.98 | +| explained_variance | -0.112 | +| learning_rate | 4.99e-05 | +| loss | -0.0331 | +| n_updates | 35988 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000281 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.0501 | +| time/ | | +| fps | 1323 | +| iterations | 162 | +| time_elapsed | 250 | +| total_timesteps | 331776 | +| train/ | | +| approx_kl | 0.014087716 | +| clip_fraction | 0.338 | +| clip_range | 0.0749 | +| entropy_loss | -6.45 | +| explained_variance | 0.555 | +| learning_rate | 4.99e-05 | +| loss | -0.0321 | +| n_updates | 35992 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.0507 | +| time/ | | +| fps | 1323 | +| iterations | 163 | +| time_elapsed | 252 | +| total_timesteps | 333824 | +| train/ | | +| approx_kl | 0.013582917 | +| clip_fraction | 0.331 | +| clip_range | 0.0749 | +| entropy_loss | -6.61 | +| explained_variance | 0.292 | +| learning_rate | 4.99e-05 | +| loss | -0.0283 | +| n_updates | 35996 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000228 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.0469 | +| time/ | | +| fps | 1323 | +| iterations | 164 | +| time_elapsed | 253 | +| total_timesteps | 335872 | +| train/ | | +| approx_kl | 0.012945811 | +| clip_fraction | 0.325 | +| clip_range | 0.0749 | +| entropy_loss | -6.53 | +| explained_variance | 0.296 | +| learning_rate | 4.99e-05 | +| loss | -0.033 | +| n_updates | 36000 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000345 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0476 | +| time/ | | +| fps | 1324 | +| iterations | 165 | +| time_elapsed | 255 | +| total_timesteps | 337920 | +| train/ | | +| approx_kl | 0.013503397 | +| clip_fraction | 0.351 | +| clip_range | 0.0749 | +| entropy_loss | -6.9 | +| explained_variance | 0.236 | +| learning_rate | 4.99e-05 | +| loss | -0.0344 | +| n_updates | 36004 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000225 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.0476 | +| time/ | | +| fps | 1323 | +| iterations | 166 | +| time_elapsed | 256 | +| total_timesteps | 339968 | +| train/ | | +| approx_kl | 0.013872141 | +| clip_fraction | 0.35 | +| clip_range | 0.0749 | +| entropy_loss | -6.57 | +| explained_variance | 0.283 | +| learning_rate | 4.99e-05 | +| loss | -0.0275 | +| n_updates | 36008 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000278 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.049 | +| time/ | | +| fps | 1323 | +| iterations | 167 | +| time_elapsed | 258 | +| total_timesteps | 342016 | +| train/ | | +| approx_kl | 0.017259609 | +| clip_fraction | 0.364 | +| clip_range | 0.0749 | +| entropy_loss | -6.65 | +| explained_variance | -0.133 | +| learning_rate | 4.99e-05 | +| loss | -0.0351 | +| n_updates | 36012 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000292 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.0452 | +| time/ | | +| fps | 1324 | +| iterations | 168 | +| time_elapsed | 259 | +| total_timesteps | 344064 | +| train/ | | +| approx_kl | 0.016628854 | +| clip_fraction | 0.37 | +| clip_range | 0.0749 | +| entropy_loss | -6.73 | +| explained_variance | 0.0668 | +| learning_rate | 4.99e-05 | +| loss | -0.0364 | +| n_updates | 36016 | +| policy_gradient_loss | -0.0227 | +| value_loss | 0.00022 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.0328 | +| time/ | | +| fps | 1324 | +| iterations | 169 | +| time_elapsed | 261 | +| total_timesteps | 346112 | +| train/ | | +| approx_kl | 0.015905213 | +| clip_fraction | 0.369 | +| clip_range | 0.0749 | +| entropy_loss | -6.61 | +| explained_variance | 0.105 | +| learning_rate | 4.99e-05 | +| loss | -0.0339 | +| n_updates | 36020 | +| policy_gradient_loss | -0.0219 | +| value_loss | 0.000316 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.0328 | +| time/ | | +| fps | 1324 | +| iterations | 170 | +| time_elapsed | 262 | +| total_timesteps | 348160 | +| train/ | | +| approx_kl | 0.01471313 | +| clip_fraction | 0.346 | +| clip_range | 0.0749 | +| entropy_loss | -6.74 | +| explained_variance | 0.313 | +| learning_rate | 4.99e-05 | +| loss | -0.0347 | +| n_updates | 36024 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000316 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.0245 | +| time/ | | +| fps | 1324 | +| iterations | 171 | +| time_elapsed | 264 | +| total_timesteps | 350208 | +| train/ | | +| approx_kl | 0.017191082 | +| clip_fraction | 0.362 | +| clip_range | 0.0749 | +| entropy_loss | -6.8 | +| explained_variance | -0.137 | +| learning_rate | 4.99e-05 | +| loss | -0.0362 | +| n_updates | 36028 | +| policy_gradient_loss | -0.0228 | +| value_loss | 0.000262 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0262 | +| time/ | | +| fps | 1323 | +| iterations | 172 | +| time_elapsed | 266 | +| total_timesteps | 352256 | +| train/ | | +| approx_kl | 0.014433473 | +| clip_fraction | 0.34 | +| clip_range | 0.0749 | +| entropy_loss | -6.72 | +| explained_variance | 0.15 | +| learning_rate | 4.99e-05 | +| loss | -0.0255 | +| n_updates | 36032 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.0003 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0262 | +| time/ | | +| fps | 1323 | +| iterations | 173 | +| time_elapsed | 267 | +| total_timesteps | 354304 | +| train/ | | +| approx_kl | 0.012591593 | +| clip_fraction | 0.322 | +| clip_range | 0.0749 | +| entropy_loss | -6.34 | +| explained_variance | 0.452 | +| learning_rate | 4.99e-05 | +| loss | -0.0332 | +| n_updates | 36036 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000208 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0238 | +| time/ | | +| fps | 1323 | +| iterations | 174 | +| time_elapsed | 269 | +| total_timesteps | 356352 | +| train/ | | +| approx_kl | 0.014559074 | +| clip_fraction | 0.351 | +| clip_range | 0.0749 | +| entropy_loss | -6.91 | +| explained_variance | -0.095 | +| learning_rate | 4.99e-05 | +| loss | -0.0294 | +| n_updates | 36040 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000216 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0234 | +| time/ | | +| fps | 1323 | +| iterations | 175 | +| time_elapsed | 270 | +| total_timesteps | 358400 | +| train/ | | +| approx_kl | 0.01419074 | +| clip_fraction | 0.377 | +| clip_range | 0.0749 | +| entropy_loss | -7.13 | +| explained_variance | -0.0561 | +| learning_rate | 4.99e-05 | +| loss | -0.0376 | +| n_updates | 36044 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000128 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.031 | +| time/ | | +| fps | 1324 | +| iterations | 176 | +| time_elapsed | 272 | +| total_timesteps | 360448 | +| train/ | | +| approx_kl | 0.014724948 | +| clip_fraction | 0.351 | +| clip_range | 0.0749 | +| entropy_loss | -6.51 | +| explained_variance | 0.115 | +| learning_rate | 4.99e-05 | +| loss | -0.0284 | +| n_updates | 36048 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.00028 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0294 | +| time/ | | +| fps | 1324 | +| iterations | 177 | +| time_elapsed | 273 | +| total_timesteps | 362496 | +| train/ | | +| approx_kl | 0.015626546 | +| clip_fraction | 0.312 | +| clip_range | 0.0749 | +| entropy_loss | -6.33 | +| explained_variance | 0.19 | +| learning_rate | 4.99e-05 | +| loss | -0.0259 | +| n_updates | 36052 | +| policy_gradient_loss | -0.0147 | +| value_loss | 0.000875 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0246 | +| time/ | | +| fps | 1324 | +| iterations | 178 | +| time_elapsed | 275 | +| total_timesteps | 364544 | +| train/ | | +| approx_kl | 0.014229306 | +| clip_fraction | 0.357 | +| clip_range | 0.0749 | +| entropy_loss | -6.9 | +| explained_variance | -0.17 | +| learning_rate | 4.99e-05 | +| loss | -0.0326 | +| n_updates | 36056 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000272 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.019 | +| time/ | | +| fps | 1324 | +| iterations | 179 | +| time_elapsed | 276 | +| total_timesteps | 366592 | +| train/ | | +| approx_kl | 0.01516144 | +| clip_fraction | 0.377 | +| clip_range | 0.0749 | +| entropy_loss | -6.5 | +| explained_variance | 0.154 | +| learning_rate | 4.99e-05 | +| loss | -0.0371 | +| n_updates | 36060 | +| policy_gradient_loss | -0.0234 | +| value_loss | 0.000268 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0191 | +| time/ | | +| fps | 1324 | +| iterations | 180 | +| time_elapsed | 278 | +| total_timesteps | 368640 | +| train/ | | +| approx_kl | 0.015720455 | +| clip_fraction | 0.361 | +| clip_range | 0.0749 | +| entropy_loss | -6.5 | +| explained_variance | 0.292 | +| learning_rate | 4.99e-05 | +| loss | -0.0377 | +| n_updates | 36064 | +| policy_gradient_loss | -0.0228 | +| value_loss | 0.000205 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0186 | +| time/ | | +| fps | 1324 | +| iterations | 181 | +| time_elapsed | 279 | +| total_timesteps | 370688 | +| train/ | | +| approx_kl | 0.015897896 | +| clip_fraction | 0.361 | +| clip_range | 0.0749 | +| entropy_loss | -6.86 | +| explained_variance | -0.0477 | +| learning_rate | 4.99e-05 | +| loss | -0.0326 | +| n_updates | 36068 | +| policy_gradient_loss | -0.0219 | +| value_loss | 0.000297 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0186 | +| time/ | | +| fps | 1324 | +| iterations | 182 | +| time_elapsed | 281 | +| total_timesteps | 372736 | +| train/ | | +| approx_kl | 0.016652256 | +| clip_fraction | 0.367 | +| clip_range | 0.0749 | +| entropy_loss | -6.92 | +| explained_variance | -0.1 | +| learning_rate | 4.99e-05 | +| loss | -0.0342 | +| n_updates | 36072 | +| policy_gradient_loss | -0.0237 | +| value_loss | 0.000319 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0122 | +| time/ | | +| fps | 1324 | +| iterations | 183 | +| time_elapsed | 282 | +| total_timesteps | 374784 | +| train/ | | +| approx_kl | 0.013223364 | +| clip_fraction | 0.353 | +| clip_range | 0.0749 | +| entropy_loss | -6.92 | +| explained_variance | 0.0354 | +| learning_rate | 4.99e-05 | +| loss | -0.0335 | +| n_updates | 36076 | +| policy_gradient_loss | -0.0223 | +| value_loss | 0.000201 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0152 | +| time/ | | +| fps | 1324 | +| iterations | 184 | +| time_elapsed | 284 | +| total_timesteps | 376832 | +| train/ | | +| approx_kl | 0.013329556 | +| clip_fraction | 0.349 | +| clip_range | 0.0749 | +| entropy_loss | -7.04 | +| explained_variance | -0.134 | +| learning_rate | 4.99e-05 | +| loss | -0.0378 | +| n_updates | 36080 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000304 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.0102 | +| time/ | | +| fps | 1324 | +| iterations | 185 | +| time_elapsed | 286 | +| total_timesteps | 378880 | +| train/ | | +| approx_kl | 0.013698123 | +| clip_fraction | 0.333 | +| clip_range | 0.0749 | +| entropy_loss | -6.37 | +| explained_variance | 0.228 | +| learning_rate | 4.99e-05 | +| loss | -0.0364 | +| n_updates | 36084 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.00032 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.00803 | +| time/ | | +| fps | 1324 | +| iterations | 186 | +| time_elapsed | 287 | +| total_timesteps | 380928 | +| train/ | | +| approx_kl | 0.015657268 | +| clip_fraction | 0.363 | +| clip_range | 0.0749 | +| entropy_loss | -6.52 | +| explained_variance | 0.403 | +| learning_rate | 4.99e-05 | +| loss | -0.0336 | +| n_updates | 36088 | +| policy_gradient_loss | -0.0221 | +| value_loss | 0.000205 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.00803 | +| time/ | | +| fps | 1324 | +| iterations | 187 | +| time_elapsed | 289 | +| total_timesteps | 382976 | +| train/ | | +| approx_kl | 0.016041458 | +| clip_fraction | 0.345 | +| clip_range | 0.0749 | +| entropy_loss | -6.18 | +| explained_variance | 0.376 | +| learning_rate | 4.99e-05 | +| loss | -0.0312 | +| n_updates | 36092 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000277 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.00878 | +| time/ | | +| fps | 1324 | +| iterations | 188 | +| time_elapsed | 290 | +| total_timesteps | 385024 | +| train/ | | +| approx_kl | 0.017466439 | +| clip_fraction | 0.331 | +| clip_range | 0.0749 | +| entropy_loss | -6.55 | +| explained_variance | 0.321 | +| learning_rate | 4.99e-05 | +| loss | -0.0332 | +| n_updates | 36096 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000264 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0111 | +| time/ | | +| fps | 1323 | +| iterations | 189 | +| time_elapsed | 292 | +| total_timesteps | 387072 | +| train/ | | +| approx_kl | 0.015631916 | +| clip_fraction | 0.344 | +| clip_range | 0.0749 | +| entropy_loss | -6.94 | +| explained_variance | 0.0105 | +| learning_rate | 4.99e-05 | +| loss | -0.0331 | +| n_updates | 36100 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.00028 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.00784 | +| time/ | | +| fps | 1323 | +| iterations | 190 | +| time_elapsed | 294 | +| total_timesteps | 389120 | +| train/ | | +| approx_kl | 0.014032049 | +| clip_fraction | 0.364 | +| clip_range | 0.0749 | +| entropy_loss | -6.92 | +| explained_variance | 0.0241 | +| learning_rate | 4.99e-05 | +| loss | -0.038 | +| n_updates | 36104 | +| policy_gradient_loss | -0.0232 | +| value_loss | 0.000192 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.00377 | +| time/ | | +| fps | 1323 | +| iterations | 191 | +| time_elapsed | 295 | +| total_timesteps | 391168 | +| train/ | | +| approx_kl | 0.01488088 | +| clip_fraction | 0.354 | +| clip_range | 0.0749 | +| entropy_loss | -6.55 | +| explained_variance | 0.373 | +| learning_rate | 4.99e-05 | +| loss | -0.0306 | +| n_updates | 36108 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.00024 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.00377 | +| time/ | | +| fps | 1323 | +| iterations | 192 | +| time_elapsed | 297 | +| total_timesteps | 393216 | +| train/ | | +| approx_kl | 0.012488872 | +| clip_fraction | 0.333 | +| clip_range | 0.0749 | +| entropy_loss | -6.68 | +| explained_variance | 0.404 | +| learning_rate | 4.99e-05 | +| loss | -0.0313 | +| n_updates | 36112 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000184 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.00501 | +| time/ | | +| fps | 1322 | +| iterations | 193 | +| time_elapsed | 298 | +| total_timesteps | 395264 | +| train/ | | +| approx_kl | 0.016821446 | +| clip_fraction | 0.347 | +| clip_range | 0.0749 | +| entropy_loss | -6.88 | +| explained_variance | 0.107 | +| learning_rate | 4.99e-05 | +| loss | -0.0319 | +| n_updates | 36116 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.00034 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.00646 | +| time/ | | +| fps | 1322 | +| iterations | 194 | +| time_elapsed | 300 | +| total_timesteps | 397312 | +| train/ | | +| approx_kl | 0.0151121635 | +| clip_fraction | 0.331 | +| clip_range | 0.0749 | +| entropy_loss | -6.83 | +| explained_variance | 0.317 | +| learning_rate | 4.99e-05 | +| loss | -0.0307 | +| n_updates | 36120 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000246 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.00701 | +| time/ | | +| fps | 1322 | +| iterations | 195 | +| time_elapsed | 302 | +| total_timesteps | 399360 | +| train/ | | +| approx_kl | 0.016020402 | +| clip_fraction | 0.363 | +| clip_range | 0.0749 | +| entropy_loss | -6.74 | +| explained_variance | 0.000723 | +| learning_rate | 4.99e-05 | +| loss | -0.0368 | +| n_updates | 36124 | +| policy_gradient_loss | -0.0236 | +| value_loss | 0.000241 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.0134 | +| time/ | | +| fps | 1322 | +| iterations | 196 | +| time_elapsed | 303 | +| total_timesteps | 401408 | +| train/ | | +| approx_kl | 0.014565621 | +| clip_fraction | 0.326 | +| clip_range | 0.0749 | +| entropy_loss | -6.37 | +| explained_variance | 0.357 | +| learning_rate | 4.99e-05 | +| loss | -0.0292 | +| n_updates | 36128 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.00035 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.0126 | +| time/ | | +| fps | 1322 | +| iterations | 197 | +| time_elapsed | 305 | +| total_timesteps | 403456 | +| train/ | | +| approx_kl | 0.015179149 | +| clip_fraction | 0.356 | +| clip_range | 0.0749 | +| entropy_loss | -6.16 | +| explained_variance | 0.551 | +| learning_rate | 4.99e-05 | +| loss | -0.0312 | +| n_updates | 36132 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000199 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.00833 | +| time/ | | +| fps | 1322 | +| iterations | 198 | +| time_elapsed | 306 | +| total_timesteps | 405504 | +| train/ | | +| approx_kl | 0.012636203 | +| clip_fraction | 0.357 | +| clip_range | 0.0749 | +| entropy_loss | -6.52 | +| explained_variance | 0.373 | +| learning_rate | 4.99e-05 | +| loss | -0.0392 | +| n_updates | 36136 | +| policy_gradient_loss | -0.0222 | +| value_loss | 0.00022 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.00972 | +| time/ | | +| fps | 1322 | +| iterations | 199 | +| time_elapsed | 308 | +| total_timesteps | 407552 | +| train/ | | +| approx_kl | 0.013554292 | +| clip_fraction | 0.35 | +| clip_range | 0.0749 | +| entropy_loss | -6.54 | +| explained_variance | 0.488 | +| learning_rate | 4.99e-05 | +| loss | -0.0307 | +| n_updates | 36140 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000251 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.00391 | +| time/ | | +| fps | 1322 | +| iterations | 200 | +| time_elapsed | 309 | +| total_timesteps | 409600 | +| train/ | | +| approx_kl | 0.017089443 | +| clip_fraction | 0.365 | +| clip_range | 0.0749 | +| entropy_loss | -6.65 | +| explained_variance | 0.131 | +| learning_rate | 4.99e-05 | +| loss | -0.0306 | +| n_updates | 36144 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000189 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.0101 | +| time/ | | +| fps | 1322 | +| iterations | 201 | +| time_elapsed | 311 | +| total_timesteps | 411648 | +| train/ | | +| approx_kl | 0.015522154 | +| clip_fraction | 0.347 | +| clip_range | 0.0749 | +| entropy_loss | -6.44 | +| explained_variance | 0.368 | +| learning_rate | 4.99e-05 | +| loss | -0.0334 | +| n_updates | 36148 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000323 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.0144 | +| time/ | | +| fps | 1322 | +| iterations | 202 | +| time_elapsed | 312 | +| total_timesteps | 413696 | +| train/ | | +| approx_kl | 0.014881886 | +| clip_fraction | 0.357 | +| clip_range | 0.0749 | +| entropy_loss | -6.9 | +| explained_variance | -0.0525 | +| learning_rate | 4.99e-05 | +| loss | -0.0304 | +| n_updates | 36152 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000435 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.0144 | +| time/ | | +| fps | 1321 | +| iterations | 203 | +| time_elapsed | 314 | +| total_timesteps | 415744 | +| train/ | | +| approx_kl | 0.01619822 | +| clip_fraction | 0.354 | +| clip_range | 0.0749 | +| entropy_loss | -6.64 | +| explained_variance | 0.204 | +| learning_rate | 4.99e-05 | +| loss | -0.0382 | +| n_updates | 36156 | +| policy_gradient_loss | -0.0225 | +| value_loss | 0.00031 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.0144 | +| time/ | | +| fps | 1321 | +| iterations | 204 | +| time_elapsed | 316 | +| total_timesteps | 417792 | +| train/ | | +| approx_kl | 0.013784147 | +| clip_fraction | 0.352 | +| clip_range | 0.0749 | +| entropy_loss | -6.87 | +| explained_variance | 0.0619 | +| learning_rate | 4.99e-05 | +| loss | -0.0291 | +| n_updates | 36160 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000257 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.0144 | +| time/ | | +| fps | 1321 | +| iterations | 205 | +| time_elapsed | 317 | +| total_timesteps | 419840 | +| train/ | | +| approx_kl | 0.015620446 | +| clip_fraction | 0.366 | +| clip_range | 0.0749 | +| entropy_loss | -6.99 | +| explained_variance | -0.0365 | +| learning_rate | 4.99e-05 | +| loss | -0.0337 | +| n_updates | 36164 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000323 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0136 | +| time/ | | +| fps | 1321 | +| iterations | 206 | +| time_elapsed | 319 | +| total_timesteps | 421888 | +| train/ | | +| approx_kl | 0.015420307 | +| clip_fraction | 0.35 | +| clip_range | 0.0749 | +| entropy_loss | -7.04 | +| explained_variance | -0.197 | +| learning_rate | 4.99e-05 | +| loss | -0.0318 | +| n_updates | 36168 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000273 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.00712 | +| time/ | | +| fps | 1321 | +| iterations | 207 | +| time_elapsed | 320 | +| total_timesteps | 423936 | +| train/ | | +| approx_kl | 0.015425601 | +| clip_fraction | 0.381 | +| clip_range | 0.0749 | +| entropy_loss | -7.02 | +| explained_variance | -0.00313 | +| learning_rate | 4.99e-05 | +| loss | -0.0363 | +| n_updates | 36172 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.00024 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.00564 | +| time/ | | +| fps | 1321 | +| iterations | 208 | +| time_elapsed | 322 | +| total_timesteps | 425984 | +| train/ | | +| approx_kl | 0.01779933 | +| clip_fraction | 0.365 | +| clip_range | 0.0749 | +| entropy_loss | -6.3 | +| explained_variance | 0.594 | +| learning_rate | 4.99e-05 | +| loss | -0.0337 | +| n_updates | 36176 | +| policy_gradient_loss | -0.0225 | +| value_loss | 0.000131 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0092 | +| time/ | | +| fps | 1322 | +| iterations | 209 | +| time_elapsed | 323 | +| total_timesteps | 428032 | +| train/ | | +| approx_kl | 0.016780287 | +| clip_fraction | 0.343 | +| clip_range | 0.0749 | +| entropy_loss | -5.72 | +| explained_variance | 0.742 | +| learning_rate | 4.99e-05 | +| loss | -0.028 | +| n_updates | 36180 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000127 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.00947 | +| time/ | | +| fps | 1322 | +| iterations | 210 | +| time_elapsed | 325 | +| total_timesteps | 430080 | +| train/ | | +| approx_kl | 0.014166538 | +| clip_fraction | 0.329 | +| clip_range | 0.0749 | +| entropy_loss | -6.37 | +| explained_variance | 0.33 | +| learning_rate | 4.99e-05 | +| loss | -0.0324 | +| n_updates | 36184 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000154 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.00947 | +| time/ | | +| fps | 1322 | +| iterations | 211 | +| time_elapsed | 326 | +| total_timesteps | 432128 | +| train/ | | +| approx_kl | 0.0202356 | +| clip_fraction | 0.361 | +| clip_range | 0.0749 | +| entropy_loss | -6.59 | +| explained_variance | 0.276 | +| learning_rate | 4.99e-05 | +| loss | -0.0323 | +| n_updates | 36188 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000164 | +--------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.0158 | +| time/ | | +| fps | 1322 | +| iterations | 212 | +| time_elapsed | 328 | +| total_timesteps | 434176 | +| train/ | | +| approx_kl | 0.0175194 | +| clip_fraction | 0.334 | +| clip_range | 0.0749 | +| entropy_loss | -6.82 | +| explained_variance | 0.227 | +| learning_rate | 4.99e-05 | +| loss | -0.0325 | +| n_updates | 36192 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000237 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.0158 | +| time/ | | +| fps | 1322 | +| iterations | 213 | +| time_elapsed | 329 | +| total_timesteps | 436224 | +| train/ | | +| approx_kl | 0.015655348 | +| clip_fraction | 0.341 | +| clip_range | 0.0749 | +| entropy_loss | -6.57 | +| explained_variance | 0.268 | +| learning_rate | 4.99e-05 | +| loss | -0.0344 | +| n_updates | 36196 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.00021 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0184 | +| time/ | | +| fps | 1322 | +| iterations | 214 | +| time_elapsed | 331 | +| total_timesteps | 438272 | +| train/ | | +| approx_kl | 0.014630396 | +| clip_fraction | 0.361 | +| clip_range | 0.0749 | +| entropy_loss | -6.77 | +| explained_variance | -0.0507 | +| learning_rate | 4.99e-05 | +| loss | -0.0308 | +| n_updates | 36200 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000228 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0184 | +| time/ | | +| fps | 1322 | +| iterations | 215 | +| time_elapsed | 333 | +| total_timesteps | 440320 | +| train/ | | +| approx_kl | 0.015632933 | +| clip_fraction | 0.359 | +| clip_range | 0.0749 | +| entropy_loss | -6.2 | +| explained_variance | 0.297 | +| learning_rate | 4.99e-05 | +| loss | -0.0347 | +| n_updates | 36204 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000337 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.0184 | +| time/ | | +| fps | 1322 | +| iterations | 216 | +| time_elapsed | 334 | +| total_timesteps | 442368 | +| train/ | | +| approx_kl | 0.015490308 | +| clip_fraction | 0.348 | +| clip_range | 0.0749 | +| entropy_loss | -6.8 | +| explained_variance | -0.11 | +| learning_rate | 4.99e-05 | +| loss | -0.0331 | +| n_updates | 36208 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000289 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0189 | +| time/ | | +| fps | 1322 | +| iterations | 217 | +| time_elapsed | 336 | +| total_timesteps | 444416 | +| train/ | | +| approx_kl | 0.0153702125 | +| clip_fraction | 0.353 | +| clip_range | 0.0749 | +| entropy_loss | -6.64 | +| explained_variance | 0.0441 | +| learning_rate | 4.99e-05 | +| loss | -0.03 | +| n_updates | 36212 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000322 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.0224 | +| time/ | | +| fps | 1323 | +| iterations | 218 | +| time_elapsed | 337 | +| total_timesteps | 446464 | +| train/ | | +| approx_kl | 0.015236544 | +| clip_fraction | 0.374 | +| clip_range | 0.0749 | +| entropy_loss | -6.76 | +| explained_variance | 0.172 | +| learning_rate | 4.99e-05 | +| loss | -0.0307 | +| n_updates | 36216 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000227 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.0274 | +| time/ | | +| fps | 1322 | +| iterations | 219 | +| time_elapsed | 339 | +| total_timesteps | 448512 | +| train/ | | +| approx_kl | 0.014489843 | +| clip_fraction | 0.375 | +| clip_range | 0.0749 | +| entropy_loss | -6.4 | +| explained_variance | 0.442 | +| learning_rate | 4.99e-05 | +| loss | -0.0382 | +| n_updates | 36220 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000211 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.0338 | +| time/ | | +| fps | 1322 | +| iterations | 220 | +| time_elapsed | 340 | +| total_timesteps | 450560 | +| train/ | | +| approx_kl | 0.014671607 | +| clip_fraction | 0.345 | +| clip_range | 0.0749 | +| entropy_loss | -6.63 | +| explained_variance | 0.163 | +| learning_rate | 4.99e-05 | +| loss | -0.0312 | +| n_updates | 36224 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000211 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0335 | +| time/ | | +| fps | 1322 | +| iterations | 221 | +| time_elapsed | 342 | +| total_timesteps | 452608 | +| train/ | | +| approx_kl | 0.016046865 | +| clip_fraction | 0.363 | +| clip_range | 0.0749 | +| entropy_loss | -6.6 | +| explained_variance | 0.235 | +| learning_rate | 4.99e-05 | +| loss | -0.0339 | +| n_updates | 36228 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000245 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0454 | +| time/ | | +| fps | 1322 | +| iterations | 222 | +| time_elapsed | 343 | +| total_timesteps | 454656 | +| train/ | | +| approx_kl | 0.016267851 | +| clip_fraction | 0.328 | +| clip_range | 0.0749 | +| entropy_loss | -6.5 | +| explained_variance | 0.196 | +| learning_rate | 4.99e-05 | +| loss | -0.0283 | +| n_updates | 36232 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000291 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0485 | +| time/ | | +| fps | 1322 | +| iterations | 223 | +| time_elapsed | 345 | +| total_timesteps | 456704 | +| train/ | | +| approx_kl | 0.013507914 | +| clip_fraction | 0.339 | +| clip_range | 0.0749 | +| entropy_loss | -6.09 | +| explained_variance | 0.143 | +| learning_rate | 4.99e-05 | +| loss | -0.019 | +| n_updates | 36236 | +| policy_gradient_loss | -0.015 | +| value_loss | 0.000738 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0481 | +| time/ | | +| fps | 1322 | +| iterations | 224 | +| time_elapsed | 346 | +| total_timesteps | 458752 | +| train/ | | +| approx_kl | 0.016922329 | +| clip_fraction | 0.37 | +| clip_range | 0.0749 | +| entropy_loss | -6.21 | +| explained_variance | 0.487 | +| learning_rate | 4.99e-05 | +| loss | -0.0379 | +| n_updates | 36240 | +| policy_gradient_loss | -0.0228 | +| value_loss | 0.000226 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0507 | +| time/ | | +| fps | 1322 | +| iterations | 225 | +| time_elapsed | 348 | +| total_timesteps | 460800 | +| train/ | | +| approx_kl | 0.015668975 | +| clip_fraction | 0.374 | +| clip_range | 0.0749 | +| entropy_loss | -6.33 | +| explained_variance | 0.314 | +| learning_rate | 4.99e-05 | +| loss | -0.0398 | +| n_updates | 36244 | +| policy_gradient_loss | -0.0225 | +| value_loss | 0.000291 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0519 | +| time/ | | +| fps | 1322 | +| iterations | 226 | +| time_elapsed | 349 | +| total_timesteps | 462848 | +| train/ | | +| approx_kl | 0.01822195 | +| clip_fraction | 0.372 | +| clip_range | 0.0749 | +| entropy_loss | -6.5 | +| explained_variance | 0.0936 | +| learning_rate | 4.99e-05 | +| loss | -0.0342 | +| n_updates | 36248 | +| policy_gradient_loss | -0.0227 | +| value_loss | 0.000283 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0519 | +| time/ | | +| fps | 1322 | +| iterations | 227 | +| time_elapsed | 351 | +| total_timesteps | 464896 | +| train/ | | +| approx_kl | 0.017541748 | +| clip_fraction | 0.351 | +| clip_range | 0.0749 | +| entropy_loss | -6.49 | +| explained_variance | 0.371 | +| learning_rate | 4.99e-05 | +| loss | -0.0344 | +| n_updates | 36252 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000272 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0519 | +| time/ | | +| fps | 1322 | +| iterations | 228 | +| time_elapsed | 353 | +| total_timesteps | 466944 | +| train/ | | +| approx_kl | 0.015950384 | +| clip_fraction | 0.384 | +| clip_range | 0.0749 | +| entropy_loss | -6.94 | +| explained_variance | -0.109 | +| learning_rate | 4.99e-05 | +| loss | -0.0331 | +| n_updates | 36256 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000217 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0548 | +| time/ | | +| fps | 1322 | +| iterations | 229 | +| time_elapsed | 354 | +| total_timesteps | 468992 | +| train/ | | +| approx_kl | 0.017340664 | +| clip_fraction | 0.367 | +| clip_range | 0.0749 | +| entropy_loss | -6.88 | +| explained_variance | -0.118 | +| learning_rate | 4.99e-05 | +| loss | -0.0321 | +| n_updates | 36260 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000292 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0568 | +| time/ | | +| fps | 1322 | +| iterations | 230 | +| time_elapsed | 356 | +| total_timesteps | 471040 | +| train/ | | +| approx_kl | 0.019072033 | +| clip_fraction | 0.38 | +| clip_range | 0.0749 | +| entropy_loss | -6.63 | +| explained_variance | 0.178 | +| learning_rate | 4.99e-05 | +| loss | -0.0328 | +| n_updates | 36264 | +| policy_gradient_loss | -0.0223 | +| value_loss | 0.000232 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0566 | +| time/ | | +| fps | 1322 | +| iterations | 231 | +| time_elapsed | 357 | +| total_timesteps | 473088 | +| train/ | | +| approx_kl | 0.014886767 | +| clip_fraction | 0.38 | +| clip_range | 0.0749 | +| entropy_loss | -6.61 | +| explained_variance | 0.2 | +| learning_rate | 4.99e-05 | +| loss | -0.0351 | +| n_updates | 36268 | +| policy_gradient_loss | -0.0223 | +| value_loss | 0.000297 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0619 | +| time/ | | +| fps | 1322 | +| iterations | 232 | +| time_elapsed | 359 | +| total_timesteps | 475136 | +| train/ | | +| approx_kl | 0.016398529 | +| clip_fraction | 0.369 | +| clip_range | 0.0749 | +| entropy_loss | -6.7 | +| explained_variance | 0.196 | +| learning_rate | 4.99e-05 | +| loss | -0.0346 | +| n_updates | 36272 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000216 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0616 | +| time/ | | +| fps | 1322 | +| iterations | 233 | +| time_elapsed | 360 | +| total_timesteps | 477184 | +| train/ | | +| approx_kl | 0.017379984 | +| clip_fraction | 0.386 | +| clip_range | 0.0749 | +| entropy_loss | -6.26 | +| explained_variance | 0.349 | +| learning_rate | 4.99e-05 | +| loss | -0.0375 | +| n_updates | 36276 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000139 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.0652 | +| time/ | | +| fps | 1322 | +| iterations | 234 | +| time_elapsed | 362 | +| total_timesteps | 479232 | +| train/ | | +| approx_kl | 0.016086608 | +| clip_fraction | 0.374 | +| clip_range | 0.0749 | +| entropy_loss | -5.91 | +| explained_variance | 0.602 | +| learning_rate | 4.99e-05 | +| loss | -0.0301 | +| n_updates | 36280 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000136 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.0615 | +| time/ | | +| fps | 1322 | +| iterations | 235 | +| time_elapsed | 363 | +| total_timesteps | 481280 | +| train/ | | +| approx_kl | 0.016284361 | +| clip_fraction | 0.371 | +| clip_range | 0.0749 | +| entropy_loss | -6.3 | +| explained_variance | 0.568 | +| learning_rate | 4.99e-05 | +| loss | -0.0296 | +| n_updates | 36284 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000112 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.0661 | +| time/ | | +| fps | 1322 | +| iterations | 236 | +| time_elapsed | 365 | +| total_timesteps | 483328 | +| train/ | | +| approx_kl | 0.016686428 | +| clip_fraction | 0.365 | +| clip_range | 0.0749 | +| entropy_loss | -6.18 | +| explained_variance | 0.392 | +| learning_rate | 4.99e-05 | +| loss | -0.031 | +| n_updates | 36288 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000157 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.0661 | +| time/ | | +| fps | 1322 | +| iterations | 237 | +| time_elapsed | 367 | +| total_timesteps | 485376 | +| train/ | | +| approx_kl | 0.017731708 | +| clip_fraction | 0.368 | +| clip_range | 0.0749 | +| entropy_loss | -6.43 | +| explained_variance | 0.159 | +| learning_rate | 4.99e-05 | +| loss | -0.0354 | +| n_updates | 36292 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000229 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.0736 | +| time/ | | +| fps | 1322 | +| iterations | 238 | +| time_elapsed | 368 | +| total_timesteps | 487424 | +| train/ | | +| approx_kl | 0.01640074 | +| clip_fraction | 0.374 | +| clip_range | 0.0749 | +| entropy_loss | -6.63 | +| explained_variance | -0.0718 | +| learning_rate | 4.99e-05 | +| loss | -0.0336 | +| n_updates | 36296 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000219 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.0739 | +| time/ | | +| fps | 1322 | +| iterations | 239 | +| time_elapsed | 370 | +| total_timesteps | 489472 | +| train/ | | +| approx_kl | 0.016747508 | +| clip_fraction | 0.319 | +| clip_range | 0.0749 | +| entropy_loss | -6.5 | +| explained_variance | 0.0408 | +| learning_rate | 4.99e-05 | +| loss | -0.0273 | +| n_updates | 36300 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.001 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.0739 | +| time/ | | +| fps | 1322 | +| iterations | 240 | +| time_elapsed | 371 | +| total_timesteps | 491520 | +| train/ | | +| approx_kl | 0.013587631 | +| clip_fraction | 0.371 | +| clip_range | 0.0749 | +| entropy_loss | -6.67 | +| explained_variance | 0.0105 | +| learning_rate | 4.99e-05 | +| loss | -0.0386 | +| n_updates | 36304 | +| policy_gradient_loss | -0.0235 | +| value_loss | 0.000407 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0742 | +| time/ | | +| fps | 1322 | +| iterations | 241 | +| time_elapsed | 373 | +| total_timesteps | 493568 | +| train/ | | +| approx_kl | 0.016656984 | +| clip_fraction | 0.389 | +| clip_range | 0.0749 | +| entropy_loss | -6.73 | +| explained_variance | -0.112 | +| learning_rate | 4.99e-05 | +| loss | -0.036 | +| n_updates | 36308 | +| policy_gradient_loss | -0.0238 | +| value_loss | 0.000252 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.06 | +| time/ | | +| fps | 1322 | +| iterations | 242 | +| time_elapsed | 374 | +| total_timesteps | 495616 | +| train/ | | +| approx_kl | 0.015521381 | +| clip_fraction | 0.381 | +| clip_range | 0.0749 | +| entropy_loss | -6.4 | +| explained_variance | 0.1 | +| learning_rate | 4.99e-05 | +| loss | -0.0367 | +| n_updates | 36312 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000315 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0652 | +| time/ | | +| fps | 1322 | +| iterations | 243 | +| time_elapsed | 376 | +| total_timesteps | 497664 | +| train/ | | +| approx_kl | 0.017067853 | +| clip_fraction | 0.362 | +| clip_range | 0.0749 | +| entropy_loss | -6.07 | +| explained_variance | 0.407 | +| learning_rate | 4.99e-05 | +| loss | -0.0295 | +| n_updates | 36316 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000284 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0661 | +| time/ | | +| fps | 1321 | +| iterations | 244 | +| time_elapsed | 378 | +| total_timesteps | 499712 | +| train/ | | +| approx_kl | 0.0152230095 | +| clip_fraction | 0.347 | +| clip_range | 0.0749 | +| entropy_loss | -6.57 | +| explained_variance | 0.247 | +| learning_rate | 4.99e-05 | +| loss | -0.0301 | +| n_updates | 36320 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000353 | +------------------------------------------ +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0661 | +| time/ | | +| fps | 1321 | +| iterations | 245 | +| time_elapsed | 379 | +| total_timesteps | 501760 | +| train/ | | +| approx_kl | 0.0170818 | +| clip_fraction | 0.394 | +| clip_range | 0.0749 | +| entropy_loss | -6.72 | +| explained_variance | 0.00227 | +| learning_rate | 4.99e-05 | +| loss | -0.0294 | +| n_updates | 36324 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000383 | +--------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0789 | +| time/ | | +| fps | 1321 | +| iterations | 246 | +| time_elapsed | 381 | +| total_timesteps | 503808 | +| train/ | | +| approx_kl | 0.0140817445 | +| clip_fraction | 0.396 | +| clip_range | 0.0749 | +| entropy_loss | -6.49 | +| explained_variance | 0.0623 | +| learning_rate | 4.99e-05 | +| loss | -0.0336 | +| n_updates | 36328 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000245 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0749 | +| time/ | | +| fps | 1321 | +| iterations | 247 | +| time_elapsed | 382 | +| total_timesteps | 505856 | +| train/ | | +| approx_kl | 0.01223812 | +| clip_fraction | 0.351 | +| clip_range | 0.0749 | +| entropy_loss | -6.27 | +| explained_variance | 0.0568 | +| learning_rate | 4.99e-05 | +| loss | -0.0311 | +| n_updates | 36332 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000945 | +---------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0707 | +| time/ | | +| fps | 1321 | +| iterations | 248 | +| time_elapsed | 384 | +| total_timesteps | 507904 | +| train/ | | +| approx_kl | 0.018358 | +| clip_fraction | 0.408 | +| clip_range | 0.0749 | +| entropy_loss | -6.09 | +| explained_variance | 0.241 | +| learning_rate | 4.99e-05 | +| loss | -0.0305 | +| n_updates | 36336 | +| policy_gradient_loss | -0.0228 | +| value_loss | 0.000242 | +-------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0707 | +| time/ | | +| fps | 1321 | +| iterations | 249 | +| time_elapsed | 385 | +| total_timesteps | 509952 | +| train/ | | +| approx_kl | 0.01847693 | +| clip_fraction | 0.39 | +| clip_range | 0.0749 | +| entropy_loss | -6.18 | +| explained_variance | 0.315 | +| learning_rate | 4.99e-05 | +| loss | -0.0396 | +| n_updates | 36340 | +| policy_gradient_loss | -0.0228 | +| value_loss | 0.000175 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0631 | +| time/ | | +| fps | 1321 | +| iterations | 250 | +| time_elapsed | 387 | +| total_timesteps | 512000 | +| train/ | | +| approx_kl | 0.015814811 | +| clip_fraction | 0.363 | +| clip_range | 0.0749 | +| entropy_loss | -6.29 | +| explained_variance | 0.246 | +| learning_rate | 4.99e-05 | +| loss | -0.0306 | +| n_updates | 36344 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000293 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0631 | +| time/ | | +| fps | 1321 | +| iterations | 251 | +| time_elapsed | 388 | +| total_timesteps | 514048 | +| train/ | | +| approx_kl | 0.016383335 | +| clip_fraction | 0.369 | +| clip_range | 0.0749 | +| entropy_loss | -6.5 | +| explained_variance | 0.241 | +| learning_rate | 4.99e-05 | +| loss | -0.0374 | +| n_updates | 36348 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000309 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0602 | +| time/ | | +| fps | 1321 | +| iterations | 252 | +| time_elapsed | 390 | +| total_timesteps | 516096 | +| train/ | | +| approx_kl | 0.01728016 | +| clip_fraction | 0.387 | +| clip_range | 0.0749 | +| entropy_loss | -6.6 | +| explained_variance | 0.0841 | +| learning_rate | 4.99e-05 | +| loss | -0.0386 | +| n_updates | 36352 | +| policy_gradient_loss | -0.0229 | +| value_loss | 0.000357 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0602 | +| time/ | | +| fps | 1321 | +| iterations | 253 | +| time_elapsed | 392 | +| total_timesteps | 518144 | +| train/ | | +| approx_kl | 0.016452137 | +| clip_fraction | 0.347 | +| clip_range | 0.0749 | +| entropy_loss | -6.45 | +| explained_variance | 0.372 | +| learning_rate | 4.99e-05 | +| loss | -0.0323 | +| n_updates | 36356 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000243 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0626 | +| time/ | | +| fps | 1321 | +| iterations | 254 | +| time_elapsed | 393 | +| total_timesteps | 520192 | +| train/ | | +| approx_kl | 0.016895559 | +| clip_fraction | 0.372 | +| clip_range | 0.0749 | +| entropy_loss | -6.7 | +| explained_variance | -0.051 | +| learning_rate | 4.99e-05 | +| loss | -0.0338 | +| n_updates | 36360 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000256 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0638 | +| time/ | | +| fps | 1321 | +| iterations | 255 | +| time_elapsed | 395 | +| total_timesteps | 522240 | +| train/ | | +| approx_kl | 0.016503189 | +| clip_fraction | 0.391 | +| clip_range | 0.0749 | +| entropy_loss | -6.68 | +| explained_variance | 0.0966 | +| learning_rate | 4.99e-05 | +| loss | -0.0343 | +| n_updates | 36364 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000426 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0698 | +| time/ | | +| fps | 1321 | +| iterations | 256 | +| time_elapsed | 396 | +| total_timesteps | 524288 | +| train/ | | +| approx_kl | 0.016849114 | +| clip_fraction | 0.387 | +| clip_range | 0.0749 | +| entropy_loss | -6.23 | +| explained_variance | 0.486 | +| learning_rate | 4.99e-05 | +| loss | -0.0398 | +| n_updates | 36368 | +| policy_gradient_loss | -0.0234 | +| value_loss | 0.000192 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0668 | +| time/ | | +| fps | 1321 | +| iterations | 257 | +| time_elapsed | 398 | +| total_timesteps | 526336 | +| train/ | | +| approx_kl | 0.016673896 | +| clip_fraction | 0.389 | +| clip_range | 0.0749 | +| entropy_loss | -5.91 | +| explained_variance | 0.461 | +| learning_rate | 4.99e-05 | +| loss | -0.0339 | +| n_updates | 36372 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000191 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0695 | +| time/ | | +| fps | 1321 | +| iterations | 258 | +| time_elapsed | 399 | +| total_timesteps | 528384 | +| train/ | | +| approx_kl | 0.018269744 | +| clip_fraction | 0.385 | +| clip_range | 0.0749 | +| entropy_loss | -6.04 | +| explained_variance | 0.417 | +| learning_rate | 4.99e-05 | +| loss | -0.0324 | +| n_updates | 36376 | +| policy_gradient_loss | -0.022 | +| value_loss | 0.00024 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0695 | +| time/ | | +| fps | 1321 | +| iterations | 259 | +| time_elapsed | 401 | +| total_timesteps | 530432 | +| train/ | | +| approx_kl | 0.015456597 | +| clip_fraction | 0.34 | +| clip_range | 0.0749 | +| entropy_loss | -5.98 | +| explained_variance | 0.351 | +| learning_rate | 4.99e-05 | +| loss | -0.0301 | +| n_updates | 36380 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000264 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0696 | +| time/ | | +| fps | 1321 | +| iterations | 260 | +| time_elapsed | 402 | +| total_timesteps | 532480 | +| train/ | | +| approx_kl | 0.017339487 | +| clip_fraction | 0.407 | +| clip_range | 0.0749 | +| entropy_loss | -6.33 | +| explained_variance | 0.271 | +| learning_rate | 4.99e-05 | +| loss | -0.0353 | +| n_updates | 36384 | +| policy_gradient_loss | -0.0229 | +| value_loss | 0.000168 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0696 | +| time/ | | +| fps | 1321 | +| iterations | 261 | +| time_elapsed | 404 | +| total_timesteps | 534528 | +| train/ | | +| approx_kl | 0.01589743 | +| clip_fraction | 0.371 | +| clip_range | 0.0749 | +| entropy_loss | -6.35 | +| explained_variance | 0.176 | +| learning_rate | 4.99e-05 | +| loss | -0.0341 | +| n_updates | 36388 | +| policy_gradient_loss | -0.0219 | +| value_loss | 0.000346 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0699 | +| time/ | | +| fps | 1321 | +| iterations | 262 | +| time_elapsed | 405 | +| total_timesteps | 536576 | +| train/ | | +| approx_kl | 0.017037716 | +| clip_fraction | 0.388 | +| clip_range | 0.0749 | +| entropy_loss | -6.69 | +| explained_variance | -0.0463 | +| learning_rate | 4.99e-05 | +| loss | -0.0346 | +| n_updates | 36392 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000378 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0742 | +| time/ | | +| fps | 1321 | +| iterations | 263 | +| time_elapsed | 407 | +| total_timesteps | 538624 | +| train/ | | +| approx_kl | 0.018767346 | +| clip_fraction | 0.4 | +| clip_range | 0.0749 | +| entropy_loss | -6.44 | +| explained_variance | 0.252 | +| learning_rate | 4.99e-05 | +| loss | -0.0389 | +| n_updates | 36396 | +| policy_gradient_loss | -0.0238 | +| value_loss | 0.000177 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0732 | +| time/ | | +| fps | 1321 | +| iterations | 264 | +| time_elapsed | 409 | +| total_timesteps | 540672 | +| train/ | | +| approx_kl | 0.017394818 | +| clip_fraction | 0.35 | +| clip_range | 0.0749 | +| entropy_loss | -6.69 | +| explained_variance | -0.0191 | +| learning_rate | 4.99e-05 | +| loss | -0.0342 | +| n_updates | 36400 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000346 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0816 | +| time/ | | +| fps | 1321 | +| iterations | 265 | +| time_elapsed | 410 | +| total_timesteps | 542720 | +| train/ | | +| approx_kl | 0.0151393125 | +| clip_fraction | 0.383 | +| clip_range | 0.0749 | +| entropy_loss | -6.33 | +| explained_variance | 0.597 | +| learning_rate | 4.99e-05 | +| loss | -0.0353 | +| n_updates | 36404 | +| policy_gradient_loss | -0.0222 | +| value_loss | 0.00015 | +------------------------------------------ +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0929 | +| time/ | | +| fps | 1321 | +| iterations | 266 | +| time_elapsed | 412 | +| total_timesteps | 544768 | +| train/ | | +| approx_kl | 0.01699336 | +| clip_fraction | 0.373 | +| clip_range | 0.0749 | +| entropy_loss | -5.96 | +| explained_variance | 0.509 | +| learning_rate | 4.99e-05 | +| loss | -0.0312 | +| n_updates | 36408 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000232 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0929 | +| time/ | | +| fps | 1321 | +| iterations | 267 | +| time_elapsed | 413 | +| total_timesteps | 546816 | +| train/ | | +| approx_kl | 0.014733784 | +| clip_fraction | 0.354 | +| clip_range | 0.0749 | +| entropy_loss | -6.4 | +| explained_variance | 0.207 | +| learning_rate | 4.99e-05 | +| loss | -0.0317 | +| n_updates | 36412 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000327 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0744 | +| time/ | | +| fps | 1321 | +| iterations | 268 | +| time_elapsed | 415 | +| total_timesteps | 548864 | +| train/ | | +| approx_kl | 0.019793075 | +| clip_fraction | 0.392 | +| clip_range | 0.0749 | +| entropy_loss | -6.33 | +| explained_variance | 0.177 | +| learning_rate | 4.99e-05 | +| loss | -0.0373 | +| n_updates | 36416 | +| policy_gradient_loss | -0.0223 | +| value_loss | 0.00022 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0712 | +| time/ | | +| fps | 1321 | +| iterations | 269 | +| time_elapsed | 416 | +| total_timesteps | 550912 | +| train/ | | +| approx_kl | 0.016772378 | +| clip_fraction | 0.38 | +| clip_range | 0.0749 | +| entropy_loss | -6.12 | +| explained_variance | 0.458 | +| learning_rate | 4.99e-05 | +| loss | -0.0337 | +| n_updates | 36420 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000185 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0643 | +| time/ | | +| fps | 1321 | +| iterations | 270 | +| time_elapsed | 418 | +| total_timesteps | 552960 | +| train/ | | +| approx_kl | 0.016826734 | +| clip_fraction | 0.366 | +| clip_range | 0.0749 | +| entropy_loss | -6.15 | +| explained_variance | 0.319 | +| learning_rate | 4.99e-05 | +| loss | -0.0319 | +| n_updates | 36424 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000202 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0643 | +| time/ | | +| fps | 1321 | +| iterations | 271 | +| time_elapsed | 419 | +| total_timesteps | 555008 | +| train/ | | +| approx_kl | 0.023383945 | +| clip_fraction | 0.405 | +| clip_range | 0.0749 | +| entropy_loss | -5.98 | +| explained_variance | 0.465 | +| learning_rate | 4.99e-05 | +| loss | -0.0301 | +| n_updates | 36428 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000164 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0642 | +| time/ | | +| fps | 1322 | +| iterations | 272 | +| time_elapsed | 421 | +| total_timesteps | 557056 | +| train/ | | +| approx_kl | 0.01877985 | +| clip_fraction | 0.372 | +| clip_range | 0.0749 | +| entropy_loss | -6.74 | +| explained_variance | -0.0984 | +| learning_rate | 4.99e-05 | +| loss | -0.0315 | +| n_updates | 36432 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000276 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0642 | +| time/ | | +| fps | 1322 | +| iterations | 273 | +| time_elapsed | 422 | +| total_timesteps | 559104 | +| train/ | | +| approx_kl | 0.018867452 | +| clip_fraction | 0.379 | +| clip_range | 0.0749 | +| entropy_loss | -6.56 | +| explained_variance | 0.238 | +| learning_rate | 4.99e-05 | +| loss | -0.0347 | +| n_updates | 36436 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000236 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0752 | +| time/ | | +| fps | 1322 | +| iterations | 274 | +| time_elapsed | 424 | +| total_timesteps | 561152 | +| train/ | | +| approx_kl | 0.018704865 | +| clip_fraction | 0.375 | +| clip_range | 0.0749 | +| entropy_loss | -6.69 | +| explained_variance | -0.0882 | +| learning_rate | 4.99e-05 | +| loss | -0.0314 | +| n_updates | 36440 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000291 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0739 | +| time/ | | +| fps | 1322 | +| iterations | 275 | +| time_elapsed | 425 | +| total_timesteps | 563200 | +| train/ | | +| approx_kl | 0.014595095 | +| clip_fraction | 0.363 | +| clip_range | 0.0749 | +| entropy_loss | -6.26 | +| explained_variance | 0.344 | +| learning_rate | 4.99e-05 | +| loss | -0.0344 | +| n_updates | 36444 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000282 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0713 | +| time/ | | +| fps | 1322 | +| iterations | 276 | +| time_elapsed | 427 | +| total_timesteps | 565248 | +| train/ | | +| approx_kl | 0.018043092 | +| clip_fraction | 0.366 | +| clip_range | 0.0749 | +| entropy_loss | -6.43 | +| explained_variance | -0.149 | +| learning_rate | 4.99e-05 | +| loss | -0.0333 | +| n_updates | 36448 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000276 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0667 | +| time/ | | +| fps | 1321 | +| iterations | 277 | +| time_elapsed | 429 | +| total_timesteps | 567296 | +| train/ | | +| approx_kl | 0.015938204 | +| clip_fraction | 0.36 | +| clip_range | 0.0749 | +| entropy_loss | -6.67 | +| explained_variance | 0.0507 | +| learning_rate | 4.99e-05 | +| loss | -0.0376 | +| n_updates | 36452 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000264 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0684 | +| time/ | | +| fps | 1321 | +| iterations | 278 | +| time_elapsed | 430 | +| total_timesteps | 569344 | +| train/ | | +| approx_kl | 0.01621176 | +| clip_fraction | 0.361 | +| clip_range | 0.0749 | +| entropy_loss | -6.22 | +| explained_variance | 0.374 | +| learning_rate | 4.99e-05 | +| loss | -0.0331 | +| n_updates | 36456 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000262 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0615 | +| time/ | | +| fps | 1321 | +| iterations | 279 | +| time_elapsed | 432 | +| total_timesteps | 571392 | +| train/ | | +| approx_kl | 0.016120581 | +| clip_fraction | 0.353 | +| clip_range | 0.0749 | +| entropy_loss | -6.21 | +| explained_variance | 0.445 | +| learning_rate | 4.99e-05 | +| loss | -0.031 | +| n_updates | 36460 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000192 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0611 | +| time/ | | +| fps | 1321 | +| iterations | 280 | +| time_elapsed | 433 | +| total_timesteps | 573440 | +| train/ | | +| approx_kl | 0.017300703 | +| clip_fraction | 0.386 | +| clip_range | 0.0749 | +| entropy_loss | -5.83 | +| explained_variance | 0.499 | +| learning_rate | 4.99e-05 | +| loss | -0.0299 | +| n_updates | 36464 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000257 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0635 | +| time/ | | +| fps | 1322 | +| iterations | 281 | +| time_elapsed | 435 | +| total_timesteps | 575488 | +| train/ | | +| approx_kl | 0.019192914 | +| clip_fraction | 0.374 | +| clip_range | 0.0749 | +| entropy_loss | -6.31 | +| explained_variance | 0.222 | +| learning_rate | 4.99e-05 | +| loss | -0.0299 | +| n_updates | 36468 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000276 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0602 | +| time/ | | +| fps | 1321 | +| iterations | 282 | +| time_elapsed | 436 | +| total_timesteps | 577536 | +| train/ | | +| approx_kl | 0.016255606 | +| clip_fraction | 0.375 | +| clip_range | 0.0749 | +| entropy_loss | -6.67 | +| explained_variance | -0.0634 | +| learning_rate | 4.99e-05 | +| loss | -0.0306 | +| n_updates | 36472 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000376 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0588 | +| time/ | | +| fps | 1322 | +| iterations | 283 | +| time_elapsed | 438 | +| total_timesteps | 579584 | +| train/ | | +| approx_kl | 0.018187437 | +| clip_fraction | 0.382 | +| clip_range | 0.0749 | +| entropy_loss | -6.42 | +| explained_variance | 0.341 | +| learning_rate | 4.99e-05 | +| loss | -0.0375 | +| n_updates | 36476 | +| policy_gradient_loss | -0.0238 | +| value_loss | 0.000234 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0504 | +| time/ | | +| fps | 1322 | +| iterations | 284 | +| time_elapsed | 439 | +| total_timesteps | 581632 | +| train/ | | +| approx_kl | 0.016618503 | +| clip_fraction | 0.375 | +| clip_range | 0.0749 | +| entropy_loss | -6.54 | +| explained_variance | 0.129 | +| learning_rate | 4.99e-05 | +| loss | -0.0331 | +| n_updates | 36480 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000267 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0504 | +| time/ | | +| fps | 1322 | +| iterations | 285 | +| time_elapsed | 441 | +| total_timesteps | 583680 | +| train/ | | +| approx_kl | 0.015974728 | +| clip_fraction | 0.349 | +| clip_range | 0.0749 | +| entropy_loss | -5.92 | +| explained_variance | 0.444 | +| learning_rate | 4.99e-05 | +| loss | -0.0345 | +| n_updates | 36484 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000355 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0504 | +| time/ | | +| fps | 1322 | +| iterations | 286 | +| time_elapsed | 443 | +| total_timesteps | 585728 | +| train/ | | +| approx_kl | 0.017566439 | +| clip_fraction | 0.382 | +| clip_range | 0.0749 | +| entropy_loss | -6.23 | +| explained_variance | 0.309 | +| learning_rate | 4.99e-05 | +| loss | -0.0362 | +| n_updates | 36488 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000178 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0537 | +| time/ | | +| fps | 1321 | +| iterations | 287 | +| time_elapsed | 444 | +| total_timesteps | 587776 | +| train/ | | +| approx_kl | 0.01921577 | +| clip_fraction | 0.394 | +| clip_range | 0.0749 | +| entropy_loss | -6.61 | +| explained_variance | -0.0301 | +| learning_rate | 4.99e-05 | +| loss | -0.0394 | +| n_updates | 36492 | +| policy_gradient_loss | -0.0223 | +| value_loss | 0.000279 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.046 | +| time/ | | +| fps | 1321 | +| iterations | 288 | +| time_elapsed | 446 | +| total_timesteps | 589824 | +| train/ | | +| approx_kl | 0.018029362 | +| clip_fraction | 0.395 | +| clip_range | 0.0749 | +| entropy_loss | -6.45 | +| explained_variance | -0.00761 | +| learning_rate | 4.99e-05 | +| loss | -0.0355 | +| n_updates | 36496 | +| policy_gradient_loss | -0.0222 | +| value_loss | 0.00018 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0459 | +| time/ | | +| fps | 1321 | +| iterations | 289 | +| time_elapsed | 447 | +| total_timesteps | 591872 | +| train/ | | +| approx_kl | 0.017588882 | +| clip_fraction | 0.396 | +| clip_range | 0.0749 | +| entropy_loss | -6.24 | +| explained_variance | 0.25 | +| learning_rate | 4.99e-05 | +| loss | -0.0374 | +| n_updates | 36500 | +| policy_gradient_loss | -0.0224 | +| value_loss | 0.000322 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0481 | +| time/ | | +| fps | 1321 | +| iterations | 290 | +| time_elapsed | 449 | +| total_timesteps | 593920 | +| train/ | | +| approx_kl | 0.019147217 | +| clip_fraction | 0.378 | +| clip_range | 0.0749 | +| entropy_loss | -6.44 | +| explained_variance | 0.226 | +| learning_rate | 4.99e-05 | +| loss | -0.0375 | +| n_updates | 36504 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000157 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0602 | +| time/ | | +| fps | 1322 | +| iterations | 291 | +| time_elapsed | 450 | +| total_timesteps | 595968 | +| train/ | | +| approx_kl | 0.01682173 | +| clip_fraction | 0.376 | +| clip_range | 0.0749 | +| entropy_loss | -6.4 | +| explained_variance | 0.247 | +| learning_rate | 4.99e-05 | +| loss | -0.0351 | +| n_updates | 36508 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000232 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0608 | +| time/ | | +| fps | 1322 | +| iterations | 292 | +| time_elapsed | 452 | +| total_timesteps | 598016 | +| train/ | | +| approx_kl | 0.016210524 | +| clip_fraction | 0.347 | +| clip_range | 0.0749 | +| entropy_loss | -5.84 | +| explained_variance | 0.287 | +| learning_rate | 4.99e-05 | +| loss | -0.0258 | +| n_updates | 36512 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.00081 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0565 | +| time/ | | +| fps | 1322 | +| iterations | 293 | +| time_elapsed | 453 | +| total_timesteps | 600064 | +| train/ | | +| approx_kl | 0.015909504 | +| clip_fraction | 0.364 | +| clip_range | 0.0749 | +| entropy_loss | -5.89 | +| explained_variance | 0.47 | +| learning_rate | 4.99e-05 | +| loss | -0.0289 | +| n_updates | 36516 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000194 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0595 | +| time/ | | +| fps | 1322 | +| iterations | 294 | +| time_elapsed | 455 | +| total_timesteps | 602112 | +| train/ | | +| approx_kl | 0.015458164 | +| clip_fraction | 0.372 | +| clip_range | 0.0748 | +| entropy_loss | -6.35 | +| explained_variance | 0.128 | +| learning_rate | 4.99e-05 | +| loss | -0.0382 | +| n_updates | 36520 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000263 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0595 | +| time/ | | +| fps | 1322 | +| iterations | 295 | +| time_elapsed | 456 | +| total_timesteps | 604160 | +| train/ | | +| approx_kl | 0.018813113 | +| clip_fraction | 0.405 | +| clip_range | 0.0748 | +| entropy_loss | -6.01 | +| explained_variance | 0.321 | +| learning_rate | 4.99e-05 | +| loss | -0.0342 | +| n_updates | 36524 | +| policy_gradient_loss | -0.0222 | +| value_loss | 0.000305 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.0551 | +| time/ | | +| fps | 1322 | +| iterations | 296 | +| time_elapsed | 458 | +| total_timesteps | 606208 | +| train/ | | +| approx_kl | 0.016777704 | +| clip_fraction | 0.389 | +| clip_range | 0.0748 | +| entropy_loss | -6.44 | +| explained_variance | 0.0575 | +| learning_rate | 4.99e-05 | +| loss | -0.0369 | +| n_updates | 36528 | +| policy_gradient_loss | -0.022 | +| value_loss | 0.000333 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.0551 | +| time/ | | +| fps | 1322 | +| iterations | 297 | +| time_elapsed | 459 | +| total_timesteps | 608256 | +| train/ | | +| approx_kl | 0.016034259 | +| clip_fraction | 0.392 | +| clip_range | 0.0748 | +| entropy_loss | -6.15 | +| explained_variance | 0.326 | +| learning_rate | 4.99e-05 | +| loss | -0.0371 | +| n_updates | 36532 | +| policy_gradient_loss | -0.0231 | +| value_loss | 0.000213 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.0663 | +| time/ | | +| fps | 1322 | +| iterations | 298 | +| time_elapsed | 461 | +| total_timesteps | 610304 | +| train/ | | +| approx_kl | 0.017436866 | +| clip_fraction | 0.39 | +| clip_range | 0.0748 | +| entropy_loss | -6.67 | +| explained_variance | -0.0482 | +| learning_rate | 4.99e-05 | +| loss | -0.032 | +| n_updates | 36536 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000246 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.066 | +| time/ | | +| fps | 1322 | +| iterations | 299 | +| time_elapsed | 463 | +| total_timesteps | 612352 | +| train/ | | +| approx_kl | 0.014140915 | +| clip_fraction | 0.342 | +| clip_range | 0.0748 | +| entropy_loss | -6.21 | +| explained_variance | 0.0847 | +| learning_rate | 4.99e-05 | +| loss | -0.0192 | +| n_updates | 36540 | +| policy_gradient_loss | -0.0135 | +| value_loss | 0.000692 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.066 | +| time/ | | +| fps | 1322 | +| iterations | 300 | +| time_elapsed | 464 | +| total_timesteps | 614400 | +| train/ | | +| approx_kl | 0.01832295 | +| clip_fraction | 0.395 | +| clip_range | 0.0748 | +| entropy_loss | -6.02 | +| explained_variance | -0.021 | +| learning_rate | 4.99e-05 | +| loss | -0.0334 | +| n_updates | 36544 | +| policy_gradient_loss | -0.0235 | +| value_loss | 0.000323 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.0619 | +| time/ | | +| fps | 1322 | +| iterations | 301 | +| time_elapsed | 466 | +| total_timesteps | 616448 | +| train/ | | +| approx_kl | 0.016074684 | +| clip_fraction | 0.391 | +| clip_range | 0.0748 | +| entropy_loss | -6.42 | +| explained_variance | -0.352 | +| learning_rate | 4.99e-05 | +| loss | -0.0418 | +| n_updates | 36548 | +| policy_gradient_loss | -0.0233 | +| value_loss | 0.000321 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.0635 | +| time/ | | +| fps | 1322 | +| iterations | 302 | +| time_elapsed | 467 | +| total_timesteps | 618496 | +| train/ | | +| approx_kl | 0.015235292 | +| clip_fraction | 0.376 | +| clip_range | 0.0748 | +| entropy_loss | -6.21 | +| explained_variance | 0.247 | +| learning_rate | 4.99e-05 | +| loss | -0.0313 | +| n_updates | 36552 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000233 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.0635 | +| time/ | | +| fps | 1322 | +| iterations | 303 | +| time_elapsed | 469 | +| total_timesteps | 620544 | +| train/ | | +| approx_kl | 0.01717629 | +| clip_fraction | 0.387 | +| clip_range | 0.0748 | +| entropy_loss | -5.86 | +| explained_variance | 0.393 | +| learning_rate | 4.99e-05 | +| loss | -0.0326 | +| n_updates | 36556 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000281 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.0635 | +| time/ | | +| fps | 1322 | +| iterations | 304 | +| time_elapsed | 470 | +| total_timesteps | 622592 | +| train/ | | +| approx_kl | 0.017465014 | +| clip_fraction | 0.375 | +| clip_range | 0.0748 | +| entropy_loss | -6.56 | +| explained_variance | 0.165 | +| learning_rate | 4.99e-05 | +| loss | -0.0351 | +| n_updates | 36560 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000244 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.0763 | +| time/ | | +| fps | 1322 | +| iterations | 305 | +| time_elapsed | 472 | +| total_timesteps | 624640 | +| train/ | | +| approx_kl | 0.015117513 | +| clip_fraction | 0.38 | +| clip_range | 0.0748 | +| entropy_loss | -6.67 | +| explained_variance | 0.0013 | +| learning_rate | 4.99e-05 | +| loss | -0.0374 | +| n_updates | 36564 | +| policy_gradient_loss | -0.0223 | +| value_loss | 0.000267 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.0742 | +| time/ | | +| fps | 1322 | +| iterations | 306 | +| time_elapsed | 473 | +| total_timesteps | 626688 | +| train/ | | +| approx_kl | 0.01257138 | +| clip_fraction | 0.32 | +| clip_range | 0.0748 | +| entropy_loss | -5.45 | +| explained_variance | 0.2 | +| learning_rate | 4.99e-05 | +| loss | -0.0238 | +| n_updates | 36568 | +| policy_gradient_loss | -0.0113 | +| value_loss | 0.00134 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.0595 | +| time/ | | +| fps | 1322 | +| iterations | 307 | +| time_elapsed | 475 | +| total_timesteps | 628736 | +| train/ | | +| approx_kl | 0.018543176 | +| clip_fraction | 0.399 | +| clip_range | 0.0748 | +| entropy_loss | -6.11 | +| explained_variance | 0.111 | +| learning_rate | 4.99e-05 | +| loss | -0.0356 | +| n_updates | 36572 | +| policy_gradient_loss | -0.0235 | +| value_loss | 0.000235 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.0613 | +| time/ | | +| fps | 1322 | +| iterations | 308 | +| time_elapsed | 476 | +| total_timesteps | 630784 | +| train/ | | +| approx_kl | 0.017791264 | +| clip_fraction | 0.393 | +| clip_range | 0.0748 | +| entropy_loss | -6.49 | +| explained_variance | -0.00409 | +| learning_rate | 4.99e-05 | +| loss | -0.0344 | +| n_updates | 36576 | +| policy_gradient_loss | -0.023 | +| value_loss | 0.000346 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.0613 | +| time/ | | +| fps | 1322 | +| iterations | 309 | +| time_elapsed | 478 | +| total_timesteps | 632832 | +| train/ | | +| approx_kl | 0.015249492 | +| clip_fraction | 0.365 | +| clip_range | 0.0748 | +| entropy_loss | -6.27 | +| explained_variance | 0.358 | +| learning_rate | 4.99e-05 | +| loss | -0.0358 | +| n_updates | 36580 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000223 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.0613 | +| time/ | | +| fps | 1322 | +| iterations | 310 | +| time_elapsed | 480 | +| total_timesteps | 634880 | +| train/ | | +| approx_kl | 0.017888326 | +| clip_fraction | 0.376 | +| clip_range | 0.0748 | +| entropy_loss | -6.42 | +| explained_variance | 0.184 | +| learning_rate | 4.98e-05 | +| loss | -0.0342 | +| n_updates | 36584 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000327 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.0625 | +| time/ | | +| fps | 1322 | +| iterations | 311 | +| time_elapsed | 481 | +| total_timesteps | 636928 | +| train/ | | +| approx_kl | 0.017206635 | +| clip_fraction | 0.414 | +| clip_range | 0.0748 | +| entropy_loss | -6.68 | +| explained_variance | -0.186 | +| learning_rate | 4.98e-05 | +| loss | -0.0391 | +| n_updates | 36588 | +| policy_gradient_loss | -0.0237 | +| value_loss | 0.00023 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.0625 | +| time/ | | +| fps | 1322 | +| iterations | 312 | +| time_elapsed | 483 | +| total_timesteps | 638976 | +| train/ | | +| approx_kl | 0.018647809 | +| clip_fraction | 0.378 | +| clip_range | 0.0748 | +| entropy_loss | -6.56 | +| explained_variance | -0.103 | +| learning_rate | 4.98e-05 | +| loss | -0.0365 | +| n_updates | 36592 | +| policy_gradient_loss | -0.023 | +| value_loss | 0.000277 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.0633 | +| time/ | | +| fps | 1322 | +| iterations | 313 | +| time_elapsed | 484 | +| total_timesteps | 641024 | +| train/ | | +| approx_kl | 0.017581496 | +| clip_fraction | 0.4 | +| clip_range | 0.0748 | +| entropy_loss | -6.56 | +| explained_variance | 0.233 | +| learning_rate | 4.98e-05 | +| loss | -0.0321 | +| n_updates | 36596 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000225 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.0635 | +| time/ | | +| fps | 1322 | +| iterations | 314 | +| time_elapsed | 486 | +| total_timesteps | 643072 | +| train/ | | +| approx_kl | 0.01770259 | +| clip_fraction | 0.386 | +| clip_range | 0.0748 | +| entropy_loss | -6.5 | +| explained_variance | 0.0036 | +| learning_rate | 4.98e-05 | +| loss | -0.0315 | +| n_updates | 36600 | +| policy_gradient_loss | -0.022 | +| value_loss | 0.000231 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.0635 | +| time/ | | +| fps | 1322 | +| iterations | 315 | +| time_elapsed | 487 | +| total_timesteps | 645120 | +| train/ | | +| approx_kl | 0.015603281 | +| clip_fraction | 0.383 | +| clip_range | 0.0748 | +| entropy_loss | -5.33 | +| explained_variance | 0.532 | +| learning_rate | 4.98e-05 | +| loss | -0.0281 | +| n_updates | 36604 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000268 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.0601 | +| time/ | | +| fps | 1322 | +| iterations | 316 | +| time_elapsed | 489 | +| total_timesteps | 647168 | +| train/ | | +| approx_kl | 0.017224312 | +| clip_fraction | 0.368 | +| clip_range | 0.0748 | +| entropy_loss | -6.29 | +| explained_variance | 0.308 | +| learning_rate | 4.98e-05 | +| loss | -0.0312 | +| n_updates | 36608 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000232 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.061 | +| time/ | | +| fps | 1322 | +| iterations | 317 | +| time_elapsed | 490 | +| total_timesteps | 649216 | +| train/ | | +| approx_kl | 0.017287754 | +| clip_fraction | 0.374 | +| clip_range | 0.0748 | +| entropy_loss | -6.16 | +| explained_variance | 0.19 | +| learning_rate | 4.98e-05 | +| loss | -0.0323 | +| n_updates | 36612 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000268 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.0566 | +| time/ | | +| fps | 1322 | +| iterations | 318 | +| time_elapsed | 492 | +| total_timesteps | 651264 | +| train/ | | +| approx_kl | 0.018469952 | +| clip_fraction | 0.376 | +| clip_range | 0.0748 | +| entropy_loss | -6.31 | +| explained_variance | 0.224 | +| learning_rate | 4.98e-05 | +| loss | -0.0343 | +| n_updates | 36616 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000151 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.0572 | +| time/ | | +| fps | 1322 | +| iterations | 319 | +| time_elapsed | 494 | +| total_timesteps | 653312 | +| train/ | | +| approx_kl | 0.018956292 | +| clip_fraction | 0.362 | +| clip_range | 0.0748 | +| entropy_loss | -5.93 | +| explained_variance | 0.483 | +| learning_rate | 4.98e-05 | +| loss | -0.0332 | +| n_updates | 36620 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000258 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.0572 | +| time/ | | +| fps | 1322 | +| iterations | 320 | +| time_elapsed | 495 | +| total_timesteps | 655360 | +| train/ | | +| approx_kl | 0.020873778 | +| clip_fraction | 0.392 | +| clip_range | 0.0748 | +| entropy_loss | -5.9 | +| explained_variance | 0.41 | +| learning_rate | 4.98e-05 | +| loss | -0.0341 | +| n_updates | 36624 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000213 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.0613 | +| time/ | | +| fps | 1322 | +| iterations | 321 | +| time_elapsed | 497 | +| total_timesteps | 657408 | +| train/ | | +| approx_kl | 0.017658245 | +| clip_fraction | 0.387 | +| clip_range | 0.0748 | +| entropy_loss | -6.56 | +| explained_variance | -0.108 | +| learning_rate | 4.98e-05 | +| loss | -0.034 | +| n_updates | 36628 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000222 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.0611 | +| time/ | | +| fps | 1322 | +| iterations | 322 | +| time_elapsed | 498 | +| total_timesteps | 659456 | +| train/ | | +| approx_kl | 0.017825045 | +| clip_fraction | 0.372 | +| clip_range | 0.0748 | +| entropy_loss | -6.58 | +| explained_variance | 0.163 | +| learning_rate | 4.98e-05 | +| loss | -0.0338 | +| n_updates | 36632 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000285 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.0611 | +| time/ | | +| fps | 1321 | +| iterations | 323 | +| time_elapsed | 500 | +| total_timesteps | 661504 | +| train/ | | +| approx_kl | 0.017984949 | +| clip_fraction | 0.378 | +| clip_range | 0.0748 | +| entropy_loss | -6.35 | +| explained_variance | -0.0297 | +| learning_rate | 4.98e-05 | +| loss | -0.0387 | +| n_updates | 36636 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000316 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.0552 | +| time/ | | +| fps | 1321 | +| iterations | 324 | +| time_elapsed | 501 | +| total_timesteps | 663552 | +| train/ | | +| approx_kl | 0.016033007 | +| clip_fraction | 0.379 | +| clip_range | 0.0748 | +| entropy_loss | -6.45 | +| explained_variance | 0.156 | +| learning_rate | 4.98e-05 | +| loss | -0.0322 | +| n_updates | 36640 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000311 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.0572 | +| time/ | | +| fps | 1321 | +| iterations | 325 | +| time_elapsed | 503 | +| total_timesteps | 665600 | +| train/ | | +| approx_kl | 0.016955713 | +| clip_fraction | 0.377 | +| clip_range | 0.0748 | +| entropy_loss | -6.44 | +| explained_variance | 0.255 | +| learning_rate | 4.98e-05 | +| loss | -0.0361 | +| n_updates | 36644 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000241 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.0537 | +| time/ | | +| fps | 1321 | +| iterations | 326 | +| time_elapsed | 505 | +| total_timesteps | 667648 | +| train/ | | +| approx_kl | 0.015545241 | +| clip_fraction | 0.371 | +| clip_range | 0.0748 | +| entropy_loss | -6.15 | +| explained_variance | 0.384 | +| learning_rate | 4.98e-05 | +| loss | -0.0331 | +| n_updates | 36648 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000223 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.0513 | +| time/ | | +| fps | 1321 | +| iterations | 327 | +| time_elapsed | 506 | +| total_timesteps | 669696 | +| train/ | | +| approx_kl | 0.016110897 | +| clip_fraction | 0.377 | +| clip_range | 0.0748 | +| entropy_loss | -6.12 | +| explained_variance | 0.517 | +| learning_rate | 4.98e-05 | +| loss | -0.0335 | +| n_updates | 36652 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000213 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.0543 | +| time/ | | +| fps | 1321 | +| iterations | 328 | +| time_elapsed | 508 | +| total_timesteps | 671744 | +| train/ | | +| approx_kl | 0.019984249 | +| clip_fraction | 0.384 | +| clip_range | 0.0748 | +| entropy_loss | -5.82 | +| explained_variance | 0.296 | +| learning_rate | 4.98e-05 | +| loss | -0.0284 | +| n_updates | 36656 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000258 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.0521 | +| time/ | | +| fps | 1321 | +| iterations | 329 | +| time_elapsed | 509 | +| total_timesteps | 673792 | +| train/ | | +| approx_kl | 0.017877707 | +| clip_fraction | 0.375 | +| clip_range | 0.0748 | +| entropy_loss | -6.4 | +| explained_variance | -0.0236 | +| learning_rate | 4.98e-05 | +| loss | -0.0337 | +| n_updates | 36660 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000283 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0512 | +| time/ | | +| fps | 1321 | +| iterations | 330 | +| time_elapsed | 511 | +| total_timesteps | 675840 | +| train/ | | +| approx_kl | 0.019528752 | +| clip_fraction | 0.397 | +| clip_range | 0.0748 | +| entropy_loss | -6.22 | +| explained_variance | 0.358 | +| learning_rate | 4.98e-05 | +| loss | -0.0335 | +| n_updates | 36664 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000157 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0456 | +| time/ | | +| fps | 1321 | +| iterations | 331 | +| time_elapsed | 512 | +| total_timesteps | 677888 | +| train/ | | +| approx_kl | 0.017725596 | +| clip_fraction | 0.379 | +| clip_range | 0.0748 | +| entropy_loss | -6.21 | +| explained_variance | 0.186 | +| learning_rate | 4.98e-05 | +| loss | -0.0342 | +| n_updates | 36668 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000224 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0456 | +| time/ | | +| fps | 1321 | +| iterations | 332 | +| time_elapsed | 514 | +| total_timesteps | 679936 | +| train/ | | +| approx_kl | 0.018112436 | +| clip_fraction | 0.388 | +| clip_range | 0.0748 | +| entropy_loss | -6.04 | +| explained_variance | 0.319 | +| learning_rate | 4.98e-05 | +| loss | -0.0355 | +| n_updates | 36672 | +| policy_gradient_loss | -0.0224 | +| value_loss | 0.000284 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0478 | +| time/ | | +| fps | 1321 | +| iterations | 333 | +| time_elapsed | 516 | +| total_timesteps | 681984 | +| train/ | | +| approx_kl | 0.015895026 | +| clip_fraction | 0.41 | +| clip_range | 0.0748 | +| entropy_loss | -6.46 | +| explained_variance | 0.0605 | +| learning_rate | 4.98e-05 | +| loss | -0.0319 | +| n_updates | 36676 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000245 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0518 | +| time/ | | +| fps | 1321 | +| iterations | 334 | +| time_elapsed | 517 | +| total_timesteps | 684032 | +| train/ | | +| approx_kl | 0.017117603 | +| clip_fraction | 0.395 | +| clip_range | 0.0748 | +| entropy_loss | -6.07 | +| explained_variance | 0.39 | +| learning_rate | 4.98e-05 | +| loss | -0.0333 | +| n_updates | 36680 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000209 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0599 | +| time/ | | +| fps | 1321 | +| iterations | 335 | +| time_elapsed | 519 | +| total_timesteps | 686080 | +| train/ | | +| approx_kl | 0.019275341 | +| clip_fraction | 0.371 | +| clip_range | 0.0748 | +| entropy_loss | -5.9 | +| explained_variance | 0.29 | +| learning_rate | 4.98e-05 | +| loss | -0.0313 | +| n_updates | 36684 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000237 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0613 | +| time/ | | +| fps | 1321 | +| iterations | 336 | +| time_elapsed | 520 | +| total_timesteps | 688128 | +| train/ | | +| approx_kl | 0.019610498 | +| clip_fraction | 0.383 | +| clip_range | 0.0748 | +| entropy_loss | -6.12 | +| explained_variance | 0.0943 | +| learning_rate | 4.98e-05 | +| loss | -0.0343 | +| n_updates | 36688 | +| policy_gradient_loss | -0.022 | +| value_loss | 0.000274 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.053 | +| time/ | | +| fps | 1321 | +| iterations | 337 | +| time_elapsed | 522 | +| total_timesteps | 690176 | +| train/ | | +| approx_kl | 0.017897898 | +| clip_fraction | 0.396 | +| clip_range | 0.0748 | +| entropy_loss | -6.05 | +| explained_variance | 0.565 | +| learning_rate | 4.98e-05 | +| loss | -0.0332 | +| n_updates | 36692 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000167 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0467 | +| time/ | | +| fps | 1321 | +| iterations | 338 | +| time_elapsed | 523 | +| total_timesteps | 692224 | +| train/ | | +| approx_kl | 0.019059833 | +| clip_fraction | 0.389 | +| clip_range | 0.0748 | +| entropy_loss | -6.09 | +| explained_variance | 0.39 | +| learning_rate | 4.98e-05 | +| loss | -0.0316 | +| n_updates | 36696 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000273 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0467 | +| time/ | | +| fps | 1321 | +| iterations | 339 | +| time_elapsed | 525 | +| total_timesteps | 694272 | +| train/ | | +| approx_kl | 0.01711217 | +| clip_fraction | 0.391 | +| clip_range | 0.0748 | +| entropy_loss | -6.19 | +| explained_variance | 0.108 | +| learning_rate | 4.98e-05 | +| loss | -0.0335 | +| n_updates | 36700 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000226 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0468 | +| time/ | | +| fps | 1321 | +| iterations | 340 | +| time_elapsed | 527 | +| total_timesteps | 696320 | +| train/ | | +| approx_kl | 0.01639791 | +| clip_fraction | 0.364 | +| clip_range | 0.0748 | +| entropy_loss | -6.21 | +| explained_variance | 0.0631 | +| learning_rate | 4.98e-05 | +| loss | -0.0363 | +| n_updates | 36704 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000339 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0475 | +| time/ | | +| fps | 1321 | +| iterations | 341 | +| time_elapsed | 528 | +| total_timesteps | 698368 | +| train/ | | +| approx_kl | 0.01998251 | +| clip_fraction | 0.383 | +| clip_range | 0.0748 | +| entropy_loss | -6.03 | +| explained_variance | 0.343 | +| learning_rate | 4.98e-05 | +| loss | -0.0326 | +| n_updates | 36708 | +| policy_gradient_loss | -0.0223 | +| value_loss | 0.000243 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0494 | +| time/ | | +| fps | 1321 | +| iterations | 342 | +| time_elapsed | 530 | +| total_timesteps | 700416 | +| train/ | | +| approx_kl | 0.01582996 | +| clip_fraction | 0.36 | +| clip_range | 0.0748 | +| entropy_loss | -6.16 | +| explained_variance | 0.129 | +| learning_rate | 4.98e-05 | +| loss | -0.031 | +| n_updates | 36712 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000278 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0494 | +| time/ | | +| fps | 1320 | +| iterations | 343 | +| time_elapsed | 531 | +| total_timesteps | 702464 | +| train/ | | +| approx_kl | 0.017663874 | +| clip_fraction | 0.397 | +| clip_range | 0.0748 | +| entropy_loss | -6.09 | +| explained_variance | 0.418 | +| learning_rate | 4.98e-05 | +| loss | -0.0316 | +| n_updates | 36716 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000221 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0445 | +| time/ | | +| fps | 1320 | +| iterations | 344 | +| time_elapsed | 533 | +| total_timesteps | 704512 | +| train/ | | +| approx_kl | 0.017862167 | +| clip_fraction | 0.407 | +| clip_range | 0.0748 | +| entropy_loss | -6.19 | +| explained_variance | 0.197 | +| learning_rate | 4.98e-05 | +| loss | -0.0361 | +| n_updates | 36720 | +| policy_gradient_loss | -0.0223 | +| value_loss | 0.000196 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0425 | +| time/ | | +| fps | 1320 | +| iterations | 345 | +| time_elapsed | 534 | +| total_timesteps | 706560 | +| train/ | | +| approx_kl | 0.01760653 | +| clip_fraction | 0.397 | +| clip_range | 0.0748 | +| entropy_loss | -5.9 | +| explained_variance | 0.135 | +| learning_rate | 4.98e-05 | +| loss | -0.0373 | +| n_updates | 36724 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.00026 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.047 | +| time/ | | +| fps | 1320 | +| iterations | 346 | +| time_elapsed | 536 | +| total_timesteps | 708608 | +| train/ | | +| approx_kl | 0.019090727 | +| clip_fraction | 0.383 | +| clip_range | 0.0748 | +| entropy_loss | -5.82 | +| explained_variance | 0.361 | +| learning_rate | 4.98e-05 | +| loss | -0.0342 | +| n_updates | 36728 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000213 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0486 | +| time/ | | +| fps | 1320 | +| iterations | 347 | +| time_elapsed | 538 | +| total_timesteps | 710656 | +| train/ | | +| approx_kl | 0.017846704 | +| clip_fraction | 0.366 | +| clip_range | 0.0748 | +| entropy_loss | -5.88 | +| explained_variance | 0.14 | +| learning_rate | 4.98e-05 | +| loss | -0.0253 | +| n_updates | 36732 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000864 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.048 | +| time/ | | +| fps | 1320 | +| iterations | 348 | +| time_elapsed | 539 | +| total_timesteps | 712704 | +| train/ | | +| approx_kl | 0.019897595 | +| clip_fraction | 0.414 | +| clip_range | 0.0748 | +| entropy_loss | -5.85 | +| explained_variance | 0.347 | +| learning_rate | 4.98e-05 | +| loss | -0.0425 | +| n_updates | 36736 | +| policy_gradient_loss | -0.0262 | +| value_loss | 0.000247 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0371 | +| time/ | | +| fps | 1320 | +| iterations | 349 | +| time_elapsed | 541 | +| total_timesteps | 714752 | +| train/ | | +| approx_kl | 0.018178094 | +| clip_fraction | 0.399 | +| clip_range | 0.0748 | +| entropy_loss | -6.19 | +| explained_variance | 0.193 | +| learning_rate | 4.98e-05 | +| loss | -0.0371 | +| n_updates | 36740 | +| policy_gradient_loss | -0.0237 | +| value_loss | 0.000264 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0399 | +| time/ | | +| fps | 1320 | +| iterations | 350 | +| time_elapsed | 542 | +| total_timesteps | 716800 | +| train/ | | +| approx_kl | 0.017737312 | +| clip_fraction | 0.395 | +| clip_range | 0.0748 | +| entropy_loss | -6.03 | +| explained_variance | 0.179 | +| learning_rate | 4.98e-05 | +| loss | -0.046 | +| n_updates | 36744 | +| policy_gradient_loss | -0.0222 | +| value_loss | 0.000248 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0405 | +| time/ | | +| fps | 1320 | +| iterations | 351 | +| time_elapsed | 544 | +| total_timesteps | 718848 | +| train/ | | +| approx_kl | 0.019017458 | +| clip_fraction | 0.401 | +| clip_range | 0.0748 | +| entropy_loss | -6.05 | +| explained_variance | 0.206 | +| learning_rate | 4.98e-05 | +| loss | -0.0355 | +| n_updates | 36748 | +| policy_gradient_loss | -0.0223 | +| value_loss | 0.000249 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0427 | +| time/ | | +| fps | 1320 | +| iterations | 352 | +| time_elapsed | 545 | +| total_timesteps | 720896 | +| train/ | | +| approx_kl | 0.019246394 | +| clip_fraction | 0.388 | +| clip_range | 0.0748 | +| entropy_loss | -5.99 | +| explained_variance | 0.374 | +| learning_rate | 4.98e-05 | +| loss | -0.0366 | +| n_updates | 36752 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000217 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0476 | +| time/ | | +| fps | 1320 | +| iterations | 353 | +| time_elapsed | 547 | +| total_timesteps | 722944 | +| train/ | | +| approx_kl | 0.018503387 | +| clip_fraction | 0.398 | +| clip_range | 0.0748 | +| entropy_loss | -5.8 | +| explained_variance | 0.33 | +| learning_rate | 4.98e-05 | +| loss | -0.0371 | +| n_updates | 36756 | +| policy_gradient_loss | -0.0222 | +| value_loss | 0.000178 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0471 | +| time/ | | +| fps | 1320 | +| iterations | 354 | +| time_elapsed | 548 | +| total_timesteps | 724992 | +| train/ | | +| approx_kl | 0.016948253 | +| clip_fraction | 0.394 | +| clip_range | 0.0748 | +| entropy_loss | -6.05 | +| explained_variance | 0.168 | +| learning_rate | 4.98e-05 | +| loss | -0.0345 | +| n_updates | 36760 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000231 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0499 | +| time/ | | +| fps | 1320 | +| iterations | 355 | +| time_elapsed | 550 | +| total_timesteps | 727040 | +| train/ | | +| approx_kl | 0.015604405 | +| clip_fraction | 0.404 | +| clip_range | 0.0748 | +| entropy_loss | -6.31 | +| explained_variance | -0.00855 | +| learning_rate | 4.98e-05 | +| loss | -0.0307 | +| n_updates | 36764 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000274 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0499 | +| time/ | | +| fps | 1321 | +| iterations | 356 | +| time_elapsed | 551 | +| total_timesteps | 729088 | +| train/ | | +| approx_kl | 0.018053722 | +| clip_fraction | 0.383 | +| clip_range | 0.0748 | +| entropy_loss | -5.68 | +| explained_variance | 0.438 | +| learning_rate | 4.98e-05 | +| loss | -0.0322 | +| n_updates | 36768 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.00025 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0499 | +| time/ | | +| fps | 1321 | +| iterations | 357 | +| time_elapsed | 553 | +| total_timesteps | 731136 | +| train/ | | +| approx_kl | 0.016382048 | +| clip_fraction | 0.391 | +| clip_range | 0.0748 | +| entropy_loss | -6.43 | +| explained_variance | -0.215 | +| learning_rate | 4.98e-05 | +| loss | -0.037 | +| n_updates | 36772 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.00018 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0366 | +| time/ | | +| fps | 1320 | +| iterations | 358 | +| time_elapsed | 555 | +| total_timesteps | 733184 | +| train/ | | +| approx_kl | 0.018153753 | +| clip_fraction | 0.384 | +| clip_range | 0.0748 | +| entropy_loss | -6.43 | +| explained_variance | -0.0435 | +| learning_rate | 4.98e-05 | +| loss | -0.0358 | +| n_updates | 36776 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000225 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0437 | +| time/ | | +| fps | 1321 | +| iterations | 359 | +| time_elapsed | 556 | +| total_timesteps | 735232 | +| train/ | | +| approx_kl | 0.018415812 | +| clip_fraction | 0.374 | +| clip_range | 0.0748 | +| entropy_loss | -5.77 | +| explained_variance | 0.489 | +| learning_rate | 4.98e-05 | +| loss | -0.0314 | +| n_updates | 36780 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.0002 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0408 | +| time/ | | +| fps | 1321 | +| iterations | 360 | +| time_elapsed | 558 | +| total_timesteps | 737280 | +| train/ | | +| approx_kl | 0.017082814 | +| clip_fraction | 0.391 | +| clip_range | 0.0748 | +| entropy_loss | -6.06 | +| explained_variance | 0.0707 | +| learning_rate | 4.98e-05 | +| loss | -0.0337 | +| n_updates | 36784 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.00026 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.038 | +| time/ | | +| fps | 1321 | +| iterations | 361 | +| time_elapsed | 559 | +| total_timesteps | 739328 | +| train/ | | +| approx_kl | 0.017655507 | +| clip_fraction | 0.387 | +| clip_range | 0.0748 | +| entropy_loss | -5.58 | +| explained_variance | 0.549 | +| learning_rate | 4.98e-05 | +| loss | -0.0336 | +| n_updates | 36788 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000203 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0213 | +| time/ | | +| fps | 1321 | +| iterations | 362 | +| time_elapsed | 561 | +| total_timesteps | 741376 | +| train/ | | +| approx_kl | 0.018072475 | +| clip_fraction | 0.364 | +| clip_range | 0.0748 | +| entropy_loss | -5.6 | +| explained_variance | 0.486 | +| learning_rate | 4.98e-05 | +| loss | -0.0306 | +| n_updates | 36792 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000261 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0213 | +| time/ | | +| fps | 1321 | +| iterations | 363 | +| time_elapsed | 562 | +| total_timesteps | 743424 | +| train/ | | +| approx_kl | 0.016691603 | +| clip_fraction | 0.37 | +| clip_range | 0.0748 | +| entropy_loss | -5.91 | +| explained_variance | 0.382 | +| learning_rate | 4.98e-05 | +| loss | -0.0342 | +| n_updates | 36796 | +| policy_gradient_loss | -0.023 | +| value_loss | 0.000216 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0156 | +| time/ | | +| fps | 1321 | +| iterations | 364 | +| time_elapsed | 564 | +| total_timesteps | 745472 | +| train/ | | +| approx_kl | 0.01862414 | +| clip_fraction | 0.392 | +| clip_range | 0.0748 | +| entropy_loss | -5.98 | +| explained_variance | 0.251 | +| learning_rate | 4.98e-05 | +| loss | -0.0367 | +| n_updates | 36800 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000207 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0156 | +| time/ | | +| fps | 1321 | +| iterations | 365 | +| time_elapsed | 565 | +| total_timesteps | 747520 | +| train/ | | +| approx_kl | 0.016986862 | +| clip_fraction | 0.392 | +| clip_range | 0.0748 | +| entropy_loss | -6.22 | +| explained_variance | 0.0255 | +| learning_rate | 4.98e-05 | +| loss | -0.0339 | +| n_updates | 36804 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.00034 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0146 | +| time/ | | +| fps | 1321 | +| iterations | 366 | +| time_elapsed | 567 | +| total_timesteps | 749568 | +| train/ | | +| approx_kl | 0.020612799 | +| clip_fraction | 0.405 | +| clip_range | 0.0748 | +| entropy_loss | -6.27 | +| explained_variance | 0.261 | +| learning_rate | 4.98e-05 | +| loss | -0.0399 | +| n_updates | 36808 | +| policy_gradient_loss | -0.0234 | +| value_loss | 0.000229 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0105 | +| time/ | | +| fps | 1321 | +| iterations | 367 | +| time_elapsed | 568 | +| total_timesteps | 751616 | +| train/ | | +| approx_kl | 0.019230943 | +| clip_fraction | 0.408 | +| clip_range | 0.0748 | +| entropy_loss | -6.43 | +| explained_variance | -0.055 | +| learning_rate | 4.98e-05 | +| loss | -0.0325 | +| n_updates | 36812 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.00027 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.00472 | +| time/ | | +| fps | 1321 | +| iterations | 368 | +| time_elapsed | 570 | +| total_timesteps | 753664 | +| train/ | | +| approx_kl | 0.017740067 | +| clip_fraction | 0.393 | +| clip_range | 0.0748 | +| entropy_loss | -6.01 | +| explained_variance | 0.385 | +| learning_rate | 4.98e-05 | +| loss | -0.0335 | +| n_updates | 36816 | +| policy_gradient_loss | -0.0221 | +| value_loss | 0.00024 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0124 | +| time/ | | +| fps | 1321 | +| iterations | 369 | +| time_elapsed | 571 | +| total_timesteps | 755712 | +| train/ | | +| approx_kl | 0.020640433 | +| clip_fraction | 0.422 | +| clip_range | 0.0748 | +| entropy_loss | -5.85 | +| explained_variance | 0.331 | +| learning_rate | 4.98e-05 | +| loss | -0.0303 | +| n_updates | 36820 | +| policy_gradient_loss | -0.0223 | +| value_loss | 0.000209 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.000333 | +| time/ | | +| fps | 1321 | +| iterations | 370 | +| time_elapsed | 573 | +| total_timesteps | 757760 | +| train/ | | +| approx_kl | 0.02244131 | +| clip_fraction | 0.398 | +| clip_range | 0.0748 | +| entropy_loss | -5.92 | +| explained_variance | 0.401 | +| learning_rate | 4.98e-05 | +| loss | -0.0283 | +| n_updates | 36824 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000224 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.00811 | +| time/ | | +| fps | 1321 | +| iterations | 371 | +| time_elapsed | 574 | +| total_timesteps | 759808 | +| train/ | | +| approx_kl | 0.017296365 | +| clip_fraction | 0.388 | +| clip_range | 0.0748 | +| entropy_loss | -5.35 | +| explained_variance | 0.668 | +| learning_rate | 4.98e-05 | +| loss | -0.0302 | +| n_updates | 36828 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000134 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | -0.00678 | +| time/ | | +| fps | 1321 | +| iterations | 372 | +| time_elapsed | 576 | +| total_timesteps | 761856 | +| train/ | | +| approx_kl | 0.019361172 | +| clip_fraction | 0.4 | +| clip_range | 0.0748 | +| entropy_loss | -5.91 | +| explained_variance | 0.235 | +| learning_rate | 4.98e-05 | +| loss | -0.0313 | +| n_updates | 36832 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000255 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | -0.00562 | +| time/ | | +| fps | 1321 | +| iterations | 373 | +| time_elapsed | 578 | +| total_timesteps | 763904 | +| train/ | | +| approx_kl | 0.016842877 | +| clip_fraction | 0.409 | +| clip_range | 0.0748 | +| entropy_loss | -5.97 | +| explained_variance | 0.414 | +| learning_rate | 4.98e-05 | +| loss | -0.0317 | +| n_updates | 36836 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000244 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | -0.00562 | +| time/ | | +| fps | 1321 | +| iterations | 374 | +| time_elapsed | 579 | +| total_timesteps | 765952 | +| train/ | | +| approx_kl | 0.016533507 | +| clip_fraction | 0.386 | +| clip_range | 0.0748 | +| entropy_loss | -6.03 | +| explained_variance | 0.269 | +| learning_rate | 4.98e-05 | +| loss | -0.0358 | +| n_updates | 36840 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000265 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.00207 | +| time/ | | +| fps | 1321 | +| iterations | 375 | +| time_elapsed | 581 | +| total_timesteps | 768000 | +| train/ | | +| approx_kl | 0.016690388 | +| clip_fraction | 0.409 | +| clip_range | 0.0748 | +| entropy_loss | -6.27 | +| explained_variance | -0.0769 | +| learning_rate | 4.98e-05 | +| loss | -0.0342 | +| n_updates | 36844 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000267 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | -0.0019 | +| time/ | | +| fps | 1321 | +| iterations | 376 | +| time_elapsed | 582 | +| total_timesteps | 770048 | +| train/ | | +| approx_kl | 0.015710697 | +| clip_fraction | 0.378 | +| clip_range | 0.0748 | +| entropy_loss | -5.97 | +| explained_variance | 0.148 | +| learning_rate | 4.98e-05 | +| loss | -0.0301 | +| n_updates | 36848 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.00104 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.00142 | +| time/ | | +| fps | 1321 | +| iterations | 377 | +| time_elapsed | 584 | +| total_timesteps | 772096 | +| train/ | | +| approx_kl | 0.015936917 | +| clip_fraction | 0.398 | +| clip_range | 0.0748 | +| entropy_loss | -5.58 | +| explained_variance | 0.433 | +| learning_rate | 4.98e-05 | +| loss | -0.0396 | +| n_updates | 36852 | +| policy_gradient_loss | -0.0223 | +| value_loss | 0.000273 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.000433 | +| time/ | | +| fps | 1321 | +| iterations | 378 | +| time_elapsed | 586 | +| total_timesteps | 774144 | +| train/ | | +| approx_kl | 0.020312347 | +| clip_fraction | 0.403 | +| clip_range | 0.0748 | +| entropy_loss | -5.59 | +| explained_variance | 0.504 | +| learning_rate | 4.98e-05 | +| loss | -0.0342 | +| n_updates | 36856 | +| policy_gradient_loss | -0.0228 | +| value_loss | 0.000188 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.000433 | +| time/ | | +| fps | 1321 | +| iterations | 379 | +| time_elapsed | 587 | +| total_timesteps | 776192 | +| train/ | | +| approx_kl | 0.021921426 | +| clip_fraction | 0.399 | +| clip_range | 0.0748 | +| entropy_loss | -5.68 | +| explained_variance | 0.308 | +| learning_rate | 4.98e-05 | +| loss | -0.0377 | +| n_updates | 36860 | +| policy_gradient_loss | -0.0229 | +| value_loss | 0.00024 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.00571 | +| time/ | | +| fps | 1321 | +| iterations | 380 | +| time_elapsed | 589 | +| total_timesteps | 778240 | +| train/ | | +| approx_kl | 0.01808157 | +| clip_fraction | 0.402 | +| clip_range | 0.0748 | +| entropy_loss | -5.9 | +| explained_variance | 0.0312 | +| learning_rate | 4.98e-05 | +| loss | -0.0404 | +| n_updates | 36864 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000252 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.008 | +| time/ | | +| fps | 1320 | +| iterations | 381 | +| time_elapsed | 590 | +| total_timesteps | 780288 | +| train/ | | +| approx_kl | 0.016720783 | +| clip_fraction | 0.406 | +| clip_range | 0.0748 | +| entropy_loss | -6.14 | +| explained_variance | 0.0643 | +| learning_rate | 4.98e-05 | +| loss | -0.0326 | +| n_updates | 36868 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000216 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.00928 | +| time/ | | +| fps | 1320 | +| iterations | 382 | +| time_elapsed | 592 | +| total_timesteps | 782336 | +| train/ | | +| approx_kl | 0.01958171 | +| clip_fraction | 0.387 | +| clip_range | 0.0748 | +| entropy_loss | -6.17 | +| explained_variance | 0.166 | +| learning_rate | 4.98e-05 | +| loss | -0.0353 | +| n_updates | 36872 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000216 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.00928 | +| time/ | | +| fps | 1320 | +| iterations | 383 | +| time_elapsed | 593 | +| total_timesteps | 784384 | +| train/ | | +| approx_kl | 0.019253068 | +| clip_fraction | 0.383 | +| clip_range | 0.0748 | +| entropy_loss | -5.75 | +| explained_variance | 0.281 | +| learning_rate | 4.98e-05 | +| loss | -0.0322 | +| n_updates | 36876 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.0004 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0172 | +| time/ | | +| fps | 1320 | +| iterations | 384 | +| time_elapsed | 595 | +| total_timesteps | 786432 | +| train/ | | +| approx_kl | 0.019919321 | +| clip_fraction | 0.407 | +| clip_range | 0.0748 | +| entropy_loss | -5.99 | +| explained_variance | 0.0606 | +| learning_rate | 4.98e-05 | +| loss | -0.0357 | +| n_updates | 36880 | +| policy_gradient_loss | -0.022 | +| value_loss | 0.000354 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0172 | +| time/ | | +| fps | 1320 | +| iterations | 385 | +| time_elapsed | 597 | +| total_timesteps | 788480 | +| train/ | | +| approx_kl | 0.017895378 | +| clip_fraction | 0.406 | +| clip_range | 0.0748 | +| entropy_loss | -6.04 | +| explained_variance | 0.145 | +| learning_rate | 4.98e-05 | +| loss | -0.0407 | +| n_updates | 36884 | +| policy_gradient_loss | -0.0222 | +| value_loss | 0.000358 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0113 | +| time/ | | +| fps | 1320 | +| iterations | 386 | +| time_elapsed | 598 | +| total_timesteps | 790528 | +| train/ | | +| approx_kl | 0.017781846 | +| clip_fraction | 0.396 | +| clip_range | 0.0748 | +| entropy_loss | -5.84 | +| explained_variance | 0.504 | +| learning_rate | 4.98e-05 | +| loss | -0.0359 | +| n_updates | 36888 | +| policy_gradient_loss | -0.0228 | +| value_loss | 0.000144 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.015 | +| time/ | | +| fps | 1320 | +| iterations | 387 | +| time_elapsed | 600 | +| total_timesteps | 792576 | +| train/ | | +| approx_kl | 0.017573388 | +| clip_fraction | 0.395 | +| clip_range | 0.0748 | +| entropy_loss | -5.74 | +| explained_variance | 0.404 | +| learning_rate | 4.98e-05 | +| loss | -0.0362 | +| n_updates | 36892 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000215 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0121 | +| time/ | | +| fps | 1320 | +| iterations | 388 | +| time_elapsed | 601 | +| total_timesteps | 794624 | +| train/ | | +| approx_kl | 0.019308295 | +| clip_fraction | 0.411 | +| clip_range | 0.0748 | +| entropy_loss | -5.62 | +| explained_variance | 0.336 | +| learning_rate | 4.98e-05 | +| loss | -0.033 | +| n_updates | 36896 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000178 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.00898 | +| time/ | | +| fps | 1320 | +| iterations | 389 | +| time_elapsed | 603 | +| total_timesteps | 796672 | +| train/ | | +| approx_kl | 0.018542362 | +| clip_fraction | 0.412 | +| clip_range | 0.0748 | +| entropy_loss | -5.86 | +| explained_variance | 0.118 | +| learning_rate | 4.98e-05 | +| loss | -0.0299 | +| n_updates | 36900 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000182 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.00898 | +| time/ | | +| fps | 1320 | +| iterations | 390 | +| time_elapsed | 604 | +| total_timesteps | 798720 | +| train/ | | +| approx_kl | 0.018359454 | +| clip_fraction | 0.385 | +| clip_range | 0.0748 | +| entropy_loss | -5.49 | +| explained_variance | 0.622 | +| learning_rate | 4.98e-05 | +| loss | -0.0271 | +| n_updates | 36904 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000178 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.00635 | +| time/ | | +| fps | 1320 | +| iterations | 391 | +| time_elapsed | 606 | +| total_timesteps | 800768 | +| train/ | | +| approx_kl | 0.018008871 | +| clip_fraction | 0.395 | +| clip_range | 0.0748 | +| entropy_loss | -6.14 | +| explained_variance | -0.041 | +| learning_rate | 4.98e-05 | +| loss | -0.0342 | +| n_updates | 36908 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000285 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.00899 | +| time/ | | +| fps | 1320 | +| iterations | 392 | +| time_elapsed | 607 | +| total_timesteps | 802816 | +| train/ | | +| approx_kl | 0.017159522 | +| clip_fraction | 0.375 | +| clip_range | 0.0748 | +| entropy_loss | -6.17 | +| explained_variance | 0.054 | +| learning_rate | 4.98e-05 | +| loss | -0.0344 | +| n_updates | 36912 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000272 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.00526 | +| time/ | | +| fps | 1320 | +| iterations | 393 | +| time_elapsed | 609 | +| total_timesteps | 804864 | +| train/ | | +| approx_kl | 0.01703839 | +| clip_fraction | 0.366 | +| clip_range | 0.0748 | +| entropy_loss | -6.05 | +| explained_variance | 0.149 | +| learning_rate | 4.98e-05 | +| loss | -0.0292 | +| n_updates | 36916 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000321 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.0103 | +| time/ | | +| fps | 1320 | +| iterations | 394 | +| time_elapsed | 610 | +| total_timesteps | 806912 | +| train/ | | +| approx_kl | 0.01774862 | +| clip_fraction | 0.384 | +| clip_range | 0.0748 | +| entropy_loss | -5.86 | +| explained_variance | 0.286 | +| learning_rate | 4.98e-05 | +| loss | -0.0341 | +| n_updates | 36920 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000182 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.0103 | +| time/ | | +| fps | 1320 | +| iterations | 395 | +| time_elapsed | 612 | +| total_timesteps | 808960 | +| train/ | | +| approx_kl | 0.019368596 | +| clip_fraction | 0.385 | +| clip_range | 0.0748 | +| entropy_loss | -5.6 | +| explained_variance | 0.318 | +| learning_rate | 4.98e-05 | +| loss | -0.0343 | +| n_updates | 36924 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000356 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.00171 | +| time/ | | +| fps | 1320 | +| iterations | 396 | +| time_elapsed | 614 | +| total_timesteps | 811008 | +| train/ | | +| approx_kl | 0.018081428 | +| clip_fraction | 0.394 | +| clip_range | 0.0748 | +| entropy_loss | -5.75 | +| explained_variance | 0.565 | +| learning_rate | 4.98e-05 | +| loss | -0.0337 | +| n_updates | 36928 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.00013 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.00171 | +| time/ | | +| fps | 1320 | +| iterations | 397 | +| time_elapsed | 615 | +| total_timesteps | 813056 | +| train/ | | +| approx_kl | 0.01964296 | +| clip_fraction | 0.398 | +| clip_range | 0.0748 | +| entropy_loss | -5.73 | +| explained_variance | 0.488 | +| learning_rate | 4.98e-05 | +| loss | -0.0347 | +| n_updates | 36932 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000265 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.00298 | +| time/ | | +| fps | 1320 | +| iterations | 398 | +| time_elapsed | 617 | +| total_timesteps | 815104 | +| train/ | | +| approx_kl | 0.018211879 | +| clip_fraction | 0.397 | +| clip_range | 0.0748 | +| entropy_loss | -5.97 | +| explained_variance | -0.15 | +| learning_rate | 4.98e-05 | +| loss | -0.0323 | +| n_updates | 36936 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000301 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | -0.000377 | +| time/ | | +| fps | 1320 | +| iterations | 399 | +| time_elapsed | 618 | +| total_timesteps | 817152 | +| train/ | | +| approx_kl | 0.017212236 | +| clip_fraction | 0.403 | +| clip_range | 0.0748 | +| entropy_loss | -5.89 | +| explained_variance | 0.0881 | +| learning_rate | 4.98e-05 | +| loss | -0.0332 | +| n_updates | 36940 | +| policy_gradient_loss | -0.0225 | +| value_loss | 0.000297 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.00201 | +| time/ | | +| fps | 1320 | +| iterations | 400 | +| time_elapsed | 620 | +| total_timesteps | 819200 | +| train/ | | +| approx_kl | 0.017853746 | +| clip_fraction | 0.431 | +| clip_range | 0.0748 | +| entropy_loss | -5.89 | +| explained_variance | 0.261 | +| learning_rate | 4.98e-05 | +| loss | -0.0362 | +| n_updates | 36944 | +| policy_gradient_loss | -0.023 | +| value_loss | 0.000188 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.0162 | +| time/ | | +| fps | 1320 | +| iterations | 401 | +| time_elapsed | 621 | +| total_timesteps | 821248 | +| train/ | | +| approx_kl | 0.017739134 | +| clip_fraction | 0.404 | +| clip_range | 0.0748 | +| entropy_loss | -5.5 | +| explained_variance | 0.427 | +| learning_rate | 4.98e-05 | +| loss | -0.0291 | +| n_updates | 36948 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.00026 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.0199 | +| time/ | | +| fps | 1320 | +| iterations | 402 | +| time_elapsed | 623 | +| total_timesteps | 823296 | +| train/ | | +| approx_kl | 0.019653749 | +| clip_fraction | 0.392 | +| clip_range | 0.0748 | +| entropy_loss | -5.81 | +| explained_variance | 0.284 | +| learning_rate | 4.98e-05 | +| loss | -0.032 | +| n_updates | 36952 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000313 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.017 | +| time/ | | +| fps | 1321 | +| iterations | 403 | +| time_elapsed | 624 | +| total_timesteps | 825344 | +| train/ | | +| approx_kl | 0.01927796 | +| clip_fraction | 0.411 | +| clip_range | 0.0748 | +| entropy_loss | -5.73 | +| explained_variance | 0.468 | +| learning_rate | 4.98e-05 | +| loss | -0.0326 | +| n_updates | 36956 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000193 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.0103 | +| time/ | | +| fps | 1321 | +| iterations | 404 | +| time_elapsed | 626 | +| total_timesteps | 827392 | +| train/ | | +| approx_kl | 0.019657383 | +| clip_fraction | 0.393 | +| clip_range | 0.0748 | +| entropy_loss | -5.82 | +| explained_variance | 0.272 | +| learning_rate | 4.98e-05 | +| loss | -0.0325 | +| n_updates | 36960 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.00036 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.0103 | +| time/ | | +| fps | 1321 | +| iterations | 405 | +| time_elapsed | 627 | +| total_timesteps | 829440 | +| train/ | | +| approx_kl | 0.014286555 | +| clip_fraction | 0.396 | +| clip_range | 0.0748 | +| entropy_loss | -6.07 | +| explained_variance | 0.212 | +| learning_rate | 4.98e-05 | +| loss | -0.0277 | +| n_updates | 36964 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000285 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.0131 | +| time/ | | +| fps | 1321 | +| iterations | 406 | +| time_elapsed | 629 | +| total_timesteps | 831488 | +| train/ | | +| approx_kl | 0.021604981 | +| clip_fraction | 0.406 | +| clip_range | 0.0748 | +| entropy_loss | -6.14 | +| explained_variance | -0.0712 | +| learning_rate | 4.98e-05 | +| loss | -0.0365 | +| n_updates | 36968 | +| policy_gradient_loss | -0.0221 | +| value_loss | 0.000205 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.0138 | +| time/ | | +| fps | 1321 | +| iterations | 407 | +| time_elapsed | 630 | +| total_timesteps | 833536 | +| train/ | | +| approx_kl | 0.019385558 | +| clip_fraction | 0.407 | +| clip_range | 0.0748 | +| entropy_loss | -6.08 | +| explained_variance | -0.102 | +| learning_rate | 4.98e-05 | +| loss | -0.0308 | +| n_updates | 36972 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000315 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.0153 | +| time/ | | +| fps | 1321 | +| iterations | 408 | +| time_elapsed | 632 | +| total_timesteps | 835584 | +| train/ | | +| approx_kl | 0.018995114 | +| clip_fraction | 0.422 | +| clip_range | 0.0748 | +| entropy_loss | -6.04 | +| explained_variance | 0.143 | +| learning_rate | 4.98e-05 | +| loss | -0.0384 | +| n_updates | 36976 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000239 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.0216 | +| time/ | | +| fps | 1321 | +| iterations | 409 | +| time_elapsed | 633 | +| total_timesteps | 837632 | +| train/ | | +| approx_kl | 0.017801598 | +| clip_fraction | 0.412 | +| clip_range | 0.0748 | +| entropy_loss | -6.12 | +| explained_variance | 0.173 | +| learning_rate | 4.98e-05 | +| loss | -0.0308 | +| n_updates | 36980 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000294 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.0105 | +| time/ | | +| fps | 1321 | +| iterations | 410 | +| time_elapsed | 635 | +| total_timesteps | 839680 | +| train/ | | +| approx_kl | 0.0202962 | +| clip_fraction | 0.401 | +| clip_range | 0.0748 | +| entropy_loss | -5.96 | +| explained_variance | 0.368 | +| learning_rate | 4.98e-05 | +| loss | -0.0316 | +| n_updates | 36984 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000219 | +--------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.0164 | +| time/ | | +| fps | 1321 | +| iterations | 411 | +| time_elapsed | 637 | +| total_timesteps | 841728 | +| train/ | | +| approx_kl | 0.01842319 | +| clip_fraction | 0.365 | +| clip_range | 0.0748 | +| entropy_loss | -5.57 | +| explained_variance | 0.367 | +| learning_rate | 4.98e-05 | +| loss | -0.0276 | +| n_updates | 36988 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000222 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.0166 | +| time/ | | +| fps | 1321 | +| iterations | 412 | +| time_elapsed | 638 | +| total_timesteps | 843776 | +| train/ | | +| approx_kl | 0.022884674 | +| clip_fraction | 0.401 | +| clip_range | 0.0748 | +| entropy_loss | -5.61 | +| explained_variance | 0.307 | +| learning_rate | 4.98e-05 | +| loss | -0.0333 | +| n_updates | 36992 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000346 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.0178 | +| time/ | | +| fps | 1321 | +| iterations | 413 | +| time_elapsed | 640 | +| total_timesteps | 845824 | +| train/ | | +| approx_kl | 0.020163849 | +| clip_fraction | 0.396 | +| clip_range | 0.0748 | +| entropy_loss | -5.53 | +| explained_variance | 0.389 | +| learning_rate | 4.98e-05 | +| loss | -0.038 | +| n_updates | 36996 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000309 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.0141 | +| time/ | | +| fps | 1321 | +| iterations | 414 | +| time_elapsed | 641 | +| total_timesteps | 847872 | +| train/ | | +| approx_kl | 0.021555591 | +| clip_fraction | 0.413 | +| clip_range | 0.0748 | +| entropy_loss | -5.82 | +| explained_variance | 0.221 | +| learning_rate | 4.98e-05 | +| loss | -0.0348 | +| n_updates | 37000 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000217 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.0146 | +| time/ | | +| fps | 1321 | +| iterations | 415 | +| time_elapsed | 643 | +| total_timesteps | 849920 | +| train/ | | +| approx_kl | 0.01819731 | +| clip_fraction | 0.413 | +| clip_range | 0.0748 | +| entropy_loss | -6.1 | +| explained_variance | -0.0208 | +| learning_rate | 4.98e-05 | +| loss | -0.037 | +| n_updates | 37004 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000318 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.0102 | +| time/ | | +| fps | 1321 | +| iterations | 416 | +| time_elapsed | 644 | +| total_timesteps | 851968 | +| train/ | | +| approx_kl | 0.02040876 | +| clip_fraction | 0.396 | +| clip_range | 0.0748 | +| entropy_loss | -5.46 | +| explained_variance | 0.458 | +| learning_rate | 4.98e-05 | +| loss | -0.0317 | +| n_updates | 37008 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000247 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.00914 | +| time/ | | +| fps | 1321 | +| iterations | 417 | +| time_elapsed | 646 | +| total_timesteps | 854016 | +| train/ | | +| approx_kl | 0.020389708 | +| clip_fraction | 0.415 | +| clip_range | 0.0748 | +| entropy_loss | -5.83 | +| explained_variance | 0.0756 | +| learning_rate | 4.98e-05 | +| loss | -0.0401 | +| n_updates | 37012 | +| policy_gradient_loss | -0.0222 | +| value_loss | 0.000342 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.0151 | +| time/ | | +| fps | 1321 | +| iterations | 418 | +| time_elapsed | 647 | +| total_timesteps | 856064 | +| train/ | | +| approx_kl | 0.01751299 | +| clip_fraction | 0.403 | +| clip_range | 0.0748 | +| entropy_loss | -5.93 | +| explained_variance | 0.0689 | +| learning_rate | 4.98e-05 | +| loss | -0.0336 | +| n_updates | 37016 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000274 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.0151 | +| time/ | | +| fps | 1321 | +| iterations | 419 | +| time_elapsed | 649 | +| total_timesteps | 858112 | +| train/ | | +| approx_kl | 0.01843715 | +| clip_fraction | 0.391 | +| clip_range | 0.0748 | +| entropy_loss | -5.95 | +| explained_variance | 0.206 | +| learning_rate | 4.98e-05 | +| loss | -0.0358 | +| n_updates | 37020 | +| policy_gradient_loss | -0.0225 | +| value_loss | 0.000268 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.0146 | +| time/ | | +| fps | 1321 | +| iterations | 420 | +| time_elapsed | 651 | +| total_timesteps | 860160 | +| train/ | | +| approx_kl | 0.02238313 | +| clip_fraction | 0.409 | +| clip_range | 0.0748 | +| entropy_loss | -5.83 | +| explained_variance | 0.207 | +| learning_rate | 4.98e-05 | +| loss | -0.0338 | +| n_updates | 37024 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000222 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.0159 | +| time/ | | +| fps | 1321 | +| iterations | 421 | +| time_elapsed | 652 | +| total_timesteps | 862208 | +| train/ | | +| approx_kl | 0.019850906 | +| clip_fraction | 0.389 | +| clip_range | 0.0748 | +| entropy_loss | -5.98 | +| explained_variance | 0.134 | +| learning_rate | 4.98e-05 | +| loss | -0.0335 | +| n_updates | 37028 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000268 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.0163 | +| time/ | | +| fps | 1320 | +| iterations | 422 | +| time_elapsed | 654 | +| total_timesteps | 864256 | +| train/ | | +| approx_kl | 0.018514838 | +| clip_fraction | 0.41 | +| clip_range | 0.0748 | +| entropy_loss | -5.87 | +| explained_variance | 0.454 | +| learning_rate | 4.98e-05 | +| loss | -0.0322 | +| n_updates | 37032 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000199 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.0222 | +| time/ | | +| fps | 1320 | +| iterations | 423 | +| time_elapsed | 655 | +| total_timesteps | 866304 | +| train/ | | +| approx_kl | 0.019250613 | +| clip_fraction | 0.38 | +| clip_range | 0.0748 | +| entropy_loss | -5.62 | +| explained_variance | 0.425 | +| learning_rate | 4.98e-05 | +| loss | -0.0324 | +| n_updates | 37036 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000249 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.0257 | +| time/ | | +| fps | 1320 | +| iterations | 424 | +| time_elapsed | 657 | +| total_timesteps | 868352 | +| train/ | | +| approx_kl | 0.017717052 | +| clip_fraction | 0.391 | +| clip_range | 0.0748 | +| entropy_loss | -5.5 | +| explained_variance | 0.399 | +| learning_rate | 4.98e-05 | +| loss | -0.0337 | +| n_updates | 37040 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000235 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.0257 | +| time/ | | +| fps | 1320 | +| iterations | 425 | +| time_elapsed | 659 | +| total_timesteps | 870400 | +| train/ | | +| approx_kl | 0.01803156 | +| clip_fraction | 0.411 | +| clip_range | 0.0748 | +| entropy_loss | -5.58 | +| explained_variance | 0.321 | +| learning_rate | 4.98e-05 | +| loss | -0.035 | +| n_updates | 37044 | +| policy_gradient_loss | -0.0224 | +| value_loss | 0.0003 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.0238 | +| time/ | | +| fps | 1320 | +| iterations | 426 | +| time_elapsed | 660 | +| total_timesteps | 872448 | +| train/ | | +| approx_kl | 0.02184521 | +| clip_fraction | 0.393 | +| clip_range | 0.0748 | +| entropy_loss | -5.84 | +| explained_variance | 0.235 | +| learning_rate | 4.98e-05 | +| loss | -0.035 | +| n_updates | 37048 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000187 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.0239 | +| time/ | | +| fps | 1320 | +| iterations | 427 | +| time_elapsed | 662 | +| total_timesteps | 874496 | +| train/ | | +| approx_kl | 0.02210768 | +| clip_fraction | 0.405 | +| clip_range | 0.0748 | +| entropy_loss | -5.64 | +| explained_variance | 0.337 | +| learning_rate | 4.98e-05 | +| loss | -0.0277 | +| n_updates | 37052 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000231 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.0293 | +| time/ | | +| fps | 1320 | +| iterations | 428 | +| time_elapsed | 663 | +| total_timesteps | 876544 | +| train/ | | +| approx_kl | 0.01812362 | +| clip_fraction | 0.383 | +| clip_range | 0.0748 | +| entropy_loss | -5.71 | +| explained_variance | 0.273 | +| learning_rate | 4.98e-05 | +| loss | -0.0334 | +| n_updates | 37056 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000328 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.0293 | +| time/ | | +| fps | 1320 | +| iterations | 429 | +| time_elapsed | 665 | +| total_timesteps | 878592 | +| train/ | | +| approx_kl | 0.019819848 | +| clip_fraction | 0.434 | +| clip_range | 0.0748 | +| entropy_loss | -5.71 | +| explained_variance | 0.286 | +| learning_rate | 4.98e-05 | +| loss | -0.0317 | +| n_updates | 37060 | +| policy_gradient_loss | -0.022 | +| value_loss | 0.000248 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.0294 | +| time/ | | +| fps | 1320 | +| iterations | 430 | +| time_elapsed | 667 | +| total_timesteps | 880640 | +| train/ | | +| approx_kl | 0.019050809 | +| clip_fraction | 0.43 | +| clip_range | 0.0748 | +| entropy_loss | -5.84 | +| explained_variance | -0.0982 | +| learning_rate | 4.98e-05 | +| loss | -0.0324 | +| n_updates | 37064 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000342 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.0341 | +| time/ | | +| fps | 1320 | +| iterations | 431 | +| time_elapsed | 668 | +| total_timesteps | 882688 | +| train/ | | +| approx_kl | 0.019100836 | +| clip_fraction | 0.407 | +| clip_range | 0.0748 | +| entropy_loss | -5.88 | +| explained_variance | 0.0438 | +| learning_rate | 4.98e-05 | +| loss | -0.0301 | +| n_updates | 37068 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000297 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.0335 | +| time/ | | +| fps | 1320 | +| iterations | 432 | +| time_elapsed | 670 | +| total_timesteps | 884736 | +| train/ | | +| approx_kl | 0.018048704 | +| clip_fraction | 0.403 | +| clip_range | 0.0748 | +| entropy_loss | -5.8 | +| explained_variance | 0.289 | +| learning_rate | 4.98e-05 | +| loss | -0.0378 | +| n_updates | 37072 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000256 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.0275 | +| time/ | | +| fps | 1320 | +| iterations | 433 | +| time_elapsed | 671 | +| total_timesteps | 886784 | +| train/ | | +| approx_kl | 0.017361036 | +| clip_fraction | 0.416 | +| clip_range | 0.0748 | +| entropy_loss | -5.85 | +| explained_variance | 0.202 | +| learning_rate | 4.98e-05 | +| loss | -0.0317 | +| n_updates | 37076 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000295 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.0329 | +| time/ | | +| fps | 1320 | +| iterations | 434 | +| time_elapsed | 673 | +| total_timesteps | 888832 | +| train/ | | +| approx_kl | 0.02132445 | +| clip_fraction | 0.402 | +| clip_range | 0.0748 | +| entropy_loss | -5.56 | +| explained_variance | 0.496 | +| learning_rate | 4.98e-05 | +| loss | -0.0407 | +| n_updates | 37080 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000157 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.0286 | +| time/ | | +| fps | 1320 | +| iterations | 435 | +| time_elapsed | 674 | +| total_timesteps | 890880 | +| train/ | | +| approx_kl | 0.018231612 | +| clip_fraction | 0.408 | +| clip_range | 0.0748 | +| entropy_loss | -5.6 | +| explained_variance | 0.4 | +| learning_rate | 4.98e-05 | +| loss | -0.0378 | +| n_updates | 37084 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.00017 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.0344 | +| time/ | | +| fps | 1320 | +| iterations | 436 | +| time_elapsed | 676 | +| total_timesteps | 892928 | +| train/ | | +| approx_kl | 0.023108037 | +| clip_fraction | 0.402 | +| clip_range | 0.0748 | +| entropy_loss | -5.91 | +| explained_variance | 0.0542 | +| learning_rate | 4.98e-05 | +| loss | -0.0329 | +| n_updates | 37088 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000143 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.0344 | +| time/ | | +| fps | 1320 | +| iterations | 437 | +| time_elapsed | 677 | +| total_timesteps | 894976 | +| train/ | | +| approx_kl | 0.01819266 | +| clip_fraction | 0.391 | +| clip_range | 0.0748 | +| entropy_loss | -5.18 | +| explained_variance | 0.592 | +| learning_rate | 4.98e-05 | +| loss | -0.0297 | +| n_updates | 37092 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000198 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.0321 | +| time/ | | +| fps | 1320 | +| iterations | 438 | +| time_elapsed | 679 | +| total_timesteps | 897024 | +| train/ | | +| approx_kl | 0.020063926 | +| clip_fraction | 0.386 | +| clip_range | 0.0748 | +| entropy_loss | -5.9 | +| explained_variance | 0.0654 | +| learning_rate | 4.98e-05 | +| loss | -0.0321 | +| n_updates | 37096 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000249 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.0342 | +| time/ | | +| fps | 1319 | +| iterations | 439 | +| time_elapsed | 681 | +| total_timesteps | 899072 | +| train/ | | +| approx_kl | 0.021142654 | +| clip_fraction | 0.41 | +| clip_range | 0.0748 | +| entropy_loss | -5.82 | +| explained_variance | 0.26 | +| learning_rate | 4.98e-05 | +| loss | -0.0325 | +| n_updates | 37100 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000208 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.0342 | +| time/ | | +| fps | 1320 | +| iterations | 440 | +| time_elapsed | 682 | +| total_timesteps | 901120 | +| train/ | | +| approx_kl | 0.016919725 | +| clip_fraction | 0.396 | +| clip_range | 0.0748 | +| entropy_loss | -5.8 | +| explained_variance | 0.315 | +| learning_rate | 4.98e-05 | +| loss | -0.0302 | +| n_updates | 37104 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000301 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.0342 | +| time/ | | +| fps | 1320 | +| iterations | 441 | +| time_elapsed | 684 | +| total_timesteps | 903168 | +| train/ | | +| approx_kl | 0.019975813 | +| clip_fraction | 0.39 | +| clip_range | 0.0748 | +| entropy_loss | -6.01 | +| explained_variance | 0.131 | +| learning_rate | 4.98e-05 | +| loss | -0.0366 | +| n_updates | 37108 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000328 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0359 | +| time/ | | +| fps | 1320 | +| iterations | 442 | +| time_elapsed | 685 | +| total_timesteps | 905216 | +| train/ | | +| approx_kl | 0.020947088 | +| clip_fraction | 0.413 | +| clip_range | 0.0748 | +| entropy_loss | -6.01 | +| explained_variance | -0.227 | +| learning_rate | 4.98e-05 | +| loss | -0.0292 | +| n_updates | 37112 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000191 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0316 | +| time/ | | +| fps | 1320 | +| iterations | 443 | +| time_elapsed | 687 | +| total_timesteps | 907264 | +| train/ | | +| approx_kl | 0.021129385 | +| clip_fraction | 0.406 | +| clip_range | 0.0748 | +| entropy_loss | -5.47 | +| explained_variance | 0.262 | +| learning_rate | 4.98e-05 | +| loss | -0.034 | +| n_updates | 37116 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000281 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0429 | +| time/ | | +| fps | 1320 | +| iterations | 444 | +| time_elapsed | 688 | +| total_timesteps | 909312 | +| train/ | | +| approx_kl | 0.02039936 | +| clip_fraction | 0.424 | +| clip_range | 0.0748 | +| entropy_loss | -5.91 | +| explained_variance | 0.0753 | +| learning_rate | 4.98e-05 | +| loss | -0.0359 | +| n_updates | 37120 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000243 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0441 | +| time/ | | +| fps | 1320 | +| iterations | 445 | +| time_elapsed | 690 | +| total_timesteps | 911360 | +| train/ | | +| approx_kl | 0.018826194 | +| clip_fraction | 0.378 | +| clip_range | 0.0748 | +| entropy_loss | -5.69 | +| explained_variance | 0.355 | +| learning_rate | 4.98e-05 | +| loss | -0.0336 | +| n_updates | 37124 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000168 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0413 | +| time/ | | +| fps | 1320 | +| iterations | 446 | +| time_elapsed | 691 | +| total_timesteps | 913408 | +| train/ | | +| approx_kl | 0.019027181 | +| clip_fraction | 0.397 | +| clip_range | 0.0748 | +| entropy_loss | -5.79 | +| explained_variance | 0.194 | +| learning_rate | 4.98e-05 | +| loss | -0.0358 | +| n_updates | 37128 | +| policy_gradient_loss | -0.0224 | +| value_loss | 0.000189 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0397 | +| time/ | | +| fps | 1320 | +| iterations | 447 | +| time_elapsed | 693 | +| total_timesteps | 915456 | +| train/ | | +| approx_kl | 0.020044964 | +| clip_fraction | 0.387 | +| clip_range | 0.0748 | +| entropy_loss | -5.41 | +| explained_variance | 0.42 | +| learning_rate | 4.98e-05 | +| loss | -0.0283 | +| n_updates | 37132 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000239 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0424 | +| time/ | | +| fps | 1320 | +| iterations | 448 | +| time_elapsed | 694 | +| total_timesteps | 917504 | +| train/ | | +| approx_kl | 0.020131556 | +| clip_fraction | 0.415 | +| clip_range | 0.0748 | +| entropy_loss | -5.68 | +| explained_variance | 0.135 | +| learning_rate | 4.98e-05 | +| loss | -0.0345 | +| n_updates | 37136 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000261 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0363 | +| time/ | | +| fps | 1320 | +| iterations | 449 | +| time_elapsed | 696 | +| total_timesteps | 919552 | +| train/ | | +| approx_kl | 0.018093195 | +| clip_fraction | 0.408 | +| clip_range | 0.0748 | +| entropy_loss | -5.86 | +| explained_variance | -0.153 | +| learning_rate | 4.98e-05 | +| loss | -0.0312 | +| n_updates | 37140 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.00029 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0363 | +| time/ | | +| fps | 1320 | +| iterations | 450 | +| time_elapsed | 698 | +| total_timesteps | 921600 | +| train/ | | +| approx_kl | 0.021923333 | +| clip_fraction | 0.427 | +| clip_range | 0.0748 | +| entropy_loss | -5.48 | +| explained_variance | 0.429 | +| learning_rate | 4.98e-05 | +| loss | -0.03 | +| n_updates | 37144 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000262 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0384 | +| time/ | | +| fps | 1320 | +| iterations | 451 | +| time_elapsed | 699 | +| total_timesteps | 923648 | +| train/ | | +| approx_kl | 0.02176294 | +| clip_fraction | 0.435 | +| clip_range | 0.0748 | +| entropy_loss | -5.79 | +| explained_variance | -0.223 | +| learning_rate | 4.98e-05 | +| loss | -0.0334 | +| n_updates | 37148 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000221 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0456 | +| time/ | | +| fps | 1320 | +| iterations | 452 | +| time_elapsed | 701 | +| total_timesteps | 925696 | +| train/ | | +| approx_kl | 0.022692464 | +| clip_fraction | 0.409 | +| clip_range | 0.0748 | +| entropy_loss | -5.68 | +| explained_variance | 0.459 | +| learning_rate | 4.98e-05 | +| loss | -0.0368 | +| n_updates | 37152 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000193 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.043 | +| time/ | | +| fps | 1320 | +| iterations | 453 | +| time_elapsed | 702 | +| total_timesteps | 927744 | +| train/ | | +| approx_kl | 0.0164837 | +| clip_fraction | 0.368 | +| clip_range | 0.0748 | +| entropy_loss | -5.67 | +| explained_variance | 0.164 | +| learning_rate | 4.98e-05 | +| loss | -0.0299 | +| n_updates | 37156 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000385 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0431 | +| time/ | | +| fps | 1320 | +| iterations | 454 | +| time_elapsed | 704 | +| total_timesteps | 929792 | +| train/ | | +| approx_kl | 0.021024885 | +| clip_fraction | 0.422 | +| clip_range | 0.0748 | +| entropy_loss | -5.73 | +| explained_variance | 0.202 | +| learning_rate | 4.98e-05 | +| loss | -0.0367 | +| n_updates | 37160 | +| policy_gradient_loss | -0.0238 | +| value_loss | 0.000231 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0438 | +| time/ | | +| fps | 1320 | +| iterations | 455 | +| time_elapsed | 705 | +| total_timesteps | 931840 | +| train/ | | +| approx_kl | 0.018349364 | +| clip_fraction | 0.415 | +| clip_range | 0.0748 | +| entropy_loss | -5.93 | +| explained_variance | -0.0464 | +| learning_rate | 4.98e-05 | +| loss | -0.0315 | +| n_updates | 37164 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000294 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0438 | +| time/ | | +| fps | 1320 | +| iterations | 456 | +| time_elapsed | 707 | +| total_timesteps | 933888 | +| train/ | | +| approx_kl | 0.01842611 | +| clip_fraction | 0.401 | +| clip_range | 0.0748 | +| entropy_loss | -5.45 | +| explained_variance | 0.393 | +| learning_rate | 4.98e-05 | +| loss | -0.0346 | +| n_updates | 37168 | +| policy_gradient_loss | -0.0221 | +| value_loss | 0.000273 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0432 | +| time/ | | +| fps | 1320 | +| iterations | 457 | +| time_elapsed | 708 | +| total_timesteps | 935936 | +| train/ | | +| approx_kl | 0.017490696 | +| clip_fraction | 0.39 | +| clip_range | 0.0748 | +| entropy_loss | -5.83 | +| explained_variance | -0.111 | +| learning_rate | 4.98e-05 | +| loss | -0.0357 | +| n_updates | 37172 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000251 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0489 | +| time/ | | +| fps | 1320 | +| iterations | 458 | +| time_elapsed | 710 | +| total_timesteps | 937984 | +| train/ | | +| approx_kl | 0.021816798 | +| clip_fraction | 0.41 | +| clip_range | 0.0748 | +| entropy_loss | -5.93 | +| explained_variance | 0.224 | +| learning_rate | 4.98e-05 | +| loss | -0.0328 | +| n_updates | 37176 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.00027 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0486 | +| time/ | | +| fps | 1320 | +| iterations | 459 | +| time_elapsed | 711 | +| total_timesteps | 940032 | +| train/ | | +| approx_kl | 0.019858113 | +| clip_fraction | 0.37 | +| clip_range | 0.0748 | +| entropy_loss | -5.72 | +| explained_variance | 0.321 | +| learning_rate | 4.98e-05 | +| loss | -0.0323 | +| n_updates | 37180 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000271 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.047 | +| time/ | | +| fps | 1320 | +| iterations | 460 | +| time_elapsed | 713 | +| total_timesteps | 942080 | +| train/ | | +| approx_kl | 0.018293148 | +| clip_fraction | 0.405 | +| clip_range | 0.0748 | +| entropy_loss | -5.8 | +| explained_variance | 0.2 | +| learning_rate | 4.98e-05 | +| loss | -0.0291 | +| n_updates | 37184 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000248 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0547 | +| time/ | | +| fps | 1320 | +| iterations | 461 | +| time_elapsed | 715 | +| total_timesteps | 944128 | +| train/ | | +| approx_kl | 0.020868286 | +| clip_fraction | 0.398 | +| clip_range | 0.0748 | +| entropy_loss | -5.73 | +| explained_variance | 0.29 | +| learning_rate | 4.98e-05 | +| loss | -0.032 | +| n_updates | 37188 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000342 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0547 | +| time/ | | +| fps | 1320 | +| iterations | 462 | +| time_elapsed | 716 | +| total_timesteps | 946176 | +| train/ | | +| approx_kl | 0.017809205 | +| clip_fraction | 0.406 | +| clip_range | 0.0748 | +| entropy_loss | -5.52 | +| explained_variance | 0.648 | +| learning_rate | 4.98e-05 | +| loss | -0.0318 | +| n_updates | 37192 | +| policy_gradient_loss | -0.0234 | +| value_loss | 0.000117 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0502 | +| time/ | | +| fps | 1320 | +| iterations | 463 | +| time_elapsed | 718 | +| total_timesteps | 948224 | +| train/ | | +| approx_kl | 0.019508362 | +| clip_fraction | 0.386 | +| clip_range | 0.0748 | +| entropy_loss | -5.75 | +| explained_variance | 0.142 | +| learning_rate | 4.98e-05 | +| loss | -0.0305 | +| n_updates | 37196 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000294 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0607 | +| time/ | | +| fps | 1320 | +| iterations | 464 | +| time_elapsed | 719 | +| total_timesteps | 950272 | +| train/ | | +| approx_kl | 0.0198843 | +| clip_fraction | 0.417 | +| clip_range | 0.0748 | +| entropy_loss | -5.99 | +| explained_variance | -0.146 | +| learning_rate | 4.98e-05 | +| loss | -0.0325 | +| n_updates | 37200 | +| policy_gradient_loss | -0.0234 | +| value_loss | 0.000284 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0473 | +| time/ | | +| fps | 1320 | +| iterations | 465 | +| time_elapsed | 721 | +| total_timesteps | 952320 | +| train/ | | +| approx_kl | 0.017688327 | +| clip_fraction | 0.411 | +| clip_range | 0.0748 | +| entropy_loss | -5.6 | +| explained_variance | 0.197 | +| learning_rate | 4.98e-05 | +| loss | -0.0299 | +| n_updates | 37204 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000306 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0473 | +| time/ | | +| fps | 1320 | +| iterations | 466 | +| time_elapsed | 722 | +| total_timesteps | 954368 | +| train/ | | +| approx_kl | 0.019381879 | +| clip_fraction | 0.393 | +| clip_range | 0.0748 | +| entropy_loss | -5.61 | +| explained_variance | 0.232 | +| learning_rate | 4.98e-05 | +| loss | -0.0315 | +| n_updates | 37208 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000372 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0468 | +| time/ | | +| fps | 1320 | +| iterations | 467 | +| time_elapsed | 724 | +| total_timesteps | 956416 | +| train/ | | +| approx_kl | 0.018718865 | +| clip_fraction | 0.384 | +| clip_range | 0.0748 | +| entropy_loss | -5.51 | +| explained_variance | 0.309 | +| learning_rate | 4.98e-05 | +| loss | -0.035 | +| n_updates | 37212 | +| policy_gradient_loss | -0.0225 | +| value_loss | 0.00028 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0485 | +| time/ | | +| fps | 1320 | +| iterations | 468 | +| time_elapsed | 725 | +| total_timesteps | 958464 | +| train/ | | +| approx_kl | 0.018326504 | +| clip_fraction | 0.438 | +| clip_range | 0.0748 | +| entropy_loss | -5.77 | +| explained_variance | 0.107 | +| learning_rate | 4.98e-05 | +| loss | -0.0473 | +| n_updates | 37216 | +| policy_gradient_loss | -0.0252 | +| value_loss | 0.000247 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0554 | +| time/ | | +| fps | 1320 | +| iterations | 469 | +| time_elapsed | 727 | +| total_timesteps | 960512 | +| train/ | | +| approx_kl | 0.020392818 | +| clip_fraction | 0.394 | +| clip_range | 0.0748 | +| entropy_loss | -5.94 | +| explained_variance | 0.0353 | +| learning_rate | 4.98e-05 | +| loss | -0.0316 | +| n_updates | 37220 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000244 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0627 | +| time/ | | +| fps | 1320 | +| iterations | 470 | +| time_elapsed | 728 | +| total_timesteps | 962560 | +| train/ | | +| approx_kl | 0.019683223 | +| clip_fraction | 0.413 | +| clip_range | 0.0748 | +| entropy_loss | -5.44 | +| explained_variance | 0.524 | +| learning_rate | 4.98e-05 | +| loss | -0.0238 | +| n_updates | 37224 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000212 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0634 | +| time/ | | +| fps | 1320 | +| iterations | 471 | +| time_elapsed | 730 | +| total_timesteps | 964608 | +| train/ | | +| approx_kl | 0.020724114 | +| clip_fraction | 0.404 | +| clip_range | 0.0748 | +| entropy_loss | -5.76 | +| explained_variance | 0.166 | +| learning_rate | 4.98e-05 | +| loss | -0.0335 | +| n_updates | 37228 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000302 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0613 | +| time/ | | +| fps | 1320 | +| iterations | 472 | +| time_elapsed | 731 | +| total_timesteps | 966656 | +| train/ | | +| approx_kl | 0.02114169 | +| clip_fraction | 0.41 | +| clip_range | 0.0748 | +| entropy_loss | -5.58 | +| explained_variance | 0.286 | +| learning_rate | 4.98e-05 | +| loss | -0.0378 | +| n_updates | 37232 | +| policy_gradient_loss | -0.0243 | +| value_loss | 0.000323 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.0613 | +| time/ | | +| fps | 1320 | +| iterations | 473 | +| time_elapsed | 733 | +| total_timesteps | 968704 | +| train/ | | +| approx_kl | 0.02129867 | +| clip_fraction | 0.404 | +| clip_range | 0.0748 | +| entropy_loss | -5.52 | +| explained_variance | 0.285 | +| learning_rate | 4.98e-05 | +| loss | -0.0359 | +| n_updates | 37236 | +| policy_gradient_loss | -0.0237 | +| value_loss | 0.000345 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.0606 | +| time/ | | +| fps | 1320 | +| iterations | 474 | +| time_elapsed | 735 | +| total_timesteps | 970752 | +| train/ | | +| approx_kl | 0.020744745 | +| clip_fraction | 0.422 | +| clip_range | 0.0748 | +| entropy_loss | -5.5 | +| explained_variance | 0.317 | +| learning_rate | 4.98e-05 | +| loss | -0.0374 | +| n_updates | 37240 | +| policy_gradient_loss | -0.024 | +| value_loss | 0.000154 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.0606 | +| time/ | | +| fps | 1320 | +| iterations | 475 | +| time_elapsed | 736 | +| total_timesteps | 972800 | +| train/ | | +| approx_kl | 0.020312332 | +| clip_fraction | 0.407 | +| clip_range | 0.0748 | +| entropy_loss | -5.31 | +| explained_variance | 0.25 | +| learning_rate | 4.98e-05 | +| loss | -0.038 | +| n_updates | 37244 | +| policy_gradient_loss | -0.0227 | +| value_loss | 0.000316 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.0615 | +| time/ | | +| fps | 1320 | +| iterations | 476 | +| time_elapsed | 738 | +| total_timesteps | 974848 | +| train/ | | +| approx_kl | 0.019715976 | +| clip_fraction | 0.417 | +| clip_range | 0.0748 | +| entropy_loss | -5.7 | +| explained_variance | 0.065 | +| learning_rate | 4.98e-05 | +| loss | -0.0365 | +| n_updates | 37248 | +| policy_gradient_loss | -0.0219 | +| value_loss | 0.00025 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.058 | +| time/ | | +| fps | 1320 | +| iterations | 477 | +| time_elapsed | 739 | +| total_timesteps | 976896 | +| train/ | | +| approx_kl | 0.024057077 | +| clip_fraction | 0.401 | +| clip_range | 0.0748 | +| entropy_loss | -5.69 | +| explained_variance | 0.0902 | +| learning_rate | 4.98e-05 | +| loss | -0.0344 | +| n_updates | 37252 | +| policy_gradient_loss | -0.0234 | +| value_loss | 0.000337 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.0507 | +| time/ | | +| fps | 1320 | +| iterations | 478 | +| time_elapsed | 741 | +| total_timesteps | 978944 | +| train/ | | +| approx_kl | 0.022002727 | +| clip_fraction | 0.409 | +| clip_range | 0.0748 | +| entropy_loss | -5.69 | +| explained_variance | 0.189 | +| learning_rate | 4.98e-05 | +| loss | -0.0398 | +| n_updates | 37256 | +| policy_gradient_loss | -0.0232 | +| value_loss | 0.000204 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.0507 | +| time/ | | +| fps | 1320 | +| iterations | 479 | +| time_elapsed | 742 | +| total_timesteps | 980992 | +| train/ | | +| approx_kl | 0.019853048 | +| clip_fraction | 0.394 | +| clip_range | 0.0748 | +| entropy_loss | -5.5 | +| explained_variance | 0.53 | +| learning_rate | 4.98e-05 | +| loss | -0.0346 | +| n_updates | 37260 | +| policy_gradient_loss | -0.022 | +| value_loss | 0.000175 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.0512 | +| time/ | | +| fps | 1320 | +| iterations | 480 | +| time_elapsed | 744 | +| total_timesteps | 983040 | +| train/ | | +| approx_kl | 0.021253183 | +| clip_fraction | 0.424 | +| clip_range | 0.0748 | +| entropy_loss | -5.72 | +| explained_variance | 0.181 | +| learning_rate | 4.98e-05 | +| loss | -0.0371 | +| n_updates | 37264 | +| policy_gradient_loss | -0.0229 | +| value_loss | 0.000197 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.0512 | +| time/ | | +| fps | 1320 | +| iterations | 481 | +| time_elapsed | 745 | +| total_timesteps | 985088 | +| train/ | | +| approx_kl | 0.02075629 | +| clip_fraction | 0.433 | +| clip_range | 0.0748 | +| entropy_loss | -5.97 | +| explained_variance | 0.00707 | +| learning_rate | 4.98e-05 | +| loss | -0.0359 | +| n_updates | 37268 | +| policy_gradient_loss | -0.023 | +| value_loss | 0.00037 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.0484 | +| time/ | | +| fps | 1320 | +| iterations | 482 | +| time_elapsed | 747 | +| total_timesteps | 987136 | +| train/ | | +| approx_kl | 0.019107884 | +| clip_fraction | 0.406 | +| clip_range | 0.0748 | +| entropy_loss | -5.52 | +| explained_variance | 0.445 | +| learning_rate | 4.98e-05 | +| loss | -0.0403 | +| n_updates | 37272 | +| policy_gradient_loss | -0.0219 | +| value_loss | 0.000176 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.0507 | +| time/ | | +| fps | 1320 | +| iterations | 483 | +| time_elapsed | 748 | +| total_timesteps | 989184 | +| train/ | | +| approx_kl | 0.018709097 | +| clip_fraction | 0.391 | +| clip_range | 0.0748 | +| entropy_loss | -5.77 | +| explained_variance | 0.358 | +| learning_rate | 4.98e-05 | +| loss | -0.0344 | +| n_updates | 37276 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000257 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.0507 | +| time/ | | +| fps | 1320 | +| iterations | 484 | +| time_elapsed | 750 | +| total_timesteps | 991232 | +| train/ | | +| approx_kl | 0.019549686 | +| clip_fraction | 0.404 | +| clip_range | 0.0748 | +| entropy_loss | -5.61 | +| explained_variance | 0.195 | +| learning_rate | 4.98e-05 | +| loss | -0.0341 | +| n_updates | 37280 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000231 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.049 | +| time/ | | +| fps | 1320 | +| iterations | 485 | +| time_elapsed | 752 | +| total_timesteps | 993280 | +| train/ | | +| approx_kl | 0.020872653 | +| clip_fraction | 0.408 | +| clip_range | 0.0748 | +| entropy_loss | -6.05 | +| explained_variance | -0.127 | +| learning_rate | 4.98e-05 | +| loss | -0.0346 | +| n_updates | 37284 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000354 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0451 | +| time/ | | +| fps | 1320 | +| iterations | 486 | +| time_elapsed | 753 | +| total_timesteps | 995328 | +| train/ | | +| approx_kl | 0.020728799 | +| clip_fraction | 0.399 | +| clip_range | 0.0748 | +| entropy_loss | -5.53 | +| explained_variance | 0.381 | +| learning_rate | 4.98e-05 | +| loss | -0.0333 | +| n_updates | 37288 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000319 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.0517 | +| time/ | | +| fps | 1320 | +| iterations | 487 | +| time_elapsed | 755 | +| total_timesteps | 997376 | +| train/ | | +| approx_kl | 0.016804082 | +| clip_fraction | 0.396 | +| clip_range | 0.0748 | +| entropy_loss | -5.42 | +| explained_variance | 0.478 | +| learning_rate | 4.98e-05 | +| loss | -0.0342 | +| n_updates | 37292 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000234 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.0517 | +| time/ | | +| fps | 1321 | +| iterations | 488 | +| time_elapsed | 756 | +| total_timesteps | 999424 | +| train/ | | +| approx_kl | 0.018193878 | +| clip_fraction | 0.372 | +| clip_range | 0.0748 | +| entropy_loss | -5.73 | +| explained_variance | 0.151 | +| learning_rate | 4.98e-05 | +| loss | -0.0313 | +| n_updates | 37296 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000413 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.0565 | +| time/ | | +| fps | 1320 | +| iterations | 489 | +| time_elapsed | 758 | +| total_timesteps | 1001472 | +| train/ | | +| approx_kl | 0.021157365 | +| clip_fraction | 0.417 | +| clip_range | 0.0748 | +| entropy_loss | -5.7 | +| explained_variance | 0.169 | +| learning_rate | 4.98e-05 | +| loss | -0.0379 | +| n_updates | 37300 | +| policy_gradient_loss | -0.0221 | +| value_loss | 0.000308 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.0717 | +| time/ | | +| fps | 1321 | +| iterations | 490 | +| time_elapsed | 759 | +| total_timesteps | 1003520 | +| train/ | | +| approx_kl | 0.017192652 | +| clip_fraction | 0.393 | +| clip_range | 0.0747 | +| entropy_loss | -5.39 | +| explained_variance | 0.51 | +| learning_rate | 4.98e-05 | +| loss | -0.0314 | +| n_updates | 37304 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.00022 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.0712 | +| time/ | | +| fps | 1321 | +| iterations | 491 | +| time_elapsed | 761 | +| total_timesteps | 1005568 | +| train/ | | +| approx_kl | 0.01819032 | +| clip_fraction | 0.382 | +| clip_range | 0.0747 | +| entropy_loss | -5.47 | +| explained_variance | 0.143 | +| learning_rate | 4.98e-05 | +| loss | -0.0256 | +| n_updates | 37308 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000724 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.0712 | +| time/ | | +| fps | 1320 | +| iterations | 492 | +| time_elapsed | 762 | +| total_timesteps | 1007616 | +| train/ | | +| approx_kl | 0.02192895 | +| clip_fraction | 0.407 | +| clip_range | 0.0747 | +| entropy_loss | -5.26 | +| explained_variance | 0.282 | +| learning_rate | 4.98e-05 | +| loss | -0.0395 | +| n_updates | 37312 | +| policy_gradient_loss | -0.0235 | +| value_loss | 0.000371 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.0712 | +| time/ | | +| fps | 1320 | +| iterations | 493 | +| time_elapsed | 764 | +| total_timesteps | 1009664 | +| train/ | | +| approx_kl | 0.02144519 | +| clip_fraction | 0.445 | +| clip_range | 0.0747 | +| entropy_loss | -5.94 | +| explained_variance | -0.133 | +| learning_rate | 4.98e-05 | +| loss | -0.0405 | +| n_updates | 37316 | +| policy_gradient_loss | -0.0268 | +| value_loss | 0.000252 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.0632 | +| time/ | | +| fps | 1320 | +| iterations | 494 | +| time_elapsed | 766 | +| total_timesteps | 1011712 | +| train/ | | +| approx_kl | 0.020717703 | +| clip_fraction | 0.431 | +| clip_range | 0.0747 | +| entropy_loss | -6.09 | +| explained_variance | -0.227 | +| learning_rate | 4.98e-05 | +| loss | -0.0373 | +| n_updates | 37320 | +| policy_gradient_loss | -0.0228 | +| value_loss | 0.00028 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.0632 | +| time/ | | +| fps | 1320 | +| iterations | 495 | +| time_elapsed | 767 | +| total_timesteps | 1013760 | +| train/ | | +| approx_kl | 0.018985612 | +| clip_fraction | 0.376 | +| clip_range | 0.0747 | +| entropy_loss | -5.16 | +| explained_variance | 0.44 | +| learning_rate | 4.98e-05 | +| loss | -0.0311 | +| n_updates | 37324 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.00029 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.0603 | +| time/ | | +| fps | 1320 | +| iterations | 496 | +| time_elapsed | 769 | +| total_timesteps | 1015808 | +| train/ | | +| approx_kl | 0.019730348 | +| clip_fraction | 0.41 | +| clip_range | 0.0747 | +| entropy_loss | -5.69 | +| explained_variance | 0.0164 | +| learning_rate | 4.98e-05 | +| loss | -0.0384 | +| n_updates | 37328 | +| policy_gradient_loss | -0.0228 | +| value_loss | 0.000317 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.0686 | +| time/ | | +| fps | 1320 | +| iterations | 497 | +| time_elapsed | 770 | +| total_timesteps | 1017856 | +| train/ | | +| approx_kl | 0.020039946 | +| clip_fraction | 0.418 | +| clip_range | 0.0747 | +| entropy_loss | -6.01 | +| explained_variance | -0.121 | +| learning_rate | 4.98e-05 | +| loss | -0.0341 | +| n_updates | 37332 | +| policy_gradient_loss | -0.0221 | +| value_loss | 0.000345 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.068 | +| time/ | | +| fps | 1320 | +| iterations | 498 | +| time_elapsed | 772 | +| total_timesteps | 1019904 | +| train/ | | +| approx_kl | 0.018759489 | +| clip_fraction | 0.405 | +| clip_range | 0.0747 | +| entropy_loss | -5.54 | +| explained_variance | 0.332 | +| learning_rate | 4.98e-05 | +| loss | -0.0314 | +| n_updates | 37336 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000259 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.068 | +| time/ | | +| fps | 1319 | +| iterations | 499 | +| time_elapsed | 774 | +| total_timesteps | 1021952 | +| train/ | | +| approx_kl | 0.021223374 | +| clip_fraction | 0.399 | +| clip_range | 0.0747 | +| entropy_loss | -5.33 | +| explained_variance | 0.396 | +| learning_rate | 4.98e-05 | +| loss | -0.0313 | +| n_updates | 37340 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000285 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.0642 | +| time/ | | +| fps | 1319 | +| iterations | 500 | +| time_elapsed | 776 | +| total_timesteps | 1024000 | +| train/ | | +| approx_kl | 0.01850698 | +| clip_fraction | 0.417 | +| clip_range | 0.0747 | +| entropy_loss | -5.69 | +| explained_variance | 0.0338 | +| learning_rate | 4.98e-05 | +| loss | -0.0373 | +| n_updates | 37344 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000187 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.0735 | +| time/ | | +| fps | 1319 | +| iterations | 501 | +| time_elapsed | 777 | +| total_timesteps | 1026048 | +| train/ | | +| approx_kl | 0.01943459 | +| clip_fraction | 0.401 | +| clip_range | 0.0747 | +| entropy_loss | -5.87 | +| explained_variance | -0.0292 | +| learning_rate | 4.98e-05 | +| loss | -0.0333 | +| n_updates | 37348 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.00021 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.0675 | +| time/ | | +| fps | 1319 | +| iterations | 502 | +| time_elapsed | 779 | +| total_timesteps | 1028096 | +| train/ | | +| approx_kl | 0.018114816 | +| clip_fraction | 0.371 | +| clip_range | 0.0747 | +| entropy_loss | -5.73 | +| explained_variance | 0.104 | +| learning_rate | 4.98e-05 | +| loss | -0.0331 | +| n_updates | 37352 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000902 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.063 | +| time/ | | +| fps | 1319 | +| iterations | 503 | +| time_elapsed | 780 | +| total_timesteps | 1030144 | +| train/ | | +| approx_kl | 0.022297975 | +| clip_fraction | 0.422 | +| clip_range | 0.0747 | +| entropy_loss | -5.74 | +| explained_variance | 0.0454 | +| learning_rate | 4.98e-05 | +| loss | -0.0415 | +| n_updates | 37356 | +| policy_gradient_loss | -0.0245 | +| value_loss | 0.000237 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.0594 | +| time/ | | +| fps | 1319 | +| iterations | 504 | +| time_elapsed | 782 | +| total_timesteps | 1032192 | +| train/ | | +| approx_kl | 0.020551434 | +| clip_fraction | 0.411 | +| clip_range | 0.0747 | +| entropy_loss | -5.3 | +| explained_variance | 0.554 | +| learning_rate | 4.98e-05 | +| loss | -0.0329 | +| n_updates | 37360 | +| policy_gradient_loss | -0.0223 | +| value_loss | 0.000164 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.0575 | +| time/ | | +| fps | 1319 | +| iterations | 505 | +| time_elapsed | 783 | +| total_timesteps | 1034240 | +| train/ | | +| approx_kl | 0.020352073 | +| clip_fraction | 0.409 | +| clip_range | 0.0747 | +| entropy_loss | -5.58 | +| explained_variance | 0.241 | +| learning_rate | 4.98e-05 | +| loss | -0.0305 | +| n_updates | 37364 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000291 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.0589 | +| time/ | | +| fps | 1319 | +| iterations | 506 | +| time_elapsed | 785 | +| total_timesteps | 1036288 | +| train/ | | +| approx_kl | 0.019379836 | +| clip_fraction | 0.416 | +| clip_range | 0.0747 | +| entropy_loss | -5.46 | +| explained_variance | 0.399 | +| learning_rate | 4.98e-05 | +| loss | -0.0341 | +| n_updates | 37368 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000273 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.0589 | +| time/ | | +| fps | 1319 | +| iterations | 507 | +| time_elapsed | 787 | +| total_timesteps | 1038336 | +| train/ | | +| approx_kl | 0.020308044 | +| clip_fraction | 0.398 | +| clip_range | 0.0747 | +| entropy_loss | -5.75 | +| explained_variance | 0.0988 | +| learning_rate | 4.98e-05 | +| loss | -0.0351 | +| n_updates | 37372 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000346 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.0589 | +| time/ | | +| fps | 1319 | +| iterations | 508 | +| time_elapsed | 788 | +| total_timesteps | 1040384 | +| train/ | | +| approx_kl | 0.018060993 | +| clip_fraction | 0.404 | +| clip_range | 0.0747 | +| entropy_loss | -5.92 | +| explained_variance | 0.0295 | +| learning_rate | 4.98e-05 | +| loss | -0.0355 | +| n_updates | 37376 | +| policy_gradient_loss | -0.0219 | +| value_loss | 0.0003 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.0537 | +| time/ | | +| fps | 1319 | +| iterations | 509 | +| time_elapsed | 790 | +| total_timesteps | 1042432 | +| train/ | | +| approx_kl | 0.019079657 | +| clip_fraction | 0.412 | +| clip_range | 0.0747 | +| entropy_loss | -6.08 | +| explained_variance | -0.156 | +| learning_rate | 4.98e-05 | +| loss | -0.0357 | +| n_updates | 37380 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000213 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.0573 | +| time/ | | +| fps | 1319 | +| iterations | 510 | +| time_elapsed | 791 | +| total_timesteps | 1044480 | +| train/ | | +| approx_kl | 0.019796621 | +| clip_fraction | 0.426 | +| clip_range | 0.0747 | +| entropy_loss | -5.9 | +| explained_variance | -0.222 | +| learning_rate | 4.98e-05 | +| loss | -0.038 | +| n_updates | 37384 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000249 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.0578 | +| time/ | | +| fps | 1319 | +| iterations | 511 | +| time_elapsed | 793 | +| total_timesteps | 1046528 | +| train/ | | +| approx_kl | 0.020959975 | +| clip_fraction | 0.397 | +| clip_range | 0.0747 | +| entropy_loss | -5.02 | +| explained_variance | 0.553 | +| learning_rate | 4.98e-05 | +| loss | -0.0336 | +| n_updates | 37388 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000178 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.0567 | +| time/ | | +| fps | 1319 | +| iterations | 512 | +| time_elapsed | 794 | +| total_timesteps | 1048576 | +| train/ | | +| approx_kl | 0.019001361 | +| clip_fraction | 0.404 | +| clip_range | 0.0747 | +| entropy_loss | -5.48 | +| explained_variance | 0.387 | +| learning_rate | 4.98e-05 | +| loss | -0.0361 | +| n_updates | 37392 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000242 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.0567 | +| time/ | | +| fps | 1319 | +| iterations | 513 | +| time_elapsed | 796 | +| total_timesteps | 1050624 | +| train/ | | +| approx_kl | 0.022900514 | +| clip_fraction | 0.396 | +| clip_range | 0.0747 | +| entropy_loss | -5.59 | +| explained_variance | 0.263 | +| learning_rate | 4.98e-05 | +| loss | -0.0329 | +| n_updates | 37396 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000281 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.0504 | +| time/ | | +| fps | 1319 | +| iterations | 514 | +| time_elapsed | 798 | +| total_timesteps | 1052672 | +| train/ | | +| approx_kl | 0.020620389 | +| clip_fraction | 0.428 | +| clip_range | 0.0747 | +| entropy_loss | -5.84 | +| explained_variance | -0.0204 | +| learning_rate | 4.98e-05 | +| loss | -0.0341 | +| n_updates | 37400 | +| policy_gradient_loss | -0.0222 | +| value_loss | 0.000221 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.0533 | +| time/ | | +| fps | 1319 | +| iterations | 515 | +| time_elapsed | 799 | +| total_timesteps | 1054720 | +| train/ | | +| approx_kl | 0.0204154 | +| clip_fraction | 0.397 | +| clip_range | 0.0747 | +| entropy_loss | -5.58 | +| explained_variance | 0.469 | +| learning_rate | 4.97e-05 | +| loss | -0.0344 | +| n_updates | 37404 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000253 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.0522 | +| time/ | | +| fps | 1319 | +| iterations | 516 | +| time_elapsed | 801 | +| total_timesteps | 1056768 | +| train/ | | +| approx_kl | 0.019652223 | +| clip_fraction | 0.386 | +| clip_range | 0.0747 | +| entropy_loss | -5.21 | +| explained_variance | 0.426 | +| learning_rate | 4.97e-05 | +| loss | -0.0304 | +| n_updates | 37408 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000248 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.0582 | +| time/ | | +| fps | 1319 | +| iterations | 517 | +| time_elapsed | 802 | +| total_timesteps | 1058816 | +| train/ | | +| approx_kl | 0.021354387 | +| clip_fraction | 0.396 | +| clip_range | 0.0747 | +| entropy_loss | -5.65 | +| explained_variance | 0.115 | +| learning_rate | 4.97e-05 | +| loss | -0.0342 | +| n_updates | 37412 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000343 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.0509 | +| time/ | | +| fps | 1319 | +| iterations | 518 | +| time_elapsed | 804 | +| total_timesteps | 1060864 | +| train/ | | +| approx_kl | 0.01917139 | +| clip_fraction | 0.384 | +| clip_range | 0.0747 | +| entropy_loss | -5.58 | +| explained_variance | 0.146 | +| learning_rate | 4.97e-05 | +| loss | -0.031 | +| n_updates | 37416 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000381 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.0587 | +| time/ | | +| fps | 1319 | +| iterations | 519 | +| time_elapsed | 805 | +| total_timesteps | 1062912 | +| train/ | | +| approx_kl | 0.021307584 | +| clip_fraction | 0.428 | +| clip_range | 0.0747 | +| entropy_loss | -5.67 | +| explained_variance | -0.0165 | +| learning_rate | 4.97e-05 | +| loss | -0.032 | +| n_updates | 37420 | +| policy_gradient_loss | -0.0226 | +| value_loss | 0.000367 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.059 | +| time/ | | +| fps | 1319 | +| iterations | 520 | +| time_elapsed | 807 | +| total_timesteps | 1064960 | +| train/ | | +| approx_kl | 0.01990324 | +| clip_fraction | 0.433 | +| clip_range | 0.0747 | +| entropy_loss | -5.47 | +| explained_variance | 0.503 | +| learning_rate | 4.97e-05 | +| loss | -0.0342 | +| n_updates | 37424 | +| policy_gradient_loss | -0.0223 | +| value_loss | 0.000233 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.0595 | +| time/ | | +| fps | 1319 | +| iterations | 521 | +| time_elapsed | 808 | +| total_timesteps | 1067008 | +| train/ | | +| approx_kl | 0.019841077 | +| clip_fraction | 0.411 | +| clip_range | 0.0747 | +| entropy_loss | -5.47 | +| explained_variance | 0.323 | +| learning_rate | 4.97e-05 | +| loss | -0.034 | +| n_updates | 37428 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000345 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.0595 | +| time/ | | +| fps | 1318 | +| iterations | 522 | +| time_elapsed | 810 | +| total_timesteps | 1069056 | +| train/ | | +| approx_kl | 0.022207022 | +| clip_fraction | 0.413 | +| clip_range | 0.0747 | +| entropy_loss | -5.28 | +| explained_variance | 0.486 | +| learning_rate | 4.97e-05 | +| loss | -0.0325 | +| n_updates | 37432 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000186 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.0595 | +| time/ | | +| fps | 1318 | +| iterations | 523 | +| time_elapsed | 812 | +| total_timesteps | 1071104 | +| train/ | | +| approx_kl | 0.021745462 | +| clip_fraction | 0.416 | +| clip_range | 0.0747 | +| entropy_loss | -5.17 | +| explained_variance | 0.478 | +| learning_rate | 4.97e-05 | +| loss | -0.0373 | +| n_updates | 37436 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000183 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.0501 | +| time/ | | +| fps | 1318 | +| iterations | 524 | +| time_elapsed | 813 | +| total_timesteps | 1073152 | +| train/ | | +| approx_kl | 0.021692108 | +| clip_fraction | 0.416 | +| clip_range | 0.0747 | +| entropy_loss | -5.9 | +| explained_variance | -0.12 | +| learning_rate | 4.97e-05 | +| loss | -0.033 | +| n_updates | 37440 | +| policy_gradient_loss | -0.0224 | +| value_loss | 0.000204 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.0501 | +| time/ | | +| fps | 1318 | +| iterations | 525 | +| time_elapsed | 815 | +| total_timesteps | 1075200 | +| train/ | | +| approx_kl | 0.021814596 | +| clip_fraction | 0.396 | +| clip_range | 0.0747 | +| entropy_loss | -5.78 | +| explained_variance | 0.043 | +| learning_rate | 4.97e-05 | +| loss | -0.0342 | +| n_updates | 37444 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000398 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.0501 | +| time/ | | +| fps | 1318 | +| iterations | 526 | +| time_elapsed | 816 | +| total_timesteps | 1077248 | +| train/ | | +| approx_kl | 0.022143478 | +| clip_fraction | 0.413 | +| clip_range | 0.0747 | +| entropy_loss | -5.6 | +| explained_variance | 0.141 | +| learning_rate | 4.97e-05 | +| loss | -0.0362 | +| n_updates | 37448 | +| policy_gradient_loss | -0.0221 | +| value_loss | 0.00022 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.0615 | +| time/ | | +| fps | 1318 | +| iterations | 527 | +| time_elapsed | 818 | +| total_timesteps | 1079296 | +| train/ | | +| approx_kl | 0.018774465 | +| clip_fraction | 0.395 | +| clip_range | 0.0747 | +| entropy_loss | -5.86 | +| explained_variance | -0.074 | +| learning_rate | 4.97e-05 | +| loss | -0.0361 | +| n_updates | 37452 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000305 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.0639 | +| time/ | | +| fps | 1319 | +| iterations | 528 | +| time_elapsed | 819 | +| total_timesteps | 1081344 | +| train/ | | +| approx_kl | 0.021776509 | +| clip_fraction | 0.416 | +| clip_range | 0.0747 | +| entropy_loss | -5.36 | +| explained_variance | 0.404 | +| learning_rate | 4.97e-05 | +| loss | -0.0341 | +| n_updates | 37456 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000226 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.0639 | +| time/ | | +| fps | 1318 | +| iterations | 529 | +| time_elapsed | 821 | +| total_timesteps | 1083392 | +| train/ | | +| approx_kl | 0.019869909 | +| clip_fraction | 0.408 | +| clip_range | 0.0747 | +| entropy_loss | -5.21 | +| explained_variance | 0.359 | +| learning_rate | 4.97e-05 | +| loss | -0.035 | +| n_updates | 37460 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000246 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.0631 | +| time/ | | +| fps | 1318 | +| iterations | 530 | +| time_elapsed | 822 | +| total_timesteps | 1085440 | +| train/ | | +| approx_kl | 0.020029712 | +| clip_fraction | 0.396 | +| clip_range | 0.0747 | +| entropy_loss | -5.56 | +| explained_variance | 0.14 | +| learning_rate | 4.97e-05 | +| loss | -0.0355 | +| n_updates | 37464 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000256 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.061 | +| time/ | | +| fps | 1319 | +| iterations | 531 | +| time_elapsed | 824 | +| total_timesteps | 1087488 | +| train/ | | +| approx_kl | 0.023683863 | +| clip_fraction | 0.417 | +| clip_range | 0.0747 | +| entropy_loss | -5.82 | +| explained_variance | -0.0164 | +| learning_rate | 4.97e-05 | +| loss | -0.0349 | +| n_updates | 37468 | +| policy_gradient_loss | -0.0219 | +| value_loss | 0.000204 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.0651 | +| time/ | | +| fps | 1319 | +| iterations | 532 | +| time_elapsed | 825 | +| total_timesteps | 1089536 | +| train/ | | +| approx_kl | 0.020526588 | +| clip_fraction | 0.419 | +| clip_range | 0.0747 | +| entropy_loss | -5.38 | +| explained_variance | 0.416 | +| learning_rate | 4.97e-05 | +| loss | -0.0298 | +| n_updates | 37472 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000269 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.0651 | +| time/ | | +| fps | 1319 | +| iterations | 533 | +| time_elapsed | 827 | +| total_timesteps | 1091584 | +| train/ | | +| approx_kl | 0.01687993 | +| clip_fraction | 0.396 | +| clip_range | 0.0747 | +| entropy_loss | -5.59 | +| explained_variance | 0.154 | +| learning_rate | 4.97e-05 | +| loss | -0.0371 | +| n_updates | 37476 | +| policy_gradient_loss | -0.023 | +| value_loss | 0.000198 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.0647 | +| time/ | | +| fps | 1319 | +| iterations | 534 | +| time_elapsed | 829 | +| total_timesteps | 1093632 | +| train/ | | +| approx_kl | 0.02301944 | +| clip_fraction | 0.44 | +| clip_range | 0.0747 | +| entropy_loss | -5.81 | +| explained_variance | -0.182 | +| learning_rate | 4.97e-05 | +| loss | -0.0352 | +| n_updates | 37480 | +| policy_gradient_loss | -0.0227 | +| value_loss | 0.00017 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.0647 | +| time/ | | +| fps | 1319 | +| iterations | 535 | +| time_elapsed | 830 | +| total_timesteps | 1095680 | +| train/ | | +| approx_kl | 0.01938197 | +| clip_fraction | 0.377 | +| clip_range | 0.0747 | +| entropy_loss | -5.33 | +| explained_variance | 0.318 | +| learning_rate | 4.97e-05 | +| loss | -0.0308 | +| n_updates | 37484 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000231 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.0665 | +| time/ | | +| fps | 1319 | +| iterations | 536 | +| time_elapsed | 832 | +| total_timesteps | 1097728 | +| train/ | | +| approx_kl | 0.014997573 | +| clip_fraction | 0.387 | +| clip_range | 0.0747 | +| entropy_loss | -6.01 | +| explained_variance | 0.217 | +| learning_rate | 4.97e-05 | +| loss | -0.0304 | +| n_updates | 37488 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.00021 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.0663 | +| time/ | | +| fps | 1319 | +| iterations | 537 | +| time_elapsed | 833 | +| total_timesteps | 1099776 | +| train/ | | +| approx_kl | 0.017242607 | +| clip_fraction | 0.382 | +| clip_range | 0.0747 | +| entropy_loss | -5.68 | +| explained_variance | 0.2 | +| learning_rate | 4.97e-05 | +| loss | -0.028 | +| n_updates | 37492 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000276 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.0663 | +| time/ | | +| fps | 1319 | +| iterations | 538 | +| time_elapsed | 835 | +| total_timesteps | 1101824 | +| train/ | | +| approx_kl | 0.019621748 | +| clip_fraction | 0.416 | +| clip_range | 0.0747 | +| entropy_loss | -5.39 | +| explained_variance | 0.621 | +| learning_rate | 4.97e-05 | +| loss | -0.0374 | +| n_updates | 37496 | +| policy_gradient_loss | -0.0242 | +| value_loss | 0.000137 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.0696 | +| time/ | | +| fps | 1319 | +| iterations | 539 | +| time_elapsed | 836 | +| total_timesteps | 1103872 | +| train/ | | +| approx_kl | 0.021150077 | +| clip_fraction | 0.432 | +| clip_range | 0.0747 | +| entropy_loss | -5.74 | +| explained_variance | -0.0643 | +| learning_rate | 4.97e-05 | +| loss | -0.0341 | +| n_updates | 37500 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000315 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.0795 | +| time/ | | +| fps | 1319 | +| iterations | 540 | +| time_elapsed | 838 | +| total_timesteps | 1105920 | +| train/ | | +| approx_kl | 0.02412735 | +| clip_fraction | 0.406 | +| clip_range | 0.0747 | +| entropy_loss | -5.35 | +| explained_variance | 0.232 | +| learning_rate | 4.97e-05 | +| loss | -0.0321 | +| n_updates | 37504 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000228 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.0781 | +| time/ | | +| fps | 1319 | +| iterations | 541 | +| time_elapsed | 839 | +| total_timesteps | 1107968 | +| train/ | | +| approx_kl | 0.01939549 | +| clip_fraction | 0.396 | +| clip_range | 0.0747 | +| entropy_loss | -4.86 | +| explained_variance | 0.694 | +| learning_rate | 4.97e-05 | +| loss | -0.0278 | +| n_updates | 37508 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000201 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.0745 | +| time/ | | +| fps | 1319 | +| iterations | 542 | +| time_elapsed | 841 | +| total_timesteps | 1110016 | +| train/ | | +| approx_kl | 0.020008508 | +| clip_fraction | 0.42 | +| clip_range | 0.0747 | +| entropy_loss | -4.96 | +| explained_variance | 0.519 | +| learning_rate | 4.97e-05 | +| loss | -0.0345 | +| n_updates | 37512 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000185 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.0745 | +| time/ | | +| fps | 1319 | +| iterations | 543 | +| time_elapsed | 842 | +| total_timesteps | 1112064 | +| train/ | | +| approx_kl | 0.019047704 | +| clip_fraction | 0.41 | +| clip_range | 0.0747 | +| entropy_loss | -5.56 | +| explained_variance | 0.46 | +| learning_rate | 4.97e-05 | +| loss | -0.0306 | +| n_updates | 37516 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000159 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.0749 | +| time/ | | +| fps | 1319 | +| iterations | 544 | +| time_elapsed | 844 | +| total_timesteps | 1114112 | +| train/ | | +| approx_kl | 0.020397622 | +| clip_fraction | 0.384 | +| clip_range | 0.0747 | +| entropy_loss | -5.69 | +| explained_variance | -0.0898 | +| learning_rate | 4.97e-05 | +| loss | -0.0314 | +| n_updates | 37520 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000337 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.0749 | +| time/ | | +| fps | 1319 | +| iterations | 545 | +| time_elapsed | 846 | +| total_timesteps | 1116160 | +| train/ | | +| approx_kl | 0.02050801 | +| clip_fraction | 0.412 | +| clip_range | 0.0747 | +| entropy_loss | -5.64 | +| explained_variance | 0.16 | +| learning_rate | 4.97e-05 | +| loss | -0.0349 | +| n_updates | 37524 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000265 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.0807 | +| time/ | | +| fps | 1319 | +| iterations | 546 | +| time_elapsed | 847 | +| total_timesteps | 1118208 | +| train/ | | +| approx_kl | 0.020508725 | +| clip_fraction | 0.429 | +| clip_range | 0.0747 | +| entropy_loss | -5.83 | +| explained_variance | -0.0488 | +| learning_rate | 4.97e-05 | +| loss | -0.0364 | +| n_updates | 37528 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000325 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.0868 | +| time/ | | +| fps | 1319 | +| iterations | 547 | +| time_elapsed | 849 | +| total_timesteps | 1120256 | +| train/ | | +| approx_kl | 0.017417992 | +| clip_fraction | 0.39 | +| clip_range | 0.0747 | +| entropy_loss | -5.14 | +| explained_variance | 0.2 | +| learning_rate | 4.97e-05 | +| loss | -0.0289 | +| n_updates | 37532 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000463 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.0811 | +| time/ | | +| fps | 1319 | +| iterations | 548 | +| time_elapsed | 850 | +| total_timesteps | 1122304 | +| train/ | | +| approx_kl | 0.02156826 | +| clip_fraction | 0.412 | +| clip_range | 0.0747 | +| entropy_loss | -5.42 | +| explained_variance | 0.208 | +| learning_rate | 4.97e-05 | +| loss | -0.0341 | +| n_updates | 37536 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000288 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.0811 | +| time/ | | +| fps | 1319 | +| iterations | 549 | +| time_elapsed | 852 | +| total_timesteps | 1124352 | +| train/ | | +| approx_kl | 0.022435002 | +| clip_fraction | 0.407 | +| clip_range | 0.0747 | +| entropy_loss | -5.4 | +| explained_variance | -0.0608 | +| learning_rate | 4.97e-05 | +| loss | -0.0355 | +| n_updates | 37540 | +| policy_gradient_loss | -0.0222 | +| value_loss | 0.000354 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.0812 | +| time/ | | +| fps | 1319 | +| iterations | 550 | +| time_elapsed | 853 | +| total_timesteps | 1126400 | +| train/ | | +| approx_kl | 0.024513813 | +| clip_fraction | 0.439 | +| clip_range | 0.0747 | +| entropy_loss | -5.54 | +| explained_variance | -0.233 | +| learning_rate | 4.97e-05 | +| loss | -0.0329 | +| n_updates | 37544 | +| policy_gradient_loss | -0.022 | +| value_loss | 0.000251 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.0916 | +| time/ | | +| fps | 1319 | +| iterations | 551 | +| time_elapsed | 855 | +| total_timesteps | 1128448 | +| train/ | | +| approx_kl | 0.021351935 | +| clip_fraction | 0.414 | +| clip_range | 0.0747 | +| entropy_loss | -5.52 | +| explained_variance | 0.237 | +| learning_rate | 4.97e-05 | +| loss | -0.0291 | +| n_updates | 37548 | +| policy_gradient_loss | -0.0219 | +| value_loss | 0.000154 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.0906 | +| time/ | | +| fps | 1319 | +| iterations | 552 | +| time_elapsed | 856 | +| total_timesteps | 1130496 | +| train/ | | +| approx_kl | 0.0220355 | +| clip_fraction | 0.374 | +| clip_range | 0.0747 | +| entropy_loss | -5.56 | +| explained_variance | 0.234 | +| learning_rate | 4.97e-05 | +| loss | -0.0235 | +| n_updates | 37552 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000422 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.0814 | +| time/ | | +| fps | 1319 | +| iterations | 553 | +| time_elapsed | 858 | +| total_timesteps | 1132544 | +| train/ | | +| approx_kl | 0.021943828 | +| clip_fraction | 0.427 | +| clip_range | 0.0747 | +| entropy_loss | -5.55 | +| explained_variance | 0.147 | +| learning_rate | 4.97e-05 | +| loss | -0.0323 | +| n_updates | 37556 | +| policy_gradient_loss | -0.0232 | +| value_loss | 0.000256 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.0894 | +| time/ | | +| fps | 1319 | +| iterations | 554 | +| time_elapsed | 859 | +| total_timesteps | 1134592 | +| train/ | | +| approx_kl | 0.023362275 | +| clip_fraction | 0.431 | +| clip_range | 0.0747 | +| entropy_loss | -5.3 | +| explained_variance | 0.542 | +| learning_rate | 4.97e-05 | +| loss | -0.0378 | +| n_updates | 37560 | +| policy_gradient_loss | -0.0233 | +| value_loss | 0.000194 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.0868 | +| time/ | | +| fps | 1319 | +| iterations | 555 | +| time_elapsed | 861 | +| total_timesteps | 1136640 | +| train/ | | +| approx_kl | 0.02075158 | +| clip_fraction | 0.392 | +| clip_range | 0.0747 | +| entropy_loss | -5.24 | +| explained_variance | 0.118 | +| learning_rate | 4.97e-05 | +| loss | -0.0301 | +| n_updates | 37564 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000317 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.0926 | +| time/ | | +| fps | 1319 | +| iterations | 556 | +| time_elapsed | 862 | +| total_timesteps | 1138688 | +| train/ | | +| approx_kl | 0.020818947 | +| clip_fraction | 0.413 | +| clip_range | 0.0747 | +| entropy_loss | -4.97 | +| explained_variance | 0.354 | +| learning_rate | 4.97e-05 | +| loss | -0.0351 | +| n_updates | 37568 | +| policy_gradient_loss | -0.0221 | +| value_loss | 0.000236 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.0846 | +| time/ | | +| fps | 1319 | +| iterations | 557 | +| time_elapsed | 864 | +| total_timesteps | 1140736 | +| train/ | | +| approx_kl | 0.022980273 | +| clip_fraction | 0.415 | +| clip_range | 0.0747 | +| entropy_loss | -4.91 | +| explained_variance | 0.491 | +| learning_rate | 4.97e-05 | +| loss | -0.0373 | +| n_updates | 37572 | +| policy_gradient_loss | -0.0235 | +| value_loss | 0.0002 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.0825 | +| time/ | | +| fps | 1319 | +| iterations | 558 | +| time_elapsed | 866 | +| total_timesteps | 1142784 | +| train/ | | +| approx_kl | 0.021579536 | +| clip_fraction | 0.437 | +| clip_range | 0.0747 | +| entropy_loss | -5.35 | +| explained_variance | 0.151 | +| learning_rate | 4.97e-05 | +| loss | -0.035 | +| n_updates | 37576 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000334 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.0814 | +| time/ | | +| fps | 1319 | +| iterations | 559 | +| time_elapsed | 867 | +| total_timesteps | 1144832 | +| train/ | | +| approx_kl | 0.021996211 | +| clip_fraction | 0.427 | +| clip_range | 0.0747 | +| entropy_loss | -5.32 | +| explained_variance | 0.332 | +| learning_rate | 4.97e-05 | +| loss | -0.0351 | +| n_updates | 37580 | +| policy_gradient_loss | -0.0226 | +| value_loss | 0.000374 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.0806 | +| time/ | | +| fps | 1319 | +| iterations | 560 | +| time_elapsed | 869 | +| total_timesteps | 1146880 | +| train/ | | +| approx_kl | 0.024189133 | +| clip_fraction | 0.429 | +| clip_range | 0.0747 | +| entropy_loss | -5.47 | +| explained_variance | -0.264 | +| learning_rate | 4.97e-05 | +| loss | -0.0356 | +| n_updates | 37584 | +| policy_gradient_loss | -0.0248 | +| value_loss | 0.000191 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.0783 | +| time/ | | +| fps | 1319 | +| iterations | 561 | +| time_elapsed | 870 | +| total_timesteps | 1148928 | +| train/ | | +| approx_kl | 0.022464594 | +| clip_fraction | 0.4 | +| clip_range | 0.0747 | +| entropy_loss | -5.31 | +| explained_variance | 0.238 | +| learning_rate | 4.97e-05 | +| loss | -0.036 | +| n_updates | 37588 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000255 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.0637 | +| time/ | | +| fps | 1319 | +| iterations | 562 | +| time_elapsed | 872 | +| total_timesteps | 1150976 | +| train/ | | +| approx_kl | 0.023153767 | +| clip_fraction | 0.411 | +| clip_range | 0.0747 | +| entropy_loss | -5.38 | +| explained_variance | 0.15 | +| learning_rate | 4.97e-05 | +| loss | -0.0357 | +| n_updates | 37592 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.00038 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.0627 | +| time/ | | +| fps | 1319 | +| iterations | 563 | +| time_elapsed | 873 | +| total_timesteps | 1153024 | +| train/ | | +| approx_kl | 0.020940064 | +| clip_fraction | 0.424 | +| clip_range | 0.0747 | +| entropy_loss | -5.35 | +| explained_variance | 0.356 | +| learning_rate | 4.97e-05 | +| loss | -0.037 | +| n_updates | 37596 | +| policy_gradient_loss | -0.0234 | +| value_loss | 0.000204 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.0687 | +| time/ | | +| fps | 1319 | +| iterations | 564 | +| time_elapsed | 875 | +| total_timesteps | 1155072 | +| train/ | | +| approx_kl | 0.020740494 | +| clip_fraction | 0.409 | +| clip_range | 0.0747 | +| entropy_loss | -5.25 | +| explained_variance | 0.436 | +| learning_rate | 4.97e-05 | +| loss | -0.0343 | +| n_updates | 37600 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000221 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.0632 | +| time/ | | +| fps | 1319 | +| iterations | 565 | +| time_elapsed | 876 | +| total_timesteps | 1157120 | +| train/ | | +| approx_kl | 0.023816234 | +| clip_fraction | 0.42 | +| clip_range | 0.0747 | +| entropy_loss | -5.14 | +| explained_variance | 0.0932 | +| learning_rate | 4.97e-05 | +| loss | -0.0333 | +| n_updates | 37604 | +| policy_gradient_loss | -0.0227 | +| value_loss | 0.000302 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.0584 | +| time/ | | +| fps | 1319 | +| iterations | 566 | +| time_elapsed | 878 | +| total_timesteps | 1159168 | +| train/ | | +| approx_kl | 0.023228362 | +| clip_fraction | 0.404 | +| clip_range | 0.0747 | +| entropy_loss | -5.25 | +| explained_variance | 0.267 | +| learning_rate | 4.97e-05 | +| loss | -0.0308 | +| n_updates | 37608 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000401 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.0608 | +| time/ | | +| fps | 1319 | +| iterations | 567 | +| time_elapsed | 880 | +| total_timesteps | 1161216 | +| train/ | | +| approx_kl | 0.022490088 | +| clip_fraction | 0.392 | +| clip_range | 0.0747 | +| entropy_loss | -5.07 | +| explained_variance | 0.262 | +| learning_rate | 4.97e-05 | +| loss | -0.0342 | +| n_updates | 37612 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000635 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.0609 | +| time/ | | +| fps | 1319 | +| iterations | 568 | +| time_elapsed | 881 | +| total_timesteps | 1163264 | +| train/ | | +| approx_kl | 0.020336203 | +| clip_fraction | 0.416 | +| clip_range | 0.0747 | +| entropy_loss | -5.3 | +| explained_variance | 0.123 | +| learning_rate | 4.97e-05 | +| loss | -0.0371 | +| n_updates | 37616 | +| policy_gradient_loss | -0.0235 | +| value_loss | 0.000294 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.0634 | +| time/ | | +| fps | 1319 | +| iterations | 569 | +| time_elapsed | 883 | +| total_timesteps | 1165312 | +| train/ | | +| approx_kl | 0.02219826 | +| clip_fraction | 0.383 | +| clip_range | 0.0747 | +| entropy_loss | -5.68 | +| explained_variance | 0.184 | +| learning_rate | 4.97e-05 | +| loss | -0.0361 | +| n_updates | 37620 | +| policy_gradient_loss | -0.0219 | +| value_loss | 0.000281 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.0559 | +| time/ | | +| fps | 1319 | +| iterations | 570 | +| time_elapsed | 884 | +| total_timesteps | 1167360 | +| train/ | | +| approx_kl | 0.020481208 | +| clip_fraction | 0.427 | +| clip_range | 0.0747 | +| entropy_loss | -5.38 | +| explained_variance | 0.0273 | +| learning_rate | 4.97e-05 | +| loss | -0.0361 | +| n_updates | 37624 | +| policy_gradient_loss | -0.023 | +| value_loss | 0.00024 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.0585 | +| time/ | | +| fps | 1319 | +| iterations | 571 | +| time_elapsed | 886 | +| total_timesteps | 1169408 | +| train/ | | +| approx_kl | 0.020477204 | +| clip_fraction | 0.406 | +| clip_range | 0.0747 | +| entropy_loss | -5.2 | +| explained_variance | 0.588 | +| learning_rate | 4.97e-05 | +| loss | -0.0302 | +| n_updates | 37628 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000177 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.0558 | +| time/ | | +| fps | 1319 | +| iterations | 572 | +| time_elapsed | 888 | +| total_timesteps | 1171456 | +| train/ | | +| approx_kl | 0.02216785 | +| clip_fraction | 0.412 | +| clip_range | 0.0747 | +| entropy_loss | -5.28 | +| explained_variance | 0.319 | +| learning_rate | 4.97e-05 | +| loss | -0.0306 | +| n_updates | 37632 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000231 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.0555 | +| time/ | | +| fps | 1319 | +| iterations | 573 | +| time_elapsed | 889 | +| total_timesteps | 1173504 | +| train/ | | +| approx_kl | 0.02130995 | +| clip_fraction | 0.425 | +| clip_range | 0.0747 | +| entropy_loss | -5.3 | +| explained_variance | -0.0104 | +| learning_rate | 4.97e-05 | +| loss | -0.0351 | +| n_updates | 37636 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000254 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.0688 | +| time/ | | +| fps | 1319 | +| iterations | 574 | +| time_elapsed | 891 | +| total_timesteps | 1175552 | +| train/ | | +| approx_kl | 0.021672893 | +| clip_fraction | 0.413 | +| clip_range | 0.0747 | +| entropy_loss | -5.29 | +| explained_variance | 0.343 | +| learning_rate | 4.97e-05 | +| loss | -0.0343 | +| n_updates | 37640 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000194 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.0609 | +| time/ | | +| fps | 1319 | +| iterations | 575 | +| time_elapsed | 892 | +| total_timesteps | 1177600 | +| train/ | | +| approx_kl | 0.019883791 | +| clip_fraction | 0.387 | +| clip_range | 0.0747 | +| entropy_loss | -5.12 | +| explained_variance | 0.22 | +| learning_rate | 4.97e-05 | +| loss | -0.0315 | +| n_updates | 37644 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000812 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.0609 | +| time/ | | +| fps | 1319 | +| iterations | 576 | +| time_elapsed | 894 | +| total_timesteps | 1179648 | +| train/ | | +| approx_kl | 0.020839619 | +| clip_fraction | 0.399 | +| clip_range | 0.0747 | +| entropy_loss | -5.29 | +| explained_variance | 0.242 | +| learning_rate | 4.97e-05 | +| loss | -0.0323 | +| n_updates | 37648 | +| policy_gradient_loss | -0.022 | +| value_loss | 0.000246 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.0575 | +| time/ | | +| fps | 1319 | +| iterations | 577 | +| time_elapsed | 895 | +| total_timesteps | 1181696 | +| train/ | | +| approx_kl | 0.024264038 | +| clip_fraction | 0.437 | +| clip_range | 0.0747 | +| entropy_loss | -5.34 | +| explained_variance | -0.195 | +| learning_rate | 4.97e-05 | +| loss | -0.0365 | +| n_updates | 37652 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.00024 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.0691 | +| time/ | | +| fps | 1319 | +| iterations | 578 | +| time_elapsed | 897 | +| total_timesteps | 1183744 | +| train/ | | +| approx_kl | 0.020721078 | +| clip_fraction | 0.433 | +| clip_range | 0.0747 | +| entropy_loss | -5.24 | +| explained_variance | -0.0564 | +| learning_rate | 4.97e-05 | +| loss | -0.0382 | +| n_updates | 37656 | +| policy_gradient_loss | -0.0231 | +| value_loss | 0.000287 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.0537 | +| time/ | | +| fps | 1318 | +| iterations | 579 | +| time_elapsed | 899 | +| total_timesteps | 1185792 | +| train/ | | +| approx_kl | 0.023623584 | +| clip_fraction | 0.396 | +| clip_range | 0.0747 | +| entropy_loss | -5.27 | +| explained_variance | 0.141 | +| learning_rate | 4.97e-05 | +| loss | -0.0314 | +| n_updates | 37660 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000829 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.0537 | +| time/ | | +| fps | 1318 | +| iterations | 580 | +| time_elapsed | 900 | +| total_timesteps | 1187840 | +| train/ | | +| approx_kl | 0.01876688 | +| clip_fraction | 0.424 | +| clip_range | 0.0747 | +| entropy_loss | -5 | +| explained_variance | 0.449 | +| learning_rate | 4.97e-05 | +| loss | -0.0407 | +| n_updates | 37664 | +| policy_gradient_loss | -0.0242 | +| value_loss | 0.000278 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.0539 | +| time/ | | +| fps | 1318 | +| iterations | 581 | +| time_elapsed | 902 | +| total_timesteps | 1189888 | +| train/ | | +| approx_kl | 0.020408016 | +| clip_fraction | 0.434 | +| clip_range | 0.0747 | +| entropy_loss | -5.46 | +| explained_variance | -0.167 | +| learning_rate | 4.97e-05 | +| loss | -0.0365 | +| n_updates | 37668 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.00033 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.0655 | +| time/ | | +| fps | 1318 | +| iterations | 582 | +| time_elapsed | 903 | +| total_timesteps | 1191936 | +| train/ | | +| approx_kl | 0.020290673 | +| clip_fraction | 0.417 | +| clip_range | 0.0747 | +| entropy_loss | -5.37 | +| explained_variance | 0.113 | +| learning_rate | 4.97e-05 | +| loss | -0.036 | +| n_updates | 37672 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000264 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.0633 | +| time/ | | +| fps | 1318 | +| iterations | 583 | +| time_elapsed | 905 | +| total_timesteps | 1193984 | +| train/ | | +| approx_kl | 0.015383848 | +| clip_fraction | 0.387 | +| clip_range | 0.0747 | +| entropy_loss | -5.19 | +| explained_variance | 0.112 | +| learning_rate | 4.97e-05 | +| loss | -0.0289 | +| n_updates | 37676 | +| policy_gradient_loss | -0.0138 | +| value_loss | 0.000791 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.0613 | +| time/ | | +| fps | 1318 | +| iterations | 584 | +| time_elapsed | 906 | +| total_timesteps | 1196032 | +| train/ | | +| approx_kl | 0.019121101 | +| clip_fraction | 0.385 | +| clip_range | 0.0747 | +| entropy_loss | -5.38 | +| explained_variance | 0.0618 | +| learning_rate | 4.97e-05 | +| loss | -0.0334 | +| n_updates | 37680 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000344 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.059 | +| time/ | | +| fps | 1318 | +| iterations | 585 | +| time_elapsed | 908 | +| total_timesteps | 1198080 | +| train/ | | +| approx_kl | 0.021595627 | +| clip_fraction | 0.419 | +| clip_range | 0.0747 | +| entropy_loss | -5.19 | +| explained_variance | 0.393 | +| learning_rate | 4.97e-05 | +| loss | -0.0404 | +| n_updates | 37684 | +| policy_gradient_loss | -0.0239 | +| value_loss | 0.000228 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.0575 | +| time/ | | +| fps | 1318 | +| iterations | 586 | +| time_elapsed | 910 | +| total_timesteps | 1200128 | +| train/ | | +| approx_kl | 0.02280391 | +| clip_fraction | 0.437 | +| clip_range | 0.0747 | +| entropy_loss | -5.24 | +| explained_variance | 0.13 | +| learning_rate | 4.97e-05 | +| loss | -0.0362 | +| n_updates | 37688 | +| policy_gradient_loss | -0.0228 | +| value_loss | 0.000226 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.0599 | +| time/ | | +| fps | 1318 | +| iterations | 587 | +| time_elapsed | 911 | +| total_timesteps | 1202176 | +| train/ | | +| approx_kl | 0.019545907 | +| clip_fraction | 0.41 | +| clip_range | 0.0747 | +| entropy_loss | -5.03 | +| explained_variance | 0.461 | +| learning_rate | 4.97e-05 | +| loss | -0.0352 | +| n_updates | 37692 | +| policy_gradient_loss | -0.0219 | +| value_loss | 0.000226 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.0561 | +| time/ | | +| fps | 1318 | +| iterations | 588 | +| time_elapsed | 913 | +| total_timesteps | 1204224 | +| train/ | | +| approx_kl | 0.024770135 | +| clip_fraction | 0.411 | +| clip_range | 0.0747 | +| entropy_loss | -5.19 | +| explained_variance | 0.26 | +| learning_rate | 4.97e-05 | +| loss | -0.0329 | +| n_updates | 37696 | +| policy_gradient_loss | -0.022 | +| value_loss | 0.000214 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.0555 | +| time/ | | +| fps | 1318 | +| iterations | 589 | +| time_elapsed | 914 | +| total_timesteps | 1206272 | +| train/ | | +| approx_kl | 0.023502626 | +| clip_fraction | 0.436 | +| clip_range | 0.0747 | +| entropy_loss | -5.19 | +| explained_variance | -0.367 | +| learning_rate | 4.97e-05 | +| loss | -0.0297 | +| n_updates | 37700 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000261 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.0555 | +| time/ | | +| fps | 1318 | +| iterations | 590 | +| time_elapsed | 916 | +| total_timesteps | 1208320 | +| train/ | | +| approx_kl | 0.023176681 | +| clip_fraction | 0.452 | +| clip_range | 0.0747 | +| entropy_loss | -5.19 | +| explained_variance | 0.353 | +| learning_rate | 4.97e-05 | +| loss | -0.0347 | +| n_updates | 37704 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000173 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.0555 | +| time/ | | +| fps | 1318 | +| iterations | 591 | +| time_elapsed | 918 | +| total_timesteps | 1210368 | +| train/ | | +| approx_kl | 0.021537002 | +| clip_fraction | 0.428 | +| clip_range | 0.0747 | +| entropy_loss | -5.64 | +| explained_variance | -0.0211 | +| learning_rate | 4.97e-05 | +| loss | -0.034 | +| n_updates | 37708 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000309 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.0542 | +| time/ | | +| fps | 1318 | +| iterations | 592 | +| time_elapsed | 919 | +| total_timesteps | 1212416 | +| train/ | | +| approx_kl | 0.020664891 | +| clip_fraction | 0.405 | +| clip_range | 0.0747 | +| entropy_loss | -5.62 | +| explained_variance | -0.0573 | +| learning_rate | 4.97e-05 | +| loss | -0.0333 | +| n_updates | 37712 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000328 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.0407 | +| time/ | | +| fps | 1318 | +| iterations | 593 | +| time_elapsed | 921 | +| total_timesteps | 1214464 | +| train/ | | +| approx_kl | 0.020635447 | +| clip_fraction | 0.416 | +| clip_range | 0.0747 | +| entropy_loss | -5.49 | +| explained_variance | 0.231 | +| learning_rate | 4.97e-05 | +| loss | -0.0315 | +| n_updates | 37716 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000246 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.0431 | +| time/ | | +| fps | 1318 | +| iterations | 594 | +| time_elapsed | 922 | +| total_timesteps | 1216512 | +| train/ | | +| approx_kl | 0.021642562 | +| clip_fraction | 0.412 | +| clip_range | 0.0747 | +| entropy_loss | -4.51 | +| explained_variance | 0.771 | +| learning_rate | 4.97e-05 | +| loss | -0.0337 | +| n_updates | 37720 | +| policy_gradient_loss | -0.0219 | +| value_loss | 0.000129 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.0418 | +| time/ | | +| fps | 1318 | +| iterations | 595 | +| time_elapsed | 924 | +| total_timesteps | 1218560 | +| train/ | | +| approx_kl | 0.022245374 | +| clip_fraction | 0.418 | +| clip_range | 0.0747 | +| entropy_loss | -5.25 | +| explained_variance | 0.348 | +| learning_rate | 4.97e-05 | +| loss | -0.0364 | +| n_updates | 37724 | +| policy_gradient_loss | -0.0221 | +| value_loss | 0.000181 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.0397 | +| time/ | | +| fps | 1318 | +| iterations | 596 | +| time_elapsed | 925 | +| total_timesteps | 1220608 | +| train/ | | +| approx_kl | 0.027539575 | +| clip_fraction | 0.437 | +| clip_range | 0.0747 | +| entropy_loss | -5.3 | +| explained_variance | 0.237 | +| learning_rate | 4.97e-05 | +| loss | -0.0361 | +| n_updates | 37728 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000202 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.0397 | +| time/ | | +| fps | 1318 | +| iterations | 597 | +| time_elapsed | 927 | +| total_timesteps | 1222656 | +| train/ | | +| approx_kl | 0.023606053 | +| clip_fraction | 0.414 | +| clip_range | 0.0747 | +| entropy_loss | -4.99 | +| explained_variance | 0.453 | +| learning_rate | 4.97e-05 | +| loss | -0.033 | +| n_updates | 37732 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000229 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.0368 | +| time/ | | +| fps | 1318 | +| iterations | 598 | +| time_elapsed | 928 | +| total_timesteps | 1224704 | +| train/ | | +| approx_kl | 0.019279353 | +| clip_fraction | 0.39 | +| clip_range | 0.0747 | +| entropy_loss | -5.45 | +| explained_variance | -0.0843 | +| learning_rate | 4.97e-05 | +| loss | -0.0358 | +| n_updates | 37736 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000306 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.0385 | +| time/ | | +| fps | 1318 | +| iterations | 599 | +| time_elapsed | 930 | +| total_timesteps | 1226752 | +| train/ | | +| approx_kl | 0.021480102 | +| clip_fraction | 0.393 | +| clip_range | 0.0747 | +| entropy_loss | -5.36 | +| explained_variance | 0.312 | +| learning_rate | 4.97e-05 | +| loss | -0.0244 | +| n_updates | 37740 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000274 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.0352 | +| time/ | | +| fps | 1318 | +| iterations | 600 | +| time_elapsed | 931 | +| total_timesteps | 1228800 | +| train/ | | +| approx_kl | 0.021364074 | +| clip_fraction | 0.42 | +| clip_range | 0.0747 | +| entropy_loss | -5.21 | +| explained_variance | 0.448 | +| learning_rate | 4.97e-05 | +| loss | -0.0326 | +| n_updates | 37744 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000304 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.0342 | +| time/ | | +| fps | 1318 | +| iterations | 601 | +| time_elapsed | 933 | +| total_timesteps | 1230848 | +| train/ | | +| approx_kl | 0.020899002 | +| clip_fraction | 0.402 | +| clip_range | 0.0747 | +| entropy_loss | -5.47 | +| explained_variance | 0.176 | +| learning_rate | 4.97e-05 | +| loss | -0.0284 | +| n_updates | 37748 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000228 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.0321 | +| time/ | | +| fps | 1318 | +| iterations | 602 | +| time_elapsed | 934 | +| total_timesteps | 1232896 | +| train/ | | +| approx_kl | 0.020200003 | +| clip_fraction | 0.418 | +| clip_range | 0.0747 | +| entropy_loss | -5.23 | +| explained_variance | 0.177 | +| learning_rate | 4.97e-05 | +| loss | -0.0335 | +| n_updates | 37752 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000357 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.035 | +| time/ | | +| fps | 1318 | +| iterations | 603 | +| time_elapsed | 936 | +| total_timesteps | 1234944 | +| train/ | | +| approx_kl | 0.021743003 | +| clip_fraction | 0.426 | +| clip_range | 0.0747 | +| entropy_loss | -5.19 | +| explained_variance | 0.249 | +| learning_rate | 4.97e-05 | +| loss | -0.0289 | +| n_updates | 37756 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000261 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.035 | +| time/ | | +| fps | 1318 | +| iterations | 604 | +| time_elapsed | 938 | +| total_timesteps | 1236992 | +| train/ | | +| approx_kl | 0.021429706 | +| clip_fraction | 0.401 | +| clip_range | 0.0747 | +| entropy_loss | -5.2 | +| explained_variance | 0.226 | +| learning_rate | 4.97e-05 | +| loss | -0.0362 | +| n_updates | 37760 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.00033 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.0392 | +| time/ | | +| fps | 1318 | +| iterations | 605 | +| time_elapsed | 939 | +| total_timesteps | 1239040 | +| train/ | | +| approx_kl | 0.02015232 | +| clip_fraction | 0.413 | +| clip_range | 0.0747 | +| entropy_loss | -5.52 | +| explained_variance | -0.285 | +| learning_rate | 4.97e-05 | +| loss | -0.0421 | +| n_updates | 37764 | +| policy_gradient_loss | -0.0219 | +| value_loss | 0.0002 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.0358 | +| time/ | | +| fps | 1318 | +| iterations | 606 | +| time_elapsed | 941 | +| total_timesteps | 1241088 | +| train/ | | +| approx_kl | 0.02328679 | +| clip_fraction | 0.413 | +| clip_range | 0.0747 | +| entropy_loss | -5.27 | +| explained_variance | 0.0756 | +| learning_rate | 4.97e-05 | +| loss | -0.0324 | +| n_updates | 37768 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.00036 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.0318 | +| time/ | | +| fps | 1319 | +| iterations | 607 | +| time_elapsed | 942 | +| total_timesteps | 1243136 | +| train/ | | +| approx_kl | 0.01966548 | +| clip_fraction | 0.376 | +| clip_range | 0.0747 | +| entropy_loss | -4.95 | +| explained_variance | 0.187 | +| learning_rate | 4.97e-05 | +| loss | -0.0335 | +| n_updates | 37772 | +| policy_gradient_loss | -0.0151 | +| value_loss | 0.000769 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.0243 | +| time/ | | +| fps | 1319 | +| iterations | 608 | +| time_elapsed | 943 | +| total_timesteps | 1245184 | +| train/ | | +| approx_kl | 0.020026192 | +| clip_fraction | 0.432 | +| clip_range | 0.0747 | +| entropy_loss | -5.31 | +| explained_variance | -0.182 | +| learning_rate | 4.97e-05 | +| loss | -0.0382 | +| n_updates | 37776 | +| policy_gradient_loss | -0.0245 | +| value_loss | 0.00041 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.0244 | +| time/ | | +| fps | 1319 | +| iterations | 609 | +| time_elapsed | 945 | +| total_timesteps | 1247232 | +| train/ | | +| approx_kl | 0.022977503 | +| clip_fraction | 0.428 | +| clip_range | 0.0747 | +| entropy_loss | -5.07 | +| explained_variance | 0.277 | +| learning_rate | 4.97e-05 | +| loss | -0.0421 | +| n_updates | 37780 | +| policy_gradient_loss | -0.0249 | +| value_loss | 0.000283 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.0238 | +| time/ | | +| fps | 1319 | +| iterations | 610 | +| time_elapsed | 947 | +| total_timesteps | 1249280 | +| train/ | | +| approx_kl | 0.021465268 | +| clip_fraction | 0.44 | +| clip_range | 0.0747 | +| entropy_loss | -4.88 | +| explained_variance | 0.388 | +| learning_rate | 4.97e-05 | +| loss | -0.0386 | +| n_updates | 37784 | +| policy_gradient_loss | -0.0245 | +| value_loss | 0.000284 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.023 | +| time/ | | +| fps | 1319 | +| iterations | 611 | +| time_elapsed | 948 | +| total_timesteps | 1251328 | +| train/ | | +| approx_kl | 0.020788815 | +| clip_fraction | 0.424 | +| clip_range | 0.0747 | +| entropy_loss | -5.16 | +| explained_variance | 0.101 | +| learning_rate | 4.97e-05 | +| loss | -0.0327 | +| n_updates | 37788 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.00053 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.0243 | +| time/ | | +| fps | 1319 | +| iterations | 612 | +| time_elapsed | 950 | +| total_timesteps | 1253376 | +| train/ | | +| approx_kl | 0.020811679 | +| clip_fraction | 0.422 | +| clip_range | 0.0747 | +| entropy_loss | -5.12 | +| explained_variance | 0.285 | +| learning_rate | 4.97e-05 | +| loss | -0.0404 | +| n_updates | 37792 | +| policy_gradient_loss | -0.0235 | +| value_loss | 0.000232 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.0214 | +| time/ | | +| fps | 1319 | +| iterations | 613 | +| time_elapsed | 951 | +| total_timesteps | 1255424 | +| train/ | | +| approx_kl | 0.022365648 | +| clip_fraction | 0.418 | +| clip_range | 0.0747 | +| entropy_loss | -5.12 | +| explained_variance | 0.158 | +| learning_rate | 4.97e-05 | +| loss | -0.0359 | +| n_updates | 37796 | +| policy_gradient_loss | -0.0225 | +| value_loss | 0.000204 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.0273 | +| time/ | | +| fps | 1318 | +| iterations | 614 | +| time_elapsed | 953 | +| total_timesteps | 1257472 | +| train/ | | +| approx_kl | 0.027131576 | +| clip_fraction | 0.385 | +| clip_range | 0.0747 | +| entropy_loss | -4.74 | +| explained_variance | 0.436 | +| learning_rate | 4.97e-05 | +| loss | -0.0291 | +| n_updates | 37800 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000328 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.0273 | +| time/ | | +| fps | 1318 | +| iterations | 615 | +| time_elapsed | 954 | +| total_timesteps | 1259520 | +| train/ | | +| approx_kl | 0.018690715 | +| clip_fraction | 0.4 | +| clip_range | 0.0747 | +| entropy_loss | -5.25 | +| explained_variance | -0.00331 | +| learning_rate | 4.97e-05 | +| loss | -0.0311 | +| n_updates | 37804 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000329 | +----------------------------------------- diff --git a/006_rgb_stack_ram_based_reward_time_reward_final_round/trained_models_ryu_vs_bison_no_coef_no_time_reward_9_frame/training_log.txt b/006_rgb_stack_ram_based_reward_time_reward_final_round/trained_models_ryu_vs_bison_no_coef_no_time_reward_9_frame/training_log.txt new file mode 100644 index 0000000..c1cf909 --- /dev/null +++ b/006_rgb_stack_ram_based_reward_time_reward_final_round/trained_models_ryu_vs_bison_no_coef_no_time_reward_9_frame/training_log.txt @@ -0,0 +1,941 @@ +Logging to logs\PPO_6 +----------------------------- +| time/ | | +| fps | 646 | +| iterations | 1 | +| time_elapsed | 3 | +| total_timesteps | 2048 | +----------------------------- +------------------------------------------ +| time/ | | +| fps | 845 | +| iterations | 2 | +| time_elapsed | 4 | +| total_timesteps | 4096 | +| train/ | | +| approx_kl | 0.0006865192 | +| clip_fraction | 0.00366 | +| clip_range | 0.15 | +| entropy_loss | -8.32 | +| explained_variance | -3.63 | +| learning_rate | 0.00025 | +| loss | -0.00368 | +| n_updates | 4 | +| policy_gradient_loss | -0.00183 | +| value_loss | 0.558 | +------------------------------------------ +----------------------------------------- +| time/ | | +| fps | 946 | +| iterations | 3 | +| time_elapsed | 6 | +| total_timesteps | 6144 | +| train/ | | +| approx_kl | 0.002127223 | +| clip_fraction | 0.00745 | +| clip_range | 0.15 | +| entropy_loss | -8.32 | +| explained_variance | -1.02 | +| learning_rate | 0.00025 | +| loss | -0.0243 | +| n_updates | 8 | +| policy_gradient_loss | -0.00382 | +| value_loss | 0.000556 | +----------------------------------------- +------------------------------------------ +| time/ | | +| fps | 1010 | +| iterations | 4 | +| time_elapsed | 8 | +| total_timesteps | 8192 | +| train/ | | +| approx_kl | 0.0044984696 | +| clip_fraction | 0.0646 | +| clip_range | 0.15 | +| entropy_loss | -8.3 | +| explained_variance | -0.638 | +| learning_rate | 0.00025 | +| loss | -0.0175 | +| n_updates | 12 | +| policy_gradient_loss | -0.0108 | +| value_loss | 0.000658 | +------------------------------------------ +----------------------------------------- +| time/ | | +| fps | 1061 | +| iterations | 5 | +| time_elapsed | 9 | +| total_timesteps | 10240 | +| train/ | | +| approx_kl | 0.005734851 | +| clip_fraction | 0.0897 | +| clip_range | 0.15 | +| entropy_loss | -8.3 | +| explained_variance | -1.8 | +| learning_rate | 0.00025 | +| loss | -0.0464 | +| n_updates | 16 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000854 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 641 | +| ep_rew_mean | -1.03 | +| time/ | | +| fps | 1094 | +| iterations | 6 | +| time_elapsed | 11 | +| total_timesteps | 12288 | +| train/ | | +| approx_kl | 0.009480905 | +| clip_fraction | 0.168 | +| clip_range | 0.15 | +| entropy_loss | -8.3 | +| explained_variance | -1.48 | +| learning_rate | 0.00025 | +| loss | -0.0465 | +| n_updates | 20 | +| policy_gradient_loss | -0.0279 | +| value_loss | 0.00133 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 776 | +| ep_rew_mean | -0.902 | +| time/ | | +| fps | 1123 | +| iterations | 7 | +| time_elapsed | 12 | +| total_timesteps | 14336 | +| train/ | | +| approx_kl | 0.0110367015 | +| clip_fraction | 0.218 | +| clip_range | 0.15 | +| entropy_loss | -8.29 | +| explained_variance | -2.01 | +| learning_rate | 0.00025 | +| loss | -0.0616 | +| n_updates | 24 | +| policy_gradient_loss | -0.0323 | +| value_loss | 0.00166 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 859 | +| ep_rew_mean | -0.697 | +| time/ | | +| fps | 1142 | +| iterations | 8 | +| time_elapsed | 14 | +| total_timesteps | 16384 | +| train/ | | +| approx_kl | 0.0151232965 | +| clip_fraction | 0.223 | +| clip_range | 0.15 | +| entropy_loss | -8.28 | +| explained_variance | -0.845 | +| learning_rate | 0.00025 | +| loss | -0.0603 | +| n_updates | 28 | +| policy_gradient_loss | -0.0354 | +| value_loss | 0.00258 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 906 | +| ep_rew_mean | -0.58 | +| time/ | | +| fps | 1158 | +| iterations | 9 | +| time_elapsed | 15 | +| total_timesteps | 18432 | +| train/ | | +| approx_kl | 0.014987826 | +| clip_fraction | 0.219 | +| clip_range | 0.15 | +| entropy_loss | -8.27 | +| explained_variance | -3.09 | +| learning_rate | 0.00025 | +| loss | -0.0666 | +| n_updates | 32 | +| policy_gradient_loss | -0.0375 | +| value_loss | 0.00238 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 906 | +| ep_rew_mean | -0.58 | +| time/ | | +| fps | 1173 | +| iterations | 10 | +| time_elapsed | 17 | +| total_timesteps | 20480 | +| train/ | | +| approx_kl | 0.013858849 | +| clip_fraction | 0.24 | +| clip_range | 0.15 | +| entropy_loss | -8.28 | +| explained_variance | -3.52 | +| learning_rate | 0.00025 | +| loss | -0.0808 | +| n_updates | 36 | +| policy_gradient_loss | -0.0403 | +| value_loss | 0.00161 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 905 | +| ep_rew_mean | -0.592 | +| time/ | | +| fps | 1186 | +| iterations | 11 | +| time_elapsed | 18 | +| total_timesteps | 22528 | +| train/ | | +| approx_kl | 0.015846182 | +| clip_fraction | 0.269 | +| clip_range | 0.15 | +| entropy_loss | -8.26 | +| explained_variance | -2.35 | +| learning_rate | 0.00025 | +| loss | -0.079 | +| n_updates | 40 | +| policy_gradient_loss | -0.0387 | +| value_loss | 0.00168 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 984 | +| ep_rew_mean | -0.53 | +| time/ | | +| fps | 1195 | +| iterations | 12 | +| time_elapsed | 20 | +| total_timesteps | 24576 | +| train/ | | +| approx_kl | 0.01491547 | +| clip_fraction | 0.255 | +| clip_range | 0.15 | +| entropy_loss | -8.25 | +| explained_variance | -1.11 | +| learning_rate | 0.00025 | +| loss | -0.062 | +| n_updates | 44 | +| policy_gradient_loss | -0.0362 | +| value_loss | 0.00198 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.03e+03 | +| ep_rew_mean | -0.512 | +| time/ | | +| fps | 1201 | +| iterations | 13 | +| time_elapsed | 22 | +| total_timesteps | 26624 | +| train/ | | +| approx_kl | 0.016814027 | +| clip_fraction | 0.26 | +| clip_range | 0.15 | +| entropy_loss | -8.25 | +| explained_variance | -2.27 | +| learning_rate | 0.00025 | +| loss | -0.0743 | +| n_updates | 48 | +| policy_gradient_loss | -0.0419 | +| value_loss | 0.00208 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.08e+03 | +| ep_rew_mean | -0.479 | +| time/ | | +| fps | 1207 | +| iterations | 14 | +| time_elapsed | 23 | +| total_timesteps | 28672 | +| train/ | | +| approx_kl | 0.016041683 | +| clip_fraction | 0.288 | +| clip_range | 0.15 | +| entropy_loss | -8.23 | +| explained_variance | -3.28 | +| learning_rate | 0.00025 | +| loss | -0.0766 | +| n_updates | 52 | +| policy_gradient_loss | -0.0389 | +| value_loss | 0.00205 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.07e+03 | +| ep_rew_mean | -0.466 | +| time/ | | +| fps | 1210 | +| iterations | 15 | +| time_elapsed | 25 | +| total_timesteps | 30720 | +| train/ | | +| approx_kl | 0.015445614 | +| clip_fraction | 0.297 | +| clip_range | 0.15 | +| entropy_loss | -8.2 | +| explained_variance | -2.72 | +| learning_rate | 0.00025 | +| loss | -0.0713 | +| n_updates | 56 | +| policy_gradient_loss | -0.038 | +| value_loss | 0.0017 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.11e+03 | +| ep_rew_mean | -0.439 | +| time/ | | +| fps | 1216 | +| iterations | 16 | +| time_elapsed | 26 | +| total_timesteps | 32768 | +| train/ | | +| approx_kl | 0.015225915 | +| clip_fraction | 0.281 | +| clip_range | 0.15 | +| entropy_loss | -8.2 | +| explained_variance | -3.47 | +| learning_rate | 0.00025 | +| loss | -0.0782 | +| n_updates | 60 | +| policy_gradient_loss | -0.039 | +| value_loss | 0.00181 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.11e+03 | +| ep_rew_mean | -0.392 | +| time/ | | +| fps | 1221 | +| iterations | 17 | +| time_elapsed | 28 | +| total_timesteps | 34816 | +| train/ | | +| approx_kl | 0.015854025 | +| clip_fraction | 0.271 | +| clip_range | 0.15 | +| entropy_loss | -8.2 | +| explained_variance | -2.11 | +| learning_rate | 0.00025 | +| loss | -0.0787 | +| n_updates | 64 | +| policy_gradient_loss | -0.0383 | +| value_loss | 0.00166 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.13e+03 | +| ep_rew_mean | -0.393 | +| time/ | | +| fps | 1219 | +| iterations | 18 | +| time_elapsed | 30 | +| total_timesteps | 36864 | +| train/ | | +| approx_kl | 0.019244976 | +| clip_fraction | 0.281 | +| clip_range | 0.15 | +| entropy_loss | -8.23 | +| explained_variance | -2.54 | +| learning_rate | 0.00025 | +| loss | -0.0813 | +| n_updates | 68 | +| policy_gradient_loss | -0.0459 | +| value_loss | 0.00148 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.16e+03 | +| ep_rew_mean | -0.374 | +| time/ | | +| fps | 1221 | +| iterations | 19 | +| time_elapsed | 31 | +| total_timesteps | 38912 | +| train/ | | +| approx_kl | 0.019559633 | +| clip_fraction | 0.282 | +| clip_range | 0.15 | +| entropy_loss | -8.23 | +| explained_variance | -2.18 | +| learning_rate | 0.00025 | +| loss | -0.0707 | +| n_updates | 72 | +| policy_gradient_loss | -0.0458 | +| value_loss | 0.00162 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.15e+03 | +| ep_rew_mean | -0.384 | +| time/ | | +| fps | 1225 | +| iterations | 20 | +| time_elapsed | 33 | +| total_timesteps | 40960 | +| train/ | | +| approx_kl | 0.018351572 | +| clip_fraction | 0.297 | +| clip_range | 0.15 | +| entropy_loss | -8.23 | +| explained_variance | -3.07 | +| learning_rate | 0.00025 | +| loss | -0.0792 | +| n_updates | 76 | +| policy_gradient_loss | -0.0437 | +| value_loss | 0.00149 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | -0.372 | +| time/ | | +| fps | 1228 | +| iterations | 21 | +| time_elapsed | 35 | +| total_timesteps | 43008 | +| train/ | | +| approx_kl | 0.020750236 | +| clip_fraction | 0.297 | +| clip_range | 0.15 | +| entropy_loss | -8.21 | +| explained_variance | -3.2 | +| learning_rate | 0.00025 | +| loss | -0.0878 | +| n_updates | 80 | +| policy_gradient_loss | -0.0498 | +| value_loss | 0.00151 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | -0.372 | +| time/ | | +| fps | 1230 | +| iterations | 22 | +| time_elapsed | 36 | +| total_timesteps | 45056 | +| train/ | | +| approx_kl | 0.021276187 | +| clip_fraction | 0.309 | +| clip_range | 0.15 | +| entropy_loss | -8.2 | +| explained_variance | -1.92 | +| learning_rate | 0.00025 | +| loss | -0.0831 | +| n_updates | 84 | +| policy_gradient_loss | -0.0436 | +| value_loss | 0.00154 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.18e+03 | +| ep_rew_mean | -0.372 | +| time/ | | +| fps | 1235 | +| iterations | 23 | +| time_elapsed | 38 | +| total_timesteps | 47104 | +| train/ | | +| approx_kl | 0.025053155 | +| clip_fraction | 0.331 | +| clip_range | 0.15 | +| entropy_loss | -8.19 | +| explained_variance | -2.63 | +| learning_rate | 0.00025 | +| loss | -0.0852 | +| n_updates | 88 | +| policy_gradient_loss | -0.0462 | +| value_loss | 0.00145 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.19e+03 | +| ep_rew_mean | -0.359 | +| time/ | | +| fps | 1238 | +| iterations | 24 | +| time_elapsed | 39 | +| total_timesteps | 49152 | +| train/ | | +| approx_kl | 0.020340582 | +| clip_fraction | 0.307 | +| clip_range | 0.15 | +| entropy_loss | -8.19 | +| explained_variance | -1.63 | +| learning_rate | 0.00025 | +| loss | -0.0892 | +| n_updates | 92 | +| policy_gradient_loss | -0.0441 | +| value_loss | 0.00132 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | -0.348 | +| time/ | | +| fps | 1239 | +| iterations | 25 | +| time_elapsed | 41 | +| total_timesteps | 51200 | +| train/ | | +| approx_kl | 0.021488946 | +| clip_fraction | 0.356 | +| clip_range | 0.15 | +| entropy_loss | -8.2 | +| explained_variance | -2.75 | +| learning_rate | 0.00025 | +| loss | -0.0726 | +| n_updates | 96 | +| policy_gradient_loss | -0.0409 | +| value_loss | 0.0015 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | -0.305 | +| time/ | | +| fps | 1239 | +| iterations | 26 | +| time_elapsed | 42 | +| total_timesteps | 53248 | +| train/ | | +| approx_kl | 0.02217162 | +| clip_fraction | 0.343 | +| clip_range | 0.15 | +| entropy_loss | -8.21 | +| explained_variance | -4.22 | +| learning_rate | 0.00025 | +| loss | -0.0876 | +| n_updates | 100 | +| policy_gradient_loss | -0.0484 | +| value_loss | 0.00121 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | -0.291 | +| time/ | | +| fps | 1241 | +| iterations | 27 | +| time_elapsed | 44 | +| total_timesteps | 55296 | +| train/ | | +| approx_kl | 0.021241352 | +| clip_fraction | 0.326 | +| clip_range | 0.15 | +| entropy_loss | -8.22 | +| explained_variance | -2.21 | +| learning_rate | 0.00025 | +| loss | -0.0815 | +| n_updates | 104 | +| policy_gradient_loss | -0.0436 | +| value_loss | 0.0011 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | -0.267 | +| time/ | | +| fps | 1242 | +| iterations | 28 | +| time_elapsed | 46 | +| total_timesteps | 57344 | +| train/ | | +| approx_kl | 0.02174874 | +| clip_fraction | 0.315 | +| clip_range | 0.15 | +| entropy_loss | -8.2 | +| explained_variance | -3.67 | +| learning_rate | 0.00025 | +| loss | -0.0848 | +| n_updates | 108 | +| policy_gradient_loss | -0.0471 | +| value_loss | 0.00107 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | -0.267 | +| time/ | | +| fps | 1243 | +| iterations | 29 | +| time_elapsed | 47 | +| total_timesteps | 59392 | +| train/ | | +| approx_kl | 0.021925835 | +| clip_fraction | 0.335 | +| clip_range | 0.15 | +| entropy_loss | -8.19 | +| explained_variance | -1.94 | +| learning_rate | 0.00025 | +| loss | -0.0844 | +| n_updates | 112 | +| policy_gradient_loss | -0.0451 | +| value_loss | 0.00102 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | -0.259 | +| time/ | | +| fps | 1243 | +| iterations | 30 | +| time_elapsed | 49 | +| total_timesteps | 61440 | +| train/ | | +| approx_kl | 0.024559658 | +| clip_fraction | 0.323 | +| clip_range | 0.15 | +| entropy_loss | -8.2 | +| explained_variance | -2.53 | +| learning_rate | 0.00025 | +| loss | -0.0829 | +| n_updates | 116 | +| policy_gradient_loss | -0.0504 | +| value_loss | 0.00119 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | -0.242 | +| time/ | | +| fps | 1244 | +| iterations | 31 | +| time_elapsed | 51 | +| total_timesteps | 63488 | +| train/ | | +| approx_kl | 0.028697252 | +| clip_fraction | 0.348 | +| clip_range | 0.15 | +| entropy_loss | -8.19 | +| explained_variance | -3.28 | +| learning_rate | 0.00025 | +| loss | -0.0895 | +| n_updates | 120 | +| policy_gradient_loss | -0.0496 | +| value_loss | 0.0012 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | -0.246 | +| time/ | | +| fps | 1244 | +| iterations | 32 | +| time_elapsed | 52 | +| total_timesteps | 65536 | +| train/ | | +| approx_kl | 0.022997446 | +| clip_fraction | 0.334 | +| clip_range | 0.15 | +| entropy_loss | -8.2 | +| explained_variance | -2.49 | +| learning_rate | 0.00025 | +| loss | -0.0787 | +| n_updates | 124 | +| policy_gradient_loss | -0.0452 | +| value_loss | 0.00111 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | -0.246 | +| time/ | | +| fps | 1244 | +| iterations | 33 | +| time_elapsed | 54 | +| total_timesteps | 67584 | +| train/ | | +| approx_kl | 0.024152309 | +| clip_fraction | 0.34 | +| clip_range | 0.15 | +| entropy_loss | -8.21 | +| explained_variance | -1.53 | +| learning_rate | 0.00025 | +| loss | -0.0803 | +| n_updates | 128 | +| policy_gradient_loss | -0.0436 | +| value_loss | 0.00116 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | -0.243 | +| time/ | | +| fps | 1244 | +| iterations | 34 | +| time_elapsed | 55 | +| total_timesteps | 69632 | +| train/ | | +| approx_kl | 0.022691075 | +| clip_fraction | 0.325 | +| clip_range | 0.15 | +| entropy_loss | -8.18 | +| explained_variance | -1.67 | +| learning_rate | 0.00025 | +| loss | -0.0822 | +| n_updates | 132 | +| policy_gradient_loss | -0.0478 | +| value_loss | 0.00113 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | -0.239 | +| time/ | | +| fps | 1247 | +| iterations | 35 | +| time_elapsed | 57 | +| total_timesteps | 71680 | +| train/ | | +| approx_kl | 0.023983043 | +| clip_fraction | 0.343 | +| clip_range | 0.15 | +| entropy_loss | -8.18 | +| explained_variance | -2.29 | +| learning_rate | 0.00025 | +| loss | -0.0878 | +| n_updates | 136 | +| policy_gradient_loss | -0.0478 | +| value_loss | 0.00114 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | -0.226 | +| time/ | | +| fps | 1250 | +| iterations | 36 | +| time_elapsed | 58 | +| total_timesteps | 73728 | +| train/ | | +| approx_kl | 0.023928368 | +| clip_fraction | 0.339 | +| clip_range | 0.15 | +| entropy_loss | -8.16 | +| explained_variance | -3.01 | +| learning_rate | 0.00025 | +| loss | -0.0875 | +| n_updates | 140 | +| policy_gradient_loss | -0.0508 | +| value_loss | 0.00123 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | -0.226 | +| time/ | | +| fps | 1251 | +| iterations | 37 | +| time_elapsed | 60 | +| total_timesteps | 75776 | +| train/ | | +| approx_kl | 0.029227499 | +| clip_fraction | 0.362 | +| clip_range | 0.15 | +| entropy_loss | -8.16 | +| explained_variance | -2.77 | +| learning_rate | 0.00025 | +| loss | -0.0825 | +| n_updates | 144 | +| policy_gradient_loss | -0.0478 | +| value_loss | 0.00105 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | -0.226 | +| time/ | | +| fps | 1254 | +| iterations | 38 | +| time_elapsed | 62 | +| total_timesteps | 77824 | +| train/ | | +| approx_kl | 0.02629639 | +| clip_fraction | 0.377 | +| clip_range | 0.15 | +| entropy_loss | -8.17 | +| explained_variance | -1.49 | +| learning_rate | 0.00025 | +| loss | -0.0794 | +| n_updates | 148 | +| policy_gradient_loss | -0.0471 | +| value_loss | 0.00104 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | -0.221 | +| time/ | | +| fps | 1255 | +| iterations | 39 | +| time_elapsed | 63 | +| total_timesteps | 79872 | +| train/ | | +| approx_kl | 0.024264112 | +| clip_fraction | 0.348 | +| clip_range | 0.15 | +| entropy_loss | -8.16 | +| explained_variance | -1.81 | +| learning_rate | 0.00025 | +| loss | -0.0864 | +| n_updates | 152 | +| policy_gradient_loss | -0.0496 | +| value_loss | 0.00101 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | -0.217 | +| time/ | | +| fps | 1257 | +| iterations | 40 | +| time_elapsed | 65 | +| total_timesteps | 81920 | +| train/ | | +| approx_kl | 0.03137113 | +| clip_fraction | 0.385 | +| clip_range | 0.15 | +| entropy_loss | -8.14 | +| explained_variance | -2.58 | +| learning_rate | 0.00025 | +| loss | -0.0907 | +| n_updates | 156 | +| policy_gradient_loss | -0.0514 | +| value_loss | 0.000992 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | -0.217 | +| time/ | | +| fps | 1259 | +| iterations | 41 | +| time_elapsed | 66 | +| total_timesteps | 83968 | +| train/ | | +| approx_kl | 0.026189182 | +| clip_fraction | 0.37 | +| clip_range | 0.15 | +| entropy_loss | -8.13 | +| explained_variance | -1.83 | +| learning_rate | 0.00025 | +| loss | -0.0842 | +| n_updates | 160 | +| policy_gradient_loss | -0.0472 | +| value_loss | 0.00098 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | -0.21 | +| time/ | | +| fps | 1261 | +| iterations | 42 | +| time_elapsed | 68 | +| total_timesteps | 86016 | +| train/ | | +| approx_kl | 0.0249079 | +| clip_fraction | 0.335 | +| clip_range | 0.15 | +| entropy_loss | -8.14 | +| explained_variance | -1.64 | +| learning_rate | 0.00025 | +| loss | -0.0877 | +| n_updates | 164 | +| policy_gradient_loss | -0.0472 | +| value_loss | 0.000896 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | -0.21 | +| time/ | | +| fps | 1263 | +| iterations | 43 | +| time_elapsed | 69 | +| total_timesteps | 88064 | +| train/ | | +| approx_kl | 0.025553392 | +| clip_fraction | 0.346 | +| clip_range | 0.15 | +| entropy_loss | -8.14 | +| explained_variance | -1.44 | +| learning_rate | 0.00025 | +| loss | -0.0829 | +| n_updates | 168 | +| policy_gradient_loss | -0.0451 | +| value_loss | 0.000811 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | -0.198 | +| time/ | | +| fps | 1265 | +| iterations | 44 | +| time_elapsed | 71 | +| total_timesteps | 90112 | +| train/ | | +| approx_kl | 0.027851868 | +| clip_fraction | 0.336 | +| clip_range | 0.15 | +| entropy_loss | -8.11 | +| explained_variance | -3.01 | +| learning_rate | 0.00025 | +| loss | -0.0836 | +| n_updates | 172 | +| policy_gradient_loss | -0.0495 | +| value_loss | 0.000813 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | -0.2 | +| time/ | | +| fps | 1266 | +| iterations | 45 | +| time_elapsed | 72 | +| total_timesteps | 92160 | +| train/ | | +| approx_kl | 0.03102021 | +| clip_fraction | 0.343 | +| clip_range | 0.15 | +| entropy_loss | -8.11 | +| explained_variance | -2.36 | +| learning_rate | 0.00025 | +| loss | -0.0771 | +| n_updates | 176 | +| policy_gradient_loss | -0.0518 | +| value_loss | 0.000777 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | -0.206 | +| time/ | | +| fps | 1266 | +| iterations | 46 | +| time_elapsed | 74 | +| total_timesteps | 94208 | +| train/ | | +| approx_kl | 0.032389328 | +| clip_fraction | 0.395 | +| clip_range | 0.15 | +| entropy_loss | -8.11 | +| explained_variance | -2.11 | +| learning_rate | 0.00025 | +| loss | -0.0933 | +| n_updates | 180 | +| policy_gradient_loss | -0.0508 | +| value_loss | 0.00094 | +----------------------------------------- diff --git a/006_rgb_stack_ram_based_reward_time_reward_final_round/trained_models_ryu_vs_bison_no_coef_no_time_reward_more_frame/training_log.txt b/006_rgb_stack_ram_based_reward_time_reward_final_round/trained_models_ryu_vs_bison_no_coef_no_time_reward_more_frame/training_log.txt new file mode 100644 index 0000000..bbe73f8 --- /dev/null +++ b/006_rgb_stack_ram_based_reward_time_reward_final_round/trained_models_ryu_vs_bison_no_coef_no_time_reward_more_frame/training_log.txt @@ -0,0 +1,22946 @@ +Logging to logs\PPO_5 +----------------------------- +| time/ | | +| fps | 707 | +| iterations | 1 | +| time_elapsed | 2 | +| total_timesteps | 2048 | +----------------------------- +----------------------------------------- +| time/ | | +| fps | 889 | +| iterations | 2 | +| time_elapsed | 4 | +| total_timesteps | 4096 | +| train/ | | +| approx_kl | 0.008694793 | +| clip_fraction | 0.273 | +| clip_range | 0.075 | +| entropy_loss | -4.25 | +| explained_variance | 0.575 | +| learning_rate | 5e-05 | +| loss | -0.018 | +| n_updates | 35352 | +| policy_gradient_loss | -0.00863 | +| value_loss | 0.00021 | +----------------------------------------- +----------------------------------------- +| time/ | | +| fps | 985 | +| iterations | 3 | +| time_elapsed | 6 | +| total_timesteps | 6144 | +| train/ | | +| approx_kl | 0.013626788 | +| clip_fraction | 0.332 | +| clip_range | 0.075 | +| entropy_loss | -7.33 | +| explained_variance | -0.124 | +| learning_rate | 5e-05 | +| loss | -0.0272 | +| n_updates | 35356 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000269 | +----------------------------------------- +----------------------------------------- +| time/ | | +| fps | 1052 | +| iterations | 4 | +| time_elapsed | 7 | +| total_timesteps | 8192 | +| train/ | | +| approx_kl | 0.013354454 | +| clip_fraction | 0.303 | +| clip_range | 0.075 | +| entropy_loss | -7.44 | +| explained_variance | -0.127 | +| learning_rate | 5e-05 | +| loss | -0.0309 | +| n_updates | 35360 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000304 | +----------------------------------------- +------------------------------------------ +| time/ | | +| fps | 1097 | +| iterations | 5 | +| time_elapsed | 9 | +| total_timesteps | 10240 | +| train/ | | +| approx_kl | 0.0133355055 | +| clip_fraction | 0.323 | +| clip_range | 0.075 | +| entropy_loss | -7.47 | +| explained_variance | -0.0456 | +| learning_rate | 5e-05 | +| loss | -0.0316 | +| n_updates | 35364 | +| policy_gradient_loss | -0.0222 | +| value_loss | 0.000401 | +------------------------------------------ +----------------------------------------- +| time/ | | +| fps | 1130 | +| iterations | 6 | +| time_elapsed | 10 | +| total_timesteps | 12288 | +| train/ | | +| approx_kl | 0.013089652 | +| clip_fraction | 0.316 | +| clip_range | 0.075 | +| entropy_loss | -7.44 | +| explained_variance | -0.0868 | +| learning_rate | 5e-05 | +| loss | -0.0338 | +| n_updates | 35368 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000377 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 798 | +| ep_rew_mean | 0.338 | +| time/ | | +| fps | 1150 | +| iterations | 7 | +| time_elapsed | 12 | +| total_timesteps | 14336 | +| train/ | | +| approx_kl | 0.012160039 | +| clip_fraction | 0.319 | +| clip_range | 0.075 | +| entropy_loss | -7.5 | +| explained_variance | -0.102 | +| learning_rate | 5e-05 | +| loss | -0.0346 | +| n_updates | 35372 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000274 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 859 | +| ep_rew_mean | 0.18 | +| time/ | | +| fps | 1168 | +| iterations | 8 | +| time_elapsed | 14 | +| total_timesteps | 16384 | +| train/ | | +| approx_kl | 0.0100000305 | +| clip_fraction | 0.264 | +| clip_range | 0.075 | +| entropy_loss | -7.18 | +| explained_variance | -0.038 | +| learning_rate | 5e-05 | +| loss | -0.0219 | +| n_updates | 35376 | +| policy_gradient_loss | -0.0141 | +| value_loss | 0.000879 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 957 | +| ep_rew_mean | 0.173 | +| time/ | | +| fps | 1188 | +| iterations | 9 | +| time_elapsed | 15 | +| total_timesteps | 18432 | +| train/ | | +| approx_kl | 0.010439659 | +| clip_fraction | 0.314 | +| clip_range | 0.075 | +| entropy_loss | -7.34 | +| explained_variance | -0.131 | +| learning_rate | 5e-05 | +| loss | -0.0345 | +| n_updates | 35380 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000267 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.05e+03 | +| ep_rew_mean | 0.0593 | +| time/ | | +| fps | 1202 | +| iterations | 10 | +| time_elapsed | 17 | +| total_timesteps | 20480 | +| train/ | | +| approx_kl | 0.012288323 | +| clip_fraction | 0.315 | +| clip_range | 0.075 | +| entropy_loss | -6.91 | +| explained_variance | 0.169 | +| learning_rate | 5e-05 | +| loss | -0.0294 | +| n_updates | 35384 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000268 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.08e+03 | +| ep_rew_mean | 0.0778 | +| time/ | | +| fps | 1205 | +| iterations | 11 | +| time_elapsed | 18 | +| total_timesteps | 22528 | +| train/ | | +| approx_kl | 0.0125561105 | +| clip_fraction | 0.322 | +| clip_range | 0.075 | +| entropy_loss | -6.94 | +| explained_variance | 0.174 | +| learning_rate | 5e-05 | +| loss | -0.0348 | +| n_updates | 35388 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000188 | +------------------------------------------ +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.12e+03 | +| ep_rew_mean | 0.0468 | +| time/ | | +| fps | 1211 | +| iterations | 12 | +| time_elapsed | 20 | +| total_timesteps | 24576 | +| train/ | | +| approx_kl | 0.0125947045 | +| clip_fraction | 0.318 | +| clip_range | 0.075 | +| entropy_loss | -7.16 | +| explained_variance | 0.00284 | +| learning_rate | 5e-05 | +| loss | -0.0316 | +| n_updates | 35392 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000268 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.2e+03 | +| ep_rew_mean | 0.121 | +| time/ | | +| fps | 1217 | +| iterations | 13 | +| time_elapsed | 21 | +| total_timesteps | 26624 | +| train/ | | +| approx_kl | 0.011201898 | +| clip_fraction | 0.297 | +| clip_range | 0.075 | +| entropy_loss | -7.44 | +| explained_variance | -0.0576 | +| learning_rate | 5e-05 | +| loss | -0.0341 | +| n_updates | 35396 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000388 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.114 | +| time/ | | +| fps | 1224 | +| iterations | 14 | +| time_elapsed | 23 | +| total_timesteps | 28672 | +| train/ | | +| approx_kl | 0.012564582 | +| clip_fraction | 0.321 | +| clip_range | 0.075 | +| entropy_loss | -6.71 | +| explained_variance | 0.0057 | +| learning_rate | 5e-05 | +| loss | -0.0318 | +| n_updates | 35400 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000435 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.114 | +| time/ | | +| fps | 1232 | +| iterations | 15 | +| time_elapsed | 24 | +| total_timesteps | 30720 | +| train/ | | +| approx_kl | 0.012026714 | +| clip_fraction | 0.311 | +| clip_range | 0.075 | +| entropy_loss | -7.14 | +| explained_variance | -0.139 | +| learning_rate | 5e-05 | +| loss | -0.0383 | +| n_updates | 35404 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.00027 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.112 | +| time/ | | +| fps | 1240 | +| iterations | 16 | +| time_elapsed | 26 | +| total_timesteps | 32768 | +| train/ | | +| approx_kl | 0.0115305865 | +| clip_fraction | 0.325 | +| clip_range | 0.075 | +| entropy_loss | -7.4 | +| explained_variance | -0.00644 | +| learning_rate | 5e-05 | +| loss | -0.0359 | +| n_updates | 35408 | +| policy_gradient_loss | -0.022 | +| value_loss | 0.000241 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.112 | +| time/ | | +| fps | 1243 | +| iterations | 17 | +| time_elapsed | 27 | +| total_timesteps | 34816 | +| train/ | | +| approx_kl | 0.010460189 | +| clip_fraction | 0.314 | +| clip_range | 0.075 | +| entropy_loss | -7.1 | +| explained_variance | 0.0972 | +| learning_rate | 5e-05 | +| loss | -0.0352 | +| n_updates | 35412 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000251 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.138 | +| time/ | | +| fps | 1249 | +| iterations | 18 | +| time_elapsed | 29 | +| total_timesteps | 36864 | +| train/ | | +| approx_kl | 0.012665698 | +| clip_fraction | 0.325 | +| clip_range | 0.075 | +| entropy_loss | -7.2 | +| explained_variance | 0.12 | +| learning_rate | 5e-05 | +| loss | -0.0334 | +| n_updates | 35416 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000283 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.139 | +| time/ | | +| fps | 1256 | +| iterations | 19 | +| time_elapsed | 30 | +| total_timesteps | 38912 | +| train/ | | +| approx_kl | 0.012311344 | +| clip_fraction | 0.323 | +| clip_range | 0.075 | +| entropy_loss | -7.08 | +| explained_variance | 0.244 | +| learning_rate | 5e-05 | +| loss | -0.0357 | +| n_updates | 35420 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000327 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.129 | +| time/ | | +| fps | 1260 | +| iterations | 20 | +| time_elapsed | 32 | +| total_timesteps | 40960 | +| train/ | | +| approx_kl | 0.012246884 | +| clip_fraction | 0.314 | +| clip_range | 0.075 | +| entropy_loss | -7.23 | +| explained_variance | -0.063 | +| learning_rate | 5e-05 | +| loss | -0.0329 | +| n_updates | 35424 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000328 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.21e+03 | +| ep_rew_mean | 0.155 | +| time/ | | +| fps | 1263 | +| iterations | 21 | +| time_elapsed | 34 | +| total_timesteps | 43008 | +| train/ | | +| approx_kl | 0.011518549 | +| clip_fraction | 0.323 | +| clip_range | 0.075 | +| entropy_loss | -7.23 | +| explained_variance | -0.0106 | +| learning_rate | 5e-05 | +| loss | -0.0333 | +| n_updates | 35428 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000266 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.12 | +| time/ | | +| fps | 1265 | +| iterations | 22 | +| time_elapsed | 35 | +| total_timesteps | 45056 | +| train/ | | +| approx_kl | 0.012419267 | +| clip_fraction | 0.308 | +| clip_range | 0.075 | +| entropy_loss | -7.06 | +| explained_variance | -0.0965 | +| learning_rate | 5e-05 | +| loss | -0.0314 | +| n_updates | 35432 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000382 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.143 | +| time/ | | +| fps | 1267 | +| iterations | 23 | +| time_elapsed | 37 | +| total_timesteps | 47104 | +| train/ | | +| approx_kl | 0.013896364 | +| clip_fraction | 0.338 | +| clip_range | 0.075 | +| entropy_loss | -6.74 | +| explained_variance | 0.104 | +| learning_rate | 5e-05 | +| loss | -0.037 | +| n_updates | 35436 | +| policy_gradient_loss | -0.0245 | +| value_loss | 0.000172 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.22e+03 | +| ep_rew_mean | 0.143 | +| time/ | | +| fps | 1272 | +| iterations | 24 | +| time_elapsed | 38 | +| total_timesteps | 49152 | +| train/ | | +| approx_kl | 0.010656891 | +| clip_fraction | 0.283 | +| clip_range | 0.075 | +| entropy_loss | -7.02 | +| explained_variance | -0.0409 | +| learning_rate | 5e-05 | +| loss | -0.0351 | +| n_updates | 35440 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.00089 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.126 | +| time/ | | +| fps | 1273 | +| iterations | 25 | +| time_elapsed | 40 | +| total_timesteps | 51200 | +| train/ | | +| approx_kl | 0.012514224 | +| clip_fraction | 0.318 | +| clip_range | 0.075 | +| entropy_loss | -7.42 | +| explained_variance | -0.0981 | +| learning_rate | 5e-05 | +| loss | -0.0372 | +| n_updates | 35444 | +| policy_gradient_loss | -0.0241 | +| value_loss | 0.000316 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.124 | +| time/ | | +| fps | 1275 | +| iterations | 26 | +| time_elapsed | 41 | +| total_timesteps | 53248 | +| train/ | | +| approx_kl | 0.012991972 | +| clip_fraction | 0.337 | +| clip_range | 0.075 | +| entropy_loss | -6.85 | +| explained_variance | 0.0415 | +| learning_rate | 5e-05 | +| loss | -0.0426 | +| n_updates | 35448 | +| policy_gradient_loss | -0.024 | +| value_loss | 0.000238 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.124 | +| time/ | | +| fps | 1276 | +| iterations | 27 | +| time_elapsed | 43 | +| total_timesteps | 55296 | +| train/ | | +| approx_kl | 0.011989423 | +| clip_fraction | 0.335 | +| clip_range | 0.075 | +| entropy_loss | -7.01 | +| explained_variance | -0.0832 | +| learning_rate | 5e-05 | +| loss | -0.0389 | +| n_updates | 35452 | +| policy_gradient_loss | -0.0225 | +| value_loss | 0.00017 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.104 | +| time/ | | +| fps | 1275 | +| iterations | 28 | +| time_elapsed | 44 | +| total_timesteps | 57344 | +| train/ | | +| approx_kl | 0.011613016 | +| clip_fraction | 0.336 | +| clip_range | 0.075 | +| entropy_loss | -7.43 | +| explained_variance | -0.0905 | +| learning_rate | 5e-05 | +| loss | -0.0394 | +| n_updates | 35456 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000198 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.104 | +| time/ | | +| fps | 1276 | +| iterations | 29 | +| time_elapsed | 46 | +| total_timesteps | 59392 | +| train/ | | +| approx_kl | 0.0121857785 | +| clip_fraction | 0.314 | +| clip_range | 0.075 | +| entropy_loss | -7.16 | +| explained_variance | 0.00163 | +| learning_rate | 5e-05 | +| loss | -0.0377 | +| n_updates | 35460 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000412 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.0831 | +| time/ | | +| fps | 1278 | +| iterations | 30 | +| time_elapsed | 48 | +| total_timesteps | 61440 | +| train/ | | +| approx_kl | 0.012641539 | +| clip_fraction | 0.32 | +| clip_range | 0.075 | +| entropy_loss | -7.36 | +| explained_variance | -0.0537 | +| learning_rate | 5e-05 | +| loss | -0.0323 | +| n_updates | 35464 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.00029 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.0831 | +| time/ | | +| fps | 1279 | +| iterations | 31 | +| time_elapsed | 49 | +| total_timesteps | 63488 | +| train/ | | +| approx_kl | 0.014840981 | +| clip_fraction | 0.33 | +| clip_range | 0.075 | +| entropy_loss | -6.68 | +| explained_variance | 0.212 | +| learning_rate | 5e-05 | +| loss | -0.0313 | +| n_updates | 35468 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000233 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.0933 | +| time/ | | +| fps | 1280 | +| iterations | 32 | +| time_elapsed | 51 | +| total_timesteps | 65536 | +| train/ | | +| approx_kl | 0.013017475 | +| clip_fraction | 0.318 | +| clip_range | 0.075 | +| entropy_loss | -7.24 | +| explained_variance | -0.0323 | +| learning_rate | 5e-05 | +| loss | -0.0334 | +| n_updates | 35472 | +| policy_gradient_loss | -0.0227 | +| value_loss | 0.000208 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.0933 | +| time/ | | +| fps | 1281 | +| iterations | 33 | +| time_elapsed | 52 | +| total_timesteps | 67584 | +| train/ | | +| approx_kl | 0.011302375 | +| clip_fraction | 0.272 | +| clip_range | 0.075 | +| entropy_loss | -7.01 | +| explained_variance | 0.121 | +| learning_rate | 5e-05 | +| loss | -0.0368 | +| n_updates | 35476 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000422 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.0907 | +| time/ | | +| fps | 1281 | +| iterations | 34 | +| time_elapsed | 54 | +| total_timesteps | 69632 | +| train/ | | +| approx_kl | 0.0120138 | +| clip_fraction | 0.315 | +| clip_range | 0.075 | +| entropy_loss | -7.29 | +| explained_variance | -0.0829 | +| learning_rate | 5e-05 | +| loss | -0.0339 | +| n_updates | 35480 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000296 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.0907 | +| time/ | | +| fps | 1282 | +| iterations | 35 | +| time_elapsed | 55 | +| total_timesteps | 71680 | +| train/ | | +| approx_kl | 0.011765625 | +| clip_fraction | 0.332 | +| clip_range | 0.075 | +| entropy_loss | -7.03 | +| explained_variance | 0.158 | +| learning_rate | 5e-05 | +| loss | -0.0349 | +| n_updates | 35484 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000259 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.0987 | +| time/ | | +| fps | 1283 | +| iterations | 36 | +| time_elapsed | 57 | +| total_timesteps | 73728 | +| train/ | | +| approx_kl | 0.010585377 | +| clip_fraction | 0.317 | +| clip_range | 0.075 | +| entropy_loss | -7.29 | +| explained_variance | -0.0984 | +| learning_rate | 5e-05 | +| loss | -0.0326 | +| n_updates | 35488 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000257 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.104 | +| time/ | | +| fps | 1283 | +| iterations | 37 | +| time_elapsed | 59 | +| total_timesteps | 75776 | +| train/ | | +| approx_kl | 0.0125219915 | +| clip_fraction | 0.322 | +| clip_range | 0.075 | +| entropy_loss | -7.01 | +| explained_variance | 0.094 | +| learning_rate | 5e-05 | +| loss | -0.0321 | +| n_updates | 35492 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.00021 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.111 | +| time/ | | +| fps | 1284 | +| iterations | 38 | +| time_elapsed | 60 | +| total_timesteps | 77824 | +| train/ | | +| approx_kl | 0.013382643 | +| clip_fraction | 0.318 | +| clip_range | 0.075 | +| entropy_loss | -6.92 | +| explained_variance | 0.114 | +| learning_rate | 5e-05 | +| loss | -0.0302 | +| n_updates | 35496 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000359 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.109 | +| time/ | | +| fps | 1283 | +| iterations | 39 | +| time_elapsed | 62 | +| total_timesteps | 79872 | +| train/ | | +| approx_kl | 0.013015201 | +| clip_fraction | 0.318 | +| clip_range | 0.075 | +| entropy_loss | -6.89 | +| explained_variance | 0.26 | +| learning_rate | 5e-05 | +| loss | -0.0339 | +| n_updates | 35500 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000301 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.104 | +| time/ | | +| fps | 1284 | +| iterations | 40 | +| time_elapsed | 63 | +| total_timesteps | 81920 | +| train/ | | +| approx_kl | 0.014263535 | +| clip_fraction | 0.332 | +| clip_range | 0.075 | +| entropy_loss | -7.08 | +| explained_variance | 0.126 | +| learning_rate | 5e-05 | +| loss | -0.0353 | +| n_updates | 35504 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000209 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.104 | +| time/ | | +| fps | 1284 | +| iterations | 41 | +| time_elapsed | 65 | +| total_timesteps | 83968 | +| train/ | | +| approx_kl | 0.012261842 | +| clip_fraction | 0.306 | +| clip_range | 0.075 | +| entropy_loss | -7.11 | +| explained_variance | 0.0339 | +| learning_rate | 5e-05 | +| loss | -0.0344 | +| n_updates | 35508 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000349 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.119 | +| time/ | | +| fps | 1286 | +| iterations | 42 | +| time_elapsed | 66 | +| total_timesteps | 86016 | +| train/ | | +| approx_kl | 0.010759295 | +| clip_fraction | 0.314 | +| clip_range | 0.075 | +| entropy_loss | -7.18 | +| explained_variance | -0.102 | +| learning_rate | 5e-05 | +| loss | -0.0345 | +| n_updates | 35512 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000267 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.115 | +| time/ | | +| fps | 1287 | +| iterations | 43 | +| time_elapsed | 68 | +| total_timesteps | 88064 | +| train/ | | +| approx_kl | 0.012538152 | +| clip_fraction | 0.319 | +| clip_range | 0.075 | +| entropy_loss | -7.03 | +| explained_variance | 0.0522 | +| learning_rate | 5e-05 | +| loss | -0.0312 | +| n_updates | 35516 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000335 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.117 | +| time/ | | +| fps | 1288 | +| iterations | 44 | +| time_elapsed | 69 | +| total_timesteps | 90112 | +| train/ | | +| approx_kl | 0.01129625 | +| clip_fraction | 0.314 | +| clip_range | 0.075 | +| entropy_loss | -7.07 | +| explained_variance | 0.123 | +| learning_rate | 5e-05 | +| loss | -0.0371 | +| n_updates | 35520 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000226 | +---------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.115 | +| time/ | | +| fps | 1289 | +| iterations | 45 | +| time_elapsed | 71 | +| total_timesteps | 92160 | +| train/ | | +| approx_kl | 0.0113363005 | +| clip_fraction | 0.322 | +| clip_range | 0.075 | +| entropy_loss | -6.8 | +| explained_variance | 0.178 | +| learning_rate | 5e-05 | +| loss | -0.0275 | +| n_updates | 35524 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000362 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.115 | +| time/ | | +| fps | 1290 | +| iterations | 46 | +| time_elapsed | 72 | +| total_timesteps | 94208 | +| train/ | | +| approx_kl | 0.010889353 | +| clip_fraction | 0.306 | +| clip_range | 0.075 | +| entropy_loss | -6.84 | +| explained_variance | 0.0711 | +| learning_rate | 5e-05 | +| loss | -0.033 | +| n_updates | 35528 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.00025 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.108 | +| time/ | | +| fps | 1292 | +| iterations | 47 | +| time_elapsed | 74 | +| total_timesteps | 96256 | +| train/ | | +| approx_kl | 0.012590229 | +| clip_fraction | 0.342 | +| clip_range | 0.075 | +| entropy_loss | -7.22 | +| explained_variance | 0.151 | +| learning_rate | 5e-05 | +| loss | -0.0368 | +| n_updates | 35532 | +| policy_gradient_loss | -0.0221 | +| value_loss | 0.000225 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.116 | +| time/ | | +| fps | 1293 | +| iterations | 48 | +| time_elapsed | 76 | +| total_timesteps | 98304 | +| train/ | | +| approx_kl | 0.013439433 | +| clip_fraction | 0.356 | +| clip_range | 0.075 | +| entropy_loss | -7.18 | +| explained_variance | -0.0348 | +| learning_rate | 5e-05 | +| loss | -0.0366 | +| n_updates | 35536 | +| policy_gradient_loss | -0.0219 | +| value_loss | 0.000216 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.113 | +| time/ | | +| fps | 1292 | +| iterations | 49 | +| time_elapsed | 77 | +| total_timesteps | 100352 | +| train/ | | +| approx_kl | 0.014364228 | +| clip_fraction | 0.322 | +| clip_range | 0.075 | +| entropy_loss | -7.19 | +| explained_variance | 0.109 | +| learning_rate | 5e-05 | +| loss | -0.0358 | +| n_updates | 35540 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000407 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.113 | +| time/ | | +| fps | 1292 | +| iterations | 50 | +| time_elapsed | 79 | +| total_timesteps | 102400 | +| train/ | | +| approx_kl | 0.012940342 | +| clip_fraction | 0.313 | +| clip_range | 0.075 | +| entropy_loss | -7.18 | +| explained_variance | -0.00267 | +| learning_rate | 5e-05 | +| loss | -0.029 | +| n_updates | 35544 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000259 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.109 | +| time/ | | +| fps | 1293 | +| iterations | 51 | +| time_elapsed | 80 | +| total_timesteps | 104448 | +| train/ | | +| approx_kl | 0.0131290965 | +| clip_fraction | 0.34 | +| clip_range | 0.075 | +| entropy_loss | -7.37 | +| explained_variance | -0.0458 | +| learning_rate | 5e-05 | +| loss | -0.0338 | +| n_updates | 35548 | +| policy_gradient_loss | -0.022 | +| value_loss | 0.000217 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.114 | +| time/ | | +| fps | 1293 | +| iterations | 52 | +| time_elapsed | 82 | +| total_timesteps | 106496 | +| train/ | | +| approx_kl | 0.014628694 | +| clip_fraction | 0.34 | +| clip_range | 0.075 | +| entropy_loss | -7.33 | +| explained_variance | -0.102 | +| learning_rate | 5e-05 | +| loss | -0.0383 | +| n_updates | 35552 | +| policy_gradient_loss | -0.023 | +| value_loss | 0.000165 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.116 | +| time/ | | +| fps | 1292 | +| iterations | 53 | +| time_elapsed | 83 | +| total_timesteps | 108544 | +| train/ | | +| approx_kl | 0.014150575 | +| clip_fraction | 0.342 | +| clip_range | 0.075 | +| entropy_loss | -7.11 | +| explained_variance | 0.0334 | +| learning_rate | 5e-05 | +| loss | -0.028 | +| n_updates | 35556 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000269 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.111 | +| time/ | | +| fps | 1291 | +| iterations | 54 | +| time_elapsed | 85 | +| total_timesteps | 110592 | +| train/ | | +| approx_kl | 0.012334612 | +| clip_fraction | 0.326 | +| clip_range | 0.075 | +| entropy_loss | -6.94 | +| explained_variance | 0.216 | +| learning_rate | 5e-05 | +| loss | -0.0325 | +| n_updates | 35560 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000172 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.111 | +| time/ | | +| fps | 1291 | +| iterations | 55 | +| time_elapsed | 87 | +| total_timesteps | 112640 | +| train/ | | +| approx_kl | 0.012865373 | +| clip_fraction | 0.324 | +| clip_range | 0.075 | +| entropy_loss | -6.61 | +| explained_variance | 0.311 | +| learning_rate | 5e-05 | +| loss | -0.0341 | +| n_updates | 35564 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000256 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0983 | +| time/ | | +| fps | 1292 | +| iterations | 56 | +| time_elapsed | 88 | +| total_timesteps | 114688 | +| train/ | | +| approx_kl | 0.014295688 | +| clip_fraction | 0.33 | +| clip_range | 0.075 | +| entropy_loss | -7.18 | +| explained_variance | -0.0406 | +| learning_rate | 5e-05 | +| loss | -0.0372 | +| n_updates | 35568 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000269 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0959 | +| time/ | | +| fps | 1291 | +| iterations | 57 | +| time_elapsed | 90 | +| total_timesteps | 116736 | +| train/ | | +| approx_kl | 0.011549253 | +| clip_fraction | 0.287 | +| clip_range | 0.075 | +| entropy_loss | -7.1 | +| explained_variance | 0.116 | +| learning_rate | 5e-05 | +| loss | -0.031 | +| n_updates | 35572 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000822 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0943 | +| time/ | | +| fps | 1291 | +| iterations | 58 | +| time_elapsed | 91 | +| total_timesteps | 118784 | +| train/ | | +| approx_kl | 0.012098371 | +| clip_fraction | 0.33 | +| clip_range | 0.075 | +| entropy_loss | -7 | +| explained_variance | 0.174 | +| learning_rate | 5e-05 | +| loss | -0.0341 | +| n_updates | 35576 | +| policy_gradient_loss | -0.0225 | +| value_loss | 0.000285 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0861 | +| time/ | | +| fps | 1291 | +| iterations | 59 | +| time_elapsed | 93 | +| total_timesteps | 120832 | +| train/ | | +| approx_kl | 0.010296847 | +| clip_fraction | 0.32 | +| clip_range | 0.075 | +| entropy_loss | -7.34 | +| explained_variance | -0.323 | +| learning_rate | 5e-05 | +| loss | -0.0361 | +| n_updates | 35580 | +| policy_gradient_loss | -0.022 | +| value_loss | 0.000346 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0729 | +| time/ | | +| fps | 1290 | +| iterations | 60 | +| time_elapsed | 95 | +| total_timesteps | 122880 | +| train/ | | +| approx_kl | 0.012682868 | +| clip_fraction | 0.32 | +| clip_range | 0.075 | +| entropy_loss | -6.79 | +| explained_variance | 0.385 | +| learning_rate | 5e-05 | +| loss | -0.0358 | +| n_updates | 35584 | +| policy_gradient_loss | -0.022 | +| value_loss | 0.000314 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0723 | +| time/ | | +| fps | 1290 | +| iterations | 61 | +| time_elapsed | 96 | +| total_timesteps | 124928 | +| train/ | | +| approx_kl | 0.01254874 | +| clip_fraction | 0.305 | +| clip_range | 0.075 | +| entropy_loss | -6.98 | +| explained_variance | 0.206 | +| learning_rate | 5e-05 | +| loss | -0.0275 | +| n_updates | 35588 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000313 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0676 | +| time/ | | +| fps | 1290 | +| iterations | 62 | +| time_elapsed | 98 | +| total_timesteps | 126976 | +| train/ | | +| approx_kl | 0.013301296 | +| clip_fraction | 0.35 | +| clip_range | 0.075 | +| entropy_loss | -6.97 | +| explained_variance | 0.265 | +| learning_rate | 5e-05 | +| loss | -0.037 | +| n_updates | 35592 | +| policy_gradient_loss | -0.0229 | +| value_loss | 0.000225 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0676 | +| time/ | | +| fps | 1289 | +| iterations | 63 | +| time_elapsed | 100 | +| total_timesteps | 129024 | +| train/ | | +| approx_kl | 0.013633428 | +| clip_fraction | 0.327 | +| clip_range | 0.075 | +| entropy_loss | -6.97 | +| explained_variance | 0.215 | +| learning_rate | 5e-05 | +| loss | -0.0329 | +| n_updates | 35596 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000276 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0641 | +| time/ | | +| fps | 1289 | +| iterations | 64 | +| time_elapsed | 101 | +| total_timesteps | 131072 | +| train/ | | +| approx_kl | 0.013543981 | +| clip_fraction | 0.345 | +| clip_range | 0.075 | +| entropy_loss | -7.27 | +| explained_variance | -0.111 | +| learning_rate | 5e-05 | +| loss | -0.0352 | +| n_updates | 35600 | +| policy_gradient_loss | -0.0227 | +| value_loss | 0.000269 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.071 | +| time/ | | +| fps | 1289 | +| iterations | 65 | +| time_elapsed | 103 | +| total_timesteps | 133120 | +| train/ | | +| approx_kl | 0.010920661 | +| clip_fraction | 0.305 | +| clip_range | 0.075 | +| entropy_loss | -7.21 | +| explained_variance | -0.0558 | +| learning_rate | 5e-05 | +| loss | -0.0354 | +| n_updates | 35604 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000224 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0659 | +| time/ | | +| fps | 1289 | +| iterations | 66 | +| time_elapsed | 104 | +| total_timesteps | 135168 | +| train/ | | +| approx_kl | 0.011831964 | +| clip_fraction | 0.313 | +| clip_range | 0.075 | +| entropy_loss | -6.66 | +| explained_variance | 0.166 | +| learning_rate | 5e-05 | +| loss | -0.0153 | +| n_updates | 35608 | +| policy_gradient_loss | -0.0158 | +| value_loss | 0.0006 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0665 | +| time/ | | +| fps | 1289 | +| iterations | 67 | +| time_elapsed | 106 | +| total_timesteps | 137216 | +| train/ | | +| approx_kl | 0.014262105 | +| clip_fraction | 0.318 | +| clip_range | 0.075 | +| entropy_loss | -6.81 | +| explained_variance | 0.101 | +| learning_rate | 5e-05 | +| loss | -0.0347 | +| n_updates | 35612 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000321 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.072 | +| time/ | | +| fps | 1289 | +| iterations | 68 | +| time_elapsed | 107 | +| total_timesteps | 139264 | +| train/ | | +| approx_kl | 0.0130115375 | +| clip_fraction | 0.342 | +| clip_range | 0.075 | +| entropy_loss | -7.14 | +| explained_variance | 0.106 | +| learning_rate | 5e-05 | +| loss | -0.0378 | +| n_updates | 35616 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000269 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0694 | +| time/ | | +| fps | 1289 | +| iterations | 69 | +| time_elapsed | 109 | +| total_timesteps | 141312 | +| train/ | | +| approx_kl | 0.020627411 | +| clip_fraction | 0.293 | +| clip_range | 0.075 | +| entropy_loss | -7.01 | +| explained_variance | 0.125 | +| learning_rate | 5e-05 | +| loss | -0.0317 | +| n_updates | 35620 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000335 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0694 | +| time/ | | +| fps | 1289 | +| iterations | 70 | +| time_elapsed | 111 | +| total_timesteps | 143360 | +| train/ | | +| approx_kl | 0.014357158 | +| clip_fraction | 0.347 | +| clip_range | 0.075 | +| entropy_loss | -6.91 | +| explained_variance | 0.144 | +| learning_rate | 5e-05 | +| loss | -0.0372 | +| n_updates | 35624 | +| policy_gradient_loss | -0.0231 | +| value_loss | 0.000339 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0606 | +| time/ | | +| fps | 1288 | +| iterations | 71 | +| time_elapsed | 112 | +| total_timesteps | 145408 | +| train/ | | +| approx_kl | 0.01085298 | +| clip_fraction | 0.304 | +| clip_range | 0.075 | +| entropy_loss | -7.28 | +| explained_variance | -0.0705 | +| learning_rate | 5e-05 | +| loss | -0.0369 | +| n_updates | 35628 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000321 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0606 | +| time/ | | +| fps | 1287 | +| iterations | 72 | +| time_elapsed | 114 | +| total_timesteps | 147456 | +| train/ | | +| approx_kl | 0.012989611 | +| clip_fraction | 0.344 | +| clip_range | 0.075 | +| entropy_loss | -6.6 | +| explained_variance | 0.116 | +| learning_rate | 5e-05 | +| loss | -0.0239 | +| n_updates | 35632 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000168 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0554 | +| time/ | | +| fps | 1287 | +| iterations | 73 | +| time_elapsed | 116 | +| total_timesteps | 149504 | +| train/ | | +| approx_kl | 0.013014437 | +| clip_fraction | 0.334 | +| clip_range | 0.075 | +| entropy_loss | -7.15 | +| explained_variance | -0.0302 | +| learning_rate | 5e-05 | +| loss | -0.0343 | +| n_updates | 35636 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000391 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0554 | +| time/ | | +| fps | 1286 | +| iterations | 74 | +| time_elapsed | 117 | +| total_timesteps | 151552 | +| train/ | | +| approx_kl | 0.012460999 | +| clip_fraction | 0.315 | +| clip_range | 0.075 | +| entropy_loss | -7.19 | +| explained_variance | 0.0603 | +| learning_rate | 5e-05 | +| loss | -0.0349 | +| n_updates | 35640 | +| policy_gradient_loss | -0.0222 | +| value_loss | 0.000342 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0605 | +| time/ | | +| fps | 1286 | +| iterations | 75 | +| time_elapsed | 119 | +| total_timesteps | 153600 | +| train/ | | +| approx_kl | 0.013939032 | +| clip_fraction | 0.337 | +| clip_range | 0.075 | +| entropy_loss | -7.19 | +| explained_variance | -0.0277 | +| learning_rate | 5e-05 | +| loss | -0.0329 | +| n_updates | 35644 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000302 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0612 | +| time/ | | +| fps | 1285 | +| iterations | 76 | +| time_elapsed | 121 | +| total_timesteps | 155648 | +| train/ | | +| approx_kl | 0.012922168 | +| clip_fraction | 0.315 | +| clip_range | 0.075 | +| entropy_loss | -6.54 | +| explained_variance | 0.11 | +| learning_rate | 5e-05 | +| loss | -0.0335 | +| n_updates | 35648 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000339 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0568 | +| time/ | | +| fps | 1285 | +| iterations | 77 | +| time_elapsed | 122 | +| total_timesteps | 157696 | +| train/ | | +| approx_kl | 0.012423674 | +| clip_fraction | 0.329 | +| clip_range | 0.075 | +| entropy_loss | -6.88 | +| explained_variance | 0.0785 | +| learning_rate | 5e-05 | +| loss | -0.0302 | +| n_updates | 35652 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000419 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0568 | +| time/ | | +| fps | 1285 | +| iterations | 78 | +| time_elapsed | 124 | +| total_timesteps | 159744 | +| train/ | | +| approx_kl | 0.0134825 | +| clip_fraction | 0.345 | +| clip_range | 0.075 | +| entropy_loss | -6.93 | +| explained_variance | 0.0594 | +| learning_rate | 5e-05 | +| loss | -0.034 | +| n_updates | 35656 | +| policy_gradient_loss | -0.0225 | +| value_loss | 0.000339 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0568 | +| time/ | | +| fps | 1286 | +| iterations | 79 | +| time_elapsed | 125 | +| total_timesteps | 161792 | +| train/ | | +| approx_kl | 0.012595461 | +| clip_fraction | 0.327 | +| clip_range | 0.075 | +| entropy_loss | -7.07 | +| explained_variance | 0.0365 | +| learning_rate | 5e-05 | +| loss | -0.036 | +| n_updates | 35660 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000296 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0568 | +| time/ | | +| fps | 1285 | +| iterations | 80 | +| time_elapsed | 127 | +| total_timesteps | 163840 | +| train/ | | +| approx_kl | 0.01367267 | +| clip_fraction | 0.359 | +| clip_range | 0.075 | +| entropy_loss | -7.29 | +| explained_variance | -0.0928 | +| learning_rate | 5e-05 | +| loss | -0.0369 | +| n_updates | 35664 | +| policy_gradient_loss | -0.0241 | +| value_loss | 0.000304 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.0412 | +| time/ | | +| fps | 1286 | +| iterations | 81 | +| time_elapsed | 128 | +| total_timesteps | 165888 | +| train/ | | +| approx_kl | 0.012356626 | +| clip_fraction | 0.329 | +| clip_range | 0.075 | +| entropy_loss | -7.34 | +| explained_variance | -0.117 | +| learning_rate | 5e-05 | +| loss | -0.0362 | +| n_updates | 35668 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000236 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.0412 | +| time/ | | +| fps | 1286 | +| iterations | 82 | +| time_elapsed | 130 | +| total_timesteps | 167936 | +| train/ | | +| approx_kl | 0.011038687 | +| clip_fraction | 0.302 | +| clip_range | 0.075 | +| entropy_loss | -6.72 | +| explained_variance | 0.392 | +| learning_rate | 5e-05 | +| loss | -0.0286 | +| n_updates | 35672 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000309 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0345 | +| time/ | | +| fps | 1285 | +| iterations | 83 | +| time_elapsed | 132 | +| total_timesteps | 169984 | +| train/ | | +| approx_kl | 0.012661379 | +| clip_fraction | 0.34 | +| clip_range | 0.075 | +| entropy_loss | -7.23 | +| explained_variance | -0.123 | +| learning_rate | 5e-05 | +| loss | -0.0326 | +| n_updates | 35676 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000228 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0306 | +| time/ | | +| fps | 1285 | +| iterations | 84 | +| time_elapsed | 133 | +| total_timesteps | 172032 | +| train/ | | +| approx_kl | 0.012483846 | +| clip_fraction | 0.313 | +| clip_range | 0.075 | +| entropy_loss | -6.97 | +| explained_variance | 0.25 | +| learning_rate | 5e-05 | +| loss | -0.0307 | +| n_updates | 35680 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000193 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0263 | +| time/ | | +| fps | 1284 | +| iterations | 85 | +| time_elapsed | 135 | +| total_timesteps | 174080 | +| train/ | | +| approx_kl | 0.013591638 | +| clip_fraction | 0.349 | +| clip_range | 0.075 | +| entropy_loss | -6.5 | +| explained_variance | 0.554 | +| learning_rate | 5e-05 | +| loss | -0.0315 | +| n_updates | 35684 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000179 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0266 | +| time/ | | +| fps | 1284 | +| iterations | 86 | +| time_elapsed | 137 | +| total_timesteps | 176128 | +| train/ | | +| approx_kl | 0.013250137 | +| clip_fraction | 0.316 | +| clip_range | 0.075 | +| entropy_loss | -6.67 | +| explained_variance | 0.501 | +| learning_rate | 5e-05 | +| loss | -0.0278 | +| n_updates | 35688 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000246 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0266 | +| time/ | | +| fps | 1284 | +| iterations | 87 | +| time_elapsed | 138 | +| total_timesteps | 178176 | +| train/ | | +| approx_kl | 0.014952358 | +| clip_fraction | 0.326 | +| clip_range | 0.075 | +| entropy_loss | -6.86 | +| explained_variance | 0.0673 | +| learning_rate | 5e-05 | +| loss | -0.0288 | +| n_updates | 35692 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000204 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0266 | +| time/ | | +| fps | 1284 | +| iterations | 88 | +| time_elapsed | 140 | +| total_timesteps | 180224 | +| train/ | | +| approx_kl | 0.012575353 | +| clip_fraction | 0.332 | +| clip_range | 0.075 | +| entropy_loss | -7.16 | +| explained_variance | 0.144 | +| learning_rate | 5e-05 | +| loss | -0.0311 | +| n_updates | 35696 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000225 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0266 | +| time/ | | +| fps | 1284 | +| iterations | 89 | +| time_elapsed | 141 | +| total_timesteps | 182272 | +| train/ | | +| approx_kl | 0.012050223 | +| clip_fraction | 0.318 | +| clip_range | 0.075 | +| entropy_loss | -7.31 | +| explained_variance | -0.072 | +| learning_rate | 5e-05 | +| loss | -0.0339 | +| n_updates | 35700 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000368 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0184 | +| time/ | | +| fps | 1285 | +| iterations | 90 | +| time_elapsed | 143 | +| total_timesteps | 184320 | +| train/ | | +| approx_kl | 0.01284045 | +| clip_fraction | 0.336 | +| clip_range | 0.075 | +| entropy_loss | -7.23 | +| explained_variance | -0.0729 | +| learning_rate | 5e-05 | +| loss | -0.0335 | +| n_updates | 35704 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000296 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0157 | +| time/ | | +| fps | 1285 | +| iterations | 91 | +| time_elapsed | 144 | +| total_timesteps | 186368 | +| train/ | | +| approx_kl | 0.014009969 | +| clip_fraction | 0.331 | +| clip_range | 0.075 | +| entropy_loss | -7.03 | +| explained_variance | 0.0845 | +| learning_rate | 5e-05 | +| loss | -0.0314 | +| n_updates | 35708 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000245 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0211 | +| time/ | | +| fps | 1286 | +| iterations | 92 | +| time_elapsed | 146 | +| total_timesteps | 188416 | +| train/ | | +| approx_kl | 0.013660973 | +| clip_fraction | 0.326 | +| clip_range | 0.075 | +| entropy_loss | -6.76 | +| explained_variance | 0.263 | +| learning_rate | 5e-05 | +| loss | -0.0333 | +| n_updates | 35712 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000293 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0238 | +| time/ | | +| fps | 1286 | +| iterations | 93 | +| time_elapsed | 148 | +| total_timesteps | 190464 | +| train/ | | +| approx_kl | 0.01112652 | +| clip_fraction | 0.31 | +| clip_range | 0.075 | +| entropy_loss | -6.81 | +| explained_variance | 0.477 | +| learning_rate | 5e-05 | +| loss | -0.0278 | +| n_updates | 35716 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000257 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0206 | +| time/ | | +| fps | 1287 | +| iterations | 94 | +| time_elapsed | 149 | +| total_timesteps | 192512 | +| train/ | | +| approx_kl | 0.014163641 | +| clip_fraction | 0.326 | +| clip_range | 0.075 | +| entropy_loss | -6.62 | +| explained_variance | 0.293 | +| learning_rate | 5e-05 | +| loss | -0.034 | +| n_updates | 35720 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000323 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.018 | +| time/ | | +| fps | 1288 | +| iterations | 95 | +| time_elapsed | 151 | +| total_timesteps | 194560 | +| train/ | | +| approx_kl | 0.013343081 | +| clip_fraction | 0.343 | +| clip_range | 0.075 | +| entropy_loss | -6.83 | +| explained_variance | -0.124 | +| learning_rate | 5e-05 | +| loss | -0.035 | +| n_updates | 35724 | +| policy_gradient_loss | -0.0221 | +| value_loss | 0.000293 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0106 | +| time/ | | +| fps | 1287 | +| iterations | 96 | +| time_elapsed | 152 | +| total_timesteps | 196608 | +| train/ | | +| approx_kl | 0.014652149 | +| clip_fraction | 0.351 | +| clip_range | 0.075 | +| entropy_loss | -6.88 | +| explained_variance | 0.119 | +| learning_rate | 5e-05 | +| loss | -0.0346 | +| n_updates | 35728 | +| policy_gradient_loss | -0.0221 | +| value_loss | 0.000229 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0106 | +| time/ | | +| fps | 1287 | +| iterations | 97 | +| time_elapsed | 154 | +| total_timesteps | 198656 | +| train/ | | +| approx_kl | 0.0124411 | +| clip_fraction | 0.332 | +| clip_range | 0.075 | +| entropy_loss | -7.09 | +| explained_variance | 0.0208 | +| learning_rate | 5e-05 | +| loss | -0.0366 | +| n_updates | 35732 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000327 | +--------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0106 | +| time/ | | +| fps | 1287 | +| iterations | 98 | +| time_elapsed | 155 | +| total_timesteps | 200704 | +| train/ | | +| approx_kl | 0.0137090655 | +| clip_fraction | 0.343 | +| clip_range | 0.075 | +| entropy_loss | -7.28 | +| explained_variance | -0.0742 | +| learning_rate | 5e-05 | +| loss | -0.0374 | +| n_updates | 35736 | +| policy_gradient_loss | -0.0227 | +| value_loss | 0.000265 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0106 | +| time/ | | +| fps | 1287 | +| iterations | 99 | +| time_elapsed | 157 | +| total_timesteps | 202752 | +| train/ | | +| approx_kl | 0.013902067 | +| clip_fraction | 0.36 | +| clip_range | 0.0749 | +| entropy_loss | -7.25 | +| explained_variance | -0.0507 | +| learning_rate | 5e-05 | +| loss | -0.0327 | +| n_updates | 35740 | +| policy_gradient_loss | -0.0229 | +| value_loss | 0.00026 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.00704 | +| time/ | | +| fps | 1287 | +| iterations | 100 | +| time_elapsed | 159 | +| total_timesteps | 204800 | +| train/ | | +| approx_kl | 0.012025487 | +| clip_fraction | 0.346 | +| clip_range | 0.0749 | +| entropy_loss | -7.23 | +| explained_variance | -0.12 | +| learning_rate | 5e-05 | +| loss | -0.0363 | +| n_updates | 35744 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000209 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | -3.43e-06 | +| time/ | | +| fps | 1288 | +| iterations | 101 | +| time_elapsed | 160 | +| total_timesteps | 206848 | +| train/ | | +| approx_kl | 0.014663134 | +| clip_fraction | 0.34 | +| clip_range | 0.0749 | +| entropy_loss | -7.04 | +| explained_variance | 0.181 | +| learning_rate | 5e-05 | +| loss | -0.0278 | +| n_updates | 35748 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000357 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | -0.00843 | +| time/ | | +| fps | 1288 | +| iterations | 102 | +| time_elapsed | 162 | +| total_timesteps | 208896 | +| train/ | | +| approx_kl | 0.012842124 | +| clip_fraction | 0.348 | +| clip_range | 0.0749 | +| entropy_loss | -6.83 | +| explained_variance | 0.289 | +| learning_rate | 5e-05 | +| loss | -0.0355 | +| n_updates | 35752 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.00029 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | -0.0123 | +| time/ | | +| fps | 1288 | +| iterations | 103 | +| time_elapsed | 163 | +| total_timesteps | 210944 | +| train/ | | +| approx_kl | 0.011865558 | +| clip_fraction | 0.34 | +| clip_range | 0.0749 | +| entropy_loss | -6.42 | +| explained_variance | 0.029 | +| learning_rate | 5e-05 | +| loss | -0.0373 | +| n_updates | 35756 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000354 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | -0.0119 | +| time/ | | +| fps | 1289 | +| iterations | 104 | +| time_elapsed | 165 | +| total_timesteps | 212992 | +| train/ | | +| approx_kl | 0.014924739 | +| clip_fraction | 0.343 | +| clip_range | 0.0749 | +| entropy_loss | -6.72 | +| explained_variance | -0.0201 | +| learning_rate | 4.99e-05 | +| loss | -0.0314 | +| n_updates | 35760 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.0002 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | -0.0119 | +| time/ | | +| fps | 1289 | +| iterations | 105 | +| time_elapsed | 166 | +| total_timesteps | 215040 | +| train/ | | +| approx_kl | 0.014323478 | +| clip_fraction | 0.358 | +| clip_range | 0.0749 | +| entropy_loss | -6.7 | +| explained_variance | 0.0574 | +| learning_rate | 4.99e-05 | +| loss | -0.0342 | +| n_updates | 35764 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000277 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | -0.0215 | +| time/ | | +| fps | 1289 | +| iterations | 106 | +| time_elapsed | 168 | +| total_timesteps | 217088 | +| train/ | | +| approx_kl | 0.013524523 | +| clip_fraction | 0.342 | +| clip_range | 0.0749 | +| entropy_loss | -7.13 | +| explained_variance | -0.0587 | +| learning_rate | 4.99e-05 | +| loss | -0.0348 | +| n_updates | 35768 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000298 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | -0.0163 | +| time/ | | +| fps | 1289 | +| iterations | 107 | +| time_elapsed | 169 | +| total_timesteps | 219136 | +| train/ | | +| approx_kl | 0.011463703 | +| clip_fraction | 0.326 | +| clip_range | 0.0749 | +| entropy_loss | -6.98 | +| explained_variance | -0.0303 | +| learning_rate | 4.99e-05 | +| loss | -0.0266 | +| n_updates | 35772 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000209 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | -0.022 | +| time/ | | +| fps | 1289 | +| iterations | 108 | +| time_elapsed | 171 | +| total_timesteps | 221184 | +| train/ | | +| approx_kl | 0.013823077 | +| clip_fraction | 0.321 | +| clip_range | 0.0749 | +| entropy_loss | -7.1 | +| explained_variance | 0.282 | +| learning_rate | 4.99e-05 | +| loss | -0.0321 | +| n_updates | 35776 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000218 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | -0.0234 | +| time/ | | +| fps | 1289 | +| iterations | 109 | +| time_elapsed | 173 | +| total_timesteps | 223232 | +| train/ | | +| approx_kl | 0.012483394 | +| clip_fraction | 0.32 | +| clip_range | 0.0749 | +| entropy_loss | -6.89 | +| explained_variance | 0.147 | +| learning_rate | 4.99e-05 | +| loss | -0.0327 | +| n_updates | 35780 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000317 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | -0.0151 | +| time/ | | +| fps | 1289 | +| iterations | 110 | +| time_elapsed | 174 | +| total_timesteps | 225280 | +| train/ | | +| approx_kl | 0.013683392 | +| clip_fraction | 0.323 | +| clip_range | 0.0749 | +| entropy_loss | -6.94 | +| explained_variance | 0.28 | +| learning_rate | 4.99e-05 | +| loss | -0.0314 | +| n_updates | 35784 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000322 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | -0.0153 | +| time/ | | +| fps | 1289 | +| iterations | 111 | +| time_elapsed | 176 | +| total_timesteps | 227328 | +| train/ | | +| approx_kl | 0.012577061 | +| clip_fraction | 0.321 | +| clip_range | 0.0749 | +| entropy_loss | -6.9 | +| explained_variance | -0.00674 | +| learning_rate | 4.99e-05 | +| loss | -0.0308 | +| n_updates | 35788 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000383 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | -0.0138 | +| time/ | | +| fps | 1289 | +| iterations | 112 | +| time_elapsed | 177 | +| total_timesteps | 229376 | +| train/ | | +| approx_kl | 0.01474574 | +| clip_fraction | 0.371 | +| clip_range | 0.0749 | +| entropy_loss | -6.98 | +| explained_variance | 0.0869 | +| learning_rate | 4.99e-05 | +| loss | -0.0355 | +| n_updates | 35792 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000303 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | -0.0138 | +| time/ | | +| fps | 1289 | +| iterations | 113 | +| time_elapsed | 179 | +| total_timesteps | 231424 | +| train/ | | +| approx_kl | 0.013261497 | +| clip_fraction | 0.321 | +| clip_range | 0.0749 | +| entropy_loss | -6.93 | +| explained_variance | 0.184 | +| learning_rate | 4.99e-05 | +| loss | -0.0344 | +| n_updates | 35796 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000399 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | -0.0111 | +| time/ | | +| fps | 1289 | +| iterations | 114 | +| time_elapsed | 181 | +| total_timesteps | 233472 | +| train/ | | +| approx_kl | 0.014343012 | +| clip_fraction | 0.355 | +| clip_range | 0.0749 | +| entropy_loss | -7.11 | +| explained_variance | -0.0962 | +| learning_rate | 4.99e-05 | +| loss | -0.0347 | +| n_updates | 35800 | +| policy_gradient_loss | -0.0231 | +| value_loss | 0.000241 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | -0.0116 | +| time/ | | +| fps | 1288 | +| iterations | 115 | +| time_elapsed | 182 | +| total_timesteps | 235520 | +| train/ | | +| approx_kl | 0.01306612 | +| clip_fraction | 0.307 | +| clip_range | 0.0749 | +| entropy_loss | -6.9 | +| explained_variance | -0.0475 | +| learning_rate | 4.99e-05 | +| loss | -0.0302 | +| n_updates | 35804 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000276 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | -0.0179 | +| time/ | | +| fps | 1289 | +| iterations | 116 | +| time_elapsed | 184 | +| total_timesteps | 237568 | +| train/ | | +| approx_kl | 0.01465725 | +| clip_fraction | 0.358 | +| clip_range | 0.0749 | +| entropy_loss | -6.92 | +| explained_variance | -0.0653 | +| learning_rate | 4.99e-05 | +| loss | -0.0347 | +| n_updates | 35808 | +| policy_gradient_loss | -0.0221 | +| value_loss | 0.000338 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | -0.0187 | +| time/ | | +| fps | 1289 | +| iterations | 117 | +| time_elapsed | 185 | +| total_timesteps | 239616 | +| train/ | | +| approx_kl | 0.015257067 | +| clip_fraction | 0.371 | +| clip_range | 0.0749 | +| entropy_loss | -6.7 | +| explained_variance | 0.172 | +| learning_rate | 4.99e-05 | +| loss | -0.0352 | +| n_updates | 35812 | +| policy_gradient_loss | -0.0232 | +| value_loss | 0.000156 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | -0.00614 | +| time/ | | +| fps | 1289 | +| iterations | 118 | +| time_elapsed | 187 | +| total_timesteps | 241664 | +| train/ | | +| approx_kl | 0.015304134 | +| clip_fraction | 0.361 | +| clip_range | 0.0749 | +| entropy_loss | -6.72 | +| explained_variance | 0.354 | +| learning_rate | 4.99e-05 | +| loss | -0.034 | +| n_updates | 35816 | +| policy_gradient_loss | -0.022 | +| value_loss | 0.000279 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | -0.000862 | +| time/ | | +| fps | 1290 | +| iterations | 119 | +| time_elapsed | 188 | +| total_timesteps | 243712 | +| train/ | | +| approx_kl | 0.012944449 | +| clip_fraction | 0.32 | +| clip_range | 0.0749 | +| entropy_loss | -6.79 | +| explained_variance | 0.0229 | +| learning_rate | 4.99e-05 | +| loss | -0.0282 | +| n_updates | 35820 | +| policy_gradient_loss | -0.0167 | +| value_loss | 0.000886 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.00277 | +| time/ | | +| fps | 1289 | +| iterations | 120 | +| time_elapsed | 190 | +| total_timesteps | 245760 | +| train/ | | +| approx_kl | 0.014985657 | +| clip_fraction | 0.352 | +| clip_range | 0.0749 | +| entropy_loss | -6.63 | +| explained_variance | 0.244 | +| learning_rate | 4.99e-05 | +| loss | -0.0355 | +| n_updates | 35824 | +| policy_gradient_loss | -0.0231 | +| value_loss | 0.000378 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.00166 | +| time/ | | +| fps | 1289 | +| iterations | 121 | +| time_elapsed | 192 | +| total_timesteps | 247808 | +| train/ | | +| approx_kl | 0.015929893 | +| clip_fraction | 0.382 | +| clip_range | 0.0749 | +| entropy_loss | -6.73 | +| explained_variance | 0.346 | +| learning_rate | 4.99e-05 | +| loss | -0.0373 | +| n_updates | 35828 | +| policy_gradient_loss | -0.0223 | +| value_loss | 0.000216 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.00166 | +| time/ | | +| fps | 1289 | +| iterations | 122 | +| time_elapsed | 193 | +| total_timesteps | 249856 | +| train/ | | +| approx_kl | 0.014398923 | +| clip_fraction | 0.353 | +| clip_range | 0.0749 | +| entropy_loss | -6.96 | +| explained_variance | -0.0408 | +| learning_rate | 4.99e-05 | +| loss | -0.0336 | +| n_updates | 35832 | +| policy_gradient_loss | -0.0219 | +| value_loss | 0.000428 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.00497 | +| time/ | | +| fps | 1288 | +| iterations | 123 | +| time_elapsed | 195 | +| total_timesteps | 251904 | +| train/ | | +| approx_kl | 0.015078885 | +| clip_fraction | 0.338 | +| clip_range | 0.0749 | +| entropy_loss | -7.1 | +| explained_variance | -0.0426 | +| learning_rate | 4.99e-05 | +| loss | -0.033 | +| n_updates | 35836 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000264 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.00497 | +| time/ | | +| fps | 1288 | +| iterations | 124 | +| time_elapsed | 197 | +| total_timesteps | 253952 | +| train/ | | +| approx_kl | 0.01347934 | +| clip_fraction | 0.335 | +| clip_range | 0.0749 | +| entropy_loss | -6.96 | +| explained_variance | 0.152 | +| learning_rate | 4.99e-05 | +| loss | -0.0328 | +| n_updates | 35840 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.00028 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.0109 | +| time/ | | +| fps | 1288 | +| iterations | 125 | +| time_elapsed | 198 | +| total_timesteps | 256000 | +| train/ | | +| approx_kl | 0.014925522 | +| clip_fraction | 0.364 | +| clip_range | 0.0749 | +| entropy_loss | -7.17 | +| explained_variance | -0.0988 | +| learning_rate | 4.99e-05 | +| loss | -0.0332 | +| n_updates | 35844 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000304 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.00848 | +| time/ | | +| fps | 1288 | +| iterations | 126 | +| time_elapsed | 200 | +| total_timesteps | 258048 | +| train/ | | +| approx_kl | 0.012720317 | +| clip_fraction | 0.33 | +| clip_range | 0.0749 | +| entropy_loss | -6.66 | +| explained_variance | 0.155 | +| learning_rate | 4.99e-05 | +| loss | -0.0306 | +| n_updates | 35848 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000303 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | -0.00127 | +| time/ | | +| fps | 1288 | +| iterations | 127 | +| time_elapsed | 201 | +| total_timesteps | 260096 | +| train/ | | +| approx_kl | 0.013579665 | +| clip_fraction | 0.336 | +| clip_range | 0.0749 | +| entropy_loss | -6.82 | +| explained_variance | -0.0662 | +| learning_rate | 4.99e-05 | +| loss | -0.0346 | +| n_updates | 35852 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000319 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.00231 | +| time/ | | +| fps | 1288 | +| iterations | 128 | +| time_elapsed | 203 | +| total_timesteps | 262144 | +| train/ | | +| approx_kl | 0.014646918 | +| clip_fraction | 0.318 | +| clip_range | 0.0749 | +| entropy_loss | -6.78 | +| explained_variance | 0.0752 | +| learning_rate | 4.99e-05 | +| loss | -0.0326 | +| n_updates | 35856 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000291 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | -0.00389 | +| time/ | | +| fps | 1288 | +| iterations | 129 | +| time_elapsed | 204 | +| total_timesteps | 264192 | +| train/ | | +| approx_kl | 0.014620803 | +| clip_fraction | 0.35 | +| clip_range | 0.0749 | +| entropy_loss | -7.06 | +| explained_variance | -0.117 | +| learning_rate | 4.99e-05 | +| loss | -0.0335 | +| n_updates | 35860 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000211 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.00175 | +| time/ | | +| fps | 1289 | +| iterations | 130 | +| time_elapsed | 206 | +| total_timesteps | 266240 | +| train/ | | +| approx_kl | 0.015275215 | +| clip_fraction | 0.382 | +| clip_range | 0.0749 | +| entropy_loss | -6.47 | +| explained_variance | 0.366 | +| learning_rate | 4.99e-05 | +| loss | -0.0333 | +| n_updates | 35864 | +| policy_gradient_loss | -0.0231 | +| value_loss | 0.000192 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | -4.67e-05 | +| time/ | | +| fps | 1289 | +| iterations | 131 | +| time_elapsed | 208 | +| total_timesteps | 268288 | +| train/ | | +| approx_kl | 0.012874752 | +| clip_fraction | 0.351 | +| clip_range | 0.0749 | +| entropy_loss | -6.7 | +| explained_variance | 0.168 | +| learning_rate | 4.99e-05 | +| loss | -0.0333 | +| n_updates | 35868 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.00028 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | -0.00799 | +| time/ | | +| fps | 1289 | +| iterations | 132 | +| time_elapsed | 209 | +| total_timesteps | 270336 | +| train/ | | +| approx_kl | 0.016231041 | +| clip_fraction | 0.363 | +| clip_range | 0.0749 | +| entropy_loss | -6.81 | +| explained_variance | 0.0291 | +| learning_rate | 4.99e-05 | +| loss | -0.0358 | +| n_updates | 35872 | +| policy_gradient_loss | -0.0238 | +| value_loss | 0.000153 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | -0.00572 | +| time/ | | +| fps | 1290 | +| iterations | 133 | +| time_elapsed | 211 | +| total_timesteps | 272384 | +| train/ | | +| approx_kl | 0.015315408 | +| clip_fraction | 0.349 | +| clip_range | 0.0749 | +| entropy_loss | -6.63 | +| explained_variance | 0.059 | +| learning_rate | 4.99e-05 | +| loss | -0.0345 | +| n_updates | 35876 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000272 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | -0.00572 | +| time/ | | +| fps | 1290 | +| iterations | 134 | +| time_elapsed | 212 | +| total_timesteps | 274432 | +| train/ | | +| approx_kl | 0.016569834 | +| clip_fraction | 0.329 | +| clip_range | 0.0749 | +| entropy_loss | -6.71 | +| explained_variance | 0.015 | +| learning_rate | 4.99e-05 | +| loss | -0.0331 | +| n_updates | 35880 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000202 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | -0.00572 | +| time/ | | +| fps | 1290 | +| iterations | 135 | +| time_elapsed | 214 | +| total_timesteps | 276480 | +| train/ | | +| approx_kl | 0.015624849 | +| clip_fraction | 0.38 | +| clip_range | 0.0749 | +| entropy_loss | -6.74 | +| explained_variance | 0.12 | +| learning_rate | 4.99e-05 | +| loss | -0.0331 | +| n_updates | 35884 | +| policy_gradient_loss | -0.022 | +| value_loss | 0.000157 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | -0.00572 | +| time/ | | +| fps | 1290 | +| iterations | 136 | +| time_elapsed | 215 | +| total_timesteps | 278528 | +| train/ | | +| approx_kl | 0.01600828 | +| clip_fraction | 0.375 | +| clip_range | 0.0749 | +| entropy_loss | -6.89 | +| explained_variance | -0.0169 | +| learning_rate | 4.99e-05 | +| loss | -0.0346 | +| n_updates | 35888 | +| policy_gradient_loss | -0.0223 | +| value_loss | 0.000201 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | -0.0019 | +| time/ | | +| fps | 1291 | +| iterations | 137 | +| time_elapsed | 217 | +| total_timesteps | 280576 | +| train/ | | +| approx_kl | 0.014485962 | +| clip_fraction | 0.337 | +| clip_range | 0.0749 | +| entropy_loss | -7.07 | +| explained_variance | -0.0502 | +| learning_rate | 4.99e-05 | +| loss | -0.0322 | +| n_updates | 35892 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.00025 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | -0.00653 | +| time/ | | +| fps | 1291 | +| iterations | 138 | +| time_elapsed | 218 | +| total_timesteps | 282624 | +| train/ | | +| approx_kl | 0.014949948 | +| clip_fraction | 0.339 | +| clip_range | 0.0749 | +| entropy_loss | -6.81 | +| explained_variance | 0.14 | +| learning_rate | 4.99e-05 | +| loss | -0.0341 | +| n_updates | 35896 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.00021 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | -0.00704 | +| time/ | | +| fps | 1292 | +| iterations | 139 | +| time_elapsed | 220 | +| total_timesteps | 284672 | +| train/ | | +| approx_kl | 0.014181206 | +| clip_fraction | 0.336 | +| clip_range | 0.0749 | +| entropy_loss | -6.85 | +| explained_variance | -0.00882 | +| learning_rate | 4.99e-05 | +| loss | -0.0309 | +| n_updates | 35900 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000316 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | -0.00782 | +| time/ | | +| fps | 1292 | +| iterations | 140 | +| time_elapsed | 221 | +| total_timesteps | 286720 | +| train/ | | +| approx_kl | 0.013898414 | +| clip_fraction | 0.315 | +| clip_range | 0.0749 | +| entropy_loss | -6.84 | +| explained_variance | 0.124 | +| learning_rate | 4.99e-05 | +| loss | -0.0326 | +| n_updates | 35904 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.00026 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | -0.0122 | +| time/ | | +| fps | 1292 | +| iterations | 141 | +| time_elapsed | 223 | +| total_timesteps | 288768 | +| train/ | | +| approx_kl | 0.014950368 | +| clip_fraction | 0.365 | +| clip_range | 0.0749 | +| entropy_loss | -6.72 | +| explained_variance | 0.0811 | +| learning_rate | 4.99e-05 | +| loss | -0.0309 | +| n_updates | 35908 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000304 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | -0.013 | +| time/ | | +| fps | 1292 | +| iterations | 142 | +| time_elapsed | 225 | +| total_timesteps | 290816 | +| train/ | | +| approx_kl | 0.01588962 | +| clip_fraction | 0.364 | +| clip_range | 0.0749 | +| entropy_loss | -6.77 | +| explained_variance | 0.129 | +| learning_rate | 4.99e-05 | +| loss | -0.0345 | +| n_updates | 35912 | +| policy_gradient_loss | -0.0231 | +| value_loss | 0.000248 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | -0.00906 | +| time/ | | +| fps | 1291 | +| iterations | 143 | +| time_elapsed | 226 | +| total_timesteps | 292864 | +| train/ | | +| approx_kl | 0.013520086 | +| clip_fraction | 0.335 | +| clip_range | 0.0749 | +| entropy_loss | -6.83 | +| explained_variance | 0.0616 | +| learning_rate | 4.99e-05 | +| loss | -0.0324 | +| n_updates | 35916 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000225 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | -0.00582 | +| time/ | | +| fps | 1291 | +| iterations | 144 | +| time_elapsed | 228 | +| total_timesteps | 294912 | +| train/ | | +| approx_kl | 0.013954798 | +| clip_fraction | 0.379 | +| clip_range | 0.0749 | +| entropy_loss | -6.86 | +| explained_variance | 0.0698 | +| learning_rate | 4.99e-05 | +| loss | -0.0343 | +| n_updates | 35920 | +| policy_gradient_loss | -0.0219 | +| value_loss | 0.000147 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | -0.00523 | +| time/ | | +| fps | 1291 | +| iterations | 145 | +| time_elapsed | 229 | +| total_timesteps | 296960 | +| train/ | | +| approx_kl | 0.015503271 | +| clip_fraction | 0.338 | +| clip_range | 0.0749 | +| entropy_loss | -6.41 | +| explained_variance | 0.144 | +| learning_rate | 4.99e-05 | +| loss | -0.0332 | +| n_updates | 35924 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000265 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | -0.00523 | +| time/ | | +| fps | 1291 | +| iterations | 146 | +| time_elapsed | 231 | +| total_timesteps | 299008 | +| train/ | | +| approx_kl | 0.01700451 | +| clip_fraction | 0.35 | +| clip_range | 0.0749 | +| entropy_loss | -6.61 | +| explained_variance | 0.294 | +| learning_rate | 4.99e-05 | +| loss | -0.0323 | +| n_updates | 35928 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000206 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | -0.021 | +| time/ | | +| fps | 1291 | +| iterations | 147 | +| time_elapsed | 233 | +| total_timesteps | 301056 | +| train/ | | +| approx_kl | 0.015490601 | +| clip_fraction | 0.346 | +| clip_range | 0.0749 | +| entropy_loss | -7.01 | +| explained_variance | -0.0301 | +| learning_rate | 4.99e-05 | +| loss | -0.0331 | +| n_updates | 35932 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000315 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | -0.0252 | +| time/ | | +| fps | 1291 | +| iterations | 148 | +| time_elapsed | 234 | +| total_timesteps | 303104 | +| train/ | | +| approx_kl | 0.012865641 | +| clip_fraction | 0.319 | +| clip_range | 0.0749 | +| entropy_loss | -6.59 | +| explained_variance | 0.116 | +| learning_rate | 4.99e-05 | +| loss | -0.0254 | +| n_updates | 35936 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000469 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | -0.0252 | +| time/ | | +| fps | 1291 | +| iterations | 149 | +| time_elapsed | 236 | +| total_timesteps | 305152 | +| train/ | | +| approx_kl | 0.015023335 | +| clip_fraction | 0.367 | +| clip_range | 0.0749 | +| entropy_loss | -6.72 | +| explained_variance | 0.0197 | +| learning_rate | 4.99e-05 | +| loss | -0.0361 | +| n_updates | 35940 | +| policy_gradient_loss | -0.0231 | +| value_loss | 0.000453 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | -0.0193 | +| time/ | | +| fps | 1291 | +| iterations | 150 | +| time_elapsed | 237 | +| total_timesteps | 307200 | +| train/ | | +| approx_kl | 0.016085211 | +| clip_fraction | 0.389 | +| clip_range | 0.0749 | +| entropy_loss | -7.07 | +| explained_variance | -0.189 | +| learning_rate | 4.99e-05 | +| loss | -0.0428 | +| n_updates | 35944 | +| policy_gradient_loss | -0.0247 | +| value_loss | 0.00018 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | -0.00661 | +| time/ | | +| fps | 1291 | +| iterations | 151 | +| time_elapsed | 239 | +| total_timesteps | 309248 | +| train/ | | +| approx_kl | 0.012965915 | +| clip_fraction | 0.351 | +| clip_range | 0.0749 | +| entropy_loss | -6.77 | +| explained_variance | 0.146 | +| learning_rate | 4.99e-05 | +| loss | -0.0347 | +| n_updates | 35948 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000363 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | -0.00661 | +| time/ | | +| fps | 1290 | +| iterations | 152 | +| time_elapsed | 241 | +| total_timesteps | 311296 | +| train/ | | +| approx_kl | 0.014039505 | +| clip_fraction | 0.339 | +| clip_range | 0.0749 | +| entropy_loss | -6.46 | +| explained_variance | 0.0118 | +| learning_rate | 4.99e-05 | +| loss | -0.0276 | +| n_updates | 35952 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000688 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | -0.0112 | +| time/ | | +| fps | 1290 | +| iterations | 153 | +| time_elapsed | 242 | +| total_timesteps | 313344 | +| train/ | | +| approx_kl | 0.014873894 | +| clip_fraction | 0.369 | +| clip_range | 0.0749 | +| entropy_loss | -7.03 | +| explained_variance | -0.249 | +| learning_rate | 4.99e-05 | +| loss | -0.0345 | +| n_updates | 35956 | +| policy_gradient_loss | -0.0237 | +| value_loss | 0.0003 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | -0.014 | +| time/ | | +| fps | 1290 | +| iterations | 154 | +| time_elapsed | 244 | +| total_timesteps | 315392 | +| train/ | | +| approx_kl | 0.014594596 | +| clip_fraction | 0.384 | +| clip_range | 0.0749 | +| entropy_loss | -6.81 | +| explained_variance | 0.253 | +| learning_rate | 4.99e-05 | +| loss | -0.038 | +| n_updates | 35960 | +| policy_gradient_loss | -0.0244 | +| value_loss | 0.000207 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | -0.02 | +| time/ | | +| fps | 1290 | +| iterations | 155 | +| time_elapsed | 245 | +| total_timesteps | 317440 | +| train/ | | +| approx_kl | 0.013670104 | +| clip_fraction | 0.344 | +| clip_range | 0.0749 | +| entropy_loss | -6.51 | +| explained_variance | 0.202 | +| learning_rate | 4.99e-05 | +| loss | -0.0324 | +| n_updates | 35964 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000404 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | -0.02 | +| time/ | | +| fps | 1290 | +| iterations | 156 | +| time_elapsed | 247 | +| total_timesteps | 319488 | +| train/ | | +| approx_kl | 0.014216889 | +| clip_fraction | 0.375 | +| clip_range | 0.0749 | +| entropy_loss | -6.6 | +| explained_variance | 0.0919 | +| learning_rate | 4.99e-05 | +| loss | -0.0361 | +| n_updates | 35968 | +| policy_gradient_loss | -0.0244 | +| value_loss | 0.000302 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | -0.0176 | +| time/ | | +| fps | 1290 | +| iterations | 157 | +| time_elapsed | 249 | +| total_timesteps | 321536 | +| train/ | | +| approx_kl | 0.017105393 | +| clip_fraction | 0.375 | +| clip_range | 0.0749 | +| entropy_loss | -7.05 | +| explained_variance | -0.119 | +| learning_rate | 4.99e-05 | +| loss | -0.0355 | +| n_updates | 35972 | +| policy_gradient_loss | -0.0225 | +| value_loss | 0.000193 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | -0.0161 | +| time/ | | +| fps | 1290 | +| iterations | 158 | +| time_elapsed | 250 | +| total_timesteps | 323584 | +| train/ | | +| approx_kl | 0.014452904 | +| clip_fraction | 0.342 | +| clip_range | 0.0749 | +| entropy_loss | -6.78 | +| explained_variance | 0.128 | +| learning_rate | 4.99e-05 | +| loss | -0.0286 | +| n_updates | 35976 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000259 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | -0.0124 | +| time/ | | +| fps | 1290 | +| iterations | 159 | +| time_elapsed | 252 | +| total_timesteps | 325632 | +| train/ | | +| approx_kl | 0.01520381 | +| clip_fraction | 0.35 | +| clip_range | 0.0749 | +| entropy_loss | -6.69 | +| explained_variance | 0.149 | +| learning_rate | 4.99e-05 | +| loss | -0.0327 | +| n_updates | 35980 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000199 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | -0.0124 | +| time/ | | +| fps | 1289 | +| iterations | 160 | +| time_elapsed | 254 | +| total_timesteps | 327680 | +| train/ | | +| approx_kl | 0.015836716 | +| clip_fraction | 0.371 | +| clip_range | 0.0749 | +| entropy_loss | -6.59 | +| explained_variance | 0.0955 | +| learning_rate | 4.99e-05 | +| loss | -0.0358 | +| n_updates | 35984 | +| policy_gradient_loss | -0.0223 | +| value_loss | 0.000282 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | -0.00994 | +| time/ | | +| fps | 1289 | +| iterations | 161 | +| time_elapsed | 255 | +| total_timesteps | 329728 | +| train/ | | +| approx_kl | 0.015319665 | +| clip_fraction | 0.358 | +| clip_range | 0.0749 | +| entropy_loss | -6.94 | +| explained_variance | -0.126 | +| learning_rate | 4.99e-05 | +| loss | -0.0343 | +| n_updates | 35988 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.0002 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | -0.0115 | +| time/ | | +| fps | 1290 | +| iterations | 162 | +| time_elapsed | 257 | +| total_timesteps | 331776 | +| train/ | | +| approx_kl | 0.014444685 | +| clip_fraction | 0.368 | +| clip_range | 0.0749 | +| entropy_loss | -6.96 | +| explained_variance | -0.0227 | +| learning_rate | 4.99e-05 | +| loss | -0.0348 | +| n_updates | 35992 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000344 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | -0.00374 | +| time/ | | +| fps | 1289 | +| iterations | 163 | +| time_elapsed | 258 | +| total_timesteps | 333824 | +| train/ | | +| approx_kl | 0.016172186 | +| clip_fraction | 0.368 | +| clip_range | 0.0749 | +| entropy_loss | -6.5 | +| explained_variance | 0.269 | +| learning_rate | 4.99e-05 | +| loss | -0.0357 | +| n_updates | 35996 | +| policy_gradient_loss | -0.0219 | +| value_loss | 0.000283 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.000708 | +| time/ | | +| fps | 1289 | +| iterations | 164 | +| time_elapsed | 260 | +| total_timesteps | 335872 | +| train/ | | +| approx_kl | 0.016484872 | +| clip_fraction | 0.37 | +| clip_range | 0.0749 | +| entropy_loss | -6.61 | +| explained_variance | 0.317 | +| learning_rate | 4.99e-05 | +| loss | -0.031 | +| n_updates | 36000 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000197 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.00318 | +| time/ | | +| fps | 1289 | +| iterations | 165 | +| time_elapsed | 262 | +| total_timesteps | 337920 | +| train/ | | +| approx_kl | 0.014146323 | +| clip_fraction | 0.336 | +| clip_range | 0.0749 | +| entropy_loss | -6.31 | +| explained_variance | 0.211 | +| learning_rate | 4.99e-05 | +| loss | -0.0312 | +| n_updates | 36004 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000319 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.00723 | +| time/ | | +| fps | 1289 | +| iterations | 166 | +| time_elapsed | 263 | +| total_timesteps | 339968 | +| train/ | | +| approx_kl | 0.016018564 | +| clip_fraction | 0.361 | +| clip_range | 0.0749 | +| entropy_loss | -6.64 | +| explained_variance | 0.104 | +| learning_rate | 4.99e-05 | +| loss | -0.0332 | +| n_updates | 36008 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000308 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.00303 | +| time/ | | +| fps | 1289 | +| iterations | 167 | +| time_elapsed | 265 | +| total_timesteps | 342016 | +| train/ | | +| approx_kl | 0.01589791 | +| clip_fraction | 0.383 | +| clip_range | 0.0749 | +| entropy_loss | -6.55 | +| explained_variance | 0.156 | +| learning_rate | 4.99e-05 | +| loss | -0.0336 | +| n_updates | 36012 | +| policy_gradient_loss | -0.0232 | +| value_loss | 0.000345 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | -0.00256 | +| time/ | | +| fps | 1289 | +| iterations | 168 | +| time_elapsed | 266 | +| total_timesteps | 344064 | +| train/ | | +| approx_kl | 0.015752275 | +| clip_fraction | 0.356 | +| clip_range | 0.0749 | +| entropy_loss | -6.78 | +| explained_variance | 0.119 | +| learning_rate | 4.99e-05 | +| loss | -0.0329 | +| n_updates | 36016 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000313 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | -0.00261 | +| time/ | | +| fps | 1289 | +| iterations | 169 | +| time_elapsed | 268 | +| total_timesteps | 346112 | +| train/ | | +| approx_kl | 0.012039191 | +| clip_fraction | 0.346 | +| clip_range | 0.0749 | +| entropy_loss | -6.67 | +| explained_variance | 0.000546 | +| learning_rate | 4.99e-05 | +| loss | -0.0371 | +| n_updates | 36020 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000286 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | -0.00261 | +| time/ | | +| fps | 1289 | +| iterations | 170 | +| time_elapsed | 270 | +| total_timesteps | 348160 | +| train/ | | +| approx_kl | 0.014782059 | +| clip_fraction | 0.369 | +| clip_range | 0.0749 | +| entropy_loss | -6.86 | +| explained_variance | -0.131 | +| learning_rate | 4.99e-05 | +| loss | -0.036 | +| n_updates | 36024 | +| policy_gradient_loss | -0.0219 | +| value_loss | 0.00023 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | -0.00796 | +| time/ | | +| fps | 1289 | +| iterations | 171 | +| time_elapsed | 271 | +| total_timesteps | 350208 | +| train/ | | +| approx_kl | 0.014103454 | +| clip_fraction | 0.35 | +| clip_range | 0.0749 | +| entropy_loss | -7.02 | +| explained_variance | -0.0112 | +| learning_rate | 4.99e-05 | +| loss | -0.0341 | +| n_updates | 36028 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000262 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | -0.011 | +| time/ | | +| fps | 1289 | +| iterations | 172 | +| time_elapsed | 273 | +| total_timesteps | 352256 | +| train/ | | +| approx_kl | 0.014946304 | +| clip_fraction | 0.342 | +| clip_range | 0.0749 | +| entropy_loss | -6.53 | +| explained_variance | 0.187 | +| learning_rate | 4.99e-05 | +| loss | -0.0291 | +| n_updates | 36032 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000331 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | -0.011 | +| time/ | | +| fps | 1289 | +| iterations | 173 | +| time_elapsed | 274 | +| total_timesteps | 354304 | +| train/ | | +| approx_kl | 0.013694823 | +| clip_fraction | 0.343 | +| clip_range | 0.0749 | +| entropy_loss | -6.8 | +| explained_variance | 0.131 | +| learning_rate | 4.99e-05 | +| loss | -0.0321 | +| n_updates | 36036 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000247 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | -0.0084 | +| time/ | | +| fps | 1289 | +| iterations | 174 | +| time_elapsed | 276 | +| total_timesteps | 356352 | +| train/ | | +| approx_kl | 0.01433181 | +| clip_fraction | 0.364 | +| clip_range | 0.0749 | +| entropy_loss | -7.07 | +| explained_variance | -0.208 | +| learning_rate | 4.99e-05 | +| loss | -0.0334 | +| n_updates | 36040 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000216 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | -0.00861 | +| time/ | | +| fps | 1289 | +| iterations | 175 | +| time_elapsed | 277 | +| total_timesteps | 358400 | +| train/ | | +| approx_kl | 0.015861679 | +| clip_fraction | 0.348 | +| clip_range | 0.0749 | +| entropy_loss | -6.88 | +| explained_variance | 0.00392 | +| learning_rate | 4.99e-05 | +| loss | -0.0327 | +| n_updates | 36044 | +| policy_gradient_loss | -0.0228 | +| value_loss | 0.000243 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | -0.0118 | +| time/ | | +| fps | 1289 | +| iterations | 176 | +| time_elapsed | 279 | +| total_timesteps | 360448 | +| train/ | | +| approx_kl | 0.013724392 | +| clip_fraction | 0.325 | +| clip_range | 0.0749 | +| entropy_loss | -6.58 | +| explained_variance | 0.116 | +| learning_rate | 4.99e-05 | +| loss | -0.034 | +| n_updates | 36048 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000359 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | -0.0112 | +| time/ | | +| fps | 1289 | +| iterations | 177 | +| time_elapsed | 281 | +| total_timesteps | 362496 | +| train/ | | +| approx_kl | 0.016872987 | +| clip_fraction | 0.37 | +| clip_range | 0.0749 | +| entropy_loss | -6.62 | +| explained_variance | -0.21 | +| learning_rate | 4.99e-05 | +| loss | -0.039 | +| n_updates | 36052 | +| policy_gradient_loss | -0.0247 | +| value_loss | 0.000165 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | -0.00483 | +| time/ | | +| fps | 1289 | +| iterations | 178 | +| time_elapsed | 282 | +| total_timesteps | 364544 | +| train/ | | +| approx_kl | 0.017990295 | +| clip_fraction | 0.368 | +| clip_range | 0.0749 | +| entropy_loss | -6.42 | +| explained_variance | 0.132 | +| learning_rate | 4.99e-05 | +| loss | -0.0371 | +| n_updates | 36056 | +| policy_gradient_loss | -0.0219 | +| value_loss | 0.000249 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | -0.00833 | +| time/ | | +| fps | 1289 | +| iterations | 179 | +| time_elapsed | 284 | +| total_timesteps | 366592 | +| train/ | | +| approx_kl | 0.0129623655 | +| clip_fraction | 0.324 | +| clip_range | 0.0749 | +| entropy_loss | -6.61 | +| explained_variance | 0.103 | +| learning_rate | 4.99e-05 | +| loss | -0.0224 | +| n_updates | 36060 | +| policy_gradient_loss | -0.0142 | +| value_loss | 0.000858 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | -0.0131 | +| time/ | | +| fps | 1289 | +| iterations | 180 | +| time_elapsed | 285 | +| total_timesteps | 368640 | +| train/ | | +| approx_kl | 0.016155433 | +| clip_fraction | 0.372 | +| clip_range | 0.0749 | +| entropy_loss | -6.69 | +| explained_variance | 0.202 | +| learning_rate | 4.99e-05 | +| loss | -0.0392 | +| n_updates | 36064 | +| policy_gradient_loss | -0.0244 | +| value_loss | 0.000254 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | -0.0131 | +| time/ | | +| fps | 1289 | +| iterations | 181 | +| time_elapsed | 287 | +| total_timesteps | 370688 | +| train/ | | +| approx_kl | 0.014387123 | +| clip_fraction | 0.365 | +| clip_range | 0.0749 | +| entropy_loss | -6.91 | +| explained_variance | -0.121 | +| learning_rate | 4.99e-05 | +| loss | -0.0343 | +| n_updates | 36068 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.00038 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | -0.0117 | +| time/ | | +| fps | 1289 | +| iterations | 182 | +| time_elapsed | 289 | +| total_timesteps | 372736 | +| train/ | | +| approx_kl | 0.0143835 | +| clip_fraction | 0.345 | +| clip_range | 0.0749 | +| entropy_loss | -6.86 | +| explained_variance | -0.0544 | +| learning_rate | 4.99e-05 | +| loss | -0.034 | +| n_updates | 36072 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000429 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | -0.0058 | +| time/ | | +| fps | 1289 | +| iterations | 183 | +| time_elapsed | 290 | +| total_timesteps | 374784 | +| train/ | | +| approx_kl | 0.015195124 | +| clip_fraction | 0.377 | +| clip_range | 0.0749 | +| entropy_loss | -6.93 | +| explained_variance | -0.162 | +| learning_rate | 4.99e-05 | +| loss | -0.0332 | +| n_updates | 36076 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000297 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | -0.00418 | +| time/ | | +| fps | 1289 | +| iterations | 184 | +| time_elapsed | 292 | +| total_timesteps | 376832 | +| train/ | | +| approx_kl | 0.0145163685 | +| clip_fraction | 0.358 | +| clip_range | 0.0749 | +| entropy_loss | -6.77 | +| explained_variance | -0.00993 | +| learning_rate | 4.99e-05 | +| loss | -0.0319 | +| n_updates | 36080 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000333 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | -0.00454 | +| time/ | | +| fps | 1289 | +| iterations | 185 | +| time_elapsed | 293 | +| total_timesteps | 378880 | +| train/ | | +| approx_kl | 0.013722148 | +| clip_fraction | 0.377 | +| clip_range | 0.0749 | +| entropy_loss | -6.84 | +| explained_variance | -0.0945 | +| learning_rate | 4.99e-05 | +| loss | -0.04 | +| n_updates | 36084 | +| policy_gradient_loss | -0.0224 | +| value_loss | 0.000197 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | -0.0148 | +| time/ | | +| fps | 1289 | +| iterations | 186 | +| time_elapsed | 295 | +| total_timesteps | 380928 | +| train/ | | +| approx_kl | 0.013996924 | +| clip_fraction | 0.347 | +| clip_range | 0.0749 | +| entropy_loss | -6.01 | +| explained_variance | 0.348 | +| learning_rate | 4.99e-05 | +| loss | -0.0334 | +| n_updates | 36088 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000356 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | -0.0133 | +| time/ | | +| fps | 1289 | +| iterations | 187 | +| time_elapsed | 296 | +| total_timesteps | 382976 | +| train/ | | +| approx_kl | 0.014851499 | +| clip_fraction | 0.374 | +| clip_range | 0.0749 | +| entropy_loss | -6.64 | +| explained_variance | 0.149 | +| learning_rate | 4.99e-05 | +| loss | -0.0372 | +| n_updates | 36092 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000246 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.00132 | +| time/ | | +| fps | 1289 | +| iterations | 188 | +| time_elapsed | 298 | +| total_timesteps | 385024 | +| train/ | | +| approx_kl | 0.015510347 | +| clip_fraction | 0.363 | +| clip_range | 0.0749 | +| entropy_loss | -6.62 | +| explained_variance | 0.0696 | +| learning_rate | 4.99e-05 | +| loss | -0.036 | +| n_updates | 36096 | +| policy_gradient_loss | -0.0225 | +| value_loss | 0.000287 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.00387 | +| time/ | | +| fps | 1289 | +| iterations | 189 | +| time_elapsed | 300 | +| total_timesteps | 387072 | +| train/ | | +| approx_kl | 0.014171483 | +| clip_fraction | 0.353 | +| clip_range | 0.0749 | +| entropy_loss | -6.72 | +| explained_variance | 0.0853 | +| learning_rate | 4.99e-05 | +| loss | -0.0266 | +| n_updates | 36100 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000895 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.00657 | +| time/ | | +| fps | 1289 | +| iterations | 190 | +| time_elapsed | 301 | +| total_timesteps | 389120 | +| train/ | | +| approx_kl | 0.017092567 | +| clip_fraction | 0.369 | +| clip_range | 0.0749 | +| entropy_loss | -6.18 | +| explained_variance | 0.24 | +| learning_rate | 4.99e-05 | +| loss | -0.0397 | +| n_updates | 36104 | +| policy_gradient_loss | -0.0254 | +| value_loss | 0.000289 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.00657 | +| time/ | | +| fps | 1289 | +| iterations | 191 | +| time_elapsed | 303 | +| total_timesteps | 391168 | +| train/ | | +| approx_kl | 0.016346373 | +| clip_fraction | 0.406 | +| clip_range | 0.0749 | +| entropy_loss | -6.59 | +| explained_variance | -0.0657 | +| learning_rate | 4.99e-05 | +| loss | -0.0396 | +| n_updates | 36108 | +| policy_gradient_loss | -0.0248 | +| value_loss | 0.00029 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.00657 | +| time/ | | +| fps | 1289 | +| iterations | 192 | +| time_elapsed | 304 | +| total_timesteps | 393216 | +| train/ | | +| approx_kl | 0.01468122 | +| clip_fraction | 0.37 | +| clip_range | 0.0749 | +| entropy_loss | -6.83 | +| explained_variance | 0.00701 | +| learning_rate | 4.99e-05 | +| loss | -0.035 | +| n_updates | 36112 | +| policy_gradient_loss | -0.022 | +| value_loss | 0.000209 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0137 | +| time/ | | +| fps | 1289 | +| iterations | 193 | +| time_elapsed | 306 | +| total_timesteps | 395264 | +| train/ | | +| approx_kl | 0.015315667 | +| clip_fraction | 0.379 | +| clip_range | 0.0749 | +| entropy_loss | -6.93 | +| explained_variance | -0.472 | +| learning_rate | 4.99e-05 | +| loss | -0.0402 | +| n_updates | 36116 | +| policy_gradient_loss | -0.0248 | +| value_loss | 0.000106 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0126 | +| time/ | | +| fps | 1289 | +| iterations | 194 | +| time_elapsed | 308 | +| total_timesteps | 397312 | +| train/ | | +| approx_kl | 0.017021399 | +| clip_fraction | 0.379 | +| clip_range | 0.0749 | +| entropy_loss | -6.87 | +| explained_variance | 0.0136 | +| learning_rate | 4.99e-05 | +| loss | -0.0349 | +| n_updates | 36120 | +| policy_gradient_loss | -0.0223 | +| value_loss | 0.000227 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0131 | +| time/ | | +| fps | 1290 | +| iterations | 195 | +| time_elapsed | 309 | +| total_timesteps | 399360 | +| train/ | | +| approx_kl | 0.015925463 | +| clip_fraction | 0.38 | +| clip_range | 0.0749 | +| entropy_loss | -6.92 | +| explained_variance | 0.0203 | +| learning_rate | 4.99e-05 | +| loss | -0.0333 | +| n_updates | 36124 | +| policy_gradient_loss | -0.0224 | +| value_loss | 0.000197 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.00909 | +| time/ | | +| fps | 1289 | +| iterations | 196 | +| time_elapsed | 311 | +| total_timesteps | 401408 | +| train/ | | +| approx_kl | 0.015767422 | +| clip_fraction | 0.361 | +| clip_range | 0.0749 | +| entropy_loss | -6.69 | +| explained_variance | 0.226 | +| learning_rate | 4.99e-05 | +| loss | -0.031 | +| n_updates | 36128 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000258 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.00909 | +| time/ | | +| fps | 1289 | +| iterations | 197 | +| time_elapsed | 312 | +| total_timesteps | 403456 | +| train/ | | +| approx_kl | 0.014451939 | +| clip_fraction | 0.355 | +| clip_range | 0.0749 | +| entropy_loss | -6.49 | +| explained_variance | 0.215 | +| learning_rate | 4.99e-05 | +| loss | -0.0305 | +| n_updates | 36132 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000255 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.00909 | +| time/ | | +| fps | 1289 | +| iterations | 198 | +| time_elapsed | 314 | +| total_timesteps | 405504 | +| train/ | | +| approx_kl | 0.014669852 | +| clip_fraction | 0.358 | +| clip_range | 0.0749 | +| entropy_loss | -6.8 | +| explained_variance | 0.0934 | +| learning_rate | 4.99e-05 | +| loss | -0.0314 | +| n_updates | 36136 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000189 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.00277 | +| time/ | | +| fps | 1289 | +| iterations | 199 | +| time_elapsed | 316 | +| total_timesteps | 407552 | +| train/ | | +| approx_kl | 0.016964018 | +| clip_fraction | 0.361 | +| clip_range | 0.0749 | +| entropy_loss | -6.87 | +| explained_variance | -0.0773 | +| learning_rate | 4.99e-05 | +| loss | -0.0358 | +| n_updates | 36140 | +| policy_gradient_loss | -0.023 | +| value_loss | 0.000385 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.00413 | +| time/ | | +| fps | 1289 | +| iterations | 200 | +| time_elapsed | 317 | +| total_timesteps | 409600 | +| train/ | | +| approx_kl | 0.016055124 | +| clip_fraction | 0.367 | +| clip_range | 0.0749 | +| entropy_loss | -6.75 | +| explained_variance | 0.0387 | +| learning_rate | 4.99e-05 | +| loss | -0.0327 | +| n_updates | 36144 | +| policy_gradient_loss | -0.022 | +| value_loss | 0.000235 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.00361 | +| time/ | | +| fps | 1289 | +| iterations | 201 | +| time_elapsed | 319 | +| total_timesteps | 411648 | +| train/ | | +| approx_kl | 0.014641109 | +| clip_fraction | 0.356 | +| clip_range | 0.0749 | +| entropy_loss | -6.88 | +| explained_variance | -0.172 | +| learning_rate | 4.99e-05 | +| loss | -0.036 | +| n_updates | 36148 | +| policy_gradient_loss | -0.0224 | +| value_loss | 0.000168 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.00512 | +| time/ | | +| fps | 1289 | +| iterations | 202 | +| time_elapsed | 320 | +| total_timesteps | 413696 | +| train/ | | +| approx_kl | 0.015430861 | +| clip_fraction | 0.37 | +| clip_range | 0.0749 | +| entropy_loss | -6.44 | +| explained_variance | 0.0271 | +| learning_rate | 4.99e-05 | +| loss | -0.0324 | +| n_updates | 36152 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000195 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.00649 | +| time/ | | +| fps | 1289 | +| iterations | 203 | +| time_elapsed | 322 | +| total_timesteps | 415744 | +| train/ | | +| approx_kl | 0.013371641 | +| clip_fraction | 0.335 | +| clip_range | 0.0749 | +| entropy_loss | -6.75 | +| explained_variance | -0.0516 | +| learning_rate | 4.99e-05 | +| loss | -0.0317 | +| n_updates | 36156 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000264 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.0059 | +| time/ | | +| fps | 1290 | +| iterations | 204 | +| time_elapsed | 323 | +| total_timesteps | 417792 | +| train/ | | +| approx_kl | 0.014861954 | +| clip_fraction | 0.358 | +| clip_range | 0.0749 | +| entropy_loss | -6.59 | +| explained_variance | -0.00912 | +| learning_rate | 4.99e-05 | +| loss | -0.0293 | +| n_updates | 36160 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.00026 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.0069 | +| time/ | | +| fps | 1290 | +| iterations | 205 | +| time_elapsed | 325 | +| total_timesteps | 419840 | +| train/ | | +| approx_kl | 0.0131338015 | +| clip_fraction | 0.347 | +| clip_range | 0.0749 | +| entropy_loss | -6.54 | +| explained_variance | 0.158 | +| learning_rate | 4.99e-05 | +| loss | -0.0267 | +| n_updates | 36164 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000281 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.00527 | +| time/ | | +| fps | 1290 | +| iterations | 206 | +| time_elapsed | 326 | +| total_timesteps | 421888 | +| train/ | | +| approx_kl | 0.017265648 | +| clip_fraction | 0.376 | +| clip_range | 0.0749 | +| entropy_loss | -6.44 | +| explained_variance | 0.372 | +| learning_rate | 4.99e-05 | +| loss | -0.0311 | +| n_updates | 36168 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000207 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.014 | +| time/ | | +| fps | 1290 | +| iterations | 207 | +| time_elapsed | 328 | +| total_timesteps | 423936 | +| train/ | | +| approx_kl | 0.016575402 | +| clip_fraction | 0.363 | +| clip_range | 0.0749 | +| entropy_loss | -6.16 | +| explained_variance | 0.424 | +| learning_rate | 4.99e-05 | +| loss | -0.0339 | +| n_updates | 36172 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000185 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.014 | +| time/ | | +| fps | 1290 | +| iterations | 208 | +| time_elapsed | 329 | +| total_timesteps | 425984 | +| train/ | | +| approx_kl | 0.013252183 | +| clip_fraction | 0.352 | +| clip_range | 0.0749 | +| entropy_loss | -6.62 | +| explained_variance | -0.57 | +| learning_rate | 4.99e-05 | +| loss | -0.0295 | +| n_updates | 36176 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000265 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.014 | +| time/ | | +| fps | 1290 | +| iterations | 209 | +| time_elapsed | 331 | +| total_timesteps | 428032 | +| train/ | | +| approx_kl | 0.015944308 | +| clip_fraction | 0.361 | +| clip_range | 0.0749 | +| entropy_loss | -6.74 | +| explained_variance | -0.0571 | +| learning_rate | 4.99e-05 | +| loss | -0.0349 | +| n_updates | 36180 | +| policy_gradient_loss | -0.0221 | +| value_loss | 0.000299 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.0179 | +| time/ | | +| fps | 1290 | +| iterations | 210 | +| time_elapsed | 333 | +| total_timesteps | 430080 | +| train/ | | +| approx_kl | 0.013487969 | +| clip_fraction | 0.36 | +| clip_range | 0.0749 | +| entropy_loss | -7.03 | +| explained_variance | 0.0117 | +| learning_rate | 4.99e-05 | +| loss | -0.031 | +| n_updates | 36184 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000318 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.0179 | +| time/ | | +| fps | 1291 | +| iterations | 211 | +| time_elapsed | 334 | +| total_timesteps | 432128 | +| train/ | | +| approx_kl | 0.014867812 | +| clip_fraction | 0.355 | +| clip_range | 0.0749 | +| entropy_loss | -6.74 | +| explained_variance | -0.0694 | +| learning_rate | 4.99e-05 | +| loss | -0.0351 | +| n_updates | 36188 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000301 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.0135 | +| time/ | | +| fps | 1290 | +| iterations | 212 | +| time_elapsed | 336 | +| total_timesteps | 434176 | +| train/ | | +| approx_kl | 0.015526163 | +| clip_fraction | 0.39 | +| clip_range | 0.0749 | +| entropy_loss | -6.71 | +| explained_variance | -0.0964 | +| learning_rate | 4.99e-05 | +| loss | -0.0374 | +| n_updates | 36192 | +| policy_gradient_loss | -0.0225 | +| value_loss | 0.000216 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.0135 | +| time/ | | +| fps | 1291 | +| iterations | 213 | +| time_elapsed | 337 | +| total_timesteps | 436224 | +| train/ | | +| approx_kl | 0.013919627 | +| clip_fraction | 0.355 | +| clip_range | 0.0749 | +| entropy_loss | -6.79 | +| explained_variance | 0.0771 | +| learning_rate | 4.99e-05 | +| loss | -0.0299 | +| n_updates | 36196 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000323 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.0199 | +| time/ | | +| fps | 1290 | +| iterations | 214 | +| time_elapsed | 339 | +| total_timesteps | 438272 | +| train/ | | +| approx_kl | 0.016452989 | +| clip_fraction | 0.371 | +| clip_range | 0.0749 | +| entropy_loss | -6.94 | +| explained_variance | -0.0191 | +| learning_rate | 4.99e-05 | +| loss | -0.0323 | +| n_updates | 36200 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000281 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.0234 | +| time/ | | +| fps | 1290 | +| iterations | 215 | +| time_elapsed | 341 | +| total_timesteps | 440320 | +| train/ | | +| approx_kl | 0.016696218 | +| clip_fraction | 0.355 | +| clip_range | 0.0749 | +| entropy_loss | -6.37 | +| explained_variance | 0.11 | +| learning_rate | 4.99e-05 | +| loss | -0.0341 | +| n_updates | 36204 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000304 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.0318 | +| time/ | | +| fps | 1290 | +| iterations | 216 | +| time_elapsed | 342 | +| total_timesteps | 442368 | +| train/ | | +| approx_kl | 0.016785104 | +| clip_fraction | 0.373 | +| clip_range | 0.0749 | +| entropy_loss | -6.14 | +| explained_variance | 0.263 | +| learning_rate | 4.99e-05 | +| loss | -0.0345 | +| n_updates | 36208 | +| policy_gradient_loss | -0.0222 | +| value_loss | 0.000358 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.0307 | +| time/ | | +| fps | 1290 | +| iterations | 217 | +| time_elapsed | 344 | +| total_timesteps | 444416 | +| train/ | | +| approx_kl | 0.015767056 | +| clip_fraction | 0.375 | +| clip_range | 0.0749 | +| entropy_loss | -6.59 | +| explained_variance | -0.0385 | +| learning_rate | 4.99e-05 | +| loss | -0.0313 | +| n_updates | 36212 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.0003 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.0307 | +| time/ | | +| fps | 1291 | +| iterations | 218 | +| time_elapsed | 345 | +| total_timesteps | 446464 | +| train/ | | +| approx_kl | 0.017050613 | +| clip_fraction | 0.409 | +| clip_range | 0.0749 | +| entropy_loss | -6.52 | +| explained_variance | 0.302 | +| learning_rate | 4.99e-05 | +| loss | -0.0365 | +| n_updates | 36216 | +| policy_gradient_loss | -0.0222 | +| value_loss | 0.000258 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.0245 | +| time/ | | +| fps | 1291 | +| iterations | 219 | +| time_elapsed | 347 | +| total_timesteps | 448512 | +| train/ | | +| approx_kl | 0.014744618 | +| clip_fraction | 0.369 | +| clip_range | 0.0749 | +| entropy_loss | -6.83 | +| explained_variance | -0.00407 | +| learning_rate | 4.99e-05 | +| loss | -0.0365 | +| n_updates | 36220 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000375 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.0346 | +| time/ | | +| fps | 1291 | +| iterations | 220 | +| time_elapsed | 348 | +| total_timesteps | 450560 | +| train/ | | +| approx_kl | 0.012984447 | +| clip_fraction | 0.324 | +| clip_range | 0.0749 | +| entropy_loss | -6.75 | +| explained_variance | 0.0559 | +| learning_rate | 4.99e-05 | +| loss | -0.0313 | +| n_updates | 36224 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000603 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.0384 | +| time/ | | +| fps | 1291 | +| iterations | 221 | +| time_elapsed | 350 | +| total_timesteps | 452608 | +| train/ | | +| approx_kl | 0.012505367 | +| clip_fraction | 0.365 | +| clip_range | 0.0749 | +| entropy_loss | -6.62 | +| explained_variance | -0.0517 | +| learning_rate | 4.99e-05 | +| loss | -0.0199 | +| n_updates | 36228 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000878 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.0388 | +| time/ | | +| fps | 1291 | +| iterations | 222 | +| time_elapsed | 351 | +| total_timesteps | 454656 | +| train/ | | +| approx_kl | 0.0153622115 | +| clip_fraction | 0.391 | +| clip_range | 0.0749 | +| entropy_loss | -6.38 | +| explained_variance | -0.0963 | +| learning_rate | 4.99e-05 | +| loss | -0.0319 | +| n_updates | 36232 | +| policy_gradient_loss | -0.0224 | +| value_loss | 0.000395 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.0511 | +| time/ | | +| fps | 1292 | +| iterations | 223 | +| time_elapsed | 353 | +| total_timesteps | 456704 | +| train/ | | +| approx_kl | 0.016704809 | +| clip_fraction | 0.39 | +| clip_range | 0.0749 | +| entropy_loss | -6.6 | +| explained_variance | 0.0186 | +| learning_rate | 4.99e-05 | +| loss | -0.0409 | +| n_updates | 36236 | +| policy_gradient_loss | -0.0244 | +| value_loss | 0.000169 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.054 | +| time/ | | +| fps | 1292 | +| iterations | 224 | +| time_elapsed | 355 | +| total_timesteps | 458752 | +| train/ | | +| approx_kl | 0.0135938 | +| clip_fraction | 0.333 | +| clip_range | 0.0749 | +| entropy_loss | -6.44 | +| explained_variance | 0.0239 | +| learning_rate | 4.99e-05 | +| loss | -0.024 | +| n_updates | 36240 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000788 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.0541 | +| time/ | | +| fps | 1292 | +| iterations | 225 | +| time_elapsed | 356 | +| total_timesteps | 460800 | +| train/ | | +| approx_kl | 0.016517907 | +| clip_fraction | 0.381 | +| clip_range | 0.0749 | +| entropy_loss | -6.4 | +| explained_variance | 0.0909 | +| learning_rate | 4.99e-05 | +| loss | -0.0374 | +| n_updates | 36244 | +| policy_gradient_loss | -0.023 | +| value_loss | 0.000349 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.0559 | +| time/ | | +| fps | 1292 | +| iterations | 226 | +| time_elapsed | 358 | +| total_timesteps | 462848 | +| train/ | | +| approx_kl | 0.015289905 | +| clip_fraction | 0.377 | +| clip_range | 0.0749 | +| entropy_loss | -6.73 | +| explained_variance | -0.129 | +| learning_rate | 4.99e-05 | +| loss | -0.0368 | +| n_updates | 36248 | +| policy_gradient_loss | -0.0241 | +| value_loss | 0.000272 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.0555 | +| time/ | | +| fps | 1292 | +| iterations | 227 | +| time_elapsed | 359 | +| total_timesteps | 464896 | +| train/ | | +| approx_kl | 0.016271885 | +| clip_fraction | 0.394 | +| clip_range | 0.0749 | +| entropy_loss | -6.71 | +| explained_variance | -0.139 | +| learning_rate | 4.99e-05 | +| loss | -0.0356 | +| n_updates | 36252 | +| policy_gradient_loss | -0.0242 | +| value_loss | 0.000325 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.0462 | +| time/ | | +| fps | 1292 | +| iterations | 228 | +| time_elapsed | 361 | +| total_timesteps | 466944 | +| train/ | | +| approx_kl | 0.013653461 | +| clip_fraction | 0.352 | +| clip_range | 0.0749 | +| entropy_loss | -6.25 | +| explained_variance | 0.244 | +| learning_rate | 4.99e-05 | +| loss | -0.0284 | +| n_updates | 36256 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000307 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.0462 | +| time/ | | +| fps | 1293 | +| iterations | 229 | +| time_elapsed | 362 | +| total_timesteps | 468992 | +| train/ | | +| approx_kl | 0.015542669 | +| clip_fraction | 0.375 | +| clip_range | 0.0749 | +| entropy_loss | -6.55 | +| explained_variance | -0.0371 | +| learning_rate | 4.99e-05 | +| loss | -0.0325 | +| n_updates | 36260 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000185 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.042 | +| time/ | | +| fps | 1293 | +| iterations | 230 | +| time_elapsed | 364 | +| total_timesteps | 471040 | +| train/ | | +| approx_kl | 0.016270956 | +| clip_fraction | 0.367 | +| clip_range | 0.0749 | +| entropy_loss | -6.62 | +| explained_variance | 0.164 | +| learning_rate | 4.99e-05 | +| loss | -0.0319 | +| n_updates | 36264 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000303 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0406 | +| time/ | | +| fps | 1293 | +| iterations | 231 | +| time_elapsed | 365 | +| total_timesteps | 473088 | +| train/ | | +| approx_kl | 0.016012654 | +| clip_fraction | 0.383 | +| clip_range | 0.0749 | +| entropy_loss | -6.59 | +| explained_variance | 0.476 | +| learning_rate | 4.99e-05 | +| loss | -0.0374 | +| n_updates | 36268 | +| policy_gradient_loss | -0.0232 | +| value_loss | 0.000232 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.0296 | +| time/ | | +| fps | 1293 | +| iterations | 232 | +| time_elapsed | 367 | +| total_timesteps | 475136 | +| train/ | | +| approx_kl | 0.015710536 | +| clip_fraction | 0.346 | +| clip_range | 0.0749 | +| entropy_loss | -6.37 | +| explained_variance | -0.744 | +| learning_rate | 4.99e-05 | +| loss | -0.0228 | +| n_updates | 36272 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000223 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.0296 | +| time/ | | +| fps | 1293 | +| iterations | 233 | +| time_elapsed | 368 | +| total_timesteps | 477184 | +| train/ | | +| approx_kl | 0.01634881 | +| clip_fraction | 0.373 | +| clip_range | 0.0749 | +| entropy_loss | -6.64 | +| explained_variance | -0.0361 | +| learning_rate | 4.99e-05 | +| loss | -0.0349 | +| n_updates | 36276 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.00034 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.0321 | +| time/ | | +| fps | 1293 | +| iterations | 234 | +| time_elapsed | 370 | +| total_timesteps | 479232 | +| train/ | | +| approx_kl | 0.016259054 | +| clip_fraction | 0.372 | +| clip_range | 0.0749 | +| entropy_loss | -6.73 | +| explained_variance | 0.0743 | +| learning_rate | 4.99e-05 | +| loss | -0.0339 | +| n_updates | 36280 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000257 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.0404 | +| time/ | | +| fps | 1293 | +| iterations | 235 | +| time_elapsed | 371 | +| total_timesteps | 481280 | +| train/ | | +| approx_kl | 0.017267417 | +| clip_fraction | 0.368 | +| clip_range | 0.0749 | +| entropy_loss | -6.59 | +| explained_variance | -0.0929 | +| learning_rate | 4.99e-05 | +| loss | -0.0378 | +| n_updates | 36284 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000177 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.0445 | +| time/ | | +| fps | 1293 | +| iterations | 236 | +| time_elapsed | 373 | +| total_timesteps | 483328 | +| train/ | | +| approx_kl | 0.01473782 | +| clip_fraction | 0.353 | +| clip_range | 0.0749 | +| entropy_loss | -6.45 | +| explained_variance | -0.0852 | +| learning_rate | 4.99e-05 | +| loss | -0.0307 | +| n_updates | 36288 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000357 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.0437 | +| time/ | | +| fps | 1294 | +| iterations | 237 | +| time_elapsed | 375 | +| total_timesteps | 485376 | +| train/ | | +| approx_kl | 0.01690213 | +| clip_fraction | 0.365 | +| clip_range | 0.0749 | +| entropy_loss | -6.49 | +| explained_variance | 0.124 | +| learning_rate | 4.99e-05 | +| loss | -0.0293 | +| n_updates | 36292 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000263 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.067 | +| time/ | | +| fps | 1293 | +| iterations | 238 | +| time_elapsed | 376 | +| total_timesteps | 487424 | +| train/ | | +| approx_kl | 0.015369243 | +| clip_fraction | 0.339 | +| clip_range | 0.0749 | +| entropy_loss | -6.7 | +| explained_variance | -0.0461 | +| learning_rate | 4.99e-05 | +| loss | -0.0333 | +| n_updates | 36296 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000237 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.0741 | +| time/ | | +| fps | 1293 | +| iterations | 239 | +| time_elapsed | 378 | +| total_timesteps | 489472 | +| train/ | | +| approx_kl | 0.013323534 | +| clip_fraction | 0.356 | +| clip_range | 0.0749 | +| entropy_loss | -6.38 | +| explained_variance | 0.151 | +| learning_rate | 4.99e-05 | +| loss | -0.0229 | +| n_updates | 36300 | +| policy_gradient_loss | -0.0147 | +| value_loss | 0.00148 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.0699 | +| time/ | | +| fps | 1293 | +| iterations | 240 | +| time_elapsed | 379 | +| total_timesteps | 491520 | +| train/ | | +| approx_kl | 0.017013332 | +| clip_fraction | 0.373 | +| clip_range | 0.0749 | +| entropy_loss | -5.94 | +| explained_variance | 0.25 | +| learning_rate | 4.99e-05 | +| loss | -0.0252 | +| n_updates | 36304 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000746 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.0661 | +| time/ | | +| fps | 1294 | +| iterations | 241 | +| time_elapsed | 381 | +| total_timesteps | 493568 | +| train/ | | +| approx_kl | 0.019014642 | +| clip_fraction | 0.438 | +| clip_range | 0.0749 | +| entropy_loss | -6.47 | +| explained_variance | 0.0166 | +| learning_rate | 4.99e-05 | +| loss | -0.0444 | +| n_updates | 36308 | +| policy_gradient_loss | -0.0265 | +| value_loss | 0.000239 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.0661 | +| time/ | | +| fps | 1294 | +| iterations | 242 | +| time_elapsed | 382 | +| total_timesteps | 495616 | +| train/ | | +| approx_kl | 0.017895002 | +| clip_fraction | 0.393 | +| clip_range | 0.0749 | +| entropy_loss | -6.46 | +| explained_variance | 0.0697 | +| learning_rate | 4.99e-05 | +| loss | -0.0352 | +| n_updates | 36312 | +| policy_gradient_loss | -0.0234 | +| value_loss | 0.000274 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.0629 | +| time/ | | +| fps | 1294 | +| iterations | 243 | +| time_elapsed | 384 | +| total_timesteps | 497664 | +| train/ | | +| approx_kl | 0.017196227 | +| clip_fraction | 0.398 | +| clip_range | 0.0749 | +| entropy_loss | -6.5 | +| explained_variance | -0.304 | +| learning_rate | 4.99e-05 | +| loss | -0.0378 | +| n_updates | 36316 | +| policy_gradient_loss | -0.0235 | +| value_loss | 0.000199 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.0629 | +| time/ | | +| fps | 1294 | +| iterations | 244 | +| time_elapsed | 386 | +| total_timesteps | 499712 | +| train/ | | +| approx_kl | 0.016638992 | +| clip_fraction | 0.416 | +| clip_range | 0.0749 | +| entropy_loss | -6.57 | +| explained_variance | 0.225 | +| learning_rate | 4.99e-05 | +| loss | -0.0374 | +| n_updates | 36320 | +| policy_gradient_loss | -0.0235 | +| value_loss | 0.000201 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.0629 | +| time/ | | +| fps | 1294 | +| iterations | 245 | +| time_elapsed | 387 | +| total_timesteps | 501760 | +| train/ | | +| approx_kl | 0.01531431 | +| clip_fraction | 0.363 | +| clip_range | 0.0749 | +| entropy_loss | -6.77 | +| explained_variance | -0.0786 | +| learning_rate | 4.99e-05 | +| loss | -0.0343 | +| n_updates | 36324 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.00036 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.0542 | +| time/ | | +| fps | 1294 | +| iterations | 246 | +| time_elapsed | 389 | +| total_timesteps | 503808 | +| train/ | | +| approx_kl | 0.016582344 | +| clip_fraction | 0.383 | +| clip_range | 0.0749 | +| entropy_loss | -6.78 | +| explained_variance | -0.221 | +| learning_rate | 4.99e-05 | +| loss | -0.0371 | +| n_updates | 36328 | +| policy_gradient_loss | -0.0223 | +| value_loss | 0.000201 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.0575 | +| time/ | | +| fps | 1294 | +| iterations | 247 | +| time_elapsed | 390 | +| total_timesteps | 505856 | +| train/ | | +| approx_kl | 0.014575968 | +| clip_fraction | 0.354 | +| clip_range | 0.0749 | +| entropy_loss | -6.39 | +| explained_variance | 0.505 | +| learning_rate | 4.99e-05 | +| loss | -0.0333 | +| n_updates | 36332 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000192 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.0565 | +| time/ | | +| fps | 1295 | +| iterations | 248 | +| time_elapsed | 392 | +| total_timesteps | 507904 | +| train/ | | +| approx_kl | 0.016698832 | +| clip_fraction | 0.374 | +| clip_range | 0.0749 | +| entropy_loss | -6.23 | +| explained_variance | 0.0576 | +| learning_rate | 4.99e-05 | +| loss | -0.0339 | +| n_updates | 36336 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000167 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.051 | +| time/ | | +| fps | 1295 | +| iterations | 249 | +| time_elapsed | 393 | +| total_timesteps | 509952 | +| train/ | | +| approx_kl | 0.01545579 | +| clip_fraction | 0.391 | +| clip_range | 0.0749 | +| entropy_loss | -6.39 | +| explained_variance | 0.435 | +| learning_rate | 4.99e-05 | +| loss | -0.0367 | +| n_updates | 36340 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000144 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.0617 | +| time/ | | +| fps | 1295 | +| iterations | 250 | +| time_elapsed | 395 | +| total_timesteps | 512000 | +| train/ | | +| approx_kl | 0.01742902 | +| clip_fraction | 0.383 | +| clip_range | 0.0749 | +| entropy_loss | -6.61 | +| explained_variance | 0.182 | +| learning_rate | 4.99e-05 | +| loss | -0.0269 | +| n_updates | 36344 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000251 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.0617 | +| time/ | | +| fps | 1295 | +| iterations | 251 | +| time_elapsed | 396 | +| total_timesteps | 514048 | +| train/ | | +| approx_kl | 0.01638745 | +| clip_fraction | 0.37 | +| clip_range | 0.0749 | +| entropy_loss | -6.35 | +| explained_variance | 0.18 | +| learning_rate | 4.99e-05 | +| loss | -0.0309 | +| n_updates | 36348 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000282 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.0627 | +| time/ | | +| fps | 1295 | +| iterations | 252 | +| time_elapsed | 398 | +| total_timesteps | 516096 | +| train/ | | +| approx_kl | 0.020288635 | +| clip_fraction | 0.377 | +| clip_range | 0.0749 | +| entropy_loss | -6.51 | +| explained_variance | 0.0977 | +| learning_rate | 4.99e-05 | +| loss | -0.0328 | +| n_updates | 36352 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000256 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.0662 | +| time/ | | +| fps | 1295 | +| iterations | 253 | +| time_elapsed | 399 | +| total_timesteps | 518144 | +| train/ | | +| approx_kl | 0.01900398 | +| clip_fraction | 0.376 | +| clip_range | 0.0749 | +| entropy_loss | -6.57 | +| explained_variance | 0.103 | +| learning_rate | 4.99e-05 | +| loss | -0.031 | +| n_updates | 36356 | +| policy_gradient_loss | -0.022 | +| value_loss | 0.000319 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.0636 | +| time/ | | +| fps | 1295 | +| iterations | 254 | +| time_elapsed | 401 | +| total_timesteps | 520192 | +| train/ | | +| approx_kl | 0.019070614 | +| clip_fraction | 0.396 | +| clip_range | 0.0749 | +| entropy_loss | -6.44 | +| explained_variance | 0.132 | +| learning_rate | 4.99e-05 | +| loss | -0.0343 | +| n_updates | 36360 | +| policy_gradient_loss | -0.0221 | +| value_loss | 0.000329 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.0636 | +| time/ | | +| fps | 1296 | +| iterations | 255 | +| time_elapsed | 402 | +| total_timesteps | 522240 | +| train/ | | +| approx_kl | 0.016398717 | +| clip_fraction | 0.343 | +| clip_range | 0.0749 | +| entropy_loss | -6.6 | +| explained_variance | 0.112 | +| learning_rate | 4.99e-05 | +| loss | -0.0367 | +| n_updates | 36364 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000291 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.053 | +| time/ | | +| fps | 1296 | +| iterations | 256 | +| time_elapsed | 404 | +| total_timesteps | 524288 | +| train/ | | +| approx_kl | 0.016675182 | +| clip_fraction | 0.38 | +| clip_range | 0.0749 | +| entropy_loss | -6.81 | +| explained_variance | -0.0508 | +| learning_rate | 4.99e-05 | +| loss | -0.0353 | +| n_updates | 36368 | +| policy_gradient_loss | -0.0221 | +| value_loss | 0.000368 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.0464 | +| time/ | | +| fps | 1296 | +| iterations | 257 | +| time_elapsed | 405 | +| total_timesteps | 526336 | +| train/ | | +| approx_kl | 0.01645287 | +| clip_fraction | 0.376 | +| clip_range | 0.0749 | +| entropy_loss | -6.51 | +| explained_variance | 0.18 | +| learning_rate | 4.99e-05 | +| loss | -0.0407 | +| n_updates | 36372 | +| policy_gradient_loss | -0.0238 | +| value_loss | 0.000166 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.0424 | +| time/ | | +| fps | 1296 | +| iterations | 258 | +| time_elapsed | 407 | +| total_timesteps | 528384 | +| train/ | | +| approx_kl | 0.017542316 | +| clip_fraction | 0.377 | +| clip_range | 0.0749 | +| entropy_loss | -6.15 | +| explained_variance | 0.568 | +| learning_rate | 4.99e-05 | +| loss | -0.0332 | +| n_updates | 36376 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000141 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.0478 | +| time/ | | +| fps | 1296 | +| iterations | 259 | +| time_elapsed | 409 | +| total_timesteps | 530432 | +| train/ | | +| approx_kl | 0.014968151 | +| clip_fraction | 0.378 | +| clip_range | 0.0749 | +| entropy_loss | -6.62 | +| explained_variance | 0.00641 | +| learning_rate | 4.99e-05 | +| loss | -0.0338 | +| n_updates | 36380 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000164 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.0478 | +| time/ | | +| fps | 1296 | +| iterations | 260 | +| time_elapsed | 410 | +| total_timesteps | 532480 | +| train/ | | +| approx_kl | 0.016888972 | +| clip_fraction | 0.371 | +| clip_range | 0.0749 | +| entropy_loss | -6.37 | +| explained_variance | 0.252 | +| learning_rate | 4.99e-05 | +| loss | -0.0291 | +| n_updates | 36384 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000211 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.0478 | +| time/ | | +| fps | 1297 | +| iterations | 261 | +| time_elapsed | 412 | +| total_timesteps | 534528 | +| train/ | | +| approx_kl | 0.020029716 | +| clip_fraction | 0.392 | +| clip_range | 0.0749 | +| entropy_loss | -6.5 | +| explained_variance | 0.135 | +| learning_rate | 4.99e-05 | +| loss | -0.0332 | +| n_updates | 36388 | +| policy_gradient_loss | -0.0227 | +| value_loss | 0.000162 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.0447 | +| time/ | | +| fps | 1297 | +| iterations | 262 | +| time_elapsed | 413 | +| total_timesteps | 536576 | +| train/ | | +| approx_kl | 0.0149641335 | +| clip_fraction | 0.376 | +| clip_range | 0.0749 | +| entropy_loss | -6.66 | +| explained_variance | -0.107 | +| learning_rate | 4.99e-05 | +| loss | -0.0286 | +| n_updates | 36392 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000361 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.0531 | +| time/ | | +| fps | 1297 | +| iterations | 263 | +| time_elapsed | 415 | +| total_timesteps | 538624 | +| train/ | | +| approx_kl | 0.016266568 | +| clip_fraction | 0.412 | +| clip_range | 0.0749 | +| entropy_loss | -6.56 | +| explained_variance | 0.293 | +| learning_rate | 4.99e-05 | +| loss | -0.0404 | +| n_updates | 36396 | +| policy_gradient_loss | -0.0226 | +| value_loss | 0.000164 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.0617 | +| time/ | | +| fps | 1297 | +| iterations | 264 | +| time_elapsed | 416 | +| total_timesteps | 540672 | +| train/ | | +| approx_kl | 0.016886376 | +| clip_fraction | 0.377 | +| clip_range | 0.0749 | +| entropy_loss | -6.62 | +| explained_variance | -0.1 | +| learning_rate | 4.99e-05 | +| loss | -0.0286 | +| n_updates | 36400 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.0003 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.0634 | +| time/ | | +| fps | 1298 | +| iterations | 265 | +| time_elapsed | 418 | +| total_timesteps | 542720 | +| train/ | | +| approx_kl | 0.017922992 | +| clip_fraction | 0.374 | +| clip_range | 0.0749 | +| entropy_loss | -6.27 | +| explained_variance | 0.523 | +| learning_rate | 4.99e-05 | +| loss | -0.0279 | +| n_updates | 36404 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000201 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.0688 | +| time/ | | +| fps | 1298 | +| iterations | 266 | +| time_elapsed | 419 | +| total_timesteps | 544768 | +| train/ | | +| approx_kl | 0.01882217 | +| clip_fraction | 0.388 | +| clip_range | 0.0749 | +| entropy_loss | -6.33 | +| explained_variance | -0.0616 | +| learning_rate | 4.99e-05 | +| loss | -0.0296 | +| n_updates | 36408 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000199 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.0677 | +| time/ | | +| fps | 1298 | +| iterations | 267 | +| time_elapsed | 421 | +| total_timesteps | 546816 | +| train/ | | +| approx_kl | 0.015981745 | +| clip_fraction | 0.348 | +| clip_range | 0.0749 | +| entropy_loss | -6.51 | +| explained_variance | 0.143 | +| learning_rate | 4.99e-05 | +| loss | -0.0295 | +| n_updates | 36412 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000388 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.0677 | +| time/ | | +| fps | 1298 | +| iterations | 268 | +| time_elapsed | 422 | +| total_timesteps | 548864 | +| train/ | | +| approx_kl | 0.014262259 | +| clip_fraction | 0.389 | +| clip_range | 0.0749 | +| entropy_loss | -5.97 | +| explained_variance | 0.507 | +| learning_rate | 4.99e-05 | +| loss | -0.0351 | +| n_updates | 36416 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000186 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.0677 | +| time/ | | +| fps | 1298 | +| iterations | 269 | +| time_elapsed | 424 | +| total_timesteps | 550912 | +| train/ | | +| approx_kl | 0.018531948 | +| clip_fraction | 0.387 | +| clip_range | 0.0749 | +| entropy_loss | -6.36 | +| explained_variance | 0.173 | +| learning_rate | 4.99e-05 | +| loss | -0.0314 | +| n_updates | 36420 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000297 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.0666 | +| time/ | | +| fps | 1298 | +| iterations | 270 | +| time_elapsed | 425 | +| total_timesteps | 552960 | +| train/ | | +| approx_kl | 0.017589062 | +| clip_fraction | 0.354 | +| clip_range | 0.0749 | +| entropy_loss | -6.69 | +| explained_variance | -0.123 | +| learning_rate | 4.99e-05 | +| loss | -0.031 | +| n_updates | 36424 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000338 | +----------------------------------------- +------------------------------------------ +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0775 | +| time/ | | +| fps | 1298 | +| iterations | 271 | +| time_elapsed | 427 | +| total_timesteps | 555008 | +| train/ | | +| approx_kl | 0.0151512325 | +| clip_fraction | 0.384 | +| clip_range | 0.0749 | +| entropy_loss | -6.76 | +| explained_variance | 0.055 | +| learning_rate | 4.99e-05 | +| loss | -0.0341 | +| n_updates | 36428 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000245 | +------------------------------------------ +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0775 | +| time/ | | +| fps | 1298 | +| iterations | 272 | +| time_elapsed | 428 | +| total_timesteps | 557056 | +| train/ | | +| approx_kl | 0.017316667 | +| clip_fraction | 0.371 | +| clip_range | 0.0749 | +| entropy_loss | -6.46 | +| explained_variance | 0.0266 | +| learning_rate | 4.99e-05 | +| loss | -0.0226 | +| n_updates | 36432 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000872 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.0773 | +| time/ | | +| fps | 1298 | +| iterations | 273 | +| time_elapsed | 430 | +| total_timesteps | 559104 | +| train/ | | +| approx_kl | 0.018035252 | +| clip_fraction | 0.396 | +| clip_range | 0.0749 | +| entropy_loss | -6.28 | +| explained_variance | 0.189 | +| learning_rate | 4.99e-05 | +| loss | -0.0427 | +| n_updates | 36436 | +| policy_gradient_loss | -0.026 | +| value_loss | 0.000235 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0763 | +| time/ | | +| fps | 1299 | +| iterations | 274 | +| time_elapsed | 431 | +| total_timesteps | 561152 | +| train/ | | +| approx_kl | 0.015909456 | +| clip_fraction | 0.378 | +| clip_range | 0.0749 | +| entropy_loss | -6.35 | +| explained_variance | 0.182 | +| learning_rate | 4.99e-05 | +| loss | -0.0369 | +| n_updates | 36440 | +| policy_gradient_loss | -0.0226 | +| value_loss | 0.000278 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0772 | +| time/ | | +| fps | 1299 | +| iterations | 275 | +| time_elapsed | 433 | +| total_timesteps | 563200 | +| train/ | | +| approx_kl | 0.021071652 | +| clip_fraction | 0.405 | +| clip_range | 0.0749 | +| entropy_loss | -6.32 | +| explained_variance | 0.135 | +| learning_rate | 4.99e-05 | +| loss | -0.0341 | +| n_updates | 36444 | +| policy_gradient_loss | -0.0232 | +| value_loss | 0.000296 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0772 | +| time/ | | +| fps | 1299 | +| iterations | 276 | +| time_elapsed | 435 | +| total_timesteps | 565248 | +| train/ | | +| approx_kl | 0.021395568 | +| clip_fraction | 0.404 | +| clip_range | 0.0749 | +| entropy_loss | -6.13 | +| explained_variance | 0.356 | +| learning_rate | 4.99e-05 | +| loss | -0.0345 | +| n_updates | 36448 | +| policy_gradient_loss | -0.0221 | +| value_loss | 0.000233 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0744 | +| time/ | | +| fps | 1299 | +| iterations | 277 | +| time_elapsed | 436 | +| total_timesteps | 567296 | +| train/ | | +| approx_kl | 0.018877946 | +| clip_fraction | 0.386 | +| clip_range | 0.0749 | +| entropy_loss | -6.48 | +| explained_variance | 0.128 | +| learning_rate | 4.99e-05 | +| loss | -0.0397 | +| n_updates | 36452 | +| policy_gradient_loss | -0.0221 | +| value_loss | 0.000275 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0638 | +| time/ | | +| fps | 1299 | +| iterations | 278 | +| time_elapsed | 438 | +| total_timesteps | 569344 | +| train/ | | +| approx_kl | 0.017517284 | +| clip_fraction | 0.393 | +| clip_range | 0.0749 | +| entropy_loss | -6.6 | +| explained_variance | -0.0308 | +| learning_rate | 4.99e-05 | +| loss | -0.0354 | +| n_updates | 36456 | +| policy_gradient_loss | -0.0236 | +| value_loss | 0.000167 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0643 | +| time/ | | +| fps | 1299 | +| iterations | 279 | +| time_elapsed | 439 | +| total_timesteps | 571392 | +| train/ | | +| approx_kl | 0.015318523 | +| clip_fraction | 0.383 | +| clip_range | 0.0749 | +| entropy_loss | -6.29 | +| explained_variance | 0.107 | +| learning_rate | 4.99e-05 | +| loss | -0.0262 | +| n_updates | 36460 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000427 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0674 | +| time/ | | +| fps | 1299 | +| iterations | 280 | +| time_elapsed | 441 | +| total_timesteps | 573440 | +| train/ | | +| approx_kl | 0.018118724 | +| clip_fraction | 0.403 | +| clip_range | 0.0749 | +| entropy_loss | -6.49 | +| explained_variance | 0.149 | +| learning_rate | 4.99e-05 | +| loss | -0.0354 | +| n_updates | 36464 | +| policy_gradient_loss | -0.0231 | +| value_loss | 0.000246 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0761 | +| time/ | | +| fps | 1299 | +| iterations | 281 | +| time_elapsed | 442 | +| total_timesteps | 575488 | +| train/ | | +| approx_kl | 0.01571189 | +| clip_fraction | 0.38 | +| clip_range | 0.0749 | +| entropy_loss | -6.45 | +| explained_variance | -0.0195 | +| learning_rate | 4.99e-05 | +| loss | -0.0344 | +| n_updates | 36468 | +| policy_gradient_loss | -0.0228 | +| value_loss | 0.000149 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0771 | +| time/ | | +| fps | 1299 | +| iterations | 282 | +| time_elapsed | 444 | +| total_timesteps | 577536 | +| train/ | | +| approx_kl | 0.015989345 | +| clip_fraction | 0.372 | +| clip_range | 0.0749 | +| entropy_loss | -6.29 | +| explained_variance | 0.162 | +| learning_rate | 4.99e-05 | +| loss | -0.0301 | +| n_updates | 36472 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000344 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0782 | +| time/ | | +| fps | 1299 | +| iterations | 283 | +| time_elapsed | 446 | +| total_timesteps | 579584 | +| train/ | | +| approx_kl | 0.01859441 | +| clip_fraction | 0.374 | +| clip_range | 0.0749 | +| entropy_loss | -6.38 | +| explained_variance | 0.192 | +| learning_rate | 4.99e-05 | +| loss | -0.0318 | +| n_updates | 36476 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000203 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0782 | +| time/ | | +| fps | 1299 | +| iterations | 284 | +| time_elapsed | 447 | +| total_timesteps | 581632 | +| train/ | | +| approx_kl | 0.01845601 | +| clip_fraction | 0.394 | +| clip_range | 0.0749 | +| entropy_loss | -6.35 | +| explained_variance | 0.345 | +| learning_rate | 4.99e-05 | +| loss | -0.0347 | +| n_updates | 36480 | +| policy_gradient_loss | -0.0219 | +| value_loss | 0.000238 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.079 | +| time/ | | +| fps | 1299 | +| iterations | 285 | +| time_elapsed | 449 | +| total_timesteps | 583680 | +| train/ | | +| approx_kl | 0.018236801 | +| clip_fraction | 0.393 | +| clip_range | 0.0749 | +| entropy_loss | -6.33 | +| explained_variance | 0.214 | +| learning_rate | 4.99e-05 | +| loss | -0.0387 | +| n_updates | 36484 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000232 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0737 | +| time/ | | +| fps | 1299 | +| iterations | 286 | +| time_elapsed | 450 | +| total_timesteps | 585728 | +| train/ | | +| approx_kl | 0.015833963 | +| clip_fraction | 0.386 | +| clip_range | 0.0749 | +| entropy_loss | -6.46 | +| explained_variance | -0.0264 | +| learning_rate | 4.99e-05 | +| loss | -0.0321 | +| n_updates | 36488 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000271 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.064 | +| time/ | | +| fps | 1299 | +| iterations | 287 | +| time_elapsed | 452 | +| total_timesteps | 587776 | +| train/ | | +| approx_kl | 0.016853906 | +| clip_fraction | 0.383 | +| clip_range | 0.0749 | +| entropy_loss | -6.06 | +| explained_variance | 0.49 | +| learning_rate | 4.99e-05 | +| loss | -0.0336 | +| n_updates | 36492 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000224 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.0617 | +| time/ | | +| fps | 1299 | +| iterations | 288 | +| time_elapsed | 453 | +| total_timesteps | 589824 | +| train/ | | +| approx_kl | 0.018604374 | +| clip_fraction | 0.4 | +| clip_range | 0.0749 | +| entropy_loss | -6.17 | +| explained_variance | -0.00785 | +| learning_rate | 4.99e-05 | +| loss | -0.0352 | +| n_updates | 36496 | +| policy_gradient_loss | -0.0223 | +| value_loss | 0.000262 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.0617 | +| time/ | | +| fps | 1299 | +| iterations | 289 | +| time_elapsed | 455 | +| total_timesteps | 591872 | +| train/ | | +| approx_kl | 0.017114896 | +| clip_fraction | 0.381 | +| clip_range | 0.0749 | +| entropy_loss | -6.14 | +| explained_variance | -0.00156 | +| learning_rate | 4.99e-05 | +| loss | -0.0323 | +| n_updates | 36500 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000319 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.0617 | +| time/ | | +| fps | 1299 | +| iterations | 290 | +| time_elapsed | 457 | +| total_timesteps | 593920 | +| train/ | | +| approx_kl | 0.016476933 | +| clip_fraction | 0.392 | +| clip_range | 0.0749 | +| entropy_loss | -6.35 | +| explained_variance | 0.0462 | +| learning_rate | 4.99e-05 | +| loss | -0.0344 | +| n_updates | 36504 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000271 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.0532 | +| time/ | | +| fps | 1299 | +| iterations | 291 | +| time_elapsed | 458 | +| total_timesteps | 595968 | +| train/ | | +| approx_kl | 0.019906424 | +| clip_fraction | 0.353 | +| clip_range | 0.0749 | +| entropy_loss | -6.75 | +| explained_variance | -0.0426 | +| learning_rate | 4.99e-05 | +| loss | -0.0351 | +| n_updates | 36508 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000288 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.0532 | +| time/ | | +| fps | 1299 | +| iterations | 292 | +| time_elapsed | 460 | +| total_timesteps | 598016 | +| train/ | | +| approx_kl | 0.01637102 | +| clip_fraction | 0.374 | +| clip_range | 0.0749 | +| entropy_loss | -6.43 | +| explained_variance | 0.17 | +| learning_rate | 4.99e-05 | +| loss | -0.0351 | +| n_updates | 36512 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000245 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.0564 | +| time/ | | +| fps | 1299 | +| iterations | 293 | +| time_elapsed | 461 | +| total_timesteps | 600064 | +| train/ | | +| approx_kl | 0.015327052 | +| clip_fraction | 0.377 | +| clip_range | 0.0749 | +| entropy_loss | -6.46 | +| explained_variance | 0.124 | +| learning_rate | 4.99e-05 | +| loss | -0.0366 | +| n_updates | 36516 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000221 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.0596 | +| time/ | | +| fps | 1298 | +| iterations | 294 | +| time_elapsed | 463 | +| total_timesteps | 602112 | +| train/ | | +| approx_kl | 0.018122489 | +| clip_fraction | 0.404 | +| clip_range | 0.0748 | +| entropy_loss | -6.53 | +| explained_variance | -0.163 | +| learning_rate | 4.99e-05 | +| loss | -0.0309 | +| n_updates | 36520 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000226 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.0629 | +| time/ | | +| fps | 1298 | +| iterations | 295 | +| time_elapsed | 465 | +| total_timesteps | 604160 | +| train/ | | +| approx_kl | 0.0159531 | +| clip_fraction | 0.353 | +| clip_range | 0.0748 | +| entropy_loss | -6.52 | +| explained_variance | 0.0621 | +| learning_rate | 4.99e-05 | +| loss | -0.0275 | +| n_updates | 36524 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.00016 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.0807 | +| time/ | | +| fps | 1298 | +| iterations | 296 | +| time_elapsed | 466 | +| total_timesteps | 606208 | +| train/ | | +| approx_kl | 0.017018791 | +| clip_fraction | 0.36 | +| clip_range | 0.0748 | +| entropy_loss | -6.1 | +| explained_variance | 0.476 | +| learning_rate | 4.99e-05 | +| loss | -0.03 | +| n_updates | 36528 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000285 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.0777 | +| time/ | | +| fps | 1298 | +| iterations | 297 | +| time_elapsed | 468 | +| total_timesteps | 608256 | +| train/ | | +| approx_kl | 0.01810703 | +| clip_fraction | 0.387 | +| clip_range | 0.0748 | +| entropy_loss | -6.12 | +| explained_variance | 0.286 | +| learning_rate | 4.99e-05 | +| loss | -0.0316 | +| n_updates | 36532 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000276 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.0814 | +| time/ | | +| fps | 1298 | +| iterations | 298 | +| time_elapsed | 470 | +| total_timesteps | 610304 | +| train/ | | +| approx_kl | 0.021975154 | +| clip_fraction | 0.409 | +| clip_range | 0.0748 | +| entropy_loss | -6.19 | +| explained_variance | 0.124 | +| learning_rate | 4.99e-05 | +| loss | -0.0355 | +| n_updates | 36536 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000285 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.0758 | +| time/ | | +| fps | 1298 | +| iterations | 299 | +| time_elapsed | 471 | +| total_timesteps | 612352 | +| train/ | | +| approx_kl | 0.018037343 | +| clip_fraction | 0.395 | +| clip_range | 0.0748 | +| entropy_loss | -6.61 | +| explained_variance | -0.0145 | +| learning_rate | 4.99e-05 | +| loss | -0.0369 | +| n_updates | 36540 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000232 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.0758 | +| time/ | | +| fps | 1298 | +| iterations | 300 | +| time_elapsed | 473 | +| total_timesteps | 614400 | +| train/ | | +| approx_kl | 0.01603316 | +| clip_fraction | 0.368 | +| clip_range | 0.0748 | +| entropy_loss | -6.2 | +| explained_variance | 0.352 | +| learning_rate | 4.99e-05 | +| loss | -0.0282 | +| n_updates | 36544 | +| policy_gradient_loss | -0.017 | +| value_loss | 0.000352 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.0758 | +| time/ | | +| fps | 1298 | +| iterations | 301 | +| time_elapsed | 474 | +| total_timesteps | 616448 | +| train/ | | +| approx_kl | 0.01605555 | +| clip_fraction | 0.384 | +| clip_range | 0.0748 | +| entropy_loss | -6.48 | +| explained_variance | -0.0383 | +| learning_rate | 4.99e-05 | +| loss | -0.0372 | +| n_updates | 36548 | +| policy_gradient_loss | -0.0234 | +| value_loss | 0.000258 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.0869 | +| time/ | | +| fps | 1298 | +| iterations | 302 | +| time_elapsed | 476 | +| total_timesteps | 618496 | +| train/ | | +| approx_kl | 0.018503042 | +| clip_fraction | 0.41 | +| clip_range | 0.0748 | +| entropy_loss | -6.64 | +| explained_variance | -0.124 | +| learning_rate | 4.99e-05 | +| loss | -0.0372 | +| n_updates | 36552 | +| policy_gradient_loss | -0.0228 | +| value_loss | 0.000354 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.0824 | +| time/ | | +| fps | 1298 | +| iterations | 303 | +| time_elapsed | 477 | +| total_timesteps | 620544 | +| train/ | | +| approx_kl | 0.015158127 | +| clip_fraction | 0.394 | +| clip_range | 0.0748 | +| entropy_loss | -6.49 | +| explained_variance | 0.184 | +| learning_rate | 4.99e-05 | +| loss | -0.0261 | +| n_updates | 36556 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000315 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.0764 | +| time/ | | +| fps | 1298 | +| iterations | 304 | +| time_elapsed | 479 | +| total_timesteps | 622592 | +| train/ | | +| approx_kl | 0.014878474 | +| clip_fraction | 0.409 | +| clip_range | 0.0748 | +| entropy_loss | -6.21 | +| explained_variance | 0.0336 | +| learning_rate | 4.99e-05 | +| loss | -0.0377 | +| n_updates | 36560 | +| policy_gradient_loss | -0.0225 | +| value_loss | 0.000185 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.0758 | +| time/ | | +| fps | 1298 | +| iterations | 305 | +| time_elapsed | 481 | +| total_timesteps | 624640 | +| train/ | | +| approx_kl | 0.017960127 | +| clip_fraction | 0.401 | +| clip_range | 0.0748 | +| entropy_loss | -6.36 | +| explained_variance | 0.135 | +| learning_rate | 4.99e-05 | +| loss | -0.0333 | +| n_updates | 36564 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000224 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.079 | +| time/ | | +| fps | 1298 | +| iterations | 306 | +| time_elapsed | 482 | +| total_timesteps | 626688 | +| train/ | | +| approx_kl | 0.019248383 | +| clip_fraction | 0.39 | +| clip_range | 0.0748 | +| entropy_loss | -6.2 | +| explained_variance | 0.424 | +| learning_rate | 4.99e-05 | +| loss | -0.0355 | +| n_updates | 36568 | +| policy_gradient_loss | -0.0221 | +| value_loss | 0.0002 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.0817 | +| time/ | | +| fps | 1298 | +| iterations | 307 | +| time_elapsed | 484 | +| total_timesteps | 628736 | +| train/ | | +| approx_kl | 0.020563692 | +| clip_fraction | 0.395 | +| clip_range | 0.0748 | +| entropy_loss | -6.2 | +| explained_variance | 0.0385 | +| learning_rate | 4.99e-05 | +| loss | -0.0347 | +| n_updates | 36572 | +| policy_gradient_loss | -0.0223 | +| value_loss | 0.000318 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.0627 | +| time/ | | +| fps | 1298 | +| iterations | 308 | +| time_elapsed | 485 | +| total_timesteps | 630784 | +| train/ | | +| approx_kl | 0.01919942 | +| clip_fraction | 0.373 | +| clip_range | 0.0748 | +| entropy_loss | -6.31 | +| explained_variance | 0.129 | +| learning_rate | 4.99e-05 | +| loss | -0.0319 | +| n_updates | 36576 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000245 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.43e+03 | +| ep_rew_mean | 0.0537 | +| time/ | | +| fps | 1297 | +| iterations | 309 | +| time_elapsed | 487 | +| total_timesteps | 632832 | +| train/ | | +| approx_kl | 0.019737946 | +| clip_fraction | 0.406 | +| clip_range | 0.0748 | +| entropy_loss | -6.2 | +| explained_variance | 0.404 | +| learning_rate | 4.99e-05 | +| loss | -0.034 | +| n_updates | 36580 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000239 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.43e+03 | +| ep_rew_mean | 0.0544 | +| time/ | | +| fps | 1297 | +| iterations | 310 | +| time_elapsed | 489 | +| total_timesteps | 634880 | +| train/ | | +| approx_kl | 0.022387285 | +| clip_fraction | 0.424 | +| clip_range | 0.0748 | +| entropy_loss | -6.07 | +| explained_variance | 0.0727 | +| learning_rate | 4.98e-05 | +| loss | -0.0315 | +| n_updates | 36584 | +| policy_gradient_loss | -0.0229 | +| value_loss | 0.000208 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.43e+03 | +| ep_rew_mean | 0.0544 | +| time/ | | +| fps | 1297 | +| iterations | 311 | +| time_elapsed | 490 | +| total_timesteps | 636928 | +| train/ | | +| approx_kl | 0.020788338 | +| clip_fraction | 0.417 | +| clip_range | 0.0748 | +| entropy_loss | -6.24 | +| explained_variance | 0.221 | +| learning_rate | 4.98e-05 | +| loss | -0.0363 | +| n_updates | 36588 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000194 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.43e+03 | +| ep_rew_mean | 0.0544 | +| time/ | | +| fps | 1297 | +| iterations | 312 | +| time_elapsed | 492 | +| total_timesteps | 638976 | +| train/ | | +| approx_kl | 0.016560972 | +| clip_fraction | 0.367 | +| clip_range | 0.0748 | +| entropy_loss | -5.96 | +| explained_variance | 0.127 | +| learning_rate | 4.98e-05 | +| loss | -0.0319 | +| n_updates | 36592 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000328 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.43e+03 | +| ep_rew_mean | 0.0544 | +| time/ | | +| fps | 1297 | +| iterations | 313 | +| time_elapsed | 493 | +| total_timesteps | 641024 | +| train/ | | +| approx_kl | 0.017235573 | +| clip_fraction | 0.36 | +| clip_range | 0.0748 | +| entropy_loss | -6.4 | +| explained_variance | -0.0809 | +| learning_rate | 4.98e-05 | +| loss | -0.0306 | +| n_updates | 36596 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000286 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.43e+03 | +| ep_rew_mean | 0.0548 | +| time/ | | +| fps | 1297 | +| iterations | 314 | +| time_elapsed | 495 | +| total_timesteps | 643072 | +| train/ | | +| approx_kl | 0.018698096 | +| clip_fraction | 0.404 | +| clip_range | 0.0748 | +| entropy_loss | -6.59 | +| explained_variance | -0.222 | +| learning_rate | 4.98e-05 | +| loss | -0.0397 | +| n_updates | 36600 | +| policy_gradient_loss | -0.0244 | +| value_loss | 0.00021 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.0578 | +| time/ | | +| fps | 1297 | +| iterations | 315 | +| time_elapsed | 497 | +| total_timesteps | 645120 | +| train/ | | +| approx_kl | 0.018413488 | +| clip_fraction | 0.403 | +| clip_range | 0.0748 | +| entropy_loss | -6.03 | +| explained_variance | 0.246 | +| learning_rate | 4.98e-05 | +| loss | -0.03 | +| n_updates | 36604 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000309 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.0578 | +| time/ | | +| fps | 1297 | +| iterations | 316 | +| time_elapsed | 498 | +| total_timesteps | 647168 | +| train/ | | +| approx_kl | 0.017576907 | +| clip_fraction | 0.393 | +| clip_range | 0.0748 | +| entropy_loss | -6 | +| explained_variance | 0.237 | +| learning_rate | 4.98e-05 | +| loss | -0.0337 | +| n_updates | 36608 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000396 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.0578 | +| time/ | | +| fps | 1297 | +| iterations | 317 | +| time_elapsed | 500 | +| total_timesteps | 649216 | +| train/ | | +| approx_kl | 0.02040435 | +| clip_fraction | 0.392 | +| clip_range | 0.0748 | +| entropy_loss | -6.32 | +| explained_variance | -0.18 | +| learning_rate | 4.98e-05 | +| loss | -0.0307 | +| n_updates | 36612 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000288 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.0569 | +| time/ | | +| fps | 1297 | +| iterations | 318 | +| time_elapsed | 501 | +| total_timesteps | 651264 | +| train/ | | +| approx_kl | 0.019748341 | +| clip_fraction | 0.421 | +| clip_range | 0.0748 | +| entropy_loss | -6.45 | +| explained_variance | -0.185 | +| learning_rate | 4.98e-05 | +| loss | -0.0366 | +| n_updates | 36616 | +| policy_gradient_loss | -0.0233 | +| value_loss | 0.000179 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.42e+03 | +| ep_rew_mean | 0.0574 | +| time/ | | +| fps | 1297 | +| iterations | 319 | +| time_elapsed | 503 | +| total_timesteps | 653312 | +| train/ | | +| approx_kl | 0.014517859 | +| clip_fraction | 0.383 | +| clip_range | 0.0748 | +| entropy_loss | -6.4 | +| explained_variance | 0.127 | +| learning_rate | 4.98e-05 | +| loss | -0.0303 | +| n_updates | 36620 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000348 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.0446 | +| time/ | | +| fps | 1297 | +| iterations | 320 | +| time_elapsed | 504 | +| total_timesteps | 655360 | +| train/ | | +| approx_kl | 0.018278979 | +| clip_fraction | 0.404 | +| clip_range | 0.0748 | +| entropy_loss | -6.38 | +| explained_variance | 0.074 | +| learning_rate | 4.98e-05 | +| loss | -0.0257 | +| n_updates | 36624 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000252 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.0443 | +| time/ | | +| fps | 1297 | +| iterations | 321 | +| time_elapsed | 506 | +| total_timesteps | 657408 | +| train/ | | +| approx_kl | 0.018425299 | +| clip_fraction | 0.4 | +| clip_range | 0.0748 | +| entropy_loss | -5.9 | +| explained_variance | 0.499 | +| learning_rate | 4.98e-05 | +| loss | -0.0322 | +| n_updates | 36628 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000285 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.0386 | +| time/ | | +| fps | 1297 | +| iterations | 322 | +| time_elapsed | 508 | +| total_timesteps | 659456 | +| train/ | | +| approx_kl | 0.01718038 | +| clip_fraction | 0.397 | +| clip_range | 0.0748 | +| entropy_loss | -6.16 | +| explained_variance | 0.307 | +| learning_rate | 4.98e-05 | +| loss | -0.0332 | +| n_updates | 36632 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000199 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.0452 | +| time/ | | +| fps | 1298 | +| iterations | 323 | +| time_elapsed | 509 | +| total_timesteps | 661504 | +| train/ | | +| approx_kl | 0.01641663 | +| clip_fraction | 0.372 | +| clip_range | 0.0748 | +| entropy_loss | -6.48 | +| explained_variance | 0.178 | +| learning_rate | 4.98e-05 | +| loss | -0.0323 | +| n_updates | 36636 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000313 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.0521 | +| time/ | | +| fps | 1298 | +| iterations | 324 | +| time_elapsed | 511 | +| total_timesteps | 663552 | +| train/ | | +| approx_kl | 0.017064603 | +| clip_fraction | 0.373 | +| clip_range | 0.0748 | +| entropy_loss | -6.27 | +| explained_variance | 0.297 | +| learning_rate | 4.98e-05 | +| loss | -0.0326 | +| n_updates | 36640 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000267 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.0573 | +| time/ | | +| fps | 1298 | +| iterations | 325 | +| time_elapsed | 512 | +| total_timesteps | 665600 | +| train/ | | +| approx_kl | 0.017048554 | +| clip_fraction | 0.384 | +| clip_range | 0.0748 | +| entropy_loss | -5.94 | +| explained_variance | 0.0799 | +| learning_rate | 4.98e-05 | +| loss | -0.0208 | +| n_updates | 36644 | +| policy_gradient_loss | -0.0146 | +| value_loss | 0.000826 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.41e+03 | +| ep_rew_mean | 0.0573 | +| time/ | | +| fps | 1298 | +| iterations | 326 | +| time_elapsed | 514 | +| total_timesteps | 667648 | +| train/ | | +| approx_kl | 0.01919904 | +| clip_fraction | 0.41 | +| clip_range | 0.0748 | +| entropy_loss | -6.23 | +| explained_variance | 0.195 | +| learning_rate | 4.98e-05 | +| loss | -0.0412 | +| n_updates | 36648 | +| policy_gradient_loss | -0.0247 | +| value_loss | 0.000248 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.4e+03 | +| ep_rew_mean | 0.0529 | +| time/ | | +| fps | 1298 | +| iterations | 327 | +| time_elapsed | 515 | +| total_timesteps | 669696 | +| train/ | | +| approx_kl | 0.02016106 | +| clip_fraction | 0.41 | +| clip_range | 0.0748 | +| entropy_loss | -6.35 | +| explained_variance | -0.224 | +| learning_rate | 4.98e-05 | +| loss | -0.0405 | +| n_updates | 36652 | +| policy_gradient_loss | -0.0246 | +| value_loss | 0.000221 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.063 | +| time/ | | +| fps | 1298 | +| iterations | 328 | +| time_elapsed | 517 | +| total_timesteps | 671744 | +| train/ | | +| approx_kl | 0.018733349 | +| clip_fraction | 0.399 | +| clip_range | 0.0748 | +| entropy_loss | -6.21 | +| explained_variance | 0.21 | +| learning_rate | 4.98e-05 | +| loss | -0.0401 | +| n_updates | 36656 | +| policy_gradient_loss | -0.0233 | +| value_loss | 0.000302 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.0599 | +| time/ | | +| fps | 1298 | +| iterations | 329 | +| time_elapsed | 518 | +| total_timesteps | 673792 | +| train/ | | +| approx_kl | 0.018780813 | +| clip_fraction | 0.394 | +| clip_range | 0.0748 | +| entropy_loss | -6.19 | +| explained_variance | -0.0573 | +| learning_rate | 4.98e-05 | +| loss | -0.0242 | +| n_updates | 36660 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000866 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.0599 | +| time/ | | +| fps | 1298 | +| iterations | 330 | +| time_elapsed | 520 | +| total_timesteps | 675840 | +| train/ | | +| approx_kl | 0.017752316 | +| clip_fraction | 0.41 | +| clip_range | 0.0748 | +| entropy_loss | -6.06 | +| explained_variance | 0.131 | +| learning_rate | 4.98e-05 | +| loss | -0.0354 | +| n_updates | 36664 | +| policy_gradient_loss | -0.0235 | +| value_loss | 0.000316 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.0643 | +| time/ | | +| fps | 1298 | +| iterations | 331 | +| time_elapsed | 522 | +| total_timesteps | 677888 | +| train/ | | +| approx_kl | 0.017563071 | +| clip_fraction | 0.393 | +| clip_range | 0.0748 | +| entropy_loss | -6.42 | +| explained_variance | -0.139 | +| learning_rate | 4.98e-05 | +| loss | -0.0381 | +| n_updates | 36668 | +| policy_gradient_loss | -0.0221 | +| value_loss | 0.000205 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.0576 | +| time/ | | +| fps | 1298 | +| iterations | 332 | +| time_elapsed | 523 | +| total_timesteps | 679936 | +| train/ | | +| approx_kl | 0.01619602 | +| clip_fraction | 0.382 | +| clip_range | 0.0748 | +| entropy_loss | -6.49 | +| explained_variance | -0.217 | +| learning_rate | 4.98e-05 | +| loss | -0.0318 | +| n_updates | 36672 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.00048 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0581 | +| time/ | | +| fps | 1298 | +| iterations | 333 | +| time_elapsed | 525 | +| total_timesteps | 681984 | +| train/ | | +| approx_kl | 0.019860292 | +| clip_fraction | 0.39 | +| clip_range | 0.0748 | +| entropy_loss | -6.1 | +| explained_variance | -0.0948 | +| learning_rate | 4.98e-05 | +| loss | -0.0372 | +| n_updates | 36676 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.00028 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0578 | +| time/ | | +| fps | 1298 | +| iterations | 334 | +| time_elapsed | 526 | +| total_timesteps | 684032 | +| train/ | | +| approx_kl | 0.018810866 | +| clip_fraction | 0.414 | +| clip_range | 0.0748 | +| entropy_loss | -6.18 | +| explained_variance | 0.113 | +| learning_rate | 4.98e-05 | +| loss | -0.0353 | +| n_updates | 36680 | +| policy_gradient_loss | -0.0221 | +| value_loss | 0.000188 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0646 | +| time/ | | +| fps | 1298 | +| iterations | 335 | +| time_elapsed | 528 | +| total_timesteps | 686080 | +| train/ | | +| approx_kl | 0.019612297 | +| clip_fraction | 0.402 | +| clip_range | 0.0748 | +| entropy_loss | -6.29 | +| explained_variance | -0.139 | +| learning_rate | 4.98e-05 | +| loss | -0.0337 | +| n_updates | 36684 | +| policy_gradient_loss | -0.0224 | +| value_loss | 0.00029 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0637 | +| time/ | | +| fps | 1298 | +| iterations | 336 | +| time_elapsed | 530 | +| total_timesteps | 688128 | +| train/ | | +| approx_kl | 0.019138498 | +| clip_fraction | 0.421 | +| clip_range | 0.0748 | +| entropy_loss | -6.1 | +| explained_variance | 0.338 | +| learning_rate | 4.98e-05 | +| loss | -0.0314 | +| n_updates | 36688 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.00018 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.0515 | +| time/ | | +| fps | 1298 | +| iterations | 337 | +| time_elapsed | 531 | +| total_timesteps | 690176 | +| train/ | | +| approx_kl | 0.021383423 | +| clip_fraction | 0.405 | +| clip_range | 0.0748 | +| entropy_loss | -6.12 | +| explained_variance | 0.325 | +| learning_rate | 4.98e-05 | +| loss | -0.0358 | +| n_updates | 36692 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000221 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.0497 | +| time/ | | +| fps | 1298 | +| iterations | 338 | +| time_elapsed | 532 | +| total_timesteps | 692224 | +| train/ | | +| approx_kl | 0.016820801 | +| clip_fraction | 0.412 | +| clip_range | 0.0748 | +| entropy_loss | -6.22 | +| explained_variance | -0.115 | +| learning_rate | 4.98e-05 | +| loss | -0.0289 | +| n_updates | 36696 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000229 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.0566 | +| time/ | | +| fps | 1298 | +| iterations | 339 | +| time_elapsed | 534 | +| total_timesteps | 694272 | +| train/ | | +| approx_kl | 0.018963527 | +| clip_fraction | 0.391 | +| clip_range | 0.0748 | +| entropy_loss | -6.26 | +| explained_variance | 0.00492 | +| learning_rate | 4.98e-05 | +| loss | -0.034 | +| n_updates | 36700 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000323 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.0566 | +| time/ | | +| fps | 1298 | +| iterations | 340 | +| time_elapsed | 536 | +| total_timesteps | 696320 | +| train/ | | +| approx_kl | 0.015203226 | +| clip_fraction | 0.386 | +| clip_range | 0.0748 | +| entropy_loss | -6.39 | +| explained_variance | 0.00953 | +| learning_rate | 4.98e-05 | +| loss | -0.0341 | +| n_updates | 36704 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000289 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.0556 | +| time/ | | +| fps | 1299 | +| iterations | 341 | +| time_elapsed | 537 | +| total_timesteps | 698368 | +| train/ | | +| approx_kl | 0.017771145 | +| clip_fraction | 0.396 | +| clip_range | 0.0748 | +| entropy_loss | -6.52 | +| explained_variance | -0.0889 | +| learning_rate | 4.98e-05 | +| loss | -0.0343 | +| n_updates | 36708 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.00023 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.0598 | +| time/ | | +| fps | 1299 | +| iterations | 342 | +| time_elapsed | 539 | +| total_timesteps | 700416 | +| train/ | | +| approx_kl | 0.017984312 | +| clip_fraction | 0.403 | +| clip_range | 0.0748 | +| entropy_loss | -6.18 | +| explained_variance | 0.21 | +| learning_rate | 4.98e-05 | +| loss | -0.0325 | +| n_updates | 36712 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000249 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.0612 | +| time/ | | +| fps | 1299 | +| iterations | 343 | +| time_elapsed | 540 | +| total_timesteps | 702464 | +| train/ | | +| approx_kl | 0.020781625 | +| clip_fraction | 0.405 | +| clip_range | 0.0748 | +| entropy_loss | -5.72 | +| explained_variance | 0.208 | +| learning_rate | 4.98e-05 | +| loss | -0.0354 | +| n_updates | 36716 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000402 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.0573 | +| time/ | | +| fps | 1299 | +| iterations | 344 | +| time_elapsed | 542 | +| total_timesteps | 704512 | +| train/ | | +| approx_kl | 0.02073829 | +| clip_fraction | 0.414 | +| clip_range | 0.0748 | +| entropy_loss | -6.05 | +| explained_variance | 0.165 | +| learning_rate | 4.98e-05 | +| loss | -0.0367 | +| n_updates | 36720 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000293 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.0707 | +| time/ | | +| fps | 1299 | +| iterations | 345 | +| time_elapsed | 543 | +| total_timesteps | 706560 | +| train/ | | +| approx_kl | 0.020762904 | +| clip_fraction | 0.389 | +| clip_range | 0.0748 | +| entropy_loss | -6.44 | +| explained_variance | -0.101 | +| learning_rate | 4.98e-05 | +| loss | -0.0329 | +| n_updates | 36724 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000325 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.0679 | +| time/ | | +| fps | 1299 | +| iterations | 346 | +| time_elapsed | 545 | +| total_timesteps | 708608 | +| train/ | | +| approx_kl | 0.020015795 | +| clip_fraction | 0.363 | +| clip_range | 0.0748 | +| entropy_loss | -5.89 | +| explained_variance | 0.417 | +| learning_rate | 4.98e-05 | +| loss | -0.0337 | +| n_updates | 36728 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000288 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.0607 | +| time/ | | +| fps | 1299 | +| iterations | 347 | +| time_elapsed | 546 | +| total_timesteps | 710656 | +| train/ | | +| approx_kl | 0.025010316 | +| clip_fraction | 0.409 | +| clip_range | 0.0748 | +| entropy_loss | -6.02 | +| explained_variance | -0.0593 | +| learning_rate | 4.98e-05 | +| loss | -0.0329 | +| n_updates | 36732 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.00024 | +----------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.0647 | +| time/ | | +| fps | 1299 | +| iterations | 348 | +| time_elapsed | 548 | +| total_timesteps | 712704 | +| train/ | | +| approx_kl | 0.020677 | +| clip_fraction | 0.407 | +| clip_range | 0.0748 | +| entropy_loss | -6.13 | +| explained_variance | 0.215 | +| learning_rate | 4.98e-05 | +| loss | -0.0386 | +| n_updates | 36736 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000304 | +-------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.065 | +| time/ | | +| fps | 1299 | +| iterations | 349 | +| time_elapsed | 549 | +| total_timesteps | 714752 | +| train/ | | +| approx_kl | 0.02032902 | +| clip_fraction | 0.393 | +| clip_range | 0.0748 | +| entropy_loss | -6.17 | +| explained_variance | 0.206 | +| learning_rate | 4.98e-05 | +| loss | -0.0286 | +| n_updates | 36740 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000282 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.065 | +| time/ | | +| fps | 1299 | +| iterations | 350 | +| time_elapsed | 551 | +| total_timesteps | 716800 | +| train/ | | +| approx_kl | 0.021322861 | +| clip_fraction | 0.392 | +| clip_range | 0.0748 | +| entropy_loss | -6.12 | +| explained_variance | -0.0361 | +| learning_rate | 4.98e-05 | +| loss | -0.0338 | +| n_updates | 36744 | +| policy_gradient_loss | -0.0233 | +| value_loss | 0.000261 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.39e+03 | +| ep_rew_mean | 0.065 | +| time/ | | +| fps | 1299 | +| iterations | 351 | +| time_elapsed | 553 | +| total_timesteps | 718848 | +| train/ | | +| approx_kl | 0.019737449 | +| clip_fraction | 0.403 | +| clip_range | 0.0748 | +| entropy_loss | -6.33 | +| explained_variance | 0.153 | +| learning_rate | 4.98e-05 | +| loss | -0.0346 | +| n_updates | 36748 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000313 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.0684 | +| time/ | | +| fps | 1299 | +| iterations | 352 | +| time_elapsed | 554 | +| total_timesteps | 720896 | +| train/ | | +| approx_kl | 0.020415425 | +| clip_fraction | 0.405 | +| clip_range | 0.0748 | +| entropy_loss | -6.37 | +| explained_variance | -0.0884 | +| learning_rate | 4.98e-05 | +| loss | -0.039 | +| n_updates | 36752 | +| policy_gradient_loss | -0.0235 | +| value_loss | 0.000272 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.0731 | +| time/ | | +| fps | 1299 | +| iterations | 353 | +| time_elapsed | 556 | +| total_timesteps | 722944 | +| train/ | | +| approx_kl | 0.018426372 | +| clip_fraction | 0.422 | +| clip_range | 0.0748 | +| entropy_loss | -6.47 | +| explained_variance | 0.0845 | +| learning_rate | 4.98e-05 | +| loss | -0.0346 | +| n_updates | 36756 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000301 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.0768 | +| time/ | | +| fps | 1299 | +| iterations | 354 | +| time_elapsed | 557 | +| total_timesteps | 724992 | +| train/ | | +| approx_kl | 0.019473225 | +| clip_fraction | 0.415 | +| clip_range | 0.0748 | +| entropy_loss | -5.84 | +| explained_variance | 0.416 | +| learning_rate | 4.98e-05 | +| loss | -0.0339 | +| n_updates | 36760 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000248 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.075 | +| time/ | | +| fps | 1299 | +| iterations | 355 | +| time_elapsed | 559 | +| total_timesteps | 727040 | +| train/ | | +| approx_kl | 0.01968651 | +| clip_fraction | 0.434 | +| clip_range | 0.0748 | +| entropy_loss | -6.04 | +| explained_variance | 0.493 | +| learning_rate | 4.98e-05 | +| loss | -0.0369 | +| n_updates | 36764 | +| policy_gradient_loss | -0.0219 | +| value_loss | 0.000193 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0777 | +| time/ | | +| fps | 1299 | +| iterations | 356 | +| time_elapsed | 561 | +| total_timesteps | 729088 | +| train/ | | +| approx_kl | 0.019608308 | +| clip_fraction | 0.415 | +| clip_range | 0.0748 | +| entropy_loss | -5.95 | +| explained_variance | 0.458 | +| learning_rate | 4.98e-05 | +| loss | -0.0285 | +| n_updates | 36768 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000253 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0775 | +| time/ | | +| fps | 1299 | +| iterations | 357 | +| time_elapsed | 562 | +| total_timesteps | 731136 | +| train/ | | +| approx_kl | 0.019001104 | +| clip_fraction | 0.418 | +| clip_range | 0.0748 | +| entropy_loss | -6 | +| explained_variance | 0.322 | +| learning_rate | 4.98e-05 | +| loss | -0.0319 | +| n_updates | 36772 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000263 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0739 | +| time/ | | +| fps | 1299 | +| iterations | 358 | +| time_elapsed | 564 | +| total_timesteps | 733184 | +| train/ | | +| approx_kl | 0.017553892 | +| clip_fraction | 0.41 | +| clip_range | 0.0748 | +| entropy_loss | -6.18 | +| explained_variance | 0.0913 | +| learning_rate | 4.98e-05 | +| loss | -0.0358 | +| n_updates | 36776 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000329 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.067 | +| time/ | | +| fps | 1299 | +| iterations | 359 | +| time_elapsed | 565 | +| total_timesteps | 735232 | +| train/ | | +| approx_kl | 0.019984387 | +| clip_fraction | 0.403 | +| clip_range | 0.0748 | +| entropy_loss | -6.24 | +| explained_variance | 0.165 | +| learning_rate | 4.98e-05 | +| loss | -0.0308 | +| n_updates | 36780 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000366 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0674 | +| time/ | | +| fps | 1299 | +| iterations | 360 | +| time_elapsed | 567 | +| total_timesteps | 737280 | +| train/ | | +| approx_kl | 0.017935459 | +| clip_fraction | 0.401 | +| clip_range | 0.0748 | +| entropy_loss | -5.89 | +| explained_variance | 0.348 | +| learning_rate | 4.98e-05 | +| loss | -0.0311 | +| n_updates | 36784 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000235 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0714 | +| time/ | | +| fps | 1299 | +| iterations | 361 | +| time_elapsed | 568 | +| total_timesteps | 739328 | +| train/ | | +| approx_kl | 0.019695025 | +| clip_fraction | 0.379 | +| clip_range | 0.0748 | +| entropy_loss | -6.28 | +| explained_variance | 0.0262 | +| learning_rate | 4.98e-05 | +| loss | -0.0327 | +| n_updates | 36788 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000219 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0682 | +| time/ | | +| fps | 1299 | +| iterations | 362 | +| time_elapsed | 570 | +| total_timesteps | 741376 | +| train/ | | +| approx_kl | 0.019256532 | +| clip_fraction | 0.429 | +| clip_range | 0.0748 | +| entropy_loss | -6.02 | +| explained_variance | 0.312 | +| learning_rate | 4.98e-05 | +| loss | -0.0319 | +| n_updates | 36792 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000251 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0724 | +| time/ | | +| fps | 1299 | +| iterations | 363 | +| time_elapsed | 572 | +| total_timesteps | 743424 | +| train/ | | +| approx_kl | 0.019577526 | +| clip_fraction | 0.397 | +| clip_range | 0.0748 | +| entropy_loss | -6.17 | +| explained_variance | 0.106 | +| learning_rate | 4.98e-05 | +| loss | -0.039 | +| n_updates | 36796 | +| policy_gradient_loss | -0.0219 | +| value_loss | 0.000353 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0713 | +| time/ | | +| fps | 1299 | +| iterations | 364 | +| time_elapsed | 573 | +| total_timesteps | 745472 | +| train/ | | +| approx_kl | 0.0161517 | +| clip_fraction | 0.364 | +| clip_range | 0.0748 | +| entropy_loss | -6.02 | +| explained_variance | 0.23 | +| learning_rate | 4.98e-05 | +| loss | -0.0319 | +| n_updates | 36800 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000396 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0841 | +| time/ | | +| fps | 1299 | +| iterations | 365 | +| time_elapsed | 575 | +| total_timesteps | 747520 | +| train/ | | +| approx_kl | 0.017631661 | +| clip_fraction | 0.41 | +| clip_range | 0.0748 | +| entropy_loss | -5.93 | +| explained_variance | 0.0708 | +| learning_rate | 4.98e-05 | +| loss | -0.0359 | +| n_updates | 36804 | +| policy_gradient_loss | -0.0236 | +| value_loss | 0.000282 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0757 | +| time/ | | +| fps | 1299 | +| iterations | 366 | +| time_elapsed | 576 | +| total_timesteps | 749568 | +| train/ | | +| approx_kl | 0.018917186 | +| clip_fraction | 0.414 | +| clip_range | 0.0748 | +| entropy_loss | -5.95 | +| explained_variance | 0.337 | +| learning_rate | 4.98e-05 | +| loss | -0.0367 | +| n_updates | 36808 | +| policy_gradient_loss | -0.0232 | +| value_loss | 0.000242 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0774 | +| time/ | | +| fps | 1299 | +| iterations | 367 | +| time_elapsed | 578 | +| total_timesteps | 751616 | +| train/ | | +| approx_kl | 0.017690405 | +| clip_fraction | 0.385 | +| clip_range | 0.0748 | +| entropy_loss | -6.15 | +| explained_variance | -0.0753 | +| learning_rate | 4.98e-05 | +| loss | -0.0332 | +| n_updates | 36812 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000237 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0774 | +| time/ | | +| fps | 1300 | +| iterations | 368 | +| time_elapsed | 579 | +| total_timesteps | 753664 | +| train/ | | +| approx_kl | 0.01719094 | +| clip_fraction | 0.371 | +| clip_range | 0.0748 | +| entropy_loss | -5.89 | +| explained_variance | 0.412 | +| learning_rate | 4.98e-05 | +| loss | -0.0301 | +| n_updates | 36816 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.00027 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0781 | +| time/ | | +| fps | 1300 | +| iterations | 369 | +| time_elapsed | 581 | +| total_timesteps | 755712 | +| train/ | | +| approx_kl | 0.02118998 | +| clip_fraction | 0.409 | +| clip_range | 0.0748 | +| entropy_loss | -6.08 | +| explained_variance | -0.0138 | +| learning_rate | 4.98e-05 | +| loss | -0.0376 | +| n_updates | 36820 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000281 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0749 | +| time/ | | +| fps | 1300 | +| iterations | 370 | +| time_elapsed | 582 | +| total_timesteps | 757760 | +| train/ | | +| approx_kl | 0.01885229 | +| clip_fraction | 0.402 | +| clip_range | 0.0748 | +| entropy_loss | -6.07 | +| explained_variance | 0.179 | +| learning_rate | 4.98e-05 | +| loss | -0.034 | +| n_updates | 36824 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000242 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0795 | +| time/ | | +| fps | 1300 | +| iterations | 371 | +| time_elapsed | 584 | +| total_timesteps | 759808 | +| train/ | | +| approx_kl | 0.019889574 | +| clip_fraction | 0.417 | +| clip_range | 0.0748 | +| entropy_loss | -6.3 | +| explained_variance | 0.0106 | +| learning_rate | 4.98e-05 | +| loss | -0.0319 | +| n_updates | 36828 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000272 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0779 | +| time/ | | +| fps | 1300 | +| iterations | 372 | +| time_elapsed | 585 | +| total_timesteps | 761856 | +| train/ | | +| approx_kl | 0.01773494 | +| clip_fraction | 0.388 | +| clip_range | 0.0748 | +| entropy_loss | -6.02 | +| explained_variance | 0.205 | +| learning_rate | 4.98e-05 | +| loss | -0.0375 | +| n_updates | 36832 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000327 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0771 | +| time/ | | +| fps | 1300 | +| iterations | 373 | +| time_elapsed | 587 | +| total_timesteps | 763904 | +| train/ | | +| approx_kl | 0.02122509 | +| clip_fraction | 0.427 | +| clip_range | 0.0748 | +| entropy_loss | -6.1 | +| explained_variance | 0.343 | +| learning_rate | 4.98e-05 | +| loss | -0.034 | +| n_updates | 36836 | +| policy_gradient_loss | -0.0225 | +| value_loss | 0.000213 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0742 | +| time/ | | +| fps | 1300 | +| iterations | 374 | +| time_elapsed | 589 | +| total_timesteps | 765952 | +| train/ | | +| approx_kl | 0.020918602 | +| clip_fraction | 0.396 | +| clip_range | 0.0748 | +| entropy_loss | -6.13 | +| explained_variance | -0.177 | +| learning_rate | 4.98e-05 | +| loss | -0.0341 | +| n_updates | 36840 | +| policy_gradient_loss | -0.0228 | +| value_loss | 0.000234 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0755 | +| time/ | | +| fps | 1300 | +| iterations | 375 | +| time_elapsed | 590 | +| total_timesteps | 768000 | +| train/ | | +| approx_kl | 0.020005919 | +| clip_fraction | 0.395 | +| clip_range | 0.0748 | +| entropy_loss | -5.82 | +| explained_variance | 0.415 | +| learning_rate | 4.98e-05 | +| loss | -0.0308 | +| n_updates | 36844 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000313 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0728 | +| time/ | | +| fps | 1300 | +| iterations | 376 | +| time_elapsed | 592 | +| total_timesteps | 770048 | +| train/ | | +| approx_kl | 0.02190248 | +| clip_fraction | 0.396 | +| clip_range | 0.0748 | +| entropy_loss | -5.76 | +| explained_variance | 0.228 | +| learning_rate | 4.98e-05 | +| loss | -0.0337 | +| n_updates | 36848 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000224 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.0772 | +| time/ | | +| fps | 1300 | +| iterations | 377 | +| time_elapsed | 593 | +| total_timesteps | 772096 | +| train/ | | +| approx_kl | 0.02040273 | +| clip_fraction | 0.407 | +| clip_range | 0.0748 | +| entropy_loss | -5.94 | +| explained_variance | 0.258 | +| learning_rate | 4.98e-05 | +| loss | -0.037 | +| n_updates | 36852 | +| policy_gradient_loss | -0.0219 | +| value_loss | 0.000141 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0752 | +| time/ | | +| fps | 1300 | +| iterations | 378 | +| time_elapsed | 595 | +| total_timesteps | 774144 | +| train/ | | +| approx_kl | 0.01921906 | +| clip_fraction | 0.366 | +| clip_range | 0.0748 | +| entropy_loss | -5.97 | +| explained_variance | 0.0545 | +| learning_rate | 4.98e-05 | +| loss | -0.0288 | +| n_updates | 36856 | +| policy_gradient_loss | -0.0149 | +| value_loss | 0.000915 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0786 | +| time/ | | +| fps | 1300 | +| iterations | 379 | +| time_elapsed | 596 | +| total_timesteps | 776192 | +| train/ | | +| approx_kl | 0.02039666 | +| clip_fraction | 0.405 | +| clip_range | 0.0748 | +| entropy_loss | -5.96 | +| explained_variance | 0.193 | +| learning_rate | 4.98e-05 | +| loss | -0.044 | +| n_updates | 36860 | +| policy_gradient_loss | -0.0259 | +| value_loss | 0.000229 | +---------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0771 | +| time/ | | +| fps | 1300 | +| iterations | 380 | +| time_elapsed | 598 | +| total_timesteps | 778240 | +| train/ | | +| approx_kl | 0.0220408 | +| clip_fraction | 0.437 | +| clip_range | 0.0748 | +| entropy_loss | -5.81 | +| explained_variance | 0.319 | +| learning_rate | 4.98e-05 | +| loss | -0.0363 | +| n_updates | 36864 | +| policy_gradient_loss | -0.023 | +| value_loss | 0.000233 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.076 | +| time/ | | +| fps | 1300 | +| iterations | 381 | +| time_elapsed | 600 | +| total_timesteps | 780288 | +| train/ | | +| approx_kl | 0.018229233 | +| clip_fraction | 0.392 | +| clip_range | 0.0748 | +| entropy_loss | -5.75 | +| explained_variance | 0.357 | +| learning_rate | 4.98e-05 | +| loss | -0.0344 | +| n_updates | 36868 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000323 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.076 | +| time/ | | +| fps | 1300 | +| iterations | 382 | +| time_elapsed | 601 | +| total_timesteps | 782336 | +| train/ | | +| approx_kl | 0.021206602 | +| clip_fraction | 0.414 | +| clip_range | 0.0748 | +| entropy_loss | -6.25 | +| explained_variance | -0.218 | +| learning_rate | 4.98e-05 | +| loss | -0.0367 | +| n_updates | 36872 | +| policy_gradient_loss | -0.024 | +| value_loss | 0.000162 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0836 | +| time/ | | +| fps | 1300 | +| iterations | 383 | +| time_elapsed | 603 | +| total_timesteps | 784384 | +| train/ | | +| approx_kl | 0.021396335 | +| clip_fraction | 0.388 | +| clip_range | 0.0748 | +| entropy_loss | -6.23 | +| explained_variance | 0.186 | +| learning_rate | 4.98e-05 | +| loss | -0.03 | +| n_updates | 36876 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000326 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0866 | +| time/ | | +| fps | 1300 | +| iterations | 384 | +| time_elapsed | 604 | +| total_timesteps | 786432 | +| train/ | | +| approx_kl | 0.01960966 | +| clip_fraction | 0.402 | +| clip_range | 0.0748 | +| entropy_loss | -6.33 | +| explained_variance | 0.00204 | +| learning_rate | 4.98e-05 | +| loss | -0.0335 | +| n_updates | 36880 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000327 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0873 | +| time/ | | +| fps | 1300 | +| iterations | 385 | +| time_elapsed | 606 | +| total_timesteps | 788480 | +| train/ | | +| approx_kl | 0.01968534 | +| clip_fraction | 0.409 | +| clip_range | 0.0748 | +| entropy_loss | -5.36 | +| explained_variance | 0.473 | +| learning_rate | 4.98e-05 | +| loss | -0.0334 | +| n_updates | 36884 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000315 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.0866 | +| time/ | | +| fps | 1300 | +| iterations | 386 | +| time_elapsed | 607 | +| total_timesteps | 790528 | +| train/ | | +| approx_kl | 0.021497581 | +| clip_fraction | 0.423 | +| clip_range | 0.0748 | +| entropy_loss | -6.01 | +| explained_variance | -0.284 | +| learning_rate | 4.98e-05 | +| loss | -0.0413 | +| n_updates | 36888 | +| policy_gradient_loss | -0.0222 | +| value_loss | 0.000192 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.0866 | +| time/ | | +| fps | 1300 | +| iterations | 387 | +| time_elapsed | 609 | +| total_timesteps | 792576 | +| train/ | | +| approx_kl | 0.020886183 | +| clip_fraction | 0.417 | +| clip_range | 0.0748 | +| entropy_loss | -5.8 | +| explained_variance | 0.495 | +| learning_rate | 4.98e-05 | +| loss | -0.0355 | +| n_updates | 36892 | +| policy_gradient_loss | -0.022 | +| value_loss | 0.000142 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.0864 | +| time/ | | +| fps | 1300 | +| iterations | 388 | +| time_elapsed | 610 | +| total_timesteps | 794624 | +| train/ | | +| approx_kl | 0.020538906 | +| clip_fraction | 0.421 | +| clip_range | 0.0748 | +| entropy_loss | -6.08 | +| explained_variance | 0.111 | +| learning_rate | 4.98e-05 | +| loss | -0.035 | +| n_updates | 36896 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.00032 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0778 | +| time/ | | +| fps | 1300 | +| iterations | 389 | +| time_elapsed | 612 | +| total_timesteps | 796672 | +| train/ | | +| approx_kl | 0.022706665 | +| clip_fraction | 0.431 | +| clip_range | 0.0748 | +| entropy_loss | -6.07 | +| explained_variance | -0.0838 | +| learning_rate | 4.98e-05 | +| loss | -0.0345 | +| n_updates | 36900 | +| policy_gradient_loss | -0.0221 | +| value_loss | 0.000235 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.078 | +| time/ | | +| fps | 1300 | +| iterations | 390 | +| time_elapsed | 614 | +| total_timesteps | 798720 | +| train/ | | +| approx_kl | 0.023037825 | +| clip_fraction | 0.415 | +| clip_range | 0.0748 | +| entropy_loss | -5.96 | +| explained_variance | 0.352 | +| learning_rate | 4.98e-05 | +| loss | -0.0319 | +| n_updates | 36904 | +| policy_gradient_loss | -0.022 | +| value_loss | 0.000224 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0808 | +| time/ | | +| fps | 1300 | +| iterations | 391 | +| time_elapsed | 615 | +| total_timesteps | 800768 | +| train/ | | +| approx_kl | 0.022995736 | +| clip_fraction | 0.408 | +| clip_range | 0.0748 | +| entropy_loss | -5.52 | +| explained_variance | 0.411 | +| learning_rate | 4.98e-05 | +| loss | -0.0237 | +| n_updates | 36908 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000348 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0808 | +| time/ | | +| fps | 1300 | +| iterations | 392 | +| time_elapsed | 617 | +| total_timesteps | 802816 | +| train/ | | +| approx_kl | 0.021678142 | +| clip_fraction | 0.389 | +| clip_range | 0.0748 | +| entropy_loss | -5.93 | +| explained_variance | 0.157 | +| learning_rate | 4.98e-05 | +| loss | -0.0324 | +| n_updates | 36912 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000324 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0691 | +| time/ | | +| fps | 1300 | +| iterations | 393 | +| time_elapsed | 618 | +| total_timesteps | 804864 | +| train/ | | +| approx_kl | 0.020752085 | +| clip_fraction | 0.417 | +| clip_range | 0.0748 | +| entropy_loss | -6.08 | +| explained_variance | 0.132 | +| learning_rate | 4.98e-05 | +| loss | -0.0342 | +| n_updates | 36916 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000341 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0814 | +| time/ | | +| fps | 1300 | +| iterations | 394 | +| time_elapsed | 620 | +| total_timesteps | 806912 | +| train/ | | +| approx_kl | 0.020614896 | +| clip_fraction | 0.411 | +| clip_range | 0.0748 | +| entropy_loss | -5.87 | +| explained_variance | 0.435 | +| learning_rate | 4.98e-05 | +| loss | -0.0329 | +| n_updates | 36920 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.00023 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0814 | +| time/ | | +| fps | 1300 | +| iterations | 395 | +| time_elapsed | 622 | +| total_timesteps | 808960 | +| train/ | | +| approx_kl | 0.015940484 | +| clip_fraction | 0.367 | +| clip_range | 0.0748 | +| entropy_loss | -5.62 | +| explained_variance | 0.196 | +| learning_rate | 4.98e-05 | +| loss | -0.0222 | +| n_updates | 36924 | +| policy_gradient_loss | -0.0145 | +| value_loss | 0.000814 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0794 | +| time/ | | +| fps | 1300 | +| iterations | 396 | +| time_elapsed | 623 | +| total_timesteps | 811008 | +| train/ | | +| approx_kl | 0.022899885 | +| clip_fraction | 0.442 | +| clip_range | 0.0748 | +| entropy_loss | -5.74 | +| explained_variance | 0.039 | +| learning_rate | 4.98e-05 | +| loss | -0.0381 | +| n_updates | 36928 | +| policy_gradient_loss | -0.022 | +| value_loss | 0.000238 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0775 | +| time/ | | +| fps | 1300 | +| iterations | 397 | +| time_elapsed | 625 | +| total_timesteps | 813056 | +| train/ | | +| approx_kl | 0.02227594 | +| clip_fraction | 0.435 | +| clip_range | 0.0748 | +| entropy_loss | -5.9 | +| explained_variance | 0.2 | +| learning_rate | 4.98e-05 | +| loss | -0.0374 | +| n_updates | 36932 | +| policy_gradient_loss | -0.024 | +| value_loss | 0.00021 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0768 | +| time/ | | +| fps | 1300 | +| iterations | 398 | +| time_elapsed | 626 | +| total_timesteps | 815104 | +| train/ | | +| approx_kl | 0.019569747 | +| clip_fraction | 0.41 | +| clip_range | 0.0748 | +| entropy_loss | -5.67 | +| explained_variance | 0.318 | +| learning_rate | 4.98e-05 | +| loss | -0.0296 | +| n_updates | 36936 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000231 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0768 | +| time/ | | +| fps | 1300 | +| iterations | 399 | +| time_elapsed | 628 | +| total_timesteps | 817152 | +| train/ | | +| approx_kl | 0.021644993 | +| clip_fraction | 0.419 | +| clip_range | 0.0748 | +| entropy_loss | -5.88 | +| explained_variance | 0.227 | +| learning_rate | 4.98e-05 | +| loss | -0.0347 | +| n_updates | 36940 | +| policy_gradient_loss | -0.0222 | +| value_loss | 0.000278 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0768 | +| time/ | | +| fps | 1300 | +| iterations | 400 | +| time_elapsed | 630 | +| total_timesteps | 819200 | +| train/ | | +| approx_kl | 0.022078589 | +| clip_fraction | 0.415 | +| clip_range | 0.0748 | +| entropy_loss | -5.97 | +| explained_variance | -0.0652 | +| learning_rate | 4.98e-05 | +| loss | -0.0334 | +| n_updates | 36944 | +| policy_gradient_loss | -0.0221 | +| value_loss | 0.000216 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0779 | +| time/ | | +| fps | 1300 | +| iterations | 401 | +| time_elapsed | 631 | +| total_timesteps | 821248 | +| train/ | | +| approx_kl | 0.019343916 | +| clip_fraction | 0.403 | +| clip_range | 0.0748 | +| entropy_loss | -6.28 | +| explained_variance | 0.0091 | +| learning_rate | 4.98e-05 | +| loss | -0.0348 | +| n_updates | 36948 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000443 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0772 | +| time/ | | +| fps | 1300 | +| iterations | 402 | +| time_elapsed | 633 | +| total_timesteps | 823296 | +| train/ | | +| approx_kl | 0.018663296 | +| clip_fraction | 0.397 | +| clip_range | 0.0748 | +| entropy_loss | -6.16 | +| explained_variance | -0.149 | +| learning_rate | 4.98e-05 | +| loss | -0.0345 | +| n_updates | 36952 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000315 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0805 | +| time/ | | +| fps | 1300 | +| iterations | 403 | +| time_elapsed | 634 | +| total_timesteps | 825344 | +| train/ | | +| approx_kl | 0.017913952 | +| clip_fraction | 0.4 | +| clip_range | 0.0748 | +| entropy_loss | -5.86 | +| explained_variance | 0.372 | +| learning_rate | 4.98e-05 | +| loss | -0.033 | +| n_updates | 36956 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000311 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0831 | +| time/ | | +| fps | 1300 | +| iterations | 404 | +| time_elapsed | 636 | +| total_timesteps | 827392 | +| train/ | | +| approx_kl | 0.01713052 | +| clip_fraction | 0.426 | +| clip_range | 0.0748 | +| entropy_loss | -5.66 | +| explained_variance | 0.433 | +| learning_rate | 4.98e-05 | +| loss | -0.0358 | +| n_updates | 36960 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000171 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0832 | +| time/ | | +| fps | 1300 | +| iterations | 405 | +| time_elapsed | 637 | +| total_timesteps | 829440 | +| train/ | | +| approx_kl | 0.018024746 | +| clip_fraction | 0.4 | +| clip_range | 0.0748 | +| entropy_loss | -5.85 | +| explained_variance | -0.644 | +| learning_rate | 4.98e-05 | +| loss | -0.0295 | +| n_updates | 36964 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000242 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0778 | +| time/ | | +| fps | 1300 | +| iterations | 406 | +| time_elapsed | 639 | +| total_timesteps | 831488 | +| train/ | | +| approx_kl | 0.019930307 | +| clip_fraction | 0.402 | +| clip_range | 0.0748 | +| entropy_loss | -5.79 | +| explained_variance | -0.159 | +| learning_rate | 4.98e-05 | +| loss | -0.032 | +| n_updates | 36968 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000308 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0775 | +| time/ | | +| fps | 1300 | +| iterations | 407 | +| time_elapsed | 641 | +| total_timesteps | 833536 | +| train/ | | +| approx_kl | 0.01984882 | +| clip_fraction | 0.415 | +| clip_range | 0.0748 | +| entropy_loss | -5.52 | +| explained_variance | 0.26 | +| learning_rate | 4.98e-05 | +| loss | -0.0202 | +| n_updates | 36972 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.000285 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0775 | +| time/ | | +| fps | 1300 | +| iterations | 408 | +| time_elapsed | 642 | +| total_timesteps | 835584 | +| train/ | | +| approx_kl | 0.01795882 | +| clip_fraction | 0.41 | +| clip_range | 0.0748 | +| entropy_loss | -6.02 | +| explained_variance | 0.088 | +| learning_rate | 4.98e-05 | +| loss | -0.0324 | +| n_updates | 36976 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000391 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0761 | +| time/ | | +| fps | 1300 | +| iterations | 409 | +| time_elapsed | 644 | +| total_timesteps | 837632 | +| train/ | | +| approx_kl | 0.019181704 | +| clip_fraction | 0.412 | +| clip_range | 0.0748 | +| entropy_loss | -6 | +| explained_variance | -0.101 | +| learning_rate | 4.98e-05 | +| loss | -0.0351 | +| n_updates | 36980 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000243 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0801 | +| time/ | | +| fps | 1300 | +| iterations | 410 | +| time_elapsed | 645 | +| total_timesteps | 839680 | +| train/ | | +| approx_kl | 0.018562667 | +| clip_fraction | 0.409 | +| clip_range | 0.0748 | +| entropy_loss | -6.2 | +| explained_variance | 0.155 | +| learning_rate | 4.98e-05 | +| loss | -0.0329 | +| n_updates | 36984 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.00031 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0877 | +| time/ | | +| fps | 1300 | +| iterations | 411 | +| time_elapsed | 647 | +| total_timesteps | 841728 | +| train/ | | +| approx_kl | 0.016184337 | +| clip_fraction | 0.376 | +| clip_range | 0.0748 | +| entropy_loss | -5.99 | +| explained_variance | 0.212 | +| learning_rate | 4.98e-05 | +| loss | -0.0314 | +| n_updates | 36988 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.00044 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0874 | +| time/ | | +| fps | 1299 | +| iterations | 412 | +| time_elapsed | 649 | +| total_timesteps | 843776 | +| train/ | | +| approx_kl | 0.021936022 | +| clip_fraction | 0.426 | +| clip_range | 0.0748 | +| entropy_loss | -5.84 | +| explained_variance | 0.299 | +| learning_rate | 4.98e-05 | +| loss | -0.0332 | +| n_updates | 36992 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000277 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0877 | +| time/ | | +| fps | 1300 | +| iterations | 413 | +| time_elapsed | 650 | +| total_timesteps | 845824 | +| train/ | | +| approx_kl | 0.022030372 | +| clip_fraction | 0.42 | +| clip_range | 0.0748 | +| entropy_loss | -5.55 | +| explained_variance | 0.46 | +| learning_rate | 4.98e-05 | +| loss | -0.0307 | +| n_updates | 36996 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.00025 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0872 | +| time/ | | +| fps | 1300 | +| iterations | 414 | +| time_elapsed | 652 | +| total_timesteps | 847872 | +| train/ | | +| approx_kl | 0.022620868 | +| clip_fraction | 0.43 | +| clip_range | 0.0748 | +| entropy_loss | -5.65 | +| explained_variance | 0.393 | +| learning_rate | 4.98e-05 | +| loss | -0.0312 | +| n_updates | 37000 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000222 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0897 | +| time/ | | +| fps | 1300 | +| iterations | 415 | +| time_elapsed | 653 | +| total_timesteps | 849920 | +| train/ | | +| approx_kl | 0.021896228 | +| clip_fraction | 0.449 | +| clip_range | 0.0748 | +| entropy_loss | -5.71 | +| explained_variance | 0.278 | +| learning_rate | 4.98e-05 | +| loss | -0.0296 | +| n_updates | 37004 | +| policy_gradient_loss | -0.0237 | +| value_loss | 0.000157 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0916 | +| time/ | | +| fps | 1299 | +| iterations | 416 | +| time_elapsed | 655 | +| total_timesteps | 851968 | +| train/ | | +| approx_kl | 0.02076009 | +| clip_fraction | 0.424 | +| clip_range | 0.0748 | +| entropy_loss | -5.91 | +| explained_variance | 0.156 | +| learning_rate | 4.98e-05 | +| loss | -0.0334 | +| n_updates | 37008 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000347 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0902 | +| time/ | | +| fps | 1300 | +| iterations | 417 | +| time_elapsed | 656 | +| total_timesteps | 854016 | +| train/ | | +| approx_kl | 0.025028786 | +| clip_fraction | 0.405 | +| clip_range | 0.0748 | +| entropy_loss | -5.68 | +| explained_variance | 0.172 | +| learning_rate | 4.98e-05 | +| loss | -0.025 | +| n_updates | 37012 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000409 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0891 | +| time/ | | +| fps | 1300 | +| iterations | 418 | +| time_elapsed | 658 | +| total_timesteps | 856064 | +| train/ | | +| approx_kl | 0.019639233 | +| clip_fraction | 0.416 | +| clip_range | 0.0748 | +| entropy_loss | -5.78 | +| explained_variance | -0.0214 | +| learning_rate | 4.98e-05 | +| loss | -0.0349 | +| n_updates | 37016 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000248 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0923 | +| time/ | | +| fps | 1300 | +| iterations | 419 | +| time_elapsed | 659 | +| total_timesteps | 858112 | +| train/ | | +| approx_kl | 0.023038901 | +| clip_fraction | 0.443 | +| clip_range | 0.0748 | +| entropy_loss | -5.74 | +| explained_variance | -0.65 | +| learning_rate | 4.98e-05 | +| loss | -0.0428 | +| n_updates | 37020 | +| policy_gradient_loss | -0.0252 | +| value_loss | 8.56e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0923 | +| time/ | | +| fps | 1300 | +| iterations | 420 | +| time_elapsed | 661 | +| total_timesteps | 860160 | +| train/ | | +| approx_kl | 0.019872282 | +| clip_fraction | 0.415 | +| clip_range | 0.0748 | +| entropy_loss | -5.73 | +| explained_variance | 0.255 | +| learning_rate | 4.98e-05 | +| loss | -0.0267 | +| n_updates | 37024 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000227 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0953 | +| time/ | | +| fps | 1300 | +| iterations | 421 | +| time_elapsed | 663 | +| total_timesteps | 862208 | +| train/ | | +| approx_kl | 0.019703247 | +| clip_fraction | 0.406 | +| clip_range | 0.0748 | +| entropy_loss | -5.89 | +| explained_variance | 0.243 | +| learning_rate | 4.98e-05 | +| loss | -0.0289 | +| n_updates | 37028 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000249 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0955 | +| time/ | | +| fps | 1300 | +| iterations | 422 | +| time_elapsed | 664 | +| total_timesteps | 864256 | +| train/ | | +| approx_kl | 0.019707862 | +| clip_fraction | 0.41 | +| clip_range | 0.0748 | +| entropy_loss | -6.06 | +| explained_variance | 0.0477 | +| learning_rate | 4.98e-05 | +| loss | -0.0291 | +| n_updates | 37032 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000452 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0958 | +| time/ | | +| fps | 1300 | +| iterations | 423 | +| time_elapsed | 666 | +| total_timesteps | 866304 | +| train/ | | +| approx_kl | 0.020830955 | +| clip_fraction | 0.419 | +| clip_range | 0.0748 | +| entropy_loss | -5.55 | +| explained_variance | 0.475 | +| learning_rate | 4.98e-05 | +| loss | -0.0357 | +| n_updates | 37036 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000236 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0958 | +| time/ | | +| fps | 1300 | +| iterations | 424 | +| time_elapsed | 667 | +| total_timesteps | 868352 | +| train/ | | +| approx_kl | 0.017816445 | +| clip_fraction | 0.42 | +| clip_range | 0.0748 | +| entropy_loss | -5.95 | +| explained_variance | -0.0562 | +| learning_rate | 4.98e-05 | +| loss | -0.0353 | +| n_updates | 37040 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000249 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0985 | +| time/ | | +| fps | 1300 | +| iterations | 425 | +| time_elapsed | 669 | +| total_timesteps | 870400 | +| train/ | | +| approx_kl | 0.020172287 | +| clip_fraction | 0.412 | +| clip_range | 0.0748 | +| entropy_loss | -5.71 | +| explained_variance | 0.23 | +| learning_rate | 4.98e-05 | +| loss | -0.0352 | +| n_updates | 37044 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000249 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0985 | +| time/ | | +| fps | 1300 | +| iterations | 426 | +| time_elapsed | 670 | +| total_timesteps | 872448 | +| train/ | | +| approx_kl | 0.019883605 | +| clip_fraction | 0.398 | +| clip_range | 0.0748 | +| entropy_loss | -5.86 | +| explained_variance | 0.254 | +| learning_rate | 4.98e-05 | +| loss | -0.0314 | +| n_updates | 37048 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000219 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0998 | +| time/ | | +| fps | 1300 | +| iterations | 427 | +| time_elapsed | 672 | +| total_timesteps | 874496 | +| train/ | | +| approx_kl | 0.021699142 | +| clip_fraction | 0.397 | +| clip_range | 0.0748 | +| entropy_loss | -5.81 | +| explained_variance | 0.163 | +| learning_rate | 4.98e-05 | +| loss | -0.0302 | +| n_updates | 37052 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000255 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0862 | +| time/ | | +| fps | 1300 | +| iterations | 428 | +| time_elapsed | 673 | +| total_timesteps | 876544 | +| train/ | | +| approx_kl | 0.020808384 | +| clip_fraction | 0.404 | +| clip_range | 0.0748 | +| entropy_loss | -5.59 | +| explained_variance | 0.387 | +| learning_rate | 4.98e-05 | +| loss | -0.0319 | +| n_updates | 37056 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000235 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0812 | +| time/ | | +| fps | 1300 | +| iterations | 429 | +| time_elapsed | 675 | +| total_timesteps | 878592 | +| train/ | | +| approx_kl | 0.017797861 | +| clip_fraction | 0.427 | +| clip_range | 0.0748 | +| entropy_loss | -5.86 | +| explained_variance | 0.148 | +| learning_rate | 4.98e-05 | +| loss | -0.035 | +| n_updates | 37060 | +| policy_gradient_loss | -0.022 | +| value_loss | 0.000245 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.073 | +| time/ | | +| fps | 1300 | +| iterations | 430 | +| time_elapsed | 677 | +| total_timesteps | 880640 | +| train/ | | +| approx_kl | 0.017893868 | +| clip_fraction | 0.402 | +| clip_range | 0.0748 | +| entropy_loss | -5.73 | +| explained_variance | -0.382 | +| learning_rate | 4.98e-05 | +| loss | -0.0242 | +| n_updates | 37064 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000321 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.077 | +| time/ | | +| fps | 1300 | +| iterations | 431 | +| time_elapsed | 678 | +| total_timesteps | 882688 | +| train/ | | +| approx_kl | 0.020347755 | +| clip_fraction | 0.404 | +| clip_range | 0.0748 | +| entropy_loss | -5.78 | +| explained_variance | -0.00337 | +| learning_rate | 4.98e-05 | +| loss | -0.0329 | +| n_updates | 37068 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000212 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.077 | +| time/ | | +| fps | 1300 | +| iterations | 432 | +| time_elapsed | 680 | +| total_timesteps | 884736 | +| train/ | | +| approx_kl | 0.019667597 | +| clip_fraction | 0.394 | +| clip_range | 0.0748 | +| entropy_loss | -5.49 | +| explained_variance | 0.293 | +| learning_rate | 4.98e-05 | +| loss | -0.0306 | +| n_updates | 37072 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000245 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0715 | +| time/ | | +| fps | 1300 | +| iterations | 433 | +| time_elapsed | 681 | +| total_timesteps | 886784 | +| train/ | | +| approx_kl | 0.02138595 | +| clip_fraction | 0.419 | +| clip_range | 0.0748 | +| entropy_loss | -5.96 | +| explained_variance | -0.185 | +| learning_rate | 4.98e-05 | +| loss | -0.029 | +| n_updates | 37076 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000249 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0715 | +| time/ | | +| fps | 1300 | +| iterations | 434 | +| time_elapsed | 683 | +| total_timesteps | 888832 | +| train/ | | +| approx_kl | 0.02151867 | +| clip_fraction | 0.422 | +| clip_range | 0.0748 | +| entropy_loss | -5.66 | +| explained_variance | 0.0892 | +| learning_rate | 4.98e-05 | +| loss | -0.0352 | +| n_updates | 37080 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000262 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0728 | +| time/ | | +| fps | 1300 | +| iterations | 435 | +| time_elapsed | 685 | +| total_timesteps | 890880 | +| train/ | | +| approx_kl | 0.018574169 | +| clip_fraction | 0.406 | +| clip_range | 0.0748 | +| entropy_loss | -6.18 | +| explained_variance | -0.0764 | +| learning_rate | 4.98e-05 | +| loss | -0.0317 | +| n_updates | 37084 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000236 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0803 | +| time/ | | +| fps | 1300 | +| iterations | 436 | +| time_elapsed | 686 | +| total_timesteps | 892928 | +| train/ | | +| approx_kl | 0.021495517 | +| clip_fraction | 0.409 | +| clip_range | 0.0748 | +| entropy_loss | -5.65 | +| explained_variance | 0.249 | +| learning_rate | 4.98e-05 | +| loss | -0.0245 | +| n_updates | 37088 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000274 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0724 | +| time/ | | +| fps | 1300 | +| iterations | 437 | +| time_elapsed | 688 | +| total_timesteps | 894976 | +| train/ | | +| approx_kl | 0.020464547 | +| clip_fraction | 0.41 | +| clip_range | 0.0748 | +| entropy_loss | -5.83 | +| explained_variance | 0.23 | +| learning_rate | 4.98e-05 | +| loss | -0.0341 | +| n_updates | 37092 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000259 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0745 | +| time/ | | +| fps | 1300 | +| iterations | 438 | +| time_elapsed | 689 | +| total_timesteps | 897024 | +| train/ | | +| approx_kl | 0.02270199 | +| clip_fraction | 0.403 | +| clip_range | 0.0748 | +| entropy_loss | -5.56 | +| explained_variance | 0.139 | +| learning_rate | 4.98e-05 | +| loss | -0.0342 | +| n_updates | 37096 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.00039 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0748 | +| time/ | | +| fps | 1300 | +| iterations | 439 | +| time_elapsed | 691 | +| total_timesteps | 899072 | +| train/ | | +| approx_kl | 0.020376623 | +| clip_fraction | 0.385 | +| clip_range | 0.0748 | +| entropy_loss | -5.62 | +| explained_variance | 0.177 | +| learning_rate | 4.98e-05 | +| loss | -0.0333 | +| n_updates | 37100 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000331 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0661 | +| time/ | | +| fps | 1300 | +| iterations | 440 | +| time_elapsed | 692 | +| total_timesteps | 901120 | +| train/ | | +| approx_kl | 0.024093842 | +| clip_fraction | 0.423 | +| clip_range | 0.0748 | +| entropy_loss | -5.75 | +| explained_variance | 0.0862 | +| learning_rate | 4.98e-05 | +| loss | -0.0341 | +| n_updates | 37104 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.00024 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0661 | +| time/ | | +| fps | 1300 | +| iterations | 441 | +| time_elapsed | 694 | +| total_timesteps | 903168 | +| train/ | | +| approx_kl | 0.017867673 | +| clip_fraction | 0.394 | +| clip_range | 0.0748 | +| entropy_loss | -5.76 | +| explained_variance | 0.0797 | +| learning_rate | 4.98e-05 | +| loss | -0.0216 | +| n_updates | 37108 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000899 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0684 | +| time/ | | +| fps | 1300 | +| iterations | 442 | +| time_elapsed | 696 | +| total_timesteps | 905216 | +| train/ | | +| approx_kl | 0.020392288 | +| clip_fraction | 0.427 | +| clip_range | 0.0748 | +| entropy_loss | -5.81 | +| explained_variance | 0.204 | +| learning_rate | 4.98e-05 | +| loss | -0.0356 | +| n_updates | 37112 | +| policy_gradient_loss | -0.0244 | +| value_loss | 0.000369 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0613 | +| time/ | | +| fps | 1300 | +| iterations | 443 | +| time_elapsed | 697 | +| total_timesteps | 907264 | +| train/ | | +| approx_kl | 0.018598294 | +| clip_fraction | 0.387 | +| clip_range | 0.0748 | +| entropy_loss | -5.79 | +| explained_variance | 0.377 | +| learning_rate | 4.98e-05 | +| loss | -0.0316 | +| n_updates | 37116 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000242 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0662 | +| time/ | | +| fps | 1300 | +| iterations | 444 | +| time_elapsed | 699 | +| total_timesteps | 909312 | +| train/ | | +| approx_kl | 0.0207661 | +| clip_fraction | 0.423 | +| clip_range | 0.0748 | +| entropy_loss | -5.87 | +| explained_variance | 0.327 | +| learning_rate | 4.98e-05 | +| loss | -0.0383 | +| n_updates | 37120 | +| policy_gradient_loss | -0.023 | +| value_loss | 0.000225 | +--------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0662 | +| time/ | | +| fps | 1300 | +| iterations | 445 | +| time_elapsed | 700 | +| total_timesteps | 911360 | +| train/ | | +| approx_kl | 0.02256437 | +| clip_fraction | 0.402 | +| clip_range | 0.0748 | +| entropy_loss | -5.78 | +| explained_variance | 0.103 | +| learning_rate | 4.98e-05 | +| loss | -0.0341 | +| n_updates | 37124 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000295 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0735 | +| time/ | | +| fps | 1300 | +| iterations | 446 | +| time_elapsed | 702 | +| total_timesteps | 913408 | +| train/ | | +| approx_kl | 0.02063933 | +| clip_fraction | 0.41 | +| clip_range | 0.0748 | +| entropy_loss | -5.72 | +| explained_variance | 0.155 | +| learning_rate | 4.98e-05 | +| loss | -0.0347 | +| n_updates | 37128 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.00027 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.081 | +| time/ | | +| fps | 1300 | +| iterations | 447 | +| time_elapsed | 703 | +| total_timesteps | 915456 | +| train/ | | +| approx_kl | 0.020785075 | +| clip_fraction | 0.406 | +| clip_range | 0.0748 | +| entropy_loss | -5.76 | +| explained_variance | 0.275 | +| learning_rate | 4.98e-05 | +| loss | -0.0332 | +| n_updates | 37132 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000229 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.076 | +| time/ | | +| fps | 1300 | +| iterations | 448 | +| time_elapsed | 705 | +| total_timesteps | 917504 | +| train/ | | +| approx_kl | 0.014846219 | +| clip_fraction | 0.374 | +| clip_range | 0.0748 | +| entropy_loss | -5.65 | +| explained_variance | 0.198 | +| learning_rate | 4.98e-05 | +| loss | -0.0261 | +| n_updates | 37136 | +| policy_gradient_loss | -0.0133 | +| value_loss | 0.000773 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0775 | +| time/ | | +| fps | 1300 | +| iterations | 449 | +| time_elapsed | 706 | +| total_timesteps | 919552 | +| train/ | | +| approx_kl | 0.02019959 | +| clip_fraction | 0.424 | +| clip_range | 0.0748 | +| entropy_loss | -5.71 | +| explained_variance | 0.0906 | +| learning_rate | 4.98e-05 | +| loss | -0.0392 | +| n_updates | 37140 | +| policy_gradient_loss | -0.0249 | +| value_loss | 0.000304 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0775 | +| time/ | | +| fps | 1300 | +| iterations | 450 | +| time_elapsed | 708 | +| total_timesteps | 921600 | +| train/ | | +| approx_kl | 0.02048764 | +| clip_fraction | 0.4 | +| clip_range | 0.0748 | +| entropy_loss | -5.56 | +| explained_variance | 0.382 | +| learning_rate | 4.98e-05 | +| loss | -0.034 | +| n_updates | 37144 | +| policy_gradient_loss | -0.0231 | +| value_loss | 0.00021 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0776 | +| time/ | | +| fps | 1300 | +| iterations | 451 | +| time_elapsed | 709 | +| total_timesteps | 923648 | +| train/ | | +| approx_kl | 0.021651318 | +| clip_fraction | 0.44 | +| clip_range | 0.0748 | +| entropy_loss | -5.78 | +| explained_variance | 0.143 | +| learning_rate | 4.98e-05 | +| loss | -0.0408 | +| n_updates | 37148 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000241 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0776 | +| time/ | | +| fps | 1300 | +| iterations | 452 | +| time_elapsed | 711 | +| total_timesteps | 925696 | +| train/ | | +| approx_kl | 0.018890107 | +| clip_fraction | 0.417 | +| clip_range | 0.0748 | +| entropy_loss | -5.53 | +| explained_variance | 0.558 | +| learning_rate | 4.98e-05 | +| loss | -0.0324 | +| n_updates | 37152 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.00017 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0776 | +| time/ | | +| fps | 1301 | +| iterations | 453 | +| time_elapsed | 713 | +| total_timesteps | 927744 | +| train/ | | +| approx_kl | 0.019728884 | +| clip_fraction | 0.388 | +| clip_range | 0.0748 | +| entropy_loss | -5.83 | +| explained_variance | -0.0957 | +| learning_rate | 4.98e-05 | +| loss | -0.0307 | +| n_updates | 37156 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000301 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0758 | +| time/ | | +| fps | 1301 | +| iterations | 454 | +| time_elapsed | 714 | +| total_timesteps | 929792 | +| train/ | | +| approx_kl | 0.02048621 | +| clip_fraction | 0.416 | +| clip_range | 0.0748 | +| entropy_loss | -6.09 | +| explained_variance | -0.2 | +| learning_rate | 4.98e-05 | +| loss | -0.0389 | +| n_updates | 37160 | +| policy_gradient_loss | -0.0226 | +| value_loss | 0.000206 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0735 | +| time/ | | +| fps | 1301 | +| iterations | 455 | +| time_elapsed | 716 | +| total_timesteps | 931840 | +| train/ | | +| approx_kl | 0.021403674 | +| clip_fraction | 0.386 | +| clip_range | 0.0748 | +| entropy_loss | -5.9 | +| explained_variance | 0.171 | +| learning_rate | 4.98e-05 | +| loss | -0.0307 | +| n_updates | 37164 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.00029 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0814 | +| time/ | | +| fps | 1301 | +| iterations | 456 | +| time_elapsed | 717 | +| total_timesteps | 933888 | +| train/ | | +| approx_kl | 0.020636734 | +| clip_fraction | 0.418 | +| clip_range | 0.0748 | +| entropy_loss | -5.69 | +| explained_variance | 0.182 | +| learning_rate | 4.98e-05 | +| loss | -0.0345 | +| n_updates | 37168 | +| policy_gradient_loss | -0.0221 | +| value_loss | 0.000243 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0787 | +| time/ | | +| fps | 1301 | +| iterations | 457 | +| time_elapsed | 719 | +| total_timesteps | 935936 | +| train/ | | +| approx_kl | 0.021920273 | +| clip_fraction | 0.408 | +| clip_range | 0.0748 | +| entropy_loss | -5.41 | +| explained_variance | 0.0346 | +| learning_rate | 4.98e-05 | +| loss | -0.0238 | +| n_updates | 37172 | +| policy_gradient_loss | -0.0142 | +| value_loss | 0.00049 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0766 | +| time/ | | +| fps | 1301 | +| iterations | 458 | +| time_elapsed | 720 | +| total_timesteps | 937984 | +| train/ | | +| approx_kl | 0.018895933 | +| clip_fraction | 0.408 | +| clip_range | 0.0748 | +| entropy_loss | -5.56 | +| explained_variance | 0.142 | +| learning_rate | 4.98e-05 | +| loss | -0.032 | +| n_updates | 37176 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000339 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0805 | +| time/ | | +| fps | 1301 | +| iterations | 459 | +| time_elapsed | 722 | +| total_timesteps | 940032 | +| train/ | | +| approx_kl | 0.019771706 | +| clip_fraction | 0.451 | +| clip_range | 0.0748 | +| entropy_loss | -5.83 | +| explained_variance | 0.143 | +| learning_rate | 4.98e-05 | +| loss | -0.0387 | +| n_updates | 37180 | +| policy_gradient_loss | -0.0222 | +| value_loss | 0.000259 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0816 | +| time/ | | +| fps | 1301 | +| iterations | 460 | +| time_elapsed | 723 | +| total_timesteps | 942080 | +| train/ | | +| approx_kl | 0.020386191 | +| clip_fraction | 0.427 | +| clip_range | 0.0748 | +| entropy_loss | -5.5 | +| explained_variance | 0.392 | +| learning_rate | 4.98e-05 | +| loss | -0.0354 | +| n_updates | 37184 | +| policy_gradient_loss | -0.0225 | +| value_loss | 0.000179 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0776 | +| time/ | | +| fps | 1301 | +| iterations | 461 | +| time_elapsed | 725 | +| total_timesteps | 944128 | +| train/ | | +| approx_kl | 0.020240571 | +| clip_fraction | 0.418 | +| clip_range | 0.0748 | +| entropy_loss | -5.72 | +| explained_variance | 0.283 | +| learning_rate | 4.98e-05 | +| loss | -0.0312 | +| n_updates | 37188 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000263 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0776 | +| time/ | | +| fps | 1301 | +| iterations | 462 | +| time_elapsed | 727 | +| total_timesteps | 946176 | +| train/ | | +| approx_kl | 0.024834666 | +| clip_fraction | 0.47 | +| clip_range | 0.0748 | +| entropy_loss | -5.61 | +| explained_variance | 0.221 | +| learning_rate | 4.98e-05 | +| loss | -0.037 | +| n_updates | 37192 | +| policy_gradient_loss | -0.023 | +| value_loss | 0.000157 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0679 | +| time/ | | +| fps | 1301 | +| iterations | 463 | +| time_elapsed | 728 | +| total_timesteps | 948224 | +| train/ | | +| approx_kl | 0.021275505 | +| clip_fraction | 0.418 | +| clip_range | 0.0748 | +| entropy_loss | -5.95 | +| explained_variance | -0.11 | +| learning_rate | 4.98e-05 | +| loss | -0.0328 | +| n_updates | 37196 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000221 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0679 | +| time/ | | +| fps | 1301 | +| iterations | 464 | +| time_elapsed | 730 | +| total_timesteps | 950272 | +| train/ | | +| approx_kl | 0.017728146 | +| clip_fraction | 0.392 | +| clip_range | 0.0748 | +| entropy_loss | -5.72 | +| explained_variance | 0.417 | +| learning_rate | 4.98e-05 | +| loss | -0.0336 | +| n_updates | 37200 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.00028 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0674 | +| time/ | | +| fps | 1301 | +| iterations | 465 | +| time_elapsed | 731 | +| total_timesteps | 952320 | +| train/ | | +| approx_kl | 0.018833257 | +| clip_fraction | 0.385 | +| clip_range | 0.0748 | +| entropy_loss | -5.84 | +| explained_variance | -0.0336 | +| learning_rate | 4.98e-05 | +| loss | -0.0288 | +| n_updates | 37204 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.00031 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0765 | +| time/ | | +| fps | 1301 | +| iterations | 466 | +| time_elapsed | 733 | +| total_timesteps | 954368 | +| train/ | | +| approx_kl | 0.018513992 | +| clip_fraction | 0.424 | +| clip_range | 0.0748 | +| entropy_loss | -6.07 | +| explained_variance | -0.155 | +| learning_rate | 4.98e-05 | +| loss | -0.0352 | +| n_updates | 37208 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000327 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0811 | +| time/ | | +| fps | 1301 | +| iterations | 467 | +| time_elapsed | 734 | +| total_timesteps | 956416 | +| train/ | | +| approx_kl | 0.016684962 | +| clip_fraction | 0.38 | +| clip_range | 0.0748 | +| entropy_loss | -5.71 | +| explained_variance | 0.22 | +| learning_rate | 4.98e-05 | +| loss | -0.0245 | +| n_updates | 37212 | +| policy_gradient_loss | -0.0141 | +| value_loss | 0.000674 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0811 | +| time/ | | +| fps | 1301 | +| iterations | 468 | +| time_elapsed | 736 | +| total_timesteps | 958464 | +| train/ | | +| approx_kl | 0.020428762 | +| clip_fraction | 0.426 | +| clip_range | 0.0748 | +| entropy_loss | -5.22 | +| explained_variance | 0.163 | +| learning_rate | 4.98e-05 | +| loss | -0.0315 | +| n_updates | 37216 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000489 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.078 | +| time/ | | +| fps | 1301 | +| iterations | 469 | +| time_elapsed | 738 | +| total_timesteps | 960512 | +| train/ | | +| approx_kl | 0.023577513 | +| clip_fraction | 0.463 | +| clip_range | 0.0748 | +| entropy_loss | -5.68 | +| explained_variance | -0.23 | +| learning_rate | 4.98e-05 | +| loss | -0.0393 | +| n_updates | 37220 | +| policy_gradient_loss | -0.0264 | +| value_loss | 0.00025 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.078 | +| time/ | | +| fps | 1301 | +| iterations | 470 | +| time_elapsed | 739 | +| total_timesteps | 962560 | +| train/ | | +| approx_kl | 0.026707614 | +| clip_fraction | 0.442 | +| clip_range | 0.0748 | +| entropy_loss | -5.5 | +| explained_variance | 0.148 | +| learning_rate | 4.98e-05 | +| loss | -0.0346 | +| n_updates | 37224 | +| policy_gradient_loss | -0.0234 | +| value_loss | 0.000293 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0769 | +| time/ | | +| fps | 1301 | +| iterations | 471 | +| time_elapsed | 741 | +| total_timesteps | 964608 | +| train/ | | +| approx_kl | 0.024135191 | +| clip_fraction | 0.459 | +| clip_range | 0.0748 | +| entropy_loss | -5.57 | +| explained_variance | -0.273 | +| learning_rate | 4.98e-05 | +| loss | -0.0351 | +| n_updates | 37228 | +| policy_gradient_loss | -0.0227 | +| value_loss | 0.000168 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0726 | +| time/ | | +| fps | 1301 | +| iterations | 472 | +| time_elapsed | 742 | +| total_timesteps | 966656 | +| train/ | | +| approx_kl | 0.019006986 | +| clip_fraction | 0.429 | +| clip_range | 0.0748 | +| entropy_loss | -5.43 | +| explained_variance | 0.368 | +| learning_rate | 4.98e-05 | +| loss | -0.0342 | +| n_updates | 37232 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.00021 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0751 | +| time/ | | +| fps | 1301 | +| iterations | 473 | +| time_elapsed | 744 | +| total_timesteps | 968704 | +| train/ | | +| approx_kl | 0.02134075 | +| clip_fraction | 0.42 | +| clip_range | 0.0748 | +| entropy_loss | -5.81 | +| explained_variance | 0.16 | +| learning_rate | 4.98e-05 | +| loss | -0.0339 | +| n_updates | 37236 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000302 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0751 | +| time/ | | +| fps | 1301 | +| iterations | 474 | +| time_elapsed | 745 | +| total_timesteps | 970752 | +| train/ | | +| approx_kl | 0.024750285 | +| clip_fraction | 0.441 | +| clip_range | 0.0748 | +| entropy_loss | -5.34 | +| explained_variance | 0.374 | +| learning_rate | 4.98e-05 | +| loss | -0.0287 | +| n_updates | 37240 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000218 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0719 | +| time/ | | +| fps | 1301 | +| iterations | 475 | +| time_elapsed | 747 | +| total_timesteps | 972800 | +| train/ | | +| approx_kl | 0.019207383 | +| clip_fraction | 0.441 | +| clip_range | 0.0748 | +| entropy_loss | -5.73 | +| explained_variance | 0.276 | +| learning_rate | 4.98e-05 | +| loss | -0.0381 | +| n_updates | 37244 | +| policy_gradient_loss | -0.0223 | +| value_loss | 0.000162 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0759 | +| time/ | | +| fps | 1301 | +| iterations | 476 | +| time_elapsed | 748 | +| total_timesteps | 974848 | +| train/ | | +| approx_kl | 0.02208988 | +| clip_fraction | 0.408 | +| clip_range | 0.0748 | +| entropy_loss | -5.55 | +| explained_variance | 0.266 | +| learning_rate | 4.98e-05 | +| loss | -0.035 | +| n_updates | 37248 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000396 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0759 | +| time/ | | +| fps | 1301 | +| iterations | 477 | +| time_elapsed | 750 | +| total_timesteps | 976896 | +| train/ | | +| approx_kl | 0.018555883 | +| clip_fraction | 0.384 | +| clip_range | 0.0748 | +| entropy_loss | -5.79 | +| explained_variance | 0.0818 | +| learning_rate | 4.98e-05 | +| loss | -0.0298 | +| n_updates | 37252 | +| policy_gradient_loss | -0.0139 | +| value_loss | 0.000788 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.078 | +| time/ | | +| fps | 1301 | +| iterations | 478 | +| time_elapsed | 751 | +| total_timesteps | 978944 | +| train/ | | +| approx_kl | 0.018935647 | +| clip_fraction | 0.439 | +| clip_range | 0.0748 | +| entropy_loss | -6 | +| explained_variance | -0.284 | +| learning_rate | 4.98e-05 | +| loss | -0.0405 | +| n_updates | 37256 | +| policy_gradient_loss | -0.0246 | +| value_loss | 0.000307 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0756 | +| time/ | | +| fps | 1301 | +| iterations | 479 | +| time_elapsed | 753 | +| total_timesteps | 980992 | +| train/ | | +| approx_kl | 0.019846689 | +| clip_fraction | 0.423 | +| clip_range | 0.0748 | +| entropy_loss | -5.69 | +| explained_variance | 0.0964 | +| learning_rate | 4.98e-05 | +| loss | -0.0407 | +| n_updates | 37260 | +| policy_gradient_loss | -0.0232 | +| value_loss | 0.000276 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0725 | +| time/ | | +| fps | 1302 | +| iterations | 480 | +| time_elapsed | 754 | +| total_timesteps | 983040 | +| train/ | | +| approx_kl | 0.021305611 | +| clip_fraction | 0.429 | +| clip_range | 0.0748 | +| entropy_loss | -5.54 | +| explained_variance | -0.219 | +| learning_rate | 4.98e-05 | +| loss | -0.0283 | +| n_updates | 37264 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000357 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0717 | +| time/ | | +| fps | 1302 | +| iterations | 481 | +| time_elapsed | 756 | +| total_timesteps | 985088 | +| train/ | | +| approx_kl | 0.02376688 | +| clip_fraction | 0.407 | +| clip_range | 0.0748 | +| entropy_loss | -5.74 | +| explained_variance | -0.00587 | +| learning_rate | 4.98e-05 | +| loss | -0.0373 | +| n_updates | 37268 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000405 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0622 | +| time/ | | +| fps | 1302 | +| iterations | 482 | +| time_elapsed | 757 | +| total_timesteps | 987136 | +| train/ | | +| approx_kl | 0.020347856 | +| clip_fraction | 0.418 | +| clip_range | 0.0748 | +| entropy_loss | -5.83 | +| explained_variance | 0.0639 | +| learning_rate | 4.98e-05 | +| loss | -0.0364 | +| n_updates | 37272 | +| policy_gradient_loss | -0.0219 | +| value_loss | 0.000252 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.0617 | +| time/ | | +| fps | 1302 | +| iterations | 483 | +| time_elapsed | 759 | +| total_timesteps | 989184 | +| train/ | | +| approx_kl | 0.02047874 | +| clip_fraction | 0.413 | +| clip_range | 0.0748 | +| entropy_loss | -5.35 | +| explained_variance | 0.544 | +| learning_rate | 4.98e-05 | +| loss | -0.0364 | +| n_updates | 37276 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000204 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.0625 | +| time/ | | +| fps | 1302 | +| iterations | 484 | +| time_elapsed | 761 | +| total_timesteps | 991232 | +| train/ | | +| approx_kl | 0.02425678 | +| clip_fraction | 0.395 | +| clip_range | 0.0748 | +| entropy_loss | -5.39 | +| explained_variance | 0.421 | +| learning_rate | 4.98e-05 | +| loss | -0.03 | +| n_updates | 37280 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.0002 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.0625 | +| time/ | | +| fps | 1302 | +| iterations | 485 | +| time_elapsed | 762 | +| total_timesteps | 993280 | +| train/ | | +| approx_kl | 0.02196468 | +| clip_fraction | 0.45 | +| clip_range | 0.0748 | +| entropy_loss | -5.53 | +| explained_variance | -0.102 | +| learning_rate | 4.98e-05 | +| loss | -0.0346 | +| n_updates | 37284 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000136 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.0625 | +| time/ | | +| fps | 1302 | +| iterations | 486 | +| time_elapsed | 764 | +| total_timesteps | 995328 | +| train/ | | +| approx_kl | 0.025173943 | +| clip_fraction | 0.426 | +| clip_range | 0.0748 | +| entropy_loss | -5.78 | +| explained_variance | -0.532 | +| learning_rate | 4.98e-05 | +| loss | -0.0259 | +| n_updates | 37288 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000281 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.0625 | +| time/ | | +| fps | 1302 | +| iterations | 487 | +| time_elapsed | 765 | +| total_timesteps | 997376 | +| train/ | | +| approx_kl | 0.026156962 | +| clip_fraction | 0.413 | +| clip_range | 0.0748 | +| entropy_loss | -5.82 | +| explained_variance | -0.177 | +| learning_rate | 4.98e-05 | +| loss | -0.0386 | +| n_updates | 37292 | +| policy_gradient_loss | -0.0234 | +| value_loss | 0.000298 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.0577 | +| time/ | | +| fps | 1302 | +| iterations | 488 | +| time_elapsed | 767 | +| total_timesteps | 999424 | +| train/ | | +| approx_kl | 0.021840835 | +| clip_fraction | 0.433 | +| clip_range | 0.0748 | +| entropy_loss | -6.07 | +| explained_variance | -0.105 | +| learning_rate | 4.98e-05 | +| loss | -0.033 | +| n_updates | 37296 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000297 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.0484 | +| time/ | | +| fps | 1302 | +| iterations | 489 | +| time_elapsed | 768 | +| total_timesteps | 1001472 | +| train/ | | +| approx_kl | 0.020868206 | +| clip_fraction | 0.419 | +| clip_range | 0.0748 | +| entropy_loss | -5.69 | +| explained_variance | -0.102 | +| learning_rate | 4.98e-05 | +| loss | -0.0271 | +| n_updates | 37300 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000375 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.0534 | +| time/ | | +| fps | 1302 | +| iterations | 490 | +| time_elapsed | 770 | +| total_timesteps | 1003520 | +| train/ | | +| approx_kl | 0.023147468 | +| clip_fraction | 0.429 | +| clip_range | 0.0747 | +| entropy_loss | -5.68 | +| explained_variance | 0.366 | +| learning_rate | 4.98e-05 | +| loss | -0.0386 | +| n_updates | 37304 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000206 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.0615 | +| time/ | | +| fps | 1302 | +| iterations | 491 | +| time_elapsed | 772 | +| total_timesteps | 1005568 | +| train/ | | +| approx_kl | 0.019981913 | +| clip_fraction | 0.38 | +| clip_range | 0.0747 | +| entropy_loss | -5.24 | +| explained_variance | 0.517 | +| learning_rate | 4.98e-05 | +| loss | -0.0326 | +| n_updates | 37308 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000213 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0517 | +| time/ | | +| fps | 1302 | +| iterations | 492 | +| time_elapsed | 773 | +| total_timesteps | 1007616 | +| train/ | | +| approx_kl | 0.015470311 | +| clip_fraction | 0.376 | +| clip_range | 0.0747 | +| entropy_loss | -5.57 | +| explained_variance | 0.0156 | +| learning_rate | 4.98e-05 | +| loss | -0.029 | +| n_updates | 37312 | +| policy_gradient_loss | -0.0135 | +| value_loss | 0.000748 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0511 | +| time/ | | +| fps | 1302 | +| iterations | 493 | +| time_elapsed | 775 | +| total_timesteps | 1009664 | +| train/ | | +| approx_kl | 0.020702956 | +| clip_fraction | 0.414 | +| clip_range | 0.0747 | +| entropy_loss | -4.76 | +| explained_variance | 0.522 | +| learning_rate | 4.98e-05 | +| loss | -0.0339 | +| n_updates | 37316 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000256 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0513 | +| time/ | | +| fps | 1302 | +| iterations | 494 | +| time_elapsed | 776 | +| total_timesteps | 1011712 | +| train/ | | +| approx_kl | 0.019863753 | +| clip_fraction | 0.415 | +| clip_range | 0.0747 | +| entropy_loss | -5.48 | +| explained_variance | 0.165 | +| learning_rate | 4.98e-05 | +| loss | -0.0313 | +| n_updates | 37320 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000246 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0513 | +| time/ | | +| fps | 1302 | +| iterations | 495 | +| time_elapsed | 778 | +| total_timesteps | 1013760 | +| train/ | | +| approx_kl | 0.0203709 | +| clip_fraction | 0.423 | +| clip_range | 0.0747 | +| entropy_loss | -5.37 | +| explained_variance | 0.358 | +| learning_rate | 4.98e-05 | +| loss | -0.0358 | +| n_updates | 37324 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000177 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0536 | +| time/ | | +| fps | 1302 | +| iterations | 496 | +| time_elapsed | 780 | +| total_timesteps | 1015808 | +| train/ | | +| approx_kl | 0.023310877 | +| clip_fraction | 0.421 | +| clip_range | 0.0747 | +| entropy_loss | -5.64 | +| explained_variance | 0.173 | +| learning_rate | 4.98e-05 | +| loss | -0.0329 | +| n_updates | 37328 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000287 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.0637 | +| time/ | | +| fps | 1302 | +| iterations | 497 | +| time_elapsed | 781 | +| total_timesteps | 1017856 | +| train/ | | +| approx_kl | 0.02167906 | +| clip_fraction | 0.427 | +| clip_range | 0.0747 | +| entropy_loss | -5.67 | +| explained_variance | 0.262 | +| learning_rate | 4.98e-05 | +| loss | -0.0347 | +| n_updates | 37332 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000254 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0633 | +| time/ | | +| fps | 1302 | +| iterations | 498 | +| time_elapsed | 783 | +| total_timesteps | 1019904 | +| train/ | | +| approx_kl | 0.021312725 | +| clip_fraction | 0.437 | +| clip_range | 0.0747 | +| entropy_loss | -5.62 | +| explained_variance | 0.111 | +| learning_rate | 4.98e-05 | +| loss | -0.0353 | +| n_updates | 37336 | +| policy_gradient_loss | -0.0223 | +| value_loss | 0.000325 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0633 | +| time/ | | +| fps | 1302 | +| iterations | 499 | +| time_elapsed | 784 | +| total_timesteps | 1021952 | +| train/ | | +| approx_kl | 0.021347284 | +| clip_fraction | 0.415 | +| clip_range | 0.0747 | +| entropy_loss | -5.41 | +| explained_variance | 0.463 | +| learning_rate | 4.98e-05 | +| loss | -0.034 | +| n_updates | 37340 | +| policy_gradient_loss | -0.0222 | +| value_loss | 0.00027 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0711 | +| time/ | | +| fps | 1302 | +| iterations | 500 | +| time_elapsed | 786 | +| total_timesteps | 1024000 | +| train/ | | +| approx_kl | 0.025076356 | +| clip_fraction | 0.427 | +| clip_range | 0.0747 | +| entropy_loss | -5.69 | +| explained_variance | 0.0316 | +| learning_rate | 4.98e-05 | +| loss | -0.0341 | +| n_updates | 37344 | +| policy_gradient_loss | -0.0225 | +| value_loss | 0.000289 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0665 | +| time/ | | +| fps | 1302 | +| iterations | 501 | +| time_elapsed | 787 | +| total_timesteps | 1026048 | +| train/ | | +| approx_kl | 0.01976763 | +| clip_fraction | 0.415 | +| clip_range | 0.0747 | +| entropy_loss | -5.6 | +| explained_variance | 0.0915 | +| learning_rate | 4.98e-05 | +| loss | -0.0335 | +| n_updates | 37348 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.0005 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0615 | +| time/ | | +| fps | 1302 | +| iterations | 502 | +| time_elapsed | 789 | +| total_timesteps | 1028096 | +| train/ | | +| approx_kl | 0.025438163 | +| clip_fraction | 0.427 | +| clip_range | 0.0747 | +| entropy_loss | -5.23 | +| explained_variance | 0.457 | +| learning_rate | 4.98e-05 | +| loss | -0.0371 | +| n_updates | 37352 | +| policy_gradient_loss | -0.0224 | +| value_loss | 0.000212 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0624 | +| time/ | | +| fps | 1302 | +| iterations | 503 | +| time_elapsed | 790 | +| total_timesteps | 1030144 | +| train/ | | +| approx_kl | 0.021905914 | +| clip_fraction | 0.41 | +| clip_range | 0.0747 | +| entropy_loss | -5.17 | +| explained_variance | 0.355 | +| learning_rate | 4.98e-05 | +| loss | -0.0336 | +| n_updates | 37356 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.00024 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.063 | +| time/ | | +| fps | 1302 | +| iterations | 504 | +| time_elapsed | 792 | +| total_timesteps | 1032192 | +| train/ | | +| approx_kl | 0.02577625 | +| clip_fraction | 0.44 | +| clip_range | 0.0747 | +| entropy_loss | -5.35 | +| explained_variance | 0.38 | +| learning_rate | 4.98e-05 | +| loss | -0.0303 | +| n_updates | 37360 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.00027 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0727 | +| time/ | | +| fps | 1302 | +| iterations | 505 | +| time_elapsed | 794 | +| total_timesteps | 1034240 | +| train/ | | +| approx_kl | 0.020050058 | +| clip_fraction | 0.402 | +| clip_range | 0.0747 | +| entropy_loss | -5.33 | +| explained_variance | 0.102 | +| learning_rate | 4.98e-05 | +| loss | -0.0268 | +| n_updates | 37364 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.00034 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0733 | +| time/ | | +| fps | 1302 | +| iterations | 506 | +| time_elapsed | 795 | +| total_timesteps | 1036288 | +| train/ | | +| approx_kl | 0.021724783 | +| clip_fraction | 0.438 | +| clip_range | 0.0747 | +| entropy_loss | -5.65 | +| explained_variance | 0.188 | +| learning_rate | 4.98e-05 | +| loss | -0.0377 | +| n_updates | 37368 | +| policy_gradient_loss | -0.0224 | +| value_loss | 0.000346 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0733 | +| time/ | | +| fps | 1302 | +| iterations | 507 | +| time_elapsed | 797 | +| total_timesteps | 1038336 | +| train/ | | +| approx_kl | 0.02209728 | +| clip_fraction | 0.417 | +| clip_range | 0.0747 | +| entropy_loss | -5.27 | +| explained_variance | 0.462 | +| learning_rate | 4.98e-05 | +| loss | -0.0284 | +| n_updates | 37372 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000211 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0801 | +| time/ | | +| fps | 1302 | +| iterations | 508 | +| time_elapsed | 798 | +| total_timesteps | 1040384 | +| train/ | | +| approx_kl | 0.01996401 | +| clip_fraction | 0.431 | +| clip_range | 0.0747 | +| entropy_loss | -5.67 | +| explained_variance | -0.134 | +| learning_rate | 4.98e-05 | +| loss | -0.0363 | +| n_updates | 37376 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000211 | +---------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0824 | +| time/ | | +| fps | 1302 | +| iterations | 509 | +| time_elapsed | 800 | +| total_timesteps | 1042432 | +| train/ | | +| approx_kl | 0.0228072 | +| clip_fraction | 0.424 | +| clip_range | 0.0747 | +| entropy_loss | -5.63 | +| explained_variance | 0.202 | +| learning_rate | 4.98e-05 | +| loss | -0.0347 | +| n_updates | 37380 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000234 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0765 | +| time/ | | +| fps | 1302 | +| iterations | 510 | +| time_elapsed | 801 | +| total_timesteps | 1044480 | +| train/ | | +| approx_kl | 0.021787599 | +| clip_fraction | 0.422 | +| clip_range | 0.0747 | +| entropy_loss | -5.53 | +| explained_variance | 0.488 | +| learning_rate | 4.98e-05 | +| loss | -0.0329 | +| n_updates | 37384 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000212 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0716 | +| time/ | | +| fps | 1302 | +| iterations | 511 | +| time_elapsed | 803 | +| total_timesteps | 1046528 | +| train/ | | +| approx_kl | 0.022876525 | +| clip_fraction | 0.417 | +| clip_range | 0.0747 | +| entropy_loss | -5.19 | +| explained_variance | 0.123 | +| learning_rate | 4.98e-05 | +| loss | -0.0319 | +| n_updates | 37388 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000261 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0716 | +| time/ | | +| fps | 1302 | +| iterations | 512 | +| time_elapsed | 804 | +| total_timesteps | 1048576 | +| train/ | | +| approx_kl | 0.024642274 | +| clip_fraction | 0.443 | +| clip_range | 0.0747 | +| entropy_loss | -5.25 | +| explained_variance | 0.442 | +| learning_rate | 4.98e-05 | +| loss | -0.0347 | +| n_updates | 37392 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000178 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0729 | +| time/ | | +| fps | 1302 | +| iterations | 513 | +| time_elapsed | 806 | +| total_timesteps | 1050624 | +| train/ | | +| approx_kl | 0.023806196 | +| clip_fraction | 0.411 | +| clip_range | 0.0747 | +| entropy_loss | -5.71 | +| explained_variance | -0.155 | +| learning_rate | 4.98e-05 | +| loss | -0.0331 | +| n_updates | 37396 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000291 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0596 | +| time/ | | +| fps | 1302 | +| iterations | 514 | +| time_elapsed | 808 | +| total_timesteps | 1052672 | +| train/ | | +| approx_kl | 0.01961346 | +| clip_fraction | 0.401 | +| clip_range | 0.0747 | +| entropy_loss | -5.51 | +| explained_variance | 0.383 | +| learning_rate | 4.98e-05 | +| loss | -0.0327 | +| n_updates | 37400 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.00031 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0765 | +| time/ | | +| fps | 1302 | +| iterations | 515 | +| time_elapsed | 809 | +| total_timesteps | 1054720 | +| train/ | | +| approx_kl | 0.021476453 | +| clip_fraction | 0.427 | +| clip_range | 0.0747 | +| entropy_loss | -5.37 | +| explained_variance | 0.494 | +| learning_rate | 4.97e-05 | +| loss | -0.0316 | +| n_updates | 37404 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000208 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0765 | +| time/ | | +| fps | 1302 | +| iterations | 516 | +| time_elapsed | 811 | +| total_timesteps | 1056768 | +| train/ | | +| approx_kl | 0.020909334 | +| clip_fraction | 0.393 | +| clip_range | 0.0747 | +| entropy_loss | -5.15 | +| explained_variance | 0.175 | +| learning_rate | 4.97e-05 | +| loss | -0.0264 | +| n_updates | 37408 | +| policy_gradient_loss | -0.0147 | +| value_loss | 0.000933 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0765 | +| time/ | | +| fps | 1302 | +| iterations | 517 | +| time_elapsed | 812 | +| total_timesteps | 1058816 | +| train/ | | +| approx_kl | 0.020482324 | +| clip_fraction | 0.432 | +| clip_range | 0.0747 | +| entropy_loss | -5.45 | +| explained_variance | -0.417 | +| learning_rate | 4.97e-05 | +| loss | -0.0349 | +| n_updates | 37412 | +| policy_gradient_loss | -0.022 | +| value_loss | 0.000386 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0784 | +| time/ | | +| fps | 1302 | +| iterations | 518 | +| time_elapsed | 814 | +| total_timesteps | 1060864 | +| train/ | | +| approx_kl | 0.026030134 | +| clip_fraction | 0.437 | +| clip_range | 0.0747 | +| entropy_loss | -5.9 | +| explained_variance | -0.249 | +| learning_rate | 4.97e-05 | +| loss | -0.0367 | +| n_updates | 37416 | +| policy_gradient_loss | -0.0236 | +| value_loss | 0.000326 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0736 | +| time/ | | +| fps | 1302 | +| iterations | 519 | +| time_elapsed | 815 | +| total_timesteps | 1062912 | +| train/ | | +| approx_kl | 0.019857004 | +| clip_fraction | 0.422 | +| clip_range | 0.0747 | +| entropy_loss | -5.4 | +| explained_variance | 0.0296 | +| learning_rate | 4.97e-05 | +| loss | -0.0314 | +| n_updates | 37420 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000295 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0566 | +| time/ | | +| fps | 1302 | +| iterations | 520 | +| time_elapsed | 817 | +| total_timesteps | 1064960 | +| train/ | | +| approx_kl | 0.016911034 | +| clip_fraction | 0.383 | +| clip_range | 0.0747 | +| entropy_loss | -5.47 | +| explained_variance | 0.138 | +| learning_rate | 4.97e-05 | +| loss | -0.0269 | +| n_updates | 37424 | +| policy_gradient_loss | -0.0157 | +| value_loss | 0.000467 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0566 | +| time/ | | +| fps | 1302 | +| iterations | 521 | +| time_elapsed | 819 | +| total_timesteps | 1067008 | +| train/ | | +| approx_kl | 0.01815604 | +| clip_fraction | 0.395 | +| clip_range | 0.0747 | +| entropy_loss | -5.54 | +| explained_variance | 0.223 | +| learning_rate | 4.97e-05 | +| loss | -0.0308 | +| n_updates | 37428 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000333 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0545 | +| time/ | | +| fps | 1302 | +| iterations | 522 | +| time_elapsed | 820 | +| total_timesteps | 1069056 | +| train/ | | +| approx_kl | 0.024062108 | +| clip_fraction | 0.422 | +| clip_range | 0.0747 | +| entropy_loss | -5.29 | +| explained_variance | 0.362 | +| learning_rate | 4.97e-05 | +| loss | -0.0323 | +| n_updates | 37432 | +| policy_gradient_loss | -0.0219 | +| value_loss | 0.000204 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.054 | +| time/ | | +| fps | 1302 | +| iterations | 523 | +| time_elapsed | 822 | +| total_timesteps | 1071104 | +| train/ | | +| approx_kl | 0.021220986 | +| clip_fraction | 0.411 | +| clip_range | 0.0747 | +| entropy_loss | -5.47 | +| explained_variance | 0.186 | +| learning_rate | 4.97e-05 | +| loss | -0.0313 | +| n_updates | 37436 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000284 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.054 | +| time/ | | +| fps | 1302 | +| iterations | 524 | +| time_elapsed | 823 | +| total_timesteps | 1073152 | +| train/ | | +| approx_kl | 0.019143863 | +| clip_fraction | 0.421 | +| clip_range | 0.0747 | +| entropy_loss | -5.58 | +| explained_variance | 0.272 | +| learning_rate | 4.97e-05 | +| loss | -0.0342 | +| n_updates | 37440 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000178 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0559 | +| time/ | | +| fps | 1302 | +| iterations | 525 | +| time_elapsed | 825 | +| total_timesteps | 1075200 | +| train/ | | +| approx_kl | 0.022437135 | +| clip_fraction | 0.42 | +| clip_range | 0.0747 | +| entropy_loss | -5.55 | +| explained_variance | -0.174 | +| learning_rate | 4.97e-05 | +| loss | -0.0334 | +| n_updates | 37444 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000223 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0526 | +| time/ | | +| fps | 1302 | +| iterations | 526 | +| time_elapsed | 826 | +| total_timesteps | 1077248 | +| train/ | | +| approx_kl | 0.020864028 | +| clip_fraction | 0.409 | +| clip_range | 0.0747 | +| entropy_loss | -5.35 | +| explained_variance | 0.277 | +| learning_rate | 4.97e-05 | +| loss | -0.0277 | +| n_updates | 37448 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000235 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0449 | +| time/ | | +| fps | 1302 | +| iterations | 527 | +| time_elapsed | 828 | +| total_timesteps | 1079296 | +| train/ | | +| approx_kl | 0.019949602 | +| clip_fraction | 0.404 | +| clip_range | 0.0747 | +| entropy_loss | -5.22 | +| explained_variance | 0.411 | +| learning_rate | 4.97e-05 | +| loss | -0.0322 | +| n_updates | 37452 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.00023 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0475 | +| time/ | | +| fps | 1302 | +| iterations | 528 | +| time_elapsed | 830 | +| total_timesteps | 1081344 | +| train/ | | +| approx_kl | 0.02584951 | +| clip_fraction | 0.43 | +| clip_range | 0.0747 | +| entropy_loss | -5.37 | +| explained_variance | 0.558 | +| learning_rate | 4.97e-05 | +| loss | -0.036 | +| n_updates | 37456 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000157 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0457 | +| time/ | | +| fps | 1302 | +| iterations | 529 | +| time_elapsed | 831 | +| total_timesteps | 1083392 | +| train/ | | +| approx_kl | 0.024061758 | +| clip_fraction | 0.418 | +| clip_range | 0.0747 | +| entropy_loss | -5.11 | +| explained_variance | 0.204 | +| learning_rate | 4.97e-05 | +| loss | -0.0297 | +| n_updates | 37460 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000197 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0457 | +| time/ | | +| fps | 1302 | +| iterations | 530 | +| time_elapsed | 833 | +| total_timesteps | 1085440 | +| train/ | | +| approx_kl | 0.018904999 | +| clip_fraction | 0.421 | +| clip_range | 0.0747 | +| entropy_loss | -5.27 | +| explained_variance | 0.427 | +| learning_rate | 4.97e-05 | +| loss | -0.0335 | +| n_updates | 37464 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000197 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0352 | +| time/ | | +| fps | 1302 | +| iterations | 531 | +| time_elapsed | 834 | +| total_timesteps | 1087488 | +| train/ | | +| approx_kl | 0.022097196 | +| clip_fraction | 0.401 | +| clip_range | 0.0747 | +| entropy_loss | -5.67 | +| explained_variance | -0.0484 | +| learning_rate | 4.97e-05 | +| loss | -0.0325 | +| n_updates | 37468 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000287 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0355 | +| time/ | | +| fps | 1302 | +| iterations | 532 | +| time_elapsed | 836 | +| total_timesteps | 1089536 | +| train/ | | +| approx_kl | 0.022797162 | +| clip_fraction | 0.407 | +| clip_range | 0.0747 | +| entropy_loss | -5.36 | +| explained_variance | 0.258 | +| learning_rate | 4.97e-05 | +| loss | -0.035 | +| n_updates | 37472 | +| policy_gradient_loss | -0.0221 | +| value_loss | 0.000307 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0264 | +| time/ | | +| fps | 1302 | +| iterations | 533 | +| time_elapsed | 838 | +| total_timesteps | 1091584 | +| train/ | | +| approx_kl | 0.021385655 | +| clip_fraction | 0.409 | +| clip_range | 0.0747 | +| entropy_loss | -5.37 | +| explained_variance | 0.0214 | +| learning_rate | 4.97e-05 | +| loss | -0.0355 | +| n_updates | 37476 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000176 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0265 | +| time/ | | +| fps | 1302 | +| iterations | 534 | +| time_elapsed | 839 | +| total_timesteps | 1093632 | +| train/ | | +| approx_kl | 0.019081444 | +| clip_fraction | 0.418 | +| clip_range | 0.0747 | +| entropy_loss | -5.4 | +| explained_variance | 0.398 | +| learning_rate | 4.97e-05 | +| loss | -0.0352 | +| n_updates | 37480 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.00029 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0212 | +| time/ | | +| fps | 1302 | +| iterations | 535 | +| time_elapsed | 841 | +| total_timesteps | 1095680 | +| train/ | | +| approx_kl | 0.025226288 | +| clip_fraction | 0.417 | +| clip_range | 0.0747 | +| entropy_loss | -5.65 | +| explained_variance | -0.11 | +| learning_rate | 4.97e-05 | +| loss | -0.0401 | +| n_updates | 37484 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000182 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0273 | +| time/ | | +| fps | 1302 | +| iterations | 536 | +| time_elapsed | 842 | +| total_timesteps | 1097728 | +| train/ | | +| approx_kl | 0.022625182 | +| clip_fraction | 0.41 | +| clip_range | 0.0747 | +| entropy_loss | -5.27 | +| explained_variance | 0.367 | +| learning_rate | 4.97e-05 | +| loss | -0.0301 | +| n_updates | 37488 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.00024 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0268 | +| time/ | | +| fps | 1302 | +| iterations | 537 | +| time_elapsed | 844 | +| total_timesteps | 1099776 | +| train/ | | +| approx_kl | 0.022493448 | +| clip_fraction | 0.387 | +| clip_range | 0.0747 | +| entropy_loss | -5.01 | +| explained_variance | 0.5 | +| learning_rate | 4.97e-05 | +| loss | -0.0206 | +| n_updates | 37492 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000272 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0268 | +| time/ | | +| fps | 1302 | +| iterations | 538 | +| time_elapsed | 845 | +| total_timesteps | 1101824 | +| train/ | | +| approx_kl | 0.023869112 | +| clip_fraction | 0.423 | +| clip_range | 0.0747 | +| entropy_loss | -5.2 | +| explained_variance | 0.212 | +| learning_rate | 4.97e-05 | +| loss | -0.0324 | +| n_updates | 37496 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000246 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0302 | +| time/ | | +| fps | 1302 | +| iterations | 539 | +| time_elapsed | 847 | +| total_timesteps | 1103872 | +| train/ | | +| approx_kl | 0.02087053 | +| clip_fraction | 0.408 | +| clip_range | 0.0747 | +| entropy_loss | -5.35 | +| explained_variance | 0.188 | +| learning_rate | 4.97e-05 | +| loss | -0.0321 | +| n_updates | 37500 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000201 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0301 | +| time/ | | +| fps | 1302 | +| iterations | 540 | +| time_elapsed | 849 | +| total_timesteps | 1105920 | +| train/ | | +| approx_kl | 0.02077547 | +| clip_fraction | 0.41 | +| clip_range | 0.0747 | +| entropy_loss | -5.4 | +| explained_variance | 0.0932 | +| learning_rate | 4.97e-05 | +| loss | -0.0207 | +| n_updates | 37504 | +| policy_gradient_loss | -0.0155 | +| value_loss | 0.000851 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0318 | +| time/ | | +| fps | 1302 | +| iterations | 541 | +| time_elapsed | 850 | +| total_timesteps | 1107968 | +| train/ | | +| approx_kl | 0.02028527 | +| clip_fraction | 0.424 | +| clip_range | 0.0747 | +| entropy_loss | -5.48 | +| explained_variance | 0.275 | +| learning_rate | 4.97e-05 | +| loss | -0.0361 | +| n_updates | 37508 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000282 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0365 | +| time/ | | +| fps | 1302 | +| iterations | 542 | +| time_elapsed | 852 | +| total_timesteps | 1110016 | +| train/ | | +| approx_kl | 0.019538376 | +| clip_fraction | 0.403 | +| clip_range | 0.0747 | +| entropy_loss | -4.93 | +| explained_variance | 0.364 | +| learning_rate | 4.97e-05 | +| loss | -0.0384 | +| n_updates | 37512 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000266 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0401 | +| time/ | | +| fps | 1302 | +| iterations | 543 | +| time_elapsed | 853 | +| total_timesteps | 1112064 | +| train/ | | +| approx_kl | 0.023017202 | +| clip_fraction | 0.412 | +| clip_range | 0.0747 | +| entropy_loss | -5.19 | +| explained_variance | 0.472 | +| learning_rate | 4.97e-05 | +| loss | -0.0349 | +| n_updates | 37516 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000307 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0401 | +| time/ | | +| fps | 1302 | +| iterations | 544 | +| time_elapsed | 855 | +| total_timesteps | 1114112 | +| train/ | | +| approx_kl | 0.02088697 | +| clip_fraction | 0.419 | +| clip_range | 0.0747 | +| entropy_loss | -5.34 | +| explained_variance | 0.231 | +| learning_rate | 4.97e-05 | +| loss | -0.0388 | +| n_updates | 37520 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000244 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0401 | +| time/ | | +| fps | 1302 | +| iterations | 545 | +| time_elapsed | 857 | +| total_timesteps | 1116160 | +| train/ | | +| approx_kl | 0.022747252 | +| clip_fraction | 0.443 | +| clip_range | 0.0747 | +| entropy_loss | -5.49 | +| explained_variance | -0.205 | +| learning_rate | 4.97e-05 | +| loss | -0.0386 | +| n_updates | 37524 | +| policy_gradient_loss | -0.0222 | +| value_loss | 0.000236 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0417 | +| time/ | | +| fps | 1302 | +| iterations | 546 | +| time_elapsed | 858 | +| total_timesteps | 1118208 | +| train/ | | +| approx_kl | 0.018554319 | +| clip_fraction | 0.43 | +| clip_range | 0.0747 | +| entropy_loss | -5.75 | +| explained_variance | -0.144 | +| learning_rate | 4.97e-05 | +| loss | -0.0379 | +| n_updates | 37528 | +| policy_gradient_loss | -0.0225 | +| value_loss | 0.000183 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0438 | +| time/ | | +| fps | 1302 | +| iterations | 547 | +| time_elapsed | 860 | +| total_timesteps | 1120256 | +| train/ | | +| approx_kl | 0.022725746 | +| clip_fraction | 0.416 | +| clip_range | 0.0747 | +| entropy_loss | -5.53 | +| explained_variance | 0.111 | +| learning_rate | 4.97e-05 | +| loss | -0.0324 | +| n_updates | 37532 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000265 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0389 | +| time/ | | +| fps | 1302 | +| iterations | 548 | +| time_elapsed | 861 | +| total_timesteps | 1122304 | +| train/ | | +| approx_kl | 0.017709922 | +| clip_fraction | 0.4 | +| clip_range | 0.0747 | +| entropy_loss | -5.76 | +| explained_variance | -0.112 | +| learning_rate | 4.97e-05 | +| loss | -0.0318 | +| n_updates | 37536 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000436 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0357 | +| time/ | | +| fps | 1302 | +| iterations | 549 | +| time_elapsed | 863 | +| total_timesteps | 1124352 | +| train/ | | +| approx_kl | 0.020670567 | +| clip_fraction | 0.443 | +| clip_range | 0.0747 | +| entropy_loss | -5.55 | +| explained_variance | -0.119 | +| learning_rate | 4.97e-05 | +| loss | -0.0318 | +| n_updates | 37540 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.00026 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.0364 | +| time/ | | +| fps | 1302 | +| iterations | 550 | +| time_elapsed | 864 | +| total_timesteps | 1126400 | +| train/ | | +| approx_kl | 0.01684009 | +| clip_fraction | 0.392 | +| clip_range | 0.0747 | +| entropy_loss | -5.15 | +| explained_variance | 0.393 | +| learning_rate | 4.97e-05 | +| loss | -0.027 | +| n_updates | 37544 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000294 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.046 | +| time/ | | +| fps | 1302 | +| iterations | 551 | +| time_elapsed | 866 | +| total_timesteps | 1128448 | +| train/ | | +| approx_kl | 0.018689219 | +| clip_fraction | 0.415 | +| clip_range | 0.0747 | +| entropy_loss | -5.21 | +| explained_variance | 0.496 | +| learning_rate | 4.97e-05 | +| loss | -0.036 | +| n_updates | 37548 | +| policy_gradient_loss | -0.0219 | +| value_loss | 0.000175 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.0306 | +| time/ | | +| fps | 1302 | +| iterations | 552 | +| time_elapsed | 868 | +| total_timesteps | 1130496 | +| train/ | | +| approx_kl | 0.021210443 | +| clip_fraction | 0.408 | +| clip_range | 0.0747 | +| entropy_loss | -5.05 | +| explained_variance | 0.505 | +| learning_rate | 4.97e-05 | +| loss | -0.023 | +| n_updates | 37552 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000283 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.0306 | +| time/ | | +| fps | 1302 | +| iterations | 553 | +| time_elapsed | 869 | +| total_timesteps | 1132544 | +| train/ | | +| approx_kl | 0.023728395 | +| clip_fraction | 0.425 | +| clip_range | 0.0747 | +| entropy_loss | -4.58 | +| explained_variance | 0.627 | +| learning_rate | 4.97e-05 | +| loss | -0.0326 | +| n_updates | 37556 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000161 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.0306 | +| time/ | | +| fps | 1302 | +| iterations | 554 | +| time_elapsed | 871 | +| total_timesteps | 1134592 | +| train/ | | +| approx_kl | 0.024572197 | +| clip_fraction | 0.444 | +| clip_range | 0.0747 | +| entropy_loss | -5.12 | +| explained_variance | 0.412 | +| learning_rate | 4.97e-05 | +| loss | -0.0343 | +| n_updates | 37560 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000197 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.0407 | +| time/ | | +| fps | 1302 | +| iterations | 555 | +| time_elapsed | 872 | +| total_timesteps | 1136640 | +| train/ | | +| approx_kl | 0.022609793 | +| clip_fraction | 0.441 | +| clip_range | 0.0747 | +| entropy_loss | -5.55 | +| explained_variance | -0.0496 | +| learning_rate | 4.97e-05 | +| loss | -0.0347 | +| n_updates | 37564 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000264 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.0432 | +| time/ | | +| fps | 1302 | +| iterations | 556 | +| time_elapsed | 874 | +| total_timesteps | 1138688 | +| train/ | | +| approx_kl | 0.020693481 | +| clip_fraction | 0.399 | +| clip_range | 0.0747 | +| entropy_loss | -5.51 | +| explained_variance | 0.0451 | +| learning_rate | 4.97e-05 | +| loss | -0.0305 | +| n_updates | 37568 | +| policy_gradient_loss | -0.0161 | +| value_loss | 0.000843 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.0432 | +| time/ | | +| fps | 1302 | +| iterations | 557 | +| time_elapsed | 875 | +| total_timesteps | 1140736 | +| train/ | | +| approx_kl | 0.025865985 | +| clip_fraction | 0.455 | +| clip_range | 0.0747 | +| entropy_loss | -5.48 | +| explained_variance | 0.0633 | +| learning_rate | 4.97e-05 | +| loss | -0.0392 | +| n_updates | 37572 | +| policy_gradient_loss | -0.0259 | +| value_loss | 0.000327 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.0432 | +| time/ | | +| fps | 1302 | +| iterations | 558 | +| time_elapsed | 877 | +| total_timesteps | 1142784 | +| train/ | | +| approx_kl | 0.026995804 | +| clip_fraction | 0.487 | +| clip_range | 0.0747 | +| entropy_loss | -5.61 | +| explained_variance | -0.0115 | +| learning_rate | 4.97e-05 | +| loss | -0.0416 | +| n_updates | 37576 | +| policy_gradient_loss | -0.0255 | +| value_loss | 0.000314 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.0562 | +| time/ | | +| fps | 1302 | +| iterations | 559 | +| time_elapsed | 878 | +| total_timesteps | 1144832 | +| train/ | | +| approx_kl | 0.024940737 | +| clip_fraction | 0.445 | +| clip_range | 0.0747 | +| entropy_loss | -5.63 | +| explained_variance | -0.208 | +| learning_rate | 4.97e-05 | +| loss | -0.0371 | +| n_updates | 37580 | +| policy_gradient_loss | -0.0227 | +| value_loss | 0.000267 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.0499 | +| time/ | | +| fps | 1302 | +| iterations | 560 | +| time_elapsed | 880 | +| total_timesteps | 1146880 | +| train/ | | +| approx_kl | 0.021000389 | +| clip_fraction | 0.427 | +| clip_range | 0.0747 | +| entropy_loss | -5.15 | +| explained_variance | 0.28 | +| learning_rate | 4.97e-05 | +| loss | -0.0371 | +| n_updates | 37584 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000359 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.0443 | +| time/ | | +| fps | 1302 | +| iterations | 561 | +| time_elapsed | 882 | +| total_timesteps | 1148928 | +| train/ | | +| approx_kl | 0.022989277 | +| clip_fraction | 0.458 | +| clip_range | 0.0747 | +| entropy_loss | -5.14 | +| explained_variance | 0.162 | +| learning_rate | 4.97e-05 | +| loss | -0.0406 | +| n_updates | 37588 | +| policy_gradient_loss | -0.0243 | +| value_loss | 0.000162 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.0422 | +| time/ | | +| fps | 1302 | +| iterations | 562 | +| time_elapsed | 883 | +| total_timesteps | 1150976 | +| train/ | | +| approx_kl | 0.018629415 | +| clip_fraction | 0.411 | +| clip_range | 0.0747 | +| entropy_loss | -5.13 | +| explained_variance | 0.3 | +| learning_rate | 4.97e-05 | +| loss | -0.0318 | +| n_updates | 37592 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000346 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.0423 | +| time/ | | +| fps | 1302 | +| iterations | 563 | +| time_elapsed | 885 | +| total_timesteps | 1153024 | +| train/ | | +| approx_kl | 0.020603325 | +| clip_fraction | 0.417 | +| clip_range | 0.0747 | +| entropy_loss | -4.81 | +| explained_variance | 0.615 | +| learning_rate | 4.97e-05 | +| loss | -0.033 | +| n_updates | 37596 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000167 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.0389 | +| time/ | | +| fps | 1302 | +| iterations | 564 | +| time_elapsed | 886 | +| total_timesteps | 1155072 | +| train/ | | +| approx_kl | 0.021973863 | +| clip_fraction | 0.414 | +| clip_range | 0.0747 | +| entropy_loss | -5.29 | +| explained_variance | 0.279 | +| learning_rate | 4.97e-05 | +| loss | -0.0341 | +| n_updates | 37600 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000268 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.0412 | +| time/ | | +| fps | 1302 | +| iterations | 565 | +| time_elapsed | 888 | +| total_timesteps | 1157120 | +| train/ | | +| approx_kl | 0.023758134 | +| clip_fraction | 0.431 | +| clip_range | 0.0747 | +| entropy_loss | -5.37 | +| explained_variance | -0.0211 | +| learning_rate | 4.97e-05 | +| loss | -0.0393 | +| n_updates | 37604 | +| policy_gradient_loss | -0.0222 | +| value_loss | 0.000215 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0471 | +| time/ | | +| fps | 1303 | +| iterations | 566 | +| time_elapsed | 889 | +| total_timesteps | 1159168 | +| train/ | | +| approx_kl | 0.022744505 | +| clip_fraction | 0.44 | +| clip_range | 0.0747 | +| entropy_loss | -5.02 | +| explained_variance | 0.664 | +| learning_rate | 4.97e-05 | +| loss | -0.0428 | +| n_updates | 37608 | +| policy_gradient_loss | -0.0237 | +| value_loss | 0.000114 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.0414 | +| time/ | | +| fps | 1303 | +| iterations | 567 | +| time_elapsed | 891 | +| total_timesteps | 1161216 | +| train/ | | +| approx_kl | 0.024347033 | +| clip_fraction | 0.46 | +| clip_range | 0.0747 | +| entropy_loss | -5.42 | +| explained_variance | 0.174 | +| learning_rate | 4.97e-05 | +| loss | -0.0339 | +| n_updates | 37612 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000195 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.0389 | +| time/ | | +| fps | 1303 | +| iterations | 568 | +| time_elapsed | 892 | +| total_timesteps | 1163264 | +| train/ | | +| approx_kl | 0.021987986 | +| clip_fraction | 0.397 | +| clip_range | 0.0747 | +| entropy_loss | -5.21 | +| explained_variance | 0.189 | +| learning_rate | 4.97e-05 | +| loss | -0.0319 | +| n_updates | 37616 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000239 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.0398 | +| time/ | | +| fps | 1303 | +| iterations | 569 | +| time_elapsed | 894 | +| total_timesteps | 1165312 | +| train/ | | +| approx_kl | 0.020235857 | +| clip_fraction | 0.445 | +| clip_range | 0.0747 | +| entropy_loss | -5.39 | +| explained_variance | 0.539 | +| learning_rate | 4.97e-05 | +| loss | -0.0355 | +| n_updates | 37620 | +| policy_gradient_loss | -0.0239 | +| value_loss | 0.000138 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.045 | +| time/ | | +| fps | 1303 | +| iterations | 570 | +| time_elapsed | 895 | +| total_timesteps | 1167360 | +| train/ | | +| approx_kl | 0.019947615 | +| clip_fraction | 0.41 | +| clip_range | 0.0747 | +| entropy_loss | -5.41 | +| explained_variance | 0.182 | +| learning_rate | 4.97e-05 | +| loss | -0.0331 | +| n_updates | 37624 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.00023 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.045 | +| time/ | | +| fps | 1303 | +| iterations | 571 | +| time_elapsed | 897 | +| total_timesteps | 1169408 | +| train/ | | +| approx_kl | 0.024442315 | +| clip_fraction | 0.408 | +| clip_range | 0.0747 | +| entropy_loss | -5.02 | +| explained_variance | 0.456 | +| learning_rate | 4.97e-05 | +| loss | -0.0367 | +| n_updates | 37628 | +| policy_gradient_loss | -0.022 | +| value_loss | 0.000178 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.0448 | +| time/ | | +| fps | 1303 | +| iterations | 572 | +| time_elapsed | 898 | +| total_timesteps | 1171456 | +| train/ | | +| approx_kl | 0.023369193 | +| clip_fraction | 0.432 | +| clip_range | 0.0747 | +| entropy_loss | -5.44 | +| explained_variance | -0.0919 | +| learning_rate | 4.97e-05 | +| loss | -0.0292 | +| n_updates | 37632 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000182 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.0407 | +| time/ | | +| fps | 1303 | +| iterations | 573 | +| time_elapsed | 900 | +| total_timesteps | 1173504 | +| train/ | | +| approx_kl | 0.020719182 | +| clip_fraction | 0.433 | +| clip_range | 0.0747 | +| entropy_loss | -5.51 | +| explained_variance | -0.085 | +| learning_rate | 4.97e-05 | +| loss | -0.0359 | +| n_updates | 37636 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000275 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.0377 | +| time/ | | +| fps | 1303 | +| iterations | 574 | +| time_elapsed | 901 | +| total_timesteps | 1175552 | +| train/ | | +| approx_kl | 0.023651809 | +| clip_fraction | 0.424 | +| clip_range | 0.0747 | +| entropy_loss | -4.93 | +| explained_variance | 0.49 | +| learning_rate | 4.97e-05 | +| loss | -0.0252 | +| n_updates | 37640 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000289 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0362 | +| time/ | | +| fps | 1303 | +| iterations | 575 | +| time_elapsed | 903 | +| total_timesteps | 1177600 | +| train/ | | +| approx_kl | 0.021755314 | +| clip_fraction | 0.436 | +| clip_range | 0.0747 | +| entropy_loss | -5.33 | +| explained_variance | 0.0982 | +| learning_rate | 4.97e-05 | +| loss | -0.0357 | +| n_updates | 37644 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000264 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.04 | +| time/ | | +| fps | 1303 | +| iterations | 576 | +| time_elapsed | 904 | +| total_timesteps | 1179648 | +| train/ | | +| approx_kl | 0.022393715 | +| clip_fraction | 0.407 | +| clip_range | 0.0747 | +| entropy_loss | -5.25 | +| explained_variance | 0.303 | +| learning_rate | 4.97e-05 | +| loss | -0.035 | +| n_updates | 37648 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000332 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.0365 | +| time/ | | +| fps | 1303 | +| iterations | 577 | +| time_elapsed | 906 | +| total_timesteps | 1181696 | +| train/ | | +| approx_kl | 0.023591733 | +| clip_fraction | 0.445 | +| clip_range | 0.0747 | +| entropy_loss | -5.37 | +| explained_variance | -0.1 | +| learning_rate | 4.97e-05 | +| loss | -0.0331 | +| n_updates | 37652 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000194 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.0396 | +| time/ | | +| fps | 1303 | +| iterations | 578 | +| time_elapsed | 907 | +| total_timesteps | 1183744 | +| train/ | | +| approx_kl | 0.020818334 | +| clip_fraction | 0.418 | +| clip_range | 0.0747 | +| entropy_loss | -5.2 | +| explained_variance | 0.253 | +| learning_rate | 4.97e-05 | +| loss | -0.0355 | +| n_updates | 37656 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000201 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.044 | +| time/ | | +| fps | 1303 | +| iterations | 579 | +| time_elapsed | 909 | +| total_timesteps | 1185792 | +| train/ | | +| approx_kl | 0.021567132 | +| clip_fraction | 0.399 | +| clip_range | 0.0747 | +| entropy_loss | -5.22 | +| explained_variance | 0.563 | +| learning_rate | 4.97e-05 | +| loss | -0.033 | +| n_updates | 37660 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000178 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0352 | +| time/ | | +| fps | 1303 | +| iterations | 580 | +| time_elapsed | 911 | +| total_timesteps | 1187840 | +| train/ | | +| approx_kl | 0.018914822 | +| clip_fraction | 0.399 | +| clip_range | 0.0747 | +| entropy_loss | -5.53 | +| explained_variance | 0.298 | +| learning_rate | 4.97e-05 | +| loss | -0.0285 | +| n_updates | 37664 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000274 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0372 | +| time/ | | +| fps | 1304 | +| iterations | 581 | +| time_elapsed | 912 | +| total_timesteps | 1189888 | +| train/ | | +| approx_kl | 0.022537848 | +| clip_fraction | 0.431 | +| clip_range | 0.0747 | +| entropy_loss | -5.22 | +| explained_variance | 0.275 | +| learning_rate | 4.97e-05 | +| loss | -0.0378 | +| n_updates | 37668 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000152 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0363 | +| time/ | | +| fps | 1304 | +| iterations | 582 | +| time_elapsed | 913 | +| total_timesteps | 1191936 | +| train/ | | +| approx_kl | 0.019757874 | +| clip_fraction | 0.424 | +| clip_range | 0.0747 | +| entropy_loss | -5.2 | +| explained_variance | 0.184 | +| learning_rate | 4.97e-05 | +| loss | -0.0316 | +| n_updates | 37672 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000346 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0363 | +| time/ | | +| fps | 1304 | +| iterations | 583 | +| time_elapsed | 915 | +| total_timesteps | 1193984 | +| train/ | | +| approx_kl | 0.019650891 | +| clip_fraction | 0.401 | +| clip_range | 0.0747 | +| entropy_loss | -5.06 | +| explained_variance | 0.387 | +| learning_rate | 4.97e-05 | +| loss | -0.0351 | +| n_updates | 37676 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000191 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0429 | +| time/ | | +| fps | 1304 | +| iterations | 584 | +| time_elapsed | 917 | +| total_timesteps | 1196032 | +| train/ | | +| approx_kl | 0.022537423 | +| clip_fraction | 0.424 | +| clip_range | 0.0747 | +| entropy_loss | -5.54 | +| explained_variance | -0.15 | +| learning_rate | 4.97e-05 | +| loss | -0.0307 | +| n_updates | 37680 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000405 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0511 | +| time/ | | +| fps | 1304 | +| iterations | 585 | +| time_elapsed | 918 | +| total_timesteps | 1198080 | +| train/ | | +| approx_kl | 0.021929238 | +| clip_fraction | 0.417 | +| clip_range | 0.0747 | +| entropy_loss | -5.22 | +| explained_variance | 0.153 | +| learning_rate | 4.97e-05 | +| loss | -0.0296 | +| n_updates | 37684 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000342 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0508 | +| time/ | | +| fps | 1304 | +| iterations | 586 | +| time_elapsed | 920 | +| total_timesteps | 1200128 | +| train/ | | +| approx_kl | 0.023723816 | +| clip_fraction | 0.429 | +| clip_range | 0.0747 | +| entropy_loss | -5.16 | +| explained_variance | 0.181 | +| learning_rate | 4.97e-05 | +| loss | -0.0325 | +| n_updates | 37688 | +| policy_gradient_loss | -0.0219 | +| value_loss | 0.000312 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0593 | +| time/ | | +| fps | 1304 | +| iterations | 587 | +| time_elapsed | 921 | +| total_timesteps | 1202176 | +| train/ | | +| approx_kl | 0.02045914 | +| clip_fraction | 0.38 | +| clip_range | 0.0747 | +| entropy_loss | -5.54 | +| explained_variance | 0.196 | +| learning_rate | 4.97e-05 | +| loss | -0.0288 | +| n_updates | 37692 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000323 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0575 | +| time/ | | +| fps | 1304 | +| iterations | 588 | +| time_elapsed | 923 | +| total_timesteps | 1204224 | +| train/ | | +| approx_kl | 0.023003709 | +| clip_fraction | 0.438 | +| clip_range | 0.0747 | +| entropy_loss | -5.38 | +| explained_variance | 0.414 | +| learning_rate | 4.97e-05 | +| loss | -0.0416 | +| n_updates | 37696 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.00021 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0606 | +| time/ | | +| fps | 1304 | +| iterations | 589 | +| time_elapsed | 924 | +| total_timesteps | 1206272 | +| train/ | | +| approx_kl | 0.023114868 | +| clip_fraction | 0.429 | +| clip_range | 0.0747 | +| entropy_loss | -5.3 | +| explained_variance | 0.402 | +| learning_rate | 4.97e-05 | +| loss | -0.0267 | +| n_updates | 37700 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000261 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0606 | +| time/ | | +| fps | 1304 | +| iterations | 590 | +| time_elapsed | 926 | +| total_timesteps | 1208320 | +| train/ | | +| approx_kl | 0.023051227 | +| clip_fraction | 0.42 | +| clip_range | 0.0747 | +| entropy_loss | -4.81 | +| explained_variance | 0.569 | +| learning_rate | 4.97e-05 | +| loss | -0.0358 | +| n_updates | 37704 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000214 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0587 | +| time/ | | +| fps | 1304 | +| iterations | 591 | +| time_elapsed | 927 | +| total_timesteps | 1210368 | +| train/ | | +| approx_kl | 0.025883254 | +| clip_fraction | 0.422 | +| clip_range | 0.0747 | +| entropy_loss | -4.76 | +| explained_variance | 0.477 | +| learning_rate | 4.97e-05 | +| loss | -0.0313 | +| n_updates | 37708 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000155 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0586 | +| time/ | | +| fps | 1304 | +| iterations | 592 | +| time_elapsed | 929 | +| total_timesteps | 1212416 | +| train/ | | +| approx_kl | 0.025157643 | +| clip_fraction | 0.402 | +| clip_range | 0.0747 | +| entropy_loss | -5.25 | +| explained_variance | 0.208 | +| learning_rate | 4.97e-05 | +| loss | -0.0333 | +| n_updates | 37712 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000255 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.0545 | +| time/ | | +| fps | 1304 | +| iterations | 593 | +| time_elapsed | 930 | +| total_timesteps | 1214464 | +| train/ | | +| approx_kl | 0.021687195 | +| clip_fraction | 0.448 | +| clip_range | 0.0747 | +| entropy_loss | -5.41 | +| explained_variance | 0.00318 | +| learning_rate | 4.97e-05 | +| loss | -0.0319 | +| n_updates | 37716 | +| policy_gradient_loss | -0.0228 | +| value_loss | 0.00025 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.0515 | +| time/ | | +| fps | 1304 | +| iterations | 594 | +| time_elapsed | 932 | +| total_timesteps | 1216512 | +| train/ | | +| approx_kl | 0.022351367 | +| clip_fraction | 0.452 | +| clip_range | 0.0747 | +| entropy_loss | -5.47 | +| explained_variance | 0.0955 | +| learning_rate | 4.97e-05 | +| loss | -0.0317 | +| n_updates | 37720 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000382 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.0515 | +| time/ | | +| fps | 1304 | +| iterations | 595 | +| time_elapsed | 933 | +| total_timesteps | 1218560 | +| train/ | | +| approx_kl | 0.02116236 | +| clip_fraction | 0.431 | +| clip_range | 0.0747 | +| entropy_loss | -5.23 | +| explained_variance | 0.463 | +| learning_rate | 4.97e-05 | +| loss | -0.0302 | +| n_updates | 37724 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000248 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.0515 | +| time/ | | +| fps | 1304 | +| iterations | 596 | +| time_elapsed | 935 | +| total_timesteps | 1220608 | +| train/ | | +| approx_kl | 0.026258064 | +| clip_fraction | 0.434 | +| clip_range | 0.0747 | +| entropy_loss | -5.39 | +| explained_variance | -0.143 | +| learning_rate | 4.97e-05 | +| loss | -0.0349 | +| n_updates | 37728 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000202 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.0528 | +| time/ | | +| fps | 1304 | +| iterations | 597 | +| time_elapsed | 937 | +| total_timesteps | 1222656 | +| train/ | | +| approx_kl | 0.02309769 | +| clip_fraction | 0.444 | +| clip_range | 0.0747 | +| entropy_loss | -5.61 | +| explained_variance | -0.219 | +| learning_rate | 4.97e-05 | +| loss | -0.0323 | +| n_updates | 37732 | +| policy_gradient_loss | -0.0223 | +| value_loss | 0.00028 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.0533 | +| time/ | | +| fps | 1304 | +| iterations | 598 | +| time_elapsed | 938 | +| total_timesteps | 1224704 | +| train/ | | +| approx_kl | 0.02155712 | +| clip_fraction | 0.422 | +| clip_range | 0.0747 | +| entropy_loss | -5.4 | +| explained_variance | 0.239 | +| learning_rate | 4.97e-05 | +| loss | -0.0358 | +| n_updates | 37736 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000236 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.0511 | +| time/ | | +| fps | 1304 | +| iterations | 599 | +| time_elapsed | 940 | +| total_timesteps | 1226752 | +| train/ | | +| approx_kl | 0.025303775 | +| clip_fraction | 0.438 | +| clip_range | 0.0747 | +| entropy_loss | -4.79 | +| explained_variance | 0.583 | +| learning_rate | 4.97e-05 | +| loss | -0.0351 | +| n_updates | 37740 | +| policy_gradient_loss | -0.0226 | +| value_loss | 0.00023 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.0345 | +| time/ | | +| fps | 1304 | +| iterations | 600 | +| time_elapsed | 941 | +| total_timesteps | 1228800 | +| train/ | | +| approx_kl | 0.026928673 | +| clip_fraction | 0.452 | +| clip_range | 0.0747 | +| entropy_loss | -5.06 | +| explained_variance | 0.201 | +| learning_rate | 4.97e-05 | +| loss | -0.0347 | +| n_updates | 37744 | +| policy_gradient_loss | -0.0227 | +| value_loss | 0.0003 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.0334 | +| time/ | | +| fps | 1305 | +| iterations | 601 | +| time_elapsed | 943 | +| total_timesteps | 1230848 | +| train/ | | +| approx_kl | 0.026471116 | +| clip_fraction | 0.425 | +| clip_range | 0.0747 | +| entropy_loss | -4.73 | +| explained_variance | 0.542 | +| learning_rate | 4.97e-05 | +| loss | -0.0348 | +| n_updates | 37748 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000231 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.0334 | +| time/ | | +| fps | 1305 | +| iterations | 602 | +| time_elapsed | 944 | +| total_timesteps | 1232896 | +| train/ | | +| approx_kl | 0.024639405 | +| clip_fraction | 0.447 | +| clip_range | 0.0747 | +| entropy_loss | -4.67 | +| explained_variance | 0.56 | +| learning_rate | 4.97e-05 | +| loss | -0.0299 | +| n_updates | 37752 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000205 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.0384 | +| time/ | | +| fps | 1305 | +| iterations | 603 | +| time_elapsed | 946 | +| total_timesteps | 1234944 | +| train/ | | +| approx_kl | 0.0235066 | +| clip_fraction | 0.453 | +| clip_range | 0.0747 | +| entropy_loss | -5.35 | +| explained_variance | -0.0143 | +| learning_rate | 4.97e-05 | +| loss | -0.0399 | +| n_updates | 37756 | +| policy_gradient_loss | -0.0222 | +| value_loss | 0.000202 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.0384 | +| time/ | | +| fps | 1305 | +| iterations | 604 | +| time_elapsed | 947 | +| total_timesteps | 1236992 | +| train/ | | +| approx_kl | 0.024115197 | +| clip_fraction | 0.411 | +| clip_range | 0.0747 | +| entropy_loss | -5.3 | +| explained_variance | -0.0492 | +| learning_rate | 4.97e-05 | +| loss | -0.0311 | +| n_updates | 37760 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000339 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.0473 | +| time/ | | +| fps | 1305 | +| iterations | 605 | +| time_elapsed | 949 | +| total_timesteps | 1239040 | +| train/ | | +| approx_kl | 0.024464093 | +| clip_fraction | 0.446 | +| clip_range | 0.0747 | +| entropy_loss | -5.53 | +| explained_variance | -0.153 | +| learning_rate | 4.97e-05 | +| loss | -0.0311 | +| n_updates | 37764 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000287 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.0459 | +| time/ | | +| fps | 1305 | +| iterations | 606 | +| time_elapsed | 950 | +| total_timesteps | 1241088 | +| train/ | | +| approx_kl | 0.019731078 | +| clip_fraction | 0.434 | +| clip_range | 0.0747 | +| entropy_loss | -5.37 | +| explained_variance | -0.061 | +| learning_rate | 4.97e-05 | +| loss | -0.0257 | +| n_updates | 37768 | +| policy_gradient_loss | -0.0154 | +| value_loss | 0.000831 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.0434 | +| time/ | | +| fps | 1305 | +| iterations | 607 | +| time_elapsed | 952 | +| total_timesteps | 1243136 | +| train/ | | +| approx_kl | 0.024016414 | +| clip_fraction | 0.442 | +| clip_range | 0.0747 | +| entropy_loss | -5.11 | +| explained_variance | -0.032 | +| learning_rate | 4.97e-05 | +| loss | -0.0371 | +| n_updates | 37772 | +| policy_gradient_loss | -0.0224 | +| value_loss | 0.000371 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.0412 | +| time/ | | +| fps | 1305 | +| iterations | 608 | +| time_elapsed | 953 | +| total_timesteps | 1245184 | +| train/ | | +| approx_kl | 0.024849901 | +| clip_fraction | 0.46 | +| clip_range | 0.0747 | +| entropy_loss | -5.03 | +| explained_variance | 0.351 | +| learning_rate | 4.97e-05 | +| loss | -0.0348 | +| n_updates | 37776 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000241 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.0394 | +| time/ | | +| fps | 1305 | +| iterations | 609 | +| time_elapsed | 955 | +| total_timesteps | 1247232 | +| train/ | | +| approx_kl | 0.026297655 | +| clip_fraction | 0.44 | +| clip_range | 0.0747 | +| entropy_loss | -5.43 | +| explained_variance | -0.121 | +| learning_rate | 4.97e-05 | +| loss | -0.0341 | +| n_updates | 37780 | +| policy_gradient_loss | -0.0224 | +| value_loss | 0.000239 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.0374 | +| time/ | | +| fps | 1305 | +| iterations | 610 | +| time_elapsed | 956 | +| total_timesteps | 1249280 | +| train/ | | +| approx_kl | 0.021079302 | +| clip_fraction | 0.435 | +| clip_range | 0.0747 | +| entropy_loss | -4.67 | +| explained_variance | 0.443 | +| learning_rate | 4.97e-05 | +| loss | -0.0289 | +| n_updates | 37784 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000287 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.0374 | +| time/ | | +| fps | 1305 | +| iterations | 611 | +| time_elapsed | 958 | +| total_timesteps | 1251328 | +| train/ | | +| approx_kl | 0.020244256 | +| clip_fraction | 0.443 | +| clip_range | 0.0747 | +| entropy_loss | -5.07 | +| explained_variance | 0.172 | +| learning_rate | 4.97e-05 | +| loss | -0.0347 | +| n_updates | 37788 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000225 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0445 | +| time/ | | +| fps | 1305 | +| iterations | 612 | +| time_elapsed | 960 | +| total_timesteps | 1253376 | +| train/ | | +| approx_kl | 0.021706676 | +| clip_fraction | 0.421 | +| clip_range | 0.0747 | +| entropy_loss | -5.25 | +| explained_variance | 0.176 | +| learning_rate | 4.97e-05 | +| loss | -0.0293 | +| n_updates | 37792 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000232 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.0451 | +| time/ | | +| fps | 1305 | +| iterations | 613 | +| time_elapsed | 961 | +| total_timesteps | 1255424 | +| train/ | | +| approx_kl | 0.018595567 | +| clip_fraction | 0.407 | +| clip_range | 0.0747 | +| entropy_loss | -4.97 | +| explained_variance | 0.466 | +| learning_rate | 4.97e-05 | +| loss | -0.0279 | +| n_updates | 37796 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.00024 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.0451 | +| time/ | | +| fps | 1305 | +| iterations | 614 | +| time_elapsed | 963 | +| total_timesteps | 1257472 | +| train/ | | +| approx_kl | 0.020157764 | +| clip_fraction | 0.43 | +| clip_range | 0.0747 | +| entropy_loss | -5.09 | +| explained_variance | 0.173 | +| learning_rate | 4.97e-05 | +| loss | -0.0313 | +| n_updates | 37800 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000208 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.0512 | +| time/ | | +| fps | 1305 | +| iterations | 615 | +| time_elapsed | 964 | +| total_timesteps | 1259520 | +| train/ | | +| approx_kl | 0.02019642 | +| clip_fraction | 0.425 | +| clip_range | 0.0747 | +| entropy_loss | -5.41 | +| explained_variance | -0.0583 | +| learning_rate | 4.97e-05 | +| loss | -0.031 | +| n_updates | 37804 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000294 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.0418 | +| time/ | | +| fps | 1305 | +| iterations | 616 | +| time_elapsed | 966 | +| total_timesteps | 1261568 | +| train/ | | +| approx_kl | 0.022323787 | +| clip_fraction | 0.431 | +| clip_range | 0.0747 | +| entropy_loss | -5.46 | +| explained_variance | -0.0106 | +| learning_rate | 4.97e-05 | +| loss | -0.0331 | +| n_updates | 37808 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000234 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.0359 | +| time/ | | +| fps | 1305 | +| iterations | 617 | +| time_elapsed | 967 | +| total_timesteps | 1263616 | +| train/ | | +| approx_kl | 0.023558464 | +| clip_fraction | 0.424 | +| clip_range | 0.0747 | +| entropy_loss | -5.15 | +| explained_variance | 0.209 | +| learning_rate | 4.97e-05 | +| loss | -0.0332 | +| n_updates | 37812 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000282 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.0401 | +| time/ | | +| fps | 1305 | +| iterations | 618 | +| time_elapsed | 969 | +| total_timesteps | 1265664 | +| train/ | | +| approx_kl | 0.02136644 | +| clip_fraction | 0.435 | +| clip_range | 0.0747 | +| entropy_loss | -5.29 | +| explained_variance | 0.298 | +| learning_rate | 4.97e-05 | +| loss | -0.03 | +| n_updates | 37816 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000197 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.0401 | +| time/ | | +| fps | 1305 | +| iterations | 619 | +| time_elapsed | 971 | +| total_timesteps | 1267712 | +| train/ | | +| approx_kl | 0.025747407 | +| clip_fraction | 0.43 | +| clip_range | 0.0747 | +| entropy_loss | -5.15 | +| explained_variance | 0.311 | +| learning_rate | 4.97e-05 | +| loss | -0.0318 | +| n_updates | 37820 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000277 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0448 | +| time/ | | +| fps | 1305 | +| iterations | 620 | +| time_elapsed | 972 | +| total_timesteps | 1269760 | +| train/ | | +| approx_kl | 0.02465178 | +| clip_fraction | 0.415 | +| clip_range | 0.0747 | +| entropy_loss | -5.48 | +| explained_variance | -0.0667 | +| learning_rate | 4.97e-05 | +| loss | -0.0327 | +| n_updates | 37824 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000452 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0309 | +| time/ | | +| fps | 1305 | +| iterations | 621 | +| time_elapsed | 974 | +| total_timesteps | 1271808 | +| train/ | | +| approx_kl | 0.021708183 | +| clip_fraction | 0.423 | +| clip_range | 0.0747 | +| entropy_loss | -5.37 | +| explained_variance | -0.409 | +| learning_rate | 4.97e-05 | +| loss | -0.037 | +| n_updates | 37828 | +| policy_gradient_loss | -0.0225 | +| value_loss | 0.000284 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.023 | +| time/ | | +| fps | 1305 | +| iterations | 622 | +| time_elapsed | 975 | +| total_timesteps | 1273856 | +| train/ | | +| approx_kl | 0.021465778 | +| clip_fraction | 0.431 | +| clip_range | 0.0747 | +| entropy_loss | -5.18 | +| explained_variance | 0.398 | +| learning_rate | 4.97e-05 | +| loss | -0.0363 | +| n_updates | 37832 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.00025 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0278 | +| time/ | | +| fps | 1305 | +| iterations | 623 | +| time_elapsed | 977 | +| total_timesteps | 1275904 | +| train/ | | +| approx_kl | 0.023286799 | +| clip_fraction | 0.427 | +| clip_range | 0.0747 | +| entropy_loss | -4.92 | +| explained_variance | 0.196 | +| learning_rate | 4.97e-05 | +| loss | -0.0341 | +| n_updates | 37836 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000256 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0278 | +| time/ | | +| fps | 1305 | +| iterations | 624 | +| time_elapsed | 978 | +| total_timesteps | 1277952 | +| train/ | | +| approx_kl | 0.027161065 | +| clip_fraction | 0.428 | +| clip_range | 0.0747 | +| entropy_loss | -4.82 | +| explained_variance | 0.519 | +| learning_rate | 4.97e-05 | +| loss | -0.0333 | +| n_updates | 37840 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000231 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0278 | +| time/ | | +| fps | 1305 | +| iterations | 625 | +| time_elapsed | 980 | +| total_timesteps | 1280000 | +| train/ | | +| approx_kl | 0.025933124 | +| clip_fraction | 0.457 | +| clip_range | 0.0747 | +| entropy_loss | -5.29 | +| explained_variance | 0.0672 | +| learning_rate | 4.97e-05 | +| loss | -0.0347 | +| n_updates | 37844 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000152 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0345 | +| time/ | | +| fps | 1305 | +| iterations | 626 | +| time_elapsed | 982 | +| total_timesteps | 1282048 | +| train/ | | +| approx_kl | 0.024287919 | +| clip_fraction | 0.452 | +| clip_range | 0.0747 | +| entropy_loss | -5.2 | +| explained_variance | -0.11 | +| learning_rate | 4.97e-05 | +| loss | -0.035 | +| n_updates | 37848 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000344 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0329 | +| time/ | | +| fps | 1305 | +| iterations | 627 | +| time_elapsed | 983 | +| total_timesteps | 1284096 | +| train/ | | +| approx_kl | 0.022148225 | +| clip_fraction | 0.425 | +| clip_range | 0.0747 | +| entropy_loss | -5.33 | +| explained_variance | 0.16 | +| learning_rate | 4.97e-05 | +| loss | -0.0332 | +| n_updates | 37852 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000346 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0366 | +| time/ | | +| fps | 1305 | +| iterations | 628 | +| time_elapsed | 985 | +| total_timesteps | 1286144 | +| train/ | | +| approx_kl | 0.019161392 | +| clip_fraction | 0.435 | +| clip_range | 0.0747 | +| entropy_loss | -5.48 | +| explained_variance | -0.0974 | +| learning_rate | 4.97e-05 | +| loss | -0.0327 | +| n_updates | 37856 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000287 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0421 | +| time/ | | +| fps | 1305 | +| iterations | 629 | +| time_elapsed | 986 | +| total_timesteps | 1288192 | +| train/ | | +| approx_kl | 0.026400577 | +| clip_fraction | 0.445 | +| clip_range | 0.0747 | +| entropy_loss | -5.12 | +| explained_variance | 0.0415 | +| learning_rate | 4.97e-05 | +| loss | -0.0328 | +| n_updates | 37860 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000232 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0421 | +| time/ | | +| fps | 1305 | +| iterations | 630 | +| time_elapsed | 988 | +| total_timesteps | 1290240 | +| train/ | | +| approx_kl | 0.025513388 | +| clip_fraction | 0.441 | +| clip_range | 0.0747 | +| entropy_loss | -5.23 | +| explained_variance | -0.0948 | +| learning_rate | 4.97e-05 | +| loss | -0.0335 | +| n_updates | 37864 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000264 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0421 | +| time/ | | +| fps | 1305 | +| iterations | 631 | +| time_elapsed | 990 | +| total_timesteps | 1292288 | +| train/ | | +| approx_kl | 0.024154369 | +| clip_fraction | 0.448 | +| clip_range | 0.0747 | +| entropy_loss | -5.29 | +| explained_variance | 0.207 | +| learning_rate | 4.97e-05 | +| loss | -0.0313 | +| n_updates | 37868 | +| policy_gradient_loss | -0.023 | +| value_loss | 0.000163 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.0497 | +| time/ | | +| fps | 1305 | +| iterations | 632 | +| time_elapsed | 991 | +| total_timesteps | 1294336 | +| train/ | | +| approx_kl | 0.024674043 | +| clip_fraction | 0.465 | +| clip_range | 0.0747 | +| entropy_loss | -5.52 | +| explained_variance | -0.118 | +| learning_rate | 4.97e-05 | +| loss | -0.0372 | +| n_updates | 37872 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000293 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0585 | +| time/ | | +| fps | 1304 | +| iterations | 633 | +| time_elapsed | 993 | +| total_timesteps | 1296384 | +| train/ | | +| approx_kl | 0.019907983 | +| clip_fraction | 0.376 | +| clip_range | 0.0747 | +| entropy_loss | -5.06 | +| explained_variance | 0.117 | +| learning_rate | 4.97e-05 | +| loss | -0.03 | +| n_updates | 37876 | +| policy_gradient_loss | -0.0147 | +| value_loss | 0.000905 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0564 | +| time/ | | +| fps | 1304 | +| iterations | 634 | +| time_elapsed | 994 | +| total_timesteps | 1298432 | +| train/ | | +| approx_kl | 0.02408325 | +| clip_fraction | 0.458 | +| clip_range | 0.0747 | +| entropy_loss | -4.9 | +| explained_variance | 0.228 | +| learning_rate | 4.97e-05 | +| loss | -0.0413 | +| n_updates | 37880 | +| policy_gradient_loss | -0.0262 | +| value_loss | 0.000256 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0482 | +| time/ | | +| fps | 1304 | +| iterations | 635 | +| time_elapsed | 996 | +| total_timesteps | 1300480 | +| train/ | | +| approx_kl | 0.026755225 | +| clip_fraction | 0.437 | +| clip_range | 0.0747 | +| entropy_loss | -4.96 | +| explained_variance | 0.48 | +| learning_rate | 4.97e-05 | +| loss | -0.033 | +| n_updates | 37884 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000231 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0423 | +| time/ | | +| fps | 1304 | +| iterations | 636 | +| time_elapsed | 998 | +| total_timesteps | 1302528 | +| train/ | | +| approx_kl | 0.029103912 | +| clip_fraction | 0.442 | +| clip_range | 0.0747 | +| entropy_loss | -4.91 | +| explained_variance | 0.112 | +| learning_rate | 4.97e-05 | +| loss | -0.0385 | +| n_updates | 37888 | +| policy_gradient_loss | -0.0226 | +| value_loss | 0.000235 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0423 | +| time/ | | +| fps | 1304 | +| iterations | 637 | +| time_elapsed | 999 | +| total_timesteps | 1304576 | +| train/ | | +| approx_kl | 0.024729963 | +| clip_fraction | 0.451 | +| clip_range | 0.0747 | +| entropy_loss | -5.15 | +| explained_variance | -0.185 | +| learning_rate | 4.97e-05 | +| loss | -0.0342 | +| n_updates | 37892 | +| policy_gradient_loss | -0.0222 | +| value_loss | 0.000293 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0416 | +| time/ | | +| fps | 1304 | +| iterations | 638 | +| time_elapsed | 1001 | +| total_timesteps | 1306624 | +| train/ | | +| approx_kl | 0.028753059 | +| clip_fraction | 0.446 | +| clip_range | 0.0747 | +| entropy_loss | -5.18 | +| explained_variance | -0.173 | +| learning_rate | 4.97e-05 | +| loss | -0.035 | +| n_updates | 37896 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000243 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0418 | +| time/ | | +| fps | 1304 | +| iterations | 639 | +| time_elapsed | 1002 | +| total_timesteps | 1308672 | +| train/ | | +| approx_kl | 0.022522444 | +| clip_fraction | 0.436 | +| clip_range | 0.0747 | +| entropy_loss | -5.02 | +| explained_variance | 0.133 | +| learning_rate | 4.97e-05 | +| loss | -0.0376 | +| n_updates | 37900 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000254 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0418 | +| time/ | | +| fps | 1304 | +| iterations | 640 | +| time_elapsed | 1004 | +| total_timesteps | 1310720 | +| train/ | | +| approx_kl | 0.021238243 | +| clip_fraction | 0.417 | +| clip_range | 0.0747 | +| entropy_loss | -5.2 | +| explained_variance | 0.446 | +| learning_rate | 4.97e-05 | +| loss | -0.0292 | +| n_updates | 37904 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000293 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0389 | +| time/ | | +| fps | 1304 | +| iterations | 641 | +| time_elapsed | 1006 | +| total_timesteps | 1312768 | +| train/ | | +| approx_kl | 0.021393733 | +| clip_fraction | 0.44 | +| clip_range | 0.0747 | +| entropy_loss | -5.03 | +| explained_variance | -0.196 | +| learning_rate | 4.97e-05 | +| loss | -0.0356 | +| n_updates | 37908 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.00025 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0411 | +| time/ | | +| fps | 1304 | +| iterations | 642 | +| time_elapsed | 1007 | +| total_timesteps | 1314816 | +| train/ | | +| approx_kl | 0.021834845 | +| clip_fraction | 0.429 | +| clip_range | 0.0747 | +| entropy_loss | -5.15 | +| explained_variance | 0.135 | +| learning_rate | 4.97e-05 | +| loss | -0.035 | +| n_updates | 37912 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000271 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0412 | +| time/ | | +| fps | 1304 | +| iterations | 643 | +| time_elapsed | 1009 | +| total_timesteps | 1316864 | +| train/ | | +| approx_kl | 0.024173515 | +| clip_fraction | 0.413 | +| clip_range | 0.0747 | +| entropy_loss | -5.03 | +| explained_variance | 0.217 | +| learning_rate | 4.97e-05 | +| loss | -0.0345 | +| n_updates | 37916 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000281 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0391 | +| time/ | | +| fps | 1304 | +| iterations | 644 | +| time_elapsed | 1010 | +| total_timesteps | 1318912 | +| train/ | | +| approx_kl | 0.025163664 | +| clip_fraction | 0.442 | +| clip_range | 0.0747 | +| entropy_loss | -4.9 | +| explained_variance | 0.367 | +| learning_rate | 4.97e-05 | +| loss | -0.0355 | +| n_updates | 37920 | +| policy_gradient_loss | -0.022 | +| value_loss | 0.000274 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0368 | +| time/ | | +| fps | 1304 | +| iterations | 645 | +| time_elapsed | 1012 | +| total_timesteps | 1320960 | +| train/ | | +| approx_kl | 0.024385575 | +| clip_fraction | 0.43 | +| clip_range | 0.0747 | +| entropy_loss | -5.2 | +| explained_variance | 0.301 | +| learning_rate | 4.97e-05 | +| loss | -0.0335 | +| n_updates | 37924 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000232 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0368 | +| time/ | | +| fps | 1304 | +| iterations | 646 | +| time_elapsed | 1013 | +| total_timesteps | 1323008 | +| train/ | | +| approx_kl | 0.024132987 | +| clip_fraction | 0.432 | +| clip_range | 0.0747 | +| entropy_loss | -4.84 | +| explained_variance | 0.335 | +| learning_rate | 4.97e-05 | +| loss | -0.0317 | +| n_updates | 37928 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.00035 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0379 | +| time/ | | +| fps | 1304 | +| iterations | 647 | +| time_elapsed | 1015 | +| total_timesteps | 1325056 | +| train/ | | +| approx_kl | 0.025188135 | +| clip_fraction | 0.456 | +| clip_range | 0.0747 | +| entropy_loss | -4.85 | +| explained_variance | 0.485 | +| learning_rate | 4.97e-05 | +| loss | -0.0422 | +| n_updates | 37932 | +| policy_gradient_loss | -0.0251 | +| value_loss | 9.67e-05 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0394 | +| time/ | | +| fps | 1304 | +| iterations | 648 | +| time_elapsed | 1017 | +| total_timesteps | 1327104 | +| train/ | | +| approx_kl | 0.02305432 | +| clip_fraction | 0.433 | +| clip_range | 0.0747 | +| entropy_loss | -5.37 | +| explained_variance | 0.313 | +| learning_rate | 4.97e-05 | +| loss | -0.0365 | +| n_updates | 37936 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000176 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0394 | +| time/ | | +| fps | 1304 | +| iterations | 649 | +| time_elapsed | 1018 | +| total_timesteps | 1329152 | +| train/ | | +| approx_kl | 0.021349372 | +| clip_fraction | 0.437 | +| clip_range | 0.0747 | +| entropy_loss | -5.14 | +| explained_variance | 0.196 | +| learning_rate | 4.97e-05 | +| loss | -0.031 | +| n_updates | 37940 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000181 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0379 | +| time/ | | +| fps | 1304 | +| iterations | 650 | +| time_elapsed | 1020 | +| total_timesteps | 1331200 | +| train/ | | +| approx_kl | 0.022907816 | +| clip_fraction | 0.435 | +| clip_range | 0.0747 | +| entropy_loss | -5.48 | +| explained_variance | -0.0829 | +| learning_rate | 4.97e-05 | +| loss | -0.0319 | +| n_updates | 37944 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000183 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0379 | +| time/ | | +| fps | 1304 | +| iterations | 651 | +| time_elapsed | 1021 | +| total_timesteps | 1333248 | +| train/ | | +| approx_kl | 0.019522876 | +| clip_fraction | 0.404 | +| clip_range | 0.0747 | +| entropy_loss | -5.04 | +| explained_variance | 0.283 | +| learning_rate | 4.97e-05 | +| loss | -0.0276 | +| n_updates | 37948 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000262 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0361 | +| time/ | | +| fps | 1304 | +| iterations | 652 | +| time_elapsed | 1023 | +| total_timesteps | 1335296 | +| train/ | | +| approx_kl | 0.023343474 | +| clip_fraction | 0.442 | +| clip_range | 0.0747 | +| entropy_loss | -5.35 | +| explained_variance | -0.0721 | +| learning_rate | 4.97e-05 | +| loss | -0.0359 | +| n_updates | 37952 | +| policy_gradient_loss | -0.0228 | +| value_loss | 0.00028 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0419 | +| time/ | | +| fps | 1304 | +| iterations | 653 | +| time_elapsed | 1024 | +| total_timesteps | 1337344 | +| train/ | | +| approx_kl | 0.02201078 | +| clip_fraction | 0.423 | +| clip_range | 0.0747 | +| entropy_loss | -5.01 | +| explained_variance | 0.205 | +| learning_rate | 4.97e-05 | +| loss | -0.0393 | +| n_updates | 37956 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000273 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0424 | +| time/ | | +| fps | 1304 | +| iterations | 654 | +| time_elapsed | 1026 | +| total_timesteps | 1339392 | +| train/ | | +| approx_kl | 0.023100004 | +| clip_fraction | 0.421 | +| clip_range | 0.0747 | +| entropy_loss | -4.75 | +| explained_variance | 0.436 | +| learning_rate | 4.97e-05 | +| loss | -0.0308 | +| n_updates | 37960 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000275 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0433 | +| time/ | | +| fps | 1304 | +| iterations | 655 | +| time_elapsed | 1027 | +| total_timesteps | 1341440 | +| train/ | | +| approx_kl | 0.02246702 | +| clip_fraction | 0.433 | +| clip_range | 0.0747 | +| entropy_loss | -4.9 | +| explained_variance | 0.218 | +| learning_rate | 4.97e-05 | +| loss | -0.0323 | +| n_updates | 37964 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000282 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0421 | +| time/ | | +| fps | 1304 | +| iterations | 656 | +| time_elapsed | 1029 | +| total_timesteps | 1343488 | +| train/ | | +| approx_kl | 0.023717951 | +| clip_fraction | 0.437 | +| clip_range | 0.0747 | +| entropy_loss | -5.05 | +| explained_variance | 0.372 | +| learning_rate | 4.97e-05 | +| loss | -0.0343 | +| n_updates | 37968 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000185 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0448 | +| time/ | | +| fps | 1304 | +| iterations | 657 | +| time_elapsed | 1031 | +| total_timesteps | 1345536 | +| train/ | | +| approx_kl | 0.023457436 | +| clip_fraction | 0.448 | +| clip_range | 0.0747 | +| entropy_loss | -4.82 | +| explained_variance | 0.426 | +| learning_rate | 4.97e-05 | +| loss | -0.034 | +| n_updates | 37972 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000212 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0431 | +| time/ | | +| fps | 1304 | +| iterations | 658 | +| time_elapsed | 1032 | +| total_timesteps | 1347584 | +| train/ | | +| approx_kl | 0.02176458 | +| clip_fraction | 0.43 | +| clip_range | 0.0747 | +| entropy_loss | -4.95 | +| explained_variance | 0.288 | +| learning_rate | 4.97e-05 | +| loss | -0.0302 | +| n_updates | 37976 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000316 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0449 | +| time/ | | +| fps | 1304 | +| iterations | 659 | +| time_elapsed | 1034 | +| total_timesteps | 1349632 | +| train/ | | +| approx_kl | 0.024750868 | +| clip_fraction | 0.428 | +| clip_range | 0.0747 | +| entropy_loss | -4.93 | +| explained_variance | 0.247 | +| learning_rate | 4.97e-05 | +| loss | -0.0318 | +| n_updates | 37980 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000221 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0483 | +| time/ | | +| fps | 1304 | +| iterations | 660 | +| time_elapsed | 1035 | +| total_timesteps | 1351680 | +| train/ | | +| approx_kl | 0.021270698 | +| clip_fraction | 0.428 | +| clip_range | 0.0747 | +| entropy_loss | -5.04 | +| explained_variance | 0.0804 | +| learning_rate | 4.97e-05 | +| loss | -0.0311 | +| n_updates | 37984 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000378 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0495 | +| time/ | | +| fps | 1304 | +| iterations | 661 | +| time_elapsed | 1037 | +| total_timesteps | 1353728 | +| train/ | | +| approx_kl | 0.028780034 | +| clip_fraction | 0.439 | +| clip_range | 0.0747 | +| entropy_loss | -4.6 | +| explained_variance | 0.624 | +| learning_rate | 4.97e-05 | +| loss | -0.0341 | +| n_updates | 37988 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000167 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0495 | +| time/ | | +| fps | 1304 | +| iterations | 662 | +| time_elapsed | 1039 | +| total_timesteps | 1355776 | +| train/ | | +| approx_kl | 0.024029458 | +| clip_fraction | 0.44 | +| clip_range | 0.0747 | +| entropy_loss | -4.69 | +| explained_variance | 0.0779 | +| learning_rate | 4.97e-05 | +| loss | -0.0363 | +| n_updates | 37992 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000249 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0495 | +| time/ | | +| fps | 1304 | +| iterations | 663 | +| time_elapsed | 1040 | +| total_timesteps | 1357824 | +| train/ | | +| approx_kl | 0.02686027 | +| clip_fraction | 0.463 | +| clip_range | 0.0747 | +| entropy_loss | -4.93 | +| explained_variance | -0.04 | +| learning_rate | 4.97e-05 | +| loss | -0.0379 | +| n_updates | 37996 | +| policy_gradient_loss | -0.0227 | +| value_loss | 0.000147 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0516 | +| time/ | | +| fps | 1304 | +| iterations | 664 | +| time_elapsed | 1042 | +| total_timesteps | 1359872 | +| train/ | | +| approx_kl | 0.022021178 | +| clip_fraction | 0.413 | +| clip_range | 0.0747 | +| entropy_loss | -5.17 | +| explained_variance | -0.151 | +| learning_rate | 4.97e-05 | +| loss | -0.0316 | +| n_updates | 38000 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000304 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0541 | +| time/ | | +| fps | 1304 | +| iterations | 665 | +| time_elapsed | 1043 | +| total_timesteps | 1361920 | +| train/ | | +| approx_kl | 0.027321156 | +| clip_fraction | 0.428 | +| clip_range | 0.0747 | +| entropy_loss | -4.69 | +| explained_variance | 0.242 | +| learning_rate | 4.97e-05 | +| loss | -0.0374 | +| n_updates | 38004 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000326 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0546 | +| time/ | | +| fps | 1304 | +| iterations | 666 | +| time_elapsed | 1045 | +| total_timesteps | 1363968 | +| train/ | | +| approx_kl | 0.025616135 | +| clip_fraction | 0.461 | +| clip_range | 0.0747 | +| entropy_loss | -4.84 | +| explained_variance | 0.356 | +| learning_rate | 4.97e-05 | +| loss | -0.0324 | +| n_updates | 38008 | +| policy_gradient_loss | -0.0223 | +| value_loss | 0.000221 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0607 | +| time/ | | +| fps | 1305 | +| iterations | 667 | +| time_elapsed | 1046 | +| total_timesteps | 1366016 | +| train/ | | +| approx_kl | 0.026432034 | +| clip_fraction | 0.438 | +| clip_range | 0.0747 | +| entropy_loss | -4.73 | +| explained_variance | 0.336 | +| learning_rate | 4.97e-05 | +| loss | -0.0335 | +| n_updates | 38012 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000278 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0607 | +| time/ | | +| fps | 1304 | +| iterations | 668 | +| time_elapsed | 1048 | +| total_timesteps | 1368064 | +| train/ | | +| approx_kl | 0.024865594 | +| clip_fraction | 0.454 | +| clip_range | 0.0747 | +| entropy_loss | -5.04 | +| explained_variance | -0.0848 | +| learning_rate | 4.97e-05 | +| loss | -0.0352 | +| n_updates | 38016 | +| policy_gradient_loss | -0.0221 | +| value_loss | 0.000199 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0607 | +| time/ | | +| fps | 1304 | +| iterations | 669 | +| time_elapsed | 1049 | +| total_timesteps | 1370112 | +| train/ | | +| approx_kl | 0.020669565 | +| clip_fraction | 0.432 | +| clip_range | 0.0747 | +| entropy_loss | -4.79 | +| explained_variance | 0.459 | +| learning_rate | 4.97e-05 | +| loss | -0.0325 | +| n_updates | 38020 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000237 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0471 | +| time/ | | +| fps | 1304 | +| iterations | 670 | +| time_elapsed | 1051 | +| total_timesteps | 1372160 | +| train/ | | +| approx_kl | 0.02124807 | +| clip_fraction | 0.419 | +| clip_range | 0.0747 | +| entropy_loss | -5.2 | +| explained_variance | -0.234 | +| learning_rate | 4.97e-05 | +| loss | -0.0302 | +| n_updates | 38024 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000331 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.0351 | +| time/ | | +| fps | 1304 | +| iterations | 671 | +| time_elapsed | 1053 | +| total_timesteps | 1374208 | +| train/ | | +| approx_kl | 0.027668752 | +| clip_fraction | 0.45 | +| clip_range | 0.0747 | +| entropy_loss | -4.55 | +| explained_variance | 0.524 | +| learning_rate | 4.97e-05 | +| loss | -0.0374 | +| n_updates | 38028 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000194 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.0351 | +| time/ | | +| fps | 1305 | +| iterations | 672 | +| time_elapsed | 1054 | +| total_timesteps | 1376256 | +| train/ | | +| approx_kl | 0.02404501 | +| clip_fraction | 0.439 | +| clip_range | 0.0747 | +| entropy_loss | -4.65 | +| explained_variance | 0.272 | +| learning_rate | 4.97e-05 | +| loss | -0.033 | +| n_updates | 38032 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000216 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.0351 | +| time/ | | +| fps | 1305 | +| iterations | 673 | +| time_elapsed | 1056 | +| total_timesteps | 1378304 | +| train/ | | +| approx_kl | 0.02262518 | +| clip_fraction | 0.437 | +| clip_range | 0.0747 | +| entropy_loss | -5 | +| explained_variance | 0.163 | +| learning_rate | 4.97e-05 | +| loss | -0.0315 | +| n_updates | 38036 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000221 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.038 | +| time/ | | +| fps | 1305 | +| iterations | 674 | +| time_elapsed | 1057 | +| total_timesteps | 1380352 | +| train/ | | +| approx_kl | 0.023289267 | +| clip_fraction | 0.433 | +| clip_range | 0.0747 | +| entropy_loss | -5.13 | +| explained_variance | -0.0998 | +| learning_rate | 4.97e-05 | +| loss | -0.0348 | +| n_updates | 38040 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000271 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.038 | +| time/ | | +| fps | 1305 | +| iterations | 675 | +| time_elapsed | 1059 | +| total_timesteps | 1382400 | +| train/ | | +| approx_kl | 0.021497292 | +| clip_fraction | 0.444 | +| clip_range | 0.0747 | +| entropy_loss | -5.12 | +| explained_variance | -0.123 | +| learning_rate | 4.97e-05 | +| loss | -0.0395 | +| n_updates | 38044 | +| policy_gradient_loss | -0.0223 | +| value_loss | 0.000282 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.0406 | +| time/ | | +| fps | 1305 | +| iterations | 676 | +| time_elapsed | 1060 | +| total_timesteps | 1384448 | +| train/ | | +| approx_kl | 0.023009103 | +| clip_fraction | 0.44 | +| clip_range | 0.0747 | +| entropy_loss | -5.11 | +| explained_variance | -0.0228 | +| learning_rate | 4.97e-05 | +| loss | -0.0343 | +| n_updates | 38048 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000325 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.0418 | +| time/ | | +| fps | 1305 | +| iterations | 677 | +| time_elapsed | 1062 | +| total_timesteps | 1386496 | +| train/ | | +| approx_kl | 0.026135294 | +| clip_fraction | 0.433 | +| clip_range | 0.0747 | +| entropy_loss | -5.04 | +| explained_variance | -0.115 | +| learning_rate | 4.97e-05 | +| loss | -0.0357 | +| n_updates | 38052 | +| policy_gradient_loss | -0.0224 | +| value_loss | 0.000175 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.0451 | +| time/ | | +| fps | 1305 | +| iterations | 678 | +| time_elapsed | 1064 | +| total_timesteps | 1388544 | +| train/ | | +| approx_kl | 0.024121301 | +| clip_fraction | 0.409 | +| clip_range | 0.0747 | +| entropy_loss | -4.8 | +| explained_variance | 0.285 | +| learning_rate | 4.97e-05 | +| loss | -0.0348 | +| n_updates | 38056 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000294 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.0384 | +| time/ | | +| fps | 1304 | +| iterations | 679 | +| time_elapsed | 1065 | +| total_timesteps | 1390592 | +| train/ | | +| approx_kl | 0.02358085 | +| clip_fraction | 0.413 | +| clip_range | 0.0747 | +| entropy_loss | -4.92 | +| explained_variance | 0.456 | +| learning_rate | 4.97e-05 | +| loss | -0.0315 | +| n_updates | 38060 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000231 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.0388 | +| time/ | | +| fps | 1304 | +| iterations | 680 | +| time_elapsed | 1067 | +| total_timesteps | 1392640 | +| train/ | | +| approx_kl | 0.023200441 | +| clip_fraction | 0.412 | +| clip_range | 0.0747 | +| entropy_loss | -4.4 | +| explained_variance | 0.631 | +| learning_rate | 4.97e-05 | +| loss | -0.0388 | +| n_updates | 38064 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000179 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.0349 | +| time/ | | +| fps | 1304 | +| iterations | 681 | +| time_elapsed | 1068 | +| total_timesteps | 1394688 | +| train/ | | +| approx_kl | 0.026007315 | +| clip_fraction | 0.46 | +| clip_range | 0.0747 | +| entropy_loss | -4.67 | +| explained_variance | 0.409 | +| learning_rate | 4.97e-05 | +| loss | -0.0352 | +| n_updates | 38068 | +| policy_gradient_loss | -0.0212 | +| value_loss | 9.96e-05 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.0402 | +| time/ | | +| fps | 1304 | +| iterations | 682 | +| time_elapsed | 1070 | +| total_timesteps | 1396736 | +| train/ | | +| approx_kl | 0.023524359 | +| clip_fraction | 0.438 | +| clip_range | 0.0747 | +| entropy_loss | -4.87 | +| explained_variance | 0.184 | +| learning_rate | 4.97e-05 | +| loss | -0.0294 | +| n_updates | 38072 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000249 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.0402 | +| time/ | | +| fps | 1304 | +| iterations | 683 | +| time_elapsed | 1071 | +| total_timesteps | 1398784 | +| train/ | | +| approx_kl | 0.026769968 | +| clip_fraction | 0.427 | +| clip_range | 0.0747 | +| entropy_loss | -4.7 | +| explained_variance | 0.28 | +| learning_rate | 4.97e-05 | +| loss | -0.0339 | +| n_updates | 38076 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000414 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.0393 | +| time/ | | +| fps | 1304 | +| iterations | 684 | +| time_elapsed | 1073 | +| total_timesteps | 1400832 | +| train/ | | +| approx_kl | 0.029699387 | +| clip_fraction | 0.451 | +| clip_range | 0.0747 | +| entropy_loss | -4.87 | +| explained_variance | 0.203 | +| learning_rate | 4.97e-05 | +| loss | -0.0316 | +| n_updates | 38080 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000298 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.0393 | +| time/ | | +| fps | 1304 | +| iterations | 685 | +| time_elapsed | 1075 | +| total_timesteps | 1402880 | +| train/ | | +| approx_kl | 0.026441708 | +| clip_fraction | 0.452 | +| clip_range | 0.0746 | +| entropy_loss | -4.99 | +| explained_variance | 0.206 | +| learning_rate | 4.97e-05 | +| loss | -0.0293 | +| n_updates | 38084 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000207 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.0438 | +| time/ | | +| fps | 1304 | +| iterations | 686 | +| time_elapsed | 1076 | +| total_timesteps | 1404928 | +| train/ | | +| approx_kl | 0.02483293 | +| clip_fraction | 0.427 | +| clip_range | 0.0746 | +| entropy_loss | -5.25 | +| explained_variance | -0.179 | +| learning_rate | 4.97e-05 | +| loss | -0.031 | +| n_updates | 38088 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000276 | +---------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.0464 | +| time/ | | +| fps | 1304 | +| iterations | 687 | +| time_elapsed | 1078 | +| total_timesteps | 1406976 | +| train/ | | +| approx_kl | 0.0232667 | +| clip_fraction | 0.45 | +| clip_range | 0.0746 | +| entropy_loss | -4.86 | +| explained_variance | 0.391 | +| learning_rate | 4.97e-05 | +| loss | -0.032 | +| n_updates | 38092 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.00035 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0448 | +| time/ | | +| fps | 1304 | +| iterations | 688 | +| time_elapsed | 1079 | +| total_timesteps | 1409024 | +| train/ | | +| approx_kl | 0.029595716 | +| clip_fraction | 0.473 | +| clip_range | 0.0746 | +| entropy_loss | -4.5 | +| explained_variance | 0.269 | +| learning_rate | 4.97e-05 | +| loss | -0.0308 | +| n_updates | 38096 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000217 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0426 | +| time/ | | +| fps | 1304 | +| iterations | 689 | +| time_elapsed | 1081 | +| total_timesteps | 1411072 | +| train/ | | +| approx_kl | 0.028720045 | +| clip_fraction | 0.44 | +| clip_range | 0.0746 | +| entropy_loss | -4.54 | +| explained_variance | 0.377 | +| learning_rate | 4.97e-05 | +| loss | -0.0332 | +| n_updates | 38100 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.0002 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0426 | +| time/ | | +| fps | 1305 | +| iterations | 690 | +| time_elapsed | 1082 | +| total_timesteps | 1413120 | +| train/ | | +| approx_kl | 0.024926797 | +| clip_fraction | 0.448 | +| clip_range | 0.0746 | +| entropy_loss | -4.62 | +| explained_variance | 0.496 | +| learning_rate | 4.97e-05 | +| loss | -0.033 | +| n_updates | 38104 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000238 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0439 | +| time/ | | +| fps | 1304 | +| iterations | 691 | +| time_elapsed | 1084 | +| total_timesteps | 1415168 | +| train/ | | +| approx_kl | 0.026510717 | +| clip_fraction | 0.453 | +| clip_range | 0.0746 | +| entropy_loss | -4.89 | +| explained_variance | -0.0524 | +| learning_rate | 4.97e-05 | +| loss | -0.0383 | +| n_updates | 38108 | +| policy_gradient_loss | -0.0233 | +| value_loss | 0.000191 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0439 | +| time/ | | +| fps | 1304 | +| iterations | 692 | +| time_elapsed | 1086 | +| total_timesteps | 1417216 | +| train/ | | +| approx_kl | 0.01810477 | +| clip_fraction | 0.417 | +| clip_range | 0.0746 | +| entropy_loss | -4.92 | +| explained_variance | -0.0195 | +| learning_rate | 4.97e-05 | +| loss | -0.0342 | +| n_updates | 38112 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000365 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.0364 | +| time/ | | +| fps | 1304 | +| iterations | 693 | +| time_elapsed | 1087 | +| total_timesteps | 1419264 | +| train/ | | +| approx_kl | 0.021809164 | +| clip_fraction | 0.42 | +| clip_range | 0.0746 | +| entropy_loss | -4.82 | +| explained_variance | 0.252 | +| learning_rate | 4.97e-05 | +| loss | -0.0279 | +| n_updates | 38116 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000326 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.0433 | +| time/ | | +| fps | 1304 | +| iterations | 694 | +| time_elapsed | 1089 | +| total_timesteps | 1421312 | +| train/ | | +| approx_kl | 0.021239193 | +| clip_fraction | 0.437 | +| clip_range | 0.0746 | +| entropy_loss | -4.92 | +| explained_variance | 0.363 | +| learning_rate | 4.97e-05 | +| loss | -0.0336 | +| n_updates | 38120 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000309 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.0391 | +| time/ | | +| fps | 1304 | +| iterations | 695 | +| time_elapsed | 1090 | +| total_timesteps | 1423360 | +| train/ | | +| approx_kl | 0.022914346 | +| clip_fraction | 0.444 | +| clip_range | 0.0746 | +| entropy_loss | -5 | +| explained_variance | 0.128 | +| learning_rate | 4.97e-05 | +| loss | -0.0373 | +| n_updates | 38124 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000174 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.0391 | +| time/ | | +| fps | 1304 | +| iterations | 696 | +| time_elapsed | 1092 | +| total_timesteps | 1425408 | +| train/ | | +| approx_kl | 0.02225504 | +| clip_fraction | 0.442 | +| clip_range | 0.0746 | +| entropy_loss | -4.86 | +| explained_variance | 0.34 | +| learning_rate | 4.97e-05 | +| loss | -0.0329 | +| n_updates | 38128 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000241 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.0418 | +| time/ | | +| fps | 1304 | +| iterations | 697 | +| time_elapsed | 1094 | +| total_timesteps | 1427456 | +| train/ | | +| approx_kl | 0.039196897 | +| clip_fraction | 0.457 | +| clip_range | 0.0746 | +| entropy_loss | -4.78 | +| explained_variance | 0.123 | +| learning_rate | 4.97e-05 | +| loss | -0.0303 | +| n_updates | 38132 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000244 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.034 | +| time/ | | +| fps | 1304 | +| iterations | 698 | +| time_elapsed | 1095 | +| total_timesteps | 1429504 | +| train/ | | +| approx_kl | 0.024342634 | +| clip_fraction | 0.44 | +| clip_range | 0.0746 | +| entropy_loss | -4.94 | +| explained_variance | 0.306 | +| learning_rate | 4.97e-05 | +| loss | -0.0301 | +| n_updates | 38136 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000265 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.034 | +| time/ | | +| fps | 1304 | +| iterations | 699 | +| time_elapsed | 1097 | +| total_timesteps | 1431552 | +| train/ | | +| approx_kl | 0.024399523 | +| clip_fraction | 0.419 | +| clip_range | 0.0746 | +| entropy_loss | -4.35 | +| explained_variance | 0.514 | +| learning_rate | 4.97e-05 | +| loss | -0.0358 | +| n_updates | 38140 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000295 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0293 | +| time/ | | +| fps | 1304 | +| iterations | 700 | +| time_elapsed | 1098 | +| total_timesteps | 1433600 | +| train/ | | +| approx_kl | 0.028682202 | +| clip_fraction | 0.43 | +| clip_range | 0.0746 | +| entropy_loss | -4.8 | +| explained_variance | -0.0306 | +| learning_rate | 4.97e-05 | +| loss | -0.0301 | +| n_updates | 38144 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.00023 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0293 | +| time/ | | +| fps | 1304 | +| iterations | 701 | +| time_elapsed | 1100 | +| total_timesteps | 1435648 | +| train/ | | +| approx_kl | 0.024955979 | +| clip_fraction | 0.449 | +| clip_range | 0.0746 | +| entropy_loss | -4.92 | +| explained_variance | 0.0998 | +| learning_rate | 4.97e-05 | +| loss | -0.0357 | +| n_updates | 38148 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.00028 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0448 | +| time/ | | +| fps | 1304 | +| iterations | 702 | +| time_elapsed | 1101 | +| total_timesteps | 1437696 | +| train/ | | +| approx_kl | 0.02181009 | +| clip_fraction | 0.43 | +| clip_range | 0.0746 | +| entropy_loss | -5.17 | +| explained_variance | -0.0184 | +| learning_rate | 4.97e-05 | +| loss | -0.0342 | +| n_updates | 38152 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.00035 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0448 | +| time/ | | +| fps | 1304 | +| iterations | 703 | +| time_elapsed | 1103 | +| total_timesteps | 1439744 | +| train/ | | +| approx_kl | 0.021724727 | +| clip_fraction | 0.419 | +| clip_range | 0.0746 | +| entropy_loss | -4.61 | +| explained_variance | 0.41 | +| learning_rate | 4.97e-05 | +| loss | -0.0363 | +| n_updates | 38156 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000343 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0506 | +| time/ | | +| fps | 1304 | +| iterations | 704 | +| time_elapsed | 1105 | +| total_timesteps | 1441792 | +| train/ | | +| approx_kl | 0.029498836 | +| clip_fraction | 0.451 | +| clip_range | 0.0746 | +| entropy_loss | -4.85 | +| explained_variance | 0.322 | +| learning_rate | 4.97e-05 | +| loss | -0.0363 | +| n_updates | 38160 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000228 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0556 | +| time/ | | +| fps | 1304 | +| iterations | 705 | +| time_elapsed | 1106 | +| total_timesteps | 1443840 | +| train/ | | +| approx_kl | 0.022917826 | +| clip_fraction | 0.44 | +| clip_range | 0.0746 | +| entropy_loss | -4.86 | +| explained_variance | 0.329 | +| learning_rate | 4.97e-05 | +| loss | -0.0319 | +| n_updates | 38164 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000294 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0526 | +| time/ | | +| fps | 1304 | +| iterations | 706 | +| time_elapsed | 1108 | +| total_timesteps | 1445888 | +| train/ | | +| approx_kl | 0.025429096 | +| clip_fraction | 0.444 | +| clip_range | 0.0746 | +| entropy_loss | -4.78 | +| explained_variance | 0.473 | +| learning_rate | 4.97e-05 | +| loss | -0.0314 | +| n_updates | 38168 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000186 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0537 | +| time/ | | +| fps | 1304 | +| iterations | 707 | +| time_elapsed | 1109 | +| total_timesteps | 1447936 | +| train/ | | +| approx_kl | 0.020986028 | +| clip_fraction | 0.423 | +| clip_range | 0.0746 | +| entropy_loss | -4.62 | +| explained_variance | 0.321 | +| learning_rate | 4.97e-05 | +| loss | -0.0367 | +| n_updates | 38172 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000274 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0537 | +| time/ | | +| fps | 1304 | +| iterations | 708 | +| time_elapsed | 1111 | +| total_timesteps | 1449984 | +| train/ | | +| approx_kl | 0.022717852 | +| clip_fraction | 0.443 | +| clip_range | 0.0746 | +| entropy_loss | -4.57 | +| explained_variance | 0.467 | +| learning_rate | 4.97e-05 | +| loss | -0.0329 | +| n_updates | 38176 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.00019 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0537 | +| time/ | | +| fps | 1304 | +| iterations | 709 | +| time_elapsed | 1112 | +| total_timesteps | 1452032 | +| train/ | | +| approx_kl | 0.029054841 | +| clip_fraction | 0.439 | +| clip_range | 0.0746 | +| entropy_loss | -4.67 | +| explained_variance | 0.064 | +| learning_rate | 4.97e-05 | +| loss | -0.0319 | +| n_updates | 38180 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000208 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0509 | +| time/ | | +| fps | 1304 | +| iterations | 710 | +| time_elapsed | 1114 | +| total_timesteps | 1454080 | +| train/ | | +| approx_kl | 0.023613162 | +| clip_fraction | 0.438 | +| clip_range | 0.0746 | +| entropy_loss | -4.99 | +| explained_variance | -0.154 | +| learning_rate | 4.97e-05 | +| loss | -0.034 | +| n_updates | 38184 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000222 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0543 | +| time/ | | +| fps | 1304 | +| iterations | 711 | +| time_elapsed | 1115 | +| total_timesteps | 1456128 | +| train/ | | +| approx_kl | 0.020610696 | +| clip_fraction | 0.426 | +| clip_range | 0.0746 | +| entropy_loss | -5.13 | +| explained_variance | -0.098 | +| learning_rate | 4.97e-05 | +| loss | -0.0369 | +| n_updates | 38188 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000329 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0505 | +| time/ | | +| fps | 1304 | +| iterations | 712 | +| time_elapsed | 1117 | +| total_timesteps | 1458176 | +| train/ | | +| approx_kl | 0.02533308 | +| clip_fraction | 0.449 | +| clip_range | 0.0746 | +| entropy_loss | -4.88 | +| explained_variance | 0.209 | +| learning_rate | 4.97e-05 | +| loss | -0.0354 | +| n_updates | 38192 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000233 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0429 | +| time/ | | +| fps | 1304 | +| iterations | 713 | +| time_elapsed | 1118 | +| total_timesteps | 1460224 | +| train/ | | +| approx_kl | 0.022762135 | +| clip_fraction | 0.451 | +| clip_range | 0.0746 | +| entropy_loss | -5.01 | +| explained_variance | 0.514 | +| learning_rate | 4.97e-05 | +| loss | -0.0349 | +| n_updates | 38196 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000245 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0394 | +| time/ | | +| fps | 1305 | +| iterations | 714 | +| time_elapsed | 1120 | +| total_timesteps | 1462272 | +| train/ | | +| approx_kl | 0.02479355 | +| clip_fraction | 0.414 | +| clip_range | 0.0746 | +| entropy_loss | -4.32 | +| explained_variance | 0.684 | +| learning_rate | 4.97e-05 | +| loss | -0.0258 | +| n_updates | 38200 | +| policy_gradient_loss | -0.0169 | +| value_loss | 0.000147 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0415 | +| time/ | | +| fps | 1305 | +| iterations | 715 | +| time_elapsed | 1122 | +| total_timesteps | 1464320 | +| train/ | | +| approx_kl | 0.026029732 | +| clip_fraction | 0.434 | +| clip_range | 0.0746 | +| entropy_loss | -4.91 | +| explained_variance | 0.284 | +| learning_rate | 4.97e-05 | +| loss | -0.0292 | +| n_updates | 38204 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000265 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0406 | +| time/ | | +| fps | 1305 | +| iterations | 716 | +| time_elapsed | 1123 | +| total_timesteps | 1466368 | +| train/ | | +| approx_kl | 0.02458802 | +| clip_fraction | 0.452 | +| clip_range | 0.0746 | +| entropy_loss | -4.95 | +| explained_variance | 0.0693 | +| learning_rate | 4.97e-05 | +| loss | -0.0373 | +| n_updates | 38208 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000321 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.036 | +| time/ | | +| fps | 1305 | +| iterations | 717 | +| time_elapsed | 1125 | +| total_timesteps | 1468416 | +| train/ | | +| approx_kl | 0.024210652 | +| clip_fraction | 0.434 | +| clip_range | 0.0746 | +| entropy_loss | -4.95 | +| explained_variance | 0.116 | +| learning_rate | 4.97e-05 | +| loss | -0.0332 | +| n_updates | 38212 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.00039 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0309 | +| time/ | | +| fps | 1305 | +| iterations | 718 | +| time_elapsed | 1126 | +| total_timesteps | 1470464 | +| train/ | | +| approx_kl | 0.028539047 | +| clip_fraction | 0.46 | +| clip_range | 0.0746 | +| entropy_loss | -4.79 | +| explained_variance | 0.192 | +| learning_rate | 4.97e-05 | +| loss | -0.0337 | +| n_updates | 38216 | +| policy_gradient_loss | -0.0224 | +| value_loss | 0.000285 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0325 | +| time/ | | +| fps | 1305 | +| iterations | 719 | +| time_elapsed | 1128 | +| total_timesteps | 1472512 | +| train/ | | +| approx_kl | 0.025703894 | +| clip_fraction | 0.407 | +| clip_range | 0.0746 | +| entropy_loss | -4.36 | +| explained_variance | 0.44 | +| learning_rate | 4.97e-05 | +| loss | -0.0225 | +| n_updates | 38220 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000251 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0309 | +| time/ | | +| fps | 1305 | +| iterations | 720 | +| time_elapsed | 1129 | +| total_timesteps | 1474560 | +| train/ | | +| approx_kl | 0.02889461 | +| clip_fraction | 0.451 | +| clip_range | 0.0746 | +| entropy_loss | -4.66 | +| explained_variance | -0.00572 | +| learning_rate | 4.97e-05 | +| loss | -0.0391 | +| n_updates | 38224 | +| policy_gradient_loss | -0.0221 | +| value_loss | 0.000223 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0309 | +| time/ | | +| fps | 1305 | +| iterations | 721 | +| time_elapsed | 1131 | +| total_timesteps | 1476608 | +| train/ | | +| approx_kl | 0.02745518 | +| clip_fraction | 0.43 | +| clip_range | 0.0746 | +| entropy_loss | -4.21 | +| explained_variance | 0.475 | +| learning_rate | 4.96e-05 | +| loss | -0.0318 | +| n_updates | 38228 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000236 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0309 | +| time/ | | +| fps | 1305 | +| iterations | 722 | +| time_elapsed | 1132 | +| total_timesteps | 1478656 | +| train/ | | +| approx_kl | 0.025460336 | +| clip_fraction | 0.454 | +| clip_range | 0.0746 | +| entropy_loss | -4.81 | +| explained_variance | 0.149 | +| learning_rate | 4.96e-05 | +| loss | -0.0362 | +| n_updates | 38232 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000216 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0312 | +| time/ | | +| fps | 1305 | +| iterations | 723 | +| time_elapsed | 1134 | +| total_timesteps | 1480704 | +| train/ | | +| approx_kl | 0.02207723 | +| clip_fraction | 0.442 | +| clip_range | 0.0746 | +| entropy_loss | -5.06 | +| explained_variance | 0.0128 | +| learning_rate | 4.96e-05 | +| loss | -0.0338 | +| n_updates | 38236 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000297 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0305 | +| time/ | | +| fps | 1305 | +| iterations | 724 | +| time_elapsed | 1135 | +| total_timesteps | 1482752 | +| train/ | | +| approx_kl | 0.024344381 | +| clip_fraction | 0.432 | +| clip_range | 0.0746 | +| entropy_loss | -4.88 | +| explained_variance | 0.255 | +| learning_rate | 4.96e-05 | +| loss | -0.0338 | +| n_updates | 38240 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000317 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0234 | +| time/ | | +| fps | 1305 | +| iterations | 725 | +| time_elapsed | 1137 | +| total_timesteps | 1484800 | +| train/ | | +| approx_kl | 0.024598546 | +| clip_fraction | 0.453 | +| clip_range | 0.0746 | +| entropy_loss | -4.98 | +| explained_variance | -0.0824 | +| learning_rate | 4.96e-05 | +| loss | -0.0309 | +| n_updates | 38244 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000251 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.0295 | +| time/ | | +| fps | 1305 | +| iterations | 726 | +| time_elapsed | 1139 | +| total_timesteps | 1486848 | +| train/ | | +| approx_kl | 0.020895101 | +| clip_fraction | 0.438 | +| clip_range | 0.0746 | +| entropy_loss | -4.96 | +| explained_variance | 0.201 | +| learning_rate | 4.96e-05 | +| loss | -0.0325 | +| n_updates | 38248 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000387 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.036 | +| time/ | | +| fps | 1305 | +| iterations | 727 | +| time_elapsed | 1140 | +| total_timesteps | 1488896 | +| train/ | | +| approx_kl | 0.021232443 | +| clip_fraction | 0.446 | +| clip_range | 0.0746 | +| entropy_loss | -4.72 | +| explained_variance | 0.407 | +| learning_rate | 4.96e-05 | +| loss | -0.0362 | +| n_updates | 38252 | +| policy_gradient_loss | -0.0219 | +| value_loss | 0.000218 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.0421 | +| time/ | | +| fps | 1305 | +| iterations | 728 | +| time_elapsed | 1142 | +| total_timesteps | 1490944 | +| train/ | | +| approx_kl | 0.023507098 | +| clip_fraction | 0.458 | +| clip_range | 0.0746 | +| entropy_loss | -4.77 | +| explained_variance | 0.263 | +| learning_rate | 4.96e-05 | +| loss | -0.0313 | +| n_updates | 38256 | +| policy_gradient_loss | -0.022 | +| value_loss | 0.0002 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.0414 | +| time/ | | +| fps | 1305 | +| iterations | 729 | +| time_elapsed | 1143 | +| total_timesteps | 1492992 | +| train/ | | +| approx_kl | 0.026208159 | +| clip_fraction | 0.416 | +| clip_range | 0.0746 | +| entropy_loss | -4.82 | +| explained_variance | 0.0467 | +| learning_rate | 4.96e-05 | +| loss | -0.0247 | +| n_updates | 38260 | +| policy_gradient_loss | -0.0142 | +| value_loss | 0.000843 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.0414 | +| time/ | | +| fps | 1305 | +| iterations | 730 | +| time_elapsed | 1145 | +| total_timesteps | 1495040 | +| train/ | | +| approx_kl | 0.027638886 | +| clip_fraction | 0.458 | +| clip_range | 0.0746 | +| entropy_loss | -4.57 | +| explained_variance | 0.336 | +| learning_rate | 4.96e-05 | +| loss | -0.0374 | +| n_updates | 38264 | +| policy_gradient_loss | -0.0257 | +| value_loss | 0.000253 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.0428 | +| time/ | | +| fps | 1305 | +| iterations | 731 | +| time_elapsed | 1146 | +| total_timesteps | 1497088 | +| train/ | | +| approx_kl | 0.022191068 | +| clip_fraction | 0.458 | +| clip_range | 0.0746 | +| entropy_loss | -4.82 | +| explained_variance | -0.286 | +| learning_rate | 4.96e-05 | +| loss | -0.0432 | +| n_updates | 38268 | +| policy_gradient_loss | -0.0239 | +| value_loss | 0.000282 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0416 | +| time/ | | +| fps | 1305 | +| iterations | 732 | +| time_elapsed | 1148 | +| total_timesteps | 1499136 | +| train/ | | +| approx_kl | 0.022056941 | +| clip_fraction | 0.448 | +| clip_range | 0.0746 | +| entropy_loss | -4.96 | +| explained_variance | 0.0644 | +| learning_rate | 4.96e-05 | +| loss | -0.0369 | +| n_updates | 38272 | +| policy_gradient_loss | -0.0231 | +| value_loss | 0.000293 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0475 | +| time/ | | +| fps | 1305 | +| iterations | 733 | +| time_elapsed | 1150 | +| total_timesteps | 1501184 | +| train/ | | +| approx_kl | 0.02592947 | +| clip_fraction | 0.467 | +| clip_range | 0.0746 | +| entropy_loss | -4.74 | +| explained_variance | 0.386 | +| learning_rate | 4.96e-05 | +| loss | -0.0357 | +| n_updates | 38276 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000178 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.0416 | +| time/ | | +| fps | 1305 | +| iterations | 734 | +| time_elapsed | 1151 | +| total_timesteps | 1503232 | +| train/ | | +| approx_kl | 0.027077507 | +| clip_fraction | 0.47 | +| clip_range | 0.0746 | +| entropy_loss | -4.59 | +| explained_variance | 0.198 | +| learning_rate | 4.96e-05 | +| loss | -0.0347 | +| n_updates | 38280 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000257 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.0379 | +| time/ | | +| fps | 1305 | +| iterations | 735 | +| time_elapsed | 1153 | +| total_timesteps | 1505280 | +| train/ | | +| approx_kl | 0.026616955 | +| clip_fraction | 0.444 | +| clip_range | 0.0746 | +| entropy_loss | -4.81 | +| explained_variance | 0.241 | +| learning_rate | 4.96e-05 | +| loss | -0.0372 | +| n_updates | 38284 | +| policy_gradient_loss | -0.0222 | +| value_loss | 0.000283 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.0381 | +| time/ | | +| fps | 1305 | +| iterations | 736 | +| time_elapsed | 1154 | +| total_timesteps | 1507328 | +| train/ | | +| approx_kl | 0.023955565 | +| clip_fraction | 0.431 | +| clip_range | 0.0746 | +| entropy_loss | -4.63 | +| explained_variance | 0.372 | +| learning_rate | 4.96e-05 | +| loss | -0.0291 | +| n_updates | 38288 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000287 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.0343 | +| time/ | | +| fps | 1305 | +| iterations | 737 | +| time_elapsed | 1156 | +| total_timesteps | 1509376 | +| train/ | | +| approx_kl | 0.0252774 | +| clip_fraction | 0.452 | +| clip_range | 0.0746 | +| entropy_loss | -4.9 | +| explained_variance | -0.237 | +| learning_rate | 4.96e-05 | +| loss | -0.0339 | +| n_updates | 38292 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000222 | +--------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.0337 | +| time/ | | +| fps | 1305 | +| iterations | 738 | +| time_elapsed | 1157 | +| total_timesteps | 1511424 | +| train/ | | +| approx_kl | 0.03096497 | +| clip_fraction | 0.451 | +| clip_range | 0.0746 | +| entropy_loss | -4.66 | +| explained_variance | 0.197 | +| learning_rate | 4.96e-05 | +| loss | -0.034 | +| n_updates | 38296 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000299 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.0337 | +| time/ | | +| fps | 1305 | +| iterations | 739 | +| time_elapsed | 1159 | +| total_timesteps | 1513472 | +| train/ | | +| approx_kl | 0.023824621 | +| clip_fraction | 0.452 | +| clip_range | 0.0746 | +| entropy_loss | -4.71 | +| explained_variance | -0.0504 | +| learning_rate | 4.96e-05 | +| loss | -0.0314 | +| n_updates | 38300 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000325 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.0337 | +| time/ | | +| fps | 1305 | +| iterations | 740 | +| time_elapsed | 1160 | +| total_timesteps | 1515520 | +| train/ | | +| approx_kl | 0.021655798 | +| clip_fraction | 0.445 | +| clip_range | 0.0746 | +| entropy_loss | -4.79 | +| explained_variance | -0.219 | +| learning_rate | 4.96e-05 | +| loss | -0.0311 | +| n_updates | 38304 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.00028 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.0306 | +| time/ | | +| fps | 1305 | +| iterations | 741 | +| time_elapsed | 1162 | +| total_timesteps | 1517568 | +| train/ | | +| approx_kl | 0.025211502 | +| clip_fraction | 0.462 | +| clip_range | 0.0746 | +| entropy_loss | -4.82 | +| explained_variance | -0.0303 | +| learning_rate | 4.96e-05 | +| loss | -0.0378 | +| n_updates | 38308 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000227 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.0295 | +| time/ | | +| fps | 1305 | +| iterations | 742 | +| time_elapsed | 1164 | +| total_timesteps | 1519616 | +| train/ | | +| approx_kl | 0.027475523 | +| clip_fraction | 0.438 | +| clip_range | 0.0746 | +| entropy_loss | -4.7 | +| explained_variance | 0.332 | +| learning_rate | 4.96e-05 | +| loss | -0.0306 | +| n_updates | 38312 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000291 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.0337 | +| time/ | | +| fps | 1305 | +| iterations | 743 | +| time_elapsed | 1165 | +| total_timesteps | 1521664 | +| train/ | | +| approx_kl | 0.029935684 | +| clip_fraction | 0.484 | +| clip_range | 0.0746 | +| entropy_loss | -4.42 | +| explained_variance | 0.479 | +| learning_rate | 4.96e-05 | +| loss | -0.0364 | +| n_updates | 38316 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000193 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.0276 | +| time/ | | +| fps | 1305 | +| iterations | 744 | +| time_elapsed | 1167 | +| total_timesteps | 1523712 | +| train/ | | +| approx_kl | 0.027708333 | +| clip_fraction | 0.462 | +| clip_range | 0.0746 | +| entropy_loss | -4.91 | +| explained_variance | -0.0745 | +| learning_rate | 4.96e-05 | +| loss | -0.0319 | +| n_updates | 38320 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000356 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.0289 | +| time/ | | +| fps | 1305 | +| iterations | 745 | +| time_elapsed | 1168 | +| total_timesteps | 1525760 | +| train/ | | +| approx_kl | 0.026088018 | +| clip_fraction | 0.428 | +| clip_range | 0.0746 | +| entropy_loss | -4.6 | +| explained_variance | 0.502 | +| learning_rate | 4.96e-05 | +| loss | -0.037 | +| n_updates | 38324 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000201 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.0289 | +| time/ | | +| fps | 1305 | +| iterations | 746 | +| time_elapsed | 1170 | +| total_timesteps | 1527808 | +| train/ | | +| approx_kl | 0.02919488 | +| clip_fraction | 0.471 | +| clip_range | 0.0746 | +| entropy_loss | -4.68 | +| explained_variance | -0.103 | +| learning_rate | 4.96e-05 | +| loss | -0.0359 | +| n_updates | 38328 | +| policy_gradient_loss | -0.0222 | +| value_loss | 0.000294 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.0266 | +| time/ | | +| fps | 1305 | +| iterations | 747 | +| time_elapsed | 1172 | +| total_timesteps | 1529856 | +| train/ | | +| approx_kl | 0.027148116 | +| clip_fraction | 0.487 | +| clip_range | 0.0746 | +| entropy_loss | -4.97 | +| explained_variance | -0.233 | +| learning_rate | 4.96e-05 | +| loss | -0.0351 | +| n_updates | 38332 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000361 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.0304 | +| time/ | | +| fps | 1305 | +| iterations | 748 | +| time_elapsed | 1173 | +| total_timesteps | 1531904 | +| train/ | | +| approx_kl | 0.024121651 | +| clip_fraction | 0.458 | +| clip_range | 0.0746 | +| entropy_loss | -4.86 | +| explained_variance | -0.0207 | +| learning_rate | 4.96e-05 | +| loss | -0.0339 | +| n_updates | 38336 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000244 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.0291 | +| time/ | | +| fps | 1305 | +| iterations | 749 | +| time_elapsed | 1175 | +| total_timesteps | 1533952 | +| train/ | | +| approx_kl | 0.028125731 | +| clip_fraction | 0.461 | +| clip_range | 0.0746 | +| entropy_loss | -4.62 | +| explained_variance | 0.188 | +| learning_rate | 4.96e-05 | +| loss | -0.0336 | +| n_updates | 38340 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000306 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.0322 | +| time/ | | +| fps | 1305 | +| iterations | 750 | +| time_elapsed | 1176 | +| total_timesteps | 1536000 | +| train/ | | +| approx_kl | 0.024931423 | +| clip_fraction | 0.466 | +| clip_range | 0.0746 | +| entropy_loss | -4.89 | +| explained_variance | 0.175 | +| learning_rate | 4.96e-05 | +| loss | -0.036 | +| n_updates | 38344 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.00024 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0274 | +| time/ | | +| fps | 1305 | +| iterations | 751 | +| time_elapsed | 1178 | +| total_timesteps | 1538048 | +| train/ | | +| approx_kl | 0.024809279 | +| clip_fraction | 0.452 | +| clip_range | 0.0746 | +| entropy_loss | -4.78 | +| explained_variance | -0.0406 | +| learning_rate | 4.96e-05 | +| loss | -0.0347 | +| n_updates | 38348 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000354 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0306 | +| time/ | | +| fps | 1304 | +| iterations | 752 | +| time_elapsed | 1180 | +| total_timesteps | 1540096 | +| train/ | | +| approx_kl | 0.026700899 | +| clip_fraction | 0.46 | +| clip_range | 0.0746 | +| entropy_loss | -4.81 | +| explained_variance | -0.663 | +| learning_rate | 4.96e-05 | +| loss | -0.0321 | +| n_updates | 38352 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000187 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0328 | +| time/ | | +| fps | 1304 | +| iterations | 753 | +| time_elapsed | 1181 | +| total_timesteps | 1542144 | +| train/ | | +| approx_kl | 0.024990972 | +| clip_fraction | 0.443 | +| clip_range | 0.0746 | +| entropy_loss | -4.43 | +| explained_variance | 0.0383 | +| learning_rate | 4.96e-05 | +| loss | -0.0206 | +| n_updates | 38356 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000281 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0371 | +| time/ | | +| fps | 1304 | +| iterations | 754 | +| time_elapsed | 1183 | +| total_timesteps | 1544192 | +| train/ | | +| approx_kl | 0.025680069 | +| clip_fraction | 0.438 | +| clip_range | 0.0746 | +| entropy_loss | -4.65 | +| explained_variance | 0.208 | +| learning_rate | 4.96e-05 | +| loss | -0.0332 | +| n_updates | 38360 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000231 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0284 | +| time/ | | +| fps | 1304 | +| iterations | 755 | +| time_elapsed | 1184 | +| total_timesteps | 1546240 | +| train/ | | +| approx_kl | 0.025759675 | +| clip_fraction | 0.46 | +| clip_range | 0.0746 | +| entropy_loss | -4.75 | +| explained_variance | 0.0318 | +| learning_rate | 4.96e-05 | +| loss | -0.034 | +| n_updates | 38364 | +| policy_gradient_loss | -0.0219 | +| value_loss | 0.000275 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0284 | +| time/ | | +| fps | 1304 | +| iterations | 756 | +| time_elapsed | 1186 | +| total_timesteps | 1548288 | +| train/ | | +| approx_kl | 0.024305861 | +| clip_fraction | 0.441 | +| clip_range | 0.0746 | +| entropy_loss | -4.88 | +| explained_variance | 0.203 | +| learning_rate | 4.96e-05 | +| loss | -0.0308 | +| n_updates | 38368 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000328 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.0235 | +| time/ | | +| fps | 1304 | +| iterations | 757 | +| time_elapsed | 1188 | +| total_timesteps | 1550336 | +| train/ | | +| approx_kl | 0.023129674 | +| clip_fraction | 0.445 | +| clip_range | 0.0746 | +| entropy_loss | -4.68 | +| explained_variance | 0.0531 | +| learning_rate | 4.96e-05 | +| loss | -0.0348 | +| n_updates | 38372 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000361 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.0312 | +| time/ | | +| fps | 1304 | +| iterations | 758 | +| time_elapsed | 1189 | +| total_timesteps | 1552384 | +| train/ | | +| approx_kl | 0.022055298 | +| clip_fraction | 0.427 | +| clip_range | 0.0746 | +| entropy_loss | -5.11 | +| explained_variance | 0.223 | +| learning_rate | 4.96e-05 | +| loss | -0.036 | +| n_updates | 38376 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000315 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.0304 | +| time/ | | +| fps | 1304 | +| iterations | 759 | +| time_elapsed | 1191 | +| total_timesteps | 1554432 | +| train/ | | +| approx_kl | 0.02402049 | +| clip_fraction | 0.45 | +| clip_range | 0.0746 | +| entropy_loss | -4.64 | +| explained_variance | 0.407 | +| learning_rate | 4.96e-05 | +| loss | -0.0354 | +| n_updates | 38380 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000302 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.0347 | +| time/ | | +| fps | 1304 | +| iterations | 760 | +| time_elapsed | 1192 | +| total_timesteps | 1556480 | +| train/ | | +| approx_kl | 0.024372261 | +| clip_fraction | 0.463 | +| clip_range | 0.0746 | +| entropy_loss | -4.67 | +| explained_variance | 0.206 | +| learning_rate | 4.96e-05 | +| loss | -0.0327 | +| n_updates | 38384 | +| policy_gradient_loss | -0.0222 | +| value_loss | 0.000247 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.0326 | +| time/ | | +| fps | 1304 | +| iterations | 761 | +| time_elapsed | 1194 | +| total_timesteps | 1558528 | +| train/ | | +| approx_kl | 0.030298922 | +| clip_fraction | 0.438 | +| clip_range | 0.0746 | +| entropy_loss | -4.4 | +| explained_variance | 0.399 | +| learning_rate | 4.96e-05 | +| loss | -0.0318 | +| n_updates | 38388 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000261 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.0233 | +| time/ | | +| fps | 1304 | +| iterations | 762 | +| time_elapsed | 1195 | +| total_timesteps | 1560576 | +| train/ | | +| approx_kl | 0.029849797 | +| clip_fraction | 0.458 | +| clip_range | 0.0746 | +| entropy_loss | -4.45 | +| explained_variance | 0.186 | +| learning_rate | 4.96e-05 | +| loss | -0.0328 | +| n_updates | 38392 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000323 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.0181 | +| time/ | | +| fps | 1304 | +| iterations | 763 | +| time_elapsed | 1197 | +| total_timesteps | 1562624 | +| train/ | | +| approx_kl | 0.028654065 | +| clip_fraction | 0.447 | +| clip_range | 0.0746 | +| entropy_loss | -4.47 | +| explained_variance | 0.228 | +| learning_rate | 4.96e-05 | +| loss | -0.0413 | +| n_updates | 38396 | +| policy_gradient_loss | -0.023 | +| value_loss | 0.000224 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.0167 | +| time/ | | +| fps | 1304 | +| iterations | 764 | +| time_elapsed | 1199 | +| total_timesteps | 1564672 | +| train/ | | +| approx_kl | 0.030807193 | +| clip_fraction | 0.447 | +| clip_range | 0.0746 | +| entropy_loss | -4.67 | +| explained_variance | 0.13 | +| learning_rate | 4.96e-05 | +| loss | -0.0291 | +| n_updates | 38400 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000325 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.0167 | +| time/ | | +| fps | 1304 | +| iterations | 765 | +| time_elapsed | 1200 | +| total_timesteps | 1566720 | +| train/ | | +| approx_kl | 0.029491676 | +| clip_fraction | 0.438 | +| clip_range | 0.0746 | +| entropy_loss | -4.56 | +| explained_variance | 0.402 | +| learning_rate | 4.96e-05 | +| loss | -0.0346 | +| n_updates | 38404 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.00027 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.0141 | +| time/ | | +| fps | 1304 | +| iterations | 766 | +| time_elapsed | 1202 | +| total_timesteps | 1568768 | +| train/ | | +| approx_kl | 0.027323524 | +| clip_fraction | 0.457 | +| clip_range | 0.0746 | +| entropy_loss | -4.68 | +| explained_variance | -0.258 | +| learning_rate | 4.96e-05 | +| loss | -0.034 | +| n_updates | 38408 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000334 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.0141 | +| time/ | | +| fps | 1304 | +| iterations | 767 | +| time_elapsed | 1204 | +| total_timesteps | 1570816 | +| train/ | | +| approx_kl | 0.02627072 | +| clip_fraction | 0.451 | +| clip_range | 0.0746 | +| entropy_loss | -4.82 | +| explained_variance | -0.244 | +| learning_rate | 4.96e-05 | +| loss | -0.0323 | +| n_updates | 38412 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000272 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.0166 | +| time/ | | +| fps | 1304 | +| iterations | 768 | +| time_elapsed | 1205 | +| total_timesteps | 1572864 | +| train/ | | +| approx_kl | 0.023493573 | +| clip_fraction | 0.459 | +| clip_range | 0.0746 | +| entropy_loss | -4.94 | +| explained_variance | -0.0372 | +| learning_rate | 4.96e-05 | +| loss | -0.0374 | +| n_updates | 38416 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000184 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.00801 | +| time/ | | +| fps | 1304 | +| iterations | 769 | +| time_elapsed | 1207 | +| total_timesteps | 1574912 | +| train/ | | +| approx_kl | 0.023815114 | +| clip_fraction | 0.437 | +| clip_range | 0.0746 | +| entropy_loss | -5.03 | +| explained_variance | -0.101 | +| learning_rate | 4.96e-05 | +| loss | -0.0273 | +| n_updates | 38420 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000298 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.00923 | +| time/ | | +| fps | 1304 | +| iterations | 770 | +| time_elapsed | 1208 | +| total_timesteps | 1576960 | +| train/ | | +| approx_kl | 0.025128072 | +| clip_fraction | 0.429 | +| clip_range | 0.0746 | +| entropy_loss | -4.67 | +| explained_variance | 0.227 | +| learning_rate | 4.96e-05 | +| loss | -0.0345 | +| n_updates | 38424 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000209 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.0175 | +| time/ | | +| fps | 1304 | +| iterations | 771 | +| time_elapsed | 1210 | +| total_timesteps | 1579008 | +| train/ | | +| approx_kl | 0.024553241 | +| clip_fraction | 0.452 | +| clip_range | 0.0746 | +| entropy_loss | -4.35 | +| explained_variance | 0.556 | +| learning_rate | 4.96e-05 | +| loss | -0.0339 | +| n_updates | 38428 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000184 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.0175 | +| time/ | | +| fps | 1304 | +| iterations | 772 | +| time_elapsed | 1212 | +| total_timesteps | 1581056 | +| train/ | | +| approx_kl | 0.024644075 | +| clip_fraction | 0.406 | +| clip_range | 0.0746 | +| entropy_loss | -4.53 | +| explained_variance | 0.195 | +| learning_rate | 4.96e-05 | +| loss | -0.0302 | +| n_updates | 38432 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000401 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.0241 | +| time/ | | +| fps | 1304 | +| iterations | 773 | +| time_elapsed | 1213 | +| total_timesteps | 1583104 | +| train/ | | +| approx_kl | 0.025982441 | +| clip_fraction | 0.453 | +| clip_range | 0.0746 | +| entropy_loss | -4.58 | +| explained_variance | 0.098 | +| learning_rate | 4.96e-05 | +| loss | -0.0347 | +| n_updates | 38436 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000309 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.0222 | +| time/ | | +| fps | 1304 | +| iterations | 774 | +| time_elapsed | 1215 | +| total_timesteps | 1585152 | +| train/ | | +| approx_kl | 0.030254325 | +| clip_fraction | 0.45 | +| clip_range | 0.0746 | +| entropy_loss | -4.54 | +| explained_variance | 0.169 | +| learning_rate | 4.96e-05 | +| loss | -0.0349 | +| n_updates | 38440 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000316 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.0194 | +| time/ | | +| fps | 1304 | +| iterations | 775 | +| time_elapsed | 1216 | +| total_timesteps | 1587200 | +| train/ | | +| approx_kl | 0.033708557 | +| clip_fraction | 0.463 | +| clip_range | 0.0746 | +| entropy_loss | -4.49 | +| explained_variance | 0.254 | +| learning_rate | 4.96e-05 | +| loss | -0.036 | +| n_updates | 38444 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000292 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.0194 | +| time/ | | +| fps | 1304 | +| iterations | 776 | +| time_elapsed | 1218 | +| total_timesteps | 1589248 | +| train/ | | +| approx_kl | 0.027131831 | +| clip_fraction | 0.441 | +| clip_range | 0.0746 | +| entropy_loss | -4.74 | +| explained_variance | 0.0967 | +| learning_rate | 4.96e-05 | +| loss | -0.0382 | +| n_updates | 38448 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000319 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.0196 | +| time/ | | +| fps | 1304 | +| iterations | 777 | +| time_elapsed | 1219 | +| total_timesteps | 1591296 | +| train/ | | +| approx_kl | 0.028376494 | +| clip_fraction | 0.476 | +| clip_range | 0.0746 | +| entropy_loss | -4.88 | +| explained_variance | -0.128 | +| learning_rate | 4.96e-05 | +| loss | -0.0387 | +| n_updates | 38452 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000331 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.0261 | +| time/ | | +| fps | 1304 | +| iterations | 778 | +| time_elapsed | 1221 | +| total_timesteps | 1593344 | +| train/ | | +| approx_kl | 0.025751773 | +| clip_fraction | 0.452 | +| clip_range | 0.0746 | +| entropy_loss | -4.84 | +| explained_variance | -0.0851 | +| learning_rate | 4.96e-05 | +| loss | -0.0327 | +| n_updates | 38456 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000307 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.0402 | +| time/ | | +| fps | 1304 | +| iterations | 779 | +| time_elapsed | 1223 | +| total_timesteps | 1595392 | +| train/ | | +| approx_kl | 0.026690299 | +| clip_fraction | 0.446 | +| clip_range | 0.0746 | +| entropy_loss | -4.68 | +| explained_variance | 0.412 | +| learning_rate | 4.96e-05 | +| loss | -0.0375 | +| n_updates | 38460 | +| policy_gradient_loss | -0.022 | +| value_loss | 0.000261 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.0432 | +| time/ | | +| fps | 1304 | +| iterations | 780 | +| time_elapsed | 1224 | +| total_timesteps | 1597440 | +| train/ | | +| approx_kl | 0.029139146 | +| clip_fraction | 0.456 | +| clip_range | 0.0746 | +| entropy_loss | -4.55 | +| explained_variance | 0.314 | +| learning_rate | 4.96e-05 | +| loss | -0.0319 | +| n_updates | 38464 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.00033 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.0421 | +| time/ | | +| fps | 1304 | +| iterations | 781 | +| time_elapsed | 1226 | +| total_timesteps | 1599488 | +| train/ | | +| approx_kl | 0.02619078 | +| clip_fraction | 0.46 | +| clip_range | 0.0746 | +| entropy_loss | -4.38 | +| explained_variance | 0.352 | +| learning_rate | 4.96e-05 | +| loss | -0.0314 | +| n_updates | 38468 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.00026 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.0449 | +| time/ | | +| fps | 1304 | +| iterations | 782 | +| time_elapsed | 1227 | +| total_timesteps | 1601536 | +| train/ | | +| approx_kl | 0.027899638 | +| clip_fraction | 0.455 | +| clip_range | 0.0746 | +| entropy_loss | -4.2 | +| explained_variance | 0.475 | +| learning_rate | 4.96e-05 | +| loss | -0.033 | +| n_updates | 38472 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000164 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.0449 | +| time/ | | +| fps | 1304 | +| iterations | 783 | +| time_elapsed | 1229 | +| total_timesteps | 1603584 | +| train/ | | +| approx_kl | 0.025709117 | +| clip_fraction | 0.447 | +| clip_range | 0.0746 | +| entropy_loss | -4.34 | +| explained_variance | -0.00352 | +| learning_rate | 4.96e-05 | +| loss | -0.0355 | +| n_updates | 38476 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000262 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.048 | +| time/ | | +| fps | 1304 | +| iterations | 784 | +| time_elapsed | 1231 | +| total_timesteps | 1605632 | +| train/ | | +| approx_kl | 0.030707642 | +| clip_fraction | 0.469 | +| clip_range | 0.0746 | +| entropy_loss | -4.47 | +| explained_variance | 0.156 | +| learning_rate | 4.96e-05 | +| loss | -0.0357 | +| n_updates | 38480 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000238 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.0597 | +| time/ | | +| fps | 1304 | +| iterations | 785 | +| time_elapsed | 1232 | +| total_timesteps | 1607680 | +| train/ | | +| approx_kl | 0.029420387 | +| clip_fraction | 0.475 | +| clip_range | 0.0746 | +| entropy_loss | -4.42 | +| explained_variance | 0.165 | +| learning_rate | 4.96e-05 | +| loss | -0.0382 | +| n_updates | 38484 | +| policy_gradient_loss | -0.0229 | +| value_loss | 0.000244 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.056 | +| time/ | | +| fps | 1304 | +| iterations | 786 | +| time_elapsed | 1234 | +| total_timesteps | 1609728 | +| train/ | | +| approx_kl | 0.019839134 | +| clip_fraction | 0.429 | +| clip_range | 0.0746 | +| entropy_loss | -4.6 | +| explained_variance | -0.0251 | +| learning_rate | 4.96e-05 | +| loss | -0.0186 | +| n_updates | 38488 | +| policy_gradient_loss | -0.0135 | +| value_loss | 0.000895 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.056 | +| time/ | | +| fps | 1304 | +| iterations | 787 | +| time_elapsed | 1235 | +| total_timesteps | 1611776 | +| train/ | | +| approx_kl | 0.025863644 | +| clip_fraction | 0.446 | +| clip_range | 0.0746 | +| entropy_loss | -4.36 | +| explained_variance | -0.0318 | +| learning_rate | 4.96e-05 | +| loss | -0.0367 | +| n_updates | 38492 | +| policy_gradient_loss | -0.0234 | +| value_loss | 0.000388 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.069 | +| time/ | | +| fps | 1304 | +| iterations | 788 | +| time_elapsed | 1237 | +| total_timesteps | 1613824 | +| train/ | | +| approx_kl | 0.030540016 | +| clip_fraction | 0.456 | +| clip_range | 0.0746 | +| entropy_loss | -4.52 | +| explained_variance | -0.0813 | +| learning_rate | 4.96e-05 | +| loss | -0.0359 | +| n_updates | 38496 | +| policy_gradient_loss | -0.0221 | +| value_loss | 0.000355 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.0637 | +| time/ | | +| fps | 1304 | +| iterations | 789 | +| time_elapsed | 1238 | +| total_timesteps | 1615872 | +| train/ | | +| approx_kl | 0.0239413 | +| clip_fraction | 0.425 | +| clip_range | 0.0746 | +| entropy_loss | -4.59 | +| explained_variance | 0.104 | +| learning_rate | 4.96e-05 | +| loss | -0.0247 | +| n_updates | 38500 | +| policy_gradient_loss | -0.0146 | +| value_loss | 0.000744 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.0553 | +| time/ | | +| fps | 1304 | +| iterations | 790 | +| time_elapsed | 1240 | +| total_timesteps | 1617920 | +| train/ | | +| approx_kl | 0.027855352 | +| clip_fraction | 0.467 | +| clip_range | 0.0746 | +| entropy_loss | -4.49 | +| explained_variance | -0.0742 | +| learning_rate | 4.96e-05 | +| loss | -0.0377 | +| n_updates | 38504 | +| policy_gradient_loss | -0.0254 | +| value_loss | 0.00036 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.0588 | +| time/ | | +| fps | 1304 | +| iterations | 791 | +| time_elapsed | 1241 | +| total_timesteps | 1619968 | +| train/ | | +| approx_kl | 0.027249176 | +| clip_fraction | 0.457 | +| clip_range | 0.0746 | +| entropy_loss | -4.17 | +| explained_variance | 0.275 | +| learning_rate | 4.96e-05 | +| loss | -0.0352 | +| n_updates | 38508 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000344 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.0588 | +| time/ | | +| fps | 1304 | +| iterations | 792 | +| time_elapsed | 1243 | +| total_timesteps | 1622016 | +| train/ | | +| approx_kl | 0.0349721 | +| clip_fraction | 0.47 | +| clip_range | 0.0746 | +| entropy_loss | -4.37 | +| explained_variance | 0.0986 | +| learning_rate | 4.96e-05 | +| loss | -0.0346 | +| n_updates | 38512 | +| policy_gradient_loss | -0.022 | +| value_loss | 0.000346 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.059 | +| time/ | | +| fps | 1304 | +| iterations | 793 | +| time_elapsed | 1245 | +| total_timesteps | 1624064 | +| train/ | | +| approx_kl | 0.032452613 | +| clip_fraction | 0.47 | +| clip_range | 0.0746 | +| entropy_loss | -4.46 | +| explained_variance | 0.0836 | +| learning_rate | 4.96e-05 | +| loss | -0.0362 | +| n_updates | 38516 | +| policy_gradient_loss | -0.0224 | +| value_loss | 0.000247 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.0588 | +| time/ | | +| fps | 1304 | +| iterations | 794 | +| time_elapsed | 1246 | +| total_timesteps | 1626112 | +| train/ | | +| approx_kl | 0.025380248 | +| clip_fraction | 0.46 | +| clip_range | 0.0746 | +| entropy_loss | -4.69 | +| explained_variance | -0.0492 | +| learning_rate | 4.96e-05 | +| loss | -0.036 | +| n_updates | 38520 | +| policy_gradient_loss | -0.0219 | +| value_loss | 0.000337 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.0546 | +| time/ | | +| fps | 1304 | +| iterations | 795 | +| time_elapsed | 1248 | +| total_timesteps | 1628160 | +| train/ | | +| approx_kl | 0.022347618 | +| clip_fraction | 0.452 | +| clip_range | 0.0746 | +| entropy_loss | -4.39 | +| explained_variance | 0.124 | +| learning_rate | 4.96e-05 | +| loss | -0.0349 | +| n_updates | 38524 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000308 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.0609 | +| time/ | | +| fps | 1304 | +| iterations | 796 | +| time_elapsed | 1249 | +| total_timesteps | 1630208 | +| train/ | | +| approx_kl | 0.026337449 | +| clip_fraction | 0.461 | +| clip_range | 0.0746 | +| entropy_loss | -4.73 | +| explained_variance | -0.0249 | +| learning_rate | 4.96e-05 | +| loss | -0.0374 | +| n_updates | 38528 | +| policy_gradient_loss | -0.0222 | +| value_loss | 0.000345 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.0633 | +| time/ | | +| fps | 1304 | +| iterations | 797 | +| time_elapsed | 1251 | +| total_timesteps | 1632256 | +| train/ | | +| approx_kl | 0.027545564 | +| clip_fraction | 0.456 | +| clip_range | 0.0746 | +| entropy_loss | -4.47 | +| explained_variance | 0.0194 | +| learning_rate | 4.96e-05 | +| loss | -0.0189 | +| n_updates | 38532 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000811 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.0704 | +| time/ | | +| fps | 1304 | +| iterations | 798 | +| time_elapsed | 1252 | +| total_timesteps | 1634304 | +| train/ | | +| approx_kl | 0.028417174 | +| clip_fraction | 0.453 | +| clip_range | 0.0746 | +| entropy_loss | -4.42 | +| explained_variance | 0.204 | +| learning_rate | 4.96e-05 | +| loss | -0.0365 | +| n_updates | 38536 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000327 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.0717 | +| time/ | | +| fps | 1304 | +| iterations | 799 | +| time_elapsed | 1254 | +| total_timesteps | 1636352 | +| train/ | | +| approx_kl | 0.028656043 | +| clip_fraction | 0.448 | +| clip_range | 0.0746 | +| entropy_loss | -4.83 | +| explained_variance | 0.0885 | +| learning_rate | 4.96e-05 | +| loss | -0.0351 | +| n_updates | 38540 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000272 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.0726 | +| time/ | | +| fps | 1304 | +| iterations | 800 | +| time_elapsed | 1256 | +| total_timesteps | 1638400 | +| train/ | | +| approx_kl | 0.025076972 | +| clip_fraction | 0.432 | +| clip_range | 0.0746 | +| entropy_loss | -4.16 | +| explained_variance | 0.478 | +| learning_rate | 4.96e-05 | +| loss | -0.035 | +| n_updates | 38544 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000243 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.0739 | +| time/ | | +| fps | 1304 | +| iterations | 801 | +| time_elapsed | 1257 | +| total_timesteps | 1640448 | +| train/ | | +| approx_kl | 0.028888393 | +| clip_fraction | 0.483 | +| clip_range | 0.0746 | +| entropy_loss | -4.34 | +| explained_variance | 0.173 | +| learning_rate | 4.96e-05 | +| loss | -0.0321 | +| n_updates | 38548 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000241 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.0796 | +| time/ | | +| fps | 1304 | +| iterations | 802 | +| time_elapsed | 1259 | +| total_timesteps | 1642496 | +| train/ | | +| approx_kl | 0.028474607 | +| clip_fraction | 0.477 | +| clip_range | 0.0746 | +| entropy_loss | -4.34 | +| explained_variance | 0.2 | +| learning_rate | 4.96e-05 | +| loss | -0.036 | +| n_updates | 38552 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000221 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.0796 | +| time/ | | +| fps | 1304 | +| iterations | 803 | +| time_elapsed | 1260 | +| total_timesteps | 1644544 | +| train/ | | +| approx_kl | 0.024403263 | +| clip_fraction | 0.415 | +| clip_range | 0.0746 | +| entropy_loss | -4.33 | +| explained_variance | 0.546 | +| learning_rate | 4.96e-05 | +| loss | -0.0324 | +| n_updates | 38556 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.00024 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.0796 | +| time/ | | +| fps | 1304 | +| iterations | 804 | +| time_elapsed | 1262 | +| total_timesteps | 1646592 | +| train/ | | +| approx_kl | 0.02534856 | +| clip_fraction | 0.465 | +| clip_range | 0.0746 | +| entropy_loss | -4.49 | +| explained_variance | -0.0601 | +| learning_rate | 4.96e-05 | +| loss | -0.0363 | +| n_updates | 38560 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000337 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.0786 | +| time/ | | +| fps | 1304 | +| iterations | 805 | +| time_elapsed | 1264 | +| total_timesteps | 1648640 | +| train/ | | +| approx_kl | 0.027468398 | +| clip_fraction | 0.474 | +| clip_range | 0.0746 | +| entropy_loss | -4.53 | +| explained_variance | -0.224 | +| learning_rate | 4.96e-05 | +| loss | -0.0419 | +| n_updates | 38564 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000222 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.0786 | +| time/ | | +| fps | 1304 | +| iterations | 806 | +| time_elapsed | 1265 | +| total_timesteps | 1650688 | +| train/ | | +| approx_kl | 0.02836474 | +| clip_fraction | 0.435 | +| clip_range | 0.0746 | +| entropy_loss | -4.56 | +| explained_variance | 0.107 | +| learning_rate | 4.96e-05 | +| loss | -0.0366 | +| n_updates | 38568 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000302 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.08 | +| time/ | | +| fps | 1304 | +| iterations | 807 | +| time_elapsed | 1267 | +| total_timesteps | 1652736 | +| train/ | | +| approx_kl | 0.028458336 | +| clip_fraction | 0.463 | +| clip_range | 0.0746 | +| entropy_loss | -4.75 | +| explained_variance | -0.232 | +| learning_rate | 4.96e-05 | +| loss | -0.0352 | +| n_updates | 38572 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000185 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.0859 | +| time/ | | +| fps | 1304 | +| iterations | 808 | +| time_elapsed | 1268 | +| total_timesteps | 1654784 | +| train/ | | +| approx_kl | 0.025131179 | +| clip_fraction | 0.46 | +| clip_range | 0.0746 | +| entropy_loss | -4.53 | +| explained_variance | 0.17 | +| learning_rate | 4.96e-05 | +| loss | -0.0328 | +| n_updates | 38576 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000266 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.0828 | +| time/ | | +| fps | 1304 | +| iterations | 809 | +| time_elapsed | 1270 | +| total_timesteps | 1656832 | +| train/ | | +| approx_kl | 0.025085982 | +| clip_fraction | 0.421 | +| clip_range | 0.0746 | +| entropy_loss | -4.63 | +| explained_variance | -0.141 | +| learning_rate | 4.96e-05 | +| loss | -0.0265 | +| n_updates | 38580 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000304 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.0782 | +| time/ | | +| fps | 1304 | +| iterations | 810 | +| time_elapsed | 1272 | +| total_timesteps | 1658880 | +| train/ | | +| approx_kl | 0.028250955 | +| clip_fraction | 0.46 | +| clip_range | 0.0746 | +| entropy_loss | -4.51 | +| explained_variance | 0.208 | +| learning_rate | 4.96e-05 | +| loss | -0.0352 | +| n_updates | 38584 | +| policy_gradient_loss | -0.0229 | +| value_loss | 0.000259 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.0791 | +| time/ | | +| fps | 1304 | +| iterations | 811 | +| time_elapsed | 1273 | +| total_timesteps | 1660928 | +| train/ | | +| approx_kl | 0.026024561 | +| clip_fraction | 0.445 | +| clip_range | 0.0746 | +| entropy_loss | -4.34 | +| explained_variance | 0.267 | +| learning_rate | 4.96e-05 | +| loss | -0.0357 | +| n_updates | 38588 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000218 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.0853 | +| time/ | | +| fps | 1304 | +| iterations | 812 | +| time_elapsed | 1275 | +| total_timesteps | 1662976 | +| train/ | | +| approx_kl | 0.029771935 | +| clip_fraction | 0.471 | +| clip_range | 0.0746 | +| entropy_loss | -4.48 | +| explained_variance | 0.174 | +| learning_rate | 4.96e-05 | +| loss | -0.0412 | +| n_updates | 38592 | +| policy_gradient_loss | -0.0223 | +| value_loss | 0.000224 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.0857 | +| time/ | | +| fps | 1304 | +| iterations | 813 | +| time_elapsed | 1276 | +| total_timesteps | 1665024 | +| train/ | | +| approx_kl | 0.018678052 | +| clip_fraction | 0.397 | +| clip_range | 0.0746 | +| entropy_loss | -4.15 | +| explained_variance | 0.0954 | +| learning_rate | 4.96e-05 | +| loss | -0.0282 | +| n_updates | 38596 | +| policy_gradient_loss | -0.0106 | +| value_loss | 0.000863 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.0842 | +| time/ | | +| fps | 1304 | +| iterations | 814 | +| time_elapsed | 1278 | +| total_timesteps | 1667072 | +| train/ | | +| approx_kl | 0.027610917 | +| clip_fraction | 0.458 | +| clip_range | 0.0746 | +| entropy_loss | -4.06 | +| explained_variance | 0.0278 | +| learning_rate | 4.96e-05 | +| loss | -0.0385 | +| n_updates | 38600 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000327 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.0855 | +| time/ | | +| fps | 1304 | +| iterations | 815 | +| time_elapsed | 1279 | +| total_timesteps | 1669120 | +| train/ | | +| approx_kl | 0.023585532 | +| clip_fraction | 0.459 | +| clip_range | 0.0746 | +| entropy_loss | -4.52 | +| explained_variance | -0.043 | +| learning_rate | 4.96e-05 | +| loss | -0.0293 | +| n_updates | 38604 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000387 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.0855 | +| time/ | | +| fps | 1303 | +| iterations | 816 | +| time_elapsed | 1281 | +| total_timesteps | 1671168 | +| train/ | | +| approx_kl | 0.02726847 | +| clip_fraction | 0.467 | +| clip_range | 0.0746 | +| entropy_loss | -4.34 | +| explained_variance | 0.0802 | +| learning_rate | 4.96e-05 | +| loss | -0.0337 | +| n_updates | 38608 | +| policy_gradient_loss | -0.0221 | +| value_loss | 0.000219 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.0826 | +| time/ | | +| fps | 1303 | +| iterations | 817 | +| time_elapsed | 1283 | +| total_timesteps | 1673216 | +| train/ | | +| approx_kl | 0.028597262 | +| clip_fraction | 0.47 | +| clip_range | 0.0746 | +| entropy_loss | -4.76 | +| explained_variance | -0.127 | +| learning_rate | 4.96e-05 | +| loss | -0.0373 | +| n_updates | 38612 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000203 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.0877 | +| time/ | | +| fps | 1303 | +| iterations | 818 | +| time_elapsed | 1284 | +| total_timesteps | 1675264 | +| train/ | | +| approx_kl | 0.028592803 | +| clip_fraction | 0.451 | +| clip_range | 0.0746 | +| entropy_loss | -4.61 | +| explained_variance | 0.0179 | +| learning_rate | 4.96e-05 | +| loss | -0.0346 | +| n_updates | 38616 | +| policy_gradient_loss | -0.0221 | +| value_loss | 0.000437 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.0918 | +| time/ | | +| fps | 1303 | +| iterations | 819 | +| time_elapsed | 1286 | +| total_timesteps | 1677312 | +| train/ | | +| approx_kl | 0.026424177 | +| clip_fraction | 0.459 | +| clip_range | 0.0746 | +| entropy_loss | -4.52 | +| explained_variance | -0.233 | +| learning_rate | 4.96e-05 | +| loss | -0.0375 | +| n_updates | 38620 | +| policy_gradient_loss | -0.0227 | +| value_loss | 0.000251 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.0918 | +| time/ | | +| fps | 1303 | +| iterations | 820 | +| time_elapsed | 1287 | +| total_timesteps | 1679360 | +| train/ | | +| approx_kl | 0.023127787 | +| clip_fraction | 0.449 | +| clip_range | 0.0746 | +| entropy_loss | -4.34 | +| explained_variance | 0.205 | +| learning_rate | 4.96e-05 | +| loss | -0.0326 | +| n_updates | 38624 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000348 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.0943 | +| time/ | | +| fps | 1303 | +| iterations | 821 | +| time_elapsed | 1289 | +| total_timesteps | 1681408 | +| train/ | | +| approx_kl | 0.024798743 | +| clip_fraction | 0.464 | +| clip_range | 0.0746 | +| entropy_loss | -4.6 | +| explained_variance | -0.0643 | +| learning_rate | 4.96e-05 | +| loss | -0.0324 | +| n_updates | 38628 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000298 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.0927 | +| time/ | | +| fps | 1303 | +| iterations | 822 | +| time_elapsed | 1291 | +| total_timesteps | 1683456 | +| train/ | | +| approx_kl | 0.026394544 | +| clip_fraction | 0.439 | +| clip_range | 0.0746 | +| entropy_loss | -4.48 | +| explained_variance | 0.0621 | +| learning_rate | 4.96e-05 | +| loss | -0.033 | +| n_updates | 38632 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.00039 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.0858 | +| time/ | | +| fps | 1303 | +| iterations | 823 | +| time_elapsed | 1292 | +| total_timesteps | 1685504 | +| train/ | | +| approx_kl | 0.023801953 | +| clip_fraction | 0.458 | +| clip_range | 0.0746 | +| entropy_loss | -4.48 | +| explained_variance | 0.367 | +| learning_rate | 4.96e-05 | +| loss | -0.0366 | +| n_updates | 38636 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000178 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.0849 | +| time/ | | +| fps | 1303 | +| iterations | 824 | +| time_elapsed | 1294 | +| total_timesteps | 1687552 | +| train/ | | +| approx_kl | 0.02500557 | +| clip_fraction | 0.435 | +| clip_range | 0.0746 | +| entropy_loss | -4.49 | +| explained_variance | -0.0336 | +| learning_rate | 4.96e-05 | +| loss | -0.0305 | +| n_updates | 38640 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000295 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.0863 | +| time/ | | +| fps | 1304 | +| iterations | 825 | +| time_elapsed | 1295 | +| total_timesteps | 1689600 | +| train/ | | +| approx_kl | 0.029987305 | +| clip_fraction | 0.423 | +| clip_range | 0.0746 | +| entropy_loss | -4.4 | +| explained_variance | 0.326 | +| learning_rate | 4.96e-05 | +| loss | -0.0332 | +| n_updates | 38644 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000244 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.0904 | +| time/ | | +| fps | 1304 | +| iterations | 826 | +| time_elapsed | 1297 | +| total_timesteps | 1691648 | +| train/ | | +| approx_kl | 0.032736853 | +| clip_fraction | 0.438 | +| clip_range | 0.0746 | +| entropy_loss | -4.26 | +| explained_variance | 0.28 | +| learning_rate | 4.96e-05 | +| loss | -0.0384 | +| n_updates | 38648 | +| policy_gradient_loss | -0.0222 | +| value_loss | 0.000164 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.0935 | +| time/ | | +| fps | 1304 | +| iterations | 827 | +| time_elapsed | 1298 | +| total_timesteps | 1693696 | +| train/ | | +| approx_kl | 0.026354078 | +| clip_fraction | 0.459 | +| clip_range | 0.0746 | +| entropy_loss | -4.34 | +| explained_variance | 0.177 | +| learning_rate | 4.96e-05 | +| loss | -0.0343 | +| n_updates | 38652 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000266 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.0978 | +| time/ | | +| fps | 1303 | +| iterations | 828 | +| time_elapsed | 1300 | +| total_timesteps | 1695744 | +| train/ | | +| approx_kl | 0.0283359 | +| clip_fraction | 0.463 | +| clip_range | 0.0746 | +| entropy_loss | -4.62 | +| explained_variance | -0.066 | +| learning_rate | 4.96e-05 | +| loss | -0.0342 | +| n_updates | 38656 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000262 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.0975 | +| time/ | | +| fps | 1303 | +| iterations | 829 | +| time_elapsed | 1302 | +| total_timesteps | 1697792 | +| train/ | | +| approx_kl | 0.023843713 | +| clip_fraction | 0.452 | +| clip_range | 0.0746 | +| entropy_loss | -4.33 | +| explained_variance | 0.296 | +| learning_rate | 4.96e-05 | +| loss | -0.0359 | +| n_updates | 38660 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000233 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.0975 | +| time/ | | +| fps | 1303 | +| iterations | 830 | +| time_elapsed | 1303 | +| total_timesteps | 1699840 | +| train/ | | +| approx_kl | 0.029342499 | +| clip_fraction | 0.454 | +| clip_range | 0.0746 | +| entropy_loss | -4.27 | +| explained_variance | 0.451 | +| learning_rate | 4.96e-05 | +| loss | -0.0288 | +| n_updates | 38664 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000236 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.0975 | +| time/ | | +| fps | 1303 | +| iterations | 831 | +| time_elapsed | 1305 | +| total_timesteps | 1701888 | +| train/ | | +| approx_kl | 0.023866795 | +| clip_fraction | 0.447 | +| clip_range | 0.0746 | +| entropy_loss | -4.37 | +| explained_variance | -0.148 | +| learning_rate | 4.96e-05 | +| loss | -0.0304 | +| n_updates | 38668 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000346 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.0933 | +| time/ | | +| fps | 1304 | +| iterations | 832 | +| time_elapsed | 1306 | +| total_timesteps | 1703936 | +| train/ | | +| approx_kl | 0.026253864 | +| clip_fraction | 0.46 | +| clip_range | 0.0746 | +| entropy_loss | -4.46 | +| explained_variance | -0.277 | +| learning_rate | 4.96e-05 | +| loss | -0.0333 | +| n_updates | 38672 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000318 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.0937 | +| time/ | | +| fps | 1304 | +| iterations | 833 | +| time_elapsed | 1308 | +| total_timesteps | 1705984 | +| train/ | | +| approx_kl | 0.024657514 | +| clip_fraction | 0.43 | +| clip_range | 0.0746 | +| entropy_loss | -4.45 | +| explained_variance | 0.274 | +| learning_rate | 4.96e-05 | +| loss | -0.0355 | +| n_updates | 38676 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000387 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.0937 | +| time/ | | +| fps | 1304 | +| iterations | 834 | +| time_elapsed | 1309 | +| total_timesteps | 1708032 | +| train/ | | +| approx_kl | 0.031076327 | +| clip_fraction | 0.471 | +| clip_range | 0.0746 | +| entropy_loss | -4.38 | +| explained_variance | -0.168 | +| learning_rate | 4.96e-05 | +| loss | -0.0345 | +| n_updates | 38680 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000229 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | 0.0956 | +| time/ | | +| fps | 1304 | +| iterations | 835 | +| time_elapsed | 1311 | +| total_timesteps | 1710080 | +| train/ | | +| approx_kl | 0.029825274 | +| clip_fraction | 0.493 | +| clip_range | 0.0746 | +| entropy_loss | -4.36 | +| explained_variance | -0.207 | +| learning_rate | 4.96e-05 | +| loss | -0.031 | +| n_updates | 38684 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000202 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0992 | +| time/ | | +| fps | 1303 | +| iterations | 836 | +| time_elapsed | 1313 | +| total_timesteps | 1712128 | +| train/ | | +| approx_kl | 0.023625195 | +| clip_fraction | 0.41 | +| clip_range | 0.0746 | +| entropy_loss | -4.11 | +| explained_variance | 0.34 | +| learning_rate | 4.96e-05 | +| loss | -0.0308 | +| n_updates | 38688 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000325 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0993 | +| time/ | | +| fps | 1303 | +| iterations | 837 | +| time_elapsed | 1314 | +| total_timesteps | 1714176 | +| train/ | | +| approx_kl | 0.024753746 | +| clip_fraction | 0.395 | +| clip_range | 0.0746 | +| entropy_loss | -4.13 | +| explained_variance | -0.0107 | +| learning_rate | 4.96e-05 | +| loss | -0.0284 | +| n_updates | 38692 | +| policy_gradient_loss | -0.0119 | +| value_loss | 0.000789 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0961 | +| time/ | | +| fps | 1303 | +| iterations | 838 | +| time_elapsed | 1316 | +| total_timesteps | 1716224 | +| train/ | | +| approx_kl | 0.03067732 | +| clip_fraction | 0.438 | +| clip_range | 0.0746 | +| entropy_loss | -4.34 | +| explained_variance | 0.0432 | +| learning_rate | 4.96e-05 | +| loss | -0.0377 | +| n_updates | 38696 | +| policy_gradient_loss | -0.0229 | +| value_loss | 0.000462 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0961 | +| time/ | | +| fps | 1303 | +| iterations | 839 | +| time_elapsed | 1317 | +| total_timesteps | 1718272 | +| train/ | | +| approx_kl | 0.033382006 | +| clip_fraction | 0.445 | +| clip_range | 0.0746 | +| entropy_loss | -3.77 | +| explained_variance | 0.27 | +| learning_rate | 4.96e-05 | +| loss | -0.0376 | +| n_updates | 38700 | +| policy_gradient_loss | -0.0231 | +| value_loss | 0.000337 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0966 | +| time/ | | +| fps | 1303 | +| iterations | 840 | +| time_elapsed | 1319 | +| total_timesteps | 1720320 | +| train/ | | +| approx_kl | 0.03143998 | +| clip_fraction | 0.456 | +| clip_range | 0.0746 | +| entropy_loss | -4.29 | +| explained_variance | -0.0358 | +| learning_rate | 4.96e-05 | +| loss | -0.0394 | +| n_updates | 38704 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000272 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0933 | +| time/ | | +| fps | 1303 | +| iterations | 841 | +| time_elapsed | 1321 | +| total_timesteps | 1722368 | +| train/ | | +| approx_kl | 0.025342429 | +| clip_fraction | 0.449 | +| clip_range | 0.0746 | +| entropy_loss | -4.3 | +| explained_variance | -0.334 | +| learning_rate | 4.96e-05 | +| loss | -0.0394 | +| n_updates | 38708 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000296 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0933 | +| time/ | | +| fps | 1303 | +| iterations | 842 | +| time_elapsed | 1322 | +| total_timesteps | 1724416 | +| train/ | | +| approx_kl | 0.0290699 | +| clip_fraction | 0.451 | +| clip_range | 0.0746 | +| entropy_loss | -4.19 | +| explained_variance | 0.273 | +| learning_rate | 4.96e-05 | +| loss | -0.032 | +| n_updates | 38712 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000324 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0905 | +| time/ | | +| fps | 1303 | +| iterations | 843 | +| time_elapsed | 1324 | +| total_timesteps | 1726464 | +| train/ | | +| approx_kl | 0.022471406 | +| clip_fraction | 0.461 | +| clip_range | 0.0746 | +| entropy_loss | -4.61 | +| explained_variance | -0.0826 | +| learning_rate | 4.96e-05 | +| loss | -0.0319 | +| n_updates | 38716 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000263 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0791 | +| time/ | | +| fps | 1303 | +| iterations | 844 | +| time_elapsed | 1325 | +| total_timesteps | 1728512 | +| train/ | | +| approx_kl | 0.024199145 | +| clip_fraction | 0.44 | +| clip_range | 0.0746 | +| entropy_loss | -4.61 | +| explained_variance | 0.0557 | +| learning_rate | 4.96e-05 | +| loss | -0.0338 | +| n_updates | 38720 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000315 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0726 | +| time/ | | +| fps | 1303 | +| iterations | 845 | +| time_elapsed | 1327 | +| total_timesteps | 1730560 | +| train/ | | +| approx_kl | 0.0240581 | +| clip_fraction | 0.422 | +| clip_range | 0.0746 | +| entropy_loss | -4.28 | +| explained_variance | 0.251 | +| learning_rate | 4.96e-05 | +| loss | -0.0296 | +| n_updates | 38724 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000273 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0726 | +| time/ | | +| fps | 1303 | +| iterations | 846 | +| time_elapsed | 1329 | +| total_timesteps | 1732608 | +| train/ | | +| approx_kl | 0.029390167 | +| clip_fraction | 0.439 | +| clip_range | 0.0746 | +| entropy_loss | -3.79 | +| explained_variance | 0.312 | +| learning_rate | 4.96e-05 | +| loss | -0.0291 | +| n_updates | 38728 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000276 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.077 | +| time/ | | +| fps | 1303 | +| iterations | 847 | +| time_elapsed | 1330 | +| total_timesteps | 1734656 | +| train/ | | +| approx_kl | 0.032080106 | +| clip_fraction | 0.483 | +| clip_range | 0.0746 | +| entropy_loss | -4.26 | +| explained_variance | -0.0238 | +| learning_rate | 4.96e-05 | +| loss | -0.0343 | +| n_updates | 38732 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000208 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0754 | +| time/ | | +| fps | 1303 | +| iterations | 848 | +| time_elapsed | 1332 | +| total_timesteps | 1736704 | +| train/ | | +| approx_kl | 0.024137296 | +| clip_fraction | 0.452 | +| clip_range | 0.0746 | +| entropy_loss | -4.11 | +| explained_variance | 0.358 | +| learning_rate | 4.96e-05 | +| loss | -0.0326 | +| n_updates | 38736 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000227 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0788 | +| time/ | | +| fps | 1303 | +| iterations | 849 | +| time_elapsed | 1333 | +| total_timesteps | 1738752 | +| train/ | | +| approx_kl | 0.032487035 | +| clip_fraction | 0.458 | +| clip_range | 0.0746 | +| entropy_loss | -4.16 | +| explained_variance | 0.296 | +| learning_rate | 4.96e-05 | +| loss | -0.035 | +| n_updates | 38740 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000206 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0684 | +| time/ | | +| fps | 1303 | +| iterations | 850 | +| time_elapsed | 1335 | +| total_timesteps | 1740800 | +| train/ | | +| approx_kl | 0.03044853 | +| clip_fraction | 0.469 | +| clip_range | 0.0746 | +| entropy_loss | -4.28 | +| explained_variance | -0.0308 | +| learning_rate | 4.96e-05 | +| loss | -0.0341 | +| n_updates | 38744 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000295 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0899 | +| time/ | | +| fps | 1303 | +| iterations | 851 | +| time_elapsed | 1337 | +| total_timesteps | 1742848 | +| train/ | | +| approx_kl | 0.026405143 | +| clip_fraction | 0.438 | +| clip_range | 0.0746 | +| entropy_loss | -4.26 | +| explained_variance | 0.375 | +| learning_rate | 4.96e-05 | +| loss | -0.0328 | +| n_updates | 38748 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000211 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0899 | +| time/ | | +| fps | 1303 | +| iterations | 852 | +| time_elapsed | 1338 | +| total_timesteps | 1744896 | +| train/ | | +| approx_kl | 0.023847029 | +| clip_fraction | 0.417 | +| clip_range | 0.0746 | +| entropy_loss | -4.52 | +| explained_variance | 0.00184 | +| learning_rate | 4.96e-05 | +| loss | -0.0235 | +| n_updates | 38752 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000843 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.0995 | +| time/ | | +| fps | 1303 | +| iterations | 853 | +| time_elapsed | 1340 | +| total_timesteps | 1746944 | +| train/ | | +| approx_kl | 0.026901148 | +| clip_fraction | 0.453 | +| clip_range | 0.0746 | +| entropy_loss | -4.16 | +| explained_variance | -0.119 | +| learning_rate | 4.96e-05 | +| loss | -0.0375 | +| n_updates | 38756 | +| policy_gradient_loss | -0.0252 | +| value_loss | 0.000441 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0917 | +| time/ | | +| fps | 1303 | +| iterations | 854 | +| time_elapsed | 1341 | +| total_timesteps | 1748992 | +| train/ | | +| approx_kl | 0.022214096 | +| clip_fraction | 0.47 | +| clip_range | 0.0746 | +| entropy_loss | -4.71 | +| explained_variance | 0.125 | +| learning_rate | 4.96e-05 | +| loss | -0.0379 | +| n_updates | 38760 | +| policy_gradient_loss | -0.023 | +| value_loss | 0.000266 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0903 | +| time/ | | +| fps | 1303 | +| iterations | 855 | +| time_elapsed | 1343 | +| total_timesteps | 1751040 | +| train/ | | +| approx_kl | 0.02329053 | +| clip_fraction | 0.444 | +| clip_range | 0.0746 | +| entropy_loss | -4.02 | +| explained_variance | 0.318 | +| learning_rate | 4.96e-05 | +| loss | -0.034 | +| n_updates | 38764 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000306 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0923 | +| time/ | | +| fps | 1303 | +| iterations | 856 | +| time_elapsed | 1345 | +| total_timesteps | 1753088 | +| train/ | | +| approx_kl | 0.026719064 | +| clip_fraction | 0.452 | +| clip_range | 0.0746 | +| entropy_loss | -4.46 | +| explained_variance | 0.121 | +| learning_rate | 4.96e-05 | +| loss | -0.0376 | +| n_updates | 38768 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000349 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0899 | +| time/ | | +| fps | 1303 | +| iterations | 857 | +| time_elapsed | 1346 | +| total_timesteps | 1755136 | +| train/ | | +| approx_kl | 0.028184365 | +| clip_fraction | 0.457 | +| clip_range | 0.0746 | +| entropy_loss | -4.43 | +| explained_variance | 0.143 | +| learning_rate | 4.96e-05 | +| loss | -0.0339 | +| n_updates | 38772 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.0003 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0929 | +| time/ | | +| fps | 1303 | +| iterations | 858 | +| time_elapsed | 1348 | +| total_timesteps | 1757184 | +| train/ | | +| approx_kl | 0.022413742 | +| clip_fraction | 0.431 | +| clip_range | 0.0746 | +| entropy_loss | -4.21 | +| explained_variance | 0.387 | +| learning_rate | 4.96e-05 | +| loss | -0.0329 | +| n_updates | 38776 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.00039 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0903 | +| time/ | | +| fps | 1303 | +| iterations | 859 | +| time_elapsed | 1349 | +| total_timesteps | 1759232 | +| train/ | | +| approx_kl | 0.026752872 | +| clip_fraction | 0.466 | +| clip_range | 0.0746 | +| entropy_loss | -4.11 | +| explained_variance | 0.447 | +| learning_rate | 4.96e-05 | +| loss | -0.0388 | +| n_updates | 38780 | +| policy_gradient_loss | -0.0238 | +| value_loss | 0.00016 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0924 | +| time/ | | +| fps | 1303 | +| iterations | 860 | +| time_elapsed | 1351 | +| total_timesteps | 1761280 | +| train/ | | +| approx_kl | 0.030456908 | +| clip_fraction | 0.465 | +| clip_range | 0.0746 | +| entropy_loss | -4.14 | +| explained_variance | 0.182 | +| learning_rate | 4.96e-05 | +| loss | -0.0349 | +| n_updates | 38784 | +| policy_gradient_loss | -0.0231 | +| value_loss | 0.000214 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0796 | +| time/ | | +| fps | 1303 | +| iterations | 861 | +| time_elapsed | 1353 | +| total_timesteps | 1763328 | +| train/ | | +| approx_kl | 0.031386442 | +| clip_fraction | 0.45 | +| clip_range | 0.0746 | +| entropy_loss | -4.14 | +| explained_variance | -0.279 | +| learning_rate | 4.96e-05 | +| loss | -0.0416 | +| n_updates | 38788 | +| policy_gradient_loss | -0.0223 | +| value_loss | 0.00016 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0796 | +| time/ | | +| fps | 1303 | +| iterations | 862 | +| time_elapsed | 1354 | +| total_timesteps | 1765376 | +| train/ | | +| approx_kl | 0.028449602 | +| clip_fraction | 0.454 | +| clip_range | 0.0746 | +| entropy_loss | -4.2 | +| explained_variance | 0.163 | +| learning_rate | 4.96e-05 | +| loss | -0.0311 | +| n_updates | 38792 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000322 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0796 | +| time/ | | +| fps | 1303 | +| iterations | 863 | +| time_elapsed | 1356 | +| total_timesteps | 1767424 | +| train/ | | +| approx_kl | 0.02482986 | +| clip_fraction | 0.458 | +| clip_range | 0.0746 | +| entropy_loss | -4.35 | +| explained_variance | -0.168 | +| learning_rate | 4.96e-05 | +| loss | -0.037 | +| n_updates | 38796 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000314 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0878 | +| time/ | | +| fps | 1303 | +| iterations | 864 | +| time_elapsed | 1357 | +| total_timesteps | 1769472 | +| train/ | | +| approx_kl | 0.02702097 | +| clip_fraction | 0.455 | +| clip_range | 0.0746 | +| entropy_loss | -4.46 | +| explained_variance | -0.145 | +| learning_rate | 4.96e-05 | +| loss | -0.0362 | +| n_updates | 38800 | +| policy_gradient_loss | -0.0222 | +| value_loss | 0.000316 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0868 | +| time/ | | +| fps | 1303 | +| iterations | 865 | +| time_elapsed | 1359 | +| total_timesteps | 1771520 | +| train/ | | +| approx_kl | 0.02241508 | +| clip_fraction | 0.419 | +| clip_range | 0.0746 | +| entropy_loss | -4.29 | +| explained_variance | 0.0956 | +| learning_rate | 4.96e-05 | +| loss | -0.0346 | +| n_updates | 38804 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000524 | +---------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0881 | +| time/ | | +| fps | 1303 | +| iterations | 866 | +| time_elapsed | 1361 | +| total_timesteps | 1773568 | +| train/ | | +| approx_kl | 0.0298609 | +| clip_fraction | 0.435 | +| clip_range | 0.0746 | +| entropy_loss | -4.41 | +| explained_variance | -0.246 | +| learning_rate | 4.96e-05 | +| loss | -0.0357 | +| n_updates | 38808 | +| policy_gradient_loss | -0.0221 | +| value_loss | 0.000306 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0902 | +| time/ | | +| fps | 1303 | +| iterations | 867 | +| time_elapsed | 1362 | +| total_timesteps | 1775616 | +| train/ | | +| approx_kl | 0.027617589 | +| clip_fraction | 0.463 | +| clip_range | 0.0746 | +| entropy_loss | -4.22 | +| explained_variance | 0.299 | +| learning_rate | 4.96e-05 | +| loss | -0.0327 | +| n_updates | 38812 | +| policy_gradient_loss | -0.0225 | +| value_loss | 0.000168 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0806 | +| time/ | | +| fps | 1303 | +| iterations | 868 | +| time_elapsed | 1364 | +| total_timesteps | 1777664 | +| train/ | | +| approx_kl | 0.028154144 | +| clip_fraction | 0.437 | +| clip_range | 0.0746 | +| entropy_loss | -4.15 | +| explained_variance | 0.14 | +| learning_rate | 4.96e-05 | +| loss | -0.0315 | +| n_updates | 38816 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000298 | +----------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0761 | +| time/ | | +| fps | 1303 | +| iterations | 869 | +| time_elapsed | 1365 | +| total_timesteps | 1779712 | +| train/ | | +| approx_kl | 0.033642 | +| clip_fraction | 0.458 | +| clip_range | 0.0746 | +| entropy_loss | -4.07 | +| explained_variance | 0.387 | +| learning_rate | 4.96e-05 | +| loss | -0.0338 | +| n_updates | 38820 | +| policy_gradient_loss | -0.022 | +| value_loss | 0.000123 | +-------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0741 | +| time/ | | +| fps | 1303 | +| iterations | 870 | +| time_elapsed | 1367 | +| total_timesteps | 1781760 | +| train/ | | +| approx_kl | 0.025930129 | +| clip_fraction | 0.411 | +| clip_range | 0.0746 | +| entropy_loss | -4.03 | +| explained_variance | 0.365 | +| learning_rate | 4.96e-05 | +| loss | -0.0322 | +| n_updates | 38824 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.00024 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.0729 | +| time/ | | +| fps | 1303 | +| iterations | 871 | +| time_elapsed | 1368 | +| total_timesteps | 1783808 | +| train/ | | +| approx_kl | 0.028225455 | +| clip_fraction | 0.475 | +| clip_range | 0.0746 | +| entropy_loss | -4.08 | +| explained_variance | 0.11 | +| learning_rate | 4.96e-05 | +| loss | -0.0292 | +| n_updates | 38828 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000246 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0733 | +| time/ | | +| fps | 1303 | +| iterations | 872 | +| time_elapsed | 1370 | +| total_timesteps | 1785856 | +| train/ | | +| approx_kl | 0.026609464 | +| clip_fraction | 0.456 | +| clip_range | 0.0746 | +| entropy_loss | -3.96 | +| explained_variance | 0.272 | +| learning_rate | 4.96e-05 | +| loss | -0.033 | +| n_updates | 38832 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000211 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.073 | +| time/ | | +| fps | 1303 | +| iterations | 873 | +| time_elapsed | 1371 | +| total_timesteps | 1787904 | +| train/ | | +| approx_kl | 0.028935496 | +| clip_fraction | 0.444 | +| clip_range | 0.0746 | +| entropy_loss | -3.77 | +| explained_variance | 0.398 | +| learning_rate | 4.96e-05 | +| loss | -0.032 | +| n_updates | 38836 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000309 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.074 | +| time/ | | +| fps | 1303 | +| iterations | 874 | +| time_elapsed | 1373 | +| total_timesteps | 1789952 | +| train/ | | +| approx_kl | 0.02728792 | +| clip_fraction | 0.464 | +| clip_range | 0.0746 | +| entropy_loss | -4.1 | +| explained_variance | 0.204 | +| learning_rate | 4.96e-05 | +| loss | -0.0339 | +| n_updates | 38840 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.00032 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.068 | +| time/ | | +| fps | 1303 | +| iterations | 875 | +| time_elapsed | 1375 | +| total_timesteps | 1792000 | +| train/ | | +| approx_kl | 0.026537003 | +| clip_fraction | 0.441 | +| clip_range | 0.0746 | +| entropy_loss | -4.31 | +| explained_variance | 0.167 | +| learning_rate | 4.96e-05 | +| loss | -0.0339 | +| n_updates | 38844 | +| policy_gradient_loss | -0.0218 | +| value_loss | 0.000317 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.068 | +| time/ | | +| fps | 1303 | +| iterations | 876 | +| time_elapsed | 1376 | +| total_timesteps | 1794048 | +| train/ | | +| approx_kl | 0.030461349 | +| clip_fraction | 0.45 | +| clip_range | 0.0746 | +| entropy_loss | -3.93 | +| explained_variance | 0.28 | +| learning_rate | 4.96e-05 | +| loss | -0.0339 | +| n_updates | 38848 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000176 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.068 | +| time/ | | +| fps | 1303 | +| iterations | 877 | +| time_elapsed | 1378 | +| total_timesteps | 1796096 | +| train/ | | +| approx_kl | 0.029945832 | +| clip_fraction | 0.473 | +| clip_range | 0.0746 | +| entropy_loss | -4.24 | +| explained_variance | -0.254 | +| learning_rate | 4.96e-05 | +| loss | -0.0332 | +| n_updates | 38852 | +| policy_gradient_loss | -0.02 | +| value_loss | 0.000255 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.067 | +| time/ | | +| fps | 1303 | +| iterations | 878 | +| time_elapsed | 1379 | +| total_timesteps | 1798144 | +| train/ | | +| approx_kl | 0.022998562 | +| clip_fraction | 0.454 | +| clip_range | 0.0746 | +| entropy_loss | -4.3 | +| explained_variance | 0.0139 | +| learning_rate | 4.96e-05 | +| loss | -0.0279 | +| n_updates | 38856 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000285 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0628 | +| time/ | | +| fps | 1303 | +| iterations | 879 | +| time_elapsed | 1381 | +| total_timesteps | 1800192 | +| train/ | | +| approx_kl | 0.02506509 | +| clip_fraction | 0.463 | +| clip_range | 0.0746 | +| entropy_loss | -4.34 | +| explained_variance | 0.101 | +| learning_rate | 4.96e-05 | +| loss | -0.0333 | +| n_updates | 38860 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.00025 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0497 | +| time/ | | +| fps | 1303 | +| iterations | 880 | +| time_elapsed | 1382 | +| total_timesteps | 1802240 | +| train/ | | +| approx_kl | 0.02325124 | +| clip_fraction | 0.44 | +| clip_range | 0.0745 | +| entropy_loss | -4.07 | +| explained_variance | 0.247 | +| learning_rate | 4.96e-05 | +| loss | -0.0336 | +| n_updates | 38864 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000181 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0441 | +| time/ | | +| fps | 1303 | +| iterations | 881 | +| time_elapsed | 1384 | +| total_timesteps | 1804288 | +| train/ | | +| approx_kl | 0.025161859 | +| clip_fraction | 0.444 | +| clip_range | 0.0745 | +| entropy_loss | -4.09 | +| explained_variance | 0.427 | +| learning_rate | 4.96e-05 | +| loss | -0.0331 | +| n_updates | 38868 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000164 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0433 | +| time/ | | +| fps | 1303 | +| iterations | 882 | +| time_elapsed | 1385 | +| total_timesteps | 1806336 | +| train/ | | +| approx_kl | 0.031719647 | +| clip_fraction | 0.448 | +| clip_range | 0.0745 | +| entropy_loss | -3.83 | +| explained_variance | 0.431 | +| learning_rate | 4.96e-05 | +| loss | -0.0337 | +| n_updates | 38872 | +| policy_gradient_loss | -0.0217 | +| value_loss | 0.000189 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.042 | +| time/ | | +| fps | 1303 | +| iterations | 883 | +| time_elapsed | 1387 | +| total_timesteps | 1808384 | +| train/ | | +| approx_kl | 0.026838195 | +| clip_fraction | 0.42 | +| clip_range | 0.0745 | +| entropy_loss | -3.85 | +| explained_variance | 0.428 | +| learning_rate | 4.96e-05 | +| loss | -0.0336 | +| n_updates | 38876 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000211 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.0397 | +| time/ | | +| fps | 1303 | +| iterations | 884 | +| time_elapsed | 1389 | +| total_timesteps | 1810432 | +| train/ | | +| approx_kl | 0.027980061 | +| clip_fraction | 0.477 | +| clip_range | 0.0745 | +| entropy_loss | -3.97 | +| explained_variance | 0.0498 | +| learning_rate | 4.96e-05 | +| loss | -0.032 | +| n_updates | 38880 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000225 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.0397 | +| time/ | | +| fps | 1303 | +| iterations | 885 | +| time_elapsed | 1390 | +| total_timesteps | 1812480 | +| train/ | | +| approx_kl | 0.02675487 | +| clip_fraction | 0.444 | +| clip_range | 0.0745 | +| entropy_loss | -4.09 | +| explained_variance | 0.31 | +| learning_rate | 4.96e-05 | +| loss | -0.0293 | +| n_updates | 38884 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000218 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.0393 | +| time/ | | +| fps | 1303 | +| iterations | 886 | +| time_elapsed | 1392 | +| total_timesteps | 1814528 | +| train/ | | +| approx_kl | 0.031247586 | +| clip_fraction | 0.449 | +| clip_range | 0.0745 | +| entropy_loss | -4.03 | +| explained_variance | 0.0542 | +| learning_rate | 4.96e-05 | +| loss | -0.0342 | +| n_updates | 38888 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.00026 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.0393 | +| time/ | | +| fps | 1303 | +| iterations | 887 | +| time_elapsed | 1393 | +| total_timesteps | 1816576 | +| train/ | | +| approx_kl | 0.029016547 | +| clip_fraction | 0.466 | +| clip_range | 0.0745 | +| entropy_loss | -4.18 | +| explained_variance | -0.502 | +| learning_rate | 4.96e-05 | +| loss | -0.0297 | +| n_updates | 38892 | +| policy_gradient_loss | -0.0172 | +| value_loss | 0.00031 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.0334 | +| time/ | | +| fps | 1303 | +| iterations | 888 | +| time_elapsed | 1395 | +| total_timesteps | 1818624 | +| train/ | | +| approx_kl | 0.032258227 | +| clip_fraction | 0.485 | +| clip_range | 0.0745 | +| entropy_loss | -4.39 | +| explained_variance | -0.186 | +| learning_rate | 4.96e-05 | +| loss | -0.0356 | +| n_updates | 38896 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000293 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.0322 | +| time/ | | +| fps | 1303 | +| iterations | 889 | +| time_elapsed | 1396 | +| total_timesteps | 1820672 | +| train/ | | +| approx_kl | 0.02560549 | +| clip_fraction | 0.455 | +| clip_range | 0.0745 | +| entropy_loss | -4.22 | +| explained_variance | -0.218 | +| learning_rate | 4.96e-05 | +| loss | -0.0293 | +| n_updates | 38900 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000263 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.38e+03 | +| ep_rew_mean | 0.0347 | +| time/ | | +| fps | 1303 | +| iterations | 890 | +| time_elapsed | 1398 | +| total_timesteps | 1822720 | +| train/ | | +| approx_kl | 0.029311165 | +| clip_fraction | 0.478 | +| clip_range | 0.0745 | +| entropy_loss | -4.17 | +| explained_variance | -0.222 | +| learning_rate | 4.96e-05 | +| loss | -0.0347 | +| n_updates | 38904 | +| policy_gradient_loss | -0.0214 | +| value_loss | 0.000246 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.0328 | +| time/ | | +| fps | 1303 | +| iterations | 891 | +| time_elapsed | 1399 | +| total_timesteps | 1824768 | +| train/ | | +| approx_kl | 0.024580967 | +| clip_fraction | 0.425 | +| clip_range | 0.0745 | +| entropy_loss | -4.02 | +| explained_variance | 0.268 | +| learning_rate | 4.96e-05 | +| loss | -0.0303 | +| n_updates | 38908 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000242 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0322 | +| time/ | | +| fps | 1303 | +| iterations | 892 | +| time_elapsed | 1401 | +| total_timesteps | 1826816 | +| train/ | | +| approx_kl | 0.02683508 | +| clip_fraction | 0.446 | +| clip_range | 0.0745 | +| entropy_loss | -3.82 | +| explained_variance | 0.315 | +| learning_rate | 4.96e-05 | +| loss | -0.0266 | +| n_updates | 38912 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000318 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0289 | +| time/ | | +| fps | 1303 | +| iterations | 893 | +| time_elapsed | 1403 | +| total_timesteps | 1828864 | +| train/ | | +| approx_kl | 0.028319549 | +| clip_fraction | 0.439 | +| clip_range | 0.0745 | +| entropy_loss | -4.14 | +| explained_variance | 0.177 | +| learning_rate | 4.96e-05 | +| loss | -0.03 | +| n_updates | 38916 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000339 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0283 | +| time/ | | +| fps | 1303 | +| iterations | 894 | +| time_elapsed | 1404 | +| total_timesteps | 1830912 | +| train/ | | +| approx_kl | 0.02855169 | +| clip_fraction | 0.456 | +| clip_range | 0.0745 | +| entropy_loss | -4.2 | +| explained_variance | -0.0412 | +| learning_rate | 4.96e-05 | +| loss | -0.0321 | +| n_updates | 38920 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.000307 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.0299 | +| time/ | | +| fps | 1303 | +| iterations | 895 | +| time_elapsed | 1406 | +| total_timesteps | 1832960 | +| train/ | | +| approx_kl | 0.03140807 | +| clip_fraction | 0.472 | +| clip_range | 0.0745 | +| entropy_loss | -3.86 | +| explained_variance | 0.432 | +| learning_rate | 4.96e-05 | +| loss | -0.0314 | +| n_updates | 38924 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000239 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.0277 | +| time/ | | +| fps | 1303 | +| iterations | 896 | +| time_elapsed | 1407 | +| total_timesteps | 1835008 | +| train/ | | +| approx_kl | 0.035754204 | +| clip_fraction | 0.466 | +| clip_range | 0.0745 | +| entropy_loss | -3.95 | +| explained_variance | 0.441 | +| learning_rate | 4.96e-05 | +| loss | -0.0349 | +| n_updates | 38928 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000166 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.0287 | +| time/ | | +| fps | 1303 | +| iterations | 897 | +| time_elapsed | 1409 | +| total_timesteps | 1837056 | +| train/ | | +| approx_kl | 0.031825587 | +| clip_fraction | 0.451 | +| clip_range | 0.0745 | +| entropy_loss | -3.83 | +| explained_variance | 0.231 | +| learning_rate | 4.96e-05 | +| loss | -0.0336 | +| n_updates | 38932 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000305 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.37e+03 | +| ep_rew_mean | 0.0311 | +| time/ | | +| fps | 1303 | +| iterations | 898 | +| time_elapsed | 1410 | +| total_timesteps | 1839104 | +| train/ | | +| approx_kl | 0.026851756 | +| clip_fraction | 0.476 | +| clip_range | 0.0745 | +| entropy_loss | -3.98 | +| explained_variance | -0.0496 | +| learning_rate | 4.96e-05 | +| loss | -0.0286 | +| n_updates | 38936 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000276 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.36e+03 | +| ep_rew_mean | 0.0358 | +| time/ | | +| fps | 1303 | +| iterations | 899 | +| time_elapsed | 1412 | +| total_timesteps | 1841152 | +| train/ | | +| approx_kl | 0.027433917 | +| clip_fraction | 0.469 | +| clip_range | 0.0745 | +| entropy_loss | -4.07 | +| explained_variance | -0.00532 | +| learning_rate | 4.96e-05 | +| loss | -0.0373 | +| n_updates | 38940 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000218 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0363 | +| time/ | | +| fps | 1303 | +| iterations | 900 | +| time_elapsed | 1413 | +| total_timesteps | 1843200 | +| train/ | | +| approx_kl | 0.031372942 | +| clip_fraction | 0.441 | +| clip_range | 0.0745 | +| entropy_loss | -4.12 | +| explained_variance | 0.217 | +| learning_rate | 4.96e-05 | +| loss | -0.0331 | +| n_updates | 38944 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000283 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.034 | +| time/ | | +| fps | 1303 | +| iterations | 901 | +| time_elapsed | 1415 | +| total_timesteps | 1845248 | +| train/ | | +| approx_kl | 0.024587568 | +| clip_fraction | 0.449 | +| clip_range | 0.0745 | +| entropy_loss | -4.09 | +| explained_variance | 0.0358 | +| learning_rate | 4.96e-05 | +| loss | -0.0361 | +| n_updates | 38948 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000245 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0227 | +| time/ | | +| fps | 1303 | +| iterations | 902 | +| time_elapsed | 1417 | +| total_timesteps | 1847296 | +| train/ | | +| approx_kl | 0.025096979 | +| clip_fraction | 0.457 | +| clip_range | 0.0745 | +| entropy_loss | -3.93 | +| explained_variance | 0.338 | +| learning_rate | 4.96e-05 | +| loss | -0.0331 | +| n_updates | 38952 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000262 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.35e+03 | +| ep_rew_mean | 0.0202 | +| time/ | | +| fps | 1303 | +| iterations | 903 | +| time_elapsed | 1418 | +| total_timesteps | 1849344 | +| train/ | | +| approx_kl | 0.03161209 | +| clip_fraction | 0.446 | +| clip_range | 0.0745 | +| entropy_loss | -3.64 | +| explained_variance | 0.509 | +| learning_rate | 4.96e-05 | +| loss | -0.0297 | +| n_updates | 38956 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000283 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.024 | +| time/ | | +| fps | 1303 | +| iterations | 904 | +| time_elapsed | 1420 | +| total_timesteps | 1851392 | +| train/ | | +| approx_kl | 0.030640196 | +| clip_fraction | 0.432 | +| clip_range | 0.0745 | +| entropy_loss | -4 | +| explained_variance | -0.205 | +| learning_rate | 4.96e-05 | +| loss | -0.0342 | +| n_updates | 38960 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000262 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0244 | +| time/ | | +| fps | 1303 | +| iterations | 905 | +| time_elapsed | 1421 | +| total_timesteps | 1853440 | +| train/ | | +| approx_kl | 0.031316392 | +| clip_fraction | 0.452 | +| clip_range | 0.0745 | +| entropy_loss | -3.81 | +| explained_variance | 0.457 | +| learning_rate | 4.96e-05 | +| loss | -0.0318 | +| n_updates | 38964 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000313 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0244 | +| time/ | | +| fps | 1303 | +| iterations | 906 | +| time_elapsed | 1423 | +| total_timesteps | 1855488 | +| train/ | | +| approx_kl | 0.029306225 | +| clip_fraction | 0.465 | +| clip_range | 0.0745 | +| entropy_loss | -3.94 | +| explained_variance | 0.202 | +| learning_rate | 4.96e-05 | +| loss | -0.03 | +| n_updates | 38968 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000255 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0252 | +| time/ | | +| fps | 1303 | +| iterations | 907 | +| time_elapsed | 1424 | +| total_timesteps | 1857536 | +| train/ | | +| approx_kl | 0.033055432 | +| clip_fraction | 0.439 | +| clip_range | 0.0745 | +| entropy_loss | -4.04 | +| explained_variance | -0.388 | +| learning_rate | 4.96e-05 | +| loss | -0.0277 | +| n_updates | 38972 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000275 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0322 | +| time/ | | +| fps | 1303 | +| iterations | 908 | +| time_elapsed | 1426 | +| total_timesteps | 1859584 | +| train/ | | +| approx_kl | 0.032348156 | +| clip_fraction | 0.473 | +| clip_range | 0.0745 | +| entropy_loss | -3.86 | +| explained_variance | 0.0447 | +| learning_rate | 4.96e-05 | +| loss | -0.0319 | +| n_updates | 38976 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000338 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0251 | +| time/ | | +| fps | 1303 | +| iterations | 909 | +| time_elapsed | 1428 | +| total_timesteps | 1861632 | +| train/ | | +| approx_kl | 0.02926705 | +| clip_fraction | 0.481 | +| clip_range | 0.0745 | +| entropy_loss | -3.8 | +| explained_variance | 0.19 | +| learning_rate | 4.96e-05 | +| loss | -0.035 | +| n_updates | 38980 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.00029 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0267 | +| time/ | | +| fps | 1303 | +| iterations | 910 | +| time_elapsed | 1429 | +| total_timesteps | 1863680 | +| train/ | | +| approx_kl | 0.029245809 | +| clip_fraction | 0.457 | +| clip_range | 0.0745 | +| entropy_loss | -3.93 | +| explained_variance | -0.316 | +| learning_rate | 4.96e-05 | +| loss | -0.042 | +| n_updates | 38984 | +| policy_gradient_loss | -0.0211 | +| value_loss | 0.000292 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.0267 | +| time/ | | +| fps | 1303 | +| iterations | 911 | +| time_elapsed | 1431 | +| total_timesteps | 1865728 | +| train/ | | +| approx_kl | 0.028657604 | +| clip_fraction | 0.458 | +| clip_range | 0.0745 | +| entropy_loss | -3.83 | +| explained_variance | 0.242 | +| learning_rate | 4.96e-05 | +| loss | -0.0299 | +| n_updates | 38988 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000237 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | 0.028 | +| time/ | | +| fps | 1303 | +| iterations | 912 | +| time_elapsed | 1432 | +| total_timesteps | 1867776 | +| train/ | | +| approx_kl | 0.032386515 | +| clip_fraction | 0.456 | +| clip_range | 0.0745 | +| entropy_loss | -3.79 | +| explained_variance | 0.14 | +| learning_rate | 4.96e-05 | +| loss | -0.0328 | +| n_updates | 38992 | +| policy_gradient_loss | -0.0221 | +| value_loss | 0.000257 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0211 | +| time/ | | +| fps | 1303 | +| iterations | 913 | +| time_elapsed | 1434 | +| total_timesteps | 1869824 | +| train/ | | +| approx_kl | 0.030642789 | +| clip_fraction | 0.459 | +| clip_range | 0.0745 | +| entropy_loss | -3.79 | +| explained_variance | 0.358 | +| learning_rate | 4.96e-05 | +| loss | -0.0309 | +| n_updates | 38996 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000287 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | 0.02 | +| time/ | | +| fps | 1303 | +| iterations | 914 | +| time_elapsed | 1435 | +| total_timesteps | 1871872 | +| train/ | | +| approx_kl | 0.02848877 | +| clip_fraction | 0.454 | +| clip_range | 0.0745 | +| entropy_loss | -3.78 | +| explained_variance | 0.488 | +| learning_rate | 4.96e-05 | +| loss | -0.03 | +| n_updates | 39000 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000233 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | 0.0108 | +| time/ | | +| fps | 1303 | +| iterations | 915 | +| time_elapsed | 1437 | +| total_timesteps | 1873920 | +| train/ | | +| approx_kl | 0.031333435 | +| clip_fraction | 0.474 | +| clip_range | 0.0745 | +| entropy_loss | -3.78 | +| explained_variance | 0.386 | +| learning_rate | 4.96e-05 | +| loss | -0.0328 | +| n_updates | 39004 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000232 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | -0.00254 | +| time/ | | +| fps | 1303 | +| iterations | 916 | +| time_elapsed | 1438 | +| total_timesteps | 1875968 | +| train/ | | +| approx_kl | 0.029821418 | +| clip_fraction | 0.475 | +| clip_range | 0.0745 | +| entropy_loss | -3.72 | +| explained_variance | 0.0242 | +| learning_rate | 4.96e-05 | +| loss | -0.0339 | +| n_updates | 39008 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000345 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | -0.00254 | +| time/ | | +| fps | 1303 | +| iterations | 917 | +| time_elapsed | 1440 | +| total_timesteps | 1878016 | +| train/ | | +| approx_kl | 0.030096428 | +| clip_fraction | 0.462 | +| clip_range | 0.0745 | +| entropy_loss | -3.85 | +| explained_variance | 0.155 | +| learning_rate | 4.96e-05 | +| loss | -0.0351 | +| n_updates | 39012 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000314 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.34e+03 | +| ep_rew_mean | -0.00928 | +| time/ | | +| fps | 1303 | +| iterations | 918 | +| time_elapsed | 1442 | +| total_timesteps | 1880064 | +| train/ | | +| approx_kl | 0.030194897 | +| clip_fraction | 0.469 | +| clip_range | 0.0745 | +| entropy_loss | -4.02 | +| explained_variance | -0.227 | +| learning_rate | 4.96e-05 | +| loss | -0.033 | +| n_updates | 39016 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000251 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | -0.0012 | +| time/ | | +| fps | 1303 | +| iterations | 919 | +| time_elapsed | 1443 | +| total_timesteps | 1882112 | +| train/ | | +| approx_kl | 0.0229311 | +| clip_fraction | 0.447 | +| clip_range | 0.0745 | +| entropy_loss | -4.06 | +| explained_variance | 0.312 | +| learning_rate | 4.96e-05 | +| loss | -0.0339 | +| n_updates | 39020 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000245 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | -0.0012 | +| time/ | | +| fps | 1303 | +| iterations | 920 | +| time_elapsed | 1445 | +| total_timesteps | 1884160 | +| train/ | | +| approx_kl | 0.025762763 | +| clip_fraction | 0.442 | +| clip_range | 0.0745 | +| entropy_loss | -3.82 | +| explained_variance | 0.223 | +| learning_rate | 4.96e-05 | +| loss | -0.0248 | +| n_updates | 39024 | +| policy_gradient_loss | -0.0123 | +| value_loss | 0.000765 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | -0.0012 | +| time/ | | +| fps | 1303 | +| iterations | 921 | +| time_elapsed | 1446 | +| total_timesteps | 1886208 | +| train/ | | +| approx_kl | 0.02955987 | +| clip_fraction | 0.481 | +| clip_range | 0.0745 | +| entropy_loss | -3.96 | +| explained_variance | -0.329 | +| learning_rate | 4.96e-05 | +| loss | -0.0339 | +| n_updates | 39028 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000303 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | -0.00447 | +| time/ | | +| fps | 1303 | +| iterations | 922 | +| time_elapsed | 1448 | +| total_timesteps | 1888256 | +| train/ | | +| approx_kl | 0.025512911 | +| clip_fraction | 0.489 | +| clip_range | 0.0745 | +| entropy_loss | -4.12 | +| explained_variance | -0.367 | +| learning_rate | 4.96e-05 | +| loss | -0.0237 | +| n_updates | 39032 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000268 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | -0.00633 | +| time/ | | +| fps | 1303 | +| iterations | 923 | +| time_elapsed | 1449 | +| total_timesteps | 1890304 | +| train/ | | +| approx_kl | 0.02519657 | +| clip_fraction | 0.444 | +| clip_range | 0.0745 | +| entropy_loss | -3.96 | +| explained_variance | 0.254 | +| learning_rate | 4.96e-05 | +| loss | -0.032 | +| n_updates | 39036 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000426 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | -0.00305 | +| time/ | | +| fps | 1303 | +| iterations | 924 | +| time_elapsed | 1451 | +| total_timesteps | 1892352 | +| train/ | | +| approx_kl | 0.03170876 | +| clip_fraction | 0.458 | +| clip_range | 0.0745 | +| entropy_loss | -3.58 | +| explained_variance | 0.0171 | +| learning_rate | 4.96e-05 | +| loss | -0.0252 | +| n_updates | 39040 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000314 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | -0.00305 | +| time/ | | +| fps | 1303 | +| iterations | 925 | +| time_elapsed | 1452 | +| total_timesteps | 1894400 | +| train/ | | +| approx_kl | 0.032167718 | +| clip_fraction | 0.47 | +| clip_range | 0.0745 | +| entropy_loss | -3.6 | +| explained_variance | 0.129 | +| learning_rate | 4.96e-05 | +| loss | -0.026 | +| n_updates | 39044 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000202 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | -0.00305 | +| time/ | | +| fps | 1303 | +| iterations | 926 | +| time_elapsed | 1454 | +| total_timesteps | 1896448 | +| train/ | | +| approx_kl | 0.033482514 | +| clip_fraction | 0.487 | +| clip_range | 0.0745 | +| entropy_loss | -3.85 | +| explained_variance | -0.107 | +| learning_rate | 4.96e-05 | +| loss | -0.0336 | +| n_updates | 39048 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000258 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | -0.0172 | +| time/ | | +| fps | 1303 | +| iterations | 927 | +| time_elapsed | 1455 | +| total_timesteps | 1898496 | +| train/ | | +| approx_kl | 0.029450204 | +| clip_fraction | 0.472 | +| clip_range | 0.0745 | +| entropy_loss | -4.2 | +| explained_variance | -0.0718 | +| learning_rate | 4.95e-05 | +| loss | -0.0323 | +| n_updates | 39052 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.00029 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | -0.0164 | +| time/ | | +| fps | 1303 | +| iterations | 928 | +| time_elapsed | 1457 | +| total_timesteps | 1900544 | +| train/ | | +| approx_kl | 0.022660417 | +| clip_fraction | 0.436 | +| clip_range | 0.0745 | +| entropy_loss | -3.96 | +| explained_variance | -0.005 | +| learning_rate | 4.95e-05 | +| loss | -0.025 | +| n_updates | 39056 | +| policy_gradient_loss | -0.0147 | +| value_loss | 0.000941 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.33e+03 | +| ep_rew_mean | -0.0141 | +| time/ | | +| fps | 1303 | +| iterations | 929 | +| time_elapsed | 1459 | +| total_timesteps | 1902592 | +| train/ | | +| approx_kl | 0.030746378 | +| clip_fraction | 0.443 | +| clip_range | 0.0745 | +| entropy_loss | -3.63 | +| explained_variance | 0.31 | +| learning_rate | 4.95e-05 | +| loss | -0.0291 | +| n_updates | 39060 | +| policy_gradient_loss | -0.0163 | +| value_loss | 0.000346 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.32e+03 | +| ep_rew_mean | -0.02 | +| time/ | | +| fps | 1303 | +| iterations | 930 | +| time_elapsed | 1460 | +| total_timesteps | 1904640 | +| train/ | | +| approx_kl | 0.030302323 | +| clip_fraction | 0.453 | +| clip_range | 0.0745 | +| entropy_loss | -4.02 | +| explained_variance | -0.38 | +| learning_rate | 4.95e-05 | +| loss | -0.0322 | +| n_updates | 39064 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000359 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | -0.0242 | +| time/ | | +| fps | 1303 | +| iterations | 931 | +| time_elapsed | 1462 | +| total_timesteps | 1906688 | +| train/ | | +| approx_kl | 0.030495971 | +| clip_fraction | 0.457 | +| clip_range | 0.0745 | +| entropy_loss | -3.91 | +| explained_variance | 0.0061 | +| learning_rate | 4.95e-05 | +| loss | -0.0335 | +| n_updates | 39068 | +| policy_gradient_loss | -0.0173 | +| value_loss | 0.000255 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.31e+03 | +| ep_rew_mean | -0.0242 | +| time/ | | +| fps | 1303 | +| iterations | 932 | +| time_elapsed | 1463 | +| total_timesteps | 1908736 | +| train/ | | +| approx_kl | 0.027402902 | +| clip_fraction | 0.47 | +| clip_range | 0.0745 | +| entropy_loss | -3.88 | +| explained_variance | 0.000868 | +| learning_rate | 4.95e-05 | +| loss | -0.0224 | +| n_updates | 39072 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000349 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | -0.0203 | +| time/ | | +| fps | 1303 | +| iterations | 933 | +| time_elapsed | 1465 | +| total_timesteps | 1910784 | +| train/ | | +| approx_kl | 0.028452355 | +| clip_fraction | 0.472 | +| clip_range | 0.0745 | +| entropy_loss | -4.13 | +| explained_variance | -0.207 | +| learning_rate | 4.95e-05 | +| loss | -0.0375 | +| n_updates | 39076 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.00023 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | -0.0227 | +| time/ | | +| fps | 1303 | +| iterations | 934 | +| time_elapsed | 1466 | +| total_timesteps | 1912832 | +| train/ | | +| approx_kl | 0.037603162 | +| clip_fraction | 0.485 | +| clip_range | 0.0745 | +| entropy_loss | -4.21 | +| explained_variance | -0.0418 | +| learning_rate | 4.95e-05 | +| loss | -0.0387 | +| n_updates | 39080 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000309 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | -0.0227 | +| time/ | | +| fps | 1303 | +| iterations | 935 | +| time_elapsed | 1468 | +| total_timesteps | 1914880 | +| train/ | | +| approx_kl | 0.029675141 | +| clip_fraction | 0.466 | +| clip_range | 0.0745 | +| entropy_loss | -4.08 | +| explained_variance | 0.11 | +| learning_rate | 4.95e-05 | +| loss | -0.0312 | +| n_updates | 39084 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000197 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | -0.0209 | +| time/ | | +| fps | 1303 | +| iterations | 936 | +| time_elapsed | 1470 | +| total_timesteps | 1916928 | +| train/ | | +| approx_kl | 0.034206465 | +| clip_fraction | 0.454 | +| clip_range | 0.0745 | +| entropy_loss | -4.08 | +| explained_variance | -0.103 | +| learning_rate | 4.95e-05 | +| loss | -0.0328 | +| n_updates | 39088 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000308 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | -0.0209 | +| time/ | | +| fps | 1304 | +| iterations | 937 | +| time_elapsed | 1471 | +| total_timesteps | 1918976 | +| train/ | | +| approx_kl | 0.032650962 | +| clip_fraction | 0.466 | +| clip_range | 0.0745 | +| entropy_loss | -3.99 | +| explained_variance | 0.337 | +| learning_rate | 4.95e-05 | +| loss | -0.0334 | +| n_updates | 39092 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000261 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | -0.014 | +| time/ | | +| fps | 1304 | +| iterations | 938 | +| time_elapsed | 1473 | +| total_timesteps | 1921024 | +| train/ | | +| approx_kl | 0.030299352 | +| clip_fraction | 0.458 | +| clip_range | 0.0745 | +| entropy_loss | -3.96 | +| explained_variance | 0.0696 | +| learning_rate | 4.95e-05 | +| loss | -0.033 | +| n_updates | 39096 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000218 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | -0.00471 | +| time/ | | +| fps | 1304 | +| iterations | 939 | +| time_elapsed | 1474 | +| total_timesteps | 1923072 | +| train/ | | +| approx_kl | 0.031217262 | +| clip_fraction | 0.453 | +| clip_range | 0.0745 | +| entropy_loss | -3.94 | +| explained_variance | 0.298 | +| learning_rate | 4.95e-05 | +| loss | -0.0309 | +| n_updates | 39100 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.00032 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.000116 | +| time/ | | +| fps | 1304 | +| iterations | 940 | +| time_elapsed | 1476 | +| total_timesteps | 1925120 | +| train/ | | +| approx_kl | 0.026585622 | +| clip_fraction | 0.431 | +| clip_range | 0.0745 | +| entropy_loss | -3.76 | +| explained_variance | 0.28 | +| learning_rate | 4.95e-05 | +| loss | -0.0289 | +| n_updates | 39104 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000261 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.00368 | +| time/ | | +| fps | 1304 | +| iterations | 941 | +| time_elapsed | 1477 | +| total_timesteps | 1927168 | +| train/ | | +| approx_kl | 0.024076033 | +| clip_fraction | 0.462 | +| clip_range | 0.0745 | +| entropy_loss | -4.01 | +| explained_variance | 0.109 | +| learning_rate | 4.95e-05 | +| loss | -0.0289 | +| n_updates | 39108 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000254 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.00804 | +| time/ | | +| fps | 1304 | +| iterations | 942 | +| time_elapsed | 1479 | +| total_timesteps | 1929216 | +| train/ | | +| approx_kl | 0.029334467 | +| clip_fraction | 0.434 | +| clip_range | 0.0745 | +| entropy_loss | -3.49 | +| explained_variance | 0.511 | +| learning_rate | 4.95e-05 | +| loss | -0.0348 | +| n_updates | 39112 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.00027 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.00416 | +| time/ | | +| fps | 1304 | +| iterations | 943 | +| time_elapsed | 1480 | +| total_timesteps | 1931264 | +| train/ | | +| approx_kl | 0.029083513 | +| clip_fraction | 0.455 | +| clip_range | 0.0745 | +| entropy_loss | -3.44 | +| explained_variance | 0.481 | +| learning_rate | 4.95e-05 | +| loss | -0.0323 | +| n_updates | 39116 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000208 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.00416 | +| time/ | | +| fps | 1304 | +| iterations | 944 | +| time_elapsed | 1482 | +| total_timesteps | 1933312 | +| train/ | | +| approx_kl | 0.029961722 | +| clip_fraction | 0.483 | +| clip_range | 0.0745 | +| entropy_loss | -3.58 | +| explained_variance | 0.29 | +| learning_rate | 4.95e-05 | +| loss | -0.0262 | +| n_updates | 39120 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000248 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.0133 | +| time/ | | +| fps | 1304 | +| iterations | 945 | +| time_elapsed | 1484 | +| total_timesteps | 1935360 | +| train/ | | +| approx_kl | 0.027055262 | +| clip_fraction | 0.474 | +| clip_range | 0.0745 | +| entropy_loss | -3.91 | +| explained_variance | -0.0946 | +| learning_rate | 4.95e-05 | +| loss | -0.0312 | +| n_updates | 39124 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000331 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.0249 | +| time/ | | +| fps | 1304 | +| iterations | 946 | +| time_elapsed | 1485 | +| total_timesteps | 1937408 | +| train/ | | +| approx_kl | 0.034223545 | +| clip_fraction | 0.463 | +| clip_range | 0.0745 | +| entropy_loss | -3.76 | +| explained_variance | 0.225 | +| learning_rate | 4.95e-05 | +| loss | -0.0325 | +| n_updates | 39128 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000427 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.0224 | +| time/ | | +| fps | 1304 | +| iterations | 947 | +| time_elapsed | 1487 | +| total_timesteps | 1939456 | +| train/ | | +| approx_kl | 0.026531834 | +| clip_fraction | 0.449 | +| clip_range | 0.0745 | +| entropy_loss | -3.76 | +| explained_variance | -0.102 | +| learning_rate | 4.95e-05 | +| loss | -0.033 | +| n_updates | 39132 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000335 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.0317 | +| time/ | | +| fps | 1304 | +| iterations | 948 | +| time_elapsed | 1488 | +| total_timesteps | 1941504 | +| train/ | | +| approx_kl | 0.02856613 | +| clip_fraction | 0.452 | +| clip_range | 0.0745 | +| entropy_loss | -3.74 | +| explained_variance | 0.196 | +| learning_rate | 4.95e-05 | +| loss | -0.031 | +| n_updates | 39136 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000454 | +---------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.0299 | +| time/ | | +| fps | 1304 | +| iterations | 949 | +| time_elapsed | 1490 | +| total_timesteps | 1943552 | +| train/ | | +| approx_kl | 0.0285962 | +| clip_fraction | 0.471 | +| clip_range | 0.0745 | +| entropy_loss | -3.73 | +| explained_variance | -0.0647 | +| learning_rate | 4.95e-05 | +| loss | -0.0323 | +| n_updates | 39140 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000392 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.0299 | +| time/ | | +| fps | 1304 | +| iterations | 950 | +| time_elapsed | 1491 | +| total_timesteps | 1945600 | +| train/ | | +| approx_kl | 0.025803452 | +| clip_fraction | 0.471 | +| clip_range | 0.0745 | +| entropy_loss | -3.99 | +| explained_variance | 0.054 | +| learning_rate | 4.95e-05 | +| loss | -0.0339 | +| n_updates | 39144 | +| policy_gradient_loss | -0.0228 | +| value_loss | 0.000268 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.031 | +| time/ | | +| fps | 1304 | +| iterations | 951 | +| time_elapsed | 1493 | +| total_timesteps | 1947648 | +| train/ | | +| approx_kl | 0.028199743 | +| clip_fraction | 0.453 | +| clip_range | 0.0745 | +| entropy_loss | -3.71 | +| explained_variance | 0.107 | +| learning_rate | 4.95e-05 | +| loss | -0.0362 | +| n_updates | 39148 | +| policy_gradient_loss | -0.0191 | +| value_loss | 0.000299 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.0349 | +| time/ | | +| fps | 1304 | +| iterations | 952 | +| time_elapsed | 1494 | +| total_timesteps | 1949696 | +| train/ | | +| approx_kl | 0.030883946 | +| clip_fraction | 0.46 | +| clip_range | 0.0745 | +| entropy_loss | -3.73 | +| explained_variance | 0.328 | +| learning_rate | 4.95e-05 | +| loss | -0.0373 | +| n_updates | 39152 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000308 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.034 | +| time/ | | +| fps | 1304 | +| iterations | 953 | +| time_elapsed | 1496 | +| total_timesteps | 1951744 | +| train/ | | +| approx_kl | 0.028708603 | +| clip_fraction | 0.47 | +| clip_range | 0.0745 | +| entropy_loss | -3.82 | +| explained_variance | -0.161 | +| learning_rate | 4.95e-05 | +| loss | -0.0291 | +| n_updates | 39156 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000214 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.0313 | +| time/ | | +| fps | 1304 | +| iterations | 954 | +| time_elapsed | 1497 | +| total_timesteps | 1953792 | +| train/ | | +| approx_kl | 0.03390611 | +| clip_fraction | 0.468 | +| clip_range | 0.0745 | +| entropy_loss | -3.76 | +| explained_variance | 0.0382 | +| learning_rate | 4.95e-05 | +| loss | -0.034 | +| n_updates | 39160 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000281 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.033 | +| time/ | | +| fps | 1304 | +| iterations | 955 | +| time_elapsed | 1499 | +| total_timesteps | 1955840 | +| train/ | | +| approx_kl | 0.031352054 | +| clip_fraction | 0.463 | +| clip_range | 0.0745 | +| entropy_loss | -3.79 | +| explained_variance | -0.394 | +| learning_rate | 4.95e-05 | +| loss | -0.0341 | +| n_updates | 39164 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000296 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.0344 | +| time/ | | +| fps | 1304 | +| iterations | 956 | +| time_elapsed | 1500 | +| total_timesteps | 1957888 | +| train/ | | +| approx_kl | 0.026497304 | +| clip_fraction | 0.449 | +| clip_range | 0.0745 | +| entropy_loss | -3.88 | +| explained_variance | 0.0206 | +| learning_rate | 4.95e-05 | +| loss | -0.0315 | +| n_updates | 39168 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000351 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.0334 | +| time/ | | +| fps | 1304 | +| iterations | 957 | +| time_elapsed | 1502 | +| total_timesteps | 1959936 | +| train/ | | +| approx_kl | 0.030844275 | +| clip_fraction | 0.478 | +| clip_range | 0.0745 | +| entropy_loss | -3.85 | +| explained_variance | 0.307 | +| learning_rate | 4.95e-05 | +| loss | -0.0379 | +| n_updates | 39172 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.0002 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.0403 | +| time/ | | +| fps | 1304 | +| iterations | 958 | +| time_elapsed | 1504 | +| total_timesteps | 1961984 | +| train/ | | +| approx_kl | 0.030897781 | +| clip_fraction | 0.464 | +| clip_range | 0.0745 | +| entropy_loss | -3.45 | +| explained_variance | 0.572 | +| learning_rate | 4.95e-05 | +| loss | -0.0337 | +| n_updates | 39176 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000146 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.0381 | +| time/ | | +| fps | 1304 | +| iterations | 959 | +| time_elapsed | 1505 | +| total_timesteps | 1964032 | +| train/ | | +| approx_kl | 0.03352805 | +| clip_fraction | 0.46 | +| clip_range | 0.0745 | +| entropy_loss | -3.72 | +| explained_variance | 0.181 | +| learning_rate | 4.95e-05 | +| loss | -0.0299 | +| n_updates | 39180 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000205 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.0408 | +| time/ | | +| fps | 1304 | +| iterations | 960 | +| time_elapsed | 1507 | +| total_timesteps | 1966080 | +| train/ | | +| approx_kl | 0.029327314 | +| clip_fraction | 0.471 | +| clip_range | 0.0745 | +| entropy_loss | -3.88 | +| explained_variance | 0.139 | +| learning_rate | 4.95e-05 | +| loss | -0.0308 | +| n_updates | 39184 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000343 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.0395 | +| time/ | | +| fps | 1304 | +| iterations | 961 | +| time_elapsed | 1508 | +| total_timesteps | 1968128 | +| train/ | | +| approx_kl | 0.035860762 | +| clip_fraction | 0.442 | +| clip_range | 0.0745 | +| entropy_loss | -3.73 | +| explained_variance | 0.0665 | +| learning_rate | 4.95e-05 | +| loss | -0.0304 | +| n_updates | 39188 | +| policy_gradient_loss | -0.0164 | +| value_loss | 0.000837 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.0356 | +| time/ | | +| fps | 1304 | +| iterations | 962 | +| time_elapsed | 1510 | +| total_timesteps | 1970176 | +| train/ | | +| approx_kl | 0.033189625 | +| clip_fraction | 0.466 | +| clip_range | 0.0745 | +| entropy_loss | -3.56 | +| explained_variance | -0.0746 | +| learning_rate | 4.95e-05 | +| loss | -0.0343 | +| n_updates | 39192 | +| policy_gradient_loss | -0.0236 | +| value_loss | 0.000536 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.0436 | +| time/ | | +| fps | 1304 | +| iterations | 963 | +| time_elapsed | 1511 | +| total_timesteps | 1972224 | +| train/ | | +| approx_kl | 0.03921161 | +| clip_fraction | 0.48 | +| clip_range | 0.0745 | +| entropy_loss | -3.65 | +| explained_variance | -0.0105 | +| learning_rate | 4.95e-05 | +| loss | -0.035 | +| n_updates | 39196 | +| policy_gradient_loss | -0.0236 | +| value_loss | 0.000394 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.0436 | +| time/ | | +| fps | 1304 | +| iterations | 964 | +| time_elapsed | 1513 | +| total_timesteps | 1974272 | +| train/ | | +| approx_kl | 0.025872406 | +| clip_fraction | 0.442 | +| clip_range | 0.0745 | +| entropy_loss | -3.51 | +| explained_variance | 0.194 | +| learning_rate | 4.95e-05 | +| loss | -0.0334 | +| n_updates | 39200 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000423 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.0436 | +| time/ | | +| fps | 1304 | +| iterations | 965 | +| time_elapsed | 1515 | +| total_timesteps | 1976320 | +| train/ | | +| approx_kl | 0.026648102 | +| clip_fraction | 0.47 | +| clip_range | 0.0745 | +| entropy_loss | -3.57 | +| explained_variance | 0.125 | +| learning_rate | 4.95e-05 | +| loss | -0.031 | +| n_updates | 39204 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000363 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.0418 | +| time/ | | +| fps | 1304 | +| iterations | 966 | +| time_elapsed | 1516 | +| total_timesteps | 1978368 | +| train/ | | +| approx_kl | 0.027938742 | +| clip_fraction | 0.487 | +| clip_range | 0.0745 | +| entropy_loss | -4.02 | +| explained_variance | -0.0804 | +| learning_rate | 4.95e-05 | +| loss | -0.0318 | +| n_updates | 39208 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000351 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.0418 | +| time/ | | +| fps | 1304 | +| iterations | 967 | +| time_elapsed | 1518 | +| total_timesteps | 1980416 | +| train/ | | +| approx_kl | 0.030628417 | +| clip_fraction | 0.459 | +| clip_range | 0.0745 | +| entropy_loss | -3.7 | +| explained_variance | 0.195 | +| learning_rate | 4.95e-05 | +| loss | -0.035 | +| n_updates | 39212 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000239 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.036 | +| time/ | | +| fps | 1304 | +| iterations | 968 | +| time_elapsed | 1519 | +| total_timesteps | 1982464 | +| train/ | | +| approx_kl | 0.028470729 | +| clip_fraction | 0.503 | +| clip_range | 0.0745 | +| entropy_loss | -3.85 | +| explained_variance | -0.382 | +| learning_rate | 4.95e-05 | +| loss | -0.0284 | +| n_updates | 39216 | +| policy_gradient_loss | -0.0196 | +| value_loss | 0.000211 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.0322 | +| time/ | | +| fps | 1304 | +| iterations | 969 | +| time_elapsed | 1521 | +| total_timesteps | 1984512 | +| train/ | | +| approx_kl | 0.030213222 | +| clip_fraction | 0.448 | +| clip_range | 0.0745 | +| entropy_loss | -3.92 | +| explained_variance | 0.275 | +| learning_rate | 4.95e-05 | +| loss | -0.0288 | +| n_updates | 39220 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.00033 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.0322 | +| time/ | | +| fps | 1304 | +| iterations | 970 | +| time_elapsed | 1523 | +| total_timesteps | 1986560 | +| train/ | | +| approx_kl | 0.030677835 | +| clip_fraction | 0.43 | +| clip_range | 0.0745 | +| entropy_loss | -3.56 | +| explained_variance | 0.358 | +| learning_rate | 4.95e-05 | +| loss | -0.026 | +| n_updates | 39224 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000315 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.0355 | +| time/ | | +| fps | 1304 | +| iterations | 971 | +| time_elapsed | 1524 | +| total_timesteps | 1988608 | +| train/ | | +| approx_kl | 0.030244747 | +| clip_fraction | 0.479 | +| clip_range | 0.0745 | +| entropy_loss | -3.66 | +| explained_variance | -0.119 | +| learning_rate | 4.95e-05 | +| loss | -0.0337 | +| n_updates | 39228 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000196 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.0377 | +| time/ | | +| fps | 1304 | +| iterations | 972 | +| time_elapsed | 1526 | +| total_timesteps | 1990656 | +| train/ | | +| approx_kl | 0.031418346 | +| clip_fraction | 0.46 | +| clip_range | 0.0745 | +| entropy_loss | -3.48 | +| explained_variance | 0.141 | +| learning_rate | 4.95e-05 | +| loss | -0.0342 | +| n_updates | 39232 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000315 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.0377 | +| time/ | | +| fps | 1304 | +| iterations | 973 | +| time_elapsed | 1527 | +| total_timesteps | 1992704 | +| train/ | | +| approx_kl | 0.03206964 | +| clip_fraction | 0.467 | +| clip_range | 0.0745 | +| entropy_loss | -3.72 | +| explained_variance | 0.0842 | +| learning_rate | 4.95e-05 | +| loss | -0.0315 | +| n_updates | 39236 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000207 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.0444 | +| time/ | | +| fps | 1304 | +| iterations | 974 | +| time_elapsed | 1529 | +| total_timesteps | 1994752 | +| train/ | | +| approx_kl | 0.03358571 | +| clip_fraction | 0.439 | +| clip_range | 0.0745 | +| entropy_loss | -3.59 | +| explained_variance | 0.372 | +| learning_rate | 4.95e-05 | +| loss | -0.0349 | +| n_updates | 39240 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000313 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.0485 | +| time/ | | +| fps | 1304 | +| iterations | 975 | +| time_elapsed | 1531 | +| total_timesteps | 1996800 | +| train/ | | +| approx_kl | 0.024606071 | +| clip_fraction | 0.438 | +| clip_range | 0.0745 | +| entropy_loss | -3.62 | +| explained_variance | 0.327 | +| learning_rate | 4.95e-05 | +| loss | -0.0323 | +| n_updates | 39244 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000317 | +----------------------------------------- +--------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.0509 | +| time/ | | +| fps | 1304 | +| iterations | 976 | +| time_elapsed | 1532 | +| total_timesteps | 1998848 | +| train/ | | +| approx_kl | 0.0286396 | +| clip_fraction | 0.424 | +| clip_range | 0.0745 | +| entropy_loss | -3.72 | +| explained_variance | 0.38 | +| learning_rate | 4.95e-05 | +| loss | -0.0307 | +| n_updates | 39248 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000259 | +--------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.0509 | +| time/ | | +| fps | 1304 | +| iterations | 977 | +| time_elapsed | 1534 | +| total_timesteps | 2000896 | +| train/ | | +| approx_kl | 0.028574536 | +| clip_fraction | 0.452 | +| clip_range | 0.0745 | +| entropy_loss | -3.89 | +| explained_variance | 0.0654 | +| learning_rate | 4.95e-05 | +| loss | -0.0284 | +| n_updates | 39252 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000336 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.0511 | +| time/ | | +| fps | 1304 | +| iterations | 978 | +| time_elapsed | 1535 | +| total_timesteps | 2002944 | +| train/ | | +| approx_kl | 0.02809409 | +| clip_fraction | 0.469 | +| clip_range | 0.0745 | +| entropy_loss | -4.23 | +| explained_variance | -0.198 | +| learning_rate | 4.95e-05 | +| loss | -0.0295 | +| n_updates | 39256 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.00021 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.0462 | +| time/ | | +| fps | 1304 | +| iterations | 979 | +| time_elapsed | 1537 | +| total_timesteps | 2004992 | +| train/ | | +| approx_kl | 0.03367228 | +| clip_fraction | 0.461 | +| clip_range | 0.0745 | +| entropy_loss | -3.68 | +| explained_variance | 0.275 | +| learning_rate | 4.95e-05 | +| loss | -0.029 | +| n_updates | 39260 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000383 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.0293 | +| time/ | | +| fps | 1303 | +| iterations | 980 | +| time_elapsed | 1539 | +| total_timesteps | 2007040 | +| train/ | | +| approx_kl | 0.027230447 | +| clip_fraction | 0.466 | +| clip_range | 0.0745 | +| entropy_loss | -3.73 | +| explained_variance | 0.163 | +| learning_rate | 4.95e-05 | +| loss | -0.0336 | +| n_updates | 39264 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000219 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.0442 | +| time/ | | +| fps | 1303 | +| iterations | 981 | +| time_elapsed | 1540 | +| total_timesteps | 2009088 | +| train/ | | +| approx_kl | 0.032670178 | +| clip_fraction | 0.463 | +| clip_range | 0.0745 | +| entropy_loss | -3.64 | +| explained_variance | 0.439 | +| learning_rate | 4.95e-05 | +| loss | -0.0284 | +| n_updates | 39268 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000221 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.0445 | +| time/ | | +| fps | 1303 | +| iterations | 982 | +| time_elapsed | 1542 | +| total_timesteps | 2011136 | +| train/ | | +| approx_kl | 0.035443246 | +| clip_fraction | 0.452 | +| clip_range | 0.0745 | +| entropy_loss | -3.21 | +| explained_variance | 0.273 | +| learning_rate | 4.95e-05 | +| loss | -0.0286 | +| n_updates | 39272 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.000345 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.0389 | +| time/ | | +| fps | 1303 | +| iterations | 983 | +| time_elapsed | 1543 | +| total_timesteps | 2013184 | +| train/ | | +| approx_kl | 0.036243767 | +| clip_fraction | 0.497 | +| clip_range | 0.0745 | +| entropy_loss | -3.66 | +| explained_variance | 0.118 | +| learning_rate | 4.95e-05 | +| loss | -0.0397 | +| n_updates | 39276 | +| policy_gradient_loss | -0.0223 | +| value_loss | 0.000216 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.0389 | +| time/ | | +| fps | 1303 | +| iterations | 984 | +| time_elapsed | 1545 | +| total_timesteps | 2015232 | +| train/ | | +| approx_kl | 0.029788682 | +| clip_fraction | 0.464 | +| clip_range | 0.0745 | +| entropy_loss | -3.85 | +| explained_variance | 0.161 | +| learning_rate | 4.95e-05 | +| loss | -0.0335 | +| n_updates | 39280 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000188 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.0431 | +| time/ | | +| fps | 1303 | +| iterations | 985 | +| time_elapsed | 1547 | +| total_timesteps | 2017280 | +| train/ | | +| approx_kl | 0.034914225 | +| clip_fraction | 0.479 | +| clip_range | 0.0745 | +| entropy_loss | -3.94 | +| explained_variance | -0.133 | +| learning_rate | 4.95e-05 | +| loss | -0.0395 | +| n_updates | 39284 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000191 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.0415 | +| time/ | | +| fps | 1303 | +| iterations | 986 | +| time_elapsed | 1548 | +| total_timesteps | 2019328 | +| train/ | | +| approx_kl | 0.029228443 | +| clip_fraction | 0.45 | +| clip_range | 0.0745 | +| entropy_loss | -3.62 | +| explained_variance | 0.207 | +| learning_rate | 4.95e-05 | +| loss | -0.032 | +| n_updates | 39288 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000355 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.0615 | +| time/ | | +| fps | 1303 | +| iterations | 987 | +| time_elapsed | 1550 | +| total_timesteps | 2021376 | +| train/ | | +| approx_kl | 0.032960497 | +| clip_fraction | 0.489 | +| clip_range | 0.0745 | +| entropy_loss | -3.88 | +| explained_variance | 0.13 | +| learning_rate | 4.95e-05 | +| loss | -0.0327 | +| n_updates | 39292 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.000184 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.0619 | +| time/ | | +| fps | 1303 | +| iterations | 988 | +| time_elapsed | 1551 | +| total_timesteps | 2023424 | +| train/ | | +| approx_kl | 0.030790454 | +| clip_fraction | 0.443 | +| clip_range | 0.0745 | +| entropy_loss | -3.76 | +| explained_variance | 0.263 | +| learning_rate | 4.95e-05 | +| loss | -0.0268 | +| n_updates | 39296 | +| policy_gradient_loss | -0.0153 | +| value_loss | 0.000295 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.0679 | +| time/ | | +| fps | 1303 | +| iterations | 989 | +| time_elapsed | 1553 | +| total_timesteps | 2025472 | +| train/ | | +| approx_kl | 0.033478387 | +| clip_fraction | 0.488 | +| clip_range | 0.0745 | +| entropy_loss | -3.55 | +| explained_variance | 0.0217 | +| learning_rate | 4.95e-05 | +| loss | -0.0345 | +| n_updates | 39300 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.00036 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.23e+03 | +| ep_rew_mean | 0.0847 | +| time/ | | +| fps | 1303 | +| iterations | 990 | +| time_elapsed | 1555 | +| total_timesteps | 2027520 | +| train/ | | +| approx_kl | 0.02625879 | +| clip_fraction | 0.459 | +| clip_range | 0.0745 | +| entropy_loss | -3.79 | +| explained_variance | 0.0932 | +| learning_rate | 4.95e-05 | +| loss | -0.0283 | +| n_updates | 39304 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000347 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.0895 | +| time/ | | +| fps | 1303 | +| iterations | 991 | +| time_elapsed | 1556 | +| total_timesteps | 2029568 | +| train/ | | +| approx_kl | 0.026138388 | +| clip_fraction | 0.447 | +| clip_range | 0.0745 | +| entropy_loss | -3.83 | +| explained_variance | 0.238 | +| learning_rate | 4.95e-05 | +| loss | -0.0305 | +| n_updates | 39308 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000342 | +----------------------------------------- +-------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.0984 | +| time/ | | +| fps | 1303 | +| iterations | 992 | +| time_elapsed | 1558 | +| total_timesteps | 2031616 | +| train/ | | +| approx_kl | 0.03567 | +| clip_fraction | 0.482 | +| clip_range | 0.0745 | +| entropy_loss | -3.79 | +| explained_variance | 0.0132 | +| learning_rate | 4.95e-05 | +| loss | -0.0301 | +| n_updates | 39312 | +| policy_gradient_loss | -0.0212 | +| value_loss | 0.000191 | +-------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.101 | +| time/ | | +| fps | 1303 | +| iterations | 993 | +| time_elapsed | 1559 | +| total_timesteps | 2033664 | +| train/ | | +| approx_kl | 0.03083434 | +| clip_fraction | 0.441 | +| clip_range | 0.0745 | +| entropy_loss | -3.53 | +| explained_variance | 0.452 | +| learning_rate | 4.95e-05 | +| loss | -0.0293 | +| n_updates | 39316 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.00024 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.101 | +| time/ | | +| fps | 1303 | +| iterations | 994 | +| time_elapsed | 1561 | +| total_timesteps | 2035712 | +| train/ | | +| approx_kl | 0.03605404 | +| clip_fraction | 0.467 | +| clip_range | 0.0745 | +| entropy_loss | -3.69 | +| explained_variance | 0.164 | +| learning_rate | 4.95e-05 | +| loss | -0.0348 | +| n_updates | 39320 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000232 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.0984 | +| time/ | | +| fps | 1303 | +| iterations | 995 | +| time_elapsed | 1563 | +| total_timesteps | 2037760 | +| train/ | | +| approx_kl | 0.028758459 | +| clip_fraction | 0.46 | +| clip_range | 0.0745 | +| entropy_loss | -3.62 | +| explained_variance | 0.121 | +| learning_rate | 4.95e-05 | +| loss | -0.0335 | +| n_updates | 39324 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000347 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.098 | +| time/ | | +| fps | 1303 | +| iterations | 996 | +| time_elapsed | 1564 | +| total_timesteps | 2039808 | +| train/ | | +| approx_kl | 0.029813431 | +| clip_fraction | 0.457 | +| clip_range | 0.0745 | +| entropy_loss | -3.74 | +| explained_variance | 0.305 | +| learning_rate | 4.95e-05 | +| loss | -0.0263 | +| n_updates | 39328 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000222 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.0948 | +| time/ | | +| fps | 1303 | +| iterations | 997 | +| time_elapsed | 1566 | +| total_timesteps | 2041856 | +| train/ | | +| approx_kl | 0.027941361 | +| clip_fraction | 0.45 | +| clip_range | 0.0745 | +| entropy_loss | -3.73 | +| explained_variance | 0.1 | +| learning_rate | 4.95e-05 | +| loss | -0.0276 | +| n_updates | 39332 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000394 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.0948 | +| time/ | | +| fps | 1303 | +| iterations | 998 | +| time_elapsed | 1568 | +| total_timesteps | 2043904 | +| train/ | | +| approx_kl | 0.038651675 | +| clip_fraction | 0.421 | +| clip_range | 0.0745 | +| entropy_loss | -3.48 | +| explained_variance | 0.373 | +| learning_rate | 4.95e-05 | +| loss | -0.0318 | +| n_updates | 39336 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.00031 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.0841 | +| time/ | | +| fps | 1303 | +| iterations | 999 | +| time_elapsed | 1569 | +| total_timesteps | 2045952 | +| train/ | | +| approx_kl | 0.027812036 | +| clip_fraction | 0.457 | +| clip_range | 0.0745 | +| entropy_loss | -3.53 | +| explained_variance | -0.239 | +| learning_rate | 4.95e-05 | +| loss | -0.0318 | +| n_updates | 39340 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000319 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.0844 | +| time/ | | +| fps | 1303 | +| iterations | 1000 | +| time_elapsed | 1571 | +| total_timesteps | 2048000 | +| train/ | | +| approx_kl | 0.029474009 | +| clip_fraction | 0.446 | +| clip_range | 0.0745 | +| entropy_loss | -3.54 | +| explained_variance | 0.442 | +| learning_rate | 4.95e-05 | +| loss | -0.031 | +| n_updates | 39344 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000236 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.0777 | +| time/ | | +| fps | 1303 | +| iterations | 1001 | +| time_elapsed | 1573 | +| total_timesteps | 2050048 | +| train/ | | +| approx_kl | 0.033031777 | +| clip_fraction | 0.459 | +| clip_range | 0.0745 | +| entropy_loss | -3.41 | +| explained_variance | 0.175 | +| learning_rate | 4.95e-05 | +| loss | -0.0349 | +| n_updates | 39348 | +| policy_gradient_loss | -0.021 | +| value_loss | 0.000164 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.0796 | +| time/ | | +| fps | 1303 | +| iterations | 1002 | +| time_elapsed | 1574 | +| total_timesteps | 2052096 | +| train/ | | +| approx_kl | 0.034659028 | +| clip_fraction | 0.477 | +| clip_range | 0.0745 | +| entropy_loss | -3.18 | +| explained_variance | 0.423 | +| learning_rate | 4.95e-05 | +| loss | -0.0317 | +| n_updates | 39352 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000178 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.0713 | +| time/ | | +| fps | 1303 | +| iterations | 1003 | +| time_elapsed | 1576 | +| total_timesteps | 2054144 | +| train/ | | +| approx_kl | 0.035673533 | +| clip_fraction | 0.452 | +| clip_range | 0.0745 | +| entropy_loss | -3.31 | +| explained_variance | 0.223 | +| learning_rate | 4.95e-05 | +| loss | -0.0359 | +| n_updates | 39356 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000211 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.0713 | +| time/ | | +| fps | 1303 | +| iterations | 1004 | +| time_elapsed | 1577 | +| total_timesteps | 2056192 | +| train/ | | +| approx_kl | 0.036117353 | +| clip_fraction | 0.451 | +| clip_range | 0.0745 | +| entropy_loss | -3.39 | +| explained_variance | 0.335 | +| learning_rate | 4.95e-05 | +| loss | -0.0235 | +| n_updates | 39360 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000251 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.0755 | +| time/ | | +| fps | 1303 | +| iterations | 1005 | +| time_elapsed | 1579 | +| total_timesteps | 2058240 | +| train/ | | +| approx_kl | 0.033050515 | +| clip_fraction | 0.45 | +| clip_range | 0.0745 | +| entropy_loss | -3.83 | +| explained_variance | 0.0714 | +| learning_rate | 4.95e-05 | +| loss | -0.0276 | +| n_updates | 39364 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000369 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.0755 | +| time/ | | +| fps | 1303 | +| iterations | 1006 | +| time_elapsed | 1580 | +| total_timesteps | 2060288 | +| train/ | | +| approx_kl | 0.029572826 | +| clip_fraction | 0.472 | +| clip_range | 0.0745 | +| entropy_loss | -3.76 | +| explained_variance | 0.106 | +| learning_rate | 4.95e-05 | +| loss | -0.0359 | +| n_updates | 39368 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000285 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.0866 | +| time/ | | +| fps | 1303 | +| iterations | 1007 | +| time_elapsed | 1582 | +| total_timesteps | 2062336 | +| train/ | | +| approx_kl | 0.031383894 | +| clip_fraction | 0.464 | +| clip_range | 0.0745 | +| entropy_loss | -3.75 | +| explained_variance | -0.0941 | +| learning_rate | 4.95e-05 | +| loss | -0.0302 | +| n_updates | 39372 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000265 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.24e+03 | +| ep_rew_mean | 0.0818 | +| time/ | | +| fps | 1303 | +| iterations | 1008 | +| time_elapsed | 1584 | +| total_timesteps | 2064384 | +| train/ | | +| approx_kl | 0.027356975 | +| clip_fraction | 0.454 | +| clip_range | 0.0745 | +| entropy_loss | -3.53 | +| explained_variance | 0.0864 | +| learning_rate | 4.95e-05 | +| loss | -0.0203 | +| n_updates | 39376 | +| policy_gradient_loss | -0.0112 | +| value_loss | 0.000791 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.25e+03 | +| ep_rew_mean | 0.0848 | +| time/ | | +| fps | 1303 | +| iterations | 1009 | +| time_elapsed | 1585 | +| total_timesteps | 2066432 | +| train/ | | +| approx_kl | 0.029774778 | +| clip_fraction | 0.456 | +| clip_range | 0.0745 | +| entropy_loss | -3.53 | +| explained_variance | 0.0115 | +| learning_rate | 4.95e-05 | +| loss | -0.0323 | +| n_updates | 39380 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000408 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.0707 | +| time/ | | +| fps | 1303 | +| iterations | 1010 | +| time_elapsed | 1587 | +| total_timesteps | 2068480 | +| train/ | | +| approx_kl | 0.034805767 | +| clip_fraction | 0.487 | +| clip_range | 0.0745 | +| entropy_loss | -3.45 | +| explained_variance | -0.0811 | +| learning_rate | 4.95e-05 | +| loss | -0.0386 | +| n_updates | 39384 | +| policy_gradient_loss | -0.0242 | +| value_loss | 0.000224 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.0755 | +| time/ | | +| fps | 1303 | +| iterations | 1011 | +| time_elapsed | 1588 | +| total_timesteps | 2070528 | +| train/ | | +| approx_kl | 0.039520927 | +| clip_fraction | 0.465 | +| clip_range | 0.0745 | +| entropy_loss | -3.28 | +| explained_variance | 0.399 | +| learning_rate | 4.95e-05 | +| loss | -0.0321 | +| n_updates | 39388 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000199 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.0705 | +| time/ | | +| fps | 1303 | +| iterations | 1012 | +| time_elapsed | 1590 | +| total_timesteps | 2072576 | +| train/ | | +| approx_kl | 0.034377567 | +| clip_fraction | 0.459 | +| clip_range | 0.0745 | +| entropy_loss | -3.47 | +| explained_variance | 0.0695 | +| learning_rate | 4.95e-05 | +| loss | -0.0363 | +| n_updates | 39392 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000301 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.076 | +| time/ | | +| fps | 1303 | +| iterations | 1013 | +| time_elapsed | 1591 | +| total_timesteps | 2074624 | +| train/ | | +| approx_kl | 0.03571752 | +| clip_fraction | 0.46 | +| clip_range | 0.0745 | +| entropy_loss | -3.29 | +| explained_variance | 0.289 | +| learning_rate | 4.95e-05 | +| loss | -0.0308 | +| n_updates | 39396 | +| policy_gradient_loss | -0.0205 | +| value_loss | 0.00024 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.0765 | +| time/ | | +| fps | 1303 | +| iterations | 1014 | +| time_elapsed | 1593 | +| total_timesteps | 2076672 | +| train/ | | +| approx_kl | 0.03291804 | +| clip_fraction | 0.463 | +| clip_range | 0.0745 | +| entropy_loss | -3.24 | +| explained_variance | 0.315 | +| learning_rate | 4.95e-05 | +| loss | -0.0294 | +| n_updates | 39400 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000295 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.0765 | +| time/ | | +| fps | 1303 | +| iterations | 1015 | +| time_elapsed | 1594 | +| total_timesteps | 2078720 | +| train/ | | +| approx_kl | 0.03274101 | +| clip_fraction | 0.473 | +| clip_range | 0.0745 | +| entropy_loss | -3.44 | +| explained_variance | 0.125 | +| learning_rate | 4.95e-05 | +| loss | -0.0348 | +| n_updates | 39404 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000254 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.0773 | +| time/ | | +| fps | 1303 | +| iterations | 1016 | +| time_elapsed | 1596 | +| total_timesteps | 2080768 | +| train/ | | +| approx_kl | 0.03492465 | +| clip_fraction | 0.46 | +| clip_range | 0.0745 | +| entropy_loss | -3.65 | +| explained_variance | -0.0255 | +| learning_rate | 4.95e-05 | +| loss | -0.0307 | +| n_updates | 39408 | +| policy_gradient_loss | -0.0204 | +| value_loss | 0.000248 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.0751 | +| time/ | | +| fps | 1303 | +| iterations | 1017 | +| time_elapsed | 1597 | +| total_timesteps | 2082816 | +| train/ | | +| approx_kl | 0.030401058 | +| clip_fraction | 0.476 | +| clip_range | 0.0745 | +| entropy_loss | -3.54 | +| explained_variance | 0.212 | +| learning_rate | 4.95e-05 | +| loss | -0.0346 | +| n_updates | 39412 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000239 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.0751 | +| time/ | | +| fps | 1303 | +| iterations | 1018 | +| time_elapsed | 1599 | +| total_timesteps | 2084864 | +| train/ | | +| approx_kl | 0.033970527 | +| clip_fraction | 0.434 | +| clip_range | 0.0745 | +| entropy_loss | -3.38 | +| explained_variance | 0.356 | +| learning_rate | 4.95e-05 | +| loss | -0.0336 | +| n_updates | 39416 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.00024 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.0742 | +| time/ | | +| fps | 1303 | +| iterations | 1019 | +| time_elapsed | 1601 | +| total_timesteps | 2086912 | +| train/ | | +| approx_kl | 0.036713578 | +| clip_fraction | 0.47 | +| clip_range | 0.0745 | +| entropy_loss | -3.55 | +| explained_variance | -0.19 | +| learning_rate | 4.95e-05 | +| loss | -0.0349 | +| n_updates | 39420 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000317 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.0713 | +| time/ | | +| fps | 1303 | +| iterations | 1020 | +| time_elapsed | 1602 | +| total_timesteps | 2088960 | +| train/ | | +| approx_kl | 0.032722186 | +| clip_fraction | 0.481 | +| clip_range | 0.0745 | +| entropy_loss | -3.61 | +| explained_variance | 0.206 | +| learning_rate | 4.95e-05 | +| loss | -0.0294 | +| n_updates | 39424 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.00028 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.0604 | +| time/ | | +| fps | 1303 | +| iterations | 1021 | +| time_elapsed | 1604 | +| total_timesteps | 2091008 | +| train/ | | +| approx_kl | 0.031407364 | +| clip_fraction | 0.481 | +| clip_range | 0.0745 | +| entropy_loss | -3.41 | +| explained_variance | 0.295 | +| learning_rate | 4.95e-05 | +| loss | -0.032 | +| n_updates | 39428 | +| policy_gradient_loss | -0.0219 | +| value_loss | 0.000189 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.0548 | +| time/ | | +| fps | 1303 | +| iterations | 1022 | +| time_elapsed | 1605 | +| total_timesteps | 2093056 | +| train/ | | +| approx_kl | 0.03247059 | +| clip_fraction | 0.438 | +| clip_range | 0.0745 | +| entropy_loss | -3.41 | +| explained_variance | 0.385 | +| learning_rate | 4.95e-05 | +| loss | -0.0327 | +| n_updates | 39432 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000254 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.053 | +| time/ | | +| fps | 1303 | +| iterations | 1023 | +| time_elapsed | 1607 | +| total_timesteps | 2095104 | +| train/ | | +| approx_kl | 0.03739809 | +| clip_fraction | 0.452 | +| clip_range | 0.0745 | +| entropy_loss | -3.34 | +| explained_variance | 0.0471 | +| learning_rate | 4.95e-05 | +| loss | -0.0291 | +| n_updates | 39436 | +| policy_gradient_loss | -0.0182 | +| value_loss | 0.000286 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.0525 | +| time/ | | +| fps | 1303 | +| iterations | 1024 | +| time_elapsed | 1609 | +| total_timesteps | 2097152 | +| train/ | | +| approx_kl | 0.03587923 | +| clip_fraction | 0.462 | +| clip_range | 0.0745 | +| entropy_loss | -3.71 | +| explained_variance | 0.0298 | +| learning_rate | 4.95e-05 | +| loss | -0.0312 | +| n_updates | 39440 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000343 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.0585 | +| time/ | | +| fps | 1303 | +| iterations | 1025 | +| time_elapsed | 1610 | +| total_timesteps | 2099200 | +| train/ | | +| approx_kl | 0.033240594 | +| clip_fraction | 0.447 | +| clip_range | 0.0745 | +| entropy_loss | -3.71 | +| explained_variance | 0.239 | +| learning_rate | 4.95e-05 | +| loss | -0.0311 | +| n_updates | 39444 | +| policy_gradient_loss | -0.022 | +| value_loss | 0.000417 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.0602 | +| time/ | | +| fps | 1303 | +| iterations | 1026 | +| time_elapsed | 1612 | +| total_timesteps | 2101248 | +| train/ | | +| approx_kl | 0.031357113 | +| clip_fraction | 0.476 | +| clip_range | 0.0745 | +| entropy_loss | -3.93 | +| explained_variance | 0.187 | +| learning_rate | 4.95e-05 | +| loss | -0.0345 | +| n_updates | 39448 | +| policy_gradient_loss | -0.0209 | +| value_loss | 0.000194 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.0545 | +| time/ | | +| fps | 1303 | +| iterations | 1027 | +| time_elapsed | 1613 | +| total_timesteps | 2103296 | +| train/ | | +| approx_kl | 0.029777963 | +| clip_fraction | 0.48 | +| clip_range | 0.0745 | +| entropy_loss | -3.63 | +| explained_variance | 0.0784 | +| learning_rate | 4.95e-05 | +| loss | -0.0308 | +| n_updates | 39452 | +| policy_gradient_loss | -0.019 | +| value_loss | 0.000275 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.0476 | +| time/ | | +| fps | 1303 | +| iterations | 1028 | +| time_elapsed | 1615 | +| total_timesteps | 2105344 | +| train/ | | +| approx_kl | 0.028895997 | +| clip_fraction | 0.44 | +| clip_range | 0.0745 | +| entropy_loss | -3.53 | +| explained_variance | 0.162 | +| learning_rate | 4.95e-05 | +| loss | -0.0337 | +| n_updates | 39456 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.00023 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.0622 | +| time/ | | +| fps | 1303 | +| iterations | 1029 | +| time_elapsed | 1616 | +| total_timesteps | 2107392 | +| train/ | | +| approx_kl | 0.023634529 | +| clip_fraction | 0.446 | +| clip_range | 0.0745 | +| entropy_loss | -3.39 | +| explained_variance | 0.454 | +| learning_rate | 4.95e-05 | +| loss | -0.0255 | +| n_updates | 39460 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000248 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.0656 | +| time/ | | +| fps | 1303 | +| iterations | 1030 | +| time_elapsed | 1618 | +| total_timesteps | 2109440 | +| train/ | | +| approx_kl | 0.026517019 | +| clip_fraction | 0.419 | +| clip_range | 0.0745 | +| entropy_loss | -3.43 | +| explained_variance | 0.11 | +| learning_rate | 4.95e-05 | +| loss | -0.0143 | +| n_updates | 39464 | +| policy_gradient_loss | -0.0123 | +| value_loss | 0.000716 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.0655 | +| time/ | | +| fps | 1303 | +| iterations | 1031 | +| time_elapsed | 1620 | +| total_timesteps | 2111488 | +| train/ | | +| approx_kl | 0.02897077 | +| clip_fraction | 0.457 | +| clip_range | 0.0745 | +| entropy_loss | -3.33 | +| explained_variance | -0.0933 | +| learning_rate | 4.95e-05 | +| loss | -0.0349 | +| n_updates | 39468 | +| policy_gradient_loss | -0.0207 | +| value_loss | 0.000505 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.0704 | +| time/ | | +| fps | 1303 | +| iterations | 1032 | +| time_elapsed | 1621 | +| total_timesteps | 2113536 | +| train/ | | +| approx_kl | 0.03447588 | +| clip_fraction | 0.472 | +| clip_range | 0.0745 | +| entropy_loss | -3.14 | +| explained_variance | 0.263 | +| learning_rate | 4.95e-05 | +| loss | -0.0343 | +| n_updates | 39472 | +| policy_gradient_loss | -0.0228 | +| value_loss | 0.000252 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.0668 | +| time/ | | +| fps | 1303 | +| iterations | 1033 | +| time_elapsed | 1623 | +| total_timesteps | 2115584 | +| train/ | | +| approx_kl | 0.031922266 | +| clip_fraction | 0.438 | +| clip_range | 0.0745 | +| entropy_loss | -3.26 | +| explained_variance | 0.298 | +| learning_rate | 4.95e-05 | +| loss | -0.0361 | +| n_updates | 39476 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000249 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.0642 | +| time/ | | +| fps | 1303 | +| iterations | 1034 | +| time_elapsed | 1624 | +| total_timesteps | 2117632 | +| train/ | | +| approx_kl | 0.03499444 | +| clip_fraction | 0.474 | +| clip_range | 0.0745 | +| entropy_loss | -3.31 | +| explained_variance | 0.208 | +| learning_rate | 4.95e-05 | +| loss | -0.0367 | +| n_updates | 39480 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000289 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.0698 | +| time/ | | +| fps | 1303 | +| iterations | 1035 | +| time_elapsed | 1626 | +| total_timesteps | 2119680 | +| train/ | | +| approx_kl | 0.027048003 | +| clip_fraction | 0.454 | +| clip_range | 0.0745 | +| entropy_loss | -3.51 | +| explained_variance | 0.0881 | +| learning_rate | 4.95e-05 | +| loss | -0.0353 | +| n_updates | 39484 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000279 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.0693 | +| time/ | | +| fps | 1303 | +| iterations | 1036 | +| time_elapsed | 1627 | +| total_timesteps | 2121728 | +| train/ | | +| approx_kl | 0.02929601 | +| clip_fraction | 0.454 | +| clip_range | 0.0745 | +| entropy_loss | -3.59 | +| explained_variance | 0.179 | +| learning_rate | 4.95e-05 | +| loss | -0.0316 | +| n_updates | 39488 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000219 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.0624 | +| time/ | | +| fps | 1303 | +| iterations | 1037 | +| time_elapsed | 1629 | +| total_timesteps | 2123776 | +| train/ | | +| approx_kl | 0.026722059 | +| clip_fraction | 0.454 | +| clip_range | 0.0745 | +| entropy_loss | -3.59 | +| explained_variance | 0.202 | +| learning_rate | 4.95e-05 | +| loss | -0.0358 | +| n_updates | 39492 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000291 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.0651 | +| time/ | | +| fps | 1303 | +| iterations | 1038 | +| time_elapsed | 1630 | +| total_timesteps | 2125824 | +| train/ | | +| approx_kl | 0.026088499 | +| clip_fraction | 0.432 | +| clip_range | 0.0745 | +| entropy_loss | -3.41 | +| explained_variance | 0.475 | +| learning_rate | 4.95e-05 | +| loss | -0.0296 | +| n_updates | 39496 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000271 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.0651 | +| time/ | | +| fps | 1303 | +| iterations | 1039 | +| time_elapsed | 1632 | +| total_timesteps | 2127872 | +| train/ | | +| approx_kl | 0.028316671 | +| clip_fraction | 0.432 | +| clip_range | 0.0745 | +| entropy_loss | -3.22 | +| explained_variance | 0.26 | +| learning_rate | 4.95e-05 | +| loss | -0.0344 | +| n_updates | 39500 | +| policy_gradient_loss | -0.0187 | +| value_loss | 0.000337 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.0651 | +| time/ | | +| fps | 1303 | +| iterations | 1040 | +| time_elapsed | 1634 | +| total_timesteps | 2129920 | +| train/ | | +| approx_kl | 0.037733797 | +| clip_fraction | 0.466 | +| clip_range | 0.0745 | +| entropy_loss | -3.38 | +| explained_variance | 0.0813 | +| learning_rate | 4.95e-05 | +| loss | -0.0334 | +| n_updates | 39504 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000285 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.0749 | +| time/ | | +| fps | 1303 | +| iterations | 1041 | +| time_elapsed | 1635 | +| total_timesteps | 2131968 | +| train/ | | +| approx_kl | 0.034959953 | +| clip_fraction | 0.486 | +| clip_range | 0.0745 | +| entropy_loss | -3.63 | +| explained_variance | -0.334 | +| learning_rate | 4.95e-05 | +| loss | -0.0338 | +| n_updates | 39508 | +| policy_gradient_loss | -0.0208 | +| value_loss | 0.00025 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.0708 | +| time/ | | +| fps | 1303 | +| iterations | 1042 | +| time_elapsed | 1637 | +| total_timesteps | 2134016 | +| train/ | | +| approx_kl | 0.03808525 | +| clip_fraction | 0.474 | +| clip_range | 0.0745 | +| entropy_loss | -3.46 | +| explained_variance | 0.185 | +| learning_rate | 4.95e-05 | +| loss | -0.0294 | +| n_updates | 39512 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000204 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.0765 | +| time/ | | +| fps | 1303 | +| iterations | 1043 | +| time_elapsed | 1638 | +| total_timesteps | 2136064 | +| train/ | | +| approx_kl | 0.033717133 | +| clip_fraction | 0.467 | +| clip_range | 0.0745 | +| entropy_loss | -3.36 | +| explained_variance | 0.301 | +| learning_rate | 4.95e-05 | +| loss | -0.0309 | +| n_updates | 39516 | +| policy_gradient_loss | -0.0193 | +| value_loss | 0.000282 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.0683 | +| time/ | | +| fps | 1303 | +| iterations | 1044 | +| time_elapsed | 1640 | +| total_timesteps | 2138112 | +| train/ | | +| approx_kl | 0.033256203 | +| clip_fraction | 0.436 | +| clip_range | 0.0745 | +| entropy_loss | -3.25 | +| explained_variance | 0.39 | +| learning_rate | 4.95e-05 | +| loss | -0.0284 | +| n_updates | 39520 | +| policy_gradient_loss | -0.0165 | +| value_loss | 0.000295 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.0672 | +| time/ | | +| fps | 1303 | +| iterations | 1045 | +| time_elapsed | 1641 | +| total_timesteps | 2140160 | +| train/ | | +| approx_kl | 0.02937683 | +| clip_fraction | 0.431 | +| clip_range | 0.0745 | +| entropy_loss | -3.03 | +| explained_variance | 0.419 | +| learning_rate | 4.95e-05 | +| loss | -0.0254 | +| n_updates | 39524 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000254 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.0684 | +| time/ | | +| fps | 1303 | +| iterations | 1046 | +| time_elapsed | 1643 | +| total_timesteps | 2142208 | +| train/ | | +| approx_kl | 0.032663375 | +| clip_fraction | 0.478 | +| clip_range | 0.0745 | +| entropy_loss | -3.29 | +| explained_variance | 0.478 | +| learning_rate | 4.95e-05 | +| loss | -0.0292 | +| n_updates | 39528 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.00016 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.0725 | +| time/ | | +| fps | 1303 | +| iterations | 1047 | +| time_elapsed | 1644 | +| total_timesteps | 2144256 | +| train/ | | +| approx_kl | 0.032597326 | +| clip_fraction | 0.438 | +| clip_range | 0.0745 | +| entropy_loss | -3.23 | +| explained_variance | 0.233 | +| learning_rate | 4.95e-05 | +| loss | -0.0292 | +| n_updates | 39532 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000324 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.0725 | +| time/ | | +| fps | 1303 | +| iterations | 1048 | +| time_elapsed | 1646 | +| total_timesteps | 2146304 | +| train/ | | +| approx_kl | 0.036690835 | +| clip_fraction | 0.486 | +| clip_range | 0.0745 | +| entropy_loss | -3.53 | +| explained_variance | -0.111 | +| learning_rate | 4.95e-05 | +| loss | -0.0352 | +| n_updates | 39536 | +| policy_gradient_loss | -0.0203 | +| value_loss | 0.000213 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.0688 | +| time/ | | +| fps | 1303 | +| iterations | 1049 | +| time_elapsed | 1648 | +| total_timesteps | 2148352 | +| train/ | | +| approx_kl | 0.037730403 | +| clip_fraction | 0.5 | +| clip_range | 0.0745 | +| entropy_loss | -3.6 | +| explained_variance | -0.0552 | +| learning_rate | 4.95e-05 | +| loss | -0.0364 | +| n_updates | 39540 | +| policy_gradient_loss | -0.0216 | +| value_loss | 0.000393 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.0634 | +| time/ | | +| fps | 1303 | +| iterations | 1050 | +| time_elapsed | 1649 | +| total_timesteps | 2150400 | +| train/ | | +| approx_kl | 0.031413514 | +| clip_fraction | 0.501 | +| clip_range | 0.0745 | +| entropy_loss | -3.6 | +| explained_variance | 0.000985 | +| learning_rate | 4.95e-05 | +| loss | -0.0336 | +| n_updates | 39544 | +| policy_gradient_loss | -0.0223 | +| value_loss | 0.000218 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.0603 | +| time/ | | +| fps | 1303 | +| iterations | 1051 | +| time_elapsed | 1651 | +| total_timesteps | 2152448 | +| train/ | | +| approx_kl | 0.029169561 | +| clip_fraction | 0.429 | +| clip_range | 0.0745 | +| entropy_loss | -3.36 | +| explained_variance | 0.299 | +| learning_rate | 4.95e-05 | +| loss | -0.0287 | +| n_updates | 39548 | +| policy_gradient_loss | -0.0171 | +| value_loss | 0.000411 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.0512 | +| time/ | | +| fps | 1303 | +| iterations | 1052 | +| time_elapsed | 1652 | +| total_timesteps | 2154496 | +| train/ | | +| approx_kl | 0.033297718 | +| clip_fraction | 0.453 | +| clip_range | 0.0745 | +| entropy_loss | -3.37 | +| explained_variance | -0.118 | +| learning_rate | 4.95e-05 | +| loss | -0.0318 | +| n_updates | 39552 | +| policy_gradient_loss | -0.0202 | +| value_loss | 0.000281 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.0514 | +| time/ | | +| fps | 1303 | +| iterations | 1053 | +| time_elapsed | 1654 | +| total_timesteps | 2156544 | +| train/ | | +| approx_kl | 0.030998416 | +| clip_fraction | 0.455 | +| clip_range | 0.0745 | +| entropy_loss | -3.1 | +| explained_variance | 0.58 | +| learning_rate | 4.95e-05 | +| loss | -0.0311 | +| n_updates | 39556 | +| policy_gradient_loss | -0.0175 | +| value_loss | 0.000177 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.0578 | +| time/ | | +| fps | 1303 | +| iterations | 1054 | +| time_elapsed | 1655 | +| total_timesteps | 2158592 | +| train/ | | +| approx_kl | 0.027933901 | +| clip_fraction | 0.464 | +| clip_range | 0.0745 | +| entropy_loss | -3.69 | +| explained_variance | -0.109 | +| learning_rate | 4.95e-05 | +| loss | -0.0311 | +| n_updates | 39560 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000267 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.0578 | +| time/ | | +| fps | 1303 | +| iterations | 1055 | +| time_elapsed | 1657 | +| total_timesteps | 2160640 | +| train/ | | +| approx_kl | 0.03445727 | +| clip_fraction | 0.446 | +| clip_range | 0.0745 | +| entropy_loss | -3.36 | +| explained_variance | 0.145 | +| learning_rate | 4.95e-05 | +| loss | -0.0322 | +| n_updates | 39564 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000309 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.0567 | +| time/ | | +| fps | 1303 | +| iterations | 1056 | +| time_elapsed | 1658 | +| total_timesteps | 2162688 | +| train/ | | +| approx_kl | 0.03192281 | +| clip_fraction | 0.486 | +| clip_range | 0.0745 | +| entropy_loss | -3.72 | +| explained_variance | -0.189 | +| learning_rate | 4.95e-05 | +| loss | -0.0353 | +| n_updates | 39568 | +| policy_gradient_loss | -0.0179 | +| value_loss | 0.000247 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.0557 | +| time/ | | +| fps | 1303 | +| iterations | 1057 | +| time_elapsed | 1660 | +| total_timesteps | 2164736 | +| train/ | | +| approx_kl | 0.032757435 | +| clip_fraction | 0.459 | +| clip_range | 0.0745 | +| entropy_loss | -3.81 | +| explained_variance | 0.126 | +| learning_rate | 4.95e-05 | +| loss | -0.0329 | +| n_updates | 39572 | +| policy_gradient_loss | -0.0195 | +| value_loss | 0.000282 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.0583 | +| time/ | | +| fps | 1303 | +| iterations | 1058 | +| time_elapsed | 1661 | +| total_timesteps | 2166784 | +| train/ | | +| approx_kl | 0.03183863 | +| clip_fraction | 0.464 | +| clip_range | 0.0745 | +| entropy_loss | -3.37 | +| explained_variance | 0.324 | +| learning_rate | 4.95e-05 | +| loss | -0.0253 | +| n_updates | 39576 | +| policy_gradient_loss | -0.016 | +| value_loss | 0.000284 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.0579 | +| time/ | | +| fps | 1303 | +| iterations | 1059 | +| time_elapsed | 1663 | +| total_timesteps | 2168832 | +| train/ | | +| approx_kl | 0.035393804 | +| clip_fraction | 0.485 | +| clip_range | 0.0745 | +| entropy_loss | -3.38 | +| explained_variance | 0.368 | +| learning_rate | 4.95e-05 | +| loss | -0.0279 | +| n_updates | 39580 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000228 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.0579 | +| time/ | | +| fps | 1303 | +| iterations | 1060 | +| time_elapsed | 1664 | +| total_timesteps | 2170880 | +| train/ | | +| approx_kl | 0.02967305 | +| clip_fraction | 0.478 | +| clip_range | 0.0745 | +| entropy_loss | -3.54 | +| explained_variance | -0.101 | +| learning_rate | 4.95e-05 | +| loss | -0.0367 | +| n_updates | 39584 | +| policy_gradient_loss | -0.0185 | +| value_loss | 0.000192 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.0568 | +| time/ | | +| fps | 1303 | +| iterations | 1061 | +| time_elapsed | 1666 | +| total_timesteps | 2172928 | +| train/ | | +| approx_kl | 0.033358827 | +| clip_fraction | 0.48 | +| clip_range | 0.0745 | +| entropy_loss | -3.43 | +| explained_variance | 0.0271 | +| learning_rate | 4.95e-05 | +| loss | -0.0293 | +| n_updates | 39588 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000237 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.0566 | +| time/ | | +| fps | 1303 | +| iterations | 1062 | +| time_elapsed | 1668 | +| total_timesteps | 2174976 | +| train/ | | +| approx_kl | 0.03246145 | +| clip_fraction | 0.482 | +| clip_range | 0.0745 | +| entropy_loss | -3.39 | +| explained_variance | 0.216 | +| learning_rate | 4.95e-05 | +| loss | -0.0304 | +| n_updates | 39592 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000201 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.0598 | +| time/ | | +| fps | 1303 | +| iterations | 1063 | +| time_elapsed | 1669 | +| total_timesteps | 2177024 | +| train/ | | +| approx_kl | 0.034684747 | +| clip_fraction | 0.458 | +| clip_range | 0.0745 | +| entropy_loss | -3.28 | +| explained_variance | 0.375 | +| learning_rate | 4.95e-05 | +| loss | -0.0287 | +| n_updates | 39596 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.00017 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.0725 | +| time/ | | +| fps | 1303 | +| iterations | 1064 | +| time_elapsed | 1671 | +| total_timesteps | 2179072 | +| train/ | | +| approx_kl | 0.02934474 | +| clip_fraction | 0.482 | +| clip_range | 0.0745 | +| entropy_loss | -3.29 | +| explained_variance | 0.417 | +| learning_rate | 4.95e-05 | +| loss | -0.0306 | +| n_updates | 39600 | +| policy_gradient_loss | -0.0176 | +| value_loss | 0.000228 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.0725 | +| time/ | | +| fps | 1303 | +| iterations | 1065 | +| time_elapsed | 1672 | +| total_timesteps | 2181120 | +| train/ | | +| approx_kl | 0.027306175 | +| clip_fraction | 0.441 | +| clip_range | 0.0745 | +| entropy_loss | -3.18 | +| explained_variance | 0.134 | +| learning_rate | 4.95e-05 | +| loss | -0.0317 | +| n_updates | 39604 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000329 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.0725 | +| time/ | | +| fps | 1303 | +| iterations | 1066 | +| time_elapsed | 1674 | +| total_timesteps | 2183168 | +| train/ | | +| approx_kl | 0.035119258 | +| clip_fraction | 0.499 | +| clip_range | 0.0745 | +| entropy_loss | -3.13 | +| explained_variance | 0.312 | +| learning_rate | 4.95e-05 | +| loss | -0.0235 | +| n_updates | 39608 | +| policy_gradient_loss | -0.0166 | +| value_loss | 0.000242 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.0725 | +| time/ | | +| fps | 1303 | +| iterations | 1067 | +| time_elapsed | 1675 | +| total_timesteps | 2185216 | +| train/ | | +| approx_kl | 0.034296945 | +| clip_fraction | 0.464 | +| clip_range | 0.0745 | +| entropy_loss | -3.58 | +| explained_variance | -0.119 | +| learning_rate | 4.95e-05 | +| loss | -0.0316 | +| n_updates | 39612 | +| policy_gradient_loss | -0.0206 | +| value_loss | 0.000293 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.0795 | +| time/ | | +| fps | 1303 | +| iterations | 1068 | +| time_elapsed | 1677 | +| total_timesteps | 2187264 | +| train/ | | +| approx_kl | 0.047942065 | +| clip_fraction | 0.483 | +| clip_range | 0.0745 | +| entropy_loss | -3.29 | +| explained_variance | -0.126 | +| learning_rate | 4.95e-05 | +| loss | -0.0315 | +| n_updates | 39616 | +| policy_gradient_loss | -0.0188 | +| value_loss | 0.000228 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.0795 | +| time/ | | +| fps | 1303 | +| iterations | 1069 | +| time_elapsed | 1678 | +| total_timesteps | 2189312 | +| train/ | | +| approx_kl | 0.02783652 | +| clip_fraction | 0.468 | +| clip_range | 0.0745 | +| entropy_loss | -3.34 | +| explained_variance | 0.0514 | +| learning_rate | 4.95e-05 | +| loss | -0.0334 | +| n_updates | 39620 | +| policy_gradient_loss | -0.0181 | +| value_loss | 0.000327 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.0694 | +| time/ | | +| fps | 1303 | +| iterations | 1070 | +| time_elapsed | 1680 | +| total_timesteps | 2191360 | +| train/ | | +| approx_kl | 0.030401604 | +| clip_fraction | 0.461 | +| clip_range | 0.0745 | +| entropy_loss | -3.55 | +| explained_variance | -0.288 | +| learning_rate | 4.95e-05 | +| loss | -0.0349 | +| n_updates | 39624 | +| policy_gradient_loss | -0.0198 | +| value_loss | 0.000173 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.0665 | +| time/ | | +| fps | 1303 | +| iterations | 1071 | +| time_elapsed | 1682 | +| total_timesteps | 2193408 | +| train/ | | +| approx_kl | 0.031883772 | +| clip_fraction | 0.445 | +| clip_range | 0.0745 | +| entropy_loss | -3.29 | +| explained_variance | 0.285 | +| learning_rate | 4.95e-05 | +| loss | -0.0275 | +| n_updates | 39628 | +| policy_gradient_loss | -0.0156 | +| value_loss | 0.000292 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.067 | +| time/ | | +| fps | 1303 | +| iterations | 1072 | +| time_elapsed | 1683 | +| total_timesteps | 2195456 | +| train/ | | +| approx_kl | 0.03586139 | +| clip_fraction | 0.459 | +| clip_range | 0.0745 | +| entropy_loss | -3.08 | +| explained_variance | 0.508 | +| learning_rate | 4.95e-05 | +| loss | -0.0274 | +| n_updates | 39632 | +| policy_gradient_loss | -0.0162 | +| value_loss | 0.000308 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.067 | +| time/ | | +| fps | 1304 | +| iterations | 1073 | +| time_elapsed | 1685 | +| total_timesteps | 2197504 | +| train/ | | +| approx_kl | 0.036543086 | +| clip_fraction | 0.443 | +| clip_range | 0.0745 | +| entropy_loss | -3.39 | +| explained_variance | 0.136 | +| learning_rate | 4.95e-05 | +| loss | -0.0347 | +| n_updates | 39636 | +| policy_gradient_loss | -0.0178 | +| value_loss | 0.000236 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.067 | +| time/ | | +| fps | 1304 | +| iterations | 1074 | +| time_elapsed | 1686 | +| total_timesteps | 2199552 | +| train/ | | +| approx_kl | 0.031362925 | +| clip_fraction | 0.455 | +| clip_range | 0.0745 | +| entropy_loss | -3.45 | +| explained_variance | 0.083 | +| learning_rate | 4.95e-05 | +| loss | -0.0325 | +| n_updates | 39640 | +| policy_gradient_loss | -0.0189 | +| value_loss | 0.00025 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.3e+03 | +| ep_rew_mean | 0.0743 | +| time/ | | +| fps | 1304 | +| iterations | 1075 | +| time_elapsed | 1688 | +| total_timesteps | 2201600 | +| train/ | | +| approx_kl | 0.03146518 | +| clip_fraction | 0.478 | +| clip_range | 0.0745 | +| entropy_loss | -3.39 | +| explained_variance | 0.126 | +| learning_rate | 4.95e-05 | +| loss | -0.0321 | +| n_updates | 39644 | +| policy_gradient_loss | -0.0177 | +| value_loss | 0.000441 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.0671 | +| time/ | | +| fps | 1304 | +| iterations | 1076 | +| time_elapsed | 1689 | +| total_timesteps | 2203648 | +| train/ | | +| approx_kl | 0.039889738 | +| clip_fraction | 0.432 | +| clip_range | 0.0744 | +| entropy_loss | -3.5 | +| explained_variance | -0.144 | +| learning_rate | 4.95e-05 | +| loss | -0.0243 | +| n_updates | 39648 | +| policy_gradient_loss | -0.0133 | +| value_loss | 0.000795 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.0671 | +| time/ | | +| fps | 1304 | +| iterations | 1077 | +| time_elapsed | 1691 | +| total_timesteps | 2205696 | +| train/ | | +| approx_kl | 0.028646737 | +| clip_fraction | 0.482 | +| clip_range | 0.0744 | +| entropy_loss | -3.44 | +| explained_variance | -0.106 | +| learning_rate | 4.95e-05 | +| loss | -0.0395 | +| n_updates | 39652 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000372 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.0551 | +| time/ | | +| fps | 1304 | +| iterations | 1078 | +| time_elapsed | 1693 | +| total_timesteps | 2207744 | +| train/ | | +| approx_kl | 0.03574335 | +| clip_fraction | 0.461 | +| clip_range | 0.0744 | +| entropy_loss | -3.28 | +| explained_variance | -0.00433 | +| learning_rate | 4.95e-05 | +| loss | -0.0344 | +| n_updates | 39656 | +| policy_gradient_loss | -0.0225 | +| value_loss | 0.000292 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.0609 | +| time/ | | +| fps | 1304 | +| iterations | 1079 | +| time_elapsed | 1694 | +| total_timesteps | 2209792 | +| train/ | | +| approx_kl | 0.031988986 | +| clip_fraction | 0.469 | +| clip_range | 0.0744 | +| entropy_loss | -3.37 | +| explained_variance | -0.0826 | +| learning_rate | 4.95e-05 | +| loss | -0.0325 | +| n_updates | 39660 | +| policy_gradient_loss | -0.0197 | +| value_loss | 0.000495 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.0655 | +| time/ | | +| fps | 1304 | +| iterations | 1080 | +| time_elapsed | 1696 | +| total_timesteps | 2211840 | +| train/ | | +| approx_kl | 0.03774424 | +| clip_fraction | 0.462 | +| clip_range | 0.0744 | +| entropy_loss | -3.43 | +| explained_variance | 0.00858 | +| learning_rate | 4.95e-05 | +| loss | -0.0385 | +| n_updates | 39664 | +| policy_gradient_loss | -0.0213 | +| value_loss | 0.000242 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.0632 | +| time/ | | +| fps | 1304 | +| iterations | 1081 | +| time_elapsed | 1697 | +| total_timesteps | 2213888 | +| train/ | | +| approx_kl | 0.03283853 | +| clip_fraction | 0.447 | +| clip_range | 0.0744 | +| entropy_loss | -3.13 | +| explained_variance | 0.158 | +| learning_rate | 4.95e-05 | +| loss | -0.0297 | +| n_updates | 39668 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000395 | +---------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.29e+03 | +| ep_rew_mean | 0.0603 | +| time/ | | +| fps | 1304 | +| iterations | 1082 | +| time_elapsed | 1699 | +| total_timesteps | 2215936 | +| train/ | | +| approx_kl | 0.03182994 | +| clip_fraction | 0.481 | +| clip_range | 0.0744 | +| entropy_loss | -3.23 | +| explained_variance | -0.1 | +| learning_rate | 4.95e-05 | +| loss | -0.0334 | +| n_updates | 39672 | +| policy_gradient_loss | -0.0186 | +| value_loss | 0.000282 | +---------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.061 | +| time/ | | +| fps | 1304 | +| iterations | 1083 | +| time_elapsed | 1700 | +| total_timesteps | 2217984 | +| train/ | | +| approx_kl | 0.031326666 | +| clip_fraction | 0.459 | +| clip_range | 0.0744 | +| entropy_loss | -3.23 | +| explained_variance | -0.0533 | +| learning_rate | 4.95e-05 | +| loss | -0.0267 | +| n_updates | 39676 | +| policy_gradient_loss | -0.018 | +| value_loss | 0.000273 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.0618 | +| time/ | | +| fps | 1303 | +| iterations | 1084 | +| time_elapsed | 1702 | +| total_timesteps | 2220032 | +| train/ | | +| approx_kl | 0.034540474 | +| clip_fraction | 0.475 | +| clip_range | 0.0744 | +| entropy_loss | -3.29 | +| explained_variance | 0.046 | +| learning_rate | 4.95e-05 | +| loss | -0.0205 | +| n_updates | 39680 | +| policy_gradient_loss | -0.0168 | +| value_loss | 0.000371 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.0618 | +| time/ | | +| fps | 1303 | +| iterations | 1085 | +| time_elapsed | 1704 | +| total_timesteps | 2222080 | +| train/ | | +| approx_kl | 0.037487485 | +| clip_fraction | 0.461 | +| clip_range | 0.0744 | +| entropy_loss | -3.05 | +| explained_variance | 0.0684 | +| learning_rate | 4.95e-05 | +| loss | -0.0326 | +| n_updates | 39684 | +| policy_gradient_loss | -0.0199 | +| value_loss | 0.000343 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.0651 | +| time/ | | +| fps | 1303 | +| iterations | 1086 | +| time_elapsed | 1705 | +| total_timesteps | 2224128 | +| train/ | | +| approx_kl | 0.029964266 | +| clip_fraction | 0.443 | +| clip_range | 0.0744 | +| entropy_loss | -3.4 | +| explained_variance | -0.0838 | +| learning_rate | 4.95e-05 | +| loss | -0.0336 | +| n_updates | 39688 | +| policy_gradient_loss | -0.0201 | +| value_loss | 0.000302 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.0623 | +| time/ | | +| fps | 1303 | +| iterations | 1087 | +| time_elapsed | 1707 | +| total_timesteps | 2226176 | +| train/ | | +| approx_kl | 0.023827888 | +| clip_fraction | 0.446 | +| clip_range | 0.0744 | +| entropy_loss | -3.29 | +| explained_variance | 0.0922 | +| learning_rate | 4.95e-05 | +| loss | -0.0335 | +| n_updates | 39692 | +| policy_gradient_loss | -0.0184 | +| value_loss | 0.000379 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.26e+03 | +| ep_rew_mean | 0.0528 | +| time/ | | +| fps | 1303 | +| iterations | 1088 | +| time_elapsed | 1708 | +| total_timesteps | 2228224 | +| train/ | | +| approx_kl | 0.030410025 | +| clip_fraction | 0.474 | +| clip_range | 0.0744 | +| entropy_loss | -3.52 | +| explained_variance | 0.0576 | +| learning_rate | 4.95e-05 | +| loss | -0.035 | +| n_updates | 39696 | +| policy_gradient_loss | -0.0194 | +| value_loss | 0.000339 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.0571 | +| time/ | | +| fps | 1303 | +| iterations | 1089 | +| time_elapsed | 1710 | +| total_timesteps | 2230272 | +| train/ | | +| approx_kl | 0.030507576 | +| clip_fraction | 0.456 | +| clip_range | 0.0744 | +| entropy_loss | -3.44 | +| explained_variance | 0.229 | +| learning_rate | 4.95e-05 | +| loss | -0.0248 | +| n_updates | 39700 | +| policy_gradient_loss | -0.0159 | +| value_loss | 0.000348 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.27e+03 | +| ep_rew_mean | 0.0614 | +| time/ | | +| fps | 1303 | +| iterations | 1090 | +| time_elapsed | 1712 | +| total_timesteps | 2232320 | +| train/ | | +| approx_kl | 0.031047314 | +| clip_fraction | 0.448 | +| clip_range | 0.0744 | +| entropy_loss | -3.08 | +| explained_variance | 0.29 | +| learning_rate | 4.95e-05 | +| loss | -0.0266 | +| n_updates | 39704 | +| policy_gradient_loss | -0.0183 | +| value_loss | 0.000289 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.0484 | +| time/ | | +| fps | 1303 | +| iterations | 1091 | +| time_elapsed | 1713 | +| total_timesteps | 2234368 | +| train/ | | +| approx_kl | 0.032301962 | +| clip_fraction | 0.459 | +| clip_range | 0.0744 | +| entropy_loss | -3.3 | +| explained_variance | 0.0565 | +| learning_rate | 4.95e-05 | +| loss | -0.0365 | +| n_updates | 39708 | +| policy_gradient_loss | -0.0215 | +| value_loss | 0.000295 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.0466 | +| time/ | | +| fps | 1303 | +| iterations | 1092 | +| time_elapsed | 1715 | +| total_timesteps | 2236416 | +| train/ | | +| approx_kl | 0.037823483 | +| clip_fraction | 0.457 | +| clip_range | 0.0744 | +| entropy_loss | -3.28 | +| explained_variance | 0.206 | +| learning_rate | 4.95e-05 | +| loss | -0.0358 | +| n_updates | 39712 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000243 | +----------------------------------------- +----------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.0454 | +| time/ | | +| fps | 1303 | +| iterations | 1093 | +| time_elapsed | 1716 | +| total_timesteps | 2238464 | +| train/ | | +| approx_kl | 0.032309357 | +| clip_fraction | 0.457 | +| clip_range | 0.0744 | +| entropy_loss | -3.34 | +| explained_variance | 0.279 | +| learning_rate | 4.95e-05 | +| loss | -0.0346 | +| n_updates | 39716 | +| policy_gradient_loss | -0.0192 | +| value_loss | 0.000217 | +----------------------------------------- +---------------------------------------- +| rollout/ | | +| ep_len_mean | 1.28e+03 | +| ep_rew_mean | 0.0395 | +| time/ | | +| fps | 1303 | +| iterations | 1094 | +| time_elapsed | 1718 | +| total_timesteps | 2240512 | +| train/ | | +| approx_kl | 0.03639219 | +| clip_fraction | 0.477 | +| clip_range | 0.0744 | +| entropy_loss | -3.23 | +| explained_variance | 0.176 | +| learning_rate | 4.95e-05 | +| loss | -0.0298 | +| n_updates | 39720 | +| policy_gradient_loss | -0.0174 | +| value_loss | 0.000275 | +---------------------------------------- diff --git a/006_rgb_stack_ram_based_reward_time_reward_final_round/tune_ppo.py b/006_rgb_stack_ram_based_reward_time_reward_final_round/tune_ppo.py new file mode 100644 index 0000000..f2d3184 --- /dev/null +++ b/006_rgb_stack_ram_based_reward_time_reward_final_round/tune_ppo.py @@ -0,0 +1,68 @@ +import os + +import retro +import optuna +from stable_baselines3 import PPO +from stable_baselines3.common.monitor import Monitor +from stable_baselines3.common.evaluation import evaluate_policy + +from street_fighter_custom_wrapper import StreetFighterCustomWrapper + +LOG_DIR = 'logs/' +OPT_DIR = 'optuna/' +os.makedirs(LOG_DIR, exist_ok=True) +os.makedirs(OPT_DIR, exist_ok=True) + +def optimize_ppo(trial): + return { + 'n_steps':trial.suggest_int('n_steps', 512, 2048, log=True), + 'gamma':trial.suggest_float('gamma', 0.9, 0.9999), + 'learning_rate':trial.suggest_float('learning_rate', 5e-5, 5e-4, log=True), + 'gae_lambda':trial.suggest_float('gae_lambda', 0.8, 0.9999) + } + +def make_env(game, state): + def _init(): + env = retro.make( + game=game, + state=state, + use_restricted_actions=retro.Actions.FILTERED, + obs_type=retro.Observations.IMAGE + ) + env = StreetFighterCustomWrapper(env) + return env + return _init + +def optimize_agent(trial): + game = "StreetFighterIISpecialChampionEdition-Genesis" + state = "Champion.Level1.ChunLiVsGuile"#"ChampionX.Level1.ChunLiVsKen" + + try: + model_params = optimize_ppo(trial) + + # Create environment + env = make_env(game, state)() + env = Monitor(env, LOG_DIR) + + # Create algo + model = PPO('CnnPolicy', env, verbose=1, **model_params) + model.learn(total_timesteps=500000) + + # Evaluate model + mean_reward, _ = evaluate_policy(model, env, n_eval_episodes=30, deterministic=False) + env.close() + + SAVE_PATH = os.path.join(OPT_DIR, 'trial_{}_best_model'.format(trial.number)) + model.save(SAVE_PATH) + + return mean_reward + + except Exception as e: + return -1 + +# Creating the experiment +study = optuna.create_study(direction='maximize') +study.optimize(optimize_agent, n_trials=10, n_jobs=1) + +print(study.best_params) +print(study.best_trial) diff --git a/data.json b/data.json new file mode 100644 index 0000000..e9bf9a7 --- /dev/null +++ b/data.json @@ -0,0 +1,60 @@ +{ + "info": { + "enemy_character": { + "address": 16745563, + "type": "|u1" + }, + "agent_hp": { + "address": 16744514, + "type": ">i2" + }, + "agent_x": { + "address": 16744454, + "type": ">u2" + }, + "agent_y": { + "address": 16744458, + "type": ">u2" + }, + "enemy_hp": { + "address": 16745154, + "type": ">i2" + }, + "enemy_x": { + "address": 16745094, + "type": ">u2" + }, + "enemy_y": { + "address": 16745098, + "type": ">u2" + }, + "score": { + "address": 16744936, + "type": ">d4" + }, + "agent_victories": { + "address": 16744922, + "type": "|u1" + }, + "enemy_victories": { + "address": 16745559, + "type": ">u4" + }, + "round_countdown": { + "address": 16750378, + "type": ">u2" + }, + "reset_countdown": { + "address": 16744917, + "type": "|u1" + }, + "agent_status": { + "address": 16744450, + "type": ">u2" + }, + "enemy_status": { + "address": 16745090, + "type": ">u2" + } + } +} \ No newline at end of file